08/30/2021 13:13:56 - INFO - __main__ - Distributed environment: MULTI_GPU Backend: nccl Num processes: 16 Process index: 0 Local process index: 0 Device: cuda:0 Use FP16 precision: True 08/30/2021 13:13:57 - WARNING - huggingface_hub.repository - /home/leandro/codeparrot-small/./ is already a clone of https://huggingface.co/transformersbook/codeparrot-small. Make sure you pull the latest changes with `repo.git_pull()`. 08/30/2021 13:14:00 - WARNING - huggingface_hub.repository - Revision `zesty-violet-116` does not exist. Created and checked out branch `zesty-violet-116`. 08/30/2021 13:14:00 - WARNING - huggingface_hub.repository - M codeparrot_training.py M requirements.txt 08/30/2021 13:14:02 - INFO - datasets.load - Some files matched the pattern '*' at /home/leandro/codeparrot-train but don't have valid data file extensions: [PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/11/70/1170a8200f43dfa3902e9d41088229febdf4d7044d9d762dd5809685e5448b11'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/fa/f2/faf2e65a89fda5ec7a00a36b9fd6c4b2429f1249072b838f2a02d5d01fcaeb18'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b1/70/b1705347d88e73a7de652d1486a3eccda92e420e65a58917c88af635baf55ac8'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/17/89/178953ae530dc7960c803bd22a37026f4190b822b95145240537840bfc5a1ad1'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/37/9d/379db3f5d257369fd927b7395599ec2aef5cefcb57811a57281487da9fd58c5b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8b/d9/8bd964dad421ed624f4bd5e4719e3e28f62d002b350d850e902688c9e9bcfd80'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1b/c7/1bc7cd472751ec9917bf55ce8b05b8ea467453335103f16c4551e94daefdbaf0'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1f/46/1f46dcfefd87339930fa912ec98a56b7b93c2f052d7f452f82c9c3d0043ffa43'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f9/91/f9915d283d95c3316a76922f129897823efd397287916e8f7af88ed7aaf517b0'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4c/10/4c10f31fa342f81c13b27e7ae0761b17729ee82f6e02824361e2cfcc4ab096c1'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/c0/0f/c00f0550d90e881145954ad24df7fdf512ffc3d63c50d2aa0c85774757d8f37d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/c3/d3/c3d3e55004ff21e36332b9612e385ba07c2610b832b4a94cca2d9fda372a9fb4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a2/17/a21791d67c018e486dde68b8956a16b8fa0c54af93dc3c6ec2c669da87861b02'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/9c/75/9c7526f2ec341f2d2483d9db25b2b2e9fe630b21b737fa7ebbc19965c6ee46b1'), PosixPath('/home/leandro/codeparrot-train/.git/logs/refs/heads/main'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/01/87/0187e92041e5ef1abe3190a48330ff50c7d5fc5ed1219c3bcbb465907430d34e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/37/f2/37f2a405d0e8c52b4a51f79b23f135bcb537eb3f61fe8a27a29ab63b74a37671'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/82/4c/824c9524070c36ed317c12b9b0e77f8b9460e8519ba32c6795a5a2e7232d088c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/18/44181da41968eab59b99558c2afd4d6f95397bc2b580622a96f2f9fb74f545b2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/5b/66/5b66654660bc52d66f5bf0e6a62e0b65a0dd2499ec316daed0432efb2c7a8d7b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/47/d1/47d1fedd443c4edfca241c00be8984a2157c668726cc06d92ad7e2704cb5c951'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/9c/83/9c83dabc6a7c8a9629093125ff70fc60f594b0b95cb56f2f12d2bd91352367c7'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/08/4a/084a245793d30784f6ae4f8b666624293bdab2d05a5e1eeadf20b7d9db444951'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/45/da/45da5a5e4acd37b6e288eb4045434fb6b4a8d77979ac61c8306ca9eca6d24128'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/10/4410ab4420ffe54105620e1f038b0f6b14afa88a8df9dcf63468f6a2c105d770'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/b9/14b9124b7b2ffa27d79dc210ae77b9b970e067ad7d3dc4d3eebc08671b770c16'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ca/00/ca00ed91ba94519faaba619e5eec6498215695acc6b3f760dc056967cefeea80'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f8/3b/f83b75420e369ae1d55e7009effe9f7a05577a31c19a8c02ce7f0b56b5dc8a87'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ba/5a/ba5ad5064f9ef5d1429abd4c4742cf37b56589c060ff3995e5331eb69fb9c1c5'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0a/03/0a03d68d6dda083d189878113e864c580b9b5572e53d3e1684b93a9996c7699d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/54/10/5410ae89d1cf3ea5325b7e948fd4db3d352e44bbd2a6a5c813f77be0da958c80'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a9/73/a973fc07ce8ae881a878bf92c6c70583c08ea6bdb2ca2583002271f96dab9543'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2b/85/2b85d040d424bde044014147be3c4949a8d2b0e558c4f4c2c65aead5ece2cde9'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e6/f0/e6f0840fa125b6ad771b853937bd215b369bfb815ff521316cf6cb46fba66968'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/23/ee/23eed9f8512ca62c4b9b4fb28a84688ee550b75ec7658209f3cd5d82a2d4aa57'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a0/53/a05359f8e5ca97304272052f806034ebdca89a94f0d052b719b8b81dd8ddd868'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/21/e1/21e166aee17c30af55849b552e2eaa9c0641dc6cb0ac6386bd3f7797d8af2a9b'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-applypatch.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/70/b0/70b01a02ca2810cf2e74a43655979028b31de42c566bc65d8b749720d1b08fb2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/21/be/21be1bf5e86f5da2dbd83f0bb904a3d68d9abea09bbd5adab6a6873c53ed0112'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7d/04/7d049e95fe5200dc13c1451523e00fd08d37ffde2a863aa025f030f00d3d747b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/41/11/4111a00cda1b0988507f8b544a9e4da7bfb0bff35c13990c6fb1c360aa6a6688'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b9/d1/b9d1c713e023c821f98968ea670a01aa7127c1c915f3d7f6368616f17369e8f2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d5/98/d59884b54759159fcaf45b671dfe9ee2a7d7aea34f1cc7762a1c25499589efb9'), PosixPath('/home/leandro/codeparrot-train/.git/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8e/81/8e81a5187b909a82581e8030a8008ffb9517519e477797b195bbcf422ef6e20c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1e/89/1e890b33c7f95f900932797f1ba2b15f1f1780926f744ea04e0a969bf270df1a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6b/f5/6bf5fd370b20157e47d88709fb5c8b572f1b682a1fdb80091900bfda70a36491'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/58/1458ee6ad39f24b25d2db9153ba9aa25f4ff2f16c2f624361a0186904a658a54'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-commit.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6b/ce/6bce0dd945b67accdd3077504bc286a26bdb4b03fbbf34d427c21582f3374994'), PosixPath('/home/leandro/codeparrot-train/.git/index'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d0/20/d02098784b5ee7b5d5206ee9cc52e881782d98fc90530322af1c5cb7d401f1fd'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7d/d3/7dd37fe8445ee2641f14179d5a2aa636780822347d880a401d41c90bfd5cfd68'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6f/bc/6fbcee1936749498486745c2dd217ee108f1a243f054dcb2591cfee772906fae'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7f/8d/7f8dc2a2357a3d91ecc5fa5f125c73181dfbe22524d853f672010513044c80f7'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/69/ef/69efdcdb035636e6a8cd18cfc4ef702f95730a381b5d86b36c10028b4df94090'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-push'), PosixPath('/home/leandro/codeparrot-train/.git/objects/pack/pack-67102b35e20edaa7f1ed9c266f37841cd38f158a.pack'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/26/99/2699022bd98f8d49f5505ab457b15dd31156713279335d0c28db1c99edc36894'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-update.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/db/d4/dbd4ddc668c0c838eecd756db64c9a3c2127d8e9bbc05b3fcba00b075854b24c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/fa/40/fa40f7fe8b2d031a32282dce9a40462d67eecff28203c1743fcace8ef4bb37e6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/bd/9b/bd9be9097633349b5ecd400375be5d511e812feadf983f3c2cbcba263a3a14ab'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/97/af/97af2a98400865661b26c3d5c0a3b6be51603452f459136bc9ab2568667ed199'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b4/2c/b42c05288d42233fb829266917ae1145a835f3ccf8e00ea21e5927f9528fb500'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6a/34/6a34d6e3ac6572933b2f66c74af568a0df3b91b94622dd4b7e5d5538c04071ff'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/05/9b/059bc5381874a28e5a467291be6ee44e3f667609290d74e5ed009be10329bdbb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/28/29/28290f1947521e2d6c58ee18d83b864b5d95e1fad3b54ee817799991642488ec'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8a/ae/8aae623a251bd31627554141be2150a5ffb8ddea900ae244fd8492cc03245b36'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/3d/35/3d354291d12d6be3833eda95bd0db307dcd26b5b4287a3f6ca33b3b51b2e46f2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/13/ae/13ae38510e10076edaa24cf051e6403a270c95febd0e2e9b9e052128d632fe36'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/85/28/8528503b464d6cbf8041e0a1481681d0bff4bb24f9d18230fe56c3bc99dfa2ab'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-commit'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ba/38/ba38a25c6b8dd335baf2c6cd925ca5b91668af93f7ecee2b120ad352f46a6565'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/77/13/77131f000b7ab27e1336a181a4e4188f31ed40cea3fdf98b6398b5bbddaa5c76'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/93/51/935137f4370f4f5c85ba6a157825fe6102edb991a46610fa9939e2960be9653d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/78/bb/78bbf19a9e7a29b17fa71e3d05842b9469e3187e938efd8c793ceadbdd38c709'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/55/cb/55cb3e32311273135568ef3da7960400d95f63dad586ccfe56996561277b483f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a7/9a/a79a92653692037bf2fd6de92d93429455cd31dc7f96513adb40277d11be891d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/96/84/9684f7bb635a937d6899902ad758fd565826bfe5b8ea42c296d791dd7089b0f9'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1c/5f/1c5f7b819a67cfca7be02b743fbf0dabf7d53a1c7ddf82e70e094d92973d95c7'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0b/de/0bde10d6ad4055811339a7ed51fca332317529d6b5854a4b7ce90000e352aa33'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/5c/d6/5cd6e14ff3ac522a3a7bac22ef6ec299833c685a9c343d347fe21152e4173856'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ff/bc/ffbc64d8a248deb916c3ef209d2a18fc5de5c56a2cfa546a633cbfec31e6ccb2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/81/7c/817cc36de53f7c914d82e2536a5538c21330ef54662366733e45c76a3c770d06'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/3a/fc/3afc8a938123d0f8e566043d271b4c6a60e3df968b72d8939982a09527763aae'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/95/2e/952eaf2d8448261925753def51d58ff5af595d6469207db42abc0b17204640fb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1d/b3/1db3132794e05cd2decef99af5f56073af4b4a27c33e3a0d0b4289e61b34c9dc'), PosixPath('/home/leandro/codeparrot-train/.git/info/exclude'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/b6/44b6239e61c700810037d9d8aa2fe706d7eaeb5766e492fad95411ad184490f5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/60/07/6007f21e5625708f4710d48386db1297bb1dbd26196ced77b305e7e35da0300d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2d/15/2d15883c4954ffcaafce389f10ccbad7c93e66fae3b7ca7db0a50343180cedf4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2e/b3/2eb3b4ea8f84ef14a84b43002a148d99df05f68c1cfc0c0f074572bda0e0e1ee'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/da/b9/dab942e6da72846fc60682ce21a8e8fa6bf3452a29abff69ec0750e058ab3b92'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/79/c1/79c13ad14568c659397387f3d0e1358393fb0041ff48ce9c98ad4f28df8cde4b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/22/c4/22c47cc7619654f7faafe250a2dd0cabae5520263e967245b8d5638215244239'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/94/e0/94e011d7b77e55164bb15d95c453fa1282d78e234ff378adb930d756bbd33f64'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b9/07/b907e571662c19245abd148afb306b5c6e411d24a5117e0bb4c182a56afb9b97'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/9d/a6/9da6dd8c62377fcfe1e95882a17aa711a8fcc38e02cf21cc1a678f22a9e50d39'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/03/bb/03bb832cf6fad7e4bc885cc1d9502cf312d2951a51afbd63fb6a90f53e49d096'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4a/54/4a54ecd83d3083585ddc7beb921140b2b2e5b4fb82dec9543ac0932c6136e84b'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-checkout'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/02/dd/02ddc3cc1a121d8e237578028f34a994a7548f0d086a1312133c3864dbff6b37'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/46/df/46df1517cd973f00262b495f82b10c46ec077a33bcfc83bade078a36590c6d0a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/04/64/04647e38d2a928e08abccf777e680adf7cb0066862374bd847c492de44cb047f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/43/98/439848f817f432ceefdf7e69a64b60dd99a75cc6fb26599a0ea5ac1167c3db4c'), PosixPath('/home/leandro/codeparrot-train/.git/objects/pack/pack-67102b35e20edaa7f1ed9c266f37841cd38f158a.idx'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7c/bf/7cbfb385a3bbebdb3eed3e154c80f0c9bf6b397aa702e5410339c2b1d74ae867'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/bd/9a/bd9af7b8106e0a773e5a12495aa88339995c2084c2f9a243733879eb73f595d8'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/63/77/6377867a616a0b6e8e3e3691c5cce9cd566773ec5bbd02f5a457edac8a0f24d4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/64/35/643576ec614d0ba328db99ae865b8f1321ec4f288164f76fd6746b3b83e34f19'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d7/c8/d7c88386b6a3c339c8a6d0beead12bf440477473df676886099ca289057fbace'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0d/07/0d07213fb514be71d57406af05dafff0edd3c7506621df761c9453ff598d89c9'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/fc/eb/fcebafda8e3681732437c98581a30faedf7802c6b90c84394d2c42b792c32507'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/applypatch-msg.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/83/14830fec70eb2227647b241d9ff90addbc461cbdcddfe12e015028cefaba6f4e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ef/8b/ef8b57ab3924e70df4f4a37b6853205113144fa01ea6c0140bea3a21b14eafeb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/98/de/98de114cefba6caad86991425c276e59a5ab4a3a1006d29f73ec5cede6233efd'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/87/fb/87fb4ab74dad4c0f520d49769333d5d1b010fcb9e8f30c8dab16430a5a0af9d2'), PosixPath('/home/leandro/codeparrot-train/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ed/ae/edae53c081ce347a58430f0930ce4fb318a9f62e15f85aa638a86c1666f70df4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/49/d8/49d89abc121b49ef8a540796b63edd68f67f679d6ad1b969d6637d852d59f79f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/87/f9/87f9d6d6889eb78e70ba55d2f959fa4e896bd3a78d02dd347792e30ddd730bf6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/bd/a8/bda8ae48acb883ddb225719c3584e3baa76887afb7198d76478af06e7f80572e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/08/26/0826780cd0e3d564882321e246176eac0fb695b706bc72c6022925075047a62e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4f/df/4fdfd51962dfc725568d88de53b29e285d52e858e849acb543101fe556779a42'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/4f/144f1231964ab251596b40abdd80f37fe7ce4ac7b2b31fc517b942cc24110341'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6b/3d/6b3d8a7164286112196af65658426d2faeda5c50fc381bdebf378f0226342d4e'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/update.sample'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-rebase.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/da/6e/da6e9d2f263cf7b0254b4c0a57483ed8ac9652d6f67a63d648e9d968c576d526'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6d/c7/6dc73c3794ad5c29870563658a7003cb2a6cfb0c1852c47037a6eda6cc3cf3a1'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/25/84/2584f186110af7310075f15e07ddadb9c50c26cafd4c66b2e2baaab040028c3b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4c/35/4c35db8d1672615cddac65cdf0a76ea9ca1ec9d1d8b18ce293be0df23ff694db'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a9/df/a9dfb7586f9a1bfaaa7175a2384e101f51513b0b98ce01eeaafe5a783cdbad96'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/3a/b5/3ab5c68d9424b10ca45197172baa495813eae7efa9b3914ea4e4afd0201995b5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4f/2c/4f2cb5d9fe3ef94da4aa3ec743d37b83c2347d6f1d3d4696a5c667ff9968ea38'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7f/4f/7f4fb07272574ef183fd21a911f45f989a941516a11fe1d71335954a54657e07'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/39/32/39325e24ddd711eacc61305d421e004de68e6f6d0b649ca695ad53d4dc53b47f'), PosixPath('/home/leandro/codeparrot-train/.git/logs/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ee/25/ee25b95231437c8795fca58f4a4d95b2698995f29e7f264956f78670f37ea982'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/5f/34/5f342fc03b8d9c90aa9ff917ca3ff3edce748b6f0b55f61aadc9940ca53b45d5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b3/84/b3849196f2777c6e3fb662ae301ae63561db9aaff9bd2ac2f32ad02e9d26d399'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f1/a5/f1a543df8fe1562a57657011c09d45778915a202f279013041e4f08d6cb1b475'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1d/a5/1da55a92827ad63ee4eb1f5eabf14500459bf357c28b767756b80342024063d4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a2/af/a2af1215060dc01f13d389abee1fc25ff94ed84262c54dea264810a5bcc074fc'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ba/86/ba86bfbe83793efcb2e89df75179188dee67b96ace3e7f1628c133ce11fc361e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a0/cc/a0ccfd373c5bb31028d4b7abb80a9a328395361cc2ac4f7376f5b1f6e89d89d0'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-push.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/79/447953386aab39785c0f6c5e44b7310d433886fb73a1e40efe67c9620639e6fa'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2b/ac/2bac46edf98c75901284aff8296f80fea6701821000b205bd85aef8399124074'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e9/95/e995f5605e676fd577e4c78ee6bf43451324ddbcb04e841cf1dfce07c69dc1b6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2a/6b/2a6b5f923b286f640ad586bc295e653ec0db8e4c8487db1c25fa384e216b6ce5'), PosixPath('/home/leandro/codeparrot-train/.git/refs/heads/main'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/12/a7/12a785cd978d3ec0330adae618ad3103dd53f63c7c11b96a7a0d33254407aaa4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/50/83/5083522f9ebdb4c72e4e384dfd9bce8293d84dcdf0a7580cab1ce8e44f2880da'), PosixPath('/home/leandro/codeparrot-train/.git/config'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/33/27/3327f7692a61d984758a71929f4466af87f91a2db0a656321df0d331ef4def20'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4c/b0/4cb0db5e545856bfeb62f7fa15d3472b705ac8fdeb8c4a831727b730951f8902'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/77/63/7763fa2cb60958f8d28fc6bebc0105ed3614addd32296fe929b7262e4d62f58a'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/commit-msg.sample'), PosixPath('/home/leandro/codeparrot-train/.git/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1c/6f/1c6ff13e754a4260b097390066ecc973302f45756b4151bbfb7efbb7b1ac9963'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/17/ba/17ba31d8c126b19d7dc4899e46ec476e059462beaf2364bf77471b2f920ddf37'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d5/74/d574d02117a4209d073c3d382e859fdf07d6e18ac38bed8a4d900c8c9975550c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/c0/8a/c08ad7d3c85ef3631747172211b65c70912bae157b55f922f1f70016bf7f64e6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/70/35/70353ba511fe03b0f820a7ef6156771de34ef20a404a1cc2c064033998de0f9f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/cf/84/cf84f4c64b1173bb12e281b88ca920c4c6d130c54214b5172bccbcc045fb2d0f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/69/63/6963f0671c853a7bb7ae245df7c1f07fd8db821e59e1ab83b74d07909e029111'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b7/d8/b7d84fc6c01ec6eb79187a7e252a3f033bfd1f2ba297d569e1bf507af9b50fa6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/32/d9/32d95bf48e9ba4ed480df0015326b0ed07647ce17e84a48a5a445db22bc5de4a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/15/95/159531500b1c473455d10fda2fb82f6ea7814500799e27eaf5f2be6f124f994c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8f/8a/8f8a74c1e1fc4ee43110f74ae0cc01de863a0ceb3f2c4815cab1dc1efeb5339a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4f/5b/4f5b4ba86fe51a134d866d06e472bd6c6f9d1f122cb905c65cb7c0a35bf51acd'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/17/da/17dac3999cf0cb027901ecb382180aa9560b4bb2c5b839f3afc8cadc229962bf'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/de/af/deaf9432f8e1fdc2bd3b9078dc3996c536e661ebb379b81818ecfc70a360c923'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d0/e5/d0e599bab79fe0054313a92ab57e7a89c65c2fc45011168aa73c0fe000c4f689'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e0/49/e049a0f4444d560849ab8c2d893157b975d183f839984001f101046ca74b7978'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f8/46/f84677f7389798b5c74ff00760d08732db022e99f60dc77e5bb4d900aa80dc60'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0f/70/0f704aab387aa4e2f0f4dd866d5f0888b25d0d0b61ef7881c38b918f22802ec2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b5/3e/b53e982e883c26c1a21db49bff0a27d8d628f4fc498715739936fa93bfb5353e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e3/62/e3627cc99f31126c54a8a4188ce59123e876c812bdbdc5cba35d2f76e369a385'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-merge'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/25/16/25162ca0d0fa0474f367ba4720b75f0cb10c70b3f62dd90cbb6e201773c99cb3'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e1/7a/e17a32eafebfa6f8d8b0edf6c0463c639f06a72fadae7907c9fd026f01136b98'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/00/33/0033a83827749523a25d0ef661ef307b27edc162ce38c44e25fd033e9a187c76'), PosixPath('/home/leandro/codeparrot-train/.git/description'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2d/31/2d3127f22a64cf04b4ab8fd23512d5b7d6373429e36ffd68b3f86d0dff4e2fdb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/55/db/55dbc21eb4360618b60fc5eaa4ce705ea71bb1e8241237099cfe43c59ed5b2ed'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b8/ac/b8acca45caffd1db94c790f13ed8f1742b71d4f9cd3d242417e87bb150b6af20'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d6/ec/d6ecd24bfd9e0c2877dfa00417568e07d9f64a150c5518d471ff91ded60bf146'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/02/a0/02a07bbab0f2b514c1a9d5296ca8c1a843aca846fcde56fc810700ee416db1b4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/96/f9/96f9e109fe3ebce8c82610b0af4398170d678185b18ce5bc0384d84eb421ace5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/eb/34/eb344442f4771eb011e0e520b8b1666903717e5e8c59a5462fe80aa82401940a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/26/142694003d3fc3bc57e51dab9eaf07472e0f24a4b092d70159943ecc8c2496a4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2a/ff/2aff254f1288353b713d8e718915f8a2eba7d65097ed5f5d0df520a7058ddf71'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-receive.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2c/a7/2ca7213ba4af470b5f4caa0b4439992b7483c8b4d1cb977089f9b9abef1c7fba'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/80/61/8061f4f61c3955c90dab77a1553ac22e9d1ff604c229375be54a38e32ce6f8ca'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f3/5e/f35ec6ce622145756740be75b1fa969996e7e716ac0a15d9bbc4e86aed616000'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a7/6e/a76e8e4bbc39a74e4ff59e02aaf1404a8bc429f1033a216058b09f7e0ee3cd0c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/07/b9/07b951a7cc55afc0d48a47f0dbd9e06c7311279e4a747256b5dcfe11ba56690d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1c/2e/1c2e85e92de0f8a29ed6e534983e0051fa2c79e31013c11c7cc66f3f3f1e0155'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/09/c2/09c237a78f8a49d7840d8e5fc58e79db7e225b9904323f46791dce8fd0585332'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f0/f9/f0f92a74ef6e03d0c05ae2012d7e33242c3b091f3e01d2d8f942e68cf295f7a4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/eb/a4/eba49c7ea511320fd7040022951873a465016ddb72d078b958a4003c396ffb52'), PosixPath('/home/leandro/codeparrot-train/.git/packed-refs'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/62/03/6203a1aae8671a6a23849de3aa6aa3efec0e3fbe3275757643abfd63a9ee9af8')] 08/30/2021 13:14:02 - INFO - datasets.load - Some files matched the pattern '*' at /home/leandro/codeparrot-train but don't have valid data file extensions: [PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/11/70/1170a8200f43dfa3902e9d41088229febdf4d7044d9d762dd5809685e5448b11'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/fa/f2/faf2e65a89fda5ec7a00a36b9fd6c4b2429f1249072b838f2a02d5d01fcaeb18'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b1/70/b1705347d88e73a7de652d1486a3eccda92e420e65a58917c88af635baf55ac8'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/17/89/178953ae530dc7960c803bd22a37026f4190b822b95145240537840bfc5a1ad1'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/37/9d/379db3f5d257369fd927b7395599ec2aef5cefcb57811a57281487da9fd58c5b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8b/d9/8bd964dad421ed624f4bd5e4719e3e28f62d002b350d850e902688c9e9bcfd80'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1b/c7/1bc7cd472751ec9917bf55ce8b05b8ea467453335103f16c4551e94daefdbaf0'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1f/46/1f46dcfefd87339930fa912ec98a56b7b93c2f052d7f452f82c9c3d0043ffa43'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f9/91/f9915d283d95c3316a76922f129897823efd397287916e8f7af88ed7aaf517b0'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4c/10/4c10f31fa342f81c13b27e7ae0761b17729ee82f6e02824361e2cfcc4ab096c1'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/c0/0f/c00f0550d90e881145954ad24df7fdf512ffc3d63c50d2aa0c85774757d8f37d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/c3/d3/c3d3e55004ff21e36332b9612e385ba07c2610b832b4a94cca2d9fda372a9fb4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a2/17/a21791d67c018e486dde68b8956a16b8fa0c54af93dc3c6ec2c669da87861b02'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/9c/75/9c7526f2ec341f2d2483d9db25b2b2e9fe630b21b737fa7ebbc19965c6ee46b1'), PosixPath('/home/leandro/codeparrot-train/.git/logs/refs/heads/main'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/01/87/0187e92041e5ef1abe3190a48330ff50c7d5fc5ed1219c3bcbb465907430d34e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/37/f2/37f2a405d0e8c52b4a51f79b23f135bcb537eb3f61fe8a27a29ab63b74a37671'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/82/4c/824c9524070c36ed317c12b9b0e77f8b9460e8519ba32c6795a5a2e7232d088c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/18/44181da41968eab59b99558c2afd4d6f95397bc2b580622a96f2f9fb74f545b2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/5b/66/5b66654660bc52d66f5bf0e6a62e0b65a0dd2499ec316daed0432efb2c7a8d7b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/47/d1/47d1fedd443c4edfca241c00be8984a2157c668726cc06d92ad7e2704cb5c951'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/9c/83/9c83dabc6a7c8a9629093125ff70fc60f594b0b95cb56f2f12d2bd91352367c7'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/08/4a/084a245793d30784f6ae4f8b666624293bdab2d05a5e1eeadf20b7d9db444951'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/45/da/45da5a5e4acd37b6e288eb4045434fb6b4a8d77979ac61c8306ca9eca6d24128'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/10/4410ab4420ffe54105620e1f038b0f6b14afa88a8df9dcf63468f6a2c105d770'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/b9/14b9124b7b2ffa27d79dc210ae77b9b970e067ad7d3dc4d3eebc08671b770c16'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ca/00/ca00ed91ba94519faaba619e5eec6498215695acc6b3f760dc056967cefeea80'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f8/3b/f83b75420e369ae1d55e7009effe9f7a05577a31c19a8c02ce7f0b56b5dc8a87'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ba/5a/ba5ad5064f9ef5d1429abd4c4742cf37b56589c060ff3995e5331eb69fb9c1c5'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0a/03/0a03d68d6dda083d189878113e864c580b9b5572e53d3e1684b93a9996c7699d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/54/10/5410ae89d1cf3ea5325b7e948fd4db3d352e44bbd2a6a5c813f77be0da958c80'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a9/73/a973fc07ce8ae881a878bf92c6c70583c08ea6bdb2ca2583002271f96dab9543'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2b/85/2b85d040d424bde044014147be3c4949a8d2b0e558c4f4c2c65aead5ece2cde9'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e6/f0/e6f0840fa125b6ad771b853937bd215b369bfb815ff521316cf6cb46fba66968'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/23/ee/23eed9f8512ca62c4b9b4fb28a84688ee550b75ec7658209f3cd5d82a2d4aa57'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a0/53/a05359f8e5ca97304272052f806034ebdca89a94f0d052b719b8b81dd8ddd868'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/21/e1/21e166aee17c30af55849b552e2eaa9c0641dc6cb0ac6386bd3f7797d8af2a9b'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-applypatch.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/70/b0/70b01a02ca2810cf2e74a43655979028b31de42c566bc65d8b749720d1b08fb2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/21/be/21be1bf5e86f5da2dbd83f0bb904a3d68d9abea09bbd5adab6a6873c53ed0112'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7d/04/7d049e95fe5200dc13c1451523e00fd08d37ffde2a863aa025f030f00d3d747b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/41/11/4111a00cda1b0988507f8b544a9e4da7bfb0bff35c13990c6fb1c360aa6a6688'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b9/d1/b9d1c713e023c821f98968ea670a01aa7127c1c915f3d7f6368616f17369e8f2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d5/98/d59884b54759159fcaf45b671dfe9ee2a7d7aea34f1cc7762a1c25499589efb9'), PosixPath('/home/leandro/codeparrot-train/.git/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8e/81/8e81a5187b909a82581e8030a8008ffb9517519e477797b195bbcf422ef6e20c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1e/89/1e890b33c7f95f900932797f1ba2b15f1f1780926f744ea04e0a969bf270df1a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6b/f5/6bf5fd370b20157e47d88709fb5c8b572f1b682a1fdb80091900bfda70a36491'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/58/1458ee6ad39f24b25d2db9153ba9aa25f4ff2f16c2f624361a0186904a658a54'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-commit.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6b/ce/6bce0dd945b67accdd3077504bc286a26bdb4b03fbbf34d427c21582f3374994'), PosixPath('/home/leandro/codeparrot-train/.git/index'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d0/20/d02098784b5ee7b5d5206ee9cc52e881782d98fc90530322af1c5cb7d401f1fd'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7d/d3/7dd37fe8445ee2641f14179d5a2aa636780822347d880a401d41c90bfd5cfd68'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6f/bc/6fbcee1936749498486745c2dd217ee108f1a243f054dcb2591cfee772906fae'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7f/8d/7f8dc2a2357a3d91ecc5fa5f125c73181dfbe22524d853f672010513044c80f7'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/69/ef/69efdcdb035636e6a8cd18cfc4ef702f95730a381b5d86b36c10028b4df94090'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-push'), PosixPath('/home/leandro/codeparrot-train/.git/objects/pack/pack-67102b35e20edaa7f1ed9c266f37841cd38f158a.pack'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/26/99/2699022bd98f8d49f5505ab457b15dd31156713279335d0c28db1c99edc36894'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-update.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/db/d4/dbd4ddc668c0c838eecd756db64c9a3c2127d8e9bbc05b3fcba00b075854b24c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/fa/40/fa40f7fe8b2d031a32282dce9a40462d67eecff28203c1743fcace8ef4bb37e6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/bd/9b/bd9be9097633349b5ecd400375be5d511e812feadf983f3c2cbcba263a3a14ab'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/97/af/97af2a98400865661b26c3d5c0a3b6be51603452f459136bc9ab2568667ed199'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b4/2c/b42c05288d42233fb829266917ae1145a835f3ccf8e00ea21e5927f9528fb500'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6a/34/6a34d6e3ac6572933b2f66c74af568a0df3b91b94622dd4b7e5d5538c04071ff'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/05/9b/059bc5381874a28e5a467291be6ee44e3f667609290d74e5ed009be10329bdbb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/28/29/28290f1947521e2d6c58ee18d83b864b5d95e1fad3b54ee817799991642488ec'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8a/ae/8aae623a251bd31627554141be2150a5ffb8ddea900ae244fd8492cc03245b36'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/3d/35/3d354291d12d6be3833eda95bd0db307dcd26b5b4287a3f6ca33b3b51b2e46f2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/13/ae/13ae38510e10076edaa24cf051e6403a270c95febd0e2e9b9e052128d632fe36'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/85/28/8528503b464d6cbf8041e0a1481681d0bff4bb24f9d18230fe56c3bc99dfa2ab'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-commit'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ba/38/ba38a25c6b8dd335baf2c6cd925ca5b91668af93f7ecee2b120ad352f46a6565'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/77/13/77131f000b7ab27e1336a181a4e4188f31ed40cea3fdf98b6398b5bbddaa5c76'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/93/51/935137f4370f4f5c85ba6a157825fe6102edb991a46610fa9939e2960be9653d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/78/bb/78bbf19a9e7a29b17fa71e3d05842b9469e3187e938efd8c793ceadbdd38c709'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/55/cb/55cb3e32311273135568ef3da7960400d95f63dad586ccfe56996561277b483f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a7/9a/a79a92653692037bf2fd6de92d93429455cd31dc7f96513adb40277d11be891d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/96/84/9684f7bb635a937d6899902ad758fd565826bfe5b8ea42c296d791dd7089b0f9'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1c/5f/1c5f7b819a67cfca7be02b743fbf0dabf7d53a1c7ddf82e70e094d92973d95c7'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0b/de/0bde10d6ad4055811339a7ed51fca332317529d6b5854a4b7ce90000e352aa33'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/5c/d6/5cd6e14ff3ac522a3a7bac22ef6ec299833c685a9c343d347fe21152e4173856'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ff/bc/ffbc64d8a248deb916c3ef209d2a18fc5de5c56a2cfa546a633cbfec31e6ccb2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/81/7c/817cc36de53f7c914d82e2536a5538c21330ef54662366733e45c76a3c770d06'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/3a/fc/3afc8a938123d0f8e566043d271b4c6a60e3df968b72d8939982a09527763aae'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/95/2e/952eaf2d8448261925753def51d58ff5af595d6469207db42abc0b17204640fb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1d/b3/1db3132794e05cd2decef99af5f56073af4b4a27c33e3a0d0b4289e61b34c9dc'), PosixPath('/home/leandro/codeparrot-train/.git/info/exclude'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/b6/44b6239e61c700810037d9d8aa2fe706d7eaeb5766e492fad95411ad184490f5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/60/07/6007f21e5625708f4710d48386db1297bb1dbd26196ced77b305e7e35da0300d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2d/15/2d15883c4954ffcaafce389f10ccbad7c93e66fae3b7ca7db0a50343180cedf4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2e/b3/2eb3b4ea8f84ef14a84b43002a148d99df05f68c1cfc0c0f074572bda0e0e1ee'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/da/b9/dab942e6da72846fc60682ce21a8e8fa6bf3452a29abff69ec0750e058ab3b92'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/79/c1/79c13ad14568c659397387f3d0e1358393fb0041ff48ce9c98ad4f28df8cde4b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/22/c4/22c47cc7619654f7faafe250a2dd0cabae5520263e967245b8d5638215244239'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/94/e0/94e011d7b77e55164bb15d95c453fa1282d78e234ff378adb930d756bbd33f64'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b9/07/b907e571662c19245abd148afb306b5c6e411d24a5117e0bb4c182a56afb9b97'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/9d/a6/9da6dd8c62377fcfe1e95882a17aa711a8fcc38e02cf21cc1a678f22a9e50d39'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/03/bb/03bb832cf6fad7e4bc885cc1d9502cf312d2951a51afbd63fb6a90f53e49d096'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4a/54/4a54ecd83d3083585ddc7beb921140b2b2e5b4fb82dec9543ac0932c6136e84b'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-checkout'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/02/dd/02ddc3cc1a121d8e237578028f34a994a7548f0d086a1312133c3864dbff6b37'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/46/df/46df1517cd973f00262b495f82b10c46ec077a33bcfc83bade078a36590c6d0a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/04/64/04647e38d2a928e08abccf777e680adf7cb0066862374bd847c492de44cb047f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/43/98/439848f817f432ceefdf7e69a64b60dd99a75cc6fb26599a0ea5ac1167c3db4c'), PosixPath('/home/leandro/codeparrot-train/.git/objects/pack/pack-67102b35e20edaa7f1ed9c266f37841cd38f158a.idx'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7c/bf/7cbfb385a3bbebdb3eed3e154c80f0c9bf6b397aa702e5410339c2b1d74ae867'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/bd/9a/bd9af7b8106e0a773e5a12495aa88339995c2084c2f9a243733879eb73f595d8'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/63/77/6377867a616a0b6e8e3e3691c5cce9cd566773ec5bbd02f5a457edac8a0f24d4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/64/35/643576ec614d0ba328db99ae865b8f1321ec4f288164f76fd6746b3b83e34f19'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d7/c8/d7c88386b6a3c339c8a6d0beead12bf440477473df676886099ca289057fbace'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0d/07/0d07213fb514be71d57406af05dafff0edd3c7506621df761c9453ff598d89c9'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/fc/eb/fcebafda8e3681732437c98581a30faedf7802c6b90c84394d2c42b792c32507'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/applypatch-msg.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/83/14830fec70eb2227647b241d9ff90addbc461cbdcddfe12e015028cefaba6f4e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ef/8b/ef8b57ab3924e70df4f4a37b6853205113144fa01ea6c0140bea3a21b14eafeb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/98/de/98de114cefba6caad86991425c276e59a5ab4a3a1006d29f73ec5cede6233efd'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/87/fb/87fb4ab74dad4c0f520d49769333d5d1b010fcb9e8f30c8dab16430a5a0af9d2'), PosixPath('/home/leandro/codeparrot-train/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ed/ae/edae53c081ce347a58430f0930ce4fb318a9f62e15f85aa638a86c1666f70df4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/49/d8/49d89abc121b49ef8a540796b63edd68f67f679d6ad1b969d6637d852d59f79f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/87/f9/87f9d6d6889eb78e70ba55d2f959fa4e896bd3a78d02dd347792e30ddd730bf6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/bd/a8/bda8ae48acb883ddb225719c3584e3baa76887afb7198d76478af06e7f80572e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/08/26/0826780cd0e3d564882321e246176eac0fb695b706bc72c6022925075047a62e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4f/df/4fdfd51962dfc725568d88de53b29e285d52e858e849acb543101fe556779a42'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/4f/144f1231964ab251596b40abdd80f37fe7ce4ac7b2b31fc517b942cc24110341'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6b/3d/6b3d8a7164286112196af65658426d2faeda5c50fc381bdebf378f0226342d4e'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/update.sample'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-rebase.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/da/6e/da6e9d2f263cf7b0254b4c0a57483ed8ac9652d6f67a63d648e9d968c576d526'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/6d/c7/6dc73c3794ad5c29870563658a7003cb2a6cfb0c1852c47037a6eda6cc3cf3a1'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/25/84/2584f186110af7310075f15e07ddadb9c50c26cafd4c66b2e2baaab040028c3b'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4c/35/4c35db8d1672615cddac65cdf0a76ea9ca1ec9d1d8b18ce293be0df23ff694db'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a9/df/a9dfb7586f9a1bfaaa7175a2384e101f51513b0b98ce01eeaafe5a783cdbad96'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/3a/b5/3ab5c68d9424b10ca45197172baa495813eae7efa9b3914ea4e4afd0201995b5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4f/2c/4f2cb5d9fe3ef94da4aa3ec743d37b83c2347d6f1d3d4696a5c667ff9968ea38'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/7f/4f/7f4fb07272574ef183fd21a911f45f989a941516a11fe1d71335954a54657e07'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/39/32/39325e24ddd711eacc61305d421e004de68e6f6d0b649ca695ad53d4dc53b47f'), PosixPath('/home/leandro/codeparrot-train/.git/logs/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ee/25/ee25b95231437c8795fca58f4a4d95b2698995f29e7f264956f78670f37ea982'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/5f/34/5f342fc03b8d9c90aa9ff917ca3ff3edce748b6f0b55f61aadc9940ca53b45d5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b3/84/b3849196f2777c6e3fb662ae301ae63561db9aaff9bd2ac2f32ad02e9d26d399'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f1/a5/f1a543df8fe1562a57657011c09d45778915a202f279013041e4f08d6cb1b475'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1d/a5/1da55a92827ad63ee4eb1f5eabf14500459bf357c28b767756b80342024063d4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a2/af/a2af1215060dc01f13d389abee1fc25ff94ed84262c54dea264810a5bcc074fc'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/ba/86/ba86bfbe83793efcb2e89df75179188dee67b96ace3e7f1628c133ce11fc361e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a0/cc/a0ccfd373c5bb31028d4b7abb80a9a328395361cc2ac4f7376f5b1f6e89d89d0'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-push.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/44/79/447953386aab39785c0f6c5e44b7310d433886fb73a1e40efe67c9620639e6fa'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2b/ac/2bac46edf98c75901284aff8296f80fea6701821000b205bd85aef8399124074'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e9/95/e995f5605e676fd577e4c78ee6bf43451324ddbcb04e841cf1dfce07c69dc1b6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2a/6b/2a6b5f923b286f640ad586bc295e653ec0db8e4c8487db1c25fa384e216b6ce5'), PosixPath('/home/leandro/codeparrot-train/.git/refs/heads/main'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/12/a7/12a785cd978d3ec0330adae618ad3103dd53f63c7c11b96a7a0d33254407aaa4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/50/83/5083522f9ebdb4c72e4e384dfd9bce8293d84dcdf0a7580cab1ce8e44f2880da'), PosixPath('/home/leandro/codeparrot-train/.git/config'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/33/27/3327f7692a61d984758a71929f4466af87f91a2db0a656321df0d331ef4def20'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4c/b0/4cb0db5e545856bfeb62f7fa15d3472b705ac8fdeb8c4a831727b730951f8902'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/77/63/7763fa2cb60958f8d28fc6bebc0105ed3614addd32296fe929b7262e4d62f58a'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/commit-msg.sample'), PosixPath('/home/leandro/codeparrot-train/.git/HEAD'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1c/6f/1c6ff13e754a4260b097390066ecc973302f45756b4151bbfb7efbb7b1ac9963'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/17/ba/17ba31d8c126b19d7dc4899e46ec476e059462beaf2364bf77471b2f920ddf37'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d5/74/d574d02117a4209d073c3d382e859fdf07d6e18ac38bed8a4d900c8c9975550c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/c0/8a/c08ad7d3c85ef3631747172211b65c70912bae157b55f922f1f70016bf7f64e6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/70/35/70353ba511fe03b0f820a7ef6156771de34ef20a404a1cc2c064033998de0f9f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/cf/84/cf84f4c64b1173bb12e281b88ca920c4c6d130c54214b5172bccbcc045fb2d0f'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/69/63/6963f0671c853a7bb7ae245df7c1f07fd8db821e59e1ab83b74d07909e029111'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b7/d8/b7d84fc6c01ec6eb79187a7e252a3f033bfd1f2ba297d569e1bf507af9b50fa6'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/32/d9/32d95bf48e9ba4ed480df0015326b0ed07647ce17e84a48a5a445db22bc5de4a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/15/95/159531500b1c473455d10fda2fb82f6ea7814500799e27eaf5f2be6f124f994c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/8f/8a/8f8a74c1e1fc4ee43110f74ae0cc01de863a0ceb3f2c4815cab1dc1efeb5339a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/4f/5b/4f5b4ba86fe51a134d866d06e472bd6c6f9d1f122cb905c65cb7c0a35bf51acd'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/17/da/17dac3999cf0cb027901ecb382180aa9560b4bb2c5b839f3afc8cadc229962bf'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/de/af/deaf9432f8e1fdc2bd3b9078dc3996c536e661ebb379b81818ecfc70a360c923'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d0/e5/d0e599bab79fe0054313a92ab57e7a89c65c2fc45011168aa73c0fe000c4f689'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e0/49/e049a0f4444d560849ab8c2d893157b975d183f839984001f101046ca74b7978'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f8/46/f84677f7389798b5c74ff00760d08732db022e99f60dc77e5bb4d900aa80dc60'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/0f/70/0f704aab387aa4e2f0f4dd866d5f0888b25d0d0b61ef7881c38b918f22802ec2'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b5/3e/b53e982e883c26c1a21db49bff0a27d8d628f4fc498715739936fa93bfb5353e'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e3/62/e3627cc99f31126c54a8a4188ce59123e876c812bdbdc5cba35d2f76e369a385'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/post-merge'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/25/16/25162ca0d0fa0474f367ba4720b75f0cb10c70b3f62dd90cbb6e201773c99cb3'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/e1/7a/e17a32eafebfa6f8d8b0edf6c0463c639f06a72fadae7907c9fd026f01136b98'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/00/33/0033a83827749523a25d0ef661ef307b27edc162ce38c44e25fd033e9a187c76'), PosixPath('/home/leandro/codeparrot-train/.git/description'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2d/31/2d3127f22a64cf04b4ab8fd23512d5b7d6373429e36ffd68b3f86d0dff4e2fdb'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/55/db/55dbc21eb4360618b60fc5eaa4ce705ea71bb1e8241237099cfe43c59ed5b2ed'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/b8/ac/b8acca45caffd1db94c790f13ed8f1742b71d4f9cd3d242417e87bb150b6af20'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/d6/ec/d6ecd24bfd9e0c2877dfa00417568e07d9f64a150c5518d471ff91ded60bf146'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/02/a0/02a07bbab0f2b514c1a9d5296ca8c1a843aca846fcde56fc810700ee416db1b4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/96/f9/96f9e109fe3ebce8c82610b0af4398170d678185b18ce5bc0384d84eb421ace5'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/eb/34/eb344442f4771eb011e0e520b8b1666903717e5e8c59a5462fe80aa82401940a'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/14/26/142694003d3fc3bc57e51dab9eaf07472e0f24a4b092d70159943ecc8c2496a4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2a/ff/2aff254f1288353b713d8e718915f8a2eba7d65097ed5f5d0df520a7058ddf71'), PosixPath('/home/leandro/codeparrot-train/.git/hooks/pre-receive.sample'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/2c/a7/2ca7213ba4af470b5f4caa0b4439992b7483c8b4d1cb977089f9b9abef1c7fba'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/80/61/8061f4f61c3955c90dab77a1553ac22e9d1ff604c229375be54a38e32ce6f8ca'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f3/5e/f35ec6ce622145756740be75b1fa969996e7e716ac0a15d9bbc4e86aed616000'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/a7/6e/a76e8e4bbc39a74e4ff59e02aaf1404a8bc429f1033a216058b09f7e0ee3cd0c'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/07/b9/07b951a7cc55afc0d48a47f0dbd9e06c7311279e4a747256b5dcfe11ba56690d'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/1c/2e/1c2e85e92de0f8a29ed6e534983e0051fa2c79e31013c11c7cc66f3f3f1e0155'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/09/c2/09c237a78f8a49d7840d8e5fc58e79db7e225b9904323f46791dce8fd0585332'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/f0/f9/f0f92a74ef6e03d0c05ae2012d7e33242c3b091f3e01d2d8f942e68cf295f7a4'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/eb/a4/eba49c7ea511320fd7040022951873a465016ddb72d078b958a4003c396ffb52'), PosixPath('/home/leandro/codeparrot-train/.git/packed-refs'), PosixPath('/home/leandro/codeparrot-train/.git/lfs/objects/62/03/6203a1aae8671a6a23849de3aa6aa3efec0e3fbe3275757643abfd63a9ee9af8')] 08/30/2021 13:14:02 - WARNING - datasets.builder - Using custom data configuration codeparrot-train-3a26f48916bbb7e0 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Attempting to acquire lock 139865678200064 on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-train-3a26f48916bbb7e0_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Lock 139865678200064 acquired on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-train-3a26f48916bbb7e0_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Attempting to release lock 139865678200064 on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-train-3a26f48916bbb7e0_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Lock 139865678200064 released on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-train-3a26f48916bbb7e0_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - INFO - datasets.load - Some files matched the pattern '*' at /home/leandro/codeparrot-valid but don't have valid data file extensions: [PosixPath('/home/leandro/codeparrot-valid/.git/objects/c6/7ccd65e0057c57364469d576a57387eaa57530'), PosixPath('/home/leandro/codeparrot-valid/.git/description'), PosixPath('/home/leandro/codeparrot-valid/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-commit'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/0b/0462e46b355e305d77ff3b85f3a01776e188ea'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/f3/fa800d7629eabb8ba09a504140b5a203d1341a'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-merge'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/update.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/info/exclude'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-rebase.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/packed-refs'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-applypatch.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/logs/refs/heads/main'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-receive.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/index'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/c9/b135a100a1770bcdc5ae26195bd4f7bd85a764'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-checkout'), PosixPath('/home/leandro/codeparrot-valid/.git/config'), PosixPath('/home/leandro/codeparrot-valid/.git/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-commit.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/logs/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/07/f0db3339ad9053dc95b284c4ae14e014efff89'), PosixPath('/home/leandro/codeparrot-valid/.git/refs/heads/main'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-push.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/5e/9d29c73e4d5b8ecb2b60628d17a791508a514f'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-push'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/applypatch-msg.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-update.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/lfs/objects/43/23/432375a8140ca79af9fa62e3145815c0f7965af8026ed1847ce6e75a11f413fd'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/commit-msg.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/d7/b8c495dd9e6df27bfd6a47dad7e33da0850a5b')] 08/30/2021 13:14:02 - INFO - datasets.load - Some files matched the pattern '*' at /home/leandro/codeparrot-valid but don't have valid data file extensions: [PosixPath('/home/leandro/codeparrot-valid/.git/objects/c6/7ccd65e0057c57364469d576a57387eaa57530'), PosixPath('/home/leandro/codeparrot-valid/.git/description'), PosixPath('/home/leandro/codeparrot-valid/.git/logs/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-commit'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/0b/0462e46b355e305d77ff3b85f3a01776e188ea'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/f3/fa800d7629eabb8ba09a504140b5a203d1341a'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-merge'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/update.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/info/exclude'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-rebase.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/prepare-commit-msg.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/packed-refs'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-applypatch.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/refs/remotes/origin/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/logs/refs/heads/main'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-receive.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/index'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/c9/b135a100a1770bcdc5ae26195bd4f7bd85a764'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-checkout'), PosixPath('/home/leandro/codeparrot-valid/.git/config'), PosixPath('/home/leandro/codeparrot-valid/.git/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-commit.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/logs/HEAD'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/07/f0db3339ad9053dc95b284c4ae14e014efff89'), PosixPath('/home/leandro/codeparrot-valid/.git/refs/heads/main'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-push.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/5e/9d29c73e4d5b8ecb2b60628d17a791508a514f'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/pre-push'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/fsmonitor-watchman.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/applypatch-msg.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/post-update.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/lfs/objects/43/23/432375a8140ca79af9fa62e3145815c0f7965af8026ed1847ce6e75a11f413fd'), PosixPath('/home/leandro/codeparrot-valid/.git/hooks/commit-msg.sample'), PosixPath('/home/leandro/codeparrot-valid/.git/objects/d7/b8c495dd9e6df27bfd6a47dad7e33da0850a5b')] 08/30/2021 13:14:02 - WARNING - datasets.builder - Using custom data configuration codeparrot-valid-52bb4ddf73523afb 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Attempting to acquire lock 139865678180160 on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-valid-52bb4ddf73523afb_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Lock 139865678180160 acquired on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-valid-52bb4ddf73523afb_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Attempting to release lock 139865678180160 on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-valid-52bb4ddf73523afb_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:02 - DEBUG - datasets.utils.filelock - Lock 139865678180160 released on /home/leandro/.cache/huggingface/datasets/_home_leandro_.cache_huggingface_datasets_json_codeparrot-valid-52bb4ddf73523afb_0.0.0_e0dcb9fb097c37d83741a1ffd70553ea5e06cb0082872d4def076475be3ec67c.lock 08/30/2021 13:14:28 - INFO - __main__ - Step 1: {'lr': 0.0, 'samples': 192, 'steps': 0, 'loss/train': 10.546818733215332} 08/30/2021 13:14:30 - INFO - root - Reducer buckets have been rebuilt in this iteration. 08/30/2021 13:14:30 - INFO - __main__ - Step 2: {'lr': 2.5e-07, 'samples': 384, 'steps': 1, 'loss/train': 10.525705337524414} 08/30/2021 13:14:30 - INFO - __main__ - Step 3: {'lr': 5e-07, 'samples': 576, 'steps': 2, 'loss/train': 10.52365493774414} 08/30/2021 13:14:31 - INFO - __main__ - Step 4: {'lr': 7.5e-07, 'samples': 768, 'steps': 3, 'loss/train': 10.503287315368652} 08/30/2021 13:14:31 - INFO - __main__ - Step 5: {'lr': 1e-06, 'samples': 960, 'steps': 4, 'loss/train': 10.504632949829102} 08/30/2021 13:14:32 - INFO - __main__ - Step 6: {'lr': 1.25e-06, 'samples': 1152, 'steps': 5, 'loss/train': 10.51413345336914} 08/30/2021 13:14:33 - INFO - __main__ - Step 7: {'lr': 1.5e-06, 'samples': 1344, 'steps': 6, 'loss/train': 10.520750999450684} 08/30/2021 13:14:33 - INFO - __main__ - Step 8: {'lr': 1.75e-06, 'samples': 1536, 'steps': 7, 'loss/train': 10.414685249328613} 08/30/2021 13:14:34 - INFO - __main__ - Step 9: {'lr': 2e-06, 'samples': 1728, 'steps': 8, 'loss/train': 10.404026985168457} 08/30/2021 13:14:34 - INFO - __main__ - Step 10: {'lr': 2.25e-06, 'samples': 1920, 'steps': 9, 'loss/train': 10.328200340270996} 08/30/2021 13:14:36 - INFO - __main__ - Step 11: {'lr': 2.5e-06, 'samples': 2112, 'steps': 10, 'loss/train': 10.321759223937988} 08/30/2021 13:14:36 - INFO - __main__ - Step 12: {'lr': 2.75e-06, 'samples': 2304, 'steps': 11, 'loss/train': 10.262408256530762} 08/30/2021 13:14:37 - INFO - __main__ - Step 13: {'lr': 3e-06, 'samples': 2496, 'steps': 12, 'loss/train': 10.278728485107422} 08/30/2021 13:14:37 - INFO - __main__ - Step 14: {'lr': 3.25e-06, 'samples': 2688, 'steps': 13, 'loss/train': 10.19308853149414} 08/30/2021 13:14:37 - INFO - __main__ - Step 15: {'lr': 3.5e-06, 'samples': 2880, 'steps': 14, 'loss/train': 10.08371353149414} 08/30/2021 13:14:39 - INFO - __main__ - Step 16: {'lr': 3.75e-06, 'samples': 3072, 'steps': 15, 'loss/train': 10.086686134338379} 08/30/2021 13:14:39 - INFO - __main__ - Step 17: {'lr': 4e-06, 'samples': 3264, 'steps': 16, 'loss/train': 9.986761093139648} 08/30/2021 13:14:40 - INFO - __main__ - Step 18: {'lr': 4.250000000000001e-06, 'samples': 3456, 'steps': 17, 'loss/train': 9.912551879882812} 08/30/2021 13:14:40 - INFO - __main__ - Step 19: {'lr': 4.5e-06, 'samples': 3648, 'steps': 18, 'loss/train': 9.928834915161133} 08/30/2021 13:14:40 - INFO - __main__ - Step 20: {'lr': 4.75e-06, 'samples': 3840, 'steps': 19, 'loss/train': 9.895331382751465} 08/30/2021 13:14:42 - INFO - __main__ - Step 21: {'lr': 5e-06, 'samples': 4032, 'steps': 20, 'loss/train': 9.97384262084961} 08/30/2021 13:14:42 - INFO - __main__ - Step 22: {'lr': 5.2500000000000006e-06, 'samples': 4224, 'steps': 21, 'loss/train': 9.905083656311035} 08/30/2021 13:14:43 - INFO - __main__ - Step 23: {'lr': 5.5e-06, 'samples': 4416, 'steps': 22, 'loss/train': 9.64094352722168} 08/30/2021 13:14:43 - INFO - __main__ - Step 24: {'lr': 5.75e-06, 'samples': 4608, 'steps': 23, 'loss/train': 9.791954040527344} 08/30/2021 13:14:44 - INFO - __main__ - Step 25: {'lr': 6e-06, 'samples': 4800, 'steps': 24, 'loss/train': 9.601712226867676} 08/30/2021 13:14:45 - INFO - __main__ - Step 26: {'lr': 6.25e-06, 'samples': 4992, 'steps': 25, 'loss/train': 9.53923225402832} 08/30/2021 13:14:46 - INFO - __main__ - Step 27: {'lr': 6.5e-06, 'samples': 5184, 'steps': 26, 'loss/train': 9.611143112182617} 08/30/2021 13:14:46 - INFO - __main__ - Step 28: {'lr': 6.75e-06, 'samples': 5376, 'steps': 27, 'loss/train': 9.653268814086914} 08/30/2021 13:14:46 - INFO - __main__ - Step 29: {'lr': 7e-06, 'samples': 5568, 'steps': 28, 'loss/train': 9.100192070007324} 08/30/2021 13:14:47 - INFO - __main__ - Step 30: {'lr': 7.250000000000001e-06, 'samples': 5760, 'steps': 29, 'loss/train': 9.508585929870605} 08/30/2021 13:14:49 - INFO - __main__ - Step 31: {'lr': 7.5e-06, 'samples': 5952, 'steps': 30, 'loss/train': 9.466412544250488} 08/30/2021 13:14:49 - INFO - __main__ - Step 32: {'lr': 7.75e-06, 'samples': 6144, 'steps': 31, 'loss/train': 9.346211433410645} 08/30/2021 13:14:49 - INFO - __main__ - Step 33: {'lr': 8e-06, 'samples': 6336, 'steps': 32, 'loss/train': 9.451282501220703} 08/30/2021 13:14:50 - INFO - __main__ - Step 34: {'lr': 8.25e-06, 'samples': 6528, 'steps': 33, 'loss/train': 9.759281158447266} 08/30/2021 13:14:50 - INFO - __main__ - Step 35: {'lr': 8.500000000000002e-06, 'samples': 6720, 'steps': 34, 'loss/train': 9.649574279785156} 08/30/2021 13:14:52 - INFO - __main__ - Step 36: {'lr': 8.750000000000001e-06, 'samples': 6912, 'steps': 35, 'loss/train': 9.331921577453613} 08/30/2021 13:14:53 - INFO - __main__ - Step 37: {'lr': 9e-06, 'samples': 7104, 'steps': 36, 'loss/train': 9.344559669494629} 08/30/2021 13:14:53 - INFO - __main__ - Step 38: {'lr': 9.25e-06, 'samples': 7296, 'steps': 37, 'loss/train': 9.458386421203613} 08/30/2021 13:14:53 - INFO - __main__ - Step 39: {'lr': 9.5e-06, 'samples': 7488, 'steps': 38, 'loss/train': 8.978026390075684} 08/30/2021 13:14:54 - INFO - __main__ - Step 40: {'lr': 9.75e-06, 'samples': 7680, 'steps': 39, 'loss/train': 9.016935348510742} 08/30/2021 13:14:55 - INFO - __main__ - Step 41: {'lr': 1e-05, 'samples': 7872, 'steps': 40, 'loss/train': 9.311957359313965} 08/30/2021 13:14:56 - INFO - __main__ - Step 42: {'lr': 1.025e-05, 'samples': 8064, 'steps': 41, 'loss/train': 9.269092559814453} 08/30/2021 13:14:56 - INFO - __main__ - Step 43: {'lr': 1.0500000000000001e-05, 'samples': 8256, 'steps': 42, 'loss/train': 9.038583755493164} 08/30/2021 13:14:56 - INFO - __main__ - Step 44: {'lr': 1.0749999999999999e-05, 'samples': 8448, 'steps': 43, 'loss/train': 8.843268394470215} 08/30/2021 13:14:57 - INFO - __main__ - Step 45: {'lr': 1.1e-05, 'samples': 8640, 'steps': 44, 'loss/train': 9.406013488769531} 08/30/2021 13:14:58 - INFO - __main__ - Step 46: {'lr': 1.1249999999999999e-05, 'samples': 8832, 'steps': 45, 'loss/train': 9.007134437561035} 08/30/2021 13:14:59 - INFO - __main__ - Step 47: {'lr': 1.15e-05, 'samples': 9024, 'steps': 46, 'loss/train': 9.294915199279785} 08/30/2021 13:14:59 - INFO - __main__ - Step 48: {'lr': 1.1750000000000001e-05, 'samples': 9216, 'steps': 47, 'loss/train': 9.259795188903809} 08/30/2021 13:15:00 - INFO - __main__ - Step 49: {'lr': 1.2e-05, 'samples': 9408, 'steps': 48, 'loss/train': 8.890713691711426} 08/30/2021 13:15:00 - INFO - __main__ - Step 50: {'lr': 1.2250000000000001e-05, 'samples': 9600, 'steps': 49, 'loss/train': 9.338799476623535} 08/30/2021 13:15:00 - INFO - __main__ - Step 51: {'lr': 1.25e-05, 'samples': 9792, 'steps': 50, 'loss/train': 8.270134925842285} 08/30/2021 13:15:02 - INFO - __main__ - Step 52: {'lr': 1.275e-05, 'samples': 9984, 'steps': 51, 'loss/train': 9.038247108459473} 08/30/2021 13:15:02 - INFO - __main__ - Step 53: {'lr': 1.3e-05, 'samples': 10176, 'steps': 52, 'loss/train': 8.898700714111328} 08/30/2021 13:15:03 - INFO - __main__ - Step 54: {'lr': 1.325e-05, 'samples': 10368, 'steps': 53, 'loss/train': 8.948592185974121} 08/30/2021 13:15:03 - INFO - __main__ - Step 55: {'lr': 1.35e-05, 'samples': 10560, 'steps': 54, 'loss/train': 9.279808044433594} 08/30/2021 13:15:03 - INFO - __main__ - Step 56: {'lr': 1.375e-05, 'samples': 10752, 'steps': 55, 'loss/train': 7.908687591552734} 08/30/2021 13:15:05 - INFO - __main__ - Step 57: {'lr': 1.4e-05, 'samples': 10944, 'steps': 56, 'loss/train': 8.963644981384277} 08/30/2021 13:15:05 - INFO - __main__ - Step 58: {'lr': 1.425e-05, 'samples': 11136, 'steps': 57, 'loss/train': 8.764342308044434} 08/30/2021 13:15:06 - INFO - __main__ - Step 59: {'lr': 1.4500000000000002e-05, 'samples': 11328, 'steps': 58, 'loss/train': 8.986572265625} 08/30/2021 13:15:06 - INFO - __main__ - Step 60: {'lr': 1.475e-05, 'samples': 11520, 'steps': 59, 'loss/train': 8.97697639465332} 08/30/2021 13:15:06 - INFO - __main__ - Step 61: {'lr': 1.5e-05, 'samples': 11712, 'steps': 60, 'loss/train': 8.946927070617676} 08/30/2021 13:15:08 - INFO - __main__ - Step 62: {'lr': 1.525e-05, 'samples': 11904, 'steps': 61, 'loss/train': 9.006952285766602} 08/30/2021 13:15:08 - INFO - __main__ - Step 63: {'lr': 1.55e-05, 'samples': 12096, 'steps': 62, 'loss/train': 8.8870849609375} 08/30/2021 13:15:09 - INFO - __main__ - Step 64: {'lr': 1.575e-05, 'samples': 12288, 'steps': 63, 'loss/train': 8.90562915802002} 08/30/2021 13:15:09 - INFO - __main__ - Step 65: {'lr': 1.6e-05, 'samples': 12480, 'steps': 64, 'loss/train': 8.861169815063477} 08/30/2021 13:15:09 - INFO - __main__ - Step 66: {'lr': 1.6250000000000002e-05, 'samples': 12672, 'steps': 65, 'loss/train': 8.712646484375} 08/30/2021 13:15:11 - INFO - __main__ - Step 67: {'lr': 1.65e-05, 'samples': 12864, 'steps': 66, 'loss/train': 8.782997131347656} 08/30/2021 13:15:12 - INFO - __main__ - Step 68: {'lr': 1.675e-05, 'samples': 13056, 'steps': 67, 'loss/train': 8.86316204071045} 08/30/2021 13:15:12 - INFO - __main__ - Step 69: {'lr': 1.7000000000000003e-05, 'samples': 13248, 'steps': 68, 'loss/train': 8.866331100463867} 08/30/2021 13:15:12 - INFO - __main__ - Step 70: {'lr': 1.7250000000000003e-05, 'samples': 13440, 'steps': 69, 'loss/train': 8.66346549987793} 08/30/2021 13:15:13 - INFO - __main__ - Step 71: {'lr': 1.7500000000000002e-05, 'samples': 13632, 'steps': 70, 'loss/train': 8.741483688354492} 08/30/2021 13:15:14 - INFO - __main__ - Step 72: {'lr': 1.7749999999999998e-05, 'samples': 13824, 'steps': 71, 'loss/train': 8.24655532836914} 08/30/2021 13:15:15 - INFO - __main__ - Step 73: {'lr': 1.8e-05, 'samples': 14016, 'steps': 72, 'loss/train': 8.648695945739746} 08/30/2021 13:15:15 - INFO - __main__ - Step 74: {'lr': 1.825e-05, 'samples': 14208, 'steps': 73, 'loss/train': 8.465259552001953} 08/30/2021 13:15:15 - INFO - __main__ - Step 75: {'lr': 1.85e-05, 'samples': 14400, 'steps': 74, 'loss/train': 8.739703178405762} 08/30/2021 13:15:16 - INFO - __main__ - Step 76: {'lr': 1.875e-05, 'samples': 14592, 'steps': 75, 'loss/train': 8.829558372497559} 08/30/2021 13:15:17 - INFO - __main__ - Step 77: {'lr': 1.9e-05, 'samples': 14784, 'steps': 76, 'loss/train': 7.585636615753174} 08/30/2021 13:15:18 - INFO - __main__ - Step 78: {'lr': 1.925e-05, 'samples': 14976, 'steps': 77, 'loss/train': 8.732975006103516} 08/30/2021 13:15:18 - INFO - __main__ - Step 79: {'lr': 1.95e-05, 'samples': 15168, 'steps': 78, 'loss/train': 8.731362342834473} 08/30/2021 13:15:19 - INFO - __main__ - Step 80: {'lr': 1.975e-05, 'samples': 15360, 'steps': 79, 'loss/train': 8.499696731567383} 08/30/2021 13:15:19 - INFO - __main__ - Step 81: {'lr': 2e-05, 'samples': 15552, 'steps': 80, 'loss/train': 9.014501571655273} 08/30/2021 13:15:19 - INFO - __main__ - Step 82: {'lr': 2.025e-05, 'samples': 15744, 'steps': 81, 'loss/train': 8.513715744018555} 08/30/2021 13:15:21 - INFO - __main__ - Step 83: {'lr': 2.05e-05, 'samples': 15936, 'steps': 82, 'loss/train': 8.84457778930664} 08/30/2021 13:15:21 - INFO - __main__ - Step 84: {'lr': 2.0750000000000003e-05, 'samples': 16128, 'steps': 83, 'loss/train': 8.340596199035645} 08/30/2021 13:15:22 - INFO - __main__ - Step 85: {'lr': 2.1000000000000002e-05, 'samples': 16320, 'steps': 84, 'loss/train': 8.586440086364746} 08/30/2021 13:15:22 - INFO - __main__ - Step 86: {'lr': 2.125e-05, 'samples': 16512, 'steps': 85, 'loss/train': 8.27778148651123} 08/30/2021 13:15:22 - INFO - __main__ - Step 87: {'lr': 2.1499999999999997e-05, 'samples': 16704, 'steps': 86, 'loss/train': 8.524147987365723} 08/30/2021 13:15:24 - INFO - __main__ - Step 88: {'lr': 2.175e-05, 'samples': 16896, 'steps': 87, 'loss/train': 8.412591934204102} 08/30/2021 13:15:25 - INFO - __main__ - Step 89: {'lr': 2.2e-05, 'samples': 17088, 'steps': 88, 'loss/train': 8.645748138427734} 08/30/2021 13:15:25 - INFO - __main__ - Step 90: {'lr': 2.225e-05, 'samples': 17280, 'steps': 89, 'loss/train': 8.578646659851074} 08/30/2021 13:15:25 - INFO - __main__ - Step 91: {'lr': 2.2499999999999998e-05, 'samples': 17472, 'steps': 90, 'loss/train': 8.59123420715332} 08/30/2021 13:15:26 - INFO - __main__ - Step 92: {'lr': 2.275e-05, 'samples': 17664, 'steps': 91, 'loss/train': 9.487090110778809} 08/30/2021 13:15:26 - INFO - __main__ - Step 93: {'lr': 2.3e-05, 'samples': 17856, 'steps': 92, 'loss/train': 8.676104545593262} 08/30/2021 13:15:26 - INFO - __main__ - Step 94: {'lr': 2.325e-05, 'samples': 18048, 'steps': 93, 'loss/train': 8.010075569152832} 08/30/2021 13:15:29 - INFO - __main__ - Step 95: {'lr': 2.3500000000000002e-05, 'samples': 18240, 'steps': 94, 'loss/train': 8.484045028686523} 08/30/2021 13:15:29 - INFO - __main__ - Step 96: {'lr': 2.375e-05, 'samples': 18432, 'steps': 95, 'loss/train': 8.230620384216309} 08/30/2021 13:15:29 - INFO - __main__ - Step 97: {'lr': 2.4e-05, 'samples': 18624, 'steps': 96, 'loss/train': 8.564264297485352} 08/30/2021 13:15:30 - INFO - __main__ - Step 98: {'lr': 2.425e-05, 'samples': 18816, 'steps': 97, 'loss/train': 8.579083442687988} 08/30/2021 13:15:30 - INFO - __main__ - Step 99: {'lr': 2.4500000000000003e-05, 'samples': 19008, 'steps': 98, 'loss/train': 8.529154777526855} 08/30/2021 13:15:32 - INFO - __main__ - Step 100: {'lr': 2.4750000000000002e-05, 'samples': 19200, 'steps': 99, 'loss/train': 8.343099594116211} 08/30/2021 13:15:32 - INFO - __main__ - Step 101: {'lr': 2.5e-05, 'samples': 19392, 'steps': 100, 'loss/train': 8.50272274017334} 08/30/2021 13:15:32 - INFO - __main__ - Step 102: {'lr': 2.525e-05, 'samples': 19584, 'steps': 101, 'loss/train': 8.26205825805664} 08/30/2021 13:15:33 - INFO - __main__ - Step 103: {'lr': 2.55e-05, 'samples': 19776, 'steps': 102, 'loss/train': 8.597186088562012} 08/30/2021 13:15:33 - INFO - __main__ - Step 104: {'lr': 2.575e-05, 'samples': 19968, 'steps': 103, 'loss/train': 8.398731231689453} 08/30/2021 13:15:35 - INFO - __main__ - Step 105: {'lr': 2.6e-05, 'samples': 20160, 'steps': 104, 'loss/train': 7.961066246032715} 08/30/2021 13:15:35 - INFO - __main__ - Step 106: {'lr': 2.625e-05, 'samples': 20352, 'steps': 105, 'loss/train': 8.320724487304688} 08/30/2021 13:15:35 - INFO - __main__ - Step 107: {'lr': 2.65e-05, 'samples': 20544, 'steps': 106, 'loss/train': 9.094656944274902} 08/30/2021 13:15:36 - INFO - __main__ - Step 108: {'lr': 2.675e-05, 'samples': 20736, 'steps': 107, 'loss/train': 8.722951889038086} 08/30/2021 13:15:36 - INFO - __main__ - Step 109: {'lr': 2.7e-05, 'samples': 20928, 'steps': 108, 'loss/train': 8.294156074523926} 08/30/2021 13:15:38 - INFO - __main__ - Step 110: {'lr': 2.725e-05, 'samples': 21120, 'steps': 109, 'loss/train': 8.313566207885742} 08/30/2021 13:15:38 - INFO - __main__ - Step 111: {'lr': 2.75e-05, 'samples': 21312, 'steps': 110, 'loss/train': 8.41221809387207} 08/30/2021 13:15:39 - INFO - __main__ - Step 112: {'lr': 2.775e-05, 'samples': 21504, 'steps': 111, 'loss/train': 8.197552680969238} 08/30/2021 13:15:39 - INFO - __main__ - Step 113: {'lr': 2.8e-05, 'samples': 21696, 'steps': 112, 'loss/train': 7.915801048278809} 08/30/2021 13:15:39 - INFO - __main__ - Step 114: {'lr': 2.8250000000000002e-05, 'samples': 21888, 'steps': 113, 'loss/train': 8.26795768737793} 08/30/2021 13:15:40 - INFO - __main__ - Step 115: {'lr': 2.85e-05, 'samples': 22080, 'steps': 114, 'loss/train': 8.088530540466309} 08/30/2021 13:15:41 - INFO - __main__ - Step 116: {'lr': 2.875e-05, 'samples': 22272, 'steps': 115, 'loss/train': 8.1422700881958} 08/30/2021 13:15:42 - INFO - __main__ - Step 117: {'lr': 2.9000000000000004e-05, 'samples': 22464, 'steps': 116, 'loss/train': 7.825667381286621} 08/30/2021 13:15:42 - INFO - __main__ - Step 118: {'lr': 2.9250000000000003e-05, 'samples': 22656, 'steps': 117, 'loss/train': 8.091445922851562} 08/30/2021 13:15:42 - INFO - __main__ - Step 119: {'lr': 2.95e-05, 'samples': 22848, 'steps': 118, 'loss/train': 8.04175853729248} 08/30/2021 13:15:43 - INFO - __main__ - Step 120: {'lr': 2.9749999999999998e-05, 'samples': 23040, 'steps': 119, 'loss/train': 8.295466423034668} 08/30/2021 13:15:44 - INFO - __main__ - Step 121: {'lr': 3e-05, 'samples': 23232, 'steps': 120, 'loss/train': 7.831602096557617} 08/30/2021 13:15:44 - INFO - __main__ - Step 122: {'lr': 3.025e-05, 'samples': 23424, 'steps': 121, 'loss/train': 7.929701328277588} 08/30/2021 13:15:45 - INFO - __main__ - Step 123: {'lr': 3.05e-05, 'samples': 23616, 'steps': 122, 'loss/train': 8.287981033325195} 08/30/2021 13:15:45 - INFO - __main__ - Step 124: {'lr': 3.075e-05, 'samples': 23808, 'steps': 123, 'loss/train': 8.041546821594238} 08/30/2021 13:15:45 - INFO - __main__ - Step 125: {'lr': 3.1e-05, 'samples': 24000, 'steps': 124, 'loss/train': 7.768130302429199} 08/30/2021 13:15:47 - INFO - __main__ - Step 126: {'lr': 3.125e-05, 'samples': 24192, 'steps': 125, 'loss/train': 8.019730567932129} 08/30/2021 13:15:47 - INFO - __main__ - Step 127: {'lr': 3.15e-05, 'samples': 24384, 'steps': 126, 'loss/train': 8.072555541992188} 08/30/2021 13:15:48 - INFO - __main__ - Step 128: {'lr': 3.175e-05, 'samples': 24576, 'steps': 127, 'loss/train': 7.807083606719971} 08/30/2021 13:15:48 - INFO - __main__ - Step 129: {'lr': 3.2e-05, 'samples': 24768, 'steps': 128, 'loss/train': 7.171544551849365} 08/30/2021 13:15:48 - INFO - __main__ - Step 130: {'lr': 3.2250000000000005e-05, 'samples': 24960, 'steps': 129, 'loss/train': 7.535074710845947} 08/30/2021 13:15:50 - INFO - __main__ - Step 131: {'lr': 3.2500000000000004e-05, 'samples': 25152, 'steps': 130, 'loss/train': 8.027023315429688} 08/30/2021 13:15:51 - INFO - __main__ - Step 132: {'lr': 3.275e-05, 'samples': 25344, 'steps': 131, 'loss/train': 7.754735469818115} 08/30/2021 13:15:51 - INFO - __main__ - Step 133: {'lr': 3.3e-05, 'samples': 25536, 'steps': 132, 'loss/train': 7.7708282470703125} 08/30/2021 13:15:51 - INFO - __main__ - Step 134: {'lr': 3.325e-05, 'samples': 25728, 'steps': 133, 'loss/train': 7.703486919403076} 08/30/2021 13:15:52 - INFO - __main__ - Step 135: {'lr': 3.35e-05, 'samples': 25920, 'steps': 134, 'loss/train': 7.797639846801758} 08/30/2021 13:15:53 - INFO - __main__ - Step 136: {'lr': 3.375e-05, 'samples': 26112, 'steps': 135, 'loss/train': 7.808203220367432} 08/30/2021 13:15:54 - INFO - __main__ - Step 137: {'lr': 3.4000000000000007e-05, 'samples': 26304, 'steps': 136, 'loss/train': 7.523798942565918} 08/30/2021 13:15:54 - INFO - __main__ - Step 138: {'lr': 3.4250000000000006e-05, 'samples': 26496, 'steps': 137, 'loss/train': 7.6538214683532715} 08/30/2021 13:15:54 - INFO - __main__ - Step 139: {'lr': 3.4500000000000005e-05, 'samples': 26688, 'steps': 138, 'loss/train': 7.683449745178223} 08/30/2021 13:15:55 - INFO - __main__ - Step 140: {'lr': 3.4750000000000004e-05, 'samples': 26880, 'steps': 139, 'loss/train': 7.692724227905273} 08/30/2021 13:15:55 - INFO - __main__ - Step 141: {'lr': 3.5000000000000004e-05, 'samples': 27072, 'steps': 140, 'loss/train': 7.852876663208008} 08/30/2021 13:15:57 - INFO - __main__ - Step 142: {'lr': 3.5249999999999996e-05, 'samples': 27264, 'steps': 141, 'loss/train': 7.375845909118652} 08/30/2021 13:15:57 - INFO - __main__ - Step 143: {'lr': 3.5499999999999996e-05, 'samples': 27456, 'steps': 142, 'loss/train': 7.803616523742676} 08/30/2021 13:15:58 - INFO - __main__ - Step 144: {'lr': 3.5749999999999995e-05, 'samples': 27648, 'steps': 143, 'loss/train': 8.747018814086914} 08/30/2021 13:15:58 - INFO - __main__ - Step 145: {'lr': 3.6e-05, 'samples': 27840, 'steps': 144, 'loss/train': 7.117000579833984} 08/30/2021 13:15:58 - INFO - __main__ - Step 146: {'lr': 3.625e-05, 'samples': 28032, 'steps': 145, 'loss/train': 7.414916038513184} 08/30/2021 13:16:01 - INFO - __main__ - Step 147: {'lr': 3.65e-05, 'samples': 28224, 'steps': 146, 'loss/train': 8.180768966674805} 08/30/2021 13:16:01 - INFO - __main__ - Step 148: {'lr': 3.675e-05, 'samples': 28416, 'steps': 147, 'loss/train': 7.569336891174316} 08/30/2021 13:16:02 - INFO - __main__ - Step 149: {'lr': 3.7e-05, 'samples': 28608, 'steps': 148, 'loss/train': 7.721749782562256} 08/30/2021 13:16:02 - INFO - __main__ - Step 150: {'lr': 3.725e-05, 'samples': 28800, 'steps': 149, 'loss/train': 9.089354515075684} 08/30/2021 13:16:02 - INFO - __main__ - Step 151: {'lr': 3.75e-05, 'samples': 28992, 'steps': 150, 'loss/train': 7.522524356842041} 08/30/2021 13:16:03 - INFO - __main__ - Step 152: {'lr': 3.775e-05, 'samples': 29184, 'steps': 151, 'loss/train': 6.467438220977783} 08/30/2021 13:16:04 - INFO - __main__ - Step 153: {'lr': 3.8e-05, 'samples': 29376, 'steps': 152, 'loss/train': 8.00661563873291} 08/30/2021 13:16:05 - INFO - __main__ - Step 154: {'lr': 3.825e-05, 'samples': 29568, 'steps': 153, 'loss/train': 8.649490356445312} 08/30/2021 13:16:05 - INFO - __main__ - Step 155: {'lr': 3.85e-05, 'samples': 29760, 'steps': 154, 'loss/train': 7.1845011711120605} 08/30/2021 13:16:06 - INFO - __main__ - Step 156: {'lr': 3.875e-05, 'samples': 29952, 'steps': 155, 'loss/train': 7.420681953430176} 08/30/2021 13:16:06 - INFO - __main__ - Step 157: {'lr': 3.9e-05, 'samples': 30144, 'steps': 156, 'loss/train': 7.687047004699707} 08/30/2021 13:16:06 - INFO - __main__ - Step 158: {'lr': 3.925e-05, 'samples': 30336, 'steps': 157, 'loss/train': 7.417532920837402} 08/30/2021 13:16:08 - INFO - __main__ - Step 159: {'lr': 3.95e-05, 'samples': 30528, 'steps': 158, 'loss/train': 7.372868537902832} 08/30/2021 13:16:08 - INFO - __main__ - Step 160: {'lr': 3.9750000000000004e-05, 'samples': 30720, 'steps': 159, 'loss/train': 7.476993560791016} 08/30/2021 13:16:09 - INFO - __main__ - Step 161: {'lr': 4e-05, 'samples': 30912, 'steps': 160, 'loss/train': 7.318636894226074} 08/30/2021 13:16:09 - INFO - __main__ - Step 162: {'lr': 4.025e-05, 'samples': 31104, 'steps': 161, 'loss/train': 6.126968860626221} 08/30/2021 13:16:09 - INFO - __main__ - Step 163: {'lr': 4.05e-05, 'samples': 31296, 'steps': 162, 'loss/train': 7.044919490814209} 08/30/2021 13:16:11 - INFO - __main__ - Step 164: {'lr': 4.075e-05, 'samples': 31488, 'steps': 163, 'loss/train': 7.408450126647949} 08/30/2021 13:16:11 - INFO - __main__ - Step 165: {'lr': 4.1e-05, 'samples': 31680, 'steps': 164, 'loss/train': 7.306212902069092} 08/30/2021 13:16:12 - INFO - __main__ - Step 166: {'lr': 4.125e-05, 'samples': 31872, 'steps': 165, 'loss/train': 7.709270000457764} 08/30/2021 13:16:12 - INFO - __main__ - Step 167: {'lr': 4.1500000000000006e-05, 'samples': 32064, 'steps': 166, 'loss/train': 8.131908416748047} 08/30/2021 13:16:12 - INFO - __main__ - Step 168: {'lr': 4.1750000000000005e-05, 'samples': 32256, 'steps': 167, 'loss/train': 7.362995624542236} 08/30/2021 13:16:14 - INFO - __main__ - Step 169: {'lr': 4.2000000000000004e-05, 'samples': 32448, 'steps': 168, 'loss/train': 7.193559646606445} 08/30/2021 13:16:14 - INFO - __main__ - Step 170: {'lr': 4.2250000000000004e-05, 'samples': 32640, 'steps': 169, 'loss/train': 7.005338191986084} 08/30/2021 13:16:15 - INFO - __main__ - Step 171: {'lr': 4.25e-05, 'samples': 32832, 'steps': 170, 'loss/train': 7.036742687225342} 08/30/2021 13:16:15 - INFO - __main__ - Step 172: {'lr': 4.275e-05, 'samples': 33024, 'steps': 171, 'loss/train': 7.050740718841553} 08/30/2021 13:16:15 - INFO - __main__ - Step 173: {'lr': 4.2999999999999995e-05, 'samples': 33216, 'steps': 172, 'loss/train': 6.541714191436768} 08/30/2021 13:16:16 - INFO - __main__ - Step 174: {'lr': 4.325e-05, 'samples': 33408, 'steps': 173, 'loss/train': 6.680890083312988} 08/30/2021 13:16:17 - INFO - __main__ - Step 175: {'lr': 4.35e-05, 'samples': 33600, 'steps': 174, 'loss/train': 8.720884323120117} 08/30/2021 13:16:18 - INFO - __main__ - Step 176: {'lr': 4.375e-05, 'samples': 33792, 'steps': 175, 'loss/train': 7.001683235168457} 08/30/2021 13:16:18 - INFO - __main__ - Step 177: {'lr': 4.4e-05, 'samples': 33984, 'steps': 176, 'loss/train': 7.472266674041748} 08/30/2021 13:16:19 - INFO - __main__ - Step 178: {'lr': 4.425e-05, 'samples': 34176, 'steps': 177, 'loss/train': 8.132484436035156} 08/30/2021 13:16:19 - INFO - __main__ - Step 179: {'lr': 4.45e-05, 'samples': 34368, 'steps': 178, 'loss/train': 7.092846393585205} 08/30/2021 13:16:20 - INFO - __main__ - Step 180: {'lr': 4.475e-05, 'samples': 34560, 'steps': 179, 'loss/train': 7.776556015014648} 08/30/2021 13:16:21 - INFO - __main__ - Step 181: {'lr': 4.4999999999999996e-05, 'samples': 34752, 'steps': 180, 'loss/train': 6.613148212432861} 08/30/2021 13:16:21 - INFO - __main__ - Step 182: {'lr': 4.525e-05, 'samples': 34944, 'steps': 181, 'loss/train': 6.981738567352295} 08/30/2021 13:16:22 - INFO - __main__ - Step 183: {'lr': 4.55e-05, 'samples': 35136, 'steps': 182, 'loss/train': 7.218873500823975} 08/30/2021 13:16:22 - INFO - __main__ - Step 184: {'lr': 4.575e-05, 'samples': 35328, 'steps': 183, 'loss/train': 7.0679473876953125} 08/30/2021 13:16:24 - INFO - __main__ - Step 185: {'lr': 4.6e-05, 'samples': 35520, 'steps': 184, 'loss/train': 6.852197170257568} 08/30/2021 13:16:24 - INFO - __main__ - Step 186: {'lr': 4.625e-05, 'samples': 35712, 'steps': 185, 'loss/train': 6.924624919891357} 08/30/2021 13:16:24 - INFO - __main__ - Step 187: {'lr': 4.65e-05, 'samples': 35904, 'steps': 186, 'loss/train': 7.059135913848877} 08/30/2021 13:16:25 - INFO - __main__ - Step 188: {'lr': 4.675e-05, 'samples': 36096, 'steps': 187, 'loss/train': 8.635014533996582} 08/30/2021 13:16:25 - INFO - __main__ - Step 189: {'lr': 4.7000000000000004e-05, 'samples': 36288, 'steps': 188, 'loss/train': 7.537959575653076} 08/30/2021 13:16:25 - INFO - __main__ - Step 190: {'lr': 4.725e-05, 'samples': 36480, 'steps': 189, 'loss/train': 6.609078884124756} 08/30/2021 13:16:27 - INFO - __main__ - Step 191: {'lr': 4.75e-05, 'samples': 36672, 'steps': 190, 'loss/train': 6.9301300048828125} 08/30/2021 13:16:27 - INFO - __main__ - Step 192: {'lr': 4.775e-05, 'samples': 36864, 'steps': 191, 'loss/train': 7.088875770568848} 08/30/2021 13:16:28 - INFO - __main__ - Step 193: {'lr': 4.8e-05, 'samples': 37056, 'steps': 192, 'loss/train': 6.6858696937561035} 08/30/2021 13:16:28 - INFO - __main__ - Step 194: {'lr': 4.825e-05, 'samples': 37248, 'steps': 193, 'loss/train': 7.036083698272705} 08/30/2021 13:16:28 - INFO - __main__ - Step 195: {'lr': 4.85e-05, 'samples': 37440, 'steps': 194, 'loss/train': 6.408541679382324} 08/30/2021 13:16:30 - INFO - __main__ - Step 196: {'lr': 4.8750000000000006e-05, 'samples': 37632, 'steps': 195, 'loss/train': 7.12893533706665} 08/30/2021 13:16:31 - INFO - __main__ - Step 197: {'lr': 4.9000000000000005e-05, 'samples': 37824, 'steps': 196, 'loss/train': 6.899067401885986} 08/30/2021 13:16:31 - INFO - __main__ - Step 198: {'lr': 4.9250000000000004e-05, 'samples': 38016, 'steps': 197, 'loss/train': 6.713313102722168} 08/30/2021 13:16:32 - INFO - __main__ - Step 199: {'lr': 4.9500000000000004e-05, 'samples': 38208, 'steps': 198, 'loss/train': 6.786980628967285} 08/30/2021 13:16:32 - INFO - __main__ - Step 200: {'lr': 4.975e-05, 'samples': 38400, 'steps': 199, 'loss/train': 7.545706748962402} 08/30/2021 13:16:32 - INFO - __main__ - Step 201: {'lr': 5e-05, 'samples': 38592, 'steps': 200, 'loss/train': 6.757307052612305} 08/30/2021 13:16:34 - INFO - __main__ - Step 202: {'lr': 5.025e-05, 'samples': 38784, 'steps': 201, 'loss/train': 6.9278669357299805} 08/30/2021 13:16:35 - INFO - __main__ - Step 203: {'lr': 5.05e-05, 'samples': 38976, 'steps': 202, 'loss/train': 6.424849987030029} 08/30/2021 13:16:35 - INFO - __main__ - Step 204: {'lr': 5.075000000000001e-05, 'samples': 39168, 'steps': 203, 'loss/train': 6.568314075469971} 08/30/2021 13:16:35 - INFO - __main__ - Step 205: {'lr': 5.1e-05, 'samples': 39360, 'steps': 204, 'loss/train': 6.462455749511719} 08/30/2021 13:16:36 - INFO - __main__ - Step 206: {'lr': 5.125e-05, 'samples': 39552, 'steps': 205, 'loss/train': 6.838433265686035} 08/30/2021 13:16:36 - INFO - __main__ - Step 207: {'lr': 5.15e-05, 'samples': 39744, 'steps': 206, 'loss/train': 6.531557559967041} 08/30/2021 13:16:38 - INFO - __main__ - Step 208: {'lr': 5.175e-05, 'samples': 39936, 'steps': 207, 'loss/train': 6.422881126403809} 08/30/2021 13:16:38 - INFO - __main__ - Step 209: {'lr': 5.2e-05, 'samples': 40128, 'steps': 208, 'loss/train': 5.729274272918701} 08/30/2021 13:16:39 - INFO - __main__ - Step 210: {'lr': 5.2249999999999996e-05, 'samples': 40320, 'steps': 209, 'loss/train': 5.9838175773620605} 08/30/2021 13:16:39 - INFO - __main__ - Step 211: {'lr': 5.25e-05, 'samples': 40512, 'steps': 210, 'loss/train': 6.901343822479248} 08/30/2021 13:16:39 - INFO - __main__ - Step 212: {'lr': 5.275e-05, 'samples': 40704, 'steps': 211, 'loss/train': 7.349523544311523} 08/30/2021 13:16:40 - INFO - __main__ - Step 213: {'lr': 5.3e-05, 'samples': 40896, 'steps': 212, 'loss/train': 6.588607311248779} 08/30/2021 13:16:42 - INFO - __main__ - Step 214: {'lr': 5.325e-05, 'samples': 41088, 'steps': 213, 'loss/train': 6.809523582458496} 08/30/2021 13:16:42 - INFO - __main__ - Step 215: {'lr': 5.35e-05, 'samples': 41280, 'steps': 214, 'loss/train': 6.712080478668213} 08/30/2021 13:16:43 - INFO - __main__ - Step 216: {'lr': 5.375e-05, 'samples': 41472, 'steps': 215, 'loss/train': 7.01638126373291} 08/30/2021 13:16:43 - INFO - __main__ - Step 217: {'lr': 5.4e-05, 'samples': 41664, 'steps': 216, 'loss/train': 6.674835681915283} 08/30/2021 13:16:43 - INFO - __main__ - Step 218: {'lr': 5.4250000000000004e-05, 'samples': 41856, 'steps': 217, 'loss/train': 5.89940881729126} 08/30/2021 13:16:44 - INFO - __main__ - Step 219: {'lr': 5.45e-05, 'samples': 42048, 'steps': 218, 'loss/train': 6.69445276260376} 08/30/2021 13:16:44 - INFO - __main__ - Step 220: {'lr': 5.475e-05, 'samples': 42240, 'steps': 219, 'loss/train': 6.964169025421143} 08/30/2021 13:16:46 - INFO - __main__ - Step 221: {'lr': 5.5e-05, 'samples': 42432, 'steps': 220, 'loss/train': 5.135345935821533} 08/30/2021 13:16:46 - INFO - __main__ - Step 222: {'lr': 5.525e-05, 'samples': 42624, 'steps': 221, 'loss/train': 6.899173259735107} 08/30/2021 13:16:47 - INFO - __main__ - Step 223: {'lr': 5.55e-05, 'samples': 42816, 'steps': 222, 'loss/train': 4.228754043579102} 08/30/2021 13:16:47 - INFO - __main__ - Step 224: {'lr': 5.575e-05, 'samples': 43008, 'steps': 223, 'loss/train': 1.7641043663024902} 08/30/2021 13:16:47 - INFO - __main__ - Step 225: {'lr': 5.6e-05, 'samples': 43200, 'steps': 224, 'loss/train': 6.569450378417969} 08/30/2021 13:16:48 - INFO - __main__ - Step 226: {'lr': 5.6250000000000005e-05, 'samples': 43392, 'steps': 225, 'loss/train': 7.532073974609375} 08/30/2021 13:16:49 - INFO - __main__ - Step 227: {'lr': 5.6500000000000005e-05, 'samples': 43584, 'steps': 226, 'loss/train': 6.195535182952881} 08/30/2021 13:16:49 - INFO - __main__ - Step 228: {'lr': 5.6750000000000004e-05, 'samples': 43776, 'steps': 227, 'loss/train': 6.496519088745117} 08/30/2021 13:16:50 - INFO - __main__ - Step 229: {'lr': 5.7e-05, 'samples': 43968, 'steps': 228, 'loss/train': 6.168381214141846} 08/30/2021 13:16:50 - INFO - __main__ - Step 230: {'lr': 5.725e-05, 'samples': 44160, 'steps': 229, 'loss/train': 7.491093635559082} 08/30/2021 13:16:51 - INFO - __main__ - Step 231: {'lr': 5.75e-05, 'samples': 44352, 'steps': 230, 'loss/train': 7.151771068572998} 08/30/2021 13:16:52 - INFO - __main__ - Step 232: {'lr': 5.775e-05, 'samples': 44544, 'steps': 231, 'loss/train': 6.826668739318848} 08/30/2021 13:16:53 - INFO - __main__ - Step 233: {'lr': 5.800000000000001e-05, 'samples': 44736, 'steps': 232, 'loss/train': 6.619130611419678} 08/30/2021 13:16:53 - INFO - __main__ - Step 234: {'lr': 5.8250000000000006e-05, 'samples': 44928, 'steps': 233, 'loss/train': 6.137080192565918} 08/30/2021 13:16:53 - INFO - __main__ - Step 235: {'lr': 5.8500000000000006e-05, 'samples': 45120, 'steps': 234, 'loss/train': 6.702738285064697} 08/30/2021 13:16:54 - INFO - __main__ - Step 236: {'lr': 5.875e-05, 'samples': 45312, 'steps': 235, 'loss/train': 6.450294494628906} 08/30/2021 13:16:55 - INFO - __main__ - Step 237: {'lr': 5.9e-05, 'samples': 45504, 'steps': 236, 'loss/train': 6.517692565917969} 08/30/2021 13:16:55 - INFO - __main__ - Step 238: {'lr': 5.925e-05, 'samples': 45696, 'steps': 237, 'loss/train': 6.6421098709106445} 08/30/2021 13:16:56 - INFO - __main__ - Step 239: {'lr': 5.9499999999999996e-05, 'samples': 45888, 'steps': 238, 'loss/train': 6.984536647796631} 08/30/2021 13:16:56 - INFO - __main__ - Step 240: {'lr': 5.9749999999999995e-05, 'samples': 46080, 'steps': 239, 'loss/train': 6.613828659057617} 08/30/2021 13:16:57 - INFO - __main__ - Step 241: {'lr': 6e-05, 'samples': 46272, 'steps': 240, 'loss/train': 6.637491226196289} 08/30/2021 13:16:57 - INFO - __main__ - Step 242: {'lr': 6.025e-05, 'samples': 46464, 'steps': 241, 'loss/train': 6.738170623779297} 08/30/2021 13:16:59 - INFO - __main__ - Step 243: {'lr': 6.05e-05, 'samples': 46656, 'steps': 242, 'loss/train': 6.628913879394531} 08/30/2021 13:16:59 - INFO - __main__ - Step 244: {'lr': 6.075e-05, 'samples': 46848, 'steps': 243, 'loss/train': 6.514838218688965} 08/30/2021 13:17:00 - INFO - __main__ - Step 245: {'lr': 6.1e-05, 'samples': 47040, 'steps': 244, 'loss/train': 6.199484825134277} 08/30/2021 13:17:00 - INFO - __main__ - Step 246: {'lr': 6.125e-05, 'samples': 47232, 'steps': 245, 'loss/train': 7.448530197143555} 08/30/2021 13:17:00 - INFO - __main__ - Step 247: {'lr': 6.15e-05, 'samples': 47424, 'steps': 246, 'loss/train': 6.739471435546875} 08/30/2021 13:17:02 - INFO - __main__ - Step 248: {'lr': 6.175e-05, 'samples': 47616, 'steps': 247, 'loss/train': 6.479034423828125} 08/30/2021 13:17:02 - INFO - __main__ - Step 249: {'lr': 6.2e-05, 'samples': 47808, 'steps': 248, 'loss/train': 6.803154468536377} 08/30/2021 13:17:03 - INFO - __main__ - Step 250: {'lr': 6.225e-05, 'samples': 48000, 'steps': 249, 'loss/train': 6.7155585289001465} 08/30/2021 13:17:03 - INFO - __main__ - Step 251: {'lr': 6.25e-05, 'samples': 48192, 'steps': 250, 'loss/train': 7.329843997955322} 08/30/2021 13:17:03 - INFO - __main__ - Step 252: {'lr': 6.275000000000001e-05, 'samples': 48384, 'steps': 251, 'loss/train': 6.693150520324707} 08/30/2021 13:17:05 - INFO - __main__ - Step 253: {'lr': 6.3e-05, 'samples': 48576, 'steps': 252, 'loss/train': 6.362494468688965} 08/30/2021 13:17:05 - INFO - __main__ - Step 254: {'lr': 6.325e-05, 'samples': 48768, 'steps': 253, 'loss/train': 6.805384159088135} 08/30/2021 13:17:05 - INFO - __main__ - Step 255: {'lr': 6.35e-05, 'samples': 48960, 'steps': 254, 'loss/train': 6.727595806121826} 08/30/2021 13:17:06 - INFO - __main__ - Step 256: {'lr': 6.375e-05, 'samples': 49152, 'steps': 255, 'loss/train': 6.758667945861816} 08/30/2021 13:17:06 - INFO - __main__ - Step 257: {'lr': 6.4e-05, 'samples': 49344, 'steps': 256, 'loss/train': 6.727235794067383} 08/30/2021 13:17:08 - INFO - __main__ - Step 258: {'lr': 6.425e-05, 'samples': 49536, 'steps': 257, 'loss/train': 6.790642261505127} 08/30/2021 13:17:08 - INFO - __main__ - Step 259: {'lr': 6.450000000000001e-05, 'samples': 49728, 'steps': 258, 'loss/train': 6.2721405029296875} 08/30/2021 13:17:09 - INFO - __main__ - Step 260: {'lr': 6.475e-05, 'samples': 49920, 'steps': 259, 'loss/train': 6.076294898986816} 08/30/2021 13:17:09 - INFO - __main__ - Step 261: {'lr': 6.500000000000001e-05, 'samples': 50112, 'steps': 260, 'loss/train': 6.275369167327881} 08/30/2021 13:17:09 - INFO - __main__ - Step 262: {'lr': 6.525e-05, 'samples': 50304, 'steps': 261, 'loss/train': 6.536117076873779} 08/30/2021 13:17:11 - INFO - __main__ - Step 263: {'lr': 6.55e-05, 'samples': 50496, 'steps': 262, 'loss/train': 6.122943878173828} 08/30/2021 13:17:12 - INFO - __main__ - Step 264: {'lr': 6.575e-05, 'samples': 50688, 'steps': 263, 'loss/train': 6.044567584991455} 08/30/2021 13:17:12 - INFO - __main__ - Step 265: {'lr': 6.6e-05, 'samples': 50880, 'steps': 264, 'loss/train': 6.834893703460693} 08/30/2021 13:17:13 - INFO - __main__ - Step 266: {'lr': 6.625000000000001e-05, 'samples': 51072, 'steps': 265, 'loss/train': 6.797702312469482} 08/30/2021 13:17:13 - INFO - __main__ - Step 267: {'lr': 6.65e-05, 'samples': 51264, 'steps': 266, 'loss/train': 6.716531276702881} 08/30/2021 13:17:15 - INFO - __main__ - Step 268: {'lr': 6.675000000000001e-05, 'samples': 51456, 'steps': 267, 'loss/train': 6.557199954986572} 08/30/2021 13:17:15 - INFO - __main__ - Step 269: {'lr': 6.7e-05, 'samples': 51648, 'steps': 268, 'loss/train': 6.293004512786865} 08/30/2021 13:17:16 - INFO - __main__ - Step 270: {'lr': 6.725000000000001e-05, 'samples': 51840, 'steps': 269, 'loss/train': 6.490097999572754} 08/30/2021 13:17:16 - INFO - __main__ - Step 271: {'lr': 6.75e-05, 'samples': 52032, 'steps': 270, 'loss/train': 5.555928707122803} 08/30/2021 13:17:16 - INFO - __main__ - Step 272: {'lr': 6.775000000000001e-05, 'samples': 52224, 'steps': 271, 'loss/train': 6.2016282081604} 08/30/2021 13:17:17 - INFO - __main__ - Step 273: {'lr': 6.800000000000001e-05, 'samples': 52416, 'steps': 272, 'loss/train': 6.706387042999268} 08/30/2021 13:17:17 - INFO - __main__ - Step 274: {'lr': 6.825e-05, 'samples': 52608, 'steps': 273, 'loss/train': 6.345366477966309} 08/30/2021 13:17:18 - INFO - __main__ - Step 275: {'lr': 6.850000000000001e-05, 'samples': 52800, 'steps': 274, 'loss/train': 6.390197277069092} 08/30/2021 13:17:19 - INFO - __main__ - Step 276: {'lr': 6.875e-05, 'samples': 52992, 'steps': 275, 'loss/train': 6.968113422393799} 08/30/2021 13:17:19 - INFO - __main__ - Step 277: {'lr': 6.900000000000001e-05, 'samples': 53184, 'steps': 276, 'loss/train': 6.015243053436279} 08/30/2021 13:17:20 - INFO - __main__ - Step 278: {'lr': 6.925e-05, 'samples': 53376, 'steps': 277, 'loss/train': 6.234228610992432} 08/30/2021 13:17:20 - INFO - __main__ - Step 279: {'lr': 6.950000000000001e-05, 'samples': 53568, 'steps': 278, 'loss/train': 6.04856538772583} 08/30/2021 13:17:21 - INFO - __main__ - Step 280: {'lr': 6.975e-05, 'samples': 53760, 'steps': 279, 'loss/train': 6.198585510253906} 08/30/2021 13:17:22 - INFO - __main__ - Step 281: {'lr': 7.000000000000001e-05, 'samples': 53952, 'steps': 280, 'loss/train': 6.070130348205566} 08/30/2021 13:17:22 - INFO - __main__ - Step 282: {'lr': 7.025000000000001e-05, 'samples': 54144, 'steps': 281, 'loss/train': 6.166639804840088} 08/30/2021 13:17:23 - INFO - __main__ - Step 283: {'lr': 7.049999999999999e-05, 'samples': 54336, 'steps': 282, 'loss/train': 6.3716888427734375} 08/30/2021 13:17:23 - INFO - __main__ - Step 284: {'lr': 7.075e-05, 'samples': 54528, 'steps': 283, 'loss/train': 6.35542106628418} 08/30/2021 13:17:25 - INFO - __main__ - Step 285: {'lr': 7.099999999999999e-05, 'samples': 54720, 'steps': 284, 'loss/train': 6.591944694519043} 08/30/2021 13:17:25 - INFO - __main__ - Step 286: {'lr': 7.125e-05, 'samples': 54912, 'steps': 285, 'loss/train': 6.389350891113281} 08/30/2021 13:17:25 - INFO - __main__ - Step 287: {'lr': 7.149999999999999e-05, 'samples': 55104, 'steps': 286, 'loss/train': 5.966076374053955} 08/30/2021 13:17:26 - INFO - __main__ - Step 288: {'lr': 7.175e-05, 'samples': 55296, 'steps': 287, 'loss/train': 6.342068672180176} 08/30/2021 13:17:26 - INFO - __main__ - Step 289: {'lr': 7.2e-05, 'samples': 55488, 'steps': 288, 'loss/train': 6.697934627532959} 08/30/2021 13:17:27 - INFO - __main__ - Step 290: {'lr': 7.225e-05, 'samples': 55680, 'steps': 289, 'loss/train': 6.229708194732666} 08/30/2021 13:17:28 - INFO - __main__ - Step 291: {'lr': 7.25e-05, 'samples': 55872, 'steps': 290, 'loss/train': 6.215189456939697} 08/30/2021 13:17:28 - INFO - __main__ - Step 292: {'lr': 7.274999999999999e-05, 'samples': 56064, 'steps': 291, 'loss/train': 6.311378479003906} 08/30/2021 13:17:29 - INFO - __main__ - Step 293: {'lr': 7.3e-05, 'samples': 56256, 'steps': 292, 'loss/train': 6.328258037567139} 08/30/2021 13:17:29 - INFO - __main__ - Step 294: {'lr': 7.324999999999999e-05, 'samples': 56448, 'steps': 293, 'loss/train': 5.831396102905273} 08/30/2021 13:17:30 - INFO - __main__ - Step 295: {'lr': 7.35e-05, 'samples': 56640, 'steps': 294, 'loss/train': 6.255168437957764} 08/30/2021 13:17:31 - INFO - __main__ - Step 296: {'lr': 7.375e-05, 'samples': 56832, 'steps': 295, 'loss/train': 5.845766067504883} 08/30/2021 13:17:31 - INFO - __main__ - Step 297: {'lr': 7.4e-05, 'samples': 57024, 'steps': 296, 'loss/train': 6.156411170959473} 08/30/2021 13:17:32 - INFO - __main__ - Step 298: {'lr': 7.425e-05, 'samples': 57216, 'steps': 297, 'loss/train': 6.51584005355835} 08/30/2021 13:17:32 - INFO - __main__ - Step 299: {'lr': 7.45e-05, 'samples': 57408, 'steps': 298, 'loss/train': 6.158653736114502} 08/30/2021 13:17:32 - INFO - __main__ - Step 300: {'lr': 7.475e-05, 'samples': 57600, 'steps': 299, 'loss/train': 6.394083023071289} 08/30/2021 13:17:34 - INFO - __main__ - Step 301: {'lr': 7.5e-05, 'samples': 57792, 'steps': 300, 'loss/train': 6.393588542938232} 08/30/2021 13:17:34 - INFO - __main__ - Step 302: {'lr': 7.525e-05, 'samples': 57984, 'steps': 301, 'loss/train': 6.1207661628723145} 08/30/2021 13:17:35 - INFO - __main__ - Step 303: {'lr': 7.55e-05, 'samples': 58176, 'steps': 302, 'loss/train': 5.8542985916137695} 08/30/2021 13:17:35 - INFO - __main__ - Step 304: {'lr': 7.575e-05, 'samples': 58368, 'steps': 303, 'loss/train': 6.160946846008301} 08/30/2021 13:17:35 - INFO - __main__ - Step 305: {'lr': 7.6e-05, 'samples': 58560, 'steps': 304, 'loss/train': 5.6898274421691895} 08/30/2021 13:17:37 - INFO - __main__ - Step 306: {'lr': 7.625e-05, 'samples': 58752, 'steps': 305, 'loss/train': 8.189115524291992} 08/30/2021 13:17:37 - INFO - __main__ - Step 307: {'lr': 7.65e-05, 'samples': 58944, 'steps': 306, 'loss/train': 6.525139331817627} 08/30/2021 13:17:38 - INFO - __main__ - Step 308: {'lr': 7.675e-05, 'samples': 59136, 'steps': 307, 'loss/train': 5.728509426116943} 08/30/2021 13:17:38 - INFO - __main__ - Step 309: {'lr': 7.7e-05, 'samples': 59328, 'steps': 308, 'loss/train': 6.039815425872803} 08/30/2021 13:17:38 - INFO - __main__ - Step 310: {'lr': 7.725000000000001e-05, 'samples': 59520, 'steps': 309, 'loss/train': 6.44235372543335} 08/30/2021 13:17:39 - INFO - __main__ - Step 311: {'lr': 7.75e-05, 'samples': 59712, 'steps': 310, 'loss/train': 6.429628849029541} 08/30/2021 13:17:40 - INFO - __main__ - Step 312: {'lr': 7.775e-05, 'samples': 59904, 'steps': 311, 'loss/train': 5.878021717071533} 08/30/2021 13:17:41 - INFO - __main__ - Step 313: {'lr': 7.8e-05, 'samples': 60096, 'steps': 312, 'loss/train': 6.173260688781738} 08/30/2021 13:17:41 - INFO - __main__ - Step 314: {'lr': 7.825e-05, 'samples': 60288, 'steps': 313, 'loss/train': 6.34955358505249} 08/30/2021 13:17:41 - INFO - __main__ - Step 315: {'lr': 7.85e-05, 'samples': 60480, 'steps': 314, 'loss/train': 5.728211402893066} 08/30/2021 13:17:42 - INFO - __main__ - Step 316: {'lr': 7.875e-05, 'samples': 60672, 'steps': 315, 'loss/train': 6.1544294357299805} 08/30/2021 13:17:44 - INFO - __main__ - Step 317: {'lr': 7.9e-05, 'samples': 60864, 'steps': 316, 'loss/train': 6.2256975173950195} 08/30/2021 13:17:45 - INFO - __main__ - Step 318: {'lr': 7.925e-05, 'samples': 61056, 'steps': 317, 'loss/train': 6.413060665130615} 08/30/2021 13:17:45 - INFO - __main__ - Step 319: {'lr': 7.950000000000001e-05, 'samples': 61248, 'steps': 318, 'loss/train': 5.53223180770874} 08/30/2021 13:17:45 - INFO - __main__ - Step 320: {'lr': 7.975e-05, 'samples': 61440, 'steps': 319, 'loss/train': 6.0107951164245605} 08/30/2021 13:17:46 - INFO - __main__ - Step 321: {'lr': 8e-05, 'samples': 61632, 'steps': 320, 'loss/train': 6.844748497009277} 08/30/2021 13:17:48 - INFO - __main__ - Step 322: {'lr': 8.025e-05, 'samples': 61824, 'steps': 321, 'loss/train': 5.647246360778809} 08/30/2021 13:17:48 - INFO - __main__ - Step 323: {'lr': 8.05e-05, 'samples': 62016, 'steps': 322, 'loss/train': 6.0663909912109375} 08/30/2021 13:17:48 - INFO - __main__ - Step 324: {'lr': 8.075e-05, 'samples': 62208, 'steps': 323, 'loss/train': 6.454882621765137} 08/30/2021 13:17:49 - INFO - __main__ - Step 325: {'lr': 8.1e-05, 'samples': 62400, 'steps': 324, 'loss/train': 6.121888160705566} 08/30/2021 13:17:49 - INFO - __main__ - Step 326: {'lr': 8.125000000000001e-05, 'samples': 62592, 'steps': 325, 'loss/train': 6.522874355316162} 08/30/2021 13:17:51 - INFO - __main__ - Step 327: {'lr': 8.15e-05, 'samples': 62784, 'steps': 326, 'loss/train': 6.217108249664307} 08/30/2021 13:17:51 - INFO - __main__ - Step 328: {'lr': 8.175000000000001e-05, 'samples': 62976, 'steps': 327, 'loss/train': 6.257899761199951} 08/30/2021 13:17:52 - INFO - __main__ - Step 329: {'lr': 8.2e-05, 'samples': 63168, 'steps': 328, 'loss/train': 6.448293209075928} 08/30/2021 13:17:52 - INFO - __main__ - Step 330: {'lr': 8.225000000000001e-05, 'samples': 63360, 'steps': 329, 'loss/train': 6.304119110107422} 08/30/2021 13:17:52 - INFO - __main__ - Step 331: {'lr': 8.25e-05, 'samples': 63552, 'steps': 330, 'loss/train': 6.791227340698242} 08/30/2021 13:17:53 - INFO - __main__ - Step 332: {'lr': 8.275e-05, 'samples': 63744, 'steps': 331, 'loss/train': 4.826516628265381} 08/30/2021 13:17:53 - INFO - __main__ - Step 333: {'lr': 8.300000000000001e-05, 'samples': 63936, 'steps': 332, 'loss/train': 6.303062915802002} 08/30/2021 13:17:55 - INFO - __main__ - Step 334: {'lr': 8.325e-05, 'samples': 64128, 'steps': 333, 'loss/train': 5.697182655334473} 08/30/2021 13:17:55 - INFO - __main__ - Step 335: {'lr': 8.350000000000001e-05, 'samples': 64320, 'steps': 334, 'loss/train': 5.643592357635498} 08/30/2021 13:17:55 - INFO - __main__ - Step 336: {'lr': 8.375e-05, 'samples': 64512, 'steps': 335, 'loss/train': 6.222052097320557} 08/30/2021 13:17:56 - INFO - __main__ - Step 337: {'lr': 8.400000000000001e-05, 'samples': 64704, 'steps': 336, 'loss/train': 5.895704746246338} 08/30/2021 13:17:56 - INFO - __main__ - Step 338: {'lr': 8.425e-05, 'samples': 64896, 'steps': 337, 'loss/train': 5.852711200714111} 08/30/2021 13:17:58 - INFO - __main__ - Step 339: {'lr': 8.450000000000001e-05, 'samples': 65088, 'steps': 338, 'loss/train': 6.112983226776123} 08/30/2021 13:17:58 - INFO - __main__ - Step 340: {'lr': 8.475000000000001e-05, 'samples': 65280, 'steps': 339, 'loss/train': 6.1996235847473145} 08/30/2021 13:17:58 - INFO - __main__ - Step 341: {'lr': 8.5e-05, 'samples': 65472, 'steps': 340, 'loss/train': 6.592947006225586} 08/30/2021 13:17:59 - INFO - __main__ - Step 342: {'lr': 8.525000000000001e-05, 'samples': 65664, 'steps': 341, 'loss/train': 5.923532962799072} 08/30/2021 13:17:59 - INFO - __main__ - Step 343: {'lr': 8.55e-05, 'samples': 65856, 'steps': 342, 'loss/train': 5.868164539337158} 08/30/2021 13:18:01 - INFO - __main__ - Step 344: {'lr': 8.575000000000001e-05, 'samples': 66048, 'steps': 343, 'loss/train': 6.542609214782715} 08/30/2021 13:18:01 - INFO - __main__ - Step 345: {'lr': 8.599999999999999e-05, 'samples': 66240, 'steps': 344, 'loss/train': 5.413185119628906} 08/30/2021 13:18:02 - INFO - __main__ - Step 346: {'lr': 8.625e-05, 'samples': 66432, 'steps': 345, 'loss/train': 5.551840305328369} 08/30/2021 13:18:02 - INFO - __main__ - Step 347: {'lr': 8.65e-05, 'samples': 66624, 'steps': 346, 'loss/train': 5.807283878326416} 08/30/2021 13:18:02 - INFO - __main__ - Step 348: {'lr': 8.675e-05, 'samples': 66816, 'steps': 347, 'loss/train': 6.04257869720459} 08/30/2021 13:18:04 - INFO - __main__ - Step 349: {'lr': 8.7e-05, 'samples': 67008, 'steps': 348, 'loss/train': 6.191489219665527} 08/30/2021 13:18:04 - INFO - __main__ - Step 350: {'lr': 8.724999999999999e-05, 'samples': 67200, 'steps': 349, 'loss/train': 6.023970603942871} 08/30/2021 13:18:05 - INFO - __main__ - Step 351: {'lr': 8.75e-05, 'samples': 67392, 'steps': 350, 'loss/train': 6.3830976486206055} 08/30/2021 13:18:05 - INFO - __main__ - Step 352: {'lr': 8.774999999999999e-05, 'samples': 67584, 'steps': 351, 'loss/train': 5.905723571777344} 08/30/2021 13:18:05 - INFO - __main__ - Step 353: {'lr': 8.8e-05, 'samples': 67776, 'steps': 352, 'loss/train': 6.28004264831543} 08/30/2021 13:18:07 - INFO - __main__ - Step 354: {'lr': 8.824999999999999e-05, 'samples': 67968, 'steps': 353, 'loss/train': 5.97433614730835} 08/30/2021 13:18:08 - INFO - __main__ - Step 355: {'lr': 8.85e-05, 'samples': 68160, 'steps': 354, 'loss/train': 6.19740104675293} 08/30/2021 13:18:08 - INFO - __main__ - Step 356: {'lr': 8.875e-05, 'samples': 68352, 'steps': 355, 'loss/train': 6.187588691711426} 08/30/2021 13:18:08 - INFO - __main__ - Step 357: {'lr': 8.9e-05, 'samples': 68544, 'steps': 356, 'loss/train': 5.520158767700195} 08/30/2021 13:18:09 - INFO - __main__ - Step 358: {'lr': 8.925e-05, 'samples': 68736, 'steps': 357, 'loss/train': 5.60365104675293} 08/30/2021 13:18:10 - INFO - __main__ - Step 359: {'lr': 8.95e-05, 'samples': 68928, 'steps': 358, 'loss/train': 5.0504889488220215} 08/30/2021 13:18:11 - INFO - __main__ - Step 360: {'lr': 8.975e-05, 'samples': 69120, 'steps': 359, 'loss/train': 6.02947998046875} 08/30/2021 13:18:11 - INFO - __main__ - Step 361: {'lr': 8.999999999999999e-05, 'samples': 69312, 'steps': 360, 'loss/train': 5.876142501831055} 08/30/2021 13:18:11 - INFO - __main__ - Step 362: {'lr': 9.025e-05, 'samples': 69504, 'steps': 361, 'loss/train': 6.375011444091797} 08/30/2021 13:18:12 - INFO - __main__ - Step 363: {'lr': 9.05e-05, 'samples': 69696, 'steps': 362, 'loss/train': 6.455024242401123} 08/30/2021 13:18:13 - INFO - __main__ - Step 364: {'lr': 9.075e-05, 'samples': 69888, 'steps': 363, 'loss/train': 4.663980484008789} 08/30/2021 13:18:14 - INFO - __main__ - Step 365: {'lr': 9.1e-05, 'samples': 70080, 'steps': 364, 'loss/train': 6.091887950897217} 08/30/2021 13:18:14 - INFO - __main__ - Step 366: {'lr': 9.125e-05, 'samples': 70272, 'steps': 365, 'loss/train': 6.282298564910889} 08/30/2021 13:18:14 - INFO - __main__ - Step 367: {'lr': 9.15e-05, 'samples': 70464, 'steps': 366, 'loss/train': 6.375043869018555} 08/30/2021 13:18:15 - INFO - __main__ - Step 368: {'lr': 9.175e-05, 'samples': 70656, 'steps': 367, 'loss/train': 5.624589920043945} 08/30/2021 13:18:15 - INFO - __main__ - Step 369: {'lr': 9.2e-05, 'samples': 70848, 'steps': 368, 'loss/train': 7.198649883270264} 08/30/2021 13:18:18 - INFO - __main__ - Step 370: {'lr': 9.225e-05, 'samples': 71040, 'steps': 369, 'loss/train': 5.610406398773193} 08/30/2021 13:18:18 - INFO - __main__ - Step 371: {'lr': 9.25e-05, 'samples': 71232, 'steps': 370, 'loss/train': 6.06537389755249} 08/30/2021 13:18:18 - INFO - __main__ - Step 372: {'lr': 9.275e-05, 'samples': 71424, 'steps': 371, 'loss/train': 4.313782215118408} 08/30/2021 13:18:19 - INFO - __main__ - Step 373: {'lr': 9.3e-05, 'samples': 71616, 'steps': 372, 'loss/train': 6.235553741455078} 08/30/2021 13:18:19 - INFO - __main__ - Step 374: {'lr': 9.325e-05, 'samples': 71808, 'steps': 373, 'loss/train': 5.99864387512207} 08/30/2021 13:18:19 - INFO - __main__ - Step 375: {'lr': 9.35e-05, 'samples': 72000, 'steps': 374, 'loss/train': 5.66547155380249} 08/30/2021 13:18:21 - INFO - __main__ - Step 376: {'lr': 9.375e-05, 'samples': 72192, 'steps': 375, 'loss/train': 5.540463447570801} 08/30/2021 13:18:21 - INFO - __main__ - Step 377: {'lr': 9.400000000000001e-05, 'samples': 72384, 'steps': 376, 'loss/train': 4.755856990814209} 08/30/2021 13:18:22 - INFO - __main__ - Step 378: {'lr': 9.425e-05, 'samples': 72576, 'steps': 377, 'loss/train': 5.674274444580078} 08/30/2021 13:18:22 - INFO - __main__ - Step 379: {'lr': 9.45e-05, 'samples': 72768, 'steps': 378, 'loss/train': 6.150738716125488} 08/30/2021 13:18:23 - INFO - __main__ - Step 380: {'lr': 9.475e-05, 'samples': 72960, 'steps': 379, 'loss/train': 6.264613628387451} 08/30/2021 13:18:24 - INFO - __main__ - Step 381: {'lr': 9.5e-05, 'samples': 73152, 'steps': 380, 'loss/train': 6.115423202514648} 08/30/2021 13:18:25 - INFO - __main__ - Step 382: {'lr': 9.525e-05, 'samples': 73344, 'steps': 381, 'loss/train': 5.927343845367432} 08/30/2021 13:18:25 - INFO - __main__ - Step 383: {'lr': 9.55e-05, 'samples': 73536, 'steps': 382, 'loss/train': 5.794401168823242} 08/30/2021 13:18:25 - INFO - __main__ - Step 384: {'lr': 9.575000000000001e-05, 'samples': 73728, 'steps': 383, 'loss/train': 3.3423562049865723} 08/30/2021 13:18:26 - INFO - __main__ - Step 385: {'lr': 9.6e-05, 'samples': 73920, 'steps': 384, 'loss/train': 5.551865100860596} 08/30/2021 13:18:28 - INFO - __main__ - Step 386: {'lr': 9.625000000000001e-05, 'samples': 74112, 'steps': 385, 'loss/train': 5.7878241539001465} 08/30/2021 13:18:28 - INFO - __main__ - Step 387: {'lr': 9.65e-05, 'samples': 74304, 'steps': 386, 'loss/train': 5.973217487335205} 08/30/2021 13:18:28 - INFO - __main__ - Step 388: {'lr': 9.675000000000001e-05, 'samples': 74496, 'steps': 387, 'loss/train': 5.955297470092773} 08/30/2021 13:18:29 - INFO - __main__ - Step 389: {'lr': 9.7e-05, 'samples': 74688, 'steps': 388, 'loss/train': 5.313389778137207} 08/30/2021 13:18:29 - INFO - __main__ - Step 390: {'lr': 9.725e-05, 'samples': 74880, 'steps': 389, 'loss/train': 5.470920562744141} 08/30/2021 13:18:30 - INFO - __main__ - Step 391: {'lr': 9.750000000000001e-05, 'samples': 75072, 'steps': 390, 'loss/train': 5.316433906555176} 08/30/2021 13:18:30 - INFO - __main__ - Step 392: {'lr': 9.775e-05, 'samples': 75264, 'steps': 391, 'loss/train': 8.51474380493164} 08/30/2021 13:18:31 - INFO - __main__ - Step 393: {'lr': 9.800000000000001e-05, 'samples': 75456, 'steps': 392, 'loss/train': 5.866165637969971} 08/30/2021 13:18:32 - INFO - __main__ - Step 394: {'lr': 9.825e-05, 'samples': 75648, 'steps': 393, 'loss/train': 5.825680732727051} 08/30/2021 13:18:32 - INFO - __main__ - Step 395: {'lr': 9.850000000000001e-05, 'samples': 75840, 'steps': 394, 'loss/train': 5.5515899658203125} 08/30/2021 13:18:33 - INFO - __main__ - Step 396: {'lr': 9.875e-05, 'samples': 76032, 'steps': 395, 'loss/train': 5.187445163726807} 08/30/2021 13:18:33 - INFO - __main__ - Step 397: {'lr': 9.900000000000001e-05, 'samples': 76224, 'steps': 396, 'loss/train': 5.892002582550049} 08/30/2021 13:18:35 - INFO - __main__ - Step 398: {'lr': 9.925000000000001e-05, 'samples': 76416, 'steps': 397, 'loss/train': 6.205374717712402} 08/30/2021 13:18:35 - INFO - __main__ - Step 399: {'lr': 9.95e-05, 'samples': 76608, 'steps': 398, 'loss/train': 5.7176055908203125} 08/30/2021 13:18:35 - INFO - __main__ - Step 400: {'lr': 9.975000000000001e-05, 'samples': 76800, 'steps': 399, 'loss/train': 5.981853485107422} 08/30/2021 13:18:36 - INFO - __main__ - Step 401: {'lr': 0.0001, 'samples': 76992, 'steps': 400, 'loss/train': 5.49164342880249} 08/30/2021 13:18:36 - INFO - __main__ - Step 402: {'lr': 0.00010025000000000001, 'samples': 77184, 'steps': 401, 'loss/train': 4.759962558746338} 08/30/2021 13:18:38 - INFO - __main__ - Step 403: {'lr': 0.0001005, 'samples': 77376, 'steps': 402, 'loss/train': 6.679123878479004} 08/30/2021 13:18:39 - INFO - __main__ - Step 404: {'lr': 0.00010075000000000001, 'samples': 77568, 'steps': 403, 'loss/train': 5.9271674156188965} 08/30/2021 13:18:39 - INFO - __main__ - Step 405: {'lr': 0.000101, 'samples': 77760, 'steps': 404, 'loss/train': 5.913862705230713} 08/30/2021 13:18:40 - INFO - __main__ - Step 406: {'lr': 0.00010125000000000001, 'samples': 77952, 'steps': 405, 'loss/train': 4.9790849685668945} 08/30/2021 13:18:40 - INFO - __main__ - Step 407: {'lr': 0.00010150000000000001, 'samples': 78144, 'steps': 406, 'loss/train': 5.997152328491211} 08/30/2021 13:18:40 - INFO - __main__ - Step 408: {'lr': 0.00010174999999999999, 'samples': 78336, 'steps': 407, 'loss/train': 5.821843147277832} 08/30/2021 13:18:41 - INFO - __main__ - Step 409: {'lr': 0.000102, 'samples': 78528, 'steps': 408, 'loss/train': 6.093254089355469} 08/30/2021 13:18:42 - INFO - __main__ - Step 410: {'lr': 0.00010224999999999999, 'samples': 78720, 'steps': 409, 'loss/train': 7.17864465713501} 08/30/2021 13:18:43 - INFO - __main__ - Step 411: {'lr': 0.0001025, 'samples': 78912, 'steps': 410, 'loss/train': 5.948477745056152} 08/30/2021 13:18:43 - INFO - __main__ - Step 412: {'lr': 0.00010274999999999999, 'samples': 79104, 'steps': 411, 'loss/train': 5.505001544952393} 08/30/2021 13:18:43 - INFO - __main__ - Step 413: {'lr': 0.000103, 'samples': 79296, 'steps': 412, 'loss/train': 5.888233184814453} 08/30/2021 13:18:44 - INFO - __main__ - Step 414: {'lr': 0.00010325, 'samples': 79488, 'steps': 413, 'loss/train': 5.7912116050720215} 08/30/2021 13:18:45 - INFO - __main__ - Step 415: {'lr': 0.0001035, 'samples': 79680, 'steps': 414, 'loss/train': 5.851842403411865} 08/30/2021 13:18:46 - INFO - __main__ - Step 416: {'lr': 0.00010375, 'samples': 79872, 'steps': 415, 'loss/train': 5.67678689956665} 08/30/2021 13:18:46 - INFO - __main__ - Step 417: {'lr': 0.000104, 'samples': 80064, 'steps': 416, 'loss/train': 6.132983684539795} 08/30/2021 13:18:46 - INFO - __main__ - Step 418: {'lr': 0.00010425, 'samples': 80256, 'steps': 417, 'loss/train': 5.8515496253967285} 08/30/2021 13:18:47 - INFO - __main__ - Step 419: {'lr': 0.00010449999999999999, 'samples': 80448, 'steps': 418, 'loss/train': 6.48202657699585} 08/30/2021 13:18:48 - INFO - __main__ - Step 420: {'lr': 0.00010475, 'samples': 80640, 'steps': 419, 'loss/train': 6.2916741371154785} 08/30/2021 13:18:48 - INFO - __main__ - Step 421: {'lr': 0.000105, 'samples': 80832, 'steps': 420, 'loss/train': 5.926718711853027} 08/30/2021 13:18:49 - INFO - __main__ - Step 422: {'lr': 0.00010525, 'samples': 81024, 'steps': 421, 'loss/train': 5.585618019104004} 08/30/2021 13:18:49 - INFO - __main__ - Step 423: {'lr': 0.0001055, 'samples': 81216, 'steps': 422, 'loss/train': 5.546139717102051} 08/30/2021 13:18:49 - INFO - __main__ - Step 424: {'lr': 0.00010575, 'samples': 81408, 'steps': 423, 'loss/train': 6.199115753173828} 08/30/2021 13:18:51 - INFO - __main__ - Step 425: {'lr': 0.000106, 'samples': 81600, 'steps': 424, 'loss/train': 5.3427348136901855} 08/30/2021 13:18:51 - INFO - __main__ - Step 426: {'lr': 0.00010625, 'samples': 81792, 'steps': 425, 'loss/train': 5.438610553741455} 08/30/2021 13:18:52 - INFO - __main__ - Step 427: {'lr': 0.0001065, 'samples': 81984, 'steps': 426, 'loss/train': 6.038686275482178} 08/30/2021 13:18:52 - INFO - __main__ - Step 428: {'lr': 0.00010675, 'samples': 82176, 'steps': 427, 'loss/train': 5.396204471588135} 08/30/2021 13:18:52 - INFO - __main__ - Step 429: {'lr': 0.000107, 'samples': 82368, 'steps': 428, 'loss/train': 5.535378456115723} 08/30/2021 13:18:53 - INFO - __main__ - Step 430: {'lr': 0.00010725, 'samples': 82560, 'steps': 429, 'loss/train': 6.227622985839844} 08/30/2021 13:18:55 - INFO - __main__ - Step 431: {'lr': 0.0001075, 'samples': 82752, 'steps': 430, 'loss/train': 6.117164611816406} 08/30/2021 13:18:55 - INFO - __main__ - Step 432: {'lr': 0.00010775, 'samples': 82944, 'steps': 431, 'loss/train': 6.0254058837890625} 08/30/2021 13:18:56 - INFO - __main__ - Step 433: {'lr': 0.000108, 'samples': 83136, 'steps': 432, 'loss/train': 5.1386590003967285} 08/30/2021 13:18:56 - INFO - __main__ - Step 434: {'lr': 0.00010825, 'samples': 83328, 'steps': 433, 'loss/train': 4.882626056671143} 08/30/2021 13:18:56 - INFO - __main__ - Step 435: {'lr': 0.00010850000000000001, 'samples': 83520, 'steps': 434, 'loss/train': 5.809022903442383} 08/30/2021 13:18:58 - INFO - __main__ - Step 436: {'lr': 0.00010875, 'samples': 83712, 'steps': 435, 'loss/train': 5.087780952453613} 08/30/2021 13:18:59 - INFO - __main__ - Step 437: {'lr': 0.000109, 'samples': 83904, 'steps': 436, 'loss/train': 5.409515380859375} 08/30/2021 13:18:59 - INFO - __main__ - Step 438: {'lr': 0.00010925, 'samples': 84096, 'steps': 437, 'loss/train': 4.946671485900879} 08/30/2021 13:18:59 - INFO - __main__ - Step 439: {'lr': 0.0001095, 'samples': 84288, 'steps': 438, 'loss/train': 4.746728420257568} 08/30/2021 13:19:00 - INFO - __main__ - Step 440: {'lr': 0.00010975, 'samples': 84480, 'steps': 439, 'loss/train': 5.767526626586914} 08/30/2021 13:19:01 - INFO - __main__ - Step 441: {'lr': 0.00011, 'samples': 84672, 'steps': 440, 'loss/train': 6.015324115753174} 08/30/2021 13:19:01 - INFO - __main__ - Step 442: {'lr': 0.00011025, 'samples': 84864, 'steps': 441, 'loss/train': 5.7094011306762695} 08/30/2021 13:19:02 - INFO - __main__ - Step 443: {'lr': 0.0001105, 'samples': 85056, 'steps': 442, 'loss/train': 5.760134696960449} 08/30/2021 13:19:02 - INFO - __main__ - Step 444: {'lr': 0.00011075000000000001, 'samples': 85248, 'steps': 443, 'loss/train': 5.706537246704102} 08/30/2021 13:19:02 - INFO - __main__ - Step 445: {'lr': 0.000111, 'samples': 85440, 'steps': 444, 'loss/train': 4.999929428100586} 08/30/2021 13:19:04 - INFO - __main__ - Step 446: {'lr': 0.00011125000000000001, 'samples': 85632, 'steps': 445, 'loss/train': 4.658752918243408} 08/30/2021 13:19:05 - INFO - __main__ - Step 447: {'lr': 0.0001115, 'samples': 85824, 'steps': 446, 'loss/train': 5.415980815887451} 08/30/2021 13:19:05 - INFO - __main__ - Step 448: {'lr': 0.00011175, 'samples': 86016, 'steps': 447, 'loss/train': 5.274680137634277} 08/30/2021 13:19:05 - INFO - __main__ - Step 449: {'lr': 0.000112, 'samples': 86208, 'steps': 448, 'loss/train': 4.624673366546631} 08/30/2021 13:19:06 - INFO - __main__ - Step 450: {'lr': 0.00011225, 'samples': 86400, 'steps': 449, 'loss/train': 5.0226640701293945} 08/30/2021 13:19:07 - INFO - __main__ - Step 451: {'lr': 0.00011250000000000001, 'samples': 86592, 'steps': 450, 'loss/train': 5.516931533813477} 08/30/2021 13:19:07 - INFO - __main__ - Step 452: {'lr': 0.00011275, 'samples': 86784, 'steps': 451, 'loss/train': 5.60693359375} 08/30/2021 13:19:08 - INFO - __main__ - Step 453: {'lr': 0.00011300000000000001, 'samples': 86976, 'steps': 452, 'loss/train': 5.57399845123291} 08/30/2021 13:19:08 - INFO - __main__ - Step 454: {'lr': 0.00011325, 'samples': 87168, 'steps': 453, 'loss/train': 5.57354211807251} 08/30/2021 13:19:08 - INFO - __main__ - Step 455: {'lr': 0.00011350000000000001, 'samples': 87360, 'steps': 454, 'loss/train': 5.579854965209961} 08/30/2021 13:19:10 - INFO - __main__ - Step 456: {'lr': 0.00011375, 'samples': 87552, 'steps': 455, 'loss/train': 5.586076259613037} 08/30/2021 13:19:10 - INFO - __main__ - Step 457: {'lr': 0.000114, 'samples': 87744, 'steps': 456, 'loss/train': 5.7872233390808105} 08/30/2021 13:19:11 - INFO - __main__ - Step 458: {'lr': 0.00011425000000000001, 'samples': 87936, 'steps': 457, 'loss/train': 5.377703666687012} 08/30/2021 13:19:11 - INFO - __main__ - Step 459: {'lr': 0.0001145, 'samples': 88128, 'steps': 458, 'loss/train': 5.658486366271973} 08/30/2021 13:19:11 - INFO - __main__ - Step 460: {'lr': 0.00011475000000000001, 'samples': 88320, 'steps': 459, 'loss/train': 5.546477794647217} 08/30/2021 13:19:13 - INFO - __main__ - Step 461: {'lr': 0.000115, 'samples': 88512, 'steps': 460, 'loss/train': 6.00485897064209} 08/30/2021 13:19:13 - INFO - __main__ - Step 462: {'lr': 0.00011525000000000001, 'samples': 88704, 'steps': 461, 'loss/train': 5.189422130584717} 08/30/2021 13:19:14 - INFO - __main__ - Step 463: {'lr': 0.0001155, 'samples': 88896, 'steps': 462, 'loss/train': 5.5748162269592285} 08/30/2021 13:19:14 - INFO - __main__ - Step 464: {'lr': 0.00011575000000000001, 'samples': 89088, 'steps': 463, 'loss/train': 6.147246360778809} 08/30/2021 13:19:14 - INFO - __main__ - Step 465: {'lr': 0.00011600000000000001, 'samples': 89280, 'steps': 464, 'loss/train': 5.877396583557129} 08/30/2021 13:19:16 - INFO - __main__ - Step 466: {'lr': 0.00011625, 'samples': 89472, 'steps': 465, 'loss/train': 5.3202362060546875} 08/30/2021 13:19:16 - INFO - __main__ - Step 467: {'lr': 0.00011650000000000001, 'samples': 89664, 'steps': 466, 'loss/train': 5.167083263397217} 08/30/2021 13:19:17 - INFO - __main__ - Step 468: {'lr': 0.00011675, 'samples': 89856, 'steps': 467, 'loss/train': 6.410694122314453} 08/30/2021 13:19:17 - INFO - __main__ - Step 469: {'lr': 0.00011700000000000001, 'samples': 90048, 'steps': 468, 'loss/train': 6.226719856262207} 08/30/2021 13:19:17 - INFO - __main__ - Step 470: {'lr': 0.00011724999999999999, 'samples': 90240, 'steps': 469, 'loss/train': 5.951915264129639} 08/30/2021 13:19:19 - INFO - __main__ - Step 471: {'lr': 0.0001175, 'samples': 90432, 'steps': 470, 'loss/train': 5.894048690795898} 08/30/2021 13:19:20 - INFO - __main__ - Step 472: {'lr': 0.00011775, 'samples': 90624, 'steps': 471, 'loss/train': 5.099086761474609} 08/30/2021 13:19:20 - INFO - __main__ - Step 473: {'lr': 0.000118, 'samples': 90816, 'steps': 472, 'loss/train': 5.429386615753174} 08/30/2021 13:19:20 - INFO - __main__ - Step 474: {'lr': 0.00011825, 'samples': 91008, 'steps': 473, 'loss/train': 5.523043155670166} 08/30/2021 13:19:21 - INFO - __main__ - Step 475: {'lr': 0.0001185, 'samples': 91200, 'steps': 474, 'loss/train': 5.883626461029053} 08/30/2021 13:19:22 - INFO - __main__ - Step 476: {'lr': 0.00011875, 'samples': 91392, 'steps': 475, 'loss/train': 5.555183410644531} 08/30/2021 13:19:23 - INFO - __main__ - Step 477: {'lr': 0.00011899999999999999, 'samples': 91584, 'steps': 476, 'loss/train': 5.388443470001221} 08/30/2021 13:19:23 - INFO - __main__ - Step 478: {'lr': 0.00011925, 'samples': 91776, 'steps': 477, 'loss/train': 9.009052276611328} 08/30/2021 13:19:24 - INFO - __main__ - Step 479: {'lr': 0.00011949999999999999, 'samples': 91968, 'steps': 478, 'loss/train': 7.975252151489258} 08/30/2021 13:19:24 - INFO - __main__ - Step 480: {'lr': 0.00011975, 'samples': 92160, 'steps': 479, 'loss/train': 6.8069963455200195} 08/30/2021 13:19:24 - INFO - __main__ - Step 481: {'lr': 0.00012, 'samples': 92352, 'steps': 480, 'loss/train': 5.477241516113281} 08/30/2021 13:19:27 - INFO - __main__ - Step 482: {'lr': 0.00012025, 'samples': 92544, 'steps': 481, 'loss/train': 4.654419898986816} 08/30/2021 13:19:27 - INFO - __main__ - Step 483: {'lr': 0.0001205, 'samples': 92736, 'steps': 482, 'loss/train': 5.462592124938965} 08/30/2021 13:19:28 - INFO - __main__ - Step 484: {'lr': 0.00012075, 'samples': 92928, 'steps': 483, 'loss/train': 6.125245571136475} 08/30/2021 13:19:28 - INFO - __main__ - Step 485: {'lr': 0.000121, 'samples': 93120, 'steps': 484, 'loss/train': 5.8257293701171875} 08/30/2021 13:19:28 - INFO - __main__ - Step 486: {'lr': 0.00012124999999999999, 'samples': 93312, 'steps': 485, 'loss/train': 6.578179836273193} 08/30/2021 13:19:29 - INFO - __main__ - Step 487: {'lr': 0.0001215, 'samples': 93504, 'steps': 486, 'loss/train': 5.597835063934326} 08/30/2021 13:19:30 - INFO - __main__ - Step 488: {'lr': 0.00012175, 'samples': 93696, 'steps': 487, 'loss/train': 5.9039740562438965} 08/30/2021 13:19:31 - INFO - __main__ - Step 489: {'lr': 0.000122, 'samples': 93888, 'steps': 488, 'loss/train': 5.389415264129639} 08/30/2021 13:19:31 - INFO - __main__ - Step 490: {'lr': 0.00012225, 'samples': 94080, 'steps': 489, 'loss/train': 6.134588241577148} 08/30/2021 13:19:31 - INFO - __main__ - Step 491: {'lr': 0.0001225, 'samples': 94272, 'steps': 490, 'loss/train': 5.465774059295654} 08/30/2021 13:19:32 - INFO - __main__ - Step 492: {'lr': 0.00012275, 'samples': 94464, 'steps': 491, 'loss/train': 5.640119552612305} 08/30/2021 13:19:32 - INFO - __main__ - Step 493: {'lr': 0.000123, 'samples': 94656, 'steps': 492, 'loss/train': 4.687599182128906} 08/30/2021 13:19:33 - INFO - __main__ - Step 494: {'lr': 0.00012325000000000001, 'samples': 94848, 'steps': 493, 'loss/train': 5.525679588317871} 08/30/2021 13:19:34 - INFO - __main__ - Step 495: {'lr': 0.0001235, 'samples': 95040, 'steps': 494, 'loss/train': 5.946816921234131} 08/30/2021 13:19:34 - INFO - __main__ - Step 496: {'lr': 0.00012375, 'samples': 95232, 'steps': 495, 'loss/train': 5.446334362030029} 08/30/2021 13:19:35 - INFO - __main__ - Step 497: {'lr': 0.000124, 'samples': 95424, 'steps': 496, 'loss/train': 5.384819507598877} 08/30/2021 13:19:35 - INFO - __main__ - Step 498: {'lr': 0.00012425, 'samples': 95616, 'steps': 497, 'loss/train': 5.5549845695495605} 08/30/2021 13:19:36 - INFO - __main__ - Step 499: {'lr': 0.0001245, 'samples': 95808, 'steps': 498, 'loss/train': 5.564133644104004} 08/30/2021 13:19:37 - INFO - __main__ - Step 500: {'lr': 0.00012475, 'samples': 96000, 'steps': 499, 'loss/train': 5.740269184112549} 08/30/2021 13:19:37 - INFO - __main__ - Step 501: {'lr': 0.000125, 'samples': 96192, 'steps': 500, 'loss/train': 5.81393575668335} 08/30/2021 13:19:38 - INFO - __main__ - Step 502: {'lr': 0.00012525, 'samples': 96384, 'steps': 501, 'loss/train': 6.138937473297119} 08/30/2021 13:19:38 - INFO - __main__ - Step 503: {'lr': 0.00012550000000000001, 'samples': 96576, 'steps': 502, 'loss/train': 5.4254631996154785} 08/30/2021 13:19:39 - INFO - __main__ - Step 504: {'lr': 0.00012575, 'samples': 96768, 'steps': 503, 'loss/train': 6.424824237823486} 08/30/2021 13:19:40 - INFO - __main__ - Step 505: {'lr': 0.000126, 'samples': 96960, 'steps': 504, 'loss/train': 5.346781253814697} 08/30/2021 13:19:40 - INFO - __main__ - Step 506: {'lr': 0.00012625, 'samples': 97152, 'steps': 505, 'loss/train': 5.492609024047852} 08/30/2021 13:19:41 - INFO - __main__ - Step 507: {'lr': 0.0001265, 'samples': 97344, 'steps': 506, 'loss/train': 5.778714656829834} 08/30/2021 13:19:41 - INFO - __main__ - Step 508: {'lr': 0.00012675, 'samples': 97536, 'steps': 507, 'loss/train': 5.443634510040283} 08/30/2021 13:19:43 - INFO - __main__ - Step 509: {'lr': 0.000127, 'samples': 97728, 'steps': 508, 'loss/train': 3.9383697509765625} 08/30/2021 13:19:43 - INFO - __main__ - Step 510: {'lr': 0.00012725, 'samples': 97920, 'steps': 509, 'loss/train': 5.67879056930542} 08/30/2021 13:19:43 - INFO - __main__ - Step 511: {'lr': 0.0001275, 'samples': 98112, 'steps': 510, 'loss/train': 5.304076671600342} 08/30/2021 13:19:44 - INFO - __main__ - Step 512: {'lr': 0.00012775000000000002, 'samples': 98304, 'steps': 511, 'loss/train': 5.341429233551025} 08/30/2021 13:19:44 - INFO - __main__ - Step 513: {'lr': 0.000128, 'samples': 98496, 'steps': 512, 'loss/train': 5.897983074188232} 08/30/2021 13:19:44 - INFO - __main__ - Step 514: {'lr': 0.00012825, 'samples': 98688, 'steps': 513, 'loss/train': 5.628521919250488} 08/30/2021 13:19:46 - INFO - __main__ - Step 515: {'lr': 0.0001285, 'samples': 98880, 'steps': 514, 'loss/train': 5.3900322914123535} 08/30/2021 13:19:46 - INFO - __main__ - Step 516: {'lr': 0.00012875, 'samples': 99072, 'steps': 515, 'loss/train': 5.59366512298584} 08/30/2021 13:19:47 - INFO - __main__ - Step 517: {'lr': 0.00012900000000000002, 'samples': 99264, 'steps': 516, 'loss/train': 5.774766445159912} 08/30/2021 13:19:47 - INFO - __main__ - Step 518: {'lr': 0.00012925, 'samples': 99456, 'steps': 517, 'loss/train': 5.637266635894775} 08/30/2021 13:19:47 - INFO - __main__ - Step 519: {'lr': 0.0001295, 'samples': 99648, 'steps': 518, 'loss/train': 5.623018264770508} 08/30/2021 13:19:49 - INFO - __main__ - Step 520: {'lr': 0.00012975, 'samples': 99840, 'steps': 519, 'loss/train': 5.417008876800537} 08/30/2021 13:19:49 - INFO - __main__ - Step 521: {'lr': 0.00013000000000000002, 'samples': 100032, 'steps': 520, 'loss/train': 7.079473972320557} 08/30/2021 13:19:50 - INFO - __main__ - Step 522: {'lr': 0.00013025, 'samples': 100224, 'steps': 521, 'loss/train': 5.893174648284912} 08/30/2021 13:19:50 - INFO - __main__ - Step 523: {'lr': 0.0001305, 'samples': 100416, 'steps': 522, 'loss/train': 5.409637451171875} 08/30/2021 13:19:50 - INFO - __main__ - Step 524: {'lr': 0.00013075, 'samples': 100608, 'steps': 523, 'loss/train': 5.7304463386535645} 08/30/2021 13:19:52 - INFO - __main__ - Step 525: {'lr': 0.000131, 'samples': 100800, 'steps': 524, 'loss/train': 5.777679920196533} 08/30/2021 13:19:53 - INFO - __main__ - Step 526: {'lr': 0.00013125000000000002, 'samples': 100992, 'steps': 525, 'loss/train': 5.652060508728027} 08/30/2021 13:19:53 - INFO - __main__ - Step 527: {'lr': 0.0001315, 'samples': 101184, 'steps': 526, 'loss/train': 5.265826225280762} 08/30/2021 13:19:53 - INFO - __main__ - Step 528: {'lr': 0.00013175, 'samples': 101376, 'steps': 527, 'loss/train': 5.488304615020752} 08/30/2021 13:19:54 - INFO - __main__ - Step 529: {'lr': 0.000132, 'samples': 101568, 'steps': 528, 'loss/train': 5.802730560302734} 08/30/2021 13:19:55 - INFO - __main__ - Step 530: {'lr': 0.00013225000000000002, 'samples': 101760, 'steps': 529, 'loss/train': 4.198696136474609} 08/30/2021 13:19:56 - INFO - __main__ - Step 531: {'lr': 0.00013250000000000002, 'samples': 101952, 'steps': 530, 'loss/train': 5.73695707321167} 08/30/2021 13:19:56 - INFO - __main__ - Step 532: {'lr': 0.00013275, 'samples': 102144, 'steps': 531, 'loss/train': 6.057995319366455} 08/30/2021 13:19:56 - INFO - __main__ - Step 533: {'lr': 0.000133, 'samples': 102336, 'steps': 532, 'loss/train': 5.944148063659668} 08/30/2021 13:19:57 - INFO - __main__ - Step 534: {'lr': 0.00013325, 'samples': 102528, 'steps': 533, 'loss/train': 5.650229454040527} 08/30/2021 13:19:57 - INFO - __main__ - Step 535: {'lr': 0.00013350000000000002, 'samples': 102720, 'steps': 534, 'loss/train': 5.595287322998047} 08/30/2021 13:19:59 - INFO - __main__ - Step 536: {'lr': 0.00013375, 'samples': 102912, 'steps': 535, 'loss/train': 5.86622953414917} 08/30/2021 13:19:59 - INFO - __main__ - Step 537: {'lr': 0.000134, 'samples': 103104, 'steps': 536, 'loss/train': 5.728094100952148} 08/30/2021 13:20:00 - INFO - __main__ - Step 538: {'lr': 0.00013425, 'samples': 103296, 'steps': 537, 'loss/train': 5.270711421966553} 08/30/2021 13:20:00 - INFO - __main__ - Step 539: {'lr': 0.00013450000000000002, 'samples': 103488, 'steps': 538, 'loss/train': 5.468379497528076} 08/30/2021 13:20:00 - INFO - __main__ - Step 540: {'lr': 0.00013475000000000002, 'samples': 103680, 'steps': 539, 'loss/train': 5.228604316711426} 08/30/2021 13:20:02 - INFO - __main__ - Step 541: {'lr': 0.000135, 'samples': 103872, 'steps': 540, 'loss/train': 5.395594120025635} 08/30/2021 13:20:02 - INFO - __main__ - Step 542: {'lr': 0.00013525, 'samples': 104064, 'steps': 541, 'loss/train': 5.566400051116943} 08/30/2021 13:20:03 - INFO - __main__ - Step 543: {'lr': 0.00013550000000000001, 'samples': 104256, 'steps': 542, 'loss/train': 5.838968276977539} 08/30/2021 13:20:03 - INFO - __main__ - Step 544: {'lr': 0.00013575000000000002, 'samples': 104448, 'steps': 543, 'loss/train': 5.202871322631836} 08/30/2021 13:20:03 - INFO - __main__ - Step 545: {'lr': 0.00013600000000000003, 'samples': 104640, 'steps': 544, 'loss/train': 5.848567485809326} 08/30/2021 13:20:05 - INFO - __main__ - Step 546: {'lr': 0.00013625, 'samples': 104832, 'steps': 545, 'loss/train': 6.2512526512146} 08/30/2021 13:20:06 - INFO - __main__ - Step 547: {'lr': 0.0001365, 'samples': 105024, 'steps': 546, 'loss/train': 5.530820846557617} 08/30/2021 13:20:06 - INFO - __main__ - Step 548: {'lr': 0.00013675000000000002, 'samples': 105216, 'steps': 547, 'loss/train': 3.847254753112793} 08/30/2021 13:20:06 - INFO - __main__ - Step 549: {'lr': 0.00013700000000000002, 'samples': 105408, 'steps': 548, 'loss/train': 4.007019519805908} 08/30/2021 13:20:07 - INFO - __main__ - Step 550: {'lr': 0.00013725, 'samples': 105600, 'steps': 549, 'loss/train': 3.8318333625793457} 08/30/2021 13:20:07 - INFO - __main__ - Step 551: {'lr': 0.0001375, 'samples': 105792, 'steps': 550, 'loss/train': 5.498006820678711} 08/30/2021 13:20:09 - INFO - __main__ - Step 552: {'lr': 0.00013775000000000001, 'samples': 105984, 'steps': 551, 'loss/train': 4.983112812042236} 08/30/2021 13:20:09 - INFO - __main__ - Step 553: {'lr': 0.00013800000000000002, 'samples': 106176, 'steps': 552, 'loss/train': 5.6042704582214355} 08/30/2021 13:20:09 - INFO - __main__ - Step 554: {'lr': 0.00013825000000000003, 'samples': 106368, 'steps': 553, 'loss/train': 5.392212390899658} 08/30/2021 13:20:10 - INFO - __main__ - Step 555: {'lr': 0.0001385, 'samples': 106560, 'steps': 554, 'loss/train': 5.752504348754883} 08/30/2021 13:20:10 - INFO - __main__ - Step 556: {'lr': 0.00013875, 'samples': 106752, 'steps': 555, 'loss/train': 4.8399810791015625} 08/30/2021 13:20:12 - INFO - __main__ - Step 557: {'lr': 0.00013900000000000002, 'samples': 106944, 'steps': 556, 'loss/train': 5.256772041320801} 08/30/2021 13:20:12 - INFO - __main__ - Step 558: {'lr': 0.00013925000000000002, 'samples': 107136, 'steps': 557, 'loss/train': 5.493489742279053} 08/30/2021 13:20:12 - INFO - __main__ - Step 559: {'lr': 0.0001395, 'samples': 107328, 'steps': 558, 'loss/train': 5.2617669105529785} 08/30/2021 13:20:13 - INFO - __main__ - Step 560: {'lr': 0.00013975, 'samples': 107520, 'steps': 559, 'loss/train': 5.1201863288879395} 08/30/2021 13:20:13 - INFO - __main__ - Step 561: {'lr': 0.00014000000000000001, 'samples': 107712, 'steps': 560, 'loss/train': 5.30458927154541} 08/30/2021 13:20:15 - INFO - __main__ - Step 562: {'lr': 0.00014025000000000002, 'samples': 107904, 'steps': 561, 'loss/train': 5.496264457702637} 08/30/2021 13:20:15 - INFO - __main__ - Step 563: {'lr': 0.00014050000000000003, 'samples': 108096, 'steps': 562, 'loss/train': 5.537848949432373} 08/30/2021 13:20:15 - INFO - __main__ - Step 564: {'lr': 0.00014074999999999998, 'samples': 108288, 'steps': 563, 'loss/train': 5.250120162963867} 08/30/2021 13:20:16 - INFO - __main__ - Step 565: {'lr': 0.00014099999999999998, 'samples': 108480, 'steps': 564, 'loss/train': 5.629787445068359} 08/30/2021 13:20:16 - INFO - __main__ - Step 566: {'lr': 0.00014125, 'samples': 108672, 'steps': 565, 'loss/train': 5.242862224578857} 08/30/2021 13:20:18 - INFO - __main__ - Step 567: {'lr': 0.0001415, 'samples': 108864, 'steps': 566, 'loss/train': 5.9160332679748535} 08/30/2021 13:20:18 - INFO - __main__ - Step 568: {'lr': 0.00014175, 'samples': 109056, 'steps': 567, 'loss/train': 6.136992454528809} 08/30/2021 13:20:18 - INFO - __main__ - Step 569: {'lr': 0.00014199999999999998, 'samples': 109248, 'steps': 568, 'loss/train': 4.711137771606445} 08/30/2021 13:20:19 - INFO - __main__ - Step 570: {'lr': 0.00014225, 'samples': 109440, 'steps': 569, 'loss/train': 5.519400596618652} 08/30/2021 13:20:19 - INFO - __main__ - Step 571: {'lr': 0.0001425, 'samples': 109632, 'steps': 570, 'loss/train': 5.262238502502441} 08/30/2021 13:20:20 - INFO - __main__ - Step 572: {'lr': 0.00014275, 'samples': 109824, 'steps': 571, 'loss/train': 4.25198221206665} 08/30/2021 13:20:21 - INFO - __main__ - Step 573: {'lr': 0.00014299999999999998, 'samples': 110016, 'steps': 572, 'loss/train': 5.467993259429932} 08/30/2021 13:20:21 - INFO - __main__ - Step 574: {'lr': 0.00014324999999999999, 'samples': 110208, 'steps': 573, 'loss/train': 6.125296592712402} 08/30/2021 13:20:22 - INFO - __main__ - Step 575: {'lr': 0.0001435, 'samples': 110400, 'steps': 574, 'loss/train': 5.636240005493164} 08/30/2021 13:20:22 - INFO - __main__ - Step 576: {'lr': 0.00014375, 'samples': 110592, 'steps': 575, 'loss/train': 5.511364459991455} 08/30/2021 13:20:24 - INFO - __main__ - Step 577: {'lr': 0.000144, 'samples': 110784, 'steps': 576, 'loss/train': 5.202625751495361} 08/30/2021 13:20:24 - INFO - __main__ - Step 578: {'lr': 0.00014424999999999998, 'samples': 110976, 'steps': 577, 'loss/train': 5.799747943878174} 08/30/2021 13:20:24 - INFO - __main__ - Step 579: {'lr': 0.0001445, 'samples': 111168, 'steps': 578, 'loss/train': 5.501727104187012} 08/30/2021 13:20:25 - INFO - __main__ - Step 580: {'lr': 0.00014475, 'samples': 111360, 'steps': 579, 'loss/train': 6.1024370193481445} 08/30/2021 13:20:25 - INFO - __main__ - Step 581: {'lr': 0.000145, 'samples': 111552, 'steps': 580, 'loss/train': 5.24338436126709} 08/30/2021 13:20:25 - INFO - __main__ - Step 582: {'lr': 0.00014524999999999998, 'samples': 111744, 'steps': 581, 'loss/train': 5.631160259246826} 08/30/2021 13:20:27 - INFO - __main__ - Step 583: {'lr': 0.00014549999999999999, 'samples': 111936, 'steps': 582, 'loss/train': 5.755254745483398} 08/30/2021 13:20:27 - INFO - __main__ - Step 584: {'lr': 0.00014575, 'samples': 112128, 'steps': 583, 'loss/train': 5.443774223327637} 08/30/2021 13:20:28 - INFO - __main__ - Step 585: {'lr': 0.000146, 'samples': 112320, 'steps': 584, 'loss/train': 5.5379638671875} 08/30/2021 13:20:28 - INFO - __main__ - Step 586: {'lr': 0.00014625, 'samples': 112512, 'steps': 585, 'loss/train': 3.491403818130493} 08/30/2021 13:20:28 - INFO - __main__ - Step 587: {'lr': 0.00014649999999999998, 'samples': 112704, 'steps': 586, 'loss/train': 5.373976230621338} 08/30/2021 13:20:30 - INFO - __main__ - Step 588: {'lr': 0.00014675, 'samples': 112896, 'steps': 587, 'loss/train': 5.232706546783447} 08/30/2021 13:20:30 - INFO - __main__ - Step 589: {'lr': 0.000147, 'samples': 113088, 'steps': 588, 'loss/train': 5.442381858825684} 08/30/2021 13:20:31 - INFO - __main__ - Step 590: {'lr': 0.00014725, 'samples': 113280, 'steps': 589, 'loss/train': 5.538836479187012} 08/30/2021 13:20:31 - INFO - __main__ - Step 591: {'lr': 0.0001475, 'samples': 113472, 'steps': 590, 'loss/train': 5.548551082611084} 08/30/2021 13:20:31 - INFO - __main__ - Step 592: {'lr': 0.00014774999999999999, 'samples': 113664, 'steps': 591, 'loss/train': 4.918911933898926} 08/30/2021 13:20:33 - INFO - __main__ - Step 593: {'lr': 0.000148, 'samples': 113856, 'steps': 592, 'loss/train': 5.318609237670898} 08/30/2021 13:20:34 - INFO - __main__ - Step 594: {'lr': 0.00014825, 'samples': 114048, 'steps': 593, 'loss/train': 4.92004919052124} 08/30/2021 13:20:34 - INFO - __main__ - Step 595: {'lr': 0.0001485, 'samples': 114240, 'steps': 594, 'loss/train': 4.587899684906006} 08/30/2021 13:20:35 - INFO - __main__ - Step 596: {'lr': 0.00014874999999999998, 'samples': 114432, 'steps': 595, 'loss/train': 5.18981409072876} 08/30/2021 13:20:35 - INFO - __main__ - Step 597: {'lr': 0.000149, 'samples': 114624, 'steps': 596, 'loss/train': 5.675904273986816} 08/30/2021 13:20:36 - INFO - __main__ - Step 598: {'lr': 0.00014925, 'samples': 114816, 'steps': 597, 'loss/train': 4.244988441467285} 08/30/2021 13:20:37 - INFO - __main__ - Step 599: {'lr': 0.0001495, 'samples': 115008, 'steps': 598, 'loss/train': 5.155581474304199} 08/30/2021 13:20:37 - INFO - __main__ - Step 600: {'lr': 0.00014975, 'samples': 115200, 'steps': 599, 'loss/train': 5.592281818389893} 08/30/2021 13:20:38 - INFO - __main__ - Step 601: {'lr': 0.00015, 'samples': 115392, 'steps': 600, 'loss/train': 5.556156158447266} 08/30/2021 13:20:38 - INFO - __main__ - Step 602: {'lr': 0.00015025, 'samples': 115584, 'steps': 601, 'loss/train': 5.371763706207275} 08/30/2021 13:20:38 - INFO - __main__ - Step 603: {'lr': 0.0001505, 'samples': 115776, 'steps': 602, 'loss/train': 5.190732002258301} 08/30/2021 13:20:40 - INFO - __main__ - Step 604: {'lr': 0.00015075, 'samples': 115968, 'steps': 603, 'loss/train': 5.801718235015869} 08/30/2021 13:20:40 - INFO - __main__ - Step 605: {'lr': 0.000151, 'samples': 116160, 'steps': 604, 'loss/train': 4.600075721740723} 08/30/2021 13:20:41 - INFO - __main__ - Step 606: {'lr': 0.00015125, 'samples': 116352, 'steps': 605, 'loss/train': 5.391104698181152} 08/30/2021 13:20:41 - INFO - __main__ - Step 607: {'lr': 0.0001515, 'samples': 116544, 'steps': 606, 'loss/train': 5.737253665924072} 08/30/2021 13:20:41 - INFO - __main__ - Step 608: {'lr': 0.00015175, 'samples': 116736, 'steps': 607, 'loss/train': 6.661869525909424} 08/30/2021 13:20:43 - INFO - __main__ - Step 609: {'lr': 0.000152, 'samples': 116928, 'steps': 608, 'loss/train': 5.0190935134887695} 08/30/2021 13:20:43 - INFO - __main__ - Step 610: {'lr': 0.00015225, 'samples': 117120, 'steps': 609, 'loss/train': 5.521247863769531} 08/30/2021 13:20:43 - INFO - __main__ - Step 611: {'lr': 0.0001525, 'samples': 117312, 'steps': 610, 'loss/train': 5.56842041015625} 08/30/2021 13:20:44 - INFO - __main__ - Step 612: {'lr': 0.00015275, 'samples': 117504, 'steps': 611, 'loss/train': 5.202230453491211} 08/30/2021 13:20:44 - INFO - __main__ - Step 613: {'lr': 0.000153, 'samples': 117696, 'steps': 612, 'loss/train': 5.65955114364624} 08/30/2021 13:20:46 - INFO - __main__ - Step 614: {'lr': 0.00015325, 'samples': 117888, 'steps': 613, 'loss/train': 5.5583577156066895} 08/30/2021 13:20:46 - INFO - __main__ - Step 615: {'lr': 0.0001535, 'samples': 118080, 'steps': 614, 'loss/train': 5.10887336730957} 08/30/2021 13:20:46 - INFO - __main__ - Step 616: {'lr': 0.00015375, 'samples': 118272, 'steps': 615, 'loss/train': 5.222726345062256} 08/30/2021 13:20:47 - INFO - __main__ - Step 617: {'lr': 0.000154, 'samples': 118464, 'steps': 616, 'loss/train': 5.619663715362549} 08/30/2021 13:20:47 - INFO - __main__ - Step 618: {'lr': 0.00015425, 'samples': 118656, 'steps': 617, 'loss/train': 5.197406768798828} 08/30/2021 13:20:49 - INFO - __main__ - Step 619: {'lr': 0.00015450000000000001, 'samples': 118848, 'steps': 618, 'loss/train': 5.745248794555664} 08/30/2021 13:20:49 - INFO - __main__ - Step 620: {'lr': 0.00015475, 'samples': 119040, 'steps': 619, 'loss/train': 5.443110466003418} 08/30/2021 13:20:49 - INFO - __main__ - Step 621: {'lr': 0.000155, 'samples': 119232, 'steps': 620, 'loss/train': 5.6602911949157715} 08/30/2021 13:20:50 - INFO - __main__ - Step 622: {'lr': 0.00015525, 'samples': 119424, 'steps': 621, 'loss/train': 5.558720588684082} 08/30/2021 13:20:50 - INFO - __main__ - Step 623: {'lr': 0.0001555, 'samples': 119616, 'steps': 622, 'loss/train': 5.768640995025635} 08/30/2021 13:20:52 - INFO - __main__ - Step 624: {'lr': 0.00015575, 'samples': 119808, 'steps': 623, 'loss/train': 5.520753860473633} 08/30/2021 13:20:52 - INFO - __main__ - Step 625: {'lr': 0.000156, 'samples': 120000, 'steps': 624, 'loss/train': 4.979221820831299} 08/30/2021 13:20:53 - INFO - __main__ - Step 626: {'lr': 0.00015625, 'samples': 120192, 'steps': 625, 'loss/train': 4.893407821655273} 08/30/2021 13:20:53 - INFO - __main__ - Step 627: {'lr': 0.0001565, 'samples': 120384, 'steps': 626, 'loss/train': 3.3585562705993652} 08/30/2021 13:20:53 - INFO - __main__ - Step 628: {'lr': 0.00015675000000000002, 'samples': 120576, 'steps': 627, 'loss/train': 4.998554229736328} 08/30/2021 13:20:54 - INFO - __main__ - Step 629: {'lr': 0.000157, 'samples': 120768, 'steps': 628, 'loss/train': 7.1863813400268555} 08/30/2021 13:20:55 - INFO - __main__ - Step 630: {'lr': 0.00015725, 'samples': 120960, 'steps': 629, 'loss/train': 5.3697638511657715} 08/30/2021 13:20:56 - INFO - __main__ - Step 631: {'lr': 0.0001575, 'samples': 121152, 'steps': 630, 'loss/train': 5.502453804016113} 08/30/2021 13:20:56 - INFO - __main__ - Step 632: {'lr': 0.00015775, 'samples': 121344, 'steps': 631, 'loss/train': 5.311975002288818} 08/30/2021 13:20:56 - INFO - __main__ - Step 633: {'lr': 0.000158, 'samples': 121536, 'steps': 632, 'loss/train': 2.156040668487549} 08/30/2021 13:20:57 - INFO - __main__ - Step 634: {'lr': 0.00015825, 'samples': 121728, 'steps': 633, 'loss/train': 5.429723739624023} 08/30/2021 13:20:58 - INFO - __main__ - Step 635: {'lr': 0.0001585, 'samples': 121920, 'steps': 634, 'loss/train': 5.562890529632568} 08/30/2021 13:20:59 - INFO - __main__ - Step 636: {'lr': 0.00015875, 'samples': 122112, 'steps': 635, 'loss/train': 6.574239253997803} 08/30/2021 13:20:59 - INFO - __main__ - Step 637: {'lr': 0.00015900000000000002, 'samples': 122304, 'steps': 636, 'loss/train': 5.023447513580322} 08/30/2021 13:20:59 - INFO - __main__ - Step 638: {'lr': 0.00015925, 'samples': 122496, 'steps': 637, 'loss/train': 5.247769832611084} 08/30/2021 13:21:00 - INFO - __main__ - Step 639: {'lr': 0.0001595, 'samples': 122688, 'steps': 638, 'loss/train': 5.273298263549805} 08/30/2021 13:21:01 - INFO - __main__ - Step 640: {'lr': 0.00015975, 'samples': 122880, 'steps': 639, 'loss/train': 5.828912258148193} 08/30/2021 13:21:02 - INFO - __main__ - Step 641: {'lr': 0.00016, 'samples': 123072, 'steps': 640, 'loss/train': 5.328188419342041} 08/30/2021 13:21:02 - INFO - __main__ - Step 642: {'lr': 0.00016025000000000002, 'samples': 123264, 'steps': 641, 'loss/train': 5.148167133331299} 08/30/2021 13:21:03 - INFO - __main__ - Step 643: {'lr': 0.0001605, 'samples': 123456, 'steps': 642, 'loss/train': 5.197710037231445} 08/30/2021 13:21:03 - INFO - __main__ - Step 644: {'lr': 0.00016075, 'samples': 123648, 'steps': 643, 'loss/train': 6.053573131561279} 08/30/2021 13:21:03 - INFO - __main__ - Step 645: {'lr': 0.000161, 'samples': 123840, 'steps': 644, 'loss/train': 5.226877689361572} 08/30/2021 13:21:05 - INFO - __main__ - Step 646: {'lr': 0.00016125000000000002, 'samples': 124032, 'steps': 645, 'loss/train': 5.793482780456543} 08/30/2021 13:21:06 - INFO - __main__ - Step 647: {'lr': 0.0001615, 'samples': 124224, 'steps': 646, 'loss/train': 5.376224517822266} 08/30/2021 13:21:06 - INFO - __main__ - Step 648: {'lr': 0.00016175, 'samples': 124416, 'steps': 647, 'loss/train': 4.9352521896362305} 08/30/2021 13:21:06 - INFO - __main__ - Step 649: {'lr': 0.000162, 'samples': 124608, 'steps': 648, 'loss/train': 5.265020370483398} 08/30/2021 13:21:07 - INFO - __main__ - Step 650: {'lr': 0.00016225000000000001, 'samples': 124800, 'steps': 649, 'loss/train': 4.683105945587158} 08/30/2021 13:21:09 - INFO - __main__ - Step 651: {'lr': 0.00016250000000000002, 'samples': 124992, 'steps': 650, 'loss/train': 5.088352203369141} 08/30/2021 13:21:09 - INFO - __main__ - Step 652: {'lr': 0.00016275, 'samples': 125184, 'steps': 651, 'loss/train': 5.291248798370361} 08/30/2021 13:21:09 - INFO - __main__ - Step 653: {'lr': 0.000163, 'samples': 125376, 'steps': 652, 'loss/train': 5.060006141662598} 08/30/2021 13:21:10 - INFO - __main__ - Step 654: {'lr': 0.00016325, 'samples': 125568, 'steps': 653, 'loss/train': 5.836855411529541} 08/30/2021 13:21:10 - INFO - __main__ - Step 655: {'lr': 0.00016350000000000002, 'samples': 125760, 'steps': 654, 'loss/train': 5.828429222106934} 08/30/2021 13:21:10 - INFO - __main__ - Step 656: {'lr': 0.00016375000000000002, 'samples': 125952, 'steps': 655, 'loss/train': 4.9753737449646} 08/30/2021 13:21:12 - INFO - __main__ - Step 657: {'lr': 0.000164, 'samples': 126144, 'steps': 656, 'loss/train': 4.924708843231201} 08/30/2021 13:21:12 - INFO - __main__ - Step 658: {'lr': 0.00016425, 'samples': 126336, 'steps': 657, 'loss/train': 5.880825519561768} 08/30/2021 13:21:13 - INFO - __main__ - Step 659: {'lr': 0.00016450000000000001, 'samples': 126528, 'steps': 658, 'loss/train': 4.768339157104492} 08/30/2021 13:21:13 - INFO - __main__ - Step 660: {'lr': 0.00016475000000000002, 'samples': 126720, 'steps': 659, 'loss/train': 5.182678699493408} 08/30/2021 13:21:13 - INFO - __main__ - Step 661: {'lr': 0.000165, 'samples': 126912, 'steps': 660, 'loss/train': 4.780258655548096} 08/30/2021 13:21:15 - INFO - __main__ - Step 662: {'lr': 0.00016525, 'samples': 127104, 'steps': 661, 'loss/train': 5.283553123474121} 08/30/2021 13:21:16 - INFO - __main__ - Step 663: {'lr': 0.0001655, 'samples': 127296, 'steps': 662, 'loss/train': 5.456881046295166} 08/30/2021 13:21:16 - INFO - __main__ - Step 664: {'lr': 0.00016575000000000002, 'samples': 127488, 'steps': 663, 'loss/train': 5.081045627593994} 08/30/2021 13:21:16 - INFO - __main__ - Step 665: {'lr': 0.00016600000000000002, 'samples': 127680, 'steps': 664, 'loss/train': 4.800060749053955} 08/30/2021 13:21:17 - INFO - __main__ - Step 666: {'lr': 0.00016625, 'samples': 127872, 'steps': 665, 'loss/train': 5.490692615509033} 08/30/2021 13:21:17 - INFO - __main__ - Step 667: {'lr': 0.0001665, 'samples': 128064, 'steps': 666, 'loss/train': 4.857069492340088} 08/30/2021 13:21:18 - INFO - __main__ - Step 668: {'lr': 0.00016675000000000001, 'samples': 128256, 'steps': 667, 'loss/train': 5.199826717376709} 08/30/2021 13:21:19 - INFO - __main__ - Step 669: {'lr': 0.00016700000000000002, 'samples': 128448, 'steps': 668, 'loss/train': 5.700835227966309} 08/30/2021 13:21:19 - INFO - __main__ - Step 670: {'lr': 0.00016725000000000003, 'samples': 128640, 'steps': 669, 'loss/train': 5.933552265167236} 08/30/2021 13:21:20 - INFO - __main__ - Step 671: {'lr': 0.0001675, 'samples': 128832, 'steps': 670, 'loss/train': 5.337162971496582} 08/30/2021 13:21:20 - INFO - __main__ - Step 672: {'lr': 0.00016775, 'samples': 129024, 'steps': 671, 'loss/train': 4.543347358703613} 08/30/2021 13:21:21 - INFO - __main__ - Step 673: {'lr': 0.00016800000000000002, 'samples': 129216, 'steps': 672, 'loss/train': 6.116588115692139} 08/30/2021 13:21:22 - INFO - __main__ - Step 674: {'lr': 0.00016825000000000002, 'samples': 129408, 'steps': 673, 'loss/train': 5.417694568634033} 08/30/2021 13:21:22 - INFO - __main__ - Step 675: {'lr': 0.0001685, 'samples': 129600, 'steps': 674, 'loss/train': 5.213335037231445} 08/30/2021 13:21:22 - INFO - __main__ - Step 676: {'lr': 0.00016875, 'samples': 129792, 'steps': 675, 'loss/train': 5.951706409454346} 08/30/2021 13:21:23 - INFO - __main__ - Step 677: {'lr': 0.00016900000000000002, 'samples': 129984, 'steps': 676, 'loss/train': 5.452194690704346} 08/30/2021 13:21:24 - INFO - __main__ - Step 678: {'lr': 0.00016925000000000002, 'samples': 130176, 'steps': 677, 'loss/train': 5.46601676940918} 08/30/2021 13:21:25 - INFO - __main__ - Step 679: {'lr': 0.00016950000000000003, 'samples': 130368, 'steps': 678, 'loss/train': 5.440823078155518} 08/30/2021 13:21:25 - INFO - __main__ - Step 680: {'lr': 0.00016975, 'samples': 130560, 'steps': 679, 'loss/train': 4.783233165740967} 08/30/2021 13:21:25 - INFO - __main__ - Step 681: {'lr': 0.00017, 'samples': 130752, 'steps': 680, 'loss/train': 6.0311150550842285} 08/30/2021 13:21:26 - INFO - __main__ - Step 682: {'lr': 0.00017025000000000002, 'samples': 130944, 'steps': 681, 'loss/train': 5.060884475708008} 08/30/2021 13:21:27 - INFO - __main__ - Step 683: {'lr': 0.00017050000000000002, 'samples': 131136, 'steps': 682, 'loss/train': 3.212306499481201} 08/30/2021 13:21:28 - INFO - __main__ - Step 684: {'lr': 0.00017075, 'samples': 131328, 'steps': 683, 'loss/train': 5.141605377197266} 08/30/2021 13:21:28 - INFO - __main__ - Step 685: {'lr': 0.000171, 'samples': 131520, 'steps': 684, 'loss/train': 5.018991470336914} 08/30/2021 13:21:29 - INFO - __main__ - Step 686: {'lr': 0.00017125000000000002, 'samples': 131712, 'steps': 685, 'loss/train': 4.840954780578613} 08/30/2021 13:21:29 - INFO - __main__ - Step 687: {'lr': 0.00017150000000000002, 'samples': 131904, 'steps': 686, 'loss/train': 6.280068397521973} 08/30/2021 13:21:29 - INFO - __main__ - Step 688: {'lr': 0.00017175000000000003, 'samples': 132096, 'steps': 687, 'loss/train': 5.397987365722656} 08/30/2021 13:21:31 - INFO - __main__ - Step 689: {'lr': 0.00017199999999999998, 'samples': 132288, 'steps': 688, 'loss/train': 4.996814250946045} 08/30/2021 13:21:31 - INFO - __main__ - Step 690: {'lr': 0.00017224999999999999, 'samples': 132480, 'steps': 689, 'loss/train': 4.932107925415039} 08/30/2021 13:21:32 - INFO - __main__ - Step 691: {'lr': 0.0001725, 'samples': 132672, 'steps': 690, 'loss/train': 5.188143253326416} 08/30/2021 13:21:32 - INFO - __main__ - Step 692: {'lr': 0.00017275, 'samples': 132864, 'steps': 691, 'loss/train': 5.35989236831665} 08/30/2021 13:21:32 - INFO - __main__ - Step 693: {'lr': 0.000173, 'samples': 133056, 'steps': 692, 'loss/train': 5.086303234100342} 08/30/2021 13:21:34 - INFO - __main__ - Step 694: {'lr': 0.00017324999999999998, 'samples': 133248, 'steps': 693, 'loss/train': 4.893771171569824} 08/30/2021 13:21:34 - INFO - __main__ - Step 695: {'lr': 0.0001735, 'samples': 133440, 'steps': 694, 'loss/train': 5.735641956329346} 08/30/2021 13:21:35 - INFO - __main__ - Step 696: {'lr': 0.00017375, 'samples': 133632, 'steps': 695, 'loss/train': 5.167459487915039} 08/30/2021 13:21:35 - INFO - __main__ - Step 697: {'lr': 0.000174, 'samples': 133824, 'steps': 696, 'loss/train': 4.828813076019287} 08/30/2021 13:21:35 - INFO - __main__ - Step 698: {'lr': 0.00017424999999999998, 'samples': 134016, 'steps': 697, 'loss/train': 4.851093292236328} 08/30/2021 13:21:37 - INFO - __main__ - Step 699: {'lr': 0.00017449999999999999, 'samples': 134208, 'steps': 698, 'loss/train': 4.942488193511963} 08/30/2021 13:21:37 - INFO - __main__ - Step 700: {'lr': 0.00017475, 'samples': 134400, 'steps': 699, 'loss/train': 5.506532669067383} 08/30/2021 13:21:38 - INFO - __main__ - Step 701: {'lr': 0.000175, 'samples': 134592, 'steps': 700, 'loss/train': 5.4863715171813965} 08/30/2021 13:21:38 - INFO - __main__ - Step 702: {'lr': 0.00017525, 'samples': 134784, 'steps': 701, 'loss/train': 5.2799553871154785} 08/30/2021 13:21:38 - INFO - __main__ - Step 703: {'lr': 0.00017549999999999998, 'samples': 134976, 'steps': 702, 'loss/train': 5.637045860290527} 08/30/2021 13:21:40 - INFO - __main__ - Step 704: {'lr': 0.00017575, 'samples': 135168, 'steps': 703, 'loss/train': 5.424383640289307} 08/30/2021 13:21:41 - INFO - __main__ - Step 705: {'lr': 0.000176, 'samples': 135360, 'steps': 704, 'loss/train': 5.126307487487793} 08/30/2021 13:21:41 - INFO - __main__ - Step 706: {'lr': 0.00017625, 'samples': 135552, 'steps': 705, 'loss/train': 5.253078460693359} 08/30/2021 13:21:42 - INFO - __main__ - Step 707: {'lr': 0.00017649999999999998, 'samples': 135744, 'steps': 706, 'loss/train': 5.362359046936035} 08/30/2021 13:21:42 - INFO - __main__ - Step 708: {'lr': 0.00017675, 'samples': 135936, 'steps': 707, 'loss/train': 5.219271659851074} 08/30/2021 13:21:43 - INFO - __main__ - Step 709: {'lr': 0.000177, 'samples': 136128, 'steps': 708, 'loss/train': 5.232418537139893} 08/30/2021 13:21:44 - INFO - __main__ - Step 710: {'lr': 0.00017725, 'samples': 136320, 'steps': 709, 'loss/train': 5.332751750946045} 08/30/2021 13:21:44 - INFO - __main__ - Step 711: {'lr': 0.0001775, 'samples': 136512, 'steps': 710, 'loss/train': 5.502506256103516} 08/30/2021 13:21:45 - INFO - __main__ - Step 712: {'lr': 0.00017774999999999998, 'samples': 136704, 'steps': 711, 'loss/train': 5.203675270080566} 08/30/2021 13:21:45 - INFO - __main__ - Step 713: {'lr': 0.000178, 'samples': 136896, 'steps': 712, 'loss/train': 5.390910625457764} 08/30/2021 13:21:46 - INFO - __main__ - Step 714: {'lr': 0.00017825, 'samples': 137088, 'steps': 713, 'loss/train': 5.454862594604492} 08/30/2021 13:21:47 - INFO - __main__ - Step 715: {'lr': 0.0001785, 'samples': 137280, 'steps': 714, 'loss/train': 5.786046981811523} 08/30/2021 13:21:47 - INFO - __main__ - Step 716: {'lr': 0.00017875, 'samples': 137472, 'steps': 715, 'loss/train': 5.449164867401123} 08/30/2021 13:21:48 - INFO - __main__ - Step 717: {'lr': 0.000179, 'samples': 137664, 'steps': 716, 'loss/train': 5.285722732543945} 08/30/2021 13:21:48 - INFO - __main__ - Step 718: {'lr': 0.00017925, 'samples': 137856, 'steps': 717, 'loss/train': 4.428260803222656} 08/30/2021 13:21:50 - INFO - __main__ - Step 719: {'lr': 0.0001795, 'samples': 138048, 'steps': 718, 'loss/train': 4.634762287139893} 08/30/2021 13:21:50 - INFO - __main__ - Step 720: {'lr': 0.00017975, 'samples': 138240, 'steps': 719, 'loss/train': 5.215118885040283} 08/30/2021 13:21:50 - INFO - __main__ - Step 721: {'lr': 0.00017999999999999998, 'samples': 138432, 'steps': 720, 'loss/train': 4.848156929016113} 08/30/2021 13:21:51 - INFO - __main__ - Step 722: {'lr': 0.00018025, 'samples': 138624, 'steps': 721, 'loss/train': 5.2248969078063965} 08/30/2021 13:21:51 - INFO - __main__ - Step 723: {'lr': 0.0001805, 'samples': 138816, 'steps': 722, 'loss/train': 5.293713569641113} 08/30/2021 13:21:51 - INFO - __main__ - Step 724: {'lr': 0.00018075, 'samples': 139008, 'steps': 723, 'loss/train': 2.9500813484191895} 08/30/2021 13:21:53 - INFO - __main__ - Step 725: {'lr': 0.000181, 'samples': 139200, 'steps': 724, 'loss/train': 5.430168151855469} 08/30/2021 13:21:53 - INFO - __main__ - Step 726: {'lr': 0.00018125, 'samples': 139392, 'steps': 725, 'loss/train': 4.909379005432129} 08/30/2021 13:21:53 - INFO - __main__ - Step 727: {'lr': 0.0001815, 'samples': 139584, 'steps': 726, 'loss/train': 4.975824356079102} 08/30/2021 13:21:54 - INFO - __main__ - Step 728: {'lr': 0.00018175, 'samples': 139776, 'steps': 727, 'loss/train': 5.0482683181762695} 08/30/2021 13:21:54 - INFO - __main__ - Step 729: {'lr': 0.000182, 'samples': 139968, 'steps': 728, 'loss/train': 4.883768558502197} 08/30/2021 13:21:56 - INFO - __main__ - Step 730: {'lr': 0.00018225, 'samples': 140160, 'steps': 729, 'loss/train': 5.080338954925537} 08/30/2021 13:21:56 - INFO - __main__ - Step 731: {'lr': 0.0001825, 'samples': 140352, 'steps': 730, 'loss/train': 6.052454948425293} 08/30/2021 13:21:56 - INFO - __main__ - Step 732: {'lr': 0.00018275, 'samples': 140544, 'steps': 731, 'loss/train': 5.398553848266602} 08/30/2021 13:21:57 - INFO - __main__ - Step 733: {'lr': 0.000183, 'samples': 140736, 'steps': 732, 'loss/train': 5.351493835449219} 08/30/2021 13:21:57 - INFO - __main__ - Step 734: {'lr': 0.00018325, 'samples': 140928, 'steps': 733, 'loss/train': 5.326423645019531} 08/30/2021 13:21:59 - INFO - __main__ - Step 735: {'lr': 0.0001835, 'samples': 141120, 'steps': 734, 'loss/train': 5.069309711456299} 08/30/2021 13:21:59 - INFO - __main__ - Step 736: {'lr': 0.00018375, 'samples': 141312, 'steps': 735, 'loss/train': 5.322574138641357} 08/30/2021 13:21:59 - INFO - __main__ - Step 737: {'lr': 0.000184, 'samples': 141504, 'steps': 736, 'loss/train': 5.334287166595459} 08/30/2021 13:22:00 - INFO - __main__ - Step 738: {'lr': 0.00018425, 'samples': 141696, 'steps': 737, 'loss/train': 5.26049280166626} 08/30/2021 13:22:00 - INFO - __main__ - Step 739: {'lr': 0.0001845, 'samples': 141888, 'steps': 738, 'loss/train': 5.1639323234558105} 08/30/2021 13:22:02 - INFO - __main__ - Step 740: {'lr': 0.00018475, 'samples': 142080, 'steps': 739, 'loss/train': 5.386720657348633} 08/30/2021 13:22:02 - INFO - __main__ - Step 741: {'lr': 0.000185, 'samples': 142272, 'steps': 740, 'loss/train': 4.5195183753967285} 08/30/2021 13:22:03 - INFO - __main__ - Step 742: {'lr': 0.00018525, 'samples': 142464, 'steps': 741, 'loss/train': 4.867159843444824} 08/30/2021 13:22:03 - INFO - __main__ - Step 743: {'lr': 0.0001855, 'samples': 142656, 'steps': 742, 'loss/train': 5.191786289215088} 08/30/2021 13:22:03 - INFO - __main__ - Step 744: {'lr': 0.00018575000000000002, 'samples': 142848, 'steps': 743, 'loss/train': 4.717995643615723} 08/30/2021 13:22:05 - INFO - __main__ - Step 745: {'lr': 0.000186, 'samples': 143040, 'steps': 744, 'loss/train': 6.0065155029296875} 08/30/2021 13:22:05 - INFO - __main__ - Step 746: {'lr': 0.00018625, 'samples': 143232, 'steps': 745, 'loss/train': 5.013382434844971} 08/30/2021 13:22:06 - INFO - __main__ - Step 747: {'lr': 0.0001865, 'samples': 143424, 'steps': 746, 'loss/train': 4.988122940063477} 08/30/2021 13:22:06 - INFO - __main__ - Step 748: {'lr': 0.00018675, 'samples': 143616, 'steps': 747, 'loss/train': 4.544159412384033} 08/30/2021 13:22:06 - INFO - __main__ - Step 749: {'lr': 0.000187, 'samples': 143808, 'steps': 748, 'loss/train': 4.364598274230957} 08/30/2021 13:22:08 - INFO - __main__ - Step 750: {'lr': 0.00018725, 'samples': 144000, 'steps': 749, 'loss/train': 4.41270112991333} 08/30/2021 13:22:08 - INFO - __main__ - Step 751: {'lr': 0.0001875, 'samples': 144192, 'steps': 750, 'loss/train': 5.2335357666015625} 08/30/2021 13:22:09 - INFO - __main__ - Step 752: {'lr': 0.00018775, 'samples': 144384, 'steps': 751, 'loss/train': 2.75010085105896} 08/30/2021 13:22:09 - INFO - __main__ - Step 753: {'lr': 0.00018800000000000002, 'samples': 144576, 'steps': 752, 'loss/train': 5.661611080169678} 08/30/2021 13:22:09 - INFO - __main__ - Step 754: {'lr': 0.00018825, 'samples': 144768, 'steps': 753, 'loss/train': 5.012766361236572} 08/30/2021 13:22:10 - INFO - __main__ - Step 755: {'lr': 0.0001885, 'samples': 144960, 'steps': 754, 'loss/train': 4.824182033538818} 08/30/2021 13:22:12 - INFO - __main__ - Step 756: {'lr': 0.00018875, 'samples': 145152, 'steps': 755, 'loss/train': 4.862341403961182} 08/30/2021 13:22:12 - INFO - __main__ - Step 757: {'lr': 0.000189, 'samples': 145344, 'steps': 756, 'loss/train': 4.939844131469727} 08/30/2021 13:22:13 - INFO - __main__ - Step 758: {'lr': 0.00018925, 'samples': 145536, 'steps': 757, 'loss/train': 3.1442975997924805} 08/30/2021 13:22:13 - INFO - __main__ - Step 759: {'lr': 0.0001895, 'samples': 145728, 'steps': 758, 'loss/train': 5.516304016113281} 08/30/2021 13:22:13 - INFO - __main__ - Step 760: {'lr': 0.00018975, 'samples': 145920, 'steps': 759, 'loss/train': 4.981257915496826} 08/30/2021 13:22:15 - INFO - __main__ - Step 761: {'lr': 0.00019, 'samples': 146112, 'steps': 760, 'loss/train': 4.415140628814697} 08/30/2021 13:22:15 - INFO - __main__ - Step 762: {'lr': 0.00019025000000000002, 'samples': 146304, 'steps': 761, 'loss/train': 4.696414470672607} 08/30/2021 13:22:15 - INFO - __main__ - Step 763: {'lr': 0.0001905, 'samples': 146496, 'steps': 762, 'loss/train': 4.768802165985107} 08/30/2021 13:22:16 - INFO - __main__ - Step 764: {'lr': 0.00019075, 'samples': 146688, 'steps': 763, 'loss/train': 2.537238836288452} 08/30/2021 13:22:16 - INFO - __main__ - Step 765: {'lr': 0.000191, 'samples': 146880, 'steps': 764, 'loss/train': 4.994415760040283} 08/30/2021 13:22:18 - INFO - __main__ - Step 766: {'lr': 0.00019125000000000001, 'samples': 147072, 'steps': 765, 'loss/train': 4.782634735107422} 08/30/2021 13:22:18 - INFO - __main__ - Step 767: {'lr': 0.00019150000000000002, 'samples': 147264, 'steps': 766, 'loss/train': 4.660978317260742} 08/30/2021 13:22:19 - INFO - __main__ - Step 768: {'lr': 0.00019175, 'samples': 147456, 'steps': 767, 'loss/train': 5.131323337554932} 08/30/2021 13:22:19 - INFO - __main__ - Step 769: {'lr': 0.000192, 'samples': 147648, 'steps': 768, 'loss/train': 5.445662021636963} 08/30/2021 13:22:19 - INFO - __main__ - Step 770: {'lr': 0.00019225, 'samples': 147840, 'steps': 769, 'loss/train': 6.240190029144287} 08/30/2021 13:22:21 - INFO - __main__ - Step 771: {'lr': 0.00019250000000000002, 'samples': 148032, 'steps': 770, 'loss/train': 2.3361003398895264} 08/30/2021 13:22:21 - INFO - __main__ - Step 772: {'lr': 0.00019275, 'samples': 148224, 'steps': 771, 'loss/train': 5.761361122131348} 08/30/2021 13:22:21 - INFO - __main__ - Step 773: {'lr': 0.000193, 'samples': 148416, 'steps': 772, 'loss/train': 4.719097137451172} 08/30/2021 13:22:22 - INFO - __main__ - Step 774: {'lr': 0.00019325, 'samples': 148608, 'steps': 773, 'loss/train': 4.363806247711182} 08/30/2021 13:22:22 - INFO - __main__ - Step 775: {'lr': 0.00019350000000000001, 'samples': 148800, 'steps': 774, 'loss/train': 5.564626216888428} 08/30/2021 13:22:24 - INFO - __main__ - Step 776: {'lr': 0.00019375000000000002, 'samples': 148992, 'steps': 775, 'loss/train': 5.3247761726379395} 08/30/2021 13:22:24 - INFO - __main__ - Step 777: {'lr': 0.000194, 'samples': 149184, 'steps': 776, 'loss/train': 5.080868721008301} 08/30/2021 13:22:25 - INFO - __main__ - Step 778: {'lr': 0.00019425, 'samples': 149376, 'steps': 777, 'loss/train': 4.219135761260986} 08/30/2021 13:22:25 - INFO - __main__ - Step 779: {'lr': 0.0001945, 'samples': 149568, 'steps': 778, 'loss/train': 4.896482944488525} 08/30/2021 13:22:25 - INFO - __main__ - Step 780: {'lr': 0.00019475000000000002, 'samples': 149760, 'steps': 779, 'loss/train': 5.075745105743408} 08/30/2021 13:22:27 - INFO - __main__ - Step 781: {'lr': 0.00019500000000000002, 'samples': 149952, 'steps': 780, 'loss/train': 5.609300136566162} 08/30/2021 13:22:27 - INFO - __main__ - Step 782: {'lr': 0.00019525, 'samples': 150144, 'steps': 781, 'loss/train': 4.639266490936279} 08/30/2021 13:22:28 - INFO - __main__ - Step 783: {'lr': 0.0001955, 'samples': 150336, 'steps': 782, 'loss/train': 4.969395637512207} 08/30/2021 13:22:28 - INFO - __main__ - Step 784: {'lr': 0.00019575000000000001, 'samples': 150528, 'steps': 783, 'loss/train': 4.845355987548828} 08/30/2021 13:22:28 - INFO - __main__ - Step 785: {'lr': 0.00019600000000000002, 'samples': 150720, 'steps': 784, 'loss/train': 4.61663818359375} 08/30/2021 13:22:30 - INFO - __main__ - Step 786: {'lr': 0.00019625, 'samples': 150912, 'steps': 785, 'loss/train': 5.339992046356201} 08/30/2021 13:22:30 - INFO - __main__ - Step 787: {'lr': 0.0001965, 'samples': 151104, 'steps': 786, 'loss/train': 5.528865814208984} 08/30/2021 13:22:31 - INFO - __main__ - Step 788: {'lr': 0.00019675, 'samples': 151296, 'steps': 787, 'loss/train': 4.822768211364746} 08/30/2021 13:22:31 - INFO - __main__ - Step 789: {'lr': 0.00019700000000000002, 'samples': 151488, 'steps': 788, 'loss/train': 5.273317337036133} 08/30/2021 13:22:31 - INFO - __main__ - Step 790: {'lr': 0.00019725000000000002, 'samples': 151680, 'steps': 789, 'loss/train': 5.14328145980835} 08/30/2021 13:22:32 - INFO - __main__ - Step 791: {'lr': 0.0001975, 'samples': 151872, 'steps': 790, 'loss/train': 3.8901455402374268} 08/30/2021 13:22:33 - INFO - __main__ - Step 792: {'lr': 0.00019775, 'samples': 152064, 'steps': 791, 'loss/train': 4.757646560668945} 08/30/2021 13:22:33 - INFO - __main__ - Step 793: {'lr': 0.00019800000000000002, 'samples': 152256, 'steps': 792, 'loss/train': 4.969261169433594} 08/30/2021 13:22:34 - INFO - __main__ - Step 794: {'lr': 0.00019825000000000002, 'samples': 152448, 'steps': 793, 'loss/train': 5.182010173797607} 08/30/2021 13:22:34 - INFO - __main__ - Step 795: {'lr': 0.00019850000000000003, 'samples': 152640, 'steps': 794, 'loss/train': 5.210019111633301} 08/30/2021 13:22:34 - INFO - __main__ - Step 796: {'lr': 0.00019875, 'samples': 152832, 'steps': 795, 'loss/train': 5.464728355407715} 08/30/2021 13:22:36 - INFO - __main__ - Step 797: {'lr': 0.000199, 'samples': 153024, 'steps': 796, 'loss/train': 4.786752223968506} 08/30/2021 13:22:36 - INFO - __main__ - Step 798: {'lr': 0.00019925000000000002, 'samples': 153216, 'steps': 797, 'loss/train': 4.941608428955078} 08/30/2021 13:22:37 - INFO - __main__ - Step 799: {'lr': 0.00019950000000000002, 'samples': 153408, 'steps': 798, 'loss/train': 5.074517726898193} 08/30/2021 13:22:37 - INFO - __main__ - Step 800: {'lr': 0.00019975, 'samples': 153600, 'steps': 799, 'loss/train': 4.99080753326416} 08/30/2021 13:22:37 - INFO - __main__ - Step 801: {'lr': 0.0002, 'samples': 153792, 'steps': 800, 'loss/train': 5.171445369720459} 08/30/2021 13:22:39 - INFO - __main__ - Step 802: {'lr': 0.00020025000000000002, 'samples': 153984, 'steps': 801, 'loss/train': 4.744009971618652} 08/30/2021 13:22:40 - INFO - __main__ - Step 803: {'lr': 0.00020050000000000002, 'samples': 154176, 'steps': 802, 'loss/train': 4.89526891708374} 08/30/2021 13:22:40 - INFO - __main__ - Step 804: {'lr': 0.00020075000000000003, 'samples': 154368, 'steps': 803, 'loss/train': 5.267028331756592} 08/30/2021 13:22:41 - INFO - __main__ - Step 805: {'lr': 0.000201, 'samples': 154560, 'steps': 804, 'loss/train': 3.488680839538574} 08/30/2021 13:22:41 - INFO - __main__ - Step 806: {'lr': 0.00020125, 'samples': 154752, 'steps': 805, 'loss/train': 5.09182071685791} 08/30/2021 13:22:41 - INFO - __main__ - Step 807: {'lr': 0.00020150000000000002, 'samples': 154944, 'steps': 806, 'loss/train': 7.005643844604492} 08/30/2021 13:22:43 - INFO - __main__ - Step 808: {'lr': 0.00020175000000000003, 'samples': 155136, 'steps': 807, 'loss/train': 5.229349136352539} 08/30/2021 13:22:44 - INFO - __main__ - Step 809: {'lr': 0.000202, 'samples': 155328, 'steps': 808, 'loss/train': 6.564152240753174} 08/30/2021 13:22:44 - INFO - __main__ - Step 810: {'lr': 0.00020225, 'samples': 155520, 'steps': 809, 'loss/train': 5.298187732696533} 08/30/2021 13:22:44 - INFO - __main__ - Step 811: {'lr': 0.00020250000000000002, 'samples': 155712, 'steps': 810, 'loss/train': 5.483476161956787} 08/30/2021 13:22:45 - INFO - __main__ - Step 812: {'lr': 0.00020275000000000002, 'samples': 155904, 'steps': 811, 'loss/train': 5.093533039093018} 08/30/2021 13:22:46 - INFO - __main__ - Step 813: {'lr': 0.00020300000000000003, 'samples': 156096, 'steps': 812, 'loss/train': 5.095035076141357} 08/30/2021 13:22:47 - INFO - __main__ - Step 814: {'lr': 0.00020324999999999998, 'samples': 156288, 'steps': 813, 'loss/train': 5.363131523132324} 08/30/2021 13:22:47 - INFO - __main__ - Step 815: {'lr': 0.00020349999999999999, 'samples': 156480, 'steps': 814, 'loss/train': 4.598577499389648} 08/30/2021 13:22:47 - INFO - __main__ - Step 816: {'lr': 0.00020375, 'samples': 156672, 'steps': 815, 'loss/train': 5.136349678039551} 08/30/2021 13:22:48 - INFO - __main__ - Step 817: {'lr': 0.000204, 'samples': 156864, 'steps': 816, 'loss/train': 5.176651954650879} 08/30/2021 13:22:49 - INFO - __main__ - Step 818: {'lr': 0.00020425, 'samples': 157056, 'steps': 817, 'loss/train': 5.160329818725586} 08/30/2021 13:22:49 - INFO - __main__ - Step 819: {'lr': 0.00020449999999999998, 'samples': 157248, 'steps': 818, 'loss/train': 5.5419111251831055} 08/30/2021 13:22:50 - INFO - __main__ - Step 820: {'lr': 0.00020475, 'samples': 157440, 'steps': 819, 'loss/train': 4.841118812561035} 08/30/2021 13:22:50 - INFO - __main__ - Step 821: {'lr': 0.000205, 'samples': 157632, 'steps': 820, 'loss/train': 5.133449077606201} 08/30/2021 13:22:51 - INFO - __main__ - Step 822: {'lr': 0.00020525, 'samples': 157824, 'steps': 821, 'loss/train': 5.230595588684082} 08/30/2021 13:22:52 - INFO - __main__ - Step 823: {'lr': 0.00020549999999999998, 'samples': 158016, 'steps': 822, 'loss/train': 4.926100254058838} 08/30/2021 13:22:53 - INFO - __main__ - Step 824: {'lr': 0.00020575, 'samples': 158208, 'steps': 823, 'loss/train': 4.861969947814941} 08/30/2021 13:22:53 - INFO - __main__ - Step 825: {'lr': 0.000206, 'samples': 158400, 'steps': 824, 'loss/train': 5.224119663238525} 08/30/2021 13:22:53 - INFO - __main__ - Step 826: {'lr': 0.00020625, 'samples': 158592, 'steps': 825, 'loss/train': 4.030957221984863} 08/30/2021 13:22:54 - INFO - __main__ - Step 827: {'lr': 0.0002065, 'samples': 158784, 'steps': 826, 'loss/train': 5.341745376586914} 08/30/2021 13:22:54 - INFO - __main__ - Step 828: {'lr': 0.00020674999999999998, 'samples': 158976, 'steps': 827, 'loss/train': 5.493295669555664} 08/30/2021 13:22:56 - INFO - __main__ - Step 829: {'lr': 0.000207, 'samples': 159168, 'steps': 828, 'loss/train': 5.471200942993164} 08/30/2021 13:22:57 - INFO - __main__ - Step 830: {'lr': 0.00020725, 'samples': 159360, 'steps': 829, 'loss/train': 5.901124000549316} 08/30/2021 13:22:57 - INFO - __main__ - Step 831: {'lr': 0.0002075, 'samples': 159552, 'steps': 830, 'loss/train': 5.5267744064331055} 08/30/2021 13:22:57 - INFO - __main__ - Step 832: {'lr': 0.00020774999999999998, 'samples': 159744, 'steps': 831, 'loss/train': 5.741833686828613} 08/30/2021 13:22:58 - INFO - __main__ - Step 833: {'lr': 0.000208, 'samples': 159936, 'steps': 832, 'loss/train': 4.6413984298706055} 08/30/2021 13:22:59 - INFO - __main__ - Step 834: {'lr': 0.00020825, 'samples': 160128, 'steps': 833, 'loss/train': 5.036070346832275} 08/30/2021 13:23:00 - INFO - __main__ - Step 835: {'lr': 0.0002085, 'samples': 160320, 'steps': 834, 'loss/train': 5.281602382659912} 08/30/2021 13:23:00 - INFO - __main__ - Step 836: {'lr': 0.00020875, 'samples': 160512, 'steps': 835, 'loss/train': 5.298867702484131} 08/30/2021 13:23:00 - INFO - __main__ - Step 837: {'lr': 0.00020899999999999998, 'samples': 160704, 'steps': 836, 'loss/train': 5.015073299407959} 08/30/2021 13:23:01 - INFO - __main__ - Step 838: {'lr': 0.00020925, 'samples': 160896, 'steps': 837, 'loss/train': 4.940237998962402} 08/30/2021 13:23:02 - INFO - __main__ - Step 839: {'lr': 0.0002095, 'samples': 161088, 'steps': 838, 'loss/train': 5.205511093139648} 08/30/2021 13:23:03 - INFO - __main__ - Step 840: {'lr': 0.00020975, 'samples': 161280, 'steps': 839, 'loss/train': 4.30275821685791} 08/30/2021 13:23:03 - INFO - __main__ - Step 841: {'lr': 0.00021, 'samples': 161472, 'steps': 840, 'loss/train': 4.556493759155273} 08/30/2021 13:23:03 - INFO - __main__ - Step 842: {'lr': 0.00021025, 'samples': 161664, 'steps': 841, 'loss/train': 5.241671562194824} 08/30/2021 13:23:04 - INFO - __main__ - Step 843: {'lr': 0.0002105, 'samples': 161856, 'steps': 842, 'loss/train': 5.299282073974609} 08/30/2021 13:23:04 - INFO - __main__ - Step 844: {'lr': 0.00021075, 'samples': 162048, 'steps': 843, 'loss/train': 5.412060260772705} 08/30/2021 13:23:05 - INFO - __main__ - Step 845: {'lr': 0.000211, 'samples': 162240, 'steps': 844, 'loss/train': 4.72500467300415} 08/30/2021 13:23:06 - INFO - __main__ - Step 846: {'lr': 0.00021124999999999998, 'samples': 162432, 'steps': 845, 'loss/train': 5.450290679931641} 08/30/2021 13:23:06 - INFO - __main__ - Step 847: {'lr': 0.0002115, 'samples': 162624, 'steps': 846, 'loss/train': 5.327075481414795} 08/30/2021 13:23:06 - INFO - __main__ - Step 848: {'lr': 0.00021175, 'samples': 162816, 'steps': 847, 'loss/train': 5.164058685302734} 08/30/2021 13:23:07 - INFO - __main__ - Step 849: {'lr': 0.000212, 'samples': 163008, 'steps': 848, 'loss/train': 2.9785478115081787} 08/30/2021 13:23:08 - INFO - __main__ - Step 850: {'lr': 0.00021225, 'samples': 163200, 'steps': 849, 'loss/train': 4.942882061004639} 08/30/2021 13:23:09 - INFO - __main__ - Step 851: {'lr': 0.0002125, 'samples': 163392, 'steps': 850, 'loss/train': 4.294112205505371} 08/30/2021 13:23:09 - INFO - __main__ - Step 852: {'lr': 0.00021275, 'samples': 163584, 'steps': 851, 'loss/train': 4.876553058624268} 08/30/2021 13:23:09 - INFO - __main__ - Step 853: {'lr': 0.000213, 'samples': 163776, 'steps': 852, 'loss/train': 5.452459335327148} 08/30/2021 13:23:10 - INFO - __main__ - Step 854: {'lr': 0.00021325, 'samples': 163968, 'steps': 853, 'loss/train': 3.861050605773926} 08/30/2021 13:23:11 - INFO - __main__ - Step 855: {'lr': 0.0002135, 'samples': 164160, 'steps': 854, 'loss/train': 5.315682888031006} 08/30/2021 13:23:12 - INFO - __main__ - Step 856: {'lr': 0.00021375, 'samples': 164352, 'steps': 855, 'loss/train': 4.639874458312988} 08/30/2021 13:23:12 - INFO - __main__ - Step 857: {'lr': 0.000214, 'samples': 164544, 'steps': 856, 'loss/train': 4.612071990966797} 08/30/2021 13:23:12 - INFO - __main__ - Step 858: {'lr': 0.00021425, 'samples': 164736, 'steps': 857, 'loss/train': 5.122485637664795} 08/30/2021 13:23:13 - INFO - __main__ - Step 859: {'lr': 0.0002145, 'samples': 164928, 'steps': 858, 'loss/train': 5.199220180511475} 08/30/2021 13:23:14 - INFO - __main__ - Step 860: {'lr': 0.00021475, 'samples': 165120, 'steps': 859, 'loss/train': 5.492043495178223} 08/30/2021 13:23:15 - INFO - __main__ - Step 861: {'lr': 0.000215, 'samples': 165312, 'steps': 860, 'loss/train': 4.861348628997803} 08/30/2021 13:23:15 - INFO - __main__ - Step 862: {'lr': 0.00021525, 'samples': 165504, 'steps': 861, 'loss/train': 5.139138698577881} 08/30/2021 13:23:15 - INFO - __main__ - Step 863: {'lr': 0.0002155, 'samples': 165696, 'steps': 862, 'loss/train': 5.403965473175049} 08/30/2021 13:23:16 - INFO - __main__ - Step 864: {'lr': 0.00021575, 'samples': 165888, 'steps': 863, 'loss/train': 5.412846565246582} 08/30/2021 13:23:16 - INFO - __main__ - Step 865: {'lr': 0.000216, 'samples': 166080, 'steps': 864, 'loss/train': 5.67106294631958} 08/30/2021 13:23:18 - INFO - __main__ - Step 866: {'lr': 0.00021625, 'samples': 166272, 'steps': 865, 'loss/train': 5.427254676818848} 08/30/2021 13:23:18 - INFO - __main__ - Step 867: {'lr': 0.0002165, 'samples': 166464, 'steps': 866, 'loss/train': 5.4803643226623535} 08/30/2021 13:23:19 - INFO - __main__ - Step 868: {'lr': 0.00021675, 'samples': 166656, 'steps': 867, 'loss/train': 4.972472667694092} 08/30/2021 13:23:19 - INFO - __main__ - Step 869: {'lr': 0.00021700000000000002, 'samples': 166848, 'steps': 868, 'loss/train': 5.120309829711914} 08/30/2021 13:23:19 - INFO - __main__ - Step 870: {'lr': 0.00021725, 'samples': 167040, 'steps': 869, 'loss/train': 4.365508556365967} 08/30/2021 13:23:21 - INFO - __main__ - Step 871: {'lr': 0.0002175, 'samples': 167232, 'steps': 870, 'loss/train': 4.659406661987305} 08/30/2021 13:23:21 - INFO - __main__ - Step 872: {'lr': 0.00021775, 'samples': 167424, 'steps': 871, 'loss/train': 3.791257381439209} 08/30/2021 13:23:22 - INFO - __main__ - Step 873: {'lr': 0.000218, 'samples': 167616, 'steps': 872, 'loss/train': 5.003664493560791} 08/30/2021 13:23:22 - INFO - __main__ - Step 874: {'lr': 0.00021825, 'samples': 167808, 'steps': 873, 'loss/train': 5.018499851226807} 08/30/2021 13:23:22 - INFO - __main__ - Step 875: {'lr': 0.0002185, 'samples': 168000, 'steps': 874, 'loss/train': 4.5537919998168945} 08/30/2021 13:23:24 - INFO - __main__ - Step 876: {'lr': 0.00021875, 'samples': 168192, 'steps': 875, 'loss/train': 5.3264007568359375} 08/30/2021 13:23:24 - INFO - __main__ - Step 877: {'lr': 0.000219, 'samples': 168384, 'steps': 876, 'loss/train': 5.37451696395874} 08/30/2021 13:23:25 - INFO - __main__ - Step 878: {'lr': 0.00021925000000000002, 'samples': 168576, 'steps': 877, 'loss/train': 5.83143424987793} 08/30/2021 13:23:25 - INFO - __main__ - Step 879: {'lr': 0.0002195, 'samples': 168768, 'steps': 878, 'loss/train': 5.012094974517822} 08/30/2021 13:23:25 - INFO - __main__ - Step 880: {'lr': 0.00021975, 'samples': 168960, 'steps': 879, 'loss/train': 5.125668048858643} 08/30/2021 13:23:27 - INFO - __main__ - Step 881: {'lr': 0.00022, 'samples': 169152, 'steps': 880, 'loss/train': 4.766420841217041} 08/30/2021 13:23:27 - INFO - __main__ - Step 882: {'lr': 0.00022025000000000001, 'samples': 169344, 'steps': 881, 'loss/train': 4.905979156494141} 08/30/2021 13:23:28 - INFO - __main__ - Step 883: {'lr': 0.0002205, 'samples': 169536, 'steps': 882, 'loss/train': 4.748187065124512} 08/30/2021 13:23:28 - INFO - __main__ - Step 884: {'lr': 0.00022075, 'samples': 169728, 'steps': 883, 'loss/train': 4.937015533447266} 08/30/2021 13:23:29 - INFO - __main__ - Step 885: {'lr': 0.000221, 'samples': 169920, 'steps': 884, 'loss/train': 5.347287654876709} 08/30/2021 13:23:29 - INFO - __main__ - Step 886: {'lr': 0.00022125, 'samples': 170112, 'steps': 885, 'loss/train': 5.439239978790283} 08/30/2021 13:23:30 - INFO - __main__ - Step 887: {'lr': 0.00022150000000000002, 'samples': 170304, 'steps': 886, 'loss/train': 3.6341307163238525} 08/30/2021 13:23:31 - INFO - __main__ - Step 888: {'lr': 0.00022175, 'samples': 170496, 'steps': 887, 'loss/train': 5.345653057098389} 08/30/2021 13:23:31 - INFO - __main__ - Step 889: {'lr': 0.000222, 'samples': 170688, 'steps': 888, 'loss/train': 4.535131931304932} 08/30/2021 13:23:31 - INFO - __main__ - Step 890: {'lr': 0.00022225, 'samples': 170880, 'steps': 889, 'loss/train': 4.764547348022461} 08/30/2021 13:23:32 - INFO - __main__ - Step 891: {'lr': 0.00022250000000000001, 'samples': 171072, 'steps': 890, 'loss/train': 5.351622104644775} 08/30/2021 13:23:34 - INFO - __main__ - Step 892: {'lr': 0.00022275000000000002, 'samples': 171264, 'steps': 891, 'loss/train': 5.136674880981445} 08/30/2021 13:23:34 - INFO - __main__ - Step 893: {'lr': 0.000223, 'samples': 171456, 'steps': 892, 'loss/train': 5.209806442260742} 08/30/2021 13:23:35 - INFO - __main__ - Step 894: {'lr': 0.00022325, 'samples': 171648, 'steps': 893, 'loss/train': 4.967884063720703} 08/30/2021 13:23:35 - INFO - __main__ - Step 895: {'lr': 0.0002235, 'samples': 171840, 'steps': 894, 'loss/train': 5.144252300262451} 08/30/2021 13:23:35 - INFO - __main__ - Step 896: {'lr': 0.00022375000000000002, 'samples': 172032, 'steps': 895, 'loss/train': 4.881674766540527} 08/30/2021 13:23:37 - INFO - __main__ - Step 897: {'lr': 0.000224, 'samples': 172224, 'steps': 896, 'loss/train': 3.2832298278808594} 08/30/2021 13:23:38 - INFO - __main__ - Step 898: {'lr': 0.00022425, 'samples': 172416, 'steps': 897, 'loss/train': 3.2080790996551514} 08/30/2021 13:23:38 - INFO - __main__ - Step 899: {'lr': 0.0002245, 'samples': 172608, 'steps': 898, 'loss/train': 4.1041364669799805} 08/30/2021 13:23:38 - INFO - __main__ - Step 900: {'lr': 0.00022475000000000001, 'samples': 172800, 'steps': 899, 'loss/train': 3.7498514652252197} 08/30/2021 13:23:39 - INFO - __main__ - Step 901: {'lr': 0.00022500000000000002, 'samples': 172992, 'steps': 900, 'loss/train': 4.493736743927002} 08/30/2021 13:23:39 - INFO - __main__ - Step 902: {'lr': 0.00022525, 'samples': 173184, 'steps': 901, 'loss/train': 4.7351813316345215} 08/30/2021 13:23:40 - INFO - __main__ - Step 903: {'lr': 0.0002255, 'samples': 173376, 'steps': 902, 'loss/train': 5.0882344245910645} 08/30/2021 13:23:41 - INFO - __main__ - Step 904: {'lr': 0.00022575, 'samples': 173568, 'steps': 903, 'loss/train': 5.257927894592285} 08/30/2021 13:23:41 - INFO - __main__ - Step 905: {'lr': 0.00022600000000000002, 'samples': 173760, 'steps': 904, 'loss/train': 5.417869567871094} 08/30/2021 13:23:42 - INFO - __main__ - Step 906: {'lr': 0.00022625000000000002, 'samples': 173952, 'steps': 905, 'loss/train': 4.744801044464111} 08/30/2021 13:23:42 - INFO - __main__ - Step 907: {'lr': 0.0002265, 'samples': 174144, 'steps': 906, 'loss/train': 5.283426761627197} 08/30/2021 13:23:44 - INFO - __main__ - Step 908: {'lr': 0.00022675, 'samples': 174336, 'steps': 907, 'loss/train': 4.119637489318848} 08/30/2021 13:23:44 - INFO - __main__ - Step 909: {'lr': 0.00022700000000000002, 'samples': 174528, 'steps': 908, 'loss/train': 4.175868034362793} 08/30/2021 13:23:45 - INFO - __main__ - Step 910: {'lr': 0.00022725000000000002, 'samples': 174720, 'steps': 909, 'loss/train': 5.934485912322998} 08/30/2021 13:23:45 - INFO - __main__ - Step 911: {'lr': 0.0002275, 'samples': 174912, 'steps': 910, 'loss/train': 2.738405704498291} 08/30/2021 13:23:45 - INFO - __main__ - Step 912: {'lr': 0.00022775, 'samples': 175104, 'steps': 911, 'loss/train': 3.277622699737549} 08/30/2021 13:23:46 - INFO - __main__ - Step 913: {'lr': 0.000228, 'samples': 175296, 'steps': 912, 'loss/train': 3.008151054382324} 08/30/2021 13:23:47 - INFO - __main__ - Step 914: {'lr': 0.00022825000000000002, 'samples': 175488, 'steps': 913, 'loss/train': 5.002523899078369} 08/30/2021 13:23:48 - INFO - __main__ - Step 915: {'lr': 0.00022850000000000002, 'samples': 175680, 'steps': 914, 'loss/train': 5.076720237731934} 08/30/2021 13:23:48 - INFO - __main__ - Step 916: {'lr': 0.00022875, 'samples': 175872, 'steps': 915, 'loss/train': 5.253383636474609} 08/30/2021 13:23:48 - INFO - __main__ - Step 917: {'lr': 0.000229, 'samples': 176064, 'steps': 916, 'loss/train': 5.0943284034729} 08/30/2021 13:23:49 - INFO - __main__ - Step 918: {'lr': 0.00022925000000000002, 'samples': 176256, 'steps': 917, 'loss/train': 4.55018949508667} 08/30/2021 13:23:51 - INFO - __main__ - Step 919: {'lr': 0.00022950000000000002, 'samples': 176448, 'steps': 918, 'loss/train': 4.921761512756348} 08/30/2021 13:23:52 - INFO - __main__ - Step 920: {'lr': 0.00022975000000000003, 'samples': 176640, 'steps': 919, 'loss/train': 5.253277778625488} 08/30/2021 13:23:52 - INFO - __main__ - Step 921: {'lr': 0.00023, 'samples': 176832, 'steps': 920, 'loss/train': 5.203185081481934} 08/30/2021 13:23:53 - INFO - __main__ - Step 922: {'lr': 0.00023025, 'samples': 177024, 'steps': 921, 'loss/train': 4.610296726226807} 08/30/2021 13:23:53 - INFO - __main__ - Step 923: {'lr': 0.00023050000000000002, 'samples': 177216, 'steps': 922, 'loss/train': 5.244607925415039} 08/30/2021 13:23:53 - INFO - __main__ - Step 924: {'lr': 0.00023075000000000003, 'samples': 177408, 'steps': 923, 'loss/train': 3.095468282699585} 08/30/2021 13:23:55 - INFO - __main__ - Step 925: {'lr': 0.000231, 'samples': 177600, 'steps': 924, 'loss/train': 5.682310104370117} 08/30/2021 13:23:55 - INFO - __main__ - Step 926: {'lr': 0.00023125, 'samples': 177792, 'steps': 925, 'loss/train': 5.327188491821289} 08/30/2021 13:23:56 - INFO - __main__ - Step 927: {'lr': 0.00023150000000000002, 'samples': 177984, 'steps': 926, 'loss/train': 4.54959774017334} 08/30/2021 13:23:56 - INFO - __main__ - Step 928: {'lr': 0.00023175000000000002, 'samples': 178176, 'steps': 927, 'loss/train': 4.926276206970215} 08/30/2021 13:23:57 - INFO - __main__ - Step 929: {'lr': 0.00023200000000000003, 'samples': 178368, 'steps': 928, 'loss/train': 5.122226238250732} 08/30/2021 13:23:57 - INFO - __main__ - Step 930: {'lr': 0.00023225, 'samples': 178560, 'steps': 929, 'loss/train': 4.549820423126221} 08/30/2021 13:23:58 - INFO - __main__ - Step 931: {'lr': 0.0002325, 'samples': 178752, 'steps': 930, 'loss/train': 4.424227237701416} 08/30/2021 13:23:59 - INFO - __main__ - Step 932: {'lr': 0.00023275000000000002, 'samples': 178944, 'steps': 931, 'loss/train': 5.274239540100098} 08/30/2021 13:23:59 - INFO - __main__ - Step 933: {'lr': 0.00023300000000000003, 'samples': 179136, 'steps': 932, 'loss/train': 4.753902912139893} 08/30/2021 13:24:00 - INFO - __main__ - Step 934: {'lr': 0.00023325, 'samples': 179328, 'steps': 933, 'loss/train': 5.339258193969727} 08/30/2021 13:24:00 - INFO - __main__ - Step 935: {'lr': 0.0002335, 'samples': 179520, 'steps': 934, 'loss/train': 5.210813045501709} 08/30/2021 13:24:00 - INFO - __main__ - Step 936: {'lr': 0.00023375000000000002, 'samples': 179712, 'steps': 935, 'loss/train': 6.598178863525391} 08/30/2021 13:24:02 - INFO - __main__ - Step 937: {'lr': 0.00023400000000000002, 'samples': 179904, 'steps': 936, 'loss/train': 5.520947456359863} 08/30/2021 13:24:02 - INFO - __main__ - Step 938: {'lr': 0.00023425000000000003, 'samples': 180096, 'steps': 937, 'loss/train': 4.812737941741943} 08/30/2021 13:24:03 - INFO - __main__ - Step 939: {'lr': 0.00023449999999999998, 'samples': 180288, 'steps': 938, 'loss/train': 5.629942893981934} 08/30/2021 13:24:03 - INFO - __main__ - Step 940: {'lr': 0.00023475, 'samples': 180480, 'steps': 939, 'loss/train': 5.933011531829834} 08/30/2021 13:24:03 - INFO - __main__ - Step 941: {'lr': 0.000235, 'samples': 180672, 'steps': 940, 'loss/train': 5.207772254943848} 08/30/2021 13:24:05 - INFO - __main__ - Step 942: {'lr': 0.00023525, 'samples': 180864, 'steps': 941, 'loss/train': 4.708285331726074} 08/30/2021 13:24:06 - INFO - __main__ - Step 943: {'lr': 0.0002355, 'samples': 181056, 'steps': 942, 'loss/train': 5.191772937774658} 08/30/2021 13:24:06 - INFO - __main__ - Step 944: {'lr': 0.00023574999999999998, 'samples': 181248, 'steps': 943, 'loss/train': 5.858270645141602} 08/30/2021 13:24:06 - INFO - __main__ - Step 945: {'lr': 0.000236, 'samples': 181440, 'steps': 944, 'loss/train': 4.297399520874023} 08/30/2021 13:24:07 - INFO - __main__ - Step 946: {'lr': 0.00023625, 'samples': 181632, 'steps': 945, 'loss/train': 4.04622745513916} 08/30/2021 13:24:07 - INFO - __main__ - Step 947: {'lr': 0.0002365, 'samples': 181824, 'steps': 946, 'loss/train': 4.916435718536377} 08/30/2021 13:24:09 - INFO - __main__ - Step 948: {'lr': 0.00023674999999999998, 'samples': 182016, 'steps': 947, 'loss/train': 4.6477370262146} 08/30/2021 13:24:09 - INFO - __main__ - Step 949: {'lr': 0.000237, 'samples': 182208, 'steps': 948, 'loss/train': 5.313317775726318} 08/30/2021 13:24:10 - INFO - __main__ - Step 950: {'lr': 0.00023725, 'samples': 182400, 'steps': 949, 'loss/train': 5.334430694580078} 08/30/2021 13:24:10 - INFO - __main__ - Step 951: {'lr': 0.0002375, 'samples': 182592, 'steps': 950, 'loss/train': 2.398557424545288} 08/30/2021 13:24:10 - INFO - __main__ - Step 952: {'lr': 0.00023775, 'samples': 182784, 'steps': 951, 'loss/train': 5.0697431564331055} 08/30/2021 13:24:12 - INFO - __main__ - Step 953: {'lr': 0.00023799999999999998, 'samples': 182976, 'steps': 952, 'loss/train': 5.132518291473389} 08/30/2021 13:24:12 - INFO - __main__ - Step 954: {'lr': 0.00023825, 'samples': 183168, 'steps': 953, 'loss/train': 4.551535606384277} 08/30/2021 13:24:12 - INFO - __main__ - Step 955: {'lr': 0.0002385, 'samples': 183360, 'steps': 954, 'loss/train': 4.82934045791626} 08/30/2021 13:24:13 - INFO - __main__ - Step 956: {'lr': 0.00023875, 'samples': 183552, 'steps': 955, 'loss/train': 5.0286688804626465} 08/30/2021 13:24:13 - INFO - __main__ - Step 957: {'lr': 0.00023899999999999998, 'samples': 183744, 'steps': 956, 'loss/train': 5.761747360229492} 08/30/2021 13:24:15 - INFO - __main__ - Step 958: {'lr': 0.00023925, 'samples': 183936, 'steps': 957, 'loss/train': 4.5377516746521} 08/30/2021 13:24:15 - INFO - __main__ - Step 959: {'lr': 0.0002395, 'samples': 184128, 'steps': 958, 'loss/train': 4.695328235626221} 08/30/2021 13:24:15 - INFO - __main__ - Step 960: {'lr': 0.00023975, 'samples': 184320, 'steps': 959, 'loss/train': 4.9971842765808105} 08/30/2021 13:24:16 - INFO - __main__ - Step 961: {'lr': 0.00024, 'samples': 184512, 'steps': 960, 'loss/train': 5.350215911865234} 08/30/2021 13:24:16 - INFO - __main__ - Step 962: {'lr': 0.00024024999999999999, 'samples': 184704, 'steps': 961, 'loss/train': 4.973150730133057} 08/30/2021 13:24:18 - INFO - __main__ - Step 963: {'lr': 0.0002405, 'samples': 184896, 'steps': 962, 'loss/train': 4.839539527893066} 08/30/2021 13:24:18 - INFO - __main__ - Step 964: {'lr': 0.00024075, 'samples': 185088, 'steps': 963, 'loss/train': 5.313961982727051} 08/30/2021 13:24:19 - INFO - __main__ - Step 965: {'lr': 0.000241, 'samples': 185280, 'steps': 964, 'loss/train': 5.329487323760986} 08/30/2021 13:24:19 - INFO - __main__ - Step 966: {'lr': 0.00024125, 'samples': 185472, 'steps': 965, 'loss/train': 4.904882907867432} 08/30/2021 13:24:19 - INFO - __main__ - Step 967: {'lr': 0.0002415, 'samples': 185664, 'steps': 966, 'loss/train': 4.989374160766602} 08/30/2021 13:24:21 - INFO - __main__ - Step 968: {'lr': 0.00024175, 'samples': 185856, 'steps': 967, 'loss/train': 4.942816734313965} 08/30/2021 13:24:21 - INFO - __main__ - Step 969: {'lr': 0.000242, 'samples': 186048, 'steps': 968, 'loss/train': 4.176417827606201} 08/30/2021 13:24:22 - INFO - __main__ - Step 970: {'lr': 0.00024225, 'samples': 186240, 'steps': 969, 'loss/train': 2.1338582038879395} 08/30/2021 13:24:22 - INFO - __main__ - Step 971: {'lr': 0.00024249999999999999, 'samples': 186432, 'steps': 970, 'loss/train': 3.527592182159424} 08/30/2021 13:24:22 - INFO - __main__ - Step 972: {'lr': 0.00024275, 'samples': 186624, 'steps': 971, 'loss/train': 7.0105485916137695} 08/30/2021 13:24:23 - INFO - __main__ - Step 973: {'lr': 0.000243, 'samples': 186816, 'steps': 972, 'loss/train': 5.990324020385742} 08/30/2021 13:24:24 - INFO - __main__ - Step 974: {'lr': 0.00024325, 'samples': 187008, 'steps': 973, 'loss/train': 4.93520975112915} 08/30/2021 13:24:25 - INFO - __main__ - Step 975: {'lr': 0.0002435, 'samples': 187200, 'steps': 974, 'loss/train': 4.439929485321045} 08/30/2021 13:24:25 - INFO - __main__ - Step 976: {'lr': 0.00024375, 'samples': 187392, 'steps': 975, 'loss/train': 5.595407962799072} 08/30/2021 13:24:25 - INFO - __main__ - Step 977: {'lr': 0.000244, 'samples': 187584, 'steps': 976, 'loss/train': 5.29143762588501} 08/30/2021 13:24:26 - INFO - __main__ - Step 978: {'lr': 0.00024425, 'samples': 187776, 'steps': 977, 'loss/train': 4.921665191650391} 08/30/2021 13:24:28 - INFO - __main__ - Step 979: {'lr': 0.0002445, 'samples': 187968, 'steps': 978, 'loss/train': 4.97409200668335} 08/30/2021 13:24:28 - INFO - __main__ - Step 980: {'lr': 0.00024475, 'samples': 188160, 'steps': 979, 'loss/train': 4.857159614562988} 08/30/2021 13:24:29 - INFO - __main__ - Step 981: {'lr': 0.000245, 'samples': 188352, 'steps': 980, 'loss/train': 5.116833209991455} 08/30/2021 13:24:29 - INFO - __main__ - Step 982: {'lr': 0.00024525, 'samples': 188544, 'steps': 981, 'loss/train': 5.800650119781494} 08/30/2021 13:24:29 - INFO - __main__ - Step 983: {'lr': 0.0002455, 'samples': 188736, 'steps': 982, 'loss/train': 4.4499077796936035} 08/30/2021 13:24:31 - INFO - __main__ - Step 984: {'lr': 0.00024575, 'samples': 188928, 'steps': 983, 'loss/train': 5.1292243003845215} 08/30/2021 13:24:32 - INFO - __main__ - Step 985: {'lr': 0.000246, 'samples': 189120, 'steps': 984, 'loss/train': 5.253803253173828} 08/30/2021 13:24:32 - INFO - __main__ - Step 986: {'lr': 0.00024625, 'samples': 189312, 'steps': 985, 'loss/train': 4.8171305656433105} 08/30/2021 13:24:32 - INFO - __main__ - Step 987: {'lr': 0.00024650000000000003, 'samples': 189504, 'steps': 986, 'loss/train': 4.849854469299316} 08/30/2021 13:24:33 - INFO - __main__ - Step 988: {'lr': 0.00024675, 'samples': 189696, 'steps': 987, 'loss/train': 4.776261806488037} 08/30/2021 13:24:34 - INFO - __main__ - Step 989: {'lr': 0.000247, 'samples': 189888, 'steps': 988, 'loss/train': 4.666213512420654} 08/30/2021 13:24:35 - INFO - __main__ - Step 990: {'lr': 0.00024725, 'samples': 190080, 'steps': 989, 'loss/train': 5.387469291687012} 08/30/2021 13:24:35 - INFO - __main__ - Step 991: {'lr': 0.0002475, 'samples': 190272, 'steps': 990, 'loss/train': 4.036428928375244} 08/30/2021 13:24:36 - INFO - __main__ - Step 992: {'lr': 0.00024775, 'samples': 190464, 'steps': 991, 'loss/train': 6.747364044189453} 08/30/2021 13:24:36 - INFO - __main__ - Step 993: {'lr': 0.000248, 'samples': 190656, 'steps': 992, 'loss/train': 6.409087181091309} 08/30/2021 13:24:36 - INFO - __main__ - Step 994: {'lr': 0.00024825, 'samples': 190848, 'steps': 993, 'loss/train': 4.653579235076904} 08/30/2021 13:24:37 - INFO - __main__ - Step 995: {'lr': 0.0002485, 'samples': 191040, 'steps': 994, 'loss/train': 5.695528984069824} 08/30/2021 13:24:38 - INFO - __main__ - Step 996: {'lr': 0.00024875, 'samples': 191232, 'steps': 995, 'loss/train': 4.943525314331055} 08/30/2021 13:24:39 - INFO - __main__ - Step 997: {'lr': 0.000249, 'samples': 191424, 'steps': 996, 'loss/train': 5.276374340057373} 08/30/2021 13:24:39 - INFO - __main__ - Step 998: {'lr': 0.00024925, 'samples': 191616, 'steps': 997, 'loss/train': 4.639342784881592} 08/30/2021 13:24:39 - INFO - __main__ - Step 999: {'lr': 0.0002495, 'samples': 191808, 'steps': 998, 'loss/train': 4.728384971618652} 08/30/2021 13:24:40 - INFO - __main__ - Step 1000: {'lr': 0.00024975, 'samples': 192000, 'steps': 999, 'loss/train': 4.859615325927734} 08/30/2021 13:24:41 - INFO - __main__ - Step 1001: {'lr': 0.00025, 'samples': 192192, 'steps': 1000, 'loss/train': 5.420141220092773} 08/30/2021 13:24:42 - INFO - __main__ - Step 1002: {'lr': 0.00025025, 'samples': 192384, 'steps': 1001, 'loss/train': 4.719789505004883} 08/30/2021 13:24:42 - INFO - __main__ - Step 1003: {'lr': 0.0002505, 'samples': 192576, 'steps': 1002, 'loss/train': 4.400145053863525} 08/30/2021 13:24:42 - INFO - __main__ - Step 1004: {'lr': 0.00025075, 'samples': 192768, 'steps': 1003, 'loss/train': 4.5933685302734375} 08/30/2021 13:24:43 - INFO - __main__ - Step 1005: {'lr': 0.00025100000000000003, 'samples': 192960, 'steps': 1004, 'loss/train': 4.682366847991943} 08/30/2021 13:24:44 - INFO - __main__ - Step 1006: {'lr': 0.00025124999999999995, 'samples': 193152, 'steps': 1005, 'loss/train': 4.802097797393799} 08/30/2021 13:24:45 - INFO - __main__ - Step 1007: {'lr': 0.0002515, 'samples': 193344, 'steps': 1006, 'loss/train': 4.660820007324219} 08/30/2021 13:24:45 - INFO - __main__ - Step 1008: {'lr': 0.00025174999999999997, 'samples': 193536, 'steps': 1007, 'loss/train': 4.959339618682861} 08/30/2021 13:24:46 - INFO - __main__ - Step 1009: {'lr': 0.000252, 'samples': 193728, 'steps': 1008, 'loss/train': 4.599143028259277} 08/30/2021 13:24:46 - INFO - __main__ - Step 1010: {'lr': 0.00025225, 'samples': 193920, 'steps': 1009, 'loss/train': 2.5530784130096436} 08/30/2021 13:24:46 - INFO - __main__ - Step 1011: {'lr': 0.0002525, 'samples': 194112, 'steps': 1010, 'loss/train': 4.39011812210083} 08/30/2021 13:24:48 - INFO - __main__ - Step 1012: {'lr': 0.00025275, 'samples': 194304, 'steps': 1011, 'loss/train': 5.429310321807861} 08/30/2021 13:24:48 - INFO - __main__ - Step 1013: {'lr': 0.000253, 'samples': 194496, 'steps': 1012, 'loss/train': 3.1441714763641357} 08/30/2021 13:24:49 - INFO - __main__ - Step 1014: {'lr': 0.00025325, 'samples': 194688, 'steps': 1013, 'loss/train': 4.4851179122924805} 08/30/2021 13:24:49 - INFO - __main__ - Step 1015: {'lr': 0.0002535, 'samples': 194880, 'steps': 1014, 'loss/train': 6.730905532836914} 08/30/2021 13:24:50 - INFO - __main__ - Step 1016: {'lr': 0.00025374999999999996, 'samples': 195072, 'steps': 1015, 'loss/train': 4.265136241912842} 08/30/2021 13:24:51 - INFO - __main__ - Step 1017: {'lr': 0.000254, 'samples': 195264, 'steps': 1016, 'loss/train': 5.068685531616211} 08/30/2021 13:24:52 - INFO - __main__ - Step 1018: {'lr': 0.00025425, 'samples': 195456, 'steps': 1017, 'loss/train': 5.1631855964660645} 08/30/2021 13:24:52 - INFO - __main__ - Step 1019: {'lr': 0.0002545, 'samples': 195648, 'steps': 1018, 'loss/train': 5.227428436279297} 08/30/2021 13:24:52 - INFO - __main__ - Step 1020: {'lr': 0.00025475, 'samples': 195840, 'steps': 1019, 'loss/train': 5.787811756134033} 08/30/2021 13:24:53 - INFO - __main__ - Step 1021: {'lr': 0.000255, 'samples': 196032, 'steps': 1020, 'loss/train': 4.167182922363281} 08/30/2021 13:24:54 - INFO - __main__ - Step 1022: {'lr': 0.00025525, 'samples': 196224, 'steps': 1021, 'loss/train': 4.919136047363281} 08/30/2021 13:24:55 - INFO - __main__ - Step 1023: {'lr': 0.00025550000000000003, 'samples': 196416, 'steps': 1022, 'loss/train': 5.054874420166016} 08/30/2021 13:24:55 - INFO - __main__ - Step 1024: {'lr': 0.00025575, 'samples': 196608, 'steps': 1023, 'loss/train': 5.161455154418945} 08/30/2021 13:24:55 - INFO - __main__ - Step 1025: {'lr': 0.000256, 'samples': 196800, 'steps': 1024, 'loss/train': 6.443774223327637} 08/30/2021 13:24:56 - INFO - __main__ - Step 1026: {'lr': 0.00025624999999999997, 'samples': 196992, 'steps': 1025, 'loss/train': 4.580659866333008} 08/30/2021 13:24:57 - INFO - __main__ - Step 1027: {'lr': 0.0002565, 'samples': 197184, 'steps': 1026, 'loss/train': 4.926455974578857} 08/30/2021 13:24:58 - INFO - __main__ - Step 1028: {'lr': 0.00025675, 'samples': 197376, 'steps': 1027, 'loss/train': 4.851318359375} 08/30/2021 13:24:58 - INFO - __main__ - Step 1029: {'lr': 0.000257, 'samples': 197568, 'steps': 1028, 'loss/train': 4.88503885269165} 08/30/2021 13:24:59 - INFO - __main__ - Step 1030: {'lr': 0.00025725, 'samples': 197760, 'steps': 1029, 'loss/train': 3.5910897254943848} 08/30/2021 13:24:59 - INFO - __main__ - Step 1031: {'lr': 0.0002575, 'samples': 197952, 'steps': 1030, 'loss/train': 5.1407999992370605} 08/30/2021 13:25:01 - INFO - __main__ - Step 1032: {'lr': 0.00025775, 'samples': 198144, 'steps': 1031, 'loss/train': 4.925992965698242} 08/30/2021 13:25:02 - INFO - __main__ - Step 1033: {'lr': 0.00025800000000000004, 'samples': 198336, 'steps': 1032, 'loss/train': 4.9896464347839355} 08/30/2021 13:25:02 - INFO - __main__ - Step 1034: {'lr': 0.00025824999999999996, 'samples': 198528, 'steps': 1033, 'loss/train': 5.108402729034424} 08/30/2021 13:25:02 - INFO - __main__ - Step 1035: {'lr': 0.0002585, 'samples': 198720, 'steps': 1034, 'loss/train': 4.846958637237549} 08/30/2021 13:25:03 - INFO - __main__ - Step 1036: {'lr': 0.00025875, 'samples': 198912, 'steps': 1035, 'loss/train': 5.197140216827393} 08/30/2021 13:25:03 - INFO - __main__ - Step 1037: {'lr': 0.000259, 'samples': 199104, 'steps': 1036, 'loss/train': 4.693840026855469} 08/30/2021 13:25:04 - INFO - __main__ - Step 1038: {'lr': 0.00025925, 'samples': 199296, 'steps': 1037, 'loss/train': 5.01608943939209} 08/30/2021 13:25:05 - INFO - __main__ - Step 1039: {'lr': 0.0002595, 'samples': 199488, 'steps': 1038, 'loss/train': 4.83984375} 08/30/2021 13:25:05 - INFO - __main__ - Step 1040: {'lr': 0.00025975, 'samples': 199680, 'steps': 1039, 'loss/train': 4.813290596008301} 08/30/2021 13:25:06 - INFO - __main__ - Step 1041: {'lr': 0.00026000000000000003, 'samples': 199872, 'steps': 1040, 'loss/train': 4.417173385620117} 08/30/2021 13:25:06 - INFO - __main__ - Step 1042: {'lr': 0.00026025, 'samples': 200064, 'steps': 1041, 'loss/train': 4.47005558013916} 08/30/2021 13:25:07 - INFO - __main__ - Step 1043: {'lr': 0.0002605, 'samples': 200256, 'steps': 1042, 'loss/train': 4.648036956787109} 08/30/2021 13:25:08 - INFO - __main__ - Step 1044: {'lr': 0.00026074999999999997, 'samples': 200448, 'steps': 1043, 'loss/train': 4.901439189910889} 08/30/2021 13:25:08 - INFO - __main__ - Step 1045: {'lr': 0.000261, 'samples': 200640, 'steps': 1044, 'loss/train': 4.551402568817139} 08/30/2021 13:25:09 - INFO - __main__ - Step 1046: {'lr': 0.00026125, 'samples': 200832, 'steps': 1045, 'loss/train': 5.28316593170166} 08/30/2021 13:25:09 - INFO - __main__ - Step 1047: {'lr': 0.0002615, 'samples': 201024, 'steps': 1046, 'loss/train': 4.648711681365967} 08/30/2021 13:25:11 - INFO - __main__ - Step 1048: {'lr': 0.00026175, 'samples': 201216, 'steps': 1047, 'loss/train': 5.267274379730225} 08/30/2021 13:25:11 - INFO - __main__ - Step 1049: {'lr': 0.000262, 'samples': 201408, 'steps': 1048, 'loss/train': 4.830605983734131} 08/30/2021 13:25:11 - INFO - __main__ - Step 1050: {'lr': 0.00026225, 'samples': 201600, 'steps': 1049, 'loss/train': 4.501389503479004} 08/30/2021 13:25:12 - INFO - __main__ - Step 1051: {'lr': 0.00026250000000000004, 'samples': 201792, 'steps': 1050, 'loss/train': 3.8279778957366943} 08/30/2021 13:25:12 - INFO - __main__ - Step 1052: {'lr': 0.00026274999999999996, 'samples': 201984, 'steps': 1051, 'loss/train': 4.429965019226074} 08/30/2021 13:25:14 - INFO - __main__ - Step 1053: {'lr': 0.000263, 'samples': 202176, 'steps': 1052, 'loss/train': 4.966457366943359} 08/30/2021 13:25:14 - INFO - __main__ - Step 1054: {'lr': 0.00026325, 'samples': 202368, 'steps': 1053, 'loss/train': 4.288132190704346} 08/30/2021 13:25:14 - INFO - __main__ - Step 1055: {'lr': 0.0002635, 'samples': 202560, 'steps': 1054, 'loss/train': 4.567619800567627} 08/30/2021 13:25:15 - INFO - __main__ - Step 1056: {'lr': 0.00026375, 'samples': 202752, 'steps': 1055, 'loss/train': 4.083355903625488} 08/30/2021 13:25:15 - INFO - __main__ - Step 1057: {'lr': 0.000264, 'samples': 202944, 'steps': 1056, 'loss/train': 4.958721160888672} 08/30/2021 13:25:16 - INFO - __main__ - Step 1058: {'lr': 0.00026425, 'samples': 203136, 'steps': 1057, 'loss/train': 5.07416296005249} 08/30/2021 13:25:17 - INFO - __main__ - Step 1059: {'lr': 0.00026450000000000003, 'samples': 203328, 'steps': 1058, 'loss/train': 4.9287543296813965} 08/30/2021 13:25:17 - INFO - __main__ - Step 1060: {'lr': 0.00026475, 'samples': 203520, 'steps': 1059, 'loss/train': 4.357052326202393} 08/30/2021 13:25:18 - INFO - __main__ - Step 1061: {'lr': 0.00026500000000000004, 'samples': 203712, 'steps': 1060, 'loss/train': 4.9349365234375} 08/30/2021 13:25:18 - INFO - __main__ - Step 1062: {'lr': 0.00026524999999999997, 'samples': 203904, 'steps': 1061, 'loss/train': 4.818123817443848} 08/30/2021 13:25:19 - INFO - __main__ - Step 1063: {'lr': 0.0002655, 'samples': 204096, 'steps': 1062, 'loss/train': 4.870808124542236} 08/30/2021 13:25:20 - INFO - __main__ - Step 1064: {'lr': 0.00026575, 'samples': 204288, 'steps': 1063, 'loss/train': 4.647601127624512} 08/30/2021 13:25:20 - INFO - __main__ - Step 1065: {'lr': 0.000266, 'samples': 204480, 'steps': 1064, 'loss/train': 3.552048444747925} 08/30/2021 13:25:21 - INFO - __main__ - Step 1066: {'lr': 0.00026625, 'samples': 204672, 'steps': 1065, 'loss/train': 4.389318943023682} 08/30/2021 13:25:21 - INFO - __main__ - Step 1067: {'lr': 0.0002665, 'samples': 204864, 'steps': 1066, 'loss/train': 4.931048393249512} 08/30/2021 13:25:23 - INFO - __main__ - Step 1068: {'lr': 0.00026675, 'samples': 205056, 'steps': 1067, 'loss/train': 3.999504327774048} 08/30/2021 13:25:23 - INFO - __main__ - Step 1069: {'lr': 0.00026700000000000004, 'samples': 205248, 'steps': 1068, 'loss/train': 5.582645893096924} 08/30/2021 13:25:23 - INFO - __main__ - Step 1070: {'lr': 0.00026725, 'samples': 205440, 'steps': 1069, 'loss/train': 5.052674770355225} 08/30/2021 13:25:24 - INFO - __main__ - Step 1071: {'lr': 0.0002675, 'samples': 205632, 'steps': 1070, 'loss/train': 5.009417533874512} 08/30/2021 13:25:24 - INFO - __main__ - Step 1072: {'lr': 0.00026775, 'samples': 205824, 'steps': 1071, 'loss/train': 4.371978282928467} 08/30/2021 13:25:26 - INFO - __main__ - Step 1073: {'lr': 0.000268, 'samples': 206016, 'steps': 1072, 'loss/train': 4.760138034820557} 08/30/2021 13:25:26 - INFO - __main__ - Step 1074: {'lr': 0.00026825, 'samples': 206208, 'steps': 1073, 'loss/train': 4.837433338165283} 08/30/2021 13:25:26 - INFO - __main__ - Step 1075: {'lr': 0.0002685, 'samples': 206400, 'steps': 1074, 'loss/train': 4.604000091552734} 08/30/2021 13:25:27 - INFO - __main__ - Step 1076: {'lr': 0.00026875, 'samples': 206592, 'steps': 1075, 'loss/train': 4.446019649505615} 08/30/2021 13:25:27 - INFO - __main__ - Step 1077: {'lr': 0.00026900000000000003, 'samples': 206784, 'steps': 1076, 'loss/train': 4.247913360595703} 08/30/2021 13:25:27 - INFO - __main__ - Step 1078: {'lr': 0.00026925, 'samples': 206976, 'steps': 1077, 'loss/train': 4.347595691680908} 08/30/2021 13:25:29 - INFO - __main__ - Step 1079: {'lr': 0.00026950000000000005, 'samples': 207168, 'steps': 1078, 'loss/train': 4.9044389724731445} 08/30/2021 13:25:29 - INFO - __main__ - Step 1080: {'lr': 0.00026974999999999997, 'samples': 207360, 'steps': 1079, 'loss/train': 4.687417507171631} 08/30/2021 13:25:30 - INFO - __main__ - Step 1081: {'lr': 0.00027, 'samples': 207552, 'steps': 1080, 'loss/train': 4.920577049255371} 08/30/2021 13:25:30 - INFO - __main__ - Step 1082: {'lr': 0.00027025, 'samples': 207744, 'steps': 1081, 'loss/train': 4.4795026779174805} 08/30/2021 13:25:30 - INFO - __main__ - Step 1083: {'lr': 0.0002705, 'samples': 207936, 'steps': 1082, 'loss/train': 4.78497314453125} 08/30/2021 13:25:32 - INFO - __main__ - Step 1084: {'lr': 0.00027075, 'samples': 208128, 'steps': 1083, 'loss/train': 4.856836318969727} 08/30/2021 13:25:32 - INFO - __main__ - Step 1085: {'lr': 0.00027100000000000003, 'samples': 208320, 'steps': 1084, 'loss/train': 2.3175480365753174} 08/30/2021 13:25:33 - INFO - __main__ - Step 1086: {'lr': 0.00027125, 'samples': 208512, 'steps': 1085, 'loss/train': 4.838772773742676} 08/30/2021 13:25:33 - INFO - __main__ - Step 1087: {'lr': 0.00027150000000000004, 'samples': 208704, 'steps': 1086, 'loss/train': 4.821920871734619} 08/30/2021 13:25:33 - INFO - __main__ - Step 1088: {'lr': 0.00027175, 'samples': 208896, 'steps': 1087, 'loss/train': 4.47393274307251} 08/30/2021 13:25:36 - INFO - __main__ - Step 1089: {'lr': 0.00027200000000000005, 'samples': 209088, 'steps': 1088, 'loss/train': 5.056207656860352} 08/30/2021 13:25:36 - INFO - __main__ - Step 1090: {'lr': 0.00027225, 'samples': 209280, 'steps': 1089, 'loss/train': 4.7649970054626465} 08/30/2021 13:25:36 - INFO - __main__ - Step 1091: {'lr': 0.0002725, 'samples': 209472, 'steps': 1090, 'loss/train': 4.859498977661133} 08/30/2021 13:25:37 - INFO - __main__ - Step 1092: {'lr': 0.00027275, 'samples': 209664, 'steps': 1091, 'loss/train': 4.725033760070801} 08/30/2021 13:25:37 - INFO - __main__ - Step 1093: {'lr': 0.000273, 'samples': 209856, 'steps': 1092, 'loss/train': 4.648543357849121} 08/30/2021 13:25:38 - INFO - __main__ - Step 1094: {'lr': 0.00027325, 'samples': 210048, 'steps': 1093, 'loss/train': 4.039570331573486} 08/30/2021 13:25:39 - INFO - __main__ - Step 1095: {'lr': 0.00027350000000000003, 'samples': 210240, 'steps': 1094, 'loss/train': 4.392956256866455} 08/30/2021 13:25:39 - INFO - __main__ - Step 1096: {'lr': 0.00027375, 'samples': 210432, 'steps': 1095, 'loss/train': 4.70611047744751} 08/30/2021 13:25:40 - INFO - __main__ - Step 1097: {'lr': 0.00027400000000000005, 'samples': 210624, 'steps': 1096, 'loss/train': 5.329628944396973} 08/30/2021 13:25:40 - INFO - __main__ - Step 1098: {'lr': 0.00027425, 'samples': 210816, 'steps': 1097, 'loss/train': 4.339066505432129} 08/30/2021 13:25:42 - INFO - __main__ - Step 1099: {'lr': 0.0002745, 'samples': 211008, 'steps': 1098, 'loss/train': 4.041830539703369} 08/30/2021 13:25:42 - INFO - __main__ - Step 1100: {'lr': 0.00027475, 'samples': 211200, 'steps': 1099, 'loss/train': 4.83737850189209} 08/30/2021 13:25:43 - INFO - __main__ - Step 1101: {'lr': 0.000275, 'samples': 211392, 'steps': 1100, 'loss/train': 4.446187496185303} 08/30/2021 13:25:43 - INFO - __main__ - Step 1102: {'lr': 0.00027525, 'samples': 211584, 'steps': 1101, 'loss/train': 4.877076148986816} 08/30/2021 13:25:43 - INFO - __main__ - Step 1103: {'lr': 0.00027550000000000003, 'samples': 211776, 'steps': 1102, 'loss/train': 4.218622207641602} 08/30/2021 13:25:45 - INFO - __main__ - Step 1104: {'lr': 0.00027575, 'samples': 211968, 'steps': 1103, 'loss/train': 5.401310443878174} 08/30/2021 13:25:45 - INFO - __main__ - Step 1105: {'lr': 0.00027600000000000004, 'samples': 212160, 'steps': 1104, 'loss/train': 4.578069686889648} 08/30/2021 13:25:46 - INFO - __main__ - Step 1106: {'lr': 0.00027625, 'samples': 212352, 'steps': 1105, 'loss/train': 4.28236198425293} 08/30/2021 13:25:46 - INFO - __main__ - Step 1107: {'lr': 0.00027650000000000005, 'samples': 212544, 'steps': 1106, 'loss/train': 1.6180003881454468} 08/30/2021 13:25:46 - INFO - __main__ - Step 1108: {'lr': 0.00027675, 'samples': 212736, 'steps': 1107, 'loss/train': 4.664124011993408} 08/30/2021 13:25:48 - INFO - __main__ - Step 1109: {'lr': 0.000277, 'samples': 212928, 'steps': 1108, 'loss/train': 4.81748104095459} 08/30/2021 13:25:48 - INFO - __main__ - Step 1110: {'lr': 0.00027725, 'samples': 213120, 'steps': 1109, 'loss/train': 4.777357578277588} 08/30/2021 13:25:49 - INFO - __main__ - Step 1111: {'lr': 0.0002775, 'samples': 213312, 'steps': 1110, 'loss/train': 5.144052982330322} 08/30/2021 13:25:49 - INFO - __main__ - Step 1112: {'lr': 0.00027775, 'samples': 213504, 'steps': 1111, 'loss/train': 5.010110378265381} 08/30/2021 13:25:49 - INFO - __main__ - Step 1113: {'lr': 0.00027800000000000004, 'samples': 213696, 'steps': 1112, 'loss/train': 4.681898593902588} 08/30/2021 13:25:51 - INFO - __main__ - Step 1114: {'lr': 0.00027825, 'samples': 213888, 'steps': 1113, 'loss/train': 4.8639960289001465} 08/30/2021 13:25:51 - INFO - __main__ - Step 1115: {'lr': 0.00027850000000000005, 'samples': 214080, 'steps': 1114, 'loss/train': 4.909400939941406} 08/30/2021 13:25:52 - INFO - __main__ - Step 1116: {'lr': 0.00027875, 'samples': 214272, 'steps': 1115, 'loss/train': 4.448228359222412} 08/30/2021 13:25:52 - INFO - __main__ - Step 1117: {'lr': 0.000279, 'samples': 214464, 'steps': 1116, 'loss/train': 4.7131147384643555} 08/30/2021 13:25:52 - INFO - __main__ - Step 1118: {'lr': 0.00027925, 'samples': 214656, 'steps': 1117, 'loss/train': 4.465978622436523} 08/30/2021 13:25:53 - INFO - __main__ - Step 1119: {'lr': 0.0002795, 'samples': 214848, 'steps': 1118, 'loss/train': 4.741469860076904} 08/30/2021 13:25:54 - INFO - __main__ - Step 1120: {'lr': 0.00027975, 'samples': 215040, 'steps': 1119, 'loss/train': 3.005525827407837} 08/30/2021 13:25:55 - INFO - __main__ - Step 1121: {'lr': 0.00028000000000000003, 'samples': 215232, 'steps': 1120, 'loss/train': 4.87128210067749} 08/30/2021 13:25:55 - INFO - __main__ - Step 1122: {'lr': 0.00028025, 'samples': 215424, 'steps': 1121, 'loss/train': 4.876620292663574} 08/30/2021 13:25:55 - INFO - __main__ - Step 1123: {'lr': 0.00028050000000000004, 'samples': 215616, 'steps': 1122, 'loss/train': 4.7476487159729} 08/30/2021 13:25:56 - INFO - __main__ - Step 1124: {'lr': 0.00028075, 'samples': 215808, 'steps': 1123, 'loss/train': 4.4817633628845215} 08/30/2021 13:25:57 - INFO - __main__ - Step 1125: {'lr': 0.00028100000000000005, 'samples': 216000, 'steps': 1124, 'loss/train': 4.958332061767578} 08/30/2021 13:25:58 - INFO - __main__ - Step 1126: {'lr': 0.00028125000000000003, 'samples': 216192, 'steps': 1125, 'loss/train': 5.6920390129089355} 08/30/2021 13:25:58 - INFO - __main__ - Step 1127: {'lr': 0.00028149999999999996, 'samples': 216384, 'steps': 1126, 'loss/train': 4.852529048919678} 08/30/2021 13:25:58 - INFO - __main__ - Step 1128: {'lr': 0.00028175, 'samples': 216576, 'steps': 1127, 'loss/train': 5.391927242279053} 08/30/2021 13:25:59 - INFO - __main__ - Step 1129: {'lr': 0.00028199999999999997, 'samples': 216768, 'steps': 1128, 'loss/train': 4.675811767578125} 08/30/2021 13:26:00 - INFO - __main__ - Step 1130: {'lr': 0.00028225, 'samples': 216960, 'steps': 1129, 'loss/train': 4.625685214996338} 08/30/2021 13:26:01 - INFO - __main__ - Step 1131: {'lr': 0.0002825, 'samples': 217152, 'steps': 1130, 'loss/train': 4.073273181915283} 08/30/2021 13:26:01 - INFO - __main__ - Step 1132: {'lr': 0.00028275, 'samples': 217344, 'steps': 1131, 'loss/train': 4.4050397872924805} 08/30/2021 13:26:01 - INFO - __main__ - Step 1133: {'lr': 0.000283, 'samples': 217536, 'steps': 1132, 'loss/train': 4.553639888763428} 08/30/2021 13:26:02 - INFO - __main__ - Step 1134: {'lr': 0.00028325000000000003, 'samples': 217728, 'steps': 1133, 'loss/train': 3.735881805419922} 08/30/2021 13:26:03 - INFO - __main__ - Step 1135: {'lr': 0.0002835, 'samples': 217920, 'steps': 1134, 'loss/train': 5.083900451660156} 08/30/2021 13:26:04 - INFO - __main__ - Step 1136: {'lr': 0.00028375, 'samples': 218112, 'steps': 1135, 'loss/train': 4.858189105987549} 08/30/2021 13:26:04 - INFO - __main__ - Step 1137: {'lr': 0.00028399999999999996, 'samples': 218304, 'steps': 1136, 'loss/train': 4.526271820068359} 08/30/2021 13:26:04 - INFO - __main__ - Step 1138: {'lr': 0.00028425, 'samples': 218496, 'steps': 1137, 'loss/train': 4.845973968505859} 08/30/2021 13:26:05 - INFO - __main__ - Step 1139: {'lr': 0.0002845, 'samples': 218688, 'steps': 1138, 'loss/train': 4.050032615661621} 08/30/2021 13:26:05 - INFO - __main__ - Step 1140: {'lr': 0.00028475, 'samples': 218880, 'steps': 1139, 'loss/train': 5.131923198699951} 08/30/2021 13:26:07 - INFO - __main__ - Step 1141: {'lr': 0.000285, 'samples': 219072, 'steps': 1140, 'loss/train': 4.84916877746582} 08/30/2021 13:26:08 - INFO - __main__ - Step 1142: {'lr': 0.00028525, 'samples': 219264, 'steps': 1141, 'loss/train': 4.465821743011475} 08/30/2021 13:26:08 - INFO - __main__ - Step 1143: {'lr': 0.0002855, 'samples': 219456, 'steps': 1142, 'loss/train': 4.294210910797119} 08/30/2021 13:26:08 - INFO - __main__ - Step 1144: {'lr': 0.00028575000000000003, 'samples': 219648, 'steps': 1143, 'loss/train': 4.31614875793457} 08/30/2021 13:26:09 - INFO - __main__ - Step 1145: {'lr': 0.00028599999999999996, 'samples': 219840, 'steps': 1144, 'loss/train': 4.901950359344482} 08/30/2021 13:26:10 - INFO - __main__ - Step 1146: {'lr': 0.00028625, 'samples': 220032, 'steps': 1145, 'loss/train': 4.419631004333496} 08/30/2021 13:26:11 - INFO - __main__ - Step 1147: {'lr': 0.00028649999999999997, 'samples': 220224, 'steps': 1146, 'loss/train': 5.121374607086182} 08/30/2021 13:26:11 - INFO - __main__ - Step 1148: {'lr': 0.00028675, 'samples': 220416, 'steps': 1147, 'loss/train': 4.64249324798584} 08/30/2021 13:26:11 - INFO - __main__ - Step 1149: {'lr': 0.000287, 'samples': 220608, 'steps': 1148, 'loss/train': 4.029555320739746} 08/30/2021 13:26:12 - INFO - __main__ - Step 1150: {'lr': 0.00028725, 'samples': 220800, 'steps': 1149, 'loss/train': 3.603362798690796} 08/30/2021 13:26:13 - INFO - __main__ - Step 1151: {'lr': 0.0002875, 'samples': 220992, 'steps': 1150, 'loss/train': 4.238906383514404} 08/30/2021 13:26:14 - INFO - __main__ - Step 1152: {'lr': 0.00028775000000000003, 'samples': 221184, 'steps': 1151, 'loss/train': 4.948597431182861} 08/30/2021 13:26:14 - INFO - __main__ - Step 1153: {'lr': 0.000288, 'samples': 221376, 'steps': 1152, 'loss/train': 4.241683006286621} 08/30/2021 13:26:15 - INFO - __main__ - Step 1154: {'lr': 0.00028825, 'samples': 221568, 'steps': 1153, 'loss/train': 4.642980098724365} 08/30/2021 13:26:15 - INFO - __main__ - Step 1155: {'lr': 0.00028849999999999997, 'samples': 221760, 'steps': 1154, 'loss/train': 4.6034393310546875} 08/30/2021 13:26:15 - INFO - __main__ - Step 1156: {'lr': 0.00028875, 'samples': 221952, 'steps': 1155, 'loss/train': 4.561765670776367} 08/30/2021 13:26:17 - INFO - __main__ - Step 1157: {'lr': 0.000289, 'samples': 222144, 'steps': 1156, 'loss/train': 5.744253158569336} 08/30/2021 13:26:17 - INFO - __main__ - Step 1158: {'lr': 0.00028925, 'samples': 222336, 'steps': 1157, 'loss/train': 5.428072929382324} 08/30/2021 13:26:18 - INFO - __main__ - Step 1159: {'lr': 0.0002895, 'samples': 222528, 'steps': 1158, 'loss/train': 4.342047691345215} 08/30/2021 13:26:18 - INFO - __main__ - Step 1160: {'lr': 0.00028975, 'samples': 222720, 'steps': 1159, 'loss/train': 4.6265668869018555} 08/30/2021 13:26:18 - INFO - __main__ - Step 1161: {'lr': 0.00029, 'samples': 222912, 'steps': 1160, 'loss/train': 4.878502368927002} 08/30/2021 13:26:20 - INFO - __main__ - Step 1162: {'lr': 0.00029025000000000003, 'samples': 223104, 'steps': 1161, 'loss/train': 3.7984821796417236} 08/30/2021 13:26:20 - INFO - __main__ - Step 1163: {'lr': 0.00029049999999999996, 'samples': 223296, 'steps': 1162, 'loss/train': 1.8246033191680908} 08/30/2021 13:26:21 - INFO - __main__ - Step 1164: {'lr': 0.00029075, 'samples': 223488, 'steps': 1163, 'loss/train': 4.839077949523926} 08/30/2021 13:26:21 - INFO - __main__ - Step 1165: {'lr': 0.00029099999999999997, 'samples': 223680, 'steps': 1164, 'loss/train': 2.739114284515381} 08/30/2021 13:26:21 - INFO - __main__ - Step 1166: {'lr': 0.00029125, 'samples': 223872, 'steps': 1165, 'loss/train': 4.731240749359131} 08/30/2021 13:26:23 - INFO - __main__ - Step 1167: {'lr': 0.0002915, 'samples': 224064, 'steps': 1166, 'loss/train': 4.460262298583984} 08/30/2021 13:26:23 - INFO - __main__ - Step 1168: {'lr': 0.00029175, 'samples': 224256, 'steps': 1167, 'loss/train': 6.072906494140625} 08/30/2021 13:26:24 - INFO - __main__ - Step 1169: {'lr': 0.000292, 'samples': 224448, 'steps': 1168, 'loss/train': 4.812139987945557} 08/30/2021 13:26:24 - INFO - __main__ - Step 1170: {'lr': 0.00029225000000000003, 'samples': 224640, 'steps': 1169, 'loss/train': 4.564539909362793} 08/30/2021 13:26:24 - INFO - __main__ - Step 1171: {'lr': 0.0002925, 'samples': 224832, 'steps': 1170, 'loss/train': 5.155861854553223} 08/30/2021 13:26:26 - INFO - __main__ - Step 1172: {'lr': 0.00029275000000000004, 'samples': 225024, 'steps': 1171, 'loss/train': 4.882957458496094} 08/30/2021 13:26:27 - INFO - __main__ - Step 1173: {'lr': 0.00029299999999999997, 'samples': 225216, 'steps': 1172, 'loss/train': 3.6840343475341797} 08/30/2021 13:26:27 - INFO - __main__ - Step 1174: {'lr': 0.00029325, 'samples': 225408, 'steps': 1173, 'loss/train': 4.6220383644104} 08/30/2021 13:26:27 - INFO - __main__ - Step 1175: {'lr': 0.0002935, 'samples': 225600, 'steps': 1174, 'loss/train': 4.422476291656494} 08/30/2021 13:26:28 - INFO - __main__ - Step 1176: {'lr': 0.00029375, 'samples': 225792, 'steps': 1175, 'loss/train': 4.572627544403076} 08/30/2021 13:26:29 - INFO - __main__ - Step 1177: {'lr': 0.000294, 'samples': 225984, 'steps': 1176, 'loss/train': 4.542801856994629} 08/30/2021 13:26:30 - INFO - __main__ - Step 1178: {'lr': 0.00029425, 'samples': 226176, 'steps': 1177, 'loss/train': 5.249860763549805} 08/30/2021 13:26:30 - INFO - __main__ - Step 1179: {'lr': 0.0002945, 'samples': 226368, 'steps': 1178, 'loss/train': 5.008918762207031} 08/30/2021 13:26:30 - INFO - __main__ - Step 1180: {'lr': 0.00029475000000000004, 'samples': 226560, 'steps': 1179, 'loss/train': 4.455695629119873} 08/30/2021 13:26:31 - INFO - __main__ - Step 1181: {'lr': 0.000295, 'samples': 226752, 'steps': 1180, 'loss/train': 2.9186155796051025} 08/30/2021 13:26:33 - INFO - __main__ - Step 1182: {'lr': 0.00029525, 'samples': 226944, 'steps': 1181, 'loss/train': 4.856095790863037} 08/30/2021 13:26:33 - INFO - __main__ - Step 1183: {'lr': 0.00029549999999999997, 'samples': 227136, 'steps': 1182, 'loss/train': 4.697263240814209} 08/30/2021 13:26:33 - INFO - __main__ - Step 1184: {'lr': 0.00029575, 'samples': 227328, 'steps': 1183, 'loss/train': 4.650768280029297} 08/30/2021 13:26:34 - INFO - __main__ - Step 1185: {'lr': 0.000296, 'samples': 227520, 'steps': 1184, 'loss/train': 3.7115986347198486} 08/30/2021 13:26:34 - INFO - __main__ - Step 1186: {'lr': 0.00029625, 'samples': 227712, 'steps': 1185, 'loss/train': 2.548330545425415} 08/30/2021 13:26:34 - INFO - __main__ - Step 1187: {'lr': 0.0002965, 'samples': 227904, 'steps': 1186, 'loss/train': 2.445172071456909} 08/30/2021 13:26:36 - INFO - __main__ - Step 1188: {'lr': 0.00029675000000000003, 'samples': 228096, 'steps': 1187, 'loss/train': 5.328794956207275} 08/30/2021 13:26:36 - INFO - __main__ - Step 1189: {'lr': 0.000297, 'samples': 228288, 'steps': 1188, 'loss/train': 4.762747287750244} 08/30/2021 13:26:37 - INFO - __main__ - Step 1190: {'lr': 0.00029725000000000004, 'samples': 228480, 'steps': 1189, 'loss/train': 4.807939052581787} 08/30/2021 13:26:37 - INFO - __main__ - Step 1191: {'lr': 0.00029749999999999997, 'samples': 228672, 'steps': 1190, 'loss/train': 4.6072187423706055} 08/30/2021 13:26:37 - INFO - __main__ - Step 1192: {'lr': 0.00029775, 'samples': 228864, 'steps': 1191, 'loss/train': 4.544644832611084} 08/30/2021 13:26:40 - INFO - __main__ - Step 1193: {'lr': 0.000298, 'samples': 229056, 'steps': 1192, 'loss/train': 4.550241470336914} 08/30/2021 13:26:40 - INFO - __main__ - Step 1194: {'lr': 0.00029825, 'samples': 229248, 'steps': 1193, 'loss/train': 6.383086204528809} 08/30/2021 13:26:41 - INFO - __main__ - Step 1195: {'lr': 0.0002985, 'samples': 229440, 'steps': 1194, 'loss/train': 3.5256423950195312} 08/30/2021 13:26:41 - INFO - __main__ - Step 1196: {'lr': 0.00029875, 'samples': 229632, 'steps': 1195, 'loss/train': 4.381834506988525} 08/30/2021 13:26:41 - INFO - __main__ - Step 1197: {'lr': 0.000299, 'samples': 229824, 'steps': 1196, 'loss/train': 4.199514865875244} 08/30/2021 13:26:42 - INFO - __main__ - Step 1198: {'lr': 0.00029925000000000004, 'samples': 230016, 'steps': 1197, 'loss/train': 4.502466201782227} 08/30/2021 13:26:43 - INFO - __main__ - Step 1199: {'lr': 0.0002995, 'samples': 230208, 'steps': 1198, 'loss/train': 4.6133036613464355} 08/30/2021 13:26:44 - INFO - __main__ - Step 1200: {'lr': 0.00029975000000000005, 'samples': 230400, 'steps': 1199, 'loss/train': 5.174978256225586} 08/30/2021 13:26:44 - INFO - __main__ - Step 1201: {'lr': 0.0003, 'samples': 230592, 'steps': 1200, 'loss/train': 4.766360282897949} 08/30/2021 13:26:44 - INFO - __main__ - Step 1202: {'lr': 0.00030025, 'samples': 230784, 'steps': 1201, 'loss/train': 4.671626091003418} 08/30/2021 13:26:45 - INFO - __main__ - Step 1203: {'lr': 0.0003005, 'samples': 230976, 'steps': 1202, 'loss/train': 4.615602970123291} 08/30/2021 13:26:46 - INFO - __main__ - Step 1204: {'lr': 0.00030075, 'samples': 231168, 'steps': 1203, 'loss/train': 4.681416988372803} 08/30/2021 13:26:47 - INFO - __main__ - Step 1205: {'lr': 0.000301, 'samples': 231360, 'steps': 1204, 'loss/train': 4.479160785675049} 08/30/2021 13:26:47 - INFO - __main__ - Step 1206: {'lr': 0.00030125000000000003, 'samples': 231552, 'steps': 1205, 'loss/train': 4.991608142852783} 08/30/2021 13:26:47 - INFO - __main__ - Step 1207: {'lr': 0.0003015, 'samples': 231744, 'steps': 1206, 'loss/train': 4.851442813873291} 08/30/2021 13:26:48 - INFO - __main__ - Step 1208: {'lr': 0.00030175000000000004, 'samples': 231936, 'steps': 1207, 'loss/train': 4.640334606170654} 08/30/2021 13:26:49 - INFO - __main__ - Step 1209: {'lr': 0.000302, 'samples': 232128, 'steps': 1208, 'loss/train': 5.395857334136963} 08/30/2021 13:26:49 - INFO - __main__ - Step 1210: {'lr': 0.00030225, 'samples': 232320, 'steps': 1209, 'loss/train': 4.886153221130371} 08/30/2021 13:26:50 - INFO - __main__ - Step 1211: {'lr': 0.0003025, 'samples': 232512, 'steps': 1210, 'loss/train': 5.126450538635254} 08/30/2021 13:26:50 - INFO - __main__ - Step 1212: {'lr': 0.00030275, 'samples': 232704, 'steps': 1211, 'loss/train': 4.263417720794678} 08/30/2021 13:26:51 - INFO - __main__ - Step 1213: {'lr': 0.000303, 'samples': 232896, 'steps': 1212, 'loss/train': 4.8280348777771} 08/30/2021 13:26:52 - INFO - __main__ - Step 1214: {'lr': 0.00030325, 'samples': 233088, 'steps': 1213, 'loss/train': 3.6417994499206543} 08/30/2021 13:26:53 - INFO - __main__ - Step 1215: {'lr': 0.0003035, 'samples': 233280, 'steps': 1214, 'loss/train': 4.839969635009766} 08/30/2021 13:26:53 - INFO - __main__ - Step 1216: {'lr': 0.00030375000000000004, 'samples': 233472, 'steps': 1215, 'loss/train': 4.414170265197754} 08/30/2021 13:26:53 - INFO - __main__ - Step 1217: {'lr': 0.000304, 'samples': 233664, 'steps': 1216, 'loss/train': 5.36515474319458} 08/30/2021 13:26:54 - INFO - __main__ - Step 1218: {'lr': 0.00030425000000000005, 'samples': 233856, 'steps': 1217, 'loss/train': 4.983379364013672} 08/30/2021 13:26:55 - INFO - __main__ - Step 1219: {'lr': 0.0003045, 'samples': 234048, 'steps': 1218, 'loss/train': 4.838827133178711} 08/30/2021 13:26:56 - INFO - __main__ - Step 1220: {'lr': 0.00030475, 'samples': 234240, 'steps': 1219, 'loss/train': 4.412363052368164} 08/30/2021 13:26:56 - INFO - __main__ - Step 1221: {'lr': 0.000305, 'samples': 234432, 'steps': 1220, 'loss/train': 4.714923858642578} 08/30/2021 13:26:56 - INFO - __main__ - Step 1222: {'lr': 0.00030525, 'samples': 234624, 'steps': 1221, 'loss/train': 3.9077796936035156} 08/30/2021 13:26:57 - INFO - __main__ - Step 1223: {'lr': 0.0003055, 'samples': 234816, 'steps': 1222, 'loss/train': 4.756908416748047} 08/30/2021 13:26:58 - INFO - __main__ - Step 1224: {'lr': 0.00030575000000000003, 'samples': 235008, 'steps': 1223, 'loss/train': 4.987254619598389} 08/30/2021 13:26:59 - INFO - __main__ - Step 1225: {'lr': 0.000306, 'samples': 235200, 'steps': 1224, 'loss/train': 4.241818428039551} 08/30/2021 13:26:59 - INFO - __main__ - Step 1226: {'lr': 0.00030625000000000004, 'samples': 235392, 'steps': 1225, 'loss/train': 4.861268043518066} 08/30/2021 13:26:59 - INFO - __main__ - Step 1227: {'lr': 0.0003065, 'samples': 235584, 'steps': 1226, 'loss/train': 4.192913055419922} 08/30/2021 13:27:00 - INFO - __main__ - Step 1228: {'lr': 0.00030675, 'samples': 235776, 'steps': 1227, 'loss/train': 4.0988993644714355} 08/30/2021 13:27:00 - INFO - __main__ - Step 1229: {'lr': 0.000307, 'samples': 235968, 'steps': 1228, 'loss/train': 4.682774543762207} 08/30/2021 13:27:01 - INFO - __main__ - Step 1230: {'lr': 0.00030725, 'samples': 236160, 'steps': 1229, 'loss/train': 5.342475414276123} 08/30/2021 13:27:02 - INFO - __main__ - Step 1231: {'lr': 0.0003075, 'samples': 236352, 'steps': 1230, 'loss/train': 4.609219551086426} 08/30/2021 13:27:02 - INFO - __main__ - Step 1232: {'lr': 0.00030775, 'samples': 236544, 'steps': 1231, 'loss/train': 4.775742530822754} 08/30/2021 13:27:03 - INFO - __main__ - Step 1233: {'lr': 0.000308, 'samples': 236736, 'steps': 1232, 'loss/train': 4.936896324157715} 08/30/2021 13:27:03 - INFO - __main__ - Step 1234: {'lr': 0.00030825000000000004, 'samples': 236928, 'steps': 1233, 'loss/train': 4.298108100891113} 08/30/2021 13:27:04 - INFO - __main__ - Step 1235: {'lr': 0.0003085, 'samples': 237120, 'steps': 1234, 'loss/train': 4.250104904174805} 08/30/2021 13:27:05 - INFO - __main__ - Step 1236: {'lr': 0.00030875000000000005, 'samples': 237312, 'steps': 1235, 'loss/train': 1.9314104318618774} 08/30/2021 13:27:05 - INFO - __main__ - Step 1237: {'lr': 0.00030900000000000003, 'samples': 237504, 'steps': 1236, 'loss/train': 4.494245529174805} 08/30/2021 13:27:06 - INFO - __main__ - Step 1238: {'lr': 0.00030925, 'samples': 237696, 'steps': 1237, 'loss/train': 4.776963233947754} 08/30/2021 13:27:06 - INFO - __main__ - Step 1239: {'lr': 0.0003095, 'samples': 237888, 'steps': 1238, 'loss/train': 4.345894813537598} 08/30/2021 13:27:07 - INFO - __main__ - Step 1240: {'lr': 0.00030975, 'samples': 238080, 'steps': 1239, 'loss/train': 5.152431488037109} 08/30/2021 13:27:08 - INFO - __main__ - Step 1241: {'lr': 0.00031, 'samples': 238272, 'steps': 1240, 'loss/train': 4.401095867156982} 08/30/2021 13:27:08 - INFO - __main__ - Step 1242: {'lr': 0.00031025000000000003, 'samples': 238464, 'steps': 1241, 'loss/train': 4.679511070251465} 08/30/2021 13:27:09 - INFO - __main__ - Step 1243: {'lr': 0.0003105, 'samples': 238656, 'steps': 1242, 'loss/train': 4.977512359619141} 08/30/2021 13:27:09 - INFO - __main__ - Step 1244: {'lr': 0.00031075000000000005, 'samples': 238848, 'steps': 1243, 'loss/train': 4.606505870819092} 08/30/2021 13:27:10 - INFO - __main__ - Step 1245: {'lr': 0.000311, 'samples': 239040, 'steps': 1244, 'loss/train': 4.016382694244385} 08/30/2021 13:27:11 - INFO - __main__ - Step 1246: {'lr': 0.00031125000000000006, 'samples': 239232, 'steps': 1245, 'loss/train': 4.495089054107666} 08/30/2021 13:27:11 - INFO - __main__ - Step 1247: {'lr': 0.0003115, 'samples': 239424, 'steps': 1246, 'loss/train': 4.898197174072266} 08/30/2021 13:27:12 - INFO - __main__ - Step 1248: {'lr': 0.00031175, 'samples': 239616, 'steps': 1247, 'loss/train': 4.841574668884277} 08/30/2021 13:27:12 - INFO - __main__ - Step 1249: {'lr': 0.000312, 'samples': 239808, 'steps': 1248, 'loss/train': 4.659887790679932} 08/30/2021 13:27:14 - INFO - __main__ - Step 1250: {'lr': 0.00031225000000000003, 'samples': 240000, 'steps': 1249, 'loss/train': 4.44929313659668} 08/30/2021 13:27:14 - INFO - __main__ - Step 1251: {'lr': 0.0003125, 'samples': 240192, 'steps': 1250, 'loss/train': 3.747215747833252} 08/30/2021 13:27:15 - INFO - __main__ - Step 1252: {'lr': 0.00031275, 'samples': 240384, 'steps': 1251, 'loss/train': 4.292858600616455} 08/30/2021 13:27:15 - INFO - __main__ - Step 1253: {'lr': 0.000313, 'samples': 240576, 'steps': 1252, 'loss/train': 4.516558647155762} 08/30/2021 13:27:15 - INFO - __main__ - Step 1254: {'lr': 0.00031325, 'samples': 240768, 'steps': 1253, 'loss/train': 4.808173179626465} 08/30/2021 13:27:17 - INFO - __main__ - Step 1255: {'lr': 0.00031350000000000003, 'samples': 240960, 'steps': 1254, 'loss/train': 4.414249420166016} 08/30/2021 13:27:17 - INFO - __main__ - Step 1256: {'lr': 0.00031374999999999996, 'samples': 241152, 'steps': 1255, 'loss/train': 4.453027725219727} 08/30/2021 13:27:18 - INFO - __main__ - Step 1257: {'lr': 0.000314, 'samples': 241344, 'steps': 1256, 'loss/train': 5.009148597717285} 08/30/2021 13:27:18 - INFO - __main__ - Step 1258: {'lr': 0.00031424999999999997, 'samples': 241536, 'steps': 1257, 'loss/train': 3.922722339630127} 08/30/2021 13:27:18 - INFO - __main__ - Step 1259: {'lr': 0.0003145, 'samples': 241728, 'steps': 1258, 'loss/train': 4.6702423095703125} 08/30/2021 13:27:19 - INFO - __main__ - Step 1260: {'lr': 0.00031475, 'samples': 241920, 'steps': 1259, 'loss/train': 4.826611518859863} 08/30/2021 13:27:20 - INFO - __main__ - Step 1261: {'lr': 0.000315, 'samples': 242112, 'steps': 1260, 'loss/train': 5.18397331237793} 08/30/2021 13:27:21 - INFO - __main__ - Step 1262: {'lr': 0.00031525, 'samples': 242304, 'steps': 1261, 'loss/train': 4.696173191070557} 08/30/2021 13:27:21 - INFO - __main__ - Step 1263: {'lr': 0.0003155, 'samples': 242496, 'steps': 1262, 'loss/train': 4.818138122558594} 08/30/2021 13:27:21 - INFO - __main__ - Step 1264: {'lr': 0.00031575, 'samples': 242688, 'steps': 1263, 'loss/train': 5.506348133087158} 08/30/2021 13:27:22 - INFO - __main__ - Step 1265: {'lr': 0.000316, 'samples': 242880, 'steps': 1264, 'loss/train': 4.260590553283691} 08/30/2021 13:27:23 - INFO - __main__ - Step 1266: {'lr': 0.00031624999999999996, 'samples': 243072, 'steps': 1265, 'loss/train': 4.641239643096924} 08/30/2021 13:27:24 - INFO - __main__ - Step 1267: {'lr': 0.0003165, 'samples': 243264, 'steps': 1266, 'loss/train': 4.229900360107422} 08/30/2021 13:27:24 - INFO - __main__ - Step 1268: {'lr': 0.00031675, 'samples': 243456, 'steps': 1267, 'loss/train': 4.410894393920898} 08/30/2021 13:27:24 - INFO - __main__ - Step 1269: {'lr': 0.000317, 'samples': 243648, 'steps': 1268, 'loss/train': 4.6991496086120605} 08/30/2021 13:27:25 - INFO - __main__ - Step 1270: {'lr': 0.00031725, 'samples': 243840, 'steps': 1269, 'loss/train': 4.288592338562012} 08/30/2021 13:27:26 - INFO - __main__ - Step 1271: {'lr': 0.0003175, 'samples': 244032, 'steps': 1270, 'loss/train': 4.804139137268066} 08/30/2021 13:27:27 - INFO - __main__ - Step 1272: {'lr': 0.00031775, 'samples': 244224, 'steps': 1271, 'loss/train': 4.242639064788818} 08/30/2021 13:27:27 - INFO - __main__ - Step 1273: {'lr': 0.00031800000000000003, 'samples': 244416, 'steps': 1272, 'loss/train': 4.992812156677246} 08/30/2021 13:27:27 - INFO - __main__ - Step 1274: {'lr': 0.00031825, 'samples': 244608, 'steps': 1273, 'loss/train': 4.1714277267456055} 08/30/2021 13:27:28 - INFO - __main__ - Step 1275: {'lr': 0.0003185, 'samples': 244800, 'steps': 1274, 'loss/train': 1.792271375656128} 08/30/2021 13:27:29 - INFO - __main__ - Step 1276: {'lr': 0.00031874999999999997, 'samples': 244992, 'steps': 1275, 'loss/train': 4.166008472442627} 08/30/2021 13:27:30 - INFO - __main__ - Step 1277: {'lr': 0.000319, 'samples': 245184, 'steps': 1276, 'loss/train': 4.203356742858887} 08/30/2021 13:27:30 - INFO - __main__ - Step 1278: {'lr': 0.00031925, 'samples': 245376, 'steps': 1277, 'loss/train': 4.392521858215332} 08/30/2021 13:27:30 - INFO - __main__ - Step 1279: {'lr': 0.0003195, 'samples': 245568, 'steps': 1278, 'loss/train': 5.123244285583496} 08/30/2021 13:27:31 - INFO - __main__ - Step 1280: {'lr': 0.00031975, 'samples': 245760, 'steps': 1279, 'loss/train': 4.326639175415039} 08/30/2021 13:27:31 - INFO - __main__ - Step 1281: {'lr': 0.00032, 'samples': 245952, 'steps': 1280, 'loss/train': 4.643868923187256} 08/30/2021 13:27:33 - INFO - __main__ - Step 1282: {'lr': 0.00032025, 'samples': 246144, 'steps': 1281, 'loss/train': 4.453815937042236} 08/30/2021 13:27:33 - INFO - __main__ - Step 1283: {'lr': 0.00032050000000000004, 'samples': 246336, 'steps': 1282, 'loss/train': 4.541042804718018} 08/30/2021 13:27:34 - INFO - __main__ - Step 1284: {'lr': 0.00032074999999999996, 'samples': 246528, 'steps': 1283, 'loss/train': 4.184276103973389} 08/30/2021 13:27:34 - INFO - __main__ - Step 1285: {'lr': 0.000321, 'samples': 246720, 'steps': 1284, 'loss/train': 4.502721786499023} 08/30/2021 13:27:34 - INFO - __main__ - Step 1286: {'lr': 0.00032125, 'samples': 246912, 'steps': 1285, 'loss/train': 4.524459362030029} 08/30/2021 13:27:36 - INFO - __main__ - Step 1287: {'lr': 0.0003215, 'samples': 247104, 'steps': 1286, 'loss/train': 4.998214244842529} 08/30/2021 13:27:36 - INFO - __main__ - Step 1288: {'lr': 0.00032175, 'samples': 247296, 'steps': 1287, 'loss/train': 4.486813068389893} 08/30/2021 13:27:36 - INFO - __main__ - Step 1289: {'lr': 0.000322, 'samples': 247488, 'steps': 1288, 'loss/train': 3.9918529987335205} 08/30/2021 13:27:37 - INFO - __main__ - Step 1290: {'lr': 0.00032225, 'samples': 247680, 'steps': 1289, 'loss/train': 4.199202537536621} 08/30/2021 13:27:37 - INFO - __main__ - Step 1291: {'lr': 0.00032250000000000003, 'samples': 247872, 'steps': 1290, 'loss/train': 4.5257134437561035} 08/30/2021 13:27:39 - INFO - __main__ - Step 1292: {'lr': 0.00032275, 'samples': 248064, 'steps': 1291, 'loss/train': 3.9086365699768066} 08/30/2021 13:27:39 - INFO - __main__ - Step 1293: {'lr': 0.000323, 'samples': 248256, 'steps': 1292, 'loss/train': 4.684390068054199} 08/30/2021 13:27:40 - INFO - __main__ - Step 1294: {'lr': 0.00032324999999999997, 'samples': 248448, 'steps': 1293, 'loss/train': 4.8196120262146} 08/30/2021 13:27:40 - INFO - __main__ - Step 1295: {'lr': 0.0003235, 'samples': 248640, 'steps': 1294, 'loss/train': 4.693305492401123} 08/30/2021 13:27:40 - INFO - __main__ - Step 1296: {'lr': 0.00032375, 'samples': 248832, 'steps': 1295, 'loss/train': 4.538880825042725} 08/30/2021 13:27:42 - INFO - __main__ - Step 1297: {'lr': 0.000324, 'samples': 249024, 'steps': 1296, 'loss/train': 3.790248155593872} 08/30/2021 13:27:42 - INFO - __main__ - Step 1298: {'lr': 0.00032425, 'samples': 249216, 'steps': 1297, 'loss/train': 4.5623779296875} 08/30/2021 13:27:43 - INFO - __main__ - Step 1299: {'lr': 0.00032450000000000003, 'samples': 249408, 'steps': 1298, 'loss/train': 4.117589950561523} 08/30/2021 13:27:43 - INFO - __main__ - Step 1300: {'lr': 0.00032475, 'samples': 249600, 'steps': 1299, 'loss/train': 4.715627670288086} 08/30/2021 13:27:43 - INFO - __main__ - Step 1301: {'lr': 0.00032500000000000004, 'samples': 249792, 'steps': 1300, 'loss/train': 4.385561943054199} 08/30/2021 13:27:45 - INFO - __main__ - Step 1302: {'lr': 0.00032524999999999996, 'samples': 249984, 'steps': 1301, 'loss/train': 4.569333076477051} 08/30/2021 13:27:46 - INFO - __main__ - Step 1303: {'lr': 0.0003255, 'samples': 250176, 'steps': 1302, 'loss/train': 4.422083377838135} 08/30/2021 13:27:46 - INFO - __main__ - Step 1304: {'lr': 0.00032575, 'samples': 250368, 'steps': 1303, 'loss/train': 4.419223308563232} 08/30/2021 13:27:47 - INFO - __main__ - Step 1305: {'lr': 0.000326, 'samples': 250560, 'steps': 1304, 'loss/train': 4.673562049865723} 08/30/2021 13:27:47 - INFO - __main__ - Step 1306: {'lr': 0.00032625, 'samples': 250752, 'steps': 1305, 'loss/train': 4.185782432556152} 08/30/2021 13:27:48 - INFO - __main__ - Step 1307: {'lr': 0.0003265, 'samples': 250944, 'steps': 1306, 'loss/train': 4.824061393737793} 08/30/2021 13:27:49 - INFO - __main__ - Step 1308: {'lr': 0.00032675, 'samples': 251136, 'steps': 1307, 'loss/train': 4.664660930633545} 08/30/2021 13:27:49 - INFO - __main__ - Step 1309: {'lr': 0.00032700000000000003, 'samples': 251328, 'steps': 1308, 'loss/train': 4.350864887237549} 08/30/2021 13:27:50 - INFO - __main__ - Step 1310: {'lr': 0.00032725, 'samples': 251520, 'steps': 1309, 'loss/train': 3.9895272254943848} 08/30/2021 13:27:50 - INFO - __main__ - Step 1311: {'lr': 0.00032750000000000005, 'samples': 251712, 'steps': 1310, 'loss/train': 5.069451332092285} 08/30/2021 13:27:51 - INFO - __main__ - Step 1312: {'lr': 0.00032774999999999997, 'samples': 251904, 'steps': 1311, 'loss/train': 4.556570529937744} 08/30/2021 13:27:52 - INFO - __main__ - Step 1313: {'lr': 0.000328, 'samples': 252096, 'steps': 1312, 'loss/train': 4.382578372955322} 08/30/2021 13:27:52 - INFO - __main__ - Step 1314: {'lr': 0.00032825, 'samples': 252288, 'steps': 1313, 'loss/train': 2.4415385723114014} 08/30/2021 13:27:53 - INFO - __main__ - Step 1315: {'lr': 0.0003285, 'samples': 252480, 'steps': 1314, 'loss/train': 4.276082515716553} 08/30/2021 13:27:53 - INFO - __main__ - Step 1316: {'lr': 0.00032875, 'samples': 252672, 'steps': 1315, 'loss/train': 4.509583473205566} 08/30/2021 13:27:54 - INFO - __main__ - Step 1317: {'lr': 0.00032900000000000003, 'samples': 252864, 'steps': 1316, 'loss/train': 4.153806686401367} 08/30/2021 13:27:55 - INFO - __main__ - Step 1318: {'lr': 0.00032925, 'samples': 253056, 'steps': 1317, 'loss/train': 4.242760181427002} 08/30/2021 13:27:55 - INFO - __main__ - Step 1319: {'lr': 0.00032950000000000004, 'samples': 253248, 'steps': 1318, 'loss/train': 3.9864144325256348} 08/30/2021 13:27:56 - INFO - __main__ - Step 1320: {'lr': 0.00032975, 'samples': 253440, 'steps': 1319, 'loss/train': 4.75071382522583} 08/30/2021 13:27:56 - INFO - __main__ - Step 1321: {'lr': 0.00033, 'samples': 253632, 'steps': 1320, 'loss/train': 3.9804000854492188} 08/30/2021 13:27:57 - INFO - __main__ - Step 1322: {'lr': 0.00033025, 'samples': 253824, 'steps': 1321, 'loss/train': 3.368206024169922} 08/30/2021 13:27:58 - INFO - __main__ - Step 1323: {'lr': 0.0003305, 'samples': 254016, 'steps': 1322, 'loss/train': 4.578549385070801} 08/30/2021 13:27:58 - INFO - __main__ - Step 1324: {'lr': 0.00033075, 'samples': 254208, 'steps': 1323, 'loss/train': 4.7281036376953125} 08/30/2021 13:27:58 - INFO - __main__ - Step 1325: {'lr': 0.000331, 'samples': 254400, 'steps': 1324, 'loss/train': 3.5485174655914307} 08/30/2021 13:27:59 - INFO - __main__ - Step 1326: {'lr': 0.00033125, 'samples': 254592, 'steps': 1325, 'loss/train': 6.437094211578369} 08/30/2021 13:27:59 - INFO - __main__ - Step 1327: {'lr': 0.00033150000000000003, 'samples': 254784, 'steps': 1326, 'loss/train': 4.145354270935059} 08/30/2021 13:28:01 - INFO - __main__ - Step 1328: {'lr': 0.00033175, 'samples': 254976, 'steps': 1327, 'loss/train': 5.2326860427856445} 08/30/2021 13:28:01 - INFO - __main__ - Step 1329: {'lr': 0.00033200000000000005, 'samples': 255168, 'steps': 1328, 'loss/train': 4.132408618927002} 08/30/2021 13:28:01 - INFO - __main__ - Step 1330: {'lr': 0.00033224999999999997, 'samples': 255360, 'steps': 1329, 'loss/train': 5.378190994262695} 08/30/2021 13:28:02 - INFO - __main__ - Step 1331: {'lr': 0.0003325, 'samples': 255552, 'steps': 1330, 'loss/train': 7.080970287322998} 08/30/2021 13:28:02 - INFO - __main__ - Step 1332: {'lr': 0.00033275, 'samples': 255744, 'steps': 1331, 'loss/train': 4.624168872833252} 08/30/2021 13:28:04 - INFO - __main__ - Step 1333: {'lr': 0.000333, 'samples': 255936, 'steps': 1332, 'loss/train': 4.436684608459473} 08/30/2021 13:28:04 - INFO - __main__ - Step 1334: {'lr': 0.00033325, 'samples': 256128, 'steps': 1333, 'loss/train': 4.374962329864502} 08/30/2021 13:28:05 - INFO - __main__ - Step 1335: {'lr': 0.00033350000000000003, 'samples': 256320, 'steps': 1334, 'loss/train': 4.5060529708862305} 08/30/2021 13:28:05 - INFO - __main__ - Step 1336: {'lr': 0.00033375, 'samples': 256512, 'steps': 1335, 'loss/train': 4.0865559577941895} 08/30/2021 13:28:05 - INFO - __main__ - Step 1337: {'lr': 0.00033400000000000004, 'samples': 256704, 'steps': 1336, 'loss/train': 4.452343463897705} 08/30/2021 13:28:07 - INFO - __main__ - Step 1338: {'lr': 0.00033425, 'samples': 256896, 'steps': 1337, 'loss/train': 4.250465393066406} 08/30/2021 13:28:07 - INFO - __main__ - Step 1339: {'lr': 0.00033450000000000005, 'samples': 257088, 'steps': 1338, 'loss/train': 4.740878582000732} 08/30/2021 13:28:07 - INFO - __main__ - Step 1340: {'lr': 0.00033475, 'samples': 257280, 'steps': 1339, 'loss/train': 3.674431085586548} 08/30/2021 13:28:08 - INFO - __main__ - Step 1341: {'lr': 0.000335, 'samples': 257472, 'steps': 1340, 'loss/train': 4.267061710357666} 08/30/2021 13:28:08 - INFO - __main__ - Step 1342: {'lr': 0.00033525, 'samples': 257664, 'steps': 1341, 'loss/train': 3.882347345352173} 08/30/2021 13:28:10 - INFO - __main__ - Step 1343: {'lr': 0.0003355, 'samples': 257856, 'steps': 1342, 'loss/train': 4.04584264755249} 08/30/2021 13:28:10 - INFO - __main__ - Step 1344: {'lr': 0.00033575, 'samples': 258048, 'steps': 1343, 'loss/train': 5.775942325592041} 08/30/2021 13:28:10 - INFO - __main__ - Step 1345: {'lr': 0.00033600000000000004, 'samples': 258240, 'steps': 1344, 'loss/train': 4.075455188751221} 08/30/2021 13:28:11 - INFO - __main__ - Step 1346: {'lr': 0.00033625, 'samples': 258432, 'steps': 1345, 'loss/train': 5.206962585449219} 08/30/2021 13:28:11 - INFO - __main__ - Step 1347: {'lr': 0.00033650000000000005, 'samples': 258624, 'steps': 1346, 'loss/train': 4.038782596588135} 08/30/2021 13:28:13 - INFO - __main__ - Step 1348: {'lr': 0.00033675, 'samples': 258816, 'steps': 1347, 'loss/train': 5.3180060386657715} 08/30/2021 13:28:13 - INFO - __main__ - Step 1349: {'lr': 0.000337, 'samples': 259008, 'steps': 1348, 'loss/train': 3.534853219985962} 08/30/2021 13:28:13 - INFO - __main__ - Step 1350: {'lr': 0.00033725, 'samples': 259200, 'steps': 1349, 'loss/train': 4.311325550079346} 08/30/2021 13:28:14 - INFO - __main__ - Step 1351: {'lr': 0.0003375, 'samples': 259392, 'steps': 1350, 'loss/train': 4.755340576171875} 08/30/2021 13:28:14 - INFO - __main__ - Step 1352: {'lr': 0.00033775, 'samples': 259584, 'steps': 1351, 'loss/train': 2.4528939723968506} 08/30/2021 13:28:16 - INFO - __main__ - Step 1353: {'lr': 0.00033800000000000003, 'samples': 259776, 'steps': 1352, 'loss/train': 4.556753635406494} 08/30/2021 13:28:16 - INFO - __main__ - Step 1354: {'lr': 0.00033825, 'samples': 259968, 'steps': 1353, 'loss/train': 4.163471698760986} 08/30/2021 13:28:16 - INFO - __main__ - Step 1355: {'lr': 0.00033850000000000004, 'samples': 260160, 'steps': 1354, 'loss/train': 4.440191745758057} 08/30/2021 13:28:17 - INFO - __main__ - Step 1356: {'lr': 0.00033875, 'samples': 260352, 'steps': 1355, 'loss/train': 4.314537525177002} 08/30/2021 13:28:17 - INFO - __main__ - Step 1357: {'lr': 0.00033900000000000005, 'samples': 260544, 'steps': 1356, 'loss/train': 4.676640033721924} 08/30/2021 13:28:19 - INFO - __main__ - Step 1358: {'lr': 0.00033925, 'samples': 260736, 'steps': 1357, 'loss/train': 3.737349033355713} 08/30/2021 13:28:19 - INFO - __main__ - Step 1359: {'lr': 0.0003395, 'samples': 260928, 'steps': 1358, 'loss/train': 4.140536308288574} 08/30/2021 13:28:20 - INFO - __main__ - Step 1360: {'lr': 0.00033975, 'samples': 261120, 'steps': 1359, 'loss/train': 4.576985836029053} 08/30/2021 13:28:20 - INFO - __main__ - Step 1361: {'lr': 0.00034, 'samples': 261312, 'steps': 1360, 'loss/train': 4.539398193359375} 08/30/2021 13:28:21 - INFO - __main__ - Step 1362: {'lr': 0.00034025, 'samples': 261504, 'steps': 1361, 'loss/train': 5.453786373138428} 08/30/2021 13:28:22 - INFO - __main__ - Step 1363: {'lr': 0.00034050000000000004, 'samples': 261696, 'steps': 1362, 'loss/train': 4.280670642852783} 08/30/2021 13:28:23 - INFO - __main__ - Step 1364: {'lr': 0.00034075, 'samples': 261888, 'steps': 1363, 'loss/train': 3.8596203327178955} 08/30/2021 13:28:23 - INFO - __main__ - Step 1365: {'lr': 0.00034100000000000005, 'samples': 262080, 'steps': 1364, 'loss/train': 3.9746007919311523} 08/30/2021 13:28:23 - INFO - __main__ - Step 1366: {'lr': 0.00034125000000000003, 'samples': 262272, 'steps': 1365, 'loss/train': 4.350702285766602} 08/30/2021 13:28:24 - INFO - __main__ - Step 1367: {'lr': 0.0003415, 'samples': 262464, 'steps': 1366, 'loss/train': 4.536733150482178} 08/30/2021 13:28:24 - INFO - __main__ - Step 1368: {'lr': 0.00034175, 'samples': 262656, 'steps': 1367, 'loss/train': 4.735171318054199} 08/30/2021 13:28:25 - INFO - __main__ - Step 1369: {'lr': 0.000342, 'samples': 262848, 'steps': 1368, 'loss/train': 4.363914966583252} 08/30/2021 13:28:26 - INFO - __main__ - Step 1370: {'lr': 0.00034225, 'samples': 263040, 'steps': 1369, 'loss/train': 4.070268630981445} 08/30/2021 13:28:26 - INFO - __main__ - Step 1371: {'lr': 0.00034250000000000003, 'samples': 263232, 'steps': 1370, 'loss/train': 4.607729911804199} 08/30/2021 13:28:27 - INFO - __main__ - Step 1372: {'lr': 0.00034275, 'samples': 263424, 'steps': 1371, 'loss/train': 4.5332465171813965} 08/30/2021 13:28:27 - INFO - __main__ - Step 1373: {'lr': 0.00034300000000000004, 'samples': 263616, 'steps': 1372, 'loss/train': 4.54966402053833} 08/30/2021 13:28:28 - INFO - __main__ - Step 1374: {'lr': 0.00034325, 'samples': 263808, 'steps': 1373, 'loss/train': 4.341580390930176} 08/30/2021 13:28:29 - INFO - __main__ - Step 1375: {'lr': 0.00034350000000000006, 'samples': 264000, 'steps': 1374, 'loss/train': 3.9261229038238525} 08/30/2021 13:28:29 - INFO - __main__ - Step 1376: {'lr': 0.00034375, 'samples': 264192, 'steps': 1375, 'loss/train': 4.626092433929443} 08/30/2021 13:28:30 - INFO - __main__ - Step 1377: {'lr': 0.00034399999999999996, 'samples': 264384, 'steps': 1376, 'loss/train': 4.53762149810791} 08/30/2021 13:28:30 - INFO - __main__ - Step 1378: {'lr': 0.00034425, 'samples': 264576, 'steps': 1377, 'loss/train': 4.843814373016357} 08/30/2021 13:28:31 - INFO - __main__ - Step 1379: {'lr': 0.00034449999999999997, 'samples': 264768, 'steps': 1378, 'loss/train': 4.533663749694824} 08/30/2021 13:28:32 - INFO - __main__ - Step 1380: {'lr': 0.00034475, 'samples': 264960, 'steps': 1379, 'loss/train': 4.268194675445557} 08/30/2021 13:28:32 - INFO - __main__ - Step 1381: {'lr': 0.000345, 'samples': 265152, 'steps': 1380, 'loss/train': 4.627920150756836} 08/30/2021 13:28:33 - INFO - __main__ - Step 1382: {'lr': 0.00034525, 'samples': 265344, 'steps': 1381, 'loss/train': 4.625608921051025} 08/30/2021 13:28:33 - INFO - __main__ - Step 1383: {'lr': 0.0003455, 'samples': 265536, 'steps': 1382, 'loss/train': 4.480739116668701} 08/30/2021 13:28:34 - INFO - __main__ - Step 1384: {'lr': 0.00034575000000000003, 'samples': 265728, 'steps': 1383, 'loss/train': 4.329967975616455} 08/30/2021 13:28:35 - INFO - __main__ - Step 1385: {'lr': 0.000346, 'samples': 265920, 'steps': 1384, 'loss/train': 4.387570858001709} 08/30/2021 13:28:35 - INFO - __main__ - Step 1386: {'lr': 0.00034625, 'samples': 266112, 'steps': 1385, 'loss/train': 4.490174770355225} 08/30/2021 13:28:36 - INFO - __main__ - Step 1387: {'lr': 0.00034649999999999997, 'samples': 266304, 'steps': 1386, 'loss/train': 4.425543785095215} 08/30/2021 13:28:36 - INFO - __main__ - Step 1388: {'lr': 0.00034675, 'samples': 266496, 'steps': 1387, 'loss/train': 3.9120686054229736} 08/30/2021 13:28:37 - INFO - __main__ - Step 1389: {'lr': 0.000347, 'samples': 266688, 'steps': 1388, 'loss/train': 4.659025192260742} 08/30/2021 13:28:38 - INFO - __main__ - Step 1390: {'lr': 0.00034725, 'samples': 266880, 'steps': 1389, 'loss/train': 4.53112268447876} 08/30/2021 13:28:38 - INFO - __main__ - Step 1391: {'lr': 0.0003475, 'samples': 267072, 'steps': 1390, 'loss/train': 4.275741100311279} 08/30/2021 13:28:38 - INFO - __main__ - Step 1392: {'lr': 0.00034775, 'samples': 267264, 'steps': 1391, 'loss/train': 4.180943965911865} 08/30/2021 13:28:39 - INFO - __main__ - Step 1393: {'lr': 0.000348, 'samples': 267456, 'steps': 1392, 'loss/train': 4.7057576179504395} 08/30/2021 13:28:40 - INFO - __main__ - Step 1394: {'lr': 0.00034825000000000004, 'samples': 267648, 'steps': 1393, 'loss/train': 4.166080951690674} 08/30/2021 13:28:41 - INFO - __main__ - Step 1395: {'lr': 0.00034849999999999996, 'samples': 267840, 'steps': 1394, 'loss/train': 4.255853652954102} 08/30/2021 13:28:41 - INFO - __main__ - Step 1396: {'lr': 0.00034875, 'samples': 268032, 'steps': 1395, 'loss/train': 4.1657938957214355} 08/30/2021 13:28:41 - INFO - __main__ - Step 1397: {'lr': 0.00034899999999999997, 'samples': 268224, 'steps': 1396, 'loss/train': 4.592858791351318} 08/30/2021 13:28:42 - INFO - __main__ - Step 1398: {'lr': 0.00034925, 'samples': 268416, 'steps': 1397, 'loss/train': 4.626420974731445} 08/30/2021 13:28:42 - INFO - __main__ - Step 1399: {'lr': 0.0003495, 'samples': 268608, 'steps': 1398, 'loss/train': 4.299635887145996} 08/30/2021 13:28:44 - INFO - __main__ - Step 1400: {'lr': 0.00034975, 'samples': 268800, 'steps': 1399, 'loss/train': 4.366077423095703} 08/30/2021 13:28:44 - INFO - __main__ - Step 1401: {'lr': 0.00035, 'samples': 268992, 'steps': 1400, 'loss/train': 5.40753698348999} 08/30/2021 13:28:45 - INFO - __main__ - Step 1402: {'lr': 0.00035025000000000003, 'samples': 269184, 'steps': 1401, 'loss/train': 4.4894537925720215} 08/30/2021 13:28:45 - INFO - __main__ - Step 1403: {'lr': 0.0003505, 'samples': 269376, 'steps': 1402, 'loss/train': 4.545291423797607} 08/30/2021 13:28:45 - INFO - __main__ - Step 1404: {'lr': 0.00035075, 'samples': 269568, 'steps': 1403, 'loss/train': 4.797220706939697} 08/30/2021 13:28:47 - INFO - __main__ - Step 1405: {'lr': 0.00035099999999999997, 'samples': 269760, 'steps': 1404, 'loss/train': 4.782083034515381} 08/30/2021 13:28:48 - INFO - __main__ - Step 1406: {'lr': 0.00035125, 'samples': 269952, 'steps': 1405, 'loss/train': 4.428123950958252} 08/30/2021 13:28:48 - INFO - __main__ - Step 1407: {'lr': 0.0003515, 'samples': 270144, 'steps': 1406, 'loss/train': 4.661625862121582} 08/30/2021 13:28:48 - INFO - __main__ - Step 1408: {'lr': 0.00035175, 'samples': 270336, 'steps': 1407, 'loss/train': 3.7704012393951416} 08/30/2021 13:28:49 - INFO - __main__ - Step 1409: {'lr': 0.000352, 'samples': 270528, 'steps': 1408, 'loss/train': 4.755863189697266} 08/30/2021 13:28:50 - INFO - __main__ - Step 1410: {'lr': 0.00035225, 'samples': 270720, 'steps': 1409, 'loss/train': 4.273111820220947} 08/30/2021 13:28:51 - INFO - __main__ - Step 1411: {'lr': 0.0003525, 'samples': 270912, 'steps': 1410, 'loss/train': 4.178704738616943} 08/30/2021 13:28:51 - INFO - __main__ - Step 1412: {'lr': 0.00035275000000000004, 'samples': 271104, 'steps': 1411, 'loss/train': 4.520911693572998} 08/30/2021 13:28:52 - INFO - __main__ - Step 1413: {'lr': 0.00035299999999999996, 'samples': 271296, 'steps': 1412, 'loss/train': 4.139966011047363} 08/30/2021 13:28:52 - INFO - __main__ - Step 1414: {'lr': 0.00035325, 'samples': 271488, 'steps': 1413, 'loss/train': 4.225654125213623} 08/30/2021 13:28:53 - INFO - __main__ - Step 1415: {'lr': 0.0003535, 'samples': 271680, 'steps': 1414, 'loss/train': 4.571483612060547} 08/30/2021 13:28:54 - INFO - __main__ - Step 1416: {'lr': 0.00035375, 'samples': 271872, 'steps': 1415, 'loss/train': 4.365446090698242} 08/30/2021 13:28:54 - INFO - __main__ - Step 1417: {'lr': 0.000354, 'samples': 272064, 'steps': 1416, 'loss/train': 4.675602912902832} 08/30/2021 13:28:55 - INFO - __main__ - Step 1418: {'lr': 0.00035425, 'samples': 272256, 'steps': 1417, 'loss/train': 4.224637508392334} 08/30/2021 13:28:55 - INFO - __main__ - Step 1419: {'lr': 0.0003545, 'samples': 272448, 'steps': 1418, 'loss/train': 4.211911678314209} 08/30/2021 13:28:55 - INFO - __main__ - Step 1420: {'lr': 0.00035475000000000003, 'samples': 272640, 'steps': 1419, 'loss/train': 5.085281848907471} 08/30/2021 13:28:57 - INFO - __main__ - Step 1421: {'lr': 0.000355, 'samples': 272832, 'steps': 1420, 'loss/train': 4.593563079833984} 08/30/2021 13:28:57 - INFO - __main__ - Step 1422: {'lr': 0.00035525000000000004, 'samples': 273024, 'steps': 1421, 'loss/train': 4.751321315765381} 08/30/2021 13:28:58 - INFO - __main__ - Step 1423: {'lr': 0.00035549999999999997, 'samples': 273216, 'steps': 1422, 'loss/train': 4.472665309906006} 08/30/2021 13:28:58 - INFO - __main__ - Step 1424: {'lr': 0.00035575, 'samples': 273408, 'steps': 1423, 'loss/train': 4.202507972717285} 08/30/2021 13:28:58 - INFO - __main__ - Step 1425: {'lr': 0.000356, 'samples': 273600, 'steps': 1424, 'loss/train': 4.3050994873046875} 08/30/2021 13:29:00 - INFO - __main__ - Step 1426: {'lr': 0.00035625, 'samples': 273792, 'steps': 1425, 'loss/train': 4.268754005432129} 08/30/2021 13:29:00 - INFO - __main__ - Step 1427: {'lr': 0.0003565, 'samples': 273984, 'steps': 1426, 'loss/train': 4.267064094543457} 08/30/2021 13:29:00 - INFO - __main__ - Step 1428: {'lr': 0.00035675, 'samples': 274176, 'steps': 1427, 'loss/train': 4.332093238830566} 08/30/2021 13:29:01 - INFO - __main__ - Step 1429: {'lr': 0.000357, 'samples': 274368, 'steps': 1428, 'loss/train': 4.247141361236572} 08/30/2021 13:29:01 - INFO - __main__ - Step 1430: {'lr': 0.00035725000000000004, 'samples': 274560, 'steps': 1429, 'loss/train': 3.9781038761138916} 08/30/2021 13:29:03 - INFO - __main__ - Step 1431: {'lr': 0.0003575, 'samples': 274752, 'steps': 1430, 'loss/train': 4.520853519439697} 08/30/2021 13:29:03 - INFO - __main__ - Step 1432: {'lr': 0.00035775, 'samples': 274944, 'steps': 1431, 'loss/train': 4.8411736488342285} 08/30/2021 13:29:03 - INFO - __main__ - Step 1433: {'lr': 0.000358, 'samples': 275136, 'steps': 1432, 'loss/train': 4.100142002105713} 08/30/2021 13:29:04 - INFO - __main__ - Step 1434: {'lr': 0.00035825, 'samples': 275328, 'steps': 1433, 'loss/train': 4.149476528167725} 08/30/2021 13:29:04 - INFO - __main__ - Step 1435: {'lr': 0.0003585, 'samples': 275520, 'steps': 1434, 'loss/train': 4.42181396484375} 08/30/2021 13:29:06 - INFO - __main__ - Step 1436: {'lr': 0.00035875, 'samples': 275712, 'steps': 1435, 'loss/train': 4.3713226318359375} 08/30/2021 13:29:06 - INFO - __main__ - Step 1437: {'lr': 0.000359, 'samples': 275904, 'steps': 1436, 'loss/train': 4.0421648025512695} 08/30/2021 13:29:06 - INFO - __main__ - Step 1438: {'lr': 0.00035925000000000003, 'samples': 276096, 'steps': 1437, 'loss/train': 4.149511337280273} 08/30/2021 13:29:07 - INFO - __main__ - Step 1439: {'lr': 0.0003595, 'samples': 276288, 'steps': 1438, 'loss/train': 4.122163772583008} 08/30/2021 13:29:07 - INFO - __main__ - Step 1440: {'lr': 0.00035975000000000004, 'samples': 276480, 'steps': 1439, 'loss/train': 4.252772808074951} 08/30/2021 13:29:09 - INFO - __main__ - Step 1441: {'lr': 0.00035999999999999997, 'samples': 276672, 'steps': 1440, 'loss/train': 4.3171210289001465} 08/30/2021 13:29:09 - INFO - __main__ - Step 1442: {'lr': 0.00036025, 'samples': 276864, 'steps': 1441, 'loss/train': 4.632924556732178} 08/30/2021 13:29:10 - INFO - __main__ - Step 1443: {'lr': 0.0003605, 'samples': 277056, 'steps': 1442, 'loss/train': 4.305054664611816} 08/30/2021 13:29:10 - INFO - __main__ - Step 1444: {'lr': 0.00036075, 'samples': 277248, 'steps': 1443, 'loss/train': 4.408972263336182} 08/30/2021 13:29:11 - INFO - __main__ - Step 1445: {'lr': 0.000361, 'samples': 277440, 'steps': 1444, 'loss/train': 4.228984832763672} 08/30/2021 13:29:12 - INFO - __main__ - Step 1446: {'lr': 0.00036125, 'samples': 277632, 'steps': 1445, 'loss/train': 4.329809665679932} 08/30/2021 13:29:12 - INFO - __main__ - Step 1447: {'lr': 0.0003615, 'samples': 277824, 'steps': 1446, 'loss/train': 4.439213752746582} 08/30/2021 13:29:13 - INFO - __main__ - Step 1448: {'lr': 0.00036175000000000004, 'samples': 278016, 'steps': 1447, 'loss/train': 4.233701705932617} 08/30/2021 13:29:13 - INFO - __main__ - Step 1449: {'lr': 0.000362, 'samples': 278208, 'steps': 1448, 'loss/train': 3.235466718673706} 08/30/2021 13:29:13 - INFO - __main__ - Step 1450: {'lr': 0.00036225000000000005, 'samples': 278400, 'steps': 1449, 'loss/train': 3.3804967403411865} 08/30/2021 13:29:15 - INFO - __main__ - Step 1451: {'lr': 0.0003625, 'samples': 278592, 'steps': 1450, 'loss/train': 4.406125068664551} 08/30/2021 13:29:15 - INFO - __main__ - Step 1452: {'lr': 0.00036275, 'samples': 278784, 'steps': 1451, 'loss/train': 1.672944188117981} 08/30/2021 13:29:16 - INFO - __main__ - Step 1453: {'lr': 0.000363, 'samples': 278976, 'steps': 1452, 'loss/train': 4.2426862716674805} 08/30/2021 13:29:16 - INFO - __main__ - Step 1454: {'lr': 0.00036325, 'samples': 279168, 'steps': 1453, 'loss/train': 4.787095546722412} 08/30/2021 13:29:16 - INFO - __main__ - Step 1455: {'lr': 0.0003635, 'samples': 279360, 'steps': 1454, 'loss/train': 4.5315728187561035} 08/30/2021 13:29:18 - INFO - __main__ - Step 1456: {'lr': 0.00036375000000000003, 'samples': 279552, 'steps': 1455, 'loss/train': 3.1854286193847656} 08/30/2021 13:29:19 - INFO - __main__ - Step 1457: {'lr': 0.000364, 'samples': 279744, 'steps': 1456, 'loss/train': 3.866952896118164} 08/30/2021 13:29:19 - INFO - __main__ - Step 1458: {'lr': 0.00036425000000000004, 'samples': 279936, 'steps': 1457, 'loss/train': 4.139428615570068} 08/30/2021 13:29:19 - INFO - __main__ - Step 1459: {'lr': 0.0003645, 'samples': 280128, 'steps': 1458, 'loss/train': 4.534155368804932} 08/30/2021 13:29:20 - INFO - __main__ - Step 1460: {'lr': 0.00036475, 'samples': 280320, 'steps': 1459, 'loss/train': 2.945066452026367} 08/30/2021 13:29:20 - INFO - __main__ - Step 1461: {'lr': 0.000365, 'samples': 280512, 'steps': 1460, 'loss/train': 2.2096877098083496} 08/30/2021 13:29:22 - INFO - __main__ - Step 1462: {'lr': 0.00036525, 'samples': 280704, 'steps': 1461, 'loss/train': 4.244150638580322} 08/30/2021 13:29:22 - INFO - __main__ - Step 1463: {'lr': 0.0003655, 'samples': 280896, 'steps': 1462, 'loss/train': 4.8449788093566895} 08/30/2021 13:29:22 - INFO - __main__ - Step 1464: {'lr': 0.00036575, 'samples': 281088, 'steps': 1463, 'loss/train': 3.7697691917419434} 08/30/2021 13:29:23 - INFO - __main__ - Step 1465: {'lr': 0.000366, 'samples': 281280, 'steps': 1464, 'loss/train': 4.358305931091309} 08/30/2021 13:29:23 - INFO - __main__ - Step 1466: {'lr': 0.00036625000000000004, 'samples': 281472, 'steps': 1465, 'loss/train': 6.622794151306152} 08/30/2021 13:29:25 - INFO - __main__ - Step 1467: {'lr': 0.0003665, 'samples': 281664, 'steps': 1466, 'loss/train': 4.413908958435059} 08/30/2021 13:29:26 - INFO - __main__ - Step 1468: {'lr': 0.00036675000000000005, 'samples': 281856, 'steps': 1467, 'loss/train': 4.058522701263428} 08/30/2021 13:29:26 - INFO - __main__ - Step 1469: {'lr': 0.000367, 'samples': 282048, 'steps': 1468, 'loss/train': 3.260404348373413} 08/30/2021 13:29:26 - INFO - __main__ - Step 1470: {'lr': 0.00036725, 'samples': 282240, 'steps': 1469, 'loss/train': 3.354424476623535} 08/30/2021 13:29:27 - INFO - __main__ - Step 1471: {'lr': 0.0003675, 'samples': 282432, 'steps': 1470, 'loss/train': 4.304652214050293} 08/30/2021 13:29:27 - INFO - __main__ - Step 1472: {'lr': 0.00036775, 'samples': 282624, 'steps': 1471, 'loss/train': 4.494898796081543} 08/30/2021 13:29:28 - INFO - __main__ - Step 1473: {'lr': 0.000368, 'samples': 282816, 'steps': 1472, 'loss/train': 5.061712265014648} 08/30/2021 13:29:29 - INFO - __main__ - Step 1474: {'lr': 0.00036825000000000003, 'samples': 283008, 'steps': 1473, 'loss/train': 4.55220890045166} 08/30/2021 13:29:29 - INFO - __main__ - Step 1475: {'lr': 0.0003685, 'samples': 283200, 'steps': 1474, 'loss/train': 4.2048845291137695} 08/30/2021 13:29:30 - INFO - __main__ - Step 1476: {'lr': 0.00036875000000000005, 'samples': 283392, 'steps': 1475, 'loss/train': 4.37580680847168} 08/30/2021 13:29:30 - INFO - __main__ - Step 1477: {'lr': 0.000369, 'samples': 283584, 'steps': 1476, 'loss/train': 4.393023490905762} 08/30/2021 13:29:32 - INFO - __main__ - Step 1478: {'lr': 0.00036925, 'samples': 283776, 'steps': 1477, 'loss/train': 4.154752254486084} 08/30/2021 13:29:32 - INFO - __main__ - Step 1479: {'lr': 0.0003695, 'samples': 283968, 'steps': 1478, 'loss/train': 4.85263729095459} 08/30/2021 13:29:33 - INFO - __main__ - Step 1480: {'lr': 0.00036975, 'samples': 284160, 'steps': 1479, 'loss/train': 4.904667854309082} 08/30/2021 13:29:33 - INFO - __main__ - Step 1481: {'lr': 0.00037, 'samples': 284352, 'steps': 1480, 'loss/train': 4.509653091430664} 08/30/2021 13:29:33 - INFO - __main__ - Step 1482: {'lr': 0.00037025000000000003, 'samples': 284544, 'steps': 1481, 'loss/train': 2.2799997329711914} 08/30/2021 13:29:35 - INFO - __main__ - Step 1483: {'lr': 0.0003705, 'samples': 284736, 'steps': 1482, 'loss/train': 4.844964027404785} 08/30/2021 13:29:36 - INFO - __main__ - Step 1484: {'lr': 0.00037075000000000004, 'samples': 284928, 'steps': 1483, 'loss/train': 4.235947132110596} 08/30/2021 13:29:36 - INFO - __main__ - Step 1485: {'lr': 0.000371, 'samples': 285120, 'steps': 1484, 'loss/train': 1.4060440063476562} 08/30/2021 13:29:36 - INFO - __main__ - Step 1486: {'lr': 0.00037125000000000005, 'samples': 285312, 'steps': 1485, 'loss/train': 4.211449146270752} 08/30/2021 13:29:37 - INFO - __main__ - Step 1487: {'lr': 0.00037150000000000003, 'samples': 285504, 'steps': 1486, 'loss/train': 4.709524631500244} 08/30/2021 13:29:37 - INFO - __main__ - Step 1488: {'lr': 0.00037175, 'samples': 285696, 'steps': 1487, 'loss/train': 3.5683043003082275} 08/30/2021 13:29:39 - INFO - __main__ - Step 1489: {'lr': 0.000372, 'samples': 285888, 'steps': 1488, 'loss/train': 5.118578910827637} 08/30/2021 13:29:39 - INFO - __main__ - Step 1490: {'lr': 0.00037225, 'samples': 286080, 'steps': 1489, 'loss/train': 4.15762186050415} 08/30/2021 13:29:39 - INFO - __main__ - Step 1491: {'lr': 0.0003725, 'samples': 286272, 'steps': 1490, 'loss/train': 3.8408548831939697} 08/30/2021 13:29:40 - INFO - __main__ - Step 1492: {'lr': 0.00037275000000000003, 'samples': 286464, 'steps': 1491, 'loss/train': 4.238423824310303} 08/30/2021 13:29:40 - INFO - __main__ - Step 1493: {'lr': 0.000373, 'samples': 286656, 'steps': 1492, 'loss/train': 6.055631160736084} 08/30/2021 13:29:42 - INFO - __main__ - Step 1494: {'lr': 0.00037325000000000005, 'samples': 286848, 'steps': 1493, 'loss/train': 4.529669761657715} 08/30/2021 13:29:42 - INFO - __main__ - Step 1495: {'lr': 0.0003735, 'samples': 287040, 'steps': 1494, 'loss/train': 4.583528995513916} 08/30/2021 13:29:42 - INFO - __main__ - Step 1496: {'lr': 0.00037375000000000006, 'samples': 287232, 'steps': 1495, 'loss/train': 4.353099346160889} 08/30/2021 13:29:43 - INFO - __main__ - Step 1497: {'lr': 0.000374, 'samples': 287424, 'steps': 1496, 'loss/train': 4.231982707977295} 08/30/2021 13:29:43 - INFO - __main__ - Step 1498: {'lr': 0.00037425, 'samples': 287616, 'steps': 1497, 'loss/train': 4.441566467285156} 08/30/2021 13:29:45 - INFO - __main__ - Step 1499: {'lr': 0.0003745, 'samples': 287808, 'steps': 1498, 'loss/train': 4.646770000457764} 08/30/2021 13:29:46 - INFO - __main__ - Step 1500: {'lr': 0.00037475000000000003, 'samples': 288000, 'steps': 1499, 'loss/train': 3.9177045822143555} 08/30/2021 13:29:46 - INFO - __main__ - Step 1501: {'lr': 0.000375, 'samples': 288192, 'steps': 1500, 'loss/train': 4.252547740936279} 08/30/2021 13:29:47 - INFO - __main__ - Step 1502: {'lr': 0.00037525, 'samples': 288384, 'steps': 1501, 'loss/train': 4.6158366203308105} 08/30/2021 13:29:47 - INFO - __main__ - Step 1503: {'lr': 0.0003755, 'samples': 288576, 'steps': 1502, 'loss/train': 4.698845386505127} 08/30/2021 13:29:47 - INFO - __main__ - Step 1504: {'lr': 0.00037575, 'samples': 288768, 'steps': 1503, 'loss/train': 4.231035232543945} 08/30/2021 13:29:49 - INFO - __main__ - Step 1505: {'lr': 0.00037600000000000003, 'samples': 288960, 'steps': 1504, 'loss/train': 4.305008411407471} 08/30/2021 13:29:49 - INFO - __main__ - Step 1506: {'lr': 0.00037624999999999996, 'samples': 289152, 'steps': 1505, 'loss/train': 3.5773348808288574} 08/30/2021 13:29:49 - INFO - __main__ - Step 1507: {'lr': 0.0003765, 'samples': 289344, 'steps': 1506, 'loss/train': 4.525704383850098} 08/30/2021 13:29:50 - INFO - __main__ - Step 1508: {'lr': 0.00037674999999999997, 'samples': 289536, 'steps': 1507, 'loss/train': 4.645226001739502} 08/30/2021 13:29:50 - INFO - __main__ - Step 1509: {'lr': 0.000377, 'samples': 289728, 'steps': 1508, 'loss/train': 4.71548318862915} 08/30/2021 13:29:52 - INFO - __main__ - Step 1510: {'lr': 0.00037725, 'samples': 289920, 'steps': 1509, 'loss/train': 4.2164106369018555} 08/30/2021 13:29:52 - INFO - __main__ - Step 1511: {'lr': 0.0003775, 'samples': 290112, 'steps': 1510, 'loss/train': 4.314056396484375} 08/30/2021 13:29:53 - INFO - __main__ - Step 1512: {'lr': 0.00037775, 'samples': 290304, 'steps': 1511, 'loss/train': 4.566384792327881} 08/30/2021 13:29:53 - INFO - __main__ - Step 1513: {'lr': 0.000378, 'samples': 290496, 'steps': 1512, 'loss/train': 2.8232011795043945} 08/30/2021 13:29:53 - INFO - __main__ - Step 1514: {'lr': 0.00037825, 'samples': 290688, 'steps': 1513, 'loss/train': 4.194929599761963} 08/30/2021 13:29:55 - INFO - __main__ - Step 1515: {'lr': 0.0003785, 'samples': 290880, 'steps': 1514, 'loss/train': 3.6204090118408203} 08/30/2021 13:29:55 - INFO - __main__ - Step 1516: {'lr': 0.00037874999999999996, 'samples': 291072, 'steps': 1515, 'loss/train': 2.259321928024292} 08/30/2021 13:29:56 - INFO - __main__ - Step 1517: {'lr': 0.000379, 'samples': 291264, 'steps': 1516, 'loss/train': 4.508073329925537} 08/30/2021 13:29:56 - INFO - __main__ - Step 1518: {'lr': 0.00037925, 'samples': 291456, 'steps': 1517, 'loss/train': 4.136277198791504} 08/30/2021 13:29:56 - INFO - __main__ - Step 1519: {'lr': 0.0003795, 'samples': 291648, 'steps': 1518, 'loss/train': 4.656012535095215} 08/30/2021 13:29:58 - INFO - __main__ - Step 1520: {'lr': 0.00037975, 'samples': 291840, 'steps': 1519, 'loss/train': 3.939546585083008} 08/30/2021 13:29:59 - INFO - __main__ - Step 1521: {'lr': 0.00038, 'samples': 292032, 'steps': 1520, 'loss/train': 4.163784980773926} 08/30/2021 13:29:59 - INFO - __main__ - Step 1522: {'lr': 0.00038025, 'samples': 292224, 'steps': 1521, 'loss/train': 3.413626194000244} 08/30/2021 13:29:59 - INFO - __main__ - Step 1523: {'lr': 0.00038050000000000003, 'samples': 292416, 'steps': 1522, 'loss/train': 4.128015041351318} 08/30/2021 13:30:00 - INFO - __main__ - Step 1524: {'lr': 0.00038075, 'samples': 292608, 'steps': 1523, 'loss/train': 4.029847145080566} 08/30/2021 13:30:01 - INFO - __main__ - Step 1525: {'lr': 0.000381, 'samples': 292800, 'steps': 1524, 'loss/train': 4.129461765289307} 08/30/2021 13:30:02 - INFO - __main__ - Step 1526: {'lr': 0.00038124999999999997, 'samples': 292992, 'steps': 1525, 'loss/train': 4.3723835945129395} 08/30/2021 13:30:02 - INFO - __main__ - Step 1527: {'lr': 0.0003815, 'samples': 293184, 'steps': 1526, 'loss/train': 4.338167190551758} 08/30/2021 13:30:02 - INFO - __main__ - Step 1528: {'lr': 0.00038175, 'samples': 293376, 'steps': 1527, 'loss/train': 3.519054651260376} 08/30/2021 13:30:03 - INFO - __main__ - Step 1529: {'lr': 0.000382, 'samples': 293568, 'steps': 1528, 'loss/train': 4.21800422668457} 08/30/2021 13:30:03 - INFO - __main__ - Step 1530: {'lr': 0.00038225, 'samples': 293760, 'steps': 1529, 'loss/train': 3.9521214962005615} 08/30/2021 13:30:05 - INFO - __main__ - Step 1531: {'lr': 0.00038250000000000003, 'samples': 293952, 'steps': 1530, 'loss/train': 6.254088878631592} 08/30/2021 13:30:05 - INFO - __main__ - Step 1532: {'lr': 0.00038275, 'samples': 294144, 'steps': 1531, 'loss/train': 4.113962650299072} 08/30/2021 13:30:06 - INFO - __main__ - Step 1533: {'lr': 0.00038300000000000004, 'samples': 294336, 'steps': 1532, 'loss/train': 4.775832176208496} 08/30/2021 13:30:06 - INFO - __main__ - Step 1534: {'lr': 0.00038324999999999996, 'samples': 294528, 'steps': 1533, 'loss/train': 4.4971537590026855} 08/30/2021 13:30:06 - INFO - __main__ - Step 1535: {'lr': 0.0003835, 'samples': 294720, 'steps': 1534, 'loss/train': 5.525181293487549} 08/30/2021 13:30:08 - INFO - __main__ - Step 1536: {'lr': 0.00038375, 'samples': 294912, 'steps': 1535, 'loss/train': 4.181306838989258} 08/30/2021 13:30:08 - INFO - __main__ - Step 1537: {'lr': 0.000384, 'samples': 295104, 'steps': 1536, 'loss/train': 3.903292417526245} 08/30/2021 13:30:09 - INFO - __main__ - Step 1538: {'lr': 0.00038425, 'samples': 295296, 'steps': 1537, 'loss/train': 5.626465797424316} 08/30/2021 13:30:09 - INFO - __main__ - Step 1539: {'lr': 0.0003845, 'samples': 295488, 'steps': 1538, 'loss/train': 4.052511692047119} 08/30/2021 13:30:09 - INFO - __main__ - Step 1540: {'lr': 0.00038475, 'samples': 295680, 'steps': 1539, 'loss/train': 3.402632713317871} 08/30/2021 13:30:10 - INFO - __main__ - Step 1541: {'lr': 0.00038500000000000003, 'samples': 295872, 'steps': 1540, 'loss/train': 4.247229099273682} 08/30/2021 13:30:11 - INFO - __main__ - Step 1542: {'lr': 0.00038525, 'samples': 296064, 'steps': 1541, 'loss/train': 4.7946672439575195} 08/30/2021 13:30:12 - INFO - __main__ - Step 1543: {'lr': 0.0003855, 'samples': 296256, 'steps': 1542, 'loss/train': 4.134920120239258} 08/30/2021 13:30:12 - INFO - __main__ - Step 1544: {'lr': 0.00038574999999999997, 'samples': 296448, 'steps': 1543, 'loss/train': 4.3115363121032715} 08/30/2021 13:30:12 - INFO - __main__ - Step 1545: {'lr': 0.000386, 'samples': 296640, 'steps': 1544, 'loss/train': 4.576611042022705} 08/30/2021 13:30:13 - INFO - __main__ - Step 1546: {'lr': 0.00038625, 'samples': 296832, 'steps': 1545, 'loss/train': 4.4993696212768555} 08/30/2021 13:30:14 - INFO - __main__ - Step 1547: {'lr': 0.0003865, 'samples': 297024, 'steps': 1546, 'loss/train': 3.7387473583221436} 08/30/2021 13:30:15 - INFO - __main__ - Step 1548: {'lr': 0.00038675, 'samples': 297216, 'steps': 1547, 'loss/train': 4.228835582733154} 08/30/2021 13:30:15 - INFO - __main__ - Step 1549: {'lr': 0.00038700000000000003, 'samples': 297408, 'steps': 1548, 'loss/train': 4.637598514556885} 08/30/2021 13:30:15 - INFO - __main__ - Step 1550: {'lr': 0.00038725, 'samples': 297600, 'steps': 1549, 'loss/train': 4.239960193634033} 08/30/2021 13:30:16 - INFO - __main__ - Step 1551: {'lr': 0.00038750000000000004, 'samples': 297792, 'steps': 1550, 'loss/train': 4.193304538726807} 08/30/2021 13:30:18 - INFO - __main__ - Step 1552: {'lr': 0.00038774999999999997, 'samples': 297984, 'steps': 1551, 'loss/train': 4.810821533203125} 08/30/2021 13:30:18 - INFO - __main__ - Step 1553: {'lr': 0.000388, 'samples': 298176, 'steps': 1552, 'loss/train': 4.437920570373535} 08/30/2021 13:30:18 - INFO - __main__ - Step 1554: {'lr': 0.00038825, 'samples': 298368, 'steps': 1553, 'loss/train': 4.394014835357666} 08/30/2021 13:30:19 - INFO - __main__ - Step 1555: {'lr': 0.0003885, 'samples': 298560, 'steps': 1554, 'loss/train': 4.478893756866455} 08/30/2021 13:30:19 - INFO - __main__ - Step 1556: {'lr': 0.00038875, 'samples': 298752, 'steps': 1555, 'loss/train': 3.117422103881836} 08/30/2021 13:30:19 - INFO - __main__ - Step 1557: {'lr': 0.000389, 'samples': 298944, 'steps': 1556, 'loss/train': 2.5692341327667236} 08/30/2021 13:30:21 - INFO - __main__ - Step 1558: {'lr': 0.00038925, 'samples': 299136, 'steps': 1557, 'loss/train': 5.1680521965026855} 08/30/2021 13:30:22 - INFO - __main__ - Step 1559: {'lr': 0.00038950000000000003, 'samples': 299328, 'steps': 1558, 'loss/train': 4.88592529296875} 08/30/2021 13:30:22 - INFO - __main__ - Step 1560: {'lr': 0.00038975, 'samples': 299520, 'steps': 1559, 'loss/train': 4.256154537200928} 08/30/2021 13:30:23 - INFO - __main__ - Step 1561: {'lr': 0.00039000000000000005, 'samples': 299712, 'steps': 1560, 'loss/train': 4.822085380554199} 08/30/2021 13:30:23 - INFO - __main__ - Step 1562: {'lr': 0.00039024999999999997, 'samples': 299904, 'steps': 1561, 'loss/train': 3.565521717071533} 08/30/2021 13:30:24 - INFO - __main__ - Step 1563: {'lr': 0.0003905, 'samples': 300096, 'steps': 1562, 'loss/train': 4.09617805480957} 08/30/2021 13:30:25 - INFO - __main__ - Step 1564: {'lr': 0.00039075, 'samples': 300288, 'steps': 1563, 'loss/train': 3.3210463523864746} 08/30/2021 13:30:25 - INFO - __main__ - Step 1565: {'lr': 0.000391, 'samples': 300480, 'steps': 1564, 'loss/train': 4.729197978973389} 08/30/2021 13:30:26 - INFO - __main__ - Step 1566: {'lr': 0.00039125, 'samples': 300672, 'steps': 1565, 'loss/train': 4.8554768562316895} 08/30/2021 13:30:26 - INFO - __main__ - Step 1567: {'lr': 0.00039150000000000003, 'samples': 300864, 'steps': 1566, 'loss/train': 3.703321695327759} 08/30/2021 13:30:28 - INFO - __main__ - Step 1568: {'lr': 0.00039175, 'samples': 301056, 'steps': 1567, 'loss/train': 3.9964680671691895} 08/30/2021 13:30:28 - INFO - __main__ - Step 1569: {'lr': 0.00039200000000000004, 'samples': 301248, 'steps': 1568, 'loss/train': 4.367398738861084} 08/30/2021 13:30:29 - INFO - __main__ - Step 1570: {'lr': 0.00039225, 'samples': 301440, 'steps': 1569, 'loss/train': 4.335350513458252} 08/30/2021 13:30:29 - INFO - __main__ - Step 1571: {'lr': 0.0003925, 'samples': 301632, 'steps': 1570, 'loss/train': 4.462733268737793} 08/30/2021 13:30:29 - INFO - __main__ - Step 1572: {'lr': 0.00039275, 'samples': 301824, 'steps': 1571, 'loss/train': 4.362184524536133} 08/30/2021 13:30:30 - INFO - __main__ - Step 1573: {'lr': 0.000393, 'samples': 302016, 'steps': 1572, 'loss/train': 3.751896381378174} 08/30/2021 13:30:31 - INFO - __main__ - Step 1574: {'lr': 0.00039325, 'samples': 302208, 'steps': 1573, 'loss/train': 2.203317642211914} 08/30/2021 13:30:32 - INFO - __main__ - Step 1575: {'lr': 0.0003935, 'samples': 302400, 'steps': 1574, 'loss/train': 4.502272129058838} 08/30/2021 13:30:32 - INFO - __main__ - Step 1576: {'lr': 0.00039375, 'samples': 302592, 'steps': 1575, 'loss/train': 4.511845111846924} 08/30/2021 13:30:33 - INFO - __main__ - Step 1577: {'lr': 0.00039400000000000004, 'samples': 302784, 'steps': 1576, 'loss/train': 3.4592127799987793} 08/30/2021 13:30:33 - INFO - __main__ - Step 1578: {'lr': 0.00039425, 'samples': 302976, 'steps': 1577, 'loss/train': 5.708824634552002} 08/30/2021 13:30:34 - INFO - __main__ - Step 1579: {'lr': 0.00039450000000000005, 'samples': 303168, 'steps': 1578, 'loss/train': 4.112600803375244} 08/30/2021 13:30:35 - INFO - __main__ - Step 1580: {'lr': 0.00039474999999999997, 'samples': 303360, 'steps': 1579, 'loss/train': 4.602146625518799} 08/30/2021 13:30:35 - INFO - __main__ - Step 1581: {'lr': 0.000395, 'samples': 303552, 'steps': 1580, 'loss/train': 3.5878899097442627} 08/30/2021 13:30:36 - INFO - __main__ - Step 1582: {'lr': 0.00039525, 'samples': 303744, 'steps': 1581, 'loss/train': 4.978146076202393} 08/30/2021 13:30:36 - INFO - __main__ - Step 1583: {'lr': 0.0003955, 'samples': 303936, 'steps': 1582, 'loss/train': 4.191125869750977} 08/30/2021 13:30:36 - INFO - __main__ - Step 1584: {'lr': 0.00039575, 'samples': 304128, 'steps': 1583, 'loss/train': 4.308163166046143} 08/30/2021 13:30:38 - INFO - __main__ - Step 1585: {'lr': 0.00039600000000000003, 'samples': 304320, 'steps': 1584, 'loss/train': 3.522921085357666} 08/30/2021 13:30:38 - INFO - __main__ - Step 1586: {'lr': 0.00039625, 'samples': 304512, 'steps': 1585, 'loss/train': 4.331756591796875} 08/30/2021 13:30:39 - INFO - __main__ - Step 1587: {'lr': 0.00039650000000000004, 'samples': 304704, 'steps': 1586, 'loss/train': 4.016501426696777} 08/30/2021 13:30:39 - INFO - __main__ - Step 1588: {'lr': 0.00039675, 'samples': 304896, 'steps': 1587, 'loss/train': 3.9630494117736816} 08/30/2021 13:30:39 - INFO - __main__ - Step 1589: {'lr': 0.00039700000000000005, 'samples': 305088, 'steps': 1588, 'loss/train': 3.8252696990966797} 08/30/2021 13:30:41 - INFO - __main__ - Step 1590: {'lr': 0.00039725, 'samples': 305280, 'steps': 1589, 'loss/train': 4.543032169342041} 08/30/2021 13:30:41 - INFO - __main__ - Step 1591: {'lr': 0.0003975, 'samples': 305472, 'steps': 1590, 'loss/train': 3.9182825088500977} 08/30/2021 13:30:42 - INFO - __main__ - Step 1592: {'lr': 0.00039775, 'samples': 305664, 'steps': 1591, 'loss/train': 3.944086790084839} 08/30/2021 13:30:42 - INFO - __main__ - Step 1593: {'lr': 0.000398, 'samples': 305856, 'steps': 1592, 'loss/train': 4.1202239990234375} 08/30/2021 13:30:42 - INFO - __main__ - Step 1594: {'lr': 0.00039825, 'samples': 306048, 'steps': 1593, 'loss/train': 4.118268013000488} 08/30/2021 13:30:44 - INFO - __main__ - Step 1595: {'lr': 0.00039850000000000004, 'samples': 306240, 'steps': 1594, 'loss/train': 4.110257625579834} 08/30/2021 13:30:44 - INFO - __main__ - Step 1596: {'lr': 0.00039875, 'samples': 306432, 'steps': 1595, 'loss/train': 4.602290153503418} 08/30/2021 13:30:45 - INFO - __main__ - Step 1597: {'lr': 0.00039900000000000005, 'samples': 306624, 'steps': 1596, 'loss/train': 4.3493332862854} 08/30/2021 13:30:45 - INFO - __main__ - Step 1598: {'lr': 0.00039925000000000003, 'samples': 306816, 'steps': 1597, 'loss/train': 4.359951496124268} 08/30/2021 13:30:45 - INFO - __main__ - Step 1599: {'lr': 0.0003995, 'samples': 307008, 'steps': 1598, 'loss/train': 4.226939678192139} 08/30/2021 13:30:47 - INFO - __main__ - Step 1600: {'lr': 0.00039975, 'samples': 307200, 'steps': 1599, 'loss/train': 3.979285717010498} 08/30/2021 13:30:47 - INFO - __main__ - Step 1601: {'lr': 0.0004, 'samples': 307392, 'steps': 1600, 'loss/train': 3.927377700805664} 08/30/2021 13:30:48 - INFO - __main__ - Step 1602: {'lr': 0.00040025, 'samples': 307584, 'steps': 1601, 'loss/train': 3.437540292739868} 08/30/2021 13:30:48 - INFO - __main__ - Step 1603: {'lr': 0.00040050000000000003, 'samples': 307776, 'steps': 1602, 'loss/train': 4.3806962966918945} 08/30/2021 13:30:48 - INFO - __main__ - Step 1604: {'lr': 0.00040075, 'samples': 307968, 'steps': 1603, 'loss/train': 4.12437629699707} 08/30/2021 13:30:50 - INFO - __main__ - Step 1605: {'lr': 0.00040100000000000004, 'samples': 308160, 'steps': 1604, 'loss/train': 3.897045373916626} 08/30/2021 13:30:50 - INFO - __main__ - Step 1606: {'lr': 0.00040125, 'samples': 308352, 'steps': 1605, 'loss/train': 3.835270643234253} 08/30/2021 13:30:51 - INFO - __main__ - Step 1607: {'lr': 0.00040150000000000006, 'samples': 308544, 'steps': 1606, 'loss/train': 4.323556900024414} 08/30/2021 13:30:51 - INFO - __main__ - Step 1608: {'lr': 0.00040175, 'samples': 308736, 'steps': 1607, 'loss/train': 3.6603899002075195} 08/30/2021 13:30:52 - INFO - __main__ - Step 1609: {'lr': 0.000402, 'samples': 308928, 'steps': 1608, 'loss/train': 4.13911247253418} 08/30/2021 13:30:54 - INFO - __main__ - Step 1610: {'lr': 0.00040225, 'samples': 309120, 'steps': 1609, 'loss/train': 3.910623788833618} 08/30/2021 13:30:54 - INFO - __main__ - Step 1611: {'lr': 0.0004025, 'samples': 309312, 'steps': 1610, 'loss/train': 4.918487548828125} 08/30/2021 13:30:55 - INFO - __main__ - Step 1612: {'lr': 0.00040275, 'samples': 309504, 'steps': 1611, 'loss/train': 4.247921943664551} 08/30/2021 13:30:55 - INFO - __main__ - Step 1613: {'lr': 0.00040300000000000004, 'samples': 309696, 'steps': 1612, 'loss/train': 4.120118618011475} 08/30/2021 13:30:55 - INFO - __main__ - Step 1614: {'lr': 0.00040325, 'samples': 309888, 'steps': 1613, 'loss/train': 4.075702667236328} 08/30/2021 13:30:57 - INFO - __main__ - Step 1615: {'lr': 0.00040350000000000005, 'samples': 310080, 'steps': 1614, 'loss/train': 4.307497978210449} 08/30/2021 13:30:57 - INFO - __main__ - Step 1616: {'lr': 0.00040375000000000003, 'samples': 310272, 'steps': 1615, 'loss/train': 4.062084197998047} 08/30/2021 13:30:58 - INFO - __main__ - Step 1617: {'lr': 0.000404, 'samples': 310464, 'steps': 1616, 'loss/train': 1.957079291343689} 08/30/2021 13:30:58 - INFO - __main__ - Step 1618: {'lr': 0.00040425, 'samples': 310656, 'steps': 1617, 'loss/train': 3.859267473220825} 08/30/2021 13:30:58 - INFO - __main__ - Step 1619: {'lr': 0.0004045, 'samples': 310848, 'steps': 1618, 'loss/train': 3.921182155609131} 08/30/2021 13:30:59 - INFO - __main__ - Step 1620: {'lr': 0.00040475, 'samples': 311040, 'steps': 1619, 'loss/train': 3.962010145187378} 08/30/2021 13:31:00 - INFO - __main__ - Step 1621: {'lr': 0.00040500000000000003, 'samples': 311232, 'steps': 1620, 'loss/train': 3.9373505115509033} 08/30/2021 13:31:01 - INFO - __main__ - Step 1622: {'lr': 0.00040525, 'samples': 311424, 'steps': 1621, 'loss/train': 1.5724457502365112} 08/30/2021 13:31:01 - INFO - __main__ - Step 1623: {'lr': 0.00040550000000000004, 'samples': 311616, 'steps': 1622, 'loss/train': 3.370074510574341} 08/30/2021 13:31:01 - INFO - __main__ - Step 1624: {'lr': 0.00040575, 'samples': 311808, 'steps': 1623, 'loss/train': 4.119229316711426} 08/30/2021 13:31:02 - INFO - __main__ - Step 1625: {'lr': 0.00040600000000000006, 'samples': 312000, 'steps': 1624, 'loss/train': 4.099151611328125} 08/30/2021 13:31:03 - INFO - __main__ - Step 1626: {'lr': 0.00040625000000000004, 'samples': 312192, 'steps': 1625, 'loss/train': 4.612451553344727} 08/30/2021 13:31:04 - INFO - __main__ - Step 1627: {'lr': 0.00040649999999999996, 'samples': 312384, 'steps': 1626, 'loss/train': 5.194092750549316} 08/30/2021 13:31:04 - INFO - __main__ - Step 1628: {'lr': 0.00040675, 'samples': 312576, 'steps': 1627, 'loss/train': 3.668224334716797} 08/30/2021 13:31:04 - INFO - __main__ - Step 1629: {'lr': 0.00040699999999999997, 'samples': 312768, 'steps': 1628, 'loss/train': 5.2241363525390625} 08/30/2021 13:31:05 - INFO - __main__ - Step 1630: {'lr': 0.00040725, 'samples': 312960, 'steps': 1629, 'loss/train': 3.1308257579803467} 08/30/2021 13:31:06 - INFO - __main__ - Step 1631: {'lr': 0.0004075, 'samples': 313152, 'steps': 1630, 'loss/train': 4.357464790344238} 08/30/2021 13:31:07 - INFO - __main__ - Step 1632: {'lr': 0.00040775, 'samples': 313344, 'steps': 1631, 'loss/train': 3.7567591667175293} 08/30/2021 13:31:07 - INFO - __main__ - Step 1633: {'lr': 0.000408, 'samples': 313536, 'steps': 1632, 'loss/train': 2.5121212005615234} 08/30/2021 13:31:08 - INFO - __main__ - Step 1634: {'lr': 0.00040825000000000003, 'samples': 313728, 'steps': 1633, 'loss/train': 3.9205658435821533} 08/30/2021 13:31:08 - INFO - __main__ - Step 1635: {'lr': 0.0004085, 'samples': 313920, 'steps': 1634, 'loss/train': 3.962059259414673} 08/30/2021 13:31:08 - INFO - __main__ - Step 1636: {'lr': 0.00040875, 'samples': 314112, 'steps': 1635, 'loss/train': 1.6473331451416016} 08/30/2021 13:31:10 - INFO - __main__ - Step 1637: {'lr': 0.00040899999999999997, 'samples': 314304, 'steps': 1636, 'loss/train': 4.067282676696777} 08/30/2021 13:31:10 - INFO - __main__ - Step 1638: {'lr': 0.00040925, 'samples': 314496, 'steps': 1637, 'loss/train': 4.295927047729492} 08/30/2021 13:31:11 - INFO - __main__ - Step 1639: {'lr': 0.0004095, 'samples': 314688, 'steps': 1638, 'loss/train': 6.340890407562256} 08/30/2021 13:31:11 - INFO - __main__ - Step 1640: {'lr': 0.00040975, 'samples': 314880, 'steps': 1639, 'loss/train': 4.031452178955078} 08/30/2021 13:31:11 - INFO - __main__ - Step 1641: {'lr': 0.00041, 'samples': 315072, 'steps': 1640, 'loss/train': 4.079275131225586} 08/30/2021 13:31:13 - INFO - __main__ - Step 1642: {'lr': 0.00041025, 'samples': 315264, 'steps': 1641, 'loss/train': 4.769386291503906} 08/30/2021 13:31:13 - INFO - __main__ - Step 1643: {'lr': 0.0004105, 'samples': 315456, 'steps': 1642, 'loss/train': 3.8678455352783203} 08/30/2021 13:31:14 - INFO - __main__ - Step 1644: {'lr': 0.00041075000000000004, 'samples': 315648, 'steps': 1643, 'loss/train': 4.219468593597412} 08/30/2021 13:31:14 - INFO - __main__ - Step 1645: {'lr': 0.00041099999999999996, 'samples': 315840, 'steps': 1644, 'loss/train': 3.7112865447998047} 08/30/2021 13:31:14 - INFO - __main__ - Step 1646: {'lr': 0.00041125, 'samples': 316032, 'steps': 1645, 'loss/train': 3.841484308242798} 08/30/2021 13:31:16 - INFO - __main__ - Step 1647: {'lr': 0.0004115, 'samples': 316224, 'steps': 1646, 'loss/train': 4.261174201965332} 08/30/2021 13:31:16 - INFO - __main__ - Step 1648: {'lr': 0.00041175, 'samples': 316416, 'steps': 1647, 'loss/train': 3.7539446353912354} 08/30/2021 13:31:17 - INFO - __main__ - Step 1649: {'lr': 0.000412, 'samples': 316608, 'steps': 1648, 'loss/train': 3.9607656002044678} 08/30/2021 13:31:17 - INFO - __main__ - Step 1650: {'lr': 0.00041225, 'samples': 316800, 'steps': 1649, 'loss/train': 4.425975322723389} 08/30/2021 13:31:17 - INFO - __main__ - Step 1651: {'lr': 0.0004125, 'samples': 316992, 'steps': 1650, 'loss/train': 4.258786201477051} 08/30/2021 13:31:18 - INFO - __main__ - Step 1652: {'lr': 0.00041275000000000003, 'samples': 317184, 'steps': 1651, 'loss/train': 4.03767204284668} 08/30/2021 13:31:19 - INFO - __main__ - Step 1653: {'lr': 0.000413, 'samples': 317376, 'steps': 1652, 'loss/train': 4.375797748565674} 08/30/2021 13:31:20 - INFO - __main__ - Step 1654: {'lr': 0.00041325, 'samples': 317568, 'steps': 1653, 'loss/train': 5.396332263946533} 08/30/2021 13:31:20 - INFO - __main__ - Step 1655: {'lr': 0.00041349999999999997, 'samples': 317760, 'steps': 1654, 'loss/train': 4.422496318817139} 08/30/2021 13:31:20 - INFO - __main__ - Step 1656: {'lr': 0.00041375, 'samples': 317952, 'steps': 1655, 'loss/train': 3.649282217025757} 08/30/2021 13:31:21 - INFO - __main__ - Step 1657: {'lr': 0.000414, 'samples': 318144, 'steps': 1656, 'loss/train': 3.2264163494110107} 08/30/2021 13:31:22 - INFO - __main__ - Step 1658: {'lr': 0.00041425, 'samples': 318336, 'steps': 1657, 'loss/train': 3.597780704498291} 08/30/2021 13:31:23 - INFO - __main__ - Step 1659: {'lr': 0.0004145, 'samples': 318528, 'steps': 1658, 'loss/train': 4.033586025238037} 08/30/2021 13:31:23 - INFO - __main__ - Step 1660: {'lr': 0.00041475, 'samples': 318720, 'steps': 1659, 'loss/train': 4.188148498535156} 08/30/2021 13:31:24 - INFO - __main__ - Step 1661: {'lr': 0.000415, 'samples': 318912, 'steps': 1660, 'loss/train': 3.688339948654175} 08/30/2021 13:31:24 - INFO - __main__ - Step 1662: {'lr': 0.00041525000000000004, 'samples': 319104, 'steps': 1661, 'loss/train': 1.469415307044983} 08/30/2021 13:31:26 - INFO - __main__ - Step 1663: {'lr': 0.00041549999999999996, 'samples': 319296, 'steps': 1662, 'loss/train': 3.908815383911133} 08/30/2021 13:31:27 - INFO - __main__ - Step 1664: {'lr': 0.00041575, 'samples': 319488, 'steps': 1663, 'loss/train': 3.91666316986084} 08/30/2021 13:31:27 - INFO - __main__ - Step 1665: {'lr': 0.000416, 'samples': 319680, 'steps': 1664, 'loss/train': 4.200262069702148} 08/30/2021 13:31:27 - INFO - __main__ - Step 1666: {'lr': 0.00041625, 'samples': 319872, 'steps': 1665, 'loss/train': 4.345694065093994} 08/30/2021 13:31:28 - INFO - __main__ - Step 1667: {'lr': 0.0004165, 'samples': 320064, 'steps': 1666, 'loss/train': 3.4992318153381348} 08/30/2021 13:31:29 - INFO - __main__ - Step 1668: {'lr': 0.00041675, 'samples': 320256, 'steps': 1667, 'loss/train': 3.7306833267211914} 08/30/2021 13:31:30 - INFO - __main__ - Step 1669: {'lr': 0.000417, 'samples': 320448, 'steps': 1668, 'loss/train': 4.227388381958008} 08/30/2021 13:31:30 - INFO - __main__ - Step 1670: {'lr': 0.00041725000000000003, 'samples': 320640, 'steps': 1669, 'loss/train': 4.318609714508057} 08/30/2021 13:31:30 - INFO - __main__ - Step 1671: {'lr': 0.0004175, 'samples': 320832, 'steps': 1670, 'loss/train': 4.057160377502441} 08/30/2021 13:31:31 - INFO - __main__ - Step 1672: {'lr': 0.00041775000000000004, 'samples': 321024, 'steps': 1671, 'loss/train': 4.666829586029053} 08/30/2021 13:31:32 - INFO - __main__ - Step 1673: {'lr': 0.00041799999999999997, 'samples': 321216, 'steps': 1672, 'loss/train': 4.118185997009277} 08/30/2021 13:31:33 - INFO - __main__ - Step 1674: {'lr': 0.00041825, 'samples': 321408, 'steps': 1673, 'loss/train': 3.671118974685669} 08/30/2021 13:31:33 - INFO - __main__ - Step 1675: {'lr': 0.0004185, 'samples': 321600, 'steps': 1674, 'loss/train': 3.7217016220092773} 08/30/2021 13:31:33 - INFO - __main__ - Step 1676: {'lr': 0.00041875, 'samples': 321792, 'steps': 1675, 'loss/train': 4.462160587310791} 08/30/2021 13:31:34 - INFO - __main__ - Step 1677: {'lr': 0.000419, 'samples': 321984, 'steps': 1676, 'loss/train': 4.042119026184082} 08/30/2021 13:31:35 - INFO - __main__ - Step 1678: {'lr': 0.00041925, 'samples': 322176, 'steps': 1677, 'loss/train': 4.16783332824707} 08/30/2021 13:31:36 - INFO - __main__ - Step 1679: {'lr': 0.0004195, 'samples': 322368, 'steps': 1678, 'loss/train': 3.4674606323242188} 08/30/2021 13:31:36 - INFO - __main__ - Step 1680: {'lr': 0.00041975000000000004, 'samples': 322560, 'steps': 1679, 'loss/train': 4.066051483154297} 08/30/2021 13:31:36 - INFO - __main__ - Step 1681: {'lr': 0.00042, 'samples': 322752, 'steps': 1680, 'loss/train': 4.4997663497924805} 08/30/2021 13:31:37 - INFO - __main__ - Step 1682: {'lr': 0.00042025, 'samples': 322944, 'steps': 1681, 'loss/train': 4.407072067260742} 08/30/2021 13:31:37 - INFO - __main__ - Step 1683: {'lr': 0.0004205, 'samples': 323136, 'steps': 1682, 'loss/train': 4.428121089935303} 08/30/2021 13:31:39 - INFO - __main__ - Step 1684: {'lr': 0.00042075, 'samples': 323328, 'steps': 1683, 'loss/train': 4.961803913116455} 08/30/2021 13:31:39 - INFO - __main__ - Step 1685: {'lr': 0.000421, 'samples': 323520, 'steps': 1684, 'loss/train': 3.9315521717071533} 08/30/2021 13:31:39 - INFO - __main__ - Step 1686: {'lr': 0.00042125, 'samples': 323712, 'steps': 1685, 'loss/train': 4.466744422912598} 08/30/2021 13:31:40 - INFO - __main__ - Step 1687: {'lr': 0.0004215, 'samples': 323904, 'steps': 1686, 'loss/train': 4.479499340057373} 08/30/2021 13:31:40 - INFO - __main__ - Step 1688: {'lr': 0.00042175000000000003, 'samples': 324096, 'steps': 1687, 'loss/train': 4.021457195281982} 08/30/2021 13:31:42 - INFO - __main__ - Step 1689: {'lr': 0.000422, 'samples': 324288, 'steps': 1688, 'loss/train': 3.9127321243286133} 08/30/2021 13:31:42 - INFO - __main__ - Step 1690: {'lr': 0.00042225000000000005, 'samples': 324480, 'steps': 1689, 'loss/train': 3.905916213989258} 08/30/2021 13:31:42 - INFO - __main__ - Step 1691: {'lr': 0.00042249999999999997, 'samples': 324672, 'steps': 1690, 'loss/train': 4.201033592224121} 08/30/2021 13:31:43 - INFO - __main__ - Step 1692: {'lr': 0.00042275, 'samples': 324864, 'steps': 1691, 'loss/train': 4.329977035522461} 08/30/2021 13:31:43 - INFO - __main__ - Step 1693: {'lr': 0.000423, 'samples': 325056, 'steps': 1692, 'loss/train': 3.6381800174713135} 08/30/2021 13:31:44 - INFO - __main__ - Step 1694: {'lr': 0.00042325, 'samples': 325248, 'steps': 1693, 'loss/train': 3.683461904525757} 08/30/2021 13:31:45 - INFO - __main__ - Step 1695: {'lr': 0.0004235, 'samples': 325440, 'steps': 1694, 'loss/train': 3.852285146713257} 08/30/2021 13:31:45 - INFO - __main__ - Step 1696: {'lr': 0.00042375000000000003, 'samples': 325632, 'steps': 1695, 'loss/train': 3.511688470840454} 08/30/2021 13:31:46 - INFO - __main__ - Step 1697: {'lr': 0.000424, 'samples': 325824, 'steps': 1696, 'loss/train': 3.8069117069244385} 08/30/2021 13:31:46 - INFO - __main__ - Step 1698: {'lr': 0.00042425000000000004, 'samples': 326016, 'steps': 1697, 'loss/train': 4.340700149536133} 08/30/2021 13:31:47 - INFO - __main__ - Step 1699: {'lr': 0.0004245, 'samples': 326208, 'steps': 1698, 'loss/train': 3.7010538578033447} 08/30/2021 13:31:48 - INFO - __main__ - Step 1700: {'lr': 0.00042475000000000005, 'samples': 326400, 'steps': 1699, 'loss/train': 3.855823516845703} 08/30/2021 13:31:48 - INFO - __main__ - Step 1701: {'lr': 0.000425, 'samples': 326592, 'steps': 1700, 'loss/train': 3.2315449714660645} 08/30/2021 13:31:48 - INFO - __main__ - Step 1702: {'lr': 0.00042525, 'samples': 326784, 'steps': 1701, 'loss/train': 4.2792887687683105} 08/30/2021 13:31:49 - INFO - __main__ - Step 1703: {'lr': 0.0004255, 'samples': 326976, 'steps': 1702, 'loss/train': 3.77683424949646} 08/30/2021 13:31:50 - INFO - __main__ - Step 1704: {'lr': 0.00042575, 'samples': 327168, 'steps': 1703, 'loss/train': 4.382048606872559} 08/30/2021 13:31:51 - INFO - __main__ - Step 1705: {'lr': 0.000426, 'samples': 327360, 'steps': 1704, 'loss/train': 4.271405220031738} 08/30/2021 13:31:51 - INFO - __main__ - Step 1706: {'lr': 0.00042625000000000003, 'samples': 327552, 'steps': 1705, 'loss/train': 3.9530229568481445} 08/30/2021 13:31:51 - INFO - __main__ - Step 1707: {'lr': 0.0004265, 'samples': 327744, 'steps': 1706, 'loss/train': 3.769348382949829} 08/30/2021 13:31:52 - INFO - __main__ - Step 1708: {'lr': 0.00042675000000000005, 'samples': 327936, 'steps': 1707, 'loss/train': 3.80161452293396} 08/30/2021 13:31:53 - INFO - __main__ - Step 1709: {'lr': 0.000427, 'samples': 328128, 'steps': 1708, 'loss/train': 4.133491516113281} 08/30/2021 13:31:54 - INFO - __main__ - Step 1710: {'lr': 0.00042725, 'samples': 328320, 'steps': 1709, 'loss/train': 3.7779102325439453} 08/30/2021 13:31:54 - INFO - __main__ - Step 1711: {'lr': 0.0004275, 'samples': 328512, 'steps': 1710, 'loss/train': 3.779893159866333} 08/30/2021 13:31:54 - INFO - __main__ - Step 1712: {'lr': 0.00042775, 'samples': 328704, 'steps': 1711, 'loss/train': 4.150379180908203} 08/30/2021 13:31:55 - INFO - __main__ - Step 1713: {'lr': 0.000428, 'samples': 328896, 'steps': 1712, 'loss/train': 3.41762375831604} 08/30/2021 13:31:56 - INFO - __main__ - Step 1714: {'lr': 0.00042825000000000003, 'samples': 329088, 'steps': 1713, 'loss/train': 4.138961315155029} 08/30/2021 13:31:57 - INFO - __main__ - Step 1715: {'lr': 0.0004285, 'samples': 329280, 'steps': 1714, 'loss/train': 3.648662805557251} 08/30/2021 13:31:57 - INFO - __main__ - Step 1716: {'lr': 0.00042875000000000004, 'samples': 329472, 'steps': 1715, 'loss/train': 1.621708869934082} 08/30/2021 13:31:58 - INFO - __main__ - Step 1717: {'lr': 0.000429, 'samples': 329664, 'steps': 1716, 'loss/train': 3.648488998413086} 08/30/2021 13:31:58 - INFO - __main__ - Step 1718: {'lr': 0.00042925000000000005, 'samples': 329856, 'steps': 1717, 'loss/train': 3.774393320083618} 08/30/2021 13:32:00 - INFO - __main__ - Step 1719: {'lr': 0.0004295, 'samples': 330048, 'steps': 1718, 'loss/train': 4.18839693069458} 08/30/2021 13:32:01 - INFO - __main__ - Step 1720: {'lr': 0.00042975, 'samples': 330240, 'steps': 1719, 'loss/train': 3.8447341918945312} 08/30/2021 13:32:01 - INFO - __main__ - Step 1721: {'lr': 0.00043, 'samples': 330432, 'steps': 1720, 'loss/train': 3.534740447998047} 08/30/2021 13:32:02 - INFO - __main__ - Step 1722: {'lr': 0.00043025, 'samples': 330624, 'steps': 1721, 'loss/train': 4.641766548156738} 08/30/2021 13:32:02 - INFO - __main__ - Step 1723: {'lr': 0.0004305, 'samples': 330816, 'steps': 1722, 'loss/train': 2.236652135848999} 08/30/2021 13:32:02 - INFO - __main__ - Step 1724: {'lr': 0.00043075000000000003, 'samples': 331008, 'steps': 1723, 'loss/train': 3.677239179611206} 08/30/2021 13:32:04 - INFO - __main__ - Step 1725: {'lr': 0.000431, 'samples': 331200, 'steps': 1724, 'loss/train': 3.2222580909729004} 08/30/2021 13:32:04 - INFO - __main__ - Step 1726: {'lr': 0.00043125000000000005, 'samples': 331392, 'steps': 1725, 'loss/train': 3.922532081604004} 08/30/2021 13:32:05 - INFO - __main__ - Step 1727: {'lr': 0.0004315, 'samples': 331584, 'steps': 1726, 'loss/train': 3.244903326034546} 08/30/2021 13:32:05 - INFO - __main__ - Step 1728: {'lr': 0.00043175, 'samples': 331776, 'steps': 1727, 'loss/train': 4.074255466461182} 08/30/2021 13:32:05 - INFO - __main__ - Step 1729: {'lr': 0.000432, 'samples': 331968, 'steps': 1728, 'loss/train': 4.264842987060547} 08/30/2021 13:32:07 - INFO - __main__ - Step 1730: {'lr': 0.00043225, 'samples': 332160, 'steps': 1729, 'loss/train': 1.3039348125457764} 08/30/2021 13:32:07 - INFO - __main__ - Step 1731: {'lr': 0.0004325, 'samples': 332352, 'steps': 1730, 'loss/train': 3.8235883712768555} 08/30/2021 13:32:08 - INFO - __main__ - Step 1732: {'lr': 0.00043275000000000003, 'samples': 332544, 'steps': 1731, 'loss/train': 3.861481189727783} 08/30/2021 13:32:08 - INFO - __main__ - Step 1733: {'lr': 0.000433, 'samples': 332736, 'steps': 1732, 'loss/train': 3.660234212875366} 08/30/2021 13:32:08 - INFO - __main__ - Step 1734: {'lr': 0.00043325000000000004, 'samples': 332928, 'steps': 1733, 'loss/train': 3.09748911857605} 08/30/2021 13:32:10 - INFO - __main__ - Step 1735: {'lr': 0.0004335, 'samples': 333120, 'steps': 1734, 'loss/train': 4.138425827026367} 08/30/2021 13:32:11 - INFO - __main__ - Step 1736: {'lr': 0.00043375000000000005, 'samples': 333312, 'steps': 1735, 'loss/train': 2.873290538787842} 08/30/2021 13:32:11 - INFO - __main__ - Step 1737: {'lr': 0.00043400000000000003, 'samples': 333504, 'steps': 1736, 'loss/train': 4.770103454589844} 08/30/2021 13:32:11 - INFO - __main__ - Step 1738: {'lr': 0.00043425, 'samples': 333696, 'steps': 1737, 'loss/train': 3.8146097660064697} 08/30/2021 13:32:12 - INFO - __main__ - Step 1739: {'lr': 0.0004345, 'samples': 333888, 'steps': 1738, 'loss/train': 2.9071238040924072} 08/30/2021 13:32:12 - INFO - __main__ - Step 1740: {'lr': 0.00043475, 'samples': 334080, 'steps': 1739, 'loss/train': 2.6069204807281494} 08/30/2021 13:32:14 - INFO - __main__ - Step 1741: {'lr': 0.000435, 'samples': 334272, 'steps': 1740, 'loss/train': 3.395693302154541} 08/30/2021 13:32:14 - INFO - __main__ - Step 1742: {'lr': 0.00043525000000000004, 'samples': 334464, 'steps': 1741, 'loss/train': 3.2589519023895264} 08/30/2021 13:32:15 - INFO - __main__ - Step 1743: {'lr': 0.0004355, 'samples': 334656, 'steps': 1742, 'loss/train': 3.994988203048706} 08/30/2021 13:32:15 - INFO - __main__ - Step 1744: {'lr': 0.00043575000000000005, 'samples': 334848, 'steps': 1743, 'loss/train': 3.7896499633789062} 08/30/2021 13:32:15 - INFO - __main__ - Step 1745: {'lr': 0.000436, 'samples': 335040, 'steps': 1744, 'loss/train': 4.0110015869140625} 08/30/2021 13:32:16 - INFO - __main__ - Step 1746: {'lr': 0.00043625000000000006, 'samples': 335232, 'steps': 1745, 'loss/train': 3.9087882041931152} 08/30/2021 13:32:17 - INFO - __main__ - Step 1747: {'lr': 0.0004365, 'samples': 335424, 'steps': 1746, 'loss/train': 3.7993640899658203} 08/30/2021 13:32:18 - INFO - __main__ - Step 1748: {'lr': 0.00043675, 'samples': 335616, 'steps': 1747, 'loss/train': 4.368635177612305} 08/30/2021 13:32:18 - INFO - __main__ - Step 1749: {'lr': 0.000437, 'samples': 335808, 'steps': 1748, 'loss/train': 4.0576958656311035} 08/30/2021 13:32:19 - INFO - __main__ - Step 1750: {'lr': 0.00043725000000000003, 'samples': 336000, 'steps': 1749, 'loss/train': 3.779649019241333} 08/30/2021 13:32:19 - INFO - __main__ - Step 1751: {'lr': 0.0004375, 'samples': 336192, 'steps': 1750, 'loss/train': 3.8256595134735107} 08/30/2021 13:32:20 - INFO - __main__ - Step 1752: {'lr': 0.00043775, 'samples': 336384, 'steps': 1751, 'loss/train': 3.8933751583099365} 08/30/2021 13:32:21 - INFO - __main__ - Step 1753: {'lr': 0.000438, 'samples': 336576, 'steps': 1752, 'loss/train': 3.610065221786499} 08/30/2021 13:32:21 - INFO - __main__ - Step 1754: {'lr': 0.00043825, 'samples': 336768, 'steps': 1753, 'loss/train': 3.787497043609619} 08/30/2021 13:32:22 - INFO - __main__ - Step 1755: {'lr': 0.00043850000000000003, 'samples': 336960, 'steps': 1754, 'loss/train': 3.547999858856201} 08/30/2021 13:32:22 - INFO - __main__ - Step 1756: {'lr': 0.00043874999999999996, 'samples': 337152, 'steps': 1755, 'loss/train': 3.187812089920044} 08/30/2021 13:32:23 - INFO - __main__ - Step 1757: {'lr': 0.000439, 'samples': 337344, 'steps': 1756, 'loss/train': 3.791693925857544} 08/30/2021 13:32:24 - INFO - __main__ - Step 1758: {'lr': 0.00043924999999999997, 'samples': 337536, 'steps': 1757, 'loss/train': 3.908297300338745} 08/30/2021 13:32:24 - INFO - __main__ - Step 1759: {'lr': 0.0004395, 'samples': 337728, 'steps': 1758, 'loss/train': 4.370672702789307} 08/30/2021 13:32:25 - INFO - __main__ - Step 1760: {'lr': 0.00043975, 'samples': 337920, 'steps': 1759, 'loss/train': 2.3841192722320557} 08/30/2021 13:32:25 - INFO - __main__ - Step 1761: {'lr': 0.00044, 'samples': 338112, 'steps': 1760, 'loss/train': 2.305006742477417} 08/30/2021 13:32:25 - INFO - __main__ - Step 1762: {'lr': 0.00044025, 'samples': 338304, 'steps': 1761, 'loss/train': 4.077214241027832} 08/30/2021 13:32:27 - INFO - __main__ - Step 1763: {'lr': 0.00044050000000000003, 'samples': 338496, 'steps': 1762, 'loss/train': 3.9649477005004883} 08/30/2021 13:32:28 - INFO - __main__ - Step 1764: {'lr': 0.00044075, 'samples': 338688, 'steps': 1763, 'loss/train': 4.029394149780273} 08/30/2021 13:32:28 - INFO - __main__ - Step 1765: {'lr': 0.000441, 'samples': 338880, 'steps': 1764, 'loss/train': 3.631580352783203} 08/30/2021 13:32:28 - INFO - __main__ - Step 1766: {'lr': 0.00044124999999999996, 'samples': 339072, 'steps': 1765, 'loss/train': 3.723358154296875} 08/30/2021 13:32:29 - INFO - __main__ - Step 1767: {'lr': 0.0004415, 'samples': 339264, 'steps': 1766, 'loss/train': 2.810429573059082} 08/30/2021 13:32:29 - INFO - __main__ - Step 1768: {'lr': 0.00044175, 'samples': 339456, 'steps': 1767, 'loss/train': 2.503378391265869} 08/30/2021 13:32:31 - INFO - __main__ - Step 1769: {'lr': 0.000442, 'samples': 339648, 'steps': 1768, 'loss/train': 5.0331950187683105} 08/30/2021 13:32:32 - INFO - __main__ - Step 1770: {'lr': 0.00044225, 'samples': 339840, 'steps': 1769, 'loss/train': 4.137406349182129} 08/30/2021 13:32:32 - INFO - __main__ - Step 1771: {'lr': 0.0004425, 'samples': 340032, 'steps': 1770, 'loss/train': 3.5637762546539307} 08/30/2021 13:32:32 - INFO - __main__ - Step 1772: {'lr': 0.00044275, 'samples': 340224, 'steps': 1771, 'loss/train': 4.73265266418457} 08/30/2021 13:32:33 - INFO - __main__ - Step 1773: {'lr': 0.00044300000000000003, 'samples': 340416, 'steps': 1772, 'loss/train': 4.167478084564209} 08/30/2021 13:32:35 - INFO - __main__ - Step 1774: {'lr': 0.00044325, 'samples': 340608, 'steps': 1773, 'loss/train': 4.121479511260986} 08/30/2021 13:32:35 - INFO - __main__ - Step 1775: {'lr': 0.0004435, 'samples': 340800, 'steps': 1774, 'loss/train': 2.0559253692626953} 08/30/2021 13:32:35 - INFO - __main__ - Step 1776: {'lr': 0.00044374999999999997, 'samples': 340992, 'steps': 1775, 'loss/train': 3.804485559463501} 08/30/2021 13:32:36 - INFO - __main__ - Step 1777: {'lr': 0.000444, 'samples': 341184, 'steps': 1776, 'loss/train': 3.524785041809082} 08/30/2021 13:32:36 - INFO - __main__ - Step 1778: {'lr': 0.00044425, 'samples': 341376, 'steps': 1777, 'loss/train': 4.243947982788086} 08/30/2021 13:32:38 - INFO - __main__ - Step 1779: {'lr': 0.0004445, 'samples': 341568, 'steps': 1778, 'loss/train': 3.671976089477539} 08/30/2021 13:32:38 - INFO - __main__ - Step 1780: {'lr': 0.00044475, 'samples': 341760, 'steps': 1779, 'loss/train': 3.7523791790008545} 08/30/2021 13:32:38 - INFO - __main__ - Step 1781: {'lr': 0.00044500000000000003, 'samples': 341952, 'steps': 1780, 'loss/train': 3.83473539352417} 08/30/2021 13:32:39 - INFO - __main__ - Step 1782: {'lr': 0.00044525, 'samples': 342144, 'steps': 1781, 'loss/train': 4.172183513641357} 08/30/2021 13:32:39 - INFO - __main__ - Step 1783: {'lr': 0.00044550000000000004, 'samples': 342336, 'steps': 1782, 'loss/train': 4.258868217468262} 08/30/2021 13:32:41 - INFO - __main__ - Step 1784: {'lr': 0.00044574999999999997, 'samples': 342528, 'steps': 1783, 'loss/train': 6.953623294830322} 08/30/2021 13:32:41 - INFO - __main__ - Step 1785: {'lr': 0.000446, 'samples': 342720, 'steps': 1784, 'loss/train': 3.3653876781463623} 08/30/2021 13:32:41 - INFO - __main__ - Step 1786: {'lr': 0.00044625, 'samples': 342912, 'steps': 1785, 'loss/train': 5.904109001159668} 08/30/2021 13:32:42 - INFO - __main__ - Step 1787: {'lr': 0.0004465, 'samples': 343104, 'steps': 1786, 'loss/train': 4.541056156158447} 08/30/2021 13:32:42 - INFO - __main__ - Step 1788: {'lr': 0.00044675, 'samples': 343296, 'steps': 1787, 'loss/train': 3.6556994915008545} 08/30/2021 13:32:44 - INFO - __main__ - Step 1789: {'lr': 0.000447, 'samples': 343488, 'steps': 1788, 'loss/train': 3.887575387954712} 08/30/2021 13:32:44 - INFO - __main__ - Step 1790: {'lr': 0.00044725, 'samples': 343680, 'steps': 1789, 'loss/train': 4.294520378112793} 08/30/2021 13:32:44 - INFO - __main__ - Step 1791: {'lr': 0.00044750000000000004, 'samples': 343872, 'steps': 1790, 'loss/train': 3.997781753540039} 08/30/2021 13:32:45 - INFO - __main__ - Step 1792: {'lr': 0.00044775, 'samples': 344064, 'steps': 1791, 'loss/train': 4.512619495391846} 08/30/2021 13:32:45 - INFO - __main__ - Step 1793: {'lr': 0.000448, 'samples': 344256, 'steps': 1792, 'loss/train': 4.260393142700195} 08/30/2021 13:32:47 - INFO - __main__ - Step 1794: {'lr': 0.00044824999999999997, 'samples': 344448, 'steps': 1793, 'loss/train': 3.5534934997558594} 08/30/2021 13:32:47 - INFO - __main__ - Step 1795: {'lr': 0.0004485, 'samples': 344640, 'steps': 1794, 'loss/train': 4.273794174194336} 08/30/2021 13:32:48 - INFO - __main__ - Step 1796: {'lr': 0.00044875, 'samples': 344832, 'steps': 1795, 'loss/train': 4.101879596710205} 08/30/2021 13:32:48 - INFO - __main__ - Step 1797: {'lr': 0.000449, 'samples': 345024, 'steps': 1796, 'loss/train': 3.60370135307312} 08/30/2021 13:32:48 - INFO - __main__ - Step 1798: {'lr': 0.00044925, 'samples': 345216, 'steps': 1797, 'loss/train': 2.5743050575256348} 08/30/2021 13:32:49 - INFO - __main__ - Step 1799: {'lr': 0.00044950000000000003, 'samples': 345408, 'steps': 1798, 'loss/train': 3.873318672180176} 08/30/2021 13:32:50 - INFO - __main__ - Step 1800: {'lr': 0.00044975, 'samples': 345600, 'steps': 1799, 'loss/train': 3.587174892425537} 08/30/2021 13:32:50 - INFO - __main__ - Step 1801: {'lr': 0.00045000000000000004, 'samples': 345792, 'steps': 1800, 'loss/train': 3.988168716430664} 08/30/2021 13:32:51 - INFO - __main__ - Step 1802: {'lr': 0.00045024999999999997, 'samples': 345984, 'steps': 1801, 'loss/train': 4.558698654174805} 08/30/2021 13:32:51 - INFO - __main__ - Step 1803: {'lr': 0.0004505, 'samples': 346176, 'steps': 1802, 'loss/train': 2.978074073791504} 08/30/2021 13:32:51 - INFO - __main__ - Step 1804: {'lr': 0.00045075, 'samples': 346368, 'steps': 1803, 'loss/train': 4.602495193481445} 08/30/2021 13:32:53 - INFO - __main__ - Step 1805: {'lr': 0.000451, 'samples': 346560, 'steps': 1804, 'loss/train': 3.7294809818267822} 08/30/2021 13:32:54 - INFO - __main__ - Step 1806: {'lr': 0.00045125, 'samples': 346752, 'steps': 1805, 'loss/train': 2.315081834793091} 08/30/2021 13:32:54 - INFO - __main__ - Step 1807: {'lr': 0.0004515, 'samples': 346944, 'steps': 1806, 'loss/train': 3.4423391819000244} 08/30/2021 13:32:54 - INFO - __main__ - Step 1808: {'lr': 0.00045175, 'samples': 347136, 'steps': 1807, 'loss/train': 4.13805627822876} 08/30/2021 13:32:55 - INFO - __main__ - Step 1809: {'lr': 0.00045200000000000004, 'samples': 347328, 'steps': 1808, 'loss/train': 3.755753993988037} 08/30/2021 13:32:56 - INFO - __main__ - Step 1810: {'lr': 0.00045225, 'samples': 347520, 'steps': 1809, 'loss/train': 3.993638277053833} 08/30/2021 13:32:57 - INFO - __main__ - Step 1811: {'lr': 0.00045250000000000005, 'samples': 347712, 'steps': 1810, 'loss/train': 4.206995964050293} 08/30/2021 13:32:57 - INFO - __main__ - Step 1812: {'lr': 0.00045275, 'samples': 347904, 'steps': 1811, 'loss/train': 4.250825881958008} 08/30/2021 13:32:57 - INFO - __main__ - Step 1813: {'lr': 0.000453, 'samples': 348096, 'steps': 1812, 'loss/train': 4.152008533477783} 08/30/2021 13:32:58 - INFO - __main__ - Step 1814: {'lr': 0.00045325, 'samples': 348288, 'steps': 1813, 'loss/train': 2.5532729625701904} 08/30/2021 13:32:59 - INFO - __main__ - Step 1815: {'lr': 0.0004535, 'samples': 348480, 'steps': 1814, 'loss/train': 3.8477673530578613} 08/30/2021 13:33:00 - INFO - __main__ - Step 1816: {'lr': 0.00045375, 'samples': 348672, 'steps': 1815, 'loss/train': 4.381932735443115} 08/30/2021 13:33:00 - INFO - __main__ - Step 1817: {'lr': 0.00045400000000000003, 'samples': 348864, 'steps': 1816, 'loss/train': 3.4737496376037598} 08/30/2021 13:33:01 - INFO - __main__ - Step 1818: {'lr': 0.00045425, 'samples': 349056, 'steps': 1817, 'loss/train': 4.0976972579956055} 08/30/2021 13:33:01 - INFO - __main__ - Step 1819: {'lr': 0.00045450000000000004, 'samples': 349248, 'steps': 1818, 'loss/train': 4.001212120056152} 08/30/2021 13:33:02 - INFO - __main__ - Step 1820: {'lr': 0.00045475, 'samples': 349440, 'steps': 1819, 'loss/train': 3.7729732990264893} 08/30/2021 13:33:03 - INFO - __main__ - Step 1821: {'lr': 0.000455, 'samples': 349632, 'steps': 1820, 'loss/train': 4.435334205627441} 08/30/2021 13:33:03 - INFO - __main__ - Step 1822: {'lr': 0.00045525, 'samples': 349824, 'steps': 1821, 'loss/train': 5.007040023803711} 08/30/2021 13:33:04 - INFO - __main__ - Step 1823: {'lr': 0.0004555, 'samples': 350016, 'steps': 1822, 'loss/train': 4.017209053039551} 08/30/2021 13:33:04 - INFO - __main__ - Step 1824: {'lr': 0.00045575, 'samples': 350208, 'steps': 1823, 'loss/train': 3.8874261379241943} 08/30/2021 13:33:06 - INFO - __main__ - Step 1825: {'lr': 0.000456, 'samples': 350400, 'steps': 1824, 'loss/train': 4.341891765594482} 08/30/2021 13:33:06 - INFO - __main__ - Step 1826: {'lr': 0.00045625, 'samples': 350592, 'steps': 1825, 'loss/train': 3.9138295650482178} 08/30/2021 13:33:06 - INFO - __main__ - Step 1827: {'lr': 0.00045650000000000004, 'samples': 350784, 'steps': 1826, 'loss/train': 4.223025798797607} 08/30/2021 13:33:07 - INFO - __main__ - Step 1828: {'lr': 0.00045675, 'samples': 350976, 'steps': 1827, 'loss/train': 4.082917213439941} 08/30/2021 13:33:07 - INFO - __main__ - Step 1829: {'lr': 0.00045700000000000005, 'samples': 351168, 'steps': 1828, 'loss/train': 3.6689260005950928} 08/30/2021 13:33:09 - INFO - __main__ - Step 1830: {'lr': 0.00045725, 'samples': 351360, 'steps': 1829, 'loss/train': 4.08038854598999} 08/30/2021 13:33:09 - INFO - __main__ - Step 1831: {'lr': 0.0004575, 'samples': 351552, 'steps': 1830, 'loss/train': 3.8469529151916504} 08/30/2021 13:33:10 - INFO - __main__ - Step 1832: {'lr': 0.00045775, 'samples': 351744, 'steps': 1831, 'loss/train': 3.804262161254883} 08/30/2021 13:33:10 - INFO - __main__ - Step 1833: {'lr': 0.000458, 'samples': 351936, 'steps': 1832, 'loss/train': 3.862908363342285} 08/30/2021 13:33:10 - INFO - __main__ - Step 1834: {'lr': 0.00045825, 'samples': 352128, 'steps': 1833, 'loss/train': 4.24948787689209} 08/30/2021 13:33:11 - INFO - __main__ - Step 1835: {'lr': 0.00045850000000000003, 'samples': 352320, 'steps': 1834, 'loss/train': 3.7653462886810303} 08/30/2021 13:33:13 - INFO - __main__ - Step 1836: {'lr': 0.00045875, 'samples': 352512, 'steps': 1835, 'loss/train': 3.9597079753875732} 08/30/2021 13:33:13 - INFO - __main__ - Step 1837: {'lr': 0.00045900000000000004, 'samples': 352704, 'steps': 1836, 'loss/train': 3.816056251525879} 08/30/2021 13:33:13 - INFO - __main__ - Step 1838: {'lr': 0.00045925, 'samples': 352896, 'steps': 1837, 'loss/train': 1.7432626485824585} 08/30/2021 13:33:14 - INFO - __main__ - Step 1839: {'lr': 0.00045950000000000006, 'samples': 353088, 'steps': 1838, 'loss/train': 3.7407479286193848} 08/30/2021 13:33:14 - INFO - __main__ - Step 1840: {'lr': 0.00045975, 'samples': 353280, 'steps': 1839, 'loss/train': 4.176888942718506} 08/30/2021 13:33:15 - INFO - __main__ - Step 1841: {'lr': 0.00046, 'samples': 353472, 'steps': 1840, 'loss/train': 3.407545328140259} 08/30/2021 13:33:16 - INFO - __main__ - Step 1842: {'lr': 0.00046025, 'samples': 353664, 'steps': 1841, 'loss/train': 4.078118324279785} 08/30/2021 13:33:16 - INFO - __main__ - Step 1843: {'lr': 0.0004605, 'samples': 353856, 'steps': 1842, 'loss/train': 3.4387409687042236} 08/30/2021 13:33:17 - INFO - __main__ - Step 1844: {'lr': 0.00046075, 'samples': 354048, 'steps': 1843, 'loss/train': 4.269843101501465} 08/30/2021 13:33:17 - INFO - __main__ - Step 1845: {'lr': 0.00046100000000000004, 'samples': 354240, 'steps': 1844, 'loss/train': 3.4776978492736816} 08/30/2021 13:33:19 - INFO - __main__ - Step 1846: {'lr': 0.00046125, 'samples': 354432, 'steps': 1845, 'loss/train': 3.323798418045044} 08/30/2021 13:33:19 - INFO - __main__ - Step 1847: {'lr': 0.00046150000000000005, 'samples': 354624, 'steps': 1846, 'loss/train': 3.570096015930176} 08/30/2021 13:33:19 - INFO - __main__ - Step 1848: {'lr': 0.00046175000000000003, 'samples': 354816, 'steps': 1847, 'loss/train': 4.458643436431885} 08/30/2021 13:33:20 - INFO - __main__ - Step 1849: {'lr': 0.000462, 'samples': 355008, 'steps': 1848, 'loss/train': 3.6618752479553223} 08/30/2021 13:33:20 - INFO - __main__ - Step 1850: {'lr': 0.00046225, 'samples': 355200, 'steps': 1849, 'loss/train': 4.308147430419922} 08/30/2021 13:33:22 - INFO - __main__ - Step 1851: {'lr': 0.0004625, 'samples': 355392, 'steps': 1850, 'loss/train': 4.221744060516357} 08/30/2021 13:33:22 - INFO - __main__ - Step 1852: {'lr': 0.00046275, 'samples': 355584, 'steps': 1851, 'loss/train': 4.10622501373291} 08/30/2021 13:33:23 - INFO - __main__ - Step 1853: {'lr': 0.00046300000000000003, 'samples': 355776, 'steps': 1852, 'loss/train': 3.997800588607788} 08/30/2021 13:33:23 - INFO - __main__ - Step 1854: {'lr': 0.00046325, 'samples': 355968, 'steps': 1853, 'loss/train': 3.75465726852417} 08/30/2021 13:33:23 - INFO - __main__ - Step 1855: {'lr': 0.00046350000000000004, 'samples': 356160, 'steps': 1854, 'loss/train': 6.074405193328857} 08/30/2021 13:33:24 - INFO - __main__ - Step 1856: {'lr': 0.00046375, 'samples': 356352, 'steps': 1855, 'loss/train': 4.297353744506836} 08/30/2021 13:33:25 - INFO - __main__ - Step 1857: {'lr': 0.00046400000000000006, 'samples': 356544, 'steps': 1856, 'loss/train': 3.6608734130859375} 08/30/2021 13:33:26 - INFO - __main__ - Step 1858: {'lr': 0.00046425, 'samples': 356736, 'steps': 1857, 'loss/train': 4.111756324768066} 08/30/2021 13:33:26 - INFO - __main__ - Step 1859: {'lr': 0.0004645, 'samples': 356928, 'steps': 1858, 'loss/train': 3.2915756702423096} 08/30/2021 13:33:26 - INFO - __main__ - Step 1860: {'lr': 0.00046475, 'samples': 357120, 'steps': 1859, 'loss/train': 4.302042007446289} 08/30/2021 13:33:27 - INFO - __main__ - Step 1861: {'lr': 0.000465, 'samples': 357312, 'steps': 1860, 'loss/train': 3.8228554725646973} 08/30/2021 13:33:28 - INFO - __main__ - Step 1862: {'lr': 0.00046525, 'samples': 357504, 'steps': 1861, 'loss/train': 3.304464817047119} 08/30/2021 13:33:29 - INFO - __main__ - Step 1863: {'lr': 0.00046550000000000004, 'samples': 357696, 'steps': 1862, 'loss/train': 4.269545078277588} 08/30/2021 13:33:29 - INFO - __main__ - Step 1864: {'lr': 0.00046575, 'samples': 357888, 'steps': 1863, 'loss/train': 3.2907872200012207} 08/30/2021 13:33:29 - INFO - __main__ - Step 1865: {'lr': 0.00046600000000000005, 'samples': 358080, 'steps': 1864, 'loss/train': 4.103222370147705} 08/30/2021 13:33:30 - INFO - __main__ - Step 1866: {'lr': 0.00046625000000000003, 'samples': 358272, 'steps': 1865, 'loss/train': 4.721673488616943} 08/30/2021 13:33:31 - INFO - __main__ - Step 1867: {'lr': 0.0004665, 'samples': 358464, 'steps': 1866, 'loss/train': 4.846536636352539} 08/30/2021 13:33:32 - INFO - __main__ - Step 1868: {'lr': 0.00046675, 'samples': 358656, 'steps': 1867, 'loss/train': 4.437201976776123} 08/30/2021 13:33:32 - INFO - __main__ - Step 1869: {'lr': 0.000467, 'samples': 358848, 'steps': 1868, 'loss/train': 3.9709482192993164} 08/30/2021 13:33:32 - INFO - __main__ - Step 1870: {'lr': 0.00046725, 'samples': 359040, 'steps': 1869, 'loss/train': 3.8383877277374268} 08/30/2021 13:33:33 - INFO - __main__ - Step 1871: {'lr': 0.00046750000000000003, 'samples': 359232, 'steps': 1870, 'loss/train': 3.8616721630096436} 08/30/2021 13:33:34 - INFO - __main__ - Step 1872: {'lr': 0.00046775, 'samples': 359424, 'steps': 1871, 'loss/train': 4.496031284332275} 08/30/2021 13:33:35 - INFO - __main__ - Step 1873: {'lr': 0.00046800000000000005, 'samples': 359616, 'steps': 1872, 'loss/train': 3.8477094173431396} 08/30/2021 13:33:35 - INFO - __main__ - Step 1874: {'lr': 0.00046825, 'samples': 359808, 'steps': 1873, 'loss/train': 3.4782001972198486} 08/30/2021 13:33:36 - INFO - __main__ - Step 1875: {'lr': 0.00046850000000000006, 'samples': 360000, 'steps': 1874, 'loss/train': 3.167875289916992} 08/30/2021 13:33:36 - INFO - __main__ - Step 1876: {'lr': 0.00046875, 'samples': 360192, 'steps': 1875, 'loss/train': 3.74480938911438} 08/30/2021 13:33:37 - INFO - __main__ - Step 1877: {'lr': 0.00046899999999999996, 'samples': 360384, 'steps': 1876, 'loss/train': 3.590226650238037} 08/30/2021 13:33:38 - INFO - __main__ - Step 1878: {'lr': 0.00046925, 'samples': 360576, 'steps': 1877, 'loss/train': 3.8205149173736572} 08/30/2021 13:33:38 - INFO - __main__ - Step 1879: {'lr': 0.0004695, 'samples': 360768, 'steps': 1878, 'loss/train': 4.053231716156006} 08/30/2021 13:33:38 - INFO - __main__ - Step 1880: {'lr': 0.00046975, 'samples': 360960, 'steps': 1879, 'loss/train': 4.020791530609131} 08/30/2021 13:33:39 - INFO - __main__ - Step 1881: {'lr': 0.00047, 'samples': 361152, 'steps': 1880, 'loss/train': 3.427460193634033} 08/30/2021 13:33:41 - INFO - __main__ - Step 1882: {'lr': 0.00047025, 'samples': 361344, 'steps': 1881, 'loss/train': 2.1546480655670166} 08/30/2021 13:33:41 - INFO - __main__ - Step 1883: {'lr': 0.0004705, 'samples': 361536, 'steps': 1882, 'loss/train': 4.243077278137207} 08/30/2021 13:33:42 - INFO - __main__ - Step 1884: {'lr': 0.00047075000000000003, 'samples': 361728, 'steps': 1883, 'loss/train': 4.100534915924072} 08/30/2021 13:33:42 - INFO - __main__ - Step 1885: {'lr': 0.000471, 'samples': 361920, 'steps': 1884, 'loss/train': 3.798335313796997} 08/30/2021 13:33:42 - INFO - __main__ - Step 1886: {'lr': 0.00047125, 'samples': 362112, 'steps': 1885, 'loss/train': 4.3711466789245605} 08/30/2021 13:33:43 - INFO - __main__ - Step 1887: {'lr': 0.00047149999999999997, 'samples': 362304, 'steps': 1886, 'loss/train': 3.492220640182495} 08/30/2021 13:33:44 - INFO - __main__ - Step 1888: {'lr': 0.00047175, 'samples': 362496, 'steps': 1887, 'loss/train': 4.2310662269592285} 08/30/2021 13:33:45 - INFO - __main__ - Step 1889: {'lr': 0.000472, 'samples': 362688, 'steps': 1888, 'loss/train': 3.697628974914551} 08/30/2021 13:33:45 - INFO - __main__ - Step 1890: {'lr': 0.00047225, 'samples': 362880, 'steps': 1889, 'loss/train': 4.416256904602051} 08/30/2021 13:33:46 - INFO - __main__ - Step 1891: {'lr': 0.0004725, 'samples': 363072, 'steps': 1890, 'loss/train': 5.274457931518555} 08/30/2021 13:33:46 - INFO - __main__ - Step 1892: {'lr': 0.00047275, 'samples': 363264, 'steps': 1891, 'loss/train': 4.132111549377441} 08/30/2021 13:33:48 - INFO - __main__ - Step 1893: {'lr': 0.000473, 'samples': 363456, 'steps': 1892, 'loss/train': 4.002604007720947} 08/30/2021 13:33:48 - INFO - __main__ - Step 1894: {'lr': 0.00047325000000000004, 'samples': 363648, 'steps': 1893, 'loss/train': 4.229362964630127} 08/30/2021 13:33:48 - INFO - __main__ - Step 1895: {'lr': 0.00047349999999999996, 'samples': 363840, 'steps': 1894, 'loss/train': 4.218633651733398} 08/30/2021 13:33:49 - INFO - __main__ - Step 1896: {'lr': 0.00047375, 'samples': 364032, 'steps': 1895, 'loss/train': 5.024405479431152} 08/30/2021 13:33:49 - INFO - __main__ - Step 1897: {'lr': 0.000474, 'samples': 364224, 'steps': 1896, 'loss/train': 4.995138645172119} 08/30/2021 13:33:49 - INFO - __main__ - Step 1898: {'lr': 0.00047425, 'samples': 364416, 'steps': 1897, 'loss/train': 4.169946193695068} 08/30/2021 13:33:51 - INFO - __main__ - Step 1899: {'lr': 0.0004745, 'samples': 364608, 'steps': 1898, 'loss/train': 4.533463001251221} 08/30/2021 13:33:51 - INFO - __main__ - Step 1900: {'lr': 0.00047475, 'samples': 364800, 'steps': 1899, 'loss/train': 3.4824893474578857} 08/30/2021 13:33:52 - INFO - __main__ - Step 1901: {'lr': 0.000475, 'samples': 364992, 'steps': 1900, 'loss/train': 4.135907173156738} 08/30/2021 13:33:52 - INFO - __main__ - Step 1902: {'lr': 0.00047525000000000003, 'samples': 365184, 'steps': 1901, 'loss/train': 2.825798988342285} 08/30/2021 13:33:52 - INFO - __main__ - Step 1903: {'lr': 0.0004755, 'samples': 365376, 'steps': 1902, 'loss/train': 3.729189872741699} 08/30/2021 13:33:54 - INFO - __main__ - Step 1904: {'lr': 0.00047575, 'samples': 365568, 'steps': 1903, 'loss/train': 4.196805477142334} 08/30/2021 13:33:54 - INFO - __main__ - Step 1905: {'lr': 0.00047599999999999997, 'samples': 365760, 'steps': 1904, 'loss/train': 4.139028549194336} 08/30/2021 13:33:55 - INFO - __main__ - Step 1906: {'lr': 0.00047625, 'samples': 365952, 'steps': 1905, 'loss/train': 4.455804824829102} 08/30/2021 13:33:55 - INFO - __main__ - Step 1907: {'lr': 0.0004765, 'samples': 366144, 'steps': 1906, 'loss/train': 3.751356840133667} 08/30/2021 13:33:55 - INFO - __main__ - Step 1908: {'lr': 0.00047675, 'samples': 366336, 'steps': 1907, 'loss/train': 3.362111806869507} 08/30/2021 13:33:57 - INFO - __main__ - Step 1909: {'lr': 0.000477, 'samples': 366528, 'steps': 1908, 'loss/train': 3.608022928237915} 08/30/2021 13:33:57 - INFO - __main__ - Step 1910: {'lr': 0.00047725, 'samples': 366720, 'steps': 1909, 'loss/train': 2.9700682163238525} 08/30/2021 13:33:58 - INFO - __main__ - Step 1911: {'lr': 0.0004775, 'samples': 366912, 'steps': 1910, 'loss/train': 4.289870738983154} 08/30/2021 13:33:58 - INFO - __main__ - Step 1912: {'lr': 0.00047775000000000004, 'samples': 367104, 'steps': 1911, 'loss/train': 4.144138336181641} 08/30/2021 13:33:58 - INFO - __main__ - Step 1913: {'lr': 0.00047799999999999996, 'samples': 367296, 'steps': 1912, 'loss/train': 4.10355281829834} 08/30/2021 13:34:00 - INFO - __main__ - Step 1914: {'lr': 0.00047825, 'samples': 367488, 'steps': 1913, 'loss/train': 2.017336368560791} 08/30/2021 13:34:00 - INFO - __main__ - Step 1915: {'lr': 0.0004785, 'samples': 367680, 'steps': 1914, 'loss/train': 3.983057975769043} 08/30/2021 13:34:01 - INFO - __main__ - Step 1916: {'lr': 0.00047875, 'samples': 367872, 'steps': 1915, 'loss/train': 3.5344715118408203} 08/30/2021 13:34:01 - INFO - __main__ - Step 1917: {'lr': 0.000479, 'samples': 368064, 'steps': 1916, 'loss/train': 3.5695202350616455} 08/30/2021 13:34:01 - INFO - __main__ - Step 1918: {'lr': 0.00047925, 'samples': 368256, 'steps': 1917, 'loss/train': 3.8029837608337402} 08/30/2021 13:34:02 - INFO - __main__ - Step 1919: {'lr': 0.0004795, 'samples': 368448, 'steps': 1918, 'loss/train': 4.074838638305664} 08/30/2021 13:34:03 - INFO - __main__ - Step 1920: {'lr': 0.00047975000000000003, 'samples': 368640, 'steps': 1919, 'loss/train': 3.663607120513916} 08/30/2021 13:34:04 - INFO - __main__ - Step 1921: {'lr': 0.00048, 'samples': 368832, 'steps': 1920, 'loss/train': 3.7792277336120605} 08/30/2021 13:34:04 - INFO - __main__ - Step 1922: {'lr': 0.00048025000000000005, 'samples': 369024, 'steps': 1921, 'loss/train': 3.6022844314575195} 08/30/2021 13:34:04 - INFO - __main__ - Step 1923: {'lr': 0.00048049999999999997, 'samples': 369216, 'steps': 1922, 'loss/train': 4.036792278289795} 08/30/2021 13:34:05 - INFO - __main__ - Step 1924: {'lr': 0.00048075, 'samples': 369408, 'steps': 1923, 'loss/train': 4.241264820098877} 08/30/2021 13:34:07 - INFO - __main__ - Step 1925: {'lr': 0.000481, 'samples': 369600, 'steps': 1924, 'loss/train': 3.9819133281707764} 08/30/2021 13:34:07 - INFO - __main__ - Step 1926: {'lr': 0.00048125, 'samples': 369792, 'steps': 1925, 'loss/train': 3.559974431991577} 08/30/2021 13:34:07 - INFO - __main__ - Step 1927: {'lr': 0.0004815, 'samples': 369984, 'steps': 1926, 'loss/train': 3.747083902359009} 08/30/2021 13:34:08 - INFO - __main__ - Step 1928: {'lr': 0.00048175000000000003, 'samples': 370176, 'steps': 1927, 'loss/train': 1.3425077199935913} 08/30/2021 13:34:08 - INFO - __main__ - Step 1929: {'lr': 0.000482, 'samples': 370368, 'steps': 1928, 'loss/train': 4.593088150024414} 08/30/2021 13:34:10 - INFO - __main__ - Step 1930: {'lr': 0.00048225000000000004, 'samples': 370560, 'steps': 1929, 'loss/train': 4.031519889831543} 08/30/2021 13:34:10 - INFO - __main__ - Step 1931: {'lr': 0.0004825, 'samples': 370752, 'steps': 1930, 'loss/train': 3.6667327880859375} 08/30/2021 13:34:10 - INFO - __main__ - Step 1932: {'lr': 0.00048275, 'samples': 370944, 'steps': 1931, 'loss/train': 3.720813512802124} 08/30/2021 13:34:11 - INFO - __main__ - Step 1933: {'lr': 0.000483, 'samples': 371136, 'steps': 1932, 'loss/train': 3.514467716217041} 08/30/2021 13:34:11 - INFO - __main__ - Step 1934: {'lr': 0.00048325, 'samples': 371328, 'steps': 1933, 'loss/train': 3.9238007068634033} 08/30/2021 13:34:13 - INFO - __main__ - Step 1935: {'lr': 0.0004835, 'samples': 371520, 'steps': 1934, 'loss/train': 4.041956424713135} 08/30/2021 13:34:14 - INFO - __main__ - Step 1936: {'lr': 0.00048375, 'samples': 371712, 'steps': 1935, 'loss/train': 3.0714752674102783} 08/30/2021 13:34:14 - INFO - __main__ - Step 1937: {'lr': 0.000484, 'samples': 371904, 'steps': 1936, 'loss/train': 3.7970077991485596} 08/30/2021 13:34:15 - INFO - __main__ - Step 1938: {'lr': 0.00048425000000000003, 'samples': 372096, 'steps': 1937, 'loss/train': 1.7311993837356567} 08/30/2021 13:34:15 - INFO - __main__ - Step 1939: {'lr': 0.0004845, 'samples': 372288, 'steps': 1938, 'loss/train': 5.09821891784668} 08/30/2021 13:34:16 - INFO - __main__ - Step 1940: {'lr': 0.00048475000000000005, 'samples': 372480, 'steps': 1939, 'loss/train': 4.333300590515137} 08/30/2021 13:34:17 - INFO - __main__ - Step 1941: {'lr': 0.00048499999999999997, 'samples': 372672, 'steps': 1940, 'loss/train': 4.0591020584106445} 08/30/2021 13:34:17 - INFO - __main__ - Step 1942: {'lr': 0.00048525, 'samples': 372864, 'steps': 1941, 'loss/train': 3.329667329788208} 08/30/2021 13:34:18 - INFO - __main__ - Step 1943: {'lr': 0.0004855, 'samples': 373056, 'steps': 1942, 'loss/train': 3.636807441711426} 08/30/2021 13:34:18 - INFO - __main__ - Step 1944: {'lr': 0.00048575, 'samples': 373248, 'steps': 1943, 'loss/train': 4.212170124053955} 08/30/2021 13:34:18 - INFO - __main__ - Step 1945: {'lr': 0.000486, 'samples': 373440, 'steps': 1944, 'loss/train': 3.7817118167877197} 08/30/2021 13:34:20 - INFO - __main__ - Step 1946: {'lr': 0.00048625000000000003, 'samples': 373632, 'steps': 1945, 'loss/train': 3.895685911178589} 08/30/2021 13:34:20 - INFO - __main__ - Step 1947: {'lr': 0.0004865, 'samples': 373824, 'steps': 1946, 'loss/train': 4.491222381591797} 08/30/2021 13:34:21 - INFO - __main__ - Step 1948: {'lr': 0.00048675000000000004, 'samples': 374016, 'steps': 1947, 'loss/train': 4.426873207092285} 08/30/2021 13:34:21 - INFO - __main__ - Step 1949: {'lr': 0.000487, 'samples': 374208, 'steps': 1948, 'loss/train': 3.7109720706939697} 08/30/2021 13:34:22 - INFO - __main__ - Step 1950: {'lr': 0.00048725000000000005, 'samples': 374400, 'steps': 1949, 'loss/train': 4.7153778076171875} 08/30/2021 13:34:23 - INFO - __main__ - Step 1951: {'lr': 0.0004875, 'samples': 374592, 'steps': 1950, 'loss/train': 4.433164119720459} 08/30/2021 13:34:23 - INFO - __main__ - Step 1952: {'lr': 0.00048775, 'samples': 374784, 'steps': 1951, 'loss/train': 4.409071445465088} 08/30/2021 13:34:24 - INFO - __main__ - Step 1953: {'lr': 0.000488, 'samples': 374976, 'steps': 1952, 'loss/train': 3.639925003051758} 08/30/2021 13:34:24 - INFO - __main__ - Step 1954: {'lr': 0.00048825, 'samples': 375168, 'steps': 1953, 'loss/train': 3.6265134811401367} 08/30/2021 13:34:24 - INFO - __main__ - Step 1955: {'lr': 0.0004885, 'samples': 375360, 'steps': 1954, 'loss/train': 4.043466091156006} 08/30/2021 13:34:26 - INFO - __main__ - Step 1956: {'lr': 0.00048875, 'samples': 375552, 'steps': 1955, 'loss/train': 3.6802093982696533} 08/30/2021 13:34:26 - INFO - __main__ - Step 1957: {'lr': 0.000489, 'samples': 375744, 'steps': 1956, 'loss/train': 3.76971173286438} 08/30/2021 13:34:27 - INFO - __main__ - Step 1958: {'lr': 0.00048925, 'samples': 375936, 'steps': 1957, 'loss/train': 4.56354284286499} 08/30/2021 13:34:27 - INFO - __main__ - Step 1959: {'lr': 0.0004895, 'samples': 376128, 'steps': 1958, 'loss/train': 4.015387535095215} 08/30/2021 13:34:27 - INFO - __main__ - Step 1960: {'lr': 0.0004897500000000001, 'samples': 376320, 'steps': 1959, 'loss/train': 3.3302128314971924} 08/30/2021 13:34:29 - INFO - __main__ - Step 1961: {'lr': 0.00049, 'samples': 376512, 'steps': 1960, 'loss/train': 3.9128339290618896} 08/30/2021 13:34:30 - INFO - __main__ - Step 1962: {'lr': 0.00049025, 'samples': 376704, 'steps': 1961, 'loss/train': 3.8968732357025146} 08/30/2021 13:34:30 - INFO - __main__ - Step 1963: {'lr': 0.0004905, 'samples': 376896, 'steps': 1962, 'loss/train': 3.8942291736602783} 08/30/2021 13:34:31 - INFO - __main__ - Step 1964: {'lr': 0.0004907500000000001, 'samples': 377088, 'steps': 1963, 'loss/train': 3.332982301712036} 08/30/2021 13:34:31 - INFO - __main__ - Step 1965: {'lr': 0.000491, 'samples': 377280, 'steps': 1964, 'loss/train': 2.7537074089050293} 08/30/2021 13:34:31 - INFO - __main__ - Step 1966: {'lr': 0.00049125, 'samples': 377472, 'steps': 1965, 'loss/train': 3.9287052154541016} 08/30/2021 13:34:32 - INFO - __main__ - Step 1967: {'lr': 0.0004915, 'samples': 377664, 'steps': 1966, 'loss/train': 4.603787899017334} 08/30/2021 13:34:33 - INFO - __main__ - Step 1968: {'lr': 0.00049175, 'samples': 377856, 'steps': 1967, 'loss/train': 4.50520658493042} 08/30/2021 13:34:34 - INFO - __main__ - Step 1969: {'lr': 0.000492, 'samples': 378048, 'steps': 1968, 'loss/train': 4.162574768066406} 08/30/2021 13:34:34 - INFO - __main__ - Step 1970: {'lr': 0.0004922500000000001, 'samples': 378240, 'steps': 1969, 'loss/train': 3.282855987548828} 08/30/2021 13:34:35 - INFO - __main__ - Step 1971: {'lr': 0.0004925, 'samples': 378432, 'steps': 1970, 'loss/train': 4.245908737182617} 08/30/2021 13:34:35 - INFO - __main__ - Step 1972: {'lr': 0.00049275, 'samples': 378624, 'steps': 1971, 'loss/train': 4.855228424072266} 08/30/2021 13:34:37 - INFO - __main__ - Step 1973: {'lr': 0.0004930000000000001, 'samples': 378816, 'steps': 1972, 'loss/train': 2.7747647762298584} 08/30/2021 13:34:37 - INFO - __main__ - Step 1974: {'lr': 0.00049325, 'samples': 379008, 'steps': 1973, 'loss/train': 1.6275231838226318} 08/30/2021 13:34:38 - INFO - __main__ - Step 1975: {'lr': 0.0004935, 'samples': 379200, 'steps': 1974, 'loss/train': 3.992391586303711} 08/30/2021 13:34:38 - INFO - __main__ - Step 1976: {'lr': 0.00049375, 'samples': 379392, 'steps': 1975, 'loss/train': 3.8086373805999756} 08/30/2021 13:34:38 - INFO - __main__ - Step 1977: {'lr': 0.000494, 'samples': 379584, 'steps': 1976, 'loss/train': 3.5776429176330566} 08/30/2021 13:34:40 - INFO - __main__ - Step 1978: {'lr': 0.00049425, 'samples': 379776, 'steps': 1977, 'loss/train': 3.87422776222229} 08/30/2021 13:34:40 - INFO - __main__ - Step 1979: {'lr': 0.0004945, 'samples': 379968, 'steps': 1978, 'loss/train': 3.7341365814208984} 08/30/2021 13:34:41 - INFO - __main__ - Step 1980: {'lr': 0.0004947500000000001, 'samples': 380160, 'steps': 1979, 'loss/train': 4.149728298187256} 08/30/2021 13:34:41 - INFO - __main__ - Step 1981: {'lr': 0.000495, 'samples': 380352, 'steps': 1980, 'loss/train': 4.304142951965332} 08/30/2021 13:34:41 - INFO - __main__ - Step 1982: {'lr': 0.00049525, 'samples': 380544, 'steps': 1981, 'loss/train': 2.1806108951568604} 08/30/2021 13:34:42 - INFO - __main__ - Step 1983: {'lr': 0.0004955, 'samples': 380736, 'steps': 1982, 'loss/train': 4.651204586029053} 08/30/2021 13:34:43 - INFO - __main__ - Step 1984: {'lr': 0.00049575, 'samples': 380928, 'steps': 1983, 'loss/train': 4.128410816192627} 08/30/2021 13:34:44 - INFO - __main__ - Step 1985: {'lr': 0.000496, 'samples': 381120, 'steps': 1984, 'loss/train': 4.110437393188477} 08/30/2021 13:34:44 - INFO - __main__ - Step 1986: {'lr': 0.0004962500000000001, 'samples': 381312, 'steps': 1985, 'loss/train': 3.878854990005493} 08/30/2021 13:34:44 - INFO - __main__ - Step 1987: {'lr': 0.0004965, 'samples': 381504, 'steps': 1986, 'loss/train': 3.836554765701294} 08/30/2021 13:34:45 - INFO - __main__ - Step 1988: {'lr': 0.00049675, 'samples': 381696, 'steps': 1987, 'loss/train': 3.9784555435180664} 08/30/2021 13:34:47 - INFO - __main__ - Step 1989: {'lr': 0.000497, 'samples': 381888, 'steps': 1988, 'loss/train': 4.467948913574219} 08/30/2021 13:34:47 - INFO - __main__ - Step 1990: {'lr': 0.0004972500000000001, 'samples': 382080, 'steps': 1989, 'loss/train': 3.5761940479278564} 08/30/2021 13:34:48 - INFO - __main__ - Step 1991: {'lr': 0.0004975, 'samples': 382272, 'steps': 1990, 'loss/train': 3.889935255050659} 08/30/2021 13:34:48 - INFO - __main__ - Step 1992: {'lr': 0.00049775, 'samples': 382464, 'steps': 1991, 'loss/train': 3.6736230850219727} 08/30/2021 13:34:48 - INFO - __main__ - Step 1993: {'lr': 0.000498, 'samples': 382656, 'steps': 1992, 'loss/train': 3.549931049346924} 08/30/2021 13:34:50 - INFO - __main__ - Step 1994: {'lr': 0.00049825, 'samples': 382848, 'steps': 1993, 'loss/train': 2.8372669219970703} 08/30/2021 13:34:50 - INFO - __main__ - Step 1995: {'lr': 0.0004985, 'samples': 383040, 'steps': 1994, 'loss/train': 4.642188549041748} 08/30/2021 13:34:51 - INFO - __main__ - Step 1996: {'lr': 0.0004987500000000001, 'samples': 383232, 'steps': 1995, 'loss/train': 4.633870601654053} 08/30/2021 13:34:51 - INFO - __main__ - Step 1997: {'lr': 0.000499, 'samples': 383424, 'steps': 1996, 'loss/train': 4.201652526855469} 08/30/2021 13:34:51 - INFO - __main__ - Step 1998: {'lr': 0.00049925, 'samples': 383616, 'steps': 1997, 'loss/train': 3.846168041229248} 08/30/2021 13:34:53 - INFO - __main__ - Step 1999: {'lr': 0.0004995, 'samples': 383808, 'steps': 1998, 'loss/train': 3.3808515071868896} 08/30/2021 13:34:53 - INFO - __main__ - Step 2000: {'lr': 0.0004997500000000001, 'samples': 384000, 'steps': 1999, 'loss/train': 4.1292548179626465} 08/30/2021 13:34:54 - INFO - __main__ - Step 2001: {'lr': 0.0005, 'samples': 384192, 'steps': 2000, 'loss/train': 2.4327993392944336} 08/30/2021 13:34:54 - INFO - __main__ - Step 2002: {'lr': 0.0004999999999436769, 'samples': 384384, 'steps': 2001, 'loss/train': 4.1023712158203125} 08/30/2021 13:34:54 - INFO - __main__ - Step 2003: {'lr': 0.0004999999997747077, 'samples': 384576, 'steps': 2002, 'loss/train': 3.875941276550293} 08/30/2021 13:34:55 - INFO - __main__ - Step 2004: {'lr': 0.0004999999994930923, 'samples': 384768, 'steps': 2003, 'loss/train': 4.333718776702881} 08/30/2021 13:34:56 - INFO - __main__ - Step 2005: {'lr': 0.0004999999990988309, 'samples': 384960, 'steps': 2004, 'loss/train': 4.039220333099365} 08/30/2021 13:34:57 - INFO - __main__ - Step 2006: {'lr': 0.0004999999985919232, 'samples': 385152, 'steps': 2005, 'loss/train': 2.0358545780181885} 08/30/2021 13:34:57 - INFO - __main__ - Step 2007: {'lr': 0.0004999999979723695, 'samples': 385344, 'steps': 2006, 'loss/train': 3.6348371505737305} 08/30/2021 13:34:57 - INFO - __main__ - Step 2008: {'lr': 0.0004999999972401696, 'samples': 385536, 'steps': 2007, 'loss/train': 3.984771490097046} 08/30/2021 13:34:58 - INFO - __main__ - Step 2009: {'lr': 0.0004999999963953234, 'samples': 385728, 'steps': 2008, 'loss/train': 3.0698065757751465} 08/30/2021 13:34:59 - INFO - __main__ - Step 2010: {'lr': 0.0004999999954378312, 'samples': 385920, 'steps': 2009, 'loss/train': 2.84944486618042} 08/30/2021 13:35:00 - INFO - __main__ - Step 2011: {'lr': 0.000499999994367693, 'samples': 386112, 'steps': 2010, 'loss/train': 3.788355827331543} 08/30/2021 13:35:00 - INFO - __main__ - Step 2012: {'lr': 0.0004999999931849084, 'samples': 386304, 'steps': 2011, 'loss/train': 3.836803674697876} 08/30/2021 13:35:01 - INFO - __main__ - Step 2013: {'lr': 0.0004999999918894778, 'samples': 386496, 'steps': 2012, 'loss/train': 4.112085342407227} 08/30/2021 13:35:01 - INFO - __main__ - Step 2014: {'lr': 0.000499999990481401, 'samples': 386688, 'steps': 2013, 'loss/train': 3.578673839569092} 08/30/2021 13:35:02 - INFO - __main__ - Step 2015: {'lr': 0.0004999999889606781, 'samples': 386880, 'steps': 2014, 'loss/train': 2.6813108921051025} 08/30/2021 13:35:03 - INFO - __main__ - Step 2016: {'lr': 0.0004999999873273091, 'samples': 387072, 'steps': 2015, 'loss/train': 3.8371644020080566} 08/30/2021 13:35:03 - INFO - __main__ - Step 2017: {'lr': 0.000499999985581294, 'samples': 387264, 'steps': 2016, 'loss/train': 3.4323573112487793} 08/30/2021 13:35:04 - INFO - __main__ - Step 2018: {'lr': 0.0004999999837226326, 'samples': 387456, 'steps': 2017, 'loss/train': 3.466071128845215} 08/30/2021 13:35:04 - INFO - __main__ - Step 2019: {'lr': 0.0004999999817513252, 'samples': 387648, 'steps': 2018, 'loss/train': 3.250668525695801} 08/30/2021 13:35:06 - INFO - __main__ - Step 2020: {'lr': 0.0004999999796673716, 'samples': 387840, 'steps': 2019, 'loss/train': 3.8105993270874023} 08/30/2021 13:35:06 - INFO - __main__ - Step 2021: {'lr': 0.0004999999774707719, 'samples': 388032, 'steps': 2020, 'loss/train': 3.876354217529297} 08/30/2021 13:35:06 - INFO - __main__ - Step 2022: {'lr': 0.0004999999751615261, 'samples': 388224, 'steps': 2021, 'loss/train': 3.8295605182647705} 08/30/2021 13:35:07 - INFO - __main__ - Step 2023: {'lr': 0.0004999999727396341, 'samples': 388416, 'steps': 2022, 'loss/train': 1.8050475120544434} 08/30/2021 13:35:07 - INFO - __main__ - Step 2024: {'lr': 0.0004999999702050959, 'samples': 388608, 'steps': 2023, 'loss/train': 4.379288196563721} 08/30/2021 13:35:09 - INFO - __main__ - Step 2025: {'lr': 0.0004999999675579118, 'samples': 388800, 'steps': 2024, 'loss/train': 1.515298843383789} 08/30/2021 13:35:09 - INFO - __main__ - Step 2026: {'lr': 0.0004999999647980814, 'samples': 388992, 'steps': 2025, 'loss/train': 4.223230361938477} 08/30/2021 13:35:10 - INFO - __main__ - Step 2027: {'lr': 0.0004999999619256049, 'samples': 389184, 'steps': 2026, 'loss/train': 3.5991108417510986} 08/30/2021 13:35:10 - INFO - __main__ - Step 2028: {'lr': 0.0004999999589404822, 'samples': 389376, 'steps': 2027, 'loss/train': 4.679903984069824} 08/30/2021 13:35:10 - INFO - __main__ - Step 2029: {'lr': 0.0004999999558427136, 'samples': 389568, 'steps': 2028, 'loss/train': 3.4045114517211914} 08/30/2021 13:35:11 - INFO - __main__ - Step 2030: {'lr': 0.0004999999526322987, 'samples': 389760, 'steps': 2029, 'loss/train': 4.606021404266357} 08/30/2021 13:35:12 - INFO - __main__ - Step 2031: {'lr': 0.0004999999493092377, 'samples': 389952, 'steps': 2030, 'loss/train': 3.9545929431915283} 08/30/2021 13:35:13 - INFO - __main__ - Step 2032: {'lr': 0.0004999999458735306, 'samples': 390144, 'steps': 2031, 'loss/train': 4.512197971343994} 08/30/2021 13:35:13 - INFO - __main__ - Step 2033: {'lr': 0.0004999999423251774, 'samples': 390336, 'steps': 2032, 'loss/train': 4.206327438354492} 08/30/2021 13:35:13 - INFO - __main__ - Step 2034: {'lr': 0.0004999999386641781, 'samples': 390528, 'steps': 2033, 'loss/train': 3.3928580284118652} 08/30/2021 13:35:14 - INFO - __main__ - Step 2035: {'lr': 0.0004999999348905326, 'samples': 390720, 'steps': 2034, 'loss/train': 3.4217634201049805} 08/30/2021 13:35:16 - INFO - __main__ - Step 2036: {'lr': 0.000499999931004241, 'samples': 390912, 'steps': 2035, 'loss/train': 3.896252393722534} 08/30/2021 13:35:16 - INFO - __main__ - Step 2037: {'lr': 0.0004999999270053034, 'samples': 391104, 'steps': 2036, 'loss/train': 4.458357334136963} 08/30/2021 13:35:16 - INFO - __main__ - Step 2038: {'lr': 0.0004999999228937196, 'samples': 391296, 'steps': 2037, 'loss/train': 1.3921507596969604} 08/30/2021 13:35:17 - INFO - __main__ - Step 2039: {'lr': 0.0004999999186694897, 'samples': 391488, 'steps': 2038, 'loss/train': 3.886890172958374} 08/30/2021 13:35:17 - INFO - __main__ - Step 2040: {'lr': 0.0004999999143326137, 'samples': 391680, 'steps': 2039, 'loss/train': 3.7923433780670166} 08/30/2021 13:35:18 - INFO - __main__ - Step 2041: {'lr': 0.0004999999098830916, 'samples': 391872, 'steps': 2040, 'loss/train': 3.740668773651123} 08/30/2021 13:35:19 - INFO - __main__ - Step 2042: {'lr': 0.0004999999053209235, 'samples': 392064, 'steps': 2041, 'loss/train': 2.651597499847412} 08/30/2021 13:35:20 - INFO - __main__ - Step 2043: {'lr': 0.0004999999006461091, 'samples': 392256, 'steps': 2042, 'loss/train': 3.898331642150879} 08/30/2021 13:35:20 - INFO - __main__ - Step 2044: {'lr': 0.0004999998958586487, 'samples': 392448, 'steps': 2043, 'loss/train': 3.453770399093628} 08/30/2021 13:35:20 - INFO - __main__ - Step 2045: {'lr': 0.0004999998909585423, 'samples': 392640, 'steps': 2044, 'loss/train': 3.8533713817596436} 08/30/2021 13:35:21 - INFO - __main__ - Step 2046: {'lr': 0.0004999998859457896, 'samples': 392832, 'steps': 2045, 'loss/train': 3.980863571166992} 08/30/2021 13:35:23 - INFO - __main__ - Step 2047: {'lr': 0.0004999998808203909, 'samples': 393024, 'steps': 2046, 'loss/train': 4.354173183441162} 08/30/2021 13:35:23 - INFO - __main__ - Step 2048: {'lr': 0.0004999998755823462, 'samples': 393216, 'steps': 2047, 'loss/train': 4.712317943572998} 08/30/2021 13:35:24 - INFO - __main__ - Step 2049: {'lr': 0.0004999998702316553, 'samples': 393408, 'steps': 2048, 'loss/train': 3.9165966510772705} 08/30/2021 13:35:24 - INFO - __main__ - Step 2050: {'lr': 0.0004999998647683184, 'samples': 393600, 'steps': 2049, 'loss/train': 4.144590854644775} 08/30/2021 13:35:24 - INFO - __main__ - Step 2051: {'lr': 0.0004999998591923353, 'samples': 393792, 'steps': 2050, 'loss/train': 4.262177467346191} 08/30/2021 13:35:25 - INFO - __main__ - Step 2052: {'lr': 0.0004999998535037063, 'samples': 393984, 'steps': 2051, 'loss/train': 3.439192295074463} 08/30/2021 13:35:26 - INFO - __main__ - Step 2053: {'lr': 0.0004999998477024311, 'samples': 394176, 'steps': 2052, 'loss/train': 4.031076908111572} 08/30/2021 13:35:27 - INFO - __main__ - Step 2054: {'lr': 0.0004999998417885099, 'samples': 394368, 'steps': 2053, 'loss/train': 4.544736385345459} 08/30/2021 13:35:27 - INFO - __main__ - Step 2055: {'lr': 0.0004999998357619425, 'samples': 394560, 'steps': 2054, 'loss/train': 4.259439468383789} 08/30/2021 13:35:27 - INFO - __main__ - Step 2056: {'lr': 0.0004999998296227291, 'samples': 394752, 'steps': 2055, 'loss/train': 3.7828798294067383} 08/30/2021 13:35:28 - INFO - __main__ - Step 2057: {'lr': 0.0004999998233708697, 'samples': 394944, 'steps': 2056, 'loss/train': 3.885012626647949} 08/30/2021 13:35:29 - INFO - __main__ - Step 2058: {'lr': 0.0004999998170063642, 'samples': 395136, 'steps': 2057, 'loss/train': 4.150326251983643} 08/30/2021 13:35:30 - INFO - __main__ - Step 2059: {'lr': 0.0004999998105292126, 'samples': 395328, 'steps': 2058, 'loss/train': 3.841209888458252} 08/30/2021 13:35:30 - INFO - __main__ - Step 2060: {'lr': 0.000499999803939415, 'samples': 395520, 'steps': 2059, 'loss/train': 4.630417346954346} 08/30/2021 13:35:30 - INFO - __main__ - Step 2061: {'lr': 0.0004999997972369713, 'samples': 395712, 'steps': 2060, 'loss/train': 3.6309611797332764} 08/30/2021 13:35:31 - INFO - __main__ - Step 2062: {'lr': 0.0004999997904218816, 'samples': 395904, 'steps': 2061, 'loss/train': 4.3275017738342285} 08/30/2021 13:35:33 - INFO - __main__ - Step 2063: {'lr': 0.0004999997834941459, 'samples': 396096, 'steps': 2062, 'loss/train': 3.459217071533203} 08/30/2021 13:35:33 - INFO - __main__ - Step 2064: {'lr': 0.000499999776453764, 'samples': 396288, 'steps': 2063, 'loss/train': 3.7469112873077393} 08/30/2021 13:35:34 - INFO - __main__ - Step 2065: {'lr': 0.0004999997693007361, 'samples': 396480, 'steps': 2064, 'loss/train': 1.6411480903625488} 08/30/2021 13:35:34 - INFO - __main__ - Step 2066: {'lr': 0.0004999997620350622, 'samples': 396672, 'steps': 2065, 'loss/train': 4.02923583984375} 08/30/2021 13:35:34 - INFO - __main__ - Step 2067: {'lr': 0.0004999997546567423, 'samples': 396864, 'steps': 2066, 'loss/train': 4.513978481292725} 08/30/2021 13:35:35 - INFO - __main__ - Step 2068: {'lr': 0.0004999997471657763, 'samples': 397056, 'steps': 2067, 'loss/train': 4.028714656829834} 08/30/2021 13:35:36 - INFO - __main__ - Step 2069: {'lr': 0.0004999997395621642, 'samples': 397248, 'steps': 2068, 'loss/train': 5.7790045738220215} 08/30/2021 13:35:37 - INFO - __main__ - Step 2070: {'lr': 0.0004999997318459064, 'samples': 397440, 'steps': 2069, 'loss/train': 3.2854936122894287} 08/30/2021 13:35:37 - INFO - __main__ - Step 2071: {'lr': 0.0004999997240170023, 'samples': 397632, 'steps': 2070, 'loss/train': 4.750792503356934} 08/30/2021 13:35:38 - INFO - __main__ - Step 2072: {'lr': 0.0004999997160754522, 'samples': 397824, 'steps': 2071, 'loss/train': 3.8799290657043457} 08/30/2021 13:35:38 - INFO - __main__ - Step 2073: {'lr': 0.0004999997080212561, 'samples': 398016, 'steps': 2072, 'loss/train': 3.8270981311798096} 08/30/2021 13:35:39 - INFO - __main__ - Step 2074: {'lr': 0.000499999699854414, 'samples': 398208, 'steps': 2073, 'loss/train': 3.9468932151794434} 08/30/2021 13:35:40 - INFO - __main__ - Step 2075: {'lr': 0.0004999996915749259, 'samples': 398400, 'steps': 2074, 'loss/train': 4.303092956542969} 08/30/2021 13:35:40 - INFO - __main__ - Step 2076: {'lr': 0.0004999996831827918, 'samples': 398592, 'steps': 2075, 'loss/train': 4.116118431091309} 08/30/2021 13:35:40 - INFO - __main__ - Step 2077: {'lr': 0.0004999996746780117, 'samples': 398784, 'steps': 2076, 'loss/train': 3.8554420471191406} 08/30/2021 13:35:41 - INFO - __main__ - Step 2078: {'lr': 0.0004999996660605856, 'samples': 398976, 'steps': 2077, 'loss/train': 4.0006585121154785} 08/30/2021 13:35:42 - INFO - __main__ - Step 2079: {'lr': 0.0004999996573305135, 'samples': 399168, 'steps': 2078, 'loss/train': 4.150618076324463} 08/30/2021 13:35:43 - INFO - __main__ - Step 2080: {'lr': 0.0004999996484877955, 'samples': 399360, 'steps': 2079, 'loss/train': 3.6302833557128906} 08/30/2021 13:35:43 - INFO - __main__ - Step 2081: {'lr': 0.0004999996395324313, 'samples': 399552, 'steps': 2080, 'loss/train': 3.340209722518921} 08/30/2021 13:35:44 - INFO - __main__ - Step 2082: {'lr': 0.0004999996304644213, 'samples': 399744, 'steps': 2081, 'loss/train': 1.185246467590332} 08/30/2021 13:35:44 - INFO - __main__ - Step 2083: {'lr': 0.0004999996212837653, 'samples': 399936, 'steps': 2082, 'loss/train': 3.8154983520507812} 08/30/2021 13:35:44 - INFO - __main__ - Step 2084: {'lr': 0.0004999996119904633, 'samples': 400128, 'steps': 2083, 'loss/train': 3.679164409637451} 08/30/2021 13:35:46 - INFO - __main__ - Step 2085: {'lr': 0.0004999996025845154, 'samples': 400320, 'steps': 2084, 'loss/train': 3.6279003620147705} 08/30/2021 13:35:46 - INFO - __main__ - Step 2086: {'lr': 0.0004999995930659215, 'samples': 400512, 'steps': 2085, 'loss/train': 3.875730037689209} 08/30/2021 13:35:47 - INFO - __main__ - Step 2087: {'lr': 0.0004999995834346815, 'samples': 400704, 'steps': 2086, 'loss/train': 3.8178493976593018} 08/30/2021 13:35:47 - INFO - __main__ - Step 2088: {'lr': 0.0004999995736907957, 'samples': 400896, 'steps': 2087, 'loss/train': 2.4050605297088623} 08/30/2021 13:35:48 - INFO - __main__ - Step 2089: {'lr': 0.000499999563834264, 'samples': 401088, 'steps': 2088, 'loss/train': 4.120197772979736} 08/30/2021 13:35:49 - INFO - __main__ - Step 2090: {'lr': 0.0004999995538650862, 'samples': 401280, 'steps': 2089, 'loss/train': 3.6348252296447754} 08/30/2021 13:35:50 - INFO - __main__ - Step 2091: {'lr': 0.0004999995437832626, 'samples': 401472, 'steps': 2090, 'loss/train': 3.6068522930145264} 08/30/2021 13:35:50 - INFO - __main__ - Step 2092: {'lr': 0.0004999995335887929, 'samples': 401664, 'steps': 2091, 'loss/train': 3.4813265800476074} 08/30/2021 13:35:50 - INFO - __main__ - Step 2093: {'lr': 0.0004999995232816774, 'samples': 401856, 'steps': 2092, 'loss/train': 3.892913579940796} 08/30/2021 13:35:51 - INFO - __main__ - Step 2094: {'lr': 0.000499999512861916, 'samples': 402048, 'steps': 2093, 'loss/train': 6.413071632385254} 08/30/2021 13:35:51 - INFO - __main__ - Step 2095: {'lr': 0.0004999995023295086, 'samples': 402240, 'steps': 2094, 'loss/train': 3.990013599395752} 08/30/2021 13:35:52 - INFO - __main__ - Step 2096: {'lr': 0.0004999994916844552, 'samples': 402432, 'steps': 2095, 'loss/train': 4.004929065704346} 08/30/2021 13:35:53 - INFO - __main__ - Step 2097: {'lr': 0.0004999994809267561, 'samples': 402624, 'steps': 2096, 'loss/train': 3.6314752101898193} 08/30/2021 13:35:53 - INFO - __main__ - Step 2098: {'lr': 0.0004999994700564109, 'samples': 402816, 'steps': 2097, 'loss/train': 4.178173065185547} 08/30/2021 13:35:54 - INFO - __main__ - Step 2099: {'lr': 0.0004999994590734199, 'samples': 403008, 'steps': 2098, 'loss/train': 3.6031713485717773} 08/30/2021 13:35:54 - INFO - __main__ - Step 2100: {'lr': 0.000499999447977783, 'samples': 403200, 'steps': 2099, 'loss/train': 4.067807197570801} 08/30/2021 13:35:56 - INFO - __main__ - Step 2101: {'lr': 0.0004999994367695001, 'samples': 403392, 'steps': 2100, 'loss/train': 5.255605220794678} 08/30/2021 13:35:57 - INFO - __main__ - Step 2102: {'lr': 0.0004999994254485714, 'samples': 403584, 'steps': 2101, 'loss/train': 3.9827678203582764} 08/30/2021 13:35:57 - INFO - __main__ - Step 2103: {'lr': 0.0004999994140149969, 'samples': 403776, 'steps': 2102, 'loss/train': 3.6580848693847656} 08/30/2021 13:35:57 - INFO - __main__ - Step 2104: {'lr': 0.0004999994024687764, 'samples': 403968, 'steps': 2103, 'loss/train': 3.2820913791656494} 08/30/2021 13:35:58 - INFO - __main__ - Step 2105: {'lr': 0.00049999939080991, 'samples': 404160, 'steps': 2104, 'loss/train': 3.5947940349578857} 08/30/2021 13:36:00 - INFO - __main__ - Step 2106: {'lr': 0.0004999993790383978, 'samples': 404352, 'steps': 2105, 'loss/train': 3.8313283920288086} 08/30/2021 13:36:00 - INFO - __main__ - Step 2107: {'lr': 0.0004999993671542397, 'samples': 404544, 'steps': 2106, 'loss/train': 3.4209165573120117} 08/30/2021 13:36:00 - INFO - __main__ - Step 2108: {'lr': 0.0004999993551574358, 'samples': 404736, 'steps': 2107, 'loss/train': 2.9385299682617188} 08/30/2021 13:36:01 - INFO - __main__ - Step 2109: {'lr': 0.000499999343047986, 'samples': 404928, 'steps': 2108, 'loss/train': 3.8535799980163574} 08/30/2021 13:36:01 - INFO - __main__ - Step 2110: {'lr': 0.0004999993308258904, 'samples': 405120, 'steps': 2109, 'loss/train': 4.167038440704346} 08/30/2021 13:36:03 - INFO - __main__ - Step 2111: {'lr': 0.0004999993184911489, 'samples': 405312, 'steps': 2110, 'loss/train': 1.7652651071548462} 08/30/2021 13:36:03 - INFO - __main__ - Step 2112: {'lr': 0.0004999993060437616, 'samples': 405504, 'steps': 2111, 'loss/train': 4.371798992156982} 08/30/2021 13:36:03 - INFO - __main__ - Step 2113: {'lr': 0.0004999992934837284, 'samples': 405696, 'steps': 2112, 'loss/train': 3.9404070377349854} 08/30/2021 13:36:04 - INFO - __main__ - Step 2114: {'lr': 0.0004999992808110495, 'samples': 405888, 'steps': 2113, 'loss/train': 3.7768027782440186} 08/30/2021 13:36:04 - INFO - __main__ - Step 2115: {'lr': 0.0004999992680257247, 'samples': 406080, 'steps': 2114, 'loss/train': 3.13139271736145} 08/30/2021 13:36:06 - INFO - __main__ - Step 2116: {'lr': 0.0004999992551277541, 'samples': 406272, 'steps': 2115, 'loss/train': 3.9997286796569824} 08/30/2021 13:36:06 - INFO - __main__ - Step 2117: {'lr': 0.0004999992421171377, 'samples': 406464, 'steps': 2116, 'loss/train': 4.288055896759033} 08/30/2021 13:36:07 - INFO - __main__ - Step 2118: {'lr': 0.0004999992289938755, 'samples': 406656, 'steps': 2117, 'loss/train': 2.2618613243103027} 08/30/2021 13:36:07 - INFO - __main__ - Step 2119: {'lr': 0.0004999992157579676, 'samples': 406848, 'steps': 2118, 'loss/train': 3.53808331489563} 08/30/2021 13:36:07 - INFO - __main__ - Step 2120: {'lr': 0.0004999992024094138, 'samples': 407040, 'steps': 2119, 'loss/train': 1.2991235256195068} 08/30/2021 13:36:08 - INFO - __main__ - Step 2121: {'lr': 0.0004999991889482142, 'samples': 407232, 'steps': 2120, 'loss/train': 3.9068098068237305} 08/30/2021 13:36:08 - INFO - __main__ - Step 2122: {'lr': 0.0004999991753743689, 'samples': 407424, 'steps': 2121, 'loss/train': 4.309406757354736} 08/30/2021 13:36:10 - INFO - __main__ - Step 2123: {'lr': 0.0004999991616878777, 'samples': 407616, 'steps': 2122, 'loss/train': 5.465785503387451} 08/30/2021 13:36:10 - INFO - __main__ - Step 2124: {'lr': 0.0004999991478887409, 'samples': 407808, 'steps': 2123, 'loss/train': 3.558007001876831} 08/30/2021 13:36:11 - INFO - __main__ - Step 2125: {'lr': 0.0004999991339769582, 'samples': 408000, 'steps': 2124, 'loss/train': 3.6818957328796387} 08/30/2021 13:36:11 - INFO - __main__ - Step 2126: {'lr': 0.0004999991199525299, 'samples': 408192, 'steps': 2125, 'loss/train': 2.7842469215393066} 08/30/2021 13:36:11 - INFO - __main__ - Step 2127: {'lr': 0.0004999991058154557, 'samples': 408384, 'steps': 2126, 'loss/train': 3.7680232524871826} 08/30/2021 13:36:13 - INFO - __main__ - Step 2128: {'lr': 0.0004999990915657359, 'samples': 408576, 'steps': 2127, 'loss/train': 3.632894515991211} 08/30/2021 13:36:13 - INFO - __main__ - Step 2129: {'lr': 0.0004999990772033702, 'samples': 408768, 'steps': 2128, 'loss/train': 3.518711805343628} 08/30/2021 13:36:14 - INFO - __main__ - Step 2130: {'lr': 0.000499999062728359, 'samples': 408960, 'steps': 2129, 'loss/train': 3.6407299041748047} 08/30/2021 13:36:14 - INFO - __main__ - Step 2131: {'lr': 0.0004999990481407018, 'samples': 409152, 'steps': 2130, 'loss/train': 4.092563629150391} 08/30/2021 13:36:14 - INFO - __main__ - Step 2132: {'lr': 0.0004999990334403991, 'samples': 409344, 'steps': 2131, 'loss/train': 3.513838052749634} 08/30/2021 13:36:16 - INFO - __main__ - Step 2133: {'lr': 0.0004999990186274506, 'samples': 409536, 'steps': 2132, 'loss/train': 3.990471124649048} 08/30/2021 13:36:17 - INFO - __main__ - Step 2134: {'lr': 0.0004999990037018564, 'samples': 409728, 'steps': 2133, 'loss/train': 4.022684574127197} 08/30/2021 13:36:17 - INFO - __main__ - Step 2135: {'lr': 0.0004999989886636166, 'samples': 409920, 'steps': 2134, 'loss/train': 3.972376823425293} 08/30/2021 13:36:17 - INFO - __main__ - Step 2136: {'lr': 0.000499998973512731, 'samples': 410112, 'steps': 2135, 'loss/train': 4.383425235748291} 08/30/2021 13:36:18 - INFO - __main__ - Step 2137: {'lr': 0.0004999989582491998, 'samples': 410304, 'steps': 2136, 'loss/train': 0.9991979002952576} 08/30/2021 13:36:19 - INFO - __main__ - Step 2138: {'lr': 0.0004999989428730229, 'samples': 410496, 'steps': 2137, 'loss/train': 3.6455819606781006} 08/30/2021 13:36:19 - INFO - __main__ - Step 2139: {'lr': 0.0004999989273842003, 'samples': 410688, 'steps': 2138, 'loss/train': 3.622770071029663} 08/30/2021 13:36:20 - INFO - __main__ - Step 2140: {'lr': 0.0004999989117827321, 'samples': 410880, 'steps': 2139, 'loss/train': 4.197285175323486} 08/30/2021 13:36:20 - INFO - __main__ - Step 2141: {'lr': 0.0004999988960686182, 'samples': 411072, 'steps': 2140, 'loss/train': 3.6964786052703857} 08/30/2021 13:36:21 - INFO - __main__ - Step 2142: {'lr': 0.0004999988802418587, 'samples': 411264, 'steps': 2141, 'loss/train': 3.747947931289673} 08/30/2021 13:36:22 - INFO - __main__ - Step 2143: {'lr': 0.0004999988643024536, 'samples': 411456, 'steps': 2142, 'loss/train': 4.155553340911865} 08/30/2021 13:36:22 - INFO - __main__ - Step 2144: {'lr': 0.0004999988482504027, 'samples': 411648, 'steps': 2143, 'loss/train': 3.367722988128662} 08/30/2021 13:36:23 - INFO - __main__ - Step 2145: {'lr': 0.0004999988320857063, 'samples': 411840, 'steps': 2144, 'loss/train': 3.669928550720215} 08/30/2021 13:36:23 - INFO - __main__ - Step 2146: {'lr': 0.0004999988158083643, 'samples': 412032, 'steps': 2145, 'loss/train': 4.159835338592529} 08/30/2021 13:36:24 - INFO - __main__ - Step 2147: {'lr': 0.0004999987994183766, 'samples': 412224, 'steps': 2146, 'loss/train': 3.7286808490753174} 08/30/2021 13:36:25 - INFO - __main__ - Step 2148: {'lr': 0.0004999987829157434, 'samples': 412416, 'steps': 2147, 'loss/train': 3.789923906326294} 08/30/2021 13:36:26 - INFO - __main__ - Step 2149: {'lr': 0.0004999987663004646, 'samples': 412608, 'steps': 2148, 'loss/train': 3.821627616882324} 08/30/2021 13:36:26 - INFO - __main__ - Step 2150: {'lr': 0.0004999987495725401, 'samples': 412800, 'steps': 2149, 'loss/train': 4.026470184326172} 08/30/2021 13:36:27 - INFO - __main__ - Step 2151: {'lr': 0.0004999987327319701, 'samples': 412992, 'steps': 2150, 'loss/train': 3.941927433013916} 08/30/2021 13:36:27 - INFO - __main__ - Step 2152: {'lr': 0.0004999987157787546, 'samples': 413184, 'steps': 2151, 'loss/train': 3.9863195419311523} 08/30/2021 13:36:27 - INFO - __main__ - Step 2153: {'lr': 0.0004999986987128934, 'samples': 413376, 'steps': 2152, 'loss/train': 2.8138444423675537} 08/30/2021 13:36:28 - INFO - __main__ - Step 2154: {'lr': 0.0004999986815343867, 'samples': 413568, 'steps': 2153, 'loss/train': 2.8728902339935303} 08/30/2021 13:36:29 - INFO - __main__ - Step 2155: {'lr': 0.0004999986642432345, 'samples': 413760, 'steps': 2154, 'loss/train': 4.75545072555542} 08/30/2021 13:36:30 - INFO - __main__ - Step 2156: {'lr': 0.0004999986468394367, 'samples': 413952, 'steps': 2155, 'loss/train': 3.888580560684204} 08/30/2021 13:36:30 - INFO - __main__ - Step 2157: {'lr': 0.0004999986293229934, 'samples': 414144, 'steps': 2156, 'loss/train': 3.8104896545410156} 08/30/2021 13:36:30 - INFO - __main__ - Step 2158: {'lr': 0.0004999986116939045, 'samples': 414336, 'steps': 2157, 'loss/train': 3.6036465167999268} 08/30/2021 13:36:31 - INFO - __main__ - Step 2159: {'lr': 0.0004999985939521702, 'samples': 414528, 'steps': 2158, 'loss/train': 4.06483268737793} 08/30/2021 13:36:33 - INFO - __main__ - Step 2160: {'lr': 0.0004999985760977903, 'samples': 414720, 'steps': 2159, 'loss/train': 3.406566858291626} 08/30/2021 13:36:33 - INFO - __main__ - Step 2161: {'lr': 0.000499998558130765, 'samples': 414912, 'steps': 2160, 'loss/train': 3.4594547748565674} 08/30/2021 13:36:34 - INFO - __main__ - Step 2162: {'lr': 0.0004999985400510941, 'samples': 415104, 'steps': 2161, 'loss/train': 4.1263933181762695} 08/30/2021 13:36:34 - INFO - __main__ - Step 2163: {'lr': 0.0004999985218587777, 'samples': 415296, 'steps': 2162, 'loss/train': 3.4256396293640137} 08/30/2021 13:36:34 - INFO - __main__ - Step 2164: {'lr': 0.0004999985035538159, 'samples': 415488, 'steps': 2163, 'loss/train': 3.1839096546173096} 08/30/2021 13:36:36 - INFO - __main__ - Step 2165: {'lr': 0.0004999984851362086, 'samples': 415680, 'steps': 2164, 'loss/train': 3.763256311416626} 08/30/2021 13:36:36 - INFO - __main__ - Step 2166: {'lr': 0.0004999984666059559, 'samples': 415872, 'steps': 2165, 'loss/train': 4.361536979675293} 08/30/2021 13:36:37 - INFO - __main__ - Step 2167: {'lr': 0.0004999984479630577, 'samples': 416064, 'steps': 2166, 'loss/train': 3.8201444149017334} 08/30/2021 13:36:37 - INFO - __main__ - Step 2168: {'lr': 0.000499998429207514, 'samples': 416256, 'steps': 2167, 'loss/train': 4.29213809967041} 08/30/2021 13:36:37 - INFO - __main__ - Step 2169: {'lr': 0.000499998410339325, 'samples': 416448, 'steps': 2168, 'loss/train': 3.7384464740753174} 08/30/2021 13:36:38 - INFO - __main__ - Step 2170: {'lr': 0.0004999983913584904, 'samples': 416640, 'steps': 2169, 'loss/train': 3.6140146255493164} 08/30/2021 13:36:39 - INFO - __main__ - Step 2171: {'lr': 0.0004999983722650106, 'samples': 416832, 'steps': 2170, 'loss/train': 3.2986245155334473} 08/30/2021 13:36:40 - INFO - __main__ - Step 2172: {'lr': 0.0004999983530588853, 'samples': 417024, 'steps': 2171, 'loss/train': 3.7747888565063477} 08/30/2021 13:36:40 - INFO - __main__ - Step 2173: {'lr': 0.0004999983337401145, 'samples': 417216, 'steps': 2172, 'loss/train': 4.175738334655762} 08/30/2021 13:36:40 - INFO - __main__ - Step 2174: {'lr': 0.0004999983143086984, 'samples': 417408, 'steps': 2173, 'loss/train': 3.6769347190856934} 08/30/2021 13:36:41 - INFO - __main__ - Step 2175: {'lr': 0.0004999982947646368, 'samples': 417600, 'steps': 2174, 'loss/train': 3.5578510761260986} 08/30/2021 13:36:42 - INFO - __main__ - Step 2176: {'lr': 0.00049999827510793, 'samples': 417792, 'steps': 2175, 'loss/train': 3.85313081741333} 08/30/2021 13:36:43 - INFO - __main__ - Step 2177: {'lr': 0.0004999982553385778, 'samples': 417984, 'steps': 2176, 'loss/train': 4.286514759063721} 08/30/2021 13:36:43 - INFO - __main__ - Step 2178: {'lr': 0.0004999982354565802, 'samples': 418176, 'steps': 2177, 'loss/train': 3.313585042953491} 08/30/2021 13:36:43 - INFO - __main__ - Step 2179: {'lr': 0.0004999982154619372, 'samples': 418368, 'steps': 2178, 'loss/train': 3.698235273361206} 08/30/2021 13:36:44 - INFO - __main__ - Step 2180: {'lr': 0.000499998195354649, 'samples': 418560, 'steps': 2179, 'loss/train': 4.317075729370117} 08/30/2021 13:36:45 - INFO - __main__ - Step 2181: {'lr': 0.0004999981751347153, 'samples': 418752, 'steps': 2180, 'loss/train': 3.5049121379852295} 08/30/2021 13:36:46 - INFO - __main__ - Step 2182: {'lr': 0.0004999981548021364, 'samples': 418944, 'steps': 2181, 'loss/train': 4.226571559906006} 08/30/2021 13:36:46 - INFO - __main__ - Step 2183: {'lr': 0.0004999981343569122, 'samples': 419136, 'steps': 2182, 'loss/train': 3.4870505332946777} 08/30/2021 13:36:46 - INFO - __main__ - Step 2184: {'lr': 0.0004999981137990425, 'samples': 419328, 'steps': 2183, 'loss/train': 4.201118469238281} 08/30/2021 13:36:47 - INFO - __main__ - Step 2185: {'lr': 0.0004999980931285278, 'samples': 419520, 'steps': 2184, 'loss/train': 3.011713743209839} 08/30/2021 13:36:48 - INFO - __main__ - Step 2186: {'lr': 0.0004999980723453676, 'samples': 419712, 'steps': 2185, 'loss/train': 4.225376605987549} 08/30/2021 13:36:49 - INFO - __main__ - Step 2187: {'lr': 0.0004999980514495623, 'samples': 419904, 'steps': 2186, 'loss/train': 3.735133647918701} 08/30/2021 13:36:49 - INFO - __main__ - Step 2188: {'lr': 0.0004999980304411116, 'samples': 420096, 'steps': 2187, 'loss/train': 4.268670082092285} 08/30/2021 13:36:49 - INFO - __main__ - Step 2189: {'lr': 0.0004999980093200157, 'samples': 420288, 'steps': 2188, 'loss/train': 4.963278293609619} 08/30/2021 13:36:50 - INFO - __main__ - Step 2190: {'lr': 0.0004999979880862745, 'samples': 420480, 'steps': 2189, 'loss/train': 3.5750648975372314} 08/30/2021 13:36:51 - INFO - __main__ - Step 2191: {'lr': 0.0004999979667398882, 'samples': 420672, 'steps': 2190, 'loss/train': 2.8247759342193604} 08/30/2021 13:36:51 - INFO - __main__ - Step 2192: {'lr': 0.0004999979452808565, 'samples': 420864, 'steps': 2191, 'loss/train': 4.099137783050537} 08/30/2021 13:36:52 - INFO - __main__ - Step 2193: {'lr': 0.0004999979237091796, 'samples': 421056, 'steps': 2192, 'loss/train': 3.661343812942505} 08/30/2021 13:36:52 - INFO - __main__ - Step 2194: {'lr': 0.0004999979020248577, 'samples': 421248, 'steps': 2193, 'loss/train': 4.581142902374268} 08/30/2021 13:36:53 - INFO - __main__ - Step 2195: {'lr': 0.0004999978802278904, 'samples': 421440, 'steps': 2194, 'loss/train': 4.2670440673828125} 08/30/2021 13:36:53 - INFO - __main__ - Step 2196: {'lr': 0.000499997858318278, 'samples': 421632, 'steps': 2195, 'loss/train': 4.95889949798584} 08/30/2021 13:36:54 - INFO - __main__ - Step 2197: {'lr': 0.0004999978362960204, 'samples': 421824, 'steps': 2196, 'loss/train': 4.856159687042236} 08/30/2021 13:36:55 - INFO - __main__ - Step 2198: {'lr': 0.0004999978141611176, 'samples': 422016, 'steps': 2197, 'loss/train': 3.22304630279541} 08/30/2021 13:36:55 - INFO - __main__ - Step 2199: {'lr': 0.0004999977919135696, 'samples': 422208, 'steps': 2198, 'loss/train': 3.554565668106079} 08/30/2021 13:36:56 - INFO - __main__ - Step 2200: {'lr': 0.0004999977695533766, 'samples': 422400, 'steps': 2199, 'loss/train': 3.392871618270874} 08/30/2021 13:36:56 - INFO - __main__ - Step 2201: {'lr': 0.0004999977470805383, 'samples': 422592, 'steps': 2200, 'loss/train': 4.376364231109619} 08/30/2021 13:36:57 - INFO - __main__ - Step 2202: {'lr': 0.0004999977244950551, 'samples': 422784, 'steps': 2201, 'loss/train': 3.8810112476348877} 08/30/2021 13:36:58 - INFO - __main__ - Step 2203: {'lr': 0.0004999977017969266, 'samples': 422976, 'steps': 2202, 'loss/train': 3.221945285797119} 08/30/2021 13:36:58 - INFO - __main__ - Step 2204: {'lr': 0.000499997678986153, 'samples': 423168, 'steps': 2203, 'loss/train': 4.205539703369141} 08/30/2021 13:36:59 - INFO - __main__ - Step 2205: {'lr': 0.0004999976560627344, 'samples': 423360, 'steps': 2204, 'loss/train': 3.4441351890563965} 08/30/2021 13:36:59 - INFO - __main__ - Step 2206: {'lr': 0.0004999976330266707, 'samples': 423552, 'steps': 2205, 'loss/train': 3.697157144546509} 08/30/2021 13:37:00 - INFO - __main__ - Step 2207: {'lr': 0.0004999976098779618, 'samples': 423744, 'steps': 2206, 'loss/train': 3.6632027626037598} 08/30/2021 13:37:01 - INFO - __main__ - Step 2208: {'lr': 0.0004999975866166079, 'samples': 423936, 'steps': 2207, 'loss/train': 5.021728038787842} 08/30/2021 13:37:01 - INFO - __main__ - Step 2209: {'lr': 0.000499997563242609, 'samples': 424128, 'steps': 2208, 'loss/train': 3.6572656631469727} 08/30/2021 13:37:02 - INFO - __main__ - Step 2210: {'lr': 0.0004999975397559649, 'samples': 424320, 'steps': 2209, 'loss/train': 3.658616781234741} 08/30/2021 13:37:02 - INFO - __main__ - Step 2211: {'lr': 0.000499997516156676, 'samples': 424512, 'steps': 2210, 'loss/train': 2.9364333152770996} 08/30/2021 13:37:04 - INFO - __main__ - Step 2212: {'lr': 0.000499997492444742, 'samples': 424704, 'steps': 2211, 'loss/train': 3.404667377471924} 08/30/2021 13:37:04 - INFO - __main__ - Step 2213: {'lr': 0.0004999974686201629, 'samples': 424896, 'steps': 2212, 'loss/train': 3.665926933288574} 08/30/2021 13:37:05 - INFO - __main__ - Step 2214: {'lr': 0.0004999974446829389, 'samples': 425088, 'steps': 2213, 'loss/train': 2.8251471519470215} 08/30/2021 13:37:05 - INFO - __main__ - Step 2215: {'lr': 0.0004999974206330698, 'samples': 425280, 'steps': 2214, 'loss/train': 3.0024397373199463} 08/30/2021 13:37:05 - INFO - __main__ - Step 2216: {'lr': 0.0004999973964705558, 'samples': 425472, 'steps': 2215, 'loss/train': 3.3037800788879395} 08/30/2021 13:37:07 - INFO - __main__ - Step 2217: {'lr': 0.0004999973721953968, 'samples': 425664, 'steps': 2216, 'loss/train': 3.28297758102417} 08/30/2021 13:37:08 - INFO - __main__ - Step 2218: {'lr': 0.0004999973478075928, 'samples': 425856, 'steps': 2217, 'loss/train': 3.300427198410034} 08/30/2021 13:37:08 - INFO - __main__ - Step 2219: {'lr': 0.0004999973233071438, 'samples': 426048, 'steps': 2218, 'loss/train': 4.051426887512207} 08/30/2021 13:37:08 - INFO - __main__ - Step 2220: {'lr': 0.00049999729869405, 'samples': 426240, 'steps': 2219, 'loss/train': 5.035614490509033} 08/30/2021 13:37:09 - INFO - __main__ - Step 2221: {'lr': 0.0004999972739683113, 'samples': 426432, 'steps': 2220, 'loss/train': 3.5028154850006104} 08/30/2021 13:37:09 - INFO - __main__ - Step 2222: {'lr': 0.0004999972491299276, 'samples': 426624, 'steps': 2221, 'loss/train': 4.06950569152832} 08/30/2021 13:37:11 - INFO - __main__ - Step 2223: {'lr': 0.000499997224178899, 'samples': 426816, 'steps': 2222, 'loss/train': 4.2269134521484375} 08/30/2021 13:37:11 - INFO - __main__ - Step 2224: {'lr': 0.0004999971991152256, 'samples': 427008, 'steps': 2223, 'loss/train': 3.994997024536133} 08/30/2021 13:37:11 - INFO - __main__ - Step 2225: {'lr': 0.0004999971739389072, 'samples': 427200, 'steps': 2224, 'loss/train': 3.972487211227417} 08/30/2021 13:37:12 - INFO - __main__ - Step 2226: {'lr': 0.000499997148649944, 'samples': 427392, 'steps': 2225, 'loss/train': 2.8659262657165527} 08/30/2021 13:37:12 - INFO - __main__ - Step 2227: {'lr': 0.0004999971232483359, 'samples': 427584, 'steps': 2226, 'loss/train': 3.4539358615875244} 08/30/2021 13:37:14 - INFO - __main__ - Step 2228: {'lr': 0.0004999970977340829, 'samples': 427776, 'steps': 2227, 'loss/train': 3.7257273197174072} 08/30/2021 13:37:14 - INFO - __main__ - Step 2229: {'lr': 0.0004999970721071852, 'samples': 427968, 'steps': 2228, 'loss/train': 3.375279426574707} 08/30/2021 13:37:14 - INFO - __main__ - Step 2230: {'lr': 0.0004999970463676427, 'samples': 428160, 'steps': 2229, 'loss/train': 3.407538652420044} 08/30/2021 13:37:15 - INFO - __main__ - Step 2231: {'lr': 0.0004999970205154553, 'samples': 428352, 'steps': 2230, 'loss/train': 1.6758882999420166} 08/30/2021 13:37:15 - INFO - __main__ - Step 2232: {'lr': 0.000499996994550623, 'samples': 428544, 'steps': 2231, 'loss/train': 3.425678253173828} 08/30/2021 13:37:17 - INFO - __main__ - Step 2233: {'lr': 0.000499996968473146, 'samples': 428736, 'steps': 2232, 'loss/train': 3.820082187652588} 08/30/2021 13:37:17 - INFO - __main__ - Step 2234: {'lr': 0.0004999969422830242, 'samples': 428928, 'steps': 2233, 'loss/train': 3.4000606536865234} 08/30/2021 13:37:17 - INFO - __main__ - Step 2235: {'lr': 0.0004999969159802577, 'samples': 429120, 'steps': 2234, 'loss/train': 4.048572540283203} 08/30/2021 13:37:18 - INFO - __main__ - Step 2236: {'lr': 0.0004999968895648464, 'samples': 429312, 'steps': 2235, 'loss/train': 3.476292133331299} 08/30/2021 13:37:18 - INFO - __main__ - Step 2237: {'lr': 0.0004999968630367905, 'samples': 429504, 'steps': 2236, 'loss/train': 1.0507943630218506} 08/30/2021 13:37:20 - INFO - __main__ - Step 2238: {'lr': 0.0004999968363960897, 'samples': 429696, 'steps': 2237, 'loss/train': 3.1623053550720215} 08/30/2021 13:37:20 - INFO - __main__ - Step 2239: {'lr': 0.0004999968096427443, 'samples': 429888, 'steps': 2238, 'loss/train': 1.3669394254684448} 08/30/2021 13:37:21 - INFO - __main__ - Step 2240: {'lr': 0.0004999967827767541, 'samples': 430080, 'steps': 2239, 'loss/train': 3.8772776126861572} 08/30/2021 13:37:21 - INFO - __main__ - Step 2241: {'lr': 0.0004999967557981192, 'samples': 430272, 'steps': 2240, 'loss/train': 3.595731019973755} 08/30/2021 13:37:21 - INFO - __main__ - Step 2242: {'lr': 0.0004999967287068396, 'samples': 430464, 'steps': 2241, 'loss/train': 3.1968882083892822} 08/30/2021 13:37:23 - INFO - __main__ - Step 2243: {'lr': 0.0004999967015029155, 'samples': 430656, 'steps': 2242, 'loss/train': 3.886357069015503} 08/30/2021 13:37:23 - INFO - __main__ - Step 2244: {'lr': 0.0004999966741863467, 'samples': 430848, 'steps': 2243, 'loss/train': 3.6338374614715576} 08/30/2021 13:37:24 - INFO - __main__ - Step 2245: {'lr': 0.000499996646757133, 'samples': 431040, 'steps': 2244, 'loss/train': 0.8551651835441589} 08/30/2021 13:37:24 - INFO - __main__ - Step 2246: {'lr': 0.0004999966192152749, 'samples': 431232, 'steps': 2245, 'loss/train': 3.852029323577881} 08/30/2021 13:37:24 - INFO - __main__ - Step 2247: {'lr': 0.0004999965915607722, 'samples': 431424, 'steps': 2246, 'loss/train': 3.4796693325042725} 08/30/2021 13:37:25 - INFO - __main__ - Step 2248: {'lr': 0.0004999965637936248, 'samples': 431616, 'steps': 2247, 'loss/train': 3.049506425857544} 08/30/2021 13:37:26 - INFO - __main__ - Step 2249: {'lr': 0.0004999965359138329, 'samples': 431808, 'steps': 2248, 'loss/train': 3.1012051105499268} 08/30/2021 13:37:27 - INFO - __main__ - Step 2250: {'lr': 0.0004999965079213964, 'samples': 432000, 'steps': 2249, 'loss/train': 3.93786358833313} 08/30/2021 13:37:27 - INFO - __main__ - Step 2251: {'lr': 0.0004999964798163152, 'samples': 432192, 'steps': 2250, 'loss/train': 3.234760284423828} 08/30/2021 13:37:28 - INFO - __main__ - Step 2252: {'lr': 0.0004999964515985896, 'samples': 432384, 'steps': 2251, 'loss/train': 2.9302399158477783} 08/30/2021 13:37:28 - INFO - __main__ - Step 2253: {'lr': 0.0004999964232682194, 'samples': 432576, 'steps': 2252, 'loss/train': 4.453218460083008} 08/30/2021 13:37:29 - INFO - __main__ - Step 2254: {'lr': 0.0004999963948252046, 'samples': 432768, 'steps': 2253, 'loss/train': 3.4095213413238525} 08/30/2021 13:37:30 - INFO - __main__ - Step 2255: {'lr': 0.0004999963662695453, 'samples': 432960, 'steps': 2254, 'loss/train': 3.3248941898345947} 08/30/2021 13:37:30 - INFO - __main__ - Step 2256: {'lr': 0.0004999963376012416, 'samples': 433152, 'steps': 2255, 'loss/train': 4.129458427429199} 08/30/2021 13:37:31 - INFO - __main__ - Step 2257: {'lr': 0.0004999963088202934, 'samples': 433344, 'steps': 2256, 'loss/train': 4.100364685058594} 08/30/2021 13:37:31 - INFO - __main__ - Step 2258: {'lr': 0.0004999962799267006, 'samples': 433536, 'steps': 2257, 'loss/train': 3.511345148086548} 08/30/2021 13:37:32 - INFO - __main__ - Step 2259: {'lr': 0.0004999962509204634, 'samples': 433728, 'steps': 2258, 'loss/train': 3.9459218978881836} 08/30/2021 13:37:33 - INFO - __main__ - Step 2260: {'lr': 0.0004999962218015818, 'samples': 433920, 'steps': 2259, 'loss/train': 3.9202263355255127} 08/30/2021 13:37:33 - INFO - __main__ - Step 2261: {'lr': 0.0004999961925700557, 'samples': 434112, 'steps': 2260, 'loss/train': 3.4376957416534424} 08/30/2021 13:37:34 - INFO - __main__ - Step 2262: {'lr': 0.0004999961632258851, 'samples': 434304, 'steps': 2261, 'loss/train': 3.3409574031829834} 08/30/2021 13:37:34 - INFO - __main__ - Step 2263: {'lr': 0.0004999961337690703, 'samples': 434496, 'steps': 2262, 'loss/train': 2.983520269393921} 08/30/2021 13:37:36 - INFO - __main__ - Step 2264: {'lr': 0.0004999961041996109, 'samples': 434688, 'steps': 2263, 'loss/train': 3.066105842590332} 08/30/2021 13:37:36 - INFO - __main__ - Step 2265: {'lr': 0.0004999960745175071, 'samples': 434880, 'steps': 2264, 'loss/train': 1.4745205640792847} 08/30/2021 13:37:37 - INFO - __main__ - Step 2266: {'lr': 0.0004999960447227591, 'samples': 435072, 'steps': 2265, 'loss/train': 4.289106845855713} 08/30/2021 13:37:37 - INFO - __main__ - Step 2267: {'lr': 0.0004999960148153667, 'samples': 435264, 'steps': 2266, 'loss/train': 3.591769218444824} 08/30/2021 13:37:37 - INFO - __main__ - Step 2268: {'lr': 0.0004999959847953299, 'samples': 435456, 'steps': 2267, 'loss/train': 3.655301094055176} 08/30/2021 13:37:39 - INFO - __main__ - Step 2269: {'lr': 0.0004999959546626487, 'samples': 435648, 'steps': 2268, 'loss/train': 4.203343391418457} 08/30/2021 13:37:39 - INFO - __main__ - Step 2270: {'lr': 0.0004999959244173232, 'samples': 435840, 'steps': 2269, 'loss/train': 3.0128376483917236} 08/30/2021 13:37:40 - INFO - __main__ - Step 2271: {'lr': 0.0004999958940593535, 'samples': 436032, 'steps': 2270, 'loss/train': 3.4220640659332275} 08/30/2021 13:37:40 - INFO - __main__ - Step 2272: {'lr': 0.0004999958635887394, 'samples': 436224, 'steps': 2271, 'loss/train': 3.169811725616455} 08/30/2021 13:37:40 - INFO - __main__ - Step 2273: {'lr': 0.0004999958330054811, 'samples': 436416, 'steps': 2272, 'loss/train': 3.8526008129119873} 08/30/2021 13:37:42 - INFO - __main__ - Step 2274: {'lr': 0.0004999958023095785, 'samples': 436608, 'steps': 2273, 'loss/train': 3.528167486190796} 08/30/2021 13:37:42 - INFO - __main__ - Step 2275: {'lr': 0.0004999957715010317, 'samples': 436800, 'steps': 2274, 'loss/train': 3.7438666820526123} 08/30/2021 13:37:43 - INFO - __main__ - Step 2276: {'lr': 0.0004999957405798405, 'samples': 436992, 'steps': 2275, 'loss/train': 3.869717836380005} 08/30/2021 13:37:43 - INFO - __main__ - Step 2277: {'lr': 0.0004999957095460052, 'samples': 437184, 'steps': 2276, 'loss/train': 3.9356942176818848} 08/30/2021 13:37:44 - INFO - __main__ - Step 2278: {'lr': 0.0004999956783995257, 'samples': 437376, 'steps': 2277, 'loss/train': 3.73154878616333} 08/30/2021 13:37:44 - INFO - __main__ - Step 2279: {'lr': 0.0004999956471404021, 'samples': 437568, 'steps': 2278, 'loss/train': 1.3698467016220093} 08/30/2021 13:37:45 - INFO - __main__ - Step 2280: {'lr': 0.0004999956157686341, 'samples': 437760, 'steps': 2279, 'loss/train': 4.439995765686035} 08/30/2021 13:37:46 - INFO - __main__ - Step 2281: {'lr': 0.0004999955842842222, 'samples': 437952, 'steps': 2280, 'loss/train': 2.8386447429656982} 08/30/2021 13:37:46 - INFO - __main__ - Step 2282: {'lr': 0.0004999955526871659, 'samples': 438144, 'steps': 2281, 'loss/train': 3.9862217903137207} 08/30/2021 13:37:46 - INFO - __main__ - Step 2283: {'lr': 0.0004999955209774656, 'samples': 438336, 'steps': 2282, 'loss/train': 3.8530850410461426} 08/30/2021 13:37:47 - INFO - __main__ - Step 2284: {'lr': 0.0004999954891551211, 'samples': 438528, 'steps': 2283, 'loss/train': 3.8454504013061523} 08/30/2021 13:37:48 - INFO - __main__ - Step 2285: {'lr': 0.0004999954572201326, 'samples': 438720, 'steps': 2284, 'loss/train': 3.486356019973755} 08/30/2021 13:37:49 - INFO - __main__ - Step 2286: {'lr': 0.0004999954251724999, 'samples': 438912, 'steps': 2285, 'loss/train': 3.396296262741089} 08/30/2021 13:37:49 - INFO - __main__ - Step 2287: {'lr': 0.0004999953930122231, 'samples': 439104, 'steps': 2286, 'loss/train': 4.753914833068848} 08/30/2021 13:37:50 - INFO - __main__ - Step 2288: {'lr': 0.0004999953607393023, 'samples': 439296, 'steps': 2287, 'loss/train': 3.2592363357543945} 08/30/2021 13:37:50 - INFO - __main__ - Step 2289: {'lr': 0.0004999953283537374, 'samples': 439488, 'steps': 2288, 'loss/train': 3.8208231925964355} 08/30/2021 13:37:51 - INFO - __main__ - Step 2290: {'lr': 0.0004999952958555285, 'samples': 439680, 'steps': 2289, 'loss/train': 0.9816742539405823} 08/30/2021 13:37:52 - INFO - __main__ - Step 2291: {'lr': 0.0004999952632446756, 'samples': 439872, 'steps': 2290, 'loss/train': 3.3279073238372803} 08/30/2021 13:37:52 - INFO - __main__ - Step 2292: {'lr': 0.0004999952305211786, 'samples': 440064, 'steps': 2291, 'loss/train': 4.148941993713379} 08/30/2021 13:37:53 - INFO - __main__ - Step 2293: {'lr': 0.0004999951976850377, 'samples': 440256, 'steps': 2292, 'loss/train': 3.7233402729034424} 08/30/2021 13:37:53 - INFO - __main__ - Step 2294: {'lr': 0.0004999951647362527, 'samples': 440448, 'steps': 2293, 'loss/train': 4.325737953186035} 08/30/2021 13:37:54 - INFO - __main__ - Step 2295: {'lr': 0.0004999951316748239, 'samples': 440640, 'steps': 2294, 'loss/train': 3.879056215286255} 08/30/2021 13:37:55 - INFO - __main__ - Step 2296: {'lr': 0.0004999950985007511, 'samples': 440832, 'steps': 2295, 'loss/train': 2.587010145187378} 08/30/2021 13:37:55 - INFO - __main__ - Step 2297: {'lr': 0.0004999950652140343, 'samples': 441024, 'steps': 2296, 'loss/train': 2.7230381965637207} 08/30/2021 13:37:56 - INFO - __main__ - Step 2298: {'lr': 0.0004999950318146737, 'samples': 441216, 'steps': 2297, 'loss/train': 3.217952013015747} 08/30/2021 13:37:56 - INFO - __main__ - Step 2299: {'lr': 0.0004999949983026691, 'samples': 441408, 'steps': 2298, 'loss/train': 3.466270685195923} 08/30/2021 13:37:57 - INFO - __main__ - Step 2300: {'lr': 0.0004999949646780205, 'samples': 441600, 'steps': 2299, 'loss/train': 3.3902628421783447} 08/30/2021 13:37:58 - INFO - __main__ - Step 2301: {'lr': 0.0004999949309407283, 'samples': 441792, 'steps': 2300, 'loss/train': 3.007880926132202} 08/30/2021 13:37:58 - INFO - __main__ - Step 2302: {'lr': 0.0004999948970907921, 'samples': 441984, 'steps': 2301, 'loss/train': 3.3225274085998535} 08/30/2021 13:37:59 - INFO - __main__ - Step 2303: {'lr': 0.0004999948631282119, 'samples': 442176, 'steps': 2302, 'loss/train': 3.5667121410369873} 08/30/2021 13:37:59 - INFO - __main__ - Step 2304: {'lr': 0.0004999948290529881, 'samples': 442368, 'steps': 2303, 'loss/train': 3.3896703720092773} 08/30/2021 13:38:01 - INFO - __main__ - Step 2305: {'lr': 0.0004999947948651204, 'samples': 442560, 'steps': 2304, 'loss/train': 3.468219757080078} 08/30/2021 13:38:01 - INFO - __main__ - Step 2306: {'lr': 0.0004999947605646089, 'samples': 442752, 'steps': 2305, 'loss/train': 3.3806169033050537} 08/30/2021 13:38:01 - INFO - __main__ - Step 2307: {'lr': 0.0004999947261514537, 'samples': 442944, 'steps': 2306, 'loss/train': 3.494899272918701} 08/30/2021 13:38:02 - INFO - __main__ - Step 2308: {'lr': 0.0004999946916256547, 'samples': 443136, 'steps': 2307, 'loss/train': 3.22977352142334} 08/30/2021 13:38:02 - INFO - __main__ - Step 2309: {'lr': 0.0004999946569872118, 'samples': 443328, 'steps': 2308, 'loss/train': 3.777221918106079} 08/30/2021 13:38:04 - INFO - __main__ - Step 2310: {'lr': 0.0004999946222361254, 'samples': 443520, 'steps': 2309, 'loss/train': 3.133528232574463} 08/30/2021 13:38:04 - INFO - __main__ - Step 2311: {'lr': 0.0004999945873723951, 'samples': 443712, 'steps': 2310, 'loss/train': 3.964779853820801} 08/30/2021 13:38:04 - INFO - __main__ - Step 2312: {'lr': 0.0004999945523960212, 'samples': 443904, 'steps': 2311, 'loss/train': 3.5267961025238037} 08/30/2021 13:38:05 - INFO - __main__ - Step 2313: {'lr': 0.0004999945173070035, 'samples': 444096, 'steps': 2312, 'loss/train': 4.563134670257568} 08/30/2021 13:38:05 - INFO - __main__ - Step 2314: {'lr': 0.0004999944821053422, 'samples': 444288, 'steps': 2313, 'loss/train': 3.2205557823181152} 08/30/2021 13:38:06 - INFO - __main__ - Step 2315: {'lr': 0.0004999944467910372, 'samples': 444480, 'steps': 2314, 'loss/train': 3.1991894245147705} 08/30/2021 13:38:07 - INFO - __main__ - Step 2316: {'lr': 0.0004999944113640887, 'samples': 444672, 'steps': 2315, 'loss/train': 2.371495246887207} 08/30/2021 13:38:07 - INFO - __main__ - Step 2317: {'lr': 0.0004999943758244964, 'samples': 444864, 'steps': 2316, 'loss/train': 3.4393770694732666} 08/30/2021 13:38:08 - INFO - __main__ - Step 2318: {'lr': 0.0004999943401722606, 'samples': 445056, 'steps': 2317, 'loss/train': 3.3501834869384766} 08/30/2021 13:38:08 - INFO - __main__ - Step 2319: {'lr': 0.0004999943044073813, 'samples': 445248, 'steps': 2318, 'loss/train': 3.7185914516448975} 08/30/2021 13:38:08 - INFO - __main__ - Step 2320: {'lr': 0.0004999942685298582, 'samples': 445440, 'steps': 2319, 'loss/train': 3.5161125659942627} 08/30/2021 13:38:10 - INFO - __main__ - Step 2321: {'lr': 0.0004999942325396916, 'samples': 445632, 'steps': 2320, 'loss/train': 4.182732582092285} 08/30/2021 13:38:11 - INFO - __main__ - Step 2322: {'lr': 0.0004999941964368817, 'samples': 445824, 'steps': 2321, 'loss/train': 3.3947317600250244} 08/30/2021 13:38:11 - INFO - __main__ - Step 2323: {'lr': 0.000499994160221428, 'samples': 446016, 'steps': 2322, 'loss/train': 0.7257397174835205} 08/30/2021 13:38:12 - INFO - __main__ - Step 2324: {'lr': 0.0004999941238933308, 'samples': 446208, 'steps': 2323, 'loss/train': 3.284926414489746} 08/30/2021 13:38:12 - INFO - __main__ - Step 2325: {'lr': 0.0004999940874525902, 'samples': 446400, 'steps': 2324, 'loss/train': 3.6126582622528076} 08/30/2021 13:38:14 - INFO - __main__ - Step 2326: {'lr': 0.0004999940508992061, 'samples': 446592, 'steps': 2325, 'loss/train': 3.614366054534912} 08/30/2021 13:38:14 - INFO - __main__ - Step 2327: {'lr': 0.0004999940142331785, 'samples': 446784, 'steps': 2326, 'loss/train': 4.015449047088623} 08/30/2021 13:38:14 - INFO - __main__ - Step 2328: {'lr': 0.0004999939774545074, 'samples': 446976, 'steps': 2327, 'loss/train': 3.174699306488037} 08/30/2021 13:38:15 - INFO - __main__ - Step 2329: {'lr': 0.000499993940563193, 'samples': 447168, 'steps': 2328, 'loss/train': 3.121023416519165} 08/30/2021 13:38:15 - INFO - __main__ - Step 2330: {'lr': 0.0004999939035592351, 'samples': 447360, 'steps': 2329, 'loss/train': 3.8974084854125977} 08/30/2021 13:38:17 - INFO - __main__ - Step 2331: {'lr': 0.0004999938664426339, 'samples': 447552, 'steps': 2330, 'loss/train': 2.9231114387512207} 08/30/2021 13:38:17 - INFO - __main__ - Step 2332: {'lr': 0.0004999938292133894, 'samples': 447744, 'steps': 2331, 'loss/train': 3.9305601119995117} 08/30/2021 13:38:17 - INFO - __main__ - Step 2333: {'lr': 0.0004999937918715013, 'samples': 447936, 'steps': 2332, 'loss/train': 3.7885520458221436} 08/30/2021 13:38:18 - INFO - __main__ - Step 2334: {'lr': 0.00049999375441697, 'samples': 448128, 'steps': 2333, 'loss/train': 2.291560173034668} 08/30/2021 13:38:18 - INFO - __main__ - Step 2335: {'lr': 0.0004999937168497954, 'samples': 448320, 'steps': 2334, 'loss/train': 3.144144296646118} 08/30/2021 13:38:19 - INFO - __main__ - Step 2336: {'lr': 0.0004999936791699773, 'samples': 448512, 'steps': 2335, 'loss/train': 2.7708489894866943} 08/30/2021 13:38:20 - INFO - __main__ - Step 2337: {'lr': 0.0004999936413775161, 'samples': 448704, 'steps': 2336, 'loss/train': 3.8705344200134277} 08/30/2021 13:38:20 - INFO - __main__ - Step 2338: {'lr': 0.0004999936034724115, 'samples': 448896, 'steps': 2337, 'loss/train': 3.3609654903411865} 08/30/2021 13:38:21 - INFO - __main__ - Step 2339: {'lr': 0.0004999935654546638, 'samples': 449088, 'steps': 2338, 'loss/train': 4.000263690948486} 08/30/2021 13:38:21 - INFO - __main__ - Step 2340: {'lr': 0.0004999935273242727, 'samples': 449280, 'steps': 2339, 'loss/train': 3.526043176651001} 08/30/2021 13:38:23 - INFO - __main__ - Step 2341: {'lr': 0.0004999934890812384, 'samples': 449472, 'steps': 2340, 'loss/train': 3.6454505920410156} 08/30/2021 13:38:23 - INFO - __main__ - Step 2342: {'lr': 0.0004999934507255609, 'samples': 449664, 'steps': 2341, 'loss/train': 3.716323137283325} 08/30/2021 13:38:24 - INFO - __main__ - Step 2343: {'lr': 0.0004999934122572403, 'samples': 449856, 'steps': 2342, 'loss/train': 3.456183910369873} 08/30/2021 13:38:24 - INFO - __main__ - Step 2344: {'lr': 0.0004999933736762763, 'samples': 450048, 'steps': 2343, 'loss/train': 1.1015268564224243} 08/30/2021 13:38:24 - INFO - __main__ - Step 2345: {'lr': 0.0004999933349826694, 'samples': 450240, 'steps': 2344, 'loss/train': 4.178706645965576} 08/30/2021 13:38:26 - INFO - __main__ - Step 2346: {'lr': 0.0004999932961764192, 'samples': 450432, 'steps': 2345, 'loss/train': 3.6283633708953857} 08/30/2021 13:38:26 - INFO - __main__ - Step 2347: {'lr': 0.000499993257257526, 'samples': 450624, 'steps': 2346, 'loss/train': 3.44881534576416} 08/30/2021 13:38:27 - INFO - __main__ - Step 2348: {'lr': 0.0004999932182259897, 'samples': 450816, 'steps': 2347, 'loss/train': 3.6039113998413086} 08/30/2021 13:38:27 - INFO - __main__ - Step 2349: {'lr': 0.0004999931790818102, 'samples': 451008, 'steps': 2348, 'loss/train': 3.0283703804016113} 08/30/2021 13:38:27 - INFO - __main__ - Step 2350: {'lr': 0.0004999931398249876, 'samples': 451200, 'steps': 2349, 'loss/train': 3.891494035720825} 08/30/2021 13:38:29 - INFO - __main__ - Step 2351: {'lr': 0.0004999931004555221, 'samples': 451392, 'steps': 2350, 'loss/train': 2.625880002975464} 08/30/2021 13:38:29 - INFO - __main__ - Step 2352: {'lr': 0.0004999930609734135, 'samples': 451584, 'steps': 2351, 'loss/train': 4.154180526733398} 08/30/2021 13:38:29 - INFO - __main__ - Step 2353: {'lr': 0.0004999930213786619, 'samples': 451776, 'steps': 2352, 'loss/train': 3.700856924057007} 08/30/2021 13:38:30 - INFO - __main__ - Step 2354: {'lr': 0.0004999929816712672, 'samples': 451968, 'steps': 2353, 'loss/train': 3.392261505126953} 08/30/2021 13:38:30 - INFO - __main__ - Step 2355: {'lr': 0.0004999929418512296, 'samples': 452160, 'steps': 2354, 'loss/train': 3.879117250442505} 08/30/2021 13:38:31 - INFO - __main__ - Step 2356: {'lr': 0.0004999929019185491, 'samples': 452352, 'steps': 2355, 'loss/train': 3.42183780670166} 08/30/2021 13:38:32 - INFO - __main__ - Step 2357: {'lr': 0.0004999928618732256, 'samples': 452544, 'steps': 2356, 'loss/train': 3.023010492324829} 08/30/2021 13:38:33 - INFO - __main__ - Step 2358: {'lr': 0.0004999928217152591, 'samples': 452736, 'steps': 2357, 'loss/train': 2.951460123062134} 08/30/2021 13:38:33 - INFO - __main__ - Step 2359: {'lr': 0.0004999927814446498, 'samples': 452928, 'steps': 2358, 'loss/train': 3.4824776649475098} 08/30/2021 13:38:33 - INFO - __main__ - Step 2360: {'lr': 0.0004999927410613975, 'samples': 453120, 'steps': 2359, 'loss/train': 3.272944927215576} 08/30/2021 13:38:34 - INFO - __main__ - Step 2361: {'lr': 0.0004999927005655024, 'samples': 453312, 'steps': 2360, 'loss/train': 4.292819976806641} 08/30/2021 13:38:35 - INFO - __main__ - Step 2362: {'lr': 0.0004999926599569644, 'samples': 453504, 'steps': 2361, 'loss/train': 3.606462240219116} 08/30/2021 13:38:36 - INFO - __main__ - Step 2363: {'lr': 0.0004999926192357836, 'samples': 453696, 'steps': 2362, 'loss/train': 3.055013656616211} 08/30/2021 13:38:36 - INFO - __main__ - Step 2364: {'lr': 0.00049999257840196, 'samples': 453888, 'steps': 2363, 'loss/train': 3.5679545402526855} 08/30/2021 13:38:37 - INFO - __main__ - Step 2365: {'lr': 0.0004999925374554936, 'samples': 454080, 'steps': 2364, 'loss/train': 3.2827484607696533} 08/30/2021 13:38:37 - INFO - __main__ - Step 2366: {'lr': 0.0004999924963963845, 'samples': 454272, 'steps': 2365, 'loss/train': 3.22670578956604} 08/30/2021 13:38:37 - INFO - __main__ - Step 2367: {'lr': 0.0004999924552246324, 'samples': 454464, 'steps': 2366, 'loss/train': 3.738640546798706} 08/30/2021 13:38:39 - INFO - __main__ - Step 2368: {'lr': 0.0004999924139402378, 'samples': 454656, 'steps': 2367, 'loss/train': 3.8646726608276367} 08/30/2021 13:38:39 - INFO - __main__ - Step 2369: {'lr': 0.0004999923725432004, 'samples': 454848, 'steps': 2368, 'loss/train': 3.3699100017547607} 08/30/2021 13:38:39 - INFO - __main__ - Step 2370: {'lr': 0.0004999923310335202, 'samples': 455040, 'steps': 2369, 'loss/train': 2.9062230587005615} 08/30/2021 13:38:40 - INFO - __main__ - Step 2371: {'lr': 0.0004999922894111975, 'samples': 455232, 'steps': 2370, 'loss/train': 2.65940523147583} 08/30/2021 13:38:40 - INFO - __main__ - Step 2372: {'lr': 0.000499992247676232, 'samples': 455424, 'steps': 2371, 'loss/train': 3.379642963409424} 08/30/2021 13:38:42 - INFO - __main__ - Step 2373: {'lr': 0.0004999922058286238, 'samples': 455616, 'steps': 2372, 'loss/train': 2.7595129013061523} 08/30/2021 13:38:43 - INFO - __main__ - Step 2374: {'lr': 0.0004999921638683731, 'samples': 455808, 'steps': 2373, 'loss/train': 3.4127492904663086} 08/30/2021 13:38:43 - INFO - __main__ - Step 2375: {'lr': 0.0004999921217954797, 'samples': 456000, 'steps': 2374, 'loss/train': 3.960245370864868} 08/30/2021 13:38:43 - INFO - __main__ - Step 2376: {'lr': 0.0004999920796099437, 'samples': 456192, 'steps': 2375, 'loss/train': 4.573826313018799} 08/30/2021 13:38:44 - INFO - __main__ - Step 2377: {'lr': 0.0004999920373117652, 'samples': 456384, 'steps': 2376, 'loss/train': 3.424320697784424} 08/30/2021 13:38:45 - INFO - __main__ - Step 2378: {'lr': 0.0004999919949009442, 'samples': 456576, 'steps': 2377, 'loss/train': 3.022109031677246} 08/30/2021 13:38:46 - INFO - __main__ - Step 2379: {'lr': 0.0004999919523774806, 'samples': 456768, 'steps': 2378, 'loss/train': 3.9209976196289062} 08/30/2021 13:38:46 - INFO - __main__ - Step 2380: {'lr': 0.0004999919097413743, 'samples': 456960, 'steps': 2379, 'loss/train': 3.20947527885437} 08/30/2021 13:38:46 - INFO - __main__ - Step 2381: {'lr': 0.0004999918669926258, 'samples': 457152, 'steps': 2380, 'loss/train': 3.571824312210083} 08/30/2021 13:38:47 - INFO - __main__ - Step 2382: {'lr': 0.0004999918241312346, 'samples': 457344, 'steps': 2381, 'loss/train': 4.165573596954346} 08/30/2021 13:38:48 - INFO - __main__ - Step 2383: {'lr': 0.0004999917811572011, 'samples': 457536, 'steps': 2382, 'loss/train': 3.543983221054077} 08/30/2021 13:38:49 - INFO - __main__ - Step 2384: {'lr': 0.000499991738070525, 'samples': 457728, 'steps': 2383, 'loss/train': 3.2464683055877686} 08/30/2021 13:38:49 - INFO - __main__ - Step 2385: {'lr': 0.0004999916948712066, 'samples': 457920, 'steps': 2384, 'loss/train': 4.028754711151123} 08/30/2021 13:38:50 - INFO - __main__ - Step 2386: {'lr': 0.0004999916515592458, 'samples': 458112, 'steps': 2385, 'loss/train': 2.846074104309082} 08/30/2021 13:38:50 - INFO - __main__ - Step 2387: {'lr': 0.0004999916081346426, 'samples': 458304, 'steps': 2386, 'loss/train': 3.153379201889038} 08/30/2021 13:38:52 - INFO - __main__ - Step 2388: {'lr': 0.000499991564597397, 'samples': 458496, 'steps': 2387, 'loss/train': 3.519200086593628} 08/30/2021 13:38:52 - INFO - __main__ - Step 2389: {'lr': 0.0004999915209475091, 'samples': 458688, 'steps': 2388, 'loss/train': 3.616925001144409} 08/30/2021 13:38:52 - INFO - __main__ - Step 2390: {'lr': 0.0004999914771849788, 'samples': 458880, 'steps': 2389, 'loss/train': 2.9786550998687744} 08/30/2021 13:38:53 - INFO - __main__ - Step 2391: {'lr': 0.0004999914333098063, 'samples': 459072, 'steps': 2390, 'loss/train': 3.6126270294189453} 08/30/2021 13:38:53 - INFO - __main__ - Step 2392: {'lr': 0.0004999913893219915, 'samples': 459264, 'steps': 2391, 'loss/train': 3.707750082015991} 08/30/2021 13:38:54 - INFO - __main__ - Step 2393: {'lr': 0.0004999913452215345, 'samples': 459456, 'steps': 2392, 'loss/train': 3.7249889373779297} 08/30/2021 13:38:55 - INFO - __main__ - Step 2394: {'lr': 0.0004999913010084351, 'samples': 459648, 'steps': 2393, 'loss/train': 3.313490867614746} 08/30/2021 13:38:55 - INFO - __main__ - Step 2395: {'lr': 0.0004999912566826935, 'samples': 459840, 'steps': 2394, 'loss/train': 2.9527111053466797} 08/30/2021 13:38:56 - INFO - __main__ - Step 2396: {'lr': 0.0004999912122443098, 'samples': 460032, 'steps': 2395, 'loss/train': 3.189500570297241} 08/30/2021 13:38:56 - INFO - __main__ - Step 2397: {'lr': 0.0004999911676932838, 'samples': 460224, 'steps': 2396, 'loss/train': 4.016993045806885} 08/30/2021 13:38:56 - INFO - __main__ - Step 2398: {'lr': 0.0004999911230296158, 'samples': 460416, 'steps': 2397, 'loss/train': 5.025796413421631} 08/30/2021 13:38:58 - INFO - __main__ - Step 2399: {'lr': 0.0004999910782533055, 'samples': 460608, 'steps': 2398, 'loss/train': 2.0938472747802734} 08/30/2021 13:38:58 - INFO - __main__ - Step 2400: {'lr': 0.0004999910333643531, 'samples': 460800, 'steps': 2399, 'loss/train': 2.946650505065918} 08/30/2021 13:38:59 - INFO - __main__ - Step 2401: {'lr': 0.0004999909883627587, 'samples': 460992, 'steps': 2400, 'loss/train': 3.4790730476379395} 08/30/2021 13:38:59 - INFO - __main__ - Step 2402: {'lr': 0.0004999909432485221, 'samples': 461184, 'steps': 2401, 'loss/train': 1.8312193155288696} 08/30/2021 13:38:59 - INFO - __main__ - Step 2403: {'lr': 0.0004999908980216436, 'samples': 461376, 'steps': 2402, 'loss/train': 2.963334083557129} 08/30/2021 13:39:01 - INFO - __main__ - Step 2404: {'lr': 0.0004999908526821229, 'samples': 461568, 'steps': 2403, 'loss/train': 3.677765130996704} 08/30/2021 13:39:01 - INFO - __main__ - Step 2405: {'lr': 0.0004999908072299602, 'samples': 461760, 'steps': 2404, 'loss/train': 3.313152551651001} 08/30/2021 13:39:01 - INFO - __main__ - Step 2406: {'lr': 0.0004999907616651556, 'samples': 461952, 'steps': 2405, 'loss/train': 3.7477095127105713} 08/30/2021 13:39:02 - INFO - __main__ - Step 2407: {'lr': 0.000499990715987709, 'samples': 462144, 'steps': 2406, 'loss/train': 3.4406871795654297} 08/30/2021 13:39:02 - INFO - __main__ - Step 2408: {'lr': 0.0004999906701976203, 'samples': 462336, 'steps': 2407, 'loss/train': 3.336057186126709} 08/30/2021 13:39:04 - INFO - __main__ - Step 2409: {'lr': 0.0004999906242948898, 'samples': 462528, 'steps': 2408, 'loss/train': 2.045273542404175} 08/30/2021 13:39:04 - INFO - __main__ - Step 2410: {'lr': 0.0004999905782795173, 'samples': 462720, 'steps': 2409, 'loss/train': 3.7166590690612793} 08/30/2021 13:39:04 - INFO - __main__ - Step 2411: {'lr': 0.000499990532151503, 'samples': 462912, 'steps': 2410, 'loss/train': 3.179212808609009} 08/30/2021 13:39:05 - INFO - __main__ - Step 2412: {'lr': 0.0004999904859108467, 'samples': 463104, 'steps': 2411, 'loss/train': 3.3981876373291016} 08/30/2021 13:39:05 - INFO - __main__ - Step 2413: {'lr': 0.0004999904395575486, 'samples': 463296, 'steps': 2412, 'loss/train': 3.156912088394165} 08/30/2021 13:39:07 - INFO - __main__ - Step 2414: {'lr': 0.0004999903930916087, 'samples': 463488, 'steps': 2413, 'loss/train': 3.3669259548187256} 08/30/2021 13:39:07 - INFO - __main__ - Step 2415: {'lr': 0.000499990346513027, 'samples': 463680, 'steps': 2414, 'loss/train': 3.3963608741760254} 08/30/2021 13:39:08 - INFO - __main__ - Step 2416: {'lr': 0.0004999902998218034, 'samples': 463872, 'steps': 2415, 'loss/train': 3.2971057891845703} 08/30/2021 13:39:08 - INFO - __main__ - Step 2417: {'lr': 0.000499990253017938, 'samples': 464064, 'steps': 2416, 'loss/train': 3.180245876312256} 08/30/2021 13:39:08 - INFO - __main__ - Step 2418: {'lr': 0.0004999902061014311, 'samples': 464256, 'steps': 2417, 'loss/train': 2.1976773738861084} 08/30/2021 13:39:09 - INFO - __main__ - Step 2419: {'lr': 0.0004999901590722823, 'samples': 464448, 'steps': 2418, 'loss/train': 3.4911413192749023} 08/30/2021 13:39:10 - INFO - __main__ - Step 2420: {'lr': 0.0004999901119304919, 'samples': 464640, 'steps': 2419, 'loss/train': 3.558926582336426} 08/30/2021 13:39:11 - INFO - __main__ - Step 2421: {'lr': 0.0004999900646760597, 'samples': 464832, 'steps': 2420, 'loss/train': 3.358968734741211} 08/30/2021 13:39:11 - INFO - __main__ - Step 2422: {'lr': 0.0004999900173089858, 'samples': 465024, 'steps': 2421, 'loss/train': 3.1792385578155518} 08/30/2021 13:39:11 - INFO - __main__ - Step 2423: {'lr': 0.0004999899698292703, 'samples': 465216, 'steps': 2422, 'loss/train': 4.46215295791626} 08/30/2021 13:39:12 - INFO - __main__ - Step 2424: {'lr': 0.0004999899222369132, 'samples': 465408, 'steps': 2423, 'loss/train': 2.913651704788208} 08/30/2021 13:39:13 - INFO - __main__ - Step 2425: {'lr': 0.0004999898745319145, 'samples': 465600, 'steps': 2424, 'loss/train': 3.9791011810302734} 08/30/2021 13:39:14 - INFO - __main__ - Step 2426: {'lr': 0.0004999898267142741, 'samples': 465792, 'steps': 2425, 'loss/train': 3.211440324783325} 08/30/2021 13:39:14 - INFO - __main__ - Step 2427: {'lr': 0.0004999897787839923, 'samples': 465984, 'steps': 2426, 'loss/train': 4.253355979919434} 08/30/2021 13:39:14 - INFO - __main__ - Step 2428: {'lr': 0.000499989730741069, 'samples': 466176, 'steps': 2427, 'loss/train': 3.0943493843078613} 08/30/2021 13:39:15 - INFO - __main__ - Step 2429: {'lr': 0.000499989682585504, 'samples': 466368, 'steps': 2428, 'loss/train': 3.28936767578125} 08/30/2021 13:39:17 - INFO - __main__ - Step 2430: {'lr': 0.0004999896343172976, 'samples': 466560, 'steps': 2429, 'loss/train': 4.029385089874268} 08/30/2021 13:39:17 - INFO - __main__ - Step 2431: {'lr': 0.0004999895859364498, 'samples': 466752, 'steps': 2430, 'loss/train': 3.9884324073791504} 08/30/2021 13:39:18 - INFO - __main__ - Step 2432: {'lr': 0.0004999895374429605, 'samples': 466944, 'steps': 2431, 'loss/train': 3.7134838104248047} 08/30/2021 13:39:18 - INFO - __main__ - Step 2433: {'lr': 0.0004999894888368297, 'samples': 467136, 'steps': 2432, 'loss/train': 3.9085521697998047} 08/30/2021 13:39:18 - INFO - __main__ - Step 2434: {'lr': 0.0004999894401180576, 'samples': 467328, 'steps': 2433, 'loss/train': 2.209113121032715} 08/30/2021 13:39:20 - INFO - __main__ - Step 2435: {'lr': 0.0004999893912866441, 'samples': 467520, 'steps': 2434, 'loss/train': 3.9369819164276123} 08/30/2021 13:39:20 - INFO - __main__ - Step 2436: {'lr': 0.0004999893423425892, 'samples': 467712, 'steps': 2435, 'loss/train': 4.0529890060424805} 08/30/2021 13:39:21 - INFO - __main__ - Step 2437: {'lr': 0.0004999892932858929, 'samples': 467904, 'steps': 2436, 'loss/train': 3.331840753555298} 08/30/2021 13:39:21 - INFO - __main__ - Step 2438: {'lr': 0.0004999892441165554, 'samples': 468096, 'steps': 2437, 'loss/train': 3.2444252967834473} 08/30/2021 13:39:21 - INFO - __main__ - Step 2439: {'lr': 0.0004999891948345765, 'samples': 468288, 'steps': 2438, 'loss/train': 3.1652252674102783} 08/30/2021 13:39:23 - INFO - __main__ - Step 2440: {'lr': 0.0004999891454399565, 'samples': 468480, 'steps': 2439, 'loss/train': 3.267704725265503} 08/30/2021 13:39:23 - INFO - __main__ - Step 2441: {'lr': 0.000499989095932695, 'samples': 468672, 'steps': 2440, 'loss/train': 4.30018949508667} 08/30/2021 13:39:24 - INFO - __main__ - Step 2442: {'lr': 0.0004999890463127924, 'samples': 468864, 'steps': 2441, 'loss/train': 4.094340801239014} 08/30/2021 13:39:24 - INFO - __main__ - Step 2443: {'lr': 0.0004999889965802486, 'samples': 469056, 'steps': 2442, 'loss/train': 4.673208236694336} 08/30/2021 13:39:24 - INFO - __main__ - Step 2444: {'lr': 0.0004999889467350636, 'samples': 469248, 'steps': 2443, 'loss/train': 3.901282548904419} 08/30/2021 13:39:25 - INFO - __main__ - Step 2445: {'lr': 0.0004999888967772375, 'samples': 469440, 'steps': 2444, 'loss/train': 4.057990550994873} 08/30/2021 13:39:26 - INFO - __main__ - Step 2446: {'lr': 0.0004999888467067702, 'samples': 469632, 'steps': 2445, 'loss/train': 4.6610589027404785} 08/30/2021 13:39:27 - INFO - __main__ - Step 2447: {'lr': 0.0004999887965236617, 'samples': 469824, 'steps': 2446, 'loss/train': 3.1241021156311035} 08/30/2021 13:39:27 - INFO - __main__ - Step 2448: {'lr': 0.0004999887462279123, 'samples': 470016, 'steps': 2447, 'loss/train': 3.665513515472412} 08/30/2021 13:39:27 - INFO - __main__ - Step 2449: {'lr': 0.0004999886958195216, 'samples': 470208, 'steps': 2448, 'loss/train': 3.249267816543579} 08/30/2021 13:39:28 - INFO - __main__ - Step 2450: {'lr': 0.00049998864529849, 'samples': 470400, 'steps': 2449, 'loss/train': 3.2747325897216797} 08/30/2021 13:39:29 - INFO - __main__ - Step 2451: {'lr': 0.0004999885946648174, 'samples': 470592, 'steps': 2450, 'loss/train': 3.5657455921173096} 08/30/2021 13:39:30 - INFO - __main__ - Step 2452: {'lr': 0.0004999885439185037, 'samples': 470784, 'steps': 2451, 'loss/train': 2.537431478500366} 08/30/2021 13:39:30 - INFO - __main__ - Step 2453: {'lr': 0.0004999884930595491, 'samples': 470976, 'steps': 2452, 'loss/train': 2.845932960510254} 08/30/2021 13:39:30 - INFO - __main__ - Step 2454: {'lr': 0.0004999884420879534, 'samples': 471168, 'steps': 2453, 'loss/train': 3.258159875869751} 08/30/2021 13:39:31 - INFO - __main__ - Step 2455: {'lr': 0.000499988391003717, 'samples': 471360, 'steps': 2454, 'loss/train': 2.972184419631958} 08/30/2021 13:39:32 - INFO - __main__ - Step 2456: {'lr': 0.0004999883398068396, 'samples': 471552, 'steps': 2455, 'loss/train': 3.4724526405334473} 08/30/2021 13:39:33 - INFO - __main__ - Step 2457: {'lr': 0.0004999882884973212, 'samples': 471744, 'steps': 2456, 'loss/train': 5.70952844619751} 08/30/2021 13:39:33 - INFO - __main__ - Step 2458: {'lr': 0.000499988237075162, 'samples': 471936, 'steps': 2457, 'loss/train': 2.890782594680786} 08/30/2021 13:39:34 - INFO - __main__ - Step 2459: {'lr': 0.000499988185540362, 'samples': 472128, 'steps': 2458, 'loss/train': 3.2589898109436035} 08/30/2021 13:39:34 - INFO - __main__ - Step 2460: {'lr': 0.0004999881338929211, 'samples': 472320, 'steps': 2459, 'loss/train': 3.168170213699341} 08/30/2021 13:39:35 - INFO - __main__ - Step 2461: {'lr': 0.0004999880821328395, 'samples': 472512, 'steps': 2460, 'loss/train': 3.469691276550293} 08/30/2021 13:39:36 - INFO - __main__ - Step 2462: {'lr': 0.000499988030260117, 'samples': 472704, 'steps': 2461, 'loss/train': 4.25238037109375} 08/30/2021 13:39:36 - INFO - __main__ - Step 2463: {'lr': 0.0004999879782747539, 'samples': 472896, 'steps': 2462, 'loss/train': 3.698615074157715} 08/30/2021 13:39:36 - INFO - __main__ - Step 2464: {'lr': 0.00049998792617675, 'samples': 473088, 'steps': 2463, 'loss/train': 3.922322988510132} 08/30/2021 13:39:37 - INFO - __main__ - Step 2465: {'lr': 0.0004999878739661053, 'samples': 473280, 'steps': 2464, 'loss/train': 3.4149012565612793} 08/30/2021 13:39:38 - INFO - __main__ - Step 2466: {'lr': 0.0004999878216428201, 'samples': 473472, 'steps': 2465, 'loss/train': 3.7355833053588867} 08/30/2021 13:39:39 - INFO - __main__ - Step 2467: {'lr': 0.0004999877692068942, 'samples': 473664, 'steps': 2466, 'loss/train': 3.661376953125} 08/30/2021 13:39:39 - INFO - __main__ - Step 2468: {'lr': 0.0004999877166583276, 'samples': 473856, 'steps': 2467, 'loss/train': 3.195875406265259} 08/30/2021 13:39:40 - INFO - __main__ - Step 2469: {'lr': 0.0004999876639971204, 'samples': 474048, 'steps': 2468, 'loss/train': 3.488727569580078} 08/30/2021 13:39:40 - INFO - __main__ - Step 2470: {'lr': 0.0004999876112232726, 'samples': 474240, 'steps': 2469, 'loss/train': 3.3036279678344727} 08/30/2021 13:39:41 - INFO - __main__ - Step 2471: {'lr': 0.0004999875583367844, 'samples': 474432, 'steps': 2470, 'loss/train': 3.79384183883667} 08/30/2021 13:39:42 - INFO - __main__ - Step 2472: {'lr': 0.0004999875053376555, 'samples': 474624, 'steps': 2471, 'loss/train': 2.880828857421875} 08/30/2021 13:39:42 - INFO - __main__ - Step 2473: {'lr': 0.0004999874522258861, 'samples': 474816, 'steps': 2472, 'loss/train': 3.9294240474700928} 08/30/2021 13:39:43 - INFO - __main__ - Step 2474: {'lr': 0.0004999873990014763, 'samples': 475008, 'steps': 2473, 'loss/train': 3.158289909362793} 08/30/2021 13:39:43 - INFO - __main__ - Step 2475: {'lr': 0.0004999873456644259, 'samples': 475200, 'steps': 2474, 'loss/train': 2.3990821838378906} 08/30/2021 13:39:44 - INFO - __main__ - Step 2476: {'lr': 0.0004999872922147352, 'samples': 475392, 'steps': 2475, 'loss/train': 3.361088275909424} 08/30/2021 13:39:45 - INFO - __main__ - Step 2477: {'lr': 0.0004999872386524041, 'samples': 475584, 'steps': 2476, 'loss/train': 3.6757729053497314} 08/30/2021 13:39:45 - INFO - __main__ - Step 2478: {'lr': 0.0004999871849774325, 'samples': 475776, 'steps': 2477, 'loss/train': 3.659137725830078} 08/30/2021 13:39:46 - INFO - __main__ - Step 2479: {'lr': 0.0004999871311898205, 'samples': 475968, 'steps': 2478, 'loss/train': 3.3369903564453125} 08/30/2021 13:39:46 - INFO - __main__ - Step 2480: {'lr': 0.0004999870772895683, 'samples': 476160, 'steps': 2479, 'loss/train': 3.4437551498413086} 08/30/2021 13:39:48 - INFO - __main__ - Step 2481: {'lr': 0.0004999870232766756, 'samples': 476352, 'steps': 2480, 'loss/train': 3.702115297317505} 08/30/2021 13:39:49 - INFO - __main__ - Step 2482: {'lr': 0.0004999869691511428, 'samples': 476544, 'steps': 2481, 'loss/train': 4.077302932739258} 08/30/2021 13:39:49 - INFO - __main__ - Step 2483: {'lr': 0.0004999869149129696, 'samples': 476736, 'steps': 2482, 'loss/train': 3.502058506011963} 08/30/2021 13:39:49 - INFO - __main__ - Step 2484: {'lr': 0.0004999868605621563, 'samples': 476928, 'steps': 2483, 'loss/train': 3.562957525253296} 08/30/2021 13:39:50 - INFO - __main__ - Step 2485: {'lr': 0.0004999868060987027, 'samples': 477120, 'steps': 2484, 'loss/train': 2.818432569503784} 08/30/2021 13:39:50 - INFO - __main__ - Step 2486: {'lr': 0.0004999867515226088, 'samples': 477312, 'steps': 2485, 'loss/train': 3.346011161804199} 08/30/2021 13:39:51 - INFO - __main__ - Step 2487: {'lr': 0.0004999866968338748, 'samples': 477504, 'steps': 2486, 'loss/train': 1.1037997007369995} 08/30/2021 13:39:52 - INFO - __main__ - Step 2488: {'lr': 0.0004999866420325006, 'samples': 477696, 'steps': 2487, 'loss/train': 3.7922840118408203} 08/30/2021 13:39:52 - INFO - __main__ - Step 2489: {'lr': 0.0004999865871184863, 'samples': 477888, 'steps': 2488, 'loss/train': 3.2803664207458496} 08/30/2021 13:39:53 - INFO - __main__ - Step 2490: {'lr': 0.000499986532091832, 'samples': 478080, 'steps': 2489, 'loss/train': 3.34903883934021} 08/30/2021 13:39:53 - INFO - __main__ - Step 2491: {'lr': 0.0004999864769525375, 'samples': 478272, 'steps': 2490, 'loss/train': 3.25426983833313} 08/30/2021 13:39:54 - INFO - __main__ - Step 2492: {'lr': 0.000499986421700603, 'samples': 478464, 'steps': 2491, 'loss/train': 3.161381959915161} 08/30/2021 13:39:55 - INFO - __main__ - Step 2493: {'lr': 0.0004999863663360285, 'samples': 478656, 'steps': 2492, 'loss/train': 3.2575273513793945} 08/30/2021 13:39:55 - INFO - __main__ - Step 2494: {'lr': 0.000499986310858814, 'samples': 478848, 'steps': 2493, 'loss/train': 2.6650431156158447} 08/30/2021 13:39:56 - INFO - __main__ - Step 2495: {'lr': 0.0004999862552689595, 'samples': 479040, 'steps': 2494, 'loss/train': 3.0776734352111816} 08/30/2021 13:39:56 - INFO - __main__ - Step 2496: {'lr': 0.000499986199566465, 'samples': 479232, 'steps': 2495, 'loss/train': 3.138657808303833} 08/30/2021 13:39:57 - INFO - __main__ - Step 2497: {'lr': 0.0004999861437513306, 'samples': 479424, 'steps': 2496, 'loss/train': 1.8879177570343018} 08/30/2021 13:39:58 - INFO - __main__ - Step 2498: {'lr': 0.0004999860878235564, 'samples': 479616, 'steps': 2497, 'loss/train': 3.305360794067383} 08/30/2021 13:39:58 - INFO - __main__ - Step 2499: {'lr': 0.0004999860317831423, 'samples': 479808, 'steps': 2498, 'loss/train': 3.1247971057891846} 08/30/2021 13:39:59 - INFO - __main__ - Step 2500: {'lr': 0.0004999859756300883, 'samples': 480000, 'steps': 2499, 'loss/train': 3.1875553131103516} 08/30/2021 13:39:59 - INFO - __main__ - Step 2501: {'lr': 0.0004999859193643945, 'samples': 480192, 'steps': 2500, 'loss/train': 3.408926010131836} 08/30/2021 13:40:01 - INFO - __main__ - Step 2502: {'lr': 0.0004999858629860609, 'samples': 480384, 'steps': 2501, 'loss/train': 3.225663900375366} 08/30/2021 13:40:01 - INFO - __main__ - Step 2503: {'lr': 0.0004999858064950875, 'samples': 480576, 'steps': 2502, 'loss/train': 2.3713886737823486} 08/30/2021 13:40:01 - INFO - __main__ - Step 2504: {'lr': 0.0004999857498914744, 'samples': 480768, 'steps': 2503, 'loss/train': 2.82582688331604} 08/30/2021 13:40:02 - INFO - __main__ - Step 2505: {'lr': 0.0004999856931752215, 'samples': 480960, 'steps': 2504, 'loss/train': 3.6427695751190186} 08/30/2021 13:40:02 - INFO - __main__ - Step 2506: {'lr': 0.000499985636346329, 'samples': 481152, 'steps': 2505, 'loss/train': 2.7283215522766113} 08/30/2021 13:40:04 - INFO - __main__ - Step 2507: {'lr': 0.0004999855794047968, 'samples': 481344, 'steps': 2506, 'loss/train': 3.2982444763183594} 08/30/2021 13:40:04 - INFO - __main__ - Step 2508: {'lr': 0.000499985522350625, 'samples': 481536, 'steps': 2507, 'loss/train': 3.2410199642181396} 08/30/2021 13:40:05 - INFO - __main__ - Step 2509: {'lr': 0.0004999854651838134, 'samples': 481728, 'steps': 2508, 'loss/train': 3.3344876766204834} 08/30/2021 13:40:05 - INFO - __main__ - Step 2510: {'lr': 0.0004999854079043624, 'samples': 481920, 'steps': 2509, 'loss/train': 1.1394327878952026} 08/30/2021 13:40:05 - INFO - __main__ - Step 2511: {'lr': 0.0004999853505122718, 'samples': 482112, 'steps': 2510, 'loss/train': 0.7066466212272644} 08/30/2021 13:40:07 - INFO - __main__ - Step 2512: {'lr': 0.0004999852930075416, 'samples': 482304, 'steps': 2511, 'loss/train': 3.296462059020996} 08/30/2021 13:40:07 - INFO - __main__ - Step 2513: {'lr': 0.0004999852353901719, 'samples': 482496, 'steps': 2512, 'loss/train': 2.5775790214538574} 08/30/2021 13:40:07 - INFO - __main__ - Step 2514: {'lr': 0.0004999851776601627, 'samples': 482688, 'steps': 2513, 'loss/train': 3.0068328380584717} 08/30/2021 13:40:08 - INFO - __main__ - Step 2515: {'lr': 0.0004999851198175141, 'samples': 482880, 'steps': 2514, 'loss/train': 3.845776319503784} 08/30/2021 13:40:08 - INFO - __main__ - Step 2516: {'lr': 0.0004999850618622259, 'samples': 483072, 'steps': 2515, 'loss/train': 3.6843724250793457} 08/30/2021 13:40:08 - INFO - __main__ - Step 2517: {'lr': 0.0004999850037942984, 'samples': 483264, 'steps': 2516, 'loss/train': 3.3851566314697266} 08/30/2021 13:40:10 - INFO - __main__ - Step 2518: {'lr': 0.0004999849456137316, 'samples': 483456, 'steps': 2517, 'loss/train': 2.5815160274505615} 08/30/2021 13:40:11 - INFO - __main__ - Step 2519: {'lr': 0.0004999848873205254, 'samples': 483648, 'steps': 2518, 'loss/train': 3.131572723388672} 08/30/2021 13:40:11 - INFO - __main__ - Step 2520: {'lr': 0.0004999848289146798, 'samples': 483840, 'steps': 2519, 'loss/train': 3.4908299446105957} 08/30/2021 13:40:11 - INFO - __main__ - Step 2521: {'lr': 0.0004999847703961948, 'samples': 484032, 'steps': 2520, 'loss/train': 3.4235336780548096} 08/30/2021 13:40:12 - INFO - __main__ - Step 2522: {'lr': 0.0004999847117650708, 'samples': 484224, 'steps': 2521, 'loss/train': 2.7699456214904785} 08/30/2021 13:40:13 - INFO - __main__ - Step 2523: {'lr': 0.0004999846530213074, 'samples': 484416, 'steps': 2522, 'loss/train': 3.3291280269622803} 08/30/2021 13:40:14 - INFO - __main__ - Step 2524: {'lr': 0.0004999845941649048, 'samples': 484608, 'steps': 2523, 'loss/train': 3.7320284843444824} 08/30/2021 13:40:14 - INFO - __main__ - Step 2525: {'lr': 0.0004999845351958629, 'samples': 484800, 'steps': 2524, 'loss/train': 0.8700743913650513} 08/30/2021 13:40:15 - INFO - __main__ - Step 2526: {'lr': 0.0004999844761141818, 'samples': 484992, 'steps': 2525, 'loss/train': 2.396313428878784} 08/30/2021 13:40:15 - INFO - __main__ - Step 2527: {'lr': 0.0004999844169198617, 'samples': 485184, 'steps': 2526, 'loss/train': 3.6103646755218506} 08/30/2021 13:40:16 - INFO - __main__ - Step 2528: {'lr': 0.0004999843576129024, 'samples': 485376, 'steps': 2527, 'loss/train': 3.05768084526062} 08/30/2021 13:40:17 - INFO - __main__ - Step 2529: {'lr': 0.000499984298193304, 'samples': 485568, 'steps': 2528, 'loss/train': 4.48790979385376} 08/30/2021 13:40:17 - INFO - __main__ - Step 2530: {'lr': 0.0004999842386610666, 'samples': 485760, 'steps': 2529, 'loss/train': 3.349534273147583} 08/30/2021 13:40:18 - INFO - __main__ - Step 2531: {'lr': 0.0004999841790161901, 'samples': 485952, 'steps': 2530, 'loss/train': 3.3274784088134766} 08/30/2021 13:40:18 - INFO - __main__ - Step 2532: {'lr': 0.0004999841192586746, 'samples': 486144, 'steps': 2531, 'loss/train': 3.838348865509033} 08/30/2021 13:40:20 - INFO - __main__ - Step 2533: {'lr': 0.0004999840593885201, 'samples': 486336, 'steps': 2532, 'loss/train': 3.1673481464385986} 08/30/2021 13:40:20 - INFO - __main__ - Step 2534: {'lr': 0.0004999839994057266, 'samples': 486528, 'steps': 2533, 'loss/train': 3.536339282989502} 08/30/2021 13:40:21 - INFO - __main__ - Step 2535: {'lr': 0.0004999839393102943, 'samples': 486720, 'steps': 2534, 'loss/train': 2.235766887664795} 08/30/2021 13:40:21 - INFO - __main__ - Step 2536: {'lr': 0.0004999838791022229, 'samples': 486912, 'steps': 2535, 'loss/train': 1.8790549039840698} 08/30/2021 13:40:21 - INFO - __main__ - Step 2537: {'lr': 0.0004999838187815128, 'samples': 487104, 'steps': 2536, 'loss/train': 3.3130922317504883} 08/30/2021 13:40:23 - INFO - __main__ - Step 2538: {'lr': 0.0004999837583481638, 'samples': 487296, 'steps': 2537, 'loss/train': 2.9206509590148926} 08/30/2021 13:40:24 - INFO - __main__ - Step 2539: {'lr': 0.000499983697802176, 'samples': 487488, 'steps': 2538, 'loss/train': 2.7371299266815186} 08/30/2021 13:40:24 - INFO - __main__ - Step 2540: {'lr': 0.0004999836371435494, 'samples': 487680, 'steps': 2539, 'loss/train': 3.4457602500915527} 08/30/2021 13:40:24 - INFO - __main__ - Step 2541: {'lr': 0.000499983576372284, 'samples': 487872, 'steps': 2540, 'loss/train': 3.235722303390503} 08/30/2021 13:40:25 - INFO - __main__ - Step 2542: {'lr': 0.0004999835154883798, 'samples': 488064, 'steps': 2541, 'loss/train': 3.3214685916900635} 08/30/2021 13:40:25 - INFO - __main__ - Step 2543: {'lr': 0.0004999834544918369, 'samples': 488256, 'steps': 2542, 'loss/train': 2.9445972442626953} 08/30/2021 13:40:27 - INFO - __main__ - Step 2544: {'lr': 0.0004999833933826554, 'samples': 488448, 'steps': 2543, 'loss/train': 3.240677833557129} 08/30/2021 13:40:27 - INFO - __main__ - Step 2545: {'lr': 0.0004999833321608351, 'samples': 488640, 'steps': 2544, 'loss/train': 2.8306660652160645} 08/30/2021 13:40:27 - INFO - __main__ - Step 2546: {'lr': 0.0004999832708263764, 'samples': 488832, 'steps': 2545, 'loss/train': 3.1749751567840576} 08/30/2021 13:40:28 - INFO - __main__ - Step 2547: {'lr': 0.000499983209379279, 'samples': 489024, 'steps': 2546, 'loss/train': 3.7916362285614014} 08/30/2021 13:40:28 - INFO - __main__ - Step 2548: {'lr': 0.0004999831478195429, 'samples': 489216, 'steps': 2547, 'loss/train': 3.540221691131592} 08/30/2021 13:40:29 - INFO - __main__ - Step 2549: {'lr': 0.0004999830861471684, 'samples': 489408, 'steps': 2548, 'loss/train': 0.5375320315361023} 08/30/2021 13:40:30 - INFO - __main__ - Step 2550: {'lr': 0.0004999830243621553, 'samples': 489600, 'steps': 2549, 'loss/train': 3.567222833633423} 08/30/2021 13:40:30 - INFO - __main__ - Step 2551: {'lr': 0.0004999829624645037, 'samples': 489792, 'steps': 2550, 'loss/train': 3.402311086654663} 08/30/2021 13:40:31 - INFO - __main__ - Step 2552: {'lr': 0.0004999829004542136, 'samples': 489984, 'steps': 2551, 'loss/train': 3.234229803085327} 08/30/2021 13:40:31 - INFO - __main__ - Step 2553: {'lr': 0.0004999828383312851, 'samples': 490176, 'steps': 2552, 'loss/train': 2.6774160861968994} 08/30/2021 13:40:32 - INFO - __main__ - Step 2554: {'lr': 0.0004999827760957182, 'samples': 490368, 'steps': 2553, 'loss/train': 2.777254581451416} 08/30/2021 13:40:33 - INFO - __main__ - Step 2555: {'lr': 0.000499982713747513, 'samples': 490560, 'steps': 2554, 'loss/train': 3.821315050125122} 08/30/2021 13:40:33 - INFO - __main__ - Step 2556: {'lr': 0.0004999826512866693, 'samples': 490752, 'steps': 2555, 'loss/train': 3.441488265991211} 08/30/2021 13:40:34 - INFO - __main__ - Step 2557: {'lr': 0.0004999825887131874, 'samples': 490944, 'steps': 2556, 'loss/train': 3.2371251583099365} 08/30/2021 13:40:34 - INFO - __main__ - Step 2558: {'lr': 0.0004999825260270671, 'samples': 491136, 'steps': 2557, 'loss/train': 3.3055927753448486} 08/30/2021 13:40:35 - INFO - __main__ - Step 2559: {'lr': 0.0004999824632283086, 'samples': 491328, 'steps': 2558, 'loss/train': 2.9721972942352295} 08/30/2021 13:40:36 - INFO - __main__ - Step 2560: {'lr': 0.0004999824003169119, 'samples': 491520, 'steps': 2559, 'loss/train': 3.119234085083008} 08/30/2021 13:40:36 - INFO - __main__ - Step 2561: {'lr': 0.000499982337292877, 'samples': 491712, 'steps': 2560, 'loss/train': 3.087674617767334} 08/30/2021 13:40:37 - INFO - __main__ - Step 2562: {'lr': 0.0004999822741562038, 'samples': 491904, 'steps': 2561, 'loss/train': 3.089181661605835} 08/30/2021 13:40:37 - INFO - __main__ - Step 2563: {'lr': 0.0004999822109068925, 'samples': 492096, 'steps': 2562, 'loss/train': 3.475480079650879} 08/30/2021 13:40:38 - INFO - __main__ - Step 2564: {'lr': 0.000499982147544943, 'samples': 492288, 'steps': 2563, 'loss/train': 3.0615687370300293} 08/30/2021 13:40:39 - INFO - __main__ - Step 2565: {'lr': 0.0004999820840703554, 'samples': 492480, 'steps': 2564, 'loss/train': 3.29472279548645} 08/30/2021 13:40:39 - INFO - __main__ - Step 2566: {'lr': 0.0004999820204831298, 'samples': 492672, 'steps': 2565, 'loss/train': 3.4640440940856934} 08/30/2021 13:40:40 - INFO - __main__ - Step 2567: {'lr': 0.0004999819567832661, 'samples': 492864, 'steps': 2566, 'loss/train': 2.8388006687164307} 08/30/2021 13:40:40 - INFO - __main__ - Step 2568: {'lr': 0.0004999818929707645, 'samples': 493056, 'steps': 2567, 'loss/train': 2.959890365600586} 08/30/2021 13:40:41 - INFO - __main__ - Step 2569: {'lr': 0.0004999818290456249, 'samples': 493248, 'steps': 2568, 'loss/train': 2.944700241088867} 08/30/2021 13:40:42 - INFO - __main__ - Step 2570: {'lr': 0.0004999817650078474, 'samples': 493440, 'steps': 2569, 'loss/train': 3.516746997833252} 08/30/2021 13:40:42 - INFO - __main__ - Step 2571: {'lr': 0.0004999817008574318, 'samples': 493632, 'steps': 2570, 'loss/train': 3.095552921295166} 08/30/2021 13:40:43 - INFO - __main__ - Step 2572: {'lr': 0.0004999816365943784, 'samples': 493824, 'steps': 2571, 'loss/train': 2.8601486682891846} 08/30/2021 13:40:43 - INFO - __main__ - Step 2573: {'lr': 0.000499981572218687, 'samples': 494016, 'steps': 2572, 'loss/train': 4.528290271759033} 08/30/2021 13:40:43 - INFO - __main__ - Step 2574: {'lr': 0.0004999815077303579, 'samples': 494208, 'steps': 2573, 'loss/train': 2.300426721572876} 08/30/2021 13:40:45 - INFO - __main__ - Step 2575: {'lr': 0.000499981443129391, 'samples': 494400, 'steps': 2574, 'loss/train': 3.0739119052886963} 08/30/2021 13:40:45 - INFO - __main__ - Step 2576: {'lr': 0.0004999813784157863, 'samples': 494592, 'steps': 2575, 'loss/train': 3.223848581314087} 08/30/2021 13:40:46 - INFO - __main__ - Step 2577: {'lr': 0.0004999813135895438, 'samples': 494784, 'steps': 2576, 'loss/train': 2.8425159454345703} 08/30/2021 13:40:46 - INFO - __main__ - Step 2578: {'lr': 0.0004999812486506637, 'samples': 494976, 'steps': 2577, 'loss/train': 2.773549795150757} 08/30/2021 13:40:46 - INFO - __main__ - Step 2579: {'lr': 0.0004999811835991457, 'samples': 495168, 'steps': 2578, 'loss/train': 2.3618130683898926} 08/30/2021 13:40:48 - INFO - __main__ - Step 2580: {'lr': 0.0004999811184349902, 'samples': 495360, 'steps': 2579, 'loss/train': 3.067438840866089} 08/30/2021 13:40:48 - INFO - __main__ - Step 2581: {'lr': 0.000499981053158197, 'samples': 495552, 'steps': 2580, 'loss/train': 3.2529942989349365} 08/30/2021 13:40:49 - INFO - __main__ - Step 2582: {'lr': 0.0004999809877687662, 'samples': 495744, 'steps': 2581, 'loss/train': 3.515986204147339} 08/30/2021 13:40:49 - INFO - __main__ - Step 2583: {'lr': 0.0004999809222666978, 'samples': 495936, 'steps': 2582, 'loss/train': 2.9327030181884766} 08/30/2021 13:40:49 - INFO - __main__ - Step 2584: {'lr': 0.0004999808566519919, 'samples': 496128, 'steps': 2583, 'loss/train': 3.3252201080322266} 08/30/2021 13:40:51 - INFO - __main__ - Step 2585: {'lr': 0.0004999807909246485, 'samples': 496320, 'steps': 2584, 'loss/train': 1.8364979028701782} 08/30/2021 13:40:51 - INFO - __main__ - Step 2586: {'lr': 0.0004999807250846676, 'samples': 496512, 'steps': 2585, 'loss/train': 3.141077756881714} 08/30/2021 13:40:52 - INFO - __main__ - Step 2587: {'lr': 0.0004999806591320492, 'samples': 496704, 'steps': 2586, 'loss/train': 3.338092088699341} 08/30/2021 13:40:52 - INFO - __main__ - Step 2588: {'lr': 0.0004999805930667934, 'samples': 496896, 'steps': 2587, 'loss/train': 3.1431477069854736} 08/30/2021 13:40:52 - INFO - __main__ - Step 2589: {'lr': 0.0004999805268889003, 'samples': 497088, 'steps': 2588, 'loss/train': 2.8831489086151123} 08/30/2021 13:40:54 - INFO - __main__ - Step 2590: {'lr': 0.0004999804605983697, 'samples': 497280, 'steps': 2589, 'loss/train': 2.7750606536865234} 08/30/2021 13:40:55 - INFO - __main__ - Step 2591: {'lr': 0.0004999803941952018, 'samples': 497472, 'steps': 2590, 'loss/train': 3.2433807849884033} 08/30/2021 13:40:55 - INFO - __main__ - Step 2592: {'lr': 0.0004999803276793965, 'samples': 497664, 'steps': 2591, 'loss/train': 3.106518268585205} 08/30/2021 13:40:56 - INFO - __main__ - Step 2593: {'lr': 0.0004999802610509541, 'samples': 497856, 'steps': 2592, 'loss/train': 2.863128900527954} 08/30/2021 13:40:56 - INFO - __main__ - Step 2594: {'lr': 0.0004999801943098743, 'samples': 498048, 'steps': 2593, 'loss/train': 3.7802350521087646} 08/30/2021 13:40:58 - INFO - __main__ - Step 2595: {'lr': 0.0004999801274561573, 'samples': 498240, 'steps': 2594, 'loss/train': 3.056262254714966} 08/30/2021 13:40:58 - INFO - __main__ - Step 2596: {'lr': 0.0004999800604898032, 'samples': 498432, 'steps': 2595, 'loss/train': 3.5432939529418945} 08/30/2021 13:40:58 - INFO - __main__ - Step 2597: {'lr': 0.000499979993410812, 'samples': 498624, 'steps': 2596, 'loss/train': 3.2634787559509277} 08/30/2021 13:40:59 - INFO - __main__ - Step 2598: {'lr': 0.0004999799262191835, 'samples': 498816, 'steps': 2597, 'loss/train': 0.46490105986595154} 08/30/2021 13:40:59 - INFO - __main__ - Step 2599: {'lr': 0.0004999798589149179, 'samples': 499008, 'steps': 2598, 'loss/train': 0.9940352439880371} 08/30/2021 13:41:01 - INFO - __main__ - Step 2600: {'lr': 0.0004999797914980154, 'samples': 499200, 'steps': 2599, 'loss/train': 3.4254579544067383} 08/30/2021 13:41:01 - INFO - __main__ - Step 2601: {'lr': 0.0004999797239684757, 'samples': 499392, 'steps': 2600, 'loss/train': 3.204349994659424} 08/30/2021 13:41:01 - INFO - __main__ - Step 2602: {'lr': 0.0004999796563262991, 'samples': 499584, 'steps': 2601, 'loss/train': 3.2098374366760254} 08/30/2021 13:41:02 - INFO - __main__ - Step 2603: {'lr': 0.0004999795885714855, 'samples': 499776, 'steps': 2602, 'loss/train': 3.2374396324157715} 08/30/2021 13:41:02 - INFO - __main__ - Step 2604: {'lr': 0.0004999795207040349, 'samples': 499968, 'steps': 2603, 'loss/train': 2.9048542976379395} 08/30/2021 13:41:02 - INFO - __main__ - Step 2605: {'lr': 0.0004999794527239474, 'samples': 500160, 'steps': 2604, 'loss/train': 1.4519882202148438} 08/30/2021 13:41:04 - INFO - __main__ - Step 2606: {'lr': 0.000499979384631223, 'samples': 500352, 'steps': 2605, 'loss/train': 3.092986583709717} 08/30/2021 13:41:05 - INFO - __main__ - Step 2607: {'lr': 0.000499979316425862, 'samples': 500544, 'steps': 2606, 'loss/train': 3.087824821472168} 08/30/2021 13:41:05 - INFO - __main__ - Step 2608: {'lr': 0.0004999792481078639, 'samples': 500736, 'steps': 2607, 'loss/train': 0.5084215998649597} 08/30/2021 13:41:05 - INFO - __main__ - Step 2609: {'lr': 0.000499979179677229, 'samples': 500928, 'steps': 2608, 'loss/train': 2.7436444759368896} 08/30/2021 13:41:06 - INFO - __main__ - Step 2610: {'lr': 0.0004999791111339574, 'samples': 501120, 'steps': 2609, 'loss/train': 2.876444101333618} 08/30/2021 13:41:07 - INFO - __main__ - Step 2611: {'lr': 0.0004999790424780492, 'samples': 501312, 'steps': 2610, 'loss/train': 3.3328187465667725} 08/30/2021 13:41:08 - INFO - __main__ - Step 2612: {'lr': 0.0004999789737095041, 'samples': 501504, 'steps': 2611, 'loss/train': 3.361556053161621} 08/30/2021 13:41:08 - INFO - __main__ - Step 2613: {'lr': 0.0004999789048283224, 'samples': 501696, 'steps': 2612, 'loss/train': 2.887472152709961} 08/30/2021 13:41:08 - INFO - __main__ - Step 2614: {'lr': 0.0004999788358345041, 'samples': 501888, 'steps': 2613, 'loss/train': 3.410672903060913} 08/30/2021 13:41:09 - INFO - __main__ - Step 2615: {'lr': 0.0004999787667280492, 'samples': 502080, 'steps': 2614, 'loss/train': 3.250086784362793} 08/30/2021 13:41:10 - INFO - __main__ - Step 2616: {'lr': 0.0004999786975089577, 'samples': 502272, 'steps': 2615, 'loss/train': 3.8277294635772705} 08/30/2021 13:41:11 - INFO - __main__ - Step 2617: {'lr': 0.0004999786281772296, 'samples': 502464, 'steps': 2616, 'loss/train': 2.623059034347534} 08/30/2021 13:41:11 - INFO - __main__ - Step 2618: {'lr': 0.0004999785587328651, 'samples': 502656, 'steps': 2617, 'loss/train': 2.9890518188476562} 08/30/2021 13:41:11 - INFO - __main__ - Step 2619: {'lr': 0.0004999784891758641, 'samples': 502848, 'steps': 2618, 'loss/train': 3.5353376865386963} 08/30/2021 13:41:12 - INFO - __main__ - Step 2620: {'lr': 0.0004999784195062266, 'samples': 503040, 'steps': 2619, 'loss/train': 3.4909520149230957} 08/30/2021 13:41:13 - INFO - __main__ - Step 2621: {'lr': 0.0004999783497239526, 'samples': 503232, 'steps': 2620, 'loss/train': 3.193816661834717} 08/30/2021 13:41:13 - INFO - __main__ - Step 2622: {'lr': 0.0004999782798290424, 'samples': 503424, 'steps': 2621, 'loss/train': 3.023629903793335} 08/30/2021 13:41:14 - INFO - __main__ - Step 2623: {'lr': 0.0004999782098214957, 'samples': 503616, 'steps': 2622, 'loss/train': 2.9927542209625244} 08/30/2021 13:41:14 - INFO - __main__ - Step 2624: {'lr': 0.0004999781397013127, 'samples': 503808, 'steps': 2623, 'loss/train': 3.0726561546325684} 08/30/2021 13:41:14 - INFO - __main__ - Step 2625: {'lr': 0.0004999780694684934, 'samples': 504000, 'steps': 2624, 'loss/train': 3.3661868572235107} 08/30/2021 13:41:16 - INFO - __main__ - Step 2626: {'lr': 0.000499977999123038, 'samples': 504192, 'steps': 2625, 'loss/train': 3.088892698287964} 08/30/2021 13:41:16 - INFO - __main__ - Step 2627: {'lr': 0.0004999779286649461, 'samples': 504384, 'steps': 2626, 'loss/train': 2.8224613666534424} 08/30/2021 13:41:17 - INFO - __main__ - Step 2628: {'lr': 0.0004999778580942183, 'samples': 504576, 'steps': 2627, 'loss/train': 3.0479722023010254} 08/30/2021 13:41:17 - INFO - __main__ - Step 2629: {'lr': 0.000499977787410854, 'samples': 504768, 'steps': 2628, 'loss/train': 2.738128900527954} 08/30/2021 13:41:17 - INFO - __main__ - Step 2630: {'lr': 0.0004999777166148539, 'samples': 504960, 'steps': 2629, 'loss/train': 3.167553186416626} 08/30/2021 13:41:19 - INFO - __main__ - Step 2631: {'lr': 0.0004999776457062175, 'samples': 505152, 'steps': 2630, 'loss/train': 3.0850493907928467} 08/30/2021 13:41:19 - INFO - __main__ - Step 2632: {'lr': 0.0004999775746849451, 'samples': 505344, 'steps': 2631, 'loss/train': 2.834916353225708} 08/30/2021 13:41:20 - INFO - __main__ - Step 2633: {'lr': 0.0004999775035510367, 'samples': 505536, 'steps': 2632, 'loss/train': 3.749802827835083} 08/30/2021 13:41:20 - INFO - __main__ - Step 2634: {'lr': 0.0004999774323044922, 'samples': 505728, 'steps': 2633, 'loss/train': 0.6642865538597107} 08/30/2021 13:41:21 - INFO - __main__ - Step 2635: {'lr': 0.0004999773609453118, 'samples': 505920, 'steps': 2634, 'loss/train': 3.4033918380737305} 08/30/2021 13:41:22 - INFO - __main__ - Step 2636: {'lr': 0.0004999772894734954, 'samples': 506112, 'steps': 2635, 'loss/train': 2.8993465900421143} 08/30/2021 13:41:22 - INFO - __main__ - Step 2637: {'lr': 0.000499977217889043, 'samples': 506304, 'steps': 2636, 'loss/train': 2.7557549476623535} 08/30/2021 13:41:23 - INFO - __main__ - Step 2638: {'lr': 0.0004999771461919549, 'samples': 506496, 'steps': 2637, 'loss/train': 2.9272453784942627} 08/30/2021 13:41:23 - INFO - __main__ - Step 2639: {'lr': 0.0004999770743822309, 'samples': 506688, 'steps': 2638, 'loss/train': 3.2562336921691895} 08/30/2021 13:41:24 - INFO - __main__ - Step 2640: {'lr': 0.0004999770024598711, 'samples': 506880, 'steps': 2639, 'loss/train': 0.7742186784744263} 08/30/2021 13:41:26 - INFO - __main__ - Step 2641: {'lr': 0.0004999769304248754, 'samples': 507072, 'steps': 2640, 'loss/train': 3.7892870903015137} 08/30/2021 13:41:26 - INFO - __main__ - Step 2642: {'lr': 0.0004999768582772442, 'samples': 507264, 'steps': 2641, 'loss/train': 2.8323965072631836} 08/30/2021 13:41:27 - INFO - __main__ - Step 2643: {'lr': 0.000499976786016977, 'samples': 507456, 'steps': 2642, 'loss/train': 3.3806533813476562} 08/30/2021 13:41:27 - INFO - __main__ - Step 2644: {'lr': 0.0004999767136440742, 'samples': 507648, 'steps': 2643, 'loss/train': 0.9227195978164673} 08/30/2021 13:41:27 - INFO - __main__ - Step 2645: {'lr': 0.0004999766411585359, 'samples': 507840, 'steps': 2644, 'loss/train': 2.237401008605957} 08/30/2021 13:41:29 - INFO - __main__ - Step 2646: {'lr': 0.0004999765685603618, 'samples': 508032, 'steps': 2645, 'loss/train': 3.269773483276367} 08/30/2021 13:41:29 - INFO - __main__ - Step 2647: {'lr': 0.0004999764958495522, 'samples': 508224, 'steps': 2646, 'loss/train': 2.6229805946350098} 08/30/2021 13:41:30 - INFO - __main__ - Step 2648: {'lr': 0.0004999764230261072, 'samples': 508416, 'steps': 2647, 'loss/train': 2.917896270751953} 08/30/2021 13:41:30 - INFO - __main__ - Step 2649: {'lr': 0.0004999763500900265, 'samples': 508608, 'steps': 2648, 'loss/train': 3.118557929992676} 08/30/2021 13:41:30 - INFO - __main__ - Step 2650: {'lr': 0.0004999762770413103, 'samples': 508800, 'steps': 2649, 'loss/train': 3.798842191696167} 08/30/2021 13:41:32 - INFO - __main__ - Step 2651: {'lr': 0.0004999762038799587, 'samples': 508992, 'steps': 2650, 'loss/train': 3.517812967300415} 08/30/2021 13:41:32 - INFO - __main__ - Step 2652: {'lr': 0.0004999761306059717, 'samples': 509184, 'steps': 2651, 'loss/train': 3.0383710861206055} 08/30/2021 13:41:33 - INFO - __main__ - Step 2653: {'lr': 0.0004999760572193492, 'samples': 509376, 'steps': 2652, 'loss/train': 3.0678305625915527} 08/30/2021 13:41:33 - INFO - __main__ - Step 2654: {'lr': 0.0004999759837200914, 'samples': 509568, 'steps': 2653, 'loss/train': 2.7814712524414062} 08/30/2021 13:41:33 - INFO - __main__ - Step 2655: {'lr': 0.0004999759101081984, 'samples': 509760, 'steps': 2654, 'loss/train': 1.8292951583862305} 08/30/2021 13:41:34 - INFO - __main__ - Step 2656: {'lr': 0.0004999758363836701, 'samples': 509952, 'steps': 2655, 'loss/train': 3.360480546951294} 08/30/2021 13:41:35 - INFO - __main__ - Step 2657: {'lr': 0.0004999757625465063, 'samples': 510144, 'steps': 2656, 'loss/train': 3.593045234680176} 08/30/2021 13:41:36 - INFO - __main__ - Step 2658: {'lr': 0.0004999756885967075, 'samples': 510336, 'steps': 2657, 'loss/train': 3.1107137203216553} 08/30/2021 13:41:36 - INFO - __main__ - Step 2659: {'lr': 0.0004999756145342735, 'samples': 510528, 'steps': 2658, 'loss/train': 3.030609130859375} 08/30/2021 13:41:36 - INFO - __main__ - Step 2660: {'lr': 0.0004999755403592043, 'samples': 510720, 'steps': 2659, 'loss/train': 2.3007168769836426} 08/30/2021 13:41:37 - INFO - __main__ - Step 2661: {'lr': 0.0004999754660714999, 'samples': 510912, 'steps': 2660, 'loss/train': 2.849210262298584} 08/30/2021 13:41:38 - INFO - __main__ - Step 2662: {'lr': 0.0004999753916711606, 'samples': 511104, 'steps': 2661, 'loss/train': 3.5313100814819336} 08/30/2021 13:41:39 - INFO - __main__ - Step 2663: {'lr': 0.0004999753171581862, 'samples': 511296, 'steps': 2662, 'loss/train': 2.643601417541504} 08/30/2021 13:41:39 - INFO - __main__ - Step 2664: {'lr': 0.0004999752425325766, 'samples': 511488, 'steps': 2663, 'loss/train': 2.52886962890625} 08/30/2021 13:41:40 - INFO - __main__ - Step 2665: {'lr': 0.0004999751677943322, 'samples': 511680, 'steps': 2664, 'loss/train': 2.724182605743408} 08/30/2021 13:41:40 - INFO - __main__ - Step 2666: {'lr': 0.0004999750929434527, 'samples': 511872, 'steps': 2665, 'loss/train': 2.8596858978271484} 08/30/2021 13:41:42 - INFO - __main__ - Step 2667: {'lr': 0.0004999750179799383, 'samples': 512064, 'steps': 2666, 'loss/train': 2.4448113441467285} 08/30/2021 13:41:42 - INFO - __main__ - Step 2668: {'lr': 0.0004999749429037892, 'samples': 512256, 'steps': 2667, 'loss/train': 3.639150381088257} 08/30/2021 13:41:43 - INFO - __main__ - Step 2669: {'lr': 0.0004999748677150051, 'samples': 512448, 'steps': 2668, 'loss/train': 3.338671922683716} 08/30/2021 13:41:43 - INFO - __main__ - Step 2670: {'lr': 0.0004999747924135862, 'samples': 512640, 'steps': 2669, 'loss/train': 3.118865728378296} 08/30/2021 13:41:43 - INFO - __main__ - Step 2671: {'lr': 0.0004999747169995325, 'samples': 512832, 'steps': 2670, 'loss/train': 3.4766738414764404} 08/30/2021 13:41:44 - INFO - __main__ - Step 2672: {'lr': 0.0004999746414728441, 'samples': 513024, 'steps': 2671, 'loss/train': 1.7491579055786133} 08/30/2021 13:41:45 - INFO - __main__ - Step 2673: {'lr': 0.0004999745658335209, 'samples': 513216, 'steps': 2672, 'loss/train': 3.3436026573181152} 08/30/2021 13:41:46 - INFO - __main__ - Step 2674: {'lr': 0.000499974490081563, 'samples': 513408, 'steps': 2673, 'loss/train': 2.8469934463500977} 08/30/2021 13:41:46 - INFO - __main__ - Step 2675: {'lr': 0.0004999744142169707, 'samples': 513600, 'steps': 2674, 'loss/train': 2.5629703998565674} 08/30/2021 13:41:46 - INFO - __main__ - Step 2676: {'lr': 0.0004999743382397435, 'samples': 513792, 'steps': 2675, 'loss/train': 2.840324640274048} 08/30/2021 13:41:47 - INFO - __main__ - Step 2677: {'lr': 0.0004999742621498818, 'samples': 513984, 'steps': 2676, 'loss/train': 3.09045147895813} 08/30/2021 13:41:48 - INFO - __main__ - Step 2678: {'lr': 0.0004999741859473857, 'samples': 514176, 'steps': 2677, 'loss/train': 2.6620028018951416} 08/30/2021 13:41:49 - INFO - __main__ - Step 2679: {'lr': 0.0004999741096322549, 'samples': 514368, 'steps': 2678, 'loss/train': 2.8295633792877197} 08/30/2021 13:41:49 - INFO - __main__ - Step 2680: {'lr': 0.0004999740332044898, 'samples': 514560, 'steps': 2679, 'loss/train': 3.2034780979156494} 08/30/2021 13:41:49 - INFO - __main__ - Step 2681: {'lr': 0.0004999739566640901, 'samples': 514752, 'steps': 2680, 'loss/train': 3.100248336791992} 08/30/2021 13:41:50 - INFO - __main__ - Step 2682: {'lr': 0.000499973880011056, 'samples': 514944, 'steps': 2681, 'loss/train': 2.816262722015381} 08/30/2021 13:41:50 - INFO - __main__ - Step 2683: {'lr': 0.0004999738032453876, 'samples': 515136, 'steps': 2682, 'loss/train': 2.5822339057922363} 08/30/2021 13:41:51 - INFO - __main__ - Step 2684: {'lr': 0.0004999737263670848, 'samples': 515328, 'steps': 2683, 'loss/train': 3.399911642074585} 08/30/2021 13:41:52 - INFO - __main__ - Step 2685: {'lr': 0.0004999736493761477, 'samples': 515520, 'steps': 2684, 'loss/train': 3.240802764892578} 08/30/2021 13:41:52 - INFO - __main__ - Step 2686: {'lr': 0.0004999735722725765, 'samples': 515712, 'steps': 2685, 'loss/train': 1.476607322692871} 08/30/2021 13:41:53 - INFO - __main__ - Step 2687: {'lr': 0.0004999734950563709, 'samples': 515904, 'steps': 2686, 'loss/train': 3.037910223007202} 08/30/2021 13:41:53 - INFO - __main__ - Step 2688: {'lr': 0.0004999734177275311, 'samples': 516096, 'steps': 2687, 'loss/train': 1.8880975246429443} 08/30/2021 13:41:54 - INFO - __main__ - Step 2689: {'lr': 0.0004999733402860572, 'samples': 516288, 'steps': 2688, 'loss/train': 3.124321699142456} 08/30/2021 13:41:55 - INFO - __main__ - Step 2690: {'lr': 0.0004999732627319491, 'samples': 516480, 'steps': 2689, 'loss/train': 3.036329984664917} 08/30/2021 13:41:55 - INFO - __main__ - Step 2691: {'lr': 0.000499973185065207, 'samples': 516672, 'steps': 2690, 'loss/train': 3.331474781036377} 08/30/2021 13:41:56 - INFO - __main__ - Step 2692: {'lr': 0.0004999731072858307, 'samples': 516864, 'steps': 2691, 'loss/train': 2.3075766563415527} 08/30/2021 13:41:56 - INFO - __main__ - Step 2693: {'lr': 0.0004999730293938205, 'samples': 517056, 'steps': 2692, 'loss/train': 3.0612525939941406} 08/30/2021 13:41:58 - INFO - __main__ - Step 2694: {'lr': 0.0004999729513891762, 'samples': 517248, 'steps': 2693, 'loss/train': 3.400170087814331} 08/30/2021 13:41:59 - INFO - __main__ - Step 2695: {'lr': 0.000499972873271898, 'samples': 517440, 'steps': 2694, 'loss/train': 3.0846455097198486} 08/30/2021 13:41:59 - INFO - __main__ - Step 2696: {'lr': 0.0004999727950419859, 'samples': 517632, 'steps': 2695, 'loss/train': 0.9213229417800903} 08/30/2021 13:41:59 - INFO - __main__ - Step 2697: {'lr': 0.0004999727166994399, 'samples': 517824, 'steps': 2696, 'loss/train': 3.088224172592163} 08/30/2021 13:42:00 - INFO - __main__ - Step 2698: {'lr': 0.0004999726382442601, 'samples': 518016, 'steps': 2697, 'loss/train': 3.2991228103637695} 08/30/2021 13:42:01 - INFO - __main__ - Step 2699: {'lr': 0.0004999725596764465, 'samples': 518208, 'steps': 2698, 'loss/train': 2.712589979171753} 08/30/2021 13:42:02 - INFO - __main__ - Step 2700: {'lr': 0.000499972480995999, 'samples': 518400, 'steps': 2699, 'loss/train': 2.3636298179626465} 08/30/2021 13:42:02 - INFO - __main__ - Step 2701: {'lr': 0.0004999724022029179, 'samples': 518592, 'steps': 2700, 'loss/train': 2.9854085445404053} 08/30/2021 13:42:02 - INFO - __main__ - Step 2702: {'lr': 0.000499972323297203, 'samples': 518784, 'steps': 2701, 'loss/train': 2.5155811309814453} 08/30/2021 13:42:03 - INFO - __main__ - Step 2703: {'lr': 0.0004999722442788544, 'samples': 518976, 'steps': 2702, 'loss/train': 2.944446563720703} 08/30/2021 13:42:04 - INFO - __main__ - Step 2704: {'lr': 0.0004999721651478723, 'samples': 519168, 'steps': 2703, 'loss/train': 2.7215254306793213} 08/30/2021 13:42:05 - INFO - __main__ - Step 2705: {'lr': 0.0004999720859042565, 'samples': 519360, 'steps': 2704, 'loss/train': 3.0727028846740723} 08/30/2021 13:42:05 - INFO - __main__ - Step 2706: {'lr': 0.0004999720065480071, 'samples': 519552, 'steps': 2705, 'loss/train': 2.5038321018218994} 08/30/2021 13:42:06 - INFO - __main__ - Step 2707: {'lr': 0.0004999719270791242, 'samples': 519744, 'steps': 2706, 'loss/train': 2.4575345516204834} 08/30/2021 13:42:06 - INFO - __main__ - Step 2708: {'lr': 0.0004999718474976078, 'samples': 519936, 'steps': 2707, 'loss/train': 2.6038658618927} 08/30/2021 13:42:08 - INFO - __main__ - Step 2709: {'lr': 0.000499971767803458, 'samples': 520128, 'steps': 2708, 'loss/train': 2.9975969791412354} 08/30/2021 13:42:08 - INFO - __main__ - Step 2710: {'lr': 0.0004999716879966747, 'samples': 520320, 'steps': 2709, 'loss/train': 2.7358040809631348} 08/30/2021 13:42:08 - INFO - __main__ - Step 2711: {'lr': 0.000499971608077258, 'samples': 520512, 'steps': 2710, 'loss/train': 1.7337361574172974} 08/30/2021 13:42:09 - INFO - __main__ - Step 2712: {'lr': 0.000499971528045208, 'samples': 520704, 'steps': 2711, 'loss/train': 2.743546962738037} 08/30/2021 13:42:09 - INFO - __main__ - Step 2713: {'lr': 0.0004999714479005248, 'samples': 520896, 'steps': 2712, 'loss/train': 2.940654754638672} 08/30/2021 13:42:11 - INFO - __main__ - Step 2714: {'lr': 0.0004999713676432082, 'samples': 521088, 'steps': 2713, 'loss/train': 2.064807176589966} 08/30/2021 13:42:11 - INFO - __main__ - Step 2715: {'lr': 0.0004999712872732584, 'samples': 521280, 'steps': 2714, 'loss/train': 3.6759839057922363} 08/30/2021 13:42:12 - INFO - __main__ - Step 2716: {'lr': 0.0004999712067906754, 'samples': 521472, 'steps': 2715, 'loss/train': 2.991039514541626} 08/30/2021 13:42:12 - INFO - __main__ - Step 2717: {'lr': 0.0004999711261954591, 'samples': 521664, 'steps': 2716, 'loss/train': 2.042520046234131} 08/30/2021 13:42:12 - INFO - __main__ - Step 2718: {'lr': 0.0004999710454876099, 'samples': 521856, 'steps': 2717, 'loss/train': 2.5179977416992188} 08/30/2021 13:42:13 - INFO - __main__ - Step 2719: {'lr': 0.0004999709646671274, 'samples': 522048, 'steps': 2718, 'loss/train': 3.064622640609741} 08/30/2021 13:42:14 - INFO - __main__ - Step 2720: {'lr': 0.0004999708837340119, 'samples': 522240, 'steps': 2719, 'loss/train': 2.5993306636810303} 08/30/2021 13:42:15 - INFO - __main__ - Step 2721: {'lr': 0.0004999708026882635, 'samples': 522432, 'steps': 2720, 'loss/train': 2.747556209564209} 08/30/2021 13:42:15 - INFO - __main__ - Step 2722: {'lr': 0.000499970721529882, 'samples': 522624, 'steps': 2721, 'loss/train': 2.8838469982147217} 08/30/2021 13:42:15 - INFO - __main__ - Step 2723: {'lr': 0.0004999706402588675, 'samples': 522816, 'steps': 2722, 'loss/train': 3.420832633972168} 08/30/2021 13:42:16 - INFO - __main__ - Step 2724: {'lr': 0.0004999705588752202, 'samples': 523008, 'steps': 2723, 'loss/train': 1.2347540855407715} 08/30/2021 13:42:17 - INFO - __main__ - Step 2725: {'lr': 0.00049997047737894, 'samples': 523200, 'steps': 2724, 'loss/train': 3.2386176586151123} 08/30/2021 13:42:18 - INFO - __main__ - Step 2726: {'lr': 0.0004999703957700269, 'samples': 523392, 'steps': 2725, 'loss/train': 2.972571849822998} 08/30/2021 13:42:18 - INFO - __main__ - Step 2727: {'lr': 0.000499970314048481, 'samples': 523584, 'steps': 2726, 'loss/train': 2.3461365699768066} 08/30/2021 13:42:18 - INFO - __main__ - Step 2728: {'lr': 0.0004999702322143023, 'samples': 523776, 'steps': 2727, 'loss/train': 2.939415216445923} 08/30/2021 13:42:19 - INFO - __main__ - Step 2729: {'lr': 0.000499970150267491, 'samples': 523968, 'steps': 2728, 'loss/train': 2.949035406112671} 08/30/2021 13:42:21 - INFO - __main__ - Step 2730: {'lr': 0.0004999700682080469, 'samples': 524160, 'steps': 2729, 'loss/train': 2.9603052139282227} 08/30/2021 13:42:21 - INFO - __main__ - Step 2731: {'lr': 0.0004999699860359702, 'samples': 524352, 'steps': 2730, 'loss/train': 2.4228169918060303} 08/30/2021 13:42:21 - INFO - __main__ - Step 2732: {'lr': 0.0004999699037512608, 'samples': 524544, 'steps': 2731, 'loss/train': 3.20652174949646} 08/30/2021 13:42:22 - INFO - __main__ - Step 2733: {'lr': 0.000499969821353919, 'samples': 524736, 'steps': 2732, 'loss/train': 2.2140450477600098} 08/30/2021 13:42:22 - INFO - __main__ - Step 2734: {'lr': 0.0004999697388439444, 'samples': 524928, 'steps': 2733, 'loss/train': 3.1131787300109863} 08/30/2021 13:42:22 - INFO - __main__ - Step 2735: {'lr': 0.0004999696562213375, 'samples': 525120, 'steps': 2734, 'loss/train': 2.2171590328216553} 08/30/2021 13:42:24 - INFO - __main__ - Step 2736: {'lr': 0.0004999695734860981, 'samples': 525312, 'steps': 2735, 'loss/train': 3.1607298851013184} 08/30/2021 13:42:25 - INFO - __main__ - Step 2737: {'lr': 0.0004999694906382262, 'samples': 525504, 'steps': 2736, 'loss/train': 2.0003676414489746} 08/30/2021 13:42:25 - INFO - __main__ - Step 2738: {'lr': 0.0004999694076777219, 'samples': 525696, 'steps': 2737, 'loss/train': 2.778306722640991} 08/30/2021 13:42:25 - INFO - __main__ - Step 2739: {'lr': 0.0004999693246045854, 'samples': 525888, 'steps': 2738, 'loss/train': 2.8651514053344727} 08/30/2021 13:42:26 - INFO - __main__ - Step 2740: {'lr': 0.0004999692414188164, 'samples': 526080, 'steps': 2739, 'loss/train': 2.8148608207702637} 08/30/2021 13:42:27 - INFO - __main__ - Step 2741: {'lr': 0.0004999691581204152, 'samples': 526272, 'steps': 2740, 'loss/train': 2.772371292114258} 08/30/2021 13:42:28 - INFO - __main__ - Step 2742: {'lr': 0.0004999690747093816, 'samples': 526464, 'steps': 2741, 'loss/train': 2.3568027019500732} 08/30/2021 13:42:28 - INFO - __main__ - Step 2743: {'lr': 0.000499968991185716, 'samples': 526656, 'steps': 2742, 'loss/train': 2.353330373764038} 08/30/2021 13:42:28 - INFO - __main__ - Step 2744: {'lr': 0.0004999689075494182, 'samples': 526848, 'steps': 2743, 'loss/train': 3.9103636741638184} 08/30/2021 13:42:29 - INFO - __main__ - Step 2745: {'lr': 0.0004999688238004882, 'samples': 527040, 'steps': 2744, 'loss/train': 2.5432333946228027} 08/30/2021 13:42:30 - INFO - __main__ - Step 2746: {'lr': 0.0004999687399389262, 'samples': 527232, 'steps': 2745, 'loss/train': 3.0544979572296143} 08/30/2021 13:42:31 - INFO - __main__ - Step 2747: {'lr': 0.0004999686559647319, 'samples': 527424, 'steps': 2746, 'loss/train': 1.6781655550003052} 08/30/2021 13:42:31 - INFO - __main__ - Step 2748: {'lr': 0.0004999685718779058, 'samples': 527616, 'steps': 2747, 'loss/train': 2.2461705207824707} 08/30/2021 13:42:31 - INFO - __main__ - Step 2749: {'lr': 0.0004999684876784477, 'samples': 527808, 'steps': 2748, 'loss/train': 2.9054646492004395} 08/30/2021 13:42:32 - INFO - __main__ - Step 2750: {'lr': 0.0004999684033663576, 'samples': 528000, 'steps': 2749, 'loss/train': 2.8186492919921875} 08/30/2021 13:42:32 - INFO - __main__ - Step 2751: {'lr': 0.0004999683189416356, 'samples': 528192, 'steps': 2750, 'loss/train': 3.3227179050445557} 08/30/2021 13:42:35 - INFO - __main__ - Step 2752: {'lr': 0.0004999682344042817, 'samples': 528384, 'steps': 2751, 'loss/train': 1.0305490493774414} 08/30/2021 13:42:35 - INFO - __main__ - Step 2753: {'lr': 0.000499968149754296, 'samples': 528576, 'steps': 2752, 'loss/train': 2.0445303916931152} 08/30/2021 13:42:35 - INFO - __main__ - Step 2754: {'lr': 0.0004999680649916786, 'samples': 528768, 'steps': 2753, 'loss/train': 2.7636899948120117} 08/30/2021 13:42:36 - INFO - __main__ - Step 2755: {'lr': 0.0004999679801164295, 'samples': 528960, 'steps': 2754, 'loss/train': 0.5936917066574097} 08/30/2021 13:42:36 - INFO - __main__ - Step 2756: {'lr': 0.0004999678951285485, 'samples': 529152, 'steps': 2755, 'loss/train': 2.809025764465332} 08/30/2021 13:42:37 - INFO - __main__ - Step 2757: {'lr': 0.0004999678100280358, 'samples': 529344, 'steps': 2756, 'loss/train': 2.439009189605713} 08/30/2021 13:42:38 - INFO - __main__ - Step 2758: {'lr': 0.0004999677248148916, 'samples': 529536, 'steps': 2757, 'loss/train': 2.985081672668457} 08/30/2021 13:42:38 - INFO - __main__ - Step 2759: {'lr': 0.0004999676394891158, 'samples': 529728, 'steps': 2758, 'loss/train': 2.110480546951294} 08/30/2021 13:42:39 - INFO - __main__ - Step 2760: {'lr': 0.0004999675540507083, 'samples': 529920, 'steps': 2759, 'loss/train': 3.4083094596862793} 08/30/2021 13:42:39 - INFO - __main__ - Step 2761: {'lr': 0.0004999674684996694, 'samples': 530112, 'steps': 2760, 'loss/train': 3.2949750423431396} 08/30/2021 13:42:41 - INFO - __main__ - Step 2762: {'lr': 0.0004999673828359989, 'samples': 530304, 'steps': 2761, 'loss/train': 2.825989246368408} 08/30/2021 13:42:41 - INFO - __main__ - Step 2763: {'lr': 0.0004999672970596971, 'samples': 530496, 'steps': 2762, 'loss/train': 2.7158119678497314} 08/30/2021 13:42:41 - INFO - __main__ - Step 2764: {'lr': 0.0004999672111707639, 'samples': 530688, 'steps': 2763, 'loss/train': 2.3397819995880127} 08/30/2021 13:42:42 - INFO - __main__ - Step 2765: {'lr': 0.0004999671251691991, 'samples': 530880, 'steps': 2764, 'loss/train': 3.135607957839966} 08/30/2021 13:42:42 - INFO - __main__ - Step 2766: {'lr': 0.0004999670390550032, 'samples': 531072, 'steps': 2765, 'loss/train': 3.184204339981079} 08/30/2021 13:42:44 - INFO - __main__ - Step 2767: {'lr': 0.000499966952828176, 'samples': 531264, 'steps': 2766, 'loss/train': 1.9256181716918945} 08/30/2021 13:42:44 - INFO - __main__ - Step 2768: {'lr': 0.0004999668664887175, 'samples': 531456, 'steps': 2767, 'loss/train': 2.995103597640991} 08/30/2021 13:42:44 - INFO - __main__ - Step 2769: {'lr': 0.0004999667800366278, 'samples': 531648, 'steps': 2768, 'loss/train': 3.041548252105713} 08/30/2021 13:42:45 - INFO - __main__ - Step 2770: {'lr': 0.0004999666934719069, 'samples': 531840, 'steps': 2769, 'loss/train': 0.5235479474067688} 08/30/2021 13:42:45 - INFO - __main__ - Step 2771: {'lr': 0.0004999666067945548, 'samples': 532032, 'steps': 2770, 'loss/train': 2.7310903072357178} 08/30/2021 13:42:47 - INFO - __main__ - Step 2772: {'lr': 0.0004999665200045716, 'samples': 532224, 'steps': 2771, 'loss/train': 3.507369041442871} 08/30/2021 13:42:47 - INFO - __main__ - Step 2773: {'lr': 0.0004999664331019574, 'samples': 532416, 'steps': 2772, 'loss/train': 3.7877254486083984} 08/30/2021 13:42:47 - INFO - __main__ - Step 2774: {'lr': 0.0004999663460867123, 'samples': 532608, 'steps': 2773, 'loss/train': 3.072702169418335} 08/30/2021 13:42:48 - INFO - __main__ - Step 2775: {'lr': 0.000499966258958836, 'samples': 532800, 'steps': 2774, 'loss/train': 2.467533826828003} 08/30/2021 13:42:48 - INFO - __main__ - Step 2776: {'lr': 0.000499966171718329, 'samples': 532992, 'steps': 2775, 'loss/train': 2.8478052616119385} 08/30/2021 13:42:50 - INFO - __main__ - Step 2777: {'lr': 0.000499966084365191, 'samples': 533184, 'steps': 2776, 'loss/train': 2.8935816287994385} 08/30/2021 13:42:50 - INFO - __main__ - Step 2778: {'lr': 0.0004999659968994221, 'samples': 533376, 'steps': 2777, 'loss/train': 2.1907730102539062} 08/30/2021 13:42:51 - INFO - __main__ - Step 2779: {'lr': 0.0004999659093210223, 'samples': 533568, 'steps': 2778, 'loss/train': 2.685602903366089} 08/30/2021 13:42:51 - INFO - __main__ - Step 2780: {'lr': 0.0004999658216299919, 'samples': 533760, 'steps': 2779, 'loss/train': 2.8193023204803467} 08/30/2021 13:42:51 - INFO - __main__ - Step 2781: {'lr': 0.0004999657338263308, 'samples': 533952, 'steps': 2780, 'loss/train': 3.0136878490448} 08/30/2021 13:42:52 - INFO - __main__ - Step 2782: {'lr': 0.0004999656459100388, 'samples': 534144, 'steps': 2781, 'loss/train': 2.5547780990600586} 08/30/2021 13:42:53 - INFO - __main__ - Step 2783: {'lr': 0.0004999655578811161, 'samples': 534336, 'steps': 2782, 'loss/train': 2.158917188644409} 08/30/2021 13:42:54 - INFO - __main__ - Step 2784: {'lr': 0.0004999654697395629, 'samples': 534528, 'steps': 2783, 'loss/train': 3.0252928733825684} 08/30/2021 13:42:54 - INFO - __main__ - Step 2785: {'lr': 0.0004999653814853791, 'samples': 534720, 'steps': 2784, 'loss/train': 3.049435615539551} 08/30/2021 13:42:54 - INFO - __main__ - Step 2786: {'lr': 0.0004999652931185648, 'samples': 534912, 'steps': 2785, 'loss/train': 2.6159462928771973} 08/30/2021 13:42:55 - INFO - __main__ - Step 2787: {'lr': 0.00049996520463912, 'samples': 535104, 'steps': 2786, 'loss/train': 2.8965871334075928} 08/30/2021 13:42:56 - INFO - __main__ - Step 2788: {'lr': 0.0004999651160470447, 'samples': 535296, 'steps': 2787, 'loss/train': 2.8150036334991455} 08/30/2021 13:42:57 - INFO - __main__ - Step 2789: {'lr': 0.0004999650273423389, 'samples': 535488, 'steps': 2788, 'loss/train': 2.938845157623291} 08/30/2021 13:42:57 - INFO - __main__ - Step 2790: {'lr': 0.0004999649385250028, 'samples': 535680, 'steps': 2789, 'loss/train': 2.8934452533721924} 08/30/2021 13:42:57 - INFO - __main__ - Step 2791: {'lr': 0.0004999648495950363, 'samples': 535872, 'steps': 2790, 'loss/train': 2.1574251651763916} 08/30/2021 13:42:58 - INFO - __main__ - Step 2792: {'lr': 0.0004999647605524396, 'samples': 536064, 'steps': 2791, 'loss/train': 3.3665034770965576} 08/30/2021 13:42:59 - INFO - __main__ - Step 2793: {'lr': 0.0004999646713972126, 'samples': 536256, 'steps': 2792, 'loss/train': 2.7290778160095215} 08/30/2021 13:43:00 - INFO - __main__ - Step 2794: {'lr': 0.0004999645821293552, 'samples': 536448, 'steps': 2793, 'loss/train': 2.9117014408111572} 08/30/2021 13:43:00 - INFO - __main__ - Step 2795: {'lr': 0.0004999644927488678, 'samples': 536640, 'steps': 2794, 'loss/train': 2.8242461681365967} 08/30/2021 13:43:00 - INFO - __main__ - Step 2796: {'lr': 0.0004999644032557503, 'samples': 536832, 'steps': 2795, 'loss/train': 3.074611186981201} 08/30/2021 13:43:01 - INFO - __main__ - Step 2797: {'lr': 0.0004999643136500027, 'samples': 537024, 'steps': 2796, 'loss/train': 2.4186532497406006} 08/30/2021 13:43:02 - INFO - __main__ - Step 2798: {'lr': 0.0004999642239316249, 'samples': 537216, 'steps': 2797, 'loss/train': 3.6229336261749268} 08/30/2021 13:43:02 - INFO - __main__ - Step 2799: {'lr': 0.000499964134100617, 'samples': 537408, 'steps': 2798, 'loss/train': 3.04872465133667} 08/30/2021 13:43:03 - INFO - __main__ - Step 2800: {'lr': 0.0004999640441569793, 'samples': 537600, 'steps': 2799, 'loss/train': 2.990837574005127} 08/30/2021 13:43:03 - INFO - __main__ - Step 2801: {'lr': 0.0004999639541007116, 'samples': 537792, 'steps': 2800, 'loss/train': 2.8396661281585693} 08/30/2021 13:43:03 - INFO - __main__ - Step 2802: {'lr': 0.0004999638639318141, 'samples': 537984, 'steps': 2801, 'loss/train': 2.4867308139801025} 08/30/2021 13:43:05 - INFO - __main__ - Step 2803: {'lr': 0.0004999637736502866, 'samples': 538176, 'steps': 2802, 'loss/train': 3.2507901191711426} 08/30/2021 13:43:06 - INFO - __main__ - Step 2804: {'lr': 0.0004999636832561293, 'samples': 538368, 'steps': 2803, 'loss/train': 2.402642011642456} 08/30/2021 13:43:06 - INFO - __main__ - Step 2805: {'lr': 0.0004999635927493423, 'samples': 538560, 'steps': 2804, 'loss/train': 3.6187822818756104} 08/30/2021 13:43:07 - INFO - __main__ - Step 2806: {'lr': 0.0004999635021299255, 'samples': 538752, 'steps': 2805, 'loss/train': 2.5364692211151123} 08/30/2021 13:43:07 - INFO - __main__ - Step 2807: {'lr': 0.0004999634113978791, 'samples': 538944, 'steps': 2806, 'loss/train': 2.9410221576690674} 08/30/2021 13:43:09 - INFO - __main__ - Step 2808: {'lr': 0.0004999633205532029, 'samples': 539136, 'steps': 2807, 'loss/train': 3.006633996963501} 08/30/2021 13:43:09 - INFO - __main__ - Step 2809: {'lr': 0.0004999632295958972, 'samples': 539328, 'steps': 2808, 'loss/train': 2.751953363418579} 08/30/2021 13:43:09 - INFO - __main__ - Step 2810: {'lr': 0.0004999631385259617, 'samples': 539520, 'steps': 2809, 'loss/train': 1.81827712059021} 08/30/2021 13:43:10 - INFO - __main__ - Step 2811: {'lr': 0.000499963047343397, 'samples': 539712, 'steps': 2810, 'loss/train': 2.962376356124878} 08/30/2021 13:43:10 - INFO - __main__ - Step 2812: {'lr': 0.0004999629560482026, 'samples': 539904, 'steps': 2811, 'loss/train': 3.367459297180176} 08/30/2021 13:43:12 - INFO - __main__ - Step 2813: {'lr': 0.0004999628646403788, 'samples': 540096, 'steps': 2812, 'loss/train': 3.043518543243408} 08/30/2021 13:43:12 - INFO - __main__ - Step 2814: {'lr': 0.0004999627731199256, 'samples': 540288, 'steps': 2813, 'loss/train': 2.4826416969299316} 08/30/2021 13:43:12 - INFO - __main__ - Step 2815: {'lr': 0.0004999626814868429, 'samples': 540480, 'steps': 2814, 'loss/train': 2.8994929790496826} 08/30/2021 13:43:13 - INFO - __main__ - Step 2816: {'lr': 0.0004999625897411311, 'samples': 540672, 'steps': 2815, 'loss/train': 2.9685115814208984} 08/30/2021 13:43:13 - INFO - __main__ - Step 2817: {'lr': 0.0004999624978827899, 'samples': 540864, 'steps': 2816, 'loss/train': 3.080095052719116} 08/30/2021 13:43:13 - INFO - __main__ - Step 2818: {'lr': 0.0004999624059118194, 'samples': 541056, 'steps': 2817, 'loss/train': 2.7055742740631104} 08/30/2021 13:43:15 - INFO - __main__ - Step 2819: {'lr': 0.0004999623138282198, 'samples': 541248, 'steps': 2818, 'loss/train': 2.3578941822052} 08/30/2021 13:43:15 - INFO - __main__ - Step 2820: {'lr': 0.000499962221631991, 'samples': 541440, 'steps': 2819, 'loss/train': 2.7520699501037598} 08/30/2021 13:43:16 - INFO - __main__ - Step 2821: {'lr': 0.0004999621293231331, 'samples': 541632, 'steps': 2820, 'loss/train': 3.0708067417144775} 08/30/2021 13:43:16 - INFO - __main__ - Step 2822: {'lr': 0.0004999620369016461, 'samples': 541824, 'steps': 2821, 'loss/train': 2.742736339569092} 08/30/2021 13:43:16 - INFO - __main__ - Step 2823: {'lr': 0.00049996194436753, 'samples': 542016, 'steps': 2822, 'loss/train': 3.262277126312256} 08/30/2021 13:43:18 - INFO - __main__ - Step 2824: {'lr': 0.000499961851720785, 'samples': 542208, 'steps': 2823, 'loss/train': 2.1122236251831055} 08/30/2021 13:43:18 - INFO - __main__ - Step 2825: {'lr': 0.000499961758961411, 'samples': 542400, 'steps': 2824, 'loss/train': 3.081420660018921} 08/30/2021 13:43:19 - INFO - __main__ - Step 2826: {'lr': 0.0004999616660894081, 'samples': 542592, 'steps': 2825, 'loss/train': 2.7934391498565674} 08/30/2021 13:43:19 - INFO - __main__ - Step 2827: {'lr': 0.0004999615731047762, 'samples': 542784, 'steps': 2826, 'loss/train': 2.1765007972717285} 08/30/2021 13:43:19 - INFO - __main__ - Step 2828: {'lr': 0.0004999614800075158, 'samples': 542976, 'steps': 2827, 'loss/train': 2.8672866821289062} 08/30/2021 13:43:21 - INFO - __main__ - Step 2829: {'lr': 0.0004999613867976264, 'samples': 543168, 'steps': 2828, 'loss/train': 2.6867456436157227} 08/30/2021 13:43:21 - INFO - __main__ - Step 2830: {'lr': 0.0004999612934751082, 'samples': 543360, 'steps': 2829, 'loss/train': 1.432883381843567} 08/30/2021 13:43:22 - INFO - __main__ - Step 2831: {'lr': 0.0004999612000399614, 'samples': 543552, 'steps': 2830, 'loss/train': 2.7495994567871094} 08/30/2021 13:43:22 - INFO - __main__ - Step 2832: {'lr': 0.0004999611064921859, 'samples': 543744, 'steps': 2831, 'loss/train': 2.7531652450561523} 08/30/2021 13:43:22 - INFO - __main__ - Step 2833: {'lr': 0.0004999610128317818, 'samples': 543936, 'steps': 2832, 'loss/train': 2.5705811977386475} 08/30/2021 13:43:24 - INFO - __main__ - Step 2834: {'lr': 0.0004999609190587492, 'samples': 544128, 'steps': 2833, 'loss/train': 2.111081123352051} 08/30/2021 13:43:24 - INFO - __main__ - Step 2835: {'lr': 0.000499960825173088, 'samples': 544320, 'steps': 2834, 'loss/train': 2.756847620010376} 08/30/2021 13:43:25 - INFO - __main__ - Step 2836: {'lr': 0.0004999607311747983, 'samples': 544512, 'steps': 2835, 'loss/train': 2.611893653869629} 08/30/2021 13:43:25 - INFO - __main__ - Step 2837: {'lr': 0.0004999606370638801, 'samples': 544704, 'steps': 2836, 'loss/train': 1.6375468969345093} 08/30/2021 13:43:25 - INFO - __main__ - Step 2838: {'lr': 0.0004999605428403336, 'samples': 544896, 'steps': 2837, 'loss/train': 2.838456153869629} 08/30/2021 13:43:27 - INFO - __main__ - Step 2839: {'lr': 0.0004999604485041585, 'samples': 545088, 'steps': 2838, 'loss/train': 3.248014211654663} 08/30/2021 13:43:27 - INFO - __main__ - Step 2840: {'lr': 0.0004999603540553554, 'samples': 545280, 'steps': 2839, 'loss/train': 3.247673511505127} 08/30/2021 13:43:28 - INFO - __main__ - Step 2841: {'lr': 0.0004999602594939238, 'samples': 545472, 'steps': 2840, 'loss/train': 2.9345333576202393} 08/30/2021 13:43:28 - INFO - __main__ - Step 2842: {'lr': 0.0004999601648198641, 'samples': 545664, 'steps': 2841, 'loss/train': 2.6978485584259033} 08/30/2021 13:43:28 - INFO - __main__ - Step 2843: {'lr': 0.0004999600700331761, 'samples': 545856, 'steps': 2842, 'loss/train': 0.5655578374862671} 08/30/2021 13:43:30 - INFO - __main__ - Step 2844: {'lr': 0.0004999599751338601, 'samples': 546048, 'steps': 2843, 'loss/train': 2.8231377601623535} 08/30/2021 13:43:30 - INFO - __main__ - Step 2845: {'lr': 0.0004999598801219158, 'samples': 546240, 'steps': 2844, 'loss/train': 2.881303548812866} 08/30/2021 13:43:31 - INFO - __main__ - Step 2846: {'lr': 0.0004999597849973435, 'samples': 546432, 'steps': 2845, 'loss/train': 3.178879499435425} 08/30/2021 13:43:31 - INFO - __main__ - Step 2847: {'lr': 0.0004999596897601432, 'samples': 546624, 'steps': 2846, 'loss/train': 1.8442654609680176} 08/30/2021 13:43:31 - INFO - __main__ - Step 2848: {'lr': 0.0004999595944103149, 'samples': 546816, 'steps': 2847, 'loss/train': 2.8082611560821533} 08/30/2021 13:43:33 - INFO - __main__ - Step 2849: {'lr': 0.0004999594989478587, 'samples': 547008, 'steps': 2848, 'loss/train': 2.5219624042510986} 08/30/2021 13:43:33 - INFO - __main__ - Step 2850: {'lr': 0.0004999594033727747, 'samples': 547200, 'steps': 2849, 'loss/train': 2.0088613033294678} 08/30/2021 13:43:34 - INFO - __main__ - Step 2851: {'lr': 0.0004999593076850627, 'samples': 547392, 'steps': 2850, 'loss/train': 2.6474480628967285} 08/30/2021 13:43:34 - INFO - __main__ - Step 2852: {'lr': 0.0004999592118847229, 'samples': 547584, 'steps': 2851, 'loss/train': 2.7833218574523926} 08/30/2021 13:43:34 - INFO - __main__ - Step 2853: {'lr': 0.0004999591159717554, 'samples': 547776, 'steps': 2852, 'loss/train': 2.896838426589966} 08/30/2021 13:43:35 - INFO - __main__ - Step 2854: {'lr': 0.0004999590199461602, 'samples': 547968, 'steps': 2853, 'loss/train': 1.6673650741577148} 08/30/2021 13:43:36 - INFO - __main__ - Step 2855: {'lr': 0.0004999589238079373, 'samples': 548160, 'steps': 2854, 'loss/train': 2.6013550758361816} 08/30/2021 13:43:37 - INFO - __main__ - Step 2856: {'lr': 0.0004999588275570868, 'samples': 548352, 'steps': 2855, 'loss/train': 3.1163270473480225} 08/30/2021 13:43:37 - INFO - __main__ - Step 2857: {'lr': 0.0004999587311936086, 'samples': 548544, 'steps': 2856, 'loss/train': 2.775830030441284} 08/30/2021 13:43:38 - INFO - __main__ - Step 2858: {'lr': 0.000499958634717503, 'samples': 548736, 'steps': 2857, 'loss/train': 2.844712018966675} 08/30/2021 13:43:38 - INFO - __main__ - Step 2859: {'lr': 0.0004999585381287696, 'samples': 548928, 'steps': 2858, 'loss/train': 2.9458110332489014} 08/30/2021 13:43:40 - INFO - __main__ - Step 2860: {'lr': 0.000499958441427409, 'samples': 549120, 'steps': 2859, 'loss/train': 4.294079303741455} 08/30/2021 13:43:40 - INFO - __main__ - Step 2861: {'lr': 0.0004999583446134209, 'samples': 549312, 'steps': 2860, 'loss/train': 2.7137980461120605} 08/30/2021 13:43:41 - INFO - __main__ - Step 2862: {'lr': 0.0004999582476868055, 'samples': 549504, 'steps': 2861, 'loss/train': 2.79823637008667} 08/30/2021 13:43:41 - INFO - __main__ - Step 2863: {'lr': 0.0004999581506475627, 'samples': 549696, 'steps': 2862, 'loss/train': 1.2336348295211792} 08/30/2021 13:43:41 - INFO - __main__ - Step 2864: {'lr': 0.0004999580534956927, 'samples': 549888, 'steps': 2863, 'loss/train': 3.2243707180023193} 08/30/2021 13:43:43 - INFO - __main__ - Step 2865: {'lr': 0.0004999579562311953, 'samples': 550080, 'steps': 2864, 'loss/train': 3.012106418609619} 08/30/2021 13:43:43 - INFO - __main__ - Step 2866: {'lr': 0.0004999578588540709, 'samples': 550272, 'steps': 2865, 'loss/train': 3.1267731189727783} 08/30/2021 13:43:44 - INFO - __main__ - Step 2867: {'lr': 0.0004999577613643192, 'samples': 550464, 'steps': 2866, 'loss/train': 2.831829786300659} 08/30/2021 13:43:44 - INFO - __main__ - Step 2868: {'lr': 0.0004999576637619404, 'samples': 550656, 'steps': 2867, 'loss/train': 3.1577987670898438} 08/30/2021 13:43:44 - INFO - __main__ - Step 2869: {'lr': 0.0004999575660469347, 'samples': 550848, 'steps': 2868, 'loss/train': 2.829087018966675} 08/30/2021 13:43:45 - INFO - __main__ - Step 2870: {'lr': 0.0004999574682193017, 'samples': 551040, 'steps': 2869, 'loss/train': 3.1651971340179443} 08/30/2021 13:43:46 - INFO - __main__ - Step 2871: {'lr': 0.0004999573702790419, 'samples': 551232, 'steps': 2870, 'loss/train': 2.851490020751953} 08/30/2021 13:43:47 - INFO - __main__ - Step 2872: {'lr': 0.0004999572722261551, 'samples': 551424, 'steps': 2871, 'loss/train': 2.3922886848449707} 08/30/2021 13:43:47 - INFO - __main__ - Step 2873: {'lr': 0.0004999571740606415, 'samples': 551616, 'steps': 2872, 'loss/train': 3.3531363010406494} 08/30/2021 13:43:47 - INFO - __main__ - Step 2874: {'lr': 0.000499957075782501, 'samples': 551808, 'steps': 2873, 'loss/train': 2.9856975078582764} 08/30/2021 13:43:48 - INFO - __main__ - Step 2875: {'lr': 0.0004999569773917337, 'samples': 552000, 'steps': 2874, 'loss/train': 2.7506093978881836} 08/30/2021 13:43:49 - INFO - __main__ - Step 2876: {'lr': 0.0004999568788883397, 'samples': 552192, 'steps': 2875, 'loss/train': 2.358212947845459} 08/30/2021 13:43:50 - INFO - __main__ - Step 2877: {'lr': 0.0004999567802723188, 'samples': 552384, 'steps': 2876, 'loss/train': 1.463113784790039} 08/30/2021 13:43:50 - INFO - __main__ - Step 2878: {'lr': 0.0004999566815436715, 'samples': 552576, 'steps': 2877, 'loss/train': 2.735790729522705} 08/30/2021 13:43:50 - INFO - __main__ - Step 2879: {'lr': 0.0004999565827023974, 'samples': 552768, 'steps': 2878, 'loss/train': 2.3349661827087402} 08/30/2021 13:43:51 - INFO - __main__ - Step 2880: {'lr': 0.0004999564837484967, 'samples': 552960, 'steps': 2879, 'loss/train': 2.679495334625244} 08/30/2021 13:43:52 - INFO - __main__ - Step 2881: {'lr': 0.0004999563846819696, 'samples': 553152, 'steps': 2880, 'loss/train': 1.8391742706298828} 08/30/2021 13:43:53 - INFO - __main__ - Step 2882: {'lr': 0.0004999562855028159, 'samples': 553344, 'steps': 2881, 'loss/train': 2.791215181350708} 08/30/2021 13:43:53 - INFO - __main__ - Step 2883: {'lr': 0.0004999561862110358, 'samples': 553536, 'steps': 2882, 'loss/train': 2.320603847503662} 08/30/2021 13:43:53 - INFO - __main__ - Step 2884: {'lr': 0.0004999560868066293, 'samples': 553728, 'steps': 2883, 'loss/train': 3.279000997543335} 08/30/2021 13:43:54 - INFO - __main__ - Step 2885: {'lr': 0.0004999559872895964, 'samples': 553920, 'steps': 2884, 'loss/train': 2.206374168395996} 08/30/2021 13:43:54 - INFO - __main__ - Step 2886: {'lr': 0.0004999558876599373, 'samples': 554112, 'steps': 2885, 'loss/train': 2.559929132461548} 08/30/2021 13:43:56 - INFO - __main__ - Step 2887: {'lr': 0.0004999557879176518, 'samples': 554304, 'steps': 2886, 'loss/train': 7.318087577819824} 08/30/2021 13:43:56 - INFO - __main__ - Step 2888: {'lr': 0.0004999556880627401, 'samples': 554496, 'steps': 2887, 'loss/train': 3.7238998413085938} 08/30/2021 13:43:56 - INFO - __main__ - Step 2889: {'lr': 0.0004999555880952023, 'samples': 554688, 'steps': 2888, 'loss/train': 3.3081536293029785} 08/30/2021 13:43:57 - INFO - __main__ - Step 2890: {'lr': 0.0004999554880150383, 'samples': 554880, 'steps': 2889, 'loss/train': 3.2428319454193115} 08/30/2021 13:43:57 - INFO - __main__ - Step 2891: {'lr': 0.0004999553878222482, 'samples': 555072, 'steps': 2890, 'loss/train': 2.8276455402374268} 08/30/2021 13:43:59 - INFO - __main__ - Step 2892: {'lr': 0.0004999552875168321, 'samples': 555264, 'steps': 2891, 'loss/train': 3.1300160884857178} 08/30/2021 13:43:59 - INFO - __main__ - Step 2893: {'lr': 0.0004999551870987901, 'samples': 555456, 'steps': 2892, 'loss/train': 3.016570806503296} 08/30/2021 13:43:59 - INFO - __main__ - Step 2894: {'lr': 0.000499955086568122, 'samples': 555648, 'steps': 2893, 'loss/train': 3.561170816421509} 08/30/2021 13:44:00 - INFO - __main__ - Step 2895: {'lr': 0.000499954985924828, 'samples': 555840, 'steps': 2894, 'loss/train': 1.5887417793273926} 08/30/2021 13:44:00 - INFO - __main__ - Step 2896: {'lr': 0.0004999548851689082, 'samples': 556032, 'steps': 2895, 'loss/train': 0.6360597014427185} 08/30/2021 13:44:01 - INFO - __main__ - Step 2897: {'lr': 0.0004999547843003627, 'samples': 556224, 'steps': 2896, 'loss/train': 2.940615177154541} 08/30/2021 13:44:02 - INFO - __main__ - Step 2898: {'lr': 0.0004999546833191912, 'samples': 556416, 'steps': 2897, 'loss/train': 2.7789878845214844} 08/30/2021 13:44:02 - INFO - __main__ - Step 2899: {'lr': 0.0004999545822253941, 'samples': 556608, 'steps': 2898, 'loss/train': 3.103320837020874} 08/30/2021 13:44:03 - INFO - __main__ - Step 2900: {'lr': 0.0004999544810189713, 'samples': 556800, 'steps': 2899, 'loss/train': 2.287760019302368} 08/30/2021 13:44:03 - INFO - __main__ - Step 2901: {'lr': 0.0004999543796999228, 'samples': 556992, 'steps': 2900, 'loss/train': 3.5957651138305664} 08/30/2021 13:44:05 - INFO - __main__ - Step 2902: {'lr': 0.0004999542782682489, 'samples': 557184, 'steps': 2901, 'loss/train': 2.924877166748047} 08/30/2021 13:44:06 - INFO - __main__ - Step 2903: {'lr': 0.0004999541767239493, 'samples': 557376, 'steps': 2902, 'loss/train': 2.783628225326538} 08/30/2021 13:44:06 - INFO - __main__ - Step 2904: {'lr': 0.0004999540750670243, 'samples': 557568, 'steps': 2903, 'loss/train': 3.0987961292266846} 08/30/2021 13:44:06 - INFO - __main__ - Step 2905: {'lr': 0.0004999539732974738, 'samples': 557760, 'steps': 2904, 'loss/train': 2.848283052444458} 08/30/2021 13:44:07 - INFO - __main__ - Step 2906: {'lr': 0.0004999538714152978, 'samples': 557952, 'steps': 2905, 'loss/train': 2.8918533325195312} 08/30/2021 13:44:07 - INFO - __main__ - Step 2907: {'lr': 0.0004999537694204966, 'samples': 558144, 'steps': 2906, 'loss/train': 2.272188663482666} 08/30/2021 13:44:09 - INFO - __main__ - Step 2908: {'lr': 0.0004999536673130701, 'samples': 558336, 'steps': 2907, 'loss/train': 3.046729326248169} 08/30/2021 13:44:09 - INFO - __main__ - Step 2909: {'lr': 0.0004999535650930182, 'samples': 558528, 'steps': 2908, 'loss/train': 2.816863775253296} 08/30/2021 13:44:10 - INFO - __main__ - Step 2910: {'lr': 0.0004999534627603411, 'samples': 558720, 'steps': 2909, 'loss/train': 2.118304967880249} 08/30/2021 13:44:10 - INFO - __main__ - Step 2911: {'lr': 0.0004999533603150389, 'samples': 558912, 'steps': 2910, 'loss/train': 2.6835672855377197} 08/30/2021 13:44:10 - INFO - __main__ - Step 2912: {'lr': 0.0004999532577571116, 'samples': 559104, 'steps': 2911, 'loss/train': 3.151839017868042} 08/30/2021 13:44:12 - INFO - __main__ - Step 2913: {'lr': 0.0004999531550865592, 'samples': 559296, 'steps': 2912, 'loss/train': 2.8047454357147217} 08/30/2021 13:44:12 - INFO - __main__ - Step 2914: {'lr': 0.0004999530523033817, 'samples': 559488, 'steps': 2913, 'loss/train': 2.8529162406921387} 08/30/2021 13:44:13 - INFO - __main__ - Step 2915: {'lr': 0.0004999529494075792, 'samples': 559680, 'steps': 2914, 'loss/train': 2.7388527393341064} 08/30/2021 13:44:13 - INFO - __main__ - Step 2916: {'lr': 0.0004999528463991518, 'samples': 559872, 'steps': 2915, 'loss/train': 2.8058598041534424} 08/30/2021 13:44:13 - INFO - __main__ - Step 2917: {'lr': 0.0004999527432780995, 'samples': 560064, 'steps': 2916, 'loss/train': 3.0856664180755615} 08/30/2021 13:44:15 - INFO - __main__ - Step 2918: {'lr': 0.0004999526400444223, 'samples': 560256, 'steps': 2917, 'loss/train': 1.9239698648452759} 08/30/2021 13:44:15 - INFO - __main__ - Step 2919: {'lr': 0.0004999525366981204, 'samples': 560448, 'steps': 2918, 'loss/train': 3.4998552799224854} 08/30/2021 13:44:16 - INFO - __main__ - Step 2920: {'lr': 0.0004999524332391937, 'samples': 560640, 'steps': 2919, 'loss/train': 2.9600071907043457} 08/30/2021 13:44:16 - INFO - __main__ - Step 2921: {'lr': 0.0004999523296676423, 'samples': 560832, 'steps': 2920, 'loss/train': 2.7623751163482666} 08/30/2021 13:44:16 - INFO - __main__ - Step 2922: {'lr': 0.0004999522259834662, 'samples': 561024, 'steps': 2921, 'loss/train': 2.79846453666687} 08/30/2021 13:44:18 - INFO - __main__ - Step 2923: {'lr': 0.0004999521221866655, 'samples': 561216, 'steps': 2922, 'loss/train': 2.631439447402954} 08/30/2021 13:44:18 - INFO - __main__ - Step 2924: {'lr': 0.0004999520182772402, 'samples': 561408, 'steps': 2923, 'loss/train': 2.282538414001465} 08/30/2021 13:44:19 - INFO - __main__ - Step 2925: {'lr': 0.0004999519142551905, 'samples': 561600, 'steps': 2924, 'loss/train': 2.5863075256347656} 08/30/2021 13:44:19 - INFO - __main__ - Step 2926: {'lr': 0.0004999518101205162, 'samples': 561792, 'steps': 2925, 'loss/train': 1.9376370906829834} 08/30/2021 13:44:19 - INFO - __main__ - Step 2927: {'lr': 0.0004999517058732175, 'samples': 561984, 'steps': 2926, 'loss/train': 2.1587612628936768} 08/30/2021 13:44:20 - INFO - __main__ - Step 2928: {'lr': 0.0004999516015132945, 'samples': 562176, 'steps': 2927, 'loss/train': 3.034369945526123} 08/30/2021 13:44:21 - INFO - __main__ - Step 2929: {'lr': 0.0004999514970407471, 'samples': 562368, 'steps': 2928, 'loss/train': 2.461535930633545} 08/30/2021 13:44:22 - INFO - __main__ - Step 2930: {'lr': 0.0004999513924555754, 'samples': 562560, 'steps': 2929, 'loss/train': 2.53454327583313} 08/30/2021 13:44:22 - INFO - __main__ - Step 2931: {'lr': 0.0004999512877577794, 'samples': 562752, 'steps': 2930, 'loss/train': 2.8248937129974365} 08/30/2021 13:44:22 - INFO - __main__ - Step 2932: {'lr': 0.0004999511829473593, 'samples': 562944, 'steps': 2931, 'loss/train': 0.7965051531791687} 08/30/2021 13:44:23 - INFO - __main__ - Step 2933: {'lr': 0.0004999510780243151, 'samples': 563136, 'steps': 2932, 'loss/train': 2.673820734024048} 08/30/2021 13:44:24 - INFO - __main__ - Step 2934: {'lr': 0.0004999509729886467, 'samples': 563328, 'steps': 2933, 'loss/train': 2.241774082183838} 08/30/2021 13:44:25 - INFO - __main__ - Step 2935: {'lr': 0.0004999508678403542, 'samples': 563520, 'steps': 2934, 'loss/train': 2.892744541168213} 08/30/2021 13:44:25 - INFO - __main__ - Step 2936: {'lr': 0.0004999507625794378, 'samples': 563712, 'steps': 2935, 'loss/train': 3.223254680633545} 08/30/2021 13:44:25 - INFO - __main__ - Step 2937: {'lr': 0.0004999506572058974, 'samples': 563904, 'steps': 2936, 'loss/train': 1.714627981185913} 08/30/2021 13:44:26 - INFO - __main__ - Step 2938: {'lr': 0.0004999505517197331, 'samples': 564096, 'steps': 2937, 'loss/train': 2.4244155883789062} 08/30/2021 13:44:27 - INFO - __main__ - Step 2939: {'lr': 0.000499950446120945, 'samples': 564288, 'steps': 2938, 'loss/train': 1.4697874784469604} 08/30/2021 13:44:28 - INFO - __main__ - Step 2940: {'lr': 0.000499950340409533, 'samples': 564480, 'steps': 2939, 'loss/train': 0.44932907819747925} 08/30/2021 13:44:28 - INFO - __main__ - Step 2941: {'lr': 0.0004999502345854973, 'samples': 564672, 'steps': 2940, 'loss/train': 2.921510934829712} 08/30/2021 13:44:28 - INFO - __main__ - Step 2942: {'lr': 0.0004999501286488378, 'samples': 564864, 'steps': 2941, 'loss/train': 2.3862104415893555} 08/30/2021 13:44:29 - INFO - __main__ - Step 2943: {'lr': 0.0004999500225995547, 'samples': 565056, 'steps': 2942, 'loss/train': 2.6102335453033447} 08/30/2021 13:44:30 - INFO - __main__ - Step 2944: {'lr': 0.000499949916437648, 'samples': 565248, 'steps': 2943, 'loss/train': 2.867708683013916} 08/30/2021 13:44:31 - INFO - __main__ - Step 2945: {'lr': 0.0004999498101631177, 'samples': 565440, 'steps': 2944, 'loss/train': 3.421034336090088} 08/30/2021 13:44:31 - INFO - __main__ - Step 2946: {'lr': 0.0004999497037759638, 'samples': 565632, 'steps': 2945, 'loss/train': 2.4923837184906006} 08/30/2021 13:44:31 - INFO - __main__ - Step 2947: {'lr': 0.0004999495972761865, 'samples': 565824, 'steps': 2946, 'loss/train': 2.0850162506103516} 08/30/2021 13:44:32 - INFO - __main__ - Step 2948: {'lr': 0.0004999494906637857, 'samples': 566016, 'steps': 2947, 'loss/train': 2.3148810863494873} 08/30/2021 13:44:33 - INFO - __main__ - Step 2949: {'lr': 0.0004999493839387615, 'samples': 566208, 'steps': 2948, 'loss/train': 2.917724370956421} 08/30/2021 13:44:34 - INFO - __main__ - Step 2950: {'lr': 0.000499949277101114, 'samples': 566400, 'steps': 2949, 'loss/train': 2.8091204166412354} 08/30/2021 13:44:34 - INFO - __main__ - Step 2951: {'lr': 0.0004999491701508433, 'samples': 566592, 'steps': 2950, 'loss/train': 2.2364890575408936} 08/30/2021 13:44:34 - INFO - __main__ - Step 2952: {'lr': 0.0004999490630879493, 'samples': 566784, 'steps': 2951, 'loss/train': 2.2985527515411377} 08/30/2021 13:44:35 - INFO - __main__ - Step 2953: {'lr': 0.0004999489559124321, 'samples': 566976, 'steps': 2952, 'loss/train': 3.4640183448791504} 08/30/2021 13:44:37 - INFO - __main__ - Step 2954: {'lr': 0.0004999488486242918, 'samples': 567168, 'steps': 2953, 'loss/train': 2.5138840675354004} 08/30/2021 13:44:38 - INFO - __main__ - Step 2955: {'lr': 0.0004999487412235284, 'samples': 567360, 'steps': 2954, 'loss/train': 2.7582364082336426} 08/30/2021 13:44:38 - INFO - __main__ - Step 2956: {'lr': 0.0004999486337101419, 'samples': 567552, 'steps': 2955, 'loss/train': 1.8475825786590576} 08/30/2021 13:44:38 - INFO - __main__ - Step 2957: {'lr': 0.0004999485260841324, 'samples': 567744, 'steps': 2956, 'loss/train': 3.014390468597412} 08/30/2021 13:44:39 - INFO - __main__ - Step 2958: {'lr': 0.0004999484183455, 'samples': 567936, 'steps': 2957, 'loss/train': 2.3483035564422607} 08/30/2021 13:44:39 - INFO - __main__ - Step 2959: {'lr': 0.0004999483104942446, 'samples': 568128, 'steps': 2958, 'loss/train': 2.8362791538238525} 08/30/2021 13:44:41 - INFO - __main__ - Step 2960: {'lr': 0.0004999482025303665, 'samples': 568320, 'steps': 2959, 'loss/train': 2.887427806854248} 08/30/2021 13:44:42 - INFO - __main__ - Step 2961: {'lr': 0.0004999480944538655, 'samples': 568512, 'steps': 2960, 'loss/train': 3.5132014751434326} 08/30/2021 13:44:42 - INFO - __main__ - Step 2962: {'lr': 0.0004999479862647417, 'samples': 568704, 'steps': 2961, 'loss/train': 3.08158540725708} 08/30/2021 13:44:42 - INFO - __main__ - Step 2963: {'lr': 0.0004999478779629953, 'samples': 568896, 'steps': 2962, 'loss/train': 2.0255677700042725} 08/30/2021 13:44:43 - INFO - __main__ - Step 2964: {'lr': 0.0004999477695486261, 'samples': 569088, 'steps': 2963, 'loss/train': 0.8236057162284851} 08/30/2021 13:44:44 - INFO - __main__ - Step 2965: {'lr': 0.0004999476610216345, 'samples': 569280, 'steps': 2964, 'loss/train': 0.859920084476471} 08/30/2021 13:44:45 - INFO - __main__ - Step 2966: {'lr': 0.0004999475523820203, 'samples': 569472, 'steps': 2965, 'loss/train': 2.7543699741363525} 08/30/2021 13:44:45 - INFO - __main__ - Step 2967: {'lr': 0.0004999474436297835, 'samples': 569664, 'steps': 2966, 'loss/train': 2.5906596183776855} 08/30/2021 13:44:45 - INFO - __main__ - Step 2968: {'lr': 0.0004999473347649242, 'samples': 569856, 'steps': 2967, 'loss/train': 1.0227876901626587} 08/30/2021 13:44:46 - INFO - __main__ - Step 2969: {'lr': 0.0004999472257874426, 'samples': 570048, 'steps': 2968, 'loss/train': 2.6242566108703613} 08/30/2021 13:44:48 - INFO - __main__ - Step 2970: {'lr': 0.0004999471166973385, 'samples': 570240, 'steps': 2969, 'loss/train': 2.424834728240967} 08/30/2021 13:44:48 - INFO - __main__ - Step 2971: {'lr': 0.0004999470074946122, 'samples': 570432, 'steps': 2970, 'loss/train': 2.5786919593811035} 08/30/2021 13:44:48 - INFO - __main__ - Step 2972: {'lr': 0.0004999468981792636, 'samples': 570624, 'steps': 2971, 'loss/train': 2.902613878250122} 08/30/2021 13:44:49 - INFO - __main__ - Step 2973: {'lr': 0.0004999467887512928, 'samples': 570816, 'steps': 2972, 'loss/train': 2.933173418045044} 08/30/2021 13:44:49 - INFO - __main__ - Step 2974: {'lr': 0.0004999466792106998, 'samples': 571008, 'steps': 2973, 'loss/train': 2.886467695236206} 08/30/2021 13:44:50 - INFO - __main__ - Step 2975: {'lr': 0.0004999465695574848, 'samples': 571200, 'steps': 2974, 'loss/train': 2.3601338863372803} 08/30/2021 13:44:51 - INFO - __main__ - Step 2976: {'lr': 0.0004999464597916476, 'samples': 571392, 'steps': 2975, 'loss/train': 2.9770824909210205} 08/30/2021 13:44:51 - INFO - __main__ - Step 2977: {'lr': 0.0004999463499131884, 'samples': 571584, 'steps': 2976, 'loss/train': 2.3549747467041016} 08/30/2021 13:44:51 - INFO - __main__ - Step 2978: {'lr': 0.0004999462399221073, 'samples': 571776, 'steps': 2977, 'loss/train': 2.3175888061523438} 08/30/2021 13:44:52 - INFO - __main__ - Step 2979: {'lr': 0.0004999461298184042, 'samples': 571968, 'steps': 2978, 'loss/train': 2.9362945556640625} 08/30/2021 13:44:52 - INFO - __main__ - Step 2980: {'lr': 0.0004999460196020793, 'samples': 572160, 'steps': 2979, 'loss/train': 2.3794565200805664} 08/30/2021 13:44:54 - INFO - __main__ - Step 2981: {'lr': 0.0004999459092731326, 'samples': 572352, 'steps': 2980, 'loss/train': 2.9920153617858887} 08/30/2021 13:44:54 - INFO - __main__ - Step 2982: {'lr': 0.000499945798831564, 'samples': 572544, 'steps': 2981, 'loss/train': 1.9340310096740723} 08/30/2021 13:44:55 - INFO - __main__ - Step 2983: {'lr': 0.0004999456882773737, 'samples': 572736, 'steps': 2982, 'loss/train': 2.715445041656494} 08/30/2021 13:44:55 - INFO - __main__ - Step 2984: {'lr': 0.0004999455776105618, 'samples': 572928, 'steps': 2983, 'loss/train': 2.7663369178771973} 08/30/2021 13:44:55 - INFO - __main__ - Step 2985: {'lr': 0.0004999454668311283, 'samples': 573120, 'steps': 2984, 'loss/train': 2.597182273864746} 08/30/2021 13:44:57 - INFO - __main__ - Step 2986: {'lr': 0.0004999453559390731, 'samples': 573312, 'steps': 2985, 'loss/train': 0.6528981328010559} 08/30/2021 13:44:57 - INFO - __main__ - Step 2987: {'lr': 0.0004999452449343967, 'samples': 573504, 'steps': 2986, 'loss/train': 2.6354496479034424} 08/30/2021 13:44:58 - INFO - __main__ - Step 2988: {'lr': 0.0004999451338170985, 'samples': 573696, 'steps': 2987, 'loss/train': 2.6551873683929443} 08/30/2021 13:44:58 - INFO - __main__ - Step 2989: {'lr': 0.000499945022587179, 'samples': 573888, 'steps': 2988, 'loss/train': 2.0231504440307617} 08/30/2021 13:44:58 - INFO - __main__ - Step 2990: {'lr': 0.0004999449112446381, 'samples': 574080, 'steps': 2989, 'loss/train': 2.8025505542755127} 08/30/2021 13:45:00 - INFO - __main__ - Step 2991: {'lr': 0.000499944799789476, 'samples': 574272, 'steps': 2990, 'loss/train': 2.741412401199341} 08/30/2021 13:45:01 - INFO - __main__ - Step 2992: {'lr': 0.0004999446882216925, 'samples': 574464, 'steps': 2991, 'loss/train': 2.3821704387664795} 08/30/2021 13:45:01 - INFO - __main__ - Step 2993: {'lr': 0.0004999445765412878, 'samples': 574656, 'steps': 2992, 'loss/train': 2.259613037109375} 08/30/2021 13:45:01 - INFO - __main__ - Step 2994: {'lr': 0.0004999444647482619, 'samples': 574848, 'steps': 2993, 'loss/train': 0.6169657707214355} 08/30/2021 13:45:02 - INFO - __main__ - Step 2995: {'lr': 0.0004999443528426149, 'samples': 575040, 'steps': 2994, 'loss/train': 2.9905946254730225} 08/30/2021 13:45:03 - INFO - __main__ - Step 2996: {'lr': 0.0004999442408243469, 'samples': 575232, 'steps': 2995, 'loss/train': 2.6902949810028076} 08/30/2021 13:45:04 - INFO - __main__ - Step 2997: {'lr': 0.0004999441286934578, 'samples': 575424, 'steps': 2996, 'loss/train': 3.835057258605957} 08/30/2021 13:45:04 - INFO - __main__ - Step 2998: {'lr': 0.0004999440164499478, 'samples': 575616, 'steps': 2997, 'loss/train': 3.012542963027954} 08/30/2021 13:45:04 - INFO - __main__ - Step 2999: {'lr': 0.0004999439040938168, 'samples': 575808, 'steps': 2998, 'loss/train': 2.139873504638672} 08/30/2021 13:45:05 - INFO - __main__ - Step 3000: {'lr': 0.000499943791625065, 'samples': 576000, 'steps': 2999, 'loss/train': 2.54128360748291} 08/30/2021 13:45:06 - INFO - __main__ - Step 3001: {'lr': 0.0004999436790436923, 'samples': 576192, 'steps': 3000, 'loss/train': 1.8351815938949585} 08/30/2021 13:45:07 - INFO - __main__ - Step 3002: {'lr': 0.000499943566349699, 'samples': 576384, 'steps': 3001, 'loss/train': 2.538656234741211} 08/30/2021 13:45:07 - INFO - __main__ - Step 3003: {'lr': 0.0004999434535430848, 'samples': 576576, 'steps': 3002, 'loss/train': 2.350154399871826} 08/30/2021 13:45:07 - INFO - __main__ - Step 3004: {'lr': 0.0004999433406238501, 'samples': 576768, 'steps': 3003, 'loss/train': 2.707881212234497} 08/30/2021 13:45:08 - INFO - __main__ - Step 3005: {'lr': 0.0004999432275919947, 'samples': 576960, 'steps': 3004, 'loss/train': 2.6003835201263428} 08/30/2021 13:45:08 - INFO - __main__ - Step 3006: {'lr': 0.0004999431144475187, 'samples': 577152, 'steps': 3005, 'loss/train': 2.8380956649780273} 08/30/2021 13:45:10 - INFO - __main__ - Step 3007: {'lr': 0.0004999430011904222, 'samples': 577344, 'steps': 3006, 'loss/train': 2.5522007942199707} 08/30/2021 13:45:10 - INFO - __main__ - Step 3008: {'lr': 0.0004999428878207054, 'samples': 577536, 'steps': 3007, 'loss/train': 2.474048137664795} 08/30/2021 13:45:11 - INFO - __main__ - Step 3009: {'lr': 0.000499942774338368, 'samples': 577728, 'steps': 3008, 'loss/train': 2.4502363204956055} 08/30/2021 13:45:11 - INFO - __main__ - Step 3010: {'lr': 0.0004999426607434104, 'samples': 577920, 'steps': 3009, 'loss/train': 2.775979518890381} 08/30/2021 13:45:11 - INFO - __main__ - Step 3011: {'lr': 0.0004999425470358324, 'samples': 578112, 'steps': 3010, 'loss/train': 3.078824043273926} 08/30/2021 13:45:13 - INFO - __main__ - Step 3012: {'lr': 0.0004999424332156341, 'samples': 578304, 'steps': 3011, 'loss/train': 2.953322172164917} 08/30/2021 13:45:14 - INFO - __main__ - Step 3013: {'lr': 0.0004999423192828156, 'samples': 578496, 'steps': 3012, 'loss/train': 2.948363780975342} 08/30/2021 13:45:14 - INFO - __main__ - Step 3014: {'lr': 0.0004999422052373771, 'samples': 578688, 'steps': 3013, 'loss/train': 3.5237135887145996} 08/30/2021 13:45:14 - INFO - __main__ - Step 3015: {'lr': 0.0004999420910793183, 'samples': 578880, 'steps': 3014, 'loss/train': 2.7692630290985107} 08/30/2021 13:45:15 - INFO - __main__ - Step 3016: {'lr': 0.0004999419768086397, 'samples': 579072, 'steps': 3015, 'loss/train': 2.4753150939941406} 08/30/2021 13:45:16 - INFO - __main__ - Step 3017: {'lr': 0.0004999418624253408, 'samples': 579264, 'steps': 3016, 'loss/train': 1.1601556539535522} 08/30/2021 13:45:17 - INFO - __main__ - Step 3018: {'lr': 0.0004999417479294221, 'samples': 579456, 'steps': 3017, 'loss/train': 2.7365775108337402} 08/30/2021 13:45:17 - INFO - __main__ - Step 3019: {'lr': 0.0004999416333208835, 'samples': 579648, 'steps': 3018, 'loss/train': 2.1109657287597656} 08/30/2021 13:45:17 - INFO - __main__ - Step 3020: {'lr': 0.0004999415185997252, 'samples': 579840, 'steps': 3019, 'loss/train': 3.3136794567108154} 08/30/2021 13:45:18 - INFO - __main__ - Step 3021: {'lr': 0.0004999414037659468, 'samples': 580032, 'steps': 3020, 'loss/train': 4.073999881744385} 08/30/2021 13:45:18 - INFO - __main__ - Step 3022: {'lr': 0.000499941288819549, 'samples': 580224, 'steps': 3021, 'loss/train': 2.3366594314575195} 08/30/2021 13:45:19 - INFO - __main__ - Step 3023: {'lr': 0.0004999411737605313, 'samples': 580416, 'steps': 3022, 'loss/train': 2.9019672870635986} 08/30/2021 13:45:20 - INFO - __main__ - Step 3024: {'lr': 0.000499941058588894, 'samples': 580608, 'steps': 3023, 'loss/train': 1.7941155433654785} 08/30/2021 13:45:20 - INFO - __main__ - Step 3025: {'lr': 0.0004999409433046371, 'samples': 580800, 'steps': 3024, 'loss/train': 2.956582546234131} 08/30/2021 13:45:21 - INFO - __main__ - Step 3026: {'lr': 0.0004999408279077607, 'samples': 580992, 'steps': 3025, 'loss/train': 2.451669454574585} 08/30/2021 13:45:21 - INFO - __main__ - Step 3027: {'lr': 0.0004999407123982649, 'samples': 581184, 'steps': 3026, 'loss/train': 2.8706061840057373} 08/30/2021 13:45:23 - INFO - __main__ - Step 3028: {'lr': 0.0004999405967761495, 'samples': 581376, 'steps': 3027, 'loss/train': 2.580427885055542} 08/30/2021 13:45:23 - INFO - __main__ - Step 3029: {'lr': 0.0004999404810414149, 'samples': 581568, 'steps': 3028, 'loss/train': 2.147118330001831} 08/30/2021 13:45:24 - INFO - __main__ - Step 3030: {'lr': 0.0004999403651940608, 'samples': 581760, 'steps': 3029, 'loss/train': 2.019071340560913} 08/30/2021 13:45:24 - INFO - __main__ - Step 3031: {'lr': 0.0004999402492340875, 'samples': 581952, 'steps': 3030, 'loss/train': 0.7779306173324585} 08/30/2021 13:45:24 - INFO - __main__ - Step 3032: {'lr': 0.000499940133161495, 'samples': 582144, 'steps': 3031, 'loss/train': 2.4335618019104004} 08/30/2021 13:45:26 - INFO - __main__ - Step 3033: {'lr': 0.0004999400169762834, 'samples': 582336, 'steps': 3032, 'loss/train': 2.718484401702881} 08/30/2021 13:45:27 - INFO - __main__ - Step 3034: {'lr': 0.0004999399006784525, 'samples': 582528, 'steps': 3033, 'loss/train': 2.593709945678711} 08/30/2021 13:45:27 - INFO - __main__ - Step 3035: {'lr': 0.0004999397842680027, 'samples': 582720, 'steps': 3034, 'loss/train': 2.043519973754883} 08/30/2021 13:45:27 - INFO - __main__ - Step 3036: {'lr': 0.0004999396677449338, 'samples': 582912, 'steps': 3035, 'loss/train': 2.6912176609039307} 08/30/2021 13:45:28 - INFO - __main__ - Step 3037: {'lr': 0.000499939551109246, 'samples': 583104, 'steps': 3036, 'loss/train': 2.847600221633911} 08/30/2021 13:45:29 - INFO - __main__ - Step 3038: {'lr': 0.0004999394343609393, 'samples': 583296, 'steps': 3037, 'loss/train': 0.6094777584075928} 08/30/2021 13:45:30 - INFO - __main__ - Step 3039: {'lr': 0.0004999393175000137, 'samples': 583488, 'steps': 3038, 'loss/train': 2.4259679317474365} 08/30/2021 13:45:30 - INFO - __main__ - Step 3040: {'lr': 0.0004999392005264694, 'samples': 583680, 'steps': 3039, 'loss/train': 3.0082595348358154} 08/30/2021 13:45:30 - INFO - __main__ - Step 3041: {'lr': 0.0004999390834403062, 'samples': 583872, 'steps': 3040, 'loss/train': 2.5855770111083984} 08/30/2021 13:45:31 - INFO - __main__ - Step 3042: {'lr': 0.0004999389662415244, 'samples': 584064, 'steps': 3041, 'loss/train': 3.4849119186401367} 08/30/2021 13:45:32 - INFO - __main__ - Step 3043: {'lr': 0.000499938848930124, 'samples': 584256, 'steps': 3042, 'loss/train': 3.171412706375122} 08/30/2021 13:45:33 - INFO - __main__ - Step 3044: {'lr': 0.0004999387315061049, 'samples': 584448, 'steps': 3043, 'loss/train': 3.1442337036132812} 08/30/2021 13:45:33 - INFO - __main__ - Step 3045: {'lr': 0.0004999386139694673, 'samples': 584640, 'steps': 3044, 'loss/train': 2.964331865310669} 08/30/2021 13:45:33 - INFO - __main__ - Step 3046: {'lr': 0.0004999384963202113, 'samples': 584832, 'steps': 3045, 'loss/train': 2.6739697456359863} 08/30/2021 13:45:34 - INFO - __main__ - Step 3047: {'lr': 0.0004999383785583368, 'samples': 585024, 'steps': 3046, 'loss/train': 2.660141944885254} 08/30/2021 13:45:34 - INFO - __main__ - Step 3048: {'lr': 0.0004999382606838439, 'samples': 585216, 'steps': 3047, 'loss/train': 2.9862749576568604} 08/30/2021 13:45:36 - INFO - __main__ - Step 3049: {'lr': 0.0004999381426967327, 'samples': 585408, 'steps': 3048, 'loss/train': 1.8866349458694458} 08/30/2021 13:45:36 - INFO - __main__ - Step 3050: {'lr': 0.0004999380245970033, 'samples': 585600, 'steps': 3049, 'loss/train': 2.671400785446167} 08/30/2021 13:45:37 - INFO - __main__ - Step 3051: {'lr': 0.0004999379063846555, 'samples': 585792, 'steps': 3050, 'loss/train': 2.8302955627441406} 08/30/2021 13:45:37 - INFO - __main__ - Step 3052: {'lr': 0.0004999377880596897, 'samples': 585984, 'steps': 3051, 'loss/train': 2.9001340866088867} 08/30/2021 13:45:37 - INFO - __main__ - Step 3053: {'lr': 0.0004999376696221057, 'samples': 586176, 'steps': 3052, 'loss/train': 2.967221260070801} 08/30/2021 13:45:39 - INFO - __main__ - Step 3054: {'lr': 0.0004999375510719037, 'samples': 586368, 'steps': 3053, 'loss/train': 2.405060291290283} 08/30/2021 13:45:39 - INFO - __main__ - Step 3055: {'lr': 0.0004999374324090837, 'samples': 586560, 'steps': 3054, 'loss/train': 2.759819984436035} 08/30/2021 13:45:40 - INFO - __main__ - Step 3056: {'lr': 0.0004999373136336457, 'samples': 586752, 'steps': 3055, 'loss/train': 2.729295015335083} 08/30/2021 13:45:40 - INFO - __main__ - Step 3057: {'lr': 0.0004999371947455899, 'samples': 586944, 'steps': 3056, 'loss/train': 2.9442522525787354} 08/30/2021 13:45:40 - INFO - __main__ - Step 3058: {'lr': 0.0004999370757449162, 'samples': 587136, 'steps': 3057, 'loss/train': 2.8332059383392334} 08/30/2021 13:45:42 - INFO - __main__ - Step 3059: {'lr': 0.0004999369566316247, 'samples': 587328, 'steps': 3058, 'loss/train': 3.4595844745635986} 08/30/2021 13:45:42 - INFO - __main__ - Step 3060: {'lr': 0.0004999368374057155, 'samples': 587520, 'steps': 3059, 'loss/train': 3.0762219429016113} 08/30/2021 13:45:43 - INFO - __main__ - Step 3061: {'lr': 0.0004999367180671886, 'samples': 587712, 'steps': 3060, 'loss/train': 2.538363218307495} 08/30/2021 13:45:43 - INFO - __main__ - Step 3062: {'lr': 0.000499936598616044, 'samples': 587904, 'steps': 3061, 'loss/train': 2.421142101287842} 08/30/2021 13:45:43 - INFO - __main__ - Step 3063: {'lr': 0.0004999364790522819, 'samples': 588096, 'steps': 3062, 'loss/train': 3.322051763534546} 08/30/2021 13:45:44 - INFO - __main__ - Step 3064: {'lr': 0.0004999363593759022, 'samples': 588288, 'steps': 3063, 'loss/train': 2.883498191833496} 08/30/2021 13:45:46 - INFO - __main__ - Step 3065: {'lr': 0.0004999362395869052, 'samples': 588480, 'steps': 3064, 'loss/train': 2.4707047939300537} 08/30/2021 13:45:46 - INFO - __main__ - Step 3066: {'lr': 0.0004999361196852906, 'samples': 588672, 'steps': 3065, 'loss/train': 3.842144012451172} 08/30/2021 13:45:47 - INFO - __main__ - Step 3067: {'lr': 0.0004999359996710588, 'samples': 588864, 'steps': 3066, 'loss/train': 1.566475749015808} 08/30/2021 13:45:47 - INFO - __main__ - Step 3068: {'lr': 0.0004999358795442096, 'samples': 589056, 'steps': 3067, 'loss/train': 2.8776683807373047} 08/30/2021 13:45:47 - INFO - __main__ - Step 3069: {'lr': 0.0004999357593047431, 'samples': 589248, 'steps': 3068, 'loss/train': 1.8093340396881104} 08/30/2021 13:45:49 - INFO - __main__ - Step 3070: {'lr': 0.0004999356389526595, 'samples': 589440, 'steps': 3069, 'loss/train': 2.1377689838409424} 08/30/2021 13:45:49 - INFO - __main__ - Step 3071: {'lr': 0.0004999355184879587, 'samples': 589632, 'steps': 3070, 'loss/train': 2.0826215744018555} 08/30/2021 13:45:50 - INFO - __main__ - Step 3072: {'lr': 0.0004999353979106409, 'samples': 589824, 'steps': 3071, 'loss/train': 2.913546085357666} 08/30/2021 13:45:50 - INFO - __main__ - Step 3073: {'lr': 0.000499935277220706, 'samples': 590016, 'steps': 3072, 'loss/train': 2.7634084224700928} 08/30/2021 13:45:50 - INFO - __main__ - Step 3074: {'lr': 0.0004999351564181541, 'samples': 590208, 'steps': 3073, 'loss/train': 2.988072156906128} 08/30/2021 13:45:52 - INFO - __main__ - Step 3075: {'lr': 0.0004999350355029854, 'samples': 590400, 'steps': 3074, 'loss/train': 3.424922466278076} 08/30/2021 13:45:53 - INFO - __main__ - Step 3076: {'lr': 0.0004999349144751997, 'samples': 590592, 'steps': 3075, 'loss/train': 2.2299084663391113} 08/30/2021 13:45:53 - INFO - __main__ - Step 3077: {'lr': 0.0004999347933347972, 'samples': 590784, 'steps': 3076, 'loss/train': 2.887336015701294} 08/30/2021 13:45:53 - INFO - __main__ - Step 3078: {'lr': 0.0004999346720817779, 'samples': 590976, 'steps': 3077, 'loss/train': 2.785231590270996} 08/30/2021 13:45:54 - INFO - __main__ - Step 3079: {'lr': 0.000499934550716142, 'samples': 591168, 'steps': 3078, 'loss/train': 2.7666194438934326} 08/30/2021 13:45:54 - INFO - __main__ - Step 3080: {'lr': 0.0004999344292378893, 'samples': 591360, 'steps': 3079, 'loss/train': 1.5362716913223267} 08/30/2021 13:45:55 - INFO - __main__ - Step 3081: {'lr': 0.0004999343076470202, 'samples': 591552, 'steps': 3080, 'loss/train': 3.3281936645507812} 08/30/2021 13:45:56 - INFO - __main__ - Step 3082: {'lr': 0.0004999341859435345, 'samples': 591744, 'steps': 3081, 'loss/train': 3.255598783493042} 08/30/2021 13:45:56 - INFO - __main__ - Step 3083: {'lr': 0.0004999340641274322, 'samples': 591936, 'steps': 3082, 'loss/train': 2.720642566680908} 08/30/2021 13:45:57 - INFO - __main__ - Step 3084: {'lr': 0.0004999339421987136, 'samples': 592128, 'steps': 3083, 'loss/train': 2.823425769805908} 08/30/2021 13:45:57 - INFO - __main__ - Step 3085: {'lr': 0.0004999338201573786, 'samples': 592320, 'steps': 3084, 'loss/train': 2.087015151977539} 08/30/2021 13:45:59 - INFO - __main__ - Step 3086: {'lr': 0.0004999336980034271, 'samples': 592512, 'steps': 3085, 'loss/train': 2.859093189239502} 08/30/2021 13:45:59 - INFO - __main__ - Step 3087: {'lr': 0.0004999335757368595, 'samples': 592704, 'steps': 3086, 'loss/train': 2.915008306503296} 08/30/2021 13:45:59 - INFO - __main__ - Step 3088: {'lr': 0.0004999334533576757, 'samples': 592896, 'steps': 3087, 'loss/train': 3.409656286239624} 08/30/2021 13:46:00 - INFO - __main__ - Step 3089: {'lr': 0.0004999333308658756, 'samples': 593088, 'steps': 3088, 'loss/train': 2.9248416423797607} 08/30/2021 13:46:00 - INFO - __main__ - Step 3090: {'lr': 0.0004999332082614597, 'samples': 593280, 'steps': 3089, 'loss/train': 2.986475706100464} 08/30/2021 13:46:01 - INFO - __main__ - Step 3091: {'lr': 0.0004999330855444274, 'samples': 593472, 'steps': 3090, 'loss/train': 2.7550384998321533} 08/30/2021 13:46:02 - INFO - __main__ - Step 3092: {'lr': 0.0004999329627147792, 'samples': 593664, 'steps': 3091, 'loss/train': 2.990790367126465} 08/30/2021 13:46:02 - INFO - __main__ - Step 3093: {'lr': 0.0004999328397725152, 'samples': 593856, 'steps': 3092, 'loss/train': 3.0946664810180664} 08/30/2021 13:46:03 - INFO - __main__ - Step 3094: {'lr': 0.0004999327167176352, 'samples': 594048, 'steps': 3093, 'loss/train': 2.7758359909057617} 08/30/2021 13:46:03 - INFO - __main__ - Step 3095: {'lr': 0.0004999325935501395, 'samples': 594240, 'steps': 3094, 'loss/train': 2.7876522541046143} 08/30/2021 13:46:05 - INFO - __main__ - Step 3096: {'lr': 0.0004999324702700279, 'samples': 594432, 'steps': 3095, 'loss/train': 2.8208346366882324} 08/30/2021 13:46:05 - INFO - __main__ - Step 3097: {'lr': 0.0004999323468773007, 'samples': 594624, 'steps': 3096, 'loss/train': 2.5343258380889893} 08/30/2021 13:46:05 - INFO - __main__ - Step 3098: {'lr': 0.0004999322233719578, 'samples': 594816, 'steps': 3097, 'loss/train': 2.228133201599121} 08/30/2021 13:46:06 - INFO - __main__ - Step 3099: {'lr': 0.0004999320997539992, 'samples': 595008, 'steps': 3098, 'loss/train': 2.6890482902526855} 08/30/2021 13:46:06 - INFO - __main__ - Step 3100: {'lr': 0.0004999319760234251, 'samples': 595200, 'steps': 3099, 'loss/train': 2.4737637042999268} 08/30/2021 13:46:08 - INFO - __main__ - Step 3101: {'lr': 0.0004999318521802356, 'samples': 595392, 'steps': 3100, 'loss/train': 2.4688541889190674} 08/30/2021 13:46:08 - INFO - __main__ - Step 3102: {'lr': 0.0004999317282244305, 'samples': 595584, 'steps': 3101, 'loss/train': 3.134523391723633} 08/30/2021 13:46:08 - INFO - __main__ - Step 3103: {'lr': 0.0004999316041560102, 'samples': 595776, 'steps': 3102, 'loss/train': 3.150975465774536} 08/30/2021 13:46:09 - INFO - __main__ - Step 3104: {'lr': 0.0004999314799749745, 'samples': 595968, 'steps': 3103, 'loss/train': 3.054753303527832} 08/30/2021 13:46:09 - INFO - __main__ - Step 3105: {'lr': 0.0004999313556813235, 'samples': 596160, 'steps': 3104, 'loss/train': 2.088566541671753} 08/30/2021 13:46:11 - INFO - __main__ - Step 3106: {'lr': 0.0004999312312750573, 'samples': 596352, 'steps': 3105, 'loss/train': 2.5453414916992188} 08/30/2021 13:46:11 - INFO - __main__ - Step 3107: {'lr': 0.000499931106756176, 'samples': 596544, 'steps': 3106, 'loss/train': 2.4794046878814697} 08/30/2021 13:46:11 - INFO - __main__ - Step 3108: {'lr': 0.0004999309821246795, 'samples': 596736, 'steps': 3107, 'loss/train': 1.930832862854004} 08/30/2021 13:46:12 - INFO - __main__ - Step 3109: {'lr': 0.000499930857380568, 'samples': 596928, 'steps': 3108, 'loss/train': 2.0653395652770996} 08/30/2021 13:46:12 - INFO - __main__ - Step 3110: {'lr': 0.0004999307325238416, 'samples': 597120, 'steps': 3109, 'loss/train': 3.090510129928589} 08/30/2021 13:46:12 - INFO - __main__ - Step 3111: {'lr': 0.0004999306075545002, 'samples': 597312, 'steps': 3110, 'loss/train': 2.944995880126953} 08/30/2021 13:46:14 - INFO - __main__ - Step 3112: {'lr': 0.0004999304824725439, 'samples': 597504, 'steps': 3111, 'loss/train': 2.595315933227539} 08/30/2021 13:46:14 - INFO - __main__ - Step 3113: {'lr': 0.0004999303572779727, 'samples': 597696, 'steps': 3112, 'loss/train': 2.949462413787842} 08/30/2021 13:46:15 - INFO - __main__ - Step 3114: {'lr': 0.0004999302319707869, 'samples': 597888, 'steps': 3113, 'loss/train': 2.5815327167510986} 08/30/2021 13:46:15 - INFO - __main__ - Step 3115: {'lr': 0.0004999301065509863, 'samples': 598080, 'steps': 3114, 'loss/train': 3.0499043464660645} 08/30/2021 13:46:15 - INFO - __main__ - Step 3116: {'lr': 0.0004999299810185712, 'samples': 598272, 'steps': 3115, 'loss/train': 2.263648748397827} 08/30/2021 13:46:17 - INFO - __main__ - Step 3117: {'lr': 0.0004999298553735413, 'samples': 598464, 'steps': 3116, 'loss/train': 2.9172823429107666} 08/30/2021 13:46:17 - INFO - __main__ - Step 3118: {'lr': 0.000499929729615897, 'samples': 598656, 'steps': 3117, 'loss/train': 2.170206308364868} 08/30/2021 13:46:18 - INFO - __main__ - Step 3119: {'lr': 0.0004999296037456381, 'samples': 598848, 'steps': 3118, 'loss/train': 2.7277300357818604} 08/30/2021 13:46:18 - INFO - __main__ - Step 3120: {'lr': 0.0004999294777627649, 'samples': 599040, 'steps': 3119, 'loss/train': 2.7261152267456055} 08/30/2021 13:46:19 - INFO - __main__ - Step 3121: {'lr': 0.0004999293516672773, 'samples': 599232, 'steps': 3120, 'loss/train': 2.6429615020751953} 08/30/2021 13:46:21 - INFO - __main__ - Step 3122: {'lr': 0.0004999292254591754, 'samples': 599424, 'steps': 3121, 'loss/train': 0.48724889755249023} 08/30/2021 13:46:21 - INFO - __main__ - Step 3123: {'lr': 0.0004999290991384591, 'samples': 599616, 'steps': 3122, 'loss/train': 2.0068628787994385} 08/30/2021 13:46:22 - INFO - __main__ - Step 3124: {'lr': 0.0004999289727051289, 'samples': 599808, 'steps': 3123, 'loss/train': 2.296069860458374} 08/30/2021 13:46:22 - INFO - __main__ - Step 3125: {'lr': 0.0004999288461591842, 'samples': 600000, 'steps': 3124, 'loss/train': 3.5134057998657227} 08/30/2021 13:46:23 - INFO - __main__ - Step 3126: {'lr': 0.0004999287195006257, 'samples': 600192, 'steps': 3125, 'loss/train': 2.448402166366577} 08/30/2021 13:46:24 - INFO - __main__ - Step 3127: {'lr': 0.000499928592729453, 'samples': 600384, 'steps': 3126, 'loss/train': 2.403609037399292} 08/30/2021 13:46:24 - INFO - __main__ - Step 3128: {'lr': 0.0004999284658456665, 'samples': 600576, 'steps': 3127, 'loss/train': 2.4453182220458984} 08/30/2021 13:46:25 - INFO - __main__ - Step 3129: {'lr': 0.000499928338849266, 'samples': 600768, 'steps': 3128, 'loss/train': 2.8014326095581055} 08/30/2021 13:46:25 - INFO - __main__ - Step 3130: {'lr': 0.0004999282117402516, 'samples': 600960, 'steps': 3129, 'loss/train': 2.376030445098877} 08/30/2021 13:46:26 - INFO - __main__ - Step 3131: {'lr': 0.0004999280845186235, 'samples': 601152, 'steps': 3130, 'loss/train': 2.396571159362793} 08/30/2021 13:46:26 - INFO - __main__ - Step 3132: {'lr': 0.0004999279571843816, 'samples': 601344, 'steps': 3131, 'loss/train': 2.4883921146392822} 08/30/2021 13:46:28 - INFO - __main__ - Step 3133: {'lr': 0.000499927829737526, 'samples': 601536, 'steps': 3132, 'loss/train': 2.477632999420166} 08/30/2021 13:46:28 - INFO - __main__ - Step 3134: {'lr': 0.0004999277021780569, 'samples': 601728, 'steps': 3133, 'loss/train': 2.8598475456237793} 08/30/2021 13:46:29 - INFO - __main__ - Step 3135: {'lr': 0.0004999275745059741, 'samples': 601920, 'steps': 3134, 'loss/train': 3.3187780380249023} 08/30/2021 13:46:29 - INFO - __main__ - Step 3136: {'lr': 0.0004999274467212779, 'samples': 602112, 'steps': 3135, 'loss/train': 2.6064679622650146} 08/30/2021 13:46:29 - INFO - __main__ - Step 3137: {'lr': 0.0004999273188239681, 'samples': 602304, 'steps': 3136, 'loss/train': 3.262578248977661} 08/30/2021 13:46:31 - INFO - __main__ - Step 3138: {'lr': 0.0004999271908140451, 'samples': 602496, 'steps': 3137, 'loss/train': 4.358016490936279} 08/30/2021 13:46:31 - INFO - __main__ - Step 3139: {'lr': 0.0004999270626915086, 'samples': 602688, 'steps': 3138, 'loss/train': 2.5021872520446777} 08/30/2021 13:46:32 - INFO - __main__ - Step 3140: {'lr': 0.0004999269344563589, 'samples': 602880, 'steps': 3139, 'loss/train': 2.635646343231201} 08/30/2021 13:46:32 - INFO - __main__ - Step 3141: {'lr': 0.0004999268061085959, 'samples': 603072, 'steps': 3140, 'loss/train': 2.6724436283111572} 08/30/2021 13:46:32 - INFO - __main__ - Step 3142: {'lr': 0.0004999266776482199, 'samples': 603264, 'steps': 3141, 'loss/train': 2.859872579574585} 08/30/2021 13:46:34 - INFO - __main__ - Step 3143: {'lr': 0.0004999265490752306, 'samples': 603456, 'steps': 3142, 'loss/train': 1.779443383216858} 08/30/2021 13:46:34 - INFO - __main__ - Step 3144: {'lr': 0.0004999264203896284, 'samples': 603648, 'steps': 3143, 'loss/train': 2.3480141162872314} 08/30/2021 13:46:34 - INFO - __main__ - Step 3145: {'lr': 0.0004999262915914132, 'samples': 603840, 'steps': 3144, 'loss/train': 2.638678550720215} 08/30/2021 13:46:35 - INFO - __main__ - Step 3146: {'lr': 0.000499926162680585, 'samples': 604032, 'steps': 3145, 'loss/train': 1.5302430391311646} 08/30/2021 13:46:35 - INFO - __main__ - Step 3147: {'lr': 0.000499926033657144, 'samples': 604224, 'steps': 3146, 'loss/train': 2.6154024600982666} 08/30/2021 13:46:37 - INFO - __main__ - Step 3148: {'lr': 0.0004999259045210901, 'samples': 604416, 'steps': 3147, 'loss/train': 2.933009147644043} 08/30/2021 13:46:37 - INFO - __main__ - Step 3149: {'lr': 0.0004999257752724234, 'samples': 604608, 'steps': 3148, 'loss/train': 2.689781427383423} 08/30/2021 13:46:38 - INFO - __main__ - Step 3150: {'lr': 0.0004999256459111443, 'samples': 604800, 'steps': 3149, 'loss/train': 3.92864727973938} 08/30/2021 13:46:38 - INFO - __main__ - Step 3151: {'lr': 0.0004999255164372523, 'samples': 604992, 'steps': 3150, 'loss/train': 2.9216690063476562} 08/30/2021 13:46:38 - INFO - __main__ - Step 3152: {'lr': 0.0004999253868507476, 'samples': 605184, 'steps': 3151, 'loss/train': 1.0915896892547607} 08/30/2021 13:46:40 - INFO - __main__ - Step 3153: {'lr': 0.0004999252571516306, 'samples': 605376, 'steps': 3152, 'loss/train': 3.0541324615478516} 08/30/2021 13:46:40 - INFO - __main__ - Step 3154: {'lr': 0.0004999251273399011, 'samples': 605568, 'steps': 3153, 'loss/train': 2.8533623218536377} 08/30/2021 13:46:40 - INFO - __main__ - Step 3155: {'lr': 0.0004999249974155592, 'samples': 605760, 'steps': 3154, 'loss/train': 1.9612441062927246} 08/30/2021 13:46:41 - INFO - __main__ - Step 3156: {'lr': 0.0004999248673786049, 'samples': 605952, 'steps': 3155, 'loss/train': 2.6098594665527344} 08/30/2021 13:46:41 - INFO - __main__ - Step 3157: {'lr': 0.0004999247372290383, 'samples': 606144, 'steps': 3156, 'loss/train': 2.979992389678955} 08/30/2021 13:46:42 - INFO - __main__ - Step 3158: {'lr': 0.0004999246069668596, 'samples': 606336, 'steps': 3157, 'loss/train': 3.557257890701294} 08/30/2021 13:46:43 - INFO - __main__ - Step 3159: {'lr': 0.0004999244765920687, 'samples': 606528, 'steps': 3158, 'loss/train': 2.915217638015747} 08/30/2021 13:46:43 - INFO - __main__ - Step 3160: {'lr': 0.0004999243461046656, 'samples': 606720, 'steps': 3159, 'loss/train': 3.2726290225982666} 08/30/2021 13:46:44 - INFO - __main__ - Step 3161: {'lr': 0.0004999242155046504, 'samples': 606912, 'steps': 3160, 'loss/train': 2.917583465576172} 08/30/2021 13:46:44 - INFO - __main__ - Step 3162: {'lr': 0.0004999240847920233, 'samples': 607104, 'steps': 3161, 'loss/train': 2.02170467376709} 08/30/2021 13:46:44 - INFO - __main__ - Step 3163: {'lr': 0.0004999239539667842, 'samples': 607296, 'steps': 3162, 'loss/train': 2.193922519683838} 08/30/2021 13:46:46 - INFO - __main__ - Step 3164: {'lr': 0.0004999238230289333, 'samples': 607488, 'steps': 3163, 'loss/train': 3.0787715911865234} 08/30/2021 13:46:47 - INFO - __main__ - Step 3165: {'lr': 0.0004999236919784705, 'samples': 607680, 'steps': 3164, 'loss/train': 2.407846212387085} 08/30/2021 13:46:47 - INFO - __main__ - Step 3166: {'lr': 0.0004999235608153961, 'samples': 607872, 'steps': 3165, 'loss/train': 6.306263446807861} 08/30/2021 13:46:47 - INFO - __main__ - Step 3167: {'lr': 0.0004999234295397098, 'samples': 608064, 'steps': 3166, 'loss/train': 2.6810712814331055} 08/30/2021 13:46:48 - INFO - __main__ - Step 3168: {'lr': 0.000499923298151412, 'samples': 608256, 'steps': 3167, 'loss/train': 2.5126678943634033} 08/30/2021 13:46:48 - INFO - __main__ - Step 3169: {'lr': 0.0004999231666505025, 'samples': 608448, 'steps': 3168, 'loss/train': 2.035252332687378} 08/30/2021 13:46:50 - INFO - __main__ - Step 3170: {'lr': 0.0004999230350369816, 'samples': 608640, 'steps': 3169, 'loss/train': 2.936342716217041} 08/30/2021 13:46:51 - INFO - __main__ - Step 3171: {'lr': 0.0004999229033108492, 'samples': 608832, 'steps': 3170, 'loss/train': 2.796079397201538} 08/30/2021 13:46:51 - INFO - __main__ - Step 3172: {'lr': 0.0004999227714721054, 'samples': 609024, 'steps': 3171, 'loss/train': 2.489570379257202} 08/30/2021 13:46:52 - INFO - __main__ - Step 3173: {'lr': 0.0004999226395207501, 'samples': 609216, 'steps': 3172, 'loss/train': 2.50984525680542} 08/30/2021 13:46:52 - INFO - __main__ - Step 3174: {'lr': 0.0004999225074567837, 'samples': 609408, 'steps': 3173, 'loss/train': 2.986717939376831} 08/30/2021 13:46:52 - INFO - __main__ - Step 3175: {'lr': 0.000499922375280206, 'samples': 609600, 'steps': 3174, 'loss/train': 3.0193252563476562} 08/30/2021 13:46:55 - INFO - __main__ - Step 3176: {'lr': 0.0004999222429910171, 'samples': 609792, 'steps': 3175, 'loss/train': 3.845912218093872} 08/30/2021 13:46:55 - INFO - __main__ - Step 3177: {'lr': 0.0004999221105892172, 'samples': 609984, 'steps': 3176, 'loss/train': 3.3472275733947754} 08/30/2021 13:46:56 - INFO - __main__ - Step 3178: {'lr': 0.0004999219780748062, 'samples': 610176, 'steps': 3177, 'loss/train': 2.7961440086364746} 08/30/2021 13:46:56 - INFO - __main__ - Step 3179: {'lr': 0.0004999218454477843, 'samples': 610368, 'steps': 3178, 'loss/train': 3.055490732192993} 08/30/2021 13:46:56 - INFO - __main__ - Step 3180: {'lr': 0.0004999217127081514, 'samples': 610560, 'steps': 3179, 'loss/train': 4.990219593048096} 08/30/2021 13:46:57 - INFO - __main__ - Step 3181: {'lr': 0.0004999215798559076, 'samples': 610752, 'steps': 3180, 'loss/train': 3.0262258052825928} 08/30/2021 13:46:58 - INFO - __main__ - Step 3182: {'lr': 0.000499921446891053, 'samples': 610944, 'steps': 3181, 'loss/train': 3.575921058654785} 08/30/2021 13:46:59 - INFO - __main__ - Step 3183: {'lr': 0.0004999213138135877, 'samples': 611136, 'steps': 3182, 'loss/train': 2.4072868824005127} 08/30/2021 13:46:59 - INFO - __main__ - Step 3184: {'lr': 0.0004999211806235117, 'samples': 611328, 'steps': 3183, 'loss/train': 3.0549840927124023} 08/30/2021 13:46:59 - INFO - __main__ - Step 3185: {'lr': 0.000499921047320825, 'samples': 611520, 'steps': 3184, 'loss/train': 3.205899715423584} 08/30/2021 13:47:00 - INFO - __main__ - Step 3186: {'lr': 0.0004999209139055278, 'samples': 611712, 'steps': 3185, 'loss/train': 3.4004037380218506} 08/30/2021 13:47:01 - INFO - __main__ - Step 3187: {'lr': 0.0004999207803776201, 'samples': 611904, 'steps': 3186, 'loss/train': 3.189333438873291} 08/30/2021 13:47:02 - INFO - __main__ - Step 3188: {'lr': 0.000499920646737102, 'samples': 612096, 'steps': 3187, 'loss/train': 1.065770149230957} 08/30/2021 13:47:02 - INFO - __main__ - Step 3189: {'lr': 0.0004999205129839734, 'samples': 612288, 'steps': 3188, 'loss/train': 3.436750888824463} 08/30/2021 13:47:03 - INFO - __main__ - Step 3190: {'lr': 0.0004999203791182345, 'samples': 612480, 'steps': 3189, 'loss/train': 4.105352878570557} 08/30/2021 13:47:03 - INFO - __main__ - Step 3191: {'lr': 0.0004999202451398853, 'samples': 612672, 'steps': 3190, 'loss/train': 3.031970739364624} 08/30/2021 13:47:03 - INFO - __main__ - Step 3192: {'lr': 0.000499920111048926, 'samples': 612864, 'steps': 3191, 'loss/train': 2.3613171577453613} 08/30/2021 13:47:05 - INFO - __main__ - Step 3193: {'lr': 0.0004999199768453565, 'samples': 613056, 'steps': 3192, 'loss/train': 2.7101738452911377} 08/30/2021 13:47:05 - INFO - __main__ - Step 3194: {'lr': 0.0004999198425291769, 'samples': 613248, 'steps': 3193, 'loss/train': 3.037245035171509} 08/30/2021 13:47:06 - INFO - __main__ - Step 3195: {'lr': 0.0004999197081003873, 'samples': 613440, 'steps': 3194, 'loss/train': 3.037924289703369} 08/30/2021 13:47:06 - INFO - __main__ - Step 3196: {'lr': 0.0004999195735589877, 'samples': 613632, 'steps': 3195, 'loss/train': 3.242856025695801} 08/30/2021 13:47:06 - INFO - __main__ - Step 3197: {'lr': 0.0004999194389049783, 'samples': 613824, 'steps': 3196, 'loss/train': 3.041048765182495} 08/30/2021 13:47:08 - INFO - __main__ - Step 3198: {'lr': 0.0004999193041383588, 'samples': 614016, 'steps': 3197, 'loss/train': 3.4910566806793213} 08/30/2021 13:47:08 - INFO - __main__ - Step 3199: {'lr': 0.0004999191692591299, 'samples': 614208, 'steps': 3198, 'loss/train': 4.287659645080566} 08/30/2021 13:47:09 - INFO - __main__ - Step 3200: {'lr': 0.000499919034267291, 'samples': 614400, 'steps': 3199, 'loss/train': 2.7867040634155273} 08/30/2021 13:47:09 - INFO - __main__ - Step 3201: {'lr': 0.0004999188991628425, 'samples': 614592, 'steps': 3200, 'loss/train': 2.268404483795166} 08/30/2021 13:47:09 - INFO - __main__ - Step 3202: {'lr': 0.0004999187639457844, 'samples': 614784, 'steps': 3201, 'loss/train': 2.992171049118042} 08/30/2021 13:47:11 - INFO - __main__ - Step 3203: {'lr': 0.0004999186286161169, 'samples': 614976, 'steps': 3202, 'loss/train': 2.7562453746795654} 08/30/2021 13:47:12 - INFO - __main__ - Step 3204: {'lr': 0.0004999184931738397, 'samples': 615168, 'steps': 3203, 'loss/train': 1.3342421054840088} 08/30/2021 13:47:12 - INFO - __main__ - Step 3205: {'lr': 0.0004999183576189532, 'samples': 615360, 'steps': 3204, 'loss/train': 2.7941534519195557} 08/30/2021 13:47:12 - INFO - __main__ - Step 3206: {'lr': 0.0004999182219514573, 'samples': 615552, 'steps': 3205, 'loss/train': 2.1377646923065186} 08/30/2021 13:47:13 - INFO - __main__ - Step 3207: {'lr': 0.0004999180861713522, 'samples': 615744, 'steps': 3206, 'loss/train': 3.188704013824463} 08/30/2021 13:47:15 - INFO - __main__ - Step 3208: {'lr': 0.0004999179502786377, 'samples': 615936, 'steps': 3207, 'loss/train': 2.582209587097168} 08/30/2021 13:47:15 - INFO - __main__ - Step 3209: {'lr': 0.0004999178142733141, 'samples': 616128, 'steps': 3208, 'loss/train': 2.6052796840667725} 08/30/2021 13:47:15 - INFO - __main__ - Step 3210: {'lr': 0.0004999176781553815, 'samples': 616320, 'steps': 3209, 'loss/train': 3.0828773975372314} 08/30/2021 13:47:16 - INFO - __main__ - Step 3211: {'lr': 0.0004999175419248398, 'samples': 616512, 'steps': 3210, 'loss/train': 2.756396770477295} 08/30/2021 13:47:16 - INFO - __main__ - Step 3212: {'lr': 0.0004999174055816891, 'samples': 616704, 'steps': 3211, 'loss/train': 2.909679651260376} 08/30/2021 13:47:16 - INFO - __main__ - Step 3213: {'lr': 0.0004999172691259293, 'samples': 616896, 'steps': 3212, 'loss/train': 3.3466978073120117} 08/30/2021 13:47:18 - INFO - __main__ - Step 3214: {'lr': 0.0004999171325575609, 'samples': 617088, 'steps': 3213, 'loss/train': 0.6976868510246277} 08/30/2021 13:47:18 - INFO - __main__ - Step 3215: {'lr': 0.0004999169958765836, 'samples': 617280, 'steps': 3214, 'loss/train': 2.3229188919067383} 08/30/2021 13:47:19 - INFO - __main__ - Step 3216: {'lr': 0.0004999168590829975, 'samples': 617472, 'steps': 3215, 'loss/train': 2.50573468208313} 08/30/2021 13:47:19 - INFO - __main__ - Step 3217: {'lr': 0.0004999167221768028, 'samples': 617664, 'steps': 3216, 'loss/train': 2.442990303039551} 08/30/2021 13:47:19 - INFO - __main__ - Step 3218: {'lr': 0.0004999165851579994, 'samples': 617856, 'steps': 3217, 'loss/train': 3.084824800491333} 08/30/2021 13:47:21 - INFO - __main__ - Step 3219: {'lr': 0.0004999164480265875, 'samples': 618048, 'steps': 3218, 'loss/train': 2.7596936225891113} 08/30/2021 13:47:22 - INFO - __main__ - Step 3220: {'lr': 0.0004999163107825671, 'samples': 618240, 'steps': 3219, 'loss/train': 2.5256688594818115} 08/30/2021 13:47:22 - INFO - __main__ - Step 3221: {'lr': 0.0004999161734259383, 'samples': 618432, 'steps': 3220, 'loss/train': 3.144214630126953} 08/30/2021 13:47:22 - INFO - __main__ - Step 3222: {'lr': 0.0004999160359567011, 'samples': 618624, 'steps': 3221, 'loss/train': 2.37947940826416} 08/30/2021 13:47:23 - INFO - __main__ - Step 3223: {'lr': 0.0004999158983748555, 'samples': 618816, 'steps': 3222, 'loss/train': 2.7375147342681885} 08/30/2021 13:47:24 - INFO - __main__ - Step 3224: {'lr': 0.0004999157606804018, 'samples': 619008, 'steps': 3223, 'loss/train': 1.6062546968460083} 08/30/2021 13:47:25 - INFO - __main__ - Step 3225: {'lr': 0.0004999156228733398, 'samples': 619200, 'steps': 3224, 'loss/train': 2.4721710681915283} 08/30/2021 13:47:25 - INFO - __main__ - Step 3226: {'lr': 0.0004999154849536698, 'samples': 619392, 'steps': 3225, 'loss/train': 2.4993298053741455} 08/30/2021 13:47:25 - INFO - __main__ - Step 3227: {'lr': 0.0004999153469213917, 'samples': 619584, 'steps': 3226, 'loss/train': 2.770925283432007} 08/30/2021 13:47:26 - INFO - __main__ - Step 3228: {'lr': 0.0004999152087765055, 'samples': 619776, 'steps': 3227, 'loss/train': 2.7168385982513428} 08/30/2021 13:47:26 - INFO - __main__ - Step 3229: {'lr': 0.0004999150705190114, 'samples': 619968, 'steps': 3228, 'loss/train': 3.37111496925354} 08/30/2021 13:47:28 - INFO - __main__ - Step 3230: {'lr': 0.0004999149321489095, 'samples': 620160, 'steps': 3229, 'loss/train': 3.021174430847168} 08/30/2021 13:47:29 - INFO - __main__ - Step 3231: {'lr': 0.0004999147936661997, 'samples': 620352, 'steps': 3230, 'loss/train': 2.9290390014648438} 08/30/2021 13:47:29 - INFO - __main__ - Step 3232: {'lr': 0.0004999146550708822, 'samples': 620544, 'steps': 3231, 'loss/train': 2.412423849105835} 08/30/2021 13:47:29 - INFO - __main__ - Step 3233: {'lr': 0.000499914516362957, 'samples': 620736, 'steps': 3232, 'loss/train': 3.0570268630981445} 08/30/2021 13:47:30 - INFO - __main__ - Step 3234: {'lr': 0.0004999143775424241, 'samples': 620928, 'steps': 3233, 'loss/train': 1.90534245967865} 08/30/2021 13:47:31 - INFO - __main__ - Step 3235: {'lr': 0.0004999142386092838, 'samples': 621120, 'steps': 3234, 'loss/train': 2.9524097442626953} 08/30/2021 13:47:32 - INFO - __main__ - Step 3236: {'lr': 0.000499914099563536, 'samples': 621312, 'steps': 3235, 'loss/train': 4.571676731109619} 08/30/2021 13:47:32 - INFO - __main__ - Step 3237: {'lr': 0.0004999139604051806, 'samples': 621504, 'steps': 3236, 'loss/train': 3.1490585803985596} 08/30/2021 13:47:33 - INFO - __main__ - Step 3238: {'lr': 0.0004999138211342179, 'samples': 621696, 'steps': 3237, 'loss/train': 3.0514590740203857} 08/30/2021 13:47:33 - INFO - __main__ - Step 3239: {'lr': 0.0004999136817506478, 'samples': 621888, 'steps': 3238, 'loss/train': 0.9605992436408997} 08/30/2021 13:47:34 - INFO - __main__ - Step 3240: {'lr': 0.0004999135422544707, 'samples': 622080, 'steps': 3239, 'loss/train': 2.3694913387298584} 08/30/2021 13:47:35 - INFO - __main__ - Step 3241: {'lr': 0.0004999134026456862, 'samples': 622272, 'steps': 3240, 'loss/train': 2.468559980392456} 08/30/2021 13:47:35 - INFO - __main__ - Step 3242: {'lr': 0.0004999132629242946, 'samples': 622464, 'steps': 3241, 'loss/train': 3.220627784729004} 08/30/2021 13:47:36 - INFO - __main__ - Step 3243: {'lr': 0.000499913123090296, 'samples': 622656, 'steps': 3242, 'loss/train': 2.988105535507202} 08/30/2021 13:47:36 - INFO - __main__ - Step 3244: {'lr': 0.0004999129831436904, 'samples': 622848, 'steps': 3243, 'loss/train': 2.8485569953918457} 08/30/2021 13:47:37 - INFO - __main__ - Step 3245: {'lr': 0.0004999128430844778, 'samples': 623040, 'steps': 3244, 'loss/train': 1.7911012172698975} 08/30/2021 13:47:38 - INFO - __main__ - Step 3246: {'lr': 0.0004999127029126585, 'samples': 623232, 'steps': 3245, 'loss/train': 2.9321649074554443} 08/30/2021 13:47:38 - INFO - __main__ - Step 3247: {'lr': 0.0004999125626282322, 'samples': 623424, 'steps': 3246, 'loss/train': 2.5870540142059326} 08/30/2021 13:47:38 - INFO - __main__ - Step 3248: {'lr': 0.0004999124222311993, 'samples': 623616, 'steps': 3247, 'loss/train': 2.862294912338257} 08/30/2021 13:47:39 - INFO - __main__ - Step 3249: {'lr': 0.0004999122817215595, 'samples': 623808, 'steps': 3248, 'loss/train': 2.49239444732666} 08/30/2021 13:47:40 - INFO - __main__ - Step 3250: {'lr': 0.0004999121410993133, 'samples': 624000, 'steps': 3249, 'loss/train': 2.8708701133728027} 08/30/2021 13:47:41 - INFO - __main__ - Step 3251: {'lr': 0.0004999120003644604, 'samples': 624192, 'steps': 3250, 'loss/train': 2.5049490928649902} 08/30/2021 13:47:41 - INFO - __main__ - Step 3252: {'lr': 0.0004999118595170011, 'samples': 624384, 'steps': 3251, 'loss/train': 3.0734362602233887} 08/30/2021 13:47:41 - INFO - __main__ - Step 3253: {'lr': 0.0004999117185569354, 'samples': 624576, 'steps': 3252, 'loss/train': 2.3230626583099365} 08/30/2021 13:47:42 - INFO - __main__ - Step 3254: {'lr': 0.0004999115774842633, 'samples': 624768, 'steps': 3253, 'loss/train': 3.3489320278167725} 08/30/2021 13:47:44 - INFO - __main__ - Step 3255: {'lr': 0.0004999114362989849, 'samples': 624960, 'steps': 3254, 'loss/train': 2.6042723655700684} 08/30/2021 13:47:44 - INFO - __main__ - Step 3256: {'lr': 0.0004999112950011002, 'samples': 625152, 'steps': 3255, 'loss/train': 3.1600685119628906} 08/30/2021 13:47:44 - INFO - __main__ - Step 3257: {'lr': 0.0004999111535906094, 'samples': 625344, 'steps': 3256, 'loss/train': 3.0841994285583496} 08/30/2021 13:47:45 - INFO - __main__ - Step 3258: {'lr': 0.0004999110120675125, 'samples': 625536, 'steps': 3257, 'loss/train': 2.4904887676239014} 08/30/2021 13:47:45 - INFO - __main__ - Step 3259: {'lr': 0.0004999108704318095, 'samples': 625728, 'steps': 3258, 'loss/train': 0.7025074362754822} 08/30/2021 13:47:47 - INFO - __main__ - Step 3260: {'lr': 0.0004999107286835006, 'samples': 625920, 'steps': 3259, 'loss/train': 2.1461243629455566} 08/30/2021 13:47:47 - INFO - __main__ - Step 3261: {'lr': 0.0004999105868225858, 'samples': 626112, 'steps': 3260, 'loss/train': 2.9746410846710205} 08/30/2021 13:47:47 - INFO - __main__ - Step 3262: {'lr': 0.0004999104448490649, 'samples': 626304, 'steps': 3261, 'loss/train': 1.9697314500808716} 08/30/2021 13:47:48 - INFO - __main__ - Step 3263: {'lr': 0.0004999103027629384, 'samples': 626496, 'steps': 3262, 'loss/train': 2.3351855278015137} 08/30/2021 13:47:48 - INFO - __main__ - Step 3264: {'lr': 0.0004999101605642061, 'samples': 626688, 'steps': 3263, 'loss/train': 2.5148749351501465} 08/30/2021 13:47:49 - INFO - __main__ - Step 3265: {'lr': 0.0004999100182528683, 'samples': 626880, 'steps': 3264, 'loss/train': 2.81813383102417} 08/30/2021 13:47:50 - INFO - __main__ - Step 3266: {'lr': 0.0004999098758289248, 'samples': 627072, 'steps': 3265, 'loss/train': 2.612733840942383} 08/30/2021 13:47:50 - INFO - __main__ - Step 3267: {'lr': 0.0004999097332923758, 'samples': 627264, 'steps': 3266, 'loss/train': 2.461395740509033} 08/30/2021 13:47:51 - INFO - __main__ - Step 3268: {'lr': 0.0004999095906432213, 'samples': 627456, 'steps': 3267, 'loss/train': 2.8094491958618164} 08/30/2021 13:47:51 - INFO - __main__ - Step 3269: {'lr': 0.0004999094478814613, 'samples': 627648, 'steps': 3268, 'loss/train': 2.8189516067504883} 08/30/2021 13:47:51 - INFO - __main__ - Step 3270: {'lr': 0.0004999093050070961, 'samples': 627840, 'steps': 3269, 'loss/train': 2.4825503826141357} 08/30/2021 13:47:53 - INFO - __main__ - Step 3271: {'lr': 0.0004999091620201255, 'samples': 628032, 'steps': 3270, 'loss/train': 2.7980663776397705} 08/30/2021 13:47:53 - INFO - __main__ - Step 3272: {'lr': 0.0004999090189205498, 'samples': 628224, 'steps': 3271, 'loss/train': 2.6761281490325928} 08/30/2021 13:47:54 - INFO - __main__ - Step 3273: {'lr': 0.0004999088757083689, 'samples': 628416, 'steps': 3272, 'loss/train': 1.788774847984314} 08/30/2021 13:47:54 - INFO - __main__ - Step 3274: {'lr': 0.0004999087323835829, 'samples': 628608, 'steps': 3273, 'loss/train': 2.6867196559906006} 08/30/2021 13:47:54 - INFO - __main__ - Step 3275: {'lr': 0.0004999085889461919, 'samples': 628800, 'steps': 3274, 'loss/train': 2.401261806488037} 08/30/2021 13:47:56 - INFO - __main__ - Step 3276: {'lr': 0.0004999084453961959, 'samples': 628992, 'steps': 3275, 'loss/train': 2.571923017501831} 08/30/2021 13:47:57 - INFO - __main__ - Step 3277: {'lr': 0.0004999083017335951, 'samples': 629184, 'steps': 3276, 'loss/train': 2.670154094696045} 08/30/2021 13:47:57 - INFO - __main__ - Step 3278: {'lr': 0.0004999081579583895, 'samples': 629376, 'steps': 3277, 'loss/train': 1.959620475769043} 08/30/2021 13:47:57 - INFO - __main__ - Step 3279: {'lr': 0.0004999080140705791, 'samples': 629568, 'steps': 3278, 'loss/train': 2.1653659343719482} 08/30/2021 13:47:58 - INFO - __main__ - Step 3280: {'lr': 0.0004999078700701639, 'samples': 629760, 'steps': 3279, 'loss/train': 1.4701002836227417} 08/30/2021 13:47:58 - INFO - __main__ - Step 3281: {'lr': 0.0004999077259571442, 'samples': 629952, 'steps': 3280, 'loss/train': 1.766237497329712} 08/30/2021 13:47:59 - INFO - __main__ - Step 3282: {'lr': 0.0004999075817315199, 'samples': 630144, 'steps': 3281, 'loss/train': 2.268458843231201} 08/30/2021 13:48:00 - INFO - __main__ - Step 3283: {'lr': 0.0004999074373932911, 'samples': 630336, 'steps': 3282, 'loss/train': 2.3677804470062256} 08/30/2021 13:48:00 - INFO - __main__ - Step 3284: {'lr': 0.0004999072929424579, 'samples': 630528, 'steps': 3283, 'loss/train': 2.5171844959259033} 08/30/2021 13:48:01 - INFO - __main__ - Step 3285: {'lr': 0.0004999071483790203, 'samples': 630720, 'steps': 3284, 'loss/train': 3.5679070949554443} 08/30/2021 13:48:01 - INFO - __main__ - Step 3286: {'lr': 0.0004999070037029783, 'samples': 630912, 'steps': 3285, 'loss/train': 2.1660118103027344} 08/30/2021 13:48:03 - INFO - __main__ - Step 3287: {'lr': 0.0004999068589143322, 'samples': 631104, 'steps': 3286, 'loss/train': 2.397390365600586} 08/30/2021 13:48:04 - INFO - __main__ - Step 3288: {'lr': 0.0004999067140130819, 'samples': 631296, 'steps': 3287, 'loss/train': 2.073444128036499} 08/30/2021 13:48:04 - INFO - __main__ - Step 3289: {'lr': 0.0004999065689992273, 'samples': 631488, 'steps': 3288, 'loss/train': 0.5190285444259644} 08/30/2021 13:48:05 - INFO - __main__ - Step 3290: {'lr': 0.0004999064238727689, 'samples': 631680, 'steps': 3289, 'loss/train': 2.7662148475646973} 08/30/2021 13:48:05 - INFO - __main__ - Step 3291: {'lr': 0.0004999062786337064, 'samples': 631872, 'steps': 3290, 'loss/train': 2.8064463138580322} 08/30/2021 13:48:06 - INFO - __main__ - Step 3292: {'lr': 0.0004999061332820401, 'samples': 632064, 'steps': 3291, 'loss/train': 2.773684501647949} 08/30/2021 13:48:07 - INFO - __main__ - Step 3293: {'lr': 0.0004999059878177699, 'samples': 632256, 'steps': 3292, 'loss/train': 2.9490532875061035} 08/30/2021 13:48:07 - INFO - __main__ - Step 3294: {'lr': 0.0004999058422408959, 'samples': 632448, 'steps': 3293, 'loss/train': 2.387587785720825} 08/30/2021 13:48:08 - INFO - __main__ - Step 3295: {'lr': 0.0004999056965514181, 'samples': 632640, 'steps': 3294, 'loss/train': 2.536912679672241} 08/30/2021 13:48:08 - INFO - __main__ - Step 3296: {'lr': 0.0004999055507493368, 'samples': 632832, 'steps': 3295, 'loss/train': 2.3596861362457275} 08/30/2021 13:48:09 - INFO - __main__ - Step 3297: {'lr': 0.0004999054048346517, 'samples': 633024, 'steps': 3296, 'loss/train': 2.387342929840088} 08/30/2021 13:48:10 - INFO - __main__ - Step 3298: {'lr': 0.0004999052588073633, 'samples': 633216, 'steps': 3297, 'loss/train': 2.5546672344207764} 08/30/2021 13:48:10 - INFO - __main__ - Step 3299: {'lr': 0.0004999051126674714, 'samples': 633408, 'steps': 3298, 'loss/train': 2.604255437850952} 08/30/2021 13:48:11 - INFO - __main__ - Step 3300: {'lr': 0.0004999049664149761, 'samples': 633600, 'steps': 3299, 'loss/train': 2.6365129947662354} 08/30/2021 13:48:11 - INFO - __main__ - Step 3301: {'lr': 0.0004999048200498774, 'samples': 633792, 'steps': 3300, 'loss/train': 2.722532033920288} 08/30/2021 13:48:12 - INFO - __main__ - Step 3302: {'lr': 0.0004999046735721755, 'samples': 633984, 'steps': 3301, 'loss/train': 2.8905324935913086} 08/30/2021 13:48:13 - INFO - __main__ - Step 3303: {'lr': 0.0004999045269818704, 'samples': 634176, 'steps': 3302, 'loss/train': 2.822232961654663} 08/30/2021 13:48:13 - INFO - __main__ - Step 3304: {'lr': 0.0004999043802789622, 'samples': 634368, 'steps': 3303, 'loss/train': 2.6634597778320312} 08/30/2021 13:48:13 - INFO - __main__ - Step 3305: {'lr': 0.000499904233463451, 'samples': 634560, 'steps': 3304, 'loss/train': 2.9877405166625977} 08/30/2021 13:48:14 - INFO - __main__ - Step 3306: {'lr': 0.0004999040865353367, 'samples': 634752, 'steps': 3305, 'loss/train': 2.688408374786377} 08/30/2021 13:48:14 - INFO - __main__ - Step 3307: {'lr': 0.0004999039394946196, 'samples': 634944, 'steps': 3306, 'loss/train': 2.555669069290161} 08/30/2021 13:48:16 - INFO - __main__ - Step 3308: {'lr': 0.0004999037923412995, 'samples': 635136, 'steps': 3307, 'loss/train': 2.469919443130493} 08/30/2021 13:48:16 - INFO - __main__ - Step 3309: {'lr': 0.0004999036450753767, 'samples': 635328, 'steps': 3308, 'loss/train': 2.422785520553589} 08/30/2021 13:48:17 - INFO - __main__ - Step 3310: {'lr': 0.0004999034976968511, 'samples': 635520, 'steps': 3309, 'loss/train': 2.396209955215454} 08/30/2021 13:48:17 - INFO - __main__ - Step 3311: {'lr': 0.0004999033502057228, 'samples': 635712, 'steps': 3310, 'loss/train': 0.4965997040271759} 08/30/2021 13:48:17 - INFO - __main__ - Step 3312: {'lr': 0.000499903202601992, 'samples': 635904, 'steps': 3311, 'loss/train': 2.49814772605896} 08/30/2021 13:48:19 - INFO - __main__ - Step 3313: {'lr': 0.0004999030548856586, 'samples': 636096, 'steps': 3312, 'loss/train': 2.534740686416626} 08/30/2021 13:48:19 - INFO - __main__ - Step 3314: {'lr': 0.0004999029070567229, 'samples': 636288, 'steps': 3313, 'loss/train': 2.4719066619873047} 08/30/2021 13:48:20 - INFO - __main__ - Step 3315: {'lr': 0.0004999027591151847, 'samples': 636480, 'steps': 3314, 'loss/train': 2.980236768722534} 08/30/2021 13:48:20 - INFO - __main__ - Step 3316: {'lr': 0.0004999026110610442, 'samples': 636672, 'steps': 3315, 'loss/train': 3.3525431156158447} 08/30/2021 13:48:20 - INFO - __main__ - Step 3317: {'lr': 0.0004999024628943014, 'samples': 636864, 'steps': 3316, 'loss/train': 3.0579843521118164} 08/30/2021 13:48:22 - INFO - __main__ - Step 3318: {'lr': 0.0004999023146149565, 'samples': 637056, 'steps': 3317, 'loss/train': 3.0031614303588867} 08/30/2021 13:48:22 - INFO - __main__ - Step 3319: {'lr': 0.0004999021662230093, 'samples': 637248, 'steps': 3318, 'loss/train': 3.110140323638916} 08/30/2021 13:48:23 - INFO - __main__ - Step 3320: {'lr': 0.0004999020177184601, 'samples': 637440, 'steps': 3319, 'loss/train': 2.562987804412842} 08/30/2021 13:48:23 - INFO - __main__ - Step 3321: {'lr': 0.000499901869101309, 'samples': 637632, 'steps': 3320, 'loss/train': 2.5110275745391846} 08/30/2021 13:48:23 - INFO - __main__ - Step 3322: {'lr': 0.0004999017203715559, 'samples': 637824, 'steps': 3321, 'loss/train': 3.200589656829834} 08/30/2021 13:48:25 - INFO - __main__ - Step 3323: {'lr': 0.000499901571529201, 'samples': 638016, 'steps': 3322, 'loss/train': 2.8086395263671875} 08/30/2021 13:48:25 - INFO - __main__ - Step 3324: {'lr': 0.0004999014225742442, 'samples': 638208, 'steps': 3323, 'loss/train': 2.0978477001190186} 08/30/2021 13:48:25 - INFO - __main__ - Step 3325: {'lr': 0.0004999012735066858, 'samples': 638400, 'steps': 3324, 'loss/train': 2.442878484725952} 08/30/2021 13:48:26 - INFO - __main__ - Step 3326: {'lr': 0.0004999011243265257, 'samples': 638592, 'steps': 3325, 'loss/train': 3.172194242477417} 08/30/2021 13:48:26 - INFO - __main__ - Step 3327: {'lr': 0.000499900975033764, 'samples': 638784, 'steps': 3326, 'loss/train': 3.3617234230041504} 08/30/2021 13:48:28 - INFO - __main__ - Step 3328: {'lr': 0.0004999008256284008, 'samples': 638976, 'steps': 3327, 'loss/train': 2.6678080558776855} 08/30/2021 13:48:28 - INFO - __main__ - Step 3329: {'lr': 0.0004999006761104361, 'samples': 639168, 'steps': 3328, 'loss/train': 2.5414741039276123} 08/30/2021 13:48:28 - INFO - __main__ - Step 3330: {'lr': 0.0004999005264798701, 'samples': 639360, 'steps': 3329, 'loss/train': 2.473289728164673} 08/30/2021 13:48:29 - INFO - __main__ - Step 3331: {'lr': 0.0004999003767367027, 'samples': 639552, 'steps': 3330, 'loss/train': 2.6687510013580322} 08/30/2021 13:48:29 - INFO - __main__ - Step 3332: {'lr': 0.0004999002268809339, 'samples': 639744, 'steps': 3331, 'loss/train': 1.7362552881240845} 08/30/2021 13:48:31 - INFO - __main__ - Step 3333: {'lr': 0.0004999000769125642, 'samples': 639936, 'steps': 3332, 'loss/train': 2.652609348297119} 08/30/2021 13:48:31 - INFO - __main__ - Step 3334: {'lr': 0.0004998999268315932, 'samples': 640128, 'steps': 3333, 'loss/train': 2.4559290409088135} 08/30/2021 13:48:31 - INFO - __main__ - Step 3335: {'lr': 0.0004998997766380212, 'samples': 640320, 'steps': 3334, 'loss/train': 2.385721445083618} 08/30/2021 13:48:32 - INFO - __main__ - Step 3336: {'lr': 0.0004998996263318482, 'samples': 640512, 'steps': 3335, 'loss/train': 2.356045961380005} 08/30/2021 13:48:32 - INFO - __main__ - Step 3337: {'lr': 0.0004998994759130743, 'samples': 640704, 'steps': 3336, 'loss/train': 2.7879414558410645} 08/30/2021 13:48:34 - INFO - __main__ - Step 3338: {'lr': 0.0004998993253816996, 'samples': 640896, 'steps': 3337, 'loss/train': 2.1548779010772705} 08/30/2021 13:48:34 - INFO - __main__ - Step 3339: {'lr': 0.000499899174737724, 'samples': 641088, 'steps': 3338, 'loss/train': 2.10243821144104} 08/30/2021 13:48:35 - INFO - __main__ - Step 3340: {'lr': 0.0004998990239811477, 'samples': 641280, 'steps': 3339, 'loss/train': 2.5220203399658203} 08/30/2021 13:48:35 - INFO - __main__ - Step 3341: {'lr': 0.0004998988731119709, 'samples': 641472, 'steps': 3340, 'loss/train': 2.620222568511963} 08/30/2021 13:48:36 - INFO - __main__ - Step 3342: {'lr': 0.0004998987221301935, 'samples': 641664, 'steps': 3341, 'loss/train': 2.443495035171509} 08/30/2021 13:48:36 - INFO - __main__ - Step 3343: {'lr': 0.0004998985710358155, 'samples': 641856, 'steps': 3342, 'loss/train': 2.132190465927124} 08/30/2021 13:48:38 - INFO - __main__ - Step 3344: {'lr': 0.0004998984198288371, 'samples': 642048, 'steps': 3343, 'loss/train': 2.160667896270752} 08/30/2021 13:48:38 - INFO - __main__ - Step 3345: {'lr': 0.0004998982685092583, 'samples': 642240, 'steps': 3344, 'loss/train': 2.8251593112945557} 08/30/2021 13:48:38 - INFO - __main__ - Step 3346: {'lr': 0.0004998981170770792, 'samples': 642432, 'steps': 3345, 'loss/train': 2.4152023792266846} 08/30/2021 13:48:39 - INFO - __main__ - Step 3347: {'lr': 0.0004998979655323, 'samples': 642624, 'steps': 3346, 'loss/train': 2.6465532779693604} 08/30/2021 13:48:39 - INFO - __main__ - Step 3348: {'lr': 0.0004998978138749204, 'samples': 642816, 'steps': 3347, 'loss/train': 2.9894039630889893} 08/30/2021 13:48:41 - INFO - __main__ - Step 3349: {'lr': 0.0004998976621049408, 'samples': 643008, 'steps': 3348, 'loss/train': 2.57108998298645} 08/30/2021 13:48:41 - INFO - __main__ - Step 3350: {'lr': 0.0004998975102223612, 'samples': 643200, 'steps': 3349, 'loss/train': 2.692763328552246} 08/30/2021 13:48:41 - INFO - __main__ - Step 3351: {'lr': 0.0004998973582271817, 'samples': 643392, 'steps': 3350, 'loss/train': 1.823738694190979} 08/30/2021 13:48:42 - INFO - __main__ - Step 3352: {'lr': 0.0004998972061194022, 'samples': 643584, 'steps': 3351, 'loss/train': 2.8077547550201416} 08/30/2021 13:48:42 - INFO - __main__ - Step 3353: {'lr': 0.0004998970538990228, 'samples': 643776, 'steps': 3352, 'loss/train': 2.885777473449707} 08/30/2021 13:48:44 - INFO - __main__ - Step 3354: {'lr': 0.0004998969015660438, 'samples': 643968, 'steps': 3353, 'loss/train': 2.5239927768707275} 08/30/2021 13:48:45 - INFO - __main__ - Step 3355: {'lr': 0.0004998967491204651, 'samples': 644160, 'steps': 3354, 'loss/train': 2.5806667804718018} 08/30/2021 13:48:45 - INFO - __main__ - Step 3356: {'lr': 0.0004998965965622867, 'samples': 644352, 'steps': 3355, 'loss/train': 2.547076940536499} 08/30/2021 13:48:45 - INFO - __main__ - Step 3357: {'lr': 0.0004998964438915088, 'samples': 644544, 'steps': 3356, 'loss/train': 2.1983394622802734} 08/30/2021 13:48:46 - INFO - __main__ - Step 3358: {'lr': 0.0004998962911081314, 'samples': 644736, 'steps': 3357, 'loss/train': 1.7727375030517578} 08/30/2021 13:48:46 - INFO - __main__ - Step 3359: {'lr': 0.0004998961382121546, 'samples': 644928, 'steps': 3358, 'loss/train': 2.59871768951416} 08/30/2021 13:48:48 - INFO - __main__ - Step 3360: {'lr': 0.0004998959852035785, 'samples': 645120, 'steps': 3359, 'loss/train': 2.518486976623535} 08/30/2021 13:48:48 - INFO - __main__ - Step 3361: {'lr': 0.0004998958320824031, 'samples': 645312, 'steps': 3360, 'loss/train': 2.533982992172241} 08/30/2021 13:48:49 - INFO - __main__ - Step 3362: {'lr': 0.0004998956788486284, 'samples': 645504, 'steps': 3361, 'loss/train': 2.8132495880126953} 08/30/2021 13:48:49 - INFO - __main__ - Step 3363: {'lr': 0.0004998955255022547, 'samples': 645696, 'steps': 3362, 'loss/train': 1.9254417419433594} 08/30/2021 13:48:49 - INFO - __main__ - Step 3364: {'lr': 0.0004998953720432818, 'samples': 645888, 'steps': 3363, 'loss/train': 2.747995376586914} 08/30/2021 13:48:50 - INFO - __main__ - Step 3365: {'lr': 0.00049989521847171, 'samples': 646080, 'steps': 3364, 'loss/train': 2.550886631011963} 08/30/2021 13:48:51 - INFO - __main__ - Step 3366: {'lr': 0.0004998950647875392, 'samples': 646272, 'steps': 3365, 'loss/train': 3.939955472946167} 08/30/2021 13:48:52 - INFO - __main__ - Step 3367: {'lr': 0.0004998949109907697, 'samples': 646464, 'steps': 3366, 'loss/train': 2.9285311698913574} 08/30/2021 13:48:52 - INFO - __main__ - Step 3368: {'lr': 0.0004998947570814012, 'samples': 646656, 'steps': 3367, 'loss/train': 2.6467556953430176} 08/30/2021 13:48:52 - INFO - __main__ - Step 3369: {'lr': 0.0004998946030594341, 'samples': 646848, 'steps': 3368, 'loss/train': 2.517835855484009} 08/30/2021 13:48:53 - INFO - __main__ - Step 3370: {'lr': 0.0004998944489248683, 'samples': 647040, 'steps': 3369, 'loss/train': 2.932713270187378} 08/30/2021 13:48:54 - INFO - __main__ - Step 3371: {'lr': 0.000499894294677704, 'samples': 647232, 'steps': 3370, 'loss/train': 2.707963228225708} 08/30/2021 13:48:55 - INFO - __main__ - Step 3372: {'lr': 0.000499894140317941, 'samples': 647424, 'steps': 3371, 'loss/train': 2.471409320831299} 08/30/2021 13:48:55 - INFO - __main__ - Step 3373: {'lr': 0.0004998939858455798, 'samples': 647616, 'steps': 3372, 'loss/train': 2.475250482559204} 08/30/2021 13:48:55 - INFO - __main__ - Step 3374: {'lr': 0.0004998938312606201, 'samples': 647808, 'steps': 3373, 'loss/train': 1.9769246578216553} 08/30/2021 13:48:56 - INFO - __main__ - Step 3375: {'lr': 0.000499893676563062, 'samples': 648000, 'steps': 3374, 'loss/train': 3.2632381916046143} 08/30/2021 13:48:57 - INFO - __main__ - Step 3376: {'lr': 0.0004998935217529058, 'samples': 648192, 'steps': 3375, 'loss/train': 2.835620880126953} 08/30/2021 13:48:58 - INFO - __main__ - Step 3377: {'lr': 0.0004998933668301514, 'samples': 648384, 'steps': 3376, 'loss/train': 3.0379831790924072} 08/30/2021 13:48:58 - INFO - __main__ - Step 3378: {'lr': 0.0004998932117947989, 'samples': 648576, 'steps': 3377, 'loss/train': 2.353278875350952} 08/30/2021 13:48:58 - INFO - __main__ - Step 3379: {'lr': 0.0004998930566468484, 'samples': 648768, 'steps': 3378, 'loss/train': 2.9702203273773193} 08/30/2021 13:48:59 - INFO - __main__ - Step 3380: {'lr': 0.0004998929013863, 'samples': 648960, 'steps': 3379, 'loss/train': 2.017845630645752} 08/30/2021 13:49:00 - INFO - __main__ - Step 3381: {'lr': 0.0004998927460131535, 'samples': 649152, 'steps': 3380, 'loss/train': 2.112061023712158} 08/30/2021 13:49:01 - INFO - __main__ - Step 3382: {'lr': 0.0004998925905274094, 'samples': 649344, 'steps': 3381, 'loss/train': 1.5845096111297607} 08/30/2021 13:49:01 - INFO - __main__ - Step 3383: {'lr': 0.0004998924349290674, 'samples': 649536, 'steps': 3382, 'loss/train': 2.748828411102295} 08/30/2021 13:49:01 - INFO - __main__ - Step 3384: {'lr': 0.0004998922792181278, 'samples': 649728, 'steps': 3383, 'loss/train': 2.293346643447876} 08/30/2021 13:49:02 - INFO - __main__ - Step 3385: {'lr': 0.0004998921233945907, 'samples': 649920, 'steps': 3384, 'loss/train': 1.8696900606155396} 08/30/2021 13:49:02 - INFO - __main__ - Step 3386: {'lr': 0.0004998919674584559, 'samples': 650112, 'steps': 3385, 'loss/train': 2.5926995277404785} 08/30/2021 13:49:04 - INFO - __main__ - Step 3387: {'lr': 0.0004998918114097237, 'samples': 650304, 'steps': 3386, 'loss/train': 2.7840747833251953} 08/30/2021 13:49:05 - INFO - __main__ - Step 3388: {'lr': 0.0004998916552483941, 'samples': 650496, 'steps': 3387, 'loss/train': 2.191200017929077} 08/30/2021 13:49:05 - INFO - __main__ - Step 3389: {'lr': 0.0004998914989744671, 'samples': 650688, 'steps': 3388, 'loss/train': 2.1903586387634277} 08/30/2021 13:49:05 - INFO - __main__ - Step 3390: {'lr': 0.000499891342587943, 'samples': 650880, 'steps': 3389, 'loss/train': 2.354968309402466} 08/30/2021 13:49:06 - INFO - __main__ - Step 3391: {'lr': 0.0004998911860888217, 'samples': 651072, 'steps': 3390, 'loss/train': 1.799631118774414} 08/30/2021 13:49:06 - INFO - __main__ - Step 3392: {'lr': 0.0004998910294771032, 'samples': 651264, 'steps': 3391, 'loss/train': 1.7778704166412354} 08/30/2021 13:49:07 - INFO - __main__ - Step 3393: {'lr': 0.0004998908727527877, 'samples': 651456, 'steps': 3392, 'loss/train': 4.1373090744018555} 08/30/2021 13:49:09 - INFO - __main__ - Step 3394: {'lr': 0.0004998907159158752, 'samples': 651648, 'steps': 3393, 'loss/train': 2.655801296234131} 08/30/2021 13:49:10 - INFO - __main__ - Step 3395: {'lr': 0.0004998905589663658, 'samples': 651840, 'steps': 3394, 'loss/train': 2.715543270111084} 08/30/2021 13:49:10 - INFO - __main__ - Step 3396: {'lr': 0.0004998904019042596, 'samples': 652032, 'steps': 3395, 'loss/train': 3.3126304149627686} 08/30/2021 13:49:11 - INFO - __main__ - Step 3397: {'lr': 0.0004998902447295567, 'samples': 652224, 'steps': 3396, 'loss/train': 3.198720693588257} 08/30/2021 13:49:11 - INFO - __main__ - Step 3398: {'lr': 0.000499890087442257, 'samples': 652416, 'steps': 3397, 'loss/train': 2.64034104347229} 08/30/2021 13:49:13 - INFO - __main__ - Step 3399: {'lr': 0.0004998899300423607, 'samples': 652608, 'steps': 3398, 'loss/train': 0.8199313879013062} 08/30/2021 13:49:13 - INFO - __main__ - Step 3400: {'lr': 0.0004998897725298679, 'samples': 652800, 'steps': 3399, 'loss/train': 2.494413375854492} 08/30/2021 13:49:13 - INFO - __main__ - Step 3401: {'lr': 0.0004998896149047786, 'samples': 652992, 'steps': 3400, 'loss/train': 2.441323757171631} 08/30/2021 13:49:14 - INFO - __main__ - Step 3402: {'lr': 0.0004998894571670929, 'samples': 653184, 'steps': 3401, 'loss/train': 3.2445061206817627} 08/30/2021 13:49:14 - INFO - __main__ - Step 3403: {'lr': 0.0004998892993168109, 'samples': 653376, 'steps': 3402, 'loss/train': 2.917768955230713} 08/30/2021 13:49:16 - INFO - __main__ - Step 3404: {'lr': 0.0004998891413539326, 'samples': 653568, 'steps': 3403, 'loss/train': 3.06826114654541} 08/30/2021 13:49:16 - INFO - __main__ - Step 3405: {'lr': 0.0004998889832784581, 'samples': 653760, 'steps': 3404, 'loss/train': 3.037091016769409} 08/30/2021 13:49:17 - INFO - __main__ - Step 3406: {'lr': 0.0004998888250903875, 'samples': 653952, 'steps': 3405, 'loss/train': 2.4964957237243652} 08/30/2021 13:49:17 - INFO - __main__ - Step 3407: {'lr': 0.0004998886667897209, 'samples': 654144, 'steps': 3406, 'loss/train': 1.899567723274231} 08/30/2021 13:49:17 - INFO - __main__ - Step 3408: {'lr': 0.0004998885083764582, 'samples': 654336, 'steps': 3407, 'loss/train': 2.579331874847412} 08/30/2021 13:49:18 - INFO - __main__ - Step 3409: {'lr': 0.0004998883498505996, 'samples': 654528, 'steps': 3408, 'loss/train': 2.5077710151672363} 08/30/2021 13:49:19 - INFO - __main__ - Step 3410: {'lr': 0.0004998881912121453, 'samples': 654720, 'steps': 3409, 'loss/train': 2.3359644412994385} 08/30/2021 13:49:20 - INFO - __main__ - Step 3411: {'lr': 0.0004998880324610952, 'samples': 654912, 'steps': 3410, 'loss/train': 2.951115608215332} 08/30/2021 13:49:20 - INFO - __main__ - Step 3412: {'lr': 0.0004998878735974493, 'samples': 655104, 'steps': 3411, 'loss/train': 2.7862660884857178} 08/30/2021 13:49:20 - INFO - __main__ - Step 3413: {'lr': 0.0004998877146212079, 'samples': 655296, 'steps': 3412, 'loss/train': 2.9797847270965576} 08/30/2021 13:49:21 - INFO - __main__ - Step 3414: {'lr': 0.0004998875555323708, 'samples': 655488, 'steps': 3413, 'loss/train': 2.2499947547912598} 08/30/2021 13:49:22 - INFO - __main__ - Step 3415: {'lr': 0.0004998873963309384, 'samples': 655680, 'steps': 3414, 'loss/train': 2.724332332611084} 08/30/2021 13:49:23 - INFO - __main__ - Step 3416: {'lr': 0.0004998872370169105, 'samples': 655872, 'steps': 3415, 'loss/train': 2.579256772994995} 08/30/2021 13:49:23 - INFO - __main__ - Step 3417: {'lr': 0.0004998870775902872, 'samples': 656064, 'steps': 3416, 'loss/train': 2.531017303466797} 08/30/2021 13:49:23 - INFO - __main__ - Step 3418: {'lr': 0.0004998869180510688, 'samples': 656256, 'steps': 3417, 'loss/train': 2.8577194213867188} 08/30/2021 13:49:24 - INFO - __main__ - Step 3419: {'lr': 0.0004998867583992551, 'samples': 656448, 'steps': 3418, 'loss/train': 3.2128517627716064} 08/30/2021 13:49:25 - INFO - __main__ - Step 3420: {'lr': 0.0004998865986348464, 'samples': 656640, 'steps': 3419, 'loss/train': 4.497913360595703} 08/30/2021 13:49:26 - INFO - __main__ - Step 3421: {'lr': 0.0004998864387578426, 'samples': 656832, 'steps': 3420, 'loss/train': 2.314352512359619} 08/30/2021 13:49:26 - INFO - __main__ - Step 3422: {'lr': 0.0004998862787682438, 'samples': 657024, 'steps': 3421, 'loss/train': 3.1587514877319336} 08/30/2021 13:49:27 - INFO - __main__ - Step 3423: {'lr': 0.00049988611866605, 'samples': 657216, 'steps': 3422, 'loss/train': 2.787001609802246} 08/30/2021 13:49:27 - INFO - __main__ - Step 3424: {'lr': 0.0004998859584512615, 'samples': 657408, 'steps': 3423, 'loss/train': 3.9919040203094482} 08/30/2021 13:49:28 - INFO - __main__ - Step 3425: {'lr': 0.0004998857981238782, 'samples': 657600, 'steps': 3424, 'loss/train': 2.7004263401031494} 08/30/2021 13:49:29 - INFO - __main__ - Step 3426: {'lr': 0.0004998856376839003, 'samples': 657792, 'steps': 3425, 'loss/train': 3.263404369354248} 08/30/2021 13:49:29 - INFO - __main__ - Step 3427: {'lr': 0.0004998854771313277, 'samples': 657984, 'steps': 3426, 'loss/train': 2.738943338394165} 08/30/2021 13:49:30 - INFO - __main__ - Step 3428: {'lr': 0.0004998853164661606, 'samples': 658176, 'steps': 3427, 'loss/train': 2.4689908027648926} 08/30/2021 13:49:30 - INFO - __main__ - Step 3429: {'lr': 0.000499885155688399, 'samples': 658368, 'steps': 3428, 'loss/train': 2.7306323051452637} 08/30/2021 13:49:32 - INFO - __main__ - Step 3430: {'lr': 0.000499884994798043, 'samples': 658560, 'steps': 3429, 'loss/train': 2.639641523361206} 08/30/2021 13:49:32 - INFO - __main__ - Step 3431: {'lr': 0.0004998848337950927, 'samples': 658752, 'steps': 3430, 'loss/train': 2.4209651947021484} 08/30/2021 13:49:33 - INFO - __main__ - Step 3432: {'lr': 0.0004998846726795482, 'samples': 658944, 'steps': 3431, 'loss/train': 3.1134023666381836} 08/30/2021 13:49:33 - INFO - __main__ - Step 3433: {'lr': 0.0004998845114514095, 'samples': 659136, 'steps': 3432, 'loss/train': 2.6262388229370117} 08/30/2021 13:49:33 - INFO - __main__ - Step 3434: {'lr': 0.0004998843501106766, 'samples': 659328, 'steps': 3433, 'loss/train': 2.3508970737457275} 08/30/2021 13:49:34 - INFO - __main__ - Step 3435: {'lr': 0.0004998841886573496, 'samples': 659520, 'steps': 3434, 'loss/train': 2.84313702583313} 08/30/2021 13:49:35 - INFO - __main__ - Step 3436: {'lr': 0.0004998840270914288, 'samples': 659712, 'steps': 3435, 'loss/train': 2.950655460357666} 08/30/2021 13:49:36 - INFO - __main__ - Step 3437: {'lr': 0.0004998838654129142, 'samples': 659904, 'steps': 3436, 'loss/train': 3.063199043273926} 08/30/2021 13:49:36 - INFO - __main__ - Step 3438: {'lr': 0.0004998837036218056, 'samples': 660096, 'steps': 3437, 'loss/train': 0.5293973684310913} 08/30/2021 13:49:36 - INFO - __main__ - Step 3439: {'lr': 0.0004998835417181033, 'samples': 660288, 'steps': 3438, 'loss/train': 2.5547447204589844} 08/30/2021 13:49:37 - INFO - __main__ - Step 3440: {'lr': 0.0004998833797018074, 'samples': 660480, 'steps': 3439, 'loss/train': 2.619832992553711} 08/30/2021 13:49:37 - INFO - __main__ - Step 3441: {'lr': 0.0004998832175729179, 'samples': 660672, 'steps': 3440, 'loss/train': 2.998067855834961} 08/30/2021 13:49:39 - INFO - __main__ - Step 3442: {'lr': 0.0004998830553314349, 'samples': 660864, 'steps': 3441, 'loss/train': 2.967714786529541} 08/30/2021 13:49:39 - INFO - __main__ - Step 3443: {'lr': 0.0004998828929773583, 'samples': 661056, 'steps': 3442, 'loss/train': 2.2500030994415283} 08/30/2021 13:49:39 - INFO - __main__ - Step 3444: {'lr': 0.0004998827305106884, 'samples': 661248, 'steps': 3443, 'loss/train': 2.594834327697754} 08/30/2021 13:49:40 - INFO - __main__ - Step 3445: {'lr': 0.0004998825679314253, 'samples': 661440, 'steps': 3444, 'loss/train': 2.74992036819458} 08/30/2021 13:49:40 - INFO - __main__ - Step 3446: {'lr': 0.0004998824052395689, 'samples': 661632, 'steps': 3445, 'loss/train': 2.596956491470337} 08/30/2021 13:49:42 - INFO - __main__ - Step 3447: {'lr': 0.0004998822424351193, 'samples': 661824, 'steps': 3446, 'loss/train': 2.3737950325012207} 08/30/2021 13:49:42 - INFO - __main__ - Step 3448: {'lr': 0.0004998820795180766, 'samples': 662016, 'steps': 3447, 'loss/train': 2.3730239868164062} 08/30/2021 13:49:42 - INFO - __main__ - Step 3449: {'lr': 0.000499881916488441, 'samples': 662208, 'steps': 3448, 'loss/train': 3.0651445388793945} 08/30/2021 13:49:43 - INFO - __main__ - Step 3450: {'lr': 0.0004998817533462123, 'samples': 662400, 'steps': 3449, 'loss/train': 1.9123895168304443} 08/30/2021 13:49:43 - INFO - __main__ - Step 3451: {'lr': 0.0004998815900913909, 'samples': 662592, 'steps': 3450, 'loss/train': 2.172102212905884} 08/30/2021 13:49:45 - INFO - __main__ - Step 3452: {'lr': 0.0004998814267239767, 'samples': 662784, 'steps': 3451, 'loss/train': 2.280928134918213} 08/30/2021 13:49:46 - INFO - __main__ - Step 3453: {'lr': 0.0004998812632439697, 'samples': 662976, 'steps': 3452, 'loss/train': 1.0883467197418213} 08/30/2021 13:49:46 - INFO - __main__ - Step 3454: {'lr': 0.00049988109965137, 'samples': 663168, 'steps': 3453, 'loss/train': 2.310020685195923} 08/30/2021 13:49:46 - INFO - __main__ - Step 3455: {'lr': 0.000499880935946178, 'samples': 663360, 'steps': 3454, 'loss/train': 2.583714485168457} 08/30/2021 13:49:47 - INFO - __main__ - Step 3456: {'lr': 0.0004998807721283932, 'samples': 663552, 'steps': 3455, 'loss/train': 2.3489978313446045} 08/30/2021 13:49:48 - INFO - __main__ - Step 3457: {'lr': 0.0004998806081980162, 'samples': 663744, 'steps': 3456, 'loss/train': 2.2940306663513184} 08/30/2021 13:49:49 - INFO - __main__ - Step 3458: {'lr': 0.0004998804441550467, 'samples': 663936, 'steps': 3457, 'loss/train': 2.3305861949920654} 08/30/2021 13:49:49 - INFO - __main__ - Step 3459: {'lr': 0.000499880279999485, 'samples': 664128, 'steps': 3458, 'loss/train': 2.65053391456604} 08/30/2021 13:49:49 - INFO - __main__ - Step 3460: {'lr': 0.0004998801157313311, 'samples': 664320, 'steps': 3459, 'loss/train': 2.539475440979004} 08/30/2021 13:49:50 - INFO - __main__ - Step 3461: {'lr': 0.0004998799513505851, 'samples': 664512, 'steps': 3460, 'loss/train': 2.5797791481018066} 08/30/2021 13:49:51 - INFO - __main__ - Step 3462: {'lr': 0.000499879786857247, 'samples': 664704, 'steps': 3461, 'loss/train': 2.5145087242126465} 08/30/2021 13:49:52 - INFO - __main__ - Step 3463: {'lr': 0.0004998796222513169, 'samples': 664896, 'steps': 3462, 'loss/train': 2.658740282058716} 08/30/2021 13:49:52 - INFO - __main__ - Step 3464: {'lr': 0.000499879457532795, 'samples': 665088, 'steps': 3463, 'loss/train': 2.358705759048462} 08/30/2021 13:49:52 - INFO - __main__ - Step 3465: {'lr': 0.0004998792927016812, 'samples': 665280, 'steps': 3464, 'loss/train': 2.325634717941284} 08/30/2021 13:49:53 - INFO - __main__ - Step 3466: {'lr': 0.0004998791277579757, 'samples': 665472, 'steps': 3465, 'loss/train': 4.067972660064697} 08/30/2021 13:49:54 - INFO - __main__ - Step 3467: {'lr': 0.0004998789627016784, 'samples': 665664, 'steps': 3466, 'loss/train': 2.500408887863159} 08/30/2021 13:49:55 - INFO - __main__ - Step 3468: {'lr': 0.0004998787975327896, 'samples': 665856, 'steps': 3467, 'loss/train': 2.69610333442688} 08/30/2021 13:49:55 - INFO - __main__ - Step 3469: {'lr': 0.0004998786322513093, 'samples': 666048, 'steps': 3468, 'loss/train': 2.477757215499878} 08/30/2021 13:49:55 - INFO - __main__ - Step 3470: {'lr': 0.0004998784668572375, 'samples': 666240, 'steps': 3469, 'loss/train': 2.623246431350708} 08/30/2021 13:49:56 - INFO - __main__ - Step 3471: {'lr': 0.0004998783013505743, 'samples': 666432, 'steps': 3470, 'loss/train': 2.584547758102417} 08/30/2021 13:49:57 - INFO - __main__ - Step 3472: {'lr': 0.0004998781357313198, 'samples': 666624, 'steps': 3471, 'loss/train': 2.7669098377227783} 08/30/2021 13:49:58 - INFO - __main__ - Step 3473: {'lr': 0.0004998779699994741, 'samples': 666816, 'steps': 3472, 'loss/train': 2.470353364944458} 08/30/2021 13:49:58 - INFO - __main__ - Step 3474: {'lr': 0.0004998778041550372, 'samples': 667008, 'steps': 3473, 'loss/train': 2.6031546592712402} 08/30/2021 13:49:58 - INFO - __main__ - Step 3475: {'lr': 0.0004998776381980092, 'samples': 667200, 'steps': 3474, 'loss/train': 2.885899305343628} 08/30/2021 13:49:59 - INFO - __main__ - Step 3476: {'lr': 0.0004998774721283903, 'samples': 667392, 'steps': 3475, 'loss/train': 2.8214433193206787} 08/30/2021 13:49:59 - INFO - __main__ - Step 3477: {'lr': 0.0004998773059461803, 'samples': 667584, 'steps': 3476, 'loss/train': 2.6902358531951904} 08/30/2021 13:50:01 - INFO - __main__ - Step 3478: {'lr': 0.0004998771396513796, 'samples': 667776, 'steps': 3477, 'loss/train': 2.731186866760254} 08/30/2021 13:50:01 - INFO - __main__ - Step 3479: {'lr': 0.000499876973243988, 'samples': 667968, 'steps': 3478, 'loss/train': 1.5921486616134644} 08/30/2021 13:50:01 - INFO - __main__ - Step 3480: {'lr': 0.0004998768067240059, 'samples': 668160, 'steps': 3479, 'loss/train': 2.509577512741089} 08/30/2021 13:50:02 - INFO - __main__ - Step 3481: {'lr': 0.0004998766400914329, 'samples': 668352, 'steps': 3480, 'loss/train': 1.6335997581481934} 08/30/2021 13:50:02 - INFO - __main__ - Step 3482: {'lr': 0.0004998764733462694, 'samples': 668544, 'steps': 3481, 'loss/train': 2.6024105548858643} 08/30/2021 13:50:04 - INFO - __main__ - Step 3483: {'lr': 0.0004998763064885155, 'samples': 668736, 'steps': 3482, 'loss/train': 1.5272482633590698} 08/30/2021 13:50:04 - INFO - __main__ - Step 3484: {'lr': 0.0004998761395181712, 'samples': 668928, 'steps': 3483, 'loss/train': 2.190028667449951} 08/30/2021 13:50:05 - INFO - __main__ - Step 3485: {'lr': 0.0004998759724352365, 'samples': 669120, 'steps': 3484, 'loss/train': 2.1334502696990967} 08/30/2021 13:50:05 - INFO - __main__ - Step 3486: {'lr': 0.0004998758052397115, 'samples': 669312, 'steps': 3485, 'loss/train': 2.725038528442383} 08/30/2021 13:50:05 - INFO - __main__ - Step 3487: {'lr': 0.0004998756379315964, 'samples': 669504, 'steps': 3486, 'loss/train': 1.879176139831543} 08/30/2021 13:50:07 - INFO - __main__ - Step 3488: {'lr': 0.0004998754705108912, 'samples': 669696, 'steps': 3487, 'loss/train': 2.227513313293457} 08/30/2021 13:50:07 - INFO - __main__ - Step 3489: {'lr': 0.000499875302977596, 'samples': 669888, 'steps': 3488, 'loss/train': 2.055891513824463} 08/30/2021 13:50:07 - INFO - __main__ - Step 3490: {'lr': 0.0004998751353317108, 'samples': 670080, 'steps': 3489, 'loss/train': 2.2259504795074463} 08/30/2021 13:50:08 - INFO - __main__ - Step 3491: {'lr': 0.0004998749675732357, 'samples': 670272, 'steps': 3490, 'loss/train': 2.086120367050171} 08/30/2021 13:50:08 - INFO - __main__ - Step 3492: {'lr': 0.0004998747997021708, 'samples': 670464, 'steps': 3491, 'loss/train': 2.984645366668701} 08/30/2021 13:50:10 - INFO - __main__ - Step 3493: {'lr': 0.0004998746317185162, 'samples': 670656, 'steps': 3492, 'loss/train': 2.691204309463501} 08/30/2021 13:50:10 - INFO - __main__ - Step 3494: {'lr': 0.000499874463622272, 'samples': 670848, 'steps': 3493, 'loss/train': 3.7327635288238525} 08/30/2021 13:50:10 - INFO - __main__ - Step 3495: {'lr': 0.000499874295413438, 'samples': 671040, 'steps': 3494, 'loss/train': 1.8792227506637573} 08/30/2021 13:50:11 - INFO - __main__ - Step 3496: {'lr': 0.0004998741270920147, 'samples': 671232, 'steps': 3495, 'loss/train': 2.2878055572509766} 08/30/2021 13:50:11 - INFO - __main__ - Step 3497: {'lr': 0.0004998739586580019, 'samples': 671424, 'steps': 3496, 'loss/train': 2.5358221530914307} 08/30/2021 13:50:13 - INFO - __main__ - Step 3498: {'lr': 0.0004998737901113999, 'samples': 671616, 'steps': 3497, 'loss/train': 2.7810819149017334} 08/30/2021 13:50:13 - INFO - __main__ - Step 3499: {'lr': 0.0004998736214522084, 'samples': 671808, 'steps': 3498, 'loss/train': 2.445444107055664} 08/30/2021 13:50:13 - INFO - __main__ - Step 3500: {'lr': 0.0004998734526804278, 'samples': 672000, 'steps': 3499, 'loss/train': 2.588060140609741} 08/30/2021 13:50:14 - INFO - __main__ - Step 3501: {'lr': 0.0004998732837960581, 'samples': 672192, 'steps': 3500, 'loss/train': 2.519333600997925} 08/30/2021 13:50:14 - INFO - __main__ - Step 3502: {'lr': 0.0004998731147990993, 'samples': 672384, 'steps': 3501, 'loss/train': 2.5726373195648193} 08/30/2021 13:50:16 - INFO - __main__ - Step 3503: {'lr': 0.0004998729456895516, 'samples': 672576, 'steps': 3502, 'loss/train': 3.3219263553619385} 08/30/2021 13:50:17 - INFO - __main__ - Step 3504: {'lr': 0.0004998727764674149, 'samples': 672768, 'steps': 3503, 'loss/train': 2.2654037475585938} 08/30/2021 13:50:17 - INFO - __main__ - Step 3505: {'lr': 0.0004998726071326896, 'samples': 672960, 'steps': 3504, 'loss/train': 2.958322763442993} 08/30/2021 13:50:17 - INFO - __main__ - Step 3506: {'lr': 0.0004998724376853754, 'samples': 673152, 'steps': 3505, 'loss/train': 1.9985573291778564} 08/30/2021 13:50:18 - INFO - __main__ - Step 3507: {'lr': 0.0004998722681254725, 'samples': 673344, 'steps': 3506, 'loss/train': 2.4221041202545166} 08/30/2021 13:50:18 - INFO - __main__ - Step 3508: {'lr': 0.0004998720984529811, 'samples': 673536, 'steps': 3507, 'loss/train': 2.9456748962402344} 08/30/2021 13:50:20 - INFO - __main__ - Step 3509: {'lr': 0.0004998719286679011, 'samples': 673728, 'steps': 3508, 'loss/train': 2.9266512393951416} 08/30/2021 13:50:20 - INFO - __main__ - Step 3510: {'lr': 0.0004998717587702328, 'samples': 673920, 'steps': 3509, 'loss/train': 2.8354921340942383} 08/30/2021 13:50:20 - INFO - __main__ - Step 3511: {'lr': 0.0004998715887599759, 'samples': 674112, 'steps': 3510, 'loss/train': 2.195363998413086} 08/30/2021 13:50:21 - INFO - __main__ - Step 3512: {'lr': 0.000499871418637131, 'samples': 674304, 'steps': 3511, 'loss/train': 2.662369966506958} 08/30/2021 13:50:21 - INFO - __main__ - Step 3513: {'lr': 0.0004998712484016977, 'samples': 674496, 'steps': 3512, 'loss/train': 2.7905404567718506} 08/30/2021 13:50:23 - INFO - __main__ - Step 3514: {'lr': 0.0004998710780536763, 'samples': 674688, 'steps': 3513, 'loss/train': 2.845914363861084} 08/30/2021 13:50:23 - INFO - __main__ - Step 3515: {'lr': 0.0004998709075930669, 'samples': 674880, 'steps': 3514, 'loss/train': 2.370758056640625} 08/30/2021 13:50:23 - INFO - __main__ - Step 3516: {'lr': 0.0004998707370198695, 'samples': 675072, 'steps': 3515, 'loss/train': 2.654289484024048} 08/30/2021 13:50:24 - INFO - __main__ - Step 3517: {'lr': 0.0004998705663340843, 'samples': 675264, 'steps': 3516, 'loss/train': 0.9861878752708435} 08/30/2021 13:50:24 - INFO - __main__ - Step 3518: {'lr': 0.0004998703955357111, 'samples': 675456, 'steps': 3517, 'loss/train': 2.767317771911621} 08/30/2021 13:50:26 - INFO - __main__ - Step 3519: {'lr': 0.0004998702246247502, 'samples': 675648, 'steps': 3518, 'loss/train': 2.1342272758483887} 08/30/2021 13:50:26 - INFO - __main__ - Step 3520: {'lr': 0.0004998700536012017, 'samples': 675840, 'steps': 3519, 'loss/train': 2.54465651512146} 08/30/2021 13:50:26 - INFO - __main__ - Step 3521: {'lr': 0.0004998698824650655, 'samples': 676032, 'steps': 3520, 'loss/train': 2.619464635848999} 08/30/2021 13:50:27 - INFO - __main__ - Step 3522: {'lr': 0.000499869711216342, 'samples': 676224, 'steps': 3521, 'loss/train': 2.869643449783325} 08/30/2021 13:50:27 - INFO - __main__ - Step 3523: {'lr': 0.0004998695398550309, 'samples': 676416, 'steps': 3522, 'loss/train': 2.5181527137756348} 08/30/2021 13:50:29 - INFO - __main__ - Step 3524: {'lr': 0.0004998693683811325, 'samples': 676608, 'steps': 3523, 'loss/train': 1.9194591045379639} 08/30/2021 13:50:29 - INFO - __main__ - Step 3525: {'lr': 0.0004998691967946468, 'samples': 676800, 'steps': 3524, 'loss/train': 0.4229249954223633} 08/30/2021 13:50:30 - INFO - __main__ - Step 3526: {'lr': 0.000499869025095574, 'samples': 676992, 'steps': 3525, 'loss/train': 2.827298879623413} 08/30/2021 13:50:30 - INFO - __main__ - Step 3527: {'lr': 0.0004998688532839139, 'samples': 677184, 'steps': 3526, 'loss/train': 2.630917549133301} 08/30/2021 13:50:30 - INFO - __main__ - Step 3528: {'lr': 0.0004998686813596668, 'samples': 677376, 'steps': 3527, 'loss/train': 2.33671498298645} 08/30/2021 13:50:31 - INFO - __main__ - Step 3529: {'lr': 0.0004998685093228327, 'samples': 677568, 'steps': 3528, 'loss/train': 3.2041265964508057} 08/30/2021 13:50:32 - INFO - __main__ - Step 3530: {'lr': 0.0004998683371734118, 'samples': 677760, 'steps': 3529, 'loss/train': 3.201237440109253} 08/30/2021 13:50:33 - INFO - __main__ - Step 3531: {'lr': 0.000499868164911404, 'samples': 677952, 'steps': 3530, 'loss/train': 2.359074354171753} 08/30/2021 13:50:33 - INFO - __main__ - Step 3532: {'lr': 0.0004998679925368094, 'samples': 678144, 'steps': 3531, 'loss/train': 2.1300902366638184} 08/30/2021 13:50:33 - INFO - __main__ - Step 3533: {'lr': 0.0004998678200496283, 'samples': 678336, 'steps': 3532, 'loss/train': 3.163862705230713} 08/30/2021 13:50:34 - INFO - __main__ - Step 3534: {'lr': 0.0004998676474498606, 'samples': 678528, 'steps': 3533, 'loss/train': 2.352466583251953} 08/30/2021 13:50:35 - INFO - __main__ - Step 3535: {'lr': 0.0004998674747375063, 'samples': 678720, 'steps': 3534, 'loss/train': 2.574796199798584} 08/30/2021 13:50:36 - INFO - __main__ - Step 3536: {'lr': 0.0004998673019125657, 'samples': 678912, 'steps': 3535, 'loss/train': 2.926755666732788} 08/30/2021 13:50:36 - INFO - __main__ - Step 3537: {'lr': 0.0004998671289750386, 'samples': 679104, 'steps': 3536, 'loss/train': 2.254777669906616} 08/30/2021 13:50:36 - INFO - __main__ - Step 3538: {'lr': 0.0004998669559249252, 'samples': 679296, 'steps': 3537, 'loss/train': 2.3179006576538086} 08/30/2021 13:50:37 - INFO - __main__ - Step 3539: {'lr': 0.0004998667827622258, 'samples': 679488, 'steps': 3538, 'loss/train': 3.5752573013305664} 08/30/2021 13:50:38 - INFO - __main__ - Step 3540: {'lr': 0.0004998666094869402, 'samples': 679680, 'steps': 3539, 'loss/train': 2.8265016078948975} 08/30/2021 13:50:39 - INFO - __main__ - Step 3541: {'lr': 0.0004998664360990685, 'samples': 679872, 'steps': 3540, 'loss/train': 2.433196783065796} 08/30/2021 13:50:39 - INFO - __main__ - Step 3542: {'lr': 0.0004998662625986109, 'samples': 680064, 'steps': 3541, 'loss/train': 2.2378532886505127} 08/30/2021 13:50:39 - INFO - __main__ - Step 3543: {'lr': 0.0004998660889855674, 'samples': 680256, 'steps': 3542, 'loss/train': 2.2512288093566895} 08/30/2021 13:50:40 - INFO - __main__ - Step 3544: {'lr': 0.0004998659152599381, 'samples': 680448, 'steps': 3543, 'loss/train': 1.9482016563415527} 08/30/2021 13:50:41 - INFO - __main__ - Step 3545: {'lr': 0.000499865741421723, 'samples': 680640, 'steps': 3544, 'loss/train': 2.8362069129943848} 08/30/2021 13:50:42 - INFO - __main__ - Step 3546: {'lr': 0.0004998655674709224, 'samples': 680832, 'steps': 3545, 'loss/train': 2.060626983642578} 08/30/2021 13:50:42 - INFO - __main__ - Step 3547: {'lr': 0.0004998653934075361, 'samples': 681024, 'steps': 3546, 'loss/train': 2.338832378387451} 08/30/2021 13:50:42 - INFO - __main__ - Step 3548: {'lr': 0.0004998652192315644, 'samples': 681216, 'steps': 3547, 'loss/train': 2.950679063796997} 08/30/2021 13:50:43 - INFO - __main__ - Step 3549: {'lr': 0.0004998650449430073, 'samples': 681408, 'steps': 3548, 'loss/train': 2.219944715499878} 08/30/2021 13:50:44 - INFO - __main__ - Step 3550: {'lr': 0.0004998648705418648, 'samples': 681600, 'steps': 3549, 'loss/train': 3.002030372619629} 08/30/2021 13:50:45 - INFO - __main__ - Step 3551: {'lr': 0.000499864696028137, 'samples': 681792, 'steps': 3550, 'loss/train': 4.705066680908203} 08/30/2021 13:50:45 - INFO - __main__ - Step 3552: {'lr': 0.000499864521401824, 'samples': 681984, 'steps': 3551, 'loss/train': 2.4122514724731445} 08/30/2021 13:50:45 - INFO - __main__ - Step 3553: {'lr': 0.000499864346662926, 'samples': 682176, 'steps': 3552, 'loss/train': 2.5135066509246826} 08/30/2021 13:50:46 - INFO - __main__ - Step 3554: {'lr': 0.000499864171811443, 'samples': 682368, 'steps': 3553, 'loss/train': 2.106393337249756} 08/30/2021 13:50:46 - INFO - __main__ - Step 3555: {'lr': 0.0004998639968473751, 'samples': 682560, 'steps': 3554, 'loss/train': 2.6872506141662598} 08/30/2021 13:50:48 - INFO - __main__ - Step 3556: {'lr': 0.0004998638217707222, 'samples': 682752, 'steps': 3555, 'loss/train': 3.0624098777770996} 08/30/2021 13:50:49 - INFO - __main__ - Step 3557: {'lr': 0.0004998636465814846, 'samples': 682944, 'steps': 3556, 'loss/train': 2.931065320968628} 08/30/2021 13:50:49 - INFO - __main__ - Step 3558: {'lr': 0.0004998634712796622, 'samples': 683136, 'steps': 3557, 'loss/train': 1.2333321571350098} 08/30/2021 13:50:50 - INFO - __main__ - Step 3559: {'lr': 0.0004998632958652554, 'samples': 683328, 'steps': 3558, 'loss/train': 2.1315107345581055} 08/30/2021 13:50:50 - INFO - __main__ - Step 3560: {'lr': 0.0004998631203382639, 'samples': 683520, 'steps': 3559, 'loss/train': 2.8830904960632324} 08/30/2021 13:50:50 - INFO - __main__ - Step 3561: {'lr': 0.0004998629446986879, 'samples': 683712, 'steps': 3560, 'loss/train': 2.5116159915924072} 08/30/2021 13:50:52 - INFO - __main__ - Step 3562: {'lr': 0.0004998627689465276, 'samples': 683904, 'steps': 3561, 'loss/train': 2.426597833633423} 08/30/2021 13:50:52 - INFO - __main__ - Step 3563: {'lr': 0.0004998625930817829, 'samples': 684096, 'steps': 3562, 'loss/train': 1.8819105625152588} 08/30/2021 13:50:53 - INFO - __main__ - Step 3564: {'lr': 0.0004998624171044541, 'samples': 684288, 'steps': 3563, 'loss/train': 2.7323007583618164} 08/30/2021 13:50:53 - INFO - __main__ - Step 3565: {'lr': 0.000499862241014541, 'samples': 684480, 'steps': 3564, 'loss/train': 2.2394044399261475} 08/30/2021 13:50:53 - INFO - __main__ - Step 3566: {'lr': 0.0004998620648120439, 'samples': 684672, 'steps': 3565, 'loss/train': 2.694523572921753} 08/30/2021 13:50:55 - INFO - __main__ - Step 3567: {'lr': 0.0004998618884969628, 'samples': 684864, 'steps': 3566, 'loss/train': 2.997663974761963} 08/30/2021 13:50:55 - INFO - __main__ - Step 3568: {'lr': 0.0004998617120692977, 'samples': 685056, 'steps': 3567, 'loss/train': 2.824540853500366} 08/30/2021 13:50:56 - INFO - __main__ - Step 3569: {'lr': 0.0004998615355290489, 'samples': 685248, 'steps': 3568, 'loss/train': 2.7600889205932617} 08/30/2021 13:50:56 - INFO - __main__ - Step 3570: {'lr': 0.0004998613588762163, 'samples': 685440, 'steps': 3569, 'loss/train': 1.759244680404663} 08/30/2021 13:50:56 - INFO - __main__ - Step 3571: {'lr': 0.0004998611821108001, 'samples': 685632, 'steps': 3570, 'loss/train': 2.763533115386963} 08/30/2021 13:50:58 - INFO - __main__ - Step 3572: {'lr': 0.0004998610052328002, 'samples': 685824, 'steps': 3571, 'loss/train': 1.9221290349960327} 08/30/2021 13:50:58 - INFO - __main__ - Step 3573: {'lr': 0.0004998608282422169, 'samples': 686016, 'steps': 3572, 'loss/train': 2.7596094608306885} 08/30/2021 13:50:59 - INFO - __main__ - Step 3574: {'lr': 0.0004998606511390501, 'samples': 686208, 'steps': 3573, 'loss/train': 2.6264867782592773} 08/30/2021 13:50:59 - INFO - __main__ - Step 3575: {'lr': 0.0004998604739232999, 'samples': 686400, 'steps': 3574, 'loss/train': 2.5383200645446777} 08/30/2021 13:50:59 - INFO - __main__ - Step 3576: {'lr': 0.0004998602965949664, 'samples': 686592, 'steps': 3575, 'loss/train': 1.304887056350708} 08/30/2021 13:51:01 - INFO - __main__ - Step 3577: {'lr': 0.0004998601191540499, 'samples': 686784, 'steps': 3576, 'loss/train': 2.421765089035034} 08/30/2021 13:51:01 - INFO - __main__ - Step 3578: {'lr': 0.0004998599416005502, 'samples': 686976, 'steps': 3577, 'loss/train': 0.7924010753631592} 08/30/2021 13:51:02 - INFO - __main__ - Step 3579: {'lr': 0.0004998597639344674, 'samples': 687168, 'steps': 3578, 'loss/train': 2.5419864654541016} 08/30/2021 13:51:02 - INFO - __main__ - Step 3580: {'lr': 0.0004998595861558016, 'samples': 687360, 'steps': 3579, 'loss/train': 2.757249593734741} 08/30/2021 13:51:02 - INFO - __main__ - Step 3581: {'lr': 0.000499859408264553, 'samples': 687552, 'steps': 3580, 'loss/train': 2.6921191215515137} 08/30/2021 13:51:04 - INFO - __main__ - Step 3582: {'lr': 0.0004998592302607217, 'samples': 687744, 'steps': 3581, 'loss/train': 2.715059280395508} 08/30/2021 13:51:04 - INFO - __main__ - Step 3583: {'lr': 0.0004998590521443075, 'samples': 687936, 'steps': 3582, 'loss/train': 2.8533082008361816} 08/30/2021 13:51:05 - INFO - __main__ - Step 3584: {'lr': 0.0004998588739153108, 'samples': 688128, 'steps': 3583, 'loss/train': 1.9397984743118286} 08/30/2021 13:51:05 - INFO - __main__ - Step 3585: {'lr': 0.0004998586955737316, 'samples': 688320, 'steps': 3584, 'loss/train': 2.611144781112671} 08/30/2021 13:51:05 - INFO - __main__ - Step 3586: {'lr': 0.0004998585171195698, 'samples': 688512, 'steps': 3585, 'loss/train': 2.3520359992980957} 08/30/2021 13:51:06 - INFO - __main__ - Step 3587: {'lr': 0.0004998583385528256, 'samples': 688704, 'steps': 3586, 'loss/train': 2.5994157791137695} 08/30/2021 13:51:07 - INFO - __main__ - Step 3588: {'lr': 0.0004998581598734991, 'samples': 688896, 'steps': 3587, 'loss/train': 2.06207275390625} 08/30/2021 13:51:08 - INFO - __main__ - Step 3589: {'lr': 0.0004998579810815905, 'samples': 689088, 'steps': 3588, 'loss/train': 2.2917850017547607} 08/30/2021 13:51:08 - INFO - __main__ - Step 3590: {'lr': 0.0004998578021770995, 'samples': 689280, 'steps': 3589, 'loss/train': 2.545503616333008} 08/30/2021 13:51:08 - INFO - __main__ - Step 3591: {'lr': 0.0004998576231600267, 'samples': 689472, 'steps': 3590, 'loss/train': 2.7478041648864746} 08/30/2021 13:51:09 - INFO - __main__ - Step 3592: {'lr': 0.0004998574440303718, 'samples': 689664, 'steps': 3591, 'loss/train': 2.556713581085205} 08/30/2021 13:51:10 - INFO - __main__ - Step 3593: {'lr': 0.0004998572647881349, 'samples': 689856, 'steps': 3592, 'loss/train': 1.7167731523513794} 08/30/2021 13:51:11 - INFO - __main__ - Step 3594: {'lr': 0.0004998570854333163, 'samples': 690048, 'steps': 3593, 'loss/train': 2.6185929775238037} 08/30/2021 13:51:11 - INFO - __main__ - Step 3595: {'lr': 0.0004998569059659158, 'samples': 690240, 'steps': 3594, 'loss/train': 2.525623083114624} 08/30/2021 13:51:11 - INFO - __main__ - Step 3596: {'lr': 0.0004998567263859338, 'samples': 690432, 'steps': 3595, 'loss/train': 2.6915581226348877} 08/30/2021 13:51:12 - INFO - __main__ - Step 3597: {'lr': 0.0004998565466933702, 'samples': 690624, 'steps': 3596, 'loss/train': 2.9205996990203857} 08/30/2021 13:51:13 - INFO - __main__ - Step 3598: {'lr': 0.000499856366888225, 'samples': 690816, 'steps': 3597, 'loss/train': 2.7925093173980713} 08/30/2021 13:51:14 - INFO - __main__ - Step 3599: {'lr': 0.0004998561869704983, 'samples': 691008, 'steps': 3598, 'loss/train': 2.9762027263641357} 08/30/2021 13:51:14 - INFO - __main__ - Step 3600: {'lr': 0.0004998560069401905, 'samples': 691200, 'steps': 3599, 'loss/train': 2.4280307292938232} 08/30/2021 13:51:14 - INFO - __main__ - Step 3601: {'lr': 0.0004998558267973013, 'samples': 691392, 'steps': 3600, 'loss/train': 2.488234043121338} 08/30/2021 13:51:15 - INFO - __main__ - Step 3602: {'lr': 0.0004998556465418309, 'samples': 691584, 'steps': 3601, 'loss/train': 2.2893667221069336} 08/30/2021 13:51:16 - INFO - __main__ - Step 3603: {'lr': 0.0004998554661737795, 'samples': 691776, 'steps': 3602, 'loss/train': 1.9183200597763062} 08/30/2021 13:51:17 - INFO - __main__ - Step 3604: {'lr': 0.000499855285693147, 'samples': 691968, 'steps': 3603, 'loss/train': 1.7201327085494995} 08/30/2021 13:51:17 - INFO - __main__ - Step 3605: {'lr': 0.0004998551050999336, 'samples': 692160, 'steps': 3604, 'loss/train': 2.437591314315796} 08/30/2021 13:51:17 - INFO - __main__ - Step 3606: {'lr': 0.0004998549243941393, 'samples': 692352, 'steps': 3605, 'loss/train': 2.7183268070220947} 08/30/2021 13:51:18 - INFO - __main__ - Step 3607: {'lr': 0.0004998547435757643, 'samples': 692544, 'steps': 3606, 'loss/train': 2.594651460647583} 08/30/2021 13:51:19 - INFO - __main__ - Step 3608: {'lr': 0.0004998545626448087, 'samples': 692736, 'steps': 3607, 'loss/train': 2.3702476024627686} 08/30/2021 13:51:20 - INFO - __main__ - Step 3609: {'lr': 0.0004998543816012723, 'samples': 692928, 'steps': 3608, 'loss/train': 2.772251844406128} 08/30/2021 13:51:20 - INFO - __main__ - Step 3610: {'lr': 0.0004998542004451554, 'samples': 693120, 'steps': 3609, 'loss/train': 2.511382818222046} 08/30/2021 13:51:20 - INFO - __main__ - Step 3611: {'lr': 0.000499854019176458, 'samples': 693312, 'steps': 3610, 'loss/train': 2.1627109050750732} 08/30/2021 13:51:21 - INFO - __main__ - Step 3612: {'lr': 0.0004998538377951803, 'samples': 693504, 'steps': 3611, 'loss/train': 2.2356529235839844} 08/30/2021 13:51:23 - INFO - __main__ - Step 3613: {'lr': 0.0004998536563013224, 'samples': 693696, 'steps': 3612, 'loss/train': 2.6171715259552} 08/30/2021 13:51:23 - INFO - __main__ - Step 3614: {'lr': 0.0004998534746948843, 'samples': 693888, 'steps': 3613, 'loss/train': 2.421427011489868} 08/30/2021 13:51:24 - INFO - __main__ - Step 3615: {'lr': 0.000499853292975866, 'samples': 694080, 'steps': 3614, 'loss/train': 2.3610634803771973} 08/30/2021 13:51:24 - INFO - __main__ - Step 3616: {'lr': 0.0004998531111442676, 'samples': 694272, 'steps': 3615, 'loss/train': 2.3349177837371826} 08/30/2021 13:51:24 - INFO - __main__ - Step 3617: {'lr': 0.0004998529292000893, 'samples': 694464, 'steps': 3616, 'loss/train': 3.0114173889160156} 08/30/2021 13:51:25 - INFO - __main__ - Step 3618: {'lr': 0.0004998527471433312, 'samples': 694656, 'steps': 3617, 'loss/train': 1.8882458209991455} 08/30/2021 13:51:26 - INFO - __main__ - Step 3619: {'lr': 0.0004998525649739932, 'samples': 694848, 'steps': 3618, 'loss/train': 2.433881998062134} 08/30/2021 13:51:27 - INFO - __main__ - Step 3620: {'lr': 0.0004998523826920756, 'samples': 695040, 'steps': 3619, 'loss/train': 1.7084941864013672} 08/30/2021 13:51:27 - INFO - __main__ - Step 3621: {'lr': 0.0004998522002975783, 'samples': 695232, 'steps': 3620, 'loss/train': 2.808939218521118} 08/30/2021 13:51:28 - INFO - __main__ - Step 3622: {'lr': 0.0004998520177905015, 'samples': 695424, 'steps': 3621, 'loss/train': 0.35889846086502075} 08/30/2021 13:51:28 - INFO - __main__ - Step 3623: {'lr': 0.0004998518351708452, 'samples': 695616, 'steps': 3622, 'loss/train': 2.5196497440338135} 08/30/2021 13:51:29 - INFO - __main__ - Step 3624: {'lr': 0.0004998516524386095, 'samples': 695808, 'steps': 3623, 'loss/train': 2.8409476280212402} 08/30/2021 13:51:30 - INFO - __main__ - Step 3625: {'lr': 0.0004998514695937945, 'samples': 696000, 'steps': 3624, 'loss/train': 2.145430088043213} 08/30/2021 13:51:30 - INFO - __main__ - Step 3626: {'lr': 0.0004998512866364003, 'samples': 696192, 'steps': 3625, 'loss/train': 2.6442580223083496} 08/30/2021 13:51:31 - INFO - __main__ - Step 3627: {'lr': 0.000499851103566427, 'samples': 696384, 'steps': 3626, 'loss/train': 2.2818148136138916} 08/30/2021 13:51:31 - INFO - __main__ - Step 3628: {'lr': 0.0004998509203838746, 'samples': 696576, 'steps': 3627, 'loss/train': 2.495744466781616} 08/30/2021 13:51:32 - INFO - __main__ - Step 3629: {'lr': 0.0004998507370887433, 'samples': 696768, 'steps': 3628, 'loss/train': 1.8277839422225952} 08/30/2021 13:51:33 - INFO - __main__ - Step 3630: {'lr': 0.000499850553681033, 'samples': 696960, 'steps': 3629, 'loss/train': 2.233485221862793} 08/30/2021 13:51:33 - INFO - __main__ - Step 3631: {'lr': 0.000499850370160744, 'samples': 697152, 'steps': 3630, 'loss/train': 2.5942776203155518} 08/30/2021 13:51:34 - INFO - __main__ - Step 3632: {'lr': 0.0004998501865278762, 'samples': 697344, 'steps': 3631, 'loss/train': 3.531891107559204} 08/30/2021 13:51:34 - INFO - __main__ - Step 3633: {'lr': 0.0004998500027824298, 'samples': 697536, 'steps': 3632, 'loss/train': 1.5935769081115723} 08/30/2021 13:51:35 - INFO - __main__ - Step 3634: {'lr': 0.0004998498189244049, 'samples': 697728, 'steps': 3633, 'loss/train': 2.510176658630371} 08/30/2021 13:51:36 - INFO - __main__ - Step 3635: {'lr': 0.0004998496349538015, 'samples': 697920, 'steps': 3634, 'loss/train': 3.216143846511841} 08/30/2021 13:51:36 - INFO - __main__ - Step 3636: {'lr': 0.0004998494508706196, 'samples': 698112, 'steps': 3635, 'loss/train': 3.237640619277954} 08/30/2021 13:51:37 - INFO - __main__ - Step 3637: {'lr': 0.0004998492666748594, 'samples': 698304, 'steps': 3636, 'loss/train': 2.424060583114624} 08/30/2021 13:51:37 - INFO - __main__ - Step 3638: {'lr': 0.0004998490823665211, 'samples': 698496, 'steps': 3637, 'loss/train': 2.499631404876709} 08/30/2021 13:51:38 - INFO - __main__ - Step 3639: {'lr': 0.0004998488979456046, 'samples': 698688, 'steps': 3638, 'loss/train': 2.908761978149414} 08/30/2021 13:51:39 - INFO - __main__ - Step 3640: {'lr': 0.00049984871341211, 'samples': 698880, 'steps': 3639, 'loss/train': 2.353151798248291} 08/30/2021 13:51:39 - INFO - __main__ - Step 3641: {'lr': 0.0004998485287660375, 'samples': 699072, 'steps': 3640, 'loss/train': 2.165651559829712} 08/30/2021 13:51:40 - INFO - __main__ - Step 3642: {'lr': 0.0004998483440073871, 'samples': 699264, 'steps': 3641, 'loss/train': 2.507444381713867} 08/30/2021 13:51:40 - INFO - __main__ - Step 3643: {'lr': 0.0004998481591361589, 'samples': 699456, 'steps': 3642, 'loss/train': 2.355511426925659} 08/30/2021 13:51:40 - INFO - __main__ - Step 3644: {'lr': 0.000499847974152353, 'samples': 699648, 'steps': 3643, 'loss/train': 2.609344482421875} 08/30/2021 13:51:42 - INFO - __main__ - Step 3645: {'lr': 0.0004998477890559693, 'samples': 699840, 'steps': 3644, 'loss/train': 3.222691535949707} 08/30/2021 13:51:42 - INFO - __main__ - Step 3646: {'lr': 0.0004998476038470082, 'samples': 700032, 'steps': 3645, 'loss/train': 2.2444677352905273} 08/30/2021 13:51:43 - INFO - __main__ - Step 3647: {'lr': 0.0004998474185254696, 'samples': 700224, 'steps': 3646, 'loss/train': 2.7029998302459717} 08/30/2021 13:51:43 - INFO - __main__ - Step 3648: {'lr': 0.0004998472330913535, 'samples': 700416, 'steps': 3647, 'loss/train': 2.3544774055480957} 08/30/2021 13:51:43 - INFO - __main__ - Step 3649: {'lr': 0.0004998470475446603, 'samples': 700608, 'steps': 3648, 'loss/train': 2.172724723815918} 08/30/2021 13:51:45 - INFO - __main__ - Step 3650: {'lr': 0.0004998468618853896, 'samples': 700800, 'steps': 3649, 'loss/train': 4.969457149505615} 08/30/2021 13:51:46 - INFO - __main__ - Step 3651: {'lr': 0.000499846676113542, 'samples': 700992, 'steps': 3650, 'loss/train': 2.372426986694336} 08/30/2021 13:51:46 - INFO - __main__ - Step 3652: {'lr': 0.0004998464902291173, 'samples': 701184, 'steps': 3651, 'loss/train': 2.1848011016845703} 08/30/2021 13:51:46 - INFO - __main__ - Step 3653: {'lr': 0.0004998463042321155, 'samples': 701376, 'steps': 3652, 'loss/train': 2.1326675415039062} 08/30/2021 13:51:47 - INFO - __main__ - Step 3654: {'lr': 0.0004998461181225369, 'samples': 701568, 'steps': 3653, 'loss/train': 2.654838800430298} 08/30/2021 13:51:47 - INFO - __main__ - Step 3655: {'lr': 0.0004998459319003815, 'samples': 701760, 'steps': 3654, 'loss/train': 2.791910409927368} 08/30/2021 13:51:48 - INFO - __main__ - Step 3656: {'lr': 0.0004998457455656493, 'samples': 701952, 'steps': 3655, 'loss/train': 2.6973209381103516} 08/30/2021 13:51:49 - INFO - __main__ - Step 3657: {'lr': 0.0004998455591183406, 'samples': 702144, 'steps': 3656, 'loss/train': 2.4102044105529785} 08/30/2021 13:51:49 - INFO - __main__ - Step 3658: {'lr': 0.0004998453725584552, 'samples': 702336, 'steps': 3657, 'loss/train': 2.5161054134368896} 08/30/2021 13:51:50 - INFO - __main__ - Step 3659: {'lr': 0.0004998451858859934, 'samples': 702528, 'steps': 3658, 'loss/train': 0.9827682375907898} 08/30/2021 13:51:50 - INFO - __main__ - Step 3660: {'lr': 0.0004998449991009552, 'samples': 702720, 'steps': 3659, 'loss/train': 3.261535882949829} 08/30/2021 13:51:52 - INFO - __main__ - Step 3661: {'lr': 0.0004998448122033408, 'samples': 702912, 'steps': 3660, 'loss/train': 2.6678919792175293} 08/30/2021 13:51:52 - INFO - __main__ - Step 3662: {'lr': 0.00049984462519315, 'samples': 703104, 'steps': 3661, 'loss/train': 2.772693157196045} 08/30/2021 13:51:52 - INFO - __main__ - Step 3663: {'lr': 0.0004998444380703832, 'samples': 703296, 'steps': 3662, 'loss/train': 2.325258255004883} 08/30/2021 13:51:53 - INFO - __main__ - Step 3664: {'lr': 0.0004998442508350404, 'samples': 703488, 'steps': 3663, 'loss/train': 3.08449387550354} 08/30/2021 13:51:53 - INFO - __main__ - Step 3665: {'lr': 0.0004998440634871215, 'samples': 703680, 'steps': 3664, 'loss/train': 2.883807897567749} 08/30/2021 13:51:53 - INFO - __main__ - Step 3666: {'lr': 0.0004998438760266267, 'samples': 703872, 'steps': 3665, 'loss/train': 2.993598461151123} 08/30/2021 13:51:55 - INFO - __main__ - Step 3667: {'lr': 0.0004998436884535562, 'samples': 704064, 'steps': 3666, 'loss/train': 3.1137425899505615} 08/30/2021 13:51:56 - INFO - __main__ - Step 3668: {'lr': 0.00049984350076791, 'samples': 704256, 'steps': 3667, 'loss/train': 2.7652134895324707} 08/30/2021 13:51:56 - INFO - __main__ - Step 3669: {'lr': 0.0004998433129696882, 'samples': 704448, 'steps': 3668, 'loss/train': 4.125020503997803} 08/30/2021 13:51:57 - INFO - __main__ - Step 3670: {'lr': 0.0004998431250588907, 'samples': 704640, 'steps': 3669, 'loss/train': 2.8697245121002197} 08/30/2021 13:51:57 - INFO - __main__ - Step 3671: {'lr': 0.0004998429370355179, 'samples': 704832, 'steps': 3670, 'loss/train': 2.544102430343628} 08/30/2021 13:51:59 - INFO - __main__ - Step 3672: {'lr': 0.0004998427488995697, 'samples': 705024, 'steps': 3671, 'loss/train': 2.3762354850769043} 08/30/2021 13:51:59 - INFO - __main__ - Step 3673: {'lr': 0.0004998425606510461, 'samples': 705216, 'steps': 3672, 'loss/train': 2.556892156600952} 08/30/2021 13:51:59 - INFO - __main__ - Step 3674: {'lr': 0.0004998423722899475, 'samples': 705408, 'steps': 3673, 'loss/train': 2.7123448848724365} 08/30/2021 13:52:00 - INFO - __main__ - Step 3675: {'lr': 0.0004998421838162735, 'samples': 705600, 'steps': 3674, 'loss/train': 2.2789807319641113} 08/30/2021 13:52:00 - INFO - __main__ - Step 3676: {'lr': 0.0004998419952300247, 'samples': 705792, 'steps': 3675, 'loss/train': 2.485870838165283} 08/30/2021 13:52:02 - INFO - __main__ - Step 3677: {'lr': 0.0004998418065312009, 'samples': 705984, 'steps': 3676, 'loss/train': 2.365833282470703} 08/30/2021 13:52:02 - INFO - __main__ - Step 3678: {'lr': 0.0004998416177198022, 'samples': 706176, 'steps': 3677, 'loss/train': 2.5473415851593018} 08/30/2021 13:52:02 - INFO - __main__ - Step 3679: {'lr': 0.0004998414287958288, 'samples': 706368, 'steps': 3678, 'loss/train': 3.116532564163208} 08/30/2021 13:52:03 - INFO - __main__ - Step 3680: {'lr': 0.0004998412397592807, 'samples': 706560, 'steps': 3679, 'loss/train': 2.694526433944702} 08/30/2021 13:52:03 - INFO - __main__ - Step 3681: {'lr': 0.0004998410506101579, 'samples': 706752, 'steps': 3680, 'loss/train': 1.8455294370651245} 08/30/2021 13:52:05 - INFO - __main__ - Step 3682: {'lr': 0.0004998408613484605, 'samples': 706944, 'steps': 3681, 'loss/train': 2.552056312561035} 08/30/2021 13:52:05 - INFO - __main__ - Step 3683: {'lr': 0.0004998406719741888, 'samples': 707136, 'steps': 3682, 'loss/train': 2.147366523742676} 08/30/2021 13:52:06 - INFO - __main__ - Step 3684: {'lr': 0.0004998404824873428, 'samples': 707328, 'steps': 3683, 'loss/train': 2.796283721923828} 08/30/2021 13:52:06 - INFO - __main__ - Step 3685: {'lr': 0.0004998402928879225, 'samples': 707520, 'steps': 3684, 'loss/train': 4.553436756134033} 08/30/2021 13:52:07 - INFO - __main__ - Step 3686: {'lr': 0.000499840103175928, 'samples': 707712, 'steps': 3685, 'loss/train': 4.194932460784912} 08/30/2021 13:52:07 - INFO - __main__ - Step 3687: {'lr': 0.0004998399133513594, 'samples': 707904, 'steps': 3686, 'loss/train': 2.6775131225585938} 08/30/2021 13:52:08 - INFO - __main__ - Step 3688: {'lr': 0.0004998397234142167, 'samples': 708096, 'steps': 3687, 'loss/train': 2.5451133251190186} 08/30/2021 13:52:09 - INFO - __main__ - Step 3689: {'lr': 0.0004998395333645002, 'samples': 708288, 'steps': 3688, 'loss/train': 2.450786828994751} 08/30/2021 13:52:09 - INFO - __main__ - Step 3690: {'lr': 0.0004998393432022098, 'samples': 708480, 'steps': 3689, 'loss/train': 2.843982219696045} 08/30/2021 13:52:09 - INFO - __main__ - Step 3691: {'lr': 0.0004998391529273457, 'samples': 708672, 'steps': 3690, 'loss/train': 3.115355968475342} 08/30/2021 13:52:10 - INFO - __main__ - Step 3692: {'lr': 0.0004998389625399079, 'samples': 708864, 'steps': 3691, 'loss/train': 2.4430673122406006} 08/30/2021 13:52:11 - INFO - __main__ - Step 3693: {'lr': 0.0004998387720398965, 'samples': 709056, 'steps': 3692, 'loss/train': 2.5386247634887695} 08/30/2021 13:52:12 - INFO - __main__ - Step 3694: {'lr': 0.0004998385814273116, 'samples': 709248, 'steps': 3693, 'loss/train': 2.9216532707214355} 08/30/2021 13:52:12 - INFO - __main__ - Step 3695: {'lr': 0.0004998383907021533, 'samples': 709440, 'steps': 3694, 'loss/train': 2.920185089111328} 08/30/2021 13:52:12 - INFO - __main__ - Step 3696: {'lr': 0.0004998381998644217, 'samples': 709632, 'steps': 3695, 'loss/train': 2.953571081161499} 08/30/2021 13:52:13 - INFO - __main__ - Step 3697: {'lr': 0.0004998380089141169, 'samples': 709824, 'steps': 3696, 'loss/train': 2.786409616470337} 08/30/2021 13:52:13 - INFO - __main__ - Step 3698: {'lr': 0.0004998378178512388, 'samples': 710016, 'steps': 3697, 'loss/train': 2.8580715656280518} 08/30/2021 13:52:15 - INFO - __main__ - Step 3699: {'lr': 0.0004998376266757878, 'samples': 710208, 'steps': 3698, 'loss/train': 2.263169527053833} 08/30/2021 13:52:15 - INFO - __main__ - Step 3700: {'lr': 0.0004998374353877638, 'samples': 710400, 'steps': 3699, 'loss/train': 2.262291193008423} 08/30/2021 13:52:16 - INFO - __main__ - Step 3701: {'lr': 0.0004998372439871668, 'samples': 710592, 'steps': 3700, 'loss/train': 2.199047088623047} 08/30/2021 13:52:16 - INFO - __main__ - Step 3702: {'lr': 0.000499837052473997, 'samples': 710784, 'steps': 3701, 'loss/train': 2.673276901245117} 08/30/2021 13:52:16 - INFO - __main__ - Step 3703: {'lr': 0.0004998368608482546, 'samples': 710976, 'steps': 3702, 'loss/train': 1.017385721206665} 08/30/2021 13:52:18 - INFO - __main__ - Step 3704: {'lr': 0.0004998366691099395, 'samples': 711168, 'steps': 3703, 'loss/train': 2.869640827178955} 08/30/2021 13:52:18 - INFO - __main__ - Step 3705: {'lr': 0.0004998364772590518, 'samples': 711360, 'steps': 3704, 'loss/train': 2.46382999420166} 08/30/2021 13:52:19 - INFO - __main__ - Step 3706: {'lr': 0.0004998362852955918, 'samples': 711552, 'steps': 3705, 'loss/train': 2.588064670562744} 08/30/2021 13:52:19 - INFO - __main__ - Step 3707: {'lr': 0.0004998360932195593, 'samples': 711744, 'steps': 3706, 'loss/train': 2.1821370124816895} 08/30/2021 13:52:19 - INFO - __main__ - Step 3708: {'lr': 0.0004998359010309544, 'samples': 711936, 'steps': 3707, 'loss/train': 2.8211324214935303} 08/30/2021 13:52:21 - INFO - __main__ - Step 3709: {'lr': 0.0004998357087297775, 'samples': 712128, 'steps': 3708, 'loss/train': 2.548093795776367} 08/30/2021 13:52:21 - INFO - __main__ - Step 3710: {'lr': 0.0004998355163160285, 'samples': 712320, 'steps': 3709, 'loss/train': 2.2347397804260254} 08/30/2021 13:52:22 - INFO - __main__ - Step 3711: {'lr': 0.0004998353237897073, 'samples': 712512, 'steps': 3710, 'loss/train': 2.639876365661621} 08/30/2021 13:52:22 - INFO - __main__ - Step 3712: {'lr': 0.0004998351311508143, 'samples': 712704, 'steps': 3711, 'loss/train': 2.1529603004455566} 08/30/2021 13:52:22 - INFO - __main__ - Step 3713: {'lr': 0.0004998349383993493, 'samples': 712896, 'steps': 3712, 'loss/train': 2.668527603149414} 08/30/2021 13:52:23 - INFO - __main__ - Step 3714: {'lr': 0.0004998347455353126, 'samples': 713088, 'steps': 3713, 'loss/train': 0.8968461751937866} 08/30/2021 13:52:24 - INFO - __main__ - Step 3715: {'lr': 0.0004998345525587042, 'samples': 713280, 'steps': 3714, 'loss/train': 2.333482027053833} 08/30/2021 13:52:25 - INFO - __main__ - Step 3716: {'lr': 0.0004998343594695242, 'samples': 713472, 'steps': 3715, 'loss/train': 2.33561635017395} 08/30/2021 13:52:25 - INFO - __main__ - Step 3717: {'lr': 0.0004998341662677728, 'samples': 713664, 'steps': 3716, 'loss/train': 2.167950391769409} 08/30/2021 13:52:25 - INFO - __main__ - Step 3718: {'lr': 0.0004998339729534499, 'samples': 713856, 'steps': 3717, 'loss/train': 2.8927276134490967} 08/30/2021 13:52:26 - INFO - __main__ - Step 3719: {'lr': 0.0004998337795265557, 'samples': 714048, 'steps': 3718, 'loss/train': 2.127739667892456} 08/30/2021 13:52:28 - INFO - __main__ - Step 3720: {'lr': 0.0004998335859870903, 'samples': 714240, 'steps': 3719, 'loss/train': 2.9572927951812744} 08/30/2021 13:52:28 - INFO - __main__ - Step 3721: {'lr': 0.0004998333923350536, 'samples': 714432, 'steps': 3720, 'loss/train': 2.553959846496582} 08/30/2021 13:52:29 - INFO - __main__ - Step 3722: {'lr': 0.000499833198570446, 'samples': 714624, 'steps': 3721, 'loss/train': 2.5492050647735596} 08/30/2021 13:52:29 - INFO - __main__ - Step 3723: {'lr': 0.0004998330046932672, 'samples': 714816, 'steps': 3722, 'loss/train': 2.729675769805908} 08/30/2021 13:52:29 - INFO - __main__ - Step 3724: {'lr': 0.0004998328107035176, 'samples': 715008, 'steps': 3723, 'loss/train': 0.5745132565498352} 08/30/2021 13:52:31 - INFO - __main__ - Step 3725: {'lr': 0.0004998326166011973, 'samples': 715200, 'steps': 3724, 'loss/train': 2.6041486263275146} 08/30/2021 13:52:31 - INFO - __main__ - Step 3726: {'lr': 0.0004998324223863061, 'samples': 715392, 'steps': 3725, 'loss/train': 2.502439260482788} 08/30/2021 13:52:32 - INFO - __main__ - Step 3727: {'lr': 0.0004998322280588445, 'samples': 715584, 'steps': 3726, 'loss/train': 2.617800712585449} 08/30/2021 13:52:32 - INFO - __main__ - Step 3728: {'lr': 0.0004998320336188121, 'samples': 715776, 'steps': 3727, 'loss/train': 1.7495018243789673} 08/30/2021 13:52:32 - INFO - __main__ - Step 3729: {'lr': 0.0004998318390662095, 'samples': 715968, 'steps': 3728, 'loss/train': 2.223163366317749} 08/30/2021 13:52:34 - INFO - __main__ - Step 3730: {'lr': 0.0004998316444010363, 'samples': 716160, 'steps': 3729, 'loss/train': 2.0308051109313965} 08/30/2021 13:52:35 - INFO - __main__ - Step 3731: {'lr': 0.0004998314496232929, 'samples': 716352, 'steps': 3730, 'loss/train': 2.0826940536499023} 08/30/2021 13:52:35 - INFO - __main__ - Step 3732: {'lr': 0.0004998312547329793, 'samples': 716544, 'steps': 3731, 'loss/train': 2.4998042583465576} 08/30/2021 13:52:35 - INFO - __main__ - Step 3733: {'lr': 0.0004998310597300956, 'samples': 716736, 'steps': 3732, 'loss/train': 2.7541556358337402} 08/30/2021 13:52:36 - INFO - __main__ - Step 3734: {'lr': 0.0004998308646146419, 'samples': 716928, 'steps': 3733, 'loss/train': 1.8123992681503296} 08/30/2021 13:52:36 - INFO - __main__ - Step 3735: {'lr': 0.0004998306693866181, 'samples': 717120, 'steps': 3734, 'loss/train': 2.1201188564300537} 08/30/2021 13:52:38 - INFO - __main__ - Step 3736: {'lr': 0.0004998304740460247, 'samples': 717312, 'steps': 3735, 'loss/train': 0.5890623331069946} 08/30/2021 13:52:38 - INFO - __main__ - Step 3737: {'lr': 0.0004998302785928614, 'samples': 717504, 'steps': 3736, 'loss/train': 2.6408166885375977} 08/30/2021 13:52:39 - INFO - __main__ - Step 3738: {'lr': 0.0004998300830271285, 'samples': 717696, 'steps': 3737, 'loss/train': 2.593217134475708} 08/30/2021 13:52:39 - INFO - __main__ - Step 3739: {'lr': 0.000499829887348826, 'samples': 717888, 'steps': 3738, 'loss/train': 2.4458932876586914} 08/30/2021 13:52:40 - INFO - __main__ - Step 3740: {'lr': 0.0004998296915579539, 'samples': 718080, 'steps': 3739, 'loss/train': 2.755025625228882} 08/30/2021 13:52:40 - INFO - __main__ - Step 3741: {'lr': 0.0004998294956545125, 'samples': 718272, 'steps': 3740, 'loss/train': 0.9906896352767944} 08/30/2021 13:52:41 - INFO - __main__ - Step 3742: {'lr': 0.0004998292996385019, 'samples': 718464, 'steps': 3741, 'loss/train': 1.7878564596176147} 08/30/2021 13:52:42 - INFO - __main__ - Step 3743: {'lr': 0.0004998291035099219, 'samples': 718656, 'steps': 3742, 'loss/train': 2.2241365909576416} 08/30/2021 13:52:42 - INFO - __main__ - Step 3744: {'lr': 0.0004998289072687728, 'samples': 718848, 'steps': 3743, 'loss/train': 2.798021078109741} 08/30/2021 13:52:43 - INFO - __main__ - Step 3745: {'lr': 0.0004998287109150547, 'samples': 719040, 'steps': 3744, 'loss/train': 1.918013572692871} 08/30/2021 13:52:43 - INFO - __main__ - Step 3746: {'lr': 0.0004998285144487676, 'samples': 719232, 'steps': 3745, 'loss/train': 2.5508880615234375} 08/30/2021 13:52:44 - INFO - __main__ - Step 3747: {'lr': 0.0004998283178699116, 'samples': 719424, 'steps': 3746, 'loss/train': 2.0125818252563477} 08/30/2021 13:52:45 - INFO - __main__ - Step 3748: {'lr': 0.0004998281211784869, 'samples': 719616, 'steps': 3747, 'loss/train': 2.6958279609680176} 08/30/2021 13:52:45 - INFO - __main__ - Step 3749: {'lr': 0.0004998279243744934, 'samples': 719808, 'steps': 3748, 'loss/train': 2.651625394821167} 08/30/2021 13:52:46 - INFO - __main__ - Step 3750: {'lr': 0.0004998277274579313, 'samples': 720000, 'steps': 3749, 'loss/train': 1.690513014793396} 08/30/2021 13:52:46 - INFO - __main__ - Step 3751: {'lr': 0.0004998275304288007, 'samples': 720192, 'steps': 3750, 'loss/train': 2.3952298164367676} 08/30/2021 13:52:47 - INFO - __main__ - Step 3752: {'lr': 0.0004998273332871017, 'samples': 720384, 'steps': 3751, 'loss/train': 2.3898682594299316} 08/30/2021 13:52:48 - INFO - __main__ - Step 3753: {'lr': 0.0004998271360328344, 'samples': 720576, 'steps': 3752, 'loss/train': 2.195742607116699} 08/30/2021 13:52:48 - INFO - __main__ - Step 3754: {'lr': 0.0004998269386659988, 'samples': 720768, 'steps': 3753, 'loss/train': 2.1724729537963867} 08/30/2021 13:52:49 - INFO - __main__ - Step 3755: {'lr': 0.000499826741186595, 'samples': 720960, 'steps': 3754, 'loss/train': 1.760980248451233} 08/30/2021 13:52:49 - INFO - __main__ - Step 3756: {'lr': 0.0004998265435946232, 'samples': 721152, 'steps': 3755, 'loss/train': 2.3340656757354736} 08/30/2021 13:52:50 - INFO - __main__ - Step 3757: {'lr': 0.0004998263458900833, 'samples': 721344, 'steps': 3756, 'loss/train': 2.6274890899658203} 08/30/2021 13:52:51 - INFO - __main__ - Step 3758: {'lr': 0.0004998261480729755, 'samples': 721536, 'steps': 3757, 'loss/train': 2.353910446166992} 08/30/2021 13:52:51 - INFO - __main__ - Step 3759: {'lr': 0.0004998259501433, 'samples': 721728, 'steps': 3758, 'loss/train': 2.0382802486419678} 08/30/2021 13:52:52 - INFO - __main__ - Step 3760: {'lr': 0.0004998257521010567, 'samples': 721920, 'steps': 3759, 'loss/train': 2.4699389934539795} 08/30/2021 13:52:52 - INFO - __main__ - Step 3761: {'lr': 0.0004998255539462459, 'samples': 722112, 'steps': 3760, 'loss/train': 2.4543662071228027} 08/30/2021 13:52:52 - INFO - __main__ - Step 3762: {'lr': 0.0004998253556788675, 'samples': 722304, 'steps': 3761, 'loss/train': 2.363558292388916} 08/30/2021 13:52:54 - INFO - __main__ - Step 3763: {'lr': 0.0004998251572989217, 'samples': 722496, 'steps': 3762, 'loss/train': 2.9797966480255127} 08/30/2021 13:52:54 - INFO - __main__ - Step 3764: {'lr': 0.0004998249588064085, 'samples': 722688, 'steps': 3763, 'loss/train': 2.7801966667175293} 08/30/2021 13:52:54 - INFO - __main__ - Step 3765: {'lr': 0.0004998247602013278, 'samples': 722880, 'steps': 3764, 'loss/train': 1.3150078058242798} 08/30/2021 13:52:55 - INFO - __main__ - Step 3766: {'lr': 0.0004998245614836802, 'samples': 723072, 'steps': 3765, 'loss/train': 2.424520492553711} 08/30/2021 13:52:55 - INFO - __main__ - Step 3767: {'lr': 0.0004998243626534655, 'samples': 723264, 'steps': 3766, 'loss/train': 2.5986714363098145} 08/30/2021 13:52:57 - INFO - __main__ - Step 3768: {'lr': 0.0004998241637106836, 'samples': 723456, 'steps': 3767, 'loss/train': 2.1446802616119385} 08/30/2021 13:52:58 - INFO - __main__ - Step 3769: {'lr': 0.0004998239646553349, 'samples': 723648, 'steps': 3768, 'loss/train': 1.9051599502563477} 08/30/2021 13:52:58 - INFO - __main__ - Step 3770: {'lr': 0.0004998237654874195, 'samples': 723840, 'steps': 3769, 'loss/train': 2.1859586238861084} 08/30/2021 13:52:58 - INFO - __main__ - Step 3771: {'lr': 0.0004998235662069372, 'samples': 724032, 'steps': 3770, 'loss/train': 2.496194839477539} 08/30/2021 13:52:59 - INFO - __main__ - Step 3772: {'lr': 0.0004998233668138883, 'samples': 724224, 'steps': 3771, 'loss/train': 2.494786024093628} 08/30/2021 13:52:59 - INFO - __main__ - Step 3773: {'lr': 0.0004998231673082729, 'samples': 724416, 'steps': 3772, 'loss/train': 0.910167396068573} 08/30/2021 13:53:00 - INFO - __main__ - Step 3774: {'lr': 0.000499822967690091, 'samples': 724608, 'steps': 3773, 'loss/train': 1.0037932395935059} 08/30/2021 13:53:01 - INFO - __main__ - Step 3775: {'lr': 0.0004998227679593426, 'samples': 724800, 'steps': 3774, 'loss/train': 2.0974268913269043} 08/30/2021 13:53:01 - INFO - __main__ - Step 3776: {'lr': 0.0004998225681160281, 'samples': 724992, 'steps': 3775, 'loss/train': 2.4184041023254395} 08/30/2021 13:53:02 - INFO - __main__ - Step 3777: {'lr': 0.0004998223681601474, 'samples': 725184, 'steps': 3776, 'loss/train': 1.980934739112854} 08/30/2021 13:53:02 - INFO - __main__ - Step 3778: {'lr': 0.0004998221680917004, 'samples': 725376, 'steps': 3777, 'loss/train': 2.4494545459747314} 08/30/2021 13:53:04 - INFO - __main__ - Step 3779: {'lr': 0.0004998219679106876, 'samples': 725568, 'steps': 3778, 'loss/train': 3.0036258697509766} 08/30/2021 13:53:05 - INFO - __main__ - Step 3780: {'lr': 0.0004998217676171088, 'samples': 725760, 'steps': 3779, 'loss/train': 2.1836447715759277} 08/30/2021 13:53:05 - INFO - __main__ - Step 3781: {'lr': 0.0004998215672109641, 'samples': 725952, 'steps': 3780, 'loss/train': 2.39762544631958} 08/30/2021 13:53:05 - INFO - __main__ - Step 3782: {'lr': 0.0004998213666922537, 'samples': 726144, 'steps': 3781, 'loss/train': 6.193061351776123} 08/30/2021 13:53:06 - INFO - __main__ - Step 3783: {'lr': 0.0004998211660609777, 'samples': 726336, 'steps': 3782, 'loss/train': 2.981644868850708} 08/30/2021 13:53:06 - INFO - __main__ - Step 3784: {'lr': 0.0004998209653171361, 'samples': 726528, 'steps': 3783, 'loss/train': 4.001317977905273} 08/30/2021 13:53:08 - INFO - __main__ - Step 3785: {'lr': 0.0004998207644607291, 'samples': 726720, 'steps': 3784, 'loss/train': 3.830148458480835} 08/30/2021 13:53:09 - INFO - __main__ - Step 3786: {'lr': 0.0004998205634917566, 'samples': 726912, 'steps': 3785, 'loss/train': 3.1851704120635986} 08/30/2021 13:53:09 - INFO - __main__ - Step 3787: {'lr': 0.0004998203624102188, 'samples': 727104, 'steps': 3786, 'loss/train': 3.435906171798706} 08/30/2021 13:53:09 - INFO - __main__ - Step 3788: {'lr': 0.0004998201612161159, 'samples': 727296, 'steps': 3787, 'loss/train': 2.6408236026763916} 08/30/2021 13:53:10 - INFO - __main__ - Step 3789: {'lr': 0.0004998199599094478, 'samples': 727488, 'steps': 3788, 'loss/train': 2.8391733169555664} 08/30/2021 13:53:10 - INFO - __main__ - Step 3790: {'lr': 0.0004998197584902147, 'samples': 727680, 'steps': 3789, 'loss/train': 3.1133480072021484} 08/30/2021 13:53:11 - INFO - __main__ - Step 3791: {'lr': 0.0004998195569584168, 'samples': 727872, 'steps': 3790, 'loss/train': 1.9843635559082031} 08/30/2021 13:53:12 - INFO - __main__ - Step 3792: {'lr': 0.0004998193553140539, 'samples': 728064, 'steps': 3791, 'loss/train': 2.3932769298553467} 08/30/2021 13:53:12 - INFO - __main__ - Step 3793: {'lr': 0.0004998191535571264, 'samples': 728256, 'steps': 3792, 'loss/train': 2.2312867641448975} 08/30/2021 13:53:13 - INFO - __main__ - Step 3794: {'lr': 0.0004998189516876342, 'samples': 728448, 'steps': 3793, 'loss/train': 1.3847050666809082} 08/30/2021 13:53:13 - INFO - __main__ - Step 3795: {'lr': 0.0004998187497055773, 'samples': 728640, 'steps': 3794, 'loss/train': 5.628871440887451} 08/30/2021 13:53:14 - INFO - __main__ - Step 3796: {'lr': 0.000499818547610956, 'samples': 728832, 'steps': 3795, 'loss/train': 3.263817071914673} 08/30/2021 13:53:15 - INFO - __main__ - Step 3797: {'lr': 0.0004998183454037703, 'samples': 729024, 'steps': 3796, 'loss/train': 2.5504064559936523} 08/30/2021 13:53:15 - INFO - __main__ - Step 3798: {'lr': 0.0004998181430840204, 'samples': 729216, 'steps': 3797, 'loss/train': 3.251636266708374} 08/30/2021 13:53:16 - INFO - __main__ - Step 3799: {'lr': 0.0004998179406517063, 'samples': 729408, 'steps': 3798, 'loss/train': 2.312483787536621} 08/30/2021 13:53:16 - INFO - __main__ - Step 3800: {'lr': 0.000499817738106828, 'samples': 729600, 'steps': 3799, 'loss/train': 2.8077876567840576} 08/30/2021 13:53:18 - INFO - __main__ - Step 3801: {'lr': 0.0004998175354493857, 'samples': 729792, 'steps': 3800, 'loss/train': 2.6324970722198486} 08/30/2021 13:53:19 - INFO - __main__ - Step 3802: {'lr': 0.0004998173326793795, 'samples': 729984, 'steps': 3801, 'loss/train': 2.687063217163086} 08/30/2021 13:53:19 - INFO - __main__ - Step 3803: {'lr': 0.0004998171297968095, 'samples': 730176, 'steps': 3802, 'loss/train': 2.632704257965088} 08/30/2021 13:53:19 - INFO - __main__ - Step 3804: {'lr': 0.0004998169268016757, 'samples': 730368, 'steps': 3803, 'loss/train': 2.495011329650879} 08/30/2021 13:53:20 - INFO - __main__ - Step 3805: {'lr': 0.0004998167236939783, 'samples': 730560, 'steps': 3804, 'loss/train': 2.9213318824768066} 08/30/2021 13:53:20 - INFO - __main__ - Step 3806: {'lr': 0.0004998165204737173, 'samples': 730752, 'steps': 3805, 'loss/train': 2.8817858695983887} 08/30/2021 13:53:21 - INFO - __main__ - Step 3807: {'lr': 0.0004998163171408928, 'samples': 730944, 'steps': 3806, 'loss/train': 0.49705567955970764} 08/30/2021 13:53:22 - INFO - __main__ - Step 3808: {'lr': 0.000499816113695505, 'samples': 731136, 'steps': 3807, 'loss/train': 2.760344982147217} 08/30/2021 13:53:22 - INFO - __main__ - Step 3809: {'lr': 0.0004998159101375538, 'samples': 731328, 'steps': 3808, 'loss/train': 3.4015262126922607} 08/30/2021 13:53:23 - INFO - __main__ - Step 3810: {'lr': 0.0004998157064670395, 'samples': 731520, 'steps': 3809, 'loss/train': 2.6240994930267334} 08/30/2021 13:53:23 - INFO - __main__ - Step 3811: {'lr': 0.0004998155026839621, 'samples': 731712, 'steps': 3810, 'loss/train': 3.15437650680542} 08/30/2021 13:53:24 - INFO - __main__ - Step 3812: {'lr': 0.0004998152987883217, 'samples': 731904, 'steps': 3811, 'loss/train': 2.288787364959717} 08/30/2021 13:53:25 - INFO - __main__ - Step 3813: {'lr': 0.0004998150947801182, 'samples': 732096, 'steps': 3812, 'loss/train': 2.1823601722717285} 08/30/2021 13:53:25 - INFO - __main__ - Step 3814: {'lr': 0.000499814890659352, 'samples': 732288, 'steps': 3813, 'loss/train': 2.1743075847625732} 08/30/2021 13:53:26 - INFO - __main__ - Step 3815: {'lr': 0.0004998146864260231, 'samples': 732480, 'steps': 3814, 'loss/train': 2.6787259578704834} 08/30/2021 13:53:26 - INFO - __main__ - Step 3816: {'lr': 0.0004998144820801316, 'samples': 732672, 'steps': 3815, 'loss/train': 2.8744006156921387} 08/30/2021 13:53:26 - INFO - __main__ - Step 3817: {'lr': 0.0004998142776216775, 'samples': 732864, 'steps': 3816, 'loss/train': 3.1672487258911133} 08/30/2021 13:53:28 - INFO - __main__ - Step 3818: {'lr': 0.0004998140730506609, 'samples': 733056, 'steps': 3817, 'loss/train': 2.4270360469818115} 08/30/2021 13:53:28 - INFO - __main__ - Step 3819: {'lr': 0.000499813868367082, 'samples': 733248, 'steps': 3818, 'loss/train': 3.1737098693847656} 08/30/2021 13:53:29 - INFO - __main__ - Step 3820: {'lr': 0.0004998136635709408, 'samples': 733440, 'steps': 3819, 'loss/train': 2.706602096557617} 08/30/2021 13:53:29 - INFO - __main__ - Step 3821: {'lr': 0.0004998134586622374, 'samples': 733632, 'steps': 3820, 'loss/train': 2.02411150932312} 08/30/2021 13:53:29 - INFO - __main__ - Step 3822: {'lr': 0.0004998132536409718, 'samples': 733824, 'steps': 3821, 'loss/train': 2.643583297729492} 08/30/2021 13:53:31 - INFO - __main__ - Step 3823: {'lr': 0.0004998130485071444, 'samples': 734016, 'steps': 3822, 'loss/train': 2.867642641067505} 08/30/2021 13:53:31 - INFO - __main__ - Step 3824: {'lr': 0.000499812843260755, 'samples': 734208, 'steps': 3823, 'loss/train': 1.7342548370361328} 08/30/2021 13:53:32 - INFO - __main__ - Step 3825: {'lr': 0.0004998126379018038, 'samples': 734400, 'steps': 3824, 'loss/train': 2.3599774837493896} 08/30/2021 13:53:32 - INFO - __main__ - Step 3826: {'lr': 0.000499812432430291, 'samples': 734592, 'steps': 3825, 'loss/train': 2.6682610511779785} 08/30/2021 13:53:33 - INFO - __main__ - Step 3827: {'lr': 0.0004998122268462164, 'samples': 734784, 'steps': 3826, 'loss/train': 1.2385571002960205} 08/30/2021 13:53:34 - INFO - __main__ - Step 3828: {'lr': 0.0004998120211495803, 'samples': 734976, 'steps': 3827, 'loss/train': 2.736721992492676} 08/30/2021 13:53:35 - INFO - __main__ - Step 3829: {'lr': 0.0004998118153403827, 'samples': 735168, 'steps': 3828, 'loss/train': 2.391437292098999} 08/30/2021 13:53:35 - INFO - __main__ - Step 3830: {'lr': 0.0004998116094186239, 'samples': 735360, 'steps': 3829, 'loss/train': 1.730520248413086} 08/30/2021 13:53:35 - INFO - __main__ - Step 3831: {'lr': 0.0004998114033843038, 'samples': 735552, 'steps': 3830, 'loss/train': 2.593935966491699} 08/30/2021 13:53:36 - INFO - __main__ - Step 3832: {'lr': 0.0004998111972374225, 'samples': 735744, 'steps': 3831, 'loss/train': 1.7919846773147583} 08/30/2021 13:53:38 - INFO - __main__ - Step 3833: {'lr': 0.0004998109909779801, 'samples': 735936, 'steps': 3832, 'loss/train': 2.8192121982574463} 08/30/2021 13:53:38 - INFO - __main__ - Step 3834: {'lr': 0.0004998107846059768, 'samples': 736128, 'steps': 3833, 'loss/train': 2.320220947265625} 08/30/2021 13:53:39 - INFO - __main__ - Step 3835: {'lr': 0.0004998105781214126, 'samples': 736320, 'steps': 3834, 'loss/train': 2.549633741378784} 08/30/2021 13:53:39 - INFO - __main__ - Step 3836: {'lr': 0.0004998103715242875, 'samples': 736512, 'steps': 3835, 'loss/train': 2.1557517051696777} 08/30/2021 13:53:39 - INFO - __main__ - Step 3837: {'lr': 0.0004998101648146018, 'samples': 736704, 'steps': 3836, 'loss/train': 2.4664957523345947} 08/30/2021 13:53:41 - INFO - __main__ - Step 3838: {'lr': 0.0004998099579923555, 'samples': 736896, 'steps': 3837, 'loss/train': 2.3150134086608887} 08/30/2021 13:53:41 - INFO - __main__ - Step 3839: {'lr': 0.0004998097510575487, 'samples': 737088, 'steps': 3838, 'loss/train': 2.5504868030548096} 08/30/2021 13:53:42 - INFO - __main__ - Step 3840: {'lr': 0.0004998095440101815, 'samples': 737280, 'steps': 3839, 'loss/train': 2.8693466186523438} 08/30/2021 13:53:42 - INFO - __main__ - Step 3841: {'lr': 0.0004998093368502539, 'samples': 737472, 'steps': 3840, 'loss/train': 2.893502712249756} 08/30/2021 13:53:42 - INFO - __main__ - Step 3842: {'lr': 0.000499809129577766, 'samples': 737664, 'steps': 3841, 'loss/train': 2.001295328140259} 08/30/2021 13:53:44 - INFO - __main__ - Step 3843: {'lr': 0.0004998089221927182, 'samples': 737856, 'steps': 3842, 'loss/train': 2.1130106449127197} 08/30/2021 13:53:44 - INFO - __main__ - Step 3844: {'lr': 0.0004998087146951101, 'samples': 738048, 'steps': 3843, 'loss/train': 2.247541666030884} 08/30/2021 13:53:45 - INFO - __main__ - Step 3845: {'lr': 0.0004998085070849422, 'samples': 738240, 'steps': 3844, 'loss/train': 2.3881845474243164} 08/30/2021 13:53:45 - INFO - __main__ - Step 3846: {'lr': 0.0004998082993622144, 'samples': 738432, 'steps': 3845, 'loss/train': 2.4177701473236084} 08/30/2021 13:53:45 - INFO - __main__ - Step 3847: {'lr': 0.0004998080915269268, 'samples': 738624, 'steps': 3846, 'loss/train': 2.283220052719116} 08/30/2021 13:53:47 - INFO - __main__ - Step 3848: {'lr': 0.0004998078835790796, 'samples': 738816, 'steps': 3847, 'loss/train': 2.7085118293762207} 08/30/2021 13:53:48 - INFO - __main__ - Step 3849: {'lr': 0.0004998076755186727, 'samples': 739008, 'steps': 3848, 'loss/train': 2.1108334064483643} 08/30/2021 13:53:48 - INFO - __main__ - Step 3850: {'lr': 0.0004998074673457064, 'samples': 739200, 'steps': 3849, 'loss/train': 0.5631784796714783} 08/30/2021 13:53:48 - INFO - __main__ - Step 3851: {'lr': 0.0004998072590601808, 'samples': 739392, 'steps': 3850, 'loss/train': 0.9390645027160645} 08/30/2021 13:53:49 - INFO - __main__ - Step 3852: {'lr': 0.0004998070506620957, 'samples': 739584, 'steps': 3851, 'loss/train': 2.112011671066284} 08/30/2021 13:53:49 - INFO - __main__ - Step 3853: {'lr': 0.0004998068421514515, 'samples': 739776, 'steps': 3852, 'loss/train': 1.1400758028030396} 08/30/2021 13:53:50 - INFO - __main__ - Step 3854: {'lr': 0.0004998066335282483, 'samples': 739968, 'steps': 3853, 'loss/train': 1.3761924505233765} 08/30/2021 13:53:51 - INFO - __main__ - Step 3855: {'lr': 0.0004998064247924859, 'samples': 740160, 'steps': 3854, 'loss/train': 1.2922638654708862} 08/30/2021 13:53:51 - INFO - __main__ - Step 3856: {'lr': 0.0004998062159441648, 'samples': 740352, 'steps': 3855, 'loss/train': 2.1958119869232178} 08/30/2021 13:53:52 - INFO - __main__ - Step 3857: {'lr': 0.0004998060069832846, 'samples': 740544, 'steps': 3856, 'loss/train': 1.2535297870635986} 08/30/2021 13:53:52 - INFO - __main__ - Step 3858: {'lr': 0.0004998057979098459, 'samples': 740736, 'steps': 3857, 'loss/train': 2.8661746978759766} 08/30/2021 13:53:52 - INFO - __main__ - Step 3859: {'lr': 0.0004998055887238485, 'samples': 740928, 'steps': 3858, 'loss/train': 2.3009345531463623} 08/30/2021 13:53:54 - INFO - __main__ - Step 3860: {'lr': 0.0004998053794252925, 'samples': 741120, 'steps': 3859, 'loss/train': 2.258052110671997} 08/30/2021 13:53:54 - INFO - __main__ - Step 3861: {'lr': 0.0004998051700141781, 'samples': 741312, 'steps': 3860, 'loss/train': 2.3379745483398438} 08/30/2021 13:53:55 - INFO - __main__ - Step 3862: {'lr': 0.0004998049604905052, 'samples': 741504, 'steps': 3861, 'loss/train': 2.379669189453125} 08/30/2021 13:53:55 - INFO - __main__ - Step 3863: {'lr': 0.0004998047508542742, 'samples': 741696, 'steps': 3862, 'loss/train': 3.0659537315368652} 08/30/2021 13:53:55 - INFO - __main__ - Step 3864: {'lr': 0.000499804541105485, 'samples': 741888, 'steps': 3863, 'loss/train': 0.3776046335697174} 08/30/2021 13:53:57 - INFO - __main__ - Step 3865: {'lr': 0.0004998043312441378, 'samples': 742080, 'steps': 3864, 'loss/train': 2.317028045654297} 08/30/2021 13:53:58 - INFO - __main__ - Step 3866: {'lr': 0.0004998041212702325, 'samples': 742272, 'steps': 3865, 'loss/train': 2.523540735244751} 08/30/2021 13:53:58 - INFO - __main__ - Step 3867: {'lr': 0.0004998039111837694, 'samples': 742464, 'steps': 3866, 'loss/train': 2.123126983642578} 08/30/2021 13:53:59 - INFO - __main__ - Step 3868: {'lr': 0.0004998037009847485, 'samples': 742656, 'steps': 3867, 'loss/train': 1.5907723903656006} 08/30/2021 13:53:59 - INFO - __main__ - Step 3869: {'lr': 0.0004998034906731699, 'samples': 742848, 'steps': 3868, 'loss/train': 2.4419124126434326} 08/30/2021 13:54:00 - INFO - __main__ - Step 3870: {'lr': 0.0004998032802490337, 'samples': 743040, 'steps': 3869, 'loss/train': 2.297422409057617} 08/30/2021 13:54:01 - INFO - __main__ - Step 3871: {'lr': 0.0004998030697123399, 'samples': 743232, 'steps': 3870, 'loss/train': 2.200152635574341} 08/30/2021 13:54:01 - INFO - __main__ - Step 3872: {'lr': 0.0004998028590630887, 'samples': 743424, 'steps': 3871, 'loss/train': 2.712414264678955} 08/30/2021 13:54:01 - INFO - __main__ - Step 3873: {'lr': 0.0004998026483012803, 'samples': 743616, 'steps': 3872, 'loss/train': 2.7476024627685547} 08/30/2021 13:54:02 - INFO - __main__ - Step 3874: {'lr': 0.0004998024374269147, 'samples': 743808, 'steps': 3873, 'loss/train': 3.092353343963623} 08/30/2021 13:54:03 - INFO - __main__ - Step 3875: {'lr': 0.000499802226439992, 'samples': 744000, 'steps': 3874, 'loss/train': 1.501655101776123} 08/30/2021 13:54:04 - INFO - __main__ - Step 3876: {'lr': 0.0004998020153405121, 'samples': 744192, 'steps': 3875, 'loss/train': 2.7606687545776367} 08/30/2021 13:54:04 - INFO - __main__ - Step 3877: {'lr': 0.0004998018041284754, 'samples': 744384, 'steps': 3876, 'loss/train': 2.262582302093506} 08/30/2021 13:54:04 - INFO - __main__ - Step 3878: {'lr': 0.0004998015928038819, 'samples': 744576, 'steps': 3877, 'loss/train': 2.9484941959381104} 08/30/2021 13:54:05 - INFO - __main__ - Step 3879: {'lr': 0.0004998013813667315, 'samples': 744768, 'steps': 3878, 'loss/train': 1.1047451496124268} 08/30/2021 13:54:06 - INFO - __main__ - Step 3880: {'lr': 0.0004998011698170245, 'samples': 744960, 'steps': 3879, 'loss/train': 2.8314123153686523} 08/30/2021 13:54:07 - INFO - __main__ - Step 3881: {'lr': 0.000499800958154761, 'samples': 745152, 'steps': 3880, 'loss/train': 1.696224331855774} 08/30/2021 13:54:07 - INFO - __main__ - Step 3882: {'lr': 0.000499800746379941, 'samples': 745344, 'steps': 3881, 'loss/train': 2.514443874359131} 08/30/2021 13:54:07 - INFO - __main__ - Step 3883: {'lr': 0.0004998005344925647, 'samples': 745536, 'steps': 3882, 'loss/train': 2.567884683609009} 08/30/2021 13:54:08 - INFO - __main__ - Step 3884: {'lr': 0.0004998003224926321, 'samples': 745728, 'steps': 3883, 'loss/train': 2.229339599609375} 08/30/2021 13:54:08 - INFO - __main__ - Step 3885: {'lr': 0.0004998001103801433, 'samples': 745920, 'steps': 3884, 'loss/train': 2.397631883621216} 08/30/2021 13:54:10 - INFO - __main__ - Step 3886: {'lr': 0.0004997998981550985, 'samples': 746112, 'steps': 3885, 'loss/train': 2.341691255569458} 08/30/2021 13:54:11 - INFO - __main__ - Step 3887: {'lr': 0.0004997996858174976, 'samples': 746304, 'steps': 3886, 'loss/train': 2.5074775218963623} 08/30/2021 13:54:11 - INFO - __main__ - Step 3888: {'lr': 0.0004997994733673409, 'samples': 746496, 'steps': 3887, 'loss/train': 2.737993001937866} 08/30/2021 13:54:12 - INFO - __main__ - Step 3889: {'lr': 0.0004997992608046283, 'samples': 746688, 'steps': 3888, 'loss/train': 2.759039878845215} 08/30/2021 13:54:12 - INFO - __main__ - Step 3890: {'lr': 0.0004997990481293602, 'samples': 746880, 'steps': 3889, 'loss/train': 2.3761377334594727} 08/30/2021 13:54:13 - INFO - __main__ - Step 3891: {'lr': 0.0004997988353415364, 'samples': 747072, 'steps': 3890, 'loss/train': 2.5499308109283447} 08/30/2021 13:54:14 - INFO - __main__ - Step 3892: {'lr': 0.0004997986224411571, 'samples': 747264, 'steps': 3891, 'loss/train': 2.0588948726654053} 08/30/2021 13:54:14 - INFO - __main__ - Step 3893: {'lr': 0.0004997984094282224, 'samples': 747456, 'steps': 3892, 'loss/train': 2.512882709503174} 08/30/2021 13:54:15 - INFO - __main__ - Step 3894: {'lr': 0.0004997981963027324, 'samples': 747648, 'steps': 3893, 'loss/train': 2.513519525527954} 08/30/2021 13:54:15 - INFO - __main__ - Step 3895: {'lr': 0.0004997979830646871, 'samples': 747840, 'steps': 3894, 'loss/train': 5.267651081085205} 08/30/2021 13:54:17 - INFO - __main__ - Step 3896: {'lr': 0.0004997977697140868, 'samples': 748032, 'steps': 3895, 'loss/train': 2.0256643295288086} 08/30/2021 13:54:17 - INFO - __main__ - Step 3897: {'lr': 0.0004997975562509315, 'samples': 748224, 'steps': 3896, 'loss/train': 1.8952407836914062} 08/30/2021 13:54:18 - INFO - __main__ - Step 3898: {'lr': 0.0004997973426752212, 'samples': 748416, 'steps': 3897, 'loss/train': 3.1216516494750977} 08/30/2021 13:54:18 - INFO - __main__ - Step 3899: {'lr': 0.0004997971289869561, 'samples': 748608, 'steps': 3898, 'loss/train': 2.1845452785491943} 08/30/2021 13:54:18 - INFO - __main__ - Step 3900: {'lr': 0.0004997969151861362, 'samples': 748800, 'steps': 3899, 'loss/train': 4.411011695861816} 08/30/2021 13:54:20 - INFO - __main__ - Step 3901: {'lr': 0.0004997967012727618, 'samples': 748992, 'steps': 3900, 'loss/train': 2.7186288833618164} 08/30/2021 13:54:20 - INFO - __main__ - Step 3902: {'lr': 0.0004997964872468327, 'samples': 749184, 'steps': 3901, 'loss/train': 2.432096242904663} 08/30/2021 13:54:20 - INFO - __main__ - Step 3903: {'lr': 0.0004997962731083492, 'samples': 749376, 'steps': 3902, 'loss/train': 2.4708166122436523} 08/30/2021 13:54:21 - INFO - __main__ - Step 3904: {'lr': 0.0004997960588573115, 'samples': 749568, 'steps': 3903, 'loss/train': 0.9756361246109009} 08/30/2021 13:54:21 - INFO - __main__ - Step 3905: {'lr': 0.0004997958444937193, 'samples': 749760, 'steps': 3904, 'loss/train': 2.6296472549438477} 08/30/2021 13:54:23 - INFO - __main__ - Step 3906: {'lr': 0.0004997956300175732, 'samples': 749952, 'steps': 3905, 'loss/train': 2.711909055709839} 08/30/2021 13:54:23 - INFO - __main__ - Step 3907: {'lr': 0.000499795415428873, 'samples': 750144, 'steps': 3906, 'loss/train': 2.2133710384368896} 08/30/2021 13:54:24 - INFO - __main__ - Step 3908: {'lr': 0.0004997952007276187, 'samples': 750336, 'steps': 3907, 'loss/train': 2.634544610977173} 08/30/2021 13:54:24 - INFO - __main__ - Step 3909: {'lr': 0.0004997949859138106, 'samples': 750528, 'steps': 3908, 'loss/train': 2.506596088409424} 08/30/2021 13:54:24 - INFO - __main__ - Step 3910: {'lr': 0.0004997947709874487, 'samples': 750720, 'steps': 3909, 'loss/train': 2.404820203781128} 08/30/2021 13:54:26 - INFO - __main__ - Step 3911: {'lr': 0.0004997945559485333, 'samples': 750912, 'steps': 3910, 'loss/train': 1.8868598937988281} 08/30/2021 13:54:27 - INFO - __main__ - Step 3912: {'lr': 0.0004997943407970642, 'samples': 751104, 'steps': 3911, 'loss/train': 2.0609493255615234} 08/30/2021 13:54:27 - INFO - __main__ - Step 3913: {'lr': 0.0004997941255330416, 'samples': 751296, 'steps': 3912, 'loss/train': 2.681518316268921} 08/30/2021 13:54:27 - INFO - __main__ - Step 3914: {'lr': 0.0004997939101564656, 'samples': 751488, 'steps': 3913, 'loss/train': 0.8284855484962463} 08/30/2021 13:54:28 - INFO - __main__ - Step 3915: {'lr': 0.0004997936946673365, 'samples': 751680, 'steps': 3914, 'loss/train': 2.8293895721435547} 08/30/2021 13:54:28 - INFO - __main__ - Step 3916: {'lr': 0.000499793479065654, 'samples': 751872, 'steps': 3915, 'loss/train': 2.407503128051758} 08/30/2021 13:54:29 - INFO - __main__ - Step 3917: {'lr': 0.0004997932633514185, 'samples': 752064, 'steps': 3916, 'loss/train': 2.8127501010894775} 08/30/2021 13:54:30 - INFO - __main__ - Step 3918: {'lr': 0.00049979304752463, 'samples': 752256, 'steps': 3917, 'loss/train': 2.591407060623169} 08/30/2021 13:54:30 - INFO - __main__ - Step 3919: {'lr': 0.0004997928315852887, 'samples': 752448, 'steps': 3918, 'loss/train': 2.1050326824188232} 08/30/2021 13:54:31 - INFO - __main__ - Step 3920: {'lr': 0.0004997926155333944, 'samples': 752640, 'steps': 3919, 'loss/train': 2.3848304748535156} 08/30/2021 13:54:31 - INFO - __main__ - Step 3921: {'lr': 0.0004997923993689476, 'samples': 752832, 'steps': 3920, 'loss/train': 2.403304100036621} 08/30/2021 13:54:32 - INFO - __main__ - Step 3922: {'lr': 0.0004997921830919481, 'samples': 753024, 'steps': 3921, 'loss/train': 1.0415692329406738} 08/30/2021 13:54:33 - INFO - __main__ - Step 3923: {'lr': 0.0004997919667023962, 'samples': 753216, 'steps': 3922, 'loss/train': 1.9141919612884521} 08/30/2021 13:54:33 - INFO - __main__ - Step 3924: {'lr': 0.0004997917502002917, 'samples': 753408, 'steps': 3923, 'loss/train': 3.112239122390747} 08/30/2021 13:54:34 - INFO - __main__ - Step 3925: {'lr': 0.000499791533585635, 'samples': 753600, 'steps': 3924, 'loss/train': 2.3157529830932617} 08/30/2021 13:54:34 - INFO - __main__ - Step 3926: {'lr': 0.0004997913168584262, 'samples': 753792, 'steps': 3925, 'loss/train': 2.479858636856079} 08/30/2021 13:54:35 - INFO - __main__ - Step 3927: {'lr': 0.0004997911000186651, 'samples': 753984, 'steps': 3926, 'loss/train': 2.8407881259918213} 08/30/2021 13:54:36 - INFO - __main__ - Step 3928: {'lr': 0.0004997908830663521, 'samples': 754176, 'steps': 3927, 'loss/train': 2.1204097270965576} 08/30/2021 13:54:36 - INFO - __main__ - Step 3929: {'lr': 0.0004997906660014871, 'samples': 754368, 'steps': 3928, 'loss/train': 3.7338621616363525} 08/30/2021 13:54:37 - INFO - __main__ - Step 3930: {'lr': 0.0004997904488240704, 'samples': 754560, 'steps': 3929, 'loss/train': 2.3179407119750977} 08/30/2021 13:54:37 - INFO - __main__ - Step 3931: {'lr': 0.0004997902315341019, 'samples': 754752, 'steps': 3930, 'loss/train': 2.3511340618133545} 08/30/2021 13:54:37 - INFO - __main__ - Step 3932: {'lr': 0.0004997900141315817, 'samples': 754944, 'steps': 3931, 'loss/train': 2.584240674972534} 08/30/2021 13:54:39 - INFO - __main__ - Step 3933: {'lr': 0.0004997897966165101, 'samples': 755136, 'steps': 3932, 'loss/train': 2.6032466888427734} 08/30/2021 13:54:39 - INFO - __main__ - Step 3934: {'lr': 0.000499789578988887, 'samples': 755328, 'steps': 3933, 'loss/train': 2.606760263442993} 08/30/2021 13:54:40 - INFO - __main__ - Step 3935: {'lr': 0.0004997893612487126, 'samples': 755520, 'steps': 3934, 'loss/train': 2.5362014770507812} 08/30/2021 13:54:40 - INFO - __main__ - Step 3936: {'lr': 0.000499789143395987, 'samples': 755712, 'steps': 3935, 'loss/train': 2.227644920349121} 08/30/2021 13:54:40 - INFO - __main__ - Step 3937: {'lr': 0.0004997889254307103, 'samples': 755904, 'steps': 3936, 'loss/train': 1.789372444152832} 08/30/2021 13:54:42 - INFO - __main__ - Step 3938: {'lr': 0.0004997887073528825, 'samples': 756096, 'steps': 3937, 'loss/train': 2.282470464706421} 08/30/2021 13:54:42 - INFO - __main__ - Step 3939: {'lr': 0.0004997884891625037, 'samples': 756288, 'steps': 3938, 'loss/train': 2.672386884689331} 08/30/2021 13:54:43 - INFO - __main__ - Step 3940: {'lr': 0.0004997882708595742, 'samples': 756480, 'steps': 3939, 'loss/train': 2.443068027496338} 08/30/2021 13:54:43 - INFO - __main__ - Step 3941: {'lr': 0.0004997880524440939, 'samples': 756672, 'steps': 3940, 'loss/train': 2.0535221099853516} 08/30/2021 13:54:43 - INFO - __main__ - Step 3942: {'lr': 0.0004997878339160628, 'samples': 756864, 'steps': 3941, 'loss/train': 2.733731269836426} 08/30/2021 13:54:46 - INFO - __main__ - Step 3943: {'lr': 0.0004997876152754814, 'samples': 757056, 'steps': 3942, 'loss/train': 2.707033395767212} 08/30/2021 13:54:46 - INFO - __main__ - Step 3944: {'lr': 0.0004997873965223495, 'samples': 757248, 'steps': 3943, 'loss/train': 2.4181621074676514} 08/30/2021 13:54:46 - INFO - __main__ - Step 3945: {'lr': 0.0004997871776566672, 'samples': 757440, 'steps': 3944, 'loss/train': 0.3946099281311035} 08/30/2021 13:54:47 - INFO - __main__ - Step 3946: {'lr': 0.0004997869586784346, 'samples': 757632, 'steps': 3945, 'loss/train': 2.1933298110961914} 08/30/2021 13:54:47 - INFO - __main__ - Step 3947: {'lr': 0.0004997867395876519, 'samples': 757824, 'steps': 3946, 'loss/train': 2.572780132293701} 08/30/2021 13:54:49 - INFO - __main__ - Step 3948: {'lr': 0.0004997865203843192, 'samples': 758016, 'steps': 3947, 'loss/train': 2.0253100395202637} 08/30/2021 13:54:49 - INFO - __main__ - Step 3949: {'lr': 0.0004997863010684365, 'samples': 758208, 'steps': 3948, 'loss/train': 2.4088943004608154} 08/30/2021 13:54:49 - INFO - __main__ - Step 3950: {'lr': 0.0004997860816400039, 'samples': 758400, 'steps': 3949, 'loss/train': 2.1114790439605713} 08/30/2021 13:54:50 - INFO - __main__ - Step 3951: {'lr': 0.0004997858620990217, 'samples': 758592, 'steps': 3950, 'loss/train': 2.383887767791748} 08/30/2021 13:54:50 - INFO - __main__ - Step 3952: {'lr': 0.0004997856424454897, 'samples': 758784, 'steps': 3951, 'loss/train': 2.504924774169922} 08/30/2021 13:54:50 - INFO - __main__ - Step 3953: {'lr': 0.0004997854226794082, 'samples': 758976, 'steps': 3952, 'loss/train': 2.293032169342041} 08/30/2021 13:54:52 - INFO - __main__ - Step 3954: {'lr': 0.0004997852028007772, 'samples': 759168, 'steps': 3953, 'loss/train': 2.7769062519073486} 08/30/2021 13:54:53 - INFO - __main__ - Step 3955: {'lr': 0.0004997849828095969, 'samples': 759360, 'steps': 3954, 'loss/train': 2.057321786880493} 08/30/2021 13:54:53 - INFO - __main__ - Step 3956: {'lr': 0.0004997847627058673, 'samples': 759552, 'steps': 3955, 'loss/train': 2.4487359523773193} 08/30/2021 13:54:53 - INFO - __main__ - Step 3957: {'lr': 0.0004997845424895886, 'samples': 759744, 'steps': 3956, 'loss/train': 0.5445548892021179} 08/30/2021 13:54:54 - INFO - __main__ - Step 3958: {'lr': 0.0004997843221607607, 'samples': 759936, 'steps': 3957, 'loss/train': 2.319689989089966} 08/30/2021 13:54:55 - INFO - __main__ - Step 3959: {'lr': 0.0004997841017193841, 'samples': 760128, 'steps': 3958, 'loss/train': 2.6205952167510986} 08/30/2021 13:54:56 - INFO - __main__ - Step 3960: {'lr': 0.0004997838811654584, 'samples': 760320, 'steps': 3959, 'loss/train': 2.4733848571777344} 08/30/2021 13:54:56 - INFO - __main__ - Step 3961: {'lr': 0.000499783660498984, 'samples': 760512, 'steps': 3960, 'loss/train': 2.2484936714172363} 08/30/2021 13:54:57 - INFO - __main__ - Step 3962: {'lr': 0.0004997834397199609, 'samples': 760704, 'steps': 3961, 'loss/train': 1.6888166666030884} 08/30/2021 13:54:57 - INFO - __main__ - Step 3963: {'lr': 0.0004997832188283893, 'samples': 760896, 'steps': 3962, 'loss/train': 3.3111376762390137} 08/30/2021 13:54:59 - INFO - __main__ - Step 3964: {'lr': 0.0004997829978242693, 'samples': 761088, 'steps': 3963, 'loss/train': 2.5132648944854736} 08/30/2021 13:54:59 - INFO - __main__ - Step 3965: {'lr': 0.0004997827767076008, 'samples': 761280, 'steps': 3964, 'loss/train': 2.3481621742248535} 08/30/2021 13:54:59 - INFO - __main__ - Step 3966: {'lr': 0.0004997825554783841, 'samples': 761472, 'steps': 3965, 'loss/train': 2.779114007949829} 08/30/2021 13:55:00 - INFO - __main__ - Step 3967: {'lr': 0.0004997823341366192, 'samples': 761664, 'steps': 3966, 'loss/train': 2.357691764831543} 08/30/2021 13:55:00 - INFO - __main__ - Step 3968: {'lr': 0.0004997821126823062, 'samples': 761856, 'steps': 3967, 'loss/train': 2.790999174118042} 08/30/2021 13:55:02 - INFO - __main__ - Step 3969: {'lr': 0.0004997818911154454, 'samples': 762048, 'steps': 3968, 'loss/train': 1.1109250783920288} 08/30/2021 13:55:03 - INFO - __main__ - Step 3970: {'lr': 0.0004997816694360367, 'samples': 762240, 'steps': 3969, 'loss/train': 2.903752088546753} 08/30/2021 13:55:03 - INFO - __main__ - Step 3971: {'lr': 0.00049978144764408, 'samples': 762432, 'steps': 3970, 'loss/train': 0.630244255065918} 08/30/2021 13:55:03 - INFO - __main__ - Step 3972: {'lr': 0.0004997812257395758, 'samples': 762624, 'steps': 3971, 'loss/train': 2.2875099182128906} 08/30/2021 13:55:04 - INFO - __main__ - Step 3973: {'lr': 0.0004997810037225241, 'samples': 762816, 'steps': 3972, 'loss/train': 2.5137999057769775} 08/30/2021 13:55:05 - INFO - __main__ - Step 3974: {'lr': 0.0004997807815929248, 'samples': 763008, 'steps': 3973, 'loss/train': 2.0932538509368896} 08/30/2021 13:55:06 - INFO - __main__ - Step 3975: {'lr': 0.0004997805593507783, 'samples': 763200, 'steps': 3974, 'loss/train': 2.383582353591919} 08/30/2021 13:55:06 - INFO - __main__ - Step 3976: {'lr': 0.0004997803369960844, 'samples': 763392, 'steps': 3975, 'loss/train': 4.0104146003723145} 08/30/2021 13:55:06 - INFO - __main__ - Step 3977: {'lr': 0.0004997801145288433, 'samples': 763584, 'steps': 3976, 'loss/train': 2.166151762008667} 08/30/2021 13:55:07 - INFO - __main__ - Step 3978: {'lr': 0.0004997798919490553, 'samples': 763776, 'steps': 3977, 'loss/train': 2.4855029582977295} 08/30/2021 13:55:07 - INFO - __main__ - Step 3979: {'lr': 0.0004997796692567202, 'samples': 763968, 'steps': 3978, 'loss/train': 2.364853858947754} 08/30/2021 13:55:09 - INFO - __main__ - Step 3980: {'lr': 0.0004997794464518383, 'samples': 764160, 'steps': 3979, 'loss/train': 2.0544681549072266} 08/30/2021 13:55:09 - INFO - __main__ - Step 3981: {'lr': 0.0004997792235344096, 'samples': 764352, 'steps': 3980, 'loss/train': 2.1070480346679688} 08/30/2021 13:55:09 - INFO - __main__ - Step 3982: {'lr': 0.0004997790005044343, 'samples': 764544, 'steps': 3981, 'loss/train': 1.9082952737808228} 08/30/2021 13:55:10 - INFO - __main__ - Step 3983: {'lr': 0.0004997787773619123, 'samples': 764736, 'steps': 3982, 'loss/train': 2.3124704360961914} 08/30/2021 13:55:10 - INFO - __main__ - Step 3984: {'lr': 0.0004997785541068439, 'samples': 764928, 'steps': 3983, 'loss/train': 2.160449266433716} 08/30/2021 13:55:12 - INFO - __main__ - Step 3985: {'lr': 0.0004997783307392292, 'samples': 765120, 'steps': 3984, 'loss/train': 1.9370083808898926} 08/30/2021 13:55:12 - INFO - __main__ - Step 3986: {'lr': 0.0004997781072590683, 'samples': 765312, 'steps': 3985, 'loss/train': 2.1351189613342285} 08/30/2021 13:55:12 - INFO - __main__ - Step 3987: {'lr': 0.000499777883666361, 'samples': 765504, 'steps': 3986, 'loss/train': 3.3185460567474365} 08/30/2021 13:55:13 - INFO - __main__ - Step 3988: {'lr': 0.0004997776599611078, 'samples': 765696, 'steps': 3987, 'loss/train': 2.0844638347625732} 08/30/2021 13:55:13 - INFO - __main__ - Step 3989: {'lr': 0.0004997774361433086, 'samples': 765888, 'steps': 3988, 'loss/train': 2.7253451347351074} 08/30/2021 13:55:15 - INFO - __main__ - Step 3990: {'lr': 0.0004997772122129635, 'samples': 766080, 'steps': 3989, 'loss/train': 1.918208360671997} 08/30/2021 13:55:15 - INFO - __main__ - Step 3991: {'lr': 0.0004997769881700727, 'samples': 766272, 'steps': 3990, 'loss/train': 2.1654398441314697} 08/30/2021 13:55:16 - INFO - __main__ - Step 3992: {'lr': 0.0004997767640146363, 'samples': 766464, 'steps': 3991, 'loss/train': 2.137949228286743} 08/30/2021 13:55:16 - INFO - __main__ - Step 3993: {'lr': 0.0004997765397466543, 'samples': 766656, 'steps': 3992, 'loss/train': 2.8130013942718506} 08/30/2021 13:55:16 - INFO - __main__ - Step 3994: {'lr': 0.0004997763153661269, 'samples': 766848, 'steps': 3993, 'loss/train': 2.2077252864837646} 08/30/2021 13:55:17 - INFO - __main__ - Step 3995: {'lr': 0.000499776090873054, 'samples': 767040, 'steps': 3994, 'loss/train': 1.7503622770309448} 08/30/2021 13:55:19 - INFO - __main__ - Step 3996: {'lr': 0.000499775866267436, 'samples': 767232, 'steps': 3995, 'loss/train': 2.386577844619751} 08/30/2021 13:55:19 - INFO - __main__ - Step 3997: {'lr': 0.0004997756415492727, 'samples': 767424, 'steps': 3996, 'loss/train': 2.0418219566345215} 08/30/2021 13:55:20 - INFO - __main__ - Step 3998: {'lr': 0.0004997754167185644, 'samples': 767616, 'steps': 3997, 'loss/train': 2.39665150642395} 08/30/2021 13:55:20 - INFO - __main__ - Step 3999: {'lr': 0.0004997751917753113, 'samples': 767808, 'steps': 3998, 'loss/train': 2.5384645462036133} 08/30/2021 13:55:20 - INFO - __main__ - Step 4000: {'lr': 0.0004997749667195132, 'samples': 768000, 'steps': 3999, 'loss/train': 2.4927403926849365} 08/30/2021 13:55:22 - INFO - __main__ - Step 4001: {'lr': 0.0004997747415511704, 'samples': 768192, 'steps': 4000, 'loss/train': 2.607116460800171} 08/30/2021 13:55:22 - INFO - __main__ - Step 4002: {'lr': 0.000499774516270283, 'samples': 768384, 'steps': 4001, 'loss/train': 2.0028114318847656} 08/30/2021 13:55:23 - INFO - __main__ - Step 4003: {'lr': 0.0004997742908768508, 'samples': 768576, 'steps': 4002, 'loss/train': 1.9878151416778564} 08/30/2021 13:55:23 - INFO - __main__ - Step 4004: {'lr': 0.0004997740653708744, 'samples': 768768, 'steps': 4003, 'loss/train': 2.348004102706909} 08/30/2021 13:55:23 - INFO - __main__ - Step 4005: {'lr': 0.0004997738397523537, 'samples': 768960, 'steps': 4004, 'loss/train': 1.797458291053772} 08/30/2021 13:55:25 - INFO - __main__ - Step 4006: {'lr': 0.0004997736140212887, 'samples': 769152, 'steps': 4005, 'loss/train': 2.4697611331939697} 08/30/2021 13:55:25 - INFO - __main__ - Step 4007: {'lr': 0.0004997733881776796, 'samples': 769344, 'steps': 4006, 'loss/train': 3.012784004211426} 08/30/2021 13:55:26 - INFO - __main__ - Step 4008: {'lr': 0.0004997731622215264, 'samples': 769536, 'steps': 4007, 'loss/train': 2.257763147354126} 08/30/2021 13:55:26 - INFO - __main__ - Step 4009: {'lr': 0.0004997729361528292, 'samples': 769728, 'steps': 4008, 'loss/train': 3.1401171684265137} 08/30/2021 13:55:26 - INFO - __main__ - Step 4010: {'lr': 0.0004997727099715882, 'samples': 769920, 'steps': 4009, 'loss/train': 2.2928898334503174} 08/30/2021 13:55:28 - INFO - __main__ - Step 4011: {'lr': 0.0004997724836778036, 'samples': 770112, 'steps': 4010, 'loss/train': 1.6429706811904907} 08/30/2021 13:55:28 - INFO - __main__ - Step 4012: {'lr': 0.0004997722572714753, 'samples': 770304, 'steps': 4011, 'loss/train': 2.2672104835510254} 08/30/2021 13:55:29 - INFO - __main__ - Step 4013: {'lr': 0.0004997720307526034, 'samples': 770496, 'steps': 4012, 'loss/train': 1.7388495206832886} 08/30/2021 13:55:29 - INFO - __main__ - Step 4014: {'lr': 0.0004997718041211881, 'samples': 770688, 'steps': 4013, 'loss/train': 2.3739945888519287} 08/30/2021 13:55:29 - INFO - __main__ - Step 4015: {'lr': 0.0004997715773772296, 'samples': 770880, 'steps': 4014, 'loss/train': 2.8052685260772705} 08/30/2021 13:55:31 - INFO - __main__ - Step 4016: {'lr': 0.0004997713505207278, 'samples': 771072, 'steps': 4015, 'loss/train': 1.839080810546875} 08/30/2021 13:55:32 - INFO - __main__ - Step 4017: {'lr': 0.0004997711235516829, 'samples': 771264, 'steps': 4016, 'loss/train': 1.589301347732544} 08/30/2021 13:55:32 - INFO - __main__ - Step 4018: {'lr': 0.000499770896470095, 'samples': 771456, 'steps': 4017, 'loss/train': 1.8437907695770264} 08/30/2021 13:55:32 - INFO - __main__ - Step 4019: {'lr': 0.0004997706692759642, 'samples': 771648, 'steps': 4018, 'loss/train': 2.4364233016967773} 08/30/2021 13:55:33 - INFO - __main__ - Step 4020: {'lr': 0.0004997704419692905, 'samples': 771840, 'steps': 4019, 'loss/train': 2.4826018810272217} 08/30/2021 13:55:35 - INFO - __main__ - Step 4021: {'lr': 0.0004997702145500741, 'samples': 772032, 'steps': 4020, 'loss/train': 1.9058207273483276} 08/30/2021 13:55:35 - INFO - __main__ - Step 4022: {'lr': 0.0004997699870183151, 'samples': 772224, 'steps': 4021, 'loss/train': 2.5359270572662354} 08/30/2021 13:55:35 - INFO - __main__ - Step 4023: {'lr': 0.0004997697593740137, 'samples': 772416, 'steps': 4022, 'loss/train': 2.793123722076416} 08/30/2021 13:55:36 - INFO - __main__ - Step 4024: {'lr': 0.0004997695316171698, 'samples': 772608, 'steps': 4023, 'loss/train': 2.240602731704712} 08/30/2021 13:55:36 - INFO - __main__ - Step 4025: {'lr': 0.0004997693037477837, 'samples': 772800, 'steps': 4024, 'loss/train': 2.421320676803589} 08/30/2021 13:55:36 - INFO - __main__ - Step 4026: {'lr': 0.0004997690757658552, 'samples': 772992, 'steps': 4025, 'loss/train': 4.291104793548584} 08/30/2021 13:55:38 - INFO - __main__ - Step 4027: {'lr': 0.0004997688476713848, 'samples': 773184, 'steps': 4026, 'loss/train': 2.386380434036255} 08/30/2021 13:55:38 - INFO - __main__ - Step 4028: {'lr': 0.0004997686194643724, 'samples': 773376, 'steps': 4027, 'loss/train': 2.6655831336975098} 08/30/2021 13:55:39 - INFO - __main__ - Step 4029: {'lr': 0.0004997683911448181, 'samples': 773568, 'steps': 4028, 'loss/train': 2.5628130435943604} 08/30/2021 13:55:39 - INFO - __main__ - Step 4030: {'lr': 0.000499768162712722, 'samples': 773760, 'steps': 4029, 'loss/train': 2.468876600265503} 08/30/2021 13:55:39 - INFO - __main__ - Step 4031: {'lr': 0.0004997679341680843, 'samples': 773952, 'steps': 4030, 'loss/train': 2.633169651031494} 08/30/2021 13:55:41 - INFO - __main__ - Step 4032: {'lr': 0.0004997677055109049, 'samples': 774144, 'steps': 4031, 'loss/train': 2.7020351886749268} 08/30/2021 13:55:41 - INFO - __main__ - Step 4033: {'lr': 0.0004997674767411841, 'samples': 774336, 'steps': 4032, 'loss/train': 2.3281779289245605} 08/30/2021 13:55:42 - INFO - __main__ - Step 4034: {'lr': 0.0004997672478589219, 'samples': 774528, 'steps': 4033, 'loss/train': 2.290341377258301} 08/30/2021 13:55:42 - INFO - __main__ - Step 4035: {'lr': 0.0004997670188641183, 'samples': 774720, 'steps': 4034, 'loss/train': 2.7043285369873047} 08/30/2021 13:55:42 - INFO - __main__ - Step 4036: {'lr': 0.0004997667897567738, 'samples': 774912, 'steps': 4035, 'loss/train': 1.0439705848693848} 08/30/2021 13:55:44 - INFO - __main__ - Step 4037: {'lr': 0.0004997665605368881, 'samples': 775104, 'steps': 4036, 'loss/train': 2.1322202682495117} 08/30/2021 13:55:44 - INFO - __main__ - Step 4038: {'lr': 0.0004997663312044614, 'samples': 775296, 'steps': 4037, 'loss/train': 2.4699625968933105} 08/30/2021 13:55:45 - INFO - __main__ - Step 4039: {'lr': 0.0004997661017594939, 'samples': 775488, 'steps': 4038, 'loss/train': 3.9698586463928223} 08/30/2021 13:55:45 - INFO - __main__ - Step 4040: {'lr': 0.0004997658722019857, 'samples': 775680, 'steps': 4039, 'loss/train': 2.4469292163848877} 08/30/2021 13:55:46 - INFO - __main__ - Step 4041: {'lr': 0.0004997656425319367, 'samples': 775872, 'steps': 4040, 'loss/train': 2.307356834411621} 08/30/2021 13:55:46 - INFO - __main__ - Step 4042: {'lr': 0.0004997654127493473, 'samples': 776064, 'steps': 4041, 'loss/train': 2.4846560955047607} 08/30/2021 13:55:47 - INFO - __main__ - Step 4043: {'lr': 0.0004997651828542173, 'samples': 776256, 'steps': 4042, 'loss/train': 0.5503510236740112} 08/30/2021 13:55:48 - INFO - __main__ - Step 4044: {'lr': 0.0004997649528465471, 'samples': 776448, 'steps': 4043, 'loss/train': 2.0111496448516846} 08/30/2021 13:55:48 - INFO - __main__ - Step 4045: {'lr': 0.0004997647227263367, 'samples': 776640, 'steps': 4044, 'loss/train': 2.676067352294922} 08/30/2021 13:55:48 - INFO - __main__ - Step 4046: {'lr': 0.000499764492493586, 'samples': 776832, 'steps': 4045, 'loss/train': 2.448500633239746} 08/30/2021 13:55:49 - INFO - __main__ - Step 4047: {'lr': 0.0004997642621482955, 'samples': 777024, 'steps': 4046, 'loss/train': 2.5388779640197754} 08/30/2021 13:55:50 - INFO - __main__ - Step 4048: {'lr': 0.0004997640316904649, 'samples': 777216, 'steps': 4047, 'loss/train': 3.0572433471679688} 08/30/2021 13:55:51 - INFO - __main__ - Step 4049: {'lr': 0.0004997638011200946, 'samples': 777408, 'steps': 4048, 'loss/train': 2.5447680950164795} 08/30/2021 13:55:51 - INFO - __main__ - Step 4050: {'lr': 0.0004997635704371844, 'samples': 777600, 'steps': 4049, 'loss/train': 2.6373209953308105} 08/30/2021 13:55:51 - INFO - __main__ - Step 4051: {'lr': 0.0004997633396417348, 'samples': 777792, 'steps': 4050, 'loss/train': 2.7491040229797363} 08/30/2021 13:55:52 - INFO - __main__ - Step 4052: {'lr': 0.0004997631087337456, 'samples': 777984, 'steps': 4051, 'loss/train': 2.096184015274048} 08/30/2021 13:55:54 - INFO - __main__ - Step 4053: {'lr': 0.000499762877713217, 'samples': 778176, 'steps': 4052, 'loss/train': 2.2926199436187744} 08/30/2021 13:55:54 - INFO - __main__ - Step 4054: {'lr': 0.0004997626465801492, 'samples': 778368, 'steps': 4053, 'loss/train': 2.4043421745300293} 08/30/2021 13:55:55 - INFO - __main__ - Step 4055: {'lr': 0.000499762415334542, 'samples': 778560, 'steps': 4054, 'loss/train': 2.2378180027008057} 08/30/2021 13:55:55 - INFO - __main__ - Step 4056: {'lr': 0.0004997621839763958, 'samples': 778752, 'steps': 4055, 'loss/train': 2.306154727935791} 08/30/2021 13:55:55 - INFO - __main__ - Step 4057: {'lr': 0.0004997619525057106, 'samples': 778944, 'steps': 4056, 'loss/train': 2.423851728439331} 08/30/2021 13:55:57 - INFO - __main__ - Step 4058: {'lr': 0.0004997617209224866, 'samples': 779136, 'steps': 4057, 'loss/train': 2.433486223220825} 08/30/2021 13:55:58 - INFO - __main__ - Step 4059: {'lr': 0.0004997614892267238, 'samples': 779328, 'steps': 4058, 'loss/train': 2.9628419876098633} 08/30/2021 13:55:58 - INFO - __main__ - Step 4060: {'lr': 0.0004997612574184223, 'samples': 779520, 'steps': 4059, 'loss/train': 1.662583351135254} 08/30/2021 13:55:58 - INFO - __main__ - Step 4061: {'lr': 0.0004997610254975823, 'samples': 779712, 'steps': 4060, 'loss/train': 1.755662441253662} 08/30/2021 13:55:59 - INFO - __main__ - Step 4062: {'lr': 0.0004997607934642038, 'samples': 779904, 'steps': 4061, 'loss/train': 2.7849385738372803} 08/30/2021 13:56:00 - INFO - __main__ - Step 4063: {'lr': 0.0004997605613182868, 'samples': 780096, 'steps': 4062, 'loss/train': 2.0621323585510254} 08/30/2021 13:56:01 - INFO - __main__ - Step 4064: {'lr': 0.0004997603290598317, 'samples': 780288, 'steps': 4063, 'loss/train': 3.1318585872650146} 08/30/2021 13:56:01 - INFO - __main__ - Step 4065: {'lr': 0.0004997600966888384, 'samples': 780480, 'steps': 4064, 'loss/train': 2.4551327228546143} 08/30/2021 13:56:01 - INFO - __main__ - Step 4066: {'lr': 0.000499759864205307, 'samples': 780672, 'steps': 4065, 'loss/train': 2.489694595336914} 08/30/2021 13:56:02 - INFO - __main__ - Step 4067: {'lr': 0.0004997596316092378, 'samples': 780864, 'steps': 4066, 'loss/train': 2.8750481605529785} 08/30/2021 13:56:03 - INFO - __main__ - Step 4068: {'lr': 0.0004997593989006306, 'samples': 781056, 'steps': 4067, 'loss/train': 2.234858274459839} 08/30/2021 13:56:04 - INFO - __main__ - Step 4069: {'lr': 0.0004997591660794858, 'samples': 781248, 'steps': 4068, 'loss/train': 2.5201728343963623} 08/30/2021 13:56:04 - INFO - __main__ - Step 4070: {'lr': 0.0004997589331458034, 'samples': 781440, 'steps': 4069, 'loss/train': 1.053739309310913} 08/30/2021 13:56:05 - INFO - __main__ - Step 4071: {'lr': 0.0004997587000995833, 'samples': 781632, 'steps': 4070, 'loss/train': 3.0745999813079834} 08/30/2021 13:56:05 - INFO - __main__ - Step 4072: {'lr': 0.000499758466940826, 'samples': 781824, 'steps': 4071, 'loss/train': 2.7624387741088867} 08/30/2021 13:56:05 - INFO - __main__ - Step 4073: {'lr': 0.0004997582336695312, 'samples': 782016, 'steps': 4072, 'loss/train': 2.297905206680298} 08/30/2021 13:56:07 - INFO - __main__ - Step 4074: {'lr': 0.0004997580002856993, 'samples': 782208, 'steps': 4073, 'loss/train': 0.4014703333377838} 08/30/2021 13:56:07 - INFO - __main__ - Step 4075: {'lr': 0.0004997577667893303, 'samples': 782400, 'steps': 4074, 'loss/train': 2.3574111461639404} 08/30/2021 13:56:08 - INFO - __main__ - Step 4076: {'lr': 0.0004997575331804243, 'samples': 782592, 'steps': 4075, 'loss/train': 2.161566734313965} 08/30/2021 13:56:08 - INFO - __main__ - Step 4077: {'lr': 0.0004997572994589812, 'samples': 782784, 'steps': 4076, 'loss/train': 3.3062691688537598} 08/30/2021 13:56:08 - INFO - __main__ - Step 4078: {'lr': 0.0004997570656250016, 'samples': 782976, 'steps': 4077, 'loss/train': 2.472597599029541} 08/30/2021 13:56:10 - INFO - __main__ - Step 4079: {'lr': 0.0004997568316784852, 'samples': 783168, 'steps': 4078, 'loss/train': 2.9864468574523926} 08/30/2021 13:56:10 - INFO - __main__ - Step 4080: {'lr': 0.0004997565976194323, 'samples': 783360, 'steps': 4079, 'loss/train': 2.3666961193084717} 08/30/2021 13:56:11 - INFO - __main__ - Step 4081: {'lr': 0.0004997563634478429, 'samples': 783552, 'steps': 4080, 'loss/train': 2.6453051567077637} 08/30/2021 13:56:11 - INFO - __main__ - Step 4082: {'lr': 0.000499756129163717, 'samples': 783744, 'steps': 4081, 'loss/train': 2.544973611831665} 08/30/2021 13:56:11 - INFO - __main__ - Step 4083: {'lr': 0.000499755894767055, 'samples': 783936, 'steps': 4082, 'loss/train': 2.2215025424957275} 08/30/2021 13:56:13 - INFO - __main__ - Step 4084: {'lr': 0.0004997556602578568, 'samples': 784128, 'steps': 4083, 'loss/train': 2.718143939971924} 08/30/2021 13:56:13 - INFO - __main__ - Step 4085: {'lr': 0.0004997554256361225, 'samples': 784320, 'steps': 4084, 'loss/train': 2.04015851020813} 08/30/2021 13:56:14 - INFO - __main__ - Step 4086: {'lr': 0.0004997551909018524, 'samples': 784512, 'steps': 4085, 'loss/train': 2.7680890560150146} 08/30/2021 13:56:14 - INFO - __main__ - Step 4087: {'lr': 0.0004997549560550464, 'samples': 784704, 'steps': 4086, 'loss/train': 2.689427137374878} 08/30/2021 13:56:14 - INFO - __main__ - Step 4088: {'lr': 0.0004997547210957047, 'samples': 784896, 'steps': 4087, 'loss/train': 3.028334617614746} 08/30/2021 13:56:16 - INFO - __main__ - Step 4089: {'lr': 0.0004997544860238272, 'samples': 785088, 'steps': 4088, 'loss/train': 2.0451505184173584} 08/30/2021 13:56:16 - INFO - __main__ - Step 4090: {'lr': 0.0004997542508394144, 'samples': 785280, 'steps': 4089, 'loss/train': 2.1984105110168457} 08/30/2021 13:56:17 - INFO - __main__ - Step 4091: {'lr': 0.000499754015542466, 'samples': 785472, 'steps': 4090, 'loss/train': 3.425971269607544} 08/30/2021 13:56:17 - INFO - __main__ - Step 4092: {'lr': 0.0004997537801329824, 'samples': 785664, 'steps': 4091, 'loss/train': 2.6176960468292236} 08/30/2021 13:56:17 - INFO - __main__ - Step 4093: {'lr': 0.0004997535446109637, 'samples': 785856, 'steps': 4092, 'loss/train': 2.0059561729431152} 08/30/2021 13:56:19 - INFO - __main__ - Step 4094: {'lr': 0.0004997533089764097, 'samples': 786048, 'steps': 4093, 'loss/train': 2.5740933418273926} 08/30/2021 13:56:20 - INFO - __main__ - Step 4095: {'lr': 0.0004997530732293209, 'samples': 786240, 'steps': 4094, 'loss/train': 2.12330961227417} 08/30/2021 13:56:20 - INFO - __main__ - Step 4096: {'lr': 0.000499752837369697, 'samples': 786432, 'steps': 4095, 'loss/train': 3.3240857124328613} 08/30/2021 13:56:20 - INFO - __main__ - Step 4097: {'lr': 0.0004997526013975385, 'samples': 786624, 'steps': 4096, 'loss/train': 2.6515917778015137} 08/30/2021 13:56:21 - INFO - __main__ - Step 4098: {'lr': 0.0004997523653128453, 'samples': 786816, 'steps': 4097, 'loss/train': 3.079754590988159} 08/30/2021 13:56:21 - INFO - __main__ - Step 4099: {'lr': 0.0004997521291156175, 'samples': 787008, 'steps': 4098, 'loss/train': 2.460397481918335} 08/30/2021 13:56:22 - INFO - __main__ - Step 4100: {'lr': 0.0004997518928058553, 'samples': 787200, 'steps': 4099, 'loss/train': 2.6524083614349365} 08/30/2021 13:56:23 - INFO - __main__ - Step 4101: {'lr': 0.0004997516563835587, 'samples': 787392, 'steps': 4100, 'loss/train': 2.4772443771362305} 08/30/2021 13:56:23 - INFO - __main__ - Step 4102: {'lr': 0.0004997514198487279, 'samples': 787584, 'steps': 4101, 'loss/train': 2.363936185836792} 08/30/2021 13:56:24 - INFO - __main__ - Step 4103: {'lr': 0.0004997511832013629, 'samples': 787776, 'steps': 4102, 'loss/train': 2.742016553878784} 08/30/2021 13:56:24 - INFO - __main__ - Step 4104: {'lr': 0.0004997509464414639, 'samples': 787968, 'steps': 4103, 'loss/train': 2.8800699710845947} 08/30/2021 13:56:26 - INFO - __main__ - Step 4105: {'lr': 0.000499750709569031, 'samples': 788160, 'steps': 4104, 'loss/train': 2.4009082317352295} 08/30/2021 13:56:27 - INFO - __main__ - Step 4106: {'lr': 0.0004997504725840644, 'samples': 788352, 'steps': 4105, 'loss/train': 1.4848320484161377} 08/30/2021 13:56:27 - INFO - __main__ - Step 4107: {'lr': 0.0004997502354865639, 'samples': 788544, 'steps': 4106, 'loss/train': 2.3617055416107178} 08/30/2021 13:56:27 - INFO - __main__ - Step 4108: {'lr': 0.0004997499982765299, 'samples': 788736, 'steps': 4107, 'loss/train': 2.733996629714966} 08/30/2021 13:56:28 - INFO - __main__ - Step 4109: {'lr': 0.0004997497609539623, 'samples': 788928, 'steps': 4108, 'loss/train': 2.7251229286193848} 08/30/2021 13:56:29 - INFO - __main__ - Step 4110: {'lr': 0.0004997495235188614, 'samples': 789120, 'steps': 4109, 'loss/train': 2.193601369857788} 08/30/2021 13:56:30 - INFO - __main__ - Step 4111: {'lr': 0.0004997492859712272, 'samples': 789312, 'steps': 4110, 'loss/train': 2.574625015258789} 08/30/2021 13:56:30 - INFO - __main__ - Step 4112: {'lr': 0.0004997490483110599, 'samples': 789504, 'steps': 4111, 'loss/train': 2.4444687366485596} 08/30/2021 13:56:30 - INFO - __main__ - Step 4113: {'lr': 0.0004997488105383594, 'samples': 789696, 'steps': 4112, 'loss/train': 1.5127551555633545} 08/30/2021 13:56:31 - INFO - __main__ - Step 4114: {'lr': 0.000499748572653126, 'samples': 789888, 'steps': 4113, 'loss/train': 2.4461772441864014} 08/30/2021 13:56:32 - INFO - __main__ - Step 4115: {'lr': 0.0004997483346553597, 'samples': 790080, 'steps': 4114, 'loss/train': 2.314634323120117} 08/30/2021 13:56:33 - INFO - __main__ - Step 4116: {'lr': 0.0004997480965450607, 'samples': 790272, 'steps': 4115, 'loss/train': 2.4725961685180664} 08/30/2021 13:56:33 - INFO - __main__ - Step 4117: {'lr': 0.0004997478583222291, 'samples': 790464, 'steps': 4116, 'loss/train': 2.412627935409546} 08/30/2021 13:56:33 - INFO - __main__ - Step 4118: {'lr': 0.0004997476199868649, 'samples': 790656, 'steps': 4117, 'loss/train': 2.497490882873535} 08/30/2021 13:56:34 - INFO - __main__ - Step 4119: {'lr': 0.0004997473815389683, 'samples': 790848, 'steps': 4118, 'loss/train': 2.241377115249634} 08/30/2021 13:56:35 - INFO - __main__ - Step 4120: {'lr': 0.0004997471429785394, 'samples': 791040, 'steps': 4119, 'loss/train': 2.279694080352783} 08/30/2021 13:56:36 - INFO - __main__ - Step 4121: {'lr': 0.0004997469043055784, 'samples': 791232, 'steps': 4120, 'loss/train': 3.4058709144592285} 08/30/2021 13:56:36 - INFO - __main__ - Step 4122: {'lr': 0.000499746665520085, 'samples': 791424, 'steps': 4121, 'loss/train': 2.493852376937866} 08/30/2021 13:56:36 - INFO - __main__ - Step 4123: {'lr': 0.0004997464266220599, 'samples': 791616, 'steps': 4122, 'loss/train': 1.5343027114868164} 08/30/2021 13:56:37 - INFO - __main__ - Step 4124: {'lr': 0.0004997461876115029, 'samples': 791808, 'steps': 4123, 'loss/train': 1.5703154802322388} 08/30/2021 13:56:38 - INFO - __main__ - Step 4125: {'lr': 0.0004997459484884139, 'samples': 792000, 'steps': 4124, 'loss/train': 2.1772875785827637} 08/30/2021 13:56:39 - INFO - __main__ - Step 4126: {'lr': 0.0004997457092527934, 'samples': 792192, 'steps': 4125, 'loss/train': 2.3461971282958984} 08/30/2021 13:56:39 - INFO - __main__ - Step 4127: {'lr': 0.0004997454699046412, 'samples': 792384, 'steps': 4126, 'loss/train': 2.3878214359283447} 08/30/2021 13:56:39 - INFO - __main__ - Step 4128: {'lr': 0.0004997452304439577, 'samples': 792576, 'steps': 4127, 'loss/train': 1.971865177154541} 08/30/2021 13:56:40 - INFO - __main__ - Step 4129: {'lr': 0.0004997449908707428, 'samples': 792768, 'steps': 4128, 'loss/train': 2.165173053741455} 08/30/2021 13:56:40 - INFO - __main__ - Step 4130: {'lr': 0.0004997447511849966, 'samples': 792960, 'steps': 4129, 'loss/train': 2.409449338912964} 08/30/2021 13:56:41 - INFO - __main__ - Step 4131: {'lr': 0.0004997445113867193, 'samples': 793152, 'steps': 4130, 'loss/train': 1.8672187328338623} 08/30/2021 13:56:42 - INFO - __main__ - Step 4132: {'lr': 0.000499744271475911, 'samples': 793344, 'steps': 4131, 'loss/train': 2.3295915126800537} 08/30/2021 13:56:42 - INFO - __main__ - Step 4133: {'lr': 0.0004997440314525718, 'samples': 793536, 'steps': 4132, 'loss/train': 2.5744876861572266} 08/30/2021 13:56:43 - INFO - __main__ - Step 4134: {'lr': 0.0004997437913167018, 'samples': 793728, 'steps': 4133, 'loss/train': 2.637343645095825} 08/30/2021 13:56:43 - INFO - __main__ - Step 4135: {'lr': 0.0004997435510683011, 'samples': 793920, 'steps': 4134, 'loss/train': 2.3382296562194824} 08/30/2021 13:56:44 - INFO - __main__ - Step 4136: {'lr': 0.0004997433107073697, 'samples': 794112, 'steps': 4135, 'loss/train': 2.1141772270202637} 08/30/2021 13:56:45 - INFO - __main__ - Step 4137: {'lr': 0.000499743070233908, 'samples': 794304, 'steps': 4136, 'loss/train': 2.3558902740478516} 08/30/2021 13:56:45 - INFO - __main__ - Step 4138: {'lr': 0.0004997428296479158, 'samples': 794496, 'steps': 4137, 'loss/train': 2.1789145469665527} 08/30/2021 13:56:46 - INFO - __main__ - Step 4139: {'lr': 0.0004997425889493933, 'samples': 794688, 'steps': 4138, 'loss/train': 2.6657779216766357} 08/30/2021 13:56:46 - INFO - __main__ - Step 4140: {'lr': 0.0004997423481383407, 'samples': 794880, 'steps': 4139, 'loss/train': 2.8600826263427734} 08/30/2021 13:56:48 - INFO - __main__ - Step 4141: {'lr': 0.0004997421072147581, 'samples': 795072, 'steps': 4140, 'loss/train': 2.526305675506592} 08/30/2021 13:56:48 - INFO - __main__ - Step 4142: {'lr': 0.0004997418661786455, 'samples': 795264, 'steps': 4141, 'loss/train': 2.5764617919921875} 08/30/2021 13:56:49 - INFO - __main__ - Step 4143: {'lr': 0.0004997416250300031, 'samples': 795456, 'steps': 4142, 'loss/train': 0.9663740396499634} 08/30/2021 13:56:49 - INFO - __main__ - Step 4144: {'lr': 0.0004997413837688309, 'samples': 795648, 'steps': 4143, 'loss/train': 2.2550570964813232} 08/30/2021 13:56:49 - INFO - __main__ - Step 4145: {'lr': 0.0004997411423951292, 'samples': 795840, 'steps': 4144, 'loss/train': 2.074369192123413} 08/30/2021 13:56:50 - INFO - __main__ - Step 4146: {'lr': 0.0004997409009088979, 'samples': 796032, 'steps': 4145, 'loss/train': 1.7636322975158691} 08/30/2021 13:56:52 - INFO - __main__ - Step 4147: {'lr': 0.0004997406593101373, 'samples': 796224, 'steps': 4146, 'loss/train': 1.8120797872543335} 08/30/2021 13:56:53 - INFO - __main__ - Step 4148: {'lr': 0.0004997404175988474, 'samples': 796416, 'steps': 4147, 'loss/train': 0.9852719306945801} 08/30/2021 13:56:53 - INFO - __main__ - Step 4149: {'lr': 0.0004997401757750282, 'samples': 796608, 'steps': 4148, 'loss/train': 1.135817289352417} 08/30/2021 13:56:53 - INFO - __main__ - Step 4150: {'lr': 0.00049973993383868, 'samples': 796800, 'steps': 4149, 'loss/train': 2.8767166137695312} 08/30/2021 13:56:54 - INFO - __main__ - Step 4151: {'lr': 0.0004997396917898029, 'samples': 796992, 'steps': 4150, 'loss/train': 2.903456449508667} 08/30/2021 13:56:54 - INFO - __main__ - Step 4152: {'lr': 0.0004997394496283969, 'samples': 797184, 'steps': 4151, 'loss/train': 2.2797820568084717} 08/30/2021 13:56:56 - INFO - __main__ - Step 4153: {'lr': 0.0004997392073544622, 'samples': 797376, 'steps': 4152, 'loss/train': 2.748669385910034} 08/30/2021 13:56:56 - INFO - __main__ - Step 4154: {'lr': 0.0004997389649679987, 'samples': 797568, 'steps': 4153, 'loss/train': 3.0491771697998047} 08/30/2021 13:56:56 - INFO - __main__ - Step 4155: {'lr': 0.0004997387224690068, 'samples': 797760, 'steps': 4154, 'loss/train': 2.677032947540283} 08/30/2021 13:56:57 - INFO - __main__ - Step 4156: {'lr': 0.0004997384798574865, 'samples': 797952, 'steps': 4155, 'loss/train': 2.6187453269958496} 08/30/2021 13:56:57 - INFO - __main__ - Step 4157: {'lr': 0.0004997382371334379, 'samples': 798144, 'steps': 4156, 'loss/train': 2.9816508293151855} 08/30/2021 13:56:59 - INFO - __main__ - Step 4158: {'lr': 0.0004997379942968611, 'samples': 798336, 'steps': 4157, 'loss/train': 2.465806722640991} 08/30/2021 13:57:00 - INFO - __main__ - Step 4159: {'lr': 0.0004997377513477562, 'samples': 798528, 'steps': 4158, 'loss/train': 2.595107316970825} 08/30/2021 13:57:00 - INFO - __main__ - Step 4160: {'lr': 0.0004997375082861234, 'samples': 798720, 'steps': 4159, 'loss/train': 2.850452184677124} 08/30/2021 13:57:00 - INFO - __main__ - Step 4161: {'lr': 0.0004997372651119626, 'samples': 798912, 'steps': 4160, 'loss/train': 1.9784674644470215} 08/30/2021 13:57:01 - INFO - __main__ - Step 4162: {'lr': 0.0004997370218252741, 'samples': 799104, 'steps': 4161, 'loss/train': 3.3903627395629883} 08/30/2021 13:57:03 - INFO - __main__ - Step 4163: {'lr': 0.000499736778426058, 'samples': 799296, 'steps': 4162, 'loss/train': 1.924661636352539} 08/30/2021 13:57:03 - INFO - __main__ - Step 4164: {'lr': 0.0004997365349143142, 'samples': 799488, 'steps': 4163, 'loss/train': 4.557950496673584} 08/30/2021 13:57:03 - INFO - __main__ - Step 4165: {'lr': 0.0004997362912900432, 'samples': 799680, 'steps': 4164, 'loss/train': 2.1999592781066895} 08/30/2021 13:57:04 - INFO - __main__ - Step 4166: {'lr': 0.0004997360475532447, 'samples': 799872, 'steps': 4165, 'loss/train': 1.7625823020935059} 08/30/2021 13:57:04 - INFO - __main__ - Step 4167: {'lr': 0.000499735803703919, 'samples': 800064, 'steps': 4166, 'loss/train': 1.29753839969635} 08/30/2021 13:57:05 - INFO - __main__ - Step 4168: {'lr': 0.0004997355597420663, 'samples': 800256, 'steps': 4167, 'loss/train': 2.5071189403533936} 08/30/2021 13:57:06 - INFO - __main__ - Step 4169: {'lr': 0.0004997353156676866, 'samples': 800448, 'steps': 4168, 'loss/train': 2.628887176513672} 08/30/2021 13:57:07 - INFO - __main__ - Step 4170: {'lr': 0.0004997350714807799, 'samples': 800640, 'steps': 4169, 'loss/train': 2.701754570007324} 08/30/2021 13:57:07 - INFO - __main__ - Step 4171: {'lr': 0.0004997348271813466, 'samples': 800832, 'steps': 4170, 'loss/train': 2.419128179550171} 08/30/2021 13:57:07 - INFO - __main__ - Step 4172: {'lr': 0.0004997345827693865, 'samples': 801024, 'steps': 4171, 'loss/train': 1.9172649383544922} 08/30/2021 13:57:08 - INFO - __main__ - Step 4173: {'lr': 0.0004997343382448999, 'samples': 801216, 'steps': 4172, 'loss/train': 2.6126654148101807} 08/30/2021 13:57:08 - INFO - __main__ - Step 4174: {'lr': 0.0004997340936078869, 'samples': 801408, 'steps': 4173, 'loss/train': 2.3526010513305664} 08/30/2021 13:57:10 - INFO - __main__ - Step 4175: {'lr': 0.0004997338488583475, 'samples': 801600, 'steps': 4174, 'loss/train': 2.316492795944214} 08/30/2021 13:57:10 - INFO - __main__ - Step 4176: {'lr': 0.000499733603996282, 'samples': 801792, 'steps': 4175, 'loss/train': 2.7608721256256104} 08/30/2021 13:57:11 - INFO - __main__ - Step 4177: {'lr': 0.0004997333590216902, 'samples': 801984, 'steps': 4176, 'loss/train': 1.7769652605056763} 08/30/2021 13:57:11 - INFO - __main__ - Step 4178: {'lr': 0.0004997331139345725, 'samples': 802176, 'steps': 4177, 'loss/train': 2.848891258239746} 08/30/2021 13:57:11 - INFO - __main__ - Step 4179: {'lr': 0.000499732868734929, 'samples': 802368, 'steps': 4178, 'loss/train': 5.5596184730529785} 08/30/2021 13:57:13 - INFO - __main__ - Step 4180: {'lr': 0.0004997326234227596, 'samples': 802560, 'steps': 4179, 'loss/train': 2.2745630741119385} 08/30/2021 13:57:13 - INFO - __main__ - Step 4181: {'lr': 0.0004997323779980646, 'samples': 802752, 'steps': 4180, 'loss/train': 2.6148009300231934} 08/30/2021 13:57:14 - INFO - __main__ - Step 4182: {'lr': 0.0004997321324608441, 'samples': 802944, 'steps': 4181, 'loss/train': 2.24898624420166} 08/30/2021 13:57:14 - INFO - __main__ - Step 4183: {'lr': 0.0004997318868110981, 'samples': 803136, 'steps': 4182, 'loss/train': 2.8404312133789062} 08/30/2021 13:57:14 - INFO - __main__ - Step 4184: {'lr': 0.0004997316410488267, 'samples': 803328, 'steps': 4183, 'loss/train': 2.5526809692382812} 08/30/2021 13:57:16 - INFO - __main__ - Step 4185: {'lr': 0.0004997313951740301, 'samples': 803520, 'steps': 4184, 'loss/train': 2.9416213035583496} 08/30/2021 13:57:17 - INFO - __main__ - Step 4186: {'lr': 0.0004997311491867083, 'samples': 803712, 'steps': 4185, 'loss/train': 2.0505666732788086} 08/30/2021 13:57:17 - INFO - __main__ - Step 4187: {'lr': 0.0004997309030868617, 'samples': 803904, 'steps': 4186, 'loss/train': 1.945277214050293} 08/30/2021 13:57:17 - INFO - __main__ - Step 4188: {'lr': 0.0004997306568744901, 'samples': 804096, 'steps': 4187, 'loss/train': 3.2816596031188965} 08/30/2021 13:57:18 - INFO - __main__ - Step 4189: {'lr': 0.0004997304105495938, 'samples': 804288, 'steps': 4188, 'loss/train': 2.8236606121063232} 08/30/2021 13:57:18 - INFO - __main__ - Step 4190: {'lr': 0.0004997301641121727, 'samples': 804480, 'steps': 4189, 'loss/train': 1.0542320013046265} 08/30/2021 13:57:19 - INFO - __main__ - Step 4191: {'lr': 0.0004997299175622271, 'samples': 804672, 'steps': 4190, 'loss/train': 2.4775097370147705} 08/30/2021 13:57:20 - INFO - __main__ - Step 4192: {'lr': 0.000499729670899757, 'samples': 804864, 'steps': 4191, 'loss/train': 2.530005931854248} 08/30/2021 13:57:20 - INFO - __main__ - Step 4193: {'lr': 0.0004997294241247627, 'samples': 805056, 'steps': 4192, 'loss/train': 2.8062233924865723} 08/30/2021 13:57:21 - INFO - __main__ - Step 4194: {'lr': 0.0004997291772372441, 'samples': 805248, 'steps': 4193, 'loss/train': 1.4623937606811523} 08/30/2021 13:57:21 - INFO - __main__ - Step 4195: {'lr': 0.0004997289302372014, 'samples': 805440, 'steps': 4194, 'loss/train': 2.715535879135132} 08/30/2021 13:57:22 - INFO - __main__ - Step 4196: {'lr': 0.0004997286831246347, 'samples': 805632, 'steps': 4195, 'loss/train': 2.6134181022644043} 08/30/2021 13:57:23 - INFO - __main__ - Step 4197: {'lr': 0.0004997284358995441, 'samples': 805824, 'steps': 4196, 'loss/train': 2.440012216567993} 08/30/2021 13:57:23 - INFO - __main__ - Step 4198: {'lr': 0.0004997281885619297, 'samples': 806016, 'steps': 4197, 'loss/train': 2.4690046310424805} 08/30/2021 13:57:24 - INFO - __main__ - Step 4199: {'lr': 0.0004997279411117916, 'samples': 806208, 'steps': 4198, 'loss/train': 2.0587642192840576} 08/30/2021 13:57:24 - INFO - __main__ - Step 4200: {'lr': 0.00049972769354913, 'samples': 806400, 'steps': 4199, 'loss/train': 2.0000696182250977} 08/30/2021 13:57:26 - INFO - __main__ - Step 4201: {'lr': 0.0004997274458739449, 'samples': 806592, 'steps': 4200, 'loss/train': 2.9006898403167725} 08/30/2021 13:57:26 - INFO - __main__ - Step 4202: {'lr': 0.0004997271980862366, 'samples': 806784, 'steps': 4201, 'loss/train': 2.264946699142456} 08/30/2021 13:57:27 - INFO - __main__ - Step 4203: {'lr': 0.000499726950186005, 'samples': 806976, 'steps': 4202, 'loss/train': 2.459864616394043} 08/30/2021 13:57:27 - INFO - __main__ - Step 4204: {'lr': 0.0004997267021732502, 'samples': 807168, 'steps': 4203, 'loss/train': 0.8687018156051636} 08/30/2021 13:57:27 - INFO - __main__ - Step 4205: {'lr': 0.0004997264540479724, 'samples': 807360, 'steps': 4204, 'loss/train': 0.7052633166313171} 08/30/2021 13:57:28 - INFO - __main__ - Step 4206: {'lr': 0.0004997262058101719, 'samples': 807552, 'steps': 4205, 'loss/train': 2.1795976161956787} 08/30/2021 13:57:29 - INFO - __main__ - Step 4207: {'lr': 0.0004997259574598485, 'samples': 807744, 'steps': 4206, 'loss/train': 2.8340301513671875} 08/30/2021 13:57:30 - INFO - __main__ - Step 4208: {'lr': 0.0004997257089970024, 'samples': 807936, 'steps': 4207, 'loss/train': 2.3500144481658936} 08/30/2021 13:57:30 - INFO - __main__ - Step 4209: {'lr': 0.0004997254604216338, 'samples': 808128, 'steps': 4208, 'loss/train': 2.3471860885620117} 08/30/2021 13:57:30 - INFO - __main__ - Step 4210: {'lr': 0.0004997252117337428, 'samples': 808320, 'steps': 4209, 'loss/train': 1.684325933456421} 08/30/2021 13:57:31 - INFO - __main__ - Step 4211: {'lr': 0.0004997249629333294, 'samples': 808512, 'steps': 4210, 'loss/train': 2.3704142570495605} 08/30/2021 13:57:32 - INFO - __main__ - Step 4212: {'lr': 0.0004997247140203939, 'samples': 808704, 'steps': 4211, 'loss/train': 2.325749397277832} 08/30/2021 13:57:33 - INFO - __main__ - Step 4213: {'lr': 0.0004997244649949362, 'samples': 808896, 'steps': 4212, 'loss/train': 2.1269288063049316} 08/30/2021 13:57:33 - INFO - __main__ - Step 4214: {'lr': 0.0004997242158569564, 'samples': 809088, 'steps': 4213, 'loss/train': 2.6444509029388428} 08/30/2021 13:57:33 - INFO - __main__ - Step 4215: {'lr': 0.0004997239666064549, 'samples': 809280, 'steps': 4214, 'loss/train': 3.029888391494751} 08/30/2021 13:57:34 - INFO - __main__ - Step 4216: {'lr': 0.0004997237172434316, 'samples': 809472, 'steps': 4215, 'loss/train': 2.305338144302368} 08/30/2021 13:57:36 - INFO - __main__ - Step 4217: {'lr': 0.0004997234677678867, 'samples': 809664, 'steps': 4216, 'loss/train': 1.9964935779571533} 08/30/2021 13:57:37 - INFO - __main__ - Step 4218: {'lr': 0.0004997232181798201, 'samples': 809856, 'steps': 4217, 'loss/train': 2.813920021057129} 08/30/2021 13:57:37 - INFO - __main__ - Step 4219: {'lr': 0.0004997229684792322, 'samples': 810048, 'steps': 4218, 'loss/train': 0.4271639585494995} 08/30/2021 13:57:37 - INFO - __main__ - Step 4220: {'lr': 0.000499722718666123, 'samples': 810240, 'steps': 4219, 'loss/train': 2.1813101768493652} 08/30/2021 13:57:38 - INFO - __main__ - Step 4221: {'lr': 0.0004997224687404926, 'samples': 810432, 'steps': 4220, 'loss/train': 2.128692865371704} 08/30/2021 13:57:40 - INFO - __main__ - Step 4222: {'lr': 0.0004997222187023409, 'samples': 810624, 'steps': 4221, 'loss/train': 2.451427698135376} 08/30/2021 13:57:40 - INFO - __main__ - Step 4223: {'lr': 0.0004997219685516684, 'samples': 810816, 'steps': 4222, 'loss/train': 2.2508769035339355} 08/30/2021 13:57:41 - INFO - __main__ - Step 4224: {'lr': 0.000499721718288475, 'samples': 811008, 'steps': 4223, 'loss/train': 2.1557271480560303} 08/30/2021 13:57:41 - INFO - __main__ - Step 4225: {'lr': 0.0004997214679127609, 'samples': 811200, 'steps': 4224, 'loss/train': 1.5057705640792847} 08/30/2021 13:57:41 - INFO - __main__ - Step 4226: {'lr': 0.000499721217424526, 'samples': 811392, 'steps': 4225, 'loss/train': 4.9801859855651855} 08/30/2021 13:57:42 - INFO - __main__ - Step 4227: {'lr': 0.0004997209668237707, 'samples': 811584, 'steps': 4226, 'loss/train': 2.1657800674438477} 08/30/2021 13:57:44 - INFO - __main__ - Step 4228: {'lr': 0.0004997207161104951, 'samples': 811776, 'steps': 4227, 'loss/train': 2.620006561279297} 08/30/2021 13:57:44 - INFO - __main__ - Step 4229: {'lr': 0.0004997204652846991, 'samples': 811968, 'steps': 4228, 'loss/train': 2.7723963260650635} 08/30/2021 13:57:45 - INFO - __main__ - Step 4230: {'lr': 0.0004997202143463828, 'samples': 812160, 'steps': 4229, 'loss/train': 2.4335696697235107} 08/30/2021 13:57:45 - INFO - __main__ - Step 4231: {'lr': 0.0004997199632955464, 'samples': 812352, 'steps': 4230, 'loss/train': 2.617645025253296} 08/30/2021 13:57:45 - INFO - __main__ - Step 4232: {'lr': 0.0004997197121321903, 'samples': 812544, 'steps': 4231, 'loss/train': 1.4652386903762817} 08/30/2021 13:57:46 - INFO - __main__ - Step 4233: {'lr': 0.0004997194608563142, 'samples': 812736, 'steps': 4232, 'loss/train': 2.947063684463501} 08/30/2021 13:57:47 - INFO - __main__ - Step 4234: {'lr': 0.0004997192094679183, 'samples': 812928, 'steps': 4233, 'loss/train': 3.2186663150787354} 08/30/2021 13:57:48 - INFO - __main__ - Step 4235: {'lr': 0.0004997189579670028, 'samples': 813120, 'steps': 4234, 'loss/train': 2.9579813480377197} 08/30/2021 13:57:48 - INFO - __main__ - Step 4236: {'lr': 0.0004997187063535679, 'samples': 813312, 'steps': 4235, 'loss/train': 2.842017412185669} 08/30/2021 13:57:49 - INFO - __main__ - Step 4237: {'lr': 0.0004997184546276135, 'samples': 813504, 'steps': 4236, 'loss/train': 2.817560911178589} 08/30/2021 13:57:49 - INFO - __main__ - Step 4238: {'lr': 0.0004997182027891399, 'samples': 813696, 'steps': 4237, 'loss/train': 3.4652514457702637} 08/30/2021 13:57:50 - INFO - __main__ - Step 4239: {'lr': 0.000499717950838147, 'samples': 813888, 'steps': 4238, 'loss/train': 1.995408058166504} 08/30/2021 13:57:51 - INFO - __main__ - Step 4240: {'lr': 0.0004997176987746352, 'samples': 814080, 'steps': 4239, 'loss/train': 2.921905517578125} 08/30/2021 13:57:51 - INFO - __main__ - Step 4241: {'lr': 0.0004997174465986043, 'samples': 814272, 'steps': 4240, 'loss/train': 3.066000461578369} 08/30/2021 13:57:52 - INFO - __main__ - Step 4242: {'lr': 0.0004997171943100547, 'samples': 814464, 'steps': 4241, 'loss/train': 3.705711603164673} 08/30/2021 13:57:52 - INFO - __main__ - Step 4243: {'lr': 0.0004997169419089863, 'samples': 814656, 'steps': 4242, 'loss/train': 1.898451328277588} 08/30/2021 13:57:52 - INFO - __main__ - Step 4244: {'lr': 0.0004997166893953994, 'samples': 814848, 'steps': 4243, 'loss/train': 2.2891695499420166} 08/30/2021 13:57:54 - INFO - __main__ - Step 4245: {'lr': 0.000499716436769294, 'samples': 815040, 'steps': 4244, 'loss/train': 2.541060447692871} 08/30/2021 13:57:54 - INFO - __main__ - Step 4246: {'lr': 0.0004997161840306701, 'samples': 815232, 'steps': 4245, 'loss/train': 2.1411869525909424} 08/30/2021 13:57:55 - INFO - __main__ - Step 4247: {'lr': 0.0004997159311795281, 'samples': 815424, 'steps': 4246, 'loss/train': 2.947779417037964} 08/30/2021 13:57:55 - INFO - __main__ - Step 4248: {'lr': 0.0004997156782158679, 'samples': 815616, 'steps': 4247, 'loss/train': 2.754335880279541} 08/30/2021 13:57:55 - INFO - __main__ - Step 4249: {'lr': 0.0004997154251396896, 'samples': 815808, 'steps': 4248, 'loss/train': 2.0951056480407715} 08/30/2021 13:57:57 - INFO - __main__ - Step 4250: {'lr': 0.0004997151719509935, 'samples': 816000, 'steps': 4249, 'loss/train': 2.4612369537353516} 08/30/2021 13:57:57 - INFO - __main__ - Step 4251: {'lr': 0.0004997149186497795, 'samples': 816192, 'steps': 4250, 'loss/train': 2.6147375106811523} 08/30/2021 13:57:58 - INFO - __main__ - Step 4252: {'lr': 0.0004997146652360478, 'samples': 816384, 'steps': 4251, 'loss/train': 2.062556743621826} 08/30/2021 13:57:58 - INFO - __main__ - Step 4253: {'lr': 0.0004997144117097986, 'samples': 816576, 'steps': 4252, 'loss/train': 2.607947587966919} 08/30/2021 13:57:58 - INFO - __main__ - Step 4254: {'lr': 0.0004997141580710318, 'samples': 816768, 'steps': 4253, 'loss/train': 2.2088544368743896} 08/30/2021 13:58:00 - INFO - __main__ - Step 4255: {'lr': 0.0004997139043197478, 'samples': 816960, 'steps': 4254, 'loss/train': 2.6336066722869873} 08/30/2021 13:58:00 - INFO - __main__ - Step 4256: {'lr': 0.0004997136504559465, 'samples': 817152, 'steps': 4255, 'loss/train': 2.7068982124328613} 08/30/2021 13:58:01 - INFO - __main__ - Step 4257: {'lr': 0.0004997133964796281, 'samples': 817344, 'steps': 4256, 'loss/train': 1.9383596181869507} 08/30/2021 13:58:01 - INFO - __main__ - Step 4258: {'lr': 0.0004997131423907927, 'samples': 817536, 'steps': 4257, 'loss/train': 1.8818825483322144} 08/30/2021 13:58:01 - INFO - __main__ - Step 4259: {'lr': 0.0004997128881894404, 'samples': 817728, 'steps': 4258, 'loss/train': 2.592486619949341} 08/30/2021 13:58:03 - INFO - __main__ - Step 4260: {'lr': 0.0004997126338755714, 'samples': 817920, 'steps': 4259, 'loss/train': 0.5001815557479858} 08/30/2021 13:58:04 - INFO - __main__ - Step 4261: {'lr': 0.0004997123794491856, 'samples': 818112, 'steps': 4260, 'loss/train': 2.1100869178771973} 08/30/2021 13:58:04 - INFO - __main__ - Step 4262: {'lr': 0.0004997121249102834, 'samples': 818304, 'steps': 4261, 'loss/train': 0.4378907084465027} 08/30/2021 13:58:04 - INFO - __main__ - Step 4263: {'lr': 0.0004997118702588647, 'samples': 818496, 'steps': 4262, 'loss/train': 1.0724092721939087} 08/30/2021 13:58:05 - INFO - __main__ - Step 4264: {'lr': 0.0004997116154949297, 'samples': 818688, 'steps': 4263, 'loss/train': 2.519207715988159} 08/30/2021 13:58:05 - INFO - __main__ - Step 4265: {'lr': 0.0004997113606184785, 'samples': 818880, 'steps': 4264, 'loss/train': 2.746309280395508} 08/30/2021 13:58:07 - INFO - __main__ - Step 4266: {'lr': 0.0004997111056295111, 'samples': 819072, 'steps': 4265, 'loss/train': 2.795696496963501} 08/30/2021 13:58:07 - INFO - __main__ - Step 4267: {'lr': 0.0004997108505280279, 'samples': 819264, 'steps': 4266, 'loss/train': 3.4674010276794434} 08/30/2021 13:58:07 - INFO - __main__ - Step 4268: {'lr': 0.0004997105953140288, 'samples': 819456, 'steps': 4267, 'loss/train': 0.369831919670105} 08/30/2021 13:58:08 - INFO - __main__ - Step 4269: {'lr': 0.0004997103399875139, 'samples': 819648, 'steps': 4268, 'loss/train': 2.382072925567627} 08/30/2021 13:58:08 - INFO - __main__ - Step 4270: {'lr': 0.0004997100845484834, 'samples': 819840, 'steps': 4269, 'loss/train': 2.774012804031372} 08/30/2021 13:58:10 - INFO - __main__ - Step 4271: {'lr': 0.0004997098289969374, 'samples': 820032, 'steps': 4270, 'loss/train': 2.4658544063568115} 08/30/2021 13:58:11 - INFO - __main__ - Step 4272: {'lr': 0.0004997095733328761, 'samples': 820224, 'steps': 4271, 'loss/train': 2.229326009750366} 08/30/2021 13:58:11 - INFO - __main__ - Step 4273: {'lr': 0.0004997093175562994, 'samples': 820416, 'steps': 4272, 'loss/train': 3.0871241092681885} 08/30/2021 13:58:12 - INFO - __main__ - Step 4274: {'lr': 0.0004997090616672076, 'samples': 820608, 'steps': 4273, 'loss/train': 2.0945723056793213} 08/30/2021 13:58:12 - INFO - __main__ - Step 4275: {'lr': 0.0004997088056656006, 'samples': 820800, 'steps': 4274, 'loss/train': 2.119072437286377} 08/30/2021 13:58:13 - INFO - __main__ - Step 4276: {'lr': 0.0004997085495514788, 'samples': 820992, 'steps': 4275, 'loss/train': 2.942012310028076} 08/30/2021 13:58:14 - INFO - __main__ - Step 4277: {'lr': 0.0004997082933248421, 'samples': 821184, 'steps': 4276, 'loss/train': 1.1856452226638794} 08/30/2021 13:58:14 - INFO - __main__ - Step 4278: {'lr': 0.0004997080369856907, 'samples': 821376, 'steps': 4277, 'loss/train': 2.270286798477173} 08/30/2021 13:58:15 - INFO - __main__ - Step 4279: {'lr': 0.0004997077805340248, 'samples': 821568, 'steps': 4278, 'loss/train': 2.501870632171631} 08/30/2021 13:58:15 - INFO - __main__ - Step 4280: {'lr': 0.0004997075239698445, 'samples': 821760, 'steps': 4279, 'loss/train': 2.7107431888580322} 08/30/2021 13:58:16 - INFO - __main__ - Step 4281: {'lr': 0.0004997072672931497, 'samples': 821952, 'steps': 4280, 'loss/train': 2.063675880432129} 08/30/2021 13:58:17 - INFO - __main__ - Step 4282: {'lr': 0.0004997070105039407, 'samples': 822144, 'steps': 4281, 'loss/train': 2.674036979675293} 08/30/2021 13:58:17 - INFO - __main__ - Step 4283: {'lr': 0.0004997067536022176, 'samples': 822336, 'steps': 4282, 'loss/train': 1.758373498916626} 08/30/2021 13:58:18 - INFO - __main__ - Step 4284: {'lr': 0.0004997064965879804, 'samples': 822528, 'steps': 4283, 'loss/train': 2.2967076301574707} 08/30/2021 13:58:18 - INFO - __main__ - Step 4285: {'lr': 0.0004997062394612293, 'samples': 822720, 'steps': 4284, 'loss/train': 2.3500163555145264} 08/30/2021 13:58:18 - INFO - __main__ - Step 4286: {'lr': 0.0004997059822219645, 'samples': 822912, 'steps': 4285, 'loss/train': 2.7859182357788086} 08/30/2021 13:58:20 - INFO - __main__ - Step 4287: {'lr': 0.000499705724870186, 'samples': 823104, 'steps': 4286, 'loss/train': 2.0944437980651855} 08/30/2021 13:58:20 - INFO - __main__ - Step 4288: {'lr': 0.0004997054674058941, 'samples': 823296, 'steps': 4287, 'loss/train': 2.4240219593048096} 08/30/2021 13:58:21 - INFO - __main__ - Step 4289: {'lr': 0.0004997052098290886, 'samples': 823488, 'steps': 4288, 'loss/train': 1.5310779809951782} 08/30/2021 13:58:21 - INFO - __main__ - Step 4290: {'lr': 0.0004997049521397698, 'samples': 823680, 'steps': 4289, 'loss/train': 1.909066081047058} 08/30/2021 13:58:21 - INFO - __main__ - Step 4291: {'lr': 0.0004997046943379379, 'samples': 823872, 'steps': 4290, 'loss/train': 1.9988086223602295} 08/30/2021 13:58:23 - INFO - __main__ - Step 4292: {'lr': 0.0004997044364235928, 'samples': 824064, 'steps': 4291, 'loss/train': 2.4219062328338623} 08/30/2021 13:58:23 - INFO - __main__ - Step 4293: {'lr': 0.0004997041783967348, 'samples': 824256, 'steps': 4292, 'loss/train': 2.3637895584106445} 08/30/2021 13:58:24 - INFO - __main__ - Step 4294: {'lr': 0.0004997039202573639, 'samples': 824448, 'steps': 4293, 'loss/train': 2.4218428134918213} 08/30/2021 13:58:24 - INFO - __main__ - Step 4295: {'lr': 0.0004997036620054803, 'samples': 824640, 'steps': 4294, 'loss/train': 2.5160958766937256} 08/30/2021 13:58:24 - INFO - __main__ - Step 4296: {'lr': 0.0004997034036410841, 'samples': 824832, 'steps': 4295, 'loss/train': 2.5857794284820557} 08/30/2021 13:58:26 - INFO - __main__ - Step 4297: {'lr': 0.0004997031451641754, 'samples': 825024, 'steps': 4296, 'loss/train': 2.141510486602783} 08/30/2021 13:58:26 - INFO - __main__ - Step 4298: {'lr': 0.0004997028865747542, 'samples': 825216, 'steps': 4297, 'loss/train': 2.3709964752197266} 08/30/2021 13:58:27 - INFO - __main__ - Step 4299: {'lr': 0.0004997026278728209, 'samples': 825408, 'steps': 4298, 'loss/train': 1.2953389883041382} 08/30/2021 13:58:27 - INFO - __main__ - Step 4300: {'lr': 0.0004997023690583753, 'samples': 825600, 'steps': 4299, 'loss/train': 1.8751654624938965} 08/30/2021 13:58:27 - INFO - __main__ - Step 4301: {'lr': 0.0004997021101314179, 'samples': 825792, 'steps': 4300, 'loss/train': 2.8405394554138184} 08/30/2021 13:58:29 - INFO - __main__ - Step 4302: {'lr': 0.0004997018510919483, 'samples': 825984, 'steps': 4301, 'loss/train': 2.485252857208252} 08/30/2021 13:58:30 - INFO - __main__ - Step 4303: {'lr': 0.0004997015919399671, 'samples': 826176, 'steps': 4302, 'loss/train': 1.3849883079528809} 08/30/2021 13:58:30 - INFO - __main__ - Step 4304: {'lr': 0.0004997013326754742, 'samples': 826368, 'steps': 4303, 'loss/train': 2.836071729660034} 08/30/2021 13:58:30 - INFO - __main__ - Step 4305: {'lr': 0.0004997010732984696, 'samples': 826560, 'steps': 4304, 'loss/train': 0.530387818813324} 08/30/2021 13:58:31 - INFO - __main__ - Step 4306: {'lr': 0.0004997008138089536, 'samples': 826752, 'steps': 4305, 'loss/train': 2.038630485534668} 08/30/2021 13:58:33 - INFO - __main__ - Step 4307: {'lr': 0.0004997005542069263, 'samples': 826944, 'steps': 4306, 'loss/train': 2.2373640537261963} 08/30/2021 13:58:33 - INFO - __main__ - Step 4308: {'lr': 0.0004997002944923878, 'samples': 827136, 'steps': 4307, 'loss/train': 2.712813377380371} 08/30/2021 13:58:33 - INFO - __main__ - Step 4309: {'lr': 0.0004997000346653381, 'samples': 827328, 'steps': 4308, 'loss/train': 0.8218368291854858} 08/30/2021 13:58:34 - INFO - __main__ - Step 4310: {'lr': 0.0004996997747257775, 'samples': 827520, 'steps': 4309, 'loss/train': 0.7425898909568787} 08/30/2021 13:58:34 - INFO - __main__ - Step 4311: {'lr': 0.000499699514673706, 'samples': 827712, 'steps': 4310, 'loss/train': 2.148676633834839} 08/30/2021 13:58:36 - INFO - __main__ - Step 4312: {'lr': 0.0004996992545091239, 'samples': 827904, 'steps': 4311, 'loss/train': 1.9591997861862183} 08/30/2021 13:58:36 - INFO - __main__ - Step 4313: {'lr': 0.000499698994232031, 'samples': 828096, 'steps': 4312, 'loss/train': 2.2927918434143066} 08/30/2021 13:58:36 - INFO - __main__ - Step 4314: {'lr': 0.0004996987338424276, 'samples': 828288, 'steps': 4313, 'loss/train': 2.691950798034668} 08/30/2021 13:58:37 - INFO - __main__ - Step 4315: {'lr': 0.0004996984733403138, 'samples': 828480, 'steps': 4314, 'loss/train': 2.2400591373443604} 08/30/2021 13:58:37 - INFO - __main__ - Step 4316: {'lr': 0.0004996982127256898, 'samples': 828672, 'steps': 4315, 'loss/train': 1.3791862726211548} 08/30/2021 13:58:39 - INFO - __main__ - Step 4317: {'lr': 0.0004996979519985556, 'samples': 828864, 'steps': 4316, 'loss/train': 2.515639543533325} 08/30/2021 13:58:40 - INFO - __main__ - Step 4318: {'lr': 0.0004996976911589114, 'samples': 829056, 'steps': 4317, 'loss/train': 2.303879976272583} 08/30/2021 13:58:40 - INFO - __main__ - Step 4319: {'lr': 0.0004996974302067572, 'samples': 829248, 'steps': 4318, 'loss/train': 2.3199965953826904} 08/30/2021 13:58:40 - INFO - __main__ - Step 4320: {'lr': 0.0004996971691420931, 'samples': 829440, 'steps': 4319, 'loss/train': 2.417445421218872} 08/30/2021 13:58:41 - INFO - __main__ - Step 4321: {'lr': 0.0004996969079649195, 'samples': 829632, 'steps': 4320, 'loss/train': 1.4854261875152588} 08/30/2021 13:58:41 - INFO - __main__ - Step 4322: {'lr': 0.0004996966466752362, 'samples': 829824, 'steps': 4321, 'loss/train': 1.9340102672576904} 08/30/2021 13:58:41 - INFO - __main__ - Step 4323: {'lr': 0.0004996963852730436, 'samples': 830016, 'steps': 4322, 'loss/train': 0.8232200741767883} 08/30/2021 13:58:43 - INFO - __main__ - Step 4324: {'lr': 0.0004996961237583415, 'samples': 830208, 'steps': 4323, 'loss/train': 2.788846015930176} 08/30/2021 13:58:43 - INFO - __main__ - Step 4325: {'lr': 0.0004996958621311302, 'samples': 830400, 'steps': 4324, 'loss/train': 1.918544054031372} 08/30/2021 13:58:44 - INFO - __main__ - Step 4326: {'lr': 0.00049969560039141, 'samples': 830592, 'steps': 4325, 'loss/train': 2.509490966796875} 08/30/2021 13:58:44 - INFO - __main__ - Step 4327: {'lr': 0.0004996953385391806, 'samples': 830784, 'steps': 4326, 'loss/train': 1.5261305570602417} 08/30/2021 13:58:45 - INFO - __main__ - Step 4328: {'lr': 0.0004996950765744424, 'samples': 830976, 'steps': 4327, 'loss/train': 4.768551349639893} 08/30/2021 13:58:47 - INFO - __main__ - Step 4329: {'lr': 0.0004996948144971953, 'samples': 831168, 'steps': 4328, 'loss/train': 2.8698997497558594} 08/30/2021 13:58:47 - INFO - __main__ - Step 4330: {'lr': 0.0004996945523074398, 'samples': 831360, 'steps': 4329, 'loss/train': 2.0760560035705566} 08/30/2021 13:58:48 - INFO - __main__ - Step 4331: {'lr': 0.0004996942900051757, 'samples': 831552, 'steps': 4330, 'loss/train': 2.6386237144470215} 08/30/2021 13:58:48 - INFO - __main__ - Step 4332: {'lr': 0.0004996940275904031, 'samples': 831744, 'steps': 4331, 'loss/train': 2.426943302154541} 08/30/2021 13:58:48 - INFO - __main__ - Step 4333: {'lr': 0.0004996937650631224, 'samples': 831936, 'steps': 4332, 'loss/train': 2.3700973987579346} 08/30/2021 13:58:49 - INFO - __main__ - Step 4334: {'lr': 0.0004996935024233335, 'samples': 832128, 'steps': 4333, 'loss/train': 2.332881212234497} 08/30/2021 13:58:50 - INFO - __main__ - Step 4335: {'lr': 0.0004996932396710365, 'samples': 832320, 'steps': 4334, 'loss/train': 2.653916358947754} 08/30/2021 13:58:51 - INFO - __main__ - Step 4336: {'lr': 0.0004996929768062316, 'samples': 832512, 'steps': 4335, 'loss/train': 0.45033589005470276} 08/30/2021 13:58:51 - INFO - __main__ - Step 4337: {'lr': 0.0004996927138289189, 'samples': 832704, 'steps': 4336, 'loss/train': 2.5595593452453613} 08/30/2021 13:58:52 - INFO - __main__ - Step 4338: {'lr': 0.0004996924507390985, 'samples': 832896, 'steps': 4337, 'loss/train': 2.6162071228027344} 08/30/2021 13:58:52 - INFO - __main__ - Step 4339: {'lr': 0.0004996921875367705, 'samples': 833088, 'steps': 4338, 'loss/train': 2.4030649662017822} 08/30/2021 13:58:53 - INFO - __main__ - Step 4340: {'lr': 0.0004996919242219352, 'samples': 833280, 'steps': 4339, 'loss/train': 2.39670467376709} 08/30/2021 13:58:54 - INFO - __main__ - Step 4341: {'lr': 0.0004996916607945925, 'samples': 833472, 'steps': 4340, 'loss/train': 2.164501667022705} 08/30/2021 13:58:54 - INFO - __main__ - Step 4342: {'lr': 0.0004996913972547426, 'samples': 833664, 'steps': 4341, 'loss/train': 2.9331772327423096} 08/30/2021 13:58:55 - INFO - __main__ - Step 4343: {'lr': 0.0004996911336023855, 'samples': 833856, 'steps': 4342, 'loss/train': 2.5203447341918945} 08/30/2021 13:58:55 - INFO - __main__ - Step 4344: {'lr': 0.0004996908698375216, 'samples': 834048, 'steps': 4343, 'loss/train': 0.7685109972953796} 08/30/2021 13:58:57 - INFO - __main__ - Step 4345: {'lr': 0.0004996906059601507, 'samples': 834240, 'steps': 4344, 'loss/train': 2.147205352783203} 08/30/2021 13:58:57 - INFO - __main__ - Step 4346: {'lr': 0.0004996903419702731, 'samples': 834432, 'steps': 4345, 'loss/train': 2.3634419441223145} 08/30/2021 13:58:58 - INFO - __main__ - Step 4347: {'lr': 0.0004996900778678889, 'samples': 834624, 'steps': 4346, 'loss/train': 2.214385509490967} 08/30/2021 13:58:58 - INFO - __main__ - Step 4348: {'lr': 0.0004996898136529982, 'samples': 834816, 'steps': 4347, 'loss/train': 2.25006365776062} 08/30/2021 13:58:58 - INFO - __main__ - Step 4349: {'lr': 0.0004996895493256012, 'samples': 835008, 'steps': 4348, 'loss/train': 0.9130091667175293} 08/30/2021 13:58:59 - INFO - __main__ - Step 4350: {'lr': 0.0004996892848856978, 'samples': 835200, 'steps': 4349, 'loss/train': 2.3988945484161377} 08/30/2021 13:59:00 - INFO - __main__ - Step 4351: {'lr': 0.0004996890203332883, 'samples': 835392, 'steps': 4350, 'loss/train': 2.3409547805786133} 08/30/2021 13:59:01 - INFO - __main__ - Step 4352: {'lr': 0.0004996887556683729, 'samples': 835584, 'steps': 4351, 'loss/train': 2.735775947570801} 08/30/2021 13:59:01 - INFO - __main__ - Step 4353: {'lr': 0.0004996884908909515, 'samples': 835776, 'steps': 4352, 'loss/train': 3.0763423442840576} 08/30/2021 13:59:01 - INFO - __main__ - Step 4354: {'lr': 0.0004996882260010243, 'samples': 835968, 'steps': 4353, 'loss/train': 2.391918897628784} 08/30/2021 13:59:02 - INFO - __main__ - Step 4355: {'lr': 0.0004996879609985915, 'samples': 836160, 'steps': 4354, 'loss/train': 2.481785774230957} 08/30/2021 13:59:04 - INFO - __main__ - Step 4356: {'lr': 0.0004996876958836532, 'samples': 836352, 'steps': 4355, 'loss/train': 2.397257089614868} 08/30/2021 13:59:04 - INFO - __main__ - Step 4357: {'lr': 0.0004996874306562093, 'samples': 836544, 'steps': 4356, 'loss/train': 2.421093702316284} 08/30/2021 13:59:05 - INFO - __main__ - Step 4358: {'lr': 0.0004996871653162602, 'samples': 836736, 'steps': 4357, 'loss/train': 2.3213443756103516} 08/30/2021 13:59:05 - INFO - __main__ - Step 4359: {'lr': 0.0004996868998638059, 'samples': 836928, 'steps': 4358, 'loss/train': 3.1187126636505127} 08/30/2021 13:59:05 - INFO - __main__ - Step 4360: {'lr': 0.0004996866342988467, 'samples': 837120, 'steps': 4359, 'loss/train': 3.13950514793396} 08/30/2021 13:59:06 - INFO - __main__ - Step 4361: {'lr': 0.0004996863686213823, 'samples': 837312, 'steps': 4360, 'loss/train': 3.030313491821289} 08/30/2021 13:59:07 - INFO - __main__ - Step 4362: {'lr': 0.0004996861028314133, 'samples': 837504, 'steps': 4361, 'loss/train': 2.4247844219207764} 08/30/2021 13:59:08 - INFO - __main__ - Step 4363: {'lr': 0.0004996858369289394, 'samples': 837696, 'steps': 4362, 'loss/train': 2.6634891033172607} 08/30/2021 13:59:08 - INFO - __main__ - Step 4364: {'lr': 0.000499685570913961, 'samples': 837888, 'steps': 4363, 'loss/train': 2.71620512008667} 08/30/2021 13:59:08 - INFO - __main__ - Step 4365: {'lr': 0.0004996853047864781, 'samples': 838080, 'steps': 4364, 'loss/train': 2.6044857501983643} 08/30/2021 13:59:09 - INFO - __main__ - Step 4366: {'lr': 0.0004996850385464909, 'samples': 838272, 'steps': 4365, 'loss/train': 2.048746347427368} 08/30/2021 13:59:10 - INFO - __main__ - Step 4367: {'lr': 0.0004996847721939994, 'samples': 838464, 'steps': 4366, 'loss/train': 2.580474615097046} 08/30/2021 13:59:11 - INFO - __main__ - Step 4368: {'lr': 0.0004996845057290039, 'samples': 838656, 'steps': 4367, 'loss/train': 2.8319928646087646} 08/30/2021 13:59:11 - INFO - __main__ - Step 4369: {'lr': 0.0004996842391515044, 'samples': 838848, 'steps': 4368, 'loss/train': 2.554839611053467} 08/30/2021 13:59:11 - INFO - __main__ - Step 4370: {'lr': 0.000499683972461501, 'samples': 839040, 'steps': 4369, 'loss/train': 2.2035911083221436} 08/30/2021 13:59:12 - INFO - __main__ - Step 4371: {'lr': 0.0004996837056589938, 'samples': 839232, 'steps': 4370, 'loss/train': 2.651333808898926} 08/30/2021 13:59:12 - INFO - __main__ - Step 4372: {'lr': 0.0004996834387439831, 'samples': 839424, 'steps': 4371, 'loss/train': 1.8789271116256714} 08/30/2021 13:59:13 - INFO - __main__ - Step 4373: {'lr': 0.0004996831717164689, 'samples': 839616, 'steps': 4372, 'loss/train': 2.723007917404175} 08/30/2021 13:59:14 - INFO - __main__ - Step 4374: {'lr': 0.0004996829045764512, 'samples': 839808, 'steps': 4373, 'loss/train': 2.5256690979003906} 08/30/2021 13:59:14 - INFO - __main__ - Step 4375: {'lr': 0.0004996826373239303, 'samples': 840000, 'steps': 4374, 'loss/train': 2.008065700531006} 08/30/2021 13:59:15 - INFO - __main__ - Step 4376: {'lr': 0.0004996823699589062, 'samples': 840192, 'steps': 4375, 'loss/train': 3.023691177368164} 08/30/2021 13:59:15 - INFO - __main__ - Step 4377: {'lr': 0.0004996821024813791, 'samples': 840384, 'steps': 4376, 'loss/train': 2.7508814334869385} 08/30/2021 13:59:16 - INFO - __main__ - Step 4378: {'lr': 0.0004996818348913491, 'samples': 840576, 'steps': 4377, 'loss/train': 2.824896812438965} 08/30/2021 13:59:17 - INFO - __main__ - Step 4379: {'lr': 0.0004996815671888163, 'samples': 840768, 'steps': 4378, 'loss/train': 2.251624345779419} 08/30/2021 13:59:17 - INFO - __main__ - Step 4380: {'lr': 0.000499681299373781, 'samples': 840960, 'steps': 4379, 'loss/train': 1.3489680290222168} 08/30/2021 13:59:18 - INFO - __main__ - Step 4381: {'lr': 0.0004996810314462429, 'samples': 841152, 'steps': 4380, 'loss/train': 3.206294298171997} 08/30/2021 13:59:18 - INFO - __main__ - Step 4382: {'lr': 0.0004996807634062025, 'samples': 841344, 'steps': 4381, 'loss/train': 2.6561877727508545} 08/30/2021 13:59:20 - INFO - __main__ - Step 4383: {'lr': 0.0004996804952536599, 'samples': 841536, 'steps': 4382, 'loss/train': 2.2637486457824707} 08/30/2021 13:59:20 - INFO - __main__ - Step 4384: {'lr': 0.0004996802269886149, 'samples': 841728, 'steps': 4383, 'loss/train': 2.256096124649048} 08/30/2021 13:59:20 - INFO - __main__ - Step 4385: {'lr': 0.0004996799586110681, 'samples': 841920, 'steps': 4384, 'loss/train': 2.0771517753601074} 08/30/2021 13:59:21 - INFO - __main__ - Step 4386: {'lr': 0.0004996796901210192, 'samples': 842112, 'steps': 4385, 'loss/train': 2.951462507247925} 08/30/2021 13:59:21 - INFO - __main__ - Step 4387: {'lr': 0.0004996794215184685, 'samples': 842304, 'steps': 4386, 'loss/train': 2.0754663944244385} 08/30/2021 13:59:24 - INFO - __main__ - Step 4388: {'lr': 0.0004996791528034161, 'samples': 842496, 'steps': 4387, 'loss/train': 2.625568389892578} 08/30/2021 13:59:24 - INFO - __main__ - Step 4389: {'lr': 0.0004996788839758622, 'samples': 842688, 'steps': 4388, 'loss/train': 2.0868711471557617} 08/30/2021 13:59:24 - INFO - __main__ - Step 4390: {'lr': 0.0004996786150358068, 'samples': 842880, 'steps': 4389, 'loss/train': 1.0992119312286377} 08/30/2021 13:59:25 - INFO - __main__ - Step 4391: {'lr': 0.00049967834598325, 'samples': 843072, 'steps': 4390, 'loss/train': 2.903900146484375} 08/30/2021 13:59:25 - INFO - __main__ - Step 4392: {'lr': 0.0004996780768181921, 'samples': 843264, 'steps': 4391, 'loss/train': 2.5160937309265137} 08/30/2021 13:59:27 - INFO - __main__ - Step 4393: {'lr': 0.0004996778075406331, 'samples': 843456, 'steps': 4392, 'loss/train': 2.3703763484954834} 08/30/2021 13:59:27 - INFO - __main__ - Step 4394: {'lr': 0.0004996775381505731, 'samples': 843648, 'steps': 4393, 'loss/train': 2.8998920917510986} 08/30/2021 13:59:28 - INFO - __main__ - Step 4395: {'lr': 0.0004996772686480122, 'samples': 843840, 'steps': 4394, 'loss/train': 2.3615400791168213} 08/30/2021 13:59:28 - INFO - __main__ - Step 4396: {'lr': 0.0004996769990329507, 'samples': 844032, 'steps': 4395, 'loss/train': 2.7064578533172607} 08/30/2021 13:59:28 - INFO - __main__ - Step 4397: {'lr': 0.0004996767293053885, 'samples': 844224, 'steps': 4396, 'loss/train': 0.9128702878952026} 08/30/2021 13:59:30 - INFO - __main__ - Step 4398: {'lr': 0.0004996764594653258, 'samples': 844416, 'steps': 4397, 'loss/train': 2.0633468627929688} 08/30/2021 13:59:30 - INFO - __main__ - Step 4399: {'lr': 0.0004996761895127628, 'samples': 844608, 'steps': 4398, 'loss/train': 3.204718828201294} 08/30/2021 13:59:31 - INFO - __main__ - Step 4400: {'lr': 0.0004996759194476996, 'samples': 844800, 'steps': 4399, 'loss/train': 2.81738018989563} 08/30/2021 13:59:31 - INFO - __main__ - Step 4401: {'lr': 0.0004996756492701362, 'samples': 844992, 'steps': 4400, 'loss/train': 2.7315587997436523} 08/30/2021 13:59:31 - INFO - __main__ - Step 4402: {'lr': 0.0004996753789800729, 'samples': 845184, 'steps': 4401, 'loss/train': 2.656501293182373} 08/30/2021 13:59:32 - INFO - __main__ - Step 4403: {'lr': 0.0004996751085775096, 'samples': 845376, 'steps': 4402, 'loss/train': 3.0188190937042236} 08/30/2021 13:59:33 - INFO - __main__ - Step 4404: {'lr': 0.0004996748380624467, 'samples': 845568, 'steps': 4403, 'loss/train': 2.4543826580047607} 08/30/2021 13:59:34 - INFO - __main__ - Step 4405: {'lr': 0.000499674567434884, 'samples': 845760, 'steps': 4404, 'loss/train': 3.0986216068267822} 08/30/2021 13:59:34 - INFO - __main__ - Step 4406: {'lr': 0.0004996742966948219, 'samples': 845952, 'steps': 4405, 'loss/train': 2.609631061553955} 08/30/2021 13:59:34 - INFO - __main__ - Step 4407: {'lr': 0.0004996740258422604, 'samples': 846144, 'steps': 4406, 'loss/train': 2.6129021644592285} 08/30/2021 13:59:35 - INFO - __main__ - Step 4408: {'lr': 0.0004996737548771997, 'samples': 846336, 'steps': 4407, 'loss/train': 1.8508158922195435} 08/30/2021 13:59:36 - INFO - __main__ - Step 4409: {'lr': 0.0004996734837996397, 'samples': 846528, 'steps': 4408, 'loss/train': 2.298949956893921} 08/30/2021 13:59:37 - INFO - __main__ - Step 4410: {'lr': 0.0004996732126095807, 'samples': 846720, 'steps': 4409, 'loss/train': 2.9131104946136475} 08/30/2021 13:59:37 - INFO - __main__ - Step 4411: {'lr': 0.0004996729413070229, 'samples': 846912, 'steps': 4410, 'loss/train': 2.257246732711792} 08/30/2021 13:59:37 - INFO - __main__ - Step 4412: {'lr': 0.0004996726698919664, 'samples': 847104, 'steps': 4411, 'loss/train': 2.803863048553467} 08/30/2021 13:59:38 - INFO - __main__ - Step 4413: {'lr': 0.0004996723983644112, 'samples': 847296, 'steps': 4412, 'loss/train': 2.301168918609619} 08/30/2021 13:59:40 - INFO - __main__ - Step 4414: {'lr': 0.0004996721267243573, 'samples': 847488, 'steps': 4413, 'loss/train': 1.7177538871765137} 08/30/2021 13:59:40 - INFO - __main__ - Step 4415: {'lr': 0.0004996718549718051, 'samples': 847680, 'steps': 4414, 'loss/train': 2.3217835426330566} 08/30/2021 13:59:40 - INFO - __main__ - Step 4416: {'lr': 0.0004996715831067546, 'samples': 847872, 'steps': 4415, 'loss/train': 1.7899372577667236} 08/30/2021 13:59:41 - INFO - __main__ - Step 4417: {'lr': 0.000499671311129206, 'samples': 848064, 'steps': 4416, 'loss/train': 2.663358211517334} 08/30/2021 13:59:41 - INFO - __main__ - Step 4418: {'lr': 0.0004996710390391593, 'samples': 848256, 'steps': 4417, 'loss/train': 2.5235495567321777} 08/30/2021 13:59:43 - INFO - __main__ - Step 4419: {'lr': 0.0004996707668366147, 'samples': 848448, 'steps': 4418, 'loss/train': 0.48375609517097473} 08/30/2021 13:59:43 - INFO - __main__ - Step 4420: {'lr': 0.0004996704945215724, 'samples': 848640, 'steps': 4419, 'loss/train': 3.206803798675537} 08/30/2021 13:59:43 - INFO - __main__ - Step 4421: {'lr': 0.0004996702220940322, 'samples': 848832, 'steps': 4420, 'loss/train': 2.434300184249878} 08/30/2021 13:59:44 - INFO - __main__ - Step 4422: {'lr': 0.0004996699495539947, 'samples': 849024, 'steps': 4421, 'loss/train': 2.0685155391693115} 08/30/2021 13:59:44 - INFO - __main__ - Step 4423: {'lr': 0.0004996696769014596, 'samples': 849216, 'steps': 4422, 'loss/train': 2.4212698936462402} 08/30/2021 13:59:46 - INFO - __main__ - Step 4424: {'lr': 0.0004996694041364272, 'samples': 849408, 'steps': 4423, 'loss/train': 2.027961492538452} 08/30/2021 13:59:46 - INFO - __main__ - Step 4425: {'lr': 0.0004996691312588977, 'samples': 849600, 'steps': 4424, 'loss/train': 2.265188694000244} 08/30/2021 13:59:46 - INFO - __main__ - Step 4426: {'lr': 0.0004996688582688711, 'samples': 849792, 'steps': 4425, 'loss/train': 2.822570562362671} 08/30/2021 13:59:47 - INFO - __main__ - Step 4427: {'lr': 0.0004996685851663477, 'samples': 849984, 'steps': 4426, 'loss/train': 2.7943873405456543} 08/30/2021 13:59:47 - INFO - __main__ - Step 4428: {'lr': 0.0004996683119513274, 'samples': 850176, 'steps': 4427, 'loss/train': 2.2864913940429688} 08/30/2021 13:59:49 - INFO - __main__ - Step 4429: {'lr': 0.0004996680386238103, 'samples': 850368, 'steps': 4428, 'loss/train': 1.8238520622253418} 08/30/2021 13:59:49 - INFO - __main__ - Step 4430: {'lr': 0.0004996677651837967, 'samples': 850560, 'steps': 4429, 'loss/train': 2.325866222381592} 08/30/2021 13:59:49 - INFO - __main__ - Step 4431: {'lr': 0.0004996674916312867, 'samples': 850752, 'steps': 4430, 'loss/train': 2.2738285064697266} 08/30/2021 13:59:50 - INFO - __main__ - Step 4432: {'lr': 0.0004996672179662803, 'samples': 850944, 'steps': 4431, 'loss/train': 2.172910213470459} 08/30/2021 13:59:50 - INFO - __main__ - Step 4433: {'lr': 0.0004996669441887778, 'samples': 851136, 'steps': 4432, 'loss/train': 2.6636414527893066} 08/30/2021 13:59:51 - INFO - __main__ - Step 4434: {'lr': 0.0004996666702987791, 'samples': 851328, 'steps': 4433, 'loss/train': 2.2548768520355225} 08/30/2021 13:59:52 - INFO - __main__ - Step 4435: {'lr': 0.0004996663962962846, 'samples': 851520, 'steps': 4434, 'loss/train': 2.0982847213745117} 08/30/2021 13:59:53 - INFO - __main__ - Step 4436: {'lr': 0.0004996661221812942, 'samples': 851712, 'steps': 4435, 'loss/train': 3.23982834815979} 08/30/2021 13:59:53 - INFO - __main__ - Step 4437: {'lr': 0.0004996658479538081, 'samples': 851904, 'steps': 4436, 'loss/train': 3.0859453678131104} 08/30/2021 13:59:53 - INFO - __main__ - Step 4438: {'lr': 0.0004996655736138265, 'samples': 852096, 'steps': 4437, 'loss/train': 0.9713526368141174} 08/30/2021 13:59:54 - INFO - __main__ - Step 4439: {'lr': 0.0004996652991613494, 'samples': 852288, 'steps': 4438, 'loss/train': 2.5843000411987305} 08/30/2021 13:59:56 - INFO - __main__ - Step 4440: {'lr': 0.0004996650245963768, 'samples': 852480, 'steps': 4439, 'loss/train': 2.302584171295166} 08/30/2021 13:59:56 - INFO - __main__ - Step 4441: {'lr': 0.0004996647499189092, 'samples': 852672, 'steps': 4440, 'loss/train': 3.055056095123291} 08/30/2021 13:59:57 - INFO - __main__ - Step 4442: {'lr': 0.0004996644751289464, 'samples': 852864, 'steps': 4441, 'loss/train': 2.611168622970581} 08/30/2021 13:59:57 - INFO - __main__ - Step 4443: {'lr': 0.0004996642002264887, 'samples': 853056, 'steps': 4442, 'loss/train': 2.2941527366638184} 08/30/2021 13:59:57 - INFO - __main__ - Step 4444: {'lr': 0.0004996639252115362, 'samples': 853248, 'steps': 4443, 'loss/train': 2.7221500873565674} 08/30/2021 13:59:59 - INFO - __main__ - Step 4445: {'lr': 0.000499663650084089, 'samples': 853440, 'steps': 4444, 'loss/train': 3.0388267040252686} 08/30/2021 14:00:00 - INFO - __main__ - Step 4446: {'lr': 0.0004996633748441472, 'samples': 853632, 'steps': 4445, 'loss/train': 2.3005685806274414} 08/30/2021 14:00:00 - INFO - __main__ - Step 4447: {'lr': 0.0004996630994917108, 'samples': 853824, 'steps': 4446, 'loss/train': 0.48164039850234985} 08/30/2021 14:00:00 - INFO - __main__ - Step 4448: {'lr': 0.0004996628240267802, 'samples': 854016, 'steps': 4447, 'loss/train': 2.155078649520874} 08/30/2021 14:00:01 - INFO - __main__ - Step 4449: {'lr': 0.0004996625484493554, 'samples': 854208, 'steps': 4448, 'loss/train': 1.9735839366912842} 08/30/2021 14:00:01 - INFO - __main__ - Step 4450: {'lr': 0.0004996622727594363, 'samples': 854400, 'steps': 4449, 'loss/train': 3.0032947063446045} 08/30/2021 14:00:03 - INFO - __main__ - Step 4451: {'lr': 0.0004996619969570234, 'samples': 854592, 'steps': 4450, 'loss/train': 2.0180344581604004} 08/30/2021 14:00:04 - INFO - __main__ - Step 4452: {'lr': 0.0004996617210421166, 'samples': 854784, 'steps': 4451, 'loss/train': 1.3236488103866577} 08/30/2021 14:00:04 - INFO - __main__ - Step 4453: {'lr': 0.0004996614450147161, 'samples': 854976, 'steps': 4452, 'loss/train': 0.774139940738678} 08/30/2021 14:00:04 - INFO - __main__ - Step 4454: {'lr': 0.0004996611688748221, 'samples': 855168, 'steps': 4453, 'loss/train': 2.6716136932373047} 08/30/2021 14:00:05 - INFO - __main__ - Step 4455: {'lr': 0.0004996608926224345, 'samples': 855360, 'steps': 4454, 'loss/train': 2.286705493927002} 08/30/2021 14:00:05 - INFO - __main__ - Step 4456: {'lr': 0.0004996606162575536, 'samples': 855552, 'steps': 4455, 'loss/train': 0.7882221937179565} 08/30/2021 14:00:06 - INFO - __main__ - Step 4457: {'lr': 0.0004996603397801795, 'samples': 855744, 'steps': 4456, 'loss/train': 3.2340660095214844} 08/30/2021 14:00:07 - INFO - __main__ - Step 4458: {'lr': 0.0004996600631903123, 'samples': 855936, 'steps': 4457, 'loss/train': 3.1454315185546875} 08/30/2021 14:00:07 - INFO - __main__ - Step 4459: {'lr': 0.0004996597864879521, 'samples': 856128, 'steps': 4458, 'loss/train': 2.2844502925872803} 08/30/2021 14:00:08 - INFO - __main__ - Step 4460: {'lr': 0.000499659509673099, 'samples': 856320, 'steps': 4459, 'loss/train': 2.2326767444610596} 08/30/2021 14:00:08 - INFO - __main__ - Step 4461: {'lr': 0.0004996592327457533, 'samples': 856512, 'steps': 4460, 'loss/train': 2.3373653888702393} 08/30/2021 14:00:09 - INFO - __main__ - Step 4462: {'lr': 0.000499658955705915, 'samples': 856704, 'steps': 4461, 'loss/train': 2.4097986221313477} 08/30/2021 14:00:10 - INFO - __main__ - Step 4463: {'lr': 0.0004996586785535841, 'samples': 856896, 'steps': 4462, 'loss/train': 2.207939624786377} 08/30/2021 14:00:10 - INFO - __main__ - Step 4464: {'lr': 0.000499658401288761, 'samples': 857088, 'steps': 4463, 'loss/train': 1.9724675416946411} 08/30/2021 14:00:11 - INFO - __main__ - Step 4465: {'lr': 0.0004996581239114456, 'samples': 857280, 'steps': 4464, 'loss/train': 2.0959792137145996} 08/30/2021 14:00:11 - INFO - __main__ - Step 4466: {'lr': 0.0004996578464216381, 'samples': 857472, 'steps': 4465, 'loss/train': 2.3610620498657227} 08/30/2021 14:00:12 - INFO - __main__ - Step 4467: {'lr': 0.0004996575688193386, 'samples': 857664, 'steps': 4466, 'loss/train': 1.904547095298767} 08/30/2021 14:00:13 - INFO - __main__ - Step 4468: {'lr': 0.0004996572911045473, 'samples': 857856, 'steps': 4467, 'loss/train': 0.7102074027061462} 08/30/2021 14:00:13 - INFO - __main__ - Step 4469: {'lr': 0.0004996570132772642, 'samples': 858048, 'steps': 4468, 'loss/train': 2.963158130645752} 08/30/2021 14:00:13 - INFO - __main__ - Step 4470: {'lr': 0.0004996567353374896, 'samples': 858240, 'steps': 4469, 'loss/train': 2.5914316177368164} 08/30/2021 14:00:14 - INFO - __main__ - Step 4471: {'lr': 0.0004996564572852235, 'samples': 858432, 'steps': 4470, 'loss/train': 3.332909107208252} 08/30/2021 14:00:16 - INFO - __main__ - Step 4472: {'lr': 0.000499656179120466, 'samples': 858624, 'steps': 4471, 'loss/train': 2.154690980911255} 08/30/2021 14:00:16 - INFO - __main__ - Step 4473: {'lr': 0.0004996559008432173, 'samples': 858816, 'steps': 4472, 'loss/train': 2.439270257949829} 08/30/2021 14:00:17 - INFO - __main__ - Step 4474: {'lr': 0.0004996556224534776, 'samples': 859008, 'steps': 4473, 'loss/train': 0.8880488276481628} 08/30/2021 14:00:17 - INFO - __main__ - Step 4475: {'lr': 0.0004996553439512468, 'samples': 859200, 'steps': 4474, 'loss/train': 0.8130812644958496} 08/30/2021 14:00:17 - INFO - __main__ - Step 4476: {'lr': 0.0004996550653365253, 'samples': 859392, 'steps': 4475, 'loss/train': 2.4375765323638916} 08/30/2021 14:00:18 - INFO - __main__ - Step 4477: {'lr': 0.0004996547866093129, 'samples': 859584, 'steps': 4476, 'loss/train': 3.0253424644470215} 08/30/2021 14:00:19 - INFO - __main__ - Step 4478: {'lr': 0.00049965450776961, 'samples': 859776, 'steps': 4477, 'loss/train': 0.6013203263282776} 08/30/2021 14:00:20 - INFO - __main__ - Step 4479: {'lr': 0.0004996542288174166, 'samples': 859968, 'steps': 4478, 'loss/train': 2.0361762046813965} 08/30/2021 14:00:20 - INFO - __main__ - Step 4480: {'lr': 0.0004996539497527329, 'samples': 860160, 'steps': 4479, 'loss/train': 0.5610140562057495} 08/30/2021 14:00:21 - INFO - __main__ - Step 4481: {'lr': 0.000499653670575559, 'samples': 860352, 'steps': 4480, 'loss/train': 2.0953292846679688} 08/30/2021 14:00:21 - INFO - __main__ - Step 4482: {'lr': 0.0004996533912858949, 'samples': 860544, 'steps': 4481, 'loss/train': 1.6098066568374634} 08/30/2021 14:00:22 - INFO - __main__ - Step 4483: {'lr': 0.000499653111883741, 'samples': 860736, 'steps': 4482, 'loss/train': 2.3210976123809814} 08/30/2021 14:00:23 - INFO - __main__ - Step 4484: {'lr': 0.0004996528323690971, 'samples': 860928, 'steps': 4483, 'loss/train': 2.522338628768921} 08/30/2021 14:00:23 - INFO - __main__ - Step 4485: {'lr': 0.0004996525527419636, 'samples': 861120, 'steps': 4484, 'loss/train': 2.73907208442688} 08/30/2021 14:00:24 - INFO - __main__ - Step 4486: {'lr': 0.0004996522730023404, 'samples': 861312, 'steps': 4485, 'loss/train': 2.050724506378174} 08/30/2021 14:00:24 - INFO - __main__ - Step 4487: {'lr': 0.0004996519931502279, 'samples': 861504, 'steps': 4486, 'loss/train': 2.388427257537842} 08/30/2021 14:00:24 - INFO - __main__ - Step 4488: {'lr': 0.0004996517131856259, 'samples': 861696, 'steps': 4487, 'loss/train': 2.3693833351135254} 08/30/2021 14:00:26 - INFO - __main__ - Step 4489: {'lr': 0.0004996514331085348, 'samples': 861888, 'steps': 4488, 'loss/train': 2.3274548053741455} 08/30/2021 14:00:26 - INFO - __main__ - Step 4490: {'lr': 0.0004996511529189546, 'samples': 862080, 'steps': 4489, 'loss/train': 0.9971614480018616} 08/30/2021 14:00:27 - INFO - __main__ - Step 4491: {'lr': 0.0004996508726168854, 'samples': 862272, 'steps': 4490, 'loss/train': 2.128624439239502} 08/30/2021 14:00:27 - INFO - __main__ - Step 4492: {'lr': 0.0004996505922023274, 'samples': 862464, 'steps': 4491, 'loss/train': 5.315568923950195} 08/30/2021 14:00:27 - INFO - __main__ - Step 4493: {'lr': 0.0004996503116752807, 'samples': 862656, 'steps': 4492, 'loss/train': 0.5561769008636475} 08/30/2021 14:00:29 - INFO - __main__ - Step 4494: {'lr': 0.0004996500310357454, 'samples': 862848, 'steps': 4493, 'loss/train': 2.6158716678619385} 08/30/2021 14:00:30 - INFO - __main__ - Step 4495: {'lr': 0.0004996497502837217, 'samples': 863040, 'steps': 4494, 'loss/train': 2.018419027328491} 08/30/2021 14:00:30 - INFO - __main__ - Step 4496: {'lr': 0.0004996494694192096, 'samples': 863232, 'steps': 4495, 'loss/train': 2.135006904602051} 08/30/2021 14:00:31 - INFO - __main__ - Step 4497: {'lr': 0.0004996491884422092, 'samples': 863424, 'steps': 4496, 'loss/train': 2.594553232192993} 08/30/2021 14:00:31 - INFO - __main__ - Step 4498: {'lr': 0.0004996489073527208, 'samples': 863616, 'steps': 4497, 'loss/train': 3.1940338611602783} 08/30/2021 14:00:31 - INFO - __main__ - Step 4499: {'lr': 0.0004996486261507445, 'samples': 863808, 'steps': 4498, 'loss/train': 0.7680402398109436} 08/30/2021 14:00:32 - INFO - __main__ - Step 4500: {'lr': 0.0004996483448362805, 'samples': 864000, 'steps': 4499, 'loss/train': 0.6784037947654724} 08/30/2021 14:00:34 - INFO - __main__ - Step 4501: {'lr': 0.0004996480634093287, 'samples': 864192, 'steps': 4500, 'loss/train': 2.0224390029907227} 08/30/2021 14:00:34 - INFO - __main__ - Step 4502: {'lr': 0.0004996477818698893, 'samples': 864384, 'steps': 4501, 'loss/train': 2.3429672718048096} 08/30/2021 14:00:34 - INFO - __main__ - Step 4503: {'lr': 0.0004996475002179625, 'samples': 864576, 'steps': 4502, 'loss/train': 2.2044742107391357} 08/30/2021 14:00:35 - INFO - __main__ - Step 4504: {'lr': 0.0004996472184535484, 'samples': 864768, 'steps': 4503, 'loss/train': 2.7269012928009033} 08/30/2021 14:00:35 - INFO - __main__ - Step 4505: {'lr': 0.0004996469365766471, 'samples': 864960, 'steps': 4504, 'loss/train': 2.5406477451324463} 08/30/2021 14:00:37 - INFO - __main__ - Step 4506: {'lr': 0.0004996466545872588, 'samples': 865152, 'steps': 4505, 'loss/train': 2.55234956741333} 08/30/2021 14:00:37 - INFO - __main__ - Step 4507: {'lr': 0.0004996463724853834, 'samples': 865344, 'steps': 4506, 'loss/train': 1.5074973106384277} 08/30/2021 14:00:37 - INFO - __main__ - Step 4508: {'lr': 0.0004996460902710214, 'samples': 865536, 'steps': 4507, 'loss/train': 2.267874002456665} 08/30/2021 14:00:38 - INFO - __main__ - Step 4509: {'lr': 0.0004996458079441727, 'samples': 865728, 'steps': 4508, 'loss/train': 2.308412790298462} 08/30/2021 14:00:38 - INFO - __main__ - Step 4510: {'lr': 0.0004996455255048373, 'samples': 865920, 'steps': 4509, 'loss/train': 2.0908989906311035} 08/30/2021 14:00:40 - INFO - __main__ - Step 4511: {'lr': 0.0004996452429530156, 'samples': 866112, 'steps': 4510, 'loss/train': 2.758845329284668} 08/30/2021 14:00:40 - INFO - __main__ - Step 4512: {'lr': 0.0004996449602887075, 'samples': 866304, 'steps': 4511, 'loss/train': 2.616922616958618} 08/30/2021 14:00:41 - INFO - __main__ - Step 4513: {'lr': 0.0004996446775119134, 'samples': 866496, 'steps': 4512, 'loss/train': 2.135817289352417} 08/30/2021 14:00:41 - INFO - __main__ - Step 4514: {'lr': 0.0004996443946226331, 'samples': 866688, 'steps': 4513, 'loss/train': 2.0573575496673584} 08/30/2021 14:00:41 - INFO - __main__ - Step 4515: {'lr': 0.000499644111620867, 'samples': 866880, 'steps': 4514, 'loss/train': 2.2674593925476074} 08/30/2021 14:00:42 - INFO - __main__ - Step 4516: {'lr': 0.000499643828506615, 'samples': 867072, 'steps': 4515, 'loss/train': 2.3302407264709473} 08/30/2021 14:00:43 - INFO - __main__ - Step 4517: {'lr': 0.0004996435452798775, 'samples': 867264, 'steps': 4516, 'loss/train': 2.6249778270721436} 08/30/2021 14:00:44 - INFO - __main__ - Step 4518: {'lr': 0.0004996432619406543, 'samples': 867456, 'steps': 4517, 'loss/train': 1.8309979438781738} 08/30/2021 14:00:44 - INFO - __main__ - Step 4519: {'lr': 0.0004996429784889458, 'samples': 867648, 'steps': 4518, 'loss/train': 3.550863742828369} 08/30/2021 14:00:44 - INFO - __main__ - Step 4520: {'lr': 0.000499642694924752, 'samples': 867840, 'steps': 4519, 'loss/train': 2.6422226428985596} 08/30/2021 14:00:45 - INFO - __main__ - Step 4521: {'lr': 0.000499642411248073, 'samples': 868032, 'steps': 4520, 'loss/train': 1.8086737394332886} 08/30/2021 14:00:46 - INFO - __main__ - Step 4522: {'lr': 0.0004996421274589091, 'samples': 868224, 'steps': 4521, 'loss/train': 2.4225997924804688} 08/30/2021 14:00:47 - INFO - __main__ - Step 4523: {'lr': 0.0004996418435572603, 'samples': 868416, 'steps': 4522, 'loss/train': 4.092549800872803} 08/30/2021 14:00:47 - INFO - __main__ - Step 4524: {'lr': 0.0004996415595431267, 'samples': 868608, 'steps': 4523, 'loss/train': 2.29569149017334} 08/30/2021 14:00:48 - INFO - __main__ - Step 4525: {'lr': 0.0004996412754165084, 'samples': 868800, 'steps': 4524, 'loss/train': 3.1504571437835693} 08/30/2021 14:00:48 - INFO - __main__ - Step 4526: {'lr': 0.0004996409911774056, 'samples': 868992, 'steps': 4525, 'loss/train': 1.3656212091445923} 08/30/2021 14:00:48 - INFO - __main__ - Step 4527: {'lr': 0.0004996407068258186, 'samples': 869184, 'steps': 4526, 'loss/train': 2.564074993133545} 08/30/2021 14:00:50 - INFO - __main__ - Step 4528: {'lr': 0.0004996404223617471, 'samples': 869376, 'steps': 4527, 'loss/train': 2.1748273372650146} 08/30/2021 14:00:50 - INFO - __main__ - Step 4529: {'lr': 0.0004996401377851917, 'samples': 869568, 'steps': 4528, 'loss/train': 3.069153308868408} 08/30/2021 14:00:51 - INFO - __main__ - Step 4530: {'lr': 0.0004996398530961522, 'samples': 869760, 'steps': 4529, 'loss/train': 2.4911487102508545} 08/30/2021 14:00:51 - INFO - __main__ - Step 4531: {'lr': 0.0004996395682946288, 'samples': 869952, 'steps': 4530, 'loss/train': 2.353128433227539} 08/30/2021 14:00:51 - INFO - __main__ - Step 4532: {'lr': 0.0004996392833806217, 'samples': 870144, 'steps': 4531, 'loss/train': 2.1468746662139893} 08/30/2021 14:00:53 - INFO - __main__ - Step 4533: {'lr': 0.000499638998354131, 'samples': 870336, 'steps': 4532, 'loss/train': 2.4447340965270996} 08/30/2021 14:00:53 - INFO - __main__ - Step 4534: {'lr': 0.0004996387132151567, 'samples': 870528, 'steps': 4533, 'loss/train': 2.0875327587127686} 08/30/2021 14:00:54 - INFO - __main__ - Step 4535: {'lr': 0.0004996384279636993, 'samples': 870720, 'steps': 4534, 'loss/train': 2.412013053894043} 08/30/2021 14:00:54 - INFO - __main__ - Step 4536: {'lr': 0.0004996381425997584, 'samples': 870912, 'steps': 4535, 'loss/train': 2.2420294284820557} 08/30/2021 14:00:55 - INFO - __main__ - Step 4537: {'lr': 0.0004996378571233347, 'samples': 871104, 'steps': 4536, 'loss/train': 2.9002840518951416} 08/30/2021 14:00:55 - INFO - __main__ - Step 4538: {'lr': 0.0004996375715344278, 'samples': 871296, 'steps': 4537, 'loss/train': 2.5866057872772217} 08/30/2021 14:00:56 - INFO - __main__ - Step 4539: {'lr': 0.0004996372858330382, 'samples': 871488, 'steps': 4538, 'loss/train': 2.988987922668457} 08/30/2021 14:00:57 - INFO - __main__ - Step 4540: {'lr': 0.0004996370000191657, 'samples': 871680, 'steps': 4539, 'loss/train': 1.8763577938079834} 08/30/2021 14:00:57 - INFO - __main__ - Step 4541: {'lr': 0.0004996367140928107, 'samples': 871872, 'steps': 4540, 'loss/train': 2.400172710418701} 08/30/2021 14:00:58 - INFO - __main__ - Step 4542: {'lr': 0.0004996364280539734, 'samples': 872064, 'steps': 4541, 'loss/train': 2.4988865852355957} 08/30/2021 14:00:58 - INFO - __main__ - Step 4543: {'lr': 0.0004996361419026537, 'samples': 872256, 'steps': 4542, 'loss/train': 2.4307539463043213} 08/30/2021 14:01:00 - INFO - __main__ - Step 4544: {'lr': 0.0004996358556388518, 'samples': 872448, 'steps': 4543, 'loss/train': 2.4443089962005615} 08/30/2021 14:01:00 - INFO - __main__ - Step 4545: {'lr': 0.0004996355692625678, 'samples': 872640, 'steps': 4544, 'loss/train': 1.9704921245574951} 08/30/2021 14:01:01 - INFO - __main__ - Step 4546: {'lr': 0.0004996352827738018, 'samples': 872832, 'steps': 4545, 'loss/train': 2.219630718231201} 08/30/2021 14:01:01 - INFO - __main__ - Step 4547: {'lr': 0.0004996349961725542, 'samples': 873024, 'steps': 4546, 'loss/train': 2.1464083194732666} 08/30/2021 14:01:01 - INFO - __main__ - Step 4548: {'lr': 0.0004996347094588247, 'samples': 873216, 'steps': 4547, 'loss/train': 1.0339703559875488} 08/30/2021 14:01:02 - INFO - __main__ - Step 4549: {'lr': 0.0004996344226326137, 'samples': 873408, 'steps': 4548, 'loss/train': 0.8882812857627869} 08/30/2021 14:01:03 - INFO - __main__ - Step 4550: {'lr': 0.0004996341356939214, 'samples': 873600, 'steps': 4549, 'loss/train': 2.229863166809082} 08/30/2021 14:01:04 - INFO - __main__ - Step 4551: {'lr': 0.0004996338486427477, 'samples': 873792, 'steps': 4550, 'loss/train': 2.621331214904785} 08/30/2021 14:01:04 - INFO - __main__ - Step 4552: {'lr': 0.0004996335614790929, 'samples': 873984, 'steps': 4551, 'loss/train': 2.852511167526245} 08/30/2021 14:01:04 - INFO - __main__ - Step 4553: {'lr': 0.0004996332742029571, 'samples': 874176, 'steps': 4552, 'loss/train': 2.0260066986083984} 08/30/2021 14:01:05 - INFO - __main__ - Step 4554: {'lr': 0.0004996329868143404, 'samples': 874368, 'steps': 4553, 'loss/train': 2.789266586303711} 08/30/2021 14:01:06 - INFO - __main__ - Step 4555: {'lr': 0.0004996326993132428, 'samples': 874560, 'steps': 4554, 'loss/train': 2.3618829250335693} 08/30/2021 14:01:07 - INFO - __main__ - Step 4556: {'lr': 0.0004996324116996647, 'samples': 874752, 'steps': 4555, 'loss/train': 2.7693419456481934} 08/30/2021 14:01:07 - INFO - __main__ - Step 4557: {'lr': 0.0004996321239736059, 'samples': 874944, 'steps': 4556, 'loss/train': 2.4524588584899902} 08/30/2021 14:01:07 - INFO - __main__ - Step 4558: {'lr': 0.000499631836135067, 'samples': 875136, 'steps': 4557, 'loss/train': 2.46193265914917} 08/30/2021 14:01:08 - INFO - __main__ - Step 4559: {'lr': 0.0004996315481840476, 'samples': 875328, 'steps': 4558, 'loss/train': 2.47141432762146} 08/30/2021 14:01:10 - INFO - __main__ - Step 4560: {'lr': 0.0004996312601205482, 'samples': 875520, 'steps': 4559, 'loss/train': 2.2694461345672607} 08/30/2021 14:01:10 - INFO - __main__ - Step 4561: {'lr': 0.0004996309719445687, 'samples': 875712, 'steps': 4560, 'loss/train': 1.6245360374450684} 08/30/2021 14:01:11 - INFO - __main__ - Step 4562: {'lr': 0.0004996306836561094, 'samples': 875904, 'steps': 4561, 'loss/train': 2.070373058319092} 08/30/2021 14:01:11 - INFO - __main__ - Step 4563: {'lr': 0.0004996303952551704, 'samples': 876096, 'steps': 4562, 'loss/train': 2.3879058361053467} 08/30/2021 14:01:11 - INFO - __main__ - Step 4564: {'lr': 0.0004996301067417517, 'samples': 876288, 'steps': 4563, 'loss/train': 2.5300660133361816} 08/30/2021 14:01:13 - INFO - __main__ - Step 4565: {'lr': 0.0004996298181158536, 'samples': 876480, 'steps': 4564, 'loss/train': 2.0309441089630127} 08/30/2021 14:01:13 - INFO - __main__ - Step 4566: {'lr': 0.0004996295293774762, 'samples': 876672, 'steps': 4565, 'loss/train': 2.1152758598327637} 08/30/2021 14:01:13 - INFO - __main__ - Step 4567: {'lr': 0.0004996292405266195, 'samples': 876864, 'steps': 4566, 'loss/train': 2.372183322906494} 08/30/2021 14:01:14 - INFO - __main__ - Step 4568: {'lr': 0.0004996289515632838, 'samples': 877056, 'steps': 4567, 'loss/train': 2.0528564453125} 08/30/2021 14:01:14 - INFO - __main__ - Step 4569: {'lr': 0.0004996286624874691, 'samples': 877248, 'steps': 4568, 'loss/train': 2.6889450550079346} 08/30/2021 14:01:16 - INFO - __main__ - Step 4570: {'lr': 0.0004996283732991755, 'samples': 877440, 'steps': 4569, 'loss/train': 2.3121769428253174} 08/30/2021 14:01:16 - INFO - __main__ - Step 4571: {'lr': 0.0004996280839984033, 'samples': 877632, 'steps': 4570, 'loss/train': 2.4112284183502197} 08/30/2021 14:01:17 - INFO - __main__ - Step 4572: {'lr': 0.0004996277945851525, 'samples': 877824, 'steps': 4571, 'loss/train': 2.571039915084839} 08/30/2021 14:01:17 - INFO - __main__ - Step 4573: {'lr': 0.0004996275050594233, 'samples': 878016, 'steps': 4572, 'loss/train': 2.2443714141845703} 08/30/2021 14:01:17 - INFO - __main__ - Step 4574: {'lr': 0.0004996272154212158, 'samples': 878208, 'steps': 4573, 'loss/train': 2.3098435401916504} 08/30/2021 14:01:19 - INFO - __main__ - Step 4575: {'lr': 0.0004996269256705301, 'samples': 878400, 'steps': 4574, 'loss/train': 1.4533641338348389} 08/30/2021 14:01:19 - INFO - __main__ - Step 4576: {'lr': 0.0004996266358073664, 'samples': 878592, 'steps': 4575, 'loss/train': 1.7222477197647095} 08/30/2021 14:01:20 - INFO - __main__ - Step 4577: {'lr': 0.0004996263458317248, 'samples': 878784, 'steps': 4576, 'loss/train': 2.734583854675293} 08/30/2021 14:01:20 - INFO - __main__ - Step 4578: {'lr': 0.0004996260557436053, 'samples': 878976, 'steps': 4577, 'loss/train': 2.314223289489746} 08/30/2021 14:01:20 - INFO - __main__ - Step 4579: {'lr': 0.0004996257655430083, 'samples': 879168, 'steps': 4578, 'loss/train': 2.07610821723938} 08/30/2021 14:01:22 - INFO - __main__ - Step 4580: {'lr': 0.0004996254752299337, 'samples': 879360, 'steps': 4579, 'loss/train': 2.4870107173919678} 08/30/2021 14:01:22 - INFO - __main__ - Step 4581: {'lr': 0.0004996251848043817, 'samples': 879552, 'steps': 4580, 'loss/train': 2.2557332515716553} 08/30/2021 14:01:23 - INFO - __main__ - Step 4582: {'lr': 0.0004996248942663525, 'samples': 879744, 'steps': 4581, 'loss/train': 3.572296380996704} 08/30/2021 14:01:23 - INFO - __main__ - Step 4583: {'lr': 0.000499624603615846, 'samples': 879936, 'steps': 4582, 'loss/train': 2.7815513610839844} 08/30/2021 14:01:23 - INFO - __main__ - Step 4584: {'lr': 0.0004996243128528628, 'samples': 880128, 'steps': 4583, 'loss/train': 2.4769766330718994} 08/30/2021 14:01:24 - INFO - __main__ - Step 4585: {'lr': 0.0004996240219774025, 'samples': 880320, 'steps': 4584, 'loss/train': 1.7290468215942383} 08/30/2021 14:01:25 - INFO - __main__ - Step 4586: {'lr': 0.0004996237309894656, 'samples': 880512, 'steps': 4585, 'loss/train': 2.123121500015259} 08/30/2021 14:01:26 - INFO - __main__ - Step 4587: {'lr': 0.0004996234398890521, 'samples': 880704, 'steps': 4586, 'loss/train': 1.958060622215271} 08/30/2021 14:01:26 - INFO - __main__ - Step 4588: {'lr': 0.000499623148676162, 'samples': 880896, 'steps': 4587, 'loss/train': 2.0216751098632812} 08/30/2021 14:01:26 - INFO - __main__ - Step 4589: {'lr': 0.0004996228573507957, 'samples': 881088, 'steps': 4588, 'loss/train': 1.9924323558807373} 08/30/2021 14:01:27 - INFO - __main__ - Step 4590: {'lr': 0.0004996225659129531, 'samples': 881280, 'steps': 4589, 'loss/train': 1.249950885772705} 08/30/2021 14:01:28 - INFO - __main__ - Step 4591: {'lr': 0.0004996222743626345, 'samples': 881472, 'steps': 4590, 'loss/train': 0.6270982027053833} 08/30/2021 14:01:29 - INFO - __main__ - Step 4592: {'lr': 0.0004996219826998399, 'samples': 881664, 'steps': 4591, 'loss/train': 2.2480950355529785} 08/30/2021 14:01:29 - INFO - __main__ - Step 4593: {'lr': 0.0004996216909245695, 'samples': 881856, 'steps': 4592, 'loss/train': 2.091141700744629} 08/30/2021 14:01:30 - INFO - __main__ - Step 4594: {'lr': 0.0004996213990368234, 'samples': 882048, 'steps': 4593, 'loss/train': 1.9925917387008667} 08/30/2021 14:01:30 - INFO - __main__ - Step 4595: {'lr': 0.0004996211070366018, 'samples': 882240, 'steps': 4594, 'loss/train': 2.223419427871704} 08/30/2021 14:01:31 - INFO - __main__ - Step 4596: {'lr': 0.0004996208149239047, 'samples': 882432, 'steps': 4595, 'loss/train': 2.09906005859375} 08/30/2021 14:01:32 - INFO - __main__ - Step 4597: {'lr': 0.0004996205226987324, 'samples': 882624, 'steps': 4596, 'loss/train': 2.025024652481079} 08/30/2021 14:01:32 - INFO - __main__ - Step 4598: {'lr': 0.0004996202303610849, 'samples': 882816, 'steps': 4597, 'loss/train': 2.3278818130493164} 08/30/2021 14:01:32 - INFO - __main__ - Step 4599: {'lr': 0.0004996199379109624, 'samples': 883008, 'steps': 4598, 'loss/train': 2.1262285709381104} 08/30/2021 14:01:33 - INFO - __main__ - Step 4600: {'lr': 0.000499619645348365, 'samples': 883200, 'steps': 4599, 'loss/train': 1.6696217060089111} 08/30/2021 14:01:35 - INFO - __main__ - Step 4601: {'lr': 0.0004996193526732929, 'samples': 883392, 'steps': 4600, 'loss/train': 1.9249932765960693} 08/30/2021 14:01:36 - INFO - __main__ - Step 4602: {'lr': 0.0004996190598857461, 'samples': 883584, 'steps': 4601, 'loss/train': 2.2383718490600586} 08/30/2021 14:01:36 - INFO - __main__ - Step 4603: {'lr': 0.0004996187669857247, 'samples': 883776, 'steps': 4602, 'loss/train': 2.4671871662139893} 08/30/2021 14:01:36 - INFO - __main__ - Step 4604: {'lr': 0.0004996184739732291, 'samples': 883968, 'steps': 4603, 'loss/train': 3.1720287799835205} 08/30/2021 14:01:37 - INFO - __main__ - Step 4605: {'lr': 0.0004996181808482592, 'samples': 884160, 'steps': 4604, 'loss/train': 4.191840171813965} 08/30/2021 14:01:37 - INFO - __main__ - Step 4606: {'lr': 0.0004996178876108152, 'samples': 884352, 'steps': 4605, 'loss/train': 2.343764543533325} 08/30/2021 14:01:37 - INFO - __main__ - Step 4607: {'lr': 0.0004996175942608973, 'samples': 884544, 'steps': 4606, 'loss/train': 1.724738597869873} 08/30/2021 14:01:39 - INFO - __main__ - Step 4608: {'lr': 0.0004996173007985055, 'samples': 884736, 'steps': 4607, 'loss/train': 2.340036630630493} 08/30/2021 14:01:40 - INFO - __main__ - Step 4609: {'lr': 0.00049961700722364, 'samples': 884928, 'steps': 4608, 'loss/train': 2.5888867378234863} 08/30/2021 14:01:40 - INFO - __main__ - Step 4610: {'lr': 0.0004996167135363009, 'samples': 885120, 'steps': 4609, 'loss/train': 2.327427864074707} 08/30/2021 14:01:41 - INFO - __main__ - Step 4611: {'lr': 0.0004996164197364884, 'samples': 885312, 'steps': 4610, 'loss/train': 2.3598992824554443} 08/30/2021 14:01:41 - INFO - __main__ - Step 4612: {'lr': 0.0004996161258242025, 'samples': 885504, 'steps': 4611, 'loss/train': 2.2096822261810303} 08/30/2021 14:01:43 - INFO - __main__ - Step 4613: {'lr': 0.0004996158317994436, 'samples': 885696, 'steps': 4612, 'loss/train': 2.1788270473480225} 08/30/2021 14:01:43 - INFO - __main__ - Step 4614: {'lr': 0.0004996155376622115, 'samples': 885888, 'steps': 4613, 'loss/train': 3.035369873046875} 08/30/2021 14:01:43 - INFO - __main__ - Step 4615: {'lr': 0.0004996152434125066, 'samples': 886080, 'steps': 4614, 'loss/train': 2.6611716747283936} 08/30/2021 14:01:44 - INFO - __main__ - Step 4616: {'lr': 0.0004996149490503289, 'samples': 886272, 'steps': 4615, 'loss/train': 2.558361291885376} 08/30/2021 14:01:44 - INFO - __main__ - Step 4617: {'lr': 0.0004996146545756786, 'samples': 886464, 'steps': 4616, 'loss/train': 1.5009498596191406} 08/30/2021 14:01:45 - INFO - __main__ - Step 4618: {'lr': 0.0004996143599885557, 'samples': 886656, 'steps': 4617, 'loss/train': 2.051567554473877} 08/30/2021 14:01:46 - INFO - __main__ - Step 4619: {'lr': 0.0004996140652889603, 'samples': 886848, 'steps': 4618, 'loss/train': 2.0170814990997314} 08/30/2021 14:01:46 - INFO - __main__ - Step 4620: {'lr': 0.0004996137704768929, 'samples': 887040, 'steps': 4619, 'loss/train': 2.647442579269409} 08/30/2021 14:01:47 - INFO - __main__ - Step 4621: {'lr': 0.0004996134755523532, 'samples': 887232, 'steps': 4620, 'loss/train': 2.3504109382629395} 08/30/2021 14:01:47 - INFO - __main__ - Step 4622: {'lr': 0.0004996131805153417, 'samples': 887424, 'steps': 4621, 'loss/train': 2.1917972564697266} 08/30/2021 14:01:49 - INFO - __main__ - Step 4623: {'lr': 0.0004996128853658583, 'samples': 887616, 'steps': 4622, 'loss/train': 2.2604334354400635} 08/30/2021 14:01:49 - INFO - __main__ - Step 4624: {'lr': 0.0004996125901039031, 'samples': 887808, 'steps': 4623, 'loss/train': 2.1874806880950928} 08/30/2021 14:01:50 - INFO - __main__ - Step 4625: {'lr': 0.0004996122947294764, 'samples': 888000, 'steps': 4624, 'loss/train': 1.9336739778518677} 08/30/2021 14:01:50 - INFO - __main__ - Step 4626: {'lr': 0.0004996119992425782, 'samples': 888192, 'steps': 4625, 'loss/train': 2.149197578430176} 08/30/2021 14:01:50 - INFO - __main__ - Step 4627: {'lr': 0.0004996117036432087, 'samples': 888384, 'steps': 4626, 'loss/train': 0.39136800169944763} 08/30/2021 14:01:52 - INFO - __main__ - Step 4628: {'lr': 0.000499611407931368, 'samples': 888576, 'steps': 4627, 'loss/train': 2.2546849250793457} 08/30/2021 14:01:52 - INFO - __main__ - Step 4629: {'lr': 0.0004996111121070562, 'samples': 888768, 'steps': 4628, 'loss/train': 2.2915778160095215} 08/30/2021 14:01:53 - INFO - __main__ - Step 4630: {'lr': 0.0004996108161702736, 'samples': 888960, 'steps': 4629, 'loss/train': 1.5151708126068115} 08/30/2021 14:01:53 - INFO - __main__ - Step 4631: {'lr': 0.0004996105201210202, 'samples': 889152, 'steps': 4630, 'loss/train': 2.403064727783203} 08/30/2021 14:01:53 - INFO - __main__ - Step 4632: {'lr': 0.0004996102239592961, 'samples': 889344, 'steps': 4631, 'loss/train': 2.241124153137207} 08/30/2021 14:01:54 - INFO - __main__ - Step 4633: {'lr': 0.0004996099276851015, 'samples': 889536, 'steps': 4632, 'loss/train': 2.1955511569976807} 08/30/2021 14:01:55 - INFO - __main__ - Step 4634: {'lr': 0.0004996096312984365, 'samples': 889728, 'steps': 4633, 'loss/train': 2.775601387023926} 08/30/2021 14:01:56 - INFO - __main__ - Step 4635: {'lr': 0.0004996093347993013, 'samples': 889920, 'steps': 4634, 'loss/train': 2.951205253601074} 08/30/2021 14:01:56 - INFO - __main__ - Step 4636: {'lr': 0.000499609038187696, 'samples': 890112, 'steps': 4635, 'loss/train': 2.262634515762329} 08/30/2021 14:01:56 - INFO - __main__ - Step 4637: {'lr': 0.0004996087414636207, 'samples': 890304, 'steps': 4636, 'loss/train': 2.2803754806518555} 08/30/2021 14:01:57 - INFO - __main__ - Step 4638: {'lr': 0.0004996084446270755, 'samples': 890496, 'steps': 4637, 'loss/train': 1.7295838594436646} 08/30/2021 14:01:58 - INFO - __main__ - Step 4639: {'lr': 0.0004996081476780607, 'samples': 890688, 'steps': 4638, 'loss/train': 2.653325319290161} 08/30/2021 14:01:59 - INFO - __main__ - Step 4640: {'lr': 0.0004996078506165762, 'samples': 890880, 'steps': 4639, 'loss/train': 2.3338510990142822} 08/30/2021 14:01:59 - INFO - __main__ - Step 4641: {'lr': 0.0004996075534426222, 'samples': 891072, 'steps': 4640, 'loss/train': 2.238651990890503} 08/30/2021 14:01:59 - INFO - __main__ - Step 4642: {'lr': 0.000499607256156199, 'samples': 891264, 'steps': 4641, 'loss/train': 2.66705584526062} 08/30/2021 14:02:00 - INFO - __main__ - Step 4643: {'lr': 0.0004996069587573067, 'samples': 891456, 'steps': 4642, 'loss/train': 2.448281764984131} 08/30/2021 14:02:01 - INFO - __main__ - Step 4644: {'lr': 0.0004996066612459452, 'samples': 891648, 'steps': 4643, 'loss/train': 2.4534547328948975} 08/30/2021 14:02:02 - INFO - __main__ - Step 4645: {'lr': 0.0004996063636221148, 'samples': 891840, 'steps': 4644, 'loss/train': 2.2594292163848877} 08/30/2021 14:02:02 - INFO - __main__ - Step 4646: {'lr': 0.0004996060658858158, 'samples': 892032, 'steps': 4645, 'loss/train': 2.293121814727783} 08/30/2021 14:02:02 - INFO - __main__ - Step 4647: {'lr': 0.000499605768037048, 'samples': 892224, 'steps': 4646, 'loss/train': 2.6149797439575195} 08/30/2021 14:02:03 - INFO - __main__ - Step 4648: {'lr': 0.0004996054700758117, 'samples': 892416, 'steps': 4647, 'loss/train': 2.524472236633301} 08/30/2021 14:02:04 - INFO - __main__ - Step 4649: {'lr': 0.0004996051720021071, 'samples': 892608, 'steps': 4648, 'loss/train': 1.813582420349121} 08/30/2021 14:02:05 - INFO - __main__ - Step 4650: {'lr': 0.0004996048738159342, 'samples': 892800, 'steps': 4649, 'loss/train': 3.308600664138794} 08/30/2021 14:02:05 - INFO - __main__ - Step 4651: {'lr': 0.0004996045755172932, 'samples': 892992, 'steps': 4650, 'loss/train': 1.810467004776001} 08/30/2021 14:02:05 - INFO - __main__ - Step 4652: {'lr': 0.0004996042771061843, 'samples': 893184, 'steps': 4651, 'loss/train': 2.401333808898926} 08/30/2021 14:02:06 - INFO - __main__ - Step 4653: {'lr': 0.0004996039785826075, 'samples': 893376, 'steps': 4652, 'loss/train': 2.4568803310394287} 08/30/2021 14:02:07 - INFO - __main__ - Step 4654: {'lr': 0.000499603679946563, 'samples': 893568, 'steps': 4653, 'loss/train': 2.008197784423828} 08/30/2021 14:02:08 - INFO - __main__ - Step 4655: {'lr': 0.0004996033811980509, 'samples': 893760, 'steps': 4654, 'loss/train': 2.252939462661743} 08/30/2021 14:02:08 - INFO - __main__ - Step 4656: {'lr': 0.0004996030823370715, 'samples': 893952, 'steps': 4655, 'loss/train': 2.41216778755188} 08/30/2021 14:02:08 - INFO - __main__ - Step 4657: {'lr': 0.0004996027833636247, 'samples': 894144, 'steps': 4656, 'loss/train': 2.4887020587921143} 08/30/2021 14:02:09 - INFO - __main__ - Step 4658: {'lr': 0.0004996024842777106, 'samples': 894336, 'steps': 4657, 'loss/train': 1.7159894704818726} 08/30/2021 14:02:10 - INFO - __main__ - Step 4659: {'lr': 0.0004996021850793297, 'samples': 894528, 'steps': 4658, 'loss/train': 2.5552608966827393} 08/30/2021 14:02:11 - INFO - __main__ - Step 4660: {'lr': 0.0004996018857684818, 'samples': 894720, 'steps': 4659, 'loss/train': 2.448089838027954} 08/30/2021 14:02:11 - INFO - __main__ - Step 4661: {'lr': 0.0004996015863451672, 'samples': 894912, 'steps': 4660, 'loss/train': 2.5309102535247803} 08/30/2021 14:02:11 - INFO - __main__ - Step 4662: {'lr': 0.0004996012868093859, 'samples': 895104, 'steps': 4661, 'loss/train': 2.3204269409179688} 08/30/2021 14:02:12 - INFO - __main__ - Step 4663: {'lr': 0.0004996009871611382, 'samples': 895296, 'steps': 4662, 'loss/train': 1.337915301322937} 08/30/2021 14:02:14 - INFO - __main__ - Step 4664: {'lr': 0.0004996006874004241, 'samples': 895488, 'steps': 4663, 'loss/train': 2.4208292961120605} 08/30/2021 14:02:14 - INFO - __main__ - Step 4665: {'lr': 0.0004996003875272438, 'samples': 895680, 'steps': 4664, 'loss/train': 1.433829665184021} 08/30/2021 14:02:15 - INFO - __main__ - Step 4666: {'lr': 0.0004996000875415973, 'samples': 895872, 'steps': 4665, 'loss/train': 1.977731466293335} 08/30/2021 14:02:15 - INFO - __main__ - Step 4667: {'lr': 0.000499599787443485, 'samples': 896064, 'steps': 4666, 'loss/train': 2.47998309135437} 08/30/2021 14:02:16 - INFO - __main__ - Step 4668: {'lr': 0.0004995994872329069, 'samples': 896256, 'steps': 4667, 'loss/train': 1.9149500131607056} 08/30/2021 14:02:16 - INFO - __main__ - Step 4669: {'lr': 0.000499599186909863, 'samples': 896448, 'steps': 4668, 'loss/train': 1.824616551399231} 08/30/2021 14:02:17 - INFO - __main__ - Step 4670: {'lr': 0.0004995988864743536, 'samples': 896640, 'steps': 4669, 'loss/train': 3.030540943145752} 08/30/2021 14:02:18 - INFO - __main__ - Step 4671: {'lr': 0.0004995985859263789, 'samples': 896832, 'steps': 4670, 'loss/train': 2.6624813079833984} 08/30/2021 14:02:18 - INFO - __main__ - Step 4672: {'lr': 0.0004995982852659388, 'samples': 897024, 'steps': 4671, 'loss/train': 2.7112202644348145} 08/30/2021 14:02:18 - INFO - __main__ - Step 4673: {'lr': 0.0004995979844930336, 'samples': 897216, 'steps': 4672, 'loss/train': 2.2876665592193604} 08/30/2021 14:02:19 - INFO - __main__ - Step 4674: {'lr': 0.0004995976836076635, 'samples': 897408, 'steps': 4673, 'loss/train': 2.294339895248413} 08/30/2021 14:02:21 - INFO - __main__ - Step 4675: {'lr': 0.0004995973826098283, 'samples': 897600, 'steps': 4674, 'loss/train': 2.1953768730163574} 08/30/2021 14:02:22 - INFO - __main__ - Step 4676: {'lr': 0.0004995970814995285, 'samples': 897792, 'steps': 4675, 'loss/train': 1.3137171268463135} 08/30/2021 14:02:22 - INFO - __main__ - Step 4677: {'lr': 0.0004995967802767641, 'samples': 897984, 'steps': 4676, 'loss/train': 3.6875035762786865} 08/30/2021 14:02:22 - INFO - __main__ - Step 4678: {'lr': 0.0004995964789415353, 'samples': 898176, 'steps': 4677, 'loss/train': 1.8820013999938965} 08/30/2021 14:02:23 - INFO - __main__ - Step 4679: {'lr': 0.0004995961774938423, 'samples': 898368, 'steps': 4678, 'loss/train': 2.1136579513549805} 08/30/2021 14:02:23 - INFO - __main__ - Step 4680: {'lr': 0.0004995958759336849, 'samples': 898560, 'steps': 4679, 'loss/train': 1.7372349500656128} 08/30/2021 14:02:25 - INFO - __main__ - Step 4681: {'lr': 0.0004995955742610635, 'samples': 898752, 'steps': 4680, 'loss/train': 0.45423734188079834} 08/30/2021 14:02:25 - INFO - __main__ - Step 4682: {'lr': 0.0004995952724759781, 'samples': 898944, 'steps': 4681, 'loss/train': 2.112457036972046} 08/30/2021 14:02:25 - INFO - __main__ - Step 4683: {'lr': 0.0004995949705784291, 'samples': 899136, 'steps': 4682, 'loss/train': 1.9973746538162231} 08/30/2021 14:02:26 - INFO - __main__ - Step 4684: {'lr': 0.0004995946685684164, 'samples': 899328, 'steps': 4683, 'loss/train': 3.928039789199829} 08/30/2021 14:02:26 - INFO - __main__ - Step 4685: {'lr': 0.0004995943664459401, 'samples': 899520, 'steps': 4684, 'loss/train': 2.448692560195923} 08/30/2021 14:02:28 - INFO - __main__ - Step 4686: {'lr': 0.0004995940642110005, 'samples': 899712, 'steps': 4685, 'loss/train': 2.1602401733398438} 08/30/2021 14:02:28 - INFO - __main__ - Step 4687: {'lr': 0.0004995937618635977, 'samples': 899904, 'steps': 4686, 'loss/train': 2.453596830368042} 08/30/2021 14:02:28 - INFO - __main__ - Step 4688: {'lr': 0.0004995934594037316, 'samples': 900096, 'steps': 4687, 'loss/train': 2.4329769611358643} 08/30/2021 14:02:29 - INFO - __main__ - Step 4689: {'lr': 0.0004995931568314028, 'samples': 900288, 'steps': 4688, 'loss/train': 2.3658831119537354} 08/30/2021 14:02:29 - INFO - __main__ - Step 4690: {'lr': 0.0004995928541466111, 'samples': 900480, 'steps': 4689, 'loss/train': 2.3486440181732178} 08/30/2021 14:02:31 - INFO - __main__ - Step 4691: {'lr': 0.0004995925513493567, 'samples': 900672, 'steps': 4690, 'loss/train': 5.228073596954346} 08/30/2021 14:02:31 - INFO - __main__ - Step 4692: {'lr': 0.0004995922484396397, 'samples': 900864, 'steps': 4691, 'loss/train': 2.1782376766204834} 08/30/2021 14:02:32 - INFO - __main__ - Step 4693: {'lr': 0.0004995919454174603, 'samples': 901056, 'steps': 4692, 'loss/train': 2.515242099761963} 08/30/2021 14:02:32 - INFO - __main__ - Step 4694: {'lr': 0.0004995916422828187, 'samples': 901248, 'steps': 4693, 'loss/train': 2.117107391357422} 08/30/2021 14:02:33 - INFO - __main__ - Step 4695: {'lr': 0.0004995913390357148, 'samples': 901440, 'steps': 4694, 'loss/train': 2.398838520050049} 08/30/2021 14:02:33 - INFO - __main__ - Step 4696: {'lr': 0.0004995910356761491, 'samples': 901632, 'steps': 4695, 'loss/train': 0.874934196472168} 08/30/2021 14:02:35 - INFO - __main__ - Step 4697: {'lr': 0.0004995907322041214, 'samples': 901824, 'steps': 4696, 'loss/train': 1.6412839889526367} 08/30/2021 14:02:35 - INFO - __main__ - Step 4698: {'lr': 0.000499590428619632, 'samples': 902016, 'steps': 4697, 'loss/train': 2.336991786956787} 08/30/2021 14:02:35 - INFO - __main__ - Step 4699: {'lr': 0.000499590124922681, 'samples': 902208, 'steps': 4698, 'loss/train': 1.6142579317092896} 08/30/2021 14:02:36 - INFO - __main__ - Step 4700: {'lr': 0.0004995898211132685, 'samples': 902400, 'steps': 4699, 'loss/train': 2.539201259613037} 08/30/2021 14:02:36 - INFO - __main__ - Step 4701: {'lr': 0.0004995895171913947, 'samples': 902592, 'steps': 4700, 'loss/train': 2.6473097801208496} 08/30/2021 14:02:38 - INFO - __main__ - Step 4702: {'lr': 0.0004995892131570598, 'samples': 902784, 'steps': 4701, 'loss/train': 2.2009053230285645} 08/30/2021 14:02:38 - INFO - __main__ - Step 4703: {'lr': 0.0004995889090102638, 'samples': 902976, 'steps': 4702, 'loss/train': 2.374619960784912} 08/30/2021 14:02:39 - INFO - __main__ - Step 4704: {'lr': 0.0004995886047510068, 'samples': 903168, 'steps': 4703, 'loss/train': 2.033463954925537} 08/30/2021 14:02:39 - INFO - __main__ - Step 4705: {'lr': 0.0004995883003792891, 'samples': 903360, 'steps': 4704, 'loss/train': 2.393458127975464} 08/30/2021 14:02:39 - INFO - __main__ - Step 4706: {'lr': 0.0004995879958951107, 'samples': 903552, 'steps': 4705, 'loss/train': 1.2720915079116821} 08/30/2021 14:02:41 - INFO - __main__ - Step 4707: {'lr': 0.0004995876912984719, 'samples': 903744, 'steps': 4706, 'loss/train': 1.4228672981262207} 08/30/2021 14:02:41 - INFO - __main__ - Step 4708: {'lr': 0.0004995873865893727, 'samples': 903936, 'steps': 4707, 'loss/train': 2.5425636768341064} 08/30/2021 14:02:42 - INFO - __main__ - Step 4709: {'lr': 0.0004995870817678133, 'samples': 904128, 'steps': 4708, 'loss/train': 2.343172550201416} 08/30/2021 14:02:42 - INFO - __main__ - Step 4710: {'lr': 0.0004995867768337938, 'samples': 904320, 'steps': 4709, 'loss/train': 1.9796204566955566} 08/30/2021 14:02:42 - INFO - __main__ - Step 4711: {'lr': 0.0004995864717873143, 'samples': 904512, 'steps': 4710, 'loss/train': 2.5738954544067383} 08/30/2021 14:02:44 - INFO - __main__ - Step 4712: {'lr': 0.000499586166628375, 'samples': 904704, 'steps': 4711, 'loss/train': 2.315624952316284} 08/30/2021 14:02:44 - INFO - __main__ - Step 4713: {'lr': 0.0004995858613569761, 'samples': 904896, 'steps': 4712, 'loss/train': 1.6377177238464355} 08/30/2021 14:02:45 - INFO - __main__ - Step 4714: {'lr': 0.0004995855559731176, 'samples': 905088, 'steps': 4713, 'loss/train': 2.1084823608398438} 08/30/2021 14:02:45 - INFO - __main__ - Step 4715: {'lr': 0.0004995852504767997, 'samples': 905280, 'steps': 4714, 'loss/train': 1.9919739961624146} 08/30/2021 14:02:45 - INFO - __main__ - Step 4716: {'lr': 0.0004995849448680225, 'samples': 905472, 'steps': 4715, 'loss/train': 2.2004289627075195} 08/30/2021 14:02:46 - INFO - __main__ - Step 4717: {'lr': 0.0004995846391467862, 'samples': 905664, 'steps': 4716, 'loss/train': 2.0319464206695557} 08/30/2021 14:02:48 - INFO - __main__ - Step 4718: {'lr': 0.000499584333313091, 'samples': 905856, 'steps': 4717, 'loss/train': 8.657270431518555} 08/30/2021 14:02:49 - INFO - __main__ - Step 4719: {'lr': 0.0004995840273669369, 'samples': 906048, 'steps': 4718, 'loss/train': 2.548557996749878} 08/30/2021 14:02:49 - INFO - __main__ - Step 4720: {'lr': 0.0004995837213083241, 'samples': 906240, 'steps': 4719, 'loss/train': 1.679852843284607} 08/30/2021 14:02:49 - INFO - __main__ - Step 4721: {'lr': 0.0004995834151372526, 'samples': 906432, 'steps': 4720, 'loss/train': 2.3638381958007812} 08/30/2021 14:02:50 - INFO - __main__ - Step 4722: {'lr': 0.0004995831088537229, 'samples': 906624, 'steps': 4721, 'loss/train': 3.4459497928619385} 08/30/2021 14:02:51 - INFO - __main__ - Step 4723: {'lr': 0.0004995828024577346, 'samples': 906816, 'steps': 4722, 'loss/train': 2.5729405879974365} 08/30/2021 14:02:52 - INFO - __main__ - Step 4724: {'lr': 0.0004995824959492884, 'samples': 907008, 'steps': 4723, 'loss/train': 2.4301981925964355} 08/30/2021 14:02:52 - INFO - __main__ - Step 4725: {'lr': 0.0004995821893283841, 'samples': 907200, 'steps': 4724, 'loss/train': 1.806684970855713} 08/30/2021 14:02:52 - INFO - __main__ - Step 4726: {'lr': 0.0004995818825950218, 'samples': 907392, 'steps': 4725, 'loss/train': 2.7768712043762207} 08/30/2021 14:02:53 - INFO - __main__ - Step 4727: {'lr': 0.0004995815757492019, 'samples': 907584, 'steps': 4726, 'loss/train': 2.3350353240966797} 08/30/2021 14:02:54 - INFO - __main__ - Step 4728: {'lr': 0.0004995812687909243, 'samples': 907776, 'steps': 4727, 'loss/train': 2.3573389053344727} 08/30/2021 14:02:55 - INFO - __main__ - Step 4729: {'lr': 0.0004995809617201894, 'samples': 907968, 'steps': 4728, 'loss/train': 2.105909585952759} 08/30/2021 14:02:55 - INFO - __main__ - Step 4730: {'lr': 0.000499580654536997, 'samples': 908160, 'steps': 4729, 'loss/train': 2.9305338859558105} 08/30/2021 14:02:56 - INFO - __main__ - Step 4731: {'lr': 0.0004995803472413474, 'samples': 908352, 'steps': 4730, 'loss/train': 1.8371176719665527} 08/30/2021 14:02:56 - INFO - __main__ - Step 4732: {'lr': 0.0004995800398332409, 'samples': 908544, 'steps': 4731, 'loss/train': 0.559933602809906} 08/30/2021 14:02:56 - INFO - __main__ - Step 4733: {'lr': 0.0004995797323126774, 'samples': 908736, 'steps': 4732, 'loss/train': 2.37628173828125} 08/30/2021 14:02:58 - INFO - __main__ - Step 4734: {'lr': 0.0004995794246796571, 'samples': 908928, 'steps': 4733, 'loss/train': 1.8568031787872314} 08/30/2021 14:02:58 - INFO - __main__ - Step 4735: {'lr': 0.0004995791169341801, 'samples': 909120, 'steps': 4734, 'loss/train': 2.468707799911499} 08/30/2021 14:02:59 - INFO - __main__ - Step 4736: {'lr': 0.0004995788090762467, 'samples': 909312, 'steps': 4735, 'loss/train': 2.731025218963623} 08/30/2021 14:02:59 - INFO - __main__ - Step 4737: {'lr': 0.000499578501105857, 'samples': 909504, 'steps': 4736, 'loss/train': 2.408590793609619} 08/30/2021 14:02:59 - INFO - __main__ - Step 4738: {'lr': 0.000499578193023011, 'samples': 909696, 'steps': 4737, 'loss/train': 2.308793067932129} 08/30/2021 14:03:01 - INFO - __main__ - Step 4739: {'lr': 0.0004995778848277088, 'samples': 909888, 'steps': 4738, 'loss/train': 2.059112548828125} 08/30/2021 14:03:01 - INFO - __main__ - Step 4740: {'lr': 0.0004995775765199509, 'samples': 910080, 'steps': 4739, 'loss/train': 2.3376755714416504} 08/30/2021 14:03:02 - INFO - __main__ - Step 4741: {'lr': 0.000499577268099737, 'samples': 910272, 'steps': 4740, 'loss/train': 2.1304550170898438} 08/30/2021 14:03:02 - INFO - __main__ - Step 4742: {'lr': 0.0004995769595670675, 'samples': 910464, 'steps': 4741, 'loss/train': 2.383237361907959} 08/30/2021 14:03:02 - INFO - __main__ - Step 4743: {'lr': 0.0004995766509219425, 'samples': 910656, 'steps': 4742, 'loss/train': 2.4115703105926514} 08/30/2021 14:03:04 - INFO - __main__ - Step 4744: {'lr': 0.0004995763421643621, 'samples': 910848, 'steps': 4743, 'loss/train': 2.3305840492248535} 08/30/2021 14:03:04 - INFO - __main__ - Step 4745: {'lr': 0.0004995760332943264, 'samples': 911040, 'steps': 4744, 'loss/train': 2.6110363006591797} 08/30/2021 14:03:05 - INFO - __main__ - Step 4746: {'lr': 0.0004995757243118356, 'samples': 911232, 'steps': 4745, 'loss/train': 2.169848918914795} 08/30/2021 14:03:05 - INFO - __main__ - Step 4747: {'lr': 0.0004995754152168899, 'samples': 911424, 'steps': 4746, 'loss/train': 1.4700475931167603} 08/30/2021 14:03:05 - INFO - __main__ - Step 4748: {'lr': 0.0004995751060094893, 'samples': 911616, 'steps': 4747, 'loss/train': 0.852035403251648} 08/30/2021 14:03:07 - INFO - __main__ - Step 4749: {'lr': 0.000499574796689634, 'samples': 911808, 'steps': 4748, 'loss/train': 1.8782111406326294} 08/30/2021 14:03:07 - INFO - __main__ - Step 4750: {'lr': 0.0004995744872573242, 'samples': 912000, 'steps': 4749, 'loss/train': 1.7904566526412964} 08/30/2021 14:03:08 - INFO - __main__ - Step 4751: {'lr': 0.00049957417771256, 'samples': 912192, 'steps': 4750, 'loss/train': 1.7794671058654785} 08/30/2021 14:03:08 - INFO - __main__ - Step 4752: {'lr': 0.0004995738680553415, 'samples': 912384, 'steps': 4751, 'loss/train': 1.608269214630127} 08/30/2021 14:03:08 - INFO - __main__ - Step 4753: {'lr': 0.0004995735582856689, 'samples': 912576, 'steps': 4752, 'loss/train': 2.1375675201416016} 08/30/2021 14:03:10 - INFO - __main__ - Step 4754: {'lr': 0.0004995732484035422, 'samples': 912768, 'steps': 4753, 'loss/train': 2.6623668670654297} 08/30/2021 14:03:10 - INFO - __main__ - Step 4755: {'lr': 0.0004995729384089618, 'samples': 912960, 'steps': 4754, 'loss/train': 2.3186020851135254} 08/30/2021 14:03:11 - INFO - __main__ - Step 4756: {'lr': 0.0004995726283019275, 'samples': 913152, 'steps': 4755, 'loss/train': 2.0165352821350098} 08/30/2021 14:03:11 - INFO - __main__ - Step 4757: {'lr': 0.0004995723180824397, 'samples': 913344, 'steps': 4756, 'loss/train': 1.5398626327514648} 08/30/2021 14:03:11 - INFO - __main__ - Step 4758: {'lr': 0.0004995720077504986, 'samples': 913536, 'steps': 4757, 'loss/train': 2.2841081619262695} 08/30/2021 14:03:12 - INFO - __main__ - Step 4759: {'lr': 0.0004995716973061041, 'samples': 913728, 'steps': 4758, 'loss/train': 2.377220869064331} 08/30/2021 14:03:13 - INFO - __main__ - Step 4760: {'lr': 0.0004995713867492564, 'samples': 913920, 'steps': 4759, 'loss/train': 2.4824860095977783} 08/30/2021 14:03:14 - INFO - __main__ - Step 4761: {'lr': 0.0004995710760799557, 'samples': 914112, 'steps': 4760, 'loss/train': 1.7118556499481201} 08/30/2021 14:03:14 - INFO - __main__ - Step 4762: {'lr': 0.0004995707652982022, 'samples': 914304, 'steps': 4761, 'loss/train': 2.071098804473877} 08/30/2021 14:03:15 - INFO - __main__ - Step 4763: {'lr': 0.0004995704544039958, 'samples': 914496, 'steps': 4762, 'loss/train': 3.8153786659240723} 08/30/2021 14:03:15 - INFO - __main__ - Step 4764: {'lr': 0.0004995701433973369, 'samples': 914688, 'steps': 4763, 'loss/train': 2.1583616733551025} 08/30/2021 14:03:16 - INFO - __main__ - Step 4765: {'lr': 0.0004995698322782257, 'samples': 914880, 'steps': 4764, 'loss/train': 2.505201578140259} 08/30/2021 14:03:17 - INFO - __main__ - Step 4766: {'lr': 0.0004995695210466619, 'samples': 915072, 'steps': 4765, 'loss/train': 2.2153713703155518} 08/30/2021 14:03:17 - INFO - __main__ - Step 4767: {'lr': 0.0004995692097026461, 'samples': 915264, 'steps': 4766, 'loss/train': 2.196841239929199} 08/30/2021 14:03:18 - INFO - __main__ - Step 4768: {'lr': 0.0004995688982461783, 'samples': 915456, 'steps': 4767, 'loss/train': 2.1606943607330322} 08/30/2021 14:03:18 - INFO - __main__ - Step 4769: {'lr': 0.0004995685866772586, 'samples': 915648, 'steps': 4768, 'loss/train': 1.0300918817520142} 08/30/2021 14:03:20 - INFO - __main__ - Step 4770: {'lr': 0.000499568274995887, 'samples': 915840, 'steps': 4769, 'loss/train': 2.6956491470336914} 08/30/2021 14:03:20 - INFO - __main__ - Step 4771: {'lr': 0.0004995679632020639, 'samples': 916032, 'steps': 4770, 'loss/train': 1.5897364616394043} 08/30/2021 14:03:20 - INFO - __main__ - Step 4772: {'lr': 0.0004995676512957892, 'samples': 916224, 'steps': 4771, 'loss/train': 2.4463539123535156} 08/30/2021 14:03:21 - INFO - __main__ - Step 4773: {'lr': 0.0004995673392770634, 'samples': 916416, 'steps': 4772, 'loss/train': 1.6611323356628418} 08/30/2021 14:03:21 - INFO - __main__ - Step 4774: {'lr': 0.0004995670271458863, 'samples': 916608, 'steps': 4773, 'loss/train': 2.0660533905029297} 08/30/2021 14:03:23 - INFO - __main__ - Step 4775: {'lr': 0.0004995667149022581, 'samples': 916800, 'steps': 4774, 'loss/train': 2.0716781616210938} 08/30/2021 14:03:24 - INFO - __main__ - Step 4776: {'lr': 0.000499566402546179, 'samples': 916992, 'steps': 4775, 'loss/train': 2.422713041305542} 08/30/2021 14:03:24 - INFO - __main__ - Step 4777: {'lr': 0.0004995660900776491, 'samples': 917184, 'steps': 4776, 'loss/train': 2.204787492752075} 08/30/2021 14:03:24 - INFO - __main__ - Step 4778: {'lr': 0.0004995657774966686, 'samples': 917376, 'steps': 4777, 'loss/train': 2.6138124465942383} 08/30/2021 14:03:25 - INFO - __main__ - Step 4779: {'lr': 0.0004995654648032377, 'samples': 917568, 'steps': 4778, 'loss/train': 2.557595729827881} 08/30/2021 14:03:26 - INFO - __main__ - Step 4780: {'lr': 0.0004995651519973563, 'samples': 917760, 'steps': 4779, 'loss/train': 1.4790884256362915} 08/30/2021 14:03:27 - INFO - __main__ - Step 4781: {'lr': 0.0004995648390790249, 'samples': 917952, 'steps': 4780, 'loss/train': 1.851643443107605} 08/30/2021 14:03:27 - INFO - __main__ - Step 4782: {'lr': 0.0004995645260482432, 'samples': 918144, 'steps': 4781, 'loss/train': 2.3874449729919434} 08/30/2021 14:03:27 - INFO - __main__ - Step 4783: {'lr': 0.0004995642129050117, 'samples': 918336, 'steps': 4782, 'loss/train': 2.0189919471740723} 08/30/2021 14:03:28 - INFO - __main__ - Step 4784: {'lr': 0.0004995638996493304, 'samples': 918528, 'steps': 4783, 'loss/train': 2.4560396671295166} 08/30/2021 14:03:28 - INFO - __main__ - Step 4785: {'lr': 0.0004995635862811994, 'samples': 918720, 'steps': 4784, 'loss/train': 1.907179355621338} 08/30/2021 14:03:30 - INFO - __main__ - Step 4786: {'lr': 0.000499563272800619, 'samples': 918912, 'steps': 4785, 'loss/train': 2.069049596786499} 08/30/2021 14:03:30 - INFO - __main__ - Step 4787: {'lr': 0.0004995629592075892, 'samples': 919104, 'steps': 4786, 'loss/train': 1.8719192743301392} 08/30/2021 14:03:30 - INFO - __main__ - Step 4788: {'lr': 0.0004995626455021101, 'samples': 919296, 'steps': 4787, 'loss/train': 2.1309146881103516} 08/30/2021 14:03:31 - INFO - __main__ - Step 4789: {'lr': 0.0004995623316841821, 'samples': 919488, 'steps': 4788, 'loss/train': 2.4332520961761475} 08/30/2021 14:03:31 - INFO - __main__ - Step 4790: {'lr': 0.0004995620177538051, 'samples': 919680, 'steps': 4789, 'loss/train': 2.584012746810913} 08/30/2021 14:03:33 - INFO - __main__ - Step 4791: {'lr': 0.0004995617037109792, 'samples': 919872, 'steps': 4790, 'loss/train': 2.0938055515289307} 08/30/2021 14:03:33 - INFO - __main__ - Step 4792: {'lr': 0.0004995613895557048, 'samples': 920064, 'steps': 4791, 'loss/train': 2.628089666366577} 08/30/2021 14:03:34 - INFO - __main__ - Step 4793: {'lr': 0.0004995610752879818, 'samples': 920256, 'steps': 4792, 'loss/train': 2.253495693206787} 08/30/2021 14:03:34 - INFO - __main__ - Step 4794: {'lr': 0.0004995607609078104, 'samples': 920448, 'steps': 4793, 'loss/train': 2.293809413909912} 08/30/2021 14:03:34 - INFO - __main__ - Step 4795: {'lr': 0.0004995604464151908, 'samples': 920640, 'steps': 4794, 'loss/train': 1.1303257942199707} 08/30/2021 14:03:36 - INFO - __main__ - Step 4796: {'lr': 0.0004995601318101231, 'samples': 920832, 'steps': 4795, 'loss/train': 1.8195961713790894} 08/30/2021 14:03:37 - INFO - __main__ - Step 4797: {'lr': 0.0004995598170926074, 'samples': 921024, 'steps': 4796, 'loss/train': 1.7572760581970215} 08/30/2021 14:03:37 - INFO - __main__ - Step 4798: {'lr': 0.000499559502262644, 'samples': 921216, 'steps': 4797, 'loss/train': 2.152740716934204} 08/30/2021 14:03:37 - INFO - __main__ - Step 4799: {'lr': 0.000499559187320233, 'samples': 921408, 'steps': 4798, 'loss/train': 2.2296159267425537} 08/30/2021 14:03:38 - INFO - __main__ - Step 4800: {'lr': 0.0004995588722653743, 'samples': 921600, 'steps': 4799, 'loss/train': 0.6443192362785339} 08/30/2021 14:03:38 - INFO - __main__ - Step 4801: {'lr': 0.0004995585570980684, 'samples': 921792, 'steps': 4800, 'loss/train': 2.578104257583618} 08/30/2021 14:03:40 - INFO - __main__ - Step 4802: {'lr': 0.0004995582418183151, 'samples': 921984, 'steps': 4801, 'loss/train': 2.2058041095733643} 08/30/2021 14:03:40 - INFO - __main__ - Step 4803: {'lr': 0.0004995579264261148, 'samples': 922176, 'steps': 4802, 'loss/train': 1.4003407955169678} 08/30/2021 14:03:40 - INFO - __main__ - Step 4804: {'lr': 0.0004995576109214676, 'samples': 922368, 'steps': 4803, 'loss/train': 2.4224884510040283} 08/30/2021 14:03:41 - INFO - __main__ - Step 4805: {'lr': 0.0004995572953043736, 'samples': 922560, 'steps': 4804, 'loss/train': 2.1731059551239014} 08/30/2021 14:03:41 - INFO - __main__ - Step 4806: {'lr': 0.0004995569795748328, 'samples': 922752, 'steps': 4805, 'loss/train': 2.401675224304199} 08/30/2021 14:03:43 - INFO - __main__ - Step 4807: {'lr': 0.0004995566637328456, 'samples': 922944, 'steps': 4806, 'loss/train': 2.5750410556793213} 08/30/2021 14:03:43 - INFO - __main__ - Step 4808: {'lr': 0.0004995563477784119, 'samples': 923136, 'steps': 4807, 'loss/train': 1.8233083486557007} 08/30/2021 14:03:44 - INFO - __main__ - Step 4809: {'lr': 0.000499556031711532, 'samples': 923328, 'steps': 4808, 'loss/train': 2.4176502227783203} 08/30/2021 14:03:44 - INFO - __main__ - Step 4810: {'lr': 0.000499555715532206, 'samples': 923520, 'steps': 4809, 'loss/train': 2.2716965675354004} 08/30/2021 14:03:44 - INFO - __main__ - Step 4811: {'lr': 0.0004995553992404342, 'samples': 923712, 'steps': 4810, 'loss/train': 2.182950973510742} 08/30/2021 14:03:45 - INFO - __main__ - Step 4812: {'lr': 0.0004995550828362163, 'samples': 923904, 'steps': 4811, 'loss/train': 1.1444370746612549} 08/30/2021 14:03:46 - INFO - __main__ - Step 4813: {'lr': 0.000499554766319553, 'samples': 924096, 'steps': 4812, 'loss/train': 3.355135202407837} 08/30/2021 14:03:47 - INFO - __main__ - Step 4814: {'lr': 0.0004995544496904441, 'samples': 924288, 'steps': 4813, 'loss/train': 1.8554887771606445} 08/30/2021 14:03:47 - INFO - __main__ - Step 4815: {'lr': 0.0004995541329488897, 'samples': 924480, 'steps': 4814, 'loss/train': 1.8497685194015503} 08/30/2021 14:03:48 - INFO - __main__ - Step 4816: {'lr': 0.0004995538160948901, 'samples': 924672, 'steps': 4815, 'loss/train': 2.6320436000823975} 08/30/2021 14:03:48 - INFO - __main__ - Step 4817: {'lr': 0.0004995534991284455, 'samples': 924864, 'steps': 4816, 'loss/train': 1.436744213104248} 08/30/2021 14:03:50 - INFO - __main__ - Step 4818: {'lr': 0.0004995531820495559, 'samples': 925056, 'steps': 4817, 'loss/train': 1.9512062072753906} 08/30/2021 14:03:50 - INFO - __main__ - Step 4819: {'lr': 0.0004995528648582214, 'samples': 925248, 'steps': 4818, 'loss/train': 2.3656439781188965} 08/30/2021 14:03:51 - INFO - __main__ - Step 4820: {'lr': 0.0004995525475544423, 'samples': 925440, 'steps': 4819, 'loss/train': 1.9629491567611694} 08/30/2021 14:03:51 - INFO - __main__ - Step 4821: {'lr': 0.0004995522301382187, 'samples': 925632, 'steps': 4820, 'loss/train': 2.170275926589966} 08/30/2021 14:03:51 - INFO - __main__ - Step 4822: {'lr': 0.0004995519126095506, 'samples': 925824, 'steps': 4821, 'loss/train': 2.4914565086364746} 08/30/2021 14:03:52 - INFO - __main__ - Step 4823: {'lr': 0.0004995515949684384, 'samples': 926016, 'steps': 4822, 'loss/train': 1.9531784057617188} 08/30/2021 14:03:53 - INFO - __main__ - Step 4824: {'lr': 0.000499551277214882, 'samples': 926208, 'steps': 4823, 'loss/train': 2.2391319274902344} 08/30/2021 14:03:54 - INFO - __main__ - Step 4825: {'lr': 0.0004995509593488818, 'samples': 926400, 'steps': 4824, 'loss/train': 1.967274785041809} 08/30/2021 14:03:54 - INFO - __main__ - Step 4826: {'lr': 0.0004995506413704376, 'samples': 926592, 'steps': 4825, 'loss/train': 2.2904481887817383} 08/30/2021 14:03:54 - INFO - __main__ - Step 4827: {'lr': 0.0004995503232795498, 'samples': 926784, 'steps': 4826, 'loss/train': 1.8858319520950317} 08/30/2021 14:03:55 - INFO - __main__ - Step 4828: {'lr': 0.0004995500050762185, 'samples': 926976, 'steps': 4827, 'loss/train': 2.434027671813965} 08/30/2021 14:03:57 - INFO - __main__ - Step 4829: {'lr': 0.0004995496867604438, 'samples': 927168, 'steps': 4828, 'loss/train': 2.4201512336730957} 08/30/2021 14:03:57 - INFO - __main__ - Step 4830: {'lr': 0.0004995493683322259, 'samples': 927360, 'steps': 4829, 'loss/train': 3.496950149536133} 08/30/2021 14:03:58 - INFO - __main__ - Step 4831: {'lr': 0.0004995490497915649, 'samples': 927552, 'steps': 4830, 'loss/train': 3.0072968006134033} 08/30/2021 14:03:58 - INFO - __main__ - Step 4832: {'lr': 0.0004995487311384609, 'samples': 927744, 'steps': 4831, 'loss/train': 2.3867318630218506} 08/30/2021 14:03:59 - INFO - __main__ - Step 4833: {'lr': 0.0004995484123729141, 'samples': 927936, 'steps': 4832, 'loss/train': 1.9825752973556519} 08/30/2021 14:04:00 - INFO - __main__ - Step 4834: {'lr': 0.0004995480934949247, 'samples': 928128, 'steps': 4833, 'loss/train': 1.8303334712982178} 08/30/2021 14:04:01 - INFO - __main__ - Step 4835: {'lr': 0.0004995477745044927, 'samples': 928320, 'steps': 4834, 'loss/train': 2.512631893157959} 08/30/2021 14:04:01 - INFO - __main__ - Step 4836: {'lr': 0.0004995474554016184, 'samples': 928512, 'steps': 4835, 'loss/train': 1.1743768453598022} 08/30/2021 14:04:01 - INFO - __main__ - Step 4837: {'lr': 0.0004995471361863017, 'samples': 928704, 'steps': 4836, 'loss/train': 2.0064592361450195} 08/30/2021 14:04:02 - INFO - __main__ - Step 4838: {'lr': 0.0004995468168585431, 'samples': 928896, 'steps': 4837, 'loss/train': 2.3148019313812256} 08/30/2021 14:04:03 - INFO - __main__ - Step 4839: {'lr': 0.0004995464974183424, 'samples': 929088, 'steps': 4838, 'loss/train': 1.4140267372131348} 08/30/2021 14:04:04 - INFO - __main__ - Step 4840: {'lr': 0.0004995461778657002, 'samples': 929280, 'steps': 4839, 'loss/train': 2.034234046936035} 08/30/2021 14:04:04 - INFO - __main__ - Step 4841: {'lr': 0.000499545858200616, 'samples': 929472, 'steps': 4840, 'loss/train': 2.642103433609009} 08/30/2021 14:04:04 - INFO - __main__ - Step 4842: {'lr': 0.0004995455384230904, 'samples': 929664, 'steps': 4841, 'loss/train': 2.2454304695129395} 08/30/2021 14:04:05 - INFO - __main__ - Step 4843: {'lr': 0.0004995452185331235, 'samples': 929856, 'steps': 4842, 'loss/train': 1.9844597578048706} 08/30/2021 14:04:05 - INFO - __main__ - Step 4844: {'lr': 0.0004995448985307153, 'samples': 930048, 'steps': 4843, 'loss/train': 2.42919921875} 08/30/2021 14:04:07 - INFO - __main__ - Step 4845: {'lr': 0.0004995445784158661, 'samples': 930240, 'steps': 4844, 'loss/train': 2.58362078666687} 08/30/2021 14:04:07 - INFO - __main__ - Step 4846: {'lr': 0.0004995442581885759, 'samples': 930432, 'steps': 4845, 'loss/train': 2.5964014530181885} 08/30/2021 14:04:07 - INFO - __main__ - Step 4847: {'lr': 0.0004995439378488449, 'samples': 930624, 'steps': 4846, 'loss/train': 2.1342966556549072} 08/30/2021 14:04:08 - INFO - __main__ - Step 4848: {'lr': 0.0004995436173966733, 'samples': 930816, 'steps': 4847, 'loss/train': 2.743109941482544} 08/30/2021 14:04:08 - INFO - __main__ - Step 4849: {'lr': 0.0004995432968320611, 'samples': 931008, 'steps': 4848, 'loss/train': 2.200352668762207} 08/30/2021 14:04:10 - INFO - __main__ - Step 4850: {'lr': 0.0004995429761550086, 'samples': 931200, 'steps': 4849, 'loss/train': 2.59735369682312} 08/30/2021 14:04:10 - INFO - __main__ - Step 4851: {'lr': 0.0004995426553655159, 'samples': 931392, 'steps': 4850, 'loss/train': 2.017277956008911} 08/30/2021 14:04:10 - INFO - __main__ - Step 4852: {'lr': 0.0004995423344635831, 'samples': 931584, 'steps': 4851, 'loss/train': 2.207967519760132} 08/30/2021 14:04:11 - INFO - __main__ - Step 4853: {'lr': 0.0004995420134492105, 'samples': 931776, 'steps': 4852, 'loss/train': 2.088369369506836} 08/30/2021 14:04:11 - INFO - __main__ - Step 4854: {'lr': 0.0004995416923223979, 'samples': 931968, 'steps': 4853, 'loss/train': 2.138617992401123} 08/30/2021 14:04:13 - INFO - __main__ - Step 4855: {'lr': 0.0004995413710831458, 'samples': 932160, 'steps': 4854, 'loss/train': 2.071810007095337} 08/30/2021 14:04:13 - INFO - __main__ - Step 4856: {'lr': 0.0004995410497314542, 'samples': 932352, 'steps': 4855, 'loss/train': 2.2474253177642822} 08/30/2021 14:04:13 - INFO - __main__ - Step 4857: {'lr': 0.0004995407282673232, 'samples': 932544, 'steps': 4856, 'loss/train': 1.3294479846954346} 08/30/2021 14:04:14 - INFO - __main__ - Step 4858: {'lr': 0.000499540406690753, 'samples': 932736, 'steps': 4857, 'loss/train': 2.495647430419922} 08/30/2021 14:04:14 - INFO - __main__ - Step 4859: {'lr': 0.0004995400850017438, 'samples': 932928, 'steps': 4858, 'loss/train': 1.8881466388702393} 08/30/2021 14:04:16 - INFO - __main__ - Step 4860: {'lr': 0.0004995397632002957, 'samples': 933120, 'steps': 4859, 'loss/train': 2.295034646987915} 08/30/2021 14:04:16 - INFO - __main__ - Step 4861: {'lr': 0.0004995394412864088, 'samples': 933312, 'steps': 4860, 'loss/train': 2.3709468841552734} 08/30/2021 14:04:16 - INFO - __main__ - Step 4862: {'lr': 0.0004995391192600834, 'samples': 933504, 'steps': 4861, 'loss/train': 2.604323148727417} 08/30/2021 14:04:17 - INFO - __main__ - Step 4863: {'lr': 0.0004995387971213194, 'samples': 933696, 'steps': 4862, 'loss/train': 1.930928111076355} 08/30/2021 14:04:17 - INFO - __main__ - Step 4864: {'lr': 0.000499538474870117, 'samples': 933888, 'steps': 4863, 'loss/train': 1.811528205871582} 08/30/2021 14:04:19 - INFO - __main__ - Step 4865: {'lr': 0.0004995381525064765, 'samples': 934080, 'steps': 4864, 'loss/train': 2.3152430057525635} 08/30/2021 14:04:19 - INFO - __main__ - Step 4866: {'lr': 0.0004995378300303979, 'samples': 934272, 'steps': 4865, 'loss/train': 0.3185814321041107} 08/30/2021 14:04:20 - INFO - __main__ - Step 4867: {'lr': 0.0004995375074418815, 'samples': 934464, 'steps': 4866, 'loss/train': 1.6159205436706543} 08/30/2021 14:04:20 - INFO - __main__ - Step 4868: {'lr': 0.0004995371847409273, 'samples': 934656, 'steps': 4867, 'loss/train': 2.578643560409546} 08/30/2021 14:04:20 - INFO - __main__ - Step 4869: {'lr': 0.0004995368619275355, 'samples': 934848, 'steps': 4868, 'loss/train': 2.7576565742492676} 08/30/2021 14:04:22 - INFO - __main__ - Step 4870: {'lr': 0.0004995365390017062, 'samples': 935040, 'steps': 4869, 'loss/train': 3.0795624256134033} 08/30/2021 14:04:23 - INFO - __main__ - Step 4871: {'lr': 0.0004995362159634396, 'samples': 935232, 'steps': 4870, 'loss/train': 2.240497350692749} 08/30/2021 14:04:23 - INFO - __main__ - Step 4872: {'lr': 0.0004995358928127359, 'samples': 935424, 'steps': 4871, 'loss/train': 0.6288450956344604} 08/30/2021 14:04:23 - INFO - __main__ - Step 4873: {'lr': 0.0004995355695495952, 'samples': 935616, 'steps': 4872, 'loss/train': 0.7128564715385437} 08/30/2021 14:04:24 - INFO - __main__ - Step 4874: {'lr': 0.0004995352461740174, 'samples': 935808, 'steps': 4873, 'loss/train': 2.3273799419403076} 08/30/2021 14:04:24 - INFO - __main__ - Step 4875: {'lr': 0.0004995349226860031, 'samples': 936000, 'steps': 4874, 'loss/train': 2.4876091480255127} 08/30/2021 14:04:25 - INFO - __main__ - Step 4876: {'lr': 0.0004995345990855522, 'samples': 936192, 'steps': 4875, 'loss/train': 0.3857323229312897} 08/30/2021 14:04:26 - INFO - __main__ - Step 4877: {'lr': 0.0004995342753726647, 'samples': 936384, 'steps': 4876, 'loss/train': 2.2492923736572266} 08/30/2021 14:04:26 - INFO - __main__ - Step 4878: {'lr': 0.0004995339515473411, 'samples': 936576, 'steps': 4877, 'loss/train': 2.3254709243774414} 08/30/2021 14:04:27 - INFO - __main__ - Step 4879: {'lr': 0.0004995336276095812, 'samples': 936768, 'steps': 4878, 'loss/train': 0.2982950210571289} 08/30/2021 14:04:27 - INFO - __main__ - Step 4880: {'lr': 0.0004995333035593853, 'samples': 936960, 'steps': 4879, 'loss/train': 3.4135165214538574} 08/30/2021 14:04:27 - INFO - __main__ - Step 4881: {'lr': 0.0004995329793967537, 'samples': 937152, 'steps': 4880, 'loss/train': 2.241283893585205} 08/30/2021 14:04:30 - INFO - __main__ - Step 4882: {'lr': 0.0004995326551216862, 'samples': 937344, 'steps': 4881, 'loss/train': 2.0210165977478027} 08/30/2021 14:04:30 - INFO - __main__ - Step 4883: {'lr': 0.0004995323307341832, 'samples': 937536, 'steps': 4882, 'loss/train': 2.4769980907440186} 08/30/2021 14:04:30 - INFO - __main__ - Step 4884: {'lr': 0.0004995320062342449, 'samples': 937728, 'steps': 4883, 'loss/train': 1.26012122631073} 08/30/2021 14:04:31 - INFO - __main__ - Step 4885: {'lr': 0.0004995316816218712, 'samples': 937920, 'steps': 4884, 'loss/train': 2.107384443283081} 08/30/2021 14:04:31 - INFO - __main__ - Step 4886: {'lr': 0.0004995313568970625, 'samples': 938112, 'steps': 4885, 'loss/train': 2.4081616401672363} 08/30/2021 14:04:33 - INFO - __main__ - Step 4887: {'lr': 0.0004995310320598187, 'samples': 938304, 'steps': 4886, 'loss/train': 2.2661356925964355} 08/30/2021 14:04:33 - INFO - __main__ - Step 4888: {'lr': 0.0004995307071101401, 'samples': 938496, 'steps': 4887, 'loss/train': 2.039107084274292} 08/30/2021 14:04:33 - INFO - __main__ - Step 4889: {'lr': 0.0004995303820480268, 'samples': 938688, 'steps': 4888, 'loss/train': 2.11918044090271} 08/30/2021 14:04:34 - INFO - __main__ - Step 4890: {'lr': 0.000499530056873479, 'samples': 938880, 'steps': 4889, 'loss/train': 2.0490710735321045} 08/30/2021 14:04:34 - INFO - __main__ - Step 4891: {'lr': 0.0004995297315864968, 'samples': 939072, 'steps': 4890, 'loss/train': 1.924241304397583} 08/30/2021 14:04:36 - INFO - __main__ - Step 4892: {'lr': 0.0004995294061870802, 'samples': 939264, 'steps': 4891, 'loss/train': 2.2429251670837402} 08/30/2021 14:04:36 - INFO - __main__ - Step 4893: {'lr': 0.0004995290806752297, 'samples': 939456, 'steps': 4892, 'loss/train': 1.9073786735534668} 08/30/2021 14:04:36 - INFO - __main__ - Step 4894: {'lr': 0.0004995287550509452, 'samples': 939648, 'steps': 4893, 'loss/train': 2.1097092628479004} 08/30/2021 14:04:37 - INFO - __main__ - Step 4895: {'lr': 0.0004995284293142268, 'samples': 939840, 'steps': 4894, 'loss/train': 1.4850573539733887} 08/30/2021 14:04:37 - INFO - __main__ - Step 4896: {'lr': 0.0004995281034650748, 'samples': 940032, 'steps': 4895, 'loss/train': 2.265522003173828} 08/30/2021 14:04:39 - INFO - __main__ - Step 4897: {'lr': 0.0004995277775034894, 'samples': 940224, 'steps': 4896, 'loss/train': 2.796849250793457} 08/30/2021 14:04:39 - INFO - __main__ - Step 4898: {'lr': 0.0004995274514294706, 'samples': 940416, 'steps': 4897, 'loss/train': 2.3835463523864746} 08/30/2021 14:04:39 - INFO - __main__ - Step 4899: {'lr': 0.0004995271252430184, 'samples': 940608, 'steps': 4898, 'loss/train': 2.095919132232666} 08/30/2021 14:04:40 - INFO - __main__ - Step 4900: {'lr': 0.0004995267989441332, 'samples': 940800, 'steps': 4899, 'loss/train': 2.317500114440918} 08/30/2021 14:04:40 - INFO - __main__ - Step 4901: {'lr': 0.0004995264725328151, 'samples': 940992, 'steps': 4900, 'loss/train': 2.312500476837158} 08/30/2021 14:04:42 - INFO - __main__ - Step 4902: {'lr': 0.0004995261460090644, 'samples': 941184, 'steps': 4901, 'loss/train': 2.338080644607544} 08/30/2021 14:04:42 - INFO - __main__ - Step 4903: {'lr': 0.0004995258193728809, 'samples': 941376, 'steps': 4902, 'loss/train': 2.4022438526153564} 08/30/2021 14:04:43 - INFO - __main__ - Step 4904: {'lr': 0.0004995254926242649, 'samples': 941568, 'steps': 4903, 'loss/train': 1.979127049446106} 08/30/2021 14:04:43 - INFO - __main__ - Step 4905: {'lr': 0.0004995251657632165, 'samples': 941760, 'steps': 4904, 'loss/train': 1.7903000116348267} 08/30/2021 14:04:43 - INFO - __main__ - Step 4906: {'lr': 0.000499524838789736, 'samples': 941952, 'steps': 4905, 'loss/train': 2.0132312774658203} 08/30/2021 14:04:44 - INFO - __main__ - Step 4907: {'lr': 0.0004995245117038235, 'samples': 942144, 'steps': 4906, 'loss/train': 2.653233051300049} 08/30/2021 14:04:45 - INFO - __main__ - Step 4908: {'lr': 0.0004995241845054791, 'samples': 942336, 'steps': 4907, 'loss/train': 6.56795072555542} 08/30/2021 14:04:46 - INFO - __main__ - Step 4909: {'lr': 0.0004995238571947029, 'samples': 942528, 'steps': 4908, 'loss/train': 0.31409645080566406} 08/30/2021 14:04:46 - INFO - __main__ - Step 4910: {'lr': 0.0004995235297714951, 'samples': 942720, 'steps': 4909, 'loss/train': 3.070596694946289} 08/30/2021 14:04:46 - INFO - __main__ - Step 4911: {'lr': 0.0004995232022358559, 'samples': 942912, 'steps': 4910, 'loss/train': 2.411649703979492} 08/30/2021 14:04:47 - INFO - __main__ - Step 4912: {'lr': 0.0004995228745877853, 'samples': 943104, 'steps': 4911, 'loss/train': 2.4639906883239746} 08/30/2021 14:04:48 - INFO - __main__ - Step 4913: {'lr': 0.0004995225468272836, 'samples': 943296, 'steps': 4912, 'loss/train': 2.8082973957061768} 08/30/2021 14:04:49 - INFO - __main__ - Step 4914: {'lr': 0.0004995222189543509, 'samples': 943488, 'steps': 4913, 'loss/train': 2.173126697540283} 08/30/2021 14:04:49 - INFO - __main__ - Step 4915: {'lr': 0.0004995218909689873, 'samples': 943680, 'steps': 4914, 'loss/train': 2.0056076049804688} 08/30/2021 14:04:49 - INFO - __main__ - Step 4916: {'lr': 0.0004995215628711931, 'samples': 943872, 'steps': 4915, 'loss/train': 1.467712640762329} 08/30/2021 14:04:50 - INFO - __main__ - Step 4917: {'lr': 0.0004995212346609682, 'samples': 944064, 'steps': 4916, 'loss/train': 1.1171711683273315} 08/30/2021 14:04:51 - INFO - __main__ - Step 4918: {'lr': 0.0004995209063383129, 'samples': 944256, 'steps': 4917, 'loss/train': 2.1496872901916504} 08/30/2021 14:04:51 - INFO - __main__ - Step 4919: {'lr': 0.0004995205779032274, 'samples': 944448, 'steps': 4918, 'loss/train': 1.7300554513931274} 08/30/2021 14:04:52 - INFO - __main__ - Step 4920: {'lr': 0.0004995202493557118, 'samples': 944640, 'steps': 4919, 'loss/train': 2.637270450592041} 08/30/2021 14:04:52 - INFO - __main__ - Step 4921: {'lr': 0.0004995199206957662, 'samples': 944832, 'steps': 4920, 'loss/train': 2.460200309753418} 08/30/2021 14:04:53 - INFO - __main__ - Step 4922: {'lr': 0.0004995195919233906, 'samples': 945024, 'steps': 4921, 'loss/train': 2.2443785667419434} 08/30/2021 14:04:54 - INFO - __main__ - Step 4923: {'lr': 0.0004995192630385855, 'samples': 945216, 'steps': 4922, 'loss/train': 2.106414556503296} 08/30/2021 14:04:55 - INFO - __main__ - Step 4924: {'lr': 0.0004995189340413509, 'samples': 945408, 'steps': 4923, 'loss/train': 1.873865008354187} 08/30/2021 14:04:55 - INFO - __main__ - Step 4925: {'lr': 0.0004995186049316868, 'samples': 945600, 'steps': 4924, 'loss/train': 1.8414298295974731} 08/30/2021 14:04:55 - INFO - __main__ - Step 4926: {'lr': 0.0004995182757095935, 'samples': 945792, 'steps': 4925, 'loss/train': 2.4885571002960205} 08/30/2021 14:04:56 - INFO - __main__ - Step 4927: {'lr': 0.0004995179463750712, 'samples': 945984, 'steps': 4926, 'loss/train': 2.6049792766571045} 08/30/2021 14:04:57 - INFO - __main__ - Step 4928: {'lr': 0.0004995176169281199, 'samples': 946176, 'steps': 4927, 'loss/train': 2.603942632675171} 08/30/2021 14:04:58 - INFO - __main__ - Step 4929: {'lr': 0.0004995172873687398, 'samples': 946368, 'steps': 4928, 'loss/train': 2.30535626411438} 08/30/2021 14:04:58 - INFO - __main__ - Step 4930: {'lr': 0.0004995169576969311, 'samples': 946560, 'steps': 4929, 'loss/train': 2.0106935501098633} 08/30/2021 14:04:58 - INFO - __main__ - Step 4931: {'lr': 0.0004995166279126938, 'samples': 946752, 'steps': 4930, 'loss/train': 1.7972948551177979} 08/30/2021 14:04:59 - INFO - __main__ - Step 4932: {'lr': 0.0004995162980160283, 'samples': 946944, 'steps': 4931, 'loss/train': 2.1604394912719727} 08/30/2021 14:05:00 - INFO - __main__ - Step 4933: {'lr': 0.0004995159680069346, 'samples': 947136, 'steps': 4932, 'loss/train': 2.5004405975341797} 08/30/2021 14:05:01 - INFO - __main__ - Step 4934: {'lr': 0.0004995156378854127, 'samples': 947328, 'steps': 4933, 'loss/train': 1.1308302879333496} 08/30/2021 14:05:01 - INFO - __main__ - Step 4935: {'lr': 0.000499515307651463, 'samples': 947520, 'steps': 4934, 'loss/train': 2.3879315853118896} 08/30/2021 14:05:01 - INFO - __main__ - Step 4936: {'lr': 0.0004995149773050857, 'samples': 947712, 'steps': 4935, 'loss/train': 2.3608946800231934} 08/30/2021 14:05:02 - INFO - __main__ - Step 4937: {'lr': 0.0004995146468462806, 'samples': 947904, 'steps': 4936, 'loss/train': 2.002999782562256} 08/30/2021 14:05:02 - INFO - __main__ - Step 4938: {'lr': 0.0004995143162750481, 'samples': 948096, 'steps': 4937, 'loss/train': 2.130701780319214} 08/30/2021 14:05:05 - INFO - __main__ - Step 4939: {'lr': 0.0004995139855913883, 'samples': 948288, 'steps': 4938, 'loss/train': 2.4854297637939453} 08/30/2021 14:05:05 - INFO - __main__ - Step 4940: {'lr': 0.0004995136547953014, 'samples': 948480, 'steps': 4939, 'loss/train': 1.814285159111023} 08/30/2021 14:05:05 - INFO - __main__ - Step 4941: {'lr': 0.0004995133238867874, 'samples': 948672, 'steps': 4940, 'loss/train': 2.1046688556671143} 08/30/2021 14:05:06 - INFO - __main__ - Step 4942: {'lr': 0.0004995129928658466, 'samples': 948864, 'steps': 4941, 'loss/train': 2.03877592086792} 08/30/2021 14:05:06 - INFO - __main__ - Step 4943: {'lr': 0.0004995126617324791, 'samples': 949056, 'steps': 4942, 'loss/train': 0.757353663444519} 08/30/2021 14:05:06 - INFO - __main__ - Step 4944: {'lr': 0.000499512330486685, 'samples': 949248, 'steps': 4943, 'loss/train': 0.7588753700256348} 08/30/2021 14:05:08 - INFO - __main__ - Step 4945: {'lr': 0.0004995119991284645, 'samples': 949440, 'steps': 4944, 'loss/train': 2.301693916320801} 08/30/2021 14:05:09 - INFO - __main__ - Step 4946: {'lr': 0.0004995116676578178, 'samples': 949632, 'steps': 4945, 'loss/train': 1.6053683757781982} 08/30/2021 14:05:09 - INFO - __main__ - Step 4947: {'lr': 0.000499511336074745, 'samples': 949824, 'steps': 4946, 'loss/train': 0.3145149052143097} 08/30/2021 14:05:09 - INFO - __main__ - Step 4948: {'lr': 0.0004995110043792462, 'samples': 950016, 'steps': 4947, 'loss/train': 2.001035213470459} 08/30/2021 14:05:10 - INFO - __main__ - Step 4949: {'lr': 0.0004995106725713217, 'samples': 950208, 'steps': 4948, 'loss/train': 2.3597168922424316} 08/30/2021 14:05:11 - INFO - __main__ - Step 4950: {'lr': 0.0004995103406509713, 'samples': 950400, 'steps': 4949, 'loss/train': 2.4153897762298584} 08/30/2021 14:05:12 - INFO - __main__ - Step 4951: {'lr': 0.0004995100086181957, 'samples': 950592, 'steps': 4950, 'loss/train': 2.0533249378204346} 08/30/2021 14:05:12 - INFO - __main__ - Step 4952: {'lr': 0.0004995096764729945, 'samples': 950784, 'steps': 4951, 'loss/train': 2.1157147884368896} 08/30/2021 14:05:13 - INFO - __main__ - Step 4953: {'lr': 0.0004995093442153681, 'samples': 950976, 'steps': 4952, 'loss/train': 2.475590467453003} 08/30/2021 14:05:13 - INFO - __main__ - Step 4954: {'lr': 0.0004995090118453167, 'samples': 951168, 'steps': 4953, 'loss/train': 2.4947054386138916} 08/30/2021 14:05:15 - INFO - __main__ - Step 4955: {'lr': 0.0004995086793628405, 'samples': 951360, 'steps': 4954, 'loss/train': 2.6105780601501465} 08/30/2021 14:05:15 - INFO - __main__ - Step 4956: {'lr': 0.0004995083467679394, 'samples': 951552, 'steps': 4955, 'loss/train': 2.253298282623291} 08/30/2021 14:05:16 - INFO - __main__ - Step 4957: {'lr': 0.0004995080140606137, 'samples': 951744, 'steps': 4956, 'loss/train': 1.762590765953064} 08/30/2021 14:05:16 - INFO - __main__ - Step 4958: {'lr': 0.0004995076812408636, 'samples': 951936, 'steps': 4957, 'loss/train': 1.8989931344985962} 08/30/2021 14:05:16 - INFO - __main__ - Step 4959: {'lr': 0.0004995073483086891, 'samples': 952128, 'steps': 4958, 'loss/train': 2.4466254711151123} 08/30/2021 14:05:17 - INFO - __main__ - Step 4960: {'lr': 0.0004995070152640905, 'samples': 952320, 'steps': 4959, 'loss/train': 1.510615348815918} 08/30/2021 14:05:18 - INFO - __main__ - Step 4961: {'lr': 0.0004995066821070679, 'samples': 952512, 'steps': 4960, 'loss/train': 1.8117167949676514} 08/30/2021 14:05:19 - INFO - __main__ - Step 4962: {'lr': 0.0004995063488376214, 'samples': 952704, 'steps': 4961, 'loss/train': 2.358320713043213} 08/30/2021 14:05:19 - INFO - __main__ - Step 4963: {'lr': 0.0004995060154557513, 'samples': 952896, 'steps': 4962, 'loss/train': 1.8514835834503174} 08/30/2021 14:05:19 - INFO - __main__ - Step 4964: {'lr': 0.0004995056819614575, 'samples': 953088, 'steps': 4963, 'loss/train': 2.4489994049072266} 08/30/2021 14:05:20 - INFO - __main__ - Step 4965: {'lr': 0.0004995053483547404, 'samples': 953280, 'steps': 4964, 'loss/train': 2.4801366329193115} 08/30/2021 14:05:21 - INFO - __main__ - Step 4966: {'lr': 0.0004995050146355999, 'samples': 953472, 'steps': 4965, 'loss/train': 2.4225547313690186} 08/30/2021 14:05:22 - INFO - __main__ - Step 4967: {'lr': 0.0004995046808040363, 'samples': 953664, 'steps': 4966, 'loss/train': 0.32150137424468994} 08/30/2021 14:05:22 - INFO - __main__ - Step 4968: {'lr': 0.0004995043468600499, 'samples': 953856, 'steps': 4967, 'loss/train': 1.9236828088760376} 08/30/2021 14:05:23 - INFO - __main__ - Step 4969: {'lr': 0.0004995040128036405, 'samples': 954048, 'steps': 4968, 'loss/train': 2.0275049209594727} 08/30/2021 14:05:23 - INFO - __main__ - Step 4970: {'lr': 0.0004995036786348086, 'samples': 954240, 'steps': 4969, 'loss/train': 2.2119622230529785} 08/30/2021 14:05:25 - INFO - __main__ - Step 4971: {'lr': 0.0004995033443535541, 'samples': 954432, 'steps': 4970, 'loss/train': 2.1632797718048096} 08/30/2021 14:05:25 - INFO - __main__ - Step 4972: {'lr': 0.0004995030099598773, 'samples': 954624, 'steps': 4971, 'loss/train': 2.516055107116699} 08/30/2021 14:05:25 - INFO - __main__ - Step 4973: {'lr': 0.0004995026754537783, 'samples': 954816, 'steps': 4972, 'loss/train': 3.1148569583892822} 08/30/2021 14:05:26 - INFO - __main__ - Step 4974: {'lr': 0.0004995023408352572, 'samples': 955008, 'steps': 4973, 'loss/train': 2.2369978427886963} 08/30/2021 14:05:26 - INFO - __main__ - Step 4975: {'lr': 0.0004995020061043142, 'samples': 955200, 'steps': 4974, 'loss/train': 2.421145439147949} 08/30/2021 14:05:28 - INFO - __main__ - Step 4976: {'lr': 0.0004995016712609495, 'samples': 955392, 'steps': 4975, 'loss/train': 2.4800565242767334} 08/30/2021 14:05:28 - INFO - __main__ - Step 4977: {'lr': 0.0004995013363051631, 'samples': 955584, 'steps': 4976, 'loss/train': 2.2450156211853027} 08/30/2021 14:05:28 - INFO - __main__ - Step 4978: {'lr': 0.0004995010012369554, 'samples': 955776, 'steps': 4977, 'loss/train': 1.7701746225357056} 08/30/2021 14:05:29 - INFO - __main__ - Step 4979: {'lr': 0.0004995006660563262, 'samples': 955968, 'steps': 4978, 'loss/train': 3.6930694580078125} 08/30/2021 14:05:29 - INFO - __main__ - Step 4980: {'lr': 0.000499500330763276, 'samples': 956160, 'steps': 4979, 'loss/train': 1.9483429193496704} 08/30/2021 14:05:31 - INFO - __main__ - Step 4981: {'lr': 0.0004994999953578048, 'samples': 956352, 'steps': 4980, 'loss/train': 2.2295784950256348} 08/30/2021 14:05:31 - INFO - __main__ - Step 4982: {'lr': 0.0004994996598399127, 'samples': 956544, 'steps': 4981, 'loss/train': 2.3952081203460693} 08/30/2021 14:05:31 - INFO - __main__ - Step 4983: {'lr': 0.0004994993242095999, 'samples': 956736, 'steps': 4982, 'loss/train': 2.151777744293213} 08/30/2021 14:05:32 - INFO - __main__ - Step 4984: {'lr': 0.0004994989884668665, 'samples': 956928, 'steps': 4983, 'loss/train': 1.5608434677124023} 08/30/2021 14:05:32 - INFO - __main__ - Step 4985: {'lr': 0.0004994986526117127, 'samples': 957120, 'steps': 4984, 'loss/train': 3.0511488914489746} 08/30/2021 14:05:34 - INFO - __main__ - Step 4986: {'lr': 0.0004994983166441388, 'samples': 957312, 'steps': 4985, 'loss/train': 1.9915233850479126} 08/30/2021 14:05:34 - INFO - __main__ - Step 4987: {'lr': 0.0004994979805641448, 'samples': 957504, 'steps': 4986, 'loss/train': 2.4051709175109863} 08/30/2021 14:05:35 - INFO - __main__ - Step 4988: {'lr': 0.0004994976443717308, 'samples': 957696, 'steps': 4987, 'loss/train': 2.454705238342285} 08/30/2021 14:05:35 - INFO - __main__ - Step 4989: {'lr': 0.000499497308066897, 'samples': 957888, 'steps': 4988, 'loss/train': 1.88473379611969} 08/30/2021 14:05:36 - INFO - __main__ - Step 4990: {'lr': 0.0004994969716496435, 'samples': 958080, 'steps': 4989, 'loss/train': 1.7168686389923096} 08/30/2021 14:05:36 - INFO - __main__ - Step 4991: {'lr': 0.0004994966351199706, 'samples': 958272, 'steps': 4990, 'loss/train': 2.2099459171295166} 08/30/2021 14:05:38 - INFO - __main__ - Step 4992: {'lr': 0.0004994962984778784, 'samples': 958464, 'steps': 4991, 'loss/train': 1.5991742610931396} 08/30/2021 14:05:38 - INFO - __main__ - Step 4993: {'lr': 0.0004994959617233669, 'samples': 958656, 'steps': 4992, 'loss/train': 2.384688138961792} 08/30/2021 14:05:39 - INFO - __main__ - Step 4994: {'lr': 0.0004994956248564364, 'samples': 958848, 'steps': 4993, 'loss/train': 2.214613914489746} 08/30/2021 14:05:39 - INFO - __main__ - Step 4995: {'lr': 0.000499495287877087, 'samples': 959040, 'steps': 4994, 'loss/train': 1.851972222328186} 08/30/2021 14:05:39 - INFO - __main__ - Step 4996: {'lr': 0.000499494950785319, 'samples': 959232, 'steps': 4995, 'loss/train': 2.390132427215576} 08/30/2021 14:05:41 - INFO - __main__ - Step 4997: {'lr': 0.0004994946135811324, 'samples': 959424, 'steps': 4996, 'loss/train': 2.9583733081817627} 08/30/2021 14:05:41 - INFO - __main__ - Step 4998: {'lr': 0.0004994942762645274, 'samples': 959616, 'steps': 4997, 'loss/train': 2.035806894302368} 08/30/2021 14:05:42 - INFO - __main__ - Step 4999: {'lr': 0.000499493938835504, 'samples': 959808, 'steps': 4998, 'loss/train': 1.8996617794036865} 08/30/2021 14:05:42 - INFO - __main__ - Step 5000: {'lr': 0.0004994936012940626, 'samples': 960000, 'steps': 4999, 'loss/train': 2.6488256454467773} 08/30/2021 14:05:42 - INFO - __main__ - Step 5001: {'lr': 0.0004994932636402031, 'samples': 960192, 'steps': 5000, 'loss/train': 2.4259438514709473} 08/30/2021 14:05:44 - INFO - __main__ - Step 5002: {'lr': 0.000499492925873926, 'samples': 960384, 'steps': 5001, 'loss/train': 2.70697021484375} 08/30/2021 14:05:44 - INFO - __main__ - Step 5003: {'lr': 0.000499492587995231, 'samples': 960576, 'steps': 5002, 'loss/train': 1.759914755821228} 08/30/2021 14:05:45 - INFO - __main__ - Step 5004: {'lr': 0.0004994922500041186, 'samples': 960768, 'steps': 5003, 'loss/train': 2.4683380126953125} 08/30/2021 14:05:45 - INFO - __main__ - Step 5005: {'lr': 0.0004994919119005888, 'samples': 960960, 'steps': 5004, 'loss/train': 3.022188186645508} 08/30/2021 14:05:45 - INFO - __main__ - Step 5006: {'lr': 0.0004994915736846418, 'samples': 961152, 'steps': 5005, 'loss/train': 2.1260223388671875} 08/30/2021 14:05:47 - INFO - __main__ - Step 5007: {'lr': 0.0004994912353562778, 'samples': 961344, 'steps': 5006, 'loss/train': 2.201915740966797} 08/30/2021 14:05:47 - INFO - __main__ - Step 5008: {'lr': 0.0004994908969154968, 'samples': 961536, 'steps': 5007, 'loss/train': 2.3067941665649414} 08/30/2021 14:05:48 - INFO - __main__ - Step 5009: {'lr': 0.0004994905583622992, 'samples': 961728, 'steps': 5008, 'loss/train': 2.307985782623291} 08/30/2021 14:05:48 - INFO - __main__ - Step 5010: {'lr': 0.000499490219696685, 'samples': 961920, 'steps': 5009, 'loss/train': 2.2486019134521484} 08/30/2021 14:05:48 - INFO - __main__ - Step 5011: {'lr': 0.0004994898809186542, 'samples': 962112, 'steps': 5010, 'loss/train': 2.5013742446899414} 08/30/2021 14:05:50 - INFO - __main__ - Step 5012: {'lr': 0.0004994895420282072, 'samples': 962304, 'steps': 5011, 'loss/train': 2.4124350547790527} 08/30/2021 14:05:50 - INFO - __main__ - Step 5013: {'lr': 0.000499489203025344, 'samples': 962496, 'steps': 5012, 'loss/train': 2.271155595779419} 08/30/2021 14:05:51 - INFO - __main__ - Step 5014: {'lr': 0.000499488863910065, 'samples': 962688, 'steps': 5013, 'loss/train': 2.2971246242523193} 08/30/2021 14:05:51 - INFO - __main__ - Step 5015: {'lr': 0.00049948852468237, 'samples': 962880, 'steps': 5014, 'loss/train': 2.2773890495300293} 08/30/2021 14:05:51 - INFO - __main__ - Step 5016: {'lr': 0.0004994881853422594, 'samples': 963072, 'steps': 5015, 'loss/train': 2.1161599159240723} 08/30/2021 14:05:52 - INFO - __main__ - Step 5017: {'lr': 0.0004994878458897332, 'samples': 963264, 'steps': 5016, 'loss/train': 2.326650857925415} 08/30/2021 14:05:53 - INFO - __main__ - Step 5018: {'lr': 0.0004994875063247916, 'samples': 963456, 'steps': 5017, 'loss/train': 2.836604118347168} 08/30/2021 14:05:54 - INFO - __main__ - Step 5019: {'lr': 0.0004994871666474348, 'samples': 963648, 'steps': 5018, 'loss/train': 2.0088050365448} 08/30/2021 14:05:54 - INFO - __main__ - Step 5020: {'lr': 0.000499486826857663, 'samples': 963840, 'steps': 5019, 'loss/train': 1.8153910636901855} 08/30/2021 14:05:54 - INFO - __main__ - Step 5021: {'lr': 0.0004994864869554763, 'samples': 964032, 'steps': 5020, 'loss/train': 2.020601749420166} 08/30/2021 14:05:55 - INFO - __main__ - Step 5022: {'lr': 0.0004994861469408748, 'samples': 964224, 'steps': 5021, 'loss/train': 3.125349998474121} 08/30/2021 14:05:56 - INFO - __main__ - Step 5023: {'lr': 0.0004994858068138587, 'samples': 964416, 'steps': 5022, 'loss/train': 2.310551404953003} 08/30/2021 14:05:57 - INFO - __main__ - Step 5024: {'lr': 0.0004994854665744282, 'samples': 964608, 'steps': 5023, 'loss/train': 2.111747980117798} 08/30/2021 14:05:57 - INFO - __main__ - Step 5025: {'lr': 0.0004994851262225832, 'samples': 964800, 'steps': 5024, 'loss/train': 2.0517771244049072} 08/30/2021 14:05:58 - INFO - __main__ - Step 5026: {'lr': 0.0004994847857583242, 'samples': 964992, 'steps': 5025, 'loss/train': 2.343459367752075} 08/30/2021 14:05:58 - INFO - __main__ - Step 5027: {'lr': 0.0004994844451816512, 'samples': 965184, 'steps': 5026, 'loss/train': 2.186488389968872} 08/30/2021 14:05:58 - INFO - __main__ - Step 5028: {'lr': 0.0004994841044925644, 'samples': 965376, 'steps': 5027, 'loss/train': 2.092644691467285} 08/30/2021 14:06:00 - INFO - __main__ - Step 5029: {'lr': 0.0004994837636910638, 'samples': 965568, 'steps': 5028, 'loss/train': 1.0676257610321045} 08/30/2021 14:06:00 - INFO - __main__ - Step 5030: {'lr': 0.0004994834227771498, 'samples': 965760, 'steps': 5029, 'loss/train': 1.7181196212768555} 08/30/2021 14:06:01 - INFO - __main__ - Step 5031: {'lr': 0.0004994830817508224, 'samples': 965952, 'steps': 5030, 'loss/train': 2.0105507373809814} 08/30/2021 14:06:01 - INFO - __main__ - Step 5032: {'lr': 0.0004994827406120816, 'samples': 966144, 'steps': 5031, 'loss/train': 2.50541615486145} 08/30/2021 14:06:01 - INFO - __main__ - Step 5033: {'lr': 0.0004994823993609279, 'samples': 966336, 'steps': 5032, 'loss/train': 2.1383092403411865} 08/30/2021 14:06:03 - INFO - __main__ - Step 5034: {'lr': 0.0004994820579973612, 'samples': 966528, 'steps': 5033, 'loss/train': 2.203997850418091} 08/30/2021 14:06:03 - INFO - __main__ - Step 5035: {'lr': 0.0004994817165213817, 'samples': 966720, 'steps': 5034, 'loss/train': 1.44949209690094} 08/30/2021 14:06:04 - INFO - __main__ - Step 5036: {'lr': 0.0004994813749329897, 'samples': 966912, 'steps': 5035, 'loss/train': 2.2587904930114746} 08/30/2021 14:06:04 - INFO - __main__ - Step 5037: {'lr': 0.0004994810332321852, 'samples': 967104, 'steps': 5036, 'loss/train': 1.158984661102295} 08/30/2021 14:06:04 - INFO - __main__ - Step 5038: {'lr': 0.0004994806914189684, 'samples': 967296, 'steps': 5037, 'loss/train': 1.4465986490249634} 08/30/2021 14:06:06 - INFO - __main__ - Step 5039: {'lr': 0.0004994803494933394, 'samples': 967488, 'steps': 5038, 'loss/train': 2.1343822479248047} 08/30/2021 14:06:07 - INFO - __main__ - Step 5040: {'lr': 0.0004994800074552985, 'samples': 967680, 'steps': 5039, 'loss/train': 1.92071533203125} 08/30/2021 14:06:07 - INFO - __main__ - Step 5041: {'lr': 0.0004994796653048457, 'samples': 967872, 'steps': 5040, 'loss/train': 1.976090908050537} 08/30/2021 14:06:08 - INFO - __main__ - Step 5042: {'lr': 0.0004994793230419812, 'samples': 968064, 'steps': 5041, 'loss/train': 2.8340530395507812} 08/30/2021 14:06:08 - INFO - __main__ - Step 5043: {'lr': 0.0004994789806667052, 'samples': 968256, 'steps': 5042, 'loss/train': 2.358433246612549} 08/30/2021 14:06:08 - INFO - __main__ - Step 5044: {'lr': 0.0004994786381790178, 'samples': 968448, 'steps': 5043, 'loss/train': 0.569067120552063} 08/30/2021 14:06:09 - INFO - __main__ - Step 5045: {'lr': 0.0004994782955789191, 'samples': 968640, 'steps': 5044, 'loss/train': 2.6374900341033936} 08/30/2021 14:06:10 - INFO - __main__ - Step 5046: {'lr': 0.0004994779528664095, 'samples': 968832, 'steps': 5045, 'loss/train': 1.999448537826538} 08/30/2021 14:06:11 - INFO - __main__ - Step 5047: {'lr': 0.0004994776100414888, 'samples': 969024, 'steps': 5046, 'loss/train': 0.5370808839797974} 08/30/2021 14:06:11 - INFO - __main__ - Step 5048: {'lr': 0.0004994772671041575, 'samples': 969216, 'steps': 5047, 'loss/train': 2.0678257942199707} 08/30/2021 14:06:11 - INFO - __main__ - Step 5049: {'lr': 0.0004994769240544155, 'samples': 969408, 'steps': 5048, 'loss/train': 2.6127657890319824} 08/30/2021 14:06:12 - INFO - __main__ - Step 5050: {'lr': 0.000499476580892263, 'samples': 969600, 'steps': 5049, 'loss/train': 2.5824270248413086} 08/30/2021 14:06:14 - INFO - __main__ - Step 5051: {'lr': 0.0004994762376177004, 'samples': 969792, 'steps': 5050, 'loss/train': 2.197941541671753} 08/30/2021 14:06:14 - INFO - __main__ - Step 5052: {'lr': 0.0004994758942307274, 'samples': 969984, 'steps': 5051, 'loss/train': 1.8828701972961426} 08/30/2021 14:06:14 - INFO - __main__ - Step 5053: {'lr': 0.0004994755507313446, 'samples': 970176, 'steps': 5052, 'loss/train': 2.1294960975646973} 08/30/2021 14:06:15 - INFO - __main__ - Step 5054: {'lr': 0.000499475207119552, 'samples': 970368, 'steps': 5053, 'loss/train': 2.3135781288146973} 08/30/2021 14:06:15 - INFO - __main__ - Step 5055: {'lr': 0.0004994748633953495, 'samples': 970560, 'steps': 5054, 'loss/train': 2.251643180847168} 08/30/2021 14:06:17 - INFO - __main__ - Step 5056: {'lr': 0.0004994745195587376, 'samples': 970752, 'steps': 5055, 'loss/train': 2.17777681350708} 08/30/2021 14:06:17 - INFO - __main__ - Step 5057: {'lr': 0.0004994741756097164, 'samples': 970944, 'steps': 5056, 'loss/train': 2.6799299716949463} 08/30/2021 14:06:18 - INFO - __main__ - Step 5058: {'lr': 0.0004994738315482859, 'samples': 971136, 'steps': 5057, 'loss/train': 2.480123281478882} 08/30/2021 14:06:18 - INFO - __main__ - Step 5059: {'lr': 0.0004994734873744464, 'samples': 971328, 'steps': 5058, 'loss/train': 2.2336738109588623} 08/30/2021 14:06:18 - INFO - __main__ - Step 5060: {'lr': 0.0004994731430881979, 'samples': 971520, 'steps': 5059, 'loss/train': 2.609337091445923} 08/30/2021 14:06:20 - INFO - __main__ - Step 5061: {'lr': 0.0004994727986895408, 'samples': 971712, 'steps': 5060, 'loss/train': 2.3969571590423584} 08/30/2021 14:06:20 - INFO - __main__ - Step 5062: {'lr': 0.0004994724541784749, 'samples': 971904, 'steps': 5061, 'loss/train': 2.1014246940612793} 08/30/2021 14:06:21 - INFO - __main__ - Step 5063: {'lr': 0.0004994721095550008, 'samples': 972096, 'steps': 5062, 'loss/train': 2.0435609817504883} 08/30/2021 14:06:21 - INFO - __main__ - Step 5064: {'lr': 0.0004994717648191182, 'samples': 972288, 'steps': 5063, 'loss/train': 1.364272117614746} 08/30/2021 14:06:21 - INFO - __main__ - Step 5065: {'lr': 0.0004994714199708276, 'samples': 972480, 'steps': 5064, 'loss/train': 3.4123785495758057} 08/30/2021 14:06:23 - INFO - __main__ - Step 5066: {'lr': 0.000499471075010129, 'samples': 972672, 'steps': 5065, 'loss/train': 2.356801986694336} 08/30/2021 14:06:23 - INFO - __main__ - Step 5067: {'lr': 0.0004994707299370226, 'samples': 972864, 'steps': 5066, 'loss/train': 2.198176860809326} 08/30/2021 14:06:23 - INFO - __main__ - Step 5068: {'lr': 0.0004994703847515084, 'samples': 973056, 'steps': 5067, 'loss/train': 1.8925210237503052} 08/30/2021 14:06:24 - INFO - __main__ - Step 5069: {'lr': 0.0004994700394535869, 'samples': 973248, 'steps': 5068, 'loss/train': 2.642307996749878} 08/30/2021 14:06:24 - INFO - __main__ - Step 5070: {'lr': 0.000499469694043258, 'samples': 973440, 'steps': 5069, 'loss/train': 2.5104517936706543} 08/30/2021 14:06:26 - INFO - __main__ - Step 5071: {'lr': 0.0004994693485205218, 'samples': 973632, 'steps': 5070, 'loss/train': 2.400275707244873} 08/30/2021 14:06:26 - INFO - __main__ - Step 5072: {'lr': 0.0004994690028853787, 'samples': 973824, 'steps': 5071, 'loss/train': 2.155043125152588} 08/30/2021 14:06:26 - INFO - __main__ - Step 5073: {'lr': 0.0004994686571378286, 'samples': 974016, 'steps': 5072, 'loss/train': 1.8040902614593506} 08/30/2021 14:06:27 - INFO - __main__ - Step 5074: {'lr': 0.0004994683112778718, 'samples': 974208, 'steps': 5073, 'loss/train': 2.012456178665161} 08/30/2021 14:06:27 - INFO - __main__ - Step 5075: {'lr': 0.0004994679653055085, 'samples': 974400, 'steps': 5074, 'loss/train': 2.6727070808410645} 08/30/2021 14:06:29 - INFO - __main__ - Step 5076: {'lr': 0.0004994676192207387, 'samples': 974592, 'steps': 5075, 'loss/train': 1.9303525686264038} 08/30/2021 14:06:29 - INFO - __main__ - Step 5077: {'lr': 0.0004994672730235626, 'samples': 974784, 'steps': 5076, 'loss/train': 2.28853178024292} 08/30/2021 14:06:30 - INFO - __main__ - Step 5078: {'lr': 0.0004994669267139806, 'samples': 974976, 'steps': 5077, 'loss/train': 1.9448527097702026} 08/30/2021 14:06:30 - INFO - __main__ - Step 5079: {'lr': 0.0004994665802919925, 'samples': 975168, 'steps': 5078, 'loss/train': 1.7412238121032715} 08/30/2021 14:06:30 - INFO - __main__ - Step 5080: {'lr': 0.0004994662337575986, 'samples': 975360, 'steps': 5079, 'loss/train': 1.8150287866592407} 08/30/2021 14:06:31 - INFO - __main__ - Step 5081: {'lr': 0.000499465887110799, 'samples': 975552, 'steps': 5080, 'loss/train': 2.751884698867798} 08/30/2021 14:06:32 - INFO - __main__ - Step 5082: {'lr': 0.0004994655403515941, 'samples': 975744, 'steps': 5081, 'loss/train': 2.125681161880493} 08/30/2021 14:06:33 - INFO - __main__ - Step 5083: {'lr': 0.0004994651934799837, 'samples': 975936, 'steps': 5082, 'loss/train': 2.4222323894500732} 08/30/2021 14:06:33 - INFO - __main__ - Step 5084: {'lr': 0.0004994648464959683, 'samples': 976128, 'steps': 5083, 'loss/train': 2.4969780445098877} 08/30/2021 14:06:33 - INFO - __main__ - Step 5085: {'lr': 0.0004994644993995478, 'samples': 976320, 'steps': 5084, 'loss/train': 2.1790761947631836} 08/30/2021 14:06:34 - INFO - __main__ - Step 5086: {'lr': 0.0004994641521907224, 'samples': 976512, 'steps': 5085, 'loss/train': 2.254190444946289} 08/30/2021 14:06:35 - INFO - __main__ - Step 5087: {'lr': 0.0004994638048694924, 'samples': 976704, 'steps': 5086, 'loss/train': 1.8640891313552856} 08/30/2021 14:06:36 - INFO - __main__ - Step 5088: {'lr': 0.0004994634574358579, 'samples': 976896, 'steps': 5087, 'loss/train': 2.1303329467773438} 08/30/2021 14:06:36 - INFO - __main__ - Step 5089: {'lr': 0.0004994631098898188, 'samples': 977088, 'steps': 5088, 'loss/train': 0.36919113993644714} 08/30/2021 14:06:37 - INFO - __main__ - Step 5090: {'lr': 0.0004994627622313757, 'samples': 977280, 'steps': 5089, 'loss/train': 0.23060260713100433} 08/30/2021 14:06:37 - INFO - __main__ - Step 5091: {'lr': 0.0004994624144605284, 'samples': 977472, 'steps': 5090, 'loss/train': 2.6076836585998535} 08/30/2021 14:06:39 - INFO - __main__ - Step 5092: {'lr': 0.0004994620665772772, 'samples': 977664, 'steps': 5091, 'loss/train': 2.365443468093872} 08/30/2021 14:06:40 - INFO - __main__ - Step 5093: {'lr': 0.0004994617185816222, 'samples': 977856, 'steps': 5092, 'loss/train': 1.8796745538711548} 08/30/2021 14:06:40 - INFO - __main__ - Step 5094: {'lr': 0.0004994613704735638, 'samples': 978048, 'steps': 5093, 'loss/train': 4.509443759918213} 08/30/2021 14:06:40 - INFO - __main__ - Step 5095: {'lr': 0.0004994610222531018, 'samples': 978240, 'steps': 5094, 'loss/train': 1.762518048286438} 08/30/2021 14:06:41 - INFO - __main__ - Step 5096: {'lr': 0.0004994606739202365, 'samples': 978432, 'steps': 5095, 'loss/train': 2.1011953353881836} 08/30/2021 14:06:41 - INFO - __main__ - Step 5097: {'lr': 0.0004994603254749681, 'samples': 978624, 'steps': 5096, 'loss/train': 2.0571515560150146} 08/30/2021 14:06:41 - INFO - __main__ - Step 5098: {'lr': 0.0004994599769172967, 'samples': 978816, 'steps': 5097, 'loss/train': 2.0882222652435303} 08/30/2021 14:06:43 - INFO - __main__ - Step 5099: {'lr': 0.0004994596282472225, 'samples': 979008, 'steps': 5098, 'loss/train': 2.3541228771209717} 08/30/2021 14:06:43 - INFO - __main__ - Step 5100: {'lr': 0.0004994592794647457, 'samples': 979200, 'steps': 5099, 'loss/train': 2.067221164703369} 08/30/2021 14:06:44 - INFO - __main__ - Step 5101: {'lr': 0.0004994589305698663, 'samples': 979392, 'steps': 5100, 'loss/train': 2.012131929397583} 08/30/2021 14:06:44 - INFO - __main__ - Step 5102: {'lr': 0.0004994585815625847, 'samples': 979584, 'steps': 5101, 'loss/train': 2.259871482849121} 08/30/2021 14:06:45 - INFO - __main__ - Step 5103: {'lr': 0.0004994582324429008, 'samples': 979776, 'steps': 5102, 'loss/train': 2.6643753051757812} 08/30/2021 14:06:45 - INFO - __main__ - Step 5104: {'lr': 0.0004994578832108148, 'samples': 979968, 'steps': 5103, 'loss/train': 2.388671636581421} 08/30/2021 14:06:47 - INFO - __main__ - Step 5105: {'lr': 0.000499457533866327, 'samples': 980160, 'steps': 5104, 'loss/train': 1.8212487697601318} 08/30/2021 14:06:48 - INFO - __main__ - Step 5106: {'lr': 0.0004994571844094375, 'samples': 980352, 'steps': 5105, 'loss/train': 1.160867691040039} 08/30/2021 14:06:48 - INFO - __main__ - Step 5107: {'lr': 0.0004994568348401466, 'samples': 980544, 'steps': 5106, 'loss/train': 2.539199113845825} 08/30/2021 14:06:48 - INFO - __main__ - Step 5108: {'lr': 0.0004994564851584541, 'samples': 980736, 'steps': 5107, 'loss/train': 2.3143012523651123} 08/30/2021 14:06:49 - INFO - __main__ - Step 5109: {'lr': 0.0004994561353643604, 'samples': 980928, 'steps': 5108, 'loss/train': 1.984595537185669} 08/30/2021 14:06:50 - INFO - __main__ - Step 5110: {'lr': 0.0004994557854578656, 'samples': 981120, 'steps': 5109, 'loss/train': 2.503065586090088} 08/30/2021 14:06:51 - INFO - __main__ - Step 5111: {'lr': 0.0004994554354389699, 'samples': 981312, 'steps': 5110, 'loss/train': 2.485055685043335} 08/30/2021 14:06:51 - INFO - __main__ - Step 5112: {'lr': 0.0004994550853076734, 'samples': 981504, 'steps': 5111, 'loss/train': 2.0640735626220703} 08/30/2021 14:06:51 - INFO - __main__ - Step 5113: {'lr': 0.0004994547350639764, 'samples': 981696, 'steps': 5112, 'loss/train': 2.373863935470581} 08/30/2021 14:06:52 - INFO - __main__ - Step 5114: {'lr': 0.0004994543847078787, 'samples': 981888, 'steps': 5113, 'loss/train': 2.16861629486084} 08/30/2021 14:06:53 - INFO - __main__ - Step 5115: {'lr': 0.000499454034239381, 'samples': 982080, 'steps': 5114, 'loss/train': 2.0705621242523193} 08/30/2021 14:06:54 - INFO - __main__ - Step 5116: {'lr': 0.000499453683658483, 'samples': 982272, 'steps': 5115, 'loss/train': 2.169928789138794} 08/30/2021 14:06:54 - INFO - __main__ - Step 5117: {'lr': 0.0004994533329651849, 'samples': 982464, 'steps': 5116, 'loss/train': 2.4235708713531494} 08/30/2021 14:06:55 - INFO - __main__ - Step 5118: {'lr': 0.0004994529821594872, 'samples': 982656, 'steps': 5117, 'loss/train': 2.439915180206299} 08/30/2021 14:06:55 - INFO - __main__ - Step 5119: {'lr': 0.0004994526312413897, 'samples': 982848, 'steps': 5118, 'loss/train': 2.178100824356079} 08/30/2021 14:06:56 - INFO - __main__ - Step 5120: {'lr': 0.0004994522802108927, 'samples': 983040, 'steps': 5119, 'loss/train': 2.2076311111450195} 08/30/2021 14:06:57 - INFO - __main__ - Step 5121: {'lr': 0.0004994519290679964, 'samples': 983232, 'steps': 5120, 'loss/train': 2.2335612773895264} 08/30/2021 14:06:57 - INFO - __main__ - Step 5122: {'lr': 0.0004994515778127009, 'samples': 983424, 'steps': 5121, 'loss/train': 2.0980303287506104} 08/30/2021 14:06:58 - INFO - __main__ - Step 5123: {'lr': 0.0004994512264450064, 'samples': 983616, 'steps': 5122, 'loss/train': 2.24619460105896} 08/30/2021 14:06:58 - INFO - __main__ - Step 5124: {'lr': 0.000499450874964913, 'samples': 983808, 'steps': 5123, 'loss/train': 2.405144214630127} 08/30/2021 14:06:58 - INFO - __main__ - Step 5125: {'lr': 0.000499450523372421, 'samples': 984000, 'steps': 5124, 'loss/train': 1.82676362991333} 08/30/2021 14:07:00 - INFO - __main__ - Step 5126: {'lr': 0.0004994501716675303, 'samples': 984192, 'steps': 5125, 'loss/train': 2.571577310562134} 08/30/2021 14:07:00 - INFO - __main__ - Step 5127: {'lr': 0.0004994498198502412, 'samples': 984384, 'steps': 5126, 'loss/train': 2.3094050884246826} 08/30/2021 14:07:01 - INFO - __main__ - Step 5128: {'lr': 0.0004994494679205539, 'samples': 984576, 'steps': 5127, 'loss/train': 2.3609585762023926} 08/30/2021 14:07:01 - INFO - __main__ - Step 5129: {'lr': 0.0004994491158784684, 'samples': 984768, 'steps': 5128, 'loss/train': 2.3722198009490967} 08/30/2021 14:07:02 - INFO - __main__ - Step 5130: {'lr': 0.0004994487637239851, 'samples': 984960, 'steps': 5129, 'loss/train': 2.0476746559143066} 08/30/2021 14:07:03 - INFO - __main__ - Step 5131: {'lr': 0.0004994484114571041, 'samples': 985152, 'steps': 5130, 'loss/train': 2.3820438385009766} 08/30/2021 14:07:03 - INFO - __main__ - Step 5132: {'lr': 0.0004994480590778254, 'samples': 985344, 'steps': 5131, 'loss/train': 1.8114874362945557} 08/30/2021 14:07:04 - INFO - __main__ - Step 5133: {'lr': 0.0004994477065861493, 'samples': 985536, 'steps': 5132, 'loss/train': 2.685075521469116} 08/30/2021 14:07:04 - INFO - __main__ - Step 5134: {'lr': 0.0004994473539820758, 'samples': 985728, 'steps': 5133, 'loss/train': 2.043989419937134} 08/30/2021 14:07:04 - INFO - __main__ - Step 5135: {'lr': 0.0004994470012656052, 'samples': 985920, 'steps': 5134, 'loss/train': 2.3362574577331543} 08/30/2021 14:07:06 - INFO - __main__ - Step 5136: {'lr': 0.0004994466484367378, 'samples': 986112, 'steps': 5135, 'loss/train': 2.7829253673553467} 08/30/2021 14:07:07 - INFO - __main__ - Step 5137: {'lr': 0.0004994462954954734, 'samples': 986304, 'steps': 5136, 'loss/train': 2.145165205001831} 08/30/2021 14:07:07 - INFO - __main__ - Step 5138: {'lr': 0.0004994459424418125, 'samples': 986496, 'steps': 5137, 'loss/train': 1.6925978660583496} 08/30/2021 14:07:07 - INFO - __main__ - Step 5139: {'lr': 0.000499445589275755, 'samples': 986688, 'steps': 5138, 'loss/train': 2.0861947536468506} 08/30/2021 14:07:08 - INFO - __main__ - Step 5140: {'lr': 0.0004994452359973012, 'samples': 986880, 'steps': 5139, 'loss/train': 2.047111749649048} 08/30/2021 14:07:09 - INFO - __main__ - Step 5141: {'lr': 0.0004994448826064512, 'samples': 987072, 'steps': 5140, 'loss/train': 1.8532780408859253} 08/30/2021 14:07:10 - INFO - __main__ - Step 5142: {'lr': 0.0004994445291032053, 'samples': 987264, 'steps': 5141, 'loss/train': 1.6752511262893677} 08/30/2021 14:07:10 - INFO - __main__ - Step 5143: {'lr': 0.0004994441754875634, 'samples': 987456, 'steps': 5142, 'loss/train': 1.545415997505188} 08/30/2021 14:07:11 - INFO - __main__ - Step 5144: {'lr': 0.0004994438217595259, 'samples': 987648, 'steps': 5143, 'loss/train': 2.0602314472198486} 08/30/2021 14:07:11 - INFO - __main__ - Step 5145: {'lr': 0.0004994434679190928, 'samples': 987840, 'steps': 5144, 'loss/train': 2.4933364391326904} 08/30/2021 14:07:11 - INFO - __main__ - Step 5146: {'lr': 0.0004994431139662643, 'samples': 988032, 'steps': 5145, 'loss/train': 0.6041566133499146} 08/30/2021 14:07:12 - INFO - __main__ - Step 5147: {'lr': 0.0004994427599010406, 'samples': 988224, 'steps': 5146, 'loss/train': 2.0003671646118164} 08/30/2021 14:07:13 - INFO - __main__ - Step 5148: {'lr': 0.0004994424057234219, 'samples': 988416, 'steps': 5147, 'loss/train': 2.1199288368225098} 08/30/2021 14:07:14 - INFO - __main__ - Step 5149: {'lr': 0.0004994420514334082, 'samples': 988608, 'steps': 5148, 'loss/train': 2.1466615200042725} 08/30/2021 14:07:14 - INFO - __main__ - Step 5150: {'lr': 0.0004994416970309999, 'samples': 988800, 'steps': 5149, 'loss/train': 2.6275534629821777} 08/30/2021 14:07:15 - INFO - __main__ - Step 5151: {'lr': 0.0004994413425161969, 'samples': 988992, 'steps': 5150, 'loss/train': 1.93808114528656} 08/30/2021 14:07:15 - INFO - __main__ - Step 5152: {'lr': 0.0004994409878889995, 'samples': 989184, 'steps': 5151, 'loss/train': 1.8684135675430298} 08/30/2021 14:07:16 - INFO - __main__ - Step 5153: {'lr': 0.0004994406331494079, 'samples': 989376, 'steps': 5152, 'loss/train': 3.0381879806518555} 08/30/2021 14:07:17 - INFO - __main__ - Step 5154: {'lr': 0.0004994402782974222, 'samples': 989568, 'steps': 5153, 'loss/train': 2.2175939083099365} 08/30/2021 14:07:17 - INFO - __main__ - Step 5155: {'lr': 0.0004994399233330426, 'samples': 989760, 'steps': 5154, 'loss/train': 2.338268280029297} 08/30/2021 14:07:18 - INFO - __main__ - Step 5156: {'lr': 0.000499439568256269, 'samples': 989952, 'steps': 5155, 'loss/train': 2.682722568511963} 08/30/2021 14:07:18 - INFO - __main__ - Step 5157: {'lr': 0.000499439213067102, 'samples': 990144, 'steps': 5156, 'loss/train': 1.8515269756317139} 08/30/2021 14:07:18 - INFO - __main__ - Step 5158: {'lr': 0.0004994388577655415, 'samples': 990336, 'steps': 5157, 'loss/train': 1.8539119958877563} 08/30/2021 14:07:21 - INFO - __main__ - Step 5159: {'lr': 0.0004994385023515876, 'samples': 990528, 'steps': 5158, 'loss/train': 2.0890052318573} 08/30/2021 14:07:21 - INFO - __main__ - Step 5160: {'lr': 0.0004994381468252406, 'samples': 990720, 'steps': 5159, 'loss/train': 0.3400194048881531} 08/30/2021 14:07:21 - INFO - __main__ - Step 5161: {'lr': 0.0004994377911865007, 'samples': 990912, 'steps': 5160, 'loss/train': 2.185608386993408} 08/30/2021 14:07:22 - INFO - __main__ - Step 5162: {'lr': 0.0004994374354353679, 'samples': 991104, 'steps': 5161, 'loss/train': 1.9886928796768188} 08/30/2021 14:07:22 - INFO - __main__ - Step 5163: {'lr': 0.0004994370795718425, 'samples': 991296, 'steps': 5162, 'loss/train': 2.439370632171631} 08/30/2021 14:07:23 - INFO - __main__ - Step 5164: {'lr': 0.0004994367235959245, 'samples': 991488, 'steps': 5163, 'loss/train': 3.3344357013702393} 08/30/2021 14:07:24 - INFO - __main__ - Step 5165: {'lr': 0.0004994363675076143, 'samples': 991680, 'steps': 5164, 'loss/train': 2.0596539974212646} 08/30/2021 14:07:24 - INFO - __main__ - Step 5166: {'lr': 0.0004994360113069118, 'samples': 991872, 'steps': 5165, 'loss/train': 2.35343074798584} 08/30/2021 14:07:25 - INFO - __main__ - Step 5167: {'lr': 0.0004994356549938173, 'samples': 992064, 'steps': 5166, 'loss/train': 1.1098432540893555} 08/30/2021 14:07:25 - INFO - __main__ - Step 5168: {'lr': 0.000499435298568331, 'samples': 992256, 'steps': 5167, 'loss/train': 2.6775572299957275} 08/30/2021 14:07:27 - INFO - __main__ - Step 5169: {'lr': 0.000499434942030453, 'samples': 992448, 'steps': 5168, 'loss/train': 1.8229023218154907} 08/30/2021 14:07:27 - INFO - __main__ - Step 5170: {'lr': 0.0004994345853801834, 'samples': 992640, 'steps': 5169, 'loss/train': 2.324307918548584} 08/30/2021 14:07:27 - INFO - __main__ - Step 5171: {'lr': 0.0004994342286175225, 'samples': 992832, 'steps': 5170, 'loss/train': 1.863842248916626} 08/30/2021 14:07:28 - INFO - __main__ - Step 5172: {'lr': 0.0004994338717424704, 'samples': 993024, 'steps': 5171, 'loss/train': 0.31887251138687134} 08/30/2021 14:07:28 - INFO - __main__ - Step 5173: {'lr': 0.0004994335147550272, 'samples': 993216, 'steps': 5172, 'loss/train': 1.6892577409744263} 08/30/2021 14:07:30 - INFO - __main__ - Step 5174: {'lr': 0.0004994331576551931, 'samples': 993408, 'steps': 5173, 'loss/train': 1.34635591506958} 08/30/2021 14:07:30 - INFO - __main__ - Step 5175: {'lr': 0.0004994328004429683, 'samples': 993600, 'steps': 5174, 'loss/train': 1.6297293901443481} 08/30/2021 14:07:30 - INFO - __main__ - Step 5176: {'lr': 0.000499432443118353, 'samples': 993792, 'steps': 5175, 'loss/train': 2.1387791633605957} 08/30/2021 14:07:31 - INFO - __main__ - Step 5177: {'lr': 0.0004994320856813471, 'samples': 993984, 'steps': 5176, 'loss/train': 2.3840878009796143} 08/30/2021 14:07:31 - INFO - __main__ - Step 5178: {'lr': 0.000499431728131951, 'samples': 994176, 'steps': 5177, 'loss/train': 2.0232748985290527} 08/30/2021 14:07:33 - INFO - __main__ - Step 5179: {'lr': 0.0004994313704701648, 'samples': 994368, 'steps': 5178, 'loss/train': 1.6016216278076172} 08/30/2021 14:07:33 - INFO - __main__ - Step 5180: {'lr': 0.0004994310126959887, 'samples': 994560, 'steps': 5179, 'loss/train': 1.867646336555481} 08/30/2021 14:07:34 - INFO - __main__ - Step 5181: {'lr': 0.000499430654809423, 'samples': 994752, 'steps': 5180, 'loss/train': 2.151320695877075} 08/30/2021 14:07:34 - INFO - __main__ - Step 5182: {'lr': 0.0004994302968104675, 'samples': 994944, 'steps': 5181, 'loss/train': 1.1911743879318237} 08/30/2021 14:07:34 - INFO - __main__ - Step 5183: {'lr': 0.0004994299386991227, 'samples': 995136, 'steps': 5182, 'loss/train': 2.3783390522003174} 08/30/2021 14:07:36 - INFO - __main__ - Step 5184: {'lr': 0.0004994295804753885, 'samples': 995328, 'steps': 5183, 'loss/train': 1.7106528282165527} 08/30/2021 14:07:37 - INFO - __main__ - Step 5185: {'lr': 0.0004994292221392652, 'samples': 995520, 'steps': 5184, 'loss/train': 2.477846145629883} 08/30/2021 14:07:37 - INFO - __main__ - Step 5186: {'lr': 0.000499428863690753, 'samples': 995712, 'steps': 5185, 'loss/train': 1.889315128326416} 08/30/2021 14:07:37 - INFO - __main__ - Step 5187: {'lr': 0.0004994285051298519, 'samples': 995904, 'steps': 5186, 'loss/train': 1.52708899974823} 08/30/2021 14:07:38 - INFO - __main__ - Step 5188: {'lr': 0.0004994281464565623, 'samples': 996096, 'steps': 5187, 'loss/train': 2.420551061630249} 08/30/2021 14:07:39 - INFO - __main__ - Step 5189: {'lr': 0.0004994277876708841, 'samples': 996288, 'steps': 5188, 'loss/train': 2.140460729598999} 08/30/2021 14:07:40 - INFO - __main__ - Step 5190: {'lr': 0.0004994274287728177, 'samples': 996480, 'steps': 5189, 'loss/train': 2.421818733215332} 08/30/2021 14:07:40 - INFO - __main__ - Step 5191: {'lr': 0.0004994270697623631, 'samples': 996672, 'steps': 5190, 'loss/train': 2.2945523262023926} 08/30/2021 14:07:40 - INFO - __main__ - Step 5192: {'lr': 0.0004994267106395205, 'samples': 996864, 'steps': 5191, 'loss/train': 2.2751009464263916} 08/30/2021 14:07:41 - INFO - __main__ - Step 5193: {'lr': 0.0004994263514042901, 'samples': 997056, 'steps': 5192, 'loss/train': 2.1930885314941406} 08/30/2021 14:07:42 - INFO - __main__ - Step 5194: {'lr': 0.0004994259920566719, 'samples': 997248, 'steps': 5193, 'loss/train': 2.067279815673828} 08/30/2021 14:07:42 - INFO - __main__ - Step 5195: {'lr': 0.0004994256325966663, 'samples': 997440, 'steps': 5194, 'loss/train': 2.3864243030548096} 08/30/2021 14:07:43 - INFO - __main__ - Step 5196: {'lr': 0.0004994252730242734, 'samples': 997632, 'steps': 5195, 'loss/train': 1.791703701019287} 08/30/2021 14:07:43 - INFO - __main__ - Step 5197: {'lr': 0.0004994249133394933, 'samples': 997824, 'steps': 5196, 'loss/train': 2.1101086139678955} 08/30/2021 14:07:44 - INFO - __main__ - Step 5198: {'lr': 0.0004994245535423262, 'samples': 998016, 'steps': 5197, 'loss/train': 2.9943315982818604} 08/30/2021 14:07:45 - INFO - __main__ - Step 5199: {'lr': 0.0004994241936327722, 'samples': 998208, 'steps': 5198, 'loss/train': 2.202904224395752} 08/30/2021 14:07:45 - INFO - __main__ - Step 5200: {'lr': 0.0004994238336108315, 'samples': 998400, 'steps': 5199, 'loss/train': 2.7223398685455322} 08/30/2021 14:07:46 - INFO - __main__ - Step 5201: {'lr': 0.0004994234734765043, 'samples': 998592, 'steps': 5200, 'loss/train': 1.8800334930419922} 08/30/2021 14:07:46 - INFO - __main__ - Step 5202: {'lr': 0.0004994231132297907, 'samples': 998784, 'steps': 5201, 'loss/train': 2.0159521102905273} 08/30/2021 14:07:47 - INFO - __main__ - Step 5203: {'lr': 0.0004994227528706909, 'samples': 998976, 'steps': 5202, 'loss/train': 1.6396052837371826} 08/30/2021 14:07:47 - INFO - __main__ - Step 5204: {'lr': 0.0004994223923992052, 'samples': 999168, 'steps': 5203, 'loss/train': 1.8067177534103394} 08/30/2021 14:07:49 - INFO - __main__ - Step 5205: {'lr': 0.0004994220318153334, 'samples': 999360, 'steps': 5204, 'loss/train': 1.9630169868469238} 08/30/2021 14:07:49 - INFO - __main__ - Step 5206: {'lr': 0.000499421671119076, 'samples': 999552, 'steps': 5205, 'loss/train': 2.928579568862915} 08/30/2021 14:07:49 - INFO - __main__ - Step 5207: {'lr': 0.0004994213103104331, 'samples': 999744, 'steps': 5206, 'loss/train': 0.20592327415943146} 08/30/2021 14:07:50 - INFO - __main__ - Step 5208: {'lr': 0.0004994209493894046, 'samples': 999936, 'steps': 5207, 'loss/train': 1.9329336881637573} 08/30/2021 14:07:50 - INFO - __main__ - Step 5209: {'lr': 0.000499420588355991, 'samples': 1000128, 'steps': 5208, 'loss/train': 1.758858323097229} 08/30/2021 14:07:52 - INFO - __main__ - Step 5210: {'lr': 0.0004994202272101923, 'samples': 1000320, 'steps': 5209, 'loss/train': 1.7124828100204468} 08/30/2021 14:07:53 - INFO - __main__ - Step 5211: {'lr': 0.0004994198659520087, 'samples': 1000512, 'steps': 5210, 'loss/train': 1.8692842721939087} 08/30/2021 14:07:53 - INFO - __main__ - Step 5212: {'lr': 0.0004994195045814404, 'samples': 1000704, 'steps': 5211, 'loss/train': 1.556260108947754} 08/30/2021 14:07:54 - INFO - __main__ - Step 5213: {'lr': 0.0004994191430984876, 'samples': 1000896, 'steps': 5212, 'loss/train': 2.590009927749634} 08/30/2021 14:07:54 - INFO - __main__ - Step 5214: {'lr': 0.0004994187815031502, 'samples': 1001088, 'steps': 5213, 'loss/train': 1.8999031782150269} 08/30/2021 14:07:56 - INFO - __main__ - Step 5215: {'lr': 0.0004994184197954286, 'samples': 1001280, 'steps': 5214, 'loss/train': 1.627764105796814} 08/30/2021 14:07:56 - INFO - __main__ - Step 5216: {'lr': 0.000499418057975323, 'samples': 1001472, 'steps': 5215, 'loss/train': 1.9653759002685547} 08/30/2021 14:07:57 - INFO - __main__ - Step 5217: {'lr': 0.0004994176960428333, 'samples': 1001664, 'steps': 5216, 'loss/train': 0.42130613327026367} 08/30/2021 14:07:57 - INFO - __main__ - Step 5218: {'lr': 0.00049941733399796, 'samples': 1001856, 'steps': 5217, 'loss/train': 2.122182607650757} 08/30/2021 14:07:57 - INFO - __main__ - Step 5219: {'lr': 0.000499416971840703, 'samples': 1002048, 'steps': 5218, 'loss/train': 1.9193789958953857} 08/30/2021 14:07:59 - INFO - __main__ - Step 5220: {'lr': 0.0004994166095710626, 'samples': 1002240, 'steps': 5219, 'loss/train': 1.726962924003601} 08/30/2021 14:07:59 - INFO - __main__ - Step 5221: {'lr': 0.000499416247189039, 'samples': 1002432, 'steps': 5220, 'loss/train': 2.058763027191162} 08/30/2021 14:08:00 - INFO - __main__ - Step 5222: {'lr': 0.0004994158846946321, 'samples': 1002624, 'steps': 5221, 'loss/train': 2.678605079650879} 08/30/2021 14:08:00 - INFO - __main__ - Step 5223: {'lr': 0.0004994155220878425, 'samples': 1002816, 'steps': 5222, 'loss/train': 1.7736533880233765} 08/30/2021 14:08:00 - INFO - __main__ - Step 5224: {'lr': 0.0004994151593686699, 'samples': 1003008, 'steps': 5223, 'loss/train': 2.163242816925049} 08/30/2021 14:08:02 - INFO - __main__ - Step 5225: {'lr': 0.0004994147965371147, 'samples': 1003200, 'steps': 5224, 'loss/train': 2.59200119972229} 08/30/2021 14:08:02 - INFO - __main__ - Step 5226: {'lr': 0.0004994144335931772, 'samples': 1003392, 'steps': 5225, 'loss/train': 1.7423933744430542} 08/30/2021 14:08:03 - INFO - __main__ - Step 5227: {'lr': 0.0004994140705368573, 'samples': 1003584, 'steps': 5226, 'loss/train': 2.2525906562805176} 08/30/2021 14:08:03 - INFO - __main__ - Step 5228: {'lr': 0.0004994137073681552, 'samples': 1003776, 'steps': 5227, 'loss/train': 2.3387978076934814} 08/30/2021 14:08:03 - INFO - __main__ - Step 5229: {'lr': 0.0004994133440870712, 'samples': 1003968, 'steps': 5228, 'loss/train': 2.445462942123413} 08/30/2021 14:08:05 - INFO - __main__ - Step 5230: {'lr': 0.0004994129806936054, 'samples': 1004160, 'steps': 5229, 'loss/train': 0.27603963017463684} 08/30/2021 14:08:05 - INFO - __main__ - Step 5231: {'lr': 0.000499412617187758, 'samples': 1004352, 'steps': 5230, 'loss/train': 2.800638437271118} 08/30/2021 14:08:06 - INFO - __main__ - Step 5232: {'lr': 0.0004994122535695291, 'samples': 1004544, 'steps': 5231, 'loss/train': 1.6900337934494019} 08/30/2021 14:08:06 - INFO - __main__ - Step 5233: {'lr': 0.0004994118898389189, 'samples': 1004736, 'steps': 5232, 'loss/train': 2.201263189315796} 08/30/2021 14:08:06 - INFO - __main__ - Step 5234: {'lr': 0.0004994115259959274, 'samples': 1004928, 'steps': 5233, 'loss/train': 2.0528626441955566} 08/30/2021 14:08:08 - INFO - __main__ - Step 5235: {'lr': 0.0004994111620405551, 'samples': 1005120, 'steps': 5234, 'loss/train': 1.8250207901000977} 08/30/2021 14:08:09 - INFO - __main__ - Step 5236: {'lr': 0.0004994107979728019, 'samples': 1005312, 'steps': 5235, 'loss/train': 2.6029181480407715} 08/30/2021 14:08:09 - INFO - __main__ - Step 5237: {'lr': 0.0004994104337926681, 'samples': 1005504, 'steps': 5236, 'loss/train': 0.3338676393032074} 08/30/2021 14:08:09 - INFO - __main__ - Step 5238: {'lr': 0.0004994100695001537, 'samples': 1005696, 'steps': 5237, 'loss/train': 1.8283063173294067} 08/30/2021 14:08:10 - INFO - __main__ - Step 5239: {'lr': 0.0004994097050952591, 'samples': 1005888, 'steps': 5238, 'loss/train': 2.0244762897491455} 08/30/2021 14:08:10 - INFO - __main__ - Step 5240: {'lr': 0.0004994093405779842, 'samples': 1006080, 'steps': 5239, 'loss/train': 1.7621753215789795} 08/30/2021 14:08:11 - INFO - __main__ - Step 5241: {'lr': 0.0004994089759483294, 'samples': 1006272, 'steps': 5240, 'loss/train': 2.115987777709961} 08/30/2021 14:08:12 - INFO - __main__ - Step 5242: {'lr': 0.0004994086112062948, 'samples': 1006464, 'steps': 5241, 'loss/train': 2.5955007076263428} 08/30/2021 14:08:12 - INFO - __main__ - Step 5243: {'lr': 0.0004994082463518804, 'samples': 1006656, 'steps': 5242, 'loss/train': 1.8649080991744995} 08/30/2021 14:08:13 - INFO - __main__ - Step 5244: {'lr': 0.0004994078813850865, 'samples': 1006848, 'steps': 5243, 'loss/train': 2.2834858894348145} 08/30/2021 14:08:13 - INFO - __main__ - Step 5245: {'lr': 0.0004994075163059134, 'samples': 1007040, 'steps': 5244, 'loss/train': 1.4247674942016602} 08/30/2021 14:08:15 - INFO - __main__ - Step 5246: {'lr': 0.0004994071511143609, 'samples': 1007232, 'steps': 5245, 'loss/train': 1.9448771476745605} 08/30/2021 14:08:15 - INFO - __main__ - Step 5247: {'lr': 0.0004994067858104296, 'samples': 1007424, 'steps': 5246, 'loss/train': 2.3362410068511963} 08/30/2021 14:08:15 - INFO - __main__ - Step 5248: {'lr': 0.0004994064203941195, 'samples': 1007616, 'steps': 5247, 'loss/train': 1.9038634300231934} 08/30/2021 14:08:16 - INFO - __main__ - Step 5249: {'lr': 0.0004994060548654304, 'samples': 1007808, 'steps': 5248, 'loss/train': 2.086329460144043} 08/30/2021 14:08:16 - INFO - __main__ - Step 5250: {'lr': 0.000499405689224363, 'samples': 1008000, 'steps': 5249, 'loss/train': 1.9584294557571411} 08/30/2021 14:08:17 - INFO - __main__ - Step 5251: {'lr': 0.0004994053234709172, 'samples': 1008192, 'steps': 5250, 'loss/train': 2.260010242462158} 08/30/2021 14:08:18 - INFO - __main__ - Step 5252: {'lr': 0.0004994049576050933, 'samples': 1008384, 'steps': 5251, 'loss/train': 2.1873691082000732} 08/30/2021 14:08:18 - INFO - __main__ - Step 5253: {'lr': 0.0004994045916268913, 'samples': 1008576, 'steps': 5252, 'loss/train': 1.9193403720855713} 08/30/2021 14:08:19 - INFO - __main__ - Step 5254: {'lr': 0.0004994042255363115, 'samples': 1008768, 'steps': 5253, 'loss/train': 2.6118009090423584} 08/30/2021 14:08:19 - INFO - __main__ - Step 5255: {'lr': 0.0004994038593333539, 'samples': 1008960, 'steps': 5254, 'loss/train': 2.529608726501465} 08/30/2021 14:08:21 - INFO - __main__ - Step 5256: {'lr': 0.0004994034930180188, 'samples': 1009152, 'steps': 5255, 'loss/train': 2.4949984550476074} 08/30/2021 14:08:21 - INFO - __main__ - Step 5257: {'lr': 0.0004994031265903063, 'samples': 1009344, 'steps': 5256, 'loss/train': 2.3542065620422363} 08/30/2021 14:08:21 - INFO - __main__ - Step 5258: {'lr': 0.0004994027600502167, 'samples': 1009536, 'steps': 5257, 'loss/train': 0.22891099750995636} 08/30/2021 14:08:22 - INFO - __main__ - Step 5259: {'lr': 0.00049940239339775, 'samples': 1009728, 'steps': 5258, 'loss/train': 1.789426565170288} 08/30/2021 14:08:22 - INFO - __main__ - Step 5260: {'lr': 0.0004994020266329064, 'samples': 1009920, 'steps': 5259, 'loss/train': 1.8118581771850586} 08/30/2021 14:08:24 - INFO - __main__ - Step 5261: {'lr': 0.0004994016597556862, 'samples': 1010112, 'steps': 5260, 'loss/train': 2.465618371963501} 08/30/2021 14:08:25 - INFO - __main__ - Step 5262: {'lr': 0.0004994012927660894, 'samples': 1010304, 'steps': 5261, 'loss/train': 3.0062427520751953} 08/30/2021 14:08:25 - INFO - __main__ - Step 5263: {'lr': 0.0004994009256641162, 'samples': 1010496, 'steps': 5262, 'loss/train': 2.997375249862671} 08/30/2021 14:08:25 - INFO - __main__ - Step 5264: {'lr': 0.0004994005584497667, 'samples': 1010688, 'steps': 5263, 'loss/train': 1.7763981819152832} 08/30/2021 14:08:26 - INFO - __main__ - Step 5265: {'lr': 0.0004994001911230413, 'samples': 1010880, 'steps': 5264, 'loss/train': 2.640120029449463} 08/30/2021 14:08:26 - INFO - __main__ - Step 5266: {'lr': 0.00049939982368394, 'samples': 1011072, 'steps': 5265, 'loss/train': 2.1227917671203613} 08/30/2021 14:08:28 - INFO - __main__ - Step 5267: {'lr': 0.000499399456132463, 'samples': 1011264, 'steps': 5266, 'loss/train': 2.0941662788391113} 08/30/2021 14:08:29 - INFO - __main__ - Step 5268: {'lr': 0.0004993990884686105, 'samples': 1011456, 'steps': 5267, 'loss/train': 2.4199488162994385} 08/30/2021 14:08:29 - INFO - __main__ - Step 5269: {'lr': 0.0004993987206923825, 'samples': 1011648, 'steps': 5268, 'loss/train': 6.3083415031433105} 08/30/2021 14:08:29 - INFO - __main__ - Step 5270: {'lr': 0.0004993983528037793, 'samples': 1011840, 'steps': 5269, 'loss/train': 1.8794220685958862} 08/30/2021 14:08:30 - INFO - __main__ - Step 5271: {'lr': 0.0004993979848028011, 'samples': 1012032, 'steps': 5270, 'loss/train': 2.3997039794921875} 08/30/2021 14:08:30 - INFO - __main__ - Step 5272: {'lr': 0.000499397616689448, 'samples': 1012224, 'steps': 5271, 'loss/train': 1.3626079559326172} 08/30/2021 14:08:31 - INFO - __main__ - Step 5273: {'lr': 0.0004993972484637202, 'samples': 1012416, 'steps': 5272, 'loss/train': 1.7811495065689087} 08/30/2021 14:08:32 - INFO - __main__ - Step 5274: {'lr': 0.0004993968801256178, 'samples': 1012608, 'steps': 5273, 'loss/train': 2.639021635055542} 08/30/2021 14:08:32 - INFO - __main__ - Step 5275: {'lr': 0.0004993965116751411, 'samples': 1012800, 'steps': 5274, 'loss/train': 1.9918279647827148} 08/30/2021 14:08:33 - INFO - __main__ - Step 5276: {'lr': 0.0004993961431122901, 'samples': 1012992, 'steps': 5275, 'loss/train': 2.6671645641326904} 08/30/2021 14:08:33 - INFO - __main__ - Step 5277: {'lr': 0.0004993957744370651, 'samples': 1013184, 'steps': 5276, 'loss/train': 1.9408828020095825} 08/30/2021 14:08:34 - INFO - __main__ - Step 5278: {'lr': 0.0004993954056494662, 'samples': 1013376, 'steps': 5277, 'loss/train': 1.4799178838729858} 08/30/2021 14:08:35 - INFO - __main__ - Step 5279: {'lr': 0.0004993950367494936, 'samples': 1013568, 'steps': 5278, 'loss/train': 2.6586716175079346} 08/30/2021 14:08:35 - INFO - __main__ - Step 5280: {'lr': 0.0004993946677371474, 'samples': 1013760, 'steps': 5279, 'loss/train': 2.5127079486846924} 08/30/2021 14:08:36 - INFO - __main__ - Step 5281: {'lr': 0.0004993942986124278, 'samples': 1013952, 'steps': 5280, 'loss/train': 2.0884318351745605} 08/30/2021 14:08:36 - INFO - __main__ - Step 5282: {'lr': 0.000499393929375335, 'samples': 1014144, 'steps': 5281, 'loss/train': 2.547905445098877} 08/30/2021 14:08:37 - INFO - __main__ - Step 5283: {'lr': 0.0004993935600258691, 'samples': 1014336, 'steps': 5282, 'loss/train': 2.7553727626800537} 08/30/2021 14:08:38 - INFO - __main__ - Step 5284: {'lr': 0.0004993931905640305, 'samples': 1014528, 'steps': 5283, 'loss/train': 1.4387353658676147} 08/30/2021 14:08:38 - INFO - __main__ - Step 5285: {'lr': 0.000499392820989819, 'samples': 1014720, 'steps': 5284, 'loss/train': 2.5183651447296143} 08/30/2021 14:08:39 - INFO - __main__ - Step 5286: {'lr': 0.0004993924513032349, 'samples': 1014912, 'steps': 5285, 'loss/train': 1.3854247331619263} 08/30/2021 14:08:39 - INFO - __main__ - Step 5287: {'lr': 0.0004993920815042785, 'samples': 1015104, 'steps': 5286, 'loss/train': 2.466095447540283} 08/30/2021 14:08:41 - INFO - __main__ - Step 5288: {'lr': 0.0004993917115929498, 'samples': 1015296, 'steps': 5287, 'loss/train': 1.8673524856567383} 08/30/2021 14:08:41 - INFO - __main__ - Step 5289: {'lr': 0.0004993913415692492, 'samples': 1015488, 'steps': 5288, 'loss/train': 2.0241940021514893} 08/30/2021 14:08:42 - INFO - __main__ - Step 5290: {'lr': 0.0004993909714331766, 'samples': 1015680, 'steps': 5289, 'loss/train': 2.5281755924224854} 08/30/2021 14:08:42 - INFO - __main__ - Step 5291: {'lr': 0.0004993906011847323, 'samples': 1015872, 'steps': 5290, 'loss/train': 2.409820318222046} 08/30/2021 14:08:42 - INFO - __main__ - Step 5292: {'lr': 0.0004993902308239164, 'samples': 1016064, 'steps': 5291, 'loss/train': 2.2571828365325928} 08/30/2021 14:08:43 - INFO - __main__ - Step 5293: {'lr': 0.0004993898603507292, 'samples': 1016256, 'steps': 5292, 'loss/train': 2.139096736907959} 08/30/2021 14:08:44 - INFO - __main__ - Step 5294: {'lr': 0.0004993894897651706, 'samples': 1016448, 'steps': 5293, 'loss/train': 0.3849567174911499} 08/30/2021 14:08:45 - INFO - __main__ - Step 5295: {'lr': 0.0004993891190672411, 'samples': 1016640, 'steps': 5294, 'loss/train': 1.9131169319152832} 08/30/2021 14:08:45 - INFO - __main__ - Step 5296: {'lr': 0.0004993887482569407, 'samples': 1016832, 'steps': 5295, 'loss/train': 2.723391532897949} 08/30/2021 14:08:46 - INFO - __main__ - Step 5297: {'lr': 0.0004993883773342695, 'samples': 1017024, 'steps': 5296, 'loss/train': 1.3873577117919922} 08/30/2021 14:08:46 - INFO - __main__ - Step 5298: {'lr': 0.0004993880062992279, 'samples': 1017216, 'steps': 5297, 'loss/train': 2.1457936763763428} 08/30/2021 14:08:48 - INFO - __main__ - Step 5299: {'lr': 0.0004993876351518157, 'samples': 1017408, 'steps': 5298, 'loss/train': 1.902564287185669} 08/30/2021 14:08:48 - INFO - __main__ - Step 5300: {'lr': 0.0004993872638920335, 'samples': 1017600, 'steps': 5299, 'loss/train': 2.003303050994873} 08/30/2021 14:08:49 - INFO - __main__ - Step 5301: {'lr': 0.0004993868925198811, 'samples': 1017792, 'steps': 5300, 'loss/train': 2.5706300735473633} 08/30/2021 14:08:49 - INFO - __main__ - Step 5302: {'lr': 0.0004993865210353588, 'samples': 1017984, 'steps': 5301, 'loss/train': 0.9811980128288269} 08/30/2021 14:08:49 - INFO - __main__ - Step 5303: {'lr': 0.0004993861494384669, 'samples': 1018176, 'steps': 5302, 'loss/train': 2.2012617588043213} 08/30/2021 14:08:50 - INFO - __main__ - Step 5304: {'lr': 0.0004993857777292053, 'samples': 1018368, 'steps': 5303, 'loss/train': 0.6270977854728699} 08/30/2021 14:08:51 - INFO - __main__ - Step 5305: {'lr': 0.0004993854059075745, 'samples': 1018560, 'steps': 5304, 'loss/train': 0.540199339389801} 08/30/2021 14:08:52 - INFO - __main__ - Step 5306: {'lr': 0.0004993850339735744, 'samples': 1018752, 'steps': 5305, 'loss/train': 2.128061294555664} 08/30/2021 14:08:52 - INFO - __main__ - Step 5307: {'lr': 0.0004993846619272052, 'samples': 1018944, 'steps': 5306, 'loss/train': 2.2702066898345947} 08/30/2021 14:08:52 - INFO - __main__ - Step 5308: {'lr': 0.0004993842897684672, 'samples': 1019136, 'steps': 5307, 'loss/train': 1.5475096702575684} 08/30/2021 14:08:53 - INFO - __main__ - Step 5309: {'lr': 0.0004993839174973604, 'samples': 1019328, 'steps': 5308, 'loss/train': 1.6055527925491333} 08/30/2021 14:08:54 - INFO - __main__ - Step 5310: {'lr': 0.0004993835451138851, 'samples': 1019520, 'steps': 5309, 'loss/train': 2.285568952560425} 08/30/2021 14:08:55 - INFO - __main__ - Step 5311: {'lr': 0.0004993831726180414, 'samples': 1019712, 'steps': 5310, 'loss/train': 2.526824474334717} 08/30/2021 14:08:55 - INFO - __main__ - Step 5312: {'lr': 0.0004993828000098296, 'samples': 1019904, 'steps': 5311, 'loss/train': 2.181748390197754} 08/30/2021 14:08:55 - INFO - __main__ - Step 5313: {'lr': 0.0004993824272892497, 'samples': 1020096, 'steps': 5312, 'loss/train': 2.0193381309509277} 08/30/2021 14:08:56 - INFO - __main__ - Step 5314: {'lr': 0.0004993820544563018, 'samples': 1020288, 'steps': 5313, 'loss/train': 2.558633804321289} 08/30/2021 14:08:56 - INFO - __main__ - Step 5315: {'lr': 0.0004993816815109863, 'samples': 1020480, 'steps': 5314, 'loss/train': 1.2283902168273926} 08/30/2021 14:08:58 - INFO - __main__ - Step 5316: {'lr': 0.0004993813084533033, 'samples': 1020672, 'steps': 5315, 'loss/train': 1.9092395305633545} 08/30/2021 14:08:58 - INFO - __main__ - Step 5317: {'lr': 0.0004993809352832529, 'samples': 1020864, 'steps': 5316, 'loss/train': 2.1001288890838623} 08/30/2021 14:08:58 - INFO - __main__ - Step 5318: {'lr': 0.0004993805620008353, 'samples': 1021056, 'steps': 5317, 'loss/train': 1.6625019311904907} 08/30/2021 14:08:59 - INFO - __main__ - Step 5319: {'lr': 0.0004993801886060506, 'samples': 1021248, 'steps': 5318, 'loss/train': 2.027336597442627} 08/30/2021 14:08:59 - INFO - __main__ - Step 5320: {'lr': 0.0004993798150988991, 'samples': 1021440, 'steps': 5319, 'loss/train': 2.322761058807373} 08/30/2021 14:09:01 - INFO - __main__ - Step 5321: {'lr': 0.0004993794414793808, 'samples': 1021632, 'steps': 5320, 'loss/train': 2.293020725250244} 08/30/2021 14:09:01 - INFO - __main__ - Step 5322: {'lr': 0.0004993790677474962, 'samples': 1021824, 'steps': 5321, 'loss/train': 2.055722951889038} 08/30/2021 14:09:02 - INFO - __main__ - Step 5323: {'lr': 0.0004993786939032451, 'samples': 1022016, 'steps': 5322, 'loss/train': 2.547273635864258} 08/30/2021 14:09:02 - INFO - __main__ - Step 5324: {'lr': 0.0004993783199466278, 'samples': 1022208, 'steps': 5323, 'loss/train': 2.078728675842285} 08/30/2021 14:09:02 - INFO - __main__ - Step 5325: {'lr': 0.0004993779458776444, 'samples': 1022400, 'steps': 5324, 'loss/train': 2.3225064277648926} 08/30/2021 14:09:04 - INFO - __main__ - Step 5326: {'lr': 0.0004993775716962953, 'samples': 1022592, 'steps': 5325, 'loss/train': 2.068955183029175} 08/30/2021 14:09:05 - INFO - __main__ - Step 5327: {'lr': 0.0004993771974025805, 'samples': 1022784, 'steps': 5326, 'loss/train': 2.1536505222320557} 08/30/2021 14:09:05 - INFO - __main__ - Step 5328: {'lr': 0.0004993768229965001, 'samples': 1022976, 'steps': 5327, 'loss/train': 1.8733011484146118} 08/30/2021 14:09:06 - INFO - __main__ - Step 5329: {'lr': 0.0004993764484780543, 'samples': 1023168, 'steps': 5328, 'loss/train': 2.5774080753326416} 08/30/2021 14:09:06 - INFO - __main__ - Step 5330: {'lr': 0.0004993760738472435, 'samples': 1023360, 'steps': 5329, 'loss/train': 1.8517621755599976} 08/30/2021 14:09:07 - INFO - __main__ - Step 5331: {'lr': 0.0004993756991040675, 'samples': 1023552, 'steps': 5330, 'loss/train': 1.9004884958267212} 08/30/2021 14:09:08 - INFO - __main__ - Step 5332: {'lr': 0.0004993753242485268, 'samples': 1023744, 'steps': 5331, 'loss/train': 1.9509395360946655} 08/30/2021 14:09:08 - INFO - __main__ - Step 5333: {'lr': 0.0004993749492806214, 'samples': 1023936, 'steps': 5332, 'loss/train': 2.135444402694702} 08/30/2021 14:09:08 - INFO - __main__ - Step 5334: {'lr': 0.0004993745742003515, 'samples': 1024128, 'steps': 5333, 'loss/train': 1.30648934841156} 08/30/2021 14:09:09 - INFO - __main__ - Step 5335: {'lr': 0.0004993741990077172, 'samples': 1024320, 'steps': 5334, 'loss/train': 1.6830708980560303} 08/30/2021 14:09:10 - INFO - __main__ - Step 5336: {'lr': 0.0004993738237027188, 'samples': 1024512, 'steps': 5335, 'loss/train': 2.0417819023132324} 08/30/2021 14:09:11 - INFO - __main__ - Step 5337: {'lr': 0.0004993734482853563, 'samples': 1024704, 'steps': 5336, 'loss/train': 1.9000158309936523} 08/30/2021 14:09:11 - INFO - __main__ - Step 5338: {'lr': 0.0004993730727556301, 'samples': 1024896, 'steps': 5337, 'loss/train': 2.2786426544189453} 08/30/2021 14:09:11 - INFO - __main__ - Step 5339: {'lr': 0.0004993726971135402, 'samples': 1025088, 'steps': 5338, 'loss/train': 2.10693097114563} 08/30/2021 14:09:12 - INFO - __main__ - Step 5340: {'lr': 0.0004993723213590868, 'samples': 1025280, 'steps': 5339, 'loss/train': 2.400607109069824} 08/30/2021 14:09:13 - INFO - __main__ - Step 5341: {'lr': 0.0004993719454922701, 'samples': 1025472, 'steps': 5340, 'loss/train': 2.1272616386413574} 08/30/2021 14:09:14 - INFO - __main__ - Step 5342: {'lr': 0.0004993715695130902, 'samples': 1025664, 'steps': 5341, 'loss/train': 2.2308144569396973} 08/30/2021 14:09:14 - INFO - __main__ - Step 5343: {'lr': 0.0004993711934215473, 'samples': 1025856, 'steps': 5342, 'loss/train': 2.4320480823516846} 08/30/2021 14:09:15 - INFO - __main__ - Step 5344: {'lr': 0.0004993708172176417, 'samples': 1026048, 'steps': 5343, 'loss/train': 2.435067892074585} 08/30/2021 14:09:15 - INFO - __main__ - Step 5345: {'lr': 0.0004993704409013734, 'samples': 1026240, 'steps': 5344, 'loss/train': 1.9322372674942017} 08/30/2021 14:09:15 - INFO - __main__ - Step 5346: {'lr': 0.0004993700644727425, 'samples': 1026432, 'steps': 5345, 'loss/train': 2.1200332641601562} 08/30/2021 14:09:17 - INFO - __main__ - Step 5347: {'lr': 0.0004993696879317495, 'samples': 1026624, 'steps': 5346, 'loss/train': 2.031440496444702} 08/30/2021 14:09:18 - INFO - __main__ - Step 5348: {'lr': 0.0004993693112783943, 'samples': 1026816, 'steps': 5347, 'loss/train': 1.5683552026748657} 08/30/2021 14:09:18 - INFO - __main__ - Step 5349: {'lr': 0.0004993689345126771, 'samples': 1027008, 'steps': 5348, 'loss/train': 0.2959568202495575} 08/30/2021 14:09:18 - INFO - __main__ - Step 5350: {'lr': 0.0004993685576345981, 'samples': 1027200, 'steps': 5349, 'loss/train': 2.23846173286438} 08/30/2021 14:09:19 - INFO - __main__ - Step 5351: {'lr': 0.0004993681806441575, 'samples': 1027392, 'steps': 5350, 'loss/train': 2.4751954078674316} 08/30/2021 14:09:20 - INFO - __main__ - Step 5352: {'lr': 0.0004993678035413554, 'samples': 1027584, 'steps': 5351, 'loss/train': 2.223661184310913} 08/30/2021 14:09:21 - INFO - __main__ - Step 5353: {'lr': 0.0004993674263261921, 'samples': 1027776, 'steps': 5352, 'loss/train': 1.4263993501663208} 08/30/2021 14:09:21 - INFO - __main__ - Step 5354: {'lr': 0.0004993670489986677, 'samples': 1027968, 'steps': 5353, 'loss/train': 2.0988636016845703} 08/30/2021 14:09:21 - INFO - __main__ - Step 5355: {'lr': 0.0004993666715587823, 'samples': 1028160, 'steps': 5354, 'loss/train': 2.2328529357910156} 08/30/2021 14:09:22 - INFO - __main__ - Step 5356: {'lr': 0.0004993662940065361, 'samples': 1028352, 'steps': 5355, 'loss/train': 1.6497890949249268} 08/30/2021 14:09:23 - INFO - __main__ - Step 5357: {'lr': 0.0004993659163419294, 'samples': 1028544, 'steps': 5356, 'loss/train': 1.1058005094528198} 08/30/2021 14:09:24 - INFO - __main__ - Step 5358: {'lr': 0.0004993655385649621, 'samples': 1028736, 'steps': 5357, 'loss/train': 2.23276686668396} 08/30/2021 14:09:24 - INFO - __main__ - Step 5359: {'lr': 0.0004993651606756347, 'samples': 1028928, 'steps': 5358, 'loss/train': 2.2387802600860596} 08/30/2021 14:09:25 - INFO - __main__ - Step 5360: {'lr': 0.0004993647826739471, 'samples': 1029120, 'steps': 5359, 'loss/train': 1.8057059049606323} 08/30/2021 14:09:25 - INFO - __main__ - Step 5361: {'lr': 0.0004993644045598997, 'samples': 1029312, 'steps': 5360, 'loss/train': 0.4468001425266266} 08/30/2021 14:09:25 - INFO - __main__ - Step 5362: {'lr': 0.0004993640263334924, 'samples': 1029504, 'steps': 5361, 'loss/train': 1.9620311260223389} 08/30/2021 14:09:27 - INFO - __main__ - Step 5363: {'lr': 0.0004993636479947256, 'samples': 1029696, 'steps': 5362, 'loss/train': 2.3470122814178467} 08/30/2021 14:09:28 - INFO - __main__ - Step 5364: {'lr': 0.0004993632695435993, 'samples': 1029888, 'steps': 5363, 'loss/train': 2.2149205207824707} 08/30/2021 14:09:28 - INFO - __main__ - Step 5365: {'lr': 0.0004993628909801138, 'samples': 1030080, 'steps': 5364, 'loss/train': 1.8443580865859985} 08/30/2021 14:09:28 - INFO - __main__ - Step 5366: {'lr': 0.0004993625123042694, 'samples': 1030272, 'steps': 5365, 'loss/train': 0.44625377655029297} 08/30/2021 14:09:29 - INFO - __main__ - Step 5367: {'lr': 0.0004993621335160659, 'samples': 1030464, 'steps': 5366, 'loss/train': 2.3478190898895264} 08/30/2021 14:09:30 - INFO - __main__ - Step 5368: {'lr': 0.0004993617546155037, 'samples': 1030656, 'steps': 5367, 'loss/train': 3.7186803817749023} 08/30/2021 14:09:31 - INFO - __main__ - Step 5369: {'lr': 0.000499361375602583, 'samples': 1030848, 'steps': 5368, 'loss/train': 2.6713244915008545} 08/30/2021 14:09:31 - INFO - __main__ - Step 5370: {'lr': 0.0004993609964773039, 'samples': 1031040, 'steps': 5369, 'loss/train': 1.7321006059646606} 08/30/2021 14:09:31 - INFO - __main__ - Step 5371: {'lr': 0.0004993606172396665, 'samples': 1031232, 'steps': 5370, 'loss/train': 1.4341566562652588} 08/30/2021 14:09:32 - INFO - __main__ - Step 5372: {'lr': 0.0004993602378896712, 'samples': 1031424, 'steps': 5371, 'loss/train': 2.197713613510132} 08/30/2021 14:09:33 - INFO - __main__ - Step 5373: {'lr': 0.0004993598584273179, 'samples': 1031616, 'steps': 5372, 'loss/train': 1.3328524827957153} 08/30/2021 14:09:34 - INFO - __main__ - Step 5374: {'lr': 0.0004993594788526069, 'samples': 1031808, 'steps': 5373, 'loss/train': 2.3513150215148926} 08/30/2021 14:09:34 - INFO - __main__ - Step 5375: {'lr': 0.0004993590991655384, 'samples': 1032000, 'steps': 5374, 'loss/train': 2.0456442832946777} 08/30/2021 14:09:34 - INFO - __main__ - Step 5376: {'lr': 0.0004993587193661126, 'samples': 1032192, 'steps': 5375, 'loss/train': 2.4715588092803955} 08/30/2021 14:09:35 - INFO - __main__ - Step 5377: {'lr': 0.0004993583394543295, 'samples': 1032384, 'steps': 5376, 'loss/train': 2.196958065032959} 08/30/2021 14:09:37 - INFO - __main__ - Step 5378: {'lr': 0.0004993579594301895, 'samples': 1032576, 'steps': 5377, 'loss/train': 2.075531482696533} 08/30/2021 14:09:37 - INFO - __main__ - Step 5379: {'lr': 0.0004993575792936925, 'samples': 1032768, 'steps': 5378, 'loss/train': 2.4638051986694336} 08/30/2021 14:09:37 - INFO - __main__ - Step 5380: {'lr': 0.000499357199044839, 'samples': 1032960, 'steps': 5379, 'loss/train': 1.3880785703659058} 08/30/2021 14:09:38 - INFO - __main__ - Step 5381: {'lr': 0.0004993568186836288, 'samples': 1033152, 'steps': 5380, 'loss/train': 2.3600668907165527} 08/30/2021 14:09:38 - INFO - __main__ - Step 5382: {'lr': 0.0004993564382100624, 'samples': 1033344, 'steps': 5381, 'loss/train': 2.009852409362793} 08/30/2021 14:09:38 - INFO - __main__ - Step 5383: {'lr': 0.0004993560576241398, 'samples': 1033536, 'steps': 5382, 'loss/train': 1.336531400680542} 08/30/2021 14:09:40 - INFO - __main__ - Step 5384: {'lr': 0.0004993556769258612, 'samples': 1033728, 'steps': 5383, 'loss/train': 2.0151145458221436} 08/30/2021 14:09:40 - INFO - __main__ - Step 5385: {'lr': 0.0004993552961152268, 'samples': 1033920, 'steps': 5384, 'loss/train': 2.3672847747802734} 08/30/2021 14:09:41 - INFO - __main__ - Step 5386: {'lr': 0.0004993549151922367, 'samples': 1034112, 'steps': 5385, 'loss/train': 1.5583224296569824} 08/30/2021 14:09:41 - INFO - __main__ - Step 5387: {'lr': 0.0004993545341568912, 'samples': 1034304, 'steps': 5386, 'loss/train': 3.142512321472168} 08/30/2021 14:09:42 - INFO - __main__ - Step 5388: {'lr': 0.0004993541530091903, 'samples': 1034496, 'steps': 5387, 'loss/train': 2.7708797454833984} 08/30/2021 14:09:43 - INFO - __main__ - Step 5389: {'lr': 0.0004993537717491343, 'samples': 1034688, 'steps': 5388, 'loss/train': 2.521812677383423} 08/30/2021 14:09:44 - INFO - __main__ - Step 5390: {'lr': 0.0004993533903767235, 'samples': 1034880, 'steps': 5389, 'loss/train': 1.5467299222946167} 08/30/2021 14:09:44 - INFO - __main__ - Step 5391: {'lr': 0.0004993530088919577, 'samples': 1035072, 'steps': 5390, 'loss/train': 2.070864677429199} 08/30/2021 14:09:44 - INFO - __main__ - Step 5392: {'lr': 0.0004993526272948374, 'samples': 1035264, 'steps': 5391, 'loss/train': 2.1507418155670166} 08/30/2021 14:09:45 - INFO - __main__ - Step 5393: {'lr': 0.0004993522455853626, 'samples': 1035456, 'steps': 5392, 'loss/train': 0.9771274924278259} 08/30/2021 14:09:46 - INFO - __main__ - Step 5394: {'lr': 0.0004993518637635334, 'samples': 1035648, 'steps': 5393, 'loss/train': 2.1481733322143555} 08/30/2021 14:09:46 - INFO - __main__ - Step 5395: {'lr': 0.0004993514818293503, 'samples': 1035840, 'steps': 5394, 'loss/train': 1.9538158178329468} 08/30/2021 14:09:47 - INFO - __main__ - Step 5396: {'lr': 0.0004993510997828132, 'samples': 1036032, 'steps': 5395, 'loss/train': 1.8449543714523315} 08/30/2021 14:09:47 - INFO - __main__ - Step 5397: {'lr': 0.0004993507176239224, 'samples': 1036224, 'steps': 5396, 'loss/train': 2.1521570682525635} 08/30/2021 14:09:48 - INFO - __main__ - Step 5398: {'lr': 0.0004993503353526779, 'samples': 1036416, 'steps': 5397, 'loss/train': 2.1995091438293457} 08/30/2021 14:09:49 - INFO - __main__ - Step 5399: {'lr': 0.0004993499529690801, 'samples': 1036608, 'steps': 5398, 'loss/train': 2.096731185913086} 08/30/2021 14:09:49 - INFO - __main__ - Step 5400: {'lr': 0.000499349570473129, 'samples': 1036800, 'steps': 5399, 'loss/train': 2.673593282699585} 08/30/2021 14:09:50 - INFO - __main__ - Step 5401: {'lr': 0.0004993491878648249, 'samples': 1036992, 'steps': 5400, 'loss/train': 1.6000927686691284} 08/30/2021 14:09:50 - INFO - __main__ - Step 5402: {'lr': 0.0004993488051441677, 'samples': 1037184, 'steps': 5401, 'loss/train': 1.3312642574310303} 08/30/2021 14:09:50 - INFO - __main__ - Step 5403: {'lr': 0.000499348422311158, 'samples': 1037376, 'steps': 5402, 'loss/train': 1.9997714757919312} 08/30/2021 14:09:52 - INFO - __main__ - Step 5404: {'lr': 0.0004993480393657956, 'samples': 1037568, 'steps': 5403, 'loss/train': 2.048255443572998} 08/30/2021 14:09:52 - INFO - __main__ - Step 5405: {'lr': 0.0004993476563080809, 'samples': 1037760, 'steps': 5404, 'loss/train': 1.9504129886627197} 08/30/2021 14:09:53 - INFO - __main__ - Step 5406: {'lr': 0.000499347273138014, 'samples': 1037952, 'steps': 5405, 'loss/train': 2.440894365310669} 08/30/2021 14:09:53 - INFO - __main__ - Step 5407: {'lr': 0.000499346889855595, 'samples': 1038144, 'steps': 5406, 'loss/train': 1.7340859174728394} 08/30/2021 14:09:53 - INFO - __main__ - Step 5408: {'lr': 0.0004993465064608242, 'samples': 1038336, 'steps': 5407, 'loss/train': 2.320876359939575} 08/30/2021 14:09:55 - INFO - __main__ - Step 5409: {'lr': 0.0004993461229537017, 'samples': 1038528, 'steps': 5408, 'loss/train': 2.4220235347747803} 08/30/2021 14:09:55 - INFO - __main__ - Step 5410: {'lr': 0.0004993457393342276, 'samples': 1038720, 'steps': 5409, 'loss/train': 2.2513859272003174} 08/30/2021 14:09:56 - INFO - __main__ - Step 5411: {'lr': 0.0004993453556024023, 'samples': 1038912, 'steps': 5410, 'loss/train': 2.6174113750457764} 08/30/2021 14:09:56 - INFO - __main__ - Step 5412: {'lr': 0.0004993449717582258, 'samples': 1039104, 'steps': 5411, 'loss/train': 2.1662635803222656} 08/30/2021 14:09:56 - INFO - __main__ - Step 5413: {'lr': 0.0004993445878016982, 'samples': 1039296, 'steps': 5412, 'loss/train': 2.164144277572632} 08/30/2021 14:09:58 - INFO - __main__ - Step 5414: {'lr': 0.0004993442037328199, 'samples': 1039488, 'steps': 5413, 'loss/train': 1.9893866777420044} 08/30/2021 14:09:59 - INFO - __main__ - Step 5415: {'lr': 0.0004993438195515909, 'samples': 1039680, 'steps': 5414, 'loss/train': 2.002112865447998} 08/30/2021 14:09:59 - INFO - __main__ - Step 5416: {'lr': 0.0004993434352580115, 'samples': 1039872, 'steps': 5415, 'loss/train': 2.2562832832336426} 08/30/2021 14:09:59 - INFO - __main__ - Step 5417: {'lr': 0.0004993430508520816, 'samples': 1040064, 'steps': 5416, 'loss/train': 2.781446695327759} 08/30/2021 14:10:00 - INFO - __main__ - Step 5418: {'lr': 0.0004993426663338018, 'samples': 1040256, 'steps': 5417, 'loss/train': 3.561868906021118} 08/30/2021 14:10:00 - INFO - __main__ - Step 5419: {'lr': 0.0004993422817031719, 'samples': 1040448, 'steps': 5418, 'loss/train': 2.6206448078155518} 08/30/2021 14:10:02 - INFO - __main__ - Step 5420: {'lr': 0.0004993418969601921, 'samples': 1040640, 'steps': 5419, 'loss/train': 0.2771877646446228} 08/30/2021 14:10:02 - INFO - __main__ - Step 5421: {'lr': 0.0004993415121048629, 'samples': 1040832, 'steps': 5420, 'loss/train': 1.951654076576233} 08/30/2021 14:10:02 - INFO - __main__ - Step 5422: {'lr': 0.0004993411271371842, 'samples': 1041024, 'steps': 5421, 'loss/train': 2.035478353500366} 08/30/2021 14:10:03 - INFO - __main__ - Step 5423: {'lr': 0.0004993407420571563, 'samples': 1041216, 'steps': 5422, 'loss/train': 2.09321665763855} 08/30/2021 14:10:03 - INFO - __main__ - Step 5424: {'lr': 0.0004993403568647792, 'samples': 1041408, 'steps': 5423, 'loss/train': 1.7867854833602905} 08/30/2021 14:10:05 - INFO - __main__ - Step 5425: {'lr': 0.0004993399715600531, 'samples': 1041600, 'steps': 5424, 'loss/train': 2.204225778579712} 08/30/2021 14:10:05 - INFO - __main__ - Step 5426: {'lr': 0.0004993395861429785, 'samples': 1041792, 'steps': 5425, 'loss/train': 2.1877803802490234} 08/30/2021 14:10:06 - INFO - __main__ - Step 5427: {'lr': 0.0004993392006135552, 'samples': 1041984, 'steps': 5426, 'loss/train': 1.9577467441558838} 08/30/2021 14:10:06 - INFO - __main__ - Step 5428: {'lr': 0.0004993388149717834, 'samples': 1042176, 'steps': 5427, 'loss/train': 2.704737901687622} 08/30/2021 14:10:06 - INFO - __main__ - Step 5429: {'lr': 0.0004993384292176636, 'samples': 1042368, 'steps': 5428, 'loss/train': 2.8021090030670166} 08/30/2021 14:10:09 - INFO - __main__ - Step 5430: {'lr': 0.0004993380433511956, 'samples': 1042560, 'steps': 5429, 'loss/train': 1.9252568483352661} 08/30/2021 14:10:09 - INFO - __main__ - Step 5431: {'lr': 0.0004993376573723798, 'samples': 1042752, 'steps': 5430, 'loss/train': 2.233086109161377} 08/30/2021 14:10:09 - INFO - __main__ - Step 5432: {'lr': 0.0004993372712812162, 'samples': 1042944, 'steps': 5431, 'loss/train': 0.5660424828529358} 08/30/2021 14:10:10 - INFO - __main__ - Step 5433: {'lr': 0.0004993368850777052, 'samples': 1043136, 'steps': 5432, 'loss/train': 2.0277514457702637} 08/30/2021 14:10:10 - INFO - __main__ - Step 5434: {'lr': 0.0004993364987618468, 'samples': 1043328, 'steps': 5433, 'loss/train': 2.2109923362731934} 08/30/2021 14:10:10 - INFO - __main__ - Step 5435: {'lr': 0.0004993361123336412, 'samples': 1043520, 'steps': 5434, 'loss/train': 2.028074264526367} 08/30/2021 14:10:12 - INFO - __main__ - Step 5436: {'lr': 0.0004993357257930887, 'samples': 1043712, 'steps': 5435, 'loss/train': 1.8543492555618286} 08/30/2021 14:10:12 - INFO - __main__ - Step 5437: {'lr': 0.0004993353391401892, 'samples': 1043904, 'steps': 5436, 'loss/train': 1.626535177230835} 08/30/2021 14:10:13 - INFO - __main__ - Step 5438: {'lr': 0.0004993349523749431, 'samples': 1044096, 'steps': 5437, 'loss/train': 2.555976152420044} 08/30/2021 14:10:13 - INFO - __main__ - Step 5439: {'lr': 0.0004993345654973505, 'samples': 1044288, 'steps': 5438, 'loss/train': 1.9841675758361816} 08/30/2021 14:10:14 - INFO - __main__ - Step 5440: {'lr': 0.0004993341785074116, 'samples': 1044480, 'steps': 5439, 'loss/train': 0.9596847891807556} 08/30/2021 14:10:15 - INFO - __main__ - Step 5441: {'lr': 0.0004993337914051266, 'samples': 1044672, 'steps': 5440, 'loss/train': 1.9429361820220947} 08/30/2021 14:10:16 - INFO - __main__ - Step 5442: {'lr': 0.0004993334041904957, 'samples': 1044864, 'steps': 5441, 'loss/train': 1.9028719663619995} 08/30/2021 14:10:16 - INFO - __main__ - Step 5443: {'lr': 0.0004993330168635189, 'samples': 1045056, 'steps': 5442, 'loss/train': 1.8421297073364258} 08/30/2021 14:10:16 - INFO - __main__ - Step 5444: {'lr': 0.0004993326294241966, 'samples': 1045248, 'steps': 5443, 'loss/train': 2.274104118347168} 08/30/2021 14:10:17 - INFO - __main__ - Step 5445: {'lr': 0.0004993322418725286, 'samples': 1045440, 'steps': 5444, 'loss/train': 2.2421417236328125} 08/30/2021 14:10:18 - INFO - __main__ - Step 5446: {'lr': 0.0004993318542085157, 'samples': 1045632, 'steps': 5445, 'loss/train': 1.3372082710266113} 08/30/2021 14:10:19 - INFO - __main__ - Step 5447: {'lr': 0.0004993314664321575, 'samples': 1045824, 'steps': 5446, 'loss/train': 1.7467808723449707} 08/30/2021 14:10:19 - INFO - __main__ - Step 5448: {'lr': 0.0004993310785434544, 'samples': 1046016, 'steps': 5447, 'loss/train': 1.7305140495300293} 08/30/2021 14:10:19 - INFO - __main__ - Step 5449: {'lr': 0.0004993306905424067, 'samples': 1046208, 'steps': 5448, 'loss/train': 2.282919406890869} 08/30/2021 14:10:20 - INFO - __main__ - Step 5450: {'lr': 0.0004993303024290143, 'samples': 1046400, 'steps': 5449, 'loss/train': 2.3551671504974365} 08/30/2021 14:10:21 - INFO - __main__ - Step 5451: {'lr': 0.0004993299142032776, 'samples': 1046592, 'steps': 5450, 'loss/train': 2.360137939453125} 08/30/2021 14:10:22 - INFO - __main__ - Step 5452: {'lr': 0.0004993295258651966, 'samples': 1046784, 'steps': 5451, 'loss/train': 1.8643544912338257} 08/30/2021 14:10:22 - INFO - __main__ - Step 5453: {'lr': 0.0004993291374147716, 'samples': 1046976, 'steps': 5452, 'loss/train': 2.229452133178711} 08/30/2021 14:10:22 - INFO - __main__ - Step 5454: {'lr': 0.0004993287488520027, 'samples': 1047168, 'steps': 5453, 'loss/train': 2.066531181335449} 08/30/2021 14:10:23 - INFO - __main__ - Step 5455: {'lr': 0.0004993283601768902, 'samples': 1047360, 'steps': 5454, 'loss/train': 1.7025607824325562} 08/30/2021 14:10:24 - INFO - __main__ - Step 5456: {'lr': 0.0004993279713894342, 'samples': 1047552, 'steps': 5455, 'loss/train': 2.2028450965881348} 08/30/2021 14:10:25 - INFO - __main__ - Step 5457: {'lr': 0.0004993275824896348, 'samples': 1047744, 'steps': 5456, 'loss/train': 2.0696890354156494} 08/30/2021 14:10:25 - INFO - __main__ - Step 5458: {'lr': 0.0004993271934774922, 'samples': 1047936, 'steps': 5457, 'loss/train': 1.9927334785461426} 08/30/2021 14:10:25 - INFO - __main__ - Step 5459: {'lr': 0.0004993268043530067, 'samples': 1048128, 'steps': 5458, 'loss/train': 0.9724563956260681} 08/30/2021 14:10:26 - INFO - __main__ - Step 5460: {'lr': 0.0004993264151161783, 'samples': 1048320, 'steps': 5459, 'loss/train': 2.131405830383301} 08/30/2021 14:10:27 - INFO - __main__ - Step 5461: {'lr': 0.0004993260257670074, 'samples': 1048512, 'steps': 5460, 'loss/train': 2.383780002593994} 08/30/2021 14:10:28 - INFO - __main__ - Step 5462: {'lr': 0.000499325636305494, 'samples': 1048704, 'steps': 5461, 'loss/train': 1.9696367979049683} 08/30/2021 14:10:28 - INFO - __main__ - Step 5463: {'lr': 0.0004993252467316382, 'samples': 1048896, 'steps': 5462, 'loss/train': 0.2647189497947693} 08/30/2021 14:10:29 - INFO - __main__ - Step 5464: {'lr': 0.0004993248570454404, 'samples': 1049088, 'steps': 5463, 'loss/train': 1.9423753023147583} 08/30/2021 14:10:29 - INFO - __main__ - Step 5465: {'lr': 0.0004993244672469007, 'samples': 1049280, 'steps': 5464, 'loss/train': 2.2232024669647217} 08/30/2021 14:10:29 - INFO - __main__ - Step 5466: {'lr': 0.000499324077336019, 'samples': 1049472, 'steps': 5465, 'loss/train': 1.8365471363067627} 08/30/2021 14:10:31 - INFO - __main__ - Step 5467: {'lr': 0.000499323687312796, 'samples': 1049664, 'steps': 5466, 'loss/train': 2.3148319721221924} 08/30/2021 14:10:31 - INFO - __main__ - Step 5468: {'lr': 0.0004993232971772315, 'samples': 1049856, 'steps': 5467, 'loss/train': 1.4730870723724365} 08/30/2021 14:10:32 - INFO - __main__ - Step 5469: {'lr': 0.0004993229069293257, 'samples': 1050048, 'steps': 5468, 'loss/train': 2.107245445251465} 08/30/2021 14:10:32 - INFO - __main__ - Step 5470: {'lr': 0.0004993225165690789, 'samples': 1050240, 'steps': 5469, 'loss/train': 2.0114569664001465} 08/30/2021 14:10:32 - INFO - __main__ - Step 5471: {'lr': 0.0004993221260964912, 'samples': 1050432, 'steps': 5470, 'loss/train': 2.575805425643921} 08/30/2021 14:10:34 - INFO - __main__ - Step 5472: {'lr': 0.0004993217355115628, 'samples': 1050624, 'steps': 5471, 'loss/train': 1.0163025856018066} 08/30/2021 14:10:34 - INFO - __main__ - Step 5473: {'lr': 0.0004993213448142939, 'samples': 1050816, 'steps': 5472, 'loss/train': 2.3085601329803467} 08/30/2021 14:10:35 - INFO - __main__ - Step 5474: {'lr': 0.0004993209540046846, 'samples': 1051008, 'steps': 5473, 'loss/train': 2.156073570251465} 08/30/2021 14:10:35 - INFO - __main__ - Step 5475: {'lr': 0.0004993205630827352, 'samples': 1051200, 'steps': 5474, 'loss/train': 2.266218662261963} 08/30/2021 14:10:35 - INFO - __main__ - Step 5476: {'lr': 0.0004993201720484458, 'samples': 1051392, 'steps': 5475, 'loss/train': 1.6573611497879028} 08/30/2021 14:10:37 - INFO - __main__ - Step 5477: {'lr': 0.0004993197809018165, 'samples': 1051584, 'steps': 5476, 'loss/train': 2.014347791671753} 08/30/2021 14:10:37 - INFO - __main__ - Step 5478: {'lr': 0.0004993193896428476, 'samples': 1051776, 'steps': 5477, 'loss/train': 1.5912764072418213} 08/30/2021 14:10:38 - INFO - __main__ - Step 5479: {'lr': 0.0004993189982715392, 'samples': 1051968, 'steps': 5478, 'loss/train': 1.98436439037323} 08/30/2021 14:10:38 - INFO - __main__ - Step 5480: {'lr': 0.0004993186067878916, 'samples': 1052160, 'steps': 5479, 'loss/train': 1.3397401571273804} 08/30/2021 14:10:38 - INFO - __main__ - Step 5481: {'lr': 0.0004993182151919049, 'samples': 1052352, 'steps': 5480, 'loss/train': 2.5370564460754395} 08/30/2021 14:10:40 - INFO - __main__ - Step 5482: {'lr': 0.0004993178234835792, 'samples': 1052544, 'steps': 5481, 'loss/train': 2.3404853343963623} 08/30/2021 14:10:40 - INFO - __main__ - Step 5483: {'lr': 0.0004993174316629146, 'samples': 1052736, 'steps': 5482, 'loss/train': 1.8672559261322021} 08/30/2021 14:10:41 - INFO - __main__ - Step 5484: {'lr': 0.0004993170397299116, 'samples': 1052928, 'steps': 5483, 'loss/train': 2.132535219192505} 08/30/2021 14:10:41 - INFO - __main__ - Step 5485: {'lr': 0.0004993166476845701, 'samples': 1053120, 'steps': 5484, 'loss/train': 1.8370695114135742} 08/30/2021 14:10:41 - INFO - __main__ - Step 5486: {'lr': 0.0004993162555268903, 'samples': 1053312, 'steps': 5485, 'loss/train': 2.283796787261963} 08/30/2021 14:10:44 - INFO - __main__ - Step 5487: {'lr': 0.0004993158632568726, 'samples': 1053504, 'steps': 5486, 'loss/train': 2.285121202468872} 08/30/2021 14:10:44 - INFO - __main__ - Step 5488: {'lr': 0.000499315470874517, 'samples': 1053696, 'steps': 5487, 'loss/train': 2.177340030670166} 08/30/2021 14:10:44 - INFO - __main__ - Step 5489: {'lr': 0.0004993150783798236, 'samples': 1053888, 'steps': 5488, 'loss/train': 1.9022594690322876} 08/30/2021 14:10:45 - INFO - __main__ - Step 5490: {'lr': 0.0004993146857727927, 'samples': 1054080, 'steps': 5489, 'loss/train': 2.1659700870513916} 08/30/2021 14:10:45 - INFO - __main__ - Step 5491: {'lr': 0.0004993142930534245, 'samples': 1054272, 'steps': 5490, 'loss/train': 2.3744122982025146} 08/30/2021 14:10:45 - INFO - __main__ - Step 5492: {'lr': 0.000499313900221719, 'samples': 1054464, 'steps': 5491, 'loss/train': 1.952682375907898} 08/30/2021 14:10:47 - INFO - __main__ - Step 5493: {'lr': 0.0004993135072776766, 'samples': 1054656, 'steps': 5492, 'loss/train': 2.821582078933716} 08/30/2021 14:10:48 - INFO - __main__ - Step 5494: {'lr': 0.0004993131142212974, 'samples': 1054848, 'steps': 5493, 'loss/train': 2.6464333534240723} 08/30/2021 14:10:48 - INFO - __main__ - Step 5495: {'lr': 0.0004993127210525815, 'samples': 1055040, 'steps': 5494, 'loss/train': 2.1936745643615723} 08/30/2021 14:10:48 - INFO - __main__ - Step 5496: {'lr': 0.0004993123277715292, 'samples': 1055232, 'steps': 5495, 'loss/train': 0.46463823318481445} 08/30/2021 14:10:49 - INFO - __main__ - Step 5497: {'lr': 0.0004993119343781406, 'samples': 1055424, 'steps': 5496, 'loss/train': 1.7416826486587524} 08/30/2021 14:10:50 - INFO - __main__ - Step 5498: {'lr': 0.0004993115408724159, 'samples': 1055616, 'steps': 5497, 'loss/train': 2.226656913757324} 08/30/2021 14:10:51 - INFO - __main__ - Step 5499: {'lr': 0.0004993111472543552, 'samples': 1055808, 'steps': 5498, 'loss/train': 2.048360586166382} 08/30/2021 14:10:51 - INFO - __main__ - Step 5500: {'lr': 0.0004993107535239588, 'samples': 1056000, 'steps': 5499, 'loss/train': 1.7542228698730469} 08/30/2021 14:10:51 - INFO - __main__ - Step 5501: {'lr': 0.0004993103596812267, 'samples': 1056192, 'steps': 5500, 'loss/train': 1.8287094831466675} 08/30/2021 14:10:52 - INFO - __main__ - Step 5502: {'lr': 0.0004993099657261594, 'samples': 1056384, 'steps': 5501, 'loss/train': 2.1925034523010254} 08/30/2021 14:10:53 - INFO - __main__ - Step 5503: {'lr': 0.0004993095716587568, 'samples': 1056576, 'steps': 5502, 'loss/train': 2.2337374687194824} 08/30/2021 14:10:54 - INFO - __main__ - Step 5504: {'lr': 0.0004993091774790191, 'samples': 1056768, 'steps': 5503, 'loss/train': 2.3906707763671875} 08/30/2021 14:10:54 - INFO - __main__ - Step 5505: {'lr': 0.0004993087831869466, 'samples': 1056960, 'steps': 5504, 'loss/train': 2.1719212532043457} 08/30/2021 14:10:55 - INFO - __main__ - Step 5506: {'lr': 0.0004993083887825393, 'samples': 1057152, 'steps': 5505, 'loss/train': 1.03645920753479} 08/30/2021 14:10:55 - INFO - __main__ - Step 5507: {'lr': 0.0004993079942657976, 'samples': 1057344, 'steps': 5506, 'loss/train': 2.3380463123321533} 08/30/2021 14:10:56 - INFO - __main__ - Step 5508: {'lr': 0.0004993075996367215, 'samples': 1057536, 'steps': 5507, 'loss/train': 2.2435622215270996} 08/30/2021 14:10:57 - INFO - __main__ - Step 5509: {'lr': 0.0004993072048953113, 'samples': 1057728, 'steps': 5508, 'loss/train': 2.1776604652404785} 08/30/2021 14:10:57 - INFO - __main__ - Step 5510: {'lr': 0.0004993068100415671, 'samples': 1057920, 'steps': 5509, 'loss/train': 2.653428316116333} 08/30/2021 14:10:57 - INFO - __main__ - Step 5511: {'lr': 0.000499306415075489, 'samples': 1058112, 'steps': 5510, 'loss/train': 2.6361703872680664} 08/30/2021 14:10:58 - INFO - __main__ - Step 5512: {'lr': 0.0004993060199970774, 'samples': 1058304, 'steps': 5511, 'loss/train': 2.427008867263794} 08/30/2021 14:10:59 - INFO - __main__ - Step 5513: {'lr': 0.0004993056248063323, 'samples': 1058496, 'steps': 5512, 'loss/train': 2.2770121097564697} 08/30/2021 14:11:00 - INFO - __main__ - Step 5514: {'lr': 0.000499305229503254, 'samples': 1058688, 'steps': 5513, 'loss/train': 2.106358289718628} 08/30/2021 14:11:00 - INFO - __main__ - Step 5515: {'lr': 0.0004993048340878425, 'samples': 1058880, 'steps': 5514, 'loss/train': 2.5477981567382812} 08/30/2021 14:11:01 - INFO - __main__ - Step 5516: {'lr': 0.0004993044385600982, 'samples': 1059072, 'steps': 5515, 'loss/train': 2.0413224697113037} 08/30/2021 14:11:01 - INFO - __main__ - Step 5517: {'lr': 0.0004993040429200211, 'samples': 1059264, 'steps': 5516, 'loss/train': 1.5816320180892944} 08/30/2021 14:11:02 - INFO - __main__ - Step 5518: {'lr': 0.0004993036471676115, 'samples': 1059456, 'steps': 5517, 'loss/train': 1.999403715133667} 08/30/2021 14:11:03 - INFO - __main__ - Step 5519: {'lr': 0.0004993032513028695, 'samples': 1059648, 'steps': 5518, 'loss/train': 2.0872840881347656} 08/30/2021 14:11:03 - INFO - __main__ - Step 5520: {'lr': 0.0004993028553257952, 'samples': 1059840, 'steps': 5519, 'loss/train': 2.4998018741607666} 08/30/2021 14:11:04 - INFO - __main__ - Step 5521: {'lr': 0.000499302459236389, 'samples': 1060032, 'steps': 5520, 'loss/train': 2.7392771244049072} 08/30/2021 14:11:04 - INFO - __main__ - Step 5522: {'lr': 0.0004993020630346509, 'samples': 1060224, 'steps': 5521, 'loss/train': 2.084122657775879} 08/30/2021 14:11:04 - INFO - __main__ - Step 5523: {'lr': 0.0004993016667205812, 'samples': 1060416, 'steps': 5522, 'loss/train': 2.190417528152466} 08/30/2021 14:11:06 - INFO - __main__ - Step 5524: {'lr': 0.0004993012702941799, 'samples': 1060608, 'steps': 5523, 'loss/train': 2.637319326400757} 08/30/2021 14:11:06 - INFO - __main__ - Step 5525: {'lr': 0.0004993008737554474, 'samples': 1060800, 'steps': 5524, 'loss/train': 1.8042362928390503} 08/30/2021 14:11:07 - INFO - __main__ - Step 5526: {'lr': 0.0004993004771043837, 'samples': 1060992, 'steps': 5525, 'loss/train': 2.6689212322235107} 08/30/2021 14:11:07 - INFO - __main__ - Step 5527: {'lr': 0.0004993000803409891, 'samples': 1061184, 'steps': 5526, 'loss/train': 1.7853155136108398} 08/30/2021 14:11:07 - INFO - __main__ - Step 5528: {'lr': 0.0004992996834652638, 'samples': 1061376, 'steps': 5527, 'loss/train': 2.338870048522949} 08/30/2021 14:11:10 - INFO - __main__ - Step 5529: {'lr': 0.0004992992864772079, 'samples': 1061568, 'steps': 5528, 'loss/train': 1.9785727262496948} 08/30/2021 14:11:10 - INFO - __main__ - Step 5530: {'lr': 0.0004992988893768214, 'samples': 1061760, 'steps': 5529, 'loss/train': 0.20871050655841827} 08/30/2021 14:11:11 - INFO - __main__ - Step 5531: {'lr': 0.0004992984921641048, 'samples': 1061952, 'steps': 5530, 'loss/train': 2.4556217193603516} 08/30/2021 14:11:11 - INFO - __main__ - Step 5532: {'lr': 0.0004992980948390582, 'samples': 1062144, 'steps': 5531, 'loss/train': 2.12160062789917} 08/30/2021 14:11:11 - INFO - __main__ - Step 5533: {'lr': 0.0004992976974016817, 'samples': 1062336, 'steps': 5532, 'loss/train': 1.3040118217468262} 08/30/2021 14:11:12 - INFO - __main__ - Step 5534: {'lr': 0.0004992972998519755, 'samples': 1062528, 'steps': 5533, 'loss/train': 1.4546117782592773} 08/30/2021 14:11:13 - INFO - __main__ - Step 5535: {'lr': 0.0004992969021899397, 'samples': 1062720, 'steps': 5534, 'loss/train': 1.5991532802581787} 08/30/2021 14:11:14 - INFO - __main__ - Step 5536: {'lr': 0.0004992965044155746, 'samples': 1062912, 'steps': 5535, 'loss/train': 3.6720755100250244} 08/30/2021 14:11:14 - INFO - __main__ - Step 5537: {'lr': 0.0004992961065288803, 'samples': 1063104, 'steps': 5536, 'loss/train': 2.046330451965332} 08/30/2021 14:11:14 - INFO - __main__ - Step 5538: {'lr': 0.0004992957085298571, 'samples': 1063296, 'steps': 5537, 'loss/train': 1.8923728466033936} 08/30/2021 14:11:15 - INFO - __main__ - Step 5539: {'lr': 0.0004992953104185052, 'samples': 1063488, 'steps': 5538, 'loss/train': 1.9728093147277832} 08/30/2021 14:11:15 - INFO - __main__ - Step 5540: {'lr': 0.0004992949121948245, 'samples': 1063680, 'steps': 5539, 'loss/train': 2.3191511631011963} 08/30/2021 14:11:17 - INFO - __main__ - Step 5541: {'lr': 0.0004992945138588154, 'samples': 1063872, 'steps': 5540, 'loss/train': 1.7350372076034546} 08/30/2021 14:11:18 - INFO - __main__ - Step 5542: {'lr': 0.0004992941154104781, 'samples': 1064064, 'steps': 5541, 'loss/train': 1.5580090284347534} 08/30/2021 14:11:18 - INFO - __main__ - Step 5543: {'lr': 0.0004992937168498126, 'samples': 1064256, 'steps': 5542, 'loss/train': 2.5731587409973145} 08/30/2021 14:11:18 - INFO - __main__ - Step 5544: {'lr': 0.0004992933181768194, 'samples': 1064448, 'steps': 5543, 'loss/train': 2.2242648601531982} 08/30/2021 14:11:19 - INFO - __main__ - Step 5545: {'lr': 0.0004992929193914983, 'samples': 1064640, 'steps': 5544, 'loss/train': 2.34719181060791} 08/30/2021 14:11:20 - INFO - __main__ - Step 5546: {'lr': 0.0004992925204938498, 'samples': 1064832, 'steps': 5545, 'loss/train': 2.010756254196167} 08/30/2021 14:11:21 - INFO - __main__ - Step 5547: {'lr': 0.0004992921214838738, 'samples': 1065024, 'steps': 5546, 'loss/train': 2.0510904788970947} 08/30/2021 14:11:21 - INFO - __main__ - Step 5548: {'lr': 0.0004992917223615706, 'samples': 1065216, 'steps': 5547, 'loss/train': 1.9226391315460205} 08/30/2021 14:11:21 - INFO - __main__ - Step 5549: {'lr': 0.0004992913231269405, 'samples': 1065408, 'steps': 5548, 'loss/train': 2.1731057167053223} 08/30/2021 14:11:22 - INFO - __main__ - Step 5550: {'lr': 0.0004992909237799835, 'samples': 1065600, 'steps': 5549, 'loss/train': 1.3518481254577637} 08/30/2021 14:11:23 - INFO - __main__ - Step 5551: {'lr': 0.0004992905243206999, 'samples': 1065792, 'steps': 5550, 'loss/train': 2.6396844387054443} 08/30/2021 14:11:23 - INFO - __main__ - Step 5552: {'lr': 0.0004992901247490899, 'samples': 1065984, 'steps': 5551, 'loss/train': 2.384359836578369} 08/30/2021 14:11:24 - INFO - __main__ - Step 5553: {'lr': 0.0004992897250651535, 'samples': 1066176, 'steps': 5552, 'loss/train': 2.3147265911102295} 08/30/2021 14:11:24 - INFO - __main__ - Step 5554: {'lr': 0.000499289325268891, 'samples': 1066368, 'steps': 5553, 'loss/train': 1.9126274585723877} 08/30/2021 14:11:25 - INFO - __main__ - Step 5555: {'lr': 0.0004992889253603027, 'samples': 1066560, 'steps': 5554, 'loss/train': 2.1129536628723145} 08/30/2021 14:11:26 - INFO - __main__ - Step 5556: {'lr': 0.0004992885253393885, 'samples': 1066752, 'steps': 5555, 'loss/train': 2.1831605434417725} 08/30/2021 14:11:26 - INFO - __main__ - Step 5557: {'lr': 0.0004992881252061489, 'samples': 1066944, 'steps': 5556, 'loss/train': 1.7416491508483887} 08/30/2021 14:11:27 - INFO - __main__ - Step 5558: {'lr': 0.0004992877249605838, 'samples': 1067136, 'steps': 5557, 'loss/train': 2.1720869541168213} 08/30/2021 14:11:27 - INFO - __main__ - Step 5559: {'lr': 0.0004992873246026935, 'samples': 1067328, 'steps': 5558, 'loss/train': 1.594710350036621} 08/30/2021 14:11:28 - INFO - __main__ - Step 5560: {'lr': 0.0004992869241324783, 'samples': 1067520, 'steps': 5559, 'loss/train': 2.2681097984313965} 08/30/2021 14:11:29 - INFO - __main__ - Step 5561: {'lr': 0.000499286523549938, 'samples': 1067712, 'steps': 5560, 'loss/train': 1.0781636238098145} 08/30/2021 14:11:30 - INFO - __main__ - Step 5562: {'lr': 0.0004992861228550733, 'samples': 1067904, 'steps': 5561, 'loss/train': 2.140679121017456} 08/30/2021 14:11:30 - INFO - __main__ - Step 5563: {'lr': 0.0004992857220478841, 'samples': 1068096, 'steps': 5562, 'loss/train': 2.354631185531616} 08/30/2021 14:11:31 - INFO - __main__ - Step 5564: {'lr': 0.0004992853211283705, 'samples': 1068288, 'steps': 5563, 'loss/train': 2.1048831939697266} 08/30/2021 14:11:31 - INFO - __main__ - Step 5565: {'lr': 0.0004992849200965327, 'samples': 1068480, 'steps': 5564, 'loss/train': 1.4562908411026} 08/30/2021 14:11:31 - INFO - __main__ - Step 5566: {'lr': 0.0004992845189523711, 'samples': 1068672, 'steps': 5565, 'loss/train': 2.081939458847046} 08/30/2021 14:11:32 - INFO - __main__ - Step 5567: {'lr': 0.0004992841176958858, 'samples': 1068864, 'steps': 5566, 'loss/train': 0.5906223654747009} 08/30/2021 14:11:33 - INFO - __main__ - Step 5568: {'lr': 0.0004992837163270769, 'samples': 1069056, 'steps': 5567, 'loss/train': 0.9060255885124207} 08/30/2021 14:11:34 - INFO - __main__ - Step 5569: {'lr': 0.0004992833148459445, 'samples': 1069248, 'steps': 5568, 'loss/train': 1.7371954917907715} 08/30/2021 14:11:34 - INFO - __main__ - Step 5570: {'lr': 0.0004992829132524889, 'samples': 1069440, 'steps': 5569, 'loss/train': 3.8672800064086914} 08/30/2021 14:11:34 - INFO - __main__ - Step 5571: {'lr': 0.0004992825115467102, 'samples': 1069632, 'steps': 5570, 'loss/train': 2.0577011108398438} 08/30/2021 14:11:35 - INFO - __main__ - Step 5572: {'lr': 0.0004992821097286088, 'samples': 1069824, 'steps': 5571, 'loss/train': 2.1876301765441895} 08/30/2021 14:11:36 - INFO - __main__ - Step 5573: {'lr': 0.0004992817077981846, 'samples': 1070016, 'steps': 5572, 'loss/train': 2.2967967987060547} 08/30/2021 14:11:37 - INFO - __main__ - Step 5574: {'lr': 0.000499281305755438, 'samples': 1070208, 'steps': 5573, 'loss/train': 2.410820960998535} 08/30/2021 14:11:37 - INFO - __main__ - Step 5575: {'lr': 0.0004992809036003691, 'samples': 1070400, 'steps': 5574, 'loss/train': 2.1856136322021484} 08/30/2021 14:11:38 - INFO - __main__ - Step 5576: {'lr': 0.000499280501332978, 'samples': 1070592, 'steps': 5575, 'loss/train': 2.0397074222564697} 08/30/2021 14:11:38 - INFO - __main__ - Step 5577: {'lr': 0.000499280098953265, 'samples': 1070784, 'steps': 5576, 'loss/train': 0.2530321776866913} 08/30/2021 14:11:39 - INFO - __main__ - Step 5578: {'lr': 0.0004992796964612302, 'samples': 1070976, 'steps': 5577, 'loss/train': 2.3651294708251953} 08/30/2021 14:11:40 - INFO - __main__ - Step 5579: {'lr': 0.0004992792938568739, 'samples': 1071168, 'steps': 5578, 'loss/train': 1.9276092052459717} 08/30/2021 14:11:40 - INFO - __main__ - Step 5580: {'lr': 0.0004992788911401961, 'samples': 1071360, 'steps': 5579, 'loss/train': 1.5673604011535645} 08/30/2021 14:11:41 - INFO - __main__ - Step 5581: {'lr': 0.0004992784883111972, 'samples': 1071552, 'steps': 5580, 'loss/train': 1.9843230247497559} 08/30/2021 14:11:41 - INFO - __main__ - Step 5582: {'lr': 0.0004992780853698771, 'samples': 1071744, 'steps': 5581, 'loss/train': 2.4910387992858887} 08/30/2021 14:11:43 - INFO - __main__ - Step 5583: {'lr': 0.0004992776823162362, 'samples': 1071936, 'steps': 5582, 'loss/train': 1.471346378326416} 08/30/2021 14:11:44 - INFO - __main__ - Step 5584: {'lr': 0.0004992772791502746, 'samples': 1072128, 'steps': 5583, 'loss/train': 2.100456714630127} 08/30/2021 14:11:44 - INFO - __main__ - Step 5585: {'lr': 0.0004992768758719926, 'samples': 1072320, 'steps': 5584, 'loss/train': 1.398590087890625} 08/30/2021 14:11:45 - INFO - __main__ - Step 5586: {'lr': 0.0004992764724813902, 'samples': 1072512, 'steps': 5585, 'loss/train': 1.7602514028549194} 08/30/2021 14:11:45 - INFO - __main__ - Step 5587: {'lr': 0.0004992760689784677, 'samples': 1072704, 'steps': 5586, 'loss/train': 2.4041781425476074} 08/30/2021 14:11:45 - INFO - __main__ - Step 5588: {'lr': 0.0004992756653632252, 'samples': 1072896, 'steps': 5587, 'loss/train': 1.75435209274292} 08/30/2021 14:11:46 - INFO - __main__ - Step 5589: {'lr': 0.0004992752616356631, 'samples': 1073088, 'steps': 5588, 'loss/train': 3.5171561241149902} 08/30/2021 14:11:46 - INFO - __main__ - Step 5590: {'lr': 0.0004992748577957812, 'samples': 1073280, 'steps': 5589, 'loss/train': 2.674107551574707} 08/30/2021 14:11:47 - INFO - __main__ - Step 5591: {'lr': 0.00049927445384358, 'samples': 1073472, 'steps': 5590, 'loss/train': 6.3213324546813965} 08/30/2021 14:11:48 - INFO - __main__ - Step 5592: {'lr': 0.0004992740497790595, 'samples': 1073664, 'steps': 5591, 'loss/train': 3.5618104934692383} 08/30/2021 14:11:48 - INFO - __main__ - Step 5593: {'lr': 0.0004992736456022201, 'samples': 1073856, 'steps': 5592, 'loss/train': 3.2196736335754395} 08/30/2021 14:11:49 - INFO - __main__ - Step 5594: {'lr': 0.0004992732413130617, 'samples': 1074048, 'steps': 5593, 'loss/train': 3.2155239582061768} 08/30/2021 14:11:49 - INFO - __main__ - Step 5595: {'lr': 0.0004992728369115848, 'samples': 1074240, 'steps': 5594, 'loss/train': 3.0582523345947266} 08/30/2021 14:11:51 - INFO - __main__ - Step 5596: {'lr': 0.0004992724323977893, 'samples': 1074432, 'steps': 5595, 'loss/train': 2.801431894302368} 08/30/2021 14:11:52 - INFO - __main__ - Step 5597: {'lr': 0.0004992720277716755, 'samples': 1074624, 'steps': 5596, 'loss/train': 2.778695583343506} 08/30/2021 14:11:52 - INFO - __main__ - Step 5598: {'lr': 0.0004992716230332435, 'samples': 1074816, 'steps': 5597, 'loss/train': 3.006305694580078} 08/30/2021 14:11:52 - INFO - __main__ - Step 5599: {'lr': 0.0004992712181824936, 'samples': 1075008, 'steps': 5598, 'loss/train': 2.5861709117889404} 08/30/2021 14:11:53 - INFO - __main__ - Step 5600: {'lr': 0.0004992708132194259, 'samples': 1075200, 'steps': 5599, 'loss/train': 2.4832420349121094} 08/30/2021 14:11:54 - INFO - __main__ - Step 5601: {'lr': 0.0004992704081440407, 'samples': 1075392, 'steps': 5600, 'loss/train': 3.009307384490967} 08/30/2021 14:11:55 - INFO - __main__ - Step 5602: {'lr': 0.0004992700029563381, 'samples': 1075584, 'steps': 5601, 'loss/train': 2.7582900524139404} 08/30/2021 14:11:55 - INFO - __main__ - Step 5603: {'lr': 0.0004992695976563182, 'samples': 1075776, 'steps': 5602, 'loss/train': 2.938291072845459} 08/30/2021 14:11:55 - INFO - __main__ - Step 5604: {'lr': 0.0004992691922439814, 'samples': 1075968, 'steps': 5603, 'loss/train': 4.9404215812683105} 08/30/2021 14:11:56 - INFO - __main__ - Step 5605: {'lr': 0.0004992687867193277, 'samples': 1076160, 'steps': 5604, 'loss/train': 3.016761302947998} 08/30/2021 14:11:57 - INFO - __main__ - Step 5606: {'lr': 0.0004992683810823572, 'samples': 1076352, 'steps': 5605, 'loss/train': 3.258758306503296} 08/30/2021 14:11:58 - INFO - __main__ - Step 5607: {'lr': 0.0004992679753330703, 'samples': 1076544, 'steps': 5606, 'loss/train': 2.7077651023864746} 08/30/2021 14:11:58 - INFO - __main__ - Step 5608: {'lr': 0.0004992675694714671, 'samples': 1076736, 'steps': 5607, 'loss/train': 2.7785913944244385} 08/30/2021 14:11:58 - INFO - __main__ - Step 5609: {'lr': 0.0004992671634975477, 'samples': 1076928, 'steps': 5608, 'loss/train': 1.9022002220153809} 08/30/2021 14:11:59 - INFO - __main__ - Step 5610: {'lr': 0.0004992667574113125, 'samples': 1077120, 'steps': 5609, 'loss/train': 2.3258204460144043} 08/30/2021 14:12:00 - INFO - __main__ - Step 5611: {'lr': 0.0004992663512127615, 'samples': 1077312, 'steps': 5610, 'loss/train': 2.915809154510498} 08/30/2021 14:12:01 - INFO - __main__ - Step 5612: {'lr': 0.0004992659449018949, 'samples': 1077504, 'steps': 5611, 'loss/train': 0.5763670206069946} 08/30/2021 14:12:01 - INFO - __main__ - Step 5613: {'lr': 0.0004992655384787129, 'samples': 1077696, 'steps': 5612, 'loss/train': 2.5807242393493652} 08/30/2021 14:12:01 - INFO - __main__ - Step 5614: {'lr': 0.0004992651319432157, 'samples': 1077888, 'steps': 5613, 'loss/train': 2.2036759853363037} 08/30/2021 14:12:02 - INFO - __main__ - Step 5615: {'lr': 0.0004992647252954035, 'samples': 1078080, 'steps': 5614, 'loss/train': 2.1674485206604004} 08/30/2021 14:12:03 - INFO - __main__ - Step 5616: {'lr': 0.0004992643185352765, 'samples': 1078272, 'steps': 5615, 'loss/train': 2.368358850479126} 08/30/2021 14:12:04 - INFO - __main__ - Step 5617: {'lr': 0.0004992639116628349, 'samples': 1078464, 'steps': 5616, 'loss/train': 2.0436251163482666} 08/30/2021 14:12:04 - INFO - __main__ - Step 5618: {'lr': 0.0004992635046780786, 'samples': 1078656, 'steps': 5617, 'loss/train': 2.672504186630249} 08/30/2021 14:12:04 - INFO - __main__ - Step 5619: {'lr': 0.0004992630975810083, 'samples': 1078848, 'steps': 5618, 'loss/train': 2.3043212890625} 08/30/2021 14:12:05 - INFO - __main__ - Step 5620: {'lr': 0.0004992626903716237, 'samples': 1079040, 'steps': 5619, 'loss/train': 2.338088274002075} 08/30/2021 14:12:06 - INFO - __main__ - Step 5621: {'lr': 0.0004992622830499252, 'samples': 1079232, 'steps': 5620, 'loss/train': 2.329005002975464} 08/30/2021 14:12:07 - INFO - __main__ - Step 5622: {'lr': 0.000499261875615913, 'samples': 1079424, 'steps': 5621, 'loss/train': 2.4516048431396484} 08/30/2021 14:12:07 - INFO - __main__ - Step 5623: {'lr': 0.0004992614680695872, 'samples': 1079616, 'steps': 5622, 'loss/train': 2.6651577949523926} 08/30/2021 14:12:07 - INFO - __main__ - Step 5624: {'lr': 0.0004992610604109481, 'samples': 1079808, 'steps': 5623, 'loss/train': 2.530071258544922} 08/30/2021 14:12:08 - INFO - __main__ - Step 5625: {'lr': 0.0004992606526399957, 'samples': 1080000, 'steps': 5624, 'loss/train': 2.181800603866577} 08/30/2021 14:12:08 - INFO - __main__ - Step 5626: {'lr': 0.0004992602447567304, 'samples': 1080192, 'steps': 5625, 'loss/train': 2.483560562133789} 08/30/2021 14:12:10 - INFO - __main__ - Step 5627: {'lr': 0.0004992598367611523, 'samples': 1080384, 'steps': 5626, 'loss/train': 2.363994598388672} 08/30/2021 14:12:10 - INFO - __main__ - Step 5628: {'lr': 0.0004992594286532615, 'samples': 1080576, 'steps': 5627, 'loss/train': 2.223031759262085} 08/30/2021 14:12:10 - INFO - __main__ - Step 5629: {'lr': 0.0004992590204330583, 'samples': 1080768, 'steps': 5628, 'loss/train': 2.554281711578369} 08/30/2021 14:12:11 - INFO - __main__ - Step 5630: {'lr': 0.0004992586121005427, 'samples': 1080960, 'steps': 5629, 'loss/train': 1.5866557359695435} 08/30/2021 14:12:11 - INFO - __main__ - Step 5631: {'lr': 0.0004992582036557152, 'samples': 1081152, 'steps': 5630, 'loss/train': 1.6307365894317627} 08/30/2021 14:12:13 - INFO - __main__ - Step 5632: {'lr': 0.0004992577950985757, 'samples': 1081344, 'steps': 5631, 'loss/train': 2.209010124206543} 08/30/2021 14:12:13 - INFO - __main__ - Step 5633: {'lr': 0.0004992573864291244, 'samples': 1081536, 'steps': 5632, 'loss/train': 2.5554189682006836} 08/30/2021 14:12:13 - INFO - __main__ - Step 5634: {'lr': 0.0004992569776473616, 'samples': 1081728, 'steps': 5633, 'loss/train': 2.378779411315918} 08/30/2021 14:12:14 - INFO - __main__ - Step 5635: {'lr': 0.0004992565687532875, 'samples': 1081920, 'steps': 5634, 'loss/train': 2.0683438777923584} 08/30/2021 14:12:14 - INFO - __main__ - Step 5636: {'lr': 0.0004992561597469023, 'samples': 1082112, 'steps': 5635, 'loss/train': 2.2773492336273193} 08/30/2021 14:12:16 - INFO - __main__ - Step 5637: {'lr': 0.0004992557506282061, 'samples': 1082304, 'steps': 5636, 'loss/train': 2.407515048980713} 08/30/2021 14:12:16 - INFO - __main__ - Step 5638: {'lr': 0.0004992553413971991, 'samples': 1082496, 'steps': 5637, 'loss/train': 2.873664617538452} 08/30/2021 14:12:16 - INFO - __main__ - Step 5639: {'lr': 0.0004992549320538814, 'samples': 1082688, 'steps': 5638, 'loss/train': 2.7536582946777344} 08/30/2021 14:12:17 - INFO - __main__ - Step 5640: {'lr': 0.0004992545225982533, 'samples': 1082880, 'steps': 5639, 'loss/train': 2.0577661991119385} 08/30/2021 14:12:17 - INFO - __main__ - Step 5641: {'lr': 0.000499254113030315, 'samples': 1083072, 'steps': 5640, 'loss/train': 2.3533098697662354} 08/30/2021 14:12:19 - INFO - __main__ - Step 5642: {'lr': 0.0004992537033500667, 'samples': 1083264, 'steps': 5641, 'loss/train': 1.821448802947998} 08/30/2021 14:12:19 - INFO - __main__ - Step 5643: {'lr': 0.0004992532935575084, 'samples': 1083456, 'steps': 5642, 'loss/train': 1.7020071744918823} 08/30/2021 14:12:19 - INFO - __main__ - Step 5644: {'lr': 0.0004992528836526405, 'samples': 1083648, 'steps': 5643, 'loss/train': 2.7386322021484375} 08/30/2021 14:12:20 - INFO - __main__ - Step 5645: {'lr': 0.0004992524736354631, 'samples': 1083840, 'steps': 5644, 'loss/train': 1.5291237831115723} 08/30/2021 14:12:20 - INFO - __main__ - Step 5646: {'lr': 0.0004992520635059762, 'samples': 1084032, 'steps': 5645, 'loss/train': 2.173515558242798} 08/30/2021 14:12:22 - INFO - __main__ - Step 5647: {'lr': 0.0004992516532641804, 'samples': 1084224, 'steps': 5646, 'loss/train': 2.7405176162719727} 08/30/2021 14:12:22 - INFO - __main__ - Step 5648: {'lr': 0.0004992512429100757, 'samples': 1084416, 'steps': 5647, 'loss/train': 1.0726940631866455} 08/30/2021 14:12:23 - INFO - __main__ - Step 5649: {'lr': 0.000499250832443662, 'samples': 1084608, 'steps': 5648, 'loss/train': 2.2058637142181396} 08/30/2021 14:12:23 - INFO - __main__ - Step 5650: {'lr': 0.0004992504218649398, 'samples': 1084800, 'steps': 5649, 'loss/train': 0.40684834122657776} 08/30/2021 14:12:23 - INFO - __main__ - Step 5651: {'lr': 0.0004992500111739093, 'samples': 1084992, 'steps': 5650, 'loss/train': 2.338634490966797} 08/30/2021 14:12:24 - INFO - __main__ - Step 5652: {'lr': 0.0004992496003705705, 'samples': 1085184, 'steps': 5651, 'loss/train': 2.478384494781494} 08/30/2021 14:12:26 - INFO - __main__ - Step 5653: {'lr': 0.0004992491894549236, 'samples': 1085376, 'steps': 5652, 'loss/train': 2.0849030017852783} 08/30/2021 14:12:26 - INFO - __main__ - Step 5654: {'lr': 0.000499248778426969, 'samples': 1085568, 'steps': 5653, 'loss/train': 2.181152582168579} 08/30/2021 14:12:27 - INFO - __main__ - Step 5655: {'lr': 0.0004992483672867068, 'samples': 1085760, 'steps': 5654, 'loss/train': 2.0722830295562744} 08/30/2021 14:12:27 - INFO - __main__ - Step 5656: {'lr': 0.000499247956034137, 'samples': 1085952, 'steps': 5655, 'loss/train': 1.231980562210083} 08/30/2021 14:12:27 - INFO - __main__ - Step 5657: {'lr': 0.00049924754466926, 'samples': 1086144, 'steps': 5656, 'loss/train': 0.8097274899482727} 08/30/2021 14:12:29 - INFO - __main__ - Step 5658: {'lr': 0.0004992471331920758, 'samples': 1086336, 'steps': 5657, 'loss/train': 2.6777894496917725} 08/30/2021 14:12:29 - INFO - __main__ - Step 5659: {'lr': 0.0004992467216025848, 'samples': 1086528, 'steps': 5658, 'loss/train': 2.5285768508911133} 08/30/2021 14:12:30 - INFO - __main__ - Step 5660: {'lr': 0.0004992463099007871, 'samples': 1086720, 'steps': 5659, 'loss/train': 2.3760643005371094} 08/30/2021 14:12:30 - INFO - __main__ - Step 5661: {'lr': 0.0004992458980866827, 'samples': 1086912, 'steps': 5660, 'loss/train': 2.465883255004883} 08/30/2021 14:12:30 - INFO - __main__ - Step 5662: {'lr': 0.000499245486160272, 'samples': 1087104, 'steps': 5661, 'loss/train': 1.6989326477050781} 08/30/2021 14:12:32 - INFO - __main__ - Step 5663: {'lr': 0.0004992450741215552, 'samples': 1087296, 'steps': 5662, 'loss/train': 2.1420459747314453} 08/30/2021 14:12:33 - INFO - __main__ - Step 5664: {'lr': 0.0004992446619705324, 'samples': 1087488, 'steps': 5663, 'loss/train': 2.51448655128479} 08/30/2021 14:12:33 - INFO - __main__ - Step 5665: {'lr': 0.0004992442497072037, 'samples': 1087680, 'steps': 5664, 'loss/train': 1.8403258323669434} 08/30/2021 14:12:34 - INFO - __main__ - Step 5666: {'lr': 0.0004992438373315694, 'samples': 1087872, 'steps': 5665, 'loss/train': 3.5829086303710938} 08/30/2021 14:12:34 - INFO - __main__ - Step 5667: {'lr': 0.0004992434248436298, 'samples': 1088064, 'steps': 5666, 'loss/train': 1.30825936794281} 08/30/2021 14:12:35 - INFO - __main__ - Step 5668: {'lr': 0.0004992430122433848, 'samples': 1088256, 'steps': 5667, 'loss/train': 2.7855496406555176} 08/30/2021 14:12:36 - INFO - __main__ - Step 5669: {'lr': 0.0004992425995308349, 'samples': 1088448, 'steps': 5668, 'loss/train': 2.707829236984253} 08/30/2021 14:12:36 - INFO - __main__ - Step 5670: {'lr': 0.0004992421867059801, 'samples': 1088640, 'steps': 5669, 'loss/train': 2.8715929985046387} 08/30/2021 14:12:37 - INFO - __main__ - Step 5671: {'lr': 0.0004992417737688206, 'samples': 1088832, 'steps': 5670, 'loss/train': 2.067136287689209} 08/30/2021 14:12:37 - INFO - __main__ - Step 5672: {'lr': 0.0004992413607193566, 'samples': 1089024, 'steps': 5671, 'loss/train': 1.989829182624817} 08/30/2021 14:12:38 - INFO - __main__ - Step 5673: {'lr': 0.0004992409475575882, 'samples': 1089216, 'steps': 5672, 'loss/train': 2.6323845386505127} 08/30/2021 14:12:39 - INFO - __main__ - Step 5674: {'lr': 0.0004992405342835158, 'samples': 1089408, 'steps': 5673, 'loss/train': 2.9494431018829346} 08/30/2021 14:12:39 - INFO - __main__ - Step 5675: {'lr': 0.0004992401208971394, 'samples': 1089600, 'steps': 5674, 'loss/train': 2.3475522994995117} 08/30/2021 14:12:40 - INFO - __main__ - Step 5676: {'lr': 0.0004992397073984592, 'samples': 1089792, 'steps': 5675, 'loss/train': 2.1629555225372314} 08/30/2021 14:12:40 - INFO - __main__ - Step 5677: {'lr': 0.0004992392937874755, 'samples': 1089984, 'steps': 5676, 'loss/train': 2.100853443145752} 08/30/2021 14:12:40 - INFO - __main__ - Step 5678: {'lr': 0.0004992388800641885, 'samples': 1090176, 'steps': 5677, 'loss/train': 2.1264657974243164} 08/30/2021 14:12:42 - INFO - __main__ - Step 5679: {'lr': 0.0004992384662285981, 'samples': 1090368, 'steps': 5678, 'loss/train': 2.2811851501464844} 08/30/2021 14:12:43 - INFO - __main__ - Step 5680: {'lr': 0.0004992380522807049, 'samples': 1090560, 'steps': 5679, 'loss/train': 0.35879984498023987} 08/30/2021 14:12:43 - INFO - __main__ - Step 5681: {'lr': 0.0004992376382205088, 'samples': 1090752, 'steps': 5680, 'loss/train': 2.296266555786133} 08/30/2021 14:12:43 - INFO - __main__ - Step 5682: {'lr': 0.00049923722404801, 'samples': 1090944, 'steps': 5681, 'loss/train': 1.342445969581604} 08/30/2021 14:12:44 - INFO - __main__ - Step 5683: {'lr': 0.0004992368097632089, 'samples': 1091136, 'steps': 5682, 'loss/train': 2.1382083892822266} 08/30/2021 14:12:45 - INFO - __main__ - Step 5684: {'lr': 0.0004992363953661054, 'samples': 1091328, 'steps': 5683, 'loss/train': 2.2334742546081543} 08/30/2021 14:12:45 - INFO - __main__ - Step 5685: {'lr': 0.0004992359808566999, 'samples': 1091520, 'steps': 5684, 'loss/train': 2.283954620361328} 08/30/2021 14:12:46 - INFO - __main__ - Step 5686: {'lr': 0.0004992355662349925, 'samples': 1091712, 'steps': 5685, 'loss/train': 2.114316701889038} 08/30/2021 14:12:46 - INFO - __main__ - Step 5687: {'lr': 0.0004992351515009833, 'samples': 1091904, 'steps': 5686, 'loss/train': 2.6024370193481445} 08/30/2021 14:12:47 - INFO - __main__ - Step 5688: {'lr': 0.0004992347366546727, 'samples': 1092096, 'steps': 5687, 'loss/train': 2.1036834716796875} 08/30/2021 14:12:48 - INFO - __main__ - Step 5689: {'lr': 0.0004992343216960607, 'samples': 1092288, 'steps': 5688, 'loss/train': 2.1468937397003174} 08/30/2021 14:12:49 - INFO - __main__ - Step 5690: {'lr': 0.0004992339066251476, 'samples': 1092480, 'steps': 5689, 'loss/train': 2.0252957344055176} 08/30/2021 14:12:49 - INFO - __main__ - Step 5691: {'lr': 0.0004992334914419337, 'samples': 1092672, 'steps': 5690, 'loss/train': 2.0974056720733643} 08/30/2021 14:12:49 - INFO - __main__ - Step 5692: {'lr': 0.0004992330761464188, 'samples': 1092864, 'steps': 5691, 'loss/train': 1.116600751876831} 08/30/2021 14:12:50 - INFO - __main__ - Step 5693: {'lr': 0.0004992326607386034, 'samples': 1093056, 'steps': 5692, 'loss/train': 2.1761841773986816} 08/30/2021 14:12:51 - INFO - __main__ - Step 5694: {'lr': 0.0004992322452184876, 'samples': 1093248, 'steps': 5693, 'loss/train': 1.6583324670791626} 08/30/2021 14:12:51 - INFO - __main__ - Step 5695: {'lr': 0.0004992318295860718, 'samples': 1093440, 'steps': 5694, 'loss/train': 1.9998258352279663} 08/30/2021 14:12:52 - INFO - __main__ - Step 5696: {'lr': 0.0004992314138413557, 'samples': 1093632, 'steps': 5695, 'loss/train': 1.500299096107483} 08/30/2021 14:12:52 - INFO - __main__ - Step 5697: {'lr': 0.0004992309979843398, 'samples': 1093824, 'steps': 5696, 'loss/train': 1.796570062637329} 08/30/2021 14:12:52 - INFO - __main__ - Step 5698: {'lr': 0.0004992305820150243, 'samples': 1094016, 'steps': 5697, 'loss/train': 2.0542001724243164} 08/30/2021 14:12:54 - INFO - __main__ - Step 5699: {'lr': 0.0004992301659334095, 'samples': 1094208, 'steps': 5698, 'loss/train': 2.145958185195923} 08/30/2021 14:12:54 - INFO - __main__ - Step 5700: {'lr': 0.0004992297497394953, 'samples': 1094400, 'steps': 5699, 'loss/train': 1.3726893663406372} 08/30/2021 14:12:55 - INFO - __main__ - Step 5701: {'lr': 0.000499229333433282, 'samples': 1094592, 'steps': 5700, 'loss/train': 0.8239323496818542} 08/30/2021 14:12:55 - INFO - __main__ - Step 5702: {'lr': 0.0004992289170147699, 'samples': 1094784, 'steps': 5701, 'loss/train': 2.321021556854248} 08/30/2021 14:12:55 - INFO - __main__ - Step 5703: {'lr': 0.000499228500483959, 'samples': 1094976, 'steps': 5702, 'loss/train': 2.34973406791687} 08/30/2021 14:12:58 - INFO - __main__ - Step 5704: {'lr': 0.0004992280838408496, 'samples': 1095168, 'steps': 5703, 'loss/train': 2.7191219329833984} 08/30/2021 14:12:58 - INFO - __main__ - Step 5705: {'lr': 0.0004992276670854419, 'samples': 1095360, 'steps': 5704, 'loss/train': 2.2663156986236572} 08/30/2021 14:12:58 - INFO - __main__ - Step 5706: {'lr': 0.000499227250217736, 'samples': 1095552, 'steps': 5705, 'loss/train': 2.295117139816284} 08/30/2021 14:12:59 - INFO - __main__ - Step 5707: {'lr': 0.0004992268332377323, 'samples': 1095744, 'steps': 5706, 'loss/train': 2.4629361629486084} 08/30/2021 14:12:59 - INFO - __main__ - Step 5708: {'lr': 0.0004992264161454306, 'samples': 1095936, 'steps': 5707, 'loss/train': 1.8976025581359863} 08/30/2021 14:13:01 - INFO - __main__ - Step 5709: {'lr': 0.0004992259989408316, 'samples': 1096128, 'steps': 5708, 'loss/train': 1.6562938690185547} 08/30/2021 14:13:01 - INFO - __main__ - Step 5710: {'lr': 0.000499225581623935, 'samples': 1096320, 'steps': 5709, 'loss/train': 2.2951793670654297} 08/30/2021 14:13:01 - INFO - __main__ - Step 5711: {'lr': 0.0004992251641947412, 'samples': 1096512, 'steps': 5710, 'loss/train': 1.9760348796844482} 08/30/2021 14:13:02 - INFO - __main__ - Step 5712: {'lr': 0.0004992247466532504, 'samples': 1096704, 'steps': 5711, 'loss/train': 2.306309461593628} 08/30/2021 14:13:02 - INFO - __main__ - Step 5713: {'lr': 0.0004992243289994629, 'samples': 1096896, 'steps': 5712, 'loss/train': 2.377441644668579} 08/30/2021 14:13:03 - INFO - __main__ - Step 5714: {'lr': 0.0004992239112333787, 'samples': 1097088, 'steps': 5713, 'loss/train': 1.9280357360839844} 08/30/2021 14:13:04 - INFO - __main__ - Step 5715: {'lr': 0.000499223493354998, 'samples': 1097280, 'steps': 5714, 'loss/train': 2.1363718509674072} 08/30/2021 14:13:04 - INFO - __main__ - Step 5716: {'lr': 0.0004992230753643211, 'samples': 1097472, 'steps': 5715, 'loss/train': 2.1121766567230225} 08/30/2021 14:13:05 - INFO - __main__ - Step 5717: {'lr': 0.0004992226572613481, 'samples': 1097664, 'steps': 5716, 'loss/train': 2.4798450469970703} 08/30/2021 14:13:05 - INFO - __main__ - Step 5718: {'lr': 0.0004992222390460792, 'samples': 1097856, 'steps': 5717, 'loss/train': 1.9710110425949097} 08/30/2021 14:13:05 - INFO - __main__ - Step 5719: {'lr': 0.0004992218207185146, 'samples': 1098048, 'steps': 5718, 'loss/train': 1.659106969833374} 08/30/2021 14:13:07 - INFO - __main__ - Step 5720: {'lr': 0.0004992214022786546, 'samples': 1098240, 'steps': 5719, 'loss/train': 1.6958831548690796} 08/30/2021 14:13:07 - INFO - __main__ - Step 5721: {'lr': 0.0004992209837264991, 'samples': 1098432, 'steps': 5720, 'loss/train': 2.4289145469665527} 08/30/2021 14:13:08 - INFO - __main__ - Step 5722: {'lr': 0.0004992205650620487, 'samples': 1098624, 'steps': 5721, 'loss/train': 1.7528969049453735} 08/30/2021 14:13:08 - INFO - __main__ - Step 5723: {'lr': 0.0004992201462853032, 'samples': 1098816, 'steps': 5722, 'loss/train': 2.3579201698303223} 08/30/2021 14:13:08 - INFO - __main__ - Step 5724: {'lr': 0.000499219727396263, 'samples': 1099008, 'steps': 5723, 'loss/train': 2.2928426265716553} 08/30/2021 14:13:10 - INFO - __main__ - Step 5725: {'lr': 0.0004992193083949282, 'samples': 1099200, 'steps': 5724, 'loss/train': 1.9065685272216797} 08/30/2021 14:13:10 - INFO - __main__ - Step 5726: {'lr': 0.000499218889281299, 'samples': 1099392, 'steps': 5725, 'loss/train': 2.054805278778076} 08/30/2021 14:13:11 - INFO - __main__ - Step 5727: {'lr': 0.0004992184700553756, 'samples': 1099584, 'steps': 5726, 'loss/train': 2.198212146759033} 08/30/2021 14:13:11 - INFO - __main__ - Step 5728: {'lr': 0.0004992180507171583, 'samples': 1099776, 'steps': 5727, 'loss/train': 1.9786972999572754} 08/30/2021 14:13:11 - INFO - __main__ - Step 5729: {'lr': 0.0004992176312666472, 'samples': 1099968, 'steps': 5728, 'loss/train': 1.439853549003601} 08/30/2021 14:13:13 - INFO - __main__ - Step 5730: {'lr': 0.0004992172117038424, 'samples': 1100160, 'steps': 5729, 'loss/train': 3.0891635417938232} 08/30/2021 14:13:13 - INFO - __main__ - Step 5731: {'lr': 0.0004992167920287443, 'samples': 1100352, 'steps': 5730, 'loss/train': 1.9488180875778198} 08/30/2021 14:13:13 - INFO - __main__ - Step 5732: {'lr': 0.0004992163722413528, 'samples': 1100544, 'steps': 5731, 'loss/train': 2.0667245388031006} 08/30/2021 14:13:14 - INFO - __main__ - Step 5733: {'lr': 0.0004992159523416683, 'samples': 1100736, 'steps': 5732, 'loss/train': 2.0932631492614746} 08/30/2021 14:13:14 - INFO - __main__ - Step 5734: {'lr': 0.000499215532329691, 'samples': 1100928, 'steps': 5733, 'loss/train': 0.6742189526557922} 08/30/2021 14:13:16 - INFO - __main__ - Step 5735: {'lr': 0.000499215112205421, 'samples': 1101120, 'steps': 5734, 'loss/train': 1.9801772832870483} 08/30/2021 14:13:16 - INFO - __main__ - Step 5736: {'lr': 0.0004992146919688584, 'samples': 1101312, 'steps': 5735, 'loss/train': 2.2107222080230713} 08/30/2021 14:13:16 - INFO - __main__ - Step 5737: {'lr': 0.0004992142716200036, 'samples': 1101504, 'steps': 5736, 'loss/train': 2.240306854248047} 08/30/2021 14:13:17 - INFO - __main__ - Step 5738: {'lr': 0.0004992138511588567, 'samples': 1101696, 'steps': 5737, 'loss/train': 1.975052833557129} 08/30/2021 14:13:17 - INFO - __main__ - Step 5739: {'lr': 0.0004992134305854179, 'samples': 1101888, 'steps': 5738, 'loss/train': 2.5487613677978516} 08/30/2021 14:13:19 - INFO - __main__ - Step 5740: {'lr': 0.0004992130098996873, 'samples': 1102080, 'steps': 5739, 'loss/train': 2.0061371326446533} 08/30/2021 14:13:19 - INFO - __main__ - Step 5741: {'lr': 0.0004992125891016652, 'samples': 1102272, 'steps': 5740, 'loss/train': 2.1268246173858643} 08/30/2021 14:13:20 - INFO - __main__ - Step 5742: {'lr': 0.0004992121681913518, 'samples': 1102464, 'steps': 5741, 'loss/train': 1.9292787313461304} 08/30/2021 14:13:20 - INFO - __main__ - Step 5743: {'lr': 0.0004992117471687472, 'samples': 1102656, 'steps': 5742, 'loss/train': 2.0467426776885986} 08/30/2021 14:13:20 - INFO - __main__ - Step 5744: {'lr': 0.0004992113260338517, 'samples': 1102848, 'steps': 5743, 'loss/train': 2.078896999359131} 08/30/2021 14:13:21 - INFO - __main__ - Step 5745: {'lr': 0.0004992109047866653, 'samples': 1103040, 'steps': 5744, 'loss/train': 2.2047533988952637} 08/30/2021 14:13:22 - INFO - __main__ - Step 5746: {'lr': 0.0004992104834271884, 'samples': 1103232, 'steps': 5745, 'loss/train': 2.364816665649414} 08/30/2021 14:13:22 - INFO - __main__ - Step 5747: {'lr': 0.0004992100619554211, 'samples': 1103424, 'steps': 5746, 'loss/train': 2.120272159576416} 08/30/2021 14:13:23 - INFO - __main__ - Step 5748: {'lr': 0.0004992096403713635, 'samples': 1103616, 'steps': 5747, 'loss/train': 2.5253005027770996} 08/30/2021 14:13:23 - INFO - __main__ - Step 5749: {'lr': 0.000499209218675016, 'samples': 1103808, 'steps': 5748, 'loss/train': 2.4032397270202637} 08/30/2021 14:13:24 - INFO - __main__ - Step 5750: {'lr': 0.0004992087968663786, 'samples': 1104000, 'steps': 5749, 'loss/train': 2.4137752056121826} 08/30/2021 14:13:25 - INFO - __main__ - Step 5751: {'lr': 0.0004992083749454515, 'samples': 1104192, 'steps': 5750, 'loss/train': 1.768087387084961} 08/30/2021 14:13:25 - INFO - __main__ - Step 5752: {'lr': 0.0004992079529122351, 'samples': 1104384, 'steps': 5751, 'loss/train': 2.147995948791504} 08/30/2021 14:13:26 - INFO - __main__ - Step 5753: {'lr': 0.0004992075307667294, 'samples': 1104576, 'steps': 5752, 'loss/train': 2.203209638595581} 08/30/2021 14:13:26 - INFO - __main__ - Step 5754: {'lr': 0.0004992071085089346, 'samples': 1104768, 'steps': 5753, 'loss/train': 2.765620231628418} 08/30/2021 14:13:27 - INFO - __main__ - Step 5755: {'lr': 0.0004992066861388509, 'samples': 1104960, 'steps': 5754, 'loss/train': 2.8312582969665527} 08/30/2021 14:13:28 - INFO - __main__ - Step 5756: {'lr': 0.0004992062636564786, 'samples': 1105152, 'steps': 5755, 'loss/train': 1.6942883729934692} 08/30/2021 14:13:29 - INFO - __main__ - Step 5757: {'lr': 0.0004992058410618177, 'samples': 1105344, 'steps': 5756, 'loss/train': 2.234927177429199} 08/30/2021 14:13:29 - INFO - __main__ - Step 5758: {'lr': 0.0004992054183548685, 'samples': 1105536, 'steps': 5757, 'loss/train': 1.7898328304290771} 08/30/2021 14:13:30 - INFO - __main__ - Step 5759: {'lr': 0.0004992049955356313, 'samples': 1105728, 'steps': 5758, 'loss/train': 1.5698727369308472} 08/30/2021 14:13:30 - INFO - __main__ - Step 5760: {'lr': 0.0004992045726041061, 'samples': 1105920, 'steps': 5759, 'loss/train': 1.4664987325668335} 08/30/2021 14:13:31 - INFO - __main__ - Step 5761: {'lr': 0.0004992041495602931, 'samples': 1106112, 'steps': 5760, 'loss/train': 2.4140067100524902} 08/30/2021 14:13:32 - INFO - __main__ - Step 5762: {'lr': 0.0004992037264041927, 'samples': 1106304, 'steps': 5761, 'loss/train': 2.1634068489074707} 08/30/2021 14:13:32 - INFO - __main__ - Step 5763: {'lr': 0.0004992033031358048, 'samples': 1106496, 'steps': 5762, 'loss/train': 1.0948678255081177} 08/30/2021 14:13:33 - INFO - __main__ - Step 5764: {'lr': 0.0004992028797551298, 'samples': 1106688, 'steps': 5763, 'loss/train': 1.8745142221450806} 08/30/2021 14:13:33 - INFO - __main__ - Step 5765: {'lr': 0.0004992024562621678, 'samples': 1106880, 'steps': 5764, 'loss/train': 2.4703831672668457} 08/30/2021 14:13:33 - INFO - __main__ - Step 5766: {'lr': 0.0004992020326569191, 'samples': 1107072, 'steps': 5765, 'loss/train': 0.3508596420288086} 08/30/2021 14:13:35 - INFO - __main__ - Step 5767: {'lr': 0.0004992016089393837, 'samples': 1107264, 'steps': 5766, 'loss/train': 2.3133385181427} 08/30/2021 14:13:35 - INFO - __main__ - Step 5768: {'lr': 0.000499201185109562, 'samples': 1107456, 'steps': 5767, 'loss/train': 1.7067315578460693} 08/30/2021 14:13:36 - INFO - __main__ - Step 5769: {'lr': 0.000499200761167454, 'samples': 1107648, 'steps': 5768, 'loss/train': 1.6532922983169556} 08/30/2021 14:13:36 - INFO - __main__ - Step 5770: {'lr': 0.0004992003371130601, 'samples': 1107840, 'steps': 5769, 'loss/train': 2.325556516647339} 08/30/2021 14:13:36 - INFO - __main__ - Step 5771: {'lr': 0.0004991999129463803, 'samples': 1108032, 'steps': 5770, 'loss/train': 2.090094566345215} 08/30/2021 14:13:38 - INFO - __main__ - Step 5772: {'lr': 0.0004991994886674148, 'samples': 1108224, 'steps': 5771, 'loss/train': 2.066429376602173} 08/30/2021 14:13:38 - INFO - __main__ - Step 5773: {'lr': 0.000499199064276164, 'samples': 1108416, 'steps': 5772, 'loss/train': 2.2343039512634277} 08/30/2021 14:13:39 - INFO - __main__ - Step 5774: {'lr': 0.0004991986397726278, 'samples': 1108608, 'steps': 5773, 'loss/train': 2.1294426918029785} 08/30/2021 14:13:39 - INFO - __main__ - Step 5775: {'lr': 0.0004991982151568066, 'samples': 1108800, 'steps': 5774, 'loss/train': 2.2161622047424316} 08/30/2021 14:13:39 - INFO - __main__ - Step 5776: {'lr': 0.0004991977904287006, 'samples': 1108992, 'steps': 5775, 'loss/train': 2.51168155670166} 08/30/2021 14:13:41 - INFO - __main__ - Step 5777: {'lr': 0.0004991973655883099, 'samples': 1109184, 'steps': 5776, 'loss/train': 1.9757490158081055} 08/30/2021 14:13:41 - INFO - __main__ - Step 5778: {'lr': 0.0004991969406356346, 'samples': 1109376, 'steps': 5777, 'loss/train': 2.0249340534210205} 08/30/2021 14:13:42 - INFO - __main__ - Step 5779: {'lr': 0.0004991965155706752, 'samples': 1109568, 'steps': 5778, 'loss/train': 1.403512716293335} 08/30/2021 14:13:42 - INFO - __main__ - Step 5780: {'lr': 0.0004991960903934315, 'samples': 1109760, 'steps': 5779, 'loss/train': 1.8740057945251465} 08/30/2021 14:13:42 - INFO - __main__ - Step 5781: {'lr': 0.0004991956651039039, 'samples': 1109952, 'steps': 5780, 'loss/train': 2.0561277866363525} 08/30/2021 14:13:43 - INFO - __main__ - Step 5782: {'lr': 0.0004991952397020927, 'samples': 1110144, 'steps': 5781, 'loss/train': 0.9645845890045166} 08/30/2021 14:13:44 - INFO - __main__ - Step 5783: {'lr': 0.0004991948141879978, 'samples': 1110336, 'steps': 5782, 'loss/train': 2.164886474609375} 08/30/2021 14:13:45 - INFO - __main__ - Step 5784: {'lr': 0.0004991943885616198, 'samples': 1110528, 'steps': 5783, 'loss/train': 1.8348333835601807} 08/30/2021 14:13:45 - INFO - __main__ - Step 5785: {'lr': 0.0004991939628229585, 'samples': 1110720, 'steps': 5784, 'loss/train': 1.9779103994369507} 08/30/2021 14:13:45 - INFO - __main__ - Step 5786: {'lr': 0.0004991935369720143, 'samples': 1110912, 'steps': 5785, 'loss/train': 1.8907867670059204} 08/30/2021 14:13:46 - INFO - __main__ - Step 5787: {'lr': 0.0004991931110087873, 'samples': 1111104, 'steps': 5786, 'loss/train': 2.2632336616516113} 08/30/2021 14:13:47 - INFO - __main__ - Step 5788: {'lr': 0.0004991926849332777, 'samples': 1111296, 'steps': 5787, 'loss/train': 2.4298908710479736} 08/30/2021 14:13:48 - INFO - __main__ - Step 5789: {'lr': 0.0004991922587454858, 'samples': 1111488, 'steps': 5788, 'loss/train': 1.721315860748291} 08/30/2021 14:13:48 - INFO - __main__ - Step 5790: {'lr': 0.0004991918324454117, 'samples': 1111680, 'steps': 5789, 'loss/train': 1.5899486541748047} 08/30/2021 14:13:48 - INFO - __main__ - Step 5791: {'lr': 0.0004991914060330556, 'samples': 1111872, 'steps': 5790, 'loss/train': 1.92160165309906} 08/30/2021 14:13:49 - INFO - __main__ - Step 5792: {'lr': 0.0004991909795084177, 'samples': 1112064, 'steps': 5791, 'loss/train': 2.054802417755127} 08/30/2021 14:13:50 - INFO - __main__ - Step 5793: {'lr': 0.0004991905528714981, 'samples': 1112256, 'steps': 5792, 'loss/train': 2.0912177562713623} 08/30/2021 14:13:51 - INFO - __main__ - Step 5794: {'lr': 0.0004991901261222971, 'samples': 1112448, 'steps': 5793, 'loss/train': 1.492459774017334} 08/30/2021 14:13:51 - INFO - __main__ - Step 5795: {'lr': 0.000499189699260815, 'samples': 1112640, 'steps': 5794, 'loss/train': 2.2374181747436523} 08/30/2021 14:13:52 - INFO - __main__ - Step 5796: {'lr': 0.0004991892722870517, 'samples': 1112832, 'steps': 5795, 'loss/train': 2.1417839527130127} 08/30/2021 14:13:52 - INFO - __main__ - Step 5797: {'lr': 0.0004991888452010076, 'samples': 1113024, 'steps': 5796, 'loss/train': 2.084658145904541} 08/30/2021 14:13:52 - INFO - __main__ - Step 5798: {'lr': 0.000499188418002683, 'samples': 1113216, 'steps': 5797, 'loss/train': 2.9410722255706787} 08/30/2021 14:13:54 - INFO - __main__ - Step 5799: {'lr': 0.0004991879906920779, 'samples': 1113408, 'steps': 5798, 'loss/train': 2.235234260559082} 08/30/2021 14:13:54 - INFO - __main__ - Step 5800: {'lr': 0.0004991875632691924, 'samples': 1113600, 'steps': 5799, 'loss/train': 2.190568685531616} 08/30/2021 14:13:55 - INFO - __main__ - Step 5801: {'lr': 0.0004991871357340269, 'samples': 1113792, 'steps': 5800, 'loss/train': 2.011568546295166} 08/30/2021 14:13:55 - INFO - __main__ - Step 5802: {'lr': 0.0004991867080865815, 'samples': 1113984, 'steps': 5801, 'loss/train': 2.3917582035064697} 08/30/2021 14:13:55 - INFO - __main__ - Step 5803: {'lr': 0.0004991862803268564, 'samples': 1114176, 'steps': 5802, 'loss/train': 1.774945616722107} 08/30/2021 14:13:57 - INFO - __main__ - Step 5804: {'lr': 0.0004991858524548519, 'samples': 1114368, 'steps': 5803, 'loss/train': 1.6664633750915527} 08/30/2021 14:13:58 - INFO - __main__ - Step 5805: {'lr': 0.000499185424470568, 'samples': 1114560, 'steps': 5804, 'loss/train': 2.505523443222046} 08/30/2021 14:13:58 - INFO - __main__ - Step 5806: {'lr': 0.0004991849963740052, 'samples': 1114752, 'steps': 5805, 'loss/train': 0.5344151258468628} 08/30/2021 14:13:58 - INFO - __main__ - Step 5807: {'lr': 0.0004991845681651632, 'samples': 1114944, 'steps': 5806, 'loss/train': 2.6453616619110107} 08/30/2021 14:13:59 - INFO - __main__ - Step 5808: {'lr': 0.0004991841398440427, 'samples': 1115136, 'steps': 5807, 'loss/train': 1.5687943696975708} 08/30/2021 14:14:00 - INFO - __main__ - Step 5809: {'lr': 0.0004991837114106436, 'samples': 1115328, 'steps': 5808, 'loss/train': 1.5863301753997803} 08/30/2021 14:14:01 - INFO - __main__ - Step 5810: {'lr': 0.0004991832828649661, 'samples': 1115520, 'steps': 5809, 'loss/train': 2.273674488067627} 08/30/2021 14:14:01 - INFO - __main__ - Step 5811: {'lr': 0.0004991828542070105, 'samples': 1115712, 'steps': 5810, 'loss/train': 2.063884735107422} 08/30/2021 14:14:01 - INFO - __main__ - Step 5812: {'lr': 0.000499182425436777, 'samples': 1115904, 'steps': 5811, 'loss/train': 2.101816177368164} 08/30/2021 14:14:02 - INFO - __main__ - Step 5813: {'lr': 0.0004991819965542657, 'samples': 1116096, 'steps': 5812, 'loss/train': 1.9726061820983887} 08/30/2021 14:14:04 - INFO - __main__ - Step 5814: {'lr': 0.0004991815675594768, 'samples': 1116288, 'steps': 5813, 'loss/train': 2.189896583557129} 08/30/2021 14:14:04 - INFO - __main__ - Step 5815: {'lr': 0.0004991811384524106, 'samples': 1116480, 'steps': 5814, 'loss/train': 1.5735437870025635} 08/30/2021 14:14:05 - INFO - __main__ - Step 5816: {'lr': 0.0004991807092330671, 'samples': 1116672, 'steps': 5815, 'loss/train': 1.6591681241989136} 08/30/2021 14:14:05 - INFO - __main__ - Step 5817: {'lr': 0.0004991802799014467, 'samples': 1116864, 'steps': 5816, 'loss/train': 3.386476516723633} 08/30/2021 14:14:05 - INFO - __main__ - Step 5818: {'lr': 0.0004991798504575495, 'samples': 1117056, 'steps': 5817, 'loss/train': 2.6909241676330566} 08/30/2021 14:14:07 - INFO - __main__ - Step 5819: {'lr': 0.0004991794209013758, 'samples': 1117248, 'steps': 5818, 'loss/train': 2.2129266262054443} 08/30/2021 14:14:07 - INFO - __main__ - Step 5820: {'lr': 0.0004991789912329257, 'samples': 1117440, 'steps': 5819, 'loss/train': 2.9793317317962646} 08/30/2021 14:14:08 - INFO - __main__ - Step 5821: {'lr': 0.0004991785614521993, 'samples': 1117632, 'steps': 5820, 'loss/train': 2.5976696014404297} 08/30/2021 14:14:08 - INFO - __main__ - Step 5822: {'lr': 0.0004991781315591969, 'samples': 1117824, 'steps': 5821, 'loss/train': 1.6759430170059204} 08/30/2021 14:14:08 - INFO - __main__ - Step 5823: {'lr': 0.0004991777015539186, 'samples': 1118016, 'steps': 5822, 'loss/train': 2.5088138580322266} 08/30/2021 14:14:11 - INFO - __main__ - Step 5824: {'lr': 0.0004991772714363649, 'samples': 1118208, 'steps': 5823, 'loss/train': 2.419053077697754} 08/30/2021 14:14:11 - INFO - __main__ - Step 5825: {'lr': 0.0004991768412065355, 'samples': 1118400, 'steps': 5824, 'loss/train': 2.1020472049713135} 08/30/2021 14:14:11 - INFO - __main__ - Step 5826: {'lr': 0.000499176410864431, 'samples': 1118592, 'steps': 5825, 'loss/train': 1.631892204284668} 08/30/2021 14:14:12 - INFO - __main__ - Step 5827: {'lr': 0.0004991759804100515, 'samples': 1118784, 'steps': 5826, 'loss/train': 1.3924821615219116} 08/30/2021 14:14:12 - INFO - __main__ - Step 5828: {'lr': 0.000499175549843397, 'samples': 1118976, 'steps': 5827, 'loss/train': 1.8927206993103027} 08/30/2021 14:14:12 - INFO - __main__ - Step 5829: {'lr': 0.0004991751191644679, 'samples': 1119168, 'steps': 5828, 'loss/train': 0.4454633593559265} 08/30/2021 14:14:14 - INFO - __main__ - Step 5830: {'lr': 0.0004991746883732644, 'samples': 1119360, 'steps': 5829, 'loss/train': 0.39374086260795593} 08/30/2021 14:14:14 - INFO - __main__ - Step 5831: {'lr': 0.0004991742574697866, 'samples': 1119552, 'steps': 5830, 'loss/train': 1.9435609579086304} 08/30/2021 14:14:15 - INFO - __main__ - Step 5832: {'lr': 0.0004991738264540347, 'samples': 1119744, 'steps': 5831, 'loss/train': 2.1106748580932617} 08/30/2021 14:14:15 - INFO - __main__ - Step 5833: {'lr': 0.0004991733953260089, 'samples': 1119936, 'steps': 5832, 'loss/train': 2.182868242263794} 08/30/2021 14:14:15 - INFO - __main__ - Step 5834: {'lr': 0.0004991729640857095, 'samples': 1120128, 'steps': 5833, 'loss/train': 1.6570278406143188} 08/30/2021 14:14:17 - INFO - __main__ - Step 5835: {'lr': 0.0004991725327331366, 'samples': 1120320, 'steps': 5834, 'loss/train': 0.9613577127456665} 08/30/2021 14:14:18 - INFO - __main__ - Step 5836: {'lr': 0.0004991721012682903, 'samples': 1120512, 'steps': 5835, 'loss/train': 2.544282913208008} 08/30/2021 14:14:18 - INFO - __main__ - Step 5837: {'lr': 0.0004991716696911709, 'samples': 1120704, 'steps': 5836, 'loss/train': 2.135673999786377} 08/30/2021 14:14:18 - INFO - __main__ - Step 5838: {'lr': 0.0004991712380017786, 'samples': 1120896, 'steps': 5837, 'loss/train': 1.9499467611312866} 08/30/2021 14:14:19 - INFO - __main__ - Step 5839: {'lr': 0.0004991708062001137, 'samples': 1121088, 'steps': 5838, 'loss/train': 1.840232014656067} 08/30/2021 14:14:20 - INFO - __main__ - Step 5840: {'lr': 0.0004991703742861762, 'samples': 1121280, 'steps': 5839, 'loss/train': 2.009258270263672} 08/30/2021 14:14:21 - INFO - __main__ - Step 5841: {'lr': 0.0004991699422599664, 'samples': 1121472, 'steps': 5840, 'loss/train': 1.9192055463790894} 08/30/2021 14:14:21 - INFO - __main__ - Step 5842: {'lr': 0.0004991695101214844, 'samples': 1121664, 'steps': 5841, 'loss/train': 1.596557855606079} 08/30/2021 14:14:21 - INFO - __main__ - Step 5843: {'lr': 0.0004991690778707305, 'samples': 1121856, 'steps': 5842, 'loss/train': 1.9584181308746338} 08/30/2021 14:14:22 - INFO - __main__ - Step 5844: {'lr': 0.0004991686455077049, 'samples': 1122048, 'steps': 5843, 'loss/train': 0.23421703279018402} 08/30/2021 14:14:23 - INFO - __main__ - Step 5845: {'lr': 0.0004991682130324078, 'samples': 1122240, 'steps': 5844, 'loss/train': 2.0000855922698975} 08/30/2021 14:14:24 - INFO - __main__ - Step 5846: {'lr': 0.0004991677804448392, 'samples': 1122432, 'steps': 5845, 'loss/train': 1.8915375471115112} 08/30/2021 14:14:24 - INFO - __main__ - Step 5847: {'lr': 0.0004991673477449995, 'samples': 1122624, 'steps': 5846, 'loss/train': 2.2981455326080322} 08/30/2021 14:14:25 - INFO - __main__ - Step 5848: {'lr': 0.0004991669149328889, 'samples': 1122816, 'steps': 5847, 'loss/train': 2.2572288513183594} 08/30/2021 14:14:25 - INFO - __main__ - Step 5849: {'lr': 0.0004991664820085074, 'samples': 1123008, 'steps': 5848, 'loss/train': 1.9210668802261353} 08/30/2021 14:14:27 - INFO - __main__ - Step 5850: {'lr': 0.0004991660489718554, 'samples': 1123200, 'steps': 5849, 'loss/train': 0.2859579920768738} 08/30/2021 14:14:27 - INFO - __main__ - Step 5851: {'lr': 0.0004991656158229331, 'samples': 1123392, 'steps': 5850, 'loss/train': 2.6969258785247803} 08/30/2021 14:14:28 - INFO - __main__ - Step 5852: {'lr': 0.0004991651825617406, 'samples': 1123584, 'steps': 5851, 'loss/train': 0.5447800755500793} 08/30/2021 14:14:28 - INFO - __main__ - Step 5853: {'lr': 0.000499164749188278, 'samples': 1123776, 'steps': 5852, 'loss/train': 3.3150076866149902} 08/30/2021 14:14:29 - INFO - __main__ - Step 5854: {'lr': 0.0004991643157025458, 'samples': 1123968, 'steps': 5853, 'loss/train': 2.355253219604492} 08/30/2021 14:14:29 - INFO - __main__ - Step 5855: {'lr': 0.0004991638821045439, 'samples': 1124160, 'steps': 5854, 'loss/train': 2.568922996520996} 08/30/2021 14:14:30 - INFO - __main__ - Step 5856: {'lr': 0.0004991634483942725, 'samples': 1124352, 'steps': 5855, 'loss/train': 1.9149999618530273} 08/30/2021 14:14:31 - INFO - __main__ - Step 5857: {'lr': 0.000499163014571732, 'samples': 1124544, 'steps': 5856, 'loss/train': 2.3357861042022705} 08/30/2021 14:14:31 - INFO - __main__ - Step 5858: {'lr': 0.0004991625806369225, 'samples': 1124736, 'steps': 5857, 'loss/train': 1.2552976608276367} 08/30/2021 14:14:31 - INFO - __main__ - Step 5859: {'lr': 0.0004991621465898441, 'samples': 1124928, 'steps': 5858, 'loss/train': 2.1629445552825928} 08/30/2021 14:14:32 - INFO - __main__ - Step 5860: {'lr': 0.0004991617124304971, 'samples': 1125120, 'steps': 5859, 'loss/train': 2.0742111206054688} 08/30/2021 14:14:32 - INFO - __main__ - Step 5861: {'lr': 0.0004991612781588818, 'samples': 1125312, 'steps': 5860, 'loss/train': 1.6806098222732544} 08/30/2021 14:14:34 - INFO - __main__ - Step 5862: {'lr': 0.0004991608437749981, 'samples': 1125504, 'steps': 5861, 'loss/train': 1.7067089080810547} 08/30/2021 14:14:34 - INFO - __main__ - Step 5863: {'lr': 0.0004991604092788465, 'samples': 1125696, 'steps': 5862, 'loss/train': 1.7889811992645264} 08/30/2021 14:14:35 - INFO - __main__ - Step 5864: {'lr': 0.000499159974670427, 'samples': 1125888, 'steps': 5863, 'loss/train': 2.5286667346954346} 08/30/2021 14:14:35 - INFO - __main__ - Step 5865: {'lr': 0.00049915953994974, 'samples': 1126080, 'steps': 5864, 'loss/train': 1.9244738817214966} 08/30/2021 14:14:35 - INFO - __main__ - Step 5866: {'lr': 0.0004991591051167853, 'samples': 1126272, 'steps': 5865, 'loss/train': 1.942263126373291} 08/30/2021 14:14:37 - INFO - __main__ - Step 5867: {'lr': 0.0004991586701715635, 'samples': 1126464, 'steps': 5866, 'loss/train': 2.4721972942352295} 08/30/2021 14:14:37 - INFO - __main__ - Step 5868: {'lr': 0.0004991582351140747, 'samples': 1126656, 'steps': 5867, 'loss/train': 2.113710403442383} 08/30/2021 14:14:38 - INFO - __main__ - Step 5869: {'lr': 0.000499157799944319, 'samples': 1126848, 'steps': 5868, 'loss/train': 2.146578788757324} 08/30/2021 14:14:38 - INFO - __main__ - Step 5870: {'lr': 0.0004991573646622965, 'samples': 1127040, 'steps': 5869, 'loss/train': 2.503370761871338} 08/30/2021 14:14:38 - INFO - __main__ - Step 5871: {'lr': 0.0004991569292680078, 'samples': 1127232, 'steps': 5870, 'loss/train': 2.4791712760925293} 08/30/2021 14:14:40 - INFO - __main__ - Step 5872: {'lr': 0.0004991564937614526, 'samples': 1127424, 'steps': 5871, 'loss/train': 1.91326105594635} 08/30/2021 14:14:41 - INFO - __main__ - Step 5873: {'lr': 0.0004991560581426314, 'samples': 1127616, 'steps': 5872, 'loss/train': 1.3771426677703857} 08/30/2021 14:14:41 - INFO - __main__ - Step 5874: {'lr': 0.0004991556224115444, 'samples': 1127808, 'steps': 5873, 'loss/train': 1.8707513809204102} 08/30/2021 14:14:42 - INFO - __main__ - Step 5875: {'lr': 0.0004991551865681916, 'samples': 1128000, 'steps': 5874, 'loss/train': 1.7729097604751587} 08/30/2021 14:14:42 - INFO - __main__ - Step 5876: {'lr': 0.0004991547506125734, 'samples': 1128192, 'steps': 5875, 'loss/train': 1.8714960813522339} 08/30/2021 14:14:44 - INFO - __main__ - Step 5877: {'lr': 0.0004991543145446899, 'samples': 1128384, 'steps': 5876, 'loss/train': 0.32309070229530334} 08/30/2021 14:14:44 - INFO - __main__ - Step 5878: {'lr': 0.0004991538783645413, 'samples': 1128576, 'steps': 5877, 'loss/train': 2.4618256092071533} 08/30/2021 14:14:44 - INFO - __main__ - Step 5879: {'lr': 0.0004991534420721278, 'samples': 1128768, 'steps': 5878, 'loss/train': 2.109403610229492} 08/30/2021 14:14:45 - INFO - __main__ - Step 5880: {'lr': 0.0004991530056674496, 'samples': 1128960, 'steps': 5879, 'loss/train': 2.2718541622161865} 08/30/2021 14:14:45 - INFO - __main__ - Step 5881: {'lr': 0.000499152569150507, 'samples': 1129152, 'steps': 5880, 'loss/train': 1.8346096277236938} 08/30/2021 14:14:46 - INFO - __main__ - Step 5882: {'lr': 0.0004991521325213, 'samples': 1129344, 'steps': 5881, 'loss/train': 2.1230640411376953} 08/30/2021 14:14:47 - INFO - __main__ - Step 5883: {'lr': 0.0004991516957798289, 'samples': 1129536, 'steps': 5882, 'loss/train': 2.804133415222168} 08/30/2021 14:14:48 - INFO - __main__ - Step 5884: {'lr': 0.0004991512589260939, 'samples': 1129728, 'steps': 5883, 'loss/train': 2.043588638305664} 08/30/2021 14:14:48 - INFO - __main__ - Step 5885: {'lr': 0.0004991508219600952, 'samples': 1129920, 'steps': 5884, 'loss/train': 2.5084891319274902} 08/30/2021 14:14:48 - INFO - __main__ - Step 5886: {'lr': 0.000499150384881833, 'samples': 1130112, 'steps': 5885, 'loss/train': 2.2138478755950928} 08/30/2021 14:14:49 - INFO - __main__ - Step 5887: {'lr': 0.0004991499476913074, 'samples': 1130304, 'steps': 5886, 'loss/train': 0.22717320919036865} 08/30/2021 14:14:50 - INFO - __main__ - Step 5888: {'lr': 0.0004991495103885187, 'samples': 1130496, 'steps': 5887, 'loss/train': 1.546987533569336} 08/30/2021 14:14:51 - INFO - __main__ - Step 5889: {'lr': 0.0004991490729734672, 'samples': 1130688, 'steps': 5888, 'loss/train': 2.1046769618988037} 08/30/2021 14:14:51 - INFO - __main__ - Step 5890: {'lr': 0.0004991486354461528, 'samples': 1130880, 'steps': 5889, 'loss/train': 2.289349317550659} 08/30/2021 14:14:51 - INFO - __main__ - Step 5891: {'lr': 0.000499148197806576, 'samples': 1131072, 'steps': 5890, 'loss/train': 2.2530016899108887} 08/30/2021 14:14:52 - INFO - __main__ - Step 5892: {'lr': 0.0004991477600547367, 'samples': 1131264, 'steps': 5891, 'loss/train': 1.896599531173706} 08/30/2021 14:14:53 - INFO - __main__ - Step 5893: {'lr': 0.0004991473221906354, 'samples': 1131456, 'steps': 5892, 'loss/train': 1.9120417833328247} 08/30/2021 14:14:54 - INFO - __main__ - Step 5894: {'lr': 0.0004991468842142722, 'samples': 1131648, 'steps': 5893, 'loss/train': 2.2635602951049805} 08/30/2021 14:14:54 - INFO - __main__ - Step 5895: {'lr': 0.0004991464461256472, 'samples': 1131840, 'steps': 5894, 'loss/train': 2.137824773788452} 08/30/2021 14:14:54 - INFO - __main__ - Step 5896: {'lr': 0.0004991460079247606, 'samples': 1132032, 'steps': 5895, 'loss/train': 2.6105568408966064} 08/30/2021 14:14:55 - INFO - __main__ - Step 5897: {'lr': 0.0004991455696116128, 'samples': 1132224, 'steps': 5896, 'loss/train': 2.203672409057617} 08/30/2021 14:14:57 - INFO - __main__ - Step 5898: {'lr': 0.0004991451311862037, 'samples': 1132416, 'steps': 5897, 'loss/train': 1.998064637184143} 08/30/2021 14:14:57 - INFO - __main__ - Step 5899: {'lr': 0.0004991446926485337, 'samples': 1132608, 'steps': 5898, 'loss/train': 1.3992269039154053} 08/30/2021 14:14:57 - INFO - __main__ - Step 5900: {'lr': 0.0004991442539986029, 'samples': 1132800, 'steps': 5899, 'loss/train': 2.071692705154419} 08/30/2021 14:14:58 - INFO - __main__ - Step 5901: {'lr': 0.0004991438152364117, 'samples': 1132992, 'steps': 5900, 'loss/train': 1.4441382884979248} 08/30/2021 14:14:58 - INFO - __main__ - Step 5902: {'lr': 0.0004991433763619599, 'samples': 1133184, 'steps': 5901, 'loss/train': 1.860714316368103} 08/30/2021 14:14:58 - INFO - __main__ - Step 5903: {'lr': 0.0004991429373752482, 'samples': 1133376, 'steps': 5902, 'loss/train': 0.9205770492553711} 08/30/2021 14:15:00 - INFO - __main__ - Step 5904: {'lr': 0.0004991424982762763, 'samples': 1133568, 'steps': 5903, 'loss/train': 4.166928291320801} 08/30/2021 14:15:01 - INFO - __main__ - Step 5905: {'lr': 0.0004991420590650448, 'samples': 1133760, 'steps': 5904, 'loss/train': 2.067859411239624} 08/30/2021 14:15:01 - INFO - __main__ - Step 5906: {'lr': 0.0004991416197415537, 'samples': 1133952, 'steps': 5905, 'loss/train': 1.859840989112854} 08/30/2021 14:15:01 - INFO - __main__ - Step 5907: {'lr': 0.0004991411803058032, 'samples': 1134144, 'steps': 5906, 'loss/train': 2.4467766284942627} 08/30/2021 14:15:02 - INFO - __main__ - Step 5908: {'lr': 0.0004991407407577936, 'samples': 1134336, 'steps': 5907, 'loss/train': 1.577459454536438} 08/30/2021 14:15:04 - INFO - __main__ - Step 5909: {'lr': 0.0004991403010975249, 'samples': 1134528, 'steps': 5908, 'loss/train': 2.255033254623413} 08/30/2021 14:15:04 - INFO - __main__ - Step 5910: {'lr': 0.0004991398613249976, 'samples': 1134720, 'steps': 5909, 'loss/train': 2.581190586090088} 08/30/2021 14:15:05 - INFO - __main__ - Step 5911: {'lr': 0.0004991394214402115, 'samples': 1134912, 'steps': 5910, 'loss/train': 1.4275797605514526} 08/30/2021 14:15:05 - INFO - __main__ - Step 5912: {'lr': 0.0004991389814431672, 'samples': 1135104, 'steps': 5911, 'loss/train': 1.2042779922485352} 08/30/2021 14:15:06 - INFO - __main__ - Step 5913: {'lr': 0.0004991385413338646, 'samples': 1135296, 'steps': 5912, 'loss/train': 1.218719720840454} 08/30/2021 14:15:06 - INFO - __main__ - Step 5914: {'lr': 0.0004991381011123041, 'samples': 1135488, 'steps': 5913, 'loss/train': 2.3741183280944824} 08/30/2021 14:15:06 - INFO - __main__ - Step 5915: {'lr': 0.0004991376607784857, 'samples': 1135680, 'steps': 5914, 'loss/train': 2.6086196899414062} 08/30/2021 14:15:08 - INFO - __main__ - Step 5916: {'lr': 0.0004991372203324098, 'samples': 1135872, 'steps': 5915, 'loss/train': 2.26519775390625} 08/30/2021 14:15:08 - INFO - __main__ - Step 5917: {'lr': 0.0004991367797740765, 'samples': 1136064, 'steps': 5916, 'loss/train': 2.4970638751983643} 08/30/2021 14:15:09 - INFO - __main__ - Step 5918: {'lr': 0.0004991363391034861, 'samples': 1136256, 'steps': 5917, 'loss/train': 2.891735553741455} 08/30/2021 14:15:09 - INFO - __main__ - Step 5919: {'lr': 0.0004991358983206386, 'samples': 1136448, 'steps': 5918, 'loss/train': 2.8727993965148926} 08/30/2021 14:15:10 - INFO - __main__ - Step 5920: {'lr': 0.0004991354574255344, 'samples': 1136640, 'steps': 5919, 'loss/train': 1.0362807512283325} 08/30/2021 14:15:11 - INFO - __main__ - Step 5921: {'lr': 0.0004991350164181735, 'samples': 1136832, 'steps': 5920, 'loss/train': 1.6289128065109253} 08/30/2021 14:15:11 - INFO - __main__ - Step 5922: {'lr': 0.0004991345752985563, 'samples': 1137024, 'steps': 5921, 'loss/train': 2.078066349029541} 08/30/2021 14:15:12 - INFO - __main__ - Step 5923: {'lr': 0.0004991341340666828, 'samples': 1137216, 'steps': 5922, 'loss/train': 2.2499353885650635} 08/30/2021 14:15:12 - INFO - __main__ - Step 5924: {'lr': 0.0004991336927225534, 'samples': 1137408, 'steps': 5923, 'loss/train': 2.663357973098755} 08/30/2021 14:15:13 - INFO - __main__ - Step 5925: {'lr': 0.0004991332512661682, 'samples': 1137600, 'steps': 5924, 'loss/train': 2.081972122192383} 08/30/2021 14:15:13 - INFO - __main__ - Step 5926: {'lr': 0.0004991328096975273, 'samples': 1137792, 'steps': 5925, 'loss/train': 1.8515006303787231} 08/30/2021 14:15:15 - INFO - __main__ - Step 5927: {'lr': 0.0004991323680166312, 'samples': 1137984, 'steps': 5926, 'loss/train': 2.6087493896484375} 08/30/2021 14:15:16 - INFO - __main__ - Step 5928: {'lr': 0.0004991319262234797, 'samples': 1138176, 'steps': 5927, 'loss/train': 1.694389820098877} 08/30/2021 14:15:16 - INFO - __main__ - Step 5929: {'lr': 0.0004991314843180733, 'samples': 1138368, 'steps': 5928, 'loss/train': 2.105149984359741} 08/30/2021 14:15:16 - INFO - __main__ - Step 5930: {'lr': 0.0004991310423004121, 'samples': 1138560, 'steps': 5929, 'loss/train': 2.134931802749634} 08/30/2021 14:15:17 - INFO - __main__ - Step 5931: {'lr': 0.0004991306001704962, 'samples': 1138752, 'steps': 5930, 'loss/train': 2.170400619506836} 08/30/2021 14:15:18 - INFO - __main__ - Step 5932: {'lr': 0.000499130157928326, 'samples': 1138944, 'steps': 5931, 'loss/train': 2.15702748298645} 08/30/2021 14:15:19 - INFO - __main__ - Step 5933: {'lr': 0.0004991297155739015, 'samples': 1139136, 'steps': 5932, 'loss/train': 2.4520421028137207} 08/30/2021 14:15:19 - INFO - __main__ - Step 5934: {'lr': 0.0004991292731072231, 'samples': 1139328, 'steps': 5933, 'loss/train': 2.2806475162506104} 08/30/2021 14:15:20 - INFO - __main__ - Step 5935: {'lr': 0.0004991288305282908, 'samples': 1139520, 'steps': 5934, 'loss/train': 2.185220241546631} 08/30/2021 14:15:20 - INFO - __main__ - Step 5936: {'lr': 0.0004991283878371049, 'samples': 1139712, 'steps': 5935, 'loss/train': 2.2513556480407715} 08/30/2021 14:15:22 - INFO - __main__ - Step 5937: {'lr': 0.0004991279450336656, 'samples': 1139904, 'steps': 5936, 'loss/train': 1.4557690620422363} 08/30/2021 14:15:22 - INFO - __main__ - Step 5938: {'lr': 0.0004991275021179732, 'samples': 1140096, 'steps': 5937, 'loss/train': 2.34891939163208} 08/30/2021 14:15:22 - INFO - __main__ - Step 5939: {'lr': 0.0004991270590900277, 'samples': 1140288, 'steps': 5938, 'loss/train': 2.1917247772216797} 08/30/2021 14:15:23 - INFO - __main__ - Step 5940: {'lr': 0.0004991266159498294, 'samples': 1140480, 'steps': 5939, 'loss/train': 2.2043163776397705} 08/30/2021 14:15:23 - INFO - __main__ - Step 5941: {'lr': 0.0004991261726973784, 'samples': 1140672, 'steps': 5940, 'loss/train': 2.1503801345825195} 08/30/2021 14:15:23 - INFO - __main__ - Step 5942: {'lr': 0.0004991257293326752, 'samples': 1140864, 'steps': 5941, 'loss/train': 1.9182548522949219} 08/30/2021 14:15:25 - INFO - __main__ - Step 5943: {'lr': 0.0004991252858557196, 'samples': 1141056, 'steps': 5942, 'loss/train': 2.4979074001312256} 08/30/2021 14:15:25 - INFO - __main__ - Step 5944: {'lr': 0.0004991248422665122, 'samples': 1141248, 'steps': 5943, 'loss/train': 2.358738660812378} 08/30/2021 14:15:26 - INFO - __main__ - Step 5945: {'lr': 0.0004991243985650528, 'samples': 1141440, 'steps': 5944, 'loss/train': 2.2329964637756348} 08/30/2021 14:15:26 - INFO - __main__ - Step 5946: {'lr': 0.0004991239547513419, 'samples': 1141632, 'steps': 5945, 'loss/train': 2.327383041381836} 08/30/2021 14:15:26 - INFO - __main__ - Step 5947: {'lr': 0.0004991235108253795, 'samples': 1141824, 'steps': 5946, 'loss/train': 2.1163156032562256} 08/30/2021 14:15:29 - INFO - __main__ - Step 5948: {'lr': 0.0004991230667871659, 'samples': 1142016, 'steps': 5947, 'loss/train': 2.240360975265503} 08/30/2021 14:15:29 - INFO - __main__ - Step 5949: {'lr': 0.0004991226226367013, 'samples': 1142208, 'steps': 5948, 'loss/train': 2.160229444503784} 08/30/2021 14:15:29 - INFO - __main__ - Step 5950: {'lr': 0.0004991221783739859, 'samples': 1142400, 'steps': 5949, 'loss/train': 0.6622193455696106} 08/30/2021 14:15:30 - INFO - __main__ - Step 5951: {'lr': 0.0004991217339990199, 'samples': 1142592, 'steps': 5950, 'loss/train': 0.7783976197242737} 08/30/2021 14:15:30 - INFO - __main__ - Step 5952: {'lr': 0.0004991212895118035, 'samples': 1142784, 'steps': 5951, 'loss/train': 2.150078058242798} 08/30/2021 14:15:30 - INFO - __main__ - Step 5953: {'lr': 0.0004991208449123369, 'samples': 1142976, 'steps': 5952, 'loss/train': 2.610722303390503} 08/30/2021 14:15:32 - INFO - __main__ - Step 5954: {'lr': 0.0004991204002006203, 'samples': 1143168, 'steps': 5953, 'loss/train': 2.232699394226074} 08/30/2021 14:15:32 - INFO - __main__ - Step 5955: {'lr': 0.0004991199553766538, 'samples': 1143360, 'steps': 5954, 'loss/train': 2.651733160018921} 08/30/2021 14:15:33 - INFO - __main__ - Step 5956: {'lr': 0.0004991195104404378, 'samples': 1143552, 'steps': 5955, 'loss/train': 1.5986006259918213} 08/30/2021 14:15:33 - INFO - __main__ - Step 5957: {'lr': 0.0004991190653919723, 'samples': 1143744, 'steps': 5956, 'loss/train': 2.460905075073242} 08/30/2021 14:15:33 - INFO - __main__ - Step 5958: {'lr': 0.0004991186202312576, 'samples': 1143936, 'steps': 5957, 'loss/train': 2.2222230434417725} 08/30/2021 14:15:35 - INFO - __main__ - Step 5959: {'lr': 0.0004991181749582941, 'samples': 1144128, 'steps': 5958, 'loss/train': 1.6441094875335693} 08/30/2021 14:15:36 - INFO - __main__ - Step 5960: {'lr': 0.0004991177295730815, 'samples': 1144320, 'steps': 5959, 'loss/train': 1.7736626863479614} 08/30/2021 14:15:36 - INFO - __main__ - Step 5961: {'lr': 0.0004991172840756204, 'samples': 1144512, 'steps': 5960, 'loss/train': 0.3163501024246216} 08/30/2021 14:15:36 - INFO - __main__ - Step 5962: {'lr': 0.000499116838465911, 'samples': 1144704, 'steps': 5961, 'loss/train': 2.9587886333465576} 08/30/2021 14:15:37 - INFO - __main__ - Step 5963: {'lr': 0.0004991163927439533, 'samples': 1144896, 'steps': 5962, 'loss/train': 1.9898011684417725} 08/30/2021 14:15:38 - INFO - __main__ - Step 5964: {'lr': 0.0004991159469097476, 'samples': 1145088, 'steps': 5963, 'loss/train': 2.3663594722747803} 08/30/2021 14:15:39 - INFO - __main__ - Step 5965: {'lr': 0.0004991155009632941, 'samples': 1145280, 'steps': 5964, 'loss/train': 2.1029508113861084} 08/30/2021 14:15:39 - INFO - __main__ - Step 5966: {'lr': 0.0004991150549045931, 'samples': 1145472, 'steps': 5965, 'loss/train': 2.3237690925598145} 08/30/2021 14:15:39 - INFO - __main__ - Step 5967: {'lr': 0.0004991146087336446, 'samples': 1145664, 'steps': 5966, 'loss/train': 2.3028342723846436} 08/30/2021 14:15:40 - INFO - __main__ - Step 5968: {'lr': 0.0004991141624504489, 'samples': 1145856, 'steps': 5967, 'loss/train': 2.658325672149658} 08/30/2021 14:15:41 - INFO - __main__ - Step 5969: {'lr': 0.0004991137160550062, 'samples': 1146048, 'steps': 5968, 'loss/train': 2.123077392578125} 08/30/2021 14:15:42 - INFO - __main__ - Step 5970: {'lr': 0.0004991132695473167, 'samples': 1146240, 'steps': 5969, 'loss/train': 2.34393048286438} 08/30/2021 14:15:42 - INFO - __main__ - Step 5971: {'lr': 0.0004991128229273807, 'samples': 1146432, 'steps': 5970, 'loss/train': 2.46962833404541} 08/30/2021 14:15:42 - INFO - __main__ - Step 5972: {'lr': 0.0004991123761951982, 'samples': 1146624, 'steps': 5971, 'loss/train': 2.4148480892181396} 08/30/2021 14:15:43 - INFO - __main__ - Step 5973: {'lr': 0.0004991119293507695, 'samples': 1146816, 'steps': 5972, 'loss/train': 2.748654365539551} 08/30/2021 14:15:44 - INFO - __main__ - Step 5974: {'lr': 0.0004991114823940948, 'samples': 1147008, 'steps': 5973, 'loss/train': 1.6396844387054443} 08/30/2021 14:15:45 - INFO - __main__ - Step 5975: {'lr': 0.0004991110353251744, 'samples': 1147200, 'steps': 5974, 'loss/train': 1.744950294494629} 08/30/2021 14:15:45 - INFO - __main__ - Step 5976: {'lr': 0.0004991105881440084, 'samples': 1147392, 'steps': 5975, 'loss/train': 2.4893743991851807} 08/30/2021 14:15:45 - INFO - __main__ - Step 5977: {'lr': 0.000499110140850597, 'samples': 1147584, 'steps': 5976, 'loss/train': 1.8989903926849365} 08/30/2021 14:15:46 - INFO - __main__ - Step 5978: {'lr': 0.0004991096934449404, 'samples': 1147776, 'steps': 5977, 'loss/train': 1.3881796598434448} 08/30/2021 14:15:46 - INFO - __main__ - Step 5979: {'lr': 0.0004991092459270388, 'samples': 1147968, 'steps': 5978, 'loss/train': 2.414862871170044} 08/30/2021 14:15:48 - INFO - __main__ - Step 5980: {'lr': 0.0004991087982968924, 'samples': 1148160, 'steps': 5979, 'loss/train': 2.1698641777038574} 08/30/2021 14:15:48 - INFO - __main__ - Step 5981: {'lr': 0.0004991083505545014, 'samples': 1148352, 'steps': 5980, 'loss/train': 2.538878917694092} 08/30/2021 14:15:48 - INFO - __main__ - Step 5982: {'lr': 0.0004991079026998662, 'samples': 1148544, 'steps': 5981, 'loss/train': 2.015629768371582} 08/30/2021 14:15:49 - INFO - __main__ - Step 5983: {'lr': 0.0004991074547329867, 'samples': 1148736, 'steps': 5982, 'loss/train': 2.450441360473633} 08/30/2021 14:15:49 - INFO - __main__ - Step 5984: {'lr': 0.0004991070066538632, 'samples': 1148928, 'steps': 5983, 'loss/train': 2.5156095027923584} 08/30/2021 14:15:51 - INFO - __main__ - Step 5985: {'lr': 0.0004991065584624959, 'samples': 1149120, 'steps': 5984, 'loss/train': 2.0208370685577393} 08/30/2021 14:15:52 - INFO - __main__ - Step 5986: {'lr': 0.0004991061101588851, 'samples': 1149312, 'steps': 5985, 'loss/train': 2.035176992416382} 08/30/2021 14:15:52 - INFO - __main__ - Step 5987: {'lr': 0.0004991056617430308, 'samples': 1149504, 'steps': 5986, 'loss/train': 2.074810266494751} 08/30/2021 14:15:53 - INFO - __main__ - Step 5988: {'lr': 0.0004991052132149336, 'samples': 1149696, 'steps': 5987, 'loss/train': 1.5656373500823975} 08/30/2021 14:15:53 - INFO - __main__ - Step 5989: {'lr': 0.0004991047645745932, 'samples': 1149888, 'steps': 5988, 'loss/train': 2.0693013668060303} 08/30/2021 14:15:54 - INFO - __main__ - Step 5990: {'lr': 0.0004991043158220101, 'samples': 1150080, 'steps': 5989, 'loss/train': 2.2472169399261475} 08/30/2021 14:15:55 - INFO - __main__ - Step 5991: {'lr': 0.0004991038669571844, 'samples': 1150272, 'steps': 5990, 'loss/train': 2.137972354888916} 08/30/2021 14:15:55 - INFO - __main__ - Step 5992: {'lr': 0.0004991034179801165, 'samples': 1150464, 'steps': 5991, 'loss/train': 1.8876259326934814} 08/30/2021 14:15:55 - INFO - __main__ - Step 5993: {'lr': 0.0004991029688908063, 'samples': 1150656, 'steps': 5992, 'loss/train': 2.2228870391845703} 08/30/2021 14:15:56 - INFO - __main__ - Step 5994: {'lr': 0.0004991025196892542, 'samples': 1150848, 'steps': 5993, 'loss/train': 2.3093504905700684} 08/30/2021 14:15:57 - INFO - __main__ - Step 5995: {'lr': 0.0004991020703754603, 'samples': 1151040, 'steps': 5994, 'loss/train': 1.75906240940094} 08/30/2021 14:15:58 - INFO - __main__ - Step 5996: {'lr': 0.0004991016209494249, 'samples': 1151232, 'steps': 5995, 'loss/train': 2.2239811420440674} 08/30/2021 14:15:58 - INFO - __main__ - Step 5997: {'lr': 0.000499101171411148, 'samples': 1151424, 'steps': 5996, 'loss/train': 1.656895637512207} 08/30/2021 14:15:58 - INFO - __main__ - Step 5998: {'lr': 0.0004991007217606303, 'samples': 1151616, 'steps': 5997, 'loss/train': 2.5214390754699707} 08/30/2021 14:15:59 - INFO - __main__ - Step 5999: {'lr': 0.0004991002719978713, 'samples': 1151808, 'steps': 5998, 'loss/train': 2.1021344661712646} 08/30/2021 14:16:00 - INFO - __main__ - Step 6000: {'lr': 0.0004990998221228718, 'samples': 1152000, 'steps': 5999, 'loss/train': 2.4656269550323486} 08/30/2021 14:16:01 - INFO - __main__ - Step 6001: {'lr': 0.0004990993721356316, 'samples': 1152192, 'steps': 6000, 'loss/train': 2.3020265102386475} 08/30/2021 14:16:01 - INFO - __main__ - Step 6002: {'lr': 0.0004990989220361511, 'samples': 1152384, 'steps': 6001, 'loss/train': 1.5774675607681274} 08/30/2021 14:16:02 - INFO - __main__ - Step 6003: {'lr': 0.0004990984718244306, 'samples': 1152576, 'steps': 6002, 'loss/train': 2.2705578804016113} 08/30/2021 14:16:02 - INFO - __main__ - Step 6004: {'lr': 0.00049909802150047, 'samples': 1152768, 'steps': 6003, 'loss/train': 1.8598873615264893} 08/30/2021 14:16:04 - INFO - __main__ - Step 6005: {'lr': 0.0004990975710642699, 'samples': 1152960, 'steps': 6004, 'loss/train': 1.7920972108840942} 08/30/2021 14:16:04 - INFO - __main__ - Step 6006: {'lr': 0.0004990971205158301, 'samples': 1153152, 'steps': 6005, 'loss/train': 1.9137616157531738} 08/30/2021 14:16:04 - INFO - __main__ - Step 6007: {'lr': 0.000499096669855151, 'samples': 1153344, 'steps': 6006, 'loss/train': 1.4915194511413574} 08/30/2021 14:16:05 - INFO - __main__ - Step 6008: {'lr': 0.0004990962190822328, 'samples': 1153536, 'steps': 6007, 'loss/train': 2.0501208305358887} 08/30/2021 14:16:05 - INFO - __main__ - Step 6009: {'lr': 0.0004990957681970757, 'samples': 1153728, 'steps': 6008, 'loss/train': 2.3642265796661377} 08/30/2021 14:16:07 - INFO - __main__ - Step 6010: {'lr': 0.0004990953171996798, 'samples': 1153920, 'steps': 6009, 'loss/train': 2.1400179862976074} 08/30/2021 14:16:07 - INFO - __main__ - Step 6011: {'lr': 0.0004990948660900455, 'samples': 1154112, 'steps': 6010, 'loss/train': 1.727049708366394} 08/30/2021 14:16:07 - INFO - __main__ - Step 6012: {'lr': 0.0004990944148681729, 'samples': 1154304, 'steps': 6011, 'loss/train': 1.639033317565918} 08/30/2021 14:16:08 - INFO - __main__ - Step 6013: {'lr': 0.0004990939635340621, 'samples': 1154496, 'steps': 6012, 'loss/train': 2.5471725463867188} 08/30/2021 14:16:08 - INFO - __main__ - Step 6014: {'lr': 0.0004990935120877136, 'samples': 1154688, 'steps': 6013, 'loss/train': 1.7235260009765625} 08/30/2021 14:16:08 - INFO - __main__ - Step 6015: {'lr': 0.0004990930605291272, 'samples': 1154880, 'steps': 6014, 'loss/train': 1.799383282661438} 08/30/2021 14:16:10 - INFO - __main__ - Step 6016: {'lr': 0.0004990926088583034, 'samples': 1155072, 'steps': 6015, 'loss/train': 1.9797793626785278} 08/30/2021 14:16:10 - INFO - __main__ - Step 6017: {'lr': 0.0004990921570752424, 'samples': 1155264, 'steps': 6016, 'loss/train': 1.3015261888504028} 08/30/2021 14:16:11 - INFO - __main__ - Step 6018: {'lr': 0.0004990917051799442, 'samples': 1155456, 'steps': 6017, 'loss/train': 2.3569891452789307} 08/30/2021 14:16:11 - INFO - __main__ - Step 6019: {'lr': 0.0004990912531724092, 'samples': 1155648, 'steps': 6018, 'loss/train': 2.2145638465881348} 08/30/2021 14:16:11 - INFO - __main__ - Step 6020: {'lr': 0.0004990908010526374, 'samples': 1155840, 'steps': 6019, 'loss/train': 2.256147623062134} 08/30/2021 14:16:13 - INFO - __main__ - Step 6021: {'lr': 0.0004990903488206292, 'samples': 1156032, 'steps': 6020, 'loss/train': 2.501497268676758} 08/30/2021 14:16:13 - INFO - __main__ - Step 6022: {'lr': 0.0004990898964763847, 'samples': 1156224, 'steps': 6021, 'loss/train': 0.7916610240936279} 08/30/2021 14:16:14 - INFO - __main__ - Step 6023: {'lr': 0.0004990894440199042, 'samples': 1156416, 'steps': 6022, 'loss/train': 3.1935312747955322} 08/30/2021 14:16:14 - INFO - __main__ - Step 6024: {'lr': 0.0004990889914511878, 'samples': 1156608, 'steps': 6023, 'loss/train': 1.8197205066680908} 08/30/2021 14:16:14 - INFO - __main__ - Step 6025: {'lr': 0.0004990885387702357, 'samples': 1156800, 'steps': 6024, 'loss/train': 1.6443145275115967} 08/30/2021 14:16:16 - INFO - __main__ - Step 6026: {'lr': 0.0004990880859770483, 'samples': 1156992, 'steps': 6025, 'loss/train': 2.036121129989624} 08/30/2021 14:16:16 - INFO - __main__ - Step 6027: {'lr': 0.0004990876330716256, 'samples': 1157184, 'steps': 6026, 'loss/train': 2.313183546066284} 08/30/2021 14:16:17 - INFO - __main__ - Step 6028: {'lr': 0.0004990871800539677, 'samples': 1157376, 'steps': 6027, 'loss/train': 2.0128965377807617} 08/30/2021 14:16:17 - INFO - __main__ - Step 6029: {'lr': 0.0004990867269240751, 'samples': 1157568, 'steps': 6028, 'loss/train': 2.1478962898254395} 08/30/2021 14:16:17 - INFO - __main__ - Step 6030: {'lr': 0.0004990862736819478, 'samples': 1157760, 'steps': 6029, 'loss/train': 1.863461971282959} 08/30/2021 14:16:19 - INFO - __main__ - Step 6031: {'lr': 0.000499085820327586, 'samples': 1157952, 'steps': 6030, 'loss/train': 2.210873603820801} 08/30/2021 14:16:19 - INFO - __main__ - Step 6032: {'lr': 0.0004990853668609902, 'samples': 1158144, 'steps': 6031, 'loss/train': 2.9212305545806885} 08/30/2021 14:16:20 - INFO - __main__ - Step 6033: {'lr': 0.0004990849132821602, 'samples': 1158336, 'steps': 6032, 'loss/train': 2.9135491847991943} 08/30/2021 14:16:20 - INFO - __main__ - Step 6034: {'lr': 0.0004990844595910965, 'samples': 1158528, 'steps': 6033, 'loss/train': 1.8108850717544556} 08/30/2021 14:16:20 - INFO - __main__ - Step 6035: {'lr': 0.0004990840057877991, 'samples': 1158720, 'steps': 6034, 'loss/train': 1.9483637809753418} 08/30/2021 14:16:23 - INFO - __main__ - Step 6036: {'lr': 0.0004990835518722683, 'samples': 1158912, 'steps': 6035, 'loss/train': 0.21011456847190857} 08/30/2021 14:16:23 - INFO - __main__ - Step 6037: {'lr': 0.0004990830978445043, 'samples': 1159104, 'steps': 6036, 'loss/train': 1.8370007276535034} 08/30/2021 14:16:23 - INFO - __main__ - Step 6038: {'lr': 0.0004990826437045073, 'samples': 1159296, 'steps': 6037, 'loss/train': 1.7020741701126099} 08/30/2021 14:16:24 - INFO - __main__ - Step 6039: {'lr': 0.0004990821894522775, 'samples': 1159488, 'steps': 6038, 'loss/train': 2.23870849609375} 08/30/2021 14:16:24 - INFO - __main__ - Step 6040: {'lr': 0.0004990817350878152, 'samples': 1159680, 'steps': 6039, 'loss/train': 2.1977384090423584} 08/30/2021 14:16:26 - INFO - __main__ - Step 6041: {'lr': 0.0004990812806111205, 'samples': 1159872, 'steps': 6040, 'loss/train': 1.9331872463226318} 08/30/2021 14:16:26 - INFO - __main__ - Step 6042: {'lr': 0.0004990808260221934, 'samples': 1160064, 'steps': 6041, 'loss/train': 1.9153445959091187} 08/30/2021 14:16:26 - INFO - __main__ - Step 6043: {'lr': 0.0004990803713210345, 'samples': 1160256, 'steps': 6042, 'loss/train': 1.7708107233047485} 08/30/2021 14:16:27 - INFO - __main__ - Step 6044: {'lr': 0.0004990799165076438, 'samples': 1160448, 'steps': 6043, 'loss/train': 1.813028335571289} 08/30/2021 14:16:27 - INFO - __main__ - Step 6045: {'lr': 0.0004990794615820216, 'samples': 1160640, 'steps': 6044, 'loss/train': 1.7955721616744995} 08/30/2021 14:16:29 - INFO - __main__ - Step 6046: {'lr': 0.0004990790065441679, 'samples': 1160832, 'steps': 6045, 'loss/train': 1.5986727476119995} 08/30/2021 14:16:29 - INFO - __main__ - Step 6047: {'lr': 0.0004990785513940832, 'samples': 1161024, 'steps': 6046, 'loss/train': 1.353219985961914} 08/30/2021 14:16:29 - INFO - __main__ - Step 6048: {'lr': 0.0004990780961317674, 'samples': 1161216, 'steps': 6047, 'loss/train': 1.878985047340393} 08/30/2021 14:16:30 - INFO - __main__ - Step 6049: {'lr': 0.0004990776407572209, 'samples': 1161408, 'steps': 6048, 'loss/train': 1.7939867973327637} 08/30/2021 14:16:30 - INFO - __main__ - Step 6050: {'lr': 0.000499077185270444, 'samples': 1161600, 'steps': 6049, 'loss/train': 1.955993890762329} 08/30/2021 14:16:32 - INFO - __main__ - Step 6051: {'lr': 0.0004990767296714365, 'samples': 1161792, 'steps': 6050, 'loss/train': 1.6843774318695068} 08/30/2021 14:16:32 - INFO - __main__ - Step 6052: {'lr': 0.000499076273960199, 'samples': 1161984, 'steps': 6051, 'loss/train': 2.232264280319214} 08/30/2021 14:16:32 - INFO - __main__ - Step 6053: {'lr': 0.0004990758181367316, 'samples': 1162176, 'steps': 6052, 'loss/train': 2.2386627197265625} 08/30/2021 14:16:33 - INFO - __main__ - Step 6054: {'lr': 0.0004990753622010345, 'samples': 1162368, 'steps': 6053, 'loss/train': 1.7334731817245483} 08/30/2021 14:16:33 - INFO - __main__ - Step 6055: {'lr': 0.0004990749061531079, 'samples': 1162560, 'steps': 6054, 'loss/train': 1.7887282371520996} 08/30/2021 14:16:34 - INFO - __main__ - Step 6056: {'lr': 0.0004990744499929519, 'samples': 1162752, 'steps': 6055, 'loss/train': 1.920432448387146} 08/30/2021 14:16:35 - INFO - __main__ - Step 6057: {'lr': 0.0004990739937205668, 'samples': 1162944, 'steps': 6056, 'loss/train': 1.9344661235809326} 08/30/2021 14:16:35 - INFO - __main__ - Step 6058: {'lr': 0.0004990735373359529, 'samples': 1163136, 'steps': 6057, 'loss/train': 2.140591859817505} 08/30/2021 14:16:36 - INFO - __main__ - Step 6059: {'lr': 0.0004990730808391102, 'samples': 1163328, 'steps': 6058, 'loss/train': 2.165710687637329} 08/30/2021 14:16:36 - INFO - __main__ - Step 6060: {'lr': 0.0004990726242300391, 'samples': 1163520, 'steps': 6059, 'loss/train': 2.912585496902466} 08/30/2021 14:16:37 - INFO - __main__ - Step 6061: {'lr': 0.0004990721675087397, 'samples': 1163712, 'steps': 6060, 'loss/train': 2.143425464630127} 08/30/2021 14:16:38 - INFO - __main__ - Step 6062: {'lr': 0.0004990717106752122, 'samples': 1163904, 'steps': 6061, 'loss/train': 2.2275428771972656} 08/30/2021 14:16:38 - INFO - __main__ - Step 6063: {'lr': 0.0004990712537294568, 'samples': 1164096, 'steps': 6062, 'loss/train': 2.4941608905792236} 08/30/2021 14:16:39 - INFO - __main__ - Step 6064: {'lr': 0.0004990707966714738, 'samples': 1164288, 'steps': 6063, 'loss/train': 1.885541558265686} 08/30/2021 14:16:39 - INFO - __main__ - Step 6065: {'lr': 0.0004990703395012634, 'samples': 1164480, 'steps': 6064, 'loss/train': 2.437563180923462} 08/30/2021 14:16:39 - INFO - __main__ - Step 6066: {'lr': 0.0004990698822188255, 'samples': 1164672, 'steps': 6065, 'loss/train': 2.015489101409912} 08/30/2021 14:16:41 - INFO - __main__ - Step 6067: {'lr': 0.0004990694248241608, 'samples': 1164864, 'steps': 6066, 'loss/train': 1.2778023481369019} 08/30/2021 14:16:41 - INFO - __main__ - Step 6068: {'lr': 0.0004990689673172691, 'samples': 1165056, 'steps': 6067, 'loss/train': 2.142285108566284} 08/30/2021 14:16:42 - INFO - __main__ - Step 6069: {'lr': 0.000499068509698151, 'samples': 1165248, 'steps': 6068, 'loss/train': 2.010939836502075} 08/30/2021 14:16:42 - INFO - __main__ - Step 6070: {'lr': 0.0004990680519668063, 'samples': 1165440, 'steps': 6069, 'loss/train': 2.111518621444702} 08/30/2021 14:16:42 - INFO - __main__ - Step 6071: {'lr': 0.0004990675941232354, 'samples': 1165632, 'steps': 6070, 'loss/train': 2.1520676612854004} 08/30/2021 14:16:44 - INFO - __main__ - Step 6072: {'lr': 0.0004990671361674384, 'samples': 1165824, 'steps': 6071, 'loss/train': 1.8499726057052612} 08/30/2021 14:16:44 - INFO - __main__ - Step 6073: {'lr': 0.0004990666780994156, 'samples': 1166016, 'steps': 6072, 'loss/train': 2.289273977279663} 08/30/2021 14:16:45 - INFO - __main__ - Step 6074: {'lr': 0.0004990662199191673, 'samples': 1166208, 'steps': 6073, 'loss/train': 2.125744342803955} 08/30/2021 14:16:45 - INFO - __main__ - Step 6075: {'lr': 0.0004990657616266936, 'samples': 1166400, 'steps': 6074, 'loss/train': 2.661235809326172} 08/30/2021 14:16:45 - INFO - __main__ - Step 6076: {'lr': 0.0004990653032219947, 'samples': 1166592, 'steps': 6075, 'loss/train': 0.7951482534408569} 08/30/2021 14:16:47 - INFO - __main__ - Step 6077: {'lr': 0.0004990648447050709, 'samples': 1166784, 'steps': 6076, 'loss/train': 2.175867795944214} 08/30/2021 14:16:47 - INFO - __main__ - Step 6078: {'lr': 0.0004990643860759222, 'samples': 1166976, 'steps': 6077, 'loss/train': 1.8009334802627563} 08/30/2021 14:16:48 - INFO - __main__ - Step 6079: {'lr': 0.0004990639273345489, 'samples': 1167168, 'steps': 6078, 'loss/train': 2.1254401206970215} 08/30/2021 14:16:48 - INFO - __main__ - Step 6080: {'lr': 0.0004990634684809513, 'samples': 1167360, 'steps': 6079, 'loss/train': 1.64859139919281} 08/30/2021 14:16:48 - INFO - __main__ - Step 6081: {'lr': 0.0004990630095151296, 'samples': 1167552, 'steps': 6080, 'loss/train': 1.9777277708053589} 08/30/2021 14:16:50 - INFO - __main__ - Step 6082: {'lr': 0.0004990625504370838, 'samples': 1167744, 'steps': 6081, 'loss/train': 2.201955556869507} 08/30/2021 14:16:50 - INFO - __main__ - Step 6083: {'lr': 0.0004990620912468143, 'samples': 1167936, 'steps': 6082, 'loss/train': 2.1902480125427246} 08/30/2021 14:16:51 - INFO - __main__ - Step 6084: {'lr': 0.0004990616319443214, 'samples': 1168128, 'steps': 6083, 'loss/train': 1.993706464767456} 08/30/2021 14:16:51 - INFO - __main__ - Step 6085: {'lr': 0.0004990611725296052, 'samples': 1168320, 'steps': 6084, 'loss/train': 2.217761993408203} 08/30/2021 14:16:51 - INFO - __main__ - Step 6086: {'lr': 0.0004990607130026657, 'samples': 1168512, 'steps': 6085, 'loss/train': 2.5983235836029053} 08/30/2021 14:16:52 - INFO - __main__ - Step 6087: {'lr': 0.0004990602533635033, 'samples': 1168704, 'steps': 6086, 'loss/train': 2.3596651554107666} 08/30/2021 14:16:54 - INFO - __main__ - Step 6088: {'lr': 0.0004990597936121182, 'samples': 1168896, 'steps': 6087, 'loss/train': 2.0918681621551514} 08/30/2021 14:16:55 - INFO - __main__ - Step 6089: {'lr': 0.0004990593337485108, 'samples': 1169088, 'steps': 6088, 'loss/train': 2.3481647968292236} 08/30/2021 14:16:55 - INFO - __main__ - Step 6090: {'lr': 0.0004990588737726809, 'samples': 1169280, 'steps': 6089, 'loss/train': 2.553339958190918} 08/30/2021 14:16:56 - INFO - __main__ - Step 6091: {'lr': 0.0004990584136846289, 'samples': 1169472, 'steps': 6090, 'loss/train': 2.537722587585449} 08/30/2021 14:16:56 - INFO - __main__ - Step 6092: {'lr': 0.0004990579534843551, 'samples': 1169664, 'steps': 6091, 'loss/train': 0.21205846965312958} 08/30/2021 14:16:56 - INFO - __main__ - Step 6093: {'lr': 0.0004990574931718597, 'samples': 1169856, 'steps': 6092, 'loss/train': 1.1033707857131958} 08/30/2021 14:16:57 - INFO - __main__ - Step 6094: {'lr': 0.0004990570327471427, 'samples': 1170048, 'steps': 6093, 'loss/train': 0.9622670412063599} 08/30/2021 14:16:58 - INFO - __main__ - Step 6095: {'lr': 0.0004990565722102045, 'samples': 1170240, 'steps': 6094, 'loss/train': 0.774612545967102} 08/30/2021 14:16:59 - INFO - __main__ - Step 6096: {'lr': 0.0004990561115610452, 'samples': 1170432, 'steps': 6095, 'loss/train': 2.0248193740844727} 08/30/2021 14:16:59 - INFO - __main__ - Step 6097: {'lr': 0.0004990556507996652, 'samples': 1170624, 'steps': 6096, 'loss/train': 1.7581862211227417} 08/30/2021 14:17:00 - INFO - __main__ - Step 6098: {'lr': 0.0004990551899260644, 'samples': 1170816, 'steps': 6097, 'loss/train': 2.1386702060699463} 08/30/2021 14:17:00 - INFO - __main__ - Step 6099: {'lr': 0.0004990547289402433, 'samples': 1171008, 'steps': 6098, 'loss/train': 2.6330530643463135} 08/30/2021 14:17:02 - INFO - __main__ - Step 6100: {'lr': 0.0004990542678422019, 'samples': 1171200, 'steps': 6099, 'loss/train': 1.5033752918243408} 08/30/2021 14:17:02 - INFO - __main__ - Step 6101: {'lr': 0.0004990538066319406, 'samples': 1171392, 'steps': 6100, 'loss/train': 0.4551768898963928} 08/30/2021 14:17:03 - INFO - __main__ - Step 6102: {'lr': 0.0004990533453094594, 'samples': 1171584, 'steps': 6101, 'loss/train': 2.0008089542388916} 08/30/2021 14:17:03 - INFO - __main__ - Step 6103: {'lr': 0.0004990528838747586, 'samples': 1171776, 'steps': 6102, 'loss/train': 2.0956332683563232} 08/30/2021 14:17:03 - INFO - __main__ - Step 6104: {'lr': 0.0004990524223278384, 'samples': 1171968, 'steps': 6103, 'loss/train': 2.2818100452423096} 08/30/2021 14:17:05 - INFO - __main__ - Step 6105: {'lr': 0.0004990519606686991, 'samples': 1172160, 'steps': 6104, 'loss/train': 2.261725664138794} 08/30/2021 14:17:05 - INFO - __main__ - Step 6106: {'lr': 0.0004990514988973408, 'samples': 1172352, 'steps': 6105, 'loss/train': 1.611903429031372} 08/30/2021 14:17:06 - INFO - __main__ - Step 6107: {'lr': 0.0004990510370137637, 'samples': 1172544, 'steps': 6106, 'loss/train': 1.9110937118530273} 08/30/2021 14:17:06 - INFO - __main__ - Step 6108: {'lr': 0.0004990505750179682, 'samples': 1172736, 'steps': 6107, 'loss/train': 1.362024188041687} 08/30/2021 14:17:06 - INFO - __main__ - Step 6109: {'lr': 0.0004990501129099542, 'samples': 1172928, 'steps': 6108, 'loss/train': 1.0821868181228638} 08/30/2021 14:17:08 - INFO - __main__ - Step 6110: {'lr': 0.000499049650689722, 'samples': 1173120, 'steps': 6109, 'loss/train': 1.912007212638855} 08/30/2021 14:17:08 - INFO - __main__ - Step 6111: {'lr': 0.000499049188357272, 'samples': 1173312, 'steps': 6110, 'loss/train': 2.309844970703125} 08/30/2021 14:17:09 - INFO - __main__ - Step 6112: {'lr': 0.0004990487259126043, 'samples': 1173504, 'steps': 6111, 'loss/train': 2.6369924545288086} 08/30/2021 14:17:09 - INFO - __main__ - Step 6113: {'lr': 0.0004990482633557189, 'samples': 1173696, 'steps': 6112, 'loss/train': 1.12046480178833} 08/30/2021 14:17:10 - INFO - __main__ - Step 6114: {'lr': 0.0004990478006866165, 'samples': 1173888, 'steps': 6113, 'loss/train': 2.1313536167144775} 08/30/2021 14:17:10 - INFO - __main__ - Step 6115: {'lr': 0.0004990473379052968, 'samples': 1174080, 'steps': 6114, 'loss/train': 1.6079707145690918} 08/30/2021 14:17:11 - INFO - __main__ - Step 6116: {'lr': 0.0004990468750117602, 'samples': 1174272, 'steps': 6115, 'loss/train': 1.6931512355804443} 08/30/2021 14:17:12 - INFO - __main__ - Step 6117: {'lr': 0.000499046412006007, 'samples': 1174464, 'steps': 6116, 'loss/train': 1.952774167060852} 08/30/2021 14:17:12 - INFO - __main__ - Step 6118: {'lr': 0.0004990459488880372, 'samples': 1174656, 'steps': 6117, 'loss/train': 1.8816965818405151} 08/30/2021 14:17:12 - INFO - __main__ - Step 6119: {'lr': 0.0004990454856578513, 'samples': 1174848, 'steps': 6118, 'loss/train': 2.5326578617095947} 08/30/2021 14:17:13 - INFO - __main__ - Step 6120: {'lr': 0.0004990450223154492, 'samples': 1175040, 'steps': 6119, 'loss/train': 1.5734384059906006} 08/30/2021 14:17:14 - INFO - __main__ - Step 6121: {'lr': 0.0004990445588608313, 'samples': 1175232, 'steps': 6120, 'loss/train': 1.8786181211471558} 08/30/2021 14:17:15 - INFO - __main__ - Step 6122: {'lr': 0.0004990440952939979, 'samples': 1175424, 'steps': 6121, 'loss/train': 1.7350105047225952} 08/30/2021 14:17:15 - INFO - __main__ - Step 6123: {'lr': 0.0004990436316149489, 'samples': 1175616, 'steps': 6122, 'loss/train': 2.220349073410034} 08/30/2021 14:17:15 - INFO - __main__ - Step 6124: {'lr': 0.0004990431678236849, 'samples': 1175808, 'steps': 6123, 'loss/train': 2.1604645252227783} 08/30/2021 14:17:16 - INFO - __main__ - Step 6125: {'lr': 0.0004990427039202057, 'samples': 1176000, 'steps': 6124, 'loss/train': 2.588308811187744} 08/30/2021 14:17:17 - INFO - __main__ - Step 6126: {'lr': 0.0004990422399045117, 'samples': 1176192, 'steps': 6125, 'loss/train': 1.2041592597961426} 08/30/2021 14:17:18 - INFO - __main__ - Step 6127: {'lr': 0.0004990417757766031, 'samples': 1176384, 'steps': 6126, 'loss/train': 1.7451285123825073} 08/30/2021 14:17:18 - INFO - __main__ - Step 6128: {'lr': 0.0004990413115364803, 'samples': 1176576, 'steps': 6127, 'loss/train': 2.5466935634613037} 08/30/2021 14:17:18 - INFO - __main__ - Step 6129: {'lr': 0.0004990408471841431, 'samples': 1176768, 'steps': 6128, 'loss/train': 2.152479887008667} 08/30/2021 14:17:19 - INFO - __main__ - Step 6130: {'lr': 0.0004990403827195921, 'samples': 1176960, 'steps': 6129, 'loss/train': 2.1017420291900635} 08/30/2021 14:17:20 - INFO - __main__ - Step 6131: {'lr': 0.0004990399181428273, 'samples': 1177152, 'steps': 6130, 'loss/train': 1.4404301643371582} 08/30/2021 14:17:21 - INFO - __main__ - Step 6132: {'lr': 0.000499039453453849, 'samples': 1177344, 'steps': 6131, 'loss/train': 2.3782787322998047} 08/30/2021 14:17:21 - INFO - __main__ - Step 6133: {'lr': 0.0004990389886526573, 'samples': 1177536, 'steps': 6132, 'loss/train': 2.0950968265533447} 08/30/2021 14:17:21 - INFO - __main__ - Step 6134: {'lr': 0.0004990385237392524, 'samples': 1177728, 'steps': 6133, 'loss/train': 2.377577543258667} 08/30/2021 14:17:22 - INFO - __main__ - Step 6135: {'lr': 0.0004990380587136347, 'samples': 1177920, 'steps': 6134, 'loss/train': 2.1193230152130127} 08/30/2021 14:17:24 - INFO - __main__ - Step 6136: {'lr': 0.0004990375935758042, 'samples': 1178112, 'steps': 6135, 'loss/train': 1.4899842739105225} 08/30/2021 14:17:24 - INFO - __main__ - Step 6137: {'lr': 0.0004990371283257613, 'samples': 1178304, 'steps': 6136, 'loss/train': 6.589000701904297} 08/30/2021 14:17:24 - INFO - __main__ - Step 6138: {'lr': 0.0004990366629635062, 'samples': 1178496, 'steps': 6137, 'loss/train': 1.8414204120635986} 08/30/2021 14:17:25 - INFO - __main__ - Step 6139: {'lr': 0.0004990361974890388, 'samples': 1178688, 'steps': 6138, 'loss/train': 1.9632432460784912} 08/30/2021 14:17:25 - INFO - __main__ - Step 6140: {'lr': 0.0004990357319023597, 'samples': 1178880, 'steps': 6139, 'loss/train': 1.5291732549667358} 08/30/2021 14:17:26 - INFO - __main__ - Step 6141: {'lr': 0.0004990352662034689, 'samples': 1179072, 'steps': 6140, 'loss/train': 0.552104651927948} 08/30/2021 14:17:28 - INFO - __main__ - Step 6142: {'lr': 0.0004990348003923665, 'samples': 1179264, 'steps': 6141, 'loss/train': 2.363502025604248} 08/30/2021 14:17:28 - INFO - __main__ - Step 6143: {'lr': 0.000499034334469053, 'samples': 1179456, 'steps': 6142, 'loss/train': 2.386108875274658} 08/30/2021 14:17:29 - INFO - __main__ - Step 6144: {'lr': 0.0004990338684335285, 'samples': 1179648, 'steps': 6143, 'loss/train': 2.582843065261841} 08/30/2021 14:17:29 - INFO - __main__ - Step 6145: {'lr': 0.0004990334022857932, 'samples': 1179840, 'steps': 6144, 'loss/train': 0.34102797508239746} 08/30/2021 14:17:29 - INFO - __main__ - Step 6146: {'lr': 0.0004990329360258472, 'samples': 1180032, 'steps': 6145, 'loss/train': 1.8113882541656494} 08/30/2021 14:17:30 - INFO - __main__ - Step 6147: {'lr': 0.0004990324696536908, 'samples': 1180224, 'steps': 6146, 'loss/train': 2.0144941806793213} 08/30/2021 14:17:32 - INFO - __main__ - Step 6148: {'lr': 0.0004990320031693242, 'samples': 1180416, 'steps': 6147, 'loss/train': 1.286054015159607} 08/30/2021 14:17:32 - INFO - __main__ - Step 6149: {'lr': 0.0004990315365727476, 'samples': 1180608, 'steps': 6148, 'loss/train': 1.892910122871399} 08/30/2021 14:17:33 - INFO - __main__ - Step 6150: {'lr': 0.0004990310698639614, 'samples': 1180800, 'steps': 6149, 'loss/train': 1.7210521697998047} 08/30/2021 14:17:33 - INFO - __main__ - Step 6151: {'lr': 0.0004990306030429655, 'samples': 1180992, 'steps': 6150, 'loss/train': 2.0882198810577393} 08/30/2021 14:17:33 - INFO - __main__ - Step 6152: {'lr': 0.0004990301361097603, 'samples': 1181184, 'steps': 6151, 'loss/train': 1.6206170320510864} 08/30/2021 14:17:35 - INFO - __main__ - Step 6153: {'lr': 0.000499029669064346, 'samples': 1181376, 'steps': 6152, 'loss/train': 0.4024379849433899} 08/30/2021 14:17:35 - INFO - __main__ - Step 6154: {'lr': 0.0004990292019067227, 'samples': 1181568, 'steps': 6153, 'loss/train': 2.0156362056732178} 08/30/2021 14:17:36 - INFO - __main__ - Step 6155: {'lr': 0.0004990287346368908, 'samples': 1181760, 'steps': 6154, 'loss/train': 2.4578709602355957} 08/30/2021 14:17:36 - INFO - __main__ - Step 6156: {'lr': 0.0004990282672548503, 'samples': 1181952, 'steps': 6155, 'loss/train': 1.9091486930847168} 08/30/2021 14:17:36 - INFO - __main__ - Step 6157: {'lr': 0.0004990277997606016, 'samples': 1182144, 'steps': 6156, 'loss/train': 1.8755120038986206} 08/30/2021 14:17:38 - INFO - __main__ - Step 6158: {'lr': 0.0004990273321541447, 'samples': 1182336, 'steps': 6157, 'loss/train': 2.099588632583618} 08/30/2021 14:17:38 - INFO - __main__ - Step 6159: {'lr': 0.0004990268644354799, 'samples': 1182528, 'steps': 6158, 'loss/train': 2.256617546081543} 08/30/2021 14:17:39 - INFO - __main__ - Step 6160: {'lr': 0.0004990263966046075, 'samples': 1182720, 'steps': 6159, 'loss/train': 1.7035191059112549} 08/30/2021 14:17:39 - INFO - __main__ - Step 6161: {'lr': 0.0004990259286615276, 'samples': 1182912, 'steps': 6160, 'loss/train': 1.9849936962127686} 08/30/2021 14:17:39 - INFO - __main__ - Step 6162: {'lr': 0.0004990254606062406, 'samples': 1183104, 'steps': 6161, 'loss/train': 2.512209892272949} 08/30/2021 14:17:41 - INFO - __main__ - Step 6163: {'lr': 0.0004990249924387465, 'samples': 1183296, 'steps': 6162, 'loss/train': 2.401766300201416} 08/30/2021 14:17:42 - INFO - __main__ - Step 6164: {'lr': 0.0004990245241590455, 'samples': 1183488, 'steps': 6163, 'loss/train': 1.8561409711837769} 08/30/2021 14:17:42 - INFO - __main__ - Step 6165: {'lr': 0.0004990240557671379, 'samples': 1183680, 'steps': 6164, 'loss/train': 2.1383039951324463} 08/30/2021 14:17:42 - INFO - __main__ - Step 6166: {'lr': 0.000499023587263024, 'samples': 1183872, 'steps': 6165, 'loss/train': 1.8972554206848145} 08/30/2021 14:17:43 - INFO - __main__ - Step 6167: {'lr': 0.0004990231186467039, 'samples': 1184064, 'steps': 6166, 'loss/train': 1.9691927433013916} 08/30/2021 14:17:43 - INFO - __main__ - Step 6168: {'lr': 0.0004990226499181778, 'samples': 1184256, 'steps': 6167, 'loss/train': 0.3678905963897705} 08/30/2021 14:17:45 - INFO - __main__ - Step 6169: {'lr': 0.0004990221810774459, 'samples': 1184448, 'steps': 6168, 'loss/train': 2.058572769165039} 08/30/2021 14:17:45 - INFO - __main__ - Step 6170: {'lr': 0.0004990217121245084, 'samples': 1184640, 'steps': 6169, 'loss/train': 2.1512398719787598} 08/30/2021 14:17:45 - INFO - __main__ - Step 6171: {'lr': 0.0004990212430593657, 'samples': 1184832, 'steps': 6170, 'loss/train': 1.8302189111709595} 08/30/2021 14:17:46 - INFO - __main__ - Step 6172: {'lr': 0.0004990207738820178, 'samples': 1185024, 'steps': 6171, 'loss/train': 1.883941650390625} 08/30/2021 14:17:46 - INFO - __main__ - Step 6173: {'lr': 0.000499020304592465, 'samples': 1185216, 'steps': 6172, 'loss/train': 2.1236584186553955} 08/30/2021 14:17:48 - INFO - __main__ - Step 6174: {'lr': 0.0004990198351907075, 'samples': 1185408, 'steps': 6173, 'loss/train': 2.120842456817627} 08/30/2021 14:17:48 - INFO - __main__ - Step 6175: {'lr': 0.0004990193656767455, 'samples': 1185600, 'steps': 6174, 'loss/train': 1.4066747426986694} 08/30/2021 14:17:49 - INFO - __main__ - Step 6176: {'lr': 0.0004990188960505792, 'samples': 1185792, 'steps': 6175, 'loss/train': 2.0758004188537598} 08/30/2021 14:17:49 - INFO - __main__ - Step 6177: {'lr': 0.0004990184263122088, 'samples': 1185984, 'steps': 6176, 'loss/train': 1.8765077590942383} 08/30/2021 14:17:50 - INFO - __main__ - Step 6178: {'lr': 0.0004990179564616346, 'samples': 1186176, 'steps': 6177, 'loss/train': 0.41296014189720154} 08/30/2021 14:17:51 - INFO - __main__ - Step 6179: {'lr': 0.0004990174864988566, 'samples': 1186368, 'steps': 6178, 'loss/train': 2.0812172889709473} 08/30/2021 14:17:52 - INFO - __main__ - Step 6180: {'lr': 0.0004990170164238754, 'samples': 1186560, 'steps': 6179, 'loss/train': 2.5438144207000732} 08/30/2021 14:17:52 - INFO - __main__ - Step 6181: {'lr': 0.0004990165462366909, 'samples': 1186752, 'steps': 6180, 'loss/train': 0.5283352136611938} 08/30/2021 14:17:53 - INFO - __main__ - Step 6182: {'lr': 0.0004990160759373033, 'samples': 1186944, 'steps': 6181, 'loss/train': 1.8242038488388062} 08/30/2021 14:17:53 - INFO - __main__ - Step 6183: {'lr': 0.0004990156055257129, 'samples': 1187136, 'steps': 6182, 'loss/train': 1.3752305507659912} 08/30/2021 14:17:55 - INFO - __main__ - Step 6184: {'lr': 0.00049901513500192, 'samples': 1187328, 'steps': 6183, 'loss/train': 2.3722639083862305} 08/30/2021 14:17:55 - INFO - __main__ - Step 6185: {'lr': 0.0004990146643659247, 'samples': 1187520, 'steps': 6184, 'loss/train': 2.003141164779663} 08/30/2021 14:17:55 - INFO - __main__ - Step 6186: {'lr': 0.0004990141936177272, 'samples': 1187712, 'steps': 6185, 'loss/train': 1.7587296962738037} 08/30/2021 14:17:56 - INFO - __main__ - Step 6187: {'lr': 0.0004990137227573278, 'samples': 1187904, 'steps': 6186, 'loss/train': 1.947689414024353} 08/30/2021 14:17:56 - INFO - __main__ - Step 6188: {'lr': 0.0004990132517847266, 'samples': 1188096, 'steps': 6187, 'loss/train': 2.373015880584717} 08/30/2021 14:17:56 - INFO - __main__ - Step 6189: {'lr': 0.0004990127806999239, 'samples': 1188288, 'steps': 6188, 'loss/train': 1.674223780632019} 08/30/2021 14:17:58 - INFO - __main__ - Step 6190: {'lr': 0.0004990123095029199, 'samples': 1188480, 'steps': 6189, 'loss/train': 2.42575740814209} 08/30/2021 14:17:59 - INFO - __main__ - Step 6191: {'lr': 0.0004990118381937148, 'samples': 1188672, 'steps': 6190, 'loss/train': 1.8693678379058838} 08/30/2021 14:17:59 - INFO - __main__ - Step 6192: {'lr': 0.0004990113667723088, 'samples': 1188864, 'steps': 6191, 'loss/train': 3.1117334365844727} 08/30/2021 14:17:59 - INFO - __main__ - Step 6193: {'lr': 0.000499010895238702, 'samples': 1189056, 'steps': 6192, 'loss/train': 1.974090814590454} 08/30/2021 14:18:00 - INFO - __main__ - Step 6194: {'lr': 0.0004990104235928948, 'samples': 1189248, 'steps': 6193, 'loss/train': 2.349508762359619} 08/30/2021 14:18:01 - INFO - __main__ - Step 6195: {'lr': 0.0004990099518348874, 'samples': 1189440, 'steps': 6194, 'loss/train': 0.2854999899864197} 08/30/2021 14:18:02 - INFO - __main__ - Step 6196: {'lr': 0.00049900947996468, 'samples': 1189632, 'steps': 6195, 'loss/train': 2.0679450035095215} 08/30/2021 14:18:02 - INFO - __main__ - Step 6197: {'lr': 0.0004990090079822726, 'samples': 1189824, 'steps': 6196, 'loss/train': 2.156909704208374} 08/30/2021 14:18:02 - INFO - __main__ - Step 6198: {'lr': 0.0004990085358876658, 'samples': 1190016, 'steps': 6197, 'loss/train': 1.727145791053772} 08/30/2021 14:18:03 - INFO - __main__ - Step 6199: {'lr': 0.0004990080636808595, 'samples': 1190208, 'steps': 6198, 'loss/train': 1.08854341506958} 08/30/2021 14:18:03 - INFO - __main__ - Step 6200: {'lr': 0.000499007591361854, 'samples': 1190400, 'steps': 6199, 'loss/train': 1.5549006462097168} 08/30/2021 14:18:05 - INFO - __main__ - Step 6201: {'lr': 0.0004990071189306495, 'samples': 1190592, 'steps': 6200, 'loss/train': 2.4462223052978516} 08/30/2021 14:18:06 - INFO - __main__ - Step 6202: {'lr': 0.0004990066463872462, 'samples': 1190784, 'steps': 6201, 'loss/train': 2.5784995555877686} 08/30/2021 14:18:06 - INFO - __main__ - Step 6203: {'lr': 0.0004990061737316445, 'samples': 1190976, 'steps': 6202, 'loss/train': 2.134146213531494} 08/30/2021 14:18:07 - INFO - __main__ - Step 6204: {'lr': 0.0004990057009638443, 'samples': 1191168, 'steps': 6203, 'loss/train': 2.2616889476776123} 08/30/2021 14:18:07 - INFO - __main__ - Step 6205: {'lr': 0.000499005228083846, 'samples': 1191360, 'steps': 6204, 'loss/train': 0.5354210138320923} 08/30/2021 14:18:08 - INFO - __main__ - Step 6206: {'lr': 0.0004990047550916498, 'samples': 1191552, 'steps': 6205, 'loss/train': 2.0784218311309814} 08/30/2021 14:18:09 - INFO - __main__ - Step 6207: {'lr': 0.000499004281987256, 'samples': 1191744, 'steps': 6206, 'loss/train': 2.5894880294799805} 08/30/2021 14:18:09 - INFO - __main__ - Step 6208: {'lr': 0.0004990038087706646, 'samples': 1191936, 'steps': 6207, 'loss/train': 2.2595319747924805} 08/30/2021 14:18:10 - INFO - __main__ - Step 6209: {'lr': 0.000499003335441876, 'samples': 1192128, 'steps': 6208, 'loss/train': 2.4695115089416504} 08/30/2021 14:18:10 - INFO - __main__ - Step 6210: {'lr': 0.0004990028620008903, 'samples': 1192320, 'steps': 6209, 'loss/train': 1.9695442914962769} 08/30/2021 14:18:12 - INFO - __main__ - Step 6211: {'lr': 0.0004990023884477077, 'samples': 1192512, 'steps': 6210, 'loss/train': 1.8410488367080688} 08/30/2021 14:18:12 - INFO - __main__ - Step 6212: {'lr': 0.0004990019147823286, 'samples': 1192704, 'steps': 6211, 'loss/train': 2.443037748336792} 08/30/2021 14:18:12 - INFO - __main__ - Step 6213: {'lr': 0.000499001441004753, 'samples': 1192896, 'steps': 6212, 'loss/train': 1.5597666501998901} 08/30/2021 14:18:13 - INFO - __main__ - Step 6214: {'lr': 0.0004990009671149811, 'samples': 1193088, 'steps': 6213, 'loss/train': 2.178555488586426} 08/30/2021 14:18:13 - INFO - __main__ - Step 6215: {'lr': 0.0004990004931130133, 'samples': 1193280, 'steps': 6214, 'loss/train': 1.4102318286895752} 08/30/2021 14:18:14 - INFO - __main__ - Step 6216: {'lr': 0.0004990000189988497, 'samples': 1193472, 'steps': 6215, 'loss/train': 2.2533822059631348} 08/30/2021 14:18:15 - INFO - __main__ - Step 6217: {'lr': 0.0004989995447724907, 'samples': 1193664, 'steps': 6216, 'loss/train': 2.015746831893921} 08/30/2021 14:18:15 - INFO - __main__ - Step 6218: {'lr': 0.0004989990704339361, 'samples': 1193856, 'steps': 6217, 'loss/train': 2.105013608932495} 08/30/2021 14:18:16 - INFO - __main__ - Step 6219: {'lr': 0.0004989985959831865, 'samples': 1194048, 'steps': 6218, 'loss/train': 2.5074172019958496} 08/30/2021 14:18:16 - INFO - __main__ - Step 6220: {'lr': 0.0004989981214202419, 'samples': 1194240, 'steps': 6219, 'loss/train': 2.59159255027771} 08/30/2021 14:18:16 - INFO - __main__ - Step 6221: {'lr': 0.0004989976467451026, 'samples': 1194432, 'steps': 6220, 'loss/train': 1.5907371044158936} 08/30/2021 14:18:18 - INFO - __main__ - Step 6222: {'lr': 0.0004989971719577688, 'samples': 1194624, 'steps': 6221, 'loss/train': 2.125783681869507} 08/30/2021 14:18:18 - INFO - __main__ - Step 6223: {'lr': 0.0004989966970582408, 'samples': 1194816, 'steps': 6222, 'loss/train': 2.1885910034179688} 08/30/2021 14:18:19 - INFO - __main__ - Step 6224: {'lr': 0.0004989962220465187, 'samples': 1195008, 'steps': 6223, 'loss/train': 2.1810812950134277} 08/30/2021 14:18:19 - INFO - __main__ - Step 6225: {'lr': 0.0004989957469226027, 'samples': 1195200, 'steps': 6224, 'loss/train': 1.6825599670410156} 08/30/2021 14:18:19 - INFO - __main__ - Step 6226: {'lr': 0.0004989952716864931, 'samples': 1195392, 'steps': 6225, 'loss/train': 2.1403675079345703} 08/30/2021 14:18:21 - INFO - __main__ - Step 6227: {'lr': 0.00049899479633819, 'samples': 1195584, 'steps': 6226, 'loss/train': 1.7359288930892944} 08/30/2021 14:18:21 - INFO - __main__ - Step 6228: {'lr': 0.0004989943208776938, 'samples': 1195776, 'steps': 6227, 'loss/train': 1.8733208179473877} 08/30/2021 14:18:22 - INFO - __main__ - Step 6229: {'lr': 0.0004989938453050045, 'samples': 1195968, 'steps': 6228, 'loss/train': 1.642006516456604} 08/30/2021 14:18:22 - INFO - __main__ - Step 6230: {'lr': 0.0004989933696201225, 'samples': 1196160, 'steps': 6229, 'loss/train': 1.9372864961624146} 08/30/2021 14:18:22 - INFO - __main__ - Step 6231: {'lr': 0.0004989928938230478, 'samples': 1196352, 'steps': 6230, 'loss/train': 2.230191707611084} 08/30/2021 14:18:24 - INFO - __main__ - Step 6232: {'lr': 0.0004989924179137808, 'samples': 1196544, 'steps': 6231, 'loss/train': 2.5581588745117188} 08/30/2021 14:18:24 - INFO - __main__ - Step 6233: {'lr': 0.0004989919418923218, 'samples': 1196736, 'steps': 6232, 'loss/train': 2.114278554916382} 08/30/2021 14:18:24 - INFO - __main__ - Step 6234: {'lr': 0.0004989914657586707, 'samples': 1196928, 'steps': 6233, 'loss/train': 2.0605738162994385} 08/30/2021 14:18:25 - INFO - __main__ - Step 6235: {'lr': 0.000498990989512828, 'samples': 1197120, 'steps': 6234, 'loss/train': 1.9753429889678955} 08/30/2021 14:18:25 - INFO - __main__ - Step 6236: {'lr': 0.0004989905131547937, 'samples': 1197312, 'steps': 6235, 'loss/train': 2.2529351711273193} 08/30/2021 14:18:27 - INFO - __main__ - Step 6237: {'lr': 0.0004989900366845682, 'samples': 1197504, 'steps': 6236, 'loss/train': 2.2310385704040527} 08/30/2021 14:18:27 - INFO - __main__ - Step 6238: {'lr': 0.0004989895601021515, 'samples': 1197696, 'steps': 6237, 'loss/train': 1.9800227880477905} 08/30/2021 14:18:27 - INFO - __main__ - Step 6239: {'lr': 0.0004989890834075441, 'samples': 1197888, 'steps': 6238, 'loss/train': 1.9875377416610718} 08/30/2021 14:18:28 - INFO - __main__ - Step 6240: {'lr': 0.000498988606600746, 'samples': 1198080, 'steps': 6239, 'loss/train': 2.0325026512145996} 08/30/2021 14:18:28 - INFO - __main__ - Step 6241: {'lr': 0.0004989881296817575, 'samples': 1198272, 'steps': 6240, 'loss/train': 2.1536710262298584} 08/30/2021 14:18:30 - INFO - __main__ - Step 6242: {'lr': 0.0004989876526505788, 'samples': 1198464, 'steps': 6241, 'loss/train': 2.5535590648651123} 08/30/2021 14:18:30 - INFO - __main__ - Step 6243: {'lr': 0.0004989871755072101, 'samples': 1198656, 'steps': 6242, 'loss/train': 2.3413236141204834} 08/30/2021 14:18:30 - INFO - __main__ - Step 6244: {'lr': 0.0004989866982516516, 'samples': 1198848, 'steps': 6243, 'loss/train': 1.6933993101119995} 08/30/2021 14:18:31 - INFO - __main__ - Step 6245: {'lr': 0.0004989862208839035, 'samples': 1199040, 'steps': 6244, 'loss/train': 2.150791883468628} 08/30/2021 14:18:31 - INFO - __main__ - Step 6246: {'lr': 0.0004989857434039661, 'samples': 1199232, 'steps': 6245, 'loss/train': 2.0392470359802246} 08/30/2021 14:18:33 - INFO - __main__ - Step 6247: {'lr': 0.0004989852658118395, 'samples': 1199424, 'steps': 6246, 'loss/train': 1.798715591430664} 08/30/2021 14:18:33 - INFO - __main__ - Step 6248: {'lr': 0.000498984788107524, 'samples': 1199616, 'steps': 6247, 'loss/train': 2.3154523372650146} 08/30/2021 14:18:33 - INFO - __main__ - Step 6249: {'lr': 0.0004989843102910198, 'samples': 1199808, 'steps': 6248, 'loss/train': 2.6237261295318604} 08/30/2021 14:18:34 - INFO - __main__ - Step 6250: {'lr': 0.0004989838323623272, 'samples': 1200000, 'steps': 6249, 'loss/train': 1.3969299793243408} 08/30/2021 14:18:34 - INFO - __main__ - Step 6251: {'lr': 0.0004989833543214463, 'samples': 1200192, 'steps': 6250, 'loss/train': 1.8402429819107056} 08/30/2021 14:18:36 - INFO - __main__ - Step 6252: {'lr': 0.0004989828761683774, 'samples': 1200384, 'steps': 6251, 'loss/train': 0.9740005135536194} 08/30/2021 14:18:36 - INFO - __main__ - Step 6253: {'lr': 0.0004989823979031205, 'samples': 1200576, 'steps': 6252, 'loss/train': 1.827061414718628} 08/30/2021 14:18:37 - INFO - __main__ - Step 6254: {'lr': 0.000498981919525676, 'samples': 1200768, 'steps': 6253, 'loss/train': 1.2323906421661377} 08/30/2021 14:18:37 - INFO - __main__ - Step 6255: {'lr': 0.0004989814410360442, 'samples': 1200960, 'steps': 6254, 'loss/train': 2.6655220985412598} 08/30/2021 14:18:37 - INFO - __main__ - Step 6256: {'lr': 0.0004989809624342251, 'samples': 1201152, 'steps': 6255, 'loss/train': 2.2425320148468018} 08/30/2021 14:18:39 - INFO - __main__ - Step 6257: {'lr': 0.000498980483720219, 'samples': 1201344, 'steps': 6256, 'loss/train': 2.5152058601379395} 08/30/2021 14:18:40 - INFO - __main__ - Step 6258: {'lr': 0.0004989800048940263, 'samples': 1201536, 'steps': 6257, 'loss/train': 1.9815870523452759} 08/30/2021 14:18:40 - INFO - __main__ - Step 6259: {'lr': 0.0004989795259556469, 'samples': 1201728, 'steps': 6258, 'loss/train': 1.9239863157272339} 08/30/2021 14:18:41 - INFO - __main__ - Step 6260: {'lr': 0.0004989790469050813, 'samples': 1201920, 'steps': 6259, 'loss/train': 1.7363396883010864} 08/30/2021 14:18:41 - INFO - __main__ - Step 6261: {'lr': 0.0004989785677423295, 'samples': 1202112, 'steps': 6260, 'loss/train': 0.8849676251411438} 08/30/2021 14:18:42 - INFO - __main__ - Step 6262: {'lr': 0.0004989780884673917, 'samples': 1202304, 'steps': 6261, 'loss/train': 2.0852367877960205} 08/30/2021 14:18:43 - INFO - __main__ - Step 6263: {'lr': 0.0004989776090802683, 'samples': 1202496, 'steps': 6262, 'loss/train': 2.010713577270508} 08/30/2021 14:18:43 - INFO - __main__ - Step 6264: {'lr': 0.0004989771295809594, 'samples': 1202688, 'steps': 6263, 'loss/train': 1.6176643371582031} 08/30/2021 14:18:44 - INFO - __main__ - Step 6265: {'lr': 0.0004989766499694653, 'samples': 1202880, 'steps': 6264, 'loss/train': 1.9133375883102417} 08/30/2021 14:18:44 - INFO - __main__ - Step 6266: {'lr': 0.0004989761702457862, 'samples': 1203072, 'steps': 6265, 'loss/train': 1.3014731407165527} 08/30/2021 14:18:45 - INFO - __main__ - Step 6267: {'lr': 0.0004989756904099222, 'samples': 1203264, 'steps': 6266, 'loss/train': 2.108015537261963} 08/30/2021 14:18:46 - INFO - __main__ - Step 6268: {'lr': 0.0004989752104618736, 'samples': 1203456, 'steps': 6267, 'loss/train': 2.1357452869415283} 08/30/2021 14:18:46 - INFO - __main__ - Step 6269: {'lr': 0.0004989747304016407, 'samples': 1203648, 'steps': 6268, 'loss/train': 2.0290212631225586} 08/30/2021 14:18:47 - INFO - __main__ - Step 6270: {'lr': 0.0004989742502292235, 'samples': 1203840, 'steps': 6269, 'loss/train': 1.945146918296814} 08/30/2021 14:18:47 - INFO - __main__ - Step 6271: {'lr': 0.0004989737699446225, 'samples': 1204032, 'steps': 6270, 'loss/train': 2.129586935043335} 08/30/2021 14:18:47 - INFO - __main__ - Step 6272: {'lr': 0.0004989732895478376, 'samples': 1204224, 'steps': 6271, 'loss/train': 2.221515655517578} 08/30/2021 14:18:49 - INFO - __main__ - Step 6273: {'lr': 0.0004989728090388693, 'samples': 1204416, 'steps': 6272, 'loss/train': 1.7734287977218628} 08/30/2021 14:18:49 - INFO - __main__ - Step 6274: {'lr': 0.0004989723284177177, 'samples': 1204608, 'steps': 6273, 'loss/train': 2.149461507797241} 08/30/2021 14:18:50 - INFO - __main__ - Step 6275: {'lr': 0.0004989718476843828, 'samples': 1204800, 'steps': 6274, 'loss/train': 1.9583441019058228} 08/30/2021 14:18:50 - INFO - __main__ - Step 6276: {'lr': 0.0004989713668388652, 'samples': 1204992, 'steps': 6275, 'loss/train': 2.027327537536621} 08/30/2021 14:18:50 - INFO - __main__ - Step 6277: {'lr': 0.000498970885881165, 'samples': 1205184, 'steps': 6276, 'loss/train': 2.7661585807800293} 08/30/2021 14:18:52 - INFO - __main__ - Step 6278: {'lr': 0.0004989704048112823, 'samples': 1205376, 'steps': 6277, 'loss/train': 2.363206386566162} 08/30/2021 14:18:52 - INFO - __main__ - Step 6279: {'lr': 0.0004989699236292173, 'samples': 1205568, 'steps': 6278, 'loss/train': 2.557337522506714} 08/30/2021 14:18:53 - INFO - __main__ - Step 6280: {'lr': 0.0004989694423349704, 'samples': 1205760, 'steps': 6279, 'loss/train': 1.611116886138916} 08/30/2021 14:18:53 - INFO - __main__ - Step 6281: {'lr': 0.0004989689609285417, 'samples': 1205952, 'steps': 6280, 'loss/train': 2.5754168033599854} 08/30/2021 14:18:53 - INFO - __main__ - Step 6282: {'lr': 0.0004989684794099314, 'samples': 1206144, 'steps': 6281, 'loss/train': 2.283574104309082} 08/30/2021 14:18:55 - INFO - __main__ - Step 6283: {'lr': 0.0004989679977791397, 'samples': 1206336, 'steps': 6282, 'loss/train': 1.8226563930511475} 08/30/2021 14:18:55 - INFO - __main__ - Step 6284: {'lr': 0.0004989675160361669, 'samples': 1206528, 'steps': 6283, 'loss/train': 1.9837374687194824} 08/30/2021 14:18:56 - INFO - __main__ - Step 6285: {'lr': 0.0004989670341810132, 'samples': 1206720, 'steps': 6284, 'loss/train': 2.731910228729248} 08/30/2021 14:18:56 - INFO - __main__ - Step 6286: {'lr': 0.0004989665522136789, 'samples': 1206912, 'steps': 6285, 'loss/train': 1.9442856311798096} 08/30/2021 14:18:56 - INFO - __main__ - Step 6287: {'lr': 0.0004989660701341639, 'samples': 1207104, 'steps': 6286, 'loss/train': 1.8635879755020142} 08/30/2021 14:18:58 - INFO - __main__ - Step 6288: {'lr': 0.0004989655879424687, 'samples': 1207296, 'steps': 6287, 'loss/train': 1.9705373048782349} 08/30/2021 14:18:58 - INFO - __main__ - Step 6289: {'lr': 0.0004989651056385936, 'samples': 1207488, 'steps': 6288, 'loss/train': 1.9441709518432617} 08/30/2021 14:18:59 - INFO - __main__ - Step 6290: {'lr': 0.0004989646232225384, 'samples': 1207680, 'steps': 6289, 'loss/train': 1.605919361114502} 08/30/2021 14:18:59 - INFO - __main__ - Step 6291: {'lr': 0.0004989641406943037, 'samples': 1207872, 'steps': 6290, 'loss/train': 1.3890336751937866} 08/30/2021 14:18:59 - INFO - __main__ - Step 6292: {'lr': 0.0004989636580538896, 'samples': 1208064, 'steps': 6291, 'loss/train': 1.718228816986084} 08/30/2021 14:19:01 - INFO - __main__ - Step 6293: {'lr': 0.0004989631753012964, 'samples': 1208256, 'steps': 6292, 'loss/train': 2.0688412189483643} 08/30/2021 14:19:01 - INFO - __main__ - Step 6294: {'lr': 0.0004989626924365242, 'samples': 1208448, 'steps': 6293, 'loss/train': 1.2345472574234009} 08/30/2021 14:19:02 - INFO - __main__ - Step 6295: {'lr': 0.0004989622094595733, 'samples': 1208640, 'steps': 6294, 'loss/train': 1.4485729932785034} 08/30/2021 14:19:02 - INFO - __main__ - Step 6296: {'lr': 0.0004989617263704437, 'samples': 1208832, 'steps': 6295, 'loss/train': 2.0158963203430176} 08/30/2021 14:19:02 - INFO - __main__ - Step 6297: {'lr': 0.0004989612431691359, 'samples': 1209024, 'steps': 6296, 'loss/train': 1.9707484245300293} 08/30/2021 14:19:03 - INFO - __main__ - Step 6298: {'lr': 0.0004989607598556501, 'samples': 1209216, 'steps': 6297, 'loss/train': 2.353196144104004} 08/30/2021 14:19:05 - INFO - __main__ - Step 6299: {'lr': 0.0004989602764299862, 'samples': 1209408, 'steps': 6298, 'loss/train': 1.7036041021347046} 08/30/2021 14:19:05 - INFO - __main__ - Step 6300: {'lr': 0.0004989597928921447, 'samples': 1209600, 'steps': 6299, 'loss/train': 0.30971235036849976} 08/30/2021 14:19:05 - INFO - __main__ - Step 6301: {'lr': 0.0004989593092421258, 'samples': 1209792, 'steps': 6300, 'loss/train': 1.692036747932434} 08/30/2021 14:19:06 - INFO - __main__ - Step 6302: {'lr': 0.0004989588254799297, 'samples': 1209984, 'steps': 6301, 'loss/train': 2.0625877380371094} 08/30/2021 14:19:06 - INFO - __main__ - Step 6303: {'lr': 0.0004989583416055566, 'samples': 1210176, 'steps': 6302, 'loss/train': 1.2793693542480469} 08/30/2021 14:19:08 - INFO - __main__ - Step 6304: {'lr': 0.0004989578576190068, 'samples': 1210368, 'steps': 6303, 'loss/train': 2.2753987312316895} 08/30/2021 14:19:08 - INFO - __main__ - Step 6305: {'lr': 0.0004989573735202802, 'samples': 1210560, 'steps': 6304, 'loss/train': 2.163113594055176} 08/30/2021 14:19:08 - INFO - __main__ - Step 6306: {'lr': 0.0004989568893093774, 'samples': 1210752, 'steps': 6305, 'loss/train': 2.0276966094970703} 08/30/2021 14:19:09 - INFO - __main__ - Step 6307: {'lr': 0.0004989564049862986, 'samples': 1210944, 'steps': 6306, 'loss/train': 2.8450539112091064} 08/30/2021 14:19:09 - INFO - __main__ - Step 6308: {'lr': 0.0004989559205510436, 'samples': 1211136, 'steps': 6307, 'loss/train': 2.1560885906219482} 08/30/2021 14:19:09 - INFO - __main__ - Step 6309: {'lr': 0.000498955436003613, 'samples': 1211328, 'steps': 6308, 'loss/train': 2.1145544052124023} 08/30/2021 14:19:12 - INFO - __main__ - Step 6310: {'lr': 0.0004989549513440071, 'samples': 1211520, 'steps': 6309, 'loss/train': 2.2295072078704834} 08/30/2021 14:19:12 - INFO - __main__ - Step 6311: {'lr': 0.0004989544665722258, 'samples': 1211712, 'steps': 6310, 'loss/train': 1.5627377033233643} 08/30/2021 14:19:13 - INFO - __main__ - Step 6312: {'lr': 0.0004989539816882694, 'samples': 1211904, 'steps': 6311, 'loss/train': 2.430529832839966} 08/30/2021 14:19:13 - INFO - __main__ - Step 6313: {'lr': 0.0004989534966921382, 'samples': 1212096, 'steps': 6312, 'loss/train': 1.8771684169769287} 08/30/2021 14:19:14 - INFO - __main__ - Step 6314: {'lr': 0.0004989530115838324, 'samples': 1212288, 'steps': 6313, 'loss/train': 0.33140167593955994} 08/30/2021 14:19:15 - INFO - __main__ - Step 6315: {'lr': 0.0004989525263633523, 'samples': 1212480, 'steps': 6314, 'loss/train': 1.9396084547042847} 08/30/2021 14:19:16 - INFO - __main__ - Step 6316: {'lr': 0.0004989520410306979, 'samples': 1212672, 'steps': 6315, 'loss/train': 1.6873884201049805} 08/30/2021 14:19:16 - INFO - __main__ - Step 6317: {'lr': 0.0004989515555858697, 'samples': 1212864, 'steps': 6316, 'loss/train': 2.732889413833618} 08/30/2021 14:19:16 - INFO - __main__ - Step 6318: {'lr': 0.0004989510700288678, 'samples': 1213056, 'steps': 6317, 'loss/train': 2.062293291091919} 08/30/2021 14:19:17 - INFO - __main__ - Step 6319: {'lr': 0.0004989505843596922, 'samples': 1213248, 'steps': 6318, 'loss/train': 2.04461932182312} 08/30/2021 14:19:18 - INFO - __main__ - Step 6320: {'lr': 0.0004989500985783434, 'samples': 1213440, 'steps': 6319, 'loss/train': 1.9916492700576782} 08/30/2021 14:19:19 - INFO - __main__ - Step 6321: {'lr': 0.0004989496126848215, 'samples': 1213632, 'steps': 6320, 'loss/train': 1.9172712564468384} 08/30/2021 14:19:19 - INFO - __main__ - Step 6322: {'lr': 0.0004989491266791268, 'samples': 1213824, 'steps': 6321, 'loss/train': 1.4685570001602173} 08/30/2021 14:19:19 - INFO - __main__ - Step 6323: {'lr': 0.0004989486405612595, 'samples': 1214016, 'steps': 6322, 'loss/train': 2.379302978515625} 08/30/2021 14:19:20 - INFO - __main__ - Step 6324: {'lr': 0.0004989481543312196, 'samples': 1214208, 'steps': 6323, 'loss/train': 2.27948260307312} 08/30/2021 14:19:21 - INFO - __main__ - Step 6325: {'lr': 0.0004989476679890077, 'samples': 1214400, 'steps': 6324, 'loss/train': 2.2262282371520996} 08/30/2021 14:19:22 - INFO - __main__ - Step 6326: {'lr': 0.0004989471815346237, 'samples': 1214592, 'steps': 6325, 'loss/train': 1.691623568534851} 08/30/2021 14:19:22 - INFO - __main__ - Step 6327: {'lr': 0.000498946694968068, 'samples': 1214784, 'steps': 6326, 'loss/train': 1.5407147407531738} 08/30/2021 14:19:22 - INFO - __main__ - Step 6328: {'lr': 0.0004989462082893407, 'samples': 1214976, 'steps': 6327, 'loss/train': 1.9831125736236572} 08/30/2021 14:19:23 - INFO - __main__ - Step 6329: {'lr': 0.0004989457214984421, 'samples': 1215168, 'steps': 6328, 'loss/train': 2.3993725776672363} 08/30/2021 14:19:24 - INFO - __main__ - Step 6330: {'lr': 0.0004989452345953725, 'samples': 1215360, 'steps': 6329, 'loss/train': 1.287635087966919} 08/30/2021 14:19:25 - INFO - __main__ - Step 6331: {'lr': 0.000498944747580132, 'samples': 1215552, 'steps': 6330, 'loss/train': 1.7396970987319946} 08/30/2021 14:19:25 - INFO - __main__ - Step 6332: {'lr': 0.0004989442604527208, 'samples': 1215744, 'steps': 6331, 'loss/train': 1.8150804042816162} 08/30/2021 14:19:25 - INFO - __main__ - Step 6333: {'lr': 0.0004989437732131391, 'samples': 1215936, 'steps': 6332, 'loss/train': 2.2430362701416016} 08/30/2021 14:19:26 - INFO - __main__ - Step 6334: {'lr': 0.0004989432858613873, 'samples': 1216128, 'steps': 6333, 'loss/train': 1.4362497329711914} 08/30/2021 14:19:27 - INFO - __main__ - Step 6335: {'lr': 0.0004989427983974653, 'samples': 1216320, 'steps': 6334, 'loss/train': 2.403474807739258} 08/30/2021 14:19:28 - INFO - __main__ - Step 6336: {'lr': 0.0004989423108213737, 'samples': 1216512, 'steps': 6335, 'loss/train': 1.6801766157150269} 08/30/2021 14:19:28 - INFO - __main__ - Step 6337: {'lr': 0.0004989418231331124, 'samples': 1216704, 'steps': 6336, 'loss/train': 1.848619818687439} 08/30/2021 14:19:28 - INFO - __main__ - Step 6338: {'lr': 0.0004989413353326818, 'samples': 1216896, 'steps': 6337, 'loss/train': 2.519618034362793} 08/30/2021 14:19:29 - INFO - __main__ - Step 6339: {'lr': 0.0004989408474200821, 'samples': 1217088, 'steps': 6338, 'loss/train': 1.8634679317474365} 08/30/2021 14:19:29 - INFO - __main__ - Step 6340: {'lr': 0.0004989403593953135, 'samples': 1217280, 'steps': 6339, 'loss/train': 1.661281704902649} 08/30/2021 14:19:31 - INFO - __main__ - Step 6341: {'lr': 0.0004989398712583762, 'samples': 1217472, 'steps': 6340, 'loss/train': 0.8902767896652222} 08/30/2021 14:19:31 - INFO - __main__ - Step 6342: {'lr': 0.0004989393830092705, 'samples': 1217664, 'steps': 6341, 'loss/train': 0.21483157575130463} 08/30/2021 14:19:32 - INFO - __main__ - Step 6343: {'lr': 0.0004989388946479965, 'samples': 1217856, 'steps': 6342, 'loss/train': 1.917526125907898} 08/30/2021 14:19:32 - INFO - __main__ - Step 6344: {'lr': 0.0004989384061745545, 'samples': 1218048, 'steps': 6343, 'loss/train': 2.1375091075897217} 08/30/2021 14:19:32 - INFO - __main__ - Step 6345: {'lr': 0.0004989379175889447, 'samples': 1218240, 'steps': 6344, 'loss/train': 1.9298045635223389} 08/30/2021 14:19:34 - INFO - __main__ - Step 6346: {'lr': 0.0004989374288911672, 'samples': 1218432, 'steps': 6345, 'loss/train': 0.2548641264438629} 08/30/2021 14:19:35 - INFO - __main__ - Step 6347: {'lr': 0.0004989369400812225, 'samples': 1218624, 'steps': 6346, 'loss/train': 1.0864231586456299} 08/30/2021 14:19:35 - INFO - __main__ - Step 6348: {'lr': 0.0004989364511591106, 'samples': 1218816, 'steps': 6347, 'loss/train': 2.2659149169921875} 08/30/2021 14:19:35 - INFO - __main__ - Step 6349: {'lr': 0.0004989359621248317, 'samples': 1219008, 'steps': 6348, 'loss/train': 2.0931715965270996} 08/30/2021 14:19:36 - INFO - __main__ - Step 6350: {'lr': 0.0004989354729783861, 'samples': 1219200, 'steps': 6349, 'loss/train': 1.9924660921096802} 08/30/2021 14:19:36 - INFO - __main__ - Step 6351: {'lr': 0.0004989349837197742, 'samples': 1219392, 'steps': 6350, 'loss/train': 0.22452615201473236} 08/30/2021 14:19:37 - INFO - __main__ - Step 6352: {'lr': 0.0004989344943489958, 'samples': 1219584, 'steps': 6351, 'loss/train': 2.3767666816711426} 08/30/2021 14:19:38 - INFO - __main__ - Step 6353: {'lr': 0.0004989340048660515, 'samples': 1219776, 'steps': 6352, 'loss/train': 1.9281697273254395} 08/30/2021 14:19:38 - INFO - __main__ - Step 6354: {'lr': 0.0004989335152709414, 'samples': 1219968, 'steps': 6353, 'loss/train': 2.7251996994018555} 08/30/2021 14:19:39 - INFO - __main__ - Step 6355: {'lr': 0.0004989330255636656, 'samples': 1220160, 'steps': 6354, 'loss/train': 1.8787678480148315} 08/30/2021 14:19:39 - INFO - __main__ - Step 6356: {'lr': 0.0004989325357442245, 'samples': 1220352, 'steps': 6355, 'loss/train': 1.6053874492645264} 08/30/2021 14:19:41 - INFO - __main__ - Step 6357: {'lr': 0.0004989320458126182, 'samples': 1220544, 'steps': 6356, 'loss/train': 2.2343366146087646} 08/30/2021 14:19:42 - INFO - __main__ - Step 6358: {'lr': 0.0004989315557688469, 'samples': 1220736, 'steps': 6357, 'loss/train': 1.4021246433258057} 08/30/2021 14:19:42 - INFO - __main__ - Step 6359: {'lr': 0.000498931065612911, 'samples': 1220928, 'steps': 6358, 'loss/train': 2.5814125537872314} 08/30/2021 14:19:42 - INFO - __main__ - Step 6360: {'lr': 0.0004989305753448106, 'samples': 1221120, 'steps': 6359, 'loss/train': 1.7415645122528076} 08/30/2021 14:19:43 - INFO - __main__ - Step 6361: {'lr': 0.0004989300849645459, 'samples': 1221312, 'steps': 6360, 'loss/train': 2.3653414249420166} 08/30/2021 14:19:43 - INFO - __main__ - Step 6362: {'lr': 0.0004989295944721171, 'samples': 1221504, 'steps': 6361, 'loss/train': 2.4741456508636475} 08/30/2021 14:19:43 - INFO - __main__ - Step 6363: {'lr': 0.0004989291038675245, 'samples': 1221696, 'steps': 6362, 'loss/train': 2.3353641033172607} 08/30/2021 14:19:45 - INFO - __main__ - Step 6364: {'lr': 0.0004989286131507682, 'samples': 1221888, 'steps': 6363, 'loss/train': 0.33484983444213867} 08/30/2021 14:19:46 - INFO - __main__ - Step 6365: {'lr': 0.0004989281223218486, 'samples': 1222080, 'steps': 6364, 'loss/train': 2.1490490436553955} 08/30/2021 14:19:46 - INFO - __main__ - Step 6366: {'lr': 0.0004989276313807658, 'samples': 1222272, 'steps': 6365, 'loss/train': 2.045421838760376} 08/30/2021 14:19:47 - INFO - __main__ - Step 6367: {'lr': 0.00049892714032752, 'samples': 1222464, 'steps': 6366, 'loss/train': 1.8140629529953003} 08/30/2021 14:19:47 - INFO - __main__ - Step 6368: {'lr': 0.0004989266491621117, 'samples': 1222656, 'steps': 6367, 'loss/train': 2.209887981414795} 08/30/2021 14:19:48 - INFO - __main__ - Step 6369: {'lr': 0.0004989261578845406, 'samples': 1222848, 'steps': 6368, 'loss/train': 1.681424856185913} 08/30/2021 14:19:49 - INFO - __main__ - Step 6370: {'lr': 0.0004989256664948073, 'samples': 1223040, 'steps': 6369, 'loss/train': 1.6200883388519287} 08/30/2021 14:19:49 - INFO - __main__ - Step 6371: {'lr': 0.000498925174992912, 'samples': 1223232, 'steps': 6370, 'loss/train': 3.0206379890441895} 08/30/2021 14:19:49 - INFO - __main__ - Step 6372: {'lr': 0.0004989246833788549, 'samples': 1223424, 'steps': 6371, 'loss/train': 2.03474760055542} 08/30/2021 14:19:50 - INFO - __main__ - Step 6373: {'lr': 0.000498924191652636, 'samples': 1223616, 'steps': 6372, 'loss/train': 1.6458381414413452} 08/30/2021 14:19:51 - INFO - __main__ - Step 6374: {'lr': 0.0004989236998142559, 'samples': 1223808, 'steps': 6373, 'loss/train': 2.533975124359131} 08/30/2021 14:19:52 - INFO - __main__ - Step 6375: {'lr': 0.0004989232078637145, 'samples': 1224000, 'steps': 6374, 'loss/train': 2.086960792541504} 08/30/2021 14:19:52 - INFO - __main__ - Step 6376: {'lr': 0.0004989227158010123, 'samples': 1224192, 'steps': 6375, 'loss/train': 1.8674033880233765} 08/30/2021 14:19:53 - INFO - __main__ - Step 6377: {'lr': 0.0004989222236261491, 'samples': 1224384, 'steps': 6376, 'loss/train': 1.910085916519165} 08/30/2021 14:19:53 - INFO - __main__ - Step 6378: {'lr': 0.0004989217313391256, 'samples': 1224576, 'steps': 6377, 'loss/train': 2.0162723064422607} 08/30/2021 14:19:54 - INFO - __main__ - Step 6379: {'lr': 0.0004989212389399417, 'samples': 1224768, 'steps': 6378, 'loss/train': 2.0569067001342773} 08/30/2021 14:19:55 - INFO - __main__ - Step 6380: {'lr': 0.0004989207464285978, 'samples': 1224960, 'steps': 6379, 'loss/train': 1.8085367679595947} 08/30/2021 14:19:55 - INFO - __main__ - Step 6381: {'lr': 0.0004989202538050939, 'samples': 1225152, 'steps': 6380, 'loss/train': 1.903486728668213} 08/30/2021 14:19:56 - INFO - __main__ - Step 6382: {'lr': 0.0004989197610694306, 'samples': 1225344, 'steps': 6381, 'loss/train': 1.8851052522659302} 08/30/2021 14:19:56 - INFO - __main__ - Step 6383: {'lr': 0.0004989192682216078, 'samples': 1225536, 'steps': 6382, 'loss/train': 2.309662342071533} 08/30/2021 14:19:57 - INFO - __main__ - Step 6384: {'lr': 0.0004989187752616258, 'samples': 1225728, 'steps': 6383, 'loss/train': 2.068089008331299} 08/30/2021 14:19:58 - INFO - __main__ - Step 6385: {'lr': 0.0004989182821894849, 'samples': 1225920, 'steps': 6384, 'loss/train': 1.5951160192489624} 08/30/2021 14:19:58 - INFO - __main__ - Step 6386: {'lr': 0.0004989177890051852, 'samples': 1226112, 'steps': 6385, 'loss/train': 2.226026773452759} 08/30/2021 14:19:59 - INFO - __main__ - Step 6387: {'lr': 0.000498917295708727, 'samples': 1226304, 'steps': 6386, 'loss/train': 2.1340386867523193} 08/30/2021 14:19:59 - INFO - __main__ - Step 6388: {'lr': 0.0004989168023001105, 'samples': 1226496, 'steps': 6387, 'loss/train': 1.9530478715896606} 08/30/2021 14:20:00 - INFO - __main__ - Step 6389: {'lr': 0.0004989163087793359, 'samples': 1226688, 'steps': 6388, 'loss/train': 0.7116537690162659} 08/30/2021 14:20:01 - INFO - __main__ - Step 6390: {'lr': 0.0004989158151464036, 'samples': 1226880, 'steps': 6389, 'loss/train': 1.7949714660644531} 08/30/2021 14:20:01 - INFO - __main__ - Step 6391: {'lr': 0.0004989153214013135, 'samples': 1227072, 'steps': 6390, 'loss/train': 2.08050537109375} 08/30/2021 14:20:02 - INFO - __main__ - Step 6392: {'lr': 0.0004989148275440661, 'samples': 1227264, 'steps': 6391, 'loss/train': 1.6071804761886597} 08/30/2021 14:20:02 - INFO - __main__ - Step 6393: {'lr': 0.0004989143335746614, 'samples': 1227456, 'steps': 6392, 'loss/train': 1.5674817562103271} 08/30/2021 14:20:03 - INFO - __main__ - Step 6394: {'lr': 0.0004989138394930998, 'samples': 1227648, 'steps': 6393, 'loss/train': 1.3918814659118652} 08/30/2021 14:20:04 - INFO - __main__ - Step 6395: {'lr': 0.0004989133452993816, 'samples': 1227840, 'steps': 6394, 'loss/train': 2.240018129348755} 08/30/2021 14:20:04 - INFO - __main__ - Step 6396: {'lr': 0.0004989128509935068, 'samples': 1228032, 'steps': 6395, 'loss/train': 2.1449835300445557} 08/30/2021 14:20:05 - INFO - __main__ - Step 6397: {'lr': 0.0004989123565754756, 'samples': 1228224, 'steps': 6396, 'loss/train': 2.164830207824707} 08/30/2021 14:20:05 - INFO - __main__ - Step 6398: {'lr': 0.0004989118620452884, 'samples': 1228416, 'steps': 6397, 'loss/train': 2.341160535812378} 08/30/2021 14:20:06 - INFO - __main__ - Step 6399: {'lr': 0.0004989113674029454, 'samples': 1228608, 'steps': 6398, 'loss/train': 1.8842697143554688} 08/30/2021 14:20:07 - INFO - __main__ - Step 6400: {'lr': 0.0004989108726484469, 'samples': 1228800, 'steps': 6399, 'loss/train': 2.3316967487335205} 08/30/2021 14:20:07 - INFO - __main__ - Step 6401: {'lr': 0.0004989103777817928, 'samples': 1228992, 'steps': 6400, 'loss/train': 1.546118974685669} 08/30/2021 14:20:07 - INFO - __main__ - Step 6402: {'lr': 0.0004989098828029836, 'samples': 1229184, 'steps': 6401, 'loss/train': 2.2582178115844727} 08/30/2021 14:20:08 - INFO - __main__ - Step 6403: {'lr': 0.0004989093877120194, 'samples': 1229376, 'steps': 6402, 'loss/train': 1.7887744903564453} 08/30/2021 14:20:08 - INFO - __main__ - Step 6404: {'lr': 0.0004989088925089005, 'samples': 1229568, 'steps': 6403, 'loss/train': 1.4423006772994995} 08/30/2021 14:20:10 - INFO - __main__ - Step 6405: {'lr': 0.0004989083971936271, 'samples': 1229760, 'steps': 6404, 'loss/train': 2.076840877532959} 08/30/2021 14:20:10 - INFO - __main__ - Step 6406: {'lr': 0.0004989079017661994, 'samples': 1229952, 'steps': 6405, 'loss/train': 2.444427490234375} 08/30/2021 14:20:10 - INFO - __main__ - Step 6407: {'lr': 0.0004989074062266177, 'samples': 1230144, 'steps': 6406, 'loss/train': 2.0568270683288574} 08/30/2021 14:20:11 - INFO - __main__ - Step 6408: {'lr': 0.0004989069105748821, 'samples': 1230336, 'steps': 6407, 'loss/train': 1.5928832292556763} 08/30/2021 14:20:11 - INFO - __main__ - Step 6409: {'lr': 0.0004989064148109929, 'samples': 1230528, 'steps': 6408, 'loss/train': 2.200293779373169} 08/30/2021 14:20:13 - INFO - __main__ - Step 6410: {'lr': 0.0004989059189349503, 'samples': 1230720, 'steps': 6409, 'loss/train': 2.3416473865509033} 08/30/2021 14:20:13 - INFO - __main__ - Step 6411: {'lr': 0.0004989054229467546, 'samples': 1230912, 'steps': 6410, 'loss/train': 2.1792893409729004} 08/30/2021 14:20:13 - INFO - __main__ - Step 6412: {'lr': 0.0004989049268464058, 'samples': 1231104, 'steps': 6411, 'loss/train': 2.018517255783081} 08/30/2021 14:20:14 - INFO - __main__ - Step 6413: {'lr': 0.0004989044306339044, 'samples': 1231296, 'steps': 6412, 'loss/train': 1.3932756185531616} 08/30/2021 14:20:14 - INFO - __main__ - Step 6414: {'lr': 0.0004989039343092505, 'samples': 1231488, 'steps': 6413, 'loss/train': 2.0457987785339355} 08/30/2021 14:20:16 - INFO - __main__ - Step 6415: {'lr': 0.0004989034378724443, 'samples': 1231680, 'steps': 6414, 'loss/train': 1.9669859409332275} 08/30/2021 14:20:17 - INFO - __main__ - Step 6416: {'lr': 0.0004989029413234861, 'samples': 1231872, 'steps': 6415, 'loss/train': 1.5404988527297974} 08/30/2021 14:20:17 - INFO - __main__ - Step 6417: {'lr': 0.000498902444662376, 'samples': 1232064, 'steps': 6416, 'loss/train': 1.5640596151351929} 08/30/2021 14:20:17 - INFO - __main__ - Step 6418: {'lr': 0.0004989019478891144, 'samples': 1232256, 'steps': 6417, 'loss/train': 2.1557815074920654} 08/30/2021 14:20:18 - INFO - __main__ - Step 6419: {'lr': 0.0004989014510037013, 'samples': 1232448, 'steps': 6418, 'loss/train': 2.441948890686035} 08/30/2021 14:20:19 - INFO - __main__ - Step 6420: {'lr': 0.0004989009540061373, 'samples': 1232640, 'steps': 6419, 'loss/train': 2.0749902725219727} 08/30/2021 14:20:20 - INFO - __main__ - Step 6421: {'lr': 0.0004989004568964221, 'samples': 1232832, 'steps': 6420, 'loss/train': 2.3868441581726074} 08/30/2021 14:20:20 - INFO - __main__ - Step 6422: {'lr': 0.0004988999596745562, 'samples': 1233024, 'steps': 6421, 'loss/train': 0.33942484855651855} 08/30/2021 14:20:20 - INFO - __main__ - Step 6423: {'lr': 0.00049889946234054, 'samples': 1233216, 'steps': 6422, 'loss/train': 2.162052631378174} 08/30/2021 14:20:21 - INFO - __main__ - Step 6424: {'lr': 0.0004988989648943734, 'samples': 1233408, 'steps': 6423, 'loss/train': 1.4928768873214722} 08/30/2021 14:20:22 - INFO - __main__ - Step 6425: {'lr': 0.0004988984673360568, 'samples': 1233600, 'steps': 6424, 'loss/train': 2.068682909011841} 08/30/2021 14:20:23 - INFO - __main__ - Step 6426: {'lr': 0.0004988979696655904, 'samples': 1233792, 'steps': 6425, 'loss/train': 1.5039173364639282} 08/30/2021 14:20:23 - INFO - __main__ - Step 6427: {'lr': 0.0004988974718829744, 'samples': 1233984, 'steps': 6426, 'loss/train': 2.104384660720825} 08/30/2021 14:20:23 - INFO - __main__ - Step 6428: {'lr': 0.0004988969739882091, 'samples': 1234176, 'steps': 6427, 'loss/train': 2.0742006301879883} 08/30/2021 14:20:24 - INFO - __main__ - Step 6429: {'lr': 0.0004988964759812946, 'samples': 1234368, 'steps': 6428, 'loss/train': 1.9064100980758667} 08/30/2021 14:20:25 - INFO - __main__ - Step 6430: {'lr': 0.0004988959778622313, 'samples': 1234560, 'steps': 6429, 'loss/train': 2.0313098430633545} 08/30/2021 14:20:26 - INFO - __main__ - Step 6431: {'lr': 0.0004988954796310191, 'samples': 1234752, 'steps': 6430, 'loss/train': 1.8159887790679932} 08/30/2021 14:20:26 - INFO - __main__ - Step 6432: {'lr': 0.0004988949812876586, 'samples': 1234944, 'steps': 6431, 'loss/train': 2.025383472442627} 08/30/2021 14:20:27 - INFO - __main__ - Step 6433: {'lr': 0.0004988944828321499, 'samples': 1235136, 'steps': 6432, 'loss/train': 1.7181217670440674} 08/30/2021 14:20:27 - INFO - __main__ - Step 6434: {'lr': 0.0004988939842644931, 'samples': 1235328, 'steps': 6433, 'loss/train': 2.1547458171844482} 08/30/2021 14:20:29 - INFO - __main__ - Step 6435: {'lr': 0.0004988934855846885, 'samples': 1235520, 'steps': 6434, 'loss/train': 3.3640191555023193} 08/30/2021 14:20:30 - INFO - __main__ - Step 6436: {'lr': 0.0004988929867927363, 'samples': 1235712, 'steps': 6435, 'loss/train': 1.8474713563919067} 08/30/2021 14:20:30 - INFO - __main__ - Step 6437: {'lr': 0.0004988924878886368, 'samples': 1235904, 'steps': 6436, 'loss/train': 0.1729724258184433} 08/30/2021 14:20:31 - INFO - __main__ - Step 6438: {'lr': 0.0004988919888723902, 'samples': 1236096, 'steps': 6437, 'loss/train': 2.002051591873169} 08/30/2021 14:20:31 - INFO - __main__ - Step 6439: {'lr': 0.0004988914897439968, 'samples': 1236288, 'steps': 6438, 'loss/train': 1.6145069599151611} 08/30/2021 14:20:31 - INFO - __main__ - Step 6440: {'lr': 0.0004988909905034566, 'samples': 1236480, 'steps': 6439, 'loss/train': 0.868749737739563} 08/30/2021 14:20:32 - INFO - __main__ - Step 6441: {'lr': 0.00049889049115077, 'samples': 1236672, 'steps': 6440, 'loss/train': 0.8868799209594727} 08/30/2021 14:20:33 - INFO - __main__ - Step 6442: {'lr': 0.0004988899916859372, 'samples': 1236864, 'steps': 6441, 'loss/train': 0.7765102386474609} 08/30/2021 14:20:34 - INFO - __main__ - Step 6443: {'lr': 0.0004988894921089584, 'samples': 1237056, 'steps': 6442, 'loss/train': 2.336009979248047} 08/30/2021 14:20:34 - INFO - __main__ - Step 6444: {'lr': 0.0004988889924198339, 'samples': 1237248, 'steps': 6443, 'loss/train': 1.799240231513977} 08/30/2021 14:20:34 - INFO - __main__ - Step 6445: {'lr': 0.0004988884926185637, 'samples': 1237440, 'steps': 6444, 'loss/train': 1.823669672012329} 08/30/2021 14:20:35 - INFO - __main__ - Step 6446: {'lr': 0.0004988879927051484, 'samples': 1237632, 'steps': 6445, 'loss/train': 2.093698740005493} 08/30/2021 14:20:36 - INFO - __main__ - Step 6447: {'lr': 0.0004988874926795878, 'samples': 1237824, 'steps': 6446, 'loss/train': 1.9283031225204468} 08/30/2021 14:20:37 - INFO - __main__ - Step 6448: {'lr': 0.0004988869925418825, 'samples': 1238016, 'steps': 6447, 'loss/train': 2.1458723545074463} 08/30/2021 14:20:37 - INFO - __main__ - Step 6449: {'lr': 0.0004988864922920325, 'samples': 1238208, 'steps': 6448, 'loss/train': 1.6288421154022217} 08/30/2021 14:20:37 - INFO - __main__ - Step 6450: {'lr': 0.000498885991930038, 'samples': 1238400, 'steps': 6449, 'loss/train': 1.8976569175720215} 08/30/2021 14:20:38 - INFO - __main__ - Step 6451: {'lr': 0.0004988854914558994, 'samples': 1238592, 'steps': 6450, 'loss/train': 2.386488437652588} 08/30/2021 14:20:39 - INFO - __main__ - Step 6452: {'lr': 0.0004988849908696169, 'samples': 1238784, 'steps': 6451, 'loss/train': 2.1098759174346924} 08/30/2021 14:20:40 - INFO - __main__ - Step 6453: {'lr': 0.0004988844901711905, 'samples': 1238976, 'steps': 6452, 'loss/train': 0.5721170902252197} 08/30/2021 14:20:40 - INFO - __main__ - Step 6454: {'lr': 0.0004988839893606208, 'samples': 1239168, 'steps': 6453, 'loss/train': 2.66838002204895} 08/30/2021 14:20:40 - INFO - __main__ - Step 6455: {'lr': 0.0004988834884379076, 'samples': 1239360, 'steps': 6454, 'loss/train': 2.5370492935180664} 08/30/2021 14:20:41 - INFO - __main__ - Step 6456: {'lr': 0.0004988829874030514, 'samples': 1239552, 'steps': 6455, 'loss/train': 2.045966863632202} 08/30/2021 14:20:42 - INFO - __main__ - Step 6457: {'lr': 0.0004988824862560525, 'samples': 1239744, 'steps': 6456, 'loss/train': 1.981670618057251} 08/30/2021 14:20:43 - INFO - __main__ - Step 6458: {'lr': 0.0004988819849969109, 'samples': 1239936, 'steps': 6457, 'loss/train': 2.628972053527832} 08/30/2021 14:20:43 - INFO - __main__ - Step 6459: {'lr': 0.0004988814836256269, 'samples': 1240128, 'steps': 6458, 'loss/train': 1.9126405715942383} 08/30/2021 14:20:43 - INFO - __main__ - Step 6460: {'lr': 0.0004988809821422008, 'samples': 1240320, 'steps': 6459, 'loss/train': 1.4414652585983276} 08/30/2021 14:20:44 - INFO - __main__ - Step 6461: {'lr': 0.0004988804805466327, 'samples': 1240512, 'steps': 6460, 'loss/train': 2.5868492126464844} 08/30/2021 14:20:45 - INFO - __main__ - Step 6462: {'lr': 0.000498879978838923, 'samples': 1240704, 'steps': 6461, 'loss/train': 2.3106813430786133} 08/30/2021 14:20:46 - INFO - __main__ - Step 6463: {'lr': 0.0004988794770190717, 'samples': 1240896, 'steps': 6462, 'loss/train': 1.930501103401184} 08/30/2021 14:20:46 - INFO - __main__ - Step 6464: {'lr': 0.0004988789750870792, 'samples': 1241088, 'steps': 6463, 'loss/train': 2.0551917552948} 08/30/2021 14:20:46 - INFO - __main__ - Step 6465: {'lr': 0.0004988784730429457, 'samples': 1241280, 'steps': 6464, 'loss/train': 1.1791571378707886} 08/30/2021 14:20:47 - INFO - __main__ - Step 6466: {'lr': 0.0004988779708866714, 'samples': 1241472, 'steps': 6465, 'loss/train': 2.0136468410491943} 08/30/2021 14:20:47 - INFO - __main__ - Step 6467: {'lr': 0.0004988774686182564, 'samples': 1241664, 'steps': 6466, 'loss/train': 1.6396267414093018} 08/30/2021 14:20:49 - INFO - __main__ - Step 6468: {'lr': 0.0004988769662377013, 'samples': 1241856, 'steps': 6467, 'loss/train': 1.455800175666809} 08/30/2021 14:20:49 - INFO - __main__ - Step 6469: {'lr': 0.0004988764637450058, 'samples': 1242048, 'steps': 6468, 'loss/train': 2.1185052394866943} 08/30/2021 14:20:50 - INFO - __main__ - Step 6470: {'lr': 0.0004988759611401706, 'samples': 1242240, 'steps': 6469, 'loss/train': 1.7665050029754639} 08/30/2021 14:20:50 - INFO - __main__ - Step 6471: {'lr': 0.0004988754584231957, 'samples': 1242432, 'steps': 6470, 'loss/train': 1.9007976055145264} 08/30/2021 14:20:50 - INFO - __main__ - Step 6472: {'lr': 0.0004988749555940814, 'samples': 1242624, 'steps': 6471, 'loss/train': 2.1194381713867188} 08/30/2021 14:20:53 - INFO - __main__ - Step 6473: {'lr': 0.0004988744526528277, 'samples': 1242816, 'steps': 6472, 'loss/train': 2.066175937652588} 08/30/2021 14:20:53 - INFO - __main__ - Step 6474: {'lr': 0.0004988739495994352, 'samples': 1243008, 'steps': 6473, 'loss/train': 1.561000943183899} 08/30/2021 14:20:54 - INFO - __main__ - Step 6475: {'lr': 0.0004988734464339038, 'samples': 1243200, 'steps': 6474, 'loss/train': 1.8860431909561157} 08/30/2021 14:20:54 - INFO - __main__ - Step 6476: {'lr': 0.0004988729431562339, 'samples': 1243392, 'steps': 6475, 'loss/train': 2.3497374057769775} 08/30/2021 14:20:54 - INFO - __main__ - Step 6477: {'lr': 0.0004988724397664258, 'samples': 1243584, 'steps': 6476, 'loss/train': 1.6888527870178223} 08/30/2021 14:20:55 - INFO - __main__ - Step 6478: {'lr': 0.0004988719362644795, 'samples': 1243776, 'steps': 6477, 'loss/train': 0.6262373924255371} 08/30/2021 14:20:57 - INFO - __main__ - Step 6479: {'lr': 0.0004988714326503953, 'samples': 1243968, 'steps': 6478, 'loss/train': 2.5752835273742676} 08/30/2021 14:20:57 - INFO - __main__ - Step 6480: {'lr': 0.0004988709289241736, 'samples': 1244160, 'steps': 6479, 'loss/train': 0.6004495024681091} 08/30/2021 14:20:57 - INFO - __main__ - Step 6481: {'lr': 0.0004988704250858145, 'samples': 1244352, 'steps': 6480, 'loss/train': 0.6630047559738159} 08/30/2021 14:20:58 - INFO - __main__ - Step 6482: {'lr': 0.0004988699211353182, 'samples': 1244544, 'steps': 6481, 'loss/train': 2.088484764099121} 08/30/2021 14:20:58 - INFO - __main__ - Step 6483: {'lr': 0.000498869417072685, 'samples': 1244736, 'steps': 6482, 'loss/train': 1.8390841484069824} 08/30/2021 14:20:58 - INFO - __main__ - Step 6484: {'lr': 0.000498868912897915, 'samples': 1244928, 'steps': 6483, 'loss/train': 2.163666248321533} 08/30/2021 14:21:00 - INFO - __main__ - Step 6485: {'lr': 0.0004988684086110085, 'samples': 1245120, 'steps': 6484, 'loss/train': 0.8672804832458496} 08/30/2021 14:21:00 - INFO - __main__ - Step 6486: {'lr': 0.0004988679042119658, 'samples': 1245312, 'steps': 6485, 'loss/train': 1.329594373703003} 08/30/2021 14:21:01 - INFO - __main__ - Step 6487: {'lr': 0.000498867399700787, 'samples': 1245504, 'steps': 6486, 'loss/train': 1.6521679162979126} 08/30/2021 14:21:01 - INFO - __main__ - Step 6488: {'lr': 0.0004988668950774724, 'samples': 1245696, 'steps': 6487, 'loss/train': 2.360351800918579} 08/30/2021 14:21:01 - INFO - __main__ - Step 6489: {'lr': 0.0004988663903420222, 'samples': 1245888, 'steps': 6488, 'loss/train': 1.4756020307540894} 08/30/2021 14:21:02 - INFO - __main__ - Step 6490: {'lr': 0.0004988658854944367, 'samples': 1246080, 'steps': 6489, 'loss/train': 2.232346773147583} 08/30/2021 14:21:04 - INFO - __main__ - Step 6491: {'lr': 0.0004988653805347161, 'samples': 1246272, 'steps': 6490, 'loss/train': 2.4621121883392334} 08/30/2021 14:21:04 - INFO - __main__ - Step 6492: {'lr': 0.0004988648754628605, 'samples': 1246464, 'steps': 6491, 'loss/train': 2.4820644855499268} 08/30/2021 14:21:05 - INFO - __main__ - Step 6493: {'lr': 0.0004988643702788703, 'samples': 1246656, 'steps': 6492, 'loss/train': 0.569169282913208} 08/30/2021 14:21:05 - INFO - __main__ - Step 6494: {'lr': 0.0004988638649827456, 'samples': 1246848, 'steps': 6493, 'loss/train': 2.4743144512176514} 08/30/2021 14:21:05 - INFO - __main__ - Step 6495: {'lr': 0.0004988633595744867, 'samples': 1247040, 'steps': 6494, 'loss/train': 2.5574920177459717} 08/30/2021 14:21:07 - INFO - __main__ - Step 6496: {'lr': 0.0004988628540540939, 'samples': 1247232, 'steps': 6495, 'loss/train': 0.23879817128181458} 08/30/2021 14:21:08 - INFO - __main__ - Step 6497: {'lr': 0.0004988623484215673, 'samples': 1247424, 'steps': 6496, 'loss/train': 2.619365692138672} 08/30/2021 14:21:08 - INFO - __main__ - Step 6498: {'lr': 0.0004988618426769071, 'samples': 1247616, 'steps': 6497, 'loss/train': 4.272124767303467} 08/30/2021 14:21:08 - INFO - __main__ - Step 6499: {'lr': 0.0004988613368201135, 'samples': 1247808, 'steps': 6498, 'loss/train': 1.8268860578536987} 08/30/2021 14:21:09 - INFO - __main__ - Step 6500: {'lr': 0.0004988608308511871, 'samples': 1248000, 'steps': 6499, 'loss/train': 1.9207829236984253} 08/30/2021 14:21:09 - INFO - __main__ - Step 6501: {'lr': 0.0004988603247701276, 'samples': 1248192, 'steps': 6500, 'loss/train': 2.391490936279297} 08/30/2021 14:21:10 - INFO - __main__ - Step 6502: {'lr': 0.0004988598185769357, 'samples': 1248384, 'steps': 6501, 'loss/train': 2.5124106407165527} 08/30/2021 14:21:11 - INFO - __main__ - Step 6503: {'lr': 0.0004988593122716112, 'samples': 1248576, 'steps': 6502, 'loss/train': 2.56439208984375} 08/30/2021 14:21:12 - INFO - __main__ - Step 6504: {'lr': 0.0004988588058541547, 'samples': 1248768, 'steps': 6503, 'loss/train': 1.1140613555908203} 08/30/2021 14:21:12 - INFO - __main__ - Step 6505: {'lr': 0.0004988582993245661, 'samples': 1248960, 'steps': 6504, 'loss/train': 2.11283540725708} 08/30/2021 14:21:12 - INFO - __main__ - Step 6506: {'lr': 0.0004988577926828459, 'samples': 1249152, 'steps': 6505, 'loss/train': 2.564568042755127} 08/30/2021 14:21:13 - INFO - __main__ - Step 6507: {'lr': 0.0004988572859289941, 'samples': 1249344, 'steps': 6506, 'loss/train': 2.540116310119629} 08/30/2021 14:21:14 - INFO - __main__ - Step 6508: {'lr': 0.0004988567790630111, 'samples': 1249536, 'steps': 6507, 'loss/train': 1.8360543251037598} 08/30/2021 14:21:15 - INFO - __main__ - Step 6509: {'lr': 0.0004988562720848973, 'samples': 1249728, 'steps': 6508, 'loss/train': 1.8385865688323975} 08/30/2021 14:21:15 - INFO - __main__ - Step 6510: {'lr': 0.0004988557649946525, 'samples': 1249920, 'steps': 6509, 'loss/train': 2.23394513130188} 08/30/2021 14:21:15 - INFO - __main__ - Step 6511: {'lr': 0.000498855257792277, 'samples': 1250112, 'steps': 6510, 'loss/train': 2.1976659297943115} 08/30/2021 14:21:16 - INFO - __main__ - Step 6512: {'lr': 0.0004988547504777714, 'samples': 1250304, 'steps': 6511, 'loss/train': 2.638313055038452} 08/30/2021 14:21:17 - INFO - __main__ - Step 6513: {'lr': 0.0004988542430511356, 'samples': 1250496, 'steps': 6512, 'loss/train': 1.8395999670028687} 08/30/2021 14:21:18 - INFO - __main__ - Step 6514: {'lr': 0.0004988537355123699, 'samples': 1250688, 'steps': 6513, 'loss/train': 1.7342604398727417} 08/30/2021 14:21:18 - INFO - __main__ - Step 6515: {'lr': 0.0004988532278614745, 'samples': 1250880, 'steps': 6514, 'loss/train': 1.4590171575546265} 08/30/2021 14:21:18 - INFO - __main__ - Step 6516: {'lr': 0.0004988527200984498, 'samples': 1251072, 'steps': 6515, 'loss/train': 2.354767084121704} 08/30/2021 14:21:19 - INFO - __main__ - Step 6517: {'lr': 0.0004988522122232958, 'samples': 1251264, 'steps': 6516, 'loss/train': 1.9950506687164307} 08/30/2021 14:21:20 - INFO - __main__ - Step 6518: {'lr': 0.0004988517042360128, 'samples': 1251456, 'steps': 6517, 'loss/train': 2.5752596855163574} 08/30/2021 14:21:21 - INFO - __main__ - Step 6519: {'lr': 0.0004988511961366012, 'samples': 1251648, 'steps': 6518, 'loss/train': 1.9904118776321411} 08/30/2021 14:21:21 - INFO - __main__ - Step 6520: {'lr': 0.000498850687925061, 'samples': 1251840, 'steps': 6519, 'loss/train': 2.0929312705993652} 08/30/2021 14:21:22 - INFO - __main__ - Step 6521: {'lr': 0.0004988501796013926, 'samples': 1252032, 'steps': 6520, 'loss/train': 1.6906882524490356} 08/30/2021 14:21:22 - INFO - __main__ - Step 6522: {'lr': 0.0004988496711655961, 'samples': 1252224, 'steps': 6521, 'loss/train': 2.0665812492370605} 08/30/2021 14:21:23 - INFO - __main__ - Step 6523: {'lr': 0.0004988491626176718, 'samples': 1252416, 'steps': 6522, 'loss/train': 1.7329615354537964} 08/30/2021 14:21:24 - INFO - __main__ - Step 6524: {'lr': 0.0004988486539576198, 'samples': 1252608, 'steps': 6523, 'loss/train': 1.7640632390975952} 08/30/2021 14:21:24 - INFO - __main__ - Step 6525: {'lr': 0.0004988481451854406, 'samples': 1252800, 'steps': 6524, 'loss/train': 1.9644182920455933} 08/30/2021 14:21:24 - INFO - __main__ - Step 6526: {'lr': 0.0004988476363011341, 'samples': 1252992, 'steps': 6525, 'loss/train': 2.612196922302246} 08/30/2021 14:21:25 - INFO - __main__ - Step 6527: {'lr': 0.0004988471273047008, 'samples': 1253184, 'steps': 6526, 'loss/train': 2.3033361434936523} 08/30/2021 14:21:27 - INFO - __main__ - Step 6528: {'lr': 0.0004988466181961408, 'samples': 1253376, 'steps': 6527, 'loss/train': 1.3639360666275024} 08/30/2021 14:21:27 - INFO - __main__ - Step 6529: {'lr': 0.0004988461089754544, 'samples': 1253568, 'steps': 6528, 'loss/train': 0.4032314121723175} 08/30/2021 14:21:28 - INFO - __main__ - Step 6530: {'lr': 0.0004988455996426418, 'samples': 1253760, 'steps': 6529, 'loss/train': 2.104724168777466} 08/30/2021 14:21:28 - INFO - __main__ - Step 6531: {'lr': 0.0004988450901977031, 'samples': 1253952, 'steps': 6530, 'loss/train': 2.3243253231048584} 08/30/2021 14:21:28 - INFO - __main__ - Step 6532: {'lr': 0.0004988445806406387, 'samples': 1254144, 'steps': 6531, 'loss/train': 2.694326639175415} 08/30/2021 14:21:30 - INFO - __main__ - Step 6533: {'lr': 0.0004988440709714487, 'samples': 1254336, 'steps': 6532, 'loss/train': 2.872575521469116} 08/30/2021 14:21:31 - INFO - __main__ - Step 6534: {'lr': 0.0004988435611901335, 'samples': 1254528, 'steps': 6533, 'loss/train': 2.5049407482147217} 08/30/2021 14:21:31 - INFO - __main__ - Step 6535: {'lr': 0.0004988430512966932, 'samples': 1254720, 'steps': 6534, 'loss/train': 2.041015625} 08/30/2021 14:21:32 - INFO - __main__ - Step 6536: {'lr': 0.000498842541291128, 'samples': 1254912, 'steps': 6535, 'loss/train': 1.6580395698547363} 08/30/2021 14:21:32 - INFO - __main__ - Step 6537: {'lr': 0.0004988420311734383, 'samples': 1255104, 'steps': 6536, 'loss/train': 1.8963825702667236} 08/30/2021 14:21:32 - INFO - __main__ - Step 6538: {'lr': 0.0004988415209436243, 'samples': 1255296, 'steps': 6537, 'loss/train': 1.7755156755447388} 08/30/2021 14:21:33 - INFO - __main__ - Step 6539: {'lr': 0.000498841010601686, 'samples': 1255488, 'steps': 6538, 'loss/train': 0.5022989511489868} 08/30/2021 14:21:34 - INFO - __main__ - Step 6540: {'lr': 0.0004988405001476237, 'samples': 1255680, 'steps': 6539, 'loss/train': 0.5564445853233337} 08/30/2021 14:21:35 - INFO - __main__ - Step 6541: {'lr': 0.0004988399895814378, 'samples': 1255872, 'steps': 6540, 'loss/train': 1.9793373346328735} 08/30/2021 14:21:35 - INFO - __main__ - Step 6542: {'lr': 0.0004988394789031286, 'samples': 1256064, 'steps': 6541, 'loss/train': 1.841233491897583} 08/30/2021 14:21:35 - INFO - __main__ - Step 6543: {'lr': 0.000498838968112696, 'samples': 1256256, 'steps': 6542, 'loss/train': 1.683853030204773} 08/30/2021 14:21:36 - INFO - __main__ - Step 6544: {'lr': 0.0004988384572101403, 'samples': 1256448, 'steps': 6543, 'loss/train': 1.94686758518219} 08/30/2021 14:21:37 - INFO - __main__ - Step 6545: {'lr': 0.000498837946195462, 'samples': 1256640, 'steps': 6544, 'loss/train': 1.6687226295471191} 08/30/2021 14:21:38 - INFO - __main__ - Step 6546: {'lr': 0.0004988374350686611, 'samples': 1256832, 'steps': 6545, 'loss/train': 1.9942381381988525} 08/30/2021 14:21:38 - INFO - __main__ - Step 6547: {'lr': 0.000498836923829738, 'samples': 1257024, 'steps': 6546, 'loss/train': 1.8168758153915405} 08/30/2021 14:21:38 - INFO - __main__ - Step 6548: {'lr': 0.0004988364124786927, 'samples': 1257216, 'steps': 6547, 'loss/train': 1.0306893587112427} 08/30/2021 14:21:39 - INFO - __main__ - Step 6549: {'lr': 0.0004988359010155255, 'samples': 1257408, 'steps': 6548, 'loss/train': 1.4069682359695435} 08/30/2021 14:21:40 - INFO - __main__ - Step 6550: {'lr': 0.0004988353894402368, 'samples': 1257600, 'steps': 6549, 'loss/train': 2.189601421356201} 08/30/2021 14:21:41 - INFO - __main__ - Step 6551: {'lr': 0.0004988348777528267, 'samples': 1257792, 'steps': 6550, 'loss/train': 1.8493245840072632} 08/30/2021 14:21:41 - INFO - __main__ - Step 6552: {'lr': 0.0004988343659532954, 'samples': 1257984, 'steps': 6551, 'loss/train': 1.8024691343307495} 08/30/2021 14:21:41 - INFO - __main__ - Step 6553: {'lr': 0.0004988338540416432, 'samples': 1258176, 'steps': 6552, 'loss/train': 1.883184790611267} 08/30/2021 14:21:42 - INFO - __main__ - Step 6554: {'lr': 0.0004988333420178704, 'samples': 1258368, 'steps': 6553, 'loss/train': 2.450090169906616} 08/30/2021 14:21:43 - INFO - __main__ - Step 6555: {'lr': 0.000498832829881977, 'samples': 1258560, 'steps': 6554, 'loss/train': 1.9142794609069824} 08/30/2021 14:21:44 - INFO - __main__ - Step 6556: {'lr': 0.0004988323176339633, 'samples': 1258752, 'steps': 6555, 'loss/train': 2.114475965499878} 08/30/2021 14:21:44 - INFO - __main__ - Step 6557: {'lr': 0.0004988318052738298, 'samples': 1258944, 'steps': 6556, 'loss/train': 1.1729118824005127} 08/30/2021 14:21:44 - INFO - __main__ - Step 6558: {'lr': 0.0004988312928015763, 'samples': 1259136, 'steps': 6557, 'loss/train': 0.6530615091323853} 08/30/2021 14:21:45 - INFO - __main__ - Step 6559: {'lr': 0.0004988307802172035, 'samples': 1259328, 'steps': 6558, 'loss/train': 1.4921109676361084} 08/30/2021 14:21:46 - INFO - __main__ - Step 6560: {'lr': 0.0004988302675207112, 'samples': 1259520, 'steps': 6559, 'loss/train': 2.1001718044281006} 08/30/2021 14:21:47 - INFO - __main__ - Step 6561: {'lr': 0.0004988297547121, 'samples': 1259712, 'steps': 6560, 'loss/train': 1.6432491540908813} 08/30/2021 14:21:47 - INFO - __main__ - Step 6562: {'lr': 0.0004988292417913698, 'samples': 1259904, 'steps': 6561, 'loss/train': 1.8221440315246582} 08/30/2021 14:21:48 - INFO - __main__ - Step 6563: {'lr': 0.0004988287287585211, 'samples': 1260096, 'steps': 6562, 'loss/train': 0.19723446667194366} 08/30/2021 14:21:48 - INFO - __main__ - Step 6564: {'lr': 0.0004988282156135539, 'samples': 1260288, 'steps': 6563, 'loss/train': 2.1554503440856934} 08/30/2021 14:21:50 - INFO - __main__ - Step 6565: {'lr': 0.0004988277023564685, 'samples': 1260480, 'steps': 6564, 'loss/train': 1.8825099468231201} 08/30/2021 14:21:50 - INFO - __main__ - Step 6566: {'lr': 0.0004988271889872654, 'samples': 1260672, 'steps': 6565, 'loss/train': 2.1260039806365967} 08/30/2021 14:21:50 - INFO - __main__ - Step 6567: {'lr': 0.0004988266755059444, 'samples': 1260864, 'steps': 6566, 'loss/train': 0.2590658664703369} 08/30/2021 14:21:51 - INFO - __main__ - Step 6568: {'lr': 0.000498826161912506, 'samples': 1261056, 'steps': 6567, 'loss/train': 1.3511930704116821} 08/30/2021 14:21:51 - INFO - __main__ - Step 6569: {'lr': 0.0004988256482069505, 'samples': 1261248, 'steps': 6568, 'loss/train': 1.351592779159546} 08/30/2021 14:21:51 - INFO - __main__ - Step 6570: {'lr': 0.0004988251343892779, 'samples': 1261440, 'steps': 6569, 'loss/train': 0.2593085467815399} 08/30/2021 14:21:53 - INFO - __main__ - Step 6571: {'lr': 0.0004988246204594885, 'samples': 1261632, 'steps': 6570, 'loss/train': 2.4204938411712646} 08/30/2021 14:21:54 - INFO - __main__ - Step 6572: {'lr': 0.0004988241064175826, 'samples': 1261824, 'steps': 6571, 'loss/train': 2.4856679439544678} 08/30/2021 14:21:54 - INFO - __main__ - Step 6573: {'lr': 0.0004988235922635604, 'samples': 1262016, 'steps': 6572, 'loss/train': 2.4744157791137695} 08/30/2021 14:21:54 - INFO - __main__ - Step 6574: {'lr': 0.0004988230779974221, 'samples': 1262208, 'steps': 6573, 'loss/train': 1.8752230405807495} 08/30/2021 14:21:55 - INFO - __main__ - Step 6575: {'lr': 0.000498822563619168, 'samples': 1262400, 'steps': 6574, 'loss/train': 1.711130976676941} 08/30/2021 14:21:57 - INFO - __main__ - Step 6576: {'lr': 0.0004988220491287983, 'samples': 1262592, 'steps': 6575, 'loss/train': 0.5284066200256348} 08/30/2021 14:21:57 - INFO - __main__ - Step 6577: {'lr': 0.0004988215345263132, 'samples': 1262784, 'steps': 6576, 'loss/train': 1.5665788650512695} 08/30/2021 14:21:57 - INFO - __main__ - Step 6578: {'lr': 0.0004988210198117129, 'samples': 1262976, 'steps': 6577, 'loss/train': 1.9515835046768188} 08/30/2021 14:21:58 - INFO - __main__ - Step 6579: {'lr': 0.0004988205049849978, 'samples': 1263168, 'steps': 6578, 'loss/train': 2.016845703125} 08/30/2021 14:21:58 - INFO - __main__ - Step 6580: {'lr': 0.0004988199900461679, 'samples': 1263360, 'steps': 6579, 'loss/train': 2.2204203605651855} 08/30/2021 14:22:00 - INFO - __main__ - Step 6581: {'lr': 0.0004988194749952237, 'samples': 1263552, 'steps': 6580, 'loss/train': 1.7538809776306152} 08/30/2021 14:22:01 - INFO - __main__ - Step 6582: {'lr': 0.0004988189598321652, 'samples': 1263744, 'steps': 6581, 'loss/train': 2.3705499172210693} 08/30/2021 14:22:01 - INFO - __main__ - Step 6583: {'lr': 0.0004988184445569926, 'samples': 1263936, 'steps': 6582, 'loss/train': 1.9933667182922363} 08/30/2021 14:22:01 - INFO - __main__ - Step 6584: {'lr': 0.0004988179291697064, 'samples': 1264128, 'steps': 6583, 'loss/train': 1.7881734371185303} 08/30/2021 14:22:02 - INFO - __main__ - Step 6585: {'lr': 0.0004988174136703066, 'samples': 1264320, 'steps': 6584, 'loss/train': 2.433642864227295} 08/30/2021 14:22:02 - INFO - __main__ - Step 6586: {'lr': 0.0004988168980587936, 'samples': 1264512, 'steps': 6585, 'loss/train': 1.5064575672149658} 08/30/2021 14:22:04 - INFO - __main__ - Step 6587: {'lr': 0.0004988163823351676, 'samples': 1264704, 'steps': 6586, 'loss/train': 1.5597121715545654} 08/30/2021 14:22:04 - INFO - __main__ - Step 6588: {'lr': 0.0004988158664994286, 'samples': 1264896, 'steps': 6587, 'loss/train': 1.962697982788086} 08/30/2021 14:22:05 - INFO - __main__ - Step 6589: {'lr': 0.0004988153505515771, 'samples': 1265088, 'steps': 6588, 'loss/train': 1.6837493181228638} 08/30/2021 14:22:05 - INFO - __main__ - Step 6590: {'lr': 0.0004988148344916133, 'samples': 1265280, 'steps': 6589, 'loss/train': 2.305677890777588} 08/30/2021 14:22:05 - INFO - __main__ - Step 6591: {'lr': 0.0004988143183195373, 'samples': 1265472, 'steps': 6590, 'loss/train': 1.7598168849945068} 08/30/2021 14:22:07 - INFO - __main__ - Step 6592: {'lr': 0.0004988138020353493, 'samples': 1265664, 'steps': 6591, 'loss/train': 1.722815990447998} 08/30/2021 14:22:07 - INFO - __main__ - Step 6593: {'lr': 0.0004988132856390498, 'samples': 1265856, 'steps': 6592, 'loss/train': 2.120572328567505} 08/30/2021 14:22:07 - INFO - __main__ - Step 6594: {'lr': 0.0004988127691306388, 'samples': 1266048, 'steps': 6593, 'loss/train': 2.207150459289551} 08/30/2021 14:22:08 - INFO - __main__ - Step 6595: {'lr': 0.0004988122525101166, 'samples': 1266240, 'steps': 6594, 'loss/train': 1.9245821237564087} 08/30/2021 14:22:08 - INFO - __main__ - Step 6596: {'lr': 0.0004988117357774835, 'samples': 1266432, 'steps': 6595, 'loss/train': 2.0989673137664795} 08/30/2021 14:22:09 - INFO - __main__ - Step 6597: {'lr': 0.0004988112189327397, 'samples': 1266624, 'steps': 6596, 'loss/train': 2.10762882232666} 08/30/2021 14:22:10 - INFO - __main__ - Step 6598: {'lr': 0.0004988107019758853, 'samples': 1266816, 'steps': 6597, 'loss/train': 2.0031373500823975} 08/30/2021 14:22:10 - INFO - __main__ - Step 6599: {'lr': 0.0004988101849069208, 'samples': 1267008, 'steps': 6598, 'loss/train': 2.4327340126037598} 08/30/2021 14:22:11 - INFO - __main__ - Step 6600: {'lr': 0.0004988096677258461, 'samples': 1267200, 'steps': 6599, 'loss/train': 0.5378065705299377} 08/30/2021 14:22:11 - INFO - __main__ - Step 6601: {'lr': 0.0004988091504326616, 'samples': 1267392, 'steps': 6600, 'loss/train': 2.8171443939208984} 08/30/2021 14:22:12 - INFO - __main__ - Step 6602: {'lr': 0.0004988086330273676, 'samples': 1267584, 'steps': 6601, 'loss/train': 0.8903299570083618} 08/30/2021 14:22:13 - INFO - __main__ - Step 6603: {'lr': 0.0004988081155099643, 'samples': 1267776, 'steps': 6602, 'loss/train': 2.2301132678985596} 08/30/2021 14:22:13 - INFO - __main__ - Step 6604: {'lr': 0.0004988075978804518, 'samples': 1267968, 'steps': 6603, 'loss/train': 2.353480815887451} 08/30/2021 14:22:14 - INFO - __main__ - Step 6605: {'lr': 0.0004988070801388306, 'samples': 1268160, 'steps': 6604, 'loss/train': 2.3417277336120605} 08/30/2021 14:22:14 - INFO - __main__ - Step 6606: {'lr': 0.0004988065622851006, 'samples': 1268352, 'steps': 6605, 'loss/train': 2.152053117752075} 08/30/2021 14:22:14 - INFO - __main__ - Step 6607: {'lr': 0.0004988060443192623, 'samples': 1268544, 'steps': 6606, 'loss/train': 1.458253264427185} 08/30/2021 14:22:16 - INFO - __main__ - Step 6608: {'lr': 0.0004988055262413158, 'samples': 1268736, 'steps': 6607, 'loss/train': 2.4444892406463623} 08/30/2021 14:22:16 - INFO - __main__ - Step 6609: {'lr': 0.0004988050080512614, 'samples': 1268928, 'steps': 6608, 'loss/train': 2.097615957260132} 08/30/2021 14:22:17 - INFO - __main__ - Step 6610: {'lr': 0.0004988044897490993, 'samples': 1269120, 'steps': 6609, 'loss/train': 1.5639092922210693} 08/30/2021 14:22:17 - INFO - __main__ - Step 6611: {'lr': 0.0004988039713348297, 'samples': 1269312, 'steps': 6610, 'loss/train': 1.8592551946640015} 08/30/2021 14:22:17 - INFO - __main__ - Step 6612: {'lr': 0.0004988034528084529, 'samples': 1269504, 'steps': 6611, 'loss/train': 2.4343392848968506} 08/30/2021 14:22:19 - INFO - __main__ - Step 6613: {'lr': 0.000498802934169969, 'samples': 1269696, 'steps': 6612, 'loss/train': 1.7656254768371582} 08/30/2021 14:22:20 - INFO - __main__ - Step 6614: {'lr': 0.0004988024154193785, 'samples': 1269888, 'steps': 6613, 'loss/train': 2.0158333778381348} 08/30/2021 14:22:20 - INFO - __main__ - Step 6615: {'lr': 0.0004988018965566814, 'samples': 1270080, 'steps': 6614, 'loss/train': 2.1076645851135254} 08/30/2021 14:22:20 - INFO - __main__ - Step 6616: {'lr': 0.000498801377581878, 'samples': 1270272, 'steps': 6615, 'loss/train': 2.292289972305298} 08/30/2021 14:22:21 - INFO - __main__ - Step 6617: {'lr': 0.0004988008584949686, 'samples': 1270464, 'steps': 6616, 'loss/train': 2.0487987995147705} 08/30/2021 14:22:21 - INFO - __main__ - Step 6618: {'lr': 0.0004988003392959533, 'samples': 1270656, 'steps': 6617, 'loss/train': 1.718287706375122} 08/30/2021 14:22:23 - INFO - __main__ - Step 6619: {'lr': 0.0004987998199848324, 'samples': 1270848, 'steps': 6618, 'loss/train': 4.278743267059326} 08/30/2021 14:22:23 - INFO - __main__ - Step 6620: {'lr': 0.0004987993005616061, 'samples': 1271040, 'steps': 6619, 'loss/train': 2.775883197784424} 08/30/2021 14:22:23 - INFO - __main__ - Step 6621: {'lr': 0.0004987987810262747, 'samples': 1271232, 'steps': 6620, 'loss/train': 4.488855361938477} 08/30/2021 14:22:24 - INFO - __main__ - Step 6622: {'lr': 0.0004987982613788384, 'samples': 1271424, 'steps': 6621, 'loss/train': 2.5627167224884033} 08/30/2021 14:22:24 - INFO - __main__ - Step 6623: {'lr': 0.0004987977416192976, 'samples': 1271616, 'steps': 6622, 'loss/train': 2.950546979904175} 08/30/2021 14:22:26 - INFO - __main__ - Step 6624: {'lr': 0.0004987972217476523, 'samples': 1271808, 'steps': 6623, 'loss/train': 3.310699701309204} 08/30/2021 14:22:26 - INFO - __main__ - Step 6625: {'lr': 0.0004987967017639027, 'samples': 1272000, 'steps': 6624, 'loss/train': 2.5881409645080566} 08/30/2021 14:22:26 - INFO - __main__ - Step 6626: {'lr': 0.0004987961816680492, 'samples': 1272192, 'steps': 6625, 'loss/train': 1.8328700065612793} 08/30/2021 14:22:27 - INFO - __main__ - Step 6627: {'lr': 0.000498795661460092, 'samples': 1272384, 'steps': 6626, 'loss/train': 2.1922333240509033} 08/30/2021 14:22:27 - INFO - __main__ - Step 6628: {'lr': 0.0004987951411400313, 'samples': 1272576, 'steps': 6627, 'loss/train': 2.490633726119995} 08/30/2021 14:22:29 - INFO - __main__ - Step 6629: {'lr': 0.0004987946207078674, 'samples': 1272768, 'steps': 6628, 'loss/train': 2.7946274280548096} 08/30/2021 14:22:29 - INFO - __main__ - Step 6630: {'lr': 0.0004987941001636004, 'samples': 1272960, 'steps': 6629, 'loss/train': 1.7833830118179321} 08/30/2021 14:22:29 - INFO - __main__ - Step 6631: {'lr': 0.0004987935795072307, 'samples': 1273152, 'steps': 6630, 'loss/train': 2.3059895038604736} 08/30/2021 14:22:30 - INFO - __main__ - Step 6632: {'lr': 0.0004987930587387584, 'samples': 1273344, 'steps': 6631, 'loss/train': 2.5678598880767822} 08/30/2021 14:22:30 - INFO - __main__ - Step 6633: {'lr': 0.0004987925378581838, 'samples': 1273536, 'steps': 6632, 'loss/train': 2.6430764198303223} 08/30/2021 14:22:30 - INFO - __main__ - Step 6634: {'lr': 0.0004987920168655071, 'samples': 1273728, 'steps': 6633, 'loss/train': 2.5122742652893066} 08/30/2021 14:22:32 - INFO - __main__ - Step 6635: {'lr': 0.0004987914957607286, 'samples': 1273920, 'steps': 6634, 'loss/train': 2.150352954864502} 08/30/2021 14:22:33 - INFO - __main__ - Step 6636: {'lr': 0.0004987909745438484, 'samples': 1274112, 'steps': 6635, 'loss/train': 2.924222707748413} 08/30/2021 14:22:33 - INFO - __main__ - Step 6637: {'lr': 0.000498790453214867, 'samples': 1274304, 'steps': 6636, 'loss/train': 2.5753657817840576} 08/30/2021 14:22:33 - INFO - __main__ - Step 6638: {'lr': 0.0004987899317737843, 'samples': 1274496, 'steps': 6637, 'loss/train': 0.3753221929073334} 08/30/2021 14:22:34 - INFO - __main__ - Step 6639: {'lr': 0.0004987894102206008, 'samples': 1274688, 'steps': 6638, 'loss/train': 2.109752655029297} 08/30/2021 14:22:36 - INFO - __main__ - Step 6640: {'lr': 0.0004987888885553166, 'samples': 1274880, 'steps': 6639, 'loss/train': 2.4767367839813232} 08/30/2021 14:22:36 - INFO - __main__ - Step 6641: {'lr': 0.0004987883667779319, 'samples': 1275072, 'steps': 6640, 'loss/train': 1.2963693141937256} 08/30/2021 14:22:37 - INFO - __main__ - Step 6642: {'lr': 0.0004987878448884471, 'samples': 1275264, 'steps': 6641, 'loss/train': 2.4667558670043945} 08/30/2021 14:22:37 - INFO - __main__ - Step 6643: {'lr': 0.0004987873228868622, 'samples': 1275456, 'steps': 6642, 'loss/train': 1.9709516763687134} 08/30/2021 14:22:37 - INFO - __main__ - Step 6644: {'lr': 0.0004987868007731778, 'samples': 1275648, 'steps': 6643, 'loss/train': 2.4716739654541016} 08/30/2021 14:22:39 - INFO - __main__ - Step 6645: {'lr': 0.0004987862785473937, 'samples': 1275840, 'steps': 6644, 'loss/train': 2.1465580463409424} 08/30/2021 14:22:39 - INFO - __main__ - Step 6646: {'lr': 0.0004987857562095103, 'samples': 1276032, 'steps': 6645, 'loss/train': 3.1854329109191895} 08/30/2021 14:22:39 - INFO - __main__ - Step 6647: {'lr': 0.0004987852337595281, 'samples': 1276224, 'steps': 6646, 'loss/train': 2.152782917022705} 08/30/2021 14:22:40 - INFO - __main__ - Step 6648: {'lr': 0.0004987847111974469, 'samples': 1276416, 'steps': 6647, 'loss/train': 2.2000057697296143} 08/30/2021 14:22:40 - INFO - __main__ - Step 6649: {'lr': 0.0004987841885232674, 'samples': 1276608, 'steps': 6648, 'loss/train': 2.0557470321655273} 08/30/2021 14:22:42 - INFO - __main__ - Step 6650: {'lr': 0.0004987836657369893, 'samples': 1276800, 'steps': 6649, 'loss/train': 2.4511828422546387} 08/30/2021 14:22:42 - INFO - __main__ - Step 6651: {'lr': 0.0004987831428386133, 'samples': 1276992, 'steps': 6650, 'loss/train': 2.5166261196136475} 08/30/2021 14:22:43 - INFO - __main__ - Step 6652: {'lr': 0.0004987826198281394, 'samples': 1277184, 'steps': 6651, 'loss/train': 1.671008586883545} 08/30/2021 14:22:43 - INFO - __main__ - Step 6653: {'lr': 0.0004987820967055678, 'samples': 1277376, 'steps': 6652, 'loss/train': 2.2135016918182373} 08/30/2021 14:22:43 - INFO - __main__ - Step 6654: {'lr': 0.000498781573470899, 'samples': 1277568, 'steps': 6653, 'loss/train': 2.2522799968719482} 08/30/2021 14:22:44 - INFO - __main__ - Step 6655: {'lr': 0.000498781050124133, 'samples': 1277760, 'steps': 6654, 'loss/train': 2.269852876663208} 08/30/2021 14:22:45 - INFO - __main__ - Step 6656: {'lr': 0.0004987805266652701, 'samples': 1277952, 'steps': 6655, 'loss/train': 0.5961964726448059} 08/30/2021 14:22:46 - INFO - __main__ - Step 6657: {'lr': 0.0004987800030943105, 'samples': 1278144, 'steps': 6656, 'loss/train': 2.3606173992156982} 08/30/2021 14:22:46 - INFO - __main__ - Step 6658: {'lr': 0.0004987794794112545, 'samples': 1278336, 'steps': 6657, 'loss/train': 1.9812132120132446} 08/30/2021 14:22:46 - INFO - __main__ - Step 6659: {'lr': 0.0004987789556161022, 'samples': 1278528, 'steps': 6658, 'loss/train': 2.4071691036224365} 08/30/2021 14:22:47 - INFO - __main__ - Step 6660: {'lr': 0.0004987784317088541, 'samples': 1278720, 'steps': 6659, 'loss/train': 2.365825653076172} 08/30/2021 14:22:48 - INFO - __main__ - Step 6661: {'lr': 0.0004987779076895102, 'samples': 1278912, 'steps': 6660, 'loss/train': 2.412134885787964} 08/30/2021 14:22:48 - INFO - __main__ - Step 6662: {'lr': 0.0004987773835580708, 'samples': 1279104, 'steps': 6661, 'loss/train': 2.232940912246704} 08/30/2021 14:22:49 - INFO - __main__ - Step 6663: {'lr': 0.0004987768593145362, 'samples': 1279296, 'steps': 6662, 'loss/train': 2.327805757522583} 08/30/2021 14:22:49 - INFO - __main__ - Step 6664: {'lr': 0.0004987763349589065, 'samples': 1279488, 'steps': 6663, 'loss/train': 2.547085762023926} 08/30/2021 14:22:50 - INFO - __main__ - Step 6665: {'lr': 0.0004987758104911821, 'samples': 1279680, 'steps': 6664, 'loss/train': 2.1866228580474854} 08/30/2021 14:22:51 - INFO - __main__ - Step 6666: {'lr': 0.0004987752859113631, 'samples': 1279872, 'steps': 6665, 'loss/train': 2.459322929382324} 08/30/2021 14:22:52 - INFO - __main__ - Step 6667: {'lr': 0.0004987747612194499, 'samples': 1280064, 'steps': 6666, 'loss/train': 2.3056182861328125} 08/30/2021 14:22:52 - INFO - __main__ - Step 6668: {'lr': 0.0004987742364154425, 'samples': 1280256, 'steps': 6667, 'loss/train': 1.7542593479156494} 08/30/2021 14:22:52 - INFO - __main__ - Step 6669: {'lr': 0.0004987737114993413, 'samples': 1280448, 'steps': 6668, 'loss/train': 1.9462021589279175} 08/30/2021 14:22:53 - INFO - __main__ - Step 6670: {'lr': 0.0004987731864711466, 'samples': 1280640, 'steps': 6669, 'loss/train': 2.1933953762054443} 08/30/2021 14:22:54 - INFO - __main__ - Step 6671: {'lr': 0.0004987726613308584, 'samples': 1280832, 'steps': 6670, 'loss/train': 0.7411926984786987} 08/30/2021 14:22:55 - INFO - __main__ - Step 6672: {'lr': 0.0004987721360784772, 'samples': 1281024, 'steps': 6671, 'loss/train': 2.0831236839294434} 08/30/2021 14:22:55 - INFO - __main__ - Step 6673: {'lr': 0.0004987716107140031, 'samples': 1281216, 'steps': 6672, 'loss/train': 2.2045445442199707} 08/30/2021 14:22:55 - INFO - __main__ - Step 6674: {'lr': 0.0004987710852374363, 'samples': 1281408, 'steps': 6673, 'loss/train': 1.5553992986679077} 08/30/2021 14:22:56 - INFO - __main__ - Step 6675: {'lr': 0.0004987705596487771, 'samples': 1281600, 'steps': 6674, 'loss/train': 1.3769099712371826} 08/30/2021 14:22:57 - INFO - __main__ - Step 6676: {'lr': 0.0004987700339480258, 'samples': 1281792, 'steps': 6675, 'loss/train': 2.0253024101257324} 08/30/2021 14:22:58 - INFO - __main__ - Step 6677: {'lr': 0.0004987695081351824, 'samples': 1281984, 'steps': 6676, 'loss/train': 1.4973565340042114} 08/30/2021 14:22:58 - INFO - __main__ - Step 6678: {'lr': 0.0004987689822102474, 'samples': 1282176, 'steps': 6677, 'loss/train': 1.3071269989013672} 08/30/2021 14:22:58 - INFO - __main__ - Step 6679: {'lr': 0.000498768456173221, 'samples': 1282368, 'steps': 6678, 'loss/train': 2.8483200073242188} 08/30/2021 14:22:59 - INFO - __main__ - Step 6680: {'lr': 0.0004987679300241033, 'samples': 1282560, 'steps': 6679, 'loss/train': 2.096766233444214} 08/30/2021 14:22:59 - INFO - __main__ - Step 6681: {'lr': 0.0004987674037628945, 'samples': 1282752, 'steps': 6680, 'loss/train': 1.8682585954666138} 08/30/2021 14:23:01 - INFO - __main__ - Step 6682: {'lr': 0.0004987668773895951, 'samples': 1282944, 'steps': 6681, 'loss/train': 2.0440986156463623} 08/30/2021 14:23:01 - INFO - __main__ - Step 6683: {'lr': 0.0004987663509042052, 'samples': 1283136, 'steps': 6682, 'loss/train': 2.422579526901245} 08/30/2021 14:23:02 - INFO - __main__ - Step 6684: {'lr': 0.000498765824306725, 'samples': 1283328, 'steps': 6683, 'loss/train': 1.7745413780212402} 08/30/2021 14:23:02 - INFO - __main__ - Step 6685: {'lr': 0.0004987652975971546, 'samples': 1283520, 'steps': 6684, 'loss/train': 2.5755810737609863} 08/30/2021 14:23:02 - INFO - __main__ - Step 6686: {'lr': 0.0004987647707754945, 'samples': 1283712, 'steps': 6685, 'loss/train': 1.5059664249420166} 08/30/2021 14:23:04 - INFO - __main__ - Step 6687: {'lr': 0.0004987642438417449, 'samples': 1283904, 'steps': 6686, 'loss/train': 0.24417662620544434} 08/30/2021 14:23:04 - INFO - __main__ - Step 6688: {'lr': 0.0004987637167959059, 'samples': 1284096, 'steps': 6687, 'loss/train': 2.0323636531829834} 08/30/2021 14:23:04 - INFO - __main__ - Step 6689: {'lr': 0.0004987631896379779, 'samples': 1284288, 'steps': 6688, 'loss/train': 2.0033011436462402} 08/30/2021 14:23:05 - INFO - __main__ - Step 6690: {'lr': 0.0004987626623679609, 'samples': 1284480, 'steps': 6689, 'loss/train': 2.01468825340271} 08/30/2021 14:23:05 - INFO - __main__ - Step 6691: {'lr': 0.0004987621349858553, 'samples': 1284672, 'steps': 6690, 'loss/train': 2.1882097721099854} 08/30/2021 14:23:07 - INFO - __main__ - Step 6692: {'lr': 0.0004987616074916615, 'samples': 1284864, 'steps': 6691, 'loss/train': 1.3407942056655884} 08/30/2021 14:23:08 - INFO - __main__ - Step 6693: {'lr': 0.0004987610798853794, 'samples': 1285056, 'steps': 6692, 'loss/train': 2.410564661026001} 08/30/2021 14:23:08 - INFO - __main__ - Step 6694: {'lr': 0.0004987605521670094, 'samples': 1285248, 'steps': 6693, 'loss/train': 1.6637507677078247} 08/30/2021 14:23:08 - INFO - __main__ - Step 6695: {'lr': 0.0004987600243365518, 'samples': 1285440, 'steps': 6694, 'loss/train': 2.1286065578460693} 08/30/2021 14:23:09 - INFO - __main__ - Step 6696: {'lr': 0.0004987594963940066, 'samples': 1285632, 'steps': 6695, 'loss/train': 2.305081367492676} 08/30/2021 14:23:11 - INFO - __main__ - Step 6697: {'lr': 0.0004987589683393744, 'samples': 1285824, 'steps': 6696, 'loss/train': 2.856034755706787} 08/30/2021 14:23:11 - INFO - __main__ - Step 6698: {'lr': 0.0004987584401726552, 'samples': 1286016, 'steps': 6697, 'loss/train': 1.4844515323638916} 08/30/2021 14:23:12 - INFO - __main__ - Step 6699: {'lr': 0.0004987579118938492, 'samples': 1286208, 'steps': 6698, 'loss/train': 0.41757792234420776} 08/30/2021 14:23:12 - INFO - __main__ - Step 6700: {'lr': 0.0004987573835029569, 'samples': 1286400, 'steps': 6699, 'loss/train': 1.9921799898147583} 08/30/2021 14:23:12 - INFO - __main__ - Step 6701: {'lr': 0.0004987568549999782, 'samples': 1286592, 'steps': 6700, 'loss/train': 0.9336510300636292} 08/30/2021 14:23:14 - INFO - __main__ - Step 6702: {'lr': 0.0004987563263849136, 'samples': 1286784, 'steps': 6701, 'loss/train': 1.6154801845550537} 08/30/2021 14:23:14 - INFO - __main__ - Step 6703: {'lr': 0.0004987557976577632, 'samples': 1286976, 'steps': 6702, 'loss/train': 2.2903635501861572} 08/30/2021 14:23:15 - INFO - __main__ - Step 6704: {'lr': 0.0004987552688185273, 'samples': 1287168, 'steps': 6703, 'loss/train': 2.2099227905273438} 08/30/2021 14:23:15 - INFO - __main__ - Step 6705: {'lr': 0.0004987547398672061, 'samples': 1287360, 'steps': 6704, 'loss/train': 2.618635892868042} 08/30/2021 14:23:15 - INFO - __main__ - Step 6706: {'lr': 0.0004987542108037998, 'samples': 1287552, 'steps': 6705, 'loss/train': 2.328796625137329} 08/30/2021 14:23:16 - INFO - __main__ - Step 6707: {'lr': 0.0004987536816283087, 'samples': 1287744, 'steps': 6706, 'loss/train': 2.121213436126709} 08/30/2021 14:23:17 - INFO - __main__ - Step 6708: {'lr': 0.0004987531523407331, 'samples': 1287936, 'steps': 6707, 'loss/train': 2.0505807399749756} 08/30/2021 14:23:18 - INFO - __main__ - Step 6709: {'lr': 0.0004987526229410732, 'samples': 1288128, 'steps': 6708, 'loss/train': 2.2908124923706055} 08/30/2021 14:23:18 - INFO - __main__ - Step 6710: {'lr': 0.000498752093429329, 'samples': 1288320, 'steps': 6709, 'loss/train': 1.6176339387893677} 08/30/2021 14:23:19 - INFO - __main__ - Step 6711: {'lr': 0.0004987515638055012, 'samples': 1288512, 'steps': 6710, 'loss/train': 1.9946929216384888} 08/30/2021 14:23:19 - INFO - __main__ - Step 6712: {'lr': 0.0004987510340695896, 'samples': 1288704, 'steps': 6711, 'loss/train': 1.9904903173446655} 08/30/2021 14:23:19 - INFO - __main__ - Step 6713: {'lr': 0.0004987505042215948, 'samples': 1288896, 'steps': 6712, 'loss/train': 0.5952053070068359} 08/30/2021 14:23:21 - INFO - __main__ - Step 6714: {'lr': 0.0004987499742615167, 'samples': 1289088, 'steps': 6713, 'loss/train': 2.0942940711975098} 08/30/2021 14:23:21 - INFO - __main__ - Step 6715: {'lr': 0.0004987494441893557, 'samples': 1289280, 'steps': 6714, 'loss/train': 1.748814582824707} 08/30/2021 14:23:22 - INFO - __main__ - Step 6716: {'lr': 0.0004987489140051121, 'samples': 1289472, 'steps': 6715, 'loss/train': 1.7371820211410522} 08/30/2021 14:23:22 - INFO - __main__ - Step 6717: {'lr': 0.000498748383708786, 'samples': 1289664, 'steps': 6716, 'loss/train': 1.1997138261795044} 08/30/2021 14:23:22 - INFO - __main__ - Step 6718: {'lr': 0.0004987478533003779, 'samples': 1289856, 'steps': 6717, 'loss/train': 1.6917279958724976} 08/30/2021 14:23:24 - INFO - __main__ - Step 6719: {'lr': 0.0004987473227798877, 'samples': 1290048, 'steps': 6718, 'loss/train': 1.7157011032104492} 08/30/2021 14:23:24 - INFO - __main__ - Step 6720: {'lr': 0.0004987467921473157, 'samples': 1290240, 'steps': 6719, 'loss/train': 1.812124490737915} 08/30/2021 14:23:25 - INFO - __main__ - Step 6721: {'lr': 0.0004987462614026624, 'samples': 1290432, 'steps': 6720, 'loss/train': 1.4346495866775513} 08/30/2021 14:23:25 - INFO - __main__ - Step 6722: {'lr': 0.0004987457305459279, 'samples': 1290624, 'steps': 6721, 'loss/train': 0.9984289407730103} 08/30/2021 14:23:26 - INFO - __main__ - Step 6723: {'lr': 0.0004987451995771124, 'samples': 1290816, 'steps': 6722, 'loss/train': 2.1301305294036865} 08/30/2021 14:23:27 - INFO - __main__ - Step 6724: {'lr': 0.000498744668496216, 'samples': 1291008, 'steps': 6723, 'loss/train': 0.3405721187591553} 08/30/2021 14:23:27 - INFO - __main__ - Step 6725: {'lr': 0.0004987441373032393, 'samples': 1291200, 'steps': 6724, 'loss/train': 2.0260512828826904} 08/30/2021 14:23:28 - INFO - __main__ - Step 6726: {'lr': 0.0004987436059981821, 'samples': 1291392, 'steps': 6725, 'loss/train': 2.4161086082458496} 08/30/2021 14:23:28 - INFO - __main__ - Step 6727: {'lr': 0.0004987430745810451, 'samples': 1291584, 'steps': 6726, 'loss/train': 1.8530292510986328} 08/30/2021 14:23:29 - INFO - __main__ - Step 6728: {'lr': 0.0004987425430518282, 'samples': 1291776, 'steps': 6727, 'loss/train': 2.0817573070526123} 08/30/2021 14:23:30 - INFO - __main__ - Step 6729: {'lr': 0.0004987420114105317, 'samples': 1291968, 'steps': 6728, 'loss/train': 2.337291955947876} 08/30/2021 14:23:31 - INFO - __main__ - Step 6730: {'lr': 0.000498741479657156, 'samples': 1292160, 'steps': 6729, 'loss/train': 1.9573829174041748} 08/30/2021 14:23:31 - INFO - __main__ - Step 6731: {'lr': 0.0004987409477917011, 'samples': 1292352, 'steps': 6730, 'loss/train': 2.6872239112854004} 08/30/2021 14:23:31 - INFO - __main__ - Step 6732: {'lr': 0.0004987404158141675, 'samples': 1292544, 'steps': 6731, 'loss/train': 1.9681702852249146} 08/30/2021 14:23:32 - INFO - __main__ - Step 6733: {'lr': 0.0004987398837245552, 'samples': 1292736, 'steps': 6732, 'loss/train': 2.351219415664673} 08/30/2021 14:23:33 - INFO - __main__ - Step 6734: {'lr': 0.0004987393515228646, 'samples': 1292928, 'steps': 6733, 'loss/train': 2.2109556198120117} 08/30/2021 14:23:33 - INFO - __main__ - Step 6735: {'lr': 0.0004987388192090959, 'samples': 1293120, 'steps': 6734, 'loss/train': 2.4044573307037354} 08/30/2021 14:23:34 - INFO - __main__ - Step 6736: {'lr': 0.0004987382867832493, 'samples': 1293312, 'steps': 6735, 'loss/train': 2.394789457321167} 08/30/2021 14:23:34 - INFO - __main__ - Step 6737: {'lr': 0.0004987377542453251, 'samples': 1293504, 'steps': 6736, 'loss/train': 1.1733660697937012} 08/30/2021 14:23:34 - INFO - __main__ - Step 6738: {'lr': 0.0004987372215953234, 'samples': 1293696, 'steps': 6737, 'loss/train': 1.9348593950271606} 08/30/2021 14:23:36 - INFO - __main__ - Step 6739: {'lr': 0.0004987366888332446, 'samples': 1293888, 'steps': 6738, 'loss/train': 1.234695315361023} 08/30/2021 14:23:36 - INFO - __main__ - Step 6740: {'lr': 0.0004987361559590889, 'samples': 1294080, 'steps': 6739, 'loss/train': 2.0923051834106445} 08/30/2021 14:23:37 - INFO - __main__ - Step 6741: {'lr': 0.0004987356229728566, 'samples': 1294272, 'steps': 6740, 'loss/train': 3.1357924938201904} 08/30/2021 14:23:37 - INFO - __main__ - Step 6742: {'lr': 0.0004987350898745477, 'samples': 1294464, 'steps': 6741, 'loss/train': 1.7173526287078857} 08/30/2021 14:23:37 - INFO - __main__ - Step 6743: {'lr': 0.0004987345566641628, 'samples': 1294656, 'steps': 6742, 'loss/train': 1.8840594291687012} 08/30/2021 14:23:38 - INFO - __main__ - Step 6744: {'lr': 0.0004987340233417019, 'samples': 1294848, 'steps': 6743, 'loss/train': 2.293461799621582} 08/30/2021 14:23:39 - INFO - __main__ - Step 6745: {'lr': 0.0004987334899071652, 'samples': 1295040, 'steps': 6744, 'loss/train': 2.139820098876953} 08/30/2021 14:23:40 - INFO - __main__ - Step 6746: {'lr': 0.000498732956360553, 'samples': 1295232, 'steps': 6745, 'loss/train': 1.7622076272964478} 08/30/2021 14:23:40 - INFO - __main__ - Step 6747: {'lr': 0.0004987324227018657, 'samples': 1295424, 'steps': 6746, 'loss/train': 2.011033535003662} 08/30/2021 14:23:41 - INFO - __main__ - Step 6748: {'lr': 0.0004987318889311033, 'samples': 1295616, 'steps': 6747, 'loss/train': 1.996565818786621} 08/30/2021 14:23:41 - INFO - __main__ - Step 6749: {'lr': 0.0004987313550482663, 'samples': 1295808, 'steps': 6748, 'loss/train': 2.0381922721862793} 08/30/2021 14:23:43 - INFO - __main__ - Step 6750: {'lr': 0.0004987308210533546, 'samples': 1296000, 'steps': 6749, 'loss/train': 2.241203784942627} 08/30/2021 14:23:43 - INFO - __main__ - Step 6751: {'lr': 0.0004987302869463686, 'samples': 1296192, 'steps': 6750, 'loss/train': 1.5493972301483154} 08/30/2021 14:23:44 - INFO - __main__ - Step 6752: {'lr': 0.0004987297527273088, 'samples': 1296384, 'steps': 6751, 'loss/train': 1.926452875137329} 08/30/2021 14:23:44 - INFO - __main__ - Step 6753: {'lr': 0.0004987292183961751, 'samples': 1296576, 'steps': 6752, 'loss/train': 2.1413750648498535} 08/30/2021 14:23:45 - INFO - __main__ - Step 6754: {'lr': 0.0004987286839529679, 'samples': 1296768, 'steps': 6753, 'loss/train': 2.2889134883880615} 08/30/2021 14:23:46 - INFO - __main__ - Step 6755: {'lr': 0.0004987281493976873, 'samples': 1296960, 'steps': 6754, 'loss/train': 1.719522476196289} 08/30/2021 14:23:47 - INFO - __main__ - Step 6756: {'lr': 0.0004987276147303337, 'samples': 1297152, 'steps': 6755, 'loss/train': 1.0310285091400146} 08/30/2021 14:23:47 - INFO - __main__ - Step 6757: {'lr': 0.0004987270799509071, 'samples': 1297344, 'steps': 6756, 'loss/train': 1.7240643501281738} 08/30/2021 14:23:47 - INFO - __main__ - Step 6758: {'lr': 0.0004987265450594082, 'samples': 1297536, 'steps': 6757, 'loss/train': 2.399144411087036} 08/30/2021 14:23:48 - INFO - __main__ - Step 6759: {'lr': 0.0004987260100558368, 'samples': 1297728, 'steps': 6758, 'loss/train': 1.979913592338562} 08/30/2021 14:23:48 - INFO - __main__ - Step 6760: {'lr': 0.0004987254749401933, 'samples': 1297920, 'steps': 6759, 'loss/train': 2.0695018768310547} 08/30/2021 14:23:50 - INFO - __main__ - Step 6761: {'lr': 0.000498724939712478, 'samples': 1298112, 'steps': 6760, 'loss/train': 1.8059402704238892} 08/30/2021 14:23:50 - INFO - __main__ - Step 6762: {'lr': 0.000498724404372691, 'samples': 1298304, 'steps': 6761, 'loss/train': 2.115511894226074} 08/30/2021 14:23:51 - INFO - __main__ - Step 6763: {'lr': 0.0004987238689208327, 'samples': 1298496, 'steps': 6762, 'loss/train': 1.4486254453659058} 08/30/2021 14:23:51 - INFO - __main__ - Step 6764: {'lr': 0.0004987233333569031, 'samples': 1298688, 'steps': 6763, 'loss/train': 1.998164415359497} 08/30/2021 14:23:52 - INFO - __main__ - Step 6765: {'lr': 0.0004987227976809028, 'samples': 1298880, 'steps': 6764, 'loss/train': 1.8888225555419922} 08/30/2021 14:23:53 - INFO - __main__ - Step 6766: {'lr': 0.0004987222618928318, 'samples': 1299072, 'steps': 6765, 'loss/train': 2.2598750591278076} 08/30/2021 14:23:54 - INFO - __main__ - Step 6767: {'lr': 0.0004987217259926904, 'samples': 1299264, 'steps': 6766, 'loss/train': 2.020343542098999} 08/30/2021 14:23:54 - INFO - __main__ - Step 6768: {'lr': 0.0004987211899804788, 'samples': 1299456, 'steps': 6767, 'loss/train': 0.40296754240989685} 08/30/2021 14:23:55 - INFO - __main__ - Step 6769: {'lr': 0.0004987206538561972, 'samples': 1299648, 'steps': 6768, 'loss/train': 1.9753944873809814} 08/30/2021 14:23:55 - INFO - __main__ - Step 6770: {'lr': 0.000498720117619846, 'samples': 1299840, 'steps': 6769, 'loss/train': 2.3677124977111816} 08/30/2021 14:23:55 - INFO - __main__ - Step 6771: {'lr': 0.0004987195812714252, 'samples': 1300032, 'steps': 6770, 'loss/train': 2.1042680740356445} 08/30/2021 14:23:57 - INFO - __main__ - Step 6772: {'lr': 0.0004987190448109354, 'samples': 1300224, 'steps': 6771, 'loss/train': 1.5415616035461426} 08/30/2021 14:23:57 - INFO - __main__ - Step 6773: {'lr': 0.0004987185082383765, 'samples': 1300416, 'steps': 6772, 'loss/train': 2.4632744789123535} 08/30/2021 14:23:58 - INFO - __main__ - Step 6774: {'lr': 0.000498717971553749, 'samples': 1300608, 'steps': 6773, 'loss/train': 2.1802873611450195} 08/30/2021 14:23:58 - INFO - __main__ - Step 6775: {'lr': 0.0004987174347570529, 'samples': 1300800, 'steps': 6774, 'loss/train': 2.395963191986084} 08/30/2021 14:23:58 - INFO - __main__ - Step 6776: {'lr': 0.0004987168978482886, 'samples': 1300992, 'steps': 6775, 'loss/train': 0.7819046974182129} 08/30/2021 14:24:00 - INFO - __main__ - Step 6777: {'lr': 0.0004987163608274564, 'samples': 1301184, 'steps': 6776, 'loss/train': 1.1793291568756104} 08/30/2021 14:24:01 - INFO - __main__ - Step 6778: {'lr': 0.0004987158236945563, 'samples': 1301376, 'steps': 6777, 'loss/train': 1.8890621662139893} 08/30/2021 14:24:01 - INFO - __main__ - Step 6779: {'lr': 0.0004987152864495887, 'samples': 1301568, 'steps': 6778, 'loss/train': 1.978233814239502} 08/30/2021 14:24:01 - INFO - __main__ - Step 6780: {'lr': 0.000498714749092554, 'samples': 1301760, 'steps': 6779, 'loss/train': 1.9923200607299805} 08/30/2021 14:24:02 - INFO - __main__ - Step 6781: {'lr': 0.0004987142116234521, 'samples': 1301952, 'steps': 6780, 'loss/train': 2.3988027572631836} 08/30/2021 14:24:02 - INFO - __main__ - Step 6782: {'lr': 0.0004987136740422835, 'samples': 1302144, 'steps': 6781, 'loss/train': 1.3582043647766113} 08/30/2021 14:24:03 - INFO - __main__ - Step 6783: {'lr': 0.0004987131363490483, 'samples': 1302336, 'steps': 6782, 'loss/train': 1.930040717124939} 08/30/2021 14:24:04 - INFO - __main__ - Step 6784: {'lr': 0.0004987125985437468, 'samples': 1302528, 'steps': 6783, 'loss/train': 1.0334081649780273} 08/30/2021 14:24:04 - INFO - __main__ - Step 6785: {'lr': 0.0004987120606263794, 'samples': 1302720, 'steps': 6784, 'loss/train': 1.7500663995742798} 08/30/2021 14:24:05 - INFO - __main__ - Step 6786: {'lr': 0.000498711522596946, 'samples': 1302912, 'steps': 6785, 'loss/train': 0.2875692546367645} 08/30/2021 14:24:05 - INFO - __main__ - Step 6787: {'lr': 0.000498710984455447, 'samples': 1303104, 'steps': 6786, 'loss/train': 1.5875511169433594} 08/30/2021 14:24:07 - INFO - __main__ - Step 6788: {'lr': 0.0004987104462018828, 'samples': 1303296, 'steps': 6787, 'loss/train': 2.2025222778320312} 08/30/2021 14:24:07 - INFO - __main__ - Step 6789: {'lr': 0.0004987099078362534, 'samples': 1303488, 'steps': 6788, 'loss/train': 2.0818910598754883} 08/30/2021 14:24:07 - INFO - __main__ - Step 6790: {'lr': 0.0004987093693585591, 'samples': 1303680, 'steps': 6789, 'loss/train': 0.3496999740600586} 08/30/2021 14:24:08 - INFO - __main__ - Step 6791: {'lr': 0.0004987088307688004, 'samples': 1303872, 'steps': 6790, 'loss/train': 2.0117506980895996} 08/30/2021 14:24:08 - INFO - __main__ - Step 6792: {'lr': 0.0004987082920669772, 'samples': 1304064, 'steps': 6791, 'loss/train': 1.7049227952957153} 08/30/2021 14:24:10 - INFO - __main__ - Step 6793: {'lr': 0.0004987077532530899, 'samples': 1304256, 'steps': 6792, 'loss/train': 1.7496565580368042} 08/30/2021 14:24:11 - INFO - __main__ - Step 6794: {'lr': 0.0004987072143271388, 'samples': 1304448, 'steps': 6793, 'loss/train': 1.5691767930984497} 08/30/2021 14:24:11 - INFO - __main__ - Step 6795: {'lr': 0.000498706675289124, 'samples': 1304640, 'steps': 6794, 'loss/train': 1.5983797311782837} 08/30/2021 14:24:11 - INFO - __main__ - Step 6796: {'lr': 0.0004987061361390458, 'samples': 1304832, 'steps': 6795, 'loss/train': 2.4334306716918945} 08/30/2021 14:24:12 - INFO - __main__ - Step 6797: {'lr': 0.0004987055968769045, 'samples': 1305024, 'steps': 6796, 'loss/train': 2.1273531913757324} 08/30/2021 14:24:14 - INFO - __main__ - Step 6798: {'lr': 0.0004987050575027002, 'samples': 1305216, 'steps': 6797, 'loss/train': 2.0953638553619385} 08/30/2021 14:24:14 - INFO - __main__ - Step 6799: {'lr': 0.0004987045180164333, 'samples': 1305408, 'steps': 6798, 'loss/train': 2.4452297687530518} 08/30/2021 14:24:14 - INFO - __main__ - Step 6800: {'lr': 0.0004987039784181041, 'samples': 1305600, 'steps': 6799, 'loss/train': 1.2725753784179688} 08/30/2021 14:24:15 - INFO - __main__ - Step 6801: {'lr': 0.0004987034387077126, 'samples': 1305792, 'steps': 6800, 'loss/train': 2.0912978649139404} 08/30/2021 14:24:15 - INFO - __main__ - Step 6802: {'lr': 0.0004987028988852592, 'samples': 1305984, 'steps': 6801, 'loss/train': 2.162841796875} 08/30/2021 14:24:17 - INFO - __main__ - Step 6803: {'lr': 0.0004987023589507441, 'samples': 1306176, 'steps': 6802, 'loss/train': 0.22545507550239563} 08/30/2021 14:24:18 - INFO - __main__ - Step 6804: {'lr': 0.0004987018189041675, 'samples': 1306368, 'steps': 6803, 'loss/train': 1.98037850856781} 08/30/2021 14:24:18 - INFO - __main__ - Step 6805: {'lr': 0.0004987012787455297, 'samples': 1306560, 'steps': 6804, 'loss/train': 2.3976211547851562} 08/30/2021 14:24:19 - INFO - __main__ - Step 6806: {'lr': 0.000498700738474831, 'samples': 1306752, 'steps': 6805, 'loss/train': 1.7677881717681885} 08/30/2021 14:24:19 - INFO - __main__ - Step 6807: {'lr': 0.0004987001980920716, 'samples': 1306944, 'steps': 6806, 'loss/train': 1.782514214515686} 08/30/2021 14:24:19 - INFO - __main__ - Step 6808: {'lr': 0.0004986996575972517, 'samples': 1307136, 'steps': 6807, 'loss/train': 1.991308331489563} 08/30/2021 14:24:21 - INFO - __main__ - Step 6809: {'lr': 0.0004986991169903716, 'samples': 1307328, 'steps': 6808, 'loss/train': 1.7893410921096802} 08/30/2021 14:24:21 - INFO - __main__ - Step 6810: {'lr': 0.0004986985762714314, 'samples': 1307520, 'steps': 6809, 'loss/train': 2.308098077774048} 08/30/2021 14:24:22 - INFO - __main__ - Step 6811: {'lr': 0.0004986980354404316, 'samples': 1307712, 'steps': 6810, 'loss/train': 2.290099859237671} 08/30/2021 14:24:22 - INFO - __main__ - Step 6812: {'lr': 0.0004986974944973723, 'samples': 1307904, 'steps': 6811, 'loss/train': 1.5586804151535034} 08/30/2021 14:24:22 - INFO - __main__ - Step 6813: {'lr': 0.0004986969534422537, 'samples': 1308096, 'steps': 6812, 'loss/train': 1.7913575172424316} 08/30/2021 14:24:24 - INFO - __main__ - Step 6814: {'lr': 0.000498696412275076, 'samples': 1308288, 'steps': 6813, 'loss/train': 2.0737788677215576} 08/30/2021 14:24:24 - INFO - __main__ - Step 6815: {'lr': 0.0004986958709958396, 'samples': 1308480, 'steps': 6814, 'loss/train': 1.83364737033844} 08/30/2021 14:24:25 - INFO - __main__ - Step 6816: {'lr': 0.0004986953296045448, 'samples': 1308672, 'steps': 6815, 'loss/train': 2.073204278945923} 08/30/2021 14:24:25 - INFO - __main__ - Step 6817: {'lr': 0.0004986947881011917, 'samples': 1308864, 'steps': 6816, 'loss/train': 1.7709569931030273} 08/30/2021 14:24:25 - INFO - __main__ - Step 6818: {'lr': 0.0004986942464857804, 'samples': 1309056, 'steps': 6817, 'loss/train': 2.5167927742004395} 08/30/2021 14:24:27 - INFO - __main__ - Step 6819: {'lr': 0.0004986937047583114, 'samples': 1309248, 'steps': 6818, 'loss/train': 2.1112968921661377} 08/30/2021 14:24:27 - INFO - __main__ - Step 6820: {'lr': 0.0004986931629187848, 'samples': 1309440, 'steps': 6819, 'loss/train': 1.6558749675750732} 08/30/2021 14:24:28 - INFO - __main__ - Step 6821: {'lr': 0.0004986926209672011, 'samples': 1309632, 'steps': 6820, 'loss/train': 2.2070367336273193} 08/30/2021 14:24:28 - INFO - __main__ - Step 6822: {'lr': 0.0004986920789035601, 'samples': 1309824, 'steps': 6821, 'loss/train': 2.034654378890991} 08/30/2021 14:24:28 - INFO - __main__ - Step 6823: {'lr': 0.0004986915367278623, 'samples': 1310016, 'steps': 6822, 'loss/train': 2.2571158409118652} 08/30/2021 14:24:30 - INFO - __main__ - Step 6824: {'lr': 0.0004986909944401082, 'samples': 1310208, 'steps': 6823, 'loss/train': 1.7329366207122803} 08/30/2021 14:24:30 - INFO - __main__ - Step 6825: {'lr': 0.0004986904520402975, 'samples': 1310400, 'steps': 6824, 'loss/train': 2.0557992458343506} 08/30/2021 14:24:31 - INFO - __main__ - Step 6826: {'lr': 0.0004986899095284308, 'samples': 1310592, 'steps': 6825, 'loss/train': 2.339568853378296} 08/30/2021 14:24:31 - INFO - __main__ - Step 6827: {'lr': 0.0004986893669045083, 'samples': 1310784, 'steps': 6826, 'loss/train': 2.054544448852539} 08/30/2021 14:24:31 - INFO - __main__ - Step 6828: {'lr': 0.0004986888241685301, 'samples': 1310976, 'steps': 6827, 'loss/train': 2.110914707183838} 08/30/2021 14:24:32 - INFO - __main__ - Step 6829: {'lr': 0.0004986882813204967, 'samples': 1311168, 'steps': 6828, 'loss/train': 1.8011455535888672} 08/30/2021 14:24:33 - INFO - __main__ - Step 6830: {'lr': 0.0004986877383604081, 'samples': 1311360, 'steps': 6829, 'loss/train': 0.4001435339450836} 08/30/2021 14:24:34 - INFO - __main__ - Step 6831: {'lr': 0.0004986871952882647, 'samples': 1311552, 'steps': 6830, 'loss/train': 2.1137337684631348} 08/30/2021 14:24:34 - INFO - __main__ - Step 6832: {'lr': 0.0004986866521040666, 'samples': 1311744, 'steps': 6831, 'loss/train': 1.8895313739776611} 08/30/2021 14:24:34 - INFO - __main__ - Step 6833: {'lr': 0.0004986861088078142, 'samples': 1311936, 'steps': 6832, 'loss/train': 2.1450235843658447} 08/30/2021 14:24:35 - INFO - __main__ - Step 6834: {'lr': 0.0004986855653995077, 'samples': 1312128, 'steps': 6833, 'loss/train': 2.0607025623321533} 08/30/2021 14:24:36 - INFO - __main__ - Step 6835: {'lr': 0.0004986850218791474, 'samples': 1312320, 'steps': 6834, 'loss/train': 1.6316173076629639} 08/30/2021 14:24:37 - INFO - __main__ - Step 6836: {'lr': 0.0004986844782467332, 'samples': 1312512, 'steps': 6835, 'loss/train': 1.3658430576324463} 08/30/2021 14:24:37 - INFO - __main__ - Step 6837: {'lr': 0.0004986839345022658, 'samples': 1312704, 'steps': 6836, 'loss/train': 1.4744865894317627} 08/30/2021 14:24:37 - INFO - __main__ - Step 6838: {'lr': 0.0004986833906457453, 'samples': 1312896, 'steps': 6837, 'loss/train': 1.8350540399551392} 08/30/2021 14:24:38 - INFO - __main__ - Step 6839: {'lr': 0.0004986828466771718, 'samples': 1313088, 'steps': 6838, 'loss/train': 1.6223552227020264} 08/30/2021 14:24:40 - INFO - __main__ - Step 6840: {'lr': 0.0004986823025965457, 'samples': 1313280, 'steps': 6839, 'loss/train': 2.226318120956421} 08/30/2021 14:24:40 - INFO - __main__ - Step 6841: {'lr': 0.0004986817584038671, 'samples': 1313472, 'steps': 6840, 'loss/train': 2.0610363483428955} 08/30/2021 14:24:41 - INFO - __main__ - Step 6842: {'lr': 0.0004986812140991365, 'samples': 1313664, 'steps': 6841, 'loss/train': 2.3503642082214355} 08/30/2021 14:24:41 - INFO - __main__ - Step 6843: {'lr': 0.0004986806696823538, 'samples': 1313856, 'steps': 6842, 'loss/train': 1.8314342498779297} 08/30/2021 14:24:41 - INFO - __main__ - Step 6844: {'lr': 0.0004986801251535195, 'samples': 1314048, 'steps': 6843, 'loss/train': 1.357712745666504} 08/30/2021 14:24:42 - INFO - __main__ - Step 6845: {'lr': 0.0004986795805126339, 'samples': 1314240, 'steps': 6844, 'loss/train': 2.556453227996826} 08/30/2021 14:24:43 - INFO - __main__ - Step 6846: {'lr': 0.000498679035759697, 'samples': 1314432, 'steps': 6845, 'loss/train': 2.0000977516174316} 08/30/2021 14:24:44 - INFO - __main__ - Step 6847: {'lr': 0.0004986784908947091, 'samples': 1314624, 'steps': 6846, 'loss/train': 1.7936652898788452} 08/30/2021 14:24:44 - INFO - __main__ - Step 6848: {'lr': 0.0004986779459176706, 'samples': 1314816, 'steps': 6847, 'loss/train': 2.091332197189331} 08/30/2021 14:24:44 - INFO - __main__ - Step 6849: {'lr': 0.0004986774008285816, 'samples': 1315008, 'steps': 6848, 'loss/train': 1.9367101192474365} 08/30/2021 14:24:45 - INFO - __main__ - Step 6850: {'lr': 0.0004986768556274425, 'samples': 1315200, 'steps': 6849, 'loss/train': 1.8169887065887451} 08/30/2021 14:24:47 - INFO - __main__ - Step 6851: {'lr': 0.0004986763103142533, 'samples': 1315392, 'steps': 6850, 'loss/train': 1.878724217414856} 08/30/2021 14:24:47 - INFO - __main__ - Step 6852: {'lr': 0.0004986757648890145, 'samples': 1315584, 'steps': 6851, 'loss/train': 0.44878795742988586} 08/30/2021 14:24:47 - INFO - __main__ - Step 6853: {'lr': 0.0004986752193517262, 'samples': 1315776, 'steps': 6852, 'loss/train': 0.3569950461387634} 08/30/2021 14:24:48 - INFO - __main__ - Step 6854: {'lr': 0.0004986746737023887, 'samples': 1315968, 'steps': 6853, 'loss/train': 1.8973006010055542} 08/30/2021 14:24:48 - INFO - __main__ - Step 6855: {'lr': 0.0004986741279410023, 'samples': 1316160, 'steps': 6854, 'loss/train': 2.3209033012390137} 08/30/2021 14:24:49 - INFO - __main__ - Step 6856: {'lr': 0.000498673582067567, 'samples': 1316352, 'steps': 6855, 'loss/train': 1.9644896984100342} 08/30/2021 14:24:51 - INFO - __main__ - Step 6857: {'lr': 0.0004986730360820833, 'samples': 1316544, 'steps': 6856, 'loss/train': 0.8535609841346741} 08/30/2021 14:24:51 - INFO - __main__ - Step 6858: {'lr': 0.0004986724899845514, 'samples': 1316736, 'steps': 6857, 'loss/train': 2.2894835472106934} 08/30/2021 14:24:52 - INFO - __main__ - Step 6859: {'lr': 0.0004986719437749716, 'samples': 1316928, 'steps': 6858, 'loss/train': 1.8458828926086426} 08/30/2021 14:24:52 - INFO - __main__ - Step 6860: {'lr': 0.0004986713974533439, 'samples': 1317120, 'steps': 6859, 'loss/train': 1.8802374601364136} 08/30/2021 14:24:52 - INFO - __main__ - Step 6861: {'lr': 0.0004986708510196688, 'samples': 1317312, 'steps': 6860, 'loss/train': 1.9847824573516846} 08/30/2021 14:24:54 - INFO - __main__ - Step 6862: {'lr': 0.0004986703044739464, 'samples': 1317504, 'steps': 6861, 'loss/train': 1.9645650386810303} 08/30/2021 14:24:54 - INFO - __main__ - Step 6863: {'lr': 0.000498669757816177, 'samples': 1317696, 'steps': 6862, 'loss/train': 2.2547049522399902} 08/30/2021 14:24:55 - INFO - __main__ - Step 6864: {'lr': 0.0004986692110463609, 'samples': 1317888, 'steps': 6863, 'loss/train': 1.7505618333816528} 08/30/2021 14:24:55 - INFO - __main__ - Step 6865: {'lr': 0.0004986686641644982, 'samples': 1318080, 'steps': 6864, 'loss/train': 1.7786399126052856} 08/30/2021 14:24:55 - INFO - __main__ - Step 6866: {'lr': 0.0004986681171705893, 'samples': 1318272, 'steps': 6865, 'loss/train': 2.016984462738037} 08/30/2021 14:24:57 - INFO - __main__ - Step 6867: {'lr': 0.0004986675700646343, 'samples': 1318464, 'steps': 6866, 'loss/train': 2.2723960876464844} 08/30/2021 14:24:57 - INFO - __main__ - Step 6868: {'lr': 0.0004986670228466337, 'samples': 1318656, 'steps': 6867, 'loss/train': 1.8527895212173462} 08/30/2021 14:24:58 - INFO - __main__ - Step 6869: {'lr': 0.0004986664755165874, 'samples': 1318848, 'steps': 6868, 'loss/train': 1.8059288263320923} 08/30/2021 14:24:58 - INFO - __main__ - Step 6870: {'lr': 0.000498665928074496, 'samples': 1319040, 'steps': 6869, 'loss/train': 2.1040046215057373} 08/30/2021 14:24:58 - INFO - __main__ - Step 6871: {'lr': 0.0004986653805203594, 'samples': 1319232, 'steps': 6870, 'loss/train': 1.7492882013320923} 08/30/2021 14:25:01 - INFO - __main__ - Step 6872: {'lr': 0.0004986648328541781, 'samples': 1319424, 'steps': 6871, 'loss/train': 2.2070772647857666} 08/30/2021 14:25:01 - INFO - __main__ - Step 6873: {'lr': 0.0004986642850759522, 'samples': 1319616, 'steps': 6872, 'loss/train': 2.392061471939087} 08/30/2021 14:25:02 - INFO - __main__ - Step 6874: {'lr': 0.0004986637371856822, 'samples': 1319808, 'steps': 6873, 'loss/train': 2.4519708156585693} 08/30/2021 14:25:02 - INFO - __main__ - Step 6875: {'lr': 0.000498663189183368, 'samples': 1320000, 'steps': 6874, 'loss/train': 1.9604814052581787} 08/30/2021 14:25:02 - INFO - __main__ - Step 6876: {'lr': 0.0004986626410690099, 'samples': 1320192, 'steps': 6875, 'loss/train': 3.5625247955322266} 08/30/2021 14:25:03 - INFO - __main__ - Step 6877: {'lr': 0.0004986620928426085, 'samples': 1320384, 'steps': 6876, 'loss/train': 3.1079251766204834} 08/30/2021 14:25:03 - INFO - __main__ - Step 6878: {'lr': 0.0004986615445041636, 'samples': 1320576, 'steps': 6877, 'loss/train': 3.7473766803741455} 08/30/2021 14:25:05 - INFO - __main__ - Step 6879: {'lr': 0.0004986609960536757, 'samples': 1320768, 'steps': 6878, 'loss/train': 3.530379295349121} 08/30/2021 14:25:05 - INFO - __main__ - Step 6880: {'lr': 0.000498660447491145, 'samples': 1320960, 'steps': 6879, 'loss/train': 2.179630756378174} 08/30/2021 14:25:05 - INFO - __main__ - Step 6881: {'lr': 0.0004986598988165718, 'samples': 1321152, 'steps': 6880, 'loss/train': 2.343501091003418} 08/30/2021 14:25:06 - INFO - __main__ - Step 6882: {'lr': 0.0004986593500299562, 'samples': 1321344, 'steps': 6881, 'loss/train': 2.252079486846924} 08/30/2021 14:25:06 - INFO - __main__ - Step 6883: {'lr': 0.0004986588011312986, 'samples': 1321536, 'steps': 6882, 'loss/train': 1.9850687980651855} 08/30/2021 14:25:07 - INFO - __main__ - Step 6884: {'lr': 0.0004986582521205992, 'samples': 1321728, 'steps': 6883, 'loss/train': 2.7311408519744873} 08/30/2021 14:25:08 - INFO - __main__ - Step 6885: {'lr': 0.0004986577029978581, 'samples': 1321920, 'steps': 6884, 'loss/train': 2.176633834838867} 08/30/2021 14:25:08 - INFO - __main__ - Step 6886: {'lr': 0.0004986571537630757, 'samples': 1322112, 'steps': 6885, 'loss/train': 2.2490451335906982} 08/30/2021 14:25:09 - INFO - __main__ - Step 6887: {'lr': 0.0004986566044162523, 'samples': 1322304, 'steps': 6886, 'loss/train': 2.356243848800659} 08/30/2021 14:25:09 - INFO - __main__ - Step 6888: {'lr': 0.0004986560549573881, 'samples': 1322496, 'steps': 6887, 'loss/train': 2.1619279384613037} 08/30/2021 14:25:11 - INFO - __main__ - Step 6889: {'lr': 0.0004986555053864833, 'samples': 1322688, 'steps': 6888, 'loss/train': 1.0654551982879639} 08/30/2021 14:25:11 - INFO - __main__ - Step 6890: {'lr': 0.0004986549557035381, 'samples': 1322880, 'steps': 6889, 'loss/train': 2.1010587215423584} 08/30/2021 14:25:11 - INFO - __main__ - Step 6891: {'lr': 0.0004986544059085528, 'samples': 1323072, 'steps': 6890, 'loss/train': 2.5215981006622314} 08/30/2021 14:25:12 - INFO - __main__ - Step 6892: {'lr': 0.0004986538560015277, 'samples': 1323264, 'steps': 6891, 'loss/train': 1.2634923458099365} 08/30/2021 14:25:12 - INFO - __main__ - Step 6893: {'lr': 0.000498653305982463, 'samples': 1323456, 'steps': 6892, 'loss/train': 2.037827968597412} 08/30/2021 14:25:14 - INFO - __main__ - Step 6894: {'lr': 0.0004986527558513591, 'samples': 1323648, 'steps': 6893, 'loss/train': 2.1294493675231934} 08/30/2021 14:25:14 - INFO - __main__ - Step 6895: {'lr': 0.0004986522056082159, 'samples': 1323840, 'steps': 6894, 'loss/train': 2.2286181449890137} 08/30/2021 14:25:14 - INFO - __main__ - Step 6896: {'lr': 0.0004986516552530339, 'samples': 1324032, 'steps': 6895, 'loss/train': 2.290353536605835} 08/30/2021 14:25:15 - INFO - __main__ - Step 6897: {'lr': 0.0004986511047858134, 'samples': 1324224, 'steps': 6896, 'loss/train': 2.7949278354644775} 08/30/2021 14:25:15 - INFO - __main__ - Step 6898: {'lr': 0.0004986505542065545, 'samples': 1324416, 'steps': 6897, 'loss/train': 2.1150217056274414} 08/30/2021 14:25:15 - INFO - __main__ - Step 6899: {'lr': 0.0004986500035152574, 'samples': 1324608, 'steps': 6898, 'loss/train': 6.054328441619873} 08/30/2021 14:25:17 - INFO - __main__ - Step 6900: {'lr': 0.0004986494527119226, 'samples': 1324800, 'steps': 6899, 'loss/train': 1.3928371667861938} 08/30/2021 14:25:17 - INFO - __main__ - Step 6901: {'lr': 0.0004986489017965501, 'samples': 1324992, 'steps': 6900, 'loss/train': 2.4879472255706787} 08/30/2021 14:25:18 - INFO - __main__ - Step 6902: {'lr': 0.0004986483507691403, 'samples': 1325184, 'steps': 6901, 'loss/train': 2.4172821044921875} 08/30/2021 14:25:18 - INFO - __main__ - Step 6903: {'lr': 0.0004986477996296934, 'samples': 1325376, 'steps': 6902, 'loss/train': 2.3754258155822754} 08/30/2021 14:25:18 - INFO - __main__ - Step 6904: {'lr': 0.0004986472483782096, 'samples': 1325568, 'steps': 6903, 'loss/train': 2.2065625190734863} 08/30/2021 14:25:20 - INFO - __main__ - Step 6905: {'lr': 0.0004986466970146891, 'samples': 1325760, 'steps': 6904, 'loss/train': 1.9135076999664307} 08/30/2021 14:25:20 - INFO - __main__ - Step 6906: {'lr': 0.0004986461455391323, 'samples': 1325952, 'steps': 6905, 'loss/train': 2.574843168258667} 08/30/2021 14:25:21 - INFO - __main__ - Step 6907: {'lr': 0.0004986455939515395, 'samples': 1326144, 'steps': 6906, 'loss/train': 2.348473310470581} 08/30/2021 14:25:21 - INFO - __main__ - Step 6908: {'lr': 0.0004986450422519107, 'samples': 1326336, 'steps': 6907, 'loss/train': 1.73892343044281} 08/30/2021 14:25:21 - INFO - __main__ - Step 6909: {'lr': 0.0004986444904402463, 'samples': 1326528, 'steps': 6908, 'loss/train': 2.617375612258911} 08/30/2021 14:25:24 - INFO - __main__ - Step 6910: {'lr': 0.0004986439385165464, 'samples': 1326720, 'steps': 6909, 'loss/train': 1.8800106048583984} 08/30/2021 14:25:24 - INFO - __main__ - Step 6911: {'lr': 0.0004986433864808115, 'samples': 1326912, 'steps': 6910, 'loss/train': 1.7740297317504883} 08/30/2021 14:25:24 - INFO - __main__ - Step 6912: {'lr': 0.0004986428343330418, 'samples': 1327104, 'steps': 6911, 'loss/train': 1.7741312980651855} 08/30/2021 14:25:25 - INFO - __main__ - Step 6913: {'lr': 0.0004986422820732375, 'samples': 1327296, 'steps': 6912, 'loss/train': 2.144261121749878} 08/30/2021 14:25:25 - INFO - __main__ - Step 6914: {'lr': 0.0004986417297013987, 'samples': 1327488, 'steps': 6913, 'loss/train': 1.825107216835022} 08/30/2021 14:25:27 - INFO - __main__ - Step 6915: {'lr': 0.0004986411772175258, 'samples': 1327680, 'steps': 6914, 'loss/train': 1.8923066854476929} 08/30/2021 14:25:27 - INFO - __main__ - Step 6916: {'lr': 0.000498640624621619, 'samples': 1327872, 'steps': 6915, 'loss/train': 2.145782470703125} 08/30/2021 14:25:27 - INFO - __main__ - Step 6917: {'lr': 0.0004986400719136786, 'samples': 1328064, 'steps': 6916, 'loss/train': 1.1515460014343262} 08/30/2021 14:25:28 - INFO - __main__ - Step 6918: {'lr': 0.0004986395190937048, 'samples': 1328256, 'steps': 6917, 'loss/train': 1.7062408924102783} 08/30/2021 14:25:28 - INFO - __main__ - Step 6919: {'lr': 0.000498638966161698, 'samples': 1328448, 'steps': 6918, 'loss/train': 2.4489738941192627} 08/30/2021 14:25:30 - INFO - __main__ - Step 6920: {'lr': 0.0004986384131176583, 'samples': 1328640, 'steps': 6919, 'loss/train': 1.9976365566253662} 08/30/2021 14:25:30 - INFO - __main__ - Step 6921: {'lr': 0.0004986378599615858, 'samples': 1328832, 'steps': 6920, 'loss/train': 1.6281598806381226} 08/30/2021 14:25:31 - INFO - __main__ - Step 6922: {'lr': 0.000498637306693481, 'samples': 1329024, 'steps': 6921, 'loss/train': 0.7272114157676697} 08/30/2021 14:25:31 - INFO - __main__ - Step 6923: {'lr': 0.0004986367533133441, 'samples': 1329216, 'steps': 6922, 'loss/train': 0.37977930903434753} 08/30/2021 14:25:31 - INFO - __main__ - Step 6924: {'lr': 0.0004986361998211752, 'samples': 1329408, 'steps': 6923, 'loss/train': 1.578798532485962} 08/30/2021 14:25:32 - INFO - __main__ - Step 6925: {'lr': 0.0004986356462169748, 'samples': 1329600, 'steps': 6924, 'loss/train': 1.8063700199127197} 08/30/2021 14:25:33 - INFO - __main__ - Step 6926: {'lr': 0.0004986350925007429, 'samples': 1329792, 'steps': 6925, 'loss/train': 1.6588304042816162} 08/30/2021 14:25:34 - INFO - __main__ - Step 6927: {'lr': 0.00049863453867248, 'samples': 1329984, 'steps': 6926, 'loss/train': 1.6391549110412598} 08/30/2021 14:25:34 - INFO - __main__ - Step 6928: {'lr': 0.0004986339847321862, 'samples': 1330176, 'steps': 6927, 'loss/train': 2.2844653129577637} 08/30/2021 14:25:35 - INFO - __main__ - Step 6929: {'lr': 0.0004986334306798616, 'samples': 1330368, 'steps': 6928, 'loss/train': 2.1090357303619385} 08/30/2021 14:25:35 - INFO - __main__ - Step 6930: {'lr': 0.0004986328765155068, 'samples': 1330560, 'steps': 6929, 'loss/train': 2.138875961303711} 08/30/2021 14:25:36 - INFO - __main__ - Step 6931: {'lr': 0.0004986323222391217, 'samples': 1330752, 'steps': 6930, 'loss/train': 1.4466071128845215} 08/30/2021 14:25:37 - INFO - __main__ - Step 6932: {'lr': 0.0004986317678507069, 'samples': 1330944, 'steps': 6931, 'loss/train': 2.406386137008667} 08/30/2021 14:25:37 - INFO - __main__ - Step 6933: {'lr': 0.0004986312133502623, 'samples': 1331136, 'steps': 6932, 'loss/train': 2.288001537322998} 08/30/2021 14:25:38 - INFO - __main__ - Step 6934: {'lr': 0.0004986306587377884, 'samples': 1331328, 'steps': 6933, 'loss/train': 2.0331573486328125} 08/30/2021 14:25:38 - INFO - __main__ - Step 6935: {'lr': 0.0004986301040132853, 'samples': 1331520, 'steps': 6934, 'loss/train': 1.7046838998794556} 08/30/2021 14:25:39 - INFO - __main__ - Step 6936: {'lr': 0.0004986295491767533, 'samples': 1331712, 'steps': 6935, 'loss/train': 2.325742244720459} 08/30/2021 14:25:40 - INFO - __main__ - Step 6937: {'lr': 0.0004986289942281927, 'samples': 1331904, 'steps': 6936, 'loss/train': 2.508173942565918} 08/30/2021 14:25:40 - INFO - __main__ - Step 6938: {'lr': 0.0004986284391676037, 'samples': 1332096, 'steps': 6937, 'loss/train': 0.506510853767395} 08/30/2021 14:25:41 - INFO - __main__ - Step 6939: {'lr': 0.0004986278839949866, 'samples': 1332288, 'steps': 6938, 'loss/train': 2.2064061164855957} 08/30/2021 14:25:41 - INFO - __main__ - Step 6940: {'lr': 0.0004986273287103416, 'samples': 1332480, 'steps': 6939, 'loss/train': 2.2642083168029785} 08/30/2021 14:25:41 - INFO - __main__ - Step 6941: {'lr': 0.0004986267733136689, 'samples': 1332672, 'steps': 6940, 'loss/train': 2.348919153213501} 08/30/2021 14:25:43 - INFO - __main__ - Step 6942: {'lr': 0.0004986262178049689, 'samples': 1332864, 'steps': 6941, 'loss/train': 1.9068524837493896} 08/30/2021 14:25:43 - INFO - __main__ - Step 6943: {'lr': 0.0004986256621842417, 'samples': 1333056, 'steps': 6942, 'loss/train': 2.513831853866577} 08/30/2021 14:25:44 - INFO - __main__ - Step 6944: {'lr': 0.0004986251064514878, 'samples': 1333248, 'steps': 6943, 'loss/train': 2.5233402252197266} 08/30/2021 14:25:44 - INFO - __main__ - Step 6945: {'lr': 0.000498624550606707, 'samples': 1333440, 'steps': 6944, 'loss/train': 2.2280867099761963} 08/30/2021 14:25:44 - INFO - __main__ - Step 6946: {'lr': 0.0004986239946498999, 'samples': 1333632, 'steps': 6945, 'loss/train': 1.7360042333602905} 08/30/2021 14:25:46 - INFO - __main__ - Step 6947: {'lr': 0.0004986234385810668, 'samples': 1333824, 'steps': 6946, 'loss/train': 3.6465749740600586} 08/30/2021 14:25:46 - INFO - __main__ - Step 6948: {'lr': 0.0004986228824002076, 'samples': 1334016, 'steps': 6947, 'loss/train': 2.2492029666900635} 08/30/2021 14:25:47 - INFO - __main__ - Step 6949: {'lr': 0.0004986223261073228, 'samples': 1334208, 'steps': 6948, 'loss/train': 1.952388882637024} 08/30/2021 14:25:47 - INFO - __main__ - Step 6950: {'lr': 0.0004986217697024128, 'samples': 1334400, 'steps': 6949, 'loss/train': 2.0262415409088135} 08/30/2021 14:25:47 - INFO - __main__ - Step 6951: {'lr': 0.0004986212131854775, 'samples': 1334592, 'steps': 6950, 'loss/train': 2.334930896759033} 08/30/2021 14:25:49 - INFO - __main__ - Step 6952: {'lr': 0.0004986206565565173, 'samples': 1334784, 'steps': 6951, 'loss/train': 1.644972801208496} 08/30/2021 14:25:50 - INFO - __main__ - Step 6953: {'lr': 0.0004986200998155325, 'samples': 1334976, 'steps': 6952, 'loss/train': 1.7954020500183105} 08/30/2021 14:25:50 - INFO - __main__ - Step 6954: {'lr': 0.0004986195429625234, 'samples': 1335168, 'steps': 6953, 'loss/train': 0.19723883271217346} 08/30/2021 14:25:50 - INFO - __main__ - Step 6955: {'lr': 0.0004986189859974901, 'samples': 1335360, 'steps': 6954, 'loss/train': 2.0334248542785645} 08/30/2021 14:25:51 - INFO - __main__ - Step 6956: {'lr': 0.000498618428920433, 'samples': 1335552, 'steps': 6955, 'loss/train': 1.721176028251648} 08/30/2021 14:25:51 - INFO - __main__ - Step 6957: {'lr': 0.0004986178717313522, 'samples': 1335744, 'steps': 6956, 'loss/train': 0.44948306679725647} 08/30/2021 14:25:53 - INFO - __main__ - Step 6958: {'lr': 0.000498617314430248, 'samples': 1335936, 'steps': 6957, 'loss/train': 0.3447542190551758} 08/30/2021 14:25:54 - INFO - __main__ - Step 6959: {'lr': 0.0004986167570171208, 'samples': 1336128, 'steps': 6958, 'loss/train': 2.662984609603882} 08/30/2021 14:25:54 - INFO - __main__ - Step 6960: {'lr': 0.0004986161994919706, 'samples': 1336320, 'steps': 6959, 'loss/train': 2.0758748054504395} 08/30/2021 14:25:54 - INFO - __main__ - Step 6961: {'lr': 0.0004986156418547978, 'samples': 1336512, 'steps': 6960, 'loss/train': 1.8414498567581177} 08/30/2021 14:25:55 - INFO - __main__ - Step 6962: {'lr': 0.0004986150841056027, 'samples': 1336704, 'steps': 6961, 'loss/train': 2.1176645755767822} 08/30/2021 14:25:55 - INFO - __main__ - Step 6963: {'lr': 0.0004986145262443854, 'samples': 1336896, 'steps': 6962, 'loss/train': 2.3262994289398193} 08/30/2021 14:25:56 - INFO - __main__ - Step 6964: {'lr': 0.0004986139682711463, 'samples': 1337088, 'steps': 6963, 'loss/train': 2.2248663902282715} 08/30/2021 14:25:57 - INFO - __main__ - Step 6965: {'lr': 0.0004986134101858854, 'samples': 1337280, 'steps': 6964, 'loss/train': 2.1714463233947754} 08/30/2021 14:25:57 - INFO - __main__ - Step 6966: {'lr': 0.0004986128519886033, 'samples': 1337472, 'steps': 6965, 'loss/train': 2.0460751056671143} 08/30/2021 14:25:58 - INFO - __main__ - Step 6967: {'lr': 0.0004986122936793, 'samples': 1337664, 'steps': 6966, 'loss/train': 2.76940655708313} 08/30/2021 14:25:58 - INFO - __main__ - Step 6968: {'lr': 0.000498611735257976, 'samples': 1337856, 'steps': 6967, 'loss/train': 2.16974139213562} 08/30/2021 14:26:00 - INFO - __main__ - Step 6969: {'lr': 0.0004986111767246313, 'samples': 1338048, 'steps': 6968, 'loss/train': 2.816469192504883} 08/30/2021 14:26:01 - INFO - __main__ - Step 6970: {'lr': 0.0004986106180792662, 'samples': 1338240, 'steps': 6969, 'loss/train': 2.0011513233184814} 08/30/2021 14:26:01 - INFO - __main__ - Step 6971: {'lr': 0.000498610059321881, 'samples': 1338432, 'steps': 6970, 'loss/train': 2.0067129135131836} 08/30/2021 14:26:01 - INFO - __main__ - Step 6972: {'lr': 0.000498609500452476, 'samples': 1338624, 'steps': 6971, 'loss/train': 2.03497576713562} 08/30/2021 14:26:02 - INFO - __main__ - Step 6973: {'lr': 0.0004986089414710513, 'samples': 1338816, 'steps': 6972, 'loss/train': 2.0776422023773193} 08/30/2021 14:26:03 - INFO - __main__ - Step 6974: {'lr': 0.0004986083823776073, 'samples': 1339008, 'steps': 6973, 'loss/train': 2.151496171951294} 08/30/2021 14:26:04 - INFO - __main__ - Step 6975: {'lr': 0.0004986078231721443, 'samples': 1339200, 'steps': 6974, 'loss/train': 1.8441307544708252} 08/30/2021 14:26:04 - INFO - __main__ - Step 6976: {'lr': 0.0004986072638546623, 'samples': 1339392, 'steps': 6975, 'loss/train': 1.173264503479004} 08/30/2021 14:26:04 - INFO - __main__ - Step 6977: {'lr': 0.0004986067044251617, 'samples': 1339584, 'steps': 6976, 'loss/train': 1.4295763969421387} 08/30/2021 14:26:05 - INFO - __main__ - Step 6978: {'lr': 0.0004986061448836428, 'samples': 1339776, 'steps': 6977, 'loss/train': 1.6548140048980713} 08/30/2021 14:26:05 - INFO - __main__ - Step 6979: {'lr': 0.0004986055852301058, 'samples': 1339968, 'steps': 6978, 'loss/train': 1.9921854734420776} 08/30/2021 14:26:06 - INFO - __main__ - Step 6980: {'lr': 0.000498605025464551, 'samples': 1340160, 'steps': 6979, 'loss/train': 1.6484514474868774} 08/30/2021 14:26:07 - INFO - __main__ - Step 6981: {'lr': 0.0004986044655869786, 'samples': 1340352, 'steps': 6980, 'loss/train': 2.116065502166748} 08/30/2021 14:26:07 - INFO - __main__ - Step 6982: {'lr': 0.0004986039055973889, 'samples': 1340544, 'steps': 6981, 'loss/train': 2.010517120361328} 08/30/2021 14:26:08 - INFO - __main__ - Step 6983: {'lr': 0.000498603345495782, 'samples': 1340736, 'steps': 6982, 'loss/train': 2.0259077548980713} 08/30/2021 14:26:08 - INFO - __main__ - Step 6984: {'lr': 0.0004986027852821583, 'samples': 1340928, 'steps': 6983, 'loss/train': 2.8793866634368896} 08/30/2021 14:26:09 - INFO - __main__ - Step 6985: {'lr': 0.000498602224956518, 'samples': 1341120, 'steps': 6984, 'loss/train': 2.0337533950805664} 08/30/2021 14:26:10 - INFO - __main__ - Step 6986: {'lr': 0.0004986016645188615, 'samples': 1341312, 'steps': 6985, 'loss/train': 2.2896721363067627} 08/30/2021 14:26:10 - INFO - __main__ - Step 6987: {'lr': 0.0004986011039691889, 'samples': 1341504, 'steps': 6986, 'loss/train': 1.809281826019287} 08/30/2021 14:26:11 - INFO - __main__ - Step 6988: {'lr': 0.0004986005433075004, 'samples': 1341696, 'steps': 6987, 'loss/train': 0.2523254156112671} 08/30/2021 14:26:11 - INFO - __main__ - Step 6989: {'lr': 0.0004985999825337964, 'samples': 1341888, 'steps': 6988, 'loss/train': 2.344238042831421} 08/30/2021 14:26:12 - INFO - __main__ - Step 6990: {'lr': 0.000498599421648077, 'samples': 1342080, 'steps': 6989, 'loss/train': 1.9715166091918945} 08/30/2021 14:26:13 - INFO - __main__ - Step 6991: {'lr': 0.0004985988606503426, 'samples': 1342272, 'steps': 6990, 'loss/train': 1.8085249662399292} 08/30/2021 14:26:13 - INFO - __main__ - Step 6992: {'lr': 0.0004985982995405933, 'samples': 1342464, 'steps': 6991, 'loss/train': 2.09302020072937} 08/30/2021 14:26:14 - INFO - __main__ - Step 6993: {'lr': 0.0004985977383188296, 'samples': 1342656, 'steps': 6992, 'loss/train': 2.913682460784912} 08/30/2021 14:26:14 - INFO - __main__ - Step 6994: {'lr': 0.0004985971769850515, 'samples': 1342848, 'steps': 6993, 'loss/train': 1.6446220874786377} 08/30/2021 14:26:16 - INFO - __main__ - Step 6995: {'lr': 0.0004985966155392593, 'samples': 1343040, 'steps': 6994, 'loss/train': 1.8418692350387573} 08/30/2021 14:26:16 - INFO - __main__ - Step 6996: {'lr': 0.0004985960539814534, 'samples': 1343232, 'steps': 6995, 'loss/train': 2.144650459289551} 08/30/2021 14:26:16 - INFO - __main__ - Step 6997: {'lr': 0.000498595492311634, 'samples': 1343424, 'steps': 6996, 'loss/train': 0.34487003087997437} 08/30/2021 14:26:17 - INFO - __main__ - Step 6998: {'lr': 0.0004985949305298012, 'samples': 1343616, 'steps': 6997, 'loss/train': 1.9332834482192993} 08/30/2021 14:26:17 - INFO - __main__ - Step 6999: {'lr': 0.0004985943686359554, 'samples': 1343808, 'steps': 6998, 'loss/train': 2.3357770442962646} 08/30/2021 14:26:19 - INFO - __main__ - Step 7000: {'lr': 0.0004985938066300968, 'samples': 1344000, 'steps': 6999, 'loss/train': 1.23027765750885} 08/30/2021 14:26:19 - INFO - __main__ - Step 7001: {'lr': 0.0004985932445122257, 'samples': 1344192, 'steps': 7000, 'loss/train': 2.541163444519043} 08/30/2021 14:26:19 - INFO - __main__ - Step 7002: {'lr': 0.0004985926822823422, 'samples': 1344384, 'steps': 7001, 'loss/train': 2.5520241260528564} 08/30/2021 14:26:20 - INFO - __main__ - Step 7003: {'lr': 0.0004985921199404467, 'samples': 1344576, 'steps': 7002, 'loss/train': 2.276765823364258} 08/30/2021 14:26:20 - INFO - __main__ - Step 7004: {'lr': 0.0004985915574865395, 'samples': 1344768, 'steps': 7003, 'loss/train': 2.1749000549316406} 08/30/2021 14:26:20 - INFO - __main__ - Step 7005: {'lr': 0.0004985909949206209, 'samples': 1344960, 'steps': 7004, 'loss/train': 2.2031936645507812} 08/30/2021 14:26:22 - INFO - __main__ - Step 7006: {'lr': 0.0004985904322426909, 'samples': 1345152, 'steps': 7005, 'loss/train': 2.3593475818634033} 08/30/2021 14:26:22 - INFO - __main__ - Step 7007: {'lr': 0.0004985898694527498, 'samples': 1345344, 'steps': 7006, 'loss/train': 2.2181200981140137} 08/30/2021 14:26:23 - INFO - __main__ - Step 7008: {'lr': 0.000498589306550798, 'samples': 1345536, 'steps': 7007, 'loss/train': 0.8213203549385071} 08/30/2021 14:26:23 - INFO - __main__ - Step 7009: {'lr': 0.0004985887435368357, 'samples': 1345728, 'steps': 7008, 'loss/train': 2.2370710372924805} 08/30/2021 14:26:24 - INFO - __main__ - Step 7010: {'lr': 0.0004985881804108632, 'samples': 1345920, 'steps': 7009, 'loss/train': 2.477621555328369} 08/30/2021 14:26:25 - INFO - __main__ - Step 7011: {'lr': 0.0004985876171728807, 'samples': 1346112, 'steps': 7010, 'loss/train': 1.947131633758545} 08/30/2021 14:26:26 - INFO - __main__ - Step 7012: {'lr': 0.0004985870538228884, 'samples': 1346304, 'steps': 7011, 'loss/train': 1.5513256788253784} 08/30/2021 14:26:26 - INFO - __main__ - Step 7013: {'lr': 0.0004985864903608866, 'samples': 1346496, 'steps': 7012, 'loss/train': 2.0416758060455322} 08/30/2021 14:26:26 - INFO - __main__ - Step 7014: {'lr': 0.0004985859267868756, 'samples': 1346688, 'steps': 7013, 'loss/train': 0.25593629479408264} 08/30/2021 14:26:27 - INFO - __main__ - Step 7015: {'lr': 0.0004985853631008557, 'samples': 1346880, 'steps': 7014, 'loss/train': 2.3708863258361816} 08/30/2021 14:26:28 - INFO - __main__ - Step 7016: {'lr': 0.000498584799302827, 'samples': 1347072, 'steps': 7015, 'loss/train': 0.8170610070228577} 08/30/2021 14:26:29 - INFO - __main__ - Step 7017: {'lr': 0.0004985842353927897, 'samples': 1347264, 'steps': 7016, 'loss/train': 2.0751936435699463} 08/30/2021 14:26:29 - INFO - __main__ - Step 7018: {'lr': 0.0004985836713707443, 'samples': 1347456, 'steps': 7017, 'loss/train': 2.1809775829315186} 08/30/2021 14:26:29 - INFO - __main__ - Step 7019: {'lr': 0.000498583107236691, 'samples': 1347648, 'steps': 7018, 'loss/train': 2.044480085372925} 08/30/2021 14:26:30 - INFO - __main__ - Step 7020: {'lr': 0.0004985825429906299, 'samples': 1347840, 'steps': 7019, 'loss/train': 2.1939988136291504} 08/30/2021 14:26:31 - INFO - __main__ - Step 7021: {'lr': 0.0004985819786325614, 'samples': 1348032, 'steps': 7020, 'loss/train': 2.0760951042175293} 08/30/2021 14:26:32 - INFO - __main__ - Step 7022: {'lr': 0.0004985814141624856, 'samples': 1348224, 'steps': 7021, 'loss/train': 1.8965190649032593} 08/30/2021 14:26:32 - INFO - __main__ - Step 7023: {'lr': 0.000498580849580403, 'samples': 1348416, 'steps': 7022, 'loss/train': 1.8502427339553833} 08/30/2021 14:26:32 - INFO - __main__ - Step 7024: {'lr': 0.0004985802848863135, 'samples': 1348608, 'steps': 7023, 'loss/train': 2.7550241947174072} 08/30/2021 14:26:33 - INFO - __main__ - Step 7025: {'lr': 0.0004985797200802176, 'samples': 1348800, 'steps': 7024, 'loss/train': 2.3097569942474365} 08/30/2021 14:26:35 - INFO - __main__ - Step 7026: {'lr': 0.0004985791551621158, 'samples': 1348992, 'steps': 7025, 'loss/train': 1.8013461828231812} 08/30/2021 14:26:35 - INFO - __main__ - Step 7027: {'lr': 0.0004985785901320078, 'samples': 1349184, 'steps': 7026, 'loss/train': 2.9754016399383545} 08/30/2021 14:26:36 - INFO - __main__ - Step 7028: {'lr': 0.0004985780249898941, 'samples': 1349376, 'steps': 7027, 'loss/train': 2.4538865089416504} 08/30/2021 14:26:36 - INFO - __main__ - Step 7029: {'lr': 0.0004985774597357751, 'samples': 1349568, 'steps': 7028, 'loss/train': 2.5522937774658203} 08/30/2021 14:26:36 - INFO - __main__ - Step 7030: {'lr': 0.0004985768943696509, 'samples': 1349760, 'steps': 7029, 'loss/train': 1.8235198259353638} 08/30/2021 14:26:38 - INFO - __main__ - Step 7031: {'lr': 0.0004985763288915217, 'samples': 1349952, 'steps': 7030, 'loss/train': 2.3612794876098633} 08/30/2021 14:26:38 - INFO - __main__ - Step 7032: {'lr': 0.0004985757633013879, 'samples': 1350144, 'steps': 7031, 'loss/train': 2.2243618965148926} 08/30/2021 14:26:39 - INFO - __main__ - Step 7033: {'lr': 0.0004985751975992497, 'samples': 1350336, 'steps': 7032, 'loss/train': 2.0661380290985107} 08/30/2021 14:26:39 - INFO - __main__ - Step 7034: {'lr': 0.0004985746317851074, 'samples': 1350528, 'steps': 7033, 'loss/train': 1.7722347974777222} 08/30/2021 14:26:39 - INFO - __main__ - Step 7035: {'lr': 0.0004985740658589612, 'samples': 1350720, 'steps': 7034, 'loss/train': 2.697772264480591} 08/30/2021 14:26:41 - INFO - __main__ - Step 7036: {'lr': 0.0004985734998208112, 'samples': 1350912, 'steps': 7035, 'loss/train': 2.218561887741089} 08/30/2021 14:26:41 - INFO - __main__ - Step 7037: {'lr': 0.000498572933670658, 'samples': 1351104, 'steps': 7036, 'loss/train': 2.1016488075256348} 08/30/2021 14:26:42 - INFO - __main__ - Step 7038: {'lr': 0.0004985723674085016, 'samples': 1351296, 'steps': 7037, 'loss/train': 1.9448717832565308} 08/30/2021 14:26:42 - INFO - __main__ - Step 7039: {'lr': 0.0004985718010343424, 'samples': 1351488, 'steps': 7038, 'loss/train': 1.8086481094360352} 08/30/2021 14:26:42 - INFO - __main__ - Step 7040: {'lr': 0.0004985712345481805, 'samples': 1351680, 'steps': 7039, 'loss/train': 2.5131611824035645} 08/30/2021 14:26:44 - INFO - __main__ - Step 7041: {'lr': 0.0004985706679500163, 'samples': 1351872, 'steps': 7040, 'loss/train': 1.7539966106414795} 08/30/2021 14:26:44 - INFO - __main__ - Step 7042: {'lr': 0.0004985701012398499, 'samples': 1352064, 'steps': 7041, 'loss/train': 1.6048985719680786} 08/30/2021 14:26:45 - INFO - __main__ - Step 7043: {'lr': 0.0004985695344176817, 'samples': 1352256, 'steps': 7042, 'loss/train': 0.719610869884491} 08/30/2021 14:26:45 - INFO - __main__ - Step 7044: {'lr': 0.0004985689674835119, 'samples': 1352448, 'steps': 7043, 'loss/train': 2.022465229034424} 08/30/2021 14:26:45 - INFO - __main__ - Step 7045: {'lr': 0.0004985684004373409, 'samples': 1352640, 'steps': 7044, 'loss/train': 0.8750408291816711} 08/30/2021 14:26:47 - INFO - __main__ - Step 7046: {'lr': 0.0004985678332791686, 'samples': 1352832, 'steps': 7045, 'loss/train': 2.137831926345825} 08/30/2021 14:26:47 - INFO - __main__ - Step 7047: {'lr': 0.0004985672660089956, 'samples': 1353024, 'steps': 7046, 'loss/train': 1.8576068878173828} 08/30/2021 14:26:48 - INFO - __main__ - Step 7048: {'lr': 0.000498566698626822, 'samples': 1353216, 'steps': 7047, 'loss/train': 2.100839138031006} 08/30/2021 14:26:48 - INFO - __main__ - Step 7049: {'lr': 0.000498566131132648, 'samples': 1353408, 'steps': 7048, 'loss/train': 4.702973365783691} 08/30/2021 14:26:49 - INFO - __main__ - Step 7050: {'lr': 0.0004985655635264739, 'samples': 1353600, 'steps': 7049, 'loss/train': 2.195896625518799} 08/30/2021 14:26:49 - INFO - __main__ - Step 7051: {'lr': 0.0004985649958083001, 'samples': 1353792, 'steps': 7050, 'loss/train': 1.644945740699768} 08/30/2021 14:26:50 - INFO - __main__ - Step 7052: {'lr': 0.0004985644279781268, 'samples': 1353984, 'steps': 7051, 'loss/train': 1.3386199474334717} 08/30/2021 14:26:51 - INFO - __main__ - Step 7053: {'lr': 0.0004985638600359542, 'samples': 1354176, 'steps': 7052, 'loss/train': 1.4313273429870605} 08/30/2021 14:26:51 - INFO - __main__ - Step 7054: {'lr': 0.0004985632919817824, 'samples': 1354368, 'steps': 7053, 'loss/train': 1.8021634817123413} 08/30/2021 14:26:52 - INFO - __main__ - Step 7055: {'lr': 0.000498562723815612, 'samples': 1354560, 'steps': 7054, 'loss/train': 0.2595697045326233} 08/30/2021 14:26:52 - INFO - __main__ - Step 7056: {'lr': 0.000498562155537443, 'samples': 1354752, 'steps': 7055, 'loss/train': 2.2817718982696533} 08/30/2021 14:26:53 - INFO - __main__ - Step 7057: {'lr': 0.0004985615871472757, 'samples': 1354944, 'steps': 7056, 'loss/train': 1.7531142234802246} 08/30/2021 14:26:54 - INFO - __main__ - Step 7058: {'lr': 0.0004985610186451104, 'samples': 1355136, 'steps': 7057, 'loss/train': 2.0245070457458496} 08/30/2021 14:26:54 - INFO - __main__ - Step 7059: {'lr': 0.0004985604500309473, 'samples': 1355328, 'steps': 7058, 'loss/train': 2.275963306427002} 08/30/2021 14:26:55 - INFO - __main__ - Step 7060: {'lr': 0.0004985598813047868, 'samples': 1355520, 'steps': 7059, 'loss/train': 1.4255527257919312} 08/30/2021 14:26:55 - INFO - __main__ - Step 7061: {'lr': 0.000498559312466629, 'samples': 1355712, 'steps': 7060, 'loss/train': 1.9848852157592773} 08/30/2021 14:26:56 - INFO - __main__ - Step 7062: {'lr': 0.0004985587435164742, 'samples': 1355904, 'steps': 7061, 'loss/train': 2.0852506160736084} 08/30/2021 14:26:57 - INFO - __main__ - Step 7063: {'lr': 0.0004985581744543226, 'samples': 1356096, 'steps': 7062, 'loss/train': 1.8649299144744873} 08/30/2021 14:26:57 - INFO - __main__ - Step 7064: {'lr': 0.0004985576052801747, 'samples': 1356288, 'steps': 7063, 'loss/train': 1.4704043865203857} 08/30/2021 14:26:58 - INFO - __main__ - Step 7065: {'lr': 0.0004985570359940304, 'samples': 1356480, 'steps': 7064, 'loss/train': 2.110185146331787} 08/30/2021 14:26:58 - INFO - __main__ - Step 7066: {'lr': 0.0004985564665958901, 'samples': 1356672, 'steps': 7065, 'loss/train': 1.8290075063705444} 08/30/2021 14:27:00 - INFO - __main__ - Step 7067: {'lr': 0.0004985558970857543, 'samples': 1356864, 'steps': 7066, 'loss/train': 1.6149054765701294} 08/30/2021 14:27:00 - INFO - __main__ - Step 7068: {'lr': 0.000498555327463623, 'samples': 1357056, 'steps': 7067, 'loss/train': 2.0574913024902344} 08/30/2021 14:27:00 - INFO - __main__ - Step 7069: {'lr': 0.0004985547577294963, 'samples': 1357248, 'steps': 7068, 'loss/train': 2.1082918643951416} 08/30/2021 14:27:01 - INFO - __main__ - Step 7070: {'lr': 0.0004985541878833749, 'samples': 1357440, 'steps': 7069, 'loss/train': 1.3834682703018188} 08/30/2021 14:27:01 - INFO - __main__ - Step 7071: {'lr': 0.0004985536179252587, 'samples': 1357632, 'steps': 7070, 'loss/train': 1.9284027814865112} 08/30/2021 14:27:01 - INFO - __main__ - Step 7072: {'lr': 0.0004985530478551481, 'samples': 1357824, 'steps': 7071, 'loss/train': 1.990464448928833} 08/30/2021 14:27:03 - INFO - __main__ - Step 7073: {'lr': 0.0004985524776730434, 'samples': 1358016, 'steps': 7072, 'loss/train': 1.6240383386611938} 08/30/2021 14:27:03 - INFO - __main__ - Step 7074: {'lr': 0.0004985519073789447, 'samples': 1358208, 'steps': 7073, 'loss/train': 1.859412670135498} 08/30/2021 14:27:04 - INFO - __main__ - Step 7075: {'lr': 0.0004985513369728524, 'samples': 1358400, 'steps': 7074, 'loss/train': 1.9900660514831543} 08/30/2021 14:27:04 - INFO - __main__ - Step 7076: {'lr': 0.0004985507664547666, 'samples': 1358592, 'steps': 7075, 'loss/train': 2.0464377403259277} 08/30/2021 14:27:04 - INFO - __main__ - Step 7077: {'lr': 0.0004985501958246878, 'samples': 1358784, 'steps': 7076, 'loss/train': 2.6055030822753906} 08/30/2021 14:27:07 - INFO - __main__ - Step 7078: {'lr': 0.000498549625082616, 'samples': 1358976, 'steps': 7077, 'loss/train': 0.6727930307388306} 08/30/2021 14:27:07 - INFO - __main__ - Step 7079: {'lr': 0.0004985490542285516, 'samples': 1359168, 'steps': 7078, 'loss/train': 2.0788557529449463} 08/30/2021 14:27:08 - INFO - __main__ - Step 7080: {'lr': 0.0004985484832624949, 'samples': 1359360, 'steps': 7079, 'loss/train': 2.1179535388946533} 08/30/2021 14:27:08 - INFO - __main__ - Step 7081: {'lr': 0.000498547912184446, 'samples': 1359552, 'steps': 7080, 'loss/train': 1.881097435951233} 08/30/2021 14:27:08 - INFO - __main__ - Step 7082: {'lr': 0.0004985473409944054, 'samples': 1359744, 'steps': 7081, 'loss/train': 1.996102213859558} 08/30/2021 14:27:09 - INFO - __main__ - Step 7083: {'lr': 0.000498546769692373, 'samples': 1359936, 'steps': 7082, 'loss/train': 2.7988317012786865} 08/30/2021 14:27:10 - INFO - __main__ - Step 7084: {'lr': 0.0004985461982783494, 'samples': 1360128, 'steps': 7083, 'loss/train': 1.7322026491165161} 08/30/2021 14:27:11 - INFO - __main__ - Step 7085: {'lr': 0.0004985456267523346, 'samples': 1360320, 'steps': 7084, 'loss/train': 2.3654000759124756} 08/30/2021 14:27:11 - INFO - __main__ - Step 7086: {'lr': 0.0004985450551143291, 'samples': 1360512, 'steps': 7085, 'loss/train': 1.8243162631988525} 08/30/2021 14:27:11 - INFO - __main__ - Step 7087: {'lr': 0.000498544483364333, 'samples': 1360704, 'steps': 7086, 'loss/train': 2.002641439437866} 08/30/2021 14:27:12 - INFO - __main__ - Step 7088: {'lr': 0.0004985439115023465, 'samples': 1360896, 'steps': 7087, 'loss/train': 1.816934585571289} 08/30/2021 14:27:13 - INFO - __main__ - Step 7089: {'lr': 0.0004985433395283701, 'samples': 1361088, 'steps': 7088, 'loss/train': 2.1620287895202637} 08/30/2021 14:27:14 - INFO - __main__ - Step 7090: {'lr': 0.0004985427674424038, 'samples': 1361280, 'steps': 7089, 'loss/train': 2.1201906204223633} 08/30/2021 14:27:14 - INFO - __main__ - Step 7091: {'lr': 0.000498542195244448, 'samples': 1361472, 'steps': 7090, 'loss/train': 1.913047432899475} 08/30/2021 14:27:14 - INFO - __main__ - Step 7092: {'lr': 0.0004985416229345029, 'samples': 1361664, 'steps': 7091, 'loss/train': 1.9856257438659668} 08/30/2021 14:27:15 - INFO - __main__ - Step 7093: {'lr': 0.0004985410505125689, 'samples': 1361856, 'steps': 7092, 'loss/train': 2.2616918087005615} 08/30/2021 14:27:16 - INFO - __main__ - Step 7094: {'lr': 0.0004985404779786459, 'samples': 1362048, 'steps': 7093, 'loss/train': 1.852012276649475} 08/30/2021 14:27:17 - INFO - __main__ - Step 7095: {'lr': 0.0004985399053327346, 'samples': 1362240, 'steps': 7094, 'loss/train': 1.8436076641082764} 08/30/2021 14:27:17 - INFO - __main__ - Step 7096: {'lr': 0.000498539332574835, 'samples': 1362432, 'steps': 7095, 'loss/train': 2.006499767303467} 08/30/2021 14:27:18 - INFO - __main__ - Step 7097: {'lr': 0.0004985387597049474, 'samples': 1362624, 'steps': 7096, 'loss/train': 1.0633573532104492} 08/30/2021 14:27:18 - INFO - __main__ - Step 7098: {'lr': 0.0004985381867230721, 'samples': 1362816, 'steps': 7097, 'loss/train': 1.9722651243209839} 08/30/2021 14:27:18 - INFO - __main__ - Step 7099: {'lr': 0.0004985376136292093, 'samples': 1363008, 'steps': 7098, 'loss/train': 5.240437030792236} 08/30/2021 14:27:20 - INFO - __main__ - Step 7100: {'lr': 0.0004985370404233592, 'samples': 1363200, 'steps': 7099, 'loss/train': 1.9567259550094604} 08/30/2021 14:27:20 - INFO - __main__ - Step 7101: {'lr': 0.0004985364671055223, 'samples': 1363392, 'steps': 7100, 'loss/train': 2.0685393810272217} 08/30/2021 14:27:21 - INFO - __main__ - Step 7102: {'lr': 0.0004985358936756985, 'samples': 1363584, 'steps': 7101, 'loss/train': 1.7404972314834595} 08/30/2021 14:27:21 - INFO - __main__ - Step 7103: {'lr': 0.0004985353201338885, 'samples': 1363776, 'steps': 7102, 'loss/train': 2.0010063648223877} 08/30/2021 14:27:21 - INFO - __main__ - Step 7104: {'lr': 0.0004985347464800921, 'samples': 1363968, 'steps': 7103, 'loss/train': 1.8056018352508545} 08/30/2021 14:27:23 - INFO - __main__ - Step 7105: {'lr': 0.0004985341727143099, 'samples': 1364160, 'steps': 7104, 'loss/train': 2.1832635402679443} 08/30/2021 14:27:24 - INFO - __main__ - Step 7106: {'lr': 0.000498533598836542, 'samples': 1364352, 'steps': 7105, 'loss/train': 2.127995729446411} 08/30/2021 14:27:24 - INFO - __main__ - Step 7107: {'lr': 0.0004985330248467888, 'samples': 1364544, 'steps': 7106, 'loss/train': 3.5202279090881348} 08/30/2021 14:27:24 - INFO - __main__ - Step 7108: {'lr': 0.0004985324507450504, 'samples': 1364736, 'steps': 7107, 'loss/train': 1.5345447063446045} 08/30/2021 14:27:25 - INFO - __main__ - Step 7109: {'lr': 0.000498531876531327, 'samples': 1364928, 'steps': 7108, 'loss/train': 1.7388873100280762} 08/30/2021 14:27:25 - INFO - __main__ - Step 7110: {'lr': 0.0004985313022056191, 'samples': 1365120, 'steps': 7109, 'loss/train': 1.996155858039856} 08/30/2021 14:27:26 - INFO - __main__ - Step 7111: {'lr': 0.0004985307277679267, 'samples': 1365312, 'steps': 7110, 'loss/train': 2.645927667617798} 08/30/2021 14:27:27 - INFO - __main__ - Step 7112: {'lr': 0.0004985301532182503, 'samples': 1365504, 'steps': 7111, 'loss/train': 2.7811317443847656} 08/30/2021 14:27:27 - INFO - __main__ - Step 7113: {'lr': 0.0004985295785565901, 'samples': 1365696, 'steps': 7112, 'loss/train': 2.0135228633880615} 08/30/2021 14:27:28 - INFO - __main__ - Step 7114: {'lr': 0.0004985290037829462, 'samples': 1365888, 'steps': 7113, 'loss/train': 1.8710907697677612} 08/30/2021 14:27:28 - INFO - __main__ - Step 7115: {'lr': 0.000498528428897319, 'samples': 1366080, 'steps': 7114, 'loss/train': 2.2685768604278564} 08/30/2021 14:27:30 - INFO - __main__ - Step 7116: {'lr': 0.0004985278538997088, 'samples': 1366272, 'steps': 7115, 'loss/train': 2.0806174278259277} 08/30/2021 14:27:30 - INFO - __main__ - Step 7117: {'lr': 0.0004985272787901156, 'samples': 1366464, 'steps': 7116, 'loss/train': 2.5690901279449463} 08/30/2021 14:27:31 - INFO - __main__ - Step 7118: {'lr': 0.00049852670356854, 'samples': 1366656, 'steps': 7117, 'loss/train': 2.0994789600372314} 08/30/2021 14:27:31 - INFO - __main__ - Step 7119: {'lr': 0.000498526128234982, 'samples': 1366848, 'steps': 7118, 'loss/train': 2.1290652751922607} 08/30/2021 14:27:31 - INFO - __main__ - Step 7120: {'lr': 0.000498525552789442, 'samples': 1367040, 'steps': 7119, 'loss/train': 0.41349098086357117} 08/30/2021 14:27:33 - INFO - __main__ - Step 7121: {'lr': 0.0004985249772319202, 'samples': 1367232, 'steps': 7120, 'loss/train': 1.3266475200653076} 08/30/2021 14:27:33 - INFO - __main__ - Step 7122: {'lr': 0.000498524401562417, 'samples': 1367424, 'steps': 7121, 'loss/train': 0.3361709713935852} 08/30/2021 14:27:34 - INFO - __main__ - Step 7123: {'lr': 0.0004985238257809325, 'samples': 1367616, 'steps': 7122, 'loss/train': 1.5390362739562988} 08/30/2021 14:27:34 - INFO - __main__ - Step 7124: {'lr': 0.0004985232498874669, 'samples': 1367808, 'steps': 7123, 'loss/train': 1.0099903345108032} 08/30/2021 14:27:34 - INFO - __main__ - Step 7125: {'lr': 0.0004985226738820207, 'samples': 1368000, 'steps': 7124, 'loss/train': 1.572208046913147} 08/30/2021 14:27:35 - INFO - __main__ - Step 7126: {'lr': 0.0004985220977645939, 'samples': 1368192, 'steps': 7125, 'loss/train': 2.1918258666992188} 08/30/2021 14:27:36 - INFO - __main__ - Step 7127: {'lr': 0.0004985215215351869, 'samples': 1368384, 'steps': 7126, 'loss/train': 1.7024544477462769} 08/30/2021 14:27:37 - INFO - __main__ - Step 7128: {'lr': 0.0004985209451937999, 'samples': 1368576, 'steps': 7127, 'loss/train': 0.7918288111686707} 08/30/2021 14:27:37 - INFO - __main__ - Step 7129: {'lr': 0.0004985203687404333, 'samples': 1368768, 'steps': 7128, 'loss/train': 2.8895046710968018} 08/30/2021 14:27:37 - INFO - __main__ - Step 7130: {'lr': 0.0004985197921750871, 'samples': 1368960, 'steps': 7129, 'loss/train': 1.8123682737350464} 08/30/2021 14:27:38 - INFO - __main__ - Step 7131: {'lr': 0.0004985192154977619, 'samples': 1369152, 'steps': 7130, 'loss/train': 1.624388575553894} 08/30/2021 14:27:40 - INFO - __main__ - Step 7132: {'lr': 0.0004985186387084577, 'samples': 1369344, 'steps': 7131, 'loss/train': 2.02010440826416} 08/30/2021 14:27:40 - INFO - __main__ - Step 7133: {'lr': 0.0004985180618071748, 'samples': 1369536, 'steps': 7132, 'loss/train': 2.0973570346832275} 08/30/2021 14:27:40 - INFO - __main__ - Step 7134: {'lr': 0.0004985174847939135, 'samples': 1369728, 'steps': 7133, 'loss/train': 1.9209593534469604} 08/30/2021 14:27:41 - INFO - __main__ - Step 7135: {'lr': 0.0004985169076686741, 'samples': 1369920, 'steps': 7134, 'loss/train': 1.8563427925109863} 08/30/2021 14:27:41 - INFO - __main__ - Step 7136: {'lr': 0.0004985163304314568, 'samples': 1370112, 'steps': 7135, 'loss/train': 2.0697617530822754} 08/30/2021 14:27:43 - INFO - __main__ - Step 7137: {'lr': 0.0004985157530822619, 'samples': 1370304, 'steps': 7136, 'loss/train': 1.9680343866348267} 08/30/2021 14:27:43 - INFO - __main__ - Step 7138: {'lr': 0.0004985151756210897, 'samples': 1370496, 'steps': 7137, 'loss/train': 2.235201120376587} 08/30/2021 14:27:44 - INFO - __main__ - Step 7139: {'lr': 0.0004985145980479402, 'samples': 1370688, 'steps': 7138, 'loss/train': 1.5232306718826294} 08/30/2021 14:27:44 - INFO - __main__ - Step 7140: {'lr': 0.000498514020362814, 'samples': 1370880, 'steps': 7139, 'loss/train': 2.722341299057007} 08/30/2021 14:27:44 - INFO - __main__ - Step 7141: {'lr': 0.0004985134425657111, 'samples': 1371072, 'steps': 7140, 'loss/train': 2.0578699111938477} 08/30/2021 14:27:45 - INFO - __main__ - Step 7142: {'lr': 0.000498512864656632, 'samples': 1371264, 'steps': 7141, 'loss/train': 1.8936917781829834} 08/30/2021 14:27:46 - INFO - __main__ - Step 7143: {'lr': 0.0004985122866355768, 'samples': 1371456, 'steps': 7142, 'loss/train': 1.4562264680862427} 08/30/2021 14:27:47 - INFO - __main__ - Step 7144: {'lr': 0.0004985117085025458, 'samples': 1371648, 'steps': 7143, 'loss/train': 1.9897072315216064} 08/30/2021 14:27:47 - INFO - __main__ - Step 7145: {'lr': 0.0004985111302575392, 'samples': 1371840, 'steps': 7144, 'loss/train': 0.3156071603298187} 08/30/2021 14:27:47 - INFO - __main__ - Step 7146: {'lr': 0.0004985105519005573, 'samples': 1372032, 'steps': 7145, 'loss/train': 2.3269412517547607} 08/30/2021 14:27:48 - INFO - __main__ - Step 7147: {'lr': 0.0004985099734316006, 'samples': 1372224, 'steps': 7146, 'loss/train': 2.2848379611968994} 08/30/2021 14:27:49 - INFO - __main__ - Step 7148: {'lr': 0.0004985093948506689, 'samples': 1372416, 'steps': 7147, 'loss/train': 1.7950539588928223} 08/30/2021 14:27:50 - INFO - __main__ - Step 7149: {'lr': 0.0004985088161577628, 'samples': 1372608, 'steps': 7148, 'loss/train': 2.1088075637817383} 08/30/2021 14:27:50 - INFO - __main__ - Step 7150: {'lr': 0.0004985082373528825, 'samples': 1372800, 'steps': 7149, 'loss/train': 2.343796730041504} 08/30/2021 14:27:51 - INFO - __main__ - Step 7151: {'lr': 0.0004985076584360282, 'samples': 1372992, 'steps': 7150, 'loss/train': 1.1312609910964966} 08/30/2021 14:27:51 - INFO - __main__ - Step 7152: {'lr': 0.0004985070794072002, 'samples': 1373184, 'steps': 7151, 'loss/train': 2.176933765411377} 08/30/2021 14:27:53 - INFO - __main__ - Step 7153: {'lr': 0.0004985065002663986, 'samples': 1373376, 'steps': 7152, 'loss/train': 2.1957783699035645} 08/30/2021 14:27:53 - INFO - __main__ - Step 7154: {'lr': 0.000498505921013624, 'samples': 1373568, 'steps': 7153, 'loss/train': 1.7569538354873657} 08/30/2021 14:27:53 - INFO - __main__ - Step 7155: {'lr': 0.0004985053416488764, 'samples': 1373760, 'steps': 7154, 'loss/train': 2.051624059677124} 08/30/2021 14:27:54 - INFO - __main__ - Step 7156: {'lr': 0.0004985047621721561, 'samples': 1373952, 'steps': 7155, 'loss/train': 2.253840923309326} 08/30/2021 14:27:54 - INFO - __main__ - Step 7157: {'lr': 0.0004985041825834634, 'samples': 1374144, 'steps': 7156, 'loss/train': 2.9600563049316406} 08/30/2021 14:27:55 - INFO - __main__ - Step 7158: {'lr': 0.0004985036028827986, 'samples': 1374336, 'steps': 7157, 'loss/train': 2.6560614109039307} 08/30/2021 14:27:56 - INFO - __main__ - Step 7159: {'lr': 0.0004985030230701619, 'samples': 1374528, 'steps': 7158, 'loss/train': 1.9453258514404297} 08/30/2021 14:27:56 - INFO - __main__ - Step 7160: {'lr': 0.0004985024431455534, 'samples': 1374720, 'steps': 7159, 'loss/train': 2.2521843910217285} 08/30/2021 14:27:57 - INFO - __main__ - Step 7161: {'lr': 0.0004985018631089738, 'samples': 1374912, 'steps': 7160, 'loss/train': 2.00766658782959} 08/30/2021 14:27:57 - INFO - __main__ - Step 7162: {'lr': 0.0004985012829604228, 'samples': 1375104, 'steps': 7161, 'loss/train': 2.114105224609375} 08/30/2021 14:27:58 - INFO - __main__ - Step 7163: {'lr': 0.0004985007026999011, 'samples': 1375296, 'steps': 7162, 'loss/train': 2.3569719791412354} 08/30/2021 14:27:59 - INFO - __main__ - Step 7164: {'lr': 0.0004985001223274089, 'samples': 1375488, 'steps': 7163, 'loss/train': 2.06986927986145} 08/30/2021 14:27:59 - INFO - __main__ - Step 7165: {'lr': 0.0004984995418429463, 'samples': 1375680, 'steps': 7164, 'loss/train': 1.9990451335906982} 08/30/2021 14:28:00 - INFO - __main__ - Step 7166: {'lr': 0.0004984989612465137, 'samples': 1375872, 'steps': 7165, 'loss/train': 2.072549343109131} 08/30/2021 14:28:00 - INFO - __main__ - Step 7167: {'lr': 0.0004984983805381112, 'samples': 1376064, 'steps': 7166, 'loss/train': 1.874739408493042} 08/30/2021 14:28:00 - INFO - __main__ - Step 7168: {'lr': 0.0004984977997177393, 'samples': 1376256, 'steps': 7167, 'loss/train': 2.100863218307495} 08/30/2021 14:28:02 - INFO - __main__ - Step 7169: {'lr': 0.000498497218785398, 'samples': 1376448, 'steps': 7168, 'loss/train': 2.31718373298645} 08/30/2021 14:28:03 - INFO - __main__ - Step 7170: {'lr': 0.0004984966377410878, 'samples': 1376640, 'steps': 7169, 'loss/train': 1.911266565322876} 08/30/2021 14:28:03 - INFO - __main__ - Step 7171: {'lr': 0.0004984960565848086, 'samples': 1376832, 'steps': 7170, 'loss/train': 1.6877858638763428} 08/30/2021 14:28:03 - INFO - __main__ - Step 7172: {'lr': 0.0004984954753165612, 'samples': 1377024, 'steps': 7171, 'loss/train': 1.5156139135360718} 08/30/2021 14:28:04 - INFO - __main__ - Step 7173: {'lr': 0.0004984948939363455, 'samples': 1377216, 'steps': 7172, 'loss/train': 1.1622527837753296} 08/30/2021 14:28:05 - INFO - __main__ - Step 7174: {'lr': 0.0004984943124441617, 'samples': 1377408, 'steps': 7173, 'loss/train': 0.2638666033744812} 08/30/2021 14:28:06 - INFO - __main__ - Step 7175: {'lr': 0.0004984937308400104, 'samples': 1377600, 'steps': 7174, 'loss/train': 2.5236616134643555} 08/30/2021 14:28:06 - INFO - __main__ - Step 7176: {'lr': 0.0004984931491238915, 'samples': 1377792, 'steps': 7175, 'loss/train': 1.7262253761291504} 08/30/2021 14:28:06 - INFO - __main__ - Step 7177: {'lr': 0.0004984925672958055, 'samples': 1377984, 'steps': 7176, 'loss/train': 2.168788194656372} 08/30/2021 14:28:07 - INFO - __main__ - Step 7178: {'lr': 0.0004984919853557526, 'samples': 1378176, 'steps': 7177, 'loss/train': 2.1983604431152344} 08/30/2021 14:28:07 - INFO - __main__ - Step 7179: {'lr': 0.000498491403303733, 'samples': 1378368, 'steps': 7178, 'loss/train': 1.6143860816955566} 08/30/2021 14:28:09 - INFO - __main__ - Step 7180: {'lr': 0.000498490821139747, 'samples': 1378560, 'steps': 7179, 'loss/train': 2.6613736152648926} 08/30/2021 14:28:09 - INFO - __main__ - Step 7181: {'lr': 0.0004984902388637949, 'samples': 1378752, 'steps': 7180, 'loss/train': 1.8948392868041992} 08/30/2021 14:28:10 - INFO - __main__ - Step 7182: {'lr': 0.000498489656475877, 'samples': 1378944, 'steps': 7181, 'loss/train': 2.170236587524414} 08/30/2021 14:28:10 - INFO - __main__ - Step 7183: {'lr': 0.0004984890739759934, 'samples': 1379136, 'steps': 7182, 'loss/train': 2.422713041305542} 08/30/2021 14:28:10 - INFO - __main__ - Step 7184: {'lr': 0.0004984884913641444, 'samples': 1379328, 'steps': 7183, 'loss/train': 3.144796371459961} 08/30/2021 14:28:12 - INFO - __main__ - Step 7185: {'lr': 0.0004984879086403304, 'samples': 1379520, 'steps': 7184, 'loss/train': 2.126748561859131} 08/30/2021 14:28:13 - INFO - __main__ - Step 7186: {'lr': 0.0004984873258045517, 'samples': 1379712, 'steps': 7185, 'loss/train': 1.6775095462799072} 08/30/2021 14:28:13 - INFO - __main__ - Step 7187: {'lr': 0.0004984867428568083, 'samples': 1379904, 'steps': 7186, 'loss/train': 1.8703340291976929} 08/30/2021 14:28:14 - INFO - __main__ - Step 7188: {'lr': 0.0004984861597971006, 'samples': 1380096, 'steps': 7187, 'loss/train': 2.2406716346740723} 08/30/2021 14:28:14 - INFO - __main__ - Step 7189: {'lr': 0.000498485576625429, 'samples': 1380288, 'steps': 7188, 'loss/train': 1.5232924222946167} 08/30/2021 14:28:15 - INFO - __main__ - Step 7190: {'lr': 0.0004984849933417935, 'samples': 1380480, 'steps': 7189, 'loss/train': 1.4126814603805542} 08/30/2021 14:28:16 - INFO - __main__ - Step 7191: {'lr': 0.0004984844099461945, 'samples': 1380672, 'steps': 7190, 'loss/train': 1.9961045980453491} 08/30/2021 14:28:16 - INFO - __main__ - Step 7192: {'lr': 0.0004984838264386322, 'samples': 1380864, 'steps': 7191, 'loss/train': 0.8886036276817322} 08/30/2021 14:28:17 - INFO - __main__ - Step 7193: {'lr': 0.000498483242819107, 'samples': 1381056, 'steps': 7192, 'loss/train': 2.149461030960083} 08/30/2021 14:28:17 - INFO - __main__ - Step 7194: {'lr': 0.0004984826590876192, 'samples': 1381248, 'steps': 7193, 'loss/train': 2.0714566707611084} 08/30/2021 14:28:17 - INFO - __main__ - Step 7195: {'lr': 0.0004984820752441688, 'samples': 1381440, 'steps': 7194, 'loss/train': 2.455793857574463} 08/30/2021 14:28:19 - INFO - __main__ - Step 7196: {'lr': 0.0004984814912887563, 'samples': 1381632, 'steps': 7195, 'loss/train': 1.7198436260223389} 08/30/2021 14:28:19 - INFO - __main__ - Step 7197: {'lr': 0.0004984809072213818, 'samples': 1381824, 'steps': 7196, 'loss/train': 2.2517521381378174} 08/30/2021 14:28:20 - INFO - __main__ - Step 7198: {'lr': 0.0004984803230420457, 'samples': 1382016, 'steps': 7197, 'loss/train': 1.8150054216384888} 08/30/2021 14:28:20 - INFO - __main__ - Step 7199: {'lr': 0.0004984797387507481, 'samples': 1382208, 'steps': 7198, 'loss/train': 1.7893643379211426} 08/30/2021 14:28:20 - INFO - __main__ - Step 7200: {'lr': 0.0004984791543474896, 'samples': 1382400, 'steps': 7199, 'loss/train': 2.0862998962402344} 08/30/2021 14:28:22 - INFO - __main__ - Step 7201: {'lr': 0.0004984785698322699, 'samples': 1382592, 'steps': 7200, 'loss/train': 1.967714786529541} 08/30/2021 14:28:23 - INFO - __main__ - Step 7202: {'lr': 0.0004984779852050898, 'samples': 1382784, 'steps': 7201, 'loss/train': 1.6195945739746094} 08/30/2021 14:28:23 - INFO - __main__ - Step 7203: {'lr': 0.0004984774004659493, 'samples': 1382976, 'steps': 7202, 'loss/train': 1.4425938129425049} 08/30/2021 14:28:23 - INFO - __main__ - Step 7204: {'lr': 0.0004984768156148489, 'samples': 1383168, 'steps': 7203, 'loss/train': 2.1850192546844482} 08/30/2021 14:28:24 - INFO - __main__ - Step 7205: {'lr': 0.0004984762306517883, 'samples': 1383360, 'steps': 7204, 'loss/train': 1.778074860572815} 08/30/2021 14:28:25 - INFO - __main__ - Step 7206: {'lr': 0.0004984756455767684, 'samples': 1383552, 'steps': 7205, 'loss/train': 2.0839364528656006} 08/30/2021 14:28:26 - INFO - __main__ - Step 7207: {'lr': 0.0004984750603897892, 'samples': 1383744, 'steps': 7206, 'loss/train': 1.8351918458938599} 08/30/2021 14:28:26 - INFO - __main__ - Step 7208: {'lr': 0.0004984744750908509, 'samples': 1383936, 'steps': 7207, 'loss/train': 1.970173954963684} 08/30/2021 14:28:26 - INFO - __main__ - Step 7209: {'lr': 0.0004984738896799539, 'samples': 1384128, 'steps': 7208, 'loss/train': 2.300081729888916} 08/30/2021 14:28:27 - INFO - __main__ - Step 7210: {'lr': 0.0004984733041570983, 'samples': 1384320, 'steps': 7209, 'loss/train': 1.91078519821167} 08/30/2021 14:28:27 - INFO - __main__ - Step 7211: {'lr': 0.0004984727185222846, 'samples': 1384512, 'steps': 7210, 'loss/train': 1.4283580780029297} 08/30/2021 14:28:29 - INFO - __main__ - Step 7212: {'lr': 0.0004984721327755128, 'samples': 1384704, 'steps': 7211, 'loss/train': 2.2765932083129883} 08/30/2021 14:28:29 - INFO - __main__ - Step 7213: {'lr': 0.0004984715469167835, 'samples': 1384896, 'steps': 7212, 'loss/train': 5.389716625213623} 08/30/2021 14:28:29 - INFO - __main__ - Step 7214: {'lr': 0.0004984709609460966, 'samples': 1385088, 'steps': 7213, 'loss/train': 1.9275394678115845} 08/30/2021 14:28:30 - INFO - __main__ - Step 7215: {'lr': 0.0004984703748634524, 'samples': 1385280, 'steps': 7214, 'loss/train': 2.6016764640808105} 08/30/2021 14:28:30 - INFO - __main__ - Step 7216: {'lr': 0.0004984697886688514, 'samples': 1385472, 'steps': 7215, 'loss/train': 1.416304111480713} 08/30/2021 14:28:32 - INFO - __main__ - Step 7217: {'lr': 0.0004984692023622938, 'samples': 1385664, 'steps': 7216, 'loss/train': 2.0171456336975098} 08/30/2021 14:28:32 - INFO - __main__ - Step 7218: {'lr': 0.0004984686159437798, 'samples': 1385856, 'steps': 7217, 'loss/train': 2.2392613887786865} 08/30/2021 14:28:32 - INFO - __main__ - Step 7219: {'lr': 0.0004984680294133096, 'samples': 1386048, 'steps': 7218, 'loss/train': 1.8295966386795044} 08/30/2021 14:28:33 - INFO - __main__ - Step 7220: {'lr': 0.0004984674427708836, 'samples': 1386240, 'steps': 7219, 'loss/train': 1.8244532346725464} 08/30/2021 14:28:33 - INFO - __main__ - Step 7221: {'lr': 0.000498466856016502, 'samples': 1386432, 'steps': 7220, 'loss/train': 0.27827927470207214} 08/30/2021 14:28:35 - INFO - __main__ - Step 7222: {'lr': 0.000498466269150165, 'samples': 1386624, 'steps': 7221, 'loss/train': 2.1558480262756348} 08/30/2021 14:28:35 - INFO - __main__ - Step 7223: {'lr': 0.000498465682171873, 'samples': 1386816, 'steps': 7222, 'loss/train': 2.070441484451294} 08/30/2021 14:28:36 - INFO - __main__ - Step 7224: {'lr': 0.0004984650950816262, 'samples': 1387008, 'steps': 7223, 'loss/train': 1.7885586023330688} 08/30/2021 14:28:36 - INFO - __main__ - Step 7225: {'lr': 0.0004984645078794248, 'samples': 1387200, 'steps': 7224, 'loss/train': 1.909603238105774} 08/30/2021 14:28:36 - INFO - __main__ - Step 7226: {'lr': 0.0004984639205652692, 'samples': 1387392, 'steps': 7225, 'loss/train': 2.0837244987487793} 08/30/2021 14:28:39 - INFO - __main__ - Step 7227: {'lr': 0.0004984633331391596, 'samples': 1387584, 'steps': 7226, 'loss/train': 1.5744858980178833} 08/30/2021 14:28:39 - INFO - __main__ - Step 7228: {'lr': 0.0004984627456010962, 'samples': 1387776, 'steps': 7227, 'loss/train': 1.8887664079666138} 08/30/2021 14:28:40 - INFO - __main__ - Step 7229: {'lr': 0.0004984621579510794, 'samples': 1387968, 'steps': 7228, 'loss/train': 2.21808123588562} 08/30/2021 14:28:40 - INFO - __main__ - Step 7230: {'lr': 0.0004984615701891093, 'samples': 1388160, 'steps': 7229, 'loss/train': 2.937943935394287} 08/30/2021 14:28:41 - INFO - __main__ - Step 7231: {'lr': 0.0004984609823151863, 'samples': 1388352, 'steps': 7230, 'loss/train': 1.2554011344909668} 08/30/2021 14:28:41 - INFO - __main__ - Step 7232: {'lr': 0.0004984603943293106, 'samples': 1388544, 'steps': 7231, 'loss/train': 1.3749245405197144} 08/30/2021 14:28:41 - INFO - __main__ - Step 7233: {'lr': 0.0004984598062314824, 'samples': 1388736, 'steps': 7232, 'loss/train': 2.8922464847564697} 08/30/2021 14:28:42 - INFO - __main__ - Step 7234: {'lr': 0.0004984592180217022, 'samples': 1388928, 'steps': 7233, 'loss/train': 2.127946376800537} 08/30/2021 14:28:43 - INFO - __main__ - Step 7235: {'lr': 0.00049845862969997, 'samples': 1389120, 'steps': 7234, 'loss/train': 2.808744192123413} 08/30/2021 14:28:44 - INFO - __main__ - Step 7236: {'lr': 0.0004984580412662862, 'samples': 1389312, 'steps': 7235, 'loss/train': 1.8293496370315552} 08/30/2021 14:28:44 - INFO - __main__ - Step 7237: {'lr': 0.000498457452720651, 'samples': 1389504, 'steps': 7236, 'loss/train': 0.6578748822212219} 08/30/2021 14:28:44 - INFO - __main__ - Step 7238: {'lr': 0.0004984568640630648, 'samples': 1389696, 'steps': 7237, 'loss/train': 2.1225314140319824} 08/30/2021 14:28:45 - INFO - __main__ - Step 7239: {'lr': 0.0004984562752935278, 'samples': 1389888, 'steps': 7238, 'loss/train': 3.227290153503418} 08/30/2021 14:28:46 - INFO - __main__ - Step 7240: {'lr': 0.0004984556864120401, 'samples': 1390080, 'steps': 7239, 'loss/train': 2.11092472076416} 08/30/2021 14:28:47 - INFO - __main__ - Step 7241: {'lr': 0.0004984550974186021, 'samples': 1390272, 'steps': 7240, 'loss/train': 2.6050875186920166} 08/30/2021 14:28:47 - INFO - __main__ - Step 7242: {'lr': 0.0004984545083132142, 'samples': 1390464, 'steps': 7241, 'loss/train': 1.6543530225753784} 08/30/2021 14:28:48 - INFO - __main__ - Step 7243: {'lr': 0.0004984539190958765, 'samples': 1390656, 'steps': 7242, 'loss/train': 7.976821422576904} 08/30/2021 14:28:48 - INFO - __main__ - Step 7244: {'lr': 0.0004984533297665892, 'samples': 1390848, 'steps': 7243, 'loss/train': 7.9502434730529785} 08/30/2021 14:28:48 - INFO - __main__ - Step 7245: {'lr': 0.0004984527403253527, 'samples': 1391040, 'steps': 7244, 'loss/train': 0.6018803715705872} 08/30/2021 14:28:49 - INFO - __main__ - Step 7246: {'lr': 0.0004984521507721672, 'samples': 1391232, 'steps': 7245, 'loss/train': 2.226489782333374} 08/30/2021 14:28:51 - INFO - __main__ - Step 7247: {'lr': 0.0004984515611070331, 'samples': 1391424, 'steps': 7246, 'loss/train': 1.9661298990249634} 08/30/2021 14:28:52 - INFO - __main__ - Step 7248: {'lr': 0.0004984509713299505, 'samples': 1391616, 'steps': 7247, 'loss/train': 3.112241744995117} 08/30/2021 14:28:52 - INFO - __main__ - Step 7249: {'lr': 0.0004984503814409198, 'samples': 1391808, 'steps': 7248, 'loss/train': 3.0227649211883545} 08/30/2021 14:28:52 - INFO - __main__ - Step 7250: {'lr': 0.000498449791439941, 'samples': 1392000, 'steps': 7249, 'loss/train': 0.5346341729164124} 08/30/2021 14:28:53 - INFO - __main__ - Step 7251: {'lr': 0.0004984492013270147, 'samples': 1392192, 'steps': 7250, 'loss/train': 2.410288095474243} 08/30/2021 14:28:53 - INFO - __main__ - Step 7252: {'lr': 0.0004984486111021411, 'samples': 1392384, 'steps': 7251, 'loss/train': 2.261244773864746} 08/30/2021 14:28:53 - INFO - __main__ - Step 7253: {'lr': 0.0004984480207653202, 'samples': 1392576, 'steps': 7252, 'loss/train': 3.137852191925049} 08/30/2021 14:28:55 - INFO - __main__ - Step 7254: {'lr': 0.0004984474303165526, 'samples': 1392768, 'steps': 7253, 'loss/train': 3.3458287715911865} 08/30/2021 14:28:56 - INFO - __main__ - Step 7255: {'lr': 0.0004984468397558384, 'samples': 1392960, 'steps': 7254, 'loss/train': 2.5857832431793213} 08/30/2021 14:28:56 - INFO - __main__ - Step 7256: {'lr': 0.0004984462490831778, 'samples': 1393152, 'steps': 7255, 'loss/train': 2.4637887477874756} 08/30/2021 14:28:56 - INFO - __main__ - Step 7257: {'lr': 0.0004984456582985713, 'samples': 1393344, 'steps': 7256, 'loss/train': 1.8142101764678955} 08/30/2021 14:28:57 - INFO - __main__ - Step 7258: {'lr': 0.0004984450674020189, 'samples': 1393536, 'steps': 7257, 'loss/train': 2.649630546569824} 08/30/2021 14:28:58 - INFO - __main__ - Step 7259: {'lr': 0.000498444476393521, 'samples': 1393728, 'steps': 7258, 'loss/train': 2.293332815170288} 08/30/2021 14:28:59 - INFO - __main__ - Step 7260: {'lr': 0.0004984438852730779, 'samples': 1393920, 'steps': 7259, 'loss/train': 1.4812675714492798} 08/30/2021 14:28:59 - INFO - __main__ - Step 7261: {'lr': 0.0004984432940406898, 'samples': 1394112, 'steps': 7260, 'loss/train': 2.5667483806610107} 08/30/2021 14:28:59 - INFO - __main__ - Step 7262: {'lr': 0.0004984427026963569, 'samples': 1394304, 'steps': 7261, 'loss/train': 2.730210781097412} 08/30/2021 14:29:00 - INFO - __main__ - Step 7263: {'lr': 0.0004984421112400796, 'samples': 1394496, 'steps': 7262, 'loss/train': 2.477018356323242} 08/30/2021 14:29:01 - INFO - __main__ - Step 7264: {'lr': 0.0004984415196718582, 'samples': 1394688, 'steps': 7263, 'loss/train': 2.386280059814453} 08/30/2021 14:29:02 - INFO - __main__ - Step 7265: {'lr': 0.0004984409279916929, 'samples': 1394880, 'steps': 7264, 'loss/train': 2.290518045425415} 08/30/2021 14:29:02 - INFO - __main__ - Step 7266: {'lr': 0.0004984403361995839, 'samples': 1395072, 'steps': 7265, 'loss/train': 2.308997869491577} 08/30/2021 14:29:02 - INFO - __main__ - Step 7267: {'lr': 0.0004984397442955315, 'samples': 1395264, 'steps': 7266, 'loss/train': 2.263298988342285} 08/30/2021 14:29:03 - INFO - __main__ - Step 7268: {'lr': 0.0004984391522795359, 'samples': 1395456, 'steps': 7267, 'loss/train': 2.382741689682007} 08/30/2021 14:29:04 - INFO - __main__ - Step 7269: {'lr': 0.0004984385601515977, 'samples': 1395648, 'steps': 7268, 'loss/train': 2.2990920543670654} 08/30/2021 14:29:05 - INFO - __main__ - Step 7270: {'lr': 0.0004984379679117166, 'samples': 1395840, 'steps': 7269, 'loss/train': 2.7670998573303223} 08/30/2021 14:29:05 - INFO - __main__ - Step 7271: {'lr': 0.0004984373755598934, 'samples': 1396032, 'steps': 7270, 'loss/train': 2.1212124824523926} 08/30/2021 14:29:05 - INFO - __main__ - Step 7272: {'lr': 0.0004984367830961281, 'samples': 1396224, 'steps': 7271, 'loss/train': 2.1122045516967773} 08/30/2021 14:29:06 - INFO - __main__ - Step 7273: {'lr': 0.0004984361905204209, 'samples': 1396416, 'steps': 7272, 'loss/train': 2.5294036865234375} 08/30/2021 14:29:07 - INFO - __main__ - Step 7274: {'lr': 0.0004984355978327724, 'samples': 1396608, 'steps': 7273, 'loss/train': 2.684483528137207} 08/30/2021 14:29:08 - INFO - __main__ - Step 7275: {'lr': 0.0004984350050331826, 'samples': 1396800, 'steps': 7274, 'loss/train': 2.8753700256347656} 08/30/2021 14:29:08 - INFO - __main__ - Step 7276: {'lr': 0.0004984344121216518, 'samples': 1396992, 'steps': 7275, 'loss/train': 2.7209572792053223} 08/30/2021 14:29:08 - INFO - __main__ - Step 7277: {'lr': 0.0004984338190981802, 'samples': 1397184, 'steps': 7276, 'loss/train': 2.787548780441284} 08/30/2021 14:29:09 - INFO - __main__ - Step 7278: {'lr': 0.0004984332259627682, 'samples': 1397376, 'steps': 7277, 'loss/train': 1.2269775867462158} 08/30/2021 14:29:11 - INFO - __main__ - Step 7279: {'lr': 0.000498432632715416, 'samples': 1397568, 'steps': 7278, 'loss/train': 2.464550733566284} 08/30/2021 14:29:11 - INFO - __main__ - Step 7280: {'lr': 0.000498432039356124, 'samples': 1397760, 'steps': 7279, 'loss/train': 2.4765076637268066} 08/30/2021 14:29:12 - INFO - __main__ - Step 7281: {'lr': 0.0004984314458848923, 'samples': 1397952, 'steps': 7280, 'loss/train': 0.7683911919593811} 08/30/2021 14:29:12 - INFO - __main__ - Step 7282: {'lr': 0.0004984308523017212, 'samples': 1398144, 'steps': 7281, 'loss/train': 1.5597885847091675} 08/30/2021 14:29:12 - INFO - __main__ - Step 7283: {'lr': 0.000498430258606611, 'samples': 1398336, 'steps': 7282, 'loss/train': 2.402383804321289} 08/30/2021 14:29:14 - INFO - __main__ - Step 7284: {'lr': 0.000498429664799562, 'samples': 1398528, 'steps': 7283, 'loss/train': 0.47472572326660156} 08/30/2021 14:29:15 - INFO - __main__ - Step 7285: {'lr': 0.0004984290708805743, 'samples': 1398720, 'steps': 7284, 'loss/train': 1.5766929388046265} 08/30/2021 14:29:15 - INFO - __main__ - Step 7286: {'lr': 0.0004984284768496484, 'samples': 1398912, 'steps': 7285, 'loss/train': 2.2995853424072266} 08/30/2021 14:29:15 - INFO - __main__ - Step 7287: {'lr': 0.0004984278827067844, 'samples': 1399104, 'steps': 7286, 'loss/train': 2.6046810150146484} 08/30/2021 14:29:16 - INFO - __main__ - Step 7288: {'lr': 0.0004984272884519827, 'samples': 1399296, 'steps': 7287, 'loss/train': 1.3832066059112549} 08/30/2021 14:29:16 - INFO - __main__ - Step 7289: {'lr': 0.0004984266940852434, 'samples': 1399488, 'steps': 7288, 'loss/train': 2.2288410663604736} 08/30/2021 14:29:17 - INFO - __main__ - Step 7290: {'lr': 0.0004984260996065671, 'samples': 1399680, 'steps': 7289, 'loss/train': 2.1831796169281006} 08/30/2021 14:29:18 - INFO - __main__ - Step 7291: {'lr': 0.0004984255050159536, 'samples': 1399872, 'steps': 7290, 'loss/train': 1.6125967502593994} 08/30/2021 14:29:18 - INFO - __main__ - Step 7292: {'lr': 0.0004984249103134035, 'samples': 1400064, 'steps': 7291, 'loss/train': 2.1078720092773438} 08/30/2021 14:29:18 - INFO - __main__ - Step 7293: {'lr': 0.0004984243154989168, 'samples': 1400256, 'steps': 7292, 'loss/train': 2.4023003578186035} 08/30/2021 14:29:19 - INFO - __main__ - Step 7294: {'lr': 0.0004984237205724942, 'samples': 1400448, 'steps': 7293, 'loss/train': 2.2205755710601807} 08/30/2021 14:29:21 - INFO - __main__ - Step 7295: {'lr': 0.0004984231255341355, 'samples': 1400640, 'steps': 7294, 'loss/train': 1.6430696249008179} 08/30/2021 14:29:21 - INFO - __main__ - Step 7296: {'lr': 0.0004984225303838413, 'samples': 1400832, 'steps': 7295, 'loss/train': 1.9313017129898071} 08/30/2021 14:29:21 - INFO - __main__ - Step 7297: {'lr': 0.0004984219351216116, 'samples': 1401024, 'steps': 7296, 'loss/train': 2.0928707122802734} 08/30/2021 14:29:22 - INFO - __main__ - Step 7298: {'lr': 0.000498421339747447, 'samples': 1401216, 'steps': 7297, 'loss/train': 1.7971556186676025} 08/30/2021 14:29:22 - INFO - __main__ - Step 7299: {'lr': 0.0004984207442613474, 'samples': 1401408, 'steps': 7298, 'loss/train': 2.812422037124634} 08/30/2021 14:29:25 - INFO - __main__ - Step 7300: {'lr': 0.0004984201486633134, 'samples': 1401600, 'steps': 7299, 'loss/train': 2.3023829460144043} 08/30/2021 14:29:25 - INFO - __main__ - Step 7301: {'lr': 0.0004984195529533451, 'samples': 1401792, 'steps': 7300, 'loss/train': 2.187779426574707} 08/30/2021 14:29:26 - INFO - __main__ - Step 7302: {'lr': 0.0004984189571314426, 'samples': 1401984, 'steps': 7301, 'loss/train': 1.8578436374664307} 08/30/2021 14:29:26 - INFO - __main__ - Step 7303: {'lr': 0.0004984183611976065, 'samples': 1402176, 'steps': 7302, 'loss/train': 2.4243733882904053} 08/30/2021 14:29:26 - INFO - __main__ - Step 7304: {'lr': 0.0004984177651518369, 'samples': 1402368, 'steps': 7303, 'loss/train': 2.580448627471924} 08/30/2021 14:29:27 - INFO - __main__ - Step 7305: {'lr': 0.0004984171689941341, 'samples': 1402560, 'steps': 7304, 'loss/train': 1.3540310859680176} 08/30/2021 14:29:28 - INFO - __main__ - Step 7306: {'lr': 0.0004984165727244984, 'samples': 1402752, 'steps': 7305, 'loss/train': 0.48593971133232117} 08/30/2021 14:29:29 - INFO - __main__ - Step 7307: {'lr': 0.0004984159763429299, 'samples': 1402944, 'steps': 7306, 'loss/train': 0.3630259335041046} 08/30/2021 14:29:29 - INFO - __main__ - Step 7308: {'lr': 0.0004984153798494291, 'samples': 1403136, 'steps': 7307, 'loss/train': 2.3465182781219482} 08/30/2021 14:29:30 - INFO - __main__ - Step 7309: {'lr': 0.000498414783243996, 'samples': 1403328, 'steps': 7308, 'loss/train': 2.074223279953003} 08/30/2021 14:29:30 - INFO - __main__ - Step 7310: {'lr': 0.0004984141865266312, 'samples': 1403520, 'steps': 7309, 'loss/train': 2.2703497409820557} 08/30/2021 14:29:31 - INFO - __main__ - Step 7311: {'lr': 0.0004984135896973348, 'samples': 1403712, 'steps': 7310, 'loss/train': 2.1518030166625977} 08/30/2021 14:29:32 - INFO - __main__ - Step 7312: {'lr': 0.000498412992756107, 'samples': 1403904, 'steps': 7311, 'loss/train': 1.5375657081604004} 08/30/2021 14:29:32 - INFO - __main__ - Step 7313: {'lr': 0.0004984123957029482, 'samples': 1404096, 'steps': 7312, 'loss/train': 2.6248369216918945} 08/30/2021 14:29:33 - INFO - __main__ - Step 7314: {'lr': 0.0004984117985378586, 'samples': 1404288, 'steps': 7313, 'loss/train': 2.0702261924743652} 08/30/2021 14:29:33 - INFO - __main__ - Step 7315: {'lr': 0.0004984112012608384, 'samples': 1404480, 'steps': 7314, 'loss/train': 1.9362568855285645} 08/30/2021 14:29:34 - INFO - __main__ - Step 7316: {'lr': 0.000498410603871888, 'samples': 1404672, 'steps': 7315, 'loss/train': 2.604275941848755} 08/30/2021 14:29:35 - INFO - __main__ - Step 7317: {'lr': 0.0004984100063710076, 'samples': 1404864, 'steps': 7316, 'loss/train': 2.0040323734283447} 08/30/2021 14:29:35 - INFO - __main__ - Step 7318: {'lr': 0.0004984094087581975, 'samples': 1405056, 'steps': 7317, 'loss/train': 2.2937192916870117} 08/30/2021 14:29:36 - INFO - __main__ - Step 7319: {'lr': 0.0004984088110334579, 'samples': 1405248, 'steps': 7318, 'loss/train': 2.2699267864227295} 08/30/2021 14:29:36 - INFO - __main__ - Step 7320: {'lr': 0.0004984082131967892, 'samples': 1405440, 'steps': 7319, 'loss/train': 2.281672954559326} 08/30/2021 14:29:38 - INFO - __main__ - Step 7321: {'lr': 0.0004984076152481916, 'samples': 1405632, 'steps': 7320, 'loss/train': 2.3214380741119385} 08/30/2021 14:29:38 - INFO - __main__ - Step 7322: {'lr': 0.0004984070171876653, 'samples': 1405824, 'steps': 7321, 'loss/train': 1.8340390920639038} 08/30/2021 14:29:39 - INFO - __main__ - Step 7323: {'lr': 0.0004984064190152106, 'samples': 1406016, 'steps': 7322, 'loss/train': 2.1536357402801514} 08/30/2021 14:29:39 - INFO - __main__ - Step 7324: {'lr': 0.0004984058207308279, 'samples': 1406208, 'steps': 7323, 'loss/train': 2.2334518432617188} 08/30/2021 14:29:39 - INFO - __main__ - Step 7325: {'lr': 0.0004984052223345174, 'samples': 1406400, 'steps': 7324, 'loss/train': 2.2364373207092285} 08/30/2021 14:29:40 - INFO - __main__ - Step 7326: {'lr': 0.0004984046238262792, 'samples': 1406592, 'steps': 7325, 'loss/train': 2.1886324882507324} 08/30/2021 14:29:41 - INFO - __main__ - Step 7327: {'lr': 0.0004984040252061137, 'samples': 1406784, 'steps': 7326, 'loss/train': 1.6918123960494995} 08/30/2021 14:29:42 - INFO - __main__ - Step 7328: {'lr': 0.0004984034264740213, 'samples': 1406976, 'steps': 7327, 'loss/train': 2.175912618637085} 08/30/2021 14:29:42 - INFO - __main__ - Step 7329: {'lr': 0.0004984028276300021, 'samples': 1407168, 'steps': 7328, 'loss/train': 0.998396098613739} 08/30/2021 14:29:42 - INFO - __main__ - Step 7330: {'lr': 0.0004984022286740565, 'samples': 1407360, 'steps': 7329, 'loss/train': 2.3154714107513428} 08/30/2021 14:29:43 - INFO - __main__ - Step 7331: {'lr': 0.0004984016296061846, 'samples': 1407552, 'steps': 7330, 'loss/train': 2.078317880630493} 08/30/2021 14:29:44 - INFO - __main__ - Step 7332: {'lr': 0.0004984010304263868, 'samples': 1407744, 'steps': 7331, 'loss/train': 2.328183889389038} 08/30/2021 14:29:45 - INFO - __main__ - Step 7333: {'lr': 0.0004984004311346632, 'samples': 1407936, 'steps': 7332, 'loss/train': 2.2446072101593018} 08/30/2021 14:29:45 - INFO - __main__ - Step 7334: {'lr': 0.0004983998317310143, 'samples': 1408128, 'steps': 7333, 'loss/train': 2.094515323638916} 08/30/2021 14:29:45 - INFO - __main__ - Step 7335: {'lr': 0.0004983992322154403, 'samples': 1408320, 'steps': 7334, 'loss/train': 2.0975446701049805} 08/30/2021 14:29:46 - INFO - __main__ - Step 7336: {'lr': 0.0004983986325879414, 'samples': 1408512, 'steps': 7335, 'loss/train': 2.3745675086975098} 08/30/2021 14:29:47 - INFO - __main__ - Step 7337: {'lr': 0.0004983980328485179, 'samples': 1408704, 'steps': 7336, 'loss/train': 2.052238702774048} 08/30/2021 14:29:48 - INFO - __main__ - Step 7338: {'lr': 0.0004983974329971702, 'samples': 1408896, 'steps': 7337, 'loss/train': 2.013025999069214} 08/30/2021 14:29:48 - INFO - __main__ - Step 7339: {'lr': 0.0004983968330338983, 'samples': 1409088, 'steps': 7338, 'loss/train': 2.086759328842163} 08/30/2021 14:29:48 - INFO - __main__ - Step 7340: {'lr': 0.0004983962329587026, 'samples': 1409280, 'steps': 7339, 'loss/train': 2.233823299407959} 08/30/2021 14:29:49 - INFO - __main__ - Step 7341: {'lr': 0.0004983956327715835, 'samples': 1409472, 'steps': 7340, 'loss/train': 1.8948982954025269} 08/30/2021 14:29:50 - INFO - __main__ - Step 7342: {'lr': 0.000498395032472541, 'samples': 1409664, 'steps': 7341, 'loss/train': 2.163719892501831} 08/30/2021 14:29:51 - INFO - __main__ - Step 7343: {'lr': 0.0004983944320615757, 'samples': 1409856, 'steps': 7342, 'loss/train': 2.064788579940796} 08/30/2021 14:29:51 - INFO - __main__ - Step 7344: {'lr': 0.0004983938315386877, 'samples': 1410048, 'steps': 7343, 'loss/train': 2.149324893951416} 08/30/2021 14:29:51 - INFO - __main__ - Step 7345: {'lr': 0.0004983932309038773, 'samples': 1410240, 'steps': 7344, 'loss/train': 1.6421600580215454} 08/30/2021 14:29:52 - INFO - __main__ - Step 7346: {'lr': 0.0004983926301571445, 'samples': 1410432, 'steps': 7345, 'loss/train': 1.915958046913147} 08/30/2021 14:29:52 - INFO - __main__ - Step 7347: {'lr': 0.00049839202929849, 'samples': 1410624, 'steps': 7346, 'loss/train': 2.089918613433838} 08/30/2021 14:29:54 - INFO - __main__ - Step 7348: {'lr': 0.0004983914283279139, 'samples': 1410816, 'steps': 7347, 'loss/train': 2.4067695140838623} 08/30/2021 14:29:54 - INFO - __main__ - Step 7349: {'lr': 0.0004983908272454164, 'samples': 1411008, 'steps': 7348, 'loss/train': 1.8284673690795898} 08/30/2021 14:29:55 - INFO - __main__ - Step 7350: {'lr': 0.0004983902260509978, 'samples': 1411200, 'steps': 7349, 'loss/train': 0.35611075162887573} 08/30/2021 14:29:55 - INFO - __main__ - Step 7351: {'lr': 0.0004983896247446585, 'samples': 1411392, 'steps': 7350, 'loss/train': 2.664098024368286} 08/30/2021 14:29:55 - INFO - __main__ - Step 7352: {'lr': 0.0004983890233263986, 'samples': 1411584, 'steps': 7351, 'loss/train': 2.089432716369629} 08/30/2021 14:29:56 - INFO - __main__ - Step 7353: {'lr': 0.0004983884217962185, 'samples': 1411776, 'steps': 7352, 'loss/train': 0.6431196928024292} 08/30/2021 14:29:57 - INFO - __main__ - Step 7354: {'lr': 0.0004983878201541183, 'samples': 1411968, 'steps': 7353, 'loss/train': 0.7944732308387756} 08/30/2021 14:29:58 - INFO - __main__ - Step 7355: {'lr': 0.0004983872184000984, 'samples': 1412160, 'steps': 7354, 'loss/train': 2.156621217727661} 08/30/2021 14:29:58 - INFO - __main__ - Step 7356: {'lr': 0.0004983866165341592, 'samples': 1412352, 'steps': 7355, 'loss/train': 2.0597763061523438} 08/30/2021 14:29:59 - INFO - __main__ - Step 7357: {'lr': 0.0004983860145563006, 'samples': 1412544, 'steps': 7356, 'loss/train': 1.9994845390319824} 08/30/2021 14:29:59 - INFO - __main__ - Step 7358: {'lr': 0.0004983854124665232, 'samples': 1412736, 'steps': 7357, 'loss/train': 2.909639596939087} 08/30/2021 14:30:00 - INFO - __main__ - Step 7359: {'lr': 0.0004983848102648273, 'samples': 1412928, 'steps': 7358, 'loss/train': 1.9383361339569092} 08/30/2021 14:30:01 - INFO - __main__ - Step 7360: {'lr': 0.0004983842079512128, 'samples': 1413120, 'steps': 7359, 'loss/train': 1.5737757682800293} 08/30/2021 14:30:01 - INFO - __main__ - Step 7361: {'lr': 0.0004983836055256804, 'samples': 1413312, 'steps': 7360, 'loss/train': 2.7860159873962402} 08/30/2021 14:30:02 - INFO - __main__ - Step 7362: {'lr': 0.0004983830029882301, 'samples': 1413504, 'steps': 7361, 'loss/train': 1.4995863437652588} 08/30/2021 14:30:02 - INFO - __main__ - Step 7363: {'lr': 0.0004983824003388622, 'samples': 1413696, 'steps': 7362, 'loss/train': 2.1719024181365967} 08/30/2021 14:30:03 - INFO - __main__ - Step 7364: {'lr': 0.0004983817975775771, 'samples': 1413888, 'steps': 7363, 'loss/train': 1.7462650537490845} 08/30/2021 14:30:04 - INFO - __main__ - Step 7365: {'lr': 0.000498381194704375, 'samples': 1414080, 'steps': 7364, 'loss/train': 2.0631139278411865} 08/30/2021 14:30:04 - INFO - __main__ - Step 7366: {'lr': 0.000498380591719256, 'samples': 1414272, 'steps': 7365, 'loss/train': 1.9877134561538696} 08/30/2021 14:30:04 - INFO - __main__ - Step 7367: {'lr': 0.0004983799886222207, 'samples': 1414464, 'steps': 7366, 'loss/train': 2.4696197509765625} 08/30/2021 14:30:05 - INFO - __main__ - Step 7368: {'lr': 0.0004983793854132693, 'samples': 1414656, 'steps': 7367, 'loss/train': 2.257033586502075} 08/30/2021 14:30:07 - INFO - __main__ - Step 7369: {'lr': 0.0004983787820924019, 'samples': 1414848, 'steps': 7368, 'loss/train': 2.3936657905578613} 08/30/2021 14:30:07 - INFO - __main__ - Step 7370: {'lr': 0.0004983781786596187, 'samples': 1415040, 'steps': 7369, 'loss/train': 2.3956568241119385} 08/30/2021 14:30:08 - INFO - __main__ - Step 7371: {'lr': 0.0004983775751149204, 'samples': 1415232, 'steps': 7370, 'loss/train': 2.376009702682495} 08/30/2021 14:30:08 - INFO - __main__ - Step 7372: {'lr': 0.0004983769714583067, 'samples': 1415424, 'steps': 7371, 'loss/train': 2.920656681060791} 08/30/2021 14:30:08 - INFO - __main__ - Step 7373: {'lr': 0.0004983763676897784, 'samples': 1415616, 'steps': 7372, 'loss/train': 1.9536528587341309} 08/30/2021 14:30:10 - INFO - __main__ - Step 7374: {'lr': 0.0004983757638093355, 'samples': 1415808, 'steps': 7373, 'loss/train': 1.974847435951233} 08/30/2021 14:30:10 - INFO - __main__ - Step 7375: {'lr': 0.0004983751598169781, 'samples': 1416000, 'steps': 7374, 'loss/train': 1.821936011314392} 08/30/2021 14:30:11 - INFO - __main__ - Step 7376: {'lr': 0.000498374555712707, 'samples': 1416192, 'steps': 7375, 'loss/train': 2.4945473670959473} 08/30/2021 14:30:11 - INFO - __main__ - Step 7377: {'lr': 0.000498373951496522, 'samples': 1416384, 'steps': 7376, 'loss/train': 2.7330830097198486} 08/30/2021 14:30:11 - INFO - __main__ - Step 7378: {'lr': 0.0004983733471684234, 'samples': 1416576, 'steps': 7377, 'loss/train': 2.330193519592285} 08/30/2021 14:30:12 - INFO - __main__ - Step 7379: {'lr': 0.0004983727427284118, 'samples': 1416768, 'steps': 7378, 'loss/train': 1.9637912511825562} 08/30/2021 14:30:13 - INFO - __main__ - Step 7380: {'lr': 0.0004983721381764873, 'samples': 1416960, 'steps': 7379, 'loss/train': 1.901741862297058} 08/30/2021 14:30:14 - INFO - __main__ - Step 7381: {'lr': 0.00049837153351265, 'samples': 1417152, 'steps': 7380, 'loss/train': 1.9059598445892334} 08/30/2021 14:30:14 - INFO - __main__ - Step 7382: {'lr': 0.0004983709287369004, 'samples': 1417344, 'steps': 7381, 'loss/train': 2.421776056289673} 08/30/2021 14:30:14 - INFO - __main__ - Step 7383: {'lr': 0.0004983703238492386, 'samples': 1417536, 'steps': 7382, 'loss/train': 2.3350424766540527} 08/30/2021 14:30:15 - INFO - __main__ - Step 7384: {'lr': 0.000498369718849665, 'samples': 1417728, 'steps': 7383, 'loss/train': 2.4568023681640625} 08/30/2021 14:30:16 - INFO - __main__ - Step 7385: {'lr': 0.00049836911373818, 'samples': 1417920, 'steps': 7384, 'loss/train': 1.2539393901824951} 08/30/2021 14:30:16 - INFO - __main__ - Step 7386: {'lr': 0.0004983685085147836, 'samples': 1418112, 'steps': 7385, 'loss/train': 2.3377857208251953} 08/30/2021 14:30:17 - INFO - __main__ - Step 7387: {'lr': 0.0004983679031794762, 'samples': 1418304, 'steps': 7386, 'loss/train': 2.0887928009033203} 08/30/2021 14:30:17 - INFO - __main__ - Step 7388: {'lr': 0.000498367297732258, 'samples': 1418496, 'steps': 7387, 'loss/train': 2.3747024536132812} 08/30/2021 14:30:18 - INFO - __main__ - Step 7389: {'lr': 0.0004983666921731293, 'samples': 1418688, 'steps': 7388, 'loss/train': 1.945997953414917} 08/30/2021 14:30:19 - INFO - __main__ - Step 7390: {'lr': 0.0004983660865020905, 'samples': 1418880, 'steps': 7389, 'loss/train': 2.0669167041778564} 08/30/2021 14:30:20 - INFO - __main__ - Step 7391: {'lr': 0.0004983654807191418, 'samples': 1419072, 'steps': 7390, 'loss/train': 1.9517908096313477} 08/30/2021 14:30:20 - INFO - __main__ - Step 7392: {'lr': 0.0004983648748242833, 'samples': 1419264, 'steps': 7391, 'loss/train': 2.733821392059326} 08/30/2021 14:30:20 - INFO - __main__ - Step 7393: {'lr': 0.0004983642688175155, 'samples': 1419456, 'steps': 7392, 'loss/train': 2.7295315265655518} 08/30/2021 14:30:21 - INFO - __main__ - Step 7394: {'lr': 0.0004983636626988386, 'samples': 1419648, 'steps': 7393, 'loss/train': 1.5603747367858887} 08/30/2021 14:30:22 - INFO - __main__ - Step 7395: {'lr': 0.0004983630564682529, 'samples': 1419840, 'steps': 7394, 'loss/train': 1.9845948219299316} 08/30/2021 14:30:23 - INFO - __main__ - Step 7396: {'lr': 0.0004983624501257585, 'samples': 1420032, 'steps': 7395, 'loss/train': 1.4001693725585938} 08/30/2021 14:30:23 - INFO - __main__ - Step 7397: {'lr': 0.000498361843671356, 'samples': 1420224, 'steps': 7396, 'loss/train': 2.3412017822265625} 08/30/2021 14:30:23 - INFO - __main__ - Step 7398: {'lr': 0.0004983612371050453, 'samples': 1420416, 'steps': 7397, 'loss/train': 1.9006016254425049} 08/30/2021 14:30:24 - INFO - __main__ - Step 7399: {'lr': 0.000498360630426827, 'samples': 1420608, 'steps': 7398, 'loss/train': 2.0284204483032227} 08/30/2021 14:30:25 - INFO - __main__ - Step 7400: {'lr': 0.0004983600236367012, 'samples': 1420800, 'steps': 7399, 'loss/train': 1.6678403615951538} 08/30/2021 14:30:26 - INFO - __main__ - Step 7401: {'lr': 0.0004983594167346681, 'samples': 1420992, 'steps': 7400, 'loss/train': 1.9424364566802979} 08/30/2021 14:30:26 - INFO - __main__ - Step 7402: {'lr': 0.0004983588097207283, 'samples': 1421184, 'steps': 7401, 'loss/train': 1.8753180503845215} 08/30/2021 14:30:26 - INFO - __main__ - Step 7403: {'lr': 0.0004983582025948816, 'samples': 1421376, 'steps': 7402, 'loss/train': 1.6198694705963135} 08/30/2021 14:30:27 - INFO - __main__ - Step 7404: {'lr': 0.0004983575953571287, 'samples': 1421568, 'steps': 7403, 'loss/train': 2.0816402435302734} 08/30/2021 14:30:28 - INFO - __main__ - Step 7405: {'lr': 0.0004983569880074696, 'samples': 1421760, 'steps': 7404, 'loss/train': 2.150106430053711} 08/30/2021 14:30:28 - INFO - __main__ - Step 7406: {'lr': 0.0004983563805459048, 'samples': 1421952, 'steps': 7405, 'loss/train': 1.9102110862731934} 08/30/2021 14:30:29 - INFO - __main__ - Step 7407: {'lr': 0.0004983557729724343, 'samples': 1422144, 'steps': 7406, 'loss/train': 2.9529612064361572} 08/30/2021 14:30:29 - INFO - __main__ - Step 7408: {'lr': 0.0004983551652870586, 'samples': 1422336, 'steps': 7407, 'loss/train': 2.0352892875671387} 08/30/2021 14:30:30 - INFO - __main__ - Step 7409: {'lr': 0.000498354557489778, 'samples': 1422528, 'steps': 7408, 'loss/train': 0.8830174803733826} 08/30/2021 14:30:31 - INFO - __main__ - Step 7410: {'lr': 0.0004983539495805925, 'samples': 1422720, 'steps': 7409, 'loss/train': 1.8262628316879272} 08/30/2021 14:30:31 - INFO - __main__ - Step 7411: {'lr': 0.0004983533415595026, 'samples': 1422912, 'steps': 7410, 'loss/train': 1.6404615640640259} 08/30/2021 14:30:32 - INFO - __main__ - Step 7412: {'lr': 0.0004983527334265085, 'samples': 1423104, 'steps': 7411, 'loss/train': 1.8170119524002075} 08/30/2021 14:30:32 - INFO - __main__ - Step 7413: {'lr': 0.0004983521251816105, 'samples': 1423296, 'steps': 7412, 'loss/train': 2.4166505336761475} 08/30/2021 14:30:32 - INFO - __main__ - Step 7414: {'lr': 0.0004983515168248088, 'samples': 1423488, 'steps': 7413, 'loss/train': 1.8743215799331665} 08/30/2021 14:30:33 - INFO - __main__ - Step 7415: {'lr': 0.0004983509083561038, 'samples': 1423680, 'steps': 7414, 'loss/train': 1.871317744255066} 08/30/2021 14:30:34 - INFO - __main__ - Step 7416: {'lr': 0.0004983502997754958, 'samples': 1423872, 'steps': 7415, 'loss/train': 1.6531336307525635} 08/30/2021 14:30:35 - INFO - __main__ - Step 7417: {'lr': 0.0004983496910829849, 'samples': 1424064, 'steps': 7416, 'loss/train': 2.0444021224975586} 08/30/2021 14:30:35 - INFO - __main__ - Step 7418: {'lr': 0.0004983490822785715, 'samples': 1424256, 'steps': 7417, 'loss/train': 0.7739229202270508} 08/30/2021 14:30:35 - INFO - __main__ - Step 7419: {'lr': 0.0004983484733622558, 'samples': 1424448, 'steps': 7418, 'loss/train': 1.9896584749221802} 08/30/2021 14:30:36 - INFO - __main__ - Step 7420: {'lr': 0.0004983478643340382, 'samples': 1424640, 'steps': 7419, 'loss/train': 1.5574097633361816} 08/30/2021 14:30:38 - INFO - __main__ - Step 7421: {'lr': 0.0004983472551939186, 'samples': 1424832, 'steps': 7420, 'loss/train': 1.8600473403930664} 08/30/2021 14:30:38 - INFO - __main__ - Step 7422: {'lr': 0.0004983466459418978, 'samples': 1425024, 'steps': 7421, 'loss/train': 2.0000452995300293} 08/30/2021 14:30:39 - INFO - __main__ - Step 7423: {'lr': 0.0004983460365779759, 'samples': 1425216, 'steps': 7422, 'loss/train': 1.8882938623428345} 08/30/2021 14:30:39 - INFO - __main__ - Step 7424: {'lr': 0.0004983454271021529, 'samples': 1425408, 'steps': 7423, 'loss/train': 2.1789987087249756} 08/30/2021 14:30:39 - INFO - __main__ - Step 7425: {'lr': 0.0004983448175144294, 'samples': 1425600, 'steps': 7424, 'loss/train': 1.816618800163269} 08/30/2021 14:30:41 - INFO - __main__ - Step 7426: {'lr': 0.0004983442078148056, 'samples': 1425792, 'steps': 7425, 'loss/train': 1.7849947214126587} 08/30/2021 14:30:42 - INFO - __main__ - Step 7427: {'lr': 0.0004983435980032817, 'samples': 1425984, 'steps': 7426, 'loss/train': 0.6277517080307007} 08/30/2021 14:30:42 - INFO - __main__ - Step 7428: {'lr': 0.0004983429880798579, 'samples': 1426176, 'steps': 7427, 'loss/train': 0.7024663090705872} 08/30/2021 14:30:42 - INFO - __main__ - Step 7429: {'lr': 0.0004983423780445346, 'samples': 1426368, 'steps': 7428, 'loss/train': 2.2815916538238525} 08/30/2021 14:30:43 - INFO - __main__ - Step 7430: {'lr': 0.0004983417678973123, 'samples': 1426560, 'steps': 7429, 'loss/train': 1.468602180480957} 08/30/2021 14:30:43 - INFO - __main__ - Step 7431: {'lr': 0.0004983411576381907, 'samples': 1426752, 'steps': 7430, 'loss/train': 1.9443392753601074} 08/30/2021 14:30:45 - INFO - __main__ - Step 7432: {'lr': 0.0004983405472671706, 'samples': 1426944, 'steps': 7431, 'loss/train': 2.1994972229003906} 08/30/2021 14:30:45 - INFO - __main__ - Step 7433: {'lr': 0.000498339936784252, 'samples': 1427136, 'steps': 7432, 'loss/train': 2.496755361557007} 08/30/2021 14:30:45 - INFO - __main__ - Step 7434: {'lr': 0.0004983393261894354, 'samples': 1427328, 'steps': 7433, 'loss/train': 2.039398431777954} 08/30/2021 14:30:46 - INFO - __main__ - Step 7435: {'lr': 0.0004983387154827208, 'samples': 1427520, 'steps': 7434, 'loss/train': 2.1109769344329834} 08/30/2021 14:30:46 - INFO - __main__ - Step 7436: {'lr': 0.0004983381046641085, 'samples': 1427712, 'steps': 7435, 'loss/train': 1.9635385274887085} 08/30/2021 14:30:47 - INFO - __main__ - Step 7437: {'lr': 0.0004983374937335991, 'samples': 1427904, 'steps': 7436, 'loss/train': 1.7011244297027588} 08/30/2021 14:30:48 - INFO - __main__ - Step 7438: {'lr': 0.0004983368826911926, 'samples': 1428096, 'steps': 7437, 'loss/train': 2.3067703247070312} 08/30/2021 14:30:48 - INFO - __main__ - Step 7439: {'lr': 0.0004983362715368893, 'samples': 1428288, 'steps': 7438, 'loss/train': 2.313699960708618} 08/30/2021 14:30:49 - INFO - __main__ - Step 7440: {'lr': 0.0004983356602706895, 'samples': 1428480, 'steps': 7439, 'loss/train': 2.028313398361206} 08/30/2021 14:30:49 - INFO - __main__ - Step 7441: {'lr': 0.0004983350488925936, 'samples': 1428672, 'steps': 7440, 'loss/train': 1.9797123670578003} 08/30/2021 14:30:49 - INFO - __main__ - Step 7442: {'lr': 0.0004983344374026016, 'samples': 1428864, 'steps': 7441, 'loss/train': 1.7195743322372437} 08/30/2021 14:30:51 - INFO - __main__ - Step 7443: {'lr': 0.0004983338258007139, 'samples': 1429056, 'steps': 7442, 'loss/train': 2.02921462059021} 08/30/2021 14:30:51 - INFO - __main__ - Step 7444: {'lr': 0.0004983332140869309, 'samples': 1429248, 'steps': 7443, 'loss/train': 2.007859230041504} 08/30/2021 14:30:52 - INFO - __main__ - Step 7445: {'lr': 0.0004983326022612528, 'samples': 1429440, 'steps': 7444, 'loss/train': 1.9799222946166992} 08/30/2021 14:30:52 - INFO - __main__ - Step 7446: {'lr': 0.0004983319903236799, 'samples': 1429632, 'steps': 7445, 'loss/train': 1.4338672161102295} 08/30/2021 14:30:52 - INFO - __main__ - Step 7447: {'lr': 0.0004983313782742124, 'samples': 1429824, 'steps': 7446, 'loss/train': 1.4499529600143433} 08/30/2021 14:30:54 - INFO - __main__ - Step 7448: {'lr': 0.0004983307661128505, 'samples': 1430016, 'steps': 7447, 'loss/train': 1.8329721689224243} 08/30/2021 14:30:55 - INFO - __main__ - Step 7449: {'lr': 0.0004983301538395948, 'samples': 1430208, 'steps': 7448, 'loss/train': 1.7827765941619873} 08/30/2021 14:30:55 - INFO - __main__ - Step 7450: {'lr': 0.0004983295414544452, 'samples': 1430400, 'steps': 7449, 'loss/train': 2.311680316925049} 08/30/2021 14:30:55 - INFO - __main__ - Step 7451: {'lr': 0.0004983289289574022, 'samples': 1430592, 'steps': 7450, 'loss/train': 2.8694517612457275} 08/30/2021 14:30:56 - INFO - __main__ - Step 7452: {'lr': 0.000498328316348466, 'samples': 1430784, 'steps': 7451, 'loss/train': 1.5860830545425415} 08/30/2021 14:30:56 - INFO - __main__ - Step 7453: {'lr': 0.0004983277036276369, 'samples': 1430976, 'steps': 7452, 'loss/train': 1.9333540201187134} 08/30/2021 14:30:58 - INFO - __main__ - Step 7454: {'lr': 0.0004983270907949152, 'samples': 1431168, 'steps': 7453, 'loss/train': 0.31429755687713623} 08/30/2021 14:30:58 - INFO - __main__ - Step 7455: {'lr': 0.0004983264778503011, 'samples': 1431360, 'steps': 7454, 'loss/train': 1.7631436586380005} 08/30/2021 14:30:58 - INFO - __main__ - Step 7456: {'lr': 0.0004983258647937949, 'samples': 1431552, 'steps': 7455, 'loss/train': 2.311392307281494} 08/30/2021 14:30:59 - INFO - __main__ - Step 7457: {'lr': 0.0004983252516253969, 'samples': 1431744, 'steps': 7456, 'loss/train': 1.570852518081665} 08/30/2021 14:30:59 - INFO - __main__ - Step 7458: {'lr': 0.0004983246383451074, 'samples': 1431936, 'steps': 7457, 'loss/train': 2.570781946182251} 08/30/2021 14:30:59 - INFO - __main__ - Step 7459: {'lr': 0.0004983240249529267, 'samples': 1432128, 'steps': 7458, 'loss/train': 2.4136455059051514} 08/30/2021 14:31:01 - INFO - __main__ - Step 7460: {'lr': 0.000498323411448855, 'samples': 1432320, 'steps': 7459, 'loss/train': 2.0277886390686035} 08/30/2021 14:31:01 - INFO - __main__ - Step 7461: {'lr': 0.0004983227978328926, 'samples': 1432512, 'steps': 7460, 'loss/train': 3.357154369354248} 08/30/2021 14:31:02 - INFO - __main__ - Step 7462: {'lr': 0.0004983221841050397, 'samples': 1432704, 'steps': 7461, 'loss/train': 1.9147751331329346} 08/30/2021 14:31:02 - INFO - __main__ - Step 7463: {'lr': 0.0004983215702652968, 'samples': 1432896, 'steps': 7462, 'loss/train': 2.4763360023498535} 08/30/2021 14:31:02 - INFO - __main__ - Step 7464: {'lr': 0.0004983209563136639, 'samples': 1433088, 'steps': 7463, 'loss/train': 1.8825286626815796} 08/30/2021 14:31:04 - INFO - __main__ - Step 7465: {'lr': 0.0004983203422501414, 'samples': 1433280, 'steps': 7464, 'loss/train': 2.0879411697387695} 08/30/2021 14:31:04 - INFO - __main__ - Step 7466: {'lr': 0.0004983197280747297, 'samples': 1433472, 'steps': 7465, 'loss/train': 1.7000820636749268} 08/30/2021 14:31:05 - INFO - __main__ - Step 7467: {'lr': 0.0004983191137874289, 'samples': 1433664, 'steps': 7466, 'loss/train': 2.187587261199951} 08/30/2021 14:31:05 - INFO - __main__ - Step 7468: {'lr': 0.0004983184993882394, 'samples': 1433856, 'steps': 7467, 'loss/train': 2.4067704677581787} 08/30/2021 14:31:05 - INFO - __main__ - Step 7469: {'lr': 0.0004983178848771613, 'samples': 1434048, 'steps': 7468, 'loss/train': 2.186933994293213} 08/30/2021 14:31:07 - INFO - __main__ - Step 7470: {'lr': 0.0004983172702541951, 'samples': 1434240, 'steps': 7469, 'loss/train': 1.7947266101837158} 08/30/2021 14:31:07 - INFO - __main__ - Step 7471: {'lr': 0.0004983166555193409, 'samples': 1434432, 'steps': 7470, 'loss/train': 1.9566001892089844} 08/30/2021 14:31:08 - INFO - __main__ - Step 7472: {'lr': 0.000498316040672599, 'samples': 1434624, 'steps': 7471, 'loss/train': 2.3320071697235107} 08/30/2021 14:31:08 - INFO - __main__ - Step 7473: {'lr': 0.00049831542571397, 'samples': 1434816, 'steps': 7472, 'loss/train': 2.0690970420837402} 08/30/2021 14:31:08 - INFO - __main__ - Step 7474: {'lr': 0.0004983148106434536, 'samples': 1435008, 'steps': 7473, 'loss/train': 1.548442006111145} 08/30/2021 14:31:10 - INFO - __main__ - Step 7475: {'lr': 0.0004983141954610505, 'samples': 1435200, 'steps': 7474, 'loss/train': 2.0176265239715576} 08/30/2021 14:31:11 - INFO - __main__ - Step 7476: {'lr': 0.0004983135801667608, 'samples': 1435392, 'steps': 7475, 'loss/train': 1.918919324874878} 08/30/2021 14:31:11 - INFO - __main__ - Step 7477: {'lr': 0.0004983129647605849, 'samples': 1435584, 'steps': 7476, 'loss/train': 1.9551241397857666} 08/30/2021 14:31:12 - INFO - __main__ - Step 7478: {'lr': 0.0004983123492425229, 'samples': 1435776, 'steps': 7477, 'loss/train': 2.201251745223999} 08/30/2021 14:31:12 - INFO - __main__ - Step 7479: {'lr': 0.0004983117336125753, 'samples': 1435968, 'steps': 7478, 'loss/train': 2.257244825363159} 08/30/2021 14:31:14 - INFO - __main__ - Step 7480: {'lr': 0.0004983111178707422, 'samples': 1436160, 'steps': 7479, 'loss/train': 2.2179291248321533} 08/30/2021 14:31:14 - INFO - __main__ - Step 7481: {'lr': 0.0004983105020170239, 'samples': 1436352, 'steps': 7480, 'loss/train': 2.157257318496704} 08/30/2021 14:31:14 - INFO - __main__ - Step 7482: {'lr': 0.0004983098860514209, 'samples': 1436544, 'steps': 7481, 'loss/train': 2.0019609928131104} 08/30/2021 14:31:15 - INFO - __main__ - Step 7483: {'lr': 0.0004983092699739331, 'samples': 1436736, 'steps': 7482, 'loss/train': 2.1381466388702393} 08/30/2021 14:31:15 - INFO - __main__ - Step 7484: {'lr': 0.0004983086537845611, 'samples': 1436928, 'steps': 7483, 'loss/train': 1.8621677160263062} 08/30/2021 14:31:17 - INFO - __main__ - Step 7485: {'lr': 0.000498308037483305, 'samples': 1437120, 'steps': 7484, 'loss/train': 1.6330540180206299} 08/30/2021 14:31:17 - INFO - __main__ - Step 7486: {'lr': 0.0004983074210701651, 'samples': 1437312, 'steps': 7485, 'loss/train': 5.841049671173096} 08/30/2021 14:31:18 - INFO - __main__ - Step 7487: {'lr': 0.0004983068045451418, 'samples': 1437504, 'steps': 7486, 'loss/train': 6.140170097351074} 08/30/2021 14:31:18 - INFO - __main__ - Step 7488: {'lr': 0.0004983061879082352, 'samples': 1437696, 'steps': 7487, 'loss/train': 1.758646845817566} 08/30/2021 14:31:18 - INFO - __main__ - Step 7489: {'lr': 0.0004983055711594458, 'samples': 1437888, 'steps': 7488, 'loss/train': 0.30131110548973083} 08/30/2021 14:31:19 - INFO - __main__ - Step 7490: {'lr': 0.0004983049542987736, 'samples': 1438080, 'steps': 7489, 'loss/train': 1.9802919626235962} 08/30/2021 14:31:20 - INFO - __main__ - Step 7491: {'lr': 0.000498304337326219, 'samples': 1438272, 'steps': 7490, 'loss/train': 2.3930904865264893} 08/30/2021 14:31:21 - INFO - __main__ - Step 7492: {'lr': 0.0004983037202417824, 'samples': 1438464, 'steps': 7491, 'loss/train': 2.141775369644165} 08/30/2021 14:31:21 - INFO - __main__ - Step 7493: {'lr': 0.0004983031030454639, 'samples': 1438656, 'steps': 7492, 'loss/train': 2.0787320137023926} 08/30/2021 14:31:21 - INFO - __main__ - Step 7494: {'lr': 0.0004983024857372639, 'samples': 1438848, 'steps': 7493, 'loss/train': 1.6597785949707031} 08/30/2021 14:31:22 - INFO - __main__ - Step 7495: {'lr': 0.0004983018683171826, 'samples': 1439040, 'steps': 7494, 'loss/train': 2.1893529891967773} 08/30/2021 14:31:23 - INFO - __main__ - Step 7496: {'lr': 0.0004983012507852203, 'samples': 1439232, 'steps': 7495, 'loss/train': 1.8672926425933838} 08/30/2021 14:31:24 - INFO - __main__ - Step 7497: {'lr': 0.0004983006331413773, 'samples': 1439424, 'steps': 7496, 'loss/train': 2.1031692028045654} 08/30/2021 14:31:24 - INFO - __main__ - Step 7498: {'lr': 0.0004983000153856539, 'samples': 1439616, 'steps': 7497, 'loss/train': 1.776388168334961} 08/30/2021 14:31:24 - INFO - __main__ - Step 7499: {'lr': 0.0004982993975180504, 'samples': 1439808, 'steps': 7498, 'loss/train': 1.5209027528762817} 08/30/2021 14:31:25 - INFO - __main__ - Step 7500: {'lr': 0.0004982987795385669, 'samples': 1440000, 'steps': 7499, 'loss/train': 2.2507176399230957} 08/30/2021 14:31:25 - INFO - __main__ - Step 7501: {'lr': 0.0004982981614472039, 'samples': 1440192, 'steps': 7500, 'loss/train': 1.0047045946121216} 08/30/2021 14:31:26 - INFO - __main__ - Step 7502: {'lr': 0.0004982975432439615, 'samples': 1440384, 'steps': 7501, 'loss/train': 2.038471221923828} 08/30/2021 14:31:27 - INFO - __main__ - Step 7503: {'lr': 0.0004982969249288401, 'samples': 1440576, 'steps': 7502, 'loss/train': 2.0150177478790283} 08/30/2021 14:31:27 - INFO - __main__ - Step 7504: {'lr': 0.0004982963065018399, 'samples': 1440768, 'steps': 7503, 'loss/train': 2.293520450592041} 08/30/2021 14:31:28 - INFO - __main__ - Step 7505: {'lr': 0.0004982956879629612, 'samples': 1440960, 'steps': 7504, 'loss/train': 1.9492920637130737} 08/30/2021 14:31:28 - INFO - __main__ - Step 7506: {'lr': 0.0004982950693122044, 'samples': 1441152, 'steps': 7505, 'loss/train': 2.2154383659362793} 08/30/2021 14:31:30 - INFO - __main__ - Step 7507: {'lr': 0.0004982944505495696, 'samples': 1441344, 'steps': 7506, 'loss/train': 2.200798749923706} 08/30/2021 14:31:30 - INFO - __main__ - Step 7508: {'lr': 0.0004982938316750572, 'samples': 1441536, 'steps': 7507, 'loss/train': 2.2443289756774902} 08/30/2021 14:31:30 - INFO - __main__ - Step 7509: {'lr': 0.0004982932126886674, 'samples': 1441728, 'steps': 7508, 'loss/train': 1.1262670755386353} 08/30/2021 14:31:31 - INFO - __main__ - Step 7510: {'lr': 0.0004982925935904004, 'samples': 1441920, 'steps': 7509, 'loss/train': 2.0964956283569336} 08/30/2021 14:31:31 - INFO - __main__ - Step 7511: {'lr': 0.0004982919743802567, 'samples': 1442112, 'steps': 7510, 'loss/train': 2.082104444503784} 08/30/2021 14:31:33 - INFO - __main__ - Step 7512: {'lr': 0.0004982913550582364, 'samples': 1442304, 'steps': 7511, 'loss/train': 1.5259950160980225} 08/30/2021 14:31:33 - INFO - __main__ - Step 7513: {'lr': 0.00049829073562434, 'samples': 1442496, 'steps': 7512, 'loss/train': 2.34053897857666} 08/30/2021 14:31:33 - INFO - __main__ - Step 7514: {'lr': 0.0004982901160785675, 'samples': 1442688, 'steps': 7513, 'loss/train': 1.7912914752960205} 08/30/2021 14:31:34 - INFO - __main__ - Step 7515: {'lr': 0.0004982894964209193, 'samples': 1442880, 'steps': 7514, 'loss/train': 1.35605788230896} 08/30/2021 14:31:34 - INFO - __main__ - Step 7516: {'lr': 0.0004982888766513957, 'samples': 1443072, 'steps': 7515, 'loss/train': 2.033628463745117} 08/30/2021 14:31:36 - INFO - __main__ - Step 7517: {'lr': 0.000498288256769997, 'samples': 1443264, 'steps': 7516, 'loss/train': 1.995079755783081} 08/30/2021 14:31:36 - INFO - __main__ - Step 7518: {'lr': 0.0004982876367767234, 'samples': 1443456, 'steps': 7517, 'loss/train': 1.6700373888015747} 08/30/2021 14:31:36 - INFO - __main__ - Step 7519: {'lr': 0.0004982870166715753, 'samples': 1443648, 'steps': 7518, 'loss/train': 1.7990601062774658} 08/30/2021 14:31:37 - INFO - __main__ - Step 7520: {'lr': 0.0004982863964545529, 'samples': 1443840, 'steps': 7519, 'loss/train': 2.0874156951904297} 08/30/2021 14:31:37 - INFO - __main__ - Step 7521: {'lr': 0.0004982857761256564, 'samples': 1444032, 'steps': 7520, 'loss/train': 2.185539960861206} 08/30/2021 14:31:39 - INFO - __main__ - Step 7522: {'lr': 0.0004982851556848861, 'samples': 1444224, 'steps': 7521, 'loss/train': 1.9383097887039185} 08/30/2021 14:31:39 - INFO - __main__ - Step 7523: {'lr': 0.0004982845351322424, 'samples': 1444416, 'steps': 7522, 'loss/train': 2.156398057937622} 08/30/2021 14:31:39 - INFO - __main__ - Step 7524: {'lr': 0.0004982839144677257, 'samples': 1444608, 'steps': 7523, 'loss/train': 2.3161704540252686} 08/30/2021 14:31:40 - INFO - __main__ - Step 7525: {'lr': 0.0004982832936913359, 'samples': 1444800, 'steps': 7524, 'loss/train': 1.7087222337722778} 08/30/2021 14:31:40 - INFO - __main__ - Step 7526: {'lr': 0.0004982826728030735, 'samples': 1444992, 'steps': 7525, 'loss/train': 1.8901242017745972} 08/30/2021 14:31:40 - INFO - __main__ - Step 7527: {'lr': 0.0004982820518029387, 'samples': 1445184, 'steps': 7526, 'loss/train': 1.875933289527893} 08/30/2021 14:31:42 - INFO - __main__ - Step 7528: {'lr': 0.000498281430690932, 'samples': 1445376, 'steps': 7527, 'loss/train': 2.131187677383423} 08/30/2021 14:31:43 - INFO - __main__ - Step 7529: {'lr': 0.0004982808094670534, 'samples': 1445568, 'steps': 7528, 'loss/train': 1.9248706102371216} 08/30/2021 14:31:43 - INFO - __main__ - Step 7530: {'lr': 0.0004982801881313034, 'samples': 1445760, 'steps': 7529, 'loss/train': 2.176140785217285} 08/30/2021 14:31:43 - INFO - __main__ - Step 7531: {'lr': 0.0004982795666836821, 'samples': 1445952, 'steps': 7530, 'loss/train': 2.0840225219726562} 08/30/2021 14:31:44 - INFO - __main__ - Step 7532: {'lr': 0.00049827894512419, 'samples': 1446144, 'steps': 7531, 'loss/train': 2.8085975646972656} 08/30/2021 14:31:46 - INFO - __main__ - Step 7533: {'lr': 0.000498278323452827, 'samples': 1446336, 'steps': 7532, 'loss/train': 0.224198579788208} 08/30/2021 14:31:46 - INFO - __main__ - Step 7534: {'lr': 0.0004982777016695937, 'samples': 1446528, 'steps': 7533, 'loss/train': 2.6613540649414062} 08/30/2021 14:31:46 - INFO - __main__ - Step 7535: {'lr': 0.0004982770797744904, 'samples': 1446720, 'steps': 7534, 'loss/train': 1.0777910947799683} 08/30/2021 14:31:47 - INFO - __main__ - Step 7536: {'lr': 0.0004982764577675172, 'samples': 1446912, 'steps': 7535, 'loss/train': 2.2682013511657715} 08/30/2021 14:31:47 - INFO - __main__ - Step 7537: {'lr': 0.0004982758356486746, 'samples': 1447104, 'steps': 7536, 'loss/train': 2.113523244857788} 08/30/2021 14:31:49 - INFO - __main__ - Step 7538: {'lr': 0.0004982752134179624, 'samples': 1447296, 'steps': 7537, 'loss/train': 2.2558867931365967} 08/30/2021 14:31:49 - INFO - __main__ - Step 7539: {'lr': 0.0004982745910753815, 'samples': 1447488, 'steps': 7538, 'loss/train': 1.9438822269439697} 08/30/2021 14:31:49 - INFO - __main__ - Step 7540: {'lr': 0.0004982739686209319, 'samples': 1447680, 'steps': 7539, 'loss/train': 1.8464691638946533} 08/30/2021 14:31:50 - INFO - __main__ - Step 7541: {'lr': 0.0004982733460546138, 'samples': 1447872, 'steps': 7540, 'loss/train': 1.8391351699829102} 08/30/2021 14:31:50 - INFO - __main__ - Step 7542: {'lr': 0.0004982727233764276, 'samples': 1448064, 'steps': 7541, 'loss/train': 1.9969525337219238} 08/30/2021 14:31:52 - INFO - __main__ - Step 7543: {'lr': 0.0004982721005863734, 'samples': 1448256, 'steps': 7542, 'loss/train': 1.9569755792617798} 08/30/2021 14:31:52 - INFO - __main__ - Step 7544: {'lr': 0.0004982714776844518, 'samples': 1448448, 'steps': 7543, 'loss/train': 2.4319441318511963} 08/30/2021 14:31:52 - INFO - __main__ - Step 7545: {'lr': 0.0004982708546706628, 'samples': 1448640, 'steps': 7544, 'loss/train': 1.3967210054397583} 08/30/2021 14:31:53 - INFO - __main__ - Step 7546: {'lr': 0.0004982702315450068, 'samples': 1448832, 'steps': 7545, 'loss/train': 1.4815490245819092} 08/30/2021 14:31:53 - INFO - __main__ - Step 7547: {'lr': 0.0004982696083074841, 'samples': 1449024, 'steps': 7546, 'loss/train': 2.012848377227783} 08/30/2021 14:31:55 - INFO - __main__ - Step 7548: {'lr': 0.0004982689849580951, 'samples': 1449216, 'steps': 7547, 'loss/train': 0.8206766247749329} 08/30/2021 14:31:55 - INFO - __main__ - Step 7549: {'lr': 0.0004982683614968396, 'samples': 1449408, 'steps': 7548, 'loss/train': 2.089946985244751} 08/30/2021 14:31:55 - INFO - __main__ - Step 7550: {'lr': 0.0004982677379237185, 'samples': 1449600, 'steps': 7549, 'loss/train': 2.0351805686950684} 08/30/2021 14:31:56 - INFO - __main__ - Step 7551: {'lr': 0.0004982671142387316, 'samples': 1449792, 'steps': 7550, 'loss/train': 1.9914253950119019} 08/30/2021 14:31:56 - INFO - __main__ - Step 7552: {'lr': 0.0004982664904418794, 'samples': 1449984, 'steps': 7551, 'loss/train': 2.4036357402801514} 08/30/2021 14:31:56 - INFO - __main__ - Step 7553: {'lr': 0.0004982658665331622, 'samples': 1450176, 'steps': 7552, 'loss/train': 2.1153810024261475} 08/30/2021 14:31:58 - INFO - __main__ - Step 7554: {'lr': 0.0004982652425125802, 'samples': 1450368, 'steps': 7553, 'loss/train': 2.22267746925354} 08/30/2021 14:31:59 - INFO - __main__ - Step 7555: {'lr': 0.0004982646183801337, 'samples': 1450560, 'steps': 7554, 'loss/train': 1.5154162645339966} 08/30/2021 14:31:59 - INFO - __main__ - Step 7556: {'lr': 0.000498263994135823, 'samples': 1450752, 'steps': 7555, 'loss/train': 2.205740213394165} 08/30/2021 14:31:59 - INFO - __main__ - Step 7557: {'lr': 0.0004982633697796484, 'samples': 1450944, 'steps': 7556, 'loss/train': 2.1476902961730957} 08/30/2021 14:32:00 - INFO - __main__ - Step 7558: {'lr': 0.0004982627453116102, 'samples': 1451136, 'steps': 7557, 'loss/train': 2.2479989528656006} 08/30/2021 14:32:01 - INFO - __main__ - Step 7559: {'lr': 0.0004982621207317086, 'samples': 1451328, 'steps': 7558, 'loss/train': 1.9805433750152588} 08/30/2021 14:32:02 - INFO - __main__ - Step 7560: {'lr': 0.0004982614960399439, 'samples': 1451520, 'steps': 7559, 'loss/train': 2.081728219985962} 08/30/2021 14:32:02 - INFO - __main__ - Step 7561: {'lr': 0.0004982608712363163, 'samples': 1451712, 'steps': 7560, 'loss/train': 2.3973753452301025} 08/30/2021 14:32:02 - INFO - __main__ - Step 7562: {'lr': 0.0004982602463208263, 'samples': 1451904, 'steps': 7561, 'loss/train': 1.589126706123352} 08/30/2021 14:32:03 - INFO - __main__ - Step 7563: {'lr': 0.0004982596212934742, 'samples': 1452096, 'steps': 7562, 'loss/train': 2.282374143600464} 08/30/2021 14:32:04 - INFO - __main__ - Step 7564: {'lr': 0.00049825899615426, 'samples': 1452288, 'steps': 7563, 'loss/train': 1.7362415790557861} 08/30/2021 14:32:05 - INFO - __main__ - Step 7565: {'lr': 0.000498258370903184, 'samples': 1452480, 'steps': 7564, 'loss/train': 1.7438775300979614} 08/30/2021 14:32:05 - INFO - __main__ - Step 7566: {'lr': 0.0004982577455402467, 'samples': 1452672, 'steps': 7565, 'loss/train': 2.1081855297088623} 08/30/2021 14:32:05 - INFO - __main__ - Step 7567: {'lr': 0.0004982571200654485, 'samples': 1452864, 'steps': 7566, 'loss/train': 2.0620479583740234} 08/30/2021 14:32:06 - INFO - __main__ - Step 7568: {'lr': 0.0004982564944787892, 'samples': 1453056, 'steps': 7567, 'loss/train': 0.9706790447235107} 08/30/2021 14:32:06 - INFO - __main__ - Step 7569: {'lr': 0.0004982558687802695, 'samples': 1453248, 'steps': 7568, 'loss/train': 2.075424909591675} 08/30/2021 14:32:08 - INFO - __main__ - Step 7570: {'lr': 0.0004982552429698894, 'samples': 1453440, 'steps': 7569, 'loss/train': 2.015124559402466} 08/30/2021 14:32:08 - INFO - __main__ - Step 7571: {'lr': 0.0004982546170476494, 'samples': 1453632, 'steps': 7570, 'loss/train': 2.06308913230896} 08/30/2021 14:32:08 - INFO - __main__ - Step 7572: {'lr': 0.0004982539910135497, 'samples': 1453824, 'steps': 7571, 'loss/train': 2.22385835647583} 08/30/2021 14:32:09 - INFO - __main__ - Step 7573: {'lr': 0.0004982533648675906, 'samples': 1454016, 'steps': 7572, 'loss/train': 1.735123872756958} 08/30/2021 14:32:09 - INFO - __main__ - Step 7574: {'lr': 0.0004982527386097723, 'samples': 1454208, 'steps': 7573, 'loss/train': 1.3776600360870361} 08/30/2021 14:32:10 - INFO - __main__ - Step 7575: {'lr': 0.0004982521122400953, 'samples': 1454400, 'steps': 7574, 'loss/train': 2.298922300338745} 08/30/2021 14:32:11 - INFO - __main__ - Step 7576: {'lr': 0.0004982514857585596, 'samples': 1454592, 'steps': 7575, 'loss/train': 1.628009557723999} 08/30/2021 14:32:11 - INFO - __main__ - Step 7577: {'lr': 0.0004982508591651657, 'samples': 1454784, 'steps': 7576, 'loss/train': 1.6538323163986206} 08/30/2021 14:32:12 - INFO - __main__ - Step 7578: {'lr': 0.0004982502324599137, 'samples': 1454976, 'steps': 7577, 'loss/train': 1.6575632095336914} 08/30/2021 14:32:12 - INFO - __main__ - Step 7579: {'lr': 0.000498249605642804, 'samples': 1455168, 'steps': 7578, 'loss/train': 2.3769774436950684} 08/30/2021 14:32:13 - INFO - __main__ - Step 7580: {'lr': 0.0004982489787138369, 'samples': 1455360, 'steps': 7579, 'loss/train': 1.8219870328903198} 08/30/2021 14:32:14 - INFO - __main__ - Step 7581: {'lr': 0.0004982483516730126, 'samples': 1455552, 'steps': 7580, 'loss/train': 2.2146756649017334} 08/30/2021 14:32:14 - INFO - __main__ - Step 7582: {'lr': 0.0004982477245203314, 'samples': 1455744, 'steps': 7581, 'loss/train': 1.9243416786193848} 08/30/2021 14:32:15 - INFO - __main__ - Step 7583: {'lr': 0.0004982470972557936, 'samples': 1455936, 'steps': 7582, 'loss/train': 1.8740180730819702} 08/30/2021 14:32:15 - INFO - __main__ - Step 7584: {'lr': 0.0004982464698793995, 'samples': 1456128, 'steps': 7583, 'loss/train': 2.0148367881774902} 08/30/2021 14:32:17 - INFO - __main__ - Step 7585: {'lr': 0.0004982458423911495, 'samples': 1456320, 'steps': 7584, 'loss/train': 2.3391404151916504} 08/30/2021 14:32:18 - INFO - __main__ - Step 7586: {'lr': 0.0004982452147910437, 'samples': 1456512, 'steps': 7585, 'loss/train': 0.4455569088459015} 08/30/2021 14:32:18 - INFO - __main__ - Step 7587: {'lr': 0.0004982445870790823, 'samples': 1456704, 'steps': 7586, 'loss/train': 1.9164934158325195} 08/30/2021 14:32:18 - INFO - __main__ - Step 7588: {'lr': 0.0004982439592552658, 'samples': 1456896, 'steps': 7587, 'loss/train': 1.9756067991256714} 08/30/2021 14:32:19 - INFO - __main__ - Step 7589: {'lr': 0.0004982433313195945, 'samples': 1457088, 'steps': 7588, 'loss/train': 2.1519882678985596} 08/30/2021 14:32:21 - INFO - __main__ - Step 7590: {'lr': 0.0004982427032720685, 'samples': 1457280, 'steps': 7589, 'loss/train': 1.8529356718063354} 08/30/2021 14:32:21 - INFO - __main__ - Step 7591: {'lr': 0.0004982420751126882, 'samples': 1457472, 'steps': 7590, 'loss/train': 2.0144546031951904} 08/30/2021 14:32:22 - INFO - __main__ - Step 7592: {'lr': 0.0004982414468414538, 'samples': 1457664, 'steps': 7591, 'loss/train': 2.052746057510376} 08/30/2021 14:32:22 - INFO - __main__ - Step 7593: {'lr': 0.0004982408184583656, 'samples': 1457856, 'steps': 7592, 'loss/train': 1.869333267211914} 08/30/2021 14:32:22 - INFO - __main__ - Step 7594: {'lr': 0.000498240189963424, 'samples': 1458048, 'steps': 7593, 'loss/train': 0.4741004407405853} 08/30/2021 14:32:23 - INFO - __main__ - Step 7595: {'lr': 0.0004982395613566291, 'samples': 1458240, 'steps': 7594, 'loss/train': 0.48749151825904846} 08/30/2021 14:32:23 - INFO - __main__ - Step 7596: {'lr': 0.0004982389326379814, 'samples': 1458432, 'steps': 7595, 'loss/train': 1.4670989513397217} 08/30/2021 14:32:24 - INFO - __main__ - Step 7597: {'lr': 0.000498238303807481, 'samples': 1458624, 'steps': 7596, 'loss/train': 1.3657543659210205} 08/30/2021 14:32:25 - INFO - __main__ - Step 7598: {'lr': 0.0004982376748651283, 'samples': 1458816, 'steps': 7597, 'loss/train': 1.751383662223816} 08/30/2021 14:32:25 - INFO - __main__ - Step 7599: {'lr': 0.0004982370458109235, 'samples': 1459008, 'steps': 7598, 'loss/train': 2.3496954441070557} 08/30/2021 14:32:26 - INFO - __main__ - Step 7600: {'lr': 0.0004982364166448669, 'samples': 1459200, 'steps': 7599, 'loss/train': 1.9759198427200317} 08/30/2021 14:32:26 - INFO - __main__ - Step 7601: {'lr': 0.0004982357873669588, 'samples': 1459392, 'steps': 7600, 'loss/train': 2.449190378189087} 08/30/2021 14:32:28 - INFO - __main__ - Step 7602: {'lr': 0.0004982351579771995, 'samples': 1459584, 'steps': 7601, 'loss/train': 2.4566941261291504} 08/30/2021 14:32:29 - INFO - __main__ - Step 7603: {'lr': 0.0004982345284755893, 'samples': 1459776, 'steps': 7602, 'loss/train': 1.5778398513793945} 08/30/2021 14:32:29 - INFO - __main__ - Step 7604: {'lr': 0.0004982338988621284, 'samples': 1459968, 'steps': 7603, 'loss/train': 0.2906356453895569} 08/30/2021 14:32:29 - INFO - __main__ - Step 7605: {'lr': 0.0004982332691368172, 'samples': 1460160, 'steps': 7604, 'loss/train': 1.720291018486023} 08/30/2021 14:32:30 - INFO - __main__ - Step 7606: {'lr': 0.0004982326392996559, 'samples': 1460352, 'steps': 7605, 'loss/train': 1.7239372730255127} 08/30/2021 14:32:31 - INFO - __main__ - Step 7607: {'lr': 0.0004982320093506449, 'samples': 1460544, 'steps': 7606, 'loss/train': 1.5500638484954834} 08/30/2021 14:32:32 - INFO - __main__ - Step 7608: {'lr': 0.0004982313792897843, 'samples': 1460736, 'steps': 7607, 'loss/train': 2.3881630897521973} 08/30/2021 14:32:32 - INFO - __main__ - Step 7609: {'lr': 0.0004982307491170744, 'samples': 1460928, 'steps': 7608, 'loss/train': 1.9098057746887207} 08/30/2021 14:32:32 - INFO - __main__ - Step 7610: {'lr': 0.0004982301188325156, 'samples': 1461120, 'steps': 7609, 'loss/train': 2.543076515197754} 08/30/2021 14:32:33 - INFO - __main__ - Step 7611: {'lr': 0.0004982294884361081, 'samples': 1461312, 'steps': 7610, 'loss/train': 1.7057809829711914} 08/30/2021 14:32:34 - INFO - __main__ - Step 7612: {'lr': 0.0004982288579278522, 'samples': 1461504, 'steps': 7611, 'loss/train': 1.8376268148422241} 08/30/2021 14:32:35 - INFO - __main__ - Step 7613: {'lr': 0.0004982282273077483, 'samples': 1461696, 'steps': 7612, 'loss/train': 1.9261051416397095} 08/30/2021 14:32:35 - INFO - __main__ - Step 7614: {'lr': 0.0004982275965757965, 'samples': 1461888, 'steps': 7613, 'loss/train': 1.7783925533294678} 08/30/2021 14:32:35 - INFO - __main__ - Step 7615: {'lr': 0.0004982269657319974, 'samples': 1462080, 'steps': 7614, 'loss/train': 2.282299757003784} 08/30/2021 14:32:36 - INFO - __main__ - Step 7616: {'lr': 0.0004982263347763508, 'samples': 1462272, 'steps': 7615, 'loss/train': 1.796460509300232} 08/30/2021 14:32:36 - INFO - __main__ - Step 7617: {'lr': 0.0004982257037088574, 'samples': 1462464, 'steps': 7616, 'loss/train': 1.541679859161377} 08/30/2021 14:32:37 - INFO - __main__ - Step 7618: {'lr': 0.0004982250725295173, 'samples': 1462656, 'steps': 7617, 'loss/train': 1.7694965600967407} 08/30/2021 14:32:38 - INFO - __main__ - Step 7619: {'lr': 0.0004982244412383307, 'samples': 1462848, 'steps': 7618, 'loss/train': 1.8106591701507568} 08/30/2021 14:32:38 - INFO - __main__ - Step 7620: {'lr': 0.0004982238098352981, 'samples': 1463040, 'steps': 7619, 'loss/train': 2.0153603553771973} 08/30/2021 14:32:39 - INFO - __main__ - Step 7621: {'lr': 0.0004982231783204196, 'samples': 1463232, 'steps': 7620, 'loss/train': 2.341870069503784} 08/30/2021 14:32:39 - INFO - __main__ - Step 7622: {'lr': 0.0004982225466936957, 'samples': 1463424, 'steps': 7621, 'loss/train': 1.6655136346817017} 08/30/2021 14:32:40 - INFO - __main__ - Step 7623: {'lr': 0.0004982219149551265, 'samples': 1463616, 'steps': 7622, 'loss/train': 1.1686482429504395} 08/30/2021 14:32:41 - INFO - __main__ - Step 7624: {'lr': 0.0004982212831047123, 'samples': 1463808, 'steps': 7623, 'loss/train': 1.8940069675445557} 08/30/2021 14:32:41 - INFO - __main__ - Step 7625: {'lr': 0.0004982206511424534, 'samples': 1464000, 'steps': 7624, 'loss/train': 2.999492883682251} 08/30/2021 14:32:42 - INFO - __main__ - Step 7626: {'lr': 0.0004982200190683502, 'samples': 1464192, 'steps': 7625, 'loss/train': 1.9776214361190796} 08/30/2021 14:32:42 - INFO - __main__ - Step 7627: {'lr': 0.0004982193868824028, 'samples': 1464384, 'steps': 7626, 'loss/train': 2.043475389480591} 08/30/2021 14:32:44 - INFO - __main__ - Step 7628: {'lr': 0.0004982187545846116, 'samples': 1464576, 'steps': 7627, 'loss/train': 1.5122380256652832} 08/30/2021 14:32:44 - INFO - __main__ - Step 7629: {'lr': 0.0004982181221749769, 'samples': 1464768, 'steps': 7628, 'loss/train': 2.130232810974121} 08/30/2021 14:32:44 - INFO - __main__ - Step 7630: {'lr': 0.0004982174896534989, 'samples': 1464960, 'steps': 7629, 'loss/train': 2.17044734954834} 08/30/2021 14:32:45 - INFO - __main__ - Step 7631: {'lr': 0.0004982168570201779, 'samples': 1465152, 'steps': 7630, 'loss/train': 2.147237539291382} 08/30/2021 14:32:45 - INFO - __main__ - Step 7632: {'lr': 0.0004982162242750143, 'samples': 1465344, 'steps': 7631, 'loss/train': 1.9035475254058838} 08/30/2021 14:32:47 - INFO - __main__ - Step 7633: {'lr': 0.0004982155914180082, 'samples': 1465536, 'steps': 7632, 'loss/train': 2.0401601791381836} 08/30/2021 14:32:47 - INFO - __main__ - Step 7634: {'lr': 0.0004982149584491601, 'samples': 1465728, 'steps': 7633, 'loss/train': 2.2002885341644287} 08/30/2021 14:32:48 - INFO - __main__ - Step 7635: {'lr': 0.0004982143253684701, 'samples': 1465920, 'steps': 7634, 'loss/train': 2.4061896800994873} 08/30/2021 14:32:48 - INFO - __main__ - Step 7636: {'lr': 0.0004982136921759385, 'samples': 1466112, 'steps': 7635, 'loss/train': 2.3751139640808105} 08/30/2021 14:32:48 - INFO - __main__ - Step 7637: {'lr': 0.0004982130588715657, 'samples': 1466304, 'steps': 7636, 'loss/train': 1.6981489658355713} 08/30/2021 14:32:49 - INFO - __main__ - Step 7638: {'lr': 0.000498212425455352, 'samples': 1466496, 'steps': 7637, 'loss/train': 0.2940669059753418} 08/30/2021 14:32:50 - INFO - __main__ - Step 7639: {'lr': 0.0004982117919272975, 'samples': 1466688, 'steps': 7638, 'loss/train': 1.4565587043762207} 08/30/2021 14:32:51 - INFO - __main__ - Step 7640: {'lr': 0.0004982111582874026, 'samples': 1466880, 'steps': 7639, 'loss/train': 2.233288049697876} 08/30/2021 14:32:51 - INFO - __main__ - Step 7641: {'lr': 0.0004982105245356676, 'samples': 1467072, 'steps': 7640, 'loss/train': 2.2874677181243896} 08/30/2021 14:32:51 - INFO - __main__ - Step 7642: {'lr': 0.0004982098906720928, 'samples': 1467264, 'steps': 7641, 'loss/train': 2.661987781524658} 08/30/2021 14:32:52 - INFO - __main__ - Step 7643: {'lr': 0.0004982092566966785, 'samples': 1467456, 'steps': 7642, 'loss/train': 1.7330474853515625} 08/30/2021 14:32:54 - INFO - __main__ - Step 7644: {'lr': 0.0004982086226094248, 'samples': 1467648, 'steps': 7643, 'loss/train': 1.758739709854126} 08/30/2021 14:32:54 - INFO - __main__ - Step 7645: {'lr': 0.0004982079884103322, 'samples': 1467840, 'steps': 7644, 'loss/train': 1.550981044769287} 08/30/2021 14:32:55 - INFO - __main__ - Step 7646: {'lr': 0.0004982073540994009, 'samples': 1468032, 'steps': 7645, 'loss/train': 1.6437125205993652} 08/30/2021 14:32:55 - INFO - __main__ - Step 7647: {'lr': 0.0004982067196766312, 'samples': 1468224, 'steps': 7646, 'loss/train': 1.827168583869934} 08/30/2021 14:32:55 - INFO - __main__ - Step 7648: {'lr': 0.0004982060851420235, 'samples': 1468416, 'steps': 7647, 'loss/train': 1.9852111339569092} 08/30/2021 14:32:57 - INFO - __main__ - Step 7649: {'lr': 0.0004982054504955778, 'samples': 1468608, 'steps': 7648, 'loss/train': 1.8847118616104126} 08/30/2021 14:32:57 - INFO - __main__ - Step 7650: {'lr': 0.0004982048157372946, 'samples': 1468800, 'steps': 7649, 'loss/train': 1.9492592811584473} 08/30/2021 14:32:58 - INFO - __main__ - Step 7651: {'lr': 0.0004982041808671741, 'samples': 1468992, 'steps': 7650, 'loss/train': 1.8398195505142212} 08/30/2021 14:32:58 - INFO - __main__ - Step 7652: {'lr': 0.0004982035458852168, 'samples': 1469184, 'steps': 7651, 'loss/train': 1.9448692798614502} 08/30/2021 14:32:58 - INFO - __main__ - Step 7653: {'lr': 0.0004982029107914226, 'samples': 1469376, 'steps': 7652, 'loss/train': 1.842936396598816} 08/30/2021 14:32:59 - INFO - __main__ - Step 7654: {'lr': 0.0004982022755857921, 'samples': 1469568, 'steps': 7653, 'loss/train': 2.1686980724334717} 08/30/2021 14:33:00 - INFO - __main__ - Step 7655: {'lr': 0.0004982016402683255, 'samples': 1469760, 'steps': 7654, 'loss/train': 3.0476479530334473} 08/30/2021 14:33:01 - INFO - __main__ - Step 7656: {'lr': 0.000498201004839023, 'samples': 1469952, 'steps': 7655, 'loss/train': 1.9071561098098755} 08/30/2021 14:33:01 - INFO - __main__ - Step 7657: {'lr': 0.000498200369297885, 'samples': 1470144, 'steps': 7656, 'loss/train': 1.9576544761657715} 08/30/2021 14:33:02 - INFO - __main__ - Step 7658: {'lr': 0.0004981997336449118, 'samples': 1470336, 'steps': 7657, 'loss/train': 2.221675157546997} 08/30/2021 14:33:02 - INFO - __main__ - Step 7659: {'lr': 0.0004981990978801035, 'samples': 1470528, 'steps': 7658, 'loss/train': 0.7236251831054688} 08/30/2021 14:33:04 - INFO - __main__ - Step 7660: {'lr': 0.0004981984620034606, 'samples': 1470720, 'steps': 7659, 'loss/train': 1.8968356847763062} 08/30/2021 14:33:04 - INFO - __main__ - Step 7661: {'lr': 0.0004981978260149833, 'samples': 1470912, 'steps': 7660, 'loss/train': 2.056927442550659} 08/30/2021 14:33:04 - INFO - __main__ - Step 7662: {'lr': 0.0004981971899146719, 'samples': 1471104, 'steps': 7661, 'loss/train': 1.60395348072052} 08/30/2021 14:33:05 - INFO - __main__ - Step 7663: {'lr': 0.0004981965537025267, 'samples': 1471296, 'steps': 7662, 'loss/train': 2.0221469402313232} 08/30/2021 14:33:05 - INFO - __main__ - Step 7664: {'lr': 0.000498195917378548, 'samples': 1471488, 'steps': 7663, 'loss/train': 1.7255994081497192} 08/30/2021 14:33:07 - INFO - __main__ - Step 7665: {'lr': 0.0004981952809427359, 'samples': 1471680, 'steps': 7664, 'loss/train': 2.2085747718811035} 08/30/2021 14:33:07 - INFO - __main__ - Step 7666: {'lr': 0.0004981946443950909, 'samples': 1471872, 'steps': 7665, 'loss/train': 1.760868787765503} 08/30/2021 14:33:08 - INFO - __main__ - Step 7667: {'lr': 0.0004981940077356132, 'samples': 1472064, 'steps': 7666, 'loss/train': 1.9882076978683472} 08/30/2021 14:33:08 - INFO - __main__ - Step 7668: {'lr': 0.0004981933709643032, 'samples': 1472256, 'steps': 7667, 'loss/train': 2.031376361846924} 08/30/2021 14:33:08 - INFO - __main__ - Step 7669: {'lr': 0.000498192734081161, 'samples': 1472448, 'steps': 7668, 'loss/train': 1.1171282529830933} 08/30/2021 14:33:10 - INFO - __main__ - Step 7670: {'lr': 0.000498192097086187, 'samples': 1472640, 'steps': 7669, 'loss/train': 0.3261836767196655} 08/30/2021 14:33:10 - INFO - __main__ - Step 7671: {'lr': 0.0004981914599793816, 'samples': 1472832, 'steps': 7670, 'loss/train': 2.1289432048797607} 08/30/2021 14:33:11 - INFO - __main__ - Step 7672: {'lr': 0.0004981908227607448, 'samples': 1473024, 'steps': 7671, 'loss/train': 1.897096872329712} 08/30/2021 14:33:11 - INFO - __main__ - Step 7673: {'lr': 0.0004981901854302771, 'samples': 1473216, 'steps': 7672, 'loss/train': 2.2631258964538574} 08/30/2021 14:33:11 - INFO - __main__ - Step 7674: {'lr': 0.0004981895479879787, 'samples': 1473408, 'steps': 7673, 'loss/train': 0.18086963891983032} 08/30/2021 14:33:13 - INFO - __main__ - Step 7675: {'lr': 0.0004981889104338499, 'samples': 1473600, 'steps': 7674, 'loss/train': 1.6707899570465088} 08/30/2021 14:33:13 - INFO - __main__ - Step 7676: {'lr': 0.0004981882727678912, 'samples': 1473792, 'steps': 7675, 'loss/train': 1.721340537071228} 08/30/2021 14:33:14 - INFO - __main__ - Step 7677: {'lr': 0.0004981876349901025, 'samples': 1473984, 'steps': 7676, 'loss/train': 2.6755495071411133} 08/30/2021 14:33:14 - INFO - __main__ - Step 7678: {'lr': 0.0004981869971004843, 'samples': 1474176, 'steps': 7677, 'loss/train': 2.2184014320373535} 08/30/2021 14:33:14 - INFO - __main__ - Step 7679: {'lr': 0.0004981863590990369, 'samples': 1474368, 'steps': 7678, 'loss/train': 2.0429258346557617} 08/30/2021 14:33:16 - INFO - __main__ - Step 7680: {'lr': 0.0004981857209857605, 'samples': 1474560, 'steps': 7679, 'loss/train': 2.1642518043518066} 08/30/2021 14:33:16 - INFO - __main__ - Step 7681: {'lr': 0.0004981850827606556, 'samples': 1474752, 'steps': 7680, 'loss/train': 2.048515558242798} 08/30/2021 14:33:17 - INFO - __main__ - Step 7682: {'lr': 0.0004981844444237223, 'samples': 1474944, 'steps': 7681, 'loss/train': 1.869009256362915} 08/30/2021 14:33:17 - INFO - __main__ - Step 7683: {'lr': 0.0004981838059749607, 'samples': 1475136, 'steps': 7682, 'loss/train': 1.895453929901123} 08/30/2021 14:33:17 - INFO - __main__ - Step 7684: {'lr': 0.0004981831674143716, 'samples': 1475328, 'steps': 7683, 'loss/train': 5.6247382164001465} 08/30/2021 14:33:19 - INFO - __main__ - Step 7685: {'lr': 0.0004981825287419549, 'samples': 1475520, 'steps': 7684, 'loss/train': 2.1324689388275146} 08/30/2021 14:33:20 - INFO - __main__ - Step 7686: {'lr': 0.0004981818899577108, 'samples': 1475712, 'steps': 7685, 'loss/train': 0.21272243559360504} 08/30/2021 14:33:20 - INFO - __main__ - Step 7687: {'lr': 0.0004981812510616399, 'samples': 1475904, 'steps': 7686, 'loss/train': 1.6858524084091187} 08/30/2021 14:33:20 - INFO - __main__ - Step 7688: {'lr': 0.0004981806120537424, 'samples': 1476096, 'steps': 7687, 'loss/train': 1.5783642530441284} 08/30/2021 14:33:21 - INFO - __main__ - Step 7689: {'lr': 0.0004981799729340185, 'samples': 1476288, 'steps': 7688, 'loss/train': 1.5531423091888428} 08/30/2021 14:33:22 - INFO - __main__ - Step 7690: {'lr': 0.0004981793337024685, 'samples': 1476480, 'steps': 7689, 'loss/train': 2.4547955989837646} 08/30/2021 14:33:23 - INFO - __main__ - Step 7691: {'lr': 0.0004981786943590928, 'samples': 1476672, 'steps': 7690, 'loss/train': 1.785744547843933} 08/30/2021 14:33:23 - INFO - __main__ - Step 7692: {'lr': 0.0004981780549038916, 'samples': 1476864, 'steps': 7691, 'loss/train': 1.6092928647994995} 08/30/2021 14:33:23 - INFO - __main__ - Step 7693: {'lr': 0.0004981774153368651, 'samples': 1477056, 'steps': 7692, 'loss/train': 1.8361210823059082} 08/30/2021 14:33:24 - INFO - __main__ - Step 7694: {'lr': 0.0004981767756580138, 'samples': 1477248, 'steps': 7693, 'loss/train': 2.2799594402313232} 08/30/2021 14:33:24 - INFO - __main__ - Step 7695: {'lr': 0.0004981761358673378, 'samples': 1477440, 'steps': 7694, 'loss/train': 4.373284339904785} 08/30/2021 14:33:27 - INFO - __main__ - Step 7696: {'lr': 0.0004981754959648376, 'samples': 1477632, 'steps': 7695, 'loss/train': 1.950577735900879} 08/30/2021 14:33:27 - INFO - __main__ - Step 7697: {'lr': 0.0004981748559505131, 'samples': 1477824, 'steps': 7696, 'loss/train': 2.0849568843841553} 08/30/2021 14:33:27 - INFO - __main__ - Step 7698: {'lr': 0.0004981742158243651, 'samples': 1478016, 'steps': 7697, 'loss/train': 1.7016234397888184} 08/30/2021 14:33:28 - INFO - __main__ - Step 7699: {'lr': 0.0004981735755863934, 'samples': 1478208, 'steps': 7698, 'loss/train': 3.159191846847534} 08/30/2021 14:33:28 - INFO - __main__ - Step 7700: {'lr': 0.0004981729352365986, 'samples': 1478400, 'steps': 7699, 'loss/train': 3.891718626022339} 08/30/2021 14:33:29 - INFO - __main__ - Step 7701: {'lr': 0.0004981722947749811, 'samples': 1478592, 'steps': 7700, 'loss/train': 2.0479910373687744} 08/30/2021 14:33:30 - INFO - __main__ - Step 7702: {'lr': 0.0004981716542015408, 'samples': 1478784, 'steps': 7701, 'loss/train': 1.7043089866638184} 08/30/2021 14:33:30 - INFO - __main__ - Step 7703: {'lr': 0.0004981710135162781, 'samples': 1478976, 'steps': 7702, 'loss/train': 2.0409011840820312} 08/30/2021 14:33:31 - INFO - __main__ - Step 7704: {'lr': 0.0004981703727191935, 'samples': 1479168, 'steps': 7703, 'loss/train': 1.478135585784912} 08/30/2021 14:33:31 - INFO - __main__ - Step 7705: {'lr': 0.0004981697318102872, 'samples': 1479360, 'steps': 7704, 'loss/train': 1.5815083980560303} 08/30/2021 14:33:31 - INFO - __main__ - Step 7706: {'lr': 0.0004981690907895594, 'samples': 1479552, 'steps': 7705, 'loss/train': 1.8284897804260254} 08/30/2021 14:33:33 - INFO - __main__ - Step 7707: {'lr': 0.0004981684496570104, 'samples': 1479744, 'steps': 7706, 'loss/train': 1.9333336353302002} 08/30/2021 14:33:34 - INFO - __main__ - Step 7708: {'lr': 0.0004981678084126405, 'samples': 1479936, 'steps': 7707, 'loss/train': 2.1768548488616943} 08/30/2021 14:33:34 - INFO - __main__ - Step 7709: {'lr': 0.0004981671670564502, 'samples': 1480128, 'steps': 7708, 'loss/train': 2.0018832683563232} 08/30/2021 14:33:34 - INFO - __main__ - Step 7710: {'lr': 0.0004981665255884394, 'samples': 1480320, 'steps': 7709, 'loss/train': 1.8176385164260864} 08/30/2021 14:33:35 - INFO - __main__ - Step 7711: {'lr': 0.0004981658840086087, 'samples': 1480512, 'steps': 7710, 'loss/train': 2.4641194343566895} 08/30/2021 14:33:37 - INFO - __main__ - Step 7712: {'lr': 0.0004981652423169582, 'samples': 1480704, 'steps': 7711, 'loss/train': 2.517939805984497} 08/30/2021 14:33:37 - INFO - __main__ - Step 7713: {'lr': 0.0004981646005134884, 'samples': 1480896, 'steps': 7712, 'loss/train': 1.9476361274719238} 08/30/2021 14:33:38 - INFO - __main__ - Step 7714: {'lr': 0.0004981639585981993, 'samples': 1481088, 'steps': 7713, 'loss/train': 1.4016057252883911} 08/30/2021 14:33:38 - INFO - __main__ - Step 7715: {'lr': 0.0004981633165710914, 'samples': 1481280, 'steps': 7714, 'loss/train': 2.2590274810791016} 08/30/2021 14:33:38 - INFO - __main__ - Step 7716: {'lr': 0.000498162674432165, 'samples': 1481472, 'steps': 7715, 'loss/train': 1.2550439834594727} 08/30/2021 14:33:39 - INFO - __main__ - Step 7717: {'lr': 0.0004981620321814203, 'samples': 1481664, 'steps': 7716, 'loss/train': 1.630491852760315} 08/30/2021 14:33:40 - INFO - __main__ - Step 7718: {'lr': 0.0004981613898188576, 'samples': 1481856, 'steps': 7717, 'loss/train': 0.3752845227718353} 08/30/2021 14:33:41 - INFO - __main__ - Step 7719: {'lr': 0.0004981607473444772, 'samples': 1482048, 'steps': 7718, 'loss/train': 2.00740385055542} 08/30/2021 14:33:41 - INFO - __main__ - Step 7720: {'lr': 0.0004981601047582794, 'samples': 1482240, 'steps': 7719, 'loss/train': 1.7867883443832397} 08/30/2021 14:33:41 - INFO - __main__ - Step 7721: {'lr': 0.0004981594620602645, 'samples': 1482432, 'steps': 7720, 'loss/train': 1.9333055019378662} 08/30/2021 14:33:42 - INFO - __main__ - Step 7722: {'lr': 0.0004981588192504329, 'samples': 1482624, 'steps': 7721, 'loss/train': 2.3572096824645996} 08/30/2021 14:33:42 - INFO - __main__ - Step 7723: {'lr': 0.0004981581763287845, 'samples': 1482816, 'steps': 7722, 'loss/train': 2.277782440185547} 08/30/2021 14:33:44 - INFO - __main__ - Step 7724: {'lr': 0.0004981575332953201, 'samples': 1483008, 'steps': 7723, 'loss/train': 2.4683494567871094} 08/30/2021 14:33:44 - INFO - __main__ - Step 7725: {'lr': 0.0004981568901500396, 'samples': 1483200, 'steps': 7724, 'loss/train': 1.2349966764450073} 08/30/2021 14:33:44 - INFO - __main__ - Step 7726: {'lr': 0.0004981562468929435, 'samples': 1483392, 'steps': 7725, 'loss/train': 2.003632068634033} 08/30/2021 14:33:45 - INFO - __main__ - Step 7727: {'lr': 0.000498155603524032, 'samples': 1483584, 'steps': 7726, 'loss/train': 2.1388509273529053} 08/30/2021 14:33:45 - INFO - __main__ - Step 7728: {'lr': 0.0004981549600433054, 'samples': 1483776, 'steps': 7727, 'loss/train': 2.016356945037842} 08/30/2021 14:33:46 - INFO - __main__ - Step 7729: {'lr': 0.000498154316450764, 'samples': 1483968, 'steps': 7728, 'loss/train': 1.7072561979293823} 08/30/2021 14:33:47 - INFO - __main__ - Step 7730: {'lr': 0.0004981536727464082, 'samples': 1484160, 'steps': 7729, 'loss/train': 2.40846586227417} 08/30/2021 14:33:47 - INFO - __main__ - Step 7731: {'lr': 0.0004981530289302381, 'samples': 1484352, 'steps': 7730, 'loss/train': 2.1133437156677246} 08/30/2021 14:33:48 - INFO - __main__ - Step 7732: {'lr': 0.000498152385002254, 'samples': 1484544, 'steps': 7731, 'loss/train': 2.262312889099121} 08/30/2021 14:33:48 - INFO - __main__ - Step 7733: {'lr': 0.0004981517409624564, 'samples': 1484736, 'steps': 7732, 'loss/train': 2.06803822517395} 08/30/2021 14:33:49 - INFO - __main__ - Step 7734: {'lr': 0.0004981510968108453, 'samples': 1484928, 'steps': 7733, 'loss/train': 1.520646572113037} 08/30/2021 14:33:50 - INFO - __main__ - Step 7735: {'lr': 0.0004981504525474214, 'samples': 1485120, 'steps': 7734, 'loss/train': 2.074373245239258} 08/30/2021 14:33:50 - INFO - __main__ - Step 7736: {'lr': 0.0004981498081721845, 'samples': 1485312, 'steps': 7735, 'loss/train': 1.8635661602020264} 08/30/2021 14:33:51 - INFO - __main__ - Step 7737: {'lr': 0.0004981491636851351, 'samples': 1485504, 'steps': 7736, 'loss/train': 1.557376742362976} 08/30/2021 14:33:51 - INFO - __main__ - Step 7738: {'lr': 0.0004981485190862737, 'samples': 1485696, 'steps': 7737, 'loss/train': 1.9101672172546387} 08/30/2021 14:33:52 - INFO - __main__ - Step 7739: {'lr': 0.0004981478743756004, 'samples': 1485888, 'steps': 7738, 'loss/train': 2.0683064460754395} 08/30/2021 14:33:53 - INFO - __main__ - Step 7740: {'lr': 0.0004981472295531153, 'samples': 1486080, 'steps': 7739, 'loss/train': 2.0462048053741455} 08/30/2021 14:33:53 - INFO - __main__ - Step 7741: {'lr': 0.000498146584618819, 'samples': 1486272, 'steps': 7740, 'loss/train': 2.059128999710083} 08/30/2021 14:33:53 - INFO - __main__ - Step 7742: {'lr': 0.0004981459395727117, 'samples': 1486464, 'steps': 7741, 'loss/train': 1.4216228723526} 08/30/2021 14:33:54 - INFO - __main__ - Step 7743: {'lr': 0.0004981452944147937, 'samples': 1486656, 'steps': 7742, 'loss/train': 1.7106612920761108} 08/30/2021 14:33:55 - INFO - __main__ - Step 7744: {'lr': 0.0004981446491450652, 'samples': 1486848, 'steps': 7743, 'loss/train': 2.3453712463378906} 08/30/2021 14:33:56 - INFO - __main__ - Step 7745: {'lr': 0.0004981440037635266, 'samples': 1487040, 'steps': 7744, 'loss/train': 1.805321216583252} 08/30/2021 14:33:56 - INFO - __main__ - Step 7746: {'lr': 0.0004981433582701781, 'samples': 1487232, 'steps': 7745, 'loss/train': 1.8666877746582031} 08/30/2021 14:33:57 - INFO - __main__ - Step 7747: {'lr': 0.00049814271266502, 'samples': 1487424, 'steps': 7746, 'loss/train': 1.5551704168319702} 08/30/2021 14:33:57 - INFO - __main__ - Step 7748: {'lr': 0.0004981420669480526, 'samples': 1487616, 'steps': 7747, 'loss/train': 1.9459718465805054} 08/30/2021 14:33:58 - INFO - __main__ - Step 7749: {'lr': 0.0004981414211192763, 'samples': 1487808, 'steps': 7748, 'loss/train': 1.812592625617981} 08/30/2021 14:33:59 - INFO - __main__ - Step 7750: {'lr': 0.0004981407751786913, 'samples': 1488000, 'steps': 7749, 'loss/train': 2.0698540210723877} 08/30/2021 14:33:59 - INFO - __main__ - Step 7751: {'lr': 0.0004981401291262979, 'samples': 1488192, 'steps': 7750, 'loss/train': 2.1763041019439697} 08/30/2021 14:34:00 - INFO - __main__ - Step 7752: {'lr': 0.0004981394829620963, 'samples': 1488384, 'steps': 7751, 'loss/train': 1.6592662334442139} 08/30/2021 14:34:00 - INFO - __main__ - Step 7753: {'lr': 0.0004981388366860869, 'samples': 1488576, 'steps': 7752, 'loss/train': 2.004002571105957} 08/30/2021 14:34:02 - INFO - __main__ - Step 7754: {'lr': 0.0004981381902982702, 'samples': 1488768, 'steps': 7753, 'loss/train': 1.9877376556396484} 08/30/2021 14:34:02 - INFO - __main__ - Step 7755: {'lr': 0.0004981375437986459, 'samples': 1488960, 'steps': 7754, 'loss/train': 1.8999247550964355} 08/30/2021 14:34:03 - INFO - __main__ - Step 7756: {'lr': 0.0004981368971872149, 'samples': 1489152, 'steps': 7755, 'loss/train': 1.6776868104934692} 08/30/2021 14:34:03 - INFO - __main__ - Step 7757: {'lr': 0.0004981362504639772, 'samples': 1489344, 'steps': 7756, 'loss/train': 1.939148187637329} 08/30/2021 14:34:04 - INFO - __main__ - Step 7758: {'lr': 0.0004981356036289331, 'samples': 1489536, 'steps': 7757, 'loss/train': 2.2283542156219482} 08/30/2021 14:34:05 - INFO - __main__ - Step 7759: {'lr': 0.0004981349566820828, 'samples': 1489728, 'steps': 7758, 'loss/train': 2.072937250137329} 08/30/2021 14:34:05 - INFO - __main__ - Step 7760: {'lr': 0.0004981343096234268, 'samples': 1489920, 'steps': 7759, 'loss/train': 1.9974037408828735} 08/30/2021 14:34:06 - INFO - __main__ - Step 7761: {'lr': 0.0004981336624529654, 'samples': 1490112, 'steps': 7760, 'loss/train': 1.4315470457077026} 08/30/2021 14:34:06 - INFO - __main__ - Step 7762: {'lr': 0.0004981330151706988, 'samples': 1490304, 'steps': 7761, 'loss/train': 2.379178762435913} 08/30/2021 14:34:07 - INFO - __main__ - Step 7763: {'lr': 0.0004981323677766273, 'samples': 1490496, 'steps': 7762, 'loss/train': 2.22389554977417} 08/30/2021 14:34:08 - INFO - __main__ - Step 7764: {'lr': 0.000498131720270751, 'samples': 1490688, 'steps': 7763, 'loss/train': 2.1621785163879395} 08/30/2021 14:34:08 - INFO - __main__ - Step 7765: {'lr': 0.0004981310726530706, 'samples': 1490880, 'steps': 7764, 'loss/train': 1.9238741397857666} 08/30/2021 14:34:09 - INFO - __main__ - Step 7766: {'lr': 0.0004981304249235861, 'samples': 1491072, 'steps': 7765, 'loss/train': 2.118007183074951} 08/30/2021 14:34:09 - INFO - __main__ - Step 7767: {'lr': 0.0004981297770822977, 'samples': 1491264, 'steps': 7766, 'loss/train': 1.4278289079666138} 08/30/2021 14:34:09 - INFO - __main__ - Step 7768: {'lr': 0.0004981291291292061, 'samples': 1491456, 'steps': 7767, 'loss/train': 2.1991090774536133} 08/30/2021 14:34:10 - INFO - __main__ - Step 7769: {'lr': 0.0004981284810643112, 'samples': 1491648, 'steps': 7768, 'loss/train': 1.9503018856048584} 08/30/2021 14:34:11 - INFO - __main__ - Step 7770: {'lr': 0.0004981278328876134, 'samples': 1491840, 'steps': 7769, 'loss/train': 1.9926166534423828} 08/30/2021 14:34:12 - INFO - __main__ - Step 7771: {'lr': 0.0004981271845991131, 'samples': 1492032, 'steps': 7770, 'loss/train': 2.072086811065674} 08/30/2021 14:34:12 - INFO - __main__ - Step 7772: {'lr': 0.0004981265361988105, 'samples': 1492224, 'steps': 7771, 'loss/train': 1.7195425033569336} 08/30/2021 14:34:13 - INFO - __main__ - Step 7773: {'lr': 0.000498125887686706, 'samples': 1492416, 'steps': 7772, 'loss/train': 2.0277905464172363} 08/30/2021 14:34:13 - INFO - __main__ - Step 7774: {'lr': 0.0004981252390627997, 'samples': 1492608, 'steps': 7773, 'loss/train': 1.9627342224121094} 08/30/2021 14:34:14 - INFO - __main__ - Step 7775: {'lr': 0.000498124590327092, 'samples': 1492800, 'steps': 7774, 'loss/train': 1.5249673128128052} 08/30/2021 14:34:15 - INFO - __main__ - Step 7776: {'lr': 0.0004981239414795832, 'samples': 1492992, 'steps': 7775, 'loss/train': 2.2362020015716553} 08/30/2021 14:34:15 - INFO - __main__ - Step 7777: {'lr': 0.0004981232925202736, 'samples': 1493184, 'steps': 7776, 'loss/train': 2.6314713954925537} 08/30/2021 14:34:15 - INFO - __main__ - Step 7778: {'lr': 0.0004981226434491635, 'samples': 1493376, 'steps': 7777, 'loss/train': 2.2494640350341797} 08/30/2021 14:34:16 - INFO - __main__ - Step 7779: {'lr': 0.000498121994266253, 'samples': 1493568, 'steps': 7778, 'loss/train': 2.3969132900238037} 08/30/2021 14:34:17 - INFO - __main__ - Step 7780: {'lr': 0.0004981213449715427, 'samples': 1493760, 'steps': 7779, 'loss/train': 1.8594331741333008} 08/30/2021 14:34:18 - INFO - __main__ - Step 7781: {'lr': 0.0004981206955650328, 'samples': 1493952, 'steps': 7780, 'loss/train': 2.656524658203125} 08/30/2021 14:34:18 - INFO - __main__ - Step 7782: {'lr': 0.0004981200460467234, 'samples': 1494144, 'steps': 7781, 'loss/train': 2.2213633060455322} 08/30/2021 14:34:19 - INFO - __main__ - Step 7783: {'lr': 0.0004981193964166151, 'samples': 1494336, 'steps': 7782, 'loss/train': 1.5977270603179932} 08/30/2021 14:34:19 - INFO - __main__ - Step 7784: {'lr': 0.0004981187466747079, 'samples': 1494528, 'steps': 7783, 'loss/train': 2.01069974899292} 08/30/2021 14:34:20 - INFO - __main__ - Step 7785: {'lr': 0.0004981180968210023, 'samples': 1494720, 'steps': 7784, 'loss/train': 1.7394118309020996} 08/30/2021 14:34:21 - INFO - __main__ - Step 7786: {'lr': 0.0004981174468554984, 'samples': 1494912, 'steps': 7785, 'loss/train': 6.545466423034668} 08/30/2021 14:34:21 - INFO - __main__ - Step 7787: {'lr': 0.0004981167967781968, 'samples': 1495104, 'steps': 7786, 'loss/train': 1.223050594329834} 08/30/2021 14:34:22 - INFO - __main__ - Step 7788: {'lr': 0.0004981161465890975, 'samples': 1495296, 'steps': 7787, 'loss/train': 1.7190486192703247} 08/30/2021 14:34:22 - INFO - __main__ - Step 7789: {'lr': 0.0004981154962882008, 'samples': 1495488, 'steps': 7788, 'loss/train': 1.9940739870071411} 08/30/2021 14:34:22 - INFO - __main__ - Step 7790: {'lr': 0.0004981148458755071, 'samples': 1495680, 'steps': 7789, 'loss/train': 2.0188848972320557} 08/30/2021 14:34:24 - INFO - __main__ - Step 7791: {'lr': 0.0004981141953510169, 'samples': 1495872, 'steps': 7790, 'loss/train': 1.7441670894622803} 08/30/2021 14:34:24 - INFO - __main__ - Step 7792: {'lr': 0.00049811354471473, 'samples': 1496064, 'steps': 7791, 'loss/train': 1.5147539377212524} 08/30/2021 14:34:25 - INFO - __main__ - Step 7793: {'lr': 0.0004981128939666471, 'samples': 1496256, 'steps': 7792, 'loss/train': 1.9101200103759766} 08/30/2021 14:34:25 - INFO - __main__ - Step 7794: {'lr': 0.0004981122431067683, 'samples': 1496448, 'steps': 7793, 'loss/train': 1.965456485748291} 08/30/2021 14:34:25 - INFO - __main__ - Step 7795: {'lr': 0.0004981115921350941, 'samples': 1496640, 'steps': 7794, 'loss/train': 2.0283596515655518} 08/30/2021 14:34:27 - INFO - __main__ - Step 7796: {'lr': 0.0004981109410516245, 'samples': 1496832, 'steps': 7795, 'loss/train': 1.6873531341552734} 08/30/2021 14:34:27 - INFO - __main__ - Step 7797: {'lr': 0.00049811028985636, 'samples': 1497024, 'steps': 7796, 'loss/train': 1.7942057847976685} 08/30/2021 14:34:28 - INFO - __main__ - Step 7798: {'lr': 0.0004981096385493007, 'samples': 1497216, 'steps': 7797, 'loss/train': 1.788494348526001} 08/30/2021 14:34:28 - INFO - __main__ - Step 7799: {'lr': 0.0004981089871304472, 'samples': 1497408, 'steps': 7798, 'loss/train': 2.047255754470825} 08/30/2021 14:34:28 - INFO - __main__ - Step 7800: {'lr': 0.0004981083355997995, 'samples': 1497600, 'steps': 7799, 'loss/train': 2.0315942764282227} 08/30/2021 14:34:30 - INFO - __main__ - Step 7801: {'lr': 0.0004981076839573581, 'samples': 1497792, 'steps': 7800, 'loss/train': 1.8836919069290161} 08/30/2021 14:34:30 - INFO - __main__ - Step 7802: {'lr': 0.0004981070322031231, 'samples': 1497984, 'steps': 7801, 'loss/train': 1.91158926486969} 08/30/2021 14:34:31 - INFO - __main__ - Step 7803: {'lr': 0.000498106380337095, 'samples': 1498176, 'steps': 7802, 'loss/train': 2.595004081726074} 08/30/2021 14:34:31 - INFO - __main__ - Step 7804: {'lr': 0.000498105728359274, 'samples': 1498368, 'steps': 7803, 'loss/train': 2.024995803833008} 08/30/2021 14:34:31 - INFO - __main__ - Step 7805: {'lr': 0.0004981050762696604, 'samples': 1498560, 'steps': 7804, 'loss/train': 1.6393280029296875} 08/30/2021 14:34:33 - INFO - __main__ - Step 7806: {'lr': 0.0004981044240682544, 'samples': 1498752, 'steps': 7805, 'loss/train': 1.9961345195770264} 08/30/2021 14:34:34 - INFO - __main__ - Step 7807: {'lr': 0.0004981037717550564, 'samples': 1498944, 'steps': 7806, 'loss/train': 1.8909987211227417} 08/30/2021 14:34:34 - INFO - __main__ - Step 7808: {'lr': 0.0004981031193300667, 'samples': 1499136, 'steps': 7807, 'loss/train': 1.900766134262085} 08/30/2021 14:34:35 - INFO - __main__ - Step 7809: {'lr': 0.0004981024667932855, 'samples': 1499328, 'steps': 7808, 'loss/train': 1.8486652374267578} 08/30/2021 14:34:35 - INFO - __main__ - Step 7810: {'lr': 0.0004981018141447133, 'samples': 1499520, 'steps': 7809, 'loss/train': 1.9063693284988403} 08/30/2021 14:34:36 - INFO - __main__ - Step 7811: {'lr': 0.00049810116138435, 'samples': 1499712, 'steps': 7810, 'loss/train': 1.9456430673599243} 08/30/2021 14:34:37 - INFO - __main__ - Step 7812: {'lr': 0.0004981005085121963, 'samples': 1499904, 'steps': 7811, 'loss/train': 1.6784391403198242} 08/30/2021 14:34:37 - INFO - __main__ - Step 7813: {'lr': 0.0004980998555282524, 'samples': 1500096, 'steps': 7812, 'loss/train': 2.22102952003479} 08/30/2021 14:34:38 - INFO - __main__ - Step 7814: {'lr': 0.0004980992024325185, 'samples': 1500288, 'steps': 7813, 'loss/train': 0.6577968001365662} 08/30/2021 14:34:38 - INFO - __main__ - Step 7815: {'lr': 0.0004980985492249949, 'samples': 1500480, 'steps': 7814, 'loss/train': 1.84895658493042} 08/30/2021 14:34:39 - INFO - __main__ - Step 7816: {'lr': 0.0004980978959056819, 'samples': 1500672, 'steps': 7815, 'loss/train': 1.110809564590454} 08/30/2021 14:34:40 - INFO - __main__ - Step 7817: {'lr': 0.0004980972424745798, 'samples': 1500864, 'steps': 7816, 'loss/train': 1.6254597902297974} 08/30/2021 14:34:40 - INFO - __main__ - Step 7818: {'lr': 0.000498096588931689, 'samples': 1501056, 'steps': 7817, 'loss/train': 1.8533543348312378} 08/30/2021 14:34:41 - INFO - __main__ - Step 7819: {'lr': 0.0004980959352770095, 'samples': 1501248, 'steps': 7818, 'loss/train': 2.1147758960723877} 08/30/2021 14:34:41 - INFO - __main__ - Step 7820: {'lr': 0.000498095281510542, 'samples': 1501440, 'steps': 7819, 'loss/train': 2.053044080734253} 08/30/2021 14:34:42 - INFO - __main__ - Step 7821: {'lr': 0.0004980946276322866, 'samples': 1501632, 'steps': 7820, 'loss/train': 1.740517258644104} 08/30/2021 14:34:43 - INFO - __main__ - Step 7822: {'lr': 0.0004980939736422436, 'samples': 1501824, 'steps': 7821, 'loss/train': 1.7762596607208252} 08/30/2021 14:34:43 - INFO - __main__ - Step 7823: {'lr': 0.0004980933195404131, 'samples': 1502016, 'steps': 7822, 'loss/train': 1.9814330339431763} 08/30/2021 14:34:44 - INFO - __main__ - Step 7824: {'lr': 0.0004980926653267957, 'samples': 1502208, 'steps': 7823, 'loss/train': 1.6790393590927124} 08/30/2021 14:34:44 - INFO - __main__ - Step 7825: {'lr': 0.0004980920110013915, 'samples': 1502400, 'steps': 7824, 'loss/train': 2.0899534225463867} 08/30/2021 14:34:45 - INFO - __main__ - Step 7826: {'lr': 0.000498091356564201, 'samples': 1502592, 'steps': 7825, 'loss/train': 1.817801833152771} 08/30/2021 14:34:46 - INFO - __main__ - Step 7827: {'lr': 0.0004980907020152242, 'samples': 1502784, 'steps': 7826, 'loss/train': 1.7425017356872559} 08/30/2021 14:34:46 - INFO - __main__ - Step 7828: {'lr': 0.0004980900473544617, 'samples': 1502976, 'steps': 7827, 'loss/train': 2.0283257961273193} 08/30/2021 14:34:47 - INFO - __main__ - Step 7829: {'lr': 0.0004980893925819137, 'samples': 1503168, 'steps': 7828, 'loss/train': 1.756772756576538} 08/30/2021 14:34:47 - INFO - __main__ - Step 7830: {'lr': 0.0004980887376975804, 'samples': 1503360, 'steps': 7829, 'loss/train': 1.8477866649627686} 08/30/2021 14:34:49 - INFO - __main__ - Step 7831: {'lr': 0.000498088082701462, 'samples': 1503552, 'steps': 7830, 'loss/train': 1.9399091005325317} 08/30/2021 14:34:49 - INFO - __main__ - Step 7832: {'lr': 0.0004980874275935591, 'samples': 1503744, 'steps': 7831, 'loss/train': 1.925467848777771} 08/30/2021 14:34:49 - INFO - __main__ - Step 7833: {'lr': 0.0004980867723738717, 'samples': 1503936, 'steps': 7832, 'loss/train': 2.454023599624634} 08/30/2021 14:34:50 - INFO - __main__ - Step 7834: {'lr': 0.0004980861170424003, 'samples': 1504128, 'steps': 7833, 'loss/train': 2.172863245010376} 08/30/2021 14:34:50 - INFO - __main__ - Step 7835: {'lr': 0.0004980854615991452, 'samples': 1504320, 'steps': 7834, 'loss/train': 5.90132999420166} 08/30/2021 14:34:51 - INFO - __main__ - Step 7836: {'lr': 0.0004980848060441064, 'samples': 1504512, 'steps': 7835, 'loss/train': 8.035666465759277} 08/30/2021 14:34:52 - INFO - __main__ - Step 7837: {'lr': 0.0004980841503772846, 'samples': 1504704, 'steps': 7836, 'loss/train': 2.5694777965545654} 08/30/2021 14:34:53 - INFO - __main__ - Step 7838: {'lr': 0.0004980834945986799, 'samples': 1504896, 'steps': 7837, 'loss/train': 2.299912691116333} 08/30/2021 14:34:53 - INFO - __main__ - Step 7839: {'lr': 0.0004980828387082925, 'samples': 1505088, 'steps': 7838, 'loss/train': 2.200338840484619} 08/30/2021 14:34:53 - INFO - __main__ - Step 7840: {'lr': 0.000498082182706123, 'samples': 1505280, 'steps': 7839, 'loss/train': 1.0367792844772339} 08/30/2021 14:34:54 - INFO - __main__ - Step 7841: {'lr': 0.0004980815265921713, 'samples': 1505472, 'steps': 7840, 'loss/train': 1.7248426675796509} 08/30/2021 14:34:54 - INFO - __main__ - Step 7842: {'lr': 0.000498080870366438, 'samples': 1505664, 'steps': 7841, 'loss/train': 3.7187607288360596} 08/30/2021 14:34:56 - INFO - __main__ - Step 7843: {'lr': 0.0004980802140289232, 'samples': 1505856, 'steps': 7842, 'loss/train': 1.994019865989685} 08/30/2021 14:34:56 - INFO - __main__ - Step 7844: {'lr': 0.0004980795575796273, 'samples': 1506048, 'steps': 7843, 'loss/train': 2.1058144569396973} 08/30/2021 14:34:56 - INFO - __main__ - Step 7845: {'lr': 0.0004980789010185507, 'samples': 1506240, 'steps': 7844, 'loss/train': 2.454730749130249} 08/30/2021 14:34:57 - INFO - __main__ - Step 7846: {'lr': 0.0004980782443456935, 'samples': 1506432, 'steps': 7845, 'loss/train': 2.023253917694092} 08/30/2021 14:34:57 - INFO - __main__ - Step 7847: {'lr': 0.000498077587561056, 'samples': 1506624, 'steps': 7846, 'loss/train': 2.3231048583984375} 08/30/2021 14:34:59 - INFO - __main__ - Step 7848: {'lr': 0.0004980769306646386, 'samples': 1506816, 'steps': 7847, 'loss/train': 2.014291286468506} 08/30/2021 14:34:59 - INFO - __main__ - Step 7849: {'lr': 0.0004980762736564417, 'samples': 1507008, 'steps': 7848, 'loss/train': 2.087556838989258} 08/30/2021 14:35:00 - INFO - __main__ - Step 7850: {'lr': 0.0004980756165364653, 'samples': 1507200, 'steps': 7849, 'loss/train': 2.1835293769836426} 08/30/2021 14:35:00 - INFO - __main__ - Step 7851: {'lr': 0.0004980749593047099, 'samples': 1507392, 'steps': 7850, 'loss/train': 1.7254502773284912} 08/30/2021 14:35:00 - INFO - __main__ - Step 7852: {'lr': 0.0004980743019611757, 'samples': 1507584, 'steps': 7851, 'loss/train': 0.8205849528312683} 08/30/2021 14:35:02 - INFO - __main__ - Step 7853: {'lr': 0.0004980736445058631, 'samples': 1507776, 'steps': 7852, 'loss/train': 0.36747708916664124} 08/30/2021 14:35:02 - INFO - __main__ - Step 7854: {'lr': 0.0004980729869387724, 'samples': 1507968, 'steps': 7853, 'loss/train': 1.8287383317947388} 08/30/2021 14:35:03 - INFO - __main__ - Step 7855: {'lr': 0.0004980723292599037, 'samples': 1508160, 'steps': 7854, 'loss/train': 2.253176689147949} 08/30/2021 14:35:03 - INFO - __main__ - Step 7856: {'lr': 0.0004980716714692576, 'samples': 1508352, 'steps': 7855, 'loss/train': 1.9407721757888794} 08/30/2021 14:35:03 - INFO - __main__ - Step 7857: {'lr': 0.0004980710135668342, 'samples': 1508544, 'steps': 7856, 'loss/train': 1.7226452827453613} 08/30/2021 14:35:06 - INFO - __main__ - Step 7858: {'lr': 0.0004980703555526338, 'samples': 1508736, 'steps': 7857, 'loss/train': 1.948722004890442} 08/30/2021 14:35:06 - INFO - __main__ - Step 7859: {'lr': 0.0004980696974266566, 'samples': 1508928, 'steps': 7858, 'loss/train': 2.246548891067505} 08/30/2021 14:35:07 - INFO - __main__ - Step 7860: {'lr': 0.0004980690391889033, 'samples': 1509120, 'steps': 7859, 'loss/train': 2.173987627029419} 08/30/2021 14:35:07 - INFO - __main__ - Step 7861: {'lr': 0.0004980683808393737, 'samples': 1509312, 'steps': 7860, 'loss/train': 1.4272888898849487} 08/30/2021 14:35:07 - INFO - __main__ - Step 7862: {'lr': 0.0004980677223780683, 'samples': 1509504, 'steps': 7861, 'loss/train': 0.162075012922287} 08/30/2021 14:35:08 - INFO - __main__ - Step 7863: {'lr': 0.0004980670638049875, 'samples': 1509696, 'steps': 7862, 'loss/train': 1.9510797262191772} 08/30/2021 14:35:09 - INFO - __main__ - Step 7864: {'lr': 0.0004980664051201315, 'samples': 1509888, 'steps': 7863, 'loss/train': 2.119154214859009} 08/30/2021 14:35:10 - INFO - __main__ - Step 7865: {'lr': 0.0004980657463235006, 'samples': 1510080, 'steps': 7864, 'loss/train': 1.5261328220367432} 08/30/2021 14:35:10 - INFO - __main__ - Step 7866: {'lr': 0.0004980650874150951, 'samples': 1510272, 'steps': 7865, 'loss/train': 1.7908101081848145} 08/30/2021 14:35:10 - INFO - __main__ - Step 7867: {'lr': 0.0004980644283949152, 'samples': 1510464, 'steps': 7866, 'loss/train': 1.9720752239227295} 08/30/2021 14:35:11 - INFO - __main__ - Step 7868: {'lr': 0.0004980637692629615, 'samples': 1510656, 'steps': 7867, 'loss/train': 1.6608741283416748} 08/30/2021 14:35:12 - INFO - __main__ - Step 7869: {'lr': 0.0004980631100192339, 'samples': 1510848, 'steps': 7868, 'loss/train': 2.1481995582580566} 08/30/2021 14:35:13 - INFO - __main__ - Step 7870: {'lr': 0.000498062450663733, 'samples': 1511040, 'steps': 7869, 'loss/train': 2.110429286956787} 08/30/2021 14:35:13 - INFO - __main__ - Step 7871: {'lr': 0.000498061791196459, 'samples': 1511232, 'steps': 7870, 'loss/train': 1.9926373958587646} 08/30/2021 14:35:14 - INFO - __main__ - Step 7872: {'lr': 0.0004980611316174122, 'samples': 1511424, 'steps': 7871, 'loss/train': 2.056915760040283} 08/30/2021 14:35:14 - INFO - __main__ - Step 7873: {'lr': 0.0004980604719265928, 'samples': 1511616, 'steps': 7872, 'loss/train': 1.4854575395584106} 08/30/2021 14:35:15 - INFO - __main__ - Step 7874: {'lr': 0.0004980598121240012, 'samples': 1511808, 'steps': 7873, 'loss/train': 2.2308859825134277} 08/30/2021 14:35:16 - INFO - __main__ - Step 7875: {'lr': 0.0004980591522096377, 'samples': 1512000, 'steps': 7874, 'loss/train': 2.1588919162750244} 08/30/2021 14:35:16 - INFO - __main__ - Step 7876: {'lr': 0.0004980584921835025, 'samples': 1512192, 'steps': 7875, 'loss/train': 2.146693706512451} 08/30/2021 14:35:17 - INFO - __main__ - Step 7877: {'lr': 0.000498057832045596, 'samples': 1512384, 'steps': 7876, 'loss/train': 2.067829132080078} 08/30/2021 14:35:17 - INFO - __main__ - Step 7878: {'lr': 0.0004980571717959186, 'samples': 1512576, 'steps': 7877, 'loss/train': 2.116293430328369} 08/30/2021 14:35:19 - INFO - __main__ - Step 7879: {'lr': 0.0004980565114344704, 'samples': 1512768, 'steps': 7878, 'loss/train': 1.7423810958862305} 08/30/2021 14:35:19 - INFO - __main__ - Step 7880: {'lr': 0.0004980558509612516, 'samples': 1512960, 'steps': 7879, 'loss/train': 1.727136492729187} 08/30/2021 14:35:19 - INFO - __main__ - Step 7881: {'lr': 0.0004980551903762629, 'samples': 1513152, 'steps': 7880, 'loss/train': 2.0340633392333984} 08/30/2021 14:35:20 - INFO - __main__ - Step 7882: {'lr': 0.0004980545296795043, 'samples': 1513344, 'steps': 7881, 'loss/train': 1.2240817546844482} 08/30/2021 14:35:20 - INFO - __main__ - Step 7883: {'lr': 0.0004980538688709761, 'samples': 1513536, 'steps': 7882, 'loss/train': 1.252685546875} 08/30/2021 14:35:22 - INFO - __main__ - Step 7884: {'lr': 0.0004980532079506786, 'samples': 1513728, 'steps': 7883, 'loss/train': 1.0615259408950806} 08/30/2021 14:35:22 - INFO - __main__ - Step 7885: {'lr': 0.0004980525469186122, 'samples': 1513920, 'steps': 7884, 'loss/train': 1.0931607484817505} 08/30/2021 14:35:23 - INFO - __main__ - Step 7886: {'lr': 0.0004980518857747772, 'samples': 1514112, 'steps': 7885, 'loss/train': 1.81352698802948} 08/30/2021 14:35:23 - INFO - __main__ - Step 7887: {'lr': 0.0004980512245191738, 'samples': 1514304, 'steps': 7886, 'loss/train': 1.7306314706802368} 08/30/2021 14:35:23 - INFO - __main__ - Step 7888: {'lr': 0.0004980505631518023, 'samples': 1514496, 'steps': 7887, 'loss/train': 2.4788763523101807} 08/30/2021 14:35:25 - INFO - __main__ - Step 7889: {'lr': 0.0004980499016726632, 'samples': 1514688, 'steps': 7888, 'loss/train': 1.7479809522628784} 08/30/2021 14:35:25 - INFO - __main__ - Step 7890: {'lr': 0.0004980492400817564, 'samples': 1514880, 'steps': 7889, 'loss/train': 2.2409465312957764} 08/30/2021 14:35:26 - INFO - __main__ - Step 7891: {'lr': 0.0004980485783790827, 'samples': 1515072, 'steps': 7890, 'loss/train': 2.0339908599853516} 08/30/2021 14:35:26 - INFO - __main__ - Step 7892: {'lr': 0.0004980479165646419, 'samples': 1515264, 'steps': 7891, 'loss/train': 2.3462719917297363} 08/30/2021 14:35:26 - INFO - __main__ - Step 7893: {'lr': 0.0004980472546384347, 'samples': 1515456, 'steps': 7892, 'loss/train': 2.127397298812866} 08/30/2021 14:35:28 - INFO - __main__ - Step 7894: {'lr': 0.0004980465926004613, 'samples': 1515648, 'steps': 7893, 'loss/train': 1.0002518892288208} 08/30/2021 14:35:28 - INFO - __main__ - Step 7895: {'lr': 0.0004980459304507218, 'samples': 1515840, 'steps': 7894, 'loss/train': 1.8891297578811646} 08/30/2021 14:35:29 - INFO - __main__ - Step 7896: {'lr': 0.0004980452681892166, 'samples': 1516032, 'steps': 7895, 'loss/train': 1.329634428024292} 08/30/2021 14:35:29 - INFO - __main__ - Step 7897: {'lr': 0.0004980446058159461, 'samples': 1516224, 'steps': 7896, 'loss/train': 1.7612277269363403} 08/30/2021 14:35:29 - INFO - __main__ - Step 7898: {'lr': 0.0004980439433309106, 'samples': 1516416, 'steps': 7897, 'loss/train': 1.8305355310440063} 08/30/2021 14:35:30 - INFO - __main__ - Step 7899: {'lr': 0.0004980432807341102, 'samples': 1516608, 'steps': 7898, 'loss/train': 1.9770076274871826} 08/30/2021 14:35:31 - INFO - __main__ - Step 7900: {'lr': 0.0004980426180255453, 'samples': 1516800, 'steps': 7899, 'loss/train': 2.2382895946502686} 08/30/2021 14:35:32 - INFO - __main__ - Step 7901: {'lr': 0.0004980419552052163, 'samples': 1516992, 'steps': 7900, 'loss/train': 1.5814892053604126} 08/30/2021 14:35:32 - INFO - __main__ - Step 7902: {'lr': 0.0004980412922731234, 'samples': 1517184, 'steps': 7901, 'loss/train': 1.792866587638855} 08/30/2021 14:35:32 - INFO - __main__ - Step 7903: {'lr': 0.0004980406292292669, 'samples': 1517376, 'steps': 7902, 'loss/train': 2.3232505321502686} 08/30/2021 14:35:33 - INFO - __main__ - Step 7904: {'lr': 0.0004980399660736472, 'samples': 1517568, 'steps': 7903, 'loss/train': 1.5798043012619019} 08/30/2021 14:35:34 - INFO - __main__ - Step 7905: {'lr': 0.0004980393028062646, 'samples': 1517760, 'steps': 7904, 'loss/train': 2.43125057220459} 08/30/2021 14:35:35 - INFO - __main__ - Step 7906: {'lr': 0.0004980386394271191, 'samples': 1517952, 'steps': 7905, 'loss/train': 2.2891671657562256} 08/30/2021 14:35:35 - INFO - __main__ - Step 7907: {'lr': 0.0004980379759362113, 'samples': 1518144, 'steps': 7906, 'loss/train': 2.1696372032165527} 08/30/2021 14:35:35 - INFO - __main__ - Step 7908: {'lr': 0.0004980373123335414, 'samples': 1518336, 'steps': 7907, 'loss/train': 2.017667770385742} 08/30/2021 14:35:36 - INFO - __main__ - Step 7909: {'lr': 0.0004980366486191098, 'samples': 1518528, 'steps': 7908, 'loss/train': 1.5882924795150757} 08/30/2021 14:35:38 - INFO - __main__ - Step 7910: {'lr': 0.0004980359847929167, 'samples': 1518720, 'steps': 7909, 'loss/train': 2.1881558895111084} 08/30/2021 14:35:38 - INFO - __main__ - Step 7911: {'lr': 0.0004980353208549623, 'samples': 1518912, 'steps': 7910, 'loss/train': 1.9824440479278564} 08/30/2021 14:35:38 - INFO - __main__ - Step 7912: {'lr': 0.0004980346568052471, 'samples': 1519104, 'steps': 7911, 'loss/train': 1.9016330242156982} 08/30/2021 14:35:39 - INFO - __main__ - Step 7913: {'lr': 0.0004980339926437713, 'samples': 1519296, 'steps': 7912, 'loss/train': 1.8732227087020874} 08/30/2021 14:35:39 - INFO - __main__ - Step 7914: {'lr': 0.0004980333283705351, 'samples': 1519488, 'steps': 7913, 'loss/train': 2.991459846496582} 08/30/2021 14:35:39 - INFO - __main__ - Step 7915: {'lr': 0.000498032663985539, 'samples': 1519680, 'steps': 7914, 'loss/train': 3.000925064086914} 08/30/2021 14:35:42 - INFO - __main__ - Step 7916: {'lr': 0.0004980319994887833, 'samples': 1519872, 'steps': 7915, 'loss/train': 2.2439892292022705} 08/30/2021 14:35:43 - INFO - __main__ - Step 7917: {'lr': 0.0004980313348802681, 'samples': 1520064, 'steps': 7916, 'loss/train': 1.8466578722000122} 08/30/2021 14:35:43 - INFO - __main__ - Step 7918: {'lr': 0.0004980306701599938, 'samples': 1520256, 'steps': 7917, 'loss/train': 2.148094654083252} 08/30/2021 14:35:43 - INFO - __main__ - Step 7919: {'lr': 0.0004980300053279607, 'samples': 1520448, 'steps': 7918, 'loss/train': 2.8910977840423584} 08/30/2021 14:35:44 - INFO - __main__ - Step 7920: {'lr': 0.0004980293403841693, 'samples': 1520640, 'steps': 7919, 'loss/train': 1.7436580657958984} 08/30/2021 14:35:44 - INFO - __main__ - Step 7921: {'lr': 0.0004980286753286195, 'samples': 1520832, 'steps': 7920, 'loss/train': 0.4521118700504303} 08/30/2021 14:35:44 - INFO - __main__ - Step 7922: {'lr': 0.0004980280101613119, 'samples': 1521024, 'steps': 7921, 'loss/train': 0.3283317983150482} 08/30/2021 14:35:45 - INFO - __main__ - Step 7923: {'lr': 0.0004980273448822466, 'samples': 1521216, 'steps': 7922, 'loss/train': 0.28704833984375} 08/30/2021 14:35:46 - INFO - __main__ - Step 7924: {'lr': 0.000498026679491424, 'samples': 1521408, 'steps': 7923, 'loss/train': 1.5692418813705444} 08/30/2021 14:35:47 - INFO - __main__ - Step 7925: {'lr': 0.0004980260139888445, 'samples': 1521600, 'steps': 7924, 'loss/train': 0.6815661787986755} 08/30/2021 14:35:47 - INFO - __main__ - Step 7926: {'lr': 0.0004980253483745083, 'samples': 1521792, 'steps': 7925, 'loss/train': 1.844468355178833} 08/30/2021 14:35:47 - INFO - __main__ - Step 7927: {'lr': 0.0004980246826484157, 'samples': 1521984, 'steps': 7926, 'loss/train': 1.6807992458343506} 08/30/2021 14:35:48 - INFO - __main__ - Step 7928: {'lr': 0.000498024016810567, 'samples': 1522176, 'steps': 7927, 'loss/train': 1.8619461059570312} 08/30/2021 14:35:49 - INFO - __main__ - Step 7929: {'lr': 0.0004980233508609625, 'samples': 1522368, 'steps': 7928, 'loss/train': 1.9839160442352295} 08/30/2021 14:35:50 - INFO - __main__ - Step 7930: {'lr': 0.0004980226847996025, 'samples': 1522560, 'steps': 7929, 'loss/train': 1.683982014656067} 08/30/2021 14:35:50 - INFO - __main__ - Step 7931: {'lr': 0.0004980220186264874, 'samples': 1522752, 'steps': 7930, 'loss/train': 1.829045057296753} 08/30/2021 14:35:50 - INFO - __main__ - Step 7932: {'lr': 0.0004980213523416172, 'samples': 1522944, 'steps': 7931, 'loss/train': 2.1909728050231934} 08/30/2021 14:35:51 - INFO - __main__ - Step 7933: {'lr': 0.0004980206859449926, 'samples': 1523136, 'steps': 7932, 'loss/train': 1.7288392782211304} 08/30/2021 14:35:52 - INFO - __main__ - Step 7934: {'lr': 0.0004980200194366136, 'samples': 1523328, 'steps': 7933, 'loss/train': 2.5279312133789062} 08/30/2021 14:35:53 - INFO - __main__ - Step 7935: {'lr': 0.0004980193528164806, 'samples': 1523520, 'steps': 7934, 'loss/train': 1.7118288278579712} 08/30/2021 14:35:53 - INFO - __main__ - Step 7936: {'lr': 0.0004980186860845939, 'samples': 1523712, 'steps': 7935, 'loss/train': 1.9207849502563477} 08/30/2021 14:35:53 - INFO - __main__ - Step 7937: {'lr': 0.0004980180192409539, 'samples': 1523904, 'steps': 7936, 'loss/train': 1.6872050762176514} 08/30/2021 14:35:54 - INFO - __main__ - Step 7938: {'lr': 0.0004980173522855608, 'samples': 1524096, 'steps': 7937, 'loss/train': 2.444744825363159} 08/30/2021 14:35:55 - INFO - __main__ - Step 7939: {'lr': 0.0004980166852184148, 'samples': 1524288, 'steps': 7938, 'loss/train': 1.7128517627716064} 08/30/2021 14:35:56 - INFO - __main__ - Step 7940: {'lr': 0.0004980160180395164, 'samples': 1524480, 'steps': 7939, 'loss/train': 1.9546692371368408} 08/30/2021 14:35:56 - INFO - __main__ - Step 7941: {'lr': 0.0004980153507488657, 'samples': 1524672, 'steps': 7940, 'loss/train': 2.101292133331299} 08/30/2021 14:35:56 - INFO - __main__ - Step 7942: {'lr': 0.0004980146833464633, 'samples': 1524864, 'steps': 7941, 'loss/train': 2.1375372409820557} 08/30/2021 14:35:57 - INFO - __main__ - Step 7943: {'lr': 0.0004980140158323092, 'samples': 1525056, 'steps': 7942, 'loss/train': 2.116997003555298} 08/30/2021 14:35:58 - INFO - __main__ - Step 7944: {'lr': 0.0004980133482064038, 'samples': 1525248, 'steps': 7943, 'loss/train': 2.504096508026123} 08/30/2021 14:35:59 - INFO - __main__ - Step 7945: {'lr': 0.0004980126804687474, 'samples': 1525440, 'steps': 7944, 'loss/train': 1.845743179321289} 08/30/2021 14:35:59 - INFO - __main__ - Step 7946: {'lr': 0.0004980120126193403, 'samples': 1525632, 'steps': 7945, 'loss/train': 0.4973115622997284} 08/30/2021 14:35:59 - INFO - __main__ - Step 7947: {'lr': 0.0004980113446581829, 'samples': 1525824, 'steps': 7946, 'loss/train': 1.9411251544952393} 08/30/2021 14:36:00 - INFO - __main__ - Step 7948: {'lr': 0.0004980106765852753, 'samples': 1526016, 'steps': 7947, 'loss/train': 2.3189473152160645} 08/30/2021 14:36:01 - INFO - __main__ - Step 7949: {'lr': 0.0004980100084006181, 'samples': 1526208, 'steps': 7948, 'loss/train': 1.9953863620758057} 08/30/2021 14:36:02 - INFO - __main__ - Step 7950: {'lr': 0.0004980093401042113, 'samples': 1526400, 'steps': 7949, 'loss/train': 2.287334442138672} 08/30/2021 14:36:02 - INFO - __main__ - Step 7951: {'lr': 0.0004980086716960552, 'samples': 1526592, 'steps': 7950, 'loss/train': 0.17116063833236694} 08/30/2021 14:36:02 - INFO - __main__ - Step 7952: {'lr': 0.0004980080031761504, 'samples': 1526784, 'steps': 7951, 'loss/train': 1.6895288228988647} 08/30/2021 14:36:03 - INFO - __main__ - Step 7953: {'lr': 0.000498007334544497, 'samples': 1526976, 'steps': 7952, 'loss/train': 1.9028524160385132} 08/30/2021 14:36:04 - INFO - __main__ - Step 7954: {'lr': 0.0004980066658010952, 'samples': 1527168, 'steps': 7953, 'loss/train': 2.0068423748016357} 08/30/2021 14:36:05 - INFO - __main__ - Step 7955: {'lr': 0.0004980059969459455, 'samples': 1527360, 'steps': 7954, 'loss/train': 2.3404934406280518} 08/30/2021 14:36:05 - INFO - __main__ - Step 7956: {'lr': 0.0004980053279790481, 'samples': 1527552, 'steps': 7955, 'loss/train': 1.9536232948303223} 08/30/2021 14:36:05 - INFO - __main__ - Step 7957: {'lr': 0.0004980046589004034, 'samples': 1527744, 'steps': 7956, 'loss/train': 0.4819597005844116} 08/30/2021 14:36:06 - INFO - __main__ - Step 7958: {'lr': 0.0004980039897100115, 'samples': 1527936, 'steps': 7957, 'loss/train': 2.34667706489563} 08/30/2021 14:36:06 - INFO - __main__ - Step 7959: {'lr': 0.000498003320407873, 'samples': 1528128, 'steps': 7958, 'loss/train': 1.59219491481781} 08/30/2021 14:36:08 - INFO - __main__ - Step 7960: {'lr': 0.000498002650993988, 'samples': 1528320, 'steps': 7959, 'loss/train': 1.3361490964889526} 08/30/2021 14:36:08 - INFO - __main__ - Step 7961: {'lr': 0.0004980019814683568, 'samples': 1528512, 'steps': 7960, 'loss/train': 1.800642967224121} 08/30/2021 14:36:09 - INFO - __main__ - Step 7962: {'lr': 0.0004980013118309796, 'samples': 1528704, 'steps': 7961, 'loss/train': 1.2711882591247559} 08/30/2021 14:36:09 - INFO - __main__ - Step 7963: {'lr': 0.000498000642081857, 'samples': 1528896, 'steps': 7962, 'loss/train': 2.0844485759735107} 08/30/2021 14:36:10 - INFO - __main__ - Step 7964: {'lr': 0.0004979999722209891, 'samples': 1529088, 'steps': 7963, 'loss/train': 3.0170657634735107} 08/30/2021 14:36:11 - INFO - __main__ - Step 7965: {'lr': 0.0004979993022483762, 'samples': 1529280, 'steps': 7964, 'loss/train': 2.1732215881347656} 08/30/2021 14:36:11 - INFO - __main__ - Step 7966: {'lr': 0.0004979986321640187, 'samples': 1529472, 'steps': 7965, 'loss/train': 1.7630354166030884} 08/30/2021 14:36:12 - INFO - __main__ - Step 7967: {'lr': 0.0004979979619679168, 'samples': 1529664, 'steps': 7966, 'loss/train': 2.0841562747955322} 08/30/2021 14:36:12 - INFO - __main__ - Step 7968: {'lr': 0.0004979972916600708, 'samples': 1529856, 'steps': 7967, 'loss/train': 1.6400091648101807} 08/30/2021 14:36:12 - INFO - __main__ - Step 7969: {'lr': 0.0004979966212404812, 'samples': 1530048, 'steps': 7968, 'loss/train': 1.864302158355713} 08/30/2021 14:36:14 - INFO - __main__ - Step 7970: {'lr': 0.0004979959507091479, 'samples': 1530240, 'steps': 7969, 'loss/train': 1.8296929597854614} 08/30/2021 14:36:15 - INFO - __main__ - Step 7971: {'lr': 0.0004979952800660717, 'samples': 1530432, 'steps': 7970, 'loss/train': 2.113858461380005} 08/30/2021 14:36:15 - INFO - __main__ - Step 7972: {'lr': 0.0004979946093112525, 'samples': 1530624, 'steps': 7971, 'loss/train': 1.1817271709442139} 08/30/2021 14:36:16 - INFO - __main__ - Step 7973: {'lr': 0.0004979939384446908, 'samples': 1530816, 'steps': 7972, 'loss/train': 1.7022167444229126} 08/30/2021 14:36:16 - INFO - __main__ - Step 7974: {'lr': 0.0004979932674663869, 'samples': 1531008, 'steps': 7973, 'loss/train': 2.165408134460449} 08/30/2021 14:36:18 - INFO - __main__ - Step 7975: {'lr': 0.000497992596376341, 'samples': 1531200, 'steps': 7974, 'loss/train': 2.0156679153442383} 08/30/2021 14:36:18 - INFO - __main__ - Step 7976: {'lr': 0.0004979919251745535, 'samples': 1531392, 'steps': 7975, 'loss/train': 2.6220502853393555} 08/30/2021 14:36:18 - INFO - __main__ - Step 7977: {'lr': 0.0004979912538610247, 'samples': 1531584, 'steps': 7976, 'loss/train': 1.8627681732177734} 08/30/2021 14:36:19 - INFO - __main__ - Step 7978: {'lr': 0.0004979905824357548, 'samples': 1531776, 'steps': 7977, 'loss/train': 1.6736421585083008} 08/30/2021 14:36:19 - INFO - __main__ - Step 7979: {'lr': 0.0004979899108987442, 'samples': 1531968, 'steps': 7978, 'loss/train': 2.027559995651245} 08/30/2021 14:36:21 - INFO - __main__ - Step 7980: {'lr': 0.0004979892392499932, 'samples': 1532160, 'steps': 7979, 'loss/train': 2.053459644317627} 08/30/2021 14:36:21 - INFO - __main__ - Step 7981: {'lr': 0.0004979885674895021, 'samples': 1532352, 'steps': 7980, 'loss/train': 2.142665386199951} 08/30/2021 14:36:22 - INFO - __main__ - Step 7982: {'lr': 0.0004979878956172711, 'samples': 1532544, 'steps': 7981, 'loss/train': 2.910045623779297} 08/30/2021 14:36:22 - INFO - __main__ - Step 7983: {'lr': 0.0004979872236333005, 'samples': 1532736, 'steps': 7982, 'loss/train': 2.21919846534729} 08/30/2021 14:36:22 - INFO - __main__ - Step 7984: {'lr': 0.0004979865515375908, 'samples': 1532928, 'steps': 7983, 'loss/train': 0.5169633030891418} 08/30/2021 14:36:23 - INFO - __main__ - Step 7985: {'lr': 0.0004979858793301422, 'samples': 1533120, 'steps': 7984, 'loss/train': 1.3447307348251343} 08/30/2021 14:36:24 - INFO - __main__ - Step 7986: {'lr': 0.000497985207010955, 'samples': 1533312, 'steps': 7985, 'loss/train': 1.9778574705123901} 08/30/2021 14:36:25 - INFO - __main__ - Step 7987: {'lr': 0.0004979845345800294, 'samples': 1533504, 'steps': 7986, 'loss/train': 3.0037994384765625} 08/30/2021 14:36:25 - INFO - __main__ - Step 7988: {'lr': 0.0004979838620373659, 'samples': 1533696, 'steps': 7987, 'loss/train': 0.644941508769989} 08/30/2021 14:36:25 - INFO - __main__ - Step 7989: {'lr': 0.0004979831893829646, 'samples': 1533888, 'steps': 7988, 'loss/train': 1.3515015840530396} 08/30/2021 14:36:26 - INFO - __main__ - Step 7990: {'lr': 0.0004979825166168259, 'samples': 1534080, 'steps': 7989, 'loss/train': 1.641153335571289} 08/30/2021 14:36:27 - INFO - __main__ - Step 7991: {'lr': 0.0004979818437389502, 'samples': 1534272, 'steps': 7990, 'loss/train': 1.7243032455444336} 08/30/2021 14:36:28 - INFO - __main__ - Step 7992: {'lr': 0.0004979811707493377, 'samples': 1534464, 'steps': 7991, 'loss/train': 2.0713040828704834} 08/30/2021 14:36:28 - INFO - __main__ - Step 7993: {'lr': 0.0004979804976479887, 'samples': 1534656, 'steps': 7992, 'loss/train': 1.9589450359344482} 08/30/2021 14:36:28 - INFO - __main__ - Step 7994: {'lr': 0.0004979798244349034, 'samples': 1534848, 'steps': 7993, 'loss/train': 2.1670055389404297} 08/30/2021 14:36:29 - INFO - __main__ - Step 7995: {'lr': 0.0004979791511100823, 'samples': 1535040, 'steps': 7994, 'loss/train': 2.0286285877227783} 08/30/2021 14:36:31 - INFO - __main__ - Step 7996: {'lr': 0.0004979784776735257, 'samples': 1535232, 'steps': 7995, 'loss/train': 1.703765869140625} 08/30/2021 14:36:31 - INFO - __main__ - Step 7997: {'lr': 0.0004979778041252338, 'samples': 1535424, 'steps': 7996, 'loss/train': 1.8905060291290283} 08/30/2021 14:36:31 - INFO - __main__ - Step 7998: {'lr': 0.0004979771304652068, 'samples': 1535616, 'steps': 7997, 'loss/train': 0.36253124475479126} 08/30/2021 14:36:32 - INFO - __main__ - Step 7999: {'lr': 0.0004979764566934452, 'samples': 1535808, 'steps': 7998, 'loss/train': 1.8920336961746216} 08/30/2021 14:36:32 - INFO - __main__ - Step 8000: {'lr': 0.0004979757828099492, 'samples': 1536000, 'steps': 7999, 'loss/train': 4.387569427490234} 08/30/2021 14:36:32 - INFO - __main__ - Step 8001: {'lr': 0.0004979751088147192, 'samples': 1536192, 'steps': 8000, 'loss/train': 1.4285427331924438} 08/30/2021 14:36:34 - INFO - __main__ - Step 8002: {'lr': 0.0004979744347077555, 'samples': 1536384, 'steps': 8001, 'loss/train': 2.4966976642608643} 08/30/2021 14:36:34 - INFO - __main__ - Step 8003: {'lr': 0.0004979737604890582, 'samples': 1536576, 'steps': 8002, 'loss/train': 1.9589344263076782} 08/30/2021 14:36:35 - INFO - __main__ - Step 8004: {'lr': 0.0004979730861586278, 'samples': 1536768, 'steps': 8003, 'loss/train': 1.8467297554016113} 08/30/2021 14:36:35 - INFO - __main__ - Step 8005: {'lr': 0.0004979724117164646, 'samples': 1536960, 'steps': 8004, 'loss/train': 2.14319109916687} 08/30/2021 14:36:35 - INFO - __main__ - Step 8006: {'lr': 0.0004979717371625689, 'samples': 1537152, 'steps': 8005, 'loss/train': 2.146137237548828} 08/30/2021 14:36:37 - INFO - __main__ - Step 8007: {'lr': 0.0004979710624969408, 'samples': 1537344, 'steps': 8006, 'loss/train': 2.2626583576202393} 08/30/2021 14:36:37 - INFO - __main__ - Step 8008: {'lr': 0.000497970387719581, 'samples': 1537536, 'steps': 8007, 'loss/train': 1.4100250005722046} 08/30/2021 14:36:38 - INFO - __main__ - Step 8009: {'lr': 0.0004979697128304893, 'samples': 1537728, 'steps': 8008, 'loss/train': 1.6080433130264282} 08/30/2021 14:36:38 - INFO - __main__ - Step 8010: {'lr': 0.0004979690378296665, 'samples': 1537920, 'steps': 8009, 'loss/train': 1.759553074836731} 08/30/2021 14:36:38 - INFO - __main__ - Step 8011: {'lr': 0.0004979683627171125, 'samples': 1538112, 'steps': 8010, 'loss/train': 2.5464515686035156} 08/30/2021 14:36:40 - INFO - __main__ - Step 8012: {'lr': 0.0004979676874928278, 'samples': 1538304, 'steps': 8011, 'loss/train': 1.9359408617019653} 08/30/2021 14:36:41 - INFO - __main__ - Step 8013: {'lr': 0.0004979670121568129, 'samples': 1538496, 'steps': 8012, 'loss/train': 1.395814061164856} 08/30/2021 14:36:41 - INFO - __main__ - Step 8014: {'lr': 0.0004979663367090676, 'samples': 1538688, 'steps': 8013, 'loss/train': 1.2997294664382935} 08/30/2021 14:36:41 - INFO - __main__ - Step 8015: {'lr': 0.0004979656611495927, 'samples': 1538880, 'steps': 8014, 'loss/train': 1.9417048692703247} 08/30/2021 14:36:42 - INFO - __main__ - Step 8016: {'lr': 0.0004979649854783883, 'samples': 1539072, 'steps': 8015, 'loss/train': 3.8958165645599365} 08/30/2021 14:36:43 - INFO - __main__ - Step 8017: {'lr': 0.0004979643096954545, 'samples': 1539264, 'steps': 8016, 'loss/train': 2.0222980976104736} 08/30/2021 14:36:44 - INFO - __main__ - Step 8018: {'lr': 0.000497963633800792, 'samples': 1539456, 'steps': 8017, 'loss/train': 0.9974882006645203} 08/30/2021 14:36:44 - INFO - __main__ - Step 8019: {'lr': 0.0004979629577944009, 'samples': 1539648, 'steps': 8018, 'loss/train': 1.9589250087738037} 08/30/2021 14:36:44 - INFO - __main__ - Step 8020: {'lr': 0.0004979622816762815, 'samples': 1539840, 'steps': 8019, 'loss/train': 1.955483317375183} 08/30/2021 14:36:45 - INFO - __main__ - Step 8021: {'lr': 0.0004979616054464341, 'samples': 1540032, 'steps': 8020, 'loss/train': 1.9251713752746582} 08/30/2021 14:36:47 - INFO - __main__ - Step 8022: {'lr': 0.000497960929104859, 'samples': 1540224, 'steps': 8021, 'loss/train': 0.7427318096160889} 08/30/2021 14:36:47 - INFO - __main__ - Step 8023: {'lr': 0.0004979602526515566, 'samples': 1540416, 'steps': 8022, 'loss/train': 1.4187557697296143} 08/30/2021 14:36:48 - INFO - __main__ - Step 8024: {'lr': 0.0004979595760865271, 'samples': 1540608, 'steps': 8023, 'loss/train': 2.1171064376831055} 08/30/2021 14:36:48 - INFO - __main__ - Step 8025: {'lr': 0.0004979588994097708, 'samples': 1540800, 'steps': 8024, 'loss/train': 3.3683278560638428} 08/30/2021 14:36:48 - INFO - __main__ - Step 8026: {'lr': 0.0004979582226212881, 'samples': 1540992, 'steps': 8025, 'loss/train': 2.1514739990234375} 08/30/2021 14:36:50 - INFO - __main__ - Step 8027: {'lr': 0.0004979575457210792, 'samples': 1541184, 'steps': 8026, 'loss/train': 1.720782995223999} 08/30/2021 14:36:50 - INFO - __main__ - Step 8028: {'lr': 0.0004979568687091446, 'samples': 1541376, 'steps': 8027, 'loss/train': 2.471392869949341} 08/30/2021 14:36:51 - INFO - __main__ - Step 8029: {'lr': 0.0004979561915854843, 'samples': 1541568, 'steps': 8028, 'loss/train': 1.839748740196228} 08/30/2021 14:36:51 - INFO - __main__ - Step 8030: {'lr': 0.0004979555143500988, 'samples': 1541760, 'steps': 8029, 'loss/train': 1.1976137161254883} 08/30/2021 14:36:51 - INFO - __main__ - Step 8031: {'lr': 0.0004979548370029884, 'samples': 1541952, 'steps': 8030, 'loss/train': 2.1068124771118164} 08/30/2021 14:36:53 - INFO - __main__ - Step 8032: {'lr': 0.0004979541595441534, 'samples': 1542144, 'steps': 8031, 'loss/train': 1.758437156677246} 08/30/2021 14:36:53 - INFO - __main__ - Step 8033: {'lr': 0.000497953481973594, 'samples': 1542336, 'steps': 8032, 'loss/train': 1.7716573476791382} 08/30/2021 14:36:54 - INFO - __main__ - Step 8034: {'lr': 0.0004979528042913106, 'samples': 1542528, 'steps': 8033, 'loss/train': 2.0524511337280273} 08/30/2021 14:36:54 - INFO - __main__ - Step 8035: {'lr': 0.0004979521264973036, 'samples': 1542720, 'steps': 8034, 'loss/train': 1.1920688152313232} 08/30/2021 14:36:54 - INFO - __main__ - Step 8036: {'lr': 0.0004979514485915731, 'samples': 1542912, 'steps': 8035, 'loss/train': 2.018043041229248} 08/30/2021 14:36:55 - INFO - __main__ - Step 8037: {'lr': 0.0004979507705741195, 'samples': 1543104, 'steps': 8036, 'loss/train': 2.270192861557007} 08/30/2021 14:36:56 - INFO - __main__ - Step 8038: {'lr': 0.0004979500924449431, 'samples': 1543296, 'steps': 8037, 'loss/train': 1.5486962795257568} 08/30/2021 14:36:57 - INFO - __main__ - Step 8039: {'lr': 0.0004979494142040444, 'samples': 1543488, 'steps': 8038, 'loss/train': 1.6932404041290283} 08/30/2021 14:36:57 - INFO - __main__ - Step 8040: {'lr': 0.0004979487358514233, 'samples': 1543680, 'steps': 8039, 'loss/train': 1.8105981349945068} 08/30/2021 14:36:57 - INFO - __main__ - Step 8041: {'lr': 0.0004979480573870803, 'samples': 1543872, 'steps': 8040, 'loss/train': 2.0685484409332275} 08/30/2021 14:36:58 - INFO - __main__ - Step 8042: {'lr': 0.000497947378811016, 'samples': 1544064, 'steps': 8041, 'loss/train': 1.8281188011169434} 08/30/2021 14:36:59 - INFO - __main__ - Step 8043: {'lr': 0.0004979467001232302, 'samples': 1544256, 'steps': 8042, 'loss/train': 1.946904182434082} 08/30/2021 14:37:00 - INFO - __main__ - Step 8044: {'lr': 0.0004979460213237235, 'samples': 1544448, 'steps': 8043, 'loss/train': 2.2791924476623535} 08/30/2021 14:37:00 - INFO - __main__ - Step 8045: {'lr': 0.0004979453424124961, 'samples': 1544640, 'steps': 8044, 'loss/train': 2.8117494583129883} 08/30/2021 14:37:00 - INFO - __main__ - Step 8046: {'lr': 0.0004979446633895484, 'samples': 1544832, 'steps': 8045, 'loss/train': 1.5231140851974487} 08/30/2021 14:37:01 - INFO - __main__ - Step 8047: {'lr': 0.0004979439842548808, 'samples': 1545024, 'steps': 8046, 'loss/train': 2.0871026515960693} 08/30/2021 14:37:03 - INFO - __main__ - Step 8048: {'lr': 0.0004979433050084933, 'samples': 1545216, 'steps': 8047, 'loss/train': 1.9119102954864502} 08/30/2021 14:37:03 - INFO - __main__ - Step 8049: {'lr': 0.0004979426256503863, 'samples': 1545408, 'steps': 8048, 'loss/train': 2.0319998264312744} 08/30/2021 14:37:03 - INFO - __main__ - Step 8050: {'lr': 0.0004979419461805603, 'samples': 1545600, 'steps': 8049, 'loss/train': 2.023425817489624} 08/30/2021 14:37:04 - INFO - __main__ - Step 8051: {'lr': 0.0004979412665990156, 'samples': 1545792, 'steps': 8050, 'loss/train': 0.29502061009407043} 08/30/2021 14:37:04 - INFO - __main__ - Step 8052: {'lr': 0.0004979405869057522, 'samples': 1545984, 'steps': 8051, 'loss/train': 1.7866392135620117} 08/30/2021 14:37:06 - INFO - __main__ - Step 8053: {'lr': 0.0004979399071007707, 'samples': 1546176, 'steps': 8052, 'loss/train': 2.1674277782440186} 08/30/2021 14:37:06 - INFO - __main__ - Step 8054: {'lr': 0.0004979392271840712, 'samples': 1546368, 'steps': 8053, 'loss/train': 2.000279664993286} 08/30/2021 14:37:06 - INFO - __main__ - Step 8055: {'lr': 0.0004979385471556542, 'samples': 1546560, 'steps': 8054, 'loss/train': 1.5608389377593994} 08/30/2021 14:37:07 - INFO - __main__ - Step 8056: {'lr': 0.00049793786701552, 'samples': 1546752, 'steps': 8055, 'loss/train': 1.789946436882019} 08/30/2021 14:37:07 - INFO - __main__ - Step 8057: {'lr': 0.0004979371867636687, 'samples': 1546944, 'steps': 8056, 'loss/train': 1.7204139232635498} 08/30/2021 14:37:07 - INFO - __main__ - Step 8058: {'lr': 0.0004979365064001007, 'samples': 1547136, 'steps': 8057, 'loss/train': 1.940467357635498} 08/30/2021 14:37:09 - INFO - __main__ - Step 8059: {'lr': 0.0004979358259248164, 'samples': 1547328, 'steps': 8058, 'loss/train': 1.6927646398544312} 08/30/2021 14:37:09 - INFO - __main__ - Step 8060: {'lr': 0.000497935145337816, 'samples': 1547520, 'steps': 8059, 'loss/train': 2.008763313293457} 08/30/2021 14:37:10 - INFO - __main__ - Step 8061: {'lr': 0.0004979344646390999, 'samples': 1547712, 'steps': 8060, 'loss/train': 1.753297209739685} 08/30/2021 14:37:10 - INFO - __main__ - Step 8062: {'lr': 0.0004979337838286684, 'samples': 1547904, 'steps': 8061, 'loss/train': 2.1832754611968994} 08/30/2021 14:37:10 - INFO - __main__ - Step 8063: {'lr': 0.0004979331029065216, 'samples': 1548096, 'steps': 8062, 'loss/train': 1.679816484451294} 08/30/2021 14:37:12 - INFO - __main__ - Step 8064: {'lr': 0.00049793242187266, 'samples': 1548288, 'steps': 8063, 'loss/train': 2.2498199939727783} 08/30/2021 14:37:12 - INFO - __main__ - Step 8065: {'lr': 0.000497931740727084, 'samples': 1548480, 'steps': 8064, 'loss/train': 1.5963996648788452} 08/30/2021 14:37:13 - INFO - __main__ - Step 8066: {'lr': 0.0004979310594697937, 'samples': 1548672, 'steps': 8065, 'loss/train': 1.532086730003357} 08/30/2021 14:37:13 - INFO - __main__ - Step 8067: {'lr': 0.0004979303781007896, 'samples': 1548864, 'steps': 8066, 'loss/train': 1.1951234340667725} 08/30/2021 14:37:13 - INFO - __main__ - Step 8068: {'lr': 0.0004979296966200718, 'samples': 1549056, 'steps': 8067, 'loss/train': 1.3954778909683228} 08/30/2021 14:37:15 - INFO - __main__ - Step 8069: {'lr': 0.0004979290150276407, 'samples': 1549248, 'steps': 8068, 'loss/train': 2.2659614086151123} 08/30/2021 14:37:15 - INFO - __main__ - Step 8070: {'lr': 0.0004979283333234966, 'samples': 1549440, 'steps': 8069, 'loss/train': 1.849366307258606} 08/30/2021 14:37:16 - INFO - __main__ - Step 8071: {'lr': 0.0004979276515076399, 'samples': 1549632, 'steps': 8070, 'loss/train': 2.1270198822021484} 08/30/2021 14:37:16 - INFO - __main__ - Step 8072: {'lr': 0.0004979269695800707, 'samples': 1549824, 'steps': 8071, 'loss/train': 0.9996500611305237} 08/30/2021 14:37:16 - INFO - __main__ - Step 8073: {'lr': 0.0004979262875407896, 'samples': 1550016, 'steps': 8072, 'loss/train': 1.990217685699463} 08/30/2021 14:37:18 - INFO - __main__ - Step 8074: {'lr': 0.0004979256053897966, 'samples': 1550208, 'steps': 8073, 'loss/train': 2.1046195030212402} 08/30/2021 14:37:19 - INFO - __main__ - Step 8075: {'lr': 0.0004979249231270923, 'samples': 1550400, 'steps': 8074, 'loss/train': 2.477461338043213} 08/30/2021 14:37:19 - INFO - __main__ - Step 8076: {'lr': 0.0004979242407526766, 'samples': 1550592, 'steps': 8075, 'loss/train': 1.9458473920822144} 08/30/2021 14:37:19 - INFO - __main__ - Step 8077: {'lr': 0.0004979235582665503, 'samples': 1550784, 'steps': 8076, 'loss/train': 0.31497299671173096} 08/30/2021 14:37:20 - INFO - __main__ - Step 8078: {'lr': 0.0004979228756687135, 'samples': 1550976, 'steps': 8077, 'loss/train': 1.9776636362075806} 08/30/2021 14:37:20 - INFO - __main__ - Step 8079: {'lr': 0.0004979221929591663, 'samples': 1551168, 'steps': 8078, 'loss/train': 1.7904404401779175} 08/30/2021 14:37:22 - INFO - __main__ - Step 8080: {'lr': 0.0004979215101379093, 'samples': 1551360, 'steps': 8079, 'loss/train': 1.9985524415969849} 08/30/2021 14:37:23 - INFO - __main__ - Step 8081: {'lr': 0.0004979208272049426, 'samples': 1551552, 'steps': 8080, 'loss/train': 1.1416809558868408} 08/30/2021 14:37:23 - INFO - __main__ - Step 8082: {'lr': 0.0004979201441602665, 'samples': 1551744, 'steps': 8081, 'loss/train': 1.9365806579589844} 08/30/2021 14:37:23 - INFO - __main__ - Step 8083: {'lr': 0.0004979194610038816, 'samples': 1551936, 'steps': 8082, 'loss/train': 2.0888302326202393} 08/30/2021 14:37:24 - INFO - __main__ - Step 8084: {'lr': 0.000497918777735788, 'samples': 1552128, 'steps': 8083, 'loss/train': 1.875905156135559} 08/30/2021 14:37:25 - INFO - __main__ - Step 8085: {'lr': 0.000497918094355986, 'samples': 1552320, 'steps': 8084, 'loss/train': 1.9774138927459717} 08/30/2021 14:37:26 - INFO - __main__ - Step 8086: {'lr': 0.000497917410864476, 'samples': 1552512, 'steps': 8085, 'loss/train': 1.722417950630188} 08/30/2021 14:37:26 - INFO - __main__ - Step 8087: {'lr': 0.0004979167272612581, 'samples': 1552704, 'steps': 8086, 'loss/train': 1.8413053750991821} 08/30/2021 14:37:26 - INFO - __main__ - Step 8088: {'lr': 0.0004979160435463328, 'samples': 1552896, 'steps': 8087, 'loss/train': 1.4524587392807007} 08/30/2021 14:37:27 - INFO - __main__ - Step 8089: {'lr': 0.0004979153597197003, 'samples': 1553088, 'steps': 8088, 'loss/train': 2.0809855461120605} 08/30/2021 14:37:28 - INFO - __main__ - Step 8090: {'lr': 0.0004979146757813611, 'samples': 1553280, 'steps': 8089, 'loss/train': 1.5562987327575684} 08/30/2021 14:37:29 - INFO - __main__ - Step 8091: {'lr': 0.0004979139917313153, 'samples': 1553472, 'steps': 8090, 'loss/train': 2.171715497970581} 08/30/2021 14:37:29 - INFO - __main__ - Step 8092: {'lr': 0.0004979133075695634, 'samples': 1553664, 'steps': 8091, 'loss/train': 1.915298342704773} 08/30/2021 14:37:29 - INFO - __main__ - Step 8093: {'lr': 0.0004979126232961054, 'samples': 1553856, 'steps': 8092, 'loss/train': 1.7592092752456665} 08/30/2021 14:37:30 - INFO - __main__ - Step 8094: {'lr': 0.0004979119389109419, 'samples': 1554048, 'steps': 8093, 'loss/train': 1.0209548473358154} 08/30/2021 14:37:32 - INFO - __main__ - Step 8095: {'lr': 0.000497911254414073, 'samples': 1554240, 'steps': 8094, 'loss/train': 1.552551031112671} 08/30/2021 14:37:32 - INFO - __main__ - Step 8096: {'lr': 0.0004979105698054992, 'samples': 1554432, 'steps': 8095, 'loss/train': 2.2468039989471436} 08/30/2021 14:37:32 - INFO - __main__ - Step 8097: {'lr': 0.0004979098850852208, 'samples': 1554624, 'steps': 8096, 'loss/train': 1.9784367084503174} 08/30/2021 14:37:33 - INFO - __main__ - Step 8098: {'lr': 0.0004979092002532379, 'samples': 1554816, 'steps': 8097, 'loss/train': 2.148533821105957} 08/30/2021 14:37:33 - INFO - __main__ - Step 8099: {'lr': 0.0004979085153095509, 'samples': 1555008, 'steps': 8098, 'loss/train': 1.7559521198272705} 08/30/2021 14:37:34 - INFO - __main__ - Step 8100: {'lr': 0.0004979078302541604, 'samples': 1555200, 'steps': 8099, 'loss/train': 2.5532238483428955} 08/30/2021 14:37:35 - INFO - __main__ - Step 8101: {'lr': 0.0004979071450870662, 'samples': 1555392, 'steps': 8100, 'loss/train': 1.8217830657958984} 08/30/2021 14:37:35 - INFO - __main__ - Step 8102: {'lr': 0.0004979064598082689, 'samples': 1555584, 'steps': 8101, 'loss/train': 1.4963428974151611} 08/30/2021 14:37:36 - INFO - __main__ - Step 8103: {'lr': 0.0004979057744177689, 'samples': 1555776, 'steps': 8102, 'loss/train': 1.7607156038284302} 08/30/2021 14:37:36 - INFO - __main__ - Step 8104: {'lr': 0.0004979050889155663, 'samples': 1555968, 'steps': 8103, 'loss/train': 2.1021783351898193} 08/30/2021 14:37:37 - INFO - __main__ - Step 8105: {'lr': 0.0004979044033016616, 'samples': 1556160, 'steps': 8104, 'loss/train': 2.1359758377075195} 08/30/2021 14:37:38 - INFO - __main__ - Step 8106: {'lr': 0.0004979037175760548, 'samples': 1556352, 'steps': 8105, 'loss/train': 1.453436017036438} 08/30/2021 14:37:38 - INFO - __main__ - Step 8107: {'lr': 0.0004979030317387466, 'samples': 1556544, 'steps': 8106, 'loss/train': 2.0098989009857178} 08/30/2021 14:37:39 - INFO - __main__ - Step 8108: {'lr': 0.0004979023457897371, 'samples': 1556736, 'steps': 8107, 'loss/train': 2.1559696197509766} 08/30/2021 14:37:39 - INFO - __main__ - Step 8109: {'lr': 0.0004979016597290264, 'samples': 1556928, 'steps': 8108, 'loss/train': 6.67866849899292} 08/30/2021 14:37:40 - INFO - __main__ - Step 8110: {'lr': 0.0004979009735566152, 'samples': 1557120, 'steps': 8109, 'loss/train': 1.5541415214538574} 08/30/2021 14:37:40 - INFO - __main__ - Step 8111: {'lr': 0.0004979002872725037, 'samples': 1557312, 'steps': 8110, 'loss/train': 1.5444889068603516} 08/30/2021 14:37:41 - INFO - __main__ - Step 8112: {'lr': 0.0004978996008766922, 'samples': 1557504, 'steps': 8111, 'loss/train': 1.3902102708816528} 08/30/2021 14:37:42 - INFO - __main__ - Step 8113: {'lr': 0.0004978989143691808, 'samples': 1557696, 'steps': 8112, 'loss/train': 1.7067283391952515} 08/30/2021 14:37:42 - INFO - __main__ - Step 8114: {'lr': 0.00049789822774997, 'samples': 1557888, 'steps': 8113, 'loss/train': 2.329395055770874} 08/30/2021 14:37:43 - INFO - __main__ - Step 8115: {'lr': 0.0004978975410190601, 'samples': 1558080, 'steps': 8114, 'loss/train': 1.9429705142974854} 08/30/2021 14:37:43 - INFO - __main__ - Step 8116: {'lr': 0.0004978968541764515, 'samples': 1558272, 'steps': 8115, 'loss/train': 2.8889026641845703} 08/30/2021 14:37:44 - INFO - __main__ - Step 8117: {'lr': 0.0004978961672221444, 'samples': 1558464, 'steps': 8116, 'loss/train': 2.5362284183502197} 08/30/2021 14:37:45 - INFO - __main__ - Step 8118: {'lr': 0.000497895480156139, 'samples': 1558656, 'steps': 8117, 'loss/train': 2.1038477420806885} 08/30/2021 14:37:45 - INFO - __main__ - Step 8119: {'lr': 0.0004978947929784358, 'samples': 1558848, 'steps': 8118, 'loss/train': 2.1302146911621094} 08/30/2021 14:37:46 - INFO - __main__ - Step 8120: {'lr': 0.0004978941056890349, 'samples': 1559040, 'steps': 8119, 'loss/train': 1.6071606874465942} 08/30/2021 14:37:46 - INFO - __main__ - Step 8121: {'lr': 0.0004978934182879369, 'samples': 1559232, 'steps': 8120, 'loss/train': 1.5273759365081787} 08/30/2021 14:37:48 - INFO - __main__ - Step 8122: {'lr': 0.0004978927307751419, 'samples': 1559424, 'steps': 8121, 'loss/train': 2.2686712741851807} 08/30/2021 14:37:48 - INFO - __main__ - Step 8123: {'lr': 0.0004978920431506501, 'samples': 1559616, 'steps': 8122, 'loss/train': 2.2746353149414062} 08/30/2021 14:37:48 - INFO - __main__ - Step 8124: {'lr': 0.0004978913554144623, 'samples': 1559808, 'steps': 8123, 'loss/train': 1.6839054822921753} 08/30/2021 14:37:49 - INFO - __main__ - Step 8125: {'lr': 0.0004978906675665782, 'samples': 1560000, 'steps': 8124, 'loss/train': 2.4230728149414062} 08/30/2021 14:37:49 - INFO - __main__ - Step 8126: {'lr': 0.0004978899796069985, 'samples': 1560192, 'steps': 8125, 'loss/train': 0.9257344007492065} 08/30/2021 14:37:51 - INFO - __main__ - Step 8127: {'lr': 0.0004978892915357234, 'samples': 1560384, 'steps': 8126, 'loss/train': 1.9891599416732788} 08/30/2021 14:37:51 - INFO - __main__ - Step 8128: {'lr': 0.0004978886033527532, 'samples': 1560576, 'steps': 8127, 'loss/train': 1.9861290454864502} 08/30/2021 14:37:51 - INFO - __main__ - Step 8129: {'lr': 0.0004978879150580882, 'samples': 1560768, 'steps': 8128, 'loss/train': 1.973615288734436} 08/30/2021 14:37:52 - INFO - __main__ - Step 8130: {'lr': 0.0004978872266517288, 'samples': 1560960, 'steps': 8129, 'loss/train': 1.6166166067123413} 08/30/2021 14:37:52 - INFO - __main__ - Step 8131: {'lr': 0.0004978865381336752, 'samples': 1561152, 'steps': 8130, 'loss/train': 2.2141826152801514} 08/30/2021 14:37:54 - INFO - __main__ - Step 8132: {'lr': 0.0004978858495039277, 'samples': 1561344, 'steps': 8131, 'loss/train': 1.6094841957092285} 08/30/2021 14:37:55 - INFO - __main__ - Step 8133: {'lr': 0.0004978851607624867, 'samples': 1561536, 'steps': 8132, 'loss/train': 1.0781852006912231} 08/30/2021 14:37:55 - INFO - __main__ - Step 8134: {'lr': 0.0004978844719093525, 'samples': 1561728, 'steps': 8133, 'loss/train': 2.2774407863616943} 08/30/2021 14:37:55 - INFO - __main__ - Step 8135: {'lr': 0.0004978837829445254, 'samples': 1561920, 'steps': 8134, 'loss/train': 1.151728630065918} 08/30/2021 14:37:56 - INFO - __main__ - Step 8136: {'lr': 0.0004978830938680056, 'samples': 1562112, 'steps': 8135, 'loss/train': 1.9238930940628052} 08/30/2021 14:37:56 - INFO - __main__ - Step 8137: {'lr': 0.0004978824046797935, 'samples': 1562304, 'steps': 8136, 'loss/train': 1.9096646308898926} 08/30/2021 14:37:57 - INFO - __main__ - Step 8138: {'lr': 0.0004978817153798895, 'samples': 1562496, 'steps': 8137, 'loss/train': 1.603022575378418} 08/30/2021 14:37:58 - INFO - __main__ - Step 8139: {'lr': 0.0004978810259682939, 'samples': 1562688, 'steps': 8138, 'loss/train': 2.0701990127563477} 08/30/2021 14:37:58 - INFO - __main__ - Step 8140: {'lr': 0.0004978803364450068, 'samples': 1562880, 'steps': 8139, 'loss/train': 2.0248944759368896} 08/30/2021 14:37:59 - INFO - __main__ - Step 8141: {'lr': 0.0004978796468100286, 'samples': 1563072, 'steps': 8140, 'loss/train': 1.6021981239318848} 08/30/2021 14:37:59 - INFO - __main__ - Step 8142: {'lr': 0.0004978789570633598, 'samples': 1563264, 'steps': 8141, 'loss/train': 2.0543816089630127} 08/30/2021 14:38:00 - INFO - __main__ - Step 8143: {'lr': 0.0004978782672050004, 'samples': 1563456, 'steps': 8142, 'loss/train': 1.8658058643341064} 08/30/2021 14:38:01 - INFO - __main__ - Step 8144: {'lr': 0.000497877577234951, 'samples': 1563648, 'steps': 8143, 'loss/train': 1.800978660583496} 08/30/2021 14:38:01 - INFO - __main__ - Step 8145: {'lr': 0.0004978768871532117, 'samples': 1563840, 'steps': 8144, 'loss/train': 3.682251214981079} 08/30/2021 14:38:02 - INFO - __main__ - Step 8146: {'lr': 0.0004978761969597831, 'samples': 1564032, 'steps': 8145, 'loss/train': 1.07888925075531} 08/30/2021 14:38:02 - INFO - __main__ - Step 8147: {'lr': 0.0004978755066546651, 'samples': 1564224, 'steps': 8146, 'loss/train': 2.555426597595215} 08/30/2021 14:38:04 - INFO - __main__ - Step 8148: {'lr': 0.0004978748162378583, 'samples': 1564416, 'steps': 8147, 'loss/train': 1.6210819482803345} 08/30/2021 14:38:04 - INFO - __main__ - Step 8149: {'lr': 0.0004978741257093629, 'samples': 1564608, 'steps': 8148, 'loss/train': 2.622602701187134} 08/30/2021 14:38:04 - INFO - __main__ - Step 8150: {'lr': 0.0004978734350691793, 'samples': 1564800, 'steps': 8149, 'loss/train': 1.7691289186477661} 08/30/2021 14:38:05 - INFO - __main__ - Step 8151: {'lr': 0.0004978727443173077, 'samples': 1564992, 'steps': 8150, 'loss/train': 1.8896803855895996} 08/30/2021 14:38:05 - INFO - __main__ - Step 8152: {'lr': 0.0004978720534537485, 'samples': 1565184, 'steps': 8151, 'loss/train': 2.401085376739502} 08/30/2021 14:38:06 - INFO - __main__ - Step 8153: {'lr': 0.000497871362478502, 'samples': 1565376, 'steps': 8152, 'loss/train': 2.000427484512329} 08/30/2021 14:38:07 - INFO - __main__ - Step 8154: {'lr': 0.0004978706713915684, 'samples': 1565568, 'steps': 8153, 'loss/train': 1.5050705671310425} 08/30/2021 14:38:07 - INFO - __main__ - Step 8155: {'lr': 0.0004978699801929481, 'samples': 1565760, 'steps': 8154, 'loss/train': 1.8289058208465576} 08/30/2021 14:38:08 - INFO - __main__ - Step 8156: {'lr': 0.0004978692888826415, 'samples': 1565952, 'steps': 8155, 'loss/train': 1.6264549493789673} 08/30/2021 14:38:08 - INFO - __main__ - Step 8157: {'lr': 0.0004978685974606488, 'samples': 1566144, 'steps': 8156, 'loss/train': 1.897903561592102} 08/30/2021 14:38:10 - INFO - __main__ - Step 8158: {'lr': 0.0004978679059269704, 'samples': 1566336, 'steps': 8157, 'loss/train': 1.8008724451065063} 08/30/2021 14:38:10 - INFO - __main__ - Step 8159: {'lr': 0.0004978672142816064, 'samples': 1566528, 'steps': 8158, 'loss/train': 1.5293163061141968} 08/30/2021 14:38:10 - INFO - __main__ - Step 8160: {'lr': 0.0004978665225245573, 'samples': 1566720, 'steps': 8159, 'loss/train': 0.18761011958122253} 08/30/2021 14:38:11 - INFO - __main__ - Step 8161: {'lr': 0.0004978658306558234, 'samples': 1566912, 'steps': 8160, 'loss/train': 2.037343978881836} 08/30/2021 14:38:11 - INFO - __main__ - Step 8162: {'lr': 0.000497865138675405, 'samples': 1567104, 'steps': 8161, 'loss/train': 1.8936717510223389} 08/30/2021 14:38:14 - INFO - __main__ - Step 8163: {'lr': 0.0004978644465833024, 'samples': 1567296, 'steps': 8162, 'loss/train': 0.6448262929916382} 08/30/2021 14:38:14 - INFO - __main__ - Step 8164: {'lr': 0.000497863754379516, 'samples': 1567488, 'steps': 8163, 'loss/train': 2.2714755535125732} 08/30/2021 14:38:14 - INFO - __main__ - Step 8165: {'lr': 0.0004978630620640458, 'samples': 1567680, 'steps': 8164, 'loss/train': 2.571237087249756} 08/30/2021 14:38:15 - INFO - __main__ - Step 8166: {'lr': 0.0004978623696368924, 'samples': 1567872, 'steps': 8165, 'loss/train': 3.3331093788146973} 08/30/2021 14:38:15 - INFO - __main__ - Step 8167: {'lr': 0.0004978616770980561, 'samples': 1568064, 'steps': 8166, 'loss/train': 1.8288649320602417} 08/30/2021 14:38:16 - INFO - __main__ - Step 8168: {'lr': 0.0004978609844475371, 'samples': 1568256, 'steps': 8167, 'loss/train': 0.547390341758728} 08/30/2021 14:38:16 - INFO - __main__ - Step 8169: {'lr': 0.0004978602916853359, 'samples': 1568448, 'steps': 8168, 'loss/train': 0.4615233540534973} 08/30/2021 14:38:17 - INFO - __main__ - Step 8170: {'lr': 0.0004978595988114525, 'samples': 1568640, 'steps': 8169, 'loss/train': 1.8013758659362793} 08/30/2021 14:38:18 - INFO - __main__ - Step 8171: {'lr': 0.0004978589058258874, 'samples': 1568832, 'steps': 8170, 'loss/train': 1.5720739364624023} 08/30/2021 14:38:18 - INFO - __main__ - Step 8172: {'lr': 0.0004978582127286409, 'samples': 1569024, 'steps': 8171, 'loss/train': 1.885957956314087} 08/30/2021 14:38:19 - INFO - __main__ - Step 8173: {'lr': 0.0004978575195197135, 'samples': 1569216, 'steps': 8172, 'loss/train': 2.101001024246216} 08/30/2021 14:38:19 - INFO - __main__ - Step 8174: {'lr': 0.0004978568261991051, 'samples': 1569408, 'steps': 8173, 'loss/train': 2.2357654571533203} 08/30/2021 14:38:20 - INFO - __main__ - Step 8175: {'lr': 0.0004978561327668164, 'samples': 1569600, 'steps': 8174, 'loss/train': 0.8115916848182678} 08/30/2021 14:38:21 - INFO - __main__ - Step 8176: {'lr': 0.0004978554392228475, 'samples': 1569792, 'steps': 8175, 'loss/train': 1.8347346782684326} 08/30/2021 14:38:21 - INFO - __main__ - Step 8177: {'lr': 0.0004978547455671986, 'samples': 1569984, 'steps': 8176, 'loss/train': 1.6068774461746216} 08/30/2021 14:38:22 - INFO - __main__ - Step 8178: {'lr': 0.0004978540517998704, 'samples': 1570176, 'steps': 8177, 'loss/train': 1.7253652811050415} 08/30/2021 14:38:22 - INFO - __main__ - Step 8179: {'lr': 0.0004978533579208629, 'samples': 1570368, 'steps': 8178, 'loss/train': 2.012005567550659} 08/30/2021 14:38:24 - INFO - __main__ - Step 8180: {'lr': 0.0004978526639301766, 'samples': 1570560, 'steps': 8179, 'loss/train': 1.7065232992172241} 08/30/2021 14:38:24 - INFO - __main__ - Step 8181: {'lr': 0.0004978519698278116, 'samples': 1570752, 'steps': 8180, 'loss/train': 2.276918411254883} 08/30/2021 14:38:24 - INFO - __main__ - Step 8182: {'lr': 0.0004978512756137684, 'samples': 1570944, 'steps': 8181, 'loss/train': 2.1926393508911133} 08/30/2021 14:38:25 - INFO - __main__ - Step 8183: {'lr': 0.0004978505812880472, 'samples': 1571136, 'steps': 8182, 'loss/train': 1.0561655759811401} 08/30/2021 14:38:25 - INFO - __main__ - Step 8184: {'lr': 0.0004978498868506483, 'samples': 1571328, 'steps': 8183, 'loss/train': 1.8270405530929565} 08/30/2021 14:38:27 - INFO - __main__ - Step 8185: {'lr': 0.0004978491923015721, 'samples': 1571520, 'steps': 8184, 'loss/train': 1.9421552419662476} 08/30/2021 14:38:28 - INFO - __main__ - Step 8186: {'lr': 0.0004978484976408189, 'samples': 1571712, 'steps': 8185, 'loss/train': 1.0923749208450317} 08/30/2021 14:38:28 - INFO - __main__ - Step 8187: {'lr': 0.000497847802868389, 'samples': 1571904, 'steps': 8186, 'loss/train': 1.879454493522644} 08/30/2021 14:38:28 - INFO - __main__ - Step 8188: {'lr': 0.0004978471079842827, 'samples': 1572096, 'steps': 8187, 'loss/train': 1.3024580478668213} 08/30/2021 14:38:29 - INFO - __main__ - Step 8189: {'lr': 0.0004978464129885003, 'samples': 1572288, 'steps': 8188, 'loss/train': 1.5856817960739136} 08/30/2021 14:38:29 - INFO - __main__ - Step 8190: {'lr': 0.0004978457178810422, 'samples': 1572480, 'steps': 8189, 'loss/train': 1.9360442161560059} 08/30/2021 14:38:30 - INFO - __main__ - Step 8191: {'lr': 0.0004978450226619085, 'samples': 1572672, 'steps': 8190, 'loss/train': 1.846137285232544} 08/30/2021 14:38:31 - INFO - __main__ - Step 8192: {'lr': 0.0004978443273310997, 'samples': 1572864, 'steps': 8191, 'loss/train': 1.784417986869812} 08/30/2021 14:38:31 - INFO - __main__ - Step 8193: {'lr': 0.0004978436318886162, 'samples': 1573056, 'steps': 8192, 'loss/train': 1.7672758102416992} 08/30/2021 14:38:32 - INFO - __main__ - Step 8194: {'lr': 0.0004978429363344581, 'samples': 1573248, 'steps': 8193, 'loss/train': 2.1513454914093018} 08/30/2021 14:38:32 - INFO - __main__ - Step 8195: {'lr': 0.0004978422406686257, 'samples': 1573440, 'steps': 8194, 'loss/train': 1.3442859649658203} 08/30/2021 14:38:33 - INFO - __main__ - Step 8196: {'lr': 0.0004978415448911196, 'samples': 1573632, 'steps': 8195, 'loss/train': 1.701888918876648} 08/30/2021 14:38:34 - INFO - __main__ - Step 8197: {'lr': 0.0004978408490019398, 'samples': 1573824, 'steps': 8196, 'loss/train': 1.7170556783676147} 08/30/2021 14:38:34 - INFO - __main__ - Step 8198: {'lr': 0.0004978401530010868, 'samples': 1574016, 'steps': 8197, 'loss/train': 1.5774528980255127} 08/30/2021 14:38:35 - INFO - __main__ - Step 8199: {'lr': 0.0004978394568885608, 'samples': 1574208, 'steps': 8198, 'loss/train': 1.5584241151809692} 08/30/2021 14:38:35 - INFO - __main__ - Step 8200: {'lr': 0.0004978387606643621, 'samples': 1574400, 'steps': 8199, 'loss/train': 2.1084234714508057} 08/30/2021 14:38:36 - INFO - __main__ - Step 8201: {'lr': 0.0004978380643284912, 'samples': 1574592, 'steps': 8200, 'loss/train': 1.483100175857544} 08/30/2021 14:38:37 - INFO - __main__ - Step 8202: {'lr': 0.0004978373678809482, 'samples': 1574784, 'steps': 8201, 'loss/train': 2.0869522094726562} 08/30/2021 14:38:37 - INFO - __main__ - Step 8203: {'lr': 0.0004978366713217336, 'samples': 1574976, 'steps': 8202, 'loss/train': 1.4451258182525635} 08/30/2021 14:38:38 - INFO - __main__ - Step 8204: {'lr': 0.0004978359746508476, 'samples': 1575168, 'steps': 8203, 'loss/train': 2.497816801071167} 08/30/2021 14:38:38 - INFO - __main__ - Step 8205: {'lr': 0.0004978352778682905, 'samples': 1575360, 'steps': 8204, 'loss/train': 2.0786960124969482} 08/30/2021 14:38:39 - INFO - __main__ - Step 8206: {'lr': 0.0004978345809740626, 'samples': 1575552, 'steps': 8205, 'loss/train': 2.1304829120635986} 08/30/2021 14:38:40 - INFO - __main__ - Step 8207: {'lr': 0.0004978338839681644, 'samples': 1575744, 'steps': 8206, 'loss/train': 2.44885516166687} 08/30/2021 14:38:40 - INFO - __main__ - Step 8208: {'lr': 0.000497833186850596, 'samples': 1575936, 'steps': 8207, 'loss/train': 1.7707266807556152} 08/30/2021 14:38:41 - INFO - __main__ - Step 8209: {'lr': 0.0004978324896213577, 'samples': 1576128, 'steps': 8208, 'loss/train': 1.025614857673645} 08/30/2021 14:38:41 - INFO - __main__ - Step 8210: {'lr': 0.00049783179228045, 'samples': 1576320, 'steps': 8209, 'loss/train': 2.0632054805755615} 08/30/2021 14:38:43 - INFO - __main__ - Step 8211: {'lr': 0.0004978310948278731, 'samples': 1576512, 'steps': 8210, 'loss/train': 1.8370667695999146} 08/30/2021 14:38:43 - INFO - __main__ - Step 8212: {'lr': 0.0004978303972636275, 'samples': 1576704, 'steps': 8211, 'loss/train': 1.8413089513778687} 08/30/2021 14:38:44 - INFO - __main__ - Step 8213: {'lr': 0.0004978296995877132, 'samples': 1576896, 'steps': 8212, 'loss/train': 2.230380058288574} 08/30/2021 14:38:44 - INFO - __main__ - Step 8214: {'lr': 0.0004978290018001306, 'samples': 1577088, 'steps': 8213, 'loss/train': 1.8136948347091675} 08/30/2021 14:38:44 - INFO - __main__ - Step 8215: {'lr': 0.0004978283039008801, 'samples': 1577280, 'steps': 8214, 'loss/train': 2.0986435413360596} 08/30/2021 14:38:46 - INFO - __main__ - Step 8216: {'lr': 0.000497827605889962, 'samples': 1577472, 'steps': 8215, 'loss/train': 1.3486262559890747} 08/30/2021 14:38:46 - INFO - __main__ - Step 8217: {'lr': 0.0004978269077673766, 'samples': 1577664, 'steps': 8216, 'loss/train': 1.6297059059143066} 08/30/2021 14:38:47 - INFO - __main__ - Step 8218: {'lr': 0.0004978262095331243, 'samples': 1577856, 'steps': 8217, 'loss/train': 1.6320127248764038} 08/30/2021 14:38:47 - INFO - __main__ - Step 8219: {'lr': 0.0004978255111872053, 'samples': 1578048, 'steps': 8218, 'loss/train': 2.2392680644989014} 08/30/2021 14:38:47 - INFO - __main__ - Step 8220: {'lr': 0.0004978248127296198, 'samples': 1578240, 'steps': 8219, 'loss/train': 5.774405002593994} 08/30/2021 14:38:48 - INFO - __main__ - Step 8221: {'lr': 0.0004978241141603685, 'samples': 1578432, 'steps': 8220, 'loss/train': 1.8457382917404175} 08/30/2021 14:38:49 - INFO - __main__ - Step 8222: {'lr': 0.0004978234154794514, 'samples': 1578624, 'steps': 8221, 'loss/train': 0.22618632018566132} 08/30/2021 14:38:50 - INFO - __main__ - Step 8223: {'lr': 0.0004978227166868689, 'samples': 1578816, 'steps': 8222, 'loss/train': 1.9204914569854736} 08/30/2021 14:38:50 - INFO - __main__ - Step 8224: {'lr': 0.0004978220177826212, 'samples': 1579008, 'steps': 8223, 'loss/train': 1.5733602046966553} 08/30/2021 14:38:50 - INFO - __main__ - Step 8225: {'lr': 0.0004978213187667087, 'samples': 1579200, 'steps': 8224, 'loss/train': 2.2170279026031494} 08/30/2021 14:38:51 - INFO - __main__ - Step 8226: {'lr': 0.0004978206196391319, 'samples': 1579392, 'steps': 8225, 'loss/train': 1.963765025138855} 08/30/2021 14:38:52 - INFO - __main__ - Step 8227: {'lr': 0.0004978199203998909, 'samples': 1579584, 'steps': 8226, 'loss/train': 2.0112295150756836} 08/30/2021 14:38:53 - INFO - __main__ - Step 8228: {'lr': 0.0004978192210489861, 'samples': 1579776, 'steps': 8227, 'loss/train': 2.229060649871826} 08/30/2021 14:38:53 - INFO - __main__ - Step 8229: {'lr': 0.0004978185215864177, 'samples': 1579968, 'steps': 8228, 'loss/train': 1.990768313407898} 08/30/2021 14:38:53 - INFO - __main__ - Step 8230: {'lr': 0.0004978178220121862, 'samples': 1580160, 'steps': 8229, 'loss/train': 1.9822341203689575} 08/30/2021 14:38:54 - INFO - __main__ - Step 8231: {'lr': 0.0004978171223262917, 'samples': 1580352, 'steps': 8230, 'loss/train': 2.1127185821533203} 08/30/2021 14:38:55 - INFO - __main__ - Step 8232: {'lr': 0.0004978164225287346, 'samples': 1580544, 'steps': 8231, 'loss/train': 2.167787790298462} 08/30/2021 14:38:56 - INFO - __main__ - Step 8233: {'lr': 0.0004978157226195153, 'samples': 1580736, 'steps': 8232, 'loss/train': 2.097172498703003} 08/30/2021 14:38:56 - INFO - __main__ - Step 8234: {'lr': 0.0004978150225986342, 'samples': 1580928, 'steps': 8233, 'loss/train': 2.1805906295776367} 08/30/2021 14:38:56 - INFO - __main__ - Step 8235: {'lr': 0.0004978143224660913, 'samples': 1581120, 'steps': 8234, 'loss/train': 1.5666084289550781} 08/30/2021 14:38:57 - INFO - __main__ - Step 8236: {'lr': 0.0004978136222218872, 'samples': 1581312, 'steps': 8235, 'loss/train': 2.2275607585906982} 08/30/2021 14:38:58 - INFO - __main__ - Step 8237: {'lr': 0.000497812921866022, 'samples': 1581504, 'steps': 8236, 'loss/train': 3.4134950637817383} 08/30/2021 14:38:59 - INFO - __main__ - Step 8238: {'lr': 0.0004978122213984961, 'samples': 1581696, 'steps': 8237, 'loss/train': 1.6897222995758057} 08/30/2021 14:38:59 - INFO - __main__ - Step 8239: {'lr': 0.00049781152081931, 'samples': 1581888, 'steps': 8238, 'loss/train': 1.742550253868103} 08/30/2021 14:39:00 - INFO - __main__ - Step 8240: {'lr': 0.0004978108201284638, 'samples': 1582080, 'steps': 8239, 'loss/train': 1.5577292442321777} 08/30/2021 14:39:00 - INFO - __main__ - Step 8241: {'lr': 0.0004978101193259578, 'samples': 1582272, 'steps': 8240, 'loss/train': 1.952988862991333} 08/30/2021 14:39:00 - INFO - __main__ - Step 8242: {'lr': 0.0004978094184117924, 'samples': 1582464, 'steps': 8241, 'loss/train': 2.8648812770843506} 08/30/2021 14:39:02 - INFO - __main__ - Step 8243: {'lr': 0.0004978087173859679, 'samples': 1582656, 'steps': 8242, 'loss/train': 1.7859591245651245} 08/30/2021 14:39:03 - INFO - __main__ - Step 8244: {'lr': 0.0004978080162484846, 'samples': 1582848, 'steps': 8243, 'loss/train': 1.9046686887741089} 08/30/2021 14:39:03 - INFO - __main__ - Step 8245: {'lr': 0.000497807314999343, 'samples': 1583040, 'steps': 8244, 'loss/train': 2.035637617111206} 08/30/2021 14:39:03 - INFO - __main__ - Step 8246: {'lr': 0.000497806613638543, 'samples': 1583232, 'steps': 8245, 'loss/train': 1.5470324754714966} 08/30/2021 14:39:04 - INFO - __main__ - Step 8247: {'lr': 0.0004978059121660853, 'samples': 1583424, 'steps': 8246, 'loss/train': 1.7327110767364502} 08/30/2021 14:39:05 - INFO - __main__ - Step 8248: {'lr': 0.0004978052105819701, 'samples': 1583616, 'steps': 8247, 'loss/train': 1.8364574909210205} 08/30/2021 14:39:06 - INFO - __main__ - Step 8249: {'lr': 0.0004978045088861976, 'samples': 1583808, 'steps': 8248, 'loss/train': 1.7338567972183228} 08/30/2021 14:39:06 - INFO - __main__ - Step 8250: {'lr': 0.0004978038070787683, 'samples': 1584000, 'steps': 8249, 'loss/train': 1.8751275539398193} 08/30/2021 14:39:07 - INFO - __main__ - Step 8251: {'lr': 0.0004978031051596824, 'samples': 1584192, 'steps': 8250, 'loss/train': 2.0312037467956543} 08/30/2021 14:39:07 - INFO - __main__ - Step 8252: {'lr': 0.0004978024031289402, 'samples': 1584384, 'steps': 8251, 'loss/train': 0.29449352622032166} 08/30/2021 14:39:09 - INFO - __main__ - Step 8253: {'lr': 0.0004978017009865421, 'samples': 1584576, 'steps': 8252, 'loss/train': 2.181436538696289} 08/30/2021 14:39:09 - INFO - __main__ - Step 8254: {'lr': 0.0004978009987324884, 'samples': 1584768, 'steps': 8253, 'loss/train': 1.90069580078125} 08/30/2021 14:39:09 - INFO - __main__ - Step 8255: {'lr': 0.0004978002963667794, 'samples': 1584960, 'steps': 8254, 'loss/train': 1.7839347124099731} 08/30/2021 14:39:10 - INFO - __main__ - Step 8256: {'lr': 0.0004977995938894153, 'samples': 1585152, 'steps': 8255, 'loss/train': 1.9654022455215454} 08/30/2021 14:39:10 - INFO - __main__ - Step 8257: {'lr': 0.0004977988913003966, 'samples': 1585344, 'steps': 8256, 'loss/train': 2.3844034671783447} 08/30/2021 14:39:11 - INFO - __main__ - Step 8258: {'lr': 0.0004977981885997235, 'samples': 1585536, 'steps': 8257, 'loss/train': 1.7496044635772705} 08/30/2021 14:39:12 - INFO - __main__ - Step 8259: {'lr': 0.0004977974857873964, 'samples': 1585728, 'steps': 8258, 'loss/train': 1.4685555696487427} 08/30/2021 14:39:12 - INFO - __main__ - Step 8260: {'lr': 0.0004977967828634157, 'samples': 1585920, 'steps': 8259, 'loss/train': 2.159745454788208} 08/30/2021 14:39:13 - INFO - __main__ - Step 8261: {'lr': 0.0004977960798277814, 'samples': 1586112, 'steps': 8260, 'loss/train': 1.9144850969314575} 08/30/2021 14:39:13 - INFO - __main__ - Step 8262: {'lr': 0.0004977953766804941, 'samples': 1586304, 'steps': 8261, 'loss/train': 1.647459864616394} 08/30/2021 14:39:15 - INFO - __main__ - Step 8263: {'lr': 0.0004977946734215541, 'samples': 1586496, 'steps': 8262, 'loss/train': 2.100821018218994} 08/30/2021 14:39:15 - INFO - __main__ - Step 8264: {'lr': 0.0004977939700509615, 'samples': 1586688, 'steps': 8263, 'loss/train': 2.0801079273223877} 08/30/2021 14:39:15 - INFO - __main__ - Step 8265: {'lr': 0.0004977932665687168, 'samples': 1586880, 'steps': 8264, 'loss/train': 1.5985188484191895} 08/30/2021 14:39:16 - INFO - __main__ - Step 8266: {'lr': 0.0004977925629748203, 'samples': 1587072, 'steps': 8265, 'loss/train': 1.9863077402114868} 08/30/2021 14:39:16 - INFO - __main__ - Step 8267: {'lr': 0.0004977918592692723, 'samples': 1587264, 'steps': 8266, 'loss/train': 1.772147536277771} 08/30/2021 14:39:17 - INFO - __main__ - Step 8268: {'lr': 0.0004977911554520731, 'samples': 1587456, 'steps': 8267, 'loss/train': 2.3003275394439697} 08/30/2021 14:39:18 - INFO - __main__ - Step 8269: {'lr': 0.000497790451523223, 'samples': 1587648, 'steps': 8268, 'loss/train': 0.24372439086437225} 08/30/2021 14:39:19 - INFO - __main__ - Step 8270: {'lr': 0.0004977897474827224, 'samples': 1587840, 'steps': 8269, 'loss/train': 1.8935787677764893} 08/30/2021 14:39:19 - INFO - __main__ - Step 8271: {'lr': 0.0004977890433305716, 'samples': 1588032, 'steps': 8270, 'loss/train': 2.200939655303955} 08/30/2021 14:39:19 - INFO - __main__ - Step 8272: {'lr': 0.0004977883390667707, 'samples': 1588224, 'steps': 8271, 'loss/train': 1.963395118713379} 08/30/2021 14:39:20 - INFO - __main__ - Step 8273: {'lr': 0.0004977876346913204, 'samples': 1588416, 'steps': 8272, 'loss/train': 2.0750908851623535} 08/30/2021 14:39:21 - INFO - __main__ - Step 8274: {'lr': 0.0004977869302042207, 'samples': 1588608, 'steps': 8273, 'loss/train': 1.9805692434310913} 08/30/2021 14:39:21 - INFO - __main__ - Step 8275: {'lr': 0.0004977862256054721, 'samples': 1588800, 'steps': 8274, 'loss/train': 2.431096076965332} 08/30/2021 14:39:22 - INFO - __main__ - Step 8276: {'lr': 0.0004977855208950748, 'samples': 1588992, 'steps': 8275, 'loss/train': 1.9583996534347534} 08/30/2021 14:39:22 - INFO - __main__ - Step 8277: {'lr': 0.0004977848160730292, 'samples': 1589184, 'steps': 8276, 'loss/train': 1.602217674255371} 08/30/2021 14:39:23 - INFO - __main__ - Step 8278: {'lr': 0.0004977841111393356, 'samples': 1589376, 'steps': 8277, 'loss/train': 2.1538069248199463} 08/30/2021 14:39:24 - INFO - __main__ - Step 8279: {'lr': 0.0004977834060939943, 'samples': 1589568, 'steps': 8278, 'loss/train': 2.474278688430786} 08/30/2021 14:39:24 - INFO - __main__ - Step 8280: {'lr': 0.0004977827009370056, 'samples': 1589760, 'steps': 8279, 'loss/train': 1.5699925422668457} 08/30/2021 14:39:25 - INFO - __main__ - Step 8281: {'lr': 0.0004977819956683698, 'samples': 1589952, 'steps': 8280, 'loss/train': 1.9401789903640747} 08/30/2021 14:39:25 - INFO - __main__ - Step 8282: {'lr': 0.0004977812902880873, 'samples': 1590144, 'steps': 8281, 'loss/train': 1.7837632894515991} 08/30/2021 14:39:25 - INFO - __main__ - Step 8283: {'lr': 0.0004977805847961584, 'samples': 1590336, 'steps': 8282, 'loss/train': 1.7989060878753662} 08/30/2021 14:39:27 - INFO - __main__ - Step 8284: {'lr': 0.0004977798791925834, 'samples': 1590528, 'steps': 8283, 'loss/train': 1.8197380304336548} 08/30/2021 14:39:28 - INFO - __main__ - Step 8285: {'lr': 0.0004977791734773624, 'samples': 1590720, 'steps': 8284, 'loss/train': 1.4514490365982056} 08/30/2021 14:39:28 - INFO - __main__ - Step 8286: {'lr': 0.0004977784676504962, 'samples': 1590912, 'steps': 8285, 'loss/train': 1.4975500106811523} 08/30/2021 14:39:29 - INFO - __main__ - Step 8287: {'lr': 0.0004977777617119847, 'samples': 1591104, 'steps': 8286, 'loss/train': 0.2620598077774048} 08/30/2021 14:39:29 - INFO - __main__ - Step 8288: {'lr': 0.0004977770556618284, 'samples': 1591296, 'steps': 8287, 'loss/train': 0.7323072552680969} 08/30/2021 14:39:30 - INFO - __main__ - Step 8289: {'lr': 0.0004977763495000276, 'samples': 1591488, 'steps': 8288, 'loss/train': 1.7614859342575073} 08/30/2021 14:39:31 - INFO - __main__ - Step 8290: {'lr': 0.0004977756432265827, 'samples': 1591680, 'steps': 8289, 'loss/train': 2.2198972702026367} 08/30/2021 14:39:31 - INFO - __main__ - Step 8291: {'lr': 0.0004977749368414937, 'samples': 1591872, 'steps': 8290, 'loss/train': 2.3375096321105957} 08/30/2021 14:39:32 - INFO - __main__ - Step 8292: {'lr': 0.0004977742303447613, 'samples': 1592064, 'steps': 8291, 'loss/train': 2.0485856533050537} 08/30/2021 14:39:32 - INFO - __main__ - Step 8293: {'lr': 0.0004977735237363855, 'samples': 1592256, 'steps': 8292, 'loss/train': 1.8509224653244019} 08/30/2021 14:39:32 - INFO - __main__ - Step 8294: {'lr': 0.0004977728170163669, 'samples': 1592448, 'steps': 8293, 'loss/train': 1.587689995765686} 08/30/2021 14:39:34 - INFO - __main__ - Step 8295: {'lr': 0.0004977721101847057, 'samples': 1592640, 'steps': 8294, 'loss/train': 3.0057520866394043} 08/30/2021 14:39:35 - INFO - __main__ - Step 8296: {'lr': 0.0004977714032414021, 'samples': 1592832, 'steps': 8295, 'loss/train': 2.1064672470092773} 08/30/2021 14:39:35 - INFO - __main__ - Step 8297: {'lr': 0.0004977706961864566, 'samples': 1593024, 'steps': 8296, 'loss/train': 1.5779653787612915} 08/30/2021 14:39:36 - INFO - __main__ - Step 8298: {'lr': 0.0004977699890198695, 'samples': 1593216, 'steps': 8297, 'loss/train': 2.4405040740966797} 08/30/2021 14:39:36 - INFO - __main__ - Step 8299: {'lr': 0.0004977692817416411, 'samples': 1593408, 'steps': 8298, 'loss/train': 0.7004013657569885} 08/30/2021 14:39:37 - INFO - __main__ - Step 8300: {'lr': 0.0004977685743517715, 'samples': 1593600, 'steps': 8299, 'loss/train': 2.3566508293151855} 08/30/2021 14:39:38 - INFO - __main__ - Step 8301: {'lr': 0.0004977678668502614, 'samples': 1593792, 'steps': 8300, 'loss/train': 1.4274485111236572} 08/30/2021 14:39:38 - INFO - __main__ - Step 8302: {'lr': 0.0004977671592371108, 'samples': 1593984, 'steps': 8301, 'loss/train': 1.6844537258148193} 08/30/2021 14:39:39 - INFO - __main__ - Step 8303: {'lr': 0.0004977664515123201, 'samples': 1594176, 'steps': 8302, 'loss/train': 2.629887104034424} 08/30/2021 14:39:39 - INFO - __main__ - Step 8304: {'lr': 0.0004977657436758898, 'samples': 1594368, 'steps': 8303, 'loss/train': 2.1009836196899414} 08/30/2021 14:39:40 - INFO - __main__ - Step 8305: {'lr': 0.00049776503572782, 'samples': 1594560, 'steps': 8304, 'loss/train': 2.045954942703247} 08/30/2021 14:39:41 - INFO - __main__ - Step 8306: {'lr': 0.0004977643276681111, 'samples': 1594752, 'steps': 8305, 'loss/train': 1.9974339008331299} 08/30/2021 14:39:41 - INFO - __main__ - Step 8307: {'lr': 0.0004977636194967634, 'samples': 1594944, 'steps': 8306, 'loss/train': 1.535595417022705} 08/30/2021 14:39:42 - INFO - __main__ - Step 8308: {'lr': 0.0004977629112137773, 'samples': 1595136, 'steps': 8307, 'loss/train': 2.3111045360565186} 08/30/2021 14:39:42 - INFO - __main__ - Step 8309: {'lr': 0.000497762202819153, 'samples': 1595328, 'steps': 8308, 'loss/train': 1.8173013925552368} 08/30/2021 14:39:43 - INFO - __main__ - Step 8310: {'lr': 0.0004977614943128909, 'samples': 1595520, 'steps': 8309, 'loss/train': 2.3394112586975098} 08/30/2021 14:39:44 - INFO - __main__ - Step 8311: {'lr': 0.0004977607856949913, 'samples': 1595712, 'steps': 8310, 'loss/train': 1.3983229398727417} 08/30/2021 14:39:44 - INFO - __main__ - Step 8312: {'lr': 0.0004977600769654545, 'samples': 1595904, 'steps': 8311, 'loss/train': 2.004567861557007} 08/30/2021 14:39:44 - INFO - __main__ - Step 8313: {'lr': 0.0004977593681242808, 'samples': 1596096, 'steps': 8312, 'loss/train': 2.938127279281616} 08/30/2021 14:39:45 - INFO - __main__ - Step 8314: {'lr': 0.0004977586591714706, 'samples': 1596288, 'steps': 8313, 'loss/train': 1.8273831605911255} 08/30/2021 14:39:46 - INFO - __main__ - Step 8315: {'lr': 0.0004977579501070241, 'samples': 1596480, 'steps': 8314, 'loss/train': 1.5774086713790894} 08/30/2021 14:39:47 - INFO - __main__ - Step 8316: {'lr': 0.0004977572409309418, 'samples': 1596672, 'steps': 8315, 'loss/train': 1.8776001930236816} 08/30/2021 14:39:47 - INFO - __main__ - Step 8317: {'lr': 0.0004977565316432238, 'samples': 1596864, 'steps': 8316, 'loss/train': 2.654694080352783} 08/30/2021 14:39:47 - INFO - __main__ - Step 8318: {'lr': 0.0004977558222438707, 'samples': 1597056, 'steps': 8317, 'loss/train': 2.268955707550049} 08/30/2021 14:39:48 - INFO - __main__ - Step 8319: {'lr': 0.0004977551127328824, 'samples': 1597248, 'steps': 8318, 'loss/train': 2.0821802616119385} 08/30/2021 14:39:49 - INFO - __main__ - Step 8320: {'lr': 0.0004977544031102597, 'samples': 1597440, 'steps': 8319, 'loss/train': 2.3473060131073} 08/30/2021 14:39:50 - INFO - __main__ - Step 8321: {'lr': 0.0004977536933760025, 'samples': 1597632, 'steps': 8320, 'loss/train': 0.9266359210014343} 08/30/2021 14:39:50 - INFO - __main__ - Step 8322: {'lr': 0.0004977529835301115, 'samples': 1597824, 'steps': 8321, 'loss/train': 1.9030746221542358} 08/30/2021 14:39:50 - INFO - __main__ - Step 8323: {'lr': 0.0004977522735725866, 'samples': 1598016, 'steps': 8322, 'loss/train': 2.0451583862304688} 08/30/2021 14:39:51 - INFO - __main__ - Step 8324: {'lr': 0.0004977515635034285, 'samples': 1598208, 'steps': 8323, 'loss/train': 1.973549246788025} 08/30/2021 14:39:53 - INFO - __main__ - Step 8325: {'lr': 0.0004977508533226374, 'samples': 1598400, 'steps': 8324, 'loss/train': 2.45467209815979} 08/30/2021 14:39:54 - INFO - __main__ - Step 8326: {'lr': 0.0004977501430302136, 'samples': 1598592, 'steps': 8325, 'loss/train': 1.719396710395813} 08/30/2021 14:39:54 - INFO - __main__ - Step 8327: {'lr': 0.0004977494326261573, 'samples': 1598784, 'steps': 8326, 'loss/train': 2.267773151397705} 08/30/2021 14:39:54 - INFO - __main__ - Step 8328: {'lr': 0.000497748722110469, 'samples': 1598976, 'steps': 8327, 'loss/train': 1.4115350246429443} 08/30/2021 14:39:55 - INFO - __main__ - Step 8329: {'lr': 0.0004977480114831489, 'samples': 1599168, 'steps': 8328, 'loss/train': 1.7805625200271606} 08/30/2021 14:39:55 - INFO - __main__ - Step 8330: {'lr': 0.0004977473007441973, 'samples': 1599360, 'steps': 8329, 'loss/train': 2.217846155166626} 08/30/2021 14:39:56 - INFO - __main__ - Step 8331: {'lr': 0.0004977465898936147, 'samples': 1599552, 'steps': 8330, 'loss/train': 1.5316822528839111} 08/30/2021 14:39:57 - INFO - __main__ - Step 8332: {'lr': 0.0004977458789314014, 'samples': 1599744, 'steps': 8331, 'loss/train': 2.6083035469055176} 08/30/2021 14:39:57 - INFO - __main__ - Step 8333: {'lr': 0.0004977451678575575, 'samples': 1599936, 'steps': 8332, 'loss/train': 1.696162223815918} 08/30/2021 14:39:58 - INFO - __main__ - Step 8334: {'lr': 0.0004977444566720834, 'samples': 1600128, 'steps': 8333, 'loss/train': 1.7151960134506226} 08/30/2021 14:39:58 - INFO - __main__ - Step 8335: {'lr': 0.0004977437453749795, 'samples': 1600320, 'steps': 8334, 'loss/train': 1.0623595714569092} 08/30/2021 14:39:58 - INFO - __main__ - Step 8336: {'lr': 0.0004977430339662462, 'samples': 1600512, 'steps': 8335, 'loss/train': 2.3184456825256348} 08/30/2021 14:40:00 - INFO - __main__ - Step 8337: {'lr': 0.0004977423224458837, 'samples': 1600704, 'steps': 8336, 'loss/train': 3.447991371154785} 08/30/2021 14:40:01 - INFO - __main__ - Step 8338: {'lr': 0.0004977416108138922, 'samples': 1600896, 'steps': 8337, 'loss/train': 2.3565752506256104} 08/30/2021 14:40:01 - INFO - __main__ - Step 8339: {'lr': 0.0004977408990702722, 'samples': 1601088, 'steps': 8338, 'loss/train': 1.8986552953720093} 08/30/2021 14:40:01 - INFO - __main__ - Step 8340: {'lr': 0.0004977401872150241, 'samples': 1601280, 'steps': 8339, 'loss/train': 1.8980979919433594} 08/30/2021 14:40:02 - INFO - __main__ - Step 8341: {'lr': 0.000497739475248148, 'samples': 1601472, 'steps': 8340, 'loss/train': 1.9785181283950806} 08/30/2021 14:40:03 - INFO - __main__ - Step 8342: {'lr': 0.0004977387631696443, 'samples': 1601664, 'steps': 8341, 'loss/train': 2.0182082653045654} 08/30/2021 14:40:04 - INFO - __main__ - Step 8343: {'lr': 0.0004977380509795133, 'samples': 1601856, 'steps': 8342, 'loss/train': 1.7331864833831787} 08/30/2021 14:40:04 - INFO - __main__ - Step 8344: {'lr': 0.0004977373386777554, 'samples': 1602048, 'steps': 8343, 'loss/train': 1.4820590019226074} 08/30/2021 14:40:04 - INFO - __main__ - Step 8345: {'lr': 0.0004977366262643709, 'samples': 1602240, 'steps': 8344, 'loss/train': 1.9779471158981323} 08/30/2021 14:40:05 - INFO - __main__ - Step 8346: {'lr': 0.0004977359137393601, 'samples': 1602432, 'steps': 8345, 'loss/train': 2.3275482654571533} 08/30/2021 14:40:07 - INFO - __main__ - Step 8347: {'lr': 0.0004977352011027233, 'samples': 1602624, 'steps': 8346, 'loss/train': 1.9353443384170532} 08/30/2021 14:40:07 - INFO - __main__ - Step 8348: {'lr': 0.0004977344883544608, 'samples': 1602816, 'steps': 8347, 'loss/train': 1.8399087190628052} 08/30/2021 14:40:08 - INFO - __main__ - Step 8349: {'lr': 0.0004977337754945731, 'samples': 1603008, 'steps': 8348, 'loss/train': 1.6668757200241089} 08/30/2021 14:40:08 - INFO - __main__ - Step 8350: {'lr': 0.0004977330625230603, 'samples': 1603200, 'steps': 8349, 'loss/train': 1.7841429710388184} 08/30/2021 14:40:08 - INFO - __main__ - Step 8351: {'lr': 0.0004977323494399227, 'samples': 1603392, 'steps': 8350, 'loss/train': 1.3776886463165283} 08/30/2021 14:40:10 - INFO - __main__ - Step 8352: {'lr': 0.0004977316362451608, 'samples': 1603584, 'steps': 8351, 'loss/train': 1.904458999633789} 08/30/2021 14:40:10 - INFO - __main__ - Step 8353: {'lr': 0.0004977309229387749, 'samples': 1603776, 'steps': 8352, 'loss/train': 1.7164230346679688} 08/30/2021 14:40:11 - INFO - __main__ - Step 8354: {'lr': 0.0004977302095207653, 'samples': 1603968, 'steps': 8353, 'loss/train': 2.028139352798462} 08/30/2021 14:40:11 - INFO - __main__ - Step 8355: {'lr': 0.0004977294959911322, 'samples': 1604160, 'steps': 8354, 'loss/train': 1.74051833152771} 08/30/2021 14:40:11 - INFO - __main__ - Step 8356: {'lr': 0.0004977287823498761, 'samples': 1604352, 'steps': 8355, 'loss/train': 2.0430409908294678} 08/30/2021 14:40:13 - INFO - __main__ - Step 8357: {'lr': 0.0004977280685969971, 'samples': 1604544, 'steps': 8356, 'loss/train': 4.812134265899658} 08/30/2021 14:40:13 - INFO - __main__ - Step 8358: {'lr': 0.0004977273547324958, 'samples': 1604736, 'steps': 8357, 'loss/train': 1.7824848890304565} 08/30/2021 14:40:14 - INFO - __main__ - Step 8359: {'lr': 0.0004977266407563722, 'samples': 1604928, 'steps': 8358, 'loss/train': 0.14400193095207214} 08/30/2021 14:40:14 - INFO - __main__ - Step 8360: {'lr': 0.0004977259266686269, 'samples': 1605120, 'steps': 8359, 'loss/train': 2.008903741836548} 08/30/2021 14:40:14 - INFO - __main__ - Step 8361: {'lr': 0.0004977252124692601, 'samples': 1605312, 'steps': 8360, 'loss/train': 2.2109179496765137} 08/30/2021 14:40:16 - INFO - __main__ - Step 8362: {'lr': 0.0004977244981582723, 'samples': 1605504, 'steps': 8361, 'loss/train': 1.3149958848953247} 08/30/2021 14:40:16 - INFO - __main__ - Step 8363: {'lr': 0.0004977237837356634, 'samples': 1605696, 'steps': 8362, 'loss/train': 1.4814249277114868} 08/30/2021 14:40:17 - INFO - __main__ - Step 8364: {'lr': 0.0004977230692014341, 'samples': 1605888, 'steps': 8363, 'loss/train': 1.2680524587631226} 08/30/2021 14:40:17 - INFO - __main__ - Step 8365: {'lr': 0.0004977223545555847, 'samples': 1606080, 'steps': 8364, 'loss/train': 1.889567494392395} 08/30/2021 14:40:18 - INFO - __main__ - Step 8366: {'lr': 0.0004977216397981153, 'samples': 1606272, 'steps': 8365, 'loss/train': 1.7285511493682861} 08/30/2021 14:40:20 - INFO - __main__ - Step 8367: {'lr': 0.0004977209249290264, 'samples': 1606464, 'steps': 8366, 'loss/train': 1.7076337337493896} 08/30/2021 14:40:20 - INFO - __main__ - Step 8368: {'lr': 0.0004977202099483184, 'samples': 1606656, 'steps': 8367, 'loss/train': 0.6797472238540649} 08/30/2021 14:40:20 - INFO - __main__ - Step 8369: {'lr': 0.0004977194948559913, 'samples': 1606848, 'steps': 8368, 'loss/train': 0.28144410252571106} 08/30/2021 14:40:21 - INFO - __main__ - Step 8370: {'lr': 0.0004977187796520457, 'samples': 1607040, 'steps': 8369, 'loss/train': 0.25786641240119934} 08/30/2021 14:40:21 - INFO - __main__ - Step 8371: {'lr': 0.0004977180643364819, 'samples': 1607232, 'steps': 8370, 'loss/train': 1.8771089315414429} 08/30/2021 14:40:21 - INFO - __main__ - Step 8372: {'lr': 0.0004977173489093, 'samples': 1607424, 'steps': 8371, 'loss/train': 1.7017828226089478} 08/30/2021 14:40:22 - INFO - __main__ - Step 8373: {'lr': 0.0004977166333705005, 'samples': 1607616, 'steps': 8372, 'loss/train': 1.0374953746795654} 08/30/2021 14:40:23 - INFO - __main__ - Step 8374: {'lr': 0.0004977159177200839, 'samples': 1607808, 'steps': 8373, 'loss/train': 0.9303935766220093} 08/30/2021 14:40:24 - INFO - __main__ - Step 8375: {'lr': 0.0004977152019580502, 'samples': 1608000, 'steps': 8374, 'loss/train': 2.3022544384002686} 08/30/2021 14:40:24 - INFO - __main__ - Step 8376: {'lr': 0.0004977144860843998, 'samples': 1608192, 'steps': 8375, 'loss/train': 1.7339766025543213} 08/30/2021 14:40:24 - INFO - __main__ - Step 8377: {'lr': 0.0004977137700991332, 'samples': 1608384, 'steps': 8376, 'loss/train': 1.1866298913955688} 08/30/2021 14:40:25 - INFO - __main__ - Step 8378: {'lr': 0.0004977130540022506, 'samples': 1608576, 'steps': 8377, 'loss/train': 2.2286288738250732} 08/30/2021 14:40:26 - INFO - __main__ - Step 8379: {'lr': 0.0004977123377937523, 'samples': 1608768, 'steps': 8378, 'loss/train': 1.5812745094299316} 08/30/2021 14:40:27 - INFO - __main__ - Step 8380: {'lr': 0.0004977116214736385, 'samples': 1608960, 'steps': 8379, 'loss/train': 2.0170328617095947} 08/30/2021 14:40:27 - INFO - __main__ - Step 8381: {'lr': 0.0004977109050419097, 'samples': 1609152, 'steps': 8380, 'loss/train': 1.406911015510559} 08/30/2021 14:40:28 - INFO - __main__ - Step 8382: {'lr': 0.0004977101884985663, 'samples': 1609344, 'steps': 8381, 'loss/train': 1.9083555936813354} 08/30/2021 14:40:28 - INFO - __main__ - Step 8383: {'lr': 0.0004977094718436085, 'samples': 1609536, 'steps': 8382, 'loss/train': 1.6277457475662231} 08/30/2021 14:40:29 - INFO - __main__ - Step 8384: {'lr': 0.0004977087550770366, 'samples': 1609728, 'steps': 8383, 'loss/train': 1.8766511678695679} 08/30/2021 14:40:30 - INFO - __main__ - Step 8385: {'lr': 0.000497708038198851, 'samples': 1609920, 'steps': 8384, 'loss/train': 1.82414972782135} 08/30/2021 14:40:30 - INFO - __main__ - Step 8386: {'lr': 0.0004977073212090519, 'samples': 1610112, 'steps': 8385, 'loss/train': 1.6500340700149536} 08/30/2021 14:40:31 - INFO - __main__ - Step 8387: {'lr': 0.0004977066041076398, 'samples': 1610304, 'steps': 8386, 'loss/train': 1.7735825777053833} 08/30/2021 14:40:31 - INFO - __main__ - Step 8388: {'lr': 0.0004977058868946148, 'samples': 1610496, 'steps': 8387, 'loss/train': 2.3419904708862305} 08/30/2021 14:40:31 - INFO - __main__ - Step 8389: {'lr': 0.0004977051695699775, 'samples': 1610688, 'steps': 8388, 'loss/train': 1.884500503540039} 08/30/2021 14:40:33 - INFO - __main__ - Step 8390: {'lr': 0.000497704452133728, 'samples': 1610880, 'steps': 8389, 'loss/train': 1.5366007089614868} 08/30/2021 14:40:33 - INFO - __main__ - Step 8391: {'lr': 0.0004977037345858667, 'samples': 1611072, 'steps': 8390, 'loss/train': 1.8311564922332764} 08/30/2021 14:40:34 - INFO - __main__ - Step 8392: {'lr': 0.0004977030169263938, 'samples': 1611264, 'steps': 8391, 'loss/train': 1.4765764474868774} 08/30/2021 14:40:34 - INFO - __main__ - Step 8393: {'lr': 0.0004977022991553099, 'samples': 1611456, 'steps': 8392, 'loss/train': 1.2311745882034302} 08/30/2021 14:40:34 - INFO - __main__ - Step 8394: {'lr': 0.0004977015812726151, 'samples': 1611648, 'steps': 8393, 'loss/train': 2.1788699626922607} 08/30/2021 14:40:36 - INFO - __main__ - Step 8395: {'lr': 0.0004977008632783098, 'samples': 1611840, 'steps': 8394, 'loss/train': 2.254236936569214} 08/30/2021 14:40:37 - INFO - __main__ - Step 8396: {'lr': 0.0004977001451723944, 'samples': 1612032, 'steps': 8395, 'loss/train': 1.889039397239685} 08/30/2021 14:40:37 - INFO - __main__ - Step 8397: {'lr': 0.000497699426954869, 'samples': 1612224, 'steps': 8396, 'loss/train': 0.2786397933959961} 08/30/2021 14:40:37 - INFO - __main__ - Step 8398: {'lr': 0.0004976987086257342, 'samples': 1612416, 'steps': 8397, 'loss/train': 2.030327320098877} 08/30/2021 14:40:38 - INFO - __main__ - Step 8399: {'lr': 0.0004976979901849901, 'samples': 1612608, 'steps': 8398, 'loss/train': 1.8387422561645508} 08/30/2021 14:40:39 - INFO - __main__ - Step 8400: {'lr': 0.000497697271632637, 'samples': 1612800, 'steps': 8399, 'loss/train': 0.24667046964168549} 08/30/2021 14:40:40 - INFO - __main__ - Step 8401: {'lr': 0.0004976965529686756, 'samples': 1612992, 'steps': 8400, 'loss/train': 1.3080761432647705} 08/30/2021 14:40:40 - INFO - __main__ - Step 8402: {'lr': 0.0004976958341931057, 'samples': 1613184, 'steps': 8401, 'loss/train': 2.1053905487060547} 08/30/2021 14:40:41 - INFO - __main__ - Step 8403: {'lr': 0.000497695115305928, 'samples': 1613376, 'steps': 8402, 'loss/train': 1.9701963663101196} 08/30/2021 14:40:41 - INFO - __main__ - Step 8404: {'lr': 0.0004976943963071426, 'samples': 1613568, 'steps': 8403, 'loss/train': 1.962083339691162} 08/30/2021 14:40:43 - INFO - __main__ - Step 8405: {'lr': 0.0004976936771967501, 'samples': 1613760, 'steps': 8404, 'loss/train': 1.8074135780334473} 08/30/2021 14:40:44 - INFO - __main__ - Step 8406: {'lr': 0.0004976929579747505, 'samples': 1613952, 'steps': 8405, 'loss/train': 1.9674524068832397} 08/30/2021 14:40:44 - INFO - __main__ - Step 8407: {'lr': 0.0004976922386411444, 'samples': 1614144, 'steps': 8406, 'loss/train': 2.0371336936950684} 08/30/2021 14:40:44 - INFO - __main__ - Step 8408: {'lr': 0.0004976915191959319, 'samples': 1614336, 'steps': 8407, 'loss/train': 3.048996686935425} 08/30/2021 14:40:45 - INFO - __main__ - Step 8409: {'lr': 0.0004976907996391135, 'samples': 1614528, 'steps': 8408, 'loss/train': 1.9434444904327393} 08/30/2021 14:40:46 - INFO - __main__ - Step 8410: {'lr': 0.0004976900799706894, 'samples': 1614720, 'steps': 8409, 'loss/train': 1.6855064630508423} 08/30/2021 14:40:47 - INFO - __main__ - Step 8411: {'lr': 0.00049768936019066, 'samples': 1614912, 'steps': 8410, 'loss/train': 2.3353629112243652} 08/30/2021 14:40:47 - INFO - __main__ - Step 8412: {'lr': 0.0004976886402990255, 'samples': 1615104, 'steps': 8411, 'loss/train': 2.074800968170166} 08/30/2021 14:40:47 - INFO - __main__ - Step 8413: {'lr': 0.0004976879202957864, 'samples': 1615296, 'steps': 8412, 'loss/train': 2.114934206008911} 08/30/2021 14:40:48 - INFO - __main__ - Step 8414: {'lr': 0.000497687200180943, 'samples': 1615488, 'steps': 8413, 'loss/train': 2.45617413520813} 08/30/2021 14:40:48 - INFO - __main__ - Step 8415: {'lr': 0.0004976864799544954, 'samples': 1615680, 'steps': 8414, 'loss/train': 2.501805305480957} 08/30/2021 14:40:50 - INFO - __main__ - Step 8416: {'lr': 0.0004976857596164443, 'samples': 1615872, 'steps': 8415, 'loss/train': 1.850860357284546} 08/30/2021 14:40:50 - INFO - __main__ - Step 8417: {'lr': 0.0004976850391667897, 'samples': 1616064, 'steps': 8416, 'loss/train': 1.9494117498397827} 08/30/2021 14:40:50 - INFO - __main__ - Step 8418: {'lr': 0.0004976843186055321, 'samples': 1616256, 'steps': 8417, 'loss/train': 1.4619063138961792} 08/30/2021 14:40:51 - INFO - __main__ - Step 8419: {'lr': 0.0004976835979326718, 'samples': 1616448, 'steps': 8418, 'loss/train': 2.0630555152893066} 08/30/2021 14:40:51 - INFO - __main__ - Step 8420: {'lr': 0.0004976828771482089, 'samples': 1616640, 'steps': 8419, 'loss/train': 1.6443235874176025} 08/30/2021 14:40:53 - INFO - __main__ - Step 8421: {'lr': 0.0004976821562521441, 'samples': 1616832, 'steps': 8420, 'loss/train': 1.9582713842391968} 08/30/2021 14:40:53 - INFO - __main__ - Step 8422: {'lr': 0.0004976814352444775, 'samples': 1617024, 'steps': 8421, 'loss/train': 2.0009896755218506} 08/30/2021 14:40:53 - INFO - __main__ - Step 8423: {'lr': 0.0004976807141252094, 'samples': 1617216, 'steps': 8422, 'loss/train': 2.197566032409668} 08/30/2021 14:40:54 - INFO - __main__ - Step 8424: {'lr': 0.0004976799928943403, 'samples': 1617408, 'steps': 8423, 'loss/train': 1.372810959815979} 08/30/2021 14:40:54 - INFO - __main__ - Step 8425: {'lr': 0.0004976792715518703, 'samples': 1617600, 'steps': 8424, 'loss/train': 2.1167540550231934} 08/30/2021 14:40:56 - INFO - __main__ - Step 8426: {'lr': 0.0004976785500978, 'samples': 1617792, 'steps': 8425, 'loss/train': 1.62273108959198} 08/30/2021 14:40:56 - INFO - __main__ - Step 8427: {'lr': 0.0004976778285321294, 'samples': 1617984, 'steps': 8426, 'loss/train': 1.919689416885376} 08/30/2021 14:40:57 - INFO - __main__ - Step 8428: {'lr': 0.0004976771068548591, 'samples': 1618176, 'steps': 8427, 'loss/train': 2.0481975078582764} 08/30/2021 14:40:57 - INFO - __main__ - Step 8429: {'lr': 0.0004976763850659893, 'samples': 1618368, 'steps': 8428, 'loss/train': 2.188000202178955} 08/30/2021 14:40:57 - INFO - __main__ - Step 8430: {'lr': 0.0004976756631655203, 'samples': 1618560, 'steps': 8429, 'loss/train': 1.6878498792648315} 08/30/2021 14:40:59 - INFO - __main__ - Step 8431: {'lr': 0.0004976749411534525, 'samples': 1618752, 'steps': 8430, 'loss/train': 2.0530524253845215} 08/30/2021 14:40:59 - INFO - __main__ - Step 8432: {'lr': 0.0004976742190297862, 'samples': 1618944, 'steps': 8431, 'loss/train': 1.426246166229248} 08/30/2021 14:41:00 - INFO - __main__ - Step 8433: {'lr': 0.0004976734967945217, 'samples': 1619136, 'steps': 8432, 'loss/train': 2.087311029434204} 08/30/2021 14:41:00 - INFO - __main__ - Step 8434: {'lr': 0.0004976727744476593, 'samples': 1619328, 'steps': 8433, 'loss/train': 1.9107396602630615} 08/30/2021 14:41:01 - INFO - __main__ - Step 8435: {'lr': 0.0004976720519891994, 'samples': 1619520, 'steps': 8434, 'loss/train': 2.3749823570251465} 08/30/2021 14:41:01 - INFO - __main__ - Step 8436: {'lr': 0.0004976713294191423, 'samples': 1619712, 'steps': 8435, 'loss/train': 1.8813793659210205} 08/30/2021 14:41:02 - INFO - __main__ - Step 8437: {'lr': 0.0004976706067374885, 'samples': 1619904, 'steps': 8436, 'loss/train': 1.721274971961975} 08/30/2021 14:41:03 - INFO - __main__ - Step 8438: {'lr': 0.0004976698839442379, 'samples': 1620096, 'steps': 8437, 'loss/train': 1.6744798421859741} 08/30/2021 14:41:03 - INFO - __main__ - Step 8439: {'lr': 0.0004976691610393911, 'samples': 1620288, 'steps': 8438, 'loss/train': 2.0879571437835693} 08/30/2021 14:41:04 - INFO - __main__ - Step 8440: {'lr': 0.0004976684380229485, 'samples': 1620480, 'steps': 8439, 'loss/train': 0.20244963467121124} 08/30/2021 14:41:04 - INFO - __main__ - Step 8441: {'lr': 0.0004976677148949102, 'samples': 1620672, 'steps': 8440, 'loss/train': 1.9900668859481812} 08/30/2021 14:41:06 - INFO - __main__ - Step 8442: {'lr': 0.0004976669916552768, 'samples': 1620864, 'steps': 8441, 'loss/train': 1.7141551971435547} 08/30/2021 14:41:06 - INFO - __main__ - Step 8443: {'lr': 0.0004976662683040484, 'samples': 1621056, 'steps': 8442, 'loss/train': 1.8672370910644531} 08/30/2021 14:41:06 - INFO - __main__ - Step 8444: {'lr': 0.0004976655448412254, 'samples': 1621248, 'steps': 8443, 'loss/train': 2.3276731967926025} 08/30/2021 14:41:07 - INFO - __main__ - Step 8445: {'lr': 0.0004976648212668081, 'samples': 1621440, 'steps': 8444, 'loss/train': 2.4769723415374756} 08/30/2021 14:41:07 - INFO - __main__ - Step 8446: {'lr': 0.0004976640975807969, 'samples': 1621632, 'steps': 8445, 'loss/train': 2.1962947845458984} 08/30/2021 14:41:09 - INFO - __main__ - Step 8447: {'lr': 0.0004976633737831921, 'samples': 1621824, 'steps': 8446, 'loss/train': 1.7524241209030151} 08/30/2021 14:41:09 - INFO - __main__ - Step 8448: {'lr': 0.000497662649873994, 'samples': 1622016, 'steps': 8447, 'loss/train': 1.8559969663619995} 08/30/2021 14:41:10 - INFO - __main__ - Step 8449: {'lr': 0.0004976619258532029, 'samples': 1622208, 'steps': 8448, 'loss/train': 1.780842900276184} 08/30/2021 14:41:10 - INFO - __main__ - Step 8450: {'lr': 0.0004976612017208191, 'samples': 1622400, 'steps': 8449, 'loss/train': 2.192594528198242} 08/30/2021 14:41:10 - INFO - __main__ - Step 8451: {'lr': 0.000497660477476843, 'samples': 1622592, 'steps': 8450, 'loss/train': 2.020826578140259} 08/30/2021 14:41:12 - INFO - __main__ - Step 8452: {'lr': 0.000497659753121275, 'samples': 1622784, 'steps': 8451, 'loss/train': 2.2761666774749756} 08/30/2021 14:41:12 - INFO - __main__ - Step 8453: {'lr': 0.0004976590286541152, 'samples': 1622976, 'steps': 8452, 'loss/train': 1.6590408086776733} 08/30/2021 14:41:12 - INFO - __main__ - Step 8454: {'lr': 0.0004976583040753643, 'samples': 1623168, 'steps': 8453, 'loss/train': 2.0330984592437744} 08/30/2021 14:41:13 - INFO - __main__ - Step 8455: {'lr': 0.0004976575793850223, 'samples': 1623360, 'steps': 8454, 'loss/train': 1.8798871040344238} 08/30/2021 14:41:13 - INFO - __main__ - Step 8456: {'lr': 0.0004976568545830894, 'samples': 1623552, 'steps': 8455, 'loss/train': 1.8375606536865234} 08/30/2021 14:41:15 - INFO - __main__ - Step 8457: {'lr': 0.0004976561296695663, 'samples': 1623744, 'steps': 8456, 'loss/train': 1.9186795949935913} 08/30/2021 14:41:16 - INFO - __main__ - Step 8458: {'lr': 0.0004976554046444532, 'samples': 1623936, 'steps': 8457, 'loss/train': 1.598724603652954} 08/30/2021 14:41:16 - INFO - __main__ - Step 8459: {'lr': 0.0004976546795077503, 'samples': 1624128, 'steps': 8458, 'loss/train': 2.0605580806732178} 08/30/2021 14:41:17 - INFO - __main__ - Step 8460: {'lr': 0.0004976539542594582, 'samples': 1624320, 'steps': 8459, 'loss/train': 0.7667750120162964} 08/30/2021 14:41:17 - INFO - __main__ - Step 8461: {'lr': 0.0004976532288995768, 'samples': 1624512, 'steps': 8460, 'loss/train': 1.062516689300537} 08/30/2021 14:41:17 - INFO - __main__ - Step 8462: {'lr': 0.0004976525034281069, 'samples': 1624704, 'steps': 8461, 'loss/train': 2.5350990295410156} 08/30/2021 14:41:19 - INFO - __main__ - Step 8463: {'lr': 0.0004976517778450486, 'samples': 1624896, 'steps': 8462, 'loss/train': 1.7621550559997559} 08/30/2021 14:41:20 - INFO - __main__ - Step 8464: {'lr': 0.000497651052150402, 'samples': 1625088, 'steps': 8463, 'loss/train': 1.9986919164657593} 08/30/2021 14:41:20 - INFO - __main__ - Step 8465: {'lr': 0.0004976503263441679, 'samples': 1625280, 'steps': 8464, 'loss/train': 0.3113585412502289} 08/30/2021 14:41:20 - INFO - __main__ - Step 8466: {'lr': 0.0004976496004263463, 'samples': 1625472, 'steps': 8465, 'loss/train': 1.6023749113082886} 08/30/2021 14:41:21 - INFO - __main__ - Step 8467: {'lr': 0.0004976488743969376, 'samples': 1625664, 'steps': 8466, 'loss/train': 2.0465993881225586} 08/30/2021 14:41:21 - INFO - __main__ - Step 8468: {'lr': 0.0004976481482559421, 'samples': 1625856, 'steps': 8467, 'loss/train': 3.549811601638794} 08/30/2021 14:41:23 - INFO - __main__ - Step 8469: {'lr': 0.0004976474220033602, 'samples': 1626048, 'steps': 8468, 'loss/train': 2.1560614109039307} 08/30/2021 14:41:23 - INFO - __main__ - Step 8470: {'lr': 0.0004976466956391922, 'samples': 1626240, 'steps': 8469, 'loss/train': 2.440587282180786} 08/30/2021 14:41:23 - INFO - __main__ - Step 8471: {'lr': 0.0004976459691634384, 'samples': 1626432, 'steps': 8470, 'loss/train': 1.8070740699768066} 08/30/2021 14:41:24 - INFO - __main__ - Step 8472: {'lr': 0.0004976452425760992, 'samples': 1626624, 'steps': 8471, 'loss/train': 2.6197290420532227} 08/30/2021 14:41:24 - INFO - __main__ - Step 8473: {'lr': 0.0004976445158771748, 'samples': 1626816, 'steps': 8472, 'loss/train': 2.0030508041381836} 08/30/2021 14:41:26 - INFO - __main__ - Step 8474: {'lr': 0.0004976437890666657, 'samples': 1627008, 'steps': 8473, 'loss/train': 1.2487941980361938} 08/30/2021 14:41:26 - INFO - __main__ - Step 8475: {'lr': 0.0004976430621445721, 'samples': 1627200, 'steps': 8474, 'loss/train': 1.7159271240234375} 08/30/2021 14:41:27 - INFO - __main__ - Step 8476: {'lr': 0.0004976423351108943, 'samples': 1627392, 'steps': 8475, 'loss/train': 2.32255482673645} 08/30/2021 14:41:27 - INFO - __main__ - Step 8477: {'lr': 0.0004976416079656328, 'samples': 1627584, 'steps': 8476, 'loss/train': 2.0413544178009033} 08/30/2021 14:41:28 - INFO - __main__ - Step 8478: {'lr': 0.0004976408807087876, 'samples': 1627776, 'steps': 8477, 'loss/train': 2.082794666290283} 08/30/2021 14:41:29 - INFO - __main__ - Step 8479: {'lr': 0.0004976401533403594, 'samples': 1627968, 'steps': 8478, 'loss/train': 2.3448400497436523} 08/30/2021 14:41:29 - INFO - __main__ - Step 8480: {'lr': 0.0004976394258603484, 'samples': 1628160, 'steps': 8479, 'loss/train': 1.9288054704666138} 08/30/2021 14:41:30 - INFO - __main__ - Step 8481: {'lr': 0.0004976386982687549, 'samples': 1628352, 'steps': 8480, 'loss/train': 1.887291669845581} 08/30/2021 14:41:30 - INFO - __main__ - Step 8482: {'lr': 0.0004976379705655791, 'samples': 1628544, 'steps': 8481, 'loss/train': 2.1422014236450195} 08/30/2021 14:41:31 - INFO - __main__ - Step 8483: {'lr': 0.0004976372427508215, 'samples': 1628736, 'steps': 8482, 'loss/train': 2.495030164718628} 08/30/2021 14:41:32 - INFO - __main__ - Step 8484: {'lr': 0.0004976365148244824, 'samples': 1628928, 'steps': 8483, 'loss/train': 3.080559015274048} 08/30/2021 14:41:33 - INFO - __main__ - Step 8485: {'lr': 0.0004976357867865621, 'samples': 1629120, 'steps': 8484, 'loss/train': 1.867462158203125} 08/30/2021 14:41:33 - INFO - __main__ - Step 8486: {'lr': 0.0004976350586370609, 'samples': 1629312, 'steps': 8485, 'loss/train': 2.1726021766662598} 08/30/2021 14:41:33 - INFO - __main__ - Step 8487: {'lr': 0.0004976343303759792, 'samples': 1629504, 'steps': 8486, 'loss/train': 1.6485310792922974} 08/30/2021 14:41:34 - INFO - __main__ - Step 8488: {'lr': 0.0004976336020033174, 'samples': 1629696, 'steps': 8487, 'loss/train': 2.2282848358154297} 08/30/2021 14:41:35 - INFO - __main__ - Step 8489: {'lr': 0.0004976328735190755, 'samples': 1629888, 'steps': 8488, 'loss/train': 1.8821983337402344} 08/30/2021 14:41:36 - INFO - __main__ - Step 8490: {'lr': 0.0004976321449232542, 'samples': 1630080, 'steps': 8489, 'loss/train': 0.7413626909255981} 08/30/2021 14:41:36 - INFO - __main__ - Step 8491: {'lr': 0.0004976314162158536, 'samples': 1630272, 'steps': 8490, 'loss/train': 1.9485259056091309} 08/30/2021 14:41:36 - INFO - __main__ - Step 8492: {'lr': 0.0004976306873968741, 'samples': 1630464, 'steps': 8491, 'loss/train': 0.3117968440055847} 08/30/2021 14:41:37 - INFO - __main__ - Step 8493: {'lr': 0.0004976299584663161, 'samples': 1630656, 'steps': 8492, 'loss/train': 2.099956512451172} 08/30/2021 14:41:37 - INFO - __main__ - Step 8494: {'lr': 0.0004976292294241798, 'samples': 1630848, 'steps': 8493, 'loss/train': 2.1442737579345703} 08/30/2021 14:41:39 - INFO - __main__ - Step 8495: {'lr': 0.0004976285002704656, 'samples': 1631040, 'steps': 8494, 'loss/train': 1.9286046028137207} 08/30/2021 14:41:39 - INFO - __main__ - Step 8496: {'lr': 0.0004976277710051739, 'samples': 1631232, 'steps': 8495, 'loss/train': 1.6619433164596558} 08/30/2021 14:41:39 - INFO - __main__ - Step 8497: {'lr': 0.0004976270416283049, 'samples': 1631424, 'steps': 8496, 'loss/train': 2.144641160964966} 08/30/2021 14:41:40 - INFO - __main__ - Step 8498: {'lr': 0.000497626312139859, 'samples': 1631616, 'steps': 8497, 'loss/train': 2.459773302078247} 08/30/2021 14:41:40 - INFO - __main__ - Step 8499: {'lr': 0.0004976255825398365, 'samples': 1631808, 'steps': 8498, 'loss/train': 2.3068463802337646} 08/30/2021 14:41:42 - INFO - __main__ - Step 8500: {'lr': 0.0004976248528282376, 'samples': 1632000, 'steps': 8499, 'loss/train': 2.0007362365722656} 08/30/2021 14:41:42 - INFO - __main__ - Step 8501: {'lr': 0.000497624123005063, 'samples': 1632192, 'steps': 8500, 'loss/train': 1.9711920022964478} 08/30/2021 14:41:42 - INFO - __main__ - Step 8502: {'lr': 0.0004976233930703126, 'samples': 1632384, 'steps': 8501, 'loss/train': 1.1688724756240845} 08/30/2021 14:41:43 - INFO - __main__ - Step 8503: {'lr': 0.000497622663023987, 'samples': 1632576, 'steps': 8502, 'loss/train': 2.0451629161834717} 08/30/2021 14:41:43 - INFO - __main__ - Step 8504: {'lr': 0.0004976219328660864, 'samples': 1632768, 'steps': 8503, 'loss/train': 2.319286346435547} 08/30/2021 14:41:44 - INFO - __main__ - Step 8505: {'lr': 0.0004976212025966112, 'samples': 1632960, 'steps': 8504, 'loss/train': 2.3594236373901367} 08/30/2021 14:41:45 - INFO - __main__ - Step 8506: {'lr': 0.0004976204722155617, 'samples': 1633152, 'steps': 8505, 'loss/train': 2.0503997802734375} 08/30/2021 14:41:45 - INFO - __main__ - Step 8507: {'lr': 0.0004976197417229383, 'samples': 1633344, 'steps': 8506, 'loss/train': 2.303234100341797} 08/30/2021 14:41:46 - INFO - __main__ - Step 8508: {'lr': 0.0004976190111187412, 'samples': 1633536, 'steps': 8507, 'loss/train': 1.8147375583648682} 08/30/2021 14:41:46 - INFO - __main__ - Step 8509: {'lr': 0.0004976182804029708, 'samples': 1633728, 'steps': 8508, 'loss/train': 1.4946863651275635} 08/30/2021 14:41:47 - INFO - __main__ - Step 8510: {'lr': 0.0004976175495756274, 'samples': 1633920, 'steps': 8509, 'loss/train': 2.2374181747436523} 08/30/2021 14:41:48 - INFO - __main__ - Step 8511: {'lr': 0.0004976168186367115, 'samples': 1634112, 'steps': 8510, 'loss/train': 1.914146065711975} 08/30/2021 14:41:48 - INFO - __main__ - Step 8512: {'lr': 0.0004976160875862231, 'samples': 1634304, 'steps': 8511, 'loss/train': 1.9570538997650146} 08/30/2021 14:41:49 - INFO - __main__ - Step 8513: {'lr': 0.0004976153564241628, 'samples': 1634496, 'steps': 8512, 'loss/train': 2.3283867835998535} 08/30/2021 14:41:49 - INFO - __main__ - Step 8514: {'lr': 0.0004976146251505309, 'samples': 1634688, 'steps': 8513, 'loss/train': 1.7819856405258179} 08/30/2021 14:41:49 - INFO - __main__ - Step 8515: {'lr': 0.0004976138937653275, 'samples': 1634880, 'steps': 8514, 'loss/train': 2.3694818019866943} 08/30/2021 14:41:51 - INFO - __main__ - Step 8516: {'lr': 0.0004976131622685532, 'samples': 1635072, 'steps': 8515, 'loss/train': 1.8378411531448364} 08/30/2021 14:41:52 - INFO - __main__ - Step 8517: {'lr': 0.0004976124306602083, 'samples': 1635264, 'steps': 8516, 'loss/train': 2.0556554794311523} 08/30/2021 14:41:52 - INFO - __main__ - Step 8518: {'lr': 0.0004976116989402929, 'samples': 1635456, 'steps': 8517, 'loss/train': 2.6223933696746826} 08/30/2021 14:41:53 - INFO - __main__ - Step 8519: {'lr': 0.0004976109671088076, 'samples': 1635648, 'steps': 8518, 'loss/train': 1.8509653806686401} 08/30/2021 14:41:53 - INFO - __main__ - Step 8520: {'lr': 0.0004976102351657526, 'samples': 1635840, 'steps': 8519, 'loss/train': 2.9559926986694336} 08/30/2021 14:41:53 - INFO - __main__ - Step 8521: {'lr': 0.0004976095031111283, 'samples': 1636032, 'steps': 8520, 'loss/train': 1.9471144676208496} 08/30/2021 14:41:55 - INFO - __main__ - Step 8522: {'lr': 0.0004976087709449348, 'samples': 1636224, 'steps': 8521, 'loss/train': 2.1203227043151855} 08/30/2021 14:41:56 - INFO - __main__ - Step 8523: {'lr': 0.0004976080386671728, 'samples': 1636416, 'steps': 8522, 'loss/train': 0.2881372570991516} 08/30/2021 14:41:56 - INFO - __main__ - Step 8524: {'lr': 0.0004976073062778423, 'samples': 1636608, 'steps': 8523, 'loss/train': 2.4722959995269775} 08/30/2021 14:41:56 - INFO - __main__ - Step 8525: {'lr': 0.0004976065737769439, 'samples': 1636800, 'steps': 8524, 'loss/train': 2.5211868286132812} 08/30/2021 14:41:57 - INFO - __main__ - Step 8526: {'lr': 0.0004976058411644777, 'samples': 1636992, 'steps': 8525, 'loss/train': 2.07977294921875} 08/30/2021 14:41:58 - INFO - __main__ - Step 8527: {'lr': 0.0004976051084404443, 'samples': 1637184, 'steps': 8526, 'loss/train': 1.9101005792617798} 08/30/2021 14:41:59 - INFO - __main__ - Step 8528: {'lr': 0.0004976043756048436, 'samples': 1637376, 'steps': 8527, 'loss/train': 2.264810562133789} 08/30/2021 14:41:59 - INFO - __main__ - Step 8529: {'lr': 0.0004976036426576763, 'samples': 1637568, 'steps': 8528, 'loss/train': 1.7202534675598145} 08/30/2021 14:41:59 - INFO - __main__ - Step 8530: {'lr': 0.0004976029095989427, 'samples': 1637760, 'steps': 8529, 'loss/train': 1.697363257408142} 08/30/2021 14:42:00 - INFO - __main__ - Step 8531: {'lr': 0.000497602176428643, 'samples': 1637952, 'steps': 8530, 'loss/train': 1.708794355392456} 08/30/2021 14:42:01 - INFO - __main__ - Step 8532: {'lr': 0.0004976014431467775, 'samples': 1638144, 'steps': 8531, 'loss/train': 2.5881059169769287} 08/30/2021 14:42:02 - INFO - __main__ - Step 8533: {'lr': 0.0004976007097533467, 'samples': 1638336, 'steps': 8532, 'loss/train': 1.8518662452697754} 08/30/2021 14:42:02 - INFO - __main__ - Step 8534: {'lr': 0.0004975999762483509, 'samples': 1638528, 'steps': 8533, 'loss/train': 0.20579160749912262} 08/30/2021 14:42:03 - INFO - __main__ - Step 8535: {'lr': 0.0004975992426317902, 'samples': 1638720, 'steps': 8534, 'loss/train': 2.5459859371185303} 08/30/2021 14:42:03 - INFO - __main__ - Step 8536: {'lr': 0.0004975985089036652, 'samples': 1638912, 'steps': 8535, 'loss/train': 1.9717767238616943} 08/30/2021 14:42:04 - INFO - __main__ - Step 8537: {'lr': 0.0004975977750639761, 'samples': 1639104, 'steps': 8536, 'loss/train': 3.9437596797943115} 08/30/2021 14:42:05 - INFO - __main__ - Step 8538: {'lr': 0.0004975970411127233, 'samples': 1639296, 'steps': 8537, 'loss/train': 2.1195478439331055} 08/30/2021 14:42:05 - INFO - __main__ - Step 8539: {'lr': 0.0004975963070499071, 'samples': 1639488, 'steps': 8538, 'loss/train': 1.6157540082931519} 08/30/2021 14:42:06 - INFO - __main__ - Step 8540: {'lr': 0.0004975955728755277, 'samples': 1639680, 'steps': 8539, 'loss/train': 2.056792974472046} 08/30/2021 14:42:06 - INFO - __main__ - Step 8541: {'lr': 0.0004975948385895858, 'samples': 1639872, 'steps': 8540, 'loss/train': 1.8156791925430298} 08/30/2021 14:42:08 - INFO - __main__ - Step 8542: {'lr': 0.0004975941041920813, 'samples': 1640064, 'steps': 8541, 'loss/train': 2.3577349185943604} 08/30/2021 14:42:08 - INFO - __main__ - Step 8543: {'lr': 0.0004975933696830147, 'samples': 1640256, 'steps': 8542, 'loss/train': 0.6268185377120972} 08/30/2021 14:42:09 - INFO - __main__ - Step 8544: {'lr': 0.0004975926350623864, 'samples': 1640448, 'steps': 8543, 'loss/train': 0.7368513941764832} 08/30/2021 14:42:09 - INFO - __main__ - Step 8545: {'lr': 0.0004975919003301967, 'samples': 1640640, 'steps': 8544, 'loss/train': 1.5377479791641235} 08/30/2021 14:42:09 - INFO - __main__ - Step 8546: {'lr': 0.0004975911654864459, 'samples': 1640832, 'steps': 8545, 'loss/train': 1.5808402299880981} 08/30/2021 14:42:10 - INFO - __main__ - Step 8547: {'lr': 0.0004975904305311344, 'samples': 1641024, 'steps': 8546, 'loss/train': 2.248965263366699} 08/30/2021 14:42:11 - INFO - __main__ - Step 8548: {'lr': 0.0004975896954642623, 'samples': 1641216, 'steps': 8547, 'loss/train': 2.206531524658203} 08/30/2021 14:42:12 - INFO - __main__ - Step 8549: {'lr': 0.0004975889602858303, 'samples': 1641408, 'steps': 8548, 'loss/train': 2.012965440750122} 08/30/2021 14:42:12 - INFO - __main__ - Step 8550: {'lr': 0.0004975882249958385, 'samples': 1641600, 'steps': 8549, 'loss/train': 1.8193858861923218} 08/30/2021 14:42:12 - INFO - __main__ - Step 8551: {'lr': 0.0004975874895942872, 'samples': 1641792, 'steps': 8550, 'loss/train': 2.252633571624756} 08/30/2021 14:42:13 - INFO - __main__ - Step 8552: {'lr': 0.0004975867540811768, 'samples': 1641984, 'steps': 8551, 'loss/train': 1.5177539587020874} 08/30/2021 14:42:14 - INFO - __main__ - Step 8553: {'lr': 0.0004975860184565076, 'samples': 1642176, 'steps': 8552, 'loss/train': 1.8967360258102417} 08/30/2021 14:42:15 - INFO - __main__ - Step 8554: {'lr': 0.0004975852827202801, 'samples': 1642368, 'steps': 8553, 'loss/train': 1.8044441938400269} 08/30/2021 14:42:15 - INFO - __main__ - Step 8555: {'lr': 0.0004975845468724944, 'samples': 1642560, 'steps': 8554, 'loss/train': 1.6104270219802856} 08/30/2021 14:42:16 - INFO - __main__ - Step 8556: {'lr': 0.0004975838109131509, 'samples': 1642752, 'steps': 8555, 'loss/train': 1.7505496740341187} 08/30/2021 14:42:16 - INFO - __main__ - Step 8557: {'lr': 0.0004975830748422499, 'samples': 1642944, 'steps': 8556, 'loss/train': 1.9093105792999268} 08/30/2021 14:42:16 - INFO - __main__ - Step 8558: {'lr': 0.0004975823386597918, 'samples': 1643136, 'steps': 8557, 'loss/train': 1.6590849161148071} 08/30/2021 14:42:18 - INFO - __main__ - Step 8559: {'lr': 0.000497581602365777, 'samples': 1643328, 'steps': 8558, 'loss/train': 2.215555191040039} 08/30/2021 14:42:18 - INFO - __main__ - Step 8560: {'lr': 0.0004975808659602058, 'samples': 1643520, 'steps': 8559, 'loss/train': 2.3118512630462646} 08/30/2021 14:42:18 - INFO - __main__ - Step 8561: {'lr': 0.0004975801294430784, 'samples': 1643712, 'steps': 8560, 'loss/train': 2.343376398086548} 08/30/2021 14:42:19 - INFO - __main__ - Step 8562: {'lr': 0.0004975793928143952, 'samples': 1643904, 'steps': 8561, 'loss/train': 2.2122883796691895} 08/30/2021 14:42:19 - INFO - __main__ - Step 8563: {'lr': 0.0004975786560741566, 'samples': 1644096, 'steps': 8562, 'loss/train': 3.140326499938965} 08/30/2021 14:42:21 - INFO - __main__ - Step 8564: {'lr': 0.0004975779192223629, 'samples': 1644288, 'steps': 8563, 'loss/train': 2.540897846221924} 08/30/2021 14:42:21 - INFO - __main__ - Step 8565: {'lr': 0.0004975771822590143, 'samples': 1644480, 'steps': 8564, 'loss/train': 1.8659827709197998} 08/30/2021 14:42:21 - INFO - __main__ - Step 8566: {'lr': 0.0004975764451841114, 'samples': 1644672, 'steps': 8565, 'loss/train': 2.5408880710601807} 08/30/2021 14:42:22 - INFO - __main__ - Step 8567: {'lr': 0.0004975757079976542, 'samples': 1644864, 'steps': 8566, 'loss/train': 2.0472939014434814} 08/30/2021 14:42:22 - INFO - __main__ - Step 8568: {'lr': 0.0004975749706996433, 'samples': 1645056, 'steps': 8567, 'loss/train': 2.1713831424713135} 08/30/2021 14:42:25 - INFO - __main__ - Step 8569: {'lr': 0.0004975742332900789, 'samples': 1645248, 'steps': 8568, 'loss/train': 2.100381374359131} 08/30/2021 14:42:25 - INFO - __main__ - Step 8570: {'lr': 0.0004975734957689614, 'samples': 1645440, 'steps': 8569, 'loss/train': 1.6959052085876465} 08/30/2021 14:42:26 - INFO - __main__ - Step 8571: {'lr': 0.0004975727581362911, 'samples': 1645632, 'steps': 8570, 'loss/train': 1.5239940881729126} 08/30/2021 14:42:26 - INFO - __main__ - Step 8572: {'lr': 0.0004975720203920683, 'samples': 1645824, 'steps': 8571, 'loss/train': 1.7015442848205566} 08/30/2021 14:42:26 - INFO - __main__ - Step 8573: {'lr': 0.0004975712825362934, 'samples': 1646016, 'steps': 8572, 'loss/train': 0.6614782214164734} 08/30/2021 14:42:27 - INFO - __main__ - Step 8574: {'lr': 0.0004975705445689668, 'samples': 1646208, 'steps': 8573, 'loss/train': 0.4116190969944} 08/30/2021 14:42:28 - INFO - __main__ - Step 8575: {'lr': 0.0004975698064900886, 'samples': 1646400, 'steps': 8574, 'loss/train': 2.1950554847717285} 08/30/2021 14:42:29 - INFO - __main__ - Step 8576: {'lr': 0.0004975690682996592, 'samples': 1646592, 'steps': 8575, 'loss/train': 2.125760316848755} 08/30/2021 14:42:29 - INFO - __main__ - Step 8577: {'lr': 0.0004975683299976791, 'samples': 1646784, 'steps': 8576, 'loss/train': 2.403451442718506} 08/30/2021 14:42:29 - INFO - __main__ - Step 8578: {'lr': 0.0004975675915841485, 'samples': 1646976, 'steps': 8577, 'loss/train': 1.502326488494873} 08/30/2021 14:42:30 - INFO - __main__ - Step 8579: {'lr': 0.0004975668530590679, 'samples': 1647168, 'steps': 8578, 'loss/train': 1.7058626413345337} 08/30/2021 14:42:31 - INFO - __main__ - Step 8580: {'lr': 0.0004975661144224374, 'samples': 1647360, 'steps': 8579, 'loss/train': 1.582490086555481} 08/30/2021 14:42:32 - INFO - __main__ - Step 8581: {'lr': 0.0004975653756742574, 'samples': 1647552, 'steps': 8580, 'loss/train': 1.988918662071228} 08/30/2021 14:42:32 - INFO - __main__ - Step 8582: {'lr': 0.0004975646368145282, 'samples': 1647744, 'steps': 8581, 'loss/train': 2.1653411388397217} 08/30/2021 14:42:32 - INFO - __main__ - Step 8583: {'lr': 0.0004975638978432503, 'samples': 1647936, 'steps': 8582, 'loss/train': 1.8184610605239868} 08/30/2021 14:42:33 - INFO - __main__ - Step 8584: {'lr': 0.0004975631587604239, 'samples': 1648128, 'steps': 8583, 'loss/train': 1.9685587882995605} 08/30/2021 14:42:34 - INFO - __main__ - Step 8585: {'lr': 0.0004975624195660494, 'samples': 1648320, 'steps': 8584, 'loss/train': 1.4592111110687256} 08/30/2021 14:42:34 - INFO - __main__ - Step 8586: {'lr': 0.0004975616802601271, 'samples': 1648512, 'steps': 8585, 'loss/train': 2.1038765907287598} 08/30/2021 14:42:35 - INFO - __main__ - Step 8587: {'lr': 0.0004975609408426572, 'samples': 1648704, 'steps': 8586, 'loss/train': 2.09875750541687} 08/30/2021 14:42:35 - INFO - __main__ - Step 8588: {'lr': 0.0004975602013136403, 'samples': 1648896, 'steps': 8587, 'loss/train': 2.227600574493408} 08/30/2021 14:42:36 - INFO - __main__ - Step 8589: {'lr': 0.0004975594616730766, 'samples': 1649088, 'steps': 8588, 'loss/train': 2.5306458473205566} 08/30/2021 14:42:37 - INFO - __main__ - Step 8590: {'lr': 0.0004975587219209663, 'samples': 1649280, 'steps': 8589, 'loss/train': 1.9463310241699219} 08/30/2021 14:42:38 - INFO - __main__ - Step 8591: {'lr': 0.0004975579820573099, 'samples': 1649472, 'steps': 8590, 'loss/train': 2.1328811645507812} 08/30/2021 14:42:38 - INFO - __main__ - Step 8592: {'lr': 0.0004975572420821078, 'samples': 1649664, 'steps': 8591, 'loss/train': 1.6399412155151367} 08/30/2021 14:42:38 - INFO - __main__ - Step 8593: {'lr': 0.0004975565019953601, 'samples': 1649856, 'steps': 8592, 'loss/train': 2.179776668548584} 08/30/2021 14:42:39 - INFO - __main__ - Step 8594: {'lr': 0.0004975557617970673, 'samples': 1650048, 'steps': 8593, 'loss/train': 2.4166452884674072} 08/30/2021 14:42:40 - INFO - __main__ - Step 8595: {'lr': 0.0004975550214872296, 'samples': 1650240, 'steps': 8594, 'loss/train': 1.673804759979248} 08/30/2021 14:42:41 - INFO - __main__ - Step 8596: {'lr': 0.0004975542810658476, 'samples': 1650432, 'steps': 8595, 'loss/train': 2.1727705001831055} 08/30/2021 14:42:41 - INFO - __main__ - Step 8597: {'lr': 0.0004975535405329213, 'samples': 1650624, 'steps': 8596, 'loss/train': 1.2749512195587158} 08/30/2021 14:42:41 - INFO - __main__ - Step 8598: {'lr': 0.0004975527998884513, 'samples': 1650816, 'steps': 8597, 'loss/train': 1.899662733078003} 08/30/2021 14:42:42 - INFO - __main__ - Step 8599: {'lr': 0.0004975520591324378, 'samples': 1651008, 'steps': 8598, 'loss/train': 1.7861813306808472} 08/30/2021 14:42:42 - INFO - __main__ - Step 8600: {'lr': 0.0004975513182648812, 'samples': 1651200, 'steps': 8599, 'loss/train': 0.19180971384048462} 08/30/2021 14:42:43 - INFO - __main__ - Step 8601: {'lr': 0.0004975505772857818, 'samples': 1651392, 'steps': 8600, 'loss/train': 1.532994270324707} 08/30/2021 14:42:44 - INFO - __main__ - Step 8602: {'lr': 0.0004975498361951398, 'samples': 1651584, 'steps': 8601, 'loss/train': 1.1918660402297974} 08/30/2021 14:42:44 - INFO - __main__ - Step 8603: {'lr': 0.0004975490949929558, 'samples': 1651776, 'steps': 8602, 'loss/train': 2.378145933151245} 08/30/2021 14:42:45 - INFO - __main__ - Step 8604: {'lr': 0.00049754835367923, 'samples': 1651968, 'steps': 8603, 'loss/train': 2.563058853149414} 08/30/2021 14:42:45 - INFO - __main__ - Step 8605: {'lr': 0.0004975476122539627, 'samples': 1652160, 'steps': 8604, 'loss/train': 1.4181443452835083} 08/30/2021 14:42:46 - INFO - __main__ - Step 8606: {'lr': 0.0004975468707171542, 'samples': 1652352, 'steps': 8605, 'loss/train': 3.0092220306396484} 08/30/2021 14:42:47 - INFO - __main__ - Step 8607: {'lr': 0.000497546129068805, 'samples': 1652544, 'steps': 8606, 'loss/train': 2.0059804916381836} 08/30/2021 14:42:47 - INFO - __main__ - Step 8608: {'lr': 0.0004975453873089153, 'samples': 1652736, 'steps': 8607, 'loss/train': 1.853925108909607} 08/30/2021 14:42:48 - INFO - __main__ - Step 8609: {'lr': 0.0004975446454374854, 'samples': 1652928, 'steps': 8608, 'loss/train': 1.9299236536026} 08/30/2021 14:42:48 - INFO - __main__ - Step 8610: {'lr': 0.0004975439034545158, 'samples': 1653120, 'steps': 8609, 'loss/train': 1.9878500699996948} 08/30/2021 14:42:49 - INFO - __main__ - Step 8611: {'lr': 0.0004975431613600067, 'samples': 1653312, 'steps': 8610, 'loss/train': 1.9883729219436646} 08/30/2021 14:42:50 - INFO - __main__ - Step 8612: {'lr': 0.0004975424191539585, 'samples': 1653504, 'steps': 8611, 'loss/train': 1.722756266593933} 08/30/2021 14:42:50 - INFO - __main__ - Step 8613: {'lr': 0.0004975416768363715, 'samples': 1653696, 'steps': 8612, 'loss/train': 1.7571719884872437} 08/30/2021 14:42:51 - INFO - __main__ - Step 8614: {'lr': 0.0004975409344072459, 'samples': 1653888, 'steps': 8613, 'loss/train': 1.6866161823272705} 08/30/2021 14:42:51 - INFO - __main__ - Step 8615: {'lr': 0.0004975401918665823, 'samples': 1654080, 'steps': 8614, 'loss/train': 2.357454538345337} 08/30/2021 14:42:52 - INFO - __main__ - Step 8616: {'lr': 0.0004975394492143808, 'samples': 1654272, 'steps': 8615, 'loss/train': 2.7173142433166504} 08/30/2021 14:42:53 - INFO - __main__ - Step 8617: {'lr': 0.0004975387064506421, 'samples': 1654464, 'steps': 8616, 'loss/train': 1.6634690761566162} 08/30/2021 14:42:53 - INFO - __main__ - Step 8618: {'lr': 0.000497537963575366, 'samples': 1654656, 'steps': 8617, 'loss/train': 2.087928056716919} 08/30/2021 14:42:54 - INFO - __main__ - Step 8619: {'lr': 0.0004975372205885533, 'samples': 1654848, 'steps': 8618, 'loss/train': 1.3401358127593994} 08/30/2021 14:42:54 - INFO - __main__ - Step 8620: {'lr': 0.0004975364774902041, 'samples': 1655040, 'steps': 8619, 'loss/train': 1.4630038738250732} 08/30/2021 14:42:56 - INFO - __main__ - Step 8621: {'lr': 0.0004975357342803187, 'samples': 1655232, 'steps': 8620, 'loss/train': 1.9419286251068115} 08/30/2021 14:42:57 - INFO - __main__ - Step 8622: {'lr': 0.0004975349909588976, 'samples': 1655424, 'steps': 8621, 'loss/train': 2.0865018367767334} 08/30/2021 14:42:57 - INFO - __main__ - Step 8623: {'lr': 0.000497534247525941, 'samples': 1655616, 'steps': 8622, 'loss/train': 2.239246129989624} 08/30/2021 14:42:57 - INFO - __main__ - Step 8624: {'lr': 0.0004975335039814493, 'samples': 1655808, 'steps': 8623, 'loss/train': 2.177828788757324} 08/30/2021 14:42:58 - INFO - __main__ - Step 8625: {'lr': 0.0004975327603254229, 'samples': 1656000, 'steps': 8624, 'loss/train': 2.105170249938965} 08/30/2021 14:42:58 - INFO - __main__ - Step 8626: {'lr': 0.000497532016557862, 'samples': 1656192, 'steps': 8625, 'loss/train': 2.0102388858795166} 08/30/2021 14:43:00 - INFO - __main__ - Step 8627: {'lr': 0.0004975312726787671, 'samples': 1656384, 'steps': 8626, 'loss/train': 1.3716613054275513} 08/30/2021 14:43:00 - INFO - __main__ - Step 8628: {'lr': 0.0004975305286881383, 'samples': 1656576, 'steps': 8627, 'loss/train': 1.680583119392395} 08/30/2021 14:43:01 - INFO - __main__ - Step 8629: {'lr': 0.0004975297845859761, 'samples': 1656768, 'steps': 8628, 'loss/train': 1.1578835248947144} 08/30/2021 14:43:01 - INFO - __main__ - Step 8630: {'lr': 0.0004975290403722807, 'samples': 1656960, 'steps': 8629, 'loss/train': 4.564239501953125} 08/30/2021 14:43:01 - INFO - __main__ - Step 8631: {'lr': 0.0004975282960470527, 'samples': 1657152, 'steps': 8630, 'loss/train': 2.5652618408203125} 08/30/2021 14:43:03 - INFO - __main__ - Step 8632: {'lr': 0.0004975275516102922, 'samples': 1657344, 'steps': 8631, 'loss/train': 1.707463026046753} 08/30/2021 14:43:03 - INFO - __main__ - Step 8633: {'lr': 0.0004975268070619996, 'samples': 1657536, 'steps': 8632, 'loss/train': 1.591426134109497} 08/30/2021 14:43:04 - INFO - __main__ - Step 8634: {'lr': 0.0004975260624021752, 'samples': 1657728, 'steps': 8633, 'loss/train': 1.105669617652893} 08/30/2021 14:43:04 - INFO - __main__ - Step 8635: {'lr': 0.0004975253176308194, 'samples': 1657920, 'steps': 8634, 'loss/train': 2.1665873527526855} 08/30/2021 14:43:04 - INFO - __main__ - Step 8636: {'lr': 0.0004975245727479325, 'samples': 1658112, 'steps': 8635, 'loss/train': 1.5017696619033813} 08/30/2021 14:43:06 - INFO - __main__ - Step 8637: {'lr': 0.0004975238277535149, 'samples': 1658304, 'steps': 8636, 'loss/train': 2.1164751052856445} 08/30/2021 14:43:06 - INFO - __main__ - Step 8638: {'lr': 0.0004975230826475669, 'samples': 1658496, 'steps': 8637, 'loss/train': 1.8092982769012451} 08/30/2021 14:43:07 - INFO - __main__ - Step 8639: {'lr': 0.0004975223374300887, 'samples': 1658688, 'steps': 8638, 'loss/train': 1.9563103914260864} 08/30/2021 14:43:07 - INFO - __main__ - Step 8640: {'lr': 0.0004975215921010808, 'samples': 1658880, 'steps': 8639, 'loss/train': 2.1875200271606445} 08/30/2021 14:43:07 - INFO - __main__ - Step 8641: {'lr': 0.0004975208466605435, 'samples': 1659072, 'steps': 8640, 'loss/train': 2.4847347736358643} 08/30/2021 14:43:08 - INFO - __main__ - Step 8642: {'lr': 0.0004975201011084773, 'samples': 1659264, 'steps': 8641, 'loss/train': 0.8208606839179993} 08/30/2021 14:43:09 - INFO - __main__ - Step 8643: {'lr': 0.0004975193554448821, 'samples': 1659456, 'steps': 8642, 'loss/train': 2.074352741241455} 08/30/2021 14:43:10 - INFO - __main__ - Step 8644: {'lr': 0.0004975186096697585, 'samples': 1659648, 'steps': 8643, 'loss/train': 1.1441607475280762} 08/30/2021 14:43:10 - INFO - __main__ - Step 8645: {'lr': 0.000497517863783107, 'samples': 1659840, 'steps': 8644, 'loss/train': 2.4295613765716553} 08/30/2021 14:43:10 - INFO - __main__ - Step 8646: {'lr': 0.0004975171177849277, 'samples': 1660032, 'steps': 8645, 'loss/train': 1.7394776344299316} 08/30/2021 14:43:11 - INFO - __main__ - Step 8647: {'lr': 0.000497516371675221, 'samples': 1660224, 'steps': 8646, 'loss/train': 1.3165230751037598} 08/30/2021 14:43:12 - INFO - __main__ - Step 8648: {'lr': 0.0004975156254539873, 'samples': 1660416, 'steps': 8647, 'loss/train': 1.8042141199111938} 08/30/2021 14:43:13 - INFO - __main__ - Step 8649: {'lr': 0.0004975148791212269, 'samples': 1660608, 'steps': 8648, 'loss/train': 1.4219919443130493} 08/30/2021 14:43:13 - INFO - __main__ - Step 8650: {'lr': 0.00049751413267694, 'samples': 1660800, 'steps': 8649, 'loss/train': 1.4245812892913818} 08/30/2021 14:43:14 - INFO - __main__ - Step 8651: {'lr': 0.000497513386121127, 'samples': 1660992, 'steps': 8650, 'loss/train': 1.7138100862503052} 08/30/2021 14:43:14 - INFO - __main__ - Step 8652: {'lr': 0.0004975126394537884, 'samples': 1661184, 'steps': 8651, 'loss/train': 2.302199363708496} 08/30/2021 14:43:16 - INFO - __main__ - Step 8653: {'lr': 0.0004975118926749245, 'samples': 1661376, 'steps': 8652, 'loss/train': 1.9023785591125488} 08/30/2021 14:43:16 - INFO - __main__ - Step 8654: {'lr': 0.0004975111457845354, 'samples': 1661568, 'steps': 8653, 'loss/train': 2.1786036491394043} 08/30/2021 14:43:16 - INFO - __main__ - Step 8655: {'lr': 0.0004975103987826217, 'samples': 1661760, 'steps': 8654, 'loss/train': 1.6991146802902222} 08/30/2021 14:43:17 - INFO - __main__ - Step 8656: {'lr': 0.0004975096516691836, 'samples': 1661952, 'steps': 8655, 'loss/train': 1.50784432888031} 08/30/2021 14:43:17 - INFO - __main__ - Step 8657: {'lr': 0.0004975089044442215, 'samples': 1662144, 'steps': 8656, 'loss/train': 1.257446527481079} 08/30/2021 14:43:19 - INFO - __main__ - Step 8658: {'lr': 0.0004975081571077357, 'samples': 1662336, 'steps': 8657, 'loss/train': 2.638295888900757} 08/30/2021 14:43:19 - INFO - __main__ - Step 8659: {'lr': 0.0004975074096597265, 'samples': 1662528, 'steps': 8658, 'loss/train': 2.5325398445129395} 08/30/2021 14:43:19 - INFO - __main__ - Step 8660: {'lr': 0.0004975066621001943, 'samples': 1662720, 'steps': 8659, 'loss/train': 2.105074167251587} 08/30/2021 14:43:20 - INFO - __main__ - Step 8661: {'lr': 0.0004975059144291394, 'samples': 1662912, 'steps': 8660, 'loss/train': 2.0656898021698} 08/30/2021 14:43:20 - INFO - __main__ - Step 8662: {'lr': 0.0004975051666465622, 'samples': 1663104, 'steps': 8661, 'loss/train': 1.915766954421997} 08/30/2021 14:43:22 - INFO - __main__ - Step 8663: {'lr': 0.0004975044187524629, 'samples': 1663296, 'steps': 8662, 'loss/train': 1.1128897666931152} 08/30/2021 14:43:22 - INFO - __main__ - Step 8664: {'lr': 0.000497503670746842, 'samples': 1663488, 'steps': 8663, 'loss/train': 2.4669487476348877} 08/30/2021 14:43:22 - INFO - __main__ - Step 8665: {'lr': 0.0004975029226296998, 'samples': 1663680, 'steps': 8664, 'loss/train': 1.8786349296569824} 08/30/2021 14:43:23 - INFO - __main__ - Step 8666: {'lr': 0.0004975021744010365, 'samples': 1663872, 'steps': 8665, 'loss/train': 1.954643964767456} 08/30/2021 14:43:23 - INFO - __main__ - Step 8667: {'lr': 0.0004975014260608527, 'samples': 1664064, 'steps': 8666, 'loss/train': 2.062811851501465} 08/30/2021 14:43:24 - INFO - __main__ - Step 8668: {'lr': 0.0004975006776091484, 'samples': 1664256, 'steps': 8667, 'loss/train': 1.7372324466705322} 08/30/2021 14:43:25 - INFO - __main__ - Step 8669: {'lr': 0.0004974999290459243, 'samples': 1664448, 'steps': 8668, 'loss/train': 1.4187322854995728} 08/30/2021 14:43:25 - INFO - __main__ - Step 8670: {'lr': 0.0004974991803711803, 'samples': 1664640, 'steps': 8669, 'loss/train': 2.0661065578460693} 08/30/2021 14:43:26 - INFO - __main__ - Step 8671: {'lr': 0.0004974984315849172, 'samples': 1664832, 'steps': 8670, 'loss/train': 2.532565116882324} 08/30/2021 14:43:26 - INFO - __main__ - Step 8672: {'lr': 0.000497497682687135, 'samples': 1665024, 'steps': 8671, 'loss/train': 2.3772478103637695} 08/30/2021 14:43:27 - INFO - __main__ - Step 8673: {'lr': 0.0004974969336778343, 'samples': 1665216, 'steps': 8672, 'loss/train': 2.5523412227630615} 08/30/2021 14:43:28 - INFO - __main__ - Step 8674: {'lr': 0.0004974961845570152, 'samples': 1665408, 'steps': 8673, 'loss/train': 2.1624512672424316} 08/30/2021 14:43:28 - INFO - __main__ - Step 8675: {'lr': 0.0004974954353246781, 'samples': 1665600, 'steps': 8674, 'loss/train': 1.8108201026916504} 08/30/2021 14:43:29 - INFO - __main__ - Step 8676: {'lr': 0.0004974946859808235, 'samples': 1665792, 'steps': 8675, 'loss/train': 2.1599326133728027} 08/30/2021 14:43:29 - INFO - __main__ - Step 8677: {'lr': 0.0004974939365254515, 'samples': 1665984, 'steps': 8676, 'loss/train': 1.6962110996246338} 08/30/2021 14:43:31 - INFO - __main__ - Step 8678: {'lr': 0.0004974931869585626, 'samples': 1666176, 'steps': 8677, 'loss/train': 2.2996740341186523} 08/30/2021 14:43:31 - INFO - __main__ - Step 8679: {'lr': 0.0004974924372801572, 'samples': 1666368, 'steps': 8678, 'loss/train': 1.165061116218567} 08/30/2021 14:43:32 - INFO - __main__ - Step 8680: {'lr': 0.0004974916874902353, 'samples': 1666560, 'steps': 8679, 'loss/train': 1.9003016948699951} 08/30/2021 14:43:32 - INFO - __main__ - Step 8681: {'lr': 0.0004974909375887976, 'samples': 1666752, 'steps': 8680, 'loss/train': 1.6566135883331299} 08/30/2021 14:43:32 - INFO - __main__ - Step 8682: {'lr': 0.0004974901875758444, 'samples': 1666944, 'steps': 8681, 'loss/train': 1.013210654258728} 08/30/2021 14:43:33 - INFO - __main__ - Step 8683: {'lr': 0.0004974894374513757, 'samples': 1667136, 'steps': 8682, 'loss/train': 1.8741066455841064} 08/30/2021 14:43:34 - INFO - __main__ - Step 8684: {'lr': 0.0004974886872153922, 'samples': 1667328, 'steps': 8683, 'loss/train': 1.609816312789917} 08/30/2021 14:43:35 - INFO - __main__ - Step 8685: {'lr': 0.0004974879368678942, 'samples': 1667520, 'steps': 8684, 'loss/train': 1.2252821922302246} 08/30/2021 14:43:35 - INFO - __main__ - Step 8686: {'lr': 0.0004974871864088818, 'samples': 1667712, 'steps': 8685, 'loss/train': 0.8664953112602234} 08/30/2021 14:43:36 - INFO - __main__ - Step 8687: {'lr': 0.0004974864358383555, 'samples': 1667904, 'steps': 8686, 'loss/train': 1.586924433708191} 08/30/2021 14:43:36 - INFO - __main__ - Step 8688: {'lr': 0.0004974856851563158, 'samples': 1668096, 'steps': 8687, 'loss/train': 2.1468544006347656} 08/30/2021 14:43:36 - INFO - __main__ - Step 8689: {'lr': 0.0004974849343627628, 'samples': 1668288, 'steps': 8688, 'loss/train': 3.491004467010498} 08/30/2021 14:43:38 - INFO - __main__ - Step 8690: {'lr': 0.0004974841834576968, 'samples': 1668480, 'steps': 8689, 'loss/train': 2.16768217086792} 08/30/2021 14:43:38 - INFO - __main__ - Step 8691: {'lr': 0.0004974834324411183, 'samples': 1668672, 'steps': 8690, 'loss/train': 2.1313111782073975} 08/30/2021 14:43:39 - INFO - __main__ - Step 8692: {'lr': 0.0004974826813130276, 'samples': 1668864, 'steps': 8691, 'loss/train': 2.2426517009735107} 08/30/2021 14:43:39 - INFO - __main__ - Step 8693: {'lr': 0.000497481930073425, 'samples': 1669056, 'steps': 8692, 'loss/train': 1.9979678392410278} 08/30/2021 14:43:39 - INFO - __main__ - Step 8694: {'lr': 0.000497481178722311, 'samples': 1669248, 'steps': 8693, 'loss/train': 1.9313017129898071} 08/30/2021 14:43:41 - INFO - __main__ - Step 8695: {'lr': 0.0004974804272596857, 'samples': 1669440, 'steps': 8694, 'loss/train': 1.756946325302124} 08/30/2021 14:43:42 - INFO - __main__ - Step 8696: {'lr': 0.0004974796756855494, 'samples': 1669632, 'steps': 8695, 'loss/train': 1.9956234693527222} 08/30/2021 14:43:42 - INFO - __main__ - Step 8697: {'lr': 0.0004974789239999027, 'samples': 1669824, 'steps': 8696, 'loss/train': 1.2921825647354126} 08/30/2021 14:43:42 - INFO - __main__ - Step 8698: {'lr': 0.0004974781722027459, 'samples': 1670016, 'steps': 8697, 'loss/train': 1.7339524030685425} 08/30/2021 14:43:43 - INFO - __main__ - Step 8699: {'lr': 0.0004974774202940791, 'samples': 1670208, 'steps': 8698, 'loss/train': 2.2512190341949463} 08/30/2021 14:43:43 - INFO - __main__ - Step 8700: {'lr': 0.000497476668273903, 'samples': 1670400, 'steps': 8699, 'loss/train': 1.6991277933120728} 08/30/2021 14:43:44 - INFO - __main__ - Step 8701: {'lr': 0.0004974759161422175, 'samples': 1670592, 'steps': 8700, 'loss/train': 2.36647367477417} 08/30/2021 14:43:45 - INFO - __main__ - Step 8702: {'lr': 0.0004974751638990233, 'samples': 1670784, 'steps': 8701, 'loss/train': 2.3939263820648193} 08/30/2021 14:43:45 - INFO - __main__ - Step 8703: {'lr': 0.0004974744115443206, 'samples': 1670976, 'steps': 8702, 'loss/train': 1.317129373550415} 08/30/2021 14:43:46 - INFO - __main__ - Step 8704: {'lr': 0.0004974736590781097, 'samples': 1671168, 'steps': 8703, 'loss/train': 0.5579120516777039} 08/30/2021 14:43:46 - INFO - __main__ - Step 8705: {'lr': 0.000497472906500391, 'samples': 1671360, 'steps': 8704, 'loss/train': 2.1611592769622803} 08/30/2021 14:43:48 - INFO - __main__ - Step 8706: {'lr': 0.0004974721538111649, 'samples': 1671552, 'steps': 8705, 'loss/train': 2.159956216812134} 08/30/2021 14:43:48 - INFO - __main__ - Step 8707: {'lr': 0.0004974714010104315, 'samples': 1671744, 'steps': 8706, 'loss/train': 1.906781554222107} 08/30/2021 14:43:49 - INFO - __main__ - Step 8708: {'lr': 0.0004974706480981914, 'samples': 1671936, 'steps': 8707, 'loss/train': 2.110795736312866} 08/30/2021 14:43:49 - INFO - __main__ - Step 8709: {'lr': 0.0004974698950744449, 'samples': 1672128, 'steps': 8708, 'loss/train': 2.0629167556762695} 08/30/2021 14:43:49 - INFO - __main__ - Step 8710: {'lr': 0.0004974691419391922, 'samples': 1672320, 'steps': 8709, 'loss/train': 1.7386436462402344} 08/30/2021 14:43:51 - INFO - __main__ - Step 8711: {'lr': 0.0004974683886924339, 'samples': 1672512, 'steps': 8710, 'loss/train': 4.081793308258057} 08/30/2021 14:43:51 - INFO - __main__ - Step 8712: {'lr': 0.00049746763533417, 'samples': 1672704, 'steps': 8711, 'loss/train': 2.1162335872650146} 08/30/2021 14:43:52 - INFO - __main__ - Step 8713: {'lr': 0.000497466881864401, 'samples': 1672896, 'steps': 8712, 'loss/train': 0.8779681324958801} 08/30/2021 14:43:52 - INFO - __main__ - Step 8714: {'lr': 0.0004974661282831272, 'samples': 1673088, 'steps': 8713, 'loss/train': 2.3679370880126953} 08/30/2021 14:43:52 - INFO - __main__ - Step 8715: {'lr': 0.0004974653745903491, 'samples': 1673280, 'steps': 8714, 'loss/train': 1.9404504299163818} 08/30/2021 14:43:54 - INFO - __main__ - Step 8716: {'lr': 0.0004974646207860668, 'samples': 1673472, 'steps': 8715, 'loss/train': 1.8773442506790161} 08/30/2021 14:43:54 - INFO - __main__ - Step 8717: {'lr': 0.0004974638668702809, 'samples': 1673664, 'steps': 8716, 'loss/train': 2.295478343963623} 08/30/2021 14:43:55 - INFO - __main__ - Step 8718: {'lr': 0.0004974631128429915, 'samples': 1673856, 'steps': 8717, 'loss/train': 1.716551423072815} 08/30/2021 14:43:55 - INFO - __main__ - Step 8719: {'lr': 0.0004974623587041991, 'samples': 1674048, 'steps': 8718, 'loss/train': 2.1509275436401367} 08/30/2021 14:43:55 - INFO - __main__ - Step 8720: {'lr': 0.000497461604453904, 'samples': 1674240, 'steps': 8719, 'loss/train': 1.9106303453445435} 08/30/2021 14:43:56 - INFO - __main__ - Step 8721: {'lr': 0.0004974608500921064, 'samples': 1674432, 'steps': 8720, 'loss/train': 2.128234624862671} 08/30/2021 14:43:57 - INFO - __main__ - Step 8722: {'lr': 0.0004974600956188068, 'samples': 1674624, 'steps': 8721, 'loss/train': 2.0519943237304688} 08/30/2021 14:43:58 - INFO - __main__ - Step 8723: {'lr': 0.0004974593410340056, 'samples': 1674816, 'steps': 8722, 'loss/train': 2.685260534286499} 08/30/2021 14:43:58 - INFO - __main__ - Step 8724: {'lr': 0.000497458586337703, 'samples': 1675008, 'steps': 8723, 'loss/train': 1.4179587364196777} 08/30/2021 14:43:59 - INFO - __main__ - Step 8725: {'lr': 0.0004974578315298993, 'samples': 1675200, 'steps': 8724, 'loss/train': 1.850721001625061} 08/30/2021 14:43:59 - INFO - __main__ - Step 8726: {'lr': 0.000497457076610595, 'samples': 1675392, 'steps': 8725, 'loss/train': 1.9255950450897217} 08/30/2021 14:44:00 - INFO - __main__ - Step 8727: {'lr': 0.0004974563215797903, 'samples': 1675584, 'steps': 8726, 'loss/train': 1.7172802686691284} 08/30/2021 14:44:01 - INFO - __main__ - Step 8728: {'lr': 0.0004974555664374857, 'samples': 1675776, 'steps': 8727, 'loss/train': 1.844247817993164} 08/30/2021 14:44:01 - INFO - __main__ - Step 8729: {'lr': 0.0004974548111836812, 'samples': 1675968, 'steps': 8728, 'loss/train': 1.299993634223938} 08/30/2021 14:44:02 - INFO - __main__ - Step 8730: {'lr': 0.0004974540558183776, 'samples': 1676160, 'steps': 8729, 'loss/train': 1.2942192554473877} 08/30/2021 14:44:02 - INFO - __main__ - Step 8731: {'lr': 0.0004974533003415751, 'samples': 1676352, 'steps': 8730, 'loss/train': 2.199471950531006} 08/30/2021 14:44:04 - INFO - __main__ - Step 8732: {'lr': 0.0004974525447532737, 'samples': 1676544, 'steps': 8731, 'loss/train': 1.7526211738586426} 08/30/2021 14:44:04 - INFO - __main__ - Step 8733: {'lr': 0.0004974517890534742, 'samples': 1676736, 'steps': 8732, 'loss/train': 0.8656116127967834} 08/30/2021 14:44:05 - INFO - __main__ - Step 8734: {'lr': 0.0004974510332421767, 'samples': 1676928, 'steps': 8733, 'loss/train': 0.3058996796607971} 08/30/2021 14:44:05 - INFO - __main__ - Step 8735: {'lr': 0.0004974502773193815, 'samples': 1677120, 'steps': 8734, 'loss/train': 1.2710117101669312} 08/30/2021 14:44:05 - INFO - __main__ - Step 8736: {'lr': 0.0004974495212850892, 'samples': 1677312, 'steps': 8735, 'loss/train': 1.5743685960769653} 08/30/2021 14:44:06 - INFO - __main__ - Step 8737: {'lr': 0.0004974487651392998, 'samples': 1677504, 'steps': 8736, 'loss/train': 1.848976492881775} 08/30/2021 14:44:08 - INFO - __main__ - Step 8738: {'lr': 0.0004974480088820139, 'samples': 1677696, 'steps': 8737, 'loss/train': 1.7711901664733887} 08/30/2021 14:44:08 - INFO - __main__ - Step 8739: {'lr': 0.0004974472525132316, 'samples': 1677888, 'steps': 8738, 'loss/train': 2.0195536613464355} 08/30/2021 14:44:09 - INFO - __main__ - Step 8740: {'lr': 0.0004974464960329536, 'samples': 1678080, 'steps': 8739, 'loss/train': 1.9348527193069458} 08/30/2021 14:44:09 - INFO - __main__ - Step 8741: {'lr': 0.0004974457394411798, 'samples': 1678272, 'steps': 8740, 'loss/train': 2.030661106109619} 08/30/2021 14:44:09 - INFO - __main__ - Step 8742: {'lr': 0.0004974449827379109, 'samples': 1678464, 'steps': 8741, 'loss/train': 2.020113468170166} 08/30/2021 14:44:11 - INFO - __main__ - Step 8743: {'lr': 0.000497444225923147, 'samples': 1678656, 'steps': 8742, 'loss/train': 2.2659518718719482} 08/30/2021 14:44:11 - INFO - __main__ - Step 8744: {'lr': 0.0004974434689968887, 'samples': 1678848, 'steps': 8743, 'loss/train': 2.0322535037994385} 08/30/2021 14:44:12 - INFO - __main__ - Step 8745: {'lr': 0.0004974427119591361, 'samples': 1679040, 'steps': 8744, 'loss/train': 2.128535747528076} 08/30/2021 14:44:12 - INFO - __main__ - Step 8746: {'lr': 0.0004974419548098897, 'samples': 1679232, 'steps': 8745, 'loss/train': 0.27330482006073} 08/30/2021 14:44:12 - INFO - __main__ - Step 8747: {'lr': 0.0004974411975491498, 'samples': 1679424, 'steps': 8746, 'loss/train': 1.9819375276565552} 08/30/2021 14:44:14 - INFO - __main__ - Step 8748: {'lr': 0.0004974404401769167, 'samples': 1679616, 'steps': 8747, 'loss/train': 1.8071480989456177} 08/30/2021 14:44:14 - INFO - __main__ - Step 8749: {'lr': 0.0004974396826931906, 'samples': 1679808, 'steps': 8748, 'loss/train': 1.9712427854537964} 08/30/2021 14:44:15 - INFO - __main__ - Step 8750: {'lr': 0.0004974389250979722, 'samples': 1680000, 'steps': 8749, 'loss/train': 2.3223397731781006} 08/30/2021 14:44:15 - INFO - __main__ - Step 8751: {'lr': 0.0004974381673912614, 'samples': 1680192, 'steps': 8750, 'loss/train': 1.570473551750183} 08/30/2021 14:44:15 - INFO - __main__ - Step 8752: {'lr': 0.000497437409573059, 'samples': 1680384, 'steps': 8751, 'loss/train': 1.8036528825759888} 08/30/2021 14:44:17 - INFO - __main__ - Step 8753: {'lr': 0.000497436651643365, 'samples': 1680576, 'steps': 8752, 'loss/train': 1.7375524044036865} 08/30/2021 14:44:17 - INFO - __main__ - Step 8754: {'lr': 0.00049743589360218, 'samples': 1680768, 'steps': 8753, 'loss/train': 1.3110918998718262} 08/30/2021 14:44:18 - INFO - __main__ - Step 8755: {'lr': 0.0004974351354495041, 'samples': 1680960, 'steps': 8754, 'loss/train': 1.7762739658355713} 08/30/2021 14:44:18 - INFO - __main__ - Step 8756: {'lr': 0.0004974343771853377, 'samples': 1681152, 'steps': 8755, 'loss/train': 2.0317671298980713} 08/30/2021 14:44:18 - INFO - __main__ - Step 8757: {'lr': 0.0004974336188096813, 'samples': 1681344, 'steps': 8756, 'loss/train': 1.98769211769104} 08/30/2021 14:44:20 - INFO - __main__ - Step 8758: {'lr': 0.0004974328603225351, 'samples': 1681536, 'steps': 8757, 'loss/train': 2.112428903579712} 08/30/2021 14:44:20 - INFO - __main__ - Step 8759: {'lr': 0.0004974321017238994, 'samples': 1681728, 'steps': 8758, 'loss/train': 2.0258026123046875} 08/30/2021 14:44:20 - INFO - __main__ - Step 8760: {'lr': 0.0004974313430137747, 'samples': 1681920, 'steps': 8759, 'loss/train': 2.1777615547180176} 08/30/2021 14:44:21 - INFO - __main__ - Step 8761: {'lr': 0.0004974305841921612, 'samples': 1682112, 'steps': 8760, 'loss/train': 1.7240231037139893} 08/30/2021 14:44:21 - INFO - __main__ - Step 8762: {'lr': 0.0004974298252590593, 'samples': 1682304, 'steps': 8761, 'loss/train': 2.205961227416992} 08/30/2021 14:44:23 - INFO - __main__ - Step 8763: {'lr': 0.0004974290662144694, 'samples': 1682496, 'steps': 8762, 'loss/train': 2.2492496967315674} 08/30/2021 14:44:23 - INFO - __main__ - Step 8764: {'lr': 0.0004974283070583917, 'samples': 1682688, 'steps': 8763, 'loss/train': 1.6165436506271362} 08/30/2021 14:44:23 - INFO - __main__ - Step 8765: {'lr': 0.0004974275477908266, 'samples': 1682880, 'steps': 8764, 'loss/train': 2.0821170806884766} 08/30/2021 14:44:24 - INFO - __main__ - Step 8766: {'lr': 0.0004974267884117746, 'samples': 1683072, 'steps': 8765, 'loss/train': 1.7335976362228394} 08/30/2021 14:44:24 - INFO - __main__ - Step 8767: {'lr': 0.0004974260289212358, 'samples': 1683264, 'steps': 8766, 'loss/train': 2.383117437362671} 08/30/2021 14:44:26 - INFO - __main__ - Step 8768: {'lr': 0.0004974252693192106, 'samples': 1683456, 'steps': 8767, 'loss/train': 2.205899715423584} 08/30/2021 14:44:26 - INFO - __main__ - Step 8769: {'lr': 0.0004974245096056995, 'samples': 1683648, 'steps': 8768, 'loss/train': 1.9440041780471802} 08/30/2021 14:44:27 - INFO - __main__ - Step 8770: {'lr': 0.0004974237497807027, 'samples': 1683840, 'steps': 8769, 'loss/train': 1.7581126689910889} 08/30/2021 14:44:27 - INFO - __main__ - Step 8771: {'lr': 0.0004974229898442207, 'samples': 1684032, 'steps': 8770, 'loss/train': 1.769744634628296} 08/30/2021 14:44:27 - INFO - __main__ - Step 8772: {'lr': 0.0004974222297962535, 'samples': 1684224, 'steps': 8771, 'loss/train': 1.9801572561264038} 08/30/2021 14:44:29 - INFO - __main__ - Step 8773: {'lr': 0.0004974214696368017, 'samples': 1684416, 'steps': 8772, 'loss/train': 2.896915912628174} 08/30/2021 14:44:29 - INFO - __main__ - Step 8774: {'lr': 0.0004974207093658657, 'samples': 1684608, 'steps': 8773, 'loss/train': 2.1361005306243896} 08/30/2021 14:44:30 - INFO - __main__ - Step 8775: {'lr': 0.0004974199489834457, 'samples': 1684800, 'steps': 8774, 'loss/train': 2.0194149017333984} 08/30/2021 14:44:30 - INFO - __main__ - Step 8776: {'lr': 0.0004974191884895421, 'samples': 1684992, 'steps': 8775, 'loss/train': 1.1998473405838013} 08/30/2021 14:44:30 - INFO - __main__ - Step 8777: {'lr': 0.0004974184278841552, 'samples': 1685184, 'steps': 8776, 'loss/train': 2.1794116497039795} 08/30/2021 14:44:32 - INFO - __main__ - Step 8778: {'lr': 0.0004974176671672854, 'samples': 1685376, 'steps': 8777, 'loss/train': 1.6326193809509277} 08/30/2021 14:44:32 - INFO - __main__ - Step 8779: {'lr': 0.000497416906338933, 'samples': 1685568, 'steps': 8778, 'loss/train': 1.7596262693405151} 08/30/2021 14:44:33 - INFO - __main__ - Step 8780: {'lr': 0.0004974161453990985, 'samples': 1685760, 'steps': 8779, 'loss/train': 1.9646741151809692} 08/30/2021 14:44:33 - INFO - __main__ - Step 8781: {'lr': 0.0004974153843477819, 'samples': 1685952, 'steps': 8780, 'loss/train': 2.227012872695923} 08/30/2021 14:44:33 - INFO - __main__ - Step 8782: {'lr': 0.0004974146231849838, 'samples': 1686144, 'steps': 8781, 'loss/train': 1.4969590902328491} 08/30/2021 14:44:34 - INFO - __main__ - Step 8783: {'lr': 0.0004974138619107046, 'samples': 1686336, 'steps': 8782, 'loss/train': 2.840508460998535} 08/30/2021 14:44:35 - INFO - __main__ - Step 8784: {'lr': 0.0004974131005249444, 'samples': 1686528, 'steps': 8783, 'loss/train': 1.302711009979248} 08/30/2021 14:44:36 - INFO - __main__ - Step 8785: {'lr': 0.0004974123390277037, 'samples': 1686720, 'steps': 8784, 'loss/train': 2.0307395458221436} 08/30/2021 14:44:36 - INFO - __main__ - Step 8786: {'lr': 0.0004974115774189829, 'samples': 1686912, 'steps': 8785, 'loss/train': 1.7665915489196777} 08/30/2021 14:44:36 - INFO - __main__ - Step 8787: {'lr': 0.0004974108156987822, 'samples': 1687104, 'steps': 8786, 'loss/train': 2.0021626949310303} 08/30/2021 14:44:37 - INFO - __main__ - Step 8788: {'lr': 0.000497410053867102, 'samples': 1687296, 'steps': 8787, 'loss/train': 2.2938144207000732} 08/30/2021 14:44:38 - INFO - __main__ - Step 8789: {'lr': 0.0004974092919239427, 'samples': 1687488, 'steps': 8788, 'loss/train': 2.082855224609375} 08/30/2021 14:44:39 - INFO - __main__ - Step 8790: {'lr': 0.0004974085298693045, 'samples': 1687680, 'steps': 8789, 'loss/train': 1.652678370475769} 08/30/2021 14:44:39 - INFO - __main__ - Step 8791: {'lr': 0.0004974077677031879, 'samples': 1687872, 'steps': 8790, 'loss/train': 2.036776065826416} 08/30/2021 14:44:40 - INFO - __main__ - Step 8792: {'lr': 0.0004974070054255932, 'samples': 1688064, 'steps': 8791, 'loss/train': 1.903337001800537} 08/30/2021 14:44:40 - INFO - __main__ - Step 8793: {'lr': 0.0004974062430365206, 'samples': 1688256, 'steps': 8792, 'loss/train': 1.8099795579910278} 08/30/2021 14:44:41 - INFO - __main__ - Step 8794: {'lr': 0.0004974054805359706, 'samples': 1688448, 'steps': 8793, 'loss/train': 1.4995594024658203} 08/30/2021 14:44:42 - INFO - __main__ - Step 8795: {'lr': 0.0004974047179239436, 'samples': 1688640, 'steps': 8794, 'loss/train': 1.7680137157440186} 08/30/2021 14:44:42 - INFO - __main__ - Step 8796: {'lr': 0.0004974039552004398, 'samples': 1688832, 'steps': 8795, 'loss/train': 2.226763963699341} 08/30/2021 14:44:43 - INFO - __main__ - Step 8797: {'lr': 0.0004974031923654596, 'samples': 1689024, 'steps': 8796, 'loss/train': 2.083266019821167} 08/30/2021 14:44:43 - INFO - __main__ - Step 8798: {'lr': 0.0004974024294190034, 'samples': 1689216, 'steps': 8797, 'loss/train': 2.0445456504821777} 08/30/2021 14:44:44 - INFO - __main__ - Step 8799: {'lr': 0.0004974016663610713, 'samples': 1689408, 'steps': 8798, 'loss/train': 1.7572485208511353} 08/30/2021 14:44:45 - INFO - __main__ - Step 8800: {'lr': 0.000497400903191664, 'samples': 1689600, 'steps': 8799, 'loss/train': 2.339501142501831} 08/30/2021 14:44:45 - INFO - __main__ - Step 8801: {'lr': 0.0004974001399107816, 'samples': 1689792, 'steps': 8800, 'loss/train': 1.8961145877838135} 08/30/2021 14:44:46 - INFO - __main__ - Step 8802: {'lr': 0.0004973993765184246, 'samples': 1689984, 'steps': 8801, 'loss/train': 2.1814019680023193} 08/30/2021 14:44:46 - INFO - __main__ - Step 8803: {'lr': 0.0004973986130145931, 'samples': 1690176, 'steps': 8802, 'loss/train': 1.8656163215637207} 08/30/2021 14:44:47 - INFO - __main__ - Step 8804: {'lr': 0.0004973978493992877, 'samples': 1690368, 'steps': 8803, 'loss/train': 2.049767255783081} 08/30/2021 14:44:48 - INFO - __main__ - Step 8805: {'lr': 0.0004973970856725086, 'samples': 1690560, 'steps': 8804, 'loss/train': 1.2457367181777954} 08/30/2021 14:44:48 - INFO - __main__ - Step 8806: {'lr': 0.0004973963218342563, 'samples': 1690752, 'steps': 8805, 'loss/train': 1.601210355758667} 08/30/2021 14:44:49 - INFO - __main__ - Step 8807: {'lr': 0.000497395557884531, 'samples': 1690944, 'steps': 8806, 'loss/train': 2.3677077293395996} 08/30/2021 14:44:49 - INFO - __main__ - Step 8808: {'lr': 0.000497394793823333, 'samples': 1691136, 'steps': 8807, 'loss/train': 1.7051234245300293} 08/30/2021 14:44:51 - INFO - __main__ - Step 8809: {'lr': 0.0004973940296506627, 'samples': 1691328, 'steps': 8808, 'loss/train': 2.554412364959717} 08/30/2021 14:44:51 - INFO - __main__ - Step 8810: {'lr': 0.0004973932653665206, 'samples': 1691520, 'steps': 8809, 'loss/train': 2.2054378986358643} 08/30/2021 14:44:52 - INFO - __main__ - Step 8811: {'lr': 0.0004973925009709068, 'samples': 1691712, 'steps': 8810, 'loss/train': 1.6742802858352661} 08/30/2021 14:44:52 - INFO - __main__ - Step 8812: {'lr': 0.0004973917364638218, 'samples': 1691904, 'steps': 8811, 'loss/train': 1.5483663082122803} 08/30/2021 14:44:52 - INFO - __main__ - Step 8813: {'lr': 0.0004973909718452659, 'samples': 1692096, 'steps': 8812, 'loss/train': 3.061603307723999} 08/30/2021 14:44:53 - INFO - __main__ - Step 8814: {'lr': 0.0004973902071152396, 'samples': 1692288, 'steps': 8813, 'loss/train': 2.0185563564300537} 08/30/2021 14:44:54 - INFO - __main__ - Step 8815: {'lr': 0.0004973894422737428, 'samples': 1692480, 'steps': 8814, 'loss/train': 1.6258715391159058} 08/30/2021 14:44:55 - INFO - __main__ - Step 8816: {'lr': 0.0004973886773207763, 'samples': 1692672, 'steps': 8815, 'loss/train': 2.1002321243286133} 08/30/2021 14:44:55 - INFO - __main__ - Step 8817: {'lr': 0.0004973879122563403, 'samples': 1692864, 'steps': 8816, 'loss/train': 2.069121837615967} 08/30/2021 14:44:55 - INFO - __main__ - Step 8818: {'lr': 0.000497387147080435, 'samples': 1693056, 'steps': 8817, 'loss/train': 1.8075968027114868} 08/30/2021 14:44:56 - INFO - __main__ - Step 8819: {'lr': 0.000497386381793061, 'samples': 1693248, 'steps': 8818, 'loss/train': 2.181338310241699} 08/30/2021 14:44:58 - INFO - __main__ - Step 8820: {'lr': 0.0004973856163942185, 'samples': 1693440, 'steps': 8819, 'loss/train': 1.995102047920227} 08/30/2021 14:44:58 - INFO - __main__ - Step 8821: {'lr': 0.0004973848508839077, 'samples': 1693632, 'steps': 8820, 'loss/train': 1.3736721277236938} 08/30/2021 14:44:59 - INFO - __main__ - Step 8822: {'lr': 0.0004973840852621293, 'samples': 1693824, 'steps': 8821, 'loss/train': 1.822910189628601} 08/30/2021 14:44:59 - INFO - __main__ - Step 8823: {'lr': 0.0004973833195288834, 'samples': 1694016, 'steps': 8822, 'loss/train': 2.0831680297851562} 08/30/2021 14:44:59 - INFO - __main__ - Step 8824: {'lr': 0.0004973825536841703, 'samples': 1694208, 'steps': 8823, 'loss/train': 1.275166392326355} 08/30/2021 14:45:01 - INFO - __main__ - Step 8825: {'lr': 0.0004973817877279906, 'samples': 1694400, 'steps': 8824, 'loss/train': 1.6611217260360718} 08/30/2021 14:45:01 - INFO - __main__ - Step 8826: {'lr': 0.0004973810216603443, 'samples': 1694592, 'steps': 8825, 'loss/train': 2.4509193897247314} 08/30/2021 14:45:01 - INFO - __main__ - Step 8827: {'lr': 0.000497380255481232, 'samples': 1694784, 'steps': 8826, 'loss/train': 2.011107921600342} 08/30/2021 14:45:02 - INFO - __main__ - Step 8828: {'lr': 0.000497379489190654, 'samples': 1694976, 'steps': 8827, 'loss/train': 2.1602694988250732} 08/30/2021 14:45:02 - INFO - __main__ - Step 8829: {'lr': 0.0004973787227886106, 'samples': 1695168, 'steps': 8828, 'loss/train': 2.0835742950439453} 08/30/2021 14:45:04 - INFO - __main__ - Step 8830: {'lr': 0.0004973779562751022, 'samples': 1695360, 'steps': 8829, 'loss/train': 1.5882266759872437} 08/30/2021 14:45:04 - INFO - __main__ - Step 8831: {'lr': 0.0004973771896501292, 'samples': 1695552, 'steps': 8830, 'loss/train': 2.53253436088562} 08/30/2021 14:45:04 - INFO - __main__ - Step 8832: {'lr': 0.0004973764229136917, 'samples': 1695744, 'steps': 8831, 'loss/train': 2.3874685764312744} 08/30/2021 14:45:05 - INFO - __main__ - Step 8833: {'lr': 0.0004973756560657901, 'samples': 1695936, 'steps': 8832, 'loss/train': 2.0688607692718506} 08/30/2021 14:45:05 - INFO - __main__ - Step 8834: {'lr': 0.0004973748891064251, 'samples': 1696128, 'steps': 8833, 'loss/train': 1.7769646644592285} 08/30/2021 14:45:06 - INFO - __main__ - Step 8835: {'lr': 0.0004973741220355967, 'samples': 1696320, 'steps': 8834, 'loss/train': 1.3691630363464355} 08/30/2021 14:45:07 - INFO - __main__ - Step 8836: {'lr': 0.0004973733548533052, 'samples': 1696512, 'steps': 8835, 'loss/train': 1.6993151903152466} 08/30/2021 14:45:07 - INFO - __main__ - Step 8837: {'lr': 0.0004973725875595513, 'samples': 1696704, 'steps': 8836, 'loss/train': 1.8598029613494873} 08/30/2021 14:45:08 - INFO - __main__ - Step 8838: {'lr': 0.000497371820154335, 'samples': 1696896, 'steps': 8837, 'loss/train': 1.9826390743255615} 08/30/2021 14:45:08 - INFO - __main__ - Step 8839: {'lr': 0.0004973710526376569, 'samples': 1697088, 'steps': 8838, 'loss/train': 1.9499104022979736} 08/30/2021 14:45:10 - INFO - __main__ - Step 8840: {'lr': 0.000497370285009517, 'samples': 1697280, 'steps': 8839, 'loss/train': 2.063833475112915} 08/30/2021 14:45:10 - INFO - __main__ - Step 8841: {'lr': 0.000497369517269916, 'samples': 1697472, 'steps': 8840, 'loss/train': 1.849187970161438} 08/30/2021 14:45:10 - INFO - __main__ - Step 8842: {'lr': 0.0004973687494188541, 'samples': 1697664, 'steps': 8841, 'loss/train': 2.716994524002075} 08/30/2021 14:45:11 - INFO - __main__ - Step 8843: {'lr': 0.0004973679814563318, 'samples': 1697856, 'steps': 8842, 'loss/train': 1.7706921100616455} 08/30/2021 14:45:11 - INFO - __main__ - Step 8844: {'lr': 0.0004973672133823491, 'samples': 1698048, 'steps': 8843, 'loss/train': 1.6797070503234863} 08/30/2021 14:45:13 - INFO - __main__ - Step 8845: {'lr': 0.0004973664451969066, 'samples': 1698240, 'steps': 8844, 'loss/train': 1.817637324333191} 08/30/2021 14:45:13 - INFO - __main__ - Step 8846: {'lr': 0.0004973656769000046, 'samples': 1698432, 'steps': 8845, 'loss/train': 1.572250247001648} 08/30/2021 14:45:13 - INFO - __main__ - Step 8847: {'lr': 0.0004973649084916435, 'samples': 1698624, 'steps': 8846, 'loss/train': 1.8365846872329712} 08/30/2021 14:45:14 - INFO - __main__ - Step 8848: {'lr': 0.0004973641399718236, 'samples': 1698816, 'steps': 8847, 'loss/train': 1.6546167135238647} 08/30/2021 14:45:14 - INFO - __main__ - Step 8849: {'lr': 0.0004973633713405451, 'samples': 1699008, 'steps': 8848, 'loss/train': 1.8078968524932861} 08/30/2021 14:45:14 - INFO - __main__ - Step 8850: {'lr': 0.0004973626025978086, 'samples': 1699200, 'steps': 8849, 'loss/train': 1.7147395610809326} 08/30/2021 14:45:16 - INFO - __main__ - Step 8851: {'lr': 0.0004973618337436143, 'samples': 1699392, 'steps': 8850, 'loss/train': 2.0545716285705566} 08/30/2021 14:45:16 - INFO - __main__ - Step 8852: {'lr': 0.0004973610647779626, 'samples': 1699584, 'steps': 8851, 'loss/train': 1.7343103885650635} 08/30/2021 14:45:17 - INFO - __main__ - Step 8853: {'lr': 0.0004973602957008537, 'samples': 1699776, 'steps': 8852, 'loss/train': 1.7753850221633911} 08/30/2021 14:45:17 - INFO - __main__ - Step 8854: {'lr': 0.0004973595265122883, 'samples': 1699968, 'steps': 8853, 'loss/train': 2.30344820022583} 08/30/2021 14:45:18 - INFO - __main__ - Step 8855: {'lr': 0.0004973587572122663, 'samples': 1700160, 'steps': 8854, 'loss/train': 2.225299119949341} 08/30/2021 14:45:19 - INFO - __main__ - Step 8856: {'lr': 0.0004973579878007884, 'samples': 1700352, 'steps': 8855, 'loss/train': 1.4403730630874634} 08/30/2021 14:45:20 - INFO - __main__ - Step 8857: {'lr': 0.0004973572182778546, 'samples': 1700544, 'steps': 8856, 'loss/train': 1.8367085456848145} 08/30/2021 14:45:20 - INFO - __main__ - Step 8858: {'lr': 0.0004973564486434656, 'samples': 1700736, 'steps': 8857, 'loss/train': 1.9998410940170288} 08/30/2021 14:45:20 - INFO - __main__ - Step 8859: {'lr': 0.0004973556788976217, 'samples': 1700928, 'steps': 8858, 'loss/train': 1.8122602701187134} 08/30/2021 14:45:21 - INFO - __main__ - Step 8860: {'lr': 0.000497354909040323, 'samples': 1701120, 'steps': 8859, 'loss/train': 3.0772290229797363} 08/30/2021 14:45:22 - INFO - __main__ - Step 8861: {'lr': 0.00049735413907157, 'samples': 1701312, 'steps': 8860, 'loss/train': 2.1263930797576904} 08/30/2021 14:45:23 - INFO - __main__ - Step 8862: {'lr': 0.0004973533689913631, 'samples': 1701504, 'steps': 8861, 'loss/train': 1.99599027633667} 08/30/2021 14:45:23 - INFO - __main__ - Step 8863: {'lr': 0.0004973525987997026, 'samples': 1701696, 'steps': 8862, 'loss/train': 1.8839139938354492} 08/30/2021 14:45:23 - INFO - __main__ - Step 8864: {'lr': 0.0004973518284965888, 'samples': 1701888, 'steps': 8863, 'loss/train': 2.3447067737579346} 08/30/2021 14:45:24 - INFO - __main__ - Step 8865: {'lr': 0.0004973510580820221, 'samples': 1702080, 'steps': 8864, 'loss/train': 2.4118566513061523} 08/30/2021 14:45:25 - INFO - __main__ - Step 8866: {'lr': 0.0004973502875560028, 'samples': 1702272, 'steps': 8865, 'loss/train': 2.1668953895568848} 08/30/2021 14:45:26 - INFO - __main__ - Step 8867: {'lr': 0.0004973495169185313, 'samples': 1702464, 'steps': 8866, 'loss/train': 1.8227133750915527} 08/30/2021 14:45:26 - INFO - __main__ - Step 8868: {'lr': 0.0004973487461696079, 'samples': 1702656, 'steps': 8867, 'loss/train': 2.0894923210144043} 08/30/2021 14:45:27 - INFO - __main__ - Step 8869: {'lr': 0.000497347975309233, 'samples': 1702848, 'steps': 8868, 'loss/train': 1.4945451021194458} 08/30/2021 14:45:27 - INFO - __main__ - Step 8870: {'lr': 0.0004973472043374069, 'samples': 1703040, 'steps': 8869, 'loss/train': 2.2598202228546143} 08/30/2021 14:45:27 - INFO - __main__ - Step 8871: {'lr': 0.00049734643325413, 'samples': 1703232, 'steps': 8870, 'loss/train': 1.9570155143737793} 08/30/2021 14:45:29 - INFO - __main__ - Step 8872: {'lr': 0.0004973456620594026, 'samples': 1703424, 'steps': 8871, 'loss/train': 1.706239938735962} 08/30/2021 14:45:30 - INFO - __main__ - Step 8873: {'lr': 0.0004973448907532251, 'samples': 1703616, 'steps': 8872, 'loss/train': 0.6889956593513489} 08/30/2021 14:45:30 - INFO - __main__ - Step 8874: {'lr': 0.0004973441193355978, 'samples': 1703808, 'steps': 8873, 'loss/train': 2.18713116645813} 08/30/2021 14:45:31 - INFO - __main__ - Step 8875: {'lr': 0.0004973433478065209, 'samples': 1704000, 'steps': 8874, 'loss/train': 1.3478615283966064} 08/30/2021 14:45:31 - INFO - __main__ - Step 8876: {'lr': 0.0004973425761659951, 'samples': 1704192, 'steps': 8875, 'loss/train': 1.8509184122085571} 08/30/2021 14:45:31 - INFO - __main__ - Step 8877: {'lr': 0.0004973418044140204, 'samples': 1704384, 'steps': 8876, 'loss/train': 2.8088579177856445} 08/30/2021 14:45:33 - INFO - __main__ - Step 8878: {'lr': 0.0004973410325505974, 'samples': 1704576, 'steps': 8877, 'loss/train': 2.0067989826202393} 08/30/2021 14:45:33 - INFO - __main__ - Step 8879: {'lr': 0.0004973402605757263, 'samples': 1704768, 'steps': 8878, 'loss/train': 2.421041250228882} 08/30/2021 14:45:34 - INFO - __main__ - Step 8880: {'lr': 0.0004973394884894075, 'samples': 1704960, 'steps': 8879, 'loss/train': 1.387993574142456} 08/30/2021 14:45:34 - INFO - __main__ - Step 8881: {'lr': 0.0004973387162916415, 'samples': 1705152, 'steps': 8880, 'loss/train': 1.5879567861557007} 08/30/2021 14:45:34 - INFO - __main__ - Step 8882: {'lr': 0.0004973379439824283, 'samples': 1705344, 'steps': 8881, 'loss/train': 1.4843741655349731} 08/30/2021 14:45:36 - INFO - __main__ - Step 8883: {'lr': 0.0004973371715617685, 'samples': 1705536, 'steps': 8882, 'loss/train': 1.8437132835388184} 08/30/2021 14:45:37 - INFO - __main__ - Step 8884: {'lr': 0.0004973363990296624, 'samples': 1705728, 'steps': 8883, 'loss/train': 1.6015136241912842} 08/30/2021 14:45:37 - INFO - __main__ - Step 8885: {'lr': 0.0004973356263861103, 'samples': 1705920, 'steps': 8884, 'loss/train': 1.8598570823669434} 08/30/2021 14:45:37 - INFO - __main__ - Step 8886: {'lr': 0.0004973348536311126, 'samples': 1706112, 'steps': 8885, 'loss/train': 0.8148157000541687} 08/30/2021 14:45:38 - INFO - __main__ - Step 8887: {'lr': 0.0004973340807646696, 'samples': 1706304, 'steps': 8886, 'loss/train': 2.130687713623047} 08/30/2021 14:45:38 - INFO - __main__ - Step 8888: {'lr': 0.0004973333077867817, 'samples': 1706496, 'steps': 8887, 'loss/train': 2.5316741466522217} 08/30/2021 14:45:39 - INFO - __main__ - Step 8889: {'lr': 0.0004973325346974493, 'samples': 1706688, 'steps': 8888, 'loss/train': 1.3335115909576416} 08/30/2021 14:45:40 - INFO - __main__ - Step 8890: {'lr': 0.0004973317614966726, 'samples': 1706880, 'steps': 8889, 'loss/train': 2.006979465484619} 08/30/2021 14:45:40 - INFO - __main__ - Step 8891: {'lr': 0.000497330988184452, 'samples': 1707072, 'steps': 8890, 'loss/train': 1.3788468837738037} 08/30/2021 14:45:41 - INFO - __main__ - Step 8892: {'lr': 0.000497330214760788, 'samples': 1707264, 'steps': 8891, 'loss/train': 2.031247854232788} 08/30/2021 14:45:41 - INFO - __main__ - Step 8893: {'lr': 0.0004973294412256807, 'samples': 1707456, 'steps': 8892, 'loss/train': 2.3019416332244873} 08/30/2021 14:45:42 - INFO - __main__ - Step 8894: {'lr': 0.0004973286675791305, 'samples': 1707648, 'steps': 8893, 'loss/train': 1.702967643737793} 08/30/2021 14:45:43 - INFO - __main__ - Step 8895: {'lr': 0.000497327893821138, 'samples': 1707840, 'steps': 8894, 'loss/train': 1.826103925704956} 08/30/2021 14:45:43 - INFO - __main__ - Step 8896: {'lr': 0.0004973271199517033, 'samples': 1708032, 'steps': 8895, 'loss/train': 1.4104102849960327} 08/30/2021 14:45:44 - INFO - __main__ - Step 8897: {'lr': 0.0004973263459708268, 'samples': 1708224, 'steps': 8896, 'loss/train': 0.6963333487510681} 08/30/2021 14:45:44 - INFO - __main__ - Step 8898: {'lr': 0.0004973255718785088, 'samples': 1708416, 'steps': 8897, 'loss/train': 1.4177162647247314} 08/30/2021 14:45:45 - INFO - __main__ - Step 8899: {'lr': 0.0004973247976747499, 'samples': 1708608, 'steps': 8898, 'loss/train': 2.370511054992676} 08/30/2021 14:45:46 - INFO - __main__ - Step 8900: {'lr': 0.00049732402335955, 'samples': 1708800, 'steps': 8899, 'loss/train': 1.8502165079116821} 08/30/2021 14:45:46 - INFO - __main__ - Step 8901: {'lr': 0.0004973232489329099, 'samples': 1708992, 'steps': 8900, 'loss/train': 2.1080193519592285} 08/30/2021 14:45:47 - INFO - __main__ - Step 8902: {'lr': 0.0004973224743948298, 'samples': 1709184, 'steps': 8901, 'loss/train': 2.1878201961517334} 08/30/2021 14:45:47 - INFO - __main__ - Step 8903: {'lr': 0.00049732169974531, 'samples': 1709376, 'steps': 8902, 'loss/train': 2.459467649459839} 08/30/2021 14:45:48 - INFO - __main__ - Step 8904: {'lr': 0.0004973209249843507, 'samples': 1709568, 'steps': 8903, 'loss/train': 1.4813534021377563} 08/30/2021 14:45:49 - INFO - __main__ - Step 8905: {'lr': 0.0004973201501119525, 'samples': 1709760, 'steps': 8904, 'loss/train': 1.8868945837020874} 08/30/2021 14:45:49 - INFO - __main__ - Step 8906: {'lr': 0.0004973193751281156, 'samples': 1709952, 'steps': 8905, 'loss/train': 2.3907878398895264} 08/30/2021 14:45:50 - INFO - __main__ - Step 8907: {'lr': 0.0004973186000328405, 'samples': 1710144, 'steps': 8906, 'loss/train': 1.8003449440002441} 08/30/2021 14:45:50 - INFO - __main__ - Step 8908: {'lr': 0.0004973178248261274, 'samples': 1710336, 'steps': 8907, 'loss/train': 1.5820327997207642} 08/30/2021 14:45:52 - INFO - __main__ - Step 8909: {'lr': 0.0004973170495079768, 'samples': 1710528, 'steps': 8908, 'loss/train': 1.7473973035812378} 08/30/2021 14:45:52 - INFO - __main__ - Step 8910: {'lr': 0.0004973162740783888, 'samples': 1710720, 'steps': 8909, 'loss/train': 1.7038699388504028} 08/30/2021 14:45:53 - INFO - __main__ - Step 8911: {'lr': 0.000497315498537364, 'samples': 1710912, 'steps': 8910, 'loss/train': 1.7031673192977905} 08/30/2021 14:45:53 - INFO - __main__ - Step 8912: {'lr': 0.0004973147228849027, 'samples': 1711104, 'steps': 8911, 'loss/train': 2.1056363582611084} 08/30/2021 14:45:53 - INFO - __main__ - Step 8913: {'lr': 0.0004973139471210051, 'samples': 1711296, 'steps': 8912, 'loss/train': 0.4294566512107849} 08/30/2021 14:45:54 - INFO - __main__ - Step 8914: {'lr': 0.0004973131712456717, 'samples': 1711488, 'steps': 8913, 'loss/train': 1.8426896333694458} 08/30/2021 14:45:55 - INFO - __main__ - Step 8915: {'lr': 0.0004973123952589027, 'samples': 1711680, 'steps': 8914, 'loss/train': 1.698033332824707} 08/30/2021 14:45:56 - INFO - __main__ - Step 8916: {'lr': 0.0004973116191606987, 'samples': 1711872, 'steps': 8915, 'loss/train': 1.9066834449768066} 08/30/2021 14:45:56 - INFO - __main__ - Step 8917: {'lr': 0.0004973108429510598, 'samples': 1712064, 'steps': 8916, 'loss/train': 1.8417645692825317} 08/30/2021 14:45:56 - INFO - __main__ - Step 8918: {'lr': 0.0004973100666299864, 'samples': 1712256, 'steps': 8917, 'loss/train': 1.8167082071304321} 08/30/2021 14:45:57 - INFO - __main__ - Step 8919: {'lr': 0.000497309290197479, 'samples': 1712448, 'steps': 8918, 'loss/train': 2.034162759780884} 08/30/2021 14:45:58 - INFO - __main__ - Step 8920: {'lr': 0.0004973085136535379, 'samples': 1712640, 'steps': 8919, 'loss/train': 2.1454975605010986} 08/30/2021 14:45:59 - INFO - __main__ - Step 8921: {'lr': 0.0004973077369981633, 'samples': 1712832, 'steps': 8920, 'loss/train': 2.238969326019287} 08/30/2021 14:45:59 - INFO - __main__ - Step 8922: {'lr': 0.0004973069602313557, 'samples': 1713024, 'steps': 8921, 'loss/train': 1.4229657649993896} 08/30/2021 14:46:00 - INFO - __main__ - Step 8923: {'lr': 0.0004973061833531154, 'samples': 1713216, 'steps': 8922, 'loss/train': 1.5363589525222778} 08/30/2021 14:46:00 - INFO - __main__ - Step 8924: {'lr': 0.0004973054063634428, 'samples': 1713408, 'steps': 8923, 'loss/train': 1.8894785642623901} 08/30/2021 14:46:02 - INFO - __main__ - Step 8925: {'lr': 0.0004973046292623382, 'samples': 1713600, 'steps': 8924, 'loss/train': 1.615864872932434} 08/30/2021 14:46:02 - INFO - __main__ - Step 8926: {'lr': 0.0004973038520498017, 'samples': 1713792, 'steps': 8925, 'loss/train': 2.2542076110839844} 08/30/2021 14:46:03 - INFO - __main__ - Step 8927: {'lr': 0.0004973030747258342, 'samples': 1713984, 'steps': 8926, 'loss/train': 1.6344541311264038} 08/30/2021 14:46:03 - INFO - __main__ - Step 8928: {'lr': 0.0004973022972904356, 'samples': 1714176, 'steps': 8927, 'loss/train': 1.416045069694519} 08/30/2021 14:46:03 - INFO - __main__ - Step 8929: {'lr': 0.0004973015197436063, 'samples': 1714368, 'steps': 8928, 'loss/train': 1.836950659751892} 08/30/2021 14:46:04 - INFO - __main__ - Step 8930: {'lr': 0.0004973007420853471, 'samples': 1714560, 'steps': 8929, 'loss/train': 1.8327442407608032} 08/30/2021 14:46:06 - INFO - __main__ - Step 8931: {'lr': 0.0004972999643156577, 'samples': 1714752, 'steps': 8930, 'loss/train': 2.138300895690918} 08/30/2021 14:46:06 - INFO - __main__ - Step 8932: {'lr': 0.0004972991864345389, 'samples': 1714944, 'steps': 8931, 'loss/train': 0.41218137741088867} 08/30/2021 14:46:06 - INFO - __main__ - Step 8933: {'lr': 0.0004972984084419908, 'samples': 1715136, 'steps': 8932, 'loss/train': 0.3619674742221832} 08/30/2021 14:46:07 - INFO - __main__ - Step 8934: {'lr': 0.0004972976303380139, 'samples': 1715328, 'steps': 8933, 'loss/train': 1.6116410493850708} 08/30/2021 14:46:07 - INFO - __main__ - Step 8935: {'lr': 0.0004972968521226085, 'samples': 1715520, 'steps': 8934, 'loss/train': 2.2196226119995117} 08/30/2021 14:46:07 - INFO - __main__ - Step 8936: {'lr': 0.0004972960737957749, 'samples': 1715712, 'steps': 8935, 'loss/train': 2.018220901489258} 08/30/2021 14:46:09 - INFO - __main__ - Step 8937: {'lr': 0.0004972952953575136, 'samples': 1715904, 'steps': 8936, 'loss/train': 1.8370572328567505} 08/30/2021 14:46:10 - INFO - __main__ - Step 8938: {'lr': 0.0004972945168078248, 'samples': 1716096, 'steps': 8937, 'loss/train': 0.41641080379486084} 08/30/2021 14:46:10 - INFO - __main__ - Step 8939: {'lr': 0.000497293738146709, 'samples': 1716288, 'steps': 8938, 'loss/train': 2.1680476665496826} 08/30/2021 14:46:11 - INFO - __main__ - Step 8940: {'lr': 0.0004972929593741662, 'samples': 1716480, 'steps': 8939, 'loss/train': 2.002331256866455} 08/30/2021 14:46:11 - INFO - __main__ - Step 8941: {'lr': 0.0004972921804901973, 'samples': 1716672, 'steps': 8940, 'loss/train': 0.567217230796814} 08/30/2021 14:46:11 - INFO - __main__ - Step 8942: {'lr': 0.0004972914014948023, 'samples': 1716864, 'steps': 8941, 'loss/train': 0.4307175874710083} 08/30/2021 14:46:13 - INFO - __main__ - Step 8943: {'lr': 0.0004972906223879815, 'samples': 1717056, 'steps': 8942, 'loss/train': 1.0863940715789795} 08/30/2021 14:46:14 - INFO - __main__ - Step 8944: {'lr': 0.0004972898431697355, 'samples': 1717248, 'steps': 8943, 'loss/train': 1.9866523742675781} 08/30/2021 14:46:14 - INFO - __main__ - Step 8945: {'lr': 0.0004972890638400644, 'samples': 1717440, 'steps': 8944, 'loss/train': 2.160125970840454} 08/30/2021 14:46:15 - INFO - __main__ - Step 8946: {'lr': 0.0004972882843989687, 'samples': 1717632, 'steps': 8945, 'loss/train': 1.9607785940170288} 08/30/2021 14:46:15 - INFO - __main__ - Step 8947: {'lr': 0.0004972875048464487, 'samples': 1717824, 'steps': 8946, 'loss/train': 0.3123684823513031} 08/30/2021 14:46:15 - INFO - __main__ - Step 8948: {'lr': 0.0004972867251825048, 'samples': 1718016, 'steps': 8947, 'loss/train': 1.7114638090133667} 08/30/2021 14:46:16 - INFO - __main__ - Step 8949: {'lr': 0.0004972859454071373, 'samples': 1718208, 'steps': 8948, 'loss/train': 1.0696732997894287} 08/30/2021 14:46:17 - INFO - __main__ - Step 8950: {'lr': 0.0004972851655203465, 'samples': 1718400, 'steps': 8949, 'loss/train': 2.3935022354125977} 08/30/2021 14:46:18 - INFO - __main__ - Step 8951: {'lr': 0.000497284385522133, 'samples': 1718592, 'steps': 8950, 'loss/train': 1.9937423467636108} 08/30/2021 14:46:18 - INFO - __main__ - Step 8952: {'lr': 0.0004972836054124968, 'samples': 1718784, 'steps': 8951, 'loss/train': 1.2871404886245728} 08/30/2021 14:46:18 - INFO - __main__ - Step 8953: {'lr': 0.0004972828251914384, 'samples': 1718976, 'steps': 8952, 'loss/train': 1.8947973251342773} 08/30/2021 14:46:19 - INFO - __main__ - Step 8954: {'lr': 0.0004972820448589584, 'samples': 1719168, 'steps': 8953, 'loss/train': 2.2932281494140625} 08/30/2021 14:46:21 - INFO - __main__ - Step 8955: {'lr': 0.0004972812644150567, 'samples': 1719360, 'steps': 8954, 'loss/train': 2.2850396633148193} 08/30/2021 14:46:21 - INFO - __main__ - Step 8956: {'lr': 0.000497280483859734, 'samples': 1719552, 'steps': 8955, 'loss/train': 2.493499279022217} 08/30/2021 14:46:21 - INFO - __main__ - Step 8957: {'lr': 0.0004972797031929904, 'samples': 1719744, 'steps': 8956, 'loss/train': 1.801703929901123} 08/30/2021 14:46:22 - INFO - __main__ - Step 8958: {'lr': 0.0004972789224148266, 'samples': 1719936, 'steps': 8957, 'loss/train': 0.33974945545196533} 08/30/2021 14:46:22 - INFO - __main__ - Step 8959: {'lr': 0.0004972781415252426, 'samples': 1720128, 'steps': 8958, 'loss/train': 1.8467414379119873} 08/30/2021 14:46:24 - INFO - __main__ - Step 8960: {'lr': 0.0004972773605242388, 'samples': 1720320, 'steps': 8959, 'loss/train': 1.8445549011230469} 08/30/2021 14:46:24 - INFO - __main__ - Step 8961: {'lr': 0.0004972765794118158, 'samples': 1720512, 'steps': 8960, 'loss/train': 2.001028060913086} 08/30/2021 14:46:24 - INFO - __main__ - Step 8962: {'lr': 0.0004972757981879737, 'samples': 1720704, 'steps': 8961, 'loss/train': 1.944581151008606} 08/30/2021 14:46:25 - INFO - __main__ - Step 8963: {'lr': 0.000497275016852713, 'samples': 1720896, 'steps': 8962, 'loss/train': 0.15324637293815613} 08/30/2021 14:46:25 - INFO - __main__ - Step 8964: {'lr': 0.0004972742354060339, 'samples': 1721088, 'steps': 8963, 'loss/train': 2.0042412281036377} 08/30/2021 14:46:27 - INFO - __main__ - Step 8965: {'lr': 0.0004972734538479369, 'samples': 1721280, 'steps': 8964, 'loss/train': 2.059574604034424} 08/30/2021 14:46:27 - INFO - __main__ - Step 8966: {'lr': 0.0004972726721784223, 'samples': 1721472, 'steps': 8965, 'loss/train': 1.6372652053833008} 08/30/2021 14:46:28 - INFO - __main__ - Step 8967: {'lr': 0.0004972718903974904, 'samples': 1721664, 'steps': 8966, 'loss/train': 1.243790864944458} 08/30/2021 14:46:28 - INFO - __main__ - Step 8968: {'lr': 0.0004972711085051417, 'samples': 1721856, 'steps': 8967, 'loss/train': 1.6012420654296875} 08/30/2021 14:46:28 - INFO - __main__ - Step 8969: {'lr': 0.0004972703265013764, 'samples': 1722048, 'steps': 8968, 'loss/train': 1.6654213666915894} 08/30/2021 14:46:30 - INFO - __main__ - Step 8970: {'lr': 0.0004972695443861949, 'samples': 1722240, 'steps': 8969, 'loss/train': 2.1250109672546387} 08/30/2021 14:46:30 - INFO - __main__ - Step 8971: {'lr': 0.0004972687621595975, 'samples': 1722432, 'steps': 8970, 'loss/train': 1.3418915271759033} 08/30/2021 14:46:31 - INFO - __main__ - Step 8972: {'lr': 0.0004972679798215847, 'samples': 1722624, 'steps': 8971, 'loss/train': 1.7405096292495728} 08/30/2021 14:46:31 - INFO - __main__ - Step 8973: {'lr': 0.0004972671973721567, 'samples': 1722816, 'steps': 8972, 'loss/train': 1.445396065711975} 08/30/2021 14:46:31 - INFO - __main__ - Step 8974: {'lr': 0.000497266414811314, 'samples': 1723008, 'steps': 8973, 'loss/train': 1.874290108680725} 08/30/2021 14:46:32 - INFO - __main__ - Step 8975: {'lr': 0.0004972656321390568, 'samples': 1723200, 'steps': 8974, 'loss/train': 1.9991459846496582} 08/30/2021 14:46:33 - INFO - __main__ - Step 8976: {'lr': 0.0004972648493553856, 'samples': 1723392, 'steps': 8975, 'loss/train': 1.369490385055542} 08/30/2021 14:46:34 - INFO - __main__ - Step 8977: {'lr': 0.0004972640664603006, 'samples': 1723584, 'steps': 8976, 'loss/train': 2.310957670211792} 08/30/2021 14:46:34 - INFO - __main__ - Step 8978: {'lr': 0.0004972632834538023, 'samples': 1723776, 'steps': 8977, 'loss/train': 2.124022960662842} 08/30/2021 14:46:34 - INFO - __main__ - Step 8979: {'lr': 0.0004972625003358908, 'samples': 1723968, 'steps': 8978, 'loss/train': 1.5275260210037231} 08/30/2021 14:46:35 - INFO - __main__ - Step 8980: {'lr': 0.0004972617171065668, 'samples': 1724160, 'steps': 8979, 'loss/train': 1.8284701108932495} 08/30/2021 14:46:37 - INFO - __main__ - Step 8981: {'lr': 0.0004972609337658305, 'samples': 1724352, 'steps': 8980, 'loss/train': 2.2119197845458984} 08/30/2021 14:46:37 - INFO - __main__ - Step 8982: {'lr': 0.0004972601503136822, 'samples': 1724544, 'steps': 8981, 'loss/train': 1.2716857194900513} 08/30/2021 14:46:38 - INFO - __main__ - Step 8983: {'lr': 0.0004972593667501222, 'samples': 1724736, 'steps': 8982, 'loss/train': 1.8443129062652588} 08/30/2021 14:46:38 - INFO - __main__ - Step 8984: {'lr': 0.0004972585830751511, 'samples': 1724928, 'steps': 8983, 'loss/train': 2.1716959476470947} 08/30/2021 14:46:38 - INFO - __main__ - Step 8985: {'lr': 0.0004972577992887689, 'samples': 1725120, 'steps': 8984, 'loss/train': 2.3679816722869873} 08/30/2021 14:46:39 - INFO - __main__ - Step 8986: {'lr': 0.0004972570153909763, 'samples': 1725312, 'steps': 8985, 'loss/train': 1.4090771675109863} 08/30/2021 14:46:40 - INFO - __main__ - Step 8987: {'lr': 0.0004972562313817735, 'samples': 1725504, 'steps': 8986, 'loss/train': 5.555885314941406} 08/30/2021 14:46:41 - INFO - __main__ - Step 8988: {'lr': 0.0004972554472611609, 'samples': 1725696, 'steps': 8987, 'loss/train': 1.9008162021636963} 08/30/2021 14:46:41 - INFO - __main__ - Step 8989: {'lr': 0.0004972546630291387, 'samples': 1725888, 'steps': 8988, 'loss/train': 2.138808012008667} 08/30/2021 14:46:41 - INFO - __main__ - Step 8990: {'lr': 0.0004972538786857073, 'samples': 1726080, 'steps': 8989, 'loss/train': 2.1921675205230713} 08/30/2021 14:46:42 - INFO - __main__ - Step 8991: {'lr': 0.0004972530942308673, 'samples': 1726272, 'steps': 8990, 'loss/train': 1.5733258724212646} 08/30/2021 14:46:43 - INFO - __main__ - Step 8992: {'lr': 0.0004972523096646188, 'samples': 1726464, 'steps': 8991, 'loss/train': 1.8545182943344116} 08/30/2021 14:46:44 - INFO - __main__ - Step 8993: {'lr': 0.0004972515249869622, 'samples': 1726656, 'steps': 8992, 'loss/train': 2.081447124481201} 08/30/2021 14:46:44 - INFO - __main__ - Step 8994: {'lr': 0.000497250740197898, 'samples': 1726848, 'steps': 8993, 'loss/train': 1.9429447650909424} 08/30/2021 14:46:44 - INFO - __main__ - Step 8995: {'lr': 0.0004972499552974263, 'samples': 1727040, 'steps': 8994, 'loss/train': 1.5408134460449219} 08/30/2021 14:46:45 - INFO - __main__ - Step 8996: {'lr': 0.0004972491702855477, 'samples': 1727232, 'steps': 8995, 'loss/train': 2.4530506134033203} 08/30/2021 14:46:46 - INFO - __main__ - Step 8997: {'lr': 0.0004972483851622623, 'samples': 1727424, 'steps': 8996, 'loss/train': 1.8891547918319702} 08/30/2021 14:46:47 - INFO - __main__ - Step 8998: {'lr': 0.0004972475999275707, 'samples': 1727616, 'steps': 8997, 'loss/train': 2.088207721710205} 08/30/2021 14:46:47 - INFO - __main__ - Step 8999: {'lr': 0.0004972468145814729, 'samples': 1727808, 'steps': 8998, 'loss/train': 2.1565043926239014} 08/30/2021 14:46:47 - INFO - __main__ - Step 9000: {'lr': 0.0004972460291239697, 'samples': 1728000, 'steps': 8999, 'loss/train': 1.3041085004806519} 08/30/2021 14:46:48 - INFO - __main__ - Step 9001: {'lr': 0.0004972452435550613, 'samples': 1728192, 'steps': 9000, 'loss/train': 1.81965172290802} 08/30/2021 14:46:49 - INFO - __main__ - Step 9002: {'lr': 0.000497244457874748, 'samples': 1728384, 'steps': 9001, 'loss/train': 2.1079812049865723} 08/30/2021 14:46:50 - INFO - __main__ - Step 9003: {'lr': 0.0004972436720830301, 'samples': 1728576, 'steps': 9002, 'loss/train': 1.979142665863037} 08/30/2021 14:46:50 - INFO - __main__ - Step 9004: {'lr': 0.000497242886179908, 'samples': 1728768, 'steps': 9003, 'loss/train': 2.252262830734253} 08/30/2021 14:46:50 - INFO - __main__ - Step 9005: {'lr': 0.0004972421001653822, 'samples': 1728960, 'steps': 9004, 'loss/train': 1.3209646940231323} 08/30/2021 14:46:51 - INFO - __main__ - Step 9006: {'lr': 0.0004972413140394528, 'samples': 1729152, 'steps': 9005, 'loss/train': 1.8071860074996948} 08/30/2021 14:46:52 - INFO - __main__ - Step 9007: {'lr': 0.0004972405278021203, 'samples': 1729344, 'steps': 9006, 'loss/train': 1.5674419403076172} 08/30/2021 14:46:53 - INFO - __main__ - Step 9008: {'lr': 0.000497239741453385, 'samples': 1729536, 'steps': 9007, 'loss/train': 2.1593832969665527} 08/30/2021 14:46:53 - INFO - __main__ - Step 9009: {'lr': 0.0004972389549932473, 'samples': 1729728, 'steps': 9008, 'loss/train': 1.8619449138641357} 08/30/2021 14:46:53 - INFO - __main__ - Step 9010: {'lr': 0.0004972381684217077, 'samples': 1729920, 'steps': 9009, 'loss/train': 1.7730443477630615} 08/30/2021 14:46:54 - INFO - __main__ - Step 9011: {'lr': 0.0004972373817387662, 'samples': 1730112, 'steps': 9010, 'loss/train': 0.21746385097503662} 08/30/2021 14:46:55 - INFO - __main__ - Step 9012: {'lr': 0.0004972365949444234, 'samples': 1730304, 'steps': 9011, 'loss/train': 1.2569061517715454} 08/30/2021 14:46:56 - INFO - __main__ - Step 9013: {'lr': 0.0004972358080386796, 'samples': 1730496, 'steps': 9012, 'loss/train': 1.710551381111145} 08/30/2021 14:46:56 - INFO - __main__ - Step 9014: {'lr': 0.0004972350210215353, 'samples': 1730688, 'steps': 9013, 'loss/train': 1.9982478618621826} 08/30/2021 14:46:56 - INFO - __main__ - Step 9015: {'lr': 0.0004972342338929906, 'samples': 1730880, 'steps': 9014, 'loss/train': 1.455694317817688} 08/30/2021 14:46:57 - INFO - __main__ - Step 9016: {'lr': 0.000497233446653046, 'samples': 1731072, 'steps': 9015, 'loss/train': 1.478135347366333} 08/30/2021 14:46:58 - INFO - __main__ - Step 9017: {'lr': 0.0004972326593017017, 'samples': 1731264, 'steps': 9016, 'loss/train': 0.3686990439891815} 08/30/2021 14:46:59 - INFO - __main__ - Step 9018: {'lr': 0.0004972318718389583, 'samples': 1731456, 'steps': 9017, 'loss/train': 2.315657138824463} 08/30/2021 14:46:59 - INFO - __main__ - Step 9019: {'lr': 0.000497231084264816, 'samples': 1731648, 'steps': 9018, 'loss/train': 1.9352573156356812} 08/30/2021 14:46:59 - INFO - __main__ - Step 9020: {'lr': 0.0004972302965792752, 'samples': 1731840, 'steps': 9019, 'loss/train': 1.8115142583847046} 08/30/2021 14:47:00 - INFO - __main__ - Step 9021: {'lr': 0.0004972295087823362, 'samples': 1732032, 'steps': 9020, 'loss/train': 2.0826833248138428} 08/30/2021 14:47:00 - INFO - __main__ - Step 9022: {'lr': 0.0004972287208739995, 'samples': 1732224, 'steps': 9021, 'loss/train': 2.076280355453491} 08/30/2021 14:47:02 - INFO - __main__ - Step 9023: {'lr': 0.0004972279328542652, 'samples': 1732416, 'steps': 9022, 'loss/train': 1.655226469039917} 08/30/2021 14:47:02 - INFO - __main__ - Step 9024: {'lr': 0.000497227144723134, 'samples': 1732608, 'steps': 9023, 'loss/train': 1.9644949436187744} 08/30/2021 14:47:02 - INFO - __main__ - Step 9025: {'lr': 0.0004972263564806059, 'samples': 1732800, 'steps': 9024, 'loss/train': 1.738426685333252} 08/30/2021 14:47:03 - INFO - __main__ - Step 9026: {'lr': 0.0004972255681266816, 'samples': 1732992, 'steps': 9025, 'loss/train': 2.129232406616211} 08/30/2021 14:47:03 - INFO - __main__ - Step 9027: {'lr': 0.0004972247796613611, 'samples': 1733184, 'steps': 9026, 'loss/train': 1.6423194408416748} 08/30/2021 14:47:05 - INFO - __main__ - Step 9028: {'lr': 0.000497223991084645, 'samples': 1733376, 'steps': 9027, 'loss/train': 2.716042995452881} 08/30/2021 14:47:05 - INFO - __main__ - Step 9029: {'lr': 0.0004972232023965335, 'samples': 1733568, 'steps': 9028, 'loss/train': 1.9740265607833862} 08/30/2021 14:47:06 - INFO - __main__ - Step 9030: {'lr': 0.0004972224135970271, 'samples': 1733760, 'steps': 9029, 'loss/train': 2.0346691608428955} 08/30/2021 14:47:06 - INFO - __main__ - Step 9031: {'lr': 0.0004972216246861262, 'samples': 1733952, 'steps': 9030, 'loss/train': 1.3250304460525513} 08/30/2021 14:47:06 - INFO - __main__ - Step 9032: {'lr': 0.0004972208356638309, 'samples': 1734144, 'steps': 9031, 'loss/train': 0.7586222290992737} 08/30/2021 14:47:08 - INFO - __main__ - Step 9033: {'lr': 0.0004972200465301418, 'samples': 1734336, 'steps': 9032, 'loss/train': 0.13911418616771698} 08/30/2021 14:47:08 - INFO - __main__ - Step 9034: {'lr': 0.0004972192572850592, 'samples': 1734528, 'steps': 9033, 'loss/train': 2.3646790981292725} 08/30/2021 14:47:09 - INFO - __main__ - Step 9035: {'lr': 0.0004972184679285833, 'samples': 1734720, 'steps': 9034, 'loss/train': 2.102095603942871} 08/30/2021 14:47:09 - INFO - __main__ - Step 9036: {'lr': 0.0004972176784607146, 'samples': 1734912, 'steps': 9035, 'loss/train': 1.5774246454238892} 08/30/2021 14:47:09 - INFO - __main__ - Step 9037: {'lr': 0.0004972168888814533, 'samples': 1735104, 'steps': 9036, 'loss/train': 1.9236433506011963} 08/30/2021 14:47:11 - INFO - __main__ - Step 9038: {'lr': 0.0004972160991908001, 'samples': 1735296, 'steps': 9037, 'loss/train': 2.431725263595581} 08/30/2021 14:47:12 - INFO - __main__ - Step 9039: {'lr': 0.0004972153093887551, 'samples': 1735488, 'steps': 9038, 'loss/train': 2.3673272132873535} 08/30/2021 14:47:12 - INFO - __main__ - Step 9040: {'lr': 0.0004972145194753186, 'samples': 1735680, 'steps': 9039, 'loss/train': 1.0304653644561768} 08/30/2021 14:47:13 - INFO - __main__ - Step 9041: {'lr': 0.0004972137294504912, 'samples': 1735872, 'steps': 9040, 'loss/train': 2.5453944206237793} 08/30/2021 14:47:13 - INFO - __main__ - Step 9042: {'lr': 0.000497212939314273, 'samples': 1736064, 'steps': 9041, 'loss/train': 2.106966257095337} 08/30/2021 14:47:13 - INFO - __main__ - Step 9043: {'lr': 0.0004972121490666644, 'samples': 1736256, 'steps': 9042, 'loss/train': 1.8059356212615967} 08/30/2021 14:47:15 - INFO - __main__ - Step 9044: {'lr': 0.000497211358707666, 'samples': 1736448, 'steps': 9043, 'loss/train': 5.437865257263184} 08/30/2021 14:47:15 - INFO - __main__ - Step 9045: {'lr': 0.0004972105682372779, 'samples': 1736640, 'steps': 9044, 'loss/train': 0.7333853840827942} 08/30/2021 14:47:16 - INFO - __main__ - Step 9046: {'lr': 0.0004972097776555005, 'samples': 1736832, 'steps': 9045, 'loss/train': 4.125444412231445} 08/30/2021 14:47:16 - INFO - __main__ - Step 9047: {'lr': 0.0004972089869623342, 'samples': 1737024, 'steps': 9046, 'loss/train': 2.1651124954223633} 08/30/2021 14:47:16 - INFO - __main__ - Step 9048: {'lr': 0.0004972081961577793, 'samples': 1737216, 'steps': 9047, 'loss/train': 1.1374707221984863} 08/30/2021 14:47:17 - INFO - __main__ - Step 9049: {'lr': 0.0004972074052418363, 'samples': 1737408, 'steps': 9048, 'loss/train': 1.8395694494247437} 08/30/2021 14:47:18 - INFO - __main__ - Step 9050: {'lr': 0.0004972066142145055, 'samples': 1737600, 'steps': 9049, 'loss/train': 2.260136127471924} 08/30/2021 14:47:19 - INFO - __main__ - Step 9051: {'lr': 0.0004972058230757871, 'samples': 1737792, 'steps': 9050, 'loss/train': 1.9717533588409424} 08/30/2021 14:47:19 - INFO - __main__ - Step 9052: {'lr': 0.0004972050318256815, 'samples': 1737984, 'steps': 9051, 'loss/train': 2.301158905029297} 08/30/2021 14:47:19 - INFO - __main__ - Step 9053: {'lr': 0.0004972042404641893, 'samples': 1738176, 'steps': 9052, 'loss/train': 2.252315044403076} 08/30/2021 14:47:20 - INFO - __main__ - Step 9054: {'lr': 0.0004972034489913106, 'samples': 1738368, 'steps': 9053, 'loss/train': 2.236299753189087} 08/30/2021 14:47:21 - INFO - __main__ - Step 9055: {'lr': 0.0004972026574070459, 'samples': 1738560, 'steps': 9054, 'loss/train': 2.087787389755249} 08/30/2021 14:47:22 - INFO - __main__ - Step 9056: {'lr': 0.0004972018657113953, 'samples': 1738752, 'steps': 9055, 'loss/train': 2.945784330368042} 08/30/2021 14:47:22 - INFO - __main__ - Step 9057: {'lr': 0.0004972010739043596, 'samples': 1738944, 'steps': 9056, 'loss/train': 2.9534263610839844} 08/30/2021 14:47:22 - INFO - __main__ - Step 9058: {'lr': 0.0004972002819859388, 'samples': 1739136, 'steps': 9057, 'loss/train': 2.2367610931396484} 08/30/2021 14:47:23 - INFO - __main__ - Step 9059: {'lr': 0.0004971994899561334, 'samples': 1739328, 'steps': 9058, 'loss/train': 2.444326162338257} 08/30/2021 14:47:24 - INFO - __main__ - Step 9060: {'lr': 0.0004971986978149437, 'samples': 1739520, 'steps': 9059, 'loss/train': 1.7260419130325317} 08/30/2021 14:47:25 - INFO - __main__ - Step 9061: {'lr': 0.0004971979055623701, 'samples': 1739712, 'steps': 9060, 'loss/train': 2.3490841388702393} 08/30/2021 14:47:25 - INFO - __main__ - Step 9062: {'lr': 0.0004971971131984129, 'samples': 1739904, 'steps': 9061, 'loss/train': 1.640828013420105} 08/30/2021 14:47:25 - INFO - __main__ - Step 9063: {'lr': 0.0004971963207230725, 'samples': 1740096, 'steps': 9062, 'loss/train': 2.176591634750366} 08/30/2021 14:47:26 - INFO - __main__ - Step 9064: {'lr': 0.0004971955281363493, 'samples': 1740288, 'steps': 9063, 'loss/train': 2.0326313972473145} 08/30/2021 14:47:27 - INFO - __main__ - Step 9065: {'lr': 0.0004971947354382436, 'samples': 1740480, 'steps': 9064, 'loss/train': 1.402564525604248} 08/30/2021 14:47:28 - INFO - __main__ - Step 9066: {'lr': 0.0004971939426287557, 'samples': 1740672, 'steps': 9065, 'loss/train': 2.0635030269622803} 08/30/2021 14:47:28 - INFO - __main__ - Step 9067: {'lr': 0.0004971931497078861, 'samples': 1740864, 'steps': 9066, 'loss/train': 0.9907790422439575} 08/30/2021 14:47:28 - INFO - __main__ - Step 9068: {'lr': 0.000497192356675635, 'samples': 1741056, 'steps': 9067, 'loss/train': 2.3744184970855713} 08/30/2021 14:47:29 - INFO - __main__ - Step 9069: {'lr': 0.0004971915635320029, 'samples': 1741248, 'steps': 9068, 'loss/train': 2.2521064281463623} 08/30/2021 14:47:29 - INFO - __main__ - Step 9070: {'lr': 0.0004971907702769901, 'samples': 1741440, 'steps': 9069, 'loss/train': 1.4979050159454346} 08/30/2021 14:47:31 - INFO - __main__ - Step 9071: {'lr': 0.000497189976910597, 'samples': 1741632, 'steps': 9070, 'loss/train': 2.048565149307251} 08/30/2021 14:47:31 - INFO - __main__ - Step 9072: {'lr': 0.0004971891834328238, 'samples': 1741824, 'steps': 9071, 'loss/train': 1.8345752954483032} 08/30/2021 14:47:31 - INFO - __main__ - Step 9073: {'lr': 0.000497188389843671, 'samples': 1742016, 'steps': 9072, 'loss/train': 1.6389049291610718} 08/30/2021 14:47:32 - INFO - __main__ - Step 9074: {'lr': 0.0004971875961431389, 'samples': 1742208, 'steps': 9073, 'loss/train': 2.1482186317443848} 08/30/2021 14:47:32 - INFO - __main__ - Step 9075: {'lr': 0.000497186802331228, 'samples': 1742400, 'steps': 9074, 'loss/train': 2.09512996673584} 08/30/2021 14:47:34 - INFO - __main__ - Step 9076: {'lr': 0.0004971860084079385, 'samples': 1742592, 'steps': 9075, 'loss/train': 2.276905059814453} 08/30/2021 14:47:34 - INFO - __main__ - Step 9077: {'lr': 0.0004971852143732707, 'samples': 1742784, 'steps': 9076, 'loss/train': 1.8982940912246704} 08/30/2021 14:47:35 - INFO - __main__ - Step 9078: {'lr': 0.0004971844202272251, 'samples': 1742976, 'steps': 9077, 'loss/train': 1.3196507692337036} 08/30/2021 14:47:35 - INFO - __main__ - Step 9079: {'lr': 0.000497183625969802, 'samples': 1743168, 'steps': 9078, 'loss/train': 1.0520685911178589} 08/30/2021 14:47:35 - INFO - __main__ - Step 9080: {'lr': 0.0004971828316010019, 'samples': 1743360, 'steps': 9079, 'loss/train': 2.0894603729248047} 08/30/2021 14:47:36 - INFO - __main__ - Step 9081: {'lr': 0.0004971820371208248, 'samples': 1743552, 'steps': 9080, 'loss/train': 2.3856382369995117} 08/30/2021 14:47:37 - INFO - __main__ - Step 9082: {'lr': 0.0004971812425292716, 'samples': 1743744, 'steps': 9081, 'loss/train': 1.1970280408859253} 08/30/2021 14:47:38 - INFO - __main__ - Step 9083: {'lr': 0.000497180447826342, 'samples': 1743936, 'steps': 9082, 'loss/train': 1.8861169815063477} 08/30/2021 14:47:38 - INFO - __main__ - Step 9084: {'lr': 0.0004971796530120371, 'samples': 1744128, 'steps': 9083, 'loss/train': 1.9659919738769531} 08/30/2021 14:47:38 - INFO - __main__ - Step 9085: {'lr': 0.0004971788580863566, 'samples': 1744320, 'steps': 9084, 'loss/train': 1.5286049842834473} 08/30/2021 14:47:39 - INFO - __main__ - Step 9086: {'lr': 0.0004971780630493012, 'samples': 1744512, 'steps': 9085, 'loss/train': 2.2692182064056396} 08/30/2021 14:47:40 - INFO - __main__ - Step 9087: {'lr': 0.000497177267900871, 'samples': 1744704, 'steps': 9086, 'loss/train': 2.5457873344421387} 08/30/2021 14:47:41 - INFO - __main__ - Step 9088: {'lr': 0.0004971764726410668, 'samples': 1744896, 'steps': 9087, 'loss/train': 1.9081003665924072} 08/30/2021 14:47:41 - INFO - __main__ - Step 9089: {'lr': 0.0004971756772698886, 'samples': 1745088, 'steps': 9088, 'loss/train': 1.959722638130188} 08/30/2021 14:47:41 - INFO - __main__ - Step 9090: {'lr': 0.0004971748817873367, 'samples': 1745280, 'steps': 9089, 'loss/train': 2.1897709369659424} 08/30/2021 14:47:42 - INFO - __main__ - Step 9091: {'lr': 0.0004971740861934117, 'samples': 1745472, 'steps': 9090, 'loss/train': 1.7882908582687378} 08/30/2021 14:47:44 - INFO - __main__ - Step 9092: {'lr': 0.000497173290488114, 'samples': 1745664, 'steps': 9091, 'loss/train': 1.8940757513046265} 08/30/2021 14:47:45 - INFO - __main__ - Step 9093: {'lr': 0.0004971724946714437, 'samples': 1745856, 'steps': 9092, 'loss/train': 1.9856022596359253} 08/30/2021 14:47:45 - INFO - __main__ - Step 9094: {'lr': 0.0004971716987434014, 'samples': 1746048, 'steps': 9093, 'loss/train': 2.1157851219177246} 08/30/2021 14:47:45 - INFO - __main__ - Step 9095: {'lr': 0.0004971709027039872, 'samples': 1746240, 'steps': 9094, 'loss/train': 1.0603735446929932} 08/30/2021 14:47:46 - INFO - __main__ - Step 9096: {'lr': 0.0004971701065532017, 'samples': 1746432, 'steps': 9095, 'loss/train': 1.6940349340438843} 08/30/2021 14:47:46 - INFO - __main__ - Step 9097: {'lr': 0.0004971693102910451, 'samples': 1746624, 'steps': 9096, 'loss/train': 2.09838604927063} 08/30/2021 14:47:47 - INFO - __main__ - Step 9098: {'lr': 0.0004971685139175179, 'samples': 1746816, 'steps': 9097, 'loss/train': 1.5774281024932861} 08/30/2021 14:47:48 - INFO - __main__ - Step 9099: {'lr': 0.0004971677174326204, 'samples': 1747008, 'steps': 9098, 'loss/train': 1.008238673210144} 08/30/2021 14:47:48 - INFO - __main__ - Step 9100: {'lr': 0.0004971669208363529, 'samples': 1747200, 'steps': 9099, 'loss/train': 2.993015766143799} 08/30/2021 14:47:49 - INFO - __main__ - Step 9101: {'lr': 0.0004971661241287157, 'samples': 1747392, 'steps': 9100, 'loss/train': 2.0401124954223633} 08/30/2021 14:47:49 - INFO - __main__ - Step 9102: {'lr': 0.0004971653273097094, 'samples': 1747584, 'steps': 9101, 'loss/train': 1.9922418594360352} 08/30/2021 14:47:51 - INFO - __main__ - Step 9103: {'lr': 0.0004971645303793342, 'samples': 1747776, 'steps': 9102, 'loss/train': 2.352294683456421} 08/30/2021 14:47:51 - INFO - __main__ - Step 9104: {'lr': 0.0004971637333375904, 'samples': 1747968, 'steps': 9103, 'loss/train': 2.1351101398468018} 08/30/2021 14:47:51 - INFO - __main__ - Step 9105: {'lr': 0.0004971629361844785, 'samples': 1748160, 'steps': 9104, 'loss/train': 1.8639625310897827} 08/30/2021 14:47:52 - INFO - __main__ - Step 9106: {'lr': 0.0004971621389199988, 'samples': 1748352, 'steps': 9105, 'loss/train': 1.1813985109329224} 08/30/2021 14:47:52 - INFO - __main__ - Step 9107: {'lr': 0.0004971613415441516, 'samples': 1748544, 'steps': 9106, 'loss/train': 0.2463376671075821} 08/30/2021 14:47:54 - INFO - __main__ - Step 9108: {'lr': 0.0004971605440569374, 'samples': 1748736, 'steps': 9107, 'loss/train': 1.4703516960144043} 08/30/2021 14:47:54 - INFO - __main__ - Step 9109: {'lr': 0.0004971597464583563, 'samples': 1748928, 'steps': 9108, 'loss/train': 2.059968948364258} 08/30/2021 14:47:54 - INFO - __main__ - Step 9110: {'lr': 0.0004971589487484091, 'samples': 1749120, 'steps': 9109, 'loss/train': 1.6971399784088135} 08/30/2021 14:47:55 - INFO - __main__ - Step 9111: {'lr': 0.0004971581509270956, 'samples': 1749312, 'steps': 9110, 'loss/train': 2.133328914642334} 08/30/2021 14:47:55 - INFO - __main__ - Step 9112: {'lr': 0.0004971573529944167, 'samples': 1749504, 'steps': 9111, 'loss/train': 1.024994969367981} 08/30/2021 14:47:57 - INFO - __main__ - Step 9113: {'lr': 0.0004971565549503723, 'samples': 1749696, 'steps': 9112, 'loss/train': 2.169511318206787} 08/30/2021 14:47:57 - INFO - __main__ - Step 9114: {'lr': 0.0004971557567949631, 'samples': 1749888, 'steps': 9113, 'loss/train': 2.1940808296203613} 08/30/2021 14:47:58 - INFO - __main__ - Step 9115: {'lr': 0.0004971549585281893, 'samples': 1750080, 'steps': 9114, 'loss/train': 1.2247960567474365} 08/30/2021 14:47:58 - INFO - __main__ - Step 9116: {'lr': 0.0004971541601500513, 'samples': 1750272, 'steps': 9115, 'loss/train': 1.9117571115493774} 08/30/2021 14:47:58 - INFO - __main__ - Step 9117: {'lr': 0.0004971533616605495, 'samples': 1750464, 'steps': 9116, 'loss/train': 2.526611328125} 08/30/2021 14:48:00 - INFO - __main__ - Step 9118: {'lr': 0.0004971525630596841, 'samples': 1750656, 'steps': 9117, 'loss/train': 2.296067714691162} 08/30/2021 14:48:00 - INFO - __main__ - Step 9119: {'lr': 0.0004971517643474556, 'samples': 1750848, 'steps': 9118, 'loss/train': 1.3903931379318237} 08/30/2021 14:48:01 - INFO - __main__ - Step 9120: {'lr': 0.0004971509655238643, 'samples': 1751040, 'steps': 9119, 'loss/train': 2.030454397201538} 08/30/2021 14:48:01 - INFO - __main__ - Step 9121: {'lr': 0.0004971501665889107, 'samples': 1751232, 'steps': 9120, 'loss/train': 2.2768170833587646} 08/30/2021 14:48:01 - INFO - __main__ - Step 9122: {'lr': 0.000497149367542595, 'samples': 1751424, 'steps': 9121, 'loss/train': 2.0302062034606934} 08/30/2021 14:48:03 - INFO - __main__ - Step 9123: {'lr': 0.0004971485683849176, 'samples': 1751616, 'steps': 9122, 'loss/train': 2.2915782928466797} 08/30/2021 14:48:04 - INFO - __main__ - Step 9124: {'lr': 0.0004971477691158788, 'samples': 1751808, 'steps': 9123, 'loss/train': 2.106600761413574} 08/30/2021 14:48:04 - INFO - __main__ - Step 9125: {'lr': 0.0004971469697354792, 'samples': 1752000, 'steps': 9124, 'loss/train': 2.216188907623291} 08/30/2021 14:48:04 - INFO - __main__ - Step 9126: {'lr': 0.0004971461702437188, 'samples': 1752192, 'steps': 9125, 'loss/train': 2.044036388397217} 08/30/2021 14:48:05 - INFO - __main__ - Step 9127: {'lr': 0.0004971453706405981, 'samples': 1752384, 'steps': 9126, 'loss/train': 2.044644355773926} 08/30/2021 14:48:05 - INFO - __main__ - Step 9128: {'lr': 0.0004971445709261177, 'samples': 1752576, 'steps': 9127, 'loss/train': 1.7316431999206543} 08/30/2021 14:48:06 - INFO - __main__ - Step 9129: {'lr': 0.0004971437711002777, 'samples': 1752768, 'steps': 9128, 'loss/train': 2.2101809978485107} 08/30/2021 14:48:07 - INFO - __main__ - Step 9130: {'lr': 0.0004971429711630786, 'samples': 1752960, 'steps': 9129, 'loss/train': 1.6328277587890625} 08/30/2021 14:48:07 - INFO - __main__ - Step 9131: {'lr': 0.0004971421711145207, 'samples': 1753152, 'steps': 9130, 'loss/train': 1.7874112129211426} 08/30/2021 14:48:08 - INFO - __main__ - Step 9132: {'lr': 0.0004971413709546043, 'samples': 1753344, 'steps': 9131, 'loss/train': 2.4208216667175293} 08/30/2021 14:48:08 - INFO - __main__ - Step 9133: {'lr': 0.0004971405706833297, 'samples': 1753536, 'steps': 9132, 'loss/train': 1.4205937385559082} 08/30/2021 14:48:09 - INFO - __main__ - Step 9134: {'lr': 0.0004971397703006974, 'samples': 1753728, 'steps': 9133, 'loss/train': 1.6057732105255127} 08/30/2021 14:48:10 - INFO - __main__ - Step 9135: {'lr': 0.0004971389698067079, 'samples': 1753920, 'steps': 9134, 'loss/train': 1.9402657747268677} 08/30/2021 14:48:10 - INFO - __main__ - Step 9136: {'lr': 0.0004971381692013612, 'samples': 1754112, 'steps': 9135, 'loss/train': 1.7869319915771484} 08/30/2021 14:48:11 - INFO - __main__ - Step 9137: {'lr': 0.000497137368484658, 'samples': 1754304, 'steps': 9136, 'loss/train': 1.8371540307998657} 08/30/2021 14:48:11 - INFO - __main__ - Step 9138: {'lr': 0.0004971365676565984, 'samples': 1754496, 'steps': 9137, 'loss/train': 1.7519088983535767} 08/30/2021 14:48:13 - INFO - __main__ - Step 9139: {'lr': 0.000497135766717183, 'samples': 1754688, 'steps': 9138, 'loss/train': 1.834581971168518} 08/30/2021 14:48:13 - INFO - __main__ - Step 9140: {'lr': 0.000497134965666412, 'samples': 1754880, 'steps': 9139, 'loss/train': 1.8342030048370361} 08/30/2021 14:48:13 - INFO - __main__ - Step 9141: {'lr': 0.0004971341645042857, 'samples': 1755072, 'steps': 9140, 'loss/train': 2.3751776218414307} 08/30/2021 14:48:14 - INFO - __main__ - Step 9142: {'lr': 0.0004971333632308047, 'samples': 1755264, 'steps': 9141, 'loss/train': 1.7557752132415771} 08/30/2021 14:48:14 - INFO - __main__ - Step 9143: {'lr': 0.0004971325618459691, 'samples': 1755456, 'steps': 9142, 'loss/train': 1.6465389728546143} 08/30/2021 14:48:17 - INFO - __main__ - Step 9144: {'lr': 0.0004971317603497795, 'samples': 1755648, 'steps': 9143, 'loss/train': 1.9172916412353516} 08/30/2021 14:48:17 - INFO - __main__ - Step 9145: {'lr': 0.000497130958742236, 'samples': 1755840, 'steps': 9144, 'loss/train': 1.1707823276519775} 08/30/2021 14:48:17 - INFO - __main__ - Step 9146: {'lr': 0.0004971301570233392, 'samples': 1756032, 'steps': 9145, 'loss/train': 1.9727407693862915} 08/30/2021 14:48:18 - INFO - __main__ - Step 9147: {'lr': 0.0004971293551930894, 'samples': 1756224, 'steps': 9146, 'loss/train': 0.9874273538589478} 08/30/2021 14:48:18 - INFO - __main__ - Step 9148: {'lr': 0.0004971285532514868, 'samples': 1756416, 'steps': 9147, 'loss/train': 1.1770209074020386} 08/30/2021 14:48:20 - INFO - __main__ - Step 9149: {'lr': 0.000497127751198532, 'samples': 1756608, 'steps': 9148, 'loss/train': 2.8048670291900635} 08/30/2021 14:48:20 - INFO - __main__ - Step 9150: {'lr': 0.0004971269490342252, 'samples': 1756800, 'steps': 9149, 'loss/train': 2.3494205474853516} 08/30/2021 14:48:21 - INFO - __main__ - Step 9151: {'lr': 0.0004971261467585669, 'samples': 1756992, 'steps': 9150, 'loss/train': 1.4400689601898193} 08/30/2021 14:48:21 - INFO - __main__ - Step 9152: {'lr': 0.0004971253443715572, 'samples': 1757184, 'steps': 9151, 'loss/train': 2.275338888168335} 08/30/2021 14:48:21 - INFO - __main__ - Step 9153: {'lr': 0.0004971245418731966, 'samples': 1757376, 'steps': 9152, 'loss/train': 0.3372267782688141} 08/30/2021 14:48:23 - INFO - __main__ - Step 9154: {'lr': 0.0004971237392634857, 'samples': 1757568, 'steps': 9153, 'loss/train': 2.4787211418151855} 08/30/2021 14:48:23 - INFO - __main__ - Step 9155: {'lr': 0.0004971229365424246, 'samples': 1757760, 'steps': 9154, 'loss/train': 1.8553352355957031} 08/30/2021 14:48:24 - INFO - __main__ - Step 9156: {'lr': 0.0004971221337100137, 'samples': 1757952, 'steps': 9155, 'loss/train': 1.895383358001709} 08/30/2021 14:48:24 - INFO - __main__ - Step 9157: {'lr': 0.0004971213307662534, 'samples': 1758144, 'steps': 9156, 'loss/train': 1.497563362121582} 08/30/2021 14:48:24 - INFO - __main__ - Step 9158: {'lr': 0.000497120527711144, 'samples': 1758336, 'steps': 9157, 'loss/train': 1.8233681917190552} 08/30/2021 14:48:26 - INFO - __main__ - Step 9159: {'lr': 0.0004971197245446859, 'samples': 1758528, 'steps': 9158, 'loss/train': 1.5231906175613403} 08/30/2021 14:48:26 - INFO - __main__ - Step 9160: {'lr': 0.0004971189212668794, 'samples': 1758720, 'steps': 9159, 'loss/train': 1.780755877494812} 08/30/2021 14:48:27 - INFO - __main__ - Step 9161: {'lr': 0.0004971181178777251, 'samples': 1758912, 'steps': 9160, 'loss/train': 2.956045150756836} 08/30/2021 14:48:27 - INFO - __main__ - Step 9162: {'lr': 0.0004971173143772231, 'samples': 1759104, 'steps': 9161, 'loss/train': 0.981243908405304} 08/30/2021 14:48:27 - INFO - __main__ - Step 9163: {'lr': 0.0004971165107653738, 'samples': 1759296, 'steps': 9162, 'loss/train': 1.437286615371704} 08/30/2021 14:48:28 - INFO - __main__ - Step 9164: {'lr': 0.0004971157070421776, 'samples': 1759488, 'steps': 9163, 'loss/train': 1.465252161026001} 08/30/2021 14:48:29 - INFO - __main__ - Step 9165: {'lr': 0.000497114903207635, 'samples': 1759680, 'steps': 9164, 'loss/train': 2.0578012466430664} 08/30/2021 14:48:30 - INFO - __main__ - Step 9166: {'lr': 0.0004971140992617462, 'samples': 1759872, 'steps': 9165, 'loss/train': 1.0709028244018555} 08/30/2021 14:48:30 - INFO - __main__ - Step 9167: {'lr': 0.0004971132952045115, 'samples': 1760064, 'steps': 9166, 'loss/train': 2.3895819187164307} 08/30/2021 14:48:30 - INFO - __main__ - Step 9168: {'lr': 0.0004971124910359315, 'samples': 1760256, 'steps': 9167, 'loss/train': 2.0490262508392334} 08/30/2021 14:48:32 - INFO - __main__ - Step 9169: {'lr': 0.0004971116867560064, 'samples': 1760448, 'steps': 9168, 'loss/train': 1.772620677947998} 08/30/2021 14:48:32 - INFO - __main__ - Step 9170: {'lr': 0.0004971108823647365, 'samples': 1760640, 'steps': 9169, 'loss/train': 1.069950819015503} 08/30/2021 14:48:33 - INFO - __main__ - Step 9171: {'lr': 0.0004971100778621223, 'samples': 1760832, 'steps': 9170, 'loss/train': 1.874866247177124} 08/30/2021 14:48:33 - INFO - __main__ - Step 9172: {'lr': 0.0004971092732481641, 'samples': 1761024, 'steps': 9171, 'loss/train': 2.2963037490844727} 08/30/2021 14:48:33 - INFO - __main__ - Step 9173: {'lr': 0.0004971084685228623, 'samples': 1761216, 'steps': 9172, 'loss/train': 2.192671298980713} 08/30/2021 14:48:34 - INFO - __main__ - Step 9174: {'lr': 0.0004971076636862172, 'samples': 1761408, 'steps': 9173, 'loss/train': 1.6010810136795044} 08/30/2021 14:48:35 - INFO - __main__ - Step 9175: {'lr': 0.0004971068587382293, 'samples': 1761600, 'steps': 9174, 'loss/train': 1.7634247541427612} 08/30/2021 14:48:36 - INFO - __main__ - Step 9176: {'lr': 0.0004971060536788988, 'samples': 1761792, 'steps': 9175, 'loss/train': 2.308720350265503} 08/30/2021 14:48:36 - INFO - __main__ - Step 9177: {'lr': 0.000497105248508226, 'samples': 1761984, 'steps': 9176, 'loss/train': 1.5760347843170166} 08/30/2021 14:48:36 - INFO - __main__ - Step 9178: {'lr': 0.0004971044432262115, 'samples': 1762176, 'steps': 9177, 'loss/train': 2.1757302284240723} 08/30/2021 14:48:37 - INFO - __main__ - Step 9179: {'lr': 0.0004971036378328556, 'samples': 1762368, 'steps': 9178, 'loss/train': 1.770199179649353} 08/30/2021 14:48:38 - INFO - __main__ - Step 9180: {'lr': 0.0004971028323281586, 'samples': 1762560, 'steps': 9179, 'loss/train': 1.6086231470108032} 08/30/2021 14:48:39 - INFO - __main__ - Step 9181: {'lr': 0.0004971020267121208, 'samples': 1762752, 'steps': 9180, 'loss/train': 1.730339765548706} 08/30/2021 14:48:39 - INFO - __main__ - Step 9182: {'lr': 0.0004971012209847427, 'samples': 1762944, 'steps': 9181, 'loss/train': 2.1406893730163574} 08/30/2021 14:48:40 - INFO - __main__ - Step 9183: {'lr': 0.0004971004151460245, 'samples': 1763136, 'steps': 9182, 'loss/train': 0.3436744213104248} 08/30/2021 14:48:40 - INFO - __main__ - Step 9184: {'lr': 0.0004970996091959668, 'samples': 1763328, 'steps': 9183, 'loss/train': 2.0354251861572266} 08/30/2021 14:48:42 - INFO - __main__ - Step 9185: {'lr': 0.0004970988031345698, 'samples': 1763520, 'steps': 9184, 'loss/train': 1.9346362352371216} 08/30/2021 14:48:43 - INFO - __main__ - Step 9186: {'lr': 0.0004970979969618338, 'samples': 1763712, 'steps': 9185, 'loss/train': 1.3773599863052368} 08/30/2021 14:48:43 - INFO - __main__ - Step 9187: {'lr': 0.0004970971906777593, 'samples': 1763904, 'steps': 9186, 'loss/train': 2.4897844791412354} 08/30/2021 14:48:43 - INFO - __main__ - Step 9188: {'lr': 0.0004970963842823468, 'samples': 1764096, 'steps': 9187, 'loss/train': 1.7319952249526978} 08/30/2021 14:48:44 - INFO - __main__ - Step 9189: {'lr': 0.0004970955777755963, 'samples': 1764288, 'steps': 9188, 'loss/train': 2.0576400756835938} 08/30/2021 14:48:45 - INFO - __main__ - Step 9190: {'lr': 0.0004970947711575083, 'samples': 1764480, 'steps': 9189, 'loss/train': 2.112687349319458} 08/30/2021 14:48:46 - INFO - __main__ - Step 9191: {'lr': 0.0004970939644280833, 'samples': 1764672, 'steps': 9190, 'loss/train': 1.8706601858139038} 08/30/2021 14:48:46 - INFO - __main__ - Step 9192: {'lr': 0.0004970931575873215, 'samples': 1764864, 'steps': 9191, 'loss/train': 2.5577428340911865} 08/30/2021 14:48:46 - INFO - __main__ - Step 9193: {'lr': 0.0004970923506352234, 'samples': 1765056, 'steps': 9192, 'loss/train': 1.8557285070419312} 08/30/2021 14:48:47 - INFO - __main__ - Step 9194: {'lr': 0.0004970915435717893, 'samples': 1765248, 'steps': 9193, 'loss/train': 2.146958589553833} 08/30/2021 14:48:47 - INFO - __main__ - Step 9195: {'lr': 0.0004970907363970196, 'samples': 1765440, 'steps': 9194, 'loss/train': 1.617411732673645} 08/30/2021 14:48:49 - INFO - __main__ - Step 9196: {'lr': 0.0004970899291109145, 'samples': 1765632, 'steps': 9195, 'loss/train': 0.2605523467063904} 08/30/2021 14:48:50 - INFO - __main__ - Step 9197: {'lr': 0.0004970891217134746, 'samples': 1765824, 'steps': 9196, 'loss/train': 1.556320071220398} 08/30/2021 14:48:50 - INFO - __main__ - Step 9198: {'lr': 0.0004970883142047001, 'samples': 1766016, 'steps': 9197, 'loss/train': 1.5277460813522339} 08/30/2021 14:48:51 - INFO - __main__ - Step 9199: {'lr': 0.0004970875065845914, 'samples': 1766208, 'steps': 9198, 'loss/train': 2.1826789379119873} 08/30/2021 14:48:51 - INFO - __main__ - Step 9200: {'lr': 0.000497086698853149, 'samples': 1766400, 'steps': 9199, 'loss/train': 2.515925645828247} 08/30/2021 14:48:53 - INFO - __main__ - Step 9201: {'lr': 0.0004970858910103731, 'samples': 1766592, 'steps': 9200, 'loss/train': 1.4338728189468384} 08/30/2021 14:48:53 - INFO - __main__ - Step 9202: {'lr': 0.0004970850830562641, 'samples': 1766784, 'steps': 9201, 'loss/train': 0.18572726845741272} 08/30/2021 14:48:53 - INFO - __main__ - Step 9203: {'lr': 0.0004970842749908223, 'samples': 1766976, 'steps': 9202, 'loss/train': 2.248081922531128} 08/30/2021 14:48:54 - INFO - __main__ - Step 9204: {'lr': 0.0004970834668140482, 'samples': 1767168, 'steps': 9203, 'loss/train': 2.0930335521698} 08/30/2021 14:48:54 - INFO - __main__ - Step 9205: {'lr': 0.0004970826585259421, 'samples': 1767360, 'steps': 9204, 'loss/train': 2.057454824447632} 08/30/2021 14:48:56 - INFO - __main__ - Step 9206: {'lr': 0.0004970818501265044, 'samples': 1767552, 'steps': 9205, 'loss/train': 1.6054198741912842} 08/30/2021 14:48:57 - INFO - __main__ - Step 9207: {'lr': 0.0004970810416157354, 'samples': 1767744, 'steps': 9206, 'loss/train': 1.9816429615020752} 08/30/2021 14:48:57 - INFO - __main__ - Step 9208: {'lr': 0.0004970802329936355, 'samples': 1767936, 'steps': 9207, 'loss/train': 1.237385630607605} 08/30/2021 14:48:57 - INFO - __main__ - Step 9209: {'lr': 0.000497079424260205, 'samples': 1768128, 'steps': 9208, 'loss/train': 1.6543488502502441} 08/30/2021 14:48:58 - INFO - __main__ - Step 9210: {'lr': 0.0004970786154154444, 'samples': 1768320, 'steps': 9209, 'loss/train': 2.1490519046783447} 08/30/2021 14:48:58 - INFO - __main__ - Step 9211: {'lr': 0.000497077806459354, 'samples': 1768512, 'steps': 9210, 'loss/train': 0.6202272176742554} 08/30/2021 14:49:00 - INFO - __main__ - Step 9212: {'lr': 0.0004970769973919341, 'samples': 1768704, 'steps': 9211, 'loss/train': 0.711371123790741} 08/30/2021 14:49:00 - INFO - __main__ - Step 9213: {'lr': 0.0004970761882131851, 'samples': 1768896, 'steps': 9212, 'loss/train': 2.2477684020996094} 08/30/2021 14:49:01 - INFO - __main__ - Step 9214: {'lr': 0.0004970753789231074, 'samples': 1769088, 'steps': 9213, 'loss/train': 2.07246470451355} 08/30/2021 14:49:01 - INFO - __main__ - Step 9215: {'lr': 0.0004970745695217014, 'samples': 1769280, 'steps': 9214, 'loss/train': 1.9545146226882935} 08/30/2021 14:49:01 - INFO - __main__ - Step 9216: {'lr': 0.0004970737600089673, 'samples': 1769472, 'steps': 9215, 'loss/train': 0.15511734783649445} 08/30/2021 14:49:03 - INFO - __main__ - Step 9217: {'lr': 0.0004970729503849057, 'samples': 1769664, 'steps': 9216, 'loss/train': 2.0614912509918213} 08/30/2021 14:49:03 - INFO - __main__ - Step 9218: {'lr': 0.0004970721406495168, 'samples': 1769856, 'steps': 9217, 'loss/train': 1.8605259656906128} 08/30/2021 14:49:04 - INFO - __main__ - Step 9219: {'lr': 0.000497071330802801, 'samples': 1770048, 'steps': 9218, 'loss/train': 2.124539613723755} 08/30/2021 14:49:04 - INFO - __main__ - Step 9220: {'lr': 0.0004970705208447587, 'samples': 1770240, 'steps': 9219, 'loss/train': 1.8342972993850708} 08/30/2021 14:49:04 - INFO - __main__ - Step 9221: {'lr': 0.0004970697107753902, 'samples': 1770432, 'steps': 9220, 'loss/train': 1.8214855194091797} 08/30/2021 14:49:06 - INFO - __main__ - Step 9222: {'lr': 0.0004970689005946959, 'samples': 1770624, 'steps': 9221, 'loss/train': 1.7121367454528809} 08/30/2021 14:49:06 - INFO - __main__ - Step 9223: {'lr': 0.0004970680903026762, 'samples': 1770816, 'steps': 9222, 'loss/train': 1.2820076942443848} 08/30/2021 14:49:06 - INFO - __main__ - Step 9224: {'lr': 0.0004970672798993313, 'samples': 1771008, 'steps': 9223, 'loss/train': 2.2044875621795654} 08/30/2021 14:49:07 - INFO - __main__ - Step 9225: {'lr': 0.0004970664693846618, 'samples': 1771200, 'steps': 9224, 'loss/train': 2.00738787651062} 08/30/2021 14:49:07 - INFO - __main__ - Step 9226: {'lr': 0.000497065658758668, 'samples': 1771392, 'steps': 9225, 'loss/train': 1.7194164991378784} 08/30/2021 14:49:09 - INFO - __main__ - Step 9227: {'lr': 0.0004970648480213502, 'samples': 1771584, 'steps': 9226, 'loss/train': 2.0624279975891113} 08/30/2021 14:49:09 - INFO - __main__ - Step 9228: {'lr': 0.0004970640371727088, 'samples': 1771776, 'steps': 9227, 'loss/train': 1.580984354019165} 08/30/2021 14:49:10 - INFO - __main__ - Step 9229: {'lr': 0.0004970632262127441, 'samples': 1771968, 'steps': 9228, 'loss/train': 1.6961482763290405} 08/30/2021 14:49:10 - INFO - __main__ - Step 9230: {'lr': 0.0004970624151414565, 'samples': 1772160, 'steps': 9229, 'loss/train': 1.8536534309387207} 08/30/2021 14:49:10 - INFO - __main__ - Step 9231: {'lr': 0.0004970616039588465, 'samples': 1772352, 'steps': 9230, 'loss/train': 1.6463274955749512} 08/30/2021 14:49:12 - INFO - __main__ - Step 9232: {'lr': 0.0004970607926649143, 'samples': 1772544, 'steps': 9231, 'loss/train': 1.9842034578323364} 08/30/2021 14:49:13 - INFO - __main__ - Step 9233: {'lr': 0.0004970599812596603, 'samples': 1772736, 'steps': 9232, 'loss/train': 0.9124844670295715} 08/30/2021 14:49:13 - INFO - __main__ - Step 9234: {'lr': 0.0004970591697430849, 'samples': 1772928, 'steps': 9233, 'loss/train': 2.3479666709899902} 08/30/2021 14:49:13 - INFO - __main__ - Step 9235: {'lr': 0.0004970583581151885, 'samples': 1773120, 'steps': 9234, 'loss/train': 2.9768569469451904} 08/30/2021 14:49:14 - INFO - __main__ - Step 9236: {'lr': 0.0004970575463759713, 'samples': 1773312, 'steps': 9235, 'loss/train': 1.4549553394317627} 08/30/2021 14:49:14 - INFO - __main__ - Step 9237: {'lr': 0.0004970567345254339, 'samples': 1773504, 'steps': 9236, 'loss/train': 1.7700152397155762} 08/30/2021 14:49:15 - INFO - __main__ - Step 9238: {'lr': 0.0004970559225635765, 'samples': 1773696, 'steps': 9237, 'loss/train': 1.04756498336792} 08/30/2021 14:49:16 - INFO - __main__ - Step 9239: {'lr': 0.0004970551104903995, 'samples': 1773888, 'steps': 9238, 'loss/train': 2.0631184577941895} 08/30/2021 14:49:16 - INFO - __main__ - Step 9240: {'lr': 0.0004970542983059033, 'samples': 1774080, 'steps': 9239, 'loss/train': 1.9168970584869385} 08/30/2021 14:49:17 - INFO - __main__ - Step 9241: {'lr': 0.0004970534860100883, 'samples': 1774272, 'steps': 9240, 'loss/train': 1.7760001420974731} 08/30/2021 14:49:17 - INFO - __main__ - Step 9242: {'lr': 0.0004970526736029547, 'samples': 1774464, 'steps': 9241, 'loss/train': 1.739051342010498} 08/30/2021 14:49:19 - INFO - __main__ - Step 9243: {'lr': 0.000497051861084503, 'samples': 1774656, 'steps': 9242, 'loss/train': 2.3888537883758545} 08/30/2021 14:49:19 - INFO - __main__ - Step 9244: {'lr': 0.0004970510484547336, 'samples': 1774848, 'steps': 9243, 'loss/train': 2.1341841220855713} 08/30/2021 14:49:20 - INFO - __main__ - Step 9245: {'lr': 0.0004970502357136468, 'samples': 1775040, 'steps': 9244, 'loss/train': 2.0101072788238525} 08/30/2021 14:49:20 - INFO - __main__ - Step 9246: {'lr': 0.0004970494228612429, 'samples': 1775232, 'steps': 9245, 'loss/train': 0.35101956129074097} 08/30/2021 14:49:20 - INFO - __main__ - Step 9247: {'lr': 0.0004970486098975224, 'samples': 1775424, 'steps': 9246, 'loss/train': 0.26647070050239563} 08/30/2021 14:49:21 - INFO - __main__ - Step 9248: {'lr': 0.0004970477968224856, 'samples': 1775616, 'steps': 9247, 'loss/train': 1.8340070247650146} 08/30/2021 14:49:22 - INFO - __main__ - Step 9249: {'lr': 0.000497046983636133, 'samples': 1775808, 'steps': 9248, 'loss/train': 2.2194974422454834} 08/30/2021 14:49:23 - INFO - __main__ - Step 9250: {'lr': 0.0004970461703384647, 'samples': 1776000, 'steps': 9249, 'loss/train': 2.377347946166992} 08/30/2021 14:49:23 - INFO - __main__ - Step 9251: {'lr': 0.0004970453569294812, 'samples': 1776192, 'steps': 9250, 'loss/train': 1.8733460903167725} 08/30/2021 14:49:23 - INFO - __main__ - Step 9252: {'lr': 0.000497044543409183, 'samples': 1776384, 'steps': 9251, 'loss/train': 1.556471347808838} 08/30/2021 14:49:24 - INFO - __main__ - Step 9253: {'lr': 0.0004970437297775702, 'samples': 1776576, 'steps': 9252, 'loss/train': 2.4468936920166016} 08/30/2021 14:49:26 - INFO - __main__ - Step 9254: {'lr': 0.0004970429160346433, 'samples': 1776768, 'steps': 9253, 'loss/train': 2.3511977195739746} 08/30/2021 14:49:26 - INFO - __main__ - Step 9255: {'lr': 0.0004970421021804027, 'samples': 1776960, 'steps': 9254, 'loss/train': 1.5434702634811401} 08/30/2021 14:49:27 - INFO - __main__ - Step 9256: {'lr': 0.0004970412882148488, 'samples': 1777152, 'steps': 9255, 'loss/train': 1.8306480646133423} 08/30/2021 14:49:27 - INFO - __main__ - Step 9257: {'lr': 0.0004970404741379818, 'samples': 1777344, 'steps': 9256, 'loss/train': 1.9176039695739746} 08/30/2021 14:49:27 - INFO - __main__ - Step 9258: {'lr': 0.0004970396599498023, 'samples': 1777536, 'steps': 9257, 'loss/train': 1.1820268630981445} 08/30/2021 14:49:29 - INFO - __main__ - Step 9259: {'lr': 0.0004970388456503105, 'samples': 1777728, 'steps': 9258, 'loss/train': 1.8463993072509766} 08/30/2021 14:49:29 - INFO - __main__ - Step 9260: {'lr': 0.0004970380312395069, 'samples': 1777920, 'steps': 9259, 'loss/train': 1.7795135974884033} 08/30/2021 14:49:30 - INFO - __main__ - Step 9261: {'lr': 0.0004970372167173915, 'samples': 1778112, 'steps': 9260, 'loss/train': 1.6793103218078613} 08/30/2021 14:49:30 - INFO - __main__ - Step 9262: {'lr': 0.0004970364020839652, 'samples': 1778304, 'steps': 9261, 'loss/train': 2.0650460720062256} 08/30/2021 14:49:30 - INFO - __main__ - Step 9263: {'lr': 0.0004970355873392281, 'samples': 1778496, 'steps': 9262, 'loss/train': 1.8135298490524292} 08/30/2021 14:49:32 - INFO - __main__ - Step 9264: {'lr': 0.0004970347724831804, 'samples': 1778688, 'steps': 9263, 'loss/train': 1.5799111127853394} 08/30/2021 14:49:33 - INFO - __main__ - Step 9265: {'lr': 0.0004970339575158228, 'samples': 1778880, 'steps': 9264, 'loss/train': 3.0635735988616943} 08/30/2021 14:49:33 - INFO - __main__ - Step 9266: {'lr': 0.0004970331424371555, 'samples': 1779072, 'steps': 9265, 'loss/train': 0.1606554388999939} 08/30/2021 14:49:33 - INFO - __main__ - Step 9267: {'lr': 0.0004970323272471788, 'samples': 1779264, 'steps': 9266, 'loss/train': 1.526602864265442} 08/30/2021 14:49:34 - INFO - __main__ - Step 9268: {'lr': 0.0004970315119458931, 'samples': 1779456, 'steps': 9267, 'loss/train': 1.529158353805542} 08/30/2021 14:49:35 - INFO - __main__ - Step 9269: {'lr': 0.000497030696533299, 'samples': 1779648, 'steps': 9268, 'loss/train': 1.557956576347351} 08/30/2021 14:49:35 - INFO - __main__ - Step 9270: {'lr': 0.0004970298810093965, 'samples': 1779840, 'steps': 9269, 'loss/train': 1.7843255996704102} 08/30/2021 14:49:36 - INFO - __main__ - Step 9271: {'lr': 0.0004970290653741863, 'samples': 1780032, 'steps': 9270, 'loss/train': 1.910145878791809} 08/30/2021 14:49:36 - INFO - __main__ - Step 9272: {'lr': 0.0004970282496276684, 'samples': 1780224, 'steps': 9271, 'loss/train': 1.6822428703308105} 08/30/2021 14:49:37 - INFO - __main__ - Step 9273: {'lr': 0.0004970274337698436, 'samples': 1780416, 'steps': 9272, 'loss/train': 2.1968302726745605} 08/30/2021 14:49:37 - INFO - __main__ - Step 9274: {'lr': 0.000497026617800712, 'samples': 1780608, 'steps': 9273, 'loss/train': 1.8006296157836914} 08/30/2021 14:49:38 - INFO - __main__ - Step 9275: {'lr': 0.000497025801720274, 'samples': 1780800, 'steps': 9274, 'loss/train': 1.6218938827514648} 08/30/2021 14:49:39 - INFO - __main__ - Step 9276: {'lr': 0.00049702498552853, 'samples': 1780992, 'steps': 9275, 'loss/train': 1.7838683128356934} 08/30/2021 14:49:39 - INFO - __main__ - Step 9277: {'lr': 0.0004970241692254803, 'samples': 1781184, 'steps': 9276, 'loss/train': 2.7925031185150146} 08/30/2021 14:49:40 - INFO - __main__ - Step 9278: {'lr': 0.0004970233528111253, 'samples': 1781376, 'steps': 9277, 'loss/train': 2.448387384414673} 08/30/2021 14:49:40 - INFO - __main__ - Step 9279: {'lr': 0.0004970225362854654, 'samples': 1781568, 'steps': 9278, 'loss/train': 1.8577622175216675} 08/30/2021 14:49:41 - INFO - __main__ - Step 9280: {'lr': 0.0004970217196485011, 'samples': 1781760, 'steps': 9279, 'loss/train': 1.6791255474090576} 08/30/2021 14:49:42 - INFO - __main__ - Step 9281: {'lr': 0.0004970209029002325, 'samples': 1781952, 'steps': 9280, 'loss/train': 1.815529704093933} 08/30/2021 14:49:42 - INFO - __main__ - Step 9282: {'lr': 0.0004970200860406601, 'samples': 1782144, 'steps': 9281, 'loss/train': 1.7856688499450684} 08/30/2021 14:49:42 - INFO - __main__ - Step 9283: {'lr': 0.0004970192690697843, 'samples': 1782336, 'steps': 9282, 'loss/train': 1.3884061574935913} 08/30/2021 14:49:43 - INFO - __main__ - Step 9284: {'lr': 0.0004970184519876053, 'samples': 1782528, 'steps': 9283, 'loss/train': 1.9603992700576782} 08/30/2021 14:49:44 - INFO - __main__ - Step 9285: {'lr': 0.0004970176347941237, 'samples': 1782720, 'steps': 9284, 'loss/train': 2.057486057281494} 08/30/2021 14:49:45 - INFO - __main__ - Step 9286: {'lr': 0.0004970168174893398, 'samples': 1782912, 'steps': 9285, 'loss/train': 1.7812455892562866} 08/30/2021 14:49:45 - INFO - __main__ - Step 9287: {'lr': 0.0004970160000732539, 'samples': 1783104, 'steps': 9286, 'loss/train': 0.725993812084198} 08/30/2021 14:49:46 - INFO - __main__ - Step 9288: {'lr': 0.0004970151825458664, 'samples': 1783296, 'steps': 9287, 'loss/train': 2.4390835762023926} 08/30/2021 14:49:46 - INFO - __main__ - Step 9289: {'lr': 0.0004970143649071777, 'samples': 1783488, 'steps': 9288, 'loss/train': 2.1218433380126953} 08/30/2021 14:49:47 - INFO - __main__ - Step 9290: {'lr': 0.0004970135471571881, 'samples': 1783680, 'steps': 9289, 'loss/train': 1.61763334274292} 08/30/2021 14:49:48 - INFO - __main__ - Step 9291: {'lr': 0.000497012729295898, 'samples': 1783872, 'steps': 9290, 'loss/train': 2.6236159801483154} 08/30/2021 14:49:48 - INFO - __main__ - Step 9292: {'lr': 0.0004970119113233078, 'samples': 1784064, 'steps': 9291, 'loss/train': 1.4758740663528442} 08/30/2021 14:49:48 - INFO - __main__ - Step 9293: {'lr': 0.0004970110932394178, 'samples': 1784256, 'steps': 9292, 'loss/train': 2.0144641399383545} 08/30/2021 14:49:49 - INFO - __main__ - Step 9294: {'lr': 0.0004970102750442285, 'samples': 1784448, 'steps': 9293, 'loss/train': 0.9846737384796143} 08/30/2021 14:49:51 - INFO - __main__ - Step 9295: {'lr': 0.0004970094567377402, 'samples': 1784640, 'steps': 9294, 'loss/train': 1.7332916259765625} 08/30/2021 14:49:51 - INFO - __main__ - Step 9296: {'lr': 0.0004970086383199532, 'samples': 1784832, 'steps': 9295, 'loss/train': 1.6792523860931396} 08/30/2021 14:49:51 - INFO - __main__ - Step 9297: {'lr': 0.0004970078197908678, 'samples': 1785024, 'steps': 9296, 'loss/train': 2.2584574222564697} 08/30/2021 14:49:52 - INFO - __main__ - Step 9298: {'lr': 0.0004970070011504846, 'samples': 1785216, 'steps': 9297, 'loss/train': 1.9478328227996826} 08/30/2021 14:49:52 - INFO - __main__ - Step 9299: {'lr': 0.0004970061823988038, 'samples': 1785408, 'steps': 9298, 'loss/train': 2.174748659133911} 08/30/2021 14:49:53 - INFO - __main__ - Step 9300: {'lr': 0.0004970053635358259, 'samples': 1785600, 'steps': 9299, 'loss/train': 1.427147626876831} 08/30/2021 14:49:54 - INFO - __main__ - Step 9301: {'lr': 0.0004970045445615512, 'samples': 1785792, 'steps': 9300, 'loss/train': 2.43338680267334} 08/30/2021 14:49:54 - INFO - __main__ - Step 9302: {'lr': 0.00049700372547598, 'samples': 1785984, 'steps': 9301, 'loss/train': 2.0076563358306885} 08/30/2021 14:49:55 - INFO - __main__ - Step 9303: {'lr': 0.0004970029062791128, 'samples': 1786176, 'steps': 9302, 'loss/train': 1.8735857009887695} 08/30/2021 14:49:55 - INFO - __main__ - Step 9304: {'lr': 0.0004970020869709498, 'samples': 1786368, 'steps': 9303, 'loss/train': 1.7932754755020142} 08/30/2021 14:49:55 - INFO - __main__ - Step 9305: {'lr': 0.0004970012675514915, 'samples': 1786560, 'steps': 9304, 'loss/train': 2.0158021450042725} 08/30/2021 14:49:58 - INFO - __main__ - Step 9306: {'lr': 0.0004970004480207384, 'samples': 1786752, 'steps': 9305, 'loss/train': 2.2706642150878906} 08/30/2021 14:49:58 - INFO - __main__ - Step 9307: {'lr': 0.0004969996283786905, 'samples': 1786944, 'steps': 9306, 'loss/train': 1.4431320428848267} 08/30/2021 14:49:58 - INFO - __main__ - Step 9308: {'lr': 0.0004969988086253486, 'samples': 1787136, 'steps': 9307, 'loss/train': 2.0406265258789062} 08/30/2021 14:49:59 - INFO - __main__ - Step 9309: {'lr': 0.0004969979887607125, 'samples': 1787328, 'steps': 9308, 'loss/train': 1.8976439237594604} 08/30/2021 14:49:59 - INFO - __main__ - Step 9310: {'lr': 0.0004969971687847832, 'samples': 1787520, 'steps': 9309, 'loss/train': 1.7175661325454712} 08/30/2021 14:50:01 - INFO - __main__ - Step 9311: {'lr': 0.0004969963486975607, 'samples': 1787712, 'steps': 9310, 'loss/train': 1.9850002527236938} 08/30/2021 14:50:01 - INFO - __main__ - Step 9312: {'lr': 0.0004969955284990455, 'samples': 1787904, 'steps': 9311, 'loss/train': 2.112910747528076} 08/30/2021 14:50:02 - INFO - __main__ - Step 9313: {'lr': 0.0004969947081892379, 'samples': 1788096, 'steps': 9312, 'loss/train': 0.1662347912788391} 08/30/2021 14:50:02 - INFO - __main__ - Step 9314: {'lr': 0.0004969938877681383, 'samples': 1788288, 'steps': 9313, 'loss/train': 0.2272965908050537} 08/30/2021 14:50:02 - INFO - __main__ - Step 9315: {'lr': 0.0004969930672357471, 'samples': 1788480, 'steps': 9314, 'loss/train': 1.179009199142456} 08/30/2021 14:50:04 - INFO - __main__ - Step 9316: {'lr': 0.0004969922465920645, 'samples': 1788672, 'steps': 9315, 'loss/train': 1.317862868309021} 08/30/2021 14:50:05 - INFO - __main__ - Step 9317: {'lr': 0.0004969914258370912, 'samples': 1788864, 'steps': 9316, 'loss/train': 1.5546584129333496} 08/30/2021 14:50:05 - INFO - __main__ - Step 9318: {'lr': 0.0004969906049708272, 'samples': 1789056, 'steps': 9317, 'loss/train': 1.9591002464294434} 08/30/2021 14:50:05 - INFO - __main__ - Step 9319: {'lr': 0.0004969897839932732, 'samples': 1789248, 'steps': 9318, 'loss/train': 0.42939651012420654} 08/30/2021 14:50:06 - INFO - __main__ - Step 9320: {'lr': 0.0004969889629044293, 'samples': 1789440, 'steps': 9319, 'loss/train': 2.0537118911743164} 08/30/2021 14:50:07 - INFO - __main__ - Step 9321: {'lr': 0.000496988141704296, 'samples': 1789632, 'steps': 9320, 'loss/train': 1.2576552629470825} 08/30/2021 14:50:08 - INFO - __main__ - Step 9322: {'lr': 0.0004969873203928737, 'samples': 1789824, 'steps': 9321, 'loss/train': 1.7723240852355957} 08/30/2021 14:50:08 - INFO - __main__ - Step 9323: {'lr': 0.0004969864989701626, 'samples': 1790016, 'steps': 9322, 'loss/train': 2.057669162750244} 08/30/2021 14:50:08 - INFO - __main__ - Step 9324: {'lr': 0.0004969856774361634, 'samples': 1790208, 'steps': 9323, 'loss/train': 1.8261970281600952} 08/30/2021 14:50:09 - INFO - __main__ - Step 9325: {'lr': 0.0004969848557908761, 'samples': 1790400, 'steps': 9324, 'loss/train': 1.5761268138885498} 08/30/2021 14:50:09 - INFO - __main__ - Step 9326: {'lr': 0.0004969840340343013, 'samples': 1790592, 'steps': 9325, 'loss/train': 2.015223264694214} 08/30/2021 14:50:11 - INFO - __main__ - Step 9327: {'lr': 0.0004969832121664394, 'samples': 1790784, 'steps': 9326, 'loss/train': 1.8708689212799072} 08/30/2021 14:50:11 - INFO - __main__ - Step 9328: {'lr': 0.0004969823901872906, 'samples': 1790976, 'steps': 9327, 'loss/train': 2.039632558822632} 08/30/2021 14:50:11 - INFO - __main__ - Step 9329: {'lr': 0.0004969815680968552, 'samples': 1791168, 'steps': 9328, 'loss/train': 2.0620734691619873} 08/30/2021 14:50:12 - INFO - __main__ - Step 9330: {'lr': 0.0004969807458951339, 'samples': 1791360, 'steps': 9329, 'loss/train': 1.9500455856323242} 08/30/2021 14:50:12 - INFO - __main__ - Step 9331: {'lr': 0.0004969799235821268, 'samples': 1791552, 'steps': 9330, 'loss/train': 1.9190891981124878} 08/30/2021 14:50:14 - INFO - __main__ - Step 9332: {'lr': 0.0004969791011578344, 'samples': 1791744, 'steps': 9331, 'loss/train': 1.569718837738037} 08/30/2021 14:50:14 - INFO - __main__ - Step 9333: {'lr': 0.000496978278622257, 'samples': 1791936, 'steps': 9332, 'loss/train': 2.2379322052001953} 08/30/2021 14:50:15 - INFO - __main__ - Step 9334: {'lr': 0.000496977455975395, 'samples': 1792128, 'steps': 9333, 'loss/train': 0.2754552364349365} 08/30/2021 14:50:15 - INFO - __main__ - Step 9335: {'lr': 0.0004969766332172488, 'samples': 1792320, 'steps': 9334, 'loss/train': 2.2136521339416504} 08/30/2021 14:50:15 - INFO - __main__ - Step 9336: {'lr': 0.0004969758103478187, 'samples': 1792512, 'steps': 9335, 'loss/train': 1.8635731935501099} 08/30/2021 14:50:17 - INFO - __main__ - Step 9337: {'lr': 0.0004969749873671051, 'samples': 1792704, 'steps': 9336, 'loss/train': 1.954540729522705} 08/30/2021 14:50:17 - INFO - __main__ - Step 9338: {'lr': 0.0004969741642751085, 'samples': 1792896, 'steps': 9337, 'loss/train': 2.115929126739502} 08/30/2021 14:50:18 - INFO - __main__ - Step 9339: {'lr': 0.000496973341071829, 'samples': 1793088, 'steps': 9338, 'loss/train': 2.2687363624572754} 08/30/2021 14:50:18 - INFO - __main__ - Step 9340: {'lr': 0.0004969725177572672, 'samples': 1793280, 'steps': 9339, 'loss/train': 1.9051958322525024} 08/30/2021 14:50:18 - INFO - __main__ - Step 9341: {'lr': 0.0004969716943314234, 'samples': 1793472, 'steps': 9340, 'loss/train': 1.7493877410888672} 08/30/2021 14:50:20 - INFO - __main__ - Step 9342: {'lr': 0.0004969708707942979, 'samples': 1793664, 'steps': 9341, 'loss/train': 2.1003103256225586} 08/30/2021 14:50:20 - INFO - __main__ - Step 9343: {'lr': 0.0004969700471458913, 'samples': 1793856, 'steps': 9342, 'loss/train': 1.5054258108139038} 08/30/2021 14:50:21 - INFO - __main__ - Step 9344: {'lr': 0.0004969692233862036, 'samples': 1794048, 'steps': 9343, 'loss/train': 2.7108588218688965} 08/30/2021 14:50:21 - INFO - __main__ - Step 9345: {'lr': 0.0004969683995152355, 'samples': 1794240, 'steps': 9344, 'loss/train': 1.6341618299484253} 08/30/2021 14:50:21 - INFO - __main__ - Step 9346: {'lr': 0.0004969675755329872, 'samples': 1794432, 'steps': 9345, 'loss/train': 2.0203230381011963} 08/30/2021 14:50:23 - INFO - __main__ - Step 9347: {'lr': 0.0004969667514394592, 'samples': 1794624, 'steps': 9346, 'loss/train': 2.1350884437561035} 08/30/2021 14:50:23 - INFO - __main__ - Step 9348: {'lr': 0.0004969659272346517, 'samples': 1794816, 'steps': 9347, 'loss/train': 1.983215093612671} 08/30/2021 14:50:24 - INFO - __main__ - Step 9349: {'lr': 0.0004969651029185652, 'samples': 1795008, 'steps': 9348, 'loss/train': 2.0139341354370117} 08/30/2021 14:50:24 - INFO - __main__ - Step 9350: {'lr': 0.0004969642784912001, 'samples': 1795200, 'steps': 9349, 'loss/train': 2.193344831466675} 08/30/2021 14:50:24 - INFO - __main__ - Step 9351: {'lr': 0.0004969634539525566, 'samples': 1795392, 'steps': 9350, 'loss/train': 1.4754719734191895} 08/30/2021 14:50:25 - INFO - __main__ - Step 9352: {'lr': 0.0004969626293026353, 'samples': 1795584, 'steps': 9351, 'loss/train': 2.1202762126922607} 08/30/2021 14:50:26 - INFO - __main__ - Step 9353: {'lr': 0.0004969618045414363, 'samples': 1795776, 'steps': 9352, 'loss/train': 1.3586260080337524} 08/30/2021 14:50:27 - INFO - __main__ - Step 9354: {'lr': 0.0004969609796689602, 'samples': 1795968, 'steps': 9353, 'loss/train': 1.8787740468978882} 08/30/2021 14:50:27 - INFO - __main__ - Step 9355: {'lr': 0.0004969601546852073, 'samples': 1796160, 'steps': 9354, 'loss/train': 1.8635075092315674} 08/30/2021 14:50:27 - INFO - __main__ - Step 9356: {'lr': 0.0004969593295901779, 'samples': 1796352, 'steps': 9355, 'loss/train': 1.9155939817428589} 08/30/2021 14:50:28 - INFO - __main__ - Step 9357: {'lr': 0.0004969585043838725, 'samples': 1796544, 'steps': 9356, 'loss/train': 2.4200963973999023} 08/30/2021 14:50:30 - INFO - __main__ - Step 9358: {'lr': 0.0004969576790662914, 'samples': 1796736, 'steps': 9357, 'loss/train': 1.6718475818634033} 08/30/2021 14:50:30 - INFO - __main__ - Step 9359: {'lr': 0.0004969568536374349, 'samples': 1796928, 'steps': 9358, 'loss/train': 0.1486867070198059} 08/30/2021 14:50:31 - INFO - __main__ - Step 9360: {'lr': 0.0004969560280973036, 'samples': 1797120, 'steps': 9359, 'loss/train': 1.8262906074523926} 08/30/2021 14:50:31 - INFO - __main__ - Step 9361: {'lr': 0.0004969552024458976, 'samples': 1797312, 'steps': 9360, 'loss/train': 2.6798460483551025} 08/30/2021 14:50:31 - INFO - __main__ - Step 9362: {'lr': 0.0004969543766832176, 'samples': 1797504, 'steps': 9361, 'loss/train': 1.361230731010437} 08/30/2021 14:50:32 - INFO - __main__ - Step 9363: {'lr': 0.0004969535508092635, 'samples': 1797696, 'steps': 9362, 'loss/train': 1.794560432434082} 08/30/2021 14:50:33 - INFO - __main__ - Step 9364: {'lr': 0.0004969527248240361, 'samples': 1797888, 'steps': 9363, 'loss/train': 1.8477025032043457} 08/30/2021 14:50:34 - INFO - __main__ - Step 9365: {'lr': 0.0004969518987275356, 'samples': 1798080, 'steps': 9364, 'loss/train': 1.7897114753723145} 08/30/2021 14:50:34 - INFO - __main__ - Step 9366: {'lr': 0.0004969510725197624, 'samples': 1798272, 'steps': 9365, 'loss/train': 2.2025904655456543} 08/30/2021 14:50:34 - INFO - __main__ - Step 9367: {'lr': 0.0004969502462007167, 'samples': 1798464, 'steps': 9366, 'loss/train': 1.8683362007141113} 08/30/2021 14:50:35 - INFO - __main__ - Step 9368: {'lr': 0.0004969494197703992, 'samples': 1798656, 'steps': 9367, 'loss/train': 1.8720678091049194} 08/30/2021 14:50:37 - INFO - __main__ - Step 9369: {'lr': 0.00049694859322881, 'samples': 1798848, 'steps': 9368, 'loss/train': 1.8280768394470215} 08/30/2021 14:50:37 - INFO - __main__ - Step 9370: {'lr': 0.0004969477665759496, 'samples': 1799040, 'steps': 9369, 'loss/train': 1.9363033771514893} 08/30/2021 14:50:38 - INFO - __main__ - Step 9371: {'lr': 0.0004969469398118184, 'samples': 1799232, 'steps': 9370, 'loss/train': 1.9637559652328491} 08/30/2021 14:50:38 - INFO - __main__ - Step 9372: {'lr': 0.0004969461129364167, 'samples': 1799424, 'steps': 9371, 'loss/train': 2.121222972869873} 08/30/2021 14:50:38 - INFO - __main__ - Step 9373: {'lr': 0.0004969452859497449, 'samples': 1799616, 'steps': 9372, 'loss/train': 1.653204321861267} 08/30/2021 14:50:40 - INFO - __main__ - Step 9374: {'lr': 0.0004969444588518034, 'samples': 1799808, 'steps': 9373, 'loss/train': 2.1637487411499023} 08/30/2021 14:50:40 - INFO - __main__ - Step 9375: {'lr': 0.0004969436316425924, 'samples': 1800000, 'steps': 9374, 'loss/train': 2.070594549179077} 08/30/2021 14:50:41 - INFO - __main__ - Step 9376: {'lr': 0.0004969428043221125, 'samples': 1800192, 'steps': 9375, 'loss/train': 2.100050210952759} 08/30/2021 14:50:41 - INFO - __main__ - Step 9377: {'lr': 0.000496941976890364, 'samples': 1800384, 'steps': 9376, 'loss/train': 2.5154988765716553} 08/30/2021 14:50:41 - INFO - __main__ - Step 9378: {'lr': 0.0004969411493473472, 'samples': 1800576, 'steps': 9377, 'loss/train': 1.6724045276641846} 08/30/2021 14:50:42 - INFO - __main__ - Step 9379: {'lr': 0.0004969403216930626, 'samples': 1800768, 'steps': 9378, 'loss/train': 1.6164556741714478} 08/30/2021 14:50:43 - INFO - __main__ - Step 9380: {'lr': 0.0004969394939275105, 'samples': 1800960, 'steps': 9379, 'loss/train': 2.2861320972442627} 08/30/2021 14:50:44 - INFO - __main__ - Step 9381: {'lr': 0.0004969386660506912, 'samples': 1801152, 'steps': 9380, 'loss/train': 1.7749894857406616} 08/30/2021 14:50:44 - INFO - __main__ - Step 9382: {'lr': 0.0004969378380626051, 'samples': 1801344, 'steps': 9381, 'loss/train': 2.0912327766418457} 08/30/2021 14:50:44 - INFO - __main__ - Step 9383: {'lr': 0.0004969370099632528, 'samples': 1801536, 'steps': 9382, 'loss/train': 1.6605771780014038} 08/30/2021 14:50:45 - INFO - __main__ - Step 9384: {'lr': 0.0004969361817526343, 'samples': 1801728, 'steps': 9383, 'loss/train': 2.2192394733428955} 08/30/2021 14:50:46 - INFO - __main__ - Step 9385: {'lr': 0.0004969353534307504, 'samples': 1801920, 'steps': 9384, 'loss/train': 1.7540037631988525} 08/30/2021 14:50:47 - INFO - __main__ - Step 9386: {'lr': 0.000496934524997601, 'samples': 1802112, 'steps': 9385, 'loss/train': 1.8286198377609253} 08/30/2021 14:50:47 - INFO - __main__ - Step 9387: {'lr': 0.0004969336964531869, 'samples': 1802304, 'steps': 9386, 'loss/train': 1.9215701818466187} 08/30/2021 14:50:47 - INFO - __main__ - Step 9388: {'lr': 0.0004969328677975083, 'samples': 1802496, 'steps': 9387, 'loss/train': 1.9116616249084473} 08/30/2021 14:50:48 - INFO - __main__ - Step 9389: {'lr': 0.0004969320390305654, 'samples': 1802688, 'steps': 9388, 'loss/train': 1.8428884744644165} 08/30/2021 14:50:49 - INFO - __main__ - Step 9390: {'lr': 0.0004969312101523588, 'samples': 1802880, 'steps': 9389, 'loss/train': 1.4747421741485596} 08/30/2021 14:50:50 - INFO - __main__ - Step 9391: {'lr': 0.0004969303811628888, 'samples': 1803072, 'steps': 9390, 'loss/train': 1.980588436126709} 08/30/2021 14:50:50 - INFO - __main__ - Step 9392: {'lr': 0.0004969295520621558, 'samples': 1803264, 'steps': 9391, 'loss/train': 0.13408294320106506} 08/30/2021 14:50:50 - INFO - __main__ - Step 9393: {'lr': 0.0004969287228501602, 'samples': 1803456, 'steps': 9392, 'loss/train': 2.0473554134368896} 08/30/2021 14:50:51 - INFO - __main__ - Step 9394: {'lr': 0.0004969278935269022, 'samples': 1803648, 'steps': 9393, 'loss/train': 1.6537960767745972} 08/30/2021 14:50:52 - INFO - __main__ - Step 9395: {'lr': 0.0004969270640923823, 'samples': 1803840, 'steps': 9394, 'loss/train': 1.537422776222229} 08/30/2021 14:50:53 - INFO - __main__ - Step 9396: {'lr': 0.0004969262345466011, 'samples': 1804032, 'steps': 9395, 'loss/train': 1.6788089275360107} 08/30/2021 14:50:53 - INFO - __main__ - Step 9397: {'lr': 0.0004969254048895585, 'samples': 1804224, 'steps': 9396, 'loss/train': 1.6357635259628296} 08/30/2021 14:50:54 - INFO - __main__ - Step 9398: {'lr': 0.0004969245751212552, 'samples': 1804416, 'steps': 9397, 'loss/train': 1.9354521036148071} 08/30/2021 14:50:54 - INFO - __main__ - Step 9399: {'lr': 0.0004969237452416915, 'samples': 1804608, 'steps': 9398, 'loss/train': 1.7608600854873657} 08/30/2021 14:50:55 - INFO - __main__ - Step 9400: {'lr': 0.0004969229152508678, 'samples': 1804800, 'steps': 9399, 'loss/train': 1.6554512977600098} 08/30/2021 14:50:56 - INFO - __main__ - Step 9401: {'lr': 0.0004969220851487844, 'samples': 1804992, 'steps': 9400, 'loss/train': 1.4405708312988281} 08/30/2021 14:50:56 - INFO - __main__ - Step 9402: {'lr': 0.0004969212549354418, 'samples': 1805184, 'steps': 9401, 'loss/train': 1.9279801845550537} 08/30/2021 14:50:57 - INFO - __main__ - Step 9403: {'lr': 0.0004969204246108402, 'samples': 1805376, 'steps': 9402, 'loss/train': 1.7291628122329712} 08/30/2021 14:50:57 - INFO - __main__ - Step 9404: {'lr': 0.0004969195941749801, 'samples': 1805568, 'steps': 9403, 'loss/train': 2.056635618209839} 08/30/2021 14:50:58 - INFO - __main__ - Step 9405: {'lr': 0.000496918763627862, 'samples': 1805760, 'steps': 9404, 'loss/train': 2.1522889137268066} 08/30/2021 14:50:59 - INFO - __main__ - Step 9406: {'lr': 0.0004969179329694859, 'samples': 1805952, 'steps': 9405, 'loss/train': 2.2526438236236572} 08/30/2021 14:50:59 - INFO - __main__ - Step 9407: {'lr': 0.0004969171021998525, 'samples': 1806144, 'steps': 9406, 'loss/train': 1.9701427221298218} 08/30/2021 14:51:00 - INFO - __main__ - Step 9408: {'lr': 0.0004969162713189619, 'samples': 1806336, 'steps': 9407, 'loss/train': 1.499146580696106} 08/30/2021 14:51:00 - INFO - __main__ - Step 9409: {'lr': 0.0004969154403268148, 'samples': 1806528, 'steps': 9408, 'loss/train': 2.4673938751220703} 08/30/2021 14:51:00 - INFO - __main__ - Step 9410: {'lr': 0.0004969146092234114, 'samples': 1806720, 'steps': 9409, 'loss/train': 1.3679702281951904} 08/30/2021 14:51:02 - INFO - __main__ - Step 9411: {'lr': 0.000496913778008752, 'samples': 1806912, 'steps': 9410, 'loss/train': 1.5414880514144897} 08/30/2021 14:51:02 - INFO - __main__ - Step 9412: {'lr': 0.0004969129466828371, 'samples': 1807104, 'steps': 9411, 'loss/train': 1.9186081886291504} 08/30/2021 14:51:03 - INFO - __main__ - Step 9413: {'lr': 0.0004969121152456671, 'samples': 1807296, 'steps': 9412, 'loss/train': 1.4455149173736572} 08/30/2021 14:51:03 - INFO - __main__ - Step 9414: {'lr': 0.0004969112836972423, 'samples': 1807488, 'steps': 9413, 'loss/train': 1.8019697666168213} 08/30/2021 14:51:03 - INFO - __main__ - Step 9415: {'lr': 0.000496910452037563, 'samples': 1807680, 'steps': 9414, 'loss/train': 1.9133750200271606} 08/30/2021 14:51:05 - INFO - __main__ - Step 9416: {'lr': 0.0004969096202666297, 'samples': 1807872, 'steps': 9415, 'loss/train': 1.8285832405090332} 08/30/2021 14:51:05 - INFO - __main__ - Step 9417: {'lr': 0.0004969087883844428, 'samples': 1808064, 'steps': 9416, 'loss/train': 1.9302802085876465} 08/30/2021 14:51:06 - INFO - __main__ - Step 9418: {'lr': 0.0004969079563910025, 'samples': 1808256, 'steps': 9417, 'loss/train': 1.6582567691802979} 08/30/2021 14:51:06 - INFO - __main__ - Step 9419: {'lr': 0.0004969071242863093, 'samples': 1808448, 'steps': 9418, 'loss/train': 0.6336837410926819} 08/30/2021 14:51:06 - INFO - __main__ - Step 9420: {'lr': 0.0004969062920703636, 'samples': 1808640, 'steps': 9419, 'loss/train': 1.6298236846923828} 08/30/2021 14:51:09 - INFO - __main__ - Step 9421: {'lr': 0.0004969054597431658, 'samples': 1808832, 'steps': 9420, 'loss/train': 2.063265800476074} 08/30/2021 14:51:09 - INFO - __main__ - Step 9422: {'lr': 0.0004969046273047161, 'samples': 1809024, 'steps': 9421, 'loss/train': 2.3442225456237793} 08/30/2021 14:51:10 - INFO - __main__ - Step 9423: {'lr': 0.0004969037947550151, 'samples': 1809216, 'steps': 9422, 'loss/train': 1.5826541185379028} 08/30/2021 14:51:10 - INFO - __main__ - Step 9424: {'lr': 0.000496902962094063, 'samples': 1809408, 'steps': 9423, 'loss/train': 2.43269944190979} 08/30/2021 14:51:10 - INFO - __main__ - Step 9425: {'lr': 0.0004969021293218602, 'samples': 1809600, 'steps': 9424, 'loss/train': 1.674534797668457} 08/30/2021 14:51:11 - INFO - __main__ - Step 9426: {'lr': 0.0004969012964384071, 'samples': 1809792, 'steps': 9425, 'loss/train': 2.499333381652832} 08/30/2021 14:51:13 - INFO - __main__ - Step 9427: {'lr': 0.0004969004634437042, 'samples': 1809984, 'steps': 9426, 'loss/train': 1.3876187801361084} 08/30/2021 14:51:13 - INFO - __main__ - Step 9428: {'lr': 0.0004968996303377517, 'samples': 1810176, 'steps': 9427, 'loss/train': 0.2191656529903412} 08/30/2021 14:51:13 - INFO - __main__ - Step 9429: {'lr': 0.00049689879712055, 'samples': 1810368, 'steps': 9428, 'loss/train': 0.17023412883281708} 08/30/2021 14:51:14 - INFO - __main__ - Step 9430: {'lr': 0.0004968979637920995, 'samples': 1810560, 'steps': 9429, 'loss/train': 1.1126787662506104} 08/30/2021 14:51:14 - INFO - __main__ - Step 9431: {'lr': 0.0004968971303524007, 'samples': 1810752, 'steps': 9430, 'loss/train': 1.171593189239502} 08/30/2021 14:51:14 - INFO - __main__ - Step 9432: {'lr': 0.0004968962968014537, 'samples': 1810944, 'steps': 9431, 'loss/train': 1.8794907331466675} 08/30/2021 14:51:16 - INFO - __main__ - Step 9433: {'lr': 0.0004968954631392592, 'samples': 1811136, 'steps': 9432, 'loss/train': 1.5810835361480713} 08/30/2021 14:51:16 - INFO - __main__ - Step 9434: {'lr': 0.0004968946293658173, 'samples': 1811328, 'steps': 9433, 'loss/train': 1.717587947845459} 08/30/2021 14:51:17 - INFO - __main__ - Step 9435: {'lr': 0.0004968937954811284, 'samples': 1811520, 'steps': 9434, 'loss/train': 1.9044227600097656} 08/30/2021 14:51:17 - INFO - __main__ - Step 9436: {'lr': 0.0004968929614851932, 'samples': 1811712, 'steps': 9435, 'loss/train': 2.173994779586792} 08/30/2021 14:51:18 - INFO - __main__ - Step 9437: {'lr': 0.0004968921273780118, 'samples': 1811904, 'steps': 9436, 'loss/train': 1.477209448814392} 08/30/2021 14:51:19 - INFO - __main__ - Step 9438: {'lr': 0.0004968912931595845, 'samples': 1812096, 'steps': 9437, 'loss/train': 1.643391728401184} 08/30/2021 14:51:20 - INFO - __main__ - Step 9439: {'lr': 0.0004968904588299118, 'samples': 1812288, 'steps': 9438, 'loss/train': 2.1049187183380127} 08/30/2021 14:51:20 - INFO - __main__ - Step 9440: {'lr': 0.0004968896243889941, 'samples': 1812480, 'steps': 9439, 'loss/train': 1.4536027908325195} 08/30/2021 14:51:21 - INFO - __main__ - Step 9441: {'lr': 0.0004968887898368318, 'samples': 1812672, 'steps': 9440, 'loss/train': 1.6639186143875122} 08/30/2021 14:51:21 - INFO - __main__ - Step 9442: {'lr': 0.0004968879551734252, 'samples': 1812864, 'steps': 9441, 'loss/train': 0.5168627500534058} 08/30/2021 14:51:21 - INFO - __main__ - Step 9443: {'lr': 0.0004968871203987746, 'samples': 1813056, 'steps': 9442, 'loss/train': 0.1469617784023285} 08/30/2021 14:51:23 - INFO - __main__ - Step 9444: {'lr': 0.0004968862855128806, 'samples': 1813248, 'steps': 9443, 'loss/train': 1.4375885725021362} 08/30/2021 14:51:23 - INFO - __main__ - Step 9445: {'lr': 0.0004968854505157434, 'samples': 1813440, 'steps': 9444, 'loss/train': 1.534547209739685} 08/30/2021 14:51:24 - INFO - __main__ - Step 9446: {'lr': 0.0004968846154073634, 'samples': 1813632, 'steps': 9445, 'loss/train': 1.9740641117095947} 08/30/2021 14:51:24 - INFO - __main__ - Step 9447: {'lr': 0.0004968837801877411, 'samples': 1813824, 'steps': 9446, 'loss/train': 1.5035918951034546} 08/30/2021 14:51:24 - INFO - __main__ - Step 9448: {'lr': 0.0004968829448568766, 'samples': 1814016, 'steps': 9447, 'loss/train': 2.2901721000671387} 08/30/2021 14:51:25 - INFO - __main__ - Step 9449: {'lr': 0.0004968821094147706, 'samples': 1814208, 'steps': 9448, 'loss/train': 1.6791605949401855} 08/30/2021 14:51:26 - INFO - __main__ - Step 9450: {'lr': 0.0004968812738614232, 'samples': 1814400, 'steps': 9449, 'loss/train': 1.6993780136108398} 08/30/2021 14:51:27 - INFO - __main__ - Step 9451: {'lr': 0.000496880438196835, 'samples': 1814592, 'steps': 9450, 'loss/train': 2.3020646572113037} 08/30/2021 14:51:27 - INFO - __main__ - Step 9452: {'lr': 0.0004968796024210064, 'samples': 1814784, 'steps': 9451, 'loss/train': 1.5926811695098877} 08/30/2021 14:51:27 - INFO - __main__ - Step 9453: {'lr': 0.0004968787665339375, 'samples': 1814976, 'steps': 9452, 'loss/train': 0.1305505633354187} 08/30/2021 14:51:28 - INFO - __main__ - Step 9454: {'lr': 0.0004968779305356289, 'samples': 1815168, 'steps': 9453, 'loss/train': 2.2053568363189697} 08/30/2021 14:51:29 - INFO - __main__ - Step 9455: {'lr': 0.0004968770944260808, 'samples': 1815360, 'steps': 9454, 'loss/train': 1.9923434257507324} 08/30/2021 14:51:30 - INFO - __main__ - Step 9456: {'lr': 0.0004968762582052938, 'samples': 1815552, 'steps': 9455, 'loss/train': 2.0484702587127686} 08/30/2021 14:51:30 - INFO - __main__ - Step 9457: {'lr': 0.0004968754218732682, 'samples': 1815744, 'steps': 9456, 'loss/train': 2.0139009952545166} 08/30/2021 14:51:30 - INFO - __main__ - Step 9458: {'lr': 0.0004968745854300043, 'samples': 1815936, 'steps': 9457, 'loss/train': 3.09591007232666} 08/30/2021 14:51:31 - INFO - __main__ - Step 9459: {'lr': 0.0004968737488755025, 'samples': 1816128, 'steps': 9458, 'loss/train': 2.00433611869812} 08/30/2021 14:51:33 - INFO - __main__ - Step 9460: {'lr': 0.0004968729122097632, 'samples': 1816320, 'steps': 9459, 'loss/train': 1.778140902519226} 08/30/2021 14:51:33 - INFO - __main__ - Step 9461: {'lr': 0.0004968720754327867, 'samples': 1816512, 'steps': 9460, 'loss/train': 1.7109475135803223} 08/30/2021 14:51:34 - INFO - __main__ - Step 9462: {'lr': 0.0004968712385445737, 'samples': 1816704, 'steps': 9461, 'loss/train': 0.22620485723018646} 08/30/2021 14:51:34 - INFO - __main__ - Step 9463: {'lr': 0.0004968704015451241, 'samples': 1816896, 'steps': 9462, 'loss/train': 1.6831026077270508} 08/30/2021 14:51:34 - INFO - __main__ - Step 9464: {'lr': 0.0004968695644344387, 'samples': 1817088, 'steps': 9463, 'loss/train': 2.1342976093292236} 08/30/2021 14:51:35 - INFO - __main__ - Step 9465: {'lr': 0.0004968687272125174, 'samples': 1817280, 'steps': 9464, 'loss/train': 1.927371621131897} 08/30/2021 14:51:36 - INFO - __main__ - Step 9466: {'lr': 0.0004968678898793611, 'samples': 1817472, 'steps': 9465, 'loss/train': 1.3137162923812866} 08/30/2021 14:51:37 - INFO - __main__ - Step 9467: {'lr': 0.0004968670524349699, 'samples': 1817664, 'steps': 9466, 'loss/train': 1.5771915912628174} 08/30/2021 14:51:37 - INFO - __main__ - Step 9468: {'lr': 0.0004968662148793441, 'samples': 1817856, 'steps': 9467, 'loss/train': 1.8674590587615967} 08/30/2021 14:51:37 - INFO - __main__ - Step 9469: {'lr': 0.0004968653772124843, 'samples': 1818048, 'steps': 9468, 'loss/train': 1.9872907400131226} 08/30/2021 14:51:38 - INFO - __main__ - Step 9470: {'lr': 0.0004968645394343908, 'samples': 1818240, 'steps': 9469, 'loss/train': 1.0401135683059692} 08/30/2021 14:51:38 - INFO - __main__ - Step 9471: {'lr': 0.0004968637015450639, 'samples': 1818432, 'steps': 9470, 'loss/train': 2.21691632270813} 08/30/2021 14:51:40 - INFO - __main__ - Step 9472: {'lr': 0.000496862863544504, 'samples': 1818624, 'steps': 9471, 'loss/train': 0.1765308529138565} 08/30/2021 14:51:40 - INFO - __main__ - Step 9473: {'lr': 0.0004968620254327114, 'samples': 1818816, 'steps': 9472, 'loss/train': 1.7371716499328613} 08/30/2021 14:51:40 - INFO - __main__ - Step 9474: {'lr': 0.0004968611872096868, 'samples': 1819008, 'steps': 9473, 'loss/train': 1.7049574851989746} 08/30/2021 14:51:41 - INFO - __main__ - Step 9475: {'lr': 0.0004968603488754302, 'samples': 1819200, 'steps': 9474, 'loss/train': 1.7634905576705933} 08/30/2021 14:51:41 - INFO - __main__ - Step 9476: {'lr': 0.0004968595104299422, 'samples': 1819392, 'steps': 9475, 'loss/train': 2.0750572681427} 08/30/2021 14:51:43 - INFO - __main__ - Step 9477: {'lr': 0.000496858671873223, 'samples': 1819584, 'steps': 9476, 'loss/train': 2.400235891342163} 08/30/2021 14:51:44 - INFO - __main__ - Step 9478: {'lr': 0.0004968578332052733, 'samples': 1819776, 'steps': 9477, 'loss/train': 2.051832675933838} 08/30/2021 14:51:44 - INFO - __main__ - Step 9479: {'lr': 0.0004968569944260932, 'samples': 1819968, 'steps': 9478, 'loss/train': 0.609390377998352} 08/30/2021 14:51:44 - INFO - __main__ - Step 9480: {'lr': 0.0004968561555356831, 'samples': 1820160, 'steps': 9479, 'loss/train': 1.7644001245498657} 08/30/2021 14:51:45 - INFO - __main__ - Step 9481: {'lr': 0.0004968553165340435, 'samples': 1820352, 'steps': 9480, 'loss/train': 1.7184343338012695} 08/30/2021 14:51:46 - INFO - __main__ - Step 9482: {'lr': 0.0004968544774211746, 'samples': 1820544, 'steps': 9481, 'loss/train': 1.5007576942443848} 08/30/2021 14:51:47 - INFO - __main__ - Step 9483: {'lr': 0.0004968536381970769, 'samples': 1820736, 'steps': 9482, 'loss/train': 1.4033454656600952} 08/30/2021 14:51:47 - INFO - __main__ - Step 9484: {'lr': 0.0004968527988617508, 'samples': 1820928, 'steps': 9483, 'loss/train': 1.3734347820281982} 08/30/2021 14:51:47 - INFO - __main__ - Step 9485: {'lr': 0.0004968519594151966, 'samples': 1821120, 'steps': 9484, 'loss/train': 1.854420781135559} 08/30/2021 14:51:48 - INFO - __main__ - Step 9486: {'lr': 0.0004968511198574147, 'samples': 1821312, 'steps': 9485, 'loss/train': 1.7000813484191895} 08/30/2021 14:51:49 - INFO - __main__ - Step 9487: {'lr': 0.0004968502801884056, 'samples': 1821504, 'steps': 9486, 'loss/train': 0.19344857335090637} 08/30/2021 14:51:50 - INFO - __main__ - Step 9488: {'lr': 0.0004968494404081695, 'samples': 1821696, 'steps': 9487, 'loss/train': 1.6949357986450195} 08/30/2021 14:51:50 - INFO - __main__ - Step 9489: {'lr': 0.0004968486005167069, 'samples': 1821888, 'steps': 9488, 'loss/train': 1.9569776058197021} 08/30/2021 14:51:51 - INFO - __main__ - Step 9490: {'lr': 0.000496847760514018, 'samples': 1822080, 'steps': 9489, 'loss/train': 1.227189540863037} 08/30/2021 14:51:51 - INFO - __main__ - Step 9491: {'lr': 0.0004968469204001035, 'samples': 1822272, 'steps': 9490, 'loss/train': 1.703311800956726} 08/30/2021 14:51:51 - INFO - __main__ - Step 9492: {'lr': 0.0004968460801749635, 'samples': 1822464, 'steps': 9491, 'loss/train': 1.6264091730117798} 08/30/2021 14:51:53 - INFO - __main__ - Step 9493: {'lr': 0.0004968452398385984, 'samples': 1822656, 'steps': 9492, 'loss/train': 1.5646148920059204} 08/30/2021 14:51:53 - INFO - __main__ - Step 9494: {'lr': 0.0004968443993910086, 'samples': 1822848, 'steps': 9493, 'loss/train': 1.6149001121520996} 08/30/2021 14:51:54 - INFO - __main__ - Step 9495: {'lr': 0.0004968435588321947, 'samples': 1823040, 'steps': 9494, 'loss/train': 3.129379987716675} 08/30/2021 14:51:54 - INFO - __main__ - Step 9496: {'lr': 0.0004968427181621567, 'samples': 1823232, 'steps': 9495, 'loss/train': 1.9704177379608154} 08/30/2021 14:51:54 - INFO - __main__ - Step 9497: {'lr': 0.0004968418773808954, 'samples': 1823424, 'steps': 9496, 'loss/train': 1.985621452331543} 08/30/2021 14:51:56 - INFO - __main__ - Step 9498: {'lr': 0.0004968410364884109, 'samples': 1823616, 'steps': 9497, 'loss/train': 2.15446138381958} 08/30/2021 14:51:56 - INFO - __main__ - Step 9499: {'lr': 0.0004968401954847035, 'samples': 1823808, 'steps': 9498, 'loss/train': 1.961751103401184} 08/30/2021 14:51:57 - INFO - __main__ - Step 9500: {'lr': 0.0004968393543697739, 'samples': 1824000, 'steps': 9499, 'loss/train': 1.8978371620178223} 08/30/2021 14:51:57 - INFO - __main__ - Step 9501: {'lr': 0.0004968385131436222, 'samples': 1824192, 'steps': 9500, 'loss/train': 2.069866895675659} 08/30/2021 14:51:57 - INFO - __main__ - Step 9502: {'lr': 0.0004968376718062488, 'samples': 1824384, 'steps': 9501, 'loss/train': 2.285006284713745} 08/30/2021 14:51:58 - INFO - __main__ - Step 9503: {'lr': 0.0004968368303576542, 'samples': 1824576, 'steps': 9502, 'loss/train': 2.062350034713745} 08/30/2021 14:51:59 - INFO - __main__ - Step 9504: {'lr': 0.0004968359887978389, 'samples': 1824768, 'steps': 9503, 'loss/train': 2.0324878692626953} 08/30/2021 14:52:00 - INFO - __main__ - Step 9505: {'lr': 0.0004968351471268029, 'samples': 1824960, 'steps': 9504, 'loss/train': 1.6162992715835571} 08/30/2021 14:52:00 - INFO - __main__ - Step 9506: {'lr': 0.0004968343053445469, 'samples': 1825152, 'steps': 9505, 'loss/train': 1.7939414978027344} 08/30/2021 14:52:00 - INFO - __main__ - Step 9507: {'lr': 0.0004968334634510712, 'samples': 1825344, 'steps': 9506, 'loss/train': 1.7104524374008179} 08/30/2021 14:52:01 - INFO - __main__ - Step 9508: {'lr': 0.000496832621446376, 'samples': 1825536, 'steps': 9507, 'loss/train': 1.705259919166565} 08/30/2021 14:52:02 - INFO - __main__ - Step 9509: {'lr': 0.000496831779330462, 'samples': 1825728, 'steps': 9508, 'loss/train': 2.0026159286499023} 08/30/2021 14:52:03 - INFO - __main__ - Step 9510: {'lr': 0.0004968309371033293, 'samples': 1825920, 'steps': 9509, 'loss/train': 2.0757880210876465} 08/30/2021 14:52:03 - INFO - __main__ - Step 9511: {'lr': 0.0004968300947649784, 'samples': 1826112, 'steps': 9510, 'loss/train': 0.965133547782898} 08/30/2021 14:52:03 - INFO - __main__ - Step 9512: {'lr': 0.0004968292523154096, 'samples': 1826304, 'steps': 9511, 'loss/train': 1.057422161102295} 08/30/2021 14:52:04 - INFO - __main__ - Step 9513: {'lr': 0.0004968284097546235, 'samples': 1826496, 'steps': 9512, 'loss/train': 2.2127723693847656} 08/30/2021 14:52:05 - INFO - __main__ - Step 9514: {'lr': 0.0004968275670826204, 'samples': 1826688, 'steps': 9513, 'loss/train': 1.9112217426300049} 08/30/2021 14:52:06 - INFO - __main__ - Step 9515: {'lr': 0.0004968267242994003, 'samples': 1826880, 'steps': 9514, 'loss/train': 2.016266345977783} 08/30/2021 14:52:06 - INFO - __main__ - Step 9516: {'lr': 0.0004968258814049641, 'samples': 1827072, 'steps': 9515, 'loss/train': 1.8917293548583984} 08/30/2021 14:52:06 - INFO - __main__ - Step 9517: {'lr': 0.0004968250383993119, 'samples': 1827264, 'steps': 9516, 'loss/train': 1.3322018384933472} 08/30/2021 14:52:07 - INFO - __main__ - Step 9518: {'lr': 0.0004968241952824442, 'samples': 1827456, 'steps': 9517, 'loss/train': 1.6007182598114014} 08/30/2021 14:52:08 - INFO - __main__ - Step 9519: {'lr': 0.0004968233520543613, 'samples': 1827648, 'steps': 9518, 'loss/train': 2.4424338340759277} 08/30/2021 14:52:09 - INFO - __main__ - Step 9520: {'lr': 0.0004968225087150636, 'samples': 1827840, 'steps': 9519, 'loss/train': 1.8217027187347412} 08/30/2021 14:52:09 - INFO - __main__ - Step 9521: {'lr': 0.0004968216652645515, 'samples': 1828032, 'steps': 9520, 'loss/train': 0.14912250638008118} 08/30/2021 14:52:09 - INFO - __main__ - Step 9522: {'lr': 0.0004968208217028254, 'samples': 1828224, 'steps': 9521, 'loss/train': 1.905614972114563} 08/30/2021 14:52:10 - INFO - __main__ - Step 9523: {'lr': 0.0004968199780298855, 'samples': 1828416, 'steps': 9522, 'loss/train': 2.1052048206329346} 08/30/2021 14:52:10 - INFO - __main__ - Step 9524: {'lr': 0.0004968191342457325, 'samples': 1828608, 'steps': 9523, 'loss/train': 1.7192381620407104} 08/30/2021 14:52:12 - INFO - __main__ - Step 9525: {'lr': 0.0004968182903503665, 'samples': 1828800, 'steps': 9524, 'loss/train': 1.6907083988189697} 08/30/2021 14:52:12 - INFO - __main__ - Step 9526: {'lr': 0.0004968174463437881, 'samples': 1828992, 'steps': 9525, 'loss/train': 2.139465570449829} 08/30/2021 14:52:13 - INFO - __main__ - Step 9527: {'lr': 0.0004968166022259974, 'samples': 1829184, 'steps': 9526, 'loss/train': 1.5463396310806274} 08/30/2021 14:52:13 - INFO - __main__ - Step 9528: {'lr': 0.0004968157579969951, 'samples': 1829376, 'steps': 9527, 'loss/train': 1.697893738746643} 08/30/2021 14:52:13 - INFO - __main__ - Step 9529: {'lr': 0.0004968149136567814, 'samples': 1829568, 'steps': 9528, 'loss/train': 1.9812012910842896} 08/30/2021 14:52:15 - INFO - __main__ - Step 9530: {'lr': 0.0004968140692053567, 'samples': 1829760, 'steps': 9529, 'loss/train': 1.7304465770721436} 08/30/2021 14:52:16 - INFO - __main__ - Step 9531: {'lr': 0.0004968132246427212, 'samples': 1829952, 'steps': 9530, 'loss/train': 1.9630389213562012} 08/30/2021 14:52:16 - INFO - __main__ - Step 9532: {'lr': 0.0004968123799688757, 'samples': 1830144, 'steps': 9531, 'loss/train': 1.8219130039215088} 08/30/2021 14:52:17 - INFO - __main__ - Step 9533: {'lr': 0.0004968115351838203, 'samples': 1830336, 'steps': 9532, 'loss/train': 2.0107686519622803} 08/30/2021 14:52:17 - INFO - __main__ - Step 9534: {'lr': 0.0004968106902875554, 'samples': 1830528, 'steps': 9533, 'loss/train': 1.0331999063491821} 08/30/2021 14:52:19 - INFO - __main__ - Step 9535: {'lr': 0.0004968098452800815, 'samples': 1830720, 'steps': 9534, 'loss/train': 2.015059471130371} 08/30/2021 14:52:19 - INFO - __main__ - Step 9536: {'lr': 0.0004968090001613987, 'samples': 1830912, 'steps': 9535, 'loss/train': 1.7272931337356567} 08/30/2021 14:52:20 - INFO - __main__ - Step 9537: {'lr': 0.0004968081549315078, 'samples': 1831104, 'steps': 9536, 'loss/train': 2.008720874786377} 08/30/2021 14:52:20 - INFO - __main__ - Step 9538: {'lr': 0.0004968073095904088, 'samples': 1831296, 'steps': 9537, 'loss/train': 1.7935843467712402} 08/30/2021 14:52:20 - INFO - __main__ - Step 9539: {'lr': 0.0004968064641381022, 'samples': 1831488, 'steps': 9538, 'loss/train': 0.15976040065288544} 08/30/2021 14:52:22 - INFO - __main__ - Step 9540: {'lr': 0.0004968056185745886, 'samples': 1831680, 'steps': 9539, 'loss/train': 1.9459625482559204} 08/30/2021 14:52:22 - INFO - __main__ - Step 9541: {'lr': 0.000496804772899868, 'samples': 1831872, 'steps': 9540, 'loss/train': 1.6825783252716064} 08/30/2021 14:52:23 - INFO - __main__ - Step 9542: {'lr': 0.0004968039271139412, 'samples': 1832064, 'steps': 9541, 'loss/train': 1.8675510883331299} 08/30/2021 14:52:23 - INFO - __main__ - Step 9543: {'lr': 0.0004968030812168082, 'samples': 1832256, 'steps': 9542, 'loss/train': 1.6803189516067505} 08/30/2021 14:52:23 - INFO - __main__ - Step 9544: {'lr': 0.0004968022352084695, 'samples': 1832448, 'steps': 9543, 'loss/train': 2.097487211227417} 08/30/2021 14:52:25 - INFO - __main__ - Step 9545: {'lr': 0.0004968013890889256, 'samples': 1832640, 'steps': 9544, 'loss/train': 1.791940689086914} 08/30/2021 14:52:26 - INFO - __main__ - Step 9546: {'lr': 0.0004968005428581767, 'samples': 1832832, 'steps': 9545, 'loss/train': 2.2272696495056152} 08/30/2021 14:52:26 - INFO - __main__ - Step 9547: {'lr': 0.0004967996965162235, 'samples': 1833024, 'steps': 9546, 'loss/train': 4.577334403991699} 08/30/2021 14:52:27 - INFO - __main__ - Step 9548: {'lr': 0.0004967988500630661, 'samples': 1833216, 'steps': 9547, 'loss/train': 7.04046630859375} 08/30/2021 14:52:27 - INFO - __main__ - Step 9549: {'lr': 0.0004967980034987048, 'samples': 1833408, 'steps': 9548, 'loss/train': 1.5037380456924438} 08/30/2021 14:52:27 - INFO - __main__ - Step 9550: {'lr': 0.0004967971568231402, 'samples': 1833600, 'steps': 9549, 'loss/train': 2.0027918815612793} 08/30/2021 14:52:29 - INFO - __main__ - Step 9551: {'lr': 0.0004967963100363726, 'samples': 1833792, 'steps': 9550, 'loss/train': 1.8694095611572266} 08/30/2021 14:52:29 - INFO - __main__ - Step 9552: {'lr': 0.0004967954631384025, 'samples': 1833984, 'steps': 9551, 'loss/train': 2.3288567066192627} 08/30/2021 14:52:30 - INFO - __main__ - Step 9553: {'lr': 0.00049679461612923, 'samples': 1834176, 'steps': 9552, 'loss/train': 1.8898195028305054} 08/30/2021 14:52:30 - INFO - __main__ - Step 9554: {'lr': 0.0004967937690088558, 'samples': 1834368, 'steps': 9553, 'loss/train': 1.0987898111343384} 08/30/2021 14:52:30 - INFO - __main__ - Step 9555: {'lr': 0.0004967929217772801, 'samples': 1834560, 'steps': 9554, 'loss/train': 1.653060793876648} 08/30/2021 14:52:32 - INFO - __main__ - Step 9556: {'lr': 0.0004967920744345033, 'samples': 1834752, 'steps': 9555, 'loss/train': 1.5633423328399658} 08/30/2021 14:52:32 - INFO - __main__ - Step 9557: {'lr': 0.0004967912269805257, 'samples': 1834944, 'steps': 9556, 'loss/train': 1.1584726572036743} 08/30/2021 14:52:33 - INFO - __main__ - Step 9558: {'lr': 0.000496790379415348, 'samples': 1835136, 'steps': 9557, 'loss/train': 2.092374563217163} 08/30/2021 14:52:33 - INFO - __main__ - Step 9559: {'lr': 0.0004967895317389702, 'samples': 1835328, 'steps': 9558, 'loss/train': 1.9063400030136108} 08/30/2021 14:52:33 - INFO - __main__ - Step 9560: {'lr': 0.0004967886839513929, 'samples': 1835520, 'steps': 9559, 'loss/train': 1.8805854320526123} 08/30/2021 14:52:35 - INFO - __main__ - Step 9561: {'lr': 0.0004967878360526163, 'samples': 1835712, 'steps': 9560, 'loss/train': 0.5825358629226685} 08/30/2021 14:52:35 - INFO - __main__ - Step 9562: {'lr': 0.0004967869880426411, 'samples': 1835904, 'steps': 9561, 'loss/train': 1.65834379196167} 08/30/2021 14:52:36 - INFO - __main__ - Step 9563: {'lr': 0.0004967861399214674, 'samples': 1836096, 'steps': 9562, 'loss/train': 1.0580202341079712} 08/30/2021 14:52:36 - INFO - __main__ - Step 9564: {'lr': 0.0004967852916890958, 'samples': 1836288, 'steps': 9563, 'loss/train': 1.9563688039779663} 08/30/2021 14:52:36 - INFO - __main__ - Step 9565: {'lr': 0.0004967844433455263, 'samples': 1836480, 'steps': 9564, 'loss/train': 1.885180115699768} 08/30/2021 14:52:38 - INFO - __main__ - Step 9566: {'lr': 0.0004967835948907598, 'samples': 1836672, 'steps': 9565, 'loss/train': 2.490196466445923} 08/30/2021 14:52:38 - INFO - __main__ - Step 9567: {'lr': 0.0004967827463247962, 'samples': 1836864, 'steps': 9566, 'loss/train': 1.6596322059631348} 08/30/2021 14:52:39 - INFO - __main__ - Step 9568: {'lr': 0.0004967818976476363, 'samples': 1837056, 'steps': 9567, 'loss/train': 1.840817928314209} 08/30/2021 14:52:39 - INFO - __main__ - Step 9569: {'lr': 0.0004967810488592801, 'samples': 1837248, 'steps': 9568, 'loss/train': 2.142194986343384} 08/30/2021 14:52:39 - INFO - __main__ - Step 9570: {'lr': 0.0004967801999597283, 'samples': 1837440, 'steps': 9569, 'loss/train': 2.2547035217285156} 08/30/2021 14:52:41 - INFO - __main__ - Step 9571: {'lr': 0.0004967793509489811, 'samples': 1837632, 'steps': 9570, 'loss/train': 1.8984874486923218} 08/30/2021 14:52:42 - INFO - __main__ - Step 9572: {'lr': 0.0004967785018270389, 'samples': 1837824, 'steps': 9571, 'loss/train': 1.471620798110962} 08/30/2021 14:52:42 - INFO - __main__ - Step 9573: {'lr': 0.0004967776525939022, 'samples': 1838016, 'steps': 9572, 'loss/train': 2.029245615005493} 08/30/2021 14:52:42 - INFO - __main__ - Step 9574: {'lr': 0.0004967768032495712, 'samples': 1838208, 'steps': 9573, 'loss/train': 1.9916651248931885} 08/30/2021 14:52:43 - INFO - __main__ - Step 9575: {'lr': 0.0004967759537940464, 'samples': 1838400, 'steps': 9574, 'loss/train': 0.35771846771240234} 08/30/2021 14:52:44 - INFO - __main__ - Step 9576: {'lr': 0.0004967751042273282, 'samples': 1838592, 'steps': 9575, 'loss/train': 1.7091983556747437} 08/30/2021 14:52:45 - INFO - __main__ - Step 9577: {'lr': 0.000496774254549417, 'samples': 1838784, 'steps': 9576, 'loss/train': 2.095242738723755} 08/30/2021 14:52:45 - INFO - __main__ - Step 9578: {'lr': 0.0004967734047603131, 'samples': 1838976, 'steps': 9577, 'loss/train': 0.8464174866676331} 08/30/2021 14:52:45 - INFO - __main__ - Step 9579: {'lr': 0.0004967725548600168, 'samples': 1839168, 'steps': 9578, 'loss/train': 1.780236840248108} 08/30/2021 14:52:46 - INFO - __main__ - Step 9580: {'lr': 0.0004967717048485287, 'samples': 1839360, 'steps': 9579, 'loss/train': 1.5458338260650635} 08/30/2021 14:52:46 - INFO - __main__ - Step 9581: {'lr': 0.000496770854725849, 'samples': 1839552, 'steps': 9580, 'loss/train': 1.8168420791625977} 08/30/2021 14:52:48 - INFO - __main__ - Step 9582: {'lr': 0.0004967700044919783, 'samples': 1839744, 'steps': 9581, 'loss/train': 2.481297731399536} 08/30/2021 14:52:48 - INFO - __main__ - Step 9583: {'lr': 0.0004967691541469167, 'samples': 1839936, 'steps': 9582, 'loss/train': 1.9234411716461182} 08/30/2021 14:52:49 - INFO - __main__ - Step 9584: {'lr': 0.0004967683036906648, 'samples': 1840128, 'steps': 9583, 'loss/train': 0.19581331312656403} 08/30/2021 14:52:49 - INFO - __main__ - Step 9585: {'lr': 0.0004967674531232229, 'samples': 1840320, 'steps': 9584, 'loss/train': 2.079195261001587} 08/30/2021 14:52:49 - INFO - __main__ - Step 9586: {'lr': 0.0004967666024445913, 'samples': 1840512, 'steps': 9585, 'loss/train': 1.999889612197876} 08/30/2021 14:52:51 - INFO - __main__ - Step 9587: {'lr': 0.0004967657516547707, 'samples': 1840704, 'steps': 9586, 'loss/train': 2.023404359817505} 08/30/2021 14:52:52 - INFO - __main__ - Step 9588: {'lr': 0.0004967649007537611, 'samples': 1840896, 'steps': 9587, 'loss/train': 2.1839041709899902} 08/30/2021 14:52:52 - INFO - __main__ - Step 9589: {'lr': 0.0004967640497415631, 'samples': 1841088, 'steps': 9588, 'loss/train': 1.8167579174041748} 08/30/2021 14:52:52 - INFO - __main__ - Step 9590: {'lr': 0.000496763198618177, 'samples': 1841280, 'steps': 9589, 'loss/train': 1.192988395690918} 08/30/2021 14:52:53 - INFO - __main__ - Step 9591: {'lr': 0.0004967623473836032, 'samples': 1841472, 'steps': 9590, 'loss/train': 1.9897503852844238} 08/30/2021 14:52:54 - INFO - __main__ - Step 9592: {'lr': 0.0004967614960378421, 'samples': 1841664, 'steps': 9591, 'loss/train': 1.6394896507263184} 08/30/2021 14:52:55 - INFO - __main__ - Step 9593: {'lr': 0.000496760644580894, 'samples': 1841856, 'steps': 9592, 'loss/train': 1.881445288658142} 08/30/2021 14:52:55 - INFO - __main__ - Step 9594: {'lr': 0.0004967597930127595, 'samples': 1842048, 'steps': 9593, 'loss/train': 3.591984987258911} 08/30/2021 14:52:56 - INFO - __main__ - Step 9595: {'lr': 0.0004967589413334387, 'samples': 1842240, 'steps': 9594, 'loss/train': 1.8645308017730713} 08/30/2021 14:52:56 - INFO - __main__ - Step 9596: {'lr': 0.0004967580895429322, 'samples': 1842432, 'steps': 9595, 'loss/train': 1.7857896089553833} 08/30/2021 14:52:57 - INFO - __main__ - Step 9597: {'lr': 0.0004967572376412405, 'samples': 1842624, 'steps': 9596, 'loss/train': 2.2183992862701416} 08/30/2021 14:52:58 - INFO - __main__ - Step 9598: {'lr': 0.0004967563856283636, 'samples': 1842816, 'steps': 9597, 'loss/train': 1.6056443452835083} 08/30/2021 14:52:58 - INFO - __main__ - Step 9599: {'lr': 0.000496755533504302, 'samples': 1843008, 'steps': 9598, 'loss/train': 1.9285104274749756} 08/30/2021 14:52:59 - INFO - __main__ - Step 9600: {'lr': 0.0004967546812690563, 'samples': 1843200, 'steps': 9599, 'loss/train': 2.4664130210876465} 08/30/2021 14:52:59 - INFO - __main__ - Step 9601: {'lr': 0.0004967538289226267, 'samples': 1843392, 'steps': 9600, 'loss/train': 2.390072822570801} 08/30/2021 14:52:59 - INFO - __main__ - Step 9602: {'lr': 0.0004967529764650137, 'samples': 1843584, 'steps': 9601, 'loss/train': 1.3265252113342285} 08/30/2021 14:53:01 - INFO - __main__ - Step 9603: {'lr': 0.0004967521238962175, 'samples': 1843776, 'steps': 9602, 'loss/train': 2.01141095161438} 08/30/2021 14:53:01 - INFO - __main__ - Step 9604: {'lr': 0.0004967512712162387, 'samples': 1843968, 'steps': 9603, 'loss/train': 1.1177914142608643} 08/30/2021 14:53:02 - INFO - __main__ - Step 9605: {'lr': 0.0004967504184250775, 'samples': 1844160, 'steps': 9604, 'loss/train': 1.9945052862167358} 08/30/2021 14:53:02 - INFO - __main__ - Step 9606: {'lr': 0.0004967495655227344, 'samples': 1844352, 'steps': 9605, 'loss/train': 2.2381575107574463} 08/30/2021 14:53:02 - INFO - __main__ - Step 9607: {'lr': 0.0004967487125092098, 'samples': 1844544, 'steps': 9606, 'loss/train': 1.798716425895691} 08/30/2021 14:53:04 - INFO - __main__ - Step 9608: {'lr': 0.0004967478593845041, 'samples': 1844736, 'steps': 9607, 'loss/train': 1.7776857614517212} 08/30/2021 14:53:04 - INFO - __main__ - Step 9609: {'lr': 0.0004967470061486175, 'samples': 1844928, 'steps': 9608, 'loss/train': 1.7392473220825195} 08/30/2021 14:53:05 - INFO - __main__ - Step 9610: {'lr': 0.0004967461528015506, 'samples': 1845120, 'steps': 9609, 'loss/train': 1.9466431140899658} 08/30/2021 14:53:05 - INFO - __main__ - Step 9611: {'lr': 0.0004967452993433036, 'samples': 1845312, 'steps': 9610, 'loss/train': 1.838362216949463} 08/30/2021 14:53:05 - INFO - __main__ - Step 9612: {'lr': 0.0004967444457738769, 'samples': 1845504, 'steps': 9611, 'loss/train': 0.1852114498615265} 08/30/2021 14:53:07 - INFO - __main__ - Step 9613: {'lr': 0.0004967435920932711, 'samples': 1845696, 'steps': 9612, 'loss/train': 2.0451154708862305} 08/30/2021 14:53:07 - INFO - __main__ - Step 9614: {'lr': 0.0004967427383014865, 'samples': 1845888, 'steps': 9613, 'loss/train': 0.8990710973739624} 08/30/2021 14:53:08 - INFO - __main__ - Step 9615: {'lr': 0.0004967418843985233, 'samples': 1846080, 'steps': 9614, 'loss/train': 1.021018624305725} 08/30/2021 14:53:08 - INFO - __main__ - Step 9616: {'lr': 0.0004967410303843821, 'samples': 1846272, 'steps': 9615, 'loss/train': 1.8680695295333862} 08/30/2021 14:53:08 - INFO - __main__ - Step 9617: {'lr': 0.0004967401762590631, 'samples': 1846464, 'steps': 9616, 'loss/train': 1.7404403686523438} 08/30/2021 14:53:10 - INFO - __main__ - Step 9618: {'lr': 0.0004967393220225668, 'samples': 1846656, 'steps': 9617, 'loss/train': 2.0626628398895264} 08/30/2021 14:53:10 - INFO - __main__ - Step 9619: {'lr': 0.0004967384676748936, 'samples': 1846848, 'steps': 9618, 'loss/train': 2.7807576656341553} 08/30/2021 14:53:11 - INFO - __main__ - Step 9620: {'lr': 0.0004967376132160438, 'samples': 1847040, 'steps': 9619, 'loss/train': 2.164260149002075} 08/30/2021 14:53:11 - INFO - __main__ - Step 9621: {'lr': 0.000496736758646018, 'samples': 1847232, 'steps': 9620, 'loss/train': 1.8069162368774414} 08/30/2021 14:53:11 - INFO - __main__ - Step 9622: {'lr': 0.0004967359039648163, 'samples': 1847424, 'steps': 9621, 'loss/train': 1.8062012195587158} 08/30/2021 14:53:13 - INFO - __main__ - Step 9623: {'lr': 0.0004967350491724392, 'samples': 1847616, 'steps': 9622, 'loss/train': 1.4811952114105225} 08/30/2021 14:53:13 - INFO - __main__ - Step 9624: {'lr': 0.0004967341942688872, 'samples': 1847808, 'steps': 9623, 'loss/train': 2.2838680744171143} 08/30/2021 14:53:14 - INFO - __main__ - Step 9625: {'lr': 0.0004967333392541604, 'samples': 1848000, 'steps': 9624, 'loss/train': 1.7904081344604492} 08/30/2021 14:53:14 - INFO - __main__ - Step 9626: {'lr': 0.0004967324841282596, 'samples': 1848192, 'steps': 9625, 'loss/train': 2.0094234943389893} 08/30/2021 14:53:14 - INFO - __main__ - Step 9627: {'lr': 0.0004967316288911847, 'samples': 1848384, 'steps': 9626, 'loss/train': 2.010408401489258} 08/30/2021 14:53:16 - INFO - __main__ - Step 9628: {'lr': 0.0004967307735429365, 'samples': 1848576, 'steps': 9627, 'loss/train': 1.8527088165283203} 08/30/2021 14:53:17 - INFO - __main__ - Step 9629: {'lr': 0.0004967299180835153, 'samples': 1848768, 'steps': 9628, 'loss/train': 1.859185814857483} 08/30/2021 14:53:17 - INFO - __main__ - Step 9630: {'lr': 0.0004967290625129212, 'samples': 1848960, 'steps': 9629, 'loss/train': 1.5661931037902832} 08/30/2021 14:53:17 - INFO - __main__ - Step 9631: {'lr': 0.0004967282068311548, 'samples': 1849152, 'steps': 9630, 'loss/train': 1.8538151979446411} 08/30/2021 14:53:18 - INFO - __main__ - Step 9632: {'lr': 0.0004967273510382166, 'samples': 1849344, 'steps': 9631, 'loss/train': 1.946212887763977} 08/30/2021 14:53:18 - INFO - __main__ - Step 9633: {'lr': 0.0004967264951341069, 'samples': 1849536, 'steps': 9632, 'loss/train': 1.5135653018951416} 08/30/2021 14:53:20 - INFO - __main__ - Step 9634: {'lr': 0.0004967256391188258, 'samples': 1849728, 'steps': 9633, 'loss/train': 0.2908616065979004} 08/30/2021 14:53:20 - INFO - __main__ - Step 9635: {'lr': 0.0004967247829923742, 'samples': 1849920, 'steps': 9634, 'loss/train': 1.8376696109771729} 08/30/2021 14:53:20 - INFO - __main__ - Step 9636: {'lr': 0.0004967239267547521, 'samples': 1850112, 'steps': 9635, 'loss/train': 1.7155654430389404} 08/30/2021 14:53:21 - INFO - __main__ - Step 9637: {'lr': 0.00049672307040596, 'samples': 1850304, 'steps': 9636, 'loss/train': 1.8015106916427612} 08/30/2021 14:53:21 - INFO - __main__ - Step 9638: {'lr': 0.0004967222139459983, 'samples': 1850496, 'steps': 9637, 'loss/train': 1.6642169952392578} 08/30/2021 14:53:23 - INFO - __main__ - Step 9639: {'lr': 0.0004967213573748674, 'samples': 1850688, 'steps': 9638, 'loss/train': 2.2503201961517334} 08/30/2021 14:53:24 - INFO - __main__ - Step 9640: {'lr': 0.0004967205006925677, 'samples': 1850880, 'steps': 9639, 'loss/train': 1.7300949096679688} 08/30/2021 14:53:24 - INFO - __main__ - Step 9641: {'lr': 0.0004967196438990995, 'samples': 1851072, 'steps': 9640, 'loss/train': 1.4293779134750366} 08/30/2021 14:53:24 - INFO - __main__ - Step 9642: {'lr': 0.0004967187869944632, 'samples': 1851264, 'steps': 9641, 'loss/train': 2.84515380859375} 08/30/2021 14:53:25 - INFO - __main__ - Step 9643: {'lr': 0.0004967179299786593, 'samples': 1851456, 'steps': 9642, 'loss/train': 1.5416079759597778} 08/30/2021 14:53:25 - INFO - __main__ - Step 9644: {'lr': 0.000496717072851688, 'samples': 1851648, 'steps': 9643, 'loss/train': 1.9394845962524414} 08/30/2021 14:53:27 - INFO - __main__ - Step 9645: {'lr': 0.0004967162156135499, 'samples': 1851840, 'steps': 9644, 'loss/train': 2.371034860610962} 08/30/2021 14:53:27 - INFO - __main__ - Step 9646: {'lr': 0.0004967153582642452, 'samples': 1852032, 'steps': 9645, 'loss/train': 1.4911154508590698} 08/30/2021 14:53:27 - INFO - __main__ - Step 9647: {'lr': 0.0004967145008037744, 'samples': 1852224, 'steps': 9646, 'loss/train': 2.4870901107788086} 08/30/2021 14:53:28 - INFO - __main__ - Step 9648: {'lr': 0.000496713643232138, 'samples': 1852416, 'steps': 9647, 'loss/train': 2.0515434741973877} 08/30/2021 14:53:28 - INFO - __main__ - Step 9649: {'lr': 0.000496712785549336, 'samples': 1852608, 'steps': 9648, 'loss/train': 2.0488858222961426} 08/30/2021 14:53:30 - INFO - __main__ - Step 9650: {'lr': 0.0004967119277553692, 'samples': 1852800, 'steps': 9649, 'loss/train': 1.652200698852539} 08/30/2021 14:53:30 - INFO - __main__ - Step 9651: {'lr': 0.0004967110698502377, 'samples': 1852992, 'steps': 9650, 'loss/train': 1.6506527662277222} 08/30/2021 14:53:31 - INFO - __main__ - Step 9652: {'lr': 0.000496710211833942, 'samples': 1853184, 'steps': 9651, 'loss/train': 1.3091411590576172} 08/30/2021 14:53:31 - INFO - __main__ - Step 9653: {'lr': 0.0004967093537064825, 'samples': 1853376, 'steps': 9652, 'loss/train': 2.4822838306427} 08/30/2021 14:53:31 - INFO - __main__ - Step 9654: {'lr': 0.0004967084954678597, 'samples': 1853568, 'steps': 9653, 'loss/train': 1.5479607582092285} 08/30/2021 14:53:33 - INFO - __main__ - Step 9655: {'lr': 0.0004967076371180738, 'samples': 1853760, 'steps': 9654, 'loss/train': 1.7819963693618774} 08/30/2021 14:53:33 - INFO - __main__ - Step 9656: {'lr': 0.0004967067786571251, 'samples': 1853952, 'steps': 9655, 'loss/train': 0.712238609790802} 08/30/2021 14:53:34 - INFO - __main__ - Step 9657: {'lr': 0.0004967059200850142, 'samples': 1854144, 'steps': 9656, 'loss/train': 1.739729881286621} 08/30/2021 14:53:34 - INFO - __main__ - Step 9658: {'lr': 0.0004967050614017415, 'samples': 1854336, 'steps': 9657, 'loss/train': 0.6492201089859009} 08/30/2021 14:53:35 - INFO - __main__ - Step 9659: {'lr': 0.0004967042026073073, 'samples': 1854528, 'steps': 9658, 'loss/train': 2.296637773513794} 08/30/2021 14:53:35 - INFO - __main__ - Step 9660: {'lr': 0.000496703343701712, 'samples': 1854720, 'steps': 9659, 'loss/train': 1.7050857543945312} 08/30/2021 14:53:36 - INFO - __main__ - Step 9661: {'lr': 0.0004967024846849558, 'samples': 1854912, 'steps': 9660, 'loss/train': 1.9776008129119873} 08/30/2021 14:53:37 - INFO - __main__ - Step 9662: {'lr': 0.0004967016255570394, 'samples': 1855104, 'steps': 9661, 'loss/train': 0.28526273369789124} 08/30/2021 14:53:37 - INFO - __main__ - Step 9663: {'lr': 0.0004967007663179632, 'samples': 1855296, 'steps': 9662, 'loss/train': 0.7856886982917786} 08/30/2021 14:53:38 - INFO - __main__ - Step 9664: {'lr': 0.0004966999069677272, 'samples': 1855488, 'steps': 9663, 'loss/train': 1.9313335418701172} 08/30/2021 14:53:38 - INFO - __main__ - Step 9665: {'lr': 0.0004966990475063321, 'samples': 1855680, 'steps': 9664, 'loss/train': 1.558266282081604} 08/30/2021 14:53:39 - INFO - __main__ - Step 9666: {'lr': 0.0004966981879337783, 'samples': 1855872, 'steps': 9665, 'loss/train': 1.5345159769058228} 08/30/2021 14:53:40 - INFO - __main__ - Step 9667: {'lr': 0.0004966973282500661, 'samples': 1856064, 'steps': 9666, 'loss/train': 1.8651546239852905} 08/30/2021 14:53:40 - INFO - __main__ - Step 9668: {'lr': 0.0004966964684551958, 'samples': 1856256, 'steps': 9667, 'loss/train': 1.5681730508804321} 08/30/2021 14:53:40 - INFO - __main__ - Step 9669: {'lr': 0.0004966956085491679, 'samples': 1856448, 'steps': 9668, 'loss/train': 1.5579904317855835} 08/30/2021 14:53:41 - INFO - __main__ - Step 9670: {'lr': 0.0004966947485319828, 'samples': 1856640, 'steps': 9669, 'loss/train': 1.712479829788208} 08/30/2021 14:53:42 - INFO - __main__ - Step 9671: {'lr': 0.0004966938884036408, 'samples': 1856832, 'steps': 9670, 'loss/train': 1.6334211826324463} 08/30/2021 14:53:43 - INFO - __main__ - Step 9672: {'lr': 0.0004966930281641423, 'samples': 1857024, 'steps': 9671, 'loss/train': 3.4267959594726562} 08/30/2021 14:53:43 - INFO - __main__ - Step 9673: {'lr': 0.0004966921678134879, 'samples': 1857216, 'steps': 9672, 'loss/train': 1.9703158140182495} 08/30/2021 14:53:44 - INFO - __main__ - Step 9674: {'lr': 0.0004966913073516777, 'samples': 1857408, 'steps': 9673, 'loss/train': 2.0359699726104736} 08/30/2021 14:53:44 - INFO - __main__ - Step 9675: {'lr': 0.0004966904467787123, 'samples': 1857600, 'steps': 9674, 'loss/train': 2.0441136360168457} 08/30/2021 14:53:44 - INFO - __main__ - Step 9676: {'lr': 0.0004966895860945918, 'samples': 1857792, 'steps': 9675, 'loss/train': 2.440521717071533} 08/30/2021 14:53:46 - INFO - __main__ - Step 9677: {'lr': 0.0004966887252993169, 'samples': 1857984, 'steps': 9676, 'loss/train': 1.7095386981964111} 08/30/2021 14:53:47 - INFO - __main__ - Step 9678: {'lr': 0.0004966878643928879, 'samples': 1858176, 'steps': 9677, 'loss/train': 1.8088562488555908} 08/30/2021 14:53:47 - INFO - __main__ - Step 9679: {'lr': 0.0004966870033753051, 'samples': 1858368, 'steps': 9678, 'loss/train': 2.0200352668762207} 08/30/2021 14:53:47 - INFO - __main__ - Step 9680: {'lr': 0.0004966861422465689, 'samples': 1858560, 'steps': 9679, 'loss/train': 0.2883291244506836} 08/30/2021 14:53:48 - INFO - __main__ - Step 9681: {'lr': 0.0004966852810066798, 'samples': 1858752, 'steps': 9680, 'loss/train': 2.0641093254089355} 08/30/2021 14:53:49 - INFO - __main__ - Step 9682: {'lr': 0.0004966844196556382, 'samples': 1858944, 'steps': 9681, 'loss/train': 1.7363930940628052} 08/30/2021 14:53:50 - INFO - __main__ - Step 9683: {'lr': 0.0004966835581934442, 'samples': 1859136, 'steps': 9682, 'loss/train': 1.9491764307022095} 08/30/2021 14:53:50 - INFO - __main__ - Step 9684: {'lr': 0.0004966826966200985, 'samples': 1859328, 'steps': 9683, 'loss/train': 1.997516393661499} 08/30/2021 14:53:50 - INFO - __main__ - Step 9685: {'lr': 0.0004966818349356015, 'samples': 1859520, 'steps': 9684, 'loss/train': 2.0222957134246826} 08/30/2021 14:53:51 - INFO - __main__ - Step 9686: {'lr': 0.0004966809731399533, 'samples': 1859712, 'steps': 9685, 'loss/train': 1.3625972270965576} 08/30/2021 14:53:52 - INFO - __main__ - Step 9687: {'lr': 0.0004966801112331545, 'samples': 1859904, 'steps': 9686, 'loss/train': 1.7286548614501953} 08/30/2021 14:53:53 - INFO - __main__ - Step 9688: {'lr': 0.0004966792492152054, 'samples': 1860096, 'steps': 9687, 'loss/train': 1.8468976020812988} 08/30/2021 14:53:53 - INFO - __main__ - Step 9689: {'lr': 0.0004966783870861066, 'samples': 1860288, 'steps': 9688, 'loss/train': 2.112144947052002} 08/30/2021 14:53:54 - INFO - __main__ - Step 9690: {'lr': 0.0004966775248458582, 'samples': 1860480, 'steps': 9689, 'loss/train': 1.7111119031906128} 08/30/2021 14:53:54 - INFO - __main__ - Step 9691: {'lr': 0.0004966766624944607, 'samples': 1860672, 'steps': 9690, 'loss/train': 1.796911597251892} 08/30/2021 14:53:54 - INFO - __main__ - Step 9692: {'lr': 0.0004966758000319147, 'samples': 1860864, 'steps': 9691, 'loss/train': 2.128903865814209} 08/30/2021 14:53:57 - INFO - __main__ - Step 9693: {'lr': 0.0004966749374582202, 'samples': 1861056, 'steps': 9692, 'loss/train': 1.1706323623657227} 08/30/2021 14:53:57 - INFO - __main__ - Step 9694: {'lr': 0.0004966740747733778, 'samples': 1861248, 'steps': 9693, 'loss/train': 1.07637619972229} 08/30/2021 14:53:57 - INFO - __main__ - Step 9695: {'lr': 0.0004966732119773879, 'samples': 1861440, 'steps': 9694, 'loss/train': 0.9190359711647034} 08/30/2021 14:53:58 - INFO - __main__ - Step 9696: {'lr': 0.0004966723490702509, 'samples': 1861632, 'steps': 9695, 'loss/train': 1.8705346584320068} 08/30/2021 14:53:58 - INFO - __main__ - Step 9697: {'lr': 0.000496671486051967, 'samples': 1861824, 'steps': 9696, 'loss/train': 1.7523695230484009} 08/30/2021 14:54:00 - INFO - __main__ - Step 9698: {'lr': 0.0004966706229225368, 'samples': 1862016, 'steps': 9697, 'loss/train': 2.006720542907715} 08/30/2021 14:54:00 - INFO - __main__ - Step 9699: {'lr': 0.0004966697596819607, 'samples': 1862208, 'steps': 9698, 'loss/train': 1.9750852584838867} 08/30/2021 14:54:01 - INFO - __main__ - Step 9700: {'lr': 0.0004966688963302389, 'samples': 1862400, 'steps': 9699, 'loss/train': 2.217642307281494} 08/30/2021 14:54:01 - INFO - __main__ - Step 9701: {'lr': 0.000496668032867372, 'samples': 1862592, 'steps': 9700, 'loss/train': 2.213373899459839} 08/30/2021 14:54:01 - INFO - __main__ - Step 9702: {'lr': 0.0004966671692933603, 'samples': 1862784, 'steps': 9701, 'loss/train': 1.9149820804595947} 08/30/2021 14:54:03 - INFO - __main__ - Step 9703: {'lr': 0.0004966663056082041, 'samples': 1862976, 'steps': 9702, 'loss/train': 1.9143811464309692} 08/30/2021 14:54:03 - INFO - __main__ - Step 9704: {'lr': 0.0004966654418119039, 'samples': 1863168, 'steps': 9703, 'loss/train': 1.3695147037506104} 08/30/2021 14:54:04 - INFO - __main__ - Step 9705: {'lr': 0.00049666457790446, 'samples': 1863360, 'steps': 9704, 'loss/train': 2.261863946914673} 08/30/2021 14:54:04 - INFO - __main__ - Step 9706: {'lr': 0.000496663713885873, 'samples': 1863552, 'steps': 9705, 'loss/train': 1.9517362117767334} 08/30/2021 14:54:04 - INFO - __main__ - Step 9707: {'lr': 0.0004966628497561431, 'samples': 1863744, 'steps': 9706, 'loss/train': 2.2061758041381836} 08/30/2021 14:54:06 - INFO - __main__ - Step 9708: {'lr': 0.0004966619855152706, 'samples': 1863936, 'steps': 9707, 'loss/train': 1.8381626605987549} 08/30/2021 14:54:06 - INFO - __main__ - Step 9709: {'lr': 0.0004966611211632561, 'samples': 1864128, 'steps': 9708, 'loss/train': 3.0681979656219482} 08/30/2021 14:54:07 - INFO - __main__ - Step 9710: {'lr': 0.0004966602567000999, 'samples': 1864320, 'steps': 9709, 'loss/train': 1.9511271715164185} 08/30/2021 14:54:07 - INFO - __main__ - Step 9711: {'lr': 0.0004966593921258023, 'samples': 1864512, 'steps': 9710, 'loss/train': 2.433972120285034} 08/30/2021 14:54:07 - INFO - __main__ - Step 9712: {'lr': 0.000496658527440364, 'samples': 1864704, 'steps': 9711, 'loss/train': 1.9139094352722168} 08/30/2021 14:54:08 - INFO - __main__ - Step 9713: {'lr': 0.000496657662643785, 'samples': 1864896, 'steps': 9712, 'loss/train': 1.9728235006332397} 08/30/2021 14:54:09 - INFO - __main__ - Step 9714: {'lr': 0.000496656797736066, 'samples': 1865088, 'steps': 9713, 'loss/train': 2.6217501163482666} 08/30/2021 14:54:10 - INFO - __main__ - Step 9715: {'lr': 0.0004966559327172071, 'samples': 1865280, 'steps': 9714, 'loss/train': 2.076709270477295} 08/30/2021 14:54:10 - INFO - __main__ - Step 9716: {'lr': 0.0004966550675872089, 'samples': 1865472, 'steps': 9715, 'loss/train': 2.4587104320526123} 08/30/2021 14:54:10 - INFO - __main__ - Step 9717: {'lr': 0.0004966542023460718, 'samples': 1865664, 'steps': 9716, 'loss/train': 2.441128969192505} 08/30/2021 14:54:11 - INFO - __main__ - Step 9718: {'lr': 0.000496653336993796, 'samples': 1865856, 'steps': 9717, 'loss/train': 1.9450116157531738} 08/30/2021 14:54:12 - INFO - __main__ - Step 9719: {'lr': 0.0004966524715303821, 'samples': 1866048, 'steps': 9718, 'loss/train': 2.079266309738159} 08/30/2021 14:54:13 - INFO - __main__ - Step 9720: {'lr': 0.0004966516059558304, 'samples': 1866240, 'steps': 9719, 'loss/train': 1.6373075246810913} 08/30/2021 14:54:13 - INFO - __main__ - Step 9721: {'lr': 0.0004966507402701413, 'samples': 1866432, 'steps': 9720, 'loss/train': 1.7225592136383057} 08/30/2021 14:54:14 - INFO - __main__ - Step 9722: {'lr': 0.0004966498744733151, 'samples': 1866624, 'steps': 9721, 'loss/train': 2.1595609188079834} 08/30/2021 14:54:14 - INFO - __main__ - Step 9723: {'lr': 0.0004966490085653523, 'samples': 1866816, 'steps': 9722, 'loss/train': 1.6869670152664185} 08/30/2021 14:54:15 - INFO - __main__ - Step 9724: {'lr': 0.0004966481425462533, 'samples': 1867008, 'steps': 9723, 'loss/train': 0.24262908101081848} 08/30/2021 14:54:16 - INFO - __main__ - Step 9725: {'lr': 0.0004966472764160183, 'samples': 1867200, 'steps': 9724, 'loss/train': 1.9964102506637573} 08/30/2021 14:54:16 - INFO - __main__ - Step 9726: {'lr': 0.000496646410174648, 'samples': 1867392, 'steps': 9725, 'loss/train': 4.726476669311523} 08/30/2021 14:54:17 - INFO - __main__ - Step 9727: {'lr': 0.0004966455438221427, 'samples': 1867584, 'steps': 9726, 'loss/train': 1.2921795845031738} 08/30/2021 14:54:17 - INFO - __main__ - Step 9728: {'lr': 0.0004966446773585026, 'samples': 1867776, 'steps': 9727, 'loss/train': 2.107571840286255} 08/30/2021 14:54:18 - INFO - __main__ - Step 9729: {'lr': 0.0004966438107837283, 'samples': 1867968, 'steps': 9728, 'loss/train': 6.637866973876953} 08/30/2021 14:54:19 - INFO - __main__ - Step 9730: {'lr': 0.00049664294409782, 'samples': 1868160, 'steps': 9729, 'loss/train': 2.1792266368865967} 08/30/2021 14:54:19 - INFO - __main__ - Step 9731: {'lr': 0.0004966420773007782, 'samples': 1868352, 'steps': 9730, 'loss/train': 1.0178474187850952} 08/30/2021 14:54:20 - INFO - __main__ - Step 9732: {'lr': 0.0004966412103926034, 'samples': 1868544, 'steps': 9731, 'loss/train': 1.7584015130996704} 08/30/2021 14:54:20 - INFO - __main__ - Step 9733: {'lr': 0.0004966403433732958, 'samples': 1868736, 'steps': 9732, 'loss/train': 1.9877625703811646} 08/30/2021 14:54:22 - INFO - __main__ - Step 9734: {'lr': 0.0004966394762428559, 'samples': 1868928, 'steps': 9733, 'loss/train': 1.9409760236740112} 08/30/2021 14:54:22 - INFO - __main__ - Step 9735: {'lr': 0.0004966386090012841, 'samples': 1869120, 'steps': 9734, 'loss/train': 1.9843204021453857} 08/30/2021 14:54:22 - INFO - __main__ - Step 9736: {'lr': 0.0004966377416485806, 'samples': 1869312, 'steps': 9735, 'loss/train': 1.9466495513916016} 08/30/2021 14:54:23 - INFO - __main__ - Step 9737: {'lr': 0.0004966368741847461, 'samples': 1869504, 'steps': 9736, 'loss/train': 1.8497463464736938} 08/30/2021 14:54:23 - INFO - __main__ - Step 9738: {'lr': 0.0004966360066097807, 'samples': 1869696, 'steps': 9737, 'loss/train': 1.6434361934661865} 08/30/2021 14:54:23 - INFO - __main__ - Step 9739: {'lr': 0.0004966351389236851, 'samples': 1869888, 'steps': 9738, 'loss/train': 0.1551797240972519} 08/30/2021 14:54:25 - INFO - __main__ - Step 9740: {'lr': 0.0004966342711264593, 'samples': 1870080, 'steps': 9739, 'loss/train': 0.14922592043876648} 08/30/2021 14:54:25 - INFO - __main__ - Step 9741: {'lr': 0.000496633403218104, 'samples': 1870272, 'steps': 9740, 'loss/train': 1.4524890184402466} 08/30/2021 14:54:26 - INFO - __main__ - Step 9742: {'lr': 0.0004966325351986195, 'samples': 1870464, 'steps': 9741, 'loss/train': 1.8672969341278076} 08/30/2021 14:54:26 - INFO - __main__ - Step 9743: {'lr': 0.0004966316670680062, 'samples': 1870656, 'steps': 9742, 'loss/train': 1.6861193180084229} 08/30/2021 14:54:26 - INFO - __main__ - Step 9744: {'lr': 0.0004966307988262644, 'samples': 1870848, 'steps': 9743, 'loss/train': 2.0013606548309326} 08/30/2021 14:54:28 - INFO - __main__ - Step 9745: {'lr': 0.0004966299304733947, 'samples': 1871040, 'steps': 9744, 'loss/train': 2.092226028442383} 08/30/2021 14:54:29 - INFO - __main__ - Step 9746: {'lr': 0.0004966290620093972, 'samples': 1871232, 'steps': 9745, 'loss/train': 2.124173879623413} 08/30/2021 14:54:29 - INFO - __main__ - Step 9747: {'lr': 0.0004966281934342725, 'samples': 1871424, 'steps': 9746, 'loss/train': 1.5140055418014526} 08/30/2021 14:54:29 - INFO - __main__ - Step 9748: {'lr': 0.000496627324748021, 'samples': 1871616, 'steps': 9747, 'loss/train': 1.7213398218154907} 08/30/2021 14:54:30 - INFO - __main__ - Step 9749: {'lr': 0.000496626455950643, 'samples': 1871808, 'steps': 9748, 'loss/train': 1.8757199048995972} 08/30/2021 14:54:32 - INFO - __main__ - Step 9750: {'lr': 0.000496625587042139, 'samples': 1872000, 'steps': 9749, 'loss/train': 1.5113251209259033} 08/30/2021 14:54:32 - INFO - __main__ - Step 9751: {'lr': 0.0004966247180225092, 'samples': 1872192, 'steps': 9750, 'loss/train': 1.7895302772521973} 08/30/2021 14:54:32 - INFO - __main__ - Step 9752: {'lr': 0.0004966238488917542, 'samples': 1872384, 'steps': 9751, 'loss/train': 1.876662254333496} 08/30/2021 14:54:33 - INFO - __main__ - Step 9753: {'lr': 0.0004966229796498742, 'samples': 1872576, 'steps': 9752, 'loss/train': 1.9065462350845337} 08/30/2021 14:54:33 - INFO - __main__ - Step 9754: {'lr': 0.0004966221102968698, 'samples': 1872768, 'steps': 9753, 'loss/train': 1.8621559143066406} 08/30/2021 14:54:33 - INFO - __main__ - Step 9755: {'lr': 0.0004966212408327412, 'samples': 1872960, 'steps': 9754, 'loss/train': 1.696763038635254} 08/30/2021 14:54:35 - INFO - __main__ - Step 9756: {'lr': 0.0004966203712574889, 'samples': 1873152, 'steps': 9755, 'loss/train': 1.6754891872406006} 08/30/2021 14:54:35 - INFO - __main__ - Step 9757: {'lr': 0.0004966195015711132, 'samples': 1873344, 'steps': 9756, 'loss/train': 2.2423617839813232} 08/30/2021 14:54:36 - INFO - __main__ - Step 9758: {'lr': 0.0004966186317736146, 'samples': 1873536, 'steps': 9757, 'loss/train': 2.1737141609191895} 08/30/2021 14:54:36 - INFO - __main__ - Step 9759: {'lr': 0.0004966177618649935, 'samples': 1873728, 'steps': 9758, 'loss/train': 1.8301485776901245} 08/30/2021 14:54:36 - INFO - __main__ - Step 9760: {'lr': 0.0004966168918452503, 'samples': 1873920, 'steps': 9759, 'loss/train': 1.9839552640914917} 08/30/2021 14:54:38 - INFO - __main__ - Step 9761: {'lr': 0.0004966160217143852, 'samples': 1874112, 'steps': 9760, 'loss/train': 1.8732393980026245} 08/30/2021 14:54:38 - INFO - __main__ - Step 9762: {'lr': 0.0004966151514723988, 'samples': 1874304, 'steps': 9761, 'loss/train': 1.56182062625885} 08/30/2021 14:54:39 - INFO - __main__ - Step 9763: {'lr': 0.0004966142811192914, 'samples': 1874496, 'steps': 9762, 'loss/train': 1.9897133111953735} 08/30/2021 14:54:39 - INFO - __main__ - Step 9764: {'lr': 0.0004966134106550634, 'samples': 1874688, 'steps': 9763, 'loss/train': 1.981635332107544} 08/30/2021 14:54:40 - INFO - __main__ - Step 9765: {'lr': 0.0004966125400797152, 'samples': 1874880, 'steps': 9764, 'loss/train': 1.4501882791519165} 08/30/2021 14:54:41 - INFO - __main__ - Step 9766: {'lr': 0.0004966116693932472, 'samples': 1875072, 'steps': 9765, 'loss/train': 1.7068828344345093} 08/30/2021 14:54:42 - INFO - __main__ - Step 9767: {'lr': 0.0004966107985956598, 'samples': 1875264, 'steps': 9766, 'loss/train': 2.004703998565674} 08/30/2021 14:54:42 - INFO - __main__ - Step 9768: {'lr': 0.0004966099276869534, 'samples': 1875456, 'steps': 9767, 'loss/train': 1.7816212177276611} 08/30/2021 14:54:42 - INFO - __main__ - Step 9769: {'lr': 0.0004966090566671283, 'samples': 1875648, 'steps': 9768, 'loss/train': 1.9179739952087402} 08/30/2021 14:54:43 - INFO - __main__ - Step 9770: {'lr': 0.000496608185536185, 'samples': 1875840, 'steps': 9769, 'loss/train': 2.208346366882324} 08/30/2021 14:54:44 - INFO - __main__ - Step 9771: {'lr': 0.0004966073142941239, 'samples': 1876032, 'steps': 9770, 'loss/train': 2.0073368549346924} 08/30/2021 14:54:45 - INFO - __main__ - Step 9772: {'lr': 0.0004966064429409452, 'samples': 1876224, 'steps': 9771, 'loss/train': 1.1819682121276855} 08/30/2021 14:54:45 - INFO - __main__ - Step 9773: {'lr': 0.0004966055714766496, 'samples': 1876416, 'steps': 9772, 'loss/train': 2.517453670501709} 08/30/2021 14:54:45 - INFO - __main__ - Step 9774: {'lr': 0.0004966046999012373, 'samples': 1876608, 'steps': 9773, 'loss/train': 1.1560664176940918} 08/30/2021 14:54:46 - INFO - __main__ - Step 9775: {'lr': 0.0004966038282147087, 'samples': 1876800, 'steps': 9774, 'loss/train': 1.7246750593185425} 08/30/2021 14:54:47 - INFO - __main__ - Step 9776: {'lr': 0.0004966029564170643, 'samples': 1876992, 'steps': 9775, 'loss/train': 1.8625199794769287} 08/30/2021 14:54:48 - INFO - __main__ - Step 9777: {'lr': 0.0004966020845083044, 'samples': 1877184, 'steps': 9776, 'loss/train': 1.667828917503357} 08/30/2021 14:54:48 - INFO - __main__ - Step 9778: {'lr': 0.0004966012124884292, 'samples': 1877376, 'steps': 9777, 'loss/train': 1.385165810585022} 08/30/2021 14:54:48 - INFO - __main__ - Step 9779: {'lr': 0.0004966003403574395, 'samples': 1877568, 'steps': 9778, 'loss/train': 2.03983998298645} 08/30/2021 14:54:49 - INFO - __main__ - Step 9780: {'lr': 0.0004965994681153355, 'samples': 1877760, 'steps': 9779, 'loss/train': 2.0109755992889404} 08/30/2021 14:54:50 - INFO - __main__ - Step 9781: {'lr': 0.0004965985957621175, 'samples': 1877952, 'steps': 9780, 'loss/train': 2.1260452270507812} 08/30/2021 14:54:50 - INFO - __main__ - Step 9782: {'lr': 0.0004965977232977861, 'samples': 1878144, 'steps': 9781, 'loss/train': 1.8748568296432495} 08/30/2021 14:54:51 - INFO - __main__ - Step 9783: {'lr': 0.0004965968507223414, 'samples': 1878336, 'steps': 9782, 'loss/train': 2.1814732551574707} 08/30/2021 14:54:51 - INFO - __main__ - Step 9784: {'lr': 0.000496595978035784, 'samples': 1878528, 'steps': 9783, 'loss/train': 1.618996500968933} 08/30/2021 14:54:51 - INFO - __main__ - Step 9785: {'lr': 0.0004965951052381144, 'samples': 1878720, 'steps': 9784, 'loss/train': 2.164748191833496} 08/30/2021 14:54:53 - INFO - __main__ - Step 9786: {'lr': 0.0004965942323293328, 'samples': 1878912, 'steps': 9785, 'loss/train': 1.624773621559143} 08/30/2021 14:54:53 - INFO - __main__ - Step 9787: {'lr': 0.0004965933593094395, 'samples': 1879104, 'steps': 9786, 'loss/train': 2.1712048053741455} 08/30/2021 14:54:54 - INFO - __main__ - Step 9788: {'lr': 0.0004965924861784352, 'samples': 1879296, 'steps': 9787, 'loss/train': 1.660886526107788} 08/30/2021 14:54:54 - INFO - __main__ - Step 9789: {'lr': 0.0004965916129363201, 'samples': 1879488, 'steps': 9788, 'loss/train': 1.4098634719848633} 08/30/2021 14:54:55 - INFO - __main__ - Step 9790: {'lr': 0.0004965907395830945, 'samples': 1879680, 'steps': 9789, 'loss/train': 1.5025256872177124} 08/30/2021 14:54:56 - INFO - __main__ - Step 9791: {'lr': 0.000496589866118759, 'samples': 1879872, 'steps': 9790, 'loss/train': 1.7650216817855835} 08/30/2021 14:54:56 - INFO - __main__ - Step 9792: {'lr': 0.000496588992543314, 'samples': 1880064, 'steps': 9791, 'loss/train': 1.3867985010147095} 08/30/2021 14:54:57 - INFO - __main__ - Step 9793: {'lr': 0.0004965881188567597, 'samples': 1880256, 'steps': 9792, 'loss/train': 1.0742295980453491} 08/30/2021 14:54:57 - INFO - __main__ - Step 9794: {'lr': 0.0004965872450590965, 'samples': 1880448, 'steps': 9793, 'loss/train': 2.1396424770355225} 08/30/2021 14:54:58 - INFO - __main__ - Step 9795: {'lr': 0.0004965863711503251, 'samples': 1880640, 'steps': 9794, 'loss/train': 1.7687004804611206} 08/30/2021 14:54:58 - INFO - __main__ - Step 9796: {'lr': 0.0004965854971304457, 'samples': 1880832, 'steps': 9795, 'loss/train': 1.7895843982696533} 08/30/2021 14:54:59 - INFO - __main__ - Step 9797: {'lr': 0.0004965846229994586, 'samples': 1881024, 'steps': 9796, 'loss/train': 1.84823477268219} 08/30/2021 14:55:00 - INFO - __main__ - Step 9798: {'lr': 0.0004965837487573641, 'samples': 1881216, 'steps': 9797, 'loss/train': 1.886412501335144} 08/30/2021 14:55:00 - INFO - __main__ - Step 9799: {'lr': 0.000496582874404163, 'samples': 1881408, 'steps': 9798, 'loss/train': 1.9770792722702026} 08/30/2021 14:55:01 - INFO - __main__ - Step 9800: {'lr': 0.0004965819999398554, 'samples': 1881600, 'steps': 9799, 'loss/train': 2.7488694190979004} 08/30/2021 14:55:01 - INFO - __main__ - Step 9801: {'lr': 0.0004965811253644418, 'samples': 1881792, 'steps': 9800, 'loss/train': 2.4854705333709717} 08/30/2021 14:55:03 - INFO - __main__ - Step 9802: {'lr': 0.0004965802506779225, 'samples': 1881984, 'steps': 9801, 'loss/train': 1.3518996238708496} 08/30/2021 14:55:04 - INFO - __main__ - Step 9803: {'lr': 0.0004965793758802978, 'samples': 1882176, 'steps': 9802, 'loss/train': 1.8334020376205444} 08/30/2021 14:55:04 - INFO - __main__ - Step 9804: {'lr': 0.0004965785009715684, 'samples': 1882368, 'steps': 9803, 'loss/train': 1.8531948328018188} 08/30/2021 14:55:04 - INFO - __main__ - Step 9805: {'lr': 0.0004965776259517345, 'samples': 1882560, 'steps': 9804, 'loss/train': 1.7855840921401978} 08/30/2021 14:55:05 - INFO - __main__ - Step 9806: {'lr': 0.0004965767508207966, 'samples': 1882752, 'steps': 9805, 'loss/train': 2.297307014465332} 08/30/2021 14:55:06 - INFO - __main__ - Step 9807: {'lr': 0.000496575875578755, 'samples': 1882944, 'steps': 9806, 'loss/train': 1.3045541048049927} 08/30/2021 14:55:07 - INFO - __main__ - Step 9808: {'lr': 0.00049657500022561, 'samples': 1883136, 'steps': 9807, 'loss/train': 1.8016923666000366} 08/30/2021 14:55:07 - INFO - __main__ - Step 9809: {'lr': 0.0004965741247613622, 'samples': 1883328, 'steps': 9808, 'loss/train': 2.0325369834899902} 08/30/2021 14:55:07 - INFO - __main__ - Step 9810: {'lr': 0.0004965732491860119, 'samples': 1883520, 'steps': 9809, 'loss/train': 2.054710626602173} 08/30/2021 14:55:08 - INFO - __main__ - Step 9811: {'lr': 0.0004965723734995594, 'samples': 1883712, 'steps': 9810, 'loss/train': 1.7265582084655762} 08/30/2021 14:55:08 - INFO - __main__ - Step 9812: {'lr': 0.0004965714977020053, 'samples': 1883904, 'steps': 9811, 'loss/train': 2.0104353427886963} 08/30/2021 14:55:10 - INFO - __main__ - Step 9813: {'lr': 0.0004965706217933499, 'samples': 1884096, 'steps': 9812, 'loss/train': 1.5940203666687012} 08/30/2021 14:55:10 - INFO - __main__ - Step 9814: {'lr': 0.0004965697457735936, 'samples': 1884288, 'steps': 9813, 'loss/train': 1.9238561391830444} 08/30/2021 14:55:11 - INFO - __main__ - Step 9815: {'lr': 0.0004965688696427366, 'samples': 1884480, 'steps': 9814, 'loss/train': 1.7064625024795532} 08/30/2021 14:55:11 - INFO - __main__ - Step 9816: {'lr': 0.0004965679934007797, 'samples': 1884672, 'steps': 9815, 'loss/train': 1.8641884326934814} 08/30/2021 14:55:11 - INFO - __main__ - Step 9817: {'lr': 0.0004965671170477229, 'samples': 1884864, 'steps': 9816, 'loss/train': 0.137808158993721} 08/30/2021 14:55:13 - INFO - __main__ - Step 9818: {'lr': 0.0004965662405835668, 'samples': 1885056, 'steps': 9817, 'loss/train': 1.7908711433410645} 08/30/2021 14:55:13 - INFO - __main__ - Step 9819: {'lr': 0.0004965653640083118, 'samples': 1885248, 'steps': 9818, 'loss/train': 1.8567848205566406} 08/30/2021 14:55:14 - INFO - __main__ - Step 9820: {'lr': 0.0004965644873219583, 'samples': 1885440, 'steps': 9819, 'loss/train': 1.9928535223007202} 08/30/2021 14:55:14 - INFO - __main__ - Step 9821: {'lr': 0.0004965636105245066, 'samples': 1885632, 'steps': 9820, 'loss/train': 1.633752465248108} 08/30/2021 14:55:14 - INFO - __main__ - Step 9822: {'lr': 0.000496562733615957, 'samples': 1885824, 'steps': 9821, 'loss/train': 1.330245852470398} 08/30/2021 14:55:16 - INFO - __main__ - Step 9823: {'lr': 0.0004965618565963102, 'samples': 1886016, 'steps': 9822, 'loss/train': 1.980771780014038} 08/30/2021 14:55:16 - INFO - __main__ - Step 9824: {'lr': 0.0004965609794655664, 'samples': 1886208, 'steps': 9823, 'loss/train': 1.154754877090454} 08/30/2021 14:55:17 - INFO - __main__ - Step 9825: {'lr': 0.0004965601022237261, 'samples': 1886400, 'steps': 9824, 'loss/train': 1.9220635890960693} 08/30/2021 14:55:17 - INFO - __main__ - Step 9826: {'lr': 0.0004965592248707895, 'samples': 1886592, 'steps': 9825, 'loss/train': 1.9596201181411743} 08/30/2021 14:55:17 - INFO - __main__ - Step 9827: {'lr': 0.0004965583474067571, 'samples': 1886784, 'steps': 9826, 'loss/train': 1.6688120365142822} 08/30/2021 14:55:19 - INFO - __main__ - Step 9828: {'lr': 0.0004965574698316294, 'samples': 1886976, 'steps': 9827, 'loss/train': 1.6392722129821777} 08/30/2021 14:55:20 - INFO - __main__ - Step 9829: {'lr': 0.0004965565921454067, 'samples': 1887168, 'steps': 9828, 'loss/train': 1.8479280471801758} 08/30/2021 14:55:20 - INFO - __main__ - Step 9830: {'lr': 0.0004965557143480893, 'samples': 1887360, 'steps': 9829, 'loss/train': 2.1281254291534424} 08/30/2021 14:55:20 - INFO - __main__ - Step 9831: {'lr': 0.0004965548364396779, 'samples': 1887552, 'steps': 9830, 'loss/train': 1.7769168615341187} 08/30/2021 14:55:21 - INFO - __main__ - Step 9832: {'lr': 0.0004965539584201725, 'samples': 1887744, 'steps': 9831, 'loss/train': 2.1063497066497803} 08/30/2021 14:55:22 - INFO - __main__ - Step 9833: {'lr': 0.0004965530802895738, 'samples': 1887936, 'steps': 9832, 'loss/train': 2.6677818298339844} 08/30/2021 14:55:23 - INFO - __main__ - Step 9834: {'lr': 0.000496552202047882, 'samples': 1888128, 'steps': 9833, 'loss/train': 1.7689239978790283} 08/30/2021 14:55:23 - INFO - __main__ - Step 9835: {'lr': 0.0004965513236950977, 'samples': 1888320, 'steps': 9834, 'loss/train': 1.2834495306015015} 08/30/2021 14:55:23 - INFO - __main__ - Step 9836: {'lr': 0.0004965504452312211, 'samples': 1888512, 'steps': 9835, 'loss/train': 2.4768779277801514} 08/30/2021 14:55:24 - INFO - __main__ - Step 9837: {'lr': 0.0004965495666562527, 'samples': 1888704, 'steps': 9836, 'loss/train': 2.052020788192749} 08/30/2021 14:55:25 - INFO - __main__ - Step 9838: {'lr': 0.0004965486879701928, 'samples': 1888896, 'steps': 9837, 'loss/train': 1.5721266269683838} 08/30/2021 14:55:26 - INFO - __main__ - Step 9839: {'lr': 0.000496547809173042, 'samples': 1889088, 'steps': 9838, 'loss/train': 1.5373854637145996} 08/30/2021 14:55:26 - INFO - __main__ - Step 9840: {'lr': 0.0004965469302648005, 'samples': 1889280, 'steps': 9839, 'loss/train': 1.5755141973495483} 08/30/2021 14:55:26 - INFO - __main__ - Step 9841: {'lr': 0.0004965460512454688, 'samples': 1889472, 'steps': 9840, 'loss/train': 2.2881150245666504} 08/30/2021 14:55:27 - INFO - __main__ - Step 9842: {'lr': 0.0004965451721150471, 'samples': 1889664, 'steps': 9841, 'loss/train': 1.7578301429748535} 08/30/2021 14:55:27 - INFO - __main__ - Step 9843: {'lr': 0.0004965442928735361, 'samples': 1889856, 'steps': 9842, 'loss/train': 1.351906418800354} 08/30/2021 14:55:29 - INFO - __main__ - Step 9844: {'lr': 0.000496543413520936, 'samples': 1890048, 'steps': 9843, 'loss/train': 1.3496830463409424} 08/30/2021 14:55:29 - INFO - __main__ - Step 9845: {'lr': 0.0004965425340572472, 'samples': 1890240, 'steps': 9844, 'loss/train': 2.4627909660339355} 08/30/2021 14:55:29 - INFO - __main__ - Step 9846: {'lr': 0.0004965416544824703, 'samples': 1890432, 'steps': 9845, 'loss/train': 2.1591267585754395} 08/30/2021 14:55:30 - INFO - __main__ - Step 9847: {'lr': 0.0004965407747966053, 'samples': 1890624, 'steps': 9846, 'loss/train': 1.8776334524154663} 08/30/2021 14:55:30 - INFO - __main__ - Step 9848: {'lr': 0.000496539894999653, 'samples': 1890816, 'steps': 9847, 'loss/train': 2.76639461517334} 08/30/2021 14:55:32 - INFO - __main__ - Step 9849: {'lr': 0.0004965390150916136, 'samples': 1891008, 'steps': 9848, 'loss/train': 1.2349870204925537} 08/30/2021 14:55:32 - INFO - __main__ - Step 9850: {'lr': 0.0004965381350724874, 'samples': 1891200, 'steps': 9849, 'loss/train': 1.6132527589797974} 08/30/2021 14:55:32 - INFO - __main__ - Step 9851: {'lr': 0.000496537254942275, 'samples': 1891392, 'steps': 9850, 'loss/train': 1.6223324537277222} 08/30/2021 14:55:33 - INFO - __main__ - Step 9852: {'lr': 0.0004965363747009767, 'samples': 1891584, 'steps': 9851, 'loss/train': 0.2330079823732376} 08/30/2021 14:55:33 - INFO - __main__ - Step 9853: {'lr': 0.000496535494348593, 'samples': 1891776, 'steps': 9852, 'loss/train': 1.5762956142425537} 08/30/2021 14:55:35 - INFO - __main__ - Step 9854: {'lr': 0.0004965346138851241, 'samples': 1891968, 'steps': 9853, 'loss/train': 1.8432313203811646} 08/30/2021 14:55:36 - INFO - __main__ - Step 9855: {'lr': 0.0004965337333105706, 'samples': 1892160, 'steps': 9854, 'loss/train': 2.1151010990142822} 08/30/2021 14:55:36 - INFO - __main__ - Step 9856: {'lr': 0.0004965328526249328, 'samples': 1892352, 'steps': 9855, 'loss/train': 1.7464637756347656} 08/30/2021 14:55:36 - INFO - __main__ - Step 9857: {'lr': 0.000496531971828211, 'samples': 1892544, 'steps': 9856, 'loss/train': 1.6803183555603027} 08/30/2021 14:55:37 - INFO - __main__ - Step 9858: {'lr': 0.0004965310909204058, 'samples': 1892736, 'steps': 9857, 'loss/train': 1.2403587102890015} 08/30/2021 14:55:39 - INFO - __main__ - Step 9859: {'lr': 0.0004965302099015175, 'samples': 1892928, 'steps': 9858, 'loss/train': 2.3438684940338135} 08/30/2021 14:55:39 - INFO - __main__ - Step 9860: {'lr': 0.0004965293287715464, 'samples': 1893120, 'steps': 9859, 'loss/train': 1.7576836347579956} 08/30/2021 14:55:40 - INFO - __main__ - Step 9861: {'lr': 0.0004965284475304931, 'samples': 1893312, 'steps': 9860, 'loss/train': 1.1783772706985474} 08/30/2021 14:55:40 - INFO - __main__ - Step 9862: {'lr': 0.0004965275661783579, 'samples': 1893504, 'steps': 9861, 'loss/train': 0.9311202168464661} 08/30/2021 14:55:41 - INFO - __main__ - Step 9863: {'lr': 0.0004965266847151411, 'samples': 1893696, 'steps': 9862, 'loss/train': 1.0494866371154785} 08/30/2021 14:55:41 - INFO - __main__ - Step 9864: {'lr': 0.0004965258031408432, 'samples': 1893888, 'steps': 9863, 'loss/train': 0.23961587250232697} 08/30/2021 14:55:41 - INFO - __main__ - Step 9865: {'lr': 0.0004965249214554645, 'samples': 1894080, 'steps': 9864, 'loss/train': 1.5181031227111816} 08/30/2021 14:55:43 - INFO - __main__ - Step 9866: {'lr': 0.0004965240396590055, 'samples': 1894272, 'steps': 9865, 'loss/train': 2.282358407974243} 08/30/2021 14:55:43 - INFO - __main__ - Step 9867: {'lr': 0.0004965231577514666, 'samples': 1894464, 'steps': 9866, 'loss/train': 1.474616527557373} 08/30/2021 14:55:44 - INFO - __main__ - Step 9868: {'lr': 0.0004965222757328482, 'samples': 1894656, 'steps': 9867, 'loss/train': 1.6655150651931763} 08/30/2021 14:55:44 - INFO - __main__ - Step 9869: {'lr': 0.0004965213936031507, 'samples': 1894848, 'steps': 9868, 'loss/train': 1.9786831140518188} 08/30/2021 14:55:44 - INFO - __main__ - Step 9870: {'lr': 0.0004965205113623744, 'samples': 1895040, 'steps': 9869, 'loss/train': 1.7262904644012451} 08/30/2021 14:55:46 - INFO - __main__ - Step 9871: {'lr': 0.0004965196290105197, 'samples': 1895232, 'steps': 9870, 'loss/train': 2.089165210723877} 08/30/2021 14:55:46 - INFO - __main__ - Step 9872: {'lr': 0.0004965187465475873, 'samples': 1895424, 'steps': 9871, 'loss/train': 2.1268012523651123} 08/30/2021 14:55:47 - INFO - __main__ - Step 9873: {'lr': 0.0004965178639735772, 'samples': 1895616, 'steps': 9872, 'loss/train': 1.8712267875671387} 08/30/2021 14:55:47 - INFO - __main__ - Step 9874: {'lr': 0.0004965169812884898, 'samples': 1895808, 'steps': 9873, 'loss/train': 2.069993734359741} 08/30/2021 14:55:47 - INFO - __main__ - Step 9875: {'lr': 0.0004965160984923259, 'samples': 1896000, 'steps': 9874, 'loss/train': 1.7645589113235474} 08/30/2021 14:55:49 - INFO - __main__ - Step 9876: {'lr': 0.0004965152155850855, 'samples': 1896192, 'steps': 9875, 'loss/train': 1.3823093175888062} 08/30/2021 14:55:49 - INFO - __main__ - Step 9877: {'lr': 0.0004965143325667692, 'samples': 1896384, 'steps': 9876, 'loss/train': 2.205920696258545} 08/30/2021 14:55:50 - INFO - __main__ - Step 9878: {'lr': 0.0004965134494373773, 'samples': 1896576, 'steps': 9877, 'loss/train': 2.026207208633423} 08/30/2021 14:55:50 - INFO - __main__ - Step 9879: {'lr': 0.0004965125661969103, 'samples': 1896768, 'steps': 9878, 'loss/train': 2.5216455459594727} 08/30/2021 14:55:50 - INFO - __main__ - Step 9880: {'lr': 0.0004965116828453685, 'samples': 1896960, 'steps': 9879, 'loss/train': 1.4107859134674072} 08/30/2021 14:55:52 - INFO - __main__ - Step 9881: {'lr': 0.0004965107993827524, 'samples': 1897152, 'steps': 9880, 'loss/train': 0.6729925870895386} 08/30/2021 14:55:52 - INFO - __main__ - Step 9882: {'lr': 0.0004965099158090624, 'samples': 1897344, 'steps': 9881, 'loss/train': 2.0988662242889404} 08/30/2021 14:55:53 - INFO - __main__ - Step 9883: {'lr': 0.0004965090321242987, 'samples': 1897536, 'steps': 9882, 'loss/train': 2.131324052810669} 08/30/2021 14:55:53 - INFO - __main__ - Step 9884: {'lr': 0.0004965081483284618, 'samples': 1897728, 'steps': 9883, 'loss/train': 1.6686666011810303} 08/30/2021 14:55:53 - INFO - __main__ - Step 9885: {'lr': 0.0004965072644215522, 'samples': 1897920, 'steps': 9884, 'loss/train': 1.809524655342102} 08/30/2021 14:55:55 - INFO - __main__ - Step 9886: {'lr': 0.0004965063804035703, 'samples': 1898112, 'steps': 9885, 'loss/train': 1.9635182619094849} 08/30/2021 14:55:55 - INFO - __main__ - Step 9887: {'lr': 0.0004965054962745163, 'samples': 1898304, 'steps': 9886, 'loss/train': 2.151871681213379} 08/30/2021 14:55:56 - INFO - __main__ - Step 9888: {'lr': 0.0004965046120343908, 'samples': 1898496, 'steps': 9887, 'loss/train': 1.6386842727661133} 08/30/2021 14:55:56 - INFO - __main__ - Step 9889: {'lr': 0.0004965037276831942, 'samples': 1898688, 'steps': 9888, 'loss/train': 0.20835186541080475} 08/30/2021 14:55:56 - INFO - __main__ - Step 9890: {'lr': 0.0004965028432209267, 'samples': 1898880, 'steps': 9889, 'loss/train': 1.7828727960586548} 08/30/2021 14:55:58 - INFO - __main__ - Step 9891: {'lr': 0.0004965019586475888, 'samples': 1899072, 'steps': 9890, 'loss/train': 2.0863196849823} 08/30/2021 14:55:58 - INFO - __main__ - Step 9892: {'lr': 0.000496501073963181, 'samples': 1899264, 'steps': 9891, 'loss/train': 1.5739202499389648} 08/30/2021 14:55:59 - INFO - __main__ - Step 9893: {'lr': 0.0004965001891677037, 'samples': 1899456, 'steps': 9892, 'loss/train': 1.9914906024932861} 08/30/2021 14:55:59 - INFO - __main__ - Step 9894: {'lr': 0.000496499304261157, 'samples': 1899648, 'steps': 9893, 'loss/train': 1.992610216140747} 08/30/2021 14:56:00 - INFO - __main__ - Step 9895: {'lr': 0.0004964984192435417, 'samples': 1899840, 'steps': 9894, 'loss/train': 1.7929564714431763} 08/30/2021 14:56:00 - INFO - __main__ - Step 9896: {'lr': 0.000496497534114858, 'samples': 1900032, 'steps': 9895, 'loss/train': 1.3171859979629517} 08/30/2021 14:56:02 - INFO - __main__ - Step 9897: {'lr': 0.0004964966488751062, 'samples': 1900224, 'steps': 9896, 'loss/train': 1.057159423828125} 08/30/2021 14:56:02 - INFO - __main__ - Step 9898: {'lr': 0.000496495763524287, 'samples': 1900416, 'steps': 9897, 'loss/train': 2.5412673950195312} 08/30/2021 14:56:03 - INFO - __main__ - Step 9899: {'lr': 0.0004964948780624005, 'samples': 1900608, 'steps': 9898, 'loss/train': 1.423126220703125} 08/30/2021 14:56:03 - INFO - __main__ - Step 9900: {'lr': 0.0004964939924894472, 'samples': 1900800, 'steps': 9899, 'loss/train': 0.8339024186134338} 08/30/2021 14:56:03 - INFO - __main__ - Step 9901: {'lr': 0.0004964931068054274, 'samples': 1900992, 'steps': 9900, 'loss/train': 1.9488730430603027} 08/30/2021 14:56:04 - INFO - __main__ - Step 9902: {'lr': 0.0004964922210103418, 'samples': 1901184, 'steps': 9901, 'loss/train': 1.639295220375061} 08/30/2021 14:56:05 - INFO - __main__ - Step 9903: {'lr': 0.0004964913351041905, 'samples': 1901376, 'steps': 9902, 'loss/train': 1.8759537935256958} 08/30/2021 14:56:06 - INFO - __main__ - Step 9904: {'lr': 0.000496490449086974, 'samples': 1901568, 'steps': 9903, 'loss/train': 2.187781572341919} 08/30/2021 14:56:06 - INFO - __main__ - Step 9905: {'lr': 0.0004964895629586928, 'samples': 1901760, 'steps': 9904, 'loss/train': 1.7618857622146606} 08/30/2021 14:56:06 - INFO - __main__ - Step 9906: {'lr': 0.0004964886767193471, 'samples': 1901952, 'steps': 9905, 'loss/train': 0.11265911161899567} 08/30/2021 14:56:07 - INFO - __main__ - Step 9907: {'lr': 0.0004964877903689375, 'samples': 1902144, 'steps': 9906, 'loss/train': 1.943421483039856} 08/30/2021 14:56:09 - INFO - __main__ - Step 9908: {'lr': 0.0004964869039074643, 'samples': 1902336, 'steps': 9907, 'loss/train': 1.5840805768966675} 08/30/2021 14:56:09 - INFO - __main__ - Step 9909: {'lr': 0.000496486017334928, 'samples': 1902528, 'steps': 9908, 'loss/train': 1.8387268781661987} 08/30/2021 14:56:09 - INFO - __main__ - Step 9910: {'lr': 0.0004964851306513287, 'samples': 1902720, 'steps': 9909, 'loss/train': 2.056471824645996} 08/30/2021 14:56:10 - INFO - __main__ - Step 9911: {'lr': 0.0004964842438566671, 'samples': 1902912, 'steps': 9910, 'loss/train': 2.14296817779541} 08/30/2021 14:56:10 - INFO - __main__ - Step 9912: {'lr': 0.0004964833569509434, 'samples': 1903104, 'steps': 9911, 'loss/train': 0.1421142816543579} 08/30/2021 14:56:12 - INFO - __main__ - Step 9913: {'lr': 0.0004964824699341582, 'samples': 1903296, 'steps': 9912, 'loss/train': 1.7805852890014648} 08/30/2021 14:56:13 - INFO - __main__ - Step 9914: {'lr': 0.0004964815828063118, 'samples': 1903488, 'steps': 9913, 'loss/train': 1.9573044776916504} 08/30/2021 14:56:13 - INFO - __main__ - Step 9915: {'lr': 0.0004964806955674046, 'samples': 1903680, 'steps': 9914, 'loss/train': 1.6270732879638672} 08/30/2021 14:56:14 - INFO - __main__ - Step 9916: {'lr': 0.0004964798082174371, 'samples': 1903872, 'steps': 9915, 'loss/train': 1.7032448053359985} 08/30/2021 14:56:14 - INFO - __main__ - Step 9917: {'lr': 0.0004964789207564094, 'samples': 1904064, 'steps': 9916, 'loss/train': 6.233009338378906} 08/30/2021 14:56:16 - INFO - __main__ - Step 9918: {'lr': 0.0004964780331843223, 'samples': 1904256, 'steps': 9917, 'loss/train': 1.977447271347046} 08/30/2021 14:56:17 - INFO - __main__ - Step 9919: {'lr': 0.0004964771455011758, 'samples': 1904448, 'steps': 9918, 'loss/train': 1.8892210721969604} 08/30/2021 14:56:17 - INFO - __main__ - Step 9920: {'lr': 0.0004964762577069707, 'samples': 1904640, 'steps': 9919, 'loss/train': 0.3782086670398712} 08/30/2021 14:56:17 - INFO - __main__ - Step 9921: {'lr': 0.0004964753698017071, 'samples': 1904832, 'steps': 9920, 'loss/train': 1.2212785482406616} 08/30/2021 14:56:18 - INFO - __main__ - Step 9922: {'lr': 0.0004964744817853855, 'samples': 1905024, 'steps': 9921, 'loss/train': 1.2019864320755005} 08/30/2021 14:56:18 - INFO - __main__ - Step 9923: {'lr': 0.0004964735936580063, 'samples': 1905216, 'steps': 9922, 'loss/train': 1.9790148735046387} 08/30/2021 14:56:20 - INFO - __main__ - Step 9924: {'lr': 0.00049647270541957, 'samples': 1905408, 'steps': 9923, 'loss/train': 0.15961384773254395} 08/30/2021 14:56:20 - INFO - __main__ - Step 9925: {'lr': 0.0004964718170700767, 'samples': 1905600, 'steps': 9924, 'loss/train': 1.9123448133468628} 08/30/2021 14:56:20 - INFO - __main__ - Step 9926: {'lr': 0.0004964709286095271, 'samples': 1905792, 'steps': 9925, 'loss/train': 1.9273356199264526} 08/30/2021 14:56:21 - INFO - __main__ - Step 9927: {'lr': 0.0004964700400379215, 'samples': 1905984, 'steps': 9926, 'loss/train': 1.5638554096221924} 08/30/2021 14:56:21 - INFO - __main__ - Step 9928: {'lr': 0.0004964691513552604, 'samples': 1906176, 'steps': 9927, 'loss/train': 2.2048823833465576} 08/30/2021 14:56:23 - INFO - __main__ - Step 9929: {'lr': 0.000496468262561544, 'samples': 1906368, 'steps': 9928, 'loss/train': 1.6114774942398071} 08/30/2021 14:56:23 - INFO - __main__ - Step 9930: {'lr': 0.0004964673736567728, 'samples': 1906560, 'steps': 9929, 'loss/train': 2.6401917934417725} 08/30/2021 14:56:23 - INFO - __main__ - Step 9931: {'lr': 0.0004964664846409473, 'samples': 1906752, 'steps': 9930, 'loss/train': 1.914066195487976} 08/30/2021 14:56:24 - INFO - __main__ - Step 9932: {'lr': 0.0004964655955140677, 'samples': 1906944, 'steps': 9931, 'loss/train': 1.8376495838165283} 08/30/2021 14:56:24 - INFO - __main__ - Step 9933: {'lr': 0.0004964647062761345, 'samples': 1907136, 'steps': 9932, 'loss/train': 1.5977219343185425} 08/30/2021 14:56:26 - INFO - __main__ - Step 9934: {'lr': 0.0004964638169271482, 'samples': 1907328, 'steps': 9933, 'loss/train': 2.038529396057129} 08/30/2021 14:56:26 - INFO - __main__ - Step 9935: {'lr': 0.0004964629274671091, 'samples': 1907520, 'steps': 9934, 'loss/train': 1.771410346031189} 08/30/2021 14:56:26 - INFO - __main__ - Step 9936: {'lr': 0.0004964620378960175, 'samples': 1907712, 'steps': 9935, 'loss/train': 1.7764892578125} 08/30/2021 14:56:27 - INFO - __main__ - Step 9937: {'lr': 0.000496461148213874, 'samples': 1907904, 'steps': 9936, 'loss/train': 1.1905723810195923} 08/30/2021 14:56:27 - INFO - __main__ - Step 9938: {'lr': 0.0004964602584206788, 'samples': 1908096, 'steps': 9937, 'loss/train': 1.829355001449585} 08/30/2021 14:56:29 - INFO - __main__ - Step 9939: {'lr': 0.0004964593685164326, 'samples': 1908288, 'steps': 9938, 'loss/train': 2.1132514476776123} 08/30/2021 14:56:29 - INFO - __main__ - Step 9940: {'lr': 0.0004964584785011355, 'samples': 1908480, 'steps': 9939, 'loss/train': 2.7216434478759766} 08/30/2021 14:56:29 - INFO - __main__ - Step 9941: {'lr': 0.000496457588374788, 'samples': 1908672, 'steps': 9940, 'loss/train': 1.8941521644592285} 08/30/2021 14:56:30 - INFO - __main__ - Step 9942: {'lr': 0.0004964566981373905, 'samples': 1908864, 'steps': 9941, 'loss/train': 1.9584522247314453} 08/30/2021 14:56:30 - INFO - __main__ - Step 9943: {'lr': 0.0004964558077889435, 'samples': 1909056, 'steps': 9942, 'loss/train': 2.0020854473114014} 08/30/2021 14:56:32 - INFO - __main__ - Step 9944: {'lr': 0.0004964549173294472, 'samples': 1909248, 'steps': 9943, 'loss/train': 1.4657632112503052} 08/30/2021 14:56:32 - INFO - __main__ - Step 9945: {'lr': 0.0004964540267589023, 'samples': 1909440, 'steps': 9944, 'loss/train': 1.6888188123703003} 08/30/2021 14:56:32 - INFO - __main__ - Step 9946: {'lr': 0.0004964531360773088, 'samples': 1909632, 'steps': 9945, 'loss/train': 1.991836667060852} 08/30/2021 14:56:33 - INFO - __main__ - Step 9947: {'lr': 0.0004964522452846675, 'samples': 1909824, 'steps': 9946, 'loss/train': 1.441489577293396} 08/30/2021 14:56:33 - INFO - __main__ - Step 9948: {'lr': 0.0004964513543809785, 'samples': 1910016, 'steps': 9947, 'loss/train': 1.6609220504760742} 08/30/2021 14:56:35 - INFO - __main__ - Step 9949: {'lr': 0.0004964504633662424, 'samples': 1910208, 'steps': 9948, 'loss/train': 2.0449202060699463} 08/30/2021 14:56:35 - INFO - __main__ - Step 9950: {'lr': 0.0004964495722404595, 'samples': 1910400, 'steps': 9949, 'loss/train': 1.8106787204742432} 08/30/2021 14:56:36 - INFO - __main__ - Step 9951: {'lr': 0.0004964486810036301, 'samples': 1910592, 'steps': 9950, 'loss/train': 1.1692430973052979} 08/30/2021 14:56:36 - INFO - __main__ - Step 9952: {'lr': 0.000496447789655755, 'samples': 1910784, 'steps': 9951, 'loss/train': 0.809981644153595} 08/30/2021 14:56:36 - INFO - __main__ - Step 9953: {'lr': 0.0004964468981968341, 'samples': 1910976, 'steps': 9952, 'loss/train': 1.773395299911499} 08/30/2021 14:56:38 - INFO - __main__ - Step 9954: {'lr': 0.0004964460066268681, 'samples': 1911168, 'steps': 9953, 'loss/train': 1.162157416343689} 08/30/2021 14:56:38 - INFO - __main__ - Step 9955: {'lr': 0.0004964451149458573, 'samples': 1911360, 'steps': 9954, 'loss/train': 1.6730577945709229} 08/30/2021 14:56:39 - INFO - __main__ - Step 9956: {'lr': 0.0004964442231538023, 'samples': 1911552, 'steps': 9955, 'loss/train': 1.6550753116607666} 08/30/2021 14:56:39 - INFO - __main__ - Step 9957: {'lr': 0.000496443331250703, 'samples': 1911744, 'steps': 9956, 'loss/train': 1.7674018144607544} 08/30/2021 14:56:39 - INFO - __main__ - Step 9958: {'lr': 0.0004964424392365604, 'samples': 1911936, 'steps': 9957, 'loss/train': 1.8954929113388062} 08/30/2021 14:56:40 - INFO - __main__ - Step 9959: {'lr': 0.0004964415471113747, 'samples': 1912128, 'steps': 9958, 'loss/train': 1.3786265850067139} 08/30/2021 14:56:41 - INFO - __main__ - Step 9960: {'lr': 0.0004964406548751461, 'samples': 1912320, 'steps': 9959, 'loss/train': 2.2502574920654297} 08/30/2021 14:56:42 - INFO - __main__ - Step 9961: {'lr': 0.0004964397625278751, 'samples': 1912512, 'steps': 9960, 'loss/train': 1.9674396514892578} 08/30/2021 14:56:42 - INFO - __main__ - Step 9962: {'lr': 0.0004964388700695623, 'samples': 1912704, 'steps': 9961, 'loss/train': 1.7398422956466675} 08/30/2021 14:56:42 - INFO - __main__ - Step 9963: {'lr': 0.0004964379775002078, 'samples': 1912896, 'steps': 9962, 'loss/train': 1.7798408269882202} 08/30/2021 14:56:43 - INFO - __main__ - Step 9964: {'lr': 0.0004964370848198122, 'samples': 1913088, 'steps': 9963, 'loss/train': 1.5920237302780151} 08/30/2021 14:56:45 - INFO - __main__ - Step 9965: {'lr': 0.0004964361920283759, 'samples': 1913280, 'steps': 9964, 'loss/train': 1.7673590183258057} 08/30/2021 14:56:45 - INFO - __main__ - Step 9966: {'lr': 0.0004964352991258992, 'samples': 1913472, 'steps': 9965, 'loss/train': 1.5249208211898804} 08/30/2021 14:56:45 - INFO - __main__ - Step 9967: {'lr': 0.0004964344061123826, 'samples': 1913664, 'steps': 9966, 'loss/train': 1.9139293432235718} 08/30/2021 14:56:46 - INFO - __main__ - Step 9968: {'lr': 0.0004964335129878264, 'samples': 1913856, 'steps': 9967, 'loss/train': 1.420186161994934} 08/30/2021 14:56:46 - INFO - __main__ - Step 9969: {'lr': 0.0004964326197522311, 'samples': 1914048, 'steps': 9968, 'loss/train': 1.9627630710601807} 08/30/2021 14:56:48 - INFO - __main__ - Step 9970: {'lr': 0.0004964317264055971, 'samples': 1914240, 'steps': 9969, 'loss/train': 1.156221866607666} 08/30/2021 14:56:48 - INFO - __main__ - Step 9971: {'lr': 0.0004964308329479247, 'samples': 1914432, 'steps': 9970, 'loss/train': 1.1966806650161743} 08/30/2021 14:56:48 - INFO - __main__ - Step 9972: {'lr': 0.0004964299393792143, 'samples': 1914624, 'steps': 9971, 'loss/train': 1.853172779083252} 08/30/2021 14:56:49 - INFO - __main__ - Step 9973: {'lr': 0.0004964290456994666, 'samples': 1914816, 'steps': 9972, 'loss/train': 1.675586462020874} 08/30/2021 14:56:49 - INFO - __main__ - Step 9974: {'lr': 0.0004964281519086816, 'samples': 1915008, 'steps': 9973, 'loss/train': 2.259634256362915} 08/30/2021 14:56:51 - INFO - __main__ - Step 9975: {'lr': 0.0004964272580068599, 'samples': 1915200, 'steps': 9974, 'loss/train': 1.6877899169921875} 08/30/2021 14:56:51 - INFO - __main__ - Step 9976: {'lr': 0.0004964263639940018, 'samples': 1915392, 'steps': 9975, 'loss/train': 1.482268214225769} 08/30/2021 14:56:51 - INFO - __main__ - Step 9977: {'lr': 0.000496425469870108, 'samples': 1915584, 'steps': 9976, 'loss/train': 1.7324260473251343} 08/30/2021 14:56:52 - INFO - __main__ - Step 9978: {'lr': 0.0004964245756351786, 'samples': 1915776, 'steps': 9977, 'loss/train': 1.5633198022842407} 08/30/2021 14:56:52 - INFO - __main__ - Step 9979: {'lr': 0.000496423681289214, 'samples': 1915968, 'steps': 9978, 'loss/train': 1.7842503786087036} 08/30/2021 14:56:53 - INFO - __main__ - Step 9980: {'lr': 0.0004964227868322148, 'samples': 1916160, 'steps': 9979, 'loss/train': 1.7017784118652344} 08/30/2021 14:56:54 - INFO - __main__ - Step 9981: {'lr': 0.0004964218922641812, 'samples': 1916352, 'steps': 9980, 'loss/train': 1.4904532432556152} 08/30/2021 14:56:54 - INFO - __main__ - Step 9982: {'lr': 0.0004964209975851137, 'samples': 1916544, 'steps': 9981, 'loss/train': 1.8057057857513428} 08/30/2021 14:56:55 - INFO - __main__ - Step 9983: {'lr': 0.0004964201027950129, 'samples': 1916736, 'steps': 9982, 'loss/train': 1.4644185304641724} 08/30/2021 14:56:55 - INFO - __main__ - Step 9984: {'lr': 0.0004964192078938788, 'samples': 1916928, 'steps': 9983, 'loss/train': 1.6545456647872925} 08/30/2021 14:56:57 - INFO - __main__ - Step 9985: {'lr': 0.0004964183128817121, 'samples': 1917120, 'steps': 9984, 'loss/train': 1.7370964288711548} 08/30/2021 14:56:57 - INFO - __main__ - Step 9986: {'lr': 0.000496417417758513, 'samples': 1917312, 'steps': 9985, 'loss/train': 2.379159927368164} 08/30/2021 14:56:57 - INFO - __main__ - Step 9987: {'lr': 0.000496416522524282, 'samples': 1917504, 'steps': 9986, 'loss/train': 1.9058454036712646} 08/30/2021 14:56:58 - INFO - __main__ - Step 9988: {'lr': 0.0004964156271790197, 'samples': 1917696, 'steps': 9987, 'loss/train': 1.170692801475525} 08/30/2021 14:56:58 - INFO - __main__ - Step 9989: {'lr': 0.0004964147317227262, 'samples': 1917888, 'steps': 9988, 'loss/train': 1.8171964883804321} 08/30/2021 14:56:59 - INFO - __main__ - Step 9990: {'lr': 0.000496413836155402, 'samples': 1918080, 'steps': 9989, 'loss/train': 1.9222526550292969} 08/30/2021 14:57:00 - INFO - __main__ - Step 9991: {'lr': 0.0004964129404770476, 'samples': 1918272, 'steps': 9990, 'loss/train': 1.1143251657485962} 08/30/2021 14:57:00 - INFO - __main__ - Step 9992: {'lr': 0.0004964120446876633, 'samples': 1918464, 'steps': 9991, 'loss/train': 1.8447924852371216} 08/30/2021 14:57:01 - INFO - __main__ - Step 9993: {'lr': 0.0004964111487872495, 'samples': 1918656, 'steps': 9992, 'loss/train': 2.0372166633605957} 08/30/2021 14:57:01 - INFO - __main__ - Step 9994: {'lr': 0.0004964102527758067, 'samples': 1918848, 'steps': 9993, 'loss/train': 1.631529688835144} 08/30/2021 14:57:01 - INFO - __main__ - Step 9995: {'lr': 0.0004964093566533352, 'samples': 1919040, 'steps': 9994, 'loss/train': 1.91537344455719} 08/30/2021 14:57:03 - INFO - __main__ - Step 9996: {'lr': 0.0004964084604198354, 'samples': 1919232, 'steps': 9995, 'loss/train': 1.7254267930984497} 08/30/2021 14:57:03 - INFO - __main__ - Step 9997: {'lr': 0.0004964075640753079, 'samples': 1919424, 'steps': 9996, 'loss/train': 1.6130692958831787} 08/30/2021 14:57:04 - INFO - __main__ - Step 9998: {'lr': 0.0004964066676197528, 'samples': 1919616, 'steps': 9997, 'loss/train': 1.1783849000930786} 08/30/2021 14:57:04 - INFO - __main__ - Step 9999: {'lr': 0.0004964057710531707, 'samples': 1919808, 'steps': 9998, 'loss/train': 1.6470781564712524} 08/30/2021 14:57:04 - INFO - __main__ - Step 10000: {'lr': 0.0004964048743755621, 'samples': 1920000, 'steps': 9999, 'loss/train': 1.5546714067459106} 08/30/2021 14:57:06 - INFO - __main__ - Step 10001: {'lr': 0.0004964039775869272, 'samples': 1920192, 'steps': 10000, 'loss/train': 1.6607551574707031} 08/30/2021 14:57:06 - INFO - __main__ - Step 10002: {'lr': 0.0004964030806872664, 'samples': 1920384, 'steps': 10001, 'loss/train': 2.0873374938964844} 08/30/2021 14:57:07 - INFO - __main__ - Step 10003: {'lr': 0.0004964021836765802, 'samples': 1920576, 'steps': 10002, 'loss/train': 2.0015244483947754} 08/30/2021 14:57:07 - INFO - __main__ - Step 10004: {'lr': 0.000496401286554869, 'samples': 1920768, 'steps': 10003, 'loss/train': 1.5208274126052856} 08/30/2021 14:57:07 - INFO - __main__ - Step 10005: {'lr': 0.000496400389322133, 'samples': 1920960, 'steps': 10004, 'loss/train': 2.051011562347412} 08/30/2021 14:57:09 - INFO - __main__ - Step 10006: {'lr': 0.000496399491978373, 'samples': 1921152, 'steps': 10005, 'loss/train': 2.166624069213867} 08/30/2021 14:57:10 - INFO - __main__ - Step 10007: {'lr': 0.0004963985945235891, 'samples': 1921344, 'steps': 10006, 'loss/train': 4.9143900871276855} 08/30/2021 14:57:10 - INFO - __main__ - Step 10008: {'lr': 0.0004963976969577819, 'samples': 1921536, 'steps': 10007, 'loss/train': 2.3767783641815186} 08/30/2021 14:57:10 - INFO - __main__ - Step 10009: {'lr': 0.0004963967992809516, 'samples': 1921728, 'steps': 10008, 'loss/train': 0.2657642662525177} 08/30/2021 14:57:11 - INFO - __main__ - Step 10010: {'lr': 0.0004963959014930988, 'samples': 1921920, 'steps': 10009, 'loss/train': 2.181117534637451} 08/30/2021 14:57:12 - INFO - __main__ - Step 10011: {'lr': 0.0004963950035942237, 'samples': 1922112, 'steps': 10010, 'loss/train': 2.0658130645751953} 08/30/2021 14:57:13 - INFO - __main__ - Step 10012: {'lr': 0.0004963941055843268, 'samples': 1922304, 'steps': 10011, 'loss/train': 1.91506028175354} 08/30/2021 14:57:13 - INFO - __main__ - Step 10013: {'lr': 0.0004963932074634087, 'samples': 1922496, 'steps': 10012, 'loss/train': 1.8211382627487183} 08/30/2021 14:57:13 - INFO - __main__ - Step 10014: {'lr': 0.0004963923092314694, 'samples': 1922688, 'steps': 10013, 'loss/train': 1.928120493888855} 08/30/2021 14:57:14 - INFO - __main__ - Step 10015: {'lr': 0.0004963914108885097, 'samples': 1922880, 'steps': 10014, 'loss/train': 1.6316910982131958} 08/30/2021 14:57:15 - INFO - __main__ - Step 10016: {'lr': 0.0004963905124345297, 'samples': 1923072, 'steps': 10015, 'loss/train': 1.9263784885406494} 08/30/2021 14:57:16 - INFO - __main__ - Step 10017: {'lr': 0.00049638961386953, 'samples': 1923264, 'steps': 10016, 'loss/train': 1.7138534784317017} 08/30/2021 14:57:16 - INFO - __main__ - Step 10018: {'lr': 0.000496388715193511, 'samples': 1923456, 'steps': 10017, 'loss/train': 1.8585059642791748} 08/30/2021 14:57:16 - INFO - __main__ - Step 10019: {'lr': 0.000496387816406473, 'samples': 1923648, 'steps': 10018, 'loss/train': 2.00970458984375} 08/30/2021 14:57:17 - INFO - __main__ - Step 10020: {'lr': 0.0004963869175084164, 'samples': 1923840, 'steps': 10019, 'loss/train': 1.9403449296951294} 08/30/2021 14:57:17 - INFO - __main__ - Step 10021: {'lr': 0.0004963860184993416, 'samples': 1924032, 'steps': 10020, 'loss/train': 1.5665193796157837} 08/30/2021 14:57:19 - INFO - __main__ - Step 10022: {'lr': 0.0004963851193792492, 'samples': 1924224, 'steps': 10021, 'loss/train': 1.9872945547103882} 08/30/2021 14:57:20 - INFO - __main__ - Step 10023: {'lr': 0.0004963842201481394, 'samples': 1924416, 'steps': 10022, 'loss/train': 2.0834667682647705} 08/30/2021 14:57:20 - INFO - __main__ - Step 10024: {'lr': 0.0004963833208060128, 'samples': 1924608, 'steps': 10023, 'loss/train': 2.122685432434082} 08/30/2021 14:57:20 - INFO - __main__ - Step 10025: {'lr': 0.0004963824213528696, 'samples': 1924800, 'steps': 10024, 'loss/train': 2.247332811355591} 08/30/2021 14:57:21 - INFO - __main__ - Step 10026: {'lr': 0.0004963815217887102, 'samples': 1924992, 'steps': 10025, 'loss/train': 1.3828188180923462} 08/30/2021 14:57:22 - INFO - __main__ - Step 10027: {'lr': 0.0004963806221135351, 'samples': 1925184, 'steps': 10026, 'loss/train': 3.7562947273254395} 08/30/2021 14:57:23 - INFO - __main__ - Step 10028: {'lr': 0.0004963797223273448, 'samples': 1925376, 'steps': 10027, 'loss/train': 1.1838608980178833} 08/30/2021 14:57:23 - INFO - __main__ - Step 10029: {'lr': 0.0004963788224301395, 'samples': 1925568, 'steps': 10028, 'loss/train': 1.8303600549697876} 08/30/2021 14:57:23 - INFO - __main__ - Step 10030: {'lr': 0.0004963779224219197, 'samples': 1925760, 'steps': 10029, 'loss/train': 1.9881763458251953} 08/30/2021 14:57:24 - INFO - __main__ - Step 10031: {'lr': 0.0004963770223026858, 'samples': 1925952, 'steps': 10030, 'loss/train': 1.942649006843567} 08/30/2021 14:57:25 - INFO - __main__ - Step 10032: {'lr': 0.0004963761220724384, 'samples': 1926144, 'steps': 10031, 'loss/train': 1.647000789642334} 08/30/2021 14:57:25 - INFO - __main__ - Step 10033: {'lr': 0.0004963752217311775, 'samples': 1926336, 'steps': 10032, 'loss/train': 1.5193215608596802} 08/30/2021 14:57:26 - INFO - __main__ - Step 10034: {'lr': 0.0004963743212789038, 'samples': 1926528, 'steps': 10033, 'loss/train': 2.008763551712036} 08/30/2021 14:57:26 - INFO - __main__ - Step 10035: {'lr': 0.0004963734207156178, 'samples': 1926720, 'steps': 10034, 'loss/train': 1.6514290571212769} 08/30/2021 14:57:26 - INFO - __main__ - Step 10036: {'lr': 0.0004963725200413195, 'samples': 1926912, 'steps': 10035, 'loss/train': 1.63376784324646} 08/30/2021 14:57:28 - INFO - __main__ - Step 10037: {'lr': 0.0004963716192560097, 'samples': 1927104, 'steps': 10036, 'loss/train': 1.6030821800231934} 08/30/2021 14:57:28 - INFO - __main__ - Step 10038: {'lr': 0.0004963707183596885, 'samples': 1927296, 'steps': 10037, 'loss/train': 1.554940938949585} 08/30/2021 14:57:29 - INFO - __main__ - Step 10039: {'lr': 0.0004963698173523566, 'samples': 1927488, 'steps': 10038, 'loss/train': 2.125246047973633} 08/30/2021 14:57:29 - INFO - __main__ - Step 10040: {'lr': 0.0004963689162340142, 'samples': 1927680, 'steps': 10039, 'loss/train': 1.491138219833374} 08/30/2021 14:57:30 - INFO - __main__ - Step 10041: {'lr': 0.0004963680150046618, 'samples': 1927872, 'steps': 10040, 'loss/train': 1.8210960626602173} 08/30/2021 14:57:31 - INFO - __main__ - Step 10042: {'lr': 0.0004963671136642997, 'samples': 1928064, 'steps': 10041, 'loss/train': 1.8418312072753906} 08/30/2021 14:57:32 - INFO - __main__ - Step 10043: {'lr': 0.0004963662122129284, 'samples': 1928256, 'steps': 10042, 'loss/train': 0.6766268610954285} 08/30/2021 14:57:32 - INFO - __main__ - Step 10044: {'lr': 0.0004963653106505483, 'samples': 1928448, 'steps': 10043, 'loss/train': 1.8348647356033325} 08/30/2021 14:57:32 - INFO - __main__ - Step 10045: {'lr': 0.0004963644089771598, 'samples': 1928640, 'steps': 10044, 'loss/train': 2.135529041290283} 08/30/2021 14:57:33 - INFO - __main__ - Step 10046: {'lr': 0.0004963635071927633, 'samples': 1928832, 'steps': 10045, 'loss/train': 1.9546533823013306} 08/30/2021 14:57:34 - INFO - __main__ - Step 10047: {'lr': 0.0004963626052973592, 'samples': 1929024, 'steps': 10046, 'loss/train': 1.526484489440918} 08/30/2021 14:57:35 - INFO - __main__ - Step 10048: {'lr': 0.0004963617032909479, 'samples': 1929216, 'steps': 10047, 'loss/train': 1.817151427268982} 08/30/2021 14:57:35 - INFO - __main__ - Step 10049: {'lr': 0.0004963608011735298, 'samples': 1929408, 'steps': 10048, 'loss/train': 1.9247368574142456} 08/30/2021 14:57:35 - INFO - __main__ - Step 10050: {'lr': 0.0004963598989451053, 'samples': 1929600, 'steps': 10049, 'loss/train': 1.6581131219863892} 08/30/2021 14:57:36 - INFO - __main__ - Step 10051: {'lr': 0.000496358996605675, 'samples': 1929792, 'steps': 10050, 'loss/train': 1.4466031789779663} 08/30/2021 14:57:37 - INFO - __main__ - Step 10052: {'lr': 0.0004963580941552391, 'samples': 1929984, 'steps': 10051, 'loss/train': 1.6546374559402466} 08/30/2021 14:57:38 - INFO - __main__ - Step 10053: {'lr': 0.0004963571915937979, 'samples': 1930176, 'steps': 10052, 'loss/train': 2.0494463443756104} 08/30/2021 14:57:38 - INFO - __main__ - Step 10054: {'lr': 0.000496356288921352, 'samples': 1930368, 'steps': 10053, 'loss/train': 1.6917833089828491} 08/30/2021 14:57:38 - INFO - __main__ - Step 10055: {'lr': 0.0004963553861379018, 'samples': 1930560, 'steps': 10054, 'loss/train': 1.950510859489441} 08/30/2021 14:57:39 - INFO - __main__ - Step 10056: {'lr': 0.0004963544832434476, 'samples': 1930752, 'steps': 10055, 'loss/train': 1.8846999406814575} 08/30/2021 14:57:40 - INFO - __main__ - Step 10057: {'lr': 0.00049635358023799, 'samples': 1930944, 'steps': 10056, 'loss/train': 1.5036273002624512} 08/30/2021 14:57:41 - INFO - __main__ - Step 10058: {'lr': 0.0004963526771215291, 'samples': 1931136, 'steps': 10057, 'loss/train': 1.988438606262207} 08/30/2021 14:57:41 - INFO - __main__ - Step 10059: {'lr': 0.0004963517738940656, 'samples': 1931328, 'steps': 10058, 'loss/train': 2.1263527870178223} 08/30/2021 14:57:41 - INFO - __main__ - Step 10060: {'lr': 0.0004963508705555998, 'samples': 1931520, 'steps': 10059, 'loss/train': 2.0561323165893555} 08/30/2021 14:57:42 - INFO - __main__ - Step 10061: {'lr': 0.000496349967106132, 'samples': 1931712, 'steps': 10060, 'loss/train': 1.9084632396697998} 08/30/2021 14:57:43 - INFO - __main__ - Step 10062: {'lr': 0.0004963490635456629, 'samples': 1931904, 'steps': 10061, 'loss/train': 2.1884217262268066} 08/30/2021 14:57:44 - INFO - __main__ - Step 10063: {'lr': 0.0004963481598741925, 'samples': 1932096, 'steps': 10062, 'loss/train': 1.8260231018066406} 08/30/2021 14:57:44 - INFO - __main__ - Step 10064: {'lr': 0.0004963472560917216, 'samples': 1932288, 'steps': 10063, 'loss/train': 2.044750213623047} 08/30/2021 14:57:44 - INFO - __main__ - Step 10065: {'lr': 0.0004963463521982503, 'samples': 1932480, 'steps': 10064, 'loss/train': 1.5723226070404053} 08/30/2021 14:57:45 - INFO - __main__ - Step 10066: {'lr': 0.0004963454481937791, 'samples': 1932672, 'steps': 10065, 'loss/train': 2.119046688079834} 08/30/2021 14:57:46 - INFO - __main__ - Step 10067: {'lr': 0.0004963445440783086, 'samples': 1932864, 'steps': 10066, 'loss/train': 1.9843782186508179} 08/30/2021 14:57:47 - INFO - __main__ - Step 10068: {'lr': 0.0004963436398518389, 'samples': 1933056, 'steps': 10067, 'loss/train': 1.5568156242370605} 08/30/2021 14:57:47 - INFO - __main__ - Step 10069: {'lr': 0.0004963427355143706, 'samples': 1933248, 'steps': 10068, 'loss/train': 1.9988080263137817} 08/30/2021 14:57:47 - INFO - __main__ - Step 10070: {'lr': 0.0004963418310659041, 'samples': 1933440, 'steps': 10069, 'loss/train': 1.257478952407837} 08/30/2021 14:57:48 - INFO - __main__ - Step 10071: {'lr': 0.0004963409265064398, 'samples': 1933632, 'steps': 10070, 'loss/train': 0.793785810470581} 08/30/2021 14:57:48 - INFO - __main__ - Step 10072: {'lr': 0.0004963400218359781, 'samples': 1933824, 'steps': 10071, 'loss/train': 1.8985668420791626} 08/30/2021 14:57:50 - INFO - __main__ - Step 10073: {'lr': 0.0004963391170545193, 'samples': 1934016, 'steps': 10072, 'loss/train': 0.1252242475748062} 08/30/2021 14:57:50 - INFO - __main__ - Step 10074: {'lr': 0.0004963382121620639, 'samples': 1934208, 'steps': 10073, 'loss/train': 2.0857741832733154} 08/30/2021 14:57:50 - INFO - __main__ - Step 10075: {'lr': 0.0004963373071586123, 'samples': 1934400, 'steps': 10074, 'loss/train': 2.034210443496704} 08/30/2021 14:57:51 - INFO - __main__ - Step 10076: {'lr': 0.000496336402044165, 'samples': 1934592, 'steps': 10075, 'loss/train': 1.6108455657958984} 08/30/2021 14:57:51 - INFO - __main__ - Step 10077: {'lr': 0.0004963354968187222, 'samples': 1934784, 'steps': 10076, 'loss/train': 2.5568816661834717} 08/30/2021 14:57:53 - INFO - __main__ - Step 10078: {'lr': 0.0004963345914822845, 'samples': 1934976, 'steps': 10077, 'loss/train': 1.9205923080444336} 08/30/2021 14:57:54 - INFO - __main__ - Step 10079: {'lr': 0.0004963336860348521, 'samples': 1935168, 'steps': 10078, 'loss/train': 1.9299153089523315} 08/30/2021 14:57:54 - INFO - __main__ - Step 10080: {'lr': 0.0004963327804764257, 'samples': 1935360, 'steps': 10079, 'loss/train': 1.9766066074371338} 08/30/2021 14:57:54 - INFO - __main__ - Step 10081: {'lr': 0.0004963318748070056, 'samples': 1935552, 'steps': 10080, 'loss/train': 1.97420334815979} 08/30/2021 14:57:55 - INFO - __main__ - Step 10082: {'lr': 0.0004963309690265921, 'samples': 1935744, 'steps': 10081, 'loss/train': 1.6910001039505005} 08/30/2021 14:57:56 - INFO - __main__ - Step 10083: {'lr': 0.0004963300631351856, 'samples': 1935936, 'steps': 10082, 'loss/train': 1.0413610935211182} 08/30/2021 14:57:57 - INFO - __main__ - Step 10084: {'lr': 0.0004963291571327866, 'samples': 1936128, 'steps': 10083, 'loss/train': 1.5702033042907715} 08/30/2021 14:57:57 - INFO - __main__ - Step 10085: {'lr': 0.0004963282510193955, 'samples': 1936320, 'steps': 10084, 'loss/train': 1.4221917390823364} 08/30/2021 14:57:57 - INFO - __main__ - Step 10086: {'lr': 0.0004963273447950126, 'samples': 1936512, 'steps': 10085, 'loss/train': 1.863145112991333} 08/30/2021 14:57:58 - INFO - __main__ - Step 10087: {'lr': 0.0004963264384596386, 'samples': 1936704, 'steps': 10086, 'loss/train': 2.041637659072876} 08/30/2021 14:57:59 - INFO - __main__ - Step 10088: {'lr': 0.0004963255320132735, 'samples': 1936896, 'steps': 10087, 'loss/train': 1.5413753986358643} 08/30/2021 14:58:00 - INFO - __main__ - Step 10089: {'lr': 0.0004963246254559181, 'samples': 1937088, 'steps': 10088, 'loss/train': 1.2902778387069702} 08/30/2021 14:58:00 - INFO - __main__ - Step 10090: {'lr': 0.0004963237187875724, 'samples': 1937280, 'steps': 10089, 'loss/train': 1.2422256469726562} 08/30/2021 14:58:00 - INFO - __main__ - Step 10091: {'lr': 0.0004963228120082372, 'samples': 1937472, 'steps': 10090, 'loss/train': 2.091702461242676} 08/30/2021 14:58:01 - INFO - __main__ - Step 10092: {'lr': 0.0004963219051179127, 'samples': 1937664, 'steps': 10091, 'loss/train': 2.056105852127075} 08/30/2021 14:58:02 - INFO - __main__ - Step 10093: {'lr': 0.0004963209981165993, 'samples': 1937856, 'steps': 10092, 'loss/train': 1.5542057752609253} 08/30/2021 14:58:03 - INFO - __main__ - Step 10094: {'lr': 0.0004963200910042976, 'samples': 1938048, 'steps': 10093, 'loss/train': 1.575708270072937} 08/30/2021 14:58:03 - INFO - __main__ - Step 10095: {'lr': 0.0004963191837810077, 'samples': 1938240, 'steps': 10094, 'loss/train': 2.1271841526031494} 08/30/2021 14:58:03 - INFO - __main__ - Step 10096: {'lr': 0.0004963182764467303, 'samples': 1938432, 'steps': 10095, 'loss/train': 0.9086203575134277} 08/30/2021 14:58:04 - INFO - __main__ - Step 10097: {'lr': 0.0004963173690014656, 'samples': 1938624, 'steps': 10096, 'loss/train': 1.4094364643096924} 08/30/2021 14:58:05 - INFO - __main__ - Step 10098: {'lr': 0.0004963164614452142, 'samples': 1938816, 'steps': 10097, 'loss/train': 2.0525710582733154} 08/30/2021 14:58:06 - INFO - __main__ - Step 10099: {'lr': 0.0004963155537779764, 'samples': 1939008, 'steps': 10098, 'loss/train': 2.0697312355041504} 08/30/2021 14:58:06 - INFO - __main__ - Step 10100: {'lr': 0.0004963146459997525, 'samples': 1939200, 'steps': 10099, 'loss/train': 1.7506622076034546} 08/30/2021 14:58:07 - INFO - __main__ - Step 10101: {'lr': 0.0004963137381105431, 'samples': 1939392, 'steps': 10100, 'loss/train': 1.7772756814956665} 08/30/2021 14:58:07 - INFO - __main__ - Step 10102: {'lr': 0.0004963128301103485, 'samples': 1939584, 'steps': 10101, 'loss/train': 1.4139899015426636} 08/30/2021 14:58:07 - INFO - __main__ - Step 10103: {'lr': 0.0004963119219991691, 'samples': 1939776, 'steps': 10102, 'loss/train': 2.061192750930786} 08/30/2021 14:58:09 - INFO - __main__ - Step 10104: {'lr': 0.0004963110137770054, 'samples': 1939968, 'steps': 10103, 'loss/train': 1.6963818073272705} 08/30/2021 14:58:09 - INFO - __main__ - Step 10105: {'lr': 0.0004963101054438578, 'samples': 1940160, 'steps': 10104, 'loss/train': 2.4496877193450928} 08/30/2021 14:58:10 - INFO - __main__ - Step 10106: {'lr': 0.0004963091969997265, 'samples': 1940352, 'steps': 10105, 'loss/train': 1.8720544576644897} 08/30/2021 14:58:10 - INFO - __main__ - Step 10107: {'lr': 0.0004963082884446123, 'samples': 1940544, 'steps': 10106, 'loss/train': 1.7878438234329224} 08/30/2021 14:58:10 - INFO - __main__ - Step 10108: {'lr': 0.0004963073797785153, 'samples': 1940736, 'steps': 10107, 'loss/train': 1.8549368381500244} 08/30/2021 14:58:12 - INFO - __main__ - Step 10109: {'lr': 0.000496306471001436, 'samples': 1940928, 'steps': 10108, 'loss/train': 2.173051595687866} 08/30/2021 14:58:12 - INFO - __main__ - Step 10110: {'lr': 0.0004963055621133748, 'samples': 1941120, 'steps': 10109, 'loss/train': 2.741757392883301} 08/30/2021 14:58:13 - INFO - __main__ - Step 10111: {'lr': 0.0004963046531143321, 'samples': 1941312, 'steps': 10110, 'loss/train': 1.8910725116729736} 08/30/2021 14:58:13 - INFO - __main__ - Step 10112: {'lr': 0.0004963037440043083, 'samples': 1941504, 'steps': 10111, 'loss/train': 2.3466920852661133} 08/30/2021 14:58:13 - INFO - __main__ - Step 10113: {'lr': 0.0004963028347833038, 'samples': 1941696, 'steps': 10112, 'loss/train': 1.580188512802124} 08/30/2021 14:58:15 - INFO - __main__ - Step 10114: {'lr': 0.0004963019254513191, 'samples': 1941888, 'steps': 10113, 'loss/train': 1.651946783065796} 08/30/2021 14:58:15 - INFO - __main__ - Step 10115: {'lr': 0.0004963010160083546, 'samples': 1942080, 'steps': 10114, 'loss/train': 1.6463650465011597} 08/30/2021 14:58:16 - INFO - __main__ - Step 10116: {'lr': 0.0004963001064544106, 'samples': 1942272, 'steps': 10115, 'loss/train': 2.0618479251861572} 08/30/2021 14:58:16 - INFO - __main__ - Step 10117: {'lr': 0.0004962991967894876, 'samples': 1942464, 'steps': 10116, 'loss/train': 1.668412208557129} 08/30/2021 14:58:16 - INFO - __main__ - Step 10118: {'lr': 0.0004962982870135859, 'samples': 1942656, 'steps': 10117, 'loss/train': 2.3173820972442627} 08/30/2021 14:58:18 - INFO - __main__ - Step 10119: {'lr': 0.0004962973771267061, 'samples': 1942848, 'steps': 10118, 'loss/train': 1.8275506496429443} 08/30/2021 14:58:18 - INFO - __main__ - Step 10120: {'lr': 0.0004962964671288484, 'samples': 1943040, 'steps': 10119, 'loss/train': 1.7746307849884033} 08/30/2021 14:58:19 - INFO - __main__ - Step 10121: {'lr': 0.0004962955570200135, 'samples': 1943232, 'steps': 10120, 'loss/train': 1.8133124113082886} 08/30/2021 14:58:19 - INFO - __main__ - Step 10122: {'lr': 0.0004962946468002014, 'samples': 1943424, 'steps': 10121, 'loss/train': 1.0313243865966797} 08/30/2021 14:58:20 - INFO - __main__ - Step 10123: {'lr': 0.0004962937364694129, 'samples': 1943616, 'steps': 10122, 'loss/train': 2.112544059753418} 08/30/2021 14:58:21 - INFO - __main__ - Step 10124: {'lr': 0.0004962928260276481, 'samples': 1943808, 'steps': 10123, 'loss/train': 2.061617374420166} 08/30/2021 14:58:21 - INFO - __main__ - Step 10125: {'lr': 0.0004962919154749077, 'samples': 1944000, 'steps': 10124, 'loss/train': 2.033141851425171} 08/30/2021 14:58:22 - INFO - __main__ - Step 10126: {'lr': 0.0004962910048111919, 'samples': 1944192, 'steps': 10125, 'loss/train': 1.267006754875183} 08/30/2021 14:58:22 - INFO - __main__ - Step 10127: {'lr': 0.0004962900940365012, 'samples': 1944384, 'steps': 10126, 'loss/train': 2.104240894317627} 08/30/2021 14:58:22 - INFO - __main__ - Step 10128: {'lr': 0.0004962891831508359, 'samples': 1944576, 'steps': 10127, 'loss/train': 1.6723476648330688} 08/30/2021 14:58:25 - INFO - __main__ - Step 10129: {'lr': 0.0004962882721541965, 'samples': 1944768, 'steps': 10128, 'loss/train': 2.021334409713745} 08/30/2021 14:58:25 - INFO - __main__ - Step 10130: {'lr': 0.0004962873610465835, 'samples': 1944960, 'steps': 10129, 'loss/train': 1.295798420906067} 08/30/2021 14:58:26 - INFO - __main__ - Step 10131: {'lr': 0.0004962864498279972, 'samples': 1945152, 'steps': 10130, 'loss/train': 2.0763285160064697} 08/30/2021 14:58:26 - INFO - __main__ - Step 10132: {'lr': 0.000496285538498438, 'samples': 1945344, 'steps': 10131, 'loss/train': 2.2645416259765625} 08/30/2021 14:58:26 - INFO - __main__ - Step 10133: {'lr': 0.0004962846270579062, 'samples': 1945536, 'steps': 10132, 'loss/train': 3.4351065158843994} 08/30/2021 14:58:27 - INFO - __main__ - Step 10134: {'lr': 0.0004962837155064025, 'samples': 1945728, 'steps': 10133, 'loss/train': 1.7721301317214966} 08/30/2021 14:58:28 - INFO - __main__ - Step 10135: {'lr': 0.0004962828038439272, 'samples': 1945920, 'steps': 10134, 'loss/train': 1.7989479303359985} 08/30/2021 14:58:29 - INFO - __main__ - Step 10136: {'lr': 0.0004962818920704805, 'samples': 1946112, 'steps': 10135, 'loss/train': 1.469241976737976} 08/30/2021 14:58:29 - INFO - __main__ - Step 10137: {'lr': 0.0004962809801860632, 'samples': 1946304, 'steps': 10136, 'loss/train': 1.559409737586975} 08/30/2021 14:58:29 - INFO - __main__ - Step 10138: {'lr': 0.0004962800681906753, 'samples': 1946496, 'steps': 10137, 'loss/train': 1.8546239137649536} 08/30/2021 14:58:30 - INFO - __main__ - Step 10139: {'lr': 0.0004962791560843175, 'samples': 1946688, 'steps': 10138, 'loss/train': 1.006983757019043} 08/30/2021 14:58:31 - INFO - __main__ - Step 10140: {'lr': 0.00049627824386699, 'samples': 1946880, 'steps': 10139, 'loss/train': 1.4265390634536743} 08/30/2021 14:58:31 - INFO - __main__ - Step 10141: {'lr': 0.0004962773315386935, 'samples': 1947072, 'steps': 10140, 'loss/train': 1.695970058441162} 08/30/2021 14:58:32 - INFO - __main__ - Step 10142: {'lr': 0.0004962764190994282, 'samples': 1947264, 'steps': 10141, 'loss/train': 2.147231101989746} 08/30/2021 14:58:32 - INFO - __main__ - Step 10143: {'lr': 0.0004962755065491944, 'samples': 1947456, 'steps': 10142, 'loss/train': 2.2169349193573} 08/30/2021 14:58:32 - INFO - __main__ - Step 10144: {'lr': 0.0004962745938879928, 'samples': 1947648, 'steps': 10143, 'loss/train': 1.2095531225204468} 08/30/2021 14:58:34 - INFO - __main__ - Step 10145: {'lr': 0.0004962736811158236, 'samples': 1947840, 'steps': 10144, 'loss/train': 1.8546603918075562} 08/30/2021 14:58:34 - INFO - __main__ - Step 10146: {'lr': 0.0004962727682326873, 'samples': 1948032, 'steps': 10145, 'loss/train': 2.2555429935455322} 08/30/2021 14:58:35 - INFO - __main__ - Step 10147: {'lr': 0.0004962718552385843, 'samples': 1948224, 'steps': 10146, 'loss/train': 2.1229538917541504} 08/30/2021 14:58:35 - INFO - __main__ - Step 10148: {'lr': 0.000496270942133515, 'samples': 1948416, 'steps': 10147, 'loss/train': 2.273806095123291} 08/30/2021 14:58:35 - INFO - __main__ - Step 10149: {'lr': 0.0004962700289174798, 'samples': 1948608, 'steps': 10148, 'loss/train': 1.9142259359359741} 08/30/2021 14:58:37 - INFO - __main__ - Step 10150: {'lr': 0.0004962691155904791, 'samples': 1948800, 'steps': 10149, 'loss/train': 1.9062116146087646} 08/30/2021 14:58:38 - INFO - __main__ - Step 10151: {'lr': 0.0004962682021525134, 'samples': 1948992, 'steps': 10150, 'loss/train': 1.9266009330749512} 08/30/2021 14:58:38 - INFO - __main__ - Step 10152: {'lr': 0.000496267288603583, 'samples': 1949184, 'steps': 10151, 'loss/train': 1.9904824495315552} 08/30/2021 14:58:38 - INFO - __main__ - Step 10153: {'lr': 0.0004962663749436883, 'samples': 1949376, 'steps': 10152, 'loss/train': 1.9961860179901123} 08/30/2021 14:58:39 - INFO - __main__ - Step 10154: {'lr': 0.0004962654611728299, 'samples': 1949568, 'steps': 10153, 'loss/train': 2.2490758895874023} 08/30/2021 14:58:41 - INFO - __main__ - Step 10155: {'lr': 0.000496264547291008, 'samples': 1949760, 'steps': 10154, 'loss/train': 0.6669377088546753} 08/30/2021 14:58:42 - INFO - __main__ - Step 10156: {'lr': 0.0004962636332982232, 'samples': 1949952, 'steps': 10155, 'loss/train': 1.332995057106018} 08/30/2021 14:58:42 - INFO - __main__ - Step 10157: {'lr': 0.0004962627191944756, 'samples': 1950144, 'steps': 10156, 'loss/train': 1.3511934280395508} 08/30/2021 14:58:42 - INFO - __main__ - Step 10158: {'lr': 0.000496261804979766, 'samples': 1950336, 'steps': 10157, 'loss/train': 1.125753402709961} 08/30/2021 14:58:43 - INFO - __main__ - Step 10159: {'lr': 0.0004962608906540946, 'samples': 1950528, 'steps': 10158, 'loss/train': 1.8245738744735718} 08/30/2021 14:58:43 - INFO - __main__ - Step 10160: {'lr': 0.0004962599762174618, 'samples': 1950720, 'steps': 10159, 'loss/train': 2.2537107467651367} 08/30/2021 14:58:45 - INFO - __main__ - Step 10161: {'lr': 0.0004962590616698681, 'samples': 1950912, 'steps': 10160, 'loss/train': 1.7657158374786377} 08/30/2021 14:58:45 - INFO - __main__ - Step 10162: {'lr': 0.0004962581470113138, 'samples': 1951104, 'steps': 10161, 'loss/train': 1.1433213949203491} 08/30/2021 14:58:45 - INFO - __main__ - Step 10163: {'lr': 0.0004962572322417994, 'samples': 1951296, 'steps': 10162, 'loss/train': 1.5990948677062988} 08/30/2021 14:58:46 - INFO - __main__ - Step 10164: {'lr': 0.0004962563173613254, 'samples': 1951488, 'steps': 10163, 'loss/train': 1.731681227684021} 08/30/2021 14:58:46 - INFO - __main__ - Step 10165: {'lr': 0.000496255402369892, 'samples': 1951680, 'steps': 10164, 'loss/train': 1.8948761224746704} 08/30/2021 14:58:48 - INFO - __main__ - Step 10166: {'lr': 0.0004962544872674997, 'samples': 1951872, 'steps': 10165, 'loss/train': 1.9159555435180664} 08/30/2021 14:58:48 - INFO - __main__ - Step 10167: {'lr': 0.000496253572054149, 'samples': 1952064, 'steps': 10166, 'loss/train': 1.0995639562606812} 08/30/2021 14:58:48 - INFO - __main__ - Step 10168: {'lr': 0.0004962526567298402, 'samples': 1952256, 'steps': 10167, 'loss/train': 1.8773449659347534} 08/30/2021 14:58:49 - INFO - __main__ - Step 10169: {'lr': 0.0004962517412945738, 'samples': 1952448, 'steps': 10168, 'loss/train': 2.614912986755371} 08/30/2021 14:58:49 - INFO - __main__ - Step 10170: {'lr': 0.00049625082574835, 'samples': 1952640, 'steps': 10169, 'loss/train': 1.9321526288986206} 08/30/2021 14:58:51 - INFO - __main__ - Step 10171: {'lr': 0.0004962499100911696, 'samples': 1952832, 'steps': 10170, 'loss/train': 2.2004430294036865} 08/30/2021 14:58:51 - INFO - __main__ - Step 10172: {'lr': 0.0004962489943230326, 'samples': 1953024, 'steps': 10171, 'loss/train': 2.0654022693634033} 08/30/2021 14:58:52 - INFO - __main__ - Step 10173: {'lr': 0.0004962480784439397, 'samples': 1953216, 'steps': 10172, 'loss/train': 0.2123950868844986} 08/30/2021 14:58:52 - INFO - __main__ - Step 10174: {'lr': 0.0004962471624538913, 'samples': 1953408, 'steps': 10173, 'loss/train': 1.478588342666626} 08/30/2021 14:58:52 - INFO - __main__ - Step 10175: {'lr': 0.0004962462463528875, 'samples': 1953600, 'steps': 10174, 'loss/train': 2.060807704925537} 08/30/2021 14:58:53 - INFO - __main__ - Step 10176: {'lr': 0.0004962453301409291, 'samples': 1953792, 'steps': 10175, 'loss/train': 1.8203874826431274} 08/30/2021 14:58:54 - INFO - __main__ - Step 10177: {'lr': 0.0004962444138180164, 'samples': 1953984, 'steps': 10176, 'loss/train': 2.0431928634643555} 08/30/2021 14:58:55 - INFO - __main__ - Step 10178: {'lr': 0.0004962434973841497, 'samples': 1954176, 'steps': 10177, 'loss/train': 1.9818137884140015} 08/30/2021 14:58:55 - INFO - __main__ - Step 10179: {'lr': 0.0004962425808393295, 'samples': 1954368, 'steps': 10178, 'loss/train': 1.7735495567321777} 08/30/2021 14:58:55 - INFO - __main__ - Step 10180: {'lr': 0.000496241664183556, 'samples': 1954560, 'steps': 10179, 'loss/train': 1.8552825450897217} 08/30/2021 14:58:56 - INFO - __main__ - Step 10181: {'lr': 0.0004962407474168301, 'samples': 1954752, 'steps': 10180, 'loss/train': 1.430060863494873} 08/30/2021 14:58:58 - INFO - __main__ - Step 10182: {'lr': 0.0004962398305391518, 'samples': 1954944, 'steps': 10181, 'loss/train': 2.282010555267334} 08/30/2021 14:58:58 - INFO - __main__ - Step 10183: {'lr': 0.0004962389135505217, 'samples': 1955136, 'steps': 10182, 'loss/train': 1.7378416061401367} 08/30/2021 14:58:58 - INFO - __main__ - Step 10184: {'lr': 0.00049623799645094, 'samples': 1955328, 'steps': 10183, 'loss/train': 1.8816922903060913} 08/30/2021 14:58:59 - INFO - __main__ - Step 10185: {'lr': 0.0004962370792404073, 'samples': 1955520, 'steps': 10184, 'loss/train': 1.8497915267944336} 08/30/2021 14:58:59 - INFO - __main__ - Step 10186: {'lr': 0.000496236161918924, 'samples': 1955712, 'steps': 10185, 'loss/train': 1.3993608951568604} 08/30/2021 14:59:01 - INFO - __main__ - Step 10187: {'lr': 0.0004962352444864904, 'samples': 1955904, 'steps': 10186, 'loss/train': 1.2489163875579834} 08/30/2021 14:59:01 - INFO - __main__ - Step 10188: {'lr': 0.0004962343269431072, 'samples': 1956096, 'steps': 10187, 'loss/train': 2.148186683654785} 08/30/2021 14:59:01 - INFO - __main__ - Step 10189: {'lr': 0.0004962334092887744, 'samples': 1956288, 'steps': 10188, 'loss/train': 1.3455642461776733} 08/30/2021 14:59:02 - INFO - __main__ - Step 10190: {'lr': 0.0004962324915234928, 'samples': 1956480, 'steps': 10189, 'loss/train': 1.4936561584472656} 08/30/2021 14:59:02 - INFO - __main__ - Step 10191: {'lr': 0.0004962315736472626, 'samples': 1956672, 'steps': 10190, 'loss/train': 1.494005560874939} 08/30/2021 14:59:04 - INFO - __main__ - Step 10192: {'lr': 0.0004962306556600842, 'samples': 1956864, 'steps': 10191, 'loss/train': 1.1978964805603027} 08/30/2021 14:59:04 - INFO - __main__ - Step 10193: {'lr': 0.0004962297375619581, 'samples': 1957056, 'steps': 10192, 'loss/train': 2.197383403778076} 08/30/2021 14:59:04 - INFO - __main__ - Step 10194: {'lr': 0.0004962288193528846, 'samples': 1957248, 'steps': 10193, 'loss/train': 1.8029744625091553} 08/30/2021 14:59:05 - INFO - __main__ - Step 10195: {'lr': 0.0004962279010328642, 'samples': 1957440, 'steps': 10194, 'loss/train': 1.7458617687225342} 08/30/2021 14:59:05 - INFO - __main__ - Step 10196: {'lr': 0.0004962269826018974, 'samples': 1957632, 'steps': 10195, 'loss/train': 2.464775562286377} 08/30/2021 14:59:06 - INFO - __main__ - Step 10197: {'lr': 0.0004962260640599845, 'samples': 1957824, 'steps': 10196, 'loss/train': 1.7174395322799683} 08/30/2021 14:59:07 - INFO - __main__ - Step 10198: {'lr': 0.0004962251454071259, 'samples': 1958016, 'steps': 10197, 'loss/train': 1.703747272491455} 08/30/2021 14:59:07 - INFO - __main__ - Step 10199: {'lr': 0.0004962242266433221, 'samples': 1958208, 'steps': 10198, 'loss/train': 1.5412509441375732} 08/30/2021 14:59:08 - INFO - __main__ - Step 10200: {'lr': 0.0004962233077685734, 'samples': 1958400, 'steps': 10199, 'loss/train': 2.7553746700286865} 08/30/2021 14:59:08 - INFO - __main__ - Step 10201: {'lr': 0.0004962223887828803, 'samples': 1958592, 'steps': 10200, 'loss/train': 1.7935335636138916} 08/30/2021 14:59:08 - INFO - __main__ - Step 10202: {'lr': 0.0004962214696862432, 'samples': 1958784, 'steps': 10201, 'loss/train': 2.0126538276672363} 08/30/2021 14:59:10 - INFO - __main__ - Step 10203: {'lr': 0.0004962205504786626, 'samples': 1958976, 'steps': 10202, 'loss/train': 1.3321278095245361} 08/30/2021 14:59:10 - INFO - __main__ - Step 10204: {'lr': 0.0004962196311601386, 'samples': 1959168, 'steps': 10203, 'loss/train': 1.842808485031128} 08/30/2021 14:59:11 - INFO - __main__ - Step 10205: {'lr': 0.000496218711730672, 'samples': 1959360, 'steps': 10204, 'loss/train': 1.4248859882354736} 08/30/2021 14:59:11 - INFO - __main__ - Step 10206: {'lr': 0.000496217792190263, 'samples': 1959552, 'steps': 10205, 'loss/train': 1.6323902606964111} 08/30/2021 14:59:11 - INFO - __main__ - Step 10207: {'lr': 0.0004962168725389121, 'samples': 1959744, 'steps': 10206, 'loss/train': 2.1328465938568115} 08/30/2021 14:59:13 - INFO - __main__ - Step 10208: {'lr': 0.0004962159527766196, 'samples': 1959936, 'steps': 10207, 'loss/train': 1.3635426759719849} 08/30/2021 14:59:13 - INFO - __main__ - Step 10209: {'lr': 0.000496215032903386, 'samples': 1960128, 'steps': 10208, 'loss/train': 2.454707622528076} 08/30/2021 14:59:14 - INFO - __main__ - Step 10210: {'lr': 0.0004962141129192118, 'samples': 1960320, 'steps': 10209, 'loss/train': 2.0520107746124268} 08/30/2021 14:59:14 - INFO - __main__ - Step 10211: {'lr': 0.0004962131928240972, 'samples': 1960512, 'steps': 10210, 'loss/train': 1.4252179861068726} 08/30/2021 14:59:14 - INFO - __main__ - Step 10212: {'lr': 0.0004962122726180428, 'samples': 1960704, 'steps': 10211, 'loss/train': 2.0074338912963867} 08/30/2021 14:59:16 - INFO - __main__ - Step 10213: {'lr': 0.000496211352301049, 'samples': 1960896, 'steps': 10212, 'loss/train': 1.5113064050674438} 08/30/2021 14:59:17 - INFO - __main__ - Step 10214: {'lr': 0.0004962104318731161, 'samples': 1961088, 'steps': 10213, 'loss/train': 1.8424110412597656} 08/30/2021 14:59:17 - INFO - __main__ - Step 10215: {'lr': 0.0004962095113342445, 'samples': 1961280, 'steps': 10214, 'loss/train': 1.7881007194519043} 08/30/2021 14:59:17 - INFO - __main__ - Step 10216: {'lr': 0.0004962085906844348, 'samples': 1961472, 'steps': 10215, 'loss/train': 1.9657223224639893} 08/30/2021 14:59:18 - INFO - __main__ - Step 10217: {'lr': 0.0004962076699236873, 'samples': 1961664, 'steps': 10216, 'loss/train': 1.7973517179489136} 08/30/2021 14:59:19 - INFO - __main__ - Step 10218: {'lr': 0.0004962067490520024, 'samples': 1961856, 'steps': 10217, 'loss/train': 1.897365689277649} 08/30/2021 14:59:20 - INFO - __main__ - Step 10219: {'lr': 0.0004962058280693805, 'samples': 1962048, 'steps': 10218, 'loss/train': 2.0293540954589844} 08/30/2021 14:59:20 - INFO - __main__ - Step 10220: {'lr': 0.0004962049069758221, 'samples': 1962240, 'steps': 10219, 'loss/train': 1.0238850116729736} 08/30/2021 14:59:20 - INFO - __main__ - Step 10221: {'lr': 0.0004962039857713276, 'samples': 1962432, 'steps': 10220, 'loss/train': 1.2621748447418213} 08/30/2021 14:59:21 - INFO - __main__ - Step 10222: {'lr': 0.0004962030644558974, 'samples': 1962624, 'steps': 10221, 'loss/train': 1.9189428091049194} 08/30/2021 14:59:22 - INFO - __main__ - Step 10223: {'lr': 0.0004962021430295319, 'samples': 1962816, 'steps': 10222, 'loss/train': 1.4690589904785156} 08/30/2021 14:59:22 - INFO - __main__ - Step 10224: {'lr': 0.0004962012214922314, 'samples': 1963008, 'steps': 10223, 'loss/train': 1.8067803382873535} 08/30/2021 14:59:23 - INFO - __main__ - Step 10225: {'lr': 0.0004962002998439966, 'samples': 1963200, 'steps': 10224, 'loss/train': 2.0416476726531982} 08/30/2021 14:59:23 - INFO - __main__ - Step 10226: {'lr': 0.0004961993780848276, 'samples': 1963392, 'steps': 10225, 'loss/train': 2.1884548664093018} 08/30/2021 14:59:24 - INFO - __main__ - Step 10227: {'lr': 0.000496198456214725, 'samples': 1963584, 'steps': 10226, 'loss/train': 1.9522669315338135} 08/30/2021 14:59:24 - INFO - __main__ - Step 10228: {'lr': 0.0004961975342336891, 'samples': 1963776, 'steps': 10227, 'loss/train': 1.6798677444458008} 08/30/2021 14:59:26 - INFO - __main__ - Step 10229: {'lr': 0.0004961966121417204, 'samples': 1963968, 'steps': 10228, 'loss/train': 1.9442551136016846} 08/30/2021 14:59:26 - INFO - __main__ - Step 10230: {'lr': 0.0004961956899388195, 'samples': 1964160, 'steps': 10229, 'loss/train': 2.0396888256073} 08/30/2021 14:59:26 - INFO - __main__ - Step 10231: {'lr': 0.0004961947676249864, 'samples': 1964352, 'steps': 10230, 'loss/train': 1.2092286348342896} 08/30/2021 14:59:27 - INFO - __main__ - Step 10232: {'lr': 0.0004961938452002218, 'samples': 1964544, 'steps': 10231, 'loss/train': 1.9337029457092285} 08/30/2021 14:59:27 - INFO - __main__ - Step 10233: {'lr': 0.0004961929226645261, 'samples': 1964736, 'steps': 10232, 'loss/train': 1.5241643190383911} 08/30/2021 14:59:29 - INFO - __main__ - Step 10234: {'lr': 0.0004961920000178996, 'samples': 1964928, 'steps': 10233, 'loss/train': 0.17785747349262238} 08/30/2021 14:59:30 - INFO - __main__ - Step 10235: {'lr': 0.0004961910772603429, 'samples': 1965120, 'steps': 10234, 'loss/train': 1.5663559436798096} 08/30/2021 14:59:30 - INFO - __main__ - Step 10236: {'lr': 0.0004961901543918563, 'samples': 1965312, 'steps': 10235, 'loss/train': 1.8163416385650635} 08/30/2021 14:59:30 - INFO - __main__ - Step 10237: {'lr': 0.0004961892314124401, 'samples': 1965504, 'steps': 10236, 'loss/train': 0.13995641469955444} 08/30/2021 14:59:31 - INFO - __main__ - Step 10238: {'lr': 0.0004961883083220948, 'samples': 1965696, 'steps': 10237, 'loss/train': 1.5841563940048218} 08/30/2021 14:59:32 - INFO - __main__ - Step 10239: {'lr': 0.0004961873851208209, 'samples': 1965888, 'steps': 10238, 'loss/train': 1.8104028701782227} 08/30/2021 14:59:33 - INFO - __main__ - Step 10240: {'lr': 0.0004961864618086188, 'samples': 1966080, 'steps': 10239, 'loss/train': 1.8419852256774902} 08/30/2021 14:59:33 - INFO - __main__ - Step 10241: {'lr': 0.0004961855383854889, 'samples': 1966272, 'steps': 10240, 'loss/train': 1.3559045791625977} 08/30/2021 14:59:33 - INFO - __main__ - Step 10242: {'lr': 0.0004961846148514315, 'samples': 1966464, 'steps': 10241, 'loss/train': 1.6722393035888672} 08/30/2021 14:59:34 - INFO - __main__ - Step 10243: {'lr': 0.0004961836912064472, 'samples': 1966656, 'steps': 10242, 'loss/train': 2.03438401222229} 08/30/2021 14:59:34 - INFO - __main__ - Step 10244: {'lr': 0.0004961827674505363, 'samples': 1966848, 'steps': 10243, 'loss/train': 1.5678279399871826} 08/30/2021 14:59:36 - INFO - __main__ - Step 10245: {'lr': 0.0004961818435836993, 'samples': 1967040, 'steps': 10244, 'loss/train': 1.594085693359375} 08/30/2021 14:59:36 - INFO - __main__ - Step 10246: {'lr': 0.0004961809196059365, 'samples': 1967232, 'steps': 10245, 'loss/train': 1.276477336883545} 08/30/2021 14:59:37 - INFO - __main__ - Step 10247: {'lr': 0.0004961799955172483, 'samples': 1967424, 'steps': 10246, 'loss/train': 1.8070474863052368} 08/30/2021 14:59:37 - INFO - __main__ - Step 10248: {'lr': 0.0004961790713176353, 'samples': 1967616, 'steps': 10247, 'loss/train': 2.1185221672058105} 08/30/2021 14:59:37 - INFO - __main__ - Step 10249: {'lr': 0.0004961781470070978, 'samples': 1967808, 'steps': 10248, 'loss/train': 1.6459875106811523} 08/30/2021 14:59:39 - INFO - __main__ - Step 10250: {'lr': 0.0004961772225856362, 'samples': 1968000, 'steps': 10249, 'loss/train': 2.2528064250946045} 08/30/2021 14:59:39 - INFO - __main__ - Step 10251: {'lr': 0.0004961762980532509, 'samples': 1968192, 'steps': 10250, 'loss/train': 1.6697717905044556} 08/30/2021 14:59:40 - INFO - __main__ - Step 10252: {'lr': 0.0004961753734099425, 'samples': 1968384, 'steps': 10251, 'loss/train': 1.2199863195419312} 08/30/2021 14:59:40 - INFO - __main__ - Step 10253: {'lr': 0.0004961744486557112, 'samples': 1968576, 'steps': 10252, 'loss/train': 1.805417776107788} 08/30/2021 14:59:40 - INFO - __main__ - Step 10254: {'lr': 0.0004961735237905574, 'samples': 1968768, 'steps': 10253, 'loss/train': 1.678693175315857} 08/30/2021 14:59:42 - INFO - __main__ - Step 10255: {'lr': 0.0004961725988144816, 'samples': 1968960, 'steps': 10254, 'loss/train': 1.8911503553390503} 08/30/2021 14:59:42 - INFO - __main__ - Step 10256: {'lr': 0.0004961716737274844, 'samples': 1969152, 'steps': 10255, 'loss/train': 2.1664628982543945} 08/30/2021 14:59:43 - INFO - __main__ - Step 10257: {'lr': 0.0004961707485295659, 'samples': 1969344, 'steps': 10256, 'loss/train': 1.5524919033050537} 08/30/2021 14:59:43 - INFO - __main__ - Step 10258: {'lr': 0.0004961698232207268, 'samples': 1969536, 'steps': 10257, 'loss/train': 2.3951942920684814} 08/30/2021 14:59:44 - INFO - __main__ - Step 10259: {'lr': 0.0004961688978009672, 'samples': 1969728, 'steps': 10258, 'loss/train': 1.9480458498001099} 08/30/2021 14:59:44 - INFO - __main__ - Step 10260: {'lr': 0.0004961679722702879, 'samples': 1969920, 'steps': 10259, 'loss/train': 1.864726185798645} 08/30/2021 14:59:45 - INFO - __main__ - Step 10261: {'lr': 0.0004961670466286889, 'samples': 1970112, 'steps': 10260, 'loss/train': 1.902874231338501} 08/30/2021 14:59:46 - INFO - __main__ - Step 10262: {'lr': 0.000496166120876171, 'samples': 1970304, 'steps': 10261, 'loss/train': 1.6221438646316528} 08/30/2021 14:59:46 - INFO - __main__ - Step 10263: {'lr': 0.0004961651950127343, 'samples': 1970496, 'steps': 10262, 'loss/train': 1.7727737426757812} 08/30/2021 14:59:46 - INFO - __main__ - Step 10264: {'lr': 0.0004961642690383794, 'samples': 1970688, 'steps': 10263, 'loss/train': 2.0062689781188965} 08/30/2021 14:59:47 - INFO - __main__ - Step 10265: {'lr': 0.0004961633429531068, 'samples': 1970880, 'steps': 10264, 'loss/train': 1.6899843215942383} 08/30/2021 14:59:48 - INFO - __main__ - Step 10266: {'lr': 0.0004961624167569166, 'samples': 1971072, 'steps': 10265, 'loss/train': 1.6278786659240723} 08/30/2021 14:59:49 - INFO - __main__ - Step 10267: {'lr': 0.0004961614904498095, 'samples': 1971264, 'steps': 10266, 'loss/train': 1.3537687063217163} 08/30/2021 14:59:49 - INFO - __main__ - Step 10268: {'lr': 0.0004961605640317858, 'samples': 1971456, 'steps': 10267, 'loss/train': 2.5009100437164307} 08/30/2021 14:59:50 - INFO - __main__ - Step 10269: {'lr': 0.0004961596375028461, 'samples': 1971648, 'steps': 10268, 'loss/train': 1.6418747901916504} 08/30/2021 14:59:50 - INFO - __main__ - Step 10270: {'lr': 0.0004961587108629906, 'samples': 1971840, 'steps': 10269, 'loss/train': 2.304105758666992} 08/30/2021 14:59:51 - INFO - __main__ - Step 10271: {'lr': 0.0004961577841122197, 'samples': 1972032, 'steps': 10270, 'loss/train': 1.972224235534668} 08/30/2021 14:59:52 - INFO - __main__ - Step 10272: {'lr': 0.000496156857250534, 'samples': 1972224, 'steps': 10271, 'loss/train': 1.9679875373840332} 08/30/2021 14:59:52 - INFO - __main__ - Step 10273: {'lr': 0.0004961559302779338, 'samples': 1972416, 'steps': 10272, 'loss/train': 1.7676537036895752} 08/30/2021 14:59:53 - INFO - __main__ - Step 10274: {'lr': 0.0004961550031944194, 'samples': 1972608, 'steps': 10273, 'loss/train': 1.8500806093215942} 08/30/2021 14:59:53 - INFO - __main__ - Step 10275: {'lr': 0.0004961540759999914, 'samples': 1972800, 'steps': 10274, 'loss/train': 1.77291738986969} 08/30/2021 14:59:55 - INFO - __main__ - Step 10276: {'lr': 0.0004961531486946502, 'samples': 1972992, 'steps': 10275, 'loss/train': 1.9960471391677856} 08/30/2021 14:59:55 - INFO - __main__ - Step 10277: {'lr': 0.0004961522212783962, 'samples': 1973184, 'steps': 10276, 'loss/train': 1.7660590410232544} 08/30/2021 14:59:56 - INFO - __main__ - Step 10278: {'lr': 0.00049615129375123, 'samples': 1973376, 'steps': 10277, 'loss/train': 1.6322904825210571} 08/30/2021 14:59:56 - INFO - __main__ - Step 10279: {'lr': 0.0004961503661131515, 'samples': 1973568, 'steps': 10278, 'loss/train': 1.6495939493179321} 08/30/2021 14:59:56 - INFO - __main__ - Step 10280: {'lr': 0.0004961494383641616, 'samples': 1973760, 'steps': 10279, 'loss/train': 0.3866509795188904} 08/30/2021 14:59:57 - INFO - __main__ - Step 10281: {'lr': 0.0004961485105042606, 'samples': 1973952, 'steps': 10280, 'loss/train': 0.7199074029922485} 08/30/2021 14:59:59 - INFO - __main__ - Step 10282: {'lr': 0.0004961475825334488, 'samples': 1974144, 'steps': 10281, 'loss/train': 1.5392190217971802} 08/30/2021 14:59:59 - INFO - __main__ - Step 10283: {'lr': 0.0004961466544517267, 'samples': 1974336, 'steps': 10282, 'loss/train': 2.1678366661071777} 08/30/2021 15:00:00 - INFO - __main__ - Step 10284: {'lr': 0.0004961457262590948, 'samples': 1974528, 'steps': 10283, 'loss/train': 1.7925416231155396} 08/30/2021 15:00:00 - INFO - __main__ - Step 10285: {'lr': 0.0004961447979555533, 'samples': 1974720, 'steps': 10284, 'loss/train': 2.2487778663635254} 08/30/2021 15:00:00 - INFO - __main__ - Step 10286: {'lr': 0.000496143869541103, 'samples': 1974912, 'steps': 10285, 'loss/train': 1.3042547702789307} 08/30/2021 15:00:01 - INFO - __main__ - Step 10287: {'lr': 0.0004961429410157437, 'samples': 1975104, 'steps': 10286, 'loss/train': 1.5594148635864258} 08/30/2021 15:00:02 - INFO - __main__ - Step 10288: {'lr': 0.0004961420123794764, 'samples': 1975296, 'steps': 10287, 'loss/train': 2.6012120246887207} 08/30/2021 15:00:03 - INFO - __main__ - Step 10289: {'lr': 0.0004961410836323014, 'samples': 1975488, 'steps': 10288, 'loss/train': 2.121105670928955} 08/30/2021 15:00:03 - INFO - __main__ - Step 10290: {'lr': 0.0004961401547742189, 'samples': 1975680, 'steps': 10289, 'loss/train': 2.434382915496826} 08/30/2021 15:00:03 - INFO - __main__ - Step 10291: {'lr': 0.0004961392258052294, 'samples': 1975872, 'steps': 10290, 'loss/train': 1.2272709608078003} 08/30/2021 15:00:04 - INFO - __main__ - Step 10292: {'lr': 0.0004961382967253335, 'samples': 1976064, 'steps': 10291, 'loss/train': 2.383918285369873} 08/30/2021 15:00:06 - INFO - __main__ - Step 10293: {'lr': 0.0004961373675345315, 'samples': 1976256, 'steps': 10292, 'loss/train': 2.726109266281128} 08/30/2021 15:00:06 - INFO - __main__ - Step 10294: {'lr': 0.0004961364382328236, 'samples': 1976448, 'steps': 10293, 'loss/train': 1.2619708776474} 08/30/2021 15:00:06 - INFO - __main__ - Step 10295: {'lr': 0.0004961355088202106, 'samples': 1976640, 'steps': 10294, 'loss/train': 2.0212178230285645} 08/30/2021 15:00:07 - INFO - __main__ - Step 10296: {'lr': 0.0004961345792966926, 'samples': 1976832, 'steps': 10295, 'loss/train': 2.1003832817077637} 08/30/2021 15:00:07 - INFO - __main__ - Step 10297: {'lr': 0.0004961336496622702, 'samples': 1977024, 'steps': 10296, 'loss/train': 1.3134616613388062} 08/30/2021 15:00:09 - INFO - __main__ - Step 10298: {'lr': 0.0004961327199169438, 'samples': 1977216, 'steps': 10297, 'loss/train': 1.7765445709228516} 08/30/2021 15:00:09 - INFO - __main__ - Step 10299: {'lr': 0.0004961317900607138, 'samples': 1977408, 'steps': 10298, 'loss/train': 2.0218944549560547} 08/30/2021 15:00:09 - INFO - __main__ - Step 10300: {'lr': 0.0004961308600935807, 'samples': 1977600, 'steps': 10299, 'loss/train': 0.15296944975852966} 08/30/2021 15:00:10 - INFO - __main__ - Step 10301: {'lr': 0.0004961299300155446, 'samples': 1977792, 'steps': 10300, 'loss/train': 1.8994289636611938} 08/30/2021 15:00:10 - INFO - __main__ - Step 10302: {'lr': 0.0004961289998266064, 'samples': 1977984, 'steps': 10301, 'loss/train': 1.953522801399231} 08/30/2021 15:00:12 - INFO - __main__ - Step 10303: {'lr': 0.0004961280695267662, 'samples': 1978176, 'steps': 10302, 'loss/train': 1.8934563398361206} 08/30/2021 15:00:12 - INFO - __main__ - Step 10304: {'lr': 0.0004961271391160243, 'samples': 1978368, 'steps': 10303, 'loss/train': 1.4899977445602417} 08/30/2021 15:00:12 - INFO - __main__ - Step 10305: {'lr': 0.0004961262085943815, 'samples': 1978560, 'steps': 10304, 'loss/train': 2.116154193878174} 08/30/2021 15:00:13 - INFO - __main__ - Step 10306: {'lr': 0.000496125277961838, 'samples': 1978752, 'steps': 10305, 'loss/train': 2.0883262157440186} 08/30/2021 15:00:13 - INFO - __main__ - Step 10307: {'lr': 0.0004961243472183942, 'samples': 1978944, 'steps': 10306, 'loss/train': 1.5113731622695923} 08/30/2021 15:00:15 - INFO - __main__ - Step 10308: {'lr': 0.0004961234163640507, 'samples': 1979136, 'steps': 10307, 'loss/train': 2.18200421333313} 08/30/2021 15:00:15 - INFO - __main__ - Step 10309: {'lr': 0.0004961224853988076, 'samples': 1979328, 'steps': 10308, 'loss/train': 1.2948338985443115} 08/30/2021 15:00:16 - INFO - __main__ - Step 10310: {'lr': 0.0004961215543226657, 'samples': 1979520, 'steps': 10309, 'loss/train': 1.7266885042190552} 08/30/2021 15:00:16 - INFO - __main__ - Step 10311: {'lr': 0.0004961206231356251, 'samples': 1979712, 'steps': 10310, 'loss/train': 2.103034257888794} 08/30/2021 15:00:16 - INFO - __main__ - Step 10312: {'lr': 0.0004961196918376864, 'samples': 1979904, 'steps': 10311, 'loss/train': 0.7564037442207336} 08/30/2021 15:00:18 - INFO - __main__ - Step 10313: {'lr': 0.0004961187604288498, 'samples': 1980096, 'steps': 10312, 'loss/train': 1.8156440258026123} 08/30/2021 15:00:18 - INFO - __main__ - Step 10314: {'lr': 0.0004961178289091161, 'samples': 1980288, 'steps': 10313, 'loss/train': 1.8133211135864258} 08/30/2021 15:00:18 - INFO - __main__ - Step 10315: {'lr': 0.0004961168972784855, 'samples': 1980480, 'steps': 10314, 'loss/train': 1.6111654043197632} 08/30/2021 15:00:19 - INFO - __main__ - Step 10316: {'lr': 0.0004961159655369582, 'samples': 1980672, 'steps': 10315, 'loss/train': 1.7434855699539185} 08/30/2021 15:00:19 - INFO - __main__ - Step 10317: {'lr': 0.0004961150336845351, 'samples': 1980864, 'steps': 10316, 'loss/train': 1.8589189052581787} 08/30/2021 15:00:21 - INFO - __main__ - Step 10318: {'lr': 0.0004961141017212162, 'samples': 1981056, 'steps': 10317, 'loss/train': 1.2972108125686646} 08/30/2021 15:00:21 - INFO - __main__ - Step 10319: {'lr': 0.0004961131696470021, 'samples': 1981248, 'steps': 10318, 'loss/train': 0.16804327070713043} 08/30/2021 15:00:22 - INFO - __main__ - Step 10320: {'lr': 0.0004961122374618933, 'samples': 1981440, 'steps': 10319, 'loss/train': 1.0443837642669678} 08/30/2021 15:00:22 - INFO - __main__ - Step 10321: {'lr': 0.00049611130516589, 'samples': 1981632, 'steps': 10320, 'loss/train': 2.0743186473846436} 08/30/2021 15:00:22 - INFO - __main__ - Step 10322: {'lr': 0.0004961103727589929, 'samples': 1981824, 'steps': 10321, 'loss/train': 2.1763031482696533} 08/30/2021 15:00:23 - INFO - __main__ - Step 10323: {'lr': 0.0004961094402412021, 'samples': 1982016, 'steps': 10322, 'loss/train': 1.3292943239212036} 08/30/2021 15:00:24 - INFO - __main__ - Step 10324: {'lr': 0.0004961085076125182, 'samples': 1982208, 'steps': 10323, 'loss/train': 2.464029550552368} 08/30/2021 15:00:25 - INFO - __main__ - Step 10325: {'lr': 0.0004961075748729418, 'samples': 1982400, 'steps': 10324, 'loss/train': 1.8568816184997559} 08/30/2021 15:00:25 - INFO - __main__ - Step 10326: {'lr': 0.0004961066420224729, 'samples': 1982592, 'steps': 10325, 'loss/train': 1.8566415309906006} 08/30/2021 15:00:26 - INFO - __main__ - Step 10327: {'lr': 0.0004961057090611123, 'samples': 1982784, 'steps': 10326, 'loss/train': 1.667598843574524} 08/30/2021 15:00:26 - INFO - __main__ - Step 10328: {'lr': 0.0004961047759888601, 'samples': 1982976, 'steps': 10327, 'loss/train': 1.8366225957870483} 08/30/2021 15:00:27 - INFO - __main__ - Step 10329: {'lr': 0.000496103842805717, 'samples': 1983168, 'steps': 10328, 'loss/train': 0.7898144125938416} 08/30/2021 15:00:28 - INFO - __main__ - Step 10330: {'lr': 0.0004961029095116833, 'samples': 1983360, 'steps': 10329, 'loss/train': 1.4821635484695435} 08/30/2021 15:00:28 - INFO - __main__ - Step 10331: {'lr': 0.0004961019761067594, 'samples': 1983552, 'steps': 10330, 'loss/train': 1.6974904537200928} 08/30/2021 15:00:29 - INFO - __main__ - Step 10332: {'lr': 0.0004961010425909458, 'samples': 1983744, 'steps': 10331, 'loss/train': 1.7204148769378662} 08/30/2021 15:00:29 - INFO - __main__ - Step 10333: {'lr': 0.0004961001089642428, 'samples': 1983936, 'steps': 10332, 'loss/train': 1.5524461269378662} 08/30/2021 15:00:30 - INFO - __main__ - Step 10334: {'lr': 0.000496099175226651, 'samples': 1984128, 'steps': 10333, 'loss/train': 2.2729852199554443} 08/30/2021 15:00:31 - INFO - __main__ - Step 10335: {'lr': 0.0004960982413781705, 'samples': 1984320, 'steps': 10334, 'loss/train': 2.2635409832000732} 08/30/2021 15:00:31 - INFO - __main__ - Step 10336: {'lr': 0.0004960973074188021, 'samples': 1984512, 'steps': 10335, 'loss/train': 2.2586538791656494} 08/30/2021 15:00:32 - INFO - __main__ - Step 10337: {'lr': 0.000496096373348546, 'samples': 1984704, 'steps': 10336, 'loss/train': 1.6437163352966309} 08/30/2021 15:00:32 - INFO - __main__ - Step 10338: {'lr': 0.0004960954391674026, 'samples': 1984896, 'steps': 10337, 'loss/train': 1.271201491355896} 08/30/2021 15:00:34 - INFO - __main__ - Step 10339: {'lr': 0.0004960945048753725, 'samples': 1985088, 'steps': 10338, 'loss/train': 1.8340805768966675} 08/30/2021 15:00:35 - INFO - __main__ - Step 10340: {'lr': 0.000496093570472456, 'samples': 1985280, 'steps': 10339, 'loss/train': 1.3790926933288574} 08/30/2021 15:00:35 - INFO - __main__ - Step 10341: {'lr': 0.0004960926359586535, 'samples': 1985472, 'steps': 10340, 'loss/train': 1.9897993803024292} 08/30/2021 15:00:35 - INFO - __main__ - Step 10342: {'lr': 0.0004960917013339656, 'samples': 1985664, 'steps': 10341, 'loss/train': 2.4562790393829346} 08/30/2021 15:00:36 - INFO - __main__ - Step 10343: {'lr': 0.0004960907665983923, 'samples': 1985856, 'steps': 10342, 'loss/train': 0.17296990752220154} 08/30/2021 15:00:36 - INFO - __main__ - Step 10344: {'lr': 0.0004960898317519345, 'samples': 1986048, 'steps': 10343, 'loss/train': 1.7110241651535034} 08/30/2021 15:00:38 - INFO - __main__ - Step 10345: {'lr': 0.0004960888967945924, 'samples': 1986240, 'steps': 10344, 'loss/train': 2.053333282470703} 08/30/2021 15:00:38 - INFO - __main__ - Step 10346: {'lr': 0.0004960879617263664, 'samples': 1986432, 'steps': 10345, 'loss/train': 1.8550726175308228} 08/30/2021 15:00:38 - INFO - __main__ - Step 10347: {'lr': 0.000496087026547257, 'samples': 1986624, 'steps': 10346, 'loss/train': 1.9350652694702148} 08/30/2021 15:00:39 - INFO - __main__ - Step 10348: {'lr': 0.0004960860912572645, 'samples': 1986816, 'steps': 10347, 'loss/train': 1.3675235509872437} 08/30/2021 15:00:39 - INFO - __main__ - Step 10349: {'lr': 0.0004960851558563895, 'samples': 1987008, 'steps': 10348, 'loss/train': 1.7497878074645996} 08/30/2021 15:00:41 - INFO - __main__ - Step 10350: {'lr': 0.0004960842203446322, 'samples': 1987200, 'steps': 10349, 'loss/train': 1.941586971282959} 08/30/2021 15:00:42 - INFO - __main__ - Step 10351: {'lr': 0.0004960832847219933, 'samples': 1987392, 'steps': 10350, 'loss/train': 2.722203493118286} 08/30/2021 15:00:42 - INFO - __main__ - Step 10352: {'lr': 0.000496082348988473, 'samples': 1987584, 'steps': 10351, 'loss/train': 1.4358041286468506} 08/30/2021 15:00:42 - INFO - __main__ - Step 10353: {'lr': 0.0004960814131440717, 'samples': 1987776, 'steps': 10352, 'loss/train': 1.8353437185287476} 08/30/2021 15:00:43 - INFO - __main__ - Step 10354: {'lr': 0.0004960804771887901, 'samples': 1987968, 'steps': 10353, 'loss/train': 2.3006680011749268} 08/30/2021 15:00:43 - INFO - __main__ - Step 10355: {'lr': 0.0004960795411226283, 'samples': 1988160, 'steps': 10354, 'loss/train': 3.0335726737976074} 08/30/2021 15:00:43 - INFO - __main__ - Step 10356: {'lr': 0.0004960786049455868, 'samples': 1988352, 'steps': 10355, 'loss/train': 2.2150301933288574} 08/30/2021 15:00:45 - INFO - __main__ - Step 10357: {'lr': 0.0004960776686576663, 'samples': 1988544, 'steps': 10356, 'loss/train': 1.997801661491394} 08/30/2021 15:00:45 - INFO - __main__ - Step 10358: {'lr': 0.0004960767322588668, 'samples': 1988736, 'steps': 10357, 'loss/train': 2.2359557151794434} 08/30/2021 15:00:46 - INFO - __main__ - Step 10359: {'lr': 0.000496075795749189, 'samples': 1988928, 'steps': 10358, 'loss/train': 2.1683826446533203} 08/30/2021 15:00:46 - INFO - __main__ - Step 10360: {'lr': 0.0004960748591286332, 'samples': 1989120, 'steps': 10359, 'loss/train': 1.3156667947769165} 08/30/2021 15:00:46 - INFO - __main__ - Step 10361: {'lr': 0.0004960739223971999, 'samples': 1989312, 'steps': 10360, 'loss/train': 1.5570313930511475} 08/30/2021 15:00:48 - INFO - __main__ - Step 10362: {'lr': 0.0004960729855548895, 'samples': 1989504, 'steps': 10361, 'loss/train': 2.5488858222961426} 08/30/2021 15:00:48 - INFO - __main__ - Step 10363: {'lr': 0.0004960720486017025, 'samples': 1989696, 'steps': 10362, 'loss/train': 2.133307695388794} 08/30/2021 15:00:49 - INFO - __main__ - Step 10364: {'lr': 0.0004960711115376391, 'samples': 1989888, 'steps': 10363, 'loss/train': 2.004369020462036} 08/30/2021 15:00:49 - INFO - __main__ - Step 10365: {'lr': 0.0004960701743626999, 'samples': 1990080, 'steps': 10364, 'loss/train': 1.4569731950759888} 08/30/2021 15:00:49 - INFO - __main__ - Step 10366: {'lr': 0.0004960692370768853, 'samples': 1990272, 'steps': 10365, 'loss/train': 2.0143885612487793} 08/30/2021 15:00:51 - INFO - __main__ - Step 10367: {'lr': 0.0004960682996801956, 'samples': 1990464, 'steps': 10366, 'loss/train': 1.5447354316711426} 08/30/2021 15:00:51 - INFO - __main__ - Step 10368: {'lr': 0.0004960673621726314, 'samples': 1990656, 'steps': 10367, 'loss/train': 0.3495093286037445} 08/30/2021 15:00:52 - INFO - __main__ - Step 10369: {'lr': 0.000496066424554193, 'samples': 1990848, 'steps': 10368, 'loss/train': 1.817546010017395} 08/30/2021 15:00:52 - INFO - __main__ - Step 10370: {'lr': 0.0004960654868248809, 'samples': 1991040, 'steps': 10369, 'loss/train': 2.059018135070801} 08/30/2021 15:00:53 - INFO - __main__ - Step 10371: {'lr': 0.0004960645489846955, 'samples': 1991232, 'steps': 10370, 'loss/train': 2.0338845252990723} 08/30/2021 15:00:54 - INFO - __main__ - Step 10372: {'lr': 0.0004960636110336371, 'samples': 1991424, 'steps': 10371, 'loss/train': 2.1590704917907715} 08/30/2021 15:00:55 - INFO - __main__ - Step 10373: {'lr': 0.0004960626729717064, 'samples': 1991616, 'steps': 10372, 'loss/train': 1.9552867412567139} 08/30/2021 15:00:55 - INFO - __main__ - Step 10374: {'lr': 0.0004960617347989036, 'samples': 1991808, 'steps': 10373, 'loss/train': 1.9777945280075073} 08/30/2021 15:00:55 - INFO - __main__ - Step 10375: {'lr': 0.0004960607965152292, 'samples': 1992000, 'steps': 10374, 'loss/train': 2.2696774005889893} 08/30/2021 15:00:56 - INFO - __main__ - Step 10376: {'lr': 0.0004960598581206835, 'samples': 1992192, 'steps': 10375, 'loss/train': 1.7620307207107544} 08/30/2021 15:00:57 - INFO - __main__ - Step 10377: {'lr': 0.000496058919615267, 'samples': 1992384, 'steps': 10376, 'loss/train': 1.7011475563049316} 08/30/2021 15:00:58 - INFO - __main__ - Step 10378: {'lr': 0.0004960579809989803, 'samples': 1992576, 'steps': 10377, 'loss/train': 2.0998213291168213} 08/30/2021 15:00:58 - INFO - __main__ - Step 10379: {'lr': 0.0004960570422718237, 'samples': 1992768, 'steps': 10378, 'loss/train': 1.3776031732559204} 08/30/2021 15:00:58 - INFO - __main__ - Step 10380: {'lr': 0.0004960561034337975, 'samples': 1992960, 'steps': 10379, 'loss/train': 2.4718332290649414} 08/30/2021 15:00:59 - INFO - __main__ - Step 10381: {'lr': 0.0004960551644849022, 'samples': 1993152, 'steps': 10380, 'loss/train': 2.3681163787841797} 08/30/2021 15:01:00 - INFO - __main__ - Step 10382: {'lr': 0.0004960542254251382, 'samples': 1993344, 'steps': 10381, 'loss/train': 1.9731279611587524} 08/30/2021 15:01:01 - INFO - __main__ - Step 10383: {'lr': 0.0004960532862545061, 'samples': 1993536, 'steps': 10382, 'loss/train': 1.7828351259231567} 08/30/2021 15:01:01 - INFO - __main__ - Step 10384: {'lr': 0.0004960523469730061, 'samples': 1993728, 'steps': 10383, 'loss/train': 1.567101001739502} 08/30/2021 15:01:01 - INFO - __main__ - Step 10385: {'lr': 0.0004960514075806387, 'samples': 1993920, 'steps': 10384, 'loss/train': 1.9627090692520142} 08/30/2021 15:01:02 - INFO - __main__ - Step 10386: {'lr': 0.0004960504680774043, 'samples': 1994112, 'steps': 10385, 'loss/train': 1.5318666696548462} 08/30/2021 15:01:02 - INFO - __main__ - Step 10387: {'lr': 0.0004960495284633034, 'samples': 1994304, 'steps': 10386, 'loss/train': 2.256319046020508} 08/30/2021 15:01:04 - INFO - __main__ - Step 10388: {'lr': 0.0004960485887383363, 'samples': 1994496, 'steps': 10387, 'loss/train': 2.194608688354492} 08/30/2021 15:01:05 - INFO - __main__ - Step 10389: {'lr': 0.0004960476489025037, 'samples': 1994688, 'steps': 10388, 'loss/train': 1.449400544166565} 08/30/2021 15:01:05 - INFO - __main__ - Step 10390: {'lr': 0.0004960467089558057, 'samples': 1994880, 'steps': 10389, 'loss/train': 1.9933476448059082} 08/30/2021 15:01:06 - INFO - __main__ - Step 10391: {'lr': 0.0004960457688982428, 'samples': 1995072, 'steps': 10390, 'loss/train': 1.4009701013565063} 08/30/2021 15:01:06 - INFO - __main__ - Step 10392: {'lr': 0.0004960448287298156, 'samples': 1995264, 'steps': 10391, 'loss/train': 1.9637444019317627} 08/30/2021 15:01:06 - INFO - __main__ - Step 10393: {'lr': 0.0004960438884505242, 'samples': 1995456, 'steps': 10392, 'loss/train': 0.5234134793281555} 08/30/2021 15:01:08 - INFO - __main__ - Step 10394: {'lr': 0.0004960429480603694, 'samples': 1995648, 'steps': 10393, 'loss/train': 0.3800166845321655} 08/30/2021 15:01:09 - INFO - __main__ - Step 10395: {'lr': 0.0004960420075593515, 'samples': 1995840, 'steps': 10394, 'loss/train': 1.6070040464401245} 08/30/2021 15:01:09 - INFO - __main__ - Step 10396: {'lr': 0.0004960410669474708, 'samples': 1996032, 'steps': 10395, 'loss/train': 2.3613502979278564} 08/30/2021 15:01:10 - INFO - __main__ - Step 10397: {'lr': 0.0004960401262247277, 'samples': 1996224, 'steps': 10396, 'loss/train': 2.0823814868927} 08/30/2021 15:01:10 - INFO - __main__ - Step 10398: {'lr': 0.0004960391853911228, 'samples': 1996416, 'steps': 10397, 'loss/train': 1.2456631660461426} 08/30/2021 15:01:10 - INFO - __main__ - Step 10399: {'lr': 0.0004960382444466564, 'samples': 1996608, 'steps': 10398, 'loss/train': 1.2787742614746094} 08/30/2021 15:01:12 - INFO - __main__ - Step 10400: {'lr': 0.0004960373033913289, 'samples': 1996800, 'steps': 10399, 'loss/train': 1.6688364744186401} 08/30/2021 15:01:12 - INFO - __main__ - Step 10401: {'lr': 0.0004960363622251409, 'samples': 1996992, 'steps': 10400, 'loss/train': 1.5278105735778809} 08/30/2021 15:01:13 - INFO - __main__ - Step 10402: {'lr': 0.0004960354209480927, 'samples': 1997184, 'steps': 10401, 'loss/train': 2.1272647380828857} 08/30/2021 15:01:13 - INFO - __main__ - Step 10403: {'lr': 0.0004960344795601847, 'samples': 1997376, 'steps': 10402, 'loss/train': 1.744810938835144} 08/30/2021 15:01:13 - INFO - __main__ - Step 10404: {'lr': 0.0004960335380614174, 'samples': 1997568, 'steps': 10403, 'loss/train': 1.9196399450302124} 08/30/2021 15:01:15 - INFO - __main__ - Step 10405: {'lr': 0.0004960325964517912, 'samples': 1997760, 'steps': 10404, 'loss/train': 0.2159660905599594} 08/30/2021 15:01:15 - INFO - __main__ - Step 10406: {'lr': 0.0004960316547313064, 'samples': 1997952, 'steps': 10405, 'loss/train': 1.7362682819366455} 08/30/2021 15:01:16 - INFO - __main__ - Step 10407: {'lr': 0.0004960307128999636, 'samples': 1998144, 'steps': 10406, 'loss/train': 0.17416583001613617} 08/30/2021 15:01:16 - INFO - __main__ - Step 10408: {'lr': 0.0004960297709577632, 'samples': 1998336, 'steps': 10407, 'loss/train': 1.4828909635543823} 08/30/2021 15:01:17 - INFO - __main__ - Step 10409: {'lr': 0.0004960288289047054, 'samples': 1998528, 'steps': 10408, 'loss/train': 1.8124011754989624} 08/30/2021 15:01:18 - INFO - __main__ - Step 10410: {'lr': 0.000496027886740791, 'samples': 1998720, 'steps': 10409, 'loss/train': 2.082686424255371} 08/30/2021 15:01:19 - INFO - __main__ - Step 10411: {'lr': 0.0004960269444660201, 'samples': 1998912, 'steps': 10410, 'loss/train': 1.58790922164917} 08/30/2021 15:01:19 - INFO - __main__ - Step 10412: {'lr': 0.0004960260020803934, 'samples': 1999104, 'steps': 10411, 'loss/train': 1.5263381004333496} 08/30/2021 15:01:19 - INFO - __main__ - Step 10413: {'lr': 0.0004960250595839111, 'samples': 1999296, 'steps': 10412, 'loss/train': 1.935903549194336} 08/30/2021 15:01:20 - INFO - __main__ - Step 10414: {'lr': 0.0004960241169765737, 'samples': 1999488, 'steps': 10413, 'loss/train': 2.782301902770996} 08/30/2021 15:01:20 - INFO - __main__ - Step 10415: {'lr': 0.0004960231742583817, 'samples': 1999680, 'steps': 10414, 'loss/train': 1.631529450416565} 08/30/2021 15:01:22 - INFO - __main__ - Step 10416: {'lr': 0.0004960222314293354, 'samples': 1999872, 'steps': 10415, 'loss/train': 2.455029010772705} 08/30/2021 15:01:22 - INFO - __main__ - Step 10417: {'lr': 0.0004960212884894353, 'samples': 2000064, 'steps': 10416, 'loss/train': 2.097196340560913} 08/30/2021 15:01:22 - INFO - __main__ - Step 10418: {'lr': 0.0004960203454386817, 'samples': 2000256, 'steps': 10417, 'loss/train': 2.1052653789520264} 08/30/2021 15:01:23 - INFO - __main__ - Step 10419: {'lr': 0.0004960194022770753, 'samples': 2000448, 'steps': 10418, 'loss/train': 2.01723051071167} 08/30/2021 15:01:23 - INFO - __main__ - Step 10420: {'lr': 0.0004960184590046162, 'samples': 2000640, 'steps': 10419, 'loss/train': 3.389378070831299} 08/30/2021 15:01:25 - INFO - __main__ - Step 10421: {'lr': 0.0004960175156213051, 'samples': 2000832, 'steps': 10420, 'loss/train': 1.6210967302322388} 08/30/2021 15:01:25 - INFO - __main__ - Step 10422: {'lr': 0.0004960165721271422, 'samples': 2001024, 'steps': 10421, 'loss/train': 2.0531251430511475} 08/30/2021 15:01:26 - INFO - __main__ - Step 10423: {'lr': 0.000496015628522128, 'samples': 2001216, 'steps': 10422, 'loss/train': 1.0741275548934937} 08/30/2021 15:01:26 - INFO - __main__ - Step 10424: {'lr': 0.000496014684806263, 'samples': 2001408, 'steps': 10423, 'loss/train': 2.350569009780884} 08/30/2021 15:01:26 - INFO - __main__ - Step 10425: {'lr': 0.0004960137409795477, 'samples': 2001600, 'steps': 10424, 'loss/train': 0.19224587082862854} 08/30/2021 15:01:28 - INFO - __main__ - Step 10426: {'lr': 0.0004960127970419822, 'samples': 2001792, 'steps': 10425, 'loss/train': 2.09647274017334} 08/30/2021 15:01:28 - INFO - __main__ - Step 10427: {'lr': 0.0004960118529935674, 'samples': 2001984, 'steps': 10426, 'loss/train': 1.908085823059082} 08/30/2021 15:01:29 - INFO - __main__ - Step 10428: {'lr': 0.0004960109088343032, 'samples': 2002176, 'steps': 10427, 'loss/train': 1.8560950756072998} 08/30/2021 15:01:29 - INFO - __main__ - Step 10429: {'lr': 0.0004960099645641903, 'samples': 2002368, 'steps': 10428, 'loss/train': 3.4126241207122803} 08/30/2021 15:01:29 - INFO - __main__ - Step 10430: {'lr': 0.0004960090201832293, 'samples': 2002560, 'steps': 10429, 'loss/train': 1.7569758892059326} 08/30/2021 15:01:31 - INFO - __main__ - Step 10431: {'lr': 0.0004960080756914203, 'samples': 2002752, 'steps': 10430, 'loss/train': 1.8876203298568726} 08/30/2021 15:01:31 - INFO - __main__ - Step 10432: {'lr': 0.0004960071310887638, 'samples': 2002944, 'steps': 10431, 'loss/train': 1.8103290796279907} 08/30/2021 15:01:32 - INFO - __main__ - Step 10433: {'lr': 0.0004960061863752604, 'samples': 2003136, 'steps': 10432, 'loss/train': 0.9473888278007507} 08/30/2021 15:01:32 - INFO - __main__ - Step 10434: {'lr': 0.0004960052415509103, 'samples': 2003328, 'steps': 10433, 'loss/train': 0.2175418883562088} 08/30/2021 15:01:32 - INFO - __main__ - Step 10435: {'lr': 0.0004960042966157141, 'samples': 2003520, 'steps': 10434, 'loss/train': 1.807892084121704} 08/30/2021 15:01:34 - INFO - __main__ - Step 10436: {'lr': 0.0004960033515696722, 'samples': 2003712, 'steps': 10435, 'loss/train': 2.193671703338623} 08/30/2021 15:01:35 - INFO - __main__ - Step 10437: {'lr': 0.0004960024064127849, 'samples': 2003904, 'steps': 10436, 'loss/train': 0.8680984973907471} 08/30/2021 15:01:35 - INFO - __main__ - Step 10438: {'lr': 0.0004960014611450527, 'samples': 2004096, 'steps': 10437, 'loss/train': 1.7945085763931274} 08/30/2021 15:01:35 - INFO - __main__ - Step 10439: {'lr': 0.0004960005157664762, 'samples': 2004288, 'steps': 10438, 'loss/train': 1.8623465299606323} 08/30/2021 15:01:36 - INFO - __main__ - Step 10440: {'lr': 0.0004959995702770555, 'samples': 2004480, 'steps': 10439, 'loss/train': 1.8561207056045532} 08/30/2021 15:01:37 - INFO - __main__ - Step 10441: {'lr': 0.0004959986246767913, 'samples': 2004672, 'steps': 10440, 'loss/train': 1.9420788288116455} 08/30/2021 15:01:38 - INFO - __main__ - Step 10442: {'lr': 0.0004959976789656838, 'samples': 2004864, 'steps': 10441, 'loss/train': 2.0702946186065674} 08/30/2021 15:01:38 - INFO - __main__ - Step 10443: {'lr': 0.0004959967331437336, 'samples': 2005056, 'steps': 10442, 'loss/train': 1.6848121881484985} 08/30/2021 15:01:38 - INFO - __main__ - Step 10444: {'lr': 0.0004959957872109411, 'samples': 2005248, 'steps': 10443, 'loss/train': 1.9728987216949463} 08/30/2021 15:01:39 - INFO - __main__ - Step 10445: {'lr': 0.0004959948411673066, 'samples': 2005440, 'steps': 10444, 'loss/train': 1.6918926239013672} 08/30/2021 15:01:39 - INFO - __main__ - Step 10446: {'lr': 0.0004959938950128308, 'samples': 2005632, 'steps': 10445, 'loss/train': 1.0344536304473877} 08/30/2021 15:01:41 - INFO - __main__ - Step 10447: {'lr': 0.0004959929487475138, 'samples': 2005824, 'steps': 10446, 'loss/train': 1.6557822227478027} 08/30/2021 15:01:41 - INFO - __main__ - Step 10448: {'lr': 0.0004959920023713563, 'samples': 2006016, 'steps': 10447, 'loss/train': 2.1298668384552} 08/30/2021 15:01:41 - INFO - __main__ - Step 10449: {'lr': 0.0004959910558843584, 'samples': 2006208, 'steps': 10448, 'loss/train': 2.1713783740997314} 08/30/2021 15:01:42 - INFO - __main__ - Step 10450: {'lr': 0.0004959901092865208, 'samples': 2006400, 'steps': 10449, 'loss/train': 1.8460066318511963} 08/30/2021 15:01:42 - INFO - __main__ - Step 10451: {'lr': 0.0004959891625778438, 'samples': 2006592, 'steps': 10450, 'loss/train': 1.6569113731384277} 08/30/2021 15:01:44 - INFO - __main__ - Step 10452: {'lr': 0.0004959882157583281, 'samples': 2006784, 'steps': 10451, 'loss/train': 1.660936951637268} 08/30/2021 15:01:45 - INFO - __main__ - Step 10453: {'lr': 0.0004959872688279737, 'samples': 2006976, 'steps': 10452, 'loss/train': 2.017768144607544} 08/30/2021 15:01:45 - INFO - __main__ - Step 10454: {'lr': 0.0004959863217867814, 'samples': 2007168, 'steps': 10453, 'loss/train': 1.8957213163375854} 08/30/2021 15:01:45 - INFO - __main__ - Step 10455: {'lr': 0.0004959853746347513, 'samples': 2007360, 'steps': 10454, 'loss/train': 1.0855712890625} 08/30/2021 15:01:46 - INFO - __main__ - Step 10456: {'lr': 0.0004959844273718841, 'samples': 2007552, 'steps': 10455, 'loss/train': 1.6310032606124878} 08/30/2021 15:01:48 - INFO - __main__ - Step 10457: {'lr': 0.00049598347999818, 'samples': 2007744, 'steps': 10456, 'loss/train': 1.9456843137741089} 08/30/2021 15:01:48 - INFO - __main__ - Step 10458: {'lr': 0.0004959825325136396, 'samples': 2007936, 'steps': 10457, 'loss/train': 1.8384852409362793} 08/30/2021 15:01:49 - INFO - __main__ - Step 10459: {'lr': 0.0004959815849182633, 'samples': 2008128, 'steps': 10458, 'loss/train': 2.7311923503875732} 08/30/2021 15:01:49 - INFO - __main__ - Step 10460: {'lr': 0.0004959806372120515, 'samples': 2008320, 'steps': 10459, 'loss/train': 1.7400085926055908} 08/30/2021 15:01:49 - INFO - __main__ - Step 10461: {'lr': 0.0004959796893950045, 'samples': 2008512, 'steps': 10460, 'loss/train': 2.2166435718536377} 08/30/2021 15:01:50 - INFO - __main__ - Step 10462: {'lr': 0.0004959787414671229, 'samples': 2008704, 'steps': 10461, 'loss/train': 0.8627303838729858} 08/30/2021 15:01:51 - INFO - __main__ - Step 10463: {'lr': 0.000495977793428407, 'samples': 2008896, 'steps': 10462, 'loss/train': 0.1974806934595108} 08/30/2021 15:01:52 - INFO - __main__ - Step 10464: {'lr': 0.0004959768452788575, 'samples': 2009088, 'steps': 10463, 'loss/train': 2.158440351486206} 08/30/2021 15:01:52 - INFO - __main__ - Step 10465: {'lr': 0.0004959758970184745, 'samples': 2009280, 'steps': 10464, 'loss/train': 1.5986219644546509} 08/30/2021 15:01:52 - INFO - __main__ - Step 10466: {'lr': 0.0004959749486472587, 'samples': 2009472, 'steps': 10465, 'loss/train': 1.4605861902236938} 08/30/2021 15:01:53 - INFO - __main__ - Step 10467: {'lr': 0.0004959740001652102, 'samples': 2009664, 'steps': 10466, 'loss/train': 2.0068705081939697} 08/30/2021 15:01:54 - INFO - __main__ - Step 10468: {'lr': 0.0004959730515723298, 'samples': 2009856, 'steps': 10467, 'loss/train': 2.039984703063965} 08/30/2021 15:01:55 - INFO - __main__ - Step 10469: {'lr': 0.0004959721028686175, 'samples': 2010048, 'steps': 10468, 'loss/train': 2.137545585632324} 08/30/2021 15:01:55 - INFO - __main__ - Step 10470: {'lr': 0.0004959711540540741, 'samples': 2010240, 'steps': 10469, 'loss/train': 1.297655701637268} 08/30/2021 15:01:56 - INFO - __main__ - Step 10471: {'lr': 0.0004959702051286999, 'samples': 2010432, 'steps': 10470, 'loss/train': 0.3394823968410492} 08/30/2021 15:01:56 - INFO - __main__ - Step 10472: {'lr': 0.0004959692560924954, 'samples': 2010624, 'steps': 10471, 'loss/train': 2.455857515335083} 08/30/2021 15:01:57 - INFO - __main__ - Step 10473: {'lr': 0.0004959683069454608, 'samples': 2010816, 'steps': 10472, 'loss/train': 2.466825246810913} 08/30/2021 15:01:58 - INFO - __main__ - Step 10474: {'lr': 0.0004959673576875967, 'samples': 2011008, 'steps': 10473, 'loss/train': 1.654446005821228} 08/30/2021 15:01:58 - INFO - __main__ - Step 10475: {'lr': 0.0004959664083189035, 'samples': 2011200, 'steps': 10474, 'loss/train': 1.4932245016098022} 08/30/2021 15:01:59 - INFO - __main__ - Step 10476: {'lr': 0.0004959654588393818, 'samples': 2011392, 'steps': 10475, 'loss/train': 1.8561971187591553} 08/30/2021 15:01:59 - INFO - __main__ - Step 10477: {'lr': 0.0004959645092490316, 'samples': 2011584, 'steps': 10476, 'loss/train': 1.9416553974151611} 08/30/2021 15:02:00 - INFO - __main__ - Step 10478: {'lr': 0.0004959635595478537, 'samples': 2011776, 'steps': 10477, 'loss/train': 2.313185930252075} 08/30/2021 15:02:01 - INFO - __main__ - Step 10479: {'lr': 0.0004959626097358485, 'samples': 2011968, 'steps': 10478, 'loss/train': 1.9820820093154907} 08/30/2021 15:02:01 - INFO - __main__ - Step 10480: {'lr': 0.0004959616598130162, 'samples': 2012160, 'steps': 10479, 'loss/train': 2.019428253173828} 08/30/2021 15:02:02 - INFO - __main__ - Step 10481: {'lr': 0.0004959607097793575, 'samples': 2012352, 'steps': 10480, 'loss/train': 2.0295042991638184} 08/30/2021 15:02:02 - INFO - __main__ - Step 10482: {'lr': 0.0004959597596348726, 'samples': 2012544, 'steps': 10481, 'loss/train': 1.7402756214141846} 08/30/2021 15:02:03 - INFO - __main__ - Step 10483: {'lr': 0.0004959588093795621, 'samples': 2012736, 'steps': 10482, 'loss/train': 1.6770402193069458} 08/30/2021 15:02:04 - INFO - __main__ - Step 10484: {'lr': 0.0004959578590134262, 'samples': 2012928, 'steps': 10483, 'loss/train': 1.5392616987228394} 08/30/2021 15:02:04 - INFO - __main__ - Step 10485: {'lr': 0.0004959569085364657, 'samples': 2013120, 'steps': 10484, 'loss/train': 1.9837473630905151} 08/30/2021 15:02:05 - INFO - __main__ - Step 10486: {'lr': 0.0004959559579486807, 'samples': 2013312, 'steps': 10485, 'loss/train': 1.8422056436538696} 08/30/2021 15:02:05 - INFO - __main__ - Step 10487: {'lr': 0.0004959550072500718, 'samples': 2013504, 'steps': 10486, 'loss/train': 1.5745959281921387} 08/30/2021 15:02:05 - INFO - __main__ - Step 10488: {'lr': 0.0004959540564406393, 'samples': 2013696, 'steps': 10487, 'loss/train': 1.6322102546691895} 08/30/2021 15:02:07 - INFO - __main__ - Step 10489: {'lr': 0.0004959531055203837, 'samples': 2013888, 'steps': 10488, 'loss/train': 2.0236124992370605} 08/30/2021 15:02:07 - INFO - __main__ - Step 10490: {'lr': 0.0004959521544893055, 'samples': 2014080, 'steps': 10489, 'loss/train': 1.785768985748291} 08/30/2021 15:02:08 - INFO - __main__ - Step 10491: {'lr': 0.000495951203347405, 'samples': 2014272, 'steps': 10490, 'loss/train': 1.6534106731414795} 08/30/2021 15:02:08 - INFO - __main__ - Step 10492: {'lr': 0.0004959502520946827, 'samples': 2014464, 'steps': 10491, 'loss/train': 0.2743142247200012} 08/30/2021 15:02:08 - INFO - __main__ - Step 10493: {'lr': 0.000495949300731139, 'samples': 2014656, 'steps': 10492, 'loss/train': 1.8411226272583008} 08/30/2021 15:02:10 - INFO - __main__ - Step 10494: {'lr': 0.0004959483492567744, 'samples': 2014848, 'steps': 10493, 'loss/train': 2.1134486198425293} 08/30/2021 15:02:10 - INFO - __main__ - Step 10495: {'lr': 0.0004959473976715892, 'samples': 2015040, 'steps': 10494, 'loss/train': 1.650178074836731} 08/30/2021 15:02:11 - INFO - __main__ - Step 10496: {'lr': 0.0004959464459755839, 'samples': 2015232, 'steps': 10495, 'loss/train': 1.9412351846694946} 08/30/2021 15:02:11 - INFO - __main__ - Step 10497: {'lr': 0.0004959454941687589, 'samples': 2015424, 'steps': 10496, 'loss/train': 2.2524361610412598} 08/30/2021 15:02:11 - INFO - __main__ - Step 10498: {'lr': 0.0004959445422511148, 'samples': 2015616, 'steps': 10497, 'loss/train': 1.2734662294387817} 08/30/2021 15:02:13 - INFO - __main__ - Step 10499: {'lr': 0.0004959435902226517, 'samples': 2015808, 'steps': 10498, 'loss/train': 1.9825326204299927} 08/30/2021 15:02:13 - INFO - __main__ - Step 10500: {'lr': 0.0004959426380833703, 'samples': 2016000, 'steps': 10499, 'loss/train': 2.5058553218841553} 08/30/2021 15:02:14 - INFO - __main__ - Step 10501: {'lr': 0.0004959416858332709, 'samples': 2016192, 'steps': 10500, 'loss/train': 0.8799305558204651} 08/30/2021 15:02:14 - INFO - __main__ - Step 10502: {'lr': 0.000495940733472354, 'samples': 2016384, 'steps': 10501, 'loss/train': 2.027930498123169} 08/30/2021 15:02:14 - INFO - __main__ - Step 10503: {'lr': 0.00049593978100062, 'samples': 2016576, 'steps': 10502, 'loss/train': 1.6999003887176514} 08/30/2021 15:02:17 - INFO - __main__ - Step 10504: {'lr': 0.0004959388284180694, 'samples': 2016768, 'steps': 10503, 'loss/train': 1.9339839220046997} 08/30/2021 15:02:17 - INFO - __main__ - Step 10505: {'lr': 0.0004959378757247024, 'samples': 2016960, 'steps': 10504, 'loss/train': 1.9652814865112305} 08/30/2021 15:02:17 - INFO - __main__ - Step 10506: {'lr': 0.0004959369229205197, 'samples': 2017152, 'steps': 10505, 'loss/train': 1.5221179723739624} 08/30/2021 15:02:18 - INFO - __main__ - Step 10507: {'lr': 0.0004959359700055216, 'samples': 2017344, 'steps': 10506, 'loss/train': 2.0980300903320312} 08/30/2021 15:02:18 - INFO - __main__ - Step 10508: {'lr': 0.0004959350169797085, 'samples': 2017536, 'steps': 10507, 'loss/train': 2.3725430965423584} 08/30/2021 15:02:20 - INFO - __main__ - Step 10509: {'lr': 0.000495934063843081, 'samples': 2017728, 'steps': 10508, 'loss/train': 1.781004548072815} 08/30/2021 15:02:20 - INFO - __main__ - Step 10510: {'lr': 0.0004959331105956393, 'samples': 2017920, 'steps': 10509, 'loss/train': 1.3632245063781738} 08/30/2021 15:02:21 - INFO - __main__ - Step 10511: {'lr': 0.000495932157237384, 'samples': 2018112, 'steps': 10510, 'loss/train': 1.4666327238082886} 08/30/2021 15:02:21 - INFO - __main__ - Step 10512: {'lr': 0.0004959312037683154, 'samples': 2018304, 'steps': 10511, 'loss/train': 1.8845940828323364} 08/30/2021 15:02:21 - INFO - __main__ - Step 10513: {'lr': 0.0004959302501884341, 'samples': 2018496, 'steps': 10512, 'loss/train': 1.7574174404144287} 08/30/2021 15:02:22 - INFO - __main__ - Step 10514: {'lr': 0.0004959292964977403, 'samples': 2018688, 'steps': 10513, 'loss/train': 0.6841381788253784} 08/30/2021 15:02:23 - INFO - __main__ - Step 10515: {'lr': 0.0004959283426962345, 'samples': 2018880, 'steps': 10514, 'loss/train': 2.153968334197998} 08/30/2021 15:02:24 - INFO - __main__ - Step 10516: {'lr': 0.0004959273887839175, 'samples': 2019072, 'steps': 10515, 'loss/train': 1.4942861795425415} 08/30/2021 15:02:24 - INFO - __main__ - Step 10517: {'lr': 0.000495926434760789, 'samples': 2019264, 'steps': 10516, 'loss/train': 1.9657281637191772} 08/30/2021 15:02:24 - INFO - __main__ - Step 10518: {'lr': 0.0004959254806268501, 'samples': 2019456, 'steps': 10517, 'loss/train': 2.0604641437530518} 08/30/2021 15:02:25 - INFO - __main__ - Step 10519: {'lr': 0.0004959245263821009, 'samples': 2019648, 'steps': 10518, 'loss/train': 1.4639756679534912} 08/30/2021 15:02:26 - INFO - __main__ - Step 10520: {'lr': 0.0004959235720265419, 'samples': 2019840, 'steps': 10519, 'loss/train': 2.400418281555176} 08/30/2021 15:02:27 - INFO - __main__ - Step 10521: {'lr': 0.0004959226175601736, 'samples': 2020032, 'steps': 10520, 'loss/train': 2.2565877437591553} 08/30/2021 15:02:27 - INFO - __main__ - Step 10522: {'lr': 0.0004959216629829964, 'samples': 2020224, 'steps': 10521, 'loss/train': 1.641075849533081} 08/30/2021 15:02:27 - INFO - __main__ - Step 10523: {'lr': 0.0004959207082950105, 'samples': 2020416, 'steps': 10522, 'loss/train': 1.942132592201233} 08/30/2021 15:02:28 - INFO - __main__ - Step 10524: {'lr': 0.0004959197534962166, 'samples': 2020608, 'steps': 10523, 'loss/train': 1.78141450881958} 08/30/2021 15:02:29 - INFO - __main__ - Step 10525: {'lr': 0.0004959187985866152, 'samples': 2020800, 'steps': 10524, 'loss/train': 2.446502208709717} 08/30/2021 15:02:30 - INFO - __main__ - Step 10526: {'lr': 0.0004959178435662064, 'samples': 2020992, 'steps': 10525, 'loss/train': 2.1773462295532227} 08/30/2021 15:02:30 - INFO - __main__ - Step 10527: {'lr': 0.0004959168884349909, 'samples': 2021184, 'steps': 10526, 'loss/train': 2.262411117553711} 08/30/2021 15:02:31 - INFO - __main__ - Step 10528: {'lr': 0.0004959159331929691, 'samples': 2021376, 'steps': 10527, 'loss/train': 0.8106072545051575} 08/30/2021 15:02:31 - INFO - __main__ - Step 10529: {'lr': 0.0004959149778401412, 'samples': 2021568, 'steps': 10528, 'loss/train': 1.9869590997695923} 08/30/2021 15:02:32 - INFO - __main__ - Step 10530: {'lr': 0.000495914022376508, 'samples': 2021760, 'steps': 10529, 'loss/train': 1.2052595615386963} 08/30/2021 15:02:33 - INFO - __main__ - Step 10531: {'lr': 0.0004959130668020696, 'samples': 2021952, 'steps': 10530, 'loss/train': 1.4175198078155518} 08/30/2021 15:02:33 - INFO - __main__ - Step 10532: {'lr': 0.0004959121111168266, 'samples': 2022144, 'steps': 10531, 'loss/train': 1.635396957397461} 08/30/2021 15:02:34 - INFO - __main__ - Step 10533: {'lr': 0.0004959111553207794, 'samples': 2022336, 'steps': 10532, 'loss/train': 1.8357553482055664} 08/30/2021 15:02:34 - INFO - __main__ - Step 10534: {'lr': 0.0004959101994139284, 'samples': 2022528, 'steps': 10533, 'loss/train': 1.7777599096298218} 08/30/2021 15:02:34 - INFO - __main__ - Step 10535: {'lr': 0.0004959092433962742, 'samples': 2022720, 'steps': 10534, 'loss/train': 2.3951852321624756} 08/30/2021 15:02:36 - INFO - __main__ - Step 10536: {'lr': 0.0004959082872678169, 'samples': 2022912, 'steps': 10535, 'loss/train': 2.1775715351104736} 08/30/2021 15:02:36 - INFO - __main__ - Step 10537: {'lr': 0.0004959073310285572, 'samples': 2023104, 'steps': 10536, 'loss/train': 1.9282255172729492} 08/30/2021 15:02:37 - INFO - __main__ - Step 10538: {'lr': 0.0004959063746784955, 'samples': 2023296, 'steps': 10537, 'loss/train': 1.8154288530349731} 08/30/2021 15:02:37 - INFO - __main__ - Step 10539: {'lr': 0.0004959054182176321, 'samples': 2023488, 'steps': 10538, 'loss/train': 1.49866783618927} 08/30/2021 15:02:37 - INFO - __main__ - Step 10540: {'lr': 0.0004959044616459676, 'samples': 2023680, 'steps': 10539, 'loss/train': 1.614794135093689} 08/30/2021 15:02:39 - INFO - __main__ - Step 10541: {'lr': 0.0004959035049635023, 'samples': 2023872, 'steps': 10540, 'loss/train': 1.7843995094299316} 08/30/2021 15:02:39 - INFO - __main__ - Step 10542: {'lr': 0.0004959025481702366, 'samples': 2024064, 'steps': 10541, 'loss/train': 1.7165087461471558} 08/30/2021 15:02:40 - INFO - __main__ - Step 10543: {'lr': 0.0004959015912661712, 'samples': 2024256, 'steps': 10542, 'loss/train': 1.9312180280685425} 08/30/2021 15:02:40 - INFO - __main__ - Step 10544: {'lr': 0.0004959006342513062, 'samples': 2024448, 'steps': 10543, 'loss/train': 1.9411728382110596} 08/30/2021 15:02:40 - INFO - __main__ - Step 10545: {'lr': 0.0004958996771256422, 'samples': 2024640, 'steps': 10544, 'loss/train': 1.5995982885360718} 08/30/2021 15:02:42 - INFO - __main__ - Step 10546: {'lr': 0.0004958987198891796, 'samples': 2024832, 'steps': 10545, 'loss/train': 2.497468948364258} 08/30/2021 15:02:42 - INFO - __main__ - Step 10547: {'lr': 0.0004958977625419187, 'samples': 2025024, 'steps': 10546, 'loss/train': 1.703046202659607} 08/30/2021 15:02:43 - INFO - __main__ - Step 10548: {'lr': 0.0004958968050838603, 'samples': 2025216, 'steps': 10547, 'loss/train': 3.0953104496002197} 08/30/2021 15:02:43 - INFO - __main__ - Step 10549: {'lr': 0.0004958958475150044, 'samples': 2025408, 'steps': 10548, 'loss/train': 3.4171063899993896} 08/30/2021 15:02:44 - INFO - __main__ - Step 10550: {'lr': 0.0004958948898353516, 'samples': 2025600, 'steps': 10549, 'loss/train': 1.3698984384536743} 08/30/2021 15:02:45 - INFO - __main__ - Step 10551: {'lr': 0.0004958939320449026, 'samples': 2025792, 'steps': 10550, 'loss/train': 1.527429461479187} 08/30/2021 15:02:45 - INFO - __main__ - Step 10552: {'lr': 0.0004958929741436574, 'samples': 2025984, 'steps': 10551, 'loss/train': 1.6819144487380981} 08/30/2021 15:02:46 - INFO - __main__ - Step 10553: {'lr': 0.0004958920161316167, 'samples': 2026176, 'steps': 10552, 'loss/train': 1.7151061296463013} 08/30/2021 15:02:46 - INFO - __main__ - Step 10554: {'lr': 0.0004958910580087808, 'samples': 2026368, 'steps': 10553, 'loss/train': 1.8407119512557983} 08/30/2021 15:02:46 - INFO - __main__ - Step 10555: {'lr': 0.0004958900997751502, 'samples': 2026560, 'steps': 10554, 'loss/train': 1.6887060403823853} 08/30/2021 15:02:48 - INFO - __main__ - Step 10556: {'lr': 0.0004958891414307253, 'samples': 2026752, 'steps': 10555, 'loss/train': 1.3946881294250488} 08/30/2021 15:02:49 - INFO - __main__ - Step 10557: {'lr': 0.0004958881829755066, 'samples': 2026944, 'steps': 10556, 'loss/train': 1.9798439741134644} 08/30/2021 15:02:49 - INFO - __main__ - Step 10558: {'lr': 0.0004958872244094944, 'samples': 2027136, 'steps': 10557, 'loss/train': 0.20437650382518768} 08/30/2021 15:02:49 - INFO - __main__ - Step 10559: {'lr': 0.0004958862657326893, 'samples': 2027328, 'steps': 10558, 'loss/train': 2.201343297958374} 08/30/2021 15:02:50 - INFO - __main__ - Step 10560: {'lr': 0.0004958853069450916, 'samples': 2027520, 'steps': 10559, 'loss/train': 1.8643922805786133} 08/30/2021 15:02:50 - INFO - __main__ - Step 10561: {'lr': 0.0004958843480467017, 'samples': 2027712, 'steps': 10560, 'loss/train': 0.7602496147155762} 08/30/2021 15:02:52 - INFO - __main__ - Step 10562: {'lr': 0.0004958833890375202, 'samples': 2027904, 'steps': 10561, 'loss/train': 1.807782769203186} 08/30/2021 15:02:52 - INFO - __main__ - Step 10563: {'lr': 0.0004958824299175474, 'samples': 2028096, 'steps': 10562, 'loss/train': 2.3995413780212402} 08/30/2021 15:02:53 - INFO - __main__ - Step 10564: {'lr': 0.0004958814706867838, 'samples': 2028288, 'steps': 10563, 'loss/train': 1.6300077438354492} 08/30/2021 15:02:53 - INFO - __main__ - Step 10565: {'lr': 0.0004958805113452298, 'samples': 2028480, 'steps': 10564, 'loss/train': 1.9002076387405396} 08/30/2021 15:02:53 - INFO - __main__ - Step 10566: {'lr': 0.0004958795518928858, 'samples': 2028672, 'steps': 10565, 'loss/train': 1.4706333875656128} 08/30/2021 15:02:55 - INFO - __main__ - Step 10567: {'lr': 0.0004958785923297522, 'samples': 2028864, 'steps': 10566, 'loss/train': 2.03666090965271} 08/30/2021 15:02:55 - INFO - __main__ - Step 10568: {'lr': 0.0004958776326558298, 'samples': 2029056, 'steps': 10567, 'loss/train': 2.123552083969116} 08/30/2021 15:02:56 - INFO - __main__ - Step 10569: {'lr': 0.0004958766728711184, 'samples': 2029248, 'steps': 10568, 'loss/train': 1.7179365158081055} 08/30/2021 15:02:56 - INFO - __main__ - Step 10570: {'lr': 0.000495875712975619, 'samples': 2029440, 'steps': 10569, 'loss/train': 0.7491295337677002} 08/30/2021 15:02:56 - INFO - __main__ - Step 10571: {'lr': 0.0004958747529693316, 'samples': 2029632, 'steps': 10570, 'loss/train': 1.47507643699646} 08/30/2021 15:02:58 - INFO - __main__ - Step 10572: {'lr': 0.000495873792852257, 'samples': 2029824, 'steps': 10571, 'loss/train': 2.0478882789611816} 08/30/2021 15:02:58 - INFO - __main__ - Step 10573: {'lr': 0.0004958728326243954, 'samples': 2030016, 'steps': 10572, 'loss/train': 1.4584681987762451} 08/30/2021 15:02:59 - INFO - __main__ - Step 10574: {'lr': 0.0004958718722857473, 'samples': 2030208, 'steps': 10573, 'loss/train': 1.727081298828125} 08/30/2021 15:02:59 - INFO - __main__ - Step 10575: {'lr': 0.0004958709118363131, 'samples': 2030400, 'steps': 10574, 'loss/train': 2.439725399017334} 08/30/2021 15:02:59 - INFO - __main__ - Step 10576: {'lr': 0.0004958699512760933, 'samples': 2030592, 'steps': 10575, 'loss/train': 2.0526723861694336} 08/30/2021 15:03:01 - INFO - __main__ - Step 10577: {'lr': 0.0004958689906050882, 'samples': 2030784, 'steps': 10576, 'loss/train': 1.855075716972351} 08/30/2021 15:03:01 - INFO - __main__ - Step 10578: {'lr': 0.0004958680298232983, 'samples': 2030976, 'steps': 10577, 'loss/train': 1.7913870811462402} 08/30/2021 15:03:02 - INFO - __main__ - Step 10579: {'lr': 0.0004958670689307242, 'samples': 2031168, 'steps': 10578, 'loss/train': 1.8129478693008423} 08/30/2021 15:03:02 - INFO - __main__ - Step 10580: {'lr': 0.0004958661079273662, 'samples': 2031360, 'steps': 10579, 'loss/train': 2.041513681411743} 08/30/2021 15:03:02 - INFO - __main__ - Step 10581: {'lr': 0.0004958651468132246, 'samples': 2031552, 'steps': 10580, 'loss/train': 1.4812042713165283} 08/30/2021 15:03:04 - INFO - __main__ - Step 10582: {'lr': 0.0004958641855883001, 'samples': 2031744, 'steps': 10581, 'loss/train': 1.9945106506347656} 08/30/2021 15:03:04 - INFO - __main__ - Step 10583: {'lr': 0.0004958632242525929, 'samples': 2031936, 'steps': 10582, 'loss/train': 2.056206226348877} 08/30/2021 15:03:05 - INFO - __main__ - Step 10584: {'lr': 0.0004958622628061035, 'samples': 2032128, 'steps': 10583, 'loss/train': 1.8133273124694824} 08/30/2021 15:03:05 - INFO - __main__ - Step 10585: {'lr': 0.0004958613012488324, 'samples': 2032320, 'steps': 10584, 'loss/train': 1.2229818105697632} 08/30/2021 15:03:05 - INFO - __main__ - Step 10586: {'lr': 0.00049586033958078, 'samples': 2032512, 'steps': 10585, 'loss/train': 1.4508144855499268} 08/30/2021 15:03:07 - INFO - __main__ - Step 10587: {'lr': 0.0004958593778019468, 'samples': 2032704, 'steps': 10586, 'loss/train': 1.7170994281768799} 08/30/2021 15:03:08 - INFO - __main__ - Step 10588: {'lr': 0.0004958584159123331, 'samples': 2032896, 'steps': 10587, 'loss/train': 1.9261326789855957} 08/30/2021 15:03:08 - INFO - __main__ - Step 10589: {'lr': 0.0004958574539119392, 'samples': 2033088, 'steps': 10588, 'loss/train': 1.8346456289291382} 08/30/2021 15:03:09 - INFO - __main__ - Step 10590: {'lr': 0.0004958564918007659, 'samples': 2033280, 'steps': 10589, 'loss/train': 1.7016843557357788} 08/30/2021 15:03:09 - INFO - __main__ - Step 10591: {'lr': 0.0004958555295788135, 'samples': 2033472, 'steps': 10590, 'loss/train': 2.2442336082458496} 08/30/2021 15:03:09 - INFO - __main__ - Step 10592: {'lr': 0.0004958545672460824, 'samples': 2033664, 'steps': 10591, 'loss/train': 1.699468970298767} 08/30/2021 15:03:11 - INFO - __main__ - Step 10593: {'lr': 0.0004958536048025729, 'samples': 2033856, 'steps': 10592, 'loss/train': 1.7041306495666504} 08/30/2021 15:03:11 - INFO - __main__ - Step 10594: {'lr': 0.0004958526422482857, 'samples': 2034048, 'steps': 10593, 'loss/train': 1.6113286018371582} 08/30/2021 15:03:12 - INFO - __main__ - Step 10595: {'lr': 0.000495851679583221, 'samples': 2034240, 'steps': 10594, 'loss/train': 1.5139615535736084} 08/30/2021 15:03:12 - INFO - __main__ - Step 10596: {'lr': 0.0004958507168073793, 'samples': 2034432, 'steps': 10595, 'loss/train': 1.9657795429229736} 08/30/2021 15:03:12 - INFO - __main__ - Step 10597: {'lr': 0.0004958497539207611, 'samples': 2034624, 'steps': 10596, 'loss/train': 1.6898196935653687} 08/30/2021 15:03:14 - INFO - __main__ - Step 10598: {'lr': 0.0004958487909233669, 'samples': 2034816, 'steps': 10597, 'loss/train': 1.334596872329712} 08/30/2021 15:03:15 - INFO - __main__ - Step 10599: {'lr': 0.0004958478278151969, 'samples': 2035008, 'steps': 10598, 'loss/train': 2.027326822280884} 08/30/2021 15:03:15 - INFO - __main__ - Step 10600: {'lr': 0.0004958468645962517, 'samples': 2035200, 'steps': 10599, 'loss/train': 1.7834383249282837} 08/30/2021 15:03:15 - INFO - __main__ - Step 10601: {'lr': 0.0004958459012665317, 'samples': 2035392, 'steps': 10600, 'loss/train': 2.2354843616485596} 08/30/2021 15:03:16 - INFO - __main__ - Step 10602: {'lr': 0.0004958449378260374, 'samples': 2035584, 'steps': 10601, 'loss/train': 1.237476110458374} 08/30/2021 15:03:16 - INFO - __main__ - Step 10603: {'lr': 0.000495843974274769, 'samples': 2035776, 'steps': 10602, 'loss/train': 2.2609970569610596} 08/30/2021 15:03:18 - INFO - __main__ - Step 10604: {'lr': 0.0004958430106127272, 'samples': 2035968, 'steps': 10603, 'loss/train': 1.93257474899292} 08/30/2021 15:03:18 - INFO - __main__ - Step 10605: {'lr': 0.0004958420468399123, 'samples': 2036160, 'steps': 10604, 'loss/train': 2.401864528656006} 08/30/2021 15:03:18 - INFO - __main__ - Step 10606: {'lr': 0.0004958410829563248, 'samples': 2036352, 'steps': 10605, 'loss/train': 1.4825185537338257} 08/30/2021 15:03:19 - INFO - __main__ - Step 10607: {'lr': 0.0004958401189619652, 'samples': 2036544, 'steps': 10606, 'loss/train': 2.18910813331604} 08/30/2021 15:03:19 - INFO - __main__ - Step 10608: {'lr': 0.0004958391548568336, 'samples': 2036736, 'steps': 10607, 'loss/train': 1.8769748210906982} 08/30/2021 15:03:21 - INFO - __main__ - Step 10609: {'lr': 0.0004958381906409308, 'samples': 2036928, 'steps': 10608, 'loss/train': 2.0168251991271973} 08/30/2021 15:03:21 - INFO - __main__ - Step 10610: {'lr': 0.0004958372263142571, 'samples': 2037120, 'steps': 10609, 'loss/train': 2.0536816120147705} 08/30/2021 15:03:21 - INFO - __main__ - Step 10611: {'lr': 0.0004958362618768129, 'samples': 2037312, 'steps': 10610, 'loss/train': 2.5476222038269043} 08/30/2021 15:03:22 - INFO - __main__ - Step 10612: {'lr': 0.0004958352973285987, 'samples': 2037504, 'steps': 10611, 'loss/train': 0.4447791576385498} 08/30/2021 15:03:22 - INFO - __main__ - Step 10613: {'lr': 0.000495834332669615, 'samples': 2037696, 'steps': 10612, 'loss/train': 2.6342968940734863} 08/30/2021 15:03:24 - INFO - __main__ - Step 10614: {'lr': 0.0004958333678998622, 'samples': 2037888, 'steps': 10613, 'loss/train': 2.205479860305786} 08/30/2021 15:03:25 - INFO - __main__ - Step 10615: {'lr': 0.0004958324030193404, 'samples': 2038080, 'steps': 10614, 'loss/train': 0.6903966069221497} 08/30/2021 15:03:25 - INFO - __main__ - Step 10616: {'lr': 0.0004958314380280504, 'samples': 2038272, 'steps': 10615, 'loss/train': 1.73091459274292} 08/30/2021 15:03:25 - INFO - __main__ - Step 10617: {'lr': 0.0004958304729259927, 'samples': 2038464, 'steps': 10616, 'loss/train': 1.6818708181381226} 08/30/2021 15:03:26 - INFO - __main__ - Step 10618: {'lr': 0.0004958295077131674, 'samples': 2038656, 'steps': 10617, 'loss/train': 1.7798888683319092} 08/30/2021 15:03:27 - INFO - __main__ - Step 10619: {'lr': 0.0004958285423895752, 'samples': 2038848, 'steps': 10618, 'loss/train': 1.265381932258606} 08/30/2021 15:03:28 - INFO - __main__ - Step 10620: {'lr': 0.0004958275769552165, 'samples': 2039040, 'steps': 10619, 'loss/train': 1.98273766040802} 08/30/2021 15:03:28 - INFO - __main__ - Step 10621: {'lr': 0.0004958266114100917, 'samples': 2039232, 'steps': 10620, 'loss/train': 2.1460537910461426} 08/30/2021 15:03:28 - INFO - __main__ - Step 10622: {'lr': 0.0004958256457542011, 'samples': 2039424, 'steps': 10621, 'loss/train': 1.9756097793579102} 08/30/2021 15:03:29 - INFO - __main__ - Step 10623: {'lr': 0.0004958246799875453, 'samples': 2039616, 'steps': 10622, 'loss/train': 2.048715591430664} 08/30/2021 15:03:31 - INFO - __main__ - Step 10624: {'lr': 0.0004958237141101247, 'samples': 2039808, 'steps': 10623, 'loss/train': 2.2093610763549805} 08/30/2021 15:03:32 - INFO - __main__ - Step 10625: {'lr': 0.0004958227481219399, 'samples': 2040000, 'steps': 10624, 'loss/train': 1.5564757585525513} 08/30/2021 15:03:32 - INFO - __main__ - Step 10626: {'lr': 0.0004958217820229909, 'samples': 2040192, 'steps': 10625, 'loss/train': 2.1298341751098633} 08/30/2021 15:03:32 - INFO - __main__ - Step 10627: {'lr': 0.0004958208158132785, 'samples': 2040384, 'steps': 10626, 'loss/train': 1.748016595840454} 08/30/2021 15:03:33 - INFO - __main__ - Step 10628: {'lr': 0.000495819849492803, 'samples': 2040576, 'steps': 10627, 'loss/train': 1.7894550561904907} 08/30/2021 15:03:33 - INFO - __main__ - Step 10629: {'lr': 0.0004958188830615649, 'samples': 2040768, 'steps': 10628, 'loss/train': 2.3215763568878174} 08/30/2021 15:03:33 - INFO - __main__ - Step 10630: {'lr': 0.0004958179165195646, 'samples': 2040960, 'steps': 10629, 'loss/train': 1.9983327388763428} 08/30/2021 15:03:34 - INFO - __main__ - Step 10631: {'lr': 0.0004958169498668026, 'samples': 2041152, 'steps': 10630, 'loss/train': 2.1977379322052} 08/30/2021 15:03:35 - INFO - __main__ - Step 10632: {'lr': 0.0004958159831032793, 'samples': 2041344, 'steps': 10631, 'loss/train': 2.129565477371216} 08/30/2021 15:03:36 - INFO - __main__ - Step 10633: {'lr': 0.000495815016228995, 'samples': 2041536, 'steps': 10632, 'loss/train': 2.476797103881836} 08/30/2021 15:03:36 - INFO - __main__ - Step 10634: {'lr': 0.0004958140492439502, 'samples': 2041728, 'steps': 10633, 'loss/train': 2.1424500942230225} 08/30/2021 15:03:36 - INFO - __main__ - Step 10635: {'lr': 0.0004958130821481455, 'samples': 2041920, 'steps': 10634, 'loss/train': 1.9851062297821045} 08/30/2021 15:03:37 - INFO - __main__ - Step 10636: {'lr': 0.0004958121149415812, 'samples': 2042112, 'steps': 10635, 'loss/train': 1.7994110584259033} 08/30/2021 15:03:38 - INFO - __main__ - Step 10637: {'lr': 0.0004958111476242577, 'samples': 2042304, 'steps': 10636, 'loss/train': 2.2752678394317627} 08/30/2021 15:03:39 - INFO - __main__ - Step 10638: {'lr': 0.0004958101801961755, 'samples': 2042496, 'steps': 10637, 'loss/train': 2.3514392375946045} 08/30/2021 15:03:39 - INFO - __main__ - Step 10639: {'lr': 0.0004958092126573352, 'samples': 2042688, 'steps': 10638, 'loss/train': 2.0725250244140625} 08/30/2021 15:03:40 - INFO - __main__ - Step 10640: {'lr': 0.0004958082450077369, 'samples': 2042880, 'steps': 10639, 'loss/train': 2.194011926651001} 08/30/2021 15:03:40 - INFO - __main__ - Step 10641: {'lr': 0.0004958072772473812, 'samples': 2043072, 'steps': 10640, 'loss/train': 1.7174255847930908} 08/30/2021 15:03:40 - INFO - __main__ - Step 10642: {'lr': 0.0004958063093762684, 'samples': 2043264, 'steps': 10641, 'loss/train': 2.1803905963897705} 08/30/2021 15:03:42 - INFO - __main__ - Step 10643: {'lr': 0.0004958053413943993, 'samples': 2043456, 'steps': 10642, 'loss/train': 1.8791708946228027} 08/30/2021 15:03:42 - INFO - __main__ - Step 10644: {'lr': 0.0004958043733017741, 'samples': 2043648, 'steps': 10643, 'loss/train': 1.8752700090408325} 08/30/2021 15:03:43 - INFO - __main__ - Step 10645: {'lr': 0.0004958034050983932, 'samples': 2043840, 'steps': 10644, 'loss/train': 1.724615454673767} 08/30/2021 15:03:43 - INFO - __main__ - Step 10646: {'lr': 0.0004958024367842569, 'samples': 2044032, 'steps': 10645, 'loss/train': 1.894936442375183} 08/30/2021 15:03:44 - INFO - __main__ - Step 10647: {'lr': 0.000495801468359366, 'samples': 2044224, 'steps': 10646, 'loss/train': 2.294870615005493} 08/30/2021 15:03:45 - INFO - __main__ - Step 10648: {'lr': 0.0004958004998237207, 'samples': 2044416, 'steps': 10647, 'loss/train': 2.764667510986328} 08/30/2021 15:03:46 - INFO - __main__ - Step 10649: {'lr': 0.0004957995311773215, 'samples': 2044608, 'steps': 10648, 'loss/train': 6.3452253341674805} 08/30/2021 15:03:46 - INFO - __main__ - Step 10650: {'lr': 0.0004957985624201688, 'samples': 2044800, 'steps': 10649, 'loss/train': 1.8892719745635986} 08/30/2021 15:03:46 - INFO - __main__ - Step 10651: {'lr': 0.0004957975935522632, 'samples': 2044992, 'steps': 10650, 'loss/train': 0.9367871284484863} 08/30/2021 15:03:47 - INFO - __main__ - Step 10652: {'lr': 0.0004957966245736048, 'samples': 2045184, 'steps': 10651, 'loss/train': 1.7667204141616821} 08/30/2021 15:03:48 - INFO - __main__ - Step 10653: {'lr': 0.0004957956554841943, 'samples': 2045376, 'steps': 10652, 'loss/train': 1.3119536638259888} 08/30/2021 15:03:49 - INFO - __main__ - Step 10654: {'lr': 0.0004957946862840321, 'samples': 2045568, 'steps': 10653, 'loss/train': 2.294827938079834} 08/30/2021 15:03:49 - INFO - __main__ - Step 10655: {'lr': 0.0004957937169731186, 'samples': 2045760, 'steps': 10654, 'loss/train': 1.4760403633117676} 08/30/2021 15:03:49 - INFO - __main__ - Step 10656: {'lr': 0.0004957927475514542, 'samples': 2045952, 'steps': 10655, 'loss/train': 1.6929547786712646} 08/30/2021 15:03:50 - INFO - __main__ - Step 10657: {'lr': 0.0004957917780190395, 'samples': 2046144, 'steps': 10656, 'loss/train': 2.8597707748413086} 08/30/2021 15:03:51 - INFO - __main__ - Step 10658: {'lr': 0.0004957908083758747, 'samples': 2046336, 'steps': 10657, 'loss/train': 1.512115240097046} 08/30/2021 15:03:52 - INFO - __main__ - Step 10659: {'lr': 0.0004957898386219603, 'samples': 2046528, 'steps': 10658, 'loss/train': 2.175381660461426} 08/30/2021 15:03:52 - INFO - __main__ - Step 10660: {'lr': 0.000495788868757297, 'samples': 2046720, 'steps': 10659, 'loss/train': 1.9193998575210571} 08/30/2021 15:03:52 - INFO - __main__ - Step 10661: {'lr': 0.0004957878987818849, 'samples': 2046912, 'steps': 10660, 'loss/train': 2.146965742111206} 08/30/2021 15:03:53 - INFO - __main__ - Step 10662: {'lr': 0.0004957869286957246, 'samples': 2047104, 'steps': 10661, 'loss/train': 2.098656415939331} 08/30/2021 15:03:53 - INFO - __main__ - Step 10663: {'lr': 0.0004957859584988164, 'samples': 2047296, 'steps': 10662, 'loss/train': 1.5975902080535889} 08/30/2021 15:03:55 - INFO - __main__ - Step 10664: {'lr': 0.0004957849881911609, 'samples': 2047488, 'steps': 10663, 'loss/train': 1.6310983896255493} 08/30/2021 15:03:55 - INFO - __main__ - Step 10665: {'lr': 0.0004957840177727585, 'samples': 2047680, 'steps': 10664, 'loss/train': 1.9936878681182861} 08/30/2021 15:03:56 - INFO - __main__ - Step 10666: {'lr': 0.0004957830472436097, 'samples': 2047872, 'steps': 10665, 'loss/train': 1.8515408039093018} 08/30/2021 15:03:56 - INFO - __main__ - Step 10667: {'lr': 0.0004957820766037147, 'samples': 2048064, 'steps': 10666, 'loss/train': 1.6449856758117676} 08/30/2021 15:03:56 - INFO - __main__ - Step 10668: {'lr': 0.0004957811058530742, 'samples': 2048256, 'steps': 10667, 'loss/train': 1.3918766975402832} 08/30/2021 15:03:58 - INFO - __main__ - Step 10669: {'lr': 0.0004957801349916884, 'samples': 2048448, 'steps': 10668, 'loss/train': 0.8530736565589905} 08/30/2021 15:03:59 - INFO - __main__ - Step 10670: {'lr': 0.000495779164019558, 'samples': 2048640, 'steps': 10669, 'loss/train': 1.6328083276748657} 08/30/2021 15:03:59 - INFO - __main__ - Step 10671: {'lr': 0.0004957781929366832, 'samples': 2048832, 'steps': 10670, 'loss/train': 1.8257925510406494} 08/30/2021 15:03:59 - INFO - __main__ - Step 10672: {'lr': 0.0004957772217430646, 'samples': 2049024, 'steps': 10671, 'loss/train': 1.3351576328277588} 08/30/2021 15:04:00 - INFO - __main__ - Step 10673: {'lr': 0.0004957762504387025, 'samples': 2049216, 'steps': 10672, 'loss/train': 1.3350465297698975} 08/30/2021 15:04:01 - INFO - __main__ - Step 10674: {'lr': 0.0004957752790235976, 'samples': 2049408, 'steps': 10673, 'loss/train': 2.212059259414673} 08/30/2021 15:04:02 - INFO - __main__ - Step 10675: {'lr': 0.00049577430749775, 'samples': 2049600, 'steps': 10674, 'loss/train': 2.780787229537964} 08/30/2021 15:04:02 - INFO - __main__ - Step 10676: {'lr': 0.0004957733358611602, 'samples': 2049792, 'steps': 10675, 'loss/train': 1.6459110975265503} 08/30/2021 15:04:02 - INFO - __main__ - Step 10677: {'lr': 0.0004957723641138289, 'samples': 2049984, 'steps': 10676, 'loss/train': 1.5592550039291382} 08/30/2021 15:04:03 - INFO - __main__ - Step 10678: {'lr': 0.0004957713922557563, 'samples': 2050176, 'steps': 10677, 'loss/train': 1.8758960962295532} 08/30/2021 15:04:03 - INFO - __main__ - Step 10679: {'lr': 0.0004957704202869429, 'samples': 2050368, 'steps': 10678, 'loss/train': 2.0165200233459473} 08/30/2021 15:04:05 - INFO - __main__ - Step 10680: {'lr': 0.0004957694482073891, 'samples': 2050560, 'steps': 10679, 'loss/train': 2.3360977172851562} 08/30/2021 15:04:05 - INFO - __main__ - Step 10681: {'lr': 0.0004957684760170955, 'samples': 2050752, 'steps': 10680, 'loss/train': 1.9172230958938599} 08/30/2021 15:04:05 - INFO - __main__ - Step 10682: {'lr': 0.0004957675037160624, 'samples': 2050944, 'steps': 10681, 'loss/train': 1.6415748596191406} 08/30/2021 15:04:06 - INFO - __main__ - Step 10683: {'lr': 0.0004957665313042902, 'samples': 2051136, 'steps': 10682, 'loss/train': 1.8189716339111328} 08/30/2021 15:04:06 - INFO - __main__ - Step 10684: {'lr': 0.0004957655587817793, 'samples': 2051328, 'steps': 10683, 'loss/train': 2.129347324371338} 08/30/2021 15:04:08 - INFO - __main__ - Step 10685: {'lr': 0.0004957645861485304, 'samples': 2051520, 'steps': 10684, 'loss/train': 1.7494794130325317} 08/30/2021 15:04:08 - INFO - __main__ - Step 10686: {'lr': 0.0004957636134045437, 'samples': 2051712, 'steps': 10685, 'loss/train': 1.7605416774749756} 08/30/2021 15:04:08 - INFO - __main__ - Step 10687: {'lr': 0.0004957626405498196, 'samples': 2051904, 'steps': 10686, 'loss/train': 2.2078678607940674} 08/30/2021 15:04:09 - INFO - __main__ - Step 10688: {'lr': 0.0004957616675843588, 'samples': 2052096, 'steps': 10687, 'loss/train': 1.554547667503357} 08/30/2021 15:04:09 - INFO - __main__ - Step 10689: {'lr': 0.0004957606945081615, 'samples': 2052288, 'steps': 10688, 'loss/train': 1.8485602140426636} 08/30/2021 15:04:11 - INFO - __main__ - Step 10690: {'lr': 0.0004957597213212284, 'samples': 2052480, 'steps': 10689, 'loss/train': 2.1953125} 08/30/2021 15:04:11 - INFO - __main__ - Step 10691: {'lr': 0.0004957587480235595, 'samples': 2052672, 'steps': 10690, 'loss/train': 1.8529311418533325} 08/30/2021 15:04:12 - INFO - __main__ - Step 10692: {'lr': 0.0004957577746151556, 'samples': 2052864, 'steps': 10691, 'loss/train': 0.44848647713661194} 08/30/2021 15:04:12 - INFO - __main__ - Step 10693: {'lr': 0.0004957568010960171, 'samples': 2053056, 'steps': 10692, 'loss/train': 0.3356359899044037} 08/30/2021 15:04:12 - INFO - __main__ - Step 10694: {'lr': 0.0004957558274661444, 'samples': 2053248, 'steps': 10693, 'loss/train': 1.0516051054000854} 08/30/2021 15:04:13 - INFO - __main__ - Step 10695: {'lr': 0.0004957548537255378, 'samples': 2053440, 'steps': 10694, 'loss/train': 0.15695035457611084} 08/30/2021 15:04:14 - INFO - __main__ - Step 10696: {'lr': 0.000495753879874198, 'samples': 2053632, 'steps': 10695, 'loss/train': 1.8583338260650635} 08/30/2021 15:04:15 - INFO - __main__ - Step 10697: {'lr': 0.0004957529059121251, 'samples': 2053824, 'steps': 10696, 'loss/train': 1.9161690473556519} 08/30/2021 15:04:15 - INFO - __main__ - Step 10698: {'lr': 0.0004957519318393199, 'samples': 2054016, 'steps': 10697, 'loss/train': 2.220370054244995} 08/30/2021 15:04:15 - INFO - __main__ - Step 10699: {'lr': 0.0004957509576557826, 'samples': 2054208, 'steps': 10698, 'loss/train': 1.381768822669983} 08/30/2021 15:04:16 - INFO - __main__ - Step 10700: {'lr': 0.0004957499833615137, 'samples': 2054400, 'steps': 10699, 'loss/train': 1.659382700920105} 08/30/2021 15:04:17 - INFO - __main__ - Step 10701: {'lr': 0.0004957490089565137, 'samples': 2054592, 'steps': 10700, 'loss/train': 1.5124784708023071} 08/30/2021 15:04:18 - INFO - __main__ - Step 10702: {'lr': 0.0004957480344407829, 'samples': 2054784, 'steps': 10701, 'loss/train': 1.7778509855270386} 08/30/2021 15:04:18 - INFO - __main__ - Step 10703: {'lr': 0.0004957470598143218, 'samples': 2054976, 'steps': 10702, 'loss/train': 1.084619164466858} 08/30/2021 15:04:18 - INFO - __main__ - Step 10704: {'lr': 0.000495746085077131, 'samples': 2055168, 'steps': 10703, 'loss/train': 1.7560259103775024} 08/30/2021 15:04:19 - INFO - __main__ - Step 10705: {'lr': 0.0004957451102292108, 'samples': 2055360, 'steps': 10704, 'loss/train': 1.4236453771591187} 08/30/2021 15:04:20 - INFO - __main__ - Step 10706: {'lr': 0.0004957441352705616, 'samples': 2055552, 'steps': 10705, 'loss/train': 2.126816987991333} 08/30/2021 15:04:20 - INFO - __main__ - Step 10707: {'lr': 0.0004957431602011839, 'samples': 2055744, 'steps': 10706, 'loss/train': 1.8676573038101196} 08/30/2021 15:04:21 - INFO - __main__ - Step 10708: {'lr': 0.0004957421850210781, 'samples': 2055936, 'steps': 10707, 'loss/train': 1.5977020263671875} 08/30/2021 15:04:21 - INFO - __main__ - Step 10709: {'lr': 0.0004957412097302446, 'samples': 2056128, 'steps': 10708, 'loss/train': 1.7649636268615723} 08/30/2021 15:04:22 - INFO - __main__ - Step 10710: {'lr': 0.000495740234328684, 'samples': 2056320, 'steps': 10709, 'loss/train': 1.82119882106781} 08/30/2021 15:04:23 - INFO - __main__ - Step 10711: {'lr': 0.0004957392588163967, 'samples': 2056512, 'steps': 10710, 'loss/train': 1.584668517112732} 08/30/2021 15:04:23 - INFO - __main__ - Step 10712: {'lr': 0.000495738283193383, 'samples': 2056704, 'steps': 10711, 'loss/train': 1.978911280632019} 08/30/2021 15:04:24 - INFO - __main__ - Step 10713: {'lr': 0.0004957373074596434, 'samples': 2056896, 'steps': 10712, 'loss/train': 1.8620069026947021} 08/30/2021 15:04:24 - INFO - __main__ - Step 10714: {'lr': 0.0004957363316151784, 'samples': 2057088, 'steps': 10713, 'loss/train': 2.139443874359131} 08/30/2021 15:04:25 - INFO - __main__ - Step 10715: {'lr': 0.0004957353556599884, 'samples': 2057280, 'steps': 10714, 'loss/train': 1.900222897529602} 08/30/2021 15:04:26 - INFO - __main__ - Step 10716: {'lr': 0.0004957343795940738, 'samples': 2057472, 'steps': 10715, 'loss/train': 1.6313177347183228} 08/30/2021 15:04:27 - INFO - __main__ - Step 10717: {'lr': 0.0004957334034174351, 'samples': 2057664, 'steps': 10716, 'loss/train': 1.8593275547027588} 08/30/2021 15:04:27 - INFO - __main__ - Step 10718: {'lr': 0.0004957324271300728, 'samples': 2057856, 'steps': 10717, 'loss/train': 1.7024364471435547} 08/30/2021 15:04:27 - INFO - __main__ - Step 10719: {'lr': 0.0004957314507319871, 'samples': 2058048, 'steps': 10718, 'loss/train': 1.9018559455871582} 08/30/2021 15:04:28 - INFO - __main__ - Step 10720: {'lr': 0.0004957304742231787, 'samples': 2058240, 'steps': 10719, 'loss/train': 2.215010643005371} 08/30/2021 15:04:29 - INFO - __main__ - Step 10721: {'lr': 0.0004957294976036479, 'samples': 2058432, 'steps': 10720, 'loss/train': 2.1520371437072754} 08/30/2021 15:04:30 - INFO - __main__ - Step 10722: {'lr': 0.0004957285208733953, 'samples': 2058624, 'steps': 10721, 'loss/train': 1.8115051984786987} 08/30/2021 15:04:30 - INFO - __main__ - Step 10723: {'lr': 0.0004957275440324211, 'samples': 2058816, 'steps': 10722, 'loss/train': 1.914891242980957} 08/30/2021 15:04:30 - INFO - __main__ - Step 10724: {'lr': 0.0004957265670807258, 'samples': 2059008, 'steps': 10723, 'loss/train': 1.5794235467910767} 08/30/2021 15:04:31 - INFO - __main__ - Step 10725: {'lr': 0.0004957255900183101, 'samples': 2059200, 'steps': 10724, 'loss/train': 1.5233807563781738} 08/30/2021 15:04:33 - INFO - __main__ - Step 10726: {'lr': 0.000495724612845174, 'samples': 2059392, 'steps': 10725, 'loss/train': 2.3213930130004883} 08/30/2021 15:04:33 - INFO - __main__ - Step 10727: {'lr': 0.0004957236355613184, 'samples': 2059584, 'steps': 10726, 'loss/train': 1.919843316078186} 08/30/2021 15:04:33 - INFO - __main__ - Step 10728: {'lr': 0.0004957226581667434, 'samples': 2059776, 'steps': 10727, 'loss/train': 1.8233662843704224} 08/30/2021 15:04:34 - INFO - __main__ - Step 10729: {'lr': 0.0004957216806614496, 'samples': 2059968, 'steps': 10728, 'loss/train': 1.996636152267456} 08/30/2021 15:04:34 - INFO - __main__ - Step 10730: {'lr': 0.0004957207030454374, 'samples': 2060160, 'steps': 10729, 'loss/train': 1.5340129137039185} 08/30/2021 15:04:36 - INFO - __main__ - Step 10731: {'lr': 0.0004957197253187073, 'samples': 2060352, 'steps': 10730, 'loss/train': 2.3949286937713623} 08/30/2021 15:04:36 - INFO - __main__ - Step 10732: {'lr': 0.0004957187474812595, 'samples': 2060544, 'steps': 10731, 'loss/train': 1.8444056510925293} 08/30/2021 15:04:36 - INFO - __main__ - Step 10733: {'lr': 0.0004957177695330948, 'samples': 2060736, 'steps': 10732, 'loss/train': 2.0066213607788086} 08/30/2021 15:04:37 - INFO - __main__ - Step 10734: {'lr': 0.0004957167914742134, 'samples': 2060928, 'steps': 10733, 'loss/train': 2.3742356300354004} 08/30/2021 15:04:37 - INFO - __main__ - Step 10735: {'lr': 0.0004957158133046158, 'samples': 2061120, 'steps': 10734, 'loss/train': 1.9590860605239868} 08/30/2021 15:04:39 - INFO - __main__ - Step 10736: {'lr': 0.0004957148350243025, 'samples': 2061312, 'steps': 10735, 'loss/train': 1.4728792905807495} 08/30/2021 15:04:39 - INFO - __main__ - Step 10737: {'lr': 0.0004957138566332738, 'samples': 2061504, 'steps': 10736, 'loss/train': 1.831321358680725} 08/30/2021 15:04:39 - INFO - __main__ - Step 10738: {'lr': 0.0004957128781315303, 'samples': 2061696, 'steps': 10737, 'loss/train': 2.2706210613250732} 08/30/2021 15:04:40 - INFO - __main__ - Step 10739: {'lr': 0.0004957118995190723, 'samples': 2061888, 'steps': 10738, 'loss/train': 1.7025460004806519} 08/30/2021 15:04:40 - INFO - __main__ - Step 10740: {'lr': 0.0004957109207959004, 'samples': 2062080, 'steps': 10739, 'loss/train': 1.8625162839889526} 08/30/2021 15:04:41 - INFO - __main__ - Step 10741: {'lr': 0.0004957099419620149, 'samples': 2062272, 'steps': 10740, 'loss/train': 1.711644172668457} 08/30/2021 15:04:42 - INFO - __main__ - Step 10742: {'lr': 0.0004957089630174163, 'samples': 2062464, 'steps': 10741, 'loss/train': 1.967525839805603} 08/30/2021 15:04:43 - INFO - __main__ - Step 10743: {'lr': 0.0004957079839621051, 'samples': 2062656, 'steps': 10742, 'loss/train': 2.0031445026397705} 08/30/2021 15:04:43 - INFO - __main__ - Step 10744: {'lr': 0.0004957070047960816, 'samples': 2062848, 'steps': 10743, 'loss/train': 1.391197919845581} 08/30/2021 15:04:43 - INFO - __main__ - Step 10745: {'lr': 0.0004957060255193462, 'samples': 2063040, 'steps': 10744, 'loss/train': 1.7929103374481201} 08/30/2021 15:04:44 - INFO - __main__ - Step 10746: {'lr': 0.0004957050461318997, 'samples': 2063232, 'steps': 10745, 'loss/train': 1.8188024759292603} 08/30/2021 15:04:45 - INFO - __main__ - Step 10747: {'lr': 0.0004957040666337422, 'samples': 2063424, 'steps': 10746, 'loss/train': 2.108142614364624} 08/30/2021 15:04:46 - INFO - __main__ - Step 10748: {'lr': 0.0004957030870248742, 'samples': 2063616, 'steps': 10747, 'loss/train': 2.050351142883301} 08/30/2021 15:04:46 - INFO - __main__ - Step 10749: {'lr': 0.0004957021073052962, 'samples': 2063808, 'steps': 10748, 'loss/train': 2.325164556503296} 08/30/2021 15:04:46 - INFO - __main__ - Step 10750: {'lr': 0.0004957011274750086, 'samples': 2064000, 'steps': 10749, 'loss/train': 6.031447410583496} 08/30/2021 15:04:47 - INFO - __main__ - Step 10751: {'lr': 0.0004957001475340119, 'samples': 2064192, 'steps': 10750, 'loss/train': 1.8415454626083374} 08/30/2021 15:04:48 - INFO - __main__ - Step 10752: {'lr': 0.0004956991674823065, 'samples': 2064384, 'steps': 10751, 'loss/train': 1.3722048997879028} 08/30/2021 15:04:49 - INFO - __main__ - Step 10753: {'lr': 0.0004956981873198928, 'samples': 2064576, 'steps': 10752, 'loss/train': 1.9432214498519897} 08/30/2021 15:04:49 - INFO - __main__ - Step 10754: {'lr': 0.0004956972070467712, 'samples': 2064768, 'steps': 10753, 'loss/train': 1.7503266334533691} 08/30/2021 15:04:49 - INFO - __main__ - Step 10755: {'lr': 0.0004956962266629424, 'samples': 2064960, 'steps': 10754, 'loss/train': 1.7071924209594727} 08/30/2021 15:04:50 - INFO - __main__ - Step 10756: {'lr': 0.0004956952461684066, 'samples': 2065152, 'steps': 10755, 'loss/train': 2.0466485023498535} 08/30/2021 15:04:51 - INFO - __main__ - Step 10757: {'lr': 0.0004956942655631644, 'samples': 2065344, 'steps': 10756, 'loss/train': 1.9296818971633911} 08/30/2021 15:04:52 - INFO - __main__ - Step 10758: {'lr': 0.0004956932848472161, 'samples': 2065536, 'steps': 10757, 'loss/train': 2.400909662246704} 08/30/2021 15:04:52 - INFO - __main__ - Step 10759: {'lr': 0.0004956923040205622, 'samples': 2065728, 'steps': 10758, 'loss/train': 1.9308323860168457} 08/30/2021 15:04:52 - INFO - __main__ - Step 10760: {'lr': 0.0004956913230832031, 'samples': 2065920, 'steps': 10759, 'loss/train': 2.390636682510376} 08/30/2021 15:04:53 - INFO - __main__ - Step 10761: {'lr': 0.0004956903420351393, 'samples': 2066112, 'steps': 10760, 'loss/train': 1.8706105947494507} 08/30/2021 15:04:53 - INFO - __main__ - Step 10762: {'lr': 0.0004956893608763713, 'samples': 2066304, 'steps': 10761, 'loss/train': 1.8931701183319092} 08/30/2021 15:04:55 - INFO - __main__ - Step 10763: {'lr': 0.0004956883796068993, 'samples': 2066496, 'steps': 10762, 'loss/train': 1.5289864540100098} 08/30/2021 15:04:55 - INFO - __main__ - Step 10764: {'lr': 0.000495687398226724, 'samples': 2066688, 'steps': 10763, 'loss/train': 2.0399932861328125} 08/30/2021 15:04:56 - INFO - __main__ - Step 10765: {'lr': 0.0004956864167358458, 'samples': 2066880, 'steps': 10764, 'loss/train': 1.2210923433303833} 08/30/2021 15:04:56 - INFO - __main__ - Step 10766: {'lr': 0.000495685435134265, 'samples': 2067072, 'steps': 10765, 'loss/train': 0.17922018468379974} 08/30/2021 15:04:56 - INFO - __main__ - Step 10767: {'lr': 0.0004956844534219822, 'samples': 2067264, 'steps': 10766, 'loss/train': 1.8820480108261108} 08/30/2021 15:04:58 - INFO - __main__ - Step 10768: {'lr': 0.0004956834715989977, 'samples': 2067456, 'steps': 10767, 'loss/train': 1.8264802694320679} 08/30/2021 15:04:58 - INFO - __main__ - Step 10769: {'lr': 0.0004956824896653122, 'samples': 2067648, 'steps': 10768, 'loss/train': 2.1791439056396484} 08/30/2021 15:04:59 - INFO - __main__ - Step 10770: {'lr': 0.0004956815076209257, 'samples': 2067840, 'steps': 10769, 'loss/train': 2.34114146232605} 08/30/2021 15:04:59 - INFO - __main__ - Step 10771: {'lr': 0.0004956805254658391, 'samples': 2068032, 'steps': 10770, 'loss/train': 1.9452028274536133} 08/30/2021 15:04:59 - INFO - __main__ - Step 10772: {'lr': 0.0004956795432000526, 'samples': 2068224, 'steps': 10771, 'loss/train': 1.3862152099609375} 08/30/2021 15:05:01 - INFO - __main__ - Step 10773: {'lr': 0.0004956785608235667, 'samples': 2068416, 'steps': 10772, 'loss/train': 1.6177400350570679} 08/30/2021 15:05:01 - INFO - __main__ - Step 10774: {'lr': 0.0004956775783363817, 'samples': 2068608, 'steps': 10773, 'loss/train': 2.16396427154541} 08/30/2021 15:05:02 - INFO - __main__ - Step 10775: {'lr': 0.0004956765957384984, 'samples': 2068800, 'steps': 10774, 'loss/train': 1.21666419506073} 08/30/2021 15:05:02 - INFO - __main__ - Step 10776: {'lr': 0.0004956756130299169, 'samples': 2068992, 'steps': 10775, 'loss/train': 2.0430588722229004} 08/30/2021 15:05:03 - INFO - __main__ - Step 10777: {'lr': 0.0004956746302106378, 'samples': 2069184, 'steps': 10776, 'loss/train': 1.5963610410690308} 08/30/2021 15:05:03 - INFO - __main__ - Step 10778: {'lr': 0.0004956736472806614, 'samples': 2069376, 'steps': 10777, 'loss/train': 0.8859256505966187} 08/30/2021 15:05:05 - INFO - __main__ - Step 10779: {'lr': 0.0004956726642399883, 'samples': 2069568, 'steps': 10778, 'loss/train': 1.70272958278656} 08/30/2021 15:05:05 - INFO - __main__ - Step 10780: {'lr': 0.0004956716810886189, 'samples': 2069760, 'steps': 10779, 'loss/train': 1.4417139291763306} 08/30/2021 15:05:06 - INFO - __main__ - Step 10781: {'lr': 0.0004956706978265536, 'samples': 2069952, 'steps': 10780, 'loss/train': 1.981103539466858} 08/30/2021 15:05:06 - INFO - __main__ - Step 10782: {'lr': 0.0004956697144537929, 'samples': 2070144, 'steps': 10781, 'loss/train': 1.9347819089889526} 08/30/2021 15:05:07 - INFO - __main__ - Step 10783: {'lr': 0.0004956687309703372, 'samples': 2070336, 'steps': 10782, 'loss/train': 1.5819716453552246} 08/30/2021 15:05:08 - INFO - __main__ - Step 10784: {'lr': 0.0004956677473761871, 'samples': 2070528, 'steps': 10783, 'loss/train': 1.8309073448181152} 08/30/2021 15:05:09 - INFO - __main__ - Step 10785: {'lr': 0.0004956667636713427, 'samples': 2070720, 'steps': 10784, 'loss/train': 2.0952024459838867} 08/30/2021 15:05:09 - INFO - __main__ - Step 10786: {'lr': 0.0004956657798558047, 'samples': 2070912, 'steps': 10785, 'loss/train': 1.7727491855621338} 08/30/2021 15:05:10 - INFO - __main__ - Step 10787: {'lr': 0.0004956647959295735, 'samples': 2071104, 'steps': 10786, 'loss/train': 1.6489266157150269} 08/30/2021 15:05:10 - INFO - __main__ - Step 10788: {'lr': 0.0004956638118926495, 'samples': 2071296, 'steps': 10787, 'loss/train': 2.277691125869751} 08/30/2021 15:05:10 - INFO - __main__ - Step 10789: {'lr': 0.0004956628277450333, 'samples': 2071488, 'steps': 10788, 'loss/train': 0.22366197407245636} 08/30/2021 15:05:12 - INFO - __main__ - Step 10790: {'lr': 0.0004956618434867251, 'samples': 2071680, 'steps': 10789, 'loss/train': 0.8237656354904175} 08/30/2021 15:05:13 - INFO - __main__ - Step 10791: {'lr': 0.0004956608591177256, 'samples': 2071872, 'steps': 10790, 'loss/train': 1.5902841091156006} 08/30/2021 15:05:13 - INFO - __main__ - Step 10792: {'lr': 0.0004956598746380349, 'samples': 2072064, 'steps': 10791, 'loss/train': 2.4441492557525635} 08/30/2021 15:05:13 - INFO - __main__ - Step 10793: {'lr': 0.0004956588900476538, 'samples': 2072256, 'steps': 10792, 'loss/train': 1.6774741411209106} 08/30/2021 15:05:14 - INFO - __main__ - Step 10794: {'lr': 0.0004956579053465826, 'samples': 2072448, 'steps': 10793, 'loss/train': 1.44629967212677} 08/30/2021 15:05:15 - INFO - __main__ - Step 10795: {'lr': 0.0004956569205348217, 'samples': 2072640, 'steps': 10794, 'loss/train': 2.2983968257904053} 08/30/2021 15:05:16 - INFO - __main__ - Step 10796: {'lr': 0.0004956559356123717, 'samples': 2072832, 'steps': 10795, 'loss/train': 1.6858317852020264} 08/30/2021 15:05:16 - INFO - __main__ - Step 10797: {'lr': 0.0004956549505792327, 'samples': 2073024, 'steps': 10796, 'loss/train': 1.852107286453247} 08/30/2021 15:05:16 - INFO - __main__ - Step 10798: {'lr': 0.0004956539654354055, 'samples': 2073216, 'steps': 10797, 'loss/train': 1.9083333015441895} 08/30/2021 15:05:17 - INFO - __main__ - Step 10799: {'lr': 0.0004956529801808904, 'samples': 2073408, 'steps': 10798, 'loss/train': 2.384979486465454} 08/30/2021 15:05:18 - INFO - __main__ - Step 10800: {'lr': 0.0004956519948156879, 'samples': 2073600, 'steps': 10799, 'loss/train': 1.8847366571426392} 08/30/2021 15:05:19 - INFO - __main__ - Step 10801: {'lr': 0.0004956510093397983, 'samples': 2073792, 'steps': 10800, 'loss/train': 1.7802255153656006} 08/30/2021 15:05:19 - INFO - __main__ - Step 10802: {'lr': 0.0004956500237532222, 'samples': 2073984, 'steps': 10801, 'loss/train': 2.1447055339813232} 08/30/2021 15:05:19 - INFO - __main__ - Step 10803: {'lr': 0.0004956490380559601, 'samples': 2074176, 'steps': 10802, 'loss/train': 1.235166072845459} 08/30/2021 15:05:20 - INFO - __main__ - Step 10804: {'lr': 0.0004956480522480121, 'samples': 2074368, 'steps': 10803, 'loss/train': 1.3955796957015991} 08/30/2021 15:05:20 - INFO - __main__ - Step 10805: {'lr': 0.000495647066329379, 'samples': 2074560, 'steps': 10804, 'loss/train': 1.908759355545044} 08/30/2021 15:05:21 - INFO - __main__ - Step 10806: {'lr': 0.0004956460803000612, 'samples': 2074752, 'steps': 10805, 'loss/train': 2.0857725143432617} 08/30/2021 15:05:22 - INFO - __main__ - Step 10807: {'lr': 0.0004956450941600589, 'samples': 2074944, 'steps': 10806, 'loss/train': 1.4821279048919678} 08/30/2021 15:05:22 - INFO - __main__ - Step 10808: {'lr': 0.0004956441079093729, 'samples': 2075136, 'steps': 10807, 'loss/train': 1.3489822149276733} 08/30/2021 15:05:23 - INFO - __main__ - Step 10809: {'lr': 0.0004956431215480034, 'samples': 2075328, 'steps': 10808, 'loss/train': 1.640360713005066} 08/30/2021 15:05:23 - INFO - __main__ - Step 10810: {'lr': 0.0004956421350759508, 'samples': 2075520, 'steps': 10809, 'loss/train': 1.8221944570541382} 08/30/2021 15:05:25 - INFO - __main__ - Step 10811: {'lr': 0.0004956411484932158, 'samples': 2075712, 'steps': 10810, 'loss/train': 2.3182005882263184} 08/30/2021 15:05:25 - INFO - __main__ - Step 10812: {'lr': 0.0004956401617997985, 'samples': 2075904, 'steps': 10811, 'loss/train': 1.3666365146636963} 08/30/2021 15:05:25 - INFO - __main__ - Step 10813: {'lr': 0.0004956391749956997, 'samples': 2076096, 'steps': 10812, 'loss/train': 2.203580141067505} 08/30/2021 15:05:26 - INFO - __main__ - Step 10814: {'lr': 0.0004956381880809195, 'samples': 2076288, 'steps': 10813, 'loss/train': 1.4165306091308594} 08/30/2021 15:05:26 - INFO - __main__ - Step 10815: {'lr': 0.0004956372010554587, 'samples': 2076480, 'steps': 10814, 'loss/train': 1.9504467248916626} 08/30/2021 15:05:28 - INFO - __main__ - Step 10816: {'lr': 0.0004956362139193174, 'samples': 2076672, 'steps': 10815, 'loss/train': 1.3715782165527344} 08/30/2021 15:05:29 - INFO - __main__ - Step 10817: {'lr': 0.0004956352266724964, 'samples': 2076864, 'steps': 10816, 'loss/train': 1.748165249824524} 08/30/2021 15:05:29 - INFO - __main__ - Step 10818: {'lr': 0.0004956342393149959, 'samples': 2077056, 'steps': 10817, 'loss/train': 1.8582464456558228} 08/30/2021 15:05:29 - INFO - __main__ - Step 10819: {'lr': 0.0004956332518468163, 'samples': 2077248, 'steps': 10818, 'loss/train': 2.4562318325042725} 08/30/2021 15:05:30 - INFO - __main__ - Step 10820: {'lr': 0.0004956322642679583, 'samples': 2077440, 'steps': 10819, 'loss/train': 1.5791183710098267} 08/30/2021 15:05:30 - INFO - __main__ - Step 10821: {'lr': 0.000495631276578422, 'samples': 2077632, 'steps': 10820, 'loss/train': 2.010395050048828} 08/30/2021 15:05:31 - INFO - __main__ - Step 10822: {'lr': 0.0004956302887782082, 'samples': 2077824, 'steps': 10821, 'loss/train': 3.501922607421875} 08/30/2021 15:05:32 - INFO - __main__ - Step 10823: {'lr': 0.0004956293008673172, 'samples': 2078016, 'steps': 10822, 'loss/train': 1.802160382270813} 08/30/2021 15:05:32 - INFO - __main__ - Step 10824: {'lr': 0.0004956283128457493, 'samples': 2078208, 'steps': 10823, 'loss/train': 0.9121621251106262} 08/30/2021 15:05:33 - INFO - __main__ - Step 10825: {'lr': 0.0004956273247135051, 'samples': 2078400, 'steps': 10824, 'loss/train': 1.7308368682861328} 08/30/2021 15:05:33 - INFO - __main__ - Step 10826: {'lr': 0.0004956263364705851, 'samples': 2078592, 'steps': 10825, 'loss/train': 2.583685874938965} 08/30/2021 15:05:34 - INFO - __main__ - Step 10827: {'lr': 0.0004956253481169895, 'samples': 2078784, 'steps': 10826, 'loss/train': 1.3237332105636597} 08/30/2021 15:05:35 - INFO - __main__ - Step 10828: {'lr': 0.0004956243596527191, 'samples': 2078976, 'steps': 10827, 'loss/train': 1.858522891998291} 08/30/2021 15:05:35 - INFO - __main__ - Step 10829: {'lr': 0.000495623371077774, 'samples': 2079168, 'steps': 10828, 'loss/train': 1.7161418199539185} 08/30/2021 15:05:36 - INFO - __main__ - Step 10830: {'lr': 0.000495622382392155, 'samples': 2079360, 'steps': 10829, 'loss/train': 1.9857534170150757} 08/30/2021 15:05:36 - INFO - __main__ - Step 10831: {'lr': 0.0004956213935958621, 'samples': 2079552, 'steps': 10830, 'loss/train': 2.1369400024414062} 08/30/2021 15:05:38 - INFO - __main__ - Step 10832: {'lr': 0.0004956204046888961, 'samples': 2079744, 'steps': 10831, 'loss/train': 2.037320137023926} 08/30/2021 15:05:38 - INFO - __main__ - Step 10833: {'lr': 0.0004956194156712574, 'samples': 2079936, 'steps': 10832, 'loss/train': 2.415008068084717} 08/30/2021 15:05:39 - INFO - __main__ - Step 10834: {'lr': 0.0004956184265429463, 'samples': 2080128, 'steps': 10833, 'loss/train': 1.4726933240890503} 08/30/2021 15:05:39 - INFO - __main__ - Step 10835: {'lr': 0.0004956174373039634, 'samples': 2080320, 'steps': 10834, 'loss/train': 1.9649070501327515} 08/30/2021 15:05:40 - INFO - __main__ - Step 10836: {'lr': 0.0004956164479543089, 'samples': 2080512, 'steps': 10835, 'loss/train': 1.7382912635803223} 08/30/2021 15:05:41 - INFO - __main__ - Step 10837: {'lr': 0.0004956154584939836, 'samples': 2080704, 'steps': 10836, 'loss/train': 1.7427713871002197} 08/30/2021 15:05:41 - INFO - __main__ - Step 10838: {'lr': 0.0004956144689229877, 'samples': 2080896, 'steps': 10837, 'loss/train': 1.9309769868850708} 08/30/2021 15:05:42 - INFO - __main__ - Step 10839: {'lr': 0.0004956134792413218, 'samples': 2081088, 'steps': 10838, 'loss/train': 1.404088020324707} 08/30/2021 15:05:42 - INFO - __main__ - Step 10840: {'lr': 0.0004956124894489861, 'samples': 2081280, 'steps': 10839, 'loss/train': 1.8259860277175903} 08/30/2021 15:05:43 - INFO - __main__ - Step 10841: {'lr': 0.0004956114995459813, 'samples': 2081472, 'steps': 10840, 'loss/train': 2.3432869911193848} 08/30/2021 15:05:44 - INFO - __main__ - Step 10842: {'lr': 0.0004956105095323077, 'samples': 2081664, 'steps': 10841, 'loss/train': 1.6931630373001099} 08/30/2021 15:05:44 - INFO - __main__ - Step 10843: {'lr': 0.0004956095194079658, 'samples': 2081856, 'steps': 10842, 'loss/train': 1.7168824672698975} 08/30/2021 15:05:45 - INFO - __main__ - Step 10844: {'lr': 0.000495608529172956, 'samples': 2082048, 'steps': 10843, 'loss/train': 1.6522506475448608} 08/30/2021 15:05:45 - INFO - __main__ - Step 10845: {'lr': 0.0004956075388272789, 'samples': 2082240, 'steps': 10844, 'loss/train': 1.83405601978302} 08/30/2021 15:05:46 - INFO - __main__ - Step 10846: {'lr': 0.0004956065483709348, 'samples': 2082432, 'steps': 10845, 'loss/train': 1.6893846988677979} 08/30/2021 15:05:47 - INFO - __main__ - Step 10847: {'lr': 0.0004956055578039241, 'samples': 2082624, 'steps': 10846, 'loss/train': 1.9587448835372925} 08/30/2021 15:05:48 - INFO - __main__ - Step 10848: {'lr': 0.0004956045671262475, 'samples': 2082816, 'steps': 10847, 'loss/train': 1.714124083518982} 08/30/2021 15:05:48 - INFO - __main__ - Step 10849: {'lr': 0.0004956035763379051, 'samples': 2083008, 'steps': 10848, 'loss/train': 1.9753811359405518} 08/30/2021 15:05:48 - INFO - __main__ - Step 10850: {'lr': 0.0004956025854388976, 'samples': 2083200, 'steps': 10849, 'loss/train': 1.519775152206421} 08/30/2021 15:05:49 - INFO - __main__ - Step 10851: {'lr': 0.0004956015944292253, 'samples': 2083392, 'steps': 10850, 'loss/train': 2.0994579792022705} 08/30/2021 15:05:49 - INFO - __main__ - Step 10852: {'lr': 0.0004956006033088888, 'samples': 2083584, 'steps': 10851, 'loss/train': 1.41232430934906} 08/30/2021 15:05:50 - INFO - __main__ - Step 10853: {'lr': 0.0004955996120778884, 'samples': 2083776, 'steps': 10852, 'loss/train': 1.8957570791244507} 08/30/2021 15:05:51 - INFO - __main__ - Step 10854: {'lr': 0.0004955986207362246, 'samples': 2083968, 'steps': 10853, 'loss/train': 1.628380537033081} 08/30/2021 15:05:51 - INFO - __main__ - Step 10855: {'lr': 0.0004955976292838979, 'samples': 2084160, 'steps': 10854, 'loss/train': 1.215693473815918} 08/30/2021 15:05:52 - INFO - __main__ - Step 10856: {'lr': 0.0004955966377209086, 'samples': 2084352, 'steps': 10855, 'loss/train': 2.0183258056640625} 08/30/2021 15:05:52 - INFO - __main__ - Step 10857: {'lr': 0.0004955956460472573, 'samples': 2084544, 'steps': 10856, 'loss/train': 1.1334675550460815} 08/30/2021 15:05:53 - INFO - __main__ - Step 10858: {'lr': 0.0004955946542629444, 'samples': 2084736, 'steps': 10857, 'loss/train': 2.163619041442871} 08/30/2021 15:05:54 - INFO - __main__ - Step 10859: {'lr': 0.0004955936623679703, 'samples': 2084928, 'steps': 10858, 'loss/train': 2.0362842082977295} 08/30/2021 15:05:54 - INFO - __main__ - Step 10860: {'lr': 0.0004955926703623356, 'samples': 2085120, 'steps': 10859, 'loss/train': 2.509580373764038} 08/30/2021 15:05:55 - INFO - __main__ - Step 10861: {'lr': 0.0004955916782460405, 'samples': 2085312, 'steps': 10860, 'loss/train': 1.321964144706726} 08/30/2021 15:05:55 - INFO - __main__ - Step 10862: {'lr': 0.0004955906860190857, 'samples': 2085504, 'steps': 10861, 'loss/train': 1.9093550443649292} 08/30/2021 15:05:56 - INFO - __main__ - Step 10863: {'lr': 0.0004955896936814714, 'samples': 2085696, 'steps': 10862, 'loss/train': 1.8934608697891235} 08/30/2021 15:05:57 - INFO - __main__ - Step 10864: {'lr': 0.0004955887012331982, 'samples': 2085888, 'steps': 10863, 'loss/train': 1.4681134223937988} 08/30/2021 15:05:57 - INFO - __main__ - Step 10865: {'lr': 0.0004955877086742666, 'samples': 2086080, 'steps': 10864, 'loss/train': 1.4558637142181396} 08/30/2021 15:05:58 - INFO - __main__ - Step 10866: {'lr': 0.0004955867160046769, 'samples': 2086272, 'steps': 10865, 'loss/train': 1.5033838748931885} 08/30/2021 15:05:58 - INFO - __main__ - Step 10867: {'lr': 0.0004955857232244297, 'samples': 2086464, 'steps': 10866, 'loss/train': 1.7385921478271484} 08/30/2021 15:05:59 - INFO - __main__ - Step 10868: {'lr': 0.0004955847303335253, 'samples': 2086656, 'steps': 10867, 'loss/train': 1.893783450126648} 08/30/2021 15:06:00 - INFO - __main__ - Step 10869: {'lr': 0.0004955837373319641, 'samples': 2086848, 'steps': 10868, 'loss/train': 1.7365012168884277} 08/30/2021 15:06:00 - INFO - __main__ - Step 10870: {'lr': 0.0004955827442197468, 'samples': 2087040, 'steps': 10869, 'loss/train': 2.0834131240844727} 08/30/2021 15:06:00 - INFO - __main__ - Step 10871: {'lr': 0.0004955817509968737, 'samples': 2087232, 'steps': 10870, 'loss/train': 1.402953863143921} 08/30/2021 15:06:01 - INFO - __main__ - Step 10872: {'lr': 0.0004955807576633452, 'samples': 2087424, 'steps': 10871, 'loss/train': 1.8041726350784302} 08/30/2021 15:06:02 - INFO - __main__ - Step 10873: {'lr': 0.0004955797642191618, 'samples': 2087616, 'steps': 10872, 'loss/train': 1.912751317024231} 08/30/2021 15:06:03 - INFO - __main__ - Step 10874: {'lr': 0.000495578770664324, 'samples': 2087808, 'steps': 10873, 'loss/train': 1.5906606912612915} 08/30/2021 15:06:03 - INFO - __main__ - Step 10875: {'lr': 0.0004955777769988322, 'samples': 2088000, 'steps': 10874, 'loss/train': 1.8554505109786987} 08/30/2021 15:06:04 - INFO - __main__ - Step 10876: {'lr': 0.0004955767832226868, 'samples': 2088192, 'steps': 10875, 'loss/train': 1.8426434993743896} 08/30/2021 15:06:04 - INFO - __main__ - Step 10877: {'lr': 0.0004955757893358884, 'samples': 2088384, 'steps': 10876, 'loss/train': 1.6191202402114868} 08/30/2021 15:06:05 - INFO - __main__ - Step 10878: {'lr': 0.0004955747953384372, 'samples': 2088576, 'steps': 10877, 'loss/train': 1.8443479537963867} 08/30/2021 15:06:06 - INFO - __main__ - Step 10879: {'lr': 0.0004955738012303338, 'samples': 2088768, 'steps': 10878, 'loss/train': 1.4832504987716675} 08/30/2021 15:06:06 - INFO - __main__ - Step 10880: {'lr': 0.0004955728070115787, 'samples': 2088960, 'steps': 10879, 'loss/train': 1.53128981590271} 08/30/2021 15:06:07 - INFO - __main__ - Step 10881: {'lr': 0.0004955718126821722, 'samples': 2089152, 'steps': 10880, 'loss/train': 1.054487943649292} 08/30/2021 15:06:07 - INFO - __main__ - Step 10882: {'lr': 0.0004955708182421149, 'samples': 2089344, 'steps': 10881, 'loss/train': 1.8855987787246704} 08/30/2021 15:06:07 - INFO - __main__ - Step 10883: {'lr': 0.0004955698236914071, 'samples': 2089536, 'steps': 10882, 'loss/train': 1.1770527362823486} 08/30/2021 15:06:09 - INFO - __main__ - Step 10884: {'lr': 0.0004955688290300494, 'samples': 2089728, 'steps': 10883, 'loss/train': 2.011972427368164} 08/30/2021 15:06:09 - INFO - __main__ - Step 10885: {'lr': 0.0004955678342580421, 'samples': 2089920, 'steps': 10884, 'loss/train': 1.6012986898422241} 08/30/2021 15:06:10 - INFO - __main__ - Step 10886: {'lr': 0.0004955668393753858, 'samples': 2090112, 'steps': 10885, 'loss/train': 1.8417295217514038} 08/30/2021 15:06:10 - INFO - __main__ - Step 10887: {'lr': 0.0004955658443820809, 'samples': 2090304, 'steps': 10886, 'loss/train': 1.6421327590942383} 08/30/2021 15:06:10 - INFO - __main__ - Step 10888: {'lr': 0.0004955648492781277, 'samples': 2090496, 'steps': 10887, 'loss/train': 1.7306485176086426} 08/30/2021 15:06:12 - INFO - __main__ - Step 10889: {'lr': 0.0004955638540635269, 'samples': 2090688, 'steps': 10888, 'loss/train': 2.8198189735412598} 08/30/2021 15:06:13 - INFO - __main__ - Step 10890: {'lr': 0.0004955628587382788, 'samples': 2090880, 'steps': 10889, 'loss/train': 1.3991672992706299} 08/30/2021 15:06:13 - INFO - __main__ - Step 10891: {'lr': 0.0004955618633023837, 'samples': 2091072, 'steps': 10890, 'loss/train': 1.8839037418365479} 08/30/2021 15:06:14 - INFO - __main__ - Step 10892: {'lr': 0.0004955608677558424, 'samples': 2091264, 'steps': 10891, 'loss/train': 2.153796434402466} 08/30/2021 15:06:14 - INFO - __main__ - Step 10893: {'lr': 0.0004955598720986551, 'samples': 2091456, 'steps': 10892, 'loss/train': 1.9644924402236938} 08/30/2021 15:06:16 - INFO - __main__ - Step 10894: {'lr': 0.0004955588763308223, 'samples': 2091648, 'steps': 10893, 'loss/train': 1.9918394088745117} 08/30/2021 15:06:16 - INFO - __main__ - Step 10895: {'lr': 0.0004955578804523445, 'samples': 2091840, 'steps': 10894, 'loss/train': 1.637222170829773} 08/30/2021 15:06:16 - INFO - __main__ - Step 10896: {'lr': 0.000495556884463222, 'samples': 2092032, 'steps': 10895, 'loss/train': 1.9392727613449097} 08/30/2021 15:06:17 - INFO - __main__ - Step 10897: {'lr': 0.0004955558883634555, 'samples': 2092224, 'steps': 10896, 'loss/train': 1.738175392150879} 08/30/2021 15:06:17 - INFO - __main__ - Step 10898: {'lr': 0.0004955548921530452, 'samples': 2092416, 'steps': 10897, 'loss/train': 1.5670162439346313} 08/30/2021 15:06:19 - INFO - __main__ - Step 10899: {'lr': 0.0004955538958319917, 'samples': 2092608, 'steps': 10898, 'loss/train': 1.8713189363479614} 08/30/2021 15:06:19 - INFO - __main__ - Step 10900: {'lr': 0.0004955528994002954, 'samples': 2092800, 'steps': 10899, 'loss/train': 0.1321968138217926} 08/30/2021 15:06:20 - INFO - __main__ - Step 10901: {'lr': 0.0004955519028579568, 'samples': 2092992, 'steps': 10900, 'loss/train': 1.6792168617248535} 08/30/2021 15:06:20 - INFO - __main__ - Step 10902: {'lr': 0.0004955509062049763, 'samples': 2093184, 'steps': 10901, 'loss/train': 1.908568263053894} 08/30/2021 15:06:20 - INFO - __main__ - Step 10903: {'lr': 0.0004955499094413542, 'samples': 2093376, 'steps': 10902, 'loss/train': 1.5589418411254883} 08/30/2021 15:06:22 - INFO - __main__ - Step 10904: {'lr': 0.0004955489125670912, 'samples': 2093568, 'steps': 10903, 'loss/train': 1.966796875} 08/30/2021 15:06:23 - INFO - __main__ - Step 10905: {'lr': 0.0004955479155821877, 'samples': 2093760, 'steps': 10904, 'loss/train': 1.5975741147994995} 08/30/2021 15:06:23 - INFO - __main__ - Step 10906: {'lr': 0.000495546918486644, 'samples': 2093952, 'steps': 10905, 'loss/train': 2.3270199298858643} 08/30/2021 15:06:23 - INFO - __main__ - Step 10907: {'lr': 0.0004955459212804607, 'samples': 2094144, 'steps': 10906, 'loss/train': 1.711856484413147} 08/30/2021 15:06:24 - INFO - __main__ - Step 10908: {'lr': 0.0004955449239636382, 'samples': 2094336, 'steps': 10907, 'loss/train': 0.9151084423065186} 08/30/2021 15:06:24 - INFO - __main__ - Step 10909: {'lr': 0.000495543926536177, 'samples': 2094528, 'steps': 10908, 'loss/train': 0.19393007457256317} 08/30/2021 15:06:26 - INFO - __main__ - Step 10910: {'lr': 0.0004955429289980774, 'samples': 2094720, 'steps': 10909, 'loss/train': 1.8715108633041382} 08/30/2021 15:06:26 - INFO - __main__ - Step 10911: {'lr': 0.00049554193134934, 'samples': 2094912, 'steps': 10910, 'loss/train': 1.3734896183013916} 08/30/2021 15:06:26 - INFO - __main__ - Step 10912: {'lr': 0.0004955409335899651, 'samples': 2095104, 'steps': 10911, 'loss/train': 1.781131625175476} 08/30/2021 15:06:27 - INFO - __main__ - Step 10913: {'lr': 0.0004955399357199534, 'samples': 2095296, 'steps': 10912, 'loss/train': 1.7393033504486084} 08/30/2021 15:06:27 - INFO - __main__ - Step 10914: {'lr': 0.0004955389377393051, 'samples': 2095488, 'steps': 10913, 'loss/train': 1.8202251195907593} 08/30/2021 15:06:29 - INFO - __main__ - Step 10915: {'lr': 0.0004955379396480207, 'samples': 2095680, 'steps': 10914, 'loss/train': 1.7318600416183472} 08/30/2021 15:06:29 - INFO - __main__ - Step 10916: {'lr': 0.0004955369414461007, 'samples': 2095872, 'steps': 10915, 'loss/train': 1.7824913263320923} 08/30/2021 15:06:29 - INFO - __main__ - Step 10917: {'lr': 0.0004955359431335456, 'samples': 2096064, 'steps': 10916, 'loss/train': 1.9956517219543457} 08/30/2021 15:06:30 - INFO - __main__ - Step 10918: {'lr': 0.0004955349447103559, 'samples': 2096256, 'steps': 10917, 'loss/train': 1.4670724868774414} 08/30/2021 15:06:30 - INFO - __main__ - Step 10919: {'lr': 0.0004955339461765318, 'samples': 2096448, 'steps': 10918, 'loss/train': 1.981136441230774} 08/30/2021 15:06:31 - INFO - __main__ - Step 10920: {'lr': 0.0004955329475320739, 'samples': 2096640, 'steps': 10919, 'loss/train': 1.8170489072799683} 08/30/2021 15:06:32 - INFO - __main__ - Step 10921: {'lr': 0.0004955319487769827, 'samples': 2096832, 'steps': 10920, 'loss/train': 1.0184874534606934} 08/30/2021 15:06:33 - INFO - __main__ - Step 10922: {'lr': 0.0004955309499112586, 'samples': 2097024, 'steps': 10921, 'loss/train': 1.5790601968765259} 08/30/2021 15:06:33 - INFO - __main__ - Step 10923: {'lr': 0.000495529950934902, 'samples': 2097216, 'steps': 10922, 'loss/train': 0.7173398733139038} 08/30/2021 15:06:34 - INFO - __main__ - Step 10924: {'lr': 0.0004955289518479134, 'samples': 2097408, 'steps': 10923, 'loss/train': 0.11908797174692154} 08/30/2021 15:06:34 - INFO - __main__ - Step 10925: {'lr': 0.0004955279526502931, 'samples': 2097600, 'steps': 10924, 'loss/train': 1.7190030813217163} 08/30/2021 15:06:34 - INFO - __main__ - Step 10926: {'lr': 0.0004955269533420419, 'samples': 2097792, 'steps': 10925, 'loss/train': 1.594948172569275} 08/30/2021 15:06:36 - INFO - __main__ - Step 10927: {'lr': 0.00049552595392316, 'samples': 2097984, 'steps': 10926, 'loss/train': 1.4549708366394043} 08/30/2021 15:06:36 - INFO - __main__ - Step 10928: {'lr': 0.0004955249543936479, 'samples': 2098176, 'steps': 10927, 'loss/train': 1.8931047916412354} 08/30/2021 15:06:37 - INFO - __main__ - Step 10929: {'lr': 0.000495523954753506, 'samples': 2098368, 'steps': 10928, 'loss/train': 1.5164992809295654} 08/30/2021 15:06:37 - INFO - __main__ - Step 10930: {'lr': 0.0004955229550027347, 'samples': 2098560, 'steps': 10929, 'loss/train': 1.9918193817138672} 08/30/2021 15:06:37 - INFO - __main__ - Step 10931: {'lr': 0.0004955219551413347, 'samples': 2098752, 'steps': 10930, 'loss/train': 1.8009387254714966} 08/30/2021 15:06:39 - INFO - __main__ - Step 10932: {'lr': 0.0004955209551693063, 'samples': 2098944, 'steps': 10931, 'loss/train': 1.9979090690612793} 08/30/2021 15:06:39 - INFO - __main__ - Step 10933: {'lr': 0.0004955199550866498, 'samples': 2099136, 'steps': 10932, 'loss/train': 1.3799176216125488} 08/30/2021 15:06:40 - INFO - __main__ - Step 10934: {'lr': 0.000495518954893366, 'samples': 2099328, 'steps': 10933, 'loss/train': 2.3226423263549805} 08/30/2021 15:06:40 - INFO - __main__ - Step 10935: {'lr': 0.000495517954589455, 'samples': 2099520, 'steps': 10934, 'loss/train': 1.6888556480407715} 08/30/2021 15:06:40 - INFO - __main__ - Step 10936: {'lr': 0.0004955169541749173, 'samples': 2099712, 'steps': 10935, 'loss/train': 1.7350400686264038} 08/30/2021 15:06:42 - INFO - __main__ - Step 10937: {'lr': 0.0004955159536497536, 'samples': 2099904, 'steps': 10936, 'loss/train': 1.9043257236480713} 08/30/2021 15:06:42 - INFO - __main__ - Step 10938: {'lr': 0.0004955149530139643, 'samples': 2100096, 'steps': 10937, 'loss/train': 1.8911716938018799} 08/30/2021 15:06:43 - INFO - __main__ - Step 10939: {'lr': 0.0004955139522675496, 'samples': 2100288, 'steps': 10938, 'loss/train': 1.575310468673706} 08/30/2021 15:06:43 - INFO - __main__ - Step 10940: {'lr': 0.0004955129514105101, 'samples': 2100480, 'steps': 10939, 'loss/train': 2.421666383743286} 08/30/2021 15:06:43 - INFO - __main__ - Step 10941: {'lr': 0.0004955119504428464, 'samples': 2100672, 'steps': 10940, 'loss/train': 1.5355712175369263} 08/30/2021 15:06:45 - INFO - __main__ - Step 10942: {'lr': 0.0004955109493645587, 'samples': 2100864, 'steps': 10941, 'loss/train': 1.5693624019622803} 08/30/2021 15:06:46 - INFO - __main__ - Step 10943: {'lr': 0.0004955099481756475, 'samples': 2101056, 'steps': 10942, 'loss/train': 2.2295072078704834} 08/30/2021 15:06:46 - INFO - __main__ - Step 10944: {'lr': 0.0004955089468761133, 'samples': 2101248, 'steps': 10943, 'loss/train': 2.020923614501953} 08/30/2021 15:06:47 - INFO - __main__ - Step 10945: {'lr': 0.0004955079454659567, 'samples': 2101440, 'steps': 10944, 'loss/train': 1.5080363750457764} 08/30/2021 15:06:47 - INFO - __main__ - Step 10946: {'lr': 0.0004955069439451778, 'samples': 2101632, 'steps': 10945, 'loss/train': 1.6412315368652344} 08/30/2021 15:06:48 - INFO - __main__ - Step 10947: {'lr': 0.0004955059423137774, 'samples': 2101824, 'steps': 10946, 'loss/train': 2.3839101791381836} 08/30/2021 15:06:49 - INFO - __main__ - Step 10948: {'lr': 0.0004955049405717558, 'samples': 2102016, 'steps': 10947, 'loss/train': 1.5545134544372559} 08/30/2021 15:06:49 - INFO - __main__ - Step 10949: {'lr': 0.0004955039387191135, 'samples': 2102208, 'steps': 10948, 'loss/train': 2.256082773208618} 08/30/2021 15:06:50 - INFO - __main__ - Step 10950: {'lr': 0.0004955029367558508, 'samples': 2102400, 'steps': 10949, 'loss/train': 2.0131309032440186} 08/30/2021 15:06:50 - INFO - __main__ - Step 10951: {'lr': 0.0004955019346819684, 'samples': 2102592, 'steps': 10950, 'loss/train': 1.2138655185699463} 08/30/2021 15:06:52 - INFO - __main__ - Step 10952: {'lr': 0.0004955009324974666, 'samples': 2102784, 'steps': 10951, 'loss/train': 1.7613660097122192} 08/30/2021 15:06:53 - INFO - __main__ - Step 10953: {'lr': 0.0004954999302023458, 'samples': 2102976, 'steps': 10952, 'loss/train': 2.2590949535369873} 08/30/2021 15:06:53 - INFO - __main__ - Step 10954: {'lr': 0.0004954989277966064, 'samples': 2103168, 'steps': 10953, 'loss/train': 0.3394987881183624} 08/30/2021 15:06:53 - INFO - __main__ - Step 10955: {'lr': 0.0004954979252802491, 'samples': 2103360, 'steps': 10954, 'loss/train': 1.7576954364776611} 08/30/2021 15:06:54 - INFO - __main__ - Step 10956: {'lr': 0.0004954969226532743, 'samples': 2103552, 'steps': 10955, 'loss/train': 2.596856117248535} 08/30/2021 15:06:54 - INFO - __main__ - Step 10957: {'lr': 0.0004954959199156824, 'samples': 2103744, 'steps': 10956, 'loss/train': 2.258389472961426} 08/30/2021 15:06:54 - INFO - __main__ - Step 10958: {'lr': 0.0004954949170674736, 'samples': 2103936, 'steps': 10957, 'loss/train': 1.8016879558563232} 08/30/2021 15:06:56 - INFO - __main__ - Step 10959: {'lr': 0.0004954939141086488, 'samples': 2104128, 'steps': 10958, 'loss/train': 1.6330764293670654} 08/30/2021 15:06:56 - INFO - __main__ - Step 10960: {'lr': 0.0004954929110392081, 'samples': 2104320, 'steps': 10959, 'loss/train': 1.2186224460601807} 08/30/2021 15:06:57 - INFO - __main__ - Step 10961: {'lr': 0.0004954919078591521, 'samples': 2104512, 'steps': 10960, 'loss/train': 1.5763354301452637} 08/30/2021 15:06:57 - INFO - __main__ - Step 10962: {'lr': 0.0004954909045684812, 'samples': 2104704, 'steps': 10961, 'loss/train': 2.034541130065918} 08/30/2021 15:06:58 - INFO - __main__ - Step 10963: {'lr': 0.000495489901167196, 'samples': 2104896, 'steps': 10962, 'loss/train': 1.691429615020752} 08/30/2021 15:06:59 - INFO - __main__ - Step 10964: {'lr': 0.0004954888976552968, 'samples': 2105088, 'steps': 10963, 'loss/train': 1.9321132898330688} 08/30/2021 15:07:00 - INFO - __main__ - Step 10965: {'lr': 0.0004954878940327841, 'samples': 2105280, 'steps': 10964, 'loss/train': 2.259718418121338} 08/30/2021 15:07:00 - INFO - __main__ - Step 10966: {'lr': 0.0004954868902996582, 'samples': 2105472, 'steps': 10965, 'loss/train': 2.1547393798828125} 08/30/2021 15:07:00 - INFO - __main__ - Step 10967: {'lr': 0.0004954858864559199, 'samples': 2105664, 'steps': 10966, 'loss/train': 1.9617149829864502} 08/30/2021 15:07:01 - INFO - __main__ - Step 10968: {'lr': 0.0004954848825015694, 'samples': 2105856, 'steps': 10967, 'loss/train': 1.6756328344345093} 08/30/2021 15:07:02 - INFO - __main__ - Step 10969: {'lr': 0.0004954838784366071, 'samples': 2106048, 'steps': 10968, 'loss/train': 0.9359736442565918} 08/30/2021 15:07:02 - INFO - __main__ - Step 10970: {'lr': 0.0004954828742610336, 'samples': 2106240, 'steps': 10969, 'loss/train': 2.3840291500091553} 08/30/2021 15:07:03 - INFO - __main__ - Step 10971: {'lr': 0.0004954818699748493, 'samples': 2106432, 'steps': 10970, 'loss/train': 1.601196527481079} 08/30/2021 15:07:03 - INFO - __main__ - Step 10972: {'lr': 0.0004954808655780546, 'samples': 2106624, 'steps': 10971, 'loss/train': 1.8679625988006592} 08/30/2021 15:07:03 - INFO - __main__ - Step 10973: {'lr': 0.0004954798610706502, 'samples': 2106816, 'steps': 10972, 'loss/train': 1.8949376344680786} 08/30/2021 15:07:04 - INFO - __main__ - Step 10974: {'lr': 0.0004954788564526362, 'samples': 2107008, 'steps': 10973, 'loss/train': 1.9796686172485352} 08/30/2021 15:07:05 - INFO - __main__ - Step 10975: {'lr': 0.0004954778517240133, 'samples': 2107200, 'steps': 10974, 'loss/train': 1.6100986003875732} 08/30/2021 15:07:06 - INFO - __main__ - Step 10976: {'lr': 0.0004954768468847818, 'samples': 2107392, 'steps': 10975, 'loss/train': 1.5986541509628296} 08/30/2021 15:07:06 - INFO - __main__ - Step 10977: {'lr': 0.0004954758419349422, 'samples': 2107584, 'steps': 10976, 'loss/train': 2.278153896331787} 08/30/2021 15:07:07 - INFO - __main__ - Step 10978: {'lr': 0.000495474836874495, 'samples': 2107776, 'steps': 10977, 'loss/train': 1.215874433517456} 08/30/2021 15:07:07 - INFO - __main__ - Step 10979: {'lr': 0.0004954738317034408, 'samples': 2107968, 'steps': 10978, 'loss/train': 2.0640335083007812} 08/30/2021 15:07:08 - INFO - __main__ - Step 10980: {'lr': 0.0004954728264217796, 'samples': 2108160, 'steps': 10979, 'loss/train': 2.2727065086364746} 08/30/2021 15:07:09 - INFO - __main__ - Step 10981: {'lr': 0.0004954718210295123, 'samples': 2108352, 'steps': 10980, 'loss/train': 1.4322324991226196} 08/30/2021 15:07:09 - INFO - __main__ - Step 10982: {'lr': 0.0004954708155266392, 'samples': 2108544, 'steps': 10981, 'loss/train': 1.4696931838989258} 08/30/2021 15:07:09 - INFO - __main__ - Step 10983: {'lr': 0.0004954698099131606, 'samples': 2108736, 'steps': 10982, 'loss/train': 1.9921832084655762} 08/30/2021 15:07:10 - INFO - __main__ - Step 10984: {'lr': 0.0004954688041890772, 'samples': 2108928, 'steps': 10983, 'loss/train': 1.360575795173645} 08/30/2021 15:07:12 - INFO - __main__ - Step 10985: {'lr': 0.0004954677983543893, 'samples': 2109120, 'steps': 10984, 'loss/train': 1.0472240447998047} 08/30/2021 15:07:12 - INFO - __main__ - Step 10986: {'lr': 0.0004954667924090974, 'samples': 2109312, 'steps': 10985, 'loss/train': 2.046184778213501} 08/30/2021 15:07:13 - INFO - __main__ - Step 10987: {'lr': 0.000495465786353202, 'samples': 2109504, 'steps': 10986, 'loss/train': 0.4741063117980957} 08/30/2021 15:07:13 - INFO - __main__ - Step 10988: {'lr': 0.0004954647801867035, 'samples': 2109696, 'steps': 10987, 'loss/train': 1.2116178274154663} 08/30/2021 15:07:13 - INFO - __main__ - Step 10989: {'lr': 0.0004954637739096023, 'samples': 2109888, 'steps': 10988, 'loss/train': 1.4974844455718994} 08/30/2021 15:07:14 - INFO - __main__ - Step 10990: {'lr': 0.0004954627675218989, 'samples': 2110080, 'steps': 10989, 'loss/train': 0.41842901706695557} 08/30/2021 15:07:15 - INFO - __main__ - Step 10991: {'lr': 0.0004954617610235939, 'samples': 2110272, 'steps': 10990, 'loss/train': 0.5526917576789856} 08/30/2021 15:07:16 - INFO - __main__ - Step 10992: {'lr': 0.0004954607544146875, 'samples': 2110464, 'steps': 10991, 'loss/train': 1.8407448530197144} 08/30/2021 15:07:16 - INFO - __main__ - Step 10993: {'lr': 0.0004954597476951804, 'samples': 2110656, 'steps': 10992, 'loss/train': 2.113936185836792} 08/30/2021 15:07:16 - INFO - __main__ - Step 10994: {'lr': 0.0004954587408650727, 'samples': 2110848, 'steps': 10993, 'loss/train': 1.3653898239135742} 08/30/2021 15:07:17 - INFO - __main__ - Step 10995: {'lr': 0.0004954577339243652, 'samples': 2111040, 'steps': 10994, 'loss/train': 1.7567837238311768} 08/30/2021 15:07:19 - INFO - __main__ - Step 10996: {'lr': 0.0004954567268730582, 'samples': 2111232, 'steps': 10995, 'loss/train': 2.195679187774658} 08/30/2021 15:07:19 - INFO - __main__ - Step 10997: {'lr': 0.0004954557197111522, 'samples': 2111424, 'steps': 10996, 'loss/train': 1.7838292121887207} 08/30/2021 15:07:20 - INFO - __main__ - Step 10998: {'lr': 0.0004954547124386477, 'samples': 2111616, 'steps': 10997, 'loss/train': 1.5152627229690552} 08/30/2021 15:07:20 - INFO - __main__ - Step 10999: {'lr': 0.0004954537050555451, 'samples': 2111808, 'steps': 10998, 'loss/train': 1.8554701805114746} 08/30/2021 15:07:20 - INFO - __main__ - Step 11000: {'lr': 0.0004954526975618447, 'samples': 2112000, 'steps': 10999, 'loss/train': 2.9708855152130127} 08/30/2021 15:07:22 - INFO - __main__ - Step 11001: {'lr': 0.0004954516899575473, 'samples': 2112192, 'steps': 11000, 'loss/train': 2.17421817779541} 08/30/2021 15:07:22 - INFO - __main__ - Step 11002: {'lr': 0.000495450682242653, 'samples': 2112384, 'steps': 11001, 'loss/train': 1.5058897733688354} 08/30/2021 15:07:23 - INFO - __main__ - Step 11003: {'lr': 0.0004954496744171624, 'samples': 2112576, 'steps': 11002, 'loss/train': 1.8715373277664185} 08/30/2021 15:07:23 - INFO - __main__ - Step 11004: {'lr': 0.0004954486664810762, 'samples': 2112768, 'steps': 11003, 'loss/train': 1.563541054725647} 08/30/2021 15:07:23 - INFO - __main__ - Step 11005: {'lr': 0.0004954476584343945, 'samples': 2112960, 'steps': 11004, 'loss/train': 1.8025926351547241} 08/30/2021 15:07:24 - INFO - __main__ - Step 11006: {'lr': 0.0004954466502771178, 'samples': 2113152, 'steps': 11005, 'loss/train': 2.0239102840423584} 08/30/2021 15:07:25 - INFO - __main__ - Step 11007: {'lr': 0.0004954456420092466, 'samples': 2113344, 'steps': 11006, 'loss/train': 1.1946940422058105} 08/30/2021 15:07:26 - INFO - __main__ - Step 11008: {'lr': 0.0004954446336307814, 'samples': 2113536, 'steps': 11007, 'loss/train': 2.891005277633667} 08/30/2021 15:07:26 - INFO - __main__ - Step 11009: {'lr': 0.0004954436251417227, 'samples': 2113728, 'steps': 11008, 'loss/train': 2.0502946376800537} 08/30/2021 15:07:27 - INFO - __main__ - Step 11010: {'lr': 0.0004954426165420709, 'samples': 2113920, 'steps': 11009, 'loss/train': 2.938062906265259} 08/30/2021 15:07:27 - INFO - __main__ - Step 11011: {'lr': 0.0004954416078318263, 'samples': 2114112, 'steps': 11010, 'loss/train': 1.9612449407577515} 08/30/2021 15:07:29 - INFO - __main__ - Step 11012: {'lr': 0.0004954405990109897, 'samples': 2114304, 'steps': 11011, 'loss/train': 1.929292917251587} 08/30/2021 15:07:29 - INFO - __main__ - Step 11013: {'lr': 0.0004954395900795611, 'samples': 2114496, 'steps': 11012, 'loss/train': 1.0514862537384033} 08/30/2021 15:07:30 - INFO - __main__ - Step 11014: {'lr': 0.0004954385810375415, 'samples': 2114688, 'steps': 11013, 'loss/train': 1.8498998880386353} 08/30/2021 15:07:30 - INFO - __main__ - Step 11015: {'lr': 0.0004954375718849308, 'samples': 2114880, 'steps': 11014, 'loss/train': 1.6812744140625} 08/30/2021 15:07:30 - INFO - __main__ - Step 11016: {'lr': 0.0004954365626217299, 'samples': 2115072, 'steps': 11015, 'loss/train': 1.5532358884811401} 08/30/2021 15:07:31 - INFO - __main__ - Step 11017: {'lr': 0.0004954355532479391, 'samples': 2115264, 'steps': 11016, 'loss/train': 1.8510565757751465} 08/30/2021 15:07:32 - INFO - __main__ - Step 11018: {'lr': 0.0004954345437635587, 'samples': 2115456, 'steps': 11017, 'loss/train': 1.8996973037719727} 08/30/2021 15:07:33 - INFO - __main__ - Step 11019: {'lr': 0.0004954335341685893, 'samples': 2115648, 'steps': 11018, 'loss/train': 1.0813733339309692} 08/30/2021 15:07:33 - INFO - __main__ - Step 11020: {'lr': 0.0004954325244630315, 'samples': 2115840, 'steps': 11019, 'loss/train': 0.32894089818000793} 08/30/2021 15:07:33 - INFO - __main__ - Step 11021: {'lr': 0.0004954315146468854, 'samples': 2116032, 'steps': 11020, 'loss/train': 2.2050979137420654} 08/30/2021 15:07:34 - INFO - __main__ - Step 11022: {'lr': 0.0004954305047201517, 'samples': 2116224, 'steps': 11021, 'loss/train': 1.703669548034668} 08/30/2021 15:07:36 - INFO - __main__ - Step 11023: {'lr': 0.0004954294946828308, 'samples': 2116416, 'steps': 11022, 'loss/train': 1.627677083015442} 08/30/2021 15:07:36 - INFO - __main__ - Step 11024: {'lr': 0.0004954284845349232, 'samples': 2116608, 'steps': 11023, 'loss/train': 2.1991710662841797} 08/30/2021 15:07:36 - INFO - __main__ - Step 11025: {'lr': 0.0004954274742764292, 'samples': 2116800, 'steps': 11024, 'loss/train': 2.265136957168579} 08/30/2021 15:07:37 - INFO - __main__ - Step 11026: {'lr': 0.0004954264639073495, 'samples': 2116992, 'steps': 11025, 'loss/train': 1.7266194820404053} 08/30/2021 15:07:37 - INFO - __main__ - Step 11027: {'lr': 0.0004954254534276843, 'samples': 2117184, 'steps': 11026, 'loss/train': 1.9154466390609741} 08/30/2021 15:07:38 - INFO - __main__ - Step 11028: {'lr': 0.0004954244428374343, 'samples': 2117376, 'steps': 11027, 'loss/train': 2.7888379096984863} 08/30/2021 15:07:39 - INFO - __main__ - Step 11029: {'lr': 0.0004954234321365998, 'samples': 2117568, 'steps': 11028, 'loss/train': 2.136707305908203} 08/30/2021 15:07:39 - INFO - __main__ - Step 11030: {'lr': 0.0004954224213251813, 'samples': 2117760, 'steps': 11029, 'loss/train': 1.9650870561599731} 08/30/2021 15:07:40 - INFO - __main__ - Step 11031: {'lr': 0.0004954214104031791, 'samples': 2117952, 'steps': 11030, 'loss/train': 1.2592624425888062} 08/30/2021 15:07:40 - INFO - __main__ - Step 11032: {'lr': 0.0004954203993705939, 'samples': 2118144, 'steps': 11031, 'loss/train': 1.9525206089019775} 08/30/2021 15:07:40 - INFO - __main__ - Step 11033: {'lr': 0.0004954193882274261, 'samples': 2118336, 'steps': 11032, 'loss/train': 2.9623115062713623} 08/30/2021 15:07:42 - INFO - __main__ - Step 11034: {'lr': 0.000495418376973676, 'samples': 2118528, 'steps': 11033, 'loss/train': 1.8920893669128418} 08/30/2021 15:07:42 - INFO - __main__ - Step 11035: {'lr': 0.0004954173656093443, 'samples': 2118720, 'steps': 11034, 'loss/train': 2.404442071914673} 08/30/2021 15:07:43 - INFO - __main__ - Step 11036: {'lr': 0.0004954163541344312, 'samples': 2118912, 'steps': 11035, 'loss/train': 2.047079563140869} 08/30/2021 15:07:43 - INFO - __main__ - Step 11037: {'lr': 0.0004954153425489374, 'samples': 2119104, 'steps': 11036, 'loss/train': 1.9804679155349731} 08/30/2021 15:07:43 - INFO - __main__ - Step 11038: {'lr': 0.0004954143308528631, 'samples': 2119296, 'steps': 11037, 'loss/train': 1.642622947692871} 08/30/2021 15:07:45 - INFO - __main__ - Step 11039: {'lr': 0.000495413319046209, 'samples': 2119488, 'steps': 11038, 'loss/train': 1.897440791130066} 08/30/2021 15:07:45 - INFO - __main__ - Step 11040: {'lr': 0.0004954123071289754, 'samples': 2119680, 'steps': 11039, 'loss/train': 2.106625556945801} 08/30/2021 15:07:46 - INFO - __main__ - Step 11041: {'lr': 0.0004954112951011628, 'samples': 2119872, 'steps': 11040, 'loss/train': 2.0594820976257324} 08/30/2021 15:07:46 - INFO - __main__ - Step 11042: {'lr': 0.0004954102829627717, 'samples': 2120064, 'steps': 11041, 'loss/train': 2.2841925621032715} 08/30/2021 15:07:46 - INFO - __main__ - Step 11043: {'lr': 0.0004954092707138024, 'samples': 2120256, 'steps': 11042, 'loss/train': 1.6776620149612427} 08/30/2021 15:07:48 - INFO - __main__ - Step 11044: {'lr': 0.0004954082583542557, 'samples': 2120448, 'steps': 11043, 'loss/train': 1.779884934425354} 08/30/2021 15:07:48 - INFO - __main__ - Step 11045: {'lr': 0.0004954072458841315, 'samples': 2120640, 'steps': 11044, 'loss/train': 1.9558268785476685} 08/30/2021 15:07:49 - INFO - __main__ - Step 11046: {'lr': 0.0004954062333034308, 'samples': 2120832, 'steps': 11045, 'loss/train': 2.6233487129211426} 08/30/2021 15:07:49 - INFO - __main__ - Step 11047: {'lr': 0.0004954052206121538, 'samples': 2121024, 'steps': 11046, 'loss/train': 2.042098045349121} 08/30/2021 15:07:49 - INFO - __main__ - Step 11048: {'lr': 0.000495404207810301, 'samples': 2121216, 'steps': 11047, 'loss/train': 1.839972972869873} 08/30/2021 15:07:50 - INFO - __main__ - Step 11049: {'lr': 0.0004954031948978729, 'samples': 2121408, 'steps': 11048, 'loss/train': 1.4205790758132935} 08/30/2021 15:07:51 - INFO - __main__ - Step 11050: {'lr': 0.0004954021818748698, 'samples': 2121600, 'steps': 11049, 'loss/train': 2.023576259613037} 08/30/2021 15:07:52 - INFO - __main__ - Step 11051: {'lr': 0.0004954011687412923, 'samples': 2121792, 'steps': 11050, 'loss/train': 2.613823890686035} 08/30/2021 15:07:52 - INFO - __main__ - Step 11052: {'lr': 0.0004954001554971409, 'samples': 2121984, 'steps': 11051, 'loss/train': 1.4308427572250366} 08/30/2021 15:07:53 - INFO - __main__ - Step 11053: {'lr': 0.0004953991421424159, 'samples': 2122176, 'steps': 11052, 'loss/train': 2.029387950897217} 08/30/2021 15:07:53 - INFO - __main__ - Step 11054: {'lr': 0.0004953981286771178, 'samples': 2122368, 'steps': 11053, 'loss/train': 0.22284691035747528} 08/30/2021 15:07:54 - INFO - __main__ - Step 11055: {'lr': 0.0004953971151012471, 'samples': 2122560, 'steps': 11054, 'loss/train': 0.20293185114860535} 08/30/2021 15:07:55 - INFO - __main__ - Step 11056: {'lr': 0.0004953961014148043, 'samples': 2122752, 'steps': 11055, 'loss/train': 1.7698132991790771} 08/30/2021 15:07:56 - INFO - __main__ - Step 11057: {'lr': 0.0004953950876177897, 'samples': 2122944, 'steps': 11056, 'loss/train': 2.290742874145508} 08/30/2021 15:07:56 - INFO - __main__ - Step 11058: {'lr': 0.000495394073710204, 'samples': 2123136, 'steps': 11057, 'loss/train': 1.5787354707717896} 08/30/2021 15:07:57 - INFO - __main__ - Step 11059: {'lr': 0.0004953930596920474, 'samples': 2123328, 'steps': 11058, 'loss/train': 2.0530502796173096} 08/30/2021 15:07:57 - INFO - __main__ - Step 11060: {'lr': 0.0004953920455633206, 'samples': 2123520, 'steps': 11059, 'loss/train': 1.7764960527420044} 08/30/2021 15:07:59 - INFO - __main__ - Step 11061: {'lr': 0.0004953910313240239, 'samples': 2123712, 'steps': 11060, 'loss/train': 2.048180341720581} 08/30/2021 15:07:59 - INFO - __main__ - Step 11062: {'lr': 0.0004953900169741577, 'samples': 2123904, 'steps': 11061, 'loss/train': 1.8457850217819214} 08/30/2021 15:07:59 - INFO - __main__ - Step 11063: {'lr': 0.0004953890025137226, 'samples': 2124096, 'steps': 11062, 'loss/train': 2.0374860763549805} 08/30/2021 15:08:00 - INFO - __main__ - Step 11064: {'lr': 0.000495387987942719, 'samples': 2124288, 'steps': 11063, 'loss/train': 1.988455891609192} 08/30/2021 15:08:00 - INFO - __main__ - Step 11065: {'lr': 0.0004953869732611474, 'samples': 2124480, 'steps': 11064, 'loss/train': 2.169694662094116} 08/30/2021 15:08:02 - INFO - __main__ - Step 11066: {'lr': 0.0004953859584690081, 'samples': 2124672, 'steps': 11065, 'loss/train': 2.019395589828491} 08/30/2021 15:08:02 - INFO - __main__ - Step 11067: {'lr': 0.0004953849435663018, 'samples': 2124864, 'steps': 11066, 'loss/train': 2.0245816707611084} 08/30/2021 15:08:02 - INFO - __main__ - Step 11068: {'lr': 0.0004953839285530287, 'samples': 2125056, 'steps': 11067, 'loss/train': 1.5807219743728638} 08/30/2021 15:08:03 - INFO - __main__ - Step 11069: {'lr': 0.0004953829134291895, 'samples': 2125248, 'steps': 11068, 'loss/train': 2.100602388381958} 08/30/2021 15:08:03 - INFO - __main__ - Step 11070: {'lr': 0.0004953818981947845, 'samples': 2125440, 'steps': 11069, 'loss/train': 2.384111166000366} 08/30/2021 15:08:05 - INFO - __main__ - Step 11071: {'lr': 0.0004953808828498142, 'samples': 2125632, 'steps': 11070, 'loss/train': 1.9089192152023315} 08/30/2021 15:08:05 - INFO - __main__ - Step 11072: {'lr': 0.0004953798673942791, 'samples': 2125824, 'steps': 11071, 'loss/train': 1.695746660232544} 08/30/2021 15:08:05 - INFO - __main__ - Step 11073: {'lr': 0.0004953788518281796, 'samples': 2126016, 'steps': 11072, 'loss/train': 2.089404821395874} 08/30/2021 15:08:06 - INFO - __main__ - Step 11074: {'lr': 0.0004953778361515163, 'samples': 2126208, 'steps': 11073, 'loss/train': 0.22820700705051422} 08/30/2021 15:08:06 - INFO - __main__ - Step 11075: {'lr': 0.0004953768203642893, 'samples': 2126400, 'steps': 11074, 'loss/train': 2.138831377029419} 08/30/2021 15:08:08 - INFO - __main__ - Step 11076: {'lr': 0.0004953758044664994, 'samples': 2126592, 'steps': 11075, 'loss/train': 2.0137264728546143} 08/30/2021 15:08:09 - INFO - __main__ - Step 11077: {'lr': 0.0004953747884581469, 'samples': 2126784, 'steps': 11076, 'loss/train': 1.7807413339614868} 08/30/2021 15:08:09 - INFO - __main__ - Step 11078: {'lr': 0.0004953737723392324, 'samples': 2126976, 'steps': 11077, 'loss/train': 1.8768905401229858} 08/30/2021 15:08:09 - INFO - __main__ - Step 11079: {'lr': 0.0004953727561097562, 'samples': 2127168, 'steps': 11078, 'loss/train': 0.15849746763706207} 08/30/2021 15:08:10 - INFO - __main__ - Step 11080: {'lr': 0.0004953717397697189, 'samples': 2127360, 'steps': 11079, 'loss/train': 2.526132583618164} 08/30/2021 15:08:10 - INFO - __main__ - Step 11081: {'lr': 0.0004953707233191207, 'samples': 2127552, 'steps': 11080, 'loss/train': 1.420319676399231} 08/30/2021 15:08:11 - INFO - __main__ - Step 11082: {'lr': 0.0004953697067579624, 'samples': 2127744, 'steps': 11081, 'loss/train': 0.12702490389347076} 08/30/2021 15:08:12 - INFO - __main__ - Step 11083: {'lr': 0.0004953686900862442, 'samples': 2127936, 'steps': 11082, 'loss/train': 1.7738608121871948} 08/30/2021 15:08:12 - INFO - __main__ - Step 11084: {'lr': 0.0004953676733039668, 'samples': 2128128, 'steps': 11083, 'loss/train': 1.782198190689087} 08/30/2021 15:08:13 - INFO - __main__ - Step 11085: {'lr': 0.0004953666564111303, 'samples': 2128320, 'steps': 11084, 'loss/train': 1.7017955780029297} 08/30/2021 15:08:13 - INFO - __main__ - Step 11086: {'lr': 0.0004953656394077355, 'samples': 2128512, 'steps': 11085, 'loss/train': 1.9793652296066284} 08/30/2021 15:08:13 - INFO - __main__ - Step 11087: {'lr': 0.0004953646222937828, 'samples': 2128704, 'steps': 11086, 'loss/train': 1.6664254665374756} 08/30/2021 15:08:15 - INFO - __main__ - Step 11088: {'lr': 0.0004953636050692724, 'samples': 2128896, 'steps': 11087, 'loss/train': 2.2110068798065186} 08/30/2021 15:08:15 - INFO - __main__ - Step 11089: {'lr': 0.0004953625877342051, 'samples': 2129088, 'steps': 11088, 'loss/train': 1.5275801420211792} 08/30/2021 15:08:16 - INFO - __main__ - Step 11090: {'lr': 0.0004953615702885812, 'samples': 2129280, 'steps': 11089, 'loss/train': 2.0113110542297363} 08/30/2021 15:08:16 - INFO - __main__ - Step 11091: {'lr': 0.0004953605527324011, 'samples': 2129472, 'steps': 11090, 'loss/train': 1.7620744705200195} 08/30/2021 15:08:16 - INFO - __main__ - Step 11092: {'lr': 0.0004953595350656653, 'samples': 2129664, 'steps': 11091, 'loss/train': 1.4105721712112427} 08/30/2021 15:08:18 - INFO - __main__ - Step 11093: {'lr': 0.0004953585172883743, 'samples': 2129856, 'steps': 11092, 'loss/train': 2.1221680641174316} 08/30/2021 15:08:19 - INFO - __main__ - Step 11094: {'lr': 0.0004953574994005286, 'samples': 2130048, 'steps': 11093, 'loss/train': 2.283801317214966} 08/30/2021 15:08:19 - INFO - __main__ - Step 11095: {'lr': 0.0004953564814021285, 'samples': 2130240, 'steps': 11094, 'loss/train': 2.1612584590911865} 08/30/2021 15:08:19 - INFO - __main__ - Step 11096: {'lr': 0.0004953554632931746, 'samples': 2130432, 'steps': 11095, 'loss/train': 2.52555775642395} 08/30/2021 15:08:20 - INFO - __main__ - Step 11097: {'lr': 0.0004953544450736674, 'samples': 2130624, 'steps': 11096, 'loss/train': 1.6636079549789429} 08/30/2021 15:08:21 - INFO - __main__ - Step 11098: {'lr': 0.0004953534267436072, 'samples': 2130816, 'steps': 11097, 'loss/train': 2.2485923767089844} 08/30/2021 15:08:22 - INFO - __main__ - Step 11099: {'lr': 0.0004953524083029945, 'samples': 2131008, 'steps': 11098, 'loss/train': 1.338276743888855} 08/30/2021 15:08:22 - INFO - __main__ - Step 11100: {'lr': 0.0004953513897518298, 'samples': 2131200, 'steps': 11099, 'loss/train': 2.069579601287842} 08/30/2021 15:08:22 - INFO - __main__ - Step 11101: {'lr': 0.0004953503710901136, 'samples': 2131392, 'steps': 11100, 'loss/train': 1.864101767539978} 08/30/2021 15:08:23 - INFO - __main__ - Step 11102: {'lr': 0.0004953493523178463, 'samples': 2131584, 'steps': 11101, 'loss/train': 1.582018256187439} 08/30/2021 15:08:24 - INFO - __main__ - Step 11103: {'lr': 0.0004953483334350283, 'samples': 2131776, 'steps': 11102, 'loss/train': 1.651454210281372} 08/30/2021 15:08:25 - INFO - __main__ - Step 11104: {'lr': 0.0004953473144416602, 'samples': 2131968, 'steps': 11103, 'loss/train': 1.8541146516799927} 08/30/2021 15:08:25 - INFO - __main__ - Step 11105: {'lr': 0.0004953462953377424, 'samples': 2132160, 'steps': 11104, 'loss/train': 1.8567306995391846} 08/30/2021 15:08:25 - INFO - __main__ - Step 11106: {'lr': 0.0004953452761232753, 'samples': 2132352, 'steps': 11105, 'loss/train': 2.2671186923980713} 08/30/2021 15:08:26 - INFO - __main__ - Step 11107: {'lr': 0.0004953442567982593, 'samples': 2132544, 'steps': 11106, 'loss/train': 1.8087079524993896} 08/30/2021 15:08:28 - INFO - __main__ - Step 11108: {'lr': 0.0004953432373626951, 'samples': 2132736, 'steps': 11107, 'loss/train': 1.1706079244613647} 08/30/2021 15:08:29 - INFO - __main__ - Step 11109: {'lr': 0.0004953422178165831, 'samples': 2132928, 'steps': 11108, 'loss/train': 1.936245322227478} 08/30/2021 15:08:29 - INFO - __main__ - Step 11110: {'lr': 0.0004953411981599235, 'samples': 2133120, 'steps': 11109, 'loss/train': 1.7550830841064453} 08/30/2021 15:08:29 - INFO - __main__ - Step 11111: {'lr': 0.0004953401783927171, 'samples': 2133312, 'steps': 11110, 'loss/train': 1.4070396423339844} 08/30/2021 15:08:30 - INFO - __main__ - Step 11112: {'lr': 0.000495339158514964, 'samples': 2133504, 'steps': 11111, 'loss/train': 0.23815692961215973} 08/30/2021 15:08:30 - INFO - __main__ - Step 11113: {'lr': 0.0004953381385266651, 'samples': 2133696, 'steps': 11112, 'loss/train': 1.2586719989776611} 08/30/2021 15:08:31 - INFO - __main__ - Step 11114: {'lr': 0.0004953371184278205, 'samples': 2133888, 'steps': 11113, 'loss/train': 1.926695466041565} 08/30/2021 15:08:32 - INFO - __main__ - Step 11115: {'lr': 0.0004953360982184308, 'samples': 2134080, 'steps': 11114, 'loss/train': 1.8673443794250488} 08/30/2021 15:08:32 - INFO - __main__ - Step 11116: {'lr': 0.0004953350778984963, 'samples': 2134272, 'steps': 11115, 'loss/train': 1.7017509937286377} 08/30/2021 15:08:33 - INFO - __main__ - Step 11117: {'lr': 0.0004953340574680177, 'samples': 2134464, 'steps': 11116, 'loss/train': 2.141362428665161} 08/30/2021 15:08:33 - INFO - __main__ - Step 11118: {'lr': 0.0004953330369269955, 'samples': 2134656, 'steps': 11117, 'loss/train': 1.6088838577270508} 08/30/2021 15:08:35 - INFO - __main__ - Step 11119: {'lr': 0.0004953320162754298, 'samples': 2134848, 'steps': 11118, 'loss/train': 0.1882239282131195} 08/30/2021 15:08:35 - INFO - __main__ - Step 11120: {'lr': 0.0004953309955133214, 'samples': 2135040, 'steps': 11119, 'loss/train': 1.9355123043060303} 08/30/2021 15:08:35 - INFO - __main__ - Step 11121: {'lr': 0.0004953299746406707, 'samples': 2135232, 'steps': 11120, 'loss/train': 1.5760687589645386} 08/30/2021 15:08:36 - INFO - __main__ - Step 11122: {'lr': 0.000495328953657478, 'samples': 2135424, 'steps': 11121, 'loss/train': 0.14006000757217407} 08/30/2021 15:08:36 - INFO - __main__ - Step 11123: {'lr': 0.0004953279325637438, 'samples': 2135616, 'steps': 11122, 'loss/train': 1.6309653520584106} 08/30/2021 15:08:38 - INFO - __main__ - Step 11124: {'lr': 0.0004953269113594687, 'samples': 2135808, 'steps': 11123, 'loss/train': 1.455532193183899} 08/30/2021 15:08:38 - INFO - __main__ - Step 11125: {'lr': 0.0004953258900446531, 'samples': 2136000, 'steps': 11124, 'loss/train': 2.2158398628234863} 08/30/2021 15:08:38 - INFO - __main__ - Step 11126: {'lr': 0.0004953248686192975, 'samples': 2136192, 'steps': 11125, 'loss/train': 1.9556537866592407} 08/30/2021 15:08:39 - INFO - __main__ - Step 11127: {'lr': 0.0004953238470834022, 'samples': 2136384, 'steps': 11126, 'loss/train': 1.7583212852478027} 08/30/2021 15:08:39 - INFO - __main__ - Step 11128: {'lr': 0.0004953228254369677, 'samples': 2136576, 'steps': 11127, 'loss/train': 1.7490719556808472} 08/30/2021 15:08:41 - INFO - __main__ - Step 11129: {'lr': 0.0004953218036799946, 'samples': 2136768, 'steps': 11128, 'loss/train': 1.490636944770813} 08/30/2021 15:08:41 - INFO - __main__ - Step 11130: {'lr': 0.0004953207818124833, 'samples': 2136960, 'steps': 11129, 'loss/train': 2.097973108291626} 08/30/2021 15:08:41 - INFO - __main__ - Step 11131: {'lr': 0.0004953197598344342, 'samples': 2137152, 'steps': 11130, 'loss/train': 2.425636053085327} 08/30/2021 15:08:42 - INFO - __main__ - Step 11132: {'lr': 0.0004953187377458478, 'samples': 2137344, 'steps': 11131, 'loss/train': 1.5264713764190674} 08/30/2021 15:08:42 - INFO - __main__ - Step 11133: {'lr': 0.0004953177155467246, 'samples': 2137536, 'steps': 11132, 'loss/train': 1.6516380310058594} 08/30/2021 15:08:44 - INFO - __main__ - Step 11134: {'lr': 0.0004953166932370651, 'samples': 2137728, 'steps': 11133, 'loss/train': 1.5329843759536743} 08/30/2021 15:08:44 - INFO - __main__ - Step 11135: {'lr': 0.0004953156708168695, 'samples': 2137920, 'steps': 11134, 'loss/train': 1.7588341236114502} 08/30/2021 15:08:44 - INFO - __main__ - Step 11136: {'lr': 0.0004953146482861385, 'samples': 2138112, 'steps': 11135, 'loss/train': 2.2730307579040527} 08/30/2021 15:08:45 - INFO - __main__ - Step 11137: {'lr': 0.0004953136256448725, 'samples': 2138304, 'steps': 11136, 'loss/train': 1.6751506328582764} 08/30/2021 15:08:45 - INFO - __main__ - Step 11138: {'lr': 0.0004953126028930721, 'samples': 2138496, 'steps': 11137, 'loss/train': 1.8939454555511475} 08/30/2021 15:08:45 - INFO - __main__ - Step 11139: {'lr': 0.0004953115800307375, 'samples': 2138688, 'steps': 11138, 'loss/train': 1.992057204246521} 08/30/2021 15:08:47 - INFO - __main__ - Step 11140: {'lr': 0.0004953105570578693, 'samples': 2138880, 'steps': 11139, 'loss/train': 1.5404541492462158} 08/30/2021 15:08:47 - INFO - __main__ - Step 11141: {'lr': 0.000495309533974468, 'samples': 2139072, 'steps': 11140, 'loss/train': 1.944646954536438} 08/30/2021 15:08:48 - INFO - __main__ - Step 11142: {'lr': 0.0004953085107805339, 'samples': 2139264, 'steps': 11141, 'loss/train': 1.9030653238296509} 08/30/2021 15:08:48 - INFO - __main__ - Step 11143: {'lr': 0.0004953074874760677, 'samples': 2139456, 'steps': 11142, 'loss/train': 2.5180866718292236} 08/30/2021 15:08:48 - INFO - __main__ - Step 11144: {'lr': 0.0004953064640610697, 'samples': 2139648, 'steps': 11143, 'loss/train': 1.5613799095153809} 08/30/2021 15:08:50 - INFO - __main__ - Step 11145: {'lr': 0.0004953054405355404, 'samples': 2139840, 'steps': 11144, 'loss/train': 1.4012560844421387} 08/30/2021 15:08:51 - INFO - __main__ - Step 11146: {'lr': 0.0004953044168994802, 'samples': 2140032, 'steps': 11145, 'loss/train': 0.13021203875541687} 08/30/2021 15:08:51 - INFO - __main__ - Step 11147: {'lr': 0.0004953033931528897, 'samples': 2140224, 'steps': 11146, 'loss/train': 1.2138471603393555} 08/30/2021 15:08:51 - INFO - __main__ - Step 11148: {'lr': 0.0004953023692957691, 'samples': 2140416, 'steps': 11147, 'loss/train': 1.539682149887085} 08/30/2021 15:08:52 - INFO - __main__ - Step 11149: {'lr': 0.0004953013453281193, 'samples': 2140608, 'steps': 11148, 'loss/train': 2.223832845687866} 08/30/2021 15:08:53 - INFO - __main__ - Step 11150: {'lr': 0.0004953003212499403, 'samples': 2140800, 'steps': 11149, 'loss/train': 2.070180654525757} 08/30/2021 15:08:54 - INFO - __main__ - Step 11151: {'lr': 0.0004952992970612328, 'samples': 2140992, 'steps': 11150, 'loss/train': 2.378373146057129} 08/30/2021 15:08:54 - INFO - __main__ - Step 11152: {'lr': 0.0004952982727619973, 'samples': 2141184, 'steps': 11151, 'loss/train': 2.1110410690307617} 08/30/2021 15:08:54 - INFO - __main__ - Step 11153: {'lr': 0.000495297248352234, 'samples': 2141376, 'steps': 11152, 'loss/train': 1.975611686706543} 08/30/2021 15:08:55 - INFO - __main__ - Step 11154: {'lr': 0.0004952962238319436, 'samples': 2141568, 'steps': 11153, 'loss/train': 1.8950594663619995} 08/30/2021 15:08:57 - INFO - __main__ - Step 11155: {'lr': 0.0004952951992011266, 'samples': 2141760, 'steps': 11154, 'loss/train': 1.828566074371338} 08/30/2021 15:08:58 - INFO - __main__ - Step 11156: {'lr': 0.0004952941744597834, 'samples': 2141952, 'steps': 11155, 'loss/train': 2.4585282802581787} 08/30/2021 15:08:58 - INFO - __main__ - Step 11157: {'lr': 0.0004952931496079143, 'samples': 2142144, 'steps': 11156, 'loss/train': 0.4626551568508148} 08/30/2021 15:08:58 - INFO - __main__ - Step 11158: {'lr': 0.00049529212464552, 'samples': 2142336, 'steps': 11157, 'loss/train': 1.9143321514129639} 08/30/2021 15:08:59 - INFO - __main__ - Step 11159: {'lr': 0.0004952910995726008, 'samples': 2142528, 'steps': 11158, 'loss/train': 1.5643495321273804} 08/30/2021 15:08:59 - INFO - __main__ - Step 11160: {'lr': 0.0004952900743891573, 'samples': 2142720, 'steps': 11159, 'loss/train': 0.9213781356811523} 08/30/2021 15:08:59 - INFO - __main__ - Step 11161: {'lr': 0.0004952890490951898, 'samples': 2142912, 'steps': 11160, 'loss/train': 0.9682077765464783} 08/30/2021 15:09:01 - INFO - __main__ - Step 11162: {'lr': 0.0004952880236906988, 'samples': 2143104, 'steps': 11161, 'loss/train': 1.2100898027420044} 08/30/2021 15:09:01 - INFO - __main__ - Step 11163: {'lr': 0.0004952869981756848, 'samples': 2143296, 'steps': 11162, 'loss/train': 1.7945683002471924} 08/30/2021 15:09:02 - INFO - __main__ - Step 11164: {'lr': 0.0004952859725501484, 'samples': 2143488, 'steps': 11163, 'loss/train': 2.1535260677337646} 08/30/2021 15:09:02 - INFO - __main__ - Step 11165: {'lr': 0.0004952849468140898, 'samples': 2143680, 'steps': 11164, 'loss/train': 1.7730416059494019} 08/30/2021 15:09:03 - INFO - __main__ - Step 11166: {'lr': 0.0004952839209675096, 'samples': 2143872, 'steps': 11165, 'loss/train': 1.5191484689712524} 08/30/2021 15:09:04 - INFO - __main__ - Step 11167: {'lr': 0.0004952828950104083, 'samples': 2144064, 'steps': 11166, 'loss/train': 0.5176580548286438} 08/30/2021 15:09:05 - INFO - __main__ - Step 11168: {'lr': 0.0004952818689427863, 'samples': 2144256, 'steps': 11167, 'loss/train': 1.9282982349395752} 08/30/2021 15:09:05 - INFO - __main__ - Step 11169: {'lr': 0.0004952808427646441, 'samples': 2144448, 'steps': 11168, 'loss/train': 1.4896656274795532} 08/30/2021 15:09:06 - INFO - __main__ - Step 11170: {'lr': 0.000495279816475982, 'samples': 2144640, 'steps': 11169, 'loss/train': 1.80918550491333} 08/30/2021 15:09:06 - INFO - __main__ - Step 11171: {'lr': 0.0004952787900768008, 'samples': 2144832, 'steps': 11170, 'loss/train': 1.5024809837341309} 08/30/2021 15:09:08 - INFO - __main__ - Step 11172: {'lr': 0.0004952777635671006, 'samples': 2145024, 'steps': 11171, 'loss/train': 2.058274030685425} 08/30/2021 15:09:08 - INFO - __main__ - Step 11173: {'lr': 0.0004952767369468821, 'samples': 2145216, 'steps': 11172, 'loss/train': 1.8573354482650757} 08/30/2021 15:09:08 - INFO - __main__ - Step 11174: {'lr': 0.0004952757102161457, 'samples': 2145408, 'steps': 11173, 'loss/train': 1.9735442399978638} 08/30/2021 15:09:09 - INFO - __main__ - Step 11175: {'lr': 0.0004952746833748918, 'samples': 2145600, 'steps': 11174, 'loss/train': 1.7319947481155396} 08/30/2021 15:09:09 - INFO - __main__ - Step 11176: {'lr': 0.0004952736564231209, 'samples': 2145792, 'steps': 11175, 'loss/train': 1.817901611328125} 08/30/2021 15:09:11 - INFO - __main__ - Step 11177: {'lr': 0.0004952726293608335, 'samples': 2145984, 'steps': 11176, 'loss/train': 2.117215633392334} 08/30/2021 15:09:11 - INFO - __main__ - Step 11178: {'lr': 0.0004952716021880301, 'samples': 2146176, 'steps': 11177, 'loss/train': 1.3609068393707275} 08/30/2021 15:09:11 - INFO - __main__ - Step 11179: {'lr': 0.0004952705749047111, 'samples': 2146368, 'steps': 11178, 'loss/train': 1.5699869394302368} 08/30/2021 15:09:12 - INFO - __main__ - Step 11180: {'lr': 0.0004952695475108768, 'samples': 2146560, 'steps': 11179, 'loss/train': 1.5526151657104492} 08/30/2021 15:09:12 - INFO - __main__ - Step 11181: {'lr': 0.000495268520006528, 'samples': 2146752, 'steps': 11180, 'loss/train': 1.577141284942627} 08/30/2021 15:09:14 - INFO - __main__ - Step 11182: {'lr': 0.000495267492391665, 'samples': 2146944, 'steps': 11181, 'loss/train': 2.015547752380371} 08/30/2021 15:09:14 - INFO - __main__ - Step 11183: {'lr': 0.0004952664646662882, 'samples': 2147136, 'steps': 11182, 'loss/train': 1.9722617864608765} 08/30/2021 15:09:15 - INFO - __main__ - Step 11184: {'lr': 0.000495265436830398, 'samples': 2147328, 'steps': 11183, 'loss/train': 1.9817020893096924} 08/30/2021 15:09:15 - INFO - __main__ - Step 11185: {'lr': 0.0004952644088839951, 'samples': 2147520, 'steps': 11184, 'loss/train': 2.0684518814086914} 08/30/2021 15:09:15 - INFO - __main__ - Step 11186: {'lr': 0.0004952633808270797, 'samples': 2147712, 'steps': 11185, 'loss/train': 1.2863656282424927} 08/30/2021 15:09:16 - INFO - __main__ - Step 11187: {'lr': 0.0004952623526596526, 'samples': 2147904, 'steps': 11186, 'loss/train': 1.9380815029144287} 08/30/2021 15:09:17 - INFO - __main__ - Step 11188: {'lr': 0.000495261324381714, 'samples': 2148096, 'steps': 11187, 'loss/train': 1.7953402996063232} 08/30/2021 15:09:18 - INFO - __main__ - Step 11189: {'lr': 0.0004952602959932644, 'samples': 2148288, 'steps': 11188, 'loss/train': 2.091665029525757} 08/30/2021 15:09:18 - INFO - __main__ - Step 11190: {'lr': 0.0004952592674943043, 'samples': 2148480, 'steps': 11189, 'loss/train': 1.566051959991455} 08/30/2021 15:09:18 - INFO - __main__ - Step 11191: {'lr': 0.0004952582388848343, 'samples': 2148672, 'steps': 11190, 'loss/train': 1.6068222522735596} 08/30/2021 15:09:19 - INFO - __main__ - Step 11192: {'lr': 0.0004952572101648545, 'samples': 2148864, 'steps': 11191, 'loss/train': 1.6725513935089111} 08/30/2021 15:09:20 - INFO - __main__ - Step 11193: {'lr': 0.0004952561813343657, 'samples': 2149056, 'steps': 11192, 'loss/train': 1.7708979845046997} 08/30/2021 15:09:21 - INFO - __main__ - Step 11194: {'lr': 0.0004952551523933682, 'samples': 2149248, 'steps': 11193, 'loss/train': 1.3797221183776855} 08/30/2021 15:09:21 - INFO - __main__ - Step 11195: {'lr': 0.0004952541233418626, 'samples': 2149440, 'steps': 11194, 'loss/train': 1.7353644371032715} 08/30/2021 15:09:21 - INFO - __main__ - Step 11196: {'lr': 0.0004952530941798492, 'samples': 2149632, 'steps': 11195, 'loss/train': 1.5461173057556152} 08/30/2021 15:09:22 - INFO - __main__ - Step 11197: {'lr': 0.0004952520649073286, 'samples': 2149824, 'steps': 11196, 'loss/train': 1.756289005279541} 08/30/2021 15:09:23 - INFO - __main__ - Step 11198: {'lr': 0.0004952510355243012, 'samples': 2150016, 'steps': 11197, 'loss/train': 1.3803040981292725} 08/30/2021 15:09:24 - INFO - __main__ - Step 11199: {'lr': 0.0004952500060307674, 'samples': 2150208, 'steps': 11198, 'loss/train': 2.0660104751586914} 08/30/2021 15:09:25 - INFO - __main__ - Step 11200: {'lr': 0.0004952489764267278, 'samples': 2150400, 'steps': 11199, 'loss/train': 1.9330822229385376} 08/30/2021 15:09:25 - INFO - __main__ - Step 11201: {'lr': 0.0004952479467121827, 'samples': 2150592, 'steps': 11200, 'loss/train': 6.268353462219238} 08/30/2021 15:09:25 - INFO - __main__ - Step 11202: {'lr': 0.0004952469168871327, 'samples': 2150784, 'steps': 11201, 'loss/train': 6.152014255523682} 08/30/2021 15:09:26 - INFO - __main__ - Step 11203: {'lr': 0.0004952458869515782, 'samples': 2150976, 'steps': 11202, 'loss/train': 3.165759801864624} 08/30/2021 15:09:28 - INFO - __main__ - Step 11204: {'lr': 0.0004952448569055198, 'samples': 2151168, 'steps': 11203, 'loss/train': 1.6261491775512695} 08/30/2021 15:09:28 - INFO - __main__ - Step 11205: {'lr': 0.0004952438267489578, 'samples': 2151360, 'steps': 11204, 'loss/train': 1.5949993133544922} 08/30/2021 15:09:29 - INFO - __main__ - Step 11206: {'lr': 0.0004952427964818927, 'samples': 2151552, 'steps': 11205, 'loss/train': 0.1325102001428604} 08/30/2021 15:09:29 - INFO - __main__ - Step 11207: {'lr': 0.0004952417661043249, 'samples': 2151744, 'steps': 11206, 'loss/train': 1.750083088874817} 08/30/2021 15:09:29 - INFO - __main__ - Step 11208: {'lr': 0.0004952407356162551, 'samples': 2151936, 'steps': 11207, 'loss/train': 1.6897622346878052} 08/30/2021 15:09:30 - INFO - __main__ - Step 11209: {'lr': 0.0004952397050176835, 'samples': 2152128, 'steps': 11208, 'loss/train': 1.6857823133468628} 08/30/2021 15:09:30 - INFO - __main__ - Step 11210: {'lr': 0.0004952386743086107, 'samples': 2152320, 'steps': 11209, 'loss/train': 1.4603480100631714} 08/30/2021 15:09:32 - INFO - __main__ - Step 11211: {'lr': 0.0004952376434890372, 'samples': 2152512, 'steps': 11210, 'loss/train': 1.1289713382720947} 08/30/2021 15:09:32 - INFO - __main__ - Step 11212: {'lr': 0.0004952366125589633, 'samples': 2152704, 'steps': 11211, 'loss/train': 2.1865925788879395} 08/30/2021 15:09:33 - INFO - __main__ - Step 11213: {'lr': 0.0004952355815183897, 'samples': 2152896, 'steps': 11212, 'loss/train': 1.869810700416565} 08/30/2021 15:09:33 - INFO - __main__ - Step 11214: {'lr': 0.0004952345503673166, 'samples': 2153088, 'steps': 11213, 'loss/train': 0.21112875640392303} 08/30/2021 15:09:33 - INFO - __main__ - Step 11215: {'lr': 0.0004952335191057447, 'samples': 2153280, 'steps': 11214, 'loss/train': 2.077345371246338} 08/30/2021 15:09:35 - INFO - __main__ - Step 11216: {'lr': 0.0004952324877336743, 'samples': 2153472, 'steps': 11215, 'loss/train': 2.015061855316162} 08/30/2021 15:09:35 - INFO - __main__ - Step 11217: {'lr': 0.0004952314562511059, 'samples': 2153664, 'steps': 11216, 'loss/train': 1.6336077451705933} 08/30/2021 15:09:36 - INFO - __main__ - Step 11218: {'lr': 0.00049523042465804, 'samples': 2153856, 'steps': 11217, 'loss/train': 1.9728543758392334} 08/30/2021 15:09:36 - INFO - __main__ - Step 11219: {'lr': 0.0004952293929544771, 'samples': 2154048, 'steps': 11218, 'loss/train': 1.814045786857605} 08/30/2021 15:09:36 - INFO - __main__ - Step 11220: {'lr': 0.0004952283611404176, 'samples': 2154240, 'steps': 11219, 'loss/train': 1.9692790508270264} 08/30/2021 15:09:39 - INFO - __main__ - Step 11221: {'lr': 0.0004952273292158619, 'samples': 2154432, 'steps': 11220, 'loss/train': 1.3120520114898682} 08/30/2021 15:09:39 - INFO - __main__ - Step 11222: {'lr': 0.0004952262971808106, 'samples': 2154624, 'steps': 11221, 'loss/train': 1.9009259939193726} 08/30/2021 15:09:40 - INFO - __main__ - Step 11223: {'lr': 0.0004952252650352642, 'samples': 2154816, 'steps': 11222, 'loss/train': 2.608480215072632} 08/30/2021 15:09:40 - INFO - __main__ - Step 11224: {'lr': 0.000495224232779223, 'samples': 2155008, 'steps': 11223, 'loss/train': 1.6276488304138184} 08/30/2021 15:09:40 - INFO - __main__ - Step 11225: {'lr': 0.0004952232004126876, 'samples': 2155200, 'steps': 11224, 'loss/train': 2.3533132076263428} 08/30/2021 15:09:41 - INFO - __main__ - Step 11226: {'lr': 0.0004952221679356583, 'samples': 2155392, 'steps': 11225, 'loss/train': 1.5897690057754517} 08/30/2021 15:09:42 - INFO - __main__ - Step 11227: {'lr': 0.0004952211353481358, 'samples': 2155584, 'steps': 11226, 'loss/train': 2.033146858215332} 08/30/2021 15:09:43 - INFO - __main__ - Step 11228: {'lr': 0.0004952201026501204, 'samples': 2155776, 'steps': 11227, 'loss/train': 2.0458672046661377} 08/30/2021 15:09:43 - INFO - __main__ - Step 11229: {'lr': 0.0004952190698416126, 'samples': 2155968, 'steps': 11228, 'loss/train': 1.9060672521591187} 08/30/2021 15:09:43 - INFO - __main__ - Step 11230: {'lr': 0.0004952180369226129, 'samples': 2156160, 'steps': 11229, 'loss/train': 2.1047184467315674} 08/30/2021 15:09:44 - INFO - __main__ - Step 11231: {'lr': 0.0004952170038931217, 'samples': 2156352, 'steps': 11230, 'loss/train': 1.7409850358963013} 08/30/2021 15:09:45 - INFO - __main__ - Step 11232: {'lr': 0.0004952159707531395, 'samples': 2156544, 'steps': 11231, 'loss/train': 2.201941728591919} 08/30/2021 15:09:46 - INFO - __main__ - Step 11233: {'lr': 0.0004952149375026668, 'samples': 2156736, 'steps': 11232, 'loss/train': 1.949341058731079} 08/30/2021 15:09:46 - INFO - __main__ - Step 11234: {'lr': 0.000495213904141704, 'samples': 2156928, 'steps': 11233, 'loss/train': 2.10192608833313} 08/30/2021 15:09:46 - INFO - __main__ - Step 11235: {'lr': 0.0004952128706702516, 'samples': 2157120, 'steps': 11234, 'loss/train': 1.432446002960205} 08/30/2021 15:09:47 - INFO - __main__ - Step 11236: {'lr': 0.0004952118370883101, 'samples': 2157312, 'steps': 11235, 'loss/train': 1.860512137413025} 08/30/2021 15:09:48 - INFO - __main__ - Step 11237: {'lr': 0.0004952108033958798, 'samples': 2157504, 'steps': 11236, 'loss/train': 1.7600961923599243} 08/30/2021 15:09:49 - INFO - __main__ - Step 11238: {'lr': 0.0004952097695929614, 'samples': 2157696, 'steps': 11237, 'loss/train': 1.8075411319732666} 08/30/2021 15:09:49 - INFO - __main__ - Step 11239: {'lr': 0.0004952087356795553, 'samples': 2157888, 'steps': 11238, 'loss/train': 1.9469932317733765} 08/30/2021 15:09:49 - INFO - __main__ - Step 11240: {'lr': 0.0004952077016556619, 'samples': 2158080, 'steps': 11239, 'loss/train': 2.207625389099121} 08/30/2021 15:09:50 - INFO - __main__ - Step 11241: {'lr': 0.0004952066675212816, 'samples': 2158272, 'steps': 11240, 'loss/train': 1.5010963678359985} 08/30/2021 15:09:50 - INFO - __main__ - Step 11242: {'lr': 0.0004952056332764151, 'samples': 2158464, 'steps': 11241, 'loss/train': 1.7851382493972778} 08/30/2021 15:09:52 - INFO - __main__ - Step 11243: {'lr': 0.0004952045989210627, 'samples': 2158656, 'steps': 11242, 'loss/train': 1.4927185773849487} 08/30/2021 15:09:52 - INFO - __main__ - Step 11244: {'lr': 0.0004952035644552249, 'samples': 2158848, 'steps': 11243, 'loss/train': 1.7379070520401} 08/30/2021 15:09:53 - INFO - __main__ - Step 11245: {'lr': 0.000495202529878902, 'samples': 2159040, 'steps': 11244, 'loss/train': 1.5175026655197144} 08/30/2021 15:09:53 - INFO - __main__ - Step 11246: {'lr': 0.0004952014951920948, 'samples': 2159232, 'steps': 11245, 'loss/train': 1.0634227991104126} 08/30/2021 15:09:53 - INFO - __main__ - Step 11247: {'lr': 0.0004952004603948034, 'samples': 2159424, 'steps': 11246, 'loss/train': 1.5533729791641235} 08/30/2021 15:09:55 - INFO - __main__ - Step 11248: {'lr': 0.0004951994254870286, 'samples': 2159616, 'steps': 11247, 'loss/train': 2.3674063682556152} 08/30/2021 15:09:55 - INFO - __main__ - Step 11249: {'lr': 0.0004951983904687708, 'samples': 2159808, 'steps': 11248, 'loss/train': 1.8283774852752686} 08/30/2021 15:09:56 - INFO - __main__ - Step 11250: {'lr': 0.0004951973553400303, 'samples': 2160000, 'steps': 11249, 'loss/train': 1.98063325881958} 08/30/2021 15:09:56 - INFO - __main__ - Step 11251: {'lr': 0.0004951963201008077, 'samples': 2160192, 'steps': 11250, 'loss/train': 1.6316938400268555} 08/30/2021 15:09:56 - INFO - __main__ - Step 11252: {'lr': 0.0004951952847511033, 'samples': 2160384, 'steps': 11251, 'loss/train': 1.882524013519287} 08/30/2021 15:09:57 - INFO - __main__ - Step 11253: {'lr': 0.0004951942492909177, 'samples': 2160576, 'steps': 11252, 'loss/train': 2.1029202938079834} 08/30/2021 15:09:58 - INFO - __main__ - Step 11254: {'lr': 0.0004951932137202515, 'samples': 2160768, 'steps': 11253, 'loss/train': 1.8152189254760742} 08/30/2021 15:09:59 - INFO - __main__ - Step 11255: {'lr': 0.0004951921780391049, 'samples': 2160960, 'steps': 11254, 'loss/train': 0.2853429615497589} 08/30/2021 15:09:59 - INFO - __main__ - Step 11256: {'lr': 0.0004951911422474785, 'samples': 2161152, 'steps': 11255, 'loss/train': 1.8781239986419678} 08/30/2021 15:10:00 - INFO - __main__ - Step 11257: {'lr': 0.0004951901063453728, 'samples': 2161344, 'steps': 11256, 'loss/train': 1.6769670248031616} 08/30/2021 15:10:00 - INFO - __main__ - Step 11258: {'lr': 0.0004951890703327883, 'samples': 2161536, 'steps': 11257, 'loss/train': 1.7944586277008057} 08/30/2021 15:10:01 - INFO - __main__ - Step 11259: {'lr': 0.0004951880342097251, 'samples': 2161728, 'steps': 11258, 'loss/train': 2.091442823410034} 08/30/2021 15:10:02 - INFO - __main__ - Step 11260: {'lr': 0.0004951869979761842, 'samples': 2161920, 'steps': 11259, 'loss/train': 2.2156801223754883} 08/30/2021 15:10:02 - INFO - __main__ - Step 11261: {'lr': 0.0004951859616321658, 'samples': 2162112, 'steps': 11260, 'loss/train': 1.9757577180862427} 08/30/2021 15:10:03 - INFO - __main__ - Step 11262: {'lr': 0.0004951849251776703, 'samples': 2162304, 'steps': 11261, 'loss/train': 1.3211166858673096} 08/30/2021 15:10:03 - INFO - __main__ - Step 11263: {'lr': 0.0004951838886126983, 'samples': 2162496, 'steps': 11262, 'loss/train': 1.3247021436691284} 08/30/2021 15:10:04 - INFO - __main__ - Step 11264: {'lr': 0.0004951828519372503, 'samples': 2162688, 'steps': 11263, 'loss/train': 1.8176363706588745} 08/30/2021 15:10:05 - INFO - __main__ - Step 11265: {'lr': 0.0004951818151513267, 'samples': 2162880, 'steps': 11264, 'loss/train': 1.9629976749420166} 08/30/2021 15:10:05 - INFO - __main__ - Step 11266: {'lr': 0.0004951807782549277, 'samples': 2163072, 'steps': 11265, 'loss/train': 1.8665183782577515} 08/30/2021 15:10:05 - INFO - __main__ - Step 11267: {'lr': 0.0004951797412480544, 'samples': 2163264, 'steps': 11266, 'loss/train': 2.1557822227478027} 08/30/2021 15:10:06 - INFO - __main__ - Step 11268: {'lr': 0.0004951787041307066, 'samples': 2163456, 'steps': 11267, 'loss/train': 1.923411250114441} 08/30/2021 15:10:07 - INFO - __main__ - Step 11269: {'lr': 0.0004951776669028851, 'samples': 2163648, 'steps': 11268, 'loss/train': 2.5946178436279297} 08/30/2021 15:10:08 - INFO - __main__ - Step 11270: {'lr': 0.0004951766295645904, 'samples': 2163840, 'steps': 11269, 'loss/train': 1.7681535482406616} 08/30/2021 15:10:08 - INFO - __main__ - Step 11271: {'lr': 0.000495175592115823, 'samples': 2164032, 'steps': 11270, 'loss/train': 1.0833417177200317} 08/30/2021 15:10:09 - INFO - __main__ - Step 11272: {'lr': 0.0004951745545565831, 'samples': 2164224, 'steps': 11271, 'loss/train': 1.4488327503204346} 08/30/2021 15:10:09 - INFO - __main__ - Step 11273: {'lr': 0.0004951735168868713, 'samples': 2164416, 'steps': 11272, 'loss/train': 1.5733282566070557} 08/30/2021 15:10:11 - INFO - __main__ - Step 11274: {'lr': 0.0004951724791066881, 'samples': 2164608, 'steps': 11273, 'loss/train': 1.629154086112976} 08/30/2021 15:10:11 - INFO - __main__ - Step 11275: {'lr': 0.0004951714412160342, 'samples': 2164800, 'steps': 11274, 'loss/train': 1.9060413837432861} 08/30/2021 15:10:12 - INFO - __main__ - Step 11276: {'lr': 0.0004951704032149096, 'samples': 2164992, 'steps': 11275, 'loss/train': 1.9716060161590576} 08/30/2021 15:10:12 - INFO - __main__ - Step 11277: {'lr': 0.000495169365103315, 'samples': 2165184, 'steps': 11276, 'loss/train': 2.704251766204834} 08/30/2021 15:10:12 - INFO - __main__ - Step 11278: {'lr': 0.0004951683268812511, 'samples': 2165376, 'steps': 11277, 'loss/train': 1.8629169464111328} 08/30/2021 15:10:13 - INFO - __main__ - Step 11279: {'lr': 0.0004951672885487178, 'samples': 2165568, 'steps': 11278, 'loss/train': 1.880487084388733} 08/30/2021 15:10:13 - INFO - __main__ - Step 11280: {'lr': 0.0004951662501057161, 'samples': 2165760, 'steps': 11279, 'loss/train': 2.465620994567871} 08/30/2021 15:10:15 - INFO - __main__ - Step 11281: {'lr': 0.0004951652115522462, 'samples': 2165952, 'steps': 11280, 'loss/train': 1.8681460618972778} 08/30/2021 15:10:16 - INFO - __main__ - Step 11282: {'lr': 0.0004951641728883087, 'samples': 2166144, 'steps': 11281, 'loss/train': 1.5482832193374634} 08/30/2021 15:10:16 - INFO - __main__ - Step 11283: {'lr': 0.000495163134113904, 'samples': 2166336, 'steps': 11282, 'loss/train': 1.5466859340667725} 08/30/2021 15:10:16 - INFO - __main__ - Step 11284: {'lr': 0.0004951620952290325, 'samples': 2166528, 'steps': 11283, 'loss/train': 1.0799888372421265} 08/30/2021 15:10:17 - INFO - __main__ - Step 11285: {'lr': 0.0004951610562336949, 'samples': 2166720, 'steps': 11284, 'loss/train': 1.5446174144744873} 08/30/2021 15:10:18 - INFO - __main__ - Step 11286: {'lr': 0.0004951600171278914, 'samples': 2166912, 'steps': 11285, 'loss/train': 2.0954701900482178} 08/30/2021 15:10:19 - INFO - __main__ - Step 11287: {'lr': 0.0004951589779116225, 'samples': 2167104, 'steps': 11286, 'loss/train': 1.807062029838562} 08/30/2021 15:10:19 - INFO - __main__ - Step 11288: {'lr': 0.0004951579385848889, 'samples': 2167296, 'steps': 11287, 'loss/train': 1.0833994150161743} 08/30/2021 15:10:19 - INFO - __main__ - Step 11289: {'lr': 0.0004951568991476908, 'samples': 2167488, 'steps': 11288, 'loss/train': 1.6628488302230835} 08/30/2021 15:10:20 - INFO - __main__ - Step 11290: {'lr': 0.0004951558596000289, 'samples': 2167680, 'steps': 11289, 'loss/train': 1.7167960405349731} 08/30/2021 15:10:21 - INFO - __main__ - Step 11291: {'lr': 0.0004951548199419035, 'samples': 2167872, 'steps': 11290, 'loss/train': 1.8201220035552979} 08/30/2021 15:10:22 - INFO - __main__ - Step 11292: {'lr': 0.0004951537801733152, 'samples': 2168064, 'steps': 11291, 'loss/train': 1.7071702480316162} 08/30/2021 15:10:22 - INFO - __main__ - Step 11293: {'lr': 0.0004951527402942643, 'samples': 2168256, 'steps': 11292, 'loss/train': 1.5277527570724487} 08/30/2021 15:10:23 - INFO - __main__ - Step 11294: {'lr': 0.0004951517003047512, 'samples': 2168448, 'steps': 11293, 'loss/train': 2.013002872467041} 08/30/2021 15:10:23 - INFO - __main__ - Step 11295: {'lr': 0.0004951506602047767, 'samples': 2168640, 'steps': 11294, 'loss/train': 1.782727837562561} 08/30/2021 15:10:24 - INFO - __main__ - Step 11296: {'lr': 0.0004951496199943412, 'samples': 2168832, 'steps': 11295, 'loss/train': 2.2067103385925293} 08/30/2021 15:10:25 - INFO - __main__ - Step 11297: {'lr': 0.0004951485796734448, 'samples': 2169024, 'steps': 11296, 'loss/train': 1.5037710666656494} 08/30/2021 15:10:25 - INFO - __main__ - Step 11298: {'lr': 0.0004951475392420884, 'samples': 2169216, 'steps': 11297, 'loss/train': 1.933862328529358} 08/30/2021 15:10:26 - INFO - __main__ - Step 11299: {'lr': 0.0004951464987002724, 'samples': 2169408, 'steps': 11298, 'loss/train': 2.2062699794769287} 08/30/2021 15:10:26 - INFO - __main__ - Step 11300: {'lr': 0.000495145458047997, 'samples': 2169600, 'steps': 11299, 'loss/train': 1.884720802307129} 08/30/2021 15:10:26 - INFO - __main__ - Step 11301: {'lr': 0.0004951444172852629, 'samples': 2169792, 'steps': 11300, 'loss/train': 1.504366397857666} 08/30/2021 15:10:28 - INFO - __main__ - Step 11302: {'lr': 0.0004951433764120705, 'samples': 2169984, 'steps': 11301, 'loss/train': 1.9274585247039795} 08/30/2021 15:10:28 - INFO - __main__ - Step 11303: {'lr': 0.0004951423354284202, 'samples': 2170176, 'steps': 11302, 'loss/train': 1.6363259553909302} 08/30/2021 15:10:29 - INFO - __main__ - Step 11304: {'lr': 0.0004951412943343126, 'samples': 2170368, 'steps': 11303, 'loss/train': 1.5677433013916016} 08/30/2021 15:10:29 - INFO - __main__ - Step 11305: {'lr': 0.0004951402531297482, 'samples': 2170560, 'steps': 11304, 'loss/train': 1.9196350574493408} 08/30/2021 15:10:29 - INFO - __main__ - Step 11306: {'lr': 0.0004951392118147273, 'samples': 2170752, 'steps': 11305, 'loss/train': 1.9655555486679077} 08/30/2021 15:10:31 - INFO - __main__ - Step 11307: {'lr': 0.0004951381703892506, 'samples': 2170944, 'steps': 11306, 'loss/train': 1.900527000427246} 08/30/2021 15:10:31 - INFO - __main__ - Step 11308: {'lr': 0.0004951371288533182, 'samples': 2171136, 'steps': 11307, 'loss/train': 6.5954670906066895} 08/30/2021 15:10:32 - INFO - __main__ - Step 11309: {'lr': 0.0004951360872069309, 'samples': 2171328, 'steps': 11308, 'loss/train': 1.617108941078186} 08/30/2021 15:10:32 - INFO - __main__ - Step 11310: {'lr': 0.0004951350454500891, 'samples': 2171520, 'steps': 11309, 'loss/train': 1.9250389337539673} 08/30/2021 15:10:32 - INFO - __main__ - Step 11311: {'lr': 0.0004951340035827932, 'samples': 2171712, 'steps': 11310, 'loss/train': 1.5192028284072876} 08/30/2021 15:10:33 - INFO - __main__ - Step 11312: {'lr': 0.0004951329616050437, 'samples': 2171904, 'steps': 11311, 'loss/train': 1.6938209533691406} 08/30/2021 15:10:34 - INFO - __main__ - Step 11313: {'lr': 0.000495131919516841, 'samples': 2172096, 'steps': 11312, 'loss/train': 0.6564881801605225} 08/30/2021 15:10:35 - INFO - __main__ - Step 11314: {'lr': 0.0004951308773181856, 'samples': 2172288, 'steps': 11313, 'loss/train': 1.6009490489959717} 08/30/2021 15:10:35 - INFO - __main__ - Step 11315: {'lr': 0.0004951298350090782, 'samples': 2172480, 'steps': 11314, 'loss/train': 2.257167339324951} 08/30/2021 15:10:35 - INFO - __main__ - Step 11316: {'lr': 0.000495128792589519, 'samples': 2172672, 'steps': 11315, 'loss/train': 1.8359655141830444} 08/30/2021 15:10:36 - INFO - __main__ - Step 11317: {'lr': 0.0004951277500595085, 'samples': 2172864, 'steps': 11316, 'loss/train': 2.183683395385742} 08/30/2021 15:10:37 - INFO - __main__ - Step 11318: {'lr': 0.0004951267074190473, 'samples': 2173056, 'steps': 11317, 'loss/train': 1.9519745111465454} 08/30/2021 15:10:38 - INFO - __main__ - Step 11319: {'lr': 0.0004951256646681356, 'samples': 2173248, 'steps': 11318, 'loss/train': 2.677309036254883} 08/30/2021 15:10:38 - INFO - __main__ - Step 11320: {'lr': 0.0004951246218067744, 'samples': 2173440, 'steps': 11319, 'loss/train': 2.2664835453033447} 08/30/2021 15:10:38 - INFO - __main__ - Step 11321: {'lr': 0.0004951235788349636, 'samples': 2173632, 'steps': 11320, 'loss/train': 1.917419672012329} 08/30/2021 15:10:39 - INFO - __main__ - Step 11322: {'lr': 0.0004951225357527038, 'samples': 2173824, 'steps': 11321, 'loss/train': 2.0854012966156006} 08/30/2021 15:10:40 - INFO - __main__ - Step 11323: {'lr': 0.0004951214925599957, 'samples': 2174016, 'steps': 11322, 'loss/train': 0.2760118246078491} 08/30/2021 15:10:41 - INFO - __main__ - Step 11324: {'lr': 0.0004951204492568397, 'samples': 2174208, 'steps': 11323, 'loss/train': 1.9507191181182861} 08/30/2021 15:10:41 - INFO - __main__ - Step 11325: {'lr': 0.0004951194058432361, 'samples': 2174400, 'steps': 11324, 'loss/train': 2.103816270828247} 08/30/2021 15:10:41 - INFO - __main__ - Step 11326: {'lr': 0.0004951183623191855, 'samples': 2174592, 'steps': 11325, 'loss/train': 2.3394269943237305} 08/30/2021 15:10:42 - INFO - __main__ - Step 11327: {'lr': 0.0004951173186846884, 'samples': 2174784, 'steps': 11326, 'loss/train': 0.3999486565589905} 08/30/2021 15:10:44 - INFO - __main__ - Step 11328: {'lr': 0.0004951162749397452, 'samples': 2174976, 'steps': 11327, 'loss/train': 1.5916470289230347} 08/30/2021 15:10:44 - INFO - __main__ - Step 11329: {'lr': 0.0004951152310843564, 'samples': 2175168, 'steps': 11328, 'loss/train': 1.4261094331741333} 08/30/2021 15:10:44 - INFO - __main__ - Step 11330: {'lr': 0.0004951141871185224, 'samples': 2175360, 'steps': 11329, 'loss/train': 1.7575404644012451} 08/30/2021 15:10:45 - INFO - __main__ - Step 11331: {'lr': 0.0004951131430422438, 'samples': 2175552, 'steps': 11330, 'loss/train': 2.1405422687530518} 08/30/2021 15:10:45 - INFO - __main__ - Step 11332: {'lr': 0.0004951120988555209, 'samples': 2175744, 'steps': 11331, 'loss/train': 1.8434191942214966} 08/30/2021 15:10:45 - INFO - __main__ - Step 11333: {'lr': 0.0004951110545583543, 'samples': 2175936, 'steps': 11332, 'loss/train': 1.2429536581039429} 08/30/2021 15:10:47 - INFO - __main__ - Step 11334: {'lr': 0.0004951100101507445, 'samples': 2176128, 'steps': 11333, 'loss/train': 0.1674688160419464} 08/30/2021 15:10:48 - INFO - __main__ - Step 11335: {'lr': 0.0004951089656326919, 'samples': 2176320, 'steps': 11334, 'loss/train': 1.6125035285949707} 08/30/2021 15:10:48 - INFO - __main__ - Step 11336: {'lr': 0.0004951079210041969, 'samples': 2176512, 'steps': 11335, 'loss/train': 1.5547882318496704} 08/30/2021 15:10:49 - INFO - __main__ - Step 11337: {'lr': 0.0004951068762652602, 'samples': 2176704, 'steps': 11336, 'loss/train': 1.0038021802902222} 08/30/2021 15:10:49 - INFO - __main__ - Step 11338: {'lr': 0.000495105831415882, 'samples': 2176896, 'steps': 11337, 'loss/train': 2.2198216915130615} 08/30/2021 15:10:50 - INFO - __main__ - Step 11339: {'lr': 0.0004951047864560629, 'samples': 2177088, 'steps': 11338, 'loss/train': 1.911068081855774} 08/30/2021 15:10:51 - INFO - __main__ - Step 11340: {'lr': 0.0004951037413858034, 'samples': 2177280, 'steps': 11339, 'loss/train': 1.9215306043624878} 08/30/2021 15:10:51 - INFO - __main__ - Step 11341: {'lr': 0.000495102696205104, 'samples': 2177472, 'steps': 11340, 'loss/train': 1.4014047384262085} 08/30/2021 15:10:51 - INFO - __main__ - Step 11342: {'lr': 0.000495101650913965, 'samples': 2177664, 'steps': 11341, 'loss/train': 1.8121275901794434} 08/30/2021 15:10:52 - INFO - __main__ - Step 11343: {'lr': 0.000495100605512387, 'samples': 2177856, 'steps': 11342, 'loss/train': 1.7509299516677856} 08/30/2021 15:10:53 - INFO - __main__ - Step 11344: {'lr': 0.0004950995600003705, 'samples': 2178048, 'steps': 11343, 'loss/train': 1.6537495851516724} 08/30/2021 15:10:54 - INFO - __main__ - Step 11345: {'lr': 0.0004950985143779159, 'samples': 2178240, 'steps': 11344, 'loss/train': 0.7755739688873291} 08/30/2021 15:10:54 - INFO - __main__ - Step 11346: {'lr': 0.0004950974686450237, 'samples': 2178432, 'steps': 11345, 'loss/train': 1.8410006761550903} 08/30/2021 15:10:54 - INFO - __main__ - Step 11347: {'lr': 0.0004950964228016944, 'samples': 2178624, 'steps': 11346, 'loss/train': 1.2583353519439697} 08/30/2021 15:10:55 - INFO - __main__ - Step 11348: {'lr': 0.0004950953768479284, 'samples': 2178816, 'steps': 11347, 'loss/train': 1.8307527303695679} 08/30/2021 15:10:57 - INFO - __main__ - Step 11349: {'lr': 0.0004950943307837261, 'samples': 2179008, 'steps': 11348, 'loss/train': 1.7371530532836914} 08/30/2021 15:10:57 - INFO - __main__ - Step 11350: {'lr': 0.0004950932846090882, 'samples': 2179200, 'steps': 11349, 'loss/train': 1.1253018379211426} 08/30/2021 15:10:58 - INFO - __main__ - Step 11351: {'lr': 0.000495092238324015, 'samples': 2179392, 'steps': 11350, 'loss/train': 1.8747700452804565} 08/30/2021 15:10:58 - INFO - __main__ - Step 11352: {'lr': 0.0004950911919285071, 'samples': 2179584, 'steps': 11351, 'loss/train': 1.7259424924850464} 08/30/2021 15:10:58 - INFO - __main__ - Step 11353: {'lr': 0.0004950901454225647, 'samples': 2179776, 'steps': 11352, 'loss/train': 1.6113831996917725} 08/30/2021 15:10:59 - INFO - __main__ - Step 11354: {'lr': 0.0004950890988061886, 'samples': 2179968, 'steps': 11353, 'loss/train': 0.8323259949684143} 08/30/2021 15:11:00 - INFO - __main__ - Step 11355: {'lr': 0.0004950880520793791, 'samples': 2180160, 'steps': 11354, 'loss/train': 0.23962008953094482} 08/30/2021 15:11:01 - INFO - __main__ - Step 11356: {'lr': 0.0004950870052421368, 'samples': 2180352, 'steps': 11355, 'loss/train': 2.2951104640960693} 08/30/2021 15:11:01 - INFO - __main__ - Step 11357: {'lr': 0.000495085958294462, 'samples': 2180544, 'steps': 11356, 'loss/train': 1.816585898399353} 08/30/2021 15:11:01 - INFO - __main__ - Step 11358: {'lr': 0.0004950849112363553, 'samples': 2180736, 'steps': 11357, 'loss/train': 2.080604314804077} 08/30/2021 15:11:02 - INFO - __main__ - Step 11359: {'lr': 0.000495083864067817, 'samples': 2180928, 'steps': 11358, 'loss/train': 1.6112520694732666} 08/30/2021 15:11:03 - INFO - __main__ - Step 11360: {'lr': 0.0004950828167888478, 'samples': 2181120, 'steps': 11359, 'loss/train': 1.975584864616394} 08/30/2021 15:11:04 - INFO - __main__ - Step 11361: {'lr': 0.0004950817693994481, 'samples': 2181312, 'steps': 11360, 'loss/train': 1.4203985929489136} 08/30/2021 15:11:04 - INFO - __main__ - Step 11362: {'lr': 0.0004950807218996182, 'samples': 2181504, 'steps': 11361, 'loss/train': 1.7508667707443237} 08/30/2021 15:11:04 - INFO - __main__ - Step 11363: {'lr': 0.0004950796742893588, 'samples': 2181696, 'steps': 11362, 'loss/train': 1.8694329261779785} 08/30/2021 15:11:05 - INFO - __main__ - Step 11364: {'lr': 0.0004950786265686702, 'samples': 2181888, 'steps': 11363, 'loss/train': 2.099109411239624} 08/30/2021 15:11:06 - INFO - __main__ - Step 11365: {'lr': 0.000495077578737553, 'samples': 2182080, 'steps': 11364, 'loss/train': 1.7561641931533813} 08/30/2021 15:11:07 - INFO - __main__ - Step 11366: {'lr': 0.0004950765307960076, 'samples': 2182272, 'steps': 11365, 'loss/train': 2.115619659423828} 08/30/2021 15:11:07 - INFO - __main__ - Step 11367: {'lr': 0.0004950754827440346, 'samples': 2182464, 'steps': 11366, 'loss/train': 2.081895112991333} 08/30/2021 15:11:07 - INFO - __main__ - Step 11368: {'lr': 0.0004950744345816342, 'samples': 2182656, 'steps': 11367, 'loss/train': 2.2468907833099365} 08/30/2021 15:11:08 - INFO - __main__ - Step 11369: {'lr': 0.0004950733863088072, 'samples': 2182848, 'steps': 11368, 'loss/train': 1.8041374683380127} 08/30/2021 15:11:09 - INFO - __main__ - Step 11370: {'lr': 0.0004950723379255538, 'samples': 2183040, 'steps': 11369, 'loss/train': 1.4568737745285034} 08/30/2021 15:11:10 - INFO - __main__ - Step 11371: {'lr': 0.0004950712894318748, 'samples': 2183232, 'steps': 11370, 'loss/train': 1.7635802030563354} 08/30/2021 15:11:10 - INFO - __main__ - Step 11372: {'lr': 0.0004950702408277702, 'samples': 2183424, 'steps': 11371, 'loss/train': 1.8993170261383057} 08/30/2021 15:11:10 - INFO - __main__ - Step 11373: {'lr': 0.0004950691921132409, 'samples': 2183616, 'steps': 11372, 'loss/train': 1.6851987838745117} 08/30/2021 15:11:11 - INFO - __main__ - Step 11374: {'lr': 0.000495068143288287, 'samples': 2183808, 'steps': 11373, 'loss/train': 1.5347603559494019} 08/30/2021 15:11:12 - INFO - __main__ - Step 11375: {'lr': 0.0004950670943529094, 'samples': 2184000, 'steps': 11374, 'loss/train': 0.24422170221805573} 08/30/2021 15:11:12 - INFO - __main__ - Step 11376: {'lr': 0.0004950660453071082, 'samples': 2184192, 'steps': 11375, 'loss/train': 1.4798616170883179} 08/30/2021 15:11:13 - INFO - __main__ - Step 11377: {'lr': 0.0004950649961508841, 'samples': 2184384, 'steps': 11376, 'loss/train': 1.8383647203445435} 08/30/2021 15:11:13 - INFO - __main__ - Step 11378: {'lr': 0.0004950639468842375, 'samples': 2184576, 'steps': 11377, 'loss/train': 1.9406672716140747} 08/30/2021 15:11:14 - INFO - __main__ - Step 11379: {'lr': 0.0004950628975071688, 'samples': 2184768, 'steps': 11378, 'loss/train': 1.8875216245651245} 08/30/2021 15:11:14 - INFO - __main__ - Step 11380: {'lr': 0.0004950618480196785, 'samples': 2184960, 'steps': 11379, 'loss/train': 2.387690305709839} 08/30/2021 15:11:15 - INFO - __main__ - Step 11381: {'lr': 0.0004950607984217674, 'samples': 2185152, 'steps': 11380, 'loss/train': 1.5684969425201416} 08/30/2021 15:11:16 - INFO - __main__ - Step 11382: {'lr': 0.0004950597487134354, 'samples': 2185344, 'steps': 11381, 'loss/train': 1.6480615139007568} 08/30/2021 15:11:16 - INFO - __main__ - Step 11383: {'lr': 0.0004950586988946834, 'samples': 2185536, 'steps': 11382, 'loss/train': 1.244276523590088} 08/30/2021 15:11:17 - INFO - __main__ - Step 11384: {'lr': 0.0004950576489655116, 'samples': 2185728, 'steps': 11383, 'loss/train': 1.6742000579833984} 08/30/2021 15:11:17 - INFO - __main__ - Step 11385: {'lr': 0.0004950565989259207, 'samples': 2185920, 'steps': 11384, 'loss/train': 4.0317583084106445} 08/30/2021 15:11:19 - INFO - __main__ - Step 11386: {'lr': 0.000495055548775911, 'samples': 2186112, 'steps': 11385, 'loss/train': 1.1463463306427002} 08/30/2021 15:11:19 - INFO - __main__ - Step 11387: {'lr': 0.0004950544985154831, 'samples': 2186304, 'steps': 11386, 'loss/train': 2.13299298286438} 08/30/2021 15:11:20 - INFO - __main__ - Step 11388: {'lr': 0.0004950534481446375, 'samples': 2186496, 'steps': 11387, 'loss/train': 1.6333603858947754} 08/30/2021 15:11:20 - INFO - __main__ - Step 11389: {'lr': 0.0004950523976633745, 'samples': 2186688, 'steps': 11388, 'loss/train': 1.558982253074646} 08/30/2021 15:11:21 - INFO - __main__ - Step 11390: {'lr': 0.0004950513470716947, 'samples': 2186880, 'steps': 11389, 'loss/train': 1.686103105545044} 08/30/2021 15:11:22 - INFO - __main__ - Step 11391: {'lr': 0.0004950502963695985, 'samples': 2187072, 'steps': 11390, 'loss/train': 1.4806197881698608} 08/30/2021 15:11:22 - INFO - __main__ - Step 11392: {'lr': 0.0004950492455570865, 'samples': 2187264, 'steps': 11391, 'loss/train': 1.9360294342041016} 08/30/2021 15:11:23 - INFO - __main__ - Step 11393: {'lr': 0.000495048194634159, 'samples': 2187456, 'steps': 11392, 'loss/train': 1.743755578994751} 08/30/2021 15:11:23 - INFO - __main__ - Step 11394: {'lr': 0.0004950471436008167, 'samples': 2187648, 'steps': 11393, 'loss/train': 1.9910410642623901} 08/30/2021 15:11:24 - INFO - __main__ - Step 11395: {'lr': 0.0004950460924570598, 'samples': 2187840, 'steps': 11394, 'loss/train': 1.5394583940505981} 08/30/2021 15:11:25 - INFO - __main__ - Step 11396: {'lr': 0.0004950450412028889, 'samples': 2188032, 'steps': 11395, 'loss/train': 2.050934314727783} 08/30/2021 15:11:26 - INFO - __main__ - Step 11397: {'lr': 0.0004950439898383047, 'samples': 2188224, 'steps': 11396, 'loss/train': 1.9023692607879639} 08/30/2021 15:11:26 - INFO - __main__ - Step 11398: {'lr': 0.0004950429383633073, 'samples': 2188416, 'steps': 11397, 'loss/train': 1.5343270301818848} 08/30/2021 15:11:26 - INFO - __main__ - Step 11399: {'lr': 0.0004950418867778973, 'samples': 2188608, 'steps': 11398, 'loss/train': 1.8388445377349854} 08/30/2021 15:11:27 - INFO - __main__ - Step 11400: {'lr': 0.0004950408350820752, 'samples': 2188800, 'steps': 11399, 'loss/train': 1.4250836372375488} 08/30/2021 15:11:28 - INFO - __main__ - Step 11401: {'lr': 0.0004950397832758415, 'samples': 2188992, 'steps': 11400, 'loss/train': 1.785843849182129} 08/30/2021 15:11:29 - INFO - __main__ - Step 11402: {'lr': 0.0004950387313591968, 'samples': 2189184, 'steps': 11401, 'loss/train': 1.565565824508667} 08/30/2021 15:11:29 - INFO - __main__ - Step 11403: {'lr': 0.0004950376793321413, 'samples': 2189376, 'steps': 11402, 'loss/train': 1.7468514442443848} 08/30/2021 15:11:29 - INFO - __main__ - Step 11404: {'lr': 0.0004950366271946756, 'samples': 2189568, 'steps': 11403, 'loss/train': 2.0025267601013184} 08/30/2021 15:11:30 - INFO - __main__ - Step 11405: {'lr': 0.0004950355749468001, 'samples': 2189760, 'steps': 11404, 'loss/train': 1.8536142110824585} 08/30/2021 15:11:30 - INFO - __main__ - Step 11406: {'lr': 0.0004950345225885155, 'samples': 2189952, 'steps': 11405, 'loss/train': 0.2752886414527893} 08/30/2021 15:11:32 - INFO - __main__ - Step 11407: {'lr': 0.0004950334701198222, 'samples': 2190144, 'steps': 11406, 'loss/train': 2.00809383392334} 08/30/2021 15:11:32 - INFO - __main__ - Step 11408: {'lr': 0.0004950324175407204, 'samples': 2190336, 'steps': 11407, 'loss/train': 1.8668293952941895} 08/30/2021 15:11:33 - INFO - __main__ - Step 11409: {'lr': 0.0004950313648512108, 'samples': 2190528, 'steps': 11408, 'loss/train': 1.761200189590454} 08/30/2021 15:11:33 - INFO - __main__ - Step 11410: {'lr': 0.0004950303120512939, 'samples': 2190720, 'steps': 11409, 'loss/train': 2.185830593109131} 08/30/2021 15:11:33 - INFO - __main__ - Step 11411: {'lr': 0.0004950292591409701, 'samples': 2190912, 'steps': 11410, 'loss/train': 1.8082395792007446} 08/30/2021 15:11:35 - INFO - __main__ - Step 11412: {'lr': 0.0004950282061202399, 'samples': 2191104, 'steps': 11411, 'loss/train': 1.9240211248397827} 08/30/2021 15:11:35 - INFO - __main__ - Step 11413: {'lr': 0.0004950271529891038, 'samples': 2191296, 'steps': 11412, 'loss/train': 2.0106911659240723} 08/30/2021 15:11:35 - INFO - __main__ - Step 11414: {'lr': 0.0004950260997475623, 'samples': 2191488, 'steps': 11413, 'loss/train': 2.187958002090454} 08/30/2021 15:11:36 - INFO - __main__ - Step 11415: {'lr': 0.0004950250463956157, 'samples': 2191680, 'steps': 11414, 'loss/train': 1.452856421470642} 08/30/2021 15:11:36 - INFO - __main__ - Step 11416: {'lr': 0.0004950239929332646, 'samples': 2191872, 'steps': 11415, 'loss/train': 1.5508602857589722} 08/30/2021 15:11:38 - INFO - __main__ - Step 11417: {'lr': 0.0004950229393605095, 'samples': 2192064, 'steps': 11416, 'loss/train': 1.605417013168335} 08/30/2021 15:11:38 - INFO - __main__ - Step 11418: {'lr': 0.0004950218856773509, 'samples': 2192256, 'steps': 11417, 'loss/train': 1.8712059259414673} 08/30/2021 15:11:38 - INFO - __main__ - Step 11419: {'lr': 0.0004950208318837892, 'samples': 2192448, 'steps': 11418, 'loss/train': 1.351062297821045} 08/30/2021 15:11:39 - INFO - __main__ - Step 11420: {'lr': 0.0004950197779798248, 'samples': 2192640, 'steps': 11419, 'loss/train': 2.036375045776367} 08/30/2021 15:11:39 - INFO - __main__ - Step 11421: {'lr': 0.0004950187239654584, 'samples': 2192832, 'steps': 11420, 'loss/train': 1.9271739721298218} 08/30/2021 15:11:40 - INFO - __main__ - Step 11422: {'lr': 0.0004950176698406903, 'samples': 2193024, 'steps': 11421, 'loss/train': 1.716298222541809} 08/30/2021 15:11:41 - INFO - __main__ - Step 11423: {'lr': 0.000495016615605521, 'samples': 2193216, 'steps': 11422, 'loss/train': 1.8552886247634888} 08/30/2021 15:11:41 - INFO - __main__ - Step 11424: {'lr': 0.0004950155612599511, 'samples': 2193408, 'steps': 11423, 'loss/train': 1.9429852962493896} 08/30/2021 15:11:42 - INFO - __main__ - Step 11425: {'lr': 0.0004950145068039808, 'samples': 2193600, 'steps': 11424, 'loss/train': 1.621841311454773} 08/30/2021 15:11:42 - INFO - __main__ - Step 11426: {'lr': 0.0004950134522376108, 'samples': 2193792, 'steps': 11425, 'loss/train': 1.1670444011688232} 08/30/2021 15:11:44 - INFO - __main__ - Step 11427: {'lr': 0.0004950123975608415, 'samples': 2193984, 'steps': 11426, 'loss/train': 1.1248893737792969} 08/30/2021 15:11:44 - INFO - __main__ - Step 11428: {'lr': 0.0004950113427736734, 'samples': 2194176, 'steps': 11427, 'loss/train': 1.8337293863296509} 08/30/2021 15:11:44 - INFO - __main__ - Step 11429: {'lr': 0.000495010287876107, 'samples': 2194368, 'steps': 11428, 'loss/train': 1.7891881465911865} 08/30/2021 15:11:45 - INFO - __main__ - Step 11430: {'lr': 0.0004950092328681428, 'samples': 2194560, 'steps': 11429, 'loss/train': 1.9474878311157227} 08/30/2021 15:11:45 - INFO - __main__ - Step 11431: {'lr': 0.0004950081777497812, 'samples': 2194752, 'steps': 11430, 'loss/train': 0.9480117559432983} 08/30/2021 15:11:47 - INFO - __main__ - Step 11432: {'lr': 0.0004950071225210226, 'samples': 2194944, 'steps': 11431, 'loss/train': 1.7373414039611816} 08/30/2021 15:11:47 - INFO - __main__ - Step 11433: {'lr': 0.0004950060671818676, 'samples': 2195136, 'steps': 11432, 'loss/train': 1.7810802459716797} 08/30/2021 15:11:47 - INFO - __main__ - Step 11434: {'lr': 0.0004950050117323167, 'samples': 2195328, 'steps': 11433, 'loss/train': 0.7894968390464783} 08/30/2021 15:11:48 - INFO - __main__ - Step 11435: {'lr': 0.0004950039561723703, 'samples': 2195520, 'steps': 11434, 'loss/train': 1.410385012626648} 08/30/2021 15:11:48 - INFO - __main__ - Step 11436: {'lr': 0.0004950029005020289, 'samples': 2195712, 'steps': 11435, 'loss/train': 1.2500255107879639} 08/30/2021 15:11:50 - INFO - __main__ - Step 11437: {'lr': 0.0004950018447212929, 'samples': 2195904, 'steps': 11436, 'loss/train': 2.069624423980713} 08/30/2021 15:11:51 - INFO - __main__ - Step 11438: {'lr': 0.000495000788830163, 'samples': 2196096, 'steps': 11437, 'loss/train': 2.014286994934082} 08/30/2021 15:11:51 - INFO - __main__ - Step 11439: {'lr': 0.0004949997328286394, 'samples': 2196288, 'steps': 11438, 'loss/train': 1.1920604705810547} 08/30/2021 15:11:51 - INFO - __main__ - Step 11440: {'lr': 0.0004949986767167228, 'samples': 2196480, 'steps': 11439, 'loss/train': 1.7225277423858643} 08/30/2021 15:11:52 - INFO - __main__ - Step 11441: {'lr': 0.0004949976204944135, 'samples': 2196672, 'steps': 11440, 'loss/train': 1.8489760160446167} 08/30/2021 15:11:52 - INFO - __main__ - Step 11442: {'lr': 0.0004949965641617121, 'samples': 2196864, 'steps': 11441, 'loss/train': 1.3143986463546753} 08/30/2021 15:11:53 - INFO - __main__ - Step 11443: {'lr': 0.000494995507718619, 'samples': 2197056, 'steps': 11442, 'loss/train': 2.4320342540740967} 08/30/2021 15:11:54 - INFO - __main__ - Step 11444: {'lr': 0.0004949944511651347, 'samples': 2197248, 'steps': 11443, 'loss/train': 1.6460480690002441} 08/30/2021 15:11:54 - INFO - __main__ - Step 11445: {'lr': 0.0004949933945012597, 'samples': 2197440, 'steps': 11444, 'loss/train': 2.2736902236938477} 08/30/2021 15:11:55 - INFO - __main__ - Step 11446: {'lr': 0.0004949923377269945, 'samples': 2197632, 'steps': 11445, 'loss/train': 1.8962833881378174} 08/30/2021 15:11:55 - INFO - __main__ - Step 11447: {'lr': 0.0004949912808423394, 'samples': 2197824, 'steps': 11446, 'loss/train': 1.2450982332229614} 08/30/2021 15:11:57 - INFO - __main__ - Step 11448: {'lr': 0.000494990223847295, 'samples': 2198016, 'steps': 11447, 'loss/train': 1.5632365942001343} 08/30/2021 15:11:57 - INFO - __main__ - Step 11449: {'lr': 0.000494989166741862, 'samples': 2198208, 'steps': 11448, 'loss/train': 1.8916257619857788} 08/30/2021 15:11:57 - INFO - __main__ - Step 11450: {'lr': 0.0004949881095260405, 'samples': 2198400, 'steps': 11449, 'loss/train': 1.5801581144332886} 08/30/2021 15:11:58 - INFO - __main__ - Step 11451: {'lr': 0.0004949870521998312, 'samples': 2198592, 'steps': 11450, 'loss/train': 1.127855658531189} 08/30/2021 15:11:58 - INFO - __main__ - Step 11452: {'lr': 0.0004949859947632344, 'samples': 2198784, 'steps': 11451, 'loss/train': 1.5080382823944092} 08/30/2021 15:12:00 - INFO - __main__ - Step 11453: {'lr': 0.0004949849372162509, 'samples': 2198976, 'steps': 11452, 'loss/train': 1.588152289390564} 08/30/2021 15:12:00 - INFO - __main__ - Step 11454: {'lr': 0.0004949838795588808, 'samples': 2199168, 'steps': 11453, 'loss/train': 1.9238343238830566} 08/30/2021 15:12:00 - INFO - __main__ - Step 11455: {'lr': 0.0004949828217911248, 'samples': 2199360, 'steps': 11454, 'loss/train': 1.08119535446167} 08/30/2021 15:12:01 - INFO - __main__ - Step 11456: {'lr': 0.0004949817639129832, 'samples': 2199552, 'steps': 11455, 'loss/train': 1.9389153718948364} 08/30/2021 15:12:01 - INFO - __main__ - Step 11457: {'lr': 0.0004949807059244568, 'samples': 2199744, 'steps': 11456, 'loss/train': 1.6951968669891357} 08/30/2021 15:12:03 - INFO - __main__ - Step 11458: {'lr': 0.0004949796478255458, 'samples': 2199936, 'steps': 11457, 'loss/train': 1.8409918546676636} 08/30/2021 15:12:04 - INFO - __main__ - Step 11459: {'lr': 0.0004949785896162507, 'samples': 2200128, 'steps': 11458, 'loss/train': 0.18376825749874115} 08/30/2021 15:12:04 - INFO - __main__ - Step 11460: {'lr': 0.0004949775312965721, 'samples': 2200320, 'steps': 11459, 'loss/train': 0.5928048491477966} 08/30/2021 15:12:04 - INFO - __main__ - Step 11461: {'lr': 0.0004949764728665103, 'samples': 2200512, 'steps': 11460, 'loss/train': 2.0808823108673096} 08/30/2021 15:12:05 - INFO - __main__ - Step 11462: {'lr': 0.000494975414326066, 'samples': 2200704, 'steps': 11461, 'loss/train': 1.1502190828323364} 08/30/2021 15:12:05 - INFO - __main__ - Step 11463: {'lr': 0.0004949743556752395, 'samples': 2200896, 'steps': 11462, 'loss/train': 2.22263240814209} 08/30/2021 15:12:06 - INFO - __main__ - Step 11464: {'lr': 0.0004949732969140313, 'samples': 2201088, 'steps': 11463, 'loss/train': 1.1926612854003906} 08/30/2021 15:12:07 - INFO - __main__ - Step 11465: {'lr': 0.000494972238042442, 'samples': 2201280, 'steps': 11464, 'loss/train': 1.6181837320327759} 08/30/2021 15:12:07 - INFO - __main__ - Step 11466: {'lr': 0.0004949711790604719, 'samples': 2201472, 'steps': 11465, 'loss/train': 2.271275520324707} 08/30/2021 15:12:08 - INFO - __main__ - Step 11467: {'lr': 0.0004949701199681217, 'samples': 2201664, 'steps': 11466, 'loss/train': 2.116138458251953} 08/30/2021 15:12:08 - INFO - __main__ - Step 11468: {'lr': 0.0004949690607653916, 'samples': 2201856, 'steps': 11467, 'loss/train': 2.0212857723236084} 08/30/2021 15:12:08 - INFO - __main__ - Step 11469: {'lr': 0.0004949680014522822, 'samples': 2202048, 'steps': 11468, 'loss/train': 2.1533942222595215} 08/30/2021 15:12:10 - INFO - __main__ - Step 11470: {'lr': 0.0004949669420287941, 'samples': 2202240, 'steps': 11469, 'loss/train': 1.9581927061080933} 08/30/2021 15:12:10 - INFO - __main__ - Step 11471: {'lr': 0.0004949658824949277, 'samples': 2202432, 'steps': 11470, 'loss/train': 1.466626763343811} 08/30/2021 15:12:11 - INFO - __main__ - Step 11472: {'lr': 0.0004949648228506834, 'samples': 2202624, 'steps': 11471, 'loss/train': 2.671245574951172} 08/30/2021 15:12:11 - INFO - __main__ - Step 11473: {'lr': 0.0004949637630960618, 'samples': 2202816, 'steps': 11472, 'loss/train': 1.816586971282959} 08/30/2021 15:12:11 - INFO - __main__ - Step 11474: {'lr': 0.0004949627032310632, 'samples': 2203008, 'steps': 11473, 'loss/train': 2.005235195159912} 08/30/2021 15:12:13 - INFO - __main__ - Step 11475: {'lr': 0.0004949616432556882, 'samples': 2203200, 'steps': 11474, 'loss/train': 1.8697184324264526} 08/30/2021 15:12:13 - INFO - __main__ - Step 11476: {'lr': 0.0004949605831699373, 'samples': 2203392, 'steps': 11475, 'loss/train': 1.800644874572754} 08/30/2021 15:12:14 - INFO - __main__ - Step 11477: {'lr': 0.000494959522973811, 'samples': 2203584, 'steps': 11476, 'loss/train': 2.8131799697875977} 08/30/2021 15:12:14 - INFO - __main__ - Step 11478: {'lr': 0.0004949584626673096, 'samples': 2203776, 'steps': 11477, 'loss/train': 1.9296927452087402} 08/30/2021 15:12:14 - INFO - __main__ - Step 11479: {'lr': 0.0004949574022504338, 'samples': 2203968, 'steps': 11478, 'loss/train': 2.1797196865081787} 08/30/2021 15:12:15 - INFO - __main__ - Step 11480: {'lr': 0.0004949563417231838, 'samples': 2204160, 'steps': 11479, 'loss/train': 1.968984842300415} 08/30/2021 15:12:16 - INFO - __main__ - Step 11481: {'lr': 0.0004949552810855605, 'samples': 2204352, 'steps': 11480, 'loss/train': 1.8311598300933838} 08/30/2021 15:12:17 - INFO - __main__ - Step 11482: {'lr': 0.000494954220337564, 'samples': 2204544, 'steps': 11481, 'loss/train': 2.0590016841888428} 08/30/2021 15:12:17 - INFO - __main__ - Step 11483: {'lr': 0.0004949531594791948, 'samples': 2204736, 'steps': 11482, 'loss/train': 2.3185112476348877} 08/30/2021 15:12:18 - INFO - __main__ - Step 11484: {'lr': 0.0004949520985104536, 'samples': 2204928, 'steps': 11483, 'loss/train': 3.4016640186309814} 08/30/2021 15:12:18 - INFO - __main__ - Step 11485: {'lr': 0.0004949510374313409, 'samples': 2205120, 'steps': 11484, 'loss/train': 2.110018014907837} 08/30/2021 15:12:19 - INFO - __main__ - Step 11486: {'lr': 0.0004949499762418568, 'samples': 2205312, 'steps': 11485, 'loss/train': 1.697204828262329} 08/30/2021 15:12:20 - INFO - __main__ - Step 11487: {'lr': 0.0004949489149420021, 'samples': 2205504, 'steps': 11486, 'loss/train': 1.617307424545288} 08/30/2021 15:12:20 - INFO - __main__ - Step 11488: {'lr': 0.0004949478535317773, 'samples': 2205696, 'steps': 11487, 'loss/train': 2.041067600250244} 08/30/2021 15:12:21 - INFO - __main__ - Step 11489: {'lr': 0.0004949467920111827, 'samples': 2205888, 'steps': 11488, 'loss/train': 1.648711919784546} 08/30/2021 15:12:21 - INFO - __main__ - Step 11490: {'lr': 0.0004949457303802189, 'samples': 2206080, 'steps': 11489, 'loss/train': 2.0404109954833984} 08/30/2021 15:12:22 - INFO - __main__ - Step 11491: {'lr': 0.0004949446686388862, 'samples': 2206272, 'steps': 11490, 'loss/train': 2.035813093185425} 08/30/2021 15:12:23 - INFO - __main__ - Step 11492: {'lr': 0.0004949436067871854, 'samples': 2206464, 'steps': 11491, 'loss/train': 1.2325630187988281} 08/30/2021 15:12:23 - INFO - __main__ - Step 11493: {'lr': 0.0004949425448251166, 'samples': 2206656, 'steps': 11492, 'loss/train': 1.953182578086853} 08/30/2021 15:12:24 - INFO - __main__ - Step 11494: {'lr': 0.0004949414827526805, 'samples': 2206848, 'steps': 11493, 'loss/train': 1.9621326923370361} 08/30/2021 15:12:24 - INFO - __main__ - Step 11495: {'lr': 0.0004949404205698777, 'samples': 2207040, 'steps': 11494, 'loss/train': 2.5060646533966064} 08/30/2021 15:12:26 - INFO - __main__ - Step 11496: {'lr': 0.0004949393582767084, 'samples': 2207232, 'steps': 11495, 'loss/train': 1.8357990980148315} 08/30/2021 15:12:27 - INFO - __main__ - Step 11497: {'lr': 0.0004949382958731733, 'samples': 2207424, 'steps': 11496, 'loss/train': 0.8789867758750916} 08/30/2021 15:12:27 - INFO - __main__ - Step 11498: {'lr': 0.0004949372333592728, 'samples': 2207616, 'steps': 11497, 'loss/train': 1.5982937812805176} 08/30/2021 15:12:27 - INFO - __main__ - Step 11499: {'lr': 0.0004949361707350072, 'samples': 2207808, 'steps': 11498, 'loss/train': 1.4534696340560913} 08/30/2021 15:12:28 - INFO - __main__ - Step 11500: {'lr': 0.0004949351080003773, 'samples': 2208000, 'steps': 11499, 'loss/train': 2.250380516052246} 08/30/2021 15:12:29 - INFO - __main__ - Step 11501: {'lr': 0.0004949340451553833, 'samples': 2208192, 'steps': 11500, 'loss/train': 1.8547236919403076} 08/30/2021 15:12:30 - INFO - __main__ - Step 11502: {'lr': 0.0004949329822000259, 'samples': 2208384, 'steps': 11501, 'loss/train': 1.9595515727996826} 08/30/2021 15:12:30 - INFO - __main__ - Step 11503: {'lr': 0.0004949319191343053, 'samples': 2208576, 'steps': 11502, 'loss/train': 1.8780261278152466} 08/30/2021 15:12:30 - INFO - __main__ - Step 11504: {'lr': 0.0004949308559582224, 'samples': 2208768, 'steps': 11503, 'loss/train': 2.0255348682403564} 08/30/2021 15:12:31 - INFO - __main__ - Step 11505: {'lr': 0.0004949297926717772, 'samples': 2208960, 'steps': 11504, 'loss/train': 1.9734972715377808} 08/30/2021 15:12:32 - INFO - __main__ - Step 11506: {'lr': 0.0004949287292749705, 'samples': 2209152, 'steps': 11505, 'loss/train': 2.2389514446258545} 08/30/2021 15:12:33 - INFO - __main__ - Step 11507: {'lr': 0.0004949276657678028, 'samples': 2209344, 'steps': 11506, 'loss/train': 1.9121968746185303} 08/30/2021 15:12:33 - INFO - __main__ - Step 11508: {'lr': 0.0004949266021502744, 'samples': 2209536, 'steps': 11507, 'loss/train': 2.019136428833008} 08/30/2021 15:12:34 - INFO - __main__ - Step 11509: {'lr': 0.0004949255384223859, 'samples': 2209728, 'steps': 11508, 'loss/train': 1.6755554676055908} 08/30/2021 15:12:34 - INFO - __main__ - Step 11510: {'lr': 0.0004949244745841377, 'samples': 2209920, 'steps': 11509, 'loss/train': 1.882054090499878} 08/30/2021 15:12:34 - INFO - __main__ - Step 11511: {'lr': 0.0004949234106355302, 'samples': 2210112, 'steps': 11510, 'loss/train': 2.2465193271636963} 08/30/2021 15:12:36 - INFO - __main__ - Step 11512: {'lr': 0.0004949223465765642, 'samples': 2210304, 'steps': 11511, 'loss/train': 0.22742246091365814} 08/30/2021 15:12:36 - INFO - __main__ - Step 11513: {'lr': 0.0004949212824072398, 'samples': 2210496, 'steps': 11512, 'loss/train': 2.0608224868774414} 08/30/2021 15:12:36 - INFO - __main__ - Step 11514: {'lr': 0.0004949202181275577, 'samples': 2210688, 'steps': 11513, 'loss/train': 2.3194799423217773} 08/30/2021 15:12:37 - INFO - __main__ - Step 11515: {'lr': 0.0004949191537375184, 'samples': 2210880, 'steps': 11514, 'loss/train': 1.2681190967559814} 08/30/2021 15:12:37 - INFO - __main__ - Step 11516: {'lr': 0.0004949180892371223, 'samples': 2211072, 'steps': 11515, 'loss/train': 2.259357213973999} 08/30/2021 15:12:39 - INFO - __main__ - Step 11517: {'lr': 0.0004949170246263697, 'samples': 2211264, 'steps': 11516, 'loss/train': 2.110447645187378} 08/30/2021 15:12:40 - INFO - __main__ - Step 11518: {'lr': 0.0004949159599052614, 'samples': 2211456, 'steps': 11517, 'loss/train': 1.9945828914642334} 08/30/2021 15:12:40 - INFO - __main__ - Step 11519: {'lr': 0.0004949148950737978, 'samples': 2211648, 'steps': 11518, 'loss/train': 1.3599166870117188} 08/30/2021 15:12:40 - INFO - __main__ - Step 11520: {'lr': 0.0004949138301319793, 'samples': 2211840, 'steps': 11519, 'loss/train': 1.9862539768218994} 08/30/2021 15:12:41 - INFO - __main__ - Step 11521: {'lr': 0.0004949127650798063, 'samples': 2212032, 'steps': 11520, 'loss/train': 1.6792529821395874} 08/30/2021 15:12:42 - INFO - __main__ - Step 11522: {'lr': 0.0004949116999172795, 'samples': 2212224, 'steps': 11521, 'loss/train': 0.1359776258468628} 08/30/2021 15:12:43 - INFO - __main__ - Step 11523: {'lr': 0.0004949106346443992, 'samples': 2212416, 'steps': 11522, 'loss/train': 1.5791847705841064} 08/30/2021 15:12:43 - INFO - __main__ - Step 11524: {'lr': 0.0004949095692611661, 'samples': 2212608, 'steps': 11523, 'loss/train': 1.855224847793579} 08/30/2021 15:12:43 - INFO - __main__ - Step 11525: {'lr': 0.0004949085037675803, 'samples': 2212800, 'steps': 11524, 'loss/train': 0.5812322497367859} 08/30/2021 15:12:44 - INFO - __main__ - Step 11526: {'lr': 0.0004949074381636427, 'samples': 2212992, 'steps': 11525, 'loss/train': 1.8495157957077026} 08/30/2021 15:12:45 - INFO - __main__ - Step 11527: {'lr': 0.0004949063724493534, 'samples': 2213184, 'steps': 11526, 'loss/train': 1.6610225439071655} 08/30/2021 15:12:46 - INFO - __main__ - Step 11528: {'lr': 0.0004949053066247133, 'samples': 2213376, 'steps': 11527, 'loss/train': 1.7594808340072632} 08/30/2021 15:12:46 - INFO - __main__ - Step 11529: {'lr': 0.0004949042406897225, 'samples': 2213568, 'steps': 11528, 'loss/train': 1.9221631288528442} 08/30/2021 15:12:46 - INFO - __main__ - Step 11530: {'lr': 0.0004949031746443816, 'samples': 2213760, 'steps': 11529, 'loss/train': 2.2979493141174316} 08/30/2021 15:12:47 - INFO - __main__ - Step 11531: {'lr': 0.0004949021084886912, 'samples': 2213952, 'steps': 11530, 'loss/train': 1.7816247940063477} 08/30/2021 15:12:47 - INFO - __main__ - Step 11532: {'lr': 0.0004949010422226517, 'samples': 2214144, 'steps': 11531, 'loss/train': 1.6920993328094482} 08/30/2021 15:12:48 - INFO - __main__ - Step 11533: {'lr': 0.0004948999758462634, 'samples': 2214336, 'steps': 11532, 'loss/train': 1.6868573427200317} 08/30/2021 15:12:49 - INFO - __main__ - Step 11534: {'lr': 0.000494898909359527, 'samples': 2214528, 'steps': 11533, 'loss/train': 1.9775546789169312} 08/30/2021 15:12:49 - INFO - __main__ - Step 11535: {'lr': 0.0004948978427624431, 'samples': 2214720, 'steps': 11534, 'loss/train': 1.809630274772644} 08/30/2021 15:12:50 - INFO - __main__ - Step 11536: {'lr': 0.0004948967760550119, 'samples': 2214912, 'steps': 11535, 'loss/train': 1.6731148958206177} 08/30/2021 15:12:50 - INFO - __main__ - Step 11537: {'lr': 0.000494895709237234, 'samples': 2215104, 'steps': 11536, 'loss/train': 0.14407263696193695} 08/30/2021 15:12:52 - INFO - __main__ - Step 11538: {'lr': 0.0004948946423091099, 'samples': 2215296, 'steps': 11537, 'loss/train': 1.6394861936569214} 08/30/2021 15:12:52 - INFO - __main__ - Step 11539: {'lr': 0.0004948935752706401, 'samples': 2215488, 'steps': 11538, 'loss/train': 1.3665229082107544} 08/30/2021 15:12:52 - INFO - __main__ - Step 11540: {'lr': 0.0004948925081218248, 'samples': 2215680, 'steps': 11539, 'loss/train': 1.4844862222671509} 08/30/2021 15:12:53 - INFO - __main__ - Step 11541: {'lr': 0.000494891440862665, 'samples': 2215872, 'steps': 11540, 'loss/train': 1.7068301439285278} 08/30/2021 15:12:53 - INFO - __main__ - Step 11542: {'lr': 0.0004948903734931608, 'samples': 2216064, 'steps': 11541, 'loss/train': 1.3557708263397217} 08/30/2021 15:12:55 - INFO - __main__ - Step 11543: {'lr': 0.0004948893060133128, 'samples': 2216256, 'steps': 11542, 'loss/train': 0.9980223178863525} 08/30/2021 15:12:56 - INFO - __main__ - Step 11544: {'lr': 0.0004948882384231213, 'samples': 2216448, 'steps': 11543, 'loss/train': 1.9851670265197754} 08/30/2021 15:12:56 - INFO - __main__ - Step 11545: {'lr': 0.0004948871707225871, 'samples': 2216640, 'steps': 11544, 'loss/train': 1.6814534664154053} 08/30/2021 15:12:56 - INFO - __main__ - Step 11546: {'lr': 0.0004948861029117104, 'samples': 2216832, 'steps': 11545, 'loss/train': 2.059412717819214} 08/30/2021 15:12:57 - INFO - __main__ - Step 11547: {'lr': 0.0004948850349904919, 'samples': 2217024, 'steps': 11546, 'loss/train': 1.3900164365768433} 08/30/2021 15:12:57 - INFO - __main__ - Step 11548: {'lr': 0.0004948839669589319, 'samples': 2217216, 'steps': 11547, 'loss/train': 2.05084228515625} 08/30/2021 15:12:57 - INFO - __main__ - Step 11549: {'lr': 0.000494882898817031, 'samples': 2217408, 'steps': 11548, 'loss/train': 0.1329517364501953} 08/30/2021 15:12:59 - INFO - __main__ - Step 11550: {'lr': 0.0004948818305647897, 'samples': 2217600, 'steps': 11549, 'loss/train': 0.5742965340614319} 08/30/2021 15:13:00 - INFO - __main__ - Step 11551: {'lr': 0.0004948807622022083, 'samples': 2217792, 'steps': 11550, 'loss/train': 1.0276354551315308} 08/30/2021 15:13:00 - INFO - __main__ - Step 11552: {'lr': 0.0004948796937292875, 'samples': 2217984, 'steps': 11551, 'loss/train': 2.0554378032684326} 08/30/2021 15:13:01 - INFO - __main__ - Step 11553: {'lr': 0.0004948786251460277, 'samples': 2218176, 'steps': 11552, 'loss/train': 1.0231890678405762} 08/30/2021 15:13:01 - INFO - __main__ - Step 11554: {'lr': 0.0004948775564524294, 'samples': 2218368, 'steps': 11553, 'loss/train': 1.4752169847488403} 08/30/2021 15:13:03 - INFO - __main__ - Step 11555: {'lr': 0.000494876487648493, 'samples': 2218560, 'steps': 11554, 'loss/train': 1.8001103401184082} 08/30/2021 15:13:03 - INFO - __main__ - Step 11556: {'lr': 0.0004948754187342189, 'samples': 2218752, 'steps': 11555, 'loss/train': 1.4499326944351196} 08/30/2021 15:13:03 - INFO - __main__ - Step 11557: {'lr': 0.0004948743497096079, 'samples': 2218944, 'steps': 11556, 'loss/train': 1.8420255184173584} 08/30/2021 15:13:04 - INFO - __main__ - Step 11558: {'lr': 0.0004948732805746604, 'samples': 2219136, 'steps': 11557, 'loss/train': 2.243739128112793} 08/30/2021 15:13:04 - INFO - __main__ - Step 11559: {'lr': 0.0004948722113293766, 'samples': 2219328, 'steps': 11558, 'loss/train': 1.9791109561920166} 08/30/2021 15:13:06 - INFO - __main__ - Step 11560: {'lr': 0.000494871141973757, 'samples': 2219520, 'steps': 11559, 'loss/train': 1.691980242729187} 08/30/2021 15:13:06 - INFO - __main__ - Step 11561: {'lr': 0.0004948700725078025, 'samples': 2219712, 'steps': 11560, 'loss/train': 1.6796391010284424} 08/30/2021 15:13:06 - INFO - __main__ - Step 11562: {'lr': 0.0004948690029315133, 'samples': 2219904, 'steps': 11561, 'loss/train': 2.0924324989318848} 08/30/2021 15:13:07 - INFO - __main__ - Step 11563: {'lr': 0.0004948679332448899, 'samples': 2220096, 'steps': 11562, 'loss/train': 1.923234224319458} 08/30/2021 15:13:07 - INFO - __main__ - Step 11564: {'lr': 0.0004948668634479327, 'samples': 2220288, 'steps': 11563, 'loss/train': 1.7105976343154907} 08/30/2021 15:13:09 - INFO - __main__ - Step 11565: {'lr': 0.0004948657935406423, 'samples': 2220480, 'steps': 11564, 'loss/train': 1.4222297668457031} 08/30/2021 15:13:09 - INFO - __main__ - Step 11566: {'lr': 0.0004948647235230192, 'samples': 2220672, 'steps': 11565, 'loss/train': 0.7465553283691406} 08/30/2021 15:13:09 - INFO - __main__ - Step 11567: {'lr': 0.0004948636533950638, 'samples': 2220864, 'steps': 11566, 'loss/train': 1.5538454055786133} 08/30/2021 15:13:10 - INFO - __main__ - Step 11568: {'lr': 0.0004948625831567766, 'samples': 2221056, 'steps': 11567, 'loss/train': 1.9415048360824585} 08/30/2021 15:13:10 - INFO - __main__ - Step 11569: {'lr': 0.000494861512808158, 'samples': 2221248, 'steps': 11568, 'loss/train': 0.1553996354341507} 08/30/2021 15:13:12 - INFO - __main__ - Step 11570: {'lr': 0.0004948604423492088, 'samples': 2221440, 'steps': 11569, 'loss/train': 1.7491966485977173} 08/30/2021 15:13:12 - INFO - __main__ - Step 11571: {'lr': 0.0004948593717799292, 'samples': 2221632, 'steps': 11570, 'loss/train': 2.1043777465820312} 08/30/2021 15:13:13 - INFO - __main__ - Step 11572: {'lr': 0.0004948583011003196, 'samples': 2221824, 'steps': 11571, 'loss/train': 1.8829469680786133} 08/30/2021 15:13:13 - INFO - __main__ - Step 11573: {'lr': 0.0004948572303103808, 'samples': 2222016, 'steps': 11572, 'loss/train': 1.7994927167892456} 08/30/2021 15:13:13 - INFO - __main__ - Step 11574: {'lr': 0.0004948561594101129, 'samples': 2222208, 'steps': 11573, 'loss/train': 0.2517626881599426} 08/30/2021 15:13:15 - INFO - __main__ - Step 11575: {'lr': 0.0004948550883995168, 'samples': 2222400, 'steps': 11574, 'loss/train': 1.8151077032089233} 08/30/2021 15:13:15 - INFO - __main__ - Step 11576: {'lr': 0.0004948540172785927, 'samples': 2222592, 'steps': 11575, 'loss/train': 1.1062935590744019} 08/30/2021 15:13:16 - INFO - __main__ - Step 11577: {'lr': 0.0004948529460473412, 'samples': 2222784, 'steps': 11576, 'loss/train': 1.9714395999908447} 08/30/2021 15:13:16 - INFO - __main__ - Step 11578: {'lr': 0.0004948518747057626, 'samples': 2222976, 'steps': 11577, 'loss/train': 2.0570592880249023} 08/30/2021 15:13:17 - INFO - __main__ - Step 11579: {'lr': 0.0004948508032538578, 'samples': 2223168, 'steps': 11578, 'loss/train': 1.7397583723068237} 08/30/2021 15:13:19 - INFO - __main__ - Step 11580: {'lr': 0.0004948497316916267, 'samples': 2223360, 'steps': 11579, 'loss/train': 1.615159273147583} 08/30/2021 15:13:20 - INFO - __main__ - Step 11581: {'lr': 0.0004948486600190702, 'samples': 2223552, 'steps': 11580, 'loss/train': 1.557171106338501} 08/30/2021 15:13:20 - INFO - __main__ - Step 11582: {'lr': 0.0004948475882361888, 'samples': 2223744, 'steps': 11581, 'loss/train': 1.523047685623169} 08/30/2021 15:13:20 - INFO - __main__ - Step 11583: {'lr': 0.0004948465163429828, 'samples': 2223936, 'steps': 11582, 'loss/train': 1.893827199935913} 08/30/2021 15:13:21 - INFO - __main__ - Step 11584: {'lr': 0.0004948454443394527, 'samples': 2224128, 'steps': 11583, 'loss/train': 2.1726720333099365} 08/30/2021 15:13:21 - INFO - __main__ - Step 11585: {'lr': 0.000494844372225599, 'samples': 2224320, 'steps': 11584, 'loss/train': 1.9161070585250854} 08/30/2021 15:13:21 - INFO - __main__ - Step 11586: {'lr': 0.0004948433000014222, 'samples': 2224512, 'steps': 11585, 'loss/train': 1.873349666595459} 08/30/2021 15:13:22 - INFO - __main__ - Step 11587: {'lr': 0.0004948422276669228, 'samples': 2224704, 'steps': 11586, 'loss/train': 1.187298059463501} 08/30/2021 15:13:23 - INFO - __main__ - Step 11588: {'lr': 0.0004948411552221012, 'samples': 2224896, 'steps': 11587, 'loss/train': 1.4286316633224487} 08/30/2021 15:13:24 - INFO - __main__ - Step 11589: {'lr': 0.000494840082666958, 'samples': 2225088, 'steps': 11588, 'loss/train': 1.7936506271362305} 08/30/2021 15:13:24 - INFO - __main__ - Step 11590: {'lr': 0.0004948390100014937, 'samples': 2225280, 'steps': 11589, 'loss/train': 1.4247270822525024} 08/30/2021 15:13:24 - INFO - __main__ - Step 11591: {'lr': 0.0004948379372257086, 'samples': 2225472, 'steps': 11590, 'loss/train': 1.708005428314209} 08/30/2021 15:13:25 - INFO - __main__ - Step 11592: {'lr': 0.0004948368643396035, 'samples': 2225664, 'steps': 11591, 'loss/train': 2.1636524200439453} 08/30/2021 15:13:27 - INFO - __main__ - Step 11593: {'lr': 0.0004948357913431786, 'samples': 2225856, 'steps': 11592, 'loss/train': 2.1388227939605713} 08/30/2021 15:13:27 - INFO - __main__ - Step 11594: {'lr': 0.0004948347182364344, 'samples': 2226048, 'steps': 11593, 'loss/train': 2.0362439155578613} 08/30/2021 15:13:27 - INFO - __main__ - Step 11595: {'lr': 0.0004948336450193715, 'samples': 2226240, 'steps': 11594, 'loss/train': 1.5221621990203857} 08/30/2021 15:13:28 - INFO - __main__ - Step 11596: {'lr': 0.0004948325716919904, 'samples': 2226432, 'steps': 11595, 'loss/train': 1.754105806350708} 08/30/2021 15:13:28 - INFO - __main__ - Step 11597: {'lr': 0.0004948314982542914, 'samples': 2226624, 'steps': 11596, 'loss/train': 1.9655364751815796} 08/30/2021 15:13:28 - INFO - __main__ - Step 11598: {'lr': 0.0004948304247062752, 'samples': 2226816, 'steps': 11597, 'loss/train': 1.792184591293335} 08/30/2021 15:13:30 - INFO - __main__ - Step 11599: {'lr': 0.0004948293510479421, 'samples': 2227008, 'steps': 11598, 'loss/train': 0.968758761882782} 08/30/2021 15:13:31 - INFO - __main__ - Step 11600: {'lr': 0.0004948282772792927, 'samples': 2227200, 'steps': 11599, 'loss/train': 1.2551875114440918} 08/30/2021 15:13:31 - INFO - __main__ - Step 11601: {'lr': 0.0004948272034003275, 'samples': 2227392, 'steps': 11600, 'loss/train': 1.6902942657470703} 08/30/2021 15:13:31 - INFO - __main__ - Step 11602: {'lr': 0.000494826129411047, 'samples': 2227584, 'steps': 11601, 'loss/train': 0.12489646673202515} 08/30/2021 15:13:32 - INFO - __main__ - Step 11603: {'lr': 0.0004948250553114516, 'samples': 2227776, 'steps': 11602, 'loss/train': 0.17888374626636505} 08/30/2021 15:13:32 - INFO - __main__ - Step 11604: {'lr': 0.0004948239811015416, 'samples': 2227968, 'steps': 11603, 'loss/train': 1.967453956604004} 08/30/2021 15:13:34 - INFO - __main__ - Step 11605: {'lr': 0.0004948229067813179, 'samples': 2228160, 'steps': 11604, 'loss/train': 1.8223035335540771} 08/30/2021 15:13:35 - INFO - __main__ - Step 11606: {'lr': 0.0004948218323507807, 'samples': 2228352, 'steps': 11605, 'loss/train': 2.1264188289642334} 08/30/2021 15:13:35 - INFO - __main__ - Step 11607: {'lr': 0.0004948207578099306, 'samples': 2228544, 'steps': 11606, 'loss/train': 1.6417908668518066} 08/30/2021 15:13:36 - INFO - __main__ - Step 11608: {'lr': 0.000494819683158768, 'samples': 2228736, 'steps': 11607, 'loss/train': 2.1653733253479004} 08/30/2021 15:13:36 - INFO - __main__ - Step 11609: {'lr': 0.0004948186083972934, 'samples': 2228928, 'steps': 11608, 'loss/train': 0.1120835468173027} 08/30/2021 15:13:38 - INFO - __main__ - Step 11610: {'lr': 0.0004948175335255075, 'samples': 2229120, 'steps': 11609, 'loss/train': 1.5846641063690186} 08/30/2021 15:13:38 - INFO - __main__ - Step 11611: {'lr': 0.0004948164585434104, 'samples': 2229312, 'steps': 11610, 'loss/train': 1.7049683332443237} 08/30/2021 15:13:38 - INFO - __main__ - Step 11612: {'lr': 0.0004948153834510028, 'samples': 2229504, 'steps': 11611, 'loss/train': 0.3726326823234558} 08/30/2021 15:13:39 - INFO - __main__ - Step 11613: {'lr': 0.0004948143082482852, 'samples': 2229696, 'steps': 11612, 'loss/train': 1.0084137916564941} 08/30/2021 15:13:39 - INFO - __main__ - Step 11614: {'lr': 0.0004948132329352582, 'samples': 2229888, 'steps': 11613, 'loss/train': 2.300612688064575} 08/30/2021 15:13:39 - INFO - __main__ - Step 11615: {'lr': 0.0004948121575119219, 'samples': 2230080, 'steps': 11614, 'loss/train': 2.115280866622925} 08/30/2021 15:13:41 - INFO - __main__ - Step 11616: {'lr': 0.0004948110819782771, 'samples': 2230272, 'steps': 11615, 'loss/train': 1.264095664024353} 08/30/2021 15:13:41 - INFO - __main__ - Step 11617: {'lr': 0.0004948100063343243, 'samples': 2230464, 'steps': 11616, 'loss/train': 1.8612920045852661} 08/30/2021 15:13:42 - INFO - __main__ - Step 11618: {'lr': 0.0004948089305800638, 'samples': 2230656, 'steps': 11617, 'loss/train': 2.0519583225250244} 08/30/2021 15:13:42 - INFO - __main__ - Step 11619: {'lr': 0.0004948078547154962, 'samples': 2230848, 'steps': 11618, 'loss/train': 0.6256502866744995} 08/30/2021 15:13:42 - INFO - __main__ - Step 11620: {'lr': 0.0004948067787406219, 'samples': 2231040, 'steps': 11619, 'loss/train': 1.9627830982208252} 08/30/2021 15:13:44 - INFO - __main__ - Step 11621: {'lr': 0.0004948057026554415, 'samples': 2231232, 'steps': 11620, 'loss/train': 1.6287304162979126} 08/30/2021 15:13:45 - INFO - __main__ - Step 11622: {'lr': 0.0004948046264599554, 'samples': 2231424, 'steps': 11621, 'loss/train': 1.494590401649475} 08/30/2021 15:13:45 - INFO - __main__ - Step 11623: {'lr': 0.0004948035501541641, 'samples': 2231616, 'steps': 11622, 'loss/train': 1.9254127740859985} 08/30/2021 15:13:45 - INFO - __main__ - Step 11624: {'lr': 0.0004948024737380681, 'samples': 2231808, 'steps': 11623, 'loss/train': 1.5182067155838013} 08/30/2021 15:13:46 - INFO - __main__ - Step 11625: {'lr': 0.000494801397211668, 'samples': 2232000, 'steps': 11624, 'loss/train': 2.621610641479492} 08/30/2021 15:13:47 - INFO - __main__ - Step 11626: {'lr': 0.000494800320574964, 'samples': 2232192, 'steps': 11625, 'loss/train': 1.7660281658172607} 08/30/2021 15:13:47 - INFO - __main__ - Step 11627: {'lr': 0.0004947992438279568, 'samples': 2232384, 'steps': 11626, 'loss/train': 2.1557624340057373} 08/30/2021 15:13:48 - INFO - __main__ - Step 11628: {'lr': 0.0004947981669706469, 'samples': 2232576, 'steps': 11627, 'loss/train': 1.7714815139770508} 08/30/2021 15:13:48 - INFO - __main__ - Step 11629: {'lr': 0.0004947970900030346, 'samples': 2232768, 'steps': 11628, 'loss/train': 1.6118674278259277} 08/30/2021 15:13:49 - INFO - __main__ - Step 11630: {'lr': 0.0004947960129251206, 'samples': 2232960, 'steps': 11629, 'loss/train': 1.5114624500274658} 08/30/2021 15:13:50 - INFO - __main__ - Step 11631: {'lr': 0.0004947949357369054, 'samples': 2233152, 'steps': 11630, 'loss/train': 2.224601984024048} 08/30/2021 15:13:51 - INFO - __main__ - Step 11632: {'lr': 0.0004947938584383892, 'samples': 2233344, 'steps': 11631, 'loss/train': 1.7478086948394775} 08/30/2021 15:13:51 - INFO - __main__ - Step 11633: {'lr': 0.0004947927810295728, 'samples': 2233536, 'steps': 11632, 'loss/train': 1.528768539428711} 08/30/2021 15:13:51 - INFO - __main__ - Step 11634: {'lr': 0.0004947917035104564, 'samples': 2233728, 'steps': 11633, 'loss/train': 1.2400212287902832} 08/30/2021 15:13:52 - INFO - __main__ - Step 11635: {'lr': 0.0004947906258810407, 'samples': 2233920, 'steps': 11634, 'loss/train': 1.4715408086776733} 08/30/2021 15:13:52 - INFO - __main__ - Step 11636: {'lr': 0.0004947895481413262, 'samples': 2234112, 'steps': 11635, 'loss/train': 2.0533626079559326} 08/30/2021 15:13:53 - INFO - __main__ - Step 11637: {'lr': 0.0004947884702913133, 'samples': 2234304, 'steps': 11636, 'loss/train': 2.067622184753418} 08/30/2021 15:13:54 - INFO - __main__ - Step 11638: {'lr': 0.0004947873923310024, 'samples': 2234496, 'steps': 11637, 'loss/train': 1.6045129299163818} 08/30/2021 15:13:54 - INFO - __main__ - Step 11639: {'lr': 0.0004947863142603941, 'samples': 2234688, 'steps': 11638, 'loss/train': 1.6627546548843384} 08/30/2021 15:13:55 - INFO - __main__ - Step 11640: {'lr': 0.0004947852360794889, 'samples': 2234880, 'steps': 11639, 'loss/train': 2.2203850746154785} 08/30/2021 15:13:55 - INFO - __main__ - Step 11641: {'lr': 0.0004947841577882873, 'samples': 2235072, 'steps': 11640, 'loss/train': 1.6208118200302124} 08/30/2021 15:13:56 - INFO - __main__ - Step 11642: {'lr': 0.0004947830793867896, 'samples': 2235264, 'steps': 11641, 'loss/train': 2.3141238689422607} 08/30/2021 15:13:57 - INFO - __main__ - Step 11643: {'lr': 0.0004947820008749965, 'samples': 2235456, 'steps': 11642, 'loss/train': 1.8353108167648315} 08/30/2021 15:13:57 - INFO - __main__ - Step 11644: {'lr': 0.0004947809222529084, 'samples': 2235648, 'steps': 11643, 'loss/train': 1.8872349262237549} 08/30/2021 15:13:58 - INFO - __main__ - Step 11645: {'lr': 0.0004947798435205258, 'samples': 2235840, 'steps': 11644, 'loss/train': 0.762294352054596} 08/30/2021 15:13:58 - INFO - __main__ - Step 11646: {'lr': 0.0004947787646778491, 'samples': 2236032, 'steps': 11645, 'loss/train': 1.9617986679077148} 08/30/2021 15:13:59 - INFO - __main__ - Step 11647: {'lr': 0.0004947776857248791, 'samples': 2236224, 'steps': 11646, 'loss/train': 2.2141122817993164} 08/30/2021 15:14:00 - INFO - __main__ - Step 11648: {'lr': 0.0004947766066616157, 'samples': 2236416, 'steps': 11647, 'loss/train': 1.7058207988739014} 08/30/2021 15:14:00 - INFO - __main__ - Step 11649: {'lr': 0.00049477552748806, 'samples': 2236608, 'steps': 11648, 'loss/train': 1.2439918518066406} 08/30/2021 15:14:01 - INFO - __main__ - Step 11650: {'lr': 0.0004947744482042122, 'samples': 2236800, 'steps': 11649, 'loss/train': 1.9238418340682983} 08/30/2021 15:14:01 - INFO - __main__ - Step 11651: {'lr': 0.0004947733688100728, 'samples': 2236992, 'steps': 11650, 'loss/train': 2.2920732498168945} 08/30/2021 15:14:02 - INFO - __main__ - Step 11652: {'lr': 0.0004947722893056423, 'samples': 2237184, 'steps': 11651, 'loss/train': 1.3203538656234741} 08/30/2021 15:14:03 - INFO - __main__ - Step 11653: {'lr': 0.0004947712096909211, 'samples': 2237376, 'steps': 11652, 'loss/train': 0.6121887564659119} 08/30/2021 15:14:03 - INFO - __main__ - Step 11654: {'lr': 0.0004947701299659097, 'samples': 2237568, 'steps': 11653, 'loss/train': 1.4888660907745361} 08/30/2021 15:14:04 - INFO - __main__ - Step 11655: {'lr': 0.0004947690501306088, 'samples': 2237760, 'steps': 11654, 'loss/train': 1.632535457611084} 08/30/2021 15:14:04 - INFO - __main__ - Step 11656: {'lr': 0.0004947679701850187, 'samples': 2237952, 'steps': 11655, 'loss/train': 1.8257781267166138} 08/30/2021 15:14:06 - INFO - __main__ - Step 11657: {'lr': 0.00049476689012914, 'samples': 2238144, 'steps': 11656, 'loss/train': 0.2034396082162857} 08/30/2021 15:14:07 - INFO - __main__ - Step 11658: {'lr': 0.0004947658099629731, 'samples': 2238336, 'steps': 11657, 'loss/train': 1.9989336729049683} 08/30/2021 15:14:07 - INFO - __main__ - Step 11659: {'lr': 0.0004947647296865184, 'samples': 2238528, 'steps': 11658, 'loss/train': 1.2351003885269165} 08/30/2021 15:14:07 - INFO - __main__ - Step 11660: {'lr': 0.0004947636492997765, 'samples': 2238720, 'steps': 11659, 'loss/train': 2.5555813312530518} 08/30/2021 15:14:08 - INFO - __main__ - Step 11661: {'lr': 0.0004947625688027479, 'samples': 2238912, 'steps': 11660, 'loss/train': 1.8151615858078003} 08/30/2021 15:14:10 - INFO - __main__ - Step 11662: {'lr': 0.0004947614881954332, 'samples': 2239104, 'steps': 11661, 'loss/train': 2.078401803970337} 08/30/2021 15:14:10 - INFO - __main__ - Step 11663: {'lr': 0.0004947604074778325, 'samples': 2239296, 'steps': 11662, 'loss/train': 1.3901219367980957} 08/30/2021 15:14:11 - INFO - __main__ - Step 11664: {'lr': 0.0004947593266499468, 'samples': 2239488, 'steps': 11663, 'loss/train': 1.5410958528518677} 08/30/2021 15:14:11 - INFO - __main__ - Step 11665: {'lr': 0.0004947582457117762, 'samples': 2239680, 'steps': 11664, 'loss/train': 2.3159220218658447} 08/30/2021 15:14:11 - INFO - __main__ - Step 11666: {'lr': 0.0004947571646633214, 'samples': 2239872, 'steps': 11665, 'loss/train': 2.055731773376465} 08/30/2021 15:14:12 - INFO - __main__ - Step 11667: {'lr': 0.0004947560835045826, 'samples': 2240064, 'steps': 11666, 'loss/train': 1.9062695503234863} 08/30/2021 15:14:12 - INFO - __main__ - Step 11668: {'lr': 0.0004947550022355606, 'samples': 2240256, 'steps': 11667, 'loss/train': 1.2207061052322388} 08/30/2021 15:14:13 - INFO - __main__ - Step 11669: {'lr': 0.0004947539208562558, 'samples': 2240448, 'steps': 11668, 'loss/train': 4.36484956741333} 08/30/2021 15:14:14 - INFO - __main__ - Step 11670: {'lr': 0.0004947528393666686, 'samples': 2240640, 'steps': 11669, 'loss/train': 1.8936094045639038} 08/30/2021 15:14:14 - INFO - __main__ - Step 11671: {'lr': 0.0004947517577667996, 'samples': 2240832, 'steps': 11670, 'loss/train': 1.8972687721252441} 08/30/2021 15:14:15 - INFO - __main__ - Step 11672: {'lr': 0.0004947506760566492, 'samples': 2241024, 'steps': 11671, 'loss/train': 1.72401762008667} 08/30/2021 15:14:15 - INFO - __main__ - Step 11673: {'lr': 0.0004947495942362179, 'samples': 2241216, 'steps': 11672, 'loss/train': 1.4126760959625244} 08/30/2021 15:14:16 - INFO - __main__ - Step 11674: {'lr': 0.0004947485123055063, 'samples': 2241408, 'steps': 11673, 'loss/train': 1.4695552587509155} 08/30/2021 15:14:17 - INFO - __main__ - Step 11675: {'lr': 0.0004947474302645147, 'samples': 2241600, 'steps': 11674, 'loss/train': 0.6995078921318054} 08/30/2021 15:14:17 - INFO - __main__ - Step 11676: {'lr': 0.0004947463481132438, 'samples': 2241792, 'steps': 11675, 'loss/train': 1.9622925519943237} 08/30/2021 15:14:18 - INFO - __main__ - Step 11677: {'lr': 0.0004947452658516938, 'samples': 2241984, 'steps': 11676, 'loss/train': 2.2733633518218994} 08/30/2021 15:14:18 - INFO - __main__ - Step 11678: {'lr': 0.0004947441834798655, 'samples': 2242176, 'steps': 11677, 'loss/train': 1.803637146949768} 08/30/2021 15:14:18 - INFO - __main__ - Step 11679: {'lr': 0.0004947431009977592, 'samples': 2242368, 'steps': 11678, 'loss/train': 1.917235255241394} 08/30/2021 15:14:20 - INFO - __main__ - Step 11680: {'lr': 0.0004947420184053755, 'samples': 2242560, 'steps': 11679, 'loss/train': 2.0380828380584717} 08/30/2021 15:14:20 - INFO - __main__ - Step 11681: {'lr': 0.0004947409357027148, 'samples': 2242752, 'steps': 11680, 'loss/train': 1.8402788639068604} 08/30/2021 15:14:21 - INFO - __main__ - Step 11682: {'lr': 0.0004947398528897775, 'samples': 2242944, 'steps': 11681, 'loss/train': 1.9232163429260254} 08/30/2021 15:14:21 - INFO - __main__ - Step 11683: {'lr': 0.0004947387699665643, 'samples': 2243136, 'steps': 11682, 'loss/train': 1.3994172811508179} 08/30/2021 15:14:21 - INFO - __main__ - Step 11684: {'lr': 0.0004947376869330755, 'samples': 2243328, 'steps': 11683, 'loss/train': 1.7823961973190308} 08/30/2021 15:14:23 - INFO - __main__ - Step 11685: {'lr': 0.0004947366037893118, 'samples': 2243520, 'steps': 11684, 'loss/train': 1.9779433012008667} 08/30/2021 15:14:23 - INFO - __main__ - Step 11686: {'lr': 0.0004947355205352735, 'samples': 2243712, 'steps': 11685, 'loss/train': 1.882994294166565} 08/30/2021 15:14:24 - INFO - __main__ - Step 11687: {'lr': 0.0004947344371709611, 'samples': 2243904, 'steps': 11686, 'loss/train': 1.4967868328094482} 08/30/2021 15:14:24 - INFO - __main__ - Step 11688: {'lr': 0.0004947333536963753, 'samples': 2244096, 'steps': 11687, 'loss/train': 1.9321844577789307} 08/30/2021 15:14:24 - INFO - __main__ - Step 11689: {'lr': 0.0004947322701115163, 'samples': 2244288, 'steps': 11688, 'loss/train': 1.6577965021133423} 08/30/2021 15:14:26 - INFO - __main__ - Step 11690: {'lr': 0.0004947311864163847, 'samples': 2244480, 'steps': 11689, 'loss/train': 0.9276034235954285} 08/30/2021 15:14:27 - INFO - __main__ - Step 11691: {'lr': 0.000494730102610981, 'samples': 2244672, 'steps': 11690, 'loss/train': 1.8576034307479858} 08/30/2021 15:14:27 - INFO - __main__ - Step 11692: {'lr': 0.0004947290186953057, 'samples': 2244864, 'steps': 11691, 'loss/train': 1.895569920539856} 08/30/2021 15:14:27 - INFO - __main__ - Step 11693: {'lr': 0.0004947279346693594, 'samples': 2245056, 'steps': 11692, 'loss/train': 0.344992071390152} 08/30/2021 15:14:28 - INFO - __main__ - Step 11694: {'lr': 0.0004947268505331424, 'samples': 2245248, 'steps': 11693, 'loss/train': 1.5632882118225098} 08/30/2021 15:14:29 - INFO - __main__ - Step 11695: {'lr': 0.0004947257662866551, 'samples': 2245440, 'steps': 11694, 'loss/train': 5.149719715118408} 08/30/2021 15:14:30 - INFO - __main__ - Step 11696: {'lr': 0.0004947246819298984, 'samples': 2245632, 'steps': 11695, 'loss/train': 1.6019090414047241} 08/30/2021 15:14:30 - INFO - __main__ - Step 11697: {'lr': 0.0004947235974628723, 'samples': 2245824, 'steps': 11696, 'loss/train': 2.453235149383545} 08/30/2021 15:14:30 - INFO - __main__ - Step 11698: {'lr': 0.0004947225128855777, 'samples': 2246016, 'steps': 11697, 'loss/train': 1.7662475109100342} 08/30/2021 15:14:31 - INFO - __main__ - Step 11699: {'lr': 0.0004947214281980149, 'samples': 2246208, 'steps': 11698, 'loss/train': 2.8919992446899414} 08/30/2021 15:14:32 - INFO - __main__ - Step 11700: {'lr': 0.0004947203434001843, 'samples': 2246400, 'steps': 11699, 'loss/train': 1.7070711851119995} 08/30/2021 15:14:33 - INFO - __main__ - Step 11701: {'lr': 0.0004947192584920866, 'samples': 2246592, 'steps': 11700, 'loss/train': 1.8991669416427612} 08/30/2021 15:14:33 - INFO - __main__ - Step 11702: {'lr': 0.000494718173473722, 'samples': 2246784, 'steps': 11701, 'loss/train': 1.8828164339065552} 08/30/2021 15:14:33 - INFO - __main__ - Step 11703: {'lr': 0.0004947170883450913, 'samples': 2246976, 'steps': 11702, 'loss/train': 1.6286585330963135} 08/30/2021 15:14:34 - INFO - __main__ - Step 11704: {'lr': 0.000494716003106195, 'samples': 2247168, 'steps': 11703, 'loss/train': 1.7860980033874512} 08/30/2021 15:14:34 - INFO - __main__ - Step 11705: {'lr': 0.0004947149177570332, 'samples': 2247360, 'steps': 11704, 'loss/train': 1.9631855487823486} 08/30/2021 15:14:35 - INFO - __main__ - Step 11706: {'lr': 0.0004947138322976067, 'samples': 2247552, 'steps': 11705, 'loss/train': 1.9514325857162476} 08/30/2021 15:14:36 - INFO - __main__ - Step 11707: {'lr': 0.000494712746727916, 'samples': 2247744, 'steps': 11706, 'loss/train': 2.257874011993408} 08/30/2021 15:14:36 - INFO - __main__ - Step 11708: {'lr': 0.0004947116610479614, 'samples': 2247936, 'steps': 11707, 'loss/train': 1.631121277809143} 08/30/2021 15:14:37 - INFO - __main__ - Step 11709: {'lr': 0.0004947105752577436, 'samples': 2248128, 'steps': 11708, 'loss/train': 1.3235853910446167} 08/30/2021 15:14:37 - INFO - __main__ - Step 11710: {'lr': 0.0004947094893572629, 'samples': 2248320, 'steps': 11709, 'loss/train': 1.4561848640441895} 08/30/2021 15:14:38 - INFO - __main__ - Step 11711: {'lr': 0.00049470840334652, 'samples': 2248512, 'steps': 11710, 'loss/train': 1.8853501081466675} 08/30/2021 15:14:39 - INFO - __main__ - Step 11712: {'lr': 0.0004947073172255151, 'samples': 2248704, 'steps': 11711, 'loss/train': 1.6063880920410156} 08/30/2021 15:14:39 - INFO - __main__ - Step 11713: {'lr': 0.000494706230994249, 'samples': 2248896, 'steps': 11712, 'loss/train': 1.1136841773986816} 08/30/2021 15:14:40 - INFO - __main__ - Step 11714: {'lr': 0.000494705144652722, 'samples': 2249088, 'steps': 11713, 'loss/train': 2.184231996536255} 08/30/2021 15:14:40 - INFO - __main__ - Step 11715: {'lr': 0.0004947040582009346, 'samples': 2249280, 'steps': 11714, 'loss/train': 1.7813596725463867} 08/30/2021 15:14:42 - INFO - __main__ - Step 11716: {'lr': 0.0004947029716388875, 'samples': 2249472, 'steps': 11715, 'loss/train': 2.1649110317230225} 08/30/2021 15:14:42 - INFO - __main__ - Step 11717: {'lr': 0.0004947018849665809, 'samples': 2249664, 'steps': 11716, 'loss/train': 1.8251116275787354} 08/30/2021 15:14:43 - INFO - __main__ - Step 11718: {'lr': 0.0004947007981840153, 'samples': 2249856, 'steps': 11717, 'loss/train': 2.155564546585083} 08/30/2021 15:14:43 - INFO - __main__ - Step 11719: {'lr': 0.0004946997112911914, 'samples': 2250048, 'steps': 11718, 'loss/train': 1.1258002519607544} 08/30/2021 15:14:43 - INFO - __main__ - Step 11720: {'lr': 0.0004946986242881096, 'samples': 2250240, 'steps': 11719, 'loss/train': 1.8737475872039795} 08/30/2021 15:14:45 - INFO - __main__ - Step 11721: {'lr': 0.0004946975371747704, 'samples': 2250432, 'steps': 11720, 'loss/train': 1.9213136434555054} 08/30/2021 15:14:45 - INFO - __main__ - Step 11722: {'lr': 0.0004946964499511742, 'samples': 2250624, 'steps': 11721, 'loss/train': 1.68390691280365} 08/30/2021 15:14:46 - INFO - __main__ - Step 11723: {'lr': 0.0004946953626173216, 'samples': 2250816, 'steps': 11722, 'loss/train': 0.8829115629196167} 08/30/2021 15:14:46 - INFO - __main__ - Step 11724: {'lr': 0.0004946942751732129, 'samples': 2251008, 'steps': 11723, 'loss/train': 2.01387095451355} 08/30/2021 15:14:46 - INFO - __main__ - Step 11725: {'lr': 0.000494693187618849, 'samples': 2251200, 'steps': 11724, 'loss/train': 0.17464707791805267} 08/30/2021 15:14:48 - INFO - __main__ - Step 11726: {'lr': 0.0004946920999542299, 'samples': 2251392, 'steps': 11725, 'loss/train': 2.0406157970428467} 08/30/2021 15:14:49 - INFO - __main__ - Step 11727: {'lr': 0.0004946910121793564, 'samples': 2251584, 'steps': 11726, 'loss/train': 1.7692480087280273} 08/30/2021 15:14:49 - INFO - __main__ - Step 11728: {'lr': 0.0004946899242942289, 'samples': 2251776, 'steps': 11727, 'loss/train': 1.89846932888031} 08/30/2021 15:14:50 - INFO - __main__ - Step 11729: {'lr': 0.000494688836298848, 'samples': 2251968, 'steps': 11728, 'loss/train': 2.0183138847351074} 08/30/2021 15:14:50 - INFO - __main__ - Step 11730: {'lr': 0.0004946877481932139, 'samples': 2252160, 'steps': 11729, 'loss/train': 1.7410293817520142} 08/30/2021 15:14:50 - INFO - __main__ - Step 11731: {'lr': 0.0004946866599773274, 'samples': 2252352, 'steps': 11730, 'loss/train': 1.5501283407211304} 08/30/2021 15:14:52 - INFO - __main__ - Step 11732: {'lr': 0.0004946855716511888, 'samples': 2252544, 'steps': 11731, 'loss/train': 0.4122734069824219} 08/30/2021 15:14:53 - INFO - __main__ - Step 11733: {'lr': 0.0004946844832147987, 'samples': 2252736, 'steps': 11732, 'loss/train': 0.14123785495758057} 08/30/2021 15:14:53 - INFO - __main__ - Step 11734: {'lr': 0.0004946833946681575, 'samples': 2252928, 'steps': 11733, 'loss/train': 1.3744008541107178} 08/30/2021 15:14:53 - INFO - __main__ - Step 11735: {'lr': 0.0004946823060112658, 'samples': 2253120, 'steps': 11734, 'loss/train': 1.4184517860412598} 08/30/2021 15:14:54 - INFO - __main__ - Step 11736: {'lr': 0.000494681217244124, 'samples': 2253312, 'steps': 11735, 'loss/train': 1.8464114665985107} 08/30/2021 15:14:54 - INFO - __main__ - Step 11737: {'lr': 0.0004946801283667326, 'samples': 2253504, 'steps': 11736, 'loss/train': 1.6429179906845093} 08/30/2021 15:14:56 - INFO - __main__ - Step 11738: {'lr': 0.0004946790393790921, 'samples': 2253696, 'steps': 11737, 'loss/train': 1.7506275177001953} 08/30/2021 15:14:56 - INFO - __main__ - Step 11739: {'lr': 0.0004946779502812031, 'samples': 2253888, 'steps': 11738, 'loss/train': 2.6980814933776855} 08/30/2021 15:14:57 - INFO - __main__ - Step 11740: {'lr': 0.0004946768610730659, 'samples': 2254080, 'steps': 11739, 'loss/train': 1.2672038078308105} 08/30/2021 15:14:57 - INFO - __main__ - Step 11741: {'lr': 0.0004946757717546812, 'samples': 2254272, 'steps': 11740, 'loss/train': 1.8932408094406128} 08/30/2021 15:14:57 - INFO - __main__ - Step 11742: {'lr': 0.0004946746823260491, 'samples': 2254464, 'steps': 11741, 'loss/train': 0.5532539486885071} 08/30/2021 15:14:58 - INFO - __main__ - Step 11743: {'lr': 0.0004946735927871706, 'samples': 2254656, 'steps': 11742, 'loss/train': 1.672285795211792} 08/30/2021 15:14:59 - INFO - __main__ - Step 11744: {'lr': 0.0004946725031380459, 'samples': 2254848, 'steps': 11743, 'loss/train': 1.7819613218307495} 08/30/2021 15:14:59 - INFO - __main__ - Step 11745: {'lr': 0.0004946714133786756, 'samples': 2255040, 'steps': 11744, 'loss/train': 1.6214816570281982} 08/30/2021 15:15:00 - INFO - __main__ - Step 11746: {'lr': 0.00049467032350906, 'samples': 2255232, 'steps': 11745, 'loss/train': 2.1793644428253174} 08/30/2021 15:15:00 - INFO - __main__ - Step 11747: {'lr': 0.0004946692335291999, 'samples': 2255424, 'steps': 11746, 'loss/train': 2.0590147972106934} 08/30/2021 15:15:00 - INFO - __main__ - Step 11748: {'lr': 0.0004946681434390955, 'samples': 2255616, 'steps': 11747, 'loss/train': 2.3604531288146973} 08/30/2021 15:15:02 - INFO - __main__ - Step 11749: {'lr': 0.0004946670532387474, 'samples': 2255808, 'steps': 11748, 'loss/train': 2.0560808181762695} 08/30/2021 15:15:02 - INFO - __main__ - Step 11750: {'lr': 0.0004946659629281561, 'samples': 2256000, 'steps': 11749, 'loss/train': 1.992100477218628} 08/30/2021 15:15:03 - INFO - __main__ - Step 11751: {'lr': 0.0004946648725073222, 'samples': 2256192, 'steps': 11750, 'loss/train': 1.704413890838623} 08/30/2021 15:15:03 - INFO - __main__ - Step 11752: {'lr': 0.0004946637819762459, 'samples': 2256384, 'steps': 11751, 'loss/train': 1.4175366163253784} 08/30/2021 15:15:03 - INFO - __main__ - Step 11753: {'lr': 0.000494662691334928, 'samples': 2256576, 'steps': 11752, 'loss/train': 1.1848088502883911} 08/30/2021 15:15:05 - INFO - __main__ - Step 11754: {'lr': 0.0004946616005833689, 'samples': 2256768, 'steps': 11753, 'loss/train': 1.4894793033599854} 08/30/2021 15:15:05 - INFO - __main__ - Step 11755: {'lr': 0.0004946605097215691, 'samples': 2256960, 'steps': 11754, 'loss/train': 1.7255768775939941} 08/30/2021 15:15:06 - INFO - __main__ - Step 11756: {'lr': 0.0004946594187495289, 'samples': 2257152, 'steps': 11755, 'loss/train': 1.7005902528762817} 08/30/2021 15:15:06 - INFO - __main__ - Step 11757: {'lr': 0.0004946583276672489, 'samples': 2257344, 'steps': 11756, 'loss/train': 1.6552094221115112} 08/30/2021 15:15:06 - INFO - __main__ - Step 11758: {'lr': 0.0004946572364747298, 'samples': 2257536, 'steps': 11757, 'loss/train': 2.274648666381836} 08/30/2021 15:15:08 - INFO - __main__ - Step 11759: {'lr': 0.0004946561451719719, 'samples': 2257728, 'steps': 11758, 'loss/train': 2.040285587310791} 08/30/2021 15:15:09 - INFO - __main__ - Step 11760: {'lr': 0.0004946550537589757, 'samples': 2257920, 'steps': 11759, 'loss/train': 2.1042490005493164} 08/30/2021 15:15:09 - INFO - __main__ - Step 11761: {'lr': 0.0004946539622357417, 'samples': 2258112, 'steps': 11760, 'loss/train': 1.696751356124878} 08/30/2021 15:15:10 - INFO - __main__ - Step 11762: {'lr': 0.0004946528706022703, 'samples': 2258304, 'steps': 11761, 'loss/train': 1.9341208934783936} 08/30/2021 15:15:10 - INFO - __main__ - Step 11763: {'lr': 0.0004946517788585622, 'samples': 2258496, 'steps': 11762, 'loss/train': 2.3381707668304443} 08/30/2021 15:15:11 - INFO - __main__ - Step 11764: {'lr': 0.0004946506870046178, 'samples': 2258688, 'steps': 11763, 'loss/train': 2.199601650238037} 08/30/2021 15:15:12 - INFO - __main__ - Step 11765: {'lr': 0.0004946495950404375, 'samples': 2258880, 'steps': 11764, 'loss/train': 1.7529102563858032} 08/30/2021 15:15:12 - INFO - __main__ - Step 11766: {'lr': 0.0004946485029660219, 'samples': 2259072, 'steps': 11765, 'loss/train': 1.9411066770553589} 08/30/2021 15:15:13 - INFO - __main__ - Step 11767: {'lr': 0.0004946474107813715, 'samples': 2259264, 'steps': 11766, 'loss/train': 1.7289375066757202} 08/30/2021 15:15:13 - INFO - __main__ - Step 11768: {'lr': 0.0004946463184864867, 'samples': 2259456, 'steps': 11767, 'loss/train': 1.5154902935028076} 08/30/2021 15:15:15 - INFO - __main__ - Step 11769: {'lr': 0.000494645226081368, 'samples': 2259648, 'steps': 11768, 'loss/train': 1.7412127256393433} 08/30/2021 15:15:15 - INFO - __main__ - Step 11770: {'lr': 0.000494644133566016, 'samples': 2259840, 'steps': 11769, 'loss/train': 1.731998324394226} 08/30/2021 15:15:15 - INFO - __main__ - Step 11771: {'lr': 0.0004946430409404311, 'samples': 2260032, 'steps': 11770, 'loss/train': 0.18437843024730682} 08/30/2021 15:15:16 - INFO - __main__ - Step 11772: {'lr': 0.0004946419482046139, 'samples': 2260224, 'steps': 11771, 'loss/train': 2.0941176414489746} 08/30/2021 15:15:16 - INFO - __main__ - Step 11773: {'lr': 0.0004946408553585648, 'samples': 2260416, 'steps': 11772, 'loss/train': 2.2236886024475098} 08/30/2021 15:15:18 - INFO - __main__ - Step 11774: {'lr': 0.0004946397624022843, 'samples': 2260608, 'steps': 11773, 'loss/train': 2.299236536026001} 08/30/2021 15:15:18 - INFO - __main__ - Step 11775: {'lr': 0.0004946386693357728, 'samples': 2260800, 'steps': 11774, 'loss/train': 1.7870864868164062} 08/30/2021 15:15:18 - INFO - __main__ - Step 11776: {'lr': 0.0004946375761590309, 'samples': 2260992, 'steps': 11775, 'loss/train': 1.6457983255386353} 08/30/2021 15:15:19 - INFO - __main__ - Step 11777: {'lr': 0.0004946364828720592, 'samples': 2261184, 'steps': 11776, 'loss/train': 1.8843894004821777} 08/30/2021 15:15:19 - INFO - __main__ - Step 11778: {'lr': 0.000494635389474858, 'samples': 2261376, 'steps': 11777, 'loss/train': 2.5461606979370117} 08/30/2021 15:15:21 - INFO - __main__ - Step 11779: {'lr': 0.0004946342959674278, 'samples': 2261568, 'steps': 11778, 'loss/train': 1.298263430595398} 08/30/2021 15:15:21 - INFO - __main__ - Step 11780: {'lr': 0.0004946332023497693, 'samples': 2261760, 'steps': 11779, 'loss/train': 1.4017049074172974} 08/30/2021 15:15:21 - INFO - __main__ - Step 11781: {'lr': 0.0004946321086218828, 'samples': 2261952, 'steps': 11780, 'loss/train': 3.3718361854553223} 08/30/2021 15:15:22 - INFO - __main__ - Step 11782: {'lr': 0.0004946310147837689, 'samples': 2262144, 'steps': 11781, 'loss/train': 1.831998348236084} 08/30/2021 15:15:22 - INFO - __main__ - Step 11783: {'lr': 0.0004946299208354279, 'samples': 2262336, 'steps': 11782, 'loss/train': 1.3627289533615112} 08/30/2021 15:15:24 - INFO - __main__ - Step 11784: {'lr': 0.0004946288267768605, 'samples': 2262528, 'steps': 11783, 'loss/train': 2.2675211429595947} 08/30/2021 15:15:24 - INFO - __main__ - Step 11785: {'lr': 0.0004946277326080672, 'samples': 2262720, 'steps': 11784, 'loss/train': 1.698428988456726} 08/30/2021 15:15:24 - INFO - __main__ - Step 11786: {'lr': 0.0004946266383290483, 'samples': 2262912, 'steps': 11785, 'loss/train': 2.13415265083313} 08/30/2021 15:15:25 - INFO - __main__ - Step 11787: {'lr': 0.0004946255439398045, 'samples': 2263104, 'steps': 11786, 'loss/train': 1.7996593713760376} 08/30/2021 15:15:25 - INFO - __main__ - Step 11788: {'lr': 0.0004946244494403361, 'samples': 2263296, 'steps': 11787, 'loss/train': 1.7397469282150269} 08/30/2021 15:15:26 - INFO - __main__ - Step 11789: {'lr': 0.0004946233548306438, 'samples': 2263488, 'steps': 11788, 'loss/train': 1.4018193483352661} 08/30/2021 15:15:27 - INFO - __main__ - Step 11790: {'lr': 0.000494622260110728, 'samples': 2263680, 'steps': 11789, 'loss/train': 1.829760193824768} 08/30/2021 15:15:28 - INFO - __main__ - Step 11791: {'lr': 0.0004946211652805891, 'samples': 2263872, 'steps': 11790, 'loss/train': 1.2616387605667114} 08/30/2021 15:15:28 - INFO - __main__ - Step 11792: {'lr': 0.0004946200703402278, 'samples': 2264064, 'steps': 11791, 'loss/train': 2.205960750579834} 08/30/2021 15:15:28 - INFO - __main__ - Step 11793: {'lr': 0.0004946189752896443, 'samples': 2264256, 'steps': 11792, 'loss/train': 2.12526798248291} 08/30/2021 15:15:29 - INFO - __main__ - Step 11794: {'lr': 0.0004946178801288394, 'samples': 2264448, 'steps': 11793, 'loss/train': 1.6127997636795044} 08/30/2021 15:15:30 - INFO - __main__ - Step 11795: {'lr': 0.0004946167848578134, 'samples': 2264640, 'steps': 11794, 'loss/train': 1.4849432706832886} 08/30/2021 15:15:31 - INFO - __main__ - Step 11796: {'lr': 0.0004946156894765669, 'samples': 2264832, 'steps': 11795, 'loss/train': 2.4573872089385986} 08/30/2021 15:15:31 - INFO - __main__ - Step 11797: {'lr': 0.0004946145939851004, 'samples': 2265024, 'steps': 11796, 'loss/train': 1.4694702625274658} 08/30/2021 15:15:32 - INFO - __main__ - Step 11798: {'lr': 0.0004946134983834142, 'samples': 2265216, 'steps': 11797, 'loss/train': 0.4310687482357025} 08/30/2021 15:15:32 - INFO - __main__ - Step 11799: {'lr': 0.0004946124026715089, 'samples': 2265408, 'steps': 11798, 'loss/train': 1.533728837966919} 08/30/2021 15:15:34 - INFO - __main__ - Step 11800: {'lr': 0.0004946113068493851, 'samples': 2265600, 'steps': 11799, 'loss/train': 1.7493268251419067} 08/30/2021 15:15:34 - INFO - __main__ - Step 11801: {'lr': 0.0004946102109170433, 'samples': 2265792, 'steps': 11800, 'loss/train': 1.5623968839645386} 08/30/2021 15:15:35 - INFO - __main__ - Step 11802: {'lr': 0.0004946091148744838, 'samples': 2265984, 'steps': 11801, 'loss/train': 1.8144017457962036} 08/30/2021 15:15:35 - INFO - __main__ - Step 11803: {'lr': 0.0004946080187217072, 'samples': 2266176, 'steps': 11802, 'loss/train': 0.19895613193511963} 08/30/2021 15:15:35 - INFO - __main__ - Step 11804: {'lr': 0.0004946069224587141, 'samples': 2266368, 'steps': 11803, 'loss/train': 1.3789323568344116} 08/30/2021 15:15:37 - INFO - __main__ - Step 11805: {'lr': 0.0004946058260855049, 'samples': 2266560, 'steps': 11804, 'loss/train': 1.8440556526184082} 08/30/2021 15:15:38 - INFO - __main__ - Step 11806: {'lr': 0.00049460472960208, 'samples': 2266752, 'steps': 11805, 'loss/train': 2.2906994819641113} 08/30/2021 15:15:38 - INFO - __main__ - Step 11807: {'lr': 0.00049460363300844, 'samples': 2266944, 'steps': 11806, 'loss/train': 1.9607677459716797} 08/30/2021 15:15:38 - INFO - __main__ - Step 11808: {'lr': 0.0004946025363045854, 'samples': 2267136, 'steps': 11807, 'loss/train': 2.244109630584717} 08/30/2021 15:15:39 - INFO - __main__ - Step 11809: {'lr': 0.0004946014394905167, 'samples': 2267328, 'steps': 11808, 'loss/train': 1.970001220703125} 08/30/2021 15:15:39 - INFO - __main__ - Step 11810: {'lr': 0.0004946003425662343, 'samples': 2267520, 'steps': 11809, 'loss/train': 0.0902596190571785} 08/30/2021 15:15:39 - INFO - __main__ - Step 11811: {'lr': 0.0004945992455317389, 'samples': 2267712, 'steps': 11810, 'loss/train': 0.5853404998779297} 08/30/2021 15:15:41 - INFO - __main__ - Step 11812: {'lr': 0.0004945981483870307, 'samples': 2267904, 'steps': 11811, 'loss/train': 1.6543635129928589} 08/30/2021 15:15:41 - INFO - __main__ - Step 11813: {'lr': 0.0004945970511321104, 'samples': 2268096, 'steps': 11812, 'loss/train': 1.7412084341049194} 08/30/2021 15:15:42 - INFO - __main__ - Step 11814: {'lr': 0.0004945959537669784, 'samples': 2268288, 'steps': 11813, 'loss/train': 1.5137156248092651} 08/30/2021 15:15:42 - INFO - __main__ - Step 11815: {'lr': 0.0004945948562916353, 'samples': 2268480, 'steps': 11814, 'loss/train': 2.1057684421539307} 08/30/2021 15:15:43 - INFO - __main__ - Step 11816: {'lr': 0.0004945937587060815, 'samples': 2268672, 'steps': 11815, 'loss/train': 1.7500317096710205} 08/30/2021 15:15:45 - INFO - __main__ - Step 11817: {'lr': 0.0004945926610103175, 'samples': 2268864, 'steps': 11816, 'loss/train': 2.100980281829834} 08/30/2021 15:15:45 - INFO - __main__ - Step 11818: {'lr': 0.0004945915632043439, 'samples': 2269056, 'steps': 11817, 'loss/train': 1.5017176866531372} 08/30/2021 15:15:46 - INFO - __main__ - Step 11819: {'lr': 0.0004945904652881611, 'samples': 2269248, 'steps': 11818, 'loss/train': 1.8831287622451782} 08/30/2021 15:15:46 - INFO - __main__ - Step 11820: {'lr': 0.0004945893672617695, 'samples': 2269440, 'steps': 11819, 'loss/train': 2.4403114318847656} 08/30/2021 15:15:46 - INFO - __main__ - Step 11821: {'lr': 0.0004945882691251699, 'samples': 2269632, 'steps': 11820, 'loss/train': 2.021946668624878} 08/30/2021 15:15:48 - INFO - __main__ - Step 11822: {'lr': 0.0004945871708783625, 'samples': 2269824, 'steps': 11821, 'loss/train': 2.088178873062134} 08/30/2021 15:15:48 - INFO - __main__ - Step 11823: {'lr': 0.0004945860725213477, 'samples': 2270016, 'steps': 11822, 'loss/train': 1.171350121498108} 08/30/2021 15:15:49 - INFO - __main__ - Step 11824: {'lr': 0.0004945849740541265, 'samples': 2270208, 'steps': 11823, 'loss/train': 1.861392855644226} 08/30/2021 15:15:49 - INFO - __main__ - Step 11825: {'lr': 0.000494583875476699, 'samples': 2270400, 'steps': 11824, 'loss/train': 2.1119577884674072} 08/30/2021 15:15:49 - INFO - __main__ - Step 11826: {'lr': 0.0004945827767890657, 'samples': 2270592, 'steps': 11825, 'loss/train': 1.9140068292617798} 08/30/2021 15:15:50 - INFO - __main__ - Step 11827: {'lr': 0.0004945816779912272, 'samples': 2270784, 'steps': 11826, 'loss/train': 1.7558281421661377} 08/30/2021 15:15:51 - INFO - __main__ - Step 11828: {'lr': 0.000494580579083184, 'samples': 2270976, 'steps': 11827, 'loss/train': 1.6848113536834717} 08/30/2021 15:15:51 - INFO - __main__ - Step 11829: {'lr': 0.0004945794800649366, 'samples': 2271168, 'steps': 11828, 'loss/train': 1.7365353107452393} 08/30/2021 15:15:52 - INFO - __main__ - Step 11830: {'lr': 0.0004945783809364853, 'samples': 2271360, 'steps': 11829, 'loss/train': 1.7429718971252441} 08/30/2021 15:15:52 - INFO - __main__ - Step 11831: {'lr': 0.0004945772816978309, 'samples': 2271552, 'steps': 11830, 'loss/train': 2.4146013259887695} 08/30/2021 15:15:52 - INFO - __main__ - Step 11832: {'lr': 0.0004945761823489737, 'samples': 2271744, 'steps': 11831, 'loss/train': 1.812188982963562} 08/30/2021 15:15:54 - INFO - __main__ - Step 11833: {'lr': 0.0004945750828899144, 'samples': 2271936, 'steps': 11832, 'loss/train': 1.648162841796875} 08/30/2021 15:15:54 - INFO - __main__ - Step 11834: {'lr': 0.0004945739833206531, 'samples': 2272128, 'steps': 11833, 'loss/train': 2.069950580596924} 08/30/2021 15:15:55 - INFO - __main__ - Step 11835: {'lr': 0.0004945728836411907, 'samples': 2272320, 'steps': 11834, 'loss/train': 2.2438645362854004} 08/30/2021 15:15:55 - INFO - __main__ - Step 11836: {'lr': 0.0004945717838515275, 'samples': 2272512, 'steps': 11835, 'loss/train': 1.9432957172393799} 08/30/2021 15:15:55 - INFO - __main__ - Step 11837: {'lr': 0.0004945706839516639, 'samples': 2272704, 'steps': 11836, 'loss/train': 1.6880847215652466} 08/30/2021 15:15:57 - INFO - __main__ - Step 11838: {'lr': 0.0004945695839416006, 'samples': 2272896, 'steps': 11837, 'loss/train': 1.4829120635986328} 08/30/2021 15:15:57 - INFO - __main__ - Step 11839: {'lr': 0.0004945684838213382, 'samples': 2273088, 'steps': 11838, 'loss/train': 2.03684139251709} 08/30/2021 15:15:58 - INFO - __main__ - Step 11840: {'lr': 0.0004945673835908767, 'samples': 2273280, 'steps': 11839, 'loss/train': 1.7222049236297607} 08/30/2021 15:15:58 - INFO - __main__ - Step 11841: {'lr': 0.0004945662832502171, 'samples': 2273472, 'steps': 11840, 'loss/train': 1.6915655136108398} 08/30/2021 15:15:58 - INFO - __main__ - Step 11842: {'lr': 0.0004945651827993597, 'samples': 2273664, 'steps': 11841, 'loss/train': 2.2450461387634277} 08/30/2021 15:16:00 - INFO - __main__ - Step 11843: {'lr': 0.000494564082238305, 'samples': 2273856, 'steps': 11842, 'loss/train': 1.5833274126052856} 08/30/2021 15:16:00 - INFO - __main__ - Step 11844: {'lr': 0.0004945629815670535, 'samples': 2274048, 'steps': 11843, 'loss/train': 1.8316855430603027} 08/30/2021 15:16:01 - INFO - __main__ - Step 11845: {'lr': 0.0004945618807856056, 'samples': 2274240, 'steps': 11844, 'loss/train': 1.6846545934677124} 08/30/2021 15:16:01 - INFO - __main__ - Step 11846: {'lr': 0.000494560779893962, 'samples': 2274432, 'steps': 11845, 'loss/train': 2.065723180770874} 08/30/2021 15:16:01 - INFO - __main__ - Step 11847: {'lr': 0.0004945596788921231, 'samples': 2274624, 'steps': 11846, 'loss/train': 1.5155576467514038} 08/30/2021 15:16:03 - INFO - __main__ - Step 11848: {'lr': 0.0004945585777800893, 'samples': 2274816, 'steps': 11847, 'loss/train': 2.3535053730010986} 08/30/2021 15:16:04 - INFO - __main__ - Step 11849: {'lr': 0.0004945574765578612, 'samples': 2275008, 'steps': 11848, 'loss/train': 1.3265169858932495} 08/30/2021 15:16:04 - INFO - __main__ - Step 11850: {'lr': 0.0004945563752254393, 'samples': 2275200, 'steps': 11849, 'loss/train': 0.10267017036676407} 08/30/2021 15:16:04 - INFO - __main__ - Step 11851: {'lr': 0.000494555273782824, 'samples': 2275392, 'steps': 11850, 'loss/train': 1.8187745809555054} 08/30/2021 15:16:05 - INFO - __main__ - Step 11852: {'lr': 0.000494554172230016, 'samples': 2275584, 'steps': 11851, 'loss/train': 1.3680561780929565} 08/30/2021 15:16:05 - INFO - __main__ - Step 11853: {'lr': 0.0004945530705670156, 'samples': 2275776, 'steps': 11852, 'loss/train': 2.0712554454803467} 08/30/2021 15:16:07 - INFO - __main__ - Step 11854: {'lr': 0.0004945519687938234, 'samples': 2275968, 'steps': 11853, 'loss/train': 0.8978202939033508} 08/30/2021 15:16:08 - INFO - __main__ - Step 11855: {'lr': 0.0004945508669104397, 'samples': 2276160, 'steps': 11854, 'loss/train': 1.6371419429779053} 08/30/2021 15:16:08 - INFO - __main__ - Step 11856: {'lr': 0.0004945497649168654, 'samples': 2276352, 'steps': 11855, 'loss/train': 1.8161147832870483} 08/30/2021 15:16:08 - INFO - __main__ - Step 11857: {'lr': 0.0004945486628131006, 'samples': 2276544, 'steps': 11856, 'loss/train': 1.4968148469924927} 08/30/2021 15:16:09 - INFO - __main__ - Step 11858: {'lr': 0.0004945475605991459, 'samples': 2276736, 'steps': 11857, 'loss/train': 1.6238117218017578} 08/30/2021 15:16:10 - INFO - __main__ - Step 11859: {'lr': 0.0004945464582750019, 'samples': 2276928, 'steps': 11858, 'loss/train': 1.0893546342849731} 08/30/2021 15:16:11 - INFO - __main__ - Step 11860: {'lr': 0.000494545355840669, 'samples': 2277120, 'steps': 11859, 'loss/train': 0.9706990122795105} 08/30/2021 15:16:11 - INFO - __main__ - Step 11861: {'lr': 0.0004945442532961478, 'samples': 2277312, 'steps': 11860, 'loss/train': 1.086559534072876} 08/30/2021 15:16:11 - INFO - __main__ - Step 11862: {'lr': 0.0004945431506414386, 'samples': 2277504, 'steps': 11861, 'loss/train': 1.9632014036178589} 08/30/2021 15:16:12 - INFO - __main__ - Step 11863: {'lr': 0.0004945420478765422, 'samples': 2277696, 'steps': 11862, 'loss/train': 1.5190651416778564} 08/30/2021 15:16:12 - INFO - __main__ - Step 11864: {'lr': 0.0004945409450014588, 'samples': 2277888, 'steps': 11863, 'loss/train': 0.6566113829612732} 08/30/2021 15:16:14 - INFO - __main__ - Step 11865: {'lr': 0.0004945398420161892, 'samples': 2278080, 'steps': 11864, 'loss/train': 1.752700924873352} 08/30/2021 15:16:15 - INFO - __main__ - Step 11866: {'lr': 0.0004945387389207335, 'samples': 2278272, 'steps': 11865, 'loss/train': 1.5283820629119873} 08/30/2021 15:16:15 - INFO - __main__ - Step 11867: {'lr': 0.0004945376357150926, 'samples': 2278464, 'steps': 11866, 'loss/train': 2.3288278579711914} 08/30/2021 15:16:15 - INFO - __main__ - Step 11868: {'lr': 0.0004945365323992668, 'samples': 2278656, 'steps': 11867, 'loss/train': 1.4412542581558228} 08/30/2021 15:16:16 - INFO - __main__ - Step 11869: {'lr': 0.0004945354289732565, 'samples': 2278848, 'steps': 11868, 'loss/train': 1.701159119606018} 08/30/2021 15:16:17 - INFO - __main__ - Step 11870: {'lr': 0.0004945343254370623, 'samples': 2279040, 'steps': 11869, 'loss/train': 2.2766289710998535} 08/30/2021 15:16:18 - INFO - __main__ - Step 11871: {'lr': 0.0004945332217906848, 'samples': 2279232, 'steps': 11870, 'loss/train': 1.0289002656936646} 08/30/2021 15:16:19 - INFO - __main__ - Step 11872: {'lr': 0.0004945321180341244, 'samples': 2279424, 'steps': 11871, 'loss/train': 1.8550326824188232} 08/30/2021 15:16:19 - INFO - __main__ - Step 11873: {'lr': 0.0004945310141673816, 'samples': 2279616, 'steps': 11872, 'loss/train': 1.3300050497055054} 08/30/2021 15:16:19 - INFO - __main__ - Step 11874: {'lr': 0.0004945299101904568, 'samples': 2279808, 'steps': 11873, 'loss/train': 1.3555680513381958} 08/30/2021 15:16:21 - INFO - __main__ - Step 11875: {'lr': 0.0004945288061033507, 'samples': 2280000, 'steps': 11874, 'loss/train': 1.2853432893753052} 08/30/2021 15:16:21 - INFO - __main__ - Step 11876: {'lr': 0.0004945277019060637, 'samples': 2280192, 'steps': 11875, 'loss/train': 1.9826915264129639} 08/30/2021 15:16:22 - INFO - __main__ - Step 11877: {'lr': 0.0004945265975985962, 'samples': 2280384, 'steps': 11876, 'loss/train': 1.8472506999969482} 08/30/2021 15:16:22 - INFO - __main__ - Step 11878: {'lr': 0.0004945254931809489, 'samples': 2280576, 'steps': 11877, 'loss/train': 1.9365565776824951} 08/30/2021 15:16:22 - INFO - __main__ - Step 11879: {'lr': 0.000494524388653122, 'samples': 2280768, 'steps': 11878, 'loss/train': 1.9993367195129395} 08/30/2021 15:16:24 - INFO - __main__ - Step 11880: {'lr': 0.0004945232840151164, 'samples': 2280960, 'steps': 11879, 'loss/train': 2.090670347213745} 08/30/2021 15:16:24 - INFO - __main__ - Step 11881: {'lr': 0.0004945221792669322, 'samples': 2281152, 'steps': 11880, 'loss/train': 1.2670029401779175} 08/30/2021 15:16:25 - INFO - __main__ - Step 11882: {'lr': 0.0004945210744085702, 'samples': 2281344, 'steps': 11881, 'loss/train': 1.4060724973678589} 08/30/2021 15:16:25 - INFO - __main__ - Step 11883: {'lr': 0.0004945199694400308, 'samples': 2281536, 'steps': 11882, 'loss/train': 1.7131822109222412} 08/30/2021 15:16:25 - INFO - __main__ - Step 11884: {'lr': 0.0004945188643613144, 'samples': 2281728, 'steps': 11883, 'loss/train': 2.860826253890991} 08/30/2021 15:16:26 - INFO - __main__ - Step 11885: {'lr': 0.0004945177591724216, 'samples': 2281920, 'steps': 11884, 'loss/train': 2.138678789138794} 08/30/2021 15:16:28 - INFO - __main__ - Step 11886: {'lr': 0.0004945166538733529, 'samples': 2282112, 'steps': 11885, 'loss/train': 2.2239696979522705} 08/30/2021 15:16:28 - INFO - __main__ - Step 11887: {'lr': 0.0004945155484641087, 'samples': 2282304, 'steps': 11886, 'loss/train': 1.3135066032409668} 08/30/2021 15:16:28 - INFO - __main__ - Step 11888: {'lr': 0.0004945144429446897, 'samples': 2282496, 'steps': 11887, 'loss/train': 1.7199856042861938} 08/30/2021 15:16:29 - INFO - __main__ - Step 11889: {'lr': 0.000494513337315096, 'samples': 2282688, 'steps': 11888, 'loss/train': 2.244947671890259} 08/30/2021 15:16:29 - INFO - __main__ - Step 11890: {'lr': 0.0004945122315753286, 'samples': 2282880, 'steps': 11889, 'loss/train': 0.1160358339548111} 08/30/2021 15:16:29 - INFO - __main__ - Step 11891: {'lr': 0.0004945111257253877, 'samples': 2283072, 'steps': 11890, 'loss/train': 1.718772292137146} 08/30/2021 15:16:31 - INFO - __main__ - Step 11892: {'lr': 0.0004945100197652738, 'samples': 2283264, 'steps': 11891, 'loss/train': 1.8626842498779297} 08/30/2021 15:16:32 - INFO - __main__ - Step 11893: {'lr': 0.0004945089136949876, 'samples': 2283456, 'steps': 11892, 'loss/train': 1.7901222705841064} 08/30/2021 15:16:32 - INFO - __main__ - Step 11894: {'lr': 0.0004945078075145292, 'samples': 2283648, 'steps': 11893, 'loss/train': 1.7418882846832275} 08/30/2021 15:16:32 - INFO - __main__ - Step 11895: {'lr': 0.0004945067012238996, 'samples': 2283840, 'steps': 11894, 'loss/train': 1.9788968563079834} 08/30/2021 15:16:33 - INFO - __main__ - Step 11896: {'lr': 0.000494505594823099, 'samples': 2284032, 'steps': 11895, 'loss/train': 2.1579482555389404} 08/30/2021 15:16:34 - INFO - __main__ - Step 11897: {'lr': 0.0004945044883121279, 'samples': 2284224, 'steps': 11896, 'loss/train': 2.1536645889282227} 08/30/2021 15:16:35 - INFO - __main__ - Step 11898: {'lr': 0.0004945033816909868, 'samples': 2284416, 'steps': 11897, 'loss/train': 1.8212894201278687} 08/30/2021 15:16:35 - INFO - __main__ - Step 11899: {'lr': 0.0004945022749596764, 'samples': 2284608, 'steps': 11898, 'loss/train': 1.8418039083480835} 08/30/2021 15:16:35 - INFO - __main__ - Step 11900: {'lr': 0.000494501168118197, 'samples': 2284800, 'steps': 11899, 'loss/train': 2.2023589611053467} 08/30/2021 15:16:36 - INFO - __main__ - Step 11901: {'lr': 0.0004945000611665491, 'samples': 2284992, 'steps': 11900, 'loss/train': 0.8514636754989624} 08/30/2021 15:16:37 - INFO - __main__ - Step 11902: {'lr': 0.0004944989541047333, 'samples': 2285184, 'steps': 11901, 'loss/train': 1.9046348333358765} 08/30/2021 15:16:38 - INFO - __main__ - Step 11903: {'lr': 0.0004944978469327499, 'samples': 2285376, 'steps': 11902, 'loss/train': 2.3624885082244873} 08/30/2021 15:16:38 - INFO - __main__ - Step 11904: {'lr': 0.0004944967396505998, 'samples': 2285568, 'steps': 11903, 'loss/train': 2.0583996772766113} 08/30/2021 15:16:38 - INFO - __main__ - Step 11905: {'lr': 0.000494495632258283, 'samples': 2285760, 'steps': 11904, 'loss/train': 1.5278751850128174} 08/30/2021 15:16:39 - INFO - __main__ - Step 11906: {'lr': 0.0004944945247558004, 'samples': 2285952, 'steps': 11905, 'loss/train': 1.9481247663497925} 08/30/2021 15:16:40 - INFO - __main__ - Step 11907: {'lr': 0.0004944934171431522, 'samples': 2286144, 'steps': 11906, 'loss/train': 2.091527223587036} 08/30/2021 15:16:41 - INFO - __main__ - Step 11908: {'lr': 0.0004944923094203391, 'samples': 2286336, 'steps': 11907, 'loss/train': 1.9200574159622192} 08/30/2021 15:16:41 - INFO - __main__ - Step 11909: {'lr': 0.0004944912015873616, 'samples': 2286528, 'steps': 11908, 'loss/train': 1.7044814825057983} 08/30/2021 15:16:41 - INFO - __main__ - Step 11910: {'lr': 0.0004944900936442201, 'samples': 2286720, 'steps': 11909, 'loss/train': 1.9967432022094727} 08/30/2021 15:16:42 - INFO - __main__ - Step 11911: {'lr': 0.000494488985590915, 'samples': 2286912, 'steps': 11910, 'loss/train': 1.1475468873977661} 08/30/2021 15:16:43 - INFO - __main__ - Step 11912: {'lr': 0.0004944878774274472, 'samples': 2287104, 'steps': 11911, 'loss/train': 2.161979913711548} 08/30/2021 15:16:44 - INFO - __main__ - Step 11913: {'lr': 0.0004944867691538167, 'samples': 2287296, 'steps': 11912, 'loss/train': 1.6226567029953003} 08/30/2021 15:16:44 - INFO - __main__ - Step 11914: {'lr': 0.0004944856607700243, 'samples': 2287488, 'steps': 11913, 'loss/train': 1.9641687870025635} 08/30/2021 15:16:44 - INFO - __main__ - Step 11915: {'lr': 0.0004944845522760706, 'samples': 2287680, 'steps': 11914, 'loss/train': 1.3493125438690186} 08/30/2021 15:16:45 - INFO - __main__ - Step 11916: {'lr': 0.0004944834436719557, 'samples': 2287872, 'steps': 11915, 'loss/train': 1.9325021505355835} 08/30/2021 15:16:47 - INFO - __main__ - Step 11917: {'lr': 0.0004944823349576805, 'samples': 2288064, 'steps': 11916, 'loss/train': 1.6535131931304932} 08/30/2021 15:16:47 - INFO - __main__ - Step 11918: {'lr': 0.0004944812261332452, 'samples': 2288256, 'steps': 11917, 'loss/train': 1.7490426301956177} 08/30/2021 15:16:48 - INFO - __main__ - Step 11919: {'lr': 0.0004944801171986505, 'samples': 2288448, 'steps': 11918, 'loss/train': 2.1977345943450928} 08/30/2021 15:16:48 - INFO - __main__ - Step 11920: {'lr': 0.0004944790081538969, 'samples': 2288640, 'steps': 11919, 'loss/train': 1.394598364830017} 08/30/2021 15:16:48 - INFO - __main__ - Step 11921: {'lr': 0.0004944778989989847, 'samples': 2288832, 'steps': 11920, 'loss/train': 1.4951305389404297} 08/30/2021 15:16:49 - INFO - __main__ - Step 11922: {'lr': 0.0004944767897339146, 'samples': 2289024, 'steps': 11921, 'loss/train': 1.8019953966140747} 08/30/2021 15:16:51 - INFO - __main__ - Step 11923: {'lr': 0.000494475680358687, 'samples': 2289216, 'steps': 11922, 'loss/train': 2.575214147567749} 08/30/2021 15:16:51 - INFO - __main__ - Step 11924: {'lr': 0.0004944745708733025, 'samples': 2289408, 'steps': 11923, 'loss/train': 1.8814994096755981} 08/30/2021 15:16:52 - INFO - __main__ - Step 11925: {'lr': 0.0004944734612777615, 'samples': 2289600, 'steps': 11924, 'loss/train': 1.3159366846084595} 08/30/2021 15:16:52 - INFO - __main__ - Step 11926: {'lr': 0.0004944723515720645, 'samples': 2289792, 'steps': 11925, 'loss/train': 1.339134693145752} 08/30/2021 15:16:53 - INFO - __main__ - Step 11927: {'lr': 0.000494471241756212, 'samples': 2289984, 'steps': 11926, 'loss/train': 1.8326565027236938} 08/30/2021 15:16:53 - INFO - __main__ - Step 11928: {'lr': 0.0004944701318302046, 'samples': 2290176, 'steps': 11927, 'loss/train': 1.7587428092956543} 08/30/2021 15:16:54 - INFO - __main__ - Step 11929: {'lr': 0.0004944690217940427, 'samples': 2290368, 'steps': 11928, 'loss/train': 1.8818683624267578} 08/30/2021 15:16:55 - INFO - __main__ - Step 11930: {'lr': 0.0004944679116477269, 'samples': 2290560, 'steps': 11929, 'loss/train': 1.6216456890106201} 08/30/2021 15:16:55 - INFO - __main__ - Step 11931: {'lr': 0.0004944668013912575, 'samples': 2290752, 'steps': 11930, 'loss/train': 4.033947944641113} 08/30/2021 15:16:56 - INFO - __main__ - Step 11932: {'lr': 0.0004944656910246352, 'samples': 2290944, 'steps': 11931, 'loss/train': 1.6390389204025269} 08/30/2021 15:16:56 - INFO - __main__ - Step 11933: {'lr': 0.0004944645805478605, 'samples': 2291136, 'steps': 11932, 'loss/train': 2.1255385875701904} 08/30/2021 15:16:58 - INFO - __main__ - Step 11934: {'lr': 0.0004944634699609338, 'samples': 2291328, 'steps': 11933, 'loss/train': 2.00468373298645} 08/30/2021 15:16:59 - INFO - __main__ - Step 11935: {'lr': 0.0004944623592638555, 'samples': 2291520, 'steps': 11934, 'loss/train': 1.8242744207382202} 08/30/2021 15:16:59 - INFO - __main__ - Step 11936: {'lr': 0.0004944612484566263, 'samples': 2291712, 'steps': 11935, 'loss/train': 1.6638684272766113} 08/30/2021 15:16:59 - INFO - __main__ - Step 11937: {'lr': 0.0004944601375392467, 'samples': 2291904, 'steps': 11936, 'loss/train': 1.7676445245742798} 08/30/2021 15:17:00 - INFO - __main__ - Step 11938: {'lr': 0.000494459026511717, 'samples': 2292096, 'steps': 11937, 'loss/train': 1.9250776767730713} 08/30/2021 15:17:00 - INFO - __main__ - Step 11939: {'lr': 0.000494457915374038, 'samples': 2292288, 'steps': 11938, 'loss/train': 0.27478641271591187} 08/30/2021 15:17:00 - INFO - __main__ - Step 11940: {'lr': 0.00049445680412621, 'samples': 2292480, 'steps': 11939, 'loss/train': 0.22299745678901672} 08/30/2021 15:17:02 - INFO - __main__ - Step 11941: {'lr': 0.0004944556927682335, 'samples': 2292672, 'steps': 11940, 'loss/train': 0.11953985691070557} 08/30/2021 15:17:02 - INFO - __main__ - Step 11942: {'lr': 0.000494454581300109, 'samples': 2292864, 'steps': 11941, 'loss/train': 1.916543960571289} 08/30/2021 15:17:03 - INFO - __main__ - Step 11943: {'lr': 0.0004944534697218371, 'samples': 2293056, 'steps': 11942, 'loss/train': 1.9661853313446045} 08/30/2021 15:17:03 - INFO - __main__ - Step 11944: {'lr': 0.0004944523580334183, 'samples': 2293248, 'steps': 11943, 'loss/train': 1.1564851999282837} 08/30/2021 15:17:03 - INFO - __main__ - Step 11945: {'lr': 0.0004944512462348528, 'samples': 2293440, 'steps': 11944, 'loss/train': 0.4339814782142639} 08/30/2021 15:17:05 - INFO - __main__ - Step 11946: {'lr': 0.0004944501343261416, 'samples': 2293632, 'steps': 11945, 'loss/train': 2.549010753631592} 08/30/2021 15:17:05 - INFO - __main__ - Step 11947: {'lr': 0.0004944490223072848, 'samples': 2293824, 'steps': 11946, 'loss/train': 1.7171857357025146} 08/30/2021 15:17:06 - INFO - __main__ - Step 11948: {'lr': 0.0004944479101782831, 'samples': 2294016, 'steps': 11947, 'loss/train': 1.3282312154769897} 08/30/2021 15:17:06 - INFO - __main__ - Step 11949: {'lr': 0.0004944467979391369, 'samples': 2294208, 'steps': 11948, 'loss/train': 1.839789628982544} 08/30/2021 15:17:06 - INFO - __main__ - Step 11950: {'lr': 0.0004944456855898469, 'samples': 2294400, 'steps': 11949, 'loss/train': 1.7644050121307373} 08/30/2021 15:17:08 - INFO - __main__ - Step 11951: {'lr': 0.0004944445731304133, 'samples': 2294592, 'steps': 11950, 'loss/train': 2.0731210708618164} 08/30/2021 15:17:08 - INFO - __main__ - Step 11952: {'lr': 0.0004944434605608367, 'samples': 2294784, 'steps': 11951, 'loss/train': 2.1134634017944336} 08/30/2021 15:17:09 - INFO - __main__ - Step 11953: {'lr': 0.0004944423478811177, 'samples': 2294976, 'steps': 11952, 'loss/train': 1.8561817407608032} 08/30/2021 15:17:09 - INFO - __main__ - Step 11954: {'lr': 0.0004944412350912567, 'samples': 2295168, 'steps': 11953, 'loss/train': 1.8143947124481201} 08/30/2021 15:17:09 - INFO - __main__ - Step 11955: {'lr': 0.0004944401221912544, 'samples': 2295360, 'steps': 11954, 'loss/train': 1.742327332496643} 08/30/2021 15:17:10 - INFO - __main__ - Step 11956: {'lr': 0.0004944390091811111, 'samples': 2295552, 'steps': 11955, 'loss/train': 1.770018219947815} 08/30/2021 15:17:11 - INFO - __main__ - Step 11957: {'lr': 0.0004944378960608272, 'samples': 2295744, 'steps': 11956, 'loss/train': 1.9021027088165283} 08/30/2021 15:17:12 - INFO - __main__ - Step 11958: {'lr': 0.0004944367828304035, 'samples': 2295936, 'steps': 11957, 'loss/train': 1.9084395170211792} 08/30/2021 15:17:12 - INFO - __main__ - Step 11959: {'lr': 0.0004944356694898404, 'samples': 2296128, 'steps': 11958, 'loss/train': 1.5890378952026367} 08/30/2021 15:17:13 - INFO - __main__ - Step 11960: {'lr': 0.0004944345560391382, 'samples': 2296320, 'steps': 11959, 'loss/train': 1.9585572481155396} 08/30/2021 15:17:13 - INFO - __main__ - Step 11961: {'lr': 0.0004944334424782977, 'samples': 2296512, 'steps': 11960, 'loss/train': 2.0318806171417236} 08/30/2021 15:17:15 - INFO - __main__ - Step 11962: {'lr': 0.0004944323288073192, 'samples': 2296704, 'steps': 11961, 'loss/train': 1.6990612745285034} 08/30/2021 15:17:15 - INFO - __main__ - Step 11963: {'lr': 0.0004944312150262033, 'samples': 2296896, 'steps': 11962, 'loss/train': 2.077442169189453} 08/30/2021 15:17:15 - INFO - __main__ - Step 11964: {'lr': 0.0004944301011349505, 'samples': 2297088, 'steps': 11963, 'loss/train': 1.551512360572815} 08/30/2021 15:17:16 - INFO - __main__ - Step 11965: {'lr': 0.0004944289871335612, 'samples': 2297280, 'steps': 11964, 'loss/train': 1.5474135875701904} 08/30/2021 15:17:16 - INFO - __main__ - Step 11966: {'lr': 0.0004944278730220359, 'samples': 2297472, 'steps': 11965, 'loss/train': 4.930060863494873} 08/30/2021 15:17:18 - INFO - __main__ - Step 11967: {'lr': 0.0004944267588003754, 'samples': 2297664, 'steps': 11966, 'loss/train': 1.3303277492523193} 08/30/2021 15:17:18 - INFO - __main__ - Step 11968: {'lr': 0.0004944256444685798, 'samples': 2297856, 'steps': 11967, 'loss/train': 2.613445520401001} 08/30/2021 15:17:18 - INFO - __main__ - Step 11969: {'lr': 0.0004944245300266498, 'samples': 2298048, 'steps': 11968, 'loss/train': 1.755059838294983} 08/30/2021 15:17:19 - INFO - __main__ - Step 11970: {'lr': 0.0004944234154745859, 'samples': 2298240, 'steps': 11969, 'loss/train': 2.520012617111206} 08/30/2021 15:17:19 - INFO - __main__ - Step 11971: {'lr': 0.0004944223008123886, 'samples': 2298432, 'steps': 11970, 'loss/train': 1.772457242012024} 08/30/2021 15:17:21 - INFO - __main__ - Step 11972: {'lr': 0.0004944211860400582, 'samples': 2298624, 'steps': 11971, 'loss/train': 2.64841628074646} 08/30/2021 15:17:21 - INFO - __main__ - Step 11973: {'lr': 0.0004944200711575956, 'samples': 2298816, 'steps': 11972, 'loss/train': 2.3025026321411133} 08/30/2021 15:17:21 - INFO - __main__ - Step 11974: {'lr': 0.0004944189561650011, 'samples': 2299008, 'steps': 11973, 'loss/train': 1.9383209943771362} 08/30/2021 15:17:22 - INFO - __main__ - Step 11975: {'lr': 0.0004944178410622751, 'samples': 2299200, 'steps': 11974, 'loss/train': 2.0031256675720215} 08/30/2021 15:17:22 - INFO - __main__ - Step 11976: {'lr': 0.0004944167258494181, 'samples': 2299392, 'steps': 11975, 'loss/train': 1.6150741577148438} 08/30/2021 15:17:24 - INFO - __main__ - Step 11977: {'lr': 0.0004944156105264308, 'samples': 2299584, 'steps': 11976, 'loss/train': 1.7885252237319946} 08/30/2021 15:17:24 - INFO - __main__ - Step 11978: {'lr': 0.0004944144950933137, 'samples': 2299776, 'steps': 11977, 'loss/train': 1.420885682106018} 08/30/2021 15:17:24 - INFO - __main__ - Step 11979: {'lr': 0.000494413379550067, 'samples': 2299968, 'steps': 11978, 'loss/train': 1.8487935066223145} 08/30/2021 15:17:25 - INFO - __main__ - Step 11980: {'lr': 0.0004944122638966916, 'samples': 2300160, 'steps': 11979, 'loss/train': 1.9244537353515625} 08/30/2021 15:17:25 - INFO - __main__ - Step 11981: {'lr': 0.0004944111481331876, 'samples': 2300352, 'steps': 11980, 'loss/train': 1.6892220973968506} 08/30/2021 15:17:26 - INFO - __main__ - Step 11982: {'lr': 0.0004944100322595558, 'samples': 2300544, 'steps': 11981, 'loss/train': 1.8874355554580688} 08/30/2021 15:17:27 - INFO - __main__ - Step 11983: {'lr': 0.0004944089162757968, 'samples': 2300736, 'steps': 11982, 'loss/train': 1.6030975580215454} 08/30/2021 15:17:28 - INFO - __main__ - Step 11984: {'lr': 0.0004944078001819106, 'samples': 2300928, 'steps': 11983, 'loss/train': 1.707241415977478} 08/30/2021 15:17:28 - INFO - __main__ - Step 11985: {'lr': 0.0004944066839778983, 'samples': 2301120, 'steps': 11984, 'loss/train': 1.5362730026245117} 08/30/2021 15:17:29 - INFO - __main__ - Step 11986: {'lr': 0.0004944055676637599, 'samples': 2301312, 'steps': 11985, 'loss/train': 1.617297887802124} 08/30/2021 15:17:29 - INFO - __main__ - Step 11987: {'lr': 0.0004944044512394962, 'samples': 2301504, 'steps': 11986, 'loss/train': 2.1507620811462402} 08/30/2021 15:17:31 - INFO - __main__ - Step 11988: {'lr': 0.0004944033347051076, 'samples': 2301696, 'steps': 11987, 'loss/train': 1.9792611598968506} 08/30/2021 15:17:31 - INFO - __main__ - Step 11989: {'lr': 0.0004944022180605947, 'samples': 2301888, 'steps': 11988, 'loss/train': 1.146347999572754} 08/30/2021 15:17:31 - INFO - __main__ - Step 11990: {'lr': 0.0004944011013059579, 'samples': 2302080, 'steps': 11989, 'loss/train': 1.4543150663375854} 08/30/2021 15:17:32 - INFO - __main__ - Step 11991: {'lr': 0.0004943999844411977, 'samples': 2302272, 'steps': 11990, 'loss/train': 2.1181256771087646} 08/30/2021 15:17:32 - INFO - __main__ - Step 11992: {'lr': 0.0004943988674663147, 'samples': 2302464, 'steps': 11991, 'loss/train': 2.086256980895996} 08/30/2021 15:17:34 - INFO - __main__ - Step 11993: {'lr': 0.0004943977503813092, 'samples': 2302656, 'steps': 11992, 'loss/train': 2.1037232875823975} 08/30/2021 15:17:34 - INFO - __main__ - Step 11994: {'lr': 0.000494396633186182, 'samples': 2302848, 'steps': 11993, 'loss/train': 2.0811357498168945} 08/30/2021 15:17:34 - INFO - __main__ - Step 11995: {'lr': 0.0004943955158809334, 'samples': 2303040, 'steps': 11994, 'loss/train': 1.6144832372665405} 08/30/2021 15:17:35 - INFO - __main__ - Step 11996: {'lr': 0.0004943943984655639, 'samples': 2303232, 'steps': 11995, 'loss/train': 1.6353332996368408} 08/30/2021 15:17:35 - INFO - __main__ - Step 11997: {'lr': 0.0004943932809400741, 'samples': 2303424, 'steps': 11996, 'loss/train': 2.0281214714050293} 08/30/2021 15:17:37 - INFO - __main__ - Step 11998: {'lr': 0.0004943921633044644, 'samples': 2303616, 'steps': 11997, 'loss/train': 1.399830937385559} 08/30/2021 15:17:37 - INFO - __main__ - Step 11999: {'lr': 0.0004943910455587354, 'samples': 2303808, 'steps': 11998, 'loss/train': 1.625523328781128} 08/30/2021 15:17:37 - INFO - __main__ - Step 12000: {'lr': 0.0004943899277028877, 'samples': 2304000, 'steps': 11999, 'loss/train': 1.9747083187103271} 08/30/2021 15:17:38 - INFO - __main__ - Step 12001: {'lr': 0.0004943888097369216, 'samples': 2304192, 'steps': 12000, 'loss/train': 1.6894176006317139} 08/30/2021 15:17:38 - INFO - __main__ - Step 12002: {'lr': 0.0004943876916608375, 'samples': 2304384, 'steps': 12001, 'loss/train': 1.666957974433899} 08/30/2021 15:17:40 - INFO - __main__ - Step 12003: {'lr': 0.0004943865734746364, 'samples': 2304576, 'steps': 12002, 'loss/train': 1.9539308547973633} 08/30/2021 15:17:40 - INFO - __main__ - Step 12004: {'lr': 0.0004943854551783182, 'samples': 2304768, 'steps': 12003, 'loss/train': 2.365431070327759} 08/30/2021 15:17:40 - INFO - __main__ - Step 12005: {'lr': 0.0004943843367718838, 'samples': 2304960, 'steps': 12004, 'loss/train': 1.2316572666168213} 08/30/2021 15:17:41 - INFO - __main__ - Step 12006: {'lr': 0.0004943832182553336, 'samples': 2305152, 'steps': 12005, 'loss/train': 1.4853630065917969} 08/30/2021 15:17:41 - INFO - __main__ - Step 12007: {'lr': 0.000494382099628668, 'samples': 2305344, 'steps': 12006, 'loss/train': 1.1035212278366089} 08/30/2021 15:17:43 - INFO - __main__ - Step 12008: {'lr': 0.0004943809808918877, 'samples': 2305536, 'steps': 12007, 'loss/train': 1.5442581176757812} 08/30/2021 15:17:44 - INFO - __main__ - Step 12009: {'lr': 0.000494379862044993, 'samples': 2305728, 'steps': 12008, 'loss/train': 2.388361692428589} 08/30/2021 15:17:44 - INFO - __main__ - Step 12010: {'lr': 0.0004943787430879846, 'samples': 2305920, 'steps': 12009, 'loss/train': 1.524498701095581} 08/30/2021 15:17:44 - INFO - __main__ - Step 12011: {'lr': 0.0004943776240208628, 'samples': 2306112, 'steps': 12010, 'loss/train': 1.300168752670288} 08/30/2021 15:17:45 - INFO - __main__ - Step 12012: {'lr': 0.0004943765048436283, 'samples': 2306304, 'steps': 12011, 'loss/train': 1.6063472032546997} 08/30/2021 15:17:45 - INFO - __main__ - Step 12013: {'lr': 0.0004943753855562815, 'samples': 2306496, 'steps': 12012, 'loss/train': 1.5207185745239258} 08/30/2021 15:17:45 - INFO - __main__ - Step 12014: {'lr': 0.000494374266158823, 'samples': 2306688, 'steps': 12013, 'loss/train': 0.12340107560157776} 08/30/2021 15:17:47 - INFO - __main__ - Step 12015: {'lr': 0.0004943731466512531, 'samples': 2306880, 'steps': 12014, 'loss/train': 1.4685721397399902} 08/30/2021 15:17:47 - INFO - __main__ - Step 12016: {'lr': 0.0004943720270335724, 'samples': 2307072, 'steps': 12015, 'loss/train': 2.2033302783966064} 08/30/2021 15:17:48 - INFO - __main__ - Step 12017: {'lr': 0.0004943709073057816, 'samples': 2307264, 'steps': 12016, 'loss/train': 2.157628059387207} 08/30/2021 15:17:48 - INFO - __main__ - Step 12018: {'lr': 0.000494369787467881, 'samples': 2307456, 'steps': 12017, 'loss/train': 6.126431941986084} 08/30/2021 15:17:48 - INFO - __main__ - Step 12019: {'lr': 0.000494368667519871, 'samples': 2307648, 'steps': 12018, 'loss/train': 1.3012217283248901} 08/30/2021 15:17:50 - INFO - __main__ - Step 12020: {'lr': 0.0004943675474617524, 'samples': 2307840, 'steps': 12019, 'loss/train': 1.4627915620803833} 08/30/2021 15:17:51 - INFO - __main__ - Step 12021: {'lr': 0.0004943664272935255, 'samples': 2308032, 'steps': 12020, 'loss/train': 1.4414600133895874} 08/30/2021 15:17:51 - INFO - __main__ - Step 12022: {'lr': 0.0004943653070151909, 'samples': 2308224, 'steps': 12021, 'loss/train': 1.6685082912445068} 08/30/2021 15:17:52 - INFO - __main__ - Step 12023: {'lr': 0.000494364186626749, 'samples': 2308416, 'steps': 12022, 'loss/train': 1.2931737899780273} 08/30/2021 15:17:52 - INFO - __main__ - Step 12024: {'lr': 0.0004943630661282004, 'samples': 2308608, 'steps': 12023, 'loss/train': 0.8000673651695251} 08/30/2021 15:17:52 - INFO - __main__ - Step 12025: {'lr': 0.0004943619455195456, 'samples': 2308800, 'steps': 12024, 'loss/train': 0.7814105153083801} 08/30/2021 15:17:54 - INFO - __main__ - Step 12026: {'lr': 0.000494360824800785, 'samples': 2308992, 'steps': 12025, 'loss/train': 0.7187609672546387} 08/30/2021 15:17:55 - INFO - __main__ - Step 12027: {'lr': 0.0004943597039719192, 'samples': 2309184, 'steps': 12026, 'loss/train': 1.802985429763794} 08/30/2021 15:17:55 - INFO - __main__ - Step 12028: {'lr': 0.0004943585830329487, 'samples': 2309376, 'steps': 12027, 'loss/train': 2.038097620010376} 08/30/2021 15:17:55 - INFO - __main__ - Step 12029: {'lr': 0.0004943574619838741, 'samples': 2309568, 'steps': 12028, 'loss/train': 1.644842505455017} 08/30/2021 15:17:56 - INFO - __main__ - Step 12030: {'lr': 0.0004943563408246957, 'samples': 2309760, 'steps': 12029, 'loss/train': 1.4243265390396118} 08/30/2021 15:17:57 - INFO - __main__ - Step 12031: {'lr': 0.000494355219555414, 'samples': 2309952, 'steps': 12030, 'loss/train': 1.8283549547195435} 08/30/2021 15:17:58 - INFO - __main__ - Step 12032: {'lr': 0.0004943540981760298, 'samples': 2310144, 'steps': 12031, 'loss/train': 2.287456750869751} 08/30/2021 15:17:58 - INFO - __main__ - Step 12033: {'lr': 0.0004943529766865434, 'samples': 2310336, 'steps': 12032, 'loss/train': 2.2850167751312256} 08/30/2021 15:17:58 - INFO - __main__ - Step 12034: {'lr': 0.0004943518550869552, 'samples': 2310528, 'steps': 12033, 'loss/train': 1.8853846788406372} 08/30/2021 15:17:59 - INFO - __main__ - Step 12035: {'lr': 0.0004943507333772659, 'samples': 2310720, 'steps': 12034, 'loss/train': 1.424363613128662} 08/30/2021 15:17:59 - INFO - __main__ - Step 12036: {'lr': 0.0004943496115574758, 'samples': 2310912, 'steps': 12035, 'loss/train': 0.38498976826667786} 08/30/2021 15:18:01 - INFO - __main__ - Step 12037: {'lr': 0.0004943484896275857, 'samples': 2311104, 'steps': 12036, 'loss/train': 1.6763032674789429} 08/30/2021 15:18:02 - INFO - __main__ - Step 12038: {'lr': 0.0004943473675875959, 'samples': 2311296, 'steps': 12037, 'loss/train': 1.6160004138946533} 08/30/2021 15:18:02 - INFO - __main__ - Step 12039: {'lr': 0.0004943462454375069, 'samples': 2311488, 'steps': 12038, 'loss/train': 1.7438759803771973} 08/30/2021 15:18:02 - INFO - __main__ - Step 12040: {'lr': 0.0004943451231773192, 'samples': 2311680, 'steps': 12039, 'loss/train': 1.6552613973617554} 08/30/2021 15:18:03 - INFO - __main__ - Step 12041: {'lr': 0.0004943440008070336, 'samples': 2311872, 'steps': 12040, 'loss/train': 1.7740602493286133} 08/30/2021 15:18:04 - INFO - __main__ - Step 12042: {'lr': 0.0004943428783266502, 'samples': 2312064, 'steps': 12041, 'loss/train': 1.8296421766281128} 08/30/2021 15:18:05 - INFO - __main__ - Step 12043: {'lr': 0.0004943417557361696, 'samples': 2312256, 'steps': 12042, 'loss/train': 2.170560359954834} 08/30/2021 15:18:05 - INFO - __main__ - Step 12044: {'lr': 0.0004943406330355925, 'samples': 2312448, 'steps': 12043, 'loss/train': 2.164201259613037} 08/30/2021 15:18:05 - INFO - __main__ - Step 12045: {'lr': 0.0004943395102249192, 'samples': 2312640, 'steps': 12044, 'loss/train': 1.9016125202178955} 08/30/2021 15:18:06 - INFO - __main__ - Step 12046: {'lr': 0.0004943383873041503, 'samples': 2312832, 'steps': 12045, 'loss/train': 0.9587546586990356} 08/30/2021 15:18:07 - INFO - __main__ - Step 12047: {'lr': 0.0004943372642732864, 'samples': 2313024, 'steps': 12046, 'loss/train': 1.6233153343200684} 08/30/2021 15:18:08 - INFO - __main__ - Step 12048: {'lr': 0.0004943361411323277, 'samples': 2313216, 'steps': 12047, 'loss/train': 1.6164321899414062} 08/30/2021 15:18:08 - INFO - __main__ - Step 12049: {'lr': 0.0004943350178812751, 'samples': 2313408, 'steps': 12048, 'loss/train': 1.4530580043792725} 08/30/2021 15:18:08 - INFO - __main__ - Step 12050: {'lr': 0.0004943338945201288, 'samples': 2313600, 'steps': 12049, 'loss/train': 2.2362661361694336} 08/30/2021 15:18:09 - INFO - __main__ - Step 12051: {'lr': 0.0004943327710488894, 'samples': 2313792, 'steps': 12050, 'loss/train': 1.9938535690307617} 08/30/2021 15:18:10 - INFO - __main__ - Step 12052: {'lr': 0.0004943316474675575, 'samples': 2313984, 'steps': 12051, 'loss/train': 1.6572089195251465} 08/30/2021 15:18:11 - INFO - __main__ - Step 12053: {'lr': 0.0004943305237761335, 'samples': 2314176, 'steps': 12052, 'loss/train': 1.9264360666275024} 08/30/2021 15:18:11 - INFO - __main__ - Step 12054: {'lr': 0.0004943293999746179, 'samples': 2314368, 'steps': 12053, 'loss/train': 5.252533912658691} 08/30/2021 15:18:11 - INFO - __main__ - Step 12055: {'lr': 0.0004943282760630114, 'samples': 2314560, 'steps': 12054, 'loss/train': 2.003549337387085} 08/30/2021 15:18:12 - INFO - __main__ - Step 12056: {'lr': 0.0004943271520413141, 'samples': 2314752, 'steps': 12055, 'loss/train': 1.935607671737671} 08/30/2021 15:18:12 - INFO - __main__ - Step 12057: {'lr': 0.0004943260279095269, 'samples': 2314944, 'steps': 12056, 'loss/train': 2.268451452255249} 08/30/2021 15:18:14 - INFO - __main__ - Step 12058: {'lr': 0.0004943249036676501, 'samples': 2315136, 'steps': 12057, 'loss/train': 1.9314218759536743} 08/30/2021 15:18:14 - INFO - __main__ - Step 12059: {'lr': 0.0004943237793156844, 'samples': 2315328, 'steps': 12058, 'loss/train': 1.8404067754745483} 08/30/2021 15:18:15 - INFO - __main__ - Step 12060: {'lr': 0.00049432265485363, 'samples': 2315520, 'steps': 12059, 'loss/train': 1.3859785795211792} 08/30/2021 15:18:15 - INFO - __main__ - Step 12061: {'lr': 0.0004943215302814877, 'samples': 2315712, 'steps': 12060, 'loss/train': 0.191435769200325} 08/30/2021 15:18:15 - INFO - __main__ - Step 12062: {'lr': 0.0004943204055992579, 'samples': 2315904, 'steps': 12061, 'loss/train': 1.8861454725265503} 08/30/2021 15:18:17 - INFO - __main__ - Step 12063: {'lr': 0.0004943192808069411, 'samples': 2316096, 'steps': 12062, 'loss/train': 1.554942011833191} 08/30/2021 15:18:17 - INFO - __main__ - Step 12064: {'lr': 0.0004943181559045378, 'samples': 2316288, 'steps': 12063, 'loss/train': 2.055192470550537} 08/30/2021 15:18:18 - INFO - __main__ - Step 12065: {'lr': 0.0004943170308920483, 'samples': 2316480, 'steps': 12064, 'loss/train': 1.8513082265853882} 08/30/2021 15:18:18 - INFO - __main__ - Step 12066: {'lr': 0.0004943159057694736, 'samples': 2316672, 'steps': 12065, 'loss/train': 1.7051243782043457} 08/30/2021 15:18:19 - INFO - __main__ - Step 12067: {'lr': 0.0004943147805368138, 'samples': 2316864, 'steps': 12066, 'loss/train': 0.13096553087234497} 08/30/2021 15:18:20 - INFO - __main__ - Step 12068: {'lr': 0.0004943136551940695, 'samples': 2317056, 'steps': 12067, 'loss/train': 2.0382769107818604} 08/30/2021 15:18:20 - INFO - __main__ - Step 12069: {'lr': 0.0004943125297412413, 'samples': 2317248, 'steps': 12068, 'loss/train': 2.5085906982421875} 08/30/2021 15:18:21 - INFO - __main__ - Step 12070: {'lr': 0.0004943114041783296, 'samples': 2317440, 'steps': 12069, 'loss/train': 1.7958232164382935} 08/30/2021 15:18:21 - INFO - __main__ - Step 12071: {'lr': 0.000494310278505335, 'samples': 2317632, 'steps': 12070, 'loss/train': 1.4741815328598022} 08/30/2021 15:18:22 - INFO - __main__ - Step 12072: {'lr': 0.0004943091527222579, 'samples': 2317824, 'steps': 12071, 'loss/train': 1.7163307666778564} 08/30/2021 15:18:23 - INFO - __main__ - Step 12073: {'lr': 0.0004943080268290989, 'samples': 2318016, 'steps': 12072, 'loss/train': 1.750003695487976} 08/30/2021 15:18:23 - INFO - __main__ - Step 12074: {'lr': 0.0004943069008258584, 'samples': 2318208, 'steps': 12073, 'loss/train': 1.5996164083480835} 08/30/2021 15:18:24 - INFO - __main__ - Step 12075: {'lr': 0.0004943057747125371, 'samples': 2318400, 'steps': 12074, 'loss/train': 1.823594093322754} 08/30/2021 15:18:24 - INFO - __main__ - Step 12076: {'lr': 0.0004943046484891352, 'samples': 2318592, 'steps': 12075, 'loss/train': 1.444747805595398} 08/30/2021 15:18:24 - INFO - __main__ - Step 12077: {'lr': 0.0004943035221556536, 'samples': 2318784, 'steps': 12076, 'loss/train': 1.5687693357467651} 08/30/2021 15:18:26 - INFO - __main__ - Step 12078: {'lr': 0.0004943023957120926, 'samples': 2318976, 'steps': 12077, 'loss/train': 1.819845199584961} 08/30/2021 15:18:27 - INFO - __main__ - Step 12079: {'lr': 0.0004943012691584526, 'samples': 2319168, 'steps': 12078, 'loss/train': 1.7982951402664185} 08/30/2021 15:18:27 - INFO - __main__ - Step 12080: {'lr': 0.0004943001424947343, 'samples': 2319360, 'steps': 12079, 'loss/train': 0.7677766680717468} 08/30/2021 15:18:27 - INFO - __main__ - Step 12081: {'lr': 0.000494299015720938, 'samples': 2319552, 'steps': 12080, 'loss/train': 1.7462985515594482} 08/30/2021 15:18:28 - INFO - __main__ - Step 12082: {'lr': 0.0004942978888370645, 'samples': 2319744, 'steps': 12081, 'loss/train': 1.373520851135254} 08/30/2021 15:18:29 - INFO - __main__ - Step 12083: {'lr': 0.000494296761843114, 'samples': 2319936, 'steps': 12082, 'loss/train': 1.4659006595611572} 08/30/2021 15:18:30 - INFO - __main__ - Step 12084: {'lr': 0.0004942956347390872, 'samples': 2320128, 'steps': 12083, 'loss/train': 1.479794979095459} 08/30/2021 15:18:30 - INFO - __main__ - Step 12085: {'lr': 0.0004942945075249845, 'samples': 2320320, 'steps': 12084, 'loss/train': 1.0551555156707764} 08/30/2021 15:18:30 - INFO - __main__ - Step 12086: {'lr': 0.0004942933802008066, 'samples': 2320512, 'steps': 12085, 'loss/train': 1.9779893159866333} 08/30/2021 15:18:31 - INFO - __main__ - Step 12087: {'lr': 0.0004942922527665538, 'samples': 2320704, 'steps': 12086, 'loss/train': 1.4531564712524414} 08/30/2021 15:18:31 - INFO - __main__ - Step 12088: {'lr': 0.0004942911252222267, 'samples': 2320896, 'steps': 12087, 'loss/train': 1.9168614149093628} 08/30/2021 15:18:32 - INFO - __main__ - Step 12089: {'lr': 0.0004942899975678257, 'samples': 2321088, 'steps': 12088, 'loss/train': 1.192571759223938} 08/30/2021 15:18:33 - INFO - __main__ - Step 12090: {'lr': 0.0004942888698033515, 'samples': 2321280, 'steps': 12089, 'loss/train': 1.5015541315078735} 08/30/2021 15:18:33 - INFO - __main__ - Step 12091: {'lr': 0.0004942877419288045, 'samples': 2321472, 'steps': 12090, 'loss/train': 1.565805435180664} 08/30/2021 15:18:34 - INFO - __main__ - Step 12092: {'lr': 0.0004942866139441851, 'samples': 2321664, 'steps': 12091, 'loss/train': 1.1745671033859253} 08/30/2021 15:18:34 - INFO - __main__ - Step 12093: {'lr': 0.0004942854858494941, 'samples': 2321856, 'steps': 12092, 'loss/train': 1.6281485557556152} 08/30/2021 15:18:36 - INFO - __main__ - Step 12094: {'lr': 0.0004942843576447316, 'samples': 2322048, 'steps': 12093, 'loss/train': 1.7991557121276855} 08/30/2021 15:18:37 - INFO - __main__ - Step 12095: {'lr': 0.0004942832293298986, 'samples': 2322240, 'steps': 12094, 'loss/train': 1.21683669090271} 08/30/2021 15:18:37 - INFO - __main__ - Step 12096: {'lr': 0.0004942821009049952, 'samples': 2322432, 'steps': 12095, 'loss/train': 1.626397967338562} 08/30/2021 15:18:37 - INFO - __main__ - Step 12097: {'lr': 0.0004942809723700221, 'samples': 2322624, 'steps': 12096, 'loss/train': 1.7386540174484253} 08/30/2021 15:18:38 - INFO - __main__ - Step 12098: {'lr': 0.0004942798437249797, 'samples': 2322816, 'steps': 12097, 'loss/train': 1.600664734840393} 08/30/2021 15:18:39 - INFO - __main__ - Step 12099: {'lr': 0.0004942787149698687, 'samples': 2323008, 'steps': 12098, 'loss/train': 2.1354129314422607} 08/30/2021 15:18:40 - INFO - __main__ - Step 12100: {'lr': 0.0004942775861046893, 'samples': 2323200, 'steps': 12099, 'loss/train': 1.0666619539260864} 08/30/2021 15:18:40 - INFO - __main__ - Step 12101: {'lr': 0.0004942764571294422, 'samples': 2323392, 'steps': 12100, 'loss/train': 1.6054303646087646} 08/30/2021 15:18:40 - INFO - __main__ - Step 12102: {'lr': 0.0004942753280441281, 'samples': 2323584, 'steps': 12101, 'loss/train': 2.294025421142578} 08/30/2021 15:18:41 - INFO - __main__ - Step 12103: {'lr': 0.0004942741988487471, 'samples': 2323776, 'steps': 12102, 'loss/train': 1.8871198892593384} 08/30/2021 15:18:42 - INFO - __main__ - Step 12104: {'lr': 0.0004942730695433001, 'samples': 2323968, 'steps': 12103, 'loss/train': 0.6726149916648865} 08/30/2021 15:18:42 - INFO - __main__ - Step 12105: {'lr': 0.0004942719401277873, 'samples': 2324160, 'steps': 12104, 'loss/train': 1.5810009241104126} 08/30/2021 15:18:43 - INFO - __main__ - Step 12106: {'lr': 0.0004942708106022094, 'samples': 2324352, 'steps': 12105, 'loss/train': 1.3863474130630493} 08/30/2021 15:18:43 - INFO - __main__ - Step 12107: {'lr': 0.0004942696809665668, 'samples': 2324544, 'steps': 12106, 'loss/train': 1.8221224546432495} 08/30/2021 15:18:44 - INFO - __main__ - Step 12108: {'lr': 0.0004942685512208599, 'samples': 2324736, 'steps': 12107, 'loss/train': 1.6639631986618042} 08/30/2021 15:18:45 - INFO - __main__ - Step 12109: {'lr': 0.0004942674213650896, 'samples': 2324928, 'steps': 12108, 'loss/train': 1.747971773147583} 08/30/2021 15:18:46 - INFO - __main__ - Step 12110: {'lr': 0.000494266291399256, 'samples': 2325120, 'steps': 12109, 'loss/train': 2.1878867149353027} 08/30/2021 15:18:46 - INFO - __main__ - Step 12111: {'lr': 0.0004942651613233599, 'samples': 2325312, 'steps': 12110, 'loss/train': 1.359521508216858} 08/30/2021 15:18:46 - INFO - __main__ - Step 12112: {'lr': 0.0004942640311374017, 'samples': 2325504, 'steps': 12111, 'loss/train': 1.5496395826339722} 08/30/2021 15:18:47 - INFO - __main__ - Step 12113: {'lr': 0.0004942629008413818, 'samples': 2325696, 'steps': 12112, 'loss/train': 1.916627049446106} 08/30/2021 15:18:48 - INFO - __main__ - Step 12114: {'lr': 0.0004942617704353008, 'samples': 2325888, 'steps': 12113, 'loss/train': 1.8518034219741821} 08/30/2021 15:18:49 - INFO - __main__ - Step 12115: {'lr': 0.0004942606399191593, 'samples': 2326080, 'steps': 12114, 'loss/train': 2.5131680965423584} 08/30/2021 15:18:49 - INFO - __main__ - Step 12116: {'lr': 0.0004942595092929577, 'samples': 2326272, 'steps': 12115, 'loss/train': 1.6142479181289673} 08/30/2021 15:18:50 - INFO - __main__ - Step 12117: {'lr': 0.0004942583785566965, 'samples': 2326464, 'steps': 12116, 'loss/train': 1.4931957721710205} 08/30/2021 15:18:50 - INFO - __main__ - Step 12118: {'lr': 0.0004942572477103763, 'samples': 2326656, 'steps': 12117, 'loss/train': 1.6612237691879272} 08/30/2021 15:18:51 - INFO - __main__ - Step 12119: {'lr': 0.0004942561167539975, 'samples': 2326848, 'steps': 12118, 'loss/train': 1.540592908859253} 08/30/2021 15:18:52 - INFO - __main__ - Step 12120: {'lr': 0.0004942549856875606, 'samples': 2327040, 'steps': 12119, 'loss/train': 1.9624732732772827} 08/30/2021 15:18:52 - INFO - __main__ - Step 12121: {'lr': 0.0004942538545110663, 'samples': 2327232, 'steps': 12120, 'loss/train': 1.8401318788528442} 08/30/2021 15:18:53 - INFO - __main__ - Step 12122: {'lr': 0.0004942527232245149, 'samples': 2327424, 'steps': 12121, 'loss/train': 1.9509354829788208} 08/30/2021 15:18:53 - INFO - __main__ - Step 12123: {'lr': 0.0004942515918279071, 'samples': 2327616, 'steps': 12122, 'loss/train': 1.8921127319335938} 08/30/2021 15:18:54 - INFO - __main__ - Step 12124: {'lr': 0.0004942504603212433, 'samples': 2327808, 'steps': 12123, 'loss/train': 1.6281896829605103} 08/30/2021 15:18:55 - INFO - __main__ - Step 12125: {'lr': 0.0004942493287045239, 'samples': 2328000, 'steps': 12124, 'loss/train': 1.2714658975601196} 08/30/2021 15:18:55 - INFO - __main__ - Step 12126: {'lr': 0.0004942481969777495, 'samples': 2328192, 'steps': 12125, 'loss/train': 1.8391683101654053} 08/30/2021 15:18:55 - INFO - __main__ - Step 12127: {'lr': 0.0004942470651409207, 'samples': 2328384, 'steps': 12126, 'loss/train': 1.2472349405288696} 08/30/2021 15:18:56 - INFO - __main__ - Step 12128: {'lr': 0.000494245933194038, 'samples': 2328576, 'steps': 12127, 'loss/train': 1.6282511949539185} 08/30/2021 15:18:57 - INFO - __main__ - Step 12129: {'lr': 0.0004942448011371018, 'samples': 2328768, 'steps': 12128, 'loss/train': 1.464552879333496} 08/30/2021 15:18:58 - INFO - __main__ - Step 12130: {'lr': 0.0004942436689701126, 'samples': 2328960, 'steps': 12129, 'loss/train': 1.3245165348052979} 08/30/2021 15:18:58 - INFO - __main__ - Step 12131: {'lr': 0.000494242536693071, 'samples': 2329152, 'steps': 12130, 'loss/train': 1.7746152877807617} 08/30/2021 15:18:58 - INFO - __main__ - Step 12132: {'lr': 0.0004942414043059776, 'samples': 2329344, 'steps': 12131, 'loss/train': 1.863704800605774} 08/30/2021 15:18:59 - INFO - __main__ - Step 12133: {'lr': 0.0004942402718088326, 'samples': 2329536, 'steps': 12132, 'loss/train': 1.7185570001602173} 08/30/2021 15:19:00 - INFO - __main__ - Step 12134: {'lr': 0.0004942391392016368, 'samples': 2329728, 'steps': 12133, 'loss/train': 1.7659586668014526} 08/30/2021 15:19:01 - INFO - __main__ - Step 12135: {'lr': 0.0004942380064843906, 'samples': 2329920, 'steps': 12134, 'loss/train': 1.9427530765533447} 08/30/2021 15:19:01 - INFO - __main__ - Step 12136: {'lr': 0.0004942368736570946, 'samples': 2330112, 'steps': 12135, 'loss/train': 1.532886028289795} 08/30/2021 15:19:02 - INFO - __main__ - Step 12137: {'lr': 0.0004942357407197491, 'samples': 2330304, 'steps': 12136, 'loss/train': 0.5886409282684326} 08/30/2021 15:19:02 - INFO - __main__ - Step 12138: {'lr': 0.0004942346076723548, 'samples': 2330496, 'steps': 12137, 'loss/train': 0.3196311593055725} 08/30/2021 15:19:04 - INFO - __main__ - Step 12139: {'lr': 0.0004942334745149122, 'samples': 2330688, 'steps': 12138, 'loss/train': 1.8268685340881348} 08/30/2021 15:19:04 - INFO - __main__ - Step 12140: {'lr': 0.0004942323412474218, 'samples': 2330880, 'steps': 12139, 'loss/train': 2.045480966567993} 08/30/2021 15:19:05 - INFO - __main__ - Step 12141: {'lr': 0.000494231207869884, 'samples': 2331072, 'steps': 12140, 'loss/train': 1.5094717741012573} 08/30/2021 15:19:05 - INFO - __main__ - Step 12142: {'lr': 0.0004942300743822993, 'samples': 2331264, 'steps': 12141, 'loss/train': 1.67244553565979} 08/30/2021 15:19:05 - INFO - __main__ - Step 12143: {'lr': 0.0004942289407846684, 'samples': 2331456, 'steps': 12142, 'loss/train': 1.5462299585342407} 08/30/2021 15:19:06 - INFO - __main__ - Step 12144: {'lr': 0.0004942278070769917, 'samples': 2331648, 'steps': 12143, 'loss/train': 0.135407492518425} 08/30/2021 15:19:08 - INFO - __main__ - Step 12145: {'lr': 0.0004942266732592697, 'samples': 2331840, 'steps': 12144, 'loss/train': 1.4855194091796875} 08/30/2021 15:19:08 - INFO - __main__ - Step 12146: {'lr': 0.0004942255393315029, 'samples': 2332032, 'steps': 12145, 'loss/train': 1.9162156581878662} 08/30/2021 15:19:09 - INFO - __main__ - Step 12147: {'lr': 0.000494224405293692, 'samples': 2332224, 'steps': 12146, 'loss/train': 1.5435060262680054} 08/30/2021 15:19:09 - INFO - __main__ - Step 12148: {'lr': 0.0004942232711458372, 'samples': 2332416, 'steps': 12147, 'loss/train': 0.9427946209907532} 08/30/2021 15:19:09 - INFO - __main__ - Step 12149: {'lr': 0.0004942221368879391, 'samples': 2332608, 'steps': 12148, 'loss/train': 1.492453694343567} 08/30/2021 15:19:11 - INFO - __main__ - Step 12150: {'lr': 0.0004942210025199985, 'samples': 2332800, 'steps': 12149, 'loss/train': 1.6069821119308472} 08/30/2021 15:19:11 - INFO - __main__ - Step 12151: {'lr': 0.0004942198680420155, 'samples': 2332992, 'steps': 12150, 'loss/train': 1.6264772415161133} 08/30/2021 15:19:12 - INFO - __main__ - Step 12152: {'lr': 0.0004942187334539908, 'samples': 2333184, 'steps': 12151, 'loss/train': 1.6122090816497803} 08/30/2021 15:19:12 - INFO - __main__ - Step 12153: {'lr': 0.0004942175987559251, 'samples': 2333376, 'steps': 12152, 'loss/train': 1.3487244844436646} 08/30/2021 15:19:12 - INFO - __main__ - Step 12154: {'lr': 0.0004942164639478185, 'samples': 2333568, 'steps': 12153, 'loss/train': 1.9462392330169678} 08/30/2021 15:19:14 - INFO - __main__ - Step 12155: {'lr': 0.0004942153290296718, 'samples': 2333760, 'steps': 12154, 'loss/train': 2.1020166873931885} 08/30/2021 15:19:14 - INFO - __main__ - Step 12156: {'lr': 0.0004942141940014854, 'samples': 2333952, 'steps': 12155, 'loss/train': 2.0489957332611084} 08/30/2021 15:19:15 - INFO - __main__ - Step 12157: {'lr': 0.0004942130588632599, 'samples': 2334144, 'steps': 12156, 'loss/train': 2.6077041625976562} 08/30/2021 15:19:15 - INFO - __main__ - Step 12158: {'lr': 0.0004942119236149958, 'samples': 2334336, 'steps': 12157, 'loss/train': 1.9298309087753296} 08/30/2021 15:19:15 - INFO - __main__ - Step 12159: {'lr': 0.0004942107882566936, 'samples': 2334528, 'steps': 12158, 'loss/train': 1.816013216972351} 08/30/2021 15:19:17 - INFO - __main__ - Step 12160: {'lr': 0.0004942096527883538, 'samples': 2334720, 'steps': 12159, 'loss/train': 1.7926967144012451} 08/30/2021 15:19:17 - INFO - __main__ - Step 12161: {'lr': 0.0004942085172099768, 'samples': 2334912, 'steps': 12160, 'loss/train': 1.8809715509414673} 08/30/2021 15:19:18 - INFO - __main__ - Step 12162: {'lr': 0.0004942073815215632, 'samples': 2335104, 'steps': 12161, 'loss/train': 2.161996364593506} 08/30/2021 15:19:18 - INFO - __main__ - Step 12163: {'lr': 0.0004942062457231136, 'samples': 2335296, 'steps': 12162, 'loss/train': 1.6908721923828125} 08/30/2021 15:19:18 - INFO - __main__ - Step 12164: {'lr': 0.0004942051098146284, 'samples': 2335488, 'steps': 12163, 'loss/train': 1.698455810546875} 08/30/2021 15:19:20 - INFO - __main__ - Step 12165: {'lr': 0.0004942039737961081, 'samples': 2335680, 'steps': 12164, 'loss/train': 1.7169294357299805} 08/30/2021 15:19:20 - INFO - __main__ - Step 12166: {'lr': 0.0004942028376675533, 'samples': 2335872, 'steps': 12165, 'loss/train': 1.8420363664627075} 08/30/2021 15:19:21 - INFO - __main__ - Step 12167: {'lr': 0.0004942017014289645, 'samples': 2336064, 'steps': 12166, 'loss/train': 2.1549808979034424} 08/30/2021 15:19:21 - INFO - __main__ - Step 12168: {'lr': 0.0004942005650803421, 'samples': 2336256, 'steps': 12167, 'loss/train': 1.9457118511199951} 08/30/2021 15:19:21 - INFO - __main__ - Step 12169: {'lr': 0.0004941994286216867, 'samples': 2336448, 'steps': 12168, 'loss/train': 1.997660756111145} 08/30/2021 15:19:23 - INFO - __main__ - Step 12170: {'lr': 0.0004941982920529989, 'samples': 2336640, 'steps': 12169, 'loss/train': 0.12547174096107483} 08/30/2021 15:19:23 - INFO - __main__ - Step 12171: {'lr': 0.0004941971553742791, 'samples': 2336832, 'steps': 12170, 'loss/train': 1.582919716835022} 08/30/2021 15:19:24 - INFO - __main__ - Step 12172: {'lr': 0.0004941960185855278, 'samples': 2337024, 'steps': 12171, 'loss/train': 1.3614516258239746} 08/30/2021 15:19:24 - INFO - __main__ - Step 12173: {'lr': 0.0004941948816867455, 'samples': 2337216, 'steps': 12172, 'loss/train': 1.503619909286499} 08/30/2021 15:19:24 - INFO - __main__ - Step 12174: {'lr': 0.0004941937446779328, 'samples': 2337408, 'steps': 12173, 'loss/train': 1.5388134717941284} 08/30/2021 15:19:26 - INFO - __main__ - Step 12175: {'lr': 0.0004941926075590901, 'samples': 2337600, 'steps': 12174, 'loss/train': 1.9619473218917847} 08/30/2021 15:19:26 - INFO - __main__ - Step 12176: {'lr': 0.0004941914703302181, 'samples': 2337792, 'steps': 12175, 'loss/train': 1.6383063793182373} 08/30/2021 15:19:27 - INFO - __main__ - Step 12177: {'lr': 0.0004941903329913172, 'samples': 2337984, 'steps': 12176, 'loss/train': 0.8161340355873108} 08/30/2021 15:19:27 - INFO - __main__ - Step 12178: {'lr': 0.0004941891955423878, 'samples': 2338176, 'steps': 12177, 'loss/train': 1.8237727880477905} 08/30/2021 15:19:27 - INFO - __main__ - Step 12179: {'lr': 0.0004941880579834306, 'samples': 2338368, 'steps': 12178, 'loss/train': 2.046415328979492} 08/30/2021 15:19:29 - INFO - __main__ - Step 12180: {'lr': 0.0004941869203144459, 'samples': 2338560, 'steps': 12179, 'loss/train': 1.5539066791534424} 08/30/2021 15:19:29 - INFO - __main__ - Step 12181: {'lr': 0.0004941857825354344, 'samples': 2338752, 'steps': 12180, 'loss/train': 2.091731071472168} 08/30/2021 15:19:30 - INFO - __main__ - Step 12182: {'lr': 0.0004941846446463966, 'samples': 2338944, 'steps': 12181, 'loss/train': 1.92172372341156} 08/30/2021 15:19:30 - INFO - __main__ - Step 12183: {'lr': 0.000494183506647333, 'samples': 2339136, 'steps': 12182, 'loss/train': 1.6249258518218994} 08/30/2021 15:19:30 - INFO - __main__ - Step 12184: {'lr': 0.000494182368538244, 'samples': 2339328, 'steps': 12183, 'loss/train': 1.3668913841247559} 08/30/2021 15:19:31 - INFO - __main__ - Step 12185: {'lr': 0.0004941812303191302, 'samples': 2339520, 'steps': 12184, 'loss/train': 1.7039155960083008} 08/30/2021 15:19:32 - INFO - __main__ - Step 12186: {'lr': 0.0004941800919899921, 'samples': 2339712, 'steps': 12185, 'loss/train': 1.3259013891220093} 08/30/2021 15:19:33 - INFO - __main__ - Step 12187: {'lr': 0.0004941789535508303, 'samples': 2339904, 'steps': 12186, 'loss/train': 1.8849434852600098} 08/30/2021 15:19:33 - INFO - __main__ - Step 12188: {'lr': 0.0004941778150016451, 'samples': 2340096, 'steps': 12187, 'loss/train': 1.3777295351028442} 08/30/2021 15:19:33 - INFO - __main__ - Step 12189: {'lr': 0.0004941766763424373, 'samples': 2340288, 'steps': 12188, 'loss/train': 1.2483760118484497} 08/30/2021 15:19:34 - INFO - __main__ - Step 12190: {'lr': 0.0004941755375732071, 'samples': 2340480, 'steps': 12189, 'loss/train': 2.1583364009857178} 08/30/2021 15:19:35 - INFO - __main__ - Step 12191: {'lr': 0.0004941743986939553, 'samples': 2340672, 'steps': 12190, 'loss/train': 1.2722080945968628} 08/30/2021 15:19:36 - INFO - __main__ - Step 12192: {'lr': 0.0004941732597046822, 'samples': 2340864, 'steps': 12191, 'loss/train': 1.8975012302398682} 08/30/2021 15:19:36 - INFO - __main__ - Step 12193: {'lr': 0.0004941721206053885, 'samples': 2341056, 'steps': 12192, 'loss/train': 1.4381009340286255} 08/30/2021 15:19:36 - INFO - __main__ - Step 12194: {'lr': 0.0004941709813960745, 'samples': 2341248, 'steps': 12193, 'loss/train': 1.772352933883667} 08/30/2021 15:19:37 - INFO - __main__ - Step 12195: {'lr': 0.0004941698420767408, 'samples': 2341440, 'steps': 12194, 'loss/train': 1.7654757499694824} 08/30/2021 15:19:39 - INFO - __main__ - Step 12196: {'lr': 0.0004941687026473881, 'samples': 2341632, 'steps': 12195, 'loss/train': 1.6286343336105347} 08/30/2021 15:19:39 - INFO - __main__ - Step 12197: {'lr': 0.0004941675631080166, 'samples': 2341824, 'steps': 12196, 'loss/train': 2.1513400077819824} 08/30/2021 15:19:40 - INFO - __main__ - Step 12198: {'lr': 0.000494166423458627, 'samples': 2342016, 'steps': 12197, 'loss/train': 0.1918555647134781} 08/30/2021 15:19:40 - INFO - __main__ - Step 12199: {'lr': 0.0004941652836992198, 'samples': 2342208, 'steps': 12198, 'loss/train': 2.00239634513855} 08/30/2021 15:19:40 - INFO - __main__ - Step 12200: {'lr': 0.0004941641438297955, 'samples': 2342400, 'steps': 12199, 'loss/train': 2.297025203704834} 08/30/2021 15:19:42 - INFO - __main__ - Step 12201: {'lr': 0.0004941630038503545, 'samples': 2342592, 'steps': 12200, 'loss/train': 1.8913379907608032} 08/30/2021 15:19:42 - INFO - __main__ - Step 12202: {'lr': 0.0004941618637608976, 'samples': 2342784, 'steps': 12201, 'loss/train': 1.133849024772644} 08/30/2021 15:19:43 - INFO - __main__ - Step 12203: {'lr': 0.000494160723561425, 'samples': 2342976, 'steps': 12202, 'loss/train': 1.7795054912567139} 08/30/2021 15:19:43 - INFO - __main__ - Step 12204: {'lr': 0.0004941595832519374, 'samples': 2343168, 'steps': 12203, 'loss/train': 1.6500552892684937} 08/30/2021 15:19:43 - INFO - __main__ - Step 12205: {'lr': 0.0004941584428324352, 'samples': 2343360, 'steps': 12204, 'loss/train': 1.7131215333938599} 08/30/2021 15:19:45 - INFO - __main__ - Step 12206: {'lr': 0.000494157302302919, 'samples': 2343552, 'steps': 12205, 'loss/train': 1.3454593420028687} 08/30/2021 15:19:46 - INFO - __main__ - Step 12207: {'lr': 0.0004941561616633893, 'samples': 2343744, 'steps': 12206, 'loss/train': 2.19356632232666} 08/30/2021 15:19:46 - INFO - __main__ - Step 12208: {'lr': 0.0004941550209138466, 'samples': 2343936, 'steps': 12207, 'loss/train': 1.1932798624038696} 08/30/2021 15:19:46 - INFO - __main__ - Step 12209: {'lr': 0.0004941538800542915, 'samples': 2344128, 'steps': 12208, 'loss/train': 1.4473735094070435} 08/30/2021 15:19:47 - INFO - __main__ - Step 12210: {'lr': 0.0004941527390847243, 'samples': 2344320, 'steps': 12209, 'loss/train': 1.747239589691162} 08/30/2021 15:19:47 - INFO - __main__ - Step 12211: {'lr': 0.0004941515980051457, 'samples': 2344512, 'steps': 12210, 'loss/train': 1.310584545135498} 08/30/2021 15:19:48 - INFO - __main__ - Step 12212: {'lr': 0.0004941504568155561, 'samples': 2344704, 'steps': 12211, 'loss/train': 2.0716114044189453} 08/30/2021 15:19:49 - INFO - __main__ - Step 12213: {'lr': 0.0004941493155159562, 'samples': 2344896, 'steps': 12212, 'loss/train': 1.9429436922073364} 08/30/2021 15:19:49 - INFO - __main__ - Step 12214: {'lr': 0.0004941481741063462, 'samples': 2345088, 'steps': 12213, 'loss/train': 1.6388980150222778} 08/30/2021 15:19:50 - INFO - __main__ - Step 12215: {'lr': 0.000494147032586727, 'samples': 2345280, 'steps': 12214, 'loss/train': 1.7224280834197998} 08/30/2021 15:19:50 - INFO - __main__ - Step 12216: {'lr': 0.0004941458909570988, 'samples': 2345472, 'steps': 12215, 'loss/train': 1.334747314453125} 08/30/2021 15:19:52 - INFO - __main__ - Step 12217: {'lr': 0.0004941447492174622, 'samples': 2345664, 'steps': 12216, 'loss/train': 1.5395238399505615} 08/30/2021 15:19:52 - INFO - __main__ - Step 12218: {'lr': 0.0004941436073678179, 'samples': 2345856, 'steps': 12217, 'loss/train': 1.8215900659561157} 08/30/2021 15:19:52 - INFO - __main__ - Step 12219: {'lr': 0.0004941424654081661, 'samples': 2346048, 'steps': 12218, 'loss/train': 1.6174993515014648} 08/30/2021 15:19:53 - INFO - __main__ - Step 12220: {'lr': 0.0004941413233385075, 'samples': 2346240, 'steps': 12219, 'loss/train': 1.6133155822753906} 08/30/2021 15:19:53 - INFO - __main__ - Step 12221: {'lr': 0.0004941401811588426, 'samples': 2346432, 'steps': 12220, 'loss/train': 1.8205928802490234} 08/30/2021 15:19:55 - INFO - __main__ - Step 12222: {'lr': 0.0004941390388691719, 'samples': 2346624, 'steps': 12221, 'loss/train': 1.6221952438354492} 08/30/2021 15:19:55 - INFO - __main__ - Step 12223: {'lr': 0.0004941378964694959, 'samples': 2346816, 'steps': 12222, 'loss/train': 0.200674906373024} 08/30/2021 15:19:55 - INFO - __main__ - Step 12224: {'lr': 0.0004941367539598152, 'samples': 2347008, 'steps': 12223, 'loss/train': 1.7082698345184326} 08/30/2021 15:19:56 - INFO - __main__ - Step 12225: {'lr': 0.0004941356113401301, 'samples': 2347200, 'steps': 12224, 'loss/train': 2.0742337703704834} 08/30/2021 15:19:56 - INFO - __main__ - Step 12226: {'lr': 0.0004941344686104414, 'samples': 2347392, 'steps': 12225, 'loss/train': 2.614518165588379} 08/30/2021 15:19:57 - INFO - __main__ - Step 12227: {'lr': 0.0004941333257707495, 'samples': 2347584, 'steps': 12226, 'loss/train': 1.2951313257217407} 08/30/2021 15:19:58 - INFO - __main__ - Step 12228: {'lr': 0.0004941321828210548, 'samples': 2347776, 'steps': 12227, 'loss/train': 2.0186338424682617} 08/30/2021 15:19:58 - INFO - __main__ - Step 12229: {'lr': 0.000494131039761358, 'samples': 2347968, 'steps': 12228, 'loss/train': 1.534130334854126} 08/30/2021 15:19:59 - INFO - __main__ - Step 12230: {'lr': 0.0004941298965916594, 'samples': 2348160, 'steps': 12229, 'loss/train': 1.3590337038040161} 08/30/2021 15:19:59 - INFO - __main__ - Step 12231: {'lr': 0.0004941287533119597, 'samples': 2348352, 'steps': 12230, 'loss/train': 1.7603479623794556} 08/30/2021 15:20:01 - INFO - __main__ - Step 12232: {'lr': 0.0004941276099222593, 'samples': 2348544, 'steps': 12231, 'loss/train': 1.6896908283233643} 08/30/2021 15:20:01 - INFO - __main__ - Step 12233: {'lr': 0.0004941264664225589, 'samples': 2348736, 'steps': 12232, 'loss/train': 1.9289885759353638} 08/30/2021 15:20:01 - INFO - __main__ - Step 12234: {'lr': 0.0004941253228128588, 'samples': 2348928, 'steps': 12233, 'loss/train': 1.995834231376648} 08/30/2021 15:20:02 - INFO - __main__ - Step 12235: {'lr': 0.0004941241790931595, 'samples': 2349120, 'steps': 12234, 'loss/train': 2.0375280380249023} 08/30/2021 15:20:02 - INFO - __main__ - Step 12236: {'lr': 0.0004941230352634617, 'samples': 2349312, 'steps': 12235, 'loss/train': 1.4215041399002075} 08/30/2021 15:20:03 - INFO - __main__ - Step 12237: {'lr': 0.0004941218913237658, 'samples': 2349504, 'steps': 12236, 'loss/train': 1.9986791610717773} 08/30/2021 15:20:04 - INFO - __main__ - Step 12238: {'lr': 0.0004941207472740724, 'samples': 2349696, 'steps': 12237, 'loss/train': 1.5555988550186157} 08/30/2021 15:20:04 - INFO - __main__ - Step 12239: {'lr': 0.000494119603114382, 'samples': 2349888, 'steps': 12238, 'loss/train': 1.4673455953598022} 08/30/2021 15:20:05 - INFO - __main__ - Step 12240: {'lr': 0.000494118458844695, 'samples': 2350080, 'steps': 12239, 'loss/train': 1.7984997034072876} 08/30/2021 15:20:05 - INFO - __main__ - Step 12241: {'lr': 0.0004941173144650119, 'samples': 2350272, 'steps': 12240, 'loss/train': 1.2752575874328613} 08/30/2021 15:20:06 - INFO - __main__ - Step 12242: {'lr': 0.0004941161699753335, 'samples': 2350464, 'steps': 12241, 'loss/train': 0.7331043481826782} 08/30/2021 15:20:07 - INFO - __main__ - Step 12243: {'lr': 0.00049411502537566, 'samples': 2350656, 'steps': 12242, 'loss/train': 1.6997778415679932} 08/30/2021 15:20:07 - INFO - __main__ - Step 12244: {'lr': 0.0004941138806659921, 'samples': 2350848, 'steps': 12243, 'loss/train': 1.990111231803894} 08/30/2021 15:20:08 - INFO - __main__ - Step 12245: {'lr': 0.00049411273584633, 'samples': 2351040, 'steps': 12244, 'loss/train': 0.49503204226493835} 08/30/2021 15:20:08 - INFO - __main__ - Step 12246: {'lr': 0.0004941115909166748, 'samples': 2351232, 'steps': 12245, 'loss/train': 3.0827579498291016} 08/30/2021 15:20:08 - INFO - __main__ - Step 12247: {'lr': 0.0004941104458770266, 'samples': 2351424, 'steps': 12246, 'loss/train': 2.4586760997772217} 08/30/2021 15:20:10 - INFO - __main__ - Step 12248: {'lr': 0.0004941093007273859, 'samples': 2351616, 'steps': 12247, 'loss/train': 1.9005318880081177} 08/30/2021 15:20:10 - INFO - __main__ - Step 12249: {'lr': 0.0004941081554677534, 'samples': 2351808, 'steps': 12248, 'loss/train': 2.209047317504883} 08/30/2021 15:20:11 - INFO - __main__ - Step 12250: {'lr': 0.0004941070100981295, 'samples': 2352000, 'steps': 12249, 'loss/train': 1.7038828134536743} 08/30/2021 15:20:11 - INFO - __main__ - Step 12251: {'lr': 0.0004941058646185148, 'samples': 2352192, 'steps': 12250, 'loss/train': 1.8614627122879028} 08/30/2021 15:20:12 - INFO - __main__ - Step 12252: {'lr': 0.0004941047190289096, 'samples': 2352384, 'steps': 12251, 'loss/train': 1.5548309087753296} 08/30/2021 15:20:13 - INFO - __main__ - Step 12253: {'lr': 0.0004941035733293148, 'samples': 2352576, 'steps': 12252, 'loss/train': 1.694841980934143} 08/30/2021 15:20:14 - INFO - __main__ - Step 12254: {'lr': 0.0004941024275197305, 'samples': 2352768, 'steps': 12253, 'loss/train': 1.6687698364257812} 08/30/2021 15:20:15 - INFO - __main__ - Step 12255: {'lr': 0.0004941012816001575, 'samples': 2352960, 'steps': 12254, 'loss/train': 1.4105418920516968} 08/30/2021 15:20:15 - INFO - __main__ - Step 12256: {'lr': 0.0004941001355705963, 'samples': 2353152, 'steps': 12255, 'loss/train': 1.5553321838378906} 08/30/2021 15:20:15 - INFO - __main__ - Step 12257: {'lr': 0.0004940989894310473, 'samples': 2353344, 'steps': 12256, 'loss/train': 1.8310878276824951} 08/30/2021 15:20:17 - INFO - __main__ - Step 12258: {'lr': 0.000494097843181511, 'samples': 2353536, 'steps': 12257, 'loss/train': 2.332899570465088} 08/30/2021 15:20:17 - INFO - __main__ - Step 12259: {'lr': 0.0004940966968219881, 'samples': 2353728, 'steps': 12258, 'loss/train': 2.1879830360412598} 08/30/2021 15:20:18 - INFO - __main__ - Step 12260: {'lr': 0.0004940955503524789, 'samples': 2353920, 'steps': 12259, 'loss/train': 0.9828661680221558} 08/30/2021 15:20:18 - INFO - __main__ - Step 12261: {'lr': 0.000494094403772984, 'samples': 2354112, 'steps': 12260, 'loss/train': 1.3328101634979248} 08/30/2021 15:20:18 - INFO - __main__ - Step 12262: {'lr': 0.0004940932570835039, 'samples': 2354304, 'steps': 12261, 'loss/train': 0.5736973881721497} 08/30/2021 15:20:19 - INFO - __main__ - Step 12263: {'lr': 0.0004940921102840393, 'samples': 2354496, 'steps': 12262, 'loss/train': 1.9213297367095947} 08/30/2021 15:20:20 - INFO - __main__ - Step 12264: {'lr': 0.0004940909633745905, 'samples': 2354688, 'steps': 12263, 'loss/train': 0.4872017204761505} 08/30/2021 15:20:21 - INFO - __main__ - Step 12265: {'lr': 0.000494089816355158, 'samples': 2354880, 'steps': 12264, 'loss/train': 1.5357216596603394} 08/30/2021 15:20:21 - INFO - __main__ - Step 12266: {'lr': 0.0004940886692257424, 'samples': 2355072, 'steps': 12265, 'loss/train': 1.768714427947998} 08/30/2021 15:20:21 - INFO - __main__ - Step 12267: {'lr': 0.0004940875219863443, 'samples': 2355264, 'steps': 12266, 'loss/train': 1.309556007385254} 08/30/2021 15:20:22 - INFO - __main__ - Step 12268: {'lr': 0.0004940863746369641, 'samples': 2355456, 'steps': 12267, 'loss/train': 1.784734845161438} 08/30/2021 15:20:24 - INFO - __main__ - Step 12269: {'lr': 0.0004940852271776023, 'samples': 2355648, 'steps': 12268, 'loss/train': 1.2673885822296143} 08/30/2021 15:20:24 - INFO - __main__ - Step 12270: {'lr': 0.0004940840796082594, 'samples': 2355840, 'steps': 12269, 'loss/train': 1.6234240531921387} 08/30/2021 15:20:24 - INFO - __main__ - Step 12271: {'lr': 0.0004940829319289361, 'samples': 2356032, 'steps': 12270, 'loss/train': 1.8377019166946411} 08/30/2021 15:20:25 - INFO - __main__ - Step 12272: {'lr': 0.0004940817841396327, 'samples': 2356224, 'steps': 12271, 'loss/train': 1.2662084102630615} 08/30/2021 15:20:25 - INFO - __main__ - Step 12273: {'lr': 0.0004940806362403499, 'samples': 2356416, 'steps': 12272, 'loss/train': 1.339592695236206} 08/30/2021 15:20:25 - INFO - __main__ - Step 12274: {'lr': 0.0004940794882310882, 'samples': 2356608, 'steps': 12273, 'loss/train': 1.7002252340316772} 08/30/2021 15:20:26 - INFO - __main__ - Step 12275: {'lr': 0.000494078340111848, 'samples': 2356800, 'steps': 12274, 'loss/train': 2.020940065383911} 08/30/2021 15:20:27 - INFO - __main__ - Step 12276: {'lr': 0.0004940771918826298, 'samples': 2356992, 'steps': 12275, 'loss/train': 1.9736751317977905} 08/30/2021 15:20:28 - INFO - __main__ - Step 12277: {'lr': 0.0004940760435434341, 'samples': 2357184, 'steps': 12276, 'loss/train': 1.4225600957870483} 08/30/2021 15:20:28 - INFO - __main__ - Step 12278: {'lr': 0.0004940748950942618, 'samples': 2357376, 'steps': 12277, 'loss/train': 1.7238681316375732} 08/30/2021 15:20:29 - INFO - __main__ - Step 12279: {'lr': 0.0004940737465351128, 'samples': 2357568, 'steps': 12278, 'loss/train': 1.6024529933929443} 08/30/2021 15:20:29 - INFO - __main__ - Step 12280: {'lr': 0.0004940725978659881, 'samples': 2357760, 'steps': 12279, 'loss/train': 1.577825903892517} 08/30/2021 15:20:31 - INFO - __main__ - Step 12281: {'lr': 0.000494071449086888, 'samples': 2357952, 'steps': 12280, 'loss/train': 2.065798282623291} 08/30/2021 15:20:31 - INFO - __main__ - Step 12282: {'lr': 0.0004940703001978131, 'samples': 2358144, 'steps': 12281, 'loss/train': 1.089477777481079} 08/30/2021 15:20:31 - INFO - __main__ - Step 12283: {'lr': 0.0004940691511987639, 'samples': 2358336, 'steps': 12282, 'loss/train': 1.8239578008651733} 08/30/2021 15:20:32 - INFO - __main__ - Step 12284: {'lr': 0.0004940680020897409, 'samples': 2358528, 'steps': 12283, 'loss/train': 1.7185299396514893} 08/30/2021 15:20:32 - INFO - __main__ - Step 12285: {'lr': 0.0004940668528707446, 'samples': 2358720, 'steps': 12284, 'loss/train': 1.0978227853775024} 08/30/2021 15:20:32 - INFO - __main__ - Step 12286: {'lr': 0.0004940657035417755, 'samples': 2358912, 'steps': 12285, 'loss/train': 2.4013559818267822} 08/30/2021 15:20:34 - INFO - __main__ - Step 12287: {'lr': 0.0004940645541028343, 'samples': 2359104, 'steps': 12286, 'loss/train': 1.9952807426452637} 08/30/2021 15:20:34 - INFO - __main__ - Step 12288: {'lr': 0.0004940634045539213, 'samples': 2359296, 'steps': 12287, 'loss/train': 1.9006563425064087} 08/30/2021 15:20:35 - INFO - __main__ - Step 12289: {'lr': 0.000494062254895037, 'samples': 2359488, 'steps': 12288, 'loss/train': 1.5698041915893555} 08/30/2021 15:20:35 - INFO - __main__ - Step 12290: {'lr': 0.0004940611051261822, 'samples': 2359680, 'steps': 12289, 'loss/train': 1.6416971683502197} 08/30/2021 15:20:35 - INFO - __main__ - Step 12291: {'lr': 0.000494059955247357, 'samples': 2359872, 'steps': 12290, 'loss/train': 1.372291088104248} 08/30/2021 15:20:37 - INFO - __main__ - Step 12292: {'lr': 0.0004940588052585624, 'samples': 2360064, 'steps': 12291, 'loss/train': 1.3547165393829346} 08/30/2021 15:20:37 - INFO - __main__ - Step 12293: {'lr': 0.0004940576551597985, 'samples': 2360256, 'steps': 12292, 'loss/train': 2.036637544631958} 08/30/2021 15:20:38 - INFO - __main__ - Step 12294: {'lr': 0.000494056504951066, 'samples': 2360448, 'steps': 12293, 'loss/train': 1.5060285329818726} 08/30/2021 15:20:38 - INFO - __main__ - Step 12295: {'lr': 0.0004940553546323655, 'samples': 2360640, 'steps': 12294, 'loss/train': 1.766244888305664} 08/30/2021 15:20:38 - INFO - __main__ - Step 12296: {'lr': 0.0004940542042036974, 'samples': 2360832, 'steps': 12295, 'loss/train': 1.63885498046875} 08/30/2021 15:20:40 - INFO - __main__ - Step 12297: {'lr': 0.0004940530536650621, 'samples': 2361024, 'steps': 12296, 'loss/train': 1.6277042627334595} 08/30/2021 15:20:40 - INFO - __main__ - Step 12298: {'lr': 0.0004940519030164605, 'samples': 2361216, 'steps': 12297, 'loss/train': 1.5816974639892578} 08/30/2021 15:20:41 - INFO - __main__ - Step 12299: {'lr': 0.0004940507522578927, 'samples': 2361408, 'steps': 12298, 'loss/train': 1.8461530208587646} 08/30/2021 15:20:41 - INFO - __main__ - Step 12300: {'lr': 0.0004940496013893594, 'samples': 2361600, 'steps': 12299, 'loss/train': 2.1077511310577393} 08/30/2021 15:20:41 - INFO - __main__ - Step 12301: {'lr': 0.0004940484504108612, 'samples': 2361792, 'steps': 12300, 'loss/train': 1.92961585521698} 08/30/2021 15:20:43 - INFO - __main__ - Step 12302: {'lr': 0.0004940472993223985, 'samples': 2361984, 'steps': 12301, 'loss/train': 1.577030897140503} 08/30/2021 15:20:44 - INFO - __main__ - Step 12303: {'lr': 0.0004940461481239719, 'samples': 2362176, 'steps': 12302, 'loss/train': 1.322467565536499} 08/30/2021 15:20:44 - INFO - __main__ - Step 12304: {'lr': 0.0004940449968155818, 'samples': 2362368, 'steps': 12303, 'loss/train': 2.117222547531128} 08/30/2021 15:20:44 - INFO - __main__ - Step 12305: {'lr': 0.0004940438453972288, 'samples': 2362560, 'steps': 12304, 'loss/train': 1.5622693300247192} 08/30/2021 15:20:45 - INFO - __main__ - Step 12306: {'lr': 0.0004940426938689135, 'samples': 2362752, 'steps': 12305, 'loss/train': 1.739802598953247} 08/30/2021 15:20:47 - INFO - __main__ - Step 12307: {'lr': 0.0004940415422306361, 'samples': 2362944, 'steps': 12306, 'loss/train': 1.2217721939086914} 08/30/2021 15:20:47 - INFO - __main__ - Step 12308: {'lr': 0.0004940403904823976, 'samples': 2363136, 'steps': 12307, 'loss/train': 1.8506790399551392} 08/30/2021 15:20:48 - INFO - __main__ - Step 12309: {'lr': 0.0004940392386241981, 'samples': 2363328, 'steps': 12308, 'loss/train': 2.1373562812805176} 08/30/2021 15:20:48 - INFO - __main__ - Step 12310: {'lr': 0.0004940380866560384, 'samples': 2363520, 'steps': 12309, 'loss/train': 1.64629328250885} 08/30/2021 15:20:48 - INFO - __main__ - Step 12311: {'lr': 0.0004940369345779187, 'samples': 2363712, 'steps': 12310, 'loss/train': 1.8088691234588623} 08/30/2021 15:20:50 - INFO - __main__ - Step 12312: {'lr': 0.00049403578238984, 'samples': 2363904, 'steps': 12311, 'loss/train': 1.6565057039260864} 08/30/2021 15:20:50 - INFO - __main__ - Step 12313: {'lr': 0.0004940346300918024, 'samples': 2364096, 'steps': 12312, 'loss/train': 2.030160903930664} 08/30/2021 15:20:51 - INFO - __main__ - Step 12314: {'lr': 0.0004940334776838065, 'samples': 2364288, 'steps': 12313, 'loss/train': 1.8640719652175903} 08/30/2021 15:20:51 - INFO - __main__ - Step 12315: {'lr': 0.000494032325165853, 'samples': 2364480, 'steps': 12314, 'loss/train': 2.038550615310669} 08/30/2021 15:20:51 - INFO - __main__ - Step 12316: {'lr': 0.0004940311725379423, 'samples': 2364672, 'steps': 12315, 'loss/train': 1.426437497138977} 08/30/2021 15:20:52 - INFO - __main__ - Step 12317: {'lr': 0.0004940300198000748, 'samples': 2364864, 'steps': 12316, 'loss/train': 1.886391282081604} 08/30/2021 15:20:53 - INFO - __main__ - Step 12318: {'lr': 0.0004940288669522513, 'samples': 2365056, 'steps': 12317, 'loss/train': 2.6517083644866943} 08/30/2021 15:20:54 - INFO - __main__ - Step 12319: {'lr': 0.000494027713994472, 'samples': 2365248, 'steps': 12318, 'loss/train': 1.4126795530319214} 08/30/2021 15:20:54 - INFO - __main__ - Step 12320: {'lr': 0.0004940265609267377, 'samples': 2365440, 'steps': 12319, 'loss/train': 1.5219357013702393} 08/30/2021 15:20:54 - INFO - __main__ - Step 12321: {'lr': 0.0004940254077490487, 'samples': 2365632, 'steps': 12320, 'loss/train': 1.2527730464935303} 08/30/2021 15:20:55 - INFO - __main__ - Step 12322: {'lr': 0.0004940242544614056, 'samples': 2365824, 'steps': 12321, 'loss/train': 2.077793836593628} 08/30/2021 15:20:56 - INFO - __main__ - Step 12323: {'lr': 0.0004940231010638091, 'samples': 2366016, 'steps': 12322, 'loss/train': 1.6778231859207153} 08/30/2021 15:20:57 - INFO - __main__ - Step 12324: {'lr': 0.0004940219475562593, 'samples': 2366208, 'steps': 12323, 'loss/train': 1.868173599243164} 08/30/2021 15:20:57 - INFO - __main__ - Step 12325: {'lr': 0.0004940207939387573, 'samples': 2366400, 'steps': 12324, 'loss/train': 2.4082648754119873} 08/30/2021 15:20:57 - INFO - __main__ - Step 12326: {'lr': 0.0004940196402113031, 'samples': 2366592, 'steps': 12325, 'loss/train': 1.8570210933685303} 08/30/2021 15:20:58 - INFO - __main__ - Step 12327: {'lr': 0.0004940184863738975, 'samples': 2366784, 'steps': 12326, 'loss/train': 2.2421019077301025} 08/30/2021 15:20:59 - INFO - __main__ - Step 12328: {'lr': 0.0004940173324265407, 'samples': 2366976, 'steps': 12327, 'loss/train': 2.0102992057800293} 08/30/2021 15:21:00 - INFO - __main__ - Step 12329: {'lr': 0.0004940161783692338, 'samples': 2367168, 'steps': 12328, 'loss/train': 1.3427133560180664} 08/30/2021 15:21:00 - INFO - __main__ - Step 12330: {'lr': 0.0004940150242019768, 'samples': 2367360, 'steps': 12329, 'loss/train': 1.481920838356018} 08/30/2021 15:21:01 - INFO - __main__ - Step 12331: {'lr': 0.0004940138699247704, 'samples': 2367552, 'steps': 12330, 'loss/train': 2.420530319213867} 08/30/2021 15:21:01 - INFO - __main__ - Step 12332: {'lr': 0.0004940127155376151, 'samples': 2367744, 'steps': 12331, 'loss/train': 1.4439826011657715} 08/30/2021 15:21:02 - INFO - __main__ - Step 12333: {'lr': 0.0004940115610405114, 'samples': 2367936, 'steps': 12332, 'loss/train': 1.0832420587539673} 08/30/2021 15:21:03 - INFO - __main__ - Step 12334: {'lr': 0.0004940104064334599, 'samples': 2368128, 'steps': 12333, 'loss/train': 1.490478277206421} 08/30/2021 15:21:03 - INFO - __main__ - Step 12335: {'lr': 0.0004940092517164612, 'samples': 2368320, 'steps': 12334, 'loss/train': 1.9114985466003418} 08/30/2021 15:21:04 - INFO - __main__ - Step 12336: {'lr': 0.0004940080968895155, 'samples': 2368512, 'steps': 12335, 'loss/train': 1.3063796758651733} 08/30/2021 15:21:04 - INFO - __main__ - Step 12337: {'lr': 0.0004940069419526236, 'samples': 2368704, 'steps': 12336, 'loss/train': 1.779631495475769} 08/30/2021 15:21:04 - INFO - __main__ - Step 12338: {'lr': 0.0004940057869057859, 'samples': 2368896, 'steps': 12337, 'loss/train': 2.4336724281311035} 08/30/2021 15:21:06 - INFO - __main__ - Step 12339: {'lr': 0.000494004631749003, 'samples': 2369088, 'steps': 12338, 'loss/train': 2.139826774597168} 08/30/2021 15:21:06 - INFO - __main__ - Step 12340: {'lr': 0.0004940034764822754, 'samples': 2369280, 'steps': 12339, 'loss/train': 1.249495029449463} 08/30/2021 15:21:07 - INFO - __main__ - Step 12341: {'lr': 0.0004940023211056036, 'samples': 2369472, 'steps': 12340, 'loss/train': 1.9051568508148193} 08/30/2021 15:21:07 - INFO - __main__ - Step 12342: {'lr': 0.0004940011656189881, 'samples': 2369664, 'steps': 12341, 'loss/train': 1.901642084121704} 08/30/2021 15:21:07 - INFO - __main__ - Step 12343: {'lr': 0.0004940000100224295, 'samples': 2369856, 'steps': 12342, 'loss/train': 1.8271327018737793} 08/30/2021 15:21:09 - INFO - __main__ - Step 12344: {'lr': 0.0004939988543159282, 'samples': 2370048, 'steps': 12343, 'loss/train': 2.083096742630005} 08/30/2021 15:21:10 - INFO - __main__ - Step 12345: {'lr': 0.0004939976984994847, 'samples': 2370240, 'steps': 12344, 'loss/train': 0.5472157001495361} 08/30/2021 15:21:10 - INFO - __main__ - Step 12346: {'lr': 0.0004939965425730996, 'samples': 2370432, 'steps': 12345, 'loss/train': 1.6035313606262207} 08/30/2021 15:21:10 - INFO - __main__ - Step 12347: {'lr': 0.0004939953865367735, 'samples': 2370624, 'steps': 12346, 'loss/train': 1.7876683473587036} 08/30/2021 15:21:11 - INFO - __main__ - Step 12348: {'lr': 0.0004939942303905069, 'samples': 2370816, 'steps': 12347, 'loss/train': 1.195544719696045} 08/30/2021 15:21:11 - INFO - __main__ - Step 12349: {'lr': 0.0004939930741343002, 'samples': 2371008, 'steps': 12348, 'loss/train': 1.6651946306228638} 08/30/2021 15:21:13 - INFO - __main__ - Step 12350: {'lr': 0.000493991917768154, 'samples': 2371200, 'steps': 12349, 'loss/train': 1.0392279624938965} 08/30/2021 15:21:13 - INFO - __main__ - Step 12351: {'lr': 0.0004939907612920688, 'samples': 2371392, 'steps': 12350, 'loss/train': 1.6462291479110718} 08/30/2021 15:21:13 - INFO - __main__ - Step 12352: {'lr': 0.0004939896047060451, 'samples': 2371584, 'steps': 12351, 'loss/train': 1.5832334756851196} 08/30/2021 15:21:14 - INFO - __main__ - Step 12353: {'lr': 0.0004939884480100836, 'samples': 2371776, 'steps': 12352, 'loss/train': 1.5563801527023315} 08/30/2021 15:21:14 - INFO - __main__ - Step 12354: {'lr': 0.0004939872912041844, 'samples': 2371968, 'steps': 12353, 'loss/train': 1.5932083129882812} 08/30/2021 15:21:16 - INFO - __main__ - Step 12355: {'lr': 0.0004939861342883485, 'samples': 2372160, 'steps': 12354, 'loss/train': 1.953323245048523} 08/30/2021 15:21:16 - INFO - __main__ - Step 12356: {'lr': 0.0004939849772625761, 'samples': 2372352, 'steps': 12355, 'loss/train': 1.797263503074646} 08/30/2021 15:21:17 - INFO - __main__ - Step 12357: {'lr': 0.0004939838201268679, 'samples': 2372544, 'steps': 12356, 'loss/train': 1.5991339683532715} 08/30/2021 15:21:17 - INFO - __main__ - Step 12358: {'lr': 0.0004939826628812244, 'samples': 2372736, 'steps': 12357, 'loss/train': 1.9488673210144043} 08/30/2021 15:21:17 - INFO - __main__ - Step 12359: {'lr': 0.000493981505525646, 'samples': 2372928, 'steps': 12358, 'loss/train': 1.513182282447815} 08/30/2021 15:21:18 - INFO - __main__ - Step 12360: {'lr': 0.0004939803480601333, 'samples': 2373120, 'steps': 12359, 'loss/train': 2.8466885089874268} 08/30/2021 15:21:20 - INFO - __main__ - Step 12361: {'lr': 0.0004939791904846869, 'samples': 2373312, 'steps': 12360, 'loss/train': 1.4838905334472656} 08/30/2021 15:21:20 - INFO - __main__ - Step 12362: {'lr': 0.0004939780327993072, 'samples': 2373504, 'steps': 12361, 'loss/train': 1.9791806936264038} 08/30/2021 15:21:21 - INFO - __main__ - Step 12363: {'lr': 0.0004939768750039946, 'samples': 2373696, 'steps': 12362, 'loss/train': 1.3516241312026978} 08/30/2021 15:21:21 - INFO - __main__ - Step 12364: {'lr': 0.00049397571709875, 'samples': 2373888, 'steps': 12363, 'loss/train': 1.4593547582626343} 08/30/2021 15:21:21 - INFO - __main__ - Step 12365: {'lr': 0.0004939745590835736, 'samples': 2374080, 'steps': 12364, 'loss/train': 1.6037418842315674} 08/30/2021 15:21:23 - INFO - __main__ - Step 12366: {'lr': 0.0004939734009584661, 'samples': 2374272, 'steps': 12365, 'loss/train': 1.8691282272338867} 08/30/2021 15:21:23 - INFO - __main__ - Step 12367: {'lr': 0.0004939722427234279, 'samples': 2374464, 'steps': 12366, 'loss/train': 1.6306006908416748} 08/30/2021 15:21:24 - INFO - __main__ - Step 12368: {'lr': 0.0004939710843784596, 'samples': 2374656, 'steps': 12367, 'loss/train': 2.2240822315216064} 08/30/2021 15:21:24 - INFO - __main__ - Step 12369: {'lr': 0.0004939699259235617, 'samples': 2374848, 'steps': 12368, 'loss/train': 1.5180351734161377} 08/30/2021 15:21:24 - INFO - __main__ - Step 12370: {'lr': 0.0004939687673587346, 'samples': 2375040, 'steps': 12369, 'loss/train': 1.2453733682632446} 08/30/2021 15:21:26 - INFO - __main__ - Step 12371: {'lr': 0.0004939676086839791, 'samples': 2375232, 'steps': 12370, 'loss/train': 1.4904848337173462} 08/30/2021 15:21:26 - INFO - __main__ - Step 12372: {'lr': 0.0004939664498992955, 'samples': 2375424, 'steps': 12371, 'loss/train': 1.5308938026428223} 08/30/2021 15:21:27 - INFO - __main__ - Step 12373: {'lr': 0.0004939652910046844, 'samples': 2375616, 'steps': 12372, 'loss/train': 1.7801154851913452} 08/30/2021 15:21:27 - INFO - __main__ - Step 12374: {'lr': 0.0004939641320001462, 'samples': 2375808, 'steps': 12373, 'loss/train': 1.9854333400726318} 08/30/2021 15:21:27 - INFO - __main__ - Step 12375: {'lr': 0.0004939629728856817, 'samples': 2376000, 'steps': 12374, 'loss/train': 1.6718435287475586} 08/30/2021 15:21:29 - INFO - __main__ - Step 12376: {'lr': 0.0004939618136612911, 'samples': 2376192, 'steps': 12375, 'loss/train': 1.6842349767684937} 08/30/2021 15:21:29 - INFO - __main__ - Step 12377: {'lr': 0.0004939606543269751, 'samples': 2376384, 'steps': 12376, 'loss/train': 1.6865808963775635} 08/30/2021 15:21:30 - INFO - __main__ - Step 12378: {'lr': 0.0004939594948827343, 'samples': 2376576, 'steps': 12377, 'loss/train': 2.005328893661499} 08/30/2021 15:21:30 - INFO - __main__ - Step 12379: {'lr': 0.000493958335328569, 'samples': 2376768, 'steps': 12378, 'loss/train': 2.3254377841949463} 08/30/2021 15:21:31 - INFO - __main__ - Step 12380: {'lr': 0.0004939571756644799, 'samples': 2376960, 'steps': 12379, 'loss/train': 1.0390169620513916} 08/30/2021 15:21:31 - INFO - __main__ - Step 12381: {'lr': 0.0004939560158904675, 'samples': 2377152, 'steps': 12380, 'loss/train': 1.4461275339126587} 08/30/2021 15:21:32 - INFO - __main__ - Step 12382: {'lr': 0.0004939548560065322, 'samples': 2377344, 'steps': 12381, 'loss/train': 1.4545270204544067} 08/30/2021 15:21:33 - INFO - __main__ - Step 12383: {'lr': 0.0004939536960126746, 'samples': 2377536, 'steps': 12382, 'loss/train': 1.4851293563842773} 08/30/2021 15:21:33 - INFO - __main__ - Step 12384: {'lr': 0.0004939525359088953, 'samples': 2377728, 'steps': 12383, 'loss/train': 1.9911237955093384} 08/30/2021 15:21:34 - INFO - __main__ - Step 12385: {'lr': 0.0004939513756951946, 'samples': 2377920, 'steps': 12384, 'loss/train': 2.0675361156463623} 08/30/2021 15:21:34 - INFO - __main__ - Step 12386: {'lr': 0.0004939502153715733, 'samples': 2378112, 'steps': 12385, 'loss/train': 1.9893680810928345} 08/30/2021 15:21:36 - INFO - __main__ - Step 12387: {'lr': 0.0004939490549380318, 'samples': 2378304, 'steps': 12386, 'loss/train': 1.779490351676941} 08/30/2021 15:21:36 - INFO - __main__ - Step 12388: {'lr': 0.0004939478943945706, 'samples': 2378496, 'steps': 12387, 'loss/train': 1.7265629768371582} 08/30/2021 15:21:37 - INFO - __main__ - Step 12389: {'lr': 0.0004939467337411903, 'samples': 2378688, 'steps': 12388, 'loss/train': 1.4875437021255493} 08/30/2021 15:21:37 - INFO - __main__ - Step 12390: {'lr': 0.0004939455729778912, 'samples': 2378880, 'steps': 12389, 'loss/train': 0.10893329232931137} 08/30/2021 15:21:37 - INFO - __main__ - Step 12391: {'lr': 0.0004939444121046741, 'samples': 2379072, 'steps': 12390, 'loss/train': 1.4834707975387573} 08/30/2021 15:21:38 - INFO - __main__ - Step 12392: {'lr': 0.0004939432511215395, 'samples': 2379264, 'steps': 12391, 'loss/train': 1.798765778541565} 08/30/2021 15:21:39 - INFO - __main__ - Step 12393: {'lr': 0.0004939420900284876, 'samples': 2379456, 'steps': 12392, 'loss/train': 2.3325815200805664} 08/30/2021 15:21:40 - INFO - __main__ - Step 12394: {'lr': 0.0004939409288255194, 'samples': 2379648, 'steps': 12393, 'loss/train': 1.9942257404327393} 08/30/2021 15:21:40 - INFO - __main__ - Step 12395: {'lr': 0.000493939767512635, 'samples': 2379840, 'steps': 12394, 'loss/train': 1.1501344442367554} 08/30/2021 15:21:40 - INFO - __main__ - Step 12396: {'lr': 0.0004939386060898353, 'samples': 2380032, 'steps': 12395, 'loss/train': 2.169787883758545} 08/30/2021 15:21:41 - INFO - __main__ - Step 12397: {'lr': 0.0004939374445571206, 'samples': 2380224, 'steps': 12396, 'loss/train': 1.9157381057739258} 08/30/2021 15:21:42 - INFO - __main__ - Step 12398: {'lr': 0.0004939362829144913, 'samples': 2380416, 'steps': 12397, 'loss/train': 1.526296854019165} 08/30/2021 15:21:43 - INFO - __main__ - Step 12399: {'lr': 0.0004939351211619481, 'samples': 2380608, 'steps': 12398, 'loss/train': 1.5075287818908691} 08/30/2021 15:21:43 - INFO - __main__ - Step 12400: {'lr': 0.0004939339592994916, 'samples': 2380800, 'steps': 12399, 'loss/train': 1.858720302581787} 08/30/2021 15:21:44 - INFO - __main__ - Step 12401: {'lr': 0.0004939327973271222, 'samples': 2380992, 'steps': 12400, 'loss/train': 1.6559598445892334} 08/30/2021 15:21:44 - INFO - __main__ - Step 12402: {'lr': 0.0004939316352448403, 'samples': 2381184, 'steps': 12401, 'loss/train': 1.5791690349578857} 08/30/2021 15:21:46 - INFO - __main__ - Step 12403: {'lr': 0.0004939304730526467, 'samples': 2381376, 'steps': 12402, 'loss/train': 2.0456554889678955} 08/30/2021 15:21:46 - INFO - __main__ - Step 12404: {'lr': 0.0004939293107505418, 'samples': 2381568, 'steps': 12403, 'loss/train': 1.1767677068710327} 08/30/2021 15:21:47 - INFO - __main__ - Step 12405: {'lr': 0.0004939281483385261, 'samples': 2381760, 'steps': 12404, 'loss/train': 1.947377324104309} 08/30/2021 15:21:47 - INFO - __main__ - Step 12406: {'lr': 0.0004939269858166001, 'samples': 2381952, 'steps': 12405, 'loss/train': 0.2319193184375763} 08/30/2021 15:21:47 - INFO - __main__ - Step 12407: {'lr': 0.0004939258231847644, 'samples': 2382144, 'steps': 12406, 'loss/train': 1.9935581684112549} 08/30/2021 15:21:49 - INFO - __main__ - Step 12408: {'lr': 0.0004939246604430195, 'samples': 2382336, 'steps': 12407, 'loss/train': 1.9596755504608154} 08/30/2021 15:21:50 - INFO - __main__ - Step 12409: {'lr': 0.0004939234975913659, 'samples': 2382528, 'steps': 12408, 'loss/train': 1.8188401460647583} 08/30/2021 15:21:50 - INFO - __main__ - Step 12410: {'lr': 0.0004939223346298042, 'samples': 2382720, 'steps': 12409, 'loss/train': 1.6885244846343994} 08/30/2021 15:21:50 - INFO - __main__ - Step 12411: {'lr': 0.0004939211715583347, 'samples': 2382912, 'steps': 12410, 'loss/train': 1.8496094942092896} 08/30/2021 15:21:51 - INFO - __main__ - Step 12412: {'lr': 0.0004939200083769582, 'samples': 2383104, 'steps': 12411, 'loss/train': 1.5743927955627441} 08/30/2021 15:21:52 - INFO - __main__ - Step 12413: {'lr': 0.000493918845085675, 'samples': 2383296, 'steps': 12412, 'loss/train': 1.727419137954712} 08/30/2021 15:21:53 - INFO - __main__ - Step 12414: {'lr': 0.000493917681684486, 'samples': 2383488, 'steps': 12413, 'loss/train': 1.1140133142471313} 08/30/2021 15:21:53 - INFO - __main__ - Step 12415: {'lr': 0.0004939165181733911, 'samples': 2383680, 'steps': 12414, 'loss/train': 0.8899873495101929} 08/30/2021 15:21:54 - INFO - __main__ - Step 12416: {'lr': 0.0004939153545523914, 'samples': 2383872, 'steps': 12415, 'loss/train': 0.7002155780792236} 08/30/2021 15:21:54 - INFO - __main__ - Step 12417: {'lr': 0.0004939141908214871, 'samples': 2384064, 'steps': 12416, 'loss/train': 1.9062436819076538} 08/30/2021 15:21:54 - INFO - __main__ - Step 12418: {'lr': 0.000493913026980679, 'samples': 2384256, 'steps': 12417, 'loss/train': 0.7851493954658508} 08/30/2021 15:21:56 - INFO - __main__ - Step 12419: {'lr': 0.0004939118630299672, 'samples': 2384448, 'steps': 12418, 'loss/train': 1.919806718826294} 08/30/2021 15:21:57 - INFO - __main__ - Step 12420: {'lr': 0.0004939106989693527, 'samples': 2384640, 'steps': 12419, 'loss/train': 0.9437406659126282} 08/30/2021 15:21:57 - INFO - __main__ - Step 12421: {'lr': 0.0004939095347988357, 'samples': 2384832, 'steps': 12420, 'loss/train': 1.8690074682235718} 08/30/2021 15:21:57 - INFO - __main__ - Step 12422: {'lr': 0.0004939083705184169, 'samples': 2385024, 'steps': 12421, 'loss/train': 2.076601266860962} 08/30/2021 15:21:58 - INFO - __main__ - Step 12423: {'lr': 0.0004939072061280967, 'samples': 2385216, 'steps': 12422, 'loss/train': 1.6892462968826294} 08/30/2021 15:22:00 - INFO - __main__ - Step 12424: {'lr': 0.0004939060416278756, 'samples': 2385408, 'steps': 12423, 'loss/train': 1.4793415069580078} 08/30/2021 15:22:00 - INFO - __main__ - Step 12425: {'lr': 0.0004939048770177543, 'samples': 2385600, 'steps': 12424, 'loss/train': 1.83730947971344} 08/30/2021 15:22:00 - INFO - __main__ - Step 12426: {'lr': 0.0004939037122977332, 'samples': 2385792, 'steps': 12425, 'loss/train': 2.017552137374878} 08/30/2021 15:22:01 - INFO - __main__ - Step 12427: {'lr': 0.0004939025474678129, 'samples': 2385984, 'steps': 12426, 'loss/train': 0.09431283921003342} 08/30/2021 15:22:01 - INFO - __main__ - Step 12428: {'lr': 0.0004939013825279939, 'samples': 2386176, 'steps': 12427, 'loss/train': 2.293602228164673} 08/30/2021 15:22:02 - INFO - __main__ - Step 12429: {'lr': 0.0004939002174782766, 'samples': 2386368, 'steps': 12428, 'loss/train': 1.7615902423858643} 08/30/2021 15:22:03 - INFO - __main__ - Step 12430: {'lr': 0.0004938990523186616, 'samples': 2386560, 'steps': 12429, 'loss/train': 0.1607472151517868} 08/30/2021 15:22:04 - INFO - __main__ - Step 12431: {'lr': 0.0004938978870491495, 'samples': 2386752, 'steps': 12430, 'loss/train': 2.0253050327301025} 08/30/2021 15:22:04 - INFO - __main__ - Step 12432: {'lr': 0.0004938967216697409, 'samples': 2386944, 'steps': 12431, 'loss/train': 1.1702685356140137} 08/30/2021 15:22:05 - INFO - __main__ - Step 12433: {'lr': 0.0004938955561804361, 'samples': 2387136, 'steps': 12432, 'loss/train': 1.8104138374328613} 08/30/2021 15:22:05 - INFO - __main__ - Step 12434: {'lr': 0.0004938943905812357, 'samples': 2387328, 'steps': 12433, 'loss/train': 0.1371229588985443} 08/30/2021 15:22:05 - INFO - __main__ - Step 12435: {'lr': 0.0004938932248721401, 'samples': 2387520, 'steps': 12434, 'loss/train': 0.5494178533554077} 08/30/2021 15:22:07 - INFO - __main__ - Step 12436: {'lr': 0.0004938920590531503, 'samples': 2387712, 'steps': 12435, 'loss/train': 1.388697624206543} 08/30/2021 15:22:07 - INFO - __main__ - Step 12437: {'lr': 0.0004938908931242663, 'samples': 2387904, 'steps': 12436, 'loss/train': 1.370986819267273} 08/30/2021 15:22:08 - INFO - __main__ - Step 12438: {'lr': 0.0004938897270854889, 'samples': 2388096, 'steps': 12437, 'loss/train': 1.4781913757324219} 08/30/2021 15:22:08 - INFO - __main__ - Step 12439: {'lr': 0.0004938885609368184, 'samples': 2388288, 'steps': 12438, 'loss/train': 1.5946956872940063} 08/30/2021 15:22:08 - INFO - __main__ - Step 12440: {'lr': 0.0004938873946782557, 'samples': 2388480, 'steps': 12439, 'loss/train': 1.0407694578170776} 08/30/2021 15:22:10 - INFO - __main__ - Step 12441: {'lr': 0.000493886228309801, 'samples': 2388672, 'steps': 12440, 'loss/train': 2.2493369579315186} 08/30/2021 15:22:10 - INFO - __main__ - Step 12442: {'lr': 0.0004938850618314549, 'samples': 2388864, 'steps': 12441, 'loss/train': 2.3278608322143555} 08/30/2021 15:22:11 - INFO - __main__ - Step 12443: {'lr': 0.000493883895243218, 'samples': 2389056, 'steps': 12442, 'loss/train': 1.4713679552078247} 08/30/2021 15:22:11 - INFO - __main__ - Step 12444: {'lr': 0.0004938827285450908, 'samples': 2389248, 'steps': 12443, 'loss/train': 1.7078709602355957} 08/30/2021 15:22:11 - INFO - __main__ - Step 12445: {'lr': 0.0004938815617370737, 'samples': 2389440, 'steps': 12444, 'loss/train': 1.4049808979034424} 08/30/2021 15:22:13 - INFO - __main__ - Step 12446: {'lr': 0.0004938803948191674, 'samples': 2389632, 'steps': 12445, 'loss/train': 0.1803952008485794} 08/30/2021 15:22:13 - INFO - __main__ - Step 12447: {'lr': 0.0004938792277913724, 'samples': 2389824, 'steps': 12446, 'loss/train': 1.6435493230819702} 08/30/2021 15:22:13 - INFO - __main__ - Step 12448: {'lr': 0.0004938780606536891, 'samples': 2390016, 'steps': 12447, 'loss/train': 1.762094497680664} 08/30/2021 15:22:14 - INFO - __main__ - Step 12449: {'lr': 0.0004938768934061182, 'samples': 2390208, 'steps': 12448, 'loss/train': 1.5482165813446045} 08/30/2021 15:22:14 - INFO - __main__ - Step 12450: {'lr': 0.0004938757260486601, 'samples': 2390400, 'steps': 12449, 'loss/train': 1.4777065515518188} 08/30/2021 15:22:16 - INFO - __main__ - Step 12451: {'lr': 0.0004938745585813153, 'samples': 2390592, 'steps': 12450, 'loss/train': 1.2664315700531006} 08/30/2021 15:22:16 - INFO - __main__ - Step 12452: {'lr': 0.0004938733910040845, 'samples': 2390784, 'steps': 12451, 'loss/train': 1.8675448894500732} 08/30/2021 15:22:17 - INFO - __main__ - Step 12453: {'lr': 0.000493872223316968, 'samples': 2390976, 'steps': 12452, 'loss/train': 1.7587313652038574} 08/30/2021 15:22:17 - INFO - __main__ - Step 12454: {'lr': 0.0004938710555199664, 'samples': 2391168, 'steps': 12453, 'loss/train': 2.098862648010254} 08/30/2021 15:22:17 - INFO - __main__ - Step 12455: {'lr': 0.0004938698876130804, 'samples': 2391360, 'steps': 12454, 'loss/train': 1.8751031160354614} 08/30/2021 15:22:18 - INFO - __main__ - Step 12456: {'lr': 0.0004938687195963104, 'samples': 2391552, 'steps': 12455, 'loss/train': 1.2401816844940186} 08/30/2021 15:22:19 - INFO - __main__ - Step 12457: {'lr': 0.0004938675514696569, 'samples': 2391744, 'steps': 12456, 'loss/train': 1.090671181678772} 08/30/2021 15:22:20 - INFO - __main__ - Step 12458: {'lr': 0.0004938663832331204, 'samples': 2391936, 'steps': 12457, 'loss/train': 1.8153104782104492} 08/30/2021 15:22:20 - INFO - __main__ - Step 12459: {'lr': 0.0004938652148867014, 'samples': 2392128, 'steps': 12458, 'loss/train': 1.4731745719909668} 08/30/2021 15:22:21 - INFO - __main__ - Step 12460: {'lr': 0.0004938640464304006, 'samples': 2392320, 'steps': 12459, 'loss/train': 2.171313524246216} 08/30/2021 15:22:21 - INFO - __main__ - Step 12461: {'lr': 0.0004938628778642185, 'samples': 2392512, 'steps': 12460, 'loss/train': 1.8743846416473389} 08/30/2021 15:22:23 - INFO - __main__ - Step 12462: {'lr': 0.0004938617091881554, 'samples': 2392704, 'steps': 12461, 'loss/train': 1.378425121307373} 08/30/2021 15:22:23 - INFO - __main__ - Step 12463: {'lr': 0.000493860540402212, 'samples': 2392896, 'steps': 12462, 'loss/train': 2.4345130920410156} 08/30/2021 15:22:23 - INFO - __main__ - Step 12464: {'lr': 0.0004938593715063888, 'samples': 2393088, 'steps': 12463, 'loss/train': 0.23290377855300903} 08/30/2021 15:22:24 - INFO - __main__ - Step 12465: {'lr': 0.0004938582025006864, 'samples': 2393280, 'steps': 12464, 'loss/train': 2.8235154151916504} 08/30/2021 15:22:24 - INFO - __main__ - Step 12466: {'lr': 0.0004938570333851052, 'samples': 2393472, 'steps': 12465, 'loss/train': 1.8025381565093994} 08/30/2021 15:22:26 - INFO - __main__ - Step 12467: {'lr': 0.0004938558641596458, 'samples': 2393664, 'steps': 12466, 'loss/train': 1.8506377935409546} 08/30/2021 15:22:26 - INFO - __main__ - Step 12468: {'lr': 0.0004938546948243087, 'samples': 2393856, 'steps': 12467, 'loss/train': 1.8140132427215576} 08/30/2021 15:22:26 - INFO - __main__ - Step 12469: {'lr': 0.0004938535253790944, 'samples': 2394048, 'steps': 12468, 'loss/train': 1.4851552248001099} 08/30/2021 15:22:27 - INFO - __main__ - Step 12470: {'lr': 0.0004938523558240035, 'samples': 2394240, 'steps': 12469, 'loss/train': 1.7355839014053345} 08/30/2021 15:22:27 - INFO - __main__ - Step 12471: {'lr': 0.0004938511861590365, 'samples': 2394432, 'steps': 12470, 'loss/train': 1.5451091527938843} 08/30/2021 15:22:30 - INFO - __main__ - Step 12472: {'lr': 0.000493850016384194, 'samples': 2394624, 'steps': 12471, 'loss/train': 1.8238810300827026} 08/30/2021 15:22:31 - INFO - __main__ - Step 12473: {'lr': 0.0004938488464994764, 'samples': 2394816, 'steps': 12472, 'loss/train': 0.9098502397537231} 08/30/2021 15:22:31 - INFO - __main__ - Step 12474: {'lr': 0.0004938476765048842, 'samples': 2395008, 'steps': 12473, 'loss/train': 0.8234099745750427} 08/30/2021 15:22:31 - INFO - __main__ - Step 12475: {'lr': 0.0004938465064004181, 'samples': 2395200, 'steps': 12474, 'loss/train': 0.6922528147697449} 08/30/2021 15:22:32 - INFO - __main__ - Step 12476: {'lr': 0.0004938453361860785, 'samples': 2395392, 'steps': 12475, 'loss/train': 1.9006537199020386} 08/30/2021 15:22:32 - INFO - __main__ - Step 12477: {'lr': 0.0004938441658618659, 'samples': 2395584, 'steps': 12476, 'loss/train': 1.4312968254089355} 08/30/2021 15:22:34 - INFO - __main__ - Step 12478: {'lr': 0.0004938429954277809, 'samples': 2395776, 'steps': 12477, 'loss/train': 2.016352653503418} 08/30/2021 15:22:34 - INFO - __main__ - Step 12479: {'lr': 0.000493841824883824, 'samples': 2395968, 'steps': 12478, 'loss/train': 2.184368848800659} 08/30/2021 15:22:35 - INFO - __main__ - Step 12480: {'lr': 0.0004938406542299956, 'samples': 2396160, 'steps': 12479, 'loss/train': 1.658437967300415} 08/30/2021 15:22:35 - INFO - __main__ - Step 12481: {'lr': 0.0004938394834662966, 'samples': 2396352, 'steps': 12480, 'loss/train': 0.22018125653266907} 08/30/2021 15:22:35 - INFO - __main__ - Step 12482: {'lr': 0.0004938383125927272, 'samples': 2396544, 'steps': 12481, 'loss/train': 2.0617432594299316} 08/30/2021 15:22:36 - INFO - __main__ - Step 12483: {'lr': 0.0004938371416092881, 'samples': 2396736, 'steps': 12482, 'loss/train': 1.5849149227142334} 08/30/2021 15:22:37 - INFO - __main__ - Step 12484: {'lr': 0.0004938359705159796, 'samples': 2396928, 'steps': 12483, 'loss/train': 1.7631844282150269} 08/30/2021 15:22:38 - INFO - __main__ - Step 12485: {'lr': 0.0004938347993128025, 'samples': 2397120, 'steps': 12484, 'loss/train': 1.6862891912460327} 08/30/2021 15:22:38 - INFO - __main__ - Step 12486: {'lr': 0.0004938336279997571, 'samples': 2397312, 'steps': 12485, 'loss/train': 1.6655131578445435} 08/30/2021 15:22:39 - INFO - __main__ - Step 12487: {'lr': 0.0004938324565768441, 'samples': 2397504, 'steps': 12486, 'loss/train': 1.7845306396484375} 08/30/2021 15:22:39 - INFO - __main__ - Step 12488: {'lr': 0.0004938312850440639, 'samples': 2397696, 'steps': 12487, 'loss/train': 0.5651407837867737} 08/30/2021 15:22:40 - INFO - __main__ - Step 12489: {'lr': 0.0004938301134014172, 'samples': 2397888, 'steps': 12488, 'loss/train': 0.9216361045837402} 08/30/2021 15:22:41 - INFO - __main__ - Step 12490: {'lr': 0.0004938289416489042, 'samples': 2398080, 'steps': 12489, 'loss/train': 1.7292640209197998} 08/30/2021 15:22:41 - INFO - __main__ - Step 12491: {'lr': 0.0004938277697865259, 'samples': 2398272, 'steps': 12490, 'loss/train': 1.921535611152649} 08/30/2021 15:22:42 - INFO - __main__ - Step 12492: {'lr': 0.0004938265978142824, 'samples': 2398464, 'steps': 12491, 'loss/train': 1.4806448221206665} 08/30/2021 15:22:42 - INFO - __main__ - Step 12493: {'lr': 0.0004938254257321745, 'samples': 2398656, 'steps': 12492, 'loss/train': 2.1684815883636475} 08/30/2021 15:22:43 - INFO - __main__ - Step 12494: {'lr': 0.0004938242535402025, 'samples': 2398848, 'steps': 12493, 'loss/train': 1.8698049783706665} 08/30/2021 15:22:44 - INFO - __main__ - Step 12495: {'lr': 0.0004938230812383672, 'samples': 2399040, 'steps': 12494, 'loss/train': 1.7525417804718018} 08/30/2021 15:22:44 - INFO - __main__ - Step 12496: {'lr': 0.0004938219088266688, 'samples': 2399232, 'steps': 12495, 'loss/train': 2.0826210975646973} 08/30/2021 15:22:44 - INFO - __main__ - Step 12497: {'lr': 0.0004938207363051082, 'samples': 2399424, 'steps': 12496, 'loss/train': 1.6311655044555664} 08/30/2021 15:22:45 - INFO - __main__ - Step 12498: {'lr': 0.0004938195636736857, 'samples': 2399616, 'steps': 12497, 'loss/train': 1.8564714193344116} 08/30/2021 15:22:46 - INFO - __main__ - Step 12499: {'lr': 0.0004938183909324017, 'samples': 2399808, 'steps': 12498, 'loss/train': 2.4576282501220703} 08/30/2021 15:22:47 - INFO - __main__ - Step 12500: {'lr': 0.0004938172180812571, 'samples': 2400000, 'steps': 12499, 'loss/train': 1.2565624713897705} 08/30/2021 15:22:47 - INFO - __main__ - Step 12501: {'lr': 0.000493816045120252, 'samples': 2400192, 'steps': 12500, 'loss/train': 1.589972972869873} 08/30/2021 15:22:48 - INFO - __main__ - Step 12502: {'lr': 0.0004938148720493873, 'samples': 2400384, 'steps': 12501, 'loss/train': 1.6916298866271973} 08/30/2021 15:22:48 - INFO - __main__ - Step 12503: {'lr': 0.0004938136988686634, 'samples': 2400576, 'steps': 12502, 'loss/train': 1.5743650197982788} 08/30/2021 15:22:48 - INFO - __main__ - Step 12504: {'lr': 0.0004938125255780808, 'samples': 2400768, 'steps': 12503, 'loss/train': 1.841348648071289} 08/30/2021 15:22:50 - INFO - __main__ - Step 12505: {'lr': 0.0004938113521776401, 'samples': 2400960, 'steps': 12504, 'loss/train': 1.791174054145813} 08/30/2021 15:22:50 - INFO - __main__ - Step 12506: {'lr': 0.0004938101786673416, 'samples': 2401152, 'steps': 12505, 'loss/train': 1.8853627443313599} 08/30/2021 15:22:51 - INFO - __main__ - Step 12507: {'lr': 0.0004938090050471861, 'samples': 2401344, 'steps': 12506, 'loss/train': 1.1951075792312622} 08/30/2021 15:22:51 - INFO - __main__ - Step 12508: {'lr': 0.000493807831317174, 'samples': 2401536, 'steps': 12507, 'loss/train': 1.2089728116989136} 08/30/2021 15:22:51 - INFO - __main__ - Step 12509: {'lr': 0.0004938066574773058, 'samples': 2401728, 'steps': 12508, 'loss/train': 1.4420223236083984} 08/30/2021 15:22:53 - INFO - __main__ - Step 12510: {'lr': 0.0004938054835275822, 'samples': 2401920, 'steps': 12509, 'loss/train': 1.7887407541275024} 08/30/2021 15:22:53 - INFO - __main__ - Step 12511: {'lr': 0.0004938043094680036, 'samples': 2402112, 'steps': 12510, 'loss/train': 1.6452138423919678} 08/30/2021 15:22:54 - INFO - __main__ - Step 12512: {'lr': 0.0004938031352985704, 'samples': 2402304, 'steps': 12511, 'loss/train': 1.6797332763671875} 08/30/2021 15:22:54 - INFO - __main__ - Step 12513: {'lr': 0.0004938019610192835, 'samples': 2402496, 'steps': 12512, 'loss/train': 1.5179246664047241} 08/30/2021 15:22:54 - INFO - __main__ - Step 12514: {'lr': 0.0004938007866301429, 'samples': 2402688, 'steps': 12513, 'loss/train': 1.9688055515289307} 08/30/2021 15:22:56 - INFO - __main__ - Step 12515: {'lr': 0.0004937996121311496, 'samples': 2402880, 'steps': 12514, 'loss/train': 1.907478928565979} 08/30/2021 15:22:56 - INFO - __main__ - Step 12516: {'lr': 0.000493798437522304, 'samples': 2403072, 'steps': 12515, 'loss/train': 1.7711124420166016} 08/30/2021 15:22:56 - INFO - __main__ - Step 12517: {'lr': 0.0004937972628036065, 'samples': 2403264, 'steps': 12516, 'loss/train': 1.4934422969818115} 08/30/2021 15:22:57 - INFO - __main__ - Step 12518: {'lr': 0.0004937960879750578, 'samples': 2403456, 'steps': 12517, 'loss/train': 1.4428638219833374} 08/30/2021 15:22:57 - INFO - __main__ - Step 12519: {'lr': 0.0004937949130366582, 'samples': 2403648, 'steps': 12518, 'loss/train': 1.6491045951843262} 08/30/2021 15:22:59 - INFO - __main__ - Step 12520: {'lr': 0.0004937937379884085, 'samples': 2403840, 'steps': 12519, 'loss/train': 1.5070687532424927} 08/30/2021 15:22:59 - INFO - __main__ - Step 12521: {'lr': 0.0004937925628303091, 'samples': 2404032, 'steps': 12520, 'loss/train': 1.9181841611862183} 08/30/2021 15:22:59 - INFO - __main__ - Step 12522: {'lr': 0.0004937913875623605, 'samples': 2404224, 'steps': 12521, 'loss/train': 1.913568139076233} 08/30/2021 15:23:00 - INFO - __main__ - Step 12523: {'lr': 0.0004937902121845633, 'samples': 2404416, 'steps': 12522, 'loss/train': 1.7699967622756958} 08/30/2021 15:23:00 - INFO - __main__ - Step 12524: {'lr': 0.000493789036696918, 'samples': 2404608, 'steps': 12523, 'loss/train': 1.8491734266281128} 08/30/2021 15:23:02 - INFO - __main__ - Step 12525: {'lr': 0.000493787861099425, 'samples': 2404800, 'steps': 12524, 'loss/train': 1.6258100271224976} 08/30/2021 15:23:02 - INFO - __main__ - Step 12526: {'lr': 0.0004937866853920851, 'samples': 2404992, 'steps': 12525, 'loss/train': 2.2164700031280518} 08/30/2021 15:23:02 - INFO - __main__ - Step 12527: {'lr': 0.0004937855095748985, 'samples': 2405184, 'steps': 12526, 'loss/train': 1.8664838075637817} 08/30/2021 15:23:03 - INFO - __main__ - Step 12528: {'lr': 0.0004937843336478661, 'samples': 2405376, 'steps': 12527, 'loss/train': 1.4773613214492798} 08/30/2021 15:23:03 - INFO - __main__ - Step 12529: {'lr': 0.0004937831576109881, 'samples': 2405568, 'steps': 12528, 'loss/train': 2.0828826427459717} 08/30/2021 15:23:05 - INFO - __main__ - Step 12530: {'lr': 0.0004937819814642653, 'samples': 2405760, 'steps': 12529, 'loss/train': 2.1169567108154297} 08/30/2021 15:23:06 - INFO - __main__ - Step 12531: {'lr': 0.000493780805207698, 'samples': 2405952, 'steps': 12530, 'loss/train': 1.6626170873641968} 08/30/2021 15:23:06 - INFO - __main__ - Step 12532: {'lr': 0.000493779628841287, 'samples': 2406144, 'steps': 12531, 'loss/train': 0.2646285593509674} 08/30/2021 15:23:06 - INFO - __main__ - Step 12533: {'lr': 0.0004937784523650324, 'samples': 2406336, 'steps': 12532, 'loss/train': 1.410550832748413} 08/30/2021 15:23:07 - INFO - __main__ - Step 12534: {'lr': 0.0004937772757789352, 'samples': 2406528, 'steps': 12533, 'loss/train': 1.9159671068191528} 08/30/2021 15:23:08 - INFO - __main__ - Step 12535: {'lr': 0.0004937760990829956, 'samples': 2406720, 'steps': 12534, 'loss/train': 1.1231690645217896} 08/30/2021 15:23:09 - INFO - __main__ - Step 12536: {'lr': 0.0004937749222772143, 'samples': 2406912, 'steps': 12535, 'loss/train': 1.831701636314392} 08/30/2021 15:23:09 - INFO - __main__ - Step 12537: {'lr': 0.0004937737453615918, 'samples': 2407104, 'steps': 12536, 'loss/train': 1.8218296766281128} 08/30/2021 15:23:09 - INFO - __main__ - Step 12538: {'lr': 0.0004937725683361286, 'samples': 2407296, 'steps': 12537, 'loss/train': 1.5685603618621826} 08/30/2021 15:23:10 - INFO - __main__ - Step 12539: {'lr': 0.0004937713912008252, 'samples': 2407488, 'steps': 12538, 'loss/train': 1.727821946144104} 08/30/2021 15:23:10 - INFO - __main__ - Step 12540: {'lr': 0.0004937702139556822, 'samples': 2407680, 'steps': 12539, 'loss/train': 1.4807853698730469} 08/30/2021 15:23:11 - INFO - __main__ - Step 12541: {'lr': 0.0004937690366007, 'samples': 2407872, 'steps': 12540, 'loss/train': 1.8320239782333374} 08/30/2021 15:23:12 - INFO - __main__ - Step 12542: {'lr': 0.0004937678591358794, 'samples': 2408064, 'steps': 12541, 'loss/train': 1.73628568649292} 08/30/2021 15:23:12 - INFO - __main__ - Step 12543: {'lr': 0.0004937666815612207, 'samples': 2408256, 'steps': 12542, 'loss/train': 1.7498762607574463} 08/30/2021 15:23:12 - INFO - __main__ - Step 12544: {'lr': 0.0004937655038767245, 'samples': 2408448, 'steps': 12543, 'loss/train': 2.125943183898926} 08/30/2021 15:23:13 - INFO - __main__ - Step 12545: {'lr': 0.0004937643260823914, 'samples': 2408640, 'steps': 12544, 'loss/train': 1.7223514318466187} 08/30/2021 15:23:14 - INFO - __main__ - Step 12546: {'lr': 0.0004937631481782218, 'samples': 2408832, 'steps': 12545, 'loss/train': 1.3177604675292969} 08/30/2021 15:23:15 - INFO - __main__ - Step 12547: {'lr': 0.0004937619701642162, 'samples': 2409024, 'steps': 12546, 'loss/train': 1.0912584066390991} 08/30/2021 15:23:15 - INFO - __main__ - Step 12548: {'lr': 0.0004937607920403752, 'samples': 2409216, 'steps': 12547, 'loss/train': 1.5156407356262207} 08/30/2021 15:23:16 - INFO - __main__ - Step 12549: {'lr': 0.0004937596138066996, 'samples': 2409408, 'steps': 12548, 'loss/train': 0.5244348049163818} 08/30/2021 15:23:16 - INFO - __main__ - Step 12550: {'lr': 0.0004937584354631894, 'samples': 2409600, 'steps': 12549, 'loss/train': 0.5477697849273682} 08/30/2021 15:23:18 - INFO - __main__ - Step 12551: {'lr': 0.0004937572570098455, 'samples': 2409792, 'steps': 12550, 'loss/train': 1.8346753120422363} 08/30/2021 15:23:18 - INFO - __main__ - Step 12552: {'lr': 0.0004937560784466685, 'samples': 2409984, 'steps': 12551, 'loss/train': 2.2612287998199463} 08/30/2021 15:23:18 - INFO - __main__ - Step 12553: {'lr': 0.0004937548997736586, 'samples': 2410176, 'steps': 12552, 'loss/train': 1.7875642776489258} 08/30/2021 15:23:19 - INFO - __main__ - Step 12554: {'lr': 0.0004937537209908165, 'samples': 2410368, 'steps': 12553, 'loss/train': 1.822165846824646} 08/30/2021 15:23:19 - INFO - __main__ - Step 12555: {'lr': 0.0004937525420981428, 'samples': 2410560, 'steps': 12554, 'loss/train': 1.816356897354126} 08/30/2021 15:23:20 - INFO - __main__ - Step 12556: {'lr': 0.0004937513630956379, 'samples': 2410752, 'steps': 12555, 'loss/train': 1.835490107536316} 08/30/2021 15:23:21 - INFO - __main__ - Step 12557: {'lr': 0.0004937501839833024, 'samples': 2410944, 'steps': 12556, 'loss/train': 2.248667001724243} 08/30/2021 15:23:22 - INFO - __main__ - Step 12558: {'lr': 0.0004937490047611369, 'samples': 2411136, 'steps': 12557, 'loss/train': 1.3210731744766235} 08/30/2021 15:23:22 - INFO - __main__ - Step 12559: {'lr': 0.0004937478254291418, 'samples': 2411328, 'steps': 12558, 'loss/train': 1.8700735569000244} 08/30/2021 15:23:22 - INFO - __main__ - Step 12560: {'lr': 0.0004937466459873178, 'samples': 2411520, 'steps': 12559, 'loss/train': 2.178784132003784} 08/30/2021 15:23:23 - INFO - __main__ - Step 12561: {'lr': 0.0004937454664356652, 'samples': 2411712, 'steps': 12560, 'loss/train': 1.6456546783447266} 08/30/2021 15:23:24 - INFO - __main__ - Step 12562: {'lr': 0.0004937442867741848, 'samples': 2411904, 'steps': 12561, 'loss/train': 1.9860590696334839} 08/30/2021 15:23:25 - INFO - __main__ - Step 12563: {'lr': 0.0004937431070028768, 'samples': 2412096, 'steps': 12562, 'loss/train': 2.0442144870758057} 08/30/2021 15:23:25 - INFO - __main__ - Step 12564: {'lr': 0.0004937419271217419, 'samples': 2412288, 'steps': 12563, 'loss/train': 1.8291712999343872} 08/30/2021 15:23:25 - INFO - __main__ - Step 12565: {'lr': 0.0004937407471307807, 'samples': 2412480, 'steps': 12564, 'loss/train': 1.5600214004516602} 08/30/2021 15:23:26 - INFO - __main__ - Step 12566: {'lr': 0.0004937395670299938, 'samples': 2412672, 'steps': 12565, 'loss/train': 1.662540078163147} 08/30/2021 15:23:27 - INFO - __main__ - Step 12567: {'lr': 0.0004937383868193815, 'samples': 2412864, 'steps': 12566, 'loss/train': 2.447221279144287} 08/30/2021 15:23:28 - INFO - __main__ - Step 12568: {'lr': 0.0004937372064989445, 'samples': 2413056, 'steps': 12567, 'loss/train': 1.4903484582901} 08/30/2021 15:23:28 - INFO - __main__ - Step 12569: {'lr': 0.0004937360260686833, 'samples': 2413248, 'steps': 12568, 'loss/train': 1.952978491783142} 08/30/2021 15:23:28 - INFO - __main__ - Step 12570: {'lr': 0.0004937348455285983, 'samples': 2413440, 'steps': 12569, 'loss/train': 1.8628313541412354} 08/30/2021 15:23:29 - INFO - __main__ - Step 12571: {'lr': 0.0004937336648786903, 'samples': 2413632, 'steps': 12570, 'loss/train': 1.6591362953186035} 08/30/2021 15:23:30 - INFO - __main__ - Step 12572: {'lr': 0.0004937324841189595, 'samples': 2413824, 'steps': 12571, 'loss/train': 2.9854345321655273} 08/30/2021 15:23:31 - INFO - __main__ - Step 12573: {'lr': 0.0004937313032494068, 'samples': 2414016, 'steps': 12572, 'loss/train': 1.566379189491272} 08/30/2021 15:23:31 - INFO - __main__ - Step 12574: {'lr': 0.0004937301222700324, 'samples': 2414208, 'steps': 12573, 'loss/train': 1.1759110689163208} 08/30/2021 15:23:31 - INFO - __main__ - Step 12575: {'lr': 0.0004937289411808369, 'samples': 2414400, 'steps': 12574, 'loss/train': 0.8813082575798035} 08/30/2021 15:23:32 - INFO - __main__ - Step 12576: {'lr': 0.000493727759981821, 'samples': 2414592, 'steps': 12575, 'loss/train': 1.5776596069335938} 08/30/2021 15:23:33 - INFO - __main__ - Step 12577: {'lr': 0.0004937265786729851, 'samples': 2414784, 'steps': 12576, 'loss/train': 0.5332491993904114} 08/30/2021 15:23:34 - INFO - __main__ - Step 12578: {'lr': 0.0004937253972543298, 'samples': 2414976, 'steps': 12577, 'loss/train': 1.688797950744629} 08/30/2021 15:23:34 - INFO - __main__ - Step 12579: {'lr': 0.0004937242157258555, 'samples': 2415168, 'steps': 12578, 'loss/train': 2.6554276943206787} 08/30/2021 15:23:35 - INFO - __main__ - Step 12580: {'lr': 0.000493723034087563, 'samples': 2415360, 'steps': 12579, 'loss/train': 1.850439429283142} 08/30/2021 15:23:35 - INFO - __main__ - Step 12581: {'lr': 0.0004937218523394525, 'samples': 2415552, 'steps': 12580, 'loss/train': 1.299819827079773} 08/30/2021 15:23:35 - INFO - __main__ - Step 12582: {'lr': 0.0004937206704815248, 'samples': 2415744, 'steps': 12581, 'loss/train': 1.8108617067337036} 08/30/2021 15:23:37 - INFO - __main__ - Step 12583: {'lr': 0.0004937194885137803, 'samples': 2415936, 'steps': 12582, 'loss/train': 2.009592294692993} 08/30/2021 15:23:38 - INFO - __main__ - Step 12584: {'lr': 0.0004937183064362196, 'samples': 2416128, 'steps': 12583, 'loss/train': 1.7571768760681152} 08/30/2021 15:23:38 - INFO - __main__ - Step 12585: {'lr': 0.0004937171242488431, 'samples': 2416320, 'steps': 12584, 'loss/train': 2.422935962677002} 08/30/2021 15:23:38 - INFO - __main__ - Step 12586: {'lr': 0.0004937159419516515, 'samples': 2416512, 'steps': 12585, 'loss/train': 1.5480355024337769} 08/30/2021 15:23:39 - INFO - __main__ - Step 12587: {'lr': 0.0004937147595446452, 'samples': 2416704, 'steps': 12586, 'loss/train': 1.3654075860977173} 08/30/2021 15:23:40 - INFO - __main__ - Step 12588: {'lr': 0.0004937135770278248, 'samples': 2416896, 'steps': 12587, 'loss/train': 1.9075508117675781} 08/30/2021 15:23:41 - INFO - __main__ - Step 12589: {'lr': 0.0004937123944011908, 'samples': 2417088, 'steps': 12588, 'loss/train': 1.8653266429901123} 08/30/2021 15:23:41 - INFO - __main__ - Step 12590: {'lr': 0.0004937112116647439, 'samples': 2417280, 'steps': 12589, 'loss/train': 1.9763001203536987} 08/30/2021 15:23:41 - INFO - __main__ - Step 12591: {'lr': 0.0004937100288184843, 'samples': 2417472, 'steps': 12590, 'loss/train': 0.810440182685852} 08/30/2021 15:23:42 - INFO - __main__ - Step 12592: {'lr': 0.0004937088458624128, 'samples': 2417664, 'steps': 12591, 'loss/train': 1.4978715181350708} 08/30/2021 15:23:43 - INFO - __main__ - Step 12593: {'lr': 0.0004937076627965299, 'samples': 2417856, 'steps': 12592, 'loss/train': 1.519140601158142} 08/30/2021 15:23:44 - INFO - __main__ - Step 12594: {'lr': 0.000493706479620836, 'samples': 2418048, 'steps': 12593, 'loss/train': 1.8998225927352905} 08/30/2021 15:23:44 - INFO - __main__ - Step 12595: {'lr': 0.0004937052963353318, 'samples': 2418240, 'steps': 12594, 'loss/train': 2.019606828689575} 08/30/2021 15:23:45 - INFO - __main__ - Step 12596: {'lr': 0.0004937041129400177, 'samples': 2418432, 'steps': 12595, 'loss/train': 1.3530529737472534} 08/30/2021 15:23:45 - INFO - __main__ - Step 12597: {'lr': 0.0004937029294348943, 'samples': 2418624, 'steps': 12596, 'loss/train': 1.3625153303146362} 08/30/2021 15:23:46 - INFO - __main__ - Step 12598: {'lr': 0.0004937017458199621, 'samples': 2418816, 'steps': 12597, 'loss/train': 1.8002816438674927} 08/30/2021 15:23:47 - INFO - __main__ - Step 12599: {'lr': 0.0004937005620952217, 'samples': 2419008, 'steps': 12598, 'loss/train': 1.3398879766464233} 08/30/2021 15:23:47 - INFO - __main__ - Step 12600: {'lr': 0.0004936993782606735, 'samples': 2419200, 'steps': 12599, 'loss/train': 1.5852748155593872} 08/30/2021 15:23:48 - INFO - __main__ - Step 12601: {'lr': 0.0004936981943163182, 'samples': 2419392, 'steps': 12600, 'loss/train': 1.806483268737793} 08/30/2021 15:23:48 - INFO - __main__ - Step 12602: {'lr': 0.0004936970102621563, 'samples': 2419584, 'steps': 12601, 'loss/train': 1.811933159828186} 08/30/2021 15:23:50 - INFO - __main__ - Step 12603: {'lr': 0.0004936958260981883, 'samples': 2419776, 'steps': 12602, 'loss/train': 1.9197443723678589} 08/30/2021 15:23:50 - INFO - __main__ - Step 12604: {'lr': 0.0004936946418244146, 'samples': 2419968, 'steps': 12603, 'loss/train': 1.1525815725326538} 08/30/2021 15:23:51 - INFO - __main__ - Step 12605: {'lr': 0.000493693457440836, 'samples': 2420160, 'steps': 12604, 'loss/train': 2.6090035438537598} 08/30/2021 15:23:51 - INFO - __main__ - Step 12606: {'lr': 0.0004936922729474526, 'samples': 2420352, 'steps': 12605, 'loss/train': 1.2480660676956177} 08/30/2021 15:23:51 - INFO - __main__ - Step 12607: {'lr': 0.0004936910883442655, 'samples': 2420544, 'steps': 12606, 'loss/train': 1.8558886051177979} 08/30/2021 15:23:52 - INFO - __main__ - Step 12608: {'lr': 0.0004936899036312749, 'samples': 2420736, 'steps': 12607, 'loss/train': 1.8366355895996094} 08/30/2021 15:23:53 - INFO - __main__ - Step 12609: {'lr': 0.0004936887188084813, 'samples': 2420928, 'steps': 12608, 'loss/train': 1.5720945596694946} 08/30/2021 15:23:54 - INFO - __main__ - Step 12610: {'lr': 0.0004936875338758855, 'samples': 2421120, 'steps': 12609, 'loss/train': 1.534041404724121} 08/30/2021 15:23:54 - INFO - __main__ - Step 12611: {'lr': 0.0004936863488334877, 'samples': 2421312, 'steps': 12610, 'loss/train': 1.8757835626602173} 08/30/2021 15:23:55 - INFO - __main__ - Step 12612: {'lr': 0.0004936851636812886, 'samples': 2421504, 'steps': 12611, 'loss/train': 1.5210860967636108} 08/30/2021 15:23:55 - INFO - __main__ - Step 12613: {'lr': 0.0004936839784192888, 'samples': 2421696, 'steps': 12612, 'loss/train': 1.7473598718643188} 08/30/2021 15:23:57 - INFO - __main__ - Step 12614: {'lr': 0.0004936827930474887, 'samples': 2421888, 'steps': 12613, 'loss/train': 0.2659986615180969} 08/30/2021 15:23:57 - INFO - __main__ - Step 12615: {'lr': 0.0004936816075658889, 'samples': 2422080, 'steps': 12614, 'loss/train': 1.3665947914123535} 08/30/2021 15:23:58 - INFO - __main__ - Step 12616: {'lr': 0.00049368042197449, 'samples': 2422272, 'steps': 12615, 'loss/train': 1.896285057067871} 08/30/2021 15:23:58 - INFO - __main__ - Step 12617: {'lr': 0.0004936792362732924, 'samples': 2422464, 'steps': 12616, 'loss/train': 1.6242717504501343} 08/30/2021 15:23:58 - INFO - __main__ - Step 12618: {'lr': 0.0004936780504622967, 'samples': 2422656, 'steps': 12617, 'loss/train': 0.108314648270607} 08/30/2021 15:24:00 - INFO - __main__ - Step 12619: {'lr': 0.0004936768645415033, 'samples': 2422848, 'steps': 12618, 'loss/train': 1.9631596803665161} 08/30/2021 15:24:00 - INFO - __main__ - Step 12620: {'lr': 0.0004936756785109131, 'samples': 2423040, 'steps': 12619, 'loss/train': 1.9854191541671753} 08/30/2021 15:24:01 - INFO - __main__ - Step 12621: {'lr': 0.0004936744923705263, 'samples': 2423232, 'steps': 12620, 'loss/train': 2.0630979537963867} 08/30/2021 15:24:01 - INFO - __main__ - Step 12622: {'lr': 0.0004936733061203435, 'samples': 2423424, 'steps': 12621, 'loss/train': 2.102893114089966} 08/30/2021 15:24:01 - INFO - __main__ - Step 12623: {'lr': 0.0004936721197603653, 'samples': 2423616, 'steps': 12622, 'loss/train': 1.8399444818496704} 08/30/2021 15:24:03 - INFO - __main__ - Step 12624: {'lr': 0.0004936709332905923, 'samples': 2423808, 'steps': 12623, 'loss/train': 2.204284429550171} 08/30/2021 15:24:03 - INFO - __main__ - Step 12625: {'lr': 0.0004936697467110248, 'samples': 2424000, 'steps': 12624, 'loss/train': 1.6818745136260986} 08/30/2021 15:24:03 - INFO - __main__ - Step 12626: {'lr': 0.0004936685600216635, 'samples': 2424192, 'steps': 12625, 'loss/train': 1.5752936601638794} 08/30/2021 15:24:04 - INFO - __main__ - Step 12627: {'lr': 0.0004936673732225088, 'samples': 2424384, 'steps': 12626, 'loss/train': 1.9554191827774048} 08/30/2021 15:24:04 - INFO - __main__ - Step 12628: {'lr': 0.0004936661863135615, 'samples': 2424576, 'steps': 12627, 'loss/train': 1.9483890533447266} 08/30/2021 15:24:04 - INFO - __main__ - Step 12629: {'lr': 0.000493664999294822, 'samples': 2424768, 'steps': 12628, 'loss/train': 1.863869309425354} 08/30/2021 15:24:06 - INFO - __main__ - Step 12630: {'lr': 0.0004936638121662908, 'samples': 2424960, 'steps': 12629, 'loss/train': 1.722177505493164} 08/30/2021 15:24:07 - INFO - __main__ - Step 12631: {'lr': 0.0004936626249279683, 'samples': 2425152, 'steps': 12630, 'loss/train': 0.61997389793396} 08/30/2021 15:24:07 - INFO - __main__ - Step 12632: {'lr': 0.0004936614375798553, 'samples': 2425344, 'steps': 12631, 'loss/train': 1.797813892364502} 08/30/2021 15:24:07 - INFO - __main__ - Step 12633: {'lr': 0.0004936602501219522, 'samples': 2425536, 'steps': 12632, 'loss/train': 1.9456511735916138} 08/30/2021 15:24:08 - INFO - __main__ - Step 12634: {'lr': 0.0004936590625542595, 'samples': 2425728, 'steps': 12633, 'loss/train': 1.688139796257019} 08/30/2021 15:24:10 - INFO - __main__ - Step 12635: {'lr': 0.0004936578748767779, 'samples': 2425920, 'steps': 12634, 'loss/train': 1.8951882123947144} 08/30/2021 15:24:10 - INFO - __main__ - Step 12636: {'lr': 0.0004936566870895078, 'samples': 2426112, 'steps': 12635, 'loss/train': 1.5163230895996094} 08/30/2021 15:24:11 - INFO - __main__ - Step 12637: {'lr': 0.0004936554991924496, 'samples': 2426304, 'steps': 12636, 'loss/train': 1.1690499782562256} 08/30/2021 15:24:11 - INFO - __main__ - Step 12638: {'lr': 0.0004936543111856041, 'samples': 2426496, 'steps': 12637, 'loss/train': 1.6015605926513672} 08/30/2021 15:24:11 - INFO - __main__ - Step 12639: {'lr': 0.0004936531230689717, 'samples': 2426688, 'steps': 12638, 'loss/train': 1.7503412961959839} 08/30/2021 15:24:13 - INFO - __main__ - Step 12640: {'lr': 0.000493651934842553, 'samples': 2426880, 'steps': 12639, 'loss/train': 1.9404630661010742} 08/30/2021 15:24:13 - INFO - __main__ - Step 12641: {'lr': 0.0004936507465063486, 'samples': 2427072, 'steps': 12640, 'loss/train': 1.403029441833496} 08/30/2021 15:24:14 - INFO - __main__ - Step 12642: {'lr': 0.0004936495580603588, 'samples': 2427264, 'steps': 12641, 'loss/train': 1.5929763317108154} 08/30/2021 15:24:14 - INFO - __main__ - Step 12643: {'lr': 0.0004936483695045842, 'samples': 2427456, 'steps': 12642, 'loss/train': 0.18132981657981873} 08/30/2021 15:24:15 - INFO - __main__ - Step 12644: {'lr': 0.0004936471808390254, 'samples': 2427648, 'steps': 12643, 'loss/train': 0.9389256834983826} 08/30/2021 15:24:15 - INFO - __main__ - Step 12645: {'lr': 0.0004936459920636832, 'samples': 2427840, 'steps': 12644, 'loss/train': 1.2691066265106201} 08/30/2021 15:24:16 - INFO - __main__ - Step 12646: {'lr': 0.0004936448031785576, 'samples': 2428032, 'steps': 12645, 'loss/train': 1.7338886260986328} 08/30/2021 15:24:17 - INFO - __main__ - Step 12647: {'lr': 0.0004936436141836496, 'samples': 2428224, 'steps': 12646, 'loss/train': 1.61439049243927} 08/30/2021 15:24:17 - INFO - __main__ - Step 12648: {'lr': 0.0004936424250789594, 'samples': 2428416, 'steps': 12647, 'loss/train': 2.189393997192383} 08/30/2021 15:24:18 - INFO - __main__ - Step 12649: {'lr': 0.0004936412358644878, 'samples': 2428608, 'steps': 12648, 'loss/train': 1.6907033920288086} 08/30/2021 15:24:18 - INFO - __main__ - Step 12650: {'lr': 0.0004936400465402351, 'samples': 2428800, 'steps': 12649, 'loss/train': 2.043912649154663} 08/30/2021 15:24:20 - INFO - __main__ - Step 12651: {'lr': 0.0004936388571062021, 'samples': 2428992, 'steps': 12650, 'loss/train': 2.0402636528015137} 08/30/2021 15:24:21 - INFO - __main__ - Step 12652: {'lr': 0.0004936376675623892, 'samples': 2429184, 'steps': 12651, 'loss/train': 1.9127482175827026} 08/30/2021 15:24:21 - INFO - __main__ - Step 12653: {'lr': 0.0004936364779087967, 'samples': 2429376, 'steps': 12652, 'loss/train': 0.11245076358318329} 08/30/2021 15:24:21 - INFO - __main__ - Step 12654: {'lr': 0.0004936352881454256, 'samples': 2429568, 'steps': 12653, 'loss/train': 0.10869347304105759} 08/30/2021 15:24:22 - INFO - __main__ - Step 12655: {'lr': 0.000493634098272276, 'samples': 2429760, 'steps': 12654, 'loss/train': 1.4098806381225586} 08/30/2021 15:24:22 - INFO - __main__ - Step 12656: {'lr': 0.0004936329082893488, 'samples': 2429952, 'steps': 12655, 'loss/train': 1.5289244651794434} 08/30/2021 15:24:22 - INFO - __main__ - Step 12657: {'lr': 0.0004936317181966443, 'samples': 2430144, 'steps': 12656, 'loss/train': 1.7236436605453491} 08/30/2021 15:24:24 - INFO - __main__ - Step 12658: {'lr': 0.000493630527994163, 'samples': 2430336, 'steps': 12657, 'loss/train': 1.7598484754562378} 08/30/2021 15:24:24 - INFO - __main__ - Step 12659: {'lr': 0.0004936293376819058, 'samples': 2430528, 'steps': 12658, 'loss/train': 1.7739248275756836} 08/30/2021 15:24:25 - INFO - __main__ - Step 12660: {'lr': 0.0004936281472598728, 'samples': 2430720, 'steps': 12659, 'loss/train': 1.8535062074661255} 08/30/2021 15:24:25 - INFO - __main__ - Step 12661: {'lr': 0.0004936269567280648, 'samples': 2430912, 'steps': 12660, 'loss/train': 1.5991106033325195} 08/30/2021 15:24:25 - INFO - __main__ - Step 12662: {'lr': 0.0004936257660864822, 'samples': 2431104, 'steps': 12661, 'loss/train': 1.926518201828003} 08/30/2021 15:24:27 - INFO - __main__ - Step 12663: {'lr': 0.0004936245753351256, 'samples': 2431296, 'steps': 12662, 'loss/train': 1.5261632204055786} 08/30/2021 15:24:27 - INFO - __main__ - Step 12664: {'lr': 0.0004936233844739955, 'samples': 2431488, 'steps': 12663, 'loss/train': 1.7146270275115967} 08/30/2021 15:24:28 - INFO - __main__ - Step 12665: {'lr': 0.0004936221935030924, 'samples': 2431680, 'steps': 12664, 'loss/train': 1.2206121683120728} 08/30/2021 15:24:28 - INFO - __main__ - Step 12666: {'lr': 0.000493621002422417, 'samples': 2431872, 'steps': 12665, 'loss/train': 0.9639013409614563} 08/30/2021 15:24:28 - INFO - __main__ - Step 12667: {'lr': 0.0004936198112319698, 'samples': 2432064, 'steps': 12666, 'loss/train': 2.054918050765991} 08/30/2021 15:24:30 - INFO - __main__ - Step 12668: {'lr': 0.0004936186199317511, 'samples': 2432256, 'steps': 12667, 'loss/train': 1.744736909866333} 08/30/2021 15:24:30 - INFO - __main__ - Step 12669: {'lr': 0.0004936174285217618, 'samples': 2432448, 'steps': 12668, 'loss/train': 1.7439709901809692} 08/30/2021 15:24:31 - INFO - __main__ - Step 12670: {'lr': 0.0004936162370020021, 'samples': 2432640, 'steps': 12669, 'loss/train': 1.9177600145339966} 08/30/2021 15:24:31 - INFO - __main__ - Step 12671: {'lr': 0.0004936150453724727, 'samples': 2432832, 'steps': 12670, 'loss/train': 1.896408200263977} 08/30/2021 15:24:31 - INFO - __main__ - Step 12672: {'lr': 0.0004936138536331742, 'samples': 2433024, 'steps': 12671, 'loss/train': 2.183018207550049} 08/30/2021 15:24:33 - INFO - __main__ - Step 12673: {'lr': 0.000493612661784107, 'samples': 2433216, 'steps': 12672, 'loss/train': 1.9232347011566162} 08/30/2021 15:24:34 - INFO - __main__ - Step 12674: {'lr': 0.0004936114698252717, 'samples': 2433408, 'steps': 12673, 'loss/train': 0.4394769072532654} 08/30/2021 15:24:34 - INFO - __main__ - Step 12675: {'lr': 0.0004936102777566688, 'samples': 2433600, 'steps': 12674, 'loss/train': 1.6537195444107056} 08/30/2021 15:24:34 - INFO - __main__ - Step 12676: {'lr': 0.0004936090855782989, 'samples': 2433792, 'steps': 12675, 'loss/train': 1.8253090381622314} 08/30/2021 15:24:35 - INFO - __main__ - Step 12677: {'lr': 0.0004936078932901625, 'samples': 2433984, 'steps': 12676, 'loss/train': 1.7961907386779785} 08/30/2021 15:24:36 - INFO - __main__ - Step 12678: {'lr': 0.0004936067008922602, 'samples': 2434176, 'steps': 12677, 'loss/train': 1.5258166790008545} 08/30/2021 15:24:37 - INFO - __main__ - Step 12679: {'lr': 0.0004936055083845924, 'samples': 2434368, 'steps': 12678, 'loss/train': 1.9338176250457764} 08/30/2021 15:24:37 - INFO - __main__ - Step 12680: {'lr': 0.0004936043157671597, 'samples': 2434560, 'steps': 12679, 'loss/train': 1.5246820449829102} 08/30/2021 15:24:37 - INFO - __main__ - Step 12681: {'lr': 0.0004936031230399628, 'samples': 2434752, 'steps': 12680, 'loss/train': 2.037579298019409} 08/30/2021 15:24:38 - INFO - __main__ - Step 12682: {'lr': 0.000493601930203002, 'samples': 2434944, 'steps': 12681, 'loss/train': 1.7349222898483276} 08/30/2021 15:24:38 - INFO - __main__ - Step 12683: {'lr': 0.0004936007372562778, 'samples': 2435136, 'steps': 12682, 'loss/train': 1.0998066663742065} 08/30/2021 15:24:40 - INFO - __main__ - Step 12684: {'lr': 0.0004935995441997911, 'samples': 2435328, 'steps': 12683, 'loss/train': 2.121187210083008} 08/30/2021 15:24:40 - INFO - __main__ - Step 12685: {'lr': 0.000493598351033542, 'samples': 2435520, 'steps': 12684, 'loss/train': 1.8788855075836182} 08/30/2021 15:24:40 - INFO - __main__ - Step 12686: {'lr': 0.0004935971577575313, 'samples': 2435712, 'steps': 12685, 'loss/train': 2.2197322845458984} 08/30/2021 15:24:41 - INFO - __main__ - Step 12687: {'lr': 0.0004935959643717595, 'samples': 2435904, 'steps': 12686, 'loss/train': 1.721380591392517} 08/30/2021 15:24:41 - INFO - __main__ - Step 12688: {'lr': 0.0004935947708762272, 'samples': 2436096, 'steps': 12687, 'loss/train': 2.050400733947754} 08/30/2021 15:24:43 - INFO - __main__ - Step 12689: {'lr': 0.0004935935772709348, 'samples': 2436288, 'steps': 12688, 'loss/train': 1.7758708000183105} 08/30/2021 15:24:43 - INFO - __main__ - Step 12690: {'lr': 0.0004935923835558829, 'samples': 2436480, 'steps': 12689, 'loss/train': 1.0109050273895264} 08/30/2021 15:24:44 - INFO - __main__ - Step 12691: {'lr': 0.0004935911897310719, 'samples': 2436672, 'steps': 12690, 'loss/train': 1.314550518989563} 08/30/2021 15:24:44 - INFO - __main__ - Step 12692: {'lr': 0.0004935899957965027, 'samples': 2436864, 'steps': 12691, 'loss/train': 1.9543402194976807} 08/30/2021 15:24:44 - INFO - __main__ - Step 12693: {'lr': 0.0004935888017521754, 'samples': 2437056, 'steps': 12692, 'loss/train': 1.5407357215881348} 08/30/2021 15:24:46 - INFO - __main__ - Step 12694: {'lr': 0.0004935876075980908, 'samples': 2437248, 'steps': 12693, 'loss/train': 1.6913949251174927} 08/30/2021 15:24:47 - INFO - __main__ - Step 12695: {'lr': 0.0004935864133342495, 'samples': 2437440, 'steps': 12694, 'loss/train': 1.5512062311172485} 08/30/2021 15:24:47 - INFO - __main__ - Step 12696: {'lr': 0.0004935852189606517, 'samples': 2437632, 'steps': 12695, 'loss/train': 1.8069430589675903} 08/30/2021 15:24:48 - INFO - __main__ - Step 12697: {'lr': 0.0004935840244772984, 'samples': 2437824, 'steps': 12696, 'loss/train': 1.825741171836853} 08/30/2021 15:24:48 - INFO - __main__ - Step 12698: {'lr': 0.0004935828298841898, 'samples': 2438016, 'steps': 12697, 'loss/train': 1.56669020652771} 08/30/2021 15:24:49 - INFO - __main__ - Step 12699: {'lr': 0.0004935816351813265, 'samples': 2438208, 'steps': 12698, 'loss/train': 1.4825313091278076} 08/30/2021 15:24:50 - INFO - __main__ - Step 12700: {'lr': 0.0004935804403687091, 'samples': 2438400, 'steps': 12699, 'loss/train': 1.686589002609253} 08/30/2021 15:24:50 - INFO - __main__ - Step 12701: {'lr': 0.0004935792454463381, 'samples': 2438592, 'steps': 12700, 'loss/train': 1.9009692668914795} 08/30/2021 15:24:51 - INFO - __main__ - Step 12702: {'lr': 0.000493578050414214, 'samples': 2438784, 'steps': 12701, 'loss/train': 0.9109597206115723} 08/30/2021 15:24:51 - INFO - __main__ - Step 12703: {'lr': 0.0004935768552723375, 'samples': 2438976, 'steps': 12702, 'loss/train': 1.5171445608139038} 08/30/2021 15:24:52 - INFO - __main__ - Step 12704: {'lr': 0.000493575660020709, 'samples': 2439168, 'steps': 12703, 'loss/train': 1.1090315580368042} 08/30/2021 15:24:53 - INFO - __main__ - Step 12705: {'lr': 0.000493574464659329, 'samples': 2439360, 'steps': 12704, 'loss/train': 1.2787632942199707} 08/30/2021 15:24:53 - INFO - __main__ - Step 12706: {'lr': 0.0004935732691881981, 'samples': 2439552, 'steps': 12705, 'loss/train': 1.6112338304519653} 08/30/2021 15:24:54 - INFO - __main__ - Step 12707: {'lr': 0.0004935720736073169, 'samples': 2439744, 'steps': 12706, 'loss/train': 1.8073229789733887} 08/30/2021 15:24:54 - INFO - __main__ - Step 12708: {'lr': 0.0004935708779166859, 'samples': 2439936, 'steps': 12707, 'loss/train': 1.8363302946090698} 08/30/2021 15:24:56 - INFO - __main__ - Step 12709: {'lr': 0.0004935696821163056, 'samples': 2440128, 'steps': 12708, 'loss/train': 1.8159846067428589} 08/30/2021 15:24:57 - INFO - __main__ - Step 12710: {'lr': 0.0004935684862061766, 'samples': 2440320, 'steps': 12709, 'loss/train': 1.759819746017456} 08/30/2021 15:24:57 - INFO - __main__ - Step 12711: {'lr': 0.0004935672901862993, 'samples': 2440512, 'steps': 12710, 'loss/train': 2.3868110179901123} 08/30/2021 15:24:57 - INFO - __main__ - Step 12712: {'lr': 0.0004935660940566744, 'samples': 2440704, 'steps': 12711, 'loss/train': 1.9664065837860107} 08/30/2021 15:24:58 - INFO - __main__ - Step 12713: {'lr': 0.0004935648978173024, 'samples': 2440896, 'steps': 12712, 'loss/train': 2.251214027404785} 08/30/2021 15:24:58 - INFO - __main__ - Step 12714: {'lr': 0.0004935637014681837, 'samples': 2441088, 'steps': 12713, 'loss/train': 1.8730881214141846} 08/30/2021 15:25:00 - INFO - __main__ - Step 12715: {'lr': 0.0004935625050093191, 'samples': 2441280, 'steps': 12714, 'loss/train': 2.399866819381714} 08/30/2021 15:25:00 - INFO - __main__ - Step 12716: {'lr': 0.000493561308440709, 'samples': 2441472, 'steps': 12715, 'loss/train': 1.6971989870071411} 08/30/2021 15:25:00 - INFO - __main__ - Step 12717: {'lr': 0.0004935601117623538, 'samples': 2441664, 'steps': 12716, 'loss/train': 2.003096580505371} 08/30/2021 15:25:01 - INFO - __main__ - Step 12718: {'lr': 0.0004935589149742542, 'samples': 2441856, 'steps': 12717, 'loss/train': 2.3252768516540527} 08/30/2021 15:25:01 - INFO - __main__ - Step 12719: {'lr': 0.0004935577180764108, 'samples': 2442048, 'steps': 12718, 'loss/train': 1.8923490047454834} 08/30/2021 15:25:04 - INFO - __main__ - Step 12720: {'lr': 0.000493556521068824, 'samples': 2442240, 'steps': 12719, 'loss/train': 2.1121156215667725} 08/30/2021 15:25:04 - INFO - __main__ - Step 12721: {'lr': 0.0004935553239514943, 'samples': 2442432, 'steps': 12720, 'loss/train': 1.3137507438659668} 08/30/2021 15:25:04 - INFO - __main__ - Step 12722: {'lr': 0.0004935541267244225, 'samples': 2442624, 'steps': 12721, 'loss/train': 1.5639243125915527} 08/30/2021 15:25:05 - INFO - __main__ - Step 12723: {'lr': 0.0004935529293876088, 'samples': 2442816, 'steps': 12722, 'loss/train': 1.3681550025939941} 08/30/2021 15:25:05 - INFO - __main__ - Step 12724: {'lr': 0.000493551731941054, 'samples': 2443008, 'steps': 12723, 'loss/train': 2.215101718902588} 08/30/2021 15:25:05 - INFO - __main__ - Step 12725: {'lr': 0.0004935505343847586, 'samples': 2443200, 'steps': 12724, 'loss/train': 0.5666799545288086} 08/30/2021 15:25:06 - INFO - __main__ - Step 12726: {'lr': 0.000493549336718723, 'samples': 2443392, 'steps': 12725, 'loss/train': 1.3400561809539795} 08/30/2021 15:25:08 - INFO - __main__ - Step 12727: {'lr': 0.0004935481389429479, 'samples': 2443584, 'steps': 12726, 'loss/train': 3.0213704109191895} 08/30/2021 15:25:08 - INFO - __main__ - Step 12728: {'lr': 0.0004935469410574337, 'samples': 2443776, 'steps': 12727, 'loss/train': 2.337177038192749} 08/30/2021 15:25:09 - INFO - __main__ - Step 12729: {'lr': 0.000493545743062181, 'samples': 2443968, 'steps': 12728, 'loss/train': 2.118790864944458} 08/30/2021 15:25:09 - INFO - __main__ - Step 12730: {'lr': 0.0004935445449571903, 'samples': 2444160, 'steps': 12729, 'loss/train': 0.36622175574302673} 08/30/2021 15:25:09 - INFO - __main__ - Step 12731: {'lr': 0.0004935433467424624, 'samples': 2444352, 'steps': 12730, 'loss/train': 2.5760347843170166} 08/30/2021 15:25:10 - INFO - __main__ - Step 12732: {'lr': 0.0004935421484179974, 'samples': 2444544, 'steps': 12731, 'loss/train': 1.9112876653671265} 08/30/2021 15:25:11 - INFO - __main__ - Step 12733: {'lr': 0.0004935409499837962, 'samples': 2444736, 'steps': 12732, 'loss/train': 0.34345391392707825} 08/30/2021 15:25:12 - INFO - __main__ - Step 12734: {'lr': 0.0004935397514398591, 'samples': 2444928, 'steps': 12733, 'loss/train': 2.2672271728515625} 08/30/2021 15:25:12 - INFO - __main__ - Step 12735: {'lr': 0.0004935385527861869, 'samples': 2445120, 'steps': 12734, 'loss/train': 2.1733508110046387} 08/30/2021 15:25:12 - INFO - __main__ - Step 12736: {'lr': 0.0004935373540227798, 'samples': 2445312, 'steps': 12735, 'loss/train': 1.9029417037963867} 08/30/2021 15:25:13 - INFO - __main__ - Step 12737: {'lr': 0.0004935361551496387, 'samples': 2445504, 'steps': 12736, 'loss/train': 2.114182472229004} 08/30/2021 15:25:14 - INFO - __main__ - Step 12738: {'lr': 0.0004935349561667638, 'samples': 2445696, 'steps': 12737, 'loss/train': 2.133676290512085} 08/30/2021 15:25:15 - INFO - __main__ - Step 12739: {'lr': 0.000493533757074156, 'samples': 2445888, 'steps': 12738, 'loss/train': 5.65504789352417} 08/30/2021 15:25:15 - INFO - __main__ - Step 12740: {'lr': 0.0004935325578718155, 'samples': 2446080, 'steps': 12739, 'loss/train': 2.1850454807281494} 08/30/2021 15:25:15 - INFO - __main__ - Step 12741: {'lr': 0.000493531358559743, 'samples': 2446272, 'steps': 12740, 'loss/train': 1.9255011081695557} 08/30/2021 15:25:16 - INFO - __main__ - Step 12742: {'lr': 0.0004935301591379391, 'samples': 2446464, 'steps': 12741, 'loss/train': 1.9801987409591675} 08/30/2021 15:25:17 - INFO - __main__ - Step 12743: {'lr': 0.0004935289596064042, 'samples': 2446656, 'steps': 12742, 'loss/train': 0.8448387980461121} 08/30/2021 15:25:17 - INFO - __main__ - Step 12744: {'lr': 0.0004935277599651389, 'samples': 2446848, 'steps': 12743, 'loss/train': 3.033478021621704} 08/30/2021 15:25:18 - INFO - __main__ - Step 12745: {'lr': 0.0004935265602141437, 'samples': 2447040, 'steps': 12744, 'loss/train': 1.927393913269043} 08/30/2021 15:25:18 - INFO - __main__ - Step 12746: {'lr': 0.0004935253603534193, 'samples': 2447232, 'steps': 12745, 'loss/train': 1.9398053884506226} 08/30/2021 15:25:19 - INFO - __main__ - Step 12747: {'lr': 0.0004935241603829661, 'samples': 2447424, 'steps': 12746, 'loss/train': 1.4622310400009155} 08/30/2021 15:25:21 - INFO - __main__ - Step 12748: {'lr': 0.0004935229603027847, 'samples': 2447616, 'steps': 12747, 'loss/train': 2.3264105319976807} 08/30/2021 15:25:21 - INFO - __main__ - Step 12749: {'lr': 0.0004935217601128755, 'samples': 2447808, 'steps': 12748, 'loss/train': 2.2108681201934814} 08/30/2021 15:25:22 - INFO - __main__ - Step 12750: {'lr': 0.0004935205598132393, 'samples': 2448000, 'steps': 12749, 'loss/train': 2.0789570808410645} 08/30/2021 15:25:22 - INFO - __main__ - Step 12751: {'lr': 0.0004935193594038764, 'samples': 2448192, 'steps': 12750, 'loss/train': 1.9540125131607056} 08/30/2021 15:25:22 - INFO - __main__ - Step 12752: {'lr': 0.0004935181588847876, 'samples': 2448384, 'steps': 12751, 'loss/train': 1.6292519569396973} 08/30/2021 15:25:24 - INFO - __main__ - Step 12753: {'lr': 0.0004935169582559731, 'samples': 2448576, 'steps': 12752, 'loss/train': 2.6580960750579834} 08/30/2021 15:25:24 - INFO - __main__ - Step 12754: {'lr': 0.0004935157575174336, 'samples': 2448768, 'steps': 12753, 'loss/train': 1.4992064237594604} 08/30/2021 15:25:24 - INFO - __main__ - Step 12755: {'lr': 0.0004935145566691698, 'samples': 2448960, 'steps': 12754, 'loss/train': 1.9568040370941162} 08/30/2021 15:25:25 - INFO - __main__ - Step 12756: {'lr': 0.000493513355711182, 'samples': 2449152, 'steps': 12755, 'loss/train': 1.905815601348877} 08/30/2021 15:25:25 - INFO - __main__ - Step 12757: {'lr': 0.0004935121546434708, 'samples': 2449344, 'steps': 12756, 'loss/train': 1.869763970375061} 08/30/2021 15:25:25 - INFO - __main__ - Step 12758: {'lr': 0.0004935109534660368, 'samples': 2449536, 'steps': 12757, 'loss/train': 2.1079020500183105} 08/30/2021 15:25:27 - INFO - __main__ - Step 12759: {'lr': 0.0004935097521788805, 'samples': 2449728, 'steps': 12758, 'loss/train': 1.1101970672607422} 08/30/2021 15:25:27 - INFO - __main__ - Step 12760: {'lr': 0.0004935085507820026, 'samples': 2449920, 'steps': 12759, 'loss/train': 1.996029019355774} 08/30/2021 15:25:28 - INFO - __main__ - Step 12761: {'lr': 0.0004935073492754034, 'samples': 2450112, 'steps': 12760, 'loss/train': 1.956479787826538} 08/30/2021 15:25:28 - INFO - __main__ - Step 12762: {'lr': 0.0004935061476590835, 'samples': 2450304, 'steps': 12761, 'loss/train': 2.4640419483184814} 08/30/2021 15:25:29 - INFO - __main__ - Step 12763: {'lr': 0.0004935049459330437, 'samples': 2450496, 'steps': 12762, 'loss/train': 2.0030322074890137} 08/30/2021 15:25:30 - INFO - __main__ - Step 12764: {'lr': 0.0004935037440972841, 'samples': 2450688, 'steps': 12763, 'loss/train': 1.5955910682678223} 08/30/2021 15:25:30 - INFO - __main__ - Step 12765: {'lr': 0.0004935025421518056, 'samples': 2450880, 'steps': 12764, 'loss/train': 1.809960961341858} 08/30/2021 15:25:31 - INFO - __main__ - Step 12766: {'lr': 0.0004935013400966086, 'samples': 2451072, 'steps': 12765, 'loss/train': 1.6778466701507568} 08/30/2021 15:25:31 - INFO - __main__ - Step 12767: {'lr': 0.0004935001379316935, 'samples': 2451264, 'steps': 12766, 'loss/train': 1.922008752822876} 08/30/2021 15:25:31 - INFO - __main__ - Step 12768: {'lr': 0.0004934989356570611, 'samples': 2451456, 'steps': 12767, 'loss/train': 2.5410382747650146} 08/30/2021 15:25:33 - INFO - __main__ - Step 12769: {'lr': 0.0004934977332727118, 'samples': 2451648, 'steps': 12768, 'loss/train': 2.064488410949707} 08/30/2021 15:25:33 - INFO - __main__ - Step 12770: {'lr': 0.0004934965307786464, 'samples': 2451840, 'steps': 12769, 'loss/train': 1.5209386348724365} 08/30/2021 15:25:34 - INFO - __main__ - Step 12771: {'lr': 0.0004934953281748649, 'samples': 2452032, 'steps': 12770, 'loss/train': 1.9649244546890259} 08/30/2021 15:25:34 - INFO - __main__ - Step 12772: {'lr': 0.0004934941254613684, 'samples': 2452224, 'steps': 12771, 'loss/train': 1.8762067556381226} 08/30/2021 15:25:35 - INFO - __main__ - Step 12773: {'lr': 0.0004934929226381572, 'samples': 2452416, 'steps': 12772, 'loss/train': 1.9542076587677002} 08/30/2021 15:25:36 - INFO - __main__ - Step 12774: {'lr': 0.0004934917197052317, 'samples': 2452608, 'steps': 12773, 'loss/train': 1.2381634712219238} 08/30/2021 15:25:37 - INFO - __main__ - Step 12775: {'lr': 0.0004934905166625926, 'samples': 2452800, 'steps': 12774, 'loss/train': 1.5721044540405273} 08/30/2021 15:25:37 - INFO - __main__ - Step 12776: {'lr': 0.0004934893135102405, 'samples': 2452992, 'steps': 12775, 'loss/train': 2.069021224975586} 08/30/2021 15:25:37 - INFO - __main__ - Step 12777: {'lr': 0.0004934881102481759, 'samples': 2453184, 'steps': 12776, 'loss/train': 1.5824388265609741} 08/30/2021 15:25:38 - INFO - __main__ - Step 12778: {'lr': 0.0004934869068763992, 'samples': 2453376, 'steps': 12777, 'loss/train': 1.8608088493347168} 08/30/2021 15:25:38 - INFO - __main__ - Step 12779: {'lr': 0.0004934857033949112, 'samples': 2453568, 'steps': 12778, 'loss/train': 1.4795398712158203} 08/30/2021 15:25:40 - INFO - __main__ - Step 12780: {'lr': 0.0004934844998037122, 'samples': 2453760, 'steps': 12779, 'loss/train': 0.2948019802570343} 08/30/2021 15:25:40 - INFO - __main__ - Step 12781: {'lr': 0.0004934832961028028, 'samples': 2453952, 'steps': 12780, 'loss/train': 2.3595540523529053} 08/30/2021 15:25:40 - INFO - __main__ - Step 12782: {'lr': 0.0004934820922921836, 'samples': 2454144, 'steps': 12781, 'loss/train': 1.6248605251312256} 08/30/2021 15:25:41 - INFO - __main__ - Step 12783: {'lr': 0.0004934808883718553, 'samples': 2454336, 'steps': 12782, 'loss/train': 1.213696837425232} 08/30/2021 15:25:41 - INFO - __main__ - Step 12784: {'lr': 0.0004934796843418181, 'samples': 2454528, 'steps': 12783, 'loss/train': 2.4891302585601807} 08/30/2021 15:25:43 - INFO - __main__ - Step 12785: {'lr': 0.0004934784802020728, 'samples': 2454720, 'steps': 12784, 'loss/train': 1.2858890295028687} 08/30/2021 15:25:43 - INFO - __main__ - Step 12786: {'lr': 0.0004934772759526198, 'samples': 2454912, 'steps': 12785, 'loss/train': 0.19185945391654968} 08/30/2021 15:25:44 - INFO - __main__ - Step 12787: {'lr': 0.0004934760715934597, 'samples': 2455104, 'steps': 12786, 'loss/train': 1.5422052145004272} 08/30/2021 15:25:44 - INFO - __main__ - Step 12788: {'lr': 0.0004934748671245931, 'samples': 2455296, 'steps': 12787, 'loss/train': 1.79157292842865} 08/30/2021 15:25:44 - INFO - __main__ - Step 12789: {'lr': 0.0004934736625460203, 'samples': 2455488, 'steps': 12788, 'loss/train': 1.1268810033798218} 08/30/2021 15:25:45 - INFO - __main__ - Step 12790: {'lr': 0.0004934724578577422, 'samples': 2455680, 'steps': 12789, 'loss/train': 1.5829182863235474} 08/30/2021 15:25:46 - INFO - __main__ - Step 12791: {'lr': 0.0004934712530597591, 'samples': 2455872, 'steps': 12790, 'loss/train': 1.360123872756958} 08/30/2021 15:25:47 - INFO - __main__ - Step 12792: {'lr': 0.0004934700481520717, 'samples': 2456064, 'steps': 12791, 'loss/train': 1.7475991249084473} 08/30/2021 15:25:47 - INFO - __main__ - Step 12793: {'lr': 0.0004934688431346804, 'samples': 2456256, 'steps': 12792, 'loss/train': 1.7553184032440186} 08/30/2021 15:25:48 - INFO - __main__ - Step 12794: {'lr': 0.0004934676380075857, 'samples': 2456448, 'steps': 12793, 'loss/train': 1.767801284790039} 08/30/2021 15:25:48 - INFO - __main__ - Step 12795: {'lr': 0.0004934664327707884, 'samples': 2456640, 'steps': 12794, 'loss/train': 1.4440882205963135} 08/30/2021 15:25:49 - INFO - __main__ - Step 12796: {'lr': 0.0004934652274242888, 'samples': 2456832, 'steps': 12795, 'loss/train': 2.174332857131958} 08/30/2021 15:25:50 - INFO - __main__ - Step 12797: {'lr': 0.0004934640219680875, 'samples': 2457024, 'steps': 12796, 'loss/train': 1.8413528203964233} 08/30/2021 15:25:50 - INFO - __main__ - Step 12798: {'lr': 0.0004934628164021851, 'samples': 2457216, 'steps': 12797, 'loss/train': 2.294133424758911} 08/30/2021 15:25:51 - INFO - __main__ - Step 12799: {'lr': 0.0004934616107265821, 'samples': 2457408, 'steps': 12798, 'loss/train': 2.405320882797241} 08/30/2021 15:25:51 - INFO - __main__ - Step 12800: {'lr': 0.0004934604049412791, 'samples': 2457600, 'steps': 12799, 'loss/train': 2.5989420413970947} 08/30/2021 15:25:53 - INFO - __main__ - Step 12801: {'lr': 0.0004934591990462766, 'samples': 2457792, 'steps': 12800, 'loss/train': 1.8813281059265137} 08/30/2021 15:25:53 - INFO - __main__ - Step 12802: {'lr': 0.0004934579930415751, 'samples': 2457984, 'steps': 12801, 'loss/train': 2.196131944656372} 08/30/2021 15:25:53 - INFO - __main__ - Step 12803: {'lr': 0.0004934567869271751, 'samples': 2458176, 'steps': 12802, 'loss/train': 1.6211522817611694} 08/30/2021 15:25:54 - INFO - __main__ - Step 12804: {'lr': 0.0004934555807030774, 'samples': 2458368, 'steps': 12803, 'loss/train': 2.0689356327056885} 08/30/2021 15:25:54 - INFO - __main__ - Step 12805: {'lr': 0.0004934543743692822, 'samples': 2458560, 'steps': 12804, 'loss/train': 1.8443782329559326} 08/30/2021 15:25:57 - INFO - __main__ - Step 12806: {'lr': 0.0004934531679257903, 'samples': 2458752, 'steps': 12805, 'loss/train': 1.8418288230895996} 08/30/2021 15:25:57 - INFO - __main__ - Step 12807: {'lr': 0.0004934519613726022, 'samples': 2458944, 'steps': 12806, 'loss/train': 1.5568180084228516} 08/30/2021 15:25:58 - INFO - __main__ - Step 12808: {'lr': 0.0004934507547097183, 'samples': 2459136, 'steps': 12807, 'loss/train': 1.6972455978393555} 08/30/2021 15:25:58 - INFO - __main__ - Step 12809: {'lr': 0.0004934495479371393, 'samples': 2459328, 'steps': 12808, 'loss/train': 1.9759559631347656} 08/30/2021 15:25:58 - INFO - __main__ - Step 12810: {'lr': 0.0004934483410548658, 'samples': 2459520, 'steps': 12809, 'loss/train': 1.7882384061813354} 08/30/2021 15:25:59 - INFO - __main__ - Step 12811: {'lr': 0.0004934471340628981, 'samples': 2459712, 'steps': 12810, 'loss/train': 1.5598998069763184} 08/30/2021 15:26:00 - INFO - __main__ - Step 12812: {'lr': 0.000493445926961237, 'samples': 2459904, 'steps': 12811, 'loss/train': 2.299872398376465} 08/30/2021 15:26:01 - INFO - __main__ - Step 12813: {'lr': 0.0004934447197498828, 'samples': 2460096, 'steps': 12812, 'loss/train': 1.3567181825637817} 08/30/2021 15:26:01 - INFO - __main__ - Step 12814: {'lr': 0.0004934435124288362, 'samples': 2460288, 'steps': 12813, 'loss/train': 1.9463375806808472} 08/30/2021 15:26:02 - INFO - __main__ - Step 12815: {'lr': 0.0004934423049980977, 'samples': 2460480, 'steps': 12814, 'loss/train': 2.5686609745025635} 08/30/2021 15:26:02 - INFO - __main__ - Step 12816: {'lr': 0.0004934410974576679, 'samples': 2460672, 'steps': 12815, 'loss/train': 2.101588487625122} 08/30/2021 15:26:04 - INFO - __main__ - Step 12817: {'lr': 0.0004934398898075472, 'samples': 2460864, 'steps': 12816, 'loss/train': 1.9919829368591309} 08/30/2021 15:26:04 - INFO - __main__ - Step 12818: {'lr': 0.0004934386820477363, 'samples': 2461056, 'steps': 12817, 'loss/train': 2.2948756217956543} 08/30/2021 15:26:05 - INFO - __main__ - Step 12819: {'lr': 0.0004934374741782357, 'samples': 2461248, 'steps': 12818, 'loss/train': 0.21224519610404968} 08/30/2021 15:26:05 - INFO - __main__ - Step 12820: {'lr': 0.000493436266199046, 'samples': 2461440, 'steps': 12819, 'loss/train': 2.1891863346099854} 08/30/2021 15:26:05 - INFO - __main__ - Step 12821: {'lr': 0.0004934350581101676, 'samples': 2461632, 'steps': 12820, 'loss/train': 2.082596778869629} 08/30/2021 15:26:07 - INFO - __main__ - Step 12822: {'lr': 0.0004934338499116011, 'samples': 2461824, 'steps': 12821, 'loss/train': 2.3154423236846924} 08/30/2021 15:26:08 - INFO - __main__ - Step 12823: {'lr': 0.0004934326416033471, 'samples': 2462016, 'steps': 12822, 'loss/train': 1.5506004095077515} 08/30/2021 15:26:08 - INFO - __main__ - Step 12824: {'lr': 0.0004934314331854061, 'samples': 2462208, 'steps': 12823, 'loss/train': 1.188932180404663} 08/30/2021 15:26:08 - INFO - __main__ - Step 12825: {'lr': 0.0004934302246577786, 'samples': 2462400, 'steps': 12824, 'loss/train': 0.27423277497291565} 08/30/2021 15:26:09 - INFO - __main__ - Step 12826: {'lr': 0.0004934290160204652, 'samples': 2462592, 'steps': 12825, 'loss/train': 0.6592503786087036} 08/30/2021 15:26:09 - INFO - __main__ - Step 12827: {'lr': 0.0004934278072734666, 'samples': 2462784, 'steps': 12826, 'loss/train': 1.895760178565979} 08/30/2021 15:26:11 - INFO - __main__ - Step 12828: {'lr': 0.000493426598416783, 'samples': 2462976, 'steps': 12827, 'loss/train': 1.7769666910171509} 08/30/2021 15:26:11 - INFO - __main__ - Step 12829: {'lr': 0.0004934253894504152, 'samples': 2463168, 'steps': 12828, 'loss/train': 2.225257635116577} 08/30/2021 15:26:11 - INFO - __main__ - Step 12830: {'lr': 0.0004934241803743637, 'samples': 2463360, 'steps': 12829, 'loss/train': 1.3340060710906982} 08/30/2021 15:26:12 - INFO - __main__ - Step 12831: {'lr': 0.000493422971188629, 'samples': 2463552, 'steps': 12830, 'loss/train': 1.8774023056030273} 08/30/2021 15:26:12 - INFO - __main__ - Step 12832: {'lr': 0.0004934217618932117, 'samples': 2463744, 'steps': 12831, 'loss/train': 1.8951119184494019} 08/30/2021 15:26:14 - INFO - __main__ - Step 12833: {'lr': 0.0004934205524881123, 'samples': 2463936, 'steps': 12832, 'loss/train': 1.9925721883773804} 08/30/2021 15:26:14 - INFO - __main__ - Step 12834: {'lr': 0.0004934193429733312, 'samples': 2464128, 'steps': 12833, 'loss/train': 2.1481235027313232} 08/30/2021 15:26:14 - INFO - __main__ - Step 12835: {'lr': 0.0004934181333488693, 'samples': 2464320, 'steps': 12834, 'loss/train': 1.726758360862732} 08/30/2021 15:26:15 - INFO - __main__ - Step 12836: {'lr': 0.0004934169236147268, 'samples': 2464512, 'steps': 12835, 'loss/train': 1.7222379446029663} 08/30/2021 15:26:15 - INFO - __main__ - Step 12837: {'lr': 0.0004934157137709044, 'samples': 2464704, 'steps': 12836, 'loss/train': 2.0570788383483887} 08/30/2021 15:26:15 - INFO - __main__ - Step 12838: {'lr': 0.0004934145038174028, 'samples': 2464896, 'steps': 12837, 'loss/train': 1.9421387910842896} 08/30/2021 15:26:17 - INFO - __main__ - Step 12839: {'lr': 0.0004934132937542223, 'samples': 2465088, 'steps': 12838, 'loss/train': 2.1006321907043457} 08/30/2021 15:26:18 - INFO - __main__ - Step 12840: {'lr': 0.0004934120835813634, 'samples': 2465280, 'steps': 12839, 'loss/train': 1.5314640998840332} 08/30/2021 15:26:18 - INFO - __main__ - Step 12841: {'lr': 0.0004934108732988269, 'samples': 2465472, 'steps': 12840, 'loss/train': 1.9027420282363892} 08/30/2021 15:26:18 - INFO - __main__ - Step 12842: {'lr': 0.0004934096629066133, 'samples': 2465664, 'steps': 12841, 'loss/train': 2.09247088432312} 08/30/2021 15:26:19 - INFO - __main__ - Step 12843: {'lr': 0.0004934084524047229, 'samples': 2465856, 'steps': 12842, 'loss/train': 2.0536134243011475} 08/30/2021 15:26:20 - INFO - __main__ - Step 12844: {'lr': 0.0004934072417931564, 'samples': 2466048, 'steps': 12843, 'loss/train': 2.0693199634552} 08/30/2021 15:26:21 - INFO - __main__ - Step 12845: {'lr': 0.0004934060310719145, 'samples': 2466240, 'steps': 12844, 'loss/train': 1.6274563074111938} 08/30/2021 15:26:21 - INFO - __main__ - Step 12846: {'lr': 0.0004934048202409974, 'samples': 2466432, 'steps': 12845, 'loss/train': 1.8991349935531616} 08/30/2021 15:26:22 - INFO - __main__ - Step 12847: {'lr': 0.000493403609300406, 'samples': 2466624, 'steps': 12846, 'loss/train': 1.8625999689102173} 08/30/2021 15:26:22 - INFO - __main__ - Step 12848: {'lr': 0.0004934023982501406, 'samples': 2466816, 'steps': 12847, 'loss/train': 1.3336262702941895} 08/30/2021 15:26:22 - INFO - __main__ - Step 12849: {'lr': 0.000493401187090202, 'samples': 2467008, 'steps': 12848, 'loss/train': 1.5156720876693726} 08/30/2021 15:26:24 - INFO - __main__ - Step 12850: {'lr': 0.0004933999758205904, 'samples': 2467200, 'steps': 12849, 'loss/train': 2.161287307739258} 08/30/2021 15:26:24 - INFO - __main__ - Step 12851: {'lr': 0.0004933987644413066, 'samples': 2467392, 'steps': 12850, 'loss/train': 2.1711788177490234} 08/30/2021 15:26:24 - INFO - __main__ - Step 12852: {'lr': 0.0004933975529523511, 'samples': 2467584, 'steps': 12851, 'loss/train': 2.485257625579834} 08/30/2021 15:26:25 - INFO - __main__ - Step 12853: {'lr': 0.0004933963413537244, 'samples': 2467776, 'steps': 12852, 'loss/train': 2.2051398754119873} 08/30/2021 15:26:25 - INFO - __main__ - Step 12854: {'lr': 0.000493395129645427, 'samples': 2467968, 'steps': 12853, 'loss/train': 0.40571528673171997} 08/30/2021 15:26:27 - INFO - __main__ - Step 12855: {'lr': 0.0004933939178274596, 'samples': 2468160, 'steps': 12854, 'loss/train': 2.2921669483184814} 08/30/2021 15:26:28 - INFO - __main__ - Step 12856: {'lr': 0.0004933927058998226, 'samples': 2468352, 'steps': 12855, 'loss/train': 0.5320433378219604} 08/30/2021 15:26:28 - INFO - __main__ - Step 12857: {'lr': 0.0004933914938625166, 'samples': 2468544, 'steps': 12856, 'loss/train': 0.6518922448158264} 08/30/2021 15:26:29 - INFO - __main__ - Step 12858: {'lr': 0.0004933902817155422, 'samples': 2468736, 'steps': 12857, 'loss/train': 0.6996716260910034} 08/30/2021 15:26:29 - INFO - __main__ - Step 12859: {'lr': 0.0004933890694588998, 'samples': 2468928, 'steps': 12858, 'loss/train': 2.0849716663360596} 08/30/2021 15:26:29 - INFO - __main__ - Step 12860: {'lr': 0.0004933878570925901, 'samples': 2469120, 'steps': 12859, 'loss/train': 1.9486299753189087} 08/30/2021 15:26:31 - INFO - __main__ - Step 12861: {'lr': 0.0004933866446166136, 'samples': 2469312, 'steps': 12860, 'loss/train': 1.7212613821029663} 08/30/2021 15:26:32 - INFO - __main__ - Step 12862: {'lr': 0.0004933854320309708, 'samples': 2469504, 'steps': 12861, 'loss/train': 1.654227375984192} 08/30/2021 15:26:32 - INFO - __main__ - Step 12863: {'lr': 0.0004933842193356624, 'samples': 2469696, 'steps': 12862, 'loss/train': 2.332019329071045} 08/30/2021 15:26:33 - INFO - __main__ - Step 12864: {'lr': 0.0004933830065306887, 'samples': 2469888, 'steps': 12863, 'loss/train': 1.7721030712127686} 08/30/2021 15:26:33 - INFO - __main__ - Step 12865: {'lr': 0.0004933817936160504, 'samples': 2470080, 'steps': 12864, 'loss/train': 1.8317217826843262} 08/30/2021 15:26:33 - INFO - __main__ - Step 12866: {'lr': 0.0004933805805917479, 'samples': 2470272, 'steps': 12865, 'loss/train': 1.6601803302764893} 08/30/2021 15:26:35 - INFO - __main__ - Step 12867: {'lr': 0.000493379367457782, 'samples': 2470464, 'steps': 12866, 'loss/train': 2.19952130317688} 08/30/2021 15:26:36 - INFO - __main__ - Step 12868: {'lr': 0.0004933781542141532, 'samples': 2470656, 'steps': 12867, 'loss/train': 1.25111722946167} 08/30/2021 15:26:36 - INFO - __main__ - Step 12869: {'lr': 0.0004933769408608618, 'samples': 2470848, 'steps': 12868, 'loss/train': 1.9844472408294678} 08/30/2021 15:26:36 - INFO - __main__ - Step 12870: {'lr': 0.0004933757273979086, 'samples': 2471040, 'steps': 12869, 'loss/train': 1.5841888189315796} 08/30/2021 15:26:37 - INFO - __main__ - Step 12871: {'lr': 0.0004933745138252939, 'samples': 2471232, 'steps': 12870, 'loss/train': 1.4705384969711304} 08/30/2021 15:26:38 - INFO - __main__ - Step 12872: {'lr': 0.0004933733001430186, 'samples': 2471424, 'steps': 12871, 'loss/train': 0.19169384241104126} 08/30/2021 15:26:39 - INFO - __main__ - Step 12873: {'lr': 0.000493372086351083, 'samples': 2471616, 'steps': 12872, 'loss/train': 1.6319408416748047} 08/30/2021 15:26:39 - INFO - __main__ - Step 12874: {'lr': 0.0004933708724494877, 'samples': 2471808, 'steps': 12873, 'loss/train': 1.8161916732788086} 08/30/2021 15:26:39 - INFO - __main__ - Step 12875: {'lr': 0.0004933696584382331, 'samples': 2472000, 'steps': 12874, 'loss/train': 1.2566332817077637} 08/30/2021 15:26:40 - INFO - __main__ - Step 12876: {'lr': 0.00049336844431732, 'samples': 2472192, 'steps': 12875, 'loss/train': 2.009991407394409} 08/30/2021 15:26:41 - INFO - __main__ - Step 12877: {'lr': 0.0004933672300867488, 'samples': 2472384, 'steps': 12876, 'loss/train': 1.9428919553756714} 08/30/2021 15:26:42 - INFO - __main__ - Step 12878: {'lr': 0.0004933660157465202, 'samples': 2472576, 'steps': 12877, 'loss/train': 1.9996424913406372} 08/30/2021 15:26:42 - INFO - __main__ - Step 12879: {'lr': 0.0004933648012966344, 'samples': 2472768, 'steps': 12878, 'loss/train': 1.4289755821228027} 08/30/2021 15:26:42 - INFO - __main__ - Step 12880: {'lr': 0.0004933635867370923, 'samples': 2472960, 'steps': 12879, 'loss/train': 1.3390545845031738} 08/30/2021 15:26:43 - INFO - __main__ - Step 12881: {'lr': 0.0004933623720678944, 'samples': 2473152, 'steps': 12880, 'loss/train': 1.5453749895095825} 08/30/2021 15:26:44 - INFO - __main__ - Step 12882: {'lr': 0.000493361157289041, 'samples': 2473344, 'steps': 12881, 'loss/train': 2.0054750442504883} 08/30/2021 15:26:45 - INFO - __main__ - Step 12883: {'lr': 0.000493359942400533, 'samples': 2473536, 'steps': 12882, 'loss/train': 1.3292654752731323} 08/30/2021 15:26:45 - INFO - __main__ - Step 12884: {'lr': 0.0004933587274023706, 'samples': 2473728, 'steps': 12883, 'loss/train': 2.0311615467071533} 08/30/2021 15:26:45 - INFO - __main__ - Step 12885: {'lr': 0.0004933575122945547, 'samples': 2473920, 'steps': 12884, 'loss/train': 1.31778883934021} 08/30/2021 15:26:46 - INFO - __main__ - Step 12886: {'lr': 0.0004933562970770855, 'samples': 2474112, 'steps': 12885, 'loss/train': 1.9492117166519165} 08/30/2021 15:26:47 - INFO - __main__ - Step 12887: {'lr': 0.0004933550817499638, 'samples': 2474304, 'steps': 12886, 'loss/train': 1.905481219291687} 08/30/2021 15:26:48 - INFO - __main__ - Step 12888: {'lr': 0.00049335386631319, 'samples': 2474496, 'steps': 12887, 'loss/train': 1.9886780977249146} 08/30/2021 15:26:48 - INFO - __main__ - Step 12889: {'lr': 0.0004933526507667648, 'samples': 2474688, 'steps': 12888, 'loss/train': 1.90106201171875} 08/30/2021 15:26:48 - INFO - __main__ - Step 12890: {'lr': 0.0004933514351106885, 'samples': 2474880, 'steps': 12889, 'loss/train': 2.4388670921325684} 08/30/2021 15:26:49 - INFO - __main__ - Step 12891: {'lr': 0.0004933502193449618, 'samples': 2475072, 'steps': 12890, 'loss/train': 1.6792958974838257} 08/30/2021 15:26:50 - INFO - __main__ - Step 12892: {'lr': 0.0004933490034695853, 'samples': 2475264, 'steps': 12891, 'loss/train': 1.1208237409591675} 08/30/2021 15:26:51 - INFO - __main__ - Step 12893: {'lr': 0.0004933477874845595, 'samples': 2475456, 'steps': 12892, 'loss/train': 0.9411040544509888} 08/30/2021 15:26:51 - INFO - __main__ - Step 12894: {'lr': 0.000493346571389885, 'samples': 2475648, 'steps': 12893, 'loss/train': 1.7961270809173584} 08/30/2021 15:26:51 - INFO - __main__ - Step 12895: {'lr': 0.0004933453551855622, 'samples': 2475840, 'steps': 12894, 'loss/train': 0.7018240094184875} 08/30/2021 15:26:52 - INFO - __main__ - Step 12896: {'lr': 0.0004933441388715919, 'samples': 2476032, 'steps': 12895, 'loss/train': 1.3613004684448242} 08/30/2021 15:26:52 - INFO - __main__ - Step 12897: {'lr': 0.0004933429224479743, 'samples': 2476224, 'steps': 12896, 'loss/train': 1.989190697669983} 08/30/2021 15:26:53 - INFO - __main__ - Step 12898: {'lr': 0.0004933417059147102, 'samples': 2476416, 'steps': 12897, 'loss/train': 1.6655298471450806} 08/30/2021 15:26:54 - INFO - __main__ - Step 12899: {'lr': 0.0004933404892718, 'samples': 2476608, 'steps': 12898, 'loss/train': 1.571376919746399} 08/30/2021 15:26:54 - INFO - __main__ - Step 12900: {'lr': 0.0004933392725192444, 'samples': 2476800, 'steps': 12899, 'loss/train': 1.7903738021850586} 08/30/2021 15:26:55 - INFO - __main__ - Step 12901: {'lr': 0.000493338055657044, 'samples': 2476992, 'steps': 12900, 'loss/train': 2.3699591159820557} 08/30/2021 15:26:55 - INFO - __main__ - Step 12902: {'lr': 0.0004933368386851991, 'samples': 2477184, 'steps': 12901, 'loss/train': 1.7695090770721436} 08/30/2021 15:26:57 - INFO - __main__ - Step 12903: {'lr': 0.0004933356216037104, 'samples': 2477376, 'steps': 12902, 'loss/train': 1.897432804107666} 08/30/2021 15:26:57 - INFO - __main__ - Step 12904: {'lr': 0.0004933344044125784, 'samples': 2477568, 'steps': 12903, 'loss/train': 2.428956985473633} 08/30/2021 15:26:57 - INFO - __main__ - Step 12905: {'lr': 0.0004933331871118037, 'samples': 2477760, 'steps': 12904, 'loss/train': 1.5634547472000122} 08/30/2021 15:26:58 - INFO - __main__ - Step 12906: {'lr': 0.0004933319697013869, 'samples': 2477952, 'steps': 12905, 'loss/train': 1.5574288368225098} 08/30/2021 15:26:58 - INFO - __main__ - Step 12907: {'lr': 0.0004933307521813282, 'samples': 2478144, 'steps': 12906, 'loss/train': 1.9178047180175781} 08/30/2021 15:27:00 - INFO - __main__ - Step 12908: {'lr': 0.0004933295345516287, 'samples': 2478336, 'steps': 12907, 'loss/train': 1.6965242624282837} 08/30/2021 15:27:00 - INFO - __main__ - Step 12909: {'lr': 0.0004933283168122886, 'samples': 2478528, 'steps': 12908, 'loss/train': 2.1432430744171143} 08/30/2021 15:27:00 - INFO - __main__ - Step 12910: {'lr': 0.0004933270989633084, 'samples': 2478720, 'steps': 12909, 'loss/train': 1.492651104927063} 08/30/2021 15:27:01 - INFO - __main__ - Step 12911: {'lr': 0.0004933258810046889, 'samples': 2478912, 'steps': 12910, 'loss/train': 2.094221591949463} 08/30/2021 15:27:01 - INFO - __main__ - Step 12912: {'lr': 0.0004933246629364304, 'samples': 2479104, 'steps': 12911, 'loss/train': 1.8227078914642334} 08/30/2021 15:27:03 - INFO - __main__ - Step 12913: {'lr': 0.0004933234447585337, 'samples': 2479296, 'steps': 12912, 'loss/train': 1.4459824562072754} 08/30/2021 15:27:04 - INFO - __main__ - Step 12914: {'lr': 0.0004933222264709991, 'samples': 2479488, 'steps': 12913, 'loss/train': 1.6463892459869385} 08/30/2021 15:27:04 - INFO - __main__ - Step 12915: {'lr': 0.0004933210080738273, 'samples': 2479680, 'steps': 12914, 'loss/train': 1.5907765626907349} 08/30/2021 15:27:04 - INFO - __main__ - Step 12916: {'lr': 0.0004933197895670187, 'samples': 2479872, 'steps': 12915, 'loss/train': 1.5506144762039185} 08/30/2021 15:27:05 - INFO - __main__ - Step 12917: {'lr': 0.0004933185709505741, 'samples': 2480064, 'steps': 12916, 'loss/train': 2.120018482208252} 08/30/2021 15:27:05 - INFO - __main__ - Step 12918: {'lr': 0.0004933173522244939, 'samples': 2480256, 'steps': 12917, 'loss/train': 1.5343645811080933} 08/30/2021 15:27:07 - INFO - __main__ - Step 12919: {'lr': 0.0004933161333887786, 'samples': 2480448, 'steps': 12918, 'loss/train': 1.7413872480392456} 08/30/2021 15:27:07 - INFO - __main__ - Step 12920: {'lr': 0.0004933149144434288, 'samples': 2480640, 'steps': 12919, 'loss/train': 1.8250689506530762} 08/30/2021 15:27:07 - INFO - __main__ - Step 12921: {'lr': 0.0004933136953884451, 'samples': 2480832, 'steps': 12920, 'loss/train': 1.645958423614502} 08/30/2021 15:27:08 - INFO - __main__ - Step 12922: {'lr': 0.0004933124762238279, 'samples': 2481024, 'steps': 12921, 'loss/train': 1.9412498474121094} 08/30/2021 15:27:08 - INFO - __main__ - Step 12923: {'lr': 0.000493311256949578, 'samples': 2481216, 'steps': 12922, 'loss/train': 1.5907375812530518} 08/30/2021 15:27:10 - INFO - __main__ - Step 12924: {'lr': 0.0004933100375656957, 'samples': 2481408, 'steps': 12923, 'loss/train': 0.8259760737419128} 08/30/2021 15:27:10 - INFO - __main__ - Step 12925: {'lr': 0.0004933088180721817, 'samples': 2481600, 'steps': 12924, 'loss/train': 1.698560357093811} 08/30/2021 15:27:10 - INFO - __main__ - Step 12926: {'lr': 0.0004933075984690365, 'samples': 2481792, 'steps': 12925, 'loss/train': 2.067666530609131} 08/30/2021 15:27:11 - INFO - __main__ - Step 12927: {'lr': 0.0004933063787562606, 'samples': 2481984, 'steps': 12926, 'loss/train': 2.4630961418151855} 08/30/2021 15:27:11 - INFO - __main__ - Step 12928: {'lr': 0.0004933051589338547, 'samples': 2482176, 'steps': 12927, 'loss/train': 1.671011209487915} 08/30/2021 15:27:13 - INFO - __main__ - Step 12929: {'lr': 0.0004933039390018192, 'samples': 2482368, 'steps': 12928, 'loss/train': 1.714061975479126} 08/30/2021 15:27:13 - INFO - __main__ - Step 12930: {'lr': 0.0004933027189601547, 'samples': 2482560, 'steps': 12929, 'loss/train': 1.7152819633483887} 08/30/2021 15:27:13 - INFO - __main__ - Step 12931: {'lr': 0.0004933014988088616, 'samples': 2482752, 'steps': 12930, 'loss/train': 1.3183889389038086} 08/30/2021 15:27:14 - INFO - __main__ - Step 12932: {'lr': 0.0004933002785479408, 'samples': 2482944, 'steps': 12931, 'loss/train': 0.16766878962516785} 08/30/2021 15:27:14 - INFO - __main__ - Step 12933: {'lr': 0.0004932990581773926, 'samples': 2483136, 'steps': 12932, 'loss/train': 2.2817769050598145} 08/30/2021 15:27:16 - INFO - __main__ - Step 12934: {'lr': 0.0004932978376972175, 'samples': 2483328, 'steps': 12933, 'loss/train': 1.4748798608779907} 08/30/2021 15:27:16 - INFO - __main__ - Step 12935: {'lr': 0.0004932966171074163, 'samples': 2483520, 'steps': 12934, 'loss/train': 1.686767816543579} 08/30/2021 15:27:16 - INFO - __main__ - Step 12936: {'lr': 0.0004932953964079893, 'samples': 2483712, 'steps': 12935, 'loss/train': 1.5524197816848755} 08/30/2021 15:27:17 - INFO - __main__ - Step 12937: {'lr': 0.0004932941755989372, 'samples': 2483904, 'steps': 12936, 'loss/train': 2.500237464904785} 08/30/2021 15:27:17 - INFO - __main__ - Step 12938: {'lr': 0.0004932929546802605, 'samples': 2484096, 'steps': 12937, 'loss/train': 1.6547746658325195} 08/30/2021 15:27:19 - INFO - __main__ - Step 12939: {'lr': 0.0004932917336519597, 'samples': 2484288, 'steps': 12938, 'loss/train': 0.5372771620750427} 08/30/2021 15:27:19 - INFO - __main__ - Step 12940: {'lr': 0.0004932905125140354, 'samples': 2484480, 'steps': 12939, 'loss/train': 1.3921217918395996} 08/30/2021 15:27:20 - INFO - __main__ - Step 12941: {'lr': 0.0004932892912664882, 'samples': 2484672, 'steps': 12940, 'loss/train': 1.3276793956756592} 08/30/2021 15:27:20 - INFO - __main__ - Step 12942: {'lr': 0.0004932880699093186, 'samples': 2484864, 'steps': 12941, 'loss/train': 1.8124228715896606} 08/30/2021 15:27:20 - INFO - __main__ - Step 12943: {'lr': 0.0004932868484425271, 'samples': 2485056, 'steps': 12942, 'loss/train': 0.16740307211875916} 08/30/2021 15:27:21 - INFO - __main__ - Step 12944: {'lr': 0.0004932856268661143, 'samples': 2485248, 'steps': 12943, 'loss/train': 1.3268613815307617} 08/30/2021 15:27:21 - INFO - __main__ - Step 12945: {'lr': 0.0004932844051800808, 'samples': 2485440, 'steps': 12944, 'loss/train': 2.3583836555480957} 08/30/2021 15:27:23 - INFO - __main__ - Step 12946: {'lr': 0.000493283183384427, 'samples': 2485632, 'steps': 12945, 'loss/train': 2.23337984085083} 08/30/2021 15:27:23 - INFO - __main__ - Step 12947: {'lr': 0.0004932819614791537, 'samples': 2485824, 'steps': 12946, 'loss/train': 1.7928889989852905} 08/30/2021 15:27:23 - INFO - __main__ - Step 12948: {'lr': 0.0004932807394642612, 'samples': 2486016, 'steps': 12947, 'loss/train': 1.3809243440628052} 08/30/2021 15:27:24 - INFO - __main__ - Step 12949: {'lr': 0.0004932795173397501, 'samples': 2486208, 'steps': 12948, 'loss/train': 1.9425253868103027} 08/30/2021 15:27:24 - INFO - __main__ - Step 12950: {'lr': 0.0004932782951056211, 'samples': 2486400, 'steps': 12949, 'loss/train': 2.1360065937042236} 08/30/2021 15:27:26 - INFO - __main__ - Step 12951: {'lr': 0.0004932770727618747, 'samples': 2486592, 'steps': 12950, 'loss/train': 2.145446538925171} 08/30/2021 15:27:26 - INFO - __main__ - Step 12952: {'lr': 0.0004932758503085114, 'samples': 2486784, 'steps': 12951, 'loss/train': 1.6578941345214844} 08/30/2021 15:27:26 - INFO - __main__ - Step 12953: {'lr': 0.0004932746277455317, 'samples': 2486976, 'steps': 12952, 'loss/train': 1.815985083580017} 08/30/2021 15:27:27 - INFO - __main__ - Step 12954: {'lr': 0.0004932734050729362, 'samples': 2487168, 'steps': 12953, 'loss/train': 1.4310932159423828} 08/30/2021 15:27:27 - INFO - __main__ - Step 12955: {'lr': 0.0004932721822907255, 'samples': 2487360, 'steps': 12954, 'loss/train': 1.784164309501648} 08/30/2021 15:27:29 - INFO - __main__ - Step 12956: {'lr': 0.0004932709593989, 'samples': 2487552, 'steps': 12955, 'loss/train': 2.0219085216522217} 08/30/2021 15:27:29 - INFO - __main__ - Step 12957: {'lr': 0.0004932697363974604, 'samples': 2487744, 'steps': 12956, 'loss/train': 1.3164905309677124} 08/30/2021 15:27:29 - INFO - __main__ - Step 12958: {'lr': 0.0004932685132864072, 'samples': 2487936, 'steps': 12957, 'loss/train': 1.2794688940048218} 08/30/2021 15:27:30 - INFO - __main__ - Step 12959: {'lr': 0.0004932672900657411, 'samples': 2488128, 'steps': 12958, 'loss/train': 1.6962989568710327} 08/30/2021 15:27:30 - INFO - __main__ - Step 12960: {'lr': 0.0004932660667354623, 'samples': 2488320, 'steps': 12959, 'loss/train': 1.8925210237503052} 08/30/2021 15:27:32 - INFO - __main__ - Step 12961: {'lr': 0.0004932648432955717, 'samples': 2488512, 'steps': 12960, 'loss/train': 1.7702349424362183} 08/30/2021 15:27:32 - INFO - __main__ - Step 12962: {'lr': 0.0004932636197460698, 'samples': 2488704, 'steps': 12961, 'loss/train': 1.7371070384979248} 08/30/2021 15:27:32 - INFO - __main__ - Step 12963: {'lr': 0.0004932623960869569, 'samples': 2488896, 'steps': 12962, 'loss/train': 1.5402714014053345} 08/30/2021 15:27:33 - INFO - __main__ - Step 12964: {'lr': 0.0004932611723182338, 'samples': 2489088, 'steps': 12963, 'loss/train': 1.582326054573059} 08/30/2021 15:27:33 - INFO - __main__ - Step 12965: {'lr': 0.000493259948439901, 'samples': 2489280, 'steps': 12964, 'loss/train': 1.4854434728622437} 08/30/2021 15:27:35 - INFO - __main__ - Step 12966: {'lr': 0.0004932587244519589, 'samples': 2489472, 'steps': 12965, 'loss/train': 2.4423863887786865} 08/30/2021 15:27:35 - INFO - __main__ - Step 12967: {'lr': 0.0004932575003544083, 'samples': 2489664, 'steps': 12966, 'loss/train': 1.630094051361084} 08/30/2021 15:27:35 - INFO - __main__ - Step 12968: {'lr': 0.0004932562761472496, 'samples': 2489856, 'steps': 12967, 'loss/train': 2.0432162284851074} 08/30/2021 15:27:36 - INFO - __main__ - Step 12969: {'lr': 0.0004932550518304833, 'samples': 2490048, 'steps': 12968, 'loss/train': 2.013092517852783} 08/30/2021 15:27:36 - INFO - __main__ - Step 12970: {'lr': 0.0004932538274041101, 'samples': 2490240, 'steps': 12969, 'loss/train': 1.8890380859375} 08/30/2021 15:27:38 - INFO - __main__ - Step 12971: {'lr': 0.0004932526028681304, 'samples': 2490432, 'steps': 12970, 'loss/train': 1.1682820320129395} 08/30/2021 15:27:38 - INFO - __main__ - Step 12972: {'lr': 0.0004932513782225449, 'samples': 2490624, 'steps': 12971, 'loss/train': 1.8650240898132324} 08/30/2021 15:27:39 - INFO - __main__ - Step 12973: {'lr': 0.000493250153467354, 'samples': 2490816, 'steps': 12972, 'loss/train': 1.0635807514190674} 08/30/2021 15:27:39 - INFO - __main__ - Step 12974: {'lr': 0.0004932489286025584, 'samples': 2491008, 'steps': 12973, 'loss/train': 1.5997942686080933} 08/30/2021 15:27:39 - INFO - __main__ - Step 12975: {'lr': 0.0004932477036281586, 'samples': 2491200, 'steps': 12974, 'loss/train': 2.061941623687744} 08/30/2021 15:27:40 - INFO - __main__ - Step 12976: {'lr': 0.0004932464785441552, 'samples': 2491392, 'steps': 12975, 'loss/train': 2.1151795387268066} 08/30/2021 15:27:41 - INFO - __main__ - Step 12977: {'lr': 0.0004932452533505486, 'samples': 2491584, 'steps': 12976, 'loss/train': 2.0156846046447754} 08/30/2021 15:27:42 - INFO - __main__ - Step 12978: {'lr': 0.0004932440280473395, 'samples': 2491776, 'steps': 12977, 'loss/train': 1.2708879709243774} 08/30/2021 15:27:42 - INFO - __main__ - Step 12979: {'lr': 0.0004932428026345282, 'samples': 2491968, 'steps': 12978, 'loss/train': 1.660595178604126} 08/30/2021 15:27:42 - INFO - __main__ - Step 12980: {'lr': 0.0004932415771121157, 'samples': 2492160, 'steps': 12979, 'loss/train': 1.8325729370117188} 08/30/2021 15:27:43 - INFO - __main__ - Step 12981: {'lr': 0.0004932403514801021, 'samples': 2492352, 'steps': 12980, 'loss/train': 1.737576961517334} 08/30/2021 15:27:45 - INFO - __main__ - Step 12982: {'lr': 0.0004932391257384883, 'samples': 2492544, 'steps': 12981, 'loss/train': 1.7842106819152832} 08/30/2021 15:27:45 - INFO - __main__ - Step 12983: {'lr': 0.0004932378998872746, 'samples': 2492736, 'steps': 12982, 'loss/train': 2.11392879486084} 08/30/2021 15:27:46 - INFO - __main__ - Step 12984: {'lr': 0.0004932366739264618, 'samples': 2492928, 'steps': 12983, 'loss/train': 1.9216110706329346} 08/30/2021 15:27:46 - INFO - __main__ - Step 12985: {'lr': 0.0004932354478560502, 'samples': 2493120, 'steps': 12984, 'loss/train': 2.0142393112182617} 08/30/2021 15:27:47 - INFO - __main__ - Step 12986: {'lr': 0.0004932342216760405, 'samples': 2493312, 'steps': 12985, 'loss/train': 0.9964456558227539} 08/30/2021 15:27:47 - INFO - __main__ - Step 12987: {'lr': 0.0004932329953864331, 'samples': 2493504, 'steps': 12986, 'loss/train': 1.4187933206558228} 08/30/2021 15:27:49 - INFO - __main__ - Step 12988: {'lr': 0.0004932317689872287, 'samples': 2493696, 'steps': 12987, 'loss/train': 1.1365156173706055} 08/30/2021 15:27:49 - INFO - __main__ - Step 12989: {'lr': 0.000493230542478428, 'samples': 2493888, 'steps': 12988, 'loss/train': 1.653011679649353} 08/30/2021 15:27:49 - INFO - __main__ - Step 12990: {'lr': 0.0004932293158600312, 'samples': 2494080, 'steps': 12989, 'loss/train': 1.5194389820098877} 08/30/2021 15:27:50 - INFO - __main__ - Step 12991: {'lr': 0.0004932280891320391, 'samples': 2494272, 'steps': 12990, 'loss/train': 1.7696212530136108} 08/30/2021 15:27:50 - INFO - __main__ - Step 12992: {'lr': 0.0004932268622944521, 'samples': 2494464, 'steps': 12991, 'loss/train': 1.1499416828155518} 08/30/2021 15:27:50 - INFO - __main__ - Step 12993: {'lr': 0.0004932256353472709, 'samples': 2494656, 'steps': 12992, 'loss/train': 0.48234203457832336} 08/30/2021 15:27:52 - INFO - __main__ - Step 12994: {'lr': 0.0004932244082904959, 'samples': 2494848, 'steps': 12993, 'loss/train': 2.079378128051758} 08/30/2021 15:27:52 - INFO - __main__ - Step 12995: {'lr': 0.0004932231811241278, 'samples': 2495040, 'steps': 12994, 'loss/train': 1.7509737014770508} 08/30/2021 15:27:53 - INFO - __main__ - Step 12996: {'lr': 0.0004932219538481672, 'samples': 2495232, 'steps': 12995, 'loss/train': 2.2721691131591797} 08/30/2021 15:27:53 - INFO - __main__ - Step 12997: {'lr': 0.0004932207264626143, 'samples': 2495424, 'steps': 12996, 'loss/train': 2.0370490550994873} 08/30/2021 15:27:53 - INFO - __main__ - Step 12998: {'lr': 0.00049321949896747, 'samples': 2495616, 'steps': 12997, 'loss/train': 1.7114466428756714} 08/30/2021 15:27:55 - INFO - __main__ - Step 12999: {'lr': 0.0004932182713627348, 'samples': 2495808, 'steps': 12998, 'loss/train': 0.8038334250450134} 08/30/2021 15:27:56 - INFO - __main__ - Step 13000: {'lr': 0.0004932170436484091, 'samples': 2496000, 'steps': 12999, 'loss/train': 2.0671768188476562} 08/30/2021 15:27:56 - INFO - __main__ - Step 13001: {'lr': 0.0004932158158244937, 'samples': 2496192, 'steps': 13000, 'loss/train': 2.1165475845336914} 08/30/2021 15:27:56 - INFO - __main__ - Step 13002: {'lr': 0.0004932145878909889, 'samples': 2496384, 'steps': 13001, 'loss/train': 1.4926173686981201} 08/30/2021 15:27:57 - INFO - __main__ - Step 13003: {'lr': 0.0004932133598478953, 'samples': 2496576, 'steps': 13002, 'loss/train': 2.1384963989257812} 08/30/2021 15:27:58 - INFO - __main__ - Step 13004: {'lr': 0.0004932121316952136, 'samples': 2496768, 'steps': 13003, 'loss/train': 2.163433313369751} 08/30/2021 15:27:59 - INFO - __main__ - Step 13005: {'lr': 0.0004932109034329442, 'samples': 2496960, 'steps': 13004, 'loss/train': 1.7609907388687134} 08/30/2021 15:27:59 - INFO - __main__ - Step 13006: {'lr': 0.0004932096750610879, 'samples': 2497152, 'steps': 13005, 'loss/train': 2.1369967460632324} 08/30/2021 15:27:59 - INFO - __main__ - Step 13007: {'lr': 0.0004932084465796449, 'samples': 2497344, 'steps': 13006, 'loss/train': 1.5515129566192627} 08/30/2021 15:28:00 - INFO - __main__ - Step 13008: {'lr': 0.000493207217988616, 'samples': 2497536, 'steps': 13007, 'loss/train': 1.4073905944824219} 08/30/2021 15:28:01 - INFO - __main__ - Step 13009: {'lr': 0.0004932059892880016, 'samples': 2497728, 'steps': 13008, 'loss/train': 1.4713689088821411} 08/30/2021 15:28:02 - INFO - __main__ - Step 13010: {'lr': 0.0004932047604778025, 'samples': 2497920, 'steps': 13009, 'loss/train': 1.11771821975708} 08/30/2021 15:28:02 - INFO - __main__ - Step 13011: {'lr': 0.0004932035315580188, 'samples': 2498112, 'steps': 13010, 'loss/train': 2.0724284648895264} 08/30/2021 15:28:02 - INFO - __main__ - Step 13012: {'lr': 0.0004932023025286516, 'samples': 2498304, 'steps': 13011, 'loss/train': 2.1573293209075928} 08/30/2021 15:28:03 - INFO - __main__ - Step 13013: {'lr': 0.0004932010733897012, 'samples': 2498496, 'steps': 13012, 'loss/train': 1.907956838607788} 08/30/2021 15:28:04 - INFO - __main__ - Step 13014: {'lr': 0.000493199844141168, 'samples': 2498688, 'steps': 13013, 'loss/train': 1.34544837474823} 08/30/2021 15:28:05 - INFO - __main__ - Step 13015: {'lr': 0.0004931986147830527, 'samples': 2498880, 'steps': 13014, 'loss/train': 1.8426891565322876} 08/30/2021 15:28:05 - INFO - __main__ - Step 13016: {'lr': 0.000493197385315356, 'samples': 2499072, 'steps': 13015, 'loss/train': 2.1983206272125244} 08/30/2021 15:28:05 - INFO - __main__ - Step 13017: {'lr': 0.0004931961557380782, 'samples': 2499264, 'steps': 13016, 'loss/train': 1.6161142587661743} 08/30/2021 15:28:06 - INFO - __main__ - Step 13018: {'lr': 0.00049319492605122, 'samples': 2499456, 'steps': 13017, 'loss/train': 1.5326571464538574} 08/30/2021 15:28:07 - INFO - __main__ - Step 13019: {'lr': 0.000493193696254782, 'samples': 2499648, 'steps': 13018, 'loss/train': 1.9193850755691528} 08/30/2021 15:28:08 - INFO - __main__ - Step 13020: {'lr': 0.0004931924663487646, 'samples': 2499840, 'steps': 13019, 'loss/train': 0.864918053150177} 08/30/2021 15:28:08 - INFO - __main__ - Step 13021: {'lr': 0.0004931912363331683, 'samples': 2500032, 'steps': 13020, 'loss/train': 1.8274675607681274} 08/30/2021 15:28:08 - INFO - __main__ - Step 13022: {'lr': 0.000493190006207994, 'samples': 2500224, 'steps': 13021, 'loss/train': 1.7764897346496582} 08/30/2021 15:28:09 - INFO - __main__ - Step 13023: {'lr': 0.0004931887759732419, 'samples': 2500416, 'steps': 13022, 'loss/train': 1.5352623462677002} 08/30/2021 15:28:11 - INFO - __main__ - Step 13024: {'lr': 0.0004931875456289128, 'samples': 2500608, 'steps': 13023, 'loss/train': 1.5049412250518799} 08/30/2021 15:28:11 - INFO - __main__ - Step 13025: {'lr': 0.000493186315175007, 'samples': 2500800, 'steps': 13024, 'loss/train': 2.0036520957946777} 08/30/2021 15:28:12 - INFO - __main__ - Step 13026: {'lr': 0.0004931850846115253, 'samples': 2500992, 'steps': 13025, 'loss/train': 1.5592503547668457} 08/30/2021 15:28:12 - INFO - __main__ - Step 13027: {'lr': 0.0004931838539384681, 'samples': 2501184, 'steps': 13026, 'loss/train': 1.9943856000900269} 08/30/2021 15:28:12 - INFO - __main__ - Step 13028: {'lr': 0.0004931826231558361, 'samples': 2501376, 'steps': 13027, 'loss/train': 1.7973827123641968} 08/30/2021 15:28:14 - INFO - __main__ - Step 13029: {'lr': 0.0004931813922636297, 'samples': 2501568, 'steps': 13028, 'loss/train': 1.706641435623169} 08/30/2021 15:28:14 - INFO - __main__ - Step 13030: {'lr': 0.0004931801612618494, 'samples': 2501760, 'steps': 13029, 'loss/train': 1.7919440269470215} 08/30/2021 15:28:15 - INFO - __main__ - Step 13031: {'lr': 0.0004931789301504961, 'samples': 2501952, 'steps': 13030, 'loss/train': 2.379535675048828} 08/30/2021 15:28:15 - INFO - __main__ - Step 13032: {'lr': 0.00049317769892957, 'samples': 2502144, 'steps': 13031, 'loss/train': 1.557008981704712} 08/30/2021 15:28:15 - INFO - __main__ - Step 13033: {'lr': 0.0004931764675990718, 'samples': 2502336, 'steps': 13032, 'loss/train': 1.3330165147781372} 08/30/2021 15:28:16 - INFO - __main__ - Step 13034: {'lr': 0.000493175236159002, 'samples': 2502528, 'steps': 13033, 'loss/train': 1.2604204416275024} 08/30/2021 15:28:17 - INFO - __main__ - Step 13035: {'lr': 0.0004931740046093612, 'samples': 2502720, 'steps': 13034, 'loss/train': 1.5593136548995972} 08/30/2021 15:28:18 - INFO - __main__ - Step 13036: {'lr': 0.0004931727729501499, 'samples': 2502912, 'steps': 13035, 'loss/train': 1.4550620317459106} 08/30/2021 15:28:18 - INFO - __main__ - Step 13037: {'lr': 0.0004931715411813689, 'samples': 2503104, 'steps': 13036, 'loss/train': 1.0847595930099487} 08/30/2021 15:28:18 - INFO - __main__ - Step 13038: {'lr': 0.0004931703093030183, 'samples': 2503296, 'steps': 13037, 'loss/train': 2.3429133892059326} 08/30/2021 15:28:19 - INFO - __main__ - Step 13039: {'lr': 0.0004931690773150991, 'samples': 2503488, 'steps': 13038, 'loss/train': 1.7359956502914429} 08/30/2021 15:28:20 - INFO - __main__ - Step 13040: {'lr': 0.0004931678452176116, 'samples': 2503680, 'steps': 13039, 'loss/train': 1.437747836112976} 08/30/2021 15:28:21 - INFO - __main__ - Step 13041: {'lr': 0.0004931666130105563, 'samples': 2503872, 'steps': 13040, 'loss/train': 1.7497220039367676} 08/30/2021 15:28:21 - INFO - __main__ - Step 13042: {'lr': 0.0004931653806939341, 'samples': 2504064, 'steps': 13041, 'loss/train': 1.897395372390747} 08/30/2021 15:28:21 - INFO - __main__ - Step 13043: {'lr': 0.0004931641482677452, 'samples': 2504256, 'steps': 13042, 'loss/train': 1.0215831995010376} 08/30/2021 15:28:22 - INFO - __main__ - Step 13044: {'lr': 0.0004931629157319904, 'samples': 2504448, 'steps': 13043, 'loss/train': 2.220050096511841} 08/30/2021 15:28:22 - INFO - __main__ - Step 13045: {'lr': 0.00049316168308667, 'samples': 2504640, 'steps': 13044, 'loss/train': 0.17489831149578094} 08/30/2021 15:28:24 - INFO - __main__ - Step 13046: {'lr': 0.0004931604503317846, 'samples': 2504832, 'steps': 13045, 'loss/train': 1.2778693437576294} 08/30/2021 15:28:24 - INFO - __main__ - Step 13047: {'lr': 0.0004931592174673351, 'samples': 2505024, 'steps': 13046, 'loss/train': 1.2653385400772095} 08/30/2021 15:28:25 - INFO - __main__ - Step 13048: {'lr': 0.0004931579844933218, 'samples': 2505216, 'steps': 13047, 'loss/train': 2.0661964416503906} 08/30/2021 15:28:25 - INFO - __main__ - Step 13049: {'lr': 0.0004931567514097451, 'samples': 2505408, 'steps': 13048, 'loss/train': 1.877793312072754} 08/30/2021 15:28:25 - INFO - __main__ - Step 13050: {'lr': 0.0004931555182166059, 'samples': 2505600, 'steps': 13049, 'loss/train': 1.6688730716705322} 08/30/2021 15:28:27 - INFO - __main__ - Step 13051: {'lr': 0.0004931542849139044, 'samples': 2505792, 'steps': 13050, 'loss/train': 2.4740827083587646} 08/30/2021 15:28:27 - INFO - __main__ - Step 13052: {'lr': 0.0004931530515016415, 'samples': 2505984, 'steps': 13051, 'loss/train': 1.5523220300674438} 08/30/2021 15:28:28 - INFO - __main__ - Step 13053: {'lr': 0.0004931518179798175, 'samples': 2506176, 'steps': 13052, 'loss/train': 1.5974029302597046} 08/30/2021 15:28:28 - INFO - __main__ - Step 13054: {'lr': 0.000493150584348433, 'samples': 2506368, 'steps': 13053, 'loss/train': 1.7093305587768555} 08/30/2021 15:28:28 - INFO - __main__ - Step 13055: {'lr': 0.0004931493506074886, 'samples': 2506560, 'steps': 13054, 'loss/train': 1.8807342052459717} 08/30/2021 15:28:30 - INFO - __main__ - Step 13056: {'lr': 0.0004931481167569849, 'samples': 2506752, 'steps': 13055, 'loss/train': 2.1391303539276123} 08/30/2021 15:28:30 - INFO - __main__ - Step 13057: {'lr': 0.0004931468827969223, 'samples': 2506944, 'steps': 13056, 'loss/train': 1.5391812324523926} 08/30/2021 15:28:31 - INFO - __main__ - Step 13058: {'lr': 0.0004931456487273017, 'samples': 2507136, 'steps': 13057, 'loss/train': 1.659219741821289} 08/30/2021 15:28:31 - INFO - __main__ - Step 13059: {'lr': 0.0004931444145481233, 'samples': 2507328, 'steps': 13058, 'loss/train': 1.429943323135376} 08/30/2021 15:28:31 - INFO - __main__ - Step 13060: {'lr': 0.0004931431802593877, 'samples': 2507520, 'steps': 13059, 'loss/train': 1.8401118516921997} 08/30/2021 15:28:33 - INFO - __main__ - Step 13061: {'lr': 0.0004931419458610956, 'samples': 2507712, 'steps': 13060, 'loss/train': 1.9002833366394043} 08/30/2021 15:28:33 - INFO - __main__ - Step 13062: {'lr': 0.0004931407113532476, 'samples': 2507904, 'steps': 13061, 'loss/train': 1.1754478216171265} 08/30/2021 15:28:33 - INFO - __main__ - Step 13063: {'lr': 0.000493139476735844, 'samples': 2508096, 'steps': 13062, 'loss/train': 1.7957676649093628} 08/30/2021 15:28:34 - INFO - __main__ - Step 13064: {'lr': 0.0004931382420088855, 'samples': 2508288, 'steps': 13063, 'loss/train': 1.8040765523910522} 08/30/2021 15:28:34 - INFO - __main__ - Step 13065: {'lr': 0.0004931370071723728, 'samples': 2508480, 'steps': 13064, 'loss/train': 1.305092453956604} 08/30/2021 15:28:36 - INFO - __main__ - Step 13066: {'lr': 0.0004931357722263061, 'samples': 2508672, 'steps': 13065, 'loss/train': 1.7021839618682861} 08/30/2021 15:28:36 - INFO - __main__ - Step 13067: {'lr': 0.0004931345371706863, 'samples': 2508864, 'steps': 13066, 'loss/train': 2.398237943649292} 08/30/2021 15:28:36 - INFO - __main__ - Step 13068: {'lr': 0.0004931333020055139, 'samples': 2509056, 'steps': 13067, 'loss/train': 2.0597445964813232} 08/30/2021 15:28:37 - INFO - __main__ - Step 13069: {'lr': 0.0004931320667307893, 'samples': 2509248, 'steps': 13068, 'loss/train': 2.1479623317718506} 08/30/2021 15:28:37 - INFO - __main__ - Step 13070: {'lr': 0.0004931308313465132, 'samples': 2509440, 'steps': 13069, 'loss/train': 1.5970937013626099} 08/30/2021 15:28:39 - INFO - __main__ - Step 13071: {'lr': 0.000493129595852686, 'samples': 2509632, 'steps': 13070, 'loss/train': 1.9472614526748657} 08/30/2021 15:28:39 - INFO - __main__ - Step 13072: {'lr': 0.0004931283602493084, 'samples': 2509824, 'steps': 13071, 'loss/train': 1.283542275428772} 08/30/2021 15:28:40 - INFO - __main__ - Step 13073: {'lr': 0.0004931271245363809, 'samples': 2510016, 'steps': 13072, 'loss/train': 1.7467390298843384} 08/30/2021 15:28:40 - INFO - __main__ - Step 13074: {'lr': 0.0004931258887139041, 'samples': 2510208, 'steps': 13073, 'loss/train': 0.3075007200241089} 08/30/2021 15:28:40 - INFO - __main__ - Step 13075: {'lr': 0.0004931246527818785, 'samples': 2510400, 'steps': 13074, 'loss/train': 1.9166795015335083} 08/30/2021 15:28:42 - INFO - __main__ - Step 13076: {'lr': 0.0004931234167403047, 'samples': 2510592, 'steps': 13075, 'loss/train': 1.3028392791748047} 08/30/2021 15:28:42 - INFO - __main__ - Step 13077: {'lr': 0.0004931221805891833, 'samples': 2510784, 'steps': 13076, 'loss/train': 1.6634352207183838} 08/30/2021 15:28:43 - INFO - __main__ - Step 13078: {'lr': 0.0004931209443285147, 'samples': 2510976, 'steps': 13077, 'loss/train': 1.9077144861221313} 08/30/2021 15:28:43 - INFO - __main__ - Step 13079: {'lr': 0.0004931197079582996, 'samples': 2511168, 'steps': 13078, 'loss/train': 1.5824267864227295} 08/30/2021 15:28:43 - INFO - __main__ - Step 13080: {'lr': 0.0004931184714785385, 'samples': 2511360, 'steps': 13079, 'loss/train': 1.7552483081817627} 08/30/2021 15:28:45 - INFO - __main__ - Step 13081: {'lr': 0.000493117234889232, 'samples': 2511552, 'steps': 13080, 'loss/train': 1.94263756275177} 08/30/2021 15:28:46 - INFO - __main__ - Step 13082: {'lr': 0.0004931159981903805, 'samples': 2511744, 'steps': 13081, 'loss/train': 1.7694244384765625} 08/30/2021 15:28:46 - INFO - __main__ - Step 13083: {'lr': 0.0004931147613819848, 'samples': 2511936, 'steps': 13082, 'loss/train': 2.3691859245300293} 08/30/2021 15:28:47 - INFO - __main__ - Step 13084: {'lr': 0.0004931135244640453, 'samples': 2512128, 'steps': 13083, 'loss/train': 1.850730061531067} 08/30/2021 15:28:47 - INFO - __main__ - Step 13085: {'lr': 0.0004931122874365627, 'samples': 2512320, 'steps': 13084, 'loss/train': 1.9314231872558594} 08/30/2021 15:28:47 - INFO - __main__ - Step 13086: {'lr': 0.0004931110502995374, 'samples': 2512512, 'steps': 13085, 'loss/train': 2.1539690494537354} 08/30/2021 15:28:49 - INFO - __main__ - Step 13087: {'lr': 0.0004931098130529699, 'samples': 2512704, 'steps': 13086, 'loss/train': 2.0296292304992676} 08/30/2021 15:28:49 - INFO - __main__ - Step 13088: {'lr': 0.000493108575696861, 'samples': 2512896, 'steps': 13087, 'loss/train': 1.527732491493225} 08/30/2021 15:28:50 - INFO - __main__ - Step 13089: {'lr': 0.0004931073382312111, 'samples': 2513088, 'steps': 13088, 'loss/train': 1.7371238470077515} 08/30/2021 15:28:50 - INFO - __main__ - Step 13090: {'lr': 0.0004931061006560207, 'samples': 2513280, 'steps': 13089, 'loss/train': 1.9282242059707642} 08/30/2021 15:28:50 - INFO - __main__ - Step 13091: {'lr': 0.0004931048629712905, 'samples': 2513472, 'steps': 13090, 'loss/train': 1.2753441333770752} 08/30/2021 15:28:52 - INFO - __main__ - Step 13092: {'lr': 0.000493103625177021, 'samples': 2513664, 'steps': 13091, 'loss/train': 1.8101255893707275} 08/30/2021 15:28:52 - INFO - __main__ - Step 13093: {'lr': 0.0004931023872732128, 'samples': 2513856, 'steps': 13092, 'loss/train': 1.4918361902236938} 08/30/2021 15:28:53 - INFO - __main__ - Step 13094: {'lr': 0.0004931011492598664, 'samples': 2514048, 'steps': 13093, 'loss/train': 1.029206395149231} 08/30/2021 15:28:53 - INFO - __main__ - Step 13095: {'lr': 0.0004930999111369824, 'samples': 2514240, 'steps': 13094, 'loss/train': 1.8578993082046509} 08/30/2021 15:28:53 - INFO - __main__ - Step 13096: {'lr': 0.0004930986729045613, 'samples': 2514432, 'steps': 13095, 'loss/train': 1.5148252248764038} 08/30/2021 15:28:55 - INFO - __main__ - Step 13097: {'lr': 0.0004930974345626036, 'samples': 2514624, 'steps': 13096, 'loss/train': 1.5347464084625244} 08/30/2021 15:28:55 - INFO - __main__ - Step 13098: {'lr': 0.00049309619611111, 'samples': 2514816, 'steps': 13097, 'loss/train': 1.093123197555542} 08/30/2021 15:28:56 - INFO - __main__ - Step 13099: {'lr': 0.000493094957550081, 'samples': 2515008, 'steps': 13098, 'loss/train': 1.668910264968872} 08/30/2021 15:28:56 - INFO - __main__ - Step 13100: {'lr': 0.0004930937188795172, 'samples': 2515200, 'steps': 13099, 'loss/train': 1.6206682920455933} 08/30/2021 15:28:56 - INFO - __main__ - Step 13101: {'lr': 0.0004930924800994192, 'samples': 2515392, 'steps': 13100, 'loss/train': 1.2876331806182861} 08/30/2021 15:28:58 - INFO - __main__ - Step 13102: {'lr': 0.0004930912412097874, 'samples': 2515584, 'steps': 13101, 'loss/train': 1.5982943773269653} 08/30/2021 15:28:58 - INFO - __main__ - Step 13103: {'lr': 0.0004930900022106224, 'samples': 2515776, 'steps': 13102, 'loss/train': 0.8433182835578918} 08/30/2021 15:28:59 - INFO - __main__ - Step 13104: {'lr': 0.0004930887631019248, 'samples': 2515968, 'steps': 13103, 'loss/train': 1.2797197103500366} 08/30/2021 15:28:59 - INFO - __main__ - Step 13105: {'lr': 0.0004930875238836951, 'samples': 2516160, 'steps': 13104, 'loss/train': 1.6055853366851807} 08/30/2021 15:28:59 - INFO - __main__ - Step 13106: {'lr': 0.000493086284555934, 'samples': 2516352, 'steps': 13105, 'loss/train': 1.447858452796936} 08/30/2021 15:29:00 - INFO - __main__ - Step 13107: {'lr': 0.0004930850451186421, 'samples': 2516544, 'steps': 13106, 'loss/train': 1.67668879032135} 08/30/2021 15:29:01 - INFO - __main__ - Step 13108: {'lr': 0.0004930838055718196, 'samples': 2516736, 'steps': 13107, 'loss/train': 1.573887825012207} 08/30/2021 15:29:02 - INFO - __main__ - Step 13109: {'lr': 0.0004930825659154674, 'samples': 2516928, 'steps': 13108, 'loss/train': 1.8749699592590332} 08/30/2021 15:29:02 - INFO - __main__ - Step 13110: {'lr': 0.000493081326149586, 'samples': 2517120, 'steps': 13109, 'loss/train': 0.5593264698982239} 08/30/2021 15:29:02 - INFO - __main__ - Step 13111: {'lr': 0.0004930800862741758, 'samples': 2517312, 'steps': 13110, 'loss/train': 1.6479274034500122} 08/30/2021 15:29:03 - INFO - __main__ - Step 13112: {'lr': 0.0004930788462892375, 'samples': 2517504, 'steps': 13111, 'loss/train': 1.4467664957046509} 08/30/2021 15:29:04 - INFO - __main__ - Step 13113: {'lr': 0.0004930776061947716, 'samples': 2517696, 'steps': 13112, 'loss/train': 0.14597637951374054} 08/30/2021 15:29:05 - INFO - __main__ - Step 13114: {'lr': 0.0004930763659907788, 'samples': 2517888, 'steps': 13113, 'loss/train': 1.8421238660812378} 08/30/2021 15:29:05 - INFO - __main__ - Step 13115: {'lr': 0.0004930751256772593, 'samples': 2518080, 'steps': 13114, 'loss/train': 2.404543876647949} 08/30/2021 15:29:05 - INFO - __main__ - Step 13116: {'lr': 0.0004930738852542141, 'samples': 2518272, 'steps': 13115, 'loss/train': 1.7245795726776123} 08/30/2021 15:29:06 - INFO - __main__ - Step 13117: {'lr': 0.0004930726447216435, 'samples': 2518464, 'steps': 13116, 'loss/train': 0.9352125525474548} 08/30/2021 15:29:07 - INFO - __main__ - Step 13118: {'lr': 0.0004930714040795481, 'samples': 2518656, 'steps': 13117, 'loss/train': 1.5468991994857788} 08/30/2021 15:29:08 - INFO - __main__ - Step 13119: {'lr': 0.0004930701633279285, 'samples': 2518848, 'steps': 13118, 'loss/train': 1.8813652992248535} 08/30/2021 15:29:08 - INFO - __main__ - Step 13120: {'lr': 0.0004930689224667853, 'samples': 2519040, 'steps': 13119, 'loss/train': 1.510832667350769} 08/30/2021 15:29:08 - INFO - __main__ - Step 13121: {'lr': 0.0004930676814961189, 'samples': 2519232, 'steps': 13120, 'loss/train': 1.934361457824707} 08/30/2021 15:29:09 - INFO - __main__ - Step 13122: {'lr': 0.00049306644041593, 'samples': 2519424, 'steps': 13121, 'loss/train': 1.4233644008636475} 08/30/2021 15:29:10 - INFO - __main__ - Step 13123: {'lr': 0.0004930651992262191, 'samples': 2519616, 'steps': 13122, 'loss/train': 1.3029298782348633} 08/30/2021 15:29:11 - INFO - __main__ - Step 13124: {'lr': 0.0004930639579269866, 'samples': 2519808, 'steps': 13123, 'loss/train': 1.943230152130127} 08/30/2021 15:29:11 - INFO - __main__ - Step 13125: {'lr': 0.0004930627165182335, 'samples': 2520000, 'steps': 13124, 'loss/train': 1.8684998750686646} 08/30/2021 15:29:11 - INFO - __main__ - Step 13126: {'lr': 0.00049306147499996, 'samples': 2520192, 'steps': 13125, 'loss/train': 1.570236325263977} 08/30/2021 15:29:12 - INFO - __main__ - Step 13127: {'lr': 0.0004930602333721667, 'samples': 2520384, 'steps': 13126, 'loss/train': 1.9651436805725098} 08/30/2021 15:29:13 - INFO - __main__ - Step 13128: {'lr': 0.0004930589916348542, 'samples': 2520576, 'steps': 13127, 'loss/train': 1.6157217025756836} 08/30/2021 15:29:14 - INFO - __main__ - Step 13129: {'lr': 0.0004930577497880231, 'samples': 2520768, 'steps': 13128, 'loss/train': 1.955784797668457} 08/30/2021 15:29:14 - INFO - __main__ - Step 13130: {'lr': 0.000493056507831674, 'samples': 2520960, 'steps': 13129, 'loss/train': 1.4171680212020874} 08/30/2021 15:29:14 - INFO - __main__ - Step 13131: {'lr': 0.0004930552657658073, 'samples': 2521152, 'steps': 13130, 'loss/train': 1.706404209136963} 08/30/2021 15:29:15 - INFO - __main__ - Step 13132: {'lr': 0.0004930540235904237, 'samples': 2521344, 'steps': 13131, 'loss/train': 0.4153987169265747} 08/30/2021 15:29:17 - INFO - __main__ - Step 13133: {'lr': 0.0004930527813055237, 'samples': 2521536, 'steps': 13132, 'loss/train': 1.846850037574768} 08/30/2021 15:29:18 - INFO - __main__ - Step 13134: {'lr': 0.0004930515389111078, 'samples': 2521728, 'steps': 13133, 'loss/train': 0.9846248030662537} 08/30/2021 15:29:18 - INFO - __main__ - Step 13135: {'lr': 0.0004930502964071767, 'samples': 2521920, 'steps': 13134, 'loss/train': 1.8380756378173828} 08/30/2021 15:29:18 - INFO - __main__ - Step 13136: {'lr': 0.0004930490537937309, 'samples': 2522112, 'steps': 13135, 'loss/train': 1.9091602563858032} 08/30/2021 15:29:19 - INFO - __main__ - Step 13137: {'lr': 0.0004930478110707709, 'samples': 2522304, 'steps': 13136, 'loss/train': 1.7970647811889648} 08/30/2021 15:29:19 - INFO - __main__ - Step 13138: {'lr': 0.0004930465682382973, 'samples': 2522496, 'steps': 13137, 'loss/train': 1.3530611991882324} 08/30/2021 15:29:21 - INFO - __main__ - Step 13139: {'lr': 0.0004930453252963107, 'samples': 2522688, 'steps': 13138, 'loss/train': 1.371092677116394} 08/30/2021 15:29:21 - INFO - __main__ - Step 13140: {'lr': 0.0004930440822448115, 'samples': 2522880, 'steps': 13139, 'loss/train': 1.1301995515823364} 08/30/2021 15:29:21 - INFO - __main__ - Step 13141: {'lr': 0.0004930428390838006, 'samples': 2523072, 'steps': 13140, 'loss/train': 1.8004950284957886} 08/30/2021 15:29:22 - INFO - __main__ - Step 13142: {'lr': 0.0004930415958132782, 'samples': 2523264, 'steps': 13141, 'loss/train': 1.6366088390350342} 08/30/2021 15:29:22 - INFO - __main__ - Step 13143: {'lr': 0.0004930403524332451, 'samples': 2523456, 'steps': 13142, 'loss/train': 1.5675653219223022} 08/30/2021 15:29:22 - INFO - __main__ - Step 13144: {'lr': 0.0004930391089437017, 'samples': 2523648, 'steps': 13143, 'loss/train': 0.7293281555175781} 08/30/2021 15:29:24 - INFO - __main__ - Step 13145: {'lr': 0.0004930378653446487, 'samples': 2523840, 'steps': 13144, 'loss/train': 2.0169146060943604} 08/30/2021 15:29:25 - INFO - __main__ - Step 13146: {'lr': 0.0004930366216360865, 'samples': 2524032, 'steps': 13145, 'loss/train': 0.2024550586938858} 08/30/2021 15:29:25 - INFO - __main__ - Step 13147: {'lr': 0.0004930353778180158, 'samples': 2524224, 'steps': 13146, 'loss/train': 1.6575980186462402} 08/30/2021 15:29:25 - INFO - __main__ - Step 13148: {'lr': 0.0004930341338904371, 'samples': 2524416, 'steps': 13147, 'loss/train': 1.7918614149093628} 08/30/2021 15:29:26 - INFO - __main__ - Step 13149: {'lr': 0.000493032889853351, 'samples': 2524608, 'steps': 13148, 'loss/train': 1.5911606550216675} 08/30/2021 15:29:27 - INFO - __main__ - Step 13150: {'lr': 0.0004930316457067579, 'samples': 2524800, 'steps': 13149, 'loss/train': 2.0211563110351562} 08/30/2021 15:29:28 - INFO - __main__ - Step 13151: {'lr': 0.0004930304014506586, 'samples': 2524992, 'steps': 13150, 'loss/train': 1.477755069732666} 08/30/2021 15:29:28 - INFO - __main__ - Step 13152: {'lr': 0.0004930291570850536, 'samples': 2525184, 'steps': 13151, 'loss/train': 1.3428807258605957} 08/30/2021 15:29:28 - INFO - __main__ - Step 13153: {'lr': 0.0004930279126099433, 'samples': 2525376, 'steps': 13152, 'loss/train': 1.9181922674179077} 08/30/2021 15:29:29 - INFO - __main__ - Step 13154: {'lr': 0.0004930266680253284, 'samples': 2525568, 'steps': 13153, 'loss/train': 2.255140542984009} 08/30/2021 15:29:31 - INFO - __main__ - Step 13155: {'lr': 0.0004930254233312095, 'samples': 2525760, 'steps': 13154, 'loss/train': 1.7637264728546143} 08/30/2021 15:29:31 - INFO - __main__ - Step 13156: {'lr': 0.000493024178527587, 'samples': 2525952, 'steps': 13155, 'loss/train': 1.082656741142273} 08/30/2021 15:29:32 - INFO - __main__ - Step 13157: {'lr': 0.0004930229336144616, 'samples': 2526144, 'steps': 13156, 'loss/train': 0.9817512631416321} 08/30/2021 15:29:32 - INFO - __main__ - Step 13158: {'lr': 0.0004930216885918339, 'samples': 2526336, 'steps': 13157, 'loss/train': 0.7919743061065674} 08/30/2021 15:29:32 - INFO - __main__ - Step 13159: {'lr': 0.0004930204434597042, 'samples': 2526528, 'steps': 13158, 'loss/train': 0.7817718386650085} 08/30/2021 15:29:33 - INFO - __main__ - Step 13160: {'lr': 0.0004930191982180734, 'samples': 2526720, 'steps': 13159, 'loss/train': 1.6986939907073975} 08/30/2021 15:29:34 - INFO - __main__ - Step 13161: {'lr': 0.0004930179528669418, 'samples': 2526912, 'steps': 13160, 'loss/train': 2.3518199920654297} 08/30/2021 15:29:35 - INFO - __main__ - Step 13162: {'lr': 0.0004930167074063101, 'samples': 2527104, 'steps': 13161, 'loss/train': 1.8200459480285645} 08/30/2021 15:29:35 - INFO - __main__ - Step 13163: {'lr': 0.0004930154618361789, 'samples': 2527296, 'steps': 13162, 'loss/train': 1.7531898021697998} 08/30/2021 15:29:35 - INFO - __main__ - Step 13164: {'lr': 0.0004930142161565486, 'samples': 2527488, 'steps': 13163, 'loss/train': 1.6355242729187012} 08/30/2021 15:29:36 - INFO - __main__ - Step 13165: {'lr': 0.0004930129703674198, 'samples': 2527680, 'steps': 13164, 'loss/train': 1.484022855758667} 08/30/2021 15:29:36 - INFO - __main__ - Step 13166: {'lr': 0.0004930117244687931, 'samples': 2527872, 'steps': 13165, 'loss/train': 1.532153844833374} 08/30/2021 15:29:38 - INFO - __main__ - Step 13167: {'lr': 0.0004930104784606692, 'samples': 2528064, 'steps': 13166, 'loss/train': 0.9530429840087891} 08/30/2021 15:29:38 - INFO - __main__ - Step 13168: {'lr': 0.0004930092323430484, 'samples': 2528256, 'steps': 13167, 'loss/train': 1.9393770694732666} 08/30/2021 15:29:38 - INFO - __main__ - Step 13169: {'lr': 0.0004930079861159315, 'samples': 2528448, 'steps': 13168, 'loss/train': 1.4961903095245361} 08/30/2021 15:29:39 - INFO - __main__ - Step 13170: {'lr': 0.0004930067397793188, 'samples': 2528640, 'steps': 13169, 'loss/train': 1.5230586528778076} 08/30/2021 15:29:39 - INFO - __main__ - Step 13171: {'lr': 0.0004930054933332111, 'samples': 2528832, 'steps': 13170, 'loss/train': 1.8054306507110596} 08/30/2021 15:29:40 - INFO - __main__ - Step 13172: {'lr': 0.0004930042467776089, 'samples': 2529024, 'steps': 13171, 'loss/train': 1.5270925760269165} 08/30/2021 15:29:41 - INFO - __main__ - Step 13173: {'lr': 0.0004930030001125128, 'samples': 2529216, 'steps': 13172, 'loss/train': 2.004761219024658} 08/30/2021 15:29:41 - INFO - __main__ - Step 13174: {'lr': 0.000493001753337923, 'samples': 2529408, 'steps': 13173, 'loss/train': 1.9755587577819824} 08/30/2021 15:29:42 - INFO - __main__ - Step 13175: {'lr': 0.0004930005064538406, 'samples': 2529600, 'steps': 13174, 'loss/train': 1.6368324756622314} 08/30/2021 15:29:42 - INFO - __main__ - Step 13176: {'lr': 0.0004929992594602659, 'samples': 2529792, 'steps': 13175, 'loss/train': 2.0778143405914307} 08/30/2021 15:29:44 - INFO - __main__ - Step 13177: {'lr': 0.0004929980123571995, 'samples': 2529984, 'steps': 13176, 'loss/train': 1.456868290901184} 08/30/2021 15:29:44 - INFO - __main__ - Step 13178: {'lr': 0.000492996765144642, 'samples': 2530176, 'steps': 13177, 'loss/train': 1.6746386289596558} 08/30/2021 15:29:44 - INFO - __main__ - Step 13179: {'lr': 0.0004929955178225938, 'samples': 2530368, 'steps': 13178, 'loss/train': 1.5261129140853882} 08/30/2021 15:29:45 - INFO - __main__ - Step 13180: {'lr': 0.0004929942703910556, 'samples': 2530560, 'steps': 13179, 'loss/train': 1.931277871131897} 08/30/2021 15:29:45 - INFO - __main__ - Step 13181: {'lr': 0.0004929930228500279, 'samples': 2530752, 'steps': 13180, 'loss/train': 1.0765554904937744} 08/30/2021 15:29:46 - INFO - __main__ - Step 13182: {'lr': 0.0004929917751995114, 'samples': 2530944, 'steps': 13181, 'loss/train': 1.4679514169692993} 08/30/2021 15:29:47 - INFO - __main__ - Step 13183: {'lr': 0.0004929905274395064, 'samples': 2531136, 'steps': 13182, 'loss/train': 1.5988885164260864} 08/30/2021 15:29:47 - INFO - __main__ - Step 13184: {'lr': 0.0004929892795700137, 'samples': 2531328, 'steps': 13183, 'loss/train': 1.6287188529968262} 08/30/2021 15:29:48 - INFO - __main__ - Step 13185: {'lr': 0.0004929880315910338, 'samples': 2531520, 'steps': 13184, 'loss/train': 2.115199565887451} 08/30/2021 15:29:48 - INFO - __main__ - Step 13186: {'lr': 0.0004929867835025672, 'samples': 2531712, 'steps': 13185, 'loss/train': 1.7262567281723022} 08/30/2021 15:29:49 - INFO - __main__ - Step 13187: {'lr': 0.0004929855353046145, 'samples': 2531904, 'steps': 13186, 'loss/train': 2.0716159343719482} 08/30/2021 15:29:50 - INFO - __main__ - Step 13188: {'lr': 0.0004929842869971763, 'samples': 2532096, 'steps': 13187, 'loss/train': 1.6969057321548462} 08/30/2021 15:29:51 - INFO - __main__ - Step 13189: {'lr': 0.000492983038580253, 'samples': 2532288, 'steps': 13188, 'loss/train': 1.133381962776184} 08/30/2021 15:29:51 - INFO - __main__ - Step 13190: {'lr': 0.0004929817900538455, 'samples': 2532480, 'steps': 13189, 'loss/train': 1.6991007328033447} 08/30/2021 15:29:52 - INFO - __main__ - Step 13191: {'lr': 0.000492980541417954, 'samples': 2532672, 'steps': 13190, 'loss/train': 2.106668472290039} 08/30/2021 15:29:52 - INFO - __main__ - Step 13192: {'lr': 0.0004929792926725794, 'samples': 2532864, 'steps': 13191, 'loss/train': 1.9648419618606567} 08/30/2021 15:29:54 - INFO - __main__ - Step 13193: {'lr': 0.000492978043817722, 'samples': 2533056, 'steps': 13192, 'loss/train': 1.5465891361236572} 08/30/2021 15:29:54 - INFO - __main__ - Step 13194: {'lr': 0.0004929767948533823, 'samples': 2533248, 'steps': 13193, 'loss/train': 0.7830932140350342} 08/30/2021 15:29:54 - INFO - __main__ - Step 13195: {'lr': 0.0004929755457795612, 'samples': 2533440, 'steps': 13194, 'loss/train': 1.7344844341278076} 08/30/2021 15:29:55 - INFO - __main__ - Step 13196: {'lr': 0.0004929742965962589, 'samples': 2533632, 'steps': 13195, 'loss/train': 1.909066081047058} 08/30/2021 15:29:55 - INFO - __main__ - Step 13197: {'lr': 0.0004929730473034763, 'samples': 2533824, 'steps': 13196, 'loss/train': 1.7170289754867554} 08/30/2021 15:29:55 - INFO - __main__ - Step 13198: {'lr': 0.0004929717979012136, 'samples': 2534016, 'steps': 13197, 'loss/train': 1.6677168607711792} 08/30/2021 15:29:57 - INFO - __main__ - Step 13199: {'lr': 0.0004929705483894717, 'samples': 2534208, 'steps': 13198, 'loss/train': 1.4450730085372925} 08/30/2021 15:29:57 - INFO - __main__ - Step 13200: {'lr': 0.000492969298768251, 'samples': 2534400, 'steps': 13199, 'loss/train': 1.698410987854004} 08/30/2021 15:29:58 - INFO - __main__ - Step 13201: {'lr': 0.000492968049037552, 'samples': 2534592, 'steps': 13200, 'loss/train': 2.3205251693725586} 08/30/2021 15:29:58 - INFO - __main__ - Step 13202: {'lr': 0.0004929667991973754, 'samples': 2534784, 'steps': 13201, 'loss/train': 1.383763313293457} 08/30/2021 15:29:58 - INFO - __main__ - Step 13203: {'lr': 0.0004929655492477218, 'samples': 2534976, 'steps': 13202, 'loss/train': 2.1142139434814453} 08/30/2021 15:30:00 - INFO - __main__ - Step 13204: {'lr': 0.0004929642991885916, 'samples': 2535168, 'steps': 13203, 'loss/train': 1.5923293828964233} 08/30/2021 15:30:01 - INFO - __main__ - Step 13205: {'lr': 0.0004929630490199854, 'samples': 2535360, 'steps': 13204, 'loss/train': 1.6323366165161133} 08/30/2021 15:30:01 - INFO - __main__ - Step 13206: {'lr': 0.0004929617987419039, 'samples': 2535552, 'steps': 13205, 'loss/train': 1.70604407787323} 08/30/2021 15:30:01 - INFO - __main__ - Step 13207: {'lr': 0.0004929605483543474, 'samples': 2535744, 'steps': 13206, 'loss/train': 1.908188819885254} 08/30/2021 15:30:02 - INFO - __main__ - Step 13208: {'lr': 0.0004929592978573168, 'samples': 2535936, 'steps': 13207, 'loss/train': 0.18984326720237732} 08/30/2021 15:30:03 - INFO - __main__ - Step 13209: {'lr': 0.0004929580472508124, 'samples': 2536128, 'steps': 13208, 'loss/train': 1.8235244750976562} 08/30/2021 15:30:04 - INFO - __main__ - Step 13210: {'lr': 0.0004929567965348347, 'samples': 2536320, 'steps': 13209, 'loss/train': 1.8458211421966553} 08/30/2021 15:30:04 - INFO - __main__ - Step 13211: {'lr': 0.0004929555457093847, 'samples': 2536512, 'steps': 13210, 'loss/train': 1.812822699546814} 08/30/2021 15:30:05 - INFO - __main__ - Step 13212: {'lr': 0.0004929542947744625, 'samples': 2536704, 'steps': 13211, 'loss/train': 2.154083728790283} 08/30/2021 15:30:05 - INFO - __main__ - Step 13213: {'lr': 0.0004929530437300689, 'samples': 2536896, 'steps': 13212, 'loss/train': 1.3480331897735596} 08/30/2021 15:30:05 - INFO - __main__ - Step 13214: {'lr': 0.0004929517925762045, 'samples': 2537088, 'steps': 13213, 'loss/train': 1.5183898210525513} 08/30/2021 15:30:07 - INFO - __main__ - Step 13215: {'lr': 0.0004929505413128696, 'samples': 2537280, 'steps': 13214, 'loss/train': 0.8376405835151672} 08/30/2021 15:30:07 - INFO - __main__ - Step 13216: {'lr': 0.000492949289940065, 'samples': 2537472, 'steps': 13215, 'loss/train': 1.357436180114746} 08/30/2021 15:30:08 - INFO - __main__ - Step 13217: {'lr': 0.0004929480384577912, 'samples': 2537664, 'steps': 13216, 'loss/train': 1.9467532634735107} 08/30/2021 15:30:08 - INFO - __main__ - Step 13218: {'lr': 0.0004929467868660487, 'samples': 2537856, 'steps': 13217, 'loss/train': 1.9680449962615967} 08/30/2021 15:30:08 - INFO - __main__ - Step 13219: {'lr': 0.0004929455351648383, 'samples': 2538048, 'steps': 13218, 'loss/train': 1.0793286561965942} 08/30/2021 15:30:10 - INFO - __main__ - Step 13220: {'lr': 0.0004929442833541603, 'samples': 2538240, 'steps': 13219, 'loss/train': 2.0653204917907715} 08/30/2021 15:30:10 - INFO - __main__ - Step 13221: {'lr': 0.0004929430314340154, 'samples': 2538432, 'steps': 13220, 'loss/train': 2.175964593887329} 08/30/2021 15:30:11 - INFO - __main__ - Step 13222: {'lr': 0.000492941779404404, 'samples': 2538624, 'steps': 13221, 'loss/train': 1.3470433950424194} 08/30/2021 15:30:11 - INFO - __main__ - Step 13223: {'lr': 0.0004929405272653269, 'samples': 2538816, 'steps': 13222, 'loss/train': 1.9551588296890259} 08/30/2021 15:30:11 - INFO - __main__ - Step 13224: {'lr': 0.0004929392750167845, 'samples': 2539008, 'steps': 13223, 'loss/train': 1.7434378862380981} 08/30/2021 15:30:13 - INFO - __main__ - Step 13225: {'lr': 0.0004929380226587774, 'samples': 2539200, 'steps': 13224, 'loss/train': 1.5585001707077026} 08/30/2021 15:30:14 - INFO - __main__ - Step 13226: {'lr': 0.0004929367701913062, 'samples': 2539392, 'steps': 13225, 'loss/train': 1.1908096075057983} 08/30/2021 15:30:14 - INFO - __main__ - Step 13227: {'lr': 0.0004929355176143714, 'samples': 2539584, 'steps': 13226, 'loss/train': 1.8879069089889526} 08/30/2021 15:30:14 - INFO - __main__ - Step 13228: {'lr': 0.0004929342649279736, 'samples': 2539776, 'steps': 13227, 'loss/train': 1.9522531032562256} 08/30/2021 15:30:15 - INFO - __main__ - Step 13229: {'lr': 0.0004929330121321134, 'samples': 2539968, 'steps': 13228, 'loss/train': 1.3740723133087158} 08/30/2021 15:30:15 - INFO - __main__ - Step 13230: {'lr': 0.0004929317592267913, 'samples': 2540160, 'steps': 13229, 'loss/train': 2.5365686416625977} 08/30/2021 15:30:17 - INFO - __main__ - Step 13231: {'lr': 0.000492930506212008, 'samples': 2540352, 'steps': 13230, 'loss/train': 1.5278126001358032} 08/30/2021 15:30:18 - INFO - __main__ - Step 13232: {'lr': 0.0004929292530877638, 'samples': 2540544, 'steps': 13231, 'loss/train': 1.9534343481063843} 08/30/2021 15:30:18 - INFO - __main__ - Step 13233: {'lr': 0.0004929279998540596, 'samples': 2540736, 'steps': 13232, 'loss/train': 1.5942615270614624} 08/30/2021 15:30:19 - INFO - __main__ - Step 13234: {'lr': 0.0004929267465108956, 'samples': 2540928, 'steps': 13233, 'loss/train': 2.1778907775878906} 08/30/2021 15:30:19 - INFO - __main__ - Step 13235: {'lr': 0.0004929254930582728, 'samples': 2541120, 'steps': 13234, 'loss/train': 1.9903875589370728} 08/30/2021 15:30:19 - INFO - __main__ - Step 13236: {'lr': 0.0004929242394961914, 'samples': 2541312, 'steps': 13235, 'loss/train': 1.5462241172790527} 08/30/2021 15:30:21 - INFO - __main__ - Step 13237: {'lr': 0.000492922985824652, 'samples': 2541504, 'steps': 13236, 'loss/train': 0.9284600615501404} 08/30/2021 15:30:21 - INFO - __main__ - Step 13238: {'lr': 0.0004929217320436553, 'samples': 2541696, 'steps': 13237, 'loss/train': 1.269327163696289} 08/30/2021 15:30:22 - INFO - __main__ - Step 13239: {'lr': 0.0004929204781532018, 'samples': 2541888, 'steps': 13238, 'loss/train': 0.7098487019538879} 08/30/2021 15:30:22 - INFO - __main__ - Step 13240: {'lr': 0.0004929192241532921, 'samples': 2542080, 'steps': 13239, 'loss/train': 1.7692023515701294} 08/30/2021 15:30:22 - INFO - __main__ - Step 13241: {'lr': 0.0004929179700439269, 'samples': 2542272, 'steps': 13240, 'loss/train': 0.8944202661514282} 08/30/2021 15:30:24 - INFO - __main__ - Step 13242: {'lr': 0.0004929167158251065, 'samples': 2542464, 'steps': 13241, 'loss/train': 2.1399567127227783} 08/30/2021 15:30:24 - INFO - __main__ - Step 13243: {'lr': 0.0004929154614968315, 'samples': 2542656, 'steps': 13242, 'loss/train': 1.815641164779663} 08/30/2021 15:30:25 - INFO - __main__ - Step 13244: {'lr': 0.0004929142070591026, 'samples': 2542848, 'steps': 13243, 'loss/train': 1.5281676054000854} 08/30/2021 15:30:25 - INFO - __main__ - Step 13245: {'lr': 0.0004929129525119203, 'samples': 2543040, 'steps': 13244, 'loss/train': 1.5754562616348267} 08/30/2021 15:30:25 - INFO - __main__ - Step 13246: {'lr': 0.0004929116978552851, 'samples': 2543232, 'steps': 13245, 'loss/train': 1.7237863540649414} 08/30/2021 15:30:27 - INFO - __main__ - Step 13247: {'lr': 0.0004929104430891978, 'samples': 2543424, 'steps': 13246, 'loss/train': 1.7179235219955444} 08/30/2021 15:30:27 - INFO - __main__ - Step 13248: {'lr': 0.0004929091882136587, 'samples': 2543616, 'steps': 13247, 'loss/train': 1.0756183862686157} 08/30/2021 15:30:28 - INFO - __main__ - Step 13249: {'lr': 0.0004929079332286685, 'samples': 2543808, 'steps': 13248, 'loss/train': 1.8723208904266357} 08/30/2021 15:30:28 - INFO - __main__ - Step 13250: {'lr': 0.0004929066781342277, 'samples': 2544000, 'steps': 13249, 'loss/train': 1.806351900100708} 08/30/2021 15:30:28 - INFO - __main__ - Step 13251: {'lr': 0.0004929054229303369, 'samples': 2544192, 'steps': 13250, 'loss/train': 1.8154417276382446} 08/30/2021 15:30:29 - INFO - __main__ - Step 13252: {'lr': 0.0004929041676169967, 'samples': 2544384, 'steps': 13251, 'loss/train': 1.8198550939559937} 08/30/2021 15:30:31 - INFO - __main__ - Step 13253: {'lr': 0.0004929029121942077, 'samples': 2544576, 'steps': 13252, 'loss/train': 1.9762464761734009} 08/30/2021 15:30:31 - INFO - __main__ - Step 13254: {'lr': 0.0004929016566619703, 'samples': 2544768, 'steps': 13253, 'loss/train': 0.40915924310684204} 08/30/2021 15:30:32 - INFO - __main__ - Step 13255: {'lr': 0.0004929004010202851, 'samples': 2544960, 'steps': 13254, 'loss/train': 0.6848592162132263} 08/30/2021 15:30:32 - INFO - __main__ - Step 13256: {'lr': 0.0004928991452691528, 'samples': 2545152, 'steps': 13255, 'loss/train': 1.5487536191940308} 08/30/2021 15:30:32 - INFO - __main__ - Step 13257: {'lr': 0.0004928978894085739, 'samples': 2545344, 'steps': 13256, 'loss/train': 1.764366626739502} 08/30/2021 15:30:34 - INFO - __main__ - Step 13258: {'lr': 0.000492896633438549, 'samples': 2545536, 'steps': 13257, 'loss/train': 1.4504001140594482} 08/30/2021 15:30:34 - INFO - __main__ - Step 13259: {'lr': 0.0004928953773590785, 'samples': 2545728, 'steps': 13258, 'loss/train': 1.9216653108596802} 08/30/2021 15:30:35 - INFO - __main__ - Step 13260: {'lr': 0.0004928941211701632, 'samples': 2545920, 'steps': 13259, 'loss/train': 2.251816987991333} 08/30/2021 15:30:35 - INFO - __main__ - Step 13261: {'lr': 0.0004928928648718035, 'samples': 2546112, 'steps': 13260, 'loss/train': 1.874138593673706} 08/30/2021 15:30:35 - INFO - __main__ - Step 13262: {'lr': 0.0004928916084640001, 'samples': 2546304, 'steps': 13261, 'loss/train': 2.1850218772888184} 08/30/2021 15:30:37 - INFO - __main__ - Step 13263: {'lr': 0.0004928903519467534, 'samples': 2546496, 'steps': 13262, 'loss/train': 1.3525229692459106} 08/30/2021 15:30:37 - INFO - __main__ - Step 13264: {'lr': 0.0004928890953200641, 'samples': 2546688, 'steps': 13263, 'loss/train': 2.343693494796753} 08/30/2021 15:30:38 - INFO - __main__ - Step 13265: {'lr': 0.0004928878385839327, 'samples': 2546880, 'steps': 13264, 'loss/train': 1.8137409687042236} 08/30/2021 15:30:38 - INFO - __main__ - Step 13266: {'lr': 0.0004928865817383597, 'samples': 2547072, 'steps': 13265, 'loss/train': 1.2084486484527588} 08/30/2021 15:30:38 - INFO - __main__ - Step 13267: {'lr': 0.0004928853247833459, 'samples': 2547264, 'steps': 13266, 'loss/train': 1.4776631593704224} 08/30/2021 15:30:40 - INFO - __main__ - Step 13268: {'lr': 0.0004928840677188918, 'samples': 2547456, 'steps': 13267, 'loss/train': 1.9044543504714966} 08/30/2021 15:30:41 - INFO - __main__ - Step 13269: {'lr': 0.0004928828105449977, 'samples': 2547648, 'steps': 13268, 'loss/train': 1.7458200454711914} 08/30/2021 15:30:41 - INFO - __main__ - Step 13270: {'lr': 0.0004928815532616644, 'samples': 2547840, 'steps': 13269, 'loss/train': 1.4329379796981812} 08/30/2021 15:30:42 - INFO - __main__ - Step 13271: {'lr': 0.0004928802958688924, 'samples': 2548032, 'steps': 13270, 'loss/train': 1.7306426763534546} 08/30/2021 15:30:42 - INFO - __main__ - Step 13272: {'lr': 0.0004928790383666823, 'samples': 2548224, 'steps': 13271, 'loss/train': 0.7937204241752625} 08/30/2021 15:30:42 - INFO - __main__ - Step 13273: {'lr': 0.0004928777807550348, 'samples': 2548416, 'steps': 13272, 'loss/train': 1.482376217842102} 08/30/2021 15:30:44 - INFO - __main__ - Step 13274: {'lr': 0.0004928765230339502, 'samples': 2548608, 'steps': 13273, 'loss/train': 1.8877966403961182} 08/30/2021 15:30:45 - INFO - __main__ - Step 13275: {'lr': 0.000492875265203429, 'samples': 2548800, 'steps': 13274, 'loss/train': 1.852259635925293} 08/30/2021 15:30:45 - INFO - __main__ - Step 13276: {'lr': 0.0004928740072634722, 'samples': 2548992, 'steps': 13275, 'loss/train': 1.7160547971725464} 08/30/2021 15:30:45 - INFO - __main__ - Step 13277: {'lr': 0.0004928727492140801, 'samples': 2549184, 'steps': 13276, 'loss/train': 1.6651161909103394} 08/30/2021 15:30:46 - INFO - __main__ - Step 13278: {'lr': 0.0004928714910552533, 'samples': 2549376, 'steps': 13277, 'loss/train': 1.5182185173034668} 08/30/2021 15:30:48 - INFO - __main__ - Step 13279: {'lr': 0.0004928702327869922, 'samples': 2549568, 'steps': 13278, 'loss/train': 2.057767391204834} 08/30/2021 15:30:48 - INFO - __main__ - Step 13280: {'lr': 0.0004928689744092976, 'samples': 2549760, 'steps': 13279, 'loss/train': 1.9808582067489624} 08/30/2021 15:30:48 - INFO - __main__ - Step 13281: {'lr': 0.0004928677159221701, 'samples': 2549952, 'steps': 13280, 'loss/train': 2.1056995391845703} 08/30/2021 15:30:49 - INFO - __main__ - Step 13282: {'lr': 0.00049286645732561, 'samples': 2550144, 'steps': 13281, 'loss/train': 1.766992449760437} 08/30/2021 15:30:49 - INFO - __main__ - Step 13283: {'lr': 0.0004928651986196181, 'samples': 2550336, 'steps': 13282, 'loss/train': 1.5733379125595093} 08/30/2021 15:30:51 - INFO - __main__ - Step 13284: {'lr': 0.0004928639398041948, 'samples': 2550528, 'steps': 13283, 'loss/train': 0.18167980015277863} 08/30/2021 15:30:52 - INFO - __main__ - Step 13285: {'lr': 0.0004928626808793409, 'samples': 2550720, 'steps': 13284, 'loss/train': 1.9902777671813965} 08/30/2021 15:30:52 - INFO - __main__ - Step 13286: {'lr': 0.0004928614218450568, 'samples': 2550912, 'steps': 13285, 'loss/train': 0.9557822942733765} 08/30/2021 15:30:52 - INFO - __main__ - Step 13287: {'lr': 0.000492860162701343, 'samples': 2551104, 'steps': 13286, 'loss/train': 1.8120317459106445} 08/30/2021 15:30:53 - INFO - __main__ - Step 13288: {'lr': 0.0004928589034482001, 'samples': 2551296, 'steps': 13287, 'loss/train': 1.8779343366622925} 08/30/2021 15:30:54 - INFO - __main__ - Step 13289: {'lr': 0.000492857644085629, 'samples': 2551488, 'steps': 13288, 'loss/train': 1.497378945350647} 08/30/2021 15:30:55 - INFO - __main__ - Step 13290: {'lr': 0.0004928563846136296, 'samples': 2551680, 'steps': 13289, 'loss/train': 1.435523509979248} 08/30/2021 15:30:55 - INFO - __main__ - Step 13291: {'lr': 0.0004928551250322032, 'samples': 2551872, 'steps': 13290, 'loss/train': 1.588564395904541} 08/30/2021 15:30:55 - INFO - __main__ - Step 13292: {'lr': 0.0004928538653413499, 'samples': 2552064, 'steps': 13291, 'loss/train': 2.1687352657318115} 08/30/2021 15:30:56 - INFO - __main__ - Step 13293: {'lr': 0.0004928526055410704, 'samples': 2552256, 'steps': 13292, 'loss/train': 1.9012430906295776} 08/30/2021 15:30:56 - INFO - __main__ - Step 13294: {'lr': 0.0004928513456313653, 'samples': 2552448, 'steps': 13293, 'loss/train': 1.6171404123306274} 08/30/2021 15:30:58 - INFO - __main__ - Step 13295: {'lr': 0.000492850085612235, 'samples': 2552640, 'steps': 13294, 'loss/train': 1.7512423992156982} 08/30/2021 15:30:58 - INFO - __main__ - Step 13296: {'lr': 0.0004928488254836804, 'samples': 2552832, 'steps': 13295, 'loss/train': 2.2569284439086914} 08/30/2021 15:30:58 - INFO - __main__ - Step 13297: {'lr': 0.0004928475652457017, 'samples': 2553024, 'steps': 13296, 'loss/train': 2.118741750717163} 08/30/2021 15:30:59 - INFO - __main__ - Step 13298: {'lr': 0.0004928463048982998, 'samples': 2553216, 'steps': 13297, 'loss/train': 1.2525237798690796} 08/30/2021 15:30:59 - INFO - __main__ - Step 13299: {'lr': 0.0004928450444414749, 'samples': 2553408, 'steps': 13298, 'loss/train': 1.3978713750839233} 08/30/2021 15:31:00 - INFO - __main__ - Step 13300: {'lr': 0.0004928437838752278, 'samples': 2553600, 'steps': 13299, 'loss/train': 1.324633240699768} 08/30/2021 15:31:01 - INFO - __main__ - Step 13301: {'lr': 0.0004928425231995593, 'samples': 2553792, 'steps': 13300, 'loss/train': 1.0953269004821777} 08/30/2021 15:31:01 - INFO - __main__ - Step 13302: {'lr': 0.0004928412624144694, 'samples': 2553984, 'steps': 13301, 'loss/train': 2.4973647594451904} 08/30/2021 15:31:02 - INFO - __main__ - Step 13303: {'lr': 0.0004928400015199591, 'samples': 2554176, 'steps': 13302, 'loss/train': 1.8358838558197021} 08/30/2021 15:31:02 - INFO - __main__ - Step 13304: {'lr': 0.0004928387405160288, 'samples': 2554368, 'steps': 13303, 'loss/train': 1.4225980043411255} 08/30/2021 15:31:03 - INFO - __main__ - Step 13305: {'lr': 0.0004928374794026792, 'samples': 2554560, 'steps': 13304, 'loss/train': 2.1696431636810303} 08/30/2021 15:31:04 - INFO - __main__ - Step 13306: {'lr': 0.0004928362181799107, 'samples': 2554752, 'steps': 13305, 'loss/train': 1.1681604385375977} 08/30/2021 15:31:04 - INFO - __main__ - Step 13307: {'lr': 0.0004928349568477239, 'samples': 2554944, 'steps': 13306, 'loss/train': 2.1276936531066895} 08/30/2021 15:31:05 - INFO - __main__ - Step 13308: {'lr': 0.0004928336954061195, 'samples': 2555136, 'steps': 13307, 'loss/train': 2.125086784362793} 08/30/2021 15:31:05 - INFO - __main__ - Step 13309: {'lr': 0.000492832433855098, 'samples': 2555328, 'steps': 13308, 'loss/train': 1.6042321920394897} 08/30/2021 15:31:07 - INFO - __main__ - Step 13310: {'lr': 0.0004928311721946599, 'samples': 2555520, 'steps': 13309, 'loss/train': 2.4290051460266113} 08/30/2021 15:31:07 - INFO - __main__ - Step 13311: {'lr': 0.0004928299104248059, 'samples': 2555712, 'steps': 13310, 'loss/train': 1.592270016670227} 08/30/2021 15:31:07 - INFO - __main__ - Step 13312: {'lr': 0.0004928286485455365, 'samples': 2555904, 'steps': 13311, 'loss/train': 1.0809060335159302} 08/30/2021 15:31:08 - INFO - __main__ - Step 13313: {'lr': 0.0004928273865568521, 'samples': 2556096, 'steps': 13312, 'loss/train': 1.4615657329559326} 08/30/2021 15:31:08 - INFO - __main__ - Step 13314: {'lr': 0.0004928261244587536, 'samples': 2556288, 'steps': 13313, 'loss/train': 1.2980906963348389} 08/30/2021 15:31:08 - INFO - __main__ - Step 13315: {'lr': 0.0004928248622512412, 'samples': 2556480, 'steps': 13314, 'loss/train': 1.498451590538025} 08/30/2021 15:31:11 - INFO - __main__ - Step 13316: {'lr': 0.0004928235999343159, 'samples': 2556672, 'steps': 13315, 'loss/train': 2.0136260986328125} 08/30/2021 15:31:11 - INFO - __main__ - Step 13317: {'lr': 0.0004928223375079778, 'samples': 2556864, 'steps': 13316, 'loss/train': 1.6528249979019165} 08/30/2021 15:31:12 - INFO - __main__ - Step 13318: {'lr': 0.0004928210749722278, 'samples': 2557056, 'steps': 13317, 'loss/train': 1.390761137008667} 08/30/2021 15:31:12 - INFO - __main__ - Step 13319: {'lr': 0.0004928198123270664, 'samples': 2557248, 'steps': 13318, 'loss/train': 1.7772823572158813} 08/30/2021 15:31:13 - INFO - __main__ - Step 13320: {'lr': 0.0004928185495724942, 'samples': 2557440, 'steps': 13319, 'loss/train': 1.8425750732421875} 08/30/2021 15:31:13 - INFO - __main__ - Step 13321: {'lr': 0.0004928172867085115, 'samples': 2557632, 'steps': 13320, 'loss/train': 1.2989501953125} 08/30/2021 15:31:13 - INFO - __main__ - Step 13322: {'lr': 0.0004928160237351192, 'samples': 2557824, 'steps': 13321, 'loss/train': 1.7174687385559082} 08/30/2021 15:31:15 - INFO - __main__ - Step 13323: {'lr': 0.0004928147606523179, 'samples': 2558016, 'steps': 13322, 'loss/train': 1.8456381559371948} 08/30/2021 15:31:15 - INFO - __main__ - Step 13324: {'lr': 0.0004928134974601078, 'samples': 2558208, 'steps': 13323, 'loss/train': 1.8499038219451904} 08/30/2021 15:31:16 - INFO - __main__ - Step 13325: {'lr': 0.0004928122341584897, 'samples': 2558400, 'steps': 13324, 'loss/train': 1.5015943050384521} 08/30/2021 15:31:16 - INFO - __main__ - Step 13326: {'lr': 0.0004928109707474643, 'samples': 2558592, 'steps': 13325, 'loss/train': 1.7252732515335083} 08/30/2021 15:31:16 - INFO - __main__ - Step 13327: {'lr': 0.0004928097072270319, 'samples': 2558784, 'steps': 13326, 'loss/train': 1.6393089294433594} 08/30/2021 15:31:18 - INFO - __main__ - Step 13328: {'lr': 0.0004928084435971932, 'samples': 2558976, 'steps': 13327, 'loss/train': 1.2961522340774536} 08/30/2021 15:31:18 - INFO - __main__ - Step 13329: {'lr': 0.0004928071798579488, 'samples': 2559168, 'steps': 13328, 'loss/train': 1.9010658264160156} 08/30/2021 15:31:19 - INFO - __main__ - Step 13330: {'lr': 0.0004928059160092993, 'samples': 2559360, 'steps': 13329, 'loss/train': 3.0207693576812744} 08/30/2021 15:31:19 - INFO - __main__ - Step 13331: {'lr': 0.000492804652051245, 'samples': 2559552, 'steps': 13330, 'loss/train': 1.5045816898345947} 08/30/2021 15:31:19 - INFO - __main__ - Step 13332: {'lr': 0.0004928033879837868, 'samples': 2559744, 'steps': 13331, 'loss/train': 2.1083710193634033} 08/30/2021 15:31:21 - INFO - __main__ - Step 13333: {'lr': 0.0004928021238069251, 'samples': 2559936, 'steps': 13332, 'loss/train': 1.9268851280212402} 08/30/2021 15:31:21 - INFO - __main__ - Step 13334: {'lr': 0.0004928008595206605, 'samples': 2560128, 'steps': 13333, 'loss/train': 2.03450608253479} 08/30/2021 15:31:22 - INFO - __main__ - Step 13335: {'lr': 0.0004927995951249937, 'samples': 2560320, 'steps': 13334, 'loss/train': 1.4016634225845337} 08/30/2021 15:31:22 - INFO - __main__ - Step 13336: {'lr': 0.0004927983306199251, 'samples': 2560512, 'steps': 13335, 'loss/train': 1.840184211730957} 08/30/2021 15:31:22 - INFO - __main__ - Step 13337: {'lr': 0.0004927970660054552, 'samples': 2560704, 'steps': 13336, 'loss/train': 2.3702948093414307} 08/30/2021 15:31:24 - INFO - __main__ - Step 13338: {'lr': 0.0004927958012815849, 'samples': 2560896, 'steps': 13337, 'loss/train': 1.7123851776123047} 08/30/2021 15:31:25 - INFO - __main__ - Step 13339: {'lr': 0.0004927945364483144, 'samples': 2561088, 'steps': 13338, 'loss/train': 1.6064941883087158} 08/30/2021 15:31:25 - INFO - __main__ - Step 13340: {'lr': 0.0004927932715056444, 'samples': 2561280, 'steps': 13339, 'loss/train': 1.7054412364959717} 08/30/2021 15:31:25 - INFO - __main__ - Step 13341: {'lr': 0.0004927920064535756, 'samples': 2561472, 'steps': 13340, 'loss/train': 1.9482789039611816} 08/30/2021 15:31:26 - INFO - __main__ - Step 13342: {'lr': 0.0004927907412921084, 'samples': 2561664, 'steps': 13341, 'loss/train': 2.082087516784668} 08/30/2021 15:31:26 - INFO - __main__ - Step 13343: {'lr': 0.0004927894760212435, 'samples': 2561856, 'steps': 13342, 'loss/train': 2.1705963611602783} 08/30/2021 15:31:28 - INFO - __main__ - Step 13344: {'lr': 0.0004927882106409813, 'samples': 2562048, 'steps': 13343, 'loss/train': 1.5502218008041382} 08/30/2021 15:31:28 - INFO - __main__ - Step 13345: {'lr': 0.0004927869451513226, 'samples': 2562240, 'steps': 13344, 'loss/train': 1.7382903099060059} 08/30/2021 15:31:28 - INFO - __main__ - Step 13346: {'lr': 0.0004927856795522678, 'samples': 2562432, 'steps': 13345, 'loss/train': 1.8929860591888428} 08/30/2021 15:31:29 - INFO - __main__ - Step 13347: {'lr': 0.0004927844138438175, 'samples': 2562624, 'steps': 13346, 'loss/train': 2.2494239807128906} 08/30/2021 15:31:29 - INFO - __main__ - Step 13348: {'lr': 0.0004927831480259723, 'samples': 2562816, 'steps': 13347, 'loss/train': 1.2005528211593628} 08/30/2021 15:31:31 - INFO - __main__ - Step 13349: {'lr': 0.0004927818820987328, 'samples': 2563008, 'steps': 13348, 'loss/train': 1.6468842029571533} 08/30/2021 15:31:31 - INFO - __main__ - Step 13350: {'lr': 0.0004927806160620995, 'samples': 2563200, 'steps': 13349, 'loss/train': 3.6370012760162354} 08/30/2021 15:31:32 - INFO - __main__ - Step 13351: {'lr': 0.0004927793499160729, 'samples': 2563392, 'steps': 13350, 'loss/train': 1.8585752248764038} 08/30/2021 15:31:32 - INFO - __main__ - Step 13352: {'lr': 0.000492778083660654, 'samples': 2563584, 'steps': 13351, 'loss/train': 1.6590094566345215} 08/30/2021 15:31:32 - INFO - __main__ - Step 13353: {'lr': 0.0004927768172958427, 'samples': 2563776, 'steps': 13352, 'loss/train': 2.0702600479125977} 08/30/2021 15:31:34 - INFO - __main__ - Step 13354: {'lr': 0.00049277555082164, 'samples': 2563968, 'steps': 13353, 'loss/train': 2.8682162761688232} 08/30/2021 15:31:35 - INFO - __main__ - Step 13355: {'lr': 0.0004927742842380465, 'samples': 2564160, 'steps': 13354, 'loss/train': 2.250650644302368} 08/30/2021 15:31:35 - INFO - __main__ - Step 13356: {'lr': 0.0004927730175450626, 'samples': 2564352, 'steps': 13355, 'loss/train': 1.4539607763290405} 08/30/2021 15:31:35 - INFO - __main__ - Step 13357: {'lr': 0.0004927717507426887, 'samples': 2564544, 'steps': 13356, 'loss/train': 2.3869025707244873} 08/30/2021 15:31:36 - INFO - __main__ - Step 13358: {'lr': 0.0004927704838309259, 'samples': 2564736, 'steps': 13357, 'loss/train': 0.7346906661987305} 08/30/2021 15:31:36 - INFO - __main__ - Step 13359: {'lr': 0.0004927692168097743, 'samples': 2564928, 'steps': 13358, 'loss/train': 0.4545074701309204} 08/30/2021 15:31:38 - INFO - __main__ - Step 13360: {'lr': 0.0004927679496792347, 'samples': 2565120, 'steps': 13359, 'loss/train': 1.3047525882720947} 08/30/2021 15:31:38 - INFO - __main__ - Step 13361: {'lr': 0.0004927666824393076, 'samples': 2565312, 'steps': 13360, 'loss/train': 2.1561946868896484} 08/30/2021 15:31:38 - INFO - __main__ - Step 13362: {'lr': 0.0004927654150899937, 'samples': 2565504, 'steps': 13361, 'loss/train': 2.065976858139038} 08/30/2021 15:31:39 - INFO - __main__ - Step 13363: {'lr': 0.0004927641476312932, 'samples': 2565696, 'steps': 13362, 'loss/train': 1.631472110748291} 08/30/2021 15:31:39 - INFO - __main__ - Step 13364: {'lr': 0.000492762880063207, 'samples': 2565888, 'steps': 13363, 'loss/train': 1.8592429161071777} 08/30/2021 15:31:40 - INFO - __main__ - Step 13365: {'lr': 0.0004927616123857357, 'samples': 2566080, 'steps': 13364, 'loss/train': 1.8340822458267212} 08/30/2021 15:31:41 - INFO - __main__ - Step 13366: {'lr': 0.0004927603445988797, 'samples': 2566272, 'steps': 13365, 'loss/train': 1.757806658744812} 08/30/2021 15:31:41 - INFO - __main__ - Step 13367: {'lr': 0.0004927590767026396, 'samples': 2566464, 'steps': 13366, 'loss/train': 2.1953835487365723} 08/30/2021 15:31:42 - INFO - __main__ - Step 13368: {'lr': 0.0004927578086970161, 'samples': 2566656, 'steps': 13367, 'loss/train': 1.2725802659988403} 08/30/2021 15:31:42 - INFO - __main__ - Step 13369: {'lr': 0.0004927565405820096, 'samples': 2566848, 'steps': 13368, 'loss/train': 1.6763789653778076} 08/30/2021 15:31:43 - INFO - __main__ - Step 13370: {'lr': 0.0004927552723576207, 'samples': 2567040, 'steps': 13369, 'loss/train': 1.4753245115280151} 08/30/2021 15:31:44 - INFO - __main__ - Step 13371: {'lr': 0.0004927540040238501, 'samples': 2567232, 'steps': 13370, 'loss/train': 1.8064439296722412} 08/30/2021 15:31:44 - INFO - __main__ - Step 13372: {'lr': 0.0004927527355806983, 'samples': 2567424, 'steps': 13371, 'loss/train': 1.9299222230911255} 08/30/2021 15:31:45 - INFO - __main__ - Step 13373: {'lr': 0.0004927514670281659, 'samples': 2567616, 'steps': 13372, 'loss/train': 2.529559373855591} 08/30/2021 15:31:45 - INFO - __main__ - Step 13374: {'lr': 0.0004927501983662534, 'samples': 2567808, 'steps': 13373, 'loss/train': 1.4066401720046997} 08/30/2021 15:31:47 - INFO - __main__ - Step 13375: {'lr': 0.0004927489295949613, 'samples': 2568000, 'steps': 13374, 'loss/train': 1.5471380949020386} 08/30/2021 15:31:47 - INFO - __main__ - Step 13376: {'lr': 0.0004927476607142904, 'samples': 2568192, 'steps': 13375, 'loss/train': 1.9019792079925537} 08/30/2021 15:31:47 - INFO - __main__ - Step 13377: {'lr': 0.0004927463917242411, 'samples': 2568384, 'steps': 13376, 'loss/train': 0.1306307017803192} 08/30/2021 15:31:48 - INFO - __main__ - Step 13378: {'lr': 0.0004927451226248141, 'samples': 2568576, 'steps': 13377, 'loss/train': 1.5481854677200317} 08/30/2021 15:31:48 - INFO - __main__ - Step 13379: {'lr': 0.0004927438534160098, 'samples': 2568768, 'steps': 13378, 'loss/train': 1.2974473237991333} 08/30/2021 15:31:49 - INFO - __main__ - Step 13380: {'lr': 0.0004927425840978289, 'samples': 2568960, 'steps': 13379, 'loss/train': 1.4157050848007202} 08/30/2021 15:31:50 - INFO - __main__ - Step 13381: {'lr': 0.0004927413146702719, 'samples': 2569152, 'steps': 13380, 'loss/train': 1.8663315773010254} 08/30/2021 15:31:50 - INFO - __main__ - Step 13382: {'lr': 0.0004927400451333394, 'samples': 2569344, 'steps': 13381, 'loss/train': 2.2063639163970947} 08/30/2021 15:31:51 - INFO - __main__ - Step 13383: {'lr': 0.0004927387754870321, 'samples': 2569536, 'steps': 13382, 'loss/train': 2.020737648010254} 08/30/2021 15:31:51 - INFO - __main__ - Step 13384: {'lr': 0.0004927375057313504, 'samples': 2569728, 'steps': 13383, 'loss/train': 1.731574535369873} 08/30/2021 15:31:53 - INFO - __main__ - Step 13385: {'lr': 0.0004927362358662948, 'samples': 2569920, 'steps': 13384, 'loss/train': 2.4749715328216553} 08/30/2021 15:31:53 - INFO - __main__ - Step 13386: {'lr': 0.0004927349658918662, 'samples': 2570112, 'steps': 13385, 'loss/train': 1.827108383178711} 08/30/2021 15:31:54 - INFO - __main__ - Step 13387: {'lr': 0.0004927336958080648, 'samples': 2570304, 'steps': 13386, 'loss/train': 0.7441443800926208} 08/30/2021 15:31:54 - INFO - __main__ - Step 13388: {'lr': 0.0004927324256148914, 'samples': 2570496, 'steps': 13387, 'loss/train': 1.480206847190857} 08/30/2021 15:31:54 - INFO - __main__ - Step 13389: {'lr': 0.0004927311553123465, 'samples': 2570688, 'steps': 13388, 'loss/train': 1.9811094999313354} 08/30/2021 15:31:56 - INFO - __main__ - Step 13390: {'lr': 0.0004927298849004307, 'samples': 2570880, 'steps': 13389, 'loss/train': 2.4168450832366943} 08/30/2021 15:31:57 - INFO - __main__ - Step 13391: {'lr': 0.0004927286143791447, 'samples': 2571072, 'steps': 13390, 'loss/train': 1.5338354110717773} 08/30/2021 15:31:57 - INFO - __main__ - Step 13392: {'lr': 0.0004927273437484888, 'samples': 2571264, 'steps': 13391, 'loss/train': 2.638021230697632} 08/30/2021 15:31:57 - INFO - __main__ - Step 13393: {'lr': 0.0004927260730084636, 'samples': 2571456, 'steps': 13392, 'loss/train': 1.6690860986709595} 08/30/2021 15:31:58 - INFO - __main__ - Step 13394: {'lr': 0.0004927248021590699, 'samples': 2571648, 'steps': 13393, 'loss/train': 1.7890369892120361} 08/30/2021 15:31:58 - INFO - __main__ - Step 13395: {'lr': 0.0004927235312003082, 'samples': 2571840, 'steps': 13394, 'loss/train': 1.6572185754776} 08/30/2021 15:32:00 - INFO - __main__ - Step 13396: {'lr': 0.0004927222601321789, 'samples': 2572032, 'steps': 13395, 'loss/train': 1.8415395021438599} 08/30/2021 15:32:00 - INFO - __main__ - Step 13397: {'lr': 0.0004927209889546828, 'samples': 2572224, 'steps': 13396, 'loss/train': 1.4626591205596924} 08/30/2021 15:32:01 - INFO - __main__ - Step 13398: {'lr': 0.0004927197176678203, 'samples': 2572416, 'steps': 13397, 'loss/train': 1.4553471803665161} 08/30/2021 15:32:01 - INFO - __main__ - Step 13399: {'lr': 0.000492718446271592, 'samples': 2572608, 'steps': 13398, 'loss/train': 1.4588000774383545} 08/30/2021 15:32:01 - INFO - __main__ - Step 13400: {'lr': 0.0004927171747659986, 'samples': 2572800, 'steps': 13399, 'loss/train': 1.9691166877746582} 08/30/2021 15:32:03 - INFO - __main__ - Step 13401: {'lr': 0.0004927159031510405, 'samples': 2572992, 'steps': 13400, 'loss/train': 1.2933005094528198} 08/30/2021 15:32:03 - INFO - __main__ - Step 13402: {'lr': 0.0004927146314267184, 'samples': 2573184, 'steps': 13401, 'loss/train': 1.8195914030075073} 08/30/2021 15:32:04 - INFO - __main__ - Step 13403: {'lr': 0.000492713359593033, 'samples': 2573376, 'steps': 13402, 'loss/train': 1.3688124418258667} 08/30/2021 15:32:04 - INFO - __main__ - Step 13404: {'lr': 0.0004927120876499846, 'samples': 2573568, 'steps': 13403, 'loss/train': 1.0743030309677124} 08/30/2021 15:32:04 - INFO - __main__ - Step 13405: {'lr': 0.0004927108155975738, 'samples': 2573760, 'steps': 13404, 'loss/train': 0.2135283201932907} 08/30/2021 15:32:06 - INFO - __main__ - Step 13406: {'lr': 0.0004927095434358012, 'samples': 2573952, 'steps': 13405, 'loss/train': 1.4170094728469849} 08/30/2021 15:32:06 - INFO - __main__ - Step 13407: {'lr': 0.0004927082711646676, 'samples': 2574144, 'steps': 13406, 'loss/train': 1.9869948625564575} 08/30/2021 15:32:07 - INFO - __main__ - Step 13408: {'lr': 0.0004927069987841733, 'samples': 2574336, 'steps': 13407, 'loss/train': 1.0781617164611816} 08/30/2021 15:32:07 - INFO - __main__ - Step 13409: {'lr': 0.0004927057262943189, 'samples': 2574528, 'steps': 13408, 'loss/train': 2.1366934776306152} 08/30/2021 15:32:07 - INFO - __main__ - Step 13410: {'lr': 0.0004927044536951052, 'samples': 2574720, 'steps': 13409, 'loss/train': 1.9036860466003418} 08/30/2021 15:32:09 - INFO - __main__ - Step 13411: {'lr': 0.0004927031809865324, 'samples': 2574912, 'steps': 13410, 'loss/train': 1.7845879793167114} 08/30/2021 15:32:09 - INFO - __main__ - Step 13412: {'lr': 0.0004927019081686015, 'samples': 2575104, 'steps': 13411, 'loss/train': 1.9031624794006348} 08/30/2021 15:32:10 - INFO - __main__ - Step 13413: {'lr': 0.0004927006352413128, 'samples': 2575296, 'steps': 13412, 'loss/train': 1.0926494598388672} 08/30/2021 15:32:10 - INFO - __main__ - Step 13414: {'lr': 0.000492699362204667, 'samples': 2575488, 'steps': 13413, 'loss/train': 1.0936707258224487} 08/30/2021 15:32:10 - INFO - __main__ - Step 13415: {'lr': 0.0004926980890586645, 'samples': 2575680, 'steps': 13414, 'loss/train': 1.6012905836105347} 08/30/2021 15:32:12 - INFO - __main__ - Step 13416: {'lr': 0.000492696815803306, 'samples': 2575872, 'steps': 13415, 'loss/train': 1.9375407695770264} 08/30/2021 15:32:12 - INFO - __main__ - Step 13417: {'lr': 0.0004926955424385921, 'samples': 2576064, 'steps': 13416, 'loss/train': 1.780282974243164} 08/30/2021 15:32:13 - INFO - __main__ - Step 13418: {'lr': 0.0004926942689645234, 'samples': 2576256, 'steps': 13417, 'loss/train': 0.8918399810791016} 08/30/2021 15:32:13 - INFO - __main__ - Step 13419: {'lr': 0.0004926929953811003, 'samples': 2576448, 'steps': 13418, 'loss/train': 1.4750359058380127} 08/30/2021 15:32:13 - INFO - __main__ - Step 13420: {'lr': 0.0004926917216883235, 'samples': 2576640, 'steps': 13419, 'loss/train': 1.820640206336975} 08/30/2021 15:32:15 - INFO - __main__ - Step 13421: {'lr': 0.0004926904478861937, 'samples': 2576832, 'steps': 13420, 'loss/train': 1.9349567890167236} 08/30/2021 15:32:15 - INFO - __main__ - Step 13422: {'lr': 0.0004926891739747111, 'samples': 2577024, 'steps': 13421, 'loss/train': 2.1062088012695312} 08/30/2021 15:32:16 - INFO - __main__ - Step 13423: {'lr': 0.0004926878999538766, 'samples': 2577216, 'steps': 13422, 'loss/train': 1.8544186353683472} 08/30/2021 15:32:16 - INFO - __main__ - Step 13424: {'lr': 0.0004926866258236907, 'samples': 2577408, 'steps': 13423, 'loss/train': 2.040912389755249} 08/30/2021 15:32:16 - INFO - __main__ - Step 13425: {'lr': 0.000492685351584154, 'samples': 2577600, 'steps': 13424, 'loss/train': 1.3988056182861328} 08/30/2021 15:32:18 - INFO - __main__ - Step 13426: {'lr': 0.000492684077235267, 'samples': 2577792, 'steps': 13425, 'loss/train': 0.15480317175388336} 08/30/2021 15:32:18 - INFO - __main__ - Step 13427: {'lr': 0.0004926828027770302, 'samples': 2577984, 'steps': 13426, 'loss/train': 1.557691216468811} 08/30/2021 15:32:19 - INFO - __main__ - Step 13428: {'lr': 0.0004926815282094443, 'samples': 2578176, 'steps': 13427, 'loss/train': 1.267248272895813} 08/30/2021 15:32:19 - INFO - __main__ - Step 13429: {'lr': 0.00049268025353251, 'samples': 2578368, 'steps': 13428, 'loss/train': 1.7829160690307617} 08/30/2021 15:32:19 - INFO - __main__ - Step 13430: {'lr': 0.0004926789787462276, 'samples': 2578560, 'steps': 13429, 'loss/train': 1.8831775188446045} 08/30/2021 15:32:21 - INFO - __main__ - Step 13431: {'lr': 0.0004926777038505978, 'samples': 2578752, 'steps': 13430, 'loss/train': 2.025161027908325} 08/30/2021 15:32:22 - INFO - __main__ - Step 13432: {'lr': 0.0004926764288456212, 'samples': 2578944, 'steps': 13431, 'loss/train': 1.5182650089263916} 08/30/2021 15:32:22 - INFO - __main__ - Step 13433: {'lr': 0.0004926751537312982, 'samples': 2579136, 'steps': 13432, 'loss/train': 2.0059070587158203} 08/30/2021 15:32:22 - INFO - __main__ - Step 13434: {'lr': 0.0004926738785076297, 'samples': 2579328, 'steps': 13433, 'loss/train': 1.5889866352081299} 08/30/2021 15:32:23 - INFO - __main__ - Step 13435: {'lr': 0.000492672603174616, 'samples': 2579520, 'steps': 13434, 'loss/train': 1.8432821035385132} 08/30/2021 15:32:23 - INFO - __main__ - Step 13436: {'lr': 0.0004926713277322579, 'samples': 2579712, 'steps': 13435, 'loss/train': 1.587931513786316} 08/30/2021 15:32:25 - INFO - __main__ - Step 13437: {'lr': 0.0004926700521805557, 'samples': 2579904, 'steps': 13436, 'loss/train': 0.8050898909568787} 08/30/2021 15:32:25 - INFO - __main__ - Step 13438: {'lr': 0.0004926687765195102, 'samples': 2580096, 'steps': 13437, 'loss/train': 1.083593487739563} 08/30/2021 15:32:26 - INFO - __main__ - Step 13439: {'lr': 0.0004926675007491218, 'samples': 2580288, 'steps': 13438, 'loss/train': 1.3361473083496094} 08/30/2021 15:32:26 - INFO - __main__ - Step 13440: {'lr': 0.0004926662248693912, 'samples': 2580480, 'steps': 13439, 'loss/train': 2.625636577606201} 08/30/2021 15:32:26 - INFO - __main__ - Step 13441: {'lr': 0.000492664948880319, 'samples': 2580672, 'steps': 13440, 'loss/train': 0.5153382420539856} 08/30/2021 15:32:28 - INFO - __main__ - Step 13442: {'lr': 0.0004926636727819057, 'samples': 2580864, 'steps': 13441, 'loss/train': 1.1688904762268066} 08/30/2021 15:32:28 - INFO - __main__ - Step 13443: {'lr': 0.0004926623965741519, 'samples': 2581056, 'steps': 13442, 'loss/train': 0.3777546286582947} 08/30/2021 15:32:29 - INFO - __main__ - Step 13444: {'lr': 0.0004926611202570582, 'samples': 2581248, 'steps': 13443, 'loss/train': 2.0682897567749023} 08/30/2021 15:32:29 - INFO - __main__ - Step 13445: {'lr': 0.0004926598438306252, 'samples': 2581440, 'steps': 13444, 'loss/train': 1.3861676454544067} 08/30/2021 15:32:29 - INFO - __main__ - Step 13446: {'lr': 0.0004926585672948532, 'samples': 2581632, 'steps': 13445, 'loss/train': 1.8295286893844604} 08/30/2021 15:32:32 - INFO - __main__ - Step 13447: {'lr': 0.0004926572906497432, 'samples': 2581824, 'steps': 13446, 'loss/train': 2.2387988567352295} 08/30/2021 15:32:32 - INFO - __main__ - Step 13448: {'lr': 0.0004926560138952955, 'samples': 2582016, 'steps': 13447, 'loss/train': 1.6616758108139038} 08/30/2021 15:32:32 - INFO - __main__ - Step 13449: {'lr': 0.0004926547370315106, 'samples': 2582208, 'steps': 13448, 'loss/train': 1.9965187311172485} 08/30/2021 15:32:33 - INFO - __main__ - Step 13450: {'lr': 0.0004926534600583894, 'samples': 2582400, 'steps': 13449, 'loss/train': 1.5119333267211914} 08/30/2021 15:32:33 - INFO - __main__ - Step 13451: {'lr': 0.0004926521829759323, 'samples': 2582592, 'steps': 13450, 'loss/train': 0.17454367876052856} 08/30/2021 15:32:35 - INFO - __main__ - Step 13452: {'lr': 0.0004926509057841397, 'samples': 2582784, 'steps': 13451, 'loss/train': 0.9735919237136841} 08/30/2021 15:32:35 - INFO - __main__ - Step 13453: {'lr': 0.0004926496284830125, 'samples': 2582976, 'steps': 13452, 'loss/train': 1.9807783365249634} 08/30/2021 15:32:36 - INFO - __main__ - Step 13454: {'lr': 0.0004926483510725511, 'samples': 2583168, 'steps': 13453, 'loss/train': 2.1969621181488037} 08/30/2021 15:32:36 - INFO - __main__ - Step 13455: {'lr': 0.000492647073552756, 'samples': 2583360, 'steps': 13454, 'loss/train': 1.5524709224700928} 08/30/2021 15:32:36 - INFO - __main__ - Step 13456: {'lr': 0.000492645795923628, 'samples': 2583552, 'steps': 13455, 'loss/train': 1.983012318611145} 08/30/2021 15:32:37 - INFO - __main__ - Step 13457: {'lr': 0.0004926445181851675, 'samples': 2583744, 'steps': 13456, 'loss/train': 1.7045586109161377} 08/30/2021 15:32:38 - INFO - __main__ - Step 13458: {'lr': 0.0004926432403373752, 'samples': 2583936, 'steps': 13457, 'loss/train': 0.1535819172859192} 08/30/2021 15:32:39 - INFO - __main__ - Step 13459: {'lr': 0.0004926419623802515, 'samples': 2584128, 'steps': 13458, 'loss/train': 2.1512367725372314} 08/30/2021 15:32:39 - INFO - __main__ - Step 13460: {'lr': 0.0004926406843137971, 'samples': 2584320, 'steps': 13459, 'loss/train': 1.4353790283203125} 08/30/2021 15:32:40 - INFO - __main__ - Step 13461: {'lr': 0.0004926394061380126, 'samples': 2584512, 'steps': 13460, 'loss/train': 1.5081475973129272} 08/30/2021 15:32:40 - INFO - __main__ - Step 13462: {'lr': 0.0004926381278528984, 'samples': 2584704, 'steps': 13461, 'loss/train': 1.1380120515823364} 08/30/2021 15:32:42 - INFO - __main__ - Step 13463: {'lr': 0.0004926368494584553, 'samples': 2584896, 'steps': 13462, 'loss/train': 0.14483055472373962} 08/30/2021 15:32:42 - INFO - __main__ - Step 13464: {'lr': 0.0004926355709546838, 'samples': 2585088, 'steps': 13463, 'loss/train': 1.4653459787368774} 08/30/2021 15:32:43 - INFO - __main__ - Step 13465: {'lr': 0.0004926342923415844, 'samples': 2585280, 'steps': 13464, 'loss/train': 1.9759973287582397} 08/30/2021 15:32:43 - INFO - __main__ - Step 13466: {'lr': 0.0004926330136191577, 'samples': 2585472, 'steps': 13465, 'loss/train': 1.9447349309921265} 08/30/2021 15:32:43 - INFO - __main__ - Step 13467: {'lr': 0.0004926317347874044, 'samples': 2585664, 'steps': 13466, 'loss/train': 3.166593074798584} 08/30/2021 15:32:44 - INFO - __main__ - Step 13468: {'lr': 0.000492630455846325, 'samples': 2585856, 'steps': 13467, 'loss/train': 0.10132548213005066} 08/30/2021 15:32:45 - INFO - __main__ - Step 13469: {'lr': 0.0004926291767959199, 'samples': 2586048, 'steps': 13468, 'loss/train': 1.5672332048416138} 08/30/2021 15:32:46 - INFO - __main__ - Step 13470: {'lr': 0.00049262789763619, 'samples': 2586240, 'steps': 13469, 'loss/train': 1.7698413133621216} 08/30/2021 15:32:46 - INFO - __main__ - Step 13471: {'lr': 0.0004926266183671356, 'samples': 2586432, 'steps': 13470, 'loss/train': 2.4681591987609863} 08/30/2021 15:32:46 - INFO - __main__ - Step 13472: {'lr': 0.0004926253389887575, 'samples': 2586624, 'steps': 13471, 'loss/train': 1.5869358777999878} 08/30/2021 15:32:47 - INFO - __main__ - Step 13473: {'lr': 0.0004926240595010561, 'samples': 2586816, 'steps': 13472, 'loss/train': 1.713945746421814} 08/30/2021 15:32:48 - INFO - __main__ - Step 13474: {'lr': 0.000492622779904032, 'samples': 2587008, 'steps': 13473, 'loss/train': 1.8002439737319946} 08/30/2021 15:32:49 - INFO - __main__ - Step 13475: {'lr': 0.000492621500197686, 'samples': 2587200, 'steps': 13474, 'loss/train': 1.5905848741531372} 08/30/2021 15:32:49 - INFO - __main__ - Step 13476: {'lr': 0.0004926202203820182, 'samples': 2587392, 'steps': 13475, 'loss/train': 1.6016812324523926} 08/30/2021 15:32:49 - INFO - __main__ - Step 13477: {'lr': 0.0004926189404570297, 'samples': 2587584, 'steps': 13476, 'loss/train': 1.763638973236084} 08/30/2021 15:32:50 - INFO - __main__ - Step 13478: {'lr': 0.0004926176604227208, 'samples': 2587776, 'steps': 13477, 'loss/train': 2.030625343322754} 08/30/2021 15:32:51 - INFO - __main__ - Step 13479: {'lr': 0.0004926163802790922, 'samples': 2587968, 'steps': 13478, 'loss/train': 2.518698215484619} 08/30/2021 15:32:52 - INFO - __main__ - Step 13480: {'lr': 0.0004926151000261442, 'samples': 2588160, 'steps': 13479, 'loss/train': 1.3181692361831665} 08/30/2021 15:32:52 - INFO - __main__ - Step 13481: {'lr': 0.0004926138196638777, 'samples': 2588352, 'steps': 13480, 'loss/train': 1.6662728786468506} 08/30/2021 15:32:52 - INFO - __main__ - Step 13482: {'lr': 0.0004926125391922932, 'samples': 2588544, 'steps': 13481, 'loss/train': 1.7330400943756104} 08/30/2021 15:32:53 - INFO - __main__ - Step 13483: {'lr': 0.0004926112586113912, 'samples': 2588736, 'steps': 13482, 'loss/train': 1.8911123275756836} 08/30/2021 15:32:55 - INFO - __main__ - Step 13484: {'lr': 0.0004926099779211723, 'samples': 2588928, 'steps': 13483, 'loss/train': 1.4070862531661987} 08/30/2021 15:32:55 - INFO - __main__ - Step 13485: {'lr': 0.0004926086971216371, 'samples': 2589120, 'steps': 13484, 'loss/train': 1.8312996625900269} 08/30/2021 15:32:55 - INFO - __main__ - Step 13486: {'lr': 0.0004926074162127862, 'samples': 2589312, 'steps': 13485, 'loss/train': 1.3259183168411255} 08/30/2021 15:32:56 - INFO - __main__ - Step 13487: {'lr': 0.0004926061351946201, 'samples': 2589504, 'steps': 13486, 'loss/train': 1.5153173208236694} 08/30/2021 15:32:56 - INFO - __main__ - Step 13488: {'lr': 0.0004926048540671394, 'samples': 2589696, 'steps': 13487, 'loss/train': 0.09712362289428711} 08/30/2021 15:32:56 - INFO - __main__ - Step 13489: {'lr': 0.0004926035728303447, 'samples': 2589888, 'steps': 13488, 'loss/train': 1.635308027267456} 08/30/2021 15:32:57 - INFO - __main__ - Step 13490: {'lr': 0.0004926022914842366, 'samples': 2590080, 'steps': 13489, 'loss/train': 1.9806077480316162} 08/30/2021 15:32:58 - INFO - __main__ - Step 13491: {'lr': 0.0004926010100288156, 'samples': 2590272, 'steps': 13490, 'loss/train': 2.0295376777648926} 08/30/2021 15:32:59 - INFO - __main__ - Step 13492: {'lr': 0.0004925997284640823, 'samples': 2590464, 'steps': 13491, 'loss/train': 1.9048993587493896} 08/30/2021 15:32:59 - INFO - __main__ - Step 13493: {'lr': 0.0004925984467900374, 'samples': 2590656, 'steps': 13492, 'loss/train': 1.0696717500686646} 08/30/2021 15:32:59 - INFO - __main__ - Step 13494: {'lr': 0.0004925971650066814, 'samples': 2590848, 'steps': 13493, 'loss/train': 1.2702785730361938} 08/30/2021 15:33:00 - INFO - __main__ - Step 13495: {'lr': 0.0004925958831140147, 'samples': 2591040, 'steps': 13494, 'loss/train': 1.4568878412246704} 08/30/2021 15:33:01 - INFO - __main__ - Step 13496: {'lr': 0.0004925946011120382, 'samples': 2591232, 'steps': 13495, 'loss/train': 0.07764939963817596} 08/30/2021 15:33:02 - INFO - __main__ - Step 13497: {'lr': 0.0004925933190007523, 'samples': 2591424, 'steps': 13496, 'loss/train': 1.8755857944488525} 08/30/2021 15:33:02 - INFO - __main__ - Step 13498: {'lr': 0.0004925920367801575, 'samples': 2591616, 'steps': 13497, 'loss/train': 1.6979717016220093} 08/30/2021 15:33:02 - INFO - __main__ - Step 13499: {'lr': 0.0004925907544502545, 'samples': 2591808, 'steps': 13498, 'loss/train': 2.2595162391662598} 08/30/2021 15:33:03 - INFO - __main__ - Step 13500: {'lr': 0.000492589472011044, 'samples': 2592000, 'steps': 13499, 'loss/train': 1.2787915468215942} 08/30/2021 15:33:04 - INFO - __main__ - Step 13501: {'lr': 0.0004925881894625263, 'samples': 2592192, 'steps': 13500, 'loss/train': 1.5989959239959717} 08/30/2021 15:33:05 - INFO - __main__ - Step 13502: {'lr': 0.0004925869068047021, 'samples': 2592384, 'steps': 13501, 'loss/train': 1.7259631156921387} 08/30/2021 15:33:05 - INFO - __main__ - Step 13503: {'lr': 0.000492585624037572, 'samples': 2592576, 'steps': 13502, 'loss/train': 1.824569582939148} 08/30/2021 15:33:05 - INFO - __main__ - Step 13504: {'lr': 0.0004925843411611366, 'samples': 2592768, 'steps': 13503, 'loss/train': 1.6618465185165405} 08/30/2021 15:33:06 - INFO - __main__ - Step 13505: {'lr': 0.0004925830581753964, 'samples': 2592960, 'steps': 13504, 'loss/train': 1.47261643409729} 08/30/2021 15:33:08 - INFO - __main__ - Step 13506: {'lr': 0.000492581775080352, 'samples': 2593152, 'steps': 13505, 'loss/train': 1.3551136255264282} 08/30/2021 15:33:08 - INFO - __main__ - Step 13507: {'lr': 0.000492580491876004, 'samples': 2593344, 'steps': 13506, 'loss/train': 1.8640018701553345} 08/30/2021 15:33:09 - INFO - __main__ - Step 13508: {'lr': 0.000492579208562353, 'samples': 2593536, 'steps': 13507, 'loss/train': 0.9833238124847412} 08/30/2021 15:33:09 - INFO - __main__ - Step 13509: {'lr': 0.0004925779251393995, 'samples': 2593728, 'steps': 13508, 'loss/train': 1.9962507486343384} 08/30/2021 15:33:09 - INFO - __main__ - Step 13510: {'lr': 0.0004925766416071441, 'samples': 2593920, 'steps': 13509, 'loss/train': 0.13176283240318298} 08/30/2021 15:33:11 - INFO - __main__ - Step 13511: {'lr': 0.0004925753579655876, 'samples': 2594112, 'steps': 13510, 'loss/train': 1.688368797302246} 08/30/2021 15:33:11 - INFO - __main__ - Step 13512: {'lr': 0.0004925740742147302, 'samples': 2594304, 'steps': 13511, 'loss/train': 1.932279109954834} 08/30/2021 15:33:12 - INFO - __main__ - Step 13513: {'lr': 0.0004925727903545727, 'samples': 2594496, 'steps': 13512, 'loss/train': 1.8428903818130493} 08/30/2021 15:33:12 - INFO - __main__ - Step 13514: {'lr': 0.0004925715063851157, 'samples': 2594688, 'steps': 13513, 'loss/train': 2.994810104370117} 08/30/2021 15:33:12 - INFO - __main__ - Step 13515: {'lr': 0.0004925702223063597, 'samples': 2594880, 'steps': 13514, 'loss/train': 1.7586320638656616} 08/30/2021 15:33:14 - INFO - __main__ - Step 13516: {'lr': 0.0004925689381183052, 'samples': 2595072, 'steps': 13515, 'loss/train': 1.5178900957107544} 08/30/2021 15:33:14 - INFO - __main__ - Step 13517: {'lr': 0.0004925676538209531, 'samples': 2595264, 'steps': 13516, 'loss/train': 1.4516875743865967} 08/30/2021 15:33:15 - INFO - __main__ - Step 13518: {'lr': 0.0004925663694143036, 'samples': 2595456, 'steps': 13517, 'loss/train': 0.3572317063808441} 08/30/2021 15:33:15 - INFO - __main__ - Step 13519: {'lr': 0.0004925650848983575, 'samples': 2595648, 'steps': 13518, 'loss/train': 5.944174766540527} 08/30/2021 15:33:15 - INFO - __main__ - Step 13520: {'lr': 0.0004925638002731153, 'samples': 2595840, 'steps': 13519, 'loss/train': 3.11750864982605} 08/30/2021 15:33:16 - INFO - __main__ - Step 13521: {'lr': 0.0004925625155385775, 'samples': 2596032, 'steps': 13520, 'loss/train': 2.209549903869629} 08/30/2021 15:33:17 - INFO - __main__ - Step 13522: {'lr': 0.0004925612306947449, 'samples': 2596224, 'steps': 13521, 'loss/train': 2.039141893386841} 08/30/2021 15:33:18 - INFO - __main__ - Step 13523: {'lr': 0.0004925599457416179, 'samples': 2596416, 'steps': 13522, 'loss/train': 1.6940282583236694} 08/30/2021 15:33:18 - INFO - __main__ - Step 13524: {'lr': 0.0004925586606791972, 'samples': 2596608, 'steps': 13523, 'loss/train': 1.8162835836410522} 08/30/2021 15:33:18 - INFO - __main__ - Step 13525: {'lr': 0.0004925573755074832, 'samples': 2596800, 'steps': 13524, 'loss/train': 1.530030608177185} 08/30/2021 15:33:19 - INFO - __main__ - Step 13526: {'lr': 0.0004925560902264766, 'samples': 2596992, 'steps': 13525, 'loss/train': 1.6636945009231567} 08/30/2021 15:33:20 - INFO - __main__ - Step 13527: {'lr': 0.000492554804836178, 'samples': 2597184, 'steps': 13526, 'loss/train': 1.7782299518585205} 08/30/2021 15:33:21 - INFO - __main__ - Step 13528: {'lr': 0.000492553519336588, 'samples': 2597376, 'steps': 13527, 'loss/train': 1.6822110414505005} 08/30/2021 15:33:21 - INFO - __main__ - Step 13529: {'lr': 0.000492552233727707, 'samples': 2597568, 'steps': 13528, 'loss/train': 1.5328527688980103} 08/30/2021 15:33:21 - INFO - __main__ - Step 13530: {'lr': 0.0004925509480095358, 'samples': 2597760, 'steps': 13529, 'loss/train': 1.6794860363006592} 08/30/2021 15:33:22 - INFO - __main__ - Step 13531: {'lr': 0.0004925496621820749, 'samples': 2597952, 'steps': 13530, 'loss/train': 1.9116847515106201} 08/30/2021 15:33:24 - INFO - __main__ - Step 13532: {'lr': 0.0004925483762453249, 'samples': 2598144, 'steps': 13531, 'loss/train': 1.8638628721237183} 08/30/2021 15:33:24 - INFO - __main__ - Step 13533: {'lr': 0.0004925470901992863, 'samples': 2598336, 'steps': 13532, 'loss/train': 1.8651126623153687} 08/30/2021 15:33:24 - INFO - __main__ - Step 13534: {'lr': 0.0004925458040439596, 'samples': 2598528, 'steps': 13533, 'loss/train': 1.7516535520553589} 08/30/2021 15:33:25 - INFO - __main__ - Step 13535: {'lr': 0.0004925445177793457, 'samples': 2598720, 'steps': 13534, 'loss/train': 3.865978956222534} 08/30/2021 15:33:25 - INFO - __main__ - Step 13536: {'lr': 0.0004925432314054448, 'samples': 2598912, 'steps': 13535, 'loss/train': 1.8925580978393555} 08/30/2021 15:33:25 - INFO - __main__ - Step 13537: {'lr': 0.0004925419449222578, 'samples': 2599104, 'steps': 13536, 'loss/train': 0.10232044756412506} 08/30/2021 15:33:27 - INFO - __main__ - Step 13538: {'lr': 0.0004925406583297851, 'samples': 2599296, 'steps': 13537, 'loss/train': 1.7366762161254883} 08/30/2021 15:33:27 - INFO - __main__ - Step 13539: {'lr': 0.0004925393716280274, 'samples': 2599488, 'steps': 13538, 'loss/train': 1.4790434837341309} 08/30/2021 15:33:28 - INFO - __main__ - Step 13540: {'lr': 0.0004925380848169851, 'samples': 2599680, 'steps': 13539, 'loss/train': 1.6714898347854614} 08/30/2021 15:33:28 - INFO - __main__ - Step 13541: {'lr': 0.0004925367978966588, 'samples': 2599872, 'steps': 13540, 'loss/train': 1.2758488655090332} 08/30/2021 15:33:28 - INFO - __main__ - Step 13542: {'lr': 0.0004925355108670493, 'samples': 2600064, 'steps': 13541, 'loss/train': 1.4123115539550781} 08/30/2021 15:33:30 - INFO - __main__ - Step 13543: {'lr': 0.0004925342237281571, 'samples': 2600256, 'steps': 13542, 'loss/train': 1.858891487121582} 08/30/2021 15:33:30 - INFO - __main__ - Step 13544: {'lr': 0.0004925329364799825, 'samples': 2600448, 'steps': 13543, 'loss/train': 1.4883283376693726} 08/30/2021 15:33:31 - INFO - __main__ - Step 13545: {'lr': 0.0004925316491225265, 'samples': 2600640, 'steps': 13544, 'loss/train': 1.4505428075790405} 08/30/2021 15:33:31 - INFO - __main__ - Step 13546: {'lr': 0.0004925303616557893, 'samples': 2600832, 'steps': 13545, 'loss/train': 2.4108376502990723} 08/30/2021 15:33:31 - INFO - __main__ - Step 13547: {'lr': 0.0004925290740797718, 'samples': 2601024, 'steps': 13546, 'loss/train': 2.0243844985961914} 08/30/2021 15:33:32 - INFO - __main__ - Step 13548: {'lr': 0.0004925277863944745, 'samples': 2601216, 'steps': 13547, 'loss/train': 1.008447527885437} 08/30/2021 15:33:33 - INFO - __main__ - Step 13549: {'lr': 0.0004925264985998978, 'samples': 2601408, 'steps': 13548, 'loss/train': 2.024259328842163} 08/30/2021 15:33:34 - INFO - __main__ - Step 13550: {'lr': 0.0004925252106960425, 'samples': 2601600, 'steps': 13549, 'loss/train': 1.6532448530197144} 08/30/2021 15:33:34 - INFO - __main__ - Step 13551: {'lr': 0.000492523922682909, 'samples': 2601792, 'steps': 13550, 'loss/train': 0.10432249307632446} 08/30/2021 15:33:35 - INFO - __main__ - Step 13552: {'lr': 0.0004925226345604979, 'samples': 2601984, 'steps': 13551, 'loss/train': 2.243321418762207} 08/30/2021 15:33:35 - INFO - __main__ - Step 13553: {'lr': 0.0004925213463288099, 'samples': 2602176, 'steps': 13552, 'loss/train': 1.8855124711990356} 08/30/2021 15:33:36 - INFO - __main__ - Step 13554: {'lr': 0.0004925200579878456, 'samples': 2602368, 'steps': 13553, 'loss/train': 1.4332842826843262} 08/30/2021 15:33:37 - INFO - __main__ - Step 13555: {'lr': 0.0004925187695376055, 'samples': 2602560, 'steps': 13554, 'loss/train': 1.4411249160766602} 08/30/2021 15:33:37 - INFO - __main__ - Step 13556: {'lr': 0.0004925174809780901, 'samples': 2602752, 'steps': 13555, 'loss/train': 1.4498666524887085} 08/30/2021 15:33:38 - INFO - __main__ - Step 13557: {'lr': 0.0004925161923093001, 'samples': 2602944, 'steps': 13556, 'loss/train': 1.8133999109268188} 08/30/2021 15:33:38 - INFO - __main__ - Step 13558: {'lr': 0.000492514903531236, 'samples': 2603136, 'steps': 13557, 'loss/train': 1.8084253072738647} 08/30/2021 15:33:40 - INFO - __main__ - Step 13559: {'lr': 0.0004925136146438986, 'samples': 2603328, 'steps': 13558, 'loss/train': 1.520235538482666} 08/30/2021 15:33:41 - INFO - __main__ - Step 13560: {'lr': 0.0004925123256472881, 'samples': 2603520, 'steps': 13559, 'loss/train': 1.945859432220459} 08/30/2021 15:33:41 - INFO - __main__ - Step 13561: {'lr': 0.0004925110365414054, 'samples': 2603712, 'steps': 13560, 'loss/train': 1.7827258110046387} 08/30/2021 15:33:42 - INFO - __main__ - Step 13562: {'lr': 0.0004925097473262509, 'samples': 2603904, 'steps': 13561, 'loss/train': 1.188539743423462} 08/30/2021 15:33:42 - INFO - __main__ - Step 13563: {'lr': 0.0004925084580018253, 'samples': 2604096, 'steps': 13562, 'loss/train': 2.1434900760650635} 08/30/2021 15:33:42 - INFO - __main__ - Step 13564: {'lr': 0.0004925071685681292, 'samples': 2604288, 'steps': 13563, 'loss/train': 2.2147574424743652} 08/30/2021 15:33:44 - INFO - __main__ - Step 13565: {'lr': 0.000492505879025163, 'samples': 2604480, 'steps': 13564, 'loss/train': 0.2813052237033844} 08/30/2021 15:33:44 - INFO - __main__ - Step 13566: {'lr': 0.0004925045893729274, 'samples': 2604672, 'steps': 13565, 'loss/train': 1.7352817058563232} 08/30/2021 15:33:45 - INFO - __main__ - Step 13567: {'lr': 0.000492503299611423, 'samples': 2604864, 'steps': 13566, 'loss/train': 1.5272668600082397} 08/30/2021 15:33:45 - INFO - __main__ - Step 13568: {'lr': 0.0004925020097406504, 'samples': 2605056, 'steps': 13567, 'loss/train': 2.014237880706787} 08/30/2021 15:33:46 - INFO - __main__ - Step 13569: {'lr': 0.00049250071976061, 'samples': 2605248, 'steps': 13568, 'loss/train': 1.9641761779785156} 08/30/2021 15:33:47 - INFO - __main__ - Step 13570: {'lr': 0.0004924994296713026, 'samples': 2605440, 'steps': 13569, 'loss/train': 1.3411521911621094} 08/30/2021 15:33:47 - INFO - __main__ - Step 13571: {'lr': 0.0004924981394727288, 'samples': 2605632, 'steps': 13570, 'loss/train': 2.0921950340270996} 08/30/2021 15:33:48 - INFO - __main__ - Step 13572: {'lr': 0.0004924968491648889, 'samples': 2605824, 'steps': 13571, 'loss/train': 1.5525544881820679} 08/30/2021 15:33:48 - INFO - __main__ - Step 13573: {'lr': 0.0004924955587477837, 'samples': 2606016, 'steps': 13572, 'loss/train': 1.8229926824569702} 08/30/2021 15:33:49 - INFO - __main__ - Step 13574: {'lr': 0.0004924942682214138, 'samples': 2606208, 'steps': 13573, 'loss/train': 1.407418131828308} 08/30/2021 15:33:50 - INFO - __main__ - Step 13575: {'lr': 0.0004924929775857798, 'samples': 2606400, 'steps': 13574, 'loss/train': 1.6291581392288208} 08/30/2021 15:33:51 - INFO - __main__ - Step 13576: {'lr': 0.0004924916868408821, 'samples': 2606592, 'steps': 13575, 'loss/train': 1.8845282793045044} 08/30/2021 15:33:51 - INFO - __main__ - Step 13577: {'lr': 0.0004924903959867214, 'samples': 2606784, 'steps': 13576, 'loss/train': 2.195474624633789} 08/30/2021 15:33:51 - INFO - __main__ - Step 13578: {'lr': 0.0004924891050232984, 'samples': 2606976, 'steps': 13577, 'loss/train': 2.0111098289489746} 08/30/2021 15:33:52 - INFO - __main__ - Step 13579: {'lr': 0.0004924878139506134, 'samples': 2607168, 'steps': 13578, 'loss/train': 1.620241403579712} 08/30/2021 15:33:52 - INFO - __main__ - Step 13580: {'lr': 0.0004924865227686671, 'samples': 2607360, 'steps': 13579, 'loss/train': 1.8174797296524048} 08/30/2021 15:33:53 - INFO - __main__ - Step 13581: {'lr': 0.0004924852314774602, 'samples': 2607552, 'steps': 13580, 'loss/train': 1.1066776514053345} 08/30/2021 15:33:54 - INFO - __main__ - Step 13582: {'lr': 0.0004924839400769932, 'samples': 2607744, 'steps': 13581, 'loss/train': 1.4693632125854492} 08/30/2021 15:33:54 - INFO - __main__ - Step 13583: {'lr': 0.0004924826485672667, 'samples': 2607936, 'steps': 13582, 'loss/train': 1.5049018859863281} 08/30/2021 15:33:55 - INFO - __main__ - Step 13584: {'lr': 0.0004924813569482812, 'samples': 2608128, 'steps': 13583, 'loss/train': 1.9511942863464355} 08/30/2021 15:33:55 - INFO - __main__ - Step 13585: {'lr': 0.0004924800652200373, 'samples': 2608320, 'steps': 13584, 'loss/train': 1.3383973836898804} 08/30/2021 15:33:57 - INFO - __main__ - Step 13586: {'lr': 0.0004924787733825357, 'samples': 2608512, 'steps': 13585, 'loss/train': 1.1023023128509521} 08/30/2021 15:33:57 - INFO - __main__ - Step 13587: {'lr': 0.0004924774814357768, 'samples': 2608704, 'steps': 13586, 'loss/train': 1.8889728784561157} 08/30/2021 15:33:57 - INFO - __main__ - Step 13588: {'lr': 0.0004924761893797615, 'samples': 2608896, 'steps': 13587, 'loss/train': 2.334665060043335} 08/30/2021 15:33:58 - INFO - __main__ - Step 13589: {'lr': 0.00049247489721449, 'samples': 2609088, 'steps': 13588, 'loss/train': 1.6174975633621216} 08/30/2021 15:33:58 - INFO - __main__ - Step 13590: {'lr': 0.0004924736049399631, 'samples': 2609280, 'steps': 13589, 'loss/train': 1.8216828107833862} 08/30/2021 15:34:00 - INFO - __main__ - Step 13591: {'lr': 0.0004924723125561813, 'samples': 2609472, 'steps': 13590, 'loss/train': 1.5053640604019165} 08/30/2021 15:34:00 - INFO - __main__ - Step 13592: {'lr': 0.0004924710200631453, 'samples': 2609664, 'steps': 13591, 'loss/train': 1.7296819686889648} 08/30/2021 15:34:01 - INFO - __main__ - Step 13593: {'lr': 0.0004924697274608556, 'samples': 2609856, 'steps': 13592, 'loss/train': 1.9816350936889648} 08/30/2021 15:34:01 - INFO - __main__ - Step 13594: {'lr': 0.0004924684347493126, 'samples': 2610048, 'steps': 13593, 'loss/train': 1.0792206525802612} 08/30/2021 15:34:01 - INFO - __main__ - Step 13595: {'lr': 0.0004924671419285172, 'samples': 2610240, 'steps': 13594, 'loss/train': 1.7045694589614868} 08/30/2021 15:34:03 - INFO - __main__ - Step 13596: {'lr': 0.0004924658489984699, 'samples': 2610432, 'steps': 13595, 'loss/train': 2.1342239379882812} 08/30/2021 15:34:03 - INFO - __main__ - Step 13597: {'lr': 0.0004924645559591712, 'samples': 2610624, 'steps': 13596, 'loss/train': 1.6696661710739136} 08/30/2021 15:34:03 - INFO - __main__ - Step 13598: {'lr': 0.0004924632628106217, 'samples': 2610816, 'steps': 13597, 'loss/train': 1.7132092714309692} 08/30/2021 15:34:04 - INFO - __main__ - Step 13599: {'lr': 0.000492461969552822, 'samples': 2611008, 'steps': 13598, 'loss/train': 0.9362173080444336} 08/30/2021 15:34:04 - INFO - __main__ - Step 13600: {'lr': 0.0004924606761857726, 'samples': 2611200, 'steps': 13599, 'loss/train': 1.4645830392837524} 08/30/2021 15:34:06 - INFO - __main__ - Step 13601: {'lr': 0.0004924593827094744, 'samples': 2611392, 'steps': 13600, 'loss/train': 1.4075853824615479} 08/30/2021 15:34:06 - INFO - __main__ - Step 13602: {'lr': 0.0004924580891239274, 'samples': 2611584, 'steps': 13601, 'loss/train': 1.5761439800262451} 08/30/2021 15:34:06 - INFO - __main__ - Step 13603: {'lr': 0.0004924567954291328, 'samples': 2611776, 'steps': 13602, 'loss/train': 1.1367765665054321} 08/30/2021 15:34:07 - INFO - __main__ - Step 13604: {'lr': 0.0004924555016250908, 'samples': 2611968, 'steps': 13603, 'loss/train': 1.0156999826431274} 08/30/2021 15:34:07 - INFO - __main__ - Step 13605: {'lr': 0.0004924542077118021, 'samples': 2612160, 'steps': 13604, 'loss/train': 1.5204416513442993} 08/30/2021 15:34:09 - INFO - __main__ - Step 13606: {'lr': 0.0004924529136892673, 'samples': 2612352, 'steps': 13605, 'loss/train': 1.3079928159713745} 08/30/2021 15:34:09 - INFO - __main__ - Step 13607: {'lr': 0.0004924516195574869, 'samples': 2612544, 'steps': 13606, 'loss/train': 5.3268280029296875} 08/30/2021 15:34:09 - INFO - __main__ - Step 13608: {'lr': 0.0004924503253164614, 'samples': 2612736, 'steps': 13607, 'loss/train': 0.18579594790935516} 08/30/2021 15:34:10 - INFO - __main__ - Step 13609: {'lr': 0.0004924490309661918, 'samples': 2612928, 'steps': 13608, 'loss/train': 1.557999849319458} 08/30/2021 15:34:10 - INFO - __main__ - Step 13610: {'lr': 0.0004924477365066783, 'samples': 2613120, 'steps': 13609, 'loss/train': 0.18215464055538177} 08/30/2021 15:34:12 - INFO - __main__ - Step 13611: {'lr': 0.0004924464419379217, 'samples': 2613312, 'steps': 13610, 'loss/train': 1.7966129779815674} 08/30/2021 15:34:12 - INFO - __main__ - Step 13612: {'lr': 0.0004924451472599222, 'samples': 2613504, 'steps': 13611, 'loss/train': 1.552573323249817} 08/30/2021 15:34:12 - INFO - __main__ - Step 13613: {'lr': 0.000492443852472681, 'samples': 2613696, 'steps': 13612, 'loss/train': 1.795635461807251} 08/30/2021 15:34:13 - INFO - __main__ - Step 13614: {'lr': 0.000492442557576198, 'samples': 2613888, 'steps': 13613, 'loss/train': 1.6038355827331543} 08/30/2021 15:34:13 - INFO - __main__ - Step 13615: {'lr': 0.0004924412625704744, 'samples': 2614080, 'steps': 13614, 'loss/train': 2.2988336086273193} 08/30/2021 15:34:15 - INFO - __main__ - Step 13616: {'lr': 0.0004924399674555103, 'samples': 2614272, 'steps': 13615, 'loss/train': 1.9128919839859009} 08/30/2021 15:34:16 - INFO - __main__ - Step 13617: {'lr': 0.0004924386722313066, 'samples': 2614464, 'steps': 13616, 'loss/train': 1.461970329284668} 08/30/2021 15:34:16 - INFO - __main__ - Step 13618: {'lr': 0.0004924373768978638, 'samples': 2614656, 'steps': 13617, 'loss/train': 1.7205674648284912} 08/30/2021 15:34:16 - INFO - __main__ - Step 13619: {'lr': 0.0004924360814551825, 'samples': 2614848, 'steps': 13618, 'loss/train': 1.3666102886199951} 08/30/2021 15:34:17 - INFO - __main__ - Step 13620: {'lr': 0.0004924347859032631, 'samples': 2615040, 'steps': 13619, 'loss/train': 2.179389476776123} 08/30/2021 15:34:17 - INFO - __main__ - Step 13621: {'lr': 0.0004924334902421065, 'samples': 2615232, 'steps': 13620, 'loss/train': 2.01278018951416} 08/30/2021 15:34:19 - INFO - __main__ - Step 13622: {'lr': 0.0004924321944717129, 'samples': 2615424, 'steps': 13621, 'loss/train': 0.9595762491226196} 08/30/2021 15:34:19 - INFO - __main__ - Step 13623: {'lr': 0.0004924308985920832, 'samples': 2615616, 'steps': 13622, 'loss/train': 2.0263359546661377} 08/30/2021 15:34:19 - INFO - __main__ - Step 13624: {'lr': 0.0004924296026032179, 'samples': 2615808, 'steps': 13623, 'loss/train': 1.9515252113342285} 08/30/2021 15:34:20 - INFO - __main__ - Step 13625: {'lr': 0.0004924283065051176, 'samples': 2616000, 'steps': 13624, 'loss/train': 1.8134857416152954} 08/30/2021 15:34:20 - INFO - __main__ - Step 13626: {'lr': 0.0004924270102977827, 'samples': 2616192, 'steps': 13625, 'loss/train': 1.8927422761917114} 08/30/2021 15:34:22 - INFO - __main__ - Step 13627: {'lr': 0.0004924257139812141, 'samples': 2616384, 'steps': 13626, 'loss/train': 1.8158823251724243} 08/30/2021 15:34:22 - INFO - __main__ - Step 13628: {'lr': 0.0004924244175554121, 'samples': 2616576, 'steps': 13627, 'loss/train': 1.0761092901229858} 08/30/2021 15:34:22 - INFO - __main__ - Step 13629: {'lr': 0.0004924231210203775, 'samples': 2616768, 'steps': 13628, 'loss/train': 1.7435681819915771} 08/30/2021 15:34:23 - INFO - __main__ - Step 13630: {'lr': 0.0004924218243761106, 'samples': 2616960, 'steps': 13629, 'loss/train': 1.5496809482574463} 08/30/2021 15:34:23 - INFO - __main__ - Step 13631: {'lr': 0.0004924205276226123, 'samples': 2617152, 'steps': 13630, 'loss/train': 2.409818649291992} 08/30/2021 15:34:25 - INFO - __main__ - Step 13632: {'lr': 0.000492419230759883, 'samples': 2617344, 'steps': 13631, 'loss/train': 0.7975999712944031} 08/30/2021 15:34:25 - INFO - __main__ - Step 13633: {'lr': 0.0004924179337879234, 'samples': 2617536, 'steps': 13632, 'loss/train': 1.728769063949585} 08/30/2021 15:34:26 - INFO - __main__ - Step 13634: {'lr': 0.000492416636706734, 'samples': 2617728, 'steps': 13633, 'loss/train': 1.2326794862747192} 08/30/2021 15:34:26 - INFO - __main__ - Step 13635: {'lr': 0.0004924153395163153, 'samples': 2617920, 'steps': 13634, 'loss/train': 1.1788344383239746} 08/30/2021 15:34:27 - INFO - __main__ - Step 13636: {'lr': 0.0004924140422166681, 'samples': 2618112, 'steps': 13635, 'loss/train': 1.7727967500686646} 08/30/2021 15:34:27 - INFO - __main__ - Step 13637: {'lr': 0.0004924127448077929, 'samples': 2618304, 'steps': 13636, 'loss/train': 1.20018470287323} 08/30/2021 15:34:29 - INFO - __main__ - Step 13638: {'lr': 0.0004924114472896902, 'samples': 2618496, 'steps': 13637, 'loss/train': 1.5733697414398193} 08/30/2021 15:34:29 - INFO - __main__ - Step 13639: {'lr': 0.0004924101496623606, 'samples': 2618688, 'steps': 13638, 'loss/train': 1.8506971597671509} 08/30/2021 15:34:30 - INFO - __main__ - Step 13640: {'lr': 0.0004924088519258049, 'samples': 2618880, 'steps': 13639, 'loss/train': 1.184861421585083} 08/30/2021 15:34:30 - INFO - __main__ - Step 13641: {'lr': 0.0004924075540800233, 'samples': 2619072, 'steps': 13640, 'loss/train': 1.7108304500579834} 08/30/2021 15:34:30 - INFO - __main__ - Step 13642: {'lr': 0.0004924062561250167, 'samples': 2619264, 'steps': 13641, 'loss/train': 1.9534341096878052} 08/30/2021 15:34:31 - INFO - __main__ - Step 13643: {'lr': 0.0004924049580607855, 'samples': 2619456, 'steps': 13642, 'loss/train': 0.7120783925056458} 08/30/2021 15:34:32 - INFO - __main__ - Step 13644: {'lr': 0.0004924036598873305, 'samples': 2619648, 'steps': 13643, 'loss/train': 0.24787519872188568} 08/30/2021 15:34:33 - INFO - __main__ - Step 13645: {'lr': 0.0004924023616046521, 'samples': 2619840, 'steps': 13644, 'loss/train': 1.3333410024642944} 08/30/2021 15:34:33 - INFO - __main__ - Step 13646: {'lr': 0.000492401063212751, 'samples': 2620032, 'steps': 13645, 'loss/train': 0.9179432988166809} 08/30/2021 15:34:33 - INFO - __main__ - Step 13647: {'lr': 0.0004923997647116276, 'samples': 2620224, 'steps': 13646, 'loss/train': 1.2959872484207153} 08/30/2021 15:34:34 - INFO - __main__ - Step 13648: {'lr': 0.0004923984661012827, 'samples': 2620416, 'steps': 13647, 'loss/train': 1.8445854187011719} 08/30/2021 15:34:35 - INFO - __main__ - Step 13649: {'lr': 0.0004923971673817167, 'samples': 2620608, 'steps': 13648, 'loss/train': 1.988378643989563} 08/30/2021 15:34:36 - INFO - __main__ - Step 13650: {'lr': 0.0004923958685529303, 'samples': 2620800, 'steps': 13649, 'loss/train': 1.8842787742614746} 08/30/2021 15:34:36 - INFO - __main__ - Step 13651: {'lr': 0.0004923945696149241, 'samples': 2620992, 'steps': 13650, 'loss/train': 1.9136470556259155} 08/30/2021 15:34:36 - INFO - __main__ - Step 13652: {'lr': 0.0004923932705676986, 'samples': 2621184, 'steps': 13651, 'loss/train': 1.5448200702667236} 08/30/2021 15:34:37 - INFO - __main__ - Step 13653: {'lr': 0.0004923919714112545, 'samples': 2621376, 'steps': 13652, 'loss/train': 1.7074371576309204} 08/30/2021 15:34:38 - INFO - __main__ - Step 13654: {'lr': 0.0004923906721455922, 'samples': 2621568, 'steps': 13653, 'loss/train': 1.8044511079788208} 08/30/2021 15:34:39 - INFO - __main__ - Step 13655: {'lr': 0.0004923893727707125, 'samples': 2621760, 'steps': 13654, 'loss/train': 1.8527477979660034} 08/30/2021 15:34:39 - INFO - __main__ - Step 13656: {'lr': 0.0004923880732866159, 'samples': 2621952, 'steps': 13655, 'loss/train': 1.6376972198486328} 08/30/2021 15:34:39 - INFO - __main__ - Step 13657: {'lr': 0.0004923867736933029, 'samples': 2622144, 'steps': 13656, 'loss/train': 1.3884831666946411} 08/30/2021 15:34:40 - INFO - __main__ - Step 13658: {'lr': 0.0004923854739907743, 'samples': 2622336, 'steps': 13657, 'loss/train': 1.9756426811218262} 08/30/2021 15:34:41 - INFO - __main__ - Step 13659: {'lr': 0.0004923841741790304, 'samples': 2622528, 'steps': 13658, 'loss/train': 1.6669288873672485} 08/30/2021 15:34:42 - INFO - __main__ - Step 13660: {'lr': 0.0004923828742580719, 'samples': 2622720, 'steps': 13659, 'loss/train': 1.7132149934768677} 08/30/2021 15:34:42 - INFO - __main__ - Step 13661: {'lr': 0.0004923815742278996, 'samples': 2622912, 'steps': 13660, 'loss/train': 1.8713726997375488} 08/30/2021 15:34:42 - INFO - __main__ - Step 13662: {'lr': 0.0004923802740885139, 'samples': 2623104, 'steps': 13661, 'loss/train': 1.4689429998397827} 08/30/2021 15:34:43 - INFO - __main__ - Step 13663: {'lr': 0.0004923789738399152, 'samples': 2623296, 'steps': 13662, 'loss/train': 1.1093848943710327} 08/30/2021 15:34:43 - INFO - __main__ - Step 13664: {'lr': 0.0004923776734821044, 'samples': 2623488, 'steps': 13663, 'loss/train': 1.5304033756256104} 08/30/2021 15:34:45 - INFO - __main__ - Step 13665: {'lr': 0.0004923763730150819, 'samples': 2623680, 'steps': 13664, 'loss/train': 1.599599003791809} 08/30/2021 15:34:45 - INFO - __main__ - Step 13666: {'lr': 0.0004923750724388483, 'samples': 2623872, 'steps': 13665, 'loss/train': 1.955889105796814} 08/30/2021 15:34:46 - INFO - __main__ - Step 13667: {'lr': 0.0004923737717534044, 'samples': 2624064, 'steps': 13666, 'loss/train': 2.132965087890625} 08/30/2021 15:34:46 - INFO - __main__ - Step 13668: {'lr': 0.0004923724709587504, 'samples': 2624256, 'steps': 13667, 'loss/train': 1.6331837177276611} 08/30/2021 15:34:46 - INFO - __main__ - Step 13669: {'lr': 0.0004923711700548873, 'samples': 2624448, 'steps': 13668, 'loss/train': 1.400579810142517} 08/30/2021 15:34:48 - INFO - __main__ - Step 13670: {'lr': 0.0004923698690418154, 'samples': 2624640, 'steps': 13669, 'loss/train': 1.7198896408081055} 08/30/2021 15:34:48 - INFO - __main__ - Step 13671: {'lr': 0.0004923685679195355, 'samples': 2624832, 'steps': 13670, 'loss/train': 2.168217420578003} 08/30/2021 15:34:49 - INFO - __main__ - Step 13672: {'lr': 0.0004923672666880479, 'samples': 2625024, 'steps': 13671, 'loss/train': 1.213516116142273} 08/30/2021 15:34:49 - INFO - __main__ - Step 13673: {'lr': 0.0004923659653473533, 'samples': 2625216, 'steps': 13672, 'loss/train': 1.551790475845337} 08/30/2021 15:34:50 - INFO - __main__ - Step 13674: {'lr': 0.0004923646638974524, 'samples': 2625408, 'steps': 13673, 'loss/train': 2.2469582557678223} 08/30/2021 15:34:51 - INFO - __main__ - Step 13675: {'lr': 0.0004923633623383459, 'samples': 2625600, 'steps': 13674, 'loss/train': 1.7807055711746216} 08/30/2021 15:34:52 - INFO - __main__ - Step 13676: {'lr': 0.0004923620606700341, 'samples': 2625792, 'steps': 13675, 'loss/train': 1.5575268268585205} 08/30/2021 15:34:52 - INFO - __main__ - Step 13677: {'lr': 0.0004923607588925177, 'samples': 2625984, 'steps': 13676, 'loss/train': 2.6210319995880127} 08/30/2021 15:34:52 - INFO - __main__ - Step 13678: {'lr': 0.0004923594570057972, 'samples': 2626176, 'steps': 13677, 'loss/train': 2.1359925270080566} 08/30/2021 15:34:53 - INFO - __main__ - Step 13679: {'lr': 0.0004923581550098733, 'samples': 2626368, 'steps': 13678, 'loss/train': 0.1307481974363327} 08/30/2021 15:34:55 - INFO - __main__ - Step 13680: {'lr': 0.0004923568529047466, 'samples': 2626560, 'steps': 13679, 'loss/train': 1.6401782035827637} 08/30/2021 15:34:55 - INFO - __main__ - Step 13681: {'lr': 0.0004923555506904176, 'samples': 2626752, 'steps': 13680, 'loss/train': 0.12490972131490707} 08/30/2021 15:34:56 - INFO - __main__ - Step 13682: {'lr': 0.0004923542483668869, 'samples': 2626944, 'steps': 13681, 'loss/train': 0.09010914713144302} 08/30/2021 15:34:56 - INFO - __main__ - Step 13683: {'lr': 0.0004923529459341553, 'samples': 2627136, 'steps': 13682, 'loss/train': 1.6802605390548706} 08/30/2021 15:34:56 - INFO - __main__ - Step 13684: {'lr': 0.000492351643392223, 'samples': 2627328, 'steps': 13683, 'loss/train': 1.671370506286621} 08/30/2021 15:34:57 - INFO - __main__ - Step 13685: {'lr': 0.0004923503407410908, 'samples': 2627520, 'steps': 13684, 'loss/train': 1.8083133697509766} 08/30/2021 15:34:57 - INFO - __main__ - Step 13686: {'lr': 0.0004923490379807594, 'samples': 2627712, 'steps': 13685, 'loss/train': 0.9506597518920898} 08/30/2021 15:34:58 - INFO - __main__ - Step 13687: {'lr': 0.0004923477351112291, 'samples': 2627904, 'steps': 13686, 'loss/train': 2.1542840003967285} 08/30/2021 15:34:59 - INFO - __main__ - Step 13688: {'lr': 0.0004923464321325008, 'samples': 2628096, 'steps': 13687, 'loss/train': 1.3836222887039185} 08/30/2021 15:34:59 - INFO - __main__ - Step 13689: {'lr': 0.0004923451290445749, 'samples': 2628288, 'steps': 13688, 'loss/train': 1.8518695831298828} 08/30/2021 15:35:00 - INFO - __main__ - Step 13690: {'lr': 0.000492343825847452, 'samples': 2628480, 'steps': 13689, 'loss/train': 1.8045462369918823} 08/30/2021 15:35:00 - INFO - __main__ - Step 13691: {'lr': 0.0004923425225411328, 'samples': 2628672, 'steps': 13690, 'loss/train': 1.5389764308929443} 08/30/2021 15:35:02 - INFO - __main__ - Step 13692: {'lr': 0.0004923412191256176, 'samples': 2628864, 'steps': 13691, 'loss/train': 2.1948177814483643} 08/30/2021 15:35:03 - INFO - __main__ - Step 13693: {'lr': 0.0004923399156009073, 'samples': 2629056, 'steps': 13692, 'loss/train': 1.0094873905181885} 08/30/2021 15:35:03 - INFO - __main__ - Step 13694: {'lr': 0.0004923386119670024, 'samples': 2629248, 'steps': 13693, 'loss/train': 0.15823443233966827} 08/30/2021 15:35:03 - INFO - __main__ - Step 13695: {'lr': 0.0004923373082239035, 'samples': 2629440, 'steps': 13694, 'loss/train': 0.6393691301345825} 08/30/2021 15:35:04 - INFO - __main__ - Step 13696: {'lr': 0.000492336004371611, 'samples': 2629632, 'steps': 13695, 'loss/train': 1.8347361087799072} 08/30/2021 15:35:06 - INFO - __main__ - Step 13697: {'lr': 0.0004923347004101257, 'samples': 2629824, 'steps': 13696, 'loss/train': 1.632712483406067} 08/30/2021 15:35:06 - INFO - __main__ - Step 13698: {'lr': 0.0004923333963394482, 'samples': 2630016, 'steps': 13697, 'loss/train': 1.9935790300369263} 08/30/2021 15:35:06 - INFO - __main__ - Step 13699: {'lr': 0.000492332092159579, 'samples': 2630208, 'steps': 13698, 'loss/train': 1.5431437492370605} 08/30/2021 15:35:07 - INFO - __main__ - Step 13700: {'lr': 0.0004923307878705186, 'samples': 2630400, 'steps': 13699, 'loss/train': 1.884891152381897} 08/30/2021 15:35:07 - INFO - __main__ - Step 13701: {'lr': 0.0004923294834722678, 'samples': 2630592, 'steps': 13700, 'loss/train': 1.852683424949646} 08/30/2021 15:35:07 - INFO - __main__ - Step 13702: {'lr': 0.000492328178964827, 'samples': 2630784, 'steps': 13701, 'loss/train': 1.8306818008422852} 08/30/2021 15:35:09 - INFO - __main__ - Step 13703: {'lr': 0.0004923268743481969, 'samples': 2630976, 'steps': 13702, 'loss/train': 0.10214895755052567} 08/30/2021 15:35:10 - INFO - __main__ - Step 13704: {'lr': 0.000492325569622378, 'samples': 2631168, 'steps': 13703, 'loss/train': 1.338849663734436} 08/30/2021 15:35:10 - INFO - __main__ - Step 13705: {'lr': 0.0004923242647873709, 'samples': 2631360, 'steps': 13704, 'loss/train': 2.2124781608581543} 08/30/2021 15:35:10 - INFO - __main__ - Step 13706: {'lr': 0.0004923229598431763, 'samples': 2631552, 'steps': 13705, 'loss/train': 1.8244792222976685} 08/30/2021 15:35:11 - INFO - __main__ - Step 13707: {'lr': 0.0004923216547897948, 'samples': 2631744, 'steps': 13706, 'loss/train': 1.1003340482711792} 08/30/2021 15:35:12 - INFO - __main__ - Step 13708: {'lr': 0.0004923203496272267, 'samples': 2631936, 'steps': 13707, 'loss/train': 1.254780888557434} 08/30/2021 15:35:12 - INFO - __main__ - Step 13709: {'lr': 0.0004923190443554729, 'samples': 2632128, 'steps': 13708, 'loss/train': 1.9208908081054688} 08/30/2021 15:35:13 - INFO - __main__ - Step 13710: {'lr': 0.0004923177389745339, 'samples': 2632320, 'steps': 13709, 'loss/train': 1.4887737035751343} 08/30/2021 15:35:13 - INFO - __main__ - Step 13711: {'lr': 0.0004923164334844103, 'samples': 2632512, 'steps': 13710, 'loss/train': 1.7068501710891724} 08/30/2021 15:35:13 - INFO - __main__ - Step 13712: {'lr': 0.0004923151278851025, 'samples': 2632704, 'steps': 13711, 'loss/train': 2.020146131515503} 08/30/2021 15:35:15 - INFO - __main__ - Step 13713: {'lr': 0.0004923138221766114, 'samples': 2632896, 'steps': 13712, 'loss/train': 1.5657011270523071} 08/30/2021 15:35:16 - INFO - __main__ - Step 13714: {'lr': 0.0004923125163589373, 'samples': 2633088, 'steps': 13713, 'loss/train': 2.091078758239746} 08/30/2021 15:35:16 - INFO - __main__ - Step 13715: {'lr': 0.0004923112104320811, 'samples': 2633280, 'steps': 13714, 'loss/train': 1.5669457912445068} 08/30/2021 15:35:16 - INFO - __main__ - Step 13716: {'lr': 0.000492309904396043, 'samples': 2633472, 'steps': 13715, 'loss/train': 1.9935438632965088} 08/30/2021 15:35:17 - INFO - __main__ - Step 13717: {'lr': 0.0004923085982508239, 'samples': 2633664, 'steps': 13716, 'loss/train': 1.3683717250823975} 08/30/2021 15:35:17 - INFO - __main__ - Step 13718: {'lr': 0.0004923072919964243, 'samples': 2633856, 'steps': 13717, 'loss/train': 5.963078498840332} 08/30/2021 15:35:19 - INFO - __main__ - Step 13719: {'lr': 0.0004923059856328447, 'samples': 2634048, 'steps': 13718, 'loss/train': 2.031951427459717} 08/30/2021 15:35:19 - INFO - __main__ - Step 13720: {'lr': 0.0004923046791600859, 'samples': 2634240, 'steps': 13719, 'loss/train': 1.8273379802703857} 08/30/2021 15:35:19 - INFO - __main__ - Step 13721: {'lr': 0.0004923033725781482, 'samples': 2634432, 'steps': 13720, 'loss/train': 1.4259757995605469} 08/30/2021 15:35:20 - INFO - __main__ - Step 13722: {'lr': 0.0004923020658870324, 'samples': 2634624, 'steps': 13721, 'loss/train': 1.7631014585494995} 08/30/2021 15:35:20 - INFO - __main__ - Step 13723: {'lr': 0.000492300759086739, 'samples': 2634816, 'steps': 13722, 'loss/train': 2.193504571914673} 08/30/2021 15:35:22 - INFO - __main__ - Step 13724: {'lr': 0.0004922994521772687, 'samples': 2635008, 'steps': 13723, 'loss/train': 2.0830652713775635} 08/30/2021 15:35:22 - INFO - __main__ - Step 13725: {'lr': 0.000492298145158622, 'samples': 2635200, 'steps': 13724, 'loss/train': 2.2276597023010254} 08/30/2021 15:35:23 - INFO - __main__ - Step 13726: {'lr': 0.0004922968380307994, 'samples': 2635392, 'steps': 13725, 'loss/train': 2.376321315765381} 08/30/2021 15:35:23 - INFO - __main__ - Step 13727: {'lr': 0.0004922955307938016, 'samples': 2635584, 'steps': 13726, 'loss/train': 1.9856606721878052} 08/30/2021 15:35:23 - INFO - __main__ - Step 13728: {'lr': 0.0004922942234476292, 'samples': 2635776, 'steps': 13727, 'loss/train': 2.001293420791626} 08/30/2021 15:35:25 - INFO - __main__ - Step 13729: {'lr': 0.0004922929159922828, 'samples': 2635968, 'steps': 13728, 'loss/train': 1.4641457796096802} 08/30/2021 15:35:25 - INFO - __main__ - Step 13730: {'lr': 0.0004922916084277629, 'samples': 2636160, 'steps': 13729, 'loss/train': 2.233157157897949} 08/30/2021 15:35:26 - INFO - __main__ - Step 13731: {'lr': 0.0004922903007540701, 'samples': 2636352, 'steps': 13730, 'loss/train': 1.1955019235610962} 08/30/2021 15:35:26 - INFO - __main__ - Step 13732: {'lr': 0.0004922889929712051, 'samples': 2636544, 'steps': 13731, 'loss/train': 2.0497384071350098} 08/30/2021 15:35:26 - INFO - __main__ - Step 13733: {'lr': 0.0004922876850791684, 'samples': 2636736, 'steps': 13732, 'loss/train': 1.1751309633255005} 08/30/2021 15:35:28 - INFO - __main__ - Step 13734: {'lr': 0.0004922863770779606, 'samples': 2636928, 'steps': 13733, 'loss/train': 1.266606092453003} 08/30/2021 15:35:28 - INFO - __main__ - Step 13735: {'lr': 0.0004922850689675823, 'samples': 2637120, 'steps': 13734, 'loss/train': 2.1586008071899414} 08/30/2021 15:35:29 - INFO - __main__ - Step 13736: {'lr': 0.0004922837607480341, 'samples': 2637312, 'steps': 13735, 'loss/train': 1.6889420747756958} 08/30/2021 15:35:29 - INFO - __main__ - Step 13737: {'lr': 0.0004922824524193166, 'samples': 2637504, 'steps': 13736, 'loss/train': 0.9684352278709412} 08/30/2021 15:35:29 - INFO - __main__ - Step 13738: {'lr': 0.0004922811439814303, 'samples': 2637696, 'steps': 13737, 'loss/train': 2.1781835556030273} 08/30/2021 15:35:30 - INFO - __main__ - Step 13739: {'lr': 0.0004922798354343758, 'samples': 2637888, 'steps': 13738, 'loss/train': 1.8887906074523926} 08/30/2021 15:35:32 - INFO - __main__ - Step 13740: {'lr': 0.0004922785267781539, 'samples': 2638080, 'steps': 13739, 'loss/train': 1.4249500036239624} 08/30/2021 15:35:32 - INFO - __main__ - Step 13741: {'lr': 0.000492277218012765, 'samples': 2638272, 'steps': 13740, 'loss/train': 1.7357696294784546} 08/30/2021 15:35:32 - INFO - __main__ - Step 13742: {'lr': 0.0004922759091382097, 'samples': 2638464, 'steps': 13741, 'loss/train': 1.5921028852462769} 08/30/2021 15:35:33 - INFO - __main__ - Step 13743: {'lr': 0.0004922746001544885, 'samples': 2638656, 'steps': 13742, 'loss/train': 1.498734474182129} 08/30/2021 15:35:33 - INFO - __main__ - Step 13744: {'lr': 0.0004922732910616023, 'samples': 2638848, 'steps': 13743, 'loss/train': 1.9081112146377563} 08/30/2021 15:35:33 - INFO - __main__ - Step 13745: {'lr': 0.0004922719818595514, 'samples': 2639040, 'steps': 13744, 'loss/train': 1.339704990386963} 08/30/2021 15:35:35 - INFO - __main__ - Step 13746: {'lr': 0.0004922706725483364, 'samples': 2639232, 'steps': 13745, 'loss/train': 2.2559444904327393} 08/30/2021 15:35:35 - INFO - __main__ - Step 13747: {'lr': 0.0004922693631279581, 'samples': 2639424, 'steps': 13746, 'loss/train': 1.1486022472381592} 08/30/2021 15:35:36 - INFO - __main__ - Step 13748: {'lr': 0.000492268053598417, 'samples': 2639616, 'steps': 13747, 'loss/train': 1.211904764175415} 08/30/2021 15:35:36 - INFO - __main__ - Step 13749: {'lr': 0.0004922667439597136, 'samples': 2639808, 'steps': 13748, 'loss/train': 1.418578863143921} 08/30/2021 15:35:36 - INFO - __main__ - Step 13750: {'lr': 0.0004922654342118484, 'samples': 2640000, 'steps': 13749, 'loss/train': 1.3844101428985596} 08/30/2021 15:35:38 - INFO - __main__ - Step 13751: {'lr': 0.0004922641243548223, 'samples': 2640192, 'steps': 13750, 'loss/train': 1.8498740196228027} 08/30/2021 15:35:38 - INFO - __main__ - Step 13752: {'lr': 0.0004922628143886358, 'samples': 2640384, 'steps': 13751, 'loss/train': 1.6858294010162354} 08/30/2021 15:35:39 - INFO - __main__ - Step 13753: {'lr': 0.0004922615043132892, 'samples': 2640576, 'steps': 13752, 'loss/train': 1.8434538841247559} 08/30/2021 15:35:39 - INFO - __main__ - Step 13754: {'lr': 0.0004922601941287835, 'samples': 2640768, 'steps': 13753, 'loss/train': 0.7334967851638794} 08/30/2021 15:35:39 - INFO - __main__ - Step 13755: {'lr': 0.0004922588838351189, 'samples': 2640960, 'steps': 13754, 'loss/train': 1.306587815284729} 08/30/2021 15:35:41 - INFO - __main__ - Step 13756: {'lr': 0.0004922575734322963, 'samples': 2641152, 'steps': 13755, 'loss/train': 2.007366180419922} 08/30/2021 15:35:41 - INFO - __main__ - Step 13757: {'lr': 0.0004922562629203161, 'samples': 2641344, 'steps': 13756, 'loss/train': 2.00295090675354} 08/30/2021 15:35:42 - INFO - __main__ - Step 13758: {'lr': 0.0004922549522991791, 'samples': 2641536, 'steps': 13757, 'loss/train': 1.7510627508163452} 08/30/2021 15:35:42 - INFO - __main__ - Step 13759: {'lr': 0.0004922536415688856, 'samples': 2641728, 'steps': 13758, 'loss/train': 1.7219719886779785} 08/30/2021 15:35:43 - INFO - __main__ - Step 13760: {'lr': 0.0004922523307294364, 'samples': 2641920, 'steps': 13759, 'loss/train': 0.19753147661685944} 08/30/2021 15:35:44 - INFO - __main__ - Step 13761: {'lr': 0.0004922510197808321, 'samples': 2642112, 'steps': 13760, 'loss/train': 1.529544472694397} 08/30/2021 15:35:44 - INFO - __main__ - Step 13762: {'lr': 0.0004922497087230732, 'samples': 2642304, 'steps': 13761, 'loss/train': 1.213055968284607} 08/30/2021 15:35:45 - INFO - __main__ - Step 13763: {'lr': 0.0004922483975561603, 'samples': 2642496, 'steps': 13762, 'loss/train': 2.152477502822876} 08/30/2021 15:35:45 - INFO - __main__ - Step 13764: {'lr': 0.000492247086280094, 'samples': 2642688, 'steps': 13763, 'loss/train': 2.0268726348876953} 08/30/2021 15:35:45 - INFO - __main__ - Step 13765: {'lr': 0.0004922457748948749, 'samples': 2642880, 'steps': 13764, 'loss/train': 2.165783166885376} 08/30/2021 15:35:47 - INFO - __main__ - Step 13766: {'lr': 0.0004922444634005037, 'samples': 2643072, 'steps': 13765, 'loss/train': 2.0102698802948} 08/30/2021 15:35:47 - INFO - __main__ - Step 13767: {'lr': 0.0004922431517969808, 'samples': 2643264, 'steps': 13766, 'loss/train': 1.9530229568481445} 08/30/2021 15:35:48 - INFO - __main__ - Step 13768: {'lr': 0.0004922418400843068, 'samples': 2643456, 'steps': 13767, 'loss/train': 1.5066810846328735} 08/30/2021 15:35:48 - INFO - __main__ - Step 13769: {'lr': 0.0004922405282624825, 'samples': 2643648, 'steps': 13768, 'loss/train': 1.6222310066223145} 08/30/2021 15:35:48 - INFO - __main__ - Step 13770: {'lr': 0.0004922392163315083, 'samples': 2643840, 'steps': 13769, 'loss/train': 1.7509607076644897} 08/30/2021 15:35:50 - INFO - __main__ - Step 13771: {'lr': 0.0004922379042913848, 'samples': 2644032, 'steps': 13770, 'loss/train': 1.8124586343765259} 08/30/2021 15:35:50 - INFO - __main__ - Step 13772: {'lr': 0.0004922365921421126, 'samples': 2644224, 'steps': 13771, 'loss/train': 1.820056676864624} 08/30/2021 15:35:51 - INFO - __main__ - Step 13773: {'lr': 0.0004922352798836924, 'samples': 2644416, 'steps': 13772, 'loss/train': 1.8008754253387451} 08/30/2021 15:35:51 - INFO - __main__ - Step 13774: {'lr': 0.0004922339675161248, 'samples': 2644608, 'steps': 13773, 'loss/train': 1.695332646369934} 08/30/2021 15:35:51 - INFO - __main__ - Step 13775: {'lr': 0.0004922326550394102, 'samples': 2644800, 'steps': 13774, 'loss/train': 1.359049916267395} 08/30/2021 15:35:54 - INFO - __main__ - Step 13776: {'lr': 0.0004922313424535494, 'samples': 2644992, 'steps': 13775, 'loss/train': 1.735809326171875} 08/30/2021 15:35:55 - INFO - __main__ - Step 13777: {'lr': 0.0004922300297585428, 'samples': 2645184, 'steps': 13776, 'loss/train': 1.83517587184906} 08/30/2021 15:35:55 - INFO - __main__ - Step 13778: {'lr': 0.0004922287169543911, 'samples': 2645376, 'steps': 13777, 'loss/train': 1.6809149980545044} 08/30/2021 15:35:55 - INFO - __main__ - Step 13779: {'lr': 0.0004922274040410949, 'samples': 2645568, 'steps': 13778, 'loss/train': 0.24220360815525055} 08/30/2021 15:35:56 - INFO - __main__ - Step 13780: {'lr': 0.0004922260910186548, 'samples': 2645760, 'steps': 13779, 'loss/train': 0.3392987847328186} 08/30/2021 15:35:57 - INFO - __main__ - Step 13781: {'lr': 0.0004922247778870714, 'samples': 2645952, 'steps': 13780, 'loss/train': 2.3549277782440186} 08/30/2021 15:35:58 - INFO - __main__ - Step 13782: {'lr': 0.0004922234646463451, 'samples': 2646144, 'steps': 13781, 'loss/train': 1.7731692790985107} 08/30/2021 15:35:58 - INFO - __main__ - Step 13783: {'lr': 0.0004922221512964767, 'samples': 2646336, 'steps': 13782, 'loss/train': 2.125839948654175} 08/30/2021 15:35:59 - INFO - __main__ - Step 13784: {'lr': 0.0004922208378374668, 'samples': 2646528, 'steps': 13783, 'loss/train': 1.2620468139648438} 08/30/2021 15:35:59 - INFO - __main__ - Step 13785: {'lr': 0.0004922195242693159, 'samples': 2646720, 'steps': 13784, 'loss/train': 0.20281535387039185} 08/30/2021 15:35:59 - INFO - __main__ - Step 13786: {'lr': 0.0004922182105920246, 'samples': 2646912, 'steps': 13785, 'loss/train': 0.11585058271884918} 08/30/2021 15:36:01 - INFO - __main__ - Step 13787: {'lr': 0.0004922168968055935, 'samples': 2647104, 'steps': 13786, 'loss/train': 1.6856178045272827} 08/30/2021 15:36:01 - INFO - __main__ - Step 13788: {'lr': 0.0004922155829100233, 'samples': 2647296, 'steps': 13787, 'loss/train': 1.5219813585281372} 08/30/2021 15:36:02 - INFO - __main__ - Step 13789: {'lr': 0.0004922142689053144, 'samples': 2647488, 'steps': 13788, 'loss/train': 1.7836838960647583} 08/30/2021 15:36:02 - INFO - __main__ - Step 13790: {'lr': 0.0004922129547914675, 'samples': 2647680, 'steps': 13789, 'loss/train': 1.9570887088775635} 08/30/2021 15:36:03 - INFO - __main__ - Step 13791: {'lr': 0.0004922116405684832, 'samples': 2647872, 'steps': 13790, 'loss/train': 1.0402331352233887} 08/30/2021 15:36:04 - INFO - __main__ - Step 13792: {'lr': 0.0004922103262363621, 'samples': 2648064, 'steps': 13791, 'loss/train': 1.649842381477356} 08/30/2021 15:36:05 - INFO - __main__ - Step 13793: {'lr': 0.0004922090117951047, 'samples': 2648256, 'steps': 13792, 'loss/train': 0.8131370544433594} 08/30/2021 15:36:05 - INFO - __main__ - Step 13794: {'lr': 0.0004922076972447117, 'samples': 2648448, 'steps': 13793, 'loss/train': 2.0038375854492188} 08/30/2021 15:36:05 - INFO - __main__ - Step 13795: {'lr': 0.0004922063825851836, 'samples': 2648640, 'steps': 13794, 'loss/train': 1.4933514595031738} 08/30/2021 15:36:06 - INFO - __main__ - Step 13796: {'lr': 0.0004922050678165211, 'samples': 2648832, 'steps': 13795, 'loss/train': 1.5484554767608643} 08/30/2021 15:36:06 - INFO - __main__ - Step 13797: {'lr': 0.0004922037529387247, 'samples': 2649024, 'steps': 13796, 'loss/train': 1.4274927377700806} 08/30/2021 15:36:08 - INFO - __main__ - Step 13798: {'lr': 0.000492202437951795, 'samples': 2649216, 'steps': 13797, 'loss/train': 1.2743474245071411} 08/30/2021 15:36:08 - INFO - __main__ - Step 13799: {'lr': 0.0004922011228557327, 'samples': 2649408, 'steps': 13798, 'loss/train': 1.3631792068481445} 08/30/2021 15:36:08 - INFO - __main__ - Step 13800: {'lr': 0.0004921998076505383, 'samples': 2649600, 'steps': 13799, 'loss/train': 1.6608229875564575} 08/30/2021 15:36:09 - INFO - __main__ - Step 13801: {'lr': 0.0004921984923362124, 'samples': 2649792, 'steps': 13800, 'loss/train': 0.8246711492538452} 08/30/2021 15:36:09 - INFO - __main__ - Step 13802: {'lr': 0.0004921971769127555, 'samples': 2649984, 'steps': 13801, 'loss/train': 1.6632049083709717} 08/30/2021 15:36:11 - INFO - __main__ - Step 13803: {'lr': 0.0004921958613801683, 'samples': 2650176, 'steps': 13802, 'loss/train': 0.21885547041893005} 08/30/2021 15:36:11 - INFO - __main__ - Step 13804: {'lr': 0.0004921945457384516, 'samples': 2650368, 'steps': 13803, 'loss/train': 0.9048483967781067} 08/30/2021 15:36:11 - INFO - __main__ - Step 13805: {'lr': 0.0004921932299876055, 'samples': 2650560, 'steps': 13804, 'loss/train': 1.8860636949539185} 08/30/2021 15:36:12 - INFO - __main__ - Step 13806: {'lr': 0.000492191914127631, 'samples': 2650752, 'steps': 13805, 'loss/train': 1.522040605545044} 08/30/2021 15:36:12 - INFO - __main__ - Step 13807: {'lr': 0.0004921905981585286, 'samples': 2650944, 'steps': 13806, 'loss/train': 1.6715176105499268} 08/30/2021 15:36:14 - INFO - __main__ - Step 13808: {'lr': 0.0004921892820802988, 'samples': 2651136, 'steps': 13807, 'loss/train': 2.209564685821533} 08/30/2021 15:36:14 - INFO - __main__ - Step 13809: {'lr': 0.0004921879658929422, 'samples': 2651328, 'steps': 13808, 'loss/train': 1.5849223136901855} 08/30/2021 15:36:14 - INFO - __main__ - Step 13810: {'lr': 0.0004921866495964594, 'samples': 2651520, 'steps': 13809, 'loss/train': 1.9061890840530396} 08/30/2021 15:36:15 - INFO - __main__ - Step 13811: {'lr': 0.0004921853331908512, 'samples': 2651712, 'steps': 13810, 'loss/train': 1.5075124502182007} 08/30/2021 15:36:15 - INFO - __main__ - Step 13812: {'lr': 0.000492184016676118, 'samples': 2651904, 'steps': 13811, 'loss/train': 1.7688640356063843} 08/30/2021 15:36:17 - INFO - __main__ - Step 13813: {'lr': 0.0004921827000522603, 'samples': 2652096, 'steps': 13812, 'loss/train': 1.7393929958343506} 08/30/2021 15:36:17 - INFO - __main__ - Step 13814: {'lr': 0.0004921813833192788, 'samples': 2652288, 'steps': 13813, 'loss/train': 1.659746766090393} 08/30/2021 15:36:17 - INFO - __main__ - Step 13815: {'lr': 0.0004921800664771743, 'samples': 2652480, 'steps': 13814, 'loss/train': 1.9074373245239258} 08/30/2021 15:36:18 - INFO - __main__ - Step 13816: {'lr': 0.0004921787495259471, 'samples': 2652672, 'steps': 13815, 'loss/train': 1.6964482069015503} 08/30/2021 15:36:18 - INFO - __main__ - Step 13817: {'lr': 0.0004921774324655978, 'samples': 2652864, 'steps': 13816, 'loss/train': 1.5799070596694946} 08/30/2021 15:36:19 - INFO - __main__ - Step 13818: {'lr': 0.0004921761152961271, 'samples': 2653056, 'steps': 13817, 'loss/train': 2.1930577754974365} 08/30/2021 15:36:20 - INFO - __main__ - Step 13819: {'lr': 0.0004921747980175357, 'samples': 2653248, 'steps': 13818, 'loss/train': 1.612560510635376} 08/30/2021 15:36:20 - INFO - __main__ - Step 13820: {'lr': 0.0004921734806298241, 'samples': 2653440, 'steps': 13819, 'loss/train': 1.8078802824020386} 08/30/2021 15:36:21 - INFO - __main__ - Step 13821: {'lr': 0.0004921721631329927, 'samples': 2653632, 'steps': 13820, 'loss/train': 1.85303795337677} 08/30/2021 15:36:21 - INFO - __main__ - Step 13822: {'lr': 0.0004921708455270424, 'samples': 2653824, 'steps': 13821, 'loss/train': 1.341817855834961} 08/30/2021 15:36:21 - INFO - __main__ - Step 13823: {'lr': 0.0004921695278119736, 'samples': 2654016, 'steps': 13822, 'loss/train': 1.5608800649642944} 08/30/2021 15:36:23 - INFO - __main__ - Step 13824: {'lr': 0.0004921682099877869, 'samples': 2654208, 'steps': 13823, 'loss/train': 1.3948137760162354} 08/30/2021 15:36:23 - INFO - __main__ - Step 13825: {'lr': 0.000492166892054483, 'samples': 2654400, 'steps': 13824, 'loss/train': 1.2661569118499756} 08/30/2021 15:36:24 - INFO - __main__ - Step 13826: {'lr': 0.0004921655740120623, 'samples': 2654592, 'steps': 13825, 'loss/train': 1.4389091730117798} 08/30/2021 15:36:24 - INFO - __main__ - Step 13827: {'lr': 0.0004921642558605257, 'samples': 2654784, 'steps': 13826, 'loss/train': 0.37669238448143005} 08/30/2021 15:36:25 - INFO - __main__ - Step 13828: {'lr': 0.0004921629375998736, 'samples': 2654976, 'steps': 13827, 'loss/train': 0.6892330050468445} 08/30/2021 15:36:26 - INFO - __main__ - Step 13829: {'lr': 0.0004921616192301065, 'samples': 2655168, 'steps': 13828, 'loss/train': 1.7391256093978882} 08/30/2021 15:36:27 - INFO - __main__ - Step 13830: {'lr': 0.0004921603007512253, 'samples': 2655360, 'steps': 13829, 'loss/train': 2.2470057010650635} 08/30/2021 15:36:27 - INFO - __main__ - Step 13831: {'lr': 0.0004921589821632302, 'samples': 2655552, 'steps': 13830, 'loss/train': 2.3947322368621826} 08/30/2021 15:36:27 - INFO - __main__ - Step 13832: {'lr': 0.0004921576634661221, 'samples': 2655744, 'steps': 13831, 'loss/train': 1.621037483215332} 08/30/2021 15:36:28 - INFO - __main__ - Step 13833: {'lr': 0.0004921563446599015, 'samples': 2655936, 'steps': 13832, 'loss/train': 0.7523802518844604} 08/30/2021 15:36:30 - INFO - __main__ - Step 13834: {'lr': 0.000492155025744569, 'samples': 2656128, 'steps': 13833, 'loss/train': 1.4243792295455933} 08/30/2021 15:36:31 - INFO - __main__ - Step 13835: {'lr': 0.0004921537067201252, 'samples': 2656320, 'steps': 13834, 'loss/train': 1.2156262397766113} 08/30/2021 15:36:31 - INFO - __main__ - Step 13836: {'lr': 0.0004921523875865706, 'samples': 2656512, 'steps': 13835, 'loss/train': 1.4866888523101807} 08/30/2021 15:36:31 - INFO - __main__ - Step 13837: {'lr': 0.000492151068343906, 'samples': 2656704, 'steps': 13836, 'loss/train': 1.5981640815734863} 08/30/2021 15:36:32 - INFO - __main__ - Step 13838: {'lr': 0.0004921497489921318, 'samples': 2656896, 'steps': 13837, 'loss/train': 1.5347036123275757} 08/30/2021 15:36:33 - INFO - __main__ - Step 13839: {'lr': 0.0004921484295312485, 'samples': 2657088, 'steps': 13838, 'loss/train': 2.1072139739990234} 08/30/2021 15:36:33 - INFO - __main__ - Step 13840: {'lr': 0.0004921471099612571, 'samples': 2657280, 'steps': 13839, 'loss/train': 1.8525291681289673} 08/30/2021 15:36:34 - INFO - __main__ - Step 13841: {'lr': 0.0004921457902821578, 'samples': 2657472, 'steps': 13840, 'loss/train': 1.9629462957382202} 08/30/2021 15:36:34 - INFO - __main__ - Step 13842: {'lr': 0.0004921444704939514, 'samples': 2657664, 'steps': 13841, 'loss/train': 1.8306949138641357} 08/30/2021 15:36:34 - INFO - __main__ - Step 13843: {'lr': 0.0004921431505966384, 'samples': 2657856, 'steps': 13842, 'loss/train': 1.860345482826233} 08/30/2021 15:36:36 - INFO - __main__ - Step 13844: {'lr': 0.0004921418305902194, 'samples': 2658048, 'steps': 13843, 'loss/train': 0.7579705715179443} 08/30/2021 15:36:36 - INFO - __main__ - Step 13845: {'lr': 0.0004921405104746951, 'samples': 2658240, 'steps': 13844, 'loss/train': 1.740308165550232} 08/30/2021 15:36:37 - INFO - __main__ - Step 13846: {'lr': 0.0004921391902500661, 'samples': 2658432, 'steps': 13845, 'loss/train': 2.0427796840667725} 08/30/2021 15:36:37 - INFO - __main__ - Step 13847: {'lr': 0.0004921378699163328, 'samples': 2658624, 'steps': 13846, 'loss/train': 1.9733552932739258} 08/30/2021 15:36:37 - INFO - __main__ - Step 13848: {'lr': 0.0004921365494734959, 'samples': 2658816, 'steps': 13847, 'loss/train': 1.2051162719726562} 08/30/2021 15:36:39 - INFO - __main__ - Step 13849: {'lr': 0.0004921352289215561, 'samples': 2659008, 'steps': 13848, 'loss/train': 1.9503183364868164} 08/30/2021 15:36:40 - INFO - __main__ - Step 13850: {'lr': 0.0004921339082605137, 'samples': 2659200, 'steps': 13849, 'loss/train': 0.5631958842277527} 08/30/2021 15:36:40 - INFO - __main__ - Step 13851: {'lr': 0.0004921325874903697, 'samples': 2659392, 'steps': 13850, 'loss/train': 3.191243886947632} 08/30/2021 15:36:40 - INFO - __main__ - Step 13852: {'lr': 0.0004921312666111245, 'samples': 2659584, 'steps': 13851, 'loss/train': 1.1803581714630127} 08/30/2021 15:36:41 - INFO - __main__ - Step 13853: {'lr': 0.0004921299456227785, 'samples': 2659776, 'steps': 13852, 'loss/train': 2.2592413425445557} 08/30/2021 15:36:41 - INFO - __main__ - Step 13854: {'lr': 0.0004921286245253327, 'samples': 2659968, 'steps': 13853, 'loss/train': 1.7450721263885498} 08/30/2021 15:36:43 - INFO - __main__ - Step 13855: {'lr': 0.0004921273033187874, 'samples': 2660160, 'steps': 13854, 'loss/train': 2.659731388092041} 08/30/2021 15:36:43 - INFO - __main__ - Step 13856: {'lr': 0.0004921259820031431, 'samples': 2660352, 'steps': 13855, 'loss/train': 1.5547701120376587} 08/30/2021 15:36:43 - INFO - __main__ - Step 13857: {'lr': 0.0004921246605784008, 'samples': 2660544, 'steps': 13856, 'loss/train': 1.8264232873916626} 08/30/2021 15:36:44 - INFO - __main__ - Step 13858: {'lr': 0.0004921233390445608, 'samples': 2660736, 'steps': 13857, 'loss/train': 1.5676571130752563} 08/30/2021 15:36:44 - INFO - __main__ - Step 13859: {'lr': 0.0004921220174016238, 'samples': 2660928, 'steps': 13858, 'loss/train': 2.17057728767395} 08/30/2021 15:36:46 - INFO - __main__ - Step 13860: {'lr': 0.0004921206956495903, 'samples': 2661120, 'steps': 13859, 'loss/train': 1.4273568391799927} 08/30/2021 15:36:46 - INFO - __main__ - Step 13861: {'lr': 0.000492119373788461, 'samples': 2661312, 'steps': 13860, 'loss/train': 1.8180774450302124} 08/30/2021 15:36:46 - INFO - __main__ - Step 13862: {'lr': 0.0004921180518182363, 'samples': 2661504, 'steps': 13861, 'loss/train': 1.031244158744812} 08/30/2021 15:36:47 - INFO - __main__ - Step 13863: {'lr': 0.0004921167297389171, 'samples': 2661696, 'steps': 13862, 'loss/train': 1.8788319826126099} 08/30/2021 15:36:47 - INFO - __main__ - Step 13864: {'lr': 0.0004921154075505038, 'samples': 2661888, 'steps': 13863, 'loss/train': 1.8196581602096558} 08/30/2021 15:36:49 - INFO - __main__ - Step 13865: {'lr': 0.0004921140852529969, 'samples': 2662080, 'steps': 13864, 'loss/train': 1.7515127658843994} 08/30/2021 15:36:49 - INFO - __main__ - Step 13866: {'lr': 0.0004921127628463972, 'samples': 2662272, 'steps': 13865, 'loss/train': 1.7796953916549683} 08/30/2021 15:36:50 - INFO - __main__ - Step 13867: {'lr': 0.0004921114403307053, 'samples': 2662464, 'steps': 13866, 'loss/train': 0.07805261760950089} 08/30/2021 15:36:50 - INFO - __main__ - Step 13868: {'lr': 0.0004921101177059218, 'samples': 2662656, 'steps': 13867, 'loss/train': 1.6172711849212646} 08/30/2021 15:36:50 - INFO - __main__ - Step 13869: {'lr': 0.0004921087949720471, 'samples': 2662848, 'steps': 13868, 'loss/train': 1.4609322547912598} 08/30/2021 15:36:51 - INFO - __main__ - Step 13870: {'lr': 0.0004921074721290819, 'samples': 2663040, 'steps': 13869, 'loss/train': 1.6962738037109375} 08/30/2021 15:36:52 - INFO - __main__ - Step 13871: {'lr': 0.0004921061491770268, 'samples': 2663232, 'steps': 13870, 'loss/train': 2.0180251598358154} 08/30/2021 15:36:53 - INFO - __main__ - Step 13872: {'lr': 0.0004921048261158825, 'samples': 2663424, 'steps': 13871, 'loss/train': 1.196499228477478} 08/30/2021 15:36:53 - INFO - __main__ - Step 13873: {'lr': 0.0004921035029456493, 'samples': 2663616, 'steps': 13872, 'loss/train': 1.5539485216140747} 08/30/2021 15:36:53 - INFO - __main__ - Step 13874: {'lr': 0.0004921021796663282, 'samples': 2663808, 'steps': 13873, 'loss/train': 1.5859588384628296} 08/30/2021 15:36:54 - INFO - __main__ - Step 13875: {'lr': 0.0004921008562779195, 'samples': 2664000, 'steps': 13874, 'loss/train': 2.119206190109253} 08/30/2021 15:36:55 - INFO - __main__ - Step 13876: {'lr': 0.0004920995327804239, 'samples': 2664192, 'steps': 13875, 'loss/train': 1.698654294013977} 08/30/2021 15:36:56 - INFO - __main__ - Step 13877: {'lr': 0.000492098209173842, 'samples': 2664384, 'steps': 13876, 'loss/train': 1.9036214351654053} 08/30/2021 15:36:56 - INFO - __main__ - Step 13878: {'lr': 0.0004920968854581745, 'samples': 2664576, 'steps': 13877, 'loss/train': 1.3836435079574585} 08/30/2021 15:36:56 - INFO - __main__ - Step 13879: {'lr': 0.0004920955616334216, 'samples': 2664768, 'steps': 13878, 'loss/train': 1.2148957252502441} 08/30/2021 15:36:57 - INFO - __main__ - Step 13880: {'lr': 0.0004920942376995844, 'samples': 2664960, 'steps': 13879, 'loss/train': 1.7520737648010254} 08/30/2021 15:36:58 - INFO - __main__ - Step 13881: {'lr': 0.0004920929136566632, 'samples': 2665152, 'steps': 13880, 'loss/train': 1.4705777168273926} 08/30/2021 15:36:59 - INFO - __main__ - Step 13882: {'lr': 0.0004920915895046587, 'samples': 2665344, 'steps': 13881, 'loss/train': 1.2839056253433228} 08/30/2021 15:36:59 - INFO - __main__ - Step 13883: {'lr': 0.0004920902652435715, 'samples': 2665536, 'steps': 13882, 'loss/train': 1.5503829717636108} 08/30/2021 15:36:59 - INFO - __main__ - Step 13884: {'lr': 0.0004920889408734021, 'samples': 2665728, 'steps': 13883, 'loss/train': 2.0199179649353027} 08/30/2021 15:37:00 - INFO - __main__ - Step 13885: {'lr': 0.0004920876163941511, 'samples': 2665920, 'steps': 13884, 'loss/train': 1.7413121461868286} 08/30/2021 15:37:02 - INFO - __main__ - Step 13886: {'lr': 0.0004920862918058192, 'samples': 2666112, 'steps': 13885, 'loss/train': 1.861501693725586} 08/30/2021 15:37:02 - INFO - __main__ - Step 13887: {'lr': 0.000492084967108407, 'samples': 2666304, 'steps': 13886, 'loss/train': 1.5949935913085938} 08/30/2021 15:37:03 - INFO - __main__ - Step 13888: {'lr': 0.000492083642301915, 'samples': 2666496, 'steps': 13887, 'loss/train': 2.0910377502441406} 08/30/2021 15:37:03 - INFO - __main__ - Step 13889: {'lr': 0.0004920823173863439, 'samples': 2666688, 'steps': 13888, 'loss/train': 0.0696505680680275} 08/30/2021 15:37:04 - INFO - __main__ - Step 13890: {'lr': 0.0004920809923616942, 'samples': 2666880, 'steps': 13889, 'loss/train': 0.8083196878433228} 08/30/2021 15:37:04 - INFO - __main__ - Step 13891: {'lr': 0.0004920796672279666, 'samples': 2667072, 'steps': 13890, 'loss/train': 1.207556128501892} 08/30/2021 15:37:05 - INFO - __main__ - Step 13892: {'lr': 0.0004920783419851615, 'samples': 2667264, 'steps': 13891, 'loss/train': 1.9331567287445068} 08/30/2021 15:37:06 - INFO - __main__ - Step 13893: {'lr': 0.0004920770166332798, 'samples': 2667456, 'steps': 13892, 'loss/train': 1.6196753978729248} 08/30/2021 15:37:06 - INFO - __main__ - Step 13894: {'lr': 0.0004920756911723219, 'samples': 2667648, 'steps': 13893, 'loss/train': 1.9326804876327515} 08/30/2021 15:37:06 - INFO - __main__ - Step 13895: {'lr': 0.0004920743656022884, 'samples': 2667840, 'steps': 13894, 'loss/train': 1.6578922271728516} 08/30/2021 15:37:07 - INFO - __main__ - Step 13896: {'lr': 0.0004920730399231799, 'samples': 2668032, 'steps': 13895, 'loss/train': 1.6116663217544556} 08/30/2021 15:37:07 - INFO - __main__ - Step 13897: {'lr': 0.000492071714134997, 'samples': 2668224, 'steps': 13896, 'loss/train': 1.697620153427124} 08/30/2021 15:37:09 - INFO - __main__ - Step 13898: {'lr': 0.0004920703882377403, 'samples': 2668416, 'steps': 13897, 'loss/train': 1.84322190284729} 08/30/2021 15:37:09 - INFO - __main__ - Step 13899: {'lr': 0.0004920690622314105, 'samples': 2668608, 'steps': 13898, 'loss/train': 2.862149953842163} 08/30/2021 15:37:10 - INFO - __main__ - Step 13900: {'lr': 0.0004920677361160081, 'samples': 2668800, 'steps': 13899, 'loss/train': 1.6132988929748535} 08/30/2021 15:37:10 - INFO - __main__ - Step 13901: {'lr': 0.0004920664098915337, 'samples': 2668992, 'steps': 13900, 'loss/train': 0.9476858377456665} 08/30/2021 15:37:10 - INFO - __main__ - Step 13902: {'lr': 0.000492065083557988, 'samples': 2669184, 'steps': 13901, 'loss/train': 1.6156305074691772} 08/30/2021 15:37:12 - INFO - __main__ - Step 13903: {'lr': 0.0004920637571153713, 'samples': 2669376, 'steps': 13902, 'loss/train': 1.4620449542999268} 08/30/2021 15:37:12 - INFO - __main__ - Step 13904: {'lr': 0.0004920624305636846, 'samples': 2669568, 'steps': 13903, 'loss/train': 1.3141453266143799} 08/30/2021 15:37:12 - INFO - __main__ - Step 13905: {'lr': 0.0004920611039029283, 'samples': 2669760, 'steps': 13904, 'loss/train': 0.782860279083252} 08/30/2021 15:37:13 - INFO - __main__ - Step 13906: {'lr': 0.0004920597771331029, 'samples': 2669952, 'steps': 13905, 'loss/train': 2.0047669410705566} 08/30/2021 15:37:13 - INFO - __main__ - Step 13907: {'lr': 0.0004920584502542091, 'samples': 2670144, 'steps': 13906, 'loss/train': 1.9071727991104126} 08/30/2021 15:37:15 - INFO - __main__ - Step 13908: {'lr': 0.0004920571232662475, 'samples': 2670336, 'steps': 13907, 'loss/train': 3.6241841316223145} 08/30/2021 15:37:15 - INFO - __main__ - Step 13909: {'lr': 0.0004920557961692188, 'samples': 2670528, 'steps': 13908, 'loss/train': 1.6944514513015747} 08/30/2021 15:37:15 - INFO - __main__ - Step 13910: {'lr': 0.0004920544689631233, 'samples': 2670720, 'steps': 13909, 'loss/train': 1.308904767036438} 08/30/2021 15:37:16 - INFO - __main__ - Step 13911: {'lr': 0.000492053141647962, 'samples': 2670912, 'steps': 13910, 'loss/train': 1.8157734870910645} 08/30/2021 15:37:16 - INFO - __main__ - Step 13912: {'lr': 0.0004920518142237352, 'samples': 2671104, 'steps': 13911, 'loss/train': 2.1475274562835693} 08/30/2021 15:37:18 - INFO - __main__ - Step 13913: {'lr': 0.0004920504866904436, 'samples': 2671296, 'steps': 13912, 'loss/train': 1.5949275493621826} 08/30/2021 15:37:18 - INFO - __main__ - Step 13914: {'lr': 0.0004920491590480878, 'samples': 2671488, 'steps': 13913, 'loss/train': 1.5115959644317627} 08/30/2021 15:37:19 - INFO - __main__ - Step 13915: {'lr': 0.0004920478312966683, 'samples': 2671680, 'steps': 13914, 'loss/train': 1.5728046894073486} 08/30/2021 15:37:19 - INFO - __main__ - Step 13916: {'lr': 0.0004920465034361859, 'samples': 2671872, 'steps': 13915, 'loss/train': 1.8880095481872559} 08/30/2021 15:37:19 - INFO - __main__ - Step 13917: {'lr': 0.000492045175466641, 'samples': 2672064, 'steps': 13916, 'loss/train': 1.8674532175064087} 08/30/2021 15:37:21 - INFO - __main__ - Step 13918: {'lr': 0.0004920438473880344, 'samples': 2672256, 'steps': 13917, 'loss/train': 1.7776989936828613} 08/30/2021 15:37:21 - INFO - __main__ - Step 13919: {'lr': 0.0004920425192003663, 'samples': 2672448, 'steps': 13918, 'loss/train': 1.404813528060913} 08/30/2021 15:37:22 - INFO - __main__ - Step 13920: {'lr': 0.0004920411909036379, 'samples': 2672640, 'steps': 13919, 'loss/train': 1.480295181274414} 08/30/2021 15:37:22 - INFO - __main__ - Step 13921: {'lr': 0.0004920398624978493, 'samples': 2672832, 'steps': 13920, 'loss/train': 1.4315030574798584} 08/30/2021 15:37:22 - INFO - __main__ - Step 13922: {'lr': 0.0004920385339830012, 'samples': 2673024, 'steps': 13921, 'loss/train': 1.4261845350265503} 08/30/2021 15:37:23 - INFO - __main__ - Step 13923: {'lr': 0.0004920372053590945, 'samples': 2673216, 'steps': 13922, 'loss/train': 2.091437339782715} 08/30/2021 15:37:24 - INFO - __main__ - Step 13924: {'lr': 0.0004920358766261294, 'samples': 2673408, 'steps': 13923, 'loss/train': 1.374764323234558} 08/30/2021 15:37:25 - INFO - __main__ - Step 13925: {'lr': 0.0004920345477841067, 'samples': 2673600, 'steps': 13924, 'loss/train': 1.987488031387329} 08/30/2021 15:37:25 - INFO - __main__ - Step 13926: {'lr': 0.000492033218833027, 'samples': 2673792, 'steps': 13925, 'loss/train': 2.5749735832214355} 08/30/2021 15:37:25 - INFO - __main__ - Step 13927: {'lr': 0.0004920318897728909, 'samples': 2673984, 'steps': 13926, 'loss/train': 1.9229964017868042} 08/30/2021 15:37:26 - INFO - __main__ - Step 13928: {'lr': 0.0004920305606036988, 'samples': 2674176, 'steps': 13927, 'loss/train': 2.0174031257629395} 08/30/2021 15:37:27 - INFO - __main__ - Step 13929: {'lr': 0.0004920292313254516, 'samples': 2674368, 'steps': 13928, 'loss/train': 1.2086713314056396} 08/30/2021 15:37:28 - INFO - __main__ - Step 13930: {'lr': 0.0004920279019381497, 'samples': 2674560, 'steps': 13929, 'loss/train': 1.6760241985321045} 08/30/2021 15:37:28 - INFO - __main__ - Step 13931: {'lr': 0.0004920265724417938, 'samples': 2674752, 'steps': 13930, 'loss/train': 1.5668439865112305} 08/30/2021 15:37:28 - INFO - __main__ - Step 13932: {'lr': 0.0004920252428363845, 'samples': 2674944, 'steps': 13931, 'loss/train': 1.283671259880066} 08/30/2021 15:37:29 - INFO - __main__ - Step 13933: {'lr': 0.0004920239131219223, 'samples': 2675136, 'steps': 13932, 'loss/train': 0.7934750318527222} 08/30/2021 15:37:30 - INFO - __main__ - Step 13934: {'lr': 0.0004920225832984079, 'samples': 2675328, 'steps': 13933, 'loss/train': 1.6775068044662476} 08/30/2021 15:37:31 - INFO - __main__ - Step 13935: {'lr': 0.0004920212533658419, 'samples': 2675520, 'steps': 13934, 'loss/train': 1.5483037233352661} 08/30/2021 15:37:31 - INFO - __main__ - Step 13936: {'lr': 0.0004920199233242247, 'samples': 2675712, 'steps': 13935, 'loss/train': 1.383685827255249} 08/30/2021 15:37:31 - INFO - __main__ - Step 13937: {'lr': 0.0004920185931735572, 'samples': 2675904, 'steps': 13936, 'loss/train': 1.6135034561157227} 08/30/2021 15:37:32 - INFO - __main__ - Step 13938: {'lr': 0.0004920172629138399, 'samples': 2676096, 'steps': 13937, 'loss/train': 1.8389533758163452} 08/30/2021 15:37:32 - INFO - __main__ - Step 13939: {'lr': 0.0004920159325450731, 'samples': 2676288, 'steps': 13938, 'loss/train': 5.266563892364502} 08/30/2021 15:37:34 - INFO - __main__ - Step 13940: {'lr': 0.0004920146020672578, 'samples': 2676480, 'steps': 13939, 'loss/train': 2.102337598800659} 08/30/2021 15:37:35 - INFO - __main__ - Step 13941: {'lr': 0.0004920132714803946, 'samples': 2676672, 'steps': 13940, 'loss/train': 1.7820079326629639} 08/30/2021 15:37:35 - INFO - __main__ - Step 13942: {'lr': 0.0004920119407844838, 'samples': 2676864, 'steps': 13941, 'loss/train': 1.3730963468551636} 08/30/2021 15:37:35 - INFO - __main__ - Step 13943: {'lr': 0.0004920106099795262, 'samples': 2677056, 'steps': 13942, 'loss/train': 1.7216168642044067} 08/30/2021 15:37:36 - INFO - __main__ - Step 13944: {'lr': 0.0004920092790655224, 'samples': 2677248, 'steps': 13943, 'loss/train': 1.7423903942108154} 08/30/2021 15:37:37 - INFO - __main__ - Step 13945: {'lr': 0.0004920079480424728, 'samples': 2677440, 'steps': 13944, 'loss/train': 1.3568315505981445} 08/30/2021 15:37:38 - INFO - __main__ - Step 13946: {'lr': 0.0004920066169103783, 'samples': 2677632, 'steps': 13945, 'loss/train': 1.8082294464111328} 08/30/2021 15:37:38 - INFO - __main__ - Step 13947: {'lr': 0.0004920052856692394, 'samples': 2677824, 'steps': 13946, 'loss/train': 0.3955638110637665} 08/30/2021 15:37:38 - INFO - __main__ - Step 13948: {'lr': 0.0004920039543190565, 'samples': 2678016, 'steps': 13947, 'loss/train': 2.1612000465393066} 08/30/2021 15:37:39 - INFO - __main__ - Step 13949: {'lr': 0.0004920026228598303, 'samples': 2678208, 'steps': 13948, 'loss/train': 2.3141117095947266} 08/30/2021 15:37:40 - INFO - __main__ - Step 13950: {'lr': 0.0004920012912915616, 'samples': 2678400, 'steps': 13949, 'loss/train': 1.8165549039840698} 08/30/2021 15:37:41 - INFO - __main__ - Step 13951: {'lr': 0.0004919999596142508, 'samples': 2678592, 'steps': 13950, 'loss/train': 1.9764556884765625} 08/30/2021 15:37:41 - INFO - __main__ - Step 13952: {'lr': 0.0004919986278278986, 'samples': 2678784, 'steps': 13951, 'loss/train': 1.7947592735290527} 08/30/2021 15:37:42 - INFO - __main__ - Step 13953: {'lr': 0.0004919972959325055, 'samples': 2678976, 'steps': 13952, 'loss/train': 0.1696995049715042} 08/30/2021 15:37:42 - INFO - __main__ - Step 13954: {'lr': 0.0004919959639280722, 'samples': 2679168, 'steps': 13953, 'loss/train': 1.772992491722107} 08/30/2021 15:37:44 - INFO - __main__ - Step 13955: {'lr': 0.0004919946318145992, 'samples': 2679360, 'steps': 13954, 'loss/train': 1.8060719966888428} 08/30/2021 15:37:44 - INFO - __main__ - Step 13956: {'lr': 0.0004919932995920872, 'samples': 2679552, 'steps': 13955, 'loss/train': 1.8740953207015991} 08/30/2021 15:37:44 - INFO - __main__ - Step 13957: {'lr': 0.0004919919672605366, 'samples': 2679744, 'steps': 13956, 'loss/train': 1.5823982954025269} 08/30/2021 15:37:45 - INFO - __main__ - Step 13958: {'lr': 0.0004919906348199483, 'samples': 2679936, 'steps': 13957, 'loss/train': 1.7188812494277954} 08/30/2021 15:37:45 - INFO - __main__ - Step 13959: {'lr': 0.0004919893022703228, 'samples': 2680128, 'steps': 13958, 'loss/train': 2.2183656692504883} 08/30/2021 15:37:45 - INFO - __main__ - Step 13960: {'lr': 0.0004919879696116605, 'samples': 2680320, 'steps': 13959, 'loss/train': 1.7986222505569458} 08/30/2021 15:37:47 - INFO - __main__ - Step 13961: {'lr': 0.0004919866368439624, 'samples': 2680512, 'steps': 13960, 'loss/train': 1.681349754333496} 08/30/2021 15:37:47 - INFO - __main__ - Step 13962: {'lr': 0.0004919853039672287, 'samples': 2680704, 'steps': 13961, 'loss/train': 1.8460050821304321} 08/30/2021 15:37:48 - INFO - __main__ - Step 13963: {'lr': 0.00049198397098146, 'samples': 2680896, 'steps': 13962, 'loss/train': 1.95518159866333} 08/30/2021 15:37:48 - INFO - __main__ - Step 13964: {'lr': 0.0004919826378866573, 'samples': 2681088, 'steps': 13963, 'loss/train': 1.8929909467697144} 08/30/2021 15:37:48 - INFO - __main__ - Step 13965: {'lr': 0.0004919813046828209, 'samples': 2681280, 'steps': 13964, 'loss/train': 1.0597758293151855} 08/30/2021 15:37:50 - INFO - __main__ - Step 13966: {'lr': 0.0004919799713699514, 'samples': 2681472, 'steps': 13965, 'loss/train': 1.583213210105896} 08/30/2021 15:37:50 - INFO - __main__ - Step 13967: {'lr': 0.0004919786379480494, 'samples': 2681664, 'steps': 13966, 'loss/train': 1.4857362508773804} 08/30/2021 15:37:51 - INFO - __main__ - Step 13968: {'lr': 0.0004919773044171158, 'samples': 2681856, 'steps': 13967, 'loss/train': 1.5280898809432983} 08/30/2021 15:37:51 - INFO - __main__ - Step 13969: {'lr': 0.0004919759707771507, 'samples': 2682048, 'steps': 13968, 'loss/train': 1.9612340927124023} 08/30/2021 15:37:51 - INFO - __main__ - Step 13970: {'lr': 0.0004919746370281551, 'samples': 2682240, 'steps': 13969, 'loss/train': 1.8146198987960815} 08/30/2021 15:37:53 - INFO - __main__ - Step 13971: {'lr': 0.0004919733031701295, 'samples': 2682432, 'steps': 13970, 'loss/train': 1.1746950149536133} 08/30/2021 15:37:54 - INFO - __main__ - Step 13972: {'lr': 0.0004919719692030743, 'samples': 2682624, 'steps': 13971, 'loss/train': 0.9985931515693665} 08/30/2021 15:37:54 - INFO - __main__ - Step 13973: {'lr': 0.0004919706351269904, 'samples': 2682816, 'steps': 13972, 'loss/train': 1.7299377918243408} 08/30/2021 15:37:54 - INFO - __main__ - Step 13974: {'lr': 0.0004919693009418782, 'samples': 2683008, 'steps': 13973, 'loss/train': 1.6628096103668213} 08/30/2021 15:37:55 - INFO - __main__ - Step 13975: {'lr': 0.0004919679666477384, 'samples': 2683200, 'steps': 13974, 'loss/train': 1.7094441652297974} 08/30/2021 15:37:55 - INFO - __main__ - Step 13976: {'lr': 0.0004919666322445715, 'samples': 2683392, 'steps': 13975, 'loss/train': 1.5595203638076782} 08/30/2021 15:37:57 - INFO - __main__ - Step 13977: {'lr': 0.0004919652977323783, 'samples': 2683584, 'steps': 13976, 'loss/train': 3.2277538776397705} 08/30/2021 15:37:57 - INFO - __main__ - Step 13978: {'lr': 0.0004919639631111592, 'samples': 2683776, 'steps': 13977, 'loss/train': 1.7416126728057861} 08/30/2021 15:37:58 - INFO - __main__ - Step 13979: {'lr': 0.0004919626283809149, 'samples': 2683968, 'steps': 13978, 'loss/train': 2.1867125034332275} 08/30/2021 15:37:58 - INFO - __main__ - Step 13980: {'lr': 0.0004919612935416459, 'samples': 2684160, 'steps': 13979, 'loss/train': 2.0710060596466064} 08/30/2021 15:37:58 - INFO - __main__ - Step 13981: {'lr': 0.000491959958593353, 'samples': 2684352, 'steps': 13980, 'loss/train': 1.9789578914642334} 08/30/2021 15:37:59 - INFO - __main__ - Step 13982: {'lr': 0.0004919586235360365, 'samples': 2684544, 'steps': 13981, 'loss/train': 2.061649799346924} 08/30/2021 15:38:00 - INFO - __main__ - Step 13983: {'lr': 0.0004919572883696974, 'samples': 2684736, 'steps': 13982, 'loss/train': 0.13816119730472565} 08/30/2021 15:38:01 - INFO - __main__ - Step 13984: {'lr': 0.0004919559530943359, 'samples': 2684928, 'steps': 13983, 'loss/train': 2.414689064025879} 08/30/2021 15:38:01 - INFO - __main__ - Step 13985: {'lr': 0.0004919546177099528, 'samples': 2685120, 'steps': 13984, 'loss/train': 1.581223964691162} 08/30/2021 15:38:01 - INFO - __main__ - Step 13986: {'lr': 0.0004919532822165487, 'samples': 2685312, 'steps': 13985, 'loss/train': 1.731987476348877} 08/30/2021 15:38:02 - INFO - __main__ - Step 13987: {'lr': 0.0004919519466141242, 'samples': 2685504, 'steps': 13986, 'loss/train': 1.7833051681518555} 08/30/2021 15:38:04 - INFO - __main__ - Step 13988: {'lr': 0.0004919506109026799, 'samples': 2685696, 'steps': 13987, 'loss/train': 1.6730360984802246} 08/30/2021 15:38:04 - INFO - __main__ - Step 13989: {'lr': 0.0004919492750822163, 'samples': 2685888, 'steps': 13988, 'loss/train': 1.2312800884246826} 08/30/2021 15:38:05 - INFO - __main__ - Step 13990: {'lr': 0.0004919479391527343, 'samples': 2686080, 'steps': 13989, 'loss/train': 1.9871710538864136} 08/30/2021 15:38:05 - INFO - __main__ - Step 13991: {'lr': 0.0004919466031142342, 'samples': 2686272, 'steps': 13990, 'loss/train': 1.8162356615066528} 08/30/2021 15:38:06 - INFO - __main__ - Step 13992: {'lr': 0.0004919452669667166, 'samples': 2686464, 'steps': 13991, 'loss/train': 1.7460132837295532} 08/30/2021 15:38:06 - INFO - __main__ - Step 13993: {'lr': 0.0004919439307101822, 'samples': 2686656, 'steps': 13992, 'loss/train': 1.6586244106292725} 08/30/2021 15:38:07 - INFO - __main__ - Step 13994: {'lr': 0.0004919425943446317, 'samples': 2686848, 'steps': 13993, 'loss/train': 0.23169642686843872} 08/30/2021 15:38:08 - INFO - __main__ - Step 13995: {'lr': 0.0004919412578700654, 'samples': 2687040, 'steps': 13994, 'loss/train': 2.336965322494507} 08/30/2021 15:38:08 - INFO - __main__ - Step 13996: {'lr': 0.0004919399212864843, 'samples': 2687232, 'steps': 13995, 'loss/train': 1.0330415964126587} 08/30/2021 15:38:09 - INFO - __main__ - Step 13997: {'lr': 0.0004919385845938888, 'samples': 2687424, 'steps': 13996, 'loss/train': 1.7321889400482178} 08/30/2021 15:38:09 - INFO - __main__ - Step 13998: {'lr': 0.0004919372477922794, 'samples': 2687616, 'steps': 13997, 'loss/train': 1.6030454635620117} 08/30/2021 15:38:11 - INFO - __main__ - Step 13999: {'lr': 0.0004919359108816569, 'samples': 2687808, 'steps': 13998, 'loss/train': 1.7427433729171753} 08/30/2021 15:38:12 - INFO - __main__ - Step 14000: {'lr': 0.0004919345738620218, 'samples': 2688000, 'steps': 13999, 'loss/train': 1.8576711416244507} 08/30/2021 15:38:12 - INFO - __main__ - Step 14001: {'lr': 0.0004919332367333747, 'samples': 2688192, 'steps': 14000, 'loss/train': 1.4826809167861938} 08/30/2021 15:38:12 - INFO - __main__ - Step 14002: {'lr': 0.0004919318994957162, 'samples': 2688384, 'steps': 14001, 'loss/train': 1.815764307975769} 08/30/2021 15:38:13 - INFO - __main__ - Step 14003: {'lr': 0.0004919305621490469, 'samples': 2688576, 'steps': 14002, 'loss/train': 2.4873239994049072} 08/30/2021 15:38:13 - INFO - __main__ - Step 14004: {'lr': 0.0004919292246933675, 'samples': 2688768, 'steps': 14003, 'loss/train': 1.6412919759750366} 08/30/2021 15:38:15 - INFO - __main__ - Step 14005: {'lr': 0.0004919278871286785, 'samples': 2688960, 'steps': 14004, 'loss/train': 2.0664548873901367} 08/30/2021 15:38:15 - INFO - __main__ - Step 14006: {'lr': 0.0004919265494549805, 'samples': 2689152, 'steps': 14005, 'loss/train': 2.6249313354492188} 08/30/2021 15:38:16 - INFO - __main__ - Step 14007: {'lr': 0.0004919252116722742, 'samples': 2689344, 'steps': 14006, 'loss/train': 1.8031655550003052} 08/30/2021 15:38:16 - INFO - __main__ - Step 14008: {'lr': 0.0004919238737805601, 'samples': 2689536, 'steps': 14007, 'loss/train': 0.16975277662277222} 08/30/2021 15:38:17 - INFO - __main__ - Step 14009: {'lr': 0.0004919225357798387, 'samples': 2689728, 'steps': 14008, 'loss/train': 1.5877736806869507} 08/30/2021 15:38:18 - INFO - __main__ - Step 14010: {'lr': 0.000491921197670111, 'samples': 2689920, 'steps': 14009, 'loss/train': 1.8153903484344482} 08/30/2021 15:38:18 - INFO - __main__ - Step 14011: {'lr': 0.0004919198594513771, 'samples': 2690112, 'steps': 14010, 'loss/train': 1.5196207761764526} 08/30/2021 15:38:19 - INFO - __main__ - Step 14012: {'lr': 0.0004919185211236379, 'samples': 2690304, 'steps': 14011, 'loss/train': 1.0222389698028564} 08/30/2021 15:38:19 - INFO - __main__ - Step 14013: {'lr': 0.000491917182686894, 'samples': 2690496, 'steps': 14012, 'loss/train': 1.8241993188858032} 08/30/2021 15:38:19 - INFO - __main__ - Step 14014: {'lr': 0.0004919158441411459, 'samples': 2690688, 'steps': 14013, 'loss/train': 1.7418286800384521} 08/30/2021 15:38:21 - INFO - __main__ - Step 14015: {'lr': 0.0004919145054863943, 'samples': 2690880, 'steps': 14014, 'loss/train': 1.3573681116104126} 08/30/2021 15:38:21 - INFO - __main__ - Step 14016: {'lr': 0.0004919131667226398, 'samples': 2691072, 'steps': 14015, 'loss/train': 1.9249037504196167} 08/30/2021 15:38:22 - INFO - __main__ - Step 14017: {'lr': 0.0004919118278498828, 'samples': 2691264, 'steps': 14016, 'loss/train': 1.7148103713989258} 08/30/2021 15:38:22 - INFO - __main__ - Step 14018: {'lr': 0.0004919104888681242, 'samples': 2691456, 'steps': 14017, 'loss/train': 2.0112602710723877} 08/30/2021 15:38:22 - INFO - __main__ - Step 14019: {'lr': 0.0004919091497773643, 'samples': 2691648, 'steps': 14018, 'loss/train': 1.5301368236541748} 08/30/2021 15:38:24 - INFO - __main__ - Step 14020: {'lr': 0.0004919078105776041, 'samples': 2691840, 'steps': 14019, 'loss/train': 0.8327675461769104} 08/30/2021 15:38:24 - INFO - __main__ - Step 14021: {'lr': 0.0004919064712688439, 'samples': 2692032, 'steps': 14020, 'loss/train': 1.8283535242080688} 08/30/2021 15:38:25 - INFO - __main__ - Step 14022: {'lr': 0.0004919051318510844, 'samples': 2692224, 'steps': 14021, 'loss/train': 1.206780195236206} 08/30/2021 15:38:25 - INFO - __main__ - Step 14023: {'lr': 0.0004919037923243261, 'samples': 2692416, 'steps': 14022, 'loss/train': 0.09630504250526428} 08/30/2021 15:38:25 - INFO - __main__ - Step 14024: {'lr': 0.0004919024526885697, 'samples': 2692608, 'steps': 14023, 'loss/train': 1.8012055158615112} 08/30/2021 15:38:27 - INFO - __main__ - Step 14025: {'lr': 0.0004919011129438158, 'samples': 2692800, 'steps': 14024, 'loss/train': 1.7135487794876099} 08/30/2021 15:38:27 - INFO - __main__ - Step 14026: {'lr': 0.0004918997730900649, 'samples': 2692992, 'steps': 14025, 'loss/train': 1.7016279697418213} 08/30/2021 15:38:28 - INFO - __main__ - Step 14027: {'lr': 0.0004918984331273178, 'samples': 2693184, 'steps': 14026, 'loss/train': 1.536525845527649} 08/30/2021 15:38:28 - INFO - __main__ - Step 14028: {'lr': 0.0004918970930555751, 'samples': 2693376, 'steps': 14027, 'loss/train': 1.658823013305664} 08/30/2021 15:38:28 - INFO - __main__ - Step 14029: {'lr': 0.0004918957528748371, 'samples': 2693568, 'steps': 14028, 'loss/train': 1.4102813005447388} 08/30/2021 15:38:30 - INFO - __main__ - Step 14030: {'lr': 0.0004918944125851047, 'samples': 2693760, 'steps': 14029, 'loss/train': 1.7518928050994873} 08/30/2021 15:38:31 - INFO - __main__ - Step 14031: {'lr': 0.0004918930721863784, 'samples': 2693952, 'steps': 14030, 'loss/train': 1.562180519104004} 08/30/2021 15:38:31 - INFO - __main__ - Step 14032: {'lr': 0.0004918917316786589, 'samples': 2694144, 'steps': 14031, 'loss/train': 1.6976679563522339} 08/30/2021 15:38:31 - INFO - __main__ - Step 14033: {'lr': 0.0004918903910619465, 'samples': 2694336, 'steps': 14032, 'loss/train': 1.5939868688583374} 08/30/2021 15:38:32 - INFO - __main__ - Step 14034: {'lr': 0.0004918890503362422, 'samples': 2694528, 'steps': 14033, 'loss/train': 1.6739760637283325} 08/30/2021 15:38:32 - INFO - __main__ - Step 14035: {'lr': 0.0004918877095015465, 'samples': 2694720, 'steps': 14034, 'loss/train': 3.0974340438842773} 08/30/2021 15:38:33 - INFO - __main__ - Step 14036: {'lr': 0.0004918863685578598, 'samples': 2694912, 'steps': 14035, 'loss/train': 0.43638405203819275} 08/30/2021 15:38:34 - INFO - __main__ - Step 14037: {'lr': 0.0004918850275051829, 'samples': 2695104, 'steps': 14036, 'loss/train': 0.8242853879928589} 08/30/2021 15:38:34 - INFO - __main__ - Step 14038: {'lr': 0.0004918836863435162, 'samples': 2695296, 'steps': 14037, 'loss/train': 1.301469326019287} 08/30/2021 15:38:35 - INFO - __main__ - Step 14039: {'lr': 0.0004918823450728606, 'samples': 2695488, 'steps': 14038, 'loss/train': 1.672101616859436} 08/30/2021 15:38:35 - INFO - __main__ - Step 14040: {'lr': 0.0004918810036932164, 'samples': 2695680, 'steps': 14039, 'loss/train': 1.5688748359680176} 08/30/2021 15:38:37 - INFO - __main__ - Step 14041: {'lr': 0.0004918796622045844, 'samples': 2695872, 'steps': 14040, 'loss/train': 0.8930960893630981} 08/30/2021 15:38:37 - INFO - __main__ - Step 14042: {'lr': 0.0004918783206069652, 'samples': 2696064, 'steps': 14041, 'loss/train': 0.10164300352334976} 08/30/2021 15:38:37 - INFO - __main__ - Step 14043: {'lr': 0.0004918769789003593, 'samples': 2696256, 'steps': 14042, 'loss/train': 1.9629344940185547} 08/30/2021 15:38:38 - INFO - __main__ - Step 14044: {'lr': 0.0004918756370847674, 'samples': 2696448, 'steps': 14043, 'loss/train': 1.7223443984985352} 08/30/2021 15:38:38 - INFO - __main__ - Step 14045: {'lr': 0.0004918742951601902, 'samples': 2696640, 'steps': 14044, 'loss/train': 2.261448383331299} 08/30/2021 15:38:40 - INFO - __main__ - Step 14046: {'lr': 0.000491872953126628, 'samples': 2696832, 'steps': 14045, 'loss/train': 2.6446807384490967} 08/30/2021 15:38:40 - INFO - __main__ - Step 14047: {'lr': 0.0004918716109840817, 'samples': 2697024, 'steps': 14046, 'loss/train': 1.6899405717849731} 08/30/2021 15:38:40 - INFO - __main__ - Step 14048: {'lr': 0.0004918702687325517, 'samples': 2697216, 'steps': 14047, 'loss/train': 1.8066340684890747} 08/30/2021 15:38:41 - INFO - __main__ - Step 14049: {'lr': 0.0004918689263720388, 'samples': 2697408, 'steps': 14048, 'loss/train': 1.766615390777588} 08/30/2021 15:38:41 - INFO - __main__ - Step 14050: {'lr': 0.0004918675839025434, 'samples': 2697600, 'steps': 14049, 'loss/train': 2.1533803939819336} 08/30/2021 15:38:44 - INFO - __main__ - Step 14051: {'lr': 0.0004918662413240662, 'samples': 2697792, 'steps': 14050, 'loss/train': 1.5729386806488037} 08/30/2021 15:38:44 - INFO - __main__ - Step 14052: {'lr': 0.0004918648986366078, 'samples': 2697984, 'steps': 14051, 'loss/train': 1.3882887363433838} 08/30/2021 15:38:44 - INFO - __main__ - Step 14053: {'lr': 0.0004918635558401687, 'samples': 2698176, 'steps': 14052, 'loss/train': 1.6236763000488281} 08/30/2021 15:38:45 - INFO - __main__ - Step 14054: {'lr': 0.0004918622129347498, 'samples': 2698368, 'steps': 14053, 'loss/train': 2.609205961227417} 08/30/2021 15:38:45 - INFO - __main__ - Step 14055: {'lr': 0.0004918608699203515, 'samples': 2698560, 'steps': 14054, 'loss/train': 1.5624489784240723} 08/30/2021 15:38:45 - INFO - __main__ - Step 14056: {'lr': 0.0004918595267969744, 'samples': 2698752, 'steps': 14055, 'loss/train': 1.3526252508163452} 08/30/2021 15:38:47 - INFO - __main__ - Step 14057: {'lr': 0.0004918581835646191, 'samples': 2698944, 'steps': 14056, 'loss/train': 1.87291419506073} 08/30/2021 15:38:47 - INFO - __main__ - Step 14058: {'lr': 0.0004918568402232863, 'samples': 2699136, 'steps': 14057, 'loss/train': 1.5407071113586426} 08/30/2021 15:38:48 - INFO - __main__ - Step 14059: {'lr': 0.0004918554967729764, 'samples': 2699328, 'steps': 14058, 'loss/train': 1.3131482601165771} 08/30/2021 15:38:48 - INFO - __main__ - Step 14060: {'lr': 0.0004918541532136902, 'samples': 2699520, 'steps': 14059, 'loss/train': 0.9513907432556152} 08/30/2021 15:38:48 - INFO - __main__ - Step 14061: {'lr': 0.0004918528095454283, 'samples': 2699712, 'steps': 14060, 'loss/train': 1.919915795326233} 08/30/2021 15:38:49 - INFO - __main__ - Step 14062: {'lr': 0.0004918514657681913, 'samples': 2699904, 'steps': 14061, 'loss/train': 1.270890235900879} 08/30/2021 15:38:50 - INFO - __main__ - Step 14063: {'lr': 0.0004918501218819796, 'samples': 2700096, 'steps': 14062, 'loss/train': 1.272247552871704} 08/30/2021 15:38:51 - INFO - __main__ - Step 14064: {'lr': 0.0004918487778867941, 'samples': 2700288, 'steps': 14063, 'loss/train': 2.140005111694336} 08/30/2021 15:38:51 - INFO - __main__ - Step 14065: {'lr': 0.0004918474337826353, 'samples': 2700480, 'steps': 14064, 'loss/train': 1.036586880683899} 08/30/2021 15:38:51 - INFO - __main__ - Step 14066: {'lr': 0.0004918460895695037, 'samples': 2700672, 'steps': 14065, 'loss/train': 1.626570701599121} 08/30/2021 15:38:52 - INFO - __main__ - Step 14067: {'lr': 0.0004918447452474, 'samples': 2700864, 'steps': 14066, 'loss/train': 1.351240634918213} 08/30/2021 15:38:53 - INFO - __main__ - Step 14068: {'lr': 0.0004918434008163247, 'samples': 2701056, 'steps': 14067, 'loss/train': 1.6912751197814941} 08/30/2021 15:38:54 - INFO - __main__ - Step 14069: {'lr': 0.0004918420562762786, 'samples': 2701248, 'steps': 14068, 'loss/train': 1.9792084693908691} 08/30/2021 15:38:54 - INFO - __main__ - Step 14070: {'lr': 0.0004918407116272622, 'samples': 2701440, 'steps': 14069, 'loss/train': 1.7819777727127075} 08/30/2021 15:38:54 - INFO - __main__ - Step 14071: {'lr': 0.000491839366869276, 'samples': 2701632, 'steps': 14070, 'loss/train': 1.1663535833358765} 08/30/2021 15:38:55 - INFO - __main__ - Step 14072: {'lr': 0.000491838022002321, 'samples': 2701824, 'steps': 14071, 'loss/train': 2.1723740100860596} 08/30/2021 15:38:56 - INFO - __main__ - Step 14073: {'lr': 0.0004918366770263972, 'samples': 2702016, 'steps': 14072, 'loss/train': 1.923164963722229} 08/30/2021 15:38:57 - INFO - __main__ - Step 14074: {'lr': 0.0004918353319415057, 'samples': 2702208, 'steps': 14073, 'loss/train': 1.9491578340530396} 08/30/2021 15:38:57 - INFO - __main__ - Step 14075: {'lr': 0.0004918339867476469, 'samples': 2702400, 'steps': 14074, 'loss/train': 1.578508734703064} 08/30/2021 15:38:57 - INFO - __main__ - Step 14076: {'lr': 0.0004918326414448214, 'samples': 2702592, 'steps': 14075, 'loss/train': 0.5960631966590881} 08/30/2021 15:38:58 - INFO - __main__ - Step 14077: {'lr': 0.0004918312960330299, 'samples': 2702784, 'steps': 14076, 'loss/train': 1.7320919036865234} 08/30/2021 15:38:59 - INFO - __main__ - Step 14078: {'lr': 0.0004918299505122729, 'samples': 2702976, 'steps': 14077, 'loss/train': 1.436476469039917} 08/30/2021 15:39:00 - INFO - __main__ - Step 14079: {'lr': 0.000491828604882551, 'samples': 2703168, 'steps': 14078, 'loss/train': 1.8881703615188599} 08/30/2021 15:39:00 - INFO - __main__ - Step 14080: {'lr': 0.0004918272591438649, 'samples': 2703360, 'steps': 14079, 'loss/train': 1.6356626749038696} 08/30/2021 15:39:01 - INFO - __main__ - Step 14081: {'lr': 0.0004918259132962153, 'samples': 2703552, 'steps': 14080, 'loss/train': 1.0681535005569458} 08/30/2021 15:39:01 - INFO - __main__ - Step 14082: {'lr': 0.0004918245673396025, 'samples': 2703744, 'steps': 14081, 'loss/train': 2.058180570602417} 08/30/2021 15:39:01 - INFO - __main__ - Step 14083: {'lr': 0.0004918232212740274, 'samples': 2703936, 'steps': 14082, 'loss/train': 1.0928046703338623} 08/30/2021 15:39:03 - INFO - __main__ - Step 14084: {'lr': 0.0004918218750994904, 'samples': 2704128, 'steps': 14083, 'loss/train': 1.6999531984329224} 08/30/2021 15:39:03 - INFO - __main__ - Step 14085: {'lr': 0.0004918205288159923, 'samples': 2704320, 'steps': 14084, 'loss/train': 1.7699096202850342} 08/30/2021 15:39:04 - INFO - __main__ - Step 14086: {'lr': 0.0004918191824235335, 'samples': 2704512, 'steps': 14085, 'loss/train': 1.5534898042678833} 08/30/2021 15:39:04 - INFO - __main__ - Step 14087: {'lr': 0.0004918178359221147, 'samples': 2704704, 'steps': 14086, 'loss/train': 1.5937029123306274} 08/30/2021 15:39:04 - INFO - __main__ - Step 14088: {'lr': 0.0004918164893117366, 'samples': 2704896, 'steps': 14087, 'loss/train': 1.4823368787765503} 08/30/2021 15:39:06 - INFO - __main__ - Step 14089: {'lr': 0.0004918151425923996, 'samples': 2705088, 'steps': 14088, 'loss/train': 1.1469001770019531} 08/30/2021 15:39:06 - INFO - __main__ - Step 14090: {'lr': 0.0004918137957641046, 'samples': 2705280, 'steps': 14089, 'loss/train': 0.939859926700592} 08/30/2021 15:39:07 - INFO - __main__ - Step 14091: {'lr': 0.000491812448826852, 'samples': 2705472, 'steps': 14090, 'loss/train': 0.8698261380195618} 08/30/2021 15:39:07 - INFO - __main__ - Step 14092: {'lr': 0.0004918111017806424, 'samples': 2705664, 'steps': 14091, 'loss/train': 1.6383382081985474} 08/30/2021 15:39:07 - INFO - __main__ - Step 14093: {'lr': 0.0004918097546254764, 'samples': 2705856, 'steps': 14092, 'loss/train': 2.0791850090026855} 08/30/2021 15:39:09 - INFO - __main__ - Step 14094: {'lr': 0.0004918084073613547, 'samples': 2706048, 'steps': 14093, 'loss/train': 2.0904128551483154} 08/30/2021 15:39:09 - INFO - __main__ - Step 14095: {'lr': 0.0004918070599882778, 'samples': 2706240, 'steps': 14094, 'loss/train': 1.762641429901123} 08/30/2021 15:39:10 - INFO - __main__ - Step 14096: {'lr': 0.0004918057125062465, 'samples': 2706432, 'steps': 14095, 'loss/train': 1.576412320137024} 08/30/2021 15:39:10 - INFO - __main__ - Step 14097: {'lr': 0.0004918043649152612, 'samples': 2706624, 'steps': 14096, 'loss/train': 1.2938681840896606} 08/30/2021 15:39:10 - INFO - __main__ - Step 14098: {'lr': 0.0004918030172153225, 'samples': 2706816, 'steps': 14097, 'loss/train': 1.8019441366195679} 08/30/2021 15:39:12 - INFO - __main__ - Step 14099: {'lr': 0.0004918016694064313, 'samples': 2707008, 'steps': 14098, 'loss/train': 1.796257495880127} 08/30/2021 15:39:12 - INFO - __main__ - Step 14100: {'lr': 0.0004918003214885877, 'samples': 2707200, 'steps': 14099, 'loss/train': 1.3860641717910767} 08/30/2021 15:39:13 - INFO - __main__ - Step 14101: {'lr': 0.0004917989734617928, 'samples': 2707392, 'steps': 14100, 'loss/train': 0.7811518311500549} 08/30/2021 15:39:13 - INFO - __main__ - Step 14102: {'lr': 0.0004917976253260471, 'samples': 2707584, 'steps': 14101, 'loss/train': 1.9318650960922241} 08/30/2021 15:39:13 - INFO - __main__ - Step 14103: {'lr': 0.000491796277081351, 'samples': 2707776, 'steps': 14102, 'loss/train': 2.0168838500976562} 08/30/2021 15:39:16 - INFO - __main__ - Step 14104: {'lr': 0.0004917949287277052, 'samples': 2707968, 'steps': 14103, 'loss/train': 2.3239035606384277} 08/30/2021 15:39:16 - INFO - __main__ - Step 14105: {'lr': 0.0004917935802651104, 'samples': 2708160, 'steps': 14104, 'loss/train': 1.8436191082000732} 08/30/2021 15:39:17 - INFO - __main__ - Step 14106: {'lr': 0.0004917922316935671, 'samples': 2708352, 'steps': 14105, 'loss/train': 1.6571234464645386} 08/30/2021 15:39:17 - INFO - __main__ - Step 14107: {'lr': 0.000491790883013076, 'samples': 2708544, 'steps': 14106, 'loss/train': 1.3560878038406372} 08/30/2021 15:39:17 - INFO - __main__ - Step 14108: {'lr': 0.0004917895342236377, 'samples': 2708736, 'steps': 14107, 'loss/train': 0.08560151606798172} 08/30/2021 15:39:18 - INFO - __main__ - Step 14109: {'lr': 0.0004917881853252527, 'samples': 2708928, 'steps': 14108, 'loss/train': 1.4498388767242432} 08/30/2021 15:39:19 - INFO - __main__ - Step 14110: {'lr': 0.0004917868363179216, 'samples': 2709120, 'steps': 14109, 'loss/train': 2.0461947917938232} 08/30/2021 15:39:20 - INFO - __main__ - Step 14111: {'lr': 0.0004917854872016451, 'samples': 2709312, 'steps': 14110, 'loss/train': 1.3963159322738647} 08/30/2021 15:39:20 - INFO - __main__ - Step 14112: {'lr': 0.000491784137976424, 'samples': 2709504, 'steps': 14111, 'loss/train': 1.5421956777572632} 08/30/2021 15:39:20 - INFO - __main__ - Step 14113: {'lr': 0.0004917827886422586, 'samples': 2709696, 'steps': 14112, 'loss/train': 1.673872709274292} 08/30/2021 15:39:21 - INFO - __main__ - Step 14114: {'lr': 0.0004917814391991494, 'samples': 2709888, 'steps': 14113, 'loss/train': 2.0303893089294434} 08/30/2021 15:39:22 - INFO - __main__ - Step 14115: {'lr': 0.0004917800896470974, 'samples': 2710080, 'steps': 14114, 'loss/train': 1.528775930404663} 08/30/2021 15:39:23 - INFO - __main__ - Step 14116: {'lr': 0.000491778739986103, 'samples': 2710272, 'steps': 14115, 'loss/train': 1.8756296634674072} 08/30/2021 15:39:23 - INFO - __main__ - Step 14117: {'lr': 0.0004917773902161669, 'samples': 2710464, 'steps': 14116, 'loss/train': 2.3668806552886963} 08/30/2021 15:39:23 - INFO - __main__ - Step 14118: {'lr': 0.0004917760403372895, 'samples': 2710656, 'steps': 14117, 'loss/train': 2.0578255653381348} 08/30/2021 15:39:24 - INFO - __main__ - Step 14119: {'lr': 0.0004917746903494717, 'samples': 2710848, 'steps': 14118, 'loss/train': 1.6370103359222412} 08/30/2021 15:39:25 - INFO - __main__ - Step 14120: {'lr': 0.0004917733402527138, 'samples': 2711040, 'steps': 14119, 'loss/train': 1.6128284931182861} 08/30/2021 15:39:26 - INFO - __main__ - Step 14121: {'lr': 0.0004917719900470167, 'samples': 2711232, 'steps': 14120, 'loss/train': 1.5568597316741943} 08/30/2021 15:39:26 - INFO - __main__ - Step 14122: {'lr': 0.0004917706397323808, 'samples': 2711424, 'steps': 14121, 'loss/train': 1.3538464307785034} 08/30/2021 15:39:27 - INFO - __main__ - Step 14123: {'lr': 0.0004917692893088067, 'samples': 2711616, 'steps': 14122, 'loss/train': 0.16965769231319427} 08/30/2021 15:39:27 - INFO - __main__ - Step 14124: {'lr': 0.0004917679387762952, 'samples': 2711808, 'steps': 14123, 'loss/train': 1.666258692741394} 08/30/2021 15:39:28 - INFO - __main__ - Step 14125: {'lr': 0.0004917665881348467, 'samples': 2712000, 'steps': 14124, 'loss/train': 1.620166540145874} 08/30/2021 15:39:29 - INFO - __main__ - Step 14126: {'lr': 0.000491765237384462, 'samples': 2712192, 'steps': 14125, 'loss/train': 1.5839182138442993} 08/30/2021 15:39:29 - INFO - __main__ - Step 14127: {'lr': 0.0004917638865251416, 'samples': 2712384, 'steps': 14126, 'loss/train': 1.9082685708999634} 08/30/2021 15:39:30 - INFO - __main__ - Step 14128: {'lr': 0.0004917625355568861, 'samples': 2712576, 'steps': 14127, 'loss/train': 2.201725482940674} 08/30/2021 15:39:30 - INFO - __main__ - Step 14129: {'lr': 0.0004917611844796962, 'samples': 2712768, 'steps': 14128, 'loss/train': 1.6258965730667114} 08/30/2021 15:39:30 - INFO - __main__ - Step 14130: {'lr': 0.0004917598332935724, 'samples': 2712960, 'steps': 14129, 'loss/train': 1.4448388814926147} 08/30/2021 15:39:32 - INFO - __main__ - Step 14131: {'lr': 0.0004917584819985153, 'samples': 2713152, 'steps': 14130, 'loss/train': 1.4698928594589233} 08/30/2021 15:39:32 - INFO - __main__ - Step 14132: {'lr': 0.0004917571305945256, 'samples': 2713344, 'steps': 14131, 'loss/train': 1.5409729480743408} 08/30/2021 15:39:33 - INFO - __main__ - Step 14133: {'lr': 0.0004917557790816039, 'samples': 2713536, 'steps': 14132, 'loss/train': 1.8997957706451416} 08/30/2021 15:39:33 - INFO - __main__ - Step 14134: {'lr': 0.0004917544274597507, 'samples': 2713728, 'steps': 14133, 'loss/train': 1.914629340171814} 08/30/2021 15:39:33 - INFO - __main__ - Step 14135: {'lr': 0.0004917530757289668, 'samples': 2713920, 'steps': 14134, 'loss/train': 1.625847339630127} 08/30/2021 15:39:35 - INFO - __main__ - Step 14136: {'lr': 0.0004917517238892526, 'samples': 2714112, 'steps': 14135, 'loss/train': 2.0104947090148926} 08/30/2021 15:39:36 - INFO - __main__ - Step 14137: {'lr': 0.0004917503719406087, 'samples': 2714304, 'steps': 14136, 'loss/train': 0.09295482188463211} 08/30/2021 15:39:36 - INFO - __main__ - Step 14138: {'lr': 0.000491749019883036, 'samples': 2714496, 'steps': 14137, 'loss/train': 0.12390390038490295} 08/30/2021 15:39:37 - INFO - __main__ - Step 14139: {'lr': 0.0004917476677165349, 'samples': 2714688, 'steps': 14138, 'loss/train': 1.3897292613983154} 08/30/2021 15:39:37 - INFO - __main__ - Step 14140: {'lr': 0.0004917463154411059, 'samples': 2714880, 'steps': 14139, 'loss/train': 1.7671445608139038} 08/30/2021 15:39:37 - INFO - __main__ - Step 14141: {'lr': 0.0004917449630567499, 'samples': 2715072, 'steps': 14140, 'loss/train': 1.804566740989685} 08/30/2021 15:39:39 - INFO - __main__ - Step 14142: {'lr': 0.0004917436105634673, 'samples': 2715264, 'steps': 14141, 'loss/train': 1.5026624202728271} 08/30/2021 15:39:39 - INFO - __main__ - Step 14143: {'lr': 0.0004917422579612587, 'samples': 2715456, 'steps': 14142, 'loss/train': 1.7232012748718262} 08/30/2021 15:39:40 - INFO - __main__ - Step 14144: {'lr': 0.0004917409052501248, 'samples': 2715648, 'steps': 14143, 'loss/train': 1.2619420289993286} 08/30/2021 15:39:40 - INFO - __main__ - Step 14145: {'lr': 0.0004917395524300661, 'samples': 2715840, 'steps': 14144, 'loss/train': 1.1857624053955078} 08/30/2021 15:39:40 - INFO - __main__ - Step 14146: {'lr': 0.0004917381995010834, 'samples': 2716032, 'steps': 14145, 'loss/train': 1.8339183330535889} 08/30/2021 15:39:42 - INFO - __main__ - Step 14147: {'lr': 0.0004917368464631772, 'samples': 2716224, 'steps': 14146, 'loss/train': 1.0906007289886475} 08/30/2021 15:39:42 - INFO - __main__ - Step 14148: {'lr': 0.0004917354933163481, 'samples': 2716416, 'steps': 14147, 'loss/train': 1.5463742017745972} 08/30/2021 15:39:43 - INFO - __main__ - Step 14149: {'lr': 0.0004917341400605967, 'samples': 2716608, 'steps': 14148, 'loss/train': 1.2037752866744995} 08/30/2021 15:39:43 - INFO - __main__ - Step 14150: {'lr': 0.0004917327866959236, 'samples': 2716800, 'steps': 14149, 'loss/train': 1.5649795532226562} 08/30/2021 15:39:44 - INFO - __main__ - Step 14151: {'lr': 0.0004917314332223295, 'samples': 2716992, 'steps': 14150, 'loss/train': 2.0070488452911377} 08/30/2021 15:39:44 - INFO - __main__ - Step 14152: {'lr': 0.0004917300796398148, 'samples': 2717184, 'steps': 14151, 'loss/train': 1.3868390321731567} 08/30/2021 15:39:45 - INFO - __main__ - Step 14153: {'lr': 0.0004917287259483805, 'samples': 2717376, 'steps': 14152, 'loss/train': 3.9668636322021484} 08/30/2021 15:39:46 - INFO - __main__ - Step 14154: {'lr': 0.0004917273721480268, 'samples': 2717568, 'steps': 14153, 'loss/train': 2.3048255443573} 08/30/2021 15:39:46 - INFO - __main__ - Step 14155: {'lr': 0.0004917260182387545, 'samples': 2717760, 'steps': 14154, 'loss/train': 1.8597017526626587} 08/30/2021 15:39:46 - INFO - __main__ - Step 14156: {'lr': 0.0004917246642205642, 'samples': 2717952, 'steps': 14155, 'loss/train': 1.8402026891708374} 08/30/2021 15:39:47 - INFO - __main__ - Step 14157: {'lr': 0.0004917233100934565, 'samples': 2718144, 'steps': 14156, 'loss/train': 1.6949419975280762} 08/30/2021 15:39:49 - INFO - __main__ - Step 14158: {'lr': 0.0004917219558574319, 'samples': 2718336, 'steps': 14157, 'loss/train': 1.4849724769592285} 08/30/2021 15:39:49 - INFO - __main__ - Step 14159: {'lr': 0.0004917206015124913, 'samples': 2718528, 'steps': 14158, 'loss/train': 1.8341007232666016} 08/30/2021 15:39:50 - INFO - __main__ - Step 14160: {'lr': 0.000491719247058635, 'samples': 2718720, 'steps': 14159, 'loss/train': 1.6200454235076904} 08/30/2021 15:39:50 - INFO - __main__ - Step 14161: {'lr': 0.0004917178924958638, 'samples': 2718912, 'steps': 14160, 'loss/train': 1.7147324085235596} 08/30/2021 15:39:50 - INFO - __main__ - Step 14162: {'lr': 0.0004917165378241782, 'samples': 2719104, 'steps': 14161, 'loss/train': 1.798283576965332} 08/30/2021 15:39:52 - INFO - __main__ - Step 14163: {'lr': 0.0004917151830435789, 'samples': 2719296, 'steps': 14162, 'loss/train': 1.7082637548446655} 08/30/2021 15:39:52 - INFO - __main__ - Step 14164: {'lr': 0.0004917138281540664, 'samples': 2719488, 'steps': 14163, 'loss/train': 1.2861160039901733} 08/30/2021 15:39:53 - INFO - __main__ - Step 14165: {'lr': 0.0004917124731556415, 'samples': 2719680, 'steps': 14164, 'loss/train': 1.4616657495498657} 08/30/2021 15:39:53 - INFO - __main__ - Step 14166: {'lr': 0.0004917111180483046, 'samples': 2719872, 'steps': 14165, 'loss/train': 1.669005274772644} 08/30/2021 15:39:53 - INFO - __main__ - Step 14167: {'lr': 0.0004917097628320564, 'samples': 2720064, 'steps': 14166, 'loss/train': 1.6722915172576904} 08/30/2021 15:39:55 - INFO - __main__ - Step 14168: {'lr': 0.0004917084075068975, 'samples': 2720256, 'steps': 14167, 'loss/train': 2.3572487831115723} 08/30/2021 15:39:55 - INFO - __main__ - Step 14169: {'lr': 0.0004917070520728286, 'samples': 2720448, 'steps': 14168, 'loss/train': 1.9552350044250488} 08/30/2021 15:39:56 - INFO - __main__ - Step 14170: {'lr': 0.0004917056965298501, 'samples': 2720640, 'steps': 14169, 'loss/train': 1.7678080797195435} 08/30/2021 15:39:56 - INFO - __main__ - Step 14171: {'lr': 0.0004917043408779629, 'samples': 2720832, 'steps': 14170, 'loss/train': 1.659894585609436} 08/30/2021 15:39:56 - INFO - __main__ - Step 14172: {'lr': 0.0004917029851171674, 'samples': 2721024, 'steps': 14171, 'loss/train': 1.7558727264404297} 08/30/2021 15:39:58 - INFO - __main__ - Step 14173: {'lr': 0.0004917016292474642, 'samples': 2721216, 'steps': 14172, 'loss/train': 2.1233808994293213} 08/30/2021 15:39:58 - INFO - __main__ - Step 14174: {'lr': 0.000491700273268854, 'samples': 2721408, 'steps': 14173, 'loss/train': 1.6767710447311401} 08/30/2021 15:39:59 - INFO - __main__ - Step 14175: {'lr': 0.0004916989171813374, 'samples': 2721600, 'steps': 14174, 'loss/train': 1.980328917503357} 08/30/2021 15:39:59 - INFO - __main__ - Step 14176: {'lr': 0.000491697560984915, 'samples': 2721792, 'steps': 14175, 'loss/train': 1.541935682296753} 08/30/2021 15:39:59 - INFO - __main__ - Step 14177: {'lr': 0.0004916962046795874, 'samples': 2721984, 'steps': 14176, 'loss/train': 1.7506691217422485} 08/30/2021 15:40:01 - INFO - __main__ - Step 14178: {'lr': 0.0004916948482653553, 'samples': 2722176, 'steps': 14177, 'loss/train': 1.729347586631775} 08/30/2021 15:40:01 - INFO - __main__ - Step 14179: {'lr': 0.0004916934917422191, 'samples': 2722368, 'steps': 14178, 'loss/train': 1.5602684020996094} 08/30/2021 15:40:02 - INFO - __main__ - Step 14180: {'lr': 0.0004916921351101796, 'samples': 2722560, 'steps': 14179, 'loss/train': 1.8815113306045532} 08/30/2021 15:40:02 - INFO - __main__ - Step 14181: {'lr': 0.0004916907783692374, 'samples': 2722752, 'steps': 14180, 'loss/train': 1.4521411657333374} 08/30/2021 15:40:02 - INFO - __main__ - Step 14182: {'lr': 0.000491689421519393, 'samples': 2722944, 'steps': 14181, 'loss/train': 0.0882885530591011} 08/30/2021 15:40:04 - INFO - __main__ - Step 14183: {'lr': 0.0004916880645606471, 'samples': 2723136, 'steps': 14182, 'loss/train': 2.0369925498962402} 08/30/2021 15:40:04 - INFO - __main__ - Step 14184: {'lr': 0.0004916867074930002, 'samples': 2723328, 'steps': 14183, 'loss/train': 1.6349990367889404} 08/30/2021 15:40:05 - INFO - __main__ - Step 14185: {'lr': 0.0004916853503164531, 'samples': 2723520, 'steps': 14184, 'loss/train': 1.890197992324829} 08/30/2021 15:40:05 - INFO - __main__ - Step 14186: {'lr': 0.0004916839930310063, 'samples': 2723712, 'steps': 14185, 'loss/train': 1.398798942565918} 08/30/2021 15:40:05 - INFO - __main__ - Step 14187: {'lr': 0.0004916826356366605, 'samples': 2723904, 'steps': 14186, 'loss/train': 1.4671858549118042} 08/30/2021 15:40:06 - INFO - __main__ - Step 14188: {'lr': 0.0004916812781334161, 'samples': 2724096, 'steps': 14187, 'loss/train': 1.8269046545028687} 08/30/2021 15:40:07 - INFO - __main__ - Step 14189: {'lr': 0.0004916799205212739, 'samples': 2724288, 'steps': 14188, 'loss/train': 1.612385630607605} 08/30/2021 15:40:08 - INFO - __main__ - Step 14190: {'lr': 0.0004916785628002345, 'samples': 2724480, 'steps': 14189, 'loss/train': 1.8590627908706665} 08/30/2021 15:40:08 - INFO - __main__ - Step 14191: {'lr': 0.0004916772049702984, 'samples': 2724672, 'steps': 14190, 'loss/train': 1.6657508611679077} 08/30/2021 15:40:08 - INFO - __main__ - Step 14192: {'lr': 0.0004916758470314662, 'samples': 2724864, 'steps': 14191, 'loss/train': 1.6730341911315918} 08/30/2021 15:40:09 - INFO - __main__ - Step 14193: {'lr': 0.0004916744889837388, 'samples': 2725056, 'steps': 14192, 'loss/train': 1.5481258630752563} 08/30/2021 15:40:10 - INFO - __main__ - Step 14194: {'lr': 0.0004916731308271165, 'samples': 2725248, 'steps': 14193, 'loss/train': 1.7963457107543945} 08/30/2021 15:40:11 - INFO - __main__ - Step 14195: {'lr': 0.0004916717725616, 'samples': 2725440, 'steps': 14194, 'loss/train': 1.623094916343689} 08/30/2021 15:40:11 - INFO - __main__ - Step 14196: {'lr': 0.0004916704141871899, 'samples': 2725632, 'steps': 14195, 'loss/train': 1.7807375192642212} 08/30/2021 15:40:11 - INFO - __main__ - Step 14197: {'lr': 0.000491669055703887, 'samples': 2725824, 'steps': 14196, 'loss/train': 1.500786542892456} 08/30/2021 15:40:12 - INFO - __main__ - Step 14198: {'lr': 0.0004916676971116916, 'samples': 2726016, 'steps': 14197, 'loss/train': 0.9933580756187439} 08/30/2021 15:40:13 - INFO - __main__ - Step 14199: {'lr': 0.0004916663384106045, 'samples': 2726208, 'steps': 14198, 'loss/train': 0.9632720947265625} 08/30/2021 15:40:14 - INFO - __main__ - Step 14200: {'lr': 0.0004916649796006263, 'samples': 2726400, 'steps': 14199, 'loss/train': 1.751441478729248} 08/30/2021 15:40:14 - INFO - __main__ - Step 14201: {'lr': 0.0004916636206817575, 'samples': 2726592, 'steps': 14200, 'loss/train': 1.7866759300231934} 08/30/2021 15:40:14 - INFO - __main__ - Step 14202: {'lr': 0.0004916622616539988, 'samples': 2726784, 'steps': 14201, 'loss/train': 1.6616225242614746} 08/30/2021 15:40:15 - INFO - __main__ - Step 14203: {'lr': 0.000491660902517351, 'samples': 2726976, 'steps': 14202, 'loss/train': 1.58908212184906} 08/30/2021 15:40:16 - INFO - __main__ - Step 14204: {'lr': 0.0004916595432718143, 'samples': 2727168, 'steps': 14203, 'loss/train': 1.4164177179336548} 08/30/2021 15:40:17 - INFO - __main__ - Step 14205: {'lr': 0.0004916581839173897, 'samples': 2727360, 'steps': 14204, 'loss/train': 1.7263103723526} 08/30/2021 15:40:17 - INFO - __main__ - Step 14206: {'lr': 0.0004916568244540776, 'samples': 2727552, 'steps': 14205, 'loss/train': 1.6879026889801025} 08/30/2021 15:40:17 - INFO - __main__ - Step 14207: {'lr': 0.0004916554648818787, 'samples': 2727744, 'steps': 14206, 'loss/train': 1.2350469827651978} 08/30/2021 15:40:18 - INFO - __main__ - Step 14208: {'lr': 0.0004916541052007936, 'samples': 2727936, 'steps': 14207, 'loss/train': 0.9809690713882446} 08/30/2021 15:40:20 - INFO - __main__ - Step 14209: {'lr': 0.0004916527454108227, 'samples': 2728128, 'steps': 14208, 'loss/train': 1.7045831680297852} 08/30/2021 15:40:20 - INFO - __main__ - Step 14210: {'lr': 0.0004916513855119669, 'samples': 2728320, 'steps': 14209, 'loss/train': 1.4296053647994995} 08/30/2021 15:40:21 - INFO - __main__ - Step 14211: {'lr': 0.0004916500255042268, 'samples': 2728512, 'steps': 14210, 'loss/train': 0.5579972267150879} 08/30/2021 15:40:21 - INFO - __main__ - Step 14212: {'lr': 0.0004916486653876029, 'samples': 2728704, 'steps': 14211, 'loss/train': 1.7848087549209595} 08/30/2021 15:40:21 - INFO - __main__ - Step 14213: {'lr': 0.0004916473051620958, 'samples': 2728896, 'steps': 14212, 'loss/train': 1.980293869972229} 08/30/2021 15:40:23 - INFO - __main__ - Step 14214: {'lr': 0.0004916459448277062, 'samples': 2729088, 'steps': 14213, 'loss/train': 1.9483768939971924} 08/30/2021 15:40:23 - INFO - __main__ - Step 14215: {'lr': 0.0004916445843844346, 'samples': 2729280, 'steps': 14214, 'loss/train': 1.2159225940704346} 08/30/2021 15:40:24 - INFO - __main__ - Step 14216: {'lr': 0.0004916432238322818, 'samples': 2729472, 'steps': 14215, 'loss/train': 0.19944612681865692} 08/30/2021 15:40:24 - INFO - __main__ - Step 14217: {'lr': 0.0004916418631712481, 'samples': 2729664, 'steps': 14216, 'loss/train': 2.559760570526123} 08/30/2021 15:40:24 - INFO - __main__ - Step 14218: {'lr': 0.0004916405024013344, 'samples': 2729856, 'steps': 14217, 'loss/train': 1.8995834589004517} 08/30/2021 15:40:27 - INFO - __main__ - Step 14219: {'lr': 0.0004916391415225413, 'samples': 2730048, 'steps': 14218, 'loss/train': 1.6571044921875} 08/30/2021 15:40:27 - INFO - __main__ - Step 14220: {'lr': 0.0004916377805348692, 'samples': 2730240, 'steps': 14219, 'loss/train': 1.1118005514144897} 08/30/2021 15:40:28 - INFO - __main__ - Step 14221: {'lr': 0.000491636419438319, 'samples': 2730432, 'steps': 14220, 'loss/train': 0.6850120425224304} 08/30/2021 15:40:28 - INFO - __main__ - Step 14222: {'lr': 0.000491635058232891, 'samples': 2730624, 'steps': 14221, 'loss/train': 0.6429716944694519} 08/30/2021 15:40:28 - INFO - __main__ - Step 14223: {'lr': 0.0004916336969185861, 'samples': 2730816, 'steps': 14222, 'loss/train': 0.6164513230323792} 08/30/2021 15:40:29 - INFO - __main__ - Step 14224: {'lr': 0.0004916323354954047, 'samples': 2731008, 'steps': 14223, 'loss/train': 1.9105051755905151} 08/30/2021 15:40:30 - INFO - __main__ - Step 14225: {'lr': 0.0004916309739633475, 'samples': 2731200, 'steps': 14224, 'loss/train': 1.7779122591018677} 08/30/2021 15:40:31 - INFO - __main__ - Step 14226: {'lr': 0.0004916296123224151, 'samples': 2731392, 'steps': 14225, 'loss/train': 1.6873564720153809} 08/30/2021 15:40:31 - INFO - __main__ - Step 14227: {'lr': 0.0004916282505726082, 'samples': 2731584, 'steps': 14226, 'loss/train': 1.4683501720428467} 08/30/2021 15:40:32 - INFO - __main__ - Step 14228: {'lr': 0.0004916268887139272, 'samples': 2731776, 'steps': 14227, 'loss/train': 0.12098906189203262} 08/30/2021 15:40:32 - INFO - __main__ - Step 14229: {'lr': 0.000491625526746373, 'samples': 2731968, 'steps': 14228, 'loss/train': 1.8777852058410645} 08/30/2021 15:40:33 - INFO - __main__ - Step 14230: {'lr': 0.000491624164669946, 'samples': 2732160, 'steps': 14229, 'loss/train': 1.4158958196640015} 08/30/2021 15:40:34 - INFO - __main__ - Step 14231: {'lr': 0.0004916228024846469, 'samples': 2732352, 'steps': 14230, 'loss/train': 0.4140443503856659} 08/30/2021 15:40:34 - INFO - __main__ - Step 14232: {'lr': 0.0004916214401904763, 'samples': 2732544, 'steps': 14231, 'loss/train': 1.8795267343521118} 08/30/2021 15:40:34 - INFO - __main__ - Step 14233: {'lr': 0.0004916200777874348, 'samples': 2732736, 'steps': 14232, 'loss/train': 1.7342122793197632} 08/30/2021 15:40:35 - INFO - __main__ - Step 14234: {'lr': 0.000491618715275523, 'samples': 2732928, 'steps': 14233, 'loss/train': 1.5589019060134888} 08/30/2021 15:40:37 - INFO - __main__ - Step 14235: {'lr': 0.0004916173526547415, 'samples': 2733120, 'steps': 14234, 'loss/train': 1.8375165462493896} 08/30/2021 15:40:37 - INFO - __main__ - Step 14236: {'lr': 0.000491615989925091, 'samples': 2733312, 'steps': 14235, 'loss/train': 1.63279128074646} 08/30/2021 15:40:37 - INFO - __main__ - Step 14237: {'lr': 0.0004916146270865721, 'samples': 2733504, 'steps': 14236, 'loss/train': 0.2016444057226181} 08/30/2021 15:40:38 - INFO - __main__ - Step 14238: {'lr': 0.0004916132641391854, 'samples': 2733696, 'steps': 14237, 'loss/train': 1.4945404529571533} 08/30/2021 15:40:38 - INFO - __main__ - Step 14239: {'lr': 0.0004916119010829314, 'samples': 2733888, 'steps': 14238, 'loss/train': 1.5928460359573364} 08/30/2021 15:40:40 - INFO - __main__ - Step 14240: {'lr': 0.0004916105379178108, 'samples': 2734080, 'steps': 14239, 'loss/train': 1.9532207250595093} 08/30/2021 15:40:40 - INFO - __main__ - Step 14241: {'lr': 0.0004916091746438243, 'samples': 2734272, 'steps': 14240, 'loss/train': 2.2842166423797607} 08/30/2021 15:40:40 - INFO - __main__ - Step 14242: {'lr': 0.0004916078112609724, 'samples': 2734464, 'steps': 14241, 'loss/train': 1.407718300819397} 08/30/2021 15:40:41 - INFO - __main__ - Step 14243: {'lr': 0.0004916064477692557, 'samples': 2734656, 'steps': 14242, 'loss/train': 1.682555913925171} 08/30/2021 15:40:41 - INFO - __main__ - Step 14244: {'lr': 0.0004916050841686748, 'samples': 2734848, 'steps': 14243, 'loss/train': 1.3194701671600342} 08/30/2021 15:40:43 - INFO - __main__ - Step 14245: {'lr': 0.0004916037204592306, 'samples': 2735040, 'steps': 14244, 'loss/train': 1.6163827180862427} 08/30/2021 15:40:43 - INFO - __main__ - Step 14246: {'lr': 0.0004916023566409233, 'samples': 2735232, 'steps': 14245, 'loss/train': 1.799128770828247} 08/30/2021 15:40:43 - INFO - __main__ - Step 14247: {'lr': 0.0004916009927137538, 'samples': 2735424, 'steps': 14246, 'loss/train': 1.4250456094741821} 08/30/2021 15:40:44 - INFO - __main__ - Step 14248: {'lr': 0.0004915996286777226, 'samples': 2735616, 'steps': 14247, 'loss/train': 1.5041444301605225} 08/30/2021 15:40:44 - INFO - __main__ - Step 14249: {'lr': 0.0004915982645328304, 'samples': 2735808, 'steps': 14248, 'loss/train': 1.6152318716049194} 08/30/2021 15:40:44 - INFO - __main__ - Step 14250: {'lr': 0.0004915969002790777, 'samples': 2736000, 'steps': 14249, 'loss/train': 2.0096380710601807} 08/30/2021 15:40:46 - INFO - __main__ - Step 14251: {'lr': 0.0004915955359164651, 'samples': 2736192, 'steps': 14250, 'loss/train': 1.9248408079147339} 08/30/2021 15:40:46 - INFO - __main__ - Step 14252: {'lr': 0.0004915941714449933, 'samples': 2736384, 'steps': 14251, 'loss/train': 0.09167566150426865} 08/30/2021 15:40:47 - INFO - __main__ - Step 14253: {'lr': 0.000491592806864663, 'samples': 2736576, 'steps': 14252, 'loss/train': 2.085392475128174} 08/30/2021 15:40:47 - INFO - __main__ - Step 14254: {'lr': 0.0004915914421754746, 'samples': 2736768, 'steps': 14253, 'loss/train': 1.867599606513977} 08/30/2021 15:40:48 - INFO - __main__ - Step 14255: {'lr': 0.0004915900773774289, 'samples': 2736960, 'steps': 14254, 'loss/train': 1.4897617101669312} 08/30/2021 15:40:49 - INFO - __main__ - Step 14256: {'lr': 0.0004915887124705263, 'samples': 2737152, 'steps': 14255, 'loss/train': 1.184784173965454} 08/30/2021 15:40:49 - INFO - __main__ - Step 14257: {'lr': 0.0004915873474547677, 'samples': 2737344, 'steps': 14256, 'loss/train': 1.953404426574707} 08/30/2021 15:40:50 - INFO - __main__ - Step 14258: {'lr': 0.0004915859823301535, 'samples': 2737536, 'steps': 14257, 'loss/train': 1.5674388408660889} 08/30/2021 15:40:50 - INFO - __main__ - Step 14259: {'lr': 0.0004915846170966845, 'samples': 2737728, 'steps': 14258, 'loss/train': 1.546112060546875} 08/30/2021 15:40:51 - INFO - __main__ - Step 14260: {'lr': 0.000491583251754361, 'samples': 2737920, 'steps': 14259, 'loss/train': 1.146052360534668} 08/30/2021 15:40:52 - INFO - __main__ - Step 14261: {'lr': 0.0004915818863031839, 'samples': 2738112, 'steps': 14260, 'loss/train': 1.3799189329147339} 08/30/2021 15:40:52 - INFO - __main__ - Step 14262: {'lr': 0.0004915805207431537, 'samples': 2738304, 'steps': 14261, 'loss/train': 1.8515392541885376} 08/30/2021 15:40:53 - INFO - __main__ - Step 14263: {'lr': 0.0004915791550742712, 'samples': 2738496, 'steps': 14262, 'loss/train': 1.4869722127914429} 08/30/2021 15:40:53 - INFO - __main__ - Step 14264: {'lr': 0.0004915777892965368, 'samples': 2738688, 'steps': 14263, 'loss/train': 0.8241997957229614} 08/30/2021 15:40:53 - INFO - __main__ - Step 14265: {'lr': 0.0004915764234099511, 'samples': 2738880, 'steps': 14264, 'loss/train': 1.3659237623214722} 08/30/2021 15:40:55 - INFO - __main__ - Step 14266: {'lr': 0.0004915750574145148, 'samples': 2739072, 'steps': 14265, 'loss/train': 1.5381276607513428} 08/30/2021 15:40:55 - INFO - __main__ - Step 14267: {'lr': 0.0004915736913102285, 'samples': 2739264, 'steps': 14266, 'loss/train': 1.520689845085144} 08/30/2021 15:40:56 - INFO - __main__ - Step 14268: {'lr': 0.0004915723250970928, 'samples': 2739456, 'steps': 14267, 'loss/train': 2.185713529586792} 08/30/2021 15:40:56 - INFO - __main__ - Step 14269: {'lr': 0.0004915709587751084, 'samples': 2739648, 'steps': 14268, 'loss/train': 11.970024108886719} 08/30/2021 15:40:57 - INFO - __main__ - Step 14270: {'lr': 0.0004915695923442759, 'samples': 2739840, 'steps': 14269, 'loss/train': 0.8003661632537842} 08/30/2021 15:40:59 - INFO - __main__ - Step 14271: {'lr': 0.0004915682258045958, 'samples': 2740032, 'steps': 14270, 'loss/train': 1.5905641317367554} 08/30/2021 15:40:59 - INFO - __main__ - Step 14272: {'lr': 0.0004915668591560688, 'samples': 2740224, 'steps': 14271, 'loss/train': 2.2194135189056396} 08/30/2021 15:40:59 - INFO - __main__ - Step 14273: {'lr': 0.0004915654923986955, 'samples': 2740416, 'steps': 14272, 'loss/train': 1.8407152891159058} 08/30/2021 15:41:00 - INFO - __main__ - Step 14274: {'lr': 0.0004915641255324764, 'samples': 2740608, 'steps': 14273, 'loss/train': 1.638126015663147} 08/30/2021 15:41:00 - INFO - __main__ - Step 14275: {'lr': 0.0004915627585574124, 'samples': 2740800, 'steps': 14274, 'loss/train': 1.9308607578277588} 08/30/2021 15:41:01 - INFO - __main__ - Step 14276: {'lr': 0.0004915613914735038, 'samples': 2740992, 'steps': 14275, 'loss/train': 1.8504908084869385} 08/30/2021 15:41:02 - INFO - __main__ - Step 14277: {'lr': 0.0004915600242807516, 'samples': 2741184, 'steps': 14276, 'loss/train': 0.22727176547050476} 08/30/2021 15:41:02 - INFO - __main__ - Step 14278: {'lr': 0.000491558656979156, 'samples': 2741376, 'steps': 14277, 'loss/train': 5.502272129058838} 08/30/2021 15:41:03 - INFO - __main__ - Step 14279: {'lr': 0.0004915572895687179, 'samples': 2741568, 'steps': 14278, 'loss/train': 1.881693720817566} 08/30/2021 15:41:03 - INFO - __main__ - Step 14280: {'lr': 0.0004915559220494376, 'samples': 2741760, 'steps': 14279, 'loss/train': 1.9186737537384033} 08/30/2021 15:41:03 - INFO - __main__ - Step 14281: {'lr': 0.0004915545544213161, 'samples': 2741952, 'steps': 14280, 'loss/train': 1.2309820652008057} 08/30/2021 15:41:05 - INFO - __main__ - Step 14282: {'lr': 0.0004915531866843539, 'samples': 2742144, 'steps': 14281, 'loss/train': 2.065537452697754} 08/30/2021 15:41:06 - INFO - __main__ - Step 14283: {'lr': 0.0004915518188385514, 'samples': 2742336, 'steps': 14282, 'loss/train': 1.8233487606048584} 08/30/2021 15:41:06 - INFO - __main__ - Step 14284: {'lr': 0.0004915504508839095, 'samples': 2742528, 'steps': 14283, 'loss/train': 1.5087192058563232} 08/30/2021 15:41:06 - INFO - __main__ - Step 14285: {'lr': 0.0004915490828204287, 'samples': 2742720, 'steps': 14284, 'loss/train': 1.539300560951233} 08/30/2021 15:41:07 - INFO - __main__ - Step 14286: {'lr': 0.0004915477146481095, 'samples': 2742912, 'steps': 14285, 'loss/train': 1.836625576019287} 08/30/2021 15:41:08 - INFO - __main__ - Step 14287: {'lr': 0.0004915463463669527, 'samples': 2743104, 'steps': 14286, 'loss/train': 0.992317795753479} 08/30/2021 15:41:09 - INFO - __main__ - Step 14288: {'lr': 0.0004915449779769589, 'samples': 2743296, 'steps': 14287, 'loss/train': 1.8336970806121826} 08/30/2021 15:41:09 - INFO - __main__ - Step 14289: {'lr': 0.0004915436094781285, 'samples': 2743488, 'steps': 14288, 'loss/train': 2.112403392791748} 08/30/2021 15:41:09 - INFO - __main__ - Step 14290: {'lr': 0.0004915422408704624, 'samples': 2743680, 'steps': 14289, 'loss/train': 1.8381317853927612} 08/30/2021 15:41:10 - INFO - __main__ - Step 14291: {'lr': 0.0004915408721539612, 'samples': 2743872, 'steps': 14290, 'loss/train': 1.4352819919586182} 08/30/2021 15:41:10 - INFO - __main__ - Step 14292: {'lr': 0.0004915395033286251, 'samples': 2744064, 'steps': 14291, 'loss/train': 1.2204521894454956} 08/30/2021 15:41:12 - INFO - __main__ - Step 14293: {'lr': 0.0004915381343944552, 'samples': 2744256, 'steps': 14292, 'loss/train': 1.5716047286987305} 08/30/2021 15:41:12 - INFO - __main__ - Step 14294: {'lr': 0.0004915367653514521, 'samples': 2744448, 'steps': 14293, 'loss/train': 1.7927772998809814} 08/30/2021 15:41:12 - INFO - __main__ - Step 14295: {'lr': 0.0004915353961996161, 'samples': 2744640, 'steps': 14294, 'loss/train': 2.267578125} 08/30/2021 15:41:13 - INFO - __main__ - Step 14296: {'lr': 0.000491534026938948, 'samples': 2744832, 'steps': 14295, 'loss/train': 1.5962440967559814} 08/30/2021 15:41:13 - INFO - __main__ - Step 14297: {'lr': 0.0004915326575694484, 'samples': 2745024, 'steps': 14296, 'loss/train': 1.5142970085144043} 08/30/2021 15:41:15 - INFO - __main__ - Step 14298: {'lr': 0.0004915312880911178, 'samples': 2745216, 'steps': 14297, 'loss/train': 1.996443748474121} 08/30/2021 15:41:15 - INFO - __main__ - Step 14299: {'lr': 0.000491529918503957, 'samples': 2745408, 'steps': 14298, 'loss/train': 1.968015432357788} 08/30/2021 15:41:15 - INFO - __main__ - Step 14300: {'lr': 0.0004915285488079666, 'samples': 2745600, 'steps': 14299, 'loss/train': 1.713179349899292} 08/30/2021 15:41:16 - INFO - __main__ - Step 14301: {'lr': 0.0004915271790031471, 'samples': 2745792, 'steps': 14300, 'loss/train': 2.0385515689849854} 08/30/2021 15:41:16 - INFO - __main__ - Step 14302: {'lr': 0.0004915258090894993, 'samples': 2745984, 'steps': 14301, 'loss/train': 1.9879531860351562} 08/30/2021 15:41:17 - INFO - __main__ - Step 14303: {'lr': 0.0004915244390670236, 'samples': 2746176, 'steps': 14302, 'loss/train': 1.8816629648208618} 08/30/2021 15:41:18 - INFO - __main__ - Step 14304: {'lr': 0.0004915230689357206, 'samples': 2746368, 'steps': 14303, 'loss/train': 2.0318562984466553} 08/30/2021 15:41:18 - INFO - __main__ - Step 14305: {'lr': 0.0004915216986955913, 'samples': 2746560, 'steps': 14304, 'loss/train': 2.043475389480591} 08/30/2021 15:41:19 - INFO - __main__ - Step 14306: {'lr': 0.0004915203283466359, 'samples': 2746752, 'steps': 14305, 'loss/train': 1.5072704553604126} 08/30/2021 15:41:19 - INFO - __main__ - Step 14307: {'lr': 0.0004915189578888552, 'samples': 2746944, 'steps': 14306, 'loss/train': 1.5600268840789795} 08/30/2021 15:41:21 - INFO - __main__ - Step 14308: {'lr': 0.0004915175873222497, 'samples': 2747136, 'steps': 14307, 'loss/train': 1.9318269491195679} 08/30/2021 15:41:21 - INFO - __main__ - Step 14309: {'lr': 0.0004915162166468201, 'samples': 2747328, 'steps': 14308, 'loss/train': 1.7547612190246582} 08/30/2021 15:41:22 - INFO - __main__ - Step 14310: {'lr': 0.0004915148458625671, 'samples': 2747520, 'steps': 14309, 'loss/train': 1.6511695384979248} 08/30/2021 15:41:22 - INFO - __main__ - Step 14311: {'lr': 0.0004915134749694912, 'samples': 2747712, 'steps': 14310, 'loss/train': 1.975413203239441} 08/30/2021 15:41:22 - INFO - __main__ - Step 14312: {'lr': 0.000491512103967593, 'samples': 2747904, 'steps': 14311, 'loss/train': 1.1436662673950195} 08/30/2021 15:41:23 - INFO - __main__ - Step 14313: {'lr': 0.0004915107328568733, 'samples': 2748096, 'steps': 14312, 'loss/train': 0.17707191407680511} 08/30/2021 15:41:24 - INFO - __main__ - Step 14314: {'lr': 0.0004915093616373326, 'samples': 2748288, 'steps': 14313, 'loss/train': 0.571360170841217} 08/30/2021 15:41:25 - INFO - __main__ - Step 14315: {'lr': 0.0004915079903089714, 'samples': 2748480, 'steps': 14314, 'loss/train': 1.20900559425354} 08/30/2021 15:41:25 - INFO - __main__ - Step 14316: {'lr': 0.0004915066188717905, 'samples': 2748672, 'steps': 14315, 'loss/train': 1.5505168437957764} 08/30/2021 15:41:26 - INFO - __main__ - Step 14317: {'lr': 0.0004915052473257904, 'samples': 2748864, 'steps': 14316, 'loss/train': 1.903862476348877} 08/30/2021 15:41:26 - INFO - __main__ - Step 14318: {'lr': 0.0004915038756709717, 'samples': 2749056, 'steps': 14317, 'loss/train': 1.8158437013626099} 08/30/2021 15:41:27 - INFO - __main__ - Step 14319: {'lr': 0.0004915025039073352, 'samples': 2749248, 'steps': 14318, 'loss/train': 1.8041901588439941} 08/30/2021 15:41:28 - INFO - __main__ - Step 14320: {'lr': 0.0004915011320348814, 'samples': 2749440, 'steps': 14319, 'loss/train': 2.1272006034851074} 08/30/2021 15:41:28 - INFO - __main__ - Step 14321: {'lr': 0.0004914997600536108, 'samples': 2749632, 'steps': 14320, 'loss/train': 1.5176854133605957} 08/30/2021 15:41:29 - INFO - __main__ - Step 14322: {'lr': 0.0004914983879635242, 'samples': 2749824, 'steps': 14321, 'loss/train': 1.4800630807876587} 08/30/2021 15:41:29 - INFO - __main__ - Step 14323: {'lr': 0.0004914970157646222, 'samples': 2750016, 'steps': 14322, 'loss/train': 1.5841407775878906} 08/30/2021 15:41:31 - INFO - __main__ - Step 14324: {'lr': 0.0004914956434569054, 'samples': 2750208, 'steps': 14323, 'loss/train': 1.765442967414856} 08/30/2021 15:41:31 - INFO - __main__ - Step 14325: {'lr': 0.0004914942710403743, 'samples': 2750400, 'steps': 14324, 'loss/train': 1.7265383005142212} 08/30/2021 15:41:32 - INFO - __main__ - Step 14326: {'lr': 0.0004914928985150296, 'samples': 2750592, 'steps': 14325, 'loss/train': 1.7524030208587646} 08/30/2021 15:41:32 - INFO - __main__ - Step 14327: {'lr': 0.0004914915258808719, 'samples': 2750784, 'steps': 14326, 'loss/train': 2.004016160964966} 08/30/2021 15:41:32 - INFO - __main__ - Step 14328: {'lr': 0.0004914901531379019, 'samples': 2750976, 'steps': 14327, 'loss/train': 1.2179161310195923} 08/30/2021 15:41:34 - INFO - __main__ - Step 14329: {'lr': 0.0004914887802861201, 'samples': 2751168, 'steps': 14328, 'loss/train': 1.6710330247879028} 08/30/2021 15:41:34 - INFO - __main__ - Step 14330: {'lr': 0.0004914874073255273, 'samples': 2751360, 'steps': 14329, 'loss/train': 2.0541014671325684} 08/30/2021 15:41:35 - INFO - __main__ - Step 14331: {'lr': 0.0004914860342561239, 'samples': 2751552, 'steps': 14330, 'loss/train': 2.1631600856781006} 08/30/2021 15:41:35 - INFO - __main__ - Step 14332: {'lr': 0.0004914846610779107, 'samples': 2751744, 'steps': 14331, 'loss/train': 1.567399024963379} 08/30/2021 15:41:35 - INFO - __main__ - Step 14333: {'lr': 0.0004914832877908881, 'samples': 2751936, 'steps': 14332, 'loss/train': 2.012059211730957} 08/30/2021 15:41:37 - INFO - __main__ - Step 14334: {'lr': 0.0004914819143950571, 'samples': 2752128, 'steps': 14333, 'loss/train': 1.7972086668014526} 08/30/2021 15:41:37 - INFO - __main__ - Step 14335: {'lr': 0.0004914805408904179, 'samples': 2752320, 'steps': 14334, 'loss/train': 1.19582998752594} 08/30/2021 15:41:38 - INFO - __main__ - Step 14336: {'lr': 0.0004914791672769713, 'samples': 2752512, 'steps': 14335, 'loss/train': 1.9483637809753418} 08/30/2021 15:41:38 - INFO - __main__ - Step 14337: {'lr': 0.000491477793554718, 'samples': 2752704, 'steps': 14336, 'loss/train': 1.8428703546524048} 08/30/2021 15:41:38 - INFO - __main__ - Step 14338: {'lr': 0.0004914764197236584, 'samples': 2752896, 'steps': 14337, 'loss/train': 1.7327208518981934} 08/30/2021 15:41:39 - INFO - __main__ - Step 14339: {'lr': 0.0004914750457837933, 'samples': 2753088, 'steps': 14338, 'loss/train': 1.4848452806472778} 08/30/2021 15:41:40 - INFO - __main__ - Step 14340: {'lr': 0.0004914736717351233, 'samples': 2753280, 'steps': 14339, 'loss/train': 1.6279864311218262} 08/30/2021 15:41:41 - INFO - __main__ - Step 14341: {'lr': 0.000491472297577649, 'samples': 2753472, 'steps': 14340, 'loss/train': 1.8970388174057007} 08/30/2021 15:41:41 - INFO - __main__ - Step 14342: {'lr': 0.000491470923311371, 'samples': 2753664, 'steps': 14341, 'loss/train': 1.8129960298538208} 08/30/2021 15:41:41 - INFO - __main__ - Step 14343: {'lr': 0.0004914695489362899, 'samples': 2753856, 'steps': 14342, 'loss/train': 1.3674474954605103} 08/30/2021 15:41:42 - INFO - __main__ - Step 14344: {'lr': 0.0004914681744524064, 'samples': 2754048, 'steps': 14343, 'loss/train': 1.4709528684616089} 08/30/2021 15:41:43 - INFO - __main__ - Step 14345: {'lr': 0.0004914667998597211, 'samples': 2754240, 'steps': 14344, 'loss/train': 1.3310235738754272} 08/30/2021 15:41:44 - INFO - __main__ - Step 14346: {'lr': 0.0004914654251582344, 'samples': 2754432, 'steps': 14345, 'loss/train': 2.2530410289764404} 08/30/2021 15:41:44 - INFO - __main__ - Step 14347: {'lr': 0.0004914640503479473, 'samples': 2754624, 'steps': 14346, 'loss/train': 1.4643199443817139} 08/30/2021 15:41:45 - INFO - __main__ - Step 14348: {'lr': 0.0004914626754288601, 'samples': 2754816, 'steps': 14347, 'loss/train': 1.0527572631835938} 08/30/2021 15:41:45 - INFO - __main__ - Step 14349: {'lr': 0.0004914613004009736, 'samples': 2755008, 'steps': 14348, 'loss/train': 1.3456844091415405} 08/30/2021 15:41:46 - INFO - __main__ - Step 14350: {'lr': 0.0004914599252642884, 'samples': 2755200, 'steps': 14349, 'loss/train': 1.5882034301757812} 08/30/2021 15:41:47 - INFO - __main__ - Step 14351: {'lr': 0.000491458550018805, 'samples': 2755392, 'steps': 14350, 'loss/train': 1.6092170476913452} 08/30/2021 15:41:47 - INFO - __main__ - Step 14352: {'lr': 0.0004914571746645242, 'samples': 2755584, 'steps': 14351, 'loss/train': 1.8229730129241943} 08/30/2021 15:41:47 - INFO - __main__ - Step 14353: {'lr': 0.0004914557992014465, 'samples': 2755776, 'steps': 14352, 'loss/train': 1.7088993787765503} 08/30/2021 15:41:48 - INFO - __main__ - Step 14354: {'lr': 0.0004914544236295725, 'samples': 2755968, 'steps': 14353, 'loss/train': 1.7496505975723267} 08/30/2021 15:41:49 - INFO - __main__ - Step 14355: {'lr': 0.0004914530479489029, 'samples': 2756160, 'steps': 14354, 'loss/train': 2.1107027530670166} 08/30/2021 15:41:50 - INFO - __main__ - Step 14356: {'lr': 0.0004914516721594382, 'samples': 2756352, 'steps': 14355, 'loss/train': 1.5025612115859985} 08/30/2021 15:41:50 - INFO - __main__ - Step 14357: {'lr': 0.0004914502962611792, 'samples': 2756544, 'steps': 14356, 'loss/train': 2.0511035919189453} 08/30/2021 15:41:51 - INFO - __main__ - Step 14358: {'lr': 0.0004914489202541264, 'samples': 2756736, 'steps': 14357, 'loss/train': 1.1436680555343628} 08/30/2021 15:41:51 - INFO - __main__ - Step 14359: {'lr': 0.0004914475441382804, 'samples': 2756928, 'steps': 14358, 'loss/train': 1.7909042835235596} 08/30/2021 15:41:52 - INFO - __main__ - Step 14360: {'lr': 0.0004914461679136419, 'samples': 2757120, 'steps': 14359, 'loss/train': 2.647141695022583} 08/30/2021 15:41:53 - INFO - __main__ - Step 14361: {'lr': 0.0004914447915802115, 'samples': 2757312, 'steps': 14360, 'loss/train': 1.8089959621429443} 08/30/2021 15:41:53 - INFO - __main__ - Step 14362: {'lr': 0.0004914434151379898, 'samples': 2757504, 'steps': 14361, 'loss/train': 1.717605471611023} 08/30/2021 15:41:54 - INFO - __main__ - Step 14363: {'lr': 0.0004914420385869773, 'samples': 2757696, 'steps': 14362, 'loss/train': 1.586990475654602} 08/30/2021 15:41:54 - INFO - __main__ - Step 14364: {'lr': 0.0004914406619271749, 'samples': 2757888, 'steps': 14363, 'loss/train': 1.747564435005188} 08/30/2021 15:41:54 - INFO - __main__ - Step 14365: {'lr': 0.0004914392851585829, 'samples': 2758080, 'steps': 14364, 'loss/train': 1.7078890800476074} 08/30/2021 15:41:56 - INFO - __main__ - Step 14366: {'lr': 0.0004914379082812023, 'samples': 2758272, 'steps': 14365, 'loss/train': 1.7765601873397827} 08/30/2021 15:41:56 - INFO - __main__ - Step 14367: {'lr': 0.0004914365312950333, 'samples': 2758464, 'steps': 14366, 'loss/train': 1.6005475521087646} 08/30/2021 15:41:56 - INFO - __main__ - Step 14368: {'lr': 0.0004914351542000768, 'samples': 2758656, 'steps': 14367, 'loss/train': 1.6172153949737549} 08/30/2021 15:41:57 - INFO - __main__ - Step 14369: {'lr': 0.0004914337769963334, 'samples': 2758848, 'steps': 14368, 'loss/train': 1.952616810798645} 08/30/2021 15:41:57 - INFO - __main__ - Step 14370: {'lr': 0.0004914323996838036, 'samples': 2759040, 'steps': 14369, 'loss/train': 1.992571234703064} 08/30/2021 15:41:59 - INFO - __main__ - Step 14371: {'lr': 0.0004914310222624881, 'samples': 2759232, 'steps': 14370, 'loss/train': 2.0507609844207764} 08/30/2021 15:41:59 - INFO - __main__ - Step 14372: {'lr': 0.0004914296447323875, 'samples': 2759424, 'steps': 14371, 'loss/train': 1.6695152521133423} 08/30/2021 15:42:00 - INFO - __main__ - Step 14373: {'lr': 0.0004914282670935025, 'samples': 2759616, 'steps': 14372, 'loss/train': 1.9530751705169678} 08/30/2021 15:42:00 - INFO - __main__ - Step 14374: {'lr': 0.0004914268893458336, 'samples': 2759808, 'steps': 14373, 'loss/train': 1.5470737218856812} 08/30/2021 15:42:00 - INFO - __main__ - Step 14375: {'lr': 0.0004914255114893814, 'samples': 2760000, 'steps': 14374, 'loss/train': 1.6123696565628052} 08/30/2021 15:42:02 - INFO - __main__ - Step 14376: {'lr': 0.0004914241335241467, 'samples': 2760192, 'steps': 14375, 'loss/train': 1.5364497900009155} 08/30/2021 15:42:02 - INFO - __main__ - Step 14377: {'lr': 0.0004914227554501299, 'samples': 2760384, 'steps': 14376, 'loss/train': 1.3919613361358643} 08/30/2021 15:42:03 - INFO - __main__ - Step 14378: {'lr': 0.0004914213772673319, 'samples': 2760576, 'steps': 14377, 'loss/train': 1.6869041919708252} 08/30/2021 15:42:03 - INFO - __main__ - Step 14379: {'lr': 0.0004914199989757529, 'samples': 2760768, 'steps': 14378, 'loss/train': 1.5844998359680176} 08/30/2021 15:42:04 - INFO - __main__ - Step 14380: {'lr': 0.000491418620575394, 'samples': 2760960, 'steps': 14379, 'loss/train': 1.8117092847824097} 08/30/2021 15:42:04 - INFO - __main__ - Step 14381: {'lr': 0.0004914172420662556, 'samples': 2761152, 'steps': 14380, 'loss/train': 1.4020788669586182} 08/30/2021 15:42:06 - INFO - __main__ - Step 14382: {'lr': 0.0004914158634483381, 'samples': 2761344, 'steps': 14381, 'loss/train': 6.557975769042969} 08/30/2021 15:42:07 - INFO - __main__ - Step 14383: {'lr': 0.0004914144847216425, 'samples': 2761536, 'steps': 14382, 'loss/train': 1.495499849319458} 08/30/2021 15:42:07 - INFO - __main__ - Step 14384: {'lr': 0.0004914131058861693, 'samples': 2761728, 'steps': 14383, 'loss/train': 1.9853951930999756} 08/30/2021 15:42:07 - INFO - __main__ - Step 14385: {'lr': 0.000491411726941919, 'samples': 2761920, 'steps': 14384, 'loss/train': 1.6249979734420776} 08/30/2021 15:42:08 - INFO - __main__ - Step 14386: {'lr': 0.0004914103478888922, 'samples': 2762112, 'steps': 14385, 'loss/train': 1.6414304971694946} 08/30/2021 15:42:09 - INFO - __main__ - Step 14387: {'lr': 0.0004914089687270898, 'samples': 2762304, 'steps': 14386, 'loss/train': 1.6743136644363403} 08/30/2021 15:42:10 - INFO - __main__ - Step 14388: {'lr': 0.0004914075894565122, 'samples': 2762496, 'steps': 14387, 'loss/train': 2.039595603942871} 08/30/2021 15:42:10 - INFO - __main__ - Step 14389: {'lr': 0.00049140621007716, 'samples': 2762688, 'steps': 14388, 'loss/train': 0.9971103072166443} 08/30/2021 15:42:10 - INFO - __main__ - Step 14390: {'lr': 0.0004914048305890339, 'samples': 2762880, 'steps': 14389, 'loss/train': 0.6940599679946899} 08/30/2021 15:42:11 - INFO - __main__ - Step 14391: {'lr': 0.0004914034509921345, 'samples': 2763072, 'steps': 14390, 'loss/train': 1.2802982330322266} 08/30/2021 15:42:12 - INFO - __main__ - Step 14392: {'lr': 0.0004914020712864626, 'samples': 2763264, 'steps': 14391, 'loss/train': 1.6955795288085938} 08/30/2021 15:42:12 - INFO - __main__ - Step 14393: {'lr': 0.0004914006914720184, 'samples': 2763456, 'steps': 14392, 'loss/train': 1.7631808519363403} 08/30/2021 15:42:13 - INFO - __main__ - Step 14394: {'lr': 0.0004913993115488029, 'samples': 2763648, 'steps': 14393, 'loss/train': 1.2318246364593506} 08/30/2021 15:42:13 - INFO - __main__ - Step 14395: {'lr': 0.0004913979315168167, 'samples': 2763840, 'steps': 14394, 'loss/train': 1.6404566764831543} 08/30/2021 15:42:13 - INFO - __main__ - Step 14396: {'lr': 0.0004913965513760601, 'samples': 2764032, 'steps': 14395, 'loss/train': 1.5663487911224365} 08/30/2021 15:42:15 - INFO - __main__ - Step 14397: {'lr': 0.0004913951711265341, 'samples': 2764224, 'steps': 14396, 'loss/train': 1.854474425315857} 08/30/2021 15:42:15 - INFO - __main__ - Step 14398: {'lr': 0.0004913937907682391, 'samples': 2764416, 'steps': 14397, 'loss/train': 2.02028751373291} 08/30/2021 15:42:16 - INFO - __main__ - Step 14399: {'lr': 0.0004913924103011757, 'samples': 2764608, 'steps': 14398, 'loss/train': 1.9994747638702393} 08/30/2021 15:42:16 - INFO - __main__ - Step 14400: {'lr': 0.0004913910297253448, 'samples': 2764800, 'steps': 14399, 'loss/train': 2.0656163692474365} 08/30/2021 15:42:16 - INFO - __main__ - Step 14401: {'lr': 0.0004913896490407467, 'samples': 2764992, 'steps': 14400, 'loss/train': 2.1407995223999023} 08/30/2021 15:42:18 - INFO - __main__ - Step 14402: {'lr': 0.0004913882682473821, 'samples': 2765184, 'steps': 14401, 'loss/train': 1.5955979824066162} 08/30/2021 15:42:18 - INFO - __main__ - Step 14403: {'lr': 0.0004913868873452519, 'samples': 2765376, 'steps': 14402, 'loss/train': 1.9759739637374878} 08/30/2021 15:42:19 - INFO - __main__ - Step 14404: {'lr': 0.0004913855063343563, 'samples': 2765568, 'steps': 14403, 'loss/train': 1.3353103399276733} 08/30/2021 15:42:19 - INFO - __main__ - Step 14405: {'lr': 0.0004913841252146961, 'samples': 2765760, 'steps': 14404, 'loss/train': 1.6983386278152466} 08/30/2021 15:42:20 - INFO - __main__ - Step 14406: {'lr': 0.000491382743986272, 'samples': 2765952, 'steps': 14405, 'loss/train': 1.600548505783081} 08/30/2021 15:42:20 - INFO - __main__ - Step 14407: {'lr': 0.0004913813626490845, 'samples': 2766144, 'steps': 14406, 'loss/train': 1.7812741994857788} 08/30/2021 15:42:21 - INFO - __main__ - Step 14408: {'lr': 0.0004913799812031343, 'samples': 2766336, 'steps': 14407, 'loss/train': 1.9552769660949707} 08/30/2021 15:42:22 - INFO - __main__ - Step 14409: {'lr': 0.0004913785996484221, 'samples': 2766528, 'steps': 14408, 'loss/train': 1.6603641510009766} 08/30/2021 15:42:22 - INFO - __main__ - Step 14410: {'lr': 0.0004913772179849483, 'samples': 2766720, 'steps': 14409, 'loss/train': 1.7005271911621094} 08/30/2021 15:42:22 - INFO - __main__ - Step 14411: {'lr': 0.0004913758362127137, 'samples': 2766912, 'steps': 14410, 'loss/train': 2.074171543121338} 08/30/2021 15:42:23 - INFO - __main__ - Step 14412: {'lr': 0.0004913744543317189, 'samples': 2767104, 'steps': 14411, 'loss/train': 1.8987823724746704} 08/30/2021 15:42:24 - INFO - __main__ - Step 14413: {'lr': 0.0004913730723419645, 'samples': 2767296, 'steps': 14412, 'loss/train': 1.542839527130127} 08/30/2021 15:42:25 - INFO - __main__ - Step 14414: {'lr': 0.000491371690243451, 'samples': 2767488, 'steps': 14413, 'loss/train': 1.8802578449249268} 08/30/2021 15:42:25 - INFO - __main__ - Step 14415: {'lr': 0.0004913703080361793, 'samples': 2767680, 'steps': 14414, 'loss/train': 1.681760549545288} 08/30/2021 15:42:25 - INFO - __main__ - Step 14416: {'lr': 0.0004913689257201499, 'samples': 2767872, 'steps': 14415, 'loss/train': 1.4980852603912354} 08/30/2021 15:42:26 - INFO - __main__ - Step 14417: {'lr': 0.0004913675432953633, 'samples': 2768064, 'steps': 14416, 'loss/train': 1.130185604095459} 08/30/2021 15:42:26 - INFO - __main__ - Step 14418: {'lr': 0.0004913661607618202, 'samples': 2768256, 'steps': 14417, 'loss/train': 1.6542071104049683} 08/30/2021 15:42:28 - INFO - __main__ - Step 14419: {'lr': 0.0004913647781195212, 'samples': 2768448, 'steps': 14418, 'loss/train': 1.6528840065002441} 08/30/2021 15:42:28 - INFO - __main__ - Step 14420: {'lr': 0.000491363395368467, 'samples': 2768640, 'steps': 14419, 'loss/train': 1.2821459770202637} 08/30/2021 15:42:29 - INFO - __main__ - Step 14421: {'lr': 0.0004913620125086581, 'samples': 2768832, 'steps': 14420, 'loss/train': 2.111851453781128} 08/30/2021 15:42:29 - INFO - __main__ - Step 14422: {'lr': 0.0004913606295400953, 'samples': 2769024, 'steps': 14421, 'loss/train': 2.1326797008514404} 08/30/2021 15:42:29 - INFO - __main__ - Step 14423: {'lr': 0.000491359246462779, 'samples': 2769216, 'steps': 14422, 'loss/train': 2.0644469261169434} 08/30/2021 15:42:31 - INFO - __main__ - Step 14424: {'lr': 0.0004913578632767101, 'samples': 2769408, 'steps': 14423, 'loss/train': 1.1016974449157715} 08/30/2021 15:42:31 - INFO - __main__ - Step 14425: {'lr': 0.0004913564799818891, 'samples': 2769600, 'steps': 14424, 'loss/train': 1.6002943515777588} 08/30/2021 15:42:32 - INFO - __main__ - Step 14426: {'lr': 0.0004913550965783165, 'samples': 2769792, 'steps': 14425, 'loss/train': 1.3188844919204712} 08/30/2021 15:42:32 - INFO - __main__ - Step 14427: {'lr': 0.000491353713065993, 'samples': 2769984, 'steps': 14426, 'loss/train': 1.687347412109375} 08/30/2021 15:42:32 - INFO - __main__ - Step 14428: {'lr': 0.0004913523294449193, 'samples': 2770176, 'steps': 14427, 'loss/train': 1.5591503381729126} 08/30/2021 15:42:34 - INFO - __main__ - Step 14429: {'lr': 0.0004913509457150959, 'samples': 2770368, 'steps': 14428, 'loss/train': 1.6258282661437988} 08/30/2021 15:42:35 - INFO - __main__ - Step 14430: {'lr': 0.0004913495618765235, 'samples': 2770560, 'steps': 14429, 'loss/train': 1.6587992906570435} 08/30/2021 15:42:35 - INFO - __main__ - Step 14431: {'lr': 0.0004913481779292027, 'samples': 2770752, 'steps': 14430, 'loss/train': 1.442101240158081} 08/30/2021 15:42:35 - INFO - __main__ - Step 14432: {'lr': 0.0004913467938731341, 'samples': 2770944, 'steps': 14431, 'loss/train': 1.6395477056503296} 08/30/2021 15:42:36 - INFO - __main__ - Step 14433: {'lr': 0.0004913454097083185, 'samples': 2771136, 'steps': 14432, 'loss/train': 1.3623318672180176} 08/30/2021 15:42:36 - INFO - __main__ - Step 14434: {'lr': 0.0004913440254347563, 'samples': 2771328, 'steps': 14433, 'loss/train': 1.7937641143798828} 08/30/2021 15:42:38 - INFO - __main__ - Step 14435: {'lr': 0.0004913426410524482, 'samples': 2771520, 'steps': 14434, 'loss/train': 0.3770926594734192} 08/30/2021 15:42:38 - INFO - __main__ - Step 14436: {'lr': 0.0004913412565613948, 'samples': 2771712, 'steps': 14435, 'loss/train': 1.848724126815796} 08/30/2021 15:42:39 - INFO - __main__ - Step 14437: {'lr': 0.0004913398719615968, 'samples': 2771904, 'steps': 14436, 'loss/train': 1.6998211145401} 08/30/2021 15:42:39 - INFO - __main__ - Step 14438: {'lr': 0.0004913384872530548, 'samples': 2772096, 'steps': 14437, 'loss/train': 1.955406665802002} 08/30/2021 15:42:39 - INFO - __main__ - Step 14439: {'lr': 0.0004913371024357694, 'samples': 2772288, 'steps': 14438, 'loss/train': 2.1819000244140625} 08/30/2021 15:42:41 - INFO - __main__ - Step 14440: {'lr': 0.0004913357175097412, 'samples': 2772480, 'steps': 14439, 'loss/train': 1.3407856225967407} 08/30/2021 15:42:41 - INFO - __main__ - Step 14441: {'lr': 0.0004913343324749708, 'samples': 2772672, 'steps': 14440, 'loss/train': 2.3821146488189697} 08/30/2021 15:42:42 - INFO - __main__ - Step 14442: {'lr': 0.000491332947331459, 'samples': 2772864, 'steps': 14441, 'loss/train': 2.2518422603607178} 08/30/2021 15:42:42 - INFO - __main__ - Step 14443: {'lr': 0.0004913315620792061, 'samples': 2773056, 'steps': 14442, 'loss/train': 1.3385586738586426} 08/30/2021 15:42:42 - INFO - __main__ - Step 14444: {'lr': 0.0004913301767182131, 'samples': 2773248, 'steps': 14443, 'loss/train': 1.8875072002410889} 08/30/2021 15:42:44 - INFO - __main__ - Step 14445: {'lr': 0.0004913287912484804, 'samples': 2773440, 'steps': 14444, 'loss/train': 1.8578765392303467} 08/30/2021 15:42:45 - INFO - __main__ - Step 14446: {'lr': 0.0004913274056700087, 'samples': 2773632, 'steps': 14445, 'loss/train': 1.2141847610473633} 08/30/2021 15:42:45 - INFO - __main__ - Step 14447: {'lr': 0.0004913260199827986, 'samples': 2773824, 'steps': 14446, 'loss/train': 1.3405717611312866} 08/30/2021 15:42:46 - INFO - __main__ - Step 14448: {'lr': 0.0004913246341868506, 'samples': 2774016, 'steps': 14447, 'loss/train': 1.4121546745300293} 08/30/2021 15:42:46 - INFO - __main__ - Step 14449: {'lr': 0.0004913232482821656, 'samples': 2774208, 'steps': 14448, 'loss/train': 1.3116148710250854} 08/30/2021 15:42:46 - INFO - __main__ - Step 14450: {'lr': 0.0004913218622687439, 'samples': 2774400, 'steps': 14449, 'loss/train': 3.291533946990967} 08/30/2021 15:42:47 - INFO - __main__ - Step 14451: {'lr': 0.0004913204761465864, 'samples': 2774592, 'steps': 14450, 'loss/train': 0.10549765825271606} 08/30/2021 15:42:48 - INFO - __main__ - Step 14452: {'lr': 0.0004913190899156936, 'samples': 2774784, 'steps': 14451, 'loss/train': 1.6932841539382935} 08/30/2021 15:42:49 - INFO - __main__ - Step 14453: {'lr': 0.0004913177035760661, 'samples': 2774976, 'steps': 14452, 'loss/train': 2.2363641262054443} 08/30/2021 15:42:49 - INFO - __main__ - Step 14454: {'lr': 0.0004913163171277046, 'samples': 2775168, 'steps': 14453, 'loss/train': 1.5592412948608398} 08/30/2021 15:42:49 - INFO - __main__ - Step 14455: {'lr': 0.0004913149305706097, 'samples': 2775360, 'steps': 14454, 'loss/train': 1.3753920793533325} 08/30/2021 15:42:50 - INFO - __main__ - Step 14456: {'lr': 0.0004913135439047821, 'samples': 2775552, 'steps': 14455, 'loss/train': 1.8267714977264404} 08/30/2021 15:42:51 - INFO - __main__ - Step 14457: {'lr': 0.0004913121571302222, 'samples': 2775744, 'steps': 14456, 'loss/train': 2.6834311485290527} 08/30/2021 15:42:52 - INFO - __main__ - Step 14458: {'lr': 0.0004913107702469308, 'samples': 2775936, 'steps': 14457, 'loss/train': 2.420761823654175} 08/30/2021 15:42:52 - INFO - __main__ - Step 14459: {'lr': 0.0004913093832549085, 'samples': 2776128, 'steps': 14458, 'loss/train': 2.002096652984619} 08/30/2021 15:42:52 - INFO - __main__ - Step 14460: {'lr': 0.000491307996154156, 'samples': 2776320, 'steps': 14459, 'loss/train': 1.5985876321792603} 08/30/2021 15:42:53 - INFO - __main__ - Step 14461: {'lr': 0.0004913066089446737, 'samples': 2776512, 'steps': 14460, 'loss/train': 1.7746468782424927} 08/30/2021 15:42:54 - INFO - __main__ - Step 14462: {'lr': 0.0004913052216264624, 'samples': 2776704, 'steps': 14461, 'loss/train': 1.565679907798767} 08/30/2021 15:42:55 - INFO - __main__ - Step 14463: {'lr': 0.0004913038341995227, 'samples': 2776896, 'steps': 14462, 'loss/train': 1.2869205474853516} 08/30/2021 15:42:55 - INFO - __main__ - Step 14464: {'lr': 0.0004913024466638553, 'samples': 2777088, 'steps': 14463, 'loss/train': 1.9432456493377686} 08/30/2021 15:42:56 - INFO - __main__ - Step 14465: {'lr': 0.0004913010590194607, 'samples': 2777280, 'steps': 14464, 'loss/train': 1.7373874187469482} 08/30/2021 15:42:56 - INFO - __main__ - Step 14466: {'lr': 0.0004912996712663396, 'samples': 2777472, 'steps': 14465, 'loss/train': 0.2349952906370163} 08/30/2021 15:42:58 - INFO - __main__ - Step 14467: {'lr': 0.0004912982834044924, 'samples': 2777664, 'steps': 14466, 'loss/train': 1.9728477001190186} 08/30/2021 15:42:58 - INFO - __main__ - Step 14468: {'lr': 0.0004912968954339202, 'samples': 2777856, 'steps': 14467, 'loss/train': 1.616193413734436} 08/30/2021 15:42:58 - INFO - __main__ - Step 14469: {'lr': 0.0004912955073546231, 'samples': 2778048, 'steps': 14468, 'loss/train': 1.854647159576416} 08/30/2021 15:42:59 - INFO - __main__ - Step 14470: {'lr': 0.0004912941191666021, 'samples': 2778240, 'steps': 14469, 'loss/train': 1.7872931957244873} 08/30/2021 15:42:59 - INFO - __main__ - Step 14471: {'lr': 0.0004912927308698576, 'samples': 2778432, 'steps': 14470, 'loss/train': 1.5087742805480957} 08/30/2021 15:42:59 - INFO - __main__ - Step 14472: {'lr': 0.0004912913424643904, 'samples': 2778624, 'steps': 14471, 'loss/train': 2.019666910171509} 08/30/2021 15:43:01 - INFO - __main__ - Step 14473: {'lr': 0.0004912899539502011, 'samples': 2778816, 'steps': 14472, 'loss/train': 1.479892373085022} 08/30/2021 15:43:01 - INFO - __main__ - Step 14474: {'lr': 0.0004912885653272902, 'samples': 2779008, 'steps': 14473, 'loss/train': 2.0292649269104004} 08/30/2021 15:43:02 - INFO - __main__ - Step 14475: {'lr': 0.0004912871765956583, 'samples': 2779200, 'steps': 14474, 'loss/train': 1.6204290390014648} 08/30/2021 15:43:02 - INFO - __main__ - Step 14476: {'lr': 0.0004912857877553062, 'samples': 2779392, 'steps': 14475, 'loss/train': 1.3374171257019043} 08/30/2021 15:43:02 - INFO - __main__ - Step 14477: {'lr': 0.0004912843988062345, 'samples': 2779584, 'steps': 14476, 'loss/train': 1.354299545288086} 08/30/2021 15:43:04 - INFO - __main__ - Step 14478: {'lr': 0.0004912830097484437, 'samples': 2779776, 'steps': 14477, 'loss/train': 1.3030502796173096} 08/30/2021 15:43:05 - INFO - __main__ - Step 14479: {'lr': 0.0004912816205819346, 'samples': 2779968, 'steps': 14478, 'loss/train': 1.8572869300842285} 08/30/2021 15:43:05 - INFO - __main__ - Step 14480: {'lr': 0.0004912802313067076, 'samples': 2780160, 'steps': 14479, 'loss/train': 1.7414358854293823} 08/30/2021 15:43:05 - INFO - __main__ - Step 14481: {'lr': 0.0004912788419227635, 'samples': 2780352, 'steps': 14480, 'loss/train': 0.28012627363204956} 08/30/2021 15:43:06 - INFO - __main__ - Step 14482: {'lr': 0.000491277452430103, 'samples': 2780544, 'steps': 14481, 'loss/train': 1.5621333122253418} 08/30/2021 15:43:07 - INFO - __main__ - Step 14483: {'lr': 0.0004912760628287264, 'samples': 2780736, 'steps': 14482, 'loss/train': 1.1264241933822632} 08/30/2021 15:43:08 - INFO - __main__ - Step 14484: {'lr': 0.0004912746731186346, 'samples': 2780928, 'steps': 14483, 'loss/train': 1.716565489768982} 08/30/2021 15:43:08 - INFO - __main__ - Step 14485: {'lr': 0.0004912732832998281, 'samples': 2781120, 'steps': 14484, 'loss/train': 1.7526382207870483} 08/30/2021 15:43:08 - INFO - __main__ - Step 14486: {'lr': 0.0004912718933723077, 'samples': 2781312, 'steps': 14485, 'loss/train': 1.299196481704712} 08/30/2021 15:43:09 - INFO - __main__ - Step 14487: {'lr': 0.0004912705033360738, 'samples': 2781504, 'steps': 14486, 'loss/train': 2.215812921524048} 08/30/2021 15:43:11 - INFO - __main__ - Step 14488: {'lr': 0.0004912691131911272, 'samples': 2781696, 'steps': 14487, 'loss/train': 2.1676204204559326} 08/30/2021 15:43:11 - INFO - __main__ - Step 14489: {'lr': 0.0004912677229374684, 'samples': 2781888, 'steps': 14488, 'loss/train': 2.0206358432769775} 08/30/2021 15:43:12 - INFO - __main__ - Step 14490: {'lr': 0.0004912663325750982, 'samples': 2782080, 'steps': 14489, 'loss/train': 1.6100986003875732} 08/30/2021 15:43:12 - INFO - __main__ - Step 14491: {'lr': 0.000491264942104017, 'samples': 2782272, 'steps': 14490, 'loss/train': 1.6361287832260132} 08/30/2021 15:43:12 - INFO - __main__ - Step 14492: {'lr': 0.0004912635515242257, 'samples': 2782464, 'steps': 14491, 'loss/train': 1.7629488706588745} 08/30/2021 15:43:13 - INFO - __main__ - Step 14493: {'lr': 0.0004912621608357246, 'samples': 2782656, 'steps': 14492, 'loss/train': 1.7426536083221436} 08/30/2021 15:43:14 - INFO - __main__ - Step 14494: {'lr': 0.0004912607700385146, 'samples': 2782848, 'steps': 14493, 'loss/train': 2.1075809001922607} 08/30/2021 15:43:15 - INFO - __main__ - Step 14495: {'lr': 0.0004912593791325962, 'samples': 2783040, 'steps': 14494, 'loss/train': 1.903563141822815} 08/30/2021 15:43:15 - INFO - __main__ - Step 14496: {'lr': 0.00049125798811797, 'samples': 2783232, 'steps': 14495, 'loss/train': 1.6912320852279663} 08/30/2021 15:43:15 - INFO - __main__ - Step 14497: {'lr': 0.0004912565969946367, 'samples': 2783424, 'steps': 14496, 'loss/train': 1.7569342851638794} 08/30/2021 15:43:16 - INFO - __main__ - Step 14498: {'lr': 0.0004912552057625969, 'samples': 2783616, 'steps': 14497, 'loss/train': 1.7169954776763916} 08/30/2021 15:43:17 - INFO - __main__ - Step 14499: {'lr': 0.0004912538144218512, 'samples': 2783808, 'steps': 14498, 'loss/train': 1.592843770980835} 08/30/2021 15:43:18 - INFO - __main__ - Step 14500: {'lr': 0.0004912524229724002, 'samples': 2784000, 'steps': 14499, 'loss/train': 1.4646787643432617} 08/30/2021 15:43:18 - INFO - __main__ - Step 14501: {'lr': 0.0004912510314142447, 'samples': 2784192, 'steps': 14500, 'loss/train': 1.7538471221923828} 08/30/2021 15:43:18 - INFO - __main__ - Step 14502: {'lr': 0.0004912496397473852, 'samples': 2784384, 'steps': 14501, 'loss/train': 2.0602452754974365} 08/30/2021 15:43:19 - INFO - __main__ - Step 14503: {'lr': 0.0004912482479718223, 'samples': 2784576, 'steps': 14502, 'loss/train': 1.6451038122177124} 08/30/2021 15:43:20 - INFO - __main__ - Step 14504: {'lr': 0.0004912468560875566, 'samples': 2784768, 'steps': 14503, 'loss/train': 1.4356677532196045} 08/30/2021 15:43:21 - INFO - __main__ - Step 14505: {'lr': 0.0004912454640945889, 'samples': 2784960, 'steps': 14504, 'loss/train': 2.1461522579193115} 08/30/2021 15:43:21 - INFO - __main__ - Step 14506: {'lr': 0.0004912440719929196, 'samples': 2785152, 'steps': 14505, 'loss/train': 1.3326867818832397} 08/30/2021 15:43:21 - INFO - __main__ - Step 14507: {'lr': 0.0004912426797825495, 'samples': 2785344, 'steps': 14506, 'loss/train': 1.4029852151870728} 08/30/2021 15:43:22 - INFO - __main__ - Step 14508: {'lr': 0.0004912412874634792, 'samples': 2785536, 'steps': 14507, 'loss/train': 2.0477237701416016} 08/30/2021 15:43:23 - INFO - __main__ - Step 14509: {'lr': 0.0004912398950357094, 'samples': 2785728, 'steps': 14508, 'loss/train': 1.2198266983032227} 08/30/2021 15:43:24 - INFO - __main__ - Step 14510: {'lr': 0.0004912385024992404, 'samples': 2785920, 'steps': 14509, 'loss/train': 2.0874016284942627} 08/30/2021 15:43:24 - INFO - __main__ - Step 14511: {'lr': 0.0004912371098540733, 'samples': 2786112, 'steps': 14510, 'loss/train': 5.1942620277404785} 08/30/2021 15:43:25 - INFO - __main__ - Step 14512: {'lr': 0.0004912357171002082, 'samples': 2786304, 'steps': 14511, 'loss/train': 3.4363343715667725} 08/30/2021 15:43:25 - INFO - __main__ - Step 14513: {'lr': 0.0004912343242376462, 'samples': 2786496, 'steps': 14512, 'loss/train': 2.5290675163269043} 08/30/2021 15:43:25 - INFO - __main__ - Step 14514: {'lr': 0.0004912329312663877, 'samples': 2786688, 'steps': 14513, 'loss/train': 2.168471574783325} 08/30/2021 15:43:27 - INFO - __main__ - Step 14515: {'lr': 0.0004912315381864333, 'samples': 2786880, 'steps': 14514, 'loss/train': 1.8507919311523438} 08/30/2021 15:43:27 - INFO - __main__ - Step 14516: {'lr': 0.0004912301449977837, 'samples': 2787072, 'steps': 14515, 'loss/train': 1.9655901193618774} 08/30/2021 15:43:28 - INFO - __main__ - Step 14517: {'lr': 0.0004912287517004397, 'samples': 2787264, 'steps': 14516, 'loss/train': 1.8701720237731934} 08/30/2021 15:43:28 - INFO - __main__ - Step 14518: {'lr': 0.0004912273582944015, 'samples': 2787456, 'steps': 14517, 'loss/train': 1.980516791343689} 08/30/2021 15:43:28 - INFO - __main__ - Step 14519: {'lr': 0.0004912259647796701, 'samples': 2787648, 'steps': 14518, 'loss/train': 1.4434527158737183} 08/30/2021 15:43:29 - INFO - __main__ - Step 14520: {'lr': 0.000491224571156246, 'samples': 2787840, 'steps': 14519, 'loss/train': 1.8004525899887085} 08/30/2021 15:43:30 - INFO - __main__ - Step 14521: {'lr': 0.0004912231774241298, 'samples': 2788032, 'steps': 14520, 'loss/train': 1.748858094215393} 08/30/2021 15:43:31 - INFO - __main__ - Step 14522: {'lr': 0.0004912217835833222, 'samples': 2788224, 'steps': 14521, 'loss/train': 1.8290034532546997} 08/30/2021 15:43:31 - INFO - __main__ - Step 14523: {'lr': 0.0004912203896338238, 'samples': 2788416, 'steps': 14522, 'loss/train': 1.771354079246521} 08/30/2021 15:43:31 - INFO - __main__ - Step 14524: {'lr': 0.0004912189955756351, 'samples': 2788608, 'steps': 14523, 'loss/train': 2.1499438285827637} 08/30/2021 15:43:32 - INFO - __main__ - Step 14525: {'lr': 0.000491217601408757, 'samples': 2788800, 'steps': 14524, 'loss/train': 1.9782694578170776} 08/30/2021 15:43:33 - INFO - __main__ - Step 14526: {'lr': 0.0004912162071331898, 'samples': 2788992, 'steps': 14525, 'loss/train': 1.9178650379180908} 08/30/2021 15:43:34 - INFO - __main__ - Step 14527: {'lr': 0.0004912148127489345, 'samples': 2789184, 'steps': 14526, 'loss/train': 1.8704619407653809} 08/30/2021 15:43:34 - INFO - __main__ - Step 14528: {'lr': 0.0004912134182559913, 'samples': 2789376, 'steps': 14527, 'loss/train': 1.8732547760009766} 08/30/2021 15:43:34 - INFO - __main__ - Step 14529: {'lr': 0.0004912120236543611, 'samples': 2789568, 'steps': 14528, 'loss/train': 1.8324247598648071} 08/30/2021 15:43:35 - INFO - __main__ - Step 14530: {'lr': 0.0004912106289440446, 'samples': 2789760, 'steps': 14529, 'loss/train': 1.3917843103408813} 08/30/2021 15:43:36 - INFO - __main__ - Step 14531: {'lr': 0.0004912092341250422, 'samples': 2789952, 'steps': 14530, 'loss/train': 2.2684664726257324} 08/30/2021 15:43:37 - INFO - __main__ - Step 14532: {'lr': 0.0004912078391973547, 'samples': 2790144, 'steps': 14531, 'loss/train': 1.54881751537323} 08/30/2021 15:43:37 - INFO - __main__ - Step 14533: {'lr': 0.0004912064441609827, 'samples': 2790336, 'steps': 14532, 'loss/train': 1.2664347887039185} 08/30/2021 15:43:37 - INFO - __main__ - Step 14534: {'lr': 0.0004912050490159268, 'samples': 2790528, 'steps': 14533, 'loss/train': 1.573196530342102} 08/30/2021 15:43:38 - INFO - __main__ - Step 14535: {'lr': 0.0004912036537621877, 'samples': 2790720, 'steps': 14534, 'loss/train': 1.3205132484436035} 08/30/2021 15:43:38 - INFO - __main__ - Step 14536: {'lr': 0.0004912022583997658, 'samples': 2790912, 'steps': 14535, 'loss/train': 2.139380931854248} 08/30/2021 15:43:40 - INFO - __main__ - Step 14537: {'lr': 0.0004912008629286619, 'samples': 2791104, 'steps': 14536, 'loss/train': 0.3022192716598511} 08/30/2021 15:43:40 - INFO - __main__ - Step 14538: {'lr': 0.0004911994673488766, 'samples': 2791296, 'steps': 14537, 'loss/train': 1.9566104412078857} 08/30/2021 15:43:40 - INFO - __main__ - Step 14539: {'lr': 0.0004911980716604107, 'samples': 2791488, 'steps': 14538, 'loss/train': 1.9875560998916626} 08/30/2021 15:43:41 - INFO - __main__ - Step 14540: {'lr': 0.0004911966758632645, 'samples': 2791680, 'steps': 14539, 'loss/train': 1.564862847328186} 08/30/2021 15:43:41 - INFO - __main__ - Step 14541: {'lr': 0.000491195279957439, 'samples': 2791872, 'steps': 14540, 'loss/train': 1.498392939567566} 08/30/2021 15:43:44 - INFO - __main__ - Step 14542: {'lr': 0.0004911938839429344, 'samples': 2792064, 'steps': 14541, 'loss/train': 1.539810061454773} 08/30/2021 15:43:45 - INFO - __main__ - Step 14543: {'lr': 0.0004911924878197517, 'samples': 2792256, 'steps': 14542, 'loss/train': 2.13578200340271} 08/30/2021 15:43:45 - INFO - __main__ - Step 14544: {'lr': 0.0004911910915878913, 'samples': 2792448, 'steps': 14543, 'loss/train': 1.6552116870880127} 08/30/2021 15:43:45 - INFO - __main__ - Step 14545: {'lr': 0.000491189695247354, 'samples': 2792640, 'steps': 14544, 'loss/train': 1.9474873542785645} 08/30/2021 15:43:46 - INFO - __main__ - Step 14546: {'lr': 0.0004911882987981404, 'samples': 2792832, 'steps': 14545, 'loss/train': 1.9455745220184326} 08/30/2021 15:43:46 - INFO - __main__ - Step 14547: {'lr': 0.0004911869022402508, 'samples': 2793024, 'steps': 14546, 'loss/train': 2.396836757659912} 08/30/2021 15:43:47 - INFO - __main__ - Step 14548: {'lr': 0.0004911855055736863, 'samples': 2793216, 'steps': 14547, 'loss/train': 0.6741005182266235} 08/30/2021 15:43:47 - INFO - __main__ - Step 14549: {'lr': 0.0004911841087984473, 'samples': 2793408, 'steps': 14548, 'loss/train': 0.5657904744148254} 08/30/2021 15:43:48 - INFO - __main__ - Step 14550: {'lr': 0.0004911827119145345, 'samples': 2793600, 'steps': 14549, 'loss/train': 0.5266324281692505} 08/30/2021 15:43:49 - INFO - __main__ - Step 14551: {'lr': 0.0004911813149219485, 'samples': 2793792, 'steps': 14550, 'loss/train': 2.2867889404296875} 08/30/2021 15:43:49 - INFO - __main__ - Step 14552: {'lr': 0.0004911799178206899, 'samples': 2793984, 'steps': 14551, 'loss/train': 1.652372121810913} 08/30/2021 15:43:50 - INFO - __main__ - Step 14553: {'lr': 0.0004911785206107592, 'samples': 2794176, 'steps': 14552, 'loss/train': 1.2229183912277222} 08/30/2021 15:43:50 - INFO - __main__ - Step 14554: {'lr': 0.0004911771232921575, 'samples': 2794368, 'steps': 14553, 'loss/train': 1.9569799900054932} 08/30/2021 15:43:52 - INFO - __main__ - Step 14555: {'lr': 0.0004911757258648849, 'samples': 2794560, 'steps': 14554, 'loss/train': 1.7661128044128418} 08/30/2021 15:43:52 - INFO - __main__ - Step 14556: {'lr': 0.0004911743283289423, 'samples': 2794752, 'steps': 14555, 'loss/train': 1.9324421882629395} 08/30/2021 15:43:52 - INFO - __main__ - Step 14557: {'lr': 0.0004911729306843302, 'samples': 2794944, 'steps': 14556, 'loss/train': 1.7198010683059692} 08/30/2021 15:43:53 - INFO - __main__ - Step 14558: {'lr': 0.0004911715329310493, 'samples': 2795136, 'steps': 14557, 'loss/train': 2.081277847290039} 08/30/2021 15:43:53 - INFO - __main__ - Step 14559: {'lr': 0.0004911701350691002, 'samples': 2795328, 'steps': 14558, 'loss/train': 1.5989199876785278} 08/30/2021 15:43:55 - INFO - __main__ - Step 14560: {'lr': 0.0004911687370984836, 'samples': 2795520, 'steps': 14559, 'loss/train': 1.6618127822875977} 08/30/2021 15:43:55 - INFO - __main__ - Step 14561: {'lr': 0.0004911673390192002, 'samples': 2795712, 'steps': 14560, 'loss/train': 1.6317024230957031} 08/30/2021 15:43:55 - INFO - __main__ - Step 14562: {'lr': 0.0004911659408312505, 'samples': 2795904, 'steps': 14561, 'loss/train': 1.6831574440002441} 08/30/2021 15:43:56 - INFO - __main__ - Step 14563: {'lr': 0.000491164542534635, 'samples': 2796096, 'steps': 14562, 'loss/train': 1.9227943420410156} 08/30/2021 15:43:56 - INFO - __main__ - Step 14564: {'lr': 0.0004911631441293546, 'samples': 2796288, 'steps': 14563, 'loss/train': 1.221450686454773} 08/30/2021 15:43:57 - INFO - __main__ - Step 14565: {'lr': 0.0004911617456154097, 'samples': 2796480, 'steps': 14564, 'loss/train': 1.5972568988800049} 08/30/2021 15:43:58 - INFO - __main__ - Step 14566: {'lr': 0.0004911603469928012, 'samples': 2796672, 'steps': 14565, 'loss/train': 1.9297749996185303} 08/30/2021 15:43:59 - INFO - __main__ - Step 14567: {'lr': 0.0004911589482615294, 'samples': 2796864, 'steps': 14566, 'loss/train': 0.8215628862380981} 08/30/2021 15:43:59 - INFO - __main__ - Step 14568: {'lr': 0.0004911575494215952, 'samples': 2797056, 'steps': 14567, 'loss/train': 2.0217251777648926} 08/30/2021 15:43:59 - INFO - __main__ - Step 14569: {'lr': 0.0004911561504729992, 'samples': 2797248, 'steps': 14568, 'loss/train': 1.7546579837799072} 08/30/2021 15:44:00 - INFO - __main__ - Step 14570: {'lr': 0.0004911547514157417, 'samples': 2797440, 'steps': 14569, 'loss/train': 1.7044743299484253} 08/30/2021 15:44:01 - INFO - __main__ - Step 14571: {'lr': 0.0004911533522498239, 'samples': 2797632, 'steps': 14570, 'loss/train': 2.543809652328491} 08/30/2021 15:44:02 - INFO - __main__ - Step 14572: {'lr': 0.0004911519529752459, 'samples': 2797824, 'steps': 14571, 'loss/train': 2.1772594451904297} 08/30/2021 15:44:02 - INFO - __main__ - Step 14573: {'lr': 0.0004911505535920086, 'samples': 2798016, 'steps': 14572, 'loss/train': 1.947395920753479} 08/30/2021 15:44:02 - INFO - __main__ - Step 14574: {'lr': 0.0004911491541001126, 'samples': 2798208, 'steps': 14573, 'loss/train': 2.5584192276000977} 08/30/2021 15:44:03 - INFO - __main__ - Step 14575: {'lr': 0.0004911477544995585, 'samples': 2798400, 'steps': 14574, 'loss/train': 1.6723089218139648} 08/30/2021 15:44:04 - INFO - __main__ - Step 14576: {'lr': 0.000491146354790347, 'samples': 2798592, 'steps': 14575, 'loss/train': 2.1901209354400635} 08/30/2021 15:44:04 - INFO - __main__ - Step 14577: {'lr': 0.0004911449549724786, 'samples': 2798784, 'steps': 14576, 'loss/train': 1.4071576595306396} 08/30/2021 15:44:05 - INFO - __main__ - Step 14578: {'lr': 0.0004911435550459541, 'samples': 2798976, 'steps': 14577, 'loss/train': 1.4971303939819336} 08/30/2021 15:44:05 - INFO - __main__ - Step 14579: {'lr': 0.0004911421550107739, 'samples': 2799168, 'steps': 14578, 'loss/train': 1.8599587678909302} 08/30/2021 15:44:06 - INFO - __main__ - Step 14580: {'lr': 0.0004911407548669389, 'samples': 2799360, 'steps': 14579, 'loss/train': 2.2231287956237793} 08/30/2021 15:44:07 - INFO - __main__ - Step 14581: {'lr': 0.0004911393546144495, 'samples': 2799552, 'steps': 14580, 'loss/train': 1.9813406467437744} 08/30/2021 15:44:07 - INFO - __main__ - Step 14582: {'lr': 0.0004911379542533065, 'samples': 2799744, 'steps': 14581, 'loss/train': 1.5219194889068604} 08/30/2021 15:44:08 - INFO - __main__ - Step 14583: {'lr': 0.0004911365537835105, 'samples': 2799936, 'steps': 14582, 'loss/train': 1.6899129152297974} 08/30/2021 15:44:08 - INFO - __main__ - Step 14584: {'lr': 0.000491135153205062, 'samples': 2800128, 'steps': 14583, 'loss/train': 1.8255943059921265} 08/30/2021 15:44:09 - INFO - __main__ - Step 14585: {'lr': 0.0004911337525179616, 'samples': 2800320, 'steps': 14584, 'loss/train': 1.802324652671814} 08/30/2021 15:44:10 - INFO - __main__ - Step 14586: {'lr': 0.0004911323517222103, 'samples': 2800512, 'steps': 14585, 'loss/train': 1.627037763595581} 08/30/2021 15:44:11 - INFO - __main__ - Step 14587: {'lr': 0.0004911309508178084, 'samples': 2800704, 'steps': 14586, 'loss/train': 1.3630696535110474} 08/30/2021 15:44:11 - INFO - __main__ - Step 14588: {'lr': 0.0004911295498047565, 'samples': 2800896, 'steps': 14587, 'loss/train': 1.8996014595031738} 08/30/2021 15:44:12 - INFO - __main__ - Step 14589: {'lr': 0.0004911281486830554, 'samples': 2801088, 'steps': 14588, 'loss/train': 2.2303671836853027} 08/30/2021 15:44:12 - INFO - __main__ - Step 14590: {'lr': 0.0004911267474527058, 'samples': 2801280, 'steps': 14589, 'loss/train': 1.1725919246673584} 08/30/2021 15:44:12 - INFO - __main__ - Step 14591: {'lr': 0.000491125346113708, 'samples': 2801472, 'steps': 14590, 'loss/train': 1.1614854335784912} 08/30/2021 15:44:14 - INFO - __main__ - Step 14592: {'lr': 0.000491123944666063, 'samples': 2801664, 'steps': 14591, 'loss/train': 2.026860475540161} 08/30/2021 15:44:14 - INFO - __main__ - Step 14593: {'lr': 0.0004911225431097712, 'samples': 2801856, 'steps': 14592, 'loss/train': 1.815241813659668} 08/30/2021 15:44:15 - INFO - __main__ - Step 14594: {'lr': 0.0004911211414448333, 'samples': 2802048, 'steps': 14593, 'loss/train': 1.818095326423645} 08/30/2021 15:44:15 - INFO - __main__ - Step 14595: {'lr': 0.0004911197396712501, 'samples': 2802240, 'steps': 14594, 'loss/train': 1.7291560173034668} 08/30/2021 15:44:15 - INFO - __main__ - Step 14596: {'lr': 0.0004911183377890218, 'samples': 2802432, 'steps': 14595, 'loss/train': 1.8934985399246216} 08/30/2021 15:44:17 - INFO - __main__ - Step 14597: {'lr': 0.0004911169357981496, 'samples': 2802624, 'steps': 14596, 'loss/train': 1.3341199159622192} 08/30/2021 15:44:17 - INFO - __main__ - Step 14598: {'lr': 0.0004911155336986335, 'samples': 2802816, 'steps': 14597, 'loss/train': 1.5891129970550537} 08/30/2021 15:44:18 - INFO - __main__ - Step 14599: {'lr': 0.0004911141314904747, 'samples': 2803008, 'steps': 14598, 'loss/train': 1.7796026468276978} 08/30/2021 15:44:18 - INFO - __main__ - Step 14600: {'lr': 0.0004911127291736735, 'samples': 2803200, 'steps': 14599, 'loss/train': 4.444014549255371} 08/30/2021 15:44:18 - INFO - __main__ - Step 14601: {'lr': 0.0004911113267482307, 'samples': 2803392, 'steps': 14600, 'loss/train': 1.5700595378875732} 08/30/2021 15:44:19 - INFO - __main__ - Step 14602: {'lr': 0.0004911099242141467, 'samples': 2803584, 'steps': 14601, 'loss/train': 1.9138917922973633} 08/30/2021 15:44:21 - INFO - __main__ - Step 14603: {'lr': 0.0004911085215714224, 'samples': 2803776, 'steps': 14602, 'loss/train': 1.6377992630004883} 08/30/2021 15:44:21 - INFO - __main__ - Step 14604: {'lr': 0.0004911071188200584, 'samples': 2803968, 'steps': 14603, 'loss/train': 1.746010184288025} 08/30/2021 15:44:21 - INFO - __main__ - Step 14605: {'lr': 0.0004911057159600551, 'samples': 2804160, 'steps': 14604, 'loss/train': 1.6858192682266235} 08/30/2021 15:44:22 - INFO - __main__ - Step 14606: {'lr': 0.0004911043129914133, 'samples': 2804352, 'steps': 14605, 'loss/train': 2.0764570236206055} 08/30/2021 15:44:22 - INFO - __main__ - Step 14607: {'lr': 0.0004911029099141336, 'samples': 2804544, 'steps': 14606, 'loss/train': 1.961524248123169} 08/30/2021 15:44:24 - INFO - __main__ - Step 14608: {'lr': 0.0004911015067282168, 'samples': 2804736, 'steps': 14607, 'loss/train': 1.7911008596420288} 08/30/2021 15:44:24 - INFO - __main__ - Step 14609: {'lr': 0.0004911001034336633, 'samples': 2804928, 'steps': 14608, 'loss/train': 1.6780343055725098} 08/30/2021 15:44:24 - INFO - __main__ - Step 14610: {'lr': 0.0004910987000304737, 'samples': 2805120, 'steps': 14609, 'loss/train': 1.8911654949188232} 08/30/2021 15:44:25 - INFO - __main__ - Step 14611: {'lr': 0.0004910972965186488, 'samples': 2805312, 'steps': 14610, 'loss/train': 2.0743560791015625} 08/30/2021 15:44:25 - INFO - __main__ - Step 14612: {'lr': 0.0004910958928981893, 'samples': 2805504, 'steps': 14611, 'loss/train': 1.5017342567443848} 08/30/2021 15:44:27 - INFO - __main__ - Step 14613: {'lr': 0.0004910944891690956, 'samples': 2805696, 'steps': 14612, 'loss/train': 1.7243694067001343} 08/30/2021 15:44:27 - INFO - __main__ - Step 14614: {'lr': 0.0004910930853313686, 'samples': 2805888, 'steps': 14613, 'loss/train': 1.8691600561141968} 08/30/2021 15:44:27 - INFO - __main__ - Step 14615: {'lr': 0.0004910916813850086, 'samples': 2806080, 'steps': 14614, 'loss/train': 1.6921037435531616} 08/30/2021 15:44:28 - INFO - __main__ - Step 14616: {'lr': 0.0004910902773300164, 'samples': 2806272, 'steps': 14615, 'loss/train': 1.556960940361023} 08/30/2021 15:44:28 - INFO - __main__ - Step 14617: {'lr': 0.0004910888731663928, 'samples': 2806464, 'steps': 14616, 'loss/train': 1.6416927576065063} 08/30/2021 15:44:30 - INFO - __main__ - Step 14618: {'lr': 0.0004910874688941381, 'samples': 2806656, 'steps': 14617, 'loss/train': 1.4495739936828613} 08/30/2021 15:44:30 - INFO - __main__ - Step 14619: {'lr': 0.0004910860645132532, 'samples': 2806848, 'steps': 14618, 'loss/train': 2.184468984603882} 08/30/2021 15:44:30 - INFO - __main__ - Step 14620: {'lr': 0.0004910846600237386, 'samples': 2807040, 'steps': 14619, 'loss/train': 1.7852646112442017} 08/30/2021 15:44:31 - INFO - __main__ - Step 14621: {'lr': 0.0004910832554255951, 'samples': 2807232, 'steps': 14620, 'loss/train': 1.9583921432495117} 08/30/2021 15:44:31 - INFO - __main__ - Step 14622: {'lr': 0.0004910818507188231, 'samples': 2807424, 'steps': 14621, 'loss/train': 1.8207911252975464} 08/30/2021 15:44:33 - INFO - __main__ - Step 14623: {'lr': 0.0004910804459034233, 'samples': 2807616, 'steps': 14622, 'loss/train': 1.994828701019287} 08/30/2021 15:44:33 - INFO - __main__ - Step 14624: {'lr': 0.0004910790409793965, 'samples': 2807808, 'steps': 14623, 'loss/train': 1.6754604578018188} 08/30/2021 15:44:34 - INFO - __main__ - Step 14625: {'lr': 0.000491077635946743, 'samples': 2808000, 'steps': 14624, 'loss/train': 1.3960660696029663} 08/30/2021 15:44:34 - INFO - __main__ - Step 14626: {'lr': 0.0004910762308054638, 'samples': 2808192, 'steps': 14625, 'loss/train': 1.5810043811798096} 08/30/2021 15:44:34 - INFO - __main__ - Step 14627: {'lr': 0.0004910748255555593, 'samples': 2808384, 'steps': 14626, 'loss/train': 1.9512444734573364} 08/30/2021 15:44:36 - INFO - __main__ - Step 14628: {'lr': 0.0004910734201970302, 'samples': 2808576, 'steps': 14627, 'loss/train': 1.7666977643966675} 08/30/2021 15:44:36 - INFO - __main__ - Step 14629: {'lr': 0.0004910720147298772, 'samples': 2808768, 'steps': 14628, 'loss/train': 1.2753146886825562} 08/30/2021 15:44:37 - INFO - __main__ - Step 14630: {'lr': 0.0004910706091541009, 'samples': 2808960, 'steps': 14629, 'loss/train': 0.964402973651886} 08/30/2021 15:44:37 - INFO - __main__ - Step 14631: {'lr': 0.0004910692034697018, 'samples': 2809152, 'steps': 14630, 'loss/train': 1.3130466938018799} 08/30/2021 15:44:37 - INFO - __main__ - Step 14632: {'lr': 0.0004910677976766807, 'samples': 2809344, 'steps': 14631, 'loss/train': 1.5554542541503906} 08/30/2021 15:44:38 - INFO - __main__ - Step 14633: {'lr': 0.0004910663917750382, 'samples': 2809536, 'steps': 14632, 'loss/train': 1.7356388568878174} 08/30/2021 15:44:39 - INFO - __main__ - Step 14634: {'lr': 0.0004910649857647748, 'samples': 2809728, 'steps': 14633, 'loss/train': 1.9776718616485596} 08/30/2021 15:44:40 - INFO - __main__ - Step 14635: {'lr': 0.0004910635796458913, 'samples': 2809920, 'steps': 14634, 'loss/train': 2.3299033641815186} 08/30/2021 15:44:40 - INFO - __main__ - Step 14636: {'lr': 0.0004910621734183882, 'samples': 2810112, 'steps': 14635, 'loss/train': 2.086420774459839} 08/30/2021 15:44:40 - INFO - __main__ - Step 14637: {'lr': 0.0004910607670822663, 'samples': 2810304, 'steps': 14636, 'loss/train': 1.181735873222351} 08/30/2021 15:44:41 - INFO - __main__ - Step 14638: {'lr': 0.0004910593606375261, 'samples': 2810496, 'steps': 14637, 'loss/train': 1.4632714986801147} 08/30/2021 15:44:41 - INFO - __main__ - Step 14639: {'lr': 0.0004910579540841683, 'samples': 2810688, 'steps': 14638, 'loss/train': 2.17461895942688} 08/30/2021 15:44:43 - INFO - __main__ - Step 14640: {'lr': 0.0004910565474221934, 'samples': 2810880, 'steps': 14639, 'loss/train': 1.7071837186813354} 08/30/2021 15:44:43 - INFO - __main__ - Step 14641: {'lr': 0.0004910551406516022, 'samples': 2811072, 'steps': 14640, 'loss/train': 1.1795498132705688} 08/30/2021 15:44:43 - INFO - __main__ - Step 14642: {'lr': 0.0004910537337723954, 'samples': 2811264, 'steps': 14641, 'loss/train': 1.0120351314544678} 08/30/2021 15:44:44 - INFO - __main__ - Step 14643: {'lr': 0.0004910523267845733, 'samples': 2811456, 'steps': 14642, 'loss/train': 2.166316270828247} 08/30/2021 15:44:44 - INFO - __main__ - Step 14644: {'lr': 0.0004910509196881369, 'samples': 2811648, 'steps': 14643, 'loss/train': 1.7520242929458618} 08/30/2021 15:44:46 - INFO - __main__ - Step 14645: {'lr': 0.0004910495124830866, 'samples': 2811840, 'steps': 14644, 'loss/train': 0.8346025347709656} 08/30/2021 15:44:46 - INFO - __main__ - Step 14646: {'lr': 0.0004910481051694231, 'samples': 2812032, 'steps': 14645, 'loss/train': 2.275949478149414} 08/30/2021 15:44:46 - INFO - __main__ - Step 14647: {'lr': 0.0004910466977471471, 'samples': 2812224, 'steps': 14646, 'loss/train': 1.7611808776855469} 08/30/2021 15:44:47 - INFO - __main__ - Step 14648: {'lr': 0.0004910452902162592, 'samples': 2812416, 'steps': 14647, 'loss/train': 2.085137367248535} 08/30/2021 15:44:47 - INFO - __main__ - Step 14649: {'lr': 0.0004910438825767599, 'samples': 2812608, 'steps': 14648, 'loss/train': 2.0280754566192627} 08/30/2021 15:44:49 - INFO - __main__ - Step 14650: {'lr': 0.00049104247482865, 'samples': 2812800, 'steps': 14649, 'loss/train': 1.8058545589447021} 08/30/2021 15:44:49 - INFO - __main__ - Step 14651: {'lr': 0.0004910410669719301, 'samples': 2812992, 'steps': 14650, 'loss/train': 1.3903549909591675} 08/30/2021 15:44:49 - INFO - __main__ - Step 14652: {'lr': 0.0004910396590066008, 'samples': 2813184, 'steps': 14651, 'loss/train': 2.116035223007202} 08/30/2021 15:44:50 - INFO - __main__ - Step 14653: {'lr': 0.0004910382509326627, 'samples': 2813376, 'steps': 14652, 'loss/train': 1.607561707496643} 08/30/2021 15:44:50 - INFO - __main__ - Step 14654: {'lr': 0.0004910368427501166, 'samples': 2813568, 'steps': 14653, 'loss/train': 1.5568851232528687} 08/30/2021 15:44:52 - INFO - __main__ - Step 14655: {'lr': 0.000491035434458963, 'samples': 2813760, 'steps': 14654, 'loss/train': 1.773860216140747} 08/30/2021 15:44:53 - INFO - __main__ - Step 14656: {'lr': 0.0004910340260592024, 'samples': 2813952, 'steps': 14655, 'loss/train': 1.6594730615615845} 08/30/2021 15:44:53 - INFO - __main__ - Step 14657: {'lr': 0.0004910326175508357, 'samples': 2814144, 'steps': 14656, 'loss/train': 1.91238272190094} 08/30/2021 15:44:54 - INFO - __main__ - Step 14658: {'lr': 0.0004910312089338634, 'samples': 2814336, 'steps': 14657, 'loss/train': 1.8704928159713745} 08/30/2021 15:44:54 - INFO - __main__ - Step 14659: {'lr': 0.0004910298002082863, 'samples': 2814528, 'steps': 14658, 'loss/train': 2.0522892475128174} 08/30/2021 15:44:54 - INFO - __main__ - Step 14660: {'lr': 0.0004910283913741047, 'samples': 2814720, 'steps': 14659, 'loss/train': 1.9995373487472534} 08/30/2021 15:44:56 - INFO - __main__ - Step 14661: {'lr': 0.0004910269824313194, 'samples': 2814912, 'steps': 14660, 'loss/train': 0.10485048592090607} 08/30/2021 15:44:57 - INFO - __main__ - Step 14662: {'lr': 0.0004910255733799312, 'samples': 2815104, 'steps': 14661, 'loss/train': 1.678443431854248} 08/30/2021 15:44:57 - INFO - __main__ - Step 14663: {'lr': 0.0004910241642199406, 'samples': 2815296, 'steps': 14662, 'loss/train': 1.8793506622314453} 08/30/2021 15:44:57 - INFO - __main__ - Step 14664: {'lr': 0.0004910227549513481, 'samples': 2815488, 'steps': 14663, 'loss/train': 1.6896947622299194} 08/30/2021 15:44:58 - INFO - __main__ - Step 14665: {'lr': 0.0004910213455741546, 'samples': 2815680, 'steps': 14664, 'loss/train': 1.2330312728881836} 08/30/2021 15:44:59 - INFO - __main__ - Step 14666: {'lr': 0.0004910199360883605, 'samples': 2815872, 'steps': 14665, 'loss/train': 0.17734304070472717} 08/30/2021 15:45:00 - INFO - __main__ - Step 14667: {'lr': 0.0004910185264939667, 'samples': 2816064, 'steps': 14666, 'loss/train': 1.6526727676391602} 08/30/2021 15:45:00 - INFO - __main__ - Step 14668: {'lr': 0.0004910171167909734, 'samples': 2816256, 'steps': 14667, 'loss/train': 1.6394777297973633} 08/30/2021 15:45:00 - INFO - __main__ - Step 14669: {'lr': 0.0004910157069793816, 'samples': 2816448, 'steps': 14668, 'loss/train': 1.6216762065887451} 08/30/2021 15:45:01 - INFO - __main__ - Step 14670: {'lr': 0.000491014297059192, 'samples': 2816640, 'steps': 14669, 'loss/train': 1.1892478466033936} 08/30/2021 15:45:02 - INFO - __main__ - Step 14671: {'lr': 0.000491012887030405, 'samples': 2816832, 'steps': 14670, 'loss/train': 1.829420566558838} 08/30/2021 15:45:02 - INFO - __main__ - Step 14672: {'lr': 0.0004910114768930212, 'samples': 2817024, 'steps': 14671, 'loss/train': 1.589525818824768} 08/30/2021 15:45:03 - INFO - __main__ - Step 14673: {'lr': 0.0004910100666470415, 'samples': 2817216, 'steps': 14672, 'loss/train': 1.4008476734161377} 08/30/2021 15:45:03 - INFO - __main__ - Step 14674: {'lr': 0.0004910086562924663, 'samples': 2817408, 'steps': 14673, 'loss/train': 1.9427365064620972} 08/30/2021 15:45:03 - INFO - __main__ - Step 14675: {'lr': 0.0004910072458292963, 'samples': 2817600, 'steps': 14674, 'loss/train': 1.1250696182250977} 08/30/2021 15:45:05 - INFO - __main__ - Step 14676: {'lr': 0.0004910058352575322, 'samples': 2817792, 'steps': 14675, 'loss/train': 1.6572259664535522} 08/30/2021 15:45:06 - INFO - __main__ - Step 14677: {'lr': 0.0004910044245771745, 'samples': 2817984, 'steps': 14676, 'loss/train': 1.3050671815872192} 08/30/2021 15:45:06 - INFO - __main__ - Step 14678: {'lr': 0.0004910030137882241, 'samples': 2818176, 'steps': 14677, 'loss/train': 1.45987868309021} 08/30/2021 15:45:06 - INFO - __main__ - Step 14679: {'lr': 0.0004910016028906813, 'samples': 2818368, 'steps': 14678, 'loss/train': 1.8911447525024414} 08/30/2021 15:45:07 - INFO - __main__ - Step 14680: {'lr': 0.000491000191884547, 'samples': 2818560, 'steps': 14679, 'loss/train': 1.4819631576538086} 08/30/2021 15:45:07 - INFO - __main__ - Step 14681: {'lr': 0.0004909987807698217, 'samples': 2818752, 'steps': 14680, 'loss/train': 1.9897003173828125} 08/30/2021 15:45:09 - INFO - __main__ - Step 14682: {'lr': 0.000490997369546506, 'samples': 2818944, 'steps': 14681, 'loss/train': 1.1989651918411255} 08/30/2021 15:45:09 - INFO - __main__ - Step 14683: {'lr': 0.0004909959582146007, 'samples': 2819136, 'steps': 14682, 'loss/train': 1.6224522590637207} 08/30/2021 15:45:09 - INFO - __main__ - Step 14684: {'lr': 0.0004909945467741063, 'samples': 2819328, 'steps': 14683, 'loss/train': 1.3895024061203003} 08/30/2021 15:45:10 - INFO - __main__ - Step 14685: {'lr': 0.0004909931352250235, 'samples': 2819520, 'steps': 14684, 'loss/train': 1.818917989730835} 08/30/2021 15:45:10 - INFO - __main__ - Step 14686: {'lr': 0.0004909917235673529, 'samples': 2819712, 'steps': 14685, 'loss/train': 1.71416437625885} 08/30/2021 15:45:13 - INFO - __main__ - Step 14687: {'lr': 0.0004909903118010951, 'samples': 2819904, 'steps': 14686, 'loss/train': 0.31285062432289124} 08/30/2021 15:45:13 - INFO - __main__ - Step 14688: {'lr': 0.0004909888999262509, 'samples': 2820096, 'steps': 14687, 'loss/train': 1.394999623298645} 08/30/2021 15:45:14 - INFO - __main__ - Step 14689: {'lr': 0.0004909874879428207, 'samples': 2820288, 'steps': 14688, 'loss/train': 1.726932406425476} 08/30/2021 15:45:14 - INFO - __main__ - Step 14690: {'lr': 0.0004909860758508052, 'samples': 2820480, 'steps': 14689, 'loss/train': 1.9724937677383423} 08/30/2021 15:45:15 - INFO - __main__ - Step 14691: {'lr': 0.0004909846636502053, 'samples': 2820672, 'steps': 14690, 'loss/train': 1.2475253343582153} 08/30/2021 15:45:15 - INFO - __main__ - Step 14692: {'lr': 0.0004909832513410213, 'samples': 2820864, 'steps': 14691, 'loss/train': 0.6993420720100403} 08/30/2021 15:45:15 - INFO - __main__ - Step 14693: {'lr': 0.000490981838923254, 'samples': 2821056, 'steps': 14692, 'loss/train': 0.6544314026832581} 08/30/2021 15:45:17 - INFO - __main__ - Step 14694: {'lr': 0.000490980426396904, 'samples': 2821248, 'steps': 14693, 'loss/train': 0.6051246523857117} 08/30/2021 15:45:17 - INFO - __main__ - Step 14695: {'lr': 0.0004909790137619719, 'samples': 2821440, 'steps': 14694, 'loss/train': 1.8594558238983154} 08/30/2021 15:45:18 - INFO - __main__ - Step 14696: {'lr': 0.0004909776010184585, 'samples': 2821632, 'steps': 14695, 'loss/train': 1.3099099397659302} 08/30/2021 15:45:18 - INFO - __main__ - Step 14697: {'lr': 0.0004909761881663642, 'samples': 2821824, 'steps': 14696, 'loss/train': 0.8243240118026733} 08/30/2021 15:45:18 - INFO - __main__ - Step 14698: {'lr': 0.0004909747752056897, 'samples': 2822016, 'steps': 14697, 'loss/train': 1.732924461364746} 08/30/2021 15:45:20 - INFO - __main__ - Step 14699: {'lr': 0.0004909733621364358, 'samples': 2822208, 'steps': 14698, 'loss/train': 1.355660319328308} 08/30/2021 15:45:20 - INFO - __main__ - Step 14700: {'lr': 0.0004909719489586029, 'samples': 2822400, 'steps': 14699, 'loss/train': 1.5890251398086548} 08/30/2021 15:45:21 - INFO - __main__ - Step 14701: {'lr': 0.0004909705356721919, 'samples': 2822592, 'steps': 14700, 'loss/train': 1.6387518644332886} 08/30/2021 15:45:21 - INFO - __main__ - Step 14702: {'lr': 0.0004909691222772032, 'samples': 2822784, 'steps': 14701, 'loss/train': 1.9046984910964966} 08/30/2021 15:45:21 - INFO - __main__ - Step 14703: {'lr': 0.0004909677087736375, 'samples': 2822976, 'steps': 14702, 'loss/train': 2.410398006439209} 08/30/2021 15:45:23 - INFO - __main__ - Step 14704: {'lr': 0.0004909662951614955, 'samples': 2823168, 'steps': 14703, 'loss/train': 2.110142469406128} 08/30/2021 15:45:24 - INFO - __main__ - Step 14705: {'lr': 0.0004909648814407779, 'samples': 2823360, 'steps': 14704, 'loss/train': 1.9797699451446533} 08/30/2021 15:45:24 - INFO - __main__ - Step 14706: {'lr': 0.0004909634676114851, 'samples': 2823552, 'steps': 14705, 'loss/train': 0.40343761444091797} 08/30/2021 15:45:24 - INFO - __main__ - Step 14707: {'lr': 0.000490962053673618, 'samples': 2823744, 'steps': 14706, 'loss/train': 2.281370162963867} 08/30/2021 15:45:25 - INFO - __main__ - Step 14708: {'lr': 0.0004909606396271771, 'samples': 2823936, 'steps': 14707, 'loss/train': 1.9501404762268066} 08/30/2021 15:45:25 - INFO - __main__ - Step 14709: {'lr': 0.000490959225472163, 'samples': 2824128, 'steps': 14708, 'loss/train': 2.140007734298706} 08/30/2021 15:45:26 - INFO - __main__ - Step 14710: {'lr': 0.0004909578112085764, 'samples': 2824320, 'steps': 14709, 'loss/train': 1.8393839597702026} 08/30/2021 15:45:27 - INFO - __main__ - Step 14711: {'lr': 0.0004909563968364179, 'samples': 2824512, 'steps': 14710, 'loss/train': 1.8584641218185425} 08/30/2021 15:45:27 - INFO - __main__ - Step 14712: {'lr': 0.0004909549823556883, 'samples': 2824704, 'steps': 14711, 'loss/train': 1.9532889127731323} 08/30/2021 15:45:28 - INFO - __main__ - Step 14713: {'lr': 0.000490953567766388, 'samples': 2824896, 'steps': 14712, 'loss/train': 1.585712194442749} 08/30/2021 15:45:28 - INFO - __main__ - Step 14714: {'lr': 0.0004909521530685177, 'samples': 2825088, 'steps': 14713, 'loss/train': 2.0731117725372314} 08/30/2021 15:45:29 - INFO - __main__ - Step 14715: {'lr': 0.0004909507382620782, 'samples': 2825280, 'steps': 14714, 'loss/train': 2.686898946762085} 08/30/2021 15:45:30 - INFO - __main__ - Step 14716: {'lr': 0.0004909493233470699, 'samples': 2825472, 'steps': 14715, 'loss/train': 1.6656004190444946} 08/30/2021 15:45:30 - INFO - __main__ - Step 14717: {'lr': 0.0004909479083234936, 'samples': 2825664, 'steps': 14716, 'loss/train': 1.4297140836715698} 08/30/2021 15:45:31 - INFO - __main__ - Step 14718: {'lr': 0.0004909464931913499, 'samples': 2825856, 'steps': 14717, 'loss/train': 2.172856569290161} 08/30/2021 15:45:31 - INFO - __main__ - Step 14719: {'lr': 0.0004909450779506393, 'samples': 2826048, 'steps': 14718, 'loss/train': 1.8576105833053589} 08/30/2021 15:45:33 - INFO - __main__ - Step 14720: {'lr': 0.0004909436626013628, 'samples': 2826240, 'steps': 14719, 'loss/train': 2.227588653564453} 08/30/2021 15:45:33 - INFO - __main__ - Step 14721: {'lr': 0.0004909422471435207, 'samples': 2826432, 'steps': 14720, 'loss/train': 0.9746146202087402} 08/30/2021 15:45:34 - INFO - __main__ - Step 14722: {'lr': 0.0004909408315771136, 'samples': 2826624, 'steps': 14721, 'loss/train': 1.4908896684646606} 08/30/2021 15:45:34 - INFO - __main__ - Step 14723: {'lr': 0.0004909394159021425, 'samples': 2826816, 'steps': 14722, 'loss/train': 1.2262314558029175} 08/30/2021 15:45:34 - INFO - __main__ - Step 14724: {'lr': 0.0004909380001186077, 'samples': 2827008, 'steps': 14723, 'loss/train': 1.6169757843017578} 08/30/2021 15:45:36 - INFO - __main__ - Step 14725: {'lr': 0.00049093658422651, 'samples': 2827200, 'steps': 14724, 'loss/train': 1.6944632530212402} 08/30/2021 15:45:36 - INFO - __main__ - Step 14726: {'lr': 0.00049093516822585, 'samples': 2827392, 'steps': 14725, 'loss/train': 1.458341121673584} 08/30/2021 15:45:37 - INFO - __main__ - Step 14727: {'lr': 0.0004909337521166282, 'samples': 2827584, 'steps': 14726, 'loss/train': 2.004753351211548} 08/30/2021 15:45:37 - INFO - __main__ - Step 14728: {'lr': 0.0004909323358988455, 'samples': 2827776, 'steps': 14727, 'loss/train': 0.2734319269657135} 08/30/2021 15:45:37 - INFO - __main__ - Step 14729: {'lr': 0.0004909309195725024, 'samples': 2827968, 'steps': 14728, 'loss/train': 2.0499861240386963} 08/30/2021 15:45:38 - INFO - __main__ - Step 14730: {'lr': 0.0004909295031375996, 'samples': 2828160, 'steps': 14729, 'loss/train': 1.128167748451233} 08/30/2021 15:45:40 - INFO - __main__ - Step 14731: {'lr': 0.0004909280865941375, 'samples': 2828352, 'steps': 14730, 'loss/train': 1.9347211122512817} 08/30/2021 15:45:40 - INFO - __main__ - Step 14732: {'lr': 0.0004909266699421171, 'samples': 2828544, 'steps': 14731, 'loss/train': 2.115064859390259} 08/30/2021 15:45:40 - INFO - __main__ - Step 14733: {'lr': 0.0004909252531815388, 'samples': 2828736, 'steps': 14732, 'loss/train': 2.062617540359497} 08/30/2021 15:45:41 - INFO - __main__ - Step 14734: {'lr': 0.0004909238363124033, 'samples': 2828928, 'steps': 14733, 'loss/train': 2.1753149032592773} 08/30/2021 15:45:41 - INFO - __main__ - Step 14735: {'lr': 0.0004909224193347112, 'samples': 2829120, 'steps': 14734, 'loss/train': 1.2242854833602905} 08/30/2021 15:45:43 - INFO - __main__ - Step 14736: {'lr': 0.0004909210022484633, 'samples': 2829312, 'steps': 14735, 'loss/train': 1.9963405132293701} 08/30/2021 15:45:43 - INFO - __main__ - Step 14737: {'lr': 0.00049091958505366, 'samples': 2829504, 'steps': 14736, 'loss/train': 1.435778021812439} 08/30/2021 15:45:44 - INFO - __main__ - Step 14738: {'lr': 0.000490918167750302, 'samples': 2829696, 'steps': 14737, 'loss/train': 0.13562822341918945} 08/30/2021 15:45:44 - INFO - __main__ - Step 14739: {'lr': 0.00049091675033839, 'samples': 2829888, 'steps': 14738, 'loss/train': 1.2889208793640137} 08/30/2021 15:45:44 - INFO - __main__ - Step 14740: {'lr': 0.0004909153328179248, 'samples': 2830080, 'steps': 14739, 'loss/train': 2.167332410812378} 08/30/2021 15:45:45 - INFO - __main__ - Step 14741: {'lr': 0.0004909139151889067, 'samples': 2830272, 'steps': 14740, 'loss/train': 1.9671624898910522} 08/30/2021 15:45:46 - INFO - __main__ - Step 14742: {'lr': 0.0004909124974513366, 'samples': 2830464, 'steps': 14741, 'loss/train': 1.864754557609558} 08/30/2021 15:45:47 - INFO - __main__ - Step 14743: {'lr': 0.000490911079605215, 'samples': 2830656, 'steps': 14742, 'loss/train': 1.824412226676941} 08/30/2021 15:45:47 - INFO - __main__ - Step 14744: {'lr': 0.0004909096616505426, 'samples': 2830848, 'steps': 14743, 'loss/train': 0.8528931140899658} 08/30/2021 15:45:48 - INFO - __main__ - Step 14745: {'lr': 0.00049090824358732, 'samples': 2831040, 'steps': 14744, 'loss/train': 1.975135326385498} 08/30/2021 15:45:48 - INFO - __main__ - Step 14746: {'lr': 0.0004909068254155479, 'samples': 2831232, 'steps': 14745, 'loss/train': 1.5108544826507568} 08/30/2021 15:45:50 - INFO - __main__ - Step 14747: {'lr': 0.0004909054071352269, 'samples': 2831424, 'steps': 14746, 'loss/train': 1.790999412536621} 08/30/2021 15:45:50 - INFO - __main__ - Step 14748: {'lr': 0.0004909039887463576, 'samples': 2831616, 'steps': 14747, 'loss/train': 1.9513864517211914} 08/30/2021 15:45:51 - INFO - __main__ - Step 14749: {'lr': 0.0004909025702489407, 'samples': 2831808, 'steps': 14748, 'loss/train': 0.9044994115829468} 08/30/2021 15:45:51 - INFO - __main__ - Step 14750: {'lr': 0.0004909011516429768, 'samples': 2832000, 'steps': 14749, 'loss/train': 1.6430326700210571} 08/30/2021 15:45:51 - INFO - __main__ - Step 14751: {'lr': 0.0004908997329284667, 'samples': 2832192, 'steps': 14750, 'loss/train': 1.896259069442749} 08/30/2021 15:45:52 - INFO - __main__ - Step 14752: {'lr': 0.0004908983141054107, 'samples': 2832384, 'steps': 14751, 'loss/train': 2.2090365886688232} 08/30/2021 15:45:53 - INFO - __main__ - Step 14753: {'lr': 0.0004908968951738098, 'samples': 2832576, 'steps': 14752, 'loss/train': 2.1068897247314453} 08/30/2021 15:45:54 - INFO - __main__ - Step 14754: {'lr': 0.0004908954761336643, 'samples': 2832768, 'steps': 14753, 'loss/train': 1.7195020914077759} 08/30/2021 15:45:54 - INFO - __main__ - Step 14755: {'lr': 0.0004908940569849751, 'samples': 2832960, 'steps': 14754, 'loss/train': 3.5167717933654785} 08/30/2021 15:45:54 - INFO - __main__ - Step 14756: {'lr': 0.0004908926377277428, 'samples': 2833152, 'steps': 14755, 'loss/train': 1.8004331588745117} 08/30/2021 15:45:55 - INFO - __main__ - Step 14757: {'lr': 0.000490891218361968, 'samples': 2833344, 'steps': 14756, 'loss/train': 1.5686569213867188} 08/30/2021 15:45:56 - INFO - __main__ - Step 14758: {'lr': 0.0004908897988876512, 'samples': 2833536, 'steps': 14757, 'loss/train': 2.927267551422119} 08/30/2021 15:45:57 - INFO - __main__ - Step 14759: {'lr': 0.0004908883793047934, 'samples': 2833728, 'steps': 14758, 'loss/train': 1.738626480102539} 08/30/2021 15:45:57 - INFO - __main__ - Step 14760: {'lr': 0.0004908869596133948, 'samples': 2833920, 'steps': 14759, 'loss/train': 1.6574175357818604} 08/30/2021 15:45:58 - INFO - __main__ - Step 14761: {'lr': 0.0004908855398134563, 'samples': 2834112, 'steps': 14760, 'loss/train': 2.0832979679107666} 08/30/2021 15:45:58 - INFO - __main__ - Step 14762: {'lr': 0.0004908841199049785, 'samples': 2834304, 'steps': 14761, 'loss/train': 1.847208023071289} 08/30/2021 15:46:00 - INFO - __main__ - Step 14763: {'lr': 0.0004908826998879621, 'samples': 2834496, 'steps': 14762, 'loss/train': 1.6407380104064941} 08/30/2021 15:46:00 - INFO - __main__ - Step 14764: {'lr': 0.0004908812797624077, 'samples': 2834688, 'steps': 14763, 'loss/train': 2.1208245754241943} 08/30/2021 15:46:00 - INFO - __main__ - Step 14765: {'lr': 0.0004908798595283159, 'samples': 2834880, 'steps': 14764, 'loss/train': 2.920278549194336} 08/30/2021 15:46:01 - INFO - __main__ - Step 14766: {'lr': 0.0004908784391856872, 'samples': 2835072, 'steps': 14765, 'loss/train': 1.6570030450820923} 08/30/2021 15:46:01 - INFO - __main__ - Step 14767: {'lr': 0.0004908770187345225, 'samples': 2835264, 'steps': 14766, 'loss/train': 1.491756796836853} 08/30/2021 15:46:01 - INFO - __main__ - Step 14768: {'lr': 0.0004908755981748223, 'samples': 2835456, 'steps': 14767, 'loss/train': 2.148419141769409} 08/30/2021 15:46:03 - INFO - __main__ - Step 14769: {'lr': 0.0004908741775065873, 'samples': 2835648, 'steps': 14768, 'loss/train': 1.8597686290740967} 08/30/2021 15:46:03 - INFO - __main__ - Step 14770: {'lr': 0.0004908727567298181, 'samples': 2835840, 'steps': 14769, 'loss/train': 1.5146944522857666} 08/30/2021 15:46:04 - INFO - __main__ - Step 14771: {'lr': 0.0004908713358445154, 'samples': 2836032, 'steps': 14770, 'loss/train': 1.489193320274353} 08/30/2021 15:46:04 - INFO - __main__ - Step 14772: {'lr': 0.0004908699148506797, 'samples': 2836224, 'steps': 14771, 'loss/train': 2.9027161598205566} 08/30/2021 15:46:04 - INFO - __main__ - Step 14773: {'lr': 0.0004908684937483119, 'samples': 2836416, 'steps': 14772, 'loss/train': 1.098861813545227} 08/30/2021 15:46:06 - INFO - __main__ - Step 14774: {'lr': 0.0004908670725374122, 'samples': 2836608, 'steps': 14773, 'loss/train': 1.5781524181365967} 08/30/2021 15:46:06 - INFO - __main__ - Step 14775: {'lr': 0.0004908656512179817, 'samples': 2836800, 'steps': 14774, 'loss/train': 1.9069923162460327} 08/30/2021 15:46:07 - INFO - __main__ - Step 14776: {'lr': 0.0004908642297900209, 'samples': 2836992, 'steps': 14775, 'loss/train': 1.7256543636322021} 08/30/2021 15:46:07 - INFO - __main__ - Step 14777: {'lr': 0.0004908628082535303, 'samples': 2837184, 'steps': 14776, 'loss/train': 1.6065256595611572} 08/30/2021 15:46:07 - INFO - __main__ - Step 14778: {'lr': 0.0004908613866085106, 'samples': 2837376, 'steps': 14777, 'loss/train': 1.8986363410949707} 08/30/2021 15:46:09 - INFO - __main__ - Step 14779: {'lr': 0.0004908599648549626, 'samples': 2837568, 'steps': 14778, 'loss/train': 2.2807629108428955} 08/30/2021 15:46:09 - INFO - __main__ - Step 14780: {'lr': 0.0004908585429928867, 'samples': 2837760, 'steps': 14779, 'loss/train': 1.5258680582046509} 08/30/2021 15:46:10 - INFO - __main__ - Step 14781: {'lr': 0.0004908571210222837, 'samples': 2837952, 'steps': 14780, 'loss/train': 1.6942903995513916} 08/30/2021 15:46:10 - INFO - __main__ - Step 14782: {'lr': 0.0004908556989431543, 'samples': 2838144, 'steps': 14781, 'loss/train': 1.432295322418213} 08/30/2021 15:46:10 - INFO - __main__ - Step 14783: {'lr': 0.0004908542767554988, 'samples': 2838336, 'steps': 14782, 'loss/train': 1.9186686277389526} 08/30/2021 15:46:12 - INFO - __main__ - Step 14784: {'lr': 0.0004908528544593184, 'samples': 2838528, 'steps': 14783, 'loss/train': 1.4333107471466064} 08/30/2021 15:46:12 - INFO - __main__ - Step 14785: {'lr': 0.0004908514320546132, 'samples': 2838720, 'steps': 14784, 'loss/train': 0.1518404483795166} 08/30/2021 15:46:13 - INFO - __main__ - Step 14786: {'lr': 0.000490850009541384, 'samples': 2838912, 'steps': 14785, 'loss/train': 1.9479858875274658} 08/30/2021 15:46:13 - INFO - __main__ - Step 14787: {'lr': 0.0004908485869196317, 'samples': 2839104, 'steps': 14786, 'loss/train': 1.773112416267395} 08/30/2021 15:46:13 - INFO - __main__ - Step 14788: {'lr': 0.0004908471641893566, 'samples': 2839296, 'steps': 14787, 'loss/train': 1.6422818899154663} 08/30/2021 15:46:15 - INFO - __main__ - Step 14789: {'lr': 0.0004908457413505596, 'samples': 2839488, 'steps': 14788, 'loss/train': 1.4594115018844604} 08/30/2021 15:46:15 - INFO - __main__ - Step 14790: {'lr': 0.0004908443184032411, 'samples': 2839680, 'steps': 14789, 'loss/train': 1.9129072427749634} 08/30/2021 15:46:16 - INFO - __main__ - Step 14791: {'lr': 0.0004908428953474019, 'samples': 2839872, 'steps': 14790, 'loss/train': 1.6468173265457153} 08/30/2021 15:46:16 - INFO - __main__ - Step 14792: {'lr': 0.0004908414721830427, 'samples': 2840064, 'steps': 14791, 'loss/train': 1.5827839374542236} 08/30/2021 15:46:16 - INFO - __main__ - Step 14793: {'lr': 0.000490840048910164, 'samples': 2840256, 'steps': 14792, 'loss/train': 1.5768771171569824} 08/30/2021 15:46:18 - INFO - __main__ - Step 14794: {'lr': 0.0004908386255287664, 'samples': 2840448, 'steps': 14793, 'loss/train': 1.356516718864441} 08/30/2021 15:46:19 - INFO - __main__ - Step 14795: {'lr': 0.0004908372020388508, 'samples': 2840640, 'steps': 14794, 'loss/train': 1.7304892539978027} 08/30/2021 15:46:19 - INFO - __main__ - Step 14796: {'lr': 0.0004908357784404175, 'samples': 2840832, 'steps': 14795, 'loss/train': 1.7871992588043213} 08/30/2021 15:46:19 - INFO - __main__ - Step 14797: {'lr': 0.0004908343547334674, 'samples': 2841024, 'steps': 14796, 'loss/train': 0.23681989312171936} 08/30/2021 15:46:20 - INFO - __main__ - Step 14798: {'lr': 0.0004908329309180011, 'samples': 2841216, 'steps': 14797, 'loss/train': 2.157694101333618} 08/30/2021 15:46:22 - INFO - __main__ - Step 14799: {'lr': 0.0004908315069940191, 'samples': 2841408, 'steps': 14798, 'loss/train': 2.138364553451538} 08/30/2021 15:46:22 - INFO - __main__ - Step 14800: {'lr': 0.0004908300829615222, 'samples': 2841600, 'steps': 14799, 'loss/train': 1.54379403591156} 08/30/2021 15:46:23 - INFO - __main__ - Step 14801: {'lr': 0.000490828658820511, 'samples': 2841792, 'steps': 14800, 'loss/train': 1.8878065347671509} 08/30/2021 15:46:23 - INFO - __main__ - Step 14802: {'lr': 0.0004908272345709861, 'samples': 2841984, 'steps': 14801, 'loss/train': 1.5881515741348267} 08/30/2021 15:46:23 - INFO - __main__ - Step 14803: {'lr': 0.0004908258102129481, 'samples': 2842176, 'steps': 14802, 'loss/train': 1.6217010021209717} 08/30/2021 15:46:24 - INFO - __main__ - Step 14804: {'lr': 0.0004908243857463978, 'samples': 2842368, 'steps': 14803, 'loss/train': 1.1415027379989624} 08/30/2021 15:46:25 - INFO - __main__ - Step 14805: {'lr': 0.0004908229611713357, 'samples': 2842560, 'steps': 14804, 'loss/train': 1.365323781967163} 08/30/2021 15:46:26 - INFO - __main__ - Step 14806: {'lr': 0.0004908215364877625, 'samples': 2842752, 'steps': 14805, 'loss/train': 2.133239269256592} 08/30/2021 15:46:26 - INFO - __main__ - Step 14807: {'lr': 0.0004908201116956788, 'samples': 2842944, 'steps': 14806, 'loss/train': 1.3232611417770386} 08/30/2021 15:46:26 - INFO - __main__ - Step 14808: {'lr': 0.0004908186867950854, 'samples': 2843136, 'steps': 14807, 'loss/train': 2.03147292137146} 08/30/2021 15:46:27 - INFO - __main__ - Step 14809: {'lr': 0.0004908172617859826, 'samples': 2843328, 'steps': 14808, 'loss/train': 1.729400396347046} 08/30/2021 15:46:28 - INFO - __main__ - Step 14810: {'lr': 0.0004908158366683714, 'samples': 2843520, 'steps': 14809, 'loss/train': 1.1836036443710327} 08/30/2021 15:46:28 - INFO - __main__ - Step 14811: {'lr': 0.0004908144114422523, 'samples': 2843712, 'steps': 14810, 'loss/train': 1.562010407447815} 08/30/2021 15:46:29 - INFO - __main__ - Step 14812: {'lr': 0.000490812986107626, 'samples': 2843904, 'steps': 14811, 'loss/train': 1.824299931526184} 08/30/2021 15:46:29 - INFO - __main__ - Step 14813: {'lr': 0.000490811560664493, 'samples': 2844096, 'steps': 14812, 'loss/train': 1.4921859502792358} 08/30/2021 15:46:30 - INFO - __main__ - Step 14814: {'lr': 0.000490810135112854, 'samples': 2844288, 'steps': 14813, 'loss/train': 1.8960782289505005} 08/30/2021 15:46:31 - INFO - __main__ - Step 14815: {'lr': 0.0004908087094527097, 'samples': 2844480, 'steps': 14814, 'loss/train': 1.6396292448043823} 08/30/2021 15:46:31 - INFO - __main__ - Step 14816: {'lr': 0.0004908072836840607, 'samples': 2844672, 'steps': 14815, 'loss/train': 1.745307445526123} 08/30/2021 15:46:32 - INFO - __main__ - Step 14817: {'lr': 0.0004908058578069077, 'samples': 2844864, 'steps': 14816, 'loss/train': 1.9213478565216064} 08/30/2021 15:46:32 - INFO - __main__ - Step 14818: {'lr': 0.0004908044318212512, 'samples': 2845056, 'steps': 14817, 'loss/train': 1.8593806028366089} 08/30/2021 15:46:32 - INFO - __main__ - Step 14819: {'lr': 0.000490803005727092, 'samples': 2845248, 'steps': 14818, 'loss/train': 1.5759621858596802} 08/30/2021 15:46:34 - INFO - __main__ - Step 14820: {'lr': 0.0004908015795244307, 'samples': 2845440, 'steps': 14819, 'loss/train': 0.7184984683990479} 08/30/2021 15:46:34 - INFO - __main__ - Step 14821: {'lr': 0.0004908001532132679, 'samples': 2845632, 'steps': 14820, 'loss/train': 1.781602382659912} 08/30/2021 15:46:35 - INFO - __main__ - Step 14822: {'lr': 0.0004907987267936042, 'samples': 2845824, 'steps': 14821, 'loss/train': 1.566272497177124} 08/30/2021 15:46:35 - INFO - __main__ - Step 14823: {'lr': 0.0004907973002654404, 'samples': 2846016, 'steps': 14822, 'loss/train': 1.946954607963562} 08/30/2021 15:46:35 - INFO - __main__ - Step 14824: {'lr': 0.0004907958736287771, 'samples': 2846208, 'steps': 14823, 'loss/train': 1.6509966850280762} 08/30/2021 15:46:36 - INFO - __main__ - Step 14825: {'lr': 0.0004907944468836148, 'samples': 2846400, 'steps': 14824, 'loss/train': 0.7784429788589478} 08/30/2021 15:46:37 - INFO - __main__ - Step 14826: {'lr': 0.0004907930200299543, 'samples': 2846592, 'steps': 14825, 'loss/train': 1.9518537521362305} 08/30/2021 15:46:38 - INFO - __main__ - Step 14827: {'lr': 0.0004907915930677961, 'samples': 2846784, 'steps': 14826, 'loss/train': 1.9460275173187256} 08/30/2021 15:46:38 - INFO - __main__ - Step 14828: {'lr': 0.000490790165997141, 'samples': 2846976, 'steps': 14827, 'loss/train': 1.861189603805542} 08/30/2021 15:46:39 - INFO - __main__ - Step 14829: {'lr': 0.0004907887388179896, 'samples': 2847168, 'steps': 14828, 'loss/train': 1.3093841075897217} 08/30/2021 15:46:39 - INFO - __main__ - Step 14830: {'lr': 0.0004907873115303424, 'samples': 2847360, 'steps': 14829, 'loss/train': 1.8715815544128418} 08/30/2021 15:46:40 - INFO - __main__ - Step 14831: {'lr': 0.0004907858841342002, 'samples': 2847552, 'steps': 14830, 'loss/train': 1.680856466293335} 08/30/2021 15:46:41 - INFO - __main__ - Step 14832: {'lr': 0.0004907844566295637, 'samples': 2847744, 'steps': 14831, 'loss/train': 1.2978127002716064} 08/30/2021 15:46:41 - INFO - __main__ - Step 14833: {'lr': 0.0004907830290164332, 'samples': 2847936, 'steps': 14832, 'loss/train': 0.87298583984375} 08/30/2021 15:46:41 - INFO - __main__ - Step 14834: {'lr': 0.0004907816012948098, 'samples': 2848128, 'steps': 14833, 'loss/train': 1.9467687606811523} 08/30/2021 15:46:42 - INFO - __main__ - Step 14835: {'lr': 0.0004907801734646938, 'samples': 2848320, 'steps': 14834, 'loss/train': 1.938592553138733} 08/30/2021 15:46:43 - INFO - __main__ - Step 14836: {'lr': 0.000490778745526086, 'samples': 2848512, 'steps': 14835, 'loss/train': 1.41289484500885} 08/30/2021 15:46:44 - INFO - __main__ - Step 14837: {'lr': 0.000490777317478987, 'samples': 2848704, 'steps': 14836, 'loss/train': 1.4709492921829224} 08/30/2021 15:46:44 - INFO - __main__ - Step 14838: {'lr': 0.0004907758893233975, 'samples': 2848896, 'steps': 14837, 'loss/train': 1.7636767625808716} 08/30/2021 15:46:44 - INFO - __main__ - Step 14839: {'lr': 0.0004907744610593181, 'samples': 2849088, 'steps': 14838, 'loss/train': 2.2299578189849854} 08/30/2021 15:46:45 - INFO - __main__ - Step 14840: {'lr': 0.0004907730326867495, 'samples': 2849280, 'steps': 14839, 'loss/train': 1.736441731452942} 08/30/2021 15:46:46 - INFO - __main__ - Step 14841: {'lr': 0.0004907716042056921, 'samples': 2849472, 'steps': 14840, 'loss/train': 1.7323708534240723} 08/30/2021 15:46:47 - INFO - __main__ - Step 14842: {'lr': 0.0004907701756161469, 'samples': 2849664, 'steps': 14841, 'loss/train': 1.5519299507141113} 08/30/2021 15:46:47 - INFO - __main__ - Step 14843: {'lr': 0.0004907687469181143, 'samples': 2849856, 'steps': 14842, 'loss/train': 1.7373147010803223} 08/30/2021 15:46:47 - INFO - __main__ - Step 14844: {'lr': 0.000490767318111595, 'samples': 2850048, 'steps': 14843, 'loss/train': 1.595334768295288} 08/30/2021 15:46:48 - INFO - __main__ - Step 14845: {'lr': 0.0004907658891965897, 'samples': 2850240, 'steps': 14844, 'loss/train': 2.56266713142395} 08/30/2021 15:46:50 - INFO - __main__ - Step 14846: {'lr': 0.000490764460173099, 'samples': 2850432, 'steps': 14845, 'loss/train': 2.260747194290161} 08/30/2021 15:46:50 - INFO - __main__ - Step 14847: {'lr': 0.0004907630310411236, 'samples': 2850624, 'steps': 14846, 'loss/train': 1.8458120822906494} 08/30/2021 15:46:51 - INFO - __main__ - Step 14848: {'lr': 0.000490761601800664, 'samples': 2850816, 'steps': 14847, 'loss/train': 1.4040337800979614} 08/30/2021 15:46:51 - INFO - __main__ - Step 14849: {'lr': 0.000490760172451721, 'samples': 2851008, 'steps': 14848, 'loss/train': 1.395462989807129} 08/30/2021 15:46:51 - INFO - __main__ - Step 14850: {'lr': 0.0004907587429942952, 'samples': 2851200, 'steps': 14849, 'loss/train': 1.7758604288101196} 08/30/2021 15:46:52 - INFO - __main__ - Step 14851: {'lr': 0.0004907573134283872, 'samples': 2851392, 'steps': 14850, 'loss/train': 0.34356027841567993} 08/30/2021 15:46:54 - INFO - __main__ - Step 14852: {'lr': 0.0004907558837539976, 'samples': 2851584, 'steps': 14851, 'loss/train': 0.09492310881614685} 08/30/2021 15:46:54 - INFO - __main__ - Step 14853: {'lr': 0.0004907544539711272, 'samples': 2851776, 'steps': 14852, 'loss/train': 2.0711779594421387} 08/30/2021 15:46:54 - INFO - __main__ - Step 14854: {'lr': 0.0004907530240797765, 'samples': 2851968, 'steps': 14853, 'loss/train': 1.9771314859390259} 08/30/2021 15:46:55 - INFO - __main__ - Step 14855: {'lr': 0.0004907515940799463, 'samples': 2852160, 'steps': 14854, 'loss/train': 1.5970083475112915} 08/30/2021 15:46:55 - INFO - __main__ - Step 14856: {'lr': 0.000490750163971637, 'samples': 2852352, 'steps': 14855, 'loss/train': 2.4142673015594482} 08/30/2021 15:46:57 - INFO - __main__ - Step 14857: {'lr': 0.0004907487337548495, 'samples': 2852544, 'steps': 14856, 'loss/train': 1.8362771272659302} 08/30/2021 15:46:57 - INFO - __main__ - Step 14858: {'lr': 0.0004907473034295843, 'samples': 2852736, 'steps': 14857, 'loss/train': 1.6539779901504517} 08/30/2021 15:46:57 - INFO - __main__ - Step 14859: {'lr': 0.0004907458729958422, 'samples': 2852928, 'steps': 14858, 'loss/train': 1.4540634155273438} 08/30/2021 15:46:58 - INFO - __main__ - Step 14860: {'lr': 0.0004907444424536235, 'samples': 2853120, 'steps': 14859, 'loss/train': 2.2673745155334473} 08/30/2021 15:46:58 - INFO - __main__ - Step 14861: {'lr': 0.0004907430118029293, 'samples': 2853312, 'steps': 14860, 'loss/train': 1.9660253524780273} 08/30/2021 15:47:00 - INFO - __main__ - Step 14862: {'lr': 0.0004907415810437598, 'samples': 2853504, 'steps': 14861, 'loss/train': 1.8410143852233887} 08/30/2021 15:47:00 - INFO - __main__ - Step 14863: {'lr': 0.0004907401501761159, 'samples': 2853696, 'steps': 14862, 'loss/train': 1.4958369731903076} 08/30/2021 15:47:00 - INFO - __main__ - Step 14864: {'lr': 0.0004907387191999984, 'samples': 2853888, 'steps': 14863, 'loss/train': 1.8503696918487549} 08/30/2021 15:47:01 - INFO - __main__ - Step 14865: {'lr': 0.0004907372881154075, 'samples': 2854080, 'steps': 14864, 'loss/train': 2.0514066219329834} 08/30/2021 15:47:01 - INFO - __main__ - Step 14866: {'lr': 0.0004907358569223442, 'samples': 2854272, 'steps': 14865, 'loss/train': 1.3077809810638428} 08/30/2021 15:47:01 - INFO - __main__ - Step 14867: {'lr': 0.000490734425620809, 'samples': 2854464, 'steps': 14866, 'loss/train': 1.553786039352417} 08/30/2021 15:47:03 - INFO - __main__ - Step 14868: {'lr': 0.0004907329942108027, 'samples': 2854656, 'steps': 14867, 'loss/train': 1.9677926301956177} 08/30/2021 15:47:04 - INFO - __main__ - Step 14869: {'lr': 0.0004907315626923258, 'samples': 2854848, 'steps': 14868, 'loss/train': 2.0620124340057373} 08/30/2021 15:47:04 - INFO - __main__ - Step 14870: {'lr': 0.0004907301310653789, 'samples': 2855040, 'steps': 14869, 'loss/train': 2.2896623611450195} 08/30/2021 15:47:04 - INFO - __main__ - Step 14871: {'lr': 0.0004907286993299627, 'samples': 2855232, 'steps': 14870, 'loss/train': 2.145505666732788} 08/30/2021 15:47:05 - INFO - __main__ - Step 14872: {'lr': 0.0004907272674860779, 'samples': 2855424, 'steps': 14871, 'loss/train': 1.4551688432693481} 08/30/2021 15:47:06 - INFO - __main__ - Step 14873: {'lr': 0.0004907258355337251, 'samples': 2855616, 'steps': 14872, 'loss/train': 1.6255871057510376} 08/30/2021 15:47:06 - INFO - __main__ - Step 14874: {'lr': 0.0004907244034729049, 'samples': 2855808, 'steps': 14873, 'loss/train': 2.0014379024505615} 08/30/2021 15:47:07 - INFO - __main__ - Step 14875: {'lr': 0.0004907229713036181, 'samples': 2856000, 'steps': 14874, 'loss/train': 1.3547459840774536} 08/30/2021 15:47:07 - INFO - __main__ - Step 14876: {'lr': 0.0004907215390258652, 'samples': 2856192, 'steps': 14875, 'loss/train': 0.11287747323513031} 08/30/2021 15:47:08 - INFO - __main__ - Step 14877: {'lr': 0.0004907201066396469, 'samples': 2856384, 'steps': 14876, 'loss/train': 1.8825775384902954} 08/30/2021 15:47:09 - INFO - __main__ - Step 14878: {'lr': 0.0004907186741449638, 'samples': 2856576, 'steps': 14877, 'loss/train': 1.454063892364502} 08/30/2021 15:47:09 - INFO - __main__ - Step 14879: {'lr': 0.0004907172415418166, 'samples': 2856768, 'steps': 14878, 'loss/train': 1.7126121520996094} 08/30/2021 15:47:10 - INFO - __main__ - Step 14880: {'lr': 0.0004907158088302059, 'samples': 2856960, 'steps': 14879, 'loss/train': 2.1869077682495117} 08/30/2021 15:47:10 - INFO - __main__ - Step 14881: {'lr': 0.0004907143760101325, 'samples': 2857152, 'steps': 14880, 'loss/train': 1.6359323263168335} 08/30/2021 15:47:11 - INFO - __main__ - Step 14882: {'lr': 0.0004907129430815968, 'samples': 2857344, 'steps': 14881, 'loss/train': 1.8957350254058838} 08/30/2021 15:47:12 - INFO - __main__ - Step 14883: {'lr': 0.0004907115100445996, 'samples': 2857536, 'steps': 14882, 'loss/train': 1.642533302307129} 08/30/2021 15:47:12 - INFO - __main__ - Step 14884: {'lr': 0.0004907100768991415, 'samples': 2857728, 'steps': 14883, 'loss/train': 1.667534351348877} 08/30/2021 15:47:13 - INFO - __main__ - Step 14885: {'lr': 0.0004907086436452231, 'samples': 2857920, 'steps': 14884, 'loss/train': 1.2480792999267578} 08/30/2021 15:47:13 - INFO - __main__ - Step 14886: {'lr': 0.0004907072102828451, 'samples': 2858112, 'steps': 14885, 'loss/train': 1.7617106437683105} 08/30/2021 15:47:14 - INFO - __main__ - Step 14887: {'lr': 0.0004907057768120082, 'samples': 2858304, 'steps': 14886, 'loss/train': 1.7082254886627197} 08/30/2021 15:47:15 - INFO - __main__ - Step 14888: {'lr': 0.000490704343232713, 'samples': 2858496, 'steps': 14887, 'loss/train': 1.3154035806655884} 08/30/2021 15:47:16 - INFO - __main__ - Step 14889: {'lr': 0.0004907029095449602, 'samples': 2858688, 'steps': 14888, 'loss/train': 1.9118108749389648} 08/30/2021 15:47:16 - INFO - __main__ - Step 14890: {'lr': 0.0004907014757487503, 'samples': 2858880, 'steps': 14889, 'loss/train': 1.3688138723373413} 08/30/2021 15:47:16 - INFO - __main__ - Step 14891: {'lr': 0.0004907000418440839, 'samples': 2859072, 'steps': 14890, 'loss/train': 1.8967663049697876} 08/30/2021 15:47:17 - INFO - __main__ - Step 14892: {'lr': 0.000490698607830962, 'samples': 2859264, 'steps': 14891, 'loss/train': 1.5738953351974487} 08/30/2021 15:47:17 - INFO - __main__ - Step 14893: {'lr': 0.0004906971737093849, 'samples': 2859456, 'steps': 14892, 'loss/train': 2.4357826709747314} 08/30/2021 15:47:19 - INFO - __main__ - Step 14894: {'lr': 0.0004906957394793534, 'samples': 2859648, 'steps': 14893, 'loss/train': 2.1864922046661377} 08/30/2021 15:47:19 - INFO - __main__ - Step 14895: {'lr': 0.0004906943051408682, 'samples': 2859840, 'steps': 14894, 'loss/train': 1.4296636581420898} 08/30/2021 15:47:19 - INFO - __main__ - Step 14896: {'lr': 0.0004906928706939296, 'samples': 2860032, 'steps': 14895, 'loss/train': 2.200885057449341} 08/30/2021 15:47:20 - INFO - __main__ - Step 14897: {'lr': 0.0004906914361385387, 'samples': 2860224, 'steps': 14896, 'loss/train': 0.5324799418449402} 08/30/2021 15:47:20 - INFO - __main__ - Step 14898: {'lr': 0.0004906900014746959, 'samples': 2860416, 'steps': 14897, 'loss/train': 1.1619032621383667} 08/30/2021 15:47:22 - INFO - __main__ - Step 14899: {'lr': 0.000490688566702402, 'samples': 2860608, 'steps': 14898, 'loss/train': 1.9572542905807495} 08/30/2021 15:47:22 - INFO - __main__ - Step 14900: {'lr': 0.0004906871318216575, 'samples': 2860800, 'steps': 14899, 'loss/train': 1.9340944290161133} 08/30/2021 15:47:22 - INFO - __main__ - Step 14901: {'lr': 0.000490685696832463, 'samples': 2860992, 'steps': 14900, 'loss/train': 1.7831494808197021} 08/30/2021 15:47:23 - INFO - __main__ - Step 14902: {'lr': 0.0004906842617348193, 'samples': 2861184, 'steps': 14901, 'loss/train': 1.7678884267807007} 08/30/2021 15:47:23 - INFO - __main__ - Step 14903: {'lr': 0.000490682826528727, 'samples': 2861376, 'steps': 14902, 'loss/train': 1.1274467706680298} 08/30/2021 15:47:24 - INFO - __main__ - Step 14904: {'lr': 0.0004906813912141868, 'samples': 2861568, 'steps': 14903, 'loss/train': 1.6408709287643433} 08/30/2021 15:47:25 - INFO - __main__ - Step 14905: {'lr': 0.0004906799557911992, 'samples': 2861760, 'steps': 14904, 'loss/train': 1.5663658380508423} 08/30/2021 15:47:25 - INFO - __main__ - Step 14906: {'lr': 0.0004906785202597649, 'samples': 2861952, 'steps': 14905, 'loss/train': 2.121103525161743} 08/30/2021 15:47:26 - INFO - __main__ - Step 14907: {'lr': 0.0004906770846198846, 'samples': 2862144, 'steps': 14906, 'loss/train': 1.4484742879867554} 08/30/2021 15:47:26 - INFO - __main__ - Step 14908: {'lr': 0.0004906756488715589, 'samples': 2862336, 'steps': 14907, 'loss/train': 1.4668267965316772} 08/30/2021 15:47:28 - INFO - __main__ - Step 14909: {'lr': 0.0004906742130147884, 'samples': 2862528, 'steps': 14908, 'loss/train': 1.9839438199996948} 08/30/2021 15:47:29 - INFO - __main__ - Step 14910: {'lr': 0.0004906727770495739, 'samples': 2862720, 'steps': 14909, 'loss/train': 1.2441987991333008} 08/30/2021 15:47:29 - INFO - __main__ - Step 14911: {'lr': 0.000490671340975916, 'samples': 2862912, 'steps': 14910, 'loss/train': 1.6728696823120117} 08/30/2021 15:47:29 - INFO - __main__ - Step 14912: {'lr': 0.0004906699047938153, 'samples': 2863104, 'steps': 14911, 'loss/train': 1.10178804397583} 08/30/2021 15:47:30 - INFO - __main__ - Step 14913: {'lr': 0.0004906684685032724, 'samples': 2863296, 'steps': 14912, 'loss/train': 1.5558502674102783} 08/30/2021 15:47:31 - INFO - __main__ - Step 14914: {'lr': 0.0004906670321042881, 'samples': 2863488, 'steps': 14913, 'loss/train': 1.8439747095108032} 08/30/2021 15:47:32 - INFO - __main__ - Step 14915: {'lr': 0.0004906655955968628, 'samples': 2863680, 'steps': 14914, 'loss/train': 1.6044782400131226} 08/30/2021 15:47:32 - INFO - __main__ - Step 14916: {'lr': 0.0004906641589809973, 'samples': 2863872, 'steps': 14915, 'loss/train': 1.4196702241897583} 08/30/2021 15:47:33 - INFO - __main__ - Step 14917: {'lr': 0.0004906627222566924, 'samples': 2864064, 'steps': 14916, 'loss/train': 1.9430594444274902} 08/30/2021 15:47:33 - INFO - __main__ - Step 14918: {'lr': 0.0004906612854239485, 'samples': 2864256, 'steps': 14917, 'loss/train': 1.3791557550430298} 08/30/2021 15:47:33 - INFO - __main__ - Step 14919: {'lr': 0.0004906598484827663, 'samples': 2864448, 'steps': 14918, 'loss/train': 1.1848090887069702} 08/30/2021 15:47:35 - INFO - __main__ - Step 14920: {'lr': 0.0004906584114331465, 'samples': 2864640, 'steps': 14919, 'loss/train': 1.3372910022735596} 08/30/2021 15:47:35 - INFO - __main__ - Step 14921: {'lr': 0.0004906569742750899, 'samples': 2864832, 'steps': 14920, 'loss/train': 1.316491723060608} 08/30/2021 15:47:35 - INFO - __main__ - Step 14922: {'lr': 0.0004906555370085968, 'samples': 2865024, 'steps': 14921, 'loss/train': 1.4104100465774536} 08/30/2021 15:47:36 - INFO - __main__ - Step 14923: {'lr': 0.000490654099633668, 'samples': 2865216, 'steps': 14922, 'loss/train': 1.2647488117218018} 08/30/2021 15:47:36 - INFO - __main__ - Step 14924: {'lr': 0.0004906526621503043, 'samples': 2865408, 'steps': 14923, 'loss/train': 1.5276551246643066} 08/30/2021 15:47:38 - INFO - __main__ - Step 14925: {'lr': 0.0004906512245585062, 'samples': 2865600, 'steps': 14924, 'loss/train': 1.7782212495803833} 08/30/2021 15:47:38 - INFO - __main__ - Step 14926: {'lr': 0.0004906497868582743, 'samples': 2865792, 'steps': 14925, 'loss/train': 0.7870326638221741} 08/30/2021 15:47:39 - INFO - __main__ - Step 14927: {'lr': 0.0004906483490496093, 'samples': 2865984, 'steps': 14926, 'loss/train': 2.2952516078948975} 08/30/2021 15:47:39 - INFO - __main__ - Step 14928: {'lr': 0.000490646911132512, 'samples': 2866176, 'steps': 14927, 'loss/train': 2.0275893211364746} 08/30/2021 15:47:39 - INFO - __main__ - Step 14929: {'lr': 0.0004906454731069828, 'samples': 2866368, 'steps': 14928, 'loss/train': 1.9735183715820312} 08/30/2021 15:47:41 - INFO - __main__ - Step 14930: {'lr': 0.0004906440349730226, 'samples': 2866560, 'steps': 14929, 'loss/train': 2.132662534713745} 08/30/2021 15:47:41 - INFO - __main__ - Step 14931: {'lr': 0.0004906425967306317, 'samples': 2866752, 'steps': 14930, 'loss/train': 1.2584959268569946} 08/30/2021 15:47:42 - INFO - __main__ - Step 14932: {'lr': 0.0004906411583798112, 'samples': 2866944, 'steps': 14931, 'loss/train': 3.4257090091705322} 08/30/2021 15:47:42 - INFO - __main__ - Step 14933: {'lr': 0.0004906397199205614, 'samples': 2867136, 'steps': 14932, 'loss/train': 1.8130868673324585} 08/30/2021 15:47:42 - INFO - __main__ - Step 14934: {'lr': 0.000490638281352883, 'samples': 2867328, 'steps': 14933, 'loss/train': 1.9742066860198975} 08/30/2021 15:47:44 - INFO - __main__ - Step 14935: {'lr': 0.0004906368426767767, 'samples': 2867520, 'steps': 14934, 'loss/train': 1.6100530624389648} 08/30/2021 15:47:45 - INFO - __main__ - Step 14936: {'lr': 0.0004906354038922432, 'samples': 2867712, 'steps': 14935, 'loss/train': 2.1630990505218506} 08/30/2021 15:47:45 - INFO - __main__ - Step 14937: {'lr': 0.000490633964999283, 'samples': 2867904, 'steps': 14936, 'loss/train': 2.1897051334381104} 08/30/2021 15:47:45 - INFO - __main__ - Step 14938: {'lr': 0.000490632525997897, 'samples': 2868096, 'steps': 14937, 'loss/train': 1.8568459749221802} 08/30/2021 15:47:46 - INFO - __main__ - Step 14939: {'lr': 0.0004906310868880856, 'samples': 2868288, 'steps': 14938, 'loss/train': 1.7828978300094604} 08/30/2021 15:47:46 - INFO - __main__ - Step 14940: {'lr': 0.0004906296476698496, 'samples': 2868480, 'steps': 14939, 'loss/train': 1.3063057661056519} 08/30/2021 15:47:48 - INFO - __main__ - Step 14941: {'lr': 0.0004906282083431897, 'samples': 2868672, 'steps': 14940, 'loss/train': 1.8772317171096802} 08/30/2021 15:47:48 - INFO - __main__ - Step 14942: {'lr': 0.0004906267689081063, 'samples': 2868864, 'steps': 14941, 'loss/train': 0.2673923075199127} 08/30/2021 15:47:49 - INFO - __main__ - Step 14943: {'lr': 0.0004906253293646002, 'samples': 2869056, 'steps': 14942, 'loss/train': 1.1200165748596191} 08/30/2021 15:47:49 - INFO - __main__ - Step 14944: {'lr': 0.0004906238897126721, 'samples': 2869248, 'steps': 14943, 'loss/train': 1.26520836353302} 08/30/2021 15:47:49 - INFO - __main__ - Step 14945: {'lr': 0.0004906224499523225, 'samples': 2869440, 'steps': 14944, 'loss/train': 2.1648335456848145} 08/30/2021 15:47:51 - INFO - __main__ - Step 14946: {'lr': 0.0004906210100835522, 'samples': 2869632, 'steps': 14945, 'loss/train': 1.5770320892333984} 08/30/2021 15:47:51 - INFO - __main__ - Step 14947: {'lr': 0.0004906195701063617, 'samples': 2869824, 'steps': 14946, 'loss/train': 2.1350629329681396} 08/30/2021 15:47:52 - INFO - __main__ - Step 14948: {'lr': 0.0004906181300207518, 'samples': 2870016, 'steps': 14947, 'loss/train': 0.7200288772583008} 08/30/2021 15:47:52 - INFO - __main__ - Step 14949: {'lr': 0.0004906166898267231, 'samples': 2870208, 'steps': 14948, 'loss/train': 1.9455991983413696} 08/30/2021 15:47:52 - INFO - __main__ - Step 14950: {'lr': 0.0004906152495242763, 'samples': 2870400, 'steps': 14949, 'loss/train': 1.9666111469268799} 08/30/2021 15:47:54 - INFO - __main__ - Step 14951: {'lr': 0.0004906138091134118, 'samples': 2870592, 'steps': 14950, 'loss/train': 1.8162511587142944} 08/30/2021 15:47:54 - INFO - __main__ - Step 14952: {'lr': 0.0004906123685941306, 'samples': 2870784, 'steps': 14951, 'loss/train': 2.864201784133911} 08/30/2021 15:47:55 - INFO - __main__ - Step 14953: {'lr': 0.000490610927966433, 'samples': 2870976, 'steps': 14952, 'loss/train': 2.0321316719055176} 08/30/2021 15:47:55 - INFO - __main__ - Step 14954: {'lr': 0.00049060948723032, 'samples': 2871168, 'steps': 14953, 'loss/train': 1.412567138671875} 08/30/2021 15:47:56 - INFO - __main__ - Step 14955: {'lr': 0.000490608046385792, 'samples': 2871360, 'steps': 14954, 'loss/train': 0.8047583699226379} 08/30/2021 15:47:57 - INFO - __main__ - Step 14956: {'lr': 0.0004906066054328498, 'samples': 2871552, 'steps': 14955, 'loss/train': 1.4855256080627441} 08/30/2021 15:47:57 - INFO - __main__ - Step 14957: {'lr': 0.0004906051643714939, 'samples': 2871744, 'steps': 14956, 'loss/train': 2.1654229164123535} 08/30/2021 15:47:58 - INFO - __main__ - Step 14958: {'lr': 0.000490603723201725, 'samples': 2871936, 'steps': 14957, 'loss/train': 1.1873350143432617} 08/30/2021 15:47:58 - INFO - __main__ - Step 14959: {'lr': 0.0004906022819235438, 'samples': 2872128, 'steps': 14958, 'loss/train': 1.7369675636291504} 08/30/2021 15:47:59 - INFO - __main__ - Step 14960: {'lr': 0.000490600840536951, 'samples': 2872320, 'steps': 14959, 'loss/train': 1.7949846982955933} 08/30/2021 15:48:01 - INFO - __main__ - Step 14961: {'lr': 0.0004905993990419471, 'samples': 2872512, 'steps': 14960, 'loss/train': 1.988272786140442} 08/30/2021 15:48:01 - INFO - __main__ - Step 14962: {'lr': 0.0004905979574385328, 'samples': 2872704, 'steps': 14961, 'loss/train': 2.0101239681243896} 08/30/2021 15:48:01 - INFO - __main__ - Step 14963: {'lr': 0.0004905965157267088, 'samples': 2872896, 'steps': 14962, 'loss/train': 1.64951491355896} 08/30/2021 15:48:02 - INFO - __main__ - Step 14964: {'lr': 0.0004905950739064758, 'samples': 2873088, 'steps': 14963, 'loss/train': 1.8198285102844238} 08/30/2021 15:48:02 - INFO - __main__ - Step 14965: {'lr': 0.0004905936319778343, 'samples': 2873280, 'steps': 14964, 'loss/train': 1.8101497888565063} 08/30/2021 15:48:02 - INFO - __main__ - Step 14966: {'lr': 0.000490592189940785, 'samples': 2873472, 'steps': 14965, 'loss/train': 1.6880543231964111} 08/30/2021 15:48:04 - INFO - __main__ - Step 14967: {'lr': 0.0004905907477953286, 'samples': 2873664, 'steps': 14966, 'loss/train': 1.7889503240585327} 08/30/2021 15:48:04 - INFO - __main__ - Step 14968: {'lr': 0.0004905893055414658, 'samples': 2873856, 'steps': 14967, 'loss/train': 1.9825594425201416} 08/30/2021 15:48:05 - INFO - __main__ - Step 14969: {'lr': 0.0004905878631791971, 'samples': 2874048, 'steps': 14968, 'loss/train': 1.815059781074524} 08/30/2021 15:48:05 - INFO - __main__ - Step 14970: {'lr': 0.0004905864207085232, 'samples': 2874240, 'steps': 14969, 'loss/train': 1.415787935256958} 08/30/2021 15:48:07 - INFO - __main__ - Step 14971: {'lr': 0.0004905849781294448, 'samples': 2874432, 'steps': 14970, 'loss/train': 1.7248291969299316} 08/30/2021 15:48:07 - INFO - __main__ - Step 14972: {'lr': 0.0004905835354419625, 'samples': 2874624, 'steps': 14971, 'loss/train': 1.9839503765106201} 08/30/2021 15:48:07 - INFO - __main__ - Step 14973: {'lr': 0.0004905820926460769, 'samples': 2874816, 'steps': 14972, 'loss/train': 1.7970905303955078} 08/30/2021 15:48:08 - INFO - __main__ - Step 14974: {'lr': 0.0004905806497417888, 'samples': 2875008, 'steps': 14973, 'loss/train': 1.7530096769332886} 08/30/2021 15:48:08 - INFO - __main__ - Step 14975: {'lr': 0.0004905792067290988, 'samples': 2875200, 'steps': 14974, 'loss/train': 1.4415957927703857} 08/30/2021 15:48:08 - INFO - __main__ - Step 14976: {'lr': 0.0004905777636080075, 'samples': 2875392, 'steps': 14975, 'loss/train': 1.703970193862915} 08/30/2021 15:48:10 - INFO - __main__ - Step 14977: {'lr': 0.0004905763203785157, 'samples': 2875584, 'steps': 14976, 'loss/train': 1.4527407884597778} 08/30/2021 15:48:10 - INFO - __main__ - Step 14978: {'lr': 0.0004905748770406237, 'samples': 2875776, 'steps': 14977, 'loss/train': 1.8297884464263916} 08/30/2021 15:48:11 - INFO - __main__ - Step 14979: {'lr': 0.0004905734335943325, 'samples': 2875968, 'steps': 14978, 'loss/train': 2.642838478088379} 08/30/2021 15:48:11 - INFO - __main__ - Step 14980: {'lr': 0.0004905719900396426, 'samples': 2876160, 'steps': 14979, 'loss/train': 1.9550862312316895} 08/30/2021 15:48:11 - INFO - __main__ - Step 14981: {'lr': 0.0004905705463765546, 'samples': 2876352, 'steps': 14980, 'loss/train': 2.4028172492980957} 08/30/2021 15:48:13 - INFO - __main__ - Step 14982: {'lr': 0.0004905691026050692, 'samples': 2876544, 'steps': 14981, 'loss/train': 0.9124690890312195} 08/30/2021 15:48:13 - INFO - __main__ - Step 14983: {'lr': 0.0004905676587251873, 'samples': 2876736, 'steps': 14982, 'loss/train': 1.3576433658599854} 08/30/2021 15:48:14 - INFO - __main__ - Step 14984: {'lr': 0.0004905662147369091, 'samples': 2876928, 'steps': 14983, 'loss/train': 1.7100127935409546} 08/30/2021 15:48:14 - INFO - __main__ - Step 14985: {'lr': 0.0004905647706402356, 'samples': 2877120, 'steps': 14984, 'loss/train': 1.6217868328094482} 08/30/2021 15:48:14 - INFO - __main__ - Step 14986: {'lr': 0.0004905633264351673, 'samples': 2877312, 'steps': 14985, 'loss/train': 1.4821100234985352} 08/30/2021 15:48:16 - INFO - __main__ - Step 14987: {'lr': 0.0004905618821217048, 'samples': 2877504, 'steps': 14986, 'loss/train': 2.151357412338257} 08/30/2021 15:48:16 - INFO - __main__ - Step 14988: {'lr': 0.0004905604376998489, 'samples': 2877696, 'steps': 14987, 'loss/train': 1.3934756517410278} 08/30/2021 15:48:17 - INFO - __main__ - Step 14989: {'lr': 0.0004905589931696002, 'samples': 2877888, 'steps': 14988, 'loss/train': 1.4435477256774902} 08/30/2021 15:48:17 - INFO - __main__ - Step 14990: {'lr': 0.0004905575485309593, 'samples': 2878080, 'steps': 14989, 'loss/train': 1.2365061044692993} 08/30/2021 15:48:17 - INFO - __main__ - Step 14991: {'lr': 0.0004905561037839269, 'samples': 2878272, 'steps': 14990, 'loss/train': 0.9699716567993164} 08/30/2021 15:48:19 - INFO - __main__ - Step 14992: {'lr': 0.0004905546589285036, 'samples': 2878464, 'steps': 14991, 'loss/train': 1.7452621459960938} 08/30/2021 15:48:19 - INFO - __main__ - Step 14993: {'lr': 0.0004905532139646901, 'samples': 2878656, 'steps': 14992, 'loss/train': 1.7208856344223022} 08/30/2021 15:48:20 - INFO - __main__ - Step 14994: {'lr': 0.000490551768892487, 'samples': 2878848, 'steps': 14993, 'loss/train': 1.2783823013305664} 08/30/2021 15:48:20 - INFO - __main__ - Step 14995: {'lr': 0.000490550323711895, 'samples': 2879040, 'steps': 14994, 'loss/train': 2.156923532485962} 08/30/2021 15:48:20 - INFO - __main__ - Step 14996: {'lr': 0.0004905488784229147, 'samples': 2879232, 'steps': 14995, 'loss/train': 1.968981385231018} 08/30/2021 15:48:23 - INFO - __main__ - Step 14997: {'lr': 0.000490547433025547, 'samples': 2879424, 'steps': 14996, 'loss/train': 1.880060076713562} 08/30/2021 15:48:23 - INFO - __main__ - Step 14998: {'lr': 0.0004905459875197921, 'samples': 2879616, 'steps': 14997, 'loss/train': 1.4786137342453003} 08/30/2021 15:48:23 - INFO - __main__ - Step 14999: {'lr': 0.000490544541905651, 'samples': 2879808, 'steps': 14998, 'loss/train': 0.6797895431518555} 08/30/2021 15:48:24 - INFO - __main__ - Step 15000: {'lr': 0.0004905430961831242, 'samples': 2880000, 'steps': 14999, 'loss/train': 0.09316903352737427} 08/30/2021 15:48:24 - INFO - __main__ - Evaluating model checkpoint 08/30/2021 15:57:02 - INFO - __main__ - Step 15000: {'loss/eval': 1.5676782131195068, 'perplexity': 4.795501232147217} 08/30/2021 15:57:02 - INFO - __main__ - Saving model checkpoint 08/30/2021 15:57:37 - INFO - __main__ - Step 15001: {'lr': 0.0004905416503522123, 'samples': 2880192, 'steps': 15000, 'loss/train': 0.08897807449102402} 08/30/2021 15:57:37 - INFO - __main__ - Step 15002: {'lr': 0.0004905402044129162, 'samples': 2880384, 'steps': 15001, 'loss/train': 1.7169634103775024} 08/30/2021 15:57:38 - INFO - __main__ - Step 15003: {'lr': 0.0004905387583652363, 'samples': 2880576, 'steps': 15002, 'loss/train': 2.079348564147949} 08/30/2021 15:57:39 - INFO - __main__ - Step 15004: {'lr': 0.0004905373122091734, 'samples': 2880768, 'steps': 15003, 'loss/train': 1.7418956756591797} 08/30/2021 15:57:40 - INFO - __main__ - Step 15005: {'lr': 0.0004905358659447281, 'samples': 2880960, 'steps': 15004, 'loss/train': 1.5207520723342896} 08/30/2021 15:57:40 - INFO - __main__ - Step 15006: {'lr': 0.000490534419571901, 'samples': 2881152, 'steps': 15005, 'loss/train': 1.5853830575942993} 08/30/2021 15:57:40 - INFO - __main__ - Step 15007: {'lr': 0.0004905329730906929, 'samples': 2881344, 'steps': 15006, 'loss/train': 1.8985745906829834} 08/30/2021 15:57:41 - INFO - __main__ - Step 15008: {'lr': 0.0004905315265011043, 'samples': 2881536, 'steps': 15007, 'loss/train': 1.9557712078094482} 08/30/2021 15:57:42 - INFO - __main__ - Step 15009: {'lr': 0.0004905300798031359, 'samples': 2881728, 'steps': 15008, 'loss/train': 1.9216936826705933} 08/30/2021 15:57:43 - INFO - __main__ - Step 15010: {'lr': 0.0004905286329967883, 'samples': 2881920, 'steps': 15009, 'loss/train': 1.2003295421600342} 08/30/2021 15:57:43 - INFO - __main__ - Step 15011: {'lr': 0.0004905271860820622, 'samples': 2882112, 'steps': 15010, 'loss/train': 2.3111867904663086} 08/30/2021 15:57:43 - INFO - __main__ - Step 15012: {'lr': 0.0004905257390589585, 'samples': 2882304, 'steps': 15011, 'loss/train': 1.5301975011825562} 08/30/2021 15:57:44 - INFO - __main__ - Step 15013: {'lr': 0.0004905242919274774, 'samples': 2882496, 'steps': 15012, 'loss/train': 1.2972427606582642} 08/30/2021 15:57:45 - INFO - __main__ - Step 15014: {'lr': 0.0004905228446876197, 'samples': 2882688, 'steps': 15013, 'loss/train': 1.50941002368927} 08/30/2021 15:57:46 - INFO - __main__ - Step 15015: {'lr': 0.0004905213973393863, 'samples': 2882880, 'steps': 15014, 'loss/train': 1.6621195077896118} 08/30/2021 15:57:46 - INFO - __main__ - Step 15016: {'lr': 0.0004905199498827776, 'samples': 2883072, 'steps': 15015, 'loss/train': 1.812369704246521} 08/30/2021 15:57:46 - INFO - __main__ - Step 15017: {'lr': 0.0004905185023177942, 'samples': 2883264, 'steps': 15016, 'loss/train': 1.7890472412109375} 08/30/2021 15:57:47 - INFO - __main__ - Step 15018: {'lr': 0.0004905170546444371, 'samples': 2883456, 'steps': 15017, 'loss/train': 1.4666922092437744} 08/30/2021 15:57:49 - INFO - __main__ - Step 15019: {'lr': 0.0004905156068627065, 'samples': 2883648, 'steps': 15018, 'loss/train': 1.536946177482605} 08/30/2021 15:57:49 - INFO - __main__ - Step 15020: {'lr': 0.0004905141589726035, 'samples': 2883840, 'steps': 15019, 'loss/train': 1.8957767486572266} 08/30/2021 15:57:50 - INFO - __main__ - Step 15021: {'lr': 0.0004905127109741284, 'samples': 2884032, 'steps': 15020, 'loss/train': 1.2258646488189697} 08/30/2021 15:57:50 - INFO - __main__ - Step 15022: {'lr': 0.000490511262867282, 'samples': 2884224, 'steps': 15021, 'loss/train': 1.2116807699203491} 08/30/2021 15:57:50 - INFO - __main__ - Step 15023: {'lr': 0.000490509814652065, 'samples': 2884416, 'steps': 15022, 'loss/train': 1.846852421760559} 08/30/2021 15:57:52 - INFO - __main__ - Step 15024: {'lr': 0.0004905083663284779, 'samples': 2884608, 'steps': 15023, 'loss/train': 1.4833589792251587} 08/30/2021 15:57:52 - INFO - __main__ - Step 15025: {'lr': 0.0004905069178965214, 'samples': 2884800, 'steps': 15024, 'loss/train': 1.6528632640838623} 08/30/2021 15:57:53 - INFO - __main__ - Step 15026: {'lr': 0.0004905054693561963, 'samples': 2884992, 'steps': 15025, 'loss/train': 1.6975077390670776} 08/30/2021 15:57:53 - INFO - __main__ - Step 15027: {'lr': 0.0004905040207075032, 'samples': 2885184, 'steps': 15026, 'loss/train': 1.3338165283203125} 08/30/2021 15:57:53 - INFO - __main__ - Step 15028: {'lr': 0.0004905025719504426, 'samples': 2885376, 'steps': 15027, 'loss/train': 1.818396806716919} 08/30/2021 15:57:54 - INFO - __main__ - Step 15029: {'lr': 0.0004905011230850152, 'samples': 2885568, 'steps': 15028, 'loss/train': 1.5168710947036743} 08/30/2021 15:57:56 - INFO - __main__ - Step 15030: {'lr': 0.0004904996741112218, 'samples': 2885760, 'steps': 15029, 'loss/train': 1.5877747535705566} 08/30/2021 15:57:56 - INFO - __main__ - Step 15031: {'lr': 0.0004904982250290629, 'samples': 2885952, 'steps': 15030, 'loss/train': 1.7008051872253418} 08/30/2021 15:57:56 - INFO - __main__ - Step 15032: {'lr': 0.0004904967758385393, 'samples': 2886144, 'steps': 15031, 'loss/train': 1.7522859573364258} 08/30/2021 15:57:57 - INFO - __main__ - Step 15033: {'lr': 0.0004904953265396515, 'samples': 2886336, 'steps': 15032, 'loss/train': 0.14056184887886047} 08/30/2021 15:57:57 - INFO - __main__ - Step 15034: {'lr': 0.0004904938771324002, 'samples': 2886528, 'steps': 15033, 'loss/train': 1.7451437711715698} 08/30/2021 15:57:59 - INFO - __main__ - Step 15035: {'lr': 0.0004904924276167861, 'samples': 2886720, 'steps': 15034, 'loss/train': 1.7355155944824219} 08/30/2021 15:57:59 - INFO - __main__ - Step 15036: {'lr': 0.0004904909779928099, 'samples': 2886912, 'steps': 15035, 'loss/train': 1.4620782136917114} 08/30/2021 15:57:59 - INFO - __main__ - Step 15037: {'lr': 0.000490489528260472, 'samples': 2887104, 'steps': 15036, 'loss/train': 0.44157060980796814} 08/30/2021 15:58:00 - INFO - __main__ - Step 15038: {'lr': 0.0004904880784197734, 'samples': 2887296, 'steps': 15037, 'loss/train': 1.6056537628173828} 08/30/2021 15:58:00 - INFO - __main__ - Step 15039: {'lr': 0.0004904866284707144, 'samples': 2887488, 'steps': 15038, 'loss/train': 2.031805992126465} 08/30/2021 15:58:02 - INFO - __main__ - Step 15040: {'lr': 0.000490485178413296, 'samples': 2887680, 'steps': 15039, 'loss/train': 1.5526639223098755} 08/30/2021 15:58:02 - INFO - __main__ - Step 15041: {'lr': 0.0004904837282475186, 'samples': 2887872, 'steps': 15040, 'loss/train': 2.158902406692505} 08/30/2021 15:58:03 - INFO - __main__ - Step 15042: {'lr': 0.000490482277973383, 'samples': 2888064, 'steps': 15041, 'loss/train': 1.7040448188781738} 08/30/2021 15:58:03 - INFO - __main__ - Step 15043: {'lr': 0.0004904808275908898, 'samples': 2888256, 'steps': 15042, 'loss/train': 0.609427809715271} 08/30/2021 15:58:03 - INFO - __main__ - Step 15044: {'lr': 0.0004904793771000396, 'samples': 2888448, 'steps': 15043, 'loss/train': 1.9580683708190918} 08/30/2021 15:58:05 - INFO - __main__ - Step 15045: {'lr': 0.0004904779265008331, 'samples': 2888640, 'steps': 15044, 'loss/train': 1.416972041130066} 08/30/2021 15:58:05 - INFO - __main__ - Step 15046: {'lr': 0.000490476475793271, 'samples': 2888832, 'steps': 15045, 'loss/train': 1.914841890335083} 08/30/2021 15:58:06 - INFO - __main__ - Step 15047: {'lr': 0.0004904750249773538, 'samples': 2889024, 'steps': 15046, 'loss/train': 1.60141122341156} 08/30/2021 15:58:06 - INFO - __main__ - Step 15048: {'lr': 0.0004904735740530825, 'samples': 2889216, 'steps': 15047, 'loss/train': 1.4357203245162964} 08/30/2021 15:58:06 - INFO - __main__ - Step 15049: {'lr': 0.0004904721230204573, 'samples': 2889408, 'steps': 15048, 'loss/train': 2.2410624027252197} 08/30/2021 15:58:08 - INFO - __main__ - Step 15050: {'lr': 0.0004904706718794791, 'samples': 2889600, 'steps': 15049, 'loss/train': 1.1474930047988892} 08/30/2021 15:58:09 - INFO - __main__ - Step 15051: {'lr': 0.0004904692206301487, 'samples': 2889792, 'steps': 15050, 'loss/train': 1.4560447931289673} 08/30/2021 15:58:09 - INFO - __main__ - Step 15052: {'lr': 0.0004904677692724664, 'samples': 2889984, 'steps': 15051, 'loss/train': 1.4431084394454956} 08/30/2021 15:58:09 - INFO - __main__ - Step 15053: {'lr': 0.000490466317806433, 'samples': 2890176, 'steps': 15052, 'loss/train': 1.6216411590576172} 08/30/2021 15:58:10 - INFO - __main__ - Step 15054: {'lr': 0.0004904648662320493, 'samples': 2890368, 'steps': 15053, 'loss/train': 0.1565411537885666} 08/30/2021 15:58:11 - INFO - __main__ - Step 15055: {'lr': 0.0004904634145493159, 'samples': 2890560, 'steps': 15054, 'loss/train': 1.1482092142105103} 08/30/2021 15:58:12 - INFO - __main__ - Step 15056: {'lr': 0.0004904619627582332, 'samples': 2890752, 'steps': 15055, 'loss/train': 1.7334765195846558} 08/30/2021 15:58:12 - INFO - __main__ - Step 15057: {'lr': 0.0004904605108588023, 'samples': 2890944, 'steps': 15056, 'loss/train': 1.4141312837600708} 08/30/2021 15:58:12 - INFO - __main__ - Step 15058: {'lr': 0.0004904590588510234, 'samples': 2891136, 'steps': 15057, 'loss/train': 1.9265528917312622} 08/30/2021 15:58:13 - INFO - __main__ - Step 15059: {'lr': 0.0004904576067348975, 'samples': 2891328, 'steps': 15058, 'loss/train': 2.2109851837158203} 08/30/2021 15:58:13 - INFO - __main__ - Step 15060: {'lr': 0.000490456154510425, 'samples': 2891520, 'steps': 15059, 'loss/train': 2.0628292560577393} 08/30/2021 15:58:15 - INFO - __main__ - Step 15061: {'lr': 0.0004904547021776067, 'samples': 2891712, 'steps': 15060, 'loss/train': 1.9347633123397827} 08/30/2021 15:58:15 - INFO - __main__ - Step 15062: {'lr': 0.0004904532497364432, 'samples': 2891904, 'steps': 15061, 'loss/train': 1.5641708374023438} 08/30/2021 15:58:15 - INFO - __main__ - Step 15063: {'lr': 0.0004904517971869352, 'samples': 2892096, 'steps': 15062, 'loss/train': 1.079559326171875} 08/30/2021 15:58:16 - INFO - __main__ - Step 15064: {'lr': 0.0004904503445290833, 'samples': 2892288, 'steps': 15063, 'loss/train': 1.13528573513031} 08/30/2021 15:58:16 - INFO - __main__ - Step 15065: {'lr': 0.0004904488917628882, 'samples': 2892480, 'steps': 15064, 'loss/train': 2.182119607925415} 08/30/2021 15:58:18 - INFO - __main__ - Step 15066: {'lr': 0.0004904474388883507, 'samples': 2892672, 'steps': 15065, 'loss/train': 1.4964021444320679} 08/30/2021 15:58:18 - INFO - __main__ - Step 15067: {'lr': 0.000490445985905471, 'samples': 2892864, 'steps': 15066, 'loss/train': 1.062370777130127} 08/30/2021 15:58:18 - INFO - __main__ - Step 15068: {'lr': 0.0004904445328142503, 'samples': 2893056, 'steps': 15067, 'loss/train': 0.9581953287124634} 08/30/2021 15:58:19 - INFO - __main__ - Step 15069: {'lr': 0.0004904430796146889, 'samples': 2893248, 'steps': 15068, 'loss/train': 1.8068184852600098} 08/30/2021 15:58:19 - INFO - __main__ - Step 15070: {'lr': 0.0004904416263067876, 'samples': 2893440, 'steps': 15069, 'loss/train': 1.8006515502929688} 08/30/2021 15:58:21 - INFO - __main__ - Step 15071: {'lr': 0.0004904401728905469, 'samples': 2893632, 'steps': 15070, 'loss/train': 1.647088646888733} 08/30/2021 15:58:22 - INFO - __main__ - Step 15072: {'lr': 0.0004904387193659677, 'samples': 2893824, 'steps': 15071, 'loss/train': 1.7353768348693848} 08/30/2021 15:58:22 - INFO - __main__ - Step 15073: {'lr': 0.0004904372657330504, 'samples': 2894016, 'steps': 15072, 'loss/train': 1.6333556175231934} 08/30/2021 15:58:22 - INFO - __main__ - Step 15074: {'lr': 0.0004904358119917959, 'samples': 2894208, 'steps': 15073, 'loss/train': 1.9115346670150757} 08/30/2021 15:58:23 - INFO - __main__ - Step 15075: {'lr': 0.0004904343581422047, 'samples': 2894400, 'steps': 15074, 'loss/train': 1.6262946128845215} 08/30/2021 15:58:24 - INFO - __main__ - Step 15076: {'lr': 0.0004904329041842774, 'samples': 2894592, 'steps': 15075, 'loss/train': 2.36826229095459} 08/30/2021 15:58:25 - INFO - __main__ - Step 15077: {'lr': 0.0004904314501180148, 'samples': 2894784, 'steps': 15076, 'loss/train': 1.9142673015594482} 08/30/2021 15:58:25 - INFO - __main__ - Step 15078: {'lr': 0.0004904299959434175, 'samples': 2894976, 'steps': 15077, 'loss/train': 1.7328768968582153} 08/30/2021 15:58:25 - INFO - __main__ - Step 15079: {'lr': 0.0004904285416604862, 'samples': 2895168, 'steps': 15078, 'loss/train': 1.6171680688858032} 08/30/2021 15:58:26 - INFO - __main__ - Step 15080: {'lr': 0.0004904270872692215, 'samples': 2895360, 'steps': 15079, 'loss/train': 2.092799663543701} 08/30/2021 15:58:27 - INFO - __main__ - Step 15081: {'lr': 0.0004904256327696241, 'samples': 2895552, 'steps': 15080, 'loss/train': 1.2302974462509155} 08/30/2021 15:58:28 - INFO - __main__ - Step 15082: {'lr': 0.0004904241781616945, 'samples': 2895744, 'steps': 15081, 'loss/train': 1.1482905149459839} 08/30/2021 15:58:28 - INFO - __main__ - Step 15083: {'lr': 0.0004904227234454335, 'samples': 2895936, 'steps': 15082, 'loss/train': 1.9209469556808472} 08/30/2021 15:58:28 - INFO - __main__ - Step 15084: {'lr': 0.0004904212686208418, 'samples': 2896128, 'steps': 15083, 'loss/train': 2.028625011444092} 08/30/2021 15:58:29 - INFO - __main__ - Step 15085: {'lr': 0.00049041981368792, 'samples': 2896320, 'steps': 15084, 'loss/train': 1.8900392055511475} 08/30/2021 15:58:29 - INFO - __main__ - Step 15086: {'lr': 0.0004904183586466686, 'samples': 2896512, 'steps': 15085, 'loss/train': 2.02756404876709} 08/30/2021 15:58:31 - INFO - __main__ - Step 15087: {'lr': 0.0004904169034970885, 'samples': 2896704, 'steps': 15086, 'loss/train': 1.0059603452682495} 08/30/2021 15:58:31 - INFO - __main__ - Step 15088: {'lr': 0.0004904154482391803, 'samples': 2896896, 'steps': 15087, 'loss/train': 1.565056562423706} 08/30/2021 15:58:31 - INFO - __main__ - Step 15089: {'lr': 0.0004904139928729445, 'samples': 2897088, 'steps': 15088, 'loss/train': 1.6708370447158813} 08/30/2021 15:58:32 - INFO - __main__ - Step 15090: {'lr': 0.0004904125373983819, 'samples': 2897280, 'steps': 15089, 'loss/train': 1.9066559076309204} 08/30/2021 15:58:32 - INFO - __main__ - Step 15091: {'lr': 0.0004904110818154931, 'samples': 2897472, 'steps': 15090, 'loss/train': 1.757454514503479} 08/30/2021 15:58:33 - INFO - __main__ - Step 15092: {'lr': 0.0004904096261242789, 'samples': 2897664, 'steps': 15091, 'loss/train': 1.1484358310699463} 08/30/2021 15:58:34 - INFO - __main__ - Step 15093: {'lr': 0.0004904081703247397, 'samples': 2897856, 'steps': 15092, 'loss/train': 1.4675343036651611} 08/30/2021 15:58:34 - INFO - __main__ - Step 15094: {'lr': 0.0004904067144168763, 'samples': 2898048, 'steps': 15093, 'loss/train': 1.3540998697280884} 08/30/2021 15:58:35 - INFO - __main__ - Step 15095: {'lr': 0.0004904052584006895, 'samples': 2898240, 'steps': 15094, 'loss/train': 2.115405321121216} 08/30/2021 15:58:35 - INFO - __main__ - Step 15096: {'lr': 0.0004904038022761797, 'samples': 2898432, 'steps': 15095, 'loss/train': 1.7329566478729248} 08/30/2021 15:58:36 - INFO - __main__ - Step 15097: {'lr': 0.0004904023460433475, 'samples': 2898624, 'steps': 15096, 'loss/train': 1.617341160774231} 08/30/2021 15:58:37 - INFO - __main__ - Step 15098: {'lr': 0.0004904008897021939, 'samples': 2898816, 'steps': 15097, 'loss/train': 1.7051061391830444} 08/30/2021 15:58:37 - INFO - __main__ - Step 15099: {'lr': 0.0004903994332527193, 'samples': 2899008, 'steps': 15098, 'loss/train': 1.9150274991989136} 08/30/2021 15:58:38 - INFO - __main__ - Step 15100: {'lr': 0.0004903979766949244, 'samples': 2899200, 'steps': 15099, 'loss/train': 2.107600450515747} 08/30/2021 15:58:38 - INFO - __main__ - Step 15101: {'lr': 0.00049039652002881, 'samples': 2899392, 'steps': 15100, 'loss/train': 2.323913335800171} 08/30/2021 15:58:39 - INFO - __main__ - Step 15102: {'lr': 0.0004903950632543766, 'samples': 2899584, 'steps': 15101, 'loss/train': 1.8349885940551758} 08/30/2021 15:58:40 - INFO - __main__ - Step 15103: {'lr': 0.0004903936063716248, 'samples': 2899776, 'steps': 15102, 'loss/train': 1.3465237617492676} 08/30/2021 15:58:40 - INFO - __main__ - Step 15104: {'lr': 0.0004903921493805554, 'samples': 2899968, 'steps': 15103, 'loss/train': 1.4871973991394043} 08/30/2021 15:58:41 - INFO - __main__ - Step 15105: {'lr': 0.000490390692281169, 'samples': 2900160, 'steps': 15104, 'loss/train': 1.7064441442489624} 08/30/2021 15:58:41 - INFO - __main__ - Step 15106: {'lr': 0.0004903892350734663, 'samples': 2900352, 'steps': 15105, 'loss/train': 1.973088264465332} 08/30/2021 15:58:43 - INFO - __main__ - Step 15107: {'lr': 0.0004903877777574479, 'samples': 2900544, 'steps': 15106, 'loss/train': 1.91025710105896} 08/30/2021 15:58:43 - INFO - __main__ - Step 15108: {'lr': 0.0004903863203331145, 'samples': 2900736, 'steps': 15107, 'loss/train': 1.796217441558838} 08/30/2021 15:58:43 - INFO - __main__ - Step 15109: {'lr': 0.0004903848628004667, 'samples': 2900928, 'steps': 15108, 'loss/train': 1.2699918746948242} 08/30/2021 15:58:44 - INFO - __main__ - Step 15110: {'lr': 0.0004903834051595052, 'samples': 2901120, 'steps': 15109, 'loss/train': 1.7588151693344116} 08/30/2021 15:58:44 - INFO - __main__ - Step 15111: {'lr': 0.0004903819474102306, 'samples': 2901312, 'steps': 15110, 'loss/train': 1.5148886442184448} 08/30/2021 15:58:45 - INFO - __main__ - Step 15112: {'lr': 0.0004903804895526437, 'samples': 2901504, 'steps': 15111, 'loss/train': 1.8466156721115112} 08/30/2021 15:58:46 - INFO - __main__ - Step 15113: {'lr': 0.0004903790315867449, 'samples': 2901696, 'steps': 15112, 'loss/train': 1.7272372245788574} 08/30/2021 15:58:46 - INFO - __main__ - Step 15114: {'lr': 0.0004903775735125352, 'samples': 2901888, 'steps': 15113, 'loss/train': 1.9933096170425415} 08/30/2021 15:58:47 - INFO - __main__ - Step 15115: {'lr': 0.0004903761153300149, 'samples': 2902080, 'steps': 15114, 'loss/train': 0.09477217495441437} 08/30/2021 15:58:47 - INFO - __main__ - Step 15116: {'lr': 0.000490374657039185, 'samples': 2902272, 'steps': 15115, 'loss/train': 1.6263753175735474} 08/30/2021 15:58:49 - INFO - __main__ - Step 15117: {'lr': 0.0004903731986400459, 'samples': 2902464, 'steps': 15116, 'loss/train': 1.6342326402664185} 08/30/2021 15:58:50 - INFO - __main__ - Step 15118: {'lr': 0.0004903717401325983, 'samples': 2902656, 'steps': 15117, 'loss/train': 2.0062599182128906} 08/30/2021 15:58:50 - INFO - __main__ - Step 15119: {'lr': 0.000490370281516843, 'samples': 2902848, 'steps': 15118, 'loss/train': 1.5492897033691406} 08/30/2021 15:58:50 - INFO - __main__ - Step 15120: {'lr': 0.0004903688227927806, 'samples': 2903040, 'steps': 15119, 'loss/train': 1.9500274658203125} 08/30/2021 15:58:51 - INFO - __main__ - Step 15121: {'lr': 0.0004903673639604116, 'samples': 2903232, 'steps': 15120, 'loss/train': 1.6372621059417725} 08/30/2021 15:58:51 - INFO - __main__ - Step 15122: {'lr': 0.0004903659050197369, 'samples': 2903424, 'steps': 15121, 'loss/train': 2.0835390090942383} 08/30/2021 15:58:51 - INFO - __main__ - Step 15123: {'lr': 0.0004903644459707569, 'samples': 2903616, 'steps': 15122, 'loss/train': 1.7659131288528442} 08/30/2021 15:58:54 - INFO - __main__ - Step 15124: {'lr': 0.0004903629868134725, 'samples': 2903808, 'steps': 15123, 'loss/train': 1.7020103931427002} 08/30/2021 15:58:54 - INFO - __main__ - Step 15125: {'lr': 0.0004903615275478841, 'samples': 2904000, 'steps': 15124, 'loss/train': 1.284178614616394} 08/30/2021 15:58:55 - INFO - __main__ - Step 15126: {'lr': 0.0004903600681739926, 'samples': 2904192, 'steps': 15125, 'loss/train': 0.15328308939933777} 08/30/2021 15:58:55 - INFO - __main__ - Step 15127: {'lr': 0.0004903586086917986, 'samples': 2904384, 'steps': 15126, 'loss/train': 1.4526680707931519} 08/30/2021 15:58:55 - INFO - __main__ - Step 15128: {'lr': 0.0004903571491013027, 'samples': 2904576, 'steps': 15127, 'loss/train': 1.530230164527893} 08/30/2021 15:58:56 - INFO - __main__ - Step 15129: {'lr': 0.0004903556894025055, 'samples': 2904768, 'steps': 15128, 'loss/train': 0.06229347363114357} 08/30/2021 15:58:57 - INFO - __main__ - Step 15130: {'lr': 0.0004903542295954077, 'samples': 2904960, 'steps': 15129, 'loss/train': 1.8654475212097168} 08/30/2021 15:58:58 - INFO - __main__ - Step 15131: {'lr': 0.0004903527696800102, 'samples': 2905152, 'steps': 15130, 'loss/train': 1.4783753156661987} 08/30/2021 15:58:58 - INFO - __main__ - Step 15132: {'lr': 0.0004903513096563133, 'samples': 2905344, 'steps': 15131, 'loss/train': 0.13516157865524292} 08/30/2021 15:58:59 - INFO - __main__ - Step 15133: {'lr': 0.0004903498495243178, 'samples': 2905536, 'steps': 15132, 'loss/train': 1.6506235599517822} 08/30/2021 15:58:59 - INFO - __main__ - Step 15134: {'lr': 0.0004903483892840244, 'samples': 2905728, 'steps': 15133, 'loss/train': 4.622920513153076} 08/30/2021 15:59:00 - INFO - __main__ - Step 15135: {'lr': 0.0004903469289354338, 'samples': 2905920, 'steps': 15134, 'loss/train': 1.3137805461883545} 08/30/2021 15:59:01 - INFO - __main__ - Step 15136: {'lr': 0.0004903454684785465, 'samples': 2906112, 'steps': 15135, 'loss/train': 1.9431031942367554} 08/30/2021 15:59:01 - INFO - __main__ - Step 15137: {'lr': 0.0004903440079133633, 'samples': 2906304, 'steps': 15136, 'loss/train': 2.1094818115234375} 08/30/2021 15:59:02 - INFO - __main__ - Step 15138: {'lr': 0.0004903425472398846, 'samples': 2906496, 'steps': 15137, 'loss/train': 1.6039923429489136} 08/30/2021 15:59:02 - INFO - __main__ - Step 15139: {'lr': 0.0004903410864581115, 'samples': 2906688, 'steps': 15138, 'loss/train': 2.016150951385498} 08/30/2021 15:59:02 - INFO - __main__ - Step 15140: {'lr': 0.0004903396255680443, 'samples': 2906880, 'steps': 15139, 'loss/train': 1.7691010236740112} 08/30/2021 15:59:04 - INFO - __main__ - Step 15141: {'lr': 0.0004903381645696838, 'samples': 2907072, 'steps': 15140, 'loss/train': 0.2667216360569} 08/30/2021 15:59:04 - INFO - __main__ - Step 15142: {'lr': 0.0004903367034630307, 'samples': 2907264, 'steps': 15141, 'loss/train': 1.5593140125274658} 08/30/2021 15:59:05 - INFO - __main__ - Step 15143: {'lr': 0.0004903352422480855, 'samples': 2907456, 'steps': 15142, 'loss/train': 1.4108080863952637} 08/30/2021 15:59:05 - INFO - __main__ - Step 15144: {'lr': 0.000490333780924849, 'samples': 2907648, 'steps': 15143, 'loss/train': 1.7154890298843384} 08/30/2021 15:59:05 - INFO - __main__ - Step 15145: {'lr': 0.0004903323194933218, 'samples': 2907840, 'steps': 15144, 'loss/train': 1.3250635862350464} 08/30/2021 15:59:07 - INFO - __main__ - Step 15146: {'lr': 0.0004903308579535045, 'samples': 2908032, 'steps': 15145, 'loss/train': 1.4927868843078613} 08/30/2021 15:59:07 - INFO - __main__ - Step 15147: {'lr': 0.0004903293963053979, 'samples': 2908224, 'steps': 15146, 'loss/train': 1.4518280029296875} 08/30/2021 15:59:08 - INFO - __main__ - Step 15148: {'lr': 0.0004903279345490026, 'samples': 2908416, 'steps': 15147, 'loss/train': 1.5175867080688477} 08/30/2021 15:59:08 - INFO - __main__ - Step 15149: {'lr': 0.0004903264726843191, 'samples': 2908608, 'steps': 15148, 'loss/train': 1.6642018556594849} 08/30/2021 15:59:08 - INFO - __main__ - Step 15150: {'lr': 0.0004903250107113483, 'samples': 2908800, 'steps': 15149, 'loss/train': 1.3926502466201782} 08/30/2021 15:59:10 - INFO - __main__ - Step 15151: {'lr': 0.0004903235486300908, 'samples': 2908992, 'steps': 15150, 'loss/train': 1.6689372062683105} 08/30/2021 15:59:10 - INFO - __main__ - Step 15152: {'lr': 0.0004903220864405471, 'samples': 2909184, 'steps': 15151, 'loss/train': 1.4074832201004028} 08/30/2021 15:59:11 - INFO - __main__ - Step 15153: {'lr': 0.000490320624142718, 'samples': 2909376, 'steps': 15152, 'loss/train': 1.8029906749725342} 08/30/2021 15:59:11 - INFO - __main__ - Step 15154: {'lr': 0.0004903191617366043, 'samples': 2909568, 'steps': 15153, 'loss/train': 2.1712491512298584} 08/30/2021 15:59:12 - INFO - __main__ - Step 15155: {'lr': 0.0004903176992222063, 'samples': 2909760, 'steps': 15154, 'loss/train': 1.6152732372283936} 08/30/2021 15:59:13 - INFO - __main__ - Step 15156: {'lr': 0.000490316236599525, 'samples': 2909952, 'steps': 15155, 'loss/train': 1.0634926557540894} 08/30/2021 15:59:14 - INFO - __main__ - Step 15157: {'lr': 0.0004903147738685609, 'samples': 2910144, 'steps': 15156, 'loss/train': 1.811274766921997} 08/30/2021 15:59:14 - INFO - __main__ - Step 15158: {'lr': 0.0004903133110293145, 'samples': 2910336, 'steps': 15157, 'loss/train': 1.590394139289856} 08/30/2021 15:59:14 - INFO - __main__ - Step 15159: {'lr': 0.0004903118480817868, 'samples': 2910528, 'steps': 15158, 'loss/train': 1.6736689805984497} 08/30/2021 15:59:15 - INFO - __main__ - Step 15160: {'lr': 0.0004903103850259781, 'samples': 2910720, 'steps': 15159, 'loss/train': 1.409801721572876} 08/30/2021 15:59:16 - INFO - __main__ - Step 15161: {'lr': 0.0004903089218618895, 'samples': 2910912, 'steps': 15160, 'loss/train': 1.5411909818649292} 08/30/2021 15:59:16 - INFO - __main__ - Step 15162: {'lr': 0.0004903074585895212, 'samples': 2911104, 'steps': 15161, 'loss/train': 2.174487590789795} 08/30/2021 15:59:17 - INFO - __main__ - Step 15163: {'lr': 0.0004903059952088742, 'samples': 2911296, 'steps': 15162, 'loss/train': 1.5213121175765991} 08/30/2021 15:59:17 - INFO - __main__ - Step 15164: {'lr': 0.0004903045317199489, 'samples': 2911488, 'steps': 15163, 'loss/train': 1.627817153930664} 08/30/2021 15:59:18 - INFO - __main__ - Step 15165: {'lr': 0.0004903030681227463, 'samples': 2911680, 'steps': 15164, 'loss/train': 1.5124437808990479} 08/30/2021 15:59:19 - INFO - __main__ - Step 15166: {'lr': 0.0004903016044172666, 'samples': 2911872, 'steps': 15165, 'loss/train': 1.874131441116333} 08/30/2021 15:59:19 - INFO - __main__ - Step 15167: {'lr': 0.0004903001406035109, 'samples': 2912064, 'steps': 15166, 'loss/train': 1.0103309154510498} 08/30/2021 15:59:20 - INFO - __main__ - Step 15168: {'lr': 0.0004902986766814795, 'samples': 2912256, 'steps': 15167, 'loss/train': 1.9327702522277832} 08/30/2021 15:59:20 - INFO - __main__ - Step 15169: {'lr': 0.0004902972126511734, 'samples': 2912448, 'steps': 15168, 'loss/train': 2.031543493270874} 08/30/2021 15:59:20 - INFO - __main__ - Step 15170: {'lr': 0.0004902957485125929, 'samples': 2912640, 'steps': 15169, 'loss/train': 2.0452992916107178} 08/30/2021 15:59:21 - INFO - __main__ - Step 15171: {'lr': 0.0004902942842657389, 'samples': 2912832, 'steps': 15170, 'loss/train': 1.6215959787368774} 08/30/2021 15:59:22 - INFO - __main__ - Step 15172: {'lr': 0.0004902928199106121, 'samples': 2913024, 'steps': 15171, 'loss/train': 1.258383870124817} 08/30/2021 15:59:23 - INFO - __main__ - Step 15173: {'lr': 0.000490291355447213, 'samples': 2913216, 'steps': 15172, 'loss/train': 1.4947481155395508} 08/30/2021 15:59:23 - INFO - __main__ - Step 15174: {'lr': 0.0004902898908755424, 'samples': 2913408, 'steps': 15173, 'loss/train': 2.7635366916656494} 08/30/2021 15:59:23 - INFO - __main__ - Step 15175: {'lr': 0.0004902884261956007, 'samples': 2913600, 'steps': 15174, 'loss/train': 1.5870851278305054} 08/30/2021 15:59:24 - INFO - __main__ - Step 15176: {'lr': 0.0004902869614073889, 'samples': 2913792, 'steps': 15175, 'loss/train': 1.5923242568969727} 08/30/2021 15:59:25 - INFO - __main__ - Step 15177: {'lr': 0.0004902854965109074, 'samples': 2913984, 'steps': 15176, 'loss/train': 1.8057106733322144} 08/30/2021 15:59:26 - INFO - __main__ - Step 15178: {'lr': 0.0004902840315061571, 'samples': 2914176, 'steps': 15177, 'loss/train': 1.4928910732269287} 08/30/2021 15:59:26 - INFO - __main__ - Step 15179: {'lr': 0.0004902825663931384, 'samples': 2914368, 'steps': 15178, 'loss/train': 1.6890974044799805} 08/30/2021 15:59:27 - INFO - __main__ - Step 15180: {'lr': 0.0004902811011718521, 'samples': 2914560, 'steps': 15179, 'loss/train': 1.528063416481018} 08/30/2021 15:59:27 - INFO - __main__ - Step 15181: {'lr': 0.0004902796358422989, 'samples': 2914752, 'steps': 15180, 'loss/train': 2.985886812210083} 08/30/2021 15:59:27 - INFO - __main__ - Step 15182: {'lr': 0.0004902781704044793, 'samples': 2914944, 'steps': 15181, 'loss/train': 1.86506187915802} 08/30/2021 15:59:29 - INFO - __main__ - Step 15183: {'lr': 0.0004902767048583942, 'samples': 2915136, 'steps': 15182, 'loss/train': 1.3643348217010498} 08/30/2021 15:59:30 - INFO - __main__ - Step 15184: {'lr': 0.000490275239204044, 'samples': 2915328, 'steps': 15183, 'loss/train': 1.420096516609192} 08/30/2021 15:59:30 - INFO - __main__ - Step 15185: {'lr': 0.0004902737734414296, 'samples': 2915520, 'steps': 15184, 'loss/train': 1.7147296667099} 08/30/2021 15:59:31 - INFO - __main__ - Step 15186: {'lr': 0.0004902723075705514, 'samples': 2915712, 'steps': 15185, 'loss/train': 2.1276416778564453} 08/30/2021 15:59:31 - INFO - __main__ - Step 15187: {'lr': 0.0004902708415914103, 'samples': 2915904, 'steps': 15186, 'loss/train': 0.7894248366355896} 08/30/2021 15:59:32 - INFO - __main__ - Step 15188: {'lr': 0.0004902693755040069, 'samples': 2916096, 'steps': 15187, 'loss/train': 1.9741934537887573} 08/30/2021 15:59:33 - INFO - __main__ - Step 15189: {'lr': 0.0004902679093083418, 'samples': 2916288, 'steps': 15188, 'loss/train': 1.7528294324874878} 08/30/2021 15:59:33 - INFO - __main__ - Step 15190: {'lr': 0.0004902664430044156, 'samples': 2916480, 'steps': 15189, 'loss/train': 1.6628696918487549} 08/30/2021 15:59:34 - INFO - __main__ - Step 15191: {'lr': 0.0004902649765922292, 'samples': 2916672, 'steps': 15190, 'loss/train': 1.560943841934204} 08/30/2021 15:59:34 - INFO - __main__ - Step 15192: {'lr': 0.0004902635100717831, 'samples': 2916864, 'steps': 15191, 'loss/train': 1.5229425430297852} 08/30/2021 15:59:36 - INFO - __main__ - Step 15193: {'lr': 0.0004902620434430778, 'samples': 2917056, 'steps': 15192, 'loss/train': 2.1835124492645264} 08/30/2021 15:59:36 - INFO - __main__ - Step 15194: {'lr': 0.0004902605767061142, 'samples': 2917248, 'steps': 15193, 'loss/train': 1.9095793962478638} 08/30/2021 15:59:36 - INFO - __main__ - Step 15195: {'lr': 0.000490259109860893, 'samples': 2917440, 'steps': 15194, 'loss/train': 1.4937175512313843} 08/30/2021 15:59:37 - INFO - __main__ - Step 15196: {'lr': 0.0004902576429074146, 'samples': 2917632, 'steps': 15195, 'loss/train': 0.872139036655426} 08/30/2021 15:59:37 - INFO - __main__ - Step 15197: {'lr': 0.0004902561758456799, 'samples': 2917824, 'steps': 15196, 'loss/train': 1.0893328189849854} 08/30/2021 15:59:39 - INFO - __main__ - Step 15198: {'lr': 0.0004902547086756895, 'samples': 2918016, 'steps': 15197, 'loss/train': 1.9009952545166016} 08/30/2021 15:59:39 - INFO - __main__ - Step 15199: {'lr': 0.000490253241397444, 'samples': 2918208, 'steps': 15198, 'loss/train': 1.7882243394851685} 08/30/2021 15:59:39 - INFO - __main__ - Step 15200: {'lr': 0.0004902517740109441, 'samples': 2918400, 'steps': 15199, 'loss/train': 2.0170230865478516} 08/30/2021 15:59:40 - INFO - __main__ - Step 15201: {'lr': 0.0004902503065161905, 'samples': 2918592, 'steps': 15200, 'loss/train': 1.1906795501708984} 08/30/2021 15:59:40 - INFO - __main__ - Step 15202: {'lr': 0.0004902488389131837, 'samples': 2918784, 'steps': 15201, 'loss/train': 1.0520771741867065} 08/30/2021 15:59:42 - INFO - __main__ - Step 15203: {'lr': 0.0004902473712019246, 'samples': 2918976, 'steps': 15202, 'loss/train': 1.7138489484786987} 08/30/2021 15:59:42 - INFO - __main__ - Step 15204: {'lr': 0.0004902459033824137, 'samples': 2919168, 'steps': 15203, 'loss/train': 1.5838242769241333} 08/30/2021 15:59:42 - INFO - __main__ - Step 15205: {'lr': 0.0004902444354546516, 'samples': 2919360, 'steps': 15204, 'loss/train': 1.8327378034591675} 08/30/2021 15:59:43 - INFO - __main__ - Step 15206: {'lr': 0.0004902429674186392, 'samples': 2919552, 'steps': 15205, 'loss/train': 1.8911542892456055} 08/30/2021 15:59:43 - INFO - __main__ - Step 15207: {'lr': 0.000490241499274377, 'samples': 2919744, 'steps': 15206, 'loss/train': 1.6966699361801147} 08/30/2021 15:59:43 - INFO - __main__ - Step 15208: {'lr': 0.0004902400310218657, 'samples': 2919936, 'steps': 15207, 'loss/train': 1.6051431894302368} 08/30/2021 15:59:45 - INFO - __main__ - Step 15209: {'lr': 0.0004902385626611059, 'samples': 2920128, 'steps': 15208, 'loss/train': 1.5678776502609253} 08/30/2021 15:59:45 - INFO - __main__ - Step 15210: {'lr': 0.0004902370941920984, 'samples': 2920320, 'steps': 15209, 'loss/train': 1.2162106037139893} 08/30/2021 15:59:46 - INFO - __main__ - Step 15211: {'lr': 0.0004902356256148437, 'samples': 2920512, 'steps': 15210, 'loss/train': 1.455880045890808} 08/30/2021 15:59:46 - INFO - __main__ - Step 15212: {'lr': 0.0004902341569293425, 'samples': 2920704, 'steps': 15211, 'loss/train': 1.459934949874878} 08/30/2021 15:59:46 - INFO - __main__ - Step 15213: {'lr': 0.0004902326881355955, 'samples': 2920896, 'steps': 15212, 'loss/train': 1.446386456489563} 08/30/2021 15:59:48 - INFO - __main__ - Step 15214: {'lr': 0.0004902312192336034, 'samples': 2921088, 'steps': 15213, 'loss/train': 1.5584096908569336} 08/30/2021 15:59:48 - INFO - __main__ - Step 15215: {'lr': 0.000490229750223367, 'samples': 2921280, 'steps': 15214, 'loss/train': 0.9233636260032654} 08/30/2021 15:59:49 - INFO - __main__ - Step 15216: {'lr': 0.0004902282811048864, 'samples': 2921472, 'steps': 15215, 'loss/train': 1.0606367588043213} 08/30/2021 15:59:49 - INFO - __main__ - Step 15217: {'lr': 0.000490226811878163, 'samples': 2921664, 'steps': 15216, 'loss/train': 1.704091191291809} 08/30/2021 15:59:50 - INFO - __main__ - Step 15218: {'lr': 0.0004902253425431969, 'samples': 2921856, 'steps': 15217, 'loss/train': 1.7339808940887451} 08/30/2021 15:59:51 - INFO - __main__ - Step 15219: {'lr': 0.000490223873099989, 'samples': 2922048, 'steps': 15218, 'loss/train': 2.1102333068847656} 08/30/2021 15:59:51 - INFO - __main__ - Step 15220: {'lr': 0.00049022240354854, 'samples': 2922240, 'steps': 15219, 'loss/train': 1.6153285503387451} 08/30/2021 15:59:52 - INFO - __main__ - Step 15221: {'lr': 0.0004902209338888503, 'samples': 2922432, 'steps': 15220, 'loss/train': 2.018859386444092} 08/30/2021 15:59:52 - INFO - __main__ - Step 15222: {'lr': 0.000490219464120921, 'samples': 2922624, 'steps': 15221, 'loss/train': 0.7686914205551147} 08/30/2021 15:59:53 - INFO - __main__ - Step 15223: {'lr': 0.0004902179942447524, 'samples': 2922816, 'steps': 15222, 'loss/train': 0.8456284999847412} 08/30/2021 15:59:54 - INFO - __main__ - Step 15224: {'lr': 0.0004902165242603452, 'samples': 2923008, 'steps': 15223, 'loss/train': 1.8118358850479126} 08/30/2021 15:59:54 - INFO - __main__ - Step 15225: {'lr': 0.0004902150541677003, 'samples': 2923200, 'steps': 15224, 'loss/train': 1.6165413856506348} 08/30/2021 15:59:55 - INFO - __main__ - Step 15226: {'lr': 0.0004902135839668181, 'samples': 2923392, 'steps': 15225, 'loss/train': 1.4570969343185425} 08/30/2021 15:59:55 - INFO - __main__ - Step 15227: {'lr': 0.0004902121136576994, 'samples': 2923584, 'steps': 15226, 'loss/train': 2.010981559753418} 08/30/2021 15:59:55 - INFO - __main__ - Step 15228: {'lr': 0.0004902106432403448, 'samples': 2923776, 'steps': 15227, 'loss/train': 2.0917279720306396} 08/30/2021 15:59:56 - INFO - __main__ - Step 15229: {'lr': 0.0004902091727147551, 'samples': 2923968, 'steps': 15228, 'loss/train': 1.145888090133667} 08/30/2021 15:59:57 - INFO - __main__ - Step 15230: {'lr': 0.0004902077020809307, 'samples': 2924160, 'steps': 15229, 'loss/train': 1.5485759973526} 08/30/2021 15:59:58 - INFO - __main__ - Step 15231: {'lr': 0.0004902062313388725, 'samples': 2924352, 'steps': 15230, 'loss/train': 1.5448799133300781} 08/30/2021 15:59:58 - INFO - __main__ - Step 15232: {'lr': 0.0004902047604885811, 'samples': 2924544, 'steps': 15231, 'loss/train': 1.6722486019134521} 08/30/2021 15:59:58 - INFO - __main__ - Step 15233: {'lr': 0.0004902032895300571, 'samples': 2924736, 'steps': 15232, 'loss/train': 1.3838722705841064} 08/30/2021 15:59:59 - INFO - __main__ - Step 15234: {'lr': 0.0004902018184633012, 'samples': 2924928, 'steps': 15233, 'loss/train': 0.8554103374481201} 08/30/2021 16:00:01 - INFO - __main__ - Step 15235: {'lr': 0.0004902003472883141, 'samples': 2925120, 'steps': 15234, 'loss/train': 1.9881125688552856} 08/30/2021 16:00:01 - INFO - __main__ - Step 15236: {'lr': 0.0004901988760050964, 'samples': 2925312, 'steps': 15235, 'loss/train': 1.5846076011657715} 08/30/2021 16:00:02 - INFO - __main__ - Step 15237: {'lr': 0.0004901974046136488, 'samples': 2925504, 'steps': 15236, 'loss/train': 2.070047378540039} 08/30/2021 16:00:02 - INFO - __main__ - Step 15238: {'lr': 0.000490195933113972, 'samples': 2925696, 'steps': 15237, 'loss/train': 1.5535564422607422} 08/30/2021 16:00:02 - INFO - __main__ - Step 15239: {'lr': 0.0004901944615060665, 'samples': 2925888, 'steps': 15238, 'loss/train': 1.2036014795303345} 08/30/2021 16:00:04 - INFO - __main__ - Step 15240: {'lr': 0.0004901929897899331, 'samples': 2926080, 'steps': 15239, 'loss/train': 1.620802402496338} 08/30/2021 16:00:05 - INFO - __main__ - Step 15241: {'lr': 0.0004901915179655726, 'samples': 2926272, 'steps': 15240, 'loss/train': 1.8651938438415527} 08/30/2021 16:00:05 - INFO - __main__ - Step 15242: {'lr': 0.0004901900460329853, 'samples': 2926464, 'steps': 15241, 'loss/train': 1.6313143968582153} 08/30/2021 16:00:05 - INFO - __main__ - Step 15243: {'lr': 0.0004901885739921723, 'samples': 2926656, 'steps': 15242, 'loss/train': 2.0313265323638916} 08/30/2021 16:00:06 - INFO - __main__ - Step 15244: {'lr': 0.0004901871018431339, 'samples': 2926848, 'steps': 15243, 'loss/train': 1.65639066696167} 08/30/2021 16:00:06 - INFO - __main__ - Step 15245: {'lr': 0.0004901856295858708, 'samples': 2927040, 'steps': 15244, 'loss/train': 1.7966381311416626} 08/30/2021 16:00:08 - INFO - __main__ - Step 15246: {'lr': 0.0004901841572203839, 'samples': 2927232, 'steps': 15245, 'loss/train': 1.388607382774353} 08/30/2021 16:00:08 - INFO - __main__ - Step 15247: {'lr': 0.0004901826847466738, 'samples': 2927424, 'steps': 15246, 'loss/train': 1.3225113153457642} 08/30/2021 16:00:09 - INFO - __main__ - Step 15248: {'lr': 0.000490181212164741, 'samples': 2927616, 'steps': 15247, 'loss/train': 1.9013538360595703} 08/30/2021 16:00:09 - INFO - __main__ - Step 15249: {'lr': 0.0004901797394745861, 'samples': 2927808, 'steps': 15248, 'loss/train': 1.9068899154663086} 08/30/2021 16:00:09 - INFO - __main__ - Step 15250: {'lr': 0.0004901782666762102, 'samples': 2928000, 'steps': 15249, 'loss/train': 0.07610747218132019} 08/30/2021 16:00:10 - INFO - __main__ - Step 15251: {'lr': 0.0004901767937696135, 'samples': 2928192, 'steps': 15250, 'loss/train': 1.5153677463531494} 08/30/2021 16:00:11 - INFO - __main__ - Step 15252: {'lr': 0.0004901753207547969, 'samples': 2928384, 'steps': 15251, 'loss/train': 1.294348955154419} 08/30/2021 16:00:11 - INFO - __main__ - Step 15253: {'lr': 0.000490173847631761, 'samples': 2928576, 'steps': 15252, 'loss/train': 1.6863707304000854} 08/30/2021 16:00:12 - INFO - __main__ - Step 15254: {'lr': 0.0004901723744005065, 'samples': 2928768, 'steps': 15253, 'loss/train': 1.673261284828186} 08/30/2021 16:00:12 - INFO - __main__ - Step 15255: {'lr': 0.0004901709010610339, 'samples': 2928960, 'steps': 15254, 'loss/train': 1.7124124765396118} 08/30/2021 16:00:12 - INFO - __main__ - Step 15256: {'lr': 0.0004901694276133441, 'samples': 2929152, 'steps': 15255, 'loss/train': 2.0685617923736572} 08/30/2021 16:00:14 - INFO - __main__ - Step 15257: {'lr': 0.0004901679540574377, 'samples': 2929344, 'steps': 15256, 'loss/train': 1.9410738945007324} 08/30/2021 16:00:14 - INFO - __main__ - Step 15258: {'lr': 0.0004901664803933153, 'samples': 2929536, 'steps': 15257, 'loss/train': 2.0417656898498535} 08/30/2021 16:00:15 - INFO - __main__ - Step 15259: {'lr': 0.0004901650066209775, 'samples': 2929728, 'steps': 15258, 'loss/train': 1.6134295463562012} 08/30/2021 16:00:15 - INFO - __main__ - Step 15260: {'lr': 0.0004901635327404252, 'samples': 2929920, 'steps': 15259, 'loss/train': 1.9462106227874756} 08/30/2021 16:00:15 - INFO - __main__ - Step 15261: {'lr': 0.0004901620587516587, 'samples': 2930112, 'steps': 15260, 'loss/train': 1.2231272459030151} 08/30/2021 16:00:17 - INFO - __main__ - Step 15262: {'lr': 0.0004901605846546791, 'samples': 2930304, 'steps': 15261, 'loss/train': 1.6867084503173828} 08/30/2021 16:00:18 - INFO - __main__ - Step 15263: {'lr': 0.0004901591104494868, 'samples': 2930496, 'steps': 15262, 'loss/train': 1.9147292375564575} 08/30/2021 16:00:18 - INFO - __main__ - Step 15264: {'lr': 0.0004901576361360825, 'samples': 2930688, 'steps': 15263, 'loss/train': 2.208069086074829} 08/30/2021 16:00:18 - INFO - __main__ - Step 15265: {'lr': 0.0004901561617144667, 'samples': 2930880, 'steps': 15264, 'loss/train': 1.3121311664581299} 08/30/2021 16:00:19 - INFO - __main__ - Step 15266: {'lr': 0.0004901546871846405, 'samples': 2931072, 'steps': 15265, 'loss/train': 2.051281690597534} 08/30/2021 16:00:20 - INFO - __main__ - Step 15267: {'lr': 0.0004901532125466041, 'samples': 2931264, 'steps': 15266, 'loss/train': 0.10278207808732986} 08/30/2021 16:00:21 - INFO - __main__ - Step 15268: {'lr': 0.0004901517378003584, 'samples': 2931456, 'steps': 15267, 'loss/train': 1.8167712688446045} 08/30/2021 16:00:21 - INFO - __main__ - Step 15269: {'lr': 0.0004901502629459042, 'samples': 2931648, 'steps': 15268, 'loss/train': 1.5532091856002808} 08/30/2021 16:00:22 - INFO - __main__ - Step 15270: {'lr': 0.000490148787983242, 'samples': 2931840, 'steps': 15269, 'loss/train': 2.1325762271881104} 08/30/2021 16:00:22 - INFO - __main__ - Step 15271: {'lr': 0.0004901473129123723, 'samples': 2932032, 'steps': 15270, 'loss/train': 1.9315848350524902} 08/30/2021 16:00:22 - INFO - __main__ - Step 15272: {'lr': 0.0004901458377332959, 'samples': 2932224, 'steps': 15271, 'loss/train': 0.2822628319263458} 08/30/2021 16:00:24 - INFO - __main__ - Step 15273: {'lr': 0.0004901443624460136, 'samples': 2932416, 'steps': 15272, 'loss/train': 1.6238374710083008} 08/30/2021 16:00:24 - INFO - __main__ - Step 15274: {'lr': 0.000490142887050526, 'samples': 2932608, 'steps': 15273, 'loss/train': 2.0749807357788086} 08/30/2021 16:00:25 - INFO - __main__ - Step 15275: {'lr': 0.0004901414115468335, 'samples': 2932800, 'steps': 15274, 'loss/train': 2.2964682579040527} 08/30/2021 16:00:25 - INFO - __main__ - Step 15276: {'lr': 0.0004901399359349372, 'samples': 2932992, 'steps': 15275, 'loss/train': 1.9444867372512817} 08/30/2021 16:00:25 - INFO - __main__ - Step 15277: {'lr': 0.0004901384602148376, 'samples': 2933184, 'steps': 15276, 'loss/train': 1.6872153282165527} 08/30/2021 16:00:27 - INFO - __main__ - Step 15278: {'lr': 0.0004901369843865351, 'samples': 2933376, 'steps': 15277, 'loss/train': 1.8935812711715698} 08/30/2021 16:00:27 - INFO - __main__ - Step 15279: {'lr': 0.0004901355084500307, 'samples': 2933568, 'steps': 15278, 'loss/train': 3.2335526943206787} 08/30/2021 16:00:28 - INFO - __main__ - Step 15280: {'lr': 0.000490134032405325, 'samples': 2933760, 'steps': 15279, 'loss/train': 1.9136563539505005} 08/30/2021 16:00:28 - INFO - __main__ - Step 15281: {'lr': 0.0004901325562524185, 'samples': 2933952, 'steps': 15280, 'loss/train': 1.8464934825897217} 08/30/2021 16:00:28 - INFO - __main__ - Step 15282: {'lr': 0.0004901310799913121, 'samples': 2934144, 'steps': 15281, 'loss/train': 1.439648151397705} 08/30/2021 16:00:30 - INFO - __main__ - Step 15283: {'lr': 0.0004901296036220062, 'samples': 2934336, 'steps': 15282, 'loss/train': 1.7032266855239868} 08/30/2021 16:00:30 - INFO - __main__ - Step 15284: {'lr': 0.0004901281271445016, 'samples': 2934528, 'steps': 15283, 'loss/train': 1.8631856441497803} 08/30/2021 16:00:31 - INFO - __main__ - Step 15285: {'lr': 0.000490126650558799, 'samples': 2934720, 'steps': 15284, 'loss/train': 2.1576526165008545} 08/30/2021 16:00:31 - INFO - __main__ - Step 15286: {'lr': 0.000490125173864899, 'samples': 2934912, 'steps': 15285, 'loss/train': 1.8573395013809204} 08/30/2021 16:00:31 - INFO - __main__ - Step 15287: {'lr': 0.0004901236970628024, 'samples': 2935104, 'steps': 15286, 'loss/train': 1.9123634099960327} 08/30/2021 16:00:33 - INFO - __main__ - Step 15288: {'lr': 0.0004901222201525099, 'samples': 2935296, 'steps': 15287, 'loss/train': 2.1508285999298096} 08/30/2021 16:00:34 - INFO - __main__ - Step 15289: {'lr': 0.0004901207431340218, 'samples': 2935488, 'steps': 15288, 'loss/train': 1.8390781879425049} 08/30/2021 16:00:34 - INFO - __main__ - Step 15290: {'lr': 0.000490119266007339, 'samples': 2935680, 'steps': 15289, 'loss/train': 1.6442031860351562} 08/30/2021 16:00:34 - INFO - __main__ - Step 15291: {'lr': 0.0004901177887724623, 'samples': 2935872, 'steps': 15290, 'loss/train': 2.0264084339141846} 08/30/2021 16:00:35 - INFO - __main__ - Step 15292: {'lr': 0.0004901163114293921, 'samples': 2936064, 'steps': 15291, 'loss/train': 1.4709222316741943} 08/30/2021 16:00:35 - INFO - __main__ - Step 15293: {'lr': 0.0004901148339781293, 'samples': 2936256, 'steps': 15292, 'loss/train': 1.3401129245758057} 08/30/2021 16:00:37 - INFO - __main__ - Step 15294: {'lr': 0.0004901133564186744, 'samples': 2936448, 'steps': 15293, 'loss/train': 1.8701170682907104} 08/30/2021 16:00:38 - INFO - __main__ - Step 15295: {'lr': 0.0004901118787510281, 'samples': 2936640, 'steps': 15294, 'loss/train': 1.311923861503601} 08/30/2021 16:00:38 - INFO - __main__ - Step 15296: {'lr': 0.0004901104009751912, 'samples': 2936832, 'steps': 15295, 'loss/train': 1.8409775495529175} 08/30/2021 16:00:39 - INFO - __main__ - Step 15297: {'lr': 0.0004901089230911642, 'samples': 2937024, 'steps': 15296, 'loss/train': 1.8538223505020142} 08/30/2021 16:00:39 - INFO - __main__ - Step 15298: {'lr': 0.0004901074450989479, 'samples': 2937216, 'steps': 15297, 'loss/train': 1.9554061889648438} 08/30/2021 16:00:41 - INFO - __main__ - Step 15299: {'lr': 0.0004901059669985427, 'samples': 2937408, 'steps': 15298, 'loss/train': 0.32535094022750854} 08/30/2021 16:00:41 - INFO - __main__ - Step 15300: {'lr': 0.0004901044887899496, 'samples': 2937600, 'steps': 15299, 'loss/train': 1.4372743368148804} 08/30/2021 16:00:41 - INFO - __main__ - Step 15301: {'lr': 0.0004901030104731691, 'samples': 2937792, 'steps': 15300, 'loss/train': 1.6454297304153442} 08/30/2021 16:00:42 - INFO - __main__ - Step 15302: {'lr': 0.0004901015320482019, 'samples': 2937984, 'steps': 15301, 'loss/train': 2.1553637981414795} 08/30/2021 16:00:42 - INFO - __main__ - Step 15303: {'lr': 0.0004901000535150486, 'samples': 2938176, 'steps': 15302, 'loss/train': 1.8293977975845337} 08/30/2021 16:00:44 - INFO - __main__ - Step 15304: {'lr': 0.0004900985748737101, 'samples': 2938368, 'steps': 15303, 'loss/train': 2.0799834728240967} 08/30/2021 16:00:44 - INFO - __main__ - Step 15305: {'lr': 0.0004900970961241866, 'samples': 2938560, 'steps': 15304, 'loss/train': 2.3479645252227783} 08/30/2021 16:00:45 - INFO - __main__ - Step 15306: {'lr': 0.0004900956172664792, 'samples': 2938752, 'steps': 15305, 'loss/train': 1.979406714439392} 08/30/2021 16:00:45 - INFO - __main__ - Step 15307: {'lr': 0.0004900941383005884, 'samples': 2938944, 'steps': 15306, 'loss/train': 2.0431814193725586} 08/30/2021 16:00:45 - INFO - __main__ - Step 15308: {'lr': 0.0004900926592265149, 'samples': 2939136, 'steps': 15307, 'loss/train': 1.457631230354309} 08/30/2021 16:00:47 - INFO - __main__ - Step 15309: {'lr': 0.0004900911800442593, 'samples': 2939328, 'steps': 15308, 'loss/train': 1.8405603170394897} 08/30/2021 16:00:47 - INFO - __main__ - Step 15310: {'lr': 0.0004900897007538225, 'samples': 2939520, 'steps': 15309, 'loss/train': 1.909132480621338} 08/30/2021 16:00:48 - INFO - __main__ - Step 15311: {'lr': 0.0004900882213552049, 'samples': 2939712, 'steps': 15310, 'loss/train': 2.91546893119812} 08/30/2021 16:00:48 - INFO - __main__ - Step 15312: {'lr': 0.0004900867418484072, 'samples': 2939904, 'steps': 15311, 'loss/train': 1.8374571800231934} 08/30/2021 16:00:48 - INFO - __main__ - Step 15313: {'lr': 0.0004900852622334301, 'samples': 2940096, 'steps': 15312, 'loss/train': 1.6467686891555786} 08/30/2021 16:00:49 - INFO - __main__ - Step 15314: {'lr': 0.0004900837825102743, 'samples': 2940288, 'steps': 15313, 'loss/train': 0.1568973809480667} 08/30/2021 16:00:50 - INFO - __main__ - Step 15315: {'lr': 0.0004900823026789405, 'samples': 2940480, 'steps': 15314, 'loss/train': 1.7074110507965088} 08/30/2021 16:00:51 - INFO - __main__ - Step 15316: {'lr': 0.0004900808227394293, 'samples': 2940672, 'steps': 15315, 'loss/train': 1.5589522123336792} 08/30/2021 16:00:51 - INFO - __main__ - Step 15317: {'lr': 0.0004900793426917412, 'samples': 2940864, 'steps': 15316, 'loss/train': 1.637278437614441} 08/30/2021 16:00:52 - INFO - __main__ - Step 15318: {'lr': 0.0004900778625358774, 'samples': 2941056, 'steps': 15317, 'loss/train': 1.842742919921875} 08/30/2021 16:00:52 - INFO - __main__ - Step 15319: {'lr': 0.000490076382271838, 'samples': 2941248, 'steps': 15318, 'loss/train': 1.6763697862625122} 08/30/2021 16:00:53 - INFO - __main__ - Step 15320: {'lr': 0.0004900749018996238, 'samples': 2941440, 'steps': 15319, 'loss/train': 1.5344160795211792} 08/30/2021 16:00:54 - INFO - __main__ - Step 15321: {'lr': 0.0004900734214192358, 'samples': 2941632, 'steps': 15320, 'loss/train': 2.8766956329345703} 08/30/2021 16:00:54 - INFO - __main__ - Step 15322: {'lr': 0.0004900719408306743, 'samples': 2941824, 'steps': 15321, 'loss/train': 2.0137224197387695} 08/30/2021 16:00:54 - INFO - __main__ - Step 15323: {'lr': 0.0004900704601339401, 'samples': 2942016, 'steps': 15322, 'loss/train': 2.109374761581421} 08/30/2021 16:00:55 - INFO - __main__ - Step 15324: {'lr': 0.0004900689793290339, 'samples': 2942208, 'steps': 15323, 'loss/train': 1.5553075075149536} 08/30/2021 16:00:56 - INFO - __main__ - Step 15325: {'lr': 0.0004900674984159562, 'samples': 2942400, 'steps': 15324, 'loss/train': 1.4952634572982788} 08/30/2021 16:00:57 - INFO - __main__ - Step 15326: {'lr': 0.0004900660173947079, 'samples': 2942592, 'steps': 15325, 'loss/train': 0.48776811361312866} 08/30/2021 16:00:57 - INFO - __main__ - Step 15327: {'lr': 0.0004900645362652895, 'samples': 2942784, 'steps': 15326, 'loss/train': 1.2803184986114502} 08/30/2021 16:00:57 - INFO - __main__ - Step 15328: {'lr': 0.0004900630550277018, 'samples': 2942976, 'steps': 15327, 'loss/train': 1.2247620820999146} 08/30/2021 16:00:58 - INFO - __main__ - Step 15329: {'lr': 0.0004900615736819452, 'samples': 2943168, 'steps': 15328, 'loss/train': 1.6304024457931519} 08/30/2021 16:00:59 - INFO - __main__ - Step 15330: {'lr': 0.0004900600922280207, 'samples': 2943360, 'steps': 15329, 'loss/train': 1.6658141613006592} 08/30/2021 16:01:00 - INFO - __main__ - Step 15331: {'lr': 0.0004900586106659289, 'samples': 2943552, 'steps': 15330, 'loss/train': 2.2869555950164795} 08/30/2021 16:01:00 - INFO - __main__ - Step 15332: {'lr': 0.0004900571289956703, 'samples': 2943744, 'steps': 15331, 'loss/train': 1.738834023475647} 08/30/2021 16:01:01 - INFO - __main__ - Step 15333: {'lr': 0.0004900556472172457, 'samples': 2943936, 'steps': 15332, 'loss/train': 1.7425967454910278} 08/30/2021 16:01:01 - INFO - __main__ - Step 15334: {'lr': 0.0004900541653306557, 'samples': 2944128, 'steps': 15333, 'loss/train': 1.44273042678833} 08/30/2021 16:01:02 - INFO - __main__ - Step 15335: {'lr': 0.0004900526833359009, 'samples': 2944320, 'steps': 15334, 'loss/train': 1.672918677330017} 08/30/2021 16:01:03 - INFO - __main__ - Step 15336: {'lr': 0.0004900512012329822, 'samples': 2944512, 'steps': 15335, 'loss/train': 1.6832565069198608} 08/30/2021 16:01:03 - INFO - __main__ - Step 15337: {'lr': 0.0004900497190219002, 'samples': 2944704, 'steps': 15336, 'loss/train': 1.8559441566467285} 08/30/2021 16:01:04 - INFO - __main__ - Step 15338: {'lr': 0.0004900482367026554, 'samples': 2944896, 'steps': 15337, 'loss/train': 1.5720969438552856} 08/30/2021 16:01:04 - INFO - __main__ - Step 15339: {'lr': 0.0004900467542752485, 'samples': 2945088, 'steps': 15338, 'loss/train': 2.4836173057556152} 08/30/2021 16:01:04 - INFO - __main__ - Step 15340: {'lr': 0.0004900452717396803, 'samples': 2945280, 'steps': 15339, 'loss/train': 2.947153091430664} 08/30/2021 16:01:06 - INFO - __main__ - Step 15341: {'lr': 0.0004900437890959515, 'samples': 2945472, 'steps': 15340, 'loss/train': 2.604426145553589} 08/30/2021 16:01:07 - INFO - __main__ - Step 15342: {'lr': 0.0004900423063440625, 'samples': 2945664, 'steps': 15341, 'loss/train': 2.2659289836883545} 08/30/2021 16:01:07 - INFO - __main__ - Step 15343: {'lr': 0.0004900408234840142, 'samples': 2945856, 'steps': 15342, 'loss/train': 0.302096426486969} 08/30/2021 16:01:07 - INFO - __main__ - Step 15344: {'lr': 0.0004900393405158073, 'samples': 2946048, 'steps': 15343, 'loss/train': 1.3263083696365356} 08/30/2021 16:01:08 - INFO - __main__ - Step 15345: {'lr': 0.0004900378574394423, 'samples': 2946240, 'steps': 15344, 'loss/train': 0.3805118203163147} 08/30/2021 16:01:10 - INFO - __main__ - Step 15346: {'lr': 0.00049003637425492, 'samples': 2946432, 'steps': 15345, 'loss/train': 2.1891603469848633} 08/30/2021 16:01:10 - INFO - __main__ - Step 15347: {'lr': 0.0004900348909622409, 'samples': 2946624, 'steps': 15346, 'loss/train': 1.907754898071289} 08/30/2021 16:01:10 - INFO - __main__ - Step 15348: {'lr': 0.0004900334075614059, 'samples': 2946816, 'steps': 15347, 'loss/train': 2.2687036991119385} 08/30/2021 16:01:11 - INFO - __main__ - Step 15349: {'lr': 0.0004900319240524155, 'samples': 2947008, 'steps': 15348, 'loss/train': 1.630103349685669} 08/30/2021 16:01:11 - INFO - __main__ - Step 15350: {'lr': 0.0004900304404352704, 'samples': 2947200, 'steps': 15349, 'loss/train': 1.5954492092132568} 08/30/2021 16:01:13 - INFO - __main__ - Step 15351: {'lr': 0.0004900289567099713, 'samples': 2947392, 'steps': 15350, 'loss/train': 0.9392467737197876} 08/30/2021 16:01:13 - INFO - __main__ - Step 15352: {'lr': 0.000490027472876519, 'samples': 2947584, 'steps': 15351, 'loss/train': 1.7012474536895752} 08/30/2021 16:01:13 - INFO - __main__ - Step 15353: {'lr': 0.0004900259889349138, 'samples': 2947776, 'steps': 15352, 'loss/train': 2.369603395462036} 08/30/2021 16:01:14 - INFO - __main__ - Step 15354: {'lr': 0.0004900245048851567, 'samples': 2947968, 'steps': 15353, 'loss/train': 2.3797850608825684} 08/30/2021 16:01:14 - INFO - __main__ - Step 15355: {'lr': 0.0004900230207272483, 'samples': 2948160, 'steps': 15354, 'loss/train': 1.4411885738372803} 08/30/2021 16:01:16 - INFO - __main__ - Step 15356: {'lr': 0.000490021536461189, 'samples': 2948352, 'steps': 15355, 'loss/train': 1.212572455406189} 08/30/2021 16:01:16 - INFO - __main__ - Step 15357: {'lr': 0.00049002005208698, 'samples': 2948544, 'steps': 15356, 'loss/train': 1.9965567588806152} 08/30/2021 16:01:16 - INFO - __main__ - Step 15358: {'lr': 0.0004900185676046214, 'samples': 2948736, 'steps': 15357, 'loss/train': 1.5751240253448486} 08/30/2021 16:01:17 - INFO - __main__ - Step 15359: {'lr': 0.0004900170830141144, 'samples': 2948928, 'steps': 15358, 'loss/train': 2.052021026611328} 08/30/2021 16:01:17 - INFO - __main__ - Step 15360: {'lr': 0.0004900155983154592, 'samples': 2949120, 'steps': 15359, 'loss/train': 1.865669846534729} 08/30/2021 16:01:19 - INFO - __main__ - Step 15361: {'lr': 0.0004900141135086569, 'samples': 2949312, 'steps': 15360, 'loss/train': 1.7544538974761963} 08/30/2021 16:01:19 - INFO - __main__ - Step 15362: {'lr': 0.0004900126285937077, 'samples': 2949504, 'steps': 15361, 'loss/train': 1.7860257625579834} 08/30/2021 16:01:19 - INFO - __main__ - Step 15363: {'lr': 0.0004900111435706127, 'samples': 2949696, 'steps': 15362, 'loss/train': 1.7874385118484497} 08/30/2021 16:01:20 - INFO - __main__ - Step 15364: {'lr': 0.0004900096584393723, 'samples': 2949888, 'steps': 15363, 'loss/train': 2.277987241744995} 08/30/2021 16:01:20 - INFO - __main__ - Step 15365: {'lr': 0.0004900081731999872, 'samples': 2950080, 'steps': 15364, 'loss/train': 1.8814116716384888} 08/30/2021 16:01:23 - INFO - __main__ - Step 15366: {'lr': 0.0004900066878524582, 'samples': 2950272, 'steps': 15365, 'loss/train': 1.7960764169692993} 08/30/2021 16:01:23 - INFO - __main__ - Step 15367: {'lr': 0.0004900052023967859, 'samples': 2950464, 'steps': 15366, 'loss/train': 1.2443969249725342} 08/30/2021 16:01:23 - INFO - __main__ - Step 15368: {'lr': 0.0004900037168329709, 'samples': 2950656, 'steps': 15367, 'loss/train': 1.445622444152832} 08/30/2021 16:01:24 - INFO - __main__ - Step 15369: {'lr': 0.000490002231161014, 'samples': 2950848, 'steps': 15368, 'loss/train': 2.6704702377319336} 08/30/2021 16:01:24 - INFO - __main__ - Step 15370: {'lr': 0.0004900007453809157, 'samples': 2951040, 'steps': 15369, 'loss/train': 3.144233465194702} 08/30/2021 16:01:25 - INFO - __main__ - Step 15371: {'lr': 0.0004899992594926769, 'samples': 2951232, 'steps': 15370, 'loss/train': 3.3713228702545166} 08/30/2021 16:01:25 - INFO - __main__ - Step 15372: {'lr': 0.000489997773496298, 'samples': 2951424, 'steps': 15371, 'loss/train': 3.7108395099639893} 08/30/2021 16:01:25 - INFO - __main__ - Step 15373: {'lr': 0.0004899962873917798, 'samples': 2951616, 'steps': 15372, 'loss/train': 2.2490532398223877} 08/30/2021 16:01:27 - INFO - __main__ - Step 15374: {'lr': 0.000489994801179123, 'samples': 2951808, 'steps': 15373, 'loss/train': 1.7610284090042114} 08/30/2021 16:01:27 - INFO - __main__ - Step 15375: {'lr': 0.0004899933148583284, 'samples': 2952000, 'steps': 15374, 'loss/train': 2.233377456665039} 08/30/2021 16:01:27 - INFO - __main__ - Step 15376: {'lr': 0.0004899918284293964, 'samples': 2952192, 'steps': 15375, 'loss/train': 1.900270938873291} 08/30/2021 16:01:28 - INFO - __main__ - Step 15377: {'lr': 0.0004899903418923278, 'samples': 2952384, 'steps': 15376, 'loss/train': 1.764028787612915} 08/30/2021 16:01:28 - INFO - __main__ - Step 15378: {'lr': 0.0004899888552471232, 'samples': 2952576, 'steps': 15377, 'loss/train': 1.6459065675735474} 08/30/2021 16:01:30 - INFO - __main__ - Step 15379: {'lr': 0.0004899873684937833, 'samples': 2952768, 'steps': 15378, 'loss/train': 1.967921257019043} 08/30/2021 16:01:30 - INFO - __main__ - Step 15380: {'lr': 0.0004899858816323089, 'samples': 2952960, 'steps': 15379, 'loss/train': 1.7271283864974976} 08/30/2021 16:01:30 - INFO - __main__ - Step 15381: {'lr': 0.0004899843946627006, 'samples': 2953152, 'steps': 15380, 'loss/train': 1.5563031435012817} 08/30/2021 16:01:31 - INFO - __main__ - Step 15382: {'lr': 0.0004899829075849589, 'samples': 2953344, 'steps': 15381, 'loss/train': 1.7910250425338745} 08/30/2021 16:01:31 - INFO - __main__ - Step 15383: {'lr': 0.0004899814203990847, 'samples': 2953536, 'steps': 15382, 'loss/train': 1.7405543327331543} 08/30/2021 16:01:33 - INFO - __main__ - Step 15384: {'lr': 0.0004899799331050785, 'samples': 2953728, 'steps': 15383, 'loss/train': 2.0326998233795166} 08/30/2021 16:01:33 - INFO - __main__ - Step 15385: {'lr': 0.0004899784457029411, 'samples': 2953920, 'steps': 15384, 'loss/train': 1.8632278442382812} 08/30/2021 16:01:34 - INFO - __main__ - Step 15386: {'lr': 0.000489976958192673, 'samples': 2954112, 'steps': 15385, 'loss/train': 1.770098328590393} 08/30/2021 16:01:34 - INFO - __main__ - Step 15387: {'lr': 0.0004899754705742752, 'samples': 2954304, 'steps': 15386, 'loss/train': 1.867549180984497} 08/30/2021 16:01:34 - INFO - __main__ - Step 15388: {'lr': 0.0004899739828477481, 'samples': 2954496, 'steps': 15387, 'loss/train': 1.5787196159362793} 08/30/2021 16:01:36 - INFO - __main__ - Step 15389: {'lr': 0.0004899724950130923, 'samples': 2954688, 'steps': 15388, 'loss/train': 1.854261040687561} 08/30/2021 16:01:36 - INFO - __main__ - Step 15390: {'lr': 0.0004899710070703087, 'samples': 2954880, 'steps': 15389, 'loss/train': 4.427979946136475} 08/30/2021 16:01:37 - INFO - __main__ - Step 15391: {'lr': 0.0004899695190193978, 'samples': 2955072, 'steps': 15390, 'loss/train': 1.817335605621338} 08/30/2021 16:01:37 - INFO - __main__ - Step 15392: {'lr': 0.0004899680308603604, 'samples': 2955264, 'steps': 15391, 'loss/train': 1.8148187398910522} 08/30/2021 16:01:37 - INFO - __main__ - Step 15393: {'lr': 0.000489966542593197, 'samples': 2955456, 'steps': 15392, 'loss/train': 1.0594487190246582} 08/30/2021 16:01:39 - INFO - __main__ - Step 15394: {'lr': 0.0004899650542179085, 'samples': 2955648, 'steps': 15393, 'loss/train': 1.8477115631103516} 08/30/2021 16:01:39 - INFO - __main__ - Step 15395: {'lr': 0.0004899635657344954, 'samples': 2955840, 'steps': 15394, 'loss/train': 0.6730448603630066} 08/30/2021 16:01:40 - INFO - __main__ - Step 15396: {'lr': 0.0004899620771429585, 'samples': 2956032, 'steps': 15395, 'loss/train': 1.3027268648147583} 08/30/2021 16:01:40 - INFO - __main__ - Step 15397: {'lr': 0.0004899605884432983, 'samples': 2956224, 'steps': 15396, 'loss/train': 2.2151174545288086} 08/30/2021 16:01:40 - INFO - __main__ - Step 15398: {'lr': 0.0004899590996355155, 'samples': 2956416, 'steps': 15397, 'loss/train': 1.4743446111679077} 08/30/2021 16:01:41 - INFO - __main__ - Step 15399: {'lr': 0.000489957610719611, 'samples': 2956608, 'steps': 15398, 'loss/train': 2.064164161682129} 08/30/2021 16:01:43 - INFO - __main__ - Step 15400: {'lr': 0.0004899561216955852, 'samples': 2956800, 'steps': 15399, 'loss/train': 1.038681149482727} 08/30/2021 16:01:43 - INFO - __main__ - Step 15401: {'lr': 0.0004899546325634388, 'samples': 2956992, 'steps': 15400, 'loss/train': 1.3875161409378052} 08/30/2021 16:01:43 - INFO - __main__ - Step 15402: {'lr': 0.0004899531433231728, 'samples': 2957184, 'steps': 15401, 'loss/train': 2.049558639526367} 08/30/2021 16:01:44 - INFO - __main__ - Step 15403: {'lr': 0.0004899516539747874, 'samples': 2957376, 'steps': 15402, 'loss/train': 2.8670461177825928} 08/30/2021 16:01:44 - INFO - __main__ - Step 15404: {'lr': 0.0004899501645182835, 'samples': 2957568, 'steps': 15403, 'loss/train': 1.763898491859436} 08/30/2021 16:01:47 - INFO - __main__ - Step 15405: {'lr': 0.0004899486749536618, 'samples': 2957760, 'steps': 15404, 'loss/train': 1.6202975511550903} 08/30/2021 16:01:47 - INFO - __main__ - Step 15406: {'lr': 0.000489947185280923, 'samples': 2957952, 'steps': 15405, 'loss/train': 1.525149941444397} 08/30/2021 16:01:47 - INFO - __main__ - Step 15407: {'lr': 0.0004899456955000676, 'samples': 2958144, 'steps': 15406, 'loss/train': 2.3715343475341797} 08/30/2021 16:01:48 - INFO - __main__ - Step 15408: {'lr': 0.0004899442056110964, 'samples': 2958336, 'steps': 15407, 'loss/train': 0.917862057685852} 08/30/2021 16:01:48 - INFO - __main__ - Step 15409: {'lr': 0.00048994271561401, 'samples': 2958528, 'steps': 15408, 'loss/train': 0.7670138478279114} 08/30/2021 16:01:48 - INFO - __main__ - Step 15410: {'lr': 0.0004899412255088091, 'samples': 2958720, 'steps': 15409, 'loss/train': 0.6514217853546143} 08/30/2021 16:01:50 - INFO - __main__ - Step 15411: {'lr': 0.0004899397352954945, 'samples': 2958912, 'steps': 15410, 'loss/train': 1.4594303369522095} 08/30/2021 16:01:50 - INFO - __main__ - Step 15412: {'lr': 0.0004899382449740667, 'samples': 2959104, 'steps': 15411, 'loss/train': 1.6789549589157104} 08/30/2021 16:01:51 - INFO - __main__ - Step 15413: {'lr': 0.0004899367545445264, 'samples': 2959296, 'steps': 15412, 'loss/train': 1.2324168682098389} 08/30/2021 16:01:51 - INFO - __main__ - Step 15414: {'lr': 0.0004899352640068743, 'samples': 2959488, 'steps': 15413, 'loss/train': 1.689152717590332} 08/30/2021 16:01:51 - INFO - __main__ - Step 15415: {'lr': 0.0004899337733611113, 'samples': 2959680, 'steps': 15414, 'loss/train': 2.1103951930999756} 08/30/2021 16:01:53 - INFO - __main__ - Step 15416: {'lr': 0.0004899322826072375, 'samples': 2959872, 'steps': 15415, 'loss/train': 1.8710706233978271} 08/30/2021 16:01:54 - INFO - __main__ - Step 15417: {'lr': 0.0004899307917452542, 'samples': 2960064, 'steps': 15416, 'loss/train': 2.642216205596924} 08/30/2021 16:01:54 - INFO - __main__ - Step 15418: {'lr': 0.0004899293007751616, 'samples': 2960256, 'steps': 15417, 'loss/train': 1.8343582153320312} 08/30/2021 16:01:54 - INFO - __main__ - Step 15419: {'lr': 0.0004899278096969605, 'samples': 2960448, 'steps': 15418, 'loss/train': 2.05309796333313} 08/30/2021 16:01:55 - INFO - __main__ - Step 15420: {'lr': 0.0004899263185106518, 'samples': 2960640, 'steps': 15419, 'loss/train': 1.5433604717254639} 08/30/2021 16:01:55 - INFO - __main__ - Step 15421: {'lr': 0.000489924827216236, 'samples': 2960832, 'steps': 15420, 'loss/train': 2.4911468029022217} 08/30/2021 16:01:57 - INFO - __main__ - Step 15422: {'lr': 0.0004899233358137137, 'samples': 2961024, 'steps': 15421, 'loss/train': 2.5839223861694336} 08/30/2021 16:01:57 - INFO - __main__ - Step 15423: {'lr': 0.0004899218443030857, 'samples': 2961216, 'steps': 15422, 'loss/train': 1.6599600315093994} 08/30/2021 16:01:57 - INFO - __main__ - Step 15424: {'lr': 0.0004899203526843526, 'samples': 2961408, 'steps': 15423, 'loss/train': 2.8455517292022705} 08/30/2021 16:01:58 - INFO - __main__ - Step 15425: {'lr': 0.000489918860957515, 'samples': 2961600, 'steps': 15424, 'loss/train': 1.2354341745376587} 08/30/2021 16:01:58 - INFO - __main__ - Step 15426: {'lr': 0.0004899173691225737, 'samples': 2961792, 'steps': 15425, 'loss/train': 1.9968653917312622} 08/30/2021 16:02:00 - INFO - __main__ - Step 15427: {'lr': 0.0004899158771795295, 'samples': 2961984, 'steps': 15426, 'loss/train': 1.388020634651184} 08/30/2021 16:02:00 - INFO - __main__ - Step 15428: {'lr': 0.0004899143851283827, 'samples': 2962176, 'steps': 15427, 'loss/train': 1.0337297916412354} 08/30/2021 16:02:01 - INFO - __main__ - Step 15429: {'lr': 0.0004899128929691343, 'samples': 2962368, 'steps': 15428, 'loss/train': 0.4183272421360016} 08/30/2021 16:02:01 - INFO - __main__ - Step 15430: {'lr': 0.0004899114007017849, 'samples': 2962560, 'steps': 15429, 'loss/train': 1.970598578453064} 08/30/2021 16:02:02 - INFO - __main__ - Step 15431: {'lr': 0.000489909908326335, 'samples': 2962752, 'steps': 15430, 'loss/train': 1.612714171409607} 08/30/2021 16:02:03 - INFO - __main__ - Step 15432: {'lr': 0.0004899084158427855, 'samples': 2962944, 'steps': 15431, 'loss/train': 1.9569873809814453} 08/30/2021 16:02:03 - INFO - __main__ - Step 15433: {'lr': 0.0004899069232511368, 'samples': 2963136, 'steps': 15432, 'loss/train': 1.9313437938690186} 08/30/2021 16:02:04 - INFO - __main__ - Step 15434: {'lr': 0.0004899054305513899, 'samples': 2963328, 'steps': 15433, 'loss/train': 1.5398770570755005} 08/30/2021 16:02:04 - INFO - __main__ - Step 15435: {'lr': 0.0004899039377435452, 'samples': 2963520, 'steps': 15434, 'loss/train': 1.5831071138381958} 08/30/2021 16:02:04 - INFO - __main__ - Step 15436: {'lr': 0.0004899024448276036, 'samples': 2963712, 'steps': 15435, 'loss/train': 1.657619833946228} 08/30/2021 16:02:06 - INFO - __main__ - Step 15437: {'lr': 0.0004899009518035657, 'samples': 2963904, 'steps': 15436, 'loss/train': 1.9374465942382812} 08/30/2021 16:02:06 - INFO - __main__ - Step 15438: {'lr': 0.000489899458671432, 'samples': 2964096, 'steps': 15437, 'loss/train': 1.7268048524856567} 08/30/2021 16:02:07 - INFO - __main__ - Step 15439: {'lr': 0.0004898979654312034, 'samples': 2964288, 'steps': 15438, 'loss/train': 2.1226131916046143} 08/30/2021 16:02:07 - INFO - __main__ - Step 15440: {'lr': 0.0004898964720828804, 'samples': 2964480, 'steps': 15439, 'loss/train': 1.9830279350280762} 08/30/2021 16:02:07 - INFO - __main__ - Step 15441: {'lr': 0.0004898949786264638, 'samples': 2964672, 'steps': 15440, 'loss/train': 1.5021300315856934} 08/30/2021 16:02:08 - INFO - __main__ - Step 15442: {'lr': 0.0004898934850619542, 'samples': 2964864, 'steps': 15441, 'loss/train': 1.5217854976654053} 08/30/2021 16:02:09 - INFO - __main__ - Step 15443: {'lr': 0.0004898919913893522, 'samples': 2965056, 'steps': 15442, 'loss/train': 1.356797456741333} 08/30/2021 16:02:10 - INFO - __main__ - Step 15444: {'lr': 0.0004898904976086588, 'samples': 2965248, 'steps': 15443, 'loss/train': 1.2115391492843628} 08/30/2021 16:02:10 - INFO - __main__ - Step 15445: {'lr': 0.0004898890037198743, 'samples': 2965440, 'steps': 15444, 'loss/train': 2.0368924140930176} 08/30/2021 16:02:11 - INFO - __main__ - Step 15446: {'lr': 0.0004898875097229995, 'samples': 2965632, 'steps': 15445, 'loss/train': 1.4779425859451294} 08/30/2021 16:02:11 - INFO - __main__ - Step 15447: {'lr': 0.0004898860156180351, 'samples': 2965824, 'steps': 15446, 'loss/train': 0.7495663166046143} 08/30/2021 16:02:12 - INFO - __main__ - Step 15448: {'lr': 0.0004898845214049818, 'samples': 2966016, 'steps': 15447, 'loss/train': 1.6176329851150513} 08/30/2021 16:02:13 - INFO - __main__ - Step 15449: {'lr': 0.0004898830270838403, 'samples': 2966208, 'steps': 15448, 'loss/train': 1.2131174802780151} 08/30/2021 16:02:13 - INFO - __main__ - Step 15450: {'lr': 0.0004898815326546111, 'samples': 2966400, 'steps': 15449, 'loss/train': 1.6455386877059937} 08/30/2021 16:02:14 - INFO - __main__ - Step 15451: {'lr': 0.0004898800381172951, 'samples': 2966592, 'steps': 15450, 'loss/train': 1.2084242105484009} 08/30/2021 16:02:14 - INFO - __main__ - Step 15452: {'lr': 0.0004898785434718927, 'samples': 2966784, 'steps': 15451, 'loss/train': 1.802215337753296} 08/30/2021 16:02:16 - INFO - __main__ - Step 15453: {'lr': 0.0004898770487184047, 'samples': 2966976, 'steps': 15452, 'loss/train': 1.7267192602157593} 08/30/2021 16:02:16 - INFO - __main__ - Step 15454: {'lr': 0.000489875553856832, 'samples': 2967168, 'steps': 15453, 'loss/train': 2.06032133102417} 08/30/2021 16:02:16 - INFO - __main__ - Step 15455: {'lr': 0.000489874058887175, 'samples': 2967360, 'steps': 15454, 'loss/train': 2.269136428833008} 08/30/2021 16:02:17 - INFO - __main__ - Step 15456: {'lr': 0.0004898725638094345, 'samples': 2967552, 'steps': 15455, 'loss/train': 1.7237387895584106} 08/30/2021 16:02:17 - INFO - __main__ - Step 15457: {'lr': 0.0004898710686236109, 'samples': 2967744, 'steps': 15456, 'loss/train': 2.390012264251709} 08/30/2021 16:02:17 - INFO - __main__ - Step 15458: {'lr': 0.0004898695733297054, 'samples': 2967936, 'steps': 15457, 'loss/train': 1.067933201789856} 08/30/2021 16:02:19 - INFO - __main__ - Step 15459: {'lr': 0.0004898680779277182, 'samples': 2968128, 'steps': 15458, 'loss/train': 1.0919665098190308} 08/30/2021 16:02:20 - INFO - __main__ - Step 15460: {'lr': 0.0004898665824176502, 'samples': 2968320, 'steps': 15459, 'loss/train': 1.6166990995407104} 08/30/2021 16:02:20 - INFO - __main__ - Step 15461: {'lr': 0.000489865086799502, 'samples': 2968512, 'steps': 15460, 'loss/train': 6.107758045196533} 08/30/2021 16:02:21 - INFO - __main__ - Step 15462: {'lr': 0.0004898635910732743, 'samples': 2968704, 'steps': 15461, 'loss/train': 1.7005637884140015} 08/30/2021 16:02:21 - INFO - __main__ - Step 15463: {'lr': 0.0004898620952389677, 'samples': 2968896, 'steps': 15462, 'loss/train': 1.6844971179962158} 08/30/2021 16:02:22 - INFO - __main__ - Step 15464: {'lr': 0.000489860599296583, 'samples': 2969088, 'steps': 15463, 'loss/train': 1.0527204275131226} 08/30/2021 16:02:23 - INFO - __main__ - Step 15465: {'lr': 0.0004898591032461208, 'samples': 2969280, 'steps': 15464, 'loss/train': 0.9791547060012817} 08/30/2021 16:02:23 - INFO - __main__ - Step 15466: {'lr': 0.0004898576070875818, 'samples': 2969472, 'steps': 15465, 'loss/train': 1.6744648218154907} 08/30/2021 16:02:24 - INFO - __main__ - Step 15467: {'lr': 0.0004898561108209667, 'samples': 2969664, 'steps': 15466, 'loss/train': 1.3549813032150269} 08/30/2021 16:02:24 - INFO - __main__ - Step 15468: {'lr': 0.0004898546144462762, 'samples': 2969856, 'steps': 15467, 'loss/train': 1.7299755811691284} 08/30/2021 16:02:25 - INFO - __main__ - Step 15469: {'lr': 0.0004898531179635108, 'samples': 2970048, 'steps': 15468, 'loss/train': 2.0573878288269043} 08/30/2021 16:02:26 - INFO - __main__ - Step 15470: {'lr': 0.0004898516213726712, 'samples': 2970240, 'steps': 15469, 'loss/train': 1.1556767225265503} 08/30/2021 16:02:26 - INFO - __main__ - Step 15471: {'lr': 0.0004898501246737583, 'samples': 2970432, 'steps': 15470, 'loss/train': 1.9659992456436157} 08/30/2021 16:02:26 - INFO - __main__ - Step 15472: {'lr': 0.0004898486278667725, 'samples': 2970624, 'steps': 15471, 'loss/train': 2.3629324436187744} 08/30/2021 16:02:27 - INFO - __main__ - Step 15473: {'lr': 0.0004898471309517148, 'samples': 2970816, 'steps': 15472, 'loss/train': 1.8187549114227295} 08/30/2021 16:02:29 - INFO - __main__ - Step 15474: {'lr': 0.0004898456339285857, 'samples': 2971008, 'steps': 15473, 'loss/train': 1.479103446006775} 08/30/2021 16:02:29 - INFO - __main__ - Step 15475: {'lr': 0.0004898441367973856, 'samples': 2971200, 'steps': 15474, 'loss/train': 1.9135509729385376} 08/30/2021 16:02:30 - INFO - __main__ - Step 15476: {'lr': 0.0004898426395581156, 'samples': 2971392, 'steps': 15475, 'loss/train': 1.8636592626571655} 08/30/2021 16:02:30 - INFO - __main__ - Step 15477: {'lr': 0.0004898411422107762, 'samples': 2971584, 'steps': 15476, 'loss/train': 1.3952314853668213} 08/30/2021 16:02:31 - INFO - __main__ - Step 15478: {'lr': 0.0004898396447553681, 'samples': 2971776, 'steps': 15477, 'loss/train': 2.1136181354522705} 08/30/2021 16:02:31 - INFO - __main__ - Step 15479: {'lr': 0.000489838147191892, 'samples': 2971968, 'steps': 15478, 'loss/train': 1.599002718925476} 08/30/2021 16:02:31 - INFO - __main__ - Step 15480: {'lr': 0.0004898366495203483, 'samples': 2972160, 'steps': 15479, 'loss/train': 1.0923447608947754} 08/30/2021 16:02:34 - INFO - __main__ - Step 15481: {'lr': 0.0004898351517407381, 'samples': 2972352, 'steps': 15480, 'loss/train': 0.9394541382789612} 08/30/2021 16:02:35 - INFO - __main__ - Step 15482: {'lr': 0.0004898336538530619, 'samples': 2972544, 'steps': 15481, 'loss/train': 1.670491337776184} 08/30/2021 16:02:35 - INFO - __main__ - Step 15483: {'lr': 0.0004898321558573203, 'samples': 2972736, 'steps': 15482, 'loss/train': 1.520904302597046} 08/30/2021 16:02:35 - INFO - __main__ - Step 15484: {'lr': 0.000489830657753514, 'samples': 2972928, 'steps': 15483, 'loss/train': 0.9412619471549988} 08/30/2021 16:02:36 - INFO - __main__ - Step 15485: {'lr': 0.0004898291595416438, 'samples': 2973120, 'steps': 15484, 'loss/train': 1.2993401288986206} 08/30/2021 16:02:36 - INFO - __main__ - Step 15486: {'lr': 0.0004898276612217102, 'samples': 2973312, 'steps': 15485, 'loss/train': 3.5321402549743652} 08/30/2021 16:02:36 - INFO - __main__ - Step 15487: {'lr': 0.0004898261627937139, 'samples': 2973504, 'steps': 15486, 'loss/train': 4.29628324508667} 08/30/2021 16:02:37 - INFO - __main__ - Step 15488: {'lr': 0.0004898246642576559, 'samples': 2973696, 'steps': 15487, 'loss/train': 4.206449508666992} 08/30/2021 16:02:38 - INFO - __main__ - Step 15489: {'lr': 0.0004898231656135362, 'samples': 2973888, 'steps': 15488, 'loss/train': 3.173597812652588} 08/30/2021 16:02:39 - INFO - __main__ - Step 15490: {'lr': 0.0004898216668613562, 'samples': 2974080, 'steps': 15489, 'loss/train': 2.2753357887268066} 08/30/2021 16:02:39 - INFO - __main__ - Step 15491: {'lr': 0.0004898201680011161, 'samples': 2974272, 'steps': 15490, 'loss/train': 1.9113277196884155} 08/30/2021 16:02:39 - INFO - __main__ - Step 15492: {'lr': 0.0004898186690328168, 'samples': 2974464, 'steps': 15491, 'loss/train': 1.8918006420135498} 08/30/2021 16:02:40 - INFO - __main__ - Step 15493: {'lr': 0.000489817169956459, 'samples': 2974656, 'steps': 15492, 'loss/train': 1.9345825910568237} 08/30/2021 16:02:42 - INFO - __main__ - Step 15494: {'lr': 0.0004898156707720432, 'samples': 2974848, 'steps': 15493, 'loss/train': 2.1934449672698975} 08/30/2021 16:02:42 - INFO - __main__ - Step 15495: {'lr': 0.0004898141714795701, 'samples': 2975040, 'steps': 15494, 'loss/train': 1.4573293924331665} 08/30/2021 16:02:43 - INFO - __main__ - Step 15496: {'lr': 0.0004898126720790405, 'samples': 2975232, 'steps': 15495, 'loss/train': 2.0083725452423096} 08/30/2021 16:02:43 - INFO - __main__ - Step 15497: {'lr': 0.0004898111725704549, 'samples': 2975424, 'steps': 15496, 'loss/train': 2.119008779525757} 08/30/2021 16:02:43 - INFO - __main__ - Step 15498: {'lr': 0.0004898096729538142, 'samples': 2975616, 'steps': 15497, 'loss/train': 1.5298768281936646} 08/30/2021 16:02:44 - INFO - __main__ - Step 15499: {'lr': 0.000489808173229119, 'samples': 2975808, 'steps': 15498, 'loss/train': 2.387995958328247} 08/30/2021 16:02:44 - INFO - __main__ - Step 15500: {'lr': 0.0004898066733963699, 'samples': 2976000, 'steps': 15499, 'loss/train': 1.9597584009170532} 08/30/2021 16:02:45 - INFO - __main__ - Step 15501: {'lr': 0.0004898051734555676, 'samples': 2976192, 'steps': 15500, 'loss/train': 2.040754795074463} 08/30/2021 16:02:46 - INFO - __main__ - Step 15502: {'lr': 0.0004898036734067127, 'samples': 2976384, 'steps': 15501, 'loss/train': 1.9665862321853638} 08/30/2021 16:02:46 - INFO - __main__ - Step 15503: {'lr': 0.000489802173249806, 'samples': 2976576, 'steps': 15502, 'loss/train': 1.9422433376312256} 08/30/2021 16:02:47 - INFO - __main__ - Step 15504: {'lr': 0.0004898006729848482, 'samples': 2976768, 'steps': 15503, 'loss/train': 2.226653575897217} 08/30/2021 16:02:47 - INFO - __main__ - Step 15505: {'lr': 0.0004897991726118399, 'samples': 2976960, 'steps': 15504, 'loss/train': 2.4603707790374756} 08/30/2021 16:02:49 - INFO - __main__ - Step 15506: {'lr': 0.0004897976721307818, 'samples': 2977152, 'steps': 15505, 'loss/train': 1.1228480339050293} 08/30/2021 16:02:49 - INFO - __main__ - Step 15507: {'lr': 0.0004897961715416746, 'samples': 2977344, 'steps': 15506, 'loss/train': 1.8973417282104492} 08/30/2021 16:02:50 - INFO - __main__ - Step 15508: {'lr': 0.0004897946708445189, 'samples': 2977536, 'steps': 15507, 'loss/train': 4.241513729095459} 08/30/2021 16:02:50 - INFO - __main__ - Step 15509: {'lr': 0.0004897931700393154, 'samples': 2977728, 'steps': 15508, 'loss/train': 2.953615665435791} 08/30/2021 16:02:50 - INFO - __main__ - Step 15510: {'lr': 0.0004897916691260648, 'samples': 2977920, 'steps': 15509, 'loss/train': 2.6631486415863037} 08/30/2021 16:02:51 - INFO - __main__ - Step 15511: {'lr': 0.0004897901681047679, 'samples': 2978112, 'steps': 15510, 'loss/train': 1.7656136751174927} 08/30/2021 16:02:53 - INFO - __main__ - Step 15512: {'lr': 0.0004897886669754251, 'samples': 2978304, 'steps': 15511, 'loss/train': 1.8558725118637085} 08/30/2021 16:02:53 - INFO - __main__ - Step 15513: {'lr': 0.0004897871657380373, 'samples': 2978496, 'steps': 15512, 'loss/train': 2.337657928466797} 08/30/2021 16:02:54 - INFO - __main__ - Step 15514: {'lr': 0.0004897856643926051, 'samples': 2978688, 'steps': 15513, 'loss/train': 2.785068988800049} 08/30/2021 16:02:54 - INFO - __main__ - Step 15515: {'lr': 0.0004897841629391291, 'samples': 2978880, 'steps': 15514, 'loss/train': 2.09179949760437} 08/30/2021 16:02:54 - INFO - __main__ - Step 15516: {'lr': 0.0004897826613776101, 'samples': 2979072, 'steps': 15515, 'loss/train': 2.7315292358398438} 08/30/2021 16:02:56 - INFO - __main__ - Step 15517: {'lr': 0.0004897811597080488, 'samples': 2979264, 'steps': 15516, 'loss/train': 2.242156744003296} 08/30/2021 16:02:56 - INFO - __main__ - Step 15518: {'lr': 0.0004897796579304458, 'samples': 2979456, 'steps': 15517, 'loss/train': 2.1583588123321533} 08/30/2021 16:02:57 - INFO - __main__ - Step 15519: {'lr': 0.0004897781560448017, 'samples': 2979648, 'steps': 15518, 'loss/train': 1.82471764087677} 08/30/2021 16:02:57 - INFO - __main__ - Step 15520: {'lr': 0.0004897766540511173, 'samples': 2979840, 'steps': 15519, 'loss/train': 0.4177507758140564} 08/30/2021 16:02:57 - INFO - __main__ - Step 15521: {'lr': 0.0004897751519493933, 'samples': 2980032, 'steps': 15520, 'loss/train': 2.0823662281036377} 08/30/2021 16:02:58 - INFO - __main__ - Step 15522: {'lr': 0.0004897736497396303, 'samples': 2980224, 'steps': 15521, 'loss/train': 2.7419381141662598} 08/30/2021 16:03:00 - INFO - __main__ - Step 15523: {'lr': 0.000489772147421829, 'samples': 2980416, 'steps': 15522, 'loss/train': 2.4459147453308105} 08/30/2021 16:03:00 - INFO - __main__ - Step 15524: {'lr': 0.0004897706449959899, 'samples': 2980608, 'steps': 15523, 'loss/train': 2.3358840942382812} 08/30/2021 16:03:00 - INFO - __main__ - Step 15525: {'lr': 0.000489769142462114, 'samples': 2980800, 'steps': 15524, 'loss/train': 1.6837490797042847} 08/30/2021 16:03:01 - INFO - __main__ - Step 15526: {'lr': 0.0004897676398202018, 'samples': 2980992, 'steps': 15525, 'loss/train': 2.7207229137420654} 08/30/2021 16:03:01 - INFO - __main__ - Step 15527: {'lr': 0.000489766137070254, 'samples': 2981184, 'steps': 15526, 'loss/train': 1.6504679918289185} 08/30/2021 16:03:02 - INFO - __main__ - Step 15528: {'lr': 0.0004897646342122713, 'samples': 2981376, 'steps': 15527, 'loss/train': 0.8819839954376221} 08/30/2021 16:03:03 - INFO - __main__ - Step 15529: {'lr': 0.0004897631312462544, 'samples': 2981568, 'steps': 15528, 'loss/train': 1.7353520393371582} 08/30/2021 16:03:03 - INFO - __main__ - Step 15530: {'lr': 0.0004897616281722038, 'samples': 2981760, 'steps': 15529, 'loss/train': 2.0722784996032715} 08/30/2021 16:03:04 - INFO - __main__ - Step 15531: {'lr': 0.0004897601249901204, 'samples': 2981952, 'steps': 15530, 'loss/train': 1.614208698272705} 08/30/2021 16:03:04 - INFO - __main__ - Step 15532: {'lr': 0.0004897586217000047, 'samples': 2982144, 'steps': 15531, 'loss/train': 2.2137129306793213} 08/30/2021 16:03:06 - INFO - __main__ - Step 15533: {'lr': 0.0004897571183018576, 'samples': 2982336, 'steps': 15532, 'loss/train': 2.5601062774658203} 08/30/2021 16:03:06 - INFO - __main__ - Step 15534: {'lr': 0.0004897556147956796, 'samples': 2982528, 'steps': 15533, 'loss/train': 1.969010591506958} 08/30/2021 16:03:06 - INFO - __main__ - Step 15535: {'lr': 0.0004897541111814714, 'samples': 2982720, 'steps': 15534, 'loss/train': 1.4815599918365479} 08/30/2021 16:03:07 - INFO - __main__ - Step 15536: {'lr': 0.0004897526074592337, 'samples': 2982912, 'steps': 15535, 'loss/train': 2.658247470855713} 08/30/2021 16:03:07 - INFO - __main__ - Step 15537: {'lr': 0.0004897511036289671, 'samples': 2983104, 'steps': 15536, 'loss/train': 1.8597320318222046} 08/30/2021 16:03:09 - INFO - __main__ - Step 15538: {'lr': 0.0004897495996906725, 'samples': 2983296, 'steps': 15537, 'loss/train': 1.9959858655929565} 08/30/2021 16:03:09 - INFO - __main__ - Step 15539: {'lr': 0.0004897480956443503, 'samples': 2983488, 'steps': 15538, 'loss/train': 1.9335285425186157} 08/30/2021 16:03:10 - INFO - __main__ - Step 15540: {'lr': 0.0004897465914900013, 'samples': 2983680, 'steps': 15539, 'loss/train': 2.258700370788574} 08/30/2021 16:03:10 - INFO - __main__ - Step 15541: {'lr': 0.0004897450872276263, 'samples': 2983872, 'steps': 15540, 'loss/train': 1.6229095458984375} 08/30/2021 16:03:10 - INFO - __main__ - Step 15542: {'lr': 0.0004897435828572258, 'samples': 2984064, 'steps': 15541, 'loss/train': 1.8740934133529663} 08/30/2021 16:03:11 - INFO - __main__ - Step 15543: {'lr': 0.0004897420783788006, 'samples': 2984256, 'steps': 15542, 'loss/train': 0.48658761382102966} 08/30/2021 16:03:12 - INFO - __main__ - Step 15544: {'lr': 0.0004897405737923511, 'samples': 2984448, 'steps': 15543, 'loss/train': 1.3301993608474731} 08/30/2021 16:03:13 - INFO - __main__ - Step 15545: {'lr': 0.0004897390690978785, 'samples': 2984640, 'steps': 15544, 'loss/train': 2.144516944885254} 08/30/2021 16:03:13 - INFO - __main__ - Step 15546: {'lr': 0.000489737564295383, 'samples': 2984832, 'steps': 15545, 'loss/train': 1.8909426927566528} 08/30/2021 16:03:13 - INFO - __main__ - Step 15547: {'lr': 0.0004897360593848655, 'samples': 2985024, 'steps': 15546, 'loss/train': 2.0608294010162354} 08/30/2021 16:03:14 - INFO - __main__ - Step 15548: {'lr': 0.0004897345543663266, 'samples': 2985216, 'steps': 15547, 'loss/train': 1.966789722442627} 08/30/2021 16:03:15 - INFO - __main__ - Step 15549: {'lr': 0.000489733049239767, 'samples': 2985408, 'steps': 15548, 'loss/train': 2.0603878498077393} 08/30/2021 16:03:16 - INFO - __main__ - Step 15550: {'lr': 0.0004897315440051874, 'samples': 2985600, 'steps': 15549, 'loss/train': 1.5398551225662231} 08/30/2021 16:03:16 - INFO - __main__ - Step 15551: {'lr': 0.0004897300386625885, 'samples': 2985792, 'steps': 15550, 'loss/train': 1.3343030214309692} 08/30/2021 16:03:16 - INFO - __main__ - Step 15552: {'lr': 0.0004897285332119709, 'samples': 2985984, 'steps': 15551, 'loss/train': 1.5717535018920898} 08/30/2021 16:03:17 - INFO - __main__ - Step 15553: {'lr': 0.0004897270276533355, 'samples': 2986176, 'steps': 15552, 'loss/train': 1.6205661296844482} 08/30/2021 16:03:18 - INFO - __main__ - Step 15554: {'lr': 0.0004897255219866825, 'samples': 2986368, 'steps': 15553, 'loss/train': 1.9927802085876465} 08/30/2021 16:03:19 - INFO - __main__ - Step 15555: {'lr': 0.000489724016212013, 'samples': 2986560, 'steps': 15554, 'loss/train': 2.115006446838379} 08/30/2021 16:03:19 - INFO - __main__ - Step 15556: {'lr': 0.0004897225103293277, 'samples': 2986752, 'steps': 15555, 'loss/train': 1.4051820039749146} 08/30/2021 16:03:19 - INFO - __main__ - Step 15557: {'lr': 0.0004897210043386269, 'samples': 2986944, 'steps': 15556, 'loss/train': 1.575562834739685} 08/30/2021 16:03:20 - INFO - __main__ - Step 15558: {'lr': 0.0004897194982399117, 'samples': 2987136, 'steps': 15557, 'loss/train': 1.874578595161438} 08/30/2021 16:03:21 - INFO - __main__ - Step 15559: {'lr': 0.0004897179920331826, 'samples': 2987328, 'steps': 15558, 'loss/train': 1.6472991704940796} 08/30/2021 16:03:22 - INFO - __main__ - Step 15560: {'lr': 0.0004897164857184401, 'samples': 2987520, 'steps': 15559, 'loss/train': 1.7609413862228394} 08/30/2021 16:03:22 - INFO - __main__ - Step 15561: {'lr': 0.0004897149792956852, 'samples': 2987712, 'steps': 15560, 'loss/train': 2.2637219429016113} 08/30/2021 16:03:22 - INFO - __main__ - Step 15562: {'lr': 0.0004897134727649184, 'samples': 2987904, 'steps': 15561, 'loss/train': 1.636091947555542} 08/30/2021 16:03:23 - INFO - __main__ - Step 15563: {'lr': 0.0004897119661261403, 'samples': 2988096, 'steps': 15562, 'loss/train': 1.4694645404815674} 08/30/2021 16:03:24 - INFO - __main__ - Step 15564: {'lr': 0.0004897104593793518, 'samples': 2988288, 'steps': 15563, 'loss/train': 1.817311406135559} 08/30/2021 16:03:25 - INFO - __main__ - Step 15565: {'lr': 0.0004897089525245535, 'samples': 2988480, 'steps': 15564, 'loss/train': 2.0266592502593994} 08/30/2021 16:03:25 - INFO - __main__ - Step 15566: {'lr': 0.000489707445561746, 'samples': 2988672, 'steps': 15565, 'loss/train': 1.5361164808273315} 08/30/2021 16:03:25 - INFO - __main__ - Step 15567: {'lr': 0.0004897059384909299, 'samples': 2988864, 'steps': 15566, 'loss/train': 2.2441718578338623} 08/30/2021 16:03:26 - INFO - __main__ - Step 15568: {'lr': 0.0004897044313121061, 'samples': 2989056, 'steps': 15567, 'loss/train': 1.7525969743728638} 08/30/2021 16:03:28 - INFO - __main__ - Step 15569: {'lr': 0.0004897029240252753, 'samples': 2989248, 'steps': 15568, 'loss/train': 2.4664337635040283} 08/30/2021 16:03:28 - INFO - __main__ - Step 15570: {'lr': 0.000489701416630438, 'samples': 2989440, 'steps': 15569, 'loss/train': 1.9209808111190796} 08/30/2021 16:03:29 - INFO - __main__ - Step 15571: {'lr': 0.0004896999091275948, 'samples': 2989632, 'steps': 15570, 'loss/train': 0.6832961440086365} 08/30/2021 16:03:29 - INFO - __main__ - Step 15572: {'lr': 0.0004896984015167466, 'samples': 2989824, 'steps': 15571, 'loss/train': 1.6293202638626099} 08/30/2021 16:03:29 - INFO - __main__ - Step 15573: {'lr': 0.0004896968937978941, 'samples': 2990016, 'steps': 15572, 'loss/train': 1.7801684141159058} 08/30/2021 16:03:31 - INFO - __main__ - Step 15574: {'lr': 0.0004896953859710379, 'samples': 2990208, 'steps': 15573, 'loss/train': 1.8957176208496094} 08/30/2021 16:03:31 - INFO - __main__ - Step 15575: {'lr': 0.0004896938780361784, 'samples': 2990400, 'steps': 15574, 'loss/train': 1.351629614830017} 08/30/2021 16:03:32 - INFO - __main__ - Step 15576: {'lr': 0.0004896923699933167, 'samples': 2990592, 'steps': 15575, 'loss/train': 1.7757244110107422} 08/30/2021 16:03:32 - INFO - __main__ - Step 15577: {'lr': 0.0004896908618424533, 'samples': 2990784, 'steps': 15576, 'loss/train': 0.904737651348114} 08/30/2021 16:03:32 - INFO - __main__ - Step 15578: {'lr': 0.0004896893535835889, 'samples': 2990976, 'steps': 15577, 'loss/train': 1.9108182191848755} 08/30/2021 16:03:34 - INFO - __main__ - Step 15579: {'lr': 0.0004896878452167241, 'samples': 2991168, 'steps': 15578, 'loss/train': 1.9039455652236938} 08/30/2021 16:03:35 - INFO - __main__ - Step 15580: {'lr': 0.0004896863367418598, 'samples': 2991360, 'steps': 15579, 'loss/train': 1.4533703327178955} 08/30/2021 16:03:35 - INFO - __main__ - Step 15581: {'lr': 0.0004896848281589966, 'samples': 2991552, 'steps': 15580, 'loss/train': 1.8411744832992554} 08/30/2021 16:03:35 - INFO - __main__ - Step 15582: {'lr': 0.0004896833194681349, 'samples': 2991744, 'steps': 15581, 'loss/train': 1.028562307357788} 08/30/2021 16:03:36 - INFO - __main__ - Step 15583: {'lr': 0.0004896818106692757, 'samples': 2991936, 'steps': 15582, 'loss/train': 1.3289109468460083} 08/30/2021 16:03:36 - INFO - __main__ - Step 15584: {'lr': 0.0004896803017624196, 'samples': 2992128, 'steps': 15583, 'loss/train': 2.1643829345703125} 08/30/2021 16:03:38 - INFO - __main__ - Step 15585: {'lr': 0.0004896787927475671, 'samples': 2992320, 'steps': 15584, 'loss/train': 1.8471970558166504} 08/30/2021 16:03:38 - INFO - __main__ - Step 15586: {'lr': 0.0004896772836247192, 'samples': 2992512, 'steps': 15585, 'loss/train': 0.6814278960227966} 08/30/2021 16:03:38 - INFO - __main__ - Step 15587: {'lr': 0.0004896757743938764, 'samples': 2992704, 'steps': 15586, 'loss/train': 1.236244559288025} 08/30/2021 16:03:39 - INFO - __main__ - Step 15588: {'lr': 0.0004896742650550393, 'samples': 2992896, 'steps': 15587, 'loss/train': 0.9975184202194214} 08/30/2021 16:03:39 - INFO - __main__ - Step 15589: {'lr': 0.0004896727556082086, 'samples': 2993088, 'steps': 15588, 'loss/train': 1.2266881465911865} 08/30/2021 16:03:41 - INFO - __main__ - Step 15590: {'lr': 0.0004896712460533854, 'samples': 2993280, 'steps': 15589, 'loss/train': 1.6080315113067627} 08/30/2021 16:03:41 - INFO - __main__ - Step 15591: {'lr': 0.0004896697363905697, 'samples': 2993472, 'steps': 15590, 'loss/train': 1.8571051359176636} 08/30/2021 16:03:41 - INFO - __main__ - Step 15592: {'lr': 0.0004896682266197626, 'samples': 2993664, 'steps': 15591, 'loss/train': 1.597836971282959} 08/30/2021 16:03:42 - INFO - __main__ - Step 15593: {'lr': 0.0004896667167409648, 'samples': 2993856, 'steps': 15592, 'loss/train': 1.7377614974975586} 08/30/2021 16:03:42 - INFO - __main__ - Step 15594: {'lr': 0.0004896652067541767, 'samples': 2994048, 'steps': 15593, 'loss/train': 2.089097738265991} 08/30/2021 16:03:44 - INFO - __main__ - Step 15595: {'lr': 0.0004896636966593993, 'samples': 2994240, 'steps': 15594, 'loss/train': 1.5005847215652466} 08/30/2021 16:03:44 - INFO - __main__ - Step 15596: {'lr': 0.0004896621864566331, 'samples': 2994432, 'steps': 15595, 'loss/train': 1.8175733089447021} 08/30/2021 16:03:44 - INFO - __main__ - Step 15597: {'lr': 0.0004896606761458788, 'samples': 2994624, 'steps': 15596, 'loss/train': 2.0225472450256348} 08/30/2021 16:03:45 - INFO - __main__ - Step 15598: {'lr': 0.0004896591657271371, 'samples': 2994816, 'steps': 15597, 'loss/train': 1.8359782695770264} 08/30/2021 16:03:45 - INFO - __main__ - Step 15599: {'lr': 0.0004896576552004087, 'samples': 2995008, 'steps': 15598, 'loss/train': 1.9440196752548218} 08/30/2021 16:03:47 - INFO - __main__ - Step 15600: {'lr': 0.0004896561445656943, 'samples': 2995200, 'steps': 15599, 'loss/train': 1.7889635562896729} 08/30/2021 16:03:47 - INFO - __main__ - Step 15601: {'lr': 0.0004896546338229945, 'samples': 2995392, 'steps': 15600, 'loss/train': 1.71900475025177} 08/30/2021 16:03:47 - INFO - __main__ - Step 15602: {'lr': 0.00048965312297231, 'samples': 2995584, 'steps': 15601, 'loss/train': 1.3022347688674927} 08/30/2021 16:03:48 - INFO - __main__ - Step 15603: {'lr': 0.0004896516120136415, 'samples': 2995776, 'steps': 15602, 'loss/train': 1.4900071620941162} 08/30/2021 16:03:48 - INFO - __main__ - Step 15604: {'lr': 0.0004896501009469896, 'samples': 2995968, 'steps': 15603, 'loss/train': 1.9007580280303955} 08/30/2021 16:03:50 - INFO - __main__ - Step 15605: {'lr': 0.0004896485897723552, 'samples': 2996160, 'steps': 15604, 'loss/train': 1.6240850687026978} 08/30/2021 16:03:50 - INFO - __main__ - Step 15606: {'lr': 0.0004896470784897388, 'samples': 2996352, 'steps': 15605, 'loss/train': 1.648932933807373} 08/30/2021 16:03:50 - INFO - __main__ - Step 15607: {'lr': 0.0004896455670991411, 'samples': 2996544, 'steps': 15606, 'loss/train': 2.3295695781707764} 08/30/2021 16:03:51 - INFO - __main__ - Step 15608: {'lr': 0.0004896440556005628, 'samples': 2996736, 'steps': 15607, 'loss/train': 1.33921480178833} 08/30/2021 16:03:51 - INFO - __main__ - Step 15609: {'lr': 0.0004896425439940047, 'samples': 2996928, 'steps': 15608, 'loss/train': 2.26648211479187} 08/30/2021 16:03:52 - INFO - __main__ - Step 15610: {'lr': 0.0004896410322794673, 'samples': 2997120, 'steps': 15609, 'loss/train': 2.101055145263672} 08/30/2021 16:03:53 - INFO - __main__ - Step 15611: {'lr': 0.0004896395204569512, 'samples': 2997312, 'steps': 15610, 'loss/train': 1.5403823852539062} 08/30/2021 16:03:54 - INFO - __main__ - Step 15612: {'lr': 0.0004896380085264573, 'samples': 2997504, 'steps': 15611, 'loss/train': 1.9643793106079102} 08/30/2021 16:03:54 - INFO - __main__ - Step 15613: {'lr': 0.0004896364964879864, 'samples': 2997696, 'steps': 15612, 'loss/train': 1.3354697227478027} 08/30/2021 16:03:54 - INFO - __main__ - Step 15614: {'lr': 0.0004896349843415389, 'samples': 2997888, 'steps': 15613, 'loss/train': 1.8205819129943848} 08/30/2021 16:03:55 - INFO - __main__ - Step 15615: {'lr': 0.0004896334720871156, 'samples': 2998080, 'steps': 15614, 'loss/train': 1.1578238010406494} 08/30/2021 16:03:57 - INFO - __main__ - Step 15616: {'lr': 0.0004896319597247169, 'samples': 2998272, 'steps': 15615, 'loss/train': 1.310843586921692} 08/30/2021 16:03:57 - INFO - __main__ - Step 15617: {'lr': 0.0004896304472543439, 'samples': 2998464, 'steps': 15616, 'loss/train': 1.4455901384353638} 08/30/2021 16:03:57 - INFO - __main__ - Step 15618: {'lr': 0.0004896289346759973, 'samples': 2998656, 'steps': 15617, 'loss/train': 2.1688995361328125} 08/30/2021 16:03:58 - INFO - __main__ - Step 15619: {'lr': 0.0004896274219896773, 'samples': 2998848, 'steps': 15618, 'loss/train': 1.1482386589050293} 08/30/2021 16:03:58 - INFO - __main__ - Step 15620: {'lr': 0.000489625909195385, 'samples': 2999040, 'steps': 15619, 'loss/train': 1.9774795770645142} 08/30/2021 16:04:00 - INFO - __main__ - Step 15621: {'lr': 0.0004896243962931211, 'samples': 2999232, 'steps': 15620, 'loss/train': 1.5860469341278076} 08/30/2021 16:04:01 - INFO - __main__ - Step 15622: {'lr': 0.0004896228832828861, 'samples': 2999424, 'steps': 15621, 'loss/train': 1.7794502973556519} 08/30/2021 16:04:01 - INFO - __main__ - Step 15623: {'lr': 0.0004896213701646806, 'samples': 2999616, 'steps': 15622, 'loss/train': 1.5514764785766602} 08/30/2021 16:04:01 - INFO - __main__ - Step 15624: {'lr': 0.0004896198569385055, 'samples': 2999808, 'steps': 15623, 'loss/train': 1.6653560400009155} 08/30/2021 16:04:02 - INFO - __main__ - Step 15625: {'lr': 0.0004896183436043613, 'samples': 3000000, 'steps': 15624, 'loss/train': 1.218605875968933} 08/30/2021 16:04:03 - INFO - __main__ - Step 15626: {'lr': 0.0004896168301622488, 'samples': 3000192, 'steps': 15625, 'loss/train': 1.5329443216323853} 08/30/2021 16:04:04 - INFO - __main__ - Step 15627: {'lr': 0.0004896153166121688, 'samples': 3000384, 'steps': 15626, 'loss/train': 2.0231528282165527} 08/30/2021 16:04:04 - INFO - __main__ - Step 15628: {'lr': 0.0004896138029541217, 'samples': 3000576, 'steps': 15627, 'loss/train': 2.0275752544403076} 08/30/2021 16:04:04 - INFO - __main__ - Step 15629: {'lr': 0.0004896122891881083, 'samples': 3000768, 'steps': 15628, 'loss/train': 1.9274102449417114} 08/30/2021 16:04:05 - INFO - __main__ - Step 15630: {'lr': 0.0004896107753141293, 'samples': 3000960, 'steps': 15629, 'loss/train': 1.6786177158355713} 08/30/2021 16:04:06 - INFO - __main__ - Step 15631: {'lr': 0.0004896092613321854, 'samples': 3001152, 'steps': 15630, 'loss/train': 1.7088583707809448} 08/30/2021 16:04:07 - INFO - __main__ - Step 15632: {'lr': 0.0004896077472422773, 'samples': 3001344, 'steps': 15631, 'loss/train': 1.5837279558181763} 08/30/2021 16:04:07 - INFO - __main__ - Step 15633: {'lr': 0.0004896062330444057, 'samples': 3001536, 'steps': 15632, 'loss/train': 1.5668208599090576} 08/30/2021 16:04:07 - INFO - __main__ - Step 15634: {'lr': 0.0004896047187385711, 'samples': 3001728, 'steps': 15633, 'loss/train': 1.3298778533935547} 08/30/2021 16:04:08 - INFO - __main__ - Step 15635: {'lr': 0.0004896032043247744, 'samples': 3001920, 'steps': 15634, 'loss/train': 1.4978915452957153} 08/30/2021 16:04:09 - INFO - __main__ - Step 15636: {'lr': 0.0004896016898030161, 'samples': 3002112, 'steps': 15635, 'loss/train': 1.8773466348648071} 08/30/2021 16:04:09 - INFO - __main__ - Step 15637: {'lr': 0.0004896001751732971, 'samples': 3002304, 'steps': 15636, 'loss/train': 1.8856909275054932} 08/30/2021 16:04:10 - INFO - __main__ - Step 15638: {'lr': 0.0004895986604356178, 'samples': 3002496, 'steps': 15637, 'loss/train': 1.6762871742248535} 08/30/2021 16:04:10 - INFO - __main__ - Step 15639: {'lr': 0.0004895971455899792, 'samples': 3002688, 'steps': 15638, 'loss/train': 1.5342628955841064} 08/30/2021 16:04:10 - INFO - __main__ - Step 15640: {'lr': 0.0004895956306363818, 'samples': 3002880, 'steps': 15639, 'loss/train': 2.096414804458618} 08/30/2021 16:04:11 - INFO - __main__ - Step 15641: {'lr': 0.0004895941155748263, 'samples': 3003072, 'steps': 15640, 'loss/train': 1.8845845460891724} 08/30/2021 16:04:12 - INFO - __main__ - Step 15642: {'lr': 0.0004895926004053133, 'samples': 3003264, 'steps': 15641, 'loss/train': 1.309841275215149} 08/30/2021 16:04:13 - INFO - __main__ - Step 15643: {'lr': 0.0004895910851278436, 'samples': 3003456, 'steps': 15642, 'loss/train': 1.4342775344848633} 08/30/2021 16:04:13 - INFO - __main__ - Step 15644: {'lr': 0.0004895895697424179, 'samples': 3003648, 'steps': 15643, 'loss/train': 1.3895652294158936} 08/30/2021 16:04:14 - INFO - __main__ - Step 15645: {'lr': 0.0004895880542490369, 'samples': 3003840, 'steps': 15644, 'loss/train': 1.7355033159255981} 08/30/2021 16:04:14 - INFO - __main__ - Step 15646: {'lr': 0.0004895865386477011, 'samples': 3004032, 'steps': 15645, 'loss/train': 1.8758642673492432} 08/30/2021 16:04:15 - INFO - __main__ - Step 15647: {'lr': 0.0004895850229384113, 'samples': 3004224, 'steps': 15646, 'loss/train': 1.4401111602783203} 08/30/2021 16:04:16 - INFO - __main__ - Step 15648: {'lr': 0.0004895835071211682, 'samples': 3004416, 'steps': 15647, 'loss/train': 1.859441876411438} 08/30/2021 16:04:16 - INFO - __main__ - Step 15649: {'lr': 0.0004895819911959725, 'samples': 3004608, 'steps': 15648, 'loss/train': 1.9605817794799805} 08/30/2021 16:04:16 - INFO - __main__ - Step 15650: {'lr': 0.0004895804751628249, 'samples': 3004800, 'steps': 15649, 'loss/train': 2.3211185932159424} 08/30/2021 16:04:17 - INFO - __main__ - Step 15651: {'lr': 0.0004895789590217259, 'samples': 3004992, 'steps': 15650, 'loss/train': 1.648622751235962} 08/30/2021 16:04:18 - INFO - __main__ - Step 15652: {'lr': 0.0004895774427726764, 'samples': 3005184, 'steps': 15651, 'loss/train': 1.631855845451355} 08/30/2021 16:04:19 - INFO - __main__ - Step 15653: {'lr': 0.000489575926415677, 'samples': 3005376, 'steps': 15652, 'loss/train': 1.496962070465088} 08/30/2021 16:04:19 - INFO - __main__ - Step 15654: {'lr': 0.0004895744099507284, 'samples': 3005568, 'steps': 15653, 'loss/train': 1.2107460498809814} 08/30/2021 16:04:20 - INFO - __main__ - Step 15655: {'lr': 0.0004895728933778313, 'samples': 3005760, 'steps': 15654, 'loss/train': 1.797992467880249} 08/30/2021 16:04:20 - INFO - __main__ - Step 15656: {'lr': 0.0004895713766969863, 'samples': 3005952, 'steps': 15655, 'loss/train': 1.4545979499816895} 08/30/2021 16:04:21 - INFO - __main__ - Step 15657: {'lr': 0.0004895698599081942, 'samples': 3006144, 'steps': 15656, 'loss/train': 1.5968542098999023} 08/30/2021 16:04:22 - INFO - __main__ - Step 15658: {'lr': 0.0004895683430114555, 'samples': 3006336, 'steps': 15657, 'loss/train': 3.075434923171997} 08/30/2021 16:04:22 - INFO - __main__ - Step 15659: {'lr': 0.0004895668260067711, 'samples': 3006528, 'steps': 15658, 'loss/train': 1.7385143041610718} 08/30/2021 16:04:23 - INFO - __main__ - Step 15660: {'lr': 0.0004895653088941416, 'samples': 3006720, 'steps': 15659, 'loss/train': 1.9182649850845337} 08/30/2021 16:04:23 - INFO - __main__ - Step 15661: {'lr': 0.0004895637916735675, 'samples': 3006912, 'steps': 15660, 'loss/train': 1.7979016304016113} 08/30/2021 16:04:25 - INFO - __main__ - Step 15662: {'lr': 0.0004895622743450497, 'samples': 3007104, 'steps': 15661, 'loss/train': 1.7512699365615845} 08/30/2021 16:04:25 - INFO - __main__ - Step 15663: {'lr': 0.000489560756908589, 'samples': 3007296, 'steps': 15662, 'loss/train': 0.8430560827255249} 08/30/2021 16:04:25 - INFO - __main__ - Step 15664: {'lr': 0.0004895592393641858, 'samples': 3007488, 'steps': 15663, 'loss/train': 1.425565242767334} 08/30/2021 16:04:26 - INFO - __main__ - Step 15665: {'lr': 0.0004895577217118408, 'samples': 3007680, 'steps': 15664, 'loss/train': 1.679845929145813} 08/30/2021 16:04:26 - INFO - __main__ - Step 15666: {'lr': 0.000489556203951555, 'samples': 3007872, 'steps': 15665, 'loss/train': 1.8205928802490234} 08/30/2021 16:04:26 - INFO - __main__ - Step 15667: {'lr': 0.0004895546860833287, 'samples': 3008064, 'steps': 15666, 'loss/train': 1.5674464702606201} 08/30/2021 16:04:28 - INFO - __main__ - Step 15668: {'lr': 0.000489553168107163, 'samples': 3008256, 'steps': 15667, 'loss/train': 2.0820534229278564} 08/30/2021 16:04:29 - INFO - __main__ - Step 15669: {'lr': 0.0004895516500230581, 'samples': 3008448, 'steps': 15668, 'loss/train': 1.8909108638763428} 08/30/2021 16:04:29 - INFO - __main__ - Step 15670: {'lr': 0.000489550131831015, 'samples': 3008640, 'steps': 15669, 'loss/train': 1.6744166612625122} 08/30/2021 16:04:29 - INFO - __main__ - Step 15671: {'lr': 0.0004895486135310343, 'samples': 3008832, 'steps': 15670, 'loss/train': 1.5791500806808472} 08/30/2021 16:04:30 - INFO - __main__ - Step 15672: {'lr': 0.0004895470951231166, 'samples': 3009024, 'steps': 15671, 'loss/train': 1.5914665460586548} 08/30/2021 16:04:31 - INFO - __main__ - Step 15673: {'lr': 0.0004895455766072629, 'samples': 3009216, 'steps': 15672, 'loss/train': 0.410793662071228} 08/30/2021 16:04:32 - INFO - __main__ - Step 15674: {'lr': 0.0004895440579834736, 'samples': 3009408, 'steps': 15673, 'loss/train': 1.7942060232162476} 08/30/2021 16:04:32 - INFO - __main__ - Step 15675: {'lr': 0.0004895425392517493, 'samples': 3009600, 'steps': 15674, 'loss/train': 1.6709843873977661} 08/30/2021 16:04:32 - INFO - __main__ - Step 15676: {'lr': 0.0004895410204120909, 'samples': 3009792, 'steps': 15675, 'loss/train': 1.6655640602111816} 08/30/2021 16:04:33 - INFO - __main__ - Step 15677: {'lr': 0.000489539501464499, 'samples': 3009984, 'steps': 15676, 'loss/train': 1.4968088865280151} 08/30/2021 16:04:35 - INFO - __main__ - Step 15678: {'lr': 0.0004895379824089743, 'samples': 3010176, 'steps': 15677, 'loss/train': 2.078408718109131} 08/30/2021 16:04:35 - INFO - __main__ - Step 15679: {'lr': 0.0004895364632455175, 'samples': 3010368, 'steps': 15678, 'loss/train': 1.7145956754684448} 08/30/2021 16:04:36 - INFO - __main__ - Step 15680: {'lr': 0.0004895349439741292, 'samples': 3010560, 'steps': 15679, 'loss/train': 2.807765483856201} 08/30/2021 16:04:36 - INFO - __main__ - Step 15681: {'lr': 0.0004895334245948103, 'samples': 3010752, 'steps': 15680, 'loss/train': 2.011272430419922} 08/30/2021 16:04:36 - INFO - __main__ - Step 15682: {'lr': 0.0004895319051075612, 'samples': 3010944, 'steps': 15681, 'loss/train': 1.902477741241455} 08/30/2021 16:04:38 - INFO - __main__ - Step 15683: {'lr': 0.0004895303855123828, 'samples': 3011136, 'steps': 15682, 'loss/train': 1.9463393688201904} 08/30/2021 16:04:38 - INFO - __main__ - Step 15684: {'lr': 0.0004895288658092757, 'samples': 3011328, 'steps': 15683, 'loss/train': 1.6282411813735962} 08/30/2021 16:04:39 - INFO - __main__ - Step 15685: {'lr': 0.0004895273459982406, 'samples': 3011520, 'steps': 15684, 'loss/train': 1.6483428478240967} 08/30/2021 16:04:39 - INFO - __main__ - Step 15686: {'lr': 0.0004895258260792781, 'samples': 3011712, 'steps': 15685, 'loss/train': 1.8689420223236084} 08/30/2021 16:04:39 - INFO - __main__ - Step 15687: {'lr': 0.0004895243060523889, 'samples': 3011904, 'steps': 15686, 'loss/train': 1.473405122756958} 08/30/2021 16:04:41 - INFO - __main__ - Step 15688: {'lr': 0.0004895227859175739, 'samples': 3012096, 'steps': 15687, 'loss/train': 1.5170730352401733} 08/30/2021 16:04:42 - INFO - __main__ - Step 15689: {'lr': 0.0004895212656748336, 'samples': 3012288, 'steps': 15688, 'loss/train': 0.24248376488685608} 08/30/2021 16:04:42 - INFO - __main__ - Step 15690: {'lr': 0.0004895197453241687, 'samples': 3012480, 'steps': 15689, 'loss/train': 2.572460174560547} 08/30/2021 16:04:43 - INFO - __main__ - Step 15691: {'lr': 0.0004895182248655798, 'samples': 3012672, 'steps': 15690, 'loss/train': 1.790162205696106} 08/30/2021 16:04:43 - INFO - __main__ - Step 15692: {'lr': 0.0004895167042990678, 'samples': 3012864, 'steps': 15691, 'loss/train': 1.0607959032058716} 08/30/2021 16:04:44 - INFO - __main__ - Step 15693: {'lr': 0.0004895151836246332, 'samples': 3013056, 'steps': 15692, 'loss/train': 1.7529367208480835} 08/30/2021 16:04:45 - INFO - __main__ - Step 15694: {'lr': 0.0004895136628422767, 'samples': 3013248, 'steps': 15693, 'loss/train': 1.3572545051574707} 08/30/2021 16:04:45 - INFO - __main__ - Step 15695: {'lr': 0.0004895121419519992, 'samples': 3013440, 'steps': 15694, 'loss/train': 1.9496676921844482} 08/30/2021 16:04:45 - INFO - __main__ - Step 15696: {'lr': 0.0004895106209538011, 'samples': 3013632, 'steps': 15695, 'loss/train': 1.5155653953552246} 08/30/2021 16:04:46 - INFO - __main__ - Step 15697: {'lr': 0.0004895090998476833, 'samples': 3013824, 'steps': 15696, 'loss/train': 1.7715060710906982} 08/30/2021 16:04:47 - INFO - __main__ - Step 15698: {'lr': 0.0004895075786336463, 'samples': 3014016, 'steps': 15697, 'loss/train': 2.041308879852295} 08/30/2021 16:04:48 - INFO - __main__ - Step 15699: {'lr': 0.000489506057311691, 'samples': 3014208, 'steps': 15698, 'loss/train': 1.2994133234024048} 08/30/2021 16:04:48 - INFO - __main__ - Step 15700: {'lr': 0.0004895045358818179, 'samples': 3014400, 'steps': 15699, 'loss/train': 1.5458451509475708} 08/30/2021 16:04:48 - INFO - __main__ - Step 15701: {'lr': 0.0004895030143440278, 'samples': 3014592, 'steps': 15700, 'loss/train': 2.004124164581299} 08/30/2021 16:04:49 - INFO - __main__ - Step 15702: {'lr': 0.0004895014926983212, 'samples': 3014784, 'steps': 15701, 'loss/train': 1.2008405923843384} 08/30/2021 16:04:49 - INFO - __main__ - Step 15703: {'lr': 0.0004894999709446991, 'samples': 3014976, 'steps': 15702, 'loss/train': 1.6882003545761108} 08/30/2021 16:04:51 - INFO - __main__ - Step 15704: {'lr': 0.0004894984490831619, 'samples': 3015168, 'steps': 15703, 'loss/train': 1.5917606353759766} 08/30/2021 16:04:51 - INFO - __main__ - Step 15705: {'lr': 0.0004894969271137104, 'samples': 3015360, 'steps': 15704, 'loss/train': 0.23126155138015747} 08/30/2021 16:04:52 - INFO - __main__ - Step 15706: {'lr': 0.0004894954050363452, 'samples': 3015552, 'steps': 15705, 'loss/train': 1.0706652402877808} 08/30/2021 16:04:52 - INFO - __main__ - Step 15707: {'lr': 0.0004894938828510672, 'samples': 3015744, 'steps': 15706, 'loss/train': 1.2698158025741577} 08/30/2021 16:04:53 - INFO - __main__ - Step 15708: {'lr': 0.000489492360557877, 'samples': 3015936, 'steps': 15707, 'loss/train': 0.8350092768669128} 08/30/2021 16:04:53 - INFO - __main__ - Step 15709: {'lr': 0.0004894908381567751, 'samples': 3016128, 'steps': 15708, 'loss/train': 2.3612992763519287} 08/30/2021 16:04:54 - INFO - __main__ - Step 15710: {'lr': 0.0004894893156477623, 'samples': 3016320, 'steps': 15709, 'loss/train': 1.7201426029205322} 08/30/2021 16:04:55 - INFO - __main__ - Step 15711: {'lr': 0.0004894877930308395, 'samples': 3016512, 'steps': 15710, 'loss/train': 1.4212003946304321} 08/30/2021 16:04:55 - INFO - __main__ - Step 15712: {'lr': 0.0004894862703060071, 'samples': 3016704, 'steps': 15711, 'loss/train': 2.0885603427886963} 08/30/2021 16:04:55 - INFO - __main__ - Step 15713: {'lr': 0.0004894847474732658, 'samples': 3016896, 'steps': 15712, 'loss/train': 2.1898651123046875} 08/30/2021 16:04:56 - INFO - __main__ - Step 15714: {'lr': 0.0004894832245326165, 'samples': 3017088, 'steps': 15713, 'loss/train': 1.267521619796753} 08/30/2021 16:04:57 - INFO - __main__ - Step 15715: {'lr': 0.0004894817014840597, 'samples': 3017280, 'steps': 15714, 'loss/train': 1.5059354305267334} 08/30/2021 16:04:58 - INFO - __main__ - Step 15716: {'lr': 0.0004894801783275961, 'samples': 3017472, 'steps': 15715, 'loss/train': 1.5661461353302002} 08/30/2021 16:04:58 - INFO - __main__ - Step 15717: {'lr': 0.0004894786550632264, 'samples': 3017664, 'steps': 15716, 'loss/train': 1.3200610876083374} 08/30/2021 16:04:58 - INFO - __main__ - Step 15718: {'lr': 0.0004894771316909514, 'samples': 3017856, 'steps': 15717, 'loss/train': 1.5051206350326538} 08/30/2021 16:04:59 - INFO - __main__ - Step 15719: {'lr': 0.0004894756082107717, 'samples': 3018048, 'steps': 15718, 'loss/train': 1.4719260931015015} 08/30/2021 16:05:00 - INFO - __main__ - Step 15720: {'lr': 0.0004894740846226879, 'samples': 3018240, 'steps': 15719, 'loss/train': 1.7230294942855835} 08/30/2021 16:05:01 - INFO - __main__ - Step 15721: {'lr': 0.0004894725609267009, 'samples': 3018432, 'steps': 15720, 'loss/train': 1.6836109161376953} 08/30/2021 16:05:01 - INFO - __main__ - Step 15722: {'lr': 0.0004894710371228111, 'samples': 3018624, 'steps': 15721, 'loss/train': 2.2346858978271484} 08/30/2021 16:05:02 - INFO - __main__ - Step 15723: {'lr': 0.0004894695132110196, 'samples': 3018816, 'steps': 15722, 'loss/train': 1.240833044052124} 08/30/2021 16:05:02 - INFO - __main__ - Step 15724: {'lr': 0.0004894679891913266, 'samples': 3019008, 'steps': 15723, 'loss/train': 1.9928617477416992} 08/30/2021 16:05:02 - INFO - __main__ - Step 15725: {'lr': 0.000489466465063733, 'samples': 3019200, 'steps': 15724, 'loss/train': 1.71743905544281} 08/30/2021 16:05:04 - INFO - __main__ - Step 15726: {'lr': 0.0004894649408282396, 'samples': 3019392, 'steps': 15725, 'loss/train': 1.3347309827804565} 08/30/2021 16:05:04 - INFO - __main__ - Step 15727: {'lr': 0.000489463416484847, 'samples': 3019584, 'steps': 15726, 'loss/train': 2.6286916732788086} 08/30/2021 16:05:05 - INFO - __main__ - Step 15728: {'lr': 0.0004894618920335558, 'samples': 3019776, 'steps': 15727, 'loss/train': 1.3679033517837524} 08/30/2021 16:05:05 - INFO - __main__ - Step 15729: {'lr': 0.0004894603674743668, 'samples': 3019968, 'steps': 15728, 'loss/train': 1.9781831502914429} 08/30/2021 16:05:05 - INFO - __main__ - Step 15730: {'lr': 0.0004894588428072808, 'samples': 3020160, 'steps': 15729, 'loss/train': 2.1462972164154053} 08/30/2021 16:05:07 - INFO - __main__ - Step 15731: {'lr': 0.0004894573180322982, 'samples': 3020352, 'steps': 15730, 'loss/train': 1.7896645069122314} 08/30/2021 16:05:08 - INFO - __main__ - Step 15732: {'lr': 0.0004894557931494199, 'samples': 3020544, 'steps': 15731, 'loss/train': 1.843048334121704} 08/30/2021 16:05:08 - INFO - __main__ - Step 15733: {'lr': 0.0004894542681586465, 'samples': 3020736, 'steps': 15732, 'loss/train': 1.7974251508712769} 08/30/2021 16:05:09 - INFO - __main__ - Step 15734: {'lr': 0.0004894527430599786, 'samples': 3020928, 'steps': 15733, 'loss/train': 1.9471001625061035} 08/30/2021 16:05:09 - INFO - __main__ - Step 15735: {'lr': 0.0004894512178534171, 'samples': 3021120, 'steps': 15734, 'loss/train': 1.8450522422790527} 08/30/2021 16:05:10 - INFO - __main__ - Step 15736: {'lr': 0.0004894496925389625, 'samples': 3021312, 'steps': 15735, 'loss/train': 1.952476143836975} 08/30/2021 16:05:11 - INFO - __main__ - Step 15737: {'lr': 0.0004894481671166155, 'samples': 3021504, 'steps': 15736, 'loss/train': 1.9185781478881836} 08/30/2021 16:05:11 - INFO - __main__ - Step 15738: {'lr': 0.0004894466415863771, 'samples': 3021696, 'steps': 15737, 'loss/train': 1.8842803239822388} 08/30/2021 16:05:12 - INFO - __main__ - Step 15739: {'lr': 0.0004894451159482476, 'samples': 3021888, 'steps': 15738, 'loss/train': 1.6598477363586426} 08/30/2021 16:05:12 - INFO - __main__ - Step 15740: {'lr': 0.0004894435902022277, 'samples': 3022080, 'steps': 15739, 'loss/train': 2.236760139465332} 08/30/2021 16:05:14 - INFO - __main__ - Step 15741: {'lr': 0.0004894420643483184, 'samples': 3022272, 'steps': 15740, 'loss/train': 1.7471964359283447} 08/30/2021 16:05:14 - INFO - __main__ - Step 15742: {'lr': 0.0004894405383865201, 'samples': 3022464, 'steps': 15741, 'loss/train': 1.1105577945709229} 08/30/2021 16:05:15 - INFO - __main__ - Step 15743: {'lr': 0.0004894390123168337, 'samples': 3022656, 'steps': 15742, 'loss/train': 1.852920413017273} 08/30/2021 16:05:15 - INFO - __main__ - Step 15744: {'lr': 0.0004894374861392596, 'samples': 3022848, 'steps': 15743, 'loss/train': 1.7588038444519043} 08/30/2021 16:05:15 - INFO - __main__ - Step 15745: {'lr': 0.0004894359598537987, 'samples': 3023040, 'steps': 15744, 'loss/train': 1.2188833951950073} 08/30/2021 16:05:17 - INFO - __main__ - Step 15746: {'lr': 0.0004894344334604517, 'samples': 3023232, 'steps': 15745, 'loss/train': 1.872450590133667} 08/30/2021 16:05:17 - INFO - __main__ - Step 15747: {'lr': 0.0004894329069592192, 'samples': 3023424, 'steps': 15746, 'loss/train': 1.7818655967712402} 08/30/2021 16:05:18 - INFO - __main__ - Step 15748: {'lr': 0.000489431380350102, 'samples': 3023616, 'steps': 15747, 'loss/train': 1.5086807012557983} 08/30/2021 16:05:18 - INFO - __main__ - Step 15749: {'lr': 0.0004894298536331007, 'samples': 3023808, 'steps': 15748, 'loss/train': 1.1315829753875732} 08/30/2021 16:05:18 - INFO - __main__ - Step 15750: {'lr': 0.000489428326808216, 'samples': 3024000, 'steps': 15749, 'loss/train': 1.984466314315796} 08/30/2021 16:05:20 - INFO - __main__ - Step 15751: {'lr': 0.0004894267998754486, 'samples': 3024192, 'steps': 15750, 'loss/train': 2.230523109436035} 08/30/2021 16:05:20 - INFO - __main__ - Step 15752: {'lr': 0.0004894252728347992, 'samples': 3024384, 'steps': 15751, 'loss/train': 1.0668296813964844} 08/30/2021 16:05:21 - INFO - __main__ - Step 15753: {'lr': 0.0004894237456862684, 'samples': 3024576, 'steps': 15752, 'loss/train': 2.916994333267212} 08/30/2021 16:05:21 - INFO - __main__ - Step 15754: {'lr': 0.000489422218429857, 'samples': 3024768, 'steps': 15753, 'loss/train': 1.766281247138977} 08/30/2021 16:05:21 - INFO - __main__ - Step 15755: {'lr': 0.0004894206910655656, 'samples': 3024960, 'steps': 15754, 'loss/train': 2.572554349899292} 08/30/2021 16:05:23 - INFO - __main__ - Step 15756: {'lr': 0.0004894191635933949, 'samples': 3025152, 'steps': 15755, 'loss/train': 1.671134114265442} 08/30/2021 16:05:23 - INFO - __main__ - Step 15757: {'lr': 0.0004894176360133456, 'samples': 3025344, 'steps': 15756, 'loss/train': 1.7096961736679077} 08/30/2021 16:05:24 - INFO - __main__ - Step 15758: {'lr': 0.0004894161083254186, 'samples': 3025536, 'steps': 15757, 'loss/train': 1.6784322261810303} 08/30/2021 16:05:24 - INFO - __main__ - Step 15759: {'lr': 0.0004894145805296143, 'samples': 3025728, 'steps': 15758, 'loss/train': 2.076785087585449} 08/30/2021 16:05:24 - INFO - __main__ - Step 15760: {'lr': 0.0004894130526259334, 'samples': 3025920, 'steps': 15759, 'loss/train': 1.7659324407577515} 08/30/2021 16:05:26 - INFO - __main__ - Step 15761: {'lr': 0.0004894115246143768, 'samples': 3026112, 'steps': 15760, 'loss/train': 0.3448126018047333} 08/30/2021 16:05:26 - INFO - __main__ - Step 15762: {'lr': 0.0004894099964949449, 'samples': 3026304, 'steps': 15761, 'loss/train': 2.420470714569092} 08/30/2021 16:05:27 - INFO - __main__ - Step 15763: {'lr': 0.0004894084682676387, 'samples': 3026496, 'steps': 15762, 'loss/train': 2.1055173873901367} 08/30/2021 16:05:27 - INFO - __main__ - Step 15764: {'lr': 0.0004894069399324586, 'samples': 3026688, 'steps': 15763, 'loss/train': 1.9874101877212524} 08/30/2021 16:05:27 - INFO - __main__ - Step 15765: {'lr': 0.0004894054114894055, 'samples': 3026880, 'steps': 15764, 'loss/train': 1.9154988527297974} 08/30/2021 16:05:28 - INFO - __main__ - Step 15766: {'lr': 0.00048940388293848, 'samples': 3027072, 'steps': 15765, 'loss/train': 1.456554889678955} 08/30/2021 16:05:29 - INFO - __main__ - Step 15767: {'lr': 0.000489402354279683, 'samples': 3027264, 'steps': 15766, 'loss/train': 1.8956642150878906} 08/30/2021 16:05:30 - INFO - __main__ - Step 15768: {'lr': 0.0004894008255130147, 'samples': 3027456, 'steps': 15767, 'loss/train': 1.8803777694702148} 08/30/2021 16:05:30 - INFO - __main__ - Step 15769: {'lr': 0.0004893992966384762, 'samples': 3027648, 'steps': 15768, 'loss/train': 1.9418342113494873} 08/30/2021 16:05:30 - INFO - __main__ - Step 15770: {'lr': 0.0004893977676560682, 'samples': 3027840, 'steps': 15769, 'loss/train': 1.8949304819107056} 08/30/2021 16:05:31 - INFO - __main__ - Step 15771: {'lr': 0.000489396238565791, 'samples': 3028032, 'steps': 15770, 'loss/train': 0.8951969146728516} 08/30/2021 16:05:32 - INFO - __main__ - Step 15772: {'lr': 0.0004893947093676458, 'samples': 3028224, 'steps': 15771, 'loss/train': 1.8372505903244019} 08/30/2021 16:05:33 - INFO - __main__ - Step 15773: {'lr': 0.0004893931800616329, 'samples': 3028416, 'steps': 15772, 'loss/train': 2.0663514137268066} 08/30/2021 16:05:33 - INFO - __main__ - Step 15774: {'lr': 0.0004893916506477532, 'samples': 3028608, 'steps': 15773, 'loss/train': 1.3187042474746704} 08/30/2021 16:05:33 - INFO - __main__ - Step 15775: {'lr': 0.0004893901211260073, 'samples': 3028800, 'steps': 15774, 'loss/train': 2.269486665725708} 08/30/2021 16:05:34 - INFO - __main__ - Step 15776: {'lr': 0.0004893885914963958, 'samples': 3028992, 'steps': 15775, 'loss/train': 1.5242422819137573} 08/30/2021 16:05:35 - INFO - __main__ - Step 15777: {'lr': 0.0004893870617589196, 'samples': 3029184, 'steps': 15776, 'loss/train': 1.0224928855895996} 08/30/2021 16:05:36 - INFO - __main__ - Step 15778: {'lr': 0.0004893855319135791, 'samples': 3029376, 'steps': 15777, 'loss/train': 1.6880754232406616} 08/30/2021 16:05:36 - INFO - __main__ - Step 15779: {'lr': 0.0004893840019603754, 'samples': 3029568, 'steps': 15778, 'loss/train': 1.4016624689102173} 08/30/2021 16:05:36 - INFO - __main__ - Step 15780: {'lr': 0.0004893824718993088, 'samples': 3029760, 'steps': 15779, 'loss/train': 1.8057093620300293} 08/30/2021 16:05:37 - INFO - __main__ - Step 15781: {'lr': 0.0004893809417303803, 'samples': 3029952, 'steps': 15780, 'loss/train': 1.8039134740829468} 08/30/2021 16:05:39 - INFO - __main__ - Step 15782: {'lr': 0.0004893794114535905, 'samples': 3030144, 'steps': 15781, 'loss/train': 1.7117946147918701} 08/30/2021 16:05:39 - INFO - __main__ - Step 15783: {'lr': 0.0004893778810689399, 'samples': 3030336, 'steps': 15782, 'loss/train': 1.8342255353927612} 08/30/2021 16:05:39 - INFO - __main__ - Step 15784: {'lr': 0.0004893763505764292, 'samples': 3030528, 'steps': 15783, 'loss/train': 1.4451026916503906} 08/30/2021 16:05:40 - INFO - __main__ - Step 15785: {'lr': 0.0004893748199760594, 'samples': 3030720, 'steps': 15784, 'loss/train': 0.1269480586051941} 08/30/2021 16:05:40 - INFO - __main__ - Step 15786: {'lr': 0.0004893732892678309, 'samples': 3030912, 'steps': 15785, 'loss/train': 1.6834965944290161} 08/30/2021 16:05:40 - INFO - __main__ - Step 15787: {'lr': 0.0004893717584517445, 'samples': 3031104, 'steps': 15786, 'loss/train': 0.7068189978599548} 08/30/2021 16:05:42 - INFO - __main__ - Step 15788: {'lr': 0.000489370227527801, 'samples': 3031296, 'steps': 15787, 'loss/train': 0.6516126990318298} 08/30/2021 16:05:43 - INFO - __main__ - Step 15789: {'lr': 0.0004893686964960009, 'samples': 3031488, 'steps': 15788, 'loss/train': 1.4837327003479004} 08/30/2021 16:05:43 - INFO - __main__ - Step 15790: {'lr': 0.0004893671653563448, 'samples': 3031680, 'steps': 15789, 'loss/train': 2.016655445098877} 08/30/2021 16:05:44 - INFO - __main__ - Step 15791: {'lr': 0.0004893656341088338, 'samples': 3031872, 'steps': 15790, 'loss/train': 1.369646430015564} 08/30/2021 16:05:44 - INFO - __main__ - Step 15792: {'lr': 0.0004893641027534682, 'samples': 3032064, 'steps': 15791, 'loss/train': 1.9633276462554932} 08/30/2021 16:05:46 - INFO - __main__ - Step 15793: {'lr': 0.0004893625712902489, 'samples': 3032256, 'steps': 15792, 'loss/train': 1.4365977048873901} 08/30/2021 16:05:46 - INFO - __main__ - Step 15794: {'lr': 0.0004893610397191764, 'samples': 3032448, 'steps': 15793, 'loss/train': 1.6184943914413452} 08/30/2021 16:05:46 - INFO - __main__ - Step 15795: {'lr': 0.0004893595080402517, 'samples': 3032640, 'steps': 15794, 'loss/train': 1.0569422245025635} 08/30/2021 16:05:47 - INFO - __main__ - Step 15796: {'lr': 0.0004893579762534751, 'samples': 3032832, 'steps': 15795, 'loss/train': 1.966475486755371} 08/30/2021 16:05:47 - INFO - __main__ - Step 15797: {'lr': 0.0004893564443588476, 'samples': 3033024, 'steps': 15796, 'loss/train': 1.7992537021636963} 08/30/2021 16:05:49 - INFO - __main__ - Step 15798: {'lr': 0.0004893549123563697, 'samples': 3033216, 'steps': 15797, 'loss/train': 1.788185477256775} 08/30/2021 16:05:49 - INFO - __main__ - Step 15799: {'lr': 0.0004893533802460422, 'samples': 3033408, 'steps': 15798, 'loss/train': 1.57007896900177} 08/30/2021 16:05:49 - INFO - __main__ - Step 15800: {'lr': 0.0004893518480278658, 'samples': 3033600, 'steps': 15799, 'loss/train': 2.435354232788086} 08/30/2021 16:05:50 - INFO - __main__ - Step 15801: {'lr': 0.0004893503157018412, 'samples': 3033792, 'steps': 15800, 'loss/train': 1.724379301071167} 08/30/2021 16:05:50 - INFO - __main__ - Step 15802: {'lr': 0.000489348783267969, 'samples': 3033984, 'steps': 15801, 'loss/train': 1.6994962692260742} 08/30/2021 16:05:50 - INFO - __main__ - Step 15803: {'lr': 0.0004893472507262499, 'samples': 3034176, 'steps': 15802, 'loss/train': 2.779169797897339} 08/30/2021 16:05:52 - INFO - __main__ - Step 15804: {'lr': 0.0004893457180766846, 'samples': 3034368, 'steps': 15803, 'loss/train': 1.732416033744812} 08/30/2021 16:05:53 - INFO - __main__ - Step 15805: {'lr': 0.0004893441853192739, 'samples': 3034560, 'steps': 15804, 'loss/train': 1.6029468774795532} 08/30/2021 16:05:53 - INFO - __main__ - Step 15806: {'lr': 0.0004893426524540183, 'samples': 3034752, 'steps': 15805, 'loss/train': 2.099090099334717} 08/30/2021 16:05:53 - INFO - __main__ - Step 15807: {'lr': 0.0004893411194809186, 'samples': 3034944, 'steps': 15806, 'loss/train': 1.7839194536209106} 08/30/2021 16:05:54 - INFO - __main__ - Step 15808: {'lr': 0.0004893395863999755, 'samples': 3035136, 'steps': 15807, 'loss/train': 1.5603755712509155} 08/30/2021 16:05:55 - INFO - __main__ - Step 15809: {'lr': 0.0004893380532111898, 'samples': 3035328, 'steps': 15808, 'loss/train': 1.5778244733810425} 08/30/2021 16:05:56 - INFO - __main__ - Step 15810: {'lr': 0.0004893365199145619, 'samples': 3035520, 'steps': 15809, 'loss/train': 1.8768761157989502} 08/30/2021 16:05:56 - INFO - __main__ - Step 15811: {'lr': 0.0004893349865100927, 'samples': 3035712, 'steps': 15810, 'loss/train': 1.9645310640335083} 08/30/2021 16:05:56 - INFO - __main__ - Step 15812: {'lr': 0.0004893334529977828, 'samples': 3035904, 'steps': 15811, 'loss/train': 1.8728632926940918} 08/30/2021 16:05:57 - INFO - __main__ - Step 15813: {'lr': 0.0004893319193776331, 'samples': 3036096, 'steps': 15812, 'loss/train': 1.7371985912322998} 08/30/2021 16:05:58 - INFO - __main__ - Step 15814: {'lr': 0.000489330385649644, 'samples': 3036288, 'steps': 15813, 'loss/train': 1.9565091133117676} 08/30/2021 16:05:59 - INFO - __main__ - Step 15815: {'lr': 0.0004893288518138163, 'samples': 3036480, 'steps': 15814, 'loss/train': 1.8143585920333862} 08/30/2021 16:05:59 - INFO - __main__ - Step 15816: {'lr': 0.0004893273178701508, 'samples': 3036672, 'steps': 15815, 'loss/train': 1.7400017976760864} 08/30/2021 16:05:59 - INFO - __main__ - Step 15817: {'lr': 0.0004893257838186481, 'samples': 3036864, 'steps': 15816, 'loss/train': 2.777813673019409} 08/30/2021 16:06:00 - INFO - __main__ - Step 15818: {'lr': 0.0004893242496593089, 'samples': 3037056, 'steps': 15817, 'loss/train': 2.0366008281707764} 08/30/2021 16:06:01 - INFO - __main__ - Step 15819: {'lr': 0.0004893227153921338, 'samples': 3037248, 'steps': 15818, 'loss/train': 1.7623364925384521} 08/30/2021 16:06:02 - INFO - __main__ - Step 15820: {'lr': 0.0004893211810171237, 'samples': 3037440, 'steps': 15819, 'loss/train': 1.1324254274368286} 08/30/2021 16:06:02 - INFO - __main__ - Step 15821: {'lr': 0.0004893196465342791, 'samples': 3037632, 'steps': 15820, 'loss/train': 2.2985141277313232} 08/30/2021 16:06:02 - INFO - __main__ - Step 15822: {'lr': 0.0004893181119436007, 'samples': 3037824, 'steps': 15821, 'loss/train': 1.7648950815200806} 08/30/2021 16:06:03 - INFO - __main__ - Step 15823: {'lr': 0.0004893165772450893, 'samples': 3038016, 'steps': 15822, 'loss/train': 1.7349241971969604} 08/30/2021 16:06:04 - INFO - __main__ - Step 15824: {'lr': 0.0004893150424387456, 'samples': 3038208, 'steps': 15823, 'loss/train': 1.8271968364715576} 08/30/2021 16:06:05 - INFO - __main__ - Step 15825: {'lr': 0.0004893135075245702, 'samples': 3038400, 'steps': 15824, 'loss/train': 1.7137402296066284} 08/30/2021 16:06:05 - INFO - __main__ - Step 15826: {'lr': 0.0004893119725025639, 'samples': 3038592, 'steps': 15825, 'loss/train': 1.4959312677383423} 08/30/2021 16:06:06 - INFO - __main__ - Step 15827: {'lr': 0.0004893104373727272, 'samples': 3038784, 'steps': 15826, 'loss/train': 1.7496213912963867} 08/30/2021 16:06:06 - INFO - __main__ - Step 15828: {'lr': 0.0004893089021350609, 'samples': 3038976, 'steps': 15827, 'loss/train': 1.48745596408844} 08/30/2021 16:06:07 - INFO - __main__ - Step 15829: {'lr': 0.0004893073667895658, 'samples': 3039168, 'steps': 15828, 'loss/train': 0.20793157815933228} 08/30/2021 16:06:08 - INFO - __main__ - Step 15830: {'lr': 0.0004893058313362424, 'samples': 3039360, 'steps': 15829, 'loss/train': 2.057208776473999} 08/30/2021 16:06:08 - INFO - __main__ - Step 15831: {'lr': 0.0004893042957750916, 'samples': 3039552, 'steps': 15830, 'loss/train': 1.514568567276001} 08/30/2021 16:06:09 - INFO - __main__ - Step 15832: {'lr': 0.0004893027601061138, 'samples': 3039744, 'steps': 15831, 'loss/train': 1.5174131393432617} 08/30/2021 16:06:09 - INFO - __main__ - Step 15833: {'lr': 0.00048930122432931, 'samples': 3039936, 'steps': 15832, 'loss/train': 1.8271756172180176} 08/30/2021 16:06:09 - INFO - __main__ - Step 15834: {'lr': 0.0004892996884446807, 'samples': 3040128, 'steps': 15833, 'loss/train': 1.2590651512145996} 08/30/2021 16:06:11 - INFO - __main__ - Step 15835: {'lr': 0.0004892981524522267, 'samples': 3040320, 'steps': 15834, 'loss/train': 1.8676629066467285} 08/30/2021 16:06:12 - INFO - __main__ - Step 15836: {'lr': 0.0004892966163519487, 'samples': 3040512, 'steps': 15835, 'loss/train': 1.9099675416946411} 08/30/2021 16:06:12 - INFO - __main__ - Step 15837: {'lr': 0.0004892950801438472, 'samples': 3040704, 'steps': 15836, 'loss/train': 1.5653126239776611} 08/30/2021 16:06:12 - INFO - __main__ - Step 15838: {'lr': 0.0004892935438279231, 'samples': 3040896, 'steps': 15837, 'loss/train': 1.9078892469406128} 08/30/2021 16:06:13 - INFO - __main__ - Step 15839: {'lr': 0.0004892920074041771, 'samples': 3041088, 'steps': 15838, 'loss/train': 1.8621835708618164} 08/30/2021 16:06:13 - INFO - __main__ - Step 15840: {'lr': 0.0004892904708726096, 'samples': 3041280, 'steps': 15839, 'loss/train': 1.7209863662719727} 08/30/2021 16:06:15 - INFO - __main__ - Step 15841: {'lr': 0.0004892889342332218, 'samples': 3041472, 'steps': 15840, 'loss/train': 1.2462749481201172} 08/30/2021 16:06:16 - INFO - __main__ - Step 15842: {'lr': 0.000489287397486014, 'samples': 3041664, 'steps': 15841, 'loss/train': 1.5948426723480225} 08/30/2021 16:06:16 - INFO - __main__ - Step 15843: {'lr': 0.0004892858606309868, 'samples': 3041856, 'steps': 15842, 'loss/train': 1.6169359683990479} 08/30/2021 16:06:16 - INFO - __main__ - Step 15844: {'lr': 0.0004892843236681412, 'samples': 3042048, 'steps': 15843, 'loss/train': 1.8096169233322144} 08/30/2021 16:06:17 - INFO - __main__ - Step 15845: {'lr': 0.0004892827865974779, 'samples': 3042240, 'steps': 15844, 'loss/train': 1.927626609802246} 08/30/2021 16:06:18 - INFO - __main__ - Step 15846: {'lr': 0.0004892812494189973, 'samples': 3042432, 'steps': 15845, 'loss/train': 1.567002534866333} 08/30/2021 16:06:19 - INFO - __main__ - Step 15847: {'lr': 0.0004892797121327003, 'samples': 3042624, 'steps': 15846, 'loss/train': 1.6373697519302368} 08/30/2021 16:06:19 - INFO - __main__ - Step 15848: {'lr': 0.0004892781747385876, 'samples': 3042816, 'steps': 15847, 'loss/train': 1.892551064491272} 08/30/2021 16:06:19 - INFO - __main__ - Step 15849: {'lr': 0.0004892766372366598, 'samples': 3043008, 'steps': 15848, 'loss/train': 2.0063562393188477} 08/30/2021 16:06:20 - INFO - __main__ - Step 15850: {'lr': 0.0004892750996269177, 'samples': 3043200, 'steps': 15849, 'loss/train': 2.2678918838500977} 08/30/2021 16:06:21 - INFO - __main__ - Step 15851: {'lr': 0.0004892735619093618, 'samples': 3043392, 'steps': 15850, 'loss/train': 2.7943601608276367} 08/30/2021 16:06:22 - INFO - __main__ - Step 15852: {'lr': 0.0004892720240839931, 'samples': 3043584, 'steps': 15851, 'loss/train': 1.4127070903778076} 08/30/2021 16:06:22 - INFO - __main__ - Step 15853: {'lr': 0.0004892704861508121, 'samples': 3043776, 'steps': 15852, 'loss/train': 2.1591296195983887} 08/30/2021 16:06:22 - INFO - __main__ - Step 15854: {'lr': 0.0004892689481098193, 'samples': 3043968, 'steps': 15853, 'loss/train': 2.0167603492736816} 08/30/2021 16:06:23 - INFO - __main__ - Step 15855: {'lr': 0.0004892674099610158, 'samples': 3044160, 'steps': 15854, 'loss/train': 1.6414259672164917} 08/30/2021 16:06:24 - INFO - __main__ - Step 15856: {'lr': 0.000489265871704402, 'samples': 3044352, 'steps': 15855, 'loss/train': 6.075537204742432} 08/30/2021 16:06:25 - INFO - __main__ - Step 15857: {'lr': 0.0004892643333399788, 'samples': 3044544, 'steps': 15856, 'loss/train': 1.768763780593872} 08/30/2021 16:06:25 - INFO - __main__ - Step 15858: {'lr': 0.0004892627948677467, 'samples': 3044736, 'steps': 15857, 'loss/train': 1.0978754758834839} 08/30/2021 16:06:26 - INFO - __main__ - Step 15859: {'lr': 0.0004892612562877066, 'samples': 3044928, 'steps': 15858, 'loss/train': 2.134469509124756} 08/30/2021 16:06:26 - INFO - __main__ - Step 15860: {'lr': 0.0004892597175998589, 'samples': 3045120, 'steps': 15859, 'loss/train': 2.2281742095947266} 08/30/2021 16:06:26 - INFO - __main__ - Step 15861: {'lr': 0.0004892581788042045, 'samples': 3045312, 'steps': 15860, 'loss/train': 1.843698263168335} 08/30/2021 16:06:28 - INFO - __main__ - Step 15862: {'lr': 0.0004892566399007441, 'samples': 3045504, 'steps': 15861, 'loss/train': 0.2343396246433258} 08/30/2021 16:06:28 - INFO - __main__ - Step 15863: {'lr': 0.0004892551008894784, 'samples': 3045696, 'steps': 15862, 'loss/train': 0.3301844000816345} 08/30/2021 16:06:29 - INFO - __main__ - Step 15864: {'lr': 0.0004892535617704079, 'samples': 3045888, 'steps': 15863, 'loss/train': 1.5133025646209717} 08/30/2021 16:06:29 - INFO - __main__ - Step 15865: {'lr': 0.0004892520225435336, 'samples': 3046080, 'steps': 15864, 'loss/train': 1.9222338199615479} 08/30/2021 16:06:29 - INFO - __main__ - Step 15866: {'lr': 0.000489250483208856, 'samples': 3046272, 'steps': 15865, 'loss/train': 1.7021836042404175} 08/30/2021 16:06:31 - INFO - __main__ - Step 15867: {'lr': 0.0004892489437663758, 'samples': 3046464, 'steps': 15866, 'loss/train': 0.7320907115936279} 08/30/2021 16:06:31 - INFO - __main__ - Step 15868: {'lr': 0.0004892474042160936, 'samples': 3046656, 'steps': 15867, 'loss/train': 2.1231696605682373} 08/30/2021 16:06:32 - INFO - __main__ - Step 15869: {'lr': 0.0004892458645580103, 'samples': 3046848, 'steps': 15868, 'loss/train': 1.857272982597351} 08/30/2021 16:06:32 - INFO - __main__ - Step 15870: {'lr': 0.0004892443247921265, 'samples': 3047040, 'steps': 15869, 'loss/train': 1.4664748907089233} 08/30/2021 16:06:33 - INFO - __main__ - Step 15871: {'lr': 0.0004892427849184428, 'samples': 3047232, 'steps': 15870, 'loss/train': 1.3892543315887451} 08/30/2021 16:06:34 - INFO - __main__ - Step 15872: {'lr': 0.0004892412449369602, 'samples': 3047424, 'steps': 15871, 'loss/train': 0.11538084596395493} 08/30/2021 16:06:34 - INFO - __main__ - Step 15873: {'lr': 0.0004892397048476791, 'samples': 3047616, 'steps': 15872, 'loss/train': 1.4485125541687012} 08/30/2021 16:06:35 - INFO - __main__ - Step 15874: {'lr': 0.0004892381646506002, 'samples': 3047808, 'steps': 15873, 'loss/train': 2.0320661067962646} 08/30/2021 16:06:35 - INFO - __main__ - Step 15875: {'lr': 0.0004892366243457244, 'samples': 3048000, 'steps': 15874, 'loss/train': 1.4326623678207397} 08/30/2021 16:06:36 - INFO - __main__ - Step 15876: {'lr': 0.0004892350839330522, 'samples': 3048192, 'steps': 15875, 'loss/train': 1.6021592617034912} 08/30/2021 16:06:37 - INFO - __main__ - Step 15877: {'lr': 0.0004892335434125844, 'samples': 3048384, 'steps': 15876, 'loss/train': 1.6339194774627686} 08/30/2021 16:06:38 - INFO - __main__ - Step 15878: {'lr': 0.0004892320027843216, 'samples': 3048576, 'steps': 15877, 'loss/train': 1.673117756843567} 08/30/2021 16:06:38 - INFO - __main__ - Step 15879: {'lr': 0.0004892304620482646, 'samples': 3048768, 'steps': 15878, 'loss/train': 1.6826636791229248} 08/30/2021 16:06:38 - INFO - __main__ - Step 15880: {'lr': 0.000489228921204414, 'samples': 3048960, 'steps': 15879, 'loss/train': 1.749036192893982} 08/30/2021 16:06:39 - INFO - __main__ - Step 15881: {'lr': 0.0004892273802527706, 'samples': 3049152, 'steps': 15880, 'loss/train': 0.9491150975227356} 08/30/2021 16:06:40 - INFO - __main__ - Step 15882: {'lr': 0.000489225839193335, 'samples': 3049344, 'steps': 15881, 'loss/train': 2.020514488220215} 08/30/2021 16:06:41 - INFO - __main__ - Step 15883: {'lr': 0.0004892242980261079, 'samples': 3049536, 'steps': 15882, 'loss/train': 1.8321619033813477} 08/30/2021 16:06:41 - INFO - __main__ - Step 15884: {'lr': 0.0004892227567510901, 'samples': 3049728, 'steps': 15883, 'loss/train': 0.1489810347557068} 08/30/2021 16:06:41 - INFO - __main__ - Step 15885: {'lr': 0.0004892212153682822, 'samples': 3049920, 'steps': 15884, 'loss/train': 1.6919065713882446} 08/30/2021 16:06:42 - INFO - __main__ - Step 15886: {'lr': 0.0004892196738776848, 'samples': 3050112, 'steps': 15885, 'loss/train': 1.034507393836975} 08/30/2021 16:06:43 - INFO - __main__ - Step 15887: {'lr': 0.0004892181322792989, 'samples': 3050304, 'steps': 15886, 'loss/train': 1.7606680393218994} 08/30/2021 16:06:44 - INFO - __main__ - Step 15888: {'lr': 0.0004892165905731248, 'samples': 3050496, 'steps': 15887, 'loss/train': 1.3945250511169434} 08/30/2021 16:06:44 - INFO - __main__ - Step 15889: {'lr': 0.0004892150487591635, 'samples': 3050688, 'steps': 15888, 'loss/train': 1.6292153596878052} 08/30/2021 16:06:44 - INFO - __main__ - Step 15890: {'lr': 0.0004892135068374156, 'samples': 3050880, 'steps': 15889, 'loss/train': 1.4689536094665527} 08/30/2021 16:06:45 - INFO - __main__ - Step 15891: {'lr': 0.0004892119648078817, 'samples': 3051072, 'steps': 15890, 'loss/train': 1.9595842361450195} 08/30/2021 16:06:47 - INFO - __main__ - Step 15892: {'lr': 0.0004892104226705627, 'samples': 3051264, 'steps': 15891, 'loss/train': 1.322706937789917} 08/30/2021 16:06:47 - INFO - __main__ - Step 15893: {'lr': 0.0004892088804254591, 'samples': 3051456, 'steps': 15892, 'loss/train': 1.619107961654663} 08/30/2021 16:06:48 - INFO - __main__ - Step 15894: {'lr': 0.0004892073380725716, 'samples': 3051648, 'steps': 15893, 'loss/train': 1.9878965616226196} 08/30/2021 16:06:48 - INFO - __main__ - Step 15895: {'lr': 0.0004892057956119012, 'samples': 3051840, 'steps': 15894, 'loss/train': 1.452697515487671} 08/30/2021 16:06:48 - INFO - __main__ - Step 15896: {'lr': 0.0004892042530434482, 'samples': 3052032, 'steps': 15895, 'loss/train': 1.6216015815734863} 08/30/2021 16:06:49 - INFO - __main__ - Step 15897: {'lr': 0.0004892027103672134, 'samples': 3052224, 'steps': 15896, 'loss/train': 1.6163655519485474} 08/30/2021 16:06:50 - INFO - __main__ - Step 15898: {'lr': 0.0004892011675831976, 'samples': 3052416, 'steps': 15897, 'loss/train': 0.8906508684158325} 08/30/2021 16:06:51 - INFO - __main__ - Step 15899: {'lr': 0.0004891996246914014, 'samples': 3052608, 'steps': 15898, 'loss/train': 1.6975879669189453} 08/30/2021 16:06:51 - INFO - __main__ - Step 15900: {'lr': 0.0004891980816918257, 'samples': 3052800, 'steps': 15899, 'loss/train': 0.37823686003685} 08/30/2021 16:06:51 - INFO - __main__ - Step 15901: {'lr': 0.0004891965385844709, 'samples': 3052992, 'steps': 15900, 'loss/train': 1.9129810333251953} 08/30/2021 16:06:52 - INFO - __main__ - Step 15902: {'lr': 0.0004891949953693378, 'samples': 3053184, 'steps': 15901, 'loss/train': 1.1313961744308472} 08/30/2021 16:06:53 - INFO - __main__ - Step 15903: {'lr': 0.0004891934520464273, 'samples': 3053376, 'steps': 15902, 'loss/train': 1.218643069267273} 08/30/2021 16:06:54 - INFO - __main__ - Step 15904: {'lr': 0.0004891919086157398, 'samples': 3053568, 'steps': 15903, 'loss/train': 2.356090784072876} 08/30/2021 16:06:54 - INFO - __main__ - Step 15905: {'lr': 0.000489190365077276, 'samples': 3053760, 'steps': 15904, 'loss/train': 1.6718299388885498} 08/30/2021 16:06:54 - INFO - __main__ - Step 15906: {'lr': 0.0004891888214310369, 'samples': 3053952, 'steps': 15905, 'loss/train': 1.7623941898345947} 08/30/2021 16:06:55 - INFO - __main__ - Step 15907: {'lr': 0.000489187277677023, 'samples': 3054144, 'steps': 15906, 'loss/train': 1.8284597396850586} 08/30/2021 16:06:56 - INFO - __main__ - Step 15908: {'lr': 0.000489185733815235, 'samples': 3054336, 'steps': 15907, 'loss/train': 1.508117437362671} 08/30/2021 16:06:57 - INFO - __main__ - Step 15909: {'lr': 0.0004891841898456735, 'samples': 3054528, 'steps': 15908, 'loss/train': 1.4869719743728638} 08/30/2021 16:06:57 - INFO - __main__ - Step 15910: {'lr': 0.0004891826457683394, 'samples': 3054720, 'steps': 15909, 'loss/train': 1.608035683631897} 08/30/2021 16:06:57 - INFO - __main__ - Step 15911: {'lr': 0.0004891811015832332, 'samples': 3054912, 'steps': 15910, 'loss/train': 1.6275404691696167} 08/30/2021 16:06:58 - INFO - __main__ - Step 15912: {'lr': 0.0004891795572903557, 'samples': 3055104, 'steps': 15911, 'loss/train': 1.6273819208145142} 08/30/2021 16:06:59 - INFO - __main__ - Step 15913: {'lr': 0.0004891780128897077, 'samples': 3055296, 'steps': 15912, 'loss/train': 1.4007941484451294} 08/30/2021 16:07:00 - INFO - __main__ - Step 15914: {'lr': 0.0004891764683812896, 'samples': 3055488, 'steps': 15913, 'loss/train': 1.4682165384292603} 08/30/2021 16:07:00 - INFO - __main__ - Step 15915: {'lr': 0.0004891749237651024, 'samples': 3055680, 'steps': 15914, 'loss/train': 1.6606872081756592} 08/30/2021 16:07:00 - INFO - __main__ - Step 15916: {'lr': 0.0004891733790411466, 'samples': 3055872, 'steps': 15915, 'loss/train': 1.191284418106079} 08/30/2021 16:07:01 - INFO - __main__ - Step 15917: {'lr': 0.000489171834209423, 'samples': 3056064, 'steps': 15916, 'loss/train': 1.778518557548523} 08/30/2021 16:07:03 - INFO - __main__ - Step 15918: {'lr': 0.0004891702892699323, 'samples': 3056256, 'steps': 15917, 'loss/train': 1.8627073764801025} 08/30/2021 16:07:03 - INFO - __main__ - Step 15919: {'lr': 0.0004891687442226751, 'samples': 3056448, 'steps': 15918, 'loss/train': 1.9882503747940063} 08/30/2021 16:07:04 - INFO - __main__ - Step 15920: {'lr': 0.0004891671990676522, 'samples': 3056640, 'steps': 15919, 'loss/train': 2.7746639251708984} 08/30/2021 16:07:04 - INFO - __main__ - Step 15921: {'lr': 0.0004891656538048642, 'samples': 3056832, 'steps': 15920, 'loss/train': 2.682562828063965} 08/30/2021 16:07:04 - INFO - __main__ - Step 15922: {'lr': 0.0004891641084343118, 'samples': 3057024, 'steps': 15921, 'loss/train': 1.0898919105529785} 08/30/2021 16:07:05 - INFO - __main__ - Step 15923: {'lr': 0.0004891625629559959, 'samples': 3057216, 'steps': 15922, 'loss/train': 1.7425451278686523} 08/30/2021 16:07:05 - INFO - __main__ - Step 15924: {'lr': 0.0004891610173699169, 'samples': 3057408, 'steps': 15923, 'loss/train': 1.8265413045883179} 08/30/2021 16:07:07 - INFO - __main__ - Step 15925: {'lr': 0.0004891594716760757, 'samples': 3057600, 'steps': 15924, 'loss/train': 2.081162214279175} 08/30/2021 16:07:07 - INFO - __main__ - Step 15926: {'lr': 0.0004891579258744728, 'samples': 3057792, 'steps': 15925, 'loss/train': 1.856448769569397} 08/30/2021 16:07:07 - INFO - __main__ - Step 15927: {'lr': 0.0004891563799651092, 'samples': 3057984, 'steps': 15926, 'loss/train': 2.0374579429626465} 08/30/2021 16:07:08 - INFO - __main__ - Step 15928: {'lr': 0.0004891548339479854, 'samples': 3058176, 'steps': 15927, 'loss/train': 1.7977981567382812} 08/30/2021 16:07:08 - INFO - __main__ - Step 15929: {'lr': 0.0004891532878231021, 'samples': 3058368, 'steps': 15928, 'loss/train': 1.543886423110962} 08/30/2021 16:07:10 - INFO - __main__ - Step 15930: {'lr': 0.00048915174159046, 'samples': 3058560, 'steps': 15929, 'loss/train': 1.049500584602356} 08/30/2021 16:07:10 - INFO - __main__ - Step 15931: {'lr': 0.0004891501952500599, 'samples': 3058752, 'steps': 15930, 'loss/train': 1.4056872129440308} 08/30/2021 16:07:10 - INFO - __main__ - Step 15932: {'lr': 0.0004891486488019023, 'samples': 3058944, 'steps': 15931, 'loss/train': 1.9798353910446167} 08/30/2021 16:07:11 - INFO - __main__ - Step 15933: {'lr': 0.000489147102245988, 'samples': 3059136, 'steps': 15932, 'loss/train': 0.31406834721565247} 08/30/2021 16:07:11 - INFO - __main__ - Step 15934: {'lr': 0.0004891455555823179, 'samples': 3059328, 'steps': 15933, 'loss/train': 2.054659605026245} 08/30/2021 16:07:13 - INFO - __main__ - Step 15935: {'lr': 0.0004891440088108923, 'samples': 3059520, 'steps': 15934, 'loss/train': 2.25657320022583} 08/30/2021 16:07:13 - INFO - __main__ - Step 15936: {'lr': 0.0004891424619317121, 'samples': 3059712, 'steps': 15935, 'loss/train': 1.7731446027755737} 08/30/2021 16:07:13 - INFO - __main__ - Step 15937: {'lr': 0.000489140914944778, 'samples': 3059904, 'steps': 15936, 'loss/train': 1.6978503465652466} 08/30/2021 16:07:14 - INFO - __main__ - Step 15938: {'lr': 0.0004891393678500909, 'samples': 3060096, 'steps': 15937, 'loss/train': 1.7160401344299316} 08/30/2021 16:07:14 - INFO - __main__ - Step 15939: {'lr': 0.0004891378206476511, 'samples': 3060288, 'steps': 15938, 'loss/train': 0.48282942175865173} 08/30/2021 16:07:14 - INFO - __main__ - Step 15940: {'lr': 0.0004891362733374595, 'samples': 3060480, 'steps': 15939, 'loss/train': 1.8949224948883057} 08/30/2021 16:07:17 - INFO - __main__ - Step 15941: {'lr': 0.0004891347259195168, 'samples': 3060672, 'steps': 15940, 'loss/train': 1.5520035028457642} 08/30/2021 16:07:17 - INFO - __main__ - Step 15942: {'lr': 0.0004891331783938238, 'samples': 3060864, 'steps': 15941, 'loss/train': 1.6616119146347046} 08/30/2021 16:07:18 - INFO - __main__ - Step 15943: {'lr': 0.000489131630760381, 'samples': 3061056, 'steps': 15942, 'loss/train': 1.7089266777038574} 08/30/2021 16:07:18 - INFO - __main__ - Step 15944: {'lr': 0.000489130083019189, 'samples': 3061248, 'steps': 15943, 'loss/train': 2.1419475078582764} 08/30/2021 16:07:18 - INFO - __main__ - Step 15945: {'lr': 0.000489128535170249, 'samples': 3061440, 'steps': 15944, 'loss/train': 1.6969479322433472} 08/30/2021 16:07:19 - INFO - __main__ - Step 15946: {'lr': 0.0004891269872135611, 'samples': 3061632, 'steps': 15945, 'loss/train': 1.1622493267059326} 08/30/2021 16:07:19 - INFO - __main__ - Step 15947: {'lr': 0.0004891254391491264, 'samples': 3061824, 'steps': 15946, 'loss/train': 1.6910468339920044} 08/30/2021 16:07:21 - INFO - __main__ - Step 15948: {'lr': 0.0004891238909769454, 'samples': 3062016, 'steps': 15947, 'loss/train': 1.6272855997085571} 08/30/2021 16:07:21 - INFO - __main__ - Step 15949: {'lr': 0.0004891223426970189, 'samples': 3062208, 'steps': 15948, 'loss/train': 1.7621570825576782} 08/30/2021 16:07:21 - INFO - __main__ - Step 15950: {'lr': 0.0004891207943093476, 'samples': 3062400, 'steps': 15949, 'loss/train': 0.6291665434837341} 08/30/2021 16:07:22 - INFO - __main__ - Step 15951: {'lr': 0.000489119245813932, 'samples': 3062592, 'steps': 15950, 'loss/train': 1.1066741943359375} 08/30/2021 16:07:22 - INFO - __main__ - Step 15952: {'lr': 0.0004891176972107731, 'samples': 3062784, 'steps': 15951, 'loss/train': 1.4184036254882812} 08/30/2021 16:07:24 - INFO - __main__ - Step 15953: {'lr': 0.0004891161484998715, 'samples': 3062976, 'steps': 15952, 'loss/train': 1.664896011352539} 08/30/2021 16:07:25 - INFO - __main__ - Step 15954: {'lr': 0.0004891145996812279, 'samples': 3063168, 'steps': 15953, 'loss/train': 1.8335856199264526} 08/30/2021 16:07:25 - INFO - __main__ - Step 15955: {'lr': 0.0004891130507548427, 'samples': 3063360, 'steps': 15954, 'loss/train': 1.547168254852295} 08/30/2021 16:07:25 - INFO - __main__ - Step 15956: {'lr': 0.000489111501720717, 'samples': 3063552, 'steps': 15955, 'loss/train': 1.9942551851272583} 08/30/2021 16:07:26 - INFO - __main__ - Step 15957: {'lr': 0.0004891099525788514, 'samples': 3063744, 'steps': 15956, 'loss/train': 1.791953206062317} 08/30/2021 16:07:26 - INFO - __main__ - Step 15958: {'lr': 0.0004891084033292464, 'samples': 3063936, 'steps': 15957, 'loss/train': 1.6415573358535767} 08/30/2021 16:07:28 - INFO - __main__ - Step 15959: {'lr': 0.0004891068539719031, 'samples': 3064128, 'steps': 15958, 'loss/train': 1.894308090209961} 08/30/2021 16:07:28 - INFO - __main__ - Step 15960: {'lr': 0.0004891053045068217, 'samples': 3064320, 'steps': 15959, 'loss/train': 2.062399387359619} 08/30/2021 16:07:28 - INFO - __main__ - Step 15961: {'lr': 0.0004891037549340032, 'samples': 3064512, 'steps': 15960, 'loss/train': 1.6622875928878784} 08/30/2021 16:07:29 - INFO - __main__ - Step 15962: {'lr': 0.0004891022052534482, 'samples': 3064704, 'steps': 15961, 'loss/train': 1.6348267793655396} 08/30/2021 16:07:29 - INFO - __main__ - Step 15963: {'lr': 0.0004891006554651574, 'samples': 3064896, 'steps': 15962, 'loss/train': 1.1106070280075073} 08/30/2021 16:07:31 - INFO - __main__ - Step 15964: {'lr': 0.0004890991055691318, 'samples': 3065088, 'steps': 15963, 'loss/train': 1.455451488494873} 08/30/2021 16:07:31 - INFO - __main__ - Step 15965: {'lr': 0.0004890975555653716, 'samples': 3065280, 'steps': 15964, 'loss/train': 1.4749478101730347} 08/30/2021 16:07:31 - INFO - __main__ - Step 15966: {'lr': 0.0004890960054538778, 'samples': 3065472, 'steps': 15965, 'loss/train': 1.6150314807891846} 08/30/2021 16:07:32 - INFO - __main__ - Step 15967: {'lr': 0.000489094455234651, 'samples': 3065664, 'steps': 15966, 'loss/train': 0.3192380368709564} 08/30/2021 16:07:32 - INFO - __main__ - Step 15968: {'lr': 0.0004890929049076919, 'samples': 3065856, 'steps': 15967, 'loss/train': 1.7374497652053833} 08/30/2021 16:07:34 - INFO - __main__ - Step 15969: {'lr': 0.0004890913544730013, 'samples': 3066048, 'steps': 15968, 'loss/train': 1.5663126707077026} 08/30/2021 16:07:35 - INFO - __main__ - Step 15970: {'lr': 0.0004890898039305798, 'samples': 3066240, 'steps': 15969, 'loss/train': 1.9863234758377075} 08/30/2021 16:07:35 - INFO - __main__ - Step 15971: {'lr': 0.000489088253280428, 'samples': 3066432, 'steps': 15970, 'loss/train': 1.812970519065857} 08/30/2021 16:07:35 - INFO - __main__ - Step 15972: {'lr': 0.0004890867025225469, 'samples': 3066624, 'steps': 15971, 'loss/train': 1.6286590099334717} 08/30/2021 16:07:36 - INFO - __main__ - Step 15973: {'lr': 0.000489085151656937, 'samples': 3066816, 'steps': 15972, 'loss/train': 2.0572667121887207} 08/30/2021 16:07:37 - INFO - __main__ - Step 15974: {'lr': 0.000489083600683599, 'samples': 3067008, 'steps': 15973, 'loss/train': 0.20823699235916138} 08/30/2021 16:07:37 - INFO - __main__ - Step 15975: {'lr': 0.0004890820496025335, 'samples': 3067200, 'steps': 15974, 'loss/train': 2.290116310119629} 08/30/2021 16:07:38 - INFO - __main__ - Step 15976: {'lr': 0.0004890804984137415, 'samples': 3067392, 'steps': 15975, 'loss/train': 1.6490013599395752} 08/30/2021 16:07:38 - INFO - __main__ - Step 15977: {'lr': 0.0004890789471172233, 'samples': 3067584, 'steps': 15976, 'loss/train': 1.6396937370300293} 08/30/2021 16:07:38 - INFO - __main__ - Step 15978: {'lr': 0.00048907739571298, 'samples': 3067776, 'steps': 15977, 'loss/train': 1.9426047801971436} 08/30/2021 16:07:39 - INFO - __main__ - Step 15979: {'lr': 0.000489075844201012, 'samples': 3067968, 'steps': 15978, 'loss/train': 1.6522164344787598} 08/30/2021 16:07:40 - INFO - __main__ - Step 15980: {'lr': 0.0004890742925813202, 'samples': 3068160, 'steps': 15979, 'loss/train': 1.8167675733566284} 08/30/2021 16:07:41 - INFO - __main__ - Step 15981: {'lr': 0.0004890727408539051, 'samples': 3068352, 'steps': 15980, 'loss/train': 1.2056710720062256} 08/30/2021 16:07:41 - INFO - __main__ - Step 15982: {'lr': 0.0004890711890187676, 'samples': 3068544, 'steps': 15981, 'loss/train': 2.293987274169922} 08/30/2021 16:07:42 - INFO - __main__ - Step 15983: {'lr': 0.0004890696370759085, 'samples': 3068736, 'steps': 15982, 'loss/train': 1.3528395891189575} 08/30/2021 16:07:42 - INFO - __main__ - Step 15984: {'lr': 0.0004890680850253281, 'samples': 3068928, 'steps': 15983, 'loss/train': 1.4105851650238037} 08/30/2021 16:07:43 - INFO - __main__ - Step 15985: {'lr': 0.0004890665328670273, 'samples': 3069120, 'steps': 15984, 'loss/train': 1.8543025255203247} 08/30/2021 16:07:44 - INFO - __main__ - Step 15986: {'lr': 0.0004890649806010067, 'samples': 3069312, 'steps': 15985, 'loss/train': 0.3930068612098694} 08/30/2021 16:07:44 - INFO - __main__ - Step 15987: {'lr': 0.0004890634282272673, 'samples': 3069504, 'steps': 15986, 'loss/train': 1.812916874885559} 08/30/2021 16:07:45 - INFO - __main__ - Step 15988: {'lr': 0.0004890618757458096, 'samples': 3069696, 'steps': 15987, 'loss/train': 1.3969653844833374} 08/30/2021 16:07:45 - INFO - __main__ - Step 15989: {'lr': 0.0004890603231566343, 'samples': 3069888, 'steps': 15988, 'loss/train': 1.9779038429260254} 08/30/2021 16:07:47 - INFO - __main__ - Step 15990: {'lr': 0.000489058770459742, 'samples': 3070080, 'steps': 15989, 'loss/train': 1.6323916912078857} 08/30/2021 16:07:47 - INFO - __main__ - Step 15991: {'lr': 0.0004890572176551337, 'samples': 3070272, 'steps': 15990, 'loss/train': 1.7052792310714722} 08/30/2021 16:07:47 - INFO - __main__ - Step 15992: {'lr': 0.0004890556647428097, 'samples': 3070464, 'steps': 15991, 'loss/train': 1.92897629737854} 08/30/2021 16:07:48 - INFO - __main__ - Step 15993: {'lr': 0.0004890541117227711, 'samples': 3070656, 'steps': 15992, 'loss/train': 1.7285797595977783} 08/30/2021 16:07:48 - INFO - __main__ - Step 15994: {'lr': 0.0004890525585950181, 'samples': 3070848, 'steps': 15993, 'loss/train': 1.4235693216323853} 08/30/2021 16:07:48 - INFO - __main__ - Step 15995: {'lr': 0.000489051005359552, 'samples': 3071040, 'steps': 15994, 'loss/train': 0.4631354510784149} 08/30/2021 16:07:50 - INFO - __main__ - Step 15996: {'lr': 0.0004890494520163731, 'samples': 3071232, 'steps': 15995, 'loss/train': 4.9341912269592285} 08/30/2021 16:07:50 - INFO - __main__ - Step 15997: {'lr': 0.0004890478985654823, 'samples': 3071424, 'steps': 15996, 'loss/train': 1.2674771547317505} 08/30/2021 16:07:51 - INFO - __main__ - Step 15998: {'lr': 0.0004890463450068801, 'samples': 3071616, 'steps': 15997, 'loss/train': 1.4238637685775757} 08/30/2021 16:07:51 - INFO - __main__ - Step 15999: {'lr': 0.0004890447913405673, 'samples': 3071808, 'steps': 15998, 'loss/train': 1.9229238033294678} 08/30/2021 16:07:51 - INFO - __main__ - Step 16000: {'lr': 0.0004890432375665447, 'samples': 3072000, 'steps': 15999, 'loss/train': 2.1698992252349854} 08/30/2021 16:07:53 - INFO - __main__ - Step 16001: {'lr': 0.0004890416836848127, 'samples': 3072192, 'steps': 16000, 'loss/train': 1.5063798427581787} 08/30/2021 16:07:53 - INFO - __main__ - Step 16002: {'lr': 0.0004890401296953723, 'samples': 3072384, 'steps': 16001, 'loss/train': 1.455306887626648} 08/30/2021 16:07:54 - INFO - __main__ - Step 16003: {'lr': 0.0004890385755982243, 'samples': 3072576, 'steps': 16002, 'loss/train': 1.368117094039917} 08/30/2021 16:07:54 - INFO - __main__ - Step 16004: {'lr': 0.0004890370213933691, 'samples': 3072768, 'steps': 16003, 'loss/train': 1.1363060474395752} 08/30/2021 16:07:54 - INFO - __main__ - Step 16005: {'lr': 0.0004890354670808074, 'samples': 3072960, 'steps': 16004, 'loss/train': 1.667634129524231} 08/30/2021 16:07:57 - INFO - __main__ - Step 16006: {'lr': 0.0004890339126605401, 'samples': 3073152, 'steps': 16005, 'loss/train': 1.5886671543121338} 08/30/2021 16:07:57 - INFO - __main__ - Step 16007: {'lr': 0.0004890323581325677, 'samples': 3073344, 'steps': 16006, 'loss/train': 1.4568320512771606} 08/30/2021 16:07:57 - INFO - __main__ - Step 16008: {'lr': 0.0004890308034968911, 'samples': 3073536, 'steps': 16007, 'loss/train': 1.618986964225769} 08/30/2021 16:07:58 - INFO - __main__ - Step 16009: {'lr': 0.0004890292487535108, 'samples': 3073728, 'steps': 16008, 'loss/train': 1.9119718074798584} 08/30/2021 16:07:58 - INFO - __main__ - Step 16010: {'lr': 0.0004890276939024278, 'samples': 3073920, 'steps': 16009, 'loss/train': 2.1318917274475098} 08/30/2021 16:08:00 - INFO - __main__ - Step 16011: {'lr': 0.0004890261389436424, 'samples': 3074112, 'steps': 16010, 'loss/train': 1.9940615892410278} 08/30/2021 16:08:01 - INFO - __main__ - Step 16012: {'lr': 0.0004890245838771557, 'samples': 3074304, 'steps': 16011, 'loss/train': 0.35355421900749207} 08/30/2021 16:08:01 - INFO - __main__ - Step 16013: {'lr': 0.0004890230287029681, 'samples': 3074496, 'steps': 16012, 'loss/train': 0.5573104023933411} 08/30/2021 16:08:01 - INFO - __main__ - Step 16014: {'lr': 0.0004890214734210805, 'samples': 3074688, 'steps': 16013, 'loss/train': 1.2571091651916504} 08/30/2021 16:08:02 - INFO - __main__ - Step 16015: {'lr': 0.0004890199180314935, 'samples': 3074880, 'steps': 16014, 'loss/train': 1.6820523738861084} 08/30/2021 16:08:02 - INFO - __main__ - Step 16016: {'lr': 0.0004890183625342078, 'samples': 3075072, 'steps': 16015, 'loss/train': 1.702893614768982} 08/30/2021 16:08:03 - INFO - __main__ - Step 16017: {'lr': 0.0004890168069292241, 'samples': 3075264, 'steps': 16016, 'loss/train': 1.690147876739502} 08/30/2021 16:08:04 - INFO - __main__ - Step 16018: {'lr': 0.000489015251216543, 'samples': 3075456, 'steps': 16017, 'loss/train': 1.5505287647247314} 08/30/2021 16:08:04 - INFO - __main__ - Step 16019: {'lr': 0.0004890136953961654, 'samples': 3075648, 'steps': 16018, 'loss/train': 1.1830521821975708} 08/30/2021 16:08:05 - INFO - __main__ - Step 16020: {'lr': 0.000489012139468092, 'samples': 3075840, 'steps': 16019, 'loss/train': 1.4839494228363037} 08/30/2021 16:08:05 - INFO - __main__ - Step 16021: {'lr': 0.0004890105834323233, 'samples': 3076032, 'steps': 16020, 'loss/train': 1.502497673034668} 08/30/2021 16:08:06 - INFO - __main__ - Step 16022: {'lr': 0.0004890090272888602, 'samples': 3076224, 'steps': 16021, 'loss/train': 1.6627182960510254} 08/30/2021 16:08:07 - INFO - __main__ - Step 16023: {'lr': 0.0004890074710377033, 'samples': 3076416, 'steps': 16022, 'loss/train': 1.9242879152297974} 08/30/2021 16:08:07 - INFO - __main__ - Step 16024: {'lr': 0.0004890059146788532, 'samples': 3076608, 'steps': 16023, 'loss/train': 1.4171985387802124} 08/30/2021 16:08:08 - INFO - __main__ - Step 16025: {'lr': 0.000489004358212311, 'samples': 3076800, 'steps': 16024, 'loss/train': 2.0105652809143066} 08/30/2021 16:08:08 - INFO - __main__ - Step 16026: {'lr': 0.0004890028016380769, 'samples': 3076992, 'steps': 16025, 'loss/train': 1.8932466506958008} 08/30/2021 16:08:10 - INFO - __main__ - Step 16027: {'lr': 0.0004890012449561518, 'samples': 3077184, 'steps': 16026, 'loss/train': 1.5929791927337646} 08/30/2021 16:08:10 - INFO - __main__ - Step 16028: {'lr': 0.0004889996881665366, 'samples': 3077376, 'steps': 16027, 'loss/train': 1.5297855138778687} 08/30/2021 16:08:10 - INFO - __main__ - Step 16029: {'lr': 0.0004889981312692317, 'samples': 3077568, 'steps': 16028, 'loss/train': 1.4741088151931763} 08/30/2021 16:08:11 - INFO - __main__ - Step 16030: {'lr': 0.000488996574264238, 'samples': 3077760, 'steps': 16029, 'loss/train': 0.3136903941631317} 08/30/2021 16:08:11 - INFO - __main__ - Step 16031: {'lr': 0.000488995017151556, 'samples': 3077952, 'steps': 16030, 'loss/train': 1.9275661706924438} 08/30/2021 16:08:13 - INFO - __main__ - Step 16032: {'lr': 0.0004889934599311867, 'samples': 3078144, 'steps': 16031, 'loss/train': 1.510998010635376} 08/30/2021 16:08:13 - INFO - __main__ - Step 16033: {'lr': 0.0004889919026031306, 'samples': 3078336, 'steps': 16032, 'loss/train': 1.4501458406448364} 08/30/2021 16:08:13 - INFO - __main__ - Step 16034: {'lr': 0.0004889903451673884, 'samples': 3078528, 'steps': 16033, 'loss/train': 1.6799242496490479} 08/30/2021 16:08:14 - INFO - __main__ - Step 16035: {'lr': 0.0004889887876239608, 'samples': 3078720, 'steps': 16034, 'loss/train': 1.4250009059906006} 08/30/2021 16:08:14 - INFO - __main__ - Step 16036: {'lr': 0.0004889872299728486, 'samples': 3078912, 'steps': 16035, 'loss/train': 1.598712682723999} 08/30/2021 16:08:15 - INFO - __main__ - Step 16037: {'lr': 0.0004889856722140525, 'samples': 3079104, 'steps': 16036, 'loss/train': 0.8378870487213135} 08/30/2021 16:08:16 - INFO - __main__ - Step 16038: {'lr': 0.000488984114347573, 'samples': 3079296, 'steps': 16037, 'loss/train': 1.6544798612594604} 08/30/2021 16:08:16 - INFO - __main__ - Step 16039: {'lr': 0.000488982556373411, 'samples': 3079488, 'steps': 16038, 'loss/train': 0.9884001612663269} 08/30/2021 16:08:17 - INFO - __main__ - Step 16040: {'lr': 0.0004889809982915672, 'samples': 3079680, 'steps': 16039, 'loss/train': 1.8656682968139648} 08/30/2021 16:08:17 - INFO - __main__ - Step 16041: {'lr': 0.0004889794401020422, 'samples': 3079872, 'steps': 16040, 'loss/train': 1.5121309757232666} 08/30/2021 16:08:18 - INFO - __main__ - Step 16042: {'lr': 0.0004889778818048368, 'samples': 3080064, 'steps': 16041, 'loss/train': 1.3341726064682007} 08/30/2021 16:08:19 - INFO - __main__ - Step 16043: {'lr': 0.0004889763233999516, 'samples': 3080256, 'steps': 16042, 'loss/train': 1.7305001020431519} 08/30/2021 16:08:19 - INFO - __main__ - Step 16044: {'lr': 0.0004889747648873874, 'samples': 3080448, 'steps': 16043, 'loss/train': 2.1049811840057373} 08/30/2021 16:08:19 - INFO - __main__ - Step 16045: {'lr': 0.0004889732062671448, 'samples': 3080640, 'steps': 16044, 'loss/train': 1.8849035501480103} 08/30/2021 16:08:20 - INFO - __main__ - Step 16046: {'lr': 0.0004889716475392247, 'samples': 3080832, 'steps': 16045, 'loss/train': 1.5957787036895752} 08/30/2021 16:08:21 - INFO - __main__ - Step 16047: {'lr': 0.0004889700887036275, 'samples': 3081024, 'steps': 16046, 'loss/train': 1.4747272729873657} 08/30/2021 16:08:22 - INFO - __main__ - Step 16048: {'lr': 0.0004889685297603541, 'samples': 3081216, 'steps': 16047, 'loss/train': 1.2768683433532715} 08/30/2021 16:08:22 - INFO - __main__ - Step 16049: {'lr': 0.0004889669707094052, 'samples': 3081408, 'steps': 16048, 'loss/train': 1.3526276350021362} 08/30/2021 16:08:23 - INFO - __main__ - Step 16050: {'lr': 0.0004889654115507815, 'samples': 3081600, 'steps': 16049, 'loss/train': 2.011629343032837} 08/30/2021 16:08:23 - INFO - __main__ - Step 16051: {'lr': 0.0004889638522844836, 'samples': 3081792, 'steps': 16050, 'loss/train': 1.3644627332687378} 08/30/2021 16:08:24 - INFO - __main__ - Step 16052: {'lr': 0.0004889622929105123, 'samples': 3081984, 'steps': 16051, 'loss/train': 1.5981725454330444} 08/30/2021 16:08:25 - INFO - __main__ - Step 16053: {'lr': 0.0004889607334288683, 'samples': 3082176, 'steps': 16052, 'loss/train': 1.5981335639953613} 08/30/2021 16:08:25 - INFO - __main__ - Step 16054: {'lr': 0.0004889591738395522, 'samples': 3082368, 'steps': 16053, 'loss/train': 1.9253791570663452} 08/30/2021 16:08:25 - INFO - __main__ - Step 16055: {'lr': 0.0004889576141425649, 'samples': 3082560, 'steps': 16054, 'loss/train': 1.7079644203186035} 08/30/2021 16:08:26 - INFO - __main__ - Step 16056: {'lr': 0.0004889560543379069, 'samples': 3082752, 'steps': 16055, 'loss/train': 1.6662176847457886} 08/30/2021 16:08:28 - INFO - __main__ - Step 16057: {'lr': 0.000488954494425579, 'samples': 3082944, 'steps': 16056, 'loss/train': 1.7057243585586548} 08/30/2021 16:08:28 - INFO - __main__ - Step 16058: {'lr': 0.000488952934405582, 'samples': 3083136, 'steps': 16057, 'loss/train': 2.2320845127105713} 08/30/2021 16:08:29 - INFO - __main__ - Step 16059: {'lr': 0.0004889513742779164, 'samples': 3083328, 'steps': 16058, 'loss/train': 1.759162425994873} 08/30/2021 16:08:29 - INFO - __main__ - Step 16060: {'lr': 0.0004889498140425829, 'samples': 3083520, 'steps': 16059, 'loss/train': 0.5264279246330261} 08/30/2021 16:08:29 - INFO - __main__ - Step 16061: {'lr': 0.0004889482536995825, 'samples': 3083712, 'steps': 16060, 'loss/train': 1.7540335655212402} 08/30/2021 16:08:30 - INFO - __main__ - Step 16062: {'lr': 0.0004889466932489157, 'samples': 3083904, 'steps': 16061, 'loss/train': 1.7482750415802002} 08/30/2021 16:08:31 - INFO - __main__ - Step 16063: {'lr': 0.0004889451326905831, 'samples': 3084096, 'steps': 16062, 'loss/train': 1.2973772287368774} 08/30/2021 16:08:32 - INFO - __main__ - Step 16064: {'lr': 0.0004889435720245855, 'samples': 3084288, 'steps': 16063, 'loss/train': 1.0407685041427612} 08/30/2021 16:08:32 - INFO - __main__ - Step 16065: {'lr': 0.0004889420112509237, 'samples': 3084480, 'steps': 16064, 'loss/train': 0.8719043135643005} 08/30/2021 16:08:33 - INFO - __main__ - Step 16066: {'lr': 0.0004889404503695983, 'samples': 3084672, 'steps': 16065, 'loss/train': 0.8405120372772217} 08/30/2021 16:08:33 - INFO - __main__ - Step 16067: {'lr': 0.0004889388893806099, 'samples': 3084864, 'steps': 16066, 'loss/train': 1.693964958190918} 08/30/2021 16:08:34 - INFO - __main__ - Step 16068: {'lr': 0.0004889373282839594, 'samples': 3085056, 'steps': 16067, 'loss/train': 1.8568710088729858} 08/30/2021 16:08:35 - INFO - __main__ - Step 16069: {'lr': 0.0004889357670796474, 'samples': 3085248, 'steps': 16068, 'loss/train': 2.2184221744537354} 08/30/2021 16:08:35 - INFO - __main__ - Step 16070: {'lr': 0.0004889342057676748, 'samples': 3085440, 'steps': 16069, 'loss/train': 1.2420254945755005} 08/30/2021 16:08:36 - INFO - __main__ - Step 16071: {'lr': 0.000488932644348042, 'samples': 3085632, 'steps': 16070, 'loss/train': 1.8536574840545654} 08/30/2021 16:08:36 - INFO - __main__ - Step 16072: {'lr': 0.0004889310828207498, 'samples': 3085824, 'steps': 16071, 'loss/train': 1.2023687362670898} 08/30/2021 16:08:37 - INFO - __main__ - Step 16073: {'lr': 0.000488929521185799, 'samples': 3086016, 'steps': 16072, 'loss/train': 1.577937126159668} 08/30/2021 16:08:38 - INFO - __main__ - Step 16074: {'lr': 0.0004889279594431903, 'samples': 3086208, 'steps': 16073, 'loss/train': 1.64153254032135} 08/30/2021 16:08:38 - INFO - __main__ - Step 16075: {'lr': 0.0004889263975929242, 'samples': 3086400, 'steps': 16074, 'loss/train': 1.453249454498291} 08/30/2021 16:08:39 - INFO - __main__ - Step 16076: {'lr': 0.0004889248356350016, 'samples': 3086592, 'steps': 16075, 'loss/train': 1.5572229623794556} 08/30/2021 16:08:39 - INFO - __main__ - Step 16077: {'lr': 0.0004889232735694232, 'samples': 3086784, 'steps': 16076, 'loss/train': 1.7651371955871582} 08/30/2021 16:08:41 - INFO - __main__ - Step 16078: {'lr': 0.0004889217113961896, 'samples': 3086976, 'steps': 16077, 'loss/train': 1.8475475311279297} 08/30/2021 16:08:41 - INFO - __main__ - Step 16079: {'lr': 0.0004889201491153016, 'samples': 3087168, 'steps': 16078, 'loss/train': 2.020800828933716} 08/30/2021 16:08:42 - INFO - __main__ - Step 16080: {'lr': 0.0004889185867267599, 'samples': 3087360, 'steps': 16079, 'loss/train': 2.3029513359069824} 08/30/2021 16:08:42 - INFO - __main__ - Step 16081: {'lr': 0.0004889170242305652, 'samples': 3087552, 'steps': 16080, 'loss/train': 0.11970590054988861} 08/30/2021 16:08:42 - INFO - __main__ - Step 16082: {'lr': 0.0004889154616267181, 'samples': 3087744, 'steps': 16081, 'loss/train': 1.6496000289916992} 08/30/2021 16:08:43 - INFO - __main__ - Step 16083: {'lr': 0.0004889138989152194, 'samples': 3087936, 'steps': 16082, 'loss/train': 1.455633282661438} 08/30/2021 16:08:44 - INFO - __main__ - Step 16084: {'lr': 0.0004889123360960698, 'samples': 3088128, 'steps': 16083, 'loss/train': 1.4459062814712524} 08/30/2021 16:08:45 - INFO - __main__ - Step 16085: {'lr': 0.0004889107731692699, 'samples': 3088320, 'steps': 16084, 'loss/train': 1.3344615697860718} 08/30/2021 16:08:45 - INFO - __main__ - Step 16086: {'lr': 0.0004889092101348206, 'samples': 3088512, 'steps': 16085, 'loss/train': 1.3583908081054688} 08/30/2021 16:08:45 - INFO - __main__ - Step 16087: {'lr': 0.0004889076469927225, 'samples': 3088704, 'steps': 16086, 'loss/train': 1.5506062507629395} 08/30/2021 16:08:46 - INFO - __main__ - Step 16088: {'lr': 0.0004889060837429762, 'samples': 3088896, 'steps': 16087, 'loss/train': 1.8411803245544434} 08/30/2021 16:08:47 - INFO - __main__ - Step 16089: {'lr': 0.0004889045203855826, 'samples': 3089088, 'steps': 16088, 'loss/train': 1.8212236166000366} 08/30/2021 16:08:48 - INFO - __main__ - Step 16090: {'lr': 0.0004889029569205423, 'samples': 3089280, 'steps': 16089, 'loss/train': 1.8571813106536865} 08/30/2021 16:08:48 - INFO - __main__ - Step 16091: {'lr': 0.0004889013933478559, 'samples': 3089472, 'steps': 16090, 'loss/train': 1.8308440446853638} 08/30/2021 16:08:48 - INFO - __main__ - Step 16092: {'lr': 0.0004888998296675243, 'samples': 3089664, 'steps': 16091, 'loss/train': 1.9102141857147217} 08/30/2021 16:08:49 - INFO - __main__ - Step 16093: {'lr': 0.0004888982658795482, 'samples': 3089856, 'steps': 16092, 'loss/train': 1.6870355606079102} 08/30/2021 16:08:49 - INFO - __main__ - Step 16094: {'lr': 0.0004888967019839282, 'samples': 3090048, 'steps': 16093, 'loss/train': 1.6751246452331543} 08/30/2021 16:08:51 - INFO - __main__ - Step 16095: {'lr': 0.000488895137980665, 'samples': 3090240, 'steps': 16094, 'loss/train': 1.1235871315002441} 08/30/2021 16:08:51 - INFO - __main__ - Step 16096: {'lr': 0.0004888935738697593, 'samples': 3090432, 'steps': 16095, 'loss/train': 0.3828321099281311} 08/30/2021 16:08:52 - INFO - __main__ - Step 16097: {'lr': 0.0004888920096512118, 'samples': 3090624, 'steps': 16096, 'loss/train': 1.1133627891540527} 08/30/2021 16:08:52 - INFO - __main__ - Step 16098: {'lr': 0.0004888904453250233, 'samples': 3090816, 'steps': 16097, 'loss/train': 1.6914875507354736} 08/30/2021 16:08:52 - INFO - __main__ - Step 16099: {'lr': 0.0004888888808911946, 'samples': 3091008, 'steps': 16098, 'loss/train': 1.1670382022857666} 08/30/2021 16:08:54 - INFO - __main__ - Step 16100: {'lr': 0.0004888873163497261, 'samples': 3091200, 'steps': 16099, 'loss/train': 2.175337076187134} 08/30/2021 16:08:54 - INFO - __main__ - Step 16101: {'lr': 0.0004888857517006186, 'samples': 3091392, 'steps': 16100, 'loss/train': 1.7574958801269531} 08/30/2021 16:08:55 - INFO - __main__ - Step 16102: {'lr': 0.000488884186943873, 'samples': 3091584, 'steps': 16101, 'loss/train': 1.4863200187683105} 08/30/2021 16:08:55 - INFO - __main__ - Step 16103: {'lr': 0.0004888826220794899, 'samples': 3091776, 'steps': 16102, 'loss/train': 1.8977420330047607} 08/30/2021 16:08:56 - INFO - __main__ - Step 16104: {'lr': 0.0004888810571074698, 'samples': 3091968, 'steps': 16103, 'loss/train': 1.5029984712600708} 08/30/2021 16:08:56 - INFO - __main__ - Step 16105: {'lr': 0.0004888794920278137, 'samples': 3092160, 'steps': 16104, 'loss/train': 1.0788410902023315} 08/30/2021 16:08:57 - INFO - __main__ - Step 16106: {'lr': 0.0004888779268405223, 'samples': 3092352, 'steps': 16105, 'loss/train': 2.3209078311920166} 08/30/2021 16:08:58 - INFO - __main__ - Step 16107: {'lr': 0.0004888763615455959, 'samples': 3092544, 'steps': 16106, 'loss/train': 0.9094582200050354} 08/30/2021 16:08:58 - INFO - __main__ - Step 16108: {'lr': 0.0004888747961430358, 'samples': 3092736, 'steps': 16107, 'loss/train': 2.0828287601470947} 08/30/2021 16:08:59 - INFO - __main__ - Step 16109: {'lr': 0.0004888732306328422, 'samples': 3092928, 'steps': 16108, 'loss/train': 1.569623589515686} 08/30/2021 16:08:59 - INFO - __main__ - Step 16110: {'lr': 0.000488871665015016, 'samples': 3093120, 'steps': 16109, 'loss/train': 1.9902257919311523} 08/30/2021 16:09:01 - INFO - __main__ - Step 16111: {'lr': 0.0004888700992895581, 'samples': 3093312, 'steps': 16110, 'loss/train': 1.6226801872253418} 08/30/2021 16:09:01 - INFO - __main__ - Step 16112: {'lr': 0.0004888685334564688, 'samples': 3093504, 'steps': 16111, 'loss/train': 1.4757969379425049} 08/30/2021 16:09:02 - INFO - __main__ - Step 16113: {'lr': 0.0004888669675157492, 'samples': 3093696, 'steps': 16112, 'loss/train': 1.684322476387024} 08/30/2021 16:09:02 - INFO - __main__ - Step 16114: {'lr': 0.0004888654014673998, 'samples': 3093888, 'steps': 16113, 'loss/train': 0.572607696056366} 08/30/2021 16:09:02 - INFO - __main__ - Step 16115: {'lr': 0.0004888638353114212, 'samples': 3094080, 'steps': 16114, 'loss/train': 3.351923704147339} 08/30/2021 16:09:04 - INFO - __main__ - Step 16116: {'lr': 0.0004888622690478144, 'samples': 3094272, 'steps': 16115, 'loss/train': 2.2719335556030273} 08/30/2021 16:09:05 - INFO - __main__ - Step 16117: {'lr': 0.0004888607026765799, 'samples': 3094464, 'steps': 16116, 'loss/train': 1.4435566663742065} 08/30/2021 16:09:05 - INFO - __main__ - Step 16118: {'lr': 0.0004888591361977184, 'samples': 3094656, 'steps': 16117, 'loss/train': 2.0642950534820557} 08/30/2021 16:09:05 - INFO - __main__ - Step 16119: {'lr': 0.0004888575696112308, 'samples': 3094848, 'steps': 16118, 'loss/train': 1.451029658317566} 08/30/2021 16:09:06 - INFO - __main__ - Step 16120: {'lr': 0.0004888560029171175, 'samples': 3095040, 'steps': 16119, 'loss/train': 0.7746983766555786} 08/30/2021 16:09:07 - INFO - __main__ - Step 16121: {'lr': 0.0004888544361153794, 'samples': 3095232, 'steps': 16120, 'loss/train': 2.073786973953247} 08/30/2021 16:09:08 - INFO - __main__ - Step 16122: {'lr': 0.0004888528692060173, 'samples': 3095424, 'steps': 16121, 'loss/train': 1.788468837738037} 08/30/2021 16:09:08 - INFO - __main__ - Step 16123: {'lr': 0.0004888513021890316, 'samples': 3095616, 'steps': 16122, 'loss/train': 1.5074615478515625} 08/30/2021 16:09:08 - INFO - __main__ - Step 16124: {'lr': 0.0004888497350644234, 'samples': 3095808, 'steps': 16123, 'loss/train': 1.744973063468933} 08/30/2021 16:09:09 - INFO - __main__ - Step 16125: {'lr': 0.000488848167832193, 'samples': 3096000, 'steps': 16124, 'loss/train': 1.935605764389038} 08/30/2021 16:09:09 - INFO - __main__ - Step 16126: {'lr': 0.0004888466004923413, 'samples': 3096192, 'steps': 16125, 'loss/train': 1.6238654851913452} 08/30/2021 16:09:10 - INFO - __main__ - Step 16127: {'lr': 0.0004888450330448692, 'samples': 3096384, 'steps': 16126, 'loss/train': 1.3200464248657227} 08/30/2021 16:09:11 - INFO - __main__ - Step 16128: {'lr': 0.000488843465489777, 'samples': 3096576, 'steps': 16127, 'loss/train': 2.069633960723877} 08/30/2021 16:09:11 - INFO - __main__ - Step 16129: {'lr': 0.0004888418978270658, 'samples': 3096768, 'steps': 16128, 'loss/train': 1.963121771812439} 08/30/2021 16:09:12 - INFO - __main__ - Step 16130: {'lr': 0.000488840330056736, 'samples': 3096960, 'steps': 16129, 'loss/train': 0.6227633953094482} 08/30/2021 16:09:12 - INFO - __main__ - Step 16131: {'lr': 0.0004888387621787885, 'samples': 3097152, 'steps': 16130, 'loss/train': 1.151824712753296} 08/30/2021 16:09:14 - INFO - __main__ - Step 16132: {'lr': 0.0004888371941932239, 'samples': 3097344, 'steps': 16131, 'loss/train': 1.8692610263824463} 08/30/2021 16:09:14 - INFO - __main__ - Step 16133: {'lr': 0.000488835626100043, 'samples': 3097536, 'steps': 16132, 'loss/train': 2.0648441314697266} 08/30/2021 16:09:15 - INFO - __main__ - Step 16134: {'lr': 0.0004888340578992464, 'samples': 3097728, 'steps': 16133, 'loss/train': 1.5093820095062256} 08/30/2021 16:09:15 - INFO - __main__ - Step 16135: {'lr': 0.0004888324895908349, 'samples': 3097920, 'steps': 16134, 'loss/train': 0.14670990407466888} 08/30/2021 16:09:15 - INFO - __main__ - Step 16136: {'lr': 0.0004888309211748091, 'samples': 3098112, 'steps': 16135, 'loss/train': 2.1670074462890625} 08/30/2021 16:09:17 - INFO - __main__ - Step 16137: {'lr': 0.0004888293526511697, 'samples': 3098304, 'steps': 16136, 'loss/train': 1.357384204864502} 08/30/2021 16:09:18 - INFO - __main__ - Step 16138: {'lr': 0.0004888277840199177, 'samples': 3098496, 'steps': 16137, 'loss/train': 2.0959296226501465} 08/30/2021 16:09:18 - INFO - __main__ - Step 16139: {'lr': 0.0004888262152810534, 'samples': 3098688, 'steps': 16138, 'loss/train': 1.4581689834594727} 08/30/2021 16:09:19 - INFO - __main__ - Step 16140: {'lr': 0.0004888246464345779, 'samples': 3098880, 'steps': 16139, 'loss/train': 1.218555212020874} 08/30/2021 16:09:19 - INFO - __main__ - Step 16141: {'lr': 0.0004888230774804915, 'samples': 3099072, 'steps': 16140, 'loss/train': 2.924306631088257} 08/30/2021 16:09:19 - INFO - __main__ - Step 16142: {'lr': 0.0004888215084187952, 'samples': 3099264, 'steps': 16141, 'loss/train': 1.1649971008300781} 08/30/2021 16:09:20 - INFO - __main__ - Step 16143: {'lr': 0.0004888199392494896, 'samples': 3099456, 'steps': 16142, 'loss/train': 1.8804823160171509} 08/30/2021 16:09:21 - INFO - __main__ - Step 16144: {'lr': 0.0004888183699725755, 'samples': 3099648, 'steps': 16143, 'loss/train': 1.9456937313079834} 08/30/2021 16:09:22 - INFO - __main__ - Step 16145: {'lr': 0.0004888168005880533, 'samples': 3099840, 'steps': 16144, 'loss/train': 1.3489423990249634} 08/30/2021 16:09:22 - INFO - __main__ - Step 16146: {'lr': 0.0004888152310959242, 'samples': 3100032, 'steps': 16145, 'loss/train': 2.2964887619018555} 08/30/2021 16:09:23 - INFO - __main__ - Step 16147: {'lr': 0.0004888136614961885, 'samples': 3100224, 'steps': 16146, 'loss/train': 1.5480968952178955} 08/30/2021 16:09:23 - INFO - __main__ - Step 16148: {'lr': 0.000488812091788847, 'samples': 3100416, 'steps': 16147, 'loss/train': 1.7133764028549194} 08/30/2021 16:09:23 - INFO - __main__ - Step 16149: {'lr': 0.0004888105219739005, 'samples': 3100608, 'steps': 16148, 'loss/train': 1.5252094268798828} 08/30/2021 16:09:25 - INFO - __main__ - Step 16150: {'lr': 0.0004888089520513497, 'samples': 3100800, 'steps': 16149, 'loss/train': 2.347001314163208} 08/30/2021 16:09:25 - INFO - __main__ - Step 16151: {'lr': 0.0004888073820211952, 'samples': 3100992, 'steps': 16150, 'loss/train': 1.6128660440444946} 08/30/2021 16:09:26 - INFO - __main__ - Step 16152: {'lr': 0.0004888058118834379, 'samples': 3101184, 'steps': 16151, 'loss/train': 1.2262918949127197} 08/30/2021 16:09:26 - INFO - __main__ - Step 16153: {'lr': 0.0004888042416380784, 'samples': 3101376, 'steps': 16152, 'loss/train': 1.3816686868667603} 08/30/2021 16:09:26 - INFO - __main__ - Step 16154: {'lr': 0.0004888026712851172, 'samples': 3101568, 'steps': 16153, 'loss/train': 1.3808690309524536} 08/30/2021 16:09:28 - INFO - __main__ - Step 16155: {'lr': 0.0004888011008245554, 'samples': 3101760, 'steps': 16154, 'loss/train': 2.342851400375366} 08/30/2021 16:09:28 - INFO - __main__ - Step 16156: {'lr': 0.0004887995302563934, 'samples': 3101952, 'steps': 16155, 'loss/train': 1.524072527885437} 08/30/2021 16:09:29 - INFO - __main__ - Step 16157: {'lr': 0.000488797959580632, 'samples': 3102144, 'steps': 16156, 'loss/train': 1.9407135248184204} 08/30/2021 16:09:29 - INFO - __main__ - Step 16158: {'lr': 0.000488796388797272, 'samples': 3102336, 'steps': 16157, 'loss/train': 1.8427869081497192} 08/30/2021 16:09:29 - INFO - __main__ - Step 16159: {'lr': 0.0004887948179063139, 'samples': 3102528, 'steps': 16158, 'loss/train': 1.2670528888702393} 08/30/2021 16:09:31 - INFO - __main__ - Step 16160: {'lr': 0.0004887932469077587, 'samples': 3102720, 'steps': 16159, 'loss/train': 1.7608425617218018} 08/30/2021 16:09:32 - INFO - __main__ - Step 16161: {'lr': 0.0004887916758016069, 'samples': 3102912, 'steps': 16160, 'loss/train': 1.6997241973876953} 08/30/2021 16:09:32 - INFO - __main__ - Step 16162: {'lr': 0.0004887901045878592, 'samples': 3103104, 'steps': 16161, 'loss/train': 1.8640961647033691} 08/30/2021 16:09:33 - INFO - __main__ - Step 16163: {'lr': 0.0004887885332665165, 'samples': 3103296, 'steps': 16162, 'loss/train': 1.8507424592971802} 08/30/2021 16:09:33 - INFO - __main__ - Step 16164: {'lr': 0.0004887869618375793, 'samples': 3103488, 'steps': 16163, 'loss/train': 1.8012827634811401} 08/30/2021 16:09:34 - INFO - __main__ - Step 16165: {'lr': 0.0004887853903010483, 'samples': 3103680, 'steps': 16164, 'loss/train': 1.77405846118927} 08/30/2021 16:09:35 - INFO - __main__ - Step 16166: {'lr': 0.0004887838186569244, 'samples': 3103872, 'steps': 16165, 'loss/train': 1.9588273763656616} 08/30/2021 16:09:35 - INFO - __main__ - Step 16167: {'lr': 0.0004887822469052081, 'samples': 3104064, 'steps': 16166, 'loss/train': 1.5669358968734741} 08/30/2021 16:09:35 - INFO - __main__ - Step 16168: {'lr': 0.0004887806750459002, 'samples': 3104256, 'steps': 16167, 'loss/train': 1.1243661642074585} 08/30/2021 16:09:36 - INFO - __main__ - Step 16169: {'lr': 0.0004887791030790016, 'samples': 3104448, 'steps': 16168, 'loss/train': 0.7587945461273193} 08/30/2021 16:09:37 - INFO - __main__ - Step 16170: {'lr': 0.0004887775310045126, 'samples': 3104640, 'steps': 16169, 'loss/train': 1.7444339990615845} 08/30/2021 16:09:38 - INFO - __main__ - Step 16171: {'lr': 0.0004887759588224342, 'samples': 3104832, 'steps': 16170, 'loss/train': 1.7415778636932373} 08/30/2021 16:09:38 - INFO - __main__ - Step 16172: {'lr': 0.000488774386532767, 'samples': 3105024, 'steps': 16171, 'loss/train': 1.9292267560958862} 08/30/2021 16:09:39 - INFO - __main__ - Step 16173: {'lr': 0.0004887728141355118, 'samples': 3105216, 'steps': 16172, 'loss/train': 1.68677818775177} 08/30/2021 16:09:39 - INFO - __main__ - Step 16174: {'lr': 0.0004887712416306693, 'samples': 3105408, 'steps': 16173, 'loss/train': 1.582221269607544} 08/30/2021 16:09:39 - INFO - __main__ - Step 16175: {'lr': 0.00048876966901824, 'samples': 3105600, 'steps': 16174, 'loss/train': 3.0712389945983887} 08/30/2021 16:09:41 - INFO - __main__ - Step 16176: {'lr': 0.0004887680962982249, 'samples': 3105792, 'steps': 16175, 'loss/train': 1.2103501558303833} 08/30/2021 16:09:41 - INFO - __main__ - Step 16177: {'lr': 0.0004887665234706247, 'samples': 3105984, 'steps': 16176, 'loss/train': 0.9753164052963257} 08/30/2021 16:09:42 - INFO - __main__ - Step 16178: {'lr': 0.0004887649505354398, 'samples': 3106176, 'steps': 16177, 'loss/train': 1.9455859661102295} 08/30/2021 16:09:42 - INFO - __main__ - Step 16179: {'lr': 0.000488763377492671, 'samples': 3106368, 'steps': 16178, 'loss/train': 2.0331685543060303} 08/30/2021 16:09:42 - INFO - __main__ - Step 16180: {'lr': 0.0004887618043423194, 'samples': 3106560, 'steps': 16179, 'loss/train': 1.3366820812225342} 08/30/2021 16:09:44 - INFO - __main__ - Step 16181: {'lr': 0.0004887602310843852, 'samples': 3106752, 'steps': 16180, 'loss/train': 1.2191157341003418} 08/30/2021 16:09:44 - INFO - __main__ - Step 16182: {'lr': 0.0004887586577188694, 'samples': 3106944, 'steps': 16181, 'loss/train': 1.6067984104156494} 08/30/2021 16:09:45 - INFO - __main__ - Step 16183: {'lr': 0.0004887570842457726, 'samples': 3107136, 'steps': 16182, 'loss/train': 1.8974665403366089} 08/30/2021 16:09:45 - INFO - __main__ - Step 16184: {'lr': 0.0004887555106650956, 'samples': 3107328, 'steps': 16183, 'loss/train': 1.5397377014160156} 08/30/2021 16:09:46 - INFO - __main__ - Step 16185: {'lr': 0.000488753936976839, 'samples': 3107520, 'steps': 16184, 'loss/train': 1.5278619527816772} 08/30/2021 16:09:47 - INFO - __main__ - Step 16186: {'lr': 0.0004887523631810036, 'samples': 3107712, 'steps': 16185, 'loss/train': 1.9503189325332642} 08/30/2021 16:09:48 - INFO - __main__ - Step 16187: {'lr': 0.00048875078927759, 'samples': 3107904, 'steps': 16186, 'loss/train': 1.579522967338562} 08/30/2021 16:09:48 - INFO - __main__ - Step 16188: {'lr': 0.000488749215266599, 'samples': 3108096, 'steps': 16187, 'loss/train': 1.55048406124115} 08/30/2021 16:09:48 - INFO - __main__ - Step 16189: {'lr': 0.0004887476411480314, 'samples': 3108288, 'steps': 16188, 'loss/train': 1.6580860614776611} 08/30/2021 16:09:49 - INFO - __main__ - Step 16190: {'lr': 0.0004887460669218877, 'samples': 3108480, 'steps': 16189, 'loss/train': 2.1892404556274414} 08/30/2021 16:09:49 - INFO - __main__ - Step 16191: {'lr': 0.0004887444925881688, 'samples': 3108672, 'steps': 16190, 'loss/train': 1.9593427181243896} 08/30/2021 16:09:50 - INFO - __main__ - Step 16192: {'lr': 0.0004887429181468752, 'samples': 3108864, 'steps': 16191, 'loss/train': 1.5536094903945923} 08/30/2021 16:09:51 - INFO - __main__ - Step 16193: {'lr': 0.0004887413435980077, 'samples': 3109056, 'steps': 16192, 'loss/train': 1.3946034908294678} 08/30/2021 16:09:51 - INFO - __main__ - Step 16194: {'lr': 0.0004887397689415672, 'samples': 3109248, 'steps': 16193, 'loss/train': 1.8941177129745483} 08/30/2021 16:09:52 - INFO - __main__ - Step 16195: {'lr': 0.0004887381941775541, 'samples': 3109440, 'steps': 16194, 'loss/train': 1.5038566589355469} 08/30/2021 16:09:52 - INFO - __main__ - Step 16196: {'lr': 0.0004887366193059693, 'samples': 3109632, 'steps': 16195, 'loss/train': 2.350515127182007} 08/30/2021 16:09:54 - INFO - __main__ - Step 16197: {'lr': 0.0004887350443268134, 'samples': 3109824, 'steps': 16196, 'loss/train': 2.0816149711608887} 08/30/2021 16:09:54 - INFO - __main__ - Step 16198: {'lr': 0.0004887334692400872, 'samples': 3110016, 'steps': 16197, 'loss/train': 2.001119375228882} 08/30/2021 16:09:54 - INFO - __main__ - Step 16199: {'lr': 0.0004887318940457915, 'samples': 3110208, 'steps': 16198, 'loss/train': 2.252450466156006} 08/30/2021 16:09:55 - INFO - __main__ - Step 16200: {'lr': 0.0004887303187439267, 'samples': 3110400, 'steps': 16199, 'loss/train': 1.8264209032058716} 08/30/2021 16:09:55 - INFO - __main__ - Step 16201: {'lr': 0.0004887287433344939, 'samples': 3110592, 'steps': 16200, 'loss/train': 2.057054281234741} 08/30/2021 16:09:57 - INFO - __main__ - Step 16202: {'lr': 0.0004887271678174935, 'samples': 3110784, 'steps': 16201, 'loss/train': 1.7432345151901245} 08/30/2021 16:09:57 - INFO - __main__ - Step 16203: {'lr': 0.0004887255921929264, 'samples': 3110976, 'steps': 16202, 'loss/train': 1.7855374813079834} 08/30/2021 16:09:57 - INFO - __main__ - Step 16204: {'lr': 0.0004887240164607931, 'samples': 3111168, 'steps': 16203, 'loss/train': 1.6861077547073364} 08/30/2021 16:09:58 - INFO - __main__ - Step 16205: {'lr': 0.0004887224406210945, 'samples': 3111360, 'steps': 16204, 'loss/train': 1.757550597190857} 08/30/2021 16:09:58 - INFO - __main__ - Step 16206: {'lr': 0.0004887208646738312, 'samples': 3111552, 'steps': 16205, 'loss/train': 1.7205955982208252} 08/30/2021 16:10:00 - INFO - __main__ - Step 16207: {'lr': 0.000488719288619004, 'samples': 3111744, 'steps': 16206, 'loss/train': 1.0609853267669678} 08/30/2021 16:10:00 - INFO - __main__ - Step 16208: {'lr': 0.0004887177124566136, 'samples': 3111936, 'steps': 16207, 'loss/train': 1.9943522214889526} 08/30/2021 16:10:01 - INFO - __main__ - Step 16209: {'lr': 0.0004887161361866607, 'samples': 3112128, 'steps': 16208, 'loss/train': 2.03987455368042} 08/30/2021 16:10:01 - INFO - __main__ - Step 16210: {'lr': 0.000488714559809146, 'samples': 3112320, 'steps': 16209, 'loss/train': 1.0090466737747192} 08/30/2021 16:10:01 - INFO - __main__ - Step 16211: {'lr': 0.0004887129833240703, 'samples': 3112512, 'steps': 16210, 'loss/train': 2.009734630584717} 08/30/2021 16:10:02 - INFO - __main__ - Step 16212: {'lr': 0.000488711406731434, 'samples': 3112704, 'steps': 16211, 'loss/train': 2.1733686923980713} 08/30/2021 16:10:04 - INFO - __main__ - Step 16213: {'lr': 0.0004887098300312381, 'samples': 3112896, 'steps': 16212, 'loss/train': 2.4037039279937744} 08/30/2021 16:10:04 - INFO - __main__ - Step 16214: {'lr': 0.0004887082532234832, 'samples': 3113088, 'steps': 16213, 'loss/train': 1.0594024658203125} 08/30/2021 16:10:05 - INFO - __main__ - Step 16215: {'lr': 0.0004887066763081702, 'samples': 3113280, 'steps': 16214, 'loss/train': 1.5682018995285034} 08/30/2021 16:10:05 - INFO - __main__ - Step 16216: {'lr': 0.0004887050992852995, 'samples': 3113472, 'steps': 16215, 'loss/train': 2.072334051132202} 08/30/2021 16:10:05 - INFO - __main__ - Step 16217: {'lr': 0.000488703522154872, 'samples': 3113664, 'steps': 16216, 'loss/train': 1.8428153991699219} 08/30/2021 16:10:07 - INFO - __main__ - Step 16218: {'lr': 0.0004887019449168884, 'samples': 3113856, 'steps': 16217, 'loss/train': 1.2231703996658325} 08/30/2021 16:10:08 - INFO - __main__ - Step 16219: {'lr': 0.0004887003675713493, 'samples': 3114048, 'steps': 16218, 'loss/train': 1.609653115272522} 08/30/2021 16:10:08 - INFO - __main__ - Step 16220: {'lr': 0.0004886987901182556, 'samples': 3114240, 'steps': 16219, 'loss/train': 0.17627251148223877} 08/30/2021 16:10:08 - INFO - __main__ - Step 16221: {'lr': 0.0004886972125576079, 'samples': 3114432, 'steps': 16220, 'loss/train': 0.09967661648988724} 08/30/2021 16:10:09 - INFO - __main__ - Step 16222: {'lr': 0.0004886956348894069, 'samples': 3114624, 'steps': 16221, 'loss/train': 1.9792263507843018} 08/30/2021 16:10:09 - INFO - __main__ - Step 16223: {'lr': 0.0004886940571136533, 'samples': 3114816, 'steps': 16222, 'loss/train': 1.4621689319610596} 08/30/2021 16:10:11 - INFO - __main__ - Step 16224: {'lr': 0.0004886924792303479, 'samples': 3115008, 'steps': 16223, 'loss/train': 1.6258628368377686} 08/30/2021 16:10:11 - INFO - __main__ - Step 16225: {'lr': 0.0004886909012394913, 'samples': 3115200, 'steps': 16224, 'loss/train': 1.3522077798843384} 08/30/2021 16:10:11 - INFO - __main__ - Step 16226: {'lr': 0.0004886893231410844, 'samples': 3115392, 'steps': 16225, 'loss/train': 2.247959613800049} 08/30/2021 16:10:12 - INFO - __main__ - Step 16227: {'lr': 0.0004886877449351276, 'samples': 3115584, 'steps': 16226, 'loss/train': 1.8723901510238647} 08/30/2021 16:10:12 - INFO - __main__ - Step 16228: {'lr': 0.0004886861666216219, 'samples': 3115776, 'steps': 16227, 'loss/train': 1.1099066734313965} 08/30/2021 16:10:14 - INFO - __main__ - Step 16229: {'lr': 0.0004886845882005679, 'samples': 3115968, 'steps': 16228, 'loss/train': 1.552213191986084} 08/30/2021 16:10:14 - INFO - __main__ - Step 16230: {'lr': 0.0004886830096719662, 'samples': 3116160, 'steps': 16229, 'loss/train': 1.9366902112960815} 08/30/2021 16:10:14 - INFO - __main__ - Step 16231: {'lr': 0.0004886814310358176, 'samples': 3116352, 'steps': 16230, 'loss/train': 1.5782767534255981} 08/30/2021 16:10:15 - INFO - __main__ - Step 16232: {'lr': 0.000488679852292123, 'samples': 3116544, 'steps': 16231, 'loss/train': 1.4731717109680176} 08/30/2021 16:10:15 - INFO - __main__ - Step 16233: {'lr': 0.0004886782734408828, 'samples': 3116736, 'steps': 16232, 'loss/train': 2.0903234481811523} 08/30/2021 16:10:17 - INFO - __main__ - Step 16234: {'lr': 0.0004886766944820979, 'samples': 3116928, 'steps': 16233, 'loss/train': 0.8610385060310364} 08/30/2021 16:10:17 - INFO - __main__ - Step 16235: {'lr': 0.0004886751154157689, 'samples': 3117120, 'steps': 16234, 'loss/train': 1.0175727605819702} 08/30/2021 16:10:17 - INFO - __main__ - Step 16236: {'lr': 0.0004886735362418967, 'samples': 3117312, 'steps': 16235, 'loss/train': 1.5067758560180664} 08/30/2021 16:10:18 - INFO - __main__ - Step 16237: {'lr': 0.0004886719569604818, 'samples': 3117504, 'steps': 16236, 'loss/train': 1.7044957876205444} 08/30/2021 16:10:18 - INFO - __main__ - Step 16238: {'lr': 0.000488670377571525, 'samples': 3117696, 'steps': 16237, 'loss/train': 3.1742258071899414} 08/30/2021 16:10:19 - INFO - __main__ - Step 16239: {'lr': 0.0004886687980750271, 'samples': 3117888, 'steps': 16238, 'loss/train': 2.278348684310913} 08/30/2021 16:10:20 - INFO - __main__ - Step 16240: {'lr': 0.0004886672184709886, 'samples': 3118080, 'steps': 16239, 'loss/train': 1.5339815616607666} 08/30/2021 16:10:20 - INFO - __main__ - Step 16241: {'lr': 0.0004886656387594104, 'samples': 3118272, 'steps': 16240, 'loss/train': 0.7528780698776245} 08/30/2021 16:10:21 - INFO - __main__ - Step 16242: {'lr': 0.0004886640589402932, 'samples': 3118464, 'steps': 16241, 'loss/train': 1.4154741764068604} 08/30/2021 16:10:21 - INFO - __main__ - Step 16243: {'lr': 0.0004886624790136375, 'samples': 3118656, 'steps': 16242, 'loss/train': 1.8899236917495728} 08/30/2021 16:10:22 - INFO - __main__ - Step 16244: {'lr': 0.0004886608989794443, 'samples': 3118848, 'steps': 16243, 'loss/train': 1.998671293258667} 08/30/2021 16:10:23 - INFO - __main__ - Step 16245: {'lr': 0.0004886593188377142, 'samples': 3119040, 'steps': 16244, 'loss/train': 1.9466640949249268} 08/30/2021 16:10:23 - INFO - __main__ - Step 16246: {'lr': 0.0004886577385884478, 'samples': 3119232, 'steps': 16245, 'loss/train': 1.231416940689087} 08/30/2021 16:10:24 - INFO - __main__ - Step 16247: {'lr': 0.0004886561582316458, 'samples': 3119424, 'steps': 16246, 'loss/train': 1.6249898672103882} 08/30/2021 16:10:24 - INFO - __main__ - Step 16248: {'lr': 0.0004886545777673093, 'samples': 3119616, 'steps': 16247, 'loss/train': 1.663931131362915} 08/30/2021 16:10:26 - INFO - __main__ - Step 16249: {'lr': 0.0004886529971954385, 'samples': 3119808, 'steps': 16248, 'loss/train': 1.503287672996521} 08/30/2021 16:10:26 - INFO - __main__ - Step 16250: {'lr': 0.0004886514165160345, 'samples': 3120000, 'steps': 16249, 'loss/train': 0.7937673330307007} 08/30/2021 16:10:26 - INFO - __main__ - Step 16251: {'lr': 0.0004886498357290979, 'samples': 3120192, 'steps': 16250, 'loss/train': 3.2912514209747314} 08/30/2021 16:10:27 - INFO - __main__ - Step 16252: {'lr': 0.0004886482548346291, 'samples': 3120384, 'steps': 16251, 'loss/train': 0.1299923211336136} 08/30/2021 16:10:27 - INFO - __main__ - Step 16253: {'lr': 0.0004886466738326293, 'samples': 3120576, 'steps': 16252, 'loss/train': 0.14120961725711823} 08/30/2021 16:10:27 - INFO - __main__ - Step 16254: {'lr': 0.000488645092723099, 'samples': 3120768, 'steps': 16253, 'loss/train': 1.906154990196228} 08/30/2021 16:10:29 - INFO - __main__ - Step 16255: {'lr': 0.0004886435115060388, 'samples': 3120960, 'steps': 16254, 'loss/train': 1.6424577236175537} 08/30/2021 16:10:29 - INFO - __main__ - Step 16256: {'lr': 0.0004886419301814495, 'samples': 3121152, 'steps': 16255, 'loss/train': 1.7797577381134033} 08/30/2021 16:10:30 - INFO - __main__ - Step 16257: {'lr': 0.0004886403487493319, 'samples': 3121344, 'steps': 16256, 'loss/train': 1.8279746770858765} 08/30/2021 16:10:30 - INFO - __main__ - Step 16258: {'lr': 0.0004886387672096866, 'samples': 3121536, 'steps': 16257, 'loss/train': 0.8470008969306946} 08/30/2021 16:10:30 - INFO - __main__ - Step 16259: {'lr': 0.0004886371855625143, 'samples': 3121728, 'steps': 16258, 'loss/train': 1.8683289289474487} 08/30/2021 16:10:32 - INFO - __main__ - Step 16260: {'lr': 0.0004886356038078159, 'samples': 3121920, 'steps': 16259, 'loss/train': 1.5578852891921997} 08/30/2021 16:10:32 - INFO - __main__ - Step 16261: {'lr': 0.0004886340219455919, 'samples': 3122112, 'steps': 16260, 'loss/train': 1.034650444984436} 08/30/2021 16:10:33 - INFO - __main__ - Step 16262: {'lr': 0.0004886324399758431, 'samples': 3122304, 'steps': 16261, 'loss/train': 1.6897884607315063} 08/30/2021 16:10:33 - INFO - __main__ - Step 16263: {'lr': 0.0004886308578985702, 'samples': 3122496, 'steps': 16262, 'loss/train': 1.7113878726959229} 08/30/2021 16:10:33 - INFO - __main__ - Step 16264: {'lr': 0.0004886292757137739, 'samples': 3122688, 'steps': 16263, 'loss/train': 2.0861010551452637} 08/30/2021 16:10:34 - INFO - __main__ - Step 16265: {'lr': 0.0004886276934214551, 'samples': 3122880, 'steps': 16264, 'loss/train': 1.7308111190795898} 08/30/2021 16:10:35 - INFO - __main__ - Step 16266: {'lr': 0.0004886261110216141, 'samples': 3123072, 'steps': 16265, 'loss/train': 1.7342652082443237} 08/30/2021 16:10:36 - INFO - __main__ - Step 16267: {'lr': 0.000488624528514252, 'samples': 3123264, 'steps': 16266, 'loss/train': 1.5815978050231934} 08/30/2021 16:10:36 - INFO - __main__ - Step 16268: {'lr': 0.0004886229458993693, 'samples': 3123456, 'steps': 16267, 'loss/train': 1.6773253679275513} 08/30/2021 16:10:36 - INFO - __main__ - Step 16269: {'lr': 0.0004886213631769669, 'samples': 3123648, 'steps': 16268, 'loss/train': 1.8577414751052856} 08/30/2021 16:10:37 - INFO - __main__ - Step 16270: {'lr': 0.0004886197803470453, 'samples': 3123840, 'steps': 16269, 'loss/train': 1.8149452209472656} 08/30/2021 16:10:39 - INFO - __main__ - Step 16271: {'lr': 0.0004886181974096052, 'samples': 3124032, 'steps': 16270, 'loss/train': 1.1607913970947266} 08/30/2021 16:10:39 - INFO - __main__ - Step 16272: {'lr': 0.0004886166143646476, 'samples': 3124224, 'steps': 16271, 'loss/train': 1.8695080280303955} 08/30/2021 16:10:40 - INFO - __main__ - Step 16273: {'lr': 0.000488615031212173, 'samples': 3124416, 'steps': 16272, 'loss/train': 1.834064245223999} 08/30/2021 16:10:40 - INFO - __main__ - Step 16274: {'lr': 0.0004886134479521821, 'samples': 3124608, 'steps': 16273, 'loss/train': 1.9997714757919312} 08/30/2021 16:10:40 - INFO - __main__ - Step 16275: {'lr': 0.0004886118645846757, 'samples': 3124800, 'steps': 16274, 'loss/train': 1.942400574684143} 08/30/2021 16:10:42 - INFO - __main__ - Step 16276: {'lr': 0.0004886102811096544, 'samples': 3124992, 'steps': 16275, 'loss/train': 1.6288559436798096} 08/30/2021 16:10:42 - INFO - __main__ - Step 16277: {'lr': 0.0004886086975271191, 'samples': 3125184, 'steps': 16276, 'loss/train': 1.7238287925720215} 08/30/2021 16:10:43 - INFO - __main__ - Step 16278: {'lr': 0.0004886071138370704, 'samples': 3125376, 'steps': 16277, 'loss/train': 1.8636168241500854} 08/30/2021 16:10:43 - INFO - __main__ - Step 16279: {'lr': 0.000488605530039509, 'samples': 3125568, 'steps': 16278, 'loss/train': 1.5248596668243408} 08/30/2021 16:10:43 - INFO - __main__ - Step 16280: {'lr': 0.0004886039461344356, 'samples': 3125760, 'steps': 16279, 'loss/train': 1.7116458415985107} 08/30/2021 16:10:45 - INFO - __main__ - Step 16281: {'lr': 0.0004886023621218509, 'samples': 3125952, 'steps': 16280, 'loss/train': 1.7959003448486328} 08/30/2021 16:10:45 - INFO - __main__ - Step 16282: {'lr': 0.0004886007780017557, 'samples': 3126144, 'steps': 16281, 'loss/train': 1.5302084684371948} 08/30/2021 16:10:46 - INFO - __main__ - Step 16283: {'lr': 0.0004885991937741506, 'samples': 3126336, 'steps': 16282, 'loss/train': 1.8500771522521973} 08/30/2021 16:10:46 - INFO - __main__ - Step 16284: {'lr': 0.0004885976094390366, 'samples': 3126528, 'steps': 16283, 'loss/train': 1.7807413339614868} 08/30/2021 16:10:46 - INFO - __main__ - Step 16285: {'lr': 0.000488596024996414, 'samples': 3126720, 'steps': 16284, 'loss/train': 1.6970168352127075} 08/30/2021 16:10:47 - INFO - __main__ - Step 16286: {'lr': 0.0004885944404462838, 'samples': 3126912, 'steps': 16285, 'loss/train': 1.7380517721176147} 08/30/2021 16:10:49 - INFO - __main__ - Step 16287: {'lr': 0.0004885928557886466, 'samples': 3127104, 'steps': 16286, 'loss/train': 1.9905680418014526} 08/30/2021 16:10:49 - INFO - __main__ - Step 16288: {'lr': 0.0004885912710235031, 'samples': 3127296, 'steps': 16287, 'loss/train': 1.461103916168213} 08/30/2021 16:10:49 - INFO - __main__ - Step 16289: {'lr': 0.0004885896861508541, 'samples': 3127488, 'steps': 16288, 'loss/train': 2.0694077014923096} 08/30/2021 16:10:50 - INFO - __main__ - Step 16290: {'lr': 0.0004885881011707003, 'samples': 3127680, 'steps': 16289, 'loss/train': 1.1995704174041748} 08/30/2021 16:10:50 - INFO - __main__ - Step 16291: {'lr': 0.0004885865160830422, 'samples': 3127872, 'steps': 16290, 'loss/train': 1.7522541284561157} 08/30/2021 16:10:51 - INFO - __main__ - Step 16292: {'lr': 0.0004885849308878809, 'samples': 3128064, 'steps': 16291, 'loss/train': 1.6052396297454834} 08/30/2021 16:10:52 - INFO - __main__ - Step 16293: {'lr': 0.0004885833455852169, 'samples': 3128256, 'steps': 16292, 'loss/train': 1.8246219158172607} 08/30/2021 16:10:52 - INFO - __main__ - Step 16294: {'lr': 0.0004885817601750509, 'samples': 3128448, 'steps': 16293, 'loss/train': 1.7759073972702026} 08/30/2021 16:10:53 - INFO - __main__ - Step 16295: {'lr': 0.0004885801746573836, 'samples': 3128640, 'steps': 16294, 'loss/train': 1.4780112504959106} 08/30/2021 16:10:53 - INFO - __main__ - Step 16296: {'lr': 0.0004885785890322158, 'samples': 3128832, 'steps': 16295, 'loss/train': 1.8578686714172363} 08/30/2021 16:10:54 - INFO - __main__ - Step 16297: {'lr': 0.0004885770032995482, 'samples': 3129024, 'steps': 16296, 'loss/train': 1.973870873451233} 08/30/2021 16:10:55 - INFO - __main__ - Step 16298: {'lr': 0.0004885754174593814, 'samples': 3129216, 'steps': 16297, 'loss/train': 1.013839602470398} 08/30/2021 16:10:55 - INFO - __main__ - Step 16299: {'lr': 0.0004885738315117162, 'samples': 3129408, 'steps': 16298, 'loss/train': 1.2680706977844238} 08/30/2021 16:10:56 - INFO - __main__ - Step 16300: {'lr': 0.0004885722454565534, 'samples': 3129600, 'steps': 16299, 'loss/train': 1.2194448709487915} 08/30/2021 16:10:56 - INFO - __main__ - Step 16301: {'lr': 0.0004885706592938936, 'samples': 3129792, 'steps': 16300, 'loss/train': 1.9567265510559082} 08/30/2021 16:10:58 - INFO - __main__ - Step 16302: {'lr': 0.0004885690730237375, 'samples': 3129984, 'steps': 16301, 'loss/train': 1.841776967048645} 08/30/2021 16:10:58 - INFO - __main__ - Step 16303: {'lr': 0.0004885674866460858, 'samples': 3130176, 'steps': 16302, 'loss/train': 2.2307300567626953} 08/30/2021 16:10:58 - INFO - __main__ - Step 16304: {'lr': 0.0004885659001609393, 'samples': 3130368, 'steps': 16303, 'loss/train': 1.4630793333053589} 08/30/2021 16:10:59 - INFO - __main__ - Step 16305: {'lr': 0.0004885643135682987, 'samples': 3130560, 'steps': 16304, 'loss/train': 1.1288224458694458} 08/30/2021 16:10:59 - INFO - __main__ - Step 16306: {'lr': 0.0004885627268681648, 'samples': 3130752, 'steps': 16305, 'loss/train': 5.890904903411865} 08/30/2021 16:10:59 - INFO - __main__ - Step 16307: {'lr': 0.0004885611400605381, 'samples': 3130944, 'steps': 16306, 'loss/train': 1.1502996683120728} 08/30/2021 16:11:01 - INFO - __main__ - Step 16308: {'lr': 0.0004885595531454195, 'samples': 3131136, 'steps': 16307, 'loss/train': 2.030357837677002} 08/30/2021 16:11:01 - INFO - __main__ - Step 16309: {'lr': 0.0004885579661228097, 'samples': 3131328, 'steps': 16308, 'loss/train': 2.012671947479248} 08/30/2021 16:11:02 - INFO - __main__ - Step 16310: {'lr': 0.0004885563789927092, 'samples': 3131520, 'steps': 16309, 'loss/train': 1.4014322757720947} 08/30/2021 16:11:02 - INFO - __main__ - Step 16311: {'lr': 0.0004885547917551189, 'samples': 3131712, 'steps': 16310, 'loss/train': 1.609916090965271} 08/30/2021 16:11:02 - INFO - __main__ - Step 16312: {'lr': 0.0004885532044100396, 'samples': 3131904, 'steps': 16311, 'loss/train': 1.7045129537582397} 08/30/2021 16:11:04 - INFO - __main__ - Step 16313: {'lr': 0.0004885516169574719, 'samples': 3132096, 'steps': 16312, 'loss/train': 1.6659396886825562} 08/30/2021 16:11:05 - INFO - __main__ - Step 16314: {'lr': 0.0004885500293974165, 'samples': 3132288, 'steps': 16313, 'loss/train': 1.6932291984558105} 08/30/2021 16:11:05 - INFO - __main__ - Step 16315: {'lr': 0.0004885484417298741, 'samples': 3132480, 'steps': 16314, 'loss/train': 1.825520396232605} 08/30/2021 16:11:05 - INFO - __main__ - Step 16316: {'lr': 0.0004885468539548455, 'samples': 3132672, 'steps': 16315, 'loss/train': 0.23717674612998962} 08/30/2021 16:11:06 - INFO - __main__ - Step 16317: {'lr': 0.0004885452660723313, 'samples': 3132864, 'steps': 16316, 'loss/train': 1.829975962638855} 08/30/2021 16:11:07 - INFO - __main__ - Step 16318: {'lr': 0.0004885436780823324, 'samples': 3133056, 'steps': 16317, 'loss/train': 1.3374109268188477} 08/30/2021 16:11:08 - INFO - __main__ - Step 16319: {'lr': 0.0004885420899848492, 'samples': 3133248, 'steps': 16318, 'loss/train': 0.565299928188324} 08/30/2021 16:11:08 - INFO - __main__ - Step 16320: {'lr': 0.0004885405017798828, 'samples': 3133440, 'steps': 16319, 'loss/train': 1.8940999507904053} 08/30/2021 16:11:08 - INFO - __main__ - Step 16321: {'lr': 0.0004885389134674337, 'samples': 3133632, 'steps': 16320, 'loss/train': 1.845708966255188} 08/30/2021 16:11:09 - INFO - __main__ - Step 16322: {'lr': 0.0004885373250475026, 'samples': 3133824, 'steps': 16321, 'loss/train': 1.7308459281921387} 08/30/2021 16:11:11 - INFO - __main__ - Step 16323: {'lr': 0.0004885357365200903, 'samples': 3134016, 'steps': 16322, 'loss/train': 1.538646936416626} 08/30/2021 16:11:11 - INFO - __main__ - Step 16324: {'lr': 0.0004885341478851975, 'samples': 3134208, 'steps': 16323, 'loss/train': 1.763047695159912} 08/30/2021 16:11:12 - INFO - __main__ - Step 16325: {'lr': 0.0004885325591428248, 'samples': 3134400, 'steps': 16324, 'loss/train': 1.3690780401229858} 08/30/2021 16:11:12 - INFO - __main__ - Step 16326: {'lr': 0.0004885309702929731, 'samples': 3134592, 'steps': 16325, 'loss/train': 1.5660958290100098} 08/30/2021 16:11:12 - INFO - __main__ - Step 16327: {'lr': 0.000488529381335643, 'samples': 3134784, 'steps': 16326, 'loss/train': 1.7297216653823853} 08/30/2021 16:11:14 - INFO - __main__ - Step 16328: {'lr': 0.0004885277922708352, 'samples': 3134976, 'steps': 16327, 'loss/train': 1.8478820323944092} 08/30/2021 16:11:14 - INFO - __main__ - Step 16329: {'lr': 0.0004885262030985504, 'samples': 3135168, 'steps': 16328, 'loss/train': 1.6181265115737915} 08/30/2021 16:11:15 - INFO - __main__ - Step 16330: {'lr': 0.0004885246138187896, 'samples': 3135360, 'steps': 16329, 'loss/train': 1.5884735584259033} 08/30/2021 16:11:15 - INFO - __main__ - Step 16331: {'lr': 0.0004885230244315531, 'samples': 3135552, 'steps': 16330, 'loss/train': 1.2228111028671265} 08/30/2021 16:11:15 - INFO - __main__ - Step 16332: {'lr': 0.0004885214349368419, 'samples': 3135744, 'steps': 16331, 'loss/train': 2.0802552700042725} 08/30/2021 16:11:16 - INFO - __main__ - Step 16333: {'lr': 0.0004885198453346565, 'samples': 3135936, 'steps': 16332, 'loss/train': 1.9758137464523315} 08/30/2021 16:11:18 - INFO - __main__ - Step 16334: {'lr': 0.0004885182556249978, 'samples': 3136128, 'steps': 16333, 'loss/train': 2.045431137084961} 08/30/2021 16:11:18 - INFO - __main__ - Step 16335: {'lr': 0.0004885166658078666, 'samples': 3136320, 'steps': 16334, 'loss/train': 1.4344342947006226} 08/30/2021 16:11:18 - INFO - __main__ - Step 16336: {'lr': 0.0004885150758832632, 'samples': 3136512, 'steps': 16335, 'loss/train': 1.4791133403778076} 08/30/2021 16:11:19 - INFO - __main__ - Step 16337: {'lr': 0.0004885134858511888, 'samples': 3136704, 'steps': 16336, 'loss/train': 1.6670126914978027} 08/30/2021 16:11:19 - INFO - __main__ - Step 16338: {'lr': 0.0004885118957116438, 'samples': 3136896, 'steps': 16337, 'loss/train': 1.0015093088150024} 08/30/2021 16:11:21 - INFO - __main__ - Step 16339: {'lr': 0.000488510305464629, 'samples': 3137088, 'steps': 16338, 'loss/train': 2.0380828380584717} 08/30/2021 16:11:21 - INFO - __main__ - Step 16340: {'lr': 0.0004885087151101453, 'samples': 3137280, 'steps': 16339, 'loss/train': 1.8990954160690308} 08/30/2021 16:11:21 - INFO - __main__ - Step 16341: {'lr': 0.0004885071246481931, 'samples': 3137472, 'steps': 16340, 'loss/train': 1.7942309379577637} 08/30/2021 16:11:22 - INFO - __main__ - Step 16342: {'lr': 0.0004885055340787733, 'samples': 3137664, 'steps': 16341, 'loss/train': 1.1840516328811646} 08/30/2021 16:11:22 - INFO - __main__ - Step 16343: {'lr': 0.0004885039434018866, 'samples': 3137856, 'steps': 16342, 'loss/train': 1.8106180429458618} 08/30/2021 16:11:24 - INFO - __main__ - Step 16344: {'lr': 0.0004885023526175337, 'samples': 3138048, 'steps': 16343, 'loss/train': 1.5840362310409546} 08/30/2021 16:11:24 - INFO - __main__ - Step 16345: {'lr': 0.0004885007617257154, 'samples': 3138240, 'steps': 16344, 'loss/train': 1.4874635934829712} 08/30/2021 16:11:25 - INFO - __main__ - Step 16346: {'lr': 0.0004884991707264322, 'samples': 3138432, 'steps': 16345, 'loss/train': 0.11009877920150757} 08/30/2021 16:11:25 - INFO - __main__ - Step 16347: {'lr': 0.000488497579619685, 'samples': 3138624, 'steps': 16346, 'loss/train': 1.738002061843872} 08/30/2021 16:11:25 - INFO - __main__ - Step 16348: {'lr': 0.0004884959884054745, 'samples': 3138816, 'steps': 16347, 'loss/train': 1.8687289953231812} 08/30/2021 16:11:26 - INFO - __main__ - Step 16349: {'lr': 0.0004884943970838014, 'samples': 3139008, 'steps': 16348, 'loss/train': 1.5455678701400757} 08/30/2021 16:11:27 - INFO - __main__ - Step 16350: {'lr': 0.0004884928056546663, 'samples': 3139200, 'steps': 16349, 'loss/train': 1.8006826639175415} 08/30/2021 16:11:28 - INFO - __main__ - Step 16351: {'lr': 0.0004884912141180701, 'samples': 3139392, 'steps': 16350, 'loss/train': 1.7931283712387085} 08/30/2021 16:11:28 - INFO - __main__ - Step 16352: {'lr': 0.0004884896224740136, 'samples': 3139584, 'steps': 16351, 'loss/train': 1.4437652826309204} 08/30/2021 16:11:28 - INFO - __main__ - Step 16353: {'lr': 0.0004884880307224972, 'samples': 3139776, 'steps': 16352, 'loss/train': 2.056745767593384} 08/30/2021 16:11:29 - INFO - __main__ - Step 16354: {'lr': 0.0004884864388635217, 'samples': 3139968, 'steps': 16353, 'loss/train': 1.7429823875427246} 08/30/2021 16:11:30 - INFO - __main__ - Step 16355: {'lr': 0.0004884848468970879, 'samples': 3140160, 'steps': 16354, 'loss/train': 1.7310128211975098} 08/30/2021 16:11:31 - INFO - __main__ - Step 16356: {'lr': 0.0004884832548231966, 'samples': 3140352, 'steps': 16355, 'loss/train': 1.6515498161315918} 08/30/2021 16:11:31 - INFO - __main__ - Step 16357: {'lr': 0.0004884816626418484, 'samples': 3140544, 'steps': 16356, 'loss/train': 1.6642929315567017} 08/30/2021 16:11:31 - INFO - __main__ - Step 16358: {'lr': 0.000488480070353044, 'samples': 3140736, 'steps': 16357, 'loss/train': 1.6606919765472412} 08/30/2021 16:11:32 - INFO - __main__ - Step 16359: {'lr': 0.0004884784779567843, 'samples': 3140928, 'steps': 16358, 'loss/train': 1.5081998109817505} 08/30/2021 16:11:34 - INFO - __main__ - Step 16360: {'lr': 0.0004884768854530696, 'samples': 3141120, 'steps': 16359, 'loss/train': 1.4753029346466064} 08/30/2021 16:11:34 - INFO - __main__ - Step 16361: {'lr': 0.0004884752928419012, 'samples': 3141312, 'steps': 16360, 'loss/train': 1.6934443712234497} 08/30/2021 16:11:35 - INFO - __main__ - Step 16362: {'lr': 0.0004884737001232793, 'samples': 3141504, 'steps': 16361, 'loss/train': 1.7826738357543945} 08/30/2021 16:11:35 - INFO - __main__ - Step 16363: {'lr': 0.000488472107297205, 'samples': 3141696, 'steps': 16362, 'loss/train': 0.815053403377533} 08/30/2021 16:11:35 - INFO - __main__ - Step 16364: {'lr': 0.0004884705143636788, 'samples': 3141888, 'steps': 16363, 'loss/train': 1.4334876537322998} 08/30/2021 16:11:36 - INFO - __main__ - Step 16365: {'lr': 0.0004884689213227013, 'samples': 3142080, 'steps': 16364, 'loss/train': 1.7051260471343994} 08/30/2021 16:11:36 - INFO - __main__ - Step 16366: {'lr': 0.0004884673281742736, 'samples': 3142272, 'steps': 16365, 'loss/train': 0.10288375616073608} 08/30/2021 16:11:38 - INFO - __main__ - Step 16367: {'lr': 0.0004884657349183961, 'samples': 3142464, 'steps': 16366, 'loss/train': 0.10311628878116608} 08/30/2021 16:11:38 - INFO - __main__ - Step 16368: {'lr': 0.0004884641415550696, 'samples': 3142656, 'steps': 16367, 'loss/train': 1.4080204963684082} 08/30/2021 16:11:38 - INFO - __main__ - Step 16369: {'lr': 0.0004884625480842949, 'samples': 3142848, 'steps': 16368, 'loss/train': 1.8912681341171265} 08/30/2021 16:11:39 - INFO - __main__ - Step 16370: {'lr': 0.0004884609545060726, 'samples': 3143040, 'steps': 16369, 'loss/train': 1.391222596168518} 08/30/2021 16:11:39 - INFO - __main__ - Step 16371: {'lr': 0.0004884593608204035, 'samples': 3143232, 'steps': 16370, 'loss/train': 1.6049600839614868} 08/30/2021 16:11:41 - INFO - __main__ - Step 16372: {'lr': 0.0004884577670272882, 'samples': 3143424, 'steps': 16371, 'loss/train': 1.399133563041687} 08/30/2021 16:11:41 - INFO - __main__ - Step 16373: {'lr': 0.0004884561731267278, 'samples': 3143616, 'steps': 16372, 'loss/train': 1.9584330320358276} 08/30/2021 16:11:41 - INFO - __main__ - Step 16374: {'lr': 0.0004884545791187224, 'samples': 3143808, 'steps': 16373, 'loss/train': 1.2325204610824585} 08/30/2021 16:11:42 - INFO - __main__ - Step 16375: {'lr': 0.0004884529850032732, 'samples': 3144000, 'steps': 16374, 'loss/train': 1.823428988456726} 08/30/2021 16:11:42 - INFO - __main__ - Step 16376: {'lr': 0.0004884513907803808, 'samples': 3144192, 'steps': 16375, 'loss/train': 2.0254604816436768} 08/30/2021 16:11:44 - INFO - __main__ - Step 16377: {'lr': 0.0004884497964500457, 'samples': 3144384, 'steps': 16376, 'loss/train': 1.838220238685608} 08/30/2021 16:11:44 - INFO - __main__ - Step 16378: {'lr': 0.000488448202012269, 'samples': 3144576, 'steps': 16377, 'loss/train': 1.714113473892212} 08/30/2021 16:11:45 - INFO - __main__ - Step 16379: {'lr': 0.0004884466074670512, 'samples': 3144768, 'steps': 16378, 'loss/train': 1.836683988571167} 08/30/2021 16:11:45 - INFO - __main__ - Step 16380: {'lr': 0.0004884450128143929, 'samples': 3144960, 'steps': 16379, 'loss/train': 1.4216639995574951} 08/30/2021 16:11:45 - INFO - __main__ - Step 16381: {'lr': 0.000488443418054295, 'samples': 3145152, 'steps': 16380, 'loss/train': 1.983205795288086} 08/30/2021 16:11:47 - INFO - __main__ - Step 16382: {'lr': 0.0004884418231867583, 'samples': 3145344, 'steps': 16381, 'loss/train': 1.8755842447280884} 08/30/2021 16:11:48 - INFO - __main__ - Step 16383: {'lr': 0.0004884402282117833, 'samples': 3145536, 'steps': 16382, 'loss/train': 1.6494497060775757} 08/30/2021 16:11:48 - INFO - __main__ - Step 16384: {'lr': 0.0004884386331293708, 'samples': 3145728, 'steps': 16383, 'loss/train': 0.07024643570184708} 08/30/2021 16:11:49 - INFO - __main__ - Step 16385: {'lr': 0.0004884370379395215, 'samples': 3145920, 'steps': 16384, 'loss/train': 1.9015545845031738} 08/30/2021 16:11:49 - INFO - __main__ - Step 16386: {'lr': 0.0004884354426422363, 'samples': 3146112, 'steps': 16385, 'loss/train': 0.16112719476222992} 08/30/2021 16:11:49 - INFO - __main__ - Step 16387: {'lr': 0.0004884338472375156, 'samples': 3146304, 'steps': 16386, 'loss/train': 1.2409710884094238} 08/30/2021 16:11:51 - INFO - __main__ - Step 16388: {'lr': 0.0004884322517253604, 'samples': 3146496, 'steps': 16387, 'loss/train': 1.0356227159500122} 08/30/2021 16:11:51 - INFO - __main__ - Step 16389: {'lr': 0.0004884306561057713, 'samples': 3146688, 'steps': 16388, 'loss/train': 1.4719094038009644} 08/30/2021 16:11:52 - INFO - __main__ - Step 16390: {'lr': 0.000488429060378749, 'samples': 3146880, 'steps': 16389, 'loss/train': 1.825208306312561} 08/30/2021 16:11:52 - INFO - __main__ - Step 16391: {'lr': 0.0004884274645442942, 'samples': 3147072, 'steps': 16390, 'loss/train': 1.7455666065216064} 08/30/2021 16:11:52 - INFO - __main__ - Step 16392: {'lr': 0.0004884258686024077, 'samples': 3147264, 'steps': 16391, 'loss/train': 1.788954734802246} 08/30/2021 16:11:54 - INFO - __main__ - Step 16393: {'lr': 0.0004884242725530902, 'samples': 3147456, 'steps': 16392, 'loss/train': 1.6024516820907593} 08/30/2021 16:11:54 - INFO - __main__ - Step 16394: {'lr': 0.0004884226763963423, 'samples': 3147648, 'steps': 16393, 'loss/train': 1.8891571760177612} 08/30/2021 16:11:55 - INFO - __main__ - Step 16395: {'lr': 0.000488421080132165, 'samples': 3147840, 'steps': 16394, 'loss/train': 1.7516354322433472} 08/30/2021 16:11:55 - INFO - __main__ - Step 16396: {'lr': 0.0004884194837605587, 'samples': 3148032, 'steps': 16395, 'loss/train': 1.6981509923934937} 08/30/2021 16:11:55 - INFO - __main__ - Step 16397: {'lr': 0.0004884178872815243, 'samples': 3148224, 'steps': 16396, 'loss/train': 1.2616357803344727} 08/30/2021 16:11:57 - INFO - __main__ - Step 16398: {'lr': 0.0004884162906950624, 'samples': 3148416, 'steps': 16397, 'loss/train': 0.14406365156173706} 08/30/2021 16:11:58 - INFO - __main__ - Step 16399: {'lr': 0.000488414694001174, 'samples': 3148608, 'steps': 16398, 'loss/train': 2.0568366050720215} 08/30/2021 16:11:58 - INFO - __main__ - Step 16400: {'lr': 0.0004884130971998595, 'samples': 3148800, 'steps': 16399, 'loss/train': 2.191758871078491} 08/30/2021 16:11:58 - INFO - __main__ - Step 16401: {'lr': 0.0004884115002911197, 'samples': 3148992, 'steps': 16400, 'loss/train': 1.3861243724822998} 08/30/2021 16:11:59 - INFO - __main__ - Step 16402: {'lr': 0.0004884099032749554, 'samples': 3149184, 'steps': 16401, 'loss/train': 0.0903669074177742} 08/30/2021 16:12:00 - INFO - __main__ - Step 16403: {'lr': 0.0004884083061513672, 'samples': 3149376, 'steps': 16402, 'loss/train': 2.5146679878234863} 08/30/2021 16:12:00 - INFO - __main__ - Step 16404: {'lr': 0.0004884067089203559, 'samples': 3149568, 'steps': 16403, 'loss/train': 1.8538411855697632} 08/30/2021 16:12:01 - INFO - __main__ - Step 16405: {'lr': 0.0004884051115819224, 'samples': 3149760, 'steps': 16404, 'loss/train': 2.032058000564575} 08/30/2021 16:12:01 - INFO - __main__ - Step 16406: {'lr': 0.000488403514136067, 'samples': 3149952, 'steps': 16405, 'loss/train': 1.4845865964889526} 08/30/2021 16:12:01 - INFO - __main__ - Step 16407: {'lr': 0.0004884019165827909, 'samples': 3150144, 'steps': 16406, 'loss/train': 1.7833247184753418} 08/30/2021 16:12:03 - INFO - __main__ - Step 16408: {'lr': 0.0004884003189220945, 'samples': 3150336, 'steps': 16407, 'loss/train': 1.4036445617675781} 08/30/2021 16:12:03 - INFO - __main__ - Step 16409: {'lr': 0.0004883987211539785, 'samples': 3150528, 'steps': 16408, 'loss/train': 2.021967649459839} 08/30/2021 16:12:04 - INFO - __main__ - Step 16410: {'lr': 0.0004883971232784438, 'samples': 3150720, 'steps': 16409, 'loss/train': 1.841018557548523} 08/30/2021 16:12:04 - INFO - __main__ - Step 16411: {'lr': 0.0004883955252954909, 'samples': 3150912, 'steps': 16410, 'loss/train': 2.0723958015441895} 08/30/2021 16:12:04 - INFO - __main__ - Step 16412: {'lr': 0.0004883939272051208, 'samples': 3151104, 'steps': 16411, 'loss/train': 1.7425384521484375} 08/30/2021 16:12:05 - INFO - __main__ - Step 16413: {'lr': 0.000488392329007334, 'samples': 3151296, 'steps': 16412, 'loss/train': 1.697700023651123} 08/30/2021 16:12:07 - INFO - __main__ - Step 16414: {'lr': 0.0004883907307021314, 'samples': 3151488, 'steps': 16413, 'loss/train': 2.5796310901641846} 08/30/2021 16:12:07 - INFO - __main__ - Step 16415: {'lr': 0.0004883891322895134, 'samples': 3151680, 'steps': 16414, 'loss/train': 2.1869726181030273} 08/30/2021 16:12:07 - INFO - __main__ - Step 16416: {'lr': 0.000488387533769481, 'samples': 3151872, 'steps': 16415, 'loss/train': 1.569940209388733} 08/30/2021 16:12:08 - INFO - __main__ - Step 16417: {'lr': 0.000488385935142035, 'samples': 3152064, 'steps': 16416, 'loss/train': 1.4833344221115112} 08/30/2021 16:12:08 - INFO - __main__ - Step 16418: {'lr': 0.0004883843364071759, 'samples': 3152256, 'steps': 16417, 'loss/train': 1.2835125923156738} 08/30/2021 16:12:09 - INFO - __main__ - Step 16419: {'lr': 0.0004883827375649045, 'samples': 3152448, 'steps': 16418, 'loss/train': 1.0750722885131836} 08/30/2021 16:12:10 - INFO - __main__ - Step 16420: {'lr': 0.0004883811386152216, 'samples': 3152640, 'steps': 16419, 'loss/train': 1.722716212272644} 08/30/2021 16:12:10 - INFO - __main__ - Step 16421: {'lr': 0.0004883795395581277, 'samples': 3152832, 'steps': 16420, 'loss/train': 0.47888919711112976} 08/30/2021 16:12:11 - INFO - __main__ - Step 16422: {'lr': 0.0004883779403936237, 'samples': 3153024, 'steps': 16421, 'loss/train': 1.4829291105270386} 08/30/2021 16:12:11 - INFO - __main__ - Step 16423: {'lr': 0.0004883763411217103, 'samples': 3153216, 'steps': 16422, 'loss/train': 1.7919137477874756} 08/30/2021 16:12:12 - INFO - __main__ - Step 16424: {'lr': 0.0004883747417423882, 'samples': 3153408, 'steps': 16423, 'loss/train': 1.6080315113067627} 08/30/2021 16:12:13 - INFO - __main__ - Step 16425: {'lr': 0.000488373142255658, 'samples': 3153600, 'steps': 16424, 'loss/train': 1.644591212272644} 08/30/2021 16:12:13 - INFO - __main__ - Step 16426: {'lr': 0.0004883715426615207, 'samples': 3153792, 'steps': 16425, 'loss/train': 1.6483370065689087} 08/30/2021 16:12:14 - INFO - __main__ - Step 16427: {'lr': 0.0004883699429599768, 'samples': 3153984, 'steps': 16426, 'loss/train': 1.8033820390701294} 08/30/2021 16:12:14 - INFO - __main__ - Step 16428: {'lr': 0.0004883683431510272, 'samples': 3154176, 'steps': 16427, 'loss/train': 1.4099290370941162} 08/30/2021 16:12:16 - INFO - __main__ - Step 16429: {'lr': 0.0004883667432346723, 'samples': 3154368, 'steps': 16428, 'loss/train': 0.9474764466285706} 08/30/2021 16:12:16 - INFO - __main__ - Step 16430: {'lr': 0.0004883651432109132, 'samples': 3154560, 'steps': 16429, 'loss/train': 2.8283019065856934} 08/30/2021 16:12:17 - INFO - __main__ - Step 16431: {'lr': 0.0004883635430797502, 'samples': 3154752, 'steps': 16430, 'loss/train': 2.3652114868164062} 08/30/2021 16:12:17 - INFO - __main__ - Step 16432: {'lr': 0.0004883619428411846, 'samples': 3154944, 'steps': 16431, 'loss/train': 1.80955171585083} 08/30/2021 16:12:17 - INFO - __main__ - Step 16433: {'lr': 0.0004883603424952165, 'samples': 3155136, 'steps': 16432, 'loss/train': 1.612752914428711} 08/30/2021 16:12:19 - INFO - __main__ - Step 16434: {'lr': 0.0004883587420418471, 'samples': 3155328, 'steps': 16433, 'loss/train': 1.9555912017822266} 08/30/2021 16:12:20 - INFO - __main__ - Step 16435: {'lr': 0.0004883571414810769, 'samples': 3155520, 'steps': 16434, 'loss/train': 1.5818567276000977} 08/30/2021 16:12:20 - INFO - __main__ - Step 16436: {'lr': 0.0004883555408129066, 'samples': 3155712, 'steps': 16435, 'loss/train': 1.2745782136917114} 08/30/2021 16:12:20 - INFO - __main__ - Step 16437: {'lr': 0.0004883539400373369, 'samples': 3155904, 'steps': 16436, 'loss/train': 1.8561028242111206} 08/30/2021 16:12:21 - INFO - __main__ - Step 16438: {'lr': 0.0004883523391543687, 'samples': 3156096, 'steps': 16437, 'loss/train': 1.5114132165908813} 08/30/2021 16:12:22 - INFO - __main__ - Step 16439: {'lr': 0.0004883507381640026, 'samples': 3156288, 'steps': 16438, 'loss/train': 1.323274850845337} 08/30/2021 16:12:23 - INFO - __main__ - Step 16440: {'lr': 0.0004883491370662393, 'samples': 3156480, 'steps': 16439, 'loss/train': 0.6661016941070557} 08/30/2021 16:12:23 - INFO - __main__ - Step 16441: {'lr': 0.0004883475358610794, 'samples': 3156672, 'steps': 16440, 'loss/train': 1.3470076322555542} 08/30/2021 16:12:24 - INFO - __main__ - Step 16442: {'lr': 0.000488345934548524, 'samples': 3156864, 'steps': 16441, 'loss/train': 1.2103748321533203} 08/30/2021 16:12:24 - INFO - __main__ - Step 16443: {'lr': 0.0004883443331285736, 'samples': 3157056, 'steps': 16442, 'loss/train': 1.5097126960754395} 08/30/2021 16:12:24 - INFO - __main__ - Step 16444: {'lr': 0.0004883427316012289, 'samples': 3157248, 'steps': 16443, 'loss/train': 1.5376880168914795} 08/30/2021 16:12:26 - INFO - __main__ - Step 16445: {'lr': 0.0004883411299664906, 'samples': 3157440, 'steps': 16444, 'loss/train': 3.0078248977661133} 08/30/2021 16:12:27 - INFO - __main__ - Step 16446: {'lr': 0.0004883395282243595, 'samples': 3157632, 'steps': 16445, 'loss/train': 0.14940780401229858} 08/30/2021 16:12:27 - INFO - __main__ - Step 16447: {'lr': 0.0004883379263748363, 'samples': 3157824, 'steps': 16446, 'loss/train': 2.0638163089752197} 08/30/2021 16:12:27 - INFO - __main__ - Step 16448: {'lr': 0.0004883363244179217, 'samples': 3158016, 'steps': 16447, 'loss/train': 1.5818711519241333} 08/30/2021 16:12:28 - INFO - __main__ - Step 16449: {'lr': 0.0004883347223536164, 'samples': 3158208, 'steps': 16448, 'loss/train': 1.8282077312469482} 08/30/2021 16:12:28 - INFO - __main__ - Step 16450: {'lr': 0.0004883331201819211, 'samples': 3158400, 'steps': 16449, 'loss/train': 0.11230821907520294} 08/30/2021 16:12:30 - INFO - __main__ - Step 16451: {'lr': 0.0004883315179028366, 'samples': 3158592, 'steps': 16450, 'loss/train': 0.17662116885185242} 08/30/2021 16:12:30 - INFO - __main__ - Step 16452: {'lr': 0.0004883299155163636, 'samples': 3158784, 'steps': 16451, 'loss/train': 1.5383926630020142} 08/30/2021 16:12:30 - INFO - __main__ - Step 16453: {'lr': 0.0004883283130225029, 'samples': 3158976, 'steps': 16452, 'loss/train': 2.2520840167999268} 08/30/2021 16:12:31 - INFO - __main__ - Step 16454: {'lr': 0.0004883267104212551, 'samples': 3159168, 'steps': 16453, 'loss/train': 0.7508336901664734} 08/30/2021 16:12:31 - INFO - __main__ - Step 16455: {'lr': 0.0004883251077126209, 'samples': 3159360, 'steps': 16454, 'loss/train': 2.7111029624938965} 08/30/2021 16:12:31 - INFO - __main__ - Step 16456: {'lr': 0.0004883235048966011, 'samples': 3159552, 'steps': 16455, 'loss/train': 1.7357203960418701} 08/30/2021 16:12:33 - INFO - __main__ - Step 16457: {'lr': 0.0004883219019731964, 'samples': 3159744, 'steps': 16456, 'loss/train': 2.1748054027557373} 08/30/2021 16:12:34 - INFO - __main__ - Step 16458: {'lr': 0.0004883202989424076, 'samples': 3159936, 'steps': 16457, 'loss/train': 1.9947377443313599} 08/30/2021 16:12:34 - INFO - __main__ - Step 16459: {'lr': 0.0004883186958042354, 'samples': 3160128, 'steps': 16458, 'loss/train': 0.9799297451972961} 08/30/2021 16:12:34 - INFO - __main__ - Step 16460: {'lr': 0.0004883170925586804, 'samples': 3160320, 'steps': 16459, 'loss/train': 1.2041651010513306} 08/30/2021 16:12:35 - INFO - __main__ - Step 16461: {'lr': 0.0004883154892057433, 'samples': 3160512, 'steps': 16460, 'loss/train': 1.4210397005081177} 08/30/2021 16:12:36 - INFO - __main__ - Step 16462: {'lr': 0.000488313885745425, 'samples': 3160704, 'steps': 16461, 'loss/train': 1.7475907802581787} 08/30/2021 16:12:37 - INFO - __main__ - Step 16463: {'lr': 0.0004883122821777261, 'samples': 3160896, 'steps': 16462, 'loss/train': 1.7158664464950562} 08/30/2021 16:12:37 - INFO - __main__ - Step 16464: {'lr': 0.0004883106785026475, 'samples': 3161088, 'steps': 16463, 'loss/train': 1.3037594556808472} 08/30/2021 16:12:37 - INFO - __main__ - Step 16465: {'lr': 0.0004883090747201897, 'samples': 3161280, 'steps': 16464, 'loss/train': 1.3759013414382935} 08/30/2021 16:12:38 - INFO - __main__ - Step 16466: {'lr': 0.0004883074708303534, 'samples': 3161472, 'steps': 16465, 'loss/train': 1.0900455713272095} 08/30/2021 16:12:39 - INFO - __main__ - Step 16467: {'lr': 0.0004883058668331396, 'samples': 3161664, 'steps': 16466, 'loss/train': 1.6898516416549683} 08/30/2021 16:12:40 - INFO - __main__ - Step 16468: {'lr': 0.0004883042627285488, 'samples': 3161856, 'steps': 16467, 'loss/train': 1.8191605806350708} 08/30/2021 16:12:40 - INFO - __main__ - Step 16469: {'lr': 0.0004883026585165817, 'samples': 3162048, 'steps': 16468, 'loss/train': 1.6544195413589478} 08/30/2021 16:12:41 - INFO - __main__ - Step 16470: {'lr': 0.0004883010541972392, 'samples': 3162240, 'steps': 16469, 'loss/train': 1.6518362760543823} 08/30/2021 16:12:41 - INFO - __main__ - Step 16471: {'lr': 0.0004882994497705219, 'samples': 3162432, 'steps': 16470, 'loss/train': 2.0174849033355713} 08/30/2021 16:12:42 - INFO - __main__ - Step 16472: {'lr': 0.0004882978452364305, 'samples': 3162624, 'steps': 16471, 'loss/train': 1.4940745830535889} 08/30/2021 16:12:43 - INFO - __main__ - Step 16473: {'lr': 0.0004882962405949658, 'samples': 3162816, 'steps': 16472, 'loss/train': 1.7469748258590698} 08/30/2021 16:12:43 - INFO - __main__ - Step 16474: {'lr': 0.0004882946358461285, 'samples': 3163008, 'steps': 16473, 'loss/train': 1.8230326175689697} 08/30/2021 16:12:44 - INFO - __main__ - Step 16475: {'lr': 0.0004882930309899192, 'samples': 3163200, 'steps': 16474, 'loss/train': 1.4943701028823853} 08/30/2021 16:12:44 - INFO - __main__ - Step 16476: {'lr': 0.000488291426026339, 'samples': 3163392, 'steps': 16475, 'loss/train': 1.4653288125991821} 08/30/2021 16:12:44 - INFO - __main__ - Step 16477: {'lr': 0.0004882898209553881, 'samples': 3163584, 'steps': 16476, 'loss/train': 1.550358533859253} 08/30/2021 16:12:46 - INFO - __main__ - Step 16478: {'lr': 0.0004882882157770676, 'samples': 3163776, 'steps': 16477, 'loss/train': 1.679360270500183} 08/30/2021 16:12:47 - INFO - __main__ - Step 16479: {'lr': 0.000488286610491378, 'samples': 3163968, 'steps': 16478, 'loss/train': 1.8442274332046509} 08/30/2021 16:12:47 - INFO - __main__ - Step 16480: {'lr': 0.0004882850050983203, 'samples': 3164160, 'steps': 16479, 'loss/train': 1.6017777919769287} 08/30/2021 16:12:47 - INFO - __main__ - Step 16481: {'lr': 0.0004882833995978949, 'samples': 3164352, 'steps': 16480, 'loss/train': 1.884262204170227} 08/30/2021 16:12:48 - INFO - __main__ - Step 16482: {'lr': 0.0004882817939901027, 'samples': 3164544, 'steps': 16481, 'loss/train': 0.0743497759103775} 08/30/2021 16:12:48 - INFO - __main__ - Step 16483: {'lr': 0.0004882801882749445, 'samples': 3164736, 'steps': 16482, 'loss/train': 0.18168054521083832} 08/30/2021 16:12:50 - INFO - __main__ - Step 16484: {'lr': 0.0004882785824524209, 'samples': 3164928, 'steps': 16483, 'loss/train': 1.5538021326065063} 08/30/2021 16:12:50 - INFO - __main__ - Step 16485: {'lr': 0.0004882769765225326, 'samples': 3165120, 'steps': 16484, 'loss/train': 2.0989391803741455} 08/30/2021 16:12:50 - INFO - __main__ - Step 16486: {'lr': 0.00048827537048528035, 'samples': 3165312, 'steps': 16485, 'loss/train': 1.651032567024231} 08/30/2021 16:12:51 - INFO - __main__ - Step 16487: {'lr': 0.00048827376434066493, 'samples': 3165504, 'steps': 16486, 'loss/train': 1.2024333477020264} 08/30/2021 16:12:51 - INFO - __main__ - Step 16488: {'lr': 0.0004882721580886871, 'samples': 3165696, 'steps': 16487, 'loss/train': 1.6652101278305054} 08/30/2021 16:12:53 - INFO - __main__ - Step 16489: {'lr': 0.00048827055172934744, 'samples': 3165888, 'steps': 16488, 'loss/train': 1.4172935485839844} 08/30/2021 16:12:54 - INFO - __main__ - Step 16490: {'lr': 0.0004882689452626468, 'samples': 3166080, 'steps': 16489, 'loss/train': 1.1986442804336548} 08/30/2021 16:12:54 - INFO - __main__ - Step 16491: {'lr': 0.00048826733868858577, 'samples': 3166272, 'steps': 16490, 'loss/train': 1.8039789199829102} 08/30/2021 16:12:55 - INFO - __main__ - Step 16492: {'lr': 0.00048826573200716516, 'samples': 3166464, 'steps': 16491, 'loss/train': 1.7548322677612305} 08/30/2021 16:12:55 - INFO - __main__ - Step 16493: {'lr': 0.0004882641252183857, 'samples': 3166656, 'steps': 16492, 'loss/train': 1.9020053148269653} 08/30/2021 16:12:55 - INFO - __main__ - Step 16494: {'lr': 0.0004882625183222481, 'samples': 3166848, 'steps': 16493, 'loss/train': 1.7261946201324463} 08/30/2021 16:12:57 - INFO - __main__ - Step 16495: {'lr': 0.00048826091131875317, 'samples': 3167040, 'steps': 16494, 'loss/train': 1.968366265296936} 08/30/2021 16:12:57 - INFO - __main__ - Step 16496: {'lr': 0.00048825930420790144, 'samples': 3167232, 'steps': 16495, 'loss/train': 1.53008234500885} 08/30/2021 16:12:58 - INFO - __main__ - Step 16497: {'lr': 0.0004882576969896938, 'samples': 3167424, 'steps': 16496, 'loss/train': 1.7781314849853516} 08/30/2021 16:12:58 - INFO - __main__ - Step 16498: {'lr': 0.00048825608966413095, 'samples': 3167616, 'steps': 16497, 'loss/train': 1.7661806344985962} 08/30/2021 16:12:58 - INFO - __main__ - Step 16499: {'lr': 0.0004882544822312135, 'samples': 3167808, 'steps': 16498, 'loss/train': 1.7144266366958618} 08/30/2021 16:13:00 - INFO - __main__ - Step 16500: {'lr': 0.00048825287469094224, 'samples': 3168000, 'steps': 16499, 'loss/train': 2.3831145763397217} 08/30/2021 16:13:00 - INFO - __main__ - Step 16501: {'lr': 0.000488251267043318, 'samples': 3168192, 'steps': 16500, 'loss/train': 1.950164794921875} 08/30/2021 16:13:01 - INFO - __main__ - Step 16502: {'lr': 0.00048824965928834143, 'samples': 3168384, 'steps': 16501, 'loss/train': 1.650948405265808} 08/30/2021 16:13:01 - INFO - __main__ - Step 16503: {'lr': 0.0004882480514260131, 'samples': 3168576, 'steps': 16502, 'loss/train': 1.506259560585022} 08/30/2021 16:13:01 - INFO - __main__ - Step 16504: {'lr': 0.000488246443456334, 'samples': 3168768, 'steps': 16503, 'loss/train': 0.11784862726926804} 08/30/2021 16:13:03 - INFO - __main__ - Step 16505: {'lr': 0.0004882448353793048, 'samples': 3168960, 'steps': 16504, 'loss/train': 2.259474039077759} 08/30/2021 16:13:03 - INFO - __main__ - Step 16506: {'lr': 0.000488243227194926, 'samples': 3169152, 'steps': 16505, 'loss/train': 1.8807767629623413} 08/30/2021 16:13:04 - INFO - __main__ - Step 16507: {'lr': 0.00048824161890319854, 'samples': 3169344, 'steps': 16506, 'loss/train': 1.8212604522705078} 08/30/2021 16:13:04 - INFO - __main__ - Step 16508: {'lr': 0.00048824001050412304, 'samples': 3169536, 'steps': 16507, 'loss/train': 1.6447376012802124} 08/30/2021 16:13:04 - INFO - __main__ - Step 16509: {'lr': 0.0004882384019977003, 'samples': 3169728, 'steps': 16508, 'loss/train': 1.7541759014129639} 08/30/2021 16:13:06 - INFO - __main__ - Step 16510: {'lr': 0.000488236793383931, 'samples': 3169920, 'steps': 16509, 'loss/train': 1.5085219144821167} 08/30/2021 16:13:07 - INFO - __main__ - Step 16511: {'lr': 0.00048823518466281586, 'samples': 3170112, 'steps': 16510, 'loss/train': 1.641247034072876} 08/30/2021 16:13:07 - INFO - __main__ - Step 16512: {'lr': 0.0004882335758343557, 'samples': 3170304, 'steps': 16511, 'loss/train': 1.3721646070480347} 08/30/2021 16:13:07 - INFO - __main__ - Step 16513: {'lr': 0.0004882319668985511, 'samples': 3170496, 'steps': 16512, 'loss/train': 0.09264480322599411} 08/30/2021 16:13:08 - INFO - __main__ - Step 16514: {'lr': 0.00048823035785540284, 'samples': 3170688, 'steps': 16513, 'loss/train': 1.4933146238327026} 08/30/2021 16:13:09 - INFO - __main__ - Step 16515: {'lr': 0.0004882287487049117, 'samples': 3170880, 'steps': 16514, 'loss/train': 2.5302674770355225} 08/30/2021 16:13:10 - INFO - __main__ - Step 16516: {'lr': 0.00048822713944707833, 'samples': 3171072, 'steps': 16515, 'loss/train': 1.7074077129364014} 08/30/2021 16:13:10 - INFO - __main__ - Step 16517: {'lr': 0.0004882255300819035, 'samples': 3171264, 'steps': 16516, 'loss/train': 2.1281604766845703} 08/30/2021 16:13:10 - INFO - __main__ - Step 16518: {'lr': 0.0004882239206093879, 'samples': 3171456, 'steps': 16517, 'loss/train': 0.7898990511894226} 08/30/2021 16:13:11 - INFO - __main__ - Step 16519: {'lr': 0.0004882223110295323, 'samples': 3171648, 'steps': 16518, 'loss/train': 1.6536293029785156} 08/30/2021 16:13:12 - INFO - __main__ - Step 16520: {'lr': 0.00048822070134233743, 'samples': 3171840, 'steps': 16519, 'loss/train': 2.1504950523376465} 08/30/2021 16:13:13 - INFO - __main__ - Step 16521: {'lr': 0.000488219091547804, 'samples': 3172032, 'steps': 16520, 'loss/train': 1.400365948677063} 08/30/2021 16:13:13 - INFO - __main__ - Step 16522: {'lr': 0.0004882174816459326, 'samples': 3172224, 'steps': 16521, 'loss/train': 2.339890480041504} 08/30/2021 16:13:13 - INFO - __main__ - Step 16523: {'lr': 0.0004882158716367242, 'samples': 3172416, 'steps': 16522, 'loss/train': 1.9823507070541382} 08/30/2021 16:13:14 - INFO - __main__ - Step 16524: {'lr': 0.0004882142615201793, 'samples': 3172608, 'steps': 16523, 'loss/train': 1.4485024213790894} 08/30/2021 16:13:14 - INFO - __main__ - Step 16525: {'lr': 0.00048821265129629887, 'samples': 3172800, 'steps': 16524, 'loss/train': 1.3576749563217163} 08/30/2021 16:13:16 - INFO - __main__ - Step 16526: {'lr': 0.0004882110409650834, 'samples': 3172992, 'steps': 16525, 'loss/train': 1.6916894912719727} 08/30/2021 16:13:16 - INFO - __main__ - Step 16527: {'lr': 0.0004882094305265338, 'samples': 3173184, 'steps': 16526, 'loss/train': 1.6859670877456665} 08/30/2021 16:13:16 - INFO - __main__ - Step 16528: {'lr': 0.00048820781998065054, 'samples': 3173376, 'steps': 16527, 'loss/train': 1.3498218059539795} 08/30/2021 16:13:17 - INFO - __main__ - Step 16529: {'lr': 0.00048820620932743465, 'samples': 3173568, 'steps': 16528, 'loss/train': 1.842890977859497} 08/30/2021 16:13:17 - INFO - __main__ - Step 16530: {'lr': 0.0004882045985668867, 'samples': 3173760, 'steps': 16529, 'loss/train': 1.518268346786499} 08/30/2021 16:13:18 - INFO - __main__ - Step 16531: {'lr': 0.0004882029876990074, 'samples': 3173952, 'steps': 16530, 'loss/train': 2.1686899662017822} 08/30/2021 16:13:19 - INFO - __main__ - Step 16532: {'lr': 0.0004882013767237975, 'samples': 3174144, 'steps': 16531, 'loss/train': 1.8740262985229492} 08/30/2021 16:13:19 - INFO - __main__ - Step 16533: {'lr': 0.0004881997656412578, 'samples': 3174336, 'steps': 16532, 'loss/train': 1.9127898216247559} 08/30/2021 16:13:20 - INFO - __main__ - Step 16534: {'lr': 0.0004881981544513889, 'samples': 3174528, 'steps': 16533, 'loss/train': 1.4909237623214722} 08/30/2021 16:13:20 - INFO - __main__ - Step 16535: {'lr': 0.0004881965431541916, 'samples': 3174720, 'steps': 16534, 'loss/train': 1.2026665210723877} 08/30/2021 16:13:21 - INFO - __main__ - Step 16536: {'lr': 0.0004881949317496667, 'samples': 3174912, 'steps': 16535, 'loss/train': 1.699640154838562} 08/30/2021 16:13:22 - INFO - __main__ - Step 16537: {'lr': 0.0004881933202378147, 'samples': 3175104, 'steps': 16536, 'loss/train': 1.465736746788025} 08/30/2021 16:13:22 - INFO - __main__ - Step 16538: {'lr': 0.0004881917086186365, 'samples': 3175296, 'steps': 16537, 'loss/train': 2.144170045852661} 08/30/2021 16:13:23 - INFO - __main__ - Step 16539: {'lr': 0.0004881900968921328, 'samples': 3175488, 'steps': 16538, 'loss/train': 1.691697597503662} 08/30/2021 16:13:23 - INFO - __main__ - Step 16540: {'lr': 0.00048818848505830436, 'samples': 3175680, 'steps': 16539, 'loss/train': 1.9390833377838135} 08/30/2021 16:13:24 - INFO - __main__ - Step 16541: {'lr': 0.0004881868731171518, 'samples': 3175872, 'steps': 16540, 'loss/train': 1.9974125623703003} 08/30/2021 16:13:25 - INFO - __main__ - Step 16542: {'lr': 0.000488185261068676, 'samples': 3176064, 'steps': 16541, 'loss/train': 2.561133623123169} 08/30/2021 16:13:25 - INFO - __main__ - Step 16543: {'lr': 0.0004881836489128776, 'samples': 3176256, 'steps': 16542, 'loss/train': 1.8090492486953735} 08/30/2021 16:13:26 - INFO - __main__ - Step 16544: {'lr': 0.00048818203664975727, 'samples': 3176448, 'steps': 16543, 'loss/train': 1.488569736480713} 08/30/2021 16:13:26 - INFO - __main__ - Step 16545: {'lr': 0.00048818042427931573, 'samples': 3176640, 'steps': 16544, 'loss/train': 1.1984081268310547} 08/30/2021 16:13:28 - INFO - __main__ - Step 16546: {'lr': 0.00048817881180155385, 'samples': 3176832, 'steps': 16545, 'loss/train': 1.8053693771362305} 08/30/2021 16:13:29 - INFO - __main__ - Step 16547: {'lr': 0.0004881771992164722, 'samples': 3177024, 'steps': 16546, 'loss/train': 1.8906036615371704} 08/30/2021 16:13:29 - INFO - __main__ - Step 16548: {'lr': 0.0004881755865240717, 'samples': 3177216, 'steps': 16547, 'loss/train': 1.862004280090332} 08/30/2021 16:13:29 - INFO - __main__ - Step 16549: {'lr': 0.0004881739737243528, 'samples': 3177408, 'steps': 16548, 'loss/train': 1.5678037405014038} 08/30/2021 16:13:30 - INFO - __main__ - Step 16550: {'lr': 0.00048817236081731655, 'samples': 3177600, 'steps': 16549, 'loss/train': 1.2787948846817017} 08/30/2021 16:13:30 - INFO - __main__ - Step 16551: {'lr': 0.0004881707478029634, 'samples': 3177792, 'steps': 16550, 'loss/train': 1.0139423608779907} 08/30/2021 16:13:32 - INFO - __main__ - Step 16552: {'lr': 0.0004881691346812942, 'samples': 3177984, 'steps': 16551, 'loss/train': 1.6228530406951904} 08/30/2021 16:13:32 - INFO - __main__ - Step 16553: {'lr': 0.0004881675214523097, 'samples': 3178176, 'steps': 16552, 'loss/train': 1.7885985374450684} 08/30/2021 16:13:33 - INFO - __main__ - Step 16554: {'lr': 0.00048816590811601054, 'samples': 3178368, 'steps': 16553, 'loss/train': 1.4082645177841187} 08/30/2021 16:13:33 - INFO - __main__ - Step 16555: {'lr': 0.0004881642946723975, 'samples': 3178560, 'steps': 16554, 'loss/train': 0.08122952282428741} 08/30/2021 16:13:33 - INFO - __main__ - Step 16556: {'lr': 0.00048816268112147134, 'samples': 3178752, 'steps': 16555, 'loss/train': 1.641249656677246} 08/30/2021 16:13:35 - INFO - __main__ - Step 16557: {'lr': 0.00048816106746323273, 'samples': 3178944, 'steps': 16556, 'loss/train': 1.8160207271575928} 08/30/2021 16:13:35 - INFO - __main__ - Step 16558: {'lr': 0.00048815945369768245, 'samples': 3179136, 'steps': 16557, 'loss/train': 1.1699459552764893} 08/30/2021 16:13:36 - INFO - __main__ - Step 16559: {'lr': 0.00048815783982482115, 'samples': 3179328, 'steps': 16558, 'loss/train': 1.8620539903640747} 08/30/2021 16:13:36 - INFO - __main__ - Step 16560: {'lr': 0.0004881562258446496, 'samples': 3179520, 'steps': 16559, 'loss/train': 1.6518065929412842} 08/30/2021 16:13:36 - INFO - __main__ - Step 16561: {'lr': 0.00048815461175716855, 'samples': 3179712, 'steps': 16560, 'loss/train': 1.3696002960205078} 08/30/2021 16:13:37 - INFO - __main__ - Step 16562: {'lr': 0.00048815299756237873, 'samples': 3179904, 'steps': 16561, 'loss/train': 1.7370407581329346} 08/30/2021 16:13:38 - INFO - __main__ - Step 16563: {'lr': 0.0004881513832602808, 'samples': 3180096, 'steps': 16562, 'loss/train': 1.635070562362671} 08/30/2021 16:13:38 - INFO - __main__ - Step 16564: {'lr': 0.0004881497688508756, 'samples': 3180288, 'steps': 16563, 'loss/train': 1.273830771446228} 08/30/2021 16:13:39 - INFO - __main__ - Step 16565: {'lr': 0.0004881481543341637, 'samples': 3180480, 'steps': 16564, 'loss/train': 1.7977510690689087} 08/30/2021 16:13:39 - INFO - __main__ - Step 16566: {'lr': 0.000488146539710146, 'samples': 3180672, 'steps': 16565, 'loss/train': 2.0253050327301025} 08/30/2021 16:13:40 - INFO - __main__ - Step 16567: {'lr': 0.00048814492497882306, 'samples': 3180864, 'steps': 16566, 'loss/train': 1.941239833831787} 08/30/2021 16:13:41 - INFO - __main__ - Step 16568: {'lr': 0.00048814331014019577, 'samples': 3181056, 'steps': 16567, 'loss/train': 1.6758822202682495} 08/30/2021 16:13:41 - INFO - __main__ - Step 16569: {'lr': 0.0004881416951942647, 'samples': 3181248, 'steps': 16568, 'loss/train': 2.201371431350708} 08/30/2021 16:13:42 - INFO - __main__ - Step 16570: {'lr': 0.0004881400801410307, 'samples': 3181440, 'steps': 16569, 'loss/train': 1.941340684890747} 08/30/2021 16:13:42 - INFO - __main__ - Step 16571: {'lr': 0.0004881384649804945, 'samples': 3181632, 'steps': 16570, 'loss/train': 2.0682497024536133} 08/30/2021 16:13:43 - INFO - __main__ - Step 16572: {'lr': 0.0004881368497126567, 'samples': 3181824, 'steps': 16571, 'loss/train': 1.958207368850708} 08/30/2021 16:13:44 - INFO - __main__ - Step 16573: {'lr': 0.00048813523433751814, 'samples': 3182016, 'steps': 16572, 'loss/train': 1.3708523511886597} 08/30/2021 16:13:45 - INFO - __main__ - Step 16574: {'lr': 0.00048813361885507956, 'samples': 3182208, 'steps': 16573, 'loss/train': 1.3560123443603516} 08/30/2021 16:13:45 - INFO - __main__ - Step 16575: {'lr': 0.00048813200326534156, 'samples': 3182400, 'steps': 16574, 'loss/train': 1.6077187061309814} 08/30/2021 16:13:45 - INFO - __main__ - Step 16576: {'lr': 0.00048813038756830506, 'samples': 3182592, 'steps': 16575, 'loss/train': 1.6748696565628052} 08/30/2021 16:13:46 - INFO - __main__ - Step 16577: {'lr': 0.00048812877176397066, 'samples': 3182784, 'steps': 16576, 'loss/train': 0.4968474507331848} 08/30/2021 16:13:47 - INFO - __main__ - Step 16578: {'lr': 0.00048812715585233905, 'samples': 3182976, 'steps': 16577, 'loss/train': 1.143213152885437} 08/30/2021 16:13:48 - INFO - __main__ - Step 16579: {'lr': 0.000488125539833411, 'samples': 3183168, 'steps': 16578, 'loss/train': 1.5067323446273804} 08/30/2021 16:13:48 - INFO - __main__ - Step 16580: {'lr': 0.0004881239237071873, 'samples': 3183360, 'steps': 16579, 'loss/train': 0.1325390636920929} 08/30/2021 16:13:49 - INFO - __main__ - Step 16581: {'lr': 0.0004881223074736687, 'samples': 3183552, 'steps': 16580, 'loss/train': 1.699009895324707} 08/30/2021 16:13:49 - INFO - __main__ - Step 16582: {'lr': 0.00048812069113285573, 'samples': 3183744, 'steps': 16581, 'loss/train': 0.08957020193338394} 08/30/2021 16:13:49 - INFO - __main__ - Step 16583: {'lr': 0.00048811907468474934, 'samples': 3183936, 'steps': 16582, 'loss/train': 1.3878061771392822} 08/30/2021 16:13:51 - INFO - __main__ - Step 16584: {'lr': 0.00048811745812935015, 'samples': 3184128, 'steps': 16583, 'loss/train': 0.20824885368347168} 08/30/2021 16:13:51 - INFO - __main__ - Step 16585: {'lr': 0.00048811584146665895, 'samples': 3184320, 'steps': 16584, 'loss/train': 1.6124420166015625} 08/30/2021 16:13:52 - INFO - __main__ - Step 16586: {'lr': 0.0004881142246966763, 'samples': 3184512, 'steps': 16585, 'loss/train': 1.8895361423492432} 08/30/2021 16:13:52 - INFO - __main__ - Step 16587: {'lr': 0.00048811260781940317, 'samples': 3184704, 'steps': 16586, 'loss/train': 1.4383306503295898} 08/30/2021 16:13:52 - INFO - __main__ - Step 16588: {'lr': 0.00048811099083484016, 'samples': 3184896, 'steps': 16587, 'loss/train': 1.6250507831573486} 08/30/2021 16:13:54 - INFO - __main__ - Step 16589: {'lr': 0.000488109373742988, 'samples': 3185088, 'steps': 16588, 'loss/train': 1.5738410949707031} 08/30/2021 16:13:54 - INFO - __main__ - Step 16590: {'lr': 0.0004881077565438474, 'samples': 3185280, 'steps': 16589, 'loss/train': 1.6363602876663208} 08/30/2021 16:13:55 - INFO - __main__ - Step 16591: {'lr': 0.0004881061392374192, 'samples': 3185472, 'steps': 16590, 'loss/train': 1.9625236988067627} 08/30/2021 16:13:55 - INFO - __main__ - Step 16592: {'lr': 0.000488104521823704, 'samples': 3185664, 'steps': 16591, 'loss/train': 1.8436386585235596} 08/30/2021 16:13:55 - INFO - __main__ - Step 16593: {'lr': 0.00048810290430270257, 'samples': 3185856, 'steps': 16592, 'loss/train': 2.055682420730591} 08/30/2021 16:13:56 - INFO - __main__ - Step 16594: {'lr': 0.0004881012866744156, 'samples': 3186048, 'steps': 16593, 'loss/train': 1.7000099420547485} 08/30/2021 16:13:57 - INFO - __main__ - Step 16595: {'lr': 0.00048809966893884396, 'samples': 3186240, 'steps': 16594, 'loss/train': 1.7137199640274048} 08/30/2021 16:13:58 - INFO - __main__ - Step 16596: {'lr': 0.00048809805109598813, 'samples': 3186432, 'steps': 16595, 'loss/train': 1.7170580625534058} 08/30/2021 16:13:58 - INFO - __main__ - Step 16597: {'lr': 0.0004880964331458492, 'samples': 3186624, 'steps': 16596, 'loss/train': 1.5858354568481445} 08/30/2021 16:13:59 - INFO - __main__ - Step 16598: {'lr': 0.0004880948150884276, 'samples': 3186816, 'steps': 16597, 'loss/train': 1.4752651453018188} 08/30/2021 16:13:59 - INFO - __main__ - Step 16599: {'lr': 0.00048809319692372406, 'samples': 3187008, 'steps': 16598, 'loss/train': 1.3279571533203125} 08/30/2021 16:14:01 - INFO - __main__ - Step 16600: {'lr': 0.0004880915786517395, 'samples': 3187200, 'steps': 16599, 'loss/train': 2.0533125400543213} 08/30/2021 16:14:01 - INFO - __main__ - Step 16601: {'lr': 0.00048808996027247453, 'samples': 3187392, 'steps': 16600, 'loss/train': 2.0156710147857666} 08/30/2021 16:14:02 - INFO - __main__ - Step 16602: {'lr': 0.0004880883417859299, 'samples': 3187584, 'steps': 16601, 'loss/train': 1.2864296436309814} 08/30/2021 16:14:02 - INFO - __main__ - Step 16603: {'lr': 0.0004880867231921063, 'samples': 3187776, 'steps': 16602, 'loss/train': 1.0905944108963013} 08/30/2021 16:14:03 - INFO - __main__ - Step 16604: {'lr': 0.0004880851044910045, 'samples': 3187968, 'steps': 16603, 'loss/train': 1.7267661094665527} 08/30/2021 16:14:04 - INFO - __main__ - Step 16605: {'lr': 0.0004880834856826253, 'samples': 3188160, 'steps': 16604, 'loss/train': 1.4709233045578003} 08/30/2021 16:14:04 - INFO - __main__ - Step 16606: {'lr': 0.0004880818667669693, 'samples': 3188352, 'steps': 16605, 'loss/train': 2.203814744949341} 08/30/2021 16:14:05 - INFO - __main__ - Step 16607: {'lr': 0.00048808024774403726, 'samples': 3188544, 'steps': 16606, 'loss/train': 1.5960253477096558} 08/30/2021 16:14:05 - INFO - __main__ - Step 16608: {'lr': 0.00048807862861382996, 'samples': 3188736, 'steps': 16607, 'loss/train': 1.7516332864761353} 08/30/2021 16:14:05 - INFO - __main__ - Step 16609: {'lr': 0.0004880770093763481, 'samples': 3188928, 'steps': 16608, 'loss/train': 2.1294281482696533} 08/30/2021 16:14:07 - INFO - __main__ - Step 16610: {'lr': 0.0004880753900315924, 'samples': 3189120, 'steps': 16609, 'loss/train': 1.4692928791046143} 08/30/2021 16:14:07 - INFO - __main__ - Step 16611: {'lr': 0.00048807377057956365, 'samples': 3189312, 'steps': 16610, 'loss/train': 1.856947422027588} 08/30/2021 16:14:08 - INFO - __main__ - Step 16612: {'lr': 0.00048807215102026247, 'samples': 3189504, 'steps': 16611, 'loss/train': 1.485852837562561} 08/30/2021 16:14:08 - INFO - __main__ - Step 16613: {'lr': 0.00048807053135368973, 'samples': 3189696, 'steps': 16612, 'loss/train': 2.0284597873687744} 08/30/2021 16:14:08 - INFO - __main__ - Step 16614: {'lr': 0.00048806891157984604, 'samples': 3189888, 'steps': 16613, 'loss/train': 1.6739753484725952} 08/30/2021 16:14:10 - INFO - __main__ - Step 16615: {'lr': 0.0004880672916987322, 'samples': 3190080, 'steps': 16614, 'loss/train': 0.4266573488712311} 08/30/2021 16:14:11 - INFO - __main__ - Step 16616: {'lr': 0.0004880656717103489, 'samples': 3190272, 'steps': 16615, 'loss/train': 1.585524320602417} 08/30/2021 16:14:11 - INFO - __main__ - Step 16617: {'lr': 0.0004880640516146968, 'samples': 3190464, 'steps': 16616, 'loss/train': 1.5404939651489258} 08/30/2021 16:14:11 - INFO - __main__ - Step 16618: {'lr': 0.0004880624314117768, 'samples': 3190656, 'steps': 16617, 'loss/train': 1.2139486074447632} 08/30/2021 16:14:12 - INFO - __main__ - Step 16619: {'lr': 0.0004880608111015895, 'samples': 3190848, 'steps': 16618, 'loss/train': 1.6645313501358032} 08/30/2021 16:14:13 - INFO - __main__ - Step 16620: {'lr': 0.00048805919068413574, 'samples': 3191040, 'steps': 16619, 'loss/train': 0.14072319865226746} 08/30/2021 16:14:14 - INFO - __main__ - Step 16621: {'lr': 0.0004880575701594161, 'samples': 3191232, 'steps': 16620, 'loss/train': 2.3166964054107666} 08/30/2021 16:14:14 - INFO - __main__ - Step 16622: {'lr': 0.0004880559495274315, 'samples': 3191424, 'steps': 16621, 'loss/train': 1.9499908685684204} 08/30/2021 16:14:15 - INFO - __main__ - Step 16623: {'lr': 0.00048805432878818247, 'samples': 3191616, 'steps': 16622, 'loss/train': 1.9381393194198608} 08/30/2021 16:14:15 - INFO - __main__ - Step 16624: {'lr': 0.0004880527079416698, 'samples': 3191808, 'steps': 16623, 'loss/train': 1.55039381980896} 08/30/2021 16:14:15 - INFO - __main__ - Step 16625: {'lr': 0.00048805108698789435, 'samples': 3192000, 'steps': 16624, 'loss/train': 1.7067677974700928} 08/30/2021 16:14:17 - INFO - __main__ - Step 16626: {'lr': 0.00048804946592685667, 'samples': 3192192, 'steps': 16625, 'loss/train': 0.2757457494735718} 08/30/2021 16:14:17 - INFO - __main__ - Step 16627: {'lr': 0.0004880478447585576, 'samples': 3192384, 'steps': 16626, 'loss/train': 0.9581832885742188} 08/30/2021 16:14:18 - INFO - __main__ - Step 16628: {'lr': 0.00048804622348299785, 'samples': 3192576, 'steps': 16627, 'loss/train': 1.693848729133606} 08/30/2021 16:14:18 - INFO - __main__ - Step 16629: {'lr': 0.0004880446021001782, 'samples': 3192768, 'steps': 16628, 'loss/train': 1.7661103010177612} 08/30/2021 16:14:18 - INFO - __main__ - Step 16630: {'lr': 0.00048804298061009925, 'samples': 3192960, 'steps': 16629, 'loss/train': 2.469510078430176} 08/30/2021 16:14:20 - INFO - __main__ - Step 16631: {'lr': 0.0004880413590127619, 'samples': 3193152, 'steps': 16630, 'loss/train': 1.0144615173339844} 08/30/2021 16:14:20 - INFO - __main__ - Step 16632: {'lr': 0.0004880397373081666, 'samples': 3193344, 'steps': 16631, 'loss/train': 1.9545166492462158} 08/30/2021 16:14:21 - INFO - __main__ - Step 16633: {'lr': 0.0004880381154963145, 'samples': 3193536, 'steps': 16632, 'loss/train': 1.8227757215499878} 08/30/2021 16:14:21 - INFO - __main__ - Step 16634: {'lr': 0.0004880364935772059, 'samples': 3193728, 'steps': 16633, 'loss/train': 1.6634933948516846} 08/30/2021 16:14:21 - INFO - __main__ - Step 16635: {'lr': 0.00048803487155084184, 'samples': 3193920, 'steps': 16634, 'loss/train': 1.8381518125534058} 08/30/2021 16:14:23 - INFO - __main__ - Step 16636: {'lr': 0.00048803324941722295, 'samples': 3194112, 'steps': 16635, 'loss/train': 1.544309377670288} 08/30/2021 16:14:23 - INFO - __main__ - Step 16637: {'lr': 0.0004880316271763499, 'samples': 3194304, 'steps': 16636, 'loss/train': 0.11979955434799194} 08/30/2021 16:14:24 - INFO - __main__ - Step 16638: {'lr': 0.0004880300048282235, 'samples': 3194496, 'steps': 16637, 'loss/train': 1.9168736934661865} 08/30/2021 16:14:24 - INFO - __main__ - Step 16639: {'lr': 0.00048802838237284443, 'samples': 3194688, 'steps': 16638, 'loss/train': 2.0347630977630615} 08/30/2021 16:14:24 - INFO - __main__ - Step 16640: {'lr': 0.0004880267598102135, 'samples': 3194880, 'steps': 16639, 'loss/train': 1.0156313180923462} 08/30/2021 16:14:25 - INFO - __main__ - Step 16641: {'lr': 0.0004880251371403313, 'samples': 3195072, 'steps': 16640, 'loss/train': 1.5347892045974731} 08/30/2021 16:14:26 - INFO - __main__ - Step 16642: {'lr': 0.0004880235143631987, 'samples': 3195264, 'steps': 16641, 'loss/train': 1.6933704614639282} 08/30/2021 16:14:27 - INFO - __main__ - Step 16643: {'lr': 0.0004880218914788164, 'samples': 3195456, 'steps': 16642, 'loss/train': 1.696418285369873} 08/30/2021 16:14:27 - INFO - __main__ - Step 16644: {'lr': 0.00048802026848718505, 'samples': 3195648, 'steps': 16643, 'loss/train': 1.2272576093673706} 08/30/2021 16:14:28 - INFO - __main__ - Step 16645: {'lr': 0.0004880186453883054, 'samples': 3195840, 'steps': 16644, 'loss/train': 1.1475294828414917} 08/30/2021 16:14:28 - INFO - __main__ - Step 16646: {'lr': 0.00048801702218217834, 'samples': 3196032, 'steps': 16645, 'loss/train': 1.7064080238342285} 08/30/2021 16:14:29 - INFO - __main__ - Step 16647: {'lr': 0.0004880153988688044, 'samples': 3196224, 'steps': 16646, 'loss/train': 0.5632283687591553} 08/30/2021 16:14:30 - INFO - __main__ - Step 16648: {'lr': 0.0004880137754481845, 'samples': 3196416, 'steps': 16647, 'loss/train': 1.7644410133361816} 08/30/2021 16:14:30 - INFO - __main__ - Step 16649: {'lr': 0.0004880121519203191, 'samples': 3196608, 'steps': 16648, 'loss/train': 1.4228501319885254} 08/30/2021 16:14:31 - INFO - __main__ - Step 16650: {'lr': 0.0004880105282852092, 'samples': 3196800, 'steps': 16649, 'loss/train': 1.9696342945098877} 08/30/2021 16:14:31 - INFO - __main__ - Step 16651: {'lr': 0.0004880089045428554, 'samples': 3196992, 'steps': 16650, 'loss/train': 1.603187918663025} 08/30/2021 16:14:33 - INFO - __main__ - Step 16652: {'lr': 0.0004880072806932585, 'samples': 3197184, 'steps': 16651, 'loss/train': 1.5181456804275513} 08/30/2021 16:14:33 - INFO - __main__ - Step 16653: {'lr': 0.00048800565673641917, 'samples': 3197376, 'steps': 16652, 'loss/train': 1.427760362625122} 08/30/2021 16:14:34 - INFO - __main__ - Step 16654: {'lr': 0.0004880040326723382, 'samples': 3197568, 'steps': 16653, 'loss/train': 1.944973349571228} 08/30/2021 16:14:34 - INFO - __main__ - Step 16655: {'lr': 0.0004880024085010162, 'samples': 3197760, 'steps': 16654, 'loss/train': 1.6088995933532715} 08/30/2021 16:14:34 - INFO - __main__ - Step 16656: {'lr': 0.00048800078422245406, 'samples': 3197952, 'steps': 16655, 'loss/train': 1.9604657888412476} 08/30/2021 16:14:36 - INFO - __main__ - Step 16657: {'lr': 0.0004879991598366524, 'samples': 3198144, 'steps': 16656, 'loss/train': 1.8557242155075073} 08/30/2021 16:14:37 - INFO - __main__ - Step 16658: {'lr': 0.000487997535343612, 'samples': 3198336, 'steps': 16657, 'loss/train': 2.594700336456299} 08/30/2021 16:14:37 - INFO - __main__ - Step 16659: {'lr': 0.0004879959107433336, 'samples': 3198528, 'steps': 16658, 'loss/train': 1.4913543462753296} 08/30/2021 16:14:37 - INFO - __main__ - Step 16660: {'lr': 0.00048799428603581786, 'samples': 3198720, 'steps': 16659, 'loss/train': 1.9455454349517822} 08/30/2021 16:14:38 - INFO - __main__ - Step 16661: {'lr': 0.0004879926612210656, 'samples': 3198912, 'steps': 16660, 'loss/train': 0.6294904947280884} 08/30/2021 16:14:38 - INFO - __main__ - Step 16662: {'lr': 0.0004879910362990775, 'samples': 3199104, 'steps': 16661, 'loss/train': 1.3812592029571533} 08/30/2021 16:14:38 - INFO - __main__ - Step 16663: {'lr': 0.0004879894112698544, 'samples': 3199296, 'steps': 16662, 'loss/train': 1.2141501903533936} 08/30/2021 16:14:40 - INFO - __main__ - Step 16664: {'lr': 0.0004879877861333969, 'samples': 3199488, 'steps': 16663, 'loss/train': 0.5333452224731445} 08/30/2021 16:14:40 - INFO - __main__ - Step 16665: {'lr': 0.00048798616088970573, 'samples': 3199680, 'steps': 16664, 'loss/train': 0.5689380168914795} 08/30/2021 16:14:41 - INFO - __main__ - Step 16666: {'lr': 0.0004879845355387817, 'samples': 3199872, 'steps': 16665, 'loss/train': 1.3376206159591675} 08/30/2021 16:14:41 - INFO - __main__ - Step 16667: {'lr': 0.00048798291008062553, 'samples': 3200064, 'steps': 16666, 'loss/train': 2.0341899394989014} 08/30/2021 16:14:41 - INFO - __main__ - Step 16668: {'lr': 0.0004879812845152379, 'samples': 3200256, 'steps': 16667, 'loss/train': 2.0121335983276367} 08/30/2021 16:14:43 - INFO - __main__ - Step 16669: {'lr': 0.0004879796588426195, 'samples': 3200448, 'steps': 16668, 'loss/train': 1.902250051498413} 08/30/2021 16:14:44 - INFO - __main__ - Step 16670: {'lr': 0.0004879780330627713, 'samples': 3200640, 'steps': 16669, 'loss/train': 1.7941910028457642} 08/30/2021 16:14:44 - INFO - __main__ - Step 16671: {'lr': 0.0004879764071756938, 'samples': 3200832, 'steps': 16670, 'loss/train': 0.3390023708343506} 08/30/2021 16:14:44 - INFO - __main__ - Step 16672: {'lr': 0.00048797478118138777, 'samples': 3201024, 'steps': 16671, 'loss/train': 1.7030514478683472} 08/30/2021 16:14:45 - INFO - __main__ - Step 16673: {'lr': 0.000487973155079854, 'samples': 3201216, 'steps': 16672, 'loss/train': 1.5212053060531616} 08/30/2021 16:14:46 - INFO - __main__ - Step 16674: {'lr': 0.0004879715288710932, 'samples': 3201408, 'steps': 16673, 'loss/train': 1.762177586555481} 08/30/2021 16:14:47 - INFO - __main__ - Step 16675: {'lr': 0.0004879699025551061, 'samples': 3201600, 'steps': 16674, 'loss/train': 1.2488783597946167} 08/30/2021 16:14:47 - INFO - __main__ - Step 16676: {'lr': 0.0004879682761318934, 'samples': 3201792, 'steps': 16675, 'loss/train': 1.6335327625274658} 08/30/2021 16:14:47 - INFO - __main__ - Step 16677: {'lr': 0.00048796664960145596, 'samples': 3201984, 'steps': 16676, 'loss/train': 0.05811972916126251} 08/30/2021 16:14:48 - INFO - __main__ - Step 16678: {'lr': 0.00048796502296379437, 'samples': 3202176, 'steps': 16677, 'loss/train': 1.8747398853302002} 08/30/2021 16:14:49 - INFO - __main__ - Step 16679: {'lr': 0.0004879633962189094, 'samples': 3202368, 'steps': 16678, 'loss/train': 1.61774742603302} 08/30/2021 16:14:50 - INFO - __main__ - Step 16680: {'lr': 0.0004879617693668018, 'samples': 3202560, 'steps': 16679, 'loss/train': 2.108137607574463} 08/30/2021 16:14:50 - INFO - __main__ - Step 16681: {'lr': 0.00048796014240747227, 'samples': 3202752, 'steps': 16680, 'loss/train': 1.5128915309906006} 08/30/2021 16:14:50 - INFO - __main__ - Step 16682: {'lr': 0.0004879585153409216, 'samples': 3202944, 'steps': 16681, 'loss/train': 1.926310420036316} 08/30/2021 16:14:51 - INFO - __main__ - Step 16683: {'lr': 0.0004879568881671505, 'samples': 3203136, 'steps': 16682, 'loss/train': 1.9453061819076538} 08/30/2021 16:14:52 - INFO - __main__ - Step 16684: {'lr': 0.0004879552608861597, 'samples': 3203328, 'steps': 16683, 'loss/train': 1.6820000410079956} 08/30/2021 16:14:53 - INFO - __main__ - Step 16685: {'lr': 0.00048795363349794996, 'samples': 3203520, 'steps': 16684, 'loss/train': 1.78916335105896} 08/30/2021 16:14:53 - INFO - __main__ - Step 16686: {'lr': 0.00048795200600252193, 'samples': 3203712, 'steps': 16685, 'loss/train': 1.3662347793579102} 08/30/2021 16:14:54 - INFO - __main__ - Step 16687: {'lr': 0.00048795037839987644, 'samples': 3203904, 'steps': 16686, 'loss/train': 1.3548601865768433} 08/30/2021 16:14:54 - INFO - __main__ - Step 16688: {'lr': 0.0004879487506900141, 'samples': 3204096, 'steps': 16687, 'loss/train': 1.7290133237838745} 08/30/2021 16:14:55 - INFO - __main__ - Step 16689: {'lr': 0.0004879471228729358, 'samples': 3204288, 'steps': 16688, 'loss/train': 0.3155171871185303} 08/30/2021 16:14:56 - INFO - __main__ - Step 16690: {'lr': 0.0004879454949486422, 'samples': 3204480, 'steps': 16689, 'loss/train': 1.1663745641708374} 08/30/2021 16:14:56 - INFO - __main__ - Step 16691: {'lr': 0.000487943866917134, 'samples': 3204672, 'steps': 16690, 'loss/train': 1.5553964376449585} 08/30/2021 16:14:57 - INFO - __main__ - Step 16692: {'lr': 0.00048794223877841197, 'samples': 3204864, 'steps': 16691, 'loss/train': 1.8806887865066528} 08/30/2021 16:14:57 - INFO - __main__ - Step 16693: {'lr': 0.00048794061053247686, 'samples': 3205056, 'steps': 16692, 'loss/train': 1.5888007879257202} 08/30/2021 16:14:58 - INFO - __main__ - Step 16694: {'lr': 0.0004879389821793294, 'samples': 3205248, 'steps': 16693, 'loss/train': 1.103945016860962} 08/30/2021 16:14:59 - INFO - __main__ - Step 16695: {'lr': 0.00048793735371897027, 'samples': 3205440, 'steps': 16694, 'loss/train': 1.3188711404800415} 08/30/2021 16:14:59 - INFO - __main__ - Step 16696: {'lr': 0.00048793572515140024, 'samples': 3205632, 'steps': 16695, 'loss/train': 1.5159010887145996} 08/30/2021 16:15:00 - INFO - __main__ - Step 16697: {'lr': 0.00048793409647662, 'samples': 3205824, 'steps': 16696, 'loss/train': 2.130124092102051} 08/30/2021 16:15:00 - INFO - __main__ - Step 16698: {'lr': 0.0004879324676946304, 'samples': 3206016, 'steps': 16697, 'loss/train': 1.5905779600143433} 08/30/2021 16:15:00 - INFO - __main__ - Step 16699: {'lr': 0.0004879308388054321, 'samples': 3206208, 'steps': 16698, 'loss/train': 1.96693754196167} 08/30/2021 16:15:03 - INFO - __main__ - Step 16700: {'lr': 0.0004879292098090258, 'samples': 3206400, 'steps': 16699, 'loss/train': 1.7866253852844238} 08/30/2021 16:15:03 - INFO - __main__ - Step 16701: {'lr': 0.00048792758070541234, 'samples': 3206592, 'steps': 16700, 'loss/train': 1.3016022443771362} 08/30/2021 16:15:04 - INFO - __main__ - Step 16702: {'lr': 0.00048792595149459226, 'samples': 3206784, 'steps': 16701, 'loss/train': 0.7525354623794556} 08/30/2021 16:15:04 - INFO - __main__ - Step 16703: {'lr': 0.0004879243221765665, 'samples': 3206976, 'steps': 16702, 'loss/train': 0.6439904570579529} 08/30/2021 16:15:04 - INFO - __main__ - Step 16704: {'lr': 0.00048792269275133574, 'samples': 3207168, 'steps': 16703, 'loss/train': 0.6069667935371399} 08/30/2021 16:15:05 - INFO - __main__ - Step 16705: {'lr': 0.0004879210632189006, 'samples': 3207360, 'steps': 16704, 'loss/train': 1.6717065572738647} 08/30/2021 16:15:06 - INFO - __main__ - Step 16706: {'lr': 0.0004879194335792619, 'samples': 3207552, 'steps': 16705, 'loss/train': 1.686883807182312} 08/30/2021 16:15:07 - INFO - __main__ - Step 16707: {'lr': 0.0004879178038324205, 'samples': 3207744, 'steps': 16706, 'loss/train': 0.46764278411865234} 08/30/2021 16:15:07 - INFO - __main__ - Step 16708: {'lr': 0.0004879161739783769, 'samples': 3207936, 'steps': 16707, 'loss/train': 1.4054722785949707} 08/30/2021 16:15:07 - INFO - __main__ - Step 16709: {'lr': 0.00048791454401713195, 'samples': 3208128, 'steps': 16708, 'loss/train': 1.715261697769165} 08/30/2021 16:15:08 - INFO - __main__ - Step 16710: {'lr': 0.00048791291394868644, 'samples': 3208320, 'steps': 16709, 'loss/train': 1.0365930795669556} 08/30/2021 16:15:10 - INFO - __main__ - Step 16711: {'lr': 0.000487911283773041, 'samples': 3208512, 'steps': 16710, 'loss/train': 0.22322697937488556} 08/30/2021 16:15:10 - INFO - __main__ - Step 16712: {'lr': 0.0004879096534901964, 'samples': 3208704, 'steps': 16711, 'loss/train': 1.6091737747192383} 08/30/2021 16:15:11 - INFO - __main__ - Step 16713: {'lr': 0.00048790802310015336, 'samples': 3208896, 'steps': 16712, 'loss/train': 1.3067803382873535} 08/30/2021 16:15:11 - INFO - __main__ - Step 16714: {'lr': 0.0004879063926029127, 'samples': 3209088, 'steps': 16713, 'loss/train': 0.07299730181694031} 08/30/2021 16:15:11 - INFO - __main__ - Step 16715: {'lr': 0.00048790476199847506, 'samples': 3209280, 'steps': 16714, 'loss/train': 1.7180428504943848} 08/30/2021 16:15:13 - INFO - __main__ - Step 16716: {'lr': 0.0004879031312868412, 'samples': 3209472, 'steps': 16715, 'loss/train': 1.3390231132507324} 08/30/2021 16:15:13 - INFO - __main__ - Step 16717: {'lr': 0.00048790150046801187, 'samples': 3209664, 'steps': 16716, 'loss/train': 1.1674901247024536} 08/30/2021 16:15:14 - INFO - __main__ - Step 16718: {'lr': 0.0004878998695419877, 'samples': 3209856, 'steps': 16717, 'loss/train': 1.949594259262085} 08/30/2021 16:15:14 - INFO - __main__ - Step 16719: {'lr': 0.0004878982385087697, 'samples': 3210048, 'steps': 16718, 'loss/train': 1.2132210731506348} 08/30/2021 16:15:15 - INFO - __main__ - Step 16720: {'lr': 0.0004878966073683583, 'samples': 3210240, 'steps': 16719, 'loss/train': 1.2069034576416016} 08/30/2021 16:15:15 - INFO - __main__ - Step 16721: {'lr': 0.0004878949761207544, 'samples': 3210432, 'steps': 16720, 'loss/train': 1.6156997680664062} 08/30/2021 16:15:16 - INFO - __main__ - Step 16722: {'lr': 0.0004878933447659587, 'samples': 3210624, 'steps': 16721, 'loss/train': 2.123835325241089} 08/30/2021 16:15:17 - INFO - __main__ - Step 16723: {'lr': 0.0004878917133039719, 'samples': 3210816, 'steps': 16722, 'loss/train': 1.9504806995391846} 08/30/2021 16:15:17 - INFO - __main__ - Step 16724: {'lr': 0.00048789008173479476, 'samples': 3211008, 'steps': 16723, 'loss/train': 1.1853959560394287} 08/30/2021 16:15:17 - INFO - __main__ - Step 16725: {'lr': 0.0004878884500584281, 'samples': 3211200, 'steps': 16724, 'loss/train': 1.256620168685913} 08/30/2021 16:15:18 - INFO - __main__ - Step 16726: {'lr': 0.0004878868182748725, 'samples': 3211392, 'steps': 16725, 'loss/train': 1.831167459487915} 08/30/2021 16:15:19 - INFO - __main__ - Step 16727: {'lr': 0.0004878851863841287, 'samples': 3211584, 'steps': 16726, 'loss/train': 1.5383081436157227} 08/30/2021 16:15:20 - INFO - __main__ - Step 16728: {'lr': 0.00048788355438619764, 'samples': 3211776, 'steps': 16727, 'loss/train': 1.5069228410720825} 08/30/2021 16:15:20 - INFO - __main__ - Step 16729: {'lr': 0.00048788192228107986, 'samples': 3211968, 'steps': 16728, 'loss/train': 1.9376816749572754} 08/30/2021 16:15:20 - INFO - __main__ - Step 16730: {'lr': 0.00048788029006877623, 'samples': 3212160, 'steps': 16729, 'loss/train': 1.933656096458435} 08/30/2021 16:15:21 - INFO - __main__ - Step 16731: {'lr': 0.0004878786577492873, 'samples': 3212352, 'steps': 16730, 'loss/train': 1.6945432424545288} 08/30/2021 16:15:22 - INFO - __main__ - Step 16732: {'lr': 0.00048787702532261396, 'samples': 3212544, 'steps': 16731, 'loss/train': 1.8733289241790771} 08/30/2021 16:15:23 - INFO - __main__ - Step 16733: {'lr': 0.0004878753927887569, 'samples': 3212736, 'steps': 16732, 'loss/train': 1.5571599006652832} 08/30/2021 16:15:23 - INFO - __main__ - Step 16734: {'lr': 0.0004878737601477169, 'samples': 3212928, 'steps': 16733, 'loss/train': 1.8006837368011475} 08/30/2021 16:15:23 - INFO - __main__ - Step 16735: {'lr': 0.0004878721273994946, 'samples': 3213120, 'steps': 16734, 'loss/train': 1.913068175315857} 08/30/2021 16:15:24 - INFO - __main__ - Step 16736: {'lr': 0.00048787049454409085, 'samples': 3213312, 'steps': 16735, 'loss/train': 1.6572901010513306} 08/30/2021 16:15:25 - INFO - __main__ - Step 16737: {'lr': 0.0004878688615815063, 'samples': 3213504, 'steps': 16736, 'loss/train': 1.5615729093551636} 08/30/2021 16:15:26 - INFO - __main__ - Step 16738: {'lr': 0.0004878672285117417, 'samples': 3213696, 'steps': 16737, 'loss/train': 1.1859101057052612} 08/30/2021 16:15:26 - INFO - __main__ - Step 16739: {'lr': 0.0004878655953347978, 'samples': 3213888, 'steps': 16738, 'loss/train': 1.5913857221603394} 08/30/2021 16:15:26 - INFO - __main__ - Step 16740: {'lr': 0.0004878639620506753, 'samples': 3214080, 'steps': 16739, 'loss/train': 1.3443471193313599} 08/30/2021 16:15:27 - INFO - __main__ - Step 16741: {'lr': 0.00048786232865937504, 'samples': 3214272, 'steps': 16740, 'loss/train': 0.7952996492385864} 08/30/2021 16:15:28 - INFO - __main__ - Step 16742: {'lr': 0.0004878606951608976, 'samples': 3214464, 'steps': 16741, 'loss/train': 1.502210021018982} 08/30/2021 16:15:29 - INFO - __main__ - Step 16743: {'lr': 0.00048785906155524386, 'samples': 3214656, 'steps': 16742, 'loss/train': 1.5023962259292603} 08/30/2021 16:15:29 - INFO - __main__ - Step 16744: {'lr': 0.0004878574278424145, 'samples': 3214848, 'steps': 16743, 'loss/train': 2.827465295791626} 08/30/2021 16:15:30 - INFO - __main__ - Step 16745: {'lr': 0.0004878557940224102, 'samples': 3215040, 'steps': 16744, 'loss/train': 1.257771611213684} 08/30/2021 16:15:30 - INFO - __main__ - Step 16746: {'lr': 0.0004878541600952318, 'samples': 3215232, 'steps': 16745, 'loss/train': 1.6157188415527344} 08/30/2021 16:15:30 - INFO - __main__ - Step 16747: {'lr': 0.00048785252606087996, 'samples': 3215424, 'steps': 16746, 'loss/train': 1.7678358554840088} 08/30/2021 16:15:32 - INFO - __main__ - Step 16748: {'lr': 0.0004878508919193555, 'samples': 3215616, 'steps': 16747, 'loss/train': 1.8955780267715454} 08/30/2021 16:15:33 - INFO - __main__ - Step 16749: {'lr': 0.000487849257670659, 'samples': 3215808, 'steps': 16748, 'loss/train': 1.434479832649231} 08/30/2021 16:15:33 - INFO - __main__ - Step 16750: {'lr': 0.0004878476233147914, 'samples': 3216000, 'steps': 16749, 'loss/train': 1.400259256362915} 08/30/2021 16:15:33 - INFO - __main__ - Step 16751: {'lr': 0.00048784598885175324, 'samples': 3216192, 'steps': 16750, 'loss/train': 1.5084441900253296} 08/30/2021 16:15:34 - INFO - __main__ - Step 16752: {'lr': 0.00048784435428154537, 'samples': 3216384, 'steps': 16751, 'loss/train': 1.7930991649627686} 08/30/2021 16:15:34 - INFO - __main__ - Step 16753: {'lr': 0.0004878427196041686, 'samples': 3216576, 'steps': 16752, 'loss/train': 1.52134370803833} 08/30/2021 16:15:35 - INFO - __main__ - Step 16754: {'lr': 0.00048784108481962347, 'samples': 3216768, 'steps': 16753, 'loss/train': 0.8323087096214294} 08/30/2021 16:15:36 - INFO - __main__ - Step 16755: {'lr': 0.00048783944992791085, 'samples': 3216960, 'steps': 16754, 'loss/train': 1.7217965126037598} 08/30/2021 16:15:36 - INFO - __main__ - Step 16756: {'lr': 0.00048783781492903145, 'samples': 3217152, 'steps': 16755, 'loss/train': 1.1818318367004395} 08/30/2021 16:15:36 - INFO - __main__ - Step 16757: {'lr': 0.00048783617982298594, 'samples': 3217344, 'steps': 16756, 'loss/train': 1.7665915489196777} 08/30/2021 16:15:37 - INFO - __main__ - Step 16758: {'lr': 0.00048783454460977517, 'samples': 3217536, 'steps': 16757, 'loss/train': 2.1646244525909424} 08/30/2021 16:15:38 - INFO - __main__ - Step 16759: {'lr': 0.00048783290928939985, 'samples': 3217728, 'steps': 16758, 'loss/train': 1.5340540409088135} 08/30/2021 16:15:39 - INFO - __main__ - Step 16760: {'lr': 0.00048783127386186064, 'samples': 3217920, 'steps': 16759, 'loss/train': 2.2429051399230957} 08/30/2021 16:15:39 - INFO - __main__ - Step 16761: {'lr': 0.00048782963832715834, 'samples': 3218112, 'steps': 16760, 'loss/train': 2.0270144939422607} 08/30/2021 16:15:39 - INFO - __main__ - Step 16762: {'lr': 0.0004878280026852937, 'samples': 3218304, 'steps': 16761, 'loss/train': 1.3143175840377808} 08/30/2021 16:15:40 - INFO - __main__ - Step 16763: {'lr': 0.00048782636693626736, 'samples': 3218496, 'steps': 16762, 'loss/train': 1.7576345205307007} 08/30/2021 16:15:42 - INFO - __main__ - Step 16764: {'lr': 0.0004878247310800802, 'samples': 3218688, 'steps': 16763, 'loss/train': 0.20639830827713013} 08/30/2021 16:15:43 - INFO - __main__ - Step 16765: {'lr': 0.0004878230951167328, 'samples': 3218880, 'steps': 16764, 'loss/train': 0.18535570800304413} 08/30/2021 16:15:43 - INFO - __main__ - Step 16766: {'lr': 0.0004878214590462261, 'samples': 3219072, 'steps': 16765, 'loss/train': 0.671101987361908} 08/30/2021 16:15:44 - INFO - __main__ - Step 16767: {'lr': 0.0004878198228685607, 'samples': 3219264, 'steps': 16766, 'loss/train': 1.7018426656723022} 08/30/2021 16:15:44 - INFO - __main__ - Step 16768: {'lr': 0.00048781818658373734, 'samples': 3219456, 'steps': 16767, 'loss/train': 1.3425238132476807} 08/30/2021 16:15:44 - INFO - __main__ - Step 16769: {'lr': 0.00048781655019175676, 'samples': 3219648, 'steps': 16768, 'loss/train': 1.5089943408966064} 08/30/2021 16:15:46 - INFO - __main__ - Step 16770: {'lr': 0.00048781491369261965, 'samples': 3219840, 'steps': 16769, 'loss/train': 1.4512887001037598} 08/30/2021 16:15:46 - INFO - __main__ - Step 16771: {'lr': 0.00048781327708632695, 'samples': 3220032, 'steps': 16770, 'loss/train': 0.9616290926933289} 08/30/2021 16:15:47 - INFO - __main__ - Step 16772: {'lr': 0.0004878116403728792, 'samples': 3220224, 'steps': 16771, 'loss/train': 1.8094511032104492} 08/30/2021 16:15:47 - INFO - __main__ - Step 16773: {'lr': 0.0004878100035522771, 'samples': 3220416, 'steps': 16772, 'loss/train': 1.944799542427063} 08/30/2021 16:15:47 - INFO - __main__ - Step 16774: {'lr': 0.00048780836662452154, 'samples': 3220608, 'steps': 16773, 'loss/train': 1.8739910125732422} 08/30/2021 16:15:49 - INFO - __main__ - Step 16775: {'lr': 0.00048780672958961325, 'samples': 3220800, 'steps': 16774, 'loss/train': 2.0597751140594482} 08/30/2021 16:15:49 - INFO - __main__ - Step 16776: {'lr': 0.0004878050924475529, 'samples': 3220992, 'steps': 16775, 'loss/train': 1.400397777557373} 08/30/2021 16:15:50 - INFO - __main__ - Step 16777: {'lr': 0.00048780345519834124, 'samples': 3221184, 'steps': 16776, 'loss/train': 1.1562952995300293} 08/30/2021 16:15:50 - INFO - __main__ - Step 16778: {'lr': 0.000487801817841979, 'samples': 3221376, 'steps': 16777, 'loss/train': 0.9177966117858887} 08/30/2021 16:15:50 - INFO - __main__ - Step 16779: {'lr': 0.0004878001803784669, 'samples': 3221568, 'steps': 16778, 'loss/train': 1.7204710245132446} 08/30/2021 16:15:51 - INFO - __main__ - Step 16780: {'lr': 0.00048779854280780576, 'samples': 3221760, 'steps': 16779, 'loss/train': 1.5911046266555786} 08/30/2021 16:15:52 - INFO - __main__ - Step 16781: {'lr': 0.00048779690512999627, 'samples': 3221952, 'steps': 16780, 'loss/train': 1.4506856203079224} 08/30/2021 16:15:53 - INFO - __main__ - Step 16782: {'lr': 0.0004877952673450391, 'samples': 3222144, 'steps': 16781, 'loss/train': 1.4995564222335815} 08/30/2021 16:15:53 - INFO - __main__ - Step 16783: {'lr': 0.0004877936294529351, 'samples': 3222336, 'steps': 16782, 'loss/train': 0.9332077503204346} 08/30/2021 16:15:53 - INFO - __main__ - Step 16784: {'lr': 0.00048779199145368494, 'samples': 3222528, 'steps': 16783, 'loss/train': 1.4664751291275024} 08/30/2021 16:15:54 - INFO - __main__ - Step 16785: {'lr': 0.0004877903533472894, 'samples': 3222720, 'steps': 16784, 'loss/train': 1.3890423774719238} 08/30/2021 16:15:55 - INFO - __main__ - Step 16786: {'lr': 0.0004877887151337492, 'samples': 3222912, 'steps': 16785, 'loss/train': 0.972080409526825} 08/30/2021 16:15:56 - INFO - __main__ - Step 16787: {'lr': 0.0004877870768130651, 'samples': 3223104, 'steps': 16786, 'loss/train': 1.5679256916046143} 08/30/2021 16:15:56 - INFO - __main__ - Step 16788: {'lr': 0.0004877854383852377, 'samples': 3223296, 'steps': 16787, 'loss/train': 1.64675772190094} 08/30/2021 16:15:57 - INFO - __main__ - Step 16789: {'lr': 0.000487783799850268, 'samples': 3223488, 'steps': 16788, 'loss/train': 1.936020016670227} 08/30/2021 16:15:57 - INFO - __main__ - Step 16790: {'lr': 0.00048778216120815644, 'samples': 3223680, 'steps': 16789, 'loss/train': 1.426086187362671} 08/30/2021 16:15:58 - INFO - __main__ - Step 16791: {'lr': 0.00048778052245890404, 'samples': 3223872, 'steps': 16790, 'loss/train': 1.7422831058502197} 08/30/2021 16:15:59 - INFO - __main__ - Step 16792: {'lr': 0.0004877788836025113, 'samples': 3224064, 'steps': 16791, 'loss/train': 1.311118245124817} 08/30/2021 16:15:59 - INFO - __main__ - Step 16793: {'lr': 0.0004877772446389791, 'samples': 3224256, 'steps': 16792, 'loss/train': 1.623799204826355} 08/30/2021 16:16:00 - INFO - __main__ - Step 16794: {'lr': 0.0004877756055683082, 'samples': 3224448, 'steps': 16793, 'loss/train': 2.0339138507843018} 08/30/2021 16:16:00 - INFO - __main__ - Step 16795: {'lr': 0.0004877739663904992, 'samples': 3224640, 'steps': 16794, 'loss/train': 1.47018301486969} 08/30/2021 16:16:02 - INFO - __main__ - Step 16796: {'lr': 0.00048777232710555296, 'samples': 3224832, 'steps': 16795, 'loss/train': 1.961258888244629} 08/30/2021 16:16:02 - INFO - __main__ - Step 16797: {'lr': 0.0004877706877134702, 'samples': 3225024, 'steps': 16796, 'loss/train': 1.7934300899505615} 08/30/2021 16:16:03 - INFO - __main__ - Step 16798: {'lr': 0.0004877690482142516, 'samples': 3225216, 'steps': 16797, 'loss/train': 1.6483789682388306} 08/30/2021 16:16:03 - INFO - __main__ - Step 16799: {'lr': 0.0004877674086078979, 'samples': 3225408, 'steps': 16798, 'loss/train': 1.7061437368392944} 08/30/2021 16:16:03 - INFO - __main__ - Step 16800: {'lr': 0.0004877657688944099, 'samples': 3225600, 'steps': 16799, 'loss/train': 1.4893561601638794} 08/30/2021 16:16:04 - INFO - __main__ - Step 16801: {'lr': 0.0004877641290737884, 'samples': 3225792, 'steps': 16800, 'loss/train': 1.5711534023284912} 08/30/2021 16:16:05 - INFO - __main__ - Step 16802: {'lr': 0.000487762489146034, 'samples': 3225984, 'steps': 16801, 'loss/train': 0.10147201269865036} 08/30/2021 16:16:06 - INFO - __main__ - Step 16803: {'lr': 0.0004877608491111475, 'samples': 3226176, 'steps': 16802, 'loss/train': 1.5733031034469604} 08/30/2021 16:16:06 - INFO - __main__ - Step 16804: {'lr': 0.0004877592089691296, 'samples': 3226368, 'steps': 16803, 'loss/train': 1.1071979999542236} 08/30/2021 16:16:06 - INFO - __main__ - Step 16805: {'lr': 0.00048775756871998106, 'samples': 3226560, 'steps': 16804, 'loss/train': 1.2677621841430664} 08/30/2021 16:16:07 - INFO - __main__ - Step 16806: {'lr': 0.0004877559283637026, 'samples': 3226752, 'steps': 16805, 'loss/train': 1.9323376417160034} 08/30/2021 16:16:08 - INFO - __main__ - Step 16807: {'lr': 0.0004877542879002951, 'samples': 3226944, 'steps': 16806, 'loss/train': 1.47136390209198} 08/30/2021 16:16:09 - INFO - __main__ - Step 16808: {'lr': 0.0004877526473297591, 'samples': 3227136, 'steps': 16807, 'loss/train': 1.6244699954986572} 08/30/2021 16:16:09 - INFO - __main__ - Step 16809: {'lr': 0.0004877510066520954, 'samples': 3227328, 'steps': 16808, 'loss/train': 1.7713903188705444} 08/30/2021 16:16:09 - INFO - __main__ - Step 16810: {'lr': 0.0004877493658673048, 'samples': 3227520, 'steps': 16809, 'loss/train': 2.050170660018921} 08/30/2021 16:16:10 - INFO - __main__ - Step 16811: {'lr': 0.00048774772497538806, 'samples': 3227712, 'steps': 16810, 'loss/train': 2.4477641582489014} 08/30/2021 16:16:11 - INFO - __main__ - Step 16812: {'lr': 0.0004877460839763458, 'samples': 3227904, 'steps': 16811, 'loss/train': 1.2472822666168213} 08/30/2021 16:16:12 - INFO - __main__ - Step 16813: {'lr': 0.0004877444428701788, 'samples': 3228096, 'steps': 16812, 'loss/train': 1.5294315814971924} 08/30/2021 16:16:12 - INFO - __main__ - Step 16814: {'lr': 0.0004877428016568879, 'samples': 3228288, 'steps': 16813, 'loss/train': 2.1093595027923584} 08/30/2021 16:16:13 - INFO - __main__ - Step 16815: {'lr': 0.00048774116033647373, 'samples': 3228480, 'steps': 16814, 'loss/train': 1.6045103073120117} 08/30/2021 16:16:13 - INFO - __main__ - Step 16816: {'lr': 0.0004877395189089371, 'samples': 3228672, 'steps': 16815, 'loss/train': 2.525740146636963} 08/30/2021 16:16:15 - INFO - __main__ - Step 16817: {'lr': 0.00048773787737427867, 'samples': 3228864, 'steps': 16816, 'loss/train': 1.4167840480804443} 08/30/2021 16:16:16 - INFO - __main__ - Step 16818: {'lr': 0.0004877362357324992, 'samples': 3229056, 'steps': 16817, 'loss/train': 2.2660722732543945} 08/30/2021 16:16:16 - INFO - __main__ - Step 16819: {'lr': 0.0004877345939835995, 'samples': 3229248, 'steps': 16818, 'loss/train': 1.4358583688735962} 08/30/2021 16:16:16 - INFO - __main__ - Step 16820: {'lr': 0.0004877329521275802, 'samples': 3229440, 'steps': 16819, 'loss/train': 1.6625192165374756} 08/30/2021 16:16:17 - INFO - __main__ - Step 16821: {'lr': 0.0004877313101644422, 'samples': 3229632, 'steps': 16820, 'loss/train': 1.6703619956970215} 08/30/2021 16:16:17 - INFO - __main__ - Step 16822: {'lr': 0.000487729668094186, 'samples': 3229824, 'steps': 16821, 'loss/train': 2.0354955196380615} 08/30/2021 16:16:18 - INFO - __main__ - Step 16823: {'lr': 0.0004877280259168125, 'samples': 3230016, 'steps': 16822, 'loss/train': 1.4470092058181763} 08/30/2021 16:16:19 - INFO - __main__ - Step 16824: {'lr': 0.0004877263836323226, 'samples': 3230208, 'steps': 16823, 'loss/train': 1.4930732250213623} 08/30/2021 16:16:19 - INFO - __main__ - Step 16825: {'lr': 0.00048772474124071663, 'samples': 3230400, 'steps': 16824, 'loss/train': 1.8102967739105225} 08/30/2021 16:16:20 - INFO - __main__ - Step 16826: {'lr': 0.0004877230987419957, 'samples': 3230592, 'steps': 16825, 'loss/train': 1.7201083898544312} 08/30/2021 16:16:20 - INFO - __main__ - Step 16827: {'lr': 0.00048772145613616035, 'samples': 3230784, 'steps': 16826, 'loss/train': 1.827391505241394} 08/30/2021 16:16:22 - INFO - __main__ - Step 16828: {'lr': 0.00048771981342321145, 'samples': 3230976, 'steps': 16827, 'loss/train': 1.4888100624084473} 08/30/2021 16:16:22 - INFO - __main__ - Step 16829: {'lr': 0.0004877181706031496, 'samples': 3231168, 'steps': 16828, 'loss/train': 1.685758352279663} 08/30/2021 16:16:23 - INFO - __main__ - Step 16830: {'lr': 0.00048771652767597563, 'samples': 3231360, 'steps': 16829, 'loss/train': 1.369916558265686} 08/30/2021 16:16:23 - INFO - __main__ - Step 16831: {'lr': 0.0004877148846416903, 'samples': 3231552, 'steps': 16830, 'loss/train': 1.7621418237686157} 08/30/2021 16:16:23 - INFO - __main__ - Step 16832: {'lr': 0.0004877132415002943, 'samples': 3231744, 'steps': 16831, 'loss/train': 1.6573519706726074} 08/30/2021 16:16:25 - INFO - __main__ - Step 16833: {'lr': 0.00048771159825178827, 'samples': 3231936, 'steps': 16832, 'loss/train': 1.4401060342788696} 08/30/2021 16:16:26 - INFO - __main__ - Step 16834: {'lr': 0.0004877099548961732, 'samples': 3232128, 'steps': 16833, 'loss/train': 1.8510234355926514} 08/30/2021 16:16:26 - INFO - __main__ - Step 16835: {'lr': 0.0004877083114334496, 'samples': 3232320, 'steps': 16834, 'loss/train': 1.7695484161376953} 08/30/2021 16:16:27 - INFO - __main__ - Step 16836: {'lr': 0.0004877066678636184, 'samples': 3232512, 'steps': 16835, 'loss/train': 1.2076002359390259} 08/30/2021 16:16:27 - INFO - __main__ - Step 16837: {'lr': 0.00048770502418668017, 'samples': 3232704, 'steps': 16836, 'loss/train': 1.9213272333145142} 08/30/2021 16:16:27 - INFO - __main__ - Step 16838: {'lr': 0.00048770338040263574, 'samples': 3232896, 'steps': 16837, 'loss/train': 1.7977879047393799} 08/30/2021 16:16:28 - INFO - __main__ - Step 16839: {'lr': 0.00048770173651148586, 'samples': 3233088, 'steps': 16838, 'loss/train': 1.4382543563842773} 08/30/2021 16:16:29 - INFO - __main__ - Step 16840: {'lr': 0.0004877000925132312, 'samples': 3233280, 'steps': 16839, 'loss/train': 1.8501614332199097} 08/30/2021 16:16:30 - INFO - __main__ - Step 16841: {'lr': 0.0004876984484078726, 'samples': 3233472, 'steps': 16840, 'loss/train': 2.0979394912719727} 08/30/2021 16:16:30 - INFO - __main__ - Step 16842: {'lr': 0.0004876968041954107, 'samples': 3233664, 'steps': 16841, 'loss/train': 1.6127644777297974} 08/30/2021 16:16:30 - INFO - __main__ - Step 16843: {'lr': 0.00048769515987584624, 'samples': 3233856, 'steps': 16842, 'loss/train': 1.70716392993927} 08/30/2021 16:16:31 - INFO - __main__ - Step 16844: {'lr': 0.0004876935154491801, 'samples': 3234048, 'steps': 16843, 'loss/train': 1.579373836517334} 08/30/2021 16:16:32 - INFO - __main__ - Step 16845: {'lr': 0.00048769187091541287, 'samples': 3234240, 'steps': 16844, 'loss/train': 2.0687344074249268} 08/30/2021 16:16:33 - INFO - __main__ - Step 16846: {'lr': 0.0004876902262745454, 'samples': 3234432, 'steps': 16845, 'loss/train': 1.246543288230896} 08/30/2021 16:16:33 - INFO - __main__ - Step 16847: {'lr': 0.00048768858152657837, 'samples': 3234624, 'steps': 16846, 'loss/train': 1.0815016031265259} 08/30/2021 16:16:33 - INFO - __main__ - Step 16848: {'lr': 0.0004876869366715125, 'samples': 3234816, 'steps': 16847, 'loss/train': 2.131363868713379} 08/30/2021 16:16:34 - INFO - __main__ - Step 16849: {'lr': 0.0004876852917093486, 'samples': 3235008, 'steps': 16848, 'loss/train': 1.6099157333374023} 08/30/2021 16:16:35 - INFO - __main__ - Step 16850: {'lr': 0.0004876836466400874, 'samples': 3235200, 'steps': 16849, 'loss/train': 1.794905185699463} 08/30/2021 16:16:36 - INFO - __main__ - Step 16851: {'lr': 0.00048768200146372955, 'samples': 3235392, 'steps': 16850, 'loss/train': 1.6487356424331665} 08/30/2021 16:16:36 - INFO - __main__ - Step 16852: {'lr': 0.00048768035618027597, 'samples': 3235584, 'steps': 16851, 'loss/train': 1.405745506286621} 08/30/2021 16:16:37 - INFO - __main__ - Step 16853: {'lr': 0.00048767871078972717, 'samples': 3235776, 'steps': 16852, 'loss/train': 0.655771791934967} 08/30/2021 16:16:37 - INFO - __main__ - Step 16854: {'lr': 0.000487677065292084, 'samples': 3235968, 'steps': 16853, 'loss/train': 0.8521744012832642} 08/30/2021 16:16:38 - INFO - __main__ - Step 16855: {'lr': 0.0004876754196873473, 'samples': 3236160, 'steps': 16854, 'loss/train': 1.6467833518981934} 08/30/2021 16:16:39 - INFO - __main__ - Step 16856: {'lr': 0.00048767377397551773, 'samples': 3236352, 'steps': 16855, 'loss/train': 1.3419854640960693} 08/30/2021 16:16:39 - INFO - __main__ - Step 16857: {'lr': 0.00048767212815659593, 'samples': 3236544, 'steps': 16856, 'loss/train': 1.296749234199524} 08/30/2021 16:16:39 - INFO - __main__ - Step 16858: {'lr': 0.0004876704822305828, 'samples': 3236736, 'steps': 16857, 'loss/train': 1.3770450353622437} 08/30/2021 16:16:40 - INFO - __main__ - Step 16859: {'lr': 0.00048766883619747906, 'samples': 3236928, 'steps': 16858, 'loss/train': 1.717189908027649} 08/30/2021 16:16:40 - INFO - __main__ - Step 16860: {'lr': 0.00048766719005728534, 'samples': 3237120, 'steps': 16859, 'loss/train': 1.4536820650100708} 08/30/2021 16:16:42 - INFO - __main__ - Step 16861: {'lr': 0.0004876655438100024, 'samples': 3237312, 'steps': 16860, 'loss/train': 1.5952472686767578} 08/30/2021 16:16:42 - INFO - __main__ - Step 16862: {'lr': 0.00048766389745563113, 'samples': 3237504, 'steps': 16861, 'loss/train': 1.6588070392608643} 08/30/2021 16:16:43 - INFO - __main__ - Step 16863: {'lr': 0.00048766225099417215, 'samples': 3237696, 'steps': 16862, 'loss/train': 2.1189510822296143} 08/30/2021 16:16:43 - INFO - __main__ - Step 16864: {'lr': 0.0004876606044256262, 'samples': 3237888, 'steps': 16863, 'loss/train': 1.515399694442749} 08/30/2021 16:16:43 - INFO - __main__ - Step 16865: {'lr': 0.0004876589577499941, 'samples': 3238080, 'steps': 16864, 'loss/train': 1.8756680488586426} 08/30/2021 16:16:45 - INFO - __main__ - Step 16866: {'lr': 0.0004876573109672765, 'samples': 3238272, 'steps': 16865, 'loss/train': 1.465890645980835} 08/30/2021 16:16:45 - INFO - __main__ - Step 16867: {'lr': 0.0004876556640774742, 'samples': 3238464, 'steps': 16866, 'loss/train': 0.9735254049301147} 08/30/2021 16:16:45 - INFO - __main__ - Step 16868: {'lr': 0.0004876540170805879, 'samples': 3238656, 'steps': 16867, 'loss/train': 1.6697684526443481} 08/30/2021 16:16:46 - INFO - __main__ - Step 16869: {'lr': 0.00048765236997661845, 'samples': 3238848, 'steps': 16868, 'loss/train': 1.7975212335586548} 08/30/2021 16:16:46 - INFO - __main__ - Step 16870: {'lr': 0.0004876507227655664, 'samples': 3239040, 'steps': 16869, 'loss/train': 2.108999252319336} 08/30/2021 16:16:48 - INFO - __main__ - Step 16871: {'lr': 0.00048764907544743264, 'samples': 3239232, 'steps': 16870, 'loss/train': 1.7371759414672852} 08/30/2021 16:16:49 - INFO - __main__ - Step 16872: {'lr': 0.0004876474280222179, 'samples': 3239424, 'steps': 16871, 'loss/train': 1.6256959438323975} 08/30/2021 16:16:49 - INFO - __main__ - Step 16873: {'lr': 0.00048764578048992284, 'samples': 3239616, 'steps': 16872, 'loss/train': 1.8462085723876953} 08/30/2021 16:16:49 - INFO - __main__ - Step 16874: {'lr': 0.0004876441328505483, 'samples': 3239808, 'steps': 16873, 'loss/train': 1.6450989246368408} 08/30/2021 16:16:50 - INFO - __main__ - Step 16875: {'lr': 0.000487642485104095, 'samples': 3240000, 'steps': 16874, 'loss/train': 1.564517617225647} 08/30/2021 16:16:50 - INFO - __main__ - Step 16876: {'lr': 0.00048764083725056365, 'samples': 3240192, 'steps': 16875, 'loss/train': 1.8679288625717163} 08/30/2021 16:16:52 - INFO - __main__ - Step 16877: {'lr': 0.00048763918928995496, 'samples': 3240384, 'steps': 16876, 'loss/train': 0.08533859252929688} 08/30/2021 16:16:53 - INFO - __main__ - Step 16878: {'lr': 0.00048763754122226977, 'samples': 3240576, 'steps': 16877, 'loss/train': 0.792040228843689} 08/30/2021 16:16:53 - INFO - __main__ - Step 16879: {'lr': 0.00048763589304750876, 'samples': 3240768, 'steps': 16878, 'loss/train': 1.5878849029541016} 08/30/2021 16:16:53 - INFO - __main__ - Step 16880: {'lr': 0.0004876342447656727, 'samples': 3240960, 'steps': 16879, 'loss/train': 1.5004578828811646} 08/30/2021 16:16:54 - INFO - __main__ - Step 16881: {'lr': 0.00048763259637676226, 'samples': 3241152, 'steps': 16880, 'loss/train': 0.9142868518829346} 08/30/2021 16:16:54 - INFO - __main__ - Step 16882: {'lr': 0.00048763094788077834, 'samples': 3241344, 'steps': 16881, 'loss/train': 2.1745200157165527} 08/30/2021 16:16:56 - INFO - __main__ - Step 16883: {'lr': 0.0004876292992777215, 'samples': 3241536, 'steps': 16882, 'loss/train': 0.9276759624481201} 08/30/2021 16:16:56 - INFO - __main__ - Step 16884: {'lr': 0.00048762765056759255, 'samples': 3241728, 'steps': 16883, 'loss/train': 1.70012366771698} 08/30/2021 16:16:56 - INFO - __main__ - Step 16885: {'lr': 0.00048762600175039227, 'samples': 3241920, 'steps': 16884, 'loss/train': 1.8063913583755493} 08/30/2021 16:16:57 - INFO - __main__ - Step 16886: {'lr': 0.0004876243528261214, 'samples': 3242112, 'steps': 16885, 'loss/train': 1.6086015701293945} 08/30/2021 16:16:57 - INFO - __main__ - Step 16887: {'lr': 0.0004876227037947807, 'samples': 3242304, 'steps': 16886, 'loss/train': 1.947364091873169} 08/30/2021 16:16:59 - INFO - __main__ - Step 16888: {'lr': 0.0004876210546563707, 'samples': 3242496, 'steps': 16887, 'loss/train': 1.076502799987793} 08/30/2021 16:16:59 - INFO - __main__ - Step 16889: {'lr': 0.0004876194054108926, 'samples': 3242688, 'steps': 16888, 'loss/train': 1.7061368227005005} 08/30/2021 16:16:59 - INFO - __main__ - Step 16890: {'lr': 0.0004876177560583466, 'samples': 3242880, 'steps': 16889, 'loss/train': 1.4884884357452393} 08/30/2021 16:17:00 - INFO - __main__ - Step 16891: {'lr': 0.00048761610659873387, 'samples': 3243072, 'steps': 16890, 'loss/train': 1.8173021078109741} 08/30/2021 16:17:00 - INFO - __main__ - Step 16892: {'lr': 0.0004876144570320549, 'samples': 3243264, 'steps': 16891, 'loss/train': 1.4878637790679932} 08/30/2021 16:17:01 - INFO - __main__ - Step 16893: {'lr': 0.0004876128073583106, 'samples': 3243456, 'steps': 16892, 'loss/train': 1.981358289718628} 08/30/2021 16:17:02 - INFO - __main__ - Step 16894: {'lr': 0.00048761115757750155, 'samples': 3243648, 'steps': 16893, 'loss/train': 1.865716814994812} 08/30/2021 16:17:02 - INFO - __main__ - Step 16895: {'lr': 0.00048760950768962863, 'samples': 3243840, 'steps': 16894, 'loss/train': 1.4976617097854614} 08/30/2021 16:17:03 - INFO - __main__ - Step 16896: {'lr': 0.00048760785769469254, 'samples': 3244032, 'steps': 16895, 'loss/train': 1.4995694160461426} 08/30/2021 16:17:03 - INFO - __main__ - Step 16897: {'lr': 0.00048760620759269403, 'samples': 3244224, 'steps': 16896, 'loss/train': 1.84534752368927} 08/30/2021 16:17:04 - INFO - __main__ - Step 16898: {'lr': 0.00048760455738363376, 'samples': 3244416, 'steps': 16897, 'loss/train': 1.0716979503631592} 08/30/2021 16:17:05 - INFO - __main__ - Step 16899: {'lr': 0.0004876029070675126, 'samples': 3244608, 'steps': 16898, 'loss/train': 1.7161740064620972} 08/30/2021 16:17:05 - INFO - __main__ - Step 16900: {'lr': 0.0004876012566443312, 'samples': 3244800, 'steps': 16899, 'loss/train': 1.3478282690048218} 08/30/2021 16:17:06 - INFO - __main__ - Step 16901: {'lr': 0.00048759960611409036, 'samples': 3244992, 'steps': 16900, 'loss/train': 1.9062011241912842} 08/30/2021 16:17:06 - INFO - __main__ - Step 16902: {'lr': 0.00048759795547679083, 'samples': 3245184, 'steps': 16901, 'loss/train': 2.2854104042053223} 08/30/2021 16:17:06 - INFO - __main__ - Step 16903: {'lr': 0.00048759630473243327, 'samples': 3245376, 'steps': 16902, 'loss/train': 1.3685877323150635} 08/30/2021 16:17:08 - INFO - __main__ - Step 16904: {'lr': 0.00048759465388101855, 'samples': 3245568, 'steps': 16903, 'loss/train': 1.9079225063323975} 08/30/2021 16:17:08 - INFO - __main__ - Step 16905: {'lr': 0.0004875930029225473, 'samples': 3245760, 'steps': 16904, 'loss/train': 0.7501497864723206} 08/30/2021 16:17:09 - INFO - __main__ - Step 16906: {'lr': 0.0004875913518570203, 'samples': 3245952, 'steps': 16905, 'loss/train': 1.463302493095398} 08/30/2021 16:17:09 - INFO - __main__ - Step 16907: {'lr': 0.0004875897006844383, 'samples': 3246144, 'steps': 16906, 'loss/train': 2.013986825942993} 08/30/2021 16:17:09 - INFO - __main__ - Step 16908: {'lr': 0.00048758804940480203, 'samples': 3246336, 'steps': 16907, 'loss/train': 1.6306395530700684} 08/30/2021 16:17:11 - INFO - __main__ - Step 16909: {'lr': 0.0004875863980181123, 'samples': 3246528, 'steps': 16908, 'loss/train': 0.6218293309211731} 08/30/2021 16:17:11 - INFO - __main__ - Step 16910: {'lr': 0.0004875847465243698, 'samples': 3246720, 'steps': 16909, 'loss/train': 2.3276655673980713} 08/30/2021 16:17:12 - INFO - __main__ - Step 16911: {'lr': 0.00048758309492357533, 'samples': 3246912, 'steps': 16910, 'loss/train': 3.1968994140625} 08/30/2021 16:17:12 - INFO - __main__ - Step 16912: {'lr': 0.0004875814432157295, 'samples': 3247104, 'steps': 16911, 'loss/train': 1.6495847702026367} 08/30/2021 16:17:12 - INFO - __main__ - Step 16913: {'lr': 0.0004875797914008332, 'samples': 3247296, 'steps': 16912, 'loss/train': 2.0352587699890137} 08/30/2021 16:17:14 - INFO - __main__ - Step 16914: {'lr': 0.00048757813947888706, 'samples': 3247488, 'steps': 16913, 'loss/train': 1.3868038654327393} 08/30/2021 16:17:14 - INFO - __main__ - Step 16915: {'lr': 0.0004875764874498919, 'samples': 3247680, 'steps': 16914, 'loss/train': 1.3998552560806274} 08/30/2021 16:17:15 - INFO - __main__ - Step 16916: {'lr': 0.00048757483531384837, 'samples': 3247872, 'steps': 16915, 'loss/train': 1.9597069025039673} 08/30/2021 16:17:15 - INFO - __main__ - Step 16917: {'lr': 0.0004875731830707574, 'samples': 3248064, 'steps': 16916, 'loss/train': 1.2749173641204834} 08/30/2021 16:17:15 - INFO - __main__ - Step 16918: {'lr': 0.00048757153072061954, 'samples': 3248256, 'steps': 16917, 'loss/train': 1.8954534530639648} 08/30/2021 16:17:17 - INFO - __main__ - Step 16919: {'lr': 0.0004875698782634357, 'samples': 3248448, 'steps': 16918, 'loss/train': 2.011024236679077} 08/30/2021 16:17:17 - INFO - __main__ - Step 16920: {'lr': 0.00048756822569920647, 'samples': 3248640, 'steps': 16919, 'loss/train': 1.3850997686386108} 08/30/2021 16:17:18 - INFO - __main__ - Step 16921: {'lr': 0.0004875665730279326, 'samples': 3248832, 'steps': 16920, 'loss/train': 1.5362807512283325} 08/30/2021 16:17:18 - INFO - __main__ - Step 16922: {'lr': 0.000487564920249615, 'samples': 3249024, 'steps': 16921, 'loss/train': 1.6729166507720947} 08/30/2021 16:17:18 - INFO - __main__ - Step 16923: {'lr': 0.00048756326736425427, 'samples': 3249216, 'steps': 16922, 'loss/train': 1.3989808559417725} 08/30/2021 16:17:20 - INFO - __main__ - Step 16924: {'lr': 0.00048756161437185126, 'samples': 3249408, 'steps': 16923, 'loss/train': 1.8012539148330688} 08/30/2021 16:17:20 - INFO - __main__ - Step 16925: {'lr': 0.0004875599612724066, 'samples': 3249600, 'steps': 16924, 'loss/train': 1.931175947189331} 08/30/2021 16:17:21 - INFO - __main__ - Step 16926: {'lr': 0.00048755830806592105, 'samples': 3249792, 'steps': 16925, 'loss/train': 1.0830150842666626} 08/30/2021 16:17:21 - INFO - __main__ - Step 16927: {'lr': 0.00048755665475239547, 'samples': 3249984, 'steps': 16926, 'loss/train': 1.3054875135421753} 08/30/2021 16:17:21 - INFO - __main__ - Step 16928: {'lr': 0.0004875550013318305, 'samples': 3250176, 'steps': 16927, 'loss/train': 1.578044056892395} 08/30/2021 16:17:22 - INFO - __main__ - Step 16929: {'lr': 0.0004875533478042269, 'samples': 3250368, 'steps': 16928, 'loss/train': 1.6108318567276} 08/30/2021 16:17:24 - INFO - __main__ - Step 16930: {'lr': 0.00048755169416958544, 'samples': 3250560, 'steps': 16929, 'loss/train': 1.500242829322815} 08/30/2021 16:17:24 - INFO - __main__ - Step 16931: {'lr': 0.00048755004042790685, 'samples': 3250752, 'steps': 16930, 'loss/train': 1.882196307182312} 08/30/2021 16:17:25 - INFO - __main__ - Step 16932: {'lr': 0.00048754838657919186, 'samples': 3250944, 'steps': 16931, 'loss/train': 1.561686635017395} 08/30/2021 16:17:25 - INFO - __main__ - Step 16933: {'lr': 0.00048754673262344124, 'samples': 3251136, 'steps': 16932, 'loss/train': 0.8742133975028992} 08/30/2021 16:17:25 - INFO - __main__ - Step 16934: {'lr': 0.00048754507856065574, 'samples': 3251328, 'steps': 16933, 'loss/train': 1.7597050666809082} 08/30/2021 16:17:27 - INFO - __main__ - Step 16935: {'lr': 0.0004875434243908361, 'samples': 3251520, 'steps': 16934, 'loss/train': 5.917540550231934} 08/30/2021 16:17:27 - INFO - __main__ - Step 16936: {'lr': 0.00048754177011398303, 'samples': 3251712, 'steps': 16935, 'loss/train': 1.3282630443572998} 08/30/2021 16:17:28 - INFO - __main__ - Step 16937: {'lr': 0.0004875401157300973, 'samples': 3251904, 'steps': 16936, 'loss/train': 1.3805826902389526} 08/30/2021 16:17:28 - INFO - __main__ - Step 16938: {'lr': 0.00048753846123917964, 'samples': 3252096, 'steps': 16937, 'loss/train': 1.926552414894104} 08/30/2021 16:17:28 - INFO - __main__ - Step 16939: {'lr': 0.0004875368066412309, 'samples': 3252288, 'steps': 16938, 'loss/train': 1.5819123983383179} 08/30/2021 16:17:30 - INFO - __main__ - Step 16940: {'lr': 0.00048753515193625165, 'samples': 3252480, 'steps': 16939, 'loss/train': 1.2893445491790771} 08/30/2021 16:17:30 - INFO - __main__ - Step 16941: {'lr': 0.00048753349712424277, 'samples': 3252672, 'steps': 16940, 'loss/train': 0.8502808809280396} 08/30/2021 16:17:31 - INFO - __main__ - Step 16942: {'lr': 0.00048753184220520497, 'samples': 3252864, 'steps': 16941, 'loss/train': 1.6763042211532593} 08/30/2021 16:17:31 - INFO - __main__ - Step 16943: {'lr': 0.000487530187179139, 'samples': 3253056, 'steps': 16942, 'loss/train': 0.5161139369010925} 08/30/2021 16:17:31 - INFO - __main__ - Step 16944: {'lr': 0.00048752853204604555, 'samples': 3253248, 'steps': 16943, 'loss/train': 1.5600448846817017} 08/30/2021 16:17:33 - INFO - __main__ - Step 16945: {'lr': 0.00048752687680592545, 'samples': 3253440, 'steps': 16944, 'loss/train': 1.602253794670105} 08/30/2021 16:17:33 - INFO - __main__ - Step 16946: {'lr': 0.00048752522145877937, 'samples': 3253632, 'steps': 16945, 'loss/train': 1.7223378419876099} 08/30/2021 16:17:34 - INFO - __main__ - Step 16947: {'lr': 0.0004875235660046081, 'samples': 3253824, 'steps': 16946, 'loss/train': 0.6119934320449829} 08/30/2021 16:17:34 - INFO - __main__ - Step 16948: {'lr': 0.0004875219104434124, 'samples': 3254016, 'steps': 16947, 'loss/train': 1.73008131980896} 08/30/2021 16:17:34 - INFO - __main__ - Step 16949: {'lr': 0.0004875202547751929, 'samples': 3254208, 'steps': 16948, 'loss/train': 1.3419551849365234} 08/30/2021 16:17:35 - INFO - __main__ - Step 16950: {'lr': 0.00048751859899995054, 'samples': 3254400, 'steps': 16949, 'loss/train': 1.8059403896331787} 08/30/2021 16:17:36 - INFO - __main__ - Step 16951: {'lr': 0.0004875169431176859, 'samples': 3254592, 'steps': 16950, 'loss/train': 2.4468488693237305} 08/30/2021 16:17:37 - INFO - __main__ - Step 16952: {'lr': 0.0004875152871283999, 'samples': 3254784, 'steps': 16951, 'loss/train': 1.3676382303237915} 08/30/2021 16:17:37 - INFO - __main__ - Step 16953: {'lr': 0.0004875136310320931, 'samples': 3254976, 'steps': 16952, 'loss/train': 0.8390756845474243} 08/30/2021 16:17:37 - INFO - __main__ - Step 16954: {'lr': 0.0004875119748287663, 'samples': 3255168, 'steps': 16953, 'loss/train': 1.3089519739151} 08/30/2021 16:17:38 - INFO - __main__ - Step 16955: {'lr': 0.0004875103185184203, 'samples': 3255360, 'steps': 16954, 'loss/train': 1.563284158706665} 08/30/2021 16:17:39 - INFO - __main__ - Step 16956: {'lr': 0.00048750866210105583, 'samples': 3255552, 'steps': 16955, 'loss/train': 1.4730861186981201} 08/30/2021 16:17:40 - INFO - __main__ - Step 16957: {'lr': 0.0004875070055766736, 'samples': 3255744, 'steps': 16956, 'loss/train': 1.0444947481155396} 08/30/2021 16:17:40 - INFO - __main__ - Step 16958: {'lr': 0.0004875053489452743, 'samples': 3255936, 'steps': 16957, 'loss/train': 1.472135066986084} 08/30/2021 16:17:40 - INFO - __main__ - Step 16959: {'lr': 0.00048750369220685886, 'samples': 3256128, 'steps': 16958, 'loss/train': 1.045244812965393} 08/30/2021 16:17:41 - INFO - __main__ - Step 16960: {'lr': 0.0004875020353614279, 'samples': 3256320, 'steps': 16959, 'loss/train': 2.2059497833251953} 08/30/2021 16:17:42 - INFO - __main__ - Step 16961: {'lr': 0.0004875003784089822, 'samples': 3256512, 'steps': 16960, 'loss/train': 1.6468404531478882} 08/30/2021 16:17:43 - INFO - __main__ - Step 16962: {'lr': 0.00048749872134952243, 'samples': 3256704, 'steps': 16961, 'loss/train': 1.4637099504470825} 08/30/2021 16:17:43 - INFO - __main__ - Step 16963: {'lr': 0.0004874970641830495, 'samples': 3256896, 'steps': 16962, 'loss/train': 1.3961182832717896} 08/30/2021 16:17:43 - INFO - __main__ - Step 16964: {'lr': 0.000487495406909564, 'samples': 3257088, 'steps': 16963, 'loss/train': 1.7496854066848755} 08/30/2021 16:17:44 - INFO - __main__ - Step 16965: {'lr': 0.00048749374952906677, 'samples': 3257280, 'steps': 16964, 'loss/train': 1.5075517892837524} 08/30/2021 16:17:46 - INFO - __main__ - Step 16966: {'lr': 0.0004874920920415584, 'samples': 3257472, 'steps': 16965, 'loss/train': 1.5595650672912598} 08/30/2021 16:17:46 - INFO - __main__ - Step 16967: {'lr': 0.0004874904344470399, 'samples': 3257664, 'steps': 16966, 'loss/train': 1.7632176876068115} 08/30/2021 16:17:46 - INFO - __main__ - Step 16968: {'lr': 0.00048748877674551183, 'samples': 3257856, 'steps': 16967, 'loss/train': 1.9016896486282349} 08/30/2021 16:17:47 - INFO - __main__ - Step 16969: {'lr': 0.00048748711893697495, 'samples': 3258048, 'steps': 16968, 'loss/train': 1.3011797666549683} 08/30/2021 16:17:47 - INFO - __main__ - Step 16970: {'lr': 0.0004874854610214301, 'samples': 3258240, 'steps': 16969, 'loss/train': 0.07831119745969772} 08/30/2021 16:17:48 - INFO - __main__ - Step 16971: {'lr': 0.00048748380299887793, 'samples': 3258432, 'steps': 16970, 'loss/train': 1.6787441968917847} 08/30/2021 16:17:48 - INFO - __main__ - Step 16972: {'lr': 0.0004874821448693192, 'samples': 3258624, 'steps': 16971, 'loss/train': 1.504599928855896} 08/30/2021 16:17:49 - INFO - __main__ - Step 16973: {'lr': 0.00048748048663275475, 'samples': 3258816, 'steps': 16972, 'loss/train': 1.9052436351776123} 08/30/2021 16:17:50 - INFO - __main__ - Step 16974: {'lr': 0.00048747882828918524, 'samples': 3259008, 'steps': 16973, 'loss/train': 1.4593864679336548} 08/30/2021 16:17:50 - INFO - __main__ - Step 16975: {'lr': 0.0004874771698386113, 'samples': 3259200, 'steps': 16974, 'loss/train': 1.39486563205719} 08/30/2021 16:17:51 - INFO - __main__ - Step 16976: {'lr': 0.00048747551128103397, 'samples': 3259392, 'steps': 16975, 'loss/train': 1.2716879844665527} 08/30/2021 16:17:51 - INFO - __main__ - Step 16977: {'lr': 0.00048747385261645377, 'samples': 3259584, 'steps': 16976, 'loss/train': 1.0684585571289062} 08/30/2021 16:17:52 - INFO - __main__ - Step 16978: {'lr': 0.0004874721938448715, 'samples': 3259776, 'steps': 16977, 'loss/train': 2.4069674015045166} 08/30/2021 16:17:53 - INFO - __main__ - Step 16979: {'lr': 0.000487470534966288, 'samples': 3259968, 'steps': 16978, 'loss/train': 1.359895944595337} 08/30/2021 16:17:53 - INFO - __main__ - Step 16980: {'lr': 0.0004874688759807039, 'samples': 3260160, 'steps': 16979, 'loss/train': 1.7185837030410767} 08/30/2021 16:17:53 - INFO - __main__ - Step 16981: {'lr': 0.00048746721688812004, 'samples': 3260352, 'steps': 16980, 'loss/train': 1.7675763368606567} 08/30/2021 16:17:54 - INFO - __main__ - Step 16982: {'lr': 0.00048746555768853703, 'samples': 3260544, 'steps': 16981, 'loss/train': 2.0602288246154785} 08/30/2021 16:17:56 - INFO - __main__ - Step 16983: {'lr': 0.00048746389838195573, 'samples': 3260736, 'steps': 16982, 'loss/train': 1.249222755432129} 08/30/2021 16:17:57 - INFO - __main__ - Step 16984: {'lr': 0.0004874622389683768, 'samples': 3260928, 'steps': 16983, 'loss/train': 1.7813916206359863} 08/30/2021 16:17:57 - INFO - __main__ - Step 16985: {'lr': 0.0004874605794478012, 'samples': 3261120, 'steps': 16984, 'loss/train': 1.7750695943832397} 08/30/2021 16:17:57 - INFO - __main__ - Step 16986: {'lr': 0.0004874589198202294, 'samples': 3261312, 'steps': 16985, 'loss/train': 2.1372036933898926} 08/30/2021 16:17:58 - INFO - __main__ - Step 16987: {'lr': 0.0004874572600856624, 'samples': 3261504, 'steps': 16986, 'loss/train': 1.801600456237793} 08/30/2021 16:17:59 - INFO - __main__ - Step 16988: {'lr': 0.0004874556002441007, 'samples': 3261696, 'steps': 16987, 'loss/train': 1.3790847063064575} 08/30/2021 16:18:00 - INFO - __main__ - Step 16989: {'lr': 0.0004874539402955452, 'samples': 3261888, 'steps': 16988, 'loss/train': 2.015305519104004} 08/30/2021 16:18:00 - INFO - __main__ - Step 16990: {'lr': 0.00048745228023999666, 'samples': 3262080, 'steps': 16989, 'loss/train': 1.1904144287109375} 08/30/2021 16:18:00 - INFO - __main__ - Step 16991: {'lr': 0.0004874506200774557, 'samples': 3262272, 'steps': 16990, 'loss/train': 1.6295344829559326} 08/30/2021 16:18:01 - INFO - __main__ - Step 16992: {'lr': 0.00048744895980792327, 'samples': 3262464, 'steps': 16991, 'loss/train': 1.7436455488204956} 08/30/2021 16:18:02 - INFO - __main__ - Step 16993: {'lr': 0.00048744729943139993, 'samples': 3262656, 'steps': 16992, 'loss/train': 1.2896414995193481} 08/30/2021 16:18:03 - INFO - __main__ - Step 16994: {'lr': 0.0004874456389478865, 'samples': 3262848, 'steps': 16993, 'loss/train': 1.5997600555419922} 08/30/2021 16:18:03 - INFO - __main__ - Step 16995: {'lr': 0.00048744397835738377, 'samples': 3263040, 'steps': 16994, 'loss/train': 1.8420839309692383} 08/30/2021 16:18:03 - INFO - __main__ - Step 16996: {'lr': 0.00048744231765989246, 'samples': 3263232, 'steps': 16995, 'loss/train': 1.8090988397598267} 08/30/2021 16:18:04 - INFO - __main__ - Step 16997: {'lr': 0.0004874406568554132, 'samples': 3263424, 'steps': 16996, 'loss/train': 1.8278638124465942} 08/30/2021 16:18:05 - INFO - __main__ - Step 16998: {'lr': 0.0004874389959439469, 'samples': 3263616, 'steps': 16997, 'loss/train': 1.401595950126648} 08/30/2021 16:18:06 - INFO - __main__ - Step 16999: {'lr': 0.0004874373349254943, 'samples': 3263808, 'steps': 16998, 'loss/train': 1.4432423114776611} 08/30/2021 16:18:06 - INFO - __main__ - Step 17000: {'lr': 0.00048743567380005604, 'samples': 3264000, 'steps': 16999, 'loss/train': 1.7033408880233765} 08/30/2021 16:18:06 - INFO - __main__ - Step 17001: {'lr': 0.000487434012567633, 'samples': 3264192, 'steps': 17000, 'loss/train': 0.7083486318588257} 08/30/2021 16:18:07 - INFO - __main__ - Step 17002: {'lr': 0.0004874323512282258, 'samples': 3264384, 'steps': 17001, 'loss/train': 1.2216070890426636} 08/30/2021 16:18:08 - INFO - __main__ - Step 17003: {'lr': 0.00048743068978183523, 'samples': 3264576, 'steps': 17002, 'loss/train': 1.9648942947387695} 08/30/2021 16:18:09 - INFO - __main__ - Step 17004: {'lr': 0.00048742902822846215, 'samples': 3264768, 'steps': 17003, 'loss/train': 1.9739830493927002} 08/30/2021 16:18:09 - INFO - __main__ - Step 17005: {'lr': 0.0004874273665681071, 'samples': 3264960, 'steps': 17004, 'loss/train': 1.4854813814163208} 08/30/2021 16:18:09 - INFO - __main__ - Step 17006: {'lr': 0.00048742570480077096, 'samples': 3265152, 'steps': 17005, 'loss/train': 1.954255223274231} 08/30/2021 16:18:10 - INFO - __main__ - Step 17007: {'lr': 0.0004874240429264545, 'samples': 3265344, 'steps': 17006, 'loss/train': 1.6127092838287354} 08/30/2021 16:18:10 - INFO - __main__ - Step 17008: {'lr': 0.00048742238094515844, 'samples': 3265536, 'steps': 17007, 'loss/train': 1.5501658916473389} 08/30/2021 16:18:11 - INFO - __main__ - Step 17009: {'lr': 0.00048742071885688354, 'samples': 3265728, 'steps': 17008, 'loss/train': 1.9240108728408813} 08/30/2021 16:18:12 - INFO - __main__ - Step 17010: {'lr': 0.00048741905666163047, 'samples': 3265920, 'steps': 17009, 'loss/train': 2.3126652240753174} 08/30/2021 16:18:12 - INFO - __main__ - Step 17011: {'lr': 0.00048741739435940003, 'samples': 3266112, 'steps': 17010, 'loss/train': 1.563551664352417} 08/30/2021 16:18:13 - INFO - __main__ - Step 17012: {'lr': 0.000487415731950193, 'samples': 3266304, 'steps': 17011, 'loss/train': 1.6391255855560303} 08/30/2021 16:18:13 - INFO - __main__ - Step 17013: {'lr': 0.0004874140694340101, 'samples': 3266496, 'steps': 17012, 'loss/train': 1.1839629411697388} 08/30/2021 16:18:15 - INFO - __main__ - Step 17014: {'lr': 0.0004874124068108521, 'samples': 3266688, 'steps': 17013, 'loss/train': 1.763357162475586} 08/30/2021 16:18:15 - INFO - __main__ - Step 17015: {'lr': 0.00048741074408071975, 'samples': 3266880, 'steps': 17014, 'loss/train': 1.1405329704284668} 08/30/2021 16:18:16 - INFO - __main__ - Step 17016: {'lr': 0.00048740908124361373, 'samples': 3267072, 'steps': 17015, 'loss/train': 1.4558064937591553} 08/30/2021 16:18:16 - INFO - __main__ - Step 17017: {'lr': 0.0004874074182995349, 'samples': 3267264, 'steps': 17016, 'loss/train': 0.0474298894405365} 08/30/2021 16:18:16 - INFO - __main__ - Step 17018: {'lr': 0.0004874057552484839, 'samples': 3267456, 'steps': 17017, 'loss/train': 1.5617492198944092} 08/30/2021 16:18:17 - INFO - __main__ - Step 17019: {'lr': 0.00048740409209046154, 'samples': 3267648, 'steps': 17018, 'loss/train': 1.7178077697753906} 08/30/2021 16:18:18 - INFO - __main__ - Step 17020: {'lr': 0.0004874024288254686, 'samples': 3267840, 'steps': 17019, 'loss/train': 1.9327551126480103} 08/30/2021 16:18:18 - INFO - __main__ - Step 17021: {'lr': 0.00048740076545350573, 'samples': 3268032, 'steps': 17020, 'loss/train': 1.848136067390442} 08/30/2021 16:18:19 - INFO - __main__ - Step 17022: {'lr': 0.00048739910197457376, 'samples': 3268224, 'steps': 17021, 'loss/train': 1.6528129577636719} 08/30/2021 16:18:19 - INFO - __main__ - Step 17023: {'lr': 0.00048739743838867344, 'samples': 3268416, 'steps': 17022, 'loss/train': 2.532574415206909} 08/30/2021 16:18:19 - INFO - __main__ - Step 17024: {'lr': 0.00048739577469580545, 'samples': 3268608, 'steps': 17023, 'loss/train': 1.4743624925613403} 08/30/2021 16:18:22 - INFO - __main__ - Step 17025: {'lr': 0.0004873941108959706, 'samples': 3268800, 'steps': 17024, 'loss/train': 1.819540023803711} 08/30/2021 16:18:22 - INFO - __main__ - Step 17026: {'lr': 0.0004873924469891697, 'samples': 3268992, 'steps': 17025, 'loss/train': 1.5908654928207397} 08/30/2021 16:18:23 - INFO - __main__ - Step 17027: {'lr': 0.00048739078297540335, 'samples': 3269184, 'steps': 17026, 'loss/train': 1.6285433769226074} 08/30/2021 16:18:23 - INFO - __main__ - Step 17028: {'lr': 0.00048738911885467243, 'samples': 3269376, 'steps': 17027, 'loss/train': 1.983981966972351} 08/30/2021 16:18:23 - INFO - __main__ - Step 17029: {'lr': 0.00048738745462697754, 'samples': 3269568, 'steps': 17028, 'loss/train': 1.3978523015975952} 08/30/2021 16:18:24 - INFO - __main__ - Step 17030: {'lr': 0.0004873857902923196, 'samples': 3269760, 'steps': 17029, 'loss/train': 1.835018515586853} 08/30/2021 16:18:24 - INFO - __main__ - Step 17031: {'lr': 0.00048738412585069927, 'samples': 3269952, 'steps': 17030, 'loss/train': 1.1982173919677734} 08/30/2021 16:18:26 - INFO - __main__ - Step 17032: {'lr': 0.00048738246130211734, 'samples': 3270144, 'steps': 17031, 'loss/train': 0.9439342617988586} 08/30/2021 16:18:26 - INFO - __main__ - Step 17033: {'lr': 0.00048738079664657454, 'samples': 3270336, 'steps': 17032, 'loss/train': 1.631165623664856} 08/30/2021 16:18:26 - INFO - __main__ - Step 17034: {'lr': 0.00048737913188407156, 'samples': 3270528, 'steps': 17033, 'loss/train': 1.7660175561904907} 08/30/2021 16:18:27 - INFO - __main__ - Step 17035: {'lr': 0.00048737746701460927, 'samples': 3270720, 'steps': 17034, 'loss/train': 2.2325189113616943} 08/30/2021 16:18:27 - INFO - __main__ - Step 17036: {'lr': 0.0004873758020381883, 'samples': 3270912, 'steps': 17035, 'loss/train': 2.220383882522583} 08/30/2021 16:18:29 - INFO - __main__ - Step 17037: {'lr': 0.00048737413695480947, 'samples': 3271104, 'steps': 17036, 'loss/train': 1.8013945817947388} 08/30/2021 16:18:30 - INFO - __main__ - Step 17038: {'lr': 0.00048737247176447354, 'samples': 3271296, 'steps': 17037, 'loss/train': 2.1499481201171875} 08/30/2021 16:18:30 - INFO - __main__ - Step 17039: {'lr': 0.0004873708064671812, 'samples': 3271488, 'steps': 17038, 'loss/train': 1.095421314239502} 08/30/2021 16:18:30 - INFO - __main__ - Step 17040: {'lr': 0.0004873691410629333, 'samples': 3271680, 'steps': 17039, 'loss/train': 1.4788717031478882} 08/30/2021 16:18:31 - INFO - __main__ - Step 17041: {'lr': 0.0004873674755517304, 'samples': 3271872, 'steps': 17040, 'loss/train': 1.1645203828811646} 08/30/2021 16:18:32 - INFO - __main__ - Step 17042: {'lr': 0.00048736580993357357, 'samples': 3272064, 'steps': 17041, 'loss/train': 0.893046498298645} 08/30/2021 16:18:33 - INFO - __main__ - Step 17043: {'lr': 0.0004873641442084632, 'samples': 3272256, 'steps': 17042, 'loss/train': 1.681810736656189} 08/30/2021 16:18:33 - INFO - __main__ - Step 17044: {'lr': 0.00048736247837640037, 'samples': 3272448, 'steps': 17043, 'loss/train': 1.2126652002334595} 08/30/2021 16:18:33 - INFO - __main__ - Step 17045: {'lr': 0.0004873608124373855, 'samples': 3272640, 'steps': 17044, 'loss/train': 1.578004240989685} 08/30/2021 16:18:34 - INFO - __main__ - Step 17046: {'lr': 0.00048735914639141964, 'samples': 3272832, 'steps': 17045, 'loss/train': 1.7768607139587402} 08/30/2021 16:18:35 - INFO - __main__ - Step 17047: {'lr': 0.00048735748023850337, 'samples': 3273024, 'steps': 17046, 'loss/train': 1.973023772239685} 08/30/2021 16:18:36 - INFO - __main__ - Step 17048: {'lr': 0.00048735581397863745, 'samples': 3273216, 'steps': 17047, 'loss/train': 1.459733247756958} 08/30/2021 16:18:36 - INFO - __main__ - Step 17049: {'lr': 0.0004873541476118227, 'samples': 3273408, 'steps': 17048, 'loss/train': 1.3695586919784546} 08/30/2021 16:18:37 - INFO - __main__ - Step 17050: {'lr': 0.00048735248113805976, 'samples': 3273600, 'steps': 17049, 'loss/train': 1.7251688241958618} 08/30/2021 16:18:37 - INFO - __main__ - Step 17051: {'lr': 0.0004873508145573495, 'samples': 3273792, 'steps': 17050, 'loss/train': 1.272658109664917} 08/30/2021 16:18:37 - INFO - __main__ - Step 17052: {'lr': 0.00048734914786969266, 'samples': 3273984, 'steps': 17051, 'loss/train': 1.9978035688400269} 08/30/2021 16:18:39 - INFO - __main__ - Step 17053: {'lr': 0.00048734748107509, 'samples': 3274176, 'steps': 17052, 'loss/train': 1.6371781826019287} 08/30/2021 16:18:39 - INFO - __main__ - Step 17054: {'lr': 0.0004873458141735421, 'samples': 3274368, 'steps': 17053, 'loss/train': 1.8606921434402466} 08/30/2021 16:18:39 - INFO - __main__ - Step 17055: {'lr': 0.0004873441471650499, 'samples': 3274560, 'steps': 17054, 'loss/train': 1.903680682182312} 08/30/2021 16:18:40 - INFO - __main__ - Step 17056: {'lr': 0.00048734248004961414, 'samples': 3274752, 'steps': 17055, 'loss/train': 1.8469626903533936} 08/30/2021 16:18:40 - INFO - __main__ - Step 17057: {'lr': 0.00048734081282723543, 'samples': 3274944, 'steps': 17056, 'loss/train': 1.2959022521972656} 08/30/2021 16:18:42 - INFO - __main__ - Step 17058: {'lr': 0.00048733914549791465, 'samples': 3275136, 'steps': 17057, 'loss/train': 0.8788344860076904} 08/30/2021 16:18:42 - INFO - __main__ - Step 17059: {'lr': 0.0004873374780616525, 'samples': 3275328, 'steps': 17058, 'loss/train': 1.9548438787460327} 08/30/2021 16:18:42 - INFO - __main__ - Step 17060: {'lr': 0.00048733581051844976, 'samples': 3275520, 'steps': 17059, 'loss/train': 1.576919674873352} 08/30/2021 16:18:43 - INFO - __main__ - Step 17061: {'lr': 0.00048733414286830716, 'samples': 3275712, 'steps': 17060, 'loss/train': 1.4760609865188599} 08/30/2021 16:18:43 - INFO - __main__ - Step 17062: {'lr': 0.00048733247511122547, 'samples': 3275904, 'steps': 17061, 'loss/train': 1.4664009809494019} 08/30/2021 16:18:45 - INFO - __main__ - Step 17063: {'lr': 0.00048733080724720545, 'samples': 3276096, 'steps': 17062, 'loss/train': 1.7509276866912842} 08/30/2021 16:18:46 - INFO - __main__ - Step 17064: {'lr': 0.00048732913927624776, 'samples': 3276288, 'steps': 17063, 'loss/train': 1.422742247581482} 08/30/2021 16:18:46 - INFO - __main__ - Step 17065: {'lr': 0.0004873274711983533, 'samples': 3276480, 'steps': 17064, 'loss/train': 1.491871953010559} 08/30/2021 16:18:47 - INFO - __main__ - Step 17066: {'lr': 0.0004873258030135227, 'samples': 3276672, 'steps': 17065, 'loss/train': 1.6416592597961426} 08/30/2021 16:18:47 - INFO - __main__ - Step 17067: {'lr': 0.0004873241347217567, 'samples': 3276864, 'steps': 17066, 'loss/train': 2.1945347785949707} 08/30/2021 16:18:47 - INFO - __main__ - Step 17068: {'lr': 0.0004873224663230562, 'samples': 3277056, 'steps': 17067, 'loss/train': 3.0288026332855225} 08/30/2021 16:18:49 - INFO - __main__ - Step 17069: {'lr': 0.0004873207978174219, 'samples': 3277248, 'steps': 17068, 'loss/train': 3.829235792160034} 08/30/2021 16:18:49 - INFO - __main__ - Step 17070: {'lr': 0.00048731912920485444, 'samples': 3277440, 'steps': 17069, 'loss/train': 2.0071985721588135} 08/30/2021 16:18:50 - INFO - __main__ - Step 17071: {'lr': 0.0004873174604853546, 'samples': 3277632, 'steps': 17070, 'loss/train': 1.8288429975509644} 08/30/2021 16:18:50 - INFO - __main__ - Step 17072: {'lr': 0.00048731579165892325, 'samples': 3277824, 'steps': 17071, 'loss/train': 1.354732871055603} 08/30/2021 16:18:50 - INFO - __main__ - Step 17073: {'lr': 0.000487314122725561, 'samples': 3278016, 'steps': 17072, 'loss/train': 1.5520434379577637} 08/30/2021 16:18:52 - INFO - __main__ - Step 17074: {'lr': 0.00048731245368526877, 'samples': 3278208, 'steps': 17073, 'loss/train': 1.3054972887039185} 08/30/2021 16:18:53 - INFO - __main__ - Step 17075: {'lr': 0.0004873107845380471, 'samples': 3278400, 'steps': 17074, 'loss/train': 2.0592572689056396} 08/30/2021 16:18:53 - INFO - __main__ - Step 17076: {'lr': 0.00048730911528389686, 'samples': 3278592, 'steps': 17075, 'loss/train': 2.3109729290008545} 08/30/2021 16:18:53 - INFO - __main__ - Step 17077: {'lr': 0.0004873074459228188, 'samples': 3278784, 'steps': 17076, 'loss/train': 1.7390919923782349} 08/30/2021 16:18:54 - INFO - __main__ - Step 17078: {'lr': 0.0004873057764548138, 'samples': 3278976, 'steps': 17077, 'loss/train': 1.2778682708740234} 08/30/2021 16:18:54 - INFO - __main__ - Step 17079: {'lr': 0.00048730410687988237, 'samples': 3279168, 'steps': 17078, 'loss/train': 1.43776535987854} 08/30/2021 16:18:55 - INFO - __main__ - Step 17080: {'lr': 0.00048730243719802535, 'samples': 3279360, 'steps': 17079, 'loss/train': 1.517069935798645} 08/30/2021 16:18:56 - INFO - __main__ - Step 17081: {'lr': 0.00048730076740924355, 'samples': 3279552, 'steps': 17080, 'loss/train': 1.8498196601867676} 08/30/2021 16:18:56 - INFO - __main__ - Step 17082: {'lr': 0.0004872990975135377, 'samples': 3279744, 'steps': 17081, 'loss/train': 1.755913496017456} 08/30/2021 16:18:57 - INFO - __main__ - Step 17083: {'lr': 0.0004872974275109085, 'samples': 3279936, 'steps': 17082, 'loss/train': 1.8197604417800903} 08/30/2021 16:18:57 - INFO - __main__ - Step 17084: {'lr': 0.00048729575740135675, 'samples': 3280128, 'steps': 17083, 'loss/train': 2.2922885417938232} 08/30/2021 16:18:59 - INFO - __main__ - Step 17085: {'lr': 0.0004872940871848832, 'samples': 3280320, 'steps': 17084, 'loss/train': 1.6462880373001099} 08/30/2021 16:18:59 - INFO - __main__ - Step 17086: {'lr': 0.00048729241686148864, 'samples': 3280512, 'steps': 17085, 'loss/train': 1.4661798477172852} 08/30/2021 16:18:59 - INFO - __main__ - Step 17087: {'lr': 0.0004872907464311737, 'samples': 3280704, 'steps': 17086, 'loss/train': 1.6990941762924194} 08/30/2021 16:19:00 - INFO - __main__ - Step 17088: {'lr': 0.0004872890758939392, 'samples': 3280896, 'steps': 17087, 'loss/train': 1.6704976558685303} 08/30/2021 16:19:00 - INFO - __main__ - Step 17089: {'lr': 0.00048728740524978597, 'samples': 3281088, 'steps': 17088, 'loss/train': 2.290745973587036} 08/30/2021 16:19:03 - INFO - __main__ - Step 17090: {'lr': 0.00048728573449871473, 'samples': 3281280, 'steps': 17089, 'loss/train': 1.4036996364593506} 08/30/2021 16:19:03 - INFO - __main__ - Step 17091: {'lr': 0.0004872840636407261, 'samples': 3281472, 'steps': 17090, 'loss/train': 1.581344723701477} 08/30/2021 16:19:03 - INFO - __main__ - Step 17092: {'lr': 0.00048728239267582096, 'samples': 3281664, 'steps': 17091, 'loss/train': 1.573412537574768} 08/30/2021 16:19:04 - INFO - __main__ - Step 17093: {'lr': 0.00048728072160400006, 'samples': 3281856, 'steps': 17092, 'loss/train': 0.24032923579216003} 08/30/2021 16:19:04 - INFO - __main__ - Step 17094: {'lr': 0.0004872790504252641, 'samples': 3282048, 'steps': 17093, 'loss/train': 0.16618132591247559} 08/30/2021 16:19:04 - INFO - __main__ - Step 17095: {'lr': 0.0004872773791396139, 'samples': 3282240, 'steps': 17094, 'loss/train': 1.9471571445465088} 08/30/2021 16:19:05 - INFO - __main__ - Step 17096: {'lr': 0.0004872757077470502, 'samples': 3282432, 'steps': 17095, 'loss/train': 0.5481041669845581} 08/30/2021 16:19:05 - INFO - __main__ - Step 17097: {'lr': 0.0004872740362475737, 'samples': 3282624, 'steps': 17096, 'loss/train': 0.5585260987281799} 08/30/2021 16:19:07 - INFO - __main__ - Step 17098: {'lr': 0.0004872723646411851, 'samples': 3282816, 'steps': 17097, 'loss/train': 1.5546623468399048} 08/30/2021 16:19:08 - INFO - __main__ - Step 17099: {'lr': 0.0004872706929278853, 'samples': 3283008, 'steps': 17098, 'loss/train': 1.0834232568740845} 08/30/2021 16:19:08 - INFO - __main__ - Step 17100: {'lr': 0.000487269021107675, 'samples': 3283200, 'steps': 17099, 'loss/train': 1.696337103843689} 08/30/2021 16:19:08 - INFO - __main__ - Step 17101: {'lr': 0.0004872673491805549, 'samples': 3283392, 'steps': 17100, 'loss/train': 1.5764994621276855} 08/30/2021 16:19:09 - INFO - __main__ - Step 17102: {'lr': 0.0004872656771465259, 'samples': 3283584, 'steps': 17101, 'loss/train': 1.586539387702942} 08/30/2021 16:19:10 - INFO - __main__ - Step 17103: {'lr': 0.00048726400500558856, 'samples': 3283776, 'steps': 17102, 'loss/train': 1.5957640409469604} 08/30/2021 16:19:11 - INFO - __main__ - Step 17104: {'lr': 0.0004872623327577437, 'samples': 3283968, 'steps': 17103, 'loss/train': 2.2525582313537598} 08/30/2021 16:19:11 - INFO - __main__ - Step 17105: {'lr': 0.0004872606604029921, 'samples': 3284160, 'steps': 17104, 'loss/train': 1.8458601236343384} 08/30/2021 16:19:11 - INFO - __main__ - Step 17106: {'lr': 0.00048725898794133455, 'samples': 3284352, 'steps': 17105, 'loss/train': 1.9900256395339966} 08/30/2021 16:19:12 - INFO - __main__ - Step 17107: {'lr': 0.00048725731537277173, 'samples': 3284544, 'steps': 17106, 'loss/train': 1.4694170951843262} 08/30/2021 16:19:13 - INFO - __main__ - Step 17108: {'lr': 0.0004872556426973044, 'samples': 3284736, 'steps': 17107, 'loss/train': 1.8389586210250854} 08/30/2021 16:19:14 - INFO - __main__ - Step 17109: {'lr': 0.0004872539699149334, 'samples': 3284928, 'steps': 17108, 'loss/train': 1.6983451843261719} 08/30/2021 16:19:14 - INFO - __main__ - Step 17110: {'lr': 0.0004872522970256594, 'samples': 3285120, 'steps': 17109, 'loss/train': 1.7530301809310913} 08/30/2021 16:19:15 - INFO - __main__ - Step 17111: {'lr': 0.00048725062402948314, 'samples': 3285312, 'steps': 17110, 'loss/train': 0.3163411319255829} 08/30/2021 16:19:15 - INFO - __main__ - Step 17112: {'lr': 0.00048724895092640546, 'samples': 3285504, 'steps': 17111, 'loss/train': 1.2892173528671265} 08/30/2021 16:19:17 - INFO - __main__ - Step 17113: {'lr': 0.00048724727771642706, 'samples': 3285696, 'steps': 17112, 'loss/train': 1.6487714052200317} 08/30/2021 16:19:17 - INFO - __main__ - Step 17114: {'lr': 0.00048724560439954867, 'samples': 3285888, 'steps': 17113, 'loss/train': 1.8985477685928345} 08/30/2021 16:19:18 - INFO - __main__ - Step 17115: {'lr': 0.00048724393097577113, 'samples': 3286080, 'steps': 17114, 'loss/train': 0.21476341784000397} 08/30/2021 16:19:18 - INFO - __main__ - Step 17116: {'lr': 0.0004872422574450951, 'samples': 3286272, 'steps': 17115, 'loss/train': 1.6858916282653809} 08/30/2021 16:19:18 - INFO - __main__ - Step 17117: {'lr': 0.0004872405838075213, 'samples': 3286464, 'steps': 17116, 'loss/train': 1.4407038688659668} 08/30/2021 16:19:20 - INFO - __main__ - Step 17118: {'lr': 0.00048723891006305066, 'samples': 3286656, 'steps': 17117, 'loss/train': 1.684228539466858} 08/30/2021 16:19:20 - INFO - __main__ - Step 17119: {'lr': 0.0004872372362116838, 'samples': 3286848, 'steps': 17118, 'loss/train': 1.4467246532440186} 08/30/2021 16:19:21 - INFO - __main__ - Step 17120: {'lr': 0.0004872355622534215, 'samples': 3287040, 'steps': 17119, 'loss/train': 1.9959315061569214} 08/30/2021 16:19:21 - INFO - __main__ - Step 17121: {'lr': 0.0004872338881882644, 'samples': 3287232, 'steps': 17120, 'loss/train': 1.707873821258545} 08/30/2021 16:19:21 - INFO - __main__ - Step 17122: {'lr': 0.00048723221401621354, 'samples': 3287424, 'steps': 17121, 'loss/train': 2.1110117435455322} 08/30/2021 16:19:23 - INFO - __main__ - Step 17123: {'lr': 0.0004872305397372694, 'samples': 3287616, 'steps': 17122, 'loss/train': 0.8126787543296814} 08/30/2021 16:19:23 - INFO - __main__ - Step 17124: {'lr': 0.0004872288653514329, 'samples': 3287808, 'steps': 17123, 'loss/train': 1.9742519855499268} 08/30/2021 16:19:24 - INFO - __main__ - Step 17125: {'lr': 0.0004872271908587047, 'samples': 3288000, 'steps': 17124, 'loss/train': 1.7569471597671509} 08/30/2021 16:19:24 - INFO - __main__ - Step 17126: {'lr': 0.0004872255162590856, 'samples': 3288192, 'steps': 17125, 'loss/train': 1.9443386793136597} 08/30/2021 16:19:25 - INFO - __main__ - Step 17127: {'lr': 0.0004872238415525764, 'samples': 3288384, 'steps': 17126, 'loss/train': 0.16956979036331177} 08/30/2021 16:19:25 - INFO - __main__ - Step 17128: {'lr': 0.0004872221667391777, 'samples': 3288576, 'steps': 17127, 'loss/train': 2.152531623840332} 08/30/2021 16:19:27 - INFO - __main__ - Step 17129: {'lr': 0.00048722049181889037, 'samples': 3288768, 'steps': 17128, 'loss/train': 1.5011897087097168} 08/30/2021 16:19:27 - INFO - __main__ - Step 17130: {'lr': 0.0004872188167917152, 'samples': 3288960, 'steps': 17129, 'loss/train': 1.6086961030960083} 08/30/2021 16:19:27 - INFO - __main__ - Step 17131: {'lr': 0.00048721714165765286, 'samples': 3289152, 'steps': 17130, 'loss/train': 1.6895132064819336} 08/30/2021 16:19:28 - INFO - __main__ - Step 17132: {'lr': 0.00048721546641670413, 'samples': 3289344, 'steps': 17131, 'loss/train': 1.262113332748413} 08/30/2021 16:19:28 - INFO - __main__ - Step 17133: {'lr': 0.00048721379106886976, 'samples': 3289536, 'steps': 17132, 'loss/train': 1.8208268880844116} 08/30/2021 16:19:29 - INFO - __main__ - Step 17134: {'lr': 0.0004872121156141506, 'samples': 3289728, 'steps': 17133, 'loss/train': 1.3156644105911255} 08/30/2021 16:19:30 - INFO - __main__ - Step 17135: {'lr': 0.0004872104400525472, 'samples': 3289920, 'steps': 17134, 'loss/train': 1.5294270515441895} 08/30/2021 16:19:30 - INFO - __main__ - Step 17136: {'lr': 0.0004872087643840605, 'samples': 3290112, 'steps': 17135, 'loss/train': 1.184144139289856} 08/30/2021 16:19:31 - INFO - __main__ - Step 17137: {'lr': 0.00048720708860869116, 'samples': 3290304, 'steps': 17136, 'loss/train': 1.7141838073730469} 08/30/2021 16:19:31 - INFO - __main__ - Step 17138: {'lr': 0.00048720541272644004, 'samples': 3290496, 'steps': 17137, 'loss/train': 0.6089520454406738} 08/30/2021 16:19:32 - INFO - __main__ - Step 17139: {'lr': 0.00048720373673730773, 'samples': 3290688, 'steps': 17138, 'loss/train': 1.5148826837539673} 08/30/2021 16:19:33 - INFO - __main__ - Step 17140: {'lr': 0.00048720206064129516, 'samples': 3290880, 'steps': 17139, 'loss/train': 1.9033597707748413} 08/30/2021 16:19:33 - INFO - __main__ - Step 17141: {'lr': 0.0004872003844384029, 'samples': 3291072, 'steps': 17140, 'loss/train': 1.4932576417922974} 08/30/2021 16:19:33 - INFO - __main__ - Step 17142: {'lr': 0.0004871987081286319, 'samples': 3291264, 'steps': 17141, 'loss/train': 0.6825220584869385} 08/30/2021 16:19:34 - INFO - __main__ - Step 17143: {'lr': 0.0004871970317119828, 'samples': 3291456, 'steps': 17142, 'loss/train': 1.1307752132415771} 08/30/2021 16:19:35 - INFO - __main__ - Step 17144: {'lr': 0.00048719535518845634, 'samples': 3291648, 'steps': 17143, 'loss/train': 1.6785632371902466} 08/30/2021 16:19:36 - INFO - __main__ - Step 17145: {'lr': 0.0004871936785580533, 'samples': 3291840, 'steps': 17144, 'loss/train': 1.5717003345489502} 08/30/2021 16:19:36 - INFO - __main__ - Step 17146: {'lr': 0.0004871920018207745, 'samples': 3292032, 'steps': 17145, 'loss/train': 1.947385549545288} 08/30/2021 16:19:37 - INFO - __main__ - Step 17147: {'lr': 0.0004871903249766206, 'samples': 3292224, 'steps': 17146, 'loss/train': 0.9774880409240723} 08/30/2021 16:19:37 - INFO - __main__ - Step 17148: {'lr': 0.0004871886480255925, 'samples': 3292416, 'steps': 17147, 'loss/train': 1.7427949905395508} 08/30/2021 16:19:39 - INFO - __main__ - Step 17149: {'lr': 0.0004871869709676907, 'samples': 3292608, 'steps': 17148, 'loss/train': 1.4562371969223022} 08/30/2021 16:19:39 - INFO - __main__ - Step 17150: {'lr': 0.0004871852938029162, 'samples': 3292800, 'steps': 17149, 'loss/train': 1.6578058004379272} 08/30/2021 16:19:40 - INFO - __main__ - Step 17151: {'lr': 0.00048718361653126975, 'samples': 3292992, 'steps': 17150, 'loss/train': 1.7739109992980957} 08/30/2021 16:19:40 - INFO - __main__ - Step 17152: {'lr': 0.0004871819391527519, 'samples': 3293184, 'steps': 17151, 'loss/train': 1.5501478910446167} 08/30/2021 16:19:40 - INFO - __main__ - Step 17153: {'lr': 0.0004871802616673636, 'samples': 3293376, 'steps': 17152, 'loss/train': 1.8780291080474854} 08/30/2021 16:19:41 - INFO - __main__ - Step 17154: {'lr': 0.00048717858407510545, 'samples': 3293568, 'steps': 17153, 'loss/train': 1.376879096031189} 08/30/2021 16:19:42 - INFO - __main__ - Step 17155: {'lr': 0.0004871769063759783, 'samples': 3293760, 'steps': 17154, 'loss/train': 1.3158879280090332} 08/30/2021 16:19:43 - INFO - __main__ - Step 17156: {'lr': 0.000487175228569983, 'samples': 3293952, 'steps': 17155, 'loss/train': 1.6738362312316895} 08/30/2021 16:19:43 - INFO - __main__ - Step 17157: {'lr': 0.0004871735506571201, 'samples': 3294144, 'steps': 17156, 'loss/train': 1.697090744972229} 08/30/2021 16:19:43 - INFO - __main__ - Step 17158: {'lr': 0.00048717187263739046, 'samples': 3294336, 'steps': 17157, 'loss/train': 1.677499532699585} 08/30/2021 16:19:44 - INFO - __main__ - Step 17159: {'lr': 0.00048717019451079493, 'samples': 3294528, 'steps': 17158, 'loss/train': 1.9471052885055542} 08/30/2021 16:19:45 - INFO - __main__ - Step 17160: {'lr': 0.00048716851627733404, 'samples': 3294720, 'steps': 17159, 'loss/train': 2.3192944526672363} 08/30/2021 16:19:46 - INFO - __main__ - Step 17161: {'lr': 0.00048716683793700876, 'samples': 3294912, 'steps': 17160, 'loss/train': 1.8594112396240234} 08/30/2021 16:19:46 - INFO - __main__ - Step 17162: {'lr': 0.00048716515948981975, 'samples': 3295104, 'steps': 17161, 'loss/train': 1.7230446338653564} 08/30/2021 16:19:46 - INFO - __main__ - Step 17163: {'lr': 0.0004871634809357678, 'samples': 3295296, 'steps': 17162, 'loss/train': 1.4229161739349365} 08/30/2021 16:19:47 - INFO - __main__ - Step 17164: {'lr': 0.00048716180227485365, 'samples': 3295488, 'steps': 17163, 'loss/train': 1.7989989519119263} 08/30/2021 16:19:48 - INFO - __main__ - Step 17165: {'lr': 0.000487160123507078, 'samples': 3295680, 'steps': 17164, 'loss/train': 1.8469843864440918} 08/30/2021 16:19:49 - INFO - __main__ - Step 17166: {'lr': 0.00048715844463244166, 'samples': 3295872, 'steps': 17165, 'loss/train': 1.6918755769729614} 08/30/2021 16:19:49 - INFO - __main__ - Step 17167: {'lr': 0.0004871567656509454, 'samples': 3296064, 'steps': 17166, 'loss/train': 1.916261076927185} 08/30/2021 16:19:49 - INFO - __main__ - Step 17168: {'lr': 0.00048715508656259, 'samples': 3296256, 'steps': 17167, 'loss/train': 1.7329760789871216} 08/30/2021 16:19:50 - INFO - __main__ - Step 17169: {'lr': 0.00048715340736737615, 'samples': 3296448, 'steps': 17168, 'loss/train': 1.7122958898544312} 08/30/2021 16:19:51 - INFO - __main__ - Step 17170: {'lr': 0.0004871517280653046, 'samples': 3296640, 'steps': 17169, 'loss/train': 2.1107749938964844} 08/30/2021 16:19:52 - INFO - __main__ - Step 17171: {'lr': 0.0004871500486563761, 'samples': 3296832, 'steps': 17170, 'loss/train': 1.417673945426941} 08/30/2021 16:19:52 - INFO - __main__ - Step 17172: {'lr': 0.0004871483691405916, 'samples': 3297024, 'steps': 17171, 'loss/train': 1.558638095855713} 08/30/2021 16:19:52 - INFO - __main__ - Step 17173: {'lr': 0.0004871466895179516, 'samples': 3297216, 'steps': 17172, 'loss/train': 1.9435893297195435} 08/30/2021 16:19:53 - INFO - __main__ - Step 17174: {'lr': 0.000487145009788457, 'samples': 3297408, 'steps': 17173, 'loss/train': 1.5993436574935913} 08/30/2021 16:19:55 - INFO - __main__ - Step 17175: {'lr': 0.0004871433299521085, 'samples': 3297600, 'steps': 17174, 'loss/train': 1.9466005563735962} 08/30/2021 16:19:55 - INFO - __main__ - Step 17176: {'lr': 0.00048714165000890685, 'samples': 3297792, 'steps': 17175, 'loss/train': 1.5319772958755493} 08/30/2021 16:19:55 - INFO - __main__ - Step 17177: {'lr': 0.00048713996995885286, 'samples': 3297984, 'steps': 17176, 'loss/train': 0.8693053722381592} 08/30/2021 16:19:56 - INFO - __main__ - Step 17178: {'lr': 0.0004871382898019472, 'samples': 3298176, 'steps': 17177, 'loss/train': 2.826000928878784} 08/30/2021 16:19:56 - INFO - __main__ - Step 17179: {'lr': 0.0004871366095381908, 'samples': 3298368, 'steps': 17178, 'loss/train': 1.463893175125122} 08/30/2021 16:19:56 - INFO - __main__ - Step 17180: {'lr': 0.00048713492916758425, 'samples': 3298560, 'steps': 17179, 'loss/train': 1.4658360481262207} 08/30/2021 16:19:58 - INFO - __main__ - Step 17181: {'lr': 0.00048713324869012833, 'samples': 3298752, 'steps': 17180, 'loss/train': 0.9056485891342163} 08/30/2021 16:19:59 - INFO - __main__ - Step 17182: {'lr': 0.0004871315681058238, 'samples': 3298944, 'steps': 17181, 'loss/train': 1.3314779996871948} 08/30/2021 16:19:59 - INFO - __main__ - Step 17183: {'lr': 0.0004871298874146716, 'samples': 3299136, 'steps': 17182, 'loss/train': 0.2603258192539215} 08/30/2021 16:19:59 - INFO - __main__ - Step 17184: {'lr': 0.00048712820661667215, 'samples': 3299328, 'steps': 17183, 'loss/train': 1.1811299324035645} 08/30/2021 16:20:00 - INFO - __main__ - Step 17185: {'lr': 0.0004871265257118265, 'samples': 3299520, 'steps': 17184, 'loss/train': 0.7493991255760193} 08/30/2021 16:20:01 - INFO - __main__ - Step 17186: {'lr': 0.0004871248447001352, 'samples': 3299712, 'steps': 17185, 'loss/train': 1.7395381927490234} 08/30/2021 16:20:02 - INFO - __main__ - Step 17187: {'lr': 0.0004871231635815992, 'samples': 3299904, 'steps': 17186, 'loss/train': 1.6505751609802246} 08/30/2021 16:20:02 - INFO - __main__ - Step 17188: {'lr': 0.0004871214823562191, 'samples': 3300096, 'steps': 17187, 'loss/train': 1.7045437097549438} 08/30/2021 16:20:02 - INFO - __main__ - Step 17189: {'lr': 0.0004871198010239958, 'samples': 3300288, 'steps': 17188, 'loss/train': 1.5755842924118042} 08/30/2021 16:20:03 - INFO - __main__ - Step 17190: {'lr': 0.0004871181195849299, 'samples': 3300480, 'steps': 17189, 'loss/train': 1.3983370065689087} 08/30/2021 16:20:04 - INFO - __main__ - Step 17191: {'lr': 0.00048711643803902227, 'samples': 3300672, 'steps': 17190, 'loss/train': 1.941197156906128} 08/30/2021 16:20:05 - INFO - __main__ - Step 17192: {'lr': 0.00048711475638627363, 'samples': 3300864, 'steps': 17191, 'loss/train': 1.90217125415802} 08/30/2021 16:20:05 - INFO - __main__ - Step 17193: {'lr': 0.0004871130746266847, 'samples': 3301056, 'steps': 17192, 'loss/train': 1.3400033712387085} 08/30/2021 16:20:05 - INFO - __main__ - Step 17194: {'lr': 0.00048711139276025626, 'samples': 3301248, 'steps': 17193, 'loss/train': 1.4913097620010376} 08/30/2021 16:20:06 - INFO - __main__ - Step 17195: {'lr': 0.00048710971078698916, 'samples': 3301440, 'steps': 17194, 'loss/train': 2.4068617820739746} 08/30/2021 16:20:07 - INFO - __main__ - Step 17196: {'lr': 0.0004871080287068841, 'samples': 3301632, 'steps': 17195, 'loss/train': 1.3379743099212646} 08/30/2021 16:20:08 - INFO - __main__ - Step 17197: {'lr': 0.00048710634651994176, 'samples': 3301824, 'steps': 17196, 'loss/train': 2.3184237480163574} 08/30/2021 16:20:08 - INFO - __main__ - Step 17198: {'lr': 0.0004871046642261629, 'samples': 3302016, 'steps': 17197, 'loss/train': 1.6905794143676758} 08/30/2021 16:20:09 - INFO - __main__ - Step 17199: {'lr': 0.0004871029818255485, 'samples': 3302208, 'steps': 17198, 'loss/train': 1.668904423713684} 08/30/2021 16:20:09 - INFO - __main__ - Step 17200: {'lr': 0.0004871012993180991, 'samples': 3302400, 'steps': 17199, 'loss/train': 1.8536714315414429} 08/30/2021 16:20:09 - INFO - __main__ - Step 17201: {'lr': 0.0004870996167038154, 'samples': 3302592, 'steps': 17200, 'loss/train': 0.12117816507816315} 08/30/2021 16:20:11 - INFO - __main__ - Step 17202: {'lr': 0.0004870979339826984, 'samples': 3302784, 'steps': 17201, 'loss/train': 1.790168285369873} 08/30/2021 16:20:11 - INFO - __main__ - Step 17203: {'lr': 0.00048709625115474865, 'samples': 3302976, 'steps': 17202, 'loss/train': 1.631544828414917} 08/30/2021 16:20:11 - INFO - __main__ - Step 17204: {'lr': 0.00048709456821996705, 'samples': 3303168, 'steps': 17203, 'loss/train': 1.6139225959777832} 08/30/2021 16:20:12 - INFO - __main__ - Step 17205: {'lr': 0.0004870928851783543, 'samples': 3303360, 'steps': 17204, 'loss/train': 1.7055037021636963} 08/30/2021 16:20:12 - INFO - __main__ - Step 17206: {'lr': 0.00048709120202991107, 'samples': 3303552, 'steps': 17205, 'loss/train': 1.8445712327957153} 08/30/2021 16:20:14 - INFO - __main__ - Step 17207: {'lr': 0.0004870895187746383, 'samples': 3303744, 'steps': 17206, 'loss/train': 1.7481948137283325} 08/30/2021 16:20:15 - INFO - __main__ - Step 17208: {'lr': 0.00048708783541253655, 'samples': 3303936, 'steps': 17207, 'loss/train': 1.8356598615646362} 08/30/2021 16:20:15 - INFO - __main__ - Step 17209: {'lr': 0.00048708615194360675, 'samples': 3304128, 'steps': 17208, 'loss/train': 1.4905062913894653} 08/30/2021 16:20:15 - INFO - __main__ - Step 17210: {'lr': 0.0004870844683678496, 'samples': 3304320, 'steps': 17209, 'loss/train': 2.038738965988159} 08/30/2021 16:20:16 - INFO - __main__ - Step 17211: {'lr': 0.0004870827846852658, 'samples': 3304512, 'steps': 17210, 'loss/train': 1.8041356801986694} 08/30/2021 16:20:17 - INFO - __main__ - Step 17212: {'lr': 0.00048708110089585617, 'samples': 3304704, 'steps': 17211, 'loss/train': 1.6887880563735962} 08/30/2021 16:20:18 - INFO - __main__ - Step 17213: {'lr': 0.00048707941699962143, 'samples': 3304896, 'steps': 17212, 'loss/train': 1.7832515239715576} 08/30/2021 16:20:18 - INFO - __main__ - Step 17214: {'lr': 0.0004870777329965624, 'samples': 3305088, 'steps': 17213, 'loss/train': 1.9115080833435059} 08/30/2021 16:20:18 - INFO - __main__ - Step 17215: {'lr': 0.00048707604888667983, 'samples': 3305280, 'steps': 17214, 'loss/train': 1.2715325355529785} 08/30/2021 16:20:19 - INFO - __main__ - Step 17216: {'lr': 0.0004870743646699744, 'samples': 3305472, 'steps': 17215, 'loss/train': 1.3081682920455933} 08/30/2021 16:20:20 - INFO - __main__ - Step 17217: {'lr': 0.0004870726803464469, 'samples': 3305664, 'steps': 17216, 'loss/train': 1.637826919555664} 08/30/2021 16:20:21 - INFO - __main__ - Step 17218: {'lr': 0.00048707099591609816, 'samples': 3305856, 'steps': 17217, 'loss/train': 1.9086990356445312} 08/30/2021 16:20:21 - INFO - __main__ - Step 17219: {'lr': 0.0004870693113789289, 'samples': 3306048, 'steps': 17218, 'loss/train': 1.7289403676986694} 08/30/2021 16:20:21 - INFO - __main__ - Step 17220: {'lr': 0.00048706762673493987, 'samples': 3306240, 'steps': 17219, 'loss/train': 1.3607165813446045} 08/30/2021 16:20:22 - INFO - __main__ - Step 17221: {'lr': 0.00048706594198413177, 'samples': 3306432, 'steps': 17220, 'loss/train': 1.6289743185043335} 08/30/2021 16:20:23 - INFO - __main__ - Step 17222: {'lr': 0.0004870642571265054, 'samples': 3306624, 'steps': 17221, 'loss/train': 1.3383699655532837} 08/30/2021 16:20:24 - INFO - __main__ - Step 17223: {'lr': 0.0004870625721620616, 'samples': 3306816, 'steps': 17222, 'loss/train': 1.5149602890014648} 08/30/2021 16:20:24 - INFO - __main__ - Step 17224: {'lr': 0.00048706088709080103, 'samples': 3307008, 'steps': 17223, 'loss/train': 2.0026845932006836} 08/30/2021 16:20:24 - INFO - __main__ - Step 17225: {'lr': 0.00048705920191272447, 'samples': 3307200, 'steps': 17224, 'loss/train': 1.5719797611236572} 08/30/2021 16:20:25 - INFO - __main__ - Step 17226: {'lr': 0.0004870575166278327, 'samples': 3307392, 'steps': 17225, 'loss/train': 1.1763685941696167} 08/30/2021 16:20:26 - INFO - __main__ - Step 17227: {'lr': 0.0004870558312361265, 'samples': 3307584, 'steps': 17226, 'loss/train': 1.4753894805908203} 08/30/2021 16:20:27 - INFO - __main__ - Step 17228: {'lr': 0.0004870541457376066, 'samples': 3307776, 'steps': 17227, 'loss/train': 1.3628004789352417} 08/30/2021 16:20:27 - INFO - __main__ - Step 17229: {'lr': 0.0004870524601322737, 'samples': 3307968, 'steps': 17228, 'loss/train': 1.4777752161026} 08/30/2021 16:20:27 - INFO - __main__ - Step 17230: {'lr': 0.00048705077442012866, 'samples': 3308160, 'steps': 17229, 'loss/train': 1.9251604080200195} 08/30/2021 16:20:28 - INFO - __main__ - Step 17231: {'lr': 0.0004870490886011723, 'samples': 3308352, 'steps': 17230, 'loss/train': 1.7312031984329224} 08/30/2021 16:20:29 - INFO - __main__ - Step 17232: {'lr': 0.0004870474026754051, 'samples': 3308544, 'steps': 17231, 'loss/train': 1.7540390491485596} 08/30/2021 16:20:30 - INFO - __main__ - Step 17233: {'lr': 0.00048704571664282806, 'samples': 3308736, 'steps': 17232, 'loss/train': 1.5850716829299927} 08/30/2021 16:20:30 - INFO - __main__ - Step 17234: {'lr': 0.0004870440305034419, 'samples': 3308928, 'steps': 17233, 'loss/train': 0.14398325979709625} 08/30/2021 16:20:30 - INFO - __main__ - Step 17235: {'lr': 0.00048704234425724736, 'samples': 3309120, 'steps': 17234, 'loss/train': 1.5970796346664429} 08/30/2021 16:20:31 - INFO - __main__ - Step 17236: {'lr': 0.0004870406579042452, 'samples': 3309312, 'steps': 17235, 'loss/train': 2.115356206893921} 08/30/2021 16:20:32 - INFO - __main__ - Step 17237: {'lr': 0.00048703897144443615, 'samples': 3309504, 'steps': 17236, 'loss/train': 1.9717119932174683} 08/30/2021 16:20:33 - INFO - __main__ - Step 17238: {'lr': 0.000487037284877821, 'samples': 3309696, 'steps': 17237, 'loss/train': 1.8846182823181152} 08/30/2021 16:20:33 - INFO - __main__ - Step 17239: {'lr': 0.00048703559820440054, 'samples': 3309888, 'steps': 17238, 'loss/train': 0.8971735239028931} 08/30/2021 16:20:34 - INFO - __main__ - Step 17240: {'lr': 0.0004870339114241755, 'samples': 3310080, 'steps': 17239, 'loss/train': 1.6554961204528809} 08/30/2021 16:20:34 - INFO - __main__ - Step 17241: {'lr': 0.00048703222453714656, 'samples': 3310272, 'steps': 17240, 'loss/train': 1.9984480142593384} 08/30/2021 16:20:35 - INFO - __main__ - Step 17242: {'lr': 0.0004870305375433146, 'samples': 3310464, 'steps': 17241, 'loss/train': 0.11705752462148666} 08/30/2021 16:20:36 - INFO - __main__ - Step 17243: {'lr': 0.0004870288504426804, 'samples': 3310656, 'steps': 17242, 'loss/train': 1.8031328916549683} 08/30/2021 16:20:36 - INFO - __main__ - Step 17244: {'lr': 0.0004870271632352446, 'samples': 3310848, 'steps': 17243, 'loss/train': 1.4639816284179688} 08/30/2021 16:20:37 - INFO - __main__ - Step 17245: {'lr': 0.000487025475921008, 'samples': 3311040, 'steps': 17244, 'loss/train': 1.7096904516220093} 08/30/2021 16:20:37 - INFO - __main__ - Step 17246: {'lr': 0.00048702378849997143, 'samples': 3311232, 'steps': 17245, 'loss/train': 1.751753330230713} 08/30/2021 16:20:38 - INFO - __main__ - Step 17247: {'lr': 0.0004870221009721356, 'samples': 3311424, 'steps': 17246, 'loss/train': 1.6622823476791382} 08/30/2021 16:20:39 - INFO - __main__ - Step 17248: {'lr': 0.00048702041333750117, 'samples': 3311616, 'steps': 17247, 'loss/train': 1.5522351264953613} 08/30/2021 16:20:39 - INFO - __main__ - Step 17249: {'lr': 0.0004870187255960691, 'samples': 3311808, 'steps': 17248, 'loss/train': 1.5034717321395874} 08/30/2021 16:20:39 - INFO - __main__ - Step 17250: {'lr': 0.00048701703774784, 'samples': 3312000, 'steps': 17249, 'loss/train': 1.4204462766647339} 08/30/2021 16:20:40 - INFO - __main__ - Step 17251: {'lr': 0.0004870153497928147, 'samples': 3312192, 'steps': 17250, 'loss/train': 1.531490683555603} 08/30/2021 16:20:41 - INFO - __main__ - Step 17252: {'lr': 0.00048701366173099396, 'samples': 3312384, 'steps': 17251, 'loss/train': 1.433632254600525} 08/30/2021 16:20:42 - INFO - __main__ - Step 17253: {'lr': 0.0004870119735623785, 'samples': 3312576, 'steps': 17252, 'loss/train': 1.6299384832382202} 08/30/2021 16:20:42 - INFO - __main__ - Step 17254: {'lr': 0.00048701028528696914, 'samples': 3312768, 'steps': 17253, 'loss/train': 1.7262139320373535} 08/30/2021 16:20:42 - INFO - __main__ - Step 17255: {'lr': 0.0004870085969047665, 'samples': 3312960, 'steps': 17254, 'loss/train': 1.7061408758163452} 08/30/2021 16:20:43 - INFO - __main__ - Step 17256: {'lr': 0.00048700690841577154, 'samples': 3313152, 'steps': 17255, 'loss/train': 0.7340334057807922} 08/30/2021 16:20:45 - INFO - __main__ - Step 17257: {'lr': 0.0004870052198199849, 'samples': 3313344, 'steps': 17256, 'loss/train': 1.5008362531661987} 08/30/2021 16:20:45 - INFO - __main__ - Step 17258: {'lr': 0.00048700353111740734, 'samples': 3313536, 'steps': 17257, 'loss/train': 0.9157738089561462} 08/30/2021 16:20:46 - INFO - __main__ - Step 17259: {'lr': 0.0004870018423080397, 'samples': 3313728, 'steps': 17258, 'loss/train': 1.6854766607284546} 08/30/2021 16:20:46 - INFO - __main__ - Step 17260: {'lr': 0.00048700015339188266, 'samples': 3313920, 'steps': 17259, 'loss/train': 1.5270642042160034} 08/30/2021 16:20:46 - INFO - __main__ - Step 17261: {'lr': 0.0004869984643689369, 'samples': 3314112, 'steps': 17260, 'loss/train': 1.520378589630127} 08/30/2021 16:20:47 - INFO - __main__ - Step 17262: {'lr': 0.00048699677523920346, 'samples': 3314304, 'steps': 17261, 'loss/train': 1.5046796798706055} 08/30/2021 16:20:48 - INFO - __main__ - Step 17263: {'lr': 0.00048699508600268284, 'samples': 3314496, 'steps': 17262, 'loss/train': 1.4834710359573364} 08/30/2021 16:20:49 - INFO - __main__ - Step 17264: {'lr': 0.00048699339665937594, 'samples': 3314688, 'steps': 17263, 'loss/train': 2.0987493991851807} 08/30/2021 16:20:49 - INFO - __main__ - Step 17265: {'lr': 0.0004869917072092834, 'samples': 3314880, 'steps': 17264, 'loss/train': 1.4187264442443848} 08/30/2021 16:20:49 - INFO - __main__ - Step 17266: {'lr': 0.00048699001765240615, 'samples': 3315072, 'steps': 17265, 'loss/train': 1.3038651943206787} 08/30/2021 16:20:50 - INFO - __main__ - Step 17267: {'lr': 0.00048698832798874477, 'samples': 3315264, 'steps': 17266, 'loss/train': 1.9730043411254883} 08/30/2021 16:20:51 - INFO - __main__ - Step 17268: {'lr': 0.0004869866382183001, 'samples': 3315456, 'steps': 17267, 'loss/train': 1.1494001150131226} 08/30/2021 16:20:52 - INFO - __main__ - Step 17269: {'lr': 0.00048698494834107297, 'samples': 3315648, 'steps': 17268, 'loss/train': 1.7524253129959106} 08/30/2021 16:20:52 - INFO - __main__ - Step 17270: {'lr': 0.000486983258357064, 'samples': 3315840, 'steps': 17269, 'loss/train': 1.5027101039886475} 08/30/2021 16:20:53 - INFO - __main__ - Step 17271: {'lr': 0.00048698156826627414, 'samples': 3316032, 'steps': 17270, 'loss/train': 1.9209132194519043} 08/30/2021 16:20:53 - INFO - __main__ - Step 17272: {'lr': 0.00048697987806870397, 'samples': 3316224, 'steps': 17271, 'loss/train': 1.8910088539123535} 08/30/2021 16:20:54 - INFO - __main__ - Step 17273: {'lr': 0.0004869781877643543, 'samples': 3316416, 'steps': 17272, 'loss/train': 1.5945838689804077} 08/30/2021 16:20:55 - INFO - __main__ - Step 17274: {'lr': 0.000486976497353226, 'samples': 3316608, 'steps': 17273, 'loss/train': 0.6928431987762451} 08/30/2021 16:20:55 - INFO - __main__ - Step 17275: {'lr': 0.0004869748068353197, 'samples': 3316800, 'steps': 17274, 'loss/train': 1.5734776258468628} 08/30/2021 16:20:56 - INFO - __main__ - Step 17276: {'lr': 0.00048697311621063625, 'samples': 3316992, 'steps': 17275, 'loss/train': 1.3791122436523438} 08/30/2021 16:20:56 - INFO - __main__ - Step 17277: {'lr': 0.0004869714254791763, 'samples': 3317184, 'steps': 17276, 'loss/train': 2.1521201133728027} 08/30/2021 16:20:58 - INFO - __main__ - Step 17278: {'lr': 0.00048696973464094076, 'samples': 3317376, 'steps': 17277, 'loss/train': 1.322631597518921} 08/30/2021 16:20:59 - INFO - __main__ - Step 17279: {'lr': 0.00048696804369593023, 'samples': 3317568, 'steps': 17278, 'loss/train': 1.4515596628189087} 08/30/2021 16:20:59 - INFO - __main__ - Step 17280: {'lr': 0.0004869663526441456, 'samples': 3317760, 'steps': 17279, 'loss/train': 1.5458523035049438} 08/30/2021 16:20:59 - INFO - __main__ - Step 17281: {'lr': 0.0004869646614855876, 'samples': 3317952, 'steps': 17280, 'loss/train': 0.6698225140571594} 08/30/2021 16:21:00 - INFO - __main__ - Step 17282: {'lr': 0.0004869629702202569, 'samples': 3318144, 'steps': 17281, 'loss/train': 0.613684892654419} 08/30/2021 16:21:00 - INFO - __main__ - Step 17283: {'lr': 0.0004869612788481544, 'samples': 3318336, 'steps': 17282, 'loss/train': 0.5401663184165955} 08/30/2021 16:21:01 - INFO - __main__ - Step 17284: {'lr': 0.00048695958736928084, 'samples': 3318528, 'steps': 17283, 'loss/train': 2.1009950637817383} 08/30/2021 16:21:02 - INFO - __main__ - Step 17285: {'lr': 0.00048695789578363693, 'samples': 3318720, 'steps': 17284, 'loss/train': 1.6466425657272339} 08/30/2021 16:21:02 - INFO - __main__ - Step 17286: {'lr': 0.00048695620409122345, 'samples': 3318912, 'steps': 17285, 'loss/train': 1.2270723581314087} 08/30/2021 16:21:03 - INFO - __main__ - Step 17287: {'lr': 0.00048695451229204115, 'samples': 3319104, 'steps': 17286, 'loss/train': 1.5756330490112305} 08/30/2021 16:21:03 - INFO - __main__ - Step 17288: {'lr': 0.0004869528203860908, 'samples': 3319296, 'steps': 17287, 'loss/train': 1.4684290885925293} 08/30/2021 16:21:04 - INFO - __main__ - Step 17289: {'lr': 0.0004869511283733732, 'samples': 3319488, 'steps': 17288, 'loss/train': 1.3921698331832886} 08/30/2021 16:21:05 - INFO - __main__ - Step 17290: {'lr': 0.000486949436253889, 'samples': 3319680, 'steps': 17289, 'loss/train': 1.5589308738708496} 08/30/2021 16:21:05 - INFO - __main__ - Step 17291: {'lr': 0.0004869477440276391, 'samples': 3319872, 'steps': 17290, 'loss/train': 1.8033311367034912} 08/30/2021 16:21:06 - INFO - __main__ - Step 17292: {'lr': 0.00048694605169462415, 'samples': 3320064, 'steps': 17291, 'loss/train': 1.333516001701355} 08/30/2021 16:21:06 - INFO - __main__ - Step 17293: {'lr': 0.00048694435925484506, 'samples': 3320256, 'steps': 17292, 'loss/train': 1.8079005479812622} 08/30/2021 16:21:08 - INFO - __main__ - Step 17294: {'lr': 0.0004869426667083024, 'samples': 3320448, 'steps': 17293, 'loss/train': 2.0321059226989746} 08/30/2021 16:21:08 - INFO - __main__ - Step 17295: {'lr': 0.00048694097405499703, 'samples': 3320640, 'steps': 17294, 'loss/train': 1.420762538909912} 08/30/2021 16:21:09 - INFO - __main__ - Step 17296: {'lr': 0.0004869392812949298, 'samples': 3320832, 'steps': 17295, 'loss/train': 0.06690653413534164} 08/30/2021 16:21:09 - INFO - __main__ - Step 17297: {'lr': 0.00048693758842810133, 'samples': 3321024, 'steps': 17296, 'loss/train': 1.6953409910202026} 08/30/2021 16:21:09 - INFO - __main__ - Step 17298: {'lr': 0.00048693589545451243, 'samples': 3321216, 'steps': 17297, 'loss/train': 1.5967339277267456} 08/30/2021 16:21:10 - INFO - __main__ - Step 17299: {'lr': 0.00048693420237416393, 'samples': 3321408, 'steps': 17298, 'loss/train': 1.582407832145691} 08/30/2021 16:21:11 - INFO - __main__ - Step 17300: {'lr': 0.00048693250918705643, 'samples': 3321600, 'steps': 17299, 'loss/train': 1.3376667499542236} 08/30/2021 16:21:12 - INFO - __main__ - Step 17301: {'lr': 0.0004869308158931909, 'samples': 3321792, 'steps': 17300, 'loss/train': 2.073134660720825} 08/30/2021 16:21:12 - INFO - __main__ - Step 17302: {'lr': 0.00048692912249256794, 'samples': 3321984, 'steps': 17301, 'loss/train': 1.2439717054367065} 08/30/2021 16:21:12 - INFO - __main__ - Step 17303: {'lr': 0.00048692742898518836, 'samples': 3322176, 'steps': 17302, 'loss/train': 1.4036697149276733} 08/30/2021 16:21:13 - INFO - __main__ - Step 17304: {'lr': 0.000486925735371053, 'samples': 3322368, 'steps': 17303, 'loss/train': 1.7767975330352783} 08/30/2021 16:21:14 - INFO - __main__ - Step 17305: {'lr': 0.00048692404165016256, 'samples': 3322560, 'steps': 17304, 'loss/train': 1.9546399116516113} 08/30/2021 16:21:15 - INFO - __main__ - Step 17306: {'lr': 0.0004869223478225178, 'samples': 3322752, 'steps': 17305, 'loss/train': 1.1804614067077637} 08/30/2021 16:21:15 - INFO - __main__ - Step 17307: {'lr': 0.00048692065388811944, 'samples': 3322944, 'steps': 17306, 'loss/train': 1.7170722484588623} 08/30/2021 16:21:15 - INFO - __main__ - Step 17308: {'lr': 0.0004869189598469683, 'samples': 3323136, 'steps': 17307, 'loss/train': 1.4930357933044434} 08/30/2021 16:21:16 - INFO - __main__ - Step 17309: {'lr': 0.00048691726569906514, 'samples': 3323328, 'steps': 17308, 'loss/train': 1.680724024772644} 08/30/2021 16:21:19 - INFO - __main__ - Step 17310: {'lr': 0.0004869155714444107, 'samples': 3323520, 'steps': 17309, 'loss/train': 1.571215271949768} 08/30/2021 16:21:19 - INFO - __main__ - Step 17311: {'lr': 0.00048691387708300584, 'samples': 3323712, 'steps': 17310, 'loss/train': 1.4766267538070679} 08/30/2021 16:21:19 - INFO - __main__ - Step 17312: {'lr': 0.00048691218261485113, 'samples': 3323904, 'steps': 17311, 'loss/train': 1.329664945602417} 08/30/2021 16:21:20 - INFO - __main__ - Step 17313: {'lr': 0.00048691048803994755, 'samples': 3324096, 'steps': 17312, 'loss/train': 1.7416303157806396} 08/30/2021 16:21:20 - INFO - __main__ - Step 17314: {'lr': 0.00048690879335829565, 'samples': 3324288, 'steps': 17313, 'loss/train': 1.323940634727478} 08/30/2021 16:21:20 - INFO - __main__ - Step 17315: {'lr': 0.00048690709856989635, 'samples': 3324480, 'steps': 17314, 'loss/train': 2.468637228012085} 08/30/2021 16:21:21 - INFO - __main__ - Step 17316: {'lr': 0.00048690540367475046, 'samples': 3324672, 'steps': 17315, 'loss/train': 0.28997504711151123} 08/30/2021 16:21:22 - INFO - __main__ - Step 17317: {'lr': 0.00048690370867285847, 'samples': 3324864, 'steps': 17316, 'loss/train': 0.3503378927707672} 08/30/2021 16:21:23 - INFO - __main__ - Step 17318: {'lr': 0.00048690201356422146, 'samples': 3325056, 'steps': 17317, 'loss/train': 1.3354766368865967} 08/30/2021 16:21:23 - INFO - __main__ - Step 17319: {'lr': 0.00048690031834884004, 'samples': 3325248, 'steps': 17318, 'loss/train': 0.25356781482696533} 08/30/2021 16:21:24 - INFO - __main__ - Step 17320: {'lr': 0.00048689862302671495, 'samples': 3325440, 'steps': 17319, 'loss/train': 1.2663406133651733} 08/30/2021 16:21:24 - INFO - __main__ - Step 17321: {'lr': 0.000486896927597847, 'samples': 3325632, 'steps': 17320, 'loss/train': 2.2433221340179443} 08/30/2021 16:21:25 - INFO - __main__ - Step 17322: {'lr': 0.00048689523206223693, 'samples': 3325824, 'steps': 17321, 'loss/train': 1.3755285739898682} 08/30/2021 16:21:26 - INFO - __main__ - Step 17323: {'lr': 0.00048689353641988563, 'samples': 3326016, 'steps': 17322, 'loss/train': 1.7116140127182007} 08/30/2021 16:21:26 - INFO - __main__ - Step 17324: {'lr': 0.0004868918406707937, 'samples': 3326208, 'steps': 17323, 'loss/train': 1.3808372020721436} 08/30/2021 16:21:27 - INFO - __main__ - Step 17325: {'lr': 0.00048689014481496197, 'samples': 3326400, 'steps': 17324, 'loss/train': 1.2138450145721436} 08/30/2021 16:21:27 - INFO - __main__ - Step 17326: {'lr': 0.0004868884488523911, 'samples': 3326592, 'steps': 17325, 'loss/train': 1.6475673913955688} 08/30/2021 16:21:29 - INFO - __main__ - Step 17327: {'lr': 0.0004868867527830821, 'samples': 3326784, 'steps': 17326, 'loss/train': 1.5045684576034546} 08/30/2021 16:21:29 - INFO - __main__ - Step 17328: {'lr': 0.0004868850566070355, 'samples': 3326976, 'steps': 17327, 'loss/train': 0.6110200881958008} 08/30/2021 16:21:29 - INFO - __main__ - Step 17329: {'lr': 0.00048688336032425217, 'samples': 3327168, 'steps': 17328, 'loss/train': 2.3573122024536133} 08/30/2021 16:21:30 - INFO - __main__ - Step 17330: {'lr': 0.0004868816639347328, 'samples': 3327360, 'steps': 17329, 'loss/train': 1.7974035739898682} 08/30/2021 16:21:30 - INFO - __main__ - Step 17331: {'lr': 0.0004868799674384783, 'samples': 3327552, 'steps': 17330, 'loss/train': 2.2172374725341797} 08/30/2021 16:21:30 - INFO - __main__ - Step 17332: {'lr': 0.0004868782708354893, 'samples': 3327744, 'steps': 17331, 'loss/train': 1.334261178970337} 08/30/2021 16:21:32 - INFO - __main__ - Step 17333: {'lr': 0.0004868765741257666, 'samples': 3327936, 'steps': 17332, 'loss/train': 1.588341236114502} 08/30/2021 16:21:32 - INFO - __main__ - Step 17334: {'lr': 0.00048687487730931096, 'samples': 3328128, 'steps': 17333, 'loss/train': 2.2034811973571777} 08/30/2021 16:21:33 - INFO - __main__ - Step 17335: {'lr': 0.00048687318038612317, 'samples': 3328320, 'steps': 17334, 'loss/train': 1.5304841995239258} 08/30/2021 16:21:33 - INFO - __main__ - Step 17336: {'lr': 0.000486871483356204, 'samples': 3328512, 'steps': 17335, 'loss/train': 1.9972132444381714} 08/30/2021 16:21:34 - INFO - __main__ - Step 17337: {'lr': 0.00048686978621955416, 'samples': 3328704, 'steps': 17336, 'loss/train': 1.6155893802642822} 08/30/2021 16:21:35 - INFO - __main__ - Step 17338: {'lr': 0.00048686808897617447, 'samples': 3328896, 'steps': 17337, 'loss/train': 2.1802656650543213} 08/30/2021 16:21:35 - INFO - __main__ - Step 17339: {'lr': 0.00048686639162606564, 'samples': 3329088, 'steps': 17338, 'loss/train': 1.9840431213378906} 08/30/2021 16:21:36 - INFO - __main__ - Step 17340: {'lr': 0.0004868646941692285, 'samples': 3329280, 'steps': 17339, 'loss/train': 1.7624295949935913} 08/30/2021 16:21:36 - INFO - __main__ - Step 17341: {'lr': 0.0004868629966056638, 'samples': 3329472, 'steps': 17340, 'loss/train': 1.2280787229537964} 08/30/2021 16:21:36 - INFO - __main__ - Step 17342: {'lr': 0.0004868612989353722, 'samples': 3329664, 'steps': 17341, 'loss/train': 1.5077310800552368} 08/30/2021 16:21:38 - INFO - __main__ - Step 17343: {'lr': 0.0004868596011583547, 'samples': 3329856, 'steps': 17342, 'loss/train': 0.6439254879951477} 08/30/2021 16:21:39 - INFO - __main__ - Step 17344: {'lr': 0.00048685790327461184, 'samples': 3330048, 'steps': 17343, 'loss/train': 1.9081764221191406} 08/30/2021 16:21:39 - INFO - __main__ - Step 17345: {'lr': 0.0004868562052841444, 'samples': 3330240, 'steps': 17344, 'loss/train': 1.3459018468856812} 08/30/2021 16:21:39 - INFO - __main__ - Step 17346: {'lr': 0.00048685450718695335, 'samples': 3330432, 'steps': 17345, 'loss/train': 0.2580951750278473} 08/30/2021 16:21:40 - INFO - __main__ - Step 17347: {'lr': 0.00048685280898303916, 'samples': 3330624, 'steps': 17346, 'loss/train': 1.4930943250656128} 08/30/2021 16:21:40 - INFO - __main__ - Step 17348: {'lr': 0.00048685111067240283, 'samples': 3330816, 'steps': 17347, 'loss/train': 1.3986310958862305} 08/30/2021 16:21:42 - INFO - __main__ - Step 17349: {'lr': 0.00048684941225504507, 'samples': 3331008, 'steps': 17348, 'loss/train': 1.661223292350769} 08/30/2021 16:21:42 - INFO - __main__ - Step 17350: {'lr': 0.0004868477137309666, 'samples': 3331200, 'steps': 17349, 'loss/train': 2.1348724365234375} 08/30/2021 16:21:43 - INFO - __main__ - Step 17351: {'lr': 0.00048684601510016817, 'samples': 3331392, 'steps': 17350, 'loss/train': 2.4937057495117188} 08/30/2021 16:21:43 - INFO - __main__ - Step 17352: {'lr': 0.00048684431636265065, 'samples': 3331584, 'steps': 17351, 'loss/train': 1.2339820861816406} 08/30/2021 16:21:43 - INFO - __main__ - Step 17353: {'lr': 0.00048684261751841463, 'samples': 3331776, 'steps': 17352, 'loss/train': 1.6313081979751587} 08/30/2021 16:21:45 - INFO - __main__ - Step 17354: {'lr': 0.000486840918567461, 'samples': 3331968, 'steps': 17353, 'loss/train': 1.693860411643982} 08/30/2021 16:21:45 - INFO - __main__ - Step 17355: {'lr': 0.0004868392195097906, 'samples': 3332160, 'steps': 17354, 'loss/train': 1.7639496326446533} 08/30/2021 16:21:46 - INFO - __main__ - Step 17356: {'lr': 0.0004868375203454041, 'samples': 3332352, 'steps': 17355, 'loss/train': 1.3028088808059692} 08/30/2021 16:21:46 - INFO - __main__ - Step 17357: {'lr': 0.00048683582107430227, 'samples': 3332544, 'steps': 17356, 'loss/train': 0.4325411319732666} 08/30/2021 16:21:46 - INFO - __main__ - Step 17358: {'lr': 0.0004868341216964858, 'samples': 3332736, 'steps': 17357, 'loss/train': 1.8419189453125} 08/30/2021 16:21:48 - INFO - __main__ - Step 17359: {'lr': 0.00048683242221195553, 'samples': 3332928, 'steps': 17358, 'loss/train': 1.6655195951461792} 08/30/2021 16:21:48 - INFO - __main__ - Step 17360: {'lr': 0.00048683072262071224, 'samples': 3333120, 'steps': 17359, 'loss/train': 0.29443657398223877} 08/30/2021 16:21:49 - INFO - __main__ - Step 17361: {'lr': 0.00048682902292275667, 'samples': 3333312, 'steps': 17360, 'loss/train': 1.6831555366516113} 08/30/2021 16:21:49 - INFO - __main__ - Step 17362: {'lr': 0.00048682732311808964, 'samples': 3333504, 'steps': 17361, 'loss/train': 1.497959017753601} 08/30/2021 16:21:49 - INFO - __main__ - Step 17363: {'lr': 0.00048682562320671185, 'samples': 3333696, 'steps': 17362, 'loss/train': 1.7417789697647095} 08/30/2021 16:21:51 - INFO - __main__ - Step 17364: {'lr': 0.00048682392318862407, 'samples': 3333888, 'steps': 17363, 'loss/train': 1.3795396089553833} 08/30/2021 16:21:52 - INFO - __main__ - Step 17365: {'lr': 0.00048682222306382705, 'samples': 3334080, 'steps': 17364, 'loss/train': 1.7262126207351685} 08/30/2021 16:21:52 - INFO - __main__ - Step 17366: {'lr': 0.0004868205228323217, 'samples': 3334272, 'steps': 17365, 'loss/train': 1.6140670776367188} 08/30/2021 16:21:53 - INFO - __main__ - Step 17367: {'lr': 0.0004868188224941086, 'samples': 3334464, 'steps': 17366, 'loss/train': 2.37587308883667} 08/30/2021 16:21:53 - INFO - __main__ - Step 17368: {'lr': 0.0004868171220491886, 'samples': 3334656, 'steps': 17367, 'loss/train': 2.0379302501678467} 08/30/2021 16:21:54 - INFO - __main__ - Step 17369: {'lr': 0.00048681542149756253, 'samples': 3334848, 'steps': 17368, 'loss/train': 1.8309261798858643} 08/30/2021 16:21:55 - INFO - __main__ - Step 17370: {'lr': 0.00048681372083923103, 'samples': 3335040, 'steps': 17369, 'loss/train': 1.9486777782440186} 08/30/2021 16:21:55 - INFO - __main__ - Step 17371: {'lr': 0.0004868120200741949, 'samples': 3335232, 'steps': 17370, 'loss/train': 2.133272886276245} 08/30/2021 16:21:56 - INFO - __main__ - Step 17372: {'lr': 0.0004868103192024549, 'samples': 3335424, 'steps': 17371, 'loss/train': 1.6345919370651245} 08/30/2021 16:21:56 - INFO - __main__ - Step 17373: {'lr': 0.0004868086182240119, 'samples': 3335616, 'steps': 17372, 'loss/train': 1.309005618095398} 08/30/2021 16:21:58 - INFO - __main__ - Step 17374: {'lr': 0.00048680691713886653, 'samples': 3335808, 'steps': 17373, 'loss/train': 1.9788750410079956} 08/30/2021 16:21:58 - INFO - __main__ - Step 17375: {'lr': 0.00048680521594701964, 'samples': 3336000, 'steps': 17374, 'loss/train': 1.8031384944915771} 08/30/2021 16:21:59 - INFO - __main__ - Step 17376: {'lr': 0.00048680351464847207, 'samples': 3336192, 'steps': 17375, 'loss/train': 1.7543350458145142} 08/30/2021 16:21:59 - INFO - __main__ - Step 17377: {'lr': 0.00048680181324322437, 'samples': 3336384, 'steps': 17376, 'loss/train': 1.9475842714309692} 08/30/2021 16:21:59 - INFO - __main__ - Step 17378: {'lr': 0.00048680011173127746, 'samples': 3336576, 'steps': 17377, 'loss/train': 1.0543763637542725} 08/30/2021 16:22:00 - INFO - __main__ - Step 17379: {'lr': 0.00048679841011263204, 'samples': 3336768, 'steps': 17378, 'loss/train': 3.990530252456665} 08/30/2021 16:22:01 - INFO - __main__ - Step 17380: {'lr': 0.00048679670838728894, 'samples': 3336960, 'steps': 17379, 'loss/train': 0.1678185611963272} 08/30/2021 16:22:02 - INFO - __main__ - Step 17381: {'lr': 0.0004867950065552489, 'samples': 3337152, 'steps': 17380, 'loss/train': 1.7439442873001099} 08/30/2021 16:22:02 - INFO - __main__ - Step 17382: {'lr': 0.00048679330461651275, 'samples': 3337344, 'steps': 17381, 'loss/train': 1.6377366781234741} 08/30/2021 16:22:03 - INFO - __main__ - Step 17383: {'lr': 0.00048679160257108107, 'samples': 3337536, 'steps': 17382, 'loss/train': 2.1917710304260254} 08/30/2021 16:22:03 - INFO - __main__ - Step 17384: {'lr': 0.00048678990041895484, 'samples': 3337728, 'steps': 17383, 'loss/train': 1.8279938697814941} 08/30/2021 16:22:05 - INFO - __main__ - Step 17385: {'lr': 0.00048678819816013467, 'samples': 3337920, 'steps': 17384, 'loss/train': 0.23291407525539398} 08/30/2021 16:22:05 - INFO - __main__ - Step 17386: {'lr': 0.0004867864957946214, 'samples': 3338112, 'steps': 17385, 'loss/train': 1.5302484035491943} 08/30/2021 16:22:05 - INFO - __main__ - Step 17387: {'lr': 0.0004867847933224158, 'samples': 3338304, 'steps': 17386, 'loss/train': 1.5825395584106445} 08/30/2021 16:22:06 - INFO - __main__ - Step 17388: {'lr': 0.0004867830907435187, 'samples': 3338496, 'steps': 17387, 'loss/train': 1.4746028184890747} 08/30/2021 16:22:06 - INFO - __main__ - Step 17389: {'lr': 0.0004867813880579307, 'samples': 3338688, 'steps': 17388, 'loss/train': 1.6257576942443848} 08/30/2021 16:22:06 - INFO - __main__ - Step 17390: {'lr': 0.0004867796852656527, 'samples': 3338880, 'steps': 17389, 'loss/train': 1.0585116147994995} 08/30/2021 16:22:08 - INFO - __main__ - Step 17391: {'lr': 0.00048677798236668537, 'samples': 3339072, 'steps': 17390, 'loss/train': 1.5680699348449707} 08/30/2021 16:22:08 - INFO - __main__ - Step 17392: {'lr': 0.00048677627936102966, 'samples': 3339264, 'steps': 17391, 'loss/train': 2.17177414894104} 08/30/2021 16:22:09 - INFO - __main__ - Step 17393: {'lr': 0.0004867745762486861, 'samples': 3339456, 'steps': 17392, 'loss/train': 2.0008177757263184} 08/30/2021 16:22:09 - INFO - __main__ - Step 17394: {'lr': 0.0004867728730296556, 'samples': 3339648, 'steps': 17393, 'loss/train': 1.4614367485046387} 08/30/2021 16:22:09 - INFO - __main__ - Step 17395: {'lr': 0.0004867711697039389, 'samples': 3339840, 'steps': 17394, 'loss/train': 1.858125925064087} 08/30/2021 16:22:11 - INFO - __main__ - Step 17396: {'lr': 0.00048676946627153675, 'samples': 3340032, 'steps': 17395, 'loss/train': 1.4392808675765991} 08/30/2021 16:22:11 - INFO - __main__ - Step 17397: {'lr': 0.00048676776273244994, 'samples': 3340224, 'steps': 17396, 'loss/train': 1.8327624797821045} 08/30/2021 16:22:12 - INFO - __main__ - Step 17398: {'lr': 0.00048676605908667926, 'samples': 3340416, 'steps': 17397, 'loss/train': 2.5532779693603516} 08/30/2021 16:22:12 - INFO - __main__ - Step 17399: {'lr': 0.00048676435533422536, 'samples': 3340608, 'steps': 17398, 'loss/train': 1.3023334741592407} 08/30/2021 16:22:12 - INFO - __main__ - Step 17400: {'lr': 0.00048676265147508917, 'samples': 3340800, 'steps': 17399, 'loss/train': 1.5067830085754395} 08/30/2021 16:22:14 - INFO - __main__ - Step 17401: {'lr': 0.00048676094750927144, 'samples': 3340992, 'steps': 17400, 'loss/train': 1.7027322053909302} 08/30/2021 16:22:14 - INFO - __main__ - Step 17402: {'lr': 0.0004867592434367728, 'samples': 3341184, 'steps': 17401, 'loss/train': 1.6238844394683838} 08/30/2021 16:22:15 - INFO - __main__ - Step 17403: {'lr': 0.0004867575392575941, 'samples': 3341376, 'steps': 17402, 'loss/train': 1.6029798984527588} 08/30/2021 16:22:15 - INFO - __main__ - Step 17404: {'lr': 0.0004867558349717361, 'samples': 3341568, 'steps': 17403, 'loss/train': 1.3958392143249512} 08/30/2021 16:22:15 - INFO - __main__ - Step 17405: {'lr': 0.0004867541305791996, 'samples': 3341760, 'steps': 17404, 'loss/train': 1.8233625888824463} 08/30/2021 16:22:17 - INFO - __main__ - Step 17406: {'lr': 0.00048675242607998533, 'samples': 3341952, 'steps': 17405, 'loss/train': 1.6665757894515991} 08/30/2021 16:22:17 - INFO - __main__ - Step 17407: {'lr': 0.00048675072147409405, 'samples': 3342144, 'steps': 17406, 'loss/train': 1.259602665901184} 08/30/2021 16:22:18 - INFO - __main__ - Step 17408: {'lr': 0.0004867490167615266, 'samples': 3342336, 'steps': 17407, 'loss/train': 2.2457082271575928} 08/30/2021 16:22:18 - INFO - __main__ - Step 17409: {'lr': 0.0004867473119422837, 'samples': 3342528, 'steps': 17408, 'loss/train': 1.7272624969482422} 08/30/2021 16:22:18 - INFO - __main__ - Step 17410: {'lr': 0.00048674560701636606, 'samples': 3342720, 'steps': 17409, 'loss/train': 1.9000693559646606} 08/30/2021 16:22:20 - INFO - __main__ - Step 17411: {'lr': 0.0004867439019837745, 'samples': 3342912, 'steps': 17410, 'loss/train': 2.7054336071014404} 08/30/2021 16:22:20 - INFO - __main__ - Step 17412: {'lr': 0.00048674219684450985, 'samples': 3343104, 'steps': 17411, 'loss/train': 1.8756489753723145} 08/30/2021 16:22:21 - INFO - __main__ - Step 17413: {'lr': 0.00048674049159857277, 'samples': 3343296, 'steps': 17412, 'loss/train': 0.689872682094574} 08/30/2021 16:22:21 - INFO - __main__ - Step 17414: {'lr': 0.0004867387862459641, 'samples': 3343488, 'steps': 17413, 'loss/train': 1.6381309032440186} 08/30/2021 16:22:21 - INFO - __main__ - Step 17415: {'lr': 0.0004867370807866845, 'samples': 3343680, 'steps': 17414, 'loss/train': 1.8539162874221802} 08/30/2021 16:22:24 - INFO - __main__ - Step 17416: {'lr': 0.000486735375220735, 'samples': 3343872, 'steps': 17415, 'loss/train': 2.4776206016540527} 08/30/2021 16:22:24 - INFO - __main__ - Step 17417: {'lr': 0.00048673366954811605, 'samples': 3344064, 'steps': 17416, 'loss/train': 1.5945243835449219} 08/30/2021 16:22:24 - INFO - __main__ - Step 17418: {'lr': 0.0004867319637688286, 'samples': 3344256, 'steps': 17417, 'loss/train': 1.1917868852615356} 08/30/2021 16:22:25 - INFO - __main__ - Step 17419: {'lr': 0.0004867302578828734, 'samples': 3344448, 'steps': 17418, 'loss/train': 1.623712182044983} 08/30/2021 16:22:25 - INFO - __main__ - Step 17420: {'lr': 0.0004867285518902512, 'samples': 3344640, 'steps': 17419, 'loss/train': 2.194242477416992} 08/30/2021 16:22:25 - INFO - __main__ - Step 17421: {'lr': 0.0004867268457909627, 'samples': 3344832, 'steps': 17420, 'loss/train': 1.349695086479187} 08/30/2021 16:22:28 - INFO - __main__ - Step 17422: {'lr': 0.0004867251395850088, 'samples': 3345024, 'steps': 17421, 'loss/train': 0.17078430950641632} 08/30/2021 16:22:29 - INFO - __main__ - Step 17423: {'lr': 0.00048672343327239024, 'samples': 3345216, 'steps': 17422, 'loss/train': 1.512771725654602} 08/30/2021 16:22:29 - INFO - __main__ - Step 17424: {'lr': 0.00048672172685310767, 'samples': 3345408, 'steps': 17423, 'loss/train': 1.4440419673919678} 08/30/2021 16:22:29 - INFO - __main__ - Step 17425: {'lr': 0.000486720020327162, 'samples': 3345600, 'steps': 17424, 'loss/train': 1.7390447854995728} 08/30/2021 16:22:30 - INFO - __main__ - Step 17426: {'lr': 0.00048671831369455386, 'samples': 3345792, 'steps': 17425, 'loss/train': 0.44793176651000977} 08/30/2021 16:22:30 - INFO - __main__ - Step 17427: {'lr': 0.0004867166069552842, 'samples': 3345984, 'steps': 17426, 'loss/train': 2.000828266143799} 08/30/2021 16:22:30 - INFO - __main__ - Step 17428: {'lr': 0.00048671490010935366, 'samples': 3346176, 'steps': 17427, 'loss/train': 1.1772760152816772} 08/30/2021 16:22:31 - INFO - __main__ - Step 17429: {'lr': 0.00048671319315676305, 'samples': 3346368, 'steps': 17428, 'loss/train': 2.734375} 08/30/2021 16:22:32 - INFO - __main__ - Step 17430: {'lr': 0.00048671148609751307, 'samples': 3346560, 'steps': 17429, 'loss/train': 1.5546437501907349} 08/30/2021 16:22:33 - INFO - __main__ - Step 17431: {'lr': 0.0004867097789316046, 'samples': 3346752, 'steps': 17430, 'loss/train': 2.1142067909240723} 08/30/2021 16:22:33 - INFO - __main__ - Step 17432: {'lr': 0.0004867080716590384, 'samples': 3346944, 'steps': 17431, 'loss/train': 1.9760955572128296} 08/30/2021 16:22:33 - INFO - __main__ - Step 17433: {'lr': 0.0004867063642798151, 'samples': 3347136, 'steps': 17432, 'loss/train': 1.793282389640808} 08/30/2021 16:22:34 - INFO - __main__ - Step 17434: {'lr': 0.0004867046567939356, 'samples': 3347328, 'steps': 17433, 'loss/train': 1.8897130489349365} 08/30/2021 16:22:35 - INFO - __main__ - Step 17435: {'lr': 0.00048670294920140063, 'samples': 3347520, 'steps': 17434, 'loss/train': 2.087878465652466} 08/30/2021 16:22:36 - INFO - __main__ - Step 17436: {'lr': 0.00048670124150221094, 'samples': 3347712, 'steps': 17435, 'loss/train': 1.708673357963562} 08/30/2021 16:22:36 - INFO - __main__ - Step 17437: {'lr': 0.00048669953369636737, 'samples': 3347904, 'steps': 17436, 'loss/train': 1.349056601524353} 08/30/2021 16:22:36 - INFO - __main__ - Step 17438: {'lr': 0.00048669782578387067, 'samples': 3348096, 'steps': 17437, 'loss/train': 0.8885194063186646} 08/30/2021 16:22:37 - INFO - __main__ - Step 17439: {'lr': 0.00048669611776472153, 'samples': 3348288, 'steps': 17438, 'loss/train': 1.7635525465011597} 08/30/2021 16:22:37 - INFO - __main__ - Step 17440: {'lr': 0.00048669440963892074, 'samples': 3348480, 'steps': 17439, 'loss/train': 2.1269845962524414} 08/30/2021 16:22:39 - INFO - __main__ - Step 17441: {'lr': 0.00048669270140646914, 'samples': 3348672, 'steps': 17440, 'loss/train': 1.8065775632858276} 08/30/2021 16:22:39 - INFO - __main__ - Step 17442: {'lr': 0.0004866909930673675, 'samples': 3348864, 'steps': 17441, 'loss/train': 2.5166263580322266} 08/30/2021 16:22:39 - INFO - __main__ - Step 17443: {'lr': 0.00048668928462161653, 'samples': 3349056, 'steps': 17442, 'loss/train': 2.0788023471832275} 08/30/2021 16:22:40 - INFO - __main__ - Step 17444: {'lr': 0.000486687576069217, 'samples': 3349248, 'steps': 17443, 'loss/train': 5.522563934326172} 08/30/2021 16:22:40 - INFO - __main__ - Step 17445: {'lr': 0.00048668586741016967, 'samples': 3349440, 'steps': 17444, 'loss/train': 2.367457866668701} 08/30/2021 16:22:42 - INFO - __main__ - Step 17446: {'lr': 0.0004866841586444754, 'samples': 3349632, 'steps': 17445, 'loss/train': 1.866705060005188} 08/30/2021 16:22:43 - INFO - __main__ - Step 17447: {'lr': 0.0004866824497721349, 'samples': 3349824, 'steps': 17446, 'loss/train': 1.8990633487701416} 08/30/2021 16:22:43 - INFO - __main__ - Step 17448: {'lr': 0.0004866807407931489, 'samples': 3350016, 'steps': 17447, 'loss/train': 1.7508528232574463} 08/30/2021 16:22:43 - INFO - __main__ - Step 17449: {'lr': 0.0004866790317075182, 'samples': 3350208, 'steps': 17448, 'loss/train': 1.650154709815979} 08/30/2021 16:22:44 - INFO - __main__ - Step 17450: {'lr': 0.00048667732251524365, 'samples': 3350400, 'steps': 17449, 'loss/train': 1.7136389017105103} 08/30/2021 16:22:44 - INFO - __main__ - Step 17451: {'lr': 0.0004866756132163259, 'samples': 3350592, 'steps': 17450, 'loss/train': 1.9944013357162476} 08/30/2021 16:22:45 - INFO - __main__ - Step 17452: {'lr': 0.0004866739038107658, 'samples': 3350784, 'steps': 17451, 'loss/train': 0.36397862434387207} 08/30/2021 16:22:46 - INFO - __main__ - Step 17453: {'lr': 0.000486672194298564, 'samples': 3350976, 'steps': 17452, 'loss/train': 1.371496558189392} 08/30/2021 16:22:46 - INFO - __main__ - Step 17454: {'lr': 0.00048667048467972146, 'samples': 3351168, 'steps': 17453, 'loss/train': 2.206498384475708} 08/30/2021 16:22:47 - INFO - __main__ - Step 17455: {'lr': 0.00048666877495423885, 'samples': 3351360, 'steps': 17454, 'loss/train': 2.2213566303253174} 08/30/2021 16:22:47 - INFO - __main__ - Step 17456: {'lr': 0.0004866670651221169, 'samples': 3351552, 'steps': 17455, 'loss/train': 1.8459641933441162} 08/30/2021 16:22:48 - INFO - __main__ - Step 17457: {'lr': 0.0004866653551833564, 'samples': 3351744, 'steps': 17456, 'loss/train': 2.0397403240203857} 08/30/2021 16:22:49 - INFO - __main__ - Step 17458: {'lr': 0.00048666364513795816, 'samples': 3351936, 'steps': 17457, 'loss/train': 1.4646025896072388} 08/30/2021 16:22:49 - INFO - __main__ - Step 17459: {'lr': 0.00048666193498592304, 'samples': 3352128, 'steps': 17458, 'loss/train': 1.1593598127365112} 08/30/2021 16:22:50 - INFO - __main__ - Step 17460: {'lr': 0.0004866602247272516, 'samples': 3352320, 'steps': 17459, 'loss/train': 0.906301736831665} 08/30/2021 16:22:50 - INFO - __main__ - Step 17461: {'lr': 0.0004866585143619447, 'samples': 3352512, 'steps': 17460, 'loss/train': 1.827962875366211} 08/30/2021 16:22:51 - INFO - __main__ - Step 17462: {'lr': 0.00048665680389000315, 'samples': 3352704, 'steps': 17461, 'loss/train': 2.0785582065582275} 08/30/2021 16:22:52 - INFO - __main__ - Step 17463: {'lr': 0.0004866550933114277, 'samples': 3352896, 'steps': 17462, 'loss/train': 1.6082682609558105} 08/30/2021 16:22:52 - INFO - __main__ - Step 17464: {'lr': 0.00048665338262621915, 'samples': 3353088, 'steps': 17463, 'loss/train': 1.9932937622070312} 08/30/2021 16:22:53 - INFO - __main__ - Step 17465: {'lr': 0.00048665167183437817, 'samples': 3353280, 'steps': 17464, 'loss/train': 1.7249715328216553} 08/30/2021 16:22:53 - INFO - __main__ - Step 17466: {'lr': 0.00048664996093590563, 'samples': 3353472, 'steps': 17465, 'loss/train': 2.252119302749634} 08/30/2021 16:22:54 - INFO - __main__ - Step 17467: {'lr': 0.0004866482499308023, 'samples': 3353664, 'steps': 17466, 'loss/train': 2.0502357482910156} 08/30/2021 16:22:55 - INFO - __main__ - Step 17468: {'lr': 0.0004866465388190689, 'samples': 3353856, 'steps': 17467, 'loss/train': 1.966733694076538} 08/30/2021 16:22:55 - INFO - __main__ - Step 17469: {'lr': 0.0004866448276007062, 'samples': 3354048, 'steps': 17468, 'loss/train': 1.647402048110962} 08/30/2021 16:22:55 - INFO - __main__ - Step 17470: {'lr': 0.000486643116275715, 'samples': 3354240, 'steps': 17469, 'loss/train': 3.549617290496826} 08/30/2021 16:22:56 - INFO - __main__ - Step 17471: {'lr': 0.00048664140484409613, 'samples': 3354432, 'steps': 17470, 'loss/train': 1.3118197917938232} 08/30/2021 16:22:57 - INFO - __main__ - Step 17472: {'lr': 0.0004866396933058502, 'samples': 3354624, 'steps': 17471, 'loss/train': 1.5544676780700684} 08/30/2021 16:22:58 - INFO - __main__ - Step 17473: {'lr': 0.00048663798166097814, 'samples': 3354816, 'steps': 17472, 'loss/train': 2.0812900066375732} 08/30/2021 16:22:58 - INFO - __main__ - Step 17474: {'lr': 0.0004866362699094806, 'samples': 3355008, 'steps': 17473, 'loss/train': 1.616500973701477} 08/30/2021 16:22:58 - INFO - __main__ - Step 17475: {'lr': 0.0004866345580513585, 'samples': 3355200, 'steps': 17474, 'loss/train': 1.8247954845428467} 08/30/2021 16:22:59 - INFO - __main__ - Step 17476: {'lr': 0.0004866328460866124, 'samples': 3355392, 'steps': 17475, 'loss/train': 1.255110740661621} 08/30/2021 16:22:59 - INFO - __main__ - Step 17477: {'lr': 0.0004866311340152433, 'samples': 3355584, 'steps': 17476, 'loss/train': 1.3190022706985474} 08/30/2021 16:23:01 - INFO - __main__ - Step 17478: {'lr': 0.0004866294218372518, 'samples': 3355776, 'steps': 17477, 'loss/train': 1.7746151685714722} 08/30/2021 16:23:02 - INFO - __main__ - Step 17479: {'lr': 0.0004866277095526387, 'samples': 3355968, 'steps': 17478, 'loss/train': 2.225783348083496} 08/30/2021 16:23:02 - INFO - __main__ - Step 17480: {'lr': 0.00048662599716140485, 'samples': 3356160, 'steps': 17479, 'loss/train': 1.618331789970398} 08/30/2021 16:23:03 - INFO - __main__ - Step 17481: {'lr': 0.00048662428466355104, 'samples': 3356352, 'steps': 17480, 'loss/train': 1.8510490655899048} 08/30/2021 16:23:03 - INFO - __main__ - Step 17482: {'lr': 0.0004866225720590779, 'samples': 3356544, 'steps': 17481, 'loss/train': 3.352268695831299} 08/30/2021 16:23:05 - INFO - __main__ - Step 17483: {'lr': 0.00048662085934798627, 'samples': 3356736, 'steps': 17482, 'loss/train': 1.5689951181411743} 08/30/2021 16:23:05 - INFO - __main__ - Step 17484: {'lr': 0.00048661914653027694, 'samples': 3356928, 'steps': 17483, 'loss/train': 1.9016592502593994} 08/30/2021 16:23:05 - INFO - __main__ - Step 17485: {'lr': 0.0004866174336059507, 'samples': 3357120, 'steps': 17484, 'loss/train': 0.360641211271286} 08/30/2021 16:23:06 - INFO - __main__ - Step 17486: {'lr': 0.00048661572057500833, 'samples': 3357312, 'steps': 17485, 'loss/train': 0.2026984840631485} 08/30/2021 16:23:06 - INFO - __main__ - Step 17487: {'lr': 0.00048661400743745057, 'samples': 3357504, 'steps': 17486, 'loss/train': 1.749847412109375} 08/30/2021 16:23:08 - INFO - __main__ - Step 17488: {'lr': 0.00048661229419327806, 'samples': 3357696, 'steps': 17487, 'loss/train': 1.402083158493042} 08/30/2021 16:23:08 - INFO - __main__ - Step 17489: {'lr': 0.0004866105808424918, 'samples': 3357888, 'steps': 17488, 'loss/train': 1.8154724836349487} 08/30/2021 16:23:09 - INFO - __main__ - Step 17490: {'lr': 0.0004866088673850925, 'samples': 3358080, 'steps': 17489, 'loss/train': 1.7261987924575806} 08/30/2021 16:23:09 - INFO - __main__ - Step 17491: {'lr': 0.0004866071538210808, 'samples': 3358272, 'steps': 17490, 'loss/train': 1.573549747467041} 08/30/2021 16:23:09 - INFO - __main__ - Step 17492: {'lr': 0.0004866054401504576, 'samples': 3358464, 'steps': 17491, 'loss/train': 2.3931453227996826} 08/30/2021 16:23:11 - INFO - __main__ - Step 17493: {'lr': 0.0004866037263732237, 'samples': 3358656, 'steps': 17492, 'loss/train': 1.9802180528640747} 08/30/2021 16:23:12 - INFO - __main__ - Step 17494: {'lr': 0.00048660201248937974, 'samples': 3358848, 'steps': 17493, 'loss/train': 1.6586722135543823} 08/30/2021 16:23:12 - INFO - __main__ - Step 17495: {'lr': 0.0004866002984989266, 'samples': 3359040, 'steps': 17494, 'loss/train': 1.571513056755066} 08/30/2021 16:23:12 - INFO - __main__ - Step 17496: {'lr': 0.000486598584401865, 'samples': 3359232, 'steps': 17495, 'loss/train': 2.110097646713257} 08/30/2021 16:23:13 - INFO - __main__ - Step 17497: {'lr': 0.0004865968701981958, 'samples': 3359424, 'steps': 17496, 'loss/train': 1.8144365549087524} 08/30/2021 16:23:13 - INFO - __main__ - Step 17498: {'lr': 0.0004865951558879196, 'samples': 3359616, 'steps': 17497, 'loss/train': 1.760158896446228} 08/30/2021 16:23:15 - INFO - __main__ - Step 17499: {'lr': 0.00048659344147103725, 'samples': 3359808, 'steps': 17498, 'loss/train': 0.44034385681152344} 08/30/2021 16:23:15 - INFO - __main__ - Step 17500: {'lr': 0.0004865917269475496, 'samples': 3360000, 'steps': 17499, 'loss/train': 1.6851074695587158} 08/30/2021 16:23:15 - INFO - __main__ - Step 17501: {'lr': 0.00048659001231745734, 'samples': 3360192, 'steps': 17500, 'loss/train': 1.7847763299942017} 08/30/2021 16:23:16 - INFO - __main__ - Step 17502: {'lr': 0.0004865882975807614, 'samples': 3360384, 'steps': 17501, 'loss/train': 1.5666096210479736} 08/30/2021 16:23:16 - INFO - __main__ - Step 17503: {'lr': 0.00048658658273746224, 'samples': 3360576, 'steps': 17502, 'loss/train': 1.6288776397705078} 08/30/2021 16:23:18 - INFO - __main__ - Step 17504: {'lr': 0.00048658486778756097, 'samples': 3360768, 'steps': 17503, 'loss/train': 1.1607974767684937} 08/30/2021 16:23:18 - INFO - __main__ - Step 17505: {'lr': 0.0004865831527310581, 'samples': 3360960, 'steps': 17504, 'loss/train': 1.639221429824829} 08/30/2021 16:23:18 - INFO - __main__ - Step 17506: {'lr': 0.00048658143756795456, 'samples': 3361152, 'steps': 17505, 'loss/train': 1.5825897455215454} 08/30/2021 16:23:19 - INFO - __main__ - Step 17507: {'lr': 0.0004865797222982511, 'samples': 3361344, 'steps': 17506, 'loss/train': 1.4309252500534058} 08/30/2021 16:23:19 - INFO - __main__ - Step 17508: {'lr': 0.0004865780069219484, 'samples': 3361536, 'steps': 17507, 'loss/train': 1.031682014465332} 08/30/2021 16:23:21 - INFO - __main__ - Step 17509: {'lr': 0.00048657629143904733, 'samples': 3361728, 'steps': 17508, 'loss/train': 1.5543208122253418} 08/30/2021 16:23:21 - INFO - __main__ - Step 17510: {'lr': 0.0004865745758495487, 'samples': 3361920, 'steps': 17509, 'loss/train': 2.160651206970215} 08/30/2021 16:23:22 - INFO - __main__ - Step 17511: {'lr': 0.00048657286015345313, 'samples': 3362112, 'steps': 17510, 'loss/train': 2.1131794452667236} 08/30/2021 16:23:22 - INFO - __main__ - Step 17512: {'lr': 0.00048657114435076153, 'samples': 3362304, 'steps': 17511, 'loss/train': 1.8827873468399048} 08/30/2021 16:23:22 - INFO - __main__ - Step 17513: {'lr': 0.00048656942844147464, 'samples': 3362496, 'steps': 17512, 'loss/train': 1.306170105934143} 08/30/2021 16:23:24 - INFO - __main__ - Step 17514: {'lr': 0.00048656771242559316, 'samples': 3362688, 'steps': 17513, 'loss/train': 1.6868219375610352} 08/30/2021 16:23:24 - INFO - __main__ - Step 17515: {'lr': 0.0004865659963031179, 'samples': 3362880, 'steps': 17514, 'loss/train': 1.9404577016830444} 08/30/2021 16:23:24 - INFO - __main__ - Step 17516: {'lr': 0.0004865642800740497, 'samples': 3363072, 'steps': 17515, 'loss/train': 1.8532264232635498} 08/30/2021 16:23:25 - INFO - __main__ - Step 17517: {'lr': 0.0004865625637383893, 'samples': 3363264, 'steps': 17516, 'loss/train': 1.0725972652435303} 08/30/2021 16:23:25 - INFO - __main__ - Step 17518: {'lr': 0.00048656084729613747, 'samples': 3363456, 'steps': 17517, 'loss/train': 1.7218142747879028} 08/30/2021 16:23:27 - INFO - __main__ - Step 17519: {'lr': 0.0004865591307472949, 'samples': 3363648, 'steps': 17518, 'loss/train': 1.6953128576278687} 08/30/2021 16:23:27 - INFO - __main__ - Step 17520: {'lr': 0.0004865574140918625, 'samples': 3363840, 'steps': 17519, 'loss/train': 1.5887824296951294} 08/30/2021 16:23:27 - INFO - __main__ - Step 17521: {'lr': 0.00048655569732984096, 'samples': 3364032, 'steps': 17520, 'loss/train': 1.7230455875396729} 08/30/2021 16:23:28 - INFO - __main__ - Step 17522: {'lr': 0.000486553980461231, 'samples': 3364224, 'steps': 17521, 'loss/train': 1.970909833908081} 08/30/2021 16:23:28 - INFO - __main__ - Step 17523: {'lr': 0.0004865522634860335, 'samples': 3364416, 'steps': 17522, 'loss/train': 1.807120442390442} 08/30/2021 16:23:30 - INFO - __main__ - Step 17524: {'lr': 0.00048655054640424936, 'samples': 3364608, 'steps': 17523, 'loss/train': 1.5671602487564087} 08/30/2021 16:23:30 - INFO - __main__ - Step 17525: {'lr': 0.00048654882921587907, 'samples': 3364800, 'steps': 17524, 'loss/train': 2.561570882797241} 08/30/2021 16:23:30 - INFO - __main__ - Step 17526: {'lr': 0.00048654711192092347, 'samples': 3364992, 'steps': 17525, 'loss/train': 0.830582857131958} 08/30/2021 16:23:31 - INFO - __main__ - Step 17527: {'lr': 0.0004865453945193835, 'samples': 3365184, 'steps': 17526, 'loss/train': 1.5798051357269287} 08/30/2021 16:23:31 - INFO - __main__ - Step 17528: {'lr': 0.00048654367701125975, 'samples': 3365376, 'steps': 17527, 'loss/train': 1.8259228467941284} 08/30/2021 16:23:33 - INFO - __main__ - Step 17529: {'lr': 0.0004865419593965531, 'samples': 3365568, 'steps': 17528, 'loss/train': 2.335393190383911} 08/30/2021 16:23:34 - INFO - __main__ - Step 17530: {'lr': 0.0004865402416752642, 'samples': 3365760, 'steps': 17529, 'loss/train': 1.5797656774520874} 08/30/2021 16:23:34 - INFO - __main__ - Step 17531: {'lr': 0.0004865385238473941, 'samples': 3365952, 'steps': 17530, 'loss/train': 1.0944950580596924} 08/30/2021 16:23:34 - INFO - __main__ - Step 17532: {'lr': 0.00048653680591294324, 'samples': 3366144, 'steps': 17531, 'loss/train': 1.232177972793579} 08/30/2021 16:23:35 - INFO - __main__ - Step 17533: {'lr': 0.00048653508787191256, 'samples': 3366336, 'steps': 17532, 'loss/train': 2.8243906497955322} 08/30/2021 16:23:37 - INFO - __main__ - Step 17534: {'lr': 0.00048653336972430297, 'samples': 3366528, 'steps': 17533, 'loss/train': 2.401196241378784} 08/30/2021 16:23:37 - INFO - __main__ - Step 17535: {'lr': 0.0004865316514701149, 'samples': 3366720, 'steps': 17534, 'loss/train': 1.4661340713500977} 08/30/2021 16:23:38 - INFO - __main__ - Step 17536: {'lr': 0.0004865299331093495, 'samples': 3366912, 'steps': 17535, 'loss/train': 1.7392544746398926} 08/30/2021 16:23:38 - INFO - __main__ - Step 17537: {'lr': 0.0004865282146420072, 'samples': 3367104, 'steps': 17536, 'loss/train': 1.827589988708496} 08/30/2021 16:23:38 - INFO - __main__ - Step 17538: {'lr': 0.000486526496068089, 'samples': 3367296, 'steps': 17537, 'loss/train': 1.1134750843048096} 08/30/2021 16:23:39 - INFO - __main__ - Step 17539: {'lr': 0.0004865247773875956, 'samples': 3367488, 'steps': 17538, 'loss/train': 1.734523892402649} 08/30/2021 16:23:39 - INFO - __main__ - Step 17540: {'lr': 0.0004865230586005278, 'samples': 3367680, 'steps': 17539, 'loss/train': 0.24024170637130737} 08/30/2021 16:23:41 - INFO - __main__ - Step 17541: {'lr': 0.00048652133970688633, 'samples': 3367872, 'steps': 17540, 'loss/train': 0.15640875697135925} 08/30/2021 16:23:41 - INFO - __main__ - Step 17542: {'lr': 0.00048651962070667197, 'samples': 3368064, 'steps': 17541, 'loss/train': 1.7502667903900146} 08/30/2021 16:23:41 - INFO - __main__ - Step 17543: {'lr': 0.00048651790159988563, 'samples': 3368256, 'steps': 17542, 'loss/train': 0.8552508354187012} 08/30/2021 16:23:42 - INFO - __main__ - Step 17544: {'lr': 0.0004865161823865279, 'samples': 3368448, 'steps': 17543, 'loss/train': 1.3909282684326172} 08/30/2021 16:23:42 - INFO - __main__ - Step 17545: {'lr': 0.0004865144630665996, 'samples': 3368640, 'steps': 17544, 'loss/train': 1.7435178756713867} 08/30/2021 16:23:44 - INFO - __main__ - Step 17546: {'lr': 0.0004865127436401016, 'samples': 3368832, 'steps': 17545, 'loss/train': 1.4475579261779785} 08/30/2021 16:23:44 - INFO - __main__ - Step 17547: {'lr': 0.00048651102410703464, 'samples': 3369024, 'steps': 17546, 'loss/train': 1.4390286207199097} 08/30/2021 16:23:44 - INFO - __main__ - Step 17548: {'lr': 0.00048650930446739936, 'samples': 3369216, 'steps': 17547, 'loss/train': 1.4975570440292358} 08/30/2021 16:23:45 - INFO - __main__ - Step 17549: {'lr': 0.00048650758472119666, 'samples': 3369408, 'steps': 17548, 'loss/train': 1.786547303199768} 08/30/2021 16:23:45 - INFO - __main__ - Step 17550: {'lr': 0.0004865058648684273, 'samples': 3369600, 'steps': 17549, 'loss/train': 1.720345139503479} 08/30/2021 16:23:46 - INFO - __main__ - Step 17551: {'lr': 0.00048650414490909207, 'samples': 3369792, 'steps': 17550, 'loss/train': 1.4965839385986328} 08/30/2021 16:23:47 - INFO - __main__ - Step 17552: {'lr': 0.00048650242484319175, 'samples': 3369984, 'steps': 17551, 'loss/train': 1.6356937885284424} 08/30/2021 16:23:47 - INFO - __main__ - Step 17553: {'lr': 0.000486500704670727, 'samples': 3370176, 'steps': 17552, 'loss/train': 1.6092661619186401} 08/30/2021 16:23:48 - INFO - __main__ - Step 17554: {'lr': 0.0004864989843916987, 'samples': 3370368, 'steps': 17553, 'loss/train': 1.1740132570266724} 08/30/2021 16:23:48 - INFO - __main__ - Step 17555: {'lr': 0.0004864972640061077, 'samples': 3370560, 'steps': 17554, 'loss/train': 1.7153794765472412} 08/30/2021 16:23:49 - INFO - __main__ - Step 17556: {'lr': 0.00048649554351395453, 'samples': 3370752, 'steps': 17555, 'loss/train': 2.135126829147339} 08/30/2021 16:23:50 - INFO - __main__ - Step 17557: {'lr': 0.00048649382291524024, 'samples': 3370944, 'steps': 17556, 'loss/train': 1.6388752460479736} 08/30/2021 16:23:50 - INFO - __main__ - Step 17558: {'lr': 0.0004864921022099654, 'samples': 3371136, 'steps': 17557, 'loss/train': 1.245361328125} 08/30/2021 16:23:51 - INFO - __main__ - Step 17559: {'lr': 0.00048649038139813097, 'samples': 3371328, 'steps': 17558, 'loss/train': 0.5165625214576721} 08/30/2021 16:23:51 - INFO - __main__ - Step 17560: {'lr': 0.00048648866047973756, 'samples': 3371520, 'steps': 17559, 'loss/train': 1.52119779586792} 08/30/2021 16:23:52 - INFO - __main__ - Step 17561: {'lr': 0.000486486939454786, 'samples': 3371712, 'steps': 17560, 'loss/train': 1.4700878858566284} 08/30/2021 16:23:53 - INFO - __main__ - Step 17562: {'lr': 0.0004864852183232771, 'samples': 3371904, 'steps': 17561, 'loss/train': 1.4670953750610352} 08/30/2021 16:23:53 - INFO - __main__ - Step 17563: {'lr': 0.0004864834970852116, 'samples': 3372096, 'steps': 17562, 'loss/train': 1.9046157598495483} 08/30/2021 16:23:54 - INFO - __main__ - Step 17564: {'lr': 0.0004864817757405903, 'samples': 3372288, 'steps': 17563, 'loss/train': 0.10192663967609406} 08/30/2021 16:23:54 - INFO - __main__ - Step 17565: {'lr': 0.0004864800542894139, 'samples': 3372480, 'steps': 17564, 'loss/train': 1.6360749006271362} 08/30/2021 16:23:56 - INFO - __main__ - Step 17566: {'lr': 0.0004864783327316833, 'samples': 3372672, 'steps': 17565, 'loss/train': 2.031972885131836} 08/30/2021 16:23:57 - INFO - __main__ - Step 17567: {'lr': 0.0004864766110673992, 'samples': 3372864, 'steps': 17566, 'loss/train': 1.7081667184829712} 08/30/2021 16:23:57 - INFO - __main__ - Step 17568: {'lr': 0.00048647488929656237, 'samples': 3373056, 'steps': 17567, 'loss/train': 1.829378604888916} 08/30/2021 16:23:57 - INFO - __main__ - Step 17569: {'lr': 0.00048647316741917365, 'samples': 3373248, 'steps': 17568, 'loss/train': 0.38812997937202454} 08/30/2021 16:23:58 - INFO - __main__ - Step 17570: {'lr': 0.0004864714454352337, 'samples': 3373440, 'steps': 17569, 'loss/train': 1.7490671873092651} 08/30/2021 16:23:59 - INFO - __main__ - Step 17571: {'lr': 0.00048646972334474343, 'samples': 3373632, 'steps': 17570, 'loss/train': 2.08906888961792} 08/30/2021 16:24:00 - INFO - __main__ - Step 17572: {'lr': 0.0004864680011477035, 'samples': 3373824, 'steps': 17571, 'loss/train': 1.4270910024642944} 08/30/2021 16:24:00 - INFO - __main__ - Step 17573: {'lr': 0.00048646627884411475, 'samples': 3374016, 'steps': 17572, 'loss/train': 1.5729337930679321} 08/30/2021 16:24:01 - INFO - __main__ - Step 17574: {'lr': 0.00048646455643397803, 'samples': 3374208, 'steps': 17573, 'loss/train': 1.4936065673828125} 08/30/2021 16:24:01 - INFO - __main__ - Step 17575: {'lr': 0.0004864628339172939, 'samples': 3374400, 'steps': 17574, 'loss/train': 2.0495150089263916} 08/30/2021 16:24:01 - INFO - __main__ - Step 17576: {'lr': 0.00048646111129406336, 'samples': 3374592, 'steps': 17575, 'loss/train': 1.1590380668640137} 08/30/2021 16:24:03 - INFO - __main__ - Step 17577: {'lr': 0.00048645938856428704, 'samples': 3374784, 'steps': 17576, 'loss/train': 1.0573232173919678} 08/30/2021 16:24:03 - INFO - __main__ - Step 17578: {'lr': 0.0004864576657279658, 'samples': 3374976, 'steps': 17577, 'loss/train': 1.2430789470672607} 08/30/2021 16:24:03 - INFO - __main__ - Step 17579: {'lr': 0.0004864559427851003, 'samples': 3375168, 'steps': 17578, 'loss/train': 1.875684142112732} 08/30/2021 16:24:04 - INFO - __main__ - Step 17580: {'lr': 0.0004864542197356915, 'samples': 3375360, 'steps': 17579, 'loss/train': 1.5721102952957153} 08/30/2021 16:24:04 - INFO - __main__ - Step 17581: {'lr': 0.00048645249657974007, 'samples': 3375552, 'steps': 17580, 'loss/train': 1.1137334108352661} 08/30/2021 16:24:06 - INFO - __main__ - Step 17582: {'lr': 0.00048645077331724675, 'samples': 3375744, 'steps': 17581, 'loss/train': 2.0492448806762695} 08/30/2021 16:24:06 - INFO - __main__ - Step 17583: {'lr': 0.00048644904994821236, 'samples': 3375936, 'steps': 17582, 'loss/train': 1.9140725135803223} 08/30/2021 16:24:06 - INFO - __main__ - Step 17584: {'lr': 0.0004864473264726377, 'samples': 3376128, 'steps': 17583, 'loss/train': 1.8759957551956177} 08/30/2021 16:24:07 - INFO - __main__ - Step 17585: {'lr': 0.00048644560289052354, 'samples': 3376320, 'steps': 17584, 'loss/train': 1.6567912101745605} 08/30/2021 16:24:07 - INFO - __main__ - Step 17586: {'lr': 0.0004864438792018706, 'samples': 3376512, 'steps': 17585, 'loss/train': 1.447975993156433} 08/30/2021 16:24:08 - INFO - __main__ - Step 17587: {'lr': 0.0004864421554066797, 'samples': 3376704, 'steps': 17586, 'loss/train': 1.0083297491073608} 08/30/2021 16:24:09 - INFO - __main__ - Step 17588: {'lr': 0.00048644043150495165, 'samples': 3376896, 'steps': 17587, 'loss/train': 1.7974839210510254} 08/30/2021 16:24:10 - INFO - __main__ - Step 17589: {'lr': 0.00048643870749668717, 'samples': 3377088, 'steps': 17588, 'loss/train': 1.3072870969772339} 08/30/2021 16:24:10 - INFO - __main__ - Step 17590: {'lr': 0.000486436983381887, 'samples': 3377280, 'steps': 17589, 'loss/train': 1.7835060358047485} 08/30/2021 16:24:11 - INFO - __main__ - Step 17591: {'lr': 0.0004864352591605521, 'samples': 3377472, 'steps': 17590, 'loss/train': 1.905362844467163} 08/30/2021 16:24:11 - INFO - __main__ - Step 17592: {'lr': 0.00048643353483268306, 'samples': 3377664, 'steps': 17591, 'loss/train': 1.7080096006393433} 08/30/2021 16:24:13 - INFO - __main__ - Step 17593: {'lr': 0.00048643181039828066, 'samples': 3377856, 'steps': 17592, 'loss/train': 1.9489187002182007} 08/30/2021 16:24:13 - INFO - __main__ - Step 17594: {'lr': 0.00048643008585734575, 'samples': 3378048, 'steps': 17593, 'loss/train': 0.11998263746500015} 08/30/2021 16:24:14 - INFO - __main__ - Step 17595: {'lr': 0.00048642836120987913, 'samples': 3378240, 'steps': 17594, 'loss/train': 2.023465156555176} 08/30/2021 16:24:14 - INFO - __main__ - Step 17596: {'lr': 0.0004864266364558816, 'samples': 3378432, 'steps': 17595, 'loss/train': 1.4682003259658813} 08/30/2021 16:24:14 - INFO - __main__ - Step 17597: {'lr': 0.00048642491159535373, 'samples': 3378624, 'steps': 17596, 'loss/train': 1.3541736602783203} 08/30/2021 16:24:15 - INFO - __main__ - Step 17598: {'lr': 0.0004864231866282965, 'samples': 3378816, 'steps': 17597, 'loss/train': 2.111245632171631} 08/30/2021 16:24:16 - INFO - __main__ - Step 17599: {'lr': 0.0004864214615547107, 'samples': 3379008, 'steps': 17598, 'loss/train': 1.268403172492981} 08/30/2021 16:24:16 - INFO - __main__ - Step 17600: {'lr': 0.000486419736374597, 'samples': 3379200, 'steps': 17599, 'loss/train': 1.5935360193252563} 08/30/2021 16:24:17 - INFO - __main__ - Step 17601: {'lr': 0.0004864180110879562, 'samples': 3379392, 'steps': 17600, 'loss/train': 1.3745697736740112} 08/30/2021 16:24:17 - INFO - __main__ - Step 17602: {'lr': 0.00048641628569478916, 'samples': 3379584, 'steps': 17601, 'loss/train': 1.301063895225525} 08/30/2021 16:24:18 - INFO - __main__ - Step 17603: {'lr': 0.00048641456019509643, 'samples': 3379776, 'steps': 17602, 'loss/train': 1.8030059337615967} 08/30/2021 16:24:19 - INFO - __main__ - Step 17604: {'lr': 0.0004864128345888791, 'samples': 3379968, 'steps': 17603, 'loss/train': 1.6895872354507446} 08/30/2021 16:24:20 - INFO - __main__ - Step 17605: {'lr': 0.0004864111088761377, 'samples': 3380160, 'steps': 17604, 'loss/train': 1.3598532676696777} 08/30/2021 16:24:20 - INFO - __main__ - Step 17606: {'lr': 0.00048640938305687315, 'samples': 3380352, 'steps': 17605, 'loss/train': 0.15379035472869873} 08/30/2021 16:24:21 - INFO - __main__ - Step 17607: {'lr': 0.00048640765713108615, 'samples': 3380544, 'steps': 17606, 'loss/train': 1.9393595457077026} 08/30/2021 16:24:21 - INFO - __main__ - Step 17608: {'lr': 0.00048640593109877754, 'samples': 3380736, 'steps': 17607, 'loss/train': 0.3218410015106201} 08/30/2021 16:24:21 - INFO - __main__ - Step 17609: {'lr': 0.00048640420495994806, 'samples': 3380928, 'steps': 17608, 'loss/train': 1.898372769355774} 08/30/2021 16:24:23 - INFO - __main__ - Step 17610: {'lr': 0.0004864024787145985, 'samples': 3381120, 'steps': 17609, 'loss/train': 1.7394880056381226} 08/30/2021 16:24:23 - INFO - __main__ - Step 17611: {'lr': 0.00048640075236272963, 'samples': 3381312, 'steps': 17610, 'loss/train': 1.656727910041809} 08/30/2021 16:24:24 - INFO - __main__ - Step 17612: {'lr': 0.00048639902590434214, 'samples': 3381504, 'steps': 17611, 'loss/train': 1.1785953044891357} 08/30/2021 16:24:24 - INFO - __main__ - Step 17613: {'lr': 0.000486397299339437, 'samples': 3381696, 'steps': 17612, 'loss/train': 1.621639609336853} 08/30/2021 16:24:24 - INFO - __main__ - Step 17614: {'lr': 0.0004863955726680149, 'samples': 3381888, 'steps': 17613, 'loss/train': 1.469756007194519} 08/30/2021 16:24:26 - INFO - __main__ - Step 17615: {'lr': 0.0004863938458900765, 'samples': 3382080, 'steps': 17614, 'loss/train': 1.897817611694336} 08/30/2021 16:24:27 - INFO - __main__ - Step 17616: {'lr': 0.0004863921190056227, 'samples': 3382272, 'steps': 17615, 'loss/train': 1.5590382814407349} 08/30/2021 16:24:27 - INFO - __main__ - Step 17617: {'lr': 0.0004863903920146544, 'samples': 3382464, 'steps': 17616, 'loss/train': 1.265742540359497} 08/30/2021 16:24:28 - INFO - __main__ - Step 17618: {'lr': 0.00048638866491717214, 'samples': 3382656, 'steps': 17617, 'loss/train': 2.574831247329712} 08/30/2021 16:24:28 - INFO - __main__ - Step 17619: {'lr': 0.00048638693771317675, 'samples': 3382848, 'steps': 17618, 'loss/train': 1.6485815048217773} 08/30/2021 16:24:28 - INFO - __main__ - Step 17620: {'lr': 0.0004863852104026691, 'samples': 3383040, 'steps': 17619, 'loss/train': 1.6006711721420288} 08/30/2021 16:24:30 - INFO - __main__ - Step 17621: {'lr': 0.00048638348298564996, 'samples': 3383232, 'steps': 17620, 'loss/train': 1.7198574542999268} 08/30/2021 16:24:31 - INFO - __main__ - Step 17622: {'lr': 0.00048638175546212, 'samples': 3383424, 'steps': 17621, 'loss/train': 2.257721424102783} 08/30/2021 16:24:31 - INFO - __main__ - Step 17623: {'lr': 0.00048638002783208013, 'samples': 3383616, 'steps': 17622, 'loss/train': 1.4844609498977661} 08/30/2021 16:24:31 - INFO - __main__ - Step 17624: {'lr': 0.000486378300095531, 'samples': 3383808, 'steps': 17623, 'loss/train': 1.7797285318374634} 08/30/2021 16:24:32 - INFO - __main__ - Step 17625: {'lr': 0.0004863765722524735, 'samples': 3384000, 'steps': 17624, 'loss/train': 1.936982274055481} 08/30/2021 16:24:33 - INFO - __main__ - Step 17626: {'lr': 0.0004863748443029083, 'samples': 3384192, 'steps': 17625, 'loss/train': 1.141573190689087} 08/30/2021 16:24:34 - INFO - __main__ - Step 17627: {'lr': 0.00048637311624683634, 'samples': 3384384, 'steps': 17626, 'loss/train': 1.7004591226577759} 08/30/2021 16:24:34 - INFO - __main__ - Step 17628: {'lr': 0.0004863713880842583, 'samples': 3384576, 'steps': 17627, 'loss/train': 1.8569802045822144} 08/30/2021 16:24:34 - INFO - __main__ - Step 17629: {'lr': 0.0004863696598151749, 'samples': 3384768, 'steps': 17628, 'loss/train': 1.8134541511535645} 08/30/2021 16:24:35 - INFO - __main__ - Step 17630: {'lr': 0.00048636793143958695, 'samples': 3384960, 'steps': 17629, 'loss/train': 1.7280523777008057} 08/30/2021 16:24:35 - INFO - __main__ - Step 17631: {'lr': 0.00048636620295749533, 'samples': 3385152, 'steps': 17630, 'loss/train': 1.4507464170455933} 08/30/2021 16:24:36 - INFO - __main__ - Step 17632: {'lr': 0.00048636447436890075, 'samples': 3385344, 'steps': 17631, 'loss/train': 1.9362410306930542} 08/30/2021 16:24:37 - INFO - __main__ - Step 17633: {'lr': 0.0004863627456738039, 'samples': 3385536, 'steps': 17632, 'loss/train': 2.50399112701416} 08/30/2021 16:24:37 - INFO - __main__ - Step 17634: {'lr': 0.00048636101687220566, 'samples': 3385728, 'steps': 17633, 'loss/train': 0.6674114465713501} 08/30/2021 16:24:38 - INFO - __main__ - Step 17635: {'lr': 0.0004863592879641069, 'samples': 3385920, 'steps': 17634, 'loss/train': 2.0079925060272217} 08/30/2021 16:24:38 - INFO - __main__ - Step 17636: {'lr': 0.0004863575589495082, 'samples': 3386112, 'steps': 17635, 'loss/train': 1.5300225019454956} 08/30/2021 16:24:40 - INFO - __main__ - Step 17637: {'lr': 0.00048635582982841047, 'samples': 3386304, 'steps': 17636, 'loss/train': 2.4551563262939453} 08/30/2021 16:24:41 - INFO - __main__ - Step 17638: {'lr': 0.0004863541006008144, 'samples': 3386496, 'steps': 17637, 'loss/train': 1.9068865776062012} 08/30/2021 16:24:41 - INFO - __main__ - Step 17639: {'lr': 0.0004863523712667209, 'samples': 3386688, 'steps': 17638, 'loss/train': 1.994493007659912} 08/30/2021 16:24:41 - INFO - __main__ - Step 17640: {'lr': 0.00048635064182613063, 'samples': 3386880, 'steps': 17639, 'loss/train': 1.995773196220398} 08/30/2021 16:24:42 - INFO - __main__ - Step 17641: {'lr': 0.00048634891227904435, 'samples': 3387072, 'steps': 17640, 'loss/train': 1.3929442167282104} 08/30/2021 16:24:43 - INFO - __main__ - Step 17642: {'lr': 0.00048634718262546297, 'samples': 3387264, 'steps': 17641, 'loss/train': 1.0950262546539307} 08/30/2021 16:24:44 - INFO - __main__ - Step 17643: {'lr': 0.0004863454528653872, 'samples': 3387456, 'steps': 17642, 'loss/train': 1.6616877317428589} 08/30/2021 16:24:44 - INFO - __main__ - Step 17644: {'lr': 0.0004863437229988178, 'samples': 3387648, 'steps': 17643, 'loss/train': 1.6589170694351196} 08/30/2021 16:24:44 - INFO - __main__ - Step 17645: {'lr': 0.00048634199302575554, 'samples': 3387840, 'steps': 17644, 'loss/train': 1.4650273323059082} 08/30/2021 16:24:45 - INFO - __main__ - Step 17646: {'lr': 0.00048634026294620125, 'samples': 3388032, 'steps': 17645, 'loss/train': 1.4868621826171875} 08/30/2021 16:24:46 - INFO - __main__ - Step 17647: {'lr': 0.00048633853276015566, 'samples': 3388224, 'steps': 17646, 'loss/train': 2.0076630115509033} 08/30/2021 16:24:47 - INFO - __main__ - Step 17648: {'lr': 0.00048633680246761956, 'samples': 3388416, 'steps': 17647, 'loss/train': 1.830798864364624} 08/30/2021 16:24:47 - INFO - __main__ - Step 17649: {'lr': 0.00048633507206859383, 'samples': 3388608, 'steps': 17648, 'loss/train': 2.4800283908843994} 08/30/2021 16:24:47 - INFO - __main__ - Step 17650: {'lr': 0.00048633334156307907, 'samples': 3388800, 'steps': 17649, 'loss/train': 1.6565618515014648} 08/30/2021 16:24:48 - INFO - __main__ - Step 17651: {'lr': 0.0004863316109510762, 'samples': 3388992, 'steps': 17650, 'loss/train': 1.6478811502456665} 08/30/2021 16:24:49 - INFO - __main__ - Step 17652: {'lr': 0.00048632988023258596, 'samples': 3389184, 'steps': 17651, 'loss/train': 1.6498517990112305} 08/30/2021 16:24:50 - INFO - __main__ - Step 17653: {'lr': 0.00048632814940760907, 'samples': 3389376, 'steps': 17652, 'loss/train': 1.7267106771469116} 08/30/2021 16:24:50 - INFO - __main__ - Step 17654: {'lr': 0.00048632641847614645, 'samples': 3389568, 'steps': 17653, 'loss/train': 1.8104838132858276} 08/30/2021 16:24:50 - INFO - __main__ - Step 17655: {'lr': 0.0004863246874381987, 'samples': 3389760, 'steps': 17654, 'loss/train': 0.7106810808181763} 08/30/2021 16:24:51 - INFO - __main__ - Step 17656: {'lr': 0.00048632295629376675, 'samples': 3389952, 'steps': 17655, 'loss/train': 1.741978406906128} 08/30/2021 16:24:52 - INFO - __main__ - Step 17657: {'lr': 0.00048632122504285133, 'samples': 3390144, 'steps': 17656, 'loss/train': 1.5844680070877075} 08/30/2021 16:24:53 - INFO - __main__ - Step 17658: {'lr': 0.0004863194936854531, 'samples': 3390336, 'steps': 17657, 'loss/train': 1.7016268968582153} 08/30/2021 16:24:53 - INFO - __main__ - Step 17659: {'lr': 0.0004863177622215731, 'samples': 3390528, 'steps': 17658, 'loss/train': 1.6292468309402466} 08/30/2021 16:24:54 - INFO - __main__ - Step 17660: {'lr': 0.00048631603065121186, 'samples': 3390720, 'steps': 17659, 'loss/train': 1.6936275959014893} 08/30/2021 16:24:54 - INFO - __main__ - Step 17661: {'lr': 0.00048631429897437033, 'samples': 3390912, 'steps': 17660, 'loss/train': 0.9331439733505249} 08/30/2021 16:24:54 - INFO - __main__ - Step 17662: {'lr': 0.0004863125671910492, 'samples': 3391104, 'steps': 17661, 'loss/train': 6.046341896057129} 08/30/2021 16:24:55 - INFO - __main__ - Step 17663: {'lr': 0.00048631083530124934, 'samples': 3391296, 'steps': 17662, 'loss/train': 1.7382398843765259} 08/30/2021 16:24:56 - INFO - __main__ - Step 17664: {'lr': 0.00048630910330497133, 'samples': 3391488, 'steps': 17663, 'loss/train': 1.9881970882415771} 08/30/2021 16:24:57 - INFO - __main__ - Step 17665: {'lr': 0.0004863073712022162, 'samples': 3391680, 'steps': 17664, 'loss/train': 1.7396708726882935} 08/30/2021 16:24:57 - INFO - __main__ - Step 17666: {'lr': 0.00048630563899298453, 'samples': 3391872, 'steps': 17665, 'loss/train': 1.8456741571426392} 08/30/2021 16:24:57 - INFO - __main__ - Step 17667: {'lr': 0.00048630390667727725, 'samples': 3392064, 'steps': 17666, 'loss/train': 1.488634467124939} 08/30/2021 16:24:58 - INFO - __main__ - Step 17668: {'lr': 0.00048630217425509503, 'samples': 3392256, 'steps': 17667, 'loss/train': 1.8691930770874023} 08/30/2021 16:24:59 - INFO - __main__ - Step 17669: {'lr': 0.00048630044172643874, 'samples': 3392448, 'steps': 17668, 'loss/train': 1.8067786693572998} 08/30/2021 16:25:00 - INFO - __main__ - Step 17670: {'lr': 0.0004862987090913091, 'samples': 3392640, 'steps': 17669, 'loss/train': 1.7889330387115479} 08/30/2021 16:25:00 - INFO - __main__ - Step 17671: {'lr': 0.0004862969763497069, 'samples': 3392832, 'steps': 17670, 'loss/train': 1.8399053812026978} 08/30/2021 16:25:01 - INFO - __main__ - Step 17672: {'lr': 0.0004862952435016329, 'samples': 3393024, 'steps': 17671, 'loss/train': 1.7011256217956543} 08/30/2021 16:25:01 - INFO - __main__ - Step 17673: {'lr': 0.00048629351054708795, 'samples': 3393216, 'steps': 17672, 'loss/train': 1.8765562772750854} 08/30/2021 16:25:02 - INFO - __main__ - Step 17674: {'lr': 0.0004862917774860728, 'samples': 3393408, 'steps': 17673, 'loss/train': 0.143140971660614} 08/30/2021 16:25:03 - INFO - __main__ - Step 17675: {'lr': 0.0004862900443185882, 'samples': 3393600, 'steps': 17674, 'loss/train': 0.4153665006160736} 08/30/2021 16:25:03 - INFO - __main__ - Step 17676: {'lr': 0.00048628831104463496, 'samples': 3393792, 'steps': 17675, 'loss/train': 1.7494155168533325} 08/30/2021 16:25:04 - INFO - __main__ - Step 17677: {'lr': 0.0004862865776642138, 'samples': 3393984, 'steps': 17676, 'loss/train': 1.814841389656067} 08/30/2021 16:25:04 - INFO - __main__ - Step 17678: {'lr': 0.00048628484417732567, 'samples': 3394176, 'steps': 17677, 'loss/train': 1.5618295669555664} 08/30/2021 16:25:06 - INFO - __main__ - Step 17679: {'lr': 0.00048628311058397113, 'samples': 3394368, 'steps': 17678, 'loss/train': 0.9141178727149963} 08/30/2021 16:25:06 - INFO - __main__ - Step 17680: {'lr': 0.0004862813768841511, 'samples': 3394560, 'steps': 17679, 'loss/train': 1.3781713247299194} 08/30/2021 16:25:06 - INFO - __main__ - Step 17681: {'lr': 0.0004862796430778663, 'samples': 3394752, 'steps': 17680, 'loss/train': 1.9683810472488403} 08/30/2021 16:25:07 - INFO - __main__ - Step 17682: {'lr': 0.0004862779091651176, 'samples': 3394944, 'steps': 17681, 'loss/train': 2.0991878509521484} 08/30/2021 16:25:07 - INFO - __main__ - Step 17683: {'lr': 0.0004862761751459057, 'samples': 3395136, 'steps': 17682, 'loss/train': 2.1489808559417725} 08/30/2021 16:25:09 - INFO - __main__ - Step 17684: {'lr': 0.0004862744410202314, 'samples': 3395328, 'steps': 17683, 'loss/train': 1.5708801746368408} 08/30/2021 16:25:09 - INFO - __main__ - Step 17685: {'lr': 0.00048627270678809544, 'samples': 3395520, 'steps': 17684, 'loss/train': 1.5949734449386597} 08/30/2021 16:25:09 - INFO - __main__ - Step 17686: {'lr': 0.0004862709724494987, 'samples': 3395712, 'steps': 17685, 'loss/train': 1.6808841228485107} 08/30/2021 16:25:10 - INFO - __main__ - Step 17687: {'lr': 0.0004862692380044419, 'samples': 3395904, 'steps': 17686, 'loss/train': 1.69366455078125} 08/30/2021 16:25:10 - INFO - __main__ - Step 17688: {'lr': 0.0004862675034529258, 'samples': 3396096, 'steps': 17687, 'loss/train': 1.183712124824524} 08/30/2021 16:25:12 - INFO - __main__ - Step 17689: {'lr': 0.0004862657687949512, 'samples': 3396288, 'steps': 17688, 'loss/train': 1.6497210264205933} 08/30/2021 16:25:12 - INFO - __main__ - Step 17690: {'lr': 0.00048626403403051894, 'samples': 3396480, 'steps': 17689, 'loss/train': 1.8684240579605103} 08/30/2021 16:25:13 - INFO - __main__ - Step 17691: {'lr': 0.00048626229915962974, 'samples': 3396672, 'steps': 17690, 'loss/train': 0.08506304025650024} 08/30/2021 16:25:13 - INFO - __main__ - Step 17692: {'lr': 0.00048626056418228436, 'samples': 3396864, 'steps': 17691, 'loss/train': 2.190805435180664} 08/30/2021 16:25:13 - INFO - __main__ - Step 17693: {'lr': 0.0004862588290984836, 'samples': 3397056, 'steps': 17692, 'loss/train': 1.9205013513565063} 08/30/2021 16:25:14 - INFO - __main__ - Step 17694: {'lr': 0.0004862570939082283, 'samples': 3397248, 'steps': 17693, 'loss/train': 1.5624686479568481} 08/30/2021 16:25:16 - INFO - __main__ - Step 17695: {'lr': 0.0004862553586115192, 'samples': 3397440, 'steps': 17694, 'loss/train': 1.7238426208496094} 08/30/2021 16:25:16 - INFO - __main__ - Step 17696: {'lr': 0.00048625362320835707, 'samples': 3397632, 'steps': 17695, 'loss/train': 1.9803744554519653} 08/30/2021 16:25:17 - INFO - __main__ - Step 17697: {'lr': 0.00048625188769874274, 'samples': 3397824, 'steps': 17696, 'loss/train': 1.5344154834747314} 08/30/2021 16:25:17 - INFO - __main__ - Step 17698: {'lr': 0.0004862501520826769, 'samples': 3398016, 'steps': 17697, 'loss/train': 0.9941984415054321} 08/30/2021 16:25:17 - INFO - __main__ - Step 17699: {'lr': 0.0004862484163601604, 'samples': 3398208, 'steps': 17698, 'loss/train': 0.08878421783447266} 08/30/2021 16:25:19 - INFO - __main__ - Step 17700: {'lr': 0.000486246680531194, 'samples': 3398400, 'steps': 17699, 'loss/train': 1.453533411026001} 08/30/2021 16:25:19 - INFO - __main__ - Step 17701: {'lr': 0.0004862449445957785, 'samples': 3398592, 'steps': 17700, 'loss/train': 1.675041913986206} 08/30/2021 16:25:20 - INFO - __main__ - Step 17702: {'lr': 0.00048624320855391467, 'samples': 3398784, 'steps': 17701, 'loss/train': 1.457558035850525} 08/30/2021 16:25:20 - INFO - __main__ - Step 17703: {'lr': 0.00048624147240560335, 'samples': 3398976, 'steps': 17702, 'loss/train': 1.555201530456543} 08/30/2021 16:25:20 - INFO - __main__ - Step 17704: {'lr': 0.00048623973615084516, 'samples': 3399168, 'steps': 17703, 'loss/train': 1.6829344034194946} 08/30/2021 16:25:22 - INFO - __main__ - Step 17705: {'lr': 0.0004862379997896411, 'samples': 3399360, 'steps': 17704, 'loss/train': 1.406872272491455} 08/30/2021 16:25:22 - INFO - __main__ - Step 17706: {'lr': 0.0004862362633219918, 'samples': 3399552, 'steps': 17705, 'loss/train': 1.8866908550262451} 08/30/2021 16:25:23 - INFO - __main__ - Step 17707: {'lr': 0.000486234526747898, 'samples': 3399744, 'steps': 17706, 'loss/train': 1.6731010675430298} 08/30/2021 16:25:23 - INFO - __main__ - Step 17708: {'lr': 0.0004862327900673607, 'samples': 3399936, 'steps': 17707, 'loss/train': 2.172962188720703} 08/30/2021 16:25:23 - INFO - __main__ - Step 17709: {'lr': 0.00048623105328038054, 'samples': 3400128, 'steps': 17708, 'loss/train': 1.1505485773086548} 08/30/2021 16:25:25 - INFO - __main__ - Step 17710: {'lr': 0.0004862293163869582, 'samples': 3400320, 'steps': 17709, 'loss/train': 1.3676457405090332} 08/30/2021 16:25:25 - INFO - __main__ - Step 17711: {'lr': 0.00048622757938709466, 'samples': 3400512, 'steps': 17710, 'loss/train': 0.37289196252822876} 08/30/2021 16:25:26 - INFO - __main__ - Step 17712: {'lr': 0.0004862258422807906, 'samples': 3400704, 'steps': 17711, 'loss/train': 1.7323291301727295} 08/30/2021 16:25:26 - INFO - __main__ - Step 17713: {'lr': 0.0004862241050680468, 'samples': 3400896, 'steps': 17712, 'loss/train': 2.248530864715576} 08/30/2021 16:25:26 - INFO - __main__ - Step 17714: {'lr': 0.00048622236774886415, 'samples': 3401088, 'steps': 17713, 'loss/train': 0.818747878074646} 08/30/2021 16:25:28 - INFO - __main__ - Step 17715: {'lr': 0.00048622063032324324, 'samples': 3401280, 'steps': 17714, 'loss/train': 1.9397470951080322} 08/30/2021 16:25:28 - INFO - __main__ - Step 17716: {'lr': 0.000486218892791185, 'samples': 3401472, 'steps': 17715, 'loss/train': 3.122344493865967} 08/30/2021 16:25:29 - INFO - __main__ - Step 17717: {'lr': 0.00048621715515269017, 'samples': 3401664, 'steps': 17716, 'loss/train': 1.2338253259658813} 08/30/2021 16:25:29 - INFO - __main__ - Step 17718: {'lr': 0.0004862154174077595, 'samples': 3401856, 'steps': 17717, 'loss/train': 1.7586365938186646} 08/30/2021 16:25:29 - INFO - __main__ - Step 17719: {'lr': 0.00048621367955639395, 'samples': 3402048, 'steps': 17718, 'loss/train': 1.6339696645736694} 08/30/2021 16:25:31 - INFO - __main__ - Step 17720: {'lr': 0.00048621194159859403, 'samples': 3402240, 'steps': 17719, 'loss/train': 1.7732384204864502} 08/30/2021 16:25:31 - INFO - __main__ - Step 17721: {'lr': 0.0004862102035343607, 'samples': 3402432, 'steps': 17720, 'loss/train': 2.0181620121002197} 08/30/2021 16:25:32 - INFO - __main__ - Step 17722: {'lr': 0.0004862084653636947, 'samples': 3402624, 'steps': 17721, 'loss/train': 2.088188886642456} 08/30/2021 16:25:32 - INFO - __main__ - Step 17723: {'lr': 0.00048620672708659675, 'samples': 3402816, 'steps': 17722, 'loss/train': 2.3807716369628906} 08/30/2021 16:25:32 - INFO - __main__ - Step 17724: {'lr': 0.0004862049887030677, 'samples': 3403008, 'steps': 17723, 'loss/train': 1.3474513292312622} 08/30/2021 16:25:34 - INFO - __main__ - Step 17725: {'lr': 0.0004862032502131084, 'samples': 3403200, 'steps': 17724, 'loss/train': 1.401879072189331} 08/30/2021 16:25:34 - INFO - __main__ - Step 17726: {'lr': 0.00048620151161671955, 'samples': 3403392, 'steps': 17725, 'loss/train': 1.8139903545379639} 08/30/2021 16:25:35 - INFO - __main__ - Step 17727: {'lr': 0.00048619977291390186, 'samples': 3403584, 'steps': 17726, 'loss/train': 2.8312020301818848} 08/30/2021 16:25:35 - INFO - __main__ - Step 17728: {'lr': 0.00048619803410465624, 'samples': 3403776, 'steps': 17727, 'loss/train': 1.4648650884628296} 08/30/2021 16:25:36 - INFO - __main__ - Step 17729: {'lr': 0.00048619629518898344, 'samples': 3403968, 'steps': 17728, 'loss/train': 2.1914825439453125} 08/30/2021 16:25:36 - INFO - __main__ - Step 17730: {'lr': 0.00048619455616688426, 'samples': 3404160, 'steps': 17729, 'loss/train': 1.0621435642242432} 08/30/2021 16:25:37 - INFO - __main__ - Step 17731: {'lr': 0.0004861928170383594, 'samples': 3404352, 'steps': 17730, 'loss/train': 1.7239242792129517} 08/30/2021 16:25:38 - INFO - __main__ - Step 17732: {'lr': 0.0004861910778034098, 'samples': 3404544, 'steps': 17731, 'loss/train': 1.5181375741958618} 08/30/2021 16:25:38 - INFO - __main__ - Step 17733: {'lr': 0.00048618933846203606, 'samples': 3404736, 'steps': 17732, 'loss/train': 1.8347440958023071} 08/30/2021 16:25:38 - INFO - __main__ - Step 17734: {'lr': 0.00048618759901423905, 'samples': 3404928, 'steps': 17733, 'loss/train': 1.5305198431015015} 08/30/2021 16:25:39 - INFO - __main__ - Step 17735: {'lr': 0.0004861858594600196, 'samples': 3405120, 'steps': 17734, 'loss/train': 1.7854728698730469} 08/30/2021 16:25:40 - INFO - __main__ - Step 17736: {'lr': 0.0004861841197993784, 'samples': 3405312, 'steps': 17735, 'loss/train': 1.6548168659210205} 08/30/2021 16:25:41 - INFO - __main__ - Step 17737: {'lr': 0.0004861823800323163, 'samples': 3405504, 'steps': 17736, 'loss/train': 1.2652748823165894} 08/30/2021 16:25:41 - INFO - __main__ - Step 17738: {'lr': 0.00048618064015883405, 'samples': 3405696, 'steps': 17737, 'loss/train': 1.4637962579727173} 08/30/2021 16:25:41 - INFO - __main__ - Step 17739: {'lr': 0.0004861789001789325, 'samples': 3405888, 'steps': 17738, 'loss/train': 1.7666879892349243} 08/30/2021 16:25:42 - INFO - __main__ - Step 17740: {'lr': 0.00048617716009261236, 'samples': 3406080, 'steps': 17739, 'loss/train': 1.6758126020431519} 08/30/2021 16:25:43 - INFO - __main__ - Step 17741: {'lr': 0.00048617541989987435, 'samples': 3406272, 'steps': 17740, 'loss/train': 1.4668971300125122} 08/30/2021 16:25:44 - INFO - __main__ - Step 17742: {'lr': 0.00048617367960071946, 'samples': 3406464, 'steps': 17741, 'loss/train': 1.4784157276153564} 08/30/2021 16:25:44 - INFO - __main__ - Step 17743: {'lr': 0.0004861719391951483, 'samples': 3406656, 'steps': 17742, 'loss/train': 1.6684218645095825} 08/30/2021 16:25:44 - INFO - __main__ - Step 17744: {'lr': 0.0004861701986831617, 'samples': 3406848, 'steps': 17743, 'loss/train': 1.5837866067886353} 08/30/2021 16:25:45 - INFO - __main__ - Step 17745: {'lr': 0.0004861684580647605, 'samples': 3407040, 'steps': 17744, 'loss/train': 1.8455150127410889} 08/30/2021 16:25:47 - INFO - __main__ - Step 17746: {'lr': 0.0004861667173399453, 'samples': 3407232, 'steps': 17745, 'loss/train': 1.2570794820785522} 08/30/2021 16:25:48 - INFO - __main__ - Step 17747: {'lr': 0.0004861649765087172, 'samples': 3407424, 'steps': 17746, 'loss/train': 2.085454225540161} 08/30/2021 16:25:48 - INFO - __main__ - Step 17748: {'lr': 0.0004861632355710767, 'samples': 3407616, 'steps': 17747, 'loss/train': 1.643376350402832} 08/30/2021 16:25:48 - INFO - __main__ - Step 17749: {'lr': 0.00048616149452702473, 'samples': 3407808, 'steps': 17748, 'loss/train': 2.5802743434906006} 08/30/2021 16:25:49 - INFO - __main__ - Step 17750: {'lr': 0.00048615975337656204, 'samples': 3408000, 'steps': 17749, 'loss/train': 1.4473512172698975} 08/30/2021 16:25:49 - INFO - __main__ - Step 17751: {'lr': 0.00048615801211968936, 'samples': 3408192, 'steps': 17750, 'loss/train': 1.7644591331481934} 08/30/2021 16:25:51 - INFO - __main__ - Step 17752: {'lr': 0.00048615627075640754, 'samples': 3408384, 'steps': 17751, 'loss/train': 1.8071231842041016} 08/30/2021 16:25:51 - INFO - __main__ - Step 17753: {'lr': 0.00048615452928671746, 'samples': 3408576, 'steps': 17752, 'loss/train': 2.0351507663726807} 08/30/2021 16:25:51 - INFO - __main__ - Step 17754: {'lr': 0.00048615278771061966, 'samples': 3408768, 'steps': 17753, 'loss/train': 0.9494560360908508} 08/30/2021 16:25:52 - INFO - __main__ - Step 17755: {'lr': 0.0004861510460281151, 'samples': 3408960, 'steps': 17754, 'loss/train': 6.22068977355957} 08/30/2021 16:25:52 - INFO - __main__ - Step 17756: {'lr': 0.0004861493042392045, 'samples': 3409152, 'steps': 17755, 'loss/train': 2.4171478748321533} 08/30/2021 16:25:54 - INFO - __main__ - Step 17757: {'lr': 0.00048614756234388866, 'samples': 3409344, 'steps': 17756, 'loss/train': 1.8834068775177002} 08/30/2021 16:25:54 - INFO - __main__ - Step 17758: {'lr': 0.00048614582034216844, 'samples': 3409536, 'steps': 17757, 'loss/train': 1.4243308305740356} 08/30/2021 16:25:54 - INFO - __main__ - Step 17759: {'lr': 0.0004861440782340445, 'samples': 3409728, 'steps': 17758, 'loss/train': 1.5687111616134644} 08/30/2021 16:25:55 - INFO - __main__ - Step 17760: {'lr': 0.0004861423360195177, 'samples': 3409920, 'steps': 17759, 'loss/train': 1.073167324066162} 08/30/2021 16:25:55 - INFO - __main__ - Step 17761: {'lr': 0.0004861405936985888, 'samples': 3410112, 'steps': 17760, 'loss/train': 1.616040587425232} 08/30/2021 16:25:57 - INFO - __main__ - Step 17762: {'lr': 0.0004861388512712586, 'samples': 3410304, 'steps': 17761, 'loss/train': 1.6898744106292725} 08/30/2021 16:25:57 - INFO - __main__ - Step 17763: {'lr': 0.0004861371087375279, 'samples': 3410496, 'steps': 17762, 'loss/train': 2.581831693649292} 08/30/2021 16:25:58 - INFO - __main__ - Step 17764: {'lr': 0.0004861353660973974, 'samples': 3410688, 'steps': 17763, 'loss/train': 1.838334560394287} 08/30/2021 16:25:58 - INFO - __main__ - Step 17765: {'lr': 0.00048613362335086797, 'samples': 3410880, 'steps': 17764, 'loss/train': 1.6511179208755493} 08/30/2021 16:25:58 - INFO - __main__ - Step 17766: {'lr': 0.00048613188049794045, 'samples': 3411072, 'steps': 17765, 'loss/train': 1.6235308647155762} 08/30/2021 16:25:59 - INFO - __main__ - Step 17767: {'lr': 0.00048613013753861546, 'samples': 3411264, 'steps': 17766, 'loss/train': 1.9086244106292725} 08/30/2021 16:26:00 - INFO - __main__ - Step 17768: {'lr': 0.0004861283944728939, 'samples': 3411456, 'steps': 17767, 'loss/train': 1.6346663236618042} 08/30/2021 16:26:00 - INFO - __main__ - Step 17769: {'lr': 0.0004861266513007765, 'samples': 3411648, 'steps': 17768, 'loss/train': 1.9003173112869263} 08/30/2021 16:26:01 - INFO - __main__ - Step 17770: {'lr': 0.00048612490802226415, 'samples': 3411840, 'steps': 17769, 'loss/train': 1.941716194152832} 08/30/2021 16:26:01 - INFO - __main__ - Step 17771: {'lr': 0.0004861231646373575, 'samples': 3412032, 'steps': 17770, 'loss/train': 2.2606074810028076} 08/30/2021 16:26:02 - INFO - __main__ - Step 17772: {'lr': 0.0004861214211460574, 'samples': 3412224, 'steps': 17771, 'loss/train': 1.241268515586853} 08/30/2021 16:26:03 - INFO - __main__ - Step 17773: {'lr': 0.00048611967754836466, 'samples': 3412416, 'steps': 17772, 'loss/train': 1.577620506286621} 08/30/2021 16:26:03 - INFO - __main__ - Step 17774: {'lr': 0.00048611793384428006, 'samples': 3412608, 'steps': 17773, 'loss/train': 1.2940549850463867} 08/30/2021 16:26:04 - INFO - __main__ - Step 17775: {'lr': 0.00048611619003380426, 'samples': 3412800, 'steps': 17774, 'loss/train': 1.457544207572937} 08/30/2021 16:26:04 - INFO - __main__ - Step 17776: {'lr': 0.0004861144461169382, 'samples': 3412992, 'steps': 17775, 'loss/train': 1.60025155544281} 08/30/2021 16:26:04 - INFO - __main__ - Step 17777: {'lr': 0.00048611270209368264, 'samples': 3413184, 'steps': 17776, 'loss/train': 1.5212907791137695} 08/30/2021 16:26:06 - INFO - __main__ - Step 17778: {'lr': 0.0004861109579640384, 'samples': 3413376, 'steps': 17777, 'loss/train': 1.9214051961898804} 08/30/2021 16:26:07 - INFO - __main__ - Step 17779: {'lr': 0.0004861092137280061, 'samples': 3413568, 'steps': 17778, 'loss/train': 1.3035353422164917} 08/30/2021 16:26:07 - INFO - __main__ - Step 17780: {'lr': 0.00048610746938558666, 'samples': 3413760, 'steps': 17779, 'loss/train': 1.7488807439804077} 08/30/2021 16:26:07 - INFO - __main__ - Step 17781: {'lr': 0.0004861057249367808, 'samples': 3413952, 'steps': 17780, 'loss/train': 0.3444135785102844} 08/30/2021 16:26:08 - INFO - __main__ - Step 17782: {'lr': 0.00048610398038158943, 'samples': 3414144, 'steps': 17781, 'loss/train': 0.3180020749568939} 08/30/2021 16:26:08 - INFO - __main__ - Step 17783: {'lr': 0.00048610223572001315, 'samples': 3414336, 'steps': 17782, 'loss/train': 1.867020606994629} 08/30/2021 16:26:09 - INFO - __main__ - Step 17784: {'lr': 0.0004861004909520529, 'samples': 3414528, 'steps': 17783, 'loss/train': 1.1937071084976196} 08/30/2021 16:26:10 - INFO - __main__ - Step 17785: {'lr': 0.00048609874607770945, 'samples': 3414720, 'steps': 17784, 'loss/train': 2.2578063011169434} 08/30/2021 16:26:10 - INFO - __main__ - Step 17786: {'lr': 0.0004860970010969835, 'samples': 3414912, 'steps': 17785, 'loss/train': 1.9325724840164185} 08/30/2021 16:26:11 - INFO - __main__ - Step 17787: {'lr': 0.0004860952560098759, 'samples': 3415104, 'steps': 17786, 'loss/train': 2.0252583026885986} 08/30/2021 16:26:11 - INFO - __main__ - Step 17788: {'lr': 0.0004860935108163874, 'samples': 3415296, 'steps': 17787, 'loss/train': 1.694702386856079} 08/30/2021 16:26:12 - INFO - __main__ - Step 17789: {'lr': 0.0004860917655165188, 'samples': 3415488, 'steps': 17788, 'loss/train': 1.336488962173462} 08/30/2021 16:26:13 - INFO - __main__ - Step 17790: {'lr': 0.00048609002011027093, 'samples': 3415680, 'steps': 17789, 'loss/train': 1.6751717329025269} 08/30/2021 16:26:13 - INFO - __main__ - Step 17791: {'lr': 0.0004860882745976445, 'samples': 3415872, 'steps': 17790, 'loss/train': 1.6190760135650635} 08/30/2021 16:26:14 - INFO - __main__ - Step 17792: {'lr': 0.00048608652897864034, 'samples': 3416064, 'steps': 17791, 'loss/train': 2.0488550662994385} 08/30/2021 16:26:14 - INFO - __main__ - Step 17793: {'lr': 0.0004860847832532593, 'samples': 3416256, 'steps': 17792, 'loss/train': 1.6386748552322388} 08/30/2021 16:26:15 - INFO - __main__ - Step 17794: {'lr': 0.00048608303742150204, 'samples': 3416448, 'steps': 17793, 'loss/train': 1.3178482055664062} 08/30/2021 16:26:16 - INFO - __main__ - Step 17795: {'lr': 0.0004860812914833694, 'samples': 3416640, 'steps': 17794, 'loss/train': 1.6896860599517822} 08/30/2021 16:26:16 - INFO - __main__ - Step 17796: {'lr': 0.00048607954543886225, 'samples': 3416832, 'steps': 17795, 'loss/train': 1.564070701599121} 08/30/2021 16:26:17 - INFO - __main__ - Step 17797: {'lr': 0.00048607779928798125, 'samples': 3417024, 'steps': 17796, 'loss/train': 1.4566324949264526} 08/30/2021 16:26:17 - INFO - __main__ - Step 17798: {'lr': 0.0004860760530307272, 'samples': 3417216, 'steps': 17797, 'loss/train': 2.0166878700256348} 08/30/2021 16:26:19 - INFO - __main__ - Step 17799: {'lr': 0.00048607430666710097, 'samples': 3417408, 'steps': 17798, 'loss/train': 2.282393217086792} 08/30/2021 16:26:19 - INFO - __main__ - Step 17800: {'lr': 0.00048607256019710327, 'samples': 3417600, 'steps': 17799, 'loss/train': 1.350229024887085} 08/30/2021 16:26:19 - INFO - __main__ - Step 17801: {'lr': 0.0004860708136207349, 'samples': 3417792, 'steps': 17800, 'loss/train': 1.3988617658615112} 08/30/2021 16:26:20 - INFO - __main__ - Step 17802: {'lr': 0.0004860690669379967, 'samples': 3417984, 'steps': 17801, 'loss/train': 1.5887693166732788} 08/30/2021 16:26:20 - INFO - __main__ - Step 17803: {'lr': 0.00048606732014888946, 'samples': 3418176, 'steps': 17802, 'loss/train': 0.10701005905866623} 08/30/2021 16:26:23 - INFO - __main__ - Step 17804: {'lr': 0.0004860655732534138, 'samples': 3418368, 'steps': 17803, 'loss/train': 1.9331892728805542} 08/30/2021 16:26:23 - INFO - __main__ - Step 17805: {'lr': 0.00048606382625157075, 'samples': 3418560, 'steps': 17804, 'loss/train': 1.2968308925628662} 08/30/2021 16:26:23 - INFO - __main__ - Step 17806: {'lr': 0.00048606207914336097, 'samples': 3418752, 'steps': 17805, 'loss/train': 0.0958833396434784} 08/30/2021 16:26:24 - INFO - __main__ - Step 17807: {'lr': 0.0004860603319287853, 'samples': 3418944, 'steps': 17806, 'loss/train': 1.3931435346603394} 08/30/2021 16:26:24 - INFO - __main__ - Step 17808: {'lr': 0.0004860585846078444, 'samples': 3419136, 'steps': 17807, 'loss/train': 2.507514238357544} 08/30/2021 16:26:24 - INFO - __main__ - Step 17809: {'lr': 0.00048605683718053915, 'samples': 3419328, 'steps': 17808, 'loss/train': 1.7126376628875732} 08/30/2021 16:26:25 - INFO - __main__ - Step 17810: {'lr': 0.0004860550896468704, 'samples': 3419520, 'steps': 17809, 'loss/train': 1.714233636856079} 08/30/2021 16:26:26 - INFO - __main__ - Step 17811: {'lr': 0.00048605334200683883, 'samples': 3419712, 'steps': 17810, 'loss/train': 1.740059733390808} 08/30/2021 16:26:27 - INFO - __main__ - Step 17812: {'lr': 0.0004860515942604452, 'samples': 3419904, 'steps': 17811, 'loss/train': 1.2822657823562622} 08/30/2021 16:26:27 - INFO - __main__ - Step 17813: {'lr': 0.00048604984640769047, 'samples': 3420096, 'steps': 17812, 'loss/train': 1.1805046796798706} 08/30/2021 16:26:27 - INFO - __main__ - Step 17814: {'lr': 0.00048604809844857524, 'samples': 3420288, 'steps': 17813, 'loss/train': 3.061659097671509} 08/30/2021 16:26:28 - INFO - __main__ - Step 17815: {'lr': 0.0004860463503831004, 'samples': 3420480, 'steps': 17814, 'loss/train': 1.9420151710510254} 08/30/2021 16:26:29 - INFO - __main__ - Step 17816: {'lr': 0.0004860446022112668, 'samples': 3420672, 'steps': 17815, 'loss/train': 1.388025164604187} 08/30/2021 16:26:30 - INFO - __main__ - Step 17817: {'lr': 0.00048604285393307503, 'samples': 3420864, 'steps': 17816, 'loss/train': 1.9964635372161865} 08/30/2021 16:26:30 - INFO - __main__ - Step 17818: {'lr': 0.000486041105548526, 'samples': 3421056, 'steps': 17817, 'loss/train': 0.955362856388092} 08/30/2021 16:26:30 - INFO - __main__ - Step 17819: {'lr': 0.00048603935705762057, 'samples': 3421248, 'steps': 17818, 'loss/train': 1.5427345037460327} 08/30/2021 16:26:31 - INFO - __main__ - Step 17820: {'lr': 0.0004860376084603594, 'samples': 3421440, 'steps': 17819, 'loss/train': 1.8449162244796753} 08/30/2021 16:26:32 - INFO - __main__ - Step 17821: {'lr': 0.00048603585975674334, 'samples': 3421632, 'steps': 17820, 'loss/train': 1.494202971458435} 08/30/2021 16:26:33 - INFO - __main__ - Step 17822: {'lr': 0.0004860341109467732, 'samples': 3421824, 'steps': 17821, 'loss/train': 1.6064958572387695} 08/30/2021 16:26:33 - INFO - __main__ - Step 17823: {'lr': 0.00048603236203044963, 'samples': 3422016, 'steps': 17822, 'loss/train': 1.8284484148025513} 08/30/2021 16:26:34 - INFO - __main__ - Step 17824: {'lr': 0.00048603061300777365, 'samples': 3422208, 'steps': 17823, 'loss/train': 1.8893921375274658} 08/30/2021 16:26:34 - INFO - __main__ - Step 17825: {'lr': 0.0004860288638787458, 'samples': 3422400, 'steps': 17824, 'loss/train': 1.239871621131897} 08/30/2021 16:26:34 - INFO - __main__ - Step 17826: {'lr': 0.000486027114643367, 'samples': 3422592, 'steps': 17825, 'loss/train': 1.517728328704834} 08/30/2021 16:26:36 - INFO - __main__ - Step 17827: {'lr': 0.0004860253653016381, 'samples': 3422784, 'steps': 17826, 'loss/train': 0.07044032216072083} 08/30/2021 16:26:36 - INFO - __main__ - Step 17828: {'lr': 0.00048602361585355975, 'samples': 3422976, 'steps': 17827, 'loss/train': 1.964586853981018} 08/30/2021 16:26:36 - INFO - __main__ - Step 17829: {'lr': 0.0004860218662991328, 'samples': 3423168, 'steps': 17828, 'loss/train': 1.9995909929275513} 08/30/2021 16:26:37 - INFO - __main__ - Step 17830: {'lr': 0.0004860201166383581, 'samples': 3423360, 'steps': 17829, 'loss/train': 1.5352898836135864} 08/30/2021 16:26:37 - INFO - __main__ - Step 17831: {'lr': 0.00048601836687123636, 'samples': 3423552, 'steps': 17830, 'loss/train': 1.1319940090179443} 08/30/2021 16:26:39 - INFO - __main__ - Step 17832: {'lr': 0.00048601661699776834, 'samples': 3423744, 'steps': 17831, 'loss/train': 1.645721197128296} 08/30/2021 16:26:39 - INFO - __main__ - Step 17833: {'lr': 0.0004860148670179549, 'samples': 3423936, 'steps': 17832, 'loss/train': 1.8793554306030273} 08/30/2021 16:26:40 - INFO - __main__ - Step 17834: {'lr': 0.0004860131169317968, 'samples': 3424128, 'steps': 17833, 'loss/train': 2.120166778564453} 08/30/2021 16:26:40 - INFO - __main__ - Step 17835: {'lr': 0.0004860113667392948, 'samples': 3424320, 'steps': 17834, 'loss/train': 0.14136287569999695} 08/30/2021 16:26:40 - INFO - __main__ - Step 17836: {'lr': 0.00048600961644044977, 'samples': 3424512, 'steps': 17835, 'loss/train': 1.4645096063613892} 08/30/2021 16:26:42 - INFO - __main__ - Step 17837: {'lr': 0.0004860078660352625, 'samples': 3424704, 'steps': 17836, 'loss/train': 0.9518241286277771} 08/30/2021 16:26:42 - INFO - __main__ - Step 17838: {'lr': 0.0004860061155237336, 'samples': 3424896, 'steps': 17837, 'loss/train': 1.8600260019302368} 08/30/2021 16:26:43 - INFO - __main__ - Step 17839: {'lr': 0.0004860043649058641, 'samples': 3425088, 'steps': 17838, 'loss/train': 1.0962424278259277} 08/30/2021 16:26:43 - INFO - __main__ - Step 17840: {'lr': 0.00048600261418165456, 'samples': 3425280, 'steps': 17839, 'loss/train': 1.6016703844070435} 08/30/2021 16:26:44 - INFO - __main__ - Step 17841: {'lr': 0.00048600086335110593, 'samples': 3425472, 'steps': 17840, 'loss/train': 1.4285876750946045} 08/30/2021 16:26:45 - INFO - __main__ - Step 17842: {'lr': 0.000485999112414219, 'samples': 3425664, 'steps': 17841, 'loss/train': 1.2479573488235474} 08/30/2021 16:26:46 - INFO - __main__ - Step 17843: {'lr': 0.0004859973613709945, 'samples': 3425856, 'steps': 17842, 'loss/train': 1.5413181781768799} 08/30/2021 16:26:46 - INFO - __main__ - Step 17844: {'lr': 0.0004859956102214332, 'samples': 3426048, 'steps': 17843, 'loss/train': 1.8095704317092896} 08/30/2021 16:26:46 - INFO - __main__ - Step 17845: {'lr': 0.00048599385896553595, 'samples': 3426240, 'steps': 17844, 'loss/train': 1.3200632333755493} 08/30/2021 16:26:47 - INFO - __main__ - Step 17846: {'lr': 0.0004859921076033034, 'samples': 3426432, 'steps': 17845, 'loss/train': 2.3370091915130615} 08/30/2021 16:26:48 - INFO - __main__ - Step 17847: {'lr': 0.00048599035613473656, 'samples': 3426624, 'steps': 17846, 'loss/train': 1.3648688793182373} 08/30/2021 16:26:49 - INFO - __main__ - Step 17848: {'lr': 0.0004859886045598361, 'samples': 3426816, 'steps': 17847, 'loss/train': 1.6096360683441162} 08/30/2021 16:26:49 - INFO - __main__ - Step 17849: {'lr': 0.0004859868528786028, 'samples': 3427008, 'steps': 17848, 'loss/train': 0.8248007297515869} 08/30/2021 16:26:50 - INFO - __main__ - Step 17850: {'lr': 0.0004859851010910374, 'samples': 3427200, 'steps': 17849, 'loss/train': 2.027937889099121} 08/30/2021 16:26:50 - INFO - __main__ - Step 17851: {'lr': 0.0004859833491971409, 'samples': 3427392, 'steps': 17850, 'loss/train': 2.022143602371216} 08/30/2021 16:26:50 - INFO - __main__ - Step 17852: {'lr': 0.0004859815971969138, 'samples': 3427584, 'steps': 17851, 'loss/train': 1.8337533473968506} 08/30/2021 16:26:52 - INFO - __main__ - Step 17853: {'lr': 0.0004859798450903571, 'samples': 3427776, 'steps': 17852, 'loss/train': 2.1065738201141357} 08/30/2021 16:26:52 - INFO - __main__ - Step 17854: {'lr': 0.00048597809287747153, 'samples': 3427968, 'steps': 17853, 'loss/train': 1.8997302055358887} 08/30/2021 16:26:53 - INFO - __main__ - Step 17855: {'lr': 0.0004859763405582579, 'samples': 3428160, 'steps': 17854, 'loss/train': 1.2824190855026245} 08/30/2021 16:26:53 - INFO - __main__ - Step 17856: {'lr': 0.00048597458813271686, 'samples': 3428352, 'steps': 17855, 'loss/train': 1.6876394748687744} 08/30/2021 16:26:53 - INFO - __main__ - Step 17857: {'lr': 0.0004859728356008494, 'samples': 3428544, 'steps': 17856, 'loss/train': 1.5995029211044312} 08/30/2021 16:26:55 - INFO - __main__ - Step 17858: {'lr': 0.00048597108296265625, 'samples': 3428736, 'steps': 17857, 'loss/train': 0.4544801414012909} 08/30/2021 16:26:56 - INFO - __main__ - Step 17859: {'lr': 0.00048596933021813815, 'samples': 3428928, 'steps': 17858, 'loss/train': 1.3313671350479126} 08/30/2021 16:26:56 - INFO - __main__ - Step 17860: {'lr': 0.0004859675773672959, 'samples': 3429120, 'steps': 17859, 'loss/train': 1.9243196249008179} 08/30/2021 16:26:57 - INFO - __main__ - Step 17861: {'lr': 0.00048596582441013026, 'samples': 3429312, 'steps': 17860, 'loss/train': 1.6134884357452393} 08/30/2021 16:26:57 - INFO - __main__ - Step 17862: {'lr': 0.0004859640713466421, 'samples': 3429504, 'steps': 17861, 'loss/train': 1.5414246320724487} 08/30/2021 16:26:59 - INFO - __main__ - Step 17863: {'lr': 0.0004859623181768321, 'samples': 3429696, 'steps': 17862, 'loss/train': 1.0997945070266724} 08/30/2021 16:26:59 - INFO - __main__ - Step 17864: {'lr': 0.0004859605649007012, 'samples': 3429888, 'steps': 17863, 'loss/train': 0.7047229409217834} 08/30/2021 16:26:59 - INFO - __main__ - Step 17865: {'lr': 0.00048595881151825015, 'samples': 3430080, 'steps': 17864, 'loss/train': 1.7464097738265991} 08/30/2021 16:27:00 - INFO - __main__ - Step 17866: {'lr': 0.00048595705802947963, 'samples': 3430272, 'steps': 17865, 'loss/train': 1.578861117362976} 08/30/2021 16:27:00 - INFO - __main__ - Step 17867: {'lr': 0.0004859553044343905, 'samples': 3430464, 'steps': 17866, 'loss/train': 1.4532793760299683} 08/30/2021 16:27:00 - INFO - __main__ - Step 17868: {'lr': 0.0004859535507329836, 'samples': 3430656, 'steps': 17867, 'loss/train': 2.017756938934326} 08/30/2021 16:27:02 - INFO - __main__ - Step 17869: {'lr': 0.0004859517969252596, 'samples': 3430848, 'steps': 17868, 'loss/train': 1.7452476024627686} 08/30/2021 16:27:02 - INFO - __main__ - Step 17870: {'lr': 0.0004859500430112194, 'samples': 3431040, 'steps': 17869, 'loss/train': 1.0578614473342896} 08/30/2021 16:27:03 - INFO - __main__ - Step 17871: {'lr': 0.0004859482889908637, 'samples': 3431232, 'steps': 17870, 'loss/train': 1.5763440132141113} 08/30/2021 16:27:03 - INFO - __main__ - Step 17872: {'lr': 0.0004859465348641934, 'samples': 3431424, 'steps': 17871, 'loss/train': 1.7885918617248535} 08/30/2021 16:27:03 - INFO - __main__ - Step 17873: {'lr': 0.0004859447806312093, 'samples': 3431616, 'steps': 17872, 'loss/train': 1.7694075107574463} 08/30/2021 16:27:05 - INFO - __main__ - Step 17874: {'lr': 0.000485943026291912, 'samples': 3431808, 'steps': 17873, 'loss/train': 1.6329407691955566} 08/30/2021 16:27:05 - INFO - __main__ - Step 17875: {'lr': 0.0004859412718463025, 'samples': 3432000, 'steps': 17874, 'loss/train': 0.8633098602294922} 08/30/2021 16:27:06 - INFO - __main__ - Step 17876: {'lr': 0.00048593951729438144, 'samples': 3432192, 'steps': 17875, 'loss/train': 1.3485416173934937} 08/30/2021 16:27:06 - INFO - __main__ - Step 17877: {'lr': 0.0004859377626361497, 'samples': 3432384, 'steps': 17876, 'loss/train': 1.8221259117126465} 08/30/2021 16:27:06 - INFO - __main__ - Step 17878: {'lr': 0.00048593600787160806, 'samples': 3432576, 'steps': 17877, 'loss/train': 0.9330003261566162} 08/30/2021 16:27:08 - INFO - __main__ - Step 17879: {'lr': 0.0004859342530007572, 'samples': 3432768, 'steps': 17878, 'loss/train': 1.376065969467163} 08/30/2021 16:27:08 - INFO - __main__ - Step 17880: {'lr': 0.0004859324980235982, 'samples': 3432960, 'steps': 17879, 'loss/train': 1.5842962265014648} 08/30/2021 16:27:09 - INFO - __main__ - Step 17881: {'lr': 0.0004859307429401315, 'samples': 3433152, 'steps': 17880, 'loss/train': 1.2794156074523926} 08/30/2021 16:27:09 - INFO - __main__ - Step 17882: {'lr': 0.0004859289877503581, 'samples': 3433344, 'steps': 17881, 'loss/train': 1.737648367881775} 08/30/2021 16:27:09 - INFO - __main__ - Step 17883: {'lr': 0.00048592723245427874, 'samples': 3433536, 'steps': 17882, 'loss/train': 0.8127500414848328} 08/30/2021 16:27:11 - INFO - __main__ - Step 17884: {'lr': 0.00048592547705189414, 'samples': 3433728, 'steps': 17883, 'loss/train': 1.9721065759658813} 08/30/2021 16:27:11 - INFO - __main__ - Step 17885: {'lr': 0.00048592372154320526, 'samples': 3433920, 'steps': 17884, 'loss/train': 1.3245036602020264} 08/30/2021 16:27:12 - INFO - __main__ - Step 17886: {'lr': 0.0004859219659282127, 'samples': 3434112, 'steps': 17885, 'loss/train': 2.183135986328125} 08/30/2021 16:27:12 - INFO - __main__ - Step 17887: {'lr': 0.00048592021020691745, 'samples': 3434304, 'steps': 17886, 'loss/train': 1.2190138101577759} 08/30/2021 16:27:12 - INFO - __main__ - Step 17888: {'lr': 0.00048591845437932014, 'samples': 3434496, 'steps': 17887, 'loss/train': 1.4049583673477173} 08/30/2021 16:27:14 - INFO - __main__ - Step 17889: {'lr': 0.0004859166984454216, 'samples': 3434688, 'steps': 17888, 'loss/train': 1.5307166576385498} 08/30/2021 16:27:14 - INFO - __main__ - Step 17890: {'lr': 0.0004859149424052226, 'samples': 3434880, 'steps': 17889, 'loss/train': 1.7316594123840332} 08/30/2021 16:27:15 - INFO - __main__ - Step 17891: {'lr': 0.00048591318625872403, 'samples': 3435072, 'steps': 17890, 'loss/train': 2.1398332118988037} 08/30/2021 16:27:15 - INFO - __main__ - Step 17892: {'lr': 0.00048591143000592665, 'samples': 3435264, 'steps': 17891, 'loss/train': 1.8469187021255493} 08/30/2021 16:27:15 - INFO - __main__ - Step 17893: {'lr': 0.00048590967364683116, 'samples': 3435456, 'steps': 17892, 'loss/train': 2.175302505493164} 08/30/2021 16:27:17 - INFO - __main__ - Step 17894: {'lr': 0.0004859079171814384, 'samples': 3435648, 'steps': 17893, 'loss/train': 1.7110624313354492} 08/30/2021 16:27:17 - INFO - __main__ - Step 17895: {'lr': 0.00048590616060974917, 'samples': 3435840, 'steps': 17894, 'loss/train': 0.8588742017745972} 08/30/2021 16:27:18 - INFO - __main__ - Step 17896: {'lr': 0.00048590440393176434, 'samples': 3436032, 'steps': 17895, 'loss/train': 1.4952541589736938} 08/30/2021 16:27:18 - INFO - __main__ - Step 17897: {'lr': 0.00048590264714748455, 'samples': 3436224, 'steps': 17896, 'loss/train': 1.6051567792892456} 08/30/2021 16:27:18 - INFO - __main__ - Step 17898: {'lr': 0.0004859008902569107, 'samples': 3436416, 'steps': 17897, 'loss/train': 1.8908735513687134} 08/30/2021 16:27:20 - INFO - __main__ - Step 17899: {'lr': 0.00048589913326004355, 'samples': 3436608, 'steps': 17898, 'loss/train': 1.6623704433441162} 08/30/2021 16:27:20 - INFO - __main__ - Step 17900: {'lr': 0.0004858973761568839, 'samples': 3436800, 'steps': 17899, 'loss/train': 1.1768349409103394} 08/30/2021 16:27:21 - INFO - __main__ - Step 17901: {'lr': 0.0004858956189474325, 'samples': 3436992, 'steps': 17900, 'loss/train': 1.343118667602539} 08/30/2021 16:27:21 - INFO - __main__ - Step 17902: {'lr': 0.0004858938616316902, 'samples': 3437184, 'steps': 17901, 'loss/train': 3.308218240737915} 08/30/2021 16:27:21 - INFO - __main__ - Step 17903: {'lr': 0.00048589210420965775, 'samples': 3437376, 'steps': 17902, 'loss/train': 1.6797643899917603} 08/30/2021 16:27:22 - INFO - __main__ - Step 17904: {'lr': 0.0004858903466813359, 'samples': 3437568, 'steps': 17903, 'loss/train': 1.4640237092971802} 08/30/2021 16:27:23 - INFO - __main__ - Step 17905: {'lr': 0.0004858885890467256, 'samples': 3437760, 'steps': 17904, 'loss/train': 0.6652421355247498} 08/30/2021 16:27:24 - INFO - __main__ - Step 17906: {'lr': 0.00048588683130582755, 'samples': 3437952, 'steps': 17905, 'loss/train': 1.5127453804016113} 08/30/2021 16:27:24 - INFO - __main__ - Step 17907: {'lr': 0.00048588507345864246, 'samples': 3438144, 'steps': 17906, 'loss/train': 1.1763780117034912} 08/30/2021 16:27:24 - INFO - __main__ - Step 17908: {'lr': 0.00048588331550517125, 'samples': 3438336, 'steps': 17907, 'loss/train': 1.3862305879592896} 08/30/2021 16:27:25 - INFO - __main__ - Step 17909: {'lr': 0.0004858815574454146, 'samples': 3438528, 'steps': 17908, 'loss/train': 1.5857625007629395} 08/30/2021 16:27:27 - INFO - __main__ - Step 17910: {'lr': 0.0004858797992793734, 'samples': 3438720, 'steps': 17909, 'loss/train': 1.6279613971710205} 08/30/2021 16:27:27 - INFO - __main__ - Step 17911: {'lr': 0.0004858780410070484, 'samples': 3438912, 'steps': 17910, 'loss/train': 2.0002217292785645} 08/30/2021 16:27:28 - INFO - __main__ - Step 17912: {'lr': 0.0004858762826284404, 'samples': 3439104, 'steps': 17911, 'loss/train': 1.3232227563858032} 08/30/2021 16:27:28 - INFO - __main__ - Step 17913: {'lr': 0.00048587452414355014, 'samples': 3439296, 'steps': 17912, 'loss/train': 1.5202692747116089} 08/30/2021 16:27:28 - INFO - __main__ - Step 17914: {'lr': 0.00048587276555237853, 'samples': 3439488, 'steps': 17913, 'loss/train': 1.5702459812164307} 08/30/2021 16:27:30 - INFO - __main__ - Step 17915: {'lr': 0.00048587100685492626, 'samples': 3439680, 'steps': 17914, 'loss/train': 1.5571792125701904} 08/30/2021 16:27:30 - INFO - __main__ - Step 17916: {'lr': 0.00048586924805119416, 'samples': 3439872, 'steps': 17915, 'loss/train': 1.0138022899627686} 08/30/2021 16:27:31 - INFO - __main__ - Step 17917: {'lr': 0.00048586748914118303, 'samples': 3440064, 'steps': 17916, 'loss/train': 1.2218353748321533} 08/30/2021 16:27:31 - INFO - __main__ - Step 17918: {'lr': 0.0004858657301248936, 'samples': 3440256, 'steps': 17917, 'loss/train': 1.5009742975234985} 08/30/2021 16:27:32 - INFO - __main__ - Step 17919: {'lr': 0.00048586397100232673, 'samples': 3440448, 'steps': 17918, 'loss/train': 1.6131455898284912} 08/30/2021 16:27:33 - INFO - __main__ - Step 17920: {'lr': 0.00048586221177348323, 'samples': 3440640, 'steps': 17919, 'loss/train': 1.9276503324508667} 08/30/2021 16:27:33 - INFO - __main__ - Step 17921: {'lr': 0.00048586045243836386, 'samples': 3440832, 'steps': 17920, 'loss/train': 1.802316427230835} 08/30/2021 16:27:34 - INFO - __main__ - Step 17922: {'lr': 0.0004858586929969693, 'samples': 3441024, 'steps': 17921, 'loss/train': 1.4100080728530884} 08/30/2021 16:27:34 - INFO - __main__ - Step 17923: {'lr': 0.0004858569334493006, 'samples': 3441216, 'steps': 17922, 'loss/train': 1.6916251182556152} 08/30/2021 16:27:34 - INFO - __main__ - Step 17924: {'lr': 0.0004858551737953583, 'samples': 3441408, 'steps': 17923, 'loss/train': 1.9449329376220703} 08/30/2021 16:27:36 - INFO - __main__ - Step 17925: {'lr': 0.00048585341403514337, 'samples': 3441600, 'steps': 17924, 'loss/train': 2.312624931335449} 08/30/2021 16:27:36 - INFO - __main__ - Step 17926: {'lr': 0.0004858516541686565, 'samples': 3441792, 'steps': 17925, 'loss/train': 1.7189046144485474} 08/30/2021 16:27:37 - INFO - __main__ - Step 17927: {'lr': 0.0004858498941958985, 'samples': 3441984, 'steps': 17926, 'loss/train': 1.7091323137283325} 08/30/2021 16:27:37 - INFO - __main__ - Step 17928: {'lr': 0.00048584813411687016, 'samples': 3442176, 'steps': 17927, 'loss/train': 1.7522549629211426} 08/30/2021 16:27:37 - INFO - __main__ - Step 17929: {'lr': 0.00048584637393157235, 'samples': 3442368, 'steps': 17928, 'loss/train': 2.142777442932129} 08/30/2021 16:27:39 - INFO - __main__ - Step 17930: {'lr': 0.00048584461364000576, 'samples': 3442560, 'steps': 17929, 'loss/train': 1.5607608556747437} 08/30/2021 16:27:40 - INFO - __main__ - Step 17931: {'lr': 0.00048584285324217125, 'samples': 3442752, 'steps': 17930, 'loss/train': 0.613991379737854} 08/30/2021 16:27:40 - INFO - __main__ - Step 17932: {'lr': 0.00048584109273806954, 'samples': 3442944, 'steps': 17931, 'loss/train': 1.3197829723358154} 08/30/2021 16:27:40 - INFO - __main__ - Step 17933: {'lr': 0.00048583933212770154, 'samples': 3443136, 'steps': 17932, 'loss/train': 1.585553765296936} 08/30/2021 16:27:41 - INFO - __main__ - Step 17934: {'lr': 0.00048583757141106796, 'samples': 3443328, 'steps': 17933, 'loss/train': 1.2175897359848022} 08/30/2021 16:27:42 - INFO - __main__ - Step 17935: {'lr': 0.00048583581058816956, 'samples': 3443520, 'steps': 17934, 'loss/train': 1.8148592710494995} 08/30/2021 16:27:42 - INFO - __main__ - Step 17936: {'lr': 0.00048583404965900725, 'samples': 3443712, 'steps': 17935, 'loss/train': 1.5685232877731323} 08/30/2021 16:27:43 - INFO - __main__ - Step 17937: {'lr': 0.0004858322886235817, 'samples': 3443904, 'steps': 17936, 'loss/train': 1.5733325481414795} 08/30/2021 16:27:43 - INFO - __main__ - Step 17938: {'lr': 0.0004858305274818938, 'samples': 3444096, 'steps': 17937, 'loss/train': 1.5058397054672241} 08/30/2021 16:27:44 - INFO - __main__ - Step 17939: {'lr': 0.0004858287662339443, 'samples': 3444288, 'steps': 17938, 'loss/train': 1.559350609779358} 08/30/2021 16:27:45 - INFO - __main__ - Step 17940: {'lr': 0.00048582700487973397, 'samples': 3444480, 'steps': 17939, 'loss/train': 1.7616230249404907} 08/30/2021 16:27:45 - INFO - __main__ - Step 17941: {'lr': 0.00048582524341926365, 'samples': 3444672, 'steps': 17940, 'loss/train': 1.6359294652938843} 08/30/2021 16:27:46 - INFO - __main__ - Step 17942: {'lr': 0.0004858234818525341, 'samples': 3444864, 'steps': 17941, 'loss/train': 1.1140216588974} 08/30/2021 16:27:46 - INFO - __main__ - Step 17943: {'lr': 0.0004858217201795462, 'samples': 3445056, 'steps': 17942, 'loss/train': 1.5846662521362305} 08/30/2021 16:27:46 - INFO - __main__ - Step 17944: {'lr': 0.0004858199584003006, 'samples': 3445248, 'steps': 17943, 'loss/train': 1.5004762411117554} 08/30/2021 16:27:47 - INFO - __main__ - Step 17945: {'lr': 0.00048581819651479814, 'samples': 3445440, 'steps': 17944, 'loss/train': 1.7346022129058838} 08/30/2021 16:27:48 - INFO - __main__ - Step 17946: {'lr': 0.0004858164345230397, 'samples': 3445632, 'steps': 17945, 'loss/train': 1.4551098346710205} 08/30/2021 16:27:49 - INFO - __main__ - Step 17947: {'lr': 0.000485814672425026, 'samples': 3445824, 'steps': 17946, 'loss/train': 1.748676061630249} 08/30/2021 16:27:49 - INFO - __main__ - Step 17948: {'lr': 0.0004858129102207578, 'samples': 3446016, 'steps': 17947, 'loss/train': 1.8068292140960693} 08/30/2021 16:27:50 - INFO - __main__ - Step 17949: {'lr': 0.0004858111479102359, 'samples': 3446208, 'steps': 17948, 'loss/train': 1.6488761901855469} 08/30/2021 16:27:50 - INFO - __main__ - Step 17950: {'lr': 0.00048580938549346134, 'samples': 3446400, 'steps': 17949, 'loss/train': 1.5202116966247559} 08/30/2021 16:27:51 - INFO - __main__ - Step 17951: {'lr': 0.00048580762297043456, 'samples': 3446592, 'steps': 17950, 'loss/train': 1.6269984245300293} 08/30/2021 16:27:52 - INFO - __main__ - Step 17952: {'lr': 0.00048580586034115646, 'samples': 3446784, 'steps': 17951, 'loss/train': 0.8832659125328064} 08/30/2021 16:27:52 - INFO - __main__ - Step 17953: {'lr': 0.000485804097605628, 'samples': 3446976, 'steps': 17952, 'loss/train': 0.5102223753929138} 08/30/2021 16:27:53 - INFO - __main__ - Step 17954: {'lr': 0.00048580233476384975, 'samples': 3447168, 'steps': 17953, 'loss/train': 1.293516993522644} 08/30/2021 16:27:53 - INFO - __main__ - Step 17955: {'lr': 0.0004858005718158227, 'samples': 3447360, 'steps': 17954, 'loss/train': 0.8091772794723511} 08/30/2021 16:27:55 - INFO - __main__ - Step 17956: {'lr': 0.0004857988087615475, 'samples': 3447552, 'steps': 17955, 'loss/train': 1.6286166906356812} 08/30/2021 16:27:55 - INFO - __main__ - Step 17957: {'lr': 0.000485797045601025, 'samples': 3447744, 'steps': 17956, 'loss/train': 1.5255802869796753} 08/30/2021 16:27:55 - INFO - __main__ - Step 17958: {'lr': 0.000485795282334256, 'samples': 3447936, 'steps': 17957, 'loss/train': 0.8993553519248962} 08/30/2021 16:27:56 - INFO - __main__ - Step 17959: {'lr': 0.00048579351896124127, 'samples': 3448128, 'steps': 17958, 'loss/train': 1.3962647914886475} 08/30/2021 16:27:56 - INFO - __main__ - Step 17960: {'lr': 0.0004857917554819816, 'samples': 3448320, 'steps': 17959, 'loss/train': 1.6764079332351685} 08/30/2021 16:27:58 - INFO - __main__ - Step 17961: {'lr': 0.00048578999189647786, 'samples': 3448512, 'steps': 17960, 'loss/train': 1.4923226833343506} 08/30/2021 16:27:59 - INFO - __main__ - Step 17962: {'lr': 0.00048578822820473074, 'samples': 3448704, 'steps': 17961, 'loss/train': 1.8143463134765625} 08/30/2021 16:27:59 - INFO - __main__ - Step 17963: {'lr': 0.00048578646440674113, 'samples': 3448896, 'steps': 17962, 'loss/train': 2.056778907775879} 08/30/2021 16:27:59 - INFO - __main__ - Step 17964: {'lr': 0.0004857847005025097, 'samples': 3449088, 'steps': 17963, 'loss/train': 1.4036874771118164} 08/30/2021 16:28:00 - INFO - __main__ - Step 17965: {'lr': 0.0004857829364920374, 'samples': 3449280, 'steps': 17964, 'loss/train': 1.3317981958389282} 08/30/2021 16:28:01 - INFO - __main__ - Step 17966: {'lr': 0.0004857811723753249, 'samples': 3449472, 'steps': 17965, 'loss/train': 1.7080540657043457} 08/30/2021 16:28:02 - INFO - __main__ - Step 17967: {'lr': 0.00048577940815237305, 'samples': 3449664, 'steps': 17966, 'loss/train': 1.4190630912780762} 08/30/2021 16:28:02 - INFO - __main__ - Step 17968: {'lr': 0.00048577764382318265, 'samples': 3449856, 'steps': 17967, 'loss/train': 1.4978206157684326} 08/30/2021 16:28:02 - INFO - __main__ - Step 17969: {'lr': 0.0004857758793877545, 'samples': 3450048, 'steps': 17968, 'loss/train': 1.8247748613357544} 08/30/2021 16:28:03 - INFO - __main__ - Step 17970: {'lr': 0.00048577411484608936, 'samples': 3450240, 'steps': 17969, 'loss/train': 1.8087624311447144} 08/30/2021 16:28:04 - INFO - __main__ - Step 17971: {'lr': 0.000485772350198188, 'samples': 3450432, 'steps': 17970, 'loss/train': 1.5536245107650757} 08/30/2021 16:28:05 - INFO - __main__ - Step 17972: {'lr': 0.00048577058544405126, 'samples': 3450624, 'steps': 17971, 'loss/train': 1.661061406135559} 08/30/2021 16:28:05 - INFO - __main__ - Step 17973: {'lr': 0.00048576882058368, 'samples': 3450816, 'steps': 17972, 'loss/train': 1.5742443799972534} 08/30/2021 16:28:05 - INFO - __main__ - Step 17974: {'lr': 0.0004857670556170749, 'samples': 3451008, 'steps': 17973, 'loss/train': 1.044863224029541} 08/30/2021 16:28:06 - INFO - __main__ - Step 17975: {'lr': 0.0004857652905442368, 'samples': 3451200, 'steps': 17974, 'loss/train': 2.287400484085083} 08/30/2021 16:28:07 - INFO - __main__ - Step 17976: {'lr': 0.0004857635253651665, 'samples': 3451392, 'steps': 17975, 'loss/train': 1.5925867557525635} 08/30/2021 16:28:08 - INFO - __main__ - Step 17977: {'lr': 0.00048576176007986485, 'samples': 3451584, 'steps': 17976, 'loss/train': 1.464400053024292} 08/30/2021 16:28:08 - INFO - __main__ - Step 17978: {'lr': 0.00048575999468833256, 'samples': 3451776, 'steps': 17977, 'loss/train': 1.465862512588501} 08/30/2021 16:28:08 - INFO - __main__ - Step 17979: {'lr': 0.0004857582291905704, 'samples': 3451968, 'steps': 17978, 'loss/train': 1.49838387966156} 08/30/2021 16:28:09 - INFO - __main__ - Step 17980: {'lr': 0.00048575646358657934, 'samples': 3452160, 'steps': 17979, 'loss/train': 1.0039933919906616} 08/30/2021 16:28:10 - INFO - __main__ - Step 17981: {'lr': 0.00048575469787635997, 'samples': 3452352, 'steps': 17980, 'loss/train': 1.6469841003417969} 08/30/2021 16:28:11 - INFO - __main__ - Step 17982: {'lr': 0.00048575293205991313, 'samples': 3452544, 'steps': 17981, 'loss/train': 1.6953777074813843} 08/30/2021 16:28:11 - INFO - __main__ - Step 17983: {'lr': 0.0004857511661372397, 'samples': 3452736, 'steps': 17982, 'loss/train': 1.6324660778045654} 08/30/2021 16:28:11 - INFO - __main__ - Step 17984: {'lr': 0.00048574940010834045, 'samples': 3452928, 'steps': 17983, 'loss/train': 1.3473966121673584} 08/30/2021 16:28:12 - INFO - __main__ - Step 17985: {'lr': 0.0004857476339732161, 'samples': 3453120, 'steps': 17984, 'loss/train': 1.9128919839859009} 08/30/2021 16:28:12 - INFO - __main__ - Step 17986: {'lr': 0.0004857458677318676, 'samples': 3453312, 'steps': 17985, 'loss/train': 1.7540589570999146} 08/30/2021 16:28:14 - INFO - __main__ - Step 17987: {'lr': 0.0004857441013842956, 'samples': 3453504, 'steps': 17986, 'loss/train': 1.6961069107055664} 08/30/2021 16:28:14 - INFO - __main__ - Step 17988: {'lr': 0.0004857423349305009, 'samples': 3453696, 'steps': 17987, 'loss/train': 1.6407495737075806} 08/30/2021 16:28:15 - INFO - __main__ - Step 17989: {'lr': 0.00048574056837048443, 'samples': 3453888, 'steps': 17988, 'loss/train': 1.7343302965164185} 08/30/2021 16:28:15 - INFO - __main__ - Step 17990: {'lr': 0.0004857388017042468, 'samples': 3454080, 'steps': 17989, 'loss/train': 0.266526997089386} 08/30/2021 16:28:15 - INFO - __main__ - Step 17991: {'lr': 0.000485737034931789, 'samples': 3454272, 'steps': 17990, 'loss/train': 1.5119613409042358} 08/30/2021 16:28:17 - INFO - __main__ - Step 17992: {'lr': 0.00048573526805311166, 'samples': 3454464, 'steps': 17991, 'loss/train': 1.3970911502838135} 08/30/2021 16:28:17 - INFO - __main__ - Step 17993: {'lr': 0.0004857335010682157, 'samples': 3454656, 'steps': 17992, 'loss/train': 2.1763477325439453} 08/30/2021 16:28:18 - INFO - __main__ - Step 17994: {'lr': 0.0004857317339771018, 'samples': 3454848, 'steps': 17993, 'loss/train': 5.6309027671813965} 08/30/2021 16:28:18 - INFO - __main__ - Step 17995: {'lr': 0.0004857299667797709, 'samples': 3455040, 'steps': 17994, 'loss/train': 1.6603909730911255} 08/30/2021 16:28:18 - INFO - __main__ - Step 17996: {'lr': 0.0004857281994762236, 'samples': 3455232, 'steps': 17995, 'loss/train': 1.3990861177444458} 08/30/2021 16:28:20 - INFO - __main__ - Step 17997: {'lr': 0.00048572643206646097, 'samples': 3455424, 'steps': 17996, 'loss/train': 1.095388412475586} 08/30/2021 16:28:21 - INFO - __main__ - Step 17998: {'lr': 0.0004857246645504835, 'samples': 3455616, 'steps': 17997, 'loss/train': 1.5710792541503906} 08/30/2021 16:28:21 - INFO - __main__ - Step 17999: {'lr': 0.00048572289692829217, 'samples': 3455808, 'steps': 17998, 'loss/train': 1.4027560949325562} 08/30/2021 16:28:21 - INFO - __main__ - Step 18000: {'lr': 0.00048572112919988776, 'samples': 3456000, 'steps': 17999, 'loss/train': 1.682323694229126} 08/30/2021 16:28:22 - INFO - __main__ - Step 18001: {'lr': 0.00048571936136527106, 'samples': 3456192, 'steps': 18000, 'loss/train': 1.7628370523452759} 08/30/2021 16:28:22 - INFO - __main__ - Step 18002: {'lr': 0.0004857175934244428, 'samples': 3456384, 'steps': 18001, 'loss/train': 1.5482879877090454} 08/30/2021 16:28:23 - INFO - __main__ - Step 18003: {'lr': 0.0004857158253774039, 'samples': 3456576, 'steps': 18002, 'loss/train': 0.09714821726083755} 08/30/2021 16:28:24 - INFO - __main__ - Step 18004: {'lr': 0.0004857140572241551, 'samples': 3456768, 'steps': 18003, 'loss/train': 0.06454353779554367} 08/30/2021 16:28:25 - INFO - __main__ - Step 18005: {'lr': 0.00048571228896469713, 'samples': 3456960, 'steps': 18004, 'loss/train': 1.6359314918518066} 08/30/2021 16:28:25 - INFO - __main__ - Step 18006: {'lr': 0.0004857105205990308, 'samples': 3457152, 'steps': 18005, 'loss/train': 1.7537561655044556} 08/30/2021 16:28:26 - INFO - __main__ - Step 18007: {'lr': 0.00048570875212715706, 'samples': 3457344, 'steps': 18006, 'loss/train': 1.392996907234192} 08/30/2021 16:28:26 - INFO - __main__ - Step 18008: {'lr': 0.0004857069835490765, 'samples': 3457536, 'steps': 18007, 'loss/train': 1.7586145401000977} 08/30/2021 16:28:26 - INFO - __main__ - Step 18009: {'lr': 0.00048570521486479004, 'samples': 3457728, 'steps': 18008, 'loss/train': 2.623910903930664} 08/30/2021 16:28:28 - INFO - __main__ - Step 18010: {'lr': 0.0004857034460742984, 'samples': 3457920, 'steps': 18009, 'loss/train': 1.8344008922576904} 08/30/2021 16:28:29 - INFO - __main__ - Step 18011: {'lr': 0.0004857016771776025, 'samples': 3458112, 'steps': 18010, 'loss/train': 2.376192092895508} 08/30/2021 16:28:29 - INFO - __main__ - Step 18012: {'lr': 0.000485699908174703, 'samples': 3458304, 'steps': 18011, 'loss/train': 2.1674773693084717} 08/30/2021 16:28:29 - INFO - __main__ - Step 18013: {'lr': 0.0004856981390656008, 'samples': 3458496, 'steps': 18012, 'loss/train': 1.5568349361419678} 08/30/2021 16:28:30 - INFO - __main__ - Step 18014: {'lr': 0.00048569636985029664, 'samples': 3458688, 'steps': 18013, 'loss/train': 2.163891077041626} 08/30/2021 16:28:31 - INFO - __main__ - Step 18015: {'lr': 0.00048569460052879136, 'samples': 3458880, 'steps': 18014, 'loss/train': 1.916684627532959} 08/30/2021 16:28:32 - INFO - __main__ - Step 18016: {'lr': 0.0004856928311010857, 'samples': 3459072, 'steps': 18015, 'loss/train': 1.7760971784591675} 08/30/2021 16:28:32 - INFO - __main__ - Step 18017: {'lr': 0.00048569106156718045, 'samples': 3459264, 'steps': 18016, 'loss/train': 1.3841313123703003} 08/30/2021 16:28:32 - INFO - __main__ - Step 18018: {'lr': 0.00048568929192707657, 'samples': 3459456, 'steps': 18017, 'loss/train': 1.5409024953842163} 08/30/2021 16:28:33 - INFO - __main__ - Step 18019: {'lr': 0.0004856875221807746, 'samples': 3459648, 'steps': 18018, 'loss/train': 1.7263318300247192} 08/30/2021 16:28:35 - INFO - __main__ - Step 18020: {'lr': 0.0004856857523282755, 'samples': 3459840, 'steps': 18019, 'loss/train': 0.9564329385757446} 08/30/2021 16:28:35 - INFO - __main__ - Step 18021: {'lr': 0.0004856839823695801, 'samples': 3460032, 'steps': 18020, 'loss/train': 1.9314879179000854} 08/30/2021 16:28:36 - INFO - __main__ - Step 18022: {'lr': 0.00048568221230468905, 'samples': 3460224, 'steps': 18021, 'loss/train': 1.7067102193832397} 08/30/2021 16:28:36 - INFO - __main__ - Step 18023: {'lr': 0.0004856804421336033, 'samples': 3460416, 'steps': 18022, 'loss/train': 2.0386927127838135} 08/30/2021 16:28:36 - INFO - __main__ - Step 18024: {'lr': 0.0004856786718563235, 'samples': 3460608, 'steps': 18023, 'loss/train': 1.5910874605178833} 08/30/2021 16:28:38 - INFO - __main__ - Step 18025: {'lr': 0.0004856769014728506, 'samples': 3460800, 'steps': 18024, 'loss/train': 1.4760442972183228} 08/30/2021 16:28:38 - INFO - __main__ - Step 18026: {'lr': 0.0004856751309831853, 'samples': 3460992, 'steps': 18025, 'loss/train': 1.577941656112671} 08/30/2021 16:28:38 - INFO - __main__ - Step 18027: {'lr': 0.00048567336038732843, 'samples': 3461184, 'steps': 18026, 'loss/train': 1.6862093210220337} 08/30/2021 16:28:39 - INFO - __main__ - Step 18028: {'lr': 0.0004856715896852808, 'samples': 3461376, 'steps': 18027, 'loss/train': 1.8757396936416626} 08/30/2021 16:28:39 - INFO - __main__ - Step 18029: {'lr': 0.0004856698188770432, 'samples': 3461568, 'steps': 18028, 'loss/train': 1.694564700126648} 08/30/2021 16:28:41 - INFO - __main__ - Step 18030: {'lr': 0.0004856680479626163, 'samples': 3461760, 'steps': 18029, 'loss/train': 1.5136922597885132} 08/30/2021 16:28:41 - INFO - __main__ - Step 18031: {'lr': 0.0004856662769420012, 'samples': 3461952, 'steps': 18030, 'loss/train': 1.7104381322860718} 08/30/2021 16:28:41 - INFO - __main__ - Step 18032: {'lr': 0.0004856645058151984, 'samples': 3462144, 'steps': 18031, 'loss/train': 0.833308219909668} 08/30/2021 16:28:42 - INFO - __main__ - Step 18033: {'lr': 0.0004856627345822088, 'samples': 3462336, 'steps': 18032, 'loss/train': 0.7060480117797852} 08/30/2021 16:28:42 - INFO - __main__ - Step 18034: {'lr': 0.0004856609632430332, 'samples': 3462528, 'steps': 18033, 'loss/train': 1.5961253643035889} 08/30/2021 16:28:42 - INFO - __main__ - Step 18035: {'lr': 0.00048565919179767246, 'samples': 3462720, 'steps': 18034, 'loss/train': 1.7715524435043335} 08/30/2021 16:28:44 - INFO - __main__ - Step 18036: {'lr': 0.0004856574202461273, 'samples': 3462912, 'steps': 18035, 'loss/train': 0.9656311273574829} 08/30/2021 16:28:45 - INFO - __main__ - Step 18037: {'lr': 0.0004856556485883985, 'samples': 3463104, 'steps': 18036, 'loss/train': 1.2984038591384888} 08/30/2021 16:28:45 - INFO - __main__ - Step 18038: {'lr': 0.000485653876824487, 'samples': 3463296, 'steps': 18037, 'loss/train': 2.0501441955566406} 08/30/2021 16:28:45 - INFO - __main__ - Step 18039: {'lr': 0.00048565210495439337, 'samples': 3463488, 'steps': 18038, 'loss/train': 1.552443265914917} 08/30/2021 16:28:46 - INFO - __main__ - Step 18040: {'lr': 0.00048565033297811867, 'samples': 3463680, 'steps': 18039, 'loss/train': 1.5536558628082275} 08/30/2021 16:28:47 - INFO - __main__ - Step 18041: {'lr': 0.0004856485608956635, 'samples': 3463872, 'steps': 18040, 'loss/train': 1.036659836769104} 08/30/2021 16:28:48 - INFO - __main__ - Step 18042: {'lr': 0.00048564678870702873, 'samples': 3464064, 'steps': 18041, 'loss/train': 1.7979850769042969} 08/30/2021 16:28:48 - INFO - __main__ - Step 18043: {'lr': 0.00048564501641221516, 'samples': 3464256, 'steps': 18042, 'loss/train': 1.3544678688049316} 08/30/2021 16:28:48 - INFO - __main__ - Step 18044: {'lr': 0.00048564324401122357, 'samples': 3464448, 'steps': 18043, 'loss/train': 1.6906307935714722} 08/30/2021 16:28:49 - INFO - __main__ - Step 18045: {'lr': 0.0004856414715040548, 'samples': 3464640, 'steps': 18044, 'loss/train': 1.0748234987258911} 08/30/2021 16:28:50 - INFO - __main__ - Step 18046: {'lr': 0.0004856396988907096, 'samples': 3464832, 'steps': 18045, 'loss/train': 1.5081632137298584} 08/30/2021 16:28:51 - INFO - __main__ - Step 18047: {'lr': 0.00048563792617118876, 'samples': 3465024, 'steps': 18046, 'loss/train': 1.872005820274353} 08/30/2021 16:28:51 - INFO - __main__ - Step 18048: {'lr': 0.00048563615334549316, 'samples': 3465216, 'steps': 18047, 'loss/train': 2.1396422386169434} 08/30/2021 16:28:51 - INFO - __main__ - Step 18049: {'lr': 0.0004856343804136235, 'samples': 3465408, 'steps': 18048, 'loss/train': 1.707249641418457} 08/30/2021 16:28:52 - INFO - __main__ - Step 18050: {'lr': 0.0004856326073755806, 'samples': 3465600, 'steps': 18049, 'loss/train': 1.3193695545196533} 08/30/2021 16:28:53 - INFO - __main__ - Step 18051: {'lr': 0.0004856308342313653, 'samples': 3465792, 'steps': 18050, 'loss/train': 0.984358549118042} 08/30/2021 16:28:54 - INFO - __main__ - Step 18052: {'lr': 0.00048562906098097847, 'samples': 3465984, 'steps': 18051, 'loss/train': 1.6047166585922241} 08/30/2021 16:28:54 - INFO - __main__ - Step 18053: {'lr': 0.0004856272876244208, 'samples': 3466176, 'steps': 18052, 'loss/train': 1.973154902458191} 08/30/2021 16:28:54 - INFO - __main__ - Step 18054: {'lr': 0.000485625514161693, 'samples': 3466368, 'steps': 18053, 'loss/train': 1.4109480381011963} 08/30/2021 16:28:55 - INFO - __main__ - Step 18055: {'lr': 0.00048562374059279604, 'samples': 3466560, 'steps': 18054, 'loss/train': 1.571926474571228} 08/30/2021 16:28:56 - INFO - __main__ - Step 18056: {'lr': 0.00048562196691773066, 'samples': 3466752, 'steps': 18055, 'loss/train': 1.6709606647491455} 08/30/2021 16:28:57 - INFO - __main__ - Step 18057: {'lr': 0.00048562019313649766, 'samples': 3466944, 'steps': 18056, 'loss/train': 0.5680364370346069} 08/30/2021 16:28:57 - INFO - __main__ - Step 18058: {'lr': 0.0004856184192490979, 'samples': 3467136, 'steps': 18057, 'loss/train': 1.7736974954605103} 08/30/2021 16:28:57 - INFO - __main__ - Step 18059: {'lr': 0.000485616645255532, 'samples': 3467328, 'steps': 18058, 'loss/train': 1.9981396198272705} 08/30/2021 16:28:58 - INFO - __main__ - Step 18060: {'lr': 0.0004856148711558009, 'samples': 3467520, 'steps': 18059, 'loss/train': 1.743849754333496} 08/30/2021 16:28:58 - INFO - __main__ - Step 18061: {'lr': 0.00048561309694990543, 'samples': 3467712, 'steps': 18060, 'loss/train': 1.9952452182769775} 08/30/2021 16:29:00 - INFO - __main__ - Step 18062: {'lr': 0.00048561132263784634, 'samples': 3467904, 'steps': 18061, 'loss/train': 1.6193169355392456} 08/30/2021 16:29:00 - INFO - __main__ - Step 18063: {'lr': 0.00048560954821962434, 'samples': 3468096, 'steps': 18062, 'loss/train': 1.4820996522903442} 08/30/2021 16:29:01 - INFO - __main__ - Step 18064: {'lr': 0.0004856077736952404, 'samples': 3468288, 'steps': 18063, 'loss/train': 0.35932403802871704} 08/30/2021 16:29:01 - INFO - __main__ - Step 18065: {'lr': 0.00048560599906469513, 'samples': 3468480, 'steps': 18064, 'loss/train': 0.5257107615470886} 08/30/2021 16:29:01 - INFO - __main__ - Step 18066: {'lr': 0.00048560422432798956, 'samples': 3468672, 'steps': 18065, 'loss/train': 2.516770124435425} 08/30/2021 16:29:02 - INFO - __main__ - Step 18067: {'lr': 0.0004856024494851243, 'samples': 3468864, 'steps': 18066, 'loss/train': 1.6919971704483032} 08/30/2021 16:29:03 - INFO - __main__ - Step 18068: {'lr': 0.00048560067453610025, 'samples': 3469056, 'steps': 18067, 'loss/train': 1.546239972114563} 08/30/2021 16:29:04 - INFO - __main__ - Step 18069: {'lr': 0.00048559889948091814, 'samples': 3469248, 'steps': 18068, 'loss/train': 1.52725088596344} 08/30/2021 16:29:04 - INFO - __main__ - Step 18070: {'lr': 0.0004855971243195788, 'samples': 3469440, 'steps': 18069, 'loss/train': 1.8115290403366089} 08/30/2021 16:29:04 - INFO - __main__ - Step 18071: {'lr': 0.00048559534905208304, 'samples': 3469632, 'steps': 18070, 'loss/train': 1.6920514106750488} 08/30/2021 16:29:05 - INFO - __main__ - Step 18072: {'lr': 0.0004855935736784316, 'samples': 3469824, 'steps': 18071, 'loss/train': 1.7712047100067139} 08/30/2021 16:29:07 - INFO - __main__ - Step 18073: {'lr': 0.00048559179819862537, 'samples': 3470016, 'steps': 18072, 'loss/train': 1.6060940027236938} 08/30/2021 16:29:07 - INFO - __main__ - Step 18074: {'lr': 0.0004855900226126651, 'samples': 3470208, 'steps': 18073, 'loss/train': 1.5529301166534424} 08/30/2021 16:29:08 - INFO - __main__ - Step 18075: {'lr': 0.00048558824692055156, 'samples': 3470400, 'steps': 18074, 'loss/train': 1.69679594039917} 08/30/2021 16:29:08 - INFO - __main__ - Step 18076: {'lr': 0.0004855864711222857, 'samples': 3470592, 'steps': 18075, 'loss/train': 1.4229506254196167} 08/30/2021 16:29:09 - INFO - __main__ - Step 18077: {'lr': 0.0004855846952178682, 'samples': 3470784, 'steps': 18076, 'loss/train': 1.3505346775054932} 08/30/2021 16:29:09 - INFO - __main__ - Step 18078: {'lr': 0.0004855829192072998, 'samples': 3470976, 'steps': 18077, 'loss/train': 1.947479009628296} 08/30/2021 16:29:10 - INFO - __main__ - Step 18079: {'lr': 0.00048558114309058144, 'samples': 3471168, 'steps': 18078, 'loss/train': 2.2514586448669434} 08/30/2021 16:29:11 - INFO - __main__ - Step 18080: {'lr': 0.00048557936686771376, 'samples': 3471360, 'steps': 18079, 'loss/train': 1.5654730796813965} 08/30/2021 16:29:11 - INFO - __main__ - Step 18081: {'lr': 0.0004855775905386977, 'samples': 3471552, 'steps': 18080, 'loss/train': 1.4146381616592407} 08/30/2021 16:29:11 - INFO - __main__ - Step 18082: {'lr': 0.000485575814103534, 'samples': 3471744, 'steps': 18081, 'loss/train': 1.4612665176391602} 08/30/2021 16:29:12 - INFO - __main__ - Step 18083: {'lr': 0.0004855740375622235, 'samples': 3471936, 'steps': 18082, 'loss/train': 1.6697293519973755} 08/30/2021 16:29:13 - INFO - __main__ - Step 18084: {'lr': 0.00048557226091476704, 'samples': 3472128, 'steps': 18083, 'loss/train': 1.5470685958862305} 08/30/2021 16:29:14 - INFO - __main__ - Step 18085: {'lr': 0.0004855704841611652, 'samples': 3472320, 'steps': 18084, 'loss/train': 1.0351128578186035} 08/30/2021 16:29:14 - INFO - __main__ - Step 18086: {'lr': 0.00048556870730141906, 'samples': 3472512, 'steps': 18085, 'loss/train': 1.4645930528640747} 08/30/2021 16:29:15 - INFO - __main__ - Step 18087: {'lr': 0.00048556693033552926, 'samples': 3472704, 'steps': 18086, 'loss/train': 1.5588650703430176} 08/30/2021 16:29:15 - INFO - __main__ - Step 18088: {'lr': 0.0004855651532634966, 'samples': 3472896, 'steps': 18087, 'loss/train': 1.4824671745300293} 08/30/2021 16:29:17 - INFO - __main__ - Step 18089: {'lr': 0.00048556337608532196, 'samples': 3473088, 'steps': 18088, 'loss/train': 1.5125601291656494} 08/30/2021 16:29:17 - INFO - __main__ - Step 18090: {'lr': 0.00048556159880100604, 'samples': 3473280, 'steps': 18089, 'loss/train': 1.5799002647399902} 08/30/2021 16:29:17 - INFO - __main__ - Step 18091: {'lr': 0.00048555982141054976, 'samples': 3473472, 'steps': 18090, 'loss/train': 1.3235498666763306} 08/30/2021 16:29:18 - INFO - __main__ - Step 18092: {'lr': 0.0004855580439139539, 'samples': 3473664, 'steps': 18091, 'loss/train': 1.2626641988754272} 08/30/2021 16:29:18 - INFO - __main__ - Step 18093: {'lr': 0.00048555626631121906, 'samples': 3473856, 'steps': 18092, 'loss/train': 1.4647942781448364} 08/30/2021 16:29:20 - INFO - __main__ - Step 18094: {'lr': 0.0004855544886023463, 'samples': 3474048, 'steps': 18093, 'loss/train': 1.4743677377700806} 08/30/2021 16:29:20 - INFO - __main__ - Step 18095: {'lr': 0.00048555271078733637, 'samples': 3474240, 'steps': 18094, 'loss/train': 1.375719666481018} 08/30/2021 16:29:20 - INFO - __main__ - Step 18096: {'lr': 0.00048555093286618996, 'samples': 3474432, 'steps': 18095, 'loss/train': 2.1218225955963135} 08/30/2021 16:29:21 - INFO - __main__ - Step 18097: {'lr': 0.0004855491548389079, 'samples': 3474624, 'steps': 18096, 'loss/train': 1.4977178573608398} 08/30/2021 16:29:21 - INFO - __main__ - Step 18098: {'lr': 0.0004855473767054911, 'samples': 3474816, 'steps': 18097, 'loss/train': 1.7799386978149414} 08/30/2021 16:29:23 - INFO - __main__ - Step 18099: {'lr': 0.00048554559846594026, 'samples': 3475008, 'steps': 18098, 'loss/train': 1.7905550003051758} 08/30/2021 16:29:23 - INFO - __main__ - Step 18100: {'lr': 0.0004855438201202562, 'samples': 3475200, 'steps': 18099, 'loss/train': 1.3962756395339966} 08/30/2021 16:29:23 - INFO - __main__ - Step 18101: {'lr': 0.0004855420416684398, 'samples': 3475392, 'steps': 18100, 'loss/train': 1.8041163682937622} 08/30/2021 16:29:24 - INFO - __main__ - Step 18102: {'lr': 0.0004855402631104917, 'samples': 3475584, 'steps': 18101, 'loss/train': 0.3637233376502991} 08/30/2021 16:29:24 - INFO - __main__ - Step 18103: {'lr': 0.0004855384844464128, 'samples': 3475776, 'steps': 18102, 'loss/train': 1.7341152429580688} 08/30/2021 16:29:24 - INFO - __main__ - Step 18104: {'lr': 0.00048553670567620395, 'samples': 3475968, 'steps': 18103, 'loss/train': 1.2765697240829468} 08/30/2021 16:29:26 - INFO - __main__ - Step 18105: {'lr': 0.0004855349267998659, 'samples': 3476160, 'steps': 18104, 'loss/train': 1.5414867401123047} 08/30/2021 16:29:26 - INFO - __main__ - Step 18106: {'lr': 0.0004855331478173994, 'samples': 3476352, 'steps': 18105, 'loss/train': 2.287764310836792} 08/30/2021 16:29:27 - INFO - __main__ - Step 18107: {'lr': 0.0004855313687288053, 'samples': 3476544, 'steps': 18106, 'loss/train': 1.6214512586593628} 08/30/2021 16:29:27 - INFO - __main__ - Step 18108: {'lr': 0.00048552958953408437, 'samples': 3476736, 'steps': 18107, 'loss/train': 1.9014850854873657} 08/30/2021 16:29:28 - INFO - __main__ - Step 18109: {'lr': 0.0004855278102332375, 'samples': 3476928, 'steps': 18108, 'loss/train': 1.979744791984558} 08/30/2021 16:29:29 - INFO - __main__ - Step 18110: {'lr': 0.0004855260308262654, 'samples': 3477120, 'steps': 18109, 'loss/train': 1.468855857849121} 08/30/2021 16:29:30 - INFO - __main__ - Step 18111: {'lr': 0.00048552425131316893, 'samples': 3477312, 'steps': 18110, 'loss/train': 2.183777093887329} 08/30/2021 16:29:30 - INFO - __main__ - Step 18112: {'lr': 0.0004855224716939488, 'samples': 3477504, 'steps': 18111, 'loss/train': 1.2424217462539673} 08/30/2021 16:29:30 - INFO - __main__ - Step 18113: {'lr': 0.0004855206919686059, 'samples': 3477696, 'steps': 18112, 'loss/train': 1.9680477380752563} 08/30/2021 16:29:31 - INFO - __main__ - Step 18114: {'lr': 0.0004855189121371411, 'samples': 3477888, 'steps': 18113, 'loss/train': 1.4735645055770874} 08/30/2021 16:29:32 - INFO - __main__ - Step 18115: {'lr': 0.00048551713219955505, 'samples': 3478080, 'steps': 18114, 'loss/train': 1.5061053037643433} 08/30/2021 16:29:32 - INFO - __main__ - Step 18116: {'lr': 0.00048551535215584865, 'samples': 3478272, 'steps': 18115, 'loss/train': 1.6229461431503296} 08/30/2021 16:29:33 - INFO - __main__ - Step 18117: {'lr': 0.00048551357200602265, 'samples': 3478464, 'steps': 18116, 'loss/train': 0.8685430288314819} 08/30/2021 16:29:33 - INFO - __main__ - Step 18118: {'lr': 0.0004855117917500778, 'samples': 3478656, 'steps': 18117, 'loss/train': 1.8633511066436768} 08/30/2021 16:29:34 - INFO - __main__ - Step 18119: {'lr': 0.000485510011388015, 'samples': 3478848, 'steps': 18118, 'loss/train': 1.6058130264282227} 08/30/2021 16:29:35 - INFO - __main__ - Step 18120: {'lr': 0.00048550823091983507, 'samples': 3479040, 'steps': 18119, 'loss/train': 0.5264639258384705} 08/30/2021 16:29:36 - INFO - __main__ - Step 18121: {'lr': 0.00048550645034553877, 'samples': 3479232, 'steps': 18120, 'loss/train': 1.413364052772522} 08/30/2021 16:29:36 - INFO - __main__ - Step 18122: {'lr': 0.00048550466966512684, 'samples': 3479424, 'steps': 18121, 'loss/train': 1.579680323600769} 08/30/2021 16:29:36 - INFO - __main__ - Step 18123: {'lr': 0.0004855028888786002, 'samples': 3479616, 'steps': 18122, 'loss/train': 1.9736636877059937} 08/30/2021 16:29:37 - INFO - __main__ - Step 18124: {'lr': 0.00048550110798595953, 'samples': 3479808, 'steps': 18123, 'loss/train': 1.5097899436950684} 08/30/2021 16:29:39 - INFO - __main__ - Step 18125: {'lr': 0.0004854993269872057, 'samples': 3480000, 'steps': 18124, 'loss/train': 1.5835509300231934} 08/30/2021 16:29:39 - INFO - __main__ - Step 18126: {'lr': 0.0004854975458823396, 'samples': 3480192, 'steps': 18125, 'loss/train': 2.423356056213379} 08/30/2021 16:29:39 - INFO - __main__ - Step 18127: {'lr': 0.0004854957646713618, 'samples': 3480384, 'steps': 18126, 'loss/train': 1.6631091833114624} 08/30/2021 16:29:40 - INFO - __main__ - Step 18128: {'lr': 0.00048549398335427337, 'samples': 3480576, 'steps': 18127, 'loss/train': 1.527232050895691} 08/30/2021 16:29:40 - INFO - __main__ - Step 18129: {'lr': 0.0004854922019310749, 'samples': 3480768, 'steps': 18128, 'loss/train': 1.6804276704788208} 08/30/2021 16:29:42 - INFO - __main__ - Step 18130: {'lr': 0.0004854904204017673, 'samples': 3480960, 'steps': 18129, 'loss/train': 1.1936918497085571} 08/30/2021 16:29:43 - INFO - __main__ - Step 18131: {'lr': 0.0004854886387663514, 'samples': 3481152, 'steps': 18130, 'loss/train': 2.179919481277466} 08/30/2021 16:29:43 - INFO - __main__ - Step 18132: {'lr': 0.0004854868570248279, 'samples': 3481344, 'steps': 18131, 'loss/train': 1.3007756471633911} 08/30/2021 16:29:43 - INFO - __main__ - Step 18133: {'lr': 0.00048548507517719766, 'samples': 3481536, 'steps': 18132, 'loss/train': 1.2625625133514404} 08/30/2021 16:29:44 - INFO - __main__ - Step 18134: {'lr': 0.0004854832932234615, 'samples': 3481728, 'steps': 18133, 'loss/train': 1.6213260889053345} 08/30/2021 16:29:44 - INFO - __main__ - Step 18135: {'lr': 0.0004854815111636202, 'samples': 3481920, 'steps': 18134, 'loss/train': 1.7813739776611328} 08/30/2021 16:29:45 - INFO - __main__ - Step 18136: {'lr': 0.00048547972899767454, 'samples': 3482112, 'steps': 18135, 'loss/train': 1.9012194871902466} 08/30/2021 16:29:46 - INFO - __main__ - Step 18137: {'lr': 0.0004854779467256254, 'samples': 3482304, 'steps': 18136, 'loss/train': 1.1619831323623657} 08/30/2021 16:29:46 - INFO - __main__ - Step 18138: {'lr': 0.00048547616434747344, 'samples': 3482496, 'steps': 18137, 'loss/train': 1.0694165229797363} 08/30/2021 16:29:47 - INFO - __main__ - Step 18139: {'lr': 0.0004854743818632196, 'samples': 3482688, 'steps': 18138, 'loss/train': 0.7140091061592102} 08/30/2021 16:29:47 - INFO - __main__ - Step 18140: {'lr': 0.0004854725992728647, 'samples': 3482880, 'steps': 18139, 'loss/train': 1.559740424156189} 08/30/2021 16:29:48 - INFO - __main__ - Step 18141: {'lr': 0.00048547081657640935, 'samples': 3483072, 'steps': 18140, 'loss/train': 1.8245887756347656} 08/30/2021 16:29:49 - INFO - __main__ - Step 18142: {'lr': 0.00048546903377385457, 'samples': 3483264, 'steps': 18141, 'loss/train': 0.4078364372253418} 08/30/2021 16:29:49 - INFO - __main__ - Step 18143: {'lr': 0.00048546725086520107, 'samples': 3483456, 'steps': 18142, 'loss/train': 2.0865206718444824} 08/30/2021 16:29:50 - INFO - __main__ - Step 18144: {'lr': 0.00048546546785044965, 'samples': 3483648, 'steps': 18143, 'loss/train': 1.1922963857650757} 08/30/2021 16:29:50 - INFO - __main__ - Step 18145: {'lr': 0.00048546368472960114, 'samples': 3483840, 'steps': 18144, 'loss/train': 1.7791651487350464} 08/30/2021 16:29:51 - INFO - __main__ - Step 18146: {'lr': 0.00048546190150265634, 'samples': 3484032, 'steps': 18145, 'loss/train': 1.6271249055862427} 08/30/2021 16:29:52 - INFO - __main__ - Step 18147: {'lr': 0.00048546011816961597, 'samples': 3484224, 'steps': 18146, 'loss/train': 1.6857608556747437} 08/30/2021 16:29:52 - INFO - __main__ - Step 18148: {'lr': 0.00048545833473048094, 'samples': 3484416, 'steps': 18147, 'loss/train': 1.4611496925354004} 08/30/2021 16:29:52 - INFO - __main__ - Step 18149: {'lr': 0.00048545655118525206, 'samples': 3484608, 'steps': 18148, 'loss/train': 1.7676684856414795} 08/30/2021 16:29:53 - INFO - __main__ - Step 18150: {'lr': 0.00048545476753393004, 'samples': 3484800, 'steps': 18149, 'loss/train': 1.7006365060806274} 08/30/2021 16:29:55 - INFO - __main__ - Step 18151: {'lr': 0.0004854529837765158, 'samples': 3484992, 'steps': 18150, 'loss/train': 2.1798832416534424} 08/30/2021 16:29:55 - INFO - __main__ - Step 18152: {'lr': 0.00048545119991301, 'samples': 3485184, 'steps': 18151, 'loss/train': 0.24442991614341736} 08/30/2021 16:29:55 - INFO - __main__ - Step 18153: {'lr': 0.0004854494159434135, 'samples': 3485376, 'steps': 18152, 'loss/train': 0.07093805074691772} 08/30/2021 16:29:56 - INFO - __main__ - Step 18154: {'lr': 0.0004854476318677272, 'samples': 3485568, 'steps': 18153, 'loss/train': 2.1398026943206787} 08/30/2021 16:29:56 - INFO - __main__ - Step 18155: {'lr': 0.00048544584768595185, 'samples': 3485760, 'steps': 18154, 'loss/train': 1.5284425020217896} 08/30/2021 16:29:56 - INFO - __main__ - Step 18156: {'lr': 0.00048544406339808823, 'samples': 3485952, 'steps': 18155, 'loss/train': 1.9047931432724} 08/30/2021 16:29:58 - INFO - __main__ - Step 18157: {'lr': 0.00048544227900413706, 'samples': 3486144, 'steps': 18156, 'loss/train': 1.0087835788726807} 08/30/2021 16:29:58 - INFO - __main__ - Step 18158: {'lr': 0.0004854404945040993, 'samples': 3486336, 'steps': 18157, 'loss/train': 1.7160950899124146} 08/30/2021 16:29:59 - INFO - __main__ - Step 18159: {'lr': 0.0004854387098979757, 'samples': 3486528, 'steps': 18158, 'loss/train': 2.1456117630004883} 08/30/2021 16:29:59 - INFO - __main__ - Step 18160: {'lr': 0.000485436925185767, 'samples': 3486720, 'steps': 18159, 'loss/train': 1.3853322267532349} 08/30/2021 16:29:59 - INFO - __main__ - Step 18161: {'lr': 0.00048543514036747404, 'samples': 3486912, 'steps': 18160, 'loss/train': 2.0687689781188965} 08/30/2021 16:30:01 - INFO - __main__ - Step 18162: {'lr': 0.00048543335544309776, 'samples': 3487104, 'steps': 18161, 'loss/train': 1.7371457815170288} 08/30/2021 16:30:02 - INFO - __main__ - Step 18163: {'lr': 0.00048543157041263876, 'samples': 3487296, 'steps': 18162, 'loss/train': 1.9401506185531616} 08/30/2021 16:30:02 - INFO - __main__ - Step 18164: {'lr': 0.0004854297852760979, 'samples': 3487488, 'steps': 18163, 'loss/train': 1.199976921081543} 08/30/2021 16:30:03 - INFO - __main__ - Step 18165: {'lr': 0.000485428000033476, 'samples': 3487680, 'steps': 18164, 'loss/train': 1.9119760990142822} 08/30/2021 16:30:03 - INFO - __main__ - Step 18166: {'lr': 0.00048542621468477393, 'samples': 3487872, 'steps': 18165, 'loss/train': 1.1560609340667725} 08/30/2021 16:30:03 - INFO - __main__ - Step 18167: {'lr': 0.0004854244292299924, 'samples': 3488064, 'steps': 18166, 'loss/train': 1.251025676727295} 08/30/2021 16:30:04 - INFO - __main__ - Step 18168: {'lr': 0.0004854226436691323, 'samples': 3488256, 'steps': 18167, 'loss/train': 0.1865871548652649} 08/30/2021 16:30:05 - INFO - __main__ - Step 18169: {'lr': 0.0004854208580021944, 'samples': 3488448, 'steps': 18168, 'loss/train': 0.15591633319854736} 08/30/2021 16:30:06 - INFO - __main__ - Step 18170: {'lr': 0.00048541907222917946, 'samples': 3488640, 'steps': 18169, 'loss/train': 2.0507378578186035} 08/30/2021 16:30:06 - INFO - __main__ - Step 18171: {'lr': 0.0004854172863500883, 'samples': 3488832, 'steps': 18170, 'loss/train': 1.788221001625061} 08/30/2021 16:30:06 - INFO - __main__ - Step 18172: {'lr': 0.00048541550036492175, 'samples': 3489024, 'steps': 18171, 'loss/train': 2.480135679244995} 08/30/2021 16:30:07 - INFO - __main__ - Step 18173: {'lr': 0.00048541371427368064, 'samples': 3489216, 'steps': 18172, 'loss/train': 2.4320027828216553} 08/30/2021 16:30:08 - INFO - __main__ - Step 18174: {'lr': 0.0004854119280763657, 'samples': 3489408, 'steps': 18173, 'loss/train': 1.6566660404205322} 08/30/2021 16:30:09 - INFO - __main__ - Step 18175: {'lr': 0.00048541014177297783, 'samples': 3489600, 'steps': 18174, 'loss/train': 1.9397094249725342} 08/30/2021 16:30:09 - INFO - __main__ - Step 18176: {'lr': 0.0004854083553635178, 'samples': 3489792, 'steps': 18175, 'loss/train': 1.500089406967163} 08/30/2021 16:30:10 - INFO - __main__ - Step 18177: {'lr': 0.00048540656884798626, 'samples': 3489984, 'steps': 18176, 'loss/train': 1.5683972835540771} 08/30/2021 16:30:10 - INFO - __main__ - Step 18178: {'lr': 0.0004854047822263843, 'samples': 3490176, 'steps': 18177, 'loss/train': 1.6979554891586304} 08/30/2021 16:30:10 - INFO - __main__ - Step 18179: {'lr': 0.00048540299549871256, 'samples': 3490368, 'steps': 18178, 'loss/train': 0.07497352361679077} 08/30/2021 16:30:11 - INFO - __main__ - Step 18180: {'lr': 0.0004854012086649718, 'samples': 3490560, 'steps': 18179, 'loss/train': 0.6716282367706299} 08/30/2021 16:30:12 - INFO - __main__ - Step 18181: {'lr': 0.00048539942172516295, 'samples': 3490752, 'steps': 18180, 'loss/train': 0.06318680942058563} 08/30/2021 16:30:13 - INFO - __main__ - Step 18182: {'lr': 0.00048539763467928665, 'samples': 3490944, 'steps': 18181, 'loss/train': 1.983986496925354} 08/30/2021 16:30:13 - INFO - __main__ - Step 18183: {'lr': 0.0004853958475273439, 'samples': 3491136, 'steps': 18182, 'loss/train': 1.9680562019348145} 08/30/2021 16:30:13 - INFO - __main__ - Step 18184: {'lr': 0.0004853940602693354, 'samples': 3491328, 'steps': 18183, 'loss/train': 1.910803198814392} 08/30/2021 16:30:14 - INFO - __main__ - Step 18185: {'lr': 0.00048539227290526194, 'samples': 3491520, 'steps': 18184, 'loss/train': 1.7229681015014648} 08/30/2021 16:30:16 - INFO - __main__ - Step 18186: {'lr': 0.00048539048543512443, 'samples': 3491712, 'steps': 18185, 'loss/train': 1.7122142314910889} 08/30/2021 16:30:17 - INFO - __main__ - Step 18187: {'lr': 0.0004853886978589235, 'samples': 3491904, 'steps': 18186, 'loss/train': 1.6136554479599} 08/30/2021 16:30:17 - INFO - __main__ - Step 18188: {'lr': 0.0004853869101766601, 'samples': 3492096, 'steps': 18187, 'loss/train': 1.744834303855896} 08/30/2021 16:30:17 - INFO - __main__ - Step 18189: {'lr': 0.000485385122388335, 'samples': 3492288, 'steps': 18188, 'loss/train': 1.8125004768371582} 08/30/2021 16:30:18 - INFO - __main__ - Step 18190: {'lr': 0.000485383334493949, 'samples': 3492480, 'steps': 18189, 'loss/train': 0.11176054179668427} 08/30/2021 16:30:19 - INFO - __main__ - Step 18191: {'lr': 0.00048538154649350286, 'samples': 3492672, 'steps': 18190, 'loss/train': 1.5933929681777954} 08/30/2021 16:30:20 - INFO - __main__ - Step 18192: {'lr': 0.00048537975838699744, 'samples': 3492864, 'steps': 18191, 'loss/train': 1.4787840843200684} 08/30/2021 16:30:20 - INFO - __main__ - Step 18193: {'lr': 0.0004853779701744335, 'samples': 3493056, 'steps': 18192, 'loss/train': 1.5653127431869507} 08/30/2021 16:30:20 - INFO - __main__ - Step 18194: {'lr': 0.000485376181855812, 'samples': 3493248, 'steps': 18193, 'loss/train': 1.5043683052062988} 08/30/2021 16:30:21 - INFO - __main__ - Step 18195: {'lr': 0.00048537439343113354, 'samples': 3493440, 'steps': 18194, 'loss/train': 1.4824970960617065} 08/30/2021 16:30:21 - INFO - __main__ - Step 18196: {'lr': 0.000485372604900399, 'samples': 3493632, 'steps': 18195, 'loss/train': 1.315542459487915} 08/30/2021 16:30:22 - INFO - __main__ - Step 18197: {'lr': 0.0004853708162636092, 'samples': 3493824, 'steps': 18196, 'loss/train': 1.5427913665771484} 08/30/2021 16:30:23 - INFO - __main__ - Step 18198: {'lr': 0.00048536902752076494, 'samples': 3494016, 'steps': 18197, 'loss/train': 1.4136998653411865} 08/30/2021 16:30:23 - INFO - __main__ - Step 18199: {'lr': 0.00048536723867186705, 'samples': 3494208, 'steps': 18198, 'loss/train': 2.3811869621276855} 08/30/2021 16:30:24 - INFO - __main__ - Step 18200: {'lr': 0.0004853654497169163, 'samples': 3494400, 'steps': 18199, 'loss/train': 1.7197117805480957} 08/30/2021 16:30:24 - INFO - __main__ - Step 18201: {'lr': 0.00048536366065591354, 'samples': 3494592, 'steps': 18200, 'loss/train': 1.966328740119934} 08/30/2021 16:30:25 - INFO - __main__ - Step 18202: {'lr': 0.00048536187148885956, 'samples': 3494784, 'steps': 18201, 'loss/train': 1.398764729499817} 08/30/2021 16:30:26 - INFO - __main__ - Step 18203: {'lr': 0.0004853600822157551, 'samples': 3494976, 'steps': 18202, 'loss/train': 1.0334347486495972} 08/30/2021 16:30:26 - INFO - __main__ - Step 18204: {'lr': 0.000485358292836601, 'samples': 3495168, 'steps': 18203, 'loss/train': 2.1281890869140625} 08/30/2021 16:30:27 - INFO - __main__ - Step 18205: {'lr': 0.0004853565033513982, 'samples': 3495360, 'steps': 18204, 'loss/train': 0.22665266692638397} 08/30/2021 16:30:27 - INFO - __main__ - Step 18206: {'lr': 0.0004853547137601473, 'samples': 3495552, 'steps': 18205, 'loss/train': 1.2151612043380737} 08/30/2021 16:30:29 - INFO - __main__ - Step 18207: {'lr': 0.0004853529240628493, 'samples': 3495744, 'steps': 18206, 'loss/train': 1.48349928855896} 08/30/2021 16:30:29 - INFO - __main__ - Step 18208: {'lr': 0.00048535113425950474, 'samples': 3495936, 'steps': 18207, 'loss/train': 1.808370590209961} 08/30/2021 16:30:29 - INFO - __main__ - Step 18209: {'lr': 0.0004853493443501147, 'samples': 3496128, 'steps': 18208, 'loss/train': 0.945346474647522} 08/30/2021 16:30:30 - INFO - __main__ - Step 18210: {'lr': 0.0004853475543346798, 'samples': 3496320, 'steps': 18209, 'loss/train': 1.5416520833969116} 08/30/2021 16:30:30 - INFO - __main__ - Step 18211: {'lr': 0.000485345764213201, 'samples': 3496512, 'steps': 18210, 'loss/train': 1.618773102760315} 08/30/2021 16:30:30 - INFO - __main__ - Step 18212: {'lr': 0.00048534397398567895, 'samples': 3496704, 'steps': 18211, 'loss/train': 1.5082675218582153} 08/30/2021 16:30:32 - INFO - __main__ - Step 18213: {'lr': 0.00048534218365211456, 'samples': 3496896, 'steps': 18212, 'loss/train': 0.14711081981658936} 08/30/2021 16:30:32 - INFO - __main__ - Step 18214: {'lr': 0.0004853403932125087, 'samples': 3497088, 'steps': 18213, 'loss/train': 1.564862608909607} 08/30/2021 16:30:33 - INFO - __main__ - Step 18215: {'lr': 0.00048533860266686203, 'samples': 3497280, 'steps': 18214, 'loss/train': 2.049409866333008} 08/30/2021 16:30:33 - INFO - __main__ - Step 18216: {'lr': 0.0004853368120151754, 'samples': 3497472, 'steps': 18215, 'loss/train': 1.8001041412353516} 08/30/2021 16:30:33 - INFO - __main__ - Step 18217: {'lr': 0.00048533502125744967, 'samples': 3497664, 'steps': 18216, 'loss/train': 1.8892565965652466} 08/30/2021 16:30:35 - INFO - __main__ - Step 18218: {'lr': 0.0004853332303936856, 'samples': 3497856, 'steps': 18217, 'loss/train': 1.4445117712020874} 08/30/2021 16:30:35 - INFO - __main__ - Step 18219: {'lr': 0.000485331439423884, 'samples': 3498048, 'steps': 18218, 'loss/train': 1.5056453943252563} 08/30/2021 16:30:36 - INFO - __main__ - Step 18220: {'lr': 0.00048532964834804566, 'samples': 3498240, 'steps': 18219, 'loss/train': 0.9864267706871033} 08/30/2021 16:30:36 - INFO - __main__ - Step 18221: {'lr': 0.00048532785716617145, 'samples': 3498432, 'steps': 18220, 'loss/train': 1.4905229806900024} 08/30/2021 16:30:37 - INFO - __main__ - Step 18222: {'lr': 0.0004853260658782621, 'samples': 3498624, 'steps': 18221, 'loss/train': 1.4205816984176636} 08/30/2021 16:30:38 - INFO - __main__ - Step 18223: {'lr': 0.0004853242744843185, 'samples': 3498816, 'steps': 18222, 'loss/train': 2.076859712600708} 08/30/2021 16:30:38 - INFO - __main__ - Step 18224: {'lr': 0.0004853224829843414, 'samples': 3499008, 'steps': 18223, 'loss/train': 2.2336368560791016} 08/30/2021 16:30:39 - INFO - __main__ - Step 18225: {'lr': 0.00048532069137833156, 'samples': 3499200, 'steps': 18224, 'loss/train': 1.8242483139038086} 08/30/2021 16:30:39 - INFO - __main__ - Step 18226: {'lr': 0.00048531889966628997, 'samples': 3499392, 'steps': 18225, 'loss/train': 1.3434109687805176} 08/30/2021 16:30:40 - INFO - __main__ - Step 18227: {'lr': 0.00048531710784821726, 'samples': 3499584, 'steps': 18226, 'loss/train': 1.7954832315444946} 08/30/2021 16:30:41 - INFO - __main__ - Step 18228: {'lr': 0.0004853153159241143, 'samples': 3499776, 'steps': 18227, 'loss/train': 1.3241018056869507} 08/30/2021 16:30:41 - INFO - __main__ - Step 18229: {'lr': 0.0004853135238939818, 'samples': 3499968, 'steps': 18228, 'loss/train': 1.6579416990280151} 08/30/2021 16:30:42 - INFO - __main__ - Step 18230: {'lr': 0.0004853117317578207, 'samples': 3500160, 'steps': 18229, 'loss/train': 2.469796657562256} 08/30/2021 16:30:42 - INFO - __main__ - Step 18231: {'lr': 0.00048530993951563186, 'samples': 3500352, 'steps': 18230, 'loss/train': 1.4420359134674072} 08/30/2021 16:30:42 - INFO - __main__ - Step 18232: {'lr': 0.0004853081471674159, 'samples': 3500544, 'steps': 18231, 'loss/train': 1.3792097568511963} 08/30/2021 16:30:43 - INFO - __main__ - Step 18233: {'lr': 0.00048530635471317373, 'samples': 3500736, 'steps': 18232, 'loss/train': 1.8431075811386108} 08/30/2021 16:30:45 - INFO - __main__ - Step 18234: {'lr': 0.0004853045621529062, 'samples': 3500928, 'steps': 18233, 'loss/train': 0.8953320980072021} 08/30/2021 16:30:45 - INFO - __main__ - Step 18235: {'lr': 0.000485302769486614, 'samples': 3501120, 'steps': 18234, 'loss/train': 1.5394054651260376} 08/30/2021 16:30:45 - INFO - __main__ - Step 18236: {'lr': 0.000485300976714298, 'samples': 3501312, 'steps': 18235, 'loss/train': 1.4558779001235962} 08/30/2021 16:30:46 - INFO - __main__ - Step 18237: {'lr': 0.00048529918383595906, 'samples': 3501504, 'steps': 18236, 'loss/train': 1.3067607879638672} 08/30/2021 16:30:46 - INFO - __main__ - Step 18238: {'lr': 0.0004852973908515979, 'samples': 3501696, 'steps': 18237, 'loss/train': 0.7174292802810669} 08/30/2021 16:30:48 - INFO - __main__ - Step 18239: {'lr': 0.0004852955977612154, 'samples': 3501888, 'steps': 18238, 'loss/train': 1.5812405347824097} 08/30/2021 16:30:49 - INFO - __main__ - Step 18240: {'lr': 0.0004852938045648123, 'samples': 3502080, 'steps': 18239, 'loss/train': 1.4285887479782104} 08/30/2021 16:30:49 - INFO - __main__ - Step 18241: {'lr': 0.0004852920112623895, 'samples': 3502272, 'steps': 18240, 'loss/train': 2.0259315967559814} 08/30/2021 16:30:49 - INFO - __main__ - Step 18242: {'lr': 0.00048529021785394765, 'samples': 3502464, 'steps': 18241, 'loss/train': 1.8416999578475952} 08/30/2021 16:30:50 - INFO - __main__ - Step 18243: {'lr': 0.00048528842433948776, 'samples': 3502656, 'steps': 18242, 'loss/train': 1.518181324005127} 08/30/2021 16:30:52 - INFO - __main__ - Step 18244: {'lr': 0.00048528663071901047, 'samples': 3502848, 'steps': 18243, 'loss/train': 1.5467149019241333} 08/30/2021 16:30:52 - INFO - __main__ - Step 18245: {'lr': 0.0004852848369925167, 'samples': 3503040, 'steps': 18244, 'loss/train': 2.726255416870117} 08/30/2021 16:30:53 - INFO - __main__ - Step 18246: {'lr': 0.00048528304316000723, 'samples': 3503232, 'steps': 18245, 'loss/train': 1.824460744857788} 08/30/2021 16:30:53 - INFO - __main__ - Step 18247: {'lr': 0.0004852812492214828, 'samples': 3503424, 'steps': 18246, 'loss/train': 1.953322172164917} 08/30/2021 16:30:53 - INFO - __main__ - Step 18248: {'lr': 0.0004852794551769443, 'samples': 3503616, 'steps': 18247, 'loss/train': 2.5393340587615967} 08/30/2021 16:30:54 - INFO - __main__ - Step 18249: {'lr': 0.0004852776610263925, 'samples': 3503808, 'steps': 18248, 'loss/train': 2.7364838123321533} 08/30/2021 16:30:54 - INFO - __main__ - Step 18250: {'lr': 0.0004852758667698282, 'samples': 3504000, 'steps': 18249, 'loss/train': 1.9968701601028442} 08/30/2021 16:30:56 - INFO - __main__ - Step 18251: {'lr': 0.00048527407240725223, 'samples': 3504192, 'steps': 18250, 'loss/train': 2.165238618850708} 08/30/2021 16:30:56 - INFO - __main__ - Step 18252: {'lr': 0.0004852722779386654, 'samples': 3504384, 'steps': 18251, 'loss/train': 2.3952183723449707} 08/30/2021 16:30:57 - INFO - __main__ - Step 18253: {'lr': 0.00048527048336406855, 'samples': 3504576, 'steps': 18252, 'loss/train': 2.9041616916656494} 08/30/2021 16:30:57 - INFO - __main__ - Step 18254: {'lr': 0.00048526868868346243, 'samples': 3504768, 'steps': 18253, 'loss/train': 2.2178878784179688} 08/30/2021 16:30:57 - INFO - __main__ - Step 18255: {'lr': 0.0004852668938968478, 'samples': 3504960, 'steps': 18254, 'loss/train': 2.0800187587738037} 08/30/2021 16:30:59 - INFO - __main__ - Step 18256: {'lr': 0.0004852650990042256, 'samples': 3505152, 'steps': 18255, 'loss/train': 1.8880712985992432} 08/30/2021 16:31:00 - INFO - __main__ - Step 18257: {'lr': 0.0004852633040055966, 'samples': 3505344, 'steps': 18256, 'loss/train': 2.0610196590423584} 08/30/2021 16:31:00 - INFO - __main__ - Step 18258: {'lr': 0.00048526150890096153, 'samples': 3505536, 'steps': 18257, 'loss/train': 1.6383503675460815} 08/30/2021 16:31:00 - INFO - __main__ - Step 18259: {'lr': 0.0004852597136903213, 'samples': 3505728, 'steps': 18258, 'loss/train': 0.2615097165107727} 08/30/2021 16:31:01 - INFO - __main__ - Step 18260: {'lr': 0.0004852579183736766, 'samples': 3505920, 'steps': 18259, 'loss/train': 1.326377511024475} 08/30/2021 16:31:01 - INFO - __main__ - Step 18261: {'lr': 0.00048525612295102836, 'samples': 3506112, 'steps': 18260, 'loss/train': 2.922910213470459} 08/30/2021 16:31:02 - INFO - __main__ - Step 18262: {'lr': 0.00048525432742237736, 'samples': 3506304, 'steps': 18261, 'loss/train': 0.17876708507537842} 08/30/2021 16:31:03 - INFO - __main__ - Step 18263: {'lr': 0.00048525253178772435, 'samples': 3506496, 'steps': 18262, 'loss/train': 1.77130925655365} 08/30/2021 16:31:03 - INFO - __main__ - Step 18264: {'lr': 0.0004852507360470702, 'samples': 3506688, 'steps': 18263, 'loss/train': 1.9590058326721191} 08/30/2021 16:31:04 - INFO - __main__ - Step 18265: {'lr': 0.0004852489402004157, 'samples': 3506880, 'steps': 18264, 'loss/train': 1.867340087890625} 08/30/2021 16:31:04 - INFO - __main__ - Step 18266: {'lr': 0.0004852471442477617, 'samples': 3507072, 'steps': 18265, 'loss/train': 1.7032133340835571} 08/30/2021 16:31:06 - INFO - __main__ - Step 18267: {'lr': 0.0004852453481891089, 'samples': 3507264, 'steps': 18266, 'loss/train': 1.5362731218338013} 08/30/2021 16:31:06 - INFO - __main__ - Step 18268: {'lr': 0.00048524355202445827, 'samples': 3507456, 'steps': 18267, 'loss/train': 2.047058343887329} 08/30/2021 16:31:06 - INFO - __main__ - Step 18269: {'lr': 0.0004852417557538104, 'samples': 3507648, 'steps': 18268, 'loss/train': 1.3270645141601562} 08/30/2021 16:31:07 - INFO - __main__ - Step 18270: {'lr': 0.00048523995937716625, 'samples': 3507840, 'steps': 18269, 'loss/train': 1.3608251810073853} 08/30/2021 16:31:07 - INFO - __main__ - Step 18271: {'lr': 0.0004852381628945267, 'samples': 3508032, 'steps': 18270, 'loss/train': 2.296241521835327} 08/30/2021 16:31:09 - INFO - __main__ - Step 18272: {'lr': 0.0004852363663058924, 'samples': 3508224, 'steps': 18271, 'loss/train': 1.6583689451217651} 08/30/2021 16:31:09 - INFO - __main__ - Step 18273: {'lr': 0.0004852345696112642, 'samples': 3508416, 'steps': 18272, 'loss/train': 1.4764230251312256} 08/30/2021 16:31:09 - INFO - __main__ - Step 18274: {'lr': 0.00048523277281064295, 'samples': 3508608, 'steps': 18273, 'loss/train': 1.6788078546524048} 08/30/2021 16:31:10 - INFO - __main__ - Step 18275: {'lr': 0.0004852309759040294, 'samples': 3508800, 'steps': 18274, 'loss/train': 1.5933668613433838} 08/30/2021 16:31:10 - INFO - __main__ - Step 18276: {'lr': 0.00048522917889142446, 'samples': 3508992, 'steps': 18275, 'loss/train': 1.636905550956726} 08/30/2021 16:31:10 - INFO - __main__ - Step 18277: {'lr': 0.00048522738177282887, 'samples': 3509184, 'steps': 18276, 'loss/train': 1.4415043592453003} 08/30/2021 16:31:12 - INFO - __main__ - Step 18278: {'lr': 0.0004852255845482435, 'samples': 3509376, 'steps': 18277, 'loss/train': 1.8900659084320068} 08/30/2021 16:31:13 - INFO - __main__ - Step 18279: {'lr': 0.0004852237872176691, 'samples': 3509568, 'steps': 18278, 'loss/train': 0.18102802336215973} 08/30/2021 16:31:13 - INFO - __main__ - Step 18280: {'lr': 0.00048522198978110645, 'samples': 3509760, 'steps': 18279, 'loss/train': 1.3858753442764282} 08/30/2021 16:31:13 - INFO - __main__ - Step 18281: {'lr': 0.0004852201922385564, 'samples': 3509952, 'steps': 18280, 'loss/train': 1.6936274766921997} 08/30/2021 16:31:14 - INFO - __main__ - Step 18282: {'lr': 0.00048521839459001977, 'samples': 3510144, 'steps': 18281, 'loss/train': 1.615212082862854} 08/30/2021 16:31:15 - INFO - __main__ - Step 18283: {'lr': 0.0004852165968354973, 'samples': 3510336, 'steps': 18282, 'loss/train': 1.8196706771850586} 08/30/2021 16:31:16 - INFO - __main__ - Step 18284: {'lr': 0.00048521479897499, 'samples': 3510528, 'steps': 18283, 'loss/train': 1.353030800819397} 08/30/2021 16:31:16 - INFO - __main__ - Step 18285: {'lr': 0.0004852130010084984, 'samples': 3510720, 'steps': 18284, 'loss/train': 1.5243914127349854} 08/30/2021 16:31:16 - INFO - __main__ - Step 18286: {'lr': 0.0004852112029360235, 'samples': 3510912, 'steps': 18285, 'loss/train': 1.9026896953582764} 08/30/2021 16:31:17 - INFO - __main__ - Step 18287: {'lr': 0.0004852094047575661, 'samples': 3511104, 'steps': 18286, 'loss/train': 2.0276737213134766} 08/30/2021 16:31:17 - INFO - __main__ - Step 18288: {'lr': 0.00048520760647312696, 'samples': 3511296, 'steps': 18287, 'loss/train': 1.7218397855758667} 08/30/2021 16:31:19 - INFO - __main__ - Step 18289: {'lr': 0.00048520580808270687, 'samples': 3511488, 'steps': 18288, 'loss/train': 1.6105717420578003} 08/30/2021 16:31:19 - INFO - __main__ - Step 18290: {'lr': 0.0004852040095863067, 'samples': 3511680, 'steps': 18289, 'loss/train': 1.9469579458236694} 08/30/2021 16:31:19 - INFO - __main__ - Step 18291: {'lr': 0.0004852022109839273, 'samples': 3511872, 'steps': 18290, 'loss/train': 0.3960586488246918} 08/30/2021 16:31:20 - INFO - __main__ - Step 18292: {'lr': 0.0004852004122755693, 'samples': 3512064, 'steps': 18291, 'loss/train': 2.3295421600341797} 08/30/2021 16:31:20 - INFO - __main__ - Step 18293: {'lr': 0.00048519861346123363, 'samples': 3512256, 'steps': 18292, 'loss/train': 1.4214847087860107} 08/30/2021 16:31:22 - INFO - __main__ - Step 18294: {'lr': 0.0004851968145409211, 'samples': 3512448, 'steps': 18293, 'loss/train': 1.611711025238037} 08/30/2021 16:31:22 - INFO - __main__ - Step 18295: {'lr': 0.00048519501551463255, 'samples': 3512640, 'steps': 18294, 'loss/train': 2.0002479553222656} 08/30/2021 16:31:22 - INFO - __main__ - Step 18296: {'lr': 0.0004851932163823688, 'samples': 3512832, 'steps': 18295, 'loss/train': 1.2055373191833496} 08/30/2021 16:31:23 - INFO - __main__ - Step 18297: {'lr': 0.0004851914171441305, 'samples': 3513024, 'steps': 18296, 'loss/train': 1.1820570230484009} 08/30/2021 16:31:23 - INFO - __main__ - Step 18298: {'lr': 0.00048518961779991866, 'samples': 3513216, 'steps': 18297, 'loss/train': 2.120363235473633} 08/30/2021 16:31:26 - INFO - __main__ - Step 18299: {'lr': 0.00048518781834973405, 'samples': 3513408, 'steps': 18298, 'loss/train': 1.4115668535232544} 08/30/2021 16:31:26 - INFO - __main__ - Step 18300: {'lr': 0.0004851860187935773, 'samples': 3513600, 'steps': 18299, 'loss/train': 1.4641038179397583} 08/30/2021 16:31:27 - INFO - __main__ - Step 18301: {'lr': 0.0004851842191314494, 'samples': 3513792, 'steps': 18300, 'loss/train': 2.2291409969329834} 08/30/2021 16:31:27 - INFO - __main__ - Step 18302: {'lr': 0.0004851824193633512, 'samples': 3513984, 'steps': 18301, 'loss/train': 1.5605565309524536} 08/30/2021 16:31:27 - INFO - __main__ - Step 18303: {'lr': 0.00048518061948928337, 'samples': 3514176, 'steps': 18302, 'loss/train': 1.9699370861053467} 08/30/2021 16:31:28 - INFO - __main__ - Step 18304: {'lr': 0.0004851788195092468, 'samples': 3514368, 'steps': 18303, 'loss/train': 0.10047666728496552} 08/30/2021 16:31:28 - INFO - __main__ - Step 18305: {'lr': 0.00048517701942324225, 'samples': 3514560, 'steps': 18304, 'loss/train': 1.6972315311431885} 08/30/2021 16:31:29 - INFO - __main__ - Step 18306: {'lr': 0.00048517521923127063, 'samples': 3514752, 'steps': 18305, 'loss/train': 1.4234768152236938} 08/30/2021 16:31:30 - INFO - __main__ - Step 18307: {'lr': 0.00048517341893333267, 'samples': 3514944, 'steps': 18306, 'loss/train': 1.5142172574996948} 08/30/2021 16:31:30 - INFO - __main__ - Step 18308: {'lr': 0.0004851716185294291, 'samples': 3515136, 'steps': 18307, 'loss/train': 2.0314602851867676} 08/30/2021 16:31:31 - INFO - __main__ - Step 18309: {'lr': 0.00048516981801956097, 'samples': 3515328, 'steps': 18308, 'loss/train': 1.5293121337890625} 08/30/2021 16:31:31 - INFO - __main__ - Step 18310: {'lr': 0.00048516801740372886, 'samples': 3515520, 'steps': 18309, 'loss/train': 1.6754064559936523} 08/30/2021 16:31:33 - INFO - __main__ - Step 18311: {'lr': 0.0004851662166819337, 'samples': 3515712, 'steps': 18310, 'loss/train': 1.343644618988037} 08/30/2021 16:31:33 - INFO - __main__ - Step 18312: {'lr': 0.00048516441585417624, 'samples': 3515904, 'steps': 18311, 'loss/train': 1.9953339099884033} 08/30/2021 16:31:33 - INFO - __main__ - Step 18313: {'lr': 0.0004851626149204573, 'samples': 3516096, 'steps': 18312, 'loss/train': 1.207190990447998} 08/30/2021 16:31:34 - INFO - __main__ - Step 18314: {'lr': 0.0004851608138807778, 'samples': 3516288, 'steps': 18313, 'loss/train': 1.730093002319336} 08/30/2021 16:31:34 - INFO - __main__ - Step 18315: {'lr': 0.0004851590127351384, 'samples': 3516480, 'steps': 18314, 'loss/train': 2.054384708404541} 08/30/2021 16:31:36 - INFO - __main__ - Step 18316: {'lr': 0.0004851572114835401, 'samples': 3516672, 'steps': 18315, 'loss/train': 2.286177158355713} 08/30/2021 16:31:36 - INFO - __main__ - Step 18317: {'lr': 0.0004851554101259834, 'samples': 3516864, 'steps': 18316, 'loss/train': 1.541135311126709} 08/30/2021 16:31:37 - INFO - __main__ - Step 18318: {'lr': 0.00048515360866246943, 'samples': 3517056, 'steps': 18317, 'loss/train': 1.7443363666534424} 08/30/2021 16:31:37 - INFO - __main__ - Step 18319: {'lr': 0.00048515180709299884, 'samples': 3517248, 'steps': 18318, 'loss/train': 3.8915019035339355} 08/30/2021 16:31:37 - INFO - __main__ - Step 18320: {'lr': 0.0004851500054175725, 'samples': 3517440, 'steps': 18319, 'loss/train': 1.7440677881240845} 08/30/2021 16:31:39 - INFO - __main__ - Step 18321: {'lr': 0.00048514820363619116, 'samples': 3517632, 'steps': 18320, 'loss/train': 0.1379471719264984} 08/30/2021 16:31:39 - INFO - __main__ - Step 18322: {'lr': 0.0004851464017488556, 'samples': 3517824, 'steps': 18321, 'loss/train': 0.9234429597854614} 08/30/2021 16:31:40 - INFO - __main__ - Step 18323: {'lr': 0.0004851445997555668, 'samples': 3518016, 'steps': 18322, 'loss/train': 2.0152969360351562} 08/30/2021 16:31:40 - INFO - __main__ - Step 18324: {'lr': 0.00048514279765632547, 'samples': 3518208, 'steps': 18323, 'loss/train': 1.6747567653656006} 08/30/2021 16:31:40 - INFO - __main__ - Step 18325: {'lr': 0.0004851409954511324, 'samples': 3518400, 'steps': 18324, 'loss/train': 1.8239686489105225} 08/30/2021 16:31:42 - INFO - __main__ - Step 18326: {'lr': 0.0004851391931399884, 'samples': 3518592, 'steps': 18325, 'loss/train': 1.2097152471542358} 08/30/2021 16:31:42 - INFO - __main__ - Step 18327: {'lr': 0.0004851373907228943, 'samples': 3518784, 'steps': 18326, 'loss/train': 1.3782691955566406} 08/30/2021 16:31:43 - INFO - __main__ - Step 18328: {'lr': 0.00048513558819985106, 'samples': 3518976, 'steps': 18327, 'loss/train': 1.735744595527649} 08/30/2021 16:31:43 - INFO - __main__ - Step 18329: {'lr': 0.0004851337855708592, 'samples': 3519168, 'steps': 18328, 'loss/train': 1.9939866065979004} 08/30/2021 16:31:43 - INFO - __main__ - Step 18330: {'lr': 0.0004851319828359198, 'samples': 3519360, 'steps': 18329, 'loss/train': 1.025618076324463} 08/30/2021 16:31:45 - INFO - __main__ - Step 18331: {'lr': 0.0004851301799950334, 'samples': 3519552, 'steps': 18330, 'loss/train': 2.0228524208068848} 08/30/2021 16:31:45 - INFO - __main__ - Step 18332: {'lr': 0.00048512837704820107, 'samples': 3519744, 'steps': 18331, 'loss/train': 1.407360315322876} 08/30/2021 16:31:46 - INFO - __main__ - Step 18333: {'lr': 0.00048512657399542346, 'samples': 3519936, 'steps': 18332, 'loss/train': 1.6591839790344238} 08/30/2021 16:31:46 - INFO - __main__ - Step 18334: {'lr': 0.0004851247708367015, 'samples': 3520128, 'steps': 18333, 'loss/train': 5.407085418701172} 08/30/2021 16:31:46 - INFO - __main__ - Step 18335: {'lr': 0.000485122967572036, 'samples': 3520320, 'steps': 18334, 'loss/train': 1.739969253540039} 08/30/2021 16:31:47 - INFO - __main__ - Step 18336: {'lr': 0.0004851211642014276, 'samples': 3520512, 'steps': 18335, 'loss/train': 1.5402262210845947} 08/30/2021 16:31:48 - INFO - __main__ - Step 18337: {'lr': 0.0004851193607248773, 'samples': 3520704, 'steps': 18336, 'loss/train': 2.23903489112854} 08/30/2021 16:31:49 - INFO - __main__ - Step 18338: {'lr': 0.00048511755714238585, 'samples': 3520896, 'steps': 18337, 'loss/train': 1.6420117616653442} 08/30/2021 16:31:49 - INFO - __main__ - Step 18339: {'lr': 0.0004851157534539541, 'samples': 3521088, 'steps': 18338, 'loss/train': 2.079241991043091} 08/30/2021 16:31:49 - INFO - __main__ - Step 18340: {'lr': 0.0004851139496595827, 'samples': 3521280, 'steps': 18339, 'loss/train': 1.5721169710159302} 08/30/2021 16:31:50 - INFO - __main__ - Step 18341: {'lr': 0.00048511214575927265, 'samples': 3521472, 'steps': 18340, 'loss/train': 2.0448737144470215} 08/30/2021 16:31:51 - INFO - __main__ - Step 18342: {'lr': 0.0004851103417530247, 'samples': 3521664, 'steps': 18341, 'loss/train': 1.964516282081604} 08/30/2021 16:31:52 - INFO - __main__ - Step 18343: {'lr': 0.0004851085376408396, 'samples': 3521856, 'steps': 18342, 'loss/train': 1.792725920677185} 08/30/2021 16:31:52 - INFO - __main__ - Step 18344: {'lr': 0.0004851067334227183, 'samples': 3522048, 'steps': 18343, 'loss/train': 1.1735317707061768} 08/30/2021 16:31:52 - INFO - __main__ - Step 18345: {'lr': 0.0004851049290986615, 'samples': 3522240, 'steps': 18344, 'loss/train': 2.0181925296783447} 08/30/2021 16:31:53 - INFO - __main__ - Step 18346: {'lr': 0.00048510312466867, 'samples': 3522432, 'steps': 18345, 'loss/train': 1.9342454671859741} 08/30/2021 16:31:54 - INFO - __main__ - Step 18347: {'lr': 0.0004851013201327448, 'samples': 3522624, 'steps': 18346, 'loss/train': 1.4876445531845093} 08/30/2021 16:31:55 - INFO - __main__ - Step 18348: {'lr': 0.0004850995154908864, 'samples': 3522816, 'steps': 18347, 'loss/train': 1.9688720703125} 08/30/2021 16:31:55 - INFO - __main__ - Step 18349: {'lr': 0.0004850977107430959, 'samples': 3523008, 'steps': 18348, 'loss/train': 1.1184128522872925} 08/30/2021 16:31:55 - INFO - __main__ - Step 18350: {'lr': 0.000485095905889374, 'samples': 3523200, 'steps': 18349, 'loss/train': 1.152635097503662} 08/30/2021 16:31:56 - INFO - __main__ - Step 18351: {'lr': 0.00048509410092972144, 'samples': 3523392, 'steps': 18350, 'loss/train': 1.8936458826065063} 08/30/2021 16:31:58 - INFO - __main__ - Step 18352: {'lr': 0.0004850922958641392, 'samples': 3523584, 'steps': 18351, 'loss/train': 1.6338152885437012} 08/30/2021 16:31:58 - INFO - __main__ - Step 18353: {'lr': 0.0004850904906926279, 'samples': 3523776, 'steps': 18352, 'loss/train': 1.175215721130371} 08/30/2021 16:31:58 - INFO - __main__ - Step 18354: {'lr': 0.0004850886854151885, 'samples': 3523968, 'steps': 18353, 'loss/train': 1.374414086341858} 08/30/2021 16:31:59 - INFO - __main__ - Step 18355: {'lr': 0.0004850868800318218, 'samples': 3524160, 'steps': 18354, 'loss/train': 1.856572151184082} 08/30/2021 16:31:59 - INFO - __main__ - Step 18356: {'lr': 0.00048508507454252846, 'samples': 3524352, 'steps': 18355, 'loss/train': 1.1230909824371338} 08/30/2021 16:31:59 - INFO - __main__ - Step 18357: {'lr': 0.00048508326894730955, 'samples': 3524544, 'steps': 18356, 'loss/train': 2.62599515914917} 08/30/2021 16:32:01 - INFO - __main__ - Step 18358: {'lr': 0.00048508146324616566, 'samples': 3524736, 'steps': 18357, 'loss/train': 1.2977162599563599} 08/30/2021 16:32:01 - INFO - __main__ - Step 18359: {'lr': 0.0004850796574390977, 'samples': 3524928, 'steps': 18358, 'loss/train': 1.9402198791503906} 08/30/2021 16:32:02 - INFO - __main__ - Step 18360: {'lr': 0.0004850778515261065, 'samples': 3525120, 'steps': 18359, 'loss/train': 1.5444425344467163} 08/30/2021 16:32:02 - INFO - __main__ - Step 18361: {'lr': 0.0004850760455071929, 'samples': 3525312, 'steps': 18360, 'loss/train': 1.594689965248108} 08/30/2021 16:32:02 - INFO - __main__ - Step 18362: {'lr': 0.0004850742393823576, 'samples': 3525504, 'steps': 18361, 'loss/train': 0.8999673128128052} 08/30/2021 16:32:04 - INFO - __main__ - Step 18363: {'lr': 0.0004850724331516014, 'samples': 3525696, 'steps': 18362, 'loss/train': 1.3309015035629272} 08/30/2021 16:32:04 - INFO - __main__ - Step 18364: {'lr': 0.0004850706268149253, 'samples': 3525888, 'steps': 18363, 'loss/train': 1.3089945316314697} 08/30/2021 16:32:05 - INFO - __main__ - Step 18365: {'lr': 0.00048506882037233, 'samples': 3526080, 'steps': 18364, 'loss/train': 1.3521586656570435} 08/30/2021 16:32:05 - INFO - __main__ - Step 18366: {'lr': 0.0004850670138238162, 'samples': 3526272, 'steps': 18365, 'loss/train': 1.974701166152954} 08/30/2021 16:32:06 - INFO - __main__ - Step 18367: {'lr': 0.00048506520716938496, 'samples': 3526464, 'steps': 18366, 'loss/train': 1.5892881155014038} 08/30/2021 16:32:07 - INFO - __main__ - Step 18368: {'lr': 0.00048506340040903697, 'samples': 3526656, 'steps': 18367, 'loss/train': 1.944163203239441} 08/30/2021 16:32:08 - INFO - __main__ - Step 18369: {'lr': 0.00048506159354277294, 'samples': 3526848, 'steps': 18368, 'loss/train': 2.3988265991210938} 08/30/2021 16:32:08 - INFO - __main__ - Step 18370: {'lr': 0.00048505978657059385, 'samples': 3527040, 'steps': 18369, 'loss/train': 1.93350350856781} 08/30/2021 16:32:08 - INFO - __main__ - Step 18371: {'lr': 0.0004850579794925004, 'samples': 3527232, 'steps': 18370, 'loss/train': 2.4299449920654297} 08/30/2021 16:32:09 - INFO - __main__ - Step 18372: {'lr': 0.0004850561723084935, 'samples': 3527424, 'steps': 18371, 'loss/train': 1.7484010457992554} 08/30/2021 16:32:10 - INFO - __main__ - Step 18373: {'lr': 0.0004850543650185739, 'samples': 3527616, 'steps': 18372, 'loss/train': 1.9789292812347412} 08/30/2021 16:32:11 - INFO - __main__ - Step 18374: {'lr': 0.0004850525576227425, 'samples': 3527808, 'steps': 18373, 'loss/train': 1.1833218336105347} 08/30/2021 16:32:11 - INFO - __main__ - Step 18375: {'lr': 0.000485050750121, 'samples': 3528000, 'steps': 18374, 'loss/train': 1.0919058322906494} 08/30/2021 16:32:11 - INFO - __main__ - Step 18376: {'lr': 0.0004850489425133472, 'samples': 3528192, 'steps': 18375, 'loss/train': 1.805298089981079} 08/30/2021 16:32:12 - INFO - __main__ - Step 18377: {'lr': 0.000485047134799785, 'samples': 3528384, 'steps': 18376, 'loss/train': 1.5543766021728516} 08/30/2021 16:32:14 - INFO - __main__ - Step 18378: {'lr': 0.00048504532698031416, 'samples': 3528576, 'steps': 18377, 'loss/train': 1.73404061794281} 08/30/2021 16:32:14 - INFO - __main__ - Step 18379: {'lr': 0.0004850435190549356, 'samples': 3528768, 'steps': 18378, 'loss/train': 1.9069091081619263} 08/30/2021 16:32:14 - INFO - __main__ - Step 18380: {'lr': 0.00048504171102365, 'samples': 3528960, 'steps': 18379, 'loss/train': 1.5401171445846558} 08/30/2021 16:32:15 - INFO - __main__ - Step 18381: {'lr': 0.0004850399028864583, 'samples': 3529152, 'steps': 18380, 'loss/train': 0.7602036595344543} 08/30/2021 16:32:15 - INFO - __main__ - Step 18382: {'lr': 0.0004850380946433611, 'samples': 3529344, 'steps': 18381, 'loss/train': 2.0335865020751953} 08/30/2021 16:32:15 - INFO - __main__ - Step 18383: {'lr': 0.00048503628629435947, 'samples': 3529536, 'steps': 18382, 'loss/train': 1.367948055267334} 08/30/2021 16:32:17 - INFO - __main__ - Step 18384: {'lr': 0.0004850344778394541, 'samples': 3529728, 'steps': 18383, 'loss/train': 1.0850682258605957} 08/30/2021 16:32:18 - INFO - __main__ - Step 18385: {'lr': 0.0004850326692786459, 'samples': 3529920, 'steps': 18384, 'loss/train': 2.2030513286590576} 08/30/2021 16:32:18 - INFO - __main__ - Step 18386: {'lr': 0.00048503086061193546, 'samples': 3530112, 'steps': 18385, 'loss/train': 2.3353638648986816} 08/30/2021 16:32:18 - INFO - __main__ - Step 18387: {'lr': 0.0004850290518393238, 'samples': 3530304, 'steps': 18386, 'loss/train': 1.7692161798477173} 08/30/2021 16:32:19 - INFO - __main__ - Step 18388: {'lr': 0.0004850272429608117, 'samples': 3530496, 'steps': 18387, 'loss/train': 1.059675693511963} 08/30/2021 16:32:20 - INFO - __main__ - Step 18389: {'lr': 0.0004850254339764, 'samples': 3530688, 'steps': 18388, 'loss/train': 1.7607570886611938} 08/30/2021 16:32:21 - INFO - __main__ - Step 18390: {'lr': 0.00048502362488608933, 'samples': 3530880, 'steps': 18389, 'loss/train': 1.701917290687561} 08/30/2021 16:32:21 - INFO - __main__ - Step 18391: {'lr': 0.0004850218156898807, 'samples': 3531072, 'steps': 18390, 'loss/train': 1.5931764841079712} 08/30/2021 16:32:21 - INFO - __main__ - Step 18392: {'lr': 0.00048502000638777487, 'samples': 3531264, 'steps': 18391, 'loss/train': 2.0616695880889893} 08/30/2021 16:32:22 - INFO - __main__ - Step 18393: {'lr': 0.0004850181969797727, 'samples': 3531456, 'steps': 18392, 'loss/train': 0.8655185103416443} 08/30/2021 16:32:23 - INFO - __main__ - Step 18394: {'lr': 0.00048501638746587493, 'samples': 3531648, 'steps': 18393, 'loss/train': 1.868634819984436} 08/30/2021 16:32:24 - INFO - __main__ - Step 18395: {'lr': 0.0004850145778460824, 'samples': 3531840, 'steps': 18394, 'loss/train': 1.9058949947357178} 08/30/2021 16:32:24 - INFO - __main__ - Step 18396: {'lr': 0.00048501276812039585, 'samples': 3532032, 'steps': 18395, 'loss/train': 1.474753737449646} 08/30/2021 16:32:24 - INFO - __main__ - Step 18397: {'lr': 0.00048501095828881627, 'samples': 3532224, 'steps': 18396, 'loss/train': 1.768510103225708} 08/30/2021 16:32:25 - INFO - __main__ - Step 18398: {'lr': 0.00048500914835134434, 'samples': 3532416, 'steps': 18397, 'loss/train': 1.8040025234222412} 08/30/2021 16:32:25 - INFO - __main__ - Step 18399: {'lr': 0.00048500733830798094, 'samples': 3532608, 'steps': 18398, 'loss/train': 1.8621283769607544} 08/30/2021 16:32:26 - INFO - __main__ - Step 18400: {'lr': 0.00048500552815872687, 'samples': 3532800, 'steps': 18399, 'loss/train': 1.68860924243927} 08/30/2021 16:32:27 - INFO - __main__ - Step 18401: {'lr': 0.0004850037179035829, 'samples': 3532992, 'steps': 18400, 'loss/train': 2.0445046424865723} 08/30/2021 16:32:27 - INFO - __main__ - Step 18402: {'lr': 0.00048500190754254994, 'samples': 3533184, 'steps': 18401, 'loss/train': 1.752744197845459} 08/30/2021 16:32:28 - INFO - __main__ - Step 18403: {'lr': 0.00048500009707562865, 'samples': 3533376, 'steps': 18402, 'loss/train': 1.315450668334961} 08/30/2021 16:32:28 - INFO - __main__ - Step 18404: {'lr': 0.00048499828650281994, 'samples': 3533568, 'steps': 18403, 'loss/train': 0.9854258894920349} 08/30/2021 16:32:30 - INFO - __main__ - Step 18405: {'lr': 0.00048499647582412475, 'samples': 3533760, 'steps': 18404, 'loss/train': 2.5694668292999268} 08/30/2021 16:32:30 - INFO - __main__ - Step 18406: {'lr': 0.0004849946650395437, 'samples': 3533952, 'steps': 18405, 'loss/train': 1.2151046991348267} 08/30/2021 16:32:30 - INFO - __main__ - Step 18407: {'lr': 0.0004849928541490777, 'samples': 3534144, 'steps': 18406, 'loss/train': 0.6300547122955322} 08/30/2021 16:32:31 - INFO - __main__ - Step 18408: {'lr': 0.0004849910431527275, 'samples': 3534336, 'steps': 18407, 'loss/train': 1.6237766742706299} 08/30/2021 16:32:31 - INFO - __main__ - Step 18409: {'lr': 0.000484989232050494, 'samples': 3534528, 'steps': 18408, 'loss/train': 1.6840767860412598} 08/30/2021 16:32:33 - INFO - __main__ - Step 18410: {'lr': 0.00048498742084237796, 'samples': 3534720, 'steps': 18409, 'loss/train': 1.428397536277771} 08/30/2021 16:32:34 - INFO - __main__ - Step 18411: {'lr': 0.00048498560952838025, 'samples': 3534912, 'steps': 18410, 'loss/train': 1.7967861890792847} 08/30/2021 16:32:34 - INFO - __main__ - Step 18412: {'lr': 0.00048498379810850157, 'samples': 3535104, 'steps': 18411, 'loss/train': 1.5502450466156006} 08/30/2021 16:32:34 - INFO - __main__ - Step 18413: {'lr': 0.0004849819865827429, 'samples': 3535296, 'steps': 18412, 'loss/train': 1.7416106462478638} 08/30/2021 16:32:35 - INFO - __main__ - Step 18414: {'lr': 0.0004849801749511049, 'samples': 3535488, 'steps': 18413, 'loss/train': 2.118992805480957} 08/30/2021 16:32:36 - INFO - __main__ - Step 18415: {'lr': 0.00048497836321358855, 'samples': 3535680, 'steps': 18414, 'loss/train': 1.533248782157898} 08/30/2021 16:32:37 - INFO - __main__ - Step 18416: {'lr': 0.00048497655137019454, 'samples': 3535872, 'steps': 18415, 'loss/train': 1.6962758302688599} 08/30/2021 16:32:37 - INFO - __main__ - Step 18417: {'lr': 0.0004849747394209237, 'samples': 3536064, 'steps': 18416, 'loss/train': 1.527657151222229} 08/30/2021 16:32:37 - INFO - __main__ - Step 18418: {'lr': 0.00048497292736577685, 'samples': 3536256, 'steps': 18417, 'loss/train': 1.5346958637237549} 08/30/2021 16:32:38 - INFO - __main__ - Step 18419: {'lr': 0.0004849711152047549, 'samples': 3536448, 'steps': 18418, 'loss/train': 1.7111904621124268} 08/30/2021 16:32:38 - INFO - __main__ - Step 18420: {'lr': 0.0004849693029378585, 'samples': 3536640, 'steps': 18419, 'loss/train': 1.6931809186935425} 08/30/2021 16:32:39 - INFO - __main__ - Step 18421: {'lr': 0.0004849674905650886, 'samples': 3536832, 'steps': 18420, 'loss/train': 1.9758563041687012} 08/30/2021 16:32:40 - INFO - __main__ - Step 18422: {'lr': 0.000484965678086446, 'samples': 3537024, 'steps': 18421, 'loss/train': 1.5684478282928467} 08/30/2021 16:32:40 - INFO - __main__ - Step 18423: {'lr': 0.0004849638655019315, 'samples': 3537216, 'steps': 18422, 'loss/train': 1.285486102104187} 08/30/2021 16:32:41 - INFO - __main__ - Step 18424: {'lr': 0.0004849620528115458, 'samples': 3537408, 'steps': 18423, 'loss/train': 1.4267280101776123} 08/30/2021 16:32:41 - INFO - __main__ - Step 18425: {'lr': 0.0004849602400152899, 'samples': 3537600, 'steps': 18424, 'loss/train': 1.044335126876831} 08/30/2021 16:32:42 - INFO - __main__ - Step 18426: {'lr': 0.0004849584271131646, 'samples': 3537792, 'steps': 18425, 'loss/train': 1.9281814098358154} 08/30/2021 16:32:43 - INFO - __main__ - Step 18427: {'lr': 0.00048495661410517056, 'samples': 3537984, 'steps': 18426, 'loss/train': 1.8135710954666138} 08/30/2021 16:32:43 - INFO - __main__ - Step 18428: {'lr': 0.0004849548009913087, 'samples': 3538176, 'steps': 18427, 'loss/train': 3.7530477046966553} 08/30/2021 16:32:44 - INFO - __main__ - Step 18429: {'lr': 0.00048495298777157994, 'samples': 3538368, 'steps': 18428, 'loss/train': 1.0768924951553345} 08/30/2021 16:32:44 - INFO - __main__ - Step 18430: {'lr': 0.0004849511744459849, 'samples': 3538560, 'steps': 18429, 'loss/train': 1.7873797416687012} 08/30/2021 16:32:45 - INFO - __main__ - Step 18431: {'lr': 0.00048494936101452446, 'samples': 3538752, 'steps': 18430, 'loss/train': 1.1974409818649292} 08/30/2021 16:32:46 - INFO - __main__ - Step 18432: {'lr': 0.00048494754747719954, 'samples': 3538944, 'steps': 18431, 'loss/train': 2.0334620475769043} 08/30/2021 16:32:46 - INFO - __main__ - Step 18433: {'lr': 0.00048494573383401084, 'samples': 3539136, 'steps': 18432, 'loss/train': 1.6517343521118164} 08/30/2021 16:32:47 - INFO - __main__ - Step 18434: {'lr': 0.0004849439200849592, 'samples': 3539328, 'steps': 18433, 'loss/train': 1.7558435201644897} 08/30/2021 16:32:47 - INFO - __main__ - Step 18435: {'lr': 0.0004849421062300455, 'samples': 3539520, 'steps': 18434, 'loss/train': 1.7587658166885376} 08/30/2021 16:32:48 - INFO - __main__ - Step 18436: {'lr': 0.0004849402922692705, 'samples': 3539712, 'steps': 18435, 'loss/train': 2.0340306758880615} 08/30/2021 16:32:49 - INFO - __main__ - Step 18437: {'lr': 0.000484938478202635, 'samples': 3539904, 'steps': 18436, 'loss/train': 1.9905076026916504} 08/30/2021 16:32:49 - INFO - __main__ - Step 18438: {'lr': 0.0004849366640301399, 'samples': 3540096, 'steps': 18437, 'loss/train': 1.4739770889282227} 08/30/2021 16:32:50 - INFO - __main__ - Step 18439: {'lr': 0.00048493484975178593, 'samples': 3540288, 'steps': 18438, 'loss/train': 1.9535123109817505} 08/30/2021 16:32:50 - INFO - __main__ - Step 18440: {'lr': 0.00048493303536757394, 'samples': 3540480, 'steps': 18439, 'loss/train': 1.733303427696228} 08/30/2021 16:32:52 - INFO - __main__ - Step 18441: {'lr': 0.00048493122087750473, 'samples': 3540672, 'steps': 18440, 'loss/train': 1.183138370513916} 08/30/2021 16:32:52 - INFO - __main__ - Step 18442: {'lr': 0.0004849294062815792, 'samples': 3540864, 'steps': 18441, 'loss/train': 1.2568312883377075} 08/30/2021 16:32:52 - INFO - __main__ - Step 18443: {'lr': 0.000484927591579798, 'samples': 3541056, 'steps': 18442, 'loss/train': 1.481009840965271} 08/30/2021 16:32:53 - INFO - __main__ - Step 18444: {'lr': 0.0004849257767721622, 'samples': 3541248, 'steps': 18443, 'loss/train': 1.2963892221450806} 08/30/2021 16:32:53 - INFO - __main__ - Step 18445: {'lr': 0.00048492396185867236, 'samples': 3541440, 'steps': 18444, 'loss/train': 1.720694899559021} 08/30/2021 16:32:53 - INFO - __main__ - Step 18446: {'lr': 0.0004849221468393294, 'samples': 3541632, 'steps': 18445, 'loss/train': 1.6941791772842407} 08/30/2021 16:32:55 - INFO - __main__ - Step 18447: {'lr': 0.00048492033171413425, 'samples': 3541824, 'steps': 18446, 'loss/train': 1.7716199159622192} 08/30/2021 16:32:55 - INFO - __main__ - Step 18448: {'lr': 0.00048491851648308756, 'samples': 3542016, 'steps': 18447, 'loss/train': 1.8997448682785034} 08/30/2021 16:32:56 - INFO - __main__ - Step 18449: {'lr': 0.00048491670114619026, 'samples': 3542208, 'steps': 18448, 'loss/train': 0.9838755130767822} 08/30/2021 16:32:56 - INFO - __main__ - Step 18450: {'lr': 0.000484914885703443, 'samples': 3542400, 'steps': 18449, 'loss/train': 1.8256545066833496} 08/30/2021 16:32:56 - INFO - __main__ - Step 18451: {'lr': 0.00048491307015484684, 'samples': 3542592, 'steps': 18450, 'loss/train': 2.717716693878174} 08/30/2021 16:32:58 - INFO - __main__ - Step 18452: {'lr': 0.0004849112545004024, 'samples': 3542784, 'steps': 18451, 'loss/train': 1.6457176208496094} 08/30/2021 16:32:59 - INFO - __main__ - Step 18453: {'lr': 0.00048490943874011054, 'samples': 3542976, 'steps': 18452, 'loss/train': 1.8555002212524414} 08/30/2021 16:32:59 - INFO - __main__ - Step 18454: {'lr': 0.00048490762287397215, 'samples': 3543168, 'steps': 18453, 'loss/train': 0.8818188309669495} 08/30/2021 16:32:59 - INFO - __main__ - Step 18455: {'lr': 0.00048490580690198804, 'samples': 3543360, 'steps': 18454, 'loss/train': 1.917466163635254} 08/30/2021 16:33:00 - INFO - __main__ - Step 18456: {'lr': 0.000484903990824159, 'samples': 3543552, 'steps': 18455, 'loss/train': 1.6682443618774414} 08/30/2021 16:33:01 - INFO - __main__ - Step 18457: {'lr': 0.0004849021746404859, 'samples': 3543744, 'steps': 18456, 'loss/train': 1.5969135761260986} 08/30/2021 16:33:02 - INFO - __main__ - Step 18458: {'lr': 0.00048490035835096936, 'samples': 3543936, 'steps': 18457, 'loss/train': 1.598833441734314} 08/30/2021 16:33:02 - INFO - __main__ - Step 18459: {'lr': 0.0004848985419556104, 'samples': 3544128, 'steps': 18458, 'loss/train': 1.4627039432525635} 08/30/2021 16:33:03 - INFO - __main__ - Step 18460: {'lr': 0.0004848967254544099, 'samples': 3544320, 'steps': 18459, 'loss/train': 1.282549500465393} 08/30/2021 16:33:03 - INFO - __main__ - Step 18461: {'lr': 0.00048489490884736844, 'samples': 3544512, 'steps': 18460, 'loss/train': 1.6859853267669678} 08/30/2021 16:33:03 - INFO - __main__ - Step 18462: {'lr': 0.00048489309213448696, 'samples': 3544704, 'steps': 18461, 'loss/train': 0.12266451865434647} 08/30/2021 16:33:05 - INFO - __main__ - Step 18463: {'lr': 0.00048489127531576627, 'samples': 3544896, 'steps': 18462, 'loss/train': 2.86110258102417} 08/30/2021 16:33:06 - INFO - __main__ - Step 18464: {'lr': 0.0004848894583912072, 'samples': 3545088, 'steps': 18463, 'loss/train': 1.9362525939941406} 08/30/2021 16:33:06 - INFO - __main__ - Step 18465: {'lr': 0.00048488764136081063, 'samples': 3545280, 'steps': 18464, 'loss/train': 1.3914740085601807} 08/30/2021 16:33:07 - INFO - __main__ - Step 18466: {'lr': 0.00048488582422457726, 'samples': 3545472, 'steps': 18465, 'loss/train': 1.8300514221191406} 08/30/2021 16:33:07 - INFO - __main__ - Step 18467: {'lr': 0.000484884006982508, 'samples': 3545664, 'steps': 18466, 'loss/train': 1.2591675519943237} 08/30/2021 16:33:09 - INFO - __main__ - Step 18468: {'lr': 0.0004848821896346036, 'samples': 3545856, 'steps': 18467, 'loss/train': 1.572219967842102} 08/30/2021 16:33:09 - INFO - __main__ - Step 18469: {'lr': 0.0004848803721808649, 'samples': 3546048, 'steps': 18468, 'loss/train': 1.520451307296753} 08/30/2021 16:33:10 - INFO - __main__ - Step 18470: {'lr': 0.0004848785546212927, 'samples': 3546240, 'steps': 18469, 'loss/train': 1.6013100147247314} 08/30/2021 16:33:10 - INFO - __main__ - Step 18471: {'lr': 0.00048487673695588794, 'samples': 3546432, 'steps': 18470, 'loss/train': 0.8847469091415405} 08/30/2021 16:33:10 - INFO - __main__ - Step 18472: {'lr': 0.00048487491918465135, 'samples': 3546624, 'steps': 18471, 'loss/train': 1.629996418952942} 08/30/2021 16:33:11 - INFO - __main__ - Step 18473: {'lr': 0.00048487310130758366, 'samples': 3546816, 'steps': 18472, 'loss/train': 1.4766883850097656} 08/30/2021 16:33:12 - INFO - __main__ - Step 18474: {'lr': 0.00048487128332468576, 'samples': 3547008, 'steps': 18473, 'loss/train': 1.941003680229187} 08/30/2021 16:33:13 - INFO - __main__ - Step 18475: {'lr': 0.00048486946523595856, 'samples': 3547200, 'steps': 18474, 'loss/train': 1.760926604270935} 08/30/2021 16:33:13 - INFO - __main__ - Step 18476: {'lr': 0.00048486764704140276, 'samples': 3547392, 'steps': 18475, 'loss/train': 1.8866465091705322} 08/30/2021 16:33:13 - INFO - __main__ - Step 18477: {'lr': 0.00048486582874101924, 'samples': 3547584, 'steps': 18476, 'loss/train': 1.8096379041671753} 08/30/2021 16:33:14 - INFO - __main__ - Step 18478: {'lr': 0.0004848640103348088, 'samples': 3547776, 'steps': 18477, 'loss/train': 1.8322175741195679} 08/30/2021 16:33:15 - INFO - __main__ - Step 18479: {'lr': 0.00048486219182277226, 'samples': 3547968, 'steps': 18478, 'loss/train': 1.4215279817581177} 08/30/2021 16:33:15 - INFO - __main__ - Step 18480: {'lr': 0.00048486037320491043, 'samples': 3548160, 'steps': 18479, 'loss/train': 2.114464044570923} 08/30/2021 16:33:16 - INFO - __main__ - Step 18481: {'lr': 0.0004848585544812242, 'samples': 3548352, 'steps': 18480, 'loss/train': 2.0277700424194336} 08/30/2021 16:33:16 - INFO - __main__ - Step 18482: {'lr': 0.0004848567356517143, 'samples': 3548544, 'steps': 18481, 'loss/train': 1.935502290725708} 08/30/2021 16:33:17 - INFO - __main__ - Step 18483: {'lr': 0.00048485491671638146, 'samples': 3548736, 'steps': 18482, 'loss/train': 1.707394003868103} 08/30/2021 16:33:18 - INFO - __main__ - Step 18484: {'lr': 0.0004848530976752268, 'samples': 3548928, 'steps': 18483, 'loss/train': 1.799896001815796} 08/30/2021 16:33:19 - INFO - __main__ - Step 18485: {'lr': 0.0004848512785282508, 'samples': 3549120, 'steps': 18484, 'loss/train': 2.754084348678589} 08/30/2021 16:33:19 - INFO - __main__ - Step 18486: {'lr': 0.00048484945927545456, 'samples': 3549312, 'steps': 18485, 'loss/train': 1.213364601135254} 08/30/2021 16:33:19 - INFO - __main__ - Step 18487: {'lr': 0.0004848476399168387, 'samples': 3549504, 'steps': 18486, 'loss/train': 1.6225429773330688} 08/30/2021 16:33:20 - INFO - __main__ - Step 18488: {'lr': 0.0004848458204524042, 'samples': 3549696, 'steps': 18487, 'loss/train': 2.1874027252197266} 08/30/2021 16:33:21 - INFO - __main__ - Step 18489: {'lr': 0.00048484400088215173, 'samples': 3549888, 'steps': 18488, 'loss/train': 1.7116848230361938} 08/30/2021 16:33:22 - INFO - __main__ - Step 18490: {'lr': 0.0004848421812060821, 'samples': 3550080, 'steps': 18489, 'loss/train': 1.7499696016311646} 08/30/2021 16:33:22 - INFO - __main__ - Step 18491: {'lr': 0.0004848403614241964, 'samples': 3550272, 'steps': 18490, 'loss/train': 0.8672402501106262} 08/30/2021 16:33:23 - INFO - __main__ - Step 18492: {'lr': 0.00048483854153649514, 'samples': 3550464, 'steps': 18491, 'loss/train': 1.9149320125579834} 08/30/2021 16:33:23 - INFO - __main__ - Step 18493: {'lr': 0.0004848367215429793, 'samples': 3550656, 'steps': 18492, 'loss/train': 1.3062007427215576} 08/30/2021 16:33:23 - INFO - __main__ - Step 18494: {'lr': 0.0004848349014436496, 'samples': 3550848, 'steps': 18493, 'loss/train': 1.0269335508346558} 08/30/2021 16:33:24 - INFO - __main__ - Step 18495: {'lr': 0.00048483308123850697, 'samples': 3551040, 'steps': 18494, 'loss/train': 0.1711260974407196} 08/30/2021 16:33:25 - INFO - __main__ - Step 18496: {'lr': 0.00048483126092755215, 'samples': 3551232, 'steps': 18495, 'loss/train': 0.07490824162960052} 08/30/2021 16:33:26 - INFO - __main__ - Step 18497: {'lr': 0.000484829440510786, 'samples': 3551424, 'steps': 18496, 'loss/train': 0.0846533253788948} 08/30/2021 16:33:26 - INFO - __main__ - Step 18498: {'lr': 0.0004848276199882093, 'samples': 3551616, 'steps': 18497, 'loss/train': 0.7802138328552246} 08/30/2021 16:33:27 - INFO - __main__ - Step 18499: {'lr': 0.0004848257993598229, 'samples': 3551808, 'steps': 18498, 'loss/train': 1.7126972675323486} 08/30/2021 16:33:27 - INFO - __main__ - Step 18500: {'lr': 0.00048482397862562764, 'samples': 3552000, 'steps': 18499, 'loss/train': 4.151735782623291} 08/30/2021 16:33:29 - INFO - __main__ - Step 18501: {'lr': 0.00048482215778562434, 'samples': 3552192, 'steps': 18500, 'loss/train': 1.5678753852844238} 08/30/2021 16:33:29 - INFO - __main__ - Step 18502: {'lr': 0.00048482033683981376, 'samples': 3552384, 'steps': 18501, 'loss/train': 0.20393653213977814} 08/30/2021 16:33:30 - INFO - __main__ - Step 18503: {'lr': 0.0004848185157881968, 'samples': 3552576, 'steps': 18502, 'loss/train': 1.5224156379699707} 08/30/2021 16:33:30 - INFO - __main__ - Step 18504: {'lr': 0.0004848166946307742, 'samples': 3552768, 'steps': 18503, 'loss/train': 1.5995322465896606} 08/30/2021 16:33:31 - INFO - __main__ - Step 18505: {'lr': 0.0004848148733675468, 'samples': 3552960, 'steps': 18504, 'loss/train': 1.0265933275222778} 08/30/2021 16:33:31 - INFO - __main__ - Step 18506: {'lr': 0.0004848130519985155, 'samples': 3553152, 'steps': 18505, 'loss/train': 1.430309534072876} 08/30/2021 16:33:31 - INFO - __main__ - Step 18507: {'lr': 0.000484811230523681, 'samples': 3553344, 'steps': 18506, 'loss/train': 1.8822970390319824} 08/30/2021 16:33:33 - INFO - __main__ - Step 18508: {'lr': 0.00048480940894304425, 'samples': 3553536, 'steps': 18507, 'loss/train': 1.445253610610962} 08/30/2021 16:33:33 - INFO - __main__ - Step 18509: {'lr': 0.000484807587256606, 'samples': 3553728, 'steps': 18508, 'loss/train': 1.4174604415893555} 08/30/2021 16:33:34 - INFO - __main__ - Step 18510: {'lr': 0.00048480576546436707, 'samples': 3553920, 'steps': 18509, 'loss/train': 1.7771098613739014} 08/30/2021 16:33:34 - INFO - __main__ - Step 18511: {'lr': 0.0004848039435663282, 'samples': 3554112, 'steps': 18510, 'loss/train': 1.7104212045669556} 08/30/2021 16:33:34 - INFO - __main__ - Step 18512: {'lr': 0.0004848021215624904, 'samples': 3554304, 'steps': 18511, 'loss/train': 1.7735743522644043} 08/30/2021 16:33:36 - INFO - __main__ - Step 18513: {'lr': 0.0004848002994528543, 'samples': 3554496, 'steps': 18512, 'loss/train': 2.0425238609313965} 08/30/2021 16:33:36 - INFO - __main__ - Step 18514: {'lr': 0.0004847984772374209, 'samples': 3554688, 'steps': 18513, 'loss/train': 0.3305189907550812} 08/30/2021 16:33:37 - INFO - __main__ - Step 18515: {'lr': 0.0004847966549161909, 'samples': 3554880, 'steps': 18514, 'loss/train': 1.1372885704040527} 08/30/2021 16:33:37 - INFO - __main__ - Step 18516: {'lr': 0.0004847948324891651, 'samples': 3555072, 'steps': 18515, 'loss/train': 1.6787761449813843} 08/30/2021 16:33:37 - INFO - __main__ - Step 18517: {'lr': 0.00048479300995634447, 'samples': 3555264, 'steps': 18516, 'loss/train': 1.302175521850586} 08/30/2021 16:33:39 - INFO - __main__ - Step 18518: {'lr': 0.0004847911873177296, 'samples': 3555456, 'steps': 18517, 'loss/train': 2.0490682125091553} 08/30/2021 16:33:40 - INFO - __main__ - Step 18519: {'lr': 0.0004847893645733216, 'samples': 3555648, 'steps': 18518, 'loss/train': 2.500790596008301} 08/30/2021 16:33:40 - INFO - __main__ - Step 18520: {'lr': 0.000484787541723121, 'samples': 3555840, 'steps': 18519, 'loss/train': 0.8049459457397461} 08/30/2021 16:33:40 - INFO - __main__ - Step 18521: {'lr': 0.0004847857187671288, 'samples': 3556032, 'steps': 18520, 'loss/train': 2.2276804447174072} 08/30/2021 16:33:41 - INFO - __main__ - Step 18522: {'lr': 0.00048478389570534575, 'samples': 3556224, 'steps': 18521, 'loss/train': 1.3165028095245361} 08/30/2021 16:33:42 - INFO - __main__ - Step 18523: {'lr': 0.0004847820725377728, 'samples': 3556416, 'steps': 18522, 'loss/train': 1.5506622791290283} 08/30/2021 16:33:43 - INFO - __main__ - Step 18524: {'lr': 0.0004847802492644106, 'samples': 3556608, 'steps': 18523, 'loss/train': 1.2318246364593506} 08/30/2021 16:33:43 - INFO - __main__ - Step 18525: {'lr': 0.00048477842588526, 'samples': 3556800, 'steps': 18524, 'loss/train': 1.4588223695755005} 08/30/2021 16:33:43 - INFO - __main__ - Step 18526: {'lr': 0.000484776602400322, 'samples': 3556992, 'steps': 18525, 'loss/train': 1.276929259300232} 08/30/2021 16:33:44 - INFO - __main__ - Step 18527: {'lr': 0.00048477477880959715, 'samples': 3557184, 'steps': 18526, 'loss/train': 1.384444236755371} 08/30/2021 16:33:45 - INFO - __main__ - Step 18528: {'lr': 0.00048477295511308645, 'samples': 3557376, 'steps': 18527, 'loss/train': 1.8755440711975098} 08/30/2021 16:33:46 - INFO - __main__ - Step 18529: {'lr': 0.0004847711313107907, 'samples': 3557568, 'steps': 18528, 'loss/train': 2.0067262649536133} 08/30/2021 16:33:46 - INFO - __main__ - Step 18530: {'lr': 0.0004847693074027106, 'samples': 3557760, 'steps': 18529, 'loss/train': 1.3764686584472656} 08/30/2021 16:33:46 - INFO - __main__ - Step 18531: {'lr': 0.0004847674833888472, 'samples': 3557952, 'steps': 18530, 'loss/train': 1.5434719324111938} 08/30/2021 16:33:47 - INFO - __main__ - Step 18532: {'lr': 0.0004847656592692012, 'samples': 3558144, 'steps': 18531, 'loss/train': 1.7961565256118774} 08/30/2021 16:33:47 - INFO - __main__ - Step 18533: {'lr': 0.00048476383504377337, 'samples': 3558336, 'steps': 18532, 'loss/train': 0.9700822234153748} 08/30/2021 16:33:49 - INFO - __main__ - Step 18534: {'lr': 0.00048476201071256453, 'samples': 3558528, 'steps': 18533, 'loss/train': 1.6476198434829712} 08/30/2021 16:33:49 - INFO - __main__ - Step 18535: {'lr': 0.0004847601862755756, 'samples': 3558720, 'steps': 18534, 'loss/train': 1.9694432020187378} 08/30/2021 16:33:49 - INFO - __main__ - Step 18536: {'lr': 0.0004847583617328074, 'samples': 3558912, 'steps': 18535, 'loss/train': 2.1525583267211914} 08/30/2021 16:33:50 - INFO - __main__ - Step 18537: {'lr': 0.00048475653708426067, 'samples': 3559104, 'steps': 18536, 'loss/train': 1.294746994972229} 08/30/2021 16:33:50 - INFO - __main__ - Step 18538: {'lr': 0.00048475471232993625, 'samples': 3559296, 'steps': 18537, 'loss/train': 1.3839820623397827} 08/30/2021 16:33:52 - INFO - __main__ - Step 18539: {'lr': 0.000484752887469835, 'samples': 3559488, 'steps': 18538, 'loss/train': 0.8167545795440674} 08/30/2021 16:33:52 - INFO - __main__ - Step 18540: {'lr': 0.0004847510625039577, 'samples': 3559680, 'steps': 18539, 'loss/train': 2.311332941055298} 08/30/2021 16:33:52 - INFO - __main__ - Step 18541: {'lr': 0.00048474923743230513, 'samples': 3559872, 'steps': 18540, 'loss/train': 1.7084465026855469} 08/30/2021 16:33:53 - INFO - __main__ - Step 18542: {'lr': 0.0004847474122548783, 'samples': 3560064, 'steps': 18541, 'loss/train': 1.2706105709075928} 08/30/2021 16:33:53 - INFO - __main__ - Step 18543: {'lr': 0.00048474558697167783, 'samples': 3560256, 'steps': 18542, 'loss/train': 1.7960759401321411} 08/30/2021 16:33:54 - INFO - __main__ - Step 18544: {'lr': 0.0004847437615827046, 'samples': 3560448, 'steps': 18543, 'loss/train': 1.3301351070404053} 08/30/2021 16:33:55 - INFO - __main__ - Step 18545: {'lr': 0.0004847419360879596, 'samples': 3560640, 'steps': 18544, 'loss/train': 1.4916123151779175} 08/30/2021 16:33:55 - INFO - __main__ - Step 18546: {'lr': 0.00048474011048744336, 'samples': 3560832, 'steps': 18545, 'loss/train': 1.7456555366516113} 08/30/2021 16:33:56 - INFO - __main__ - Step 18547: {'lr': 0.0004847382847811569, 'samples': 3561024, 'steps': 18546, 'loss/train': 1.4895341396331787} 08/30/2021 16:33:56 - INFO - __main__ - Step 18548: {'lr': 0.00048473645896910094, 'samples': 3561216, 'steps': 18547, 'loss/train': 2.0263867378234863} 08/30/2021 16:33:58 - INFO - __main__ - Step 18549: {'lr': 0.0004847346330512764, 'samples': 3561408, 'steps': 18548, 'loss/train': 1.640236496925354} 08/30/2021 16:33:58 - INFO - __main__ - Step 18550: {'lr': 0.0004847328070276841, 'samples': 3561600, 'steps': 18549, 'loss/train': 1.829225778579712} 08/30/2021 16:33:58 - INFO - __main__ - Step 18551: {'lr': 0.00048473098089832475, 'samples': 3561792, 'steps': 18550, 'loss/train': 1.2299416065216064} 08/30/2021 16:33:59 - INFO - __main__ - Step 18552: {'lr': 0.0004847291546631992, 'samples': 3561984, 'steps': 18551, 'loss/train': 0.17121967673301697} 08/30/2021 16:33:59 - INFO - __main__ - Step 18553: {'lr': 0.0004847273283223084, 'samples': 3562176, 'steps': 18552, 'loss/train': 1.252171277999878} 08/30/2021 16:34:01 - INFO - __main__ - Step 18554: {'lr': 0.0004847255018756531, 'samples': 3562368, 'steps': 18553, 'loss/train': 1.419908046722412} 08/30/2021 16:34:01 - INFO - __main__ - Step 18555: {'lr': 0.0004847236753232341, 'samples': 3562560, 'steps': 18554, 'loss/train': 1.4968973398208618} 08/30/2021 16:34:01 - INFO - __main__ - Step 18556: {'lr': 0.0004847218486650522, 'samples': 3562752, 'steps': 18555, 'loss/train': 2.253539562225342} 08/30/2021 16:34:02 - INFO - __main__ - Step 18557: {'lr': 0.00048472002190110827, 'samples': 3562944, 'steps': 18556, 'loss/train': 1.9014835357666016} 08/30/2021 16:34:02 - INFO - __main__ - Step 18558: {'lr': 0.0004847181950314031, 'samples': 3563136, 'steps': 18557, 'loss/train': 1.7548178434371948} 08/30/2021 16:34:04 - INFO - __main__ - Step 18559: {'lr': 0.00048471636805593756, 'samples': 3563328, 'steps': 18558, 'loss/train': 1.438714861869812} 08/30/2021 16:34:04 - INFO - __main__ - Step 18560: {'lr': 0.0004847145409747125, 'samples': 3563520, 'steps': 18559, 'loss/train': 1.4307847023010254} 08/30/2021 16:34:04 - INFO - __main__ - Step 18561: {'lr': 0.00048471271378772857, 'samples': 3563712, 'steps': 18560, 'loss/train': 1.4135974645614624} 08/30/2021 16:34:05 - INFO - __main__ - Step 18562: {'lr': 0.00048471088649498675, 'samples': 3563904, 'steps': 18561, 'loss/train': 1.8708280324935913} 08/30/2021 16:34:05 - INFO - __main__ - Step 18563: {'lr': 0.0004847090590964879, 'samples': 3564096, 'steps': 18562, 'loss/train': 2.121454954147339} 08/30/2021 16:34:07 - INFO - __main__ - Step 18564: {'lr': 0.00048470723159223266, 'samples': 3564288, 'steps': 18563, 'loss/train': 1.6470462083816528} 08/30/2021 16:34:07 - INFO - __main__ - Step 18565: {'lr': 0.00048470540398222207, 'samples': 3564480, 'steps': 18564, 'loss/train': 2.0197346210479736} 08/30/2021 16:34:07 - INFO - __main__ - Step 18566: {'lr': 0.00048470357626645676, 'samples': 3564672, 'steps': 18565, 'loss/train': 1.9334089756011963} 08/30/2021 16:34:08 - INFO - __main__ - Step 18567: {'lr': 0.0004847017484449377, 'samples': 3564864, 'steps': 18566, 'loss/train': 1.6592752933502197} 08/30/2021 16:34:08 - INFO - __main__ - Step 18568: {'lr': 0.0004846999205176657, 'samples': 3565056, 'steps': 18567, 'loss/train': 1.9945423603057861} 08/30/2021 16:34:10 - INFO - __main__ - Step 18569: {'lr': 0.00048469809248464135, 'samples': 3565248, 'steps': 18568, 'loss/train': 1.9166946411132812} 08/30/2021 16:34:11 - INFO - __main__ - Step 18570: {'lr': 0.0004846962643458658, 'samples': 3565440, 'steps': 18569, 'loss/train': 1.3833893537521362} 08/30/2021 16:34:11 - INFO - __main__ - Step 18571: {'lr': 0.00048469443610133975, 'samples': 3565632, 'steps': 18570, 'loss/train': 1.9449726343154907} 08/30/2021 16:34:12 - INFO - __main__ - Step 18572: {'lr': 0.00048469260775106394, 'samples': 3565824, 'steps': 18571, 'loss/train': 0.8559990525245667} 08/30/2021 16:34:12 - INFO - __main__ - Step 18573: {'lr': 0.0004846907792950393, 'samples': 3566016, 'steps': 18572, 'loss/train': 1.033095121383667} 08/30/2021 16:34:12 - INFO - __main__ - Step 18574: {'lr': 0.00048468895073326663, 'samples': 3566208, 'steps': 18573, 'loss/train': 1.4956058263778687} 08/30/2021 16:34:14 - INFO - __main__ - Step 18575: {'lr': 0.0004846871220657467, 'samples': 3566400, 'steps': 18574, 'loss/train': 1.2601957321166992} 08/30/2021 16:34:14 - INFO - __main__ - Step 18576: {'lr': 0.0004846852932924804, 'samples': 3566592, 'steps': 18575, 'loss/train': 1.1903382539749146} 08/30/2021 16:34:15 - INFO - __main__ - Step 18577: {'lr': 0.00048468346441346853, 'samples': 3566784, 'steps': 18576, 'loss/train': 1.7406201362609863} 08/30/2021 16:34:15 - INFO - __main__ - Step 18578: {'lr': 0.0004846816354287119, 'samples': 3566976, 'steps': 18577, 'loss/train': 1.6070871353149414} 08/30/2021 16:34:15 - INFO - __main__ - Step 18579: {'lr': 0.0004846798063382114, 'samples': 3567168, 'steps': 18578, 'loss/train': 1.9260528087615967} 08/30/2021 16:34:17 - INFO - __main__ - Step 18580: {'lr': 0.0004846779771419677, 'samples': 3567360, 'steps': 18579, 'loss/train': 1.7920345067977905} 08/30/2021 16:34:17 - INFO - __main__ - Step 18581: {'lr': 0.0004846761478399818, 'samples': 3567552, 'steps': 18580, 'loss/train': 1.483244776725769} 08/30/2021 16:34:18 - INFO - __main__ - Step 18582: {'lr': 0.0004846743184322544, 'samples': 3567744, 'steps': 18581, 'loss/train': 1.7939437627792358} 08/30/2021 16:34:18 - INFO - __main__ - Step 18583: {'lr': 0.00048467248891878644, 'samples': 3567936, 'steps': 18582, 'loss/train': 1.690280795097351} 08/30/2021 16:34:18 - INFO - __main__ - Step 18584: {'lr': 0.00048467065929957867, 'samples': 3568128, 'steps': 18583, 'loss/train': 1.767741084098816} 08/30/2021 16:34:20 - INFO - __main__ - Step 18585: {'lr': 0.00048466882957463186, 'samples': 3568320, 'steps': 18584, 'loss/train': 0.10865940153598785} 08/30/2021 16:34:21 - INFO - __main__ - Step 18586: {'lr': 0.0004846669997439469, 'samples': 3568512, 'steps': 18585, 'loss/train': 1.2697912454605103} 08/30/2021 16:34:21 - INFO - __main__ - Step 18587: {'lr': 0.0004846651698075246, 'samples': 3568704, 'steps': 18586, 'loss/train': 1.837859869003296} 08/30/2021 16:34:22 - INFO - __main__ - Step 18588: {'lr': 0.00048466333976536594, 'samples': 3568896, 'steps': 18587, 'loss/train': 1.3561391830444336} 08/30/2021 16:34:22 - INFO - __main__ - Step 18589: {'lr': 0.0004846615096174715, 'samples': 3569088, 'steps': 18588, 'loss/train': 1.76717209815979} 08/30/2021 16:34:22 - INFO - __main__ - Step 18590: {'lr': 0.00048465967936384217, 'samples': 3569280, 'steps': 18589, 'loss/train': 1.7219301462173462} 08/30/2021 16:34:23 - INFO - __main__ - Step 18591: {'lr': 0.00048465784900447885, 'samples': 3569472, 'steps': 18590, 'loss/train': 5.92577600479126} 08/30/2021 16:34:24 - INFO - __main__ - Step 18592: {'lr': 0.00048465601853938224, 'samples': 3569664, 'steps': 18591, 'loss/train': 5.849154472351074} 08/30/2021 16:34:25 - INFO - __main__ - Step 18593: {'lr': 0.0004846541879685533, 'samples': 3569856, 'steps': 18592, 'loss/train': 1.7809295654296875} 08/30/2021 16:34:25 - INFO - __main__ - Step 18594: {'lr': 0.0004846523572919929, 'samples': 3570048, 'steps': 18593, 'loss/train': 1.50161874294281} 08/30/2021 16:34:25 - INFO - __main__ - Step 18595: {'lr': 0.00048465052650970166, 'samples': 3570240, 'steps': 18594, 'loss/train': 1.2964003086090088} 08/30/2021 16:34:26 - INFO - __main__ - Step 18596: {'lr': 0.00048464869562168055, 'samples': 3570432, 'steps': 18595, 'loss/train': 1.6343309879302979} 08/30/2021 16:34:27 - INFO - __main__ - Step 18597: {'lr': 0.0004846468646279304, 'samples': 3570624, 'steps': 18596, 'loss/train': 1.6104968786239624} 08/30/2021 16:34:28 - INFO - __main__ - Step 18598: {'lr': 0.0004846450335284519, 'samples': 3570816, 'steps': 18597, 'loss/train': 0.6221204400062561} 08/30/2021 16:34:28 - INFO - __main__ - Step 18599: {'lr': 0.00048464320232324604, 'samples': 3571008, 'steps': 18598, 'loss/train': 2.2074191570281982} 08/30/2021 16:34:28 - INFO - __main__ - Step 18600: {'lr': 0.00048464137101231355, 'samples': 3571200, 'steps': 18599, 'loss/train': 1.2850799560546875} 08/30/2021 16:34:29 - INFO - __main__ - Step 18601: {'lr': 0.0004846395395956553, 'samples': 3571392, 'steps': 18600, 'loss/train': 1.0383111238479614} 08/30/2021 16:34:30 - INFO - __main__ - Step 18602: {'lr': 0.00048463770807327206, 'samples': 3571584, 'steps': 18601, 'loss/train': 1.3161869049072266} 08/30/2021 16:34:30 - INFO - __main__ - Step 18603: {'lr': 0.00048463587644516473, 'samples': 3571776, 'steps': 18602, 'loss/train': 1.3902069330215454} 08/30/2021 16:34:31 - INFO - __main__ - Step 18604: {'lr': 0.00048463404471133404, 'samples': 3571968, 'steps': 18603, 'loss/train': 1.687749981880188} 08/30/2021 16:34:31 - INFO - __main__ - Step 18605: {'lr': 0.00048463221287178094, 'samples': 3572160, 'steps': 18604, 'loss/train': 1.7741122245788574} 08/30/2021 16:34:32 - INFO - __main__ - Step 18606: {'lr': 0.0004846303809265061, 'samples': 3572352, 'steps': 18605, 'loss/train': 1.8821640014648438} 08/30/2021 16:34:33 - INFO - __main__ - Step 18607: {'lr': 0.00048462854887551044, 'samples': 3572544, 'steps': 18606, 'loss/train': 1.5964727401733398} 08/30/2021 16:34:33 - INFO - __main__ - Step 18608: {'lr': 0.0004846267167187949, 'samples': 3572736, 'steps': 18607, 'loss/train': 1.278092861175537} 08/30/2021 16:34:34 - INFO - __main__ - Step 18609: {'lr': 0.00048462488445636005, 'samples': 3572928, 'steps': 18608, 'loss/train': 1.5015875101089478} 08/30/2021 16:34:34 - INFO - __main__ - Step 18610: {'lr': 0.0004846230520882069, 'samples': 3573120, 'steps': 18609, 'loss/train': 1.857212781906128} 08/30/2021 16:34:34 - INFO - __main__ - Step 18611: {'lr': 0.00048462121961433623, 'samples': 3573312, 'steps': 18610, 'loss/train': 1.809973120689392} 08/30/2021 16:34:35 - INFO - __main__ - Step 18612: {'lr': 0.00048461938703474886, 'samples': 3573504, 'steps': 18611, 'loss/train': 1.3722333908081055} 08/30/2021 16:34:36 - INFO - __main__ - Step 18613: {'lr': 0.00048461755434944554, 'samples': 3573696, 'steps': 18612, 'loss/train': 1.4379137754440308} 08/30/2021 16:34:37 - INFO - __main__ - Step 18614: {'lr': 0.00048461572155842725, 'samples': 3573888, 'steps': 18613, 'loss/train': 2.0803561210632324} 08/30/2021 16:34:37 - INFO - __main__ - Step 18615: {'lr': 0.00048461388866169474, 'samples': 3574080, 'steps': 18614, 'loss/train': 2.1274871826171875} 08/30/2021 16:34:38 - INFO - __main__ - Step 18616: {'lr': 0.00048461205565924884, 'samples': 3574272, 'steps': 18615, 'loss/train': 1.253926396369934} 08/30/2021 16:34:38 - INFO - __main__ - Step 18617: {'lr': 0.0004846102225510903, 'samples': 3574464, 'steps': 18616, 'loss/train': 1.4275085926055908} 08/30/2021 16:34:39 - INFO - __main__ - Step 18618: {'lr': 0.00048460838933722005, 'samples': 3574656, 'steps': 18617, 'loss/train': 1.5730656385421753} 08/30/2021 16:34:40 - INFO - __main__ - Step 18619: {'lr': 0.0004846065560176389, 'samples': 3574848, 'steps': 18618, 'loss/train': 1.208412528038025} 08/30/2021 16:34:40 - INFO - __main__ - Step 18620: {'lr': 0.00048460472259234764, 'samples': 3575040, 'steps': 18619, 'loss/train': 1.4797141551971436} 08/30/2021 16:34:41 - INFO - __main__ - Step 18621: {'lr': 0.0004846028890613471, 'samples': 3575232, 'steps': 18620, 'loss/train': 1.6955381631851196} 08/30/2021 16:34:41 - INFO - __main__ - Step 18622: {'lr': 0.00048460105542463805, 'samples': 3575424, 'steps': 18621, 'loss/train': 1.2728599309921265} 08/30/2021 16:34:42 - INFO - __main__ - Step 18623: {'lr': 0.00048459922168222146, 'samples': 3575616, 'steps': 18622, 'loss/train': 1.4494702816009521} 08/30/2021 16:34:43 - INFO - __main__ - Step 18624: {'lr': 0.00048459738783409814, 'samples': 3575808, 'steps': 18623, 'loss/train': 1.8204737901687622} 08/30/2021 16:34:43 - INFO - __main__ - Step 18625: {'lr': 0.0004845955538802688, 'samples': 3576000, 'steps': 18624, 'loss/train': 1.6453754901885986} 08/30/2021 16:34:44 - INFO - __main__ - Step 18626: {'lr': 0.0004845937198207343, 'samples': 3576192, 'steps': 18625, 'loss/train': 1.7081118822097778} 08/30/2021 16:34:44 - INFO - __main__ - Step 18627: {'lr': 0.0004845918856554955, 'samples': 3576384, 'steps': 18626, 'loss/train': 1.1042102575302124} 08/30/2021 16:34:46 - INFO - __main__ - Step 18628: {'lr': 0.00048459005138455326, 'samples': 3576576, 'steps': 18627, 'loss/train': 1.6801420450210571} 08/30/2021 16:34:46 - INFO - __main__ - Step 18629: {'lr': 0.0004845882170079083, 'samples': 3576768, 'steps': 18628, 'loss/train': 2.0579943656921387} 08/30/2021 16:34:47 - INFO - __main__ - Step 18630: {'lr': 0.00048458638252556153, 'samples': 3576960, 'steps': 18629, 'loss/train': 1.502411127090454} 08/30/2021 16:34:47 - INFO - __main__ - Step 18631: {'lr': 0.0004845845479375138, 'samples': 3577152, 'steps': 18630, 'loss/train': 1.7819527387619019} 08/30/2021 16:34:47 - INFO - __main__ - Step 18632: {'lr': 0.00048458271324376586, 'samples': 3577344, 'steps': 18631, 'loss/train': 1.3876886367797852} 08/30/2021 16:34:49 - INFO - __main__ - Step 18633: {'lr': 0.0004845808784443185, 'samples': 3577536, 'steps': 18632, 'loss/train': 1.173553466796875} 08/30/2021 16:34:49 - INFO - __main__ - Step 18634: {'lr': 0.00048457904353917277, 'samples': 3577728, 'steps': 18633, 'loss/train': 2.2251369953155518} 08/30/2021 16:34:50 - INFO - __main__ - Step 18635: {'lr': 0.0004845772085283292, 'samples': 3577920, 'steps': 18634, 'loss/train': 1.0557796955108643} 08/30/2021 16:34:50 - INFO - __main__ - Step 18636: {'lr': 0.00048457537341178885, 'samples': 3578112, 'steps': 18635, 'loss/train': 1.8288823366165161} 08/30/2021 16:34:51 - INFO - __main__ - Step 18637: {'lr': 0.0004845735381895524, 'samples': 3578304, 'steps': 18636, 'loss/train': 1.7181144952774048} 08/30/2021 16:34:52 - INFO - __main__ - Step 18638: {'lr': 0.0004845717028616208, 'samples': 3578496, 'steps': 18637, 'loss/train': 0.7587200999259949} 08/30/2021 16:34:53 - INFO - __main__ - Step 18639: {'lr': 0.00048456986742799474, 'samples': 3578688, 'steps': 18638, 'loss/train': 1.7869253158569336} 08/30/2021 16:34:53 - INFO - __main__ - Step 18640: {'lr': 0.00048456803188867513, 'samples': 3578880, 'steps': 18639, 'loss/train': 1.3770478963851929} 08/30/2021 16:34:53 - INFO - __main__ - Step 18641: {'lr': 0.00048456619624366284, 'samples': 3579072, 'steps': 18640, 'loss/train': 1.5366994142532349} 08/30/2021 16:34:54 - INFO - __main__ - Step 18642: {'lr': 0.0004845643604929586, 'samples': 3579264, 'steps': 18641, 'loss/train': 1.6829020977020264} 08/30/2021 16:34:55 - INFO - __main__ - Step 18643: {'lr': 0.00048456252463656326, 'samples': 3579456, 'steps': 18642, 'loss/train': 1.63473379611969} 08/30/2021 16:34:56 - INFO - __main__ - Step 18644: {'lr': 0.00048456068867447767, 'samples': 3579648, 'steps': 18643, 'loss/train': 1.4576683044433594} 08/30/2021 16:34:56 - INFO - __main__ - Step 18645: {'lr': 0.0004845588526067027, 'samples': 3579840, 'steps': 18644, 'loss/train': 1.4982426166534424} 08/30/2021 16:34:56 - INFO - __main__ - Step 18646: {'lr': 0.00048455701643323914, 'samples': 3580032, 'steps': 18645, 'loss/train': 1.80778169631958} 08/30/2021 16:34:57 - INFO - __main__ - Step 18647: {'lr': 0.00048455518015408773, 'samples': 3580224, 'steps': 18646, 'loss/train': 1.5563485622406006} 08/30/2021 16:34:59 - INFO - __main__ - Step 18648: {'lr': 0.00048455334376924943, 'samples': 3580416, 'steps': 18647, 'loss/train': 1.4022586345672607} 08/30/2021 16:34:59 - INFO - __main__ - Step 18649: {'lr': 0.000484551507278725, 'samples': 3580608, 'steps': 18648, 'loss/train': 1.4820568561553955} 08/30/2021 16:35:00 - INFO - __main__ - Step 18650: {'lr': 0.0004845496706825152, 'samples': 3580800, 'steps': 18649, 'loss/train': 0.0739121288061142} 08/30/2021 16:35:00 - INFO - __main__ - Step 18651: {'lr': 0.0004845478339806211, 'samples': 3580992, 'steps': 18650, 'loss/train': 0.09882553666830063} 08/30/2021 16:35:00 - INFO - __main__ - Step 18652: {'lr': 0.00048454599717304327, 'samples': 3581184, 'steps': 18651, 'loss/train': 1.7683773040771484} 08/30/2021 16:35:01 - INFO - __main__ - Step 18653: {'lr': 0.0004845441602597826, 'samples': 3581376, 'steps': 18652, 'loss/train': 2.580165386199951} 08/30/2021 16:35:01 - INFO - __main__ - Step 18654: {'lr': 0.00048454232324084004, 'samples': 3581568, 'steps': 18653, 'loss/train': 2.1176917552948} 08/30/2021 16:35:03 - INFO - __main__ - Step 18655: {'lr': 0.0004845404861162163, 'samples': 3581760, 'steps': 18654, 'loss/train': 2.0859687328338623} 08/30/2021 16:35:03 - INFO - __main__ - Step 18656: {'lr': 0.00048453864888591214, 'samples': 3581952, 'steps': 18655, 'loss/train': 2.2482786178588867} 08/30/2021 16:35:04 - INFO - __main__ - Step 18657: {'lr': 0.0004845368115499286, 'samples': 3582144, 'steps': 18656, 'loss/train': 1.875685214996338} 08/30/2021 16:35:04 - INFO - __main__ - Step 18658: {'lr': 0.0004845349741082663, 'samples': 3582336, 'steps': 18657, 'loss/train': 1.0968303680419922} 08/30/2021 16:35:04 - INFO - __main__ - Step 18659: {'lr': 0.00048453313656092624, 'samples': 3582528, 'steps': 18658, 'loss/train': 1.6515830755233765} 08/30/2021 16:35:05 - INFO - __main__ - Step 18660: {'lr': 0.0004845312989079091, 'samples': 3582720, 'steps': 18659, 'loss/train': 1.2533869743347168} 08/30/2021 16:35:06 - INFO - __main__ - Step 18661: {'lr': 0.0004845294611492158, 'samples': 3582912, 'steps': 18660, 'loss/train': 0.9937903881072998} 08/30/2021 16:35:07 - INFO - __main__ - Step 18662: {'lr': 0.00048452762328484724, 'samples': 3583104, 'steps': 18661, 'loss/train': 0.3184073567390442} 08/30/2021 16:35:07 - INFO - __main__ - Step 18663: {'lr': 0.000484525785314804, 'samples': 3583296, 'steps': 18662, 'loss/train': 1.3504564762115479} 08/30/2021 16:35:07 - INFO - __main__ - Step 18664: {'lr': 0.0004845239472390872, 'samples': 3583488, 'steps': 18663, 'loss/train': 1.2113533020019531} 08/30/2021 16:35:08 - INFO - __main__ - Step 18665: {'lr': 0.0004845221090576974, 'samples': 3583680, 'steps': 18664, 'loss/train': 1.6577436923980713} 08/30/2021 16:35:09 - INFO - __main__ - Step 18666: {'lr': 0.0004845202707706356, 'samples': 3583872, 'steps': 18665, 'loss/train': 2.0766139030456543} 08/30/2021 16:35:09 - INFO - __main__ - Step 18667: {'lr': 0.0004845184323779026, 'samples': 3584064, 'steps': 18666, 'loss/train': 1.9564974308013916} 08/30/2021 16:35:10 - INFO - __main__ - Step 18668: {'lr': 0.0004845165938794992, 'samples': 3584256, 'steps': 18667, 'loss/train': 1.630800485610962} 08/30/2021 16:35:10 - INFO - __main__ - Step 18669: {'lr': 0.0004845147552754263, 'samples': 3584448, 'steps': 18668, 'loss/train': 1.7552801370620728} 08/30/2021 16:35:10 - INFO - __main__ - Step 18670: {'lr': 0.0004845129165656846, 'samples': 3584640, 'steps': 18669, 'loss/train': 1.6562836170196533} 08/30/2021 16:35:12 - INFO - __main__ - Step 18671: {'lr': 0.00048451107775027505, 'samples': 3584832, 'steps': 18670, 'loss/train': 1.9035931825637817} 08/30/2021 16:35:12 - INFO - __main__ - Step 18672: {'lr': 0.0004845092388291984, 'samples': 3585024, 'steps': 18671, 'loss/train': 1.4335185289382935} 08/30/2021 16:35:13 - INFO - __main__ - Step 18673: {'lr': 0.0004845073998024555, 'samples': 3585216, 'steps': 18672, 'loss/train': 1.2621657848358154} 08/30/2021 16:35:13 - INFO - __main__ - Step 18674: {'lr': 0.0004845055606700472, 'samples': 3585408, 'steps': 18673, 'loss/train': 1.5613656044006348} 08/30/2021 16:35:13 - INFO - __main__ - Step 18675: {'lr': 0.0004845037214319743, 'samples': 3585600, 'steps': 18674, 'loss/train': 1.5874727964401245} 08/30/2021 16:35:15 - INFO - __main__ - Step 18676: {'lr': 0.00048450188208823766, 'samples': 3585792, 'steps': 18675, 'loss/train': 0.40764713287353516} 08/30/2021 16:35:15 - INFO - __main__ - Step 18677: {'lr': 0.00048450004263883806, 'samples': 3585984, 'steps': 18676, 'loss/train': 1.5625742673873901} 08/30/2021 16:35:16 - INFO - __main__ - Step 18678: {'lr': 0.00048449820308377634, 'samples': 3586176, 'steps': 18677, 'loss/train': 1.9346193075180054} 08/30/2021 16:35:16 - INFO - __main__ - Step 18679: {'lr': 0.00048449636342305343, 'samples': 3586368, 'steps': 18678, 'loss/train': 1.4314703941345215} 08/30/2021 16:35:16 - INFO - __main__ - Step 18680: {'lr': 0.00048449452365667003, 'samples': 3586560, 'steps': 18679, 'loss/train': 1.5792099237442017} 08/30/2021 16:35:19 - INFO - __main__ - Step 18681: {'lr': 0.00048449268378462695, 'samples': 3586752, 'steps': 18680, 'loss/train': 1.8770092725753784} 08/30/2021 16:35:20 - INFO - __main__ - Step 18682: {'lr': 0.00048449084380692523, 'samples': 3586944, 'steps': 18681, 'loss/train': 1.610478162765503} 08/30/2021 16:35:20 - INFO - __main__ - Step 18683: {'lr': 0.0004844890037235654, 'samples': 3587136, 'steps': 18682, 'loss/train': 1.8821977376937866} 08/30/2021 16:35:20 - INFO - __main__ - Step 18684: {'lr': 0.00048448716353454856, 'samples': 3587328, 'steps': 18683, 'loss/train': 3.1390202045440674} 08/30/2021 16:35:21 - INFO - __main__ - Step 18685: {'lr': 0.0004844853232398754, 'samples': 3587520, 'steps': 18684, 'loss/train': 3.5587410926818848} 08/30/2021 16:35:21 - INFO - __main__ - Step 18686: {'lr': 0.00048448348283954674, 'samples': 3587712, 'steps': 18685, 'loss/train': 1.690757155418396} 08/30/2021 16:35:22 - INFO - __main__ - Step 18687: {'lr': 0.00048448164233356344, 'samples': 3587904, 'steps': 18686, 'loss/train': 2.143714427947998} 08/30/2021 16:35:23 - INFO - __main__ - Step 18688: {'lr': 0.0004844798017219264, 'samples': 3588096, 'steps': 18687, 'loss/train': 1.801722764968872} 08/30/2021 16:35:23 - INFO - __main__ - Step 18689: {'lr': 0.00048447796100463625, 'samples': 3588288, 'steps': 18688, 'loss/train': 2.230644941329956} 08/30/2021 16:35:24 - INFO - __main__ - Step 18690: {'lr': 0.0004844761201816941, 'samples': 3588480, 'steps': 18689, 'loss/train': 1.5586072206497192} 08/30/2021 16:35:24 - INFO - __main__ - Step 18691: {'lr': 0.0004844742792531005, 'samples': 3588672, 'steps': 18690, 'loss/train': 1.4849650859832764} 08/30/2021 16:35:24 - INFO - __main__ - Step 18692: {'lr': 0.00048447243821885644, 'samples': 3588864, 'steps': 18691, 'loss/train': 1.0598472356796265} 08/30/2021 16:35:26 - INFO - __main__ - Step 18693: {'lr': 0.0004844705970789628, 'samples': 3589056, 'steps': 18692, 'loss/train': 1.4825066328048706} 08/30/2021 16:35:26 - INFO - __main__ - Step 18694: {'lr': 0.0004844687558334202, 'samples': 3589248, 'steps': 18693, 'loss/train': 1.6356847286224365} 08/30/2021 16:35:27 - INFO - __main__ - Step 18695: {'lr': 0.0004844669144822297, 'samples': 3589440, 'steps': 18694, 'loss/train': 2.0778491497039795} 08/30/2021 16:35:27 - INFO - __main__ - Step 18696: {'lr': 0.000484465073025392, 'samples': 3589632, 'steps': 18695, 'loss/train': 1.254042148590088} 08/30/2021 16:35:27 - INFO - __main__ - Step 18697: {'lr': 0.00048446323146290795, 'samples': 3589824, 'steps': 18696, 'loss/train': 2.0559182167053223} 08/30/2021 16:35:29 - INFO - __main__ - Step 18698: {'lr': 0.0004844613897947784, 'samples': 3590016, 'steps': 18697, 'loss/train': 1.9842222929000854} 08/30/2021 16:35:29 - INFO - __main__ - Step 18699: {'lr': 0.00048445954802100414, 'samples': 3590208, 'steps': 18698, 'loss/train': 1.610824704170227} 08/30/2021 16:35:30 - INFO - __main__ - Step 18700: {'lr': 0.000484457706141586, 'samples': 3590400, 'steps': 18699, 'loss/train': 1.5430368185043335} 08/30/2021 16:35:30 - INFO - __main__ - Step 18701: {'lr': 0.0004844558641565249, 'samples': 3590592, 'steps': 18700, 'loss/train': 1.5543664693832397} 08/30/2021 16:35:30 - INFO - __main__ - Step 18702: {'lr': 0.00048445402206582155, 'samples': 3590784, 'steps': 18701, 'loss/train': 1.8709467649459839} 08/30/2021 16:35:32 - INFO - __main__ - Step 18703: {'lr': 0.0004844521798694768, 'samples': 3590976, 'steps': 18702, 'loss/train': 1.660312294960022} 08/30/2021 16:35:32 - INFO - __main__ - Step 18704: {'lr': 0.0004844503375674916, 'samples': 3591168, 'steps': 18703, 'loss/train': 1.8360676765441895} 08/30/2021 16:35:33 - INFO - __main__ - Step 18705: {'lr': 0.0004844484951598667, 'samples': 3591360, 'steps': 18704, 'loss/train': 1.815129280090332} 08/30/2021 16:35:33 - INFO - __main__ - Step 18706: {'lr': 0.00048444665264660286, 'samples': 3591552, 'steps': 18705, 'loss/train': 0.14327189326286316} 08/30/2021 16:35:33 - INFO - __main__ - Step 18707: {'lr': 0.000484444810027701, 'samples': 3591744, 'steps': 18706, 'loss/train': 1.789504051208496} 08/30/2021 16:35:35 - INFO - __main__ - Step 18708: {'lr': 0.00048444296730316196, 'samples': 3591936, 'steps': 18707, 'loss/train': 1.9275892972946167} 08/30/2021 16:35:35 - INFO - __main__ - Step 18709: {'lr': 0.0004844411244729865, 'samples': 3592128, 'steps': 18708, 'loss/train': 2.6028988361358643} 08/30/2021 16:35:36 - INFO - __main__ - Step 18710: {'lr': 0.00048443928153717555, 'samples': 3592320, 'steps': 18709, 'loss/train': 1.8521556854248047} 08/30/2021 16:35:36 - INFO - __main__ - Step 18711: {'lr': 0.00048443743849572974, 'samples': 3592512, 'steps': 18710, 'loss/train': 1.3215727806091309} 08/30/2021 16:35:36 - INFO - __main__ - Step 18712: {'lr': 0.00048443559534865017, 'samples': 3592704, 'steps': 18711, 'loss/train': 1.9808443784713745} 08/30/2021 16:35:37 - INFO - __main__ - Step 18713: {'lr': 0.0004844337520959375, 'samples': 3592896, 'steps': 18712, 'loss/train': 1.8047269582748413} 08/30/2021 16:35:39 - INFO - __main__ - Step 18714: {'lr': 0.00048443190873759256, 'samples': 3593088, 'steps': 18713, 'loss/train': 1.957062005996704} 08/30/2021 16:35:39 - INFO - __main__ - Step 18715: {'lr': 0.00048443006527361626, 'samples': 3593280, 'steps': 18714, 'loss/train': 1.7376261949539185} 08/30/2021 16:35:40 - INFO - __main__ - Step 18716: {'lr': 0.0004844282217040094, 'samples': 3593472, 'steps': 18715, 'loss/train': 1.8164899349212646} 08/30/2021 16:35:40 - INFO - __main__ - Step 18717: {'lr': 0.00048442637802877277, 'samples': 3593664, 'steps': 18716, 'loss/train': 0.22864291071891785} 08/30/2021 16:35:40 - INFO - __main__ - Step 18718: {'lr': 0.0004844245342479072, 'samples': 3593856, 'steps': 18717, 'loss/train': 1.6635072231292725} 08/30/2021 16:35:41 - INFO - __main__ - Step 18719: {'lr': 0.00048442269036141363, 'samples': 3594048, 'steps': 18718, 'loss/train': 1.2503526210784912} 08/30/2021 16:35:42 - INFO - __main__ - Step 18720: {'lr': 0.0004844208463692928, 'samples': 3594240, 'steps': 18719, 'loss/train': 0.14091970026493073} 08/30/2021 16:35:43 - INFO - __main__ - Step 18721: {'lr': 0.00048441900227154557, 'samples': 3594432, 'steps': 18720, 'loss/train': 1.1688940525054932} 08/30/2021 16:35:43 - INFO - __main__ - Step 18722: {'lr': 0.00048441715806817265, 'samples': 3594624, 'steps': 18721, 'loss/train': 1.5595972537994385} 08/30/2021 16:35:43 - INFO - __main__ - Step 18723: {'lr': 0.0004844153137591751, 'samples': 3594816, 'steps': 18722, 'loss/train': 2.0275187492370605} 08/30/2021 16:35:44 - INFO - __main__ - Step 18724: {'lr': 0.00048441346934455356, 'samples': 3595008, 'steps': 18723, 'loss/train': 1.7118854522705078} 08/30/2021 16:35:45 - INFO - __main__ - Step 18725: {'lr': 0.0004844116248243089, 'samples': 3595200, 'steps': 18724, 'loss/train': 1.8899564743041992} 08/30/2021 16:35:46 - INFO - __main__ - Step 18726: {'lr': 0.0004844097801984421, 'samples': 3595392, 'steps': 18725, 'loss/train': 1.701796054840088} 08/30/2021 16:35:46 - INFO - __main__ - Step 18727: {'lr': 0.0004844079354669537, 'samples': 3595584, 'steps': 18726, 'loss/train': 1.674830675125122} 08/30/2021 16:35:46 - INFO - __main__ - Step 18728: {'lr': 0.0004844060906298448, 'samples': 3595776, 'steps': 18727, 'loss/train': 2.0198514461517334} 08/30/2021 16:35:47 - INFO - __main__ - Step 18729: {'lr': 0.0004844042456871162, 'samples': 3595968, 'steps': 18728, 'loss/train': 1.8553674221038818} 08/30/2021 16:35:48 - INFO - __main__ - Step 18730: {'lr': 0.0004844024006387685, 'samples': 3596160, 'steps': 18729, 'loss/train': 1.6953486204147339} 08/30/2021 16:35:49 - INFO - __main__ - Step 18731: {'lr': 0.00048440055548480275, 'samples': 3596352, 'steps': 18730, 'loss/train': 1.5249199867248535} 08/30/2021 16:35:49 - INFO - __main__ - Step 18732: {'lr': 0.0004843987102252198, 'samples': 3596544, 'steps': 18731, 'loss/train': 1.6466822624206543} 08/30/2021 16:35:49 - INFO - __main__ - Step 18733: {'lr': 0.0004843968648600204, 'samples': 3596736, 'steps': 18732, 'loss/train': 1.4004868268966675} 08/30/2021 16:35:50 - INFO - __main__ - Step 18734: {'lr': 0.00048439501938920534, 'samples': 3596928, 'steps': 18733, 'loss/train': 1.815832495689392} 08/30/2021 16:35:51 - INFO - __main__ - Step 18735: {'lr': 0.0004843931738127755, 'samples': 3597120, 'steps': 18734, 'loss/train': 1.5569733381271362} 08/30/2021 16:35:52 - INFO - __main__ - Step 18736: {'lr': 0.0004843913281307317, 'samples': 3597312, 'steps': 18735, 'loss/train': 1.4122766256332397} 08/30/2021 16:35:52 - INFO - __main__ - Step 18737: {'lr': 0.0004843894823430749, 'samples': 3597504, 'steps': 18736, 'loss/train': 1.5067040920257568} 08/30/2021 16:35:52 - INFO - __main__ - Step 18738: {'lr': 0.00048438763644980564, 'samples': 3597696, 'steps': 18737, 'loss/train': 1.0526565313339233} 08/30/2021 16:35:53 - INFO - __main__ - Step 18739: {'lr': 0.0004843857904509251, 'samples': 3597888, 'steps': 18738, 'loss/train': 1.0327776670455933} 08/30/2021 16:35:55 - INFO - __main__ - Step 18740: {'lr': 0.00048438394434643386, 'samples': 3598080, 'steps': 18739, 'loss/train': 2.21777081489563} 08/30/2021 16:35:55 - INFO - __main__ - Step 18741: {'lr': 0.0004843820981363328, 'samples': 3598272, 'steps': 18740, 'loss/train': 1.4588394165039062} 08/30/2021 16:35:55 - INFO - __main__ - Step 18742: {'lr': 0.00048438025182062286, 'samples': 3598464, 'steps': 18741, 'loss/train': 1.724167823791504} 08/30/2021 16:35:56 - INFO - __main__ - Step 18743: {'lr': 0.00048437840539930466, 'samples': 3598656, 'steps': 18742, 'loss/train': 1.81268310546875} 08/30/2021 16:35:56 - INFO - __main__ - Step 18744: {'lr': 0.0004843765588723793, 'samples': 3598848, 'steps': 18743, 'loss/train': 1.3539683818817139} 08/30/2021 16:35:57 - INFO - __main__ - Step 18745: {'lr': 0.00048437471223984743, 'samples': 3599040, 'steps': 18744, 'loss/train': 2.382828712463379} 08/30/2021 16:35:58 - INFO - __main__ - Step 18746: {'lr': 0.00048437286550170996, 'samples': 3599232, 'steps': 18745, 'loss/train': 2.2191319465637207} 08/30/2021 16:35:58 - INFO - __main__ - Step 18747: {'lr': 0.00048437101865796763, 'samples': 3599424, 'steps': 18746, 'loss/train': 1.140054702758789} 08/30/2021 16:35:59 - INFO - __main__ - Step 18748: {'lr': 0.0004843691717086214, 'samples': 3599616, 'steps': 18747, 'loss/train': 1.7695509195327759} 08/30/2021 16:35:59 - INFO - __main__ - Step 18749: {'lr': 0.000484367324653672, 'samples': 3599808, 'steps': 18748, 'loss/train': 1.8163909912109375} 08/30/2021 16:36:00 - INFO - __main__ - Step 18750: {'lr': 0.0004843654774931203, 'samples': 3600000, 'steps': 18749, 'loss/train': 1.4683212041854858} 08/30/2021 16:36:01 - INFO - __main__ - Step 18751: {'lr': 0.00048436363022696715, 'samples': 3600192, 'steps': 18750, 'loss/train': 1.4695026874542236} 08/30/2021 16:36:01 - INFO - __main__ - Step 18752: {'lr': 0.0004843617828552134, 'samples': 3600384, 'steps': 18751, 'loss/train': 2.245600938796997} 08/30/2021 16:36:02 - INFO - __main__ - Step 18753: {'lr': 0.00048435993537785976, 'samples': 3600576, 'steps': 18752, 'loss/train': 2.03971266746521} 08/30/2021 16:36:02 - INFO - __main__ - Step 18754: {'lr': 0.0004843580877949072, 'samples': 3600768, 'steps': 18753, 'loss/train': 1.674576997756958} 08/30/2021 16:36:02 - INFO - __main__ - Step 18755: {'lr': 0.0004843562401063565, 'samples': 3600960, 'steps': 18754, 'loss/train': 1.3875715732574463} 08/30/2021 16:36:04 - INFO - __main__ - Step 18756: {'lr': 0.0004843543923122085, 'samples': 3601152, 'steps': 18755, 'loss/train': 1.7169502973556519} 08/30/2021 16:36:04 - INFO - __main__ - Step 18757: {'lr': 0.000484352544412464, 'samples': 3601344, 'steps': 18756, 'loss/train': 2.0435969829559326} 08/30/2021 16:36:05 - INFO - __main__ - Step 18758: {'lr': 0.0004843506964071239, 'samples': 3601536, 'steps': 18757, 'loss/train': 1.4638701677322388} 08/30/2021 16:36:05 - INFO - __main__ - Step 18759: {'lr': 0.000484348848296189, 'samples': 3601728, 'steps': 18758, 'loss/train': 1.5171616077423096} 08/30/2021 16:36:05 - INFO - __main__ - Step 18760: {'lr': 0.00048434700007966006, 'samples': 3601920, 'steps': 18759, 'loss/train': 1.8144410848617554} 08/30/2021 16:36:07 - INFO - __main__ - Step 18761: {'lr': 0.000484345151757538, 'samples': 3602112, 'steps': 18760, 'loss/train': 1.88290536403656} 08/30/2021 16:36:08 - INFO - __main__ - Step 18762: {'lr': 0.0004843433033298237, 'samples': 3602304, 'steps': 18761, 'loss/train': 1.8810815811157227} 08/30/2021 16:36:08 - INFO - __main__ - Step 18763: {'lr': 0.00048434145479651783, 'samples': 3602496, 'steps': 18762, 'loss/train': 1.4046201705932617} 08/30/2021 16:36:08 - INFO - __main__ - Step 18764: {'lr': 0.00048433960615762136, 'samples': 3602688, 'steps': 18763, 'loss/train': 1.8820677995681763} 08/30/2021 16:36:09 - INFO - __main__ - Step 18765: {'lr': 0.0004843377574131351, 'samples': 3602880, 'steps': 18764, 'loss/train': 1.4780255556106567} 08/30/2021 16:36:10 - INFO - __main__ - Step 18766: {'lr': 0.0004843359085630598, 'samples': 3603072, 'steps': 18765, 'loss/train': 1.659212350845337} 08/30/2021 16:36:11 - INFO - __main__ - Step 18767: {'lr': 0.0004843340596073964, 'samples': 3603264, 'steps': 18766, 'loss/train': 1.403775691986084} 08/30/2021 16:36:11 - INFO - __main__ - Step 18768: {'lr': 0.0004843322105461457, 'samples': 3603456, 'steps': 18767, 'loss/train': 1.7835924625396729} 08/30/2021 16:36:11 - INFO - __main__ - Step 18769: {'lr': 0.0004843303613793085, 'samples': 3603648, 'steps': 18768, 'loss/train': 1.0598496198654175} 08/30/2021 16:36:12 - INFO - __main__ - Step 18770: {'lr': 0.00048432851210688567, 'samples': 3603840, 'steps': 18769, 'loss/train': 1.6672589778900146} 08/30/2021 16:36:13 - INFO - __main__ - Step 18771: {'lr': 0.00048432666272887805, 'samples': 3604032, 'steps': 18770, 'loss/train': 2.340057849884033} 08/30/2021 16:36:13 - INFO - __main__ - Step 18772: {'lr': 0.0004843248132452864, 'samples': 3604224, 'steps': 18771, 'loss/train': 1.585218071937561} 08/30/2021 16:36:14 - INFO - __main__ - Step 18773: {'lr': 0.0004843229636561116, 'samples': 3604416, 'steps': 18772, 'loss/train': 1.4477012157440186} 08/30/2021 16:36:14 - INFO - __main__ - Step 18774: {'lr': 0.00048432111396135447, 'samples': 3604608, 'steps': 18773, 'loss/train': 1.6103549003601074} 08/30/2021 16:36:15 - INFO - __main__ - Step 18775: {'lr': 0.0004843192641610159, 'samples': 3604800, 'steps': 18774, 'loss/train': 1.2788995504379272} 08/30/2021 16:36:16 - INFO - __main__ - Step 18776: {'lr': 0.00048431741425509676, 'samples': 3604992, 'steps': 18775, 'loss/train': 1.5461417436599731} 08/30/2021 16:36:16 - INFO - __main__ - Step 18777: {'lr': 0.0004843155642435977, 'samples': 3605184, 'steps': 18776, 'loss/train': 2.0165276527404785} 08/30/2021 16:36:17 - INFO - __main__ - Step 18778: {'lr': 0.0004843137141265197, 'samples': 3605376, 'steps': 18777, 'loss/train': 1.8745001554489136} 08/30/2021 16:36:17 - INFO - __main__ - Step 18779: {'lr': 0.00048431186390386356, 'samples': 3605568, 'steps': 18778, 'loss/train': 1.5030087232589722} 08/30/2021 16:36:18 - INFO - __main__ - Step 18780: {'lr': 0.0004843100135756301, 'samples': 3605760, 'steps': 18779, 'loss/train': 2.11687970161438} 08/30/2021 16:36:18 - INFO - __main__ - Step 18781: {'lr': 0.0004843081631418202, 'samples': 3605952, 'steps': 18780, 'loss/train': 2.195359945297241} 08/30/2021 16:36:19 - INFO - __main__ - Step 18782: {'lr': 0.00048430631260243465, 'samples': 3606144, 'steps': 18781, 'loss/train': 1.9703930616378784} 08/30/2021 16:36:20 - INFO - __main__ - Step 18783: {'lr': 0.00048430446195747424, 'samples': 3606336, 'steps': 18782, 'loss/train': 1.436973214149475} 08/30/2021 16:36:20 - INFO - __main__ - Step 18784: {'lr': 0.00048430261120693986, 'samples': 3606528, 'steps': 18783, 'loss/train': 1.4219201803207397} 08/30/2021 16:36:21 - INFO - __main__ - Step 18785: {'lr': 0.0004843007603508324, 'samples': 3606720, 'steps': 18784, 'loss/train': 1.6902960538864136} 08/30/2021 16:36:21 - INFO - __main__ - Step 18786: {'lr': 0.00048429890938915255, 'samples': 3606912, 'steps': 18785, 'loss/train': 1.467069387435913} 08/30/2021 16:36:22 - INFO - __main__ - Step 18787: {'lr': 0.0004842970583219013, 'samples': 3607104, 'steps': 18786, 'loss/train': 1.503032922744751} 08/30/2021 16:36:23 - INFO - __main__ - Step 18788: {'lr': 0.0004842952071490794, 'samples': 3607296, 'steps': 18787, 'loss/train': 1.3325965404510498} 08/30/2021 16:36:23 - INFO - __main__ - Step 18789: {'lr': 0.0004842933558706877, 'samples': 3607488, 'steps': 18788, 'loss/train': 1.8448175191879272} 08/30/2021 16:36:24 - INFO - __main__ - Step 18790: {'lr': 0.000484291504486727, 'samples': 3607680, 'steps': 18789, 'loss/train': 1.696388602256775} 08/30/2021 16:36:24 - INFO - __main__ - Step 18791: {'lr': 0.0004842896529971982, 'samples': 3607872, 'steps': 18790, 'loss/train': 1.762611746788025} 08/30/2021 16:36:26 - INFO - __main__ - Step 18792: {'lr': 0.00048428780140210204, 'samples': 3608064, 'steps': 18791, 'loss/train': 1.8964207172393799} 08/30/2021 16:36:27 - INFO - __main__ - Step 18793: {'lr': 0.0004842859497014394, 'samples': 3608256, 'steps': 18792, 'loss/train': 1.6959890127182007} 08/30/2021 16:36:27 - INFO - __main__ - Step 18794: {'lr': 0.0004842840978952112, 'samples': 3608448, 'steps': 18793, 'loss/train': 0.7731893658638} 08/30/2021 16:36:27 - INFO - __main__ - Step 18795: {'lr': 0.00048428224598341815, 'samples': 3608640, 'steps': 18794, 'loss/train': 1.503921389579773} 08/30/2021 16:36:28 - INFO - __main__ - Step 18796: {'lr': 0.0004842803939660612, 'samples': 3608832, 'steps': 18795, 'loss/train': 1.7576403617858887} 08/30/2021 16:36:29 - INFO - __main__ - Step 18797: {'lr': 0.00048427854184314103, 'samples': 3609024, 'steps': 18796, 'loss/train': 1.324228286743164} 08/30/2021 16:36:30 - INFO - __main__ - Step 18798: {'lr': 0.0004842766896146586, 'samples': 3609216, 'steps': 18797, 'loss/train': 1.5051244497299194} 08/30/2021 16:36:30 - INFO - __main__ - Step 18799: {'lr': 0.0004842748372806147, 'samples': 3609408, 'steps': 18798, 'loss/train': 1.8872275352478027} 08/30/2021 16:36:30 - INFO - __main__ - Step 18800: {'lr': 0.00048427298484101023, 'samples': 3609600, 'steps': 18799, 'loss/train': 1.111180067062378} 08/30/2021 16:36:31 - INFO - __main__ - Step 18801: {'lr': 0.0004842711322958459, 'samples': 3609792, 'steps': 18800, 'loss/train': 1.7275948524475098} 08/30/2021 16:36:33 - INFO - __main__ - Step 18802: {'lr': 0.0004842692796451226, 'samples': 3609984, 'steps': 18801, 'loss/train': 1.684067726135254} 08/30/2021 16:36:33 - INFO - __main__ - Step 18803: {'lr': 0.0004842674268888413, 'samples': 3610176, 'steps': 18802, 'loss/train': 1.430519938468933} 08/30/2021 16:36:33 - INFO - __main__ - Step 18804: {'lr': 0.0004842655740270026, 'samples': 3610368, 'steps': 18803, 'loss/train': 1.34248948097229} 08/30/2021 16:36:34 - INFO - __main__ - Step 18805: {'lr': 0.0004842637210596075, 'samples': 3610560, 'steps': 18804, 'loss/train': 1.3173251152038574} 08/30/2021 16:36:34 - INFO - __main__ - Step 18806: {'lr': 0.0004842618679866567, 'samples': 3610752, 'steps': 18805, 'loss/train': 1.451834797859192} 08/30/2021 16:36:36 - INFO - __main__ - Step 18807: {'lr': 0.0004842600148081512, 'samples': 3610944, 'steps': 18806, 'loss/train': 1.028164029121399} 08/30/2021 16:36:36 - INFO - __main__ - Step 18808: {'lr': 0.00048425816152409173, 'samples': 3611136, 'steps': 18807, 'loss/train': 2.2420125007629395} 08/30/2021 16:36:36 - INFO - __main__ - Step 18809: {'lr': 0.00048425630813447916, 'samples': 3611328, 'steps': 18808, 'loss/train': 1.931848406791687} 08/30/2021 16:36:37 - INFO - __main__ - Step 18810: {'lr': 0.0004842544546393143, 'samples': 3611520, 'steps': 18809, 'loss/train': 1.5243005752563477} 08/30/2021 16:36:37 - INFO - __main__ - Step 18811: {'lr': 0.00048425260103859797, 'samples': 3611712, 'steps': 18810, 'loss/train': 2.062664270401001} 08/30/2021 16:36:39 - INFO - __main__ - Step 18812: {'lr': 0.0004842507473323311, 'samples': 3611904, 'steps': 18811, 'loss/train': 1.3754416704177856} 08/30/2021 16:36:39 - INFO - __main__ - Step 18813: {'lr': 0.00048424889352051436, 'samples': 3612096, 'steps': 18812, 'loss/train': 1.0482581853866577} 08/30/2021 16:36:39 - INFO - __main__ - Step 18814: {'lr': 0.00048424703960314876, 'samples': 3612288, 'steps': 18813, 'loss/train': 1.5366097688674927} 08/30/2021 16:36:40 - INFO - __main__ - Step 18815: {'lr': 0.00048424518558023505, 'samples': 3612480, 'steps': 18814, 'loss/train': 1.6471534967422485} 08/30/2021 16:36:40 - INFO - __main__ - Step 18816: {'lr': 0.00048424333145177405, 'samples': 3612672, 'steps': 18815, 'loss/train': 2.2628097534179688} 08/30/2021 16:36:40 - INFO - __main__ - Step 18817: {'lr': 0.00048424147721776666, 'samples': 3612864, 'steps': 18816, 'loss/train': 1.8539897203445435} 08/30/2021 16:36:42 - INFO - __main__ - Step 18818: {'lr': 0.00048423962287821366, 'samples': 3613056, 'steps': 18817, 'loss/train': 1.4543426036834717} 08/30/2021 16:36:43 - INFO - __main__ - Step 18819: {'lr': 0.00048423776843311585, 'samples': 3613248, 'steps': 18818, 'loss/train': 1.724756121635437} 08/30/2021 16:36:43 - INFO - __main__ - Step 18820: {'lr': 0.00048423591388247416, 'samples': 3613440, 'steps': 18819, 'loss/train': 1.831925392150879} 08/30/2021 16:36:44 - INFO - __main__ - Step 18821: {'lr': 0.0004842340592262894, 'samples': 3613632, 'steps': 18820, 'loss/train': 1.9668060541152954} 08/30/2021 16:36:44 - INFO - __main__ - Step 18822: {'lr': 0.00048423220446456233, 'samples': 3613824, 'steps': 18821, 'loss/train': 1.4850150346755981} 08/30/2021 16:36:44 - INFO - __main__ - Step 18823: {'lr': 0.0004842303495972939, 'samples': 3614016, 'steps': 18822, 'loss/train': 1.7642061710357666} 08/30/2021 16:36:46 - INFO - __main__ - Step 18824: {'lr': 0.00048422849462448483, 'samples': 3614208, 'steps': 18823, 'loss/train': 2.1004860401153564} 08/30/2021 16:36:47 - INFO - __main__ - Step 18825: {'lr': 0.0004842266395461361, 'samples': 3614400, 'steps': 18824, 'loss/train': 1.674424409866333} 08/30/2021 16:36:47 - INFO - __main__ - Step 18826: {'lr': 0.0004842247843622484, 'samples': 3614592, 'steps': 18825, 'loss/train': 1.7505078315734863} 08/30/2021 16:36:47 - INFO - __main__ - Step 18827: {'lr': 0.0004842229290728226, 'samples': 3614784, 'steps': 18826, 'loss/train': 1.1835781335830688} 08/30/2021 16:36:48 - INFO - __main__ - Step 18828: {'lr': 0.0004842210736778596, 'samples': 3614976, 'steps': 18827, 'loss/train': 2.0453503131866455} 08/30/2021 16:36:48 - INFO - __main__ - Step 18829: {'lr': 0.0004842192181773602, 'samples': 3615168, 'steps': 18828, 'loss/train': 1.901028037071228} 08/30/2021 16:36:48 - INFO - __main__ - Step 18830: {'lr': 0.0004842173625713252, 'samples': 3615360, 'steps': 18829, 'loss/train': 1.8921504020690918} 08/30/2021 16:36:50 - INFO - __main__ - Step 18831: {'lr': 0.0004842155068597556, 'samples': 3615552, 'steps': 18830, 'loss/train': 2.693031072616577} 08/30/2021 16:36:50 - INFO - __main__ - Step 18832: {'lr': 0.0004842136510426519, 'samples': 3615744, 'steps': 18831, 'loss/train': 1.7852935791015625} 08/30/2021 16:36:51 - INFO - __main__ - Step 18833: {'lr': 0.00048421179512001536, 'samples': 3615936, 'steps': 18832, 'loss/train': 1.0270863771438599} 08/30/2021 16:36:51 - INFO - __main__ - Step 18834: {'lr': 0.0004842099390918464, 'samples': 3616128, 'steps': 18833, 'loss/train': 1.476439356803894} 08/30/2021 16:36:51 - INFO - __main__ - Step 18835: {'lr': 0.00048420808295814624, 'samples': 3616320, 'steps': 18834, 'loss/train': 1.4553825855255127} 08/30/2021 16:36:53 - INFO - __main__ - Step 18836: {'lr': 0.00048420622671891533, 'samples': 3616512, 'steps': 18835, 'loss/train': 1.8982298374176025} 08/30/2021 16:36:53 - INFO - __main__ - Step 18837: {'lr': 0.00048420437037415486, 'samples': 3616704, 'steps': 18836, 'loss/train': 1.5830507278442383} 08/30/2021 16:36:54 - INFO - __main__ - Step 18838: {'lr': 0.00048420251392386547, 'samples': 3616896, 'steps': 18837, 'loss/train': 2.066307544708252} 08/30/2021 16:36:54 - INFO - __main__ - Step 18839: {'lr': 0.0004842006573680481, 'samples': 3617088, 'steps': 18838, 'loss/train': 1.865342617034912} 08/30/2021 16:36:54 - INFO - __main__ - Step 18840: {'lr': 0.0004841988007067034, 'samples': 3617280, 'steps': 18839, 'loss/train': 1.5887759923934937} 08/30/2021 16:36:56 - INFO - __main__ - Step 18841: {'lr': 0.00048419694393983244, 'samples': 3617472, 'steps': 18840, 'loss/train': 1.801106572151184} 08/30/2021 16:36:56 - INFO - __main__ - Step 18842: {'lr': 0.00048419508706743587, 'samples': 3617664, 'steps': 18841, 'loss/train': 1.5339930057525635} 08/30/2021 16:36:57 - INFO - __main__ - Step 18843: {'lr': 0.00048419323008951467, 'samples': 3617856, 'steps': 18842, 'loss/train': 1.4506832361221313} 08/30/2021 16:36:57 - INFO - __main__ - Step 18844: {'lr': 0.00048419137300606963, 'samples': 3618048, 'steps': 18843, 'loss/train': 1.8783767223358154} 08/30/2021 16:36:57 - INFO - __main__ - Step 18845: {'lr': 0.00048418951581710154, 'samples': 3618240, 'steps': 18844, 'loss/train': 1.9886521100997925} 08/30/2021 16:37:00 - INFO - __main__ - Step 18846: {'lr': 0.00048418765852261124, 'samples': 3618432, 'steps': 18845, 'loss/train': 1.754531979560852} 08/30/2021 16:37:00 - INFO - __main__ - Step 18847: {'lr': 0.0004841858011225996, 'samples': 3618624, 'steps': 18846, 'loss/train': 1.5919480323791504} 08/30/2021 16:37:00 - INFO - __main__ - Step 18848: {'lr': 0.0004841839436170675, 'samples': 3618816, 'steps': 18847, 'loss/train': 1.814907193183899} 08/30/2021 16:37:01 - INFO - __main__ - Step 18849: {'lr': 0.0004841820860060157, 'samples': 3619008, 'steps': 18848, 'loss/train': 1.5920826196670532} 08/30/2021 16:37:01 - INFO - __main__ - Step 18850: {'lr': 0.0004841802282894451, 'samples': 3619200, 'steps': 18849, 'loss/train': 2.005141496658325} 08/30/2021 16:37:01 - INFO - __main__ - Step 18851: {'lr': 0.0004841783704673565, 'samples': 3619392, 'steps': 18850, 'loss/train': 2.8705596923828125} 08/30/2021 16:37:03 - INFO - __main__ - Step 18852: {'lr': 0.00048417651253975067, 'samples': 3619584, 'steps': 18851, 'loss/train': 1.971785545349121} 08/30/2021 16:37:04 - INFO - __main__ - Step 18853: {'lr': 0.00048417465450662856, 'samples': 3619776, 'steps': 18852, 'loss/train': 1.8574641942977905} 08/30/2021 16:37:04 - INFO - __main__ - Step 18854: {'lr': 0.0004841727963679909, 'samples': 3619968, 'steps': 18853, 'loss/train': 1.6750909090042114} 08/30/2021 16:37:04 - INFO - __main__ - Step 18855: {'lr': 0.0004841709381238387, 'samples': 3620160, 'steps': 18854, 'loss/train': 1.5622586011886597} 08/30/2021 16:37:05 - INFO - __main__ - Step 18856: {'lr': 0.0004841690797741726, 'samples': 3620352, 'steps': 18855, 'loss/train': 1.5276461839675903} 08/30/2021 16:37:06 - INFO - __main__ - Step 18857: {'lr': 0.0004841672213189936, 'samples': 3620544, 'steps': 18856, 'loss/train': 1.2764571905136108} 08/30/2021 16:37:06 - INFO - __main__ - Step 18858: {'lr': 0.00048416536275830245, 'samples': 3620736, 'steps': 18857, 'loss/train': 1.8183342218399048} 08/30/2021 16:37:07 - INFO - __main__ - Step 18859: {'lr': 0.00048416350409209995, 'samples': 3620928, 'steps': 18858, 'loss/train': 1.6793569326400757} 08/30/2021 16:37:07 - INFO - __main__ - Step 18860: {'lr': 0.000484161645320387, 'samples': 3621120, 'steps': 18859, 'loss/train': 1.5738416910171509} 08/30/2021 16:37:08 - INFO - __main__ - Step 18861: {'lr': 0.0004841597864431645, 'samples': 3621312, 'steps': 18860, 'loss/train': 1.579481840133667} 08/30/2021 16:37:09 - INFO - __main__ - Step 18862: {'lr': 0.00048415792746043314, 'samples': 3621504, 'steps': 18861, 'loss/train': 1.9011242389678955} 08/30/2021 16:37:10 - INFO - __main__ - Step 18863: {'lr': 0.00048415606837219383, 'samples': 3621696, 'steps': 18862, 'loss/train': 2.1082510948181152} 08/30/2021 16:37:10 - INFO - __main__ - Step 18864: {'lr': 0.00048415420917844744, 'samples': 3621888, 'steps': 18863, 'loss/train': 2.0008208751678467} 08/30/2021 16:37:10 - INFO - __main__ - Step 18865: {'lr': 0.00048415234987919474, 'samples': 3622080, 'steps': 18864, 'loss/train': 0.12366552650928497} 08/30/2021 16:37:11 - INFO - __main__ - Step 18866: {'lr': 0.0004841504904744367, 'samples': 3622272, 'steps': 18865, 'loss/train': 1.6811604499816895} 08/30/2021 16:37:11 - INFO - __main__ - Step 18867: {'lr': 0.0004841486309641739, 'samples': 3622464, 'steps': 18866, 'loss/train': 1.8319847583770752} 08/30/2021 16:37:13 - INFO - __main__ - Step 18868: {'lr': 0.00048414677134840753, 'samples': 3622656, 'steps': 18867, 'loss/train': 1.8587208986282349} 08/30/2021 16:37:13 - INFO - __main__ - Step 18869: {'lr': 0.00048414491162713814, 'samples': 3622848, 'steps': 18868, 'loss/train': 1.55882728099823} 08/30/2021 16:37:13 - INFO - __main__ - Step 18870: {'lr': 0.00048414305180036665, 'samples': 3623040, 'steps': 18869, 'loss/train': 1.6058638095855713} 08/30/2021 16:37:14 - INFO - __main__ - Step 18871: {'lr': 0.0004841411918680939, 'samples': 3623232, 'steps': 18870, 'loss/train': 1.3894546031951904} 08/30/2021 16:37:14 - INFO - __main__ - Step 18872: {'lr': 0.0004841393318303208, 'samples': 3623424, 'steps': 18871, 'loss/train': 1.9317538738250732} 08/30/2021 16:37:16 - INFO - __main__ - Step 18873: {'lr': 0.0004841374716870481, 'samples': 3623616, 'steps': 18872, 'loss/train': 2.1624057292938232} 08/30/2021 16:37:16 - INFO - __main__ - Step 18874: {'lr': 0.00048413561143827665, 'samples': 3623808, 'steps': 18873, 'loss/train': 4.072031497955322} 08/30/2021 16:37:17 - INFO - __main__ - Step 18875: {'lr': 0.00048413375108400736, 'samples': 3624000, 'steps': 18874, 'loss/train': 1.3719980716705322} 08/30/2021 16:37:17 - INFO - __main__ - Step 18876: {'lr': 0.000484131890624241, 'samples': 3624192, 'steps': 18875, 'loss/train': 2.0993733406066895} 08/30/2021 16:37:17 - INFO - __main__ - Step 18877: {'lr': 0.00048413003005897835, 'samples': 3624384, 'steps': 18876, 'loss/train': 1.4373953342437744} 08/30/2021 16:37:19 - INFO - __main__ - Step 18878: {'lr': 0.0004841281693882204, 'samples': 3624576, 'steps': 18877, 'loss/train': 1.7812221050262451} 08/30/2021 16:37:19 - INFO - __main__ - Step 18879: {'lr': 0.0004841263086119679, 'samples': 3624768, 'steps': 18878, 'loss/train': 1.3264883756637573} 08/30/2021 16:37:20 - INFO - __main__ - Step 18880: {'lr': 0.00048412444773022166, 'samples': 3624960, 'steps': 18879, 'loss/train': 1.821436882019043} 08/30/2021 16:37:20 - INFO - __main__ - Step 18881: {'lr': 0.0004841225867429826, 'samples': 3625152, 'steps': 18880, 'loss/train': 0.1224297508597374} 08/30/2021 16:37:20 - INFO - __main__ - Step 18882: {'lr': 0.0004841207256502515, 'samples': 3625344, 'steps': 18881, 'loss/train': 1.7958325147628784} 08/30/2021 16:37:22 - INFO - __main__ - Step 18883: {'lr': 0.0004841188644520292, 'samples': 3625536, 'steps': 18882, 'loss/train': 1.6555604934692383} 08/30/2021 16:37:22 - INFO - __main__ - Step 18884: {'lr': 0.0004841170031483165, 'samples': 3625728, 'steps': 18883, 'loss/train': 1.895039439201355} 08/30/2021 16:37:23 - INFO - __main__ - Step 18885: {'lr': 0.0004841151417391144, 'samples': 3625920, 'steps': 18884, 'loss/train': 1.6589775085449219} 08/30/2021 16:37:23 - INFO - __main__ - Step 18886: {'lr': 0.00048411328022442357, 'samples': 3626112, 'steps': 18885, 'loss/train': 2.0037918090820312} 08/30/2021 16:37:23 - INFO - __main__ - Step 18887: {'lr': 0.000484111418604245, 'samples': 3626304, 'steps': 18886, 'loss/train': 0.38222405314445496} 08/30/2021 16:37:24 - INFO - __main__ - Step 18888: {'lr': 0.00048410955687857926, 'samples': 3626496, 'steps': 18887, 'loss/train': 0.8166512846946716} 08/30/2021 16:37:25 - INFO - __main__ - Step 18889: {'lr': 0.0004841076950474275, 'samples': 3626688, 'steps': 18888, 'loss/train': 1.5573936700820923} 08/30/2021 16:37:26 - INFO - __main__ - Step 18890: {'lr': 0.0004841058331107904, 'samples': 3626880, 'steps': 18889, 'loss/train': 1.5806729793548584} 08/30/2021 16:37:26 - INFO - __main__ - Step 18891: {'lr': 0.00048410397106866883, 'samples': 3627072, 'steps': 18890, 'loss/train': 1.5310070514678955} 08/30/2021 16:37:26 - INFO - __main__ - Step 18892: {'lr': 0.0004841021089210636, 'samples': 3627264, 'steps': 18891, 'loss/train': 1.0836338996887207} 08/30/2021 16:37:27 - INFO - __main__ - Step 18893: {'lr': 0.0004841002466679756, 'samples': 3627456, 'steps': 18892, 'loss/train': 1.0207998752593994} 08/30/2021 16:37:28 - INFO - __main__ - Step 18894: {'lr': 0.00048409838430940556, 'samples': 3627648, 'steps': 18893, 'loss/train': 1.770282506942749} 08/30/2021 16:37:29 - INFO - __main__ - Step 18895: {'lr': 0.00048409652184535447, 'samples': 3627840, 'steps': 18894, 'loss/train': 2.0498998165130615} 08/30/2021 16:37:29 - INFO - __main__ - Step 18896: {'lr': 0.0004840946592758231, 'samples': 3628032, 'steps': 18895, 'loss/train': 1.9854480028152466} 08/30/2021 16:37:29 - INFO - __main__ - Step 18897: {'lr': 0.00048409279660081226, 'samples': 3628224, 'steps': 18896, 'loss/train': 1.1680973768234253} 08/30/2021 16:37:30 - INFO - __main__ - Step 18898: {'lr': 0.0004840909338203229, 'samples': 3628416, 'steps': 18897, 'loss/train': 1.9105874300003052} 08/30/2021 16:37:31 - INFO - __main__ - Step 18899: {'lr': 0.0004840890709343557, 'samples': 3628608, 'steps': 18898, 'loss/train': 1.7854198217391968} 08/30/2021 16:37:32 - INFO - __main__ - Step 18900: {'lr': 0.0004840872079429116, 'samples': 3628800, 'steps': 18899, 'loss/train': 1.3159809112548828} 08/30/2021 16:37:32 - INFO - __main__ - Step 18901: {'lr': 0.00048408534484599143, 'samples': 3628992, 'steps': 18900, 'loss/train': 1.999829888343811} 08/30/2021 16:37:32 - INFO - __main__ - Step 18902: {'lr': 0.00048408348164359594, 'samples': 3629184, 'steps': 18901, 'loss/train': 1.5713098049163818} 08/30/2021 16:37:33 - INFO - __main__ - Step 18903: {'lr': 0.00048408161833572613, 'samples': 3629376, 'steps': 18902, 'loss/train': 1.4454656839370728} 08/30/2021 16:37:35 - INFO - __main__ - Step 18904: {'lr': 0.0004840797549223827, 'samples': 3629568, 'steps': 18903, 'loss/train': 1.9976674318313599} 08/30/2021 16:37:35 - INFO - __main__ - Step 18905: {'lr': 0.00048407789140356654, 'samples': 3629760, 'steps': 18904, 'loss/train': 1.8277145624160767} 08/30/2021 16:37:36 - INFO - __main__ - Step 18906: {'lr': 0.00048407602777927856, 'samples': 3629952, 'steps': 18905, 'loss/train': 1.0211728811264038} 08/30/2021 16:37:36 - INFO - __main__ - Step 18907: {'lr': 0.0004840741640495195, 'samples': 3630144, 'steps': 18906, 'loss/train': 1.4919006824493408} 08/30/2021 16:37:36 - INFO - __main__ - Step 18908: {'lr': 0.0004840723002142902, 'samples': 3630336, 'steps': 18907, 'loss/train': 1.4708335399627686} 08/30/2021 16:37:37 - INFO - __main__ - Step 18909: {'lr': 0.0004840704362735916, 'samples': 3630528, 'steps': 18908, 'loss/train': 1.542413592338562} 08/30/2021 16:37:39 - INFO - __main__ - Step 18910: {'lr': 0.0004840685722274244, 'samples': 3630720, 'steps': 18909, 'loss/train': 0.1078791692852974} 08/30/2021 16:37:39 - INFO - __main__ - Step 18911: {'lr': 0.0004840667080757896, 'samples': 3630912, 'steps': 18910, 'loss/train': 1.592965006828308} 08/30/2021 16:37:40 - INFO - __main__ - Step 18912: {'lr': 0.00048406484381868786, 'samples': 3631104, 'steps': 18911, 'loss/train': 0.6894677877426147} 08/30/2021 16:37:40 - INFO - __main__ - Step 18913: {'lr': 0.0004840629794561202, 'samples': 3631296, 'steps': 18912, 'loss/train': 0.5969001054763794} 08/30/2021 16:37:41 - INFO - __main__ - Step 18914: {'lr': 0.0004840611149880873, 'samples': 3631488, 'steps': 18913, 'loss/train': 0.5913561582565308} 08/30/2021 16:37:41 - INFO - __main__ - Step 18915: {'lr': 0.0004840592504145901, 'samples': 3631680, 'steps': 18914, 'loss/train': 1.8101297616958618} 08/30/2021 16:37:42 - INFO - __main__ - Step 18916: {'lr': 0.0004840573857356294, 'samples': 3631872, 'steps': 18915, 'loss/train': 0.9657647609710693} 08/30/2021 16:37:43 - INFO - __main__ - Step 18917: {'lr': 0.0004840555209512061, 'samples': 3632064, 'steps': 18916, 'loss/train': 1.3331830501556396} 08/30/2021 16:37:43 - INFO - __main__ - Step 18918: {'lr': 0.00048405365606132096, 'samples': 3632256, 'steps': 18917, 'loss/train': 1.512233018875122} 08/30/2021 16:37:43 - INFO - __main__ - Step 18919: {'lr': 0.00048405179106597487, 'samples': 3632448, 'steps': 18918, 'loss/train': 1.2156389951705933} 08/30/2021 16:37:44 - INFO - __main__ - Step 18920: {'lr': 0.0004840499259651686, 'samples': 3632640, 'steps': 18919, 'loss/train': 1.3688234090805054} 08/30/2021 16:37:45 - INFO - __main__ - Step 18921: {'lr': 0.0004840480607589031, 'samples': 3632832, 'steps': 18920, 'loss/train': 2.3019397258758545} 08/30/2021 16:37:46 - INFO - __main__ - Step 18922: {'lr': 0.0004840461954471792, 'samples': 3633024, 'steps': 18921, 'loss/train': 1.5780038833618164} 08/30/2021 16:37:46 - INFO - __main__ - Step 18923: {'lr': 0.00048404433002999757, 'samples': 3633216, 'steps': 18922, 'loss/train': 1.473617434501648} 08/30/2021 16:37:46 - INFO - __main__ - Step 18924: {'lr': 0.0004840424645073593, 'samples': 3633408, 'steps': 18923, 'loss/train': 1.555058479309082} 08/30/2021 16:37:47 - INFO - __main__ - Step 18925: {'lr': 0.000484040598879265, 'samples': 3633600, 'steps': 18924, 'loss/train': 1.5462207794189453} 08/30/2021 16:37:48 - INFO - __main__ - Step 18926: {'lr': 0.0004840387331457157, 'samples': 3633792, 'steps': 18925, 'loss/train': 1.7636566162109375} 08/30/2021 16:37:49 - INFO - __main__ - Step 18927: {'lr': 0.00048403686730671215, 'samples': 3633984, 'steps': 18926, 'loss/train': 1.7328298091888428} 08/30/2021 16:37:49 - INFO - __main__ - Step 18928: {'lr': 0.0004840350013622552, 'samples': 3634176, 'steps': 18927, 'loss/train': 1.6066393852233887} 08/30/2021 16:37:49 - INFO - __main__ - Step 18929: {'lr': 0.0004840331353123456, 'samples': 3634368, 'steps': 18928, 'loss/train': 1.3455466032028198} 08/30/2021 16:37:50 - INFO - __main__ - Step 18930: {'lr': 0.00048403126915698435, 'samples': 3634560, 'steps': 18929, 'loss/train': 1.7716022729873657} 08/30/2021 16:37:51 - INFO - __main__ - Step 18931: {'lr': 0.00048402940289617223, 'samples': 3634752, 'steps': 18930, 'loss/train': 1.5083965063095093} 08/30/2021 16:37:52 - INFO - __main__ - Step 18932: {'lr': 0.00048402753652991007, 'samples': 3634944, 'steps': 18931, 'loss/train': 1.6436960697174072} 08/30/2021 16:37:52 - INFO - __main__ - Step 18933: {'lr': 0.0004840256700581988, 'samples': 3635136, 'steps': 18932, 'loss/train': 1.7264306545257568} 08/30/2021 16:37:52 - INFO - __main__ - Step 18934: {'lr': 0.000484023803481039, 'samples': 3635328, 'steps': 18933, 'loss/train': 2.0844295024871826} 08/30/2021 16:37:53 - INFO - __main__ - Step 18935: {'lr': 0.00048402193679843175, 'samples': 3635520, 'steps': 18934, 'loss/train': 2.012082815170288} 08/30/2021 16:37:54 - INFO - __main__ - Step 18936: {'lr': 0.00048402007001037786, 'samples': 3635712, 'steps': 18935, 'loss/train': 1.2280157804489136} 08/30/2021 16:37:55 - INFO - __main__ - Step 18937: {'lr': 0.0004840182031168781, 'samples': 3635904, 'steps': 18936, 'loss/train': 1.131327509880066} 08/30/2021 16:37:55 - INFO - __main__ - Step 18938: {'lr': 0.0004840163361179334, 'samples': 3636096, 'steps': 18937, 'loss/train': 2.4972782135009766} 08/30/2021 16:37:56 - INFO - __main__ - Step 18939: {'lr': 0.00048401446901354453, 'samples': 3636288, 'steps': 18938, 'loss/train': 1.8392916917800903} 08/30/2021 16:37:56 - INFO - __main__ - Step 18940: {'lr': 0.0004840126018037123, 'samples': 3636480, 'steps': 18939, 'loss/train': 1.055567979812622} 08/30/2021 16:37:56 - INFO - __main__ - Step 18941: {'lr': 0.0004840107344884377, 'samples': 3636672, 'steps': 18940, 'loss/train': 1.5509389638900757} 08/30/2021 16:37:58 - INFO - __main__ - Step 18942: {'lr': 0.0004840088670677214, 'samples': 3636864, 'steps': 18941, 'loss/train': 1.7684361934661865} 08/30/2021 16:37:58 - INFO - __main__ - Step 18943: {'lr': 0.0004840069995415643, 'samples': 3637056, 'steps': 18942, 'loss/train': 1.6116442680358887} 08/30/2021 16:37:58 - INFO - __main__ - Step 18944: {'lr': 0.0004840051319099673, 'samples': 3637248, 'steps': 18943, 'loss/train': 1.3261322975158691} 08/30/2021 16:37:59 - INFO - __main__ - Step 18945: {'lr': 0.0004840032641729312, 'samples': 3637440, 'steps': 18944, 'loss/train': 1.5126307010650635} 08/30/2021 16:37:59 - INFO - __main__ - Step 18946: {'lr': 0.0004840013963304568, 'samples': 3637632, 'steps': 18945, 'loss/train': 1.330876350402832} 08/30/2021 16:38:01 - INFO - __main__ - Step 18947: {'lr': 0.000483999528382545, 'samples': 3637824, 'steps': 18946, 'loss/train': 1.518810510635376} 08/30/2021 16:38:01 - INFO - __main__ - Step 18948: {'lr': 0.00048399766032919666, 'samples': 3638016, 'steps': 18947, 'loss/train': 1.6638489961624146} 08/30/2021 16:38:02 - INFO - __main__ - Step 18949: {'lr': 0.0004839957921704126, 'samples': 3638208, 'steps': 18948, 'loss/train': 1.2972757816314697} 08/30/2021 16:38:02 - INFO - __main__ - Step 18950: {'lr': 0.0004839939239061936, 'samples': 3638400, 'steps': 18949, 'loss/train': 1.5717649459838867} 08/30/2021 16:38:02 - INFO - __main__ - Step 18951: {'lr': 0.00048399205553654046, 'samples': 3638592, 'steps': 18950, 'loss/train': 2.0166611671447754} 08/30/2021 16:38:04 - INFO - __main__ - Step 18952: {'lr': 0.0004839901870614543, 'samples': 3638784, 'steps': 18951, 'loss/train': 2.096992254257202} 08/30/2021 16:38:05 - INFO - __main__ - Step 18953: {'lr': 0.0004839883184809356, 'samples': 3638976, 'steps': 18952, 'loss/train': 1.51292884349823} 08/30/2021 16:38:05 - INFO - __main__ - Step 18954: {'lr': 0.00048398644979498543, 'samples': 3639168, 'steps': 18953, 'loss/train': 1.4720566272735596} 08/30/2021 16:38:05 - INFO - __main__ - Step 18955: {'lr': 0.0004839845810036047, 'samples': 3639360, 'steps': 18954, 'loss/train': 1.8984678983688354} 08/30/2021 16:38:06 - INFO - __main__ - Step 18956: {'lr': 0.00048398271210679393, 'samples': 3639552, 'steps': 18955, 'loss/train': 1.601037621498108} 08/30/2021 16:38:06 - INFO - __main__ - Step 18957: {'lr': 0.0004839808431045543, 'samples': 3639744, 'steps': 18956, 'loss/train': 2.0644285678863525} 08/30/2021 16:38:08 - INFO - __main__ - Step 18958: {'lr': 0.00048397897399688643, 'samples': 3639936, 'steps': 18957, 'loss/train': 0.19773952662944794} 08/30/2021 16:38:09 - INFO - __main__ - Step 18959: {'lr': 0.0004839771047837913, 'samples': 3640128, 'steps': 18958, 'loss/train': 2.199984550476074} 08/30/2021 16:38:09 - INFO - __main__ - Step 18960: {'lr': 0.00048397523546526966, 'samples': 3640320, 'steps': 18959, 'loss/train': 1.8648544549942017} 08/30/2021 16:38:10 - INFO - __main__ - Step 18961: {'lr': 0.0004839733660413224, 'samples': 3640512, 'steps': 18960, 'loss/train': 0.8826211094856262} 08/30/2021 16:38:10 - INFO - __main__ - Step 18962: {'lr': 0.0004839714965119504, 'samples': 3640704, 'steps': 18961, 'loss/train': 1.3562123775482178} 08/30/2021 16:38:11 - INFO - __main__ - Step 18963: {'lr': 0.0004839696268771544, 'samples': 3640896, 'steps': 18962, 'loss/train': 1.1805273294448853} 08/30/2021 16:38:12 - INFO - __main__ - Step 18964: {'lr': 0.0004839677571369353, 'samples': 3641088, 'steps': 18963, 'loss/train': 1.6383274793624878} 08/30/2021 16:38:12 - INFO - __main__ - Step 18965: {'lr': 0.000483965887291294, 'samples': 3641280, 'steps': 18964, 'loss/train': 1.8031878471374512} 08/30/2021 16:38:13 - INFO - __main__ - Step 18966: {'lr': 0.0004839640173402312, 'samples': 3641472, 'steps': 18965, 'loss/train': 1.878609538078308} 08/30/2021 16:38:13 - INFO - __main__ - Step 18967: {'lr': 0.00048396214728374786, 'samples': 3641664, 'steps': 18966, 'loss/train': 1.4588313102722168} 08/30/2021 16:38:15 - INFO - __main__ - Step 18968: {'lr': 0.00048396027712184475, 'samples': 3641856, 'steps': 18967, 'loss/train': 1.53431236743927} 08/30/2021 16:38:15 - INFO - __main__ - Step 18969: {'lr': 0.0004839584068545228, 'samples': 3642048, 'steps': 18968, 'loss/train': 1.6313693523406982} 08/30/2021 16:38:16 - INFO - __main__ - Step 18970: {'lr': 0.0004839565364817828, 'samples': 3642240, 'steps': 18969, 'loss/train': 2.1428191661834717} 08/30/2021 16:38:16 - INFO - __main__ - Step 18971: {'lr': 0.0004839546660036256, 'samples': 3642432, 'steps': 18970, 'loss/train': 1.717660903930664} 08/30/2021 16:38:16 - INFO - __main__ - Step 18972: {'lr': 0.000483952795420052, 'samples': 3642624, 'steps': 18971, 'loss/train': 2.3953351974487305} 08/30/2021 16:38:19 - INFO - __main__ - Step 18973: {'lr': 0.0004839509247310629, 'samples': 3642816, 'steps': 18972, 'loss/train': 2.4619195461273193} 08/30/2021 16:38:19 - INFO - __main__ - Step 18974: {'lr': 0.00048394905393665913, 'samples': 3643008, 'steps': 18973, 'loss/train': 1.441680908203125} 08/30/2021 16:38:19 - INFO - __main__ - Step 18975: {'lr': 0.00048394718303684147, 'samples': 3643200, 'steps': 18974, 'loss/train': 1.2632781267166138} 08/30/2021 16:38:20 - INFO - __main__ - Step 18976: {'lr': 0.00048394531203161084, 'samples': 3643392, 'steps': 18975, 'loss/train': 1.9469889402389526} 08/30/2021 16:38:20 - INFO - __main__ - Step 18977: {'lr': 0.00048394344092096816, 'samples': 3643584, 'steps': 18976, 'loss/train': 1.5366647243499756} 08/30/2021 16:38:21 - INFO - __main__ - Step 18978: {'lr': 0.0004839415697049141, 'samples': 3643776, 'steps': 18977, 'loss/train': 1.3638979196548462} 08/30/2021 16:38:21 - INFO - __main__ - Step 18979: {'lr': 0.00048393969838344956, 'samples': 3643968, 'steps': 18978, 'loss/train': 1.0342578887939453} 08/30/2021 16:38:22 - INFO - __main__ - Step 18980: {'lr': 0.0004839378269565754, 'samples': 3644160, 'steps': 18979, 'loss/train': 0.22066383063793182} 08/30/2021 16:38:23 - INFO - __main__ - Step 18981: {'lr': 0.00048393595542429253, 'samples': 3644352, 'steps': 18980, 'loss/train': 1.4377784729003906} 08/30/2021 16:38:23 - INFO - __main__ - Step 18982: {'lr': 0.0004839340837866016, 'samples': 3644544, 'steps': 18981, 'loss/train': 1.9067206382751465} 08/30/2021 16:38:24 - INFO - __main__ - Step 18983: {'lr': 0.00048393221204350376, 'samples': 3644736, 'steps': 18982, 'loss/train': 1.786861777305603} 08/30/2021 16:38:24 - INFO - __main__ - Step 18984: {'lr': 0.0004839303401949996, 'samples': 3644928, 'steps': 18983, 'loss/train': 2.1087722778320312} 08/30/2021 16:38:25 - INFO - __main__ - Step 18985: {'lr': 0.00048392846824109, 'samples': 3645120, 'steps': 18984, 'loss/train': 1.2350329160690308} 08/30/2021 16:38:26 - INFO - __main__ - Step 18986: {'lr': 0.00048392659618177585, 'samples': 3645312, 'steps': 18985, 'loss/train': 1.221070408821106} 08/30/2021 16:38:26 - INFO - __main__ - Step 18987: {'lr': 0.000483924724017058, 'samples': 3645504, 'steps': 18986, 'loss/train': 1.5440654754638672} 08/30/2021 16:38:27 - INFO - __main__ - Step 18988: {'lr': 0.00048392285174693727, 'samples': 3645696, 'steps': 18987, 'loss/train': 1.292403221130371} 08/30/2021 16:38:27 - INFO - __main__ - Step 18989: {'lr': 0.0004839209793714146, 'samples': 3645888, 'steps': 18988, 'loss/train': 1.4480961561203003} 08/30/2021 16:38:28 - INFO - __main__ - Step 18990: {'lr': 0.00048391910689049057, 'samples': 3646080, 'steps': 18989, 'loss/train': 1.1235562562942505} 08/30/2021 16:38:29 - INFO - __main__ - Step 18991: {'lr': 0.00048391723430416634, 'samples': 3646272, 'steps': 18990, 'loss/train': 1.2940679788589478} 08/30/2021 16:38:29 - INFO - __main__ - Step 18992: {'lr': 0.00048391536161244254, 'samples': 3646464, 'steps': 18991, 'loss/train': 1.7962981462478638} 08/30/2021 16:38:29 - INFO - __main__ - Step 18993: {'lr': 0.0004839134888153202, 'samples': 3646656, 'steps': 18992, 'loss/train': 1.6466200351715088} 08/30/2021 16:38:30 - INFO - __main__ - Step 18994: {'lr': 0.00048391161591279994, 'samples': 3646848, 'steps': 18993, 'loss/train': 1.578004240989685} 08/30/2021 16:38:32 - INFO - __main__ - Step 18995: {'lr': 0.0004839097429048827, 'samples': 3647040, 'steps': 18994, 'loss/train': 1.8380944728851318} 08/30/2021 16:38:32 - INFO - __main__ - Step 18996: {'lr': 0.00048390786979156944, 'samples': 3647232, 'steps': 18995, 'loss/train': 1.4364378452301025} 08/30/2021 16:38:32 - INFO - __main__ - Step 18997: {'lr': 0.0004839059965728608, 'samples': 3647424, 'steps': 18996, 'loss/train': 3.3598239421844482} 08/30/2021 16:38:33 - INFO - __main__ - Step 18998: {'lr': 0.0004839041232487578, 'samples': 3647616, 'steps': 18997, 'loss/train': 2.0735983848571777} 08/30/2021 16:38:33 - INFO - __main__ - Step 18999: {'lr': 0.0004839022498192612, 'samples': 3647808, 'steps': 18998, 'loss/train': 1.5744572877883911} 08/30/2021 16:38:33 - INFO - __main__ - Step 19000: {'lr': 0.0004839003762843718, 'samples': 3648000, 'steps': 18999, 'loss/train': 1.8879928588867188} 08/30/2021 16:38:35 - INFO - __main__ - Step 19001: {'lr': 0.00048389850264409054, 'samples': 3648192, 'steps': 19000, 'loss/train': 0.9014919996261597} 08/30/2021 16:38:35 - INFO - __main__ - Step 19002: {'lr': 0.00048389662889841825, 'samples': 3648384, 'steps': 19001, 'loss/train': 2.4000437259674072} 08/30/2021 16:38:36 - INFO - __main__ - Step 19003: {'lr': 0.0004838947550473557, 'samples': 3648576, 'steps': 19002, 'loss/train': 1.8039371967315674} 08/30/2021 16:38:36 - INFO - __main__ - Step 19004: {'lr': 0.00048389288109090383, 'samples': 3648768, 'steps': 19003, 'loss/train': 2.0567820072174072} 08/30/2021 16:38:36 - INFO - __main__ - Step 19005: {'lr': 0.0004838910070290634, 'samples': 3648960, 'steps': 19004, 'loss/train': 1.4886016845703125} 08/30/2021 16:38:38 - INFO - __main__ - Step 19006: {'lr': 0.00048388913286183535, 'samples': 3649152, 'steps': 19005, 'loss/train': 2.1133718490600586} 08/30/2021 16:38:39 - INFO - __main__ - Step 19007: {'lr': 0.0004838872585892204, 'samples': 3649344, 'steps': 19006, 'loss/train': 1.2090160846710205} 08/30/2021 16:38:39 - INFO - __main__ - Step 19008: {'lr': 0.00048388538421121946, 'samples': 3649536, 'steps': 19007, 'loss/train': 2.146662473678589} 08/30/2021 16:38:40 - INFO - __main__ - Step 19009: {'lr': 0.00048388350972783346, 'samples': 3649728, 'steps': 19008, 'loss/train': 2.1458070278167725} 08/30/2021 16:38:40 - INFO - __main__ - Step 19010: {'lr': 0.000483881635139063, 'samples': 3649920, 'steps': 19009, 'loss/train': 1.6581511497497559} 08/30/2021 16:38:40 - INFO - __main__ - Step 19011: {'lr': 0.00048387976044490924, 'samples': 3650112, 'steps': 19010, 'loss/train': 1.9609956741333008} 08/30/2021 16:38:41 - INFO - __main__ - Step 19012: {'lr': 0.0004838778856453728, 'samples': 3650304, 'steps': 19011, 'loss/train': 1.3583651781082153} 08/30/2021 16:38:43 - INFO - __main__ - Step 19013: {'lr': 0.00048387601074045464, 'samples': 3650496, 'steps': 19012, 'loss/train': 1.2468626499176025} 08/30/2021 16:38:43 - INFO - __main__ - Step 19014: {'lr': 0.0004838741357301555, 'samples': 3650688, 'steps': 19013, 'loss/train': 1.5498229265213013} 08/30/2021 16:38:44 - INFO - __main__ - Step 19015: {'lr': 0.00048387226061447633, 'samples': 3650880, 'steps': 19014, 'loss/train': 1.8786801099777222} 08/30/2021 16:38:44 - INFO - __main__ - Step 19016: {'lr': 0.0004838703853934179, 'samples': 3651072, 'steps': 19015, 'loss/train': 1.5610238313674927} 08/30/2021 16:38:44 - INFO - __main__ - Step 19017: {'lr': 0.0004838685100669811, 'samples': 3651264, 'steps': 19016, 'loss/train': 1.8917293548583984} 08/30/2021 16:38:46 - INFO - __main__ - Step 19018: {'lr': 0.0004838666346351667, 'samples': 3651456, 'steps': 19017, 'loss/train': 2.051845073699951} 08/30/2021 16:38:46 - INFO - __main__ - Step 19019: {'lr': 0.0004838647590979757, 'samples': 3651648, 'steps': 19018, 'loss/train': 1.5275967121124268} 08/30/2021 16:38:47 - INFO - __main__ - Step 19020: {'lr': 0.00048386288345540876, 'samples': 3651840, 'steps': 19019, 'loss/train': 2.161799907684326} 08/30/2021 16:38:47 - INFO - __main__ - Step 19021: {'lr': 0.00048386100770746686, 'samples': 3652032, 'steps': 19020, 'loss/train': 1.8600828647613525} 08/30/2021 16:38:47 - INFO - __main__ - Step 19022: {'lr': 0.00048385913185415076, 'samples': 3652224, 'steps': 19021, 'loss/train': 1.7161812782287598} 08/30/2021 16:38:49 - INFO - __main__ - Step 19023: {'lr': 0.00048385725589546137, 'samples': 3652416, 'steps': 19022, 'loss/train': 1.2950397729873657} 08/30/2021 16:38:50 - INFO - __main__ - Step 19024: {'lr': 0.0004838553798313995, 'samples': 3652608, 'steps': 19023, 'loss/train': 1.843496561050415} 08/30/2021 16:38:50 - INFO - __main__ - Step 19025: {'lr': 0.000483853503661966, 'samples': 3652800, 'steps': 19024, 'loss/train': 1.6987963914871216} 08/30/2021 16:38:50 - INFO - __main__ - Step 19026: {'lr': 0.00048385162738716174, 'samples': 3652992, 'steps': 19025, 'loss/train': 1.9262787103652954} 08/30/2021 16:38:51 - INFO - __main__ - Step 19027: {'lr': 0.00048384975100698756, 'samples': 3653184, 'steps': 19026, 'loss/train': 1.5370110273361206} 08/30/2021 16:38:51 - INFO - __main__ - Step 19028: {'lr': 0.0004838478745214443, 'samples': 3653376, 'steps': 19027, 'loss/train': 0.09243328869342804} 08/30/2021 16:38:53 - INFO - __main__ - Step 19029: {'lr': 0.00048384599793053275, 'samples': 3653568, 'steps': 19028, 'loss/train': 2.0480871200561523} 08/30/2021 16:38:53 - INFO - __main__ - Step 19030: {'lr': 0.0004838441212342538, 'samples': 3653760, 'steps': 19029, 'loss/train': 1.5750621557235718} 08/30/2021 16:38:54 - INFO - __main__ - Step 19031: {'lr': 0.0004838422444326084, 'samples': 3653952, 'steps': 19030, 'loss/train': 3.643911361694336} 08/30/2021 16:38:54 - INFO - __main__ - Step 19032: {'lr': 0.0004838403675255971, 'samples': 3654144, 'steps': 19031, 'loss/train': 1.4532514810562134} 08/30/2021 16:38:54 - INFO - __main__ - Step 19033: {'lr': 0.0004838384905132211, 'samples': 3654336, 'steps': 19032, 'loss/train': 1.6092004776000977} 08/30/2021 16:38:55 - INFO - __main__ - Step 19034: {'lr': 0.000483836613395481, 'samples': 3654528, 'steps': 19033, 'loss/train': 1.7530258893966675} 08/30/2021 16:38:56 - INFO - __main__ - Step 19035: {'lr': 0.0004838347361723778, 'samples': 3654720, 'steps': 19034, 'loss/train': 0.6507481932640076} 08/30/2021 16:38:57 - INFO - __main__ - Step 19036: {'lr': 0.0004838328588439123, 'samples': 3654912, 'steps': 19035, 'loss/train': 1.0046108961105347} 08/30/2021 16:38:57 - INFO - __main__ - Step 19037: {'lr': 0.0004838309814100852, 'samples': 3655104, 'steps': 19036, 'loss/train': 2.8187057971954346} 08/30/2021 16:38:57 - INFO - __main__ - Step 19038: {'lr': 0.0004838291038708975, 'samples': 3655296, 'steps': 19037, 'loss/train': 2.971289873123169} 08/30/2021 16:38:58 - INFO - __main__ - Step 19039: {'lr': 0.00048382722622635014, 'samples': 3655488, 'steps': 19038, 'loss/train': 1.3843629360198975} 08/30/2021 16:38:59 - INFO - __main__ - Step 19040: {'lr': 0.0004838253484764437, 'samples': 3655680, 'steps': 19039, 'loss/train': 1.6307727098464966} 08/30/2021 16:39:00 - INFO - __main__ - Step 19041: {'lr': 0.0004838234706211792, 'samples': 3655872, 'steps': 19040, 'loss/train': 1.6135318279266357} 08/30/2021 16:39:00 - INFO - __main__ - Step 19042: {'lr': 0.00048382159266055746, 'samples': 3656064, 'steps': 19041, 'loss/train': 0.16198968887329102} 08/30/2021 16:39:00 - INFO - __main__ - Step 19043: {'lr': 0.0004838197145945793, 'samples': 3656256, 'steps': 19042, 'loss/train': 1.6448854207992554} 08/30/2021 16:39:01 - INFO - __main__ - Step 19044: {'lr': 0.0004838178364232456, 'samples': 3656448, 'steps': 19043, 'loss/train': 2.0197489261627197} 08/30/2021 16:39:02 - INFO - __main__ - Step 19045: {'lr': 0.00048381595814655723, 'samples': 3656640, 'steps': 19044, 'loss/train': 1.3987911939620972} 08/30/2021 16:39:03 - INFO - __main__ - Step 19046: {'lr': 0.000483814079764515, 'samples': 3656832, 'steps': 19045, 'loss/train': 1.6451157331466675} 08/30/2021 16:39:03 - INFO - __main__ - Step 19047: {'lr': 0.00048381220127711967, 'samples': 3657024, 'steps': 19046, 'loss/train': 2.3354761600494385} 08/30/2021 16:39:03 - INFO - __main__ - Step 19048: {'lr': 0.0004838103226843722, 'samples': 3657216, 'steps': 19047, 'loss/train': 1.6441980600357056} 08/30/2021 16:39:04 - INFO - __main__ - Step 19049: {'lr': 0.00048380844398627343, 'samples': 3657408, 'steps': 19048, 'loss/train': 1.3039494752883911} 08/30/2021 16:39:04 - INFO - __main__ - Step 19050: {'lr': 0.0004838065651828242, 'samples': 3657600, 'steps': 19049, 'loss/train': 1.348453402519226} 08/30/2021 16:39:06 - INFO - __main__ - Step 19051: {'lr': 0.0004838046862740253, 'samples': 3657792, 'steps': 19050, 'loss/train': 1.6213575601577759} 08/30/2021 16:39:06 - INFO - __main__ - Step 19052: {'lr': 0.0004838028072598777, 'samples': 3657984, 'steps': 19051, 'loss/train': 1.3830773830413818} 08/30/2021 16:39:06 - INFO - __main__ - Step 19053: {'lr': 0.00048380092814038204, 'samples': 3658176, 'steps': 19052, 'loss/train': 1.631980299949646} 08/30/2021 16:39:07 - INFO - __main__ - Step 19054: {'lr': 0.0004837990489155394, 'samples': 3658368, 'steps': 19053, 'loss/train': 1.7626631259918213} 08/30/2021 16:39:07 - INFO - __main__ - Step 19055: {'lr': 0.00048379716958535043, 'samples': 3658560, 'steps': 19054, 'loss/train': 1.5269496440887451} 08/30/2021 16:39:09 - INFO - __main__ - Step 19056: {'lr': 0.00048379529014981604, 'samples': 3658752, 'steps': 19055, 'loss/train': 0.27664247155189514} 08/30/2021 16:39:09 - INFO - __main__ - Step 19057: {'lr': 0.0004837934106089372, 'samples': 3658944, 'steps': 19056, 'loss/train': 1.5194077491760254} 08/30/2021 16:39:09 - INFO - __main__ - Step 19058: {'lr': 0.0004837915309627146, 'samples': 3659136, 'steps': 19057, 'loss/train': 1.365946650505066} 08/30/2021 16:39:10 - INFO - __main__ - Step 19059: {'lr': 0.00048378965121114917, 'samples': 3659328, 'steps': 19058, 'loss/train': 1.3631266355514526} 08/30/2021 16:39:10 - INFO - __main__ - Step 19060: {'lr': 0.00048378777135424166, 'samples': 3659520, 'steps': 19059, 'loss/train': 1.2037910223007202} 08/30/2021 16:39:12 - INFO - __main__ - Step 19061: {'lr': 0.0004837858913919931, 'samples': 3659712, 'steps': 19060, 'loss/train': 1.6297072172164917} 08/30/2021 16:39:12 - INFO - __main__ - Step 19062: {'lr': 0.0004837840113244042, 'samples': 3659904, 'steps': 19061, 'loss/train': 1.5092374086380005} 08/30/2021 16:39:12 - INFO - __main__ - Step 19063: {'lr': 0.00048378213115147573, 'samples': 3660096, 'steps': 19062, 'loss/train': 1.9230157136917114} 08/30/2021 16:39:13 - INFO - __main__ - Step 19064: {'lr': 0.00048378025087320877, 'samples': 3660288, 'steps': 19063, 'loss/train': 1.9381505250930786} 08/30/2021 16:39:13 - INFO - __main__ - Step 19065: {'lr': 0.0004837783704896039, 'samples': 3660480, 'steps': 19064, 'loss/train': 0.7553221583366394} 08/30/2021 16:39:15 - INFO - __main__ - Step 19066: {'lr': 0.0004837764900006623, 'samples': 3660672, 'steps': 19065, 'loss/train': 1.3389997482299805} 08/30/2021 16:39:15 - INFO - __main__ - Step 19067: {'lr': 0.0004837746094063844, 'samples': 3660864, 'steps': 19066, 'loss/train': 1.5995224714279175} 08/30/2021 16:39:16 - INFO - __main__ - Step 19068: {'lr': 0.00048377272870677135, 'samples': 3661056, 'steps': 19067, 'loss/train': 1.7355479001998901} 08/30/2021 16:39:16 - INFO - __main__ - Step 19069: {'lr': 0.000483770847901824, 'samples': 3661248, 'steps': 19068, 'loss/train': 2.67655611038208} 08/30/2021 16:39:16 - INFO - __main__ - Step 19070: {'lr': 0.000483768966991543, 'samples': 3661440, 'steps': 19069, 'loss/train': 1.287881851196289} 08/30/2021 16:39:18 - INFO - __main__ - Step 19071: {'lr': 0.0004837670859759294, 'samples': 3661632, 'steps': 19070, 'loss/train': 1.5589580535888672} 08/30/2021 16:39:18 - INFO - __main__ - Step 19072: {'lr': 0.0004837652048549839, 'samples': 3661824, 'steps': 19071, 'loss/train': 1.855506181716919} 08/30/2021 16:39:19 - INFO - __main__ - Step 19073: {'lr': 0.00048376332362870745, 'samples': 3662016, 'steps': 19072, 'loss/train': 1.6589117050170898} 08/30/2021 16:39:19 - INFO - __main__ - Step 19074: {'lr': 0.00048376144229710083, 'samples': 3662208, 'steps': 19073, 'loss/train': 1.7377173900604248} 08/30/2021 16:39:19 - INFO - __main__ - Step 19075: {'lr': 0.00048375956086016495, 'samples': 3662400, 'steps': 19074, 'loss/train': 0.11043886095285416} 08/30/2021 16:39:21 - INFO - __main__ - Step 19076: {'lr': 0.0004837576793179005, 'samples': 3662592, 'steps': 19075, 'loss/train': 2.205615997314453} 08/30/2021 16:39:22 - INFO - __main__ - Step 19077: {'lr': 0.00048375579767030854, 'samples': 3662784, 'steps': 19076, 'loss/train': 1.613686203956604} 08/30/2021 16:39:22 - INFO - __main__ - Step 19078: {'lr': 0.0004837539159173898, 'samples': 3662976, 'steps': 19077, 'loss/train': 1.8518331050872803} 08/30/2021 16:39:22 - INFO - __main__ - Step 19079: {'lr': 0.00048375203405914515, 'samples': 3663168, 'steps': 19078, 'loss/train': 0.1458100527524948} 08/30/2021 16:39:23 - INFO - __main__ - Step 19080: {'lr': 0.00048375015209557547, 'samples': 3663360, 'steps': 19079, 'loss/train': 1.805875301361084} 08/30/2021 16:39:24 - INFO - __main__ - Step 19081: {'lr': 0.00048374827002668156, 'samples': 3663552, 'steps': 19080, 'loss/train': 1.8509334325790405} 08/30/2021 16:39:25 - INFO - __main__ - Step 19082: {'lr': 0.0004837463878524643, 'samples': 3663744, 'steps': 19081, 'loss/train': 1.6861164569854736} 08/30/2021 16:39:25 - INFO - __main__ - Step 19083: {'lr': 0.0004837445055729245, 'samples': 3663936, 'steps': 19082, 'loss/train': 1.4038214683532715} 08/30/2021 16:39:25 - INFO - __main__ - Step 19084: {'lr': 0.00048374262318806306, 'samples': 3664128, 'steps': 19083, 'loss/train': 1.2989164590835571} 08/30/2021 16:39:26 - INFO - __main__ - Step 19085: {'lr': 0.00048374074069788077, 'samples': 3664320, 'steps': 19084, 'loss/train': 0.9655818939208984} 08/30/2021 16:39:27 - INFO - __main__ - Step 19086: {'lr': 0.0004837388581023785, 'samples': 3664512, 'steps': 19085, 'loss/train': 1.4404168128967285} 08/30/2021 16:39:28 - INFO - __main__ - Step 19087: {'lr': 0.0004837369754015571, 'samples': 3664704, 'steps': 19086, 'loss/train': 1.8048416376113892} 08/30/2021 16:39:28 - INFO - __main__ - Step 19088: {'lr': 0.0004837350925954175, 'samples': 3664896, 'steps': 19087, 'loss/train': 2.047614336013794} 08/30/2021 16:39:28 - INFO - __main__ - Step 19089: {'lr': 0.00048373320968396043, 'samples': 3665088, 'steps': 19088, 'loss/train': 0.8277368545532227} 08/30/2021 16:39:29 - INFO - __main__ - Step 19090: {'lr': 0.0004837313266671868, 'samples': 3665280, 'steps': 19089, 'loss/train': 1.7643955945968628} 08/30/2021 16:39:29 - INFO - __main__ - Step 19091: {'lr': 0.0004837294435450974, 'samples': 3665472, 'steps': 19090, 'loss/train': 1.066404104232788} 08/30/2021 16:39:31 - INFO - __main__ - Step 19092: {'lr': 0.00048372756031769316, 'samples': 3665664, 'steps': 19091, 'loss/train': 0.10456026345491409} 08/30/2021 16:39:31 - INFO - __main__ - Step 19093: {'lr': 0.00048372567698497487, 'samples': 3665856, 'steps': 19092, 'loss/train': 1.5527896881103516} 08/30/2021 16:39:32 - INFO - __main__ - Step 19094: {'lr': 0.0004837237935469434, 'samples': 3666048, 'steps': 19093, 'loss/train': 1.5800169706344604} 08/30/2021 16:39:32 - INFO - __main__ - Step 19095: {'lr': 0.00048372191000359955, 'samples': 3666240, 'steps': 19094, 'loss/train': 1.4646916389465332} 08/30/2021 16:39:32 - INFO - __main__ - Step 19096: {'lr': 0.00048372002635494425, 'samples': 3666432, 'steps': 19095, 'loss/train': 1.577537178993225} 08/30/2021 16:39:34 - INFO - __main__ - Step 19097: {'lr': 0.00048371814260097834, 'samples': 3666624, 'steps': 19096, 'loss/train': 1.6097098588943481} 08/30/2021 16:39:34 - INFO - __main__ - Step 19098: {'lr': 0.0004837162587417027, 'samples': 3666816, 'steps': 19097, 'loss/train': 1.6733466386795044} 08/30/2021 16:39:35 - INFO - __main__ - Step 19099: {'lr': 0.000483714374777118, 'samples': 3667008, 'steps': 19098, 'loss/train': 1.3653650283813477} 08/30/2021 16:39:35 - INFO - __main__ - Step 19100: {'lr': 0.00048371249070722525, 'samples': 3667200, 'steps': 19099, 'loss/train': 1.6094400882720947} 08/30/2021 16:39:35 - INFO - __main__ - Step 19101: {'lr': 0.0004837106065320253, 'samples': 3667392, 'steps': 19100, 'loss/train': 1.5213968753814697} 08/30/2021 16:39:37 - INFO - __main__ - Step 19102: {'lr': 0.00048370872225151886, 'samples': 3667584, 'steps': 19101, 'loss/train': 1.5737665891647339} 08/30/2021 16:39:37 - INFO - __main__ - Step 19103: {'lr': 0.0004837068378657069, 'samples': 3667776, 'steps': 19102, 'loss/train': 0.6638611555099487} 08/30/2021 16:39:38 - INFO - __main__ - Step 19104: {'lr': 0.0004837049533745903, 'samples': 3667968, 'steps': 19103, 'loss/train': 1.7117505073547363} 08/30/2021 16:39:38 - INFO - __main__ - Step 19105: {'lr': 0.00048370306877816983, 'samples': 3668160, 'steps': 19104, 'loss/train': 2.4603612422943115} 08/30/2021 16:39:38 - INFO - __main__ - Step 19106: {'lr': 0.00048370118407644637, 'samples': 3668352, 'steps': 19105, 'loss/train': 1.5029852390289307} 08/30/2021 16:39:40 - INFO - __main__ - Step 19107: {'lr': 0.0004836992992694208, 'samples': 3668544, 'steps': 19106, 'loss/train': 1.1753807067871094} 08/30/2021 16:39:40 - INFO - __main__ - Step 19108: {'lr': 0.00048369741435709383, 'samples': 3668736, 'steps': 19107, 'loss/train': 1.6933237314224243} 08/30/2021 16:39:41 - INFO - __main__ - Step 19109: {'lr': 0.0004836955293394665, 'samples': 3668928, 'steps': 19108, 'loss/train': 1.3555686473846436} 08/30/2021 16:39:41 - INFO - __main__ - Step 19110: {'lr': 0.00048369364421653953, 'samples': 3669120, 'steps': 19109, 'loss/train': 1.6328330039978027} 08/30/2021 16:39:41 - INFO - __main__ - Step 19111: {'lr': 0.00048369175898831384, 'samples': 3669312, 'steps': 19110, 'loss/train': 1.8126920461654663} 08/30/2021 16:39:43 - INFO - __main__ - Step 19112: {'lr': 0.0004836898736547902, 'samples': 3669504, 'steps': 19111, 'loss/train': 1.669182538986206} 08/30/2021 16:39:44 - INFO - __main__ - Step 19113: {'lr': 0.0004836879882159696, 'samples': 3669696, 'steps': 19112, 'loss/train': 1.6478606462478638} 08/30/2021 16:39:44 - INFO - __main__ - Step 19114: {'lr': 0.0004836861026718527, 'samples': 3669888, 'steps': 19113, 'loss/train': 2.1226742267608643} 08/30/2021 16:39:44 - INFO - __main__ - Step 19115: {'lr': 0.00048368421702244045, 'samples': 3670080, 'steps': 19114, 'loss/train': 1.5584373474121094} 08/30/2021 16:39:45 - INFO - __main__ - Step 19116: {'lr': 0.00048368233126773377, 'samples': 3670272, 'steps': 19115, 'loss/train': 1.6307731866836548} 08/30/2021 16:39:45 - INFO - __main__ - Step 19117: {'lr': 0.0004836804454077334, 'samples': 3670464, 'steps': 19116, 'loss/train': 1.074960470199585} 08/30/2021 16:39:47 - INFO - __main__ - Step 19118: {'lr': 0.0004836785594424402, 'samples': 3670656, 'steps': 19117, 'loss/train': 1.7020268440246582} 08/30/2021 16:39:47 - INFO - __main__ - Step 19119: {'lr': 0.0004836766733718551, 'samples': 3670848, 'steps': 19118, 'loss/train': 1.8478784561157227} 08/30/2021 16:39:48 - INFO - __main__ - Step 19120: {'lr': 0.0004836747871959789, 'samples': 3671040, 'steps': 19119, 'loss/train': 1.623666763305664} 08/30/2021 16:39:48 - INFO - __main__ - Step 19121: {'lr': 0.0004836729009148124, 'samples': 3671232, 'steps': 19120, 'loss/train': 1.8176316022872925} 08/30/2021 16:39:48 - INFO - __main__ - Step 19122: {'lr': 0.0004836710145283565, 'samples': 3671424, 'steps': 19121, 'loss/train': 4.032705783843994} 08/30/2021 16:39:50 - INFO - __main__ - Step 19123: {'lr': 0.0004836691280366121, 'samples': 3671616, 'steps': 19122, 'loss/train': 1.6686691045761108} 08/30/2021 16:39:51 - INFO - __main__ - Step 19124: {'lr': 0.00048366724143958, 'samples': 3671808, 'steps': 19123, 'loss/train': 1.7045818567276} 08/30/2021 16:39:51 - INFO - __main__ - Step 19125: {'lr': 0.0004836653547372609, 'samples': 3672000, 'steps': 19124, 'loss/train': 1.033792495727539} 08/30/2021 16:39:52 - INFO - __main__ - Step 19126: {'lr': 0.00048366346792965597, 'samples': 3672192, 'steps': 19125, 'loss/train': 1.7519725561141968} 08/30/2021 16:39:52 - INFO - __main__ - Step 19127: {'lr': 0.0004836615810167658, 'samples': 3672384, 'steps': 19126, 'loss/train': 1.4983408451080322} 08/30/2021 16:39:52 - INFO - __main__ - Step 19128: {'lr': 0.00048365969399859134, 'samples': 3672576, 'steps': 19127, 'loss/train': 1.1733825206756592} 08/30/2021 16:39:54 - INFO - __main__ - Step 19129: {'lr': 0.00048365780687513346, 'samples': 3672768, 'steps': 19128, 'loss/train': 0.09725673496723175} 08/30/2021 16:39:54 - INFO - __main__ - Step 19130: {'lr': 0.00048365591964639294, 'samples': 3672960, 'steps': 19129, 'loss/train': 1.7708055973052979} 08/30/2021 16:39:54 - INFO - __main__ - Step 19131: {'lr': 0.0004836540323123707, 'samples': 3673152, 'steps': 19130, 'loss/train': 1.1902272701263428} 08/30/2021 16:39:55 - INFO - __main__ - Step 19132: {'lr': 0.00048365214487306753, 'samples': 3673344, 'steps': 19131, 'loss/train': 1.6898306608200073} 08/30/2021 16:39:55 - INFO - __main__ - Step 19133: {'lr': 0.00048365025732848433, 'samples': 3673536, 'steps': 19132, 'loss/train': 1.5089027881622314} 08/30/2021 16:39:57 - INFO - __main__ - Step 19134: {'lr': 0.0004836483696786219, 'samples': 3673728, 'steps': 19133, 'loss/train': 1.7575311660766602} 08/30/2021 16:39:57 - INFO - __main__ - Step 19135: {'lr': 0.00048364648192348117, 'samples': 3673920, 'steps': 19134, 'loss/train': 2.394428253173828} 08/30/2021 16:39:58 - INFO - __main__ - Step 19136: {'lr': 0.0004836445940630629, 'samples': 3674112, 'steps': 19135, 'loss/train': 1.6285349130630493} 08/30/2021 16:39:58 - INFO - __main__ - Step 19137: {'lr': 0.0004836427060973679, 'samples': 3674304, 'steps': 19136, 'loss/train': 1.4491521120071411} 08/30/2021 16:39:58 - INFO - __main__ - Step 19138: {'lr': 0.00048364081802639724, 'samples': 3674496, 'steps': 19137, 'loss/train': 1.5877060890197754} 08/30/2021 16:40:00 - INFO - __main__ - Step 19139: {'lr': 0.00048363892985015157, 'samples': 3674688, 'steps': 19138, 'loss/train': 1.4455280303955078} 08/30/2021 16:40:00 - INFO - __main__ - Step 19140: {'lr': 0.00048363704156863187, 'samples': 3674880, 'steps': 19139, 'loss/train': 1.3501614332199097} 08/30/2021 16:40:01 - INFO - __main__ - Step 19141: {'lr': 0.0004836351531818388, 'samples': 3675072, 'steps': 19140, 'loss/train': 1.4317426681518555} 08/30/2021 16:40:01 - INFO - __main__ - Step 19142: {'lr': 0.00048363326468977343, 'samples': 3675264, 'steps': 19141, 'loss/train': 1.8610998392105103} 08/30/2021 16:40:01 - INFO - __main__ - Step 19143: {'lr': 0.00048363137609243654, 'samples': 3675456, 'steps': 19142, 'loss/train': 1.4787158966064453} 08/30/2021 16:40:03 - INFO - __main__ - Step 19144: {'lr': 0.0004836294873898289, 'samples': 3675648, 'steps': 19143, 'loss/train': 1.950890064239502} 08/30/2021 16:40:03 - INFO - __main__ - Step 19145: {'lr': 0.00048362759858195146, 'samples': 3675840, 'steps': 19144, 'loss/train': 1.7649948596954346} 08/30/2021 16:40:04 - INFO - __main__ - Step 19146: {'lr': 0.0004836257096688049, 'samples': 3676032, 'steps': 19145, 'loss/train': 1.7138363122940063} 08/30/2021 16:40:04 - INFO - __main__ - Step 19147: {'lr': 0.00048362382065039034, 'samples': 3676224, 'steps': 19146, 'loss/train': 1.4875048398971558} 08/30/2021 16:40:04 - INFO - __main__ - Step 19148: {'lr': 0.00048362193152670847, 'samples': 3676416, 'steps': 19147, 'loss/train': 1.2919530868530273} 08/30/2021 16:40:06 - INFO - __main__ - Step 19149: {'lr': 0.0004836200422977601, 'samples': 3676608, 'steps': 19148, 'loss/train': 1.6786713600158691} 08/30/2021 16:40:06 - INFO - __main__ - Step 19150: {'lr': 0.00048361815296354624, 'samples': 3676800, 'steps': 19149, 'loss/train': 1.4627530574798584} 08/30/2021 16:40:07 - INFO - __main__ - Step 19151: {'lr': 0.00048361626352406756, 'samples': 3676992, 'steps': 19150, 'loss/train': 1.4496657848358154} 08/30/2021 16:40:07 - INFO - __main__ - Step 19152: {'lr': 0.00048361437397932504, 'samples': 3677184, 'steps': 19151, 'loss/train': 1.9575152397155762} 08/30/2021 16:40:07 - INFO - __main__ - Step 19153: {'lr': 0.0004836124843293195, 'samples': 3677376, 'steps': 19152, 'loss/train': 1.3367133140563965} 08/30/2021 16:40:08 - INFO - __main__ - Step 19154: {'lr': 0.00048361059457405176, 'samples': 3677568, 'steps': 19153, 'loss/train': 1.7624095678329468} 08/30/2021 16:40:09 - INFO - __main__ - Step 19155: {'lr': 0.0004836087047135227, 'samples': 3677760, 'steps': 19154, 'loss/train': 1.8370709419250488} 08/30/2021 16:40:10 - INFO - __main__ - Step 19156: {'lr': 0.0004836068147477331, 'samples': 3677952, 'steps': 19155, 'loss/train': 1.474143385887146} 08/30/2021 16:40:10 - INFO - __main__ - Step 19157: {'lr': 0.0004836049246766839, 'samples': 3678144, 'steps': 19156, 'loss/train': 0.8988378643989563} 08/30/2021 16:40:10 - INFO - __main__ - Step 19158: {'lr': 0.000483603034500376, 'samples': 3678336, 'steps': 19157, 'loss/train': 1.754389762878418} 08/30/2021 16:40:11 - INFO - __main__ - Step 19159: {'lr': 0.0004836011442188101, 'samples': 3678528, 'steps': 19158, 'loss/train': 0.9265342950820923} 08/30/2021 16:40:12 - INFO - __main__ - Step 19160: {'lr': 0.00048359925383198714, 'samples': 3678720, 'steps': 19159, 'loss/train': 1.2509101629257202} 08/30/2021 16:40:13 - INFO - __main__ - Step 19161: {'lr': 0.000483597363339908, 'samples': 3678912, 'steps': 19160, 'loss/train': 1.1521157026290894} 08/30/2021 16:40:13 - INFO - __main__ - Step 19162: {'lr': 0.0004835954727425734, 'samples': 3679104, 'steps': 19161, 'loss/train': 2.0359926223754883} 08/30/2021 16:40:13 - INFO - __main__ - Step 19163: {'lr': 0.0004835935820399844, 'samples': 3679296, 'steps': 19162, 'loss/train': 1.5492124557495117} 08/30/2021 16:40:14 - INFO - __main__ - Step 19164: {'lr': 0.0004835916912321417, 'samples': 3679488, 'steps': 19163, 'loss/train': 1.642147421836853} 08/30/2021 16:40:15 - INFO - __main__ - Step 19165: {'lr': 0.0004835898003190462, 'samples': 3679680, 'steps': 19164, 'loss/train': 1.559041142463684} 08/30/2021 16:40:16 - INFO - __main__ - Step 19166: {'lr': 0.00048358790930069876, 'samples': 3679872, 'steps': 19165, 'loss/train': 1.1350476741790771} 08/30/2021 16:40:16 - INFO - __main__ - Step 19167: {'lr': 0.0004835860181771001, 'samples': 3680064, 'steps': 19166, 'loss/train': 1.5662000179290771} 08/30/2021 16:40:17 - INFO - __main__ - Step 19168: {'lr': 0.0004835841269482513, 'samples': 3680256, 'steps': 19167, 'loss/train': 0.23353731632232666} 08/30/2021 16:40:17 - INFO - __main__ - Step 19169: {'lr': 0.00048358223561415306, 'samples': 3680448, 'steps': 19168, 'loss/train': 2.1290228366851807} 08/30/2021 16:40:18 - INFO - __main__ - Step 19170: {'lr': 0.0004835803441748062, 'samples': 3680640, 'steps': 19169, 'loss/train': 2.134377956390381} 08/30/2021 16:40:19 - INFO - __main__ - Step 19171: {'lr': 0.0004835784526302117, 'samples': 3680832, 'steps': 19170, 'loss/train': 1.7741402387619019} 08/30/2021 16:40:19 - INFO - __main__ - Step 19172: {'lr': 0.0004835765609803704, 'samples': 3681024, 'steps': 19171, 'loss/train': 1.4562523365020752} 08/30/2021 16:40:20 - INFO - __main__ - Step 19173: {'lr': 0.00048357466922528306, 'samples': 3681216, 'steps': 19172, 'loss/train': 1.050406813621521} 08/30/2021 16:40:20 - INFO - __main__ - Step 19174: {'lr': 0.00048357277736495055, 'samples': 3681408, 'steps': 19173, 'loss/train': 1.797304391860962} 08/30/2021 16:40:22 - INFO - __main__ - Step 19175: {'lr': 0.0004835708853993738, 'samples': 3681600, 'steps': 19174, 'loss/train': 1.1651562452316284} 08/30/2021 16:40:22 - INFO - __main__ - Step 19176: {'lr': 0.0004835689933285536, 'samples': 3681792, 'steps': 19175, 'loss/train': 1.6475266218185425} 08/30/2021 16:40:22 - INFO - __main__ - Step 19177: {'lr': 0.0004835671011524908, 'samples': 3681984, 'steps': 19176, 'loss/train': 1.2482472658157349} 08/30/2021 16:40:23 - INFO - __main__ - Step 19178: {'lr': 0.0004835652088711863, 'samples': 3682176, 'steps': 19177, 'loss/train': 1.5967295169830322} 08/30/2021 16:40:23 - INFO - __main__ - Step 19179: {'lr': 0.0004835633164846409, 'samples': 3682368, 'steps': 19178, 'loss/train': 1.1644779443740845} 08/30/2021 16:40:23 - INFO - __main__ - Step 19180: {'lr': 0.00048356142399285545, 'samples': 3682560, 'steps': 19179, 'loss/train': 0.6553381085395813} 08/30/2021 16:40:25 - INFO - __main__ - Step 19181: {'lr': 0.00048355953139583087, 'samples': 3682752, 'steps': 19180, 'loss/train': 2.0194222927093506} 08/30/2021 16:40:26 - INFO - __main__ - Step 19182: {'lr': 0.00048355763869356794, 'samples': 3682944, 'steps': 19181, 'loss/train': 1.7708877325057983} 08/30/2021 16:40:26 - INFO - __main__ - Step 19183: {'lr': 0.0004835557458860675, 'samples': 3683136, 'steps': 19182, 'loss/train': 2.164074659347534} 08/30/2021 16:40:27 - INFO - __main__ - Step 19184: {'lr': 0.00048355385297333054, 'samples': 3683328, 'steps': 19183, 'loss/train': 2.01297926902771} 08/30/2021 16:40:27 - INFO - __main__ - Step 19185: {'lr': 0.0004835519599553578, 'samples': 3683520, 'steps': 19184, 'loss/train': 0.9082038402557373} 08/30/2021 16:40:28 - INFO - __main__ - Step 19186: {'lr': 0.0004835500668321501, 'samples': 3683712, 'steps': 19185, 'loss/train': 1.8561290502548218} 08/30/2021 16:40:29 - INFO - __main__ - Step 19187: {'lr': 0.0004835481736037084, 'samples': 3683904, 'steps': 19186, 'loss/train': 1.6833256483078003} 08/30/2021 16:40:29 - INFO - __main__ - Step 19188: {'lr': 0.0004835462802700334, 'samples': 3684096, 'steps': 19187, 'loss/train': 0.865152895450592} 08/30/2021 16:40:30 - INFO - __main__ - Step 19189: {'lr': 0.00048354438683112614, 'samples': 3684288, 'steps': 19188, 'loss/train': 1.5439050197601318} 08/30/2021 16:40:30 - INFO - __main__ - Step 19190: {'lr': 0.00048354249328698743, 'samples': 3684480, 'steps': 19189, 'loss/train': 1.1552523374557495} 08/30/2021 16:40:32 - INFO - __main__ - Step 19191: {'lr': 0.000483540599637618, 'samples': 3684672, 'steps': 19190, 'loss/train': 1.3549734354019165} 08/30/2021 16:40:32 - INFO - __main__ - Step 19192: {'lr': 0.00048353870588301875, 'samples': 3684864, 'steps': 19191, 'loss/train': 1.8058332204818726} 08/30/2021 16:40:32 - INFO - __main__ - Step 19193: {'lr': 0.00048353681202319056, 'samples': 3685056, 'steps': 19192, 'loss/train': 1.5506209135055542} 08/30/2021 16:40:33 - INFO - __main__ - Step 19194: {'lr': 0.0004835349180581343, 'samples': 3685248, 'steps': 19193, 'loss/train': 1.9190616607666016} 08/30/2021 16:40:33 - INFO - __main__ - Step 19195: {'lr': 0.0004835330239878509, 'samples': 3685440, 'steps': 19194, 'loss/train': 1.884497880935669} 08/30/2021 16:40:34 - INFO - __main__ - Step 19196: {'lr': 0.00048353112981234104, 'samples': 3685632, 'steps': 19195, 'loss/train': 2.119391441345215} 08/30/2021 16:40:35 - INFO - __main__ - Step 19197: {'lr': 0.0004835292355316057, 'samples': 3685824, 'steps': 19196, 'loss/train': 1.1468201875686646} 08/30/2021 16:40:35 - INFO - __main__ - Step 19198: {'lr': 0.0004835273411456456, 'samples': 3686016, 'steps': 19197, 'loss/train': 1.3540319204330444} 08/30/2021 16:40:36 - INFO - __main__ - Step 19199: {'lr': 0.00048352544665446174, 'samples': 3686208, 'steps': 19198, 'loss/train': 1.6521283388137817} 08/30/2021 16:40:36 - INFO - __main__ - Step 19200: {'lr': 0.000483523552058055, 'samples': 3686400, 'steps': 19199, 'loss/train': 1.589746117591858} 08/30/2021 16:40:37 - INFO - __main__ - Step 19201: {'lr': 0.00048352165735642607, 'samples': 3686592, 'steps': 19200, 'loss/train': 1.7299714088439941} 08/30/2021 16:40:38 - INFO - __main__ - Step 19202: {'lr': 0.00048351976254957585, 'samples': 3686784, 'steps': 19201, 'loss/train': 1.8458266258239746} 08/30/2021 16:40:38 - INFO - __main__ - Step 19203: {'lr': 0.0004835178676375053, 'samples': 3686976, 'steps': 19202, 'loss/train': 1.3130806684494019} 08/30/2021 16:40:39 - INFO - __main__ - Step 19204: {'lr': 0.0004835159726202151, 'samples': 3687168, 'steps': 19203, 'loss/train': 0.9123445153236389} 08/30/2021 16:40:39 - INFO - __main__ - Step 19205: {'lr': 0.0004835140774977063, 'samples': 3687360, 'steps': 19204, 'loss/train': 2.004091739654541} 08/30/2021 16:40:41 - INFO - __main__ - Step 19206: {'lr': 0.0004835121822699796, 'samples': 3687552, 'steps': 19205, 'loss/train': 1.6181484460830688} 08/30/2021 16:40:41 - INFO - __main__ - Step 19207: {'lr': 0.000483510286937036, 'samples': 3687744, 'steps': 19206, 'loss/train': 1.237630844116211} 08/30/2021 16:40:42 - INFO - __main__ - Step 19208: {'lr': 0.0004835083914988762, 'samples': 3687936, 'steps': 19207, 'loss/train': 1.074430227279663} 08/30/2021 16:40:42 - INFO - __main__ - Step 19209: {'lr': 0.0004835064959555011, 'samples': 3688128, 'steps': 19208, 'loss/train': 1.427473783493042} 08/30/2021 16:40:42 - INFO - __main__ - Step 19210: {'lr': 0.00048350460030691165, 'samples': 3688320, 'steps': 19209, 'loss/train': 1.7300118207931519} 08/30/2021 16:40:43 - INFO - __main__ - Step 19211: {'lr': 0.00048350270455310864, 'samples': 3688512, 'steps': 19210, 'loss/train': 1.803452730178833} 08/30/2021 16:40:44 - INFO - __main__ - Step 19212: {'lr': 0.00048350080869409285, 'samples': 3688704, 'steps': 19211, 'loss/train': 1.4562078714370728} 08/30/2021 16:40:45 - INFO - __main__ - Step 19213: {'lr': 0.0004834989127298652, 'samples': 3688896, 'steps': 19212, 'loss/train': 1.6275389194488525} 08/30/2021 16:40:45 - INFO - __main__ - Step 19214: {'lr': 0.00048349701666042656, 'samples': 3689088, 'steps': 19213, 'loss/train': 2.423234462738037} 08/30/2021 16:40:45 - INFO - __main__ - Step 19215: {'lr': 0.00048349512048577784, 'samples': 3689280, 'steps': 19214, 'loss/train': 0.1250191479921341} 08/30/2021 16:40:46 - INFO - __main__ - Step 19216: {'lr': 0.00048349322420591966, 'samples': 3689472, 'steps': 19215, 'loss/train': 1.613912582397461} 08/30/2021 16:40:47 - INFO - __main__ - Step 19217: {'lr': 0.00048349132782085316, 'samples': 3689664, 'steps': 19216, 'loss/train': 1.6297813653945923} 08/30/2021 16:40:48 - INFO - __main__ - Step 19218: {'lr': 0.00048348943133057903, 'samples': 3689856, 'steps': 19217, 'loss/train': 1.4121403694152832} 08/30/2021 16:40:48 - INFO - __main__ - Step 19219: {'lr': 0.0004834875347350982, 'samples': 3690048, 'steps': 19218, 'loss/train': 1.678435206413269} 08/30/2021 16:40:48 - INFO - __main__ - Step 19220: {'lr': 0.00048348563803441146, 'samples': 3690240, 'steps': 19219, 'loss/train': 1.1719179153442383} 08/30/2021 16:40:49 - INFO - __main__ - Step 19221: {'lr': 0.0004834837412285197, 'samples': 3690432, 'steps': 19220, 'loss/train': 1.373894453048706} 08/30/2021 16:40:50 - INFO - __main__ - Step 19222: {'lr': 0.00048348184431742377, 'samples': 3690624, 'steps': 19221, 'loss/train': 1.4711549282073975} 08/30/2021 16:40:51 - INFO - __main__ - Step 19223: {'lr': 0.00048347994730112457, 'samples': 3690816, 'steps': 19222, 'loss/train': 1.4518851041793823} 08/30/2021 16:40:51 - INFO - __main__ - Step 19224: {'lr': 0.00048347805017962274, 'samples': 3691008, 'steps': 19223, 'loss/train': 1.7468440532684326} 08/30/2021 16:40:51 - INFO - __main__ - Step 19225: {'lr': 0.00048347615295291947, 'samples': 3691200, 'steps': 19224, 'loss/train': 1.2006101608276367} 08/30/2021 16:40:52 - INFO - __main__ - Step 19226: {'lr': 0.0004834742556210154, 'samples': 3691392, 'steps': 19225, 'loss/train': 1.5260684490203857} 08/30/2021 16:40:53 - INFO - __main__ - Step 19227: {'lr': 0.00048347235818391144, 'samples': 3691584, 'steps': 19226, 'loss/train': 1.6461853981018066} 08/30/2021 16:40:54 - INFO - __main__ - Step 19228: {'lr': 0.0004834704606416084, 'samples': 3691776, 'steps': 19227, 'loss/train': 1.7791305780410767} 08/30/2021 16:40:54 - INFO - __main__ - Step 19229: {'lr': 0.00048346856299410725, 'samples': 3691968, 'steps': 19228, 'loss/train': 1.5573664903640747} 08/30/2021 16:40:54 - INFO - __main__ - Step 19230: {'lr': 0.0004834666652414087, 'samples': 3692160, 'steps': 19229, 'loss/train': 1.4086616039276123} 08/30/2021 16:40:55 - INFO - __main__ - Step 19231: {'lr': 0.0004834647673835137, 'samples': 3692352, 'steps': 19230, 'loss/train': 1.5888431072235107} 08/30/2021 16:40:57 - INFO - __main__ - Step 19232: {'lr': 0.00048346286942042307, 'samples': 3692544, 'steps': 19231, 'loss/train': 1.8565961122512817} 08/30/2021 16:40:57 - INFO - __main__ - Step 19233: {'lr': 0.0004834609713521377, 'samples': 3692736, 'steps': 19232, 'loss/train': 1.3755172491073608} 08/30/2021 16:40:58 - INFO - __main__ - Step 19234: {'lr': 0.0004834590731786584, 'samples': 3692928, 'steps': 19233, 'loss/train': 2.0674779415130615} 08/30/2021 16:40:58 - INFO - __main__ - Step 19235: {'lr': 0.000483457174899986, 'samples': 3693120, 'steps': 19234, 'loss/train': 1.592346429824829} 08/30/2021 16:40:58 - INFO - __main__ - Step 19236: {'lr': 0.00048345527651612145, 'samples': 3693312, 'steps': 19235, 'loss/train': 1.53139066696167} 08/30/2021 16:41:00 - INFO - __main__ - Step 19237: {'lr': 0.00048345337802706555, 'samples': 3693504, 'steps': 19236, 'loss/train': 1.984649419784546} 08/30/2021 16:41:00 - INFO - __main__ - Step 19238: {'lr': 0.0004834514794328192, 'samples': 3693696, 'steps': 19237, 'loss/train': 1.4567769765853882} 08/30/2021 16:41:01 - INFO - __main__ - Step 19239: {'lr': 0.00048344958073338315, 'samples': 3693888, 'steps': 19238, 'loss/train': 1.2409563064575195} 08/30/2021 16:41:01 - INFO - __main__ - Step 19240: {'lr': 0.00048344768192875833, 'samples': 3694080, 'steps': 19239, 'loss/train': 1.451059341430664} 08/30/2021 16:41:01 - INFO - __main__ - Step 19241: {'lr': 0.00048344578301894557, 'samples': 3694272, 'steps': 19240, 'loss/train': 1.528473973274231} 08/30/2021 16:41:03 - INFO - __main__ - Step 19242: {'lr': 0.0004834438840039458, 'samples': 3694464, 'steps': 19241, 'loss/train': 1.8752729892730713} 08/30/2021 16:41:03 - INFO - __main__ - Step 19243: {'lr': 0.0004834419848837598, 'samples': 3694656, 'steps': 19242, 'loss/train': 1.4833667278289795} 08/30/2021 16:41:03 - INFO - __main__ - Step 19244: {'lr': 0.00048344008565838844, 'samples': 3694848, 'steps': 19243, 'loss/train': 1.3282593488693237} 08/30/2021 16:41:04 - INFO - __main__ - Step 19245: {'lr': 0.00048343818632783255, 'samples': 3695040, 'steps': 19244, 'loss/train': 1.71040678024292} 08/30/2021 16:41:04 - INFO - __main__ - Step 19246: {'lr': 0.00048343628689209305, 'samples': 3695232, 'steps': 19245, 'loss/train': 1.2799099683761597} 08/30/2021 16:41:06 - INFO - __main__ - Step 19247: {'lr': 0.00048343438735117076, 'samples': 3695424, 'steps': 19246, 'loss/train': 1.4637094736099243} 08/30/2021 16:41:06 - INFO - __main__ - Step 19248: {'lr': 0.00048343248770506655, 'samples': 3695616, 'steps': 19247, 'loss/train': 1.267026424407959} 08/30/2021 16:41:06 - INFO - __main__ - Step 19249: {'lr': 0.0004834305879537812, 'samples': 3695808, 'steps': 19248, 'loss/train': 1.6086654663085938} 08/30/2021 16:41:07 - INFO - __main__ - Step 19250: {'lr': 0.00048342868809731567, 'samples': 3696000, 'steps': 19249, 'loss/train': 1.593589425086975} 08/30/2021 16:41:07 - INFO - __main__ - Step 19251: {'lr': 0.0004834267881356708, 'samples': 3696192, 'steps': 19250, 'loss/train': 2.4772422313690186} 08/30/2021 16:41:09 - INFO - __main__ - Step 19252: {'lr': 0.0004834248880688474, 'samples': 3696384, 'steps': 19251, 'loss/train': 1.9250917434692383} 08/30/2021 16:41:09 - INFO - __main__ - Step 19253: {'lr': 0.00048342298789684637, 'samples': 3696576, 'steps': 19252, 'loss/train': 0.587297797203064} 08/30/2021 16:41:10 - INFO - __main__ - Step 19254: {'lr': 0.0004834210876196685, 'samples': 3696768, 'steps': 19253, 'loss/train': 0.7421675324440002} 08/30/2021 16:41:10 - INFO - __main__ - Step 19255: {'lr': 0.0004834191872373147, 'samples': 3696960, 'steps': 19254, 'loss/train': 1.430770993232727} 08/30/2021 16:41:10 - INFO - __main__ - Step 19256: {'lr': 0.0004834172867497858, 'samples': 3697152, 'steps': 19255, 'loss/train': 1.7474435567855835} 08/30/2021 16:41:11 - INFO - __main__ - Step 19257: {'lr': 0.0004834153861570827, 'samples': 3697344, 'steps': 19256, 'loss/train': 1.3884469270706177} 08/30/2021 16:41:12 - INFO - __main__ - Step 19258: {'lr': 0.00048341348545920623, 'samples': 3697536, 'steps': 19257, 'loss/train': 1.7233219146728516} 08/30/2021 16:41:13 - INFO - __main__ - Step 19259: {'lr': 0.0004834115846561572, 'samples': 3697728, 'steps': 19258, 'loss/train': 1.4816497564315796} 08/30/2021 16:41:13 - INFO - __main__ - Step 19260: {'lr': 0.0004834096837479366, 'samples': 3697920, 'steps': 19259, 'loss/train': 1.445310115814209} 08/30/2021 16:41:13 - INFO - __main__ - Step 19261: {'lr': 0.00048340778273454514, 'samples': 3698112, 'steps': 19260, 'loss/train': 1.3448522090911865} 08/30/2021 16:41:14 - INFO - __main__ - Step 19262: {'lr': 0.00048340588161598373, 'samples': 3698304, 'steps': 19261, 'loss/train': 1.6510472297668457} 08/30/2021 16:41:15 - INFO - __main__ - Step 19263: {'lr': 0.00048340398039225325, 'samples': 3698496, 'steps': 19262, 'loss/train': 1.1248397827148438} 08/30/2021 16:41:16 - INFO - __main__ - Step 19264: {'lr': 0.0004834020790633545, 'samples': 3698688, 'steps': 19263, 'loss/train': 1.4149553775787354} 08/30/2021 16:41:16 - INFO - __main__ - Step 19265: {'lr': 0.00048340017762928843, 'samples': 3698880, 'steps': 19264, 'loss/train': 1.1894426345825195} 08/30/2021 16:41:16 - INFO - __main__ - Step 19266: {'lr': 0.00048339827609005583, 'samples': 3699072, 'steps': 19265, 'loss/train': 1.9458779096603394} 08/30/2021 16:41:17 - INFO - __main__ - Step 19267: {'lr': 0.00048339637444565756, 'samples': 3699264, 'steps': 19266, 'loss/train': 1.5638084411621094} 08/30/2021 16:41:18 - INFO - __main__ - Step 19268: {'lr': 0.0004833944726960945, 'samples': 3699456, 'steps': 19267, 'loss/train': 1.2100439071655273} 08/30/2021 16:41:19 - INFO - __main__ - Step 19269: {'lr': 0.00048339257084136747, 'samples': 3699648, 'steps': 19268, 'loss/train': 1.7518751621246338} 08/30/2021 16:41:19 - INFO - __main__ - Step 19270: {'lr': 0.0004833906688814774, 'samples': 3699840, 'steps': 19269, 'loss/train': 1.656874179840088} 08/30/2021 16:41:19 - INFO - __main__ - Step 19271: {'lr': 0.00048338876681642504, 'samples': 3700032, 'steps': 19270, 'loss/train': 1.2396714687347412} 08/30/2021 16:41:20 - INFO - __main__ - Step 19272: {'lr': 0.0004833868646462113, 'samples': 3700224, 'steps': 19271, 'loss/train': 1.0070147514343262} 08/30/2021 16:41:21 - INFO - __main__ - Step 19273: {'lr': 0.00048338496237083705, 'samples': 3700416, 'steps': 19272, 'loss/train': 1.6314671039581299} 08/30/2021 16:41:22 - INFO - __main__ - Step 19274: {'lr': 0.00048338305999030313, 'samples': 3700608, 'steps': 19273, 'loss/train': 1.4817777872085571} 08/30/2021 16:41:22 - INFO - __main__ - Step 19275: {'lr': 0.00048338115750461044, 'samples': 3700800, 'steps': 19274, 'loss/train': 1.095033049583435} 08/30/2021 16:41:22 - INFO - __main__ - Step 19276: {'lr': 0.0004833792549137598, 'samples': 3700992, 'steps': 19275, 'loss/train': 1.7891143560409546} 08/30/2021 16:41:23 - INFO - __main__ - Step 19277: {'lr': 0.00048337735221775204, 'samples': 3701184, 'steps': 19276, 'loss/train': 1.3591951131820679} 08/30/2021 16:41:23 - INFO - __main__ - Step 19278: {'lr': 0.000483375449416588, 'samples': 3701376, 'steps': 19277, 'loss/train': 1.4019490480422974} 08/30/2021 16:41:25 - INFO - __main__ - Step 19279: {'lr': 0.0004833735465102687, 'samples': 3701568, 'steps': 19278, 'loss/train': 2.0010457038879395} 08/30/2021 16:41:25 - INFO - __main__ - Step 19280: {'lr': 0.0004833716434987948, 'samples': 3701760, 'steps': 19279, 'loss/train': 1.1725772619247437} 08/30/2021 16:41:25 - INFO - __main__ - Step 19281: {'lr': 0.0004833697403821672, 'samples': 3701952, 'steps': 19280, 'loss/train': 1.2886343002319336} 08/30/2021 16:41:26 - INFO - __main__ - Step 19282: {'lr': 0.0004833678371603869, 'samples': 3702144, 'steps': 19281, 'loss/train': 1.4475995302200317} 08/30/2021 16:41:26 - INFO - __main__ - Step 19283: {'lr': 0.0004833659338334546, 'samples': 3702336, 'steps': 19282, 'loss/train': 1.569151520729065} 08/30/2021 16:41:28 - INFO - __main__ - Step 19284: {'lr': 0.0004833640304013712, 'samples': 3702528, 'steps': 19283, 'loss/train': 1.0333819389343262} 08/30/2021 16:41:28 - INFO - __main__ - Step 19285: {'lr': 0.0004833621268641376, 'samples': 3702720, 'steps': 19284, 'loss/train': 1.674288272857666} 08/30/2021 16:41:28 - INFO - __main__ - Step 19286: {'lr': 0.0004833602232217546, 'samples': 3702912, 'steps': 19285, 'loss/train': 1.4194025993347168} 08/30/2021 16:41:29 - INFO - __main__ - Step 19287: {'lr': 0.0004833583194742231, 'samples': 3703104, 'steps': 19286, 'loss/train': 1.5545814037322998} 08/30/2021 16:41:29 - INFO - __main__ - Step 19288: {'lr': 0.00048335641562154396, 'samples': 3703296, 'steps': 19287, 'loss/train': 1.0568838119506836} 08/30/2021 16:41:31 - INFO - __main__ - Step 19289: {'lr': 0.00048335451166371803, 'samples': 3703488, 'steps': 19288, 'loss/train': 2.0425543785095215} 08/30/2021 16:41:32 - INFO - __main__ - Step 19290: {'lr': 0.0004833526076007461, 'samples': 3703680, 'steps': 19289, 'loss/train': 1.287030816078186} 08/30/2021 16:41:32 - INFO - __main__ - Step 19291: {'lr': 0.0004833507034326291, 'samples': 3703872, 'steps': 19290, 'loss/train': 1.7177244424819946} 08/30/2021 16:41:32 - INFO - __main__ - Step 19292: {'lr': 0.0004833487991593679, 'samples': 3704064, 'steps': 19291, 'loss/train': 1.2387974262237549} 08/30/2021 16:41:33 - INFO - __main__ - Step 19293: {'lr': 0.0004833468947809633, 'samples': 3704256, 'steps': 19292, 'loss/train': 1.8201804161071777} 08/30/2021 16:41:34 - INFO - __main__ - Step 19294: {'lr': 0.0004833449902974162, 'samples': 3704448, 'steps': 19293, 'loss/train': 1.149401068687439} 08/30/2021 16:41:35 - INFO - __main__ - Step 19295: {'lr': 0.00048334308570872745, 'samples': 3704640, 'steps': 19294, 'loss/train': 2.3005709648132324} 08/30/2021 16:41:35 - INFO - __main__ - Step 19296: {'lr': 0.00048334118101489793, 'samples': 3704832, 'steps': 19295, 'loss/train': 1.070224642753601} 08/30/2021 16:41:35 - INFO - __main__ - Step 19297: {'lr': 0.00048333927621592844, 'samples': 3705024, 'steps': 19296, 'loss/train': 1.6150513887405396} 08/30/2021 16:41:36 - INFO - __main__ - Step 19298: {'lr': 0.00048333737131181986, 'samples': 3705216, 'steps': 19297, 'loss/train': 1.8145430088043213} 08/30/2021 16:41:36 - INFO - __main__ - Step 19299: {'lr': 0.00048333546630257315, 'samples': 3705408, 'steps': 19298, 'loss/train': 1.3970966339111328} 08/30/2021 16:41:38 - INFO - __main__ - Step 19300: {'lr': 0.000483333561188189, 'samples': 3705600, 'steps': 19299, 'loss/train': 0.6124410033226013} 08/30/2021 16:41:38 - INFO - __main__ - Step 19301: {'lr': 0.00048333165596866837, 'samples': 3705792, 'steps': 19300, 'loss/train': 1.4383171796798706} 08/30/2021 16:41:38 - INFO - __main__ - Step 19302: {'lr': 0.00048332975064401207, 'samples': 3705984, 'steps': 19301, 'loss/train': 1.7804783582687378} 08/30/2021 16:41:39 - INFO - __main__ - Step 19303: {'lr': 0.000483327845214221, 'samples': 3706176, 'steps': 19302, 'loss/train': 1.6774909496307373} 08/30/2021 16:41:39 - INFO - __main__ - Step 19304: {'lr': 0.00048332593967929607, 'samples': 3706368, 'steps': 19303, 'loss/train': 2.2327358722686768} 08/30/2021 16:41:40 - INFO - __main__ - Step 19305: {'lr': 0.000483324034039238, 'samples': 3706560, 'steps': 19304, 'loss/train': 1.806740403175354} 08/30/2021 16:41:41 - INFO - __main__ - Step 19306: {'lr': 0.00048332212829404775, 'samples': 3706752, 'steps': 19305, 'loss/train': 1.667768120765686} 08/30/2021 16:41:41 - INFO - __main__ - Step 19307: {'lr': 0.0004833202224437261, 'samples': 3706944, 'steps': 19306, 'loss/train': 1.2210687398910522} 08/30/2021 16:41:42 - INFO - __main__ - Step 19308: {'lr': 0.000483318316488274, 'samples': 3707136, 'steps': 19307, 'loss/train': 2.147545337677002} 08/30/2021 16:41:42 - INFO - __main__ - Step 19309: {'lr': 0.00048331641042769223, 'samples': 3707328, 'steps': 19308, 'loss/train': 1.5021699666976929} 08/30/2021 16:41:43 - INFO - __main__ - Step 19310: {'lr': 0.00048331450426198177, 'samples': 3707520, 'steps': 19309, 'loss/train': 1.634742259979248} 08/30/2021 16:41:44 - INFO - __main__ - Step 19311: {'lr': 0.0004833125979911434, 'samples': 3707712, 'steps': 19310, 'loss/train': 1.7047052383422852} 08/30/2021 16:41:44 - INFO - __main__ - Step 19312: {'lr': 0.0004833106916151778, 'samples': 3707904, 'steps': 19311, 'loss/train': 1.4949703216552734} 08/30/2021 16:41:45 - INFO - __main__ - Step 19313: {'lr': 0.00048330878513408616, 'samples': 3708096, 'steps': 19312, 'loss/train': 1.2732231616973877} 08/30/2021 16:41:45 - INFO - __main__ - Step 19314: {'lr': 0.00048330687854786914, 'samples': 3708288, 'steps': 19313, 'loss/train': 1.2981466054916382} 08/30/2021 16:41:47 - INFO - __main__ - Step 19315: {'lr': 0.00048330497185652765, 'samples': 3708480, 'steps': 19314, 'loss/train': 1.2048128843307495} 08/30/2021 16:41:47 - INFO - __main__ - Step 19316: {'lr': 0.00048330306506006257, 'samples': 3708672, 'steps': 19315, 'loss/train': 1.9277514219284058} 08/30/2021 16:41:48 - INFO - __main__ - Step 19317: {'lr': 0.00048330115815847465, 'samples': 3708864, 'steps': 19316, 'loss/train': 1.4384599924087524} 08/30/2021 16:41:48 - INFO - __main__ - Step 19318: {'lr': 0.0004832992511517649, 'samples': 3709056, 'steps': 19317, 'loss/train': 0.2641623318195343} 08/30/2021 16:41:48 - INFO - __main__ - Step 19319: {'lr': 0.00048329734403993406, 'samples': 3709248, 'steps': 19318, 'loss/train': 1.6658275127410889} 08/30/2021 16:41:49 - INFO - __main__ - Step 19320: {'lr': 0.00048329543682298307, 'samples': 3709440, 'steps': 19319, 'loss/train': 1.0207011699676514} 08/30/2021 16:41:50 - INFO - __main__ - Step 19321: {'lr': 0.0004832935295009127, 'samples': 3709632, 'steps': 19320, 'loss/train': 0.1176118329167366} 08/30/2021 16:41:51 - INFO - __main__ - Step 19322: {'lr': 0.0004832916220737239, 'samples': 3709824, 'steps': 19321, 'loss/train': 1.34175443649292} 08/30/2021 16:41:51 - INFO - __main__ - Step 19323: {'lr': 0.0004832897145414175, 'samples': 3710016, 'steps': 19322, 'loss/train': 1.9319572448730469} 08/30/2021 16:41:52 - INFO - __main__ - Step 19324: {'lr': 0.0004832878069039943, 'samples': 3710208, 'steps': 19323, 'loss/train': 1.999365210533142} 08/30/2021 16:41:52 - INFO - __main__ - Step 19325: {'lr': 0.0004832858991614553, 'samples': 3710400, 'steps': 19324, 'loss/train': 1.1017085313796997} 08/30/2021 16:41:53 - INFO - __main__ - Step 19326: {'lr': 0.00048328399131380127, 'samples': 3710592, 'steps': 19325, 'loss/train': 0.11377518624067307} 08/30/2021 16:41:54 - INFO - __main__ - Step 19327: {'lr': 0.00048328208336103305, 'samples': 3710784, 'steps': 19326, 'loss/train': 1.020818829536438} 08/30/2021 16:41:54 - INFO - __main__ - Step 19328: {'lr': 0.0004832801753031515, 'samples': 3710976, 'steps': 19327, 'loss/train': 0.6918624639511108} 08/30/2021 16:41:55 - INFO - __main__ - Step 19329: {'lr': 0.00048327826714015756, 'samples': 3711168, 'steps': 19328, 'loss/train': 1.8891956806182861} 08/30/2021 16:41:55 - INFO - __main__ - Step 19330: {'lr': 0.00048327635887205196, 'samples': 3711360, 'steps': 19329, 'loss/train': 1.7779945135116577} 08/30/2021 16:41:56 - INFO - __main__ - Step 19331: {'lr': 0.00048327445049883567, 'samples': 3711552, 'steps': 19330, 'loss/train': 1.7812371253967285} 08/30/2021 16:41:57 - INFO - __main__ - Step 19332: {'lr': 0.0004832725420205095, 'samples': 3711744, 'steps': 19331, 'loss/train': 2.511662006378174} 08/30/2021 16:41:57 - INFO - __main__ - Step 19333: {'lr': 0.00048327063343707433, 'samples': 3711936, 'steps': 19332, 'loss/train': 1.664101004600525} 08/30/2021 16:41:57 - INFO - __main__ - Step 19334: {'lr': 0.000483268724748531, 'samples': 3712128, 'steps': 19333, 'loss/train': 1.742770791053772} 08/30/2021 16:41:58 - INFO - __main__ - Step 19335: {'lr': 0.0004832668159548804, 'samples': 3712320, 'steps': 19334, 'loss/train': 1.5348186492919922} 08/30/2021 16:41:59 - INFO - __main__ - Step 19336: {'lr': 0.00048326490705612337, 'samples': 3712512, 'steps': 19335, 'loss/train': 1.2737853527069092} 08/30/2021 16:42:00 - INFO - __main__ - Step 19337: {'lr': 0.0004832629980522608, 'samples': 3712704, 'steps': 19336, 'loss/train': 1.415540099143982} 08/30/2021 16:42:00 - INFO - __main__ - Step 19338: {'lr': 0.00048326108894329345, 'samples': 3712896, 'steps': 19337, 'loss/train': 1.4279959201812744} 08/30/2021 16:42:00 - INFO - __main__ - Step 19339: {'lr': 0.00048325917972922227, 'samples': 3713088, 'steps': 19338, 'loss/train': 1.3825029134750366} 08/30/2021 16:42:01 - INFO - __main__ - Step 19340: {'lr': 0.00048325727041004815, 'samples': 3713280, 'steps': 19339, 'loss/train': 2.0216457843780518} 08/30/2021 16:42:01 - INFO - __main__ - Step 19341: {'lr': 0.0004832553609857719, 'samples': 3713472, 'steps': 19340, 'loss/train': 0.8572243452072144} 08/30/2021 16:42:03 - INFO - __main__ - Step 19342: {'lr': 0.0004832534514563943, 'samples': 3713664, 'steps': 19341, 'loss/train': 1.5212790966033936} 08/30/2021 16:42:04 - INFO - __main__ - Step 19343: {'lr': 0.0004832515418219164, 'samples': 3713856, 'steps': 19342, 'loss/train': 3.0543317794799805} 08/30/2021 16:42:04 - INFO - __main__ - Step 19344: {'lr': 0.0004832496320823389, 'samples': 3714048, 'steps': 19343, 'loss/train': 1.8511292934417725} 08/30/2021 16:42:05 - INFO - __main__ - Step 19345: {'lr': 0.0004832477222376627, 'samples': 3714240, 'steps': 19344, 'loss/train': 1.4760186672210693} 08/30/2021 16:42:05 - INFO - __main__ - Step 19346: {'lr': 0.0004832458122878888, 'samples': 3714432, 'steps': 19345, 'loss/train': 1.3504347801208496} 08/30/2021 16:42:05 - INFO - __main__ - Step 19347: {'lr': 0.0004832439022330178, 'samples': 3714624, 'steps': 19346, 'loss/train': 1.0208516120910645} 08/30/2021 16:42:07 - INFO - __main__ - Step 19348: {'lr': 0.00048324199207305075, 'samples': 3714816, 'steps': 19347, 'loss/train': 1.5862152576446533} 08/30/2021 16:42:07 - INFO - __main__ - Step 19349: {'lr': 0.0004832400818079884, 'samples': 3715008, 'steps': 19348, 'loss/train': 0.6771523952484131} 08/30/2021 16:42:07 - INFO - __main__ - Step 19350: {'lr': 0.00048323817143783174, 'samples': 3715200, 'steps': 19349, 'loss/train': 1.9784314632415771} 08/30/2021 16:42:08 - INFO - __main__ - Step 19351: {'lr': 0.0004832362609625815, 'samples': 3715392, 'steps': 19350, 'loss/train': 1.5952527523040771} 08/30/2021 16:42:08 - INFO - __main__ - Step 19352: {'lr': 0.0004832343503822386, 'samples': 3715584, 'steps': 19351, 'loss/train': 1.8875341415405273} 08/30/2021 16:42:10 - INFO - __main__ - Step 19353: {'lr': 0.000483232439696804, 'samples': 3715776, 'steps': 19352, 'loss/train': 1.3885711431503296} 08/30/2021 16:42:10 - INFO - __main__ - Step 19354: {'lr': 0.0004832305289062784, 'samples': 3715968, 'steps': 19353, 'loss/train': 0.8795766830444336} 08/30/2021 16:42:10 - INFO - __main__ - Step 19355: {'lr': 0.00048322861801066265, 'samples': 3716160, 'steps': 19354, 'loss/train': 1.794315218925476} 08/30/2021 16:42:11 - INFO - __main__ - Step 19356: {'lr': 0.00048322670700995775, 'samples': 3716352, 'steps': 19355, 'loss/train': 2.2336206436157227} 08/30/2021 16:42:11 - INFO - __main__ - Step 19357: {'lr': 0.0004832247959041645, 'samples': 3716544, 'steps': 19356, 'loss/train': 1.6674057245254517} 08/30/2021 16:42:13 - INFO - __main__ - Step 19358: {'lr': 0.0004832228846932838, 'samples': 3716736, 'steps': 19357, 'loss/train': 1.828009843826294} 08/30/2021 16:42:13 - INFO - __main__ - Step 19359: {'lr': 0.0004832209733773164, 'samples': 3716928, 'steps': 19358, 'loss/train': 2.1200366020202637} 08/30/2021 16:42:13 - INFO - __main__ - Step 19360: {'lr': 0.0004832190619562632, 'samples': 3717120, 'steps': 19359, 'loss/train': 2.2332732677459717} 08/30/2021 16:42:14 - INFO - __main__ - Step 19361: {'lr': 0.00048321715043012515, 'samples': 3717312, 'steps': 19360, 'loss/train': 1.1754701137542725} 08/30/2021 16:42:14 - INFO - __main__ - Step 19362: {'lr': 0.00048321523879890307, 'samples': 3717504, 'steps': 19361, 'loss/train': 1.480566143989563} 08/30/2021 16:42:16 - INFO - __main__ - Step 19363: {'lr': 0.00048321332706259773, 'samples': 3717696, 'steps': 19362, 'loss/train': 0.8196985125541687} 08/30/2021 16:42:16 - INFO - __main__ - Step 19364: {'lr': 0.0004832114152212101, 'samples': 3717888, 'steps': 19363, 'loss/train': 1.7934433221817017} 08/30/2021 16:42:16 - INFO - __main__ - Step 19365: {'lr': 0.000483209503274741, 'samples': 3718080, 'steps': 19364, 'loss/train': 1.9399924278259277} 08/30/2021 16:42:17 - INFO - __main__ - Step 19366: {'lr': 0.0004832075912231913, 'samples': 3718272, 'steps': 19365, 'loss/train': 1.6247559785842896} 08/30/2021 16:42:17 - INFO - __main__ - Step 19367: {'lr': 0.0004832056790665619, 'samples': 3718464, 'steps': 19366, 'loss/train': 1.808705449104309} 08/30/2021 16:42:19 - INFO - __main__ - Step 19368: {'lr': 0.0004832037668048536, 'samples': 3718656, 'steps': 19367, 'loss/train': 0.978150486946106} 08/30/2021 16:42:19 - INFO - __main__ - Step 19369: {'lr': 0.00048320185443806717, 'samples': 3718848, 'steps': 19368, 'loss/train': 1.0606640577316284} 08/30/2021 16:42:19 - INFO - __main__ - Step 19370: {'lr': 0.0004831999419662037, 'samples': 3719040, 'steps': 19369, 'loss/train': 1.6687099933624268} 08/30/2021 16:42:20 - INFO - __main__ - Step 19371: {'lr': 0.0004831980293892639, 'samples': 3719232, 'steps': 19370, 'loss/train': 1.8510860204696655} 08/30/2021 16:42:20 - INFO - __main__ - Step 19372: {'lr': 0.0004831961167072487, 'samples': 3719424, 'steps': 19371, 'loss/train': 1.5339409112930298} 08/30/2021 16:42:22 - INFO - __main__ - Step 19373: {'lr': 0.0004831942039201589, 'samples': 3719616, 'steps': 19372, 'loss/train': 1.3339210748672485} 08/30/2021 16:42:22 - INFO - __main__ - Step 19374: {'lr': 0.0004831922910279954, 'samples': 3719808, 'steps': 19373, 'loss/train': 1.6575361490249634} 08/30/2021 16:42:23 - INFO - __main__ - Step 19375: {'lr': 0.000483190378030759, 'samples': 3720000, 'steps': 19374, 'loss/train': 0.06456669420003891} 08/30/2021 16:42:23 - INFO - __main__ - Step 19376: {'lr': 0.0004831884649284507, 'samples': 3720192, 'steps': 19375, 'loss/train': 0.7960783839225769} 08/30/2021 16:42:23 - INFO - __main__ - Step 19377: {'lr': 0.00048318655172107126, 'samples': 3720384, 'steps': 19376, 'loss/train': 4.159504413604736} 08/30/2021 16:42:25 - INFO - __main__ - Step 19378: {'lr': 0.0004831846384086215, 'samples': 3720576, 'steps': 19377, 'loss/train': 1.4446724653244019} 08/30/2021 16:42:25 - INFO - __main__ - Step 19379: {'lr': 0.0004831827249911024, 'samples': 3720768, 'steps': 19378, 'loss/train': 1.2134758234024048} 08/30/2021 16:42:26 - INFO - __main__ - Step 19380: {'lr': 0.0004831808114685147, 'samples': 3720960, 'steps': 19379, 'loss/train': 1.2609055042266846} 08/30/2021 16:42:26 - INFO - __main__ - Step 19381: {'lr': 0.00048317889784085935, 'samples': 3721152, 'steps': 19380, 'loss/train': 0.6011592149734497} 08/30/2021 16:42:26 - INFO - __main__ - Step 19382: {'lr': 0.0004831769841081372, 'samples': 3721344, 'steps': 19381, 'loss/train': 2.1070375442504883} 08/30/2021 16:42:27 - INFO - __main__ - Step 19383: {'lr': 0.00048317507027034913, 'samples': 3721536, 'steps': 19382, 'loss/train': 1.7769204378128052} 08/30/2021 16:42:28 - INFO - __main__ - Step 19384: {'lr': 0.0004831731563274959, 'samples': 3721728, 'steps': 19383, 'loss/train': 1.5864990949630737} 08/30/2021 16:42:29 - INFO - __main__ - Step 19385: {'lr': 0.0004831712422795785, 'samples': 3721920, 'steps': 19384, 'loss/train': 1.2622509002685547} 08/30/2021 16:42:29 - INFO - __main__ - Step 19386: {'lr': 0.00048316932812659776, 'samples': 3722112, 'steps': 19385, 'loss/train': 1.7974189519882202} 08/30/2021 16:42:30 - INFO - __main__ - Step 19387: {'lr': 0.00048316741386855445, 'samples': 3722304, 'steps': 19386, 'loss/train': 0.48866257071495056} 08/30/2021 16:42:30 - INFO - __main__ - Step 19388: {'lr': 0.0004831654995054495, 'samples': 3722496, 'steps': 19387, 'loss/train': 1.4563623666763306} 08/30/2021 16:42:32 - INFO - __main__ - Step 19389: {'lr': 0.0004831635850372838, 'samples': 3722688, 'steps': 19388, 'loss/train': 1.7257275581359863} 08/30/2021 16:42:32 - INFO - __main__ - Step 19390: {'lr': 0.00048316167046405826, 'samples': 3722880, 'steps': 19389, 'loss/train': 0.7319338917732239} 08/30/2021 16:42:32 - INFO - __main__ - Step 19391: {'lr': 0.0004831597557857735, 'samples': 3723072, 'steps': 19390, 'loss/train': 1.5165249109268188} 08/30/2021 16:42:33 - INFO - __main__ - Step 19392: {'lr': 0.00048315784100243063, 'samples': 3723264, 'steps': 19391, 'loss/train': 1.9773688316345215} 08/30/2021 16:42:33 - INFO - __main__ - Step 19393: {'lr': 0.0004831559261140305, 'samples': 3723456, 'steps': 19392, 'loss/train': 1.6093653440475464} 08/30/2021 16:42:35 - INFO - __main__ - Step 19394: {'lr': 0.0004831540111205739, 'samples': 3723648, 'steps': 19393, 'loss/train': 1.6279922723770142} 08/30/2021 16:42:35 - INFO - __main__ - Step 19395: {'lr': 0.00048315209602206165, 'samples': 3723840, 'steps': 19394, 'loss/train': 1.7154209613800049} 08/30/2021 16:42:36 - INFO - __main__ - Step 19396: {'lr': 0.0004831501808184947, 'samples': 3724032, 'steps': 19395, 'loss/train': 1.2043235301971436} 08/30/2021 16:42:36 - INFO - __main__ - Step 19397: {'lr': 0.0004831482655098738, 'samples': 3724224, 'steps': 19396, 'loss/train': 1.9871405363082886} 08/30/2021 16:42:36 - INFO - __main__ - Step 19398: {'lr': 0.00048314635009619997, 'samples': 3724416, 'steps': 19397, 'loss/train': 1.6793252229690552} 08/30/2021 16:42:37 - INFO - __main__ - Step 19399: {'lr': 0.0004831444345774739, 'samples': 3724608, 'steps': 19398, 'loss/train': 0.517352283000946} 08/30/2021 16:42:39 - INFO - __main__ - Step 19400: {'lr': 0.00048314251895369663, 'samples': 3724800, 'steps': 19399, 'loss/train': 1.0613000392913818} 08/30/2021 16:42:39 - INFO - __main__ - Step 19401: {'lr': 0.000483140603224869, 'samples': 3724992, 'steps': 19400, 'loss/train': 1.8209928274154663} 08/30/2021 16:42:40 - INFO - __main__ - Step 19402: {'lr': 0.00048313868739099166, 'samples': 3725184, 'steps': 19401, 'loss/train': 1.1783801317214966} 08/30/2021 16:42:40 - INFO - __main__ - Step 19403: {'lr': 0.0004831367714520657, 'samples': 3725376, 'steps': 19402, 'loss/train': 1.5873388051986694} 08/30/2021 16:42:40 - INFO - __main__ - Step 19404: {'lr': 0.0004831348554080919, 'samples': 3725568, 'steps': 19403, 'loss/train': 2.2661373615264893} 08/30/2021 16:42:42 - INFO - __main__ - Step 19405: {'lr': 0.0004831329392590711, 'samples': 3725760, 'steps': 19404, 'loss/train': 0.8620322346687317} 08/30/2021 16:42:42 - INFO - __main__ - Step 19406: {'lr': 0.00048313102300500424, 'samples': 3725952, 'steps': 19405, 'loss/train': 1.3002861738204956} 08/30/2021 16:42:42 - INFO - __main__ - Step 19407: {'lr': 0.00048312910664589215, 'samples': 3726144, 'steps': 19406, 'loss/train': 1.7104800939559937} 08/30/2021 16:42:43 - INFO - __main__ - Step 19408: {'lr': 0.0004831271901817357, 'samples': 3726336, 'steps': 19407, 'loss/train': 1.7206051349639893} 08/30/2021 16:42:43 - INFO - __main__ - Step 19409: {'lr': 0.00048312527361253567, 'samples': 3726528, 'steps': 19408, 'loss/train': 0.7446151971817017} 08/30/2021 16:42:45 - INFO - __main__ - Step 19410: {'lr': 0.000483123356938293, 'samples': 3726720, 'steps': 19409, 'loss/train': 1.662960410118103} 08/30/2021 16:42:45 - INFO - __main__ - Step 19411: {'lr': 0.00048312144015900856, 'samples': 3726912, 'steps': 19410, 'loss/train': 2.022324323654175} 08/30/2021 16:42:46 - INFO - __main__ - Step 19412: {'lr': 0.00048311952327468325, 'samples': 3727104, 'steps': 19411, 'loss/train': 1.5919524431228638} 08/30/2021 16:42:46 - INFO - __main__ - Step 19413: {'lr': 0.00048311760628531777, 'samples': 3727296, 'steps': 19412, 'loss/train': 0.9535502195358276} 08/30/2021 16:42:46 - INFO - __main__ - Step 19414: {'lr': 0.00048311568919091316, 'samples': 3727488, 'steps': 19413, 'loss/train': 1.7854655981063843} 08/30/2021 16:42:48 - INFO - __main__ - Step 19415: {'lr': 0.00048311377199147023, 'samples': 3727680, 'steps': 19414, 'loss/train': 1.4093464612960815} 08/30/2021 16:42:48 - INFO - __main__ - Step 19416: {'lr': 0.00048311185468698974, 'samples': 3727872, 'steps': 19415, 'loss/train': 1.5233309268951416} 08/30/2021 16:42:49 - INFO - __main__ - Step 19417: {'lr': 0.00048310993727747277, 'samples': 3728064, 'steps': 19416, 'loss/train': 1.3573007583618164} 08/30/2021 16:42:49 - INFO - __main__ - Step 19418: {'lr': 0.00048310801976292, 'samples': 3728256, 'steps': 19417, 'loss/train': 0.570035994052887} 08/30/2021 16:42:49 - INFO - __main__ - Step 19419: {'lr': 0.0004831061021433323, 'samples': 3728448, 'steps': 19418, 'loss/train': 0.9198406338691711} 08/30/2021 16:42:51 - INFO - __main__ - Step 19420: {'lr': 0.00048310418441871065, 'samples': 3728640, 'steps': 19419, 'loss/train': 1.227281928062439} 08/30/2021 16:42:51 - INFO - __main__ - Step 19421: {'lr': 0.00048310226658905585, 'samples': 3728832, 'steps': 19420, 'loss/train': 1.704697608947754} 08/30/2021 16:42:52 - INFO - __main__ - Step 19422: {'lr': 0.00048310034865436876, 'samples': 3729024, 'steps': 19421, 'loss/train': 1.689162254333496} 08/30/2021 16:42:52 - INFO - __main__ - Step 19423: {'lr': 0.0004830984306146503, 'samples': 3729216, 'steps': 19422, 'loss/train': 1.5913020372390747} 08/30/2021 16:42:52 - INFO - __main__ - Step 19424: {'lr': 0.0004830965124699012, 'samples': 3729408, 'steps': 19423, 'loss/train': 2.141072988510132} 08/30/2021 16:42:53 - INFO - __main__ - Step 19425: {'lr': 0.00048309459422012243, 'samples': 3729600, 'steps': 19424, 'loss/train': 1.4321925640106201} 08/30/2021 16:42:54 - INFO - __main__ - Step 19426: {'lr': 0.0004830926758653148, 'samples': 3729792, 'steps': 19425, 'loss/train': 1.5611809492111206} 08/30/2021 16:42:55 - INFO - __main__ - Step 19427: {'lr': 0.00048309075740547925, 'samples': 3729984, 'steps': 19426, 'loss/train': 0.10041192173957825} 08/30/2021 16:42:55 - INFO - __main__ - Step 19428: {'lr': 0.0004830888388406166, 'samples': 3730176, 'steps': 19427, 'loss/train': 1.552420973777771} 08/30/2021 16:42:56 - INFO - __main__ - Step 19429: {'lr': 0.00048308692017072773, 'samples': 3730368, 'steps': 19428, 'loss/train': 2.0706841945648193} 08/30/2021 16:42:56 - INFO - __main__ - Step 19430: {'lr': 0.00048308500139581344, 'samples': 3730560, 'steps': 19429, 'loss/train': 1.984182596206665} 08/30/2021 16:42:57 - INFO - __main__ - Step 19431: {'lr': 0.00048308308251587476, 'samples': 3730752, 'steps': 19430, 'loss/train': 1.6536108255386353} 08/30/2021 16:42:58 - INFO - __main__ - Step 19432: {'lr': 0.00048308116353091234, 'samples': 3730944, 'steps': 19431, 'loss/train': 1.4992344379425049} 08/30/2021 16:42:58 - INFO - __main__ - Step 19433: {'lr': 0.00048307924444092716, 'samples': 3731136, 'steps': 19432, 'loss/train': 1.4667798280715942} 08/30/2021 16:42:58 - INFO - __main__ - Step 19434: {'lr': 0.0004830773252459201, 'samples': 3731328, 'steps': 19433, 'loss/train': 1.0226434469223022} 08/30/2021 16:42:59 - INFO - __main__ - Step 19435: {'lr': 0.00048307540594589194, 'samples': 3731520, 'steps': 19434, 'loss/train': 1.4328798055648804} 08/30/2021 16:43:00 - INFO - __main__ - Step 19436: {'lr': 0.0004830734865408437, 'samples': 3731712, 'steps': 19435, 'loss/train': 1.447022795677185} 08/30/2021 16:43:01 - INFO - __main__ - Step 19437: {'lr': 0.000483071567030776, 'samples': 3731904, 'steps': 19436, 'loss/train': 1.696250557899475} 08/30/2021 16:43:01 - INFO - __main__ - Step 19438: {'lr': 0.00048306964741568994, 'samples': 3732096, 'steps': 19437, 'loss/train': 1.3995155096054077} 08/30/2021 16:43:01 - INFO - __main__ - Step 19439: {'lr': 0.00048306772769558624, 'samples': 3732288, 'steps': 19438, 'loss/train': 1.395381212234497} 08/30/2021 16:43:02 - INFO - __main__ - Step 19440: {'lr': 0.0004830658078704659, 'samples': 3732480, 'steps': 19439, 'loss/train': 1.5541294813156128} 08/30/2021 16:43:04 - INFO - __main__ - Step 19441: {'lr': 0.0004830638879403296, 'samples': 3732672, 'steps': 19440, 'loss/train': 1.2075867652893066} 08/30/2021 16:43:04 - INFO - __main__ - Step 19442: {'lr': 0.00048306196790517844, 'samples': 3732864, 'steps': 19441, 'loss/train': 1.0280719995498657} 08/30/2021 16:43:04 - INFO - __main__ - Step 19443: {'lr': 0.0004830600477650131, 'samples': 3733056, 'steps': 19442, 'loss/train': 0.19573047757148743} 08/30/2021 16:43:05 - INFO - __main__ - Step 19444: {'lr': 0.0004830581275198344, 'samples': 3733248, 'steps': 19443, 'loss/train': 0.19728131592273712} 08/30/2021 16:43:05 - INFO - __main__ - Step 19445: {'lr': 0.00048305620716964336, 'samples': 3733440, 'steps': 19444, 'loss/train': 1.397684931755066} 08/30/2021 16:43:05 - INFO - __main__ - Step 19446: {'lr': 0.00048305428671444083, 'samples': 3733632, 'steps': 19445, 'loss/train': 1.491231083869934} 08/30/2021 16:43:07 - INFO - __main__ - Step 19447: {'lr': 0.00048305236615422763, 'samples': 3733824, 'steps': 19446, 'loss/train': 1.369369387626648} 08/30/2021 16:43:08 - INFO - __main__ - Step 19448: {'lr': 0.00048305044548900463, 'samples': 3734016, 'steps': 19447, 'loss/train': 1.5268791913986206} 08/30/2021 16:43:08 - INFO - __main__ - Step 19449: {'lr': 0.0004830485247187727, 'samples': 3734208, 'steps': 19448, 'loss/train': 1.5801888704299927} 08/30/2021 16:43:08 - INFO - __main__ - Step 19450: {'lr': 0.0004830466038435327, 'samples': 3734400, 'steps': 19449, 'loss/train': 1.4094716310501099} 08/30/2021 16:43:09 - INFO - __main__ - Step 19451: {'lr': 0.0004830446828632854, 'samples': 3734592, 'steps': 19450, 'loss/train': 0.9922022223472595} 08/30/2021 16:43:09 - INFO - __main__ - Step 19452: {'lr': 0.00048304276177803186, 'samples': 3734784, 'steps': 19451, 'loss/train': 1.7343542575836182} 08/30/2021 16:43:11 - INFO - __main__ - Step 19453: {'lr': 0.00048304084058777285, 'samples': 3734976, 'steps': 19452, 'loss/train': 1.4883506298065186} 08/30/2021 16:43:11 - INFO - __main__ - Step 19454: {'lr': 0.00048303891929250923, 'samples': 3735168, 'steps': 19453, 'loss/train': 2.03281831741333} 08/30/2021 16:43:12 - INFO - __main__ - Step 19455: {'lr': 0.0004830369978922418, 'samples': 3735360, 'steps': 19454, 'loss/train': 1.4497188329696655} 08/30/2021 16:43:12 - INFO - __main__ - Step 19456: {'lr': 0.00048303507638697155, 'samples': 3735552, 'steps': 19455, 'loss/train': 1.403900384902954} 08/30/2021 16:43:12 - INFO - __main__ - Step 19457: {'lr': 0.0004830331547766993, 'samples': 3735744, 'steps': 19456, 'loss/train': 1.4013632535934448} 08/30/2021 16:43:14 - INFO - __main__ - Step 19458: {'lr': 0.0004830312330614259, 'samples': 3735936, 'steps': 19457, 'loss/train': 1.2117112874984741} 08/30/2021 16:43:15 - INFO - __main__ - Step 19459: {'lr': 0.00048302931124115226, 'samples': 3736128, 'steps': 19458, 'loss/train': 0.4895917773246765} 08/30/2021 16:43:15 - INFO - __main__ - Step 19460: {'lr': 0.0004830273893158791, 'samples': 3736320, 'steps': 19459, 'loss/train': 1.79667329788208} 08/30/2021 16:43:15 - INFO - __main__ - Step 19461: {'lr': 0.0004830254672856075, 'samples': 3736512, 'steps': 19460, 'loss/train': 1.1802961826324463} 08/30/2021 16:43:16 - INFO - __main__ - Step 19462: {'lr': 0.00048302354515033813, 'samples': 3736704, 'steps': 19461, 'loss/train': 1.596136212348938} 08/30/2021 16:43:16 - INFO - __main__ - Step 19463: {'lr': 0.00048302162291007203, 'samples': 3736896, 'steps': 19462, 'loss/train': 1.3673269748687744} 08/30/2021 16:43:17 - INFO - __main__ - Step 19464: {'lr': 0.00048301970056480994, 'samples': 3737088, 'steps': 19463, 'loss/train': 1.8032881021499634} 08/30/2021 16:43:18 - INFO - __main__ - Step 19465: {'lr': 0.00048301777811455274, 'samples': 3737280, 'steps': 19464, 'loss/train': 1.113150954246521} 08/30/2021 16:43:18 - INFO - __main__ - Step 19466: {'lr': 0.0004830158555593014, 'samples': 3737472, 'steps': 19465, 'loss/train': 1.349056601524353} 08/30/2021 16:43:19 - INFO - __main__ - Step 19467: {'lr': 0.00048301393289905663, 'samples': 3737664, 'steps': 19466, 'loss/train': 1.4769805669784546} 08/30/2021 16:43:19 - INFO - __main__ - Step 19468: {'lr': 0.00048301201013381946, 'samples': 3737856, 'steps': 19467, 'loss/train': 1.7169746160507202} 08/30/2021 16:43:20 - INFO - __main__ - Step 19469: {'lr': 0.00048301008726359064, 'samples': 3738048, 'steps': 19468, 'loss/train': 1.3549416065216064} 08/30/2021 16:43:21 - INFO - __main__ - Step 19470: {'lr': 0.00048300816428837104, 'samples': 3738240, 'steps': 19469, 'loss/train': 1.4819215536117554} 08/30/2021 16:43:21 - INFO - __main__ - Step 19471: {'lr': 0.00048300624120816153, 'samples': 3738432, 'steps': 19470, 'loss/train': 1.624529242515564} 08/30/2021 16:43:22 - INFO - __main__ - Step 19472: {'lr': 0.0004830043180229631, 'samples': 3738624, 'steps': 19471, 'loss/train': 1.4806876182556152} 08/30/2021 16:43:22 - INFO - __main__ - Step 19473: {'lr': 0.0004830023947327764, 'samples': 3738816, 'steps': 19472, 'loss/train': 1.8842469453811646} 08/30/2021 16:43:24 - INFO - __main__ - Step 19474: {'lr': 0.0004830004713376025, 'samples': 3739008, 'steps': 19473, 'loss/train': 0.922451913356781} 08/30/2021 16:43:24 - INFO - __main__ - Step 19475: {'lr': 0.00048299854783744224, 'samples': 3739200, 'steps': 19474, 'loss/train': 1.7893987894058228} 08/30/2021 16:43:24 - INFO - __main__ - Step 19476: {'lr': 0.0004829966242322963, 'samples': 3739392, 'steps': 19475, 'loss/train': 1.2062294483184814} 08/30/2021 16:43:25 - INFO - __main__ - Step 19477: {'lr': 0.00048299470052216576, 'samples': 3739584, 'steps': 19476, 'loss/train': 1.5458911657333374} 08/30/2021 16:43:25 - INFO - __main__ - Step 19478: {'lr': 0.0004829927767070514, 'samples': 3739776, 'steps': 19477, 'loss/train': 1.5041776895523071} 08/30/2021 16:43:27 - INFO - __main__ - Step 19479: {'lr': 0.0004829908527869541, 'samples': 3739968, 'steps': 19478, 'loss/train': 2.5316600799560547} 08/30/2021 16:43:27 - INFO - __main__ - Step 19480: {'lr': 0.0004829889287618746, 'samples': 3740160, 'steps': 19479, 'loss/train': 1.558606743812561} 08/30/2021 16:43:27 - INFO - __main__ - Step 19481: {'lr': 0.000482987004631814, 'samples': 3740352, 'steps': 19480, 'loss/train': 1.1558796167373657} 08/30/2021 16:43:28 - INFO - __main__ - Step 19482: {'lr': 0.000482985080396773, 'samples': 3740544, 'steps': 19481, 'loss/train': 1.0911834239959717} 08/30/2021 16:43:28 - INFO - __main__ - Step 19483: {'lr': 0.00048298315605675257, 'samples': 3740736, 'steps': 19482, 'loss/train': 2.164764404296875} 08/30/2021 16:43:28 - INFO - __main__ - Step 19484: {'lr': 0.0004829812316117535, 'samples': 3740928, 'steps': 19483, 'loss/train': 1.5163272619247437} 08/30/2021 16:43:30 - INFO - __main__ - Step 19485: {'lr': 0.0004829793070617767, 'samples': 3741120, 'steps': 19484, 'loss/train': 0.15662556886672974} 08/30/2021 16:43:31 - INFO - __main__ - Step 19486: {'lr': 0.000482977382406823, 'samples': 3741312, 'steps': 19485, 'loss/train': 2.4153854846954346} 08/30/2021 16:43:31 - INFO - __main__ - Step 19487: {'lr': 0.00048297545764689327, 'samples': 3741504, 'steps': 19486, 'loss/train': 1.7778544425964355} 08/30/2021 16:43:31 - INFO - __main__ - Step 19488: {'lr': 0.00048297353278198843, 'samples': 3741696, 'steps': 19487, 'loss/train': 2.195345640182495} 08/30/2021 16:43:32 - INFO - __main__ - Step 19489: {'lr': 0.00048297160781210925, 'samples': 3741888, 'steps': 19488, 'loss/train': 1.1673959493637085} 08/30/2021 16:43:33 - INFO - __main__ - Step 19490: {'lr': 0.00048296968273725673, 'samples': 3742080, 'steps': 19489, 'loss/train': 1.3847583532333374} 08/30/2021 16:43:33 - INFO - __main__ - Step 19491: {'lr': 0.0004829677575574316, 'samples': 3742272, 'steps': 19490, 'loss/train': 1.5721217393875122} 08/30/2021 16:43:34 - INFO - __main__ - Step 19492: {'lr': 0.0004829658322726348, 'samples': 3742464, 'steps': 19491, 'loss/train': 2.139817476272583} 08/30/2021 16:43:34 - INFO - __main__ - Step 19493: {'lr': 0.00048296390688286724, 'samples': 3742656, 'steps': 19492, 'loss/train': 1.1478424072265625} 08/30/2021 16:43:35 - INFO - __main__ - Step 19494: {'lr': 0.00048296198138812974, 'samples': 3742848, 'steps': 19493, 'loss/train': 1.6474329233169556} 08/30/2021 16:43:36 - INFO - __main__ - Step 19495: {'lr': 0.00048296005578842314, 'samples': 3743040, 'steps': 19494, 'loss/train': 1.5222991704940796} 08/30/2021 16:43:37 - INFO - __main__ - Step 19496: {'lr': 0.0004829581300837483, 'samples': 3743232, 'steps': 19495, 'loss/train': 1.2511401176452637} 08/30/2021 16:43:37 - INFO - __main__ - Step 19497: {'lr': 0.00048295620427410614, 'samples': 3743424, 'steps': 19496, 'loss/train': 2.0683276653289795} 08/30/2021 16:43:38 - INFO - __main__ - Step 19498: {'lr': 0.00048295427835949757, 'samples': 3743616, 'steps': 19497, 'loss/train': 0.14382371306419373} 08/30/2021 16:43:38 - INFO - __main__ - Step 19499: {'lr': 0.0004829523523399233, 'samples': 3743808, 'steps': 19498, 'loss/train': 1.646743655204773} 08/30/2021 16:43:39 - INFO - __main__ - Step 19500: {'lr': 0.0004829504262153844, 'samples': 3744000, 'steps': 19499, 'loss/train': 1.6095962524414062} 08/30/2021 16:43:40 - INFO - __main__ - Step 19501: {'lr': 0.00048294849998588155, 'samples': 3744192, 'steps': 19500, 'loss/train': 1.597055196762085} 08/30/2021 16:43:40 - INFO - __main__ - Step 19502: {'lr': 0.0004829465736514157, 'samples': 3744384, 'steps': 19501, 'loss/train': 1.6863080263137817} 08/30/2021 16:43:40 - INFO - __main__ - Step 19503: {'lr': 0.0004829446472119878, 'samples': 3744576, 'steps': 19502, 'loss/train': 1.519710659980774} 08/30/2021 16:43:41 - INFO - __main__ - Step 19504: {'lr': 0.0004829427206675986, 'samples': 3744768, 'steps': 19503, 'loss/train': 1.3485311269760132} 08/30/2021 16:43:43 - INFO - __main__ - Step 19505: {'lr': 0.000482940794018249, 'samples': 3744960, 'steps': 19504, 'loss/train': 1.680020809173584} 08/30/2021 16:43:44 - INFO - __main__ - Step 19506: {'lr': 0.00048293886726393984, 'samples': 3745152, 'steps': 19505, 'loss/train': 1.2845860719680786} 08/30/2021 16:43:44 - INFO - __main__ - Step 19507: {'lr': 0.00048293694040467205, 'samples': 3745344, 'steps': 19506, 'loss/train': 1.7753819227218628} 08/30/2021 16:43:44 - INFO - __main__ - Step 19508: {'lr': 0.00048293501344044644, 'samples': 3745536, 'steps': 19507, 'loss/train': 1.3423000574111938} 08/30/2021 16:43:45 - INFO - __main__ - Step 19509: {'lr': 0.00048293308637126393, 'samples': 3745728, 'steps': 19508, 'loss/train': 0.06995130330324173} 08/30/2021 16:43:45 - INFO - __main__ - Step 19510: {'lr': 0.0004829311591971254, 'samples': 3745920, 'steps': 19509, 'loss/train': 1.3867766857147217} 08/30/2021 16:43:46 - INFO - __main__ - Step 19511: {'lr': 0.0004829292319180316, 'samples': 3746112, 'steps': 19510, 'loss/train': 1.5491560697555542} 08/30/2021 16:43:47 - INFO - __main__ - Step 19512: {'lr': 0.00048292730453398355, 'samples': 3746304, 'steps': 19511, 'loss/train': 2.0232818126678467} 08/30/2021 16:43:47 - INFO - __main__ - Step 19513: {'lr': 0.00048292537704498203, 'samples': 3746496, 'steps': 19512, 'loss/train': 0.7678455114364624} 08/30/2021 16:43:48 - INFO - __main__ - Step 19514: {'lr': 0.00048292344945102795, 'samples': 3746688, 'steps': 19513, 'loss/train': 1.5709292888641357} 08/30/2021 16:43:48 - INFO - __main__ - Step 19515: {'lr': 0.0004829215217521221, 'samples': 3746880, 'steps': 19514, 'loss/train': 1.579296350479126} 08/30/2021 16:43:49 - INFO - __main__ - Step 19516: {'lr': 0.00048291959394826546, 'samples': 3747072, 'steps': 19515, 'loss/train': 1.4513450860977173} 08/30/2021 16:43:50 - INFO - __main__ - Step 19517: {'lr': 0.00048291766603945885, 'samples': 3747264, 'steps': 19516, 'loss/train': 1.569222331047058} 08/30/2021 16:43:50 - INFO - __main__ - Step 19518: {'lr': 0.0004829157380257031, 'samples': 3747456, 'steps': 19517, 'loss/train': 0.45005112886428833} 08/30/2021 16:43:51 - INFO - __main__ - Step 19519: {'lr': 0.0004829138099069991, 'samples': 3747648, 'steps': 19518, 'loss/train': 2.1218044757843018} 08/30/2021 16:43:51 - INFO - __main__ - Step 19520: {'lr': 0.0004829118816833478, 'samples': 3747840, 'steps': 19519, 'loss/train': 1.4196314811706543} 08/30/2021 16:43:51 - INFO - __main__ - Step 19521: {'lr': 0.00048290995335474997, 'samples': 3748032, 'steps': 19520, 'loss/train': 1.3461363315582275} 08/30/2021 16:43:53 - INFO - __main__ - Step 19522: {'lr': 0.0004829080249212064, 'samples': 3748224, 'steps': 19521, 'loss/train': 1.23183012008667} 08/30/2021 16:43:53 - INFO - __main__ - Step 19523: {'lr': 0.00048290609638271823, 'samples': 3748416, 'steps': 19522, 'loss/train': 0.9542306661605835} 08/30/2021 16:43:54 - INFO - __main__ - Step 19524: {'lr': 0.00048290416773928615, 'samples': 3748608, 'steps': 19523, 'loss/train': 1.4460543394088745} 08/30/2021 16:43:54 - INFO - __main__ - Step 19525: {'lr': 0.00048290223899091094, 'samples': 3748800, 'steps': 19524, 'loss/train': 1.4835989475250244} 08/30/2021 16:43:54 - INFO - __main__ - Step 19526: {'lr': 0.0004829003101375937, 'samples': 3748992, 'steps': 19525, 'loss/train': 1.1736853122711182} 08/30/2021 16:43:56 - INFO - __main__ - Step 19527: {'lr': 0.00048289838117933505, 'samples': 3749184, 'steps': 19526, 'loss/train': 1.1716976165771484} 08/30/2021 16:43:56 - INFO - __main__ - Step 19528: {'lr': 0.0004828964521161361, 'samples': 3749376, 'steps': 19527, 'loss/train': 1.5114786624908447} 08/30/2021 16:43:57 - INFO - __main__ - Step 19529: {'lr': 0.0004828945229479975, 'samples': 3749568, 'steps': 19528, 'loss/train': 1.2109297513961792} 08/30/2021 16:43:57 - INFO - __main__ - Step 19530: {'lr': 0.0004828925936749202, 'samples': 3749760, 'steps': 19529, 'loss/train': 1.4926478862762451} 08/30/2021 16:43:57 - INFO - __main__ - Step 19531: {'lr': 0.0004828906642969052, 'samples': 3749952, 'steps': 19530, 'loss/train': 1.70020592212677} 08/30/2021 16:43:59 - INFO - __main__ - Step 19532: {'lr': 0.00048288873481395323, 'samples': 3750144, 'steps': 19531, 'loss/train': 2.006854295730591} 08/30/2021 16:43:59 - INFO - __main__ - Step 19533: {'lr': 0.0004828868052260652, 'samples': 3750336, 'steps': 19532, 'loss/train': 1.75969398021698} 08/30/2021 16:44:00 - INFO - __main__ - Step 19534: {'lr': 0.0004828848755332419, 'samples': 3750528, 'steps': 19533, 'loss/train': 1.984788179397583} 08/30/2021 16:44:00 - INFO - __main__ - Step 19535: {'lr': 0.0004828829457354843, 'samples': 3750720, 'steps': 19534, 'loss/train': 1.0613036155700684} 08/30/2021 16:44:01 - INFO - __main__ - Step 19536: {'lr': 0.0004828810158327933, 'samples': 3750912, 'steps': 19535, 'loss/train': 1.3652853965759277} 08/30/2021 16:44:01 - INFO - __main__ - Step 19537: {'lr': 0.00048287908582516964, 'samples': 3751104, 'steps': 19536, 'loss/train': 1.3489757776260376} 08/30/2021 16:44:02 - INFO - __main__ - Step 19538: {'lr': 0.00048287715571261424, 'samples': 3751296, 'steps': 19537, 'loss/train': 1.5740211009979248} 08/30/2021 16:44:03 - INFO - __main__ - Step 19539: {'lr': 0.00048287522549512806, 'samples': 3751488, 'steps': 19538, 'loss/train': 1.7897087335586548} 08/30/2021 16:44:03 - INFO - __main__ - Step 19540: {'lr': 0.0004828732951727119, 'samples': 3751680, 'steps': 19539, 'loss/train': 1.388185977935791} 08/30/2021 16:44:04 - INFO - __main__ - Step 19541: {'lr': 0.00048287136474536657, 'samples': 3751872, 'steps': 19540, 'loss/train': 1.5125842094421387} 08/30/2021 16:44:04 - INFO - __main__ - Step 19542: {'lr': 0.000482869434213093, 'samples': 3752064, 'steps': 19541, 'loss/train': 1.222025990486145} 08/30/2021 16:44:05 - INFO - __main__ - Step 19543: {'lr': 0.0004828675035758921, 'samples': 3752256, 'steps': 19542, 'loss/train': 0.8148073554039001} 08/30/2021 16:44:06 - INFO - __main__ - Step 19544: {'lr': 0.00048286557283376465, 'samples': 3752448, 'steps': 19543, 'loss/train': 1.2790478467941284} 08/30/2021 16:44:06 - INFO - __main__ - Step 19545: {'lr': 0.0004828636419867116, 'samples': 3752640, 'steps': 19544, 'loss/train': 0.9558858871459961} 08/30/2021 16:44:07 - INFO - __main__ - Step 19546: {'lr': 0.00048286171103473376, 'samples': 3752832, 'steps': 19545, 'loss/train': 1.670215368270874} 08/30/2021 16:44:07 - INFO - __main__ - Step 19547: {'lr': 0.00048285977997783203, 'samples': 3753024, 'steps': 19546, 'loss/train': 2.879312515258789} 08/30/2021 16:44:09 - INFO - __main__ - Step 19548: {'lr': 0.0004828578488160073, 'samples': 3753216, 'steps': 19547, 'loss/train': 1.5151432752609253} 08/30/2021 16:44:09 - INFO - __main__ - Step 19549: {'lr': 0.0004828559175492604, 'samples': 3753408, 'steps': 19548, 'loss/train': 1.454259991645813} 08/30/2021 16:44:09 - INFO - __main__ - Step 19550: {'lr': 0.0004828539861775922, 'samples': 3753600, 'steps': 19549, 'loss/train': 1.4162417650222778} 08/30/2021 16:44:10 - INFO - __main__ - Step 19551: {'lr': 0.0004828520547010036, 'samples': 3753792, 'steps': 19550, 'loss/train': 2.0042665004730225} 08/30/2021 16:44:10 - INFO - __main__ - Step 19552: {'lr': 0.0004828501231194955, 'samples': 3753984, 'steps': 19551, 'loss/train': 1.8019202947616577} 08/30/2021 16:44:10 - INFO - __main__ - Step 19553: {'lr': 0.0004828481914330687, 'samples': 3754176, 'steps': 19552, 'loss/train': 1.7917029857635498} 08/30/2021 16:44:13 - INFO - __main__ - Step 19554: {'lr': 0.000482846259641724, 'samples': 3754368, 'steps': 19553, 'loss/train': 0.7208302617073059} 08/30/2021 16:44:13 - INFO - __main__ - Step 19555: {'lr': 0.0004828443277454625, 'samples': 3754560, 'steps': 19554, 'loss/train': 1.9223098754882812} 08/30/2021 16:44:13 - INFO - __main__ - Step 19556: {'lr': 0.0004828423957442849, 'samples': 3754752, 'steps': 19555, 'loss/train': 1.1059141159057617} 08/30/2021 16:44:14 - INFO - __main__ - Step 19557: {'lr': 0.00048284046363819213, 'samples': 3754944, 'steps': 19556, 'loss/train': 1.0503833293914795} 08/30/2021 16:44:14 - INFO - __main__ - Step 19558: {'lr': 0.000482838531427185, 'samples': 3755136, 'steps': 19557, 'loss/train': 0.42678242921829224} 08/30/2021 16:44:14 - INFO - __main__ - Step 19559: {'lr': 0.00048283659911126445, 'samples': 3755328, 'steps': 19558, 'loss/train': 1.0968704223632812} 08/30/2021 16:44:17 - INFO - __main__ - Step 19560: {'lr': 0.0004828346666904313, 'samples': 3755520, 'steps': 19559, 'loss/train': 1.1777867078781128} 08/30/2021 16:44:18 - INFO - __main__ - Step 19561: {'lr': 0.00048283273416468644, 'samples': 3755712, 'steps': 19560, 'loss/train': 1.7494573593139648} 08/30/2021 16:44:18 - INFO - __main__ - Step 19562: {'lr': 0.0004828308015340307, 'samples': 3755904, 'steps': 19561, 'loss/train': 1.6501796245574951} 08/30/2021 16:44:18 - INFO - __main__ - Step 19563: {'lr': 0.0004828288687984651, 'samples': 3756096, 'steps': 19562, 'loss/train': 1.9800878763198853} 08/30/2021 16:44:19 - INFO - __main__ - Step 19564: {'lr': 0.0004828269359579903, 'samples': 3756288, 'steps': 19563, 'loss/train': 1.352666974067688} 08/30/2021 16:44:19 - INFO - __main__ - Step 19565: {'lr': 0.00048282500301260735, 'samples': 3756480, 'steps': 19564, 'loss/train': 1.8031508922576904} 08/30/2021 16:44:21 - INFO - __main__ - Step 19566: {'lr': 0.000482823069962317, 'samples': 3756672, 'steps': 19565, 'loss/train': 1.3478760719299316} 08/30/2021 16:44:21 - INFO - __main__ - Step 19567: {'lr': 0.0004828211368071202, 'samples': 3756864, 'steps': 19566, 'loss/train': 1.795411229133606} 08/30/2021 16:44:21 - INFO - __main__ - Step 19568: {'lr': 0.0004828192035470178, 'samples': 3757056, 'steps': 19567, 'loss/train': 1.5540285110473633} 08/30/2021 16:44:22 - INFO - __main__ - Step 19569: {'lr': 0.00048281727018201063, 'samples': 3757248, 'steps': 19568, 'loss/train': 0.5638701915740967} 08/30/2021 16:44:22 - INFO - __main__ - Step 19570: {'lr': 0.00048281533671209955, 'samples': 3757440, 'steps': 19569, 'loss/train': 1.6570943593978882} 08/30/2021 16:44:24 - INFO - __main__ - Step 19571: {'lr': 0.0004828134031372855, 'samples': 3757632, 'steps': 19570, 'loss/train': 1.484034538269043} 08/30/2021 16:44:24 - INFO - __main__ - Step 19572: {'lr': 0.00048281146945756937, 'samples': 3757824, 'steps': 19571, 'loss/train': 2.0269041061401367} 08/30/2021 16:44:25 - INFO - __main__ - Step 19573: {'lr': 0.00048280953567295196, 'samples': 3758016, 'steps': 19572, 'loss/train': 1.5945733785629272} 08/30/2021 16:44:25 - INFO - __main__ - Step 19574: {'lr': 0.0004828076017834342, 'samples': 3758208, 'steps': 19573, 'loss/train': 1.7511272430419922} 08/30/2021 16:44:25 - INFO - __main__ - Step 19575: {'lr': 0.00048280566778901684, 'samples': 3758400, 'steps': 19574, 'loss/train': 1.7083972692489624} 08/30/2021 16:44:26 - INFO - __main__ - Step 19576: {'lr': 0.00048280373368970086, 'samples': 3758592, 'steps': 19575, 'loss/train': 0.8600512742996216} 08/30/2021 16:44:27 - INFO - __main__ - Step 19577: {'lr': 0.0004828017994854872, 'samples': 3758784, 'steps': 19576, 'loss/train': 5.872617244720459} 08/30/2021 16:44:28 - INFO - __main__ - Step 19578: {'lr': 0.0004827998651763765, 'samples': 3758976, 'steps': 19577, 'loss/train': 1.3304845094680786} 08/30/2021 16:44:28 - INFO - __main__ - Step 19579: {'lr': 0.0004827979307623699, 'samples': 3759168, 'steps': 19578, 'loss/train': 1.8319852352142334} 08/30/2021 16:44:29 - INFO - __main__ - Step 19580: {'lr': 0.0004827959962434681, 'samples': 3759360, 'steps': 19579, 'loss/train': 1.463954210281372} 08/30/2021 16:44:29 - INFO - __main__ - Step 19581: {'lr': 0.00048279406161967197, 'samples': 3759552, 'steps': 19580, 'loss/train': 1.9977972507476807} 08/30/2021 16:44:29 - INFO - __main__ - Step 19582: {'lr': 0.0004827921268909825, 'samples': 3759744, 'steps': 19581, 'loss/train': 1.2031890153884888} 08/30/2021 16:44:31 - INFO - __main__ - Step 19583: {'lr': 0.0004827901920574005, 'samples': 3759936, 'steps': 19582, 'loss/train': 4.179448127746582} 08/30/2021 16:44:31 - INFO - __main__ - Step 19584: {'lr': 0.0004827882571189268, 'samples': 3760128, 'steps': 19583, 'loss/train': 1.2608264684677124} 08/30/2021 16:44:32 - INFO - __main__ - Step 19585: {'lr': 0.00048278632207556226, 'samples': 3760320, 'steps': 19584, 'loss/train': 1.7685452699661255} 08/30/2021 16:44:32 - INFO - __main__ - Step 19586: {'lr': 0.00048278438692730784, 'samples': 3760512, 'steps': 19585, 'loss/train': 1.4851990938186646} 08/30/2021 16:44:32 - INFO - __main__ - Step 19587: {'lr': 0.00048278245167416434, 'samples': 3760704, 'steps': 19586, 'loss/train': 1.9291446208953857} 08/30/2021 16:44:34 - INFO - __main__ - Step 19588: {'lr': 0.0004827805163161327, 'samples': 3760896, 'steps': 19587, 'loss/train': 1.251665472984314} 08/30/2021 16:44:34 - INFO - __main__ - Step 19589: {'lr': 0.0004827785808532137, 'samples': 3761088, 'steps': 19588, 'loss/train': 1.1816458702087402} 08/30/2021 16:44:35 - INFO - __main__ - Step 19590: {'lr': 0.0004827766452854083, 'samples': 3761280, 'steps': 19589, 'loss/train': 1.5434032678604126} 08/30/2021 16:44:35 - INFO - __main__ - Step 19591: {'lr': 0.0004827747096127173, 'samples': 3761472, 'steps': 19590, 'loss/train': 1.9463564157485962} 08/30/2021 16:44:35 - INFO - __main__ - Step 19592: {'lr': 0.00048277277383514165, 'samples': 3761664, 'steps': 19591, 'loss/train': 1.7181123495101929} 08/30/2021 16:44:37 - INFO - __main__ - Step 19593: {'lr': 0.00048277083795268216, 'samples': 3761856, 'steps': 19592, 'loss/train': 1.314265251159668} 08/30/2021 16:44:37 - INFO - __main__ - Step 19594: {'lr': 0.0004827689019653397, 'samples': 3762048, 'steps': 19593, 'loss/train': 2.241570234298706} 08/30/2021 16:44:38 - INFO - __main__ - Step 19595: {'lr': 0.00048276696587311525, 'samples': 3762240, 'steps': 19594, 'loss/train': 2.594907283782959} 08/30/2021 16:44:38 - INFO - __main__ - Step 19596: {'lr': 0.00048276502967600955, 'samples': 3762432, 'steps': 19595, 'loss/train': 1.2087441682815552} 08/30/2021 16:44:38 - INFO - __main__ - Step 19597: {'lr': 0.00048276309337402345, 'samples': 3762624, 'steps': 19596, 'loss/train': 1.221699833869934} 08/30/2021 16:44:40 - INFO - __main__ - Step 19598: {'lr': 0.000482761156967158, 'samples': 3762816, 'steps': 19597, 'loss/train': 0.21570028364658356} 08/30/2021 16:44:40 - INFO - __main__ - Step 19599: {'lr': 0.0004827592204554139, 'samples': 3763008, 'steps': 19598, 'loss/train': 1.727426290512085} 08/30/2021 16:44:41 - INFO - __main__ - Step 19600: {'lr': 0.00048275728383879215, 'samples': 3763200, 'steps': 19599, 'loss/train': 2.093048572540283} 08/30/2021 16:44:41 - INFO - __main__ - Step 19601: {'lr': 0.0004827553471172935, 'samples': 3763392, 'steps': 19600, 'loss/train': 1.3071701526641846} 08/30/2021 16:44:41 - INFO - __main__ - Step 19602: {'lr': 0.00048275341029091885, 'samples': 3763584, 'steps': 19601, 'loss/train': 1.304287075996399} 08/30/2021 16:44:42 - INFO - __main__ - Step 19603: {'lr': 0.0004827514733596692, 'samples': 3763776, 'steps': 19602, 'loss/train': 1.56734037399292} 08/30/2021 16:44:43 - INFO - __main__ - Step 19604: {'lr': 0.00048274953632354524, 'samples': 3763968, 'steps': 19603, 'loss/train': 1.830305814743042} 08/30/2021 16:44:44 - INFO - __main__ - Step 19605: {'lr': 0.000482747599182548, 'samples': 3764160, 'steps': 19604, 'loss/train': 1.419538140296936} 08/30/2021 16:44:44 - INFO - __main__ - Step 19606: {'lr': 0.00048274566193667824, 'samples': 3764352, 'steps': 19605, 'loss/train': 1.2372103929519653} 08/30/2021 16:44:45 - INFO - __main__ - Step 19607: {'lr': 0.0004827437245859369, 'samples': 3764544, 'steps': 19606, 'loss/train': 1.2850303649902344} 08/30/2021 16:44:45 - INFO - __main__ - Step 19608: {'lr': 0.0004827417871303248, 'samples': 3764736, 'steps': 19607, 'loss/train': 0.9325003027915955} 08/30/2021 16:44:47 - INFO - __main__ - Step 19609: {'lr': 0.00048273984956984285, 'samples': 3764928, 'steps': 19608, 'loss/train': 1.6945222616195679} 08/30/2021 16:44:47 - INFO - __main__ - Step 19610: {'lr': 0.0004827379119044919, 'samples': 3765120, 'steps': 19609, 'loss/train': 2.009012460708618} 08/30/2021 16:44:47 - INFO - __main__ - Step 19611: {'lr': 0.00048273597413427284, 'samples': 3765312, 'steps': 19610, 'loss/train': 0.20731039345264435} 08/30/2021 16:44:48 - INFO - __main__ - Step 19612: {'lr': 0.00048273403625918653, 'samples': 3765504, 'steps': 19611, 'loss/train': 1.801841139793396} 08/30/2021 16:44:48 - INFO - __main__ - Step 19613: {'lr': 0.0004827320982792339, 'samples': 3765696, 'steps': 19612, 'loss/train': 1.930281639099121} 08/30/2021 16:44:50 - INFO - __main__ - Step 19614: {'lr': 0.00048273016019441585, 'samples': 3765888, 'steps': 19613, 'loss/train': 2.790879487991333} 08/30/2021 16:44:50 - INFO - __main__ - Step 19615: {'lr': 0.00048272822200473304, 'samples': 3766080, 'steps': 19614, 'loss/train': 0.7464519739151001} 08/30/2021 16:44:51 - INFO - __main__ - Step 19616: {'lr': 0.0004827262837101866, 'samples': 3766272, 'steps': 19615, 'loss/train': 1.577192783355713} 08/30/2021 16:44:51 - INFO - __main__ - Step 19617: {'lr': 0.0004827243453107772, 'samples': 3766464, 'steps': 19616, 'loss/train': 1.2627135515213013} 08/30/2021 16:44:51 - INFO - __main__ - Step 19618: {'lr': 0.0004827224068065058, 'samples': 3766656, 'steps': 19617, 'loss/train': 2.4496021270751953} 08/30/2021 16:44:53 - INFO - __main__ - Step 19619: {'lr': 0.0004827204681973733, 'samples': 3766848, 'steps': 19618, 'loss/train': 1.3852035999298096} 08/30/2021 16:44:54 - INFO - __main__ - Step 19620: {'lr': 0.00048271852948338057, 'samples': 3767040, 'steps': 19619, 'loss/train': 2.0666980743408203} 08/30/2021 16:44:54 - INFO - __main__ - Step 19621: {'lr': 0.00048271659066452847, 'samples': 3767232, 'steps': 19620, 'loss/train': 6.3381547927856445} 08/30/2021 16:44:55 - INFO - __main__ - Step 19622: {'lr': 0.0004827146517408178, 'samples': 3767424, 'steps': 19621, 'loss/train': 1.6556847095489502} 08/30/2021 16:44:55 - INFO - __main__ - Step 19623: {'lr': 0.0004827127127122495, 'samples': 3767616, 'steps': 19622, 'loss/train': 1.4426981210708618} 08/30/2021 16:44:55 - INFO - __main__ - Step 19624: {'lr': 0.00048271077357882455, 'samples': 3767808, 'steps': 19623, 'loss/train': 0.5524057745933533} 08/30/2021 16:44:57 - INFO - __main__ - Step 19625: {'lr': 0.00048270883434054364, 'samples': 3768000, 'steps': 19624, 'loss/train': 1.514841914176941} 08/30/2021 16:44:57 - INFO - __main__ - Step 19626: {'lr': 0.00048270689499740774, 'samples': 3768192, 'steps': 19625, 'loss/train': 1.9654330015182495} 08/30/2021 16:44:58 - INFO - __main__ - Step 19627: {'lr': 0.0004827049555494176, 'samples': 3768384, 'steps': 19626, 'loss/train': 1.2500262260437012} 08/30/2021 16:44:58 - INFO - __main__ - Step 19628: {'lr': 0.00048270301599657436, 'samples': 3768576, 'steps': 19627, 'loss/train': 1.5800343751907349} 08/30/2021 16:44:58 - INFO - __main__ - Step 19629: {'lr': 0.0004827010763388786, 'samples': 3768768, 'steps': 19628, 'loss/train': 1.7905545234680176} 08/30/2021 16:44:59 - INFO - __main__ - Step 19630: {'lr': 0.00048269913657633147, 'samples': 3768960, 'steps': 19629, 'loss/train': 1.5206153392791748} 08/30/2021 16:45:00 - INFO - __main__ - Step 19631: {'lr': 0.00048269719670893357, 'samples': 3769152, 'steps': 19630, 'loss/train': 1.2802495956420898} 08/30/2021 16:45:01 - INFO - __main__ - Step 19632: {'lr': 0.00048269525673668595, 'samples': 3769344, 'steps': 19631, 'loss/train': 1.1612682342529297} 08/30/2021 16:45:01 - INFO - __main__ - Step 19633: {'lr': 0.00048269331665958947, 'samples': 3769536, 'steps': 19632, 'loss/train': 1.210286021232605} 08/30/2021 16:45:02 - INFO - __main__ - Step 19634: {'lr': 0.00048269137647764495, 'samples': 3769728, 'steps': 19633, 'loss/train': 1.4296683073043823} 08/30/2021 16:45:02 - INFO - __main__ - Step 19635: {'lr': 0.00048268943619085325, 'samples': 3769920, 'steps': 19634, 'loss/train': 2.321168899536133} 08/30/2021 16:45:04 - INFO - __main__ - Step 19636: {'lr': 0.00048268749579921536, 'samples': 3770112, 'steps': 19635, 'loss/train': 1.4415132999420166} 08/30/2021 16:45:04 - INFO - __main__ - Step 19637: {'lr': 0.00048268555530273197, 'samples': 3770304, 'steps': 19636, 'loss/train': 0.2824762761592865} 08/30/2021 16:45:04 - INFO - __main__ - Step 19638: {'lr': 0.0004826836147014041, 'samples': 3770496, 'steps': 19637, 'loss/train': 1.977523922920227} 08/30/2021 16:45:05 - INFO - __main__ - Step 19639: {'lr': 0.0004826816739952326, 'samples': 3770688, 'steps': 19638, 'loss/train': 1.6820950508117676} 08/30/2021 16:45:05 - INFO - __main__ - Step 19640: {'lr': 0.0004826797331842183, 'samples': 3770880, 'steps': 19639, 'loss/train': 2.1210596561431885} 08/30/2021 16:45:07 - INFO - __main__ - Step 19641: {'lr': 0.0004826777922683622, 'samples': 3771072, 'steps': 19640, 'loss/train': 1.9992430210113525} 08/30/2021 16:45:07 - INFO - __main__ - Step 19642: {'lr': 0.0004826758512476649, 'samples': 3771264, 'steps': 19641, 'loss/train': 2.0058212280273438} 08/30/2021 16:45:08 - INFO - __main__ - Step 19643: {'lr': 0.0004826739101221276, 'samples': 3771456, 'steps': 19642, 'loss/train': 1.8318320512771606} 08/30/2021 16:45:08 - INFO - __main__ - Step 19644: {'lr': 0.000482671968891751, 'samples': 3771648, 'steps': 19643, 'loss/train': 1.7951756715774536} 08/30/2021 16:45:08 - INFO - __main__ - Step 19645: {'lr': 0.000482670027556536, 'samples': 3771840, 'steps': 19644, 'loss/train': 1.7677150964736938} 08/30/2021 16:45:09 - INFO - __main__ - Step 19646: {'lr': 0.0004826680861164834, 'samples': 3772032, 'steps': 19645, 'loss/train': 1.8392150402069092} 08/30/2021 16:45:10 - INFO - __main__ - Step 19647: {'lr': 0.00048266614457159426, 'samples': 3772224, 'steps': 19646, 'loss/train': 1.3000612258911133} 08/30/2021 16:45:11 - INFO - __main__ - Step 19648: {'lr': 0.0004826642029218693, 'samples': 3772416, 'steps': 19647, 'loss/train': 1.3055709600448608} 08/30/2021 16:45:11 - INFO - __main__ - Step 19649: {'lr': 0.00048266226116730937, 'samples': 3772608, 'steps': 19648, 'loss/train': 1.7779978513717651} 08/30/2021 16:45:11 - INFO - __main__ - Step 19650: {'lr': 0.00048266031930791555, 'samples': 3772800, 'steps': 19649, 'loss/train': 1.8078025579452515} 08/30/2021 16:45:12 - INFO - __main__ - Step 19651: {'lr': 0.0004826583773436884, 'samples': 3772992, 'steps': 19650, 'loss/train': 1.2400726079940796} 08/30/2021 16:45:13 - INFO - __main__ - Step 19652: {'lr': 0.00048265643527462915, 'samples': 3773184, 'steps': 19651, 'loss/train': 1.1456602811813354} 08/30/2021 16:45:14 - INFO - __main__ - Step 19653: {'lr': 0.00048265449310073847, 'samples': 3773376, 'steps': 19652, 'loss/train': 1.620891809463501} 08/30/2021 16:45:14 - INFO - __main__ - Step 19654: {'lr': 0.0004826525508220172, 'samples': 3773568, 'steps': 19653, 'loss/train': 1.7850602865219116} 08/30/2021 16:45:15 - INFO - __main__ - Step 19655: {'lr': 0.0004826506084384663, 'samples': 3773760, 'steps': 19654, 'loss/train': 0.13912451267242432} 08/30/2021 16:45:15 - INFO - __main__ - Step 19656: {'lr': 0.00048264866595008665, 'samples': 3773952, 'steps': 19655, 'loss/train': 1.826074481010437} 08/30/2021 16:45:17 - INFO - __main__ - Step 19657: {'lr': 0.0004826467233568791, 'samples': 3774144, 'steps': 19656, 'loss/train': 1.2786715030670166} 08/30/2021 16:45:17 - INFO - __main__ - Step 19658: {'lr': 0.00048264478065884454, 'samples': 3774336, 'steps': 19657, 'loss/train': 1.6209207773208618} 08/30/2021 16:45:18 - INFO - __main__ - Step 19659: {'lr': 0.0004826428378559838, 'samples': 3774528, 'steps': 19658, 'loss/train': 1.7213256359100342} 08/30/2021 16:45:18 - INFO - __main__ - Step 19660: {'lr': 0.00048264089494829776, 'samples': 3774720, 'steps': 19659, 'loss/train': 0.07078750431537628} 08/30/2021 16:45:18 - INFO - __main__ - Step 19661: {'lr': 0.0004826389519357874, 'samples': 3774912, 'steps': 19660, 'loss/train': 1.532974362373352} 08/30/2021 16:45:19 - INFO - __main__ - Step 19662: {'lr': 0.00048263700881845346, 'samples': 3775104, 'steps': 19661, 'loss/train': 1.3122813701629639} 08/30/2021 16:45:20 - INFO - __main__ - Step 19663: {'lr': 0.00048263506559629687, 'samples': 3775296, 'steps': 19662, 'loss/train': 1.125578761100769} 08/30/2021 16:45:21 - INFO - __main__ - Step 19664: {'lr': 0.00048263312226931853, 'samples': 3775488, 'steps': 19663, 'loss/train': 2.198880434036255} 08/30/2021 16:45:21 - INFO - __main__ - Step 19665: {'lr': 0.0004826311788375193, 'samples': 3775680, 'steps': 19664, 'loss/train': 1.7454428672790527} 08/30/2021 16:45:21 - INFO - __main__ - Step 19666: {'lr': 0.00048262923530090007, 'samples': 3775872, 'steps': 19665, 'loss/train': 1.5772764682769775} 08/30/2021 16:45:22 - INFO - __main__ - Step 19667: {'lr': 0.0004826272916594616, 'samples': 3776064, 'steps': 19666, 'loss/train': 1.87223482131958} 08/30/2021 16:45:23 - INFO - __main__ - Step 19668: {'lr': 0.000482625347913205, 'samples': 3776256, 'steps': 19667, 'loss/train': 1.2227168083190918} 08/30/2021 16:45:23 - INFO - __main__ - Step 19669: {'lr': 0.0004826234040621309, 'samples': 3776448, 'steps': 19668, 'loss/train': 0.7310164570808411} 08/30/2021 16:45:24 - INFO - __main__ - Step 19670: {'lr': 0.00048262146010624035, 'samples': 3776640, 'steps': 19669, 'loss/train': 0.8155099749565125} 08/30/2021 16:45:24 - INFO - __main__ - Step 19671: {'lr': 0.0004826195160455341, 'samples': 3776832, 'steps': 19670, 'loss/train': 1.195999264717102} 08/30/2021 16:45:25 - INFO - __main__ - Step 19672: {'lr': 0.00048261757188001314, 'samples': 3777024, 'steps': 19671, 'loss/train': 1.8243367671966553} 08/30/2021 16:45:25 - INFO - __main__ - Step 19673: {'lr': 0.00048261562760967824, 'samples': 3777216, 'steps': 19672, 'loss/train': 1.3731988668441772} 08/30/2021 16:45:27 - INFO - __main__ - Step 19674: {'lr': 0.0004826136832345304, 'samples': 3777408, 'steps': 19673, 'loss/train': 1.8078889846801758} 08/30/2021 16:45:27 - INFO - __main__ - Step 19675: {'lr': 0.00048261173875457035, 'samples': 3777600, 'steps': 19674, 'loss/train': 1.550720453262329} 08/30/2021 16:45:28 - INFO - __main__ - Step 19676: {'lr': 0.0004826097941697991, 'samples': 3777792, 'steps': 19675, 'loss/train': 1.763080358505249} 08/30/2021 16:45:28 - INFO - __main__ - Step 19677: {'lr': 0.0004826078494802174, 'samples': 3777984, 'steps': 19676, 'loss/train': 0.2705342173576355} 08/30/2021 16:45:28 - INFO - __main__ - Step 19678: {'lr': 0.00048260590468582624, 'samples': 3778176, 'steps': 19677, 'loss/train': 1.0702122449874878} 08/30/2021 16:45:30 - INFO - __main__ - Step 19679: {'lr': 0.0004826039597866265, 'samples': 3778368, 'steps': 19678, 'loss/train': 1.5734738111495972} 08/30/2021 16:45:31 - INFO - __main__ - Step 19680: {'lr': 0.00048260201478261887, 'samples': 3778560, 'steps': 19679, 'loss/train': 1.3631218671798706} 08/30/2021 16:45:31 - INFO - __main__ - Step 19681: {'lr': 0.0004826000696738045, 'samples': 3778752, 'steps': 19680, 'loss/train': 1.1993298530578613} 08/30/2021 16:45:31 - INFO - __main__ - Step 19682: {'lr': 0.000482598124460184, 'samples': 3778944, 'steps': 19681, 'loss/train': 1.9589277505874634} 08/30/2021 16:45:32 - INFO - __main__ - Step 19683: {'lr': 0.00048259617914175846, 'samples': 3779136, 'steps': 19682, 'loss/train': 1.520262360572815} 08/30/2021 16:45:33 - INFO - __main__ - Step 19684: {'lr': 0.00048259423371852867, 'samples': 3779328, 'steps': 19683, 'loss/train': 1.4517934322357178} 08/30/2021 16:45:34 - INFO - __main__ - Step 19685: {'lr': 0.0004825922881904955, 'samples': 3779520, 'steps': 19684, 'loss/train': 1.9209898710250854} 08/30/2021 16:45:34 - INFO - __main__ - Step 19686: {'lr': 0.00048259034255765984, 'samples': 3779712, 'steps': 19685, 'loss/train': 1.4244006872177124} 08/30/2021 16:45:34 - INFO - __main__ - Step 19687: {'lr': 0.00048258839682002253, 'samples': 3779904, 'steps': 19686, 'loss/train': 1.7588123083114624} 08/30/2021 16:45:35 - INFO - __main__ - Step 19688: {'lr': 0.00048258645097758445, 'samples': 3780096, 'steps': 19687, 'loss/train': 1.736598014831543} 08/30/2021 16:45:36 - INFO - __main__ - Step 19689: {'lr': 0.0004825845050303466, 'samples': 3780288, 'steps': 19688, 'loss/train': 1.4805346727371216} 08/30/2021 16:45:37 - INFO - __main__ - Step 19690: {'lr': 0.00048258255897830967, 'samples': 3780480, 'steps': 19689, 'loss/train': 1.5934196710586548} 08/30/2021 16:45:37 - INFO - __main__ - Step 19691: {'lr': 0.0004825806128214747, 'samples': 3780672, 'steps': 19690, 'loss/train': 1.61527419090271} 08/30/2021 16:45:37 - INFO - __main__ - Step 19692: {'lr': 0.00048257866655984237, 'samples': 3780864, 'steps': 19691, 'loss/train': 1.6771128177642822} 08/30/2021 16:45:38 - INFO - __main__ - Step 19693: {'lr': 0.0004825767201934138, 'samples': 3781056, 'steps': 19692, 'loss/train': 1.5107687711715698} 08/30/2021 16:45:39 - INFO - __main__ - Step 19694: {'lr': 0.0004825747737221897, 'samples': 3781248, 'steps': 19693, 'loss/train': 1.7452632188796997} 08/30/2021 16:45:40 - INFO - __main__ - Step 19695: {'lr': 0.000482572827146171, 'samples': 3781440, 'steps': 19694, 'loss/train': 1.260412335395813} 08/30/2021 16:45:40 - INFO - __main__ - Step 19696: {'lr': 0.00048257088046535864, 'samples': 3781632, 'steps': 19695, 'loss/train': 1.8159458637237549} 08/30/2021 16:45:41 - INFO - __main__ - Step 19697: {'lr': 0.0004825689336797534, 'samples': 3781824, 'steps': 19696, 'loss/train': 1.7496967315673828} 08/30/2021 16:45:41 - INFO - __main__ - Step 19698: {'lr': 0.00048256698678935615, 'samples': 3782016, 'steps': 19697, 'loss/train': 6.348109245300293} 08/30/2021 16:45:41 - INFO - __main__ - Step 19699: {'lr': 0.00048256503979416776, 'samples': 3782208, 'steps': 19698, 'loss/train': 2.1363143920898438} 08/30/2021 16:45:43 - INFO - __main__ - Step 19700: {'lr': 0.0004825630926941892, 'samples': 3782400, 'steps': 19699, 'loss/train': 0.06274674832820892} 08/30/2021 16:45:43 - INFO - __main__ - Step 19701: {'lr': 0.0004825611454894213, 'samples': 3782592, 'steps': 19700, 'loss/train': 1.3938616514205933} 08/30/2021 16:45:44 - INFO - __main__ - Step 19702: {'lr': 0.000482559198179865, 'samples': 3782784, 'steps': 19701, 'loss/train': 1.8158903121948242} 08/30/2021 16:45:44 - INFO - __main__ - Step 19703: {'lr': 0.00048255725076552103, 'samples': 3782976, 'steps': 19702, 'loss/train': 1.9675157070159912} 08/30/2021 16:45:44 - INFO - __main__ - Step 19704: {'lr': 0.0004825553032463904, 'samples': 3783168, 'steps': 19703, 'loss/train': 1.5207316875457764} 08/30/2021 16:45:45 - INFO - __main__ - Step 19705: {'lr': 0.00048255335562247395, 'samples': 3783360, 'steps': 19704, 'loss/train': 1.7516065835952759} 08/30/2021 16:45:46 - INFO - __main__ - Step 19706: {'lr': 0.0004825514078937725, 'samples': 3783552, 'steps': 19705, 'loss/train': 1.459518313407898} 08/30/2021 16:45:47 - INFO - __main__ - Step 19707: {'lr': 0.000482549460060287, 'samples': 3783744, 'steps': 19706, 'loss/train': 1.0809588432312012} 08/30/2021 16:45:47 - INFO - __main__ - Step 19708: {'lr': 0.0004825475121220183, 'samples': 3783936, 'steps': 19707, 'loss/train': 1.7737821340560913} 08/30/2021 16:45:47 - INFO - __main__ - Step 19709: {'lr': 0.0004825455640789672, 'samples': 3784128, 'steps': 19708, 'loss/train': 1.630860447883606} 08/30/2021 16:45:48 - INFO - __main__ - Step 19710: {'lr': 0.00048254361593113475, 'samples': 3784320, 'steps': 19709, 'loss/train': 1.9221594333648682} 08/30/2021 16:45:49 - INFO - __main__ - Step 19711: {'lr': 0.0004825416676785217, 'samples': 3784512, 'steps': 19710, 'loss/train': 2.125366687774658} 08/30/2021 16:45:50 - INFO - __main__ - Step 19712: {'lr': 0.000482539719321129, 'samples': 3784704, 'steps': 19711, 'loss/train': 1.2897369861602783} 08/30/2021 16:45:50 - INFO - __main__ - Step 19713: {'lr': 0.00048253777085895745, 'samples': 3784896, 'steps': 19712, 'loss/train': 1.3967864513397217} 08/30/2021 16:45:50 - INFO - __main__ - Step 19714: {'lr': 0.000482535822292008, 'samples': 3785088, 'steps': 19713, 'loss/train': 1.3750593662261963} 08/30/2021 16:45:51 - INFO - __main__ - Step 19715: {'lr': 0.0004825338736202815, 'samples': 3785280, 'steps': 19714, 'loss/train': 1.3700599670410156} 08/30/2021 16:45:52 - INFO - __main__ - Step 19716: {'lr': 0.00048253192484377884, 'samples': 3785472, 'steps': 19715, 'loss/train': 1.6668800115585327} 08/30/2021 16:45:53 - INFO - __main__ - Step 19717: {'lr': 0.0004825299759625008, 'samples': 3785664, 'steps': 19716, 'loss/train': 1.5117876529693604} 08/30/2021 16:45:53 - INFO - __main__ - Step 19718: {'lr': 0.0004825280269764484, 'samples': 3785856, 'steps': 19717, 'loss/train': 1.9901987314224243} 08/30/2021 16:45:53 - INFO - __main__ - Step 19719: {'lr': 0.0004825260778856224, 'samples': 3786048, 'steps': 19718, 'loss/train': 1.9022563695907593} 08/30/2021 16:45:54 - INFO - __main__ - Step 19720: {'lr': 0.0004825241286900238, 'samples': 3786240, 'steps': 19719, 'loss/train': 1.249380111694336} 08/30/2021 16:45:55 - INFO - __main__ - Step 19721: {'lr': 0.0004825221793896535, 'samples': 3786432, 'steps': 19720, 'loss/train': 2.0074994564056396} 08/30/2021 16:45:56 - INFO - __main__ - Step 19722: {'lr': 0.0004825202299845122, 'samples': 3786624, 'steps': 19721, 'loss/train': 2.1659655570983887} 08/30/2021 16:45:56 - INFO - __main__ - Step 19723: {'lr': 0.00048251828047460077, 'samples': 3786816, 'steps': 19722, 'loss/train': 1.6186447143554688} 08/30/2021 16:45:56 - INFO - __main__ - Step 19724: {'lr': 0.0004825163308599203, 'samples': 3787008, 'steps': 19723, 'loss/train': 1.5282928943634033} 08/30/2021 16:45:57 - INFO - __main__ - Step 19725: {'lr': 0.0004825143811404716, 'samples': 3787200, 'steps': 19724, 'loss/train': 1.08818519115448} 08/30/2021 16:45:59 - INFO - __main__ - Step 19726: {'lr': 0.00048251243131625543, 'samples': 3787392, 'steps': 19725, 'loss/train': 1.213646411895752} 08/30/2021 16:45:59 - INFO - __main__ - Step 19727: {'lr': 0.0004825104813872728, 'samples': 3787584, 'steps': 19726, 'loss/train': 1.608264446258545} 08/30/2021 16:46:00 - INFO - __main__ - Step 19728: {'lr': 0.0004825085313535245, 'samples': 3787776, 'steps': 19727, 'loss/train': 1.5605945587158203} 08/30/2021 16:46:00 - INFO - __main__ - Step 19729: {'lr': 0.00048250658121501145, 'samples': 3787968, 'steps': 19728, 'loss/train': 2.1500375270843506} 08/30/2021 16:46:00 - INFO - __main__ - Step 19730: {'lr': 0.00048250463097173447, 'samples': 3788160, 'steps': 19729, 'loss/train': 1.2001900672912598} 08/30/2021 16:46:02 - INFO - __main__ - Step 19731: {'lr': 0.0004825026806236946, 'samples': 3788352, 'steps': 19730, 'loss/train': 1.7775330543518066} 08/30/2021 16:46:02 - INFO - __main__ - Step 19732: {'lr': 0.00048250073017089257, 'samples': 3788544, 'steps': 19731, 'loss/train': 1.0759825706481934} 08/30/2021 16:46:03 - INFO - __main__ - Step 19733: {'lr': 0.00048249877961332923, 'samples': 3788736, 'steps': 19732, 'loss/train': 2.6747982501983643} 08/30/2021 16:46:03 - INFO - __main__ - Step 19734: {'lr': 0.0004824968289510056, 'samples': 3788928, 'steps': 19733, 'loss/train': 1.3608564138412476} 08/30/2021 16:46:03 - INFO - __main__ - Step 19735: {'lr': 0.0004824948781839225, 'samples': 3789120, 'steps': 19734, 'loss/train': 1.852820873260498} 08/30/2021 16:46:05 - INFO - __main__ - Step 19736: {'lr': 0.0004824929273120807, 'samples': 3789312, 'steps': 19735, 'loss/train': 1.777243971824646} 08/30/2021 16:46:05 - INFO - __main__ - Step 19737: {'lr': 0.0004824909763354813, 'samples': 3789504, 'steps': 19736, 'loss/train': 1.8846819400787354} 08/30/2021 16:46:06 - INFO - __main__ - Step 19738: {'lr': 0.00048248902525412497, 'samples': 3789696, 'steps': 19737, 'loss/train': 1.4429880380630493} 08/30/2021 16:46:06 - INFO - __main__ - Step 19739: {'lr': 0.0004824870740680127, 'samples': 3789888, 'steps': 19738, 'loss/train': 1.995111107826233} 08/30/2021 16:46:07 - INFO - __main__ - Step 19740: {'lr': 0.0004824851227771453, 'samples': 3790080, 'steps': 19739, 'loss/train': 1.3590061664581299} 08/30/2021 16:46:07 - INFO - __main__ - Step 19741: {'lr': 0.00048248317138152374, 'samples': 3790272, 'steps': 19740, 'loss/train': 1.6957652568817139} 08/30/2021 16:46:08 - INFO - __main__ - Step 19742: {'lr': 0.00048248121988114887, 'samples': 3790464, 'steps': 19741, 'loss/train': 2.3059370517730713} 08/30/2021 16:46:09 - INFO - __main__ - Step 19743: {'lr': 0.00048247926827602153, 'samples': 3790656, 'steps': 19742, 'loss/train': 1.349485158920288} 08/30/2021 16:46:09 - INFO - __main__ - Step 19744: {'lr': 0.0004824773165661426, 'samples': 3790848, 'steps': 19743, 'loss/train': 1.3163179159164429} 08/30/2021 16:46:10 - INFO - __main__ - Step 19745: {'lr': 0.000482475364751513, 'samples': 3791040, 'steps': 19744, 'loss/train': 1.5471094846725464} 08/30/2021 16:46:10 - INFO - __main__ - Step 19746: {'lr': 0.0004824734128321335, 'samples': 3791232, 'steps': 19745, 'loss/train': 1.1037479639053345} 08/30/2021 16:46:11 - INFO - __main__ - Step 19747: {'lr': 0.0004824714608080052, 'samples': 3791424, 'steps': 19746, 'loss/train': 1.6759765148162842} 08/30/2021 16:46:12 - INFO - __main__ - Step 19748: {'lr': 0.00048246950867912873, 'samples': 3791616, 'steps': 19747, 'loss/train': 1.7748245000839233} 08/30/2021 16:46:12 - INFO - __main__ - Step 19749: {'lr': 0.0004824675564455052, 'samples': 3791808, 'steps': 19748, 'loss/train': 1.7343673706054688} 08/30/2021 16:46:13 - INFO - __main__ - Step 19750: {'lr': 0.0004824656041071353, 'samples': 3792000, 'steps': 19749, 'loss/train': 1.4536768198013306} 08/30/2021 16:46:13 - INFO - __main__ - Step 19751: {'lr': 0.00048246365166402003, 'samples': 3792192, 'steps': 19750, 'loss/train': 1.4853363037109375} 08/30/2021 16:46:14 - INFO - __main__ - Step 19752: {'lr': 0.00048246169911616015, 'samples': 3792384, 'steps': 19751, 'loss/train': 2.1229076385498047} 08/30/2021 16:46:15 - INFO - __main__ - Step 19753: {'lr': 0.00048245974646355673, 'samples': 3792576, 'steps': 19752, 'loss/train': 1.5881577730178833} 08/30/2021 16:46:15 - INFO - __main__ - Step 19754: {'lr': 0.00048245779370621045, 'samples': 3792768, 'steps': 19753, 'loss/train': 0.0828220397233963} 08/30/2021 16:46:16 - INFO - __main__ - Step 19755: {'lr': 0.0004824558408441223, 'samples': 3792960, 'steps': 19754, 'loss/train': 1.7623757123947144} 08/30/2021 16:46:16 - INFO - __main__ - Step 19756: {'lr': 0.00048245388787729316, 'samples': 3793152, 'steps': 19755, 'loss/train': 1.5343509912490845} 08/30/2021 16:46:18 - INFO - __main__ - Step 19757: {'lr': 0.00048245193480572383, 'samples': 3793344, 'steps': 19756, 'loss/train': 1.145225167274475} 08/30/2021 16:46:18 - INFO - __main__ - Step 19758: {'lr': 0.0004824499816294152, 'samples': 3793536, 'steps': 19757, 'loss/train': 1.65183424949646} 08/30/2021 16:46:18 - INFO - __main__ - Step 19759: {'lr': 0.0004824480283483683, 'samples': 3793728, 'steps': 19758, 'loss/train': 1.3957730531692505} 08/30/2021 16:46:19 - INFO - __main__ - Step 19760: {'lr': 0.0004824460749625839, 'samples': 3793920, 'steps': 19759, 'loss/train': 0.8056812286376953} 08/30/2021 16:46:19 - INFO - __main__ - Step 19761: {'lr': 0.00048244412147206283, 'samples': 3794112, 'steps': 19760, 'loss/train': 1.4695429801940918} 08/30/2021 16:46:21 - INFO - __main__ - Step 19762: {'lr': 0.00048244216787680607, 'samples': 3794304, 'steps': 19761, 'loss/train': 1.407184362411499} 08/30/2021 16:46:21 - INFO - __main__ - Step 19763: {'lr': 0.0004824402141768145, 'samples': 3794496, 'steps': 19762, 'loss/train': 1.706057071685791} 08/30/2021 16:46:21 - INFO - __main__ - Step 19764: {'lr': 0.0004824382603720888, 'samples': 3794688, 'steps': 19763, 'loss/train': 1.8974753618240356} 08/30/2021 16:46:22 - INFO - __main__ - Step 19765: {'lr': 0.00048243630646263016, 'samples': 3794880, 'steps': 19764, 'loss/train': 1.7434874773025513} 08/30/2021 16:46:22 - INFO - __main__ - Step 19766: {'lr': 0.00048243435244843926, 'samples': 3795072, 'steps': 19765, 'loss/train': 1.6711057424545288} 08/30/2021 16:46:22 - INFO - __main__ - Step 19767: {'lr': 0.000482432398329517, 'samples': 3795264, 'steps': 19766, 'loss/train': 1.4974653720855713} 08/30/2021 16:46:24 - INFO - __main__ - Step 19768: {'lr': 0.00048243044410586433, 'samples': 3795456, 'steps': 19767, 'loss/train': 1.5653835535049438} 08/30/2021 16:46:24 - INFO - __main__ - Step 19769: {'lr': 0.00048242848977748205, 'samples': 3795648, 'steps': 19768, 'loss/train': 0.8201896548271179} 08/30/2021 16:46:25 - INFO - __main__ - Step 19770: {'lr': 0.0004824265353443711, 'samples': 3795840, 'steps': 19769, 'loss/train': 1.5632750988006592} 08/30/2021 16:46:25 - INFO - __main__ - Step 19771: {'lr': 0.00048242458080653233, 'samples': 3796032, 'steps': 19770, 'loss/train': 1.306421160697937} 08/30/2021 16:46:26 - INFO - __main__ - Step 19772: {'lr': 0.0004824226261639666, 'samples': 3796224, 'steps': 19771, 'loss/train': 1.869511604309082} 08/30/2021 16:46:27 - INFO - __main__ - Step 19773: {'lr': 0.00048242067141667487, 'samples': 3796416, 'steps': 19772, 'loss/train': 1.3827139139175415} 08/30/2021 16:46:28 - INFO - __main__ - Step 19774: {'lr': 0.00048241871656465795, 'samples': 3796608, 'steps': 19773, 'loss/train': 0.756730854511261} 08/30/2021 16:46:28 - INFO - __main__ - Step 19775: {'lr': 0.0004824167616079168, 'samples': 3796800, 'steps': 19774, 'loss/train': 1.6832746267318726} 08/30/2021 16:46:28 - INFO - __main__ - Step 19776: {'lr': 0.0004824148065464522, 'samples': 3796992, 'steps': 19775, 'loss/train': 1.5018789768218994} 08/30/2021 16:46:29 - INFO - __main__ - Step 19777: {'lr': 0.00048241285138026505, 'samples': 3797184, 'steps': 19776, 'loss/train': 1.9354379177093506} 08/30/2021 16:46:30 - INFO - __main__ - Step 19778: {'lr': 0.00048241089610935627, 'samples': 3797376, 'steps': 19777, 'loss/train': 1.5387619733810425} 08/30/2021 16:46:31 - INFO - __main__ - Step 19779: {'lr': 0.0004824089407337267, 'samples': 3797568, 'steps': 19778, 'loss/train': 1.7963557243347168} 08/30/2021 16:46:31 - INFO - __main__ - Step 19780: {'lr': 0.00048240698525337726, 'samples': 3797760, 'steps': 19779, 'loss/train': 1.811444878578186} 08/30/2021 16:46:31 - INFO - __main__ - Step 19781: {'lr': 0.0004824050296683089, 'samples': 3797952, 'steps': 19780, 'loss/train': 1.7149640321731567} 08/30/2021 16:46:32 - INFO - __main__ - Step 19782: {'lr': 0.0004824030739785223, 'samples': 3798144, 'steps': 19781, 'loss/train': 1.2311028242111206} 08/30/2021 16:46:32 - INFO - __main__ - Step 19783: {'lr': 0.00048240111818401854, 'samples': 3798336, 'steps': 19782, 'loss/train': 1.7671340703964233} 08/30/2021 16:46:34 - INFO - __main__ - Step 19784: {'lr': 0.0004823991622847984, 'samples': 3798528, 'steps': 19783, 'loss/train': 1.5080082416534424} 08/30/2021 16:46:35 - INFO - __main__ - Step 19785: {'lr': 0.0004823972062808628, 'samples': 3798720, 'steps': 19784, 'loss/train': 1.4996699094772339} 08/30/2021 16:46:35 - INFO - __main__ - Step 19786: {'lr': 0.0004823952501722126, 'samples': 3798912, 'steps': 19785, 'loss/train': 1.8464879989624023} 08/30/2021 16:46:35 - INFO - __main__ - Step 19787: {'lr': 0.00048239329395884865, 'samples': 3799104, 'steps': 19786, 'loss/train': 1.6811447143554688} 08/30/2021 16:46:36 - INFO - __main__ - Step 19788: {'lr': 0.00048239133764077193, 'samples': 3799296, 'steps': 19787, 'loss/train': 1.9512839317321777} 08/30/2021 16:46:37 - INFO - __main__ - Step 19789: {'lr': 0.00048238938121798313, 'samples': 3799488, 'steps': 19788, 'loss/train': 1.5324562788009644} 08/30/2021 16:46:38 - INFO - __main__ - Step 19790: {'lr': 0.00048238742469048344, 'samples': 3799680, 'steps': 19789, 'loss/train': 1.4485249519348145} 08/30/2021 16:46:38 - INFO - __main__ - Step 19791: {'lr': 0.00048238546805827345, 'samples': 3799872, 'steps': 19790, 'loss/train': 1.9327707290649414} 08/30/2021 16:46:39 - INFO - __main__ - Step 19792: {'lr': 0.00048238351132135415, 'samples': 3800064, 'steps': 19791, 'loss/train': 1.6438424587249756} 08/30/2021 16:46:39 - INFO - __main__ - Step 19793: {'lr': 0.0004823815544797265, 'samples': 3800256, 'steps': 19792, 'loss/train': 1.512700080871582} 08/30/2021 16:46:40 - INFO - __main__ - Step 19794: {'lr': 0.0004823795975333912, 'samples': 3800448, 'steps': 19793, 'loss/train': 1.6888874769210815} 08/30/2021 16:46:41 - INFO - __main__ - Step 19795: {'lr': 0.0004823776404823493, 'samples': 3800640, 'steps': 19794, 'loss/train': 1.5916376113891602} 08/30/2021 16:46:41 - INFO - __main__ - Step 19796: {'lr': 0.00048237568332660163, 'samples': 3800832, 'steps': 19795, 'loss/train': 2.0096867084503174} 08/30/2021 16:46:41 - INFO - __main__ - Step 19797: {'lr': 0.0004823737260661491, 'samples': 3801024, 'steps': 19796, 'loss/train': 1.7896571159362793} 08/30/2021 16:46:42 - INFO - __main__ - Step 19798: {'lr': 0.00048237176870099256, 'samples': 3801216, 'steps': 19797, 'loss/train': 1.7274136543273926} 08/30/2021 16:46:43 - INFO - __main__ - Step 19799: {'lr': 0.0004823698112311328, 'samples': 3801408, 'steps': 19798, 'loss/train': 1.4035961627960205} 08/30/2021 16:46:44 - INFO - __main__ - Step 19800: {'lr': 0.00048236785365657076, 'samples': 3801600, 'steps': 19799, 'loss/train': 0.17131058871746063} 08/30/2021 16:46:44 - INFO - __main__ - Step 19801: {'lr': 0.00048236589597730744, 'samples': 3801792, 'steps': 19800, 'loss/train': 1.7156814336776733} 08/30/2021 16:46:45 - INFO - __main__ - Step 19802: {'lr': 0.00048236393819334363, 'samples': 3801984, 'steps': 19801, 'loss/train': 1.3876007795333862} 08/30/2021 16:46:45 - INFO - __main__ - Step 19803: {'lr': 0.0004823619803046802, 'samples': 3802176, 'steps': 19802, 'loss/train': 0.6160278916358948} 08/30/2021 16:46:47 - INFO - __main__ - Step 19804: {'lr': 0.00048236002231131803, 'samples': 3802368, 'steps': 19803, 'loss/train': 1.3296622037887573} 08/30/2021 16:46:47 - INFO - __main__ - Step 19805: {'lr': 0.00048235806421325803, 'samples': 3802560, 'steps': 19804, 'loss/train': 1.531077265739441} 08/30/2021 16:46:47 - INFO - __main__ - Step 19806: {'lr': 0.0004823561060105011, 'samples': 3802752, 'steps': 19805, 'loss/train': 1.6807235479354858} 08/30/2021 16:46:48 - INFO - __main__ - Step 19807: {'lr': 0.00048235414770304803, 'samples': 3802944, 'steps': 19806, 'loss/train': 1.673302173614502} 08/30/2021 16:46:48 - INFO - __main__ - Step 19808: {'lr': 0.00048235218929089987, 'samples': 3803136, 'steps': 19807, 'loss/train': 1.5240333080291748} 08/30/2021 16:46:49 - INFO - __main__ - Step 19809: {'lr': 0.00048235023077405724, 'samples': 3803328, 'steps': 19808, 'loss/train': 1.59073805809021} 08/30/2021 16:46:50 - INFO - __main__ - Step 19810: {'lr': 0.0004823482721525213, 'samples': 3803520, 'steps': 19809, 'loss/train': 1.7584518194198608} 08/30/2021 16:46:50 - INFO - __main__ - Step 19811: {'lr': 0.0004823463134262928, 'samples': 3803712, 'steps': 19810, 'loss/train': 1.5256023406982422} 08/30/2021 16:46:51 - INFO - __main__ - Step 19812: {'lr': 0.00048234435459537265, 'samples': 3803904, 'steps': 19811, 'loss/train': 1.4290350675582886} 08/30/2021 16:46:51 - INFO - __main__ - Step 19813: {'lr': 0.0004823423956597617, 'samples': 3804096, 'steps': 19812, 'loss/train': 1.2690590620040894} 08/30/2021 16:46:52 - INFO - __main__ - Step 19814: {'lr': 0.0004823404366194608, 'samples': 3804288, 'steps': 19813, 'loss/train': 1.546666145324707} 08/30/2021 16:46:53 - INFO - __main__ - Step 19815: {'lr': 0.0004823384774744709, 'samples': 3804480, 'steps': 19814, 'loss/train': 1.6375718116760254} 08/30/2021 16:46:53 - INFO - __main__ - Step 19816: {'lr': 0.000482336518224793, 'samples': 3804672, 'steps': 19815, 'loss/train': 0.07490232586860657} 08/30/2021 16:46:54 - INFO - __main__ - Step 19817: {'lr': 0.00048233455887042764, 'samples': 3804864, 'steps': 19816, 'loss/train': 1.213105320930481} 08/30/2021 16:46:54 - INFO - __main__ - Step 19818: {'lr': 0.0004823325994113761, 'samples': 3805056, 'steps': 19817, 'loss/train': 1.383909821510315} 08/30/2021 16:46:56 - INFO - __main__ - Step 19819: {'lr': 0.00048233063984763895, 'samples': 3805248, 'steps': 19818, 'loss/train': 1.2611336708068848} 08/30/2021 16:46:56 - INFO - __main__ - Step 19820: {'lr': 0.0004823286801792173, 'samples': 3805440, 'steps': 19819, 'loss/train': 1.7871754169464111} 08/30/2021 16:46:56 - INFO - __main__ - Step 19821: {'lr': 0.0004823267204061118, 'samples': 3805632, 'steps': 19820, 'loss/train': 2.1539313793182373} 08/30/2021 16:46:57 - INFO - __main__ - Step 19822: {'lr': 0.0004823247605283236, 'samples': 3805824, 'steps': 19821, 'loss/train': 0.15021799504756927} 08/30/2021 16:46:57 - INFO - __main__ - Step 19823: {'lr': 0.0004823228005458534, 'samples': 3806016, 'steps': 19822, 'loss/train': 1.92867112159729} 08/30/2021 16:46:59 - INFO - __main__ - Step 19824: {'lr': 0.00048232084045870204, 'samples': 3806208, 'steps': 19823, 'loss/train': 0.8178573250770569} 08/30/2021 16:46:59 - INFO - __main__ - Step 19825: {'lr': 0.00048231888026687065, 'samples': 3806400, 'steps': 19824, 'loss/train': 1.4814424514770508} 08/30/2021 16:46:59 - INFO - __main__ - Step 19826: {'lr': 0.00048231691997035987, 'samples': 3806592, 'steps': 19825, 'loss/train': 1.6040164232254028} 08/30/2021 16:47:00 - INFO - __main__ - Step 19827: {'lr': 0.00048231495956917067, 'samples': 3806784, 'steps': 19826, 'loss/train': 1.462829351425171} 08/30/2021 16:47:00 - INFO - __main__ - Step 19828: {'lr': 0.00048231299906330397, 'samples': 3806976, 'steps': 19827, 'loss/train': 1.1462972164154053} 08/30/2021 16:47:02 - INFO - __main__ - Step 19829: {'lr': 0.0004823110384527606, 'samples': 3807168, 'steps': 19828, 'loss/train': 1.4257042407989502} 08/30/2021 16:47:02 - INFO - __main__ - Step 19830: {'lr': 0.0004823090777375414, 'samples': 3807360, 'steps': 19829, 'loss/train': 1.8113360404968262} 08/30/2021 16:47:02 - INFO - __main__ - Step 19831: {'lr': 0.0004823071169176474, 'samples': 3807552, 'steps': 19830, 'loss/train': 2.2109315395355225} 08/30/2021 16:47:03 - INFO - __main__ - Step 19832: {'lr': 0.00048230515599307933, 'samples': 3807744, 'steps': 19831, 'loss/train': 1.2028950452804565} 08/30/2021 16:47:03 - INFO - __main__ - Step 19833: {'lr': 0.0004823031949638382, 'samples': 3807936, 'steps': 19832, 'loss/train': 1.6282076835632324} 08/30/2021 16:47:03 - INFO - __main__ - Step 19834: {'lr': 0.0004823012338299248, 'samples': 3808128, 'steps': 19833, 'loss/train': 1.61159348487854} 08/30/2021 16:47:06 - INFO - __main__ - Step 19835: {'lr': 0.0004822992725913401, 'samples': 3808320, 'steps': 19834, 'loss/train': 1.688277244567871} 08/30/2021 16:47:06 - INFO - __main__ - Step 19836: {'lr': 0.00048229731124808484, 'samples': 3808512, 'steps': 19835, 'loss/train': 1.5510793924331665} 08/30/2021 16:47:07 - INFO - __main__ - Step 19837: {'lr': 0.00048229534980016007, 'samples': 3808704, 'steps': 19836, 'loss/train': 1.5770598649978638} 08/30/2021 16:47:07 - INFO - __main__ - Step 19838: {'lr': 0.0004822933882475666, 'samples': 3808896, 'steps': 19837, 'loss/train': 1.6042286157608032} 08/30/2021 16:47:07 - INFO - __main__ - Step 19839: {'lr': 0.00048229142659030527, 'samples': 3809088, 'steps': 19838, 'loss/train': 1.6330395936965942} 08/30/2021 16:47:08 - INFO - __main__ - Step 19840: {'lr': 0.000482289464828377, 'samples': 3809280, 'steps': 19839, 'loss/train': 0.057610705494880676} 08/30/2021 16:47:09 - INFO - __main__ - Step 19841: {'lr': 0.00048228750296178276, 'samples': 3809472, 'steps': 19840, 'loss/train': 1.5284667015075684} 08/30/2021 16:47:10 - INFO - __main__ - Step 19842: {'lr': 0.0004822855409905233, 'samples': 3809664, 'steps': 19841, 'loss/train': 1.4956417083740234} 08/30/2021 16:47:10 - INFO - __main__ - Step 19843: {'lr': 0.00048228357891459954, 'samples': 3809856, 'steps': 19842, 'loss/train': 2.1752610206604004} 08/30/2021 16:47:11 - INFO - __main__ - Step 19844: {'lr': 0.0004822816167340124, 'samples': 3810048, 'steps': 19843, 'loss/train': 0.914184033870697} 08/30/2021 16:47:11 - INFO - __main__ - Step 19845: {'lr': 0.00048227965444876277, 'samples': 3810240, 'steps': 19844, 'loss/train': 2.04819655418396} 08/30/2021 16:47:12 - INFO - __main__ - Step 19846: {'lr': 0.0004822776920588515, 'samples': 3810432, 'steps': 19845, 'loss/train': 1.589402437210083} 08/30/2021 16:47:13 - INFO - __main__ - Step 19847: {'lr': 0.0004822757295642795, 'samples': 3810624, 'steps': 19846, 'loss/train': 1.5684795379638672} 08/30/2021 16:47:13 - INFO - __main__ - Step 19848: {'lr': 0.00048227376696504765, 'samples': 3810816, 'steps': 19847, 'loss/train': 1.812343955039978} 08/30/2021 16:47:14 - INFO - __main__ - Step 19849: {'lr': 0.0004822718042611568, 'samples': 3811008, 'steps': 19848, 'loss/train': 1.5832816362380981} 08/30/2021 16:47:14 - INFO - __main__ - Step 19850: {'lr': 0.0004822698414526079, 'samples': 3811200, 'steps': 19849, 'loss/train': 1.8289332389831543} 08/30/2021 16:47:16 - INFO - __main__ - Step 19851: {'lr': 0.0004822678785394017, 'samples': 3811392, 'steps': 19850, 'loss/train': 1.7046853303909302} 08/30/2021 16:47:16 - INFO - __main__ - Step 19852: {'lr': 0.0004822659155215393, 'samples': 3811584, 'steps': 19851, 'loss/train': 0.8314381837844849} 08/30/2021 16:47:17 - INFO - __main__ - Step 19853: {'lr': 0.00048226395239902133, 'samples': 3811776, 'steps': 19852, 'loss/train': 1.683605670928955} 08/30/2021 16:47:17 - INFO - __main__ - Step 19854: {'lr': 0.00048226198917184886, 'samples': 3811968, 'steps': 19853, 'loss/train': 1.5703904628753662} 08/30/2021 16:47:17 - INFO - __main__ - Step 19855: {'lr': 0.00048226002584002276, 'samples': 3812160, 'steps': 19854, 'loss/train': 0.059553273022174835} 08/30/2021 16:47:18 - INFO - __main__ - Step 19856: {'lr': 0.00048225806240354387, 'samples': 3812352, 'steps': 19855, 'loss/train': 0.06528206169605255} 08/30/2021 16:47:19 - INFO - __main__ - Step 19857: {'lr': 0.0004822560988624131, 'samples': 3812544, 'steps': 19856, 'loss/train': 2.0399603843688965} 08/30/2021 16:47:20 - INFO - __main__ - Step 19858: {'lr': 0.0004822541352166312, 'samples': 3812736, 'steps': 19857, 'loss/train': 1.376532793045044} 08/30/2021 16:47:20 - INFO - __main__ - Step 19859: {'lr': 0.0004822521714661993, 'samples': 3812928, 'steps': 19858, 'loss/train': 1.4827698469161987} 08/30/2021 16:47:20 - INFO - __main__ - Step 19860: {'lr': 0.0004822502076111181, 'samples': 3813120, 'steps': 19859, 'loss/train': 1.3917800188064575} 08/30/2021 16:47:21 - INFO - __main__ - Step 19861: {'lr': 0.0004822482436513885, 'samples': 3813312, 'steps': 19860, 'loss/train': 0.8752621412277222} 08/30/2021 16:47:21 - INFO - __main__ - Step 19862: {'lr': 0.0004822462795870115, 'samples': 3813504, 'steps': 19861, 'loss/train': 0.5461375713348389} 08/30/2021 16:47:23 - INFO - __main__ - Step 19863: {'lr': 0.00048224431541798784, 'samples': 3813696, 'steps': 19862, 'loss/train': 1.2158832550048828} 08/30/2021 16:47:23 - INFO - __main__ - Step 19864: {'lr': 0.00048224235114431856, 'samples': 3813888, 'steps': 19863, 'loss/train': 2.0124335289001465} 08/30/2021 16:47:23 - INFO - __main__ - Step 19865: {'lr': 0.0004822403867660044, 'samples': 3814080, 'steps': 19864, 'loss/train': 1.2959673404693604} 08/30/2021 16:47:24 - INFO - __main__ - Step 19866: {'lr': 0.0004822384222830463, 'samples': 3814272, 'steps': 19865, 'loss/train': 2.120906352996826} 08/30/2021 16:47:24 - INFO - __main__ - Step 19867: {'lr': 0.0004822364576954452, 'samples': 3814464, 'steps': 19866, 'loss/train': 1.5623080730438232} 08/30/2021 16:47:26 - INFO - __main__ - Step 19868: {'lr': 0.0004822344930032019, 'samples': 3814656, 'steps': 19867, 'loss/train': 1.6022862195968628} 08/30/2021 16:47:26 - INFO - __main__ - Step 19869: {'lr': 0.00048223252820631736, 'samples': 3814848, 'steps': 19868, 'loss/train': 1.5811340808868408} 08/30/2021 16:47:26 - INFO - __main__ - Step 19870: {'lr': 0.00048223056330479235, 'samples': 3815040, 'steps': 19869, 'loss/train': 0.598106324672699} 08/30/2021 16:47:27 - INFO - __main__ - Step 19871: {'lr': 0.00048222859829862784, 'samples': 3815232, 'steps': 19870, 'loss/train': 1.6351191997528076} 08/30/2021 16:47:27 - INFO - __main__ - Step 19872: {'lr': 0.0004822266331878248, 'samples': 3815424, 'steps': 19871, 'loss/train': 1.4950696229934692} 08/30/2021 16:47:29 - INFO - __main__ - Step 19873: {'lr': 0.00048222466797238396, 'samples': 3815616, 'steps': 19872, 'loss/train': 1.8534035682678223} 08/30/2021 16:47:29 - INFO - __main__ - Step 19874: {'lr': 0.00048222270265230627, 'samples': 3815808, 'steps': 19873, 'loss/train': 2.3191308975219727} 08/30/2021 16:47:30 - INFO - __main__ - Step 19875: {'lr': 0.0004822207372275926, 'samples': 3816000, 'steps': 19874, 'loss/train': 0.8441720008850098} 08/30/2021 16:47:30 - INFO - __main__ - Step 19876: {'lr': 0.0004822187716982439, 'samples': 3816192, 'steps': 19875, 'loss/train': 1.893140435218811} 08/30/2021 16:47:30 - INFO - __main__ - Step 19877: {'lr': 0.000482216806064261, 'samples': 3816384, 'steps': 19876, 'loss/train': 1.9657264947891235} 08/30/2021 16:47:32 - INFO - __main__ - Step 19878: {'lr': 0.0004822148403256447, 'samples': 3816576, 'steps': 19877, 'loss/train': 1.5532938241958618} 08/30/2021 16:47:33 - INFO - __main__ - Step 19879: {'lr': 0.00048221287448239604, 'samples': 3816768, 'steps': 19878, 'loss/train': 2.102879047393799} 08/30/2021 16:47:33 - INFO - __main__ - Step 19880: {'lr': 0.00048221090853451586, 'samples': 3816960, 'steps': 19879, 'loss/train': 1.3816614151000977} 08/30/2021 16:47:33 - INFO - __main__ - Step 19881: {'lr': 0.000482208942482005, 'samples': 3817152, 'steps': 19880, 'loss/train': 1.6331406831741333} 08/30/2021 16:47:34 - INFO - __main__ - Step 19882: {'lr': 0.00048220697632486443, 'samples': 3817344, 'steps': 19881, 'loss/train': 1.5460662841796875} 08/30/2021 16:47:35 - INFO - __main__ - Step 19883: {'lr': 0.0004822050100630949, 'samples': 3817536, 'steps': 19882, 'loss/train': 1.1174434423446655} 08/30/2021 16:47:36 - INFO - __main__ - Step 19884: {'lr': 0.0004822030436966974, 'samples': 3817728, 'steps': 19883, 'loss/train': 1.226914644241333} 08/30/2021 16:47:36 - INFO - __main__ - Step 19885: {'lr': 0.0004822010772256728, 'samples': 3817920, 'steps': 19884, 'loss/train': 1.0844295024871826} 08/30/2021 16:47:37 - INFO - __main__ - Step 19886: {'lr': 0.00048219911065002196, 'samples': 3818112, 'steps': 19885, 'loss/train': 0.13883930444717407} 08/30/2021 16:47:37 - INFO - __main__ - Step 19887: {'lr': 0.00048219714396974587, 'samples': 3818304, 'steps': 19886, 'loss/train': 0.388445645570755} 08/30/2021 16:47:37 - INFO - __main__ - Step 19888: {'lr': 0.0004821951771848452, 'samples': 3818496, 'steps': 19887, 'loss/train': 1.543168544769287} 08/30/2021 16:47:39 - INFO - __main__ - Step 19889: {'lr': 0.00048219321029532104, 'samples': 3818688, 'steps': 19888, 'loss/train': 1.3442749977111816} 08/30/2021 16:47:39 - INFO - __main__ - Step 19890: {'lr': 0.0004821912433011742, 'samples': 3818880, 'steps': 19889, 'loss/train': 2.1364612579345703} 08/30/2021 16:47:39 - INFO - __main__ - Step 19891: {'lr': 0.00048218927620240557, 'samples': 3819072, 'steps': 19890, 'loss/train': 1.3614708185195923} 08/30/2021 16:47:40 - INFO - __main__ - Step 19892: {'lr': 0.00048218730899901596, 'samples': 3819264, 'steps': 19891, 'loss/train': 1.7762341499328613} 08/30/2021 16:47:40 - INFO - __main__ - Step 19893: {'lr': 0.0004821853416910065, 'samples': 3819456, 'steps': 19892, 'loss/train': 2.399401903152466} 08/30/2021 16:47:42 - INFO - __main__ - Step 19894: {'lr': 0.0004821833742783778, 'samples': 3819648, 'steps': 19893, 'loss/train': 1.5506436824798584} 08/30/2021 16:47:43 - INFO - __main__ - Step 19895: {'lr': 0.0004821814067611308, 'samples': 3819840, 'steps': 19894, 'loss/train': 1.3862872123718262} 08/30/2021 16:47:43 - INFO - __main__ - Step 19896: {'lr': 0.00048217943913926646, 'samples': 3820032, 'steps': 19895, 'loss/train': 1.5992727279663086} 08/30/2021 16:47:43 - INFO - __main__ - Step 19897: {'lr': 0.00048217747141278574, 'samples': 3820224, 'steps': 19896, 'loss/train': 1.7001378536224365} 08/30/2021 16:47:44 - INFO - __main__ - Step 19898: {'lr': 0.00048217550358168937, 'samples': 3820416, 'steps': 19897, 'loss/train': 1.771938443183899} 08/30/2021 16:47:44 - INFO - __main__ - Step 19899: {'lr': 0.00048217353564597833, 'samples': 3820608, 'steps': 19898, 'loss/train': 0.980220377445221} 08/30/2021 16:47:46 - INFO - __main__ - Step 19900: {'lr': 0.0004821715676056534, 'samples': 3820800, 'steps': 19899, 'loss/train': 1.2470473051071167} 08/30/2021 16:47:46 - INFO - __main__ - Step 19901: {'lr': 0.0004821695994607156, 'samples': 3820992, 'steps': 19900, 'loss/train': 1.54640793800354} 08/30/2021 16:47:46 - INFO - __main__ - Step 19902: {'lr': 0.0004821676312111658, 'samples': 3821184, 'steps': 19901, 'loss/train': 1.4011132717132568} 08/30/2021 16:47:47 - INFO - __main__ - Step 19903: {'lr': 0.0004821656628570048, 'samples': 3821376, 'steps': 19902, 'loss/train': 1.692028522491455} 08/30/2021 16:47:47 - INFO - __main__ - Step 19904: {'lr': 0.00048216369439823355, 'samples': 3821568, 'steps': 19903, 'loss/train': 1.0948528051376343} 08/30/2021 16:47:49 - INFO - __main__ - Step 19905: {'lr': 0.0004821617258348529, 'samples': 3821760, 'steps': 19904, 'loss/train': 1.3367528915405273} 08/30/2021 16:47:49 - INFO - __main__ - Step 19906: {'lr': 0.0004821597571668638, 'samples': 3821952, 'steps': 19905, 'loss/train': 1.7913727760314941} 08/30/2021 16:47:50 - INFO - __main__ - Step 19907: {'lr': 0.00048215778839426706, 'samples': 3822144, 'steps': 19906, 'loss/train': 1.740395426750183} 08/30/2021 16:47:50 - INFO - __main__ - Step 19908: {'lr': 0.0004821558195170636, 'samples': 3822336, 'steps': 19907, 'loss/train': 1.95854651927948} 08/30/2021 16:47:51 - INFO - __main__ - Step 19909: {'lr': 0.00048215385053525434, 'samples': 3822528, 'steps': 19908, 'loss/train': 1.7856106758117676} 08/30/2021 16:47:52 - INFO - __main__ - Step 19910: {'lr': 0.00048215188144884013, 'samples': 3822720, 'steps': 19909, 'loss/train': 1.7378044128417969} 08/30/2021 16:47:52 - INFO - __main__ - Step 19911: {'lr': 0.0004821499122578218, 'samples': 3822912, 'steps': 19910, 'loss/train': 1.4063925743103027} 08/30/2021 16:47:53 - INFO - __main__ - Step 19912: {'lr': 0.00048214794296220045, 'samples': 3823104, 'steps': 19911, 'loss/train': 2.181438684463501} 08/30/2021 16:47:53 - INFO - __main__ - Step 19913: {'lr': 0.00048214597356197665, 'samples': 3823296, 'steps': 19912, 'loss/train': 1.8075560331344604} 08/30/2021 16:47:53 - INFO - __main__ - Step 19914: {'lr': 0.00048214400405715153, 'samples': 3823488, 'steps': 19913, 'loss/train': 1.2732000350952148} 08/30/2021 16:47:55 - INFO - __main__ - Step 19915: {'lr': 0.000482142034447726, 'samples': 3823680, 'steps': 19914, 'loss/train': 2.2317516803741455} 08/30/2021 16:47:55 - INFO - __main__ - Step 19916: {'lr': 0.0004821400647337007, 'samples': 3823872, 'steps': 19915, 'loss/train': 1.7764110565185547} 08/30/2021 16:47:56 - INFO - __main__ - Step 19917: {'lr': 0.0004821380949150768, 'samples': 3824064, 'steps': 19916, 'loss/train': 1.7857691049575806} 08/30/2021 16:47:56 - INFO - __main__ - Step 19918: {'lr': 0.0004821361249918549, 'samples': 3824256, 'steps': 19917, 'loss/train': 2.807133197784424} 08/30/2021 16:47:56 - INFO - __main__ - Step 19919: {'lr': 0.0004821341549640361, 'samples': 3824448, 'steps': 19918, 'loss/train': 1.948252558708191} 08/30/2021 16:47:57 - INFO - __main__ - Step 19920: {'lr': 0.00048213218483162133, 'samples': 3824640, 'steps': 19919, 'loss/train': 1.578928828239441} 08/30/2021 16:47:58 - INFO - __main__ - Step 19921: {'lr': 0.0004821302145946113, 'samples': 3824832, 'steps': 19920, 'loss/train': 1.0670801401138306} 08/30/2021 16:47:59 - INFO - __main__ - Step 19922: {'lr': 0.00048212824425300694, 'samples': 3825024, 'steps': 19921, 'loss/train': 1.6731804609298706} 08/30/2021 16:47:59 - INFO - __main__ - Step 19923: {'lr': 0.0004821262738068093, 'samples': 3825216, 'steps': 19922, 'loss/train': 0.26068222522735596} 08/30/2021 16:48:00 - INFO - __main__ - Step 19924: {'lr': 0.00048212430325601905, 'samples': 3825408, 'steps': 19923, 'loss/train': 1.7669562101364136} 08/30/2021 16:48:00 - INFO - __main__ - Step 19925: {'lr': 0.0004821223326006372, 'samples': 3825600, 'steps': 19924, 'loss/train': 1.3206557035446167} 08/30/2021 16:48:01 - INFO - __main__ - Step 19926: {'lr': 0.0004821203618406645, 'samples': 3825792, 'steps': 19925, 'loss/train': 1.6502186059951782} 08/30/2021 16:48:02 - INFO - __main__ - Step 19927: {'lr': 0.0004821183909761021, 'samples': 3825984, 'steps': 19926, 'loss/train': 1.5708249807357788} 08/30/2021 16:48:02 - INFO - __main__ - Step 19928: {'lr': 0.00048211642000695065, 'samples': 3826176, 'steps': 19927, 'loss/train': 1.6866652965545654} 08/30/2021 16:48:03 - INFO - __main__ - Step 19929: {'lr': 0.0004821144489332112, 'samples': 3826368, 'steps': 19928, 'loss/train': 1.0631749629974365} 08/30/2021 16:48:03 - INFO - __main__ - Step 19930: {'lr': 0.0004821124777548845, 'samples': 3826560, 'steps': 19929, 'loss/train': 1.2046526670455933} 08/30/2021 16:48:05 - INFO - __main__ - Step 19931: {'lr': 0.0004821105064719715, 'samples': 3826752, 'steps': 19930, 'loss/train': 1.9138237237930298} 08/30/2021 16:48:05 - INFO - __main__ - Step 19932: {'lr': 0.0004821085350844731, 'samples': 3826944, 'steps': 19931, 'loss/train': 0.1442057490348816} 08/30/2021 16:48:05 - INFO - __main__ - Step 19933: {'lr': 0.0004821065635923902, 'samples': 3827136, 'steps': 19932, 'loss/train': 1.5246555805206299} 08/30/2021 16:48:06 - INFO - __main__ - Step 19934: {'lr': 0.0004821045919957237, 'samples': 3827328, 'steps': 19933, 'loss/train': 1.7617788314819336} 08/30/2021 16:48:06 - INFO - __main__ - Step 19935: {'lr': 0.00048210262029447425, 'samples': 3827520, 'steps': 19934, 'loss/train': 1.624178409576416} 08/30/2021 16:48:08 - INFO - __main__ - Step 19936: {'lr': 0.0004821006484886431, 'samples': 3827712, 'steps': 19935, 'loss/train': 1.6159640550613403} 08/30/2021 16:48:08 - INFO - __main__ - Step 19937: {'lr': 0.000482098676578231, 'samples': 3827904, 'steps': 19936, 'loss/train': 1.2737667560577393} 08/30/2021 16:48:09 - INFO - __main__ - Step 19938: {'lr': 0.0004820967045632388, 'samples': 3828096, 'steps': 19937, 'loss/train': 1.4769971370697021} 08/30/2021 16:48:09 - INFO - __main__ - Step 19939: {'lr': 0.00048209473244366737, 'samples': 3828288, 'steps': 19938, 'loss/train': 0.9654390811920166} 08/30/2021 16:48:09 - INFO - __main__ - Step 19940: {'lr': 0.00048209276021951765, 'samples': 3828480, 'steps': 19939, 'loss/train': 1.6610724925994873} 08/30/2021 16:48:11 - INFO - __main__ - Step 19941: {'lr': 0.00048209078789079055, 'samples': 3828672, 'steps': 19940, 'loss/train': 1.4529668092727661} 08/30/2021 16:48:11 - INFO - __main__ - Step 19942: {'lr': 0.00048208881545748684, 'samples': 3828864, 'steps': 19941, 'loss/train': 2.073242664337158} 08/30/2021 16:48:12 - INFO - __main__ - Step 19943: {'lr': 0.00048208684291960755, 'samples': 3829056, 'steps': 19942, 'loss/train': 1.3615379333496094} 08/30/2021 16:48:12 - INFO - __main__ - Step 19944: {'lr': 0.0004820848702771535, 'samples': 3829248, 'steps': 19943, 'loss/train': 1.5603870153427124} 08/30/2021 16:48:12 - INFO - __main__ - Step 19945: {'lr': 0.0004820828975301256, 'samples': 3829440, 'steps': 19944, 'loss/train': 1.638757348060608} 08/30/2021 16:48:14 - INFO - __main__ - Step 19946: {'lr': 0.0004820809246785247, 'samples': 3829632, 'steps': 19945, 'loss/train': 1.8357417583465576} 08/30/2021 16:48:15 - INFO - __main__ - Step 19947: {'lr': 0.00048207895172235174, 'samples': 3829824, 'steps': 19946, 'loss/train': 0.8339240550994873} 08/30/2021 16:48:15 - INFO - __main__ - Step 19948: {'lr': 0.00048207697866160755, 'samples': 3830016, 'steps': 19947, 'loss/train': 0.9164642691612244} 08/30/2021 16:48:15 - INFO - __main__ - Step 19949: {'lr': 0.0004820750054962931, 'samples': 3830208, 'steps': 19948, 'loss/train': 1.6671268939971924} 08/30/2021 16:48:16 - INFO - __main__ - Step 19950: {'lr': 0.00048207303222640917, 'samples': 3830400, 'steps': 19949, 'loss/train': 1.640650749206543} 08/30/2021 16:48:17 - INFO - __main__ - Step 19951: {'lr': 0.00048207105885195677, 'samples': 3830592, 'steps': 19950, 'loss/train': 1.5497727394104004} 08/30/2021 16:48:18 - INFO - __main__ - Step 19952: {'lr': 0.0004820690853729367, 'samples': 3830784, 'steps': 19951, 'loss/train': 0.19414319097995758} 08/30/2021 16:48:18 - INFO - __main__ - Step 19953: {'lr': 0.00048206711178934994, 'samples': 3830976, 'steps': 19952, 'loss/train': 1.789297342300415} 08/30/2021 16:48:19 - INFO - __main__ - Step 19954: {'lr': 0.00048206513810119725, 'samples': 3831168, 'steps': 19953, 'loss/train': 1.8761667013168335} 08/30/2021 16:48:19 - INFO - __main__ - Step 19955: {'lr': 0.0004820631643084796, 'samples': 3831360, 'steps': 19954, 'loss/train': 1.4396812915802002} 08/30/2021 16:48:19 - INFO - __main__ - Step 19956: {'lr': 0.00048206119041119787, 'samples': 3831552, 'steps': 19955, 'loss/train': 1.5129131078720093} 08/30/2021 16:48:21 - INFO - __main__ - Step 19957: {'lr': 0.000482059216409353, 'samples': 3831744, 'steps': 19956, 'loss/train': 1.8082789182662964} 08/30/2021 16:48:22 - INFO - __main__ - Step 19958: {'lr': 0.0004820572423029458, 'samples': 3831936, 'steps': 19957, 'loss/train': 1.9943994283676147} 08/30/2021 16:48:22 - INFO - __main__ - Step 19959: {'lr': 0.00048205526809197717, 'samples': 3832128, 'steps': 19958, 'loss/train': 1.5847307443618774} 08/30/2021 16:48:22 - INFO - __main__ - Step 19960: {'lr': 0.000482053293776448, 'samples': 3832320, 'steps': 19959, 'loss/train': 1.7793534994125366} 08/30/2021 16:48:23 - INFO - __main__ - Step 19961: {'lr': 0.0004820513193563593, 'samples': 3832512, 'steps': 19960, 'loss/train': 0.25694942474365234} 08/30/2021 16:48:24 - INFO - __main__ - Step 19962: {'lr': 0.00048204934483171176, 'samples': 3832704, 'steps': 19961, 'loss/train': 1.4777239561080933} 08/30/2021 16:48:25 - INFO - __main__ - Step 19963: {'lr': 0.0004820473702025064, 'samples': 3832896, 'steps': 19962, 'loss/train': 1.6857661008834839} 08/30/2021 16:48:25 - INFO - __main__ - Step 19964: {'lr': 0.000482045395468744, 'samples': 3833088, 'steps': 19963, 'loss/train': 0.335319459438324} 08/30/2021 16:48:26 - INFO - __main__ - Step 19965: {'lr': 0.0004820434206304256, 'samples': 3833280, 'steps': 19964, 'loss/train': 1.5853749513626099} 08/30/2021 16:48:26 - INFO - __main__ - Step 19966: {'lr': 0.000482041445687552, 'samples': 3833472, 'steps': 19965, 'loss/train': 2.2551088333129883} 08/30/2021 16:48:27 - INFO - __main__ - Step 19967: {'lr': 0.0004820394706401242, 'samples': 3833664, 'steps': 19966, 'loss/train': 0.075727179646492} 08/30/2021 16:48:28 - INFO - __main__ - Step 19968: {'lr': 0.0004820374954881429, 'samples': 3833856, 'steps': 19967, 'loss/train': 1.5370581150054932} 08/30/2021 16:48:28 - INFO - __main__ - Step 19969: {'lr': 0.000482035520231609, 'samples': 3834048, 'steps': 19968, 'loss/train': 1.8862011432647705} 08/30/2021 16:48:29 - INFO - __main__ - Step 19970: {'lr': 0.00048203354487052363, 'samples': 3834240, 'steps': 19969, 'loss/train': 1.4049559831619263} 08/30/2021 16:48:29 - INFO - __main__ - Step 19971: {'lr': 0.00048203156940488745, 'samples': 3834432, 'steps': 19970, 'loss/train': 1.6679749488830566} 08/30/2021 16:48:29 - INFO - __main__ - Step 19972: {'lr': 0.00048202959383470144, 'samples': 3834624, 'steps': 19971, 'loss/train': 0.8248991966247559} 08/30/2021 16:48:31 - INFO - __main__ - Step 19973: {'lr': 0.00048202761815996646, 'samples': 3834816, 'steps': 19972, 'loss/train': 1.5690691471099854} 08/30/2021 16:48:31 - INFO - __main__ - Step 19974: {'lr': 0.0004820256423806835, 'samples': 3835008, 'steps': 19973, 'loss/train': 1.0361708402633667} 08/30/2021 16:48:32 - INFO - __main__ - Step 19975: {'lr': 0.00048202366649685325, 'samples': 3835200, 'steps': 19974, 'loss/train': 1.9095230102539062} 08/30/2021 16:48:32 - INFO - __main__ - Step 19976: {'lr': 0.0004820216905084768, 'samples': 3835392, 'steps': 19975, 'loss/train': 2.128371238708496} 08/30/2021 16:48:32 - INFO - __main__ - Step 19977: {'lr': 0.00048201971441555485, 'samples': 3835584, 'steps': 19976, 'loss/train': 1.6646312475204468} 08/30/2021 16:48:34 - INFO - __main__ - Step 19978: {'lr': 0.0004820177382180885, 'samples': 3835776, 'steps': 19977, 'loss/train': 1.3691110610961914} 08/30/2021 16:48:34 - INFO - __main__ - Step 19979: {'lr': 0.00048201576191607843, 'samples': 3835968, 'steps': 19978, 'loss/train': 0.21969597041606903} 08/30/2021 16:48:35 - INFO - __main__ - Step 19980: {'lr': 0.00048201378550952575, 'samples': 3836160, 'steps': 19979, 'loss/train': 1.217984914779663} 08/30/2021 16:48:35 - INFO - __main__ - Step 19981: {'lr': 0.0004820118089984312, 'samples': 3836352, 'steps': 19980, 'loss/train': 1.7248014211654663} 08/30/2021 16:48:35 - INFO - __main__ - Step 19982: {'lr': 0.0004820098323827957, 'samples': 3836544, 'steps': 19981, 'loss/train': 1.9163602590560913} 08/30/2021 16:48:37 - INFO - __main__ - Step 19983: {'lr': 0.0004820078556626202, 'samples': 3836736, 'steps': 19982, 'loss/train': 1.093578815460205} 08/30/2021 16:48:37 - INFO - __main__ - Step 19984: {'lr': 0.0004820058788379055, 'samples': 3836928, 'steps': 19983, 'loss/train': 1.651665449142456} 08/30/2021 16:48:38 - INFO - __main__ - Step 19985: {'lr': 0.0004820039019086525, 'samples': 3837120, 'steps': 19984, 'loss/train': 1.1406774520874023} 08/30/2021 16:48:38 - INFO - __main__ - Step 19986: {'lr': 0.00048200192487486216, 'samples': 3837312, 'steps': 19985, 'loss/train': 1.5559415817260742} 08/30/2021 16:48:38 - INFO - __main__ - Step 19987: {'lr': 0.00048199994773653535, 'samples': 3837504, 'steps': 19986, 'loss/train': 1.3614102602005005} 08/30/2021 16:48:40 - INFO - __main__ - Step 19988: {'lr': 0.0004819979704936729, 'samples': 3837696, 'steps': 19987, 'loss/train': 1.2424564361572266} 08/30/2021 16:48:40 - INFO - __main__ - Step 19989: {'lr': 0.00048199599314627576, 'samples': 3837888, 'steps': 19988, 'loss/train': 1.5290501117706299} 08/30/2021 16:48:41 - INFO - __main__ - Step 19990: {'lr': 0.00048199401569434477, 'samples': 3838080, 'steps': 19989, 'loss/train': 2.1153290271759033} 08/30/2021 16:48:41 - INFO - __main__ - Step 19991: {'lr': 0.00048199203813788086, 'samples': 3838272, 'steps': 19990, 'loss/train': 1.7672927379608154} 08/30/2021 16:48:42 - INFO - __main__ - Step 19992: {'lr': 0.00048199006047688496, 'samples': 3838464, 'steps': 19991, 'loss/train': 1.7383555173873901} 08/30/2021 16:48:43 - INFO - __main__ - Step 19993: {'lr': 0.0004819880827113579, 'samples': 3838656, 'steps': 19992, 'loss/train': 1.8264869451522827} 08/30/2021 16:48:44 - INFO - __main__ - Step 19994: {'lr': 0.0004819861048413006, 'samples': 3838848, 'steps': 19993, 'loss/train': 1.6042386293411255} 08/30/2021 16:48:44 - INFO - __main__ - Step 19995: {'lr': 0.00048198412686671394, 'samples': 3839040, 'steps': 19994, 'loss/train': 0.16026639938354492} 08/30/2021 16:48:45 - INFO - __main__ - Step 19996: {'lr': 0.0004819821487875988, 'samples': 3839232, 'steps': 19995, 'loss/train': 0.062003571540117264} 08/30/2021 16:48:45 - INFO - __main__ - Step 19997: {'lr': 0.0004819801706039561, 'samples': 3839424, 'steps': 19996, 'loss/train': 1.302549123764038} 08/30/2021 16:48:45 - INFO - __main__ - Step 19998: {'lr': 0.0004819781923157867, 'samples': 3839616, 'steps': 19997, 'loss/train': 1.3895676136016846} 08/30/2021 16:48:47 - INFO - __main__ - Step 19999: {'lr': 0.00048197621392309154, 'samples': 3839808, 'steps': 19998, 'loss/train': 1.644120454788208} 08/30/2021 16:48:47 - INFO - __main__ - Step 20000: {'lr': 0.00048197423542587143, 'samples': 3840000, 'steps': 19999, 'loss/train': 1.5134613513946533} 08/30/2021 16:48:48 - INFO - __main__ - Step 20001: {'lr': 0.0004819722568241274, 'samples': 3840192, 'steps': 20000, 'loss/train': 0.9177433848381042} 08/30/2021 16:48:48 - INFO - __main__ - Step 20002: {'lr': 0.0004819702781178601, 'samples': 3840384, 'steps': 20001, 'loss/train': 1.7758409976959229} 08/30/2021 16:48:48 - INFO - __main__ - Step 20003: {'lr': 0.00048196829930707066, 'samples': 3840576, 'steps': 20002, 'loss/train': 1.3711930513381958} 08/30/2021 16:48:50 - INFO - __main__ - Step 20004: {'lr': 0.0004819663203917599, 'samples': 3840768, 'steps': 20003, 'loss/train': 1.7435840368270874} 08/30/2021 16:48:51 - INFO - __main__ - Step 20005: {'lr': 0.0004819643413719287, 'samples': 3840960, 'steps': 20004, 'loss/train': 1.8693407773971558} 08/30/2021 16:48:51 - INFO - __main__ - Step 20006: {'lr': 0.0004819623622475779, 'samples': 3841152, 'steps': 20005, 'loss/train': 1.7306019067764282} 08/30/2021 16:48:51 - INFO - __main__ - Step 20007: {'lr': 0.00048196038301870847, 'samples': 3841344, 'steps': 20006, 'loss/train': 1.9947823286056519} 08/30/2021 16:48:52 - INFO - __main__ - Step 20008: {'lr': 0.0004819584036853212, 'samples': 3841536, 'steps': 20007, 'loss/train': 1.286116123199463} 08/30/2021 16:48:52 - INFO - __main__ - Step 20009: {'lr': 0.00048195642424741716, 'samples': 3841728, 'steps': 20008, 'loss/train': 1.6496145725250244} 08/30/2021 16:48:54 - INFO - __main__ - Step 20010: {'lr': 0.00048195444470499704, 'samples': 3841920, 'steps': 20009, 'loss/train': 1.3488520383834839} 08/30/2021 16:48:54 - INFO - __main__ - Step 20011: {'lr': 0.0004819524650580619, 'samples': 3842112, 'steps': 20010, 'loss/train': 1.5523463487625122} 08/30/2021 16:48:54 - INFO - __main__ - Step 20012: {'lr': 0.0004819504853066126, 'samples': 3842304, 'steps': 20011, 'loss/train': 2.034449577331543} 08/30/2021 16:48:55 - INFO - __main__ - Step 20013: {'lr': 0.0004819485054506498, 'samples': 3842496, 'steps': 20012, 'loss/train': 1.734606146812439} 08/30/2021 16:48:55 - INFO - __main__ - Step 20014: {'lr': 0.00048194652549017484, 'samples': 3842688, 'steps': 20013, 'loss/train': 1.9898678064346313} 08/30/2021 16:48:57 - INFO - __main__ - Step 20015: {'lr': 0.0004819445454251882, 'samples': 3842880, 'steps': 20014, 'loss/train': 0.9438971877098083} 08/30/2021 16:48:57 - INFO - __main__ - Step 20016: {'lr': 0.0004819425652556909, 'samples': 3843072, 'steps': 20015, 'loss/train': 2.579280376434326} 08/30/2021 16:48:58 - INFO - __main__ - Step 20017: {'lr': 0.0004819405849816839, 'samples': 3843264, 'steps': 20016, 'loss/train': 1.5702136754989624} 08/30/2021 16:48:58 - INFO - __main__ - Step 20018: {'lr': 0.00048193860460316805, 'samples': 3843456, 'steps': 20017, 'loss/train': 0.5301432609558105} 08/30/2021 16:48:58 - INFO - __main__ - Step 20019: {'lr': 0.00048193662412014427, 'samples': 3843648, 'steps': 20018, 'loss/train': 1.7974170446395874} 08/30/2021 16:49:00 - INFO - __main__ - Step 20020: {'lr': 0.0004819346435326134, 'samples': 3843840, 'steps': 20019, 'loss/train': 1.2705624103546143} 08/30/2021 16:49:00 - INFO - __main__ - Step 20021: {'lr': 0.00048193266284057634, 'samples': 3844032, 'steps': 20020, 'loss/train': 1.3145122528076172} 08/30/2021 16:49:01 - INFO - __main__ - Step 20022: {'lr': 0.0004819306820440341, 'samples': 3844224, 'steps': 20021, 'loss/train': 1.5394717454910278} 08/30/2021 16:49:01 - INFO - __main__ - Step 20023: {'lr': 0.0004819287011429874, 'samples': 3844416, 'steps': 20022, 'loss/train': 1.6912767887115479} 08/30/2021 16:49:01 - INFO - __main__ - Step 20024: {'lr': 0.0004819267201374372, 'samples': 3844608, 'steps': 20023, 'loss/train': 1.8691939115524292} 08/30/2021 16:49:03 - INFO - __main__ - Step 20025: {'lr': 0.0004819247390273844, 'samples': 3844800, 'steps': 20024, 'loss/train': 1.7553164958953857} 08/30/2021 16:49:03 - INFO - __main__ - Step 20026: {'lr': 0.00048192275781282993, 'samples': 3844992, 'steps': 20025, 'loss/train': 1.6538194417953491} 08/30/2021 16:49:04 - INFO - __main__ - Step 20027: {'lr': 0.00048192077649377455, 'samples': 3845184, 'steps': 20026, 'loss/train': 2.2352724075317383} 08/30/2021 16:49:04 - INFO - __main__ - Step 20028: {'lr': 0.0004819187950702193, 'samples': 3845376, 'steps': 20027, 'loss/train': 1.1791073083877563} 08/30/2021 16:49:04 - INFO - __main__ - Step 20029: {'lr': 0.00048191681354216504, 'samples': 3845568, 'steps': 20028, 'loss/train': 1.2517369985580444} 08/30/2021 16:49:06 - INFO - __main__ - Step 20030: {'lr': 0.0004819148319096126, 'samples': 3845760, 'steps': 20029, 'loss/train': 1.0241451263427734} 08/30/2021 16:49:06 - INFO - __main__ - Step 20031: {'lr': 0.00048191285017256297, 'samples': 3845952, 'steps': 20030, 'loss/train': 1.7977837324142456} 08/30/2021 16:49:07 - INFO - __main__ - Step 20032: {'lr': 0.00048191086833101695, 'samples': 3846144, 'steps': 20031, 'loss/train': 1.4658101797103882} 08/30/2021 16:49:07 - INFO - __main__ - Step 20033: {'lr': 0.00048190888638497553, 'samples': 3846336, 'steps': 20032, 'loss/train': 1.695029616355896} 08/30/2021 16:49:07 - INFO - __main__ - Step 20034: {'lr': 0.00048190690433443946, 'samples': 3846528, 'steps': 20033, 'loss/train': 1.1877739429473877} 08/30/2021 16:49:08 - INFO - __main__ - Step 20035: {'lr': 0.0004819049221794097, 'samples': 3846720, 'steps': 20034, 'loss/train': 0.08224710822105408} 08/30/2021 16:49:09 - INFO - __main__ - Step 20036: {'lr': 0.0004819029399198873, 'samples': 3846912, 'steps': 20035, 'loss/train': 1.4298524856567383} 08/30/2021 16:49:10 - INFO - __main__ - Step 20037: {'lr': 0.0004819009575558729, 'samples': 3847104, 'steps': 20036, 'loss/train': 1.6943835020065308} 08/30/2021 16:49:10 - INFO - __main__ - Step 20038: {'lr': 0.0004818989750873676, 'samples': 3847296, 'steps': 20037, 'loss/train': 0.03754433989524841} 08/30/2021 16:49:11 - INFO - __main__ - Step 20039: {'lr': 0.00048189699251437206, 'samples': 3847488, 'steps': 20038, 'loss/train': 1.9434560537338257} 08/30/2021 16:49:11 - INFO - __main__ - Step 20040: {'lr': 0.0004818950098368874, 'samples': 3847680, 'steps': 20039, 'loss/train': 1.8073323965072632} 08/30/2021 16:49:11 - INFO - __main__ - Step 20041: {'lr': 0.00048189302705491446, 'samples': 3847872, 'steps': 20040, 'loss/train': 1.7424969673156738} 08/30/2021 16:49:13 - INFO - __main__ - Step 20042: {'lr': 0.000481891044168454, 'samples': 3848064, 'steps': 20041, 'loss/train': 1.8437080383300781} 08/30/2021 16:49:13 - INFO - __main__ - Step 20043: {'lr': 0.00048188906117750706, 'samples': 3848256, 'steps': 20042, 'loss/train': 0.10665156692266464} 08/30/2021 16:49:14 - INFO - __main__ - Step 20044: {'lr': 0.00048188707808207457, 'samples': 3848448, 'steps': 20043, 'loss/train': 1.8833436965942383} 08/30/2021 16:49:14 - INFO - __main__ - Step 20045: {'lr': 0.00048188509488215724, 'samples': 3848640, 'steps': 20044, 'loss/train': 1.396911859512329} 08/30/2021 16:49:14 - INFO - __main__ - Step 20046: {'lr': 0.0004818831115777561, 'samples': 3848832, 'steps': 20045, 'loss/train': 1.676553726196289} 08/30/2021 16:49:16 - INFO - __main__ - Step 20047: {'lr': 0.00048188112816887203, 'samples': 3849024, 'steps': 20046, 'loss/train': 1.7872953414916992} 08/30/2021 16:49:16 - INFO - __main__ - Step 20048: {'lr': 0.0004818791446555059, 'samples': 3849216, 'steps': 20047, 'loss/train': 1.4919394254684448} 08/30/2021 16:49:17 - INFO - __main__ - Step 20049: {'lr': 0.00048187716103765854, 'samples': 3849408, 'steps': 20048, 'loss/train': 0.8091785311698914} 08/30/2021 16:49:17 - INFO - __main__ - Step 20050: {'lr': 0.0004818751773153309, 'samples': 3849600, 'steps': 20049, 'loss/train': 0.6129899621009827} 08/30/2021 16:49:17 - INFO - __main__ - Step 20051: {'lr': 0.000481873193488524, 'samples': 3849792, 'steps': 20050, 'loss/train': 1.6006039381027222} 08/30/2021 16:49:19 - INFO - __main__ - Step 20052: {'lr': 0.0004818712095572385, 'samples': 3849984, 'steps': 20051, 'loss/train': 1.1631252765655518} 08/30/2021 16:49:19 - INFO - __main__ - Step 20053: {'lr': 0.0004818692255214755, 'samples': 3850176, 'steps': 20052, 'loss/train': 1.6821677684783936} 08/30/2021 16:49:20 - INFO - __main__ - Step 20054: {'lr': 0.00048186724138123577, 'samples': 3850368, 'steps': 20053, 'loss/train': 1.827529788017273} 08/30/2021 16:49:20 - INFO - __main__ - Step 20055: {'lr': 0.00048186525713652024, 'samples': 3850560, 'steps': 20054, 'loss/train': 1.3900905847549438} 08/30/2021 16:49:20 - INFO - __main__ - Step 20056: {'lr': 0.0004818632727873298, 'samples': 3850752, 'steps': 20055, 'loss/train': 1.4969857931137085} 08/30/2021 16:49:22 - INFO - __main__ - Step 20057: {'lr': 0.00048186128833366536, 'samples': 3850944, 'steps': 20056, 'loss/train': 1.184066653251648} 08/30/2021 16:49:23 - INFO - __main__ - Step 20058: {'lr': 0.0004818593037755278, 'samples': 3851136, 'steps': 20057, 'loss/train': 1.6948479413986206} 08/30/2021 16:49:23 - INFO - __main__ - Step 20059: {'lr': 0.000481857319112918, 'samples': 3851328, 'steps': 20058, 'loss/train': 1.9170730113983154} 08/30/2021 16:49:23 - INFO - __main__ - Step 20060: {'lr': 0.0004818553343458368, 'samples': 3851520, 'steps': 20059, 'loss/train': 1.23885178565979} 08/30/2021 16:49:24 - INFO - __main__ - Step 20061: {'lr': 0.00048185334947428525, 'samples': 3851712, 'steps': 20060, 'loss/train': 2.0625462532043457} 08/30/2021 16:49:24 - INFO - __main__ - Step 20062: {'lr': 0.0004818513644982642, 'samples': 3851904, 'steps': 20061, 'loss/train': 1.9079039096832275} 08/30/2021 16:49:26 - INFO - __main__ - Step 20063: {'lr': 0.0004818493794177744, 'samples': 3852096, 'steps': 20062, 'loss/train': 1.435896635055542} 08/30/2021 16:49:26 - INFO - __main__ - Step 20064: {'lr': 0.00048184739423281695, 'samples': 3852288, 'steps': 20063, 'loss/train': 1.9172650575637817} 08/30/2021 16:49:27 - INFO - __main__ - Step 20065: {'lr': 0.00048184540894339256, 'samples': 3852480, 'steps': 20064, 'loss/train': 0.9635215401649475} 08/30/2021 16:49:27 - INFO - __main__ - Step 20066: {'lr': 0.00048184342354950225, 'samples': 3852672, 'steps': 20065, 'loss/train': 1.7241082191467285} 08/30/2021 16:49:27 - INFO - __main__ - Step 20067: {'lr': 0.00048184143805114684, 'samples': 3852864, 'steps': 20066, 'loss/train': 1.6395256519317627} 08/30/2021 16:49:29 - INFO - __main__ - Step 20068: {'lr': 0.00048183945244832725, 'samples': 3853056, 'steps': 20067, 'loss/train': 1.6814159154891968} 08/30/2021 16:49:29 - INFO - __main__ - Step 20069: {'lr': 0.00048183746674104446, 'samples': 3853248, 'steps': 20068, 'loss/train': 1.5684231519699097} 08/30/2021 16:49:29 - INFO - __main__ - Step 20070: {'lr': 0.00048183548092929916, 'samples': 3853440, 'steps': 20069, 'loss/train': 1.3256232738494873} 08/30/2021 16:49:30 - INFO - __main__ - Step 20071: {'lr': 0.0004818334950130925, 'samples': 3853632, 'steps': 20070, 'loss/train': 1.4391560554504395} 08/30/2021 16:49:30 - INFO - __main__ - Step 20072: {'lr': 0.00048183150899242514, 'samples': 3853824, 'steps': 20071, 'loss/train': 1.5120980739593506} 08/30/2021 16:49:32 - INFO - __main__ - Step 20073: {'lr': 0.0004818295228672981, 'samples': 3854016, 'steps': 20072, 'loss/train': 1.8095577955245972} 08/30/2021 16:49:32 - INFO - __main__ - Step 20074: {'lr': 0.0004818275366377123, 'samples': 3854208, 'steps': 20073, 'loss/train': 1.1560922861099243} 08/30/2021 16:49:32 - INFO - __main__ - Step 20075: {'lr': 0.00048182555030366854, 'samples': 3854400, 'steps': 20074, 'loss/train': 1.2336541414260864} 08/30/2021 16:49:33 - INFO - __main__ - Step 20076: {'lr': 0.0004818235638651678, 'samples': 3854592, 'steps': 20075, 'loss/train': 1.116799235343933} 08/30/2021 16:49:33 - INFO - __main__ - Step 20077: {'lr': 0.0004818215773222109, 'samples': 3854784, 'steps': 20076, 'loss/train': 0.4001154601573944} 08/30/2021 16:49:35 - INFO - __main__ - Step 20078: {'lr': 0.0004818195906747988, 'samples': 3854976, 'steps': 20077, 'loss/train': 2.4976325035095215} 08/30/2021 16:49:35 - INFO - __main__ - Step 20079: {'lr': 0.0004818176039229324, 'samples': 3855168, 'steps': 20078, 'loss/train': 1.6350609064102173} 08/30/2021 16:49:35 - INFO - __main__ - Step 20080: {'lr': 0.0004818156170666125, 'samples': 3855360, 'steps': 20079, 'loss/train': 1.3892173767089844} 08/30/2021 16:49:36 - INFO - __main__ - Step 20081: {'lr': 0.0004818136301058401, 'samples': 3855552, 'steps': 20080, 'loss/train': 1.1264094114303589} 08/30/2021 16:49:36 - INFO - __main__ - Step 20082: {'lr': 0.0004818116430406161, 'samples': 3855744, 'steps': 20081, 'loss/train': 2.3538107872009277} 08/30/2021 16:49:36 - INFO - __main__ - Step 20083: {'lr': 0.00048180965587094125, 'samples': 3855936, 'steps': 20082, 'loss/train': 1.9352130889892578} 08/30/2021 16:49:38 - INFO - __main__ - Step 20084: {'lr': 0.00048180766859681664, 'samples': 3856128, 'steps': 20083, 'loss/train': 1.302859902381897} 08/30/2021 16:49:39 - INFO - __main__ - Step 20085: {'lr': 0.000481805681218243, 'samples': 3856320, 'steps': 20084, 'loss/train': 1.5741057395935059} 08/30/2021 16:49:39 - INFO - __main__ - Step 20086: {'lr': 0.0004818036937352214, 'samples': 3856512, 'steps': 20085, 'loss/train': 2.0826728343963623} 08/30/2021 16:49:39 - INFO - __main__ - Step 20087: {'lr': 0.0004818017061477525, 'samples': 3856704, 'steps': 20086, 'loss/train': 1.552943468093872} 08/30/2021 16:49:40 - INFO - __main__ - Step 20088: {'lr': 0.00048179971845583734, 'samples': 3856896, 'steps': 20087, 'loss/train': 1.6637585163116455} 08/30/2021 16:49:42 - INFO - __main__ - Step 20089: {'lr': 0.00048179773065947683, 'samples': 3857088, 'steps': 20088, 'loss/train': 1.3537242412567139} 08/30/2021 16:49:42 - INFO - __main__ - Step 20090: {'lr': 0.0004817957427586719, 'samples': 3857280, 'steps': 20089, 'loss/train': 0.22368521988391876} 08/30/2021 16:49:42 - INFO - __main__ - Step 20091: {'lr': 0.00048179375475342333, 'samples': 3857472, 'steps': 20090, 'loss/train': 0.22531534731388092} 08/30/2021 16:49:43 - INFO - __main__ - Step 20092: {'lr': 0.00048179176664373214, 'samples': 3857664, 'steps': 20091, 'loss/train': 1.5876214504241943} 08/30/2021 16:49:43 - INFO - __main__ - Step 20093: {'lr': 0.0004817897784295991, 'samples': 3857856, 'steps': 20092, 'loss/train': 1.9929802417755127} 08/30/2021 16:49:43 - INFO - __main__ - Step 20094: {'lr': 0.0004817877901110251, 'samples': 3858048, 'steps': 20093, 'loss/train': 1.6999971866607666} 08/30/2021 16:49:45 - INFO - __main__ - Step 20095: {'lr': 0.0004817858016880112, 'samples': 3858240, 'steps': 20094, 'loss/train': 1.4086908102035522} 08/30/2021 16:49:45 - INFO - __main__ - Step 20096: {'lr': 0.0004817838131605582, 'samples': 3858432, 'steps': 20095, 'loss/train': 1.7002785205841064} 08/30/2021 16:49:46 - INFO - __main__ - Step 20097: {'lr': 0.00048178182452866694, 'samples': 3858624, 'steps': 20096, 'loss/train': 0.9283069968223572} 08/30/2021 16:49:46 - INFO - __main__ - Step 20098: {'lr': 0.0004817798357923384, 'samples': 3858816, 'steps': 20097, 'loss/train': 1.4377996921539307} 08/30/2021 16:49:46 - INFO - __main__ - Step 20099: {'lr': 0.00048177784695157335, 'samples': 3859008, 'steps': 20098, 'loss/train': 1.0285416841506958} 08/30/2021 16:49:48 - INFO - __main__ - Step 20100: {'lr': 0.00048177585800637286, 'samples': 3859200, 'steps': 20099, 'loss/train': 0.9273505210876465} 08/30/2021 16:49:48 - INFO - __main__ - Step 20101: {'lr': 0.00048177386895673774, 'samples': 3859392, 'steps': 20100, 'loss/train': 1.3331303596496582} 08/30/2021 16:49:49 - INFO - __main__ - Step 20102: {'lr': 0.0004817718798026689, 'samples': 3859584, 'steps': 20101, 'loss/train': 1.147251844406128} 08/30/2021 16:49:49 - INFO - __main__ - Step 20103: {'lr': 0.0004817698905441672, 'samples': 3859776, 'steps': 20102, 'loss/train': 1.8079439401626587} 08/30/2021 16:49:50 - INFO - __main__ - Step 20104: {'lr': 0.0004817679011812336, 'samples': 3859968, 'steps': 20103, 'loss/train': 2.1963179111480713} 08/30/2021 16:49:50 - INFO - __main__ - Step 20105: {'lr': 0.00048176591171386884, 'samples': 3860160, 'steps': 20104, 'loss/train': 1.6470838785171509} 08/30/2021 16:49:51 - INFO - __main__ - Step 20106: {'lr': 0.0004817639221420741, 'samples': 3860352, 'steps': 20105, 'loss/train': 1.1575138568878174} 08/30/2021 16:49:52 - INFO - __main__ - Step 20107: {'lr': 0.00048176193246585, 'samples': 3860544, 'steps': 20106, 'loss/train': 1.32097327709198} 08/30/2021 16:49:52 - INFO - __main__ - Step 20108: {'lr': 0.00048175994268519765, 'samples': 3860736, 'steps': 20107, 'loss/train': 1.5724048614501953} 08/30/2021 16:49:52 - INFO - __main__ - Step 20109: {'lr': 0.00048175795280011775, 'samples': 3860928, 'steps': 20108, 'loss/train': 2.2219698429107666} 08/30/2021 16:49:53 - INFO - __main__ - Step 20110: {'lr': 0.00048175596281061135, 'samples': 3861120, 'steps': 20109, 'loss/train': 1.98557448387146} 08/30/2021 16:49:55 - INFO - __main__ - Step 20111: {'lr': 0.00048175397271667925, 'samples': 3861312, 'steps': 20110, 'loss/train': 1.6294634342193604} 08/30/2021 16:49:55 - INFO - __main__ - Step 20112: {'lr': 0.00048175198251832244, 'samples': 3861504, 'steps': 20111, 'loss/train': 1.6430479288101196} 08/30/2021 16:49:56 - INFO - __main__ - Step 20113: {'lr': 0.00048174999221554173, 'samples': 3861696, 'steps': 20112, 'loss/train': 1.6404865980148315} 08/30/2021 16:49:56 - INFO - __main__ - Step 20114: {'lr': 0.000481748001808338, 'samples': 3861888, 'steps': 20113, 'loss/train': 1.6970770359039307} 08/30/2021 16:49:56 - INFO - __main__ - Step 20115: {'lr': 0.00048174601129671223, 'samples': 3862080, 'steps': 20114, 'loss/train': 1.7774577140808105} 08/30/2021 16:49:58 - INFO - __main__ - Step 20116: {'lr': 0.00048174402068066534, 'samples': 3862272, 'steps': 20115, 'loss/train': 1.4758708477020264} 08/30/2021 16:49:58 - INFO - __main__ - Step 20117: {'lr': 0.0004817420299601981, 'samples': 3862464, 'steps': 20116, 'loss/train': 1.9957894086837769} 08/30/2021 16:49:59 - INFO - __main__ - Step 20118: {'lr': 0.0004817400391353115, 'samples': 3862656, 'steps': 20117, 'loss/train': 1.3740090131759644} 08/30/2021 16:49:59 - INFO - __main__ - Step 20119: {'lr': 0.00048173804820600646, 'samples': 3862848, 'steps': 20118, 'loss/train': 2.055910110473633} 08/30/2021 16:49:59 - INFO - __main__ - Step 20120: {'lr': 0.0004817360571722838, 'samples': 3863040, 'steps': 20119, 'loss/train': 1.3270663022994995} 08/30/2021 16:50:01 - INFO - __main__ - Step 20121: {'lr': 0.00048173406603414445, 'samples': 3863232, 'steps': 20120, 'loss/train': 1.580013632774353} 08/30/2021 16:50:01 - INFO - __main__ - Step 20122: {'lr': 0.00048173207479158933, 'samples': 3863424, 'steps': 20121, 'loss/train': 1.3592381477355957} 08/30/2021 16:50:02 - INFO - __main__ - Step 20123: {'lr': 0.0004817300834446192, 'samples': 3863616, 'steps': 20122, 'loss/train': 1.9252469539642334} 08/30/2021 16:50:02 - INFO - __main__ - Step 20124: {'lr': 0.0004817280919932352, 'samples': 3863808, 'steps': 20123, 'loss/train': 1.3935565948486328} 08/30/2021 16:50:02 - INFO - __main__ - Step 20125: {'lr': 0.000481726100437438, 'samples': 3864000, 'steps': 20124, 'loss/train': 1.8088167905807495} 08/30/2021 16:50:04 - INFO - __main__ - Step 20126: {'lr': 0.00048172410877722865, 'samples': 3864192, 'steps': 20125, 'loss/train': 1.7946019172668457} 08/30/2021 16:50:04 - INFO - __main__ - Step 20127: {'lr': 0.00048172211701260807, 'samples': 3864384, 'steps': 20126, 'loss/train': 0.818877100944519} 08/30/2021 16:50:05 - INFO - __main__ - Step 20128: {'lr': 0.0004817201251435769, 'samples': 3864576, 'steps': 20127, 'loss/train': 1.384813666343689} 08/30/2021 16:50:05 - INFO - __main__ - Step 20129: {'lr': 0.00048171813317013633, 'samples': 3864768, 'steps': 20128, 'loss/train': 1.5953658819198608} 08/30/2021 16:50:05 - INFO - __main__ - Step 20130: {'lr': 0.00048171614109228714, 'samples': 3864960, 'steps': 20129, 'loss/train': 1.6424446105957031} 08/30/2021 16:50:07 - INFO - __main__ - Step 20131: {'lr': 0.0004817141489100302, 'samples': 3865152, 'steps': 20130, 'loss/train': 1.778563141822815} 08/30/2021 16:50:07 - INFO - __main__ - Step 20132: {'lr': 0.0004817121566233665, 'samples': 3865344, 'steps': 20131, 'loss/train': 1.9810020923614502} 08/30/2021 16:50:08 - INFO - __main__ - Step 20133: {'lr': 0.0004817101642322968, 'samples': 3865536, 'steps': 20132, 'loss/train': 0.08221045136451721} 08/30/2021 16:50:08 - INFO - __main__ - Step 20134: {'lr': 0.00048170817173682215, 'samples': 3865728, 'steps': 20133, 'loss/train': 1.5096927881240845} 08/30/2021 16:50:08 - INFO - __main__ - Step 20135: {'lr': 0.00048170617913694333, 'samples': 3865920, 'steps': 20134, 'loss/train': 2.2990646362304688} 08/30/2021 16:50:10 - INFO - __main__ - Step 20136: {'lr': 0.00048170418643266125, 'samples': 3866112, 'steps': 20135, 'loss/train': 1.6849663257598877} 08/30/2021 16:50:10 - INFO - __main__ - Step 20137: {'lr': 0.00048170219362397685, 'samples': 3866304, 'steps': 20136, 'loss/train': 1.553839921951294} 08/30/2021 16:50:11 - INFO - __main__ - Step 20138: {'lr': 0.00048170020071089105, 'samples': 3866496, 'steps': 20137, 'loss/train': 1.7705405950546265} 08/30/2021 16:50:11 - INFO - __main__ - Step 20139: {'lr': 0.00048169820769340476, 'samples': 3866688, 'steps': 20138, 'loss/train': 0.19859115779399872} 08/30/2021 16:50:11 - INFO - __main__ - Step 20140: {'lr': 0.0004816962145715188, 'samples': 3866880, 'steps': 20139, 'loss/train': 1.2331286668777466} 08/30/2021 16:50:13 - INFO - __main__ - Step 20141: {'lr': 0.00048169422134523404, 'samples': 3867072, 'steps': 20140, 'loss/train': 1.1087123155593872} 08/30/2021 16:50:13 - INFO - __main__ - Step 20142: {'lr': 0.0004816922280145515, 'samples': 3867264, 'steps': 20141, 'loss/train': 1.4092648029327393} 08/30/2021 16:50:14 - INFO - __main__ - Step 20143: {'lr': 0.00048169023457947195, 'samples': 3867456, 'steps': 20142, 'loss/train': 1.1133297681808472} 08/30/2021 16:50:14 - INFO - __main__ - Step 20144: {'lr': 0.0004816882410399964, 'samples': 3867648, 'steps': 20143, 'loss/train': 1.3509678840637207} 08/30/2021 16:50:14 - INFO - __main__ - Step 20145: {'lr': 0.00048168624739612577, 'samples': 3867840, 'steps': 20144, 'loss/train': 1.8391437530517578} 08/30/2021 16:50:16 - INFO - __main__ - Step 20146: {'lr': 0.0004816842536478608, 'samples': 3868032, 'steps': 20145, 'loss/train': 3.161020517349243} 08/30/2021 16:50:16 - INFO - __main__ - Step 20147: {'lr': 0.00048168225979520254, 'samples': 3868224, 'steps': 20146, 'loss/train': 2.0961363315582275} 08/30/2021 16:50:17 - INFO - __main__ - Step 20148: {'lr': 0.0004816802658381518, 'samples': 3868416, 'steps': 20147, 'loss/train': 1.7573124170303345} 08/30/2021 16:50:17 - INFO - __main__ - Step 20149: {'lr': 0.00048167827177670946, 'samples': 3868608, 'steps': 20148, 'loss/train': 1.8705545663833618} 08/30/2021 16:50:18 - INFO - __main__ - Step 20150: {'lr': 0.0004816762776108765, 'samples': 3868800, 'steps': 20149, 'loss/train': 1.470387578010559} 08/30/2021 16:50:18 - INFO - __main__ - Step 20151: {'lr': 0.0004816742833406538, 'samples': 3868992, 'steps': 20150, 'loss/train': 2.1693620681762695} 08/30/2021 16:50:19 - INFO - __main__ - Step 20152: {'lr': 0.0004816722889660423, 'samples': 3869184, 'steps': 20151, 'loss/train': 1.0245689153671265} 08/30/2021 16:50:20 - INFO - __main__ - Step 20153: {'lr': 0.00048167029448704273, 'samples': 3869376, 'steps': 20152, 'loss/train': 1.4094831943511963} 08/30/2021 16:50:20 - INFO - __main__ - Step 20154: {'lr': 0.00048166829990365615, 'samples': 3869568, 'steps': 20153, 'loss/train': 1.484419822692871} 08/30/2021 16:50:20 - INFO - __main__ - Step 20155: {'lr': 0.0004816663052158834, 'samples': 3869760, 'steps': 20154, 'loss/train': 1.6280980110168457} 08/30/2021 16:50:21 - INFO - __main__ - Step 20156: {'lr': 0.0004816643104237254, 'samples': 3869952, 'steps': 20155, 'loss/train': 1.244726538658142} 08/30/2021 16:50:22 - INFO - __main__ - Step 20157: {'lr': 0.00048166231552718305, 'samples': 3870144, 'steps': 20156, 'loss/train': 1.5656678676605225} 08/30/2021 16:50:23 - INFO - __main__ - Step 20158: {'lr': 0.0004816603205262572, 'samples': 3870336, 'steps': 20157, 'loss/train': 1.7199552059173584} 08/30/2021 16:50:23 - INFO - __main__ - Step 20159: {'lr': 0.0004816583254209488, 'samples': 3870528, 'steps': 20158, 'loss/train': 1.8591266870498657} 08/30/2021 16:50:23 - INFO - __main__ - Step 20160: {'lr': 0.00048165633021125874, 'samples': 3870720, 'steps': 20159, 'loss/train': 1.7345173358917236} 08/30/2021 16:50:24 - INFO - __main__ - Step 20161: {'lr': 0.0004816543348971879, 'samples': 3870912, 'steps': 20160, 'loss/train': 1.5919828414916992} 08/30/2021 16:50:25 - INFO - __main__ - Step 20162: {'lr': 0.0004816523394787372, 'samples': 3871104, 'steps': 20161, 'loss/train': 1.9427335262298584} 08/30/2021 16:50:26 - INFO - __main__ - Step 20163: {'lr': 0.00048165034395590756, 'samples': 3871296, 'steps': 20162, 'loss/train': 2.0290613174438477} 08/30/2021 16:50:26 - INFO - __main__ - Step 20164: {'lr': 0.0004816483483286998, 'samples': 3871488, 'steps': 20163, 'loss/train': 0.8475186228752136} 08/30/2021 16:50:26 - INFO - __main__ - Step 20165: {'lr': 0.0004816463525971149, 'samples': 3871680, 'steps': 20164, 'loss/train': 1.5292781591415405} 08/30/2021 16:50:27 - INFO - __main__ - Step 20166: {'lr': 0.0004816443567611537, 'samples': 3871872, 'steps': 20165, 'loss/train': 1.7337758541107178} 08/30/2021 16:50:29 - INFO - __main__ - Step 20167: {'lr': 0.00048164236082081713, 'samples': 3872064, 'steps': 20166, 'loss/train': 1.8352793455123901} 08/30/2021 16:50:29 - INFO - __main__ - Step 20168: {'lr': 0.00048164036477610616, 'samples': 3872256, 'steps': 20167, 'loss/train': 1.8482677936553955} 08/30/2021 16:50:30 - INFO - __main__ - Step 20169: {'lr': 0.00048163836862702154, 'samples': 3872448, 'steps': 20168, 'loss/train': 0.8686457276344299} 08/30/2021 16:50:30 - INFO - __main__ - Step 20170: {'lr': 0.0004816363723735643, 'samples': 3872640, 'steps': 20169, 'loss/train': 1.7034279108047485} 08/30/2021 16:50:30 - INFO - __main__ - Step 20171: {'lr': 0.00048163437601573525, 'samples': 3872832, 'steps': 20170, 'loss/train': 0.10003358125686646} 08/30/2021 16:50:32 - INFO - __main__ - Step 20172: {'lr': 0.00048163237955353526, 'samples': 3873024, 'steps': 20171, 'loss/train': 1.6900075674057007} 08/30/2021 16:50:32 - INFO - __main__ - Step 20173: {'lr': 0.00048163038298696537, 'samples': 3873216, 'steps': 20172, 'loss/train': 1.5002872943878174} 08/30/2021 16:50:33 - INFO - __main__ - Step 20174: {'lr': 0.00048162838631602643, 'samples': 3873408, 'steps': 20173, 'loss/train': 1.8476632833480835} 08/30/2021 16:50:33 - INFO - __main__ - Step 20175: {'lr': 0.00048162638954071926, 'samples': 3873600, 'steps': 20174, 'loss/train': 1.378610372543335} 08/30/2021 16:50:33 - INFO - __main__ - Step 20176: {'lr': 0.0004816243926610448, 'samples': 3873792, 'steps': 20175, 'loss/train': 1.5293242931365967} 08/30/2021 16:50:35 - INFO - __main__ - Step 20177: {'lr': 0.000481622395677004, 'samples': 3873984, 'steps': 20176, 'loss/train': 1.675130844116211} 08/30/2021 16:50:35 - INFO - __main__ - Step 20178: {'lr': 0.0004816203985885977, 'samples': 3874176, 'steps': 20177, 'loss/train': 1.2655019760131836} 08/30/2021 16:50:36 - INFO - __main__ - Step 20179: {'lr': 0.0004816184013958268, 'samples': 3874368, 'steps': 20178, 'loss/train': 0.8092939257621765} 08/30/2021 16:50:36 - INFO - __main__ - Step 20180: {'lr': 0.0004816164040986923, 'samples': 3874560, 'steps': 20179, 'loss/train': 1.2360841035842896} 08/30/2021 16:50:36 - INFO - __main__ - Step 20181: {'lr': 0.00048161440669719496, 'samples': 3874752, 'steps': 20180, 'loss/train': 1.3704040050506592} 08/30/2021 16:50:37 - INFO - __main__ - Step 20182: {'lr': 0.00048161240919133573, 'samples': 3874944, 'steps': 20181, 'loss/train': 1.7986598014831543} 08/30/2021 16:50:39 - INFO - __main__ - Step 20183: {'lr': 0.00048161041158111564, 'samples': 3875136, 'steps': 20182, 'loss/train': 1.7684286832809448} 08/30/2021 16:50:39 - INFO - __main__ - Step 20184: {'lr': 0.0004816084138665353, 'samples': 3875328, 'steps': 20183, 'loss/train': 2.0559840202331543} 08/30/2021 16:50:40 - INFO - __main__ - Step 20185: {'lr': 0.00048160641604759593, 'samples': 3875520, 'steps': 20184, 'loss/train': 1.800355315208435} 08/30/2021 16:50:40 - INFO - __main__ - Step 20186: {'lr': 0.0004816044181242982, 'samples': 3875712, 'steps': 20185, 'loss/train': 1.0849143266677856} 08/30/2021 16:50:40 - INFO - __main__ - Step 20187: {'lr': 0.0004816024200966431, 'samples': 3875904, 'steps': 20186, 'loss/train': 1.4484061002731323} 08/30/2021 16:50:41 - INFO - __main__ - Step 20188: {'lr': 0.00048160042196463153, 'samples': 3876096, 'steps': 20187, 'loss/train': 1.6775819063186646} 08/30/2021 16:50:43 - INFO - __main__ - Step 20189: {'lr': 0.00048159842372826446, 'samples': 3876288, 'steps': 20188, 'loss/train': 0.43652939796447754} 08/30/2021 16:50:43 - INFO - __main__ - Step 20190: {'lr': 0.0004815964253875426, 'samples': 3876480, 'steps': 20189, 'loss/train': 1.82103431224823} 08/30/2021 16:50:44 - INFO - __main__ - Step 20191: {'lr': 0.000481594426942467, 'samples': 3876672, 'steps': 20190, 'loss/train': 1.695461630821228} 08/30/2021 16:50:44 - INFO - __main__ - Step 20192: {'lr': 0.0004815924283930385, 'samples': 3876864, 'steps': 20191, 'loss/train': 0.7486909031867981} 08/30/2021 16:50:45 - INFO - __main__ - Step 20193: {'lr': 0.0004815904297392582, 'samples': 3877056, 'steps': 20192, 'loss/train': 1.5004451274871826} 08/30/2021 16:50:45 - INFO - __main__ - Step 20194: {'lr': 0.00048158843098112657, 'samples': 3877248, 'steps': 20193, 'loss/train': 0.9767536520957947} 08/30/2021 16:50:45 - INFO - __main__ - Step 20195: {'lr': 0.00048158643211864495, 'samples': 3877440, 'steps': 20194, 'loss/train': 0.047608163207769394} 08/30/2021 16:50:47 - INFO - __main__ - Step 20196: {'lr': 0.000481584433151814, 'samples': 3877632, 'steps': 20195, 'loss/train': 0.05013556405901909} 08/30/2021 16:50:47 - INFO - __main__ - Step 20197: {'lr': 0.00048158243408063465, 'samples': 3877824, 'steps': 20196, 'loss/train': 1.9597336053848267} 08/30/2021 16:50:47 - INFO - __main__ - Step 20198: {'lr': 0.0004815804349051078, 'samples': 3878016, 'steps': 20197, 'loss/train': 1.4055026769638062} 08/30/2021 16:50:48 - INFO - __main__ - Step 20199: {'lr': 0.0004815784356252344, 'samples': 3878208, 'steps': 20198, 'loss/train': 1.3472555875778198} 08/30/2021 16:50:48 - INFO - __main__ - Step 20200: {'lr': 0.0004815764362410154, 'samples': 3878400, 'steps': 20199, 'loss/train': 2.0765771865844727} 08/30/2021 16:50:50 - INFO - __main__ - Step 20201: {'lr': 0.0004815744367524516, 'samples': 3878592, 'steps': 20200, 'loss/train': 1.5773504972457886} 08/30/2021 16:50:50 - INFO - __main__ - Step 20202: {'lr': 0.0004815724371595439, 'samples': 3878784, 'steps': 20201, 'loss/train': 2.0365428924560547} 08/30/2021 16:50:51 - INFO - __main__ - Step 20203: {'lr': 0.00048157043746229324, 'samples': 3878976, 'steps': 20202, 'loss/train': 1.6232331991195679} 08/30/2021 16:50:51 - INFO - __main__ - Step 20204: {'lr': 0.0004815684376607006, 'samples': 3879168, 'steps': 20203, 'loss/train': 1.6831016540527344} 08/30/2021 16:50:52 - INFO - __main__ - Step 20205: {'lr': 0.0004815664377547667, 'samples': 3879360, 'steps': 20204, 'loss/train': 1.1959266662597656} 08/30/2021 16:50:52 - INFO - __main__ - Step 20206: {'lr': 0.00048156443774449254, 'samples': 3879552, 'steps': 20205, 'loss/train': 1.4080724716186523} 08/30/2021 16:50:53 - INFO - __main__ - Step 20207: {'lr': 0.00048156243762987905, 'samples': 3879744, 'steps': 20206, 'loss/train': 0.19121168553829193} 08/30/2021 16:50:54 - INFO - __main__ - Step 20208: {'lr': 0.00048156043741092705, 'samples': 3879936, 'steps': 20207, 'loss/train': 1.7060894966125488} 08/30/2021 16:50:54 - INFO - __main__ - Step 20209: {'lr': 0.00048155843708763755, 'samples': 3880128, 'steps': 20208, 'loss/train': 1.4156874418258667} 08/30/2021 16:50:54 - INFO - __main__ - Step 20210: {'lr': 0.0004815564366600114, 'samples': 3880320, 'steps': 20209, 'loss/train': 1.5062568187713623} 08/30/2021 16:50:55 - INFO - __main__ - Step 20211: {'lr': 0.0004815544361280494, 'samples': 3880512, 'steps': 20210, 'loss/train': 1.4830186367034912} 08/30/2021 16:50:56 - INFO - __main__ - Step 20212: {'lr': 0.00048155243549175263, 'samples': 3880704, 'steps': 20211, 'loss/train': 1.079834222793579} 08/30/2021 16:50:57 - INFO - __main__ - Step 20213: {'lr': 0.00048155043475112184, 'samples': 3880896, 'steps': 20212, 'loss/train': 2.0521597862243652} 08/30/2021 16:50:57 - INFO - __main__ - Step 20214: {'lr': 0.0004815484339061581, 'samples': 3881088, 'steps': 20213, 'loss/train': 1.731704831123352} 08/30/2021 16:50:58 - INFO - __main__ - Step 20215: {'lr': 0.0004815464329568621, 'samples': 3881280, 'steps': 20214, 'loss/train': 1.4401785135269165} 08/30/2021 16:50:58 - INFO - __main__ - Step 20216: {'lr': 0.00048154443190323495, 'samples': 3881472, 'steps': 20215, 'loss/train': 1.3341749906539917} 08/30/2021 16:51:00 - INFO - __main__ - Step 20217: {'lr': 0.0004815424307452774, 'samples': 3881664, 'steps': 20216, 'loss/train': 1.637634515762329} 08/30/2021 16:51:00 - INFO - __main__ - Step 20218: {'lr': 0.0004815404294829904, 'samples': 3881856, 'steps': 20217, 'loss/train': 1.7783867120742798} 08/30/2021 16:51:01 - INFO - __main__ - Step 20219: {'lr': 0.0004815384281163748, 'samples': 3882048, 'steps': 20218, 'loss/train': 1.814454436302185} 08/30/2021 16:51:01 - INFO - __main__ - Step 20220: {'lr': 0.0004815364266454316, 'samples': 3882240, 'steps': 20219, 'loss/train': 1.4207069873809814} 08/30/2021 16:51:01 - INFO - __main__ - Step 20221: {'lr': 0.00048153442507016173, 'samples': 3882432, 'steps': 20220, 'loss/train': 1.6495163440704346} 08/30/2021 16:51:03 - INFO - __main__ - Step 20222: {'lr': 0.00048153242339056594, 'samples': 3882624, 'steps': 20221, 'loss/train': 1.6814595460891724} 08/30/2021 16:51:04 - INFO - __main__ - Step 20223: {'lr': 0.0004815304216066453, 'samples': 3882816, 'steps': 20222, 'loss/train': 0.20040147006511688} 08/30/2021 16:51:04 - INFO - __main__ - Step 20224: {'lr': 0.0004815284197184005, 'samples': 3883008, 'steps': 20223, 'loss/train': 1.9685205221176147} 08/30/2021 16:51:04 - INFO - __main__ - Step 20225: {'lr': 0.0004815264177258326, 'samples': 3883200, 'steps': 20224, 'loss/train': 1.3303196430206299} 08/30/2021 16:51:05 - INFO - __main__ - Step 20226: {'lr': 0.00048152441562894255, 'samples': 3883392, 'steps': 20225, 'loss/train': 1.6731454133987427} 08/30/2021 16:51:06 - INFO - __main__ - Step 20227: {'lr': 0.0004815224134277311, 'samples': 3883584, 'steps': 20226, 'loss/train': 1.7326157093048096} 08/30/2021 16:51:07 - INFO - __main__ - Step 20228: {'lr': 0.00048152041112219926, 'samples': 3883776, 'steps': 20227, 'loss/train': 1.5589109659194946} 08/30/2021 16:51:07 - INFO - __main__ - Step 20229: {'lr': 0.0004815184087123479, 'samples': 3883968, 'steps': 20228, 'loss/train': 0.0714040994644165} 08/30/2021 16:51:07 - INFO - __main__ - Step 20230: {'lr': 0.0004815164061981778, 'samples': 3884160, 'steps': 20229, 'loss/train': 1.3627091646194458} 08/30/2021 16:51:08 - INFO - __main__ - Step 20231: {'lr': 0.0004815144035796901, 'samples': 3884352, 'steps': 20230, 'loss/train': 1.625974178314209} 08/30/2021 16:51:09 - INFO - __main__ - Step 20232: {'lr': 0.0004815124008568856, 'samples': 3884544, 'steps': 20231, 'loss/train': 1.6093692779541016} 08/30/2021 16:51:10 - INFO - __main__ - Step 20233: {'lr': 0.00048151039802976517, 'samples': 3884736, 'steps': 20232, 'loss/train': 1.4500622749328613} 08/30/2021 16:51:10 - INFO - __main__ - Step 20234: {'lr': 0.00048150839509832966, 'samples': 3884928, 'steps': 20233, 'loss/train': 1.9628890752792358} 08/30/2021 16:51:10 - INFO - __main__ - Step 20235: {'lr': 0.0004815063920625801, 'samples': 3885120, 'steps': 20234, 'loss/train': 1.5627418756484985} 08/30/2021 16:51:11 - INFO - __main__ - Step 20236: {'lr': 0.00048150438892251724, 'samples': 3885312, 'steps': 20235, 'loss/train': 1.7016435861587524} 08/30/2021 16:51:11 - INFO - __main__ - Step 20237: {'lr': 0.00048150238567814217, 'samples': 3885504, 'steps': 20236, 'loss/train': 2.050870418548584} 08/30/2021 16:51:13 - INFO - __main__ - Step 20238: {'lr': 0.0004815003823294557, 'samples': 3885696, 'steps': 20237, 'loss/train': 1.4891928434371948} 08/30/2021 16:51:13 - INFO - __main__ - Step 20239: {'lr': 0.0004814983788764587, 'samples': 3885888, 'steps': 20238, 'loss/train': 1.7690858840942383} 08/30/2021 16:51:13 - INFO - __main__ - Step 20240: {'lr': 0.00048149637531915215, 'samples': 3886080, 'steps': 20239, 'loss/train': 1.8192404508590698} 08/30/2021 16:51:14 - INFO - __main__ - Step 20241: {'lr': 0.00048149437165753684, 'samples': 3886272, 'steps': 20240, 'loss/train': 1.5038063526153564} 08/30/2021 16:51:14 - INFO - __main__ - Step 20242: {'lr': 0.00048149236789161374, 'samples': 3886464, 'steps': 20241, 'loss/train': 1.7118151187896729} 08/30/2021 16:51:16 - INFO - __main__ - Step 20243: {'lr': 0.0004814903640213838, 'samples': 3886656, 'steps': 20242, 'loss/train': 1.7593092918395996} 08/30/2021 16:51:16 - INFO - __main__ - Step 20244: {'lr': 0.0004814883600468478, 'samples': 3886848, 'steps': 20243, 'loss/train': 1.4841561317443848} 08/30/2021 16:51:16 - INFO - __main__ - Step 20245: {'lr': 0.0004814863559680068, 'samples': 3887040, 'steps': 20244, 'loss/train': 1.5900686979293823} 08/30/2021 16:51:17 - INFO - __main__ - Step 20246: {'lr': 0.00048148435178486156, 'samples': 3887232, 'steps': 20245, 'loss/train': 1.7600446939468384} 08/30/2021 16:51:17 - INFO - __main__ - Step 20247: {'lr': 0.00048148234749741304, 'samples': 3887424, 'steps': 20246, 'loss/train': 1.2677690982818604} 08/30/2021 16:51:19 - INFO - __main__ - Step 20248: {'lr': 0.0004814803431056622, 'samples': 3887616, 'steps': 20247, 'loss/train': 0.11285198479890823} 08/30/2021 16:51:19 - INFO - __main__ - Step 20249: {'lr': 0.0004814783386096099, 'samples': 3887808, 'steps': 20248, 'loss/train': 1.5451240539550781} 08/30/2021 16:51:19 - INFO - __main__ - Step 20250: {'lr': 0.00048147633400925693, 'samples': 3888000, 'steps': 20249, 'loss/train': 1.4259566068649292} 08/30/2021 16:51:20 - INFO - __main__ - Step 20251: {'lr': 0.00048147432930460433, 'samples': 3888192, 'steps': 20250, 'loss/train': 1.0979019403457642} 08/30/2021 16:51:20 - INFO - __main__ - Step 20252: {'lr': 0.00048147232449565305, 'samples': 3888384, 'steps': 20251, 'loss/train': 1.3598960638046265} 08/30/2021 16:51:22 - INFO - __main__ - Step 20253: {'lr': 0.00048147031958240384, 'samples': 3888576, 'steps': 20252, 'loss/train': 1.4012603759765625} 08/30/2021 16:51:22 - INFO - __main__ - Step 20254: {'lr': 0.00048146831456485776, 'samples': 3888768, 'steps': 20253, 'loss/train': 1.9264036417007446} 08/30/2021 16:51:22 - INFO - __main__ - Step 20255: {'lr': 0.0004814663094430155, 'samples': 3888960, 'steps': 20254, 'loss/train': 1.0462913513183594} 08/30/2021 16:51:23 - INFO - __main__ - Step 20256: {'lr': 0.00048146430421687817, 'samples': 3889152, 'steps': 20255, 'loss/train': 2.1124379634857178} 08/30/2021 16:51:23 - INFO - __main__ - Step 20257: {'lr': 0.00048146229888644656, 'samples': 3889344, 'steps': 20256, 'loss/train': 1.7220581769943237} 08/30/2021 16:51:24 - INFO - __main__ - Step 20258: {'lr': 0.00048146029345172165, 'samples': 3889536, 'steps': 20257, 'loss/train': 2.0938880443573} 08/30/2021 16:51:25 - INFO - __main__ - Step 20259: {'lr': 0.0004814582879127043, 'samples': 3889728, 'steps': 20258, 'loss/train': 1.6154398918151855} 08/30/2021 16:51:25 - INFO - __main__ - Step 20260: {'lr': 0.0004814562822693954, 'samples': 3889920, 'steps': 20259, 'loss/train': 1.5098820924758911} 08/30/2021 16:51:26 - INFO - __main__ - Step 20261: {'lr': 0.00048145427652179583, 'samples': 3890112, 'steps': 20260, 'loss/train': 1.702278733253479} 08/30/2021 16:51:26 - INFO - __main__ - Step 20262: {'lr': 0.0004814522706699066, 'samples': 3890304, 'steps': 20261, 'loss/train': 2.050403356552124} 08/30/2021 16:51:27 - INFO - __main__ - Step 20263: {'lr': 0.00048145026471372855, 'samples': 3890496, 'steps': 20262, 'loss/train': 1.369707703590393} 08/30/2021 16:51:28 - INFO - __main__ - Step 20264: {'lr': 0.0004814482586532626, 'samples': 3890688, 'steps': 20263, 'loss/train': 1.726524829864502} 08/30/2021 16:51:28 - INFO - __main__ - Step 20265: {'lr': 0.00048144625248850955, 'samples': 3890880, 'steps': 20264, 'loss/train': 1.3683204650878906} 08/30/2021 16:51:29 - INFO - __main__ - Step 20266: {'lr': 0.0004814442462194704, 'samples': 3891072, 'steps': 20265, 'loss/train': 1.4735925197601318} 08/30/2021 16:51:29 - INFO - __main__ - Step 20267: {'lr': 0.0004814422398461461, 'samples': 3891264, 'steps': 20266, 'loss/train': 1.1498258113861084} 08/30/2021 16:51:29 - INFO - __main__ - Step 20268: {'lr': 0.00048144023336853746, 'samples': 3891456, 'steps': 20267, 'loss/train': 1.1298660039901733} 08/30/2021 16:51:31 - INFO - __main__ - Step 20269: {'lr': 0.00048143822678664545, 'samples': 3891648, 'steps': 20268, 'loss/train': 1.6574901342391968} 08/30/2021 16:51:31 - INFO - __main__ - Step 20270: {'lr': 0.00048143622010047096, 'samples': 3891840, 'steps': 20269, 'loss/train': 1.2668615579605103} 08/30/2021 16:51:32 - INFO - __main__ - Step 20271: {'lr': 0.0004814342133100149, 'samples': 3892032, 'steps': 20270, 'loss/train': 1.652359962463379} 08/30/2021 16:51:32 - INFO - __main__ - Step 20272: {'lr': 0.00048143220641527805, 'samples': 3892224, 'steps': 20271, 'loss/train': 0.955489456653595} 08/30/2021 16:51:32 - INFO - __main__ - Step 20273: {'lr': 0.0004814301994162615, 'samples': 3892416, 'steps': 20272, 'loss/train': 1.2216873168945312} 08/30/2021 16:51:34 - INFO - __main__ - Step 20274: {'lr': 0.000481428192312966, 'samples': 3892608, 'steps': 20273, 'loss/train': 0.6006215214729309} 08/30/2021 16:51:35 - INFO - __main__ - Step 20275: {'lr': 0.0004814261851053926, 'samples': 3892800, 'steps': 20274, 'loss/train': 2.2969014644622803} 08/30/2021 16:51:35 - INFO - __main__ - Step 20276: {'lr': 0.00048142417779354214, 'samples': 3892992, 'steps': 20275, 'loss/train': 1.3134269714355469} 08/30/2021 16:51:35 - INFO - __main__ - Step 20277: {'lr': 0.0004814221703774155, 'samples': 3893184, 'steps': 20276, 'loss/train': 1.9949308633804321} 08/30/2021 16:51:36 - INFO - __main__ - Step 20278: {'lr': 0.00048142016285701356, 'samples': 3893376, 'steps': 20277, 'loss/train': 0.6431128978729248} 08/30/2021 16:51:37 - INFO - __main__ - Step 20279: {'lr': 0.00048141815523233735, 'samples': 3893568, 'steps': 20278, 'loss/train': 1.374727487564087} 08/30/2021 16:51:38 - INFO - __main__ - Step 20280: {'lr': 0.00048141614750338757, 'samples': 3893760, 'steps': 20279, 'loss/train': 1.5767276287078857} 08/30/2021 16:51:38 - INFO - __main__ - Step 20281: {'lr': 0.00048141413967016535, 'samples': 3893952, 'steps': 20280, 'loss/train': 2.1855556964874268} 08/30/2021 16:51:38 - INFO - __main__ - Step 20282: {'lr': 0.00048141213173267145, 'samples': 3894144, 'steps': 20281, 'loss/train': 1.0905746221542358} 08/30/2021 16:51:39 - INFO - __main__ - Step 20283: {'lr': 0.0004814101236909068, 'samples': 3894336, 'steps': 20282, 'loss/train': 1.8638893365859985} 08/30/2021 16:51:40 - INFO - __main__ - Step 20284: {'lr': 0.00048140811554487234, 'samples': 3894528, 'steps': 20283, 'loss/train': 1.758457064628601} 08/30/2021 16:51:41 - INFO - __main__ - Step 20285: {'lr': 0.000481406107294569, 'samples': 3894720, 'steps': 20284, 'loss/train': 1.4025347232818604} 08/30/2021 16:51:41 - INFO - __main__ - Step 20286: {'lr': 0.0004814040989399975, 'samples': 3894912, 'steps': 20285, 'loss/train': 1.8196550607681274} 08/30/2021 16:51:41 - INFO - __main__ - Step 20287: {'lr': 0.000481402090481159, 'samples': 3895104, 'steps': 20286, 'loss/train': 1.3624060153961182} 08/30/2021 16:51:42 - INFO - __main__ - Step 20288: {'lr': 0.0004814000819180543, 'samples': 3895296, 'steps': 20287, 'loss/train': 0.644443929195404} 08/30/2021 16:51:42 - INFO - __main__ - Step 20289: {'lr': 0.00048139807325068423, 'samples': 3895488, 'steps': 20288, 'loss/train': 1.156691074371338} 08/30/2021 16:51:44 - INFO - __main__ - Step 20290: {'lr': 0.0004813960644790498, 'samples': 3895680, 'steps': 20289, 'loss/train': 1.8000234365463257} 08/30/2021 16:51:44 - INFO - __main__ - Step 20291: {'lr': 0.00048139405560315186, 'samples': 3895872, 'steps': 20290, 'loss/train': 1.5448402166366577} 08/30/2021 16:51:44 - INFO - __main__ - Step 20292: {'lr': 0.0004813920466229913, 'samples': 3896064, 'steps': 20291, 'loss/train': 2.0204708576202393} 08/30/2021 16:51:45 - INFO - __main__ - Step 20293: {'lr': 0.0004813900375385691, 'samples': 3896256, 'steps': 20292, 'loss/train': 1.535262107849121} 08/30/2021 16:51:45 - INFO - __main__ - Step 20294: {'lr': 0.0004813880283498861, 'samples': 3896448, 'steps': 20293, 'loss/train': 1.7797614336013794} 08/30/2021 16:51:47 - INFO - __main__ - Step 20295: {'lr': 0.00048138601905694324, 'samples': 3896640, 'steps': 20294, 'loss/train': 1.4918376207351685} 08/30/2021 16:51:47 - INFO - __main__ - Step 20296: {'lr': 0.0004813840096597414, 'samples': 3896832, 'steps': 20295, 'loss/train': 1.7750217914581299} 08/30/2021 16:51:47 - INFO - __main__ - Step 20297: {'lr': 0.00048138200015828146, 'samples': 3897024, 'steps': 20296, 'loss/train': 0.6045969724655151} 08/30/2021 16:51:48 - INFO - __main__ - Step 20298: {'lr': 0.00048137999055256444, 'samples': 3897216, 'steps': 20297, 'loss/train': 1.321756362915039} 08/30/2021 16:51:48 - INFO - __main__ - Step 20299: {'lr': 0.0004813779808425911, 'samples': 3897408, 'steps': 20298, 'loss/train': 2.277691125869751} 08/30/2021 16:51:50 - INFO - __main__ - Step 20300: {'lr': 0.0004813759710283624, 'samples': 3897600, 'steps': 20299, 'loss/train': 1.074888825416565} 08/30/2021 16:51:51 - INFO - __main__ - Step 20301: {'lr': 0.0004813739611098793, 'samples': 3897792, 'steps': 20300, 'loss/train': 1.1064374446868896} 08/30/2021 16:51:51 - INFO - __main__ - Step 20302: {'lr': 0.00048137195108714266, 'samples': 3897984, 'steps': 20301, 'loss/train': 1.246031641960144} 08/30/2021 16:51:51 - INFO - __main__ - Step 20303: {'lr': 0.00048136994096015343, 'samples': 3898176, 'steps': 20302, 'loss/train': 2.2300167083740234} 08/30/2021 16:51:52 - INFO - __main__ - Step 20304: {'lr': 0.00048136793072891236, 'samples': 3898368, 'steps': 20303, 'loss/train': 0.9699680805206299} 08/30/2021 16:51:52 - INFO - __main__ - Step 20305: {'lr': 0.00048136592039342053, 'samples': 3898560, 'steps': 20304, 'loss/train': 0.25588709115982056} 08/30/2021 16:51:54 - INFO - __main__ - Step 20306: {'lr': 0.0004813639099536789, 'samples': 3898752, 'steps': 20305, 'loss/train': 0.08922585099935532} 08/30/2021 16:51:54 - INFO - __main__ - Step 20307: {'lr': 0.0004813618994096881, 'samples': 3898944, 'steps': 20306, 'loss/train': 1.9414191246032715} 08/30/2021 16:51:54 - INFO - __main__ - Step 20308: {'lr': 0.0004813598887614492, 'samples': 3899136, 'steps': 20307, 'loss/train': 2.3342318534851074} 08/30/2021 16:51:55 - INFO - __main__ - Step 20309: {'lr': 0.0004813578780089632, 'samples': 3899328, 'steps': 20308, 'loss/train': 1.780541181564331} 08/30/2021 16:51:55 - INFO - __main__ - Step 20310: {'lr': 0.00048135586715223087, 'samples': 3899520, 'steps': 20309, 'loss/train': 1.5144213438034058} 08/30/2021 16:51:56 - INFO - __main__ - Step 20311: {'lr': 0.00048135385619125316, 'samples': 3899712, 'steps': 20310, 'loss/train': 1.6306337118148804} 08/30/2021 16:51:57 - INFO - __main__ - Step 20312: {'lr': 0.00048135184512603093, 'samples': 3899904, 'steps': 20311, 'loss/train': 1.8974195718765259} 08/30/2021 16:51:57 - INFO - __main__ - Step 20313: {'lr': 0.00048134983395656516, 'samples': 3900096, 'steps': 20312, 'loss/train': 1.349603533744812} 08/30/2021 16:51:58 - INFO - __main__ - Step 20314: {'lr': 0.00048134782268285676, 'samples': 3900288, 'steps': 20313, 'loss/train': 1.4073094129562378} 08/30/2021 16:51:58 - INFO - __main__ - Step 20315: {'lr': 0.00048134581130490655, 'samples': 3900480, 'steps': 20314, 'loss/train': 0.14571332931518555} 08/30/2021 16:51:59 - INFO - __main__ - Step 20316: {'lr': 0.0004813437998227155, 'samples': 3900672, 'steps': 20315, 'loss/train': 1.4282830953598022} 08/30/2021 16:52:00 - INFO - __main__ - Step 20317: {'lr': 0.00048134178823628455, 'samples': 3900864, 'steps': 20316, 'loss/train': 0.07498446106910706} 08/30/2021 16:52:00 - INFO - __main__ - Step 20318: {'lr': 0.0004813397765456145, 'samples': 3901056, 'steps': 20317, 'loss/train': 1.475098729133606} 08/30/2021 16:52:01 - INFO - __main__ - Step 20319: {'lr': 0.00048133776475070637, 'samples': 3901248, 'steps': 20318, 'loss/train': 1.4537569284439087} 08/30/2021 16:52:01 - INFO - __main__ - Step 20320: {'lr': 0.00048133575285156093, 'samples': 3901440, 'steps': 20319, 'loss/train': 1.7889646291732788} 08/30/2021 16:52:03 - INFO - __main__ - Step 20321: {'lr': 0.00048133374084817927, 'samples': 3901632, 'steps': 20320, 'loss/train': 1.2979167699813843} 08/30/2021 16:52:03 - INFO - __main__ - Step 20322: {'lr': 0.00048133172874056213, 'samples': 3901824, 'steps': 20321, 'loss/train': 1.4164572954177856} 08/30/2021 16:52:04 - INFO - __main__ - Step 20323: {'lr': 0.0004813297165287105, 'samples': 3902016, 'steps': 20322, 'loss/train': 0.38410359621047974} 08/30/2021 16:52:04 - INFO - __main__ - Step 20324: {'lr': 0.00048132770421262526, 'samples': 3902208, 'steps': 20323, 'loss/train': 1.6559373140335083} 08/30/2021 16:52:04 - INFO - __main__ - Step 20325: {'lr': 0.00048132569179230736, 'samples': 3902400, 'steps': 20324, 'loss/train': 1.012794852256775} 08/30/2021 16:52:06 - INFO - __main__ - Step 20326: {'lr': 0.0004813236792677577, 'samples': 3902592, 'steps': 20325, 'loss/train': 1.9623057842254639} 08/30/2021 16:52:07 - INFO - __main__ - Step 20327: {'lr': 0.00048132166663897703, 'samples': 3902784, 'steps': 20326, 'loss/train': 1.7337126731872559} 08/30/2021 16:52:07 - INFO - __main__ - Step 20328: {'lr': 0.0004813196539059665, 'samples': 3902976, 'steps': 20327, 'loss/train': 1.6525582075119019} 08/30/2021 16:52:08 - INFO - __main__ - Step 20329: {'lr': 0.0004813176410687269, 'samples': 3903168, 'steps': 20328, 'loss/train': 1.8098485469818115} 08/30/2021 16:52:08 - INFO - __main__ - Step 20330: {'lr': 0.00048131562812725904, 'samples': 3903360, 'steps': 20329, 'loss/train': 1.4743527173995972} 08/30/2021 16:52:09 - INFO - __main__ - Step 20331: {'lr': 0.000481313615081564, 'samples': 3903552, 'steps': 20330, 'loss/train': 0.7975194454193115} 08/30/2021 16:52:10 - INFO - __main__ - Step 20332: {'lr': 0.00048131160193164266, 'samples': 3903744, 'steps': 20331, 'loss/train': 1.6436889171600342} 08/30/2021 16:52:10 - INFO - __main__ - Step 20333: {'lr': 0.0004813095886774958, 'samples': 3903936, 'steps': 20332, 'loss/train': 1.3344805240631104} 08/30/2021 16:52:11 - INFO - __main__ - Step 20334: {'lr': 0.00048130757531912447, 'samples': 3904128, 'steps': 20333, 'loss/train': 1.0350271463394165} 08/30/2021 16:52:11 - INFO - __main__ - Step 20335: {'lr': 0.00048130556185652947, 'samples': 3904320, 'steps': 20334, 'loss/train': 1.1588261127471924} 08/30/2021 16:52:13 - INFO - __main__ - Step 20336: {'lr': 0.0004813035482897118, 'samples': 3904512, 'steps': 20335, 'loss/train': 0.1003037616610527} 08/30/2021 16:52:13 - INFO - __main__ - Step 20337: {'lr': 0.00048130153461867225, 'samples': 3904704, 'steps': 20336, 'loss/train': 1.3650394678115845} 08/30/2021 16:52:13 - INFO - __main__ - Step 20338: {'lr': 0.0004812995208434119, 'samples': 3904896, 'steps': 20337, 'loss/train': 1.2996113300323486} 08/30/2021 16:52:14 - INFO - __main__ - Step 20339: {'lr': 0.00048129750696393144, 'samples': 3905088, 'steps': 20338, 'loss/train': 0.38042551279067993} 08/30/2021 16:52:14 - INFO - __main__ - Step 20340: {'lr': 0.00048129549298023196, 'samples': 3905280, 'steps': 20339, 'loss/train': 2.639559745788574} 08/30/2021 16:52:16 - INFO - __main__ - Step 20341: {'lr': 0.0004812934788923143, 'samples': 3905472, 'steps': 20340, 'loss/train': 2.066987991333008} 08/30/2021 16:52:16 - INFO - __main__ - Step 20342: {'lr': 0.00048129146470017933, 'samples': 3905664, 'steps': 20341, 'loss/train': 1.4800901412963867} 08/30/2021 16:52:16 - INFO - __main__ - Step 20343: {'lr': 0.000481289450403828, 'samples': 3905856, 'steps': 20342, 'loss/train': 1.8806313276290894} 08/30/2021 16:52:17 - INFO - __main__ - Step 20344: {'lr': 0.0004812874360032613, 'samples': 3906048, 'steps': 20343, 'loss/train': 0.0669122040271759} 08/30/2021 16:52:17 - INFO - __main__ - Step 20345: {'lr': 0.0004812854214984799, 'samples': 3906240, 'steps': 20344, 'loss/train': 1.2670842409133911} 08/30/2021 16:52:19 - INFO - __main__ - Step 20346: {'lr': 0.000481283406889485, 'samples': 3906432, 'steps': 20345, 'loss/train': 1.4036363363265991} 08/30/2021 16:52:19 - INFO - __main__ - Step 20347: {'lr': 0.00048128139217627725, 'samples': 3906624, 'steps': 20346, 'loss/train': 1.4741283655166626} 08/30/2021 16:52:20 - INFO - __main__ - Step 20348: {'lr': 0.00048127937735885774, 'samples': 3906816, 'steps': 20347, 'loss/train': 1.190222978591919} 08/30/2021 16:52:20 - INFO - __main__ - Step 20349: {'lr': 0.0004812773624372273, 'samples': 3907008, 'steps': 20348, 'loss/train': 1.4741625785827637} 08/30/2021 16:52:20 - INFO - __main__ - Step 20350: {'lr': 0.0004812753474113869, 'samples': 3907200, 'steps': 20349, 'loss/train': 0.13493667542934418} 08/30/2021 16:52:21 - INFO - __main__ - Step 20351: {'lr': 0.0004812733322813373, 'samples': 3907392, 'steps': 20350, 'loss/train': 1.3247870206832886} 08/30/2021 16:52:22 - INFO - __main__ - Step 20352: {'lr': 0.00048127131704707953, 'samples': 3907584, 'steps': 20351, 'loss/train': 1.2110882997512817} 08/30/2021 16:52:23 - INFO - __main__ - Step 20353: {'lr': 0.0004812693017086145, 'samples': 3907776, 'steps': 20352, 'loss/train': 1.2169265747070312} 08/30/2021 16:52:23 - INFO - __main__ - Step 20354: {'lr': 0.00048126728626594315, 'samples': 3907968, 'steps': 20353, 'loss/train': 1.8783468008041382} 08/30/2021 16:52:24 - INFO - __main__ - Step 20355: {'lr': 0.00048126527071906623, 'samples': 3908160, 'steps': 20354, 'loss/train': 1.3172804117202759} 08/30/2021 16:52:24 - INFO - __main__ - Step 20356: {'lr': 0.0004812632550679848, 'samples': 3908352, 'steps': 20355, 'loss/train': 1.304091215133667} 08/30/2021 16:52:25 - INFO - __main__ - Step 20357: {'lr': 0.00048126123931269973, 'samples': 3908544, 'steps': 20356, 'loss/train': 2.1128251552581787} 08/30/2021 16:52:26 - INFO - __main__ - Step 20358: {'lr': 0.0004812592234532118, 'samples': 3908736, 'steps': 20357, 'loss/train': 1.362840175628662} 08/30/2021 16:52:26 - INFO - __main__ - Step 20359: {'lr': 0.00048125720748952216, 'samples': 3908928, 'steps': 20358, 'loss/train': 1.3950108289718628} 08/30/2021 16:52:27 - INFO - __main__ - Step 20360: {'lr': 0.00048125519142163157, 'samples': 3909120, 'steps': 20359, 'loss/train': 1.794309139251709} 08/30/2021 16:52:27 - INFO - __main__ - Step 20361: {'lr': 0.0004812531752495409, 'samples': 3909312, 'steps': 20360, 'loss/train': 1.2508519887924194} 08/30/2021 16:52:28 - INFO - __main__ - Step 20362: {'lr': 0.00048125115897325115, 'samples': 3909504, 'steps': 20361, 'loss/train': 1.7729012966156006} 08/30/2021 16:52:29 - INFO - __main__ - Step 20363: {'lr': 0.0004812491425927632, 'samples': 3909696, 'steps': 20362, 'loss/train': 1.9157298803329468} 08/30/2021 16:52:29 - INFO - __main__ - Step 20364: {'lr': 0.000481247126108078, 'samples': 3909888, 'steps': 20363, 'loss/train': 0.7351324558258057} 08/30/2021 16:52:29 - INFO - __main__ - Step 20365: {'lr': 0.00048124510951919633, 'samples': 3910080, 'steps': 20364, 'loss/train': 1.759158968925476} 08/30/2021 16:52:30 - INFO - __main__ - Step 20366: {'lr': 0.0004812430928261192, 'samples': 3910272, 'steps': 20365, 'loss/train': 1.376376748085022} 08/30/2021 16:52:30 - INFO - __main__ - Step 20367: {'lr': 0.00048124107602884753, 'samples': 3910464, 'steps': 20366, 'loss/train': 0.8080965876579285} 08/30/2021 16:52:32 - INFO - __main__ - Step 20368: {'lr': 0.0004812390591273822, 'samples': 3910656, 'steps': 20367, 'loss/train': 2.2293286323547363} 08/30/2021 16:52:32 - INFO - __main__ - Step 20369: {'lr': 0.00048123704212172416, 'samples': 3910848, 'steps': 20368, 'loss/train': 1.5028109550476074} 08/30/2021 16:52:32 - INFO - __main__ - Step 20370: {'lr': 0.0004812350250118742, 'samples': 3911040, 'steps': 20369, 'loss/train': 1.318708896636963} 08/30/2021 16:52:33 - INFO - __main__ - Step 20371: {'lr': 0.0004812330077978333, 'samples': 3911232, 'steps': 20370, 'loss/train': 1.5189670324325562} 08/30/2021 16:52:33 - INFO - __main__ - Step 20372: {'lr': 0.0004812309904796024, 'samples': 3911424, 'steps': 20371, 'loss/train': 2.112004518508911} 08/30/2021 16:52:35 - INFO - __main__ - Step 20373: {'lr': 0.0004812289730571824, 'samples': 3911616, 'steps': 20372, 'loss/train': 1.28286612033844} 08/30/2021 16:52:35 - INFO - __main__ - Step 20374: {'lr': 0.00048122695553057417, 'samples': 3911808, 'steps': 20373, 'loss/train': 0.4064999222755432} 08/30/2021 16:52:35 - INFO - __main__ - Step 20375: {'lr': 0.00048122493789977866, 'samples': 3912000, 'steps': 20374, 'loss/train': 0.8093968033790588} 08/30/2021 16:52:36 - INFO - __main__ - Step 20376: {'lr': 0.00048122292016479674, 'samples': 3912192, 'steps': 20375, 'loss/train': 1.5330499410629272} 08/30/2021 16:52:36 - INFO - __main__ - Step 20377: {'lr': 0.0004812209023256294, 'samples': 3912384, 'steps': 20376, 'loss/train': 1.7736256122589111} 08/30/2021 16:52:38 - INFO - __main__ - Step 20378: {'lr': 0.0004812188843822775, 'samples': 3912576, 'steps': 20377, 'loss/train': 1.1705150604248047} 08/30/2021 16:52:38 - INFO - __main__ - Step 20379: {'lr': 0.0004812168663347418, 'samples': 3912768, 'steps': 20378, 'loss/train': 1.4795498847961426} 08/30/2021 16:52:38 - INFO - __main__ - Step 20380: {'lr': 0.00048121484818302343, 'samples': 3912960, 'steps': 20379, 'loss/train': 1.5681957006454468} 08/30/2021 16:52:39 - INFO - __main__ - Step 20381: {'lr': 0.00048121282992712324, 'samples': 3913152, 'steps': 20380, 'loss/train': 1.891641616821289} 08/30/2021 16:52:39 - INFO - __main__ - Step 20382: {'lr': 0.00048121081156704207, 'samples': 3913344, 'steps': 20381, 'loss/train': 1.8444931507110596} 08/30/2021 16:52:39 - INFO - __main__ - Step 20383: {'lr': 0.00048120879310278094, 'samples': 3913536, 'steps': 20382, 'loss/train': 1.2242088317871094} 08/30/2021 16:52:41 - INFO - __main__ - Step 20384: {'lr': 0.00048120677453434066, 'samples': 3913728, 'steps': 20383, 'loss/train': 1.4907710552215576} 08/30/2021 16:52:42 - INFO - __main__ - Step 20385: {'lr': 0.00048120475586172217, 'samples': 3913920, 'steps': 20384, 'loss/train': 2.6739895343780518} 08/30/2021 16:52:42 - INFO - __main__ - Step 20386: {'lr': 0.00048120273708492637, 'samples': 3914112, 'steps': 20385, 'loss/train': 1.0332735776901245} 08/30/2021 16:52:43 - INFO - __main__ - Step 20387: {'lr': 0.0004812007182039542, 'samples': 3914304, 'steps': 20386, 'loss/train': 1.4726247787475586} 08/30/2021 16:52:43 - INFO - __main__ - Step 20388: {'lr': 0.00048119869921880656, 'samples': 3914496, 'steps': 20387, 'loss/train': 2.6740262508392334} 08/30/2021 16:52:44 - INFO - __main__ - Step 20389: {'lr': 0.00048119668012948434, 'samples': 3914688, 'steps': 20388, 'loss/train': 1.3015917539596558} 08/30/2021 16:52:45 - INFO - __main__ - Step 20390: {'lr': 0.0004811946609359885, 'samples': 3914880, 'steps': 20389, 'loss/train': 1.6949397325515747} 08/30/2021 16:52:45 - INFO - __main__ - Step 20391: {'lr': 0.00048119264163831987, 'samples': 3915072, 'steps': 20390, 'loss/train': 1.654359221458435} 08/30/2021 16:52:46 - INFO - __main__ - Step 20392: {'lr': 0.0004811906222364794, 'samples': 3915264, 'steps': 20391, 'loss/train': 2.69132924079895} 08/30/2021 16:52:46 - INFO - __main__ - Step 20393: {'lr': 0.00048118860273046804, 'samples': 3915456, 'steps': 20392, 'loss/train': 1.7485592365264893} 08/30/2021 16:52:47 - INFO - __main__ - Step 20394: {'lr': 0.00048118658312028663, 'samples': 3915648, 'steps': 20393, 'loss/train': 1.83722984790802} 08/30/2021 16:52:48 - INFO - __main__ - Step 20395: {'lr': 0.0004811845634059361, 'samples': 3915840, 'steps': 20394, 'loss/train': 1.4899861812591553} 08/30/2021 16:52:48 - INFO - __main__ - Step 20396: {'lr': 0.0004811825435874174, 'samples': 3916032, 'steps': 20395, 'loss/train': 1.6030021905899048} 08/30/2021 16:52:49 - INFO - __main__ - Step 20397: {'lr': 0.0004811805236647314, 'samples': 3916224, 'steps': 20396, 'loss/train': 1.620742917060852} 08/30/2021 16:52:49 - INFO - __main__ - Step 20398: {'lr': 0.0004811785036378791, 'samples': 3916416, 'steps': 20397, 'loss/train': 1.9796329736709595} 08/30/2021 16:52:50 - INFO - __main__ - Step 20399: {'lr': 0.0004811764835068613, 'samples': 3916608, 'steps': 20398, 'loss/train': 1.9112696647644043} 08/30/2021 16:52:51 - INFO - __main__ - Step 20400: {'lr': 0.0004811744632716789, 'samples': 3916800, 'steps': 20399, 'loss/train': 2.097015142440796} 08/30/2021 16:52:51 - INFO - __main__ - Step 20401: {'lr': 0.0004811724429323329, 'samples': 3916992, 'steps': 20400, 'loss/train': 1.3521363735198975} 08/30/2021 16:52:52 - INFO - __main__ - Step 20402: {'lr': 0.0004811704224888241, 'samples': 3917184, 'steps': 20401, 'loss/train': 0.9783707857131958} 08/30/2021 16:52:52 - INFO - __main__ - Step 20403: {'lr': 0.0004811684019411535, 'samples': 3917376, 'steps': 20402, 'loss/train': 1.3182331323623657} 08/30/2021 16:52:54 - INFO - __main__ - Step 20404: {'lr': 0.000481166381289322, 'samples': 3917568, 'steps': 20403, 'loss/train': 1.7120299339294434} 08/30/2021 16:52:54 - INFO - __main__ - Step 20405: {'lr': 0.0004811643605333305, 'samples': 3917760, 'steps': 20404, 'loss/train': 1.4472341537475586} 08/30/2021 16:52:55 - INFO - __main__ - Step 20406: {'lr': 0.0004811623396731799, 'samples': 3917952, 'steps': 20405, 'loss/train': 1.9274582862854004} 08/30/2021 16:52:55 - INFO - __main__ - Step 20407: {'lr': 0.0004811603187088711, 'samples': 3918144, 'steps': 20406, 'loss/train': 2.011478900909424} 08/30/2021 16:52:55 - INFO - __main__ - Step 20408: {'lr': 0.00048115829764040503, 'samples': 3918336, 'steps': 20407, 'loss/train': 1.7389706373214722} 08/30/2021 16:52:56 - INFO - __main__ - Step 20409: {'lr': 0.0004811562764677826, 'samples': 3918528, 'steps': 20408, 'loss/train': 1.454147219657898} 08/30/2021 16:52:57 - INFO - __main__ - Step 20410: {'lr': 0.00048115425519100474, 'samples': 3918720, 'steps': 20409, 'loss/train': 0.04675471782684326} 08/30/2021 16:52:58 - INFO - __main__ - Step 20411: {'lr': 0.0004811522338100723, 'samples': 3918912, 'steps': 20410, 'loss/train': 1.6382688283920288} 08/30/2021 16:52:58 - INFO - __main__ - Step 20412: {'lr': 0.0004811502123249862, 'samples': 3919104, 'steps': 20411, 'loss/train': 0.9834139347076416} 08/30/2021 16:52:58 - INFO - __main__ - Step 20413: {'lr': 0.0004811481907357475, 'samples': 3919296, 'steps': 20412, 'loss/train': 1.166786789894104} 08/30/2021 16:52:59 - INFO - __main__ - Step 20414: {'lr': 0.000481146169042357, 'samples': 3919488, 'steps': 20413, 'loss/train': 1.9236106872558594} 08/30/2021 16:53:00 - INFO - __main__ - Step 20415: {'lr': 0.0004811441472448155, 'samples': 3919680, 'steps': 20414, 'loss/train': 1.2484660148620605} 08/30/2021 16:53:01 - INFO - __main__ - Step 20416: {'lr': 0.000481142125343124, 'samples': 3919872, 'steps': 20415, 'loss/train': 0.8506363034248352} 08/30/2021 16:53:01 - INFO - __main__ - Step 20417: {'lr': 0.0004811401033372835, 'samples': 3920064, 'steps': 20416, 'loss/train': 1.2502920627593994} 08/30/2021 16:53:01 - INFO - __main__ - Step 20418: {'lr': 0.0004811380812272948, 'samples': 3920256, 'steps': 20417, 'loss/train': 1.8344799280166626} 08/30/2021 16:53:02 - INFO - __main__ - Step 20419: {'lr': 0.0004811360590131589, 'samples': 3920448, 'steps': 20418, 'loss/train': 1.6395113468170166} 08/30/2021 16:53:02 - INFO - __main__ - Step 20420: {'lr': 0.00048113403669487655, 'samples': 3920640, 'steps': 20419, 'loss/train': 1.2615171670913696} 08/30/2021 16:53:04 - INFO - __main__ - Step 20421: {'lr': 0.0004811320142724489, 'samples': 3920832, 'steps': 20420, 'loss/train': 1.563582181930542} 08/30/2021 16:53:04 - INFO - __main__ - Step 20422: {'lr': 0.0004811299917458766, 'samples': 3921024, 'steps': 20421, 'loss/train': 1.7724220752716064} 08/30/2021 16:53:04 - INFO - __main__ - Step 20423: {'lr': 0.00048112796911516076, 'samples': 3921216, 'steps': 20422, 'loss/train': 1.7514982223510742} 08/30/2021 16:53:05 - INFO - __main__ - Step 20424: {'lr': 0.00048112594638030225, 'samples': 3921408, 'steps': 20423, 'loss/train': 1.2668033838272095} 08/30/2021 16:53:05 - INFO - __main__ - Step 20425: {'lr': 0.00048112392354130194, 'samples': 3921600, 'steps': 20424, 'loss/train': 1.2459012269973755} 08/30/2021 16:53:07 - INFO - __main__ - Step 20426: {'lr': 0.00048112190059816076, 'samples': 3921792, 'steps': 20425, 'loss/train': 1.2621666193008423} 08/30/2021 16:53:07 - INFO - __main__ - Step 20427: {'lr': 0.0004811198775508796, 'samples': 3921984, 'steps': 20426, 'loss/train': 1.5181001424789429} 08/30/2021 16:53:07 - INFO - __main__ - Step 20428: {'lr': 0.0004811178543994593, 'samples': 3922176, 'steps': 20427, 'loss/train': 1.673447847366333} 08/30/2021 16:53:08 - INFO - __main__ - Step 20429: {'lr': 0.000481115831143901, 'samples': 3922368, 'steps': 20428, 'loss/train': 1.9533108472824097} 08/30/2021 16:53:08 - INFO - __main__ - Step 20430: {'lr': 0.00048111380778420544, 'samples': 3922560, 'steps': 20429, 'loss/train': 1.0703402757644653} 08/30/2021 16:53:10 - INFO - __main__ - Step 20431: {'lr': 0.0004811117843203735, 'samples': 3922752, 'steps': 20430, 'loss/train': 1.6772987842559814} 08/30/2021 16:53:10 - INFO - __main__ - Step 20432: {'lr': 0.00048110976075240624, 'samples': 3922944, 'steps': 20431, 'loss/train': 1.4068084955215454} 08/30/2021 16:53:11 - INFO - __main__ - Step 20433: {'lr': 0.00048110773708030444, 'samples': 3923136, 'steps': 20432, 'loss/train': 0.09284914284944534} 08/30/2021 16:53:11 - INFO - __main__ - Step 20434: {'lr': 0.00048110571330406903, 'samples': 3923328, 'steps': 20433, 'loss/train': 2.2277603149414062} 08/30/2021 16:53:11 - INFO - __main__ - Step 20435: {'lr': 0.0004811036894237011, 'samples': 3923520, 'steps': 20434, 'loss/train': 1.6527063846588135} 08/30/2021 16:53:13 - INFO - __main__ - Step 20436: {'lr': 0.00048110166543920125, 'samples': 3923712, 'steps': 20435, 'loss/train': 0.29340869188308716} 08/30/2021 16:53:14 - INFO - __main__ - Step 20437: {'lr': 0.0004810996413505706, 'samples': 3923904, 'steps': 20436, 'loss/train': 1.0672272443771362} 08/30/2021 16:53:14 - INFO - __main__ - Step 20438: {'lr': 0.0004810976171578101, 'samples': 3924096, 'steps': 20437, 'loss/train': 1.6259253025054932} 08/30/2021 16:53:15 - INFO - __main__ - Step 20439: {'lr': 0.00048109559286092047, 'samples': 3924288, 'steps': 20438, 'loss/train': 1.3832546472549438} 08/30/2021 16:53:15 - INFO - __main__ - Step 20440: {'lr': 0.0004810935684599028, 'samples': 3924480, 'steps': 20439, 'loss/train': 0.8807126879692078} 08/30/2021 16:53:16 - INFO - __main__ - Step 20441: {'lr': 0.00048109154395475787, 'samples': 3924672, 'steps': 20440, 'loss/train': 1.526767373085022} 08/30/2021 16:53:17 - INFO - __main__ - Step 20442: {'lr': 0.00048108951934548673, 'samples': 3924864, 'steps': 20441, 'loss/train': 1.0425728559494019} 08/30/2021 16:53:17 - INFO - __main__ - Step 20443: {'lr': 0.0004810874946320901, 'samples': 3925056, 'steps': 20442, 'loss/train': 1.772262692451477} 08/30/2021 16:53:18 - INFO - __main__ - Step 20444: {'lr': 0.00048108546981456916, 'samples': 3925248, 'steps': 20443, 'loss/train': 1.2528482675552368} 08/30/2021 16:53:18 - INFO - __main__ - Step 20445: {'lr': 0.0004810834448929246, 'samples': 3925440, 'steps': 20444, 'loss/train': 2.1821045875549316} 08/30/2021 16:53:18 - INFO - __main__ - Step 20446: {'lr': 0.0004810814198671574, 'samples': 3925632, 'steps': 20445, 'loss/train': 1.8502366542816162} 08/30/2021 16:53:20 - INFO - __main__ - Step 20447: {'lr': 0.00048107939473726846, 'samples': 3925824, 'steps': 20446, 'loss/train': 1.2826957702636719} 08/30/2021 16:53:20 - INFO - __main__ - Step 20448: {'lr': 0.0004810773695032588, 'samples': 3926016, 'steps': 20447, 'loss/train': 2.0178780555725098} 08/30/2021 16:53:21 - INFO - __main__ - Step 20449: {'lr': 0.00048107534416512915, 'samples': 3926208, 'steps': 20448, 'loss/train': 0.7107794880867004} 08/30/2021 16:53:21 - INFO - __main__ - Step 20450: {'lr': 0.00048107331872288055, 'samples': 3926400, 'steps': 20449, 'loss/train': 1.8956117630004883} 08/30/2021 16:53:21 - INFO - __main__ - Step 20451: {'lr': 0.0004810712931765139, 'samples': 3926592, 'steps': 20450, 'loss/train': 1.7767422199249268} 08/30/2021 16:53:23 - INFO - __main__ - Step 20452: {'lr': 0.00048106926752603007, 'samples': 3926784, 'steps': 20451, 'loss/train': 1.5847138166427612} 08/30/2021 16:53:23 - INFO - __main__ - Step 20453: {'lr': 0.00048106724177143, 'samples': 3926976, 'steps': 20452, 'loss/train': 1.5756040811538696} 08/30/2021 16:53:24 - INFO - __main__ - Step 20454: {'lr': 0.00048106521591271455, 'samples': 3927168, 'steps': 20453, 'loss/train': 1.307875633239746} 08/30/2021 16:53:24 - INFO - __main__ - Step 20455: {'lr': 0.00048106318994988476, 'samples': 3927360, 'steps': 20454, 'loss/train': 1.1496918201446533} 08/30/2021 16:53:24 - INFO - __main__ - Step 20456: {'lr': 0.0004810611638829414, 'samples': 3927552, 'steps': 20455, 'loss/train': 1.597902536392212} 08/30/2021 16:53:26 - INFO - __main__ - Step 20457: {'lr': 0.00048105913771188545, 'samples': 3927744, 'steps': 20456, 'loss/train': 1.5206817388534546} 08/30/2021 16:53:26 - INFO - __main__ - Step 20458: {'lr': 0.00048105711143671783, 'samples': 3927936, 'steps': 20457, 'loss/train': 1.676174283027649} 08/30/2021 16:53:27 - INFO - __main__ - Step 20459: {'lr': 0.0004810550850574394, 'samples': 3928128, 'steps': 20458, 'loss/train': 0.932281494140625} 08/30/2021 16:53:27 - INFO - __main__ - Step 20460: {'lr': 0.0004810530585740512, 'samples': 3928320, 'steps': 20459, 'loss/train': 1.3992466926574707} 08/30/2021 16:53:27 - INFO - __main__ - Step 20461: {'lr': 0.00048105103198655406, 'samples': 3928512, 'steps': 20460, 'loss/train': 1.2533982992172241} 08/30/2021 16:53:29 - INFO - __main__ - Step 20462: {'lr': 0.0004810490052949488, 'samples': 3928704, 'steps': 20461, 'loss/train': 1.4120899438858032} 08/30/2021 16:53:29 - INFO - __main__ - Step 20463: {'lr': 0.0004810469784992365, 'samples': 3928896, 'steps': 20462, 'loss/train': 1.0651419162750244} 08/30/2021 16:53:30 - INFO - __main__ - Step 20464: {'lr': 0.00048104495159941794, 'samples': 3929088, 'steps': 20463, 'loss/train': 1.827168583869934} 08/30/2021 16:53:30 - INFO - __main__ - Step 20465: {'lr': 0.00048104292459549413, 'samples': 3929280, 'steps': 20464, 'loss/train': 1.2470966577529907} 08/30/2021 16:53:30 - INFO - __main__ - Step 20466: {'lr': 0.0004810408974874659, 'samples': 3929472, 'steps': 20465, 'loss/train': 1.5338815450668335} 08/30/2021 16:53:32 - INFO - __main__ - Step 20467: {'lr': 0.0004810388702753342, 'samples': 3929664, 'steps': 20466, 'loss/train': 1.6177653074264526} 08/30/2021 16:53:32 - INFO - __main__ - Step 20468: {'lr': 0.0004810368429591, 'samples': 3929856, 'steps': 20467, 'loss/train': 1.5753872394561768} 08/30/2021 16:53:33 - INFO - __main__ - Step 20469: {'lr': 0.00048103481553876415, 'samples': 3930048, 'steps': 20468, 'loss/train': 1.6142983436584473} 08/30/2021 16:53:33 - INFO - __main__ - Step 20470: {'lr': 0.0004810327880143276, 'samples': 3930240, 'steps': 20469, 'loss/train': 1.7200350761413574} 08/30/2021 16:53:33 - INFO - __main__ - Step 20471: {'lr': 0.00048103076038579125, 'samples': 3930432, 'steps': 20470, 'loss/train': 1.4600830078125} 08/30/2021 16:53:35 - INFO - __main__ - Step 20472: {'lr': 0.00048102873265315596, 'samples': 3930624, 'steps': 20471, 'loss/train': 1.7758893966674805} 08/30/2021 16:53:36 - INFO - __main__ - Step 20473: {'lr': 0.0004810267048164227, 'samples': 3930816, 'steps': 20472, 'loss/train': 1.8201944828033447} 08/30/2021 16:53:36 - INFO - __main__ - Step 20474: {'lr': 0.0004810246768755924, 'samples': 3931008, 'steps': 20473, 'loss/train': 1.5521976947784424} 08/30/2021 16:53:37 - INFO - __main__ - Step 20475: {'lr': 0.0004810226488306659, 'samples': 3931200, 'steps': 20474, 'loss/train': 1.2664735317230225} 08/30/2021 16:53:37 - INFO - __main__ - Step 20476: {'lr': 0.00048102062068164413, 'samples': 3931392, 'steps': 20475, 'loss/train': 1.3742451667785645} 08/30/2021 16:53:38 - INFO - __main__ - Step 20477: {'lr': 0.0004810185924285281, 'samples': 3931584, 'steps': 20476, 'loss/train': 0.20455193519592285} 08/30/2021 16:53:39 - INFO - __main__ - Step 20478: {'lr': 0.00048101656407131864, 'samples': 3931776, 'steps': 20477, 'loss/train': 1.7805805206298828} 08/30/2021 16:53:39 - INFO - __main__ - Step 20479: {'lr': 0.00048101453561001667, 'samples': 3931968, 'steps': 20478, 'loss/train': 1.5799874067306519} 08/30/2021 16:53:40 - INFO - __main__ - Step 20480: {'lr': 0.00048101250704462315, 'samples': 3932160, 'steps': 20479, 'loss/train': 1.4885618686676025} 08/30/2021 16:53:40 - INFO - __main__ - Step 20481: {'lr': 0.0004810104783751389, 'samples': 3932352, 'steps': 20480, 'loss/train': 1.9872725009918213} 08/30/2021 16:53:40 - INFO - __main__ - Step 20482: {'lr': 0.00048100844960156496, 'samples': 3932544, 'steps': 20481, 'loss/train': 0.8941634893417358} 08/30/2021 16:53:42 - INFO - __main__ - Step 20483: {'lr': 0.0004810064207239021, 'samples': 3932736, 'steps': 20482, 'loss/train': 1.4970029592514038} 08/30/2021 16:53:42 - INFO - __main__ - Step 20484: {'lr': 0.0004810043917421514, 'samples': 3932928, 'steps': 20483, 'loss/train': 1.6084808111190796} 08/30/2021 16:53:43 - INFO - __main__ - Step 20485: {'lr': 0.0004810023626563136, 'samples': 3933120, 'steps': 20484, 'loss/train': 1.541935682296753} 08/30/2021 16:53:43 - INFO - __main__ - Step 20486: {'lr': 0.0004810003334663898, 'samples': 3933312, 'steps': 20485, 'loss/train': 1.511197566986084} 08/30/2021 16:53:43 - INFO - __main__ - Step 20487: {'lr': 0.0004809983041723807, 'samples': 3933504, 'steps': 20486, 'loss/train': 1.2819828987121582} 08/30/2021 16:53:46 - INFO - __main__ - Step 20488: {'lr': 0.00048099627477428744, 'samples': 3933696, 'steps': 20487, 'loss/train': 1.2189552783966064} 08/30/2021 16:53:47 - INFO - __main__ - Step 20489: {'lr': 0.0004809942452721107, 'samples': 3933888, 'steps': 20488, 'loss/train': 1.914501667022705} 08/30/2021 16:53:47 - INFO - __main__ - Step 20490: {'lr': 0.0004809922156658516, 'samples': 3934080, 'steps': 20489, 'loss/train': 1.2167168855667114} 08/30/2021 16:53:48 - INFO - __main__ - Step 20491: {'lr': 0.00048099018595551096, 'samples': 3934272, 'steps': 20490, 'loss/train': 1.6059019565582275} 08/30/2021 16:53:48 - INFO - __main__ - Step 20492: {'lr': 0.0004809881561410897, 'samples': 3934464, 'steps': 20491, 'loss/train': 1.2520502805709839} 08/30/2021 16:53:48 - INFO - __main__ - Step 20493: {'lr': 0.00048098612622258873, 'samples': 3934656, 'steps': 20492, 'loss/train': 5.677497863769531} 08/30/2021 16:53:49 - INFO - __main__ - Step 20494: {'lr': 0.00048098409620000906, 'samples': 3934848, 'steps': 20493, 'loss/train': 5.572636127471924} 08/30/2021 16:53:50 - INFO - __main__ - Step 20495: {'lr': 0.00048098206607335135, 'samples': 3935040, 'steps': 20494, 'loss/train': 5.476930141448975} 08/30/2021 16:53:51 - INFO - __main__ - Step 20496: {'lr': 0.00048098003584261684, 'samples': 3935232, 'steps': 20495, 'loss/train': 1.538805365562439} 08/30/2021 16:53:51 - INFO - __main__ - Step 20497: {'lr': 0.00048097800550780625, 'samples': 3935424, 'steps': 20496, 'loss/train': 0.8303343057632446} 08/30/2021 16:53:52 - INFO - __main__ - Step 20498: {'lr': 0.0004809759750689205, 'samples': 3935616, 'steps': 20497, 'loss/train': 1.6164000034332275} 08/30/2021 16:53:52 - INFO - __main__ - Step 20499: {'lr': 0.00048097394452596053, 'samples': 3935808, 'steps': 20498, 'loss/train': 1.4405229091644287} 08/30/2021 16:53:52 - INFO - __main__ - Step 20500: {'lr': 0.0004809719138789273, 'samples': 3936000, 'steps': 20499, 'loss/train': 1.1235699653625488} 08/30/2021 16:53:54 - INFO - __main__ - Step 20501: {'lr': 0.0004809698831278217, 'samples': 3936192, 'steps': 20500, 'loss/train': 1.742831826210022} 08/30/2021 16:53:54 - INFO - __main__ - Step 20502: {'lr': 0.0004809678522726446, 'samples': 3936384, 'steps': 20501, 'loss/train': 1.0082358121871948} 08/30/2021 16:53:55 - INFO - __main__ - Step 20503: {'lr': 0.000480965821313397, 'samples': 3936576, 'steps': 20502, 'loss/train': 1.5180387496948242} 08/30/2021 16:53:55 - INFO - __main__ - Step 20504: {'lr': 0.0004809637902500797, 'samples': 3936768, 'steps': 20503, 'loss/train': 1.0592870712280273} 08/30/2021 16:53:55 - INFO - __main__ - Step 20505: {'lr': 0.00048096175908269375, 'samples': 3936960, 'steps': 20504, 'loss/train': 1.5597378015518188} 08/30/2021 16:53:57 - INFO - __main__ - Step 20506: {'lr': 0.00048095972781124, 'samples': 3937152, 'steps': 20505, 'loss/train': 1.4473786354064941} 08/30/2021 16:53:58 - INFO - __main__ - Step 20507: {'lr': 0.00048095769643571927, 'samples': 3937344, 'steps': 20506, 'loss/train': 1.6616387367248535} 08/30/2021 16:53:58 - INFO - __main__ - Step 20508: {'lr': 0.0004809556649561326, 'samples': 3937536, 'steps': 20507, 'loss/train': 1.440677285194397} 08/30/2021 16:53:58 - INFO - __main__ - Step 20509: {'lr': 0.0004809536333724809, 'samples': 3937728, 'steps': 20508, 'loss/train': 1.7490971088409424} 08/30/2021 16:53:59 - INFO - __main__ - Step 20510: {'lr': 0.000480951601684765, 'samples': 3937920, 'steps': 20509, 'loss/train': 0.3238224983215332} 08/30/2021 16:54:00 - INFO - __main__ - Step 20511: {'lr': 0.00048094956989298593, 'samples': 3938112, 'steps': 20510, 'loss/train': 0.40685346722602844} 08/30/2021 16:54:00 - INFO - __main__ - Step 20512: {'lr': 0.0004809475379971445, 'samples': 3938304, 'steps': 20511, 'loss/train': 1.6993385553359985} 08/30/2021 16:54:01 - INFO - __main__ - Step 20513: {'lr': 0.00048094550599724176, 'samples': 3938496, 'steps': 20512, 'loss/train': 0.4886229634284973} 08/30/2021 16:54:01 - INFO - __main__ - Step 20514: {'lr': 0.0004809434738932785, 'samples': 3938688, 'steps': 20513, 'loss/train': 2.4234566688537598} 08/30/2021 16:54:01 - INFO - __main__ - Step 20515: {'lr': 0.0004809414416852557, 'samples': 3938880, 'steps': 20514, 'loss/train': 1.7882490158081055} 08/30/2021 16:54:03 - INFO - __main__ - Step 20516: {'lr': 0.00048093940937317414, 'samples': 3939072, 'steps': 20515, 'loss/train': 1.388883352279663} 08/30/2021 16:54:03 - INFO - __main__ - Step 20517: {'lr': 0.00048093737695703494, 'samples': 3939264, 'steps': 20516, 'loss/train': 1.4843791723251343} 08/30/2021 16:54:04 - INFO - __main__ - Step 20518: {'lr': 0.0004809353444368389, 'samples': 3939456, 'steps': 20517, 'loss/train': 1.5473222732543945} 08/30/2021 16:54:04 - INFO - __main__ - Step 20519: {'lr': 0.00048093331181258694, 'samples': 3939648, 'steps': 20518, 'loss/train': 1.5043143033981323} 08/30/2021 16:54:04 - INFO - __main__ - Step 20520: {'lr': 0.00048093127908428, 'samples': 3939840, 'steps': 20519, 'loss/train': 0.6837820410728455} 08/30/2021 16:54:06 - INFO - __main__ - Step 20521: {'lr': 0.00048092924625191903, 'samples': 3940032, 'steps': 20520, 'loss/train': 1.4310814142227173} 08/30/2021 16:54:06 - INFO - __main__ - Step 20522: {'lr': 0.0004809272133155048, 'samples': 3940224, 'steps': 20521, 'loss/train': 1.9825042486190796} 08/30/2021 16:54:07 - INFO - __main__ - Step 20523: {'lr': 0.00048092518027503844, 'samples': 3940416, 'steps': 20522, 'loss/train': 1.2254289388656616} 08/30/2021 16:54:07 - INFO - __main__ - Step 20524: {'lr': 0.0004809231471305208, 'samples': 3940608, 'steps': 20523, 'loss/train': 1.680452585220337} 08/30/2021 16:54:07 - INFO - __main__ - Step 20525: {'lr': 0.0004809211138819526, 'samples': 3940800, 'steps': 20524, 'loss/train': 1.5076162815093994} 08/30/2021 16:54:09 - INFO - __main__ - Step 20526: {'lr': 0.000480919080529335, 'samples': 3940992, 'steps': 20525, 'loss/train': 0.3464648127555847} 08/30/2021 16:54:09 - INFO - __main__ - Step 20527: {'lr': 0.0004809170470726688, 'samples': 3941184, 'steps': 20526, 'loss/train': 1.5762031078338623} 08/30/2021 16:54:10 - INFO - __main__ - Step 20528: {'lr': 0.00048091501351195495, 'samples': 3941376, 'steps': 20527, 'loss/train': 1.6600455045700073} 08/30/2021 16:54:10 - INFO - __main__ - Step 20529: {'lr': 0.00048091297984719433, 'samples': 3941568, 'steps': 20528, 'loss/train': 1.404067873954773} 08/30/2021 16:54:10 - INFO - __main__ - Step 20530: {'lr': 0.0004809109460783879, 'samples': 3941760, 'steps': 20529, 'loss/train': 0.9669828414916992} 08/30/2021 16:54:11 - INFO - __main__ - Step 20531: {'lr': 0.0004809089122055366, 'samples': 3941952, 'steps': 20530, 'loss/train': 1.045242190361023} 08/30/2021 16:54:12 - INFO - __main__ - Step 20532: {'lr': 0.00048090687822864125, 'samples': 3942144, 'steps': 20531, 'loss/train': 1.9114315509796143} 08/30/2021 16:54:13 - INFO - __main__ - Step 20533: {'lr': 0.00048090484414770284, 'samples': 3942336, 'steps': 20532, 'loss/train': 1.3316726684570312} 08/30/2021 16:54:13 - INFO - __main__ - Step 20534: {'lr': 0.00048090280996272234, 'samples': 3942528, 'steps': 20533, 'loss/train': 0.9302244782447815} 08/30/2021 16:54:13 - INFO - __main__ - Step 20535: {'lr': 0.0004809007756737005, 'samples': 3942720, 'steps': 20534, 'loss/train': 1.5411350727081299} 08/30/2021 16:54:14 - INFO - __main__ - Step 20536: {'lr': 0.0004808987412806384, 'samples': 3942912, 'steps': 20535, 'loss/train': 1.745179533958435} 08/30/2021 16:54:15 - INFO - __main__ - Step 20537: {'lr': 0.0004808967067835369, 'samples': 3943104, 'steps': 20536, 'loss/train': 1.4986993074417114} 08/30/2021 16:54:16 - INFO - __main__ - Step 20538: {'lr': 0.00048089467218239687, 'samples': 3943296, 'steps': 20537, 'loss/train': 1.336204171180725} 08/30/2021 16:54:16 - INFO - __main__ - Step 20539: {'lr': 0.00048089263747721925, 'samples': 3943488, 'steps': 20538, 'loss/train': 1.4198871850967407} 08/30/2021 16:54:17 - INFO - __main__ - Step 20540: {'lr': 0.000480890602668005, 'samples': 3943680, 'steps': 20539, 'loss/train': 1.5905554294586182} 08/30/2021 16:54:17 - INFO - __main__ - Step 20541: {'lr': 0.000480888567754755, 'samples': 3943872, 'steps': 20540, 'loss/train': 0.6319172382354736} 08/30/2021 16:54:19 - INFO - __main__ - Step 20542: {'lr': 0.0004808865327374701, 'samples': 3944064, 'steps': 20541, 'loss/train': 1.8303757905960083} 08/30/2021 16:54:19 - INFO - __main__ - Step 20543: {'lr': 0.0004808844976161514, 'samples': 3944256, 'steps': 20542, 'loss/train': 1.858598232269287} 08/30/2021 16:54:19 - INFO - __main__ - Step 20544: {'lr': 0.0004808824623907997, 'samples': 3944448, 'steps': 20543, 'loss/train': 1.625712275505066} 08/30/2021 16:54:20 - INFO - __main__ - Step 20545: {'lr': 0.0004808804270614159, 'samples': 3944640, 'steps': 20544, 'loss/train': 1.5935778617858887} 08/30/2021 16:54:20 - INFO - __main__ - Step 20546: {'lr': 0.0004808783916280008, 'samples': 3944832, 'steps': 20545, 'loss/train': 1.4860432147979736} 08/30/2021 16:54:22 - INFO - __main__ - Step 20547: {'lr': 0.0004808763560905557, 'samples': 3945024, 'steps': 20546, 'loss/train': 1.3092674016952515} 08/30/2021 16:54:22 - INFO - __main__ - Step 20548: {'lr': 0.0004808743204490811, 'samples': 3945216, 'steps': 20547, 'loss/train': 1.6856248378753662} 08/30/2021 16:54:23 - INFO - __main__ - Step 20549: {'lr': 0.00048087228470357823, 'samples': 3945408, 'steps': 20548, 'loss/train': 1.1017231941223145} 08/30/2021 16:54:23 - INFO - __main__ - Step 20550: {'lr': 0.00048087024885404777, 'samples': 3945600, 'steps': 20549, 'loss/train': 1.039155125617981} 08/30/2021 16:54:24 - INFO - __main__ - Step 20551: {'lr': 0.00048086821290049077, 'samples': 3945792, 'steps': 20550, 'loss/train': 1.5275973081588745} 08/30/2021 16:54:25 - INFO - __main__ - Step 20552: {'lr': 0.00048086617684290814, 'samples': 3945984, 'steps': 20551, 'loss/train': 1.4478583335876465} 08/30/2021 16:54:25 - INFO - __main__ - Step 20553: {'lr': 0.00048086414068130077, 'samples': 3946176, 'steps': 20552, 'loss/train': 1.6303349733352661} 08/30/2021 16:54:26 - INFO - __main__ - Step 20554: {'lr': 0.00048086210441566956, 'samples': 3946368, 'steps': 20553, 'loss/train': 1.3500038385391235} 08/30/2021 16:54:26 - INFO - __main__ - Step 20555: {'lr': 0.00048086006804601544, 'samples': 3946560, 'steps': 20554, 'loss/train': 1.5991129875183105} 08/30/2021 16:54:26 - INFO - __main__ - Step 20556: {'lr': 0.00048085803157233933, 'samples': 3946752, 'steps': 20555, 'loss/train': 1.458549976348877} 08/30/2021 16:54:28 - INFO - __main__ - Step 20557: {'lr': 0.00048085599499464216, 'samples': 3946944, 'steps': 20556, 'loss/train': 1.3403385877609253} 08/30/2021 16:54:28 - INFO - __main__ - Step 20558: {'lr': 0.0004808539583129249, 'samples': 3947136, 'steps': 20557, 'loss/train': 0.9676722288131714} 08/30/2021 16:54:29 - INFO - __main__ - Step 20559: {'lr': 0.0004808519215271884, 'samples': 3947328, 'steps': 20558, 'loss/train': 1.908630609512329} 08/30/2021 16:54:29 - INFO - __main__ - Step 20560: {'lr': 0.0004808498846374335, 'samples': 3947520, 'steps': 20559, 'loss/train': 1.5557866096496582} 08/30/2021 16:54:29 - INFO - __main__ - Step 20561: {'lr': 0.0004808478476436612, 'samples': 3947712, 'steps': 20560, 'loss/train': 1.6522068977355957} 08/30/2021 16:54:30 - INFO - __main__ - Step 20562: {'lr': 0.00048084581054587253, 'samples': 3947904, 'steps': 20561, 'loss/train': 1.812275767326355} 08/30/2021 16:54:31 - INFO - __main__ - Step 20563: {'lr': 0.0004808437733440682, 'samples': 3948096, 'steps': 20562, 'loss/train': 1.1599609851837158} 08/30/2021 16:54:32 - INFO - __main__ - Step 20564: {'lr': 0.0004808417360382493, 'samples': 3948288, 'steps': 20563, 'loss/train': 1.241487979888916} 08/30/2021 16:54:32 - INFO - __main__ - Step 20565: {'lr': 0.00048083969862841667, 'samples': 3948480, 'steps': 20564, 'loss/train': 1.663413405418396} 08/30/2021 16:54:32 - INFO - __main__ - Step 20566: {'lr': 0.00048083766111457115, 'samples': 3948672, 'steps': 20565, 'loss/train': 1.9653089046478271} 08/30/2021 16:54:33 - INFO - __main__ - Step 20567: {'lr': 0.0004808356234967138, 'samples': 3948864, 'steps': 20566, 'loss/train': 1.7561421394348145} 08/30/2021 16:54:34 - INFO - __main__ - Step 20568: {'lr': 0.00048083358577484547, 'samples': 3949056, 'steps': 20567, 'loss/train': 2.359469175338745} 08/30/2021 16:54:35 - INFO - __main__ - Step 20569: {'lr': 0.0004808315479489671, 'samples': 3949248, 'steps': 20568, 'loss/train': 1.3442726135253906} 08/30/2021 16:54:35 - INFO - __main__ - Step 20570: {'lr': 0.00048082951001907965, 'samples': 3949440, 'steps': 20569, 'loss/train': 1.7343682050704956} 08/30/2021 16:54:35 - INFO - __main__ - Step 20571: {'lr': 0.0004808274719851839, 'samples': 3949632, 'steps': 20570, 'loss/train': 1.5264581441879272} 08/30/2021 16:54:36 - INFO - __main__ - Step 20572: {'lr': 0.0004808254338472809, 'samples': 3949824, 'steps': 20571, 'loss/train': 1.246448278427124} 08/30/2021 16:54:36 - INFO - __main__ - Step 20573: {'lr': 0.00048082339560537145, 'samples': 3950016, 'steps': 20572, 'loss/train': 1.5132750272750854} 08/30/2021 16:54:38 - INFO - __main__ - Step 20574: {'lr': 0.00048082135725945665, 'samples': 3950208, 'steps': 20573, 'loss/train': 1.9364030361175537} 08/30/2021 16:54:38 - INFO - __main__ - Step 20575: {'lr': 0.0004808193188095372, 'samples': 3950400, 'steps': 20574, 'loss/train': 1.4878729581832886} 08/30/2021 16:54:38 - INFO - __main__ - Step 20576: {'lr': 0.0004808172802556142, 'samples': 3950592, 'steps': 20575, 'loss/train': 1.508954644203186} 08/30/2021 16:54:39 - INFO - __main__ - Step 20577: {'lr': 0.0004808152415976885, 'samples': 3950784, 'steps': 20576, 'loss/train': 1.4431802034378052} 08/30/2021 16:54:39 - INFO - __main__ - Step 20578: {'lr': 0.000480813202835761, 'samples': 3950976, 'steps': 20577, 'loss/train': 1.0431770086288452} 08/30/2021 16:54:41 - INFO - __main__ - Step 20579: {'lr': 0.0004808111639698326, 'samples': 3951168, 'steps': 20578, 'loss/train': 1.4277130365371704} 08/30/2021 16:54:41 - INFO - __main__ - Step 20580: {'lr': 0.0004808091249999043, 'samples': 3951360, 'steps': 20579, 'loss/train': 1.4637948274612427} 08/30/2021 16:54:41 - INFO - __main__ - Step 20581: {'lr': 0.0004808070859259769, 'samples': 3951552, 'steps': 20580, 'loss/train': 2.0352847576141357} 08/30/2021 16:54:42 - INFO - __main__ - Step 20582: {'lr': 0.0004808050467480515, 'samples': 3951744, 'steps': 20581, 'loss/train': 1.7960317134857178} 08/30/2021 16:54:42 - INFO - __main__ - Step 20583: {'lr': 0.0004808030074661288, 'samples': 3951936, 'steps': 20582, 'loss/train': 1.302974820137024} 08/30/2021 16:54:44 - INFO - __main__ - Step 20584: {'lr': 0.0004808009680802099, 'samples': 3952128, 'steps': 20583, 'loss/train': 1.623962640762329} 08/30/2021 16:54:44 - INFO - __main__ - Step 20585: {'lr': 0.00048079892859029564, 'samples': 3952320, 'steps': 20584, 'loss/train': 1.8166264295578003} 08/30/2021 16:54:45 - INFO - __main__ - Step 20586: {'lr': 0.00048079688899638684, 'samples': 3952512, 'steps': 20585, 'loss/train': 2.028949022293091} 08/30/2021 16:54:45 - INFO - __main__ - Step 20587: {'lr': 0.0004807948492984846, 'samples': 3952704, 'steps': 20586, 'loss/train': 2.6005401611328125} 08/30/2021 16:54:45 - INFO - __main__ - Step 20588: {'lr': 0.0004807928094965898, 'samples': 3952896, 'steps': 20587, 'loss/train': 1.4047460556030273} 08/30/2021 16:54:47 - INFO - __main__ - Step 20589: {'lr': 0.0004807907695907032, 'samples': 3953088, 'steps': 20588, 'loss/train': 1.6047488451004028} 08/30/2021 16:54:48 - INFO - __main__ - Step 20590: {'lr': 0.000480788729580826, 'samples': 3953280, 'steps': 20589, 'loss/train': 1.1475815773010254} 08/30/2021 16:54:48 - INFO - __main__ - Step 20591: {'lr': 0.00048078668946695887, 'samples': 3953472, 'steps': 20590, 'loss/train': 1.7670137882232666} 08/30/2021 16:54:49 - INFO - __main__ - Step 20592: {'lr': 0.0004807846492491028, 'samples': 3953664, 'steps': 20591, 'loss/train': 2.0738556385040283} 08/30/2021 16:54:49 - INFO - __main__ - Step 20593: {'lr': 0.0004807826089272588, 'samples': 3953856, 'steps': 20592, 'loss/train': 0.7206501960754395} 08/30/2021 16:54:50 - INFO - __main__ - Step 20594: {'lr': 0.0004807805685014277, 'samples': 3954048, 'steps': 20593, 'loss/train': 1.4145188331604004} 08/30/2021 16:54:51 - INFO - __main__ - Step 20595: {'lr': 0.00048077852797161034, 'samples': 3954240, 'steps': 20594, 'loss/train': 1.3185465335845947} 08/30/2021 16:54:51 - INFO - __main__ - Step 20596: {'lr': 0.0004807764873378079, 'samples': 3954432, 'steps': 20595, 'loss/train': 1.6892168521881104} 08/30/2021 16:54:52 - INFO - __main__ - Step 20597: {'lr': 0.000480774446600021, 'samples': 3954624, 'steps': 20596, 'loss/train': 0.9227716326713562} 08/30/2021 16:54:52 - INFO - __main__ - Step 20598: {'lr': 0.00048077240575825075, 'samples': 3954816, 'steps': 20597, 'loss/train': 1.5762578248977661} 08/30/2021 16:54:54 - INFO - __main__ - Step 20599: {'lr': 0.000480770364812498, 'samples': 3955008, 'steps': 20598, 'loss/train': 1.6765204668045044} 08/30/2021 16:54:55 - INFO - __main__ - Step 20600: {'lr': 0.0004807683237627637, 'samples': 3955200, 'steps': 20599, 'loss/train': 1.3946428298950195} 08/30/2021 16:54:55 - INFO - __main__ - Step 20601: {'lr': 0.0004807662826090488, 'samples': 3955392, 'steps': 20600, 'loss/train': 1.2109757661819458} 08/30/2021 16:54:55 - INFO - __main__ - Step 20602: {'lr': 0.00048076424135135406, 'samples': 3955584, 'steps': 20601, 'loss/train': 1.6038706302642822} 08/30/2021 16:54:56 - INFO - __main__ - Step 20603: {'lr': 0.00048076219998968055, 'samples': 3955776, 'steps': 20602, 'loss/train': 0.7600698471069336} 08/30/2021 16:54:56 - INFO - __main__ - Step 20604: {'lr': 0.0004807601585240292, 'samples': 3955968, 'steps': 20603, 'loss/train': 1.781967282295227} 08/30/2021 16:54:58 - INFO - __main__ - Step 20605: {'lr': 0.0004807581169544009, 'samples': 3956160, 'steps': 20604, 'loss/train': 0.2823835611343384} 08/30/2021 16:54:58 - INFO - __main__ - Step 20606: {'lr': 0.00048075607528079645, 'samples': 3956352, 'steps': 20605, 'loss/train': 1.9294631481170654} 08/30/2021 16:54:58 - INFO - __main__ - Step 20607: {'lr': 0.0004807540335032169, 'samples': 3956544, 'steps': 20606, 'loss/train': 1.2828264236450195} 08/30/2021 16:54:59 - INFO - __main__ - Step 20608: {'lr': 0.0004807519916216633, 'samples': 3956736, 'steps': 20607, 'loss/train': 0.6966751217842102} 08/30/2021 16:54:59 - INFO - __main__ - Step 20609: {'lr': 0.0004807499496361362, 'samples': 3956928, 'steps': 20608, 'loss/train': 1.4355417490005493} 08/30/2021 16:55:00 - INFO - __main__ - Step 20610: {'lr': 0.00048074790754663686, 'samples': 3957120, 'steps': 20609, 'loss/train': 1.3458967208862305} 08/30/2021 16:55:01 - INFO - __main__ - Step 20611: {'lr': 0.000480745865353166, 'samples': 3957312, 'steps': 20610, 'loss/train': 1.2405227422714233} 08/30/2021 16:55:01 - INFO - __main__ - Step 20612: {'lr': 0.0004807438230557247, 'samples': 3957504, 'steps': 20611, 'loss/train': 1.2547762393951416} 08/30/2021 16:55:02 - INFO - __main__ - Step 20613: {'lr': 0.00048074178065431373, 'samples': 3957696, 'steps': 20612, 'loss/train': 1.6068294048309326} 08/30/2021 16:55:02 - INFO - __main__ - Step 20614: {'lr': 0.0004807397381489341, 'samples': 3957888, 'steps': 20613, 'loss/train': 1.6361725330352783} 08/30/2021 16:55:04 - INFO - __main__ - Step 20615: {'lr': 0.00048073769553958666, 'samples': 3958080, 'steps': 20614, 'loss/train': 1.3007580041885376} 08/30/2021 16:55:04 - INFO - __main__ - Step 20616: {'lr': 0.00048073565282627246, 'samples': 3958272, 'steps': 20615, 'loss/train': 1.7681808471679688} 08/30/2021 16:55:05 - INFO - __main__ - Step 20617: {'lr': 0.0004807336100089923, 'samples': 3958464, 'steps': 20616, 'loss/train': 2.222637414932251} 08/30/2021 16:55:05 - INFO - __main__ - Step 20618: {'lr': 0.0004807315670877471, 'samples': 3958656, 'steps': 20617, 'loss/train': 1.2972687482833862} 08/30/2021 16:55:05 - INFO - __main__ - Step 20619: {'lr': 0.00048072952406253783, 'samples': 3958848, 'steps': 20618, 'loss/train': 1.7866398096084595} 08/30/2021 16:55:06 - INFO - __main__ - Step 20620: {'lr': 0.00048072748093336536, 'samples': 3959040, 'steps': 20619, 'loss/train': 1.496514081954956} 08/30/2021 16:55:07 - INFO - __main__ - Step 20621: {'lr': 0.00048072543770023076, 'samples': 3959232, 'steps': 20620, 'loss/train': 0.11282919347286224} 08/30/2021 16:55:08 - INFO - __main__ - Step 20622: {'lr': 0.0004807233943631347, 'samples': 3959424, 'steps': 20621, 'loss/train': 1.8915866613388062} 08/30/2021 16:55:08 - INFO - __main__ - Step 20623: {'lr': 0.0004807213509220784, 'samples': 3959616, 'steps': 20622, 'loss/train': 1.8186583518981934} 08/30/2021 16:55:09 - INFO - __main__ - Step 20624: {'lr': 0.0004807193073770625, 'samples': 3959808, 'steps': 20623, 'loss/train': 1.4623253345489502} 08/30/2021 16:55:09 - INFO - __main__ - Step 20625: {'lr': 0.0004807172637280881, 'samples': 3960000, 'steps': 20624, 'loss/train': 2.0191798210144043} 08/30/2021 16:55:09 - INFO - __main__ - Step 20626: {'lr': 0.000480715219975156, 'samples': 3960192, 'steps': 20625, 'loss/train': 1.9373518228530884} 08/30/2021 16:55:11 - INFO - __main__ - Step 20627: {'lr': 0.0004807131761182672, 'samples': 3960384, 'steps': 20626, 'loss/train': 0.041183751076459885} 08/30/2021 16:55:12 - INFO - __main__ - Step 20628: {'lr': 0.00048071113215742263, 'samples': 3960576, 'steps': 20627, 'loss/train': 1.5153496265411377} 08/30/2021 16:55:12 - INFO - __main__ - Step 20629: {'lr': 0.00048070908809262316, 'samples': 3960768, 'steps': 20628, 'loss/train': 1.4794275760650635} 08/30/2021 16:55:12 - INFO - __main__ - Step 20630: {'lr': 0.0004807070439238698, 'samples': 3960960, 'steps': 20629, 'loss/train': 1.4660319089889526} 08/30/2021 16:55:13 - INFO - __main__ - Step 20631: {'lr': 0.0004807049996511633, 'samples': 3961152, 'steps': 20630, 'loss/train': 1.8759181499481201} 08/30/2021 16:55:13 - INFO - __main__ - Step 20632: {'lr': 0.00048070295527450474, 'samples': 3961344, 'steps': 20631, 'loss/train': 0.585408091545105} 08/30/2021 16:55:14 - INFO - __main__ - Step 20633: {'lr': 0.000480700910793895, 'samples': 3961536, 'steps': 20632, 'loss/train': 1.9259815216064453} 08/30/2021 16:55:15 - INFO - __main__ - Step 20634: {'lr': 0.000480698866209335, 'samples': 3961728, 'steps': 20633, 'loss/train': 1.8975882530212402} 08/30/2021 16:55:15 - INFO - __main__ - Step 20635: {'lr': 0.0004806968215208256, 'samples': 3961920, 'steps': 20634, 'loss/train': 1.6896079778671265} 08/30/2021 16:55:16 - INFO - __main__ - Step 20636: {'lr': 0.0004806947767283678, 'samples': 3962112, 'steps': 20635, 'loss/train': 1.4961246252059937} 08/30/2021 16:55:16 - INFO - __main__ - Step 20637: {'lr': 0.0004806927318319625, 'samples': 3962304, 'steps': 20636, 'loss/train': 1.7835643291473389} 08/30/2021 16:55:18 - INFO - __main__ - Step 20638: {'lr': 0.0004806906868316106, 'samples': 3962496, 'steps': 20637, 'loss/train': 1.540489673614502} 08/30/2021 16:55:18 - INFO - __main__ - Step 20639: {'lr': 0.000480688641727313, 'samples': 3962688, 'steps': 20638, 'loss/train': 1.471384048461914} 08/30/2021 16:55:19 - INFO - __main__ - Step 20640: {'lr': 0.00048068659651907076, 'samples': 3962880, 'steps': 20639, 'loss/train': 2.1339805126190186} 08/30/2021 16:55:19 - INFO - __main__ - Step 20641: {'lr': 0.0004806845512068846, 'samples': 3963072, 'steps': 20640, 'loss/train': 1.4799166917800903} 08/30/2021 16:55:19 - INFO - __main__ - Step 20642: {'lr': 0.00048068250579075554, 'samples': 3963264, 'steps': 20641, 'loss/train': 1.211970329284668} 08/30/2021 16:55:21 - INFO - __main__ - Step 20643: {'lr': 0.00048068046027068456, 'samples': 3963456, 'steps': 20642, 'loss/train': 1.1890201568603516} 08/30/2021 16:55:22 - INFO - __main__ - Step 20644: {'lr': 0.0004806784146466726, 'samples': 3963648, 'steps': 20643, 'loss/train': 1.6303956508636475} 08/30/2021 16:55:22 - INFO - __main__ - Step 20645: {'lr': 0.00048067636891872036, 'samples': 3963840, 'steps': 20644, 'loss/train': 2.086669921875} 08/30/2021 16:55:22 - INFO - __main__ - Step 20646: {'lr': 0.00048067432308682894, 'samples': 3964032, 'steps': 20645, 'loss/train': 1.1525413990020752} 08/30/2021 16:55:23 - INFO - __main__ - Step 20647: {'lr': 0.0004806722771509993, 'samples': 3964224, 'steps': 20646, 'loss/train': 1.4894037246704102} 08/30/2021 16:55:24 - INFO - __main__ - Step 20648: {'lr': 0.0004806702311112322, 'samples': 3964416, 'steps': 20647, 'loss/train': 1.3572239875793457} 08/30/2021 16:55:25 - INFO - __main__ - Step 20649: {'lr': 0.0004806681849675287, 'samples': 3964608, 'steps': 20648, 'loss/train': 1.565950632095337} 08/30/2021 16:55:25 - INFO - __main__ - Step 20650: {'lr': 0.00048066613871988967, 'samples': 3964800, 'steps': 20649, 'loss/train': 1.4098584651947021} 08/30/2021 16:55:25 - INFO - __main__ - Step 20651: {'lr': 0.00048066409236831607, 'samples': 3964992, 'steps': 20650, 'loss/train': 1.4266493320465088} 08/30/2021 16:55:26 - INFO - __main__ - Step 20652: {'lr': 0.0004806620459128087, 'samples': 3965184, 'steps': 20651, 'loss/train': 1.2918858528137207} 08/30/2021 16:55:26 - INFO - __main__ - Step 20653: {'lr': 0.0004806599993533687, 'samples': 3965376, 'steps': 20652, 'loss/train': 1.5336929559707642} 08/30/2021 16:55:28 - INFO - __main__ - Step 20654: {'lr': 0.00048065795268999677, 'samples': 3965568, 'steps': 20653, 'loss/train': 1.3345450162887573} 08/30/2021 16:55:28 - INFO - __main__ - Step 20655: {'lr': 0.00048065590592269393, 'samples': 3965760, 'steps': 20654, 'loss/train': 2.247145652770996} 08/30/2021 16:55:28 - INFO - __main__ - Step 20656: {'lr': 0.00048065385905146114, 'samples': 3965952, 'steps': 20655, 'loss/train': 1.7187037467956543} 08/30/2021 16:55:29 - INFO - __main__ - Step 20657: {'lr': 0.0004806518120762993, 'samples': 3966144, 'steps': 20656, 'loss/train': 1.3709335327148438} 08/30/2021 16:55:29 - INFO - __main__ - Step 20658: {'lr': 0.00048064976499720923, 'samples': 3966336, 'steps': 20657, 'loss/train': 2.0189366340637207} 08/30/2021 16:55:31 - INFO - __main__ - Step 20659: {'lr': 0.000480647717814192, 'samples': 3966528, 'steps': 20658, 'loss/train': 1.8227946758270264} 08/30/2021 16:55:31 - INFO - __main__ - Step 20660: {'lr': 0.0004806456705272484, 'samples': 3966720, 'steps': 20659, 'loss/train': 1.3422613143920898} 08/30/2021 16:55:31 - INFO - __main__ - Step 20661: {'lr': 0.0004806436231363795, 'samples': 3966912, 'steps': 20660, 'loss/train': 1.457248568534851} 08/30/2021 16:55:32 - INFO - __main__ - Step 20662: {'lr': 0.00048064157564158607, 'samples': 3967104, 'steps': 20661, 'loss/train': 1.3451411724090576} 08/30/2021 16:55:32 - INFO - __main__ - Step 20663: {'lr': 0.00048063952804286913, 'samples': 3967296, 'steps': 20662, 'loss/train': 2.052534341812134} 08/30/2021 16:55:34 - INFO - __main__ - Step 20664: {'lr': 0.0004806374803402296, 'samples': 3967488, 'steps': 20663, 'loss/train': 0.9287270307540894} 08/30/2021 16:55:35 - INFO - __main__ - Step 20665: {'lr': 0.00048063543253366837, 'samples': 3967680, 'steps': 20664, 'loss/train': 1.0546422004699707} 08/30/2021 16:55:35 - INFO - __main__ - Step 20666: {'lr': 0.0004806333846231864, 'samples': 3967872, 'steps': 20665, 'loss/train': 0.13127905130386353} 08/30/2021 16:55:35 - INFO - __main__ - Step 20667: {'lr': 0.00048063133660878455, 'samples': 3968064, 'steps': 20666, 'loss/train': 1.5059527158737183} 08/30/2021 16:55:36 - INFO - __main__ - Step 20668: {'lr': 0.00048062928849046377, 'samples': 3968256, 'steps': 20667, 'loss/train': 1.7320287227630615} 08/30/2021 16:55:36 - INFO - __main__ - Step 20669: {'lr': 0.00048062724026822504, 'samples': 3968448, 'steps': 20668, 'loss/train': 0.11046398431062698} 08/30/2021 16:55:38 - INFO - __main__ - Step 20670: {'lr': 0.00048062519194206916, 'samples': 3968640, 'steps': 20669, 'loss/train': 0.32149767875671387} 08/30/2021 16:55:38 - INFO - __main__ - Step 20671: {'lr': 0.0004806231435119972, 'samples': 3968832, 'steps': 20670, 'loss/train': 1.7202013731002808} 08/30/2021 16:55:38 - INFO - __main__ - Step 20672: {'lr': 0.00048062109497800997, 'samples': 3969024, 'steps': 20671, 'loss/train': 1.3532297611236572} 08/30/2021 16:55:39 - INFO - __main__ - Step 20673: {'lr': 0.00048061904634010845, 'samples': 3969216, 'steps': 20672, 'loss/train': 1.7341771125793457} 08/30/2021 16:55:39 - INFO - __main__ - Step 20674: {'lr': 0.0004806169975982935, 'samples': 3969408, 'steps': 20673, 'loss/train': 1.6083941459655762} 08/30/2021 16:55:41 - INFO - __main__ - Step 20675: {'lr': 0.0004806149487525662, 'samples': 3969600, 'steps': 20674, 'loss/train': 1.7800225019454956} 08/30/2021 16:55:41 - INFO - __main__ - Step 20676: {'lr': 0.0004806128998029272, 'samples': 3969792, 'steps': 20675, 'loss/train': 2.0995993614196777} 08/30/2021 16:55:41 - INFO - __main__ - Step 20677: {'lr': 0.0004806108507493777, 'samples': 3969984, 'steps': 20676, 'loss/train': 1.972775936126709} 08/30/2021 16:55:42 - INFO - __main__ - Step 20678: {'lr': 0.0004806088015919185, 'samples': 3970176, 'steps': 20677, 'loss/train': 5.629034996032715} 08/30/2021 16:55:42 - INFO - __main__ - Step 20679: {'lr': 0.0004806067523305505, 'samples': 3970368, 'steps': 20678, 'loss/train': 2.0154056549072266} 08/30/2021 16:55:43 - INFO - __main__ - Step 20680: {'lr': 0.0004806047029652747, 'samples': 3970560, 'steps': 20679, 'loss/train': 1.756956696510315} 08/30/2021 16:55:44 - INFO - __main__ - Step 20681: {'lr': 0.00048060265349609193, 'samples': 3970752, 'steps': 20680, 'loss/train': 1.3318066596984863} 08/30/2021 16:55:44 - INFO - __main__ - Step 20682: {'lr': 0.0004806006039230032, 'samples': 3970944, 'steps': 20681, 'loss/train': 1.3747334480285645} 08/30/2021 16:55:45 - INFO - __main__ - Step 20683: {'lr': 0.0004805985542460094, 'samples': 3971136, 'steps': 20682, 'loss/train': 1.322189450263977} 08/30/2021 16:55:45 - INFO - __main__ - Step 20684: {'lr': 0.00048059650446511136, 'samples': 3971328, 'steps': 20683, 'loss/train': 0.8517647981643677} 08/30/2021 16:55:46 - INFO - __main__ - Step 20685: {'lr': 0.00048059445458031023, 'samples': 3971520, 'steps': 20684, 'loss/train': 1.3851511478424072} 08/30/2021 16:55:47 - INFO - __main__ - Step 20686: {'lr': 0.0004805924045916067, 'samples': 3971712, 'steps': 20685, 'loss/train': 1.5475938320159912} 08/30/2021 16:55:48 - INFO - __main__ - Step 20687: {'lr': 0.00048059035449900185, 'samples': 3971904, 'steps': 20686, 'loss/train': 1.7559659481048584} 08/30/2021 16:55:48 - INFO - __main__ - Step 20688: {'lr': 0.0004805883043024965, 'samples': 3972096, 'steps': 20687, 'loss/train': 0.40264657139778137} 08/30/2021 16:55:48 - INFO - __main__ - Step 20689: {'lr': 0.0004805862540020917, 'samples': 3972288, 'steps': 20688, 'loss/train': 0.4182220697402954} 08/30/2021 16:55:49 - INFO - __main__ - Step 20690: {'lr': 0.0004805842035977882, 'samples': 3972480, 'steps': 20689, 'loss/train': 1.4698597192764282} 08/30/2021 16:55:49 - INFO - __main__ - Step 20691: {'lr': 0.00048058215308958703, 'samples': 3972672, 'steps': 20690, 'loss/train': 1.8014353513717651} 08/30/2021 16:55:51 - INFO - __main__ - Step 20692: {'lr': 0.00048058010247748904, 'samples': 3972864, 'steps': 20691, 'loss/train': 0.4119693338871002} 08/30/2021 16:55:51 - INFO - __main__ - Step 20693: {'lr': 0.0004805780517614954, 'samples': 3973056, 'steps': 20692, 'loss/train': 1.5545519590377808} 08/30/2021 16:55:52 - INFO - __main__ - Step 20694: {'lr': 0.0004805760009416067, 'samples': 3973248, 'steps': 20693, 'loss/train': 2.980133056640625} 08/30/2021 16:55:52 - INFO - __main__ - Step 20695: {'lr': 0.000480573950017824, 'samples': 3973440, 'steps': 20694, 'loss/train': 0.15593315660953522} 08/30/2021 16:55:52 - INFO - __main__ - Step 20696: {'lr': 0.0004805718989901483, 'samples': 3973632, 'steps': 20695, 'loss/train': 1.651999592781067} 08/30/2021 16:55:54 - INFO - __main__ - Step 20697: {'lr': 0.00048056984785858046, 'samples': 3973824, 'steps': 20696, 'loss/train': 0.1327599734067917} 08/30/2021 16:55:55 - INFO - __main__ - Step 20698: {'lr': 0.0004805677966231214, 'samples': 3974016, 'steps': 20697, 'loss/train': 1.5303266048431396} 08/30/2021 16:55:55 - INFO - __main__ - Step 20699: {'lr': 0.00048056574528377205, 'samples': 3974208, 'steps': 20698, 'loss/train': 1.2969508171081543} 08/30/2021 16:55:55 - INFO - __main__ - Step 20700: {'lr': 0.00048056369384053335, 'samples': 3974400, 'steps': 20699, 'loss/train': 1.381152629852295} 08/30/2021 16:55:56 - INFO - __main__ - Step 20701: {'lr': 0.00048056164229340613, 'samples': 3974592, 'steps': 20700, 'loss/train': 1.2419464588165283} 08/30/2021 16:55:57 - INFO - __main__ - Step 20702: {'lr': 0.0004805595906423914, 'samples': 3974784, 'steps': 20701, 'loss/train': 1.3216350078582764} 08/30/2021 16:55:58 - INFO - __main__ - Step 20703: {'lr': 0.00048055753888749013, 'samples': 3974976, 'steps': 20702, 'loss/train': 2.056077480316162} 08/30/2021 16:55:58 - INFO - __main__ - Step 20704: {'lr': 0.0004805554870287032, 'samples': 3975168, 'steps': 20703, 'loss/train': 1.2361171245574951} 08/30/2021 16:55:58 - INFO - __main__ - Step 20705: {'lr': 0.0004805534350660315, 'samples': 3975360, 'steps': 20704, 'loss/train': 1.7923864126205444} 08/30/2021 16:55:59 - INFO - __main__ - Step 20706: {'lr': 0.000480551382999476, 'samples': 3975552, 'steps': 20705, 'loss/train': 1.4378912448883057} 08/30/2021 16:56:00 - INFO - __main__ - Step 20707: {'lr': 0.00048054933082903754, 'samples': 3975744, 'steps': 20706, 'loss/train': 1.7227957248687744} 08/30/2021 16:56:01 - INFO - __main__ - Step 20708: {'lr': 0.00048054727855471717, 'samples': 3975936, 'steps': 20707, 'loss/train': 1.7430933713912964} 08/30/2021 16:56:01 - INFO - __main__ - Step 20709: {'lr': 0.00048054522617651575, 'samples': 3976128, 'steps': 20708, 'loss/train': 1.4573649168014526} 08/30/2021 16:56:01 - INFO - __main__ - Step 20710: {'lr': 0.0004805431736944342, 'samples': 3976320, 'steps': 20709, 'loss/train': 1.2537758350372314} 08/30/2021 16:56:02 - INFO - __main__ - Step 20711: {'lr': 0.0004805411211084735, 'samples': 3976512, 'steps': 20710, 'loss/train': 0.9819672703742981} 08/30/2021 16:56:03 - INFO - __main__ - Step 20712: {'lr': 0.0004805390684186344, 'samples': 3976704, 'steps': 20711, 'loss/train': 2.3263676166534424} 08/30/2021 16:56:04 - INFO - __main__ - Step 20713: {'lr': 0.00048053701562491804, 'samples': 3976896, 'steps': 20712, 'loss/train': 1.2889982461929321} 08/30/2021 16:56:04 - INFO - __main__ - Step 20714: {'lr': 0.0004805349627273253, 'samples': 3977088, 'steps': 20713, 'loss/train': 1.423947811126709} 08/30/2021 16:56:05 - INFO - __main__ - Step 20715: {'lr': 0.00048053290972585697, 'samples': 3977280, 'steps': 20714, 'loss/train': 1.1521159410476685} 08/30/2021 16:56:05 - INFO - __main__ - Step 20716: {'lr': 0.0004805308566205141, 'samples': 3977472, 'steps': 20715, 'loss/train': 1.5645651817321777} 08/30/2021 16:56:05 - INFO - __main__ - Step 20717: {'lr': 0.00048052880341129764, 'samples': 3977664, 'steps': 20716, 'loss/train': 0.8094602823257446} 08/30/2021 16:56:07 - INFO - __main__ - Step 20718: {'lr': 0.00048052675009820837, 'samples': 3977856, 'steps': 20717, 'loss/train': 1.7630436420440674} 08/30/2021 16:56:07 - INFO - __main__ - Step 20719: {'lr': 0.0004805246966812474, 'samples': 3978048, 'steps': 20718, 'loss/train': 2.433021068572998} 08/30/2021 16:56:07 - INFO - __main__ - Step 20720: {'lr': 0.0004805226431604155, 'samples': 3978240, 'steps': 20719, 'loss/train': 1.4015146493911743} 08/30/2021 16:56:08 - INFO - __main__ - Step 20721: {'lr': 0.00048052058953571366, 'samples': 3978432, 'steps': 20720, 'loss/train': 1.4894248247146606} 08/30/2021 16:56:08 - INFO - __main__ - Step 20722: {'lr': 0.0004805185358071428, 'samples': 3978624, 'steps': 20721, 'loss/train': 1.6452594995498657} 08/30/2021 16:56:10 - INFO - __main__ - Step 20723: {'lr': 0.0004805164819747038, 'samples': 3978816, 'steps': 20722, 'loss/train': 1.3686636686325073} 08/30/2021 16:56:10 - INFO - __main__ - Step 20724: {'lr': 0.0004805144280383977, 'samples': 3979008, 'steps': 20723, 'loss/train': 1.8824739456176758} 08/30/2021 16:56:11 - INFO - __main__ - Step 20725: {'lr': 0.00048051237399822534, 'samples': 3979200, 'steps': 20724, 'loss/train': 1.6183282136917114} 08/30/2021 16:56:11 - INFO - __main__ - Step 20726: {'lr': 0.00048051031985418764, 'samples': 3979392, 'steps': 20725, 'loss/train': 1.4658023118972778} 08/30/2021 16:56:11 - INFO - __main__ - Step 20727: {'lr': 0.0004805082656062856, 'samples': 3979584, 'steps': 20726, 'loss/train': 1.5528312921524048} 08/30/2021 16:56:13 - INFO - __main__ - Step 20728: {'lr': 0.00048050621125451996, 'samples': 3979776, 'steps': 20727, 'loss/train': 1.1035397052764893} 08/30/2021 16:56:13 - INFO - __main__ - Step 20729: {'lr': 0.00048050415679889194, 'samples': 3979968, 'steps': 20728, 'loss/train': 2.0017354488372803} 08/30/2021 16:56:14 - INFO - __main__ - Step 20730: {'lr': 0.0004805021022394022, 'samples': 3980160, 'steps': 20729, 'loss/train': 1.5923737287521362} 08/30/2021 16:56:14 - INFO - __main__ - Step 20731: {'lr': 0.0004805000475760518, 'samples': 3980352, 'steps': 20730, 'loss/train': 1.7138861417770386} 08/30/2021 16:56:14 - INFO - __main__ - Step 20732: {'lr': 0.0004804979928088417, 'samples': 3980544, 'steps': 20731, 'loss/train': 1.8164052963256836} 08/30/2021 16:56:16 - INFO - __main__ - Step 20733: {'lr': 0.0004804959379377727, 'samples': 3980736, 'steps': 20732, 'loss/train': 1.570721983909607} 08/30/2021 16:56:16 - INFO - __main__ - Step 20734: {'lr': 0.00048049388296284576, 'samples': 3980928, 'steps': 20733, 'loss/train': 0.9652804136276245} 08/30/2021 16:56:17 - INFO - __main__ - Step 20735: {'lr': 0.00048049182788406186, 'samples': 3981120, 'steps': 20734, 'loss/train': 1.8427886962890625} 08/30/2021 16:56:17 - INFO - __main__ - Step 20736: {'lr': 0.0004804897727014219, 'samples': 3981312, 'steps': 20735, 'loss/train': 2.443028688430786} 08/30/2021 16:56:17 - INFO - __main__ - Step 20737: {'lr': 0.0004804877174149268, 'samples': 3981504, 'steps': 20736, 'loss/train': 0.9933156967163086} 08/30/2021 16:56:18 - INFO - __main__ - Step 20738: {'lr': 0.00048048566202457747, 'samples': 3981696, 'steps': 20737, 'loss/train': 1.6103301048278809} 08/30/2021 16:56:19 - INFO - __main__ - Step 20739: {'lr': 0.00048048360653037494, 'samples': 3981888, 'steps': 20738, 'loss/train': 1.3910224437713623} 08/30/2021 16:56:20 - INFO - __main__ - Step 20740: {'lr': 0.00048048155093231994, 'samples': 3982080, 'steps': 20739, 'loss/train': 1.2703614234924316} 08/30/2021 16:56:20 - INFO - __main__ - Step 20741: {'lr': 0.00048047949523041355, 'samples': 3982272, 'steps': 20740, 'loss/train': 0.5967580676078796} 08/30/2021 16:56:21 - INFO - __main__ - Step 20742: {'lr': 0.0004804774394246567, 'samples': 3982464, 'steps': 20741, 'loss/train': 1.376112461090088} 08/30/2021 16:56:21 - INFO - __main__ - Step 20743: {'lr': 0.0004804753835150503, 'samples': 3982656, 'steps': 20742, 'loss/train': 1.4000831842422485} 08/30/2021 16:56:23 - INFO - __main__ - Step 20744: {'lr': 0.0004804733275015951, 'samples': 3982848, 'steps': 20743, 'loss/train': 1.4413738250732422} 08/30/2021 16:56:24 - INFO - __main__ - Step 20745: {'lr': 0.0004804712713842923, 'samples': 3983040, 'steps': 20744, 'loss/train': 1.568382740020752} 08/30/2021 16:56:24 - INFO - __main__ - Step 20746: {'lr': 0.0004804692151631427, 'samples': 3983232, 'steps': 20745, 'loss/train': 1.5668437480926514} 08/30/2021 16:56:24 - INFO - __main__ - Step 20747: {'lr': 0.00048046715883814716, 'samples': 3983424, 'steps': 20746, 'loss/train': 1.9023722410202026} 08/30/2021 16:56:25 - INFO - __main__ - Step 20748: {'lr': 0.00048046510240930674, 'samples': 3983616, 'steps': 20747, 'loss/train': 0.3020634055137634} 08/30/2021 16:56:27 - INFO - __main__ - Step 20749: {'lr': 0.00048046304587662225, 'samples': 3983808, 'steps': 20748, 'loss/train': 1.6442160606384277} 08/30/2021 16:56:27 - INFO - __main__ - Step 20750: {'lr': 0.00048046098924009467, 'samples': 3984000, 'steps': 20749, 'loss/train': 1.6216952800750732} 08/30/2021 16:56:27 - INFO - __main__ - Step 20751: {'lr': 0.00048045893249972497, 'samples': 3984192, 'steps': 20750, 'loss/train': 1.441290259361267} 08/30/2021 16:56:28 - INFO - __main__ - Step 20752: {'lr': 0.000480456875655514, 'samples': 3984384, 'steps': 20751, 'loss/train': 1.5465011596679688} 08/30/2021 16:56:28 - INFO - __main__ - Step 20753: {'lr': 0.0004804548187074628, 'samples': 3984576, 'steps': 20752, 'loss/train': 1.6776716709136963} 08/30/2021 16:56:28 - INFO - __main__ - Step 20754: {'lr': 0.0004804527616555721, 'samples': 3984768, 'steps': 20753, 'loss/train': 1.7566523551940918} 08/30/2021 16:56:30 - INFO - __main__ - Step 20755: {'lr': 0.00048045070449984295, 'samples': 3984960, 'steps': 20754, 'loss/train': 1.4441533088684082} 08/30/2021 16:56:30 - INFO - __main__ - Step 20756: {'lr': 0.0004804486472402763, 'samples': 3985152, 'steps': 20755, 'loss/train': 1.2981563806533813} 08/30/2021 16:56:31 - INFO - __main__ - Step 20757: {'lr': 0.0004804465898768731, 'samples': 3985344, 'steps': 20756, 'loss/train': 2.227184772491455} 08/30/2021 16:56:31 - INFO - __main__ - Step 20758: {'lr': 0.00048044453240963413, 'samples': 3985536, 'steps': 20757, 'loss/train': 2.007504463195801} 08/30/2021 16:56:31 - INFO - __main__ - Step 20759: {'lr': 0.00048044247483856043, 'samples': 3985728, 'steps': 20758, 'loss/train': 2.0310137271881104} 08/30/2021 16:56:33 - INFO - __main__ - Step 20760: {'lr': 0.00048044041716365296, 'samples': 3985920, 'steps': 20759, 'loss/train': 0.8354974985122681} 08/30/2021 16:56:33 - INFO - __main__ - Step 20761: {'lr': 0.00048043835938491253, 'samples': 3986112, 'steps': 20760, 'loss/train': 1.1922798156738281} 08/30/2021 16:56:34 - INFO - __main__ - Step 20762: {'lr': 0.0004804363015023402, 'samples': 3986304, 'steps': 20761, 'loss/train': 1.7823498249053955} 08/30/2021 16:56:34 - INFO - __main__ - Step 20763: {'lr': 0.00048043424351593676, 'samples': 3986496, 'steps': 20762, 'loss/train': 2.0763256549835205} 08/30/2021 16:56:34 - INFO - __main__ - Step 20764: {'lr': 0.0004804321854257032, 'samples': 3986688, 'steps': 20763, 'loss/train': 1.223707914352417} 08/30/2021 16:56:36 - INFO - __main__ - Step 20765: {'lr': 0.0004804301272316405, 'samples': 3986880, 'steps': 20764, 'loss/train': 0.4089663326740265} 08/30/2021 16:56:36 - INFO - __main__ - Step 20766: {'lr': 0.0004804280689337496, 'samples': 3987072, 'steps': 20765, 'loss/train': 1.802085280418396} 08/30/2021 16:56:37 - INFO - __main__ - Step 20767: {'lr': 0.00048042601053203125, 'samples': 3987264, 'steps': 20766, 'loss/train': 1.5809887647628784} 08/30/2021 16:56:37 - INFO - __main__ - Step 20768: {'lr': 0.00048042395202648646, 'samples': 3987456, 'steps': 20767, 'loss/train': 1.6898623704910278} 08/30/2021 16:56:37 - INFO - __main__ - Step 20769: {'lr': 0.00048042189341711636, 'samples': 3987648, 'steps': 20768, 'loss/train': 1.701935052871704} 08/30/2021 16:56:38 - INFO - __main__ - Step 20770: {'lr': 0.0004804198347039216, 'samples': 3987840, 'steps': 20769, 'loss/train': 2.0882790088653564} 08/30/2021 16:56:39 - INFO - __main__ - Step 20771: {'lr': 0.0004804177758869032, 'samples': 3988032, 'steps': 20770, 'loss/train': 1.356032133102417} 08/30/2021 16:56:40 - INFO - __main__ - Step 20772: {'lr': 0.0004804157169660622, 'samples': 3988224, 'steps': 20771, 'loss/train': 2.3334457874298096} 08/30/2021 16:56:40 - INFO - __main__ - Step 20773: {'lr': 0.00048041365794139934, 'samples': 3988416, 'steps': 20772, 'loss/train': 0.2663647532463074} 08/30/2021 16:56:41 - INFO - __main__ - Step 20774: {'lr': 0.00048041159881291574, 'samples': 3988608, 'steps': 20773, 'loss/train': 1.5477395057678223} 08/30/2021 16:56:41 - INFO - __main__ - Step 20775: {'lr': 0.0004804095395806122, 'samples': 3988800, 'steps': 20774, 'loss/train': 1.612539529800415} 08/30/2021 16:56:43 - INFO - __main__ - Step 20776: {'lr': 0.00048040748024448954, 'samples': 3988992, 'steps': 20775, 'loss/train': 1.688582420349121} 08/30/2021 16:56:43 - INFO - __main__ - Step 20777: {'lr': 0.00048040542080454897, 'samples': 3989184, 'steps': 20776, 'loss/train': 1.3352688550949097} 08/30/2021 16:56:44 - INFO - __main__ - Step 20778: {'lr': 0.0004804033612607912, 'samples': 3989376, 'steps': 20777, 'loss/train': 1.4921340942382812} 08/30/2021 16:56:44 - INFO - __main__ - Step 20779: {'lr': 0.00048040130161321724, 'samples': 3989568, 'steps': 20778, 'loss/train': 1.7791802883148193} 08/30/2021 16:56:44 - INFO - __main__ - Step 20780: {'lr': 0.0004803992418618281, 'samples': 3989760, 'steps': 20779, 'loss/train': 1.817274808883667} 08/30/2021 16:56:46 - INFO - __main__ - Step 20781: {'lr': 0.00048039718200662454, 'samples': 3989952, 'steps': 20780, 'loss/train': 0.6666374206542969} 08/30/2021 16:56:47 - INFO - __main__ - Step 20782: {'lr': 0.0004803951220476076, 'samples': 3990144, 'steps': 20781, 'loss/train': 2.2849414348602295} 08/30/2021 16:56:47 - INFO - __main__ - Step 20783: {'lr': 0.00048039306198477817, 'samples': 3990336, 'steps': 20782, 'loss/train': 1.2788106203079224} 08/30/2021 16:56:47 - INFO - __main__ - Step 20784: {'lr': 0.0004803910018181371, 'samples': 3990528, 'steps': 20783, 'loss/train': 1.457331895828247} 08/30/2021 16:56:48 - INFO - __main__ - Step 20785: {'lr': 0.0004803889415476855, 'samples': 3990720, 'steps': 20784, 'loss/train': 1.5049031972885132} 08/30/2021 16:56:50 - INFO - __main__ - Step 20786: {'lr': 0.0004803868811734242, 'samples': 3990912, 'steps': 20785, 'loss/train': 0.9126980304718018} 08/30/2021 16:56:50 - INFO - __main__ - Step 20787: {'lr': 0.00048038482069535406, 'samples': 3991104, 'steps': 20786, 'loss/train': 0.9489515423774719} 08/30/2021 16:56:50 - INFO - __main__ - Step 20788: {'lr': 0.000480382760113476, 'samples': 3991296, 'steps': 20787, 'loss/train': 1.571537733078003} 08/30/2021 16:56:51 - INFO - __main__ - Step 20789: {'lr': 0.00048038069942779116, 'samples': 3991488, 'steps': 20788, 'loss/train': 1.521704912185669} 08/30/2021 16:56:51 - INFO - __main__ - Step 20790: {'lr': 0.00048037863863830034, 'samples': 3991680, 'steps': 20789, 'loss/train': 1.4000773429870605} 08/30/2021 16:56:51 - INFO - __main__ - Step 20791: {'lr': 0.0004803765777450044, 'samples': 3991872, 'steps': 20790, 'loss/train': 1.6413817405700684} 08/30/2021 16:56:53 - INFO - __main__ - Step 20792: {'lr': 0.00048037451674790433, 'samples': 3992064, 'steps': 20791, 'loss/train': 0.200750470161438} 08/30/2021 16:56:53 - INFO - __main__ - Step 20793: {'lr': 0.0004803724556470011, 'samples': 3992256, 'steps': 20792, 'loss/train': 1.843687653541565} 08/30/2021 16:56:54 - INFO - __main__ - Step 20794: {'lr': 0.0004803703944422956, 'samples': 3992448, 'steps': 20793, 'loss/train': 1.8204582929611206} 08/30/2021 16:56:54 - INFO - __main__ - Step 20795: {'lr': 0.0004803683331337887, 'samples': 3992640, 'steps': 20794, 'loss/train': 1.6987535953521729} 08/30/2021 16:56:54 - INFO - __main__ - Step 20796: {'lr': 0.0004803662717214814, 'samples': 3992832, 'steps': 20795, 'loss/train': 1.7447631359100342} 08/30/2021 16:56:56 - INFO - __main__ - Step 20797: {'lr': 0.00048036421020537464, 'samples': 3993024, 'steps': 20796, 'loss/train': 1.2406423091888428} 08/30/2021 16:56:56 - INFO - __main__ - Step 20798: {'lr': 0.0004803621485854693, 'samples': 3993216, 'steps': 20797, 'loss/train': 1.7606385946273804} 08/30/2021 16:56:57 - INFO - __main__ - Step 20799: {'lr': 0.00048036008686176636, 'samples': 3993408, 'steps': 20798, 'loss/train': 2.0389721393585205} 08/30/2021 16:56:57 - INFO - __main__ - Step 20800: {'lr': 0.0004803580250342666, 'samples': 3993600, 'steps': 20799, 'loss/train': 0.8765015006065369} 08/30/2021 16:56:57 - INFO - __main__ - Step 20801: {'lr': 0.00048035596310297125, 'samples': 3993792, 'steps': 20800, 'loss/train': 1.6353588104248047} 08/30/2021 16:56:58 - INFO - __main__ - Step 20802: {'lr': 0.0004803539010678809, 'samples': 3993984, 'steps': 20801, 'loss/train': 1.1891461610794067} 08/30/2021 16:57:00 - INFO - __main__ - Step 20803: {'lr': 0.00048035183892899676, 'samples': 3994176, 'steps': 20802, 'loss/train': 1.509429931640625} 08/30/2021 16:57:00 - INFO - __main__ - Step 20804: {'lr': 0.0004803497766863195, 'samples': 3994368, 'steps': 20803, 'loss/train': 1.8290326595306396} 08/30/2021 16:57:01 - INFO - __main__ - Step 20805: {'lr': 0.00048034771433985035, 'samples': 3994560, 'steps': 20804, 'loss/train': 1.8175963163375854} 08/30/2021 16:57:01 - INFO - __main__ - Step 20806: {'lr': 0.00048034565188959, 'samples': 3994752, 'steps': 20805, 'loss/train': 1.915069341659546} 08/30/2021 16:57:01 - INFO - __main__ - Step 20807: {'lr': 0.0004803435893355394, 'samples': 3994944, 'steps': 20806, 'loss/train': 1.5590801239013672} 08/30/2021 16:57:03 - INFO - __main__ - Step 20808: {'lr': 0.00048034152667769957, 'samples': 3995136, 'steps': 20807, 'loss/train': 1.4858994483947754} 08/30/2021 16:57:03 - INFO - __main__ - Step 20809: {'lr': 0.0004803394639160714, 'samples': 3995328, 'steps': 20808, 'loss/train': 1.0625766515731812} 08/30/2021 16:57:04 - INFO - __main__ - Step 20810: {'lr': 0.00048033740105065585, 'samples': 3995520, 'steps': 20809, 'loss/train': 0.7241296768188477} 08/30/2021 16:57:04 - INFO - __main__ - Step 20811: {'lr': 0.0004803353380814538, 'samples': 3995712, 'steps': 20810, 'loss/train': 1.686326503753662} 08/30/2021 16:57:04 - INFO - __main__ - Step 20812: {'lr': 0.00048033327500846625, 'samples': 3995904, 'steps': 20811, 'loss/train': 1.425820231437683} 08/30/2021 16:57:06 - INFO - __main__ - Step 20813: {'lr': 0.000480331211831694, 'samples': 3996096, 'steps': 20812, 'loss/train': 0.8603524565696716} 08/30/2021 16:57:06 - INFO - __main__ - Step 20814: {'lr': 0.00048032914855113807, 'samples': 3996288, 'steps': 20813, 'loss/train': 1.022192120552063} 08/30/2021 16:57:06 - INFO - __main__ - Step 20815: {'lr': 0.00048032708516679946, 'samples': 3996480, 'steps': 20814, 'loss/train': 0.7716886401176453} 08/30/2021 16:57:07 - INFO - __main__ - Step 20816: {'lr': 0.00048032502167867896, 'samples': 3996672, 'steps': 20815, 'loss/train': 1.5297855138778687} 08/30/2021 16:57:07 - INFO - __main__ - Step 20817: {'lr': 0.0004803229580867775, 'samples': 3996864, 'steps': 20816, 'loss/train': 1.4987337589263916} 08/30/2021 16:57:09 - INFO - __main__ - Step 20818: {'lr': 0.0004803208943910962, 'samples': 3997056, 'steps': 20817, 'loss/train': 1.2595634460449219} 08/30/2021 16:57:09 - INFO - __main__ - Step 20819: {'lr': 0.00048031883059163576, 'samples': 3997248, 'steps': 20818, 'loss/train': 1.42384934425354} 08/30/2021 16:57:09 - INFO - __main__ - Step 20820: {'lr': 0.00048031676668839723, 'samples': 3997440, 'steps': 20819, 'loss/train': 1.623425006866455} 08/30/2021 16:57:10 - INFO - __main__ - Step 20821: {'lr': 0.00048031470268138153, 'samples': 3997632, 'steps': 20820, 'loss/train': 1.529524564743042} 08/30/2021 16:57:10 - INFO - __main__ - Step 20822: {'lr': 0.00048031263857058957, 'samples': 3997824, 'steps': 20821, 'loss/train': 1.398085355758667} 08/30/2021 16:57:12 - INFO - __main__ - Step 20823: {'lr': 0.00048031057435602234, 'samples': 3998016, 'steps': 20822, 'loss/train': 0.6544572710990906} 08/30/2021 16:57:12 - INFO - __main__ - Step 20824: {'lr': 0.0004803085100376807, 'samples': 3998208, 'steps': 20823, 'loss/train': 1.5054800510406494} 08/30/2021 16:57:12 - INFO - __main__ - Step 20825: {'lr': 0.00048030644561556556, 'samples': 3998400, 'steps': 20824, 'loss/train': 2.384716749191284} 08/30/2021 16:57:13 - INFO - __main__ - Step 20826: {'lr': 0.0004803043810896779, 'samples': 3998592, 'steps': 20825, 'loss/train': 1.834130883216858} 08/30/2021 16:57:13 - INFO - __main__ - Step 20827: {'lr': 0.00048030231646001867, 'samples': 3998784, 'steps': 20826, 'loss/train': 1.5747114419937134} 08/30/2021 16:57:15 - INFO - __main__ - Step 20828: {'lr': 0.0004803002517265887, 'samples': 3998976, 'steps': 20827, 'loss/train': 1.1097772121429443} 08/30/2021 16:57:15 - INFO - __main__ - Step 20829: {'lr': 0.0004802981868893891, 'samples': 3999168, 'steps': 20828, 'loss/train': 1.3051564693450928} 08/30/2021 16:57:16 - INFO - __main__ - Step 20830: {'lr': 0.00048029612194842056, 'samples': 3999360, 'steps': 20829, 'loss/train': 1.3877121210098267} 08/30/2021 16:57:16 - INFO - __main__ - Step 20831: {'lr': 0.0004802940569036842, 'samples': 3999552, 'steps': 20830, 'loss/train': 1.4898688793182373} 08/30/2021 16:57:16 - INFO - __main__ - Step 20832: {'lr': 0.0004802919917551809, 'samples': 3999744, 'steps': 20831, 'loss/train': 1.796456217765808} 08/30/2021 16:57:18 - INFO - __main__ - Step 20833: {'lr': 0.00048028992650291156, 'samples': 3999936, 'steps': 20832, 'loss/train': 1.4047584533691406} 08/30/2021 16:57:18 - INFO - __main__ - Step 20834: {'lr': 0.00048028786114687715, 'samples': 4000128, 'steps': 20833, 'loss/train': 0.3299529552459717} 08/30/2021 16:57:18 - INFO - __main__ - Step 20835: {'lr': 0.0004802857956870786, 'samples': 4000320, 'steps': 20834, 'loss/train': 1.3085787296295166} 08/30/2021 16:57:19 - INFO - __main__ - Step 20836: {'lr': 0.00048028373012351684, 'samples': 4000512, 'steps': 20835, 'loss/train': 1.2915829420089722} 08/30/2021 16:57:19 - INFO - __main__ - Step 20837: {'lr': 0.00048028166445619275, 'samples': 4000704, 'steps': 20836, 'loss/train': 1.332929015159607} 08/30/2021 16:57:21 - INFO - __main__ - Step 20838: {'lr': 0.0004802795986851073, 'samples': 4000896, 'steps': 20837, 'loss/train': 1.5033856630325317} 08/30/2021 16:57:21 - INFO - __main__ - Step 20839: {'lr': 0.00048027753281026144, 'samples': 4001088, 'steps': 20838, 'loss/train': 1.496140956878662} 08/30/2021 16:57:21 - INFO - __main__ - Step 20840: {'lr': 0.000480275466831656, 'samples': 4001280, 'steps': 20839, 'loss/train': 1.7681258916854858} 08/30/2021 16:57:22 - INFO - __main__ - Step 20841: {'lr': 0.00048027340074929207, 'samples': 4001472, 'steps': 20840, 'loss/train': 1.8449194431304932} 08/30/2021 16:57:22 - INFO - __main__ - Step 20842: {'lr': 0.0004802713345631705, 'samples': 4001664, 'steps': 20841, 'loss/train': 1.9577341079711914} 08/30/2021 16:57:23 - INFO - __main__ - Step 20843: {'lr': 0.0004802692682732922, 'samples': 4001856, 'steps': 20842, 'loss/train': 1.7500014305114746} 08/30/2021 16:57:24 - INFO - __main__ - Step 20844: {'lr': 0.0004802672018796581, 'samples': 4002048, 'steps': 20843, 'loss/train': 0.7694911360740662} 08/30/2021 16:57:25 - INFO - __main__ - Step 20845: {'lr': 0.0004802651353822691, 'samples': 4002240, 'steps': 20844, 'loss/train': 1.3434566259384155} 08/30/2021 16:57:25 - INFO - __main__ - Step 20846: {'lr': 0.0004802630687811263, 'samples': 4002432, 'steps': 20845, 'loss/train': 0.157589390873909} 08/30/2021 16:57:25 - INFO - __main__ - Step 20847: {'lr': 0.00048026100207623047, 'samples': 4002624, 'steps': 20846, 'loss/train': 1.613234281539917} 08/30/2021 16:57:26 - INFO - __main__ - Step 20848: {'lr': 0.0004802589352675826, 'samples': 4002816, 'steps': 20847, 'loss/train': 5.843477725982666} 08/30/2021 16:57:27 - INFO - __main__ - Step 20849: {'lr': 0.0004802568683551836, 'samples': 4003008, 'steps': 20848, 'loss/train': 1.3360764980316162} 08/30/2021 16:57:28 - INFO - __main__ - Step 20850: {'lr': 0.0004802548013390343, 'samples': 4003200, 'steps': 20849, 'loss/train': 1.213433027267456} 08/30/2021 16:57:28 - INFO - __main__ - Step 20851: {'lr': 0.00048025273421913587, 'samples': 4003392, 'steps': 20850, 'loss/train': 1.7084523439407349} 08/30/2021 16:57:28 - INFO - __main__ - Step 20852: {'lr': 0.0004802506669954891, 'samples': 4003584, 'steps': 20851, 'loss/train': 1.7778393030166626} 08/30/2021 16:57:29 - INFO - __main__ - Step 20853: {'lr': 0.00048024859966809487, 'samples': 4003776, 'steps': 20852, 'loss/train': 2.043734550476074} 08/30/2021 16:57:30 - INFO - __main__ - Step 20854: {'lr': 0.00048024653223695425, 'samples': 4003968, 'steps': 20853, 'loss/train': 1.2937445640563965} 08/30/2021 16:57:31 - INFO - __main__ - Step 20855: {'lr': 0.00048024446470206806, 'samples': 4004160, 'steps': 20854, 'loss/train': 0.8848605155944824} 08/30/2021 16:57:31 - INFO - __main__ - Step 20856: {'lr': 0.0004802423970634373, 'samples': 4004352, 'steps': 20855, 'loss/train': 1.7068744897842407} 08/30/2021 16:57:31 - INFO - __main__ - Step 20857: {'lr': 0.00048024032932106277, 'samples': 4004544, 'steps': 20856, 'loss/train': 1.936099648475647} 08/30/2021 16:57:32 - INFO - __main__ - Step 20858: {'lr': 0.00048023826147494556, 'samples': 4004736, 'steps': 20857, 'loss/train': 1.530527949333191} 08/30/2021 16:57:32 - INFO - __main__ - Step 20859: {'lr': 0.0004802361935250865, 'samples': 4004928, 'steps': 20858, 'loss/train': 1.242943525314331} 08/30/2021 16:57:34 - INFO - __main__ - Step 20860: {'lr': 0.0004802341254714867, 'samples': 4005120, 'steps': 20859, 'loss/train': 1.5698579549789429} 08/30/2021 16:57:35 - INFO - __main__ - Step 20861: {'lr': 0.00048023205731414684, 'samples': 4005312, 'steps': 20860, 'loss/train': 1.8995860815048218} 08/30/2021 16:57:35 - INFO - __main__ - Step 20862: {'lr': 0.00048022998905306795, 'samples': 4005504, 'steps': 20861, 'loss/train': 0.5663987994194031} 08/30/2021 16:57:35 - INFO - __main__ - Step 20863: {'lr': 0.00048022792068825107, 'samples': 4005696, 'steps': 20862, 'loss/train': 1.5970838069915771} 08/30/2021 16:57:36 - INFO - __main__ - Step 20864: {'lr': 0.00048022585221969697, 'samples': 4005888, 'steps': 20863, 'loss/train': 0.8861684799194336} 08/30/2021 16:57:38 - INFO - __main__ - Step 20865: {'lr': 0.00048022378364740673, 'samples': 4006080, 'steps': 20864, 'loss/train': 1.7130883932113647} 08/30/2021 16:57:38 - INFO - __main__ - Step 20866: {'lr': 0.0004802217149713811, 'samples': 4006272, 'steps': 20865, 'loss/train': 1.4740095138549805} 08/30/2021 16:57:39 - INFO - __main__ - Step 20867: {'lr': 0.0004802196461916212, 'samples': 4006464, 'steps': 20866, 'loss/train': 1.6010992527008057} 08/30/2021 16:57:39 - INFO - __main__ - Step 20868: {'lr': 0.0004802175773081278, 'samples': 4006656, 'steps': 20867, 'loss/train': 1.6782881021499634} 08/30/2021 16:57:39 - INFO - __main__ - Step 20869: {'lr': 0.000480215508320902, 'samples': 4006848, 'steps': 20868, 'loss/train': 0.167189359664917} 08/30/2021 16:57:41 - INFO - __main__ - Step 20870: {'lr': 0.0004802134392299446, 'samples': 4007040, 'steps': 20869, 'loss/train': 1.6451122760772705} 08/30/2021 16:57:41 - INFO - __main__ - Step 20871: {'lr': 0.0004802113700352566, 'samples': 4007232, 'steps': 20870, 'loss/train': 1.909308910369873} 08/30/2021 16:57:42 - INFO - __main__ - Step 20872: {'lr': 0.00048020930073683886, 'samples': 4007424, 'steps': 20871, 'loss/train': 1.7468796968460083} 08/30/2021 16:57:42 - INFO - __main__ - Step 20873: {'lr': 0.0004802072313346924, 'samples': 4007616, 'steps': 20872, 'loss/train': 1.462784767150879} 08/30/2021 16:57:42 - INFO - __main__ - Step 20874: {'lr': 0.00048020516182881813, 'samples': 4007808, 'steps': 20873, 'loss/train': 1.947792410850525} 08/30/2021 16:57:44 - INFO - __main__ - Step 20875: {'lr': 0.00048020309221921686, 'samples': 4008000, 'steps': 20874, 'loss/train': 1.4549416303634644} 08/30/2021 16:57:44 - INFO - __main__ - Step 20876: {'lr': 0.00048020102250588976, 'samples': 4008192, 'steps': 20875, 'loss/train': 1.3103128671646118} 08/30/2021 16:57:45 - INFO - __main__ - Step 20877: {'lr': 0.00048019895268883764, 'samples': 4008384, 'steps': 20876, 'loss/train': 1.1322263479232788} 08/30/2021 16:57:45 - INFO - __main__ - Step 20878: {'lr': 0.0004801968827680613, 'samples': 4008576, 'steps': 20877, 'loss/train': 1.3397971391677856} 08/30/2021 16:57:45 - INFO - __main__ - Step 20879: {'lr': 0.00048019481274356194, 'samples': 4008768, 'steps': 20878, 'loss/train': 1.1345170736312866} 08/30/2021 16:57:47 - INFO - __main__ - Step 20880: {'lr': 0.0004801927426153402, 'samples': 4008960, 'steps': 20879, 'loss/train': 1.5402135848999023} 08/30/2021 16:57:48 - INFO - __main__ - Step 20881: {'lr': 0.00048019067238339725, 'samples': 4009152, 'steps': 20880, 'loss/train': 1.3619599342346191} 08/30/2021 16:57:48 - INFO - __main__ - Step 20882: {'lr': 0.000480188602047734, 'samples': 4009344, 'steps': 20881, 'loss/train': 1.7267178297042847} 08/30/2021 16:57:49 - INFO - __main__ - Step 20883: {'lr': 0.0004801865316083512, 'samples': 4009536, 'steps': 20882, 'loss/train': 2.110841989517212} 08/30/2021 16:57:49 - INFO - __main__ - Step 20884: {'lr': 0.0004801844610652499, 'samples': 4009728, 'steps': 20883, 'loss/train': 1.598005771636963} 08/30/2021 16:57:49 - INFO - __main__ - Step 20885: {'lr': 0.0004801823904184311, 'samples': 4009920, 'steps': 20884, 'loss/train': 1.4082896709442139} 08/30/2021 16:57:51 - INFO - __main__ - Step 20886: {'lr': 0.00048018031966789564, 'samples': 4010112, 'steps': 20885, 'loss/train': 0.14600832760334015} 08/30/2021 16:57:52 - INFO - __main__ - Step 20887: {'lr': 0.0004801782488136445, 'samples': 4010304, 'steps': 20886, 'loss/train': 1.7309308052062988} 08/30/2021 16:57:52 - INFO - __main__ - Step 20888: {'lr': 0.00048017617785567855, 'samples': 4010496, 'steps': 20887, 'loss/train': 0.1437617540359497} 08/30/2021 16:57:52 - INFO - __main__ - Step 20889: {'lr': 0.00048017410679399876, 'samples': 4010688, 'steps': 20888, 'loss/train': 1.4162567853927612} 08/30/2021 16:57:53 - INFO - __main__ - Step 20890: {'lr': 0.00048017203562860614, 'samples': 4010880, 'steps': 20889, 'loss/train': 2.313275098800659} 08/30/2021 16:57:53 - INFO - __main__ - Step 20891: {'lr': 0.0004801699643595015, 'samples': 4011072, 'steps': 20890, 'loss/train': 1.5743414163589478} 08/30/2021 16:57:54 - INFO - __main__ - Step 20892: {'lr': 0.00048016789298668583, 'samples': 4011264, 'steps': 20891, 'loss/train': 0.7836162447929382} 08/30/2021 16:57:55 - INFO - __main__ - Step 20893: {'lr': 0.0004801658215101601, 'samples': 4011456, 'steps': 20892, 'loss/train': 1.8106706142425537} 08/30/2021 16:57:55 - INFO - __main__ - Step 20894: {'lr': 0.00048016374992992516, 'samples': 4011648, 'steps': 20893, 'loss/train': 1.6870431900024414} 08/30/2021 16:57:56 - INFO - __main__ - Step 20895: {'lr': 0.000480161678245982, 'samples': 4011840, 'steps': 20894, 'loss/train': 1.6460051536560059} 08/30/2021 16:57:57 - INFO - __main__ - Step 20896: {'lr': 0.0004801596064583315, 'samples': 4012032, 'steps': 20895, 'loss/train': 1.2648009061813354} 08/30/2021 16:57:58 - INFO - __main__ - Step 20897: {'lr': 0.00048015753456697466, 'samples': 4012224, 'steps': 20896, 'loss/train': 1.7518366575241089} 08/30/2021 16:57:58 - INFO - __main__ - Step 20898: {'lr': 0.00048015546257191243, 'samples': 4012416, 'steps': 20897, 'loss/train': 1.0268855094909668} 08/30/2021 16:57:58 - INFO - __main__ - Step 20899: {'lr': 0.00048015339047314566, 'samples': 4012608, 'steps': 20898, 'loss/train': 1.3595432043075562} 08/30/2021 16:57:59 - INFO - __main__ - Step 20900: {'lr': 0.00048015131827067534, 'samples': 4012800, 'steps': 20899, 'loss/train': 0.8023666739463806} 08/30/2021 16:57:59 - INFO - __main__ - Step 20901: {'lr': 0.0004801492459645024, 'samples': 4012992, 'steps': 20900, 'loss/train': 1.5363144874572754} 08/30/2021 16:58:00 - INFO - __main__ - Step 20902: {'lr': 0.0004801471735546277, 'samples': 4013184, 'steps': 20901, 'loss/train': 1.5872712135314941} 08/30/2021 16:58:01 - INFO - __main__ - Step 20903: {'lr': 0.0004801451010410522, 'samples': 4013376, 'steps': 20902, 'loss/train': 1.7590477466583252} 08/30/2021 16:58:01 - INFO - __main__ - Step 20904: {'lr': 0.000480143028423777, 'samples': 4013568, 'steps': 20903, 'loss/train': 1.8734040260314941} 08/30/2021 16:58:02 - INFO - __main__ - Step 20905: {'lr': 0.0004801409557028028, 'samples': 4013760, 'steps': 20904, 'loss/train': 1.6589394807815552} 08/30/2021 16:58:02 - INFO - __main__ - Step 20906: {'lr': 0.0004801388828781307, 'samples': 4013952, 'steps': 20905, 'loss/train': 1.5599116086959839} 08/30/2021 16:58:04 - INFO - __main__ - Step 20907: {'lr': 0.00048013680994976154, 'samples': 4014144, 'steps': 20906, 'loss/train': 1.3931597471237183} 08/30/2021 16:58:05 - INFO - __main__ - Step 20908: {'lr': 0.0004801347369176963, 'samples': 4014336, 'steps': 20907, 'loss/train': 1.6757256984710693} 08/30/2021 16:58:05 - INFO - __main__ - Step 20909: {'lr': 0.00048013266378193586, 'samples': 4014528, 'steps': 20908, 'loss/train': 1.1520507335662842} 08/30/2021 16:58:05 - INFO - __main__ - Step 20910: {'lr': 0.00048013059054248134, 'samples': 4014720, 'steps': 20909, 'loss/train': 1.6782448291778564} 08/30/2021 16:58:06 - INFO - __main__ - Step 20911: {'lr': 0.00048012851719933335, 'samples': 4014912, 'steps': 20910, 'loss/train': 1.9210513830184937} 08/30/2021 16:58:06 - INFO - __main__ - Step 20912: {'lr': 0.000480126443752493, 'samples': 4015104, 'steps': 20911, 'loss/train': 5.031146049499512} 08/30/2021 16:58:08 - INFO - __main__ - Step 20913: {'lr': 0.0004801243702019614, 'samples': 4015296, 'steps': 20912, 'loss/train': 1.5334185361862183} 08/30/2021 16:58:08 - INFO - __main__ - Step 20914: {'lr': 0.00048012229654773915, 'samples': 4015488, 'steps': 20913, 'loss/train': 1.430576205253601} 08/30/2021 16:58:08 - INFO - __main__ - Step 20915: {'lr': 0.0004801202227898274, 'samples': 4015680, 'steps': 20914, 'loss/train': 1.8230525255203247} 08/30/2021 16:58:09 - INFO - __main__ - Step 20916: {'lr': 0.00048011814892822704, 'samples': 4015872, 'steps': 20915, 'loss/train': 1.590773105621338} 08/30/2021 16:58:09 - INFO - __main__ - Step 20917: {'lr': 0.00048011607496293896, 'samples': 4016064, 'steps': 20916, 'loss/train': 1.8072232007980347} 08/30/2021 16:58:11 - INFO - __main__ - Step 20918: {'lr': 0.0004801140008939642, 'samples': 4016256, 'steps': 20917, 'loss/train': 1.6074912548065186} 08/30/2021 16:58:11 - INFO - __main__ - Step 20919: {'lr': 0.00048011192672130356, 'samples': 4016448, 'steps': 20918, 'loss/train': 1.6177542209625244} 08/30/2021 16:58:11 - INFO - __main__ - Step 20920: {'lr': 0.000480109852444958, 'samples': 4016640, 'steps': 20919, 'loss/train': 0.4326907992362976} 08/30/2021 16:58:12 - INFO - __main__ - Step 20921: {'lr': 0.0004801077780649286, 'samples': 4016832, 'steps': 20920, 'loss/train': 1.431039571762085} 08/30/2021 16:58:12 - INFO - __main__ - Step 20922: {'lr': 0.00048010570358121606, 'samples': 4017024, 'steps': 20921, 'loss/train': 1.421709418296814} 08/30/2021 16:58:14 - INFO - __main__ - Step 20923: {'lr': 0.0004801036289938215, 'samples': 4017216, 'steps': 20922, 'loss/train': 1.3588948249816895} 08/30/2021 16:58:14 - INFO - __main__ - Step 20924: {'lr': 0.0004801015543027458, 'samples': 4017408, 'steps': 20923, 'loss/train': 1.118821144104004} 08/30/2021 16:58:15 - INFO - __main__ - Step 20925: {'lr': 0.0004800994795079899, 'samples': 4017600, 'steps': 20924, 'loss/train': 1.0915248394012451} 08/30/2021 16:58:15 - INFO - __main__ - Step 20926: {'lr': 0.00048009740460955465, 'samples': 4017792, 'steps': 20925, 'loss/train': 1.7997756004333496} 08/30/2021 16:58:16 - INFO - __main__ - Step 20927: {'lr': 0.00048009532960744116, 'samples': 4017984, 'steps': 20926, 'loss/train': 1.7789839506149292} 08/30/2021 16:58:17 - INFO - __main__ - Step 20928: {'lr': 0.0004800932545016502, 'samples': 4018176, 'steps': 20927, 'loss/train': 2.1777122020721436} 08/30/2021 16:58:18 - INFO - __main__ - Step 20929: {'lr': 0.0004800911792921828, 'samples': 4018368, 'steps': 20928, 'loss/train': 0.8171807527542114} 08/30/2021 16:58:18 - INFO - __main__ - Step 20930: {'lr': 0.0004800891039790399, 'samples': 4018560, 'steps': 20929, 'loss/train': 2.5374791622161865} 08/30/2021 16:58:18 - INFO - __main__ - Step 20931: {'lr': 0.00048008702856222233, 'samples': 4018752, 'steps': 20930, 'loss/train': 0.07208096235990524} 08/30/2021 16:58:19 - INFO - __main__ - Step 20932: {'lr': 0.0004800849530417312, 'samples': 4018944, 'steps': 20931, 'loss/train': 0.8734824657440186} 08/30/2021 16:58:20 - INFO - __main__ - Step 20933: {'lr': 0.00048008287741756715, 'samples': 4019136, 'steps': 20932, 'loss/train': 1.5740123987197876} 08/30/2021 16:58:20 - INFO - __main__ - Step 20934: {'lr': 0.00048008080168973144, 'samples': 4019328, 'steps': 20933, 'loss/train': 1.2088955640792847} 08/30/2021 16:58:21 - INFO - __main__ - Step 20935: {'lr': 0.00048007872585822486, 'samples': 4019520, 'steps': 20934, 'loss/train': 2.1600000858306885} 08/30/2021 16:58:21 - INFO - __main__ - Step 20936: {'lr': 0.00048007664992304834, 'samples': 4019712, 'steps': 20935, 'loss/train': 1.962638020515442} 08/30/2021 16:58:22 - INFO - __main__ - Step 20937: {'lr': 0.0004800745738842029, 'samples': 4019904, 'steps': 20936, 'loss/train': 1.4366098642349243} 08/30/2021 16:58:23 - INFO - __main__ - Step 20938: {'lr': 0.0004800724977416894, 'samples': 4020096, 'steps': 20937, 'loss/train': 1.3570092916488647} 08/30/2021 16:58:23 - INFO - __main__ - Step 20939: {'lr': 0.00048007042149550866, 'samples': 4020288, 'steps': 20938, 'loss/train': 2.136103868484497} 08/30/2021 16:58:24 - INFO - __main__ - Step 20940: {'lr': 0.00048006834514566183, 'samples': 4020480, 'steps': 20939, 'loss/train': 1.2310088872909546} 08/30/2021 16:58:24 - INFO - __main__ - Step 20941: {'lr': 0.00048006626869214977, 'samples': 4020672, 'steps': 20940, 'loss/train': 1.283164620399475} 08/30/2021 16:58:24 - INFO - __main__ - Step 20942: {'lr': 0.00048006419213497334, 'samples': 4020864, 'steps': 20941, 'loss/train': 1.5024957656860352} 08/30/2021 16:58:25 - INFO - __main__ - Step 20943: {'lr': 0.0004800621154741335, 'samples': 4021056, 'steps': 20942, 'loss/train': 1.8647565841674805} 08/30/2021 16:58:27 - INFO - __main__ - Step 20944: {'lr': 0.00048006003870963135, 'samples': 4021248, 'steps': 20943, 'loss/train': 1.7144920825958252} 08/30/2021 16:58:28 - INFO - __main__ - Step 20945: {'lr': 0.0004800579618414676, 'samples': 4021440, 'steps': 20944, 'loss/train': 0.9009919762611389} 08/30/2021 16:58:28 - INFO - __main__ - Step 20946: {'lr': 0.0004800558848696433, 'samples': 4021632, 'steps': 20945, 'loss/train': 1.5119132995605469} 08/30/2021 16:58:28 - INFO - __main__ - Step 20947: {'lr': 0.0004800538077941594, 'samples': 4021824, 'steps': 20946, 'loss/train': 1.3563536405563354} 08/30/2021 16:58:29 - INFO - __main__ - Step 20948: {'lr': 0.00048005173061501673, 'samples': 4022016, 'steps': 20947, 'loss/train': 0.7356158494949341} 08/30/2021 16:58:29 - INFO - __main__ - Step 20949: {'lr': 0.0004800496533322164, 'samples': 4022208, 'steps': 20948, 'loss/train': 0.7174288034439087} 08/30/2021 16:58:31 - INFO - __main__ - Step 20950: {'lr': 0.00048004757594575923, 'samples': 4022400, 'steps': 20949, 'loss/train': 0.5843749046325684} 08/30/2021 16:58:31 - INFO - __main__ - Step 20951: {'lr': 0.0004800454984556461, 'samples': 4022592, 'steps': 20950, 'loss/train': 1.7752432823181152} 08/30/2021 16:58:31 - INFO - __main__ - Step 20952: {'lr': 0.00048004342086187805, 'samples': 4022784, 'steps': 20951, 'loss/train': 1.4212886095046997} 08/30/2021 16:58:32 - INFO - __main__ - Step 20953: {'lr': 0.000480041343164456, 'samples': 4022976, 'steps': 20952, 'loss/train': 1.3968759775161743} 08/30/2021 16:58:32 - INFO - __main__ - Step 20954: {'lr': 0.0004800392653633808, 'samples': 4023168, 'steps': 20953, 'loss/train': 1.6341660022735596} 08/30/2021 16:58:34 - INFO - __main__ - Step 20955: {'lr': 0.0004800371874586535, 'samples': 4023360, 'steps': 20954, 'loss/train': 0.8786346912384033} 08/30/2021 16:58:34 - INFO - __main__ - Step 20956: {'lr': 0.0004800351094502751, 'samples': 4023552, 'steps': 20955, 'loss/train': 1.3521685600280762} 08/30/2021 16:58:34 - INFO - __main__ - Step 20957: {'lr': 0.00048003303133824633, 'samples': 4023744, 'steps': 20956, 'loss/train': 1.648524522781372} 08/30/2021 16:58:35 - INFO - __main__ - Step 20958: {'lr': 0.0004800309531225683, 'samples': 4023936, 'steps': 20957, 'loss/train': 1.6984584331512451} 08/30/2021 16:58:35 - INFO - __main__ - Step 20959: {'lr': 0.00048002887480324175, 'samples': 4024128, 'steps': 20958, 'loss/train': 1.4897602796554565} 08/30/2021 16:58:37 - INFO - __main__ - Step 20960: {'lr': 0.0004800267963802678, 'samples': 4024320, 'steps': 20959, 'loss/train': 1.420543909072876} 08/30/2021 16:58:38 - INFO - __main__ - Step 20961: {'lr': 0.0004800247178536473, 'samples': 4024512, 'steps': 20960, 'loss/train': 1.5173707008361816} 08/30/2021 16:58:38 - INFO - __main__ - Step 20962: {'lr': 0.0004800226392233813, 'samples': 4024704, 'steps': 20961, 'loss/train': 1.550585389137268} 08/30/2021 16:58:38 - INFO - __main__ - Step 20963: {'lr': 0.00048002056048947054, 'samples': 4024896, 'steps': 20962, 'loss/train': 1.3969539403915405} 08/30/2021 16:58:39 - INFO - __main__ - Step 20964: {'lr': 0.0004800184816519161, 'samples': 4025088, 'steps': 20963, 'loss/train': 1.7827870845794678} 08/30/2021 16:58:39 - INFO - __main__ - Step 20965: {'lr': 0.0004800164027107189, 'samples': 4025280, 'steps': 20964, 'loss/train': 0.1982184797525406} 08/30/2021 16:58:41 - INFO - __main__ - Step 20966: {'lr': 0.0004800143236658798, 'samples': 4025472, 'steps': 20965, 'loss/train': 1.8056644201278687} 08/30/2021 16:58:41 - INFO - __main__ - Step 20967: {'lr': 0.0004800122445173999, 'samples': 4025664, 'steps': 20966, 'loss/train': 1.2438685894012451} 08/30/2021 16:58:42 - INFO - __main__ - Step 20968: {'lr': 0.00048001016526528, 'samples': 4025856, 'steps': 20967, 'loss/train': 1.4209654331207275} 08/30/2021 16:58:42 - INFO - __main__ - Step 20969: {'lr': 0.00048000808590952106, 'samples': 4026048, 'steps': 20968, 'loss/train': 1.1624550819396973} 08/30/2021 16:58:42 - INFO - __main__ - Step 20970: {'lr': 0.0004800060064501239, 'samples': 4026240, 'steps': 20969, 'loss/train': 1.373073935508728} 08/30/2021 16:58:44 - INFO - __main__ - Step 20971: {'lr': 0.00048000392688708976, 'samples': 4026432, 'steps': 20970, 'loss/train': 1.401117205619812} 08/30/2021 16:58:44 - INFO - __main__ - Step 20972: {'lr': 0.00048000184722041934, 'samples': 4026624, 'steps': 20971, 'loss/train': 1.7493475675582886} 08/30/2021 16:58:45 - INFO - __main__ - Step 20973: {'lr': 0.00047999976745011366, 'samples': 4026816, 'steps': 20972, 'loss/train': 1.0928475856781006} 08/30/2021 16:58:45 - INFO - __main__ - Step 20974: {'lr': 0.0004799976875761736, 'samples': 4027008, 'steps': 20973, 'loss/train': 2.1853578090667725} 08/30/2021 16:58:45 - INFO - __main__ - Step 20975: {'lr': 0.00047999560759860006, 'samples': 4027200, 'steps': 20974, 'loss/train': 2.230820894241333} 08/30/2021 16:58:47 - INFO - __main__ - Step 20976: {'lr': 0.00047999352751739414, 'samples': 4027392, 'steps': 20975, 'loss/train': 1.414308786392212} 08/30/2021 16:58:48 - INFO - __main__ - Step 20977: {'lr': 0.0004799914473325567, 'samples': 4027584, 'steps': 20976, 'loss/train': 1.6380691528320312} 08/30/2021 16:58:48 - INFO - __main__ - Step 20978: {'lr': 0.00047998936704408865, 'samples': 4027776, 'steps': 20977, 'loss/train': 1.5667731761932373} 08/30/2021 16:58:48 - INFO - __main__ - Step 20979: {'lr': 0.00047998728665199085, 'samples': 4027968, 'steps': 20978, 'loss/train': 0.7598178386688232} 08/30/2021 16:58:49 - INFO - __main__ - Step 20980: {'lr': 0.00047998520615626447, 'samples': 4028160, 'steps': 20979, 'loss/train': 0.548076331615448} 08/30/2021 16:58:49 - INFO - __main__ - Step 20981: {'lr': 0.0004799831255569102, 'samples': 4028352, 'steps': 20980, 'loss/train': 3.950775384902954} 08/30/2021 16:58:51 - INFO - __main__ - Step 20982: {'lr': 0.00047998104485392915, 'samples': 4028544, 'steps': 20981, 'loss/train': 1.2458995580673218} 08/30/2021 16:58:51 - INFO - __main__ - Step 20983: {'lr': 0.0004799789640473221, 'samples': 4028736, 'steps': 20982, 'loss/train': 3.2928640842437744} 08/30/2021 16:58:51 - INFO - __main__ - Step 20984: {'lr': 0.0004799768831370902, 'samples': 4028928, 'steps': 20983, 'loss/train': 1.4735898971557617} 08/30/2021 16:58:52 - INFO - __main__ - Step 20985: {'lr': 0.0004799748021232342, 'samples': 4029120, 'steps': 20984, 'loss/train': 1.8679158687591553} 08/30/2021 16:58:52 - INFO - __main__ - Step 20986: {'lr': 0.00047997272100575505, 'samples': 4029312, 'steps': 20985, 'loss/train': 2.7078568935394287} 08/30/2021 16:58:54 - INFO - __main__ - Step 20987: {'lr': 0.00047997063978465383, 'samples': 4029504, 'steps': 20986, 'loss/train': 1.5304360389709473} 08/30/2021 16:58:54 - INFO - __main__ - Step 20988: {'lr': 0.0004799685584599313, 'samples': 4029696, 'steps': 20987, 'loss/train': 1.5792006254196167} 08/30/2021 16:58:54 - INFO - __main__ - Step 20989: {'lr': 0.00047996647703158857, 'samples': 4029888, 'steps': 20988, 'loss/train': 2.113802433013916} 08/30/2021 16:58:55 - INFO - __main__ - Step 20990: {'lr': 0.00047996439549962647, 'samples': 4030080, 'steps': 20989, 'loss/train': 1.8476831912994385} 08/30/2021 16:58:55 - INFO - __main__ - Step 20991: {'lr': 0.00047996231386404593, 'samples': 4030272, 'steps': 20990, 'loss/train': 1.592795729637146} 08/30/2021 16:58:57 - INFO - __main__ - Step 20992: {'lr': 0.00047996023212484797, 'samples': 4030464, 'steps': 20991, 'loss/train': 1.5453822612762451} 08/30/2021 16:58:57 - INFO - __main__ - Step 20993: {'lr': 0.00047995815028203346, 'samples': 4030656, 'steps': 20992, 'loss/train': 2.155550003051758} 08/30/2021 16:58:58 - INFO - __main__ - Step 20994: {'lr': 0.00047995606833560337, 'samples': 4030848, 'steps': 20993, 'loss/train': 3.0335333347320557} 08/30/2021 16:58:58 - INFO - __main__ - Step 20995: {'lr': 0.0004799539862855585, 'samples': 4031040, 'steps': 20994, 'loss/train': 1.8598829507827759} 08/30/2021 16:58:58 - INFO - __main__ - Step 20996: {'lr': 0.00047995190413190004, 'samples': 4031232, 'steps': 20995, 'loss/train': 0.11773476749658585} 08/30/2021 16:58:59 - INFO - __main__ - Step 20997: {'lr': 0.00047994982187462876, 'samples': 4031424, 'steps': 20996, 'loss/train': 1.9217010736465454} 08/30/2021 16:59:00 - INFO - __main__ - Step 20998: {'lr': 0.0004799477395137457, 'samples': 4031616, 'steps': 20997, 'loss/train': 2.0599071979522705} 08/30/2021 16:59:01 - INFO - __main__ - Step 20999: {'lr': 0.00047994565704925166, 'samples': 4031808, 'steps': 20998, 'loss/train': 1.5909682512283325} 08/30/2021 16:59:01 - INFO - __main__ - Step 21000: {'lr': 0.0004799435744811477, 'samples': 4032000, 'steps': 20999, 'loss/train': 1.0935367345809937} 08/30/2021 16:59:01 - INFO - __main__ - Step 21001: {'lr': 0.0004799414918094347, 'samples': 4032192, 'steps': 21000, 'loss/train': 1.9355828762054443} 08/30/2021 16:59:02 - INFO - __main__ - Step 21002: {'lr': 0.0004799394090341136, 'samples': 4032384, 'steps': 21001, 'loss/train': 1.5669392347335815} 08/30/2021 16:59:03 - INFO - __main__ - Step 21003: {'lr': 0.0004799373261551854, 'samples': 4032576, 'steps': 21002, 'loss/train': 1.6707897186279297} 08/30/2021 16:59:04 - INFO - __main__ - Step 21004: {'lr': 0.0004799352431726509, 'samples': 4032768, 'steps': 21003, 'loss/train': 1.8671692609786987} 08/30/2021 16:59:04 - INFO - __main__ - Step 21005: {'lr': 0.0004799331600865112, 'samples': 4032960, 'steps': 21004, 'loss/train': 1.4355348348617554} 08/30/2021 16:59:04 - INFO - __main__ - Step 21006: {'lr': 0.0004799310768967671, 'samples': 4033152, 'steps': 21005, 'loss/train': 1.6290297508239746} 08/30/2021 16:59:05 - INFO - __main__ - Step 21007: {'lr': 0.00047992899360341966, 'samples': 4033344, 'steps': 21006, 'loss/train': 1.5777473449707031} 08/30/2021 16:59:06 - INFO - __main__ - Step 21008: {'lr': 0.0004799269102064698, 'samples': 4033536, 'steps': 21007, 'loss/train': 1.8052923679351807} 08/30/2021 16:59:06 - INFO - __main__ - Step 21009: {'lr': 0.0004799248267059183, 'samples': 4033728, 'steps': 21008, 'loss/train': 1.715876579284668} 08/30/2021 16:59:07 - INFO - __main__ - Step 21010: {'lr': 0.0004799227431017663, 'samples': 4033920, 'steps': 21009, 'loss/train': 1.5748149156570435} 08/30/2021 16:59:07 - INFO - __main__ - Step 21011: {'lr': 0.0004799206593940147, 'samples': 4034112, 'steps': 21010, 'loss/train': 1.6504967212677002} 08/30/2021 16:59:08 - INFO - __main__ - Step 21012: {'lr': 0.0004799185755826644, 'samples': 4034304, 'steps': 21011, 'loss/train': 1.7354111671447754} 08/30/2021 16:59:09 - INFO - __main__ - Step 21013: {'lr': 0.00047991649166771624, 'samples': 4034496, 'steps': 21012, 'loss/train': 1.6346644163131714} 08/30/2021 16:59:10 - INFO - __main__ - Step 21014: {'lr': 0.00047991440764917127, 'samples': 4034688, 'steps': 21013, 'loss/train': 2.4204812049865723} 08/30/2021 16:59:10 - INFO - __main__ - Step 21015: {'lr': 0.0004799123235270305, 'samples': 4034880, 'steps': 21014, 'loss/train': 1.6461856365203857} 08/30/2021 16:59:10 - INFO - __main__ - Step 21016: {'lr': 0.0004799102393012947, 'samples': 4035072, 'steps': 21015, 'loss/train': 1.6606346368789673} 08/30/2021 16:59:11 - INFO - __main__ - Step 21017: {'lr': 0.0004799081549719649, 'samples': 4035264, 'steps': 21016, 'loss/train': 1.1760226488113403} 08/30/2021 16:59:12 - INFO - __main__ - Step 21018: {'lr': 0.0004799060705390421, 'samples': 4035456, 'steps': 21017, 'loss/train': 2.0579817295074463} 08/30/2021 16:59:12 - INFO - __main__ - Step 21019: {'lr': 0.00047990398600252713, 'samples': 4035648, 'steps': 21018, 'loss/train': 1.7861557006835938} 08/30/2021 16:59:13 - INFO - __main__ - Step 21020: {'lr': 0.00047990190136242103, 'samples': 4035840, 'steps': 21019, 'loss/train': 1.7574015855789185} 08/30/2021 16:59:13 - INFO - __main__ - Step 21021: {'lr': 0.0004798998166187246, 'samples': 4036032, 'steps': 21020, 'loss/train': 1.1989426612854004} 08/30/2021 16:59:14 - INFO - __main__ - Step 21022: {'lr': 0.0004798977317714389, 'samples': 4036224, 'steps': 21021, 'loss/train': 1.8363909721374512} 08/30/2021 16:59:16 - INFO - __main__ - Step 21023: {'lr': 0.00047989564682056487, 'samples': 4036416, 'steps': 21022, 'loss/train': 1.7746086120605469} 08/30/2021 16:59:16 - INFO - __main__ - Step 21024: {'lr': 0.0004798935617661033, 'samples': 4036608, 'steps': 21023, 'loss/train': 1.5361837148666382} 08/30/2021 16:59:16 - INFO - __main__ - Step 21025: {'lr': 0.0004798914766080553, 'samples': 4036800, 'steps': 21024, 'loss/train': 2.529196262359619} 08/30/2021 16:59:17 - INFO - __main__ - Step 21026: {'lr': 0.00047988939134642174, 'samples': 4036992, 'steps': 21025, 'loss/train': 1.467066764831543} 08/30/2021 16:59:17 - INFO - __main__ - Step 21027: {'lr': 0.00047988730598120356, 'samples': 4037184, 'steps': 21026, 'loss/train': 1.8944923877716064} 08/30/2021 16:59:19 - INFO - __main__ - Step 21028: {'lr': 0.00047988522051240173, 'samples': 4037376, 'steps': 21027, 'loss/train': 0.8948488831520081} 08/30/2021 16:59:19 - INFO - __main__ - Step 21029: {'lr': 0.0004798831349400172, 'samples': 4037568, 'steps': 21028, 'loss/train': 2.0099880695343018} 08/30/2021 16:59:19 - INFO - __main__ - Step 21030: {'lr': 0.0004798810492640508, 'samples': 4037760, 'steps': 21029, 'loss/train': 1.7088042497634888} 08/30/2021 16:59:20 - INFO - __main__ - Step 21031: {'lr': 0.00047987896348450354, 'samples': 4037952, 'steps': 21030, 'loss/train': 1.5720404386520386} 08/30/2021 16:59:20 - INFO - __main__ - Step 21032: {'lr': 0.00047987687760137646, 'samples': 4038144, 'steps': 21031, 'loss/train': 1.5632773637771606} 08/30/2021 16:59:21 - INFO - __main__ - Step 21033: {'lr': 0.00047987479161467033, 'samples': 4038336, 'steps': 21032, 'loss/train': 1.9008517265319824} 08/30/2021 16:59:22 - INFO - __main__ - Step 21034: {'lr': 0.0004798727055243862, 'samples': 4038528, 'steps': 21033, 'loss/train': 1.5379389524459839} 08/30/2021 16:59:23 - INFO - __main__ - Step 21035: {'lr': 0.000479870619330525, 'samples': 4038720, 'steps': 21034, 'loss/train': 0.876471757888794} 08/30/2021 16:59:23 - INFO - __main__ - Step 21036: {'lr': 0.0004798685330330876, 'samples': 4038912, 'steps': 21035, 'loss/train': 1.7168902158737183} 08/30/2021 16:59:23 - INFO - __main__ - Step 21037: {'lr': 0.000479866446632075, 'samples': 4039104, 'steps': 21036, 'loss/train': 1.406392216682434} 08/30/2021 16:59:24 - INFO - __main__ - Step 21038: {'lr': 0.00047986436012748815, 'samples': 4039296, 'steps': 21037, 'loss/train': 1.267569661140442} 08/30/2021 16:59:25 - INFO - __main__ - Step 21039: {'lr': 0.00047986227351932785, 'samples': 4039488, 'steps': 21038, 'loss/train': 1.684775710105896} 08/30/2021 16:59:26 - INFO - __main__ - Step 21040: {'lr': 0.00047986018680759525, 'samples': 4039680, 'steps': 21039, 'loss/train': 1.8256009817123413} 08/30/2021 16:59:26 - INFO - __main__ - Step 21041: {'lr': 0.00047985809999229125, 'samples': 4039872, 'steps': 21040, 'loss/train': 1.766939640045166} 08/30/2021 16:59:26 - INFO - __main__ - Step 21042: {'lr': 0.00047985601307341667, 'samples': 4040064, 'steps': 21041, 'loss/train': 1.1235382556915283} 08/30/2021 16:59:27 - INFO - __main__ - Step 21043: {'lr': 0.0004798539260509725, 'samples': 4040256, 'steps': 21042, 'loss/train': 1.7099907398223877} 08/30/2021 16:59:28 - INFO - __main__ - Step 21044: {'lr': 0.00047985183892495977, 'samples': 4040448, 'steps': 21043, 'loss/train': 1.3469377756118774} 08/30/2021 16:59:29 - INFO - __main__ - Step 21045: {'lr': 0.00047984975169537925, 'samples': 4040640, 'steps': 21044, 'loss/train': 0.8599517941474915} 08/30/2021 16:59:29 - INFO - __main__ - Step 21046: {'lr': 0.00047984766436223205, 'samples': 4040832, 'steps': 21045, 'loss/train': 1.3645668029785156} 08/30/2021 16:59:29 - INFO - __main__ - Step 21047: {'lr': 0.000479845576925519, 'samples': 4041024, 'steps': 21046, 'loss/train': 1.9667969942092896} 08/30/2021 16:59:30 - INFO - __main__ - Step 21048: {'lr': 0.00047984348938524113, 'samples': 4041216, 'steps': 21047, 'loss/train': 1.1815723180770874} 08/30/2021 16:59:31 - INFO - __main__ - Step 21049: {'lr': 0.00047984140174139926, 'samples': 4041408, 'steps': 21048, 'loss/train': 1.5975016355514526} 08/30/2021 16:59:32 - INFO - __main__ - Step 21050: {'lr': 0.0004798393139939945, 'samples': 4041600, 'steps': 21049, 'loss/train': 1.9904526472091675} 08/30/2021 16:59:32 - INFO - __main__ - Step 21051: {'lr': 0.0004798372261430276, 'samples': 4041792, 'steps': 21050, 'loss/train': 2.2192118167877197} 08/30/2021 16:59:33 - INFO - __main__ - Step 21052: {'lr': 0.00047983513818849967, 'samples': 4041984, 'steps': 21051, 'loss/train': 1.5575976371765137} 08/30/2021 16:59:33 - INFO - __main__ - Step 21053: {'lr': 0.0004798330501304115, 'samples': 4042176, 'steps': 21052, 'loss/train': 1.6344659328460693} 08/30/2021 16:59:34 - INFO - __main__ - Step 21054: {'lr': 0.00047983096196876413, 'samples': 4042368, 'steps': 21053, 'loss/train': 1.3212599754333496} 08/30/2021 16:59:35 - INFO - __main__ - Step 21055: {'lr': 0.00047982887370355846, 'samples': 4042560, 'steps': 21054, 'loss/train': 1.4824053049087524} 08/30/2021 16:59:35 - INFO - __main__ - Step 21056: {'lr': 0.0004798267853347955, 'samples': 4042752, 'steps': 21055, 'loss/train': 1.472094178199768} 08/30/2021 16:59:36 - INFO - __main__ - Step 21057: {'lr': 0.0004798246968624761, 'samples': 4042944, 'steps': 21056, 'loss/train': 1.0333106517791748} 08/30/2021 16:59:36 - INFO - __main__ - Step 21058: {'lr': 0.00047982260828660124, 'samples': 4043136, 'steps': 21057, 'loss/train': 1.8350293636322021} 08/30/2021 16:59:37 - INFO - __main__ - Step 21059: {'lr': 0.0004798205196071719, 'samples': 4043328, 'steps': 21058, 'loss/train': 1.284170150756836} 08/30/2021 16:59:38 - INFO - __main__ - Step 21060: {'lr': 0.00047981843082418884, 'samples': 4043520, 'steps': 21059, 'loss/train': 1.7510058879852295} 08/30/2021 16:59:38 - INFO - __main__ - Step 21061: {'lr': 0.0004798163419376533, 'samples': 4043712, 'steps': 21060, 'loss/train': 1.8825178146362305} 08/30/2021 16:59:39 - INFO - __main__ - Step 21062: {'lr': 0.00047981425294756595, 'samples': 4043904, 'steps': 21061, 'loss/train': 1.579464316368103} 08/30/2021 16:59:39 - INFO - __main__ - Step 21063: {'lr': 0.00047981216385392796, 'samples': 4044096, 'steps': 21062, 'loss/train': 1.7650657892227173} 08/30/2021 16:59:39 - INFO - __main__ - Step 21064: {'lr': 0.0004798100746567401, 'samples': 4044288, 'steps': 21063, 'loss/train': 1.6939369440078735} 08/30/2021 16:59:41 - INFO - __main__ - Step 21065: {'lr': 0.00047980798535600334, 'samples': 4044480, 'steps': 21064, 'loss/train': 1.627752661705017} 08/30/2021 16:59:41 - INFO - __main__ - Step 21066: {'lr': 0.00047980589595171866, 'samples': 4044672, 'steps': 21065, 'loss/train': 1.8847434520721436} 08/30/2021 16:59:42 - INFO - __main__ - Step 21067: {'lr': 0.000479803806443887, 'samples': 4044864, 'steps': 21066, 'loss/train': 1.7405376434326172} 08/30/2021 16:59:42 - INFO - __main__ - Step 21068: {'lr': 0.0004798017168325093, 'samples': 4045056, 'steps': 21067, 'loss/train': 1.945316195487976} 08/30/2021 16:59:42 - INFO - __main__ - Step 21069: {'lr': 0.0004797996271175865, 'samples': 4045248, 'steps': 21068, 'loss/train': 2.127417802810669} 08/30/2021 16:59:44 - INFO - __main__ - Step 21070: {'lr': 0.00047979753729911944, 'samples': 4045440, 'steps': 21069, 'loss/train': 1.282895803451538} 08/30/2021 16:59:44 - INFO - __main__ - Step 21071: {'lr': 0.00047979544737710925, 'samples': 4045632, 'steps': 21070, 'loss/train': 1.419189691543579} 08/30/2021 16:59:45 - INFO - __main__ - Step 21072: {'lr': 0.00047979335735155677, 'samples': 4045824, 'steps': 21071, 'loss/train': 1.1895549297332764} 08/30/2021 16:59:45 - INFO - __main__ - Step 21073: {'lr': 0.00047979126722246294, 'samples': 4046016, 'steps': 21072, 'loss/train': 1.095531940460205} 08/30/2021 16:59:45 - INFO - __main__ - Step 21074: {'lr': 0.0004797891769898287, 'samples': 4046208, 'steps': 21073, 'loss/train': 1.6173202991485596} 08/30/2021 16:59:47 - INFO - __main__ - Step 21075: {'lr': 0.00047978708665365503, 'samples': 4046400, 'steps': 21074, 'loss/train': 0.8989821672439575} 08/30/2021 16:59:48 - INFO - __main__ - Step 21076: {'lr': 0.0004797849962139428, 'samples': 4046592, 'steps': 21075, 'loss/train': 1.6845216751098633} 08/30/2021 16:59:48 - INFO - __main__ - Step 21077: {'lr': 0.00047978290567069306, 'samples': 4046784, 'steps': 21076, 'loss/train': 1.3722569942474365} 08/30/2021 16:59:49 - INFO - __main__ - Step 21078: {'lr': 0.00047978081502390656, 'samples': 4046976, 'steps': 21077, 'loss/train': 1.6358416080474854} 08/30/2021 16:59:49 - INFO - __main__ - Step 21079: {'lr': 0.0004797787242735845, 'samples': 4047168, 'steps': 21078, 'loss/train': 0.790678083896637} 08/30/2021 16:59:49 - INFO - __main__ - Step 21080: {'lr': 0.00047977663341972765, 'samples': 4047360, 'steps': 21079, 'loss/train': 2.2479915618896484} 08/30/2021 16:59:51 - INFO - __main__ - Step 21081: {'lr': 0.00047977454246233696, 'samples': 4047552, 'steps': 21080, 'loss/train': 1.709816575050354} 08/30/2021 16:59:51 - INFO - __main__ - Step 21082: {'lr': 0.00047977245140141354, 'samples': 4047744, 'steps': 21081, 'loss/train': 1.2808079719543457} 08/30/2021 16:59:52 - INFO - __main__ - Step 21083: {'lr': 0.00047977036023695807, 'samples': 4047936, 'steps': 21082, 'loss/train': 1.2697173357009888} 08/30/2021 16:59:52 - INFO - __main__ - Step 21084: {'lr': 0.00047976826896897165, 'samples': 4048128, 'steps': 21083, 'loss/train': 1.6275309324264526} 08/30/2021 16:59:52 - INFO - __main__ - Step 21085: {'lr': 0.0004797661775974552, 'samples': 4048320, 'steps': 21084, 'loss/train': 1.8187636137008667} 08/30/2021 16:59:54 - INFO - __main__ - Step 21086: {'lr': 0.00047976408612240964, 'samples': 4048512, 'steps': 21085, 'loss/train': 1.1905463933944702} 08/30/2021 16:59:54 - INFO - __main__ - Step 21087: {'lr': 0.00047976199454383595, 'samples': 4048704, 'steps': 21086, 'loss/train': 2.2994184494018555} 08/30/2021 16:59:55 - INFO - __main__ - Step 21088: {'lr': 0.00047975990286173504, 'samples': 4048896, 'steps': 21087, 'loss/train': 1.679661512374878} 08/30/2021 16:59:55 - INFO - __main__ - Step 21089: {'lr': 0.00047975781107610784, 'samples': 4049088, 'steps': 21088, 'loss/train': 0.8422901034355164} 08/30/2021 16:59:56 - INFO - __main__ - Step 21090: {'lr': 0.0004797557191869554, 'samples': 4049280, 'steps': 21089, 'loss/train': 1.6706513166427612} 08/30/2021 16:59:57 - INFO - __main__ - Step 21091: {'lr': 0.0004797536271942785, 'samples': 4049472, 'steps': 21090, 'loss/train': 1.8182177543640137} 08/30/2021 16:59:57 - INFO - __main__ - Step 21092: {'lr': 0.00047975153509807815, 'samples': 4049664, 'steps': 21091, 'loss/train': 1.387774109840393} 08/30/2021 16:59:58 - INFO - __main__ - Step 21093: {'lr': 0.0004797494428983553, 'samples': 4049856, 'steps': 21092, 'loss/train': 1.8198074102401733} 08/30/2021 16:59:58 - INFO - __main__ - Step 21094: {'lr': 0.000479747350595111, 'samples': 4050048, 'steps': 21093, 'loss/train': 1.0651737451553345} 08/30/2021 16:59:58 - INFO - __main__ - Step 21095: {'lr': 0.00047974525818834604, 'samples': 4050240, 'steps': 21094, 'loss/train': 1.5520455837249756} 08/30/2021 17:00:00 - INFO - __main__ - Step 21096: {'lr': 0.0004797431656780613, 'samples': 4050432, 'steps': 21095, 'loss/train': 1.5461673736572266} 08/30/2021 17:00:00 - INFO - __main__ - Step 21097: {'lr': 0.000479741073064258, 'samples': 4050624, 'steps': 21096, 'loss/train': 1.611256718635559} 08/30/2021 17:00:01 - INFO - __main__ - Step 21098: {'lr': 0.0004797389803469369, 'samples': 4050816, 'steps': 21097, 'loss/train': 1.0551233291625977} 08/30/2021 17:00:01 - INFO - __main__ - Step 21099: {'lr': 0.0004797368875260988, 'samples': 4051008, 'steps': 21098, 'loss/train': 0.49395498633384705} 08/30/2021 17:00:01 - INFO - __main__ - Step 21100: {'lr': 0.00047973479460174497, 'samples': 4051200, 'steps': 21099, 'loss/train': 1.0994573831558228} 08/30/2021 17:00:03 - INFO - __main__ - Step 21101: {'lr': 0.00047973270157387605, 'samples': 4051392, 'steps': 21100, 'loss/train': 1.73939847946167} 08/30/2021 17:00:04 - INFO - __main__ - Step 21102: {'lr': 0.0004797306084424932, 'samples': 4051584, 'steps': 21101, 'loss/train': 1.246307611465454} 08/30/2021 17:00:04 - INFO - __main__ - Step 21103: {'lr': 0.0004797285152075973, 'samples': 4051776, 'steps': 21102, 'loss/train': 1.6441198587417603} 08/30/2021 17:00:04 - INFO - __main__ - Step 21104: {'lr': 0.00047972642186918925, 'samples': 4051968, 'steps': 21103, 'loss/train': 1.1580528020858765} 08/30/2021 17:00:05 - INFO - __main__ - Step 21105: {'lr': 0.00047972432842727003, 'samples': 4052160, 'steps': 21104, 'loss/train': 2.2623374462127686} 08/30/2021 17:00:06 - INFO - __main__ - Step 21106: {'lr': 0.0004797222348818405, 'samples': 4052352, 'steps': 21105, 'loss/train': 2.3679537773132324} 08/30/2021 17:00:07 - INFO - __main__ - Step 21107: {'lr': 0.00047972014123290183, 'samples': 4052544, 'steps': 21106, 'loss/train': 1.9266010522842407} 08/30/2021 17:00:07 - INFO - __main__ - Step 21108: {'lr': 0.00047971804748045464, 'samples': 4052736, 'steps': 21107, 'loss/train': 1.6839982271194458} 08/30/2021 17:00:07 - INFO - __main__ - Step 21109: {'lr': 0.00047971595362450014, 'samples': 4052928, 'steps': 21108, 'loss/train': 1.119568109512329} 08/30/2021 17:00:08 - INFO - __main__ - Step 21110: {'lr': 0.00047971385966503923, 'samples': 4053120, 'steps': 21109, 'loss/train': 1.3776720762252808} 08/30/2021 17:00:08 - INFO - __main__ - Step 21111: {'lr': 0.0004797117656020727, 'samples': 4053312, 'steps': 21110, 'loss/train': 2.06646728515625} 08/30/2021 17:00:09 - INFO - __main__ - Step 21112: {'lr': 0.0004797096714356016, 'samples': 4053504, 'steps': 21111, 'loss/train': 1.4350123405456543} 08/30/2021 17:00:10 - INFO - __main__ - Step 21113: {'lr': 0.0004797075771656269, 'samples': 4053696, 'steps': 21112, 'loss/train': 6.5142292976379395} 08/30/2021 17:00:10 - INFO - __main__ - Step 21114: {'lr': 0.0004797054827921495, 'samples': 4053888, 'steps': 21113, 'loss/train': 1.6243597269058228} 08/30/2021 17:00:11 - INFO - __main__ - Step 21115: {'lr': 0.0004797033883151703, 'samples': 4054080, 'steps': 21114, 'loss/train': 1.6746667623519897} 08/30/2021 17:00:11 - INFO - __main__ - Step 21116: {'lr': 0.0004797012937346904, 'samples': 4054272, 'steps': 21115, 'loss/train': 1.171312928199768} 08/30/2021 17:00:12 - INFO - __main__ - Step 21117: {'lr': 0.0004796991990507106, 'samples': 4054464, 'steps': 21116, 'loss/train': 1.5629198551177979} 08/30/2021 17:00:13 - INFO - __main__ - Step 21118: {'lr': 0.00047969710426323185, 'samples': 4054656, 'steps': 21117, 'loss/train': 1.9510616064071655} 08/30/2021 17:00:13 - INFO - __main__ - Step 21119: {'lr': 0.0004796950093722552, 'samples': 4054848, 'steps': 21118, 'loss/train': 1.6718730926513672} 08/30/2021 17:00:14 - INFO - __main__ - Step 21120: {'lr': 0.00047969291437778143, 'samples': 4055040, 'steps': 21119, 'loss/train': 1.4792535305023193} 08/30/2021 17:00:14 - INFO - __main__ - Step 21121: {'lr': 0.00047969081927981165, 'samples': 4055232, 'steps': 21120, 'loss/train': 1.7120091915130615} 08/30/2021 17:00:15 - INFO - __main__ - Step 21122: {'lr': 0.0004796887240783467, 'samples': 4055424, 'steps': 21121, 'loss/train': 1.5738706588745117} 08/30/2021 17:00:16 - INFO - __main__ - Step 21123: {'lr': 0.0004796866287733875, 'samples': 4055616, 'steps': 21122, 'loss/train': 1.5310466289520264} 08/30/2021 17:00:16 - INFO - __main__ - Step 21124: {'lr': 0.0004796845333649352, 'samples': 4055808, 'steps': 21123, 'loss/train': 1.5130800008773804} 08/30/2021 17:00:17 - INFO - __main__ - Step 21125: {'lr': 0.00047968243785299046, 'samples': 4056000, 'steps': 21124, 'loss/train': 1.5441941022872925} 08/30/2021 17:00:17 - INFO - __main__ - Step 21126: {'lr': 0.0004796803422375544, 'samples': 4056192, 'steps': 21125, 'loss/train': 1.8245644569396973} 08/30/2021 17:00:17 - INFO - __main__ - Step 21127: {'lr': 0.0004796782465186279, 'samples': 4056384, 'steps': 21126, 'loss/train': 1.6191391944885254} 08/30/2021 17:00:19 - INFO - __main__ - Step 21128: {'lr': 0.00047967615069621197, 'samples': 4056576, 'steps': 21127, 'loss/train': 1.7516992092132568} 08/30/2021 17:00:19 - INFO - __main__ - Step 21129: {'lr': 0.0004796740547703075, 'samples': 4056768, 'steps': 21128, 'loss/train': 1.7212977409362793} 08/30/2021 17:00:20 - INFO - __main__ - Step 21130: {'lr': 0.00047967195874091547, 'samples': 4056960, 'steps': 21129, 'loss/train': 1.614676833152771} 08/30/2021 17:00:20 - INFO - __main__ - Step 21131: {'lr': 0.00047966986260803676, 'samples': 4057152, 'steps': 21130, 'loss/train': 0.2862565517425537} 08/30/2021 17:00:20 - INFO - __main__ - Step 21132: {'lr': 0.0004796677663716723, 'samples': 4057344, 'steps': 21131, 'loss/train': 1.4826680421829224} 08/30/2021 17:00:22 - INFO - __main__ - Step 21133: {'lr': 0.00047966567003182315, 'samples': 4057536, 'steps': 21132, 'loss/train': 1.4634411334991455} 08/30/2021 17:00:23 - INFO - __main__ - Step 21134: {'lr': 0.0004796635735884902, 'samples': 4057728, 'steps': 21133, 'loss/train': 1.0680818557739258} 08/30/2021 17:00:23 - INFO - __main__ - Step 21135: {'lr': 0.0004796614770416744, 'samples': 4057920, 'steps': 21134, 'loss/train': 1.6191478967666626} 08/30/2021 17:00:23 - INFO - __main__ - Step 21136: {'lr': 0.00047965938039137666, 'samples': 4058112, 'steps': 21135, 'loss/train': 1.191550850868225} 08/30/2021 17:00:24 - INFO - __main__ - Step 21137: {'lr': 0.000479657283637598, 'samples': 4058304, 'steps': 21136, 'loss/train': 1.3693060874938965} 08/30/2021 17:00:25 - INFO - __main__ - Step 21138: {'lr': 0.00047965518678033924, 'samples': 4058496, 'steps': 21137, 'loss/train': 0.7484496235847473} 08/30/2021 17:00:26 - INFO - __main__ - Step 21139: {'lr': 0.00047965308981960143, 'samples': 4058688, 'steps': 21138, 'loss/train': 1.3798872232437134} 08/30/2021 17:00:26 - INFO - __main__ - Step 21140: {'lr': 0.0004796509927553854, 'samples': 4058880, 'steps': 21139, 'loss/train': 1.4580025672912598} 08/30/2021 17:00:26 - INFO - __main__ - Step 21141: {'lr': 0.00047964889558769233, 'samples': 4059072, 'steps': 21140, 'loss/train': 2.0219380855560303} 08/30/2021 17:00:27 - INFO - __main__ - Step 21142: {'lr': 0.00047964679831652294, 'samples': 4059264, 'steps': 21141, 'loss/train': 1.180588960647583} 08/30/2021 17:00:28 - INFO - __main__ - Step 21143: {'lr': 0.00047964470094187815, 'samples': 4059456, 'steps': 21142, 'loss/train': 1.8486741781234741} 08/30/2021 17:00:29 - INFO - __main__ - Step 21144: {'lr': 0.0004796426034637591, 'samples': 4059648, 'steps': 21143, 'loss/train': 2.0078158378601074} 08/30/2021 17:00:29 - INFO - __main__ - Step 21145: {'lr': 0.0004796405058821666, 'samples': 4059840, 'steps': 21144, 'loss/train': 1.6045961380004883} 08/30/2021 17:00:30 - INFO - __main__ - Step 21146: {'lr': 0.0004796384081971017, 'samples': 4060032, 'steps': 21145, 'loss/train': 1.570224404335022} 08/30/2021 17:00:30 - INFO - __main__ - Step 21147: {'lr': 0.0004796363104085652, 'samples': 4060224, 'steps': 21146, 'loss/train': 2.0301578044891357} 08/30/2021 17:00:31 - INFO - __main__ - Step 21148: {'lr': 0.00047963421251655817, 'samples': 4060416, 'steps': 21147, 'loss/train': 1.9047797918319702} 08/30/2021 17:00:32 - INFO - __main__ - Step 21149: {'lr': 0.00047963211452108144, 'samples': 4060608, 'steps': 21148, 'loss/train': 1.92880380153656} 08/30/2021 17:00:32 - INFO - __main__ - Step 21150: {'lr': 0.0004796300164221361, 'samples': 4060800, 'steps': 21149, 'loss/train': 1.8172188997268677} 08/30/2021 17:00:33 - INFO - __main__ - Step 21151: {'lr': 0.00047962791821972296, 'samples': 4060992, 'steps': 21150, 'loss/train': 2.119884967803955} 08/30/2021 17:00:33 - INFO - __main__ - Step 21152: {'lr': 0.00047962581991384305, 'samples': 4061184, 'steps': 21151, 'loss/train': 1.7036997079849243} 08/30/2021 17:00:33 - INFO - __main__ - Step 21153: {'lr': 0.0004796237215044973, 'samples': 4061376, 'steps': 21152, 'loss/train': 1.6930289268493652} 08/30/2021 17:00:35 - INFO - __main__ - Step 21154: {'lr': 0.0004796216229916867, 'samples': 4061568, 'steps': 21153, 'loss/train': 1.6659579277038574} 08/30/2021 17:00:35 - INFO - __main__ - Step 21155: {'lr': 0.000479619524375412, 'samples': 4061760, 'steps': 21154, 'loss/train': 1.9712690114974976} 08/30/2021 17:00:36 - INFO - __main__ - Step 21156: {'lr': 0.0004796174256556744, 'samples': 4061952, 'steps': 21155, 'loss/train': 1.701959252357483} 08/30/2021 17:00:36 - INFO - __main__ - Step 21157: {'lr': 0.0004796153268324747, 'samples': 4062144, 'steps': 21156, 'loss/train': 1.6595348119735718} 08/30/2021 17:00:36 - INFO - __main__ - Step 21158: {'lr': 0.00047961322790581384, 'samples': 4062336, 'steps': 21157, 'loss/train': 1.7811648845672607} 08/30/2021 17:00:38 - INFO - __main__ - Step 21159: {'lr': 0.00047961112887569285, 'samples': 4062528, 'steps': 21158, 'loss/train': 1.2896312475204468} 08/30/2021 17:00:38 - INFO - __main__ - Step 21160: {'lr': 0.0004796090297421126, 'samples': 4062720, 'steps': 21159, 'loss/train': 1.0237380266189575} 08/30/2021 17:00:39 - INFO - __main__ - Step 21161: {'lr': 0.0004796069305050741, 'samples': 4062912, 'steps': 21160, 'loss/train': 1.6675056219100952} 08/30/2021 17:00:39 - INFO - __main__ - Step 21162: {'lr': 0.0004796048311645782, 'samples': 4063104, 'steps': 21161, 'loss/train': 1.378087043762207} 08/30/2021 17:00:39 - INFO - __main__ - Step 21163: {'lr': 0.00047960273172062596, 'samples': 4063296, 'steps': 21162, 'loss/train': 1.5852527618408203} 08/30/2021 17:00:41 - INFO - __main__ - Step 21164: {'lr': 0.00047960063217321824, 'samples': 4063488, 'steps': 21163, 'loss/train': 1.6329618692398071} 08/30/2021 17:00:41 - INFO - __main__ - Step 21165: {'lr': 0.0004795985325223561, 'samples': 4063680, 'steps': 21164, 'loss/train': 6.379885673522949} 08/30/2021 17:00:41 - INFO - __main__ - Step 21166: {'lr': 0.00047959643276804026, 'samples': 4063872, 'steps': 21165, 'loss/train': 1.1205564737319946} 08/30/2021 17:00:42 - INFO - __main__ - Step 21167: {'lr': 0.0004795943329102719, 'samples': 4064064, 'steps': 21166, 'loss/train': 1.3630781173706055} 08/30/2021 17:00:42 - INFO - __main__ - Step 21168: {'lr': 0.00047959223294905185, 'samples': 4064256, 'steps': 21167, 'loss/train': 1.8570128679275513} 08/30/2021 17:00:44 - INFO - __main__ - Step 21169: {'lr': 0.00047959013288438113, 'samples': 4064448, 'steps': 21168, 'loss/train': 1.3203643560409546} 08/30/2021 17:00:45 - INFO - __main__ - Step 21170: {'lr': 0.0004795880327162606, 'samples': 4064640, 'steps': 21169, 'loss/train': 1.1915868520736694} 08/30/2021 17:00:45 - INFO - __main__ - Step 21171: {'lr': 0.0004795859324446912, 'samples': 4064832, 'steps': 21170, 'loss/train': 0.10693927109241486} 08/30/2021 17:00:45 - INFO - __main__ - Step 21172: {'lr': 0.000479583832069674, 'samples': 4065024, 'steps': 21171, 'loss/train': 0.39779266715049744} 08/30/2021 17:00:46 - INFO - __main__ - Step 21173: {'lr': 0.00047958173159120984, 'samples': 4065216, 'steps': 21172, 'loss/train': 1.258679986000061} 08/30/2021 17:00:47 - INFO - __main__ - Step 21174: {'lr': 0.0004795796310092997, 'samples': 4065408, 'steps': 21173, 'loss/train': 1.0735141038894653} 08/30/2021 17:00:48 - INFO - __main__ - Step 21175: {'lr': 0.00047957753032394445, 'samples': 4065600, 'steps': 21174, 'loss/train': 1.6297802925109863} 08/30/2021 17:00:48 - INFO - __main__ - Step 21176: {'lr': 0.00047957542953514523, 'samples': 4065792, 'steps': 21175, 'loss/train': 1.7633613348007202} 08/30/2021 17:00:48 - INFO - __main__ - Step 21177: {'lr': 0.00047957332864290283, 'samples': 4065984, 'steps': 21176, 'loss/train': 2.5928258895874023} 08/30/2021 17:00:49 - INFO - __main__ - Step 21178: {'lr': 0.00047957122764721817, 'samples': 4066176, 'steps': 21177, 'loss/train': 1.5828711986541748} 08/30/2021 17:00:50 - INFO - __main__ - Step 21179: {'lr': 0.00047956912654809227, 'samples': 4066368, 'steps': 21178, 'loss/train': 1.8395119905471802} 08/30/2021 17:00:51 - INFO - __main__ - Step 21180: {'lr': 0.0004795670253455261, 'samples': 4066560, 'steps': 21179, 'loss/train': 1.6991662979125977} 08/30/2021 17:00:51 - INFO - __main__ - Step 21181: {'lr': 0.00047956492403952055, 'samples': 4066752, 'steps': 21180, 'loss/train': 2.4299497604370117} 08/30/2021 17:00:51 - INFO - __main__ - Step 21182: {'lr': 0.00047956282263007663, 'samples': 4066944, 'steps': 21181, 'loss/train': 1.1073206663131714} 08/30/2021 17:00:52 - INFO - __main__ - Step 21183: {'lr': 0.00047956072111719517, 'samples': 4067136, 'steps': 21182, 'loss/train': 0.08222738653421402} 08/30/2021 17:00:52 - INFO - __main__ - Step 21184: {'lr': 0.00047955861950087724, 'samples': 4067328, 'steps': 21183, 'loss/train': 1.4232593774795532} 08/30/2021 17:00:54 - INFO - __main__ - Step 21185: {'lr': 0.00047955651778112376, 'samples': 4067520, 'steps': 21184, 'loss/train': 1.5396087169647217} 08/30/2021 17:00:55 - INFO - __main__ - Step 21186: {'lr': 0.00047955441595793556, 'samples': 4067712, 'steps': 21185, 'loss/train': 1.8421236276626587} 08/30/2021 17:00:55 - INFO - __main__ - Step 21187: {'lr': 0.0004795523140313138, 'samples': 4067904, 'steps': 21186, 'loss/train': 1.4485394954681396} 08/30/2021 17:00:56 - INFO - __main__ - Step 21188: {'lr': 0.00047955021200125924, 'samples': 4068096, 'steps': 21187, 'loss/train': 1.758474349975586} 08/30/2021 17:00:56 - INFO - __main__ - Step 21189: {'lr': 0.0004795481098677729, 'samples': 4068288, 'steps': 21188, 'loss/train': 1.2918554544448853} 08/30/2021 17:00:57 - INFO - __main__ - Step 21190: {'lr': 0.00047954600763085577, 'samples': 4068480, 'steps': 21189, 'loss/train': 3.0587217807769775} 08/30/2021 17:00:58 - INFO - __main__ - Step 21191: {'lr': 0.0004795439052905087, 'samples': 4068672, 'steps': 21190, 'loss/train': 1.4779027700424194} 08/30/2021 17:00:58 - INFO - __main__ - Step 21192: {'lr': 0.0004795418028467327, 'samples': 4068864, 'steps': 21191, 'loss/train': 1.567817211151123} 08/30/2021 17:00:59 - INFO - __main__ - Step 21193: {'lr': 0.0004795397002995288, 'samples': 4069056, 'steps': 21192, 'loss/train': 1.5164625644683838} 08/30/2021 17:00:59 - INFO - __main__ - Step 21194: {'lr': 0.0004795375976488977, 'samples': 4069248, 'steps': 21193, 'loss/train': 1.7314308881759644} 08/30/2021 17:01:00 - INFO - __main__ - Step 21195: {'lr': 0.00047953549489484056, 'samples': 4069440, 'steps': 21194, 'loss/train': 1.236986756324768} 08/30/2021 17:01:01 - INFO - __main__ - Step 21196: {'lr': 0.0004795333920373583, 'samples': 4069632, 'steps': 21195, 'loss/train': 1.9612573385238647} 08/30/2021 17:01:01 - INFO - __main__ - Step 21197: {'lr': 0.00047953128907645185, 'samples': 4069824, 'steps': 21196, 'loss/train': 1.5197736024856567} 08/30/2021 17:01:02 - INFO - __main__ - Step 21198: {'lr': 0.000479529186012122, 'samples': 4070016, 'steps': 21197, 'loss/train': 1.5771238803863525} 08/30/2021 17:01:02 - INFO - __main__ - Step 21199: {'lr': 0.00047952708284437, 'samples': 4070208, 'steps': 21198, 'loss/train': 1.7781250476837158} 08/30/2021 17:01:02 - INFO - __main__ - Step 21200: {'lr': 0.0004795249795731966, 'samples': 4070400, 'steps': 21199, 'loss/train': 2.0518839359283447} 08/30/2021 17:01:04 - INFO - __main__ - Step 21201: {'lr': 0.00047952287619860273, 'samples': 4070592, 'steps': 21200, 'loss/train': 1.9785789251327515} 08/30/2021 17:01:04 - INFO - __main__ - Step 21202: {'lr': 0.0004795207727205895, 'samples': 4070784, 'steps': 21201, 'loss/train': 2.0732979774475098} 08/30/2021 17:01:05 - INFO - __main__ - Step 21203: {'lr': 0.00047951866913915767, 'samples': 4070976, 'steps': 21202, 'loss/train': 1.606500506401062} 08/30/2021 17:01:05 - INFO - __main__ - Step 21204: {'lr': 0.0004795165654543082, 'samples': 4071168, 'steps': 21203, 'loss/train': 0.6346612572669983} 08/30/2021 17:01:05 - INFO - __main__ - Step 21205: {'lr': 0.0004795144616660422, 'samples': 4071360, 'steps': 21204, 'loss/train': 1.6594130992889404} 08/30/2021 17:01:07 - INFO - __main__ - Step 21206: {'lr': 0.0004795123577743605, 'samples': 4071552, 'steps': 21205, 'loss/train': 1.4455301761627197} 08/30/2021 17:01:07 - INFO - __main__ - Step 21207: {'lr': 0.0004795102537792641, 'samples': 4071744, 'steps': 21206, 'loss/train': 1.718607783317566} 08/30/2021 17:01:08 - INFO - __main__ - Step 21208: {'lr': 0.000479508149680754, 'samples': 4071936, 'steps': 21207, 'loss/train': 2.245089530944824} 08/30/2021 17:01:08 - INFO - __main__ - Step 21209: {'lr': 0.0004795060454788309, 'samples': 4072128, 'steps': 21208, 'loss/train': 1.3547050952911377} 08/30/2021 17:01:08 - INFO - __main__ - Step 21210: {'lr': 0.000479503941173496, 'samples': 4072320, 'steps': 21209, 'loss/train': 1.5988857746124268} 08/30/2021 17:01:10 - INFO - __main__ - Step 21211: {'lr': 0.0004795018367647501, 'samples': 4072512, 'steps': 21210, 'loss/train': 1.6448431015014648} 08/30/2021 17:01:11 - INFO - __main__ - Step 21212: {'lr': 0.0004794997322525944, 'samples': 4072704, 'steps': 21211, 'loss/train': 1.3287367820739746} 08/30/2021 17:01:11 - INFO - __main__ - Step 21213: {'lr': 0.0004794976276370295, 'samples': 4072896, 'steps': 21212, 'loss/train': 1.5425965785980225} 08/30/2021 17:01:11 - INFO - __main__ - Step 21214: {'lr': 0.00047949552291805654, 'samples': 4073088, 'steps': 21213, 'loss/train': 1.610379934310913} 08/30/2021 17:01:12 - INFO - __main__ - Step 21215: {'lr': 0.0004794934180956764, 'samples': 4073280, 'steps': 21214, 'loss/train': 1.6742967367172241} 08/30/2021 17:01:13 - INFO - __main__ - Step 21216: {'lr': 0.00047949131316989016, 'samples': 4073472, 'steps': 21215, 'loss/train': 1.3280588388442993} 08/30/2021 17:01:14 - INFO - __main__ - Step 21217: {'lr': 0.0004794892081406986, 'samples': 4073664, 'steps': 21216, 'loss/train': 1.492698073387146} 08/30/2021 17:01:14 - INFO - __main__ - Step 21218: {'lr': 0.00047948710300810276, 'samples': 4073856, 'steps': 21217, 'loss/train': 0.12345721572637558} 08/30/2021 17:01:14 - INFO - __main__ - Step 21219: {'lr': 0.0004794849977721036, 'samples': 4074048, 'steps': 21218, 'loss/train': 0.09284964948892593} 08/30/2021 17:01:15 - INFO - __main__ - Step 21220: {'lr': 0.00047948289243270205, 'samples': 4074240, 'steps': 21219, 'loss/train': 0.8473216891288757} 08/30/2021 17:01:16 - INFO - __main__ - Step 21221: {'lr': 0.000479480786989899, 'samples': 4074432, 'steps': 21220, 'loss/train': 0.8647047877311707} 08/30/2021 17:01:17 - INFO - __main__ - Step 21222: {'lr': 0.0004794786814436955, 'samples': 4074624, 'steps': 21221, 'loss/train': 1.4903291463851929} 08/30/2021 17:01:17 - INFO - __main__ - Step 21223: {'lr': 0.0004794765757940924, 'samples': 4074816, 'steps': 21222, 'loss/train': 1.6796345710754395} 08/30/2021 17:01:17 - INFO - __main__ - Step 21224: {'lr': 0.00047947447004109066, 'samples': 4075008, 'steps': 21223, 'loss/train': 1.7726914882659912} 08/30/2021 17:01:18 - INFO - __main__ - Step 21225: {'lr': 0.0004794723641846914, 'samples': 4075200, 'steps': 21224, 'loss/train': 1.5440503358840942} 08/30/2021 17:01:19 - INFO - __main__ - Step 21226: {'lr': 0.0004794702582248953, 'samples': 4075392, 'steps': 21225, 'loss/train': 1.757509708404541} 08/30/2021 17:01:20 - INFO - __main__ - Step 21227: {'lr': 0.0004794681521617035, 'samples': 4075584, 'steps': 21226, 'loss/train': 1.6705842018127441} 08/30/2021 17:01:20 - INFO - __main__ - Step 21228: {'lr': 0.0004794660459951169, 'samples': 4075776, 'steps': 21227, 'loss/train': 1.9040278196334839} 08/30/2021 17:01:20 - INFO - __main__ - Step 21229: {'lr': 0.0004794639397251365, 'samples': 4075968, 'steps': 21228, 'loss/train': 2.0275213718414307} 08/30/2021 17:01:21 - INFO - __main__ - Step 21230: {'lr': 0.00047946183335176307, 'samples': 4076160, 'steps': 21229, 'loss/train': 2.0773203372955322} 08/30/2021 17:01:22 - INFO - __main__ - Step 21231: {'lr': 0.00047945972687499775, 'samples': 4076352, 'steps': 21230, 'loss/train': 1.6731206178665161} 08/30/2021 17:01:23 - INFO - __main__ - Step 21232: {'lr': 0.0004794576202948414, 'samples': 4076544, 'steps': 21231, 'loss/train': 1.5735644102096558} 08/30/2021 17:01:23 - INFO - __main__ - Step 21233: {'lr': 0.000479455513611295, 'samples': 4076736, 'steps': 21232, 'loss/train': 1.4337577819824219} 08/30/2021 17:01:23 - INFO - __main__ - Step 21234: {'lr': 0.00047945340682435943, 'samples': 4076928, 'steps': 21233, 'loss/train': 1.6810390949249268} 08/30/2021 17:01:24 - INFO - __main__ - Step 21235: {'lr': 0.00047945129993403577, 'samples': 4077120, 'steps': 21234, 'loss/train': 1.6172901391983032} 08/30/2021 17:01:26 - INFO - __main__ - Step 21236: {'lr': 0.00047944919294032486, 'samples': 4077312, 'steps': 21235, 'loss/train': 1.9328231811523438} 08/30/2021 17:01:27 - INFO - __main__ - Step 21237: {'lr': 0.00047944708584322763, 'samples': 4077504, 'steps': 21236, 'loss/train': 1.6461139917373657} 08/30/2021 17:01:27 - INFO - __main__ - Step 21238: {'lr': 0.00047944497864274517, 'samples': 4077696, 'steps': 21237, 'loss/train': 1.55856192111969} 08/30/2021 17:01:27 - INFO - __main__ - Step 21239: {'lr': 0.00047944287133887834, 'samples': 4077888, 'steps': 21238, 'loss/train': 2.0300607681274414} 08/30/2021 17:01:28 - INFO - __main__ - Step 21240: {'lr': 0.00047944076393162806, 'samples': 4078080, 'steps': 21239, 'loss/train': 1.751529335975647} 08/30/2021 17:01:28 - INFO - __main__ - Step 21241: {'lr': 0.00047943865642099525, 'samples': 4078272, 'steps': 21240, 'loss/train': 4.960762977600098} 08/30/2021 17:01:30 - INFO - __main__ - Step 21242: {'lr': 0.00047943654880698106, 'samples': 4078464, 'steps': 21241, 'loss/train': 1.579373836517334} 08/30/2021 17:01:30 - INFO - __main__ - Step 21243: {'lr': 0.00047943444108958623, 'samples': 4078656, 'steps': 21242, 'loss/train': 1.9401285648345947} 08/30/2021 17:01:30 - INFO - __main__ - Step 21244: {'lr': 0.00047943233326881176, 'samples': 4078848, 'steps': 21243, 'loss/train': 1.4131957292556763} 08/30/2021 17:01:31 - INFO - __main__ - Step 21245: {'lr': 0.00047943022534465866, 'samples': 4079040, 'steps': 21244, 'loss/train': 1.450485348701477} 08/30/2021 17:01:31 - INFO - __main__ - Step 21246: {'lr': 0.00047942811731712775, 'samples': 4079232, 'steps': 21245, 'loss/train': 2.1429929733276367} 08/30/2021 17:01:33 - INFO - __main__ - Step 21247: {'lr': 0.0004794260091862202, 'samples': 4079424, 'steps': 21246, 'loss/train': 1.7352527379989624} 08/30/2021 17:01:34 - INFO - __main__ - Step 21248: {'lr': 0.0004794239009519368, 'samples': 4079616, 'steps': 21247, 'loss/train': 0.8411003351211548} 08/30/2021 17:01:34 - INFO - __main__ - Step 21249: {'lr': 0.00047942179261427847, 'samples': 4079808, 'steps': 21248, 'loss/train': 1.6848970651626587} 08/30/2021 17:01:34 - INFO - __main__ - Step 21250: {'lr': 0.0004794196841732463, 'samples': 4080000, 'steps': 21249, 'loss/train': 1.6532396078109741} 08/30/2021 17:01:35 - INFO - __main__ - Step 21251: {'lr': 0.0004794175756288411, 'samples': 4080192, 'steps': 21250, 'loss/train': 1.8748997449874878} 08/30/2021 17:01:35 - INFO - __main__ - Step 21252: {'lr': 0.00047941546698106386, 'samples': 4080384, 'steps': 21251, 'loss/train': 1.5357121229171753} 08/30/2021 17:01:36 - INFO - __main__ - Step 21253: {'lr': 0.0004794133582299156, 'samples': 4080576, 'steps': 21252, 'loss/train': 1.219651699066162} 08/30/2021 17:01:37 - INFO - __main__ - Step 21254: {'lr': 0.0004794112493753972, 'samples': 4080768, 'steps': 21253, 'loss/train': 0.07995536178350449} 08/30/2021 17:01:37 - INFO - __main__ - Step 21255: {'lr': 0.0004794091404175097, 'samples': 4080960, 'steps': 21254, 'loss/train': 1.646977424621582} 08/30/2021 17:01:38 - INFO - __main__ - Step 21256: {'lr': 0.00047940703135625386, 'samples': 4081152, 'steps': 21255, 'loss/train': 1.963430643081665} 08/30/2021 17:01:38 - INFO - __main__ - Step 21257: {'lr': 0.0004794049221916308, 'samples': 4081344, 'steps': 21256, 'loss/train': 1.7822097539901733} 08/30/2021 17:01:40 - INFO - __main__ - Step 21258: {'lr': 0.00047940281292364146, 'samples': 4081536, 'steps': 21257, 'loss/train': 1.6705876588821411} 08/30/2021 17:01:40 - INFO - __main__ - Step 21259: {'lr': 0.0004794007035522867, 'samples': 4081728, 'steps': 21258, 'loss/train': 1.3476759195327759} 08/30/2021 17:01:40 - INFO - __main__ - Step 21260: {'lr': 0.0004793985940775676, 'samples': 4081920, 'steps': 21259, 'loss/train': 1.230209469795227} 08/30/2021 17:01:41 - INFO - __main__ - Step 21261: {'lr': 0.0004793964844994849, 'samples': 4082112, 'steps': 21260, 'loss/train': 1.8870868682861328} 08/30/2021 17:01:41 - INFO - __main__ - Step 21262: {'lr': 0.00047939437481803984, 'samples': 4082304, 'steps': 21261, 'loss/train': 1.3441853523254395} 08/30/2021 17:01:43 - INFO - __main__ - Step 21263: {'lr': 0.00047939226503323313, 'samples': 4082496, 'steps': 21262, 'loss/train': 1.5473906993865967} 08/30/2021 17:01:43 - INFO - __main__ - Step 21264: {'lr': 0.0004793901551450658, 'samples': 4082688, 'steps': 21263, 'loss/train': 1.3980252742767334} 08/30/2021 17:01:43 - INFO - __main__ - Step 21265: {'lr': 0.00047938804515353887, 'samples': 4082880, 'steps': 21264, 'loss/train': 1.3707047700881958} 08/30/2021 17:01:44 - INFO - __main__ - Step 21266: {'lr': 0.00047938593505865315, 'samples': 4083072, 'steps': 21265, 'loss/train': 1.526796579360962} 08/30/2021 17:01:44 - INFO - __main__ - Step 21267: {'lr': 0.00047938382486040963, 'samples': 4083264, 'steps': 21266, 'loss/train': 1.7023826837539673} 08/30/2021 17:01:46 - INFO - __main__ - Step 21268: {'lr': 0.0004793817145588094, 'samples': 4083456, 'steps': 21267, 'loss/train': 1.8478944301605225} 08/30/2021 17:01:46 - INFO - __main__ - Step 21269: {'lr': 0.0004793796041538533, 'samples': 4083648, 'steps': 21268, 'loss/train': 1.783738136291504} 08/30/2021 17:01:46 - INFO - __main__ - Step 21270: {'lr': 0.00047937749364554226, 'samples': 4083840, 'steps': 21269, 'loss/train': 1.3065569400787354} 08/30/2021 17:01:47 - INFO - __main__ - Step 21271: {'lr': 0.0004793753830338773, 'samples': 4084032, 'steps': 21270, 'loss/train': 1.9068880081176758} 08/30/2021 17:01:47 - INFO - __main__ - Step 21272: {'lr': 0.00047937327231885925, 'samples': 4084224, 'steps': 21271, 'loss/train': 1.276872992515564} 08/30/2021 17:01:49 - INFO - __main__ - Step 21273: {'lr': 0.0004793711615004892, 'samples': 4084416, 'steps': 21272, 'loss/train': 1.3377857208251953} 08/30/2021 17:01:49 - INFO - __main__ - Step 21274: {'lr': 0.000479369050578768, 'samples': 4084608, 'steps': 21273, 'loss/train': 1.797074317932129} 08/30/2021 17:01:50 - INFO - __main__ - Step 21275: {'lr': 0.0004793669395536967, 'samples': 4084800, 'steps': 21274, 'loss/train': 1.3432343006134033} 08/30/2021 17:01:50 - INFO - __main__ - Step 21276: {'lr': 0.00047936482842527616, 'samples': 4084992, 'steps': 21275, 'loss/train': 0.7991041541099548} 08/30/2021 17:01:50 - INFO - __main__ - Step 21277: {'lr': 0.00047936271719350743, 'samples': 4085184, 'steps': 21276, 'loss/train': 1.4765595197677612} 08/30/2021 17:01:51 - INFO - __main__ - Step 21278: {'lr': 0.0004793606058583913, 'samples': 4085376, 'steps': 21277, 'loss/train': 1.7148023843765259} 08/30/2021 17:01:52 - INFO - __main__ - Step 21279: {'lr': 0.00047935849441992887, 'samples': 4085568, 'steps': 21278, 'loss/train': 1.9708300828933716} 08/30/2021 17:01:53 - INFO - __main__ - Step 21280: {'lr': 0.00047935638287812104, 'samples': 4085760, 'steps': 21279, 'loss/train': 1.4684146642684937} 08/30/2021 17:01:53 - INFO - __main__ - Step 21281: {'lr': 0.00047935427123296884, 'samples': 4085952, 'steps': 21280, 'loss/train': 1.9510747194290161} 08/30/2021 17:01:53 - INFO - __main__ - Step 21282: {'lr': 0.000479352159484473, 'samples': 4086144, 'steps': 21281, 'loss/train': 2.0200250148773193} 08/30/2021 17:01:54 - INFO - __main__ - Step 21283: {'lr': 0.0004793500476326347, 'samples': 4086336, 'steps': 21282, 'loss/train': 1.6954630613327026} 08/30/2021 17:01:56 - INFO - __main__ - Step 21284: {'lr': 0.0004793479356774548, 'samples': 4086528, 'steps': 21283, 'loss/train': 1.9972984790802002} 08/30/2021 17:01:56 - INFO - __main__ - Step 21285: {'lr': 0.00047934582361893423, 'samples': 4086720, 'steps': 21284, 'loss/train': 0.32936790585517883} 08/30/2021 17:01:56 - INFO - __main__ - Step 21286: {'lr': 0.000479343711457074, 'samples': 4086912, 'steps': 21285, 'loss/train': 1.0872018337249756} 08/30/2021 17:01:57 - INFO - __main__ - Step 21287: {'lr': 0.00047934159919187504, 'samples': 4087104, 'steps': 21286, 'loss/train': 2.5703048706054688} 08/30/2021 17:01:57 - INFO - __main__ - Step 21288: {'lr': 0.0004793394868233383, 'samples': 4087296, 'steps': 21287, 'loss/train': 2.1616835594177246} 08/30/2021 17:01:59 - INFO - __main__ - Step 21289: {'lr': 0.0004793373743514647, 'samples': 4087488, 'steps': 21288, 'loss/train': 1.4142788648605347} 08/30/2021 17:01:59 - INFO - __main__ - Step 21290: {'lr': 0.0004793352617762552, 'samples': 4087680, 'steps': 21289, 'loss/train': 1.209137201309204} 08/30/2021 17:02:00 - INFO - __main__ - Step 21291: {'lr': 0.0004793331490977108, 'samples': 4087872, 'steps': 21290, 'loss/train': 1.85906982421875} 08/30/2021 17:02:00 - INFO - __main__ - Step 21292: {'lr': 0.0004793310363158324, 'samples': 4088064, 'steps': 21291, 'loss/train': 1.5463615655899048} 08/30/2021 17:02:00 - INFO - __main__ - Step 21293: {'lr': 0.00047932892343062103, 'samples': 4088256, 'steps': 21292, 'loss/train': 1.8606971502304077} 08/30/2021 17:02:01 - INFO - __main__ - Step 21294: {'lr': 0.00047932681044207757, 'samples': 4088448, 'steps': 21293, 'loss/train': 1.606949806213379} 08/30/2021 17:02:03 - INFO - __main__ - Step 21295: {'lr': 0.0004793246973502029, 'samples': 4088640, 'steps': 21294, 'loss/train': 1.5698412656784058} 08/30/2021 17:02:03 - INFO - __main__ - Step 21296: {'lr': 0.0004793225841549982, 'samples': 4088832, 'steps': 21295, 'loss/train': 1.4163990020751953} 08/30/2021 17:02:04 - INFO - __main__ - Step 21297: {'lr': 0.00047932047085646416, 'samples': 4089024, 'steps': 21296, 'loss/train': 1.8476744890213013} 08/30/2021 17:02:04 - INFO - __main__ - Step 21298: {'lr': 0.0004793183574546019, 'samples': 4089216, 'steps': 21297, 'loss/train': 1.4494456052780151} 08/30/2021 17:02:04 - INFO - __main__ - Step 21299: {'lr': 0.0004793162439494123, 'samples': 4089408, 'steps': 21298, 'loss/train': 2.0465006828308105} 08/30/2021 17:02:06 - INFO - __main__ - Step 21300: {'lr': 0.00047931413034089644, 'samples': 4089600, 'steps': 21299, 'loss/train': 1.387484073638916} 08/30/2021 17:02:06 - INFO - __main__ - Step 21301: {'lr': 0.00047931201662905503, 'samples': 4089792, 'steps': 21300, 'loss/train': 1.4023079872131348} 08/30/2021 17:02:07 - INFO - __main__ - Step 21302: {'lr': 0.00047930990281388927, 'samples': 4089984, 'steps': 21301, 'loss/train': 0.8452826738357544} 08/30/2021 17:02:07 - INFO - __main__ - Step 21303: {'lr': 0.00047930778889539996, 'samples': 4090176, 'steps': 21302, 'loss/train': 1.6854580640792847} 08/30/2021 17:02:07 - INFO - __main__ - Step 21304: {'lr': 0.00047930567487358813, 'samples': 4090368, 'steps': 21303, 'loss/train': 1.1011916399002075} 08/30/2021 17:02:09 - INFO - __main__ - Step 21305: {'lr': 0.00047930356074845466, 'samples': 4090560, 'steps': 21304, 'loss/train': 1.9323705434799194} 08/30/2021 17:02:09 - INFO - __main__ - Step 21306: {'lr': 0.0004793014465200005, 'samples': 4090752, 'steps': 21305, 'loss/train': 2.0195205211639404} 08/30/2021 17:02:10 - INFO - __main__ - Step 21307: {'lr': 0.0004792993321882267, 'samples': 4090944, 'steps': 21306, 'loss/train': 1.7164374589920044} 08/30/2021 17:02:10 - INFO - __main__ - Step 21308: {'lr': 0.0004792972177531342, 'samples': 4091136, 'steps': 21307, 'loss/train': 1.4937433004379272} 08/30/2021 17:02:10 - INFO - __main__ - Step 21309: {'lr': 0.0004792951032147239, 'samples': 4091328, 'steps': 21308, 'loss/train': 2.822166681289673} 08/30/2021 17:02:12 - INFO - __main__ - Step 21310: {'lr': 0.00047929298857299677, 'samples': 4091520, 'steps': 21309, 'loss/train': 1.6812840700149536} 08/30/2021 17:02:13 - INFO - __main__ - Step 21311: {'lr': 0.00047929087382795374, 'samples': 4091712, 'steps': 21310, 'loss/train': 1.897234559059143} 08/30/2021 17:02:13 - INFO - __main__ - Step 21312: {'lr': 0.0004792887589795957, 'samples': 4091904, 'steps': 21311, 'loss/train': 1.7426352500915527} 08/30/2021 17:02:13 - INFO - __main__ - Step 21313: {'lr': 0.00047928664402792376, 'samples': 4092096, 'steps': 21312, 'loss/train': 0.15013180673122406} 08/30/2021 17:02:14 - INFO - __main__ - Step 21314: {'lr': 0.0004792845289729388, 'samples': 4092288, 'steps': 21313, 'loss/train': 1.1719199419021606} 08/30/2021 17:02:14 - INFO - __main__ - Step 21315: {'lr': 0.00047928241381464177, 'samples': 4092480, 'steps': 21314, 'loss/train': 1.3982666730880737} 08/30/2021 17:02:16 - INFO - __main__ - Step 21316: {'lr': 0.0004792802985530337, 'samples': 4092672, 'steps': 21315, 'loss/train': 1.6239895820617676} 08/30/2021 17:02:16 - INFO - __main__ - Step 21317: {'lr': 0.0004792781831881153, 'samples': 4092864, 'steps': 21316, 'loss/train': 1.5348361730575562} 08/30/2021 17:02:16 - INFO - __main__ - Step 21318: {'lr': 0.0004792760677198878, 'samples': 4093056, 'steps': 21317, 'loss/train': 1.8626474142074585} 08/30/2021 17:02:17 - INFO - __main__ - Step 21319: {'lr': 0.00047927395214835203, 'samples': 4093248, 'steps': 21318, 'loss/train': 0.3177369236946106} 08/30/2021 17:02:17 - INFO - __main__ - Step 21320: {'lr': 0.0004792718364735089, 'samples': 4093440, 'steps': 21319, 'loss/train': 1.8100190162658691} 08/30/2021 17:02:19 - INFO - __main__ - Step 21321: {'lr': 0.00047926972069535945, 'samples': 4093632, 'steps': 21320, 'loss/train': 1.7661763429641724} 08/30/2021 17:02:19 - INFO - __main__ - Step 21322: {'lr': 0.00047926760481390465, 'samples': 4093824, 'steps': 21321, 'loss/train': 1.6134295463562012} 08/30/2021 17:02:19 - INFO - __main__ - Step 21323: {'lr': 0.00047926548882914533, 'samples': 4094016, 'steps': 21322, 'loss/train': 1.5928452014923096} 08/30/2021 17:02:20 - INFO - __main__ - Step 21324: {'lr': 0.0004792633727410826, 'samples': 4094208, 'steps': 21323, 'loss/train': 2.4081175327301025} 08/30/2021 17:02:20 - INFO - __main__ - Step 21325: {'lr': 0.0004792612565497172, 'samples': 4094400, 'steps': 21324, 'loss/train': 1.9535518884658813} 08/30/2021 17:02:22 - INFO - __main__ - Step 21326: {'lr': 0.00047925914025505036, 'samples': 4094592, 'steps': 21325, 'loss/train': 1.9374675750732422} 08/30/2021 17:02:22 - INFO - __main__ - Step 21327: {'lr': 0.0004792570238570828, 'samples': 4094784, 'steps': 21326, 'loss/train': 1.8380175828933716} 08/30/2021 17:02:22 - INFO - __main__ - Step 21328: {'lr': 0.00047925490735581557, 'samples': 4094976, 'steps': 21327, 'loss/train': 1.7587676048278809} 08/30/2021 17:02:23 - INFO - __main__ - Step 21329: {'lr': 0.00047925279075124963, 'samples': 4095168, 'steps': 21328, 'loss/train': 1.9400763511657715} 08/30/2021 17:02:23 - INFO - __main__ - Step 21330: {'lr': 0.00047925067404338596, 'samples': 4095360, 'steps': 21329, 'loss/train': 1.9073177576065063} 08/30/2021 17:02:25 - INFO - __main__ - Step 21331: {'lr': 0.00047924855723222536, 'samples': 4095552, 'steps': 21330, 'loss/train': 2.1923956871032715} 08/30/2021 17:02:25 - INFO - __main__ - Step 21332: {'lr': 0.000479246440317769, 'samples': 4095744, 'steps': 21331, 'loss/train': 1.843536138534546} 08/30/2021 17:02:26 - INFO - __main__ - Step 21333: {'lr': 0.00047924432330001776, 'samples': 4095936, 'steps': 21332, 'loss/train': 0.8867649435997009} 08/30/2021 17:02:26 - INFO - __main__ - Step 21334: {'lr': 0.0004792422061789725, 'samples': 4096128, 'steps': 21333, 'loss/train': 1.6919630765914917} 08/30/2021 17:02:26 - INFO - __main__ - Step 21335: {'lr': 0.0004792400889546342, 'samples': 4096320, 'steps': 21334, 'loss/train': 1.719007134437561} 08/30/2021 17:02:27 - INFO - __main__ - Step 21336: {'lr': 0.00047923797162700393, 'samples': 4096512, 'steps': 21335, 'loss/train': 1.297482967376709} 08/30/2021 17:02:28 - INFO - __main__ - Step 21337: {'lr': 0.0004792358541960826, 'samples': 4096704, 'steps': 21336, 'loss/train': 1.2600412368774414} 08/30/2021 17:02:29 - INFO - __main__ - Step 21338: {'lr': 0.000479233736661871, 'samples': 4096896, 'steps': 21337, 'loss/train': 6.028919696807861} 08/30/2021 17:02:29 - INFO - __main__ - Step 21339: {'lr': 0.0004792316190243703, 'samples': 4097088, 'steps': 21338, 'loss/train': 1.9485559463500977} 08/30/2021 17:02:29 - INFO - __main__ - Step 21340: {'lr': 0.0004792295012835814, 'samples': 4097280, 'steps': 21339, 'loss/train': 1.1493204832077026} 08/30/2021 17:02:30 - INFO - __main__ - Step 21341: {'lr': 0.0004792273834395052, 'samples': 4097472, 'steps': 21340, 'loss/train': 1.0050369501113892} 08/30/2021 17:02:31 - INFO - __main__ - Step 21342: {'lr': 0.0004792252654921426, 'samples': 4097664, 'steps': 21341, 'loss/train': 0.5513942837715149} 08/30/2021 17:02:32 - INFO - __main__ - Step 21343: {'lr': 0.00047922314744149475, 'samples': 4097856, 'steps': 21342, 'loss/train': 0.792652428150177} 08/30/2021 17:02:32 - INFO - __main__ - Step 21344: {'lr': 0.0004792210292875624, 'samples': 4098048, 'steps': 21343, 'loss/train': 1.4035366773605347} 08/30/2021 17:02:32 - INFO - __main__ - Step 21345: {'lr': 0.00047921891103034665, 'samples': 4098240, 'steps': 21344, 'loss/train': 1.606066346168518} 08/30/2021 17:02:33 - INFO - __main__ - Step 21346: {'lr': 0.0004792167926698483, 'samples': 4098432, 'steps': 21345, 'loss/train': 1.0577651262283325} 08/30/2021 17:02:33 - INFO - __main__ - Step 21347: {'lr': 0.0004792146742060685, 'samples': 4098624, 'steps': 21346, 'loss/train': 1.8724123239517212} 08/30/2021 17:02:35 - INFO - __main__ - Step 21348: {'lr': 0.00047921255563900813, 'samples': 4098816, 'steps': 21347, 'loss/train': 0.8765449523925781} 08/30/2021 17:02:36 - INFO - __main__ - Step 21349: {'lr': 0.000479210436968668, 'samples': 4099008, 'steps': 21348, 'loss/train': 2.4227795600891113} 08/30/2021 17:02:36 - INFO - __main__ - Step 21350: {'lr': 0.0004792083181950493, 'samples': 4099200, 'steps': 21349, 'loss/train': 1.9457899332046509} 08/30/2021 17:02:37 - INFO - __main__ - Step 21351: {'lr': 0.0004792061993181528, 'samples': 4099392, 'steps': 21350, 'loss/train': 1.9755337238311768} 08/30/2021 17:02:37 - INFO - __main__ - Step 21352: {'lr': 0.00047920408033797954, 'samples': 4099584, 'steps': 21351, 'loss/train': 1.3816801309585571} 08/30/2021 17:02:37 - INFO - __main__ - Step 21353: {'lr': 0.0004792019612545304, 'samples': 4099776, 'steps': 21352, 'loss/train': 1.5029605627059937} 08/30/2021 17:02:39 - INFO - __main__ - Step 21354: {'lr': 0.00047919984206780647, 'samples': 4099968, 'steps': 21353, 'loss/train': 1.8080503940582275} 08/30/2021 17:02:39 - INFO - __main__ - Step 21355: {'lr': 0.0004791977227778086, 'samples': 4100160, 'steps': 21354, 'loss/train': 1.749057650566101} 08/30/2021 17:02:40 - INFO - __main__ - Step 21356: {'lr': 0.00047919560338453783, 'samples': 4100352, 'steps': 21355, 'loss/train': 1.466055989265442} 08/30/2021 17:02:40 - INFO - __main__ - Step 21357: {'lr': 0.000479193483887995, 'samples': 4100544, 'steps': 21356, 'loss/train': 1.9566959142684937} 08/30/2021 17:02:40 - INFO - __main__ - Step 21358: {'lr': 0.0004791913642881811, 'samples': 4100736, 'steps': 21357, 'loss/train': 1.5667201280593872} 08/30/2021 17:02:42 - INFO - __main__ - Step 21359: {'lr': 0.00047918924458509717, 'samples': 4100928, 'steps': 21358, 'loss/train': 1.3140431642532349} 08/30/2021 17:02:42 - INFO - __main__ - Step 21360: {'lr': 0.00047918712477874404, 'samples': 4101120, 'steps': 21359, 'loss/train': 1.1423887014389038} 08/30/2021 17:02:43 - INFO - __main__ - Step 21361: {'lr': 0.00047918500486912276, 'samples': 4101312, 'steps': 21360, 'loss/train': 1.8200029134750366} 08/30/2021 17:02:43 - INFO - __main__ - Step 21362: {'lr': 0.00047918288485623427, 'samples': 4101504, 'steps': 21361, 'loss/train': 1.862265706062317} 08/30/2021 17:02:43 - INFO - __main__ - Step 21363: {'lr': 0.0004791807647400795, 'samples': 4101696, 'steps': 21362, 'loss/train': 1.2375341653823853} 08/30/2021 17:02:44 - INFO - __main__ - Step 21364: {'lr': 0.0004791786445206594, 'samples': 4101888, 'steps': 21363, 'loss/train': 1.9139901399612427} 08/30/2021 17:02:46 - INFO - __main__ - Step 21365: {'lr': 0.00047917652419797495, 'samples': 4102080, 'steps': 21364, 'loss/train': 1.5732009410858154} 08/30/2021 17:02:46 - INFO - __main__ - Step 21366: {'lr': 0.0004791744037720271, 'samples': 4102272, 'steps': 21365, 'loss/train': 1.735299825668335} 08/30/2021 17:02:47 - INFO - __main__ - Step 21367: {'lr': 0.00047917228324281683, 'samples': 4102464, 'steps': 21366, 'loss/train': 0.15128643810749054} 08/30/2021 17:02:47 - INFO - __main__ - Step 21368: {'lr': 0.00047917016261034496, 'samples': 4102656, 'steps': 21367, 'loss/train': 2.277677297592163} 08/30/2021 17:02:47 - INFO - __main__ - Step 21369: {'lr': 0.0004791680418746126, 'samples': 4102848, 'steps': 21368, 'loss/train': 1.6648612022399902} 08/30/2021 17:02:49 - INFO - __main__ - Step 21370: {'lr': 0.00047916592103562075, 'samples': 4103040, 'steps': 21369, 'loss/train': 1.4361931085586548} 08/30/2021 17:02:49 - INFO - __main__ - Step 21371: {'lr': 0.00047916380009337014, 'samples': 4103232, 'steps': 21370, 'loss/train': 1.1085540056228638} 08/30/2021 17:02:50 - INFO - __main__ - Step 21372: {'lr': 0.0004791616790478619, 'samples': 4103424, 'steps': 21371, 'loss/train': 1.6016608476638794} 08/30/2021 17:02:50 - INFO - __main__ - Step 21373: {'lr': 0.000479159557899097, 'samples': 4103616, 'steps': 21372, 'loss/train': 1.678863525390625} 08/30/2021 17:02:50 - INFO - __main__ - Step 21374: {'lr': 0.00047915743664707626, 'samples': 4103808, 'steps': 21373, 'loss/train': 1.0617471933364868} 08/30/2021 17:02:52 - INFO - __main__ - Step 21375: {'lr': 0.0004791553152918008, 'samples': 4104000, 'steps': 21374, 'loss/train': 1.9959217309951782} 08/30/2021 17:02:52 - INFO - __main__ - Step 21376: {'lr': 0.0004791531938332714, 'samples': 4104192, 'steps': 21375, 'loss/train': 1.020253300666809} 08/30/2021 17:02:53 - INFO - __main__ - Step 21377: {'lr': 0.0004791510722714891, 'samples': 4104384, 'steps': 21376, 'loss/train': 1.9851142168045044} 08/30/2021 17:02:53 - INFO - __main__ - Step 21378: {'lr': 0.000479148950606455, 'samples': 4104576, 'steps': 21377, 'loss/train': 1.816135287284851} 08/30/2021 17:02:53 - INFO - __main__ - Step 21379: {'lr': 0.00047914682883816977, 'samples': 4104768, 'steps': 21378, 'loss/train': 1.3393754959106445} 08/30/2021 17:02:54 - INFO - __main__ - Step 21380: {'lr': 0.00047914470696663457, 'samples': 4104960, 'steps': 21379, 'loss/train': 1.6631602048873901} 08/30/2021 17:02:55 - INFO - __main__ - Step 21381: {'lr': 0.00047914258499185037, 'samples': 4105152, 'steps': 21380, 'loss/train': 2.0020618438720703} 08/30/2021 17:02:56 - INFO - __main__ - Step 21382: {'lr': 0.000479140462913818, 'samples': 4105344, 'steps': 21381, 'loss/train': 1.894571304321289} 08/30/2021 17:02:56 - INFO - __main__ - Step 21383: {'lr': 0.0004791383407325384, 'samples': 4105536, 'steps': 21382, 'loss/train': 1.5259020328521729} 08/30/2021 17:02:56 - INFO - __main__ - Step 21384: {'lr': 0.0004791362184480127, 'samples': 4105728, 'steps': 21383, 'loss/train': 1.774632215499878} 08/30/2021 17:02:57 - INFO - __main__ - Step 21385: {'lr': 0.0004791340960602417, 'samples': 4105920, 'steps': 21384, 'loss/train': 1.8958078622817993} 08/30/2021 17:02:58 - INFO - __main__ - Step 21386: {'lr': 0.0004791319735692264, 'samples': 4106112, 'steps': 21385, 'loss/train': 1.8974725008010864} 08/30/2021 17:02:59 - INFO - __main__ - Step 21387: {'lr': 0.00047912985097496786, 'samples': 4106304, 'steps': 21386, 'loss/train': 1.1539653539657593} 08/30/2021 17:02:59 - INFO - __main__ - Step 21388: {'lr': 0.00047912772827746685, 'samples': 4106496, 'steps': 21387, 'loss/train': 1.3914194107055664} 08/30/2021 17:02:59 - INFO - __main__ - Step 21389: {'lr': 0.00047912560547672453, 'samples': 4106688, 'steps': 21388, 'loss/train': 0.16680869460105896} 08/30/2021 17:03:00 - INFO - __main__ - Step 21390: {'lr': 0.0004791234825727416, 'samples': 4106880, 'steps': 21389, 'loss/train': 1.2506459951400757} 08/30/2021 17:03:02 - INFO - __main__ - Step 21391: {'lr': 0.0004791213595655193, 'samples': 4107072, 'steps': 21390, 'loss/train': 1.9134588241577148} 08/30/2021 17:03:02 - INFO - __main__ - Step 21392: {'lr': 0.0004791192364550584, 'samples': 4107264, 'steps': 21391, 'loss/train': 1.4890049695968628} 08/30/2021 17:03:03 - INFO - __main__ - Step 21393: {'lr': 0.00047911711324135985, 'samples': 4107456, 'steps': 21392, 'loss/train': 1.4686373472213745} 08/30/2021 17:03:03 - INFO - __main__ - Step 21394: {'lr': 0.00047911498992442476, 'samples': 4107648, 'steps': 21393, 'loss/train': 1.9358030557632446} 08/30/2021 17:03:03 - INFO - __main__ - Step 21395: {'lr': 0.0004791128665042539, 'samples': 4107840, 'steps': 21394, 'loss/train': 1.6533355712890625} 08/30/2021 17:03:04 - INFO - __main__ - Step 21396: {'lr': 0.0004791107429808484, 'samples': 4108032, 'steps': 21395, 'loss/train': 1.1145198345184326} 08/30/2021 17:03:05 - INFO - __main__ - Step 21397: {'lr': 0.00047910861935420915, 'samples': 4108224, 'steps': 21396, 'loss/train': 3.0373291969299316} 08/30/2021 17:03:06 - INFO - __main__ - Step 21398: {'lr': 0.00047910649562433696, 'samples': 4108416, 'steps': 21397, 'loss/train': 1.8464752435684204} 08/30/2021 17:03:06 - INFO - __main__ - Step 21399: {'lr': 0.000479104371791233, 'samples': 4108608, 'steps': 21398, 'loss/train': 1.7620136737823486} 08/30/2021 17:03:06 - INFO - __main__ - Step 21400: {'lr': 0.0004791022478548982, 'samples': 4108800, 'steps': 21399, 'loss/train': 1.8300144672393799} 08/30/2021 17:03:07 - INFO - __main__ - Step 21401: {'lr': 0.0004791001238153334, 'samples': 4108992, 'steps': 21400, 'loss/train': 1.0013267993927002} 08/30/2021 17:03:09 - INFO - __main__ - Step 21402: {'lr': 0.00047909799967253957, 'samples': 4109184, 'steps': 21401, 'loss/train': 1.5706853866577148} 08/30/2021 17:03:09 - INFO - __main__ - Step 21403: {'lr': 0.00047909587542651776, 'samples': 4109376, 'steps': 21402, 'loss/train': 1.5404706001281738} 08/30/2021 17:03:10 - INFO - __main__ - Step 21404: {'lr': 0.00047909375107726894, 'samples': 4109568, 'steps': 21403, 'loss/train': 1.8566616773605347} 08/30/2021 17:03:10 - INFO - __main__ - Step 21405: {'lr': 0.000479091626624794, 'samples': 4109760, 'steps': 21404, 'loss/train': 5.978694915771484} 08/30/2021 17:03:10 - INFO - __main__ - Step 21406: {'lr': 0.00047908950206909385, 'samples': 4109952, 'steps': 21405, 'loss/train': 1.2774567604064941} 08/30/2021 17:03:11 - INFO - __main__ - Step 21407: {'lr': 0.0004790873774101695, 'samples': 4110144, 'steps': 21406, 'loss/train': 1.7675304412841797} 08/30/2021 17:03:12 - INFO - __main__ - Step 21408: {'lr': 0.00047908525264802194, 'samples': 4110336, 'steps': 21407, 'loss/train': 1.8614758253097534} 08/30/2021 17:03:13 - INFO - __main__ - Step 21409: {'lr': 0.00047908312778265213, 'samples': 4110528, 'steps': 21408, 'loss/train': 2.530635356903076} 08/30/2021 17:03:13 - INFO - __main__ - Step 21410: {'lr': 0.00047908100281406096, 'samples': 4110720, 'steps': 21409, 'loss/train': 0.6041358113288879} 08/30/2021 17:03:14 - INFO - __main__ - Step 21411: {'lr': 0.00047907887774224946, 'samples': 4110912, 'steps': 21410, 'loss/train': 1.3304941654205322} 08/30/2021 17:03:14 - INFO - __main__ - Step 21412: {'lr': 0.0004790767525672185, 'samples': 4111104, 'steps': 21411, 'loss/train': 1.4318076372146606} 08/30/2021 17:03:15 - INFO - __main__ - Step 21413: {'lr': 0.0004790746272889691, 'samples': 4111296, 'steps': 21412, 'loss/train': 1.6282638311386108} 08/30/2021 17:03:16 - INFO - __main__ - Step 21414: {'lr': 0.00047907250190750225, 'samples': 4111488, 'steps': 21413, 'loss/train': 1.9806156158447266} 08/30/2021 17:03:16 - INFO - __main__ - Step 21415: {'lr': 0.0004790703764228188, 'samples': 4111680, 'steps': 21414, 'loss/train': 1.3572484254837036} 08/30/2021 17:03:17 - INFO - __main__ - Step 21416: {'lr': 0.0004790682508349198, 'samples': 4111872, 'steps': 21415, 'loss/train': 1.2222541570663452} 08/30/2021 17:03:17 - INFO - __main__ - Step 21417: {'lr': 0.00047906612514380623, 'samples': 4112064, 'steps': 21416, 'loss/train': 1.5520838499069214} 08/30/2021 17:03:19 - INFO - __main__ - Step 21418: {'lr': 0.000479063999349479, 'samples': 4112256, 'steps': 21417, 'loss/train': 1.7586411237716675} 08/30/2021 17:03:20 - INFO - __main__ - Step 21419: {'lr': 0.00047906187345193895, 'samples': 4112448, 'steps': 21418, 'loss/train': 1.270230770111084} 08/30/2021 17:03:20 - INFO - __main__ - Step 21420: {'lr': 0.0004790597474511873, 'samples': 4112640, 'steps': 21419, 'loss/train': 1.4617196321487427} 08/30/2021 17:03:20 - INFO - __main__ - Step 21421: {'lr': 0.0004790576213472248, 'samples': 4112832, 'steps': 21420, 'loss/train': 1.1790966987609863} 08/30/2021 17:03:21 - INFO - __main__ - Step 21422: {'lr': 0.0004790554951400524, 'samples': 4113024, 'steps': 21421, 'loss/train': 1.1328461170196533} 08/30/2021 17:03:21 - INFO - __main__ - Step 21423: {'lr': 0.0004790533688296712, 'samples': 4113216, 'steps': 21422, 'loss/train': 1.5887815952301025} 08/30/2021 17:03:22 - INFO - __main__ - Step 21424: {'lr': 0.0004790512424160821, 'samples': 4113408, 'steps': 21423, 'loss/train': 1.9631133079528809} 08/30/2021 17:03:23 - INFO - __main__ - Step 21425: {'lr': 0.00047904911589928605, 'samples': 4113600, 'steps': 21424, 'loss/train': 1.9130054712295532} 08/30/2021 17:03:23 - INFO - __main__ - Step 21426: {'lr': 0.00047904698927928404, 'samples': 4113792, 'steps': 21425, 'loss/train': 1.599796175956726} 08/30/2021 17:03:23 - INFO - __main__ - Step 21427: {'lr': 0.0004790448625560769, 'samples': 4113984, 'steps': 21426, 'loss/train': 1.6329631805419922} 08/30/2021 17:03:24 - INFO - __main__ - Step 21428: {'lr': 0.0004790427357296657, 'samples': 4114176, 'steps': 21427, 'loss/train': 1.3552738428115845} 08/30/2021 17:03:26 - INFO - __main__ - Step 21429: {'lr': 0.0004790406088000514, 'samples': 4114368, 'steps': 21428, 'loss/train': 1.5520470142364502} 08/30/2021 17:03:26 - INFO - __main__ - Step 21430: {'lr': 0.00047903848176723493, 'samples': 4114560, 'steps': 21429, 'loss/train': 1.6015326976776123} 08/30/2021 17:03:27 - INFO - __main__ - Step 21431: {'lr': 0.0004790363546312172, 'samples': 4114752, 'steps': 21430, 'loss/train': 1.2645312547683716} 08/30/2021 17:03:27 - INFO - __main__ - Step 21432: {'lr': 0.0004790342273919993, 'samples': 4114944, 'steps': 21431, 'loss/train': 1.4015811681747437} 08/30/2021 17:03:27 - INFO - __main__ - Step 21433: {'lr': 0.00047903210004958207, 'samples': 4115136, 'steps': 21432, 'loss/train': 2.077160120010376} 08/30/2021 17:03:28 - INFO - __main__ - Step 21434: {'lr': 0.0004790299726039665, 'samples': 4115328, 'steps': 21433, 'loss/train': 1.6486338376998901} 08/30/2021 17:03:29 - INFO - __main__ - Step 21435: {'lr': 0.0004790278450551536, 'samples': 4115520, 'steps': 21434, 'loss/train': 0.08832631260156631} 08/30/2021 17:03:30 - INFO - __main__ - Step 21436: {'lr': 0.00047902571740314427, 'samples': 4115712, 'steps': 21435, 'loss/train': 2.3777639865875244} 08/30/2021 17:03:30 - INFO - __main__ - Step 21437: {'lr': 0.00047902358964793944, 'samples': 4115904, 'steps': 21436, 'loss/train': 1.1027485132217407} 08/30/2021 17:03:30 - INFO - __main__ - Step 21438: {'lr': 0.0004790214617895402, 'samples': 4116096, 'steps': 21437, 'loss/train': 2.061546564102173} 08/30/2021 17:03:31 - INFO - __main__ - Step 21439: {'lr': 0.0004790193338279474, 'samples': 4116288, 'steps': 21438, 'loss/train': 1.7133933305740356} 08/30/2021 17:03:32 - INFO - __main__ - Step 21440: {'lr': 0.000479017205763162, 'samples': 4116480, 'steps': 21439, 'loss/train': 1.7539247274398804} 08/30/2021 17:03:33 - INFO - __main__ - Step 21441: {'lr': 0.000479015077595185, 'samples': 4116672, 'steps': 21440, 'loss/train': 1.705939769744873} 08/30/2021 17:03:33 - INFO - __main__ - Step 21442: {'lr': 0.0004790129493240173, 'samples': 4116864, 'steps': 21441, 'loss/train': 1.0331511497497559} 08/30/2021 17:03:33 - INFO - __main__ - Step 21443: {'lr': 0.0004790108209496599, 'samples': 4117056, 'steps': 21442, 'loss/train': 4.733749866485596} 08/30/2021 17:03:34 - INFO - __main__ - Step 21444: {'lr': 0.00047900869247211384, 'samples': 4117248, 'steps': 21443, 'loss/train': 1.3099116086959839} 08/30/2021 17:03:36 - INFO - __main__ - Step 21445: {'lr': 0.0004790065638913799, 'samples': 4117440, 'steps': 21444, 'loss/train': 0.6812911033630371} 08/30/2021 17:03:36 - INFO - __main__ - Step 21446: {'lr': 0.00047900443520745915, 'samples': 4117632, 'steps': 21445, 'loss/train': 1.9747036695480347} 08/30/2021 17:03:36 - INFO - __main__ - Step 21447: {'lr': 0.0004790023064203526, 'samples': 4117824, 'steps': 21446, 'loss/train': 1.5440456867218018} 08/30/2021 17:03:37 - INFO - __main__ - Step 21448: {'lr': 0.00047900017753006106, 'samples': 4118016, 'steps': 21447, 'loss/train': 1.5677807331085205} 08/30/2021 17:03:37 - INFO - __main__ - Step 21449: {'lr': 0.0004789980485365857, 'samples': 4118208, 'steps': 21448, 'loss/train': 1.4878294467926025} 08/30/2021 17:03:38 - INFO - __main__ - Step 21450: {'lr': 0.00047899591943992726, 'samples': 4118400, 'steps': 21449, 'loss/train': 1.6379958391189575} 08/30/2021 17:03:39 - INFO - __main__ - Step 21451: {'lr': 0.0004789937902400868, 'samples': 4118592, 'steps': 21450, 'loss/train': 0.2603890299797058} 08/30/2021 17:03:39 - INFO - __main__ - Step 21452: {'lr': 0.00047899166093706523, 'samples': 4118784, 'steps': 21451, 'loss/train': 1.7019600868225098} 08/30/2021 17:03:40 - INFO - __main__ - Step 21453: {'lr': 0.0004789895315308636, 'samples': 4118976, 'steps': 21452, 'loss/train': 1.7137532234191895} 08/30/2021 17:03:40 - INFO - __main__ - Step 21454: {'lr': 0.00047898740202148284, 'samples': 4119168, 'steps': 21453, 'loss/train': 1.0620163679122925} 08/30/2021 17:03:41 - INFO - __main__ - Step 21455: {'lr': 0.0004789852724089239, 'samples': 4119360, 'steps': 21454, 'loss/train': 1.5766828060150146} 08/30/2021 17:03:42 - INFO - __main__ - Step 21456: {'lr': 0.00047898314269318766, 'samples': 4119552, 'steps': 21455, 'loss/train': 1.6099308729171753} 08/30/2021 17:03:43 - INFO - __main__ - Step 21457: {'lr': 0.00047898101287427523, 'samples': 4119744, 'steps': 21456, 'loss/train': 1.6593270301818848} 08/30/2021 17:03:43 - INFO - __main__ - Step 21458: {'lr': 0.0004789788829521874, 'samples': 4119936, 'steps': 21457, 'loss/train': 1.2930656671524048} 08/30/2021 17:03:44 - INFO - __main__ - Step 21459: {'lr': 0.0004789767529269253, 'samples': 4120128, 'steps': 21458, 'loss/train': 1.334293246269226} 08/30/2021 17:03:44 - INFO - __main__ - Step 21460: {'lr': 0.0004789746227984897, 'samples': 4120320, 'steps': 21459, 'loss/train': 1.5533400774002075} 08/30/2021 17:03:46 - INFO - __main__ - Step 21461: {'lr': 0.0004789724925668818, 'samples': 4120512, 'steps': 21460, 'loss/train': 1.022534728050232} 08/30/2021 17:03:46 - INFO - __main__ - Step 21462: {'lr': 0.00047897036223210234, 'samples': 4120704, 'steps': 21461, 'loss/train': 1.3876748085021973} 08/30/2021 17:03:46 - INFO - __main__ - Step 21463: {'lr': 0.00047896823179415237, 'samples': 4120896, 'steps': 21462, 'loss/train': 1.795861005783081} 08/30/2021 17:03:47 - INFO - __main__ - Step 21464: {'lr': 0.0004789661012530329, 'samples': 4121088, 'steps': 21463, 'loss/train': 1.9045308828353882} 08/30/2021 17:03:47 - INFO - __main__ - Step 21465: {'lr': 0.00047896397060874485, 'samples': 4121280, 'steps': 21464, 'loss/train': 1.2129464149475098} 08/30/2021 17:03:47 - INFO - __main__ - Step 21466: {'lr': 0.0004789618398612891, 'samples': 4121472, 'steps': 21465, 'loss/train': 1.1078848838806152} 08/30/2021 17:03:49 - INFO - __main__ - Step 21467: {'lr': 0.0004789597090106667, 'samples': 4121664, 'steps': 21466, 'loss/train': 1.749743103981018} 08/30/2021 17:03:50 - INFO - __main__ - Step 21468: {'lr': 0.00047895757805687864, 'samples': 4121856, 'steps': 21467, 'loss/train': 2.036487102508545} 08/30/2021 17:03:50 - INFO - __main__ - Step 21469: {'lr': 0.0004789554469999258, 'samples': 4122048, 'steps': 21468, 'loss/train': 1.7220492362976074} 08/30/2021 17:03:50 - INFO - __main__ - Step 21470: {'lr': 0.0004789533158398091, 'samples': 4122240, 'steps': 21469, 'loss/train': 1.6133811473846436} 08/30/2021 17:03:51 - INFO - __main__ - Step 21471: {'lr': 0.00047895118457652965, 'samples': 4122432, 'steps': 21470, 'loss/train': 1.4600428342819214} 08/30/2021 17:03:51 - INFO - __main__ - Step 21472: {'lr': 0.0004789490532100883, 'samples': 4122624, 'steps': 21471, 'loss/train': 0.05137605592608452} 08/30/2021 17:03:53 - INFO - __main__ - Step 21473: {'lr': 0.000478946921740486, 'samples': 4122816, 'steps': 21472, 'loss/train': 1.4794323444366455} 08/30/2021 17:03:53 - INFO - __main__ - Step 21474: {'lr': 0.0004789447901677238, 'samples': 4123008, 'steps': 21473, 'loss/train': 1.8282737731933594} 08/30/2021 17:03:53 - INFO - __main__ - Step 21475: {'lr': 0.00047894265849180264, 'samples': 4123200, 'steps': 21474, 'loss/train': 0.7590158581733704} 08/30/2021 17:03:54 - INFO - __main__ - Step 21476: {'lr': 0.00047894052671272337, 'samples': 4123392, 'steps': 21475, 'loss/train': 1.4974853992462158} 08/30/2021 17:03:54 - INFO - __main__ - Step 21477: {'lr': 0.0004789383948304871, 'samples': 4123584, 'steps': 21476, 'loss/train': 1.531650185585022} 08/30/2021 17:03:56 - INFO - __main__ - Step 21478: {'lr': 0.00047893626284509466, 'samples': 4123776, 'steps': 21477, 'loss/train': 1.5932615995407104} 08/30/2021 17:03:56 - INFO - __main__ - Step 21479: {'lr': 0.0004789341307565471, 'samples': 4123968, 'steps': 21478, 'loss/train': 1.7813539505004883} 08/30/2021 17:03:56 - INFO - __main__ - Step 21480: {'lr': 0.0004789319985648454, 'samples': 4124160, 'steps': 21479, 'loss/train': 1.3085589408874512} 08/30/2021 17:03:57 - INFO - __main__ - Step 21481: {'lr': 0.0004789298662699905, 'samples': 4124352, 'steps': 21480, 'loss/train': 1.8414041996002197} 08/30/2021 17:03:57 - INFO - __main__ - Step 21482: {'lr': 0.0004789277338719832, 'samples': 4124544, 'steps': 21481, 'loss/train': 0.3708147406578064} 08/30/2021 17:03:59 - INFO - __main__ - Step 21483: {'lr': 0.0004789256013708246, 'samples': 4124736, 'steps': 21482, 'loss/train': 1.0991530418395996} 08/30/2021 17:03:59 - INFO - __main__ - Step 21484: {'lr': 0.0004789234687665158, 'samples': 4124928, 'steps': 21483, 'loss/train': 1.7097718715667725} 08/30/2021 17:04:00 - INFO - __main__ - Step 21485: {'lr': 0.0004789213360590575, 'samples': 4125120, 'steps': 21484, 'loss/train': 1.0717169046401978} 08/30/2021 17:04:00 - INFO - __main__ - Step 21486: {'lr': 0.00047891920324845085, 'samples': 4125312, 'steps': 21485, 'loss/train': 1.573041558265686} 08/30/2021 17:04:00 - INFO - __main__ - Step 21487: {'lr': 0.00047891707033469665, 'samples': 4125504, 'steps': 21486, 'loss/train': 1.5038706064224243} 08/30/2021 17:04:01 - INFO - __main__ - Step 21488: {'lr': 0.00047891493731779607, 'samples': 4125696, 'steps': 21487, 'loss/train': 2.181943893432617} 08/30/2021 17:04:02 - INFO - __main__ - Step 21489: {'lr': 0.00047891280419774985, 'samples': 4125888, 'steps': 21488, 'loss/train': 1.6918127536773682} 08/30/2021 17:04:03 - INFO - __main__ - Step 21490: {'lr': 0.0004789106709745591, 'samples': 4126080, 'steps': 21489, 'loss/train': 1.6460556983947754} 08/30/2021 17:04:03 - INFO - __main__ - Step 21491: {'lr': 0.0004789085376482247, 'samples': 4126272, 'steps': 21490, 'loss/train': 1.7745941877365112} 08/30/2021 17:04:03 - INFO - __main__ - Step 21492: {'lr': 0.00047890640421874775, 'samples': 4126464, 'steps': 21491, 'loss/train': 1.7836967706680298} 08/30/2021 17:04:05 - INFO - __main__ - Step 21493: {'lr': 0.000478904270686129, 'samples': 4126656, 'steps': 21492, 'loss/train': 2.0360591411590576} 08/30/2021 17:04:06 - INFO - __main__ - Step 21494: {'lr': 0.00047890213705036955, 'samples': 4126848, 'steps': 21493, 'loss/train': 1.0421425104141235} 08/30/2021 17:04:06 - INFO - __main__ - Step 21495: {'lr': 0.00047890000331147033, 'samples': 4127040, 'steps': 21494, 'loss/train': 1.2720959186553955} 08/30/2021 17:04:07 - INFO - __main__ - Step 21496: {'lr': 0.0004788978694694323, 'samples': 4127232, 'steps': 21495, 'loss/train': 1.3424983024597168} 08/30/2021 17:04:07 - INFO - __main__ - Step 21497: {'lr': 0.0004788957355242564, 'samples': 4127424, 'steps': 21496, 'loss/train': 1.0823028087615967} 08/30/2021 17:04:07 - INFO - __main__ - Step 21498: {'lr': 0.00047889360147594363, 'samples': 4127616, 'steps': 21497, 'loss/train': 2.1946630477905273} 08/30/2021 17:04:09 - INFO - __main__ - Step 21499: {'lr': 0.00047889146732449497, 'samples': 4127808, 'steps': 21498, 'loss/train': 1.4539885520935059} 08/30/2021 17:04:09 - INFO - __main__ - Step 21500: {'lr': 0.00047888933306991136, 'samples': 4128000, 'steps': 21499, 'loss/train': 1.671066403388977} 08/30/2021 17:04:10 - INFO - __main__ - Step 21501: {'lr': 0.00047888719871219367, 'samples': 4128192, 'steps': 21500, 'loss/train': 2.1623952388763428} 08/30/2021 17:04:10 - INFO - __main__ - Step 21502: {'lr': 0.00047888506425134293, 'samples': 4128384, 'steps': 21501, 'loss/train': 1.7121566534042358} 08/30/2021 17:04:10 - INFO - __main__ - Step 21503: {'lr': 0.0004788829296873601, 'samples': 4128576, 'steps': 21502, 'loss/train': 0.30309751629829407} 08/30/2021 17:04:12 - INFO - __main__ - Step 21504: {'lr': 0.0004788807950202463, 'samples': 4128768, 'steps': 21503, 'loss/train': 1.3717628717422485} 08/30/2021 17:04:13 - INFO - __main__ - Step 21505: {'lr': 0.00047887866025000226, 'samples': 4128960, 'steps': 21504, 'loss/train': 1.7132471799850464} 08/30/2021 17:04:13 - INFO - __main__ - Step 21506: {'lr': 0.000478876525376629, 'samples': 4129152, 'steps': 21505, 'loss/train': 1.2056117057800293} 08/30/2021 17:04:13 - INFO - __main__ - Step 21507: {'lr': 0.00047887439040012755, 'samples': 4129344, 'steps': 21506, 'loss/train': 1.7914046049118042} 08/30/2021 17:04:14 - INFO - __main__ - Step 21508: {'lr': 0.0004788722553204988, 'samples': 4129536, 'steps': 21507, 'loss/train': 1.4132291078567505} 08/30/2021 17:04:14 - INFO - __main__ - Step 21509: {'lr': 0.0004788701201377438, 'samples': 4129728, 'steps': 21508, 'loss/train': 1.8986529111862183} 08/30/2021 17:04:15 - INFO - __main__ - Step 21510: {'lr': 0.0004788679848518633, 'samples': 4129920, 'steps': 21509, 'loss/train': 1.638746976852417} 08/30/2021 17:04:16 - INFO - __main__ - Step 21511: {'lr': 0.0004788658494628586, 'samples': 4130112, 'steps': 21510, 'loss/train': 1.896509051322937} 08/30/2021 17:04:16 - INFO - __main__ - Step 21512: {'lr': 0.0004788637139707304, 'samples': 4130304, 'steps': 21511, 'loss/train': 1.7294583320617676} 08/30/2021 17:04:16 - INFO - __main__ - Step 21513: {'lr': 0.00047886157837547975, 'samples': 4130496, 'steps': 21512, 'loss/train': 1.6490304470062256} 08/30/2021 17:04:17 - INFO - __main__ - Step 21514: {'lr': 0.0004788594426771076, 'samples': 4130688, 'steps': 21513, 'loss/train': 1.3523578643798828} 08/30/2021 17:04:20 - INFO - __main__ - Step 21515: {'lr': 0.0004788573068756149, 'samples': 4130880, 'steps': 21514, 'loss/train': 1.8092198371887207} 08/30/2021 17:04:20 - INFO - __main__ - Step 21516: {'lr': 0.0004788551709710027, 'samples': 4131072, 'steps': 21515, 'loss/train': 0.7204294204711914} 08/30/2021 17:04:21 - INFO - __main__ - Step 21517: {'lr': 0.0004788530349632718, 'samples': 4131264, 'steps': 21516, 'loss/train': 0.5451465845108032} 08/30/2021 17:04:21 - INFO - __main__ - Step 21518: {'lr': 0.00047885089885242333, 'samples': 4131456, 'steps': 21517, 'loss/train': 1.6412653923034668} 08/30/2021 17:04:21 - INFO - __main__ - Step 21519: {'lr': 0.0004788487626384581, 'samples': 4131648, 'steps': 21518, 'loss/train': 1.5881367921829224} 08/30/2021 17:04:22 - INFO - __main__ - Step 21520: {'lr': 0.0004788466263213772, 'samples': 4131840, 'steps': 21519, 'loss/train': 1.8423503637313843} 08/30/2021 17:04:23 - INFO - __main__ - Step 21521: {'lr': 0.00047884448990118155, 'samples': 4132032, 'steps': 21520, 'loss/train': 1.8779414892196655} 08/30/2021 17:04:24 - INFO - __main__ - Step 21522: {'lr': 0.0004788423533778721, 'samples': 4132224, 'steps': 21521, 'loss/train': 1.0586224794387817} 08/30/2021 17:04:24 - INFO - __main__ - Step 21523: {'lr': 0.00047884021675144987, 'samples': 4132416, 'steps': 21522, 'loss/train': 1.344202995300293} 08/30/2021 17:04:24 - INFO - __main__ - Step 21524: {'lr': 0.0004788380800219156, 'samples': 4132608, 'steps': 21523, 'loss/train': 1.41176176071167} 08/30/2021 17:04:25 - INFO - __main__ - Step 21525: {'lr': 0.0004788359431892706, 'samples': 4132800, 'steps': 21524, 'loss/train': 1.1432011127471924} 08/30/2021 17:04:26 - INFO - __main__ - Step 21526: {'lr': 0.00047883380625351557, 'samples': 4132992, 'steps': 21525, 'loss/train': 1.7957347631454468} 08/30/2021 17:04:27 - INFO - __main__ - Step 21527: {'lr': 0.00047883166921465156, 'samples': 4133184, 'steps': 21526, 'loss/train': 1.4472945928573608} 08/30/2021 17:04:27 - INFO - __main__ - Step 21528: {'lr': 0.00047882953207267954, 'samples': 4133376, 'steps': 21527, 'loss/train': 1.212437391281128} 08/30/2021 17:04:27 - INFO - __main__ - Step 21529: {'lr': 0.00047882739482760044, 'samples': 4133568, 'steps': 21528, 'loss/train': 1.0129021406173706} 08/30/2021 17:04:28 - INFO - __main__ - Step 21530: {'lr': 0.0004788252574794153, 'samples': 4133760, 'steps': 21529, 'loss/train': 1.4399173259735107} 08/30/2021 17:04:29 - INFO - __main__ - Step 21531: {'lr': 0.000478823120028125, 'samples': 4133952, 'steps': 21530, 'loss/train': 1.6369318962097168} 08/30/2021 17:04:30 - INFO - __main__ - Step 21532: {'lr': 0.0004788209824737305, 'samples': 4134144, 'steps': 21531, 'loss/train': 0.7602819204330444} 08/30/2021 17:04:30 - INFO - __main__ - Step 21533: {'lr': 0.00047881884481623286, 'samples': 4134336, 'steps': 21532, 'loss/train': 0.9776489734649658} 08/30/2021 17:04:30 - INFO - __main__ - Step 21534: {'lr': 0.000478816707055633, 'samples': 4134528, 'steps': 21533, 'loss/train': 1.3832441568374634} 08/30/2021 17:04:31 - INFO - __main__ - Step 21535: {'lr': 0.0004788145691919318, 'samples': 4134720, 'steps': 21534, 'loss/train': 1.7407586574554443} 08/30/2021 17:04:31 - INFO - __main__ - Step 21536: {'lr': 0.0004788124312251303, 'samples': 4134912, 'steps': 21535, 'loss/train': 1.6053481101989746} 08/30/2021 17:04:32 - INFO - __main__ - Step 21537: {'lr': 0.0004788102931552294, 'samples': 4135104, 'steps': 21536, 'loss/train': 1.5271402597427368} 08/30/2021 17:04:33 - INFO - __main__ - Step 21538: {'lr': 0.0004788081549822302, 'samples': 4135296, 'steps': 21537, 'loss/train': 1.834592580795288} 08/30/2021 17:04:33 - INFO - __main__ - Step 21539: {'lr': 0.0004788060167061335, 'samples': 4135488, 'steps': 21538, 'loss/train': 0.9684967994689941} 08/30/2021 17:04:34 - INFO - __main__ - Step 21540: {'lr': 0.0004788038783269404, 'samples': 4135680, 'steps': 21539, 'loss/train': 1.3103408813476562} 08/30/2021 17:04:34 - INFO - __main__ - Step 21541: {'lr': 0.00047880173984465174, 'samples': 4135872, 'steps': 21540, 'loss/train': 1.6949554681777954} 08/30/2021 17:04:36 - INFO - __main__ - Step 21542: {'lr': 0.0004787996012592686, 'samples': 4136064, 'steps': 21541, 'loss/train': 1.6658117771148682} 08/30/2021 17:04:36 - INFO - __main__ - Step 21543: {'lr': 0.0004787974625707919, 'samples': 4136256, 'steps': 21542, 'loss/train': 1.4745776653289795} 08/30/2021 17:04:36 - INFO - __main__ - Step 21544: {'lr': 0.0004787953237792225, 'samples': 4136448, 'steps': 21543, 'loss/train': 1.6299556493759155} 08/30/2021 17:04:37 - INFO - __main__ - Step 21545: {'lr': 0.0004787931848845616, 'samples': 4136640, 'steps': 21544, 'loss/train': 1.6548094749450684} 08/30/2021 17:04:37 - INFO - __main__ - Step 21546: {'lr': 0.00047879104588680987, 'samples': 4136832, 'steps': 21545, 'loss/train': 1.4136765003204346} 08/30/2021 17:04:38 - INFO - __main__ - Step 21547: {'lr': 0.00047878890678596854, 'samples': 4137024, 'steps': 21546, 'loss/train': 1.978952407836914} 08/30/2021 17:04:39 - INFO - __main__ - Step 21548: {'lr': 0.00047878676758203844, 'samples': 4137216, 'steps': 21547, 'loss/train': 2.357581377029419} 08/30/2021 17:04:39 - INFO - __main__ - Step 21549: {'lr': 0.00047878462827502055, 'samples': 4137408, 'steps': 21548, 'loss/train': 1.579661250114441} 08/30/2021 17:04:40 - INFO - __main__ - Step 21550: {'lr': 0.0004787824888649158, 'samples': 4137600, 'steps': 21549, 'loss/train': 1.5313758850097656} 08/30/2021 17:04:40 - INFO - __main__ - Step 21551: {'lr': 0.0004787803493517252, 'samples': 4137792, 'steps': 21550, 'loss/train': 1.173863172531128} 08/30/2021 17:04:42 - INFO - __main__ - Step 21552: {'lr': 0.0004787782097354497, 'samples': 4137984, 'steps': 21551, 'loss/train': 1.7947689294815063} 08/30/2021 17:04:42 - INFO - __main__ - Step 21553: {'lr': 0.00047877607001609035, 'samples': 4138176, 'steps': 21552, 'loss/train': 1.6152856349945068} 08/30/2021 17:04:42 - INFO - __main__ - Step 21554: {'lr': 0.00047877393019364796, 'samples': 4138368, 'steps': 21553, 'loss/train': 0.08391077816486359} 08/30/2021 17:04:43 - INFO - __main__ - Step 21555: {'lr': 0.0004787717902681236, 'samples': 4138560, 'steps': 21554, 'loss/train': 1.3522006273269653} 08/30/2021 17:04:43 - INFO - __main__ - Step 21556: {'lr': 0.00047876965023951814, 'samples': 4138752, 'steps': 21555, 'loss/train': 1.7337920665740967} 08/30/2021 17:04:45 - INFO - __main__ - Step 21557: {'lr': 0.00047876751010783266, 'samples': 4138944, 'steps': 21556, 'loss/train': 1.6510796546936035} 08/30/2021 17:04:45 - INFO - __main__ - Step 21558: {'lr': 0.0004787653698730681, 'samples': 4139136, 'steps': 21557, 'loss/train': 1.9008625745773315} 08/30/2021 17:04:46 - INFO - __main__ - Step 21559: {'lr': 0.00047876322953522535, 'samples': 4139328, 'steps': 21558, 'loss/train': 0.08120544999837875} 08/30/2021 17:04:46 - INFO - __main__ - Step 21560: {'lr': 0.00047876108909430536, 'samples': 4139520, 'steps': 21559, 'loss/train': 1.7383759021759033} 08/30/2021 17:04:46 - INFO - __main__ - Step 21561: {'lr': 0.00047875894855030923, 'samples': 4139712, 'steps': 21560, 'loss/train': 1.2564455270767212} 08/30/2021 17:04:47 - INFO - __main__ - Step 21562: {'lr': 0.00047875680790323785, 'samples': 4139904, 'steps': 21561, 'loss/train': 1.6330316066741943} 08/30/2021 17:04:48 - INFO - __main__ - Step 21563: {'lr': 0.0004787546671530921, 'samples': 4140096, 'steps': 21562, 'loss/train': 1.9583455324172974} 08/30/2021 17:04:48 - INFO - __main__ - Step 21564: {'lr': 0.0004787525262998731, 'samples': 4140288, 'steps': 21563, 'loss/train': 2.428619146347046} 08/30/2021 17:04:49 - INFO - __main__ - Step 21565: {'lr': 0.0004787503853435817, 'samples': 4140480, 'steps': 21564, 'loss/train': 1.3141828775405884} 08/30/2021 17:04:49 - INFO - __main__ - Step 21566: {'lr': 0.00047874824428421897, 'samples': 4140672, 'steps': 21565, 'loss/train': 1.6801226139068604} 08/30/2021 17:04:50 - INFO - __main__ - Step 21567: {'lr': 0.0004787461031217858, 'samples': 4140864, 'steps': 21566, 'loss/train': 1.6470086574554443} 08/30/2021 17:04:51 - INFO - __main__ - Step 21568: {'lr': 0.0004787439618562831, 'samples': 4141056, 'steps': 21567, 'loss/train': 2.1003711223602295} 08/30/2021 17:04:52 - INFO - __main__ - Step 21569: {'lr': 0.000478741820487712, 'samples': 4141248, 'steps': 21568, 'loss/train': 1.7431973218917847} 08/30/2021 17:04:52 - INFO - __main__ - Step 21570: {'lr': 0.0004787396790160733, 'samples': 4141440, 'steps': 21569, 'loss/train': 1.4745862483978271} 08/30/2021 17:04:52 - INFO - __main__ - Step 21571: {'lr': 0.00047873753744136807, 'samples': 4141632, 'steps': 21570, 'loss/train': 1.5483851432800293} 08/30/2021 17:04:53 - INFO - __main__ - Step 21572: {'lr': 0.0004787353957635971, 'samples': 4141824, 'steps': 21571, 'loss/train': 1.7145155668258667} 08/30/2021 17:04:55 - INFO - __main__ - Step 21573: {'lr': 0.0004787332539827617, 'samples': 4142016, 'steps': 21572, 'loss/train': 2.096367835998535} 08/30/2021 17:04:55 - INFO - __main__ - Step 21574: {'lr': 0.00047873111209886245, 'samples': 4142208, 'steps': 21573, 'loss/train': 1.3759455680847168} 08/30/2021 17:04:56 - INFO - __main__ - Step 21575: {'lr': 0.00047872897011190063, 'samples': 4142400, 'steps': 21574, 'loss/train': 1.3320780992507935} 08/30/2021 17:04:56 - INFO - __main__ - Step 21576: {'lr': 0.00047872682802187693, 'samples': 4142592, 'steps': 21575, 'loss/train': 1.7277063131332397} 08/30/2021 17:04:56 - INFO - __main__ - Step 21577: {'lr': 0.0004787246858287926, 'samples': 4142784, 'steps': 21576, 'loss/train': 1.3015682697296143} 08/30/2021 17:04:58 - INFO - __main__ - Step 21578: {'lr': 0.0004787225435326483, 'samples': 4142976, 'steps': 21577, 'loss/train': 1.412316083908081} 08/30/2021 17:04:58 - INFO - __main__ - Step 21579: {'lr': 0.0004787204011334453, 'samples': 4143168, 'steps': 21578, 'loss/train': 2.0656633377075195} 08/30/2021 17:04:59 - INFO - __main__ - Step 21580: {'lr': 0.0004787182586311843, 'samples': 4143360, 'steps': 21579, 'loss/train': 1.8539068698883057} 08/30/2021 17:04:59 - INFO - __main__ - Step 21581: {'lr': 0.0004787161160258664, 'samples': 4143552, 'steps': 21580, 'loss/train': 1.6576381921768188} 08/30/2021 17:04:59 - INFO - __main__ - Step 21582: {'lr': 0.00047871397331749254, 'samples': 4143744, 'steps': 21581, 'loss/train': 1.424061894416809} 08/30/2021 17:05:01 - INFO - __main__ - Step 21583: {'lr': 0.00047871183050606376, 'samples': 4143936, 'steps': 21582, 'loss/train': 1.6823989152908325} 08/30/2021 17:05:02 - INFO - __main__ - Step 21584: {'lr': 0.00047870968759158096, 'samples': 4144128, 'steps': 21583, 'loss/train': 1.2910590171813965} 08/30/2021 17:05:02 - INFO - __main__ - Step 21585: {'lr': 0.000478707544574045, 'samples': 4144320, 'steps': 21584, 'loss/train': 1.3867682218551636} 08/30/2021 17:05:02 - INFO - __main__ - Step 21586: {'lr': 0.000478705401453457, 'samples': 4144512, 'steps': 21585, 'loss/train': 1.9276567697525024} 08/30/2021 17:05:03 - INFO - __main__ - Step 21587: {'lr': 0.000478703258229818, 'samples': 4144704, 'steps': 21586, 'loss/train': 0.12375839799642563} 08/30/2021 17:05:03 - INFO - __main__ - Step 21588: {'lr': 0.0004787011149031287, 'samples': 4144896, 'steps': 21587, 'loss/train': 1.468145728111267} 08/30/2021 17:05:05 - INFO - __main__ - Step 21589: {'lr': 0.0004786989714733902, 'samples': 4145088, 'steps': 21588, 'loss/train': 1.724992036819458} 08/30/2021 17:05:05 - INFO - __main__ - Step 21590: {'lr': 0.0004786968279406035, 'samples': 4145280, 'steps': 21589, 'loss/train': 1.1805689334869385} 08/30/2021 17:05:05 - INFO - __main__ - Step 21591: {'lr': 0.0004786946843047696, 'samples': 4145472, 'steps': 21590, 'loss/train': 1.4405713081359863} 08/30/2021 17:05:06 - INFO - __main__ - Step 21592: {'lr': 0.00047869254056588927, 'samples': 4145664, 'steps': 21591, 'loss/train': 1.5672636032104492} 08/30/2021 17:05:06 - INFO - __main__ - Step 21593: {'lr': 0.0004786903967239637, 'samples': 4145856, 'steps': 21592, 'loss/train': 1.586122751235962} 08/30/2021 17:05:08 - INFO - __main__ - Step 21594: {'lr': 0.0004786882527789938, 'samples': 4146048, 'steps': 21593, 'loss/train': 1.1756656169891357} 08/30/2021 17:05:08 - INFO - __main__ - Step 21595: {'lr': 0.00047868610873098047, 'samples': 4146240, 'steps': 21594, 'loss/train': 2.0050926208496094} 08/30/2021 17:05:09 - INFO - __main__ - Step 21596: {'lr': 0.0004786839645799247, 'samples': 4146432, 'steps': 21595, 'loss/train': 1.450789213180542} 08/30/2021 17:05:09 - INFO - __main__ - Step 21597: {'lr': 0.00047868182032582746, 'samples': 4146624, 'steps': 21596, 'loss/train': 1.3242963552474976} 08/30/2021 17:05:09 - INFO - __main__ - Step 21598: {'lr': 0.00047867967596868974, 'samples': 4146816, 'steps': 21597, 'loss/train': 0.3487500250339508} 08/30/2021 17:05:11 - INFO - __main__ - Step 21599: {'lr': 0.00047867753150851244, 'samples': 4147008, 'steps': 21598, 'loss/train': 2.2175378799438477} 08/30/2021 17:05:11 - INFO - __main__ - Step 21600: {'lr': 0.0004786753869452966, 'samples': 4147200, 'steps': 21599, 'loss/train': 1.419573426246643} 08/30/2021 17:05:12 - INFO - __main__ - Step 21601: {'lr': 0.00047867324227904317, 'samples': 4147392, 'steps': 21600, 'loss/train': 1.3353098630905151} 08/30/2021 17:05:12 - INFO - __main__ - Step 21602: {'lr': 0.0004786710975097531, 'samples': 4147584, 'steps': 21601, 'loss/train': 1.6635923385620117} 08/30/2021 17:05:12 - INFO - __main__ - Step 21603: {'lr': 0.0004786689526374274, 'samples': 4147776, 'steps': 21602, 'loss/train': 1.8505805730819702} 08/30/2021 17:05:13 - INFO - __main__ - Step 21604: {'lr': 0.00047866680766206693, 'samples': 4147968, 'steps': 21603, 'loss/train': 1.4862685203552246} 08/30/2021 17:05:14 - INFO - __main__ - Step 21605: {'lr': 0.0004786646625836727, 'samples': 4148160, 'steps': 21604, 'loss/train': 1.943293809890747} 08/30/2021 17:05:15 - INFO - __main__ - Step 21606: {'lr': 0.0004786625174022458, 'samples': 4148352, 'steps': 21605, 'loss/train': 1.1202270984649658} 08/30/2021 17:05:15 - INFO - __main__ - Step 21607: {'lr': 0.00047866037211778705, 'samples': 4148544, 'steps': 21606, 'loss/train': 2.019742965698242} 08/30/2021 17:05:16 - INFO - __main__ - Step 21608: {'lr': 0.0004786582267302975, 'samples': 4148736, 'steps': 21607, 'loss/train': 1.2123949527740479} 08/30/2021 17:05:16 - INFO - __main__ - Step 21609: {'lr': 0.000478656081239778, 'samples': 4148928, 'steps': 21608, 'loss/train': 1.9415785074234009} 08/30/2021 17:05:17 - INFO - __main__ - Step 21610: {'lr': 0.0004786539356462297, 'samples': 4149120, 'steps': 21609, 'loss/train': 1.5333104133605957} 08/30/2021 17:05:18 - INFO - __main__ - Step 21611: {'lr': 0.0004786517899496534, 'samples': 4149312, 'steps': 21610, 'loss/train': 1.5422704219818115} 08/30/2021 17:05:18 - INFO - __main__ - Step 21612: {'lr': 0.0004786496441500502, 'samples': 4149504, 'steps': 21611, 'loss/train': 1.368769645690918} 08/30/2021 17:05:19 - INFO - __main__ - Step 21613: {'lr': 0.00047864749824742093, 'samples': 4149696, 'steps': 21612, 'loss/train': 1.8876041173934937} 08/30/2021 17:05:19 - INFO - __main__ - Step 21614: {'lr': 0.00047864535224176666, 'samples': 4149888, 'steps': 21613, 'loss/train': 1.2801645994186401} 08/30/2021 17:05:20 - INFO - __main__ - Step 21615: {'lr': 0.0004786432061330882, 'samples': 4150080, 'steps': 21614, 'loss/train': 1.3951793909072876} 08/30/2021 17:05:21 - INFO - __main__ - Step 21616: {'lr': 0.0004786410599213868, 'samples': 4150272, 'steps': 21615, 'loss/train': 1.6834088563919067} 08/30/2021 17:05:21 - INFO - __main__ - Step 21617: {'lr': 0.00047863891360666323, 'samples': 4150464, 'steps': 21616, 'loss/train': 1.1598668098449707} 08/30/2021 17:05:22 - INFO - __main__ - Step 21618: {'lr': 0.00047863676718891846, 'samples': 4150656, 'steps': 21617, 'loss/train': 1.665282130241394} 08/30/2021 17:05:22 - INFO - __main__ - Step 21619: {'lr': 0.0004786346206681535, 'samples': 4150848, 'steps': 21618, 'loss/train': 1.9712655544281006} 08/30/2021 17:05:24 - INFO - __main__ - Step 21620: {'lr': 0.0004786324740443693, 'samples': 4151040, 'steps': 21619, 'loss/train': 1.265072226524353} 08/30/2021 17:05:24 - INFO - __main__ - Step 21621: {'lr': 0.00047863032731756684, 'samples': 4151232, 'steps': 21620, 'loss/train': 0.20737281441688538} 08/30/2021 17:05:24 - INFO - __main__ - Step 21622: {'lr': 0.0004786281804877471, 'samples': 4151424, 'steps': 21621, 'loss/train': 1.6420605182647705} 08/30/2021 17:05:25 - INFO - __main__ - Step 21623: {'lr': 0.00047862603355491103, 'samples': 4151616, 'steps': 21622, 'loss/train': 2.252286434173584} 08/30/2021 17:05:25 - INFO - __main__ - Step 21624: {'lr': 0.0004786238865190595, 'samples': 4151808, 'steps': 21623, 'loss/train': 1.5345619916915894} 08/30/2021 17:05:27 - INFO - __main__ - Step 21625: {'lr': 0.0004786217393801937, 'samples': 4152000, 'steps': 21624, 'loss/train': 1.3157330751419067} 08/30/2021 17:05:27 - INFO - __main__ - Step 21626: {'lr': 0.00047861959213831446, 'samples': 4152192, 'steps': 21625, 'loss/train': 1.9387462139129639} 08/30/2021 17:05:28 - INFO - __main__ - Step 21627: {'lr': 0.0004786174447934227, 'samples': 4152384, 'steps': 21626, 'loss/train': 1.5936999320983887} 08/30/2021 17:05:28 - INFO - __main__ - Step 21628: {'lr': 0.0004786152973455195, 'samples': 4152576, 'steps': 21627, 'loss/train': 1.2677874565124512} 08/30/2021 17:05:28 - INFO - __main__ - Step 21629: {'lr': 0.0004786131497946058, 'samples': 4152768, 'steps': 21628, 'loss/train': 1.9037866592407227} 08/30/2021 17:05:30 - INFO - __main__ - Step 21630: {'lr': 0.0004786110021406824, 'samples': 4152960, 'steps': 21629, 'loss/train': 1.6569949388504028} 08/30/2021 17:05:30 - INFO - __main__ - Step 21631: {'lr': 0.0004786088543837506, 'samples': 4153152, 'steps': 21630, 'loss/train': 1.278141975402832} 08/30/2021 17:05:31 - INFO - __main__ - Step 21632: {'lr': 0.00047860670652381105, 'samples': 4153344, 'steps': 21631, 'loss/train': 1.80409574508667} 08/30/2021 17:05:31 - INFO - __main__ - Step 21633: {'lr': 0.00047860455856086487, 'samples': 4153536, 'steps': 21632, 'loss/train': 1.2285655736923218} 08/30/2021 17:05:31 - INFO - __main__ - Step 21634: {'lr': 0.00047860241049491303, 'samples': 4153728, 'steps': 21633, 'loss/train': 1.7540972232818604} 08/30/2021 17:05:34 - INFO - __main__ - Step 21635: {'lr': 0.00047860026232595645, 'samples': 4153920, 'steps': 21634, 'loss/train': 1.0764487981796265} 08/30/2021 17:05:34 - INFO - __main__ - Step 21636: {'lr': 0.0004785981140539961, 'samples': 4154112, 'steps': 21635, 'loss/train': 2.0278148651123047} 08/30/2021 17:05:34 - INFO - __main__ - Step 21637: {'lr': 0.000478595965679033, 'samples': 4154304, 'steps': 21636, 'loss/train': 1.2128251791000366} 08/30/2021 17:05:35 - INFO - __main__ - Step 21638: {'lr': 0.0004785938172010681, 'samples': 4154496, 'steps': 21637, 'loss/train': 1.9851192235946655} 08/30/2021 17:05:35 - INFO - __main__ - Step 21639: {'lr': 0.0004785916686201023, 'samples': 4154688, 'steps': 21638, 'loss/train': 2.2266154289245605} 08/30/2021 17:05:35 - INFO - __main__ - Step 21640: {'lr': 0.00047858951993613665, 'samples': 4154880, 'steps': 21639, 'loss/train': 1.9012534618377686} 08/30/2021 17:05:37 - INFO - __main__ - Step 21641: {'lr': 0.0004785873711491721, 'samples': 4155072, 'steps': 21640, 'loss/train': 1.3370827436447144} 08/30/2021 17:05:38 - INFO - __main__ - Step 21642: {'lr': 0.00047858522225920964, 'samples': 4155264, 'steps': 21641, 'loss/train': 1.211037039756775} 08/30/2021 17:05:38 - INFO - __main__ - Step 21643: {'lr': 0.00047858307326625014, 'samples': 4155456, 'steps': 21642, 'loss/train': 1.617024540901184} 08/30/2021 17:05:38 - INFO - __main__ - Step 21644: {'lr': 0.00047858092417029464, 'samples': 4155648, 'steps': 21643, 'loss/train': 1.245651125907898} 08/30/2021 17:05:39 - INFO - __main__ - Step 21645: {'lr': 0.00047857877497134416, 'samples': 4155840, 'steps': 21644, 'loss/train': 1.972427248954773} 08/30/2021 17:05:39 - INFO - __main__ - Step 21646: {'lr': 0.0004785766256693995, 'samples': 4156032, 'steps': 21645, 'loss/train': 1.904283881187439} 08/30/2021 17:05:41 - INFO - __main__ - Step 21647: {'lr': 0.0004785744762644619, 'samples': 4156224, 'steps': 21646, 'loss/train': 1.5063691139221191} 08/30/2021 17:05:41 - INFO - __main__ - Step 21648: {'lr': 0.00047857232675653207, 'samples': 4156416, 'steps': 21647, 'loss/train': 0.1265147179365158} 08/30/2021 17:05:42 - INFO - __main__ - Step 21649: {'lr': 0.00047857017714561105, 'samples': 4156608, 'steps': 21648, 'loss/train': 1.8977305889129639} 08/30/2021 17:05:42 - INFO - __main__ - Step 21650: {'lr': 0.00047856802743169994, 'samples': 4156800, 'steps': 21649, 'loss/train': 2.013026237487793} 08/30/2021 17:05:42 - INFO - __main__ - Step 21651: {'lr': 0.00047856587761479954, 'samples': 4156992, 'steps': 21650, 'loss/train': 2.245924711227417} 08/30/2021 17:05:44 - INFO - __main__ - Step 21652: {'lr': 0.00047856372769491083, 'samples': 4157184, 'steps': 21651, 'loss/train': 2.003310203552246} 08/30/2021 17:05:44 - INFO - __main__ - Step 21653: {'lr': 0.0004785615776720349, 'samples': 4157376, 'steps': 21652, 'loss/train': 1.499346375465393} 08/30/2021 17:05:45 - INFO - __main__ - Step 21654: {'lr': 0.0004785594275461726, 'samples': 4157568, 'steps': 21653, 'loss/train': 1.6132514476776123} 08/30/2021 17:05:45 - INFO - __main__ - Step 21655: {'lr': 0.00047855727731732503, 'samples': 4157760, 'steps': 21654, 'loss/train': 1.4317113161087036} 08/30/2021 17:05:45 - INFO - __main__ - Step 21656: {'lr': 0.00047855512698549295, 'samples': 4157952, 'steps': 21655, 'loss/train': 1.4344325065612793} 08/30/2021 17:05:47 - INFO - __main__ - Step 21657: {'lr': 0.00047855297655067754, 'samples': 4158144, 'steps': 21656, 'loss/train': 1.5683907270431519} 08/30/2021 17:05:47 - INFO - __main__ - Step 21658: {'lr': 0.0004785508260128797, 'samples': 4158336, 'steps': 21657, 'loss/train': 1.5640400648117065} 08/30/2021 17:05:48 - INFO - __main__ - Step 21659: {'lr': 0.00047854867537210034, 'samples': 4158528, 'steps': 21658, 'loss/train': 1.8587629795074463} 08/30/2021 17:05:48 - INFO - __main__ - Step 21660: {'lr': 0.00047854652462834055, 'samples': 4158720, 'steps': 21659, 'loss/train': 1.7621623277664185} 08/30/2021 17:05:48 - INFO - __main__ - Step 21661: {'lr': 0.0004785443737816012, 'samples': 4158912, 'steps': 21660, 'loss/train': 1.5130053758621216} 08/30/2021 17:05:50 - INFO - __main__ - Step 21662: {'lr': 0.0004785422228318832, 'samples': 4159104, 'steps': 21661, 'loss/train': 1.2033276557922363} 08/30/2021 17:05:50 - INFO - __main__ - Step 21663: {'lr': 0.0004785400717791877, 'samples': 4159296, 'steps': 21662, 'loss/train': 1.7768971920013428} 08/30/2021 17:05:51 - INFO - __main__ - Step 21664: {'lr': 0.0004785379206235155, 'samples': 4159488, 'steps': 21663, 'loss/train': 1.7159216403961182} 08/30/2021 17:05:51 - INFO - __main__ - Step 21665: {'lr': 0.00047853576936486764, 'samples': 4159680, 'steps': 21664, 'loss/train': 1.5477763414382935} 08/30/2021 17:05:51 - INFO - __main__ - Step 21666: {'lr': 0.00047853361800324516, 'samples': 4159872, 'steps': 21665, 'loss/train': 1.7746342420578003} 08/30/2021 17:05:53 - INFO - __main__ - Step 21667: {'lr': 0.0004785314665386489, 'samples': 4160064, 'steps': 21666, 'loss/train': 1.3123118877410889} 08/30/2021 17:05:53 - INFO - __main__ - Step 21668: {'lr': 0.00047852931497107987, 'samples': 4160256, 'steps': 21667, 'loss/train': 1.0089551210403442} 08/30/2021 17:05:54 - INFO - __main__ - Step 21669: {'lr': 0.0004785271633005391, 'samples': 4160448, 'steps': 21668, 'loss/train': 0.8854736089706421} 08/30/2021 17:05:54 - INFO - __main__ - Step 21670: {'lr': 0.0004785250115270275, 'samples': 4160640, 'steps': 21669, 'loss/train': 1.405593991279602} 08/30/2021 17:05:55 - INFO - __main__ - Step 21671: {'lr': 0.00047852285965054606, 'samples': 4160832, 'steps': 21670, 'loss/train': 1.7800955772399902} 08/30/2021 17:05:56 - INFO - __main__ - Step 21672: {'lr': 0.00047852070767109573, 'samples': 4161024, 'steps': 21671, 'loss/train': 0.6641238927841187} 08/30/2021 17:05:57 - INFO - __main__ - Step 21673: {'lr': 0.00047851855558867754, 'samples': 4161216, 'steps': 21672, 'loss/train': 1.8311665058135986} 08/30/2021 17:05:57 - INFO - __main__ - Step 21674: {'lr': 0.0004785164034032924, 'samples': 4161408, 'steps': 21673, 'loss/train': 1.4423707723617554} 08/30/2021 17:05:57 - INFO - __main__ - Step 21675: {'lr': 0.0004785142511149412, 'samples': 4161600, 'steps': 21674, 'loss/train': 1.4329500198364258} 08/30/2021 17:05:58 - INFO - __main__ - Step 21676: {'lr': 0.0004785120987236251, 'samples': 4161792, 'steps': 21675, 'loss/train': 1.7964509725570679} 08/30/2021 17:05:58 - INFO - __main__ - Step 21677: {'lr': 0.00047850994622934494, 'samples': 4161984, 'steps': 21676, 'loss/train': 2.149315357208252} 08/30/2021 17:06:00 - INFO - __main__ - Step 21678: {'lr': 0.0004785077936321018, 'samples': 4162176, 'steps': 21677, 'loss/train': 1.191805362701416} 08/30/2021 17:06:00 - INFO - __main__ - Step 21679: {'lr': 0.00047850564093189653, 'samples': 4162368, 'steps': 21678, 'loss/train': 1.8324463367462158} 08/30/2021 17:06:01 - INFO - __main__ - Step 21680: {'lr': 0.0004785034881287301, 'samples': 4162560, 'steps': 21679, 'loss/train': 1.6059406995773315} 08/30/2021 17:06:01 - INFO - __main__ - Step 21681: {'lr': 0.0004785013352226035, 'samples': 4162752, 'steps': 21680, 'loss/train': 1.2899469137191772} 08/30/2021 17:06:02 - INFO - __main__ - Step 21682: {'lr': 0.00047849918221351783, 'samples': 4162944, 'steps': 21681, 'loss/train': 1.5513609647750854} 08/30/2021 17:06:03 - INFO - __main__ - Step 21683: {'lr': 0.0004784970291014739, 'samples': 4163136, 'steps': 21682, 'loss/train': 1.4121525287628174} 08/30/2021 17:06:04 - INFO - __main__ - Step 21684: {'lr': 0.0004784948758864727, 'samples': 4163328, 'steps': 21683, 'loss/train': 1.5040241479873657} 08/30/2021 17:06:04 - INFO - __main__ - Step 21685: {'lr': 0.0004784927225685153, 'samples': 4163520, 'steps': 21684, 'loss/train': 1.7399235963821411} 08/30/2021 17:06:04 - INFO - __main__ - Step 21686: {'lr': 0.00047849056914760256, 'samples': 4163712, 'steps': 21685, 'loss/train': 1.5813474655151367} 08/30/2021 17:06:05 - INFO - __main__ - Step 21687: {'lr': 0.00047848841562373557, 'samples': 4163904, 'steps': 21686, 'loss/train': 1.3997126817703247} 08/30/2021 17:06:06 - INFO - __main__ - Step 21688: {'lr': 0.00047848626199691513, 'samples': 4164096, 'steps': 21687, 'loss/train': 0.8966947197914124} 08/30/2021 17:06:07 - INFO - __main__ - Step 21689: {'lr': 0.00047848410826714237, 'samples': 4164288, 'steps': 21688, 'loss/train': 2.055316209793091} 08/30/2021 17:06:07 - INFO - __main__ - Step 21690: {'lr': 0.00047848195443441817, 'samples': 4164480, 'steps': 21689, 'loss/train': 1.6565885543823242} 08/30/2021 17:06:07 - INFO - __main__ - Step 21691: {'lr': 0.0004784798004987435, 'samples': 4164672, 'steps': 21690, 'loss/train': 1.4507962465286255} 08/30/2021 17:06:08 - INFO - __main__ - Step 21692: {'lr': 0.00047847764646011937, 'samples': 4164864, 'steps': 21691, 'loss/train': 1.6128380298614502} 08/30/2021 17:06:09 - INFO - __main__ - Step 21693: {'lr': 0.0004784754923185468, 'samples': 4165056, 'steps': 21692, 'loss/train': 1.4008574485778809} 08/30/2021 17:06:10 - INFO - __main__ - Step 21694: {'lr': 0.00047847333807402666, 'samples': 4165248, 'steps': 21693, 'loss/train': 1.9528981447219849} 08/30/2021 17:06:10 - INFO - __main__ - Step 21695: {'lr': 0.00047847118372655996, 'samples': 4165440, 'steps': 21694, 'loss/train': 1.243920087814331} 08/30/2021 17:06:10 - INFO - __main__ - Step 21696: {'lr': 0.00047846902927614767, 'samples': 4165632, 'steps': 21695, 'loss/train': 1.3261280059814453} 08/30/2021 17:06:11 - INFO - __main__ - Step 21697: {'lr': 0.0004784668747227907, 'samples': 4165824, 'steps': 21696, 'loss/train': 1.3166300058364868} 08/30/2021 17:06:12 - INFO - __main__ - Step 21698: {'lr': 0.00047846472006649016, 'samples': 4166016, 'steps': 21697, 'loss/train': 1.4801424741744995} 08/30/2021 17:06:13 - INFO - __main__ - Step 21699: {'lr': 0.0004784625653072469, 'samples': 4166208, 'steps': 21698, 'loss/train': 1.820278286933899} 08/30/2021 17:06:13 - INFO - __main__ - Step 21700: {'lr': 0.00047846041044506194, 'samples': 4166400, 'steps': 21699, 'loss/train': 1.6920466423034668} 08/30/2021 17:06:13 - INFO - __main__ - Step 21701: {'lr': 0.00047845825547993627, 'samples': 4166592, 'steps': 21700, 'loss/train': 1.3065929412841797} 08/30/2021 17:06:14 - INFO - __main__ - Step 21702: {'lr': 0.0004784561004118708, 'samples': 4166784, 'steps': 21701, 'loss/train': 0.916358470916748} 08/30/2021 17:06:14 - INFO - __main__ - Step 21703: {'lr': 0.0004784539452408666, 'samples': 4166976, 'steps': 21702, 'loss/train': 1.397084355354309} 08/30/2021 17:06:16 - INFO - __main__ - Step 21704: {'lr': 0.0004784517899669245, 'samples': 4167168, 'steps': 21703, 'loss/train': 1.5995969772338867} 08/30/2021 17:06:16 - INFO - __main__ - Step 21705: {'lr': 0.00047844963459004565, 'samples': 4167360, 'steps': 21704, 'loss/train': 1.1845390796661377} 08/30/2021 17:06:16 - INFO - __main__ - Step 21706: {'lr': 0.00047844747911023077, 'samples': 4167552, 'steps': 21705, 'loss/train': 1.4429291486740112} 08/30/2021 17:06:17 - INFO - __main__ - Step 21707: {'lr': 0.00047844532352748115, 'samples': 4167744, 'steps': 21706, 'loss/train': 1.5198560953140259} 08/30/2021 17:06:18 - INFO - __main__ - Step 21708: {'lr': 0.0004784431678417975, 'samples': 4167936, 'steps': 21707, 'loss/train': 1.672396183013916} 08/30/2021 17:06:19 - INFO - __main__ - Step 21709: {'lr': 0.00047844101205318085, 'samples': 4168128, 'steps': 21708, 'loss/train': 1.552107334136963} 08/30/2021 17:06:19 - INFO - __main__ - Step 21710: {'lr': 0.0004784388561616323, 'samples': 4168320, 'steps': 21709, 'loss/train': 1.5733312368392944} 08/30/2021 17:06:20 - INFO - __main__ - Step 21711: {'lr': 0.0004784367001671526, 'samples': 4168512, 'steps': 21710, 'loss/train': 2.090911388397217} 08/30/2021 17:06:20 - INFO - __main__ - Step 21712: {'lr': 0.00047843454406974295, 'samples': 4168704, 'steps': 21711, 'loss/train': 0.10917995125055313} 08/30/2021 17:06:20 - INFO - __main__ - Step 21713: {'lr': 0.00047843238786940423, 'samples': 4168896, 'steps': 21712, 'loss/train': 1.238024115562439} 08/30/2021 17:06:22 - INFO - __main__ - Step 21714: {'lr': 0.0004784302315661373, 'samples': 4169088, 'steps': 21713, 'loss/train': 1.3346723318099976} 08/30/2021 17:06:22 - INFO - __main__ - Step 21715: {'lr': 0.00047842807515994335, 'samples': 4169280, 'steps': 21714, 'loss/train': 1.1240020990371704} 08/30/2021 17:06:22 - INFO - __main__ - Step 21716: {'lr': 0.00047842591865082315, 'samples': 4169472, 'steps': 21715, 'loss/train': 1.3416444063186646} 08/30/2021 17:06:23 - INFO - __main__ - Step 21717: {'lr': 0.0004784237620387778, 'samples': 4169664, 'steps': 21716, 'loss/train': 1.1611155271530151} 08/30/2021 17:06:23 - INFO - __main__ - Step 21718: {'lr': 0.0004784216053238082, 'samples': 4169856, 'steps': 21717, 'loss/train': 1.9573583602905273} 08/30/2021 17:06:25 - INFO - __main__ - Step 21719: {'lr': 0.00047841944850591535, 'samples': 4170048, 'steps': 21718, 'loss/train': 1.6516616344451904} 08/30/2021 17:06:25 - INFO - __main__ - Step 21720: {'lr': 0.0004784172915851003, 'samples': 4170240, 'steps': 21719, 'loss/train': 1.3609671592712402} 08/30/2021 17:06:26 - INFO - __main__ - Step 21721: {'lr': 0.00047841513456136383, 'samples': 4170432, 'steps': 21720, 'loss/train': 1.008778691291809} 08/30/2021 17:06:26 - INFO - __main__ - Step 21722: {'lr': 0.000478412977434707, 'samples': 4170624, 'steps': 21721, 'loss/train': 1.7178418636322021} 08/30/2021 17:06:26 - INFO - __main__ - Step 21723: {'lr': 0.00047841082020513094, 'samples': 4170816, 'steps': 21722, 'loss/train': 1.863709568977356} 08/30/2021 17:06:28 - INFO - __main__ - Step 21724: {'lr': 0.0004784086628726364, 'samples': 4171008, 'steps': 21723, 'loss/train': 3.1482386589050293} 08/30/2021 17:06:28 - INFO - __main__ - Step 21725: {'lr': 0.0004784065054372245, 'samples': 4171200, 'steps': 21724, 'loss/train': 1.9970582723617554} 08/30/2021 17:06:29 - INFO - __main__ - Step 21726: {'lr': 0.0004784043478988961, 'samples': 4171392, 'steps': 21725, 'loss/train': 1.3224568367004395} 08/30/2021 17:06:29 - INFO - __main__ - Step 21727: {'lr': 0.00047840219025765225, 'samples': 4171584, 'steps': 21726, 'loss/train': 2.3315300941467285} 08/30/2021 17:06:29 - INFO - __main__ - Step 21728: {'lr': 0.0004784000325134939, 'samples': 4171776, 'steps': 21727, 'loss/train': 0.11365387588739395} 08/30/2021 17:06:30 - INFO - __main__ - Step 21729: {'lr': 0.00047839787466642206, 'samples': 4171968, 'steps': 21728, 'loss/train': 1.4912441968917847} 08/30/2021 17:06:32 - INFO - __main__ - Step 21730: {'lr': 0.00047839571671643756, 'samples': 4172160, 'steps': 21729, 'loss/train': 1.7546395063400269} 08/30/2021 17:06:33 - INFO - __main__ - Step 21731: {'lr': 0.0004783935586635415, 'samples': 4172352, 'steps': 21730, 'loss/train': 2.2621519565582275} 08/30/2021 17:06:33 - INFO - __main__ - Step 21732: {'lr': 0.0004783914005077349, 'samples': 4172544, 'steps': 21731, 'loss/train': 1.6448993682861328} 08/30/2021 17:06:33 - INFO - __main__ - Step 21733: {'lr': 0.0004783892422490186, 'samples': 4172736, 'steps': 21732, 'loss/train': 1.3782418966293335} 08/30/2021 17:06:34 - INFO - __main__ - Step 21734: {'lr': 0.00047838708388739365, 'samples': 4172928, 'steps': 21733, 'loss/train': 1.9569100141525269} 08/30/2021 17:06:35 - INFO - __main__ - Step 21735: {'lr': 0.000478384925422861, 'samples': 4173120, 'steps': 21734, 'loss/train': 1.675588846206665} 08/30/2021 17:06:36 - INFO - __main__ - Step 21736: {'lr': 0.00047838276685542157, 'samples': 4173312, 'steps': 21735, 'loss/train': 1.4226258993148804} 08/30/2021 17:06:36 - INFO - __main__ - Step 21737: {'lr': 0.0004783806081850765, 'samples': 4173504, 'steps': 21736, 'loss/train': 1.2623894214630127} 08/30/2021 17:06:37 - INFO - __main__ - Step 21738: {'lr': 0.0004783784494118266, 'samples': 4173696, 'steps': 21737, 'loss/train': 1.5730348825454712} 08/30/2021 17:06:37 - INFO - __main__ - Step 21739: {'lr': 0.00047837629053567286, 'samples': 4173888, 'steps': 21738, 'loss/train': 1.30971360206604} 08/30/2021 17:06:39 - INFO - __main__ - Step 21740: {'lr': 0.00047837413155661635, 'samples': 4174080, 'steps': 21739, 'loss/train': 0.17382727563381195} 08/30/2021 17:06:39 - INFO - __main__ - Step 21741: {'lr': 0.000478371972474658, 'samples': 4174272, 'steps': 21740, 'loss/train': 1.891969084739685} 08/30/2021 17:06:39 - INFO - __main__ - Step 21742: {'lr': 0.00047836981328979865, 'samples': 4174464, 'steps': 21741, 'loss/train': 1.3879209756851196} 08/30/2021 17:06:40 - INFO - __main__ - Step 21743: {'lr': 0.00047836765400203953, 'samples': 4174656, 'steps': 21742, 'loss/train': 1.1069267988204956} 08/30/2021 17:06:40 - INFO - __main__ - Step 21744: {'lr': 0.00047836549461138133, 'samples': 4174848, 'steps': 21743, 'loss/train': 1.566767930984497} 08/30/2021 17:06:42 - INFO - __main__ - Step 21745: {'lr': 0.00047836333511782524, 'samples': 4175040, 'steps': 21744, 'loss/train': 1.494236707687378} 08/30/2021 17:06:43 - INFO - __main__ - Step 21746: {'lr': 0.00047836117552137213, 'samples': 4175232, 'steps': 21745, 'loss/train': 1.5211020708084106} 08/30/2021 17:06:43 - INFO - __main__ - Step 21747: {'lr': 0.00047835901582202303, 'samples': 4175424, 'steps': 21746, 'loss/train': 1.3371444940567017} 08/30/2021 17:06:43 - INFO - __main__ - Step 21748: {'lr': 0.00047835685601977886, 'samples': 4175616, 'steps': 21747, 'loss/train': 1.6107068061828613} 08/30/2021 17:06:44 - INFO - __main__ - Step 21749: {'lr': 0.00047835469611464055, 'samples': 4175808, 'steps': 21748, 'loss/train': 1.7145252227783203} 08/30/2021 17:06:44 - INFO - __main__ - Step 21750: {'lr': 0.0004783525361066092, 'samples': 4176000, 'steps': 21749, 'loss/train': 1.872490644454956} 08/30/2021 17:06:46 - INFO - __main__ - Step 21751: {'lr': 0.00047835037599568576, 'samples': 4176192, 'steps': 21750, 'loss/train': 1.7199158668518066} 08/30/2021 17:06:46 - INFO - __main__ - Step 21752: {'lr': 0.0004783482157818711, 'samples': 4176384, 'steps': 21751, 'loss/train': 1.058449149131775} 08/30/2021 17:06:46 - INFO - __main__ - Step 21753: {'lr': 0.0004783460554651663, 'samples': 4176576, 'steps': 21752, 'loss/train': 1.4700802564620972} 08/30/2021 17:06:47 - INFO - __main__ - Step 21754: {'lr': 0.0004783438950455723, 'samples': 4176768, 'steps': 21753, 'loss/train': 1.7727082967758179} 08/30/2021 17:06:47 - INFO - __main__ - Step 21755: {'lr': 0.00047834173452309005, 'samples': 4176960, 'steps': 21754, 'loss/train': 1.5789827108383179} 08/30/2021 17:06:48 - INFO - __main__ - Step 21756: {'lr': 0.00047833957389772046, 'samples': 4177152, 'steps': 21755, 'loss/train': 1.455665946006775} 08/30/2021 17:06:49 - INFO - __main__ - Step 21757: {'lr': 0.0004783374131694647, 'samples': 4177344, 'steps': 21756, 'loss/train': 1.679849624633789} 08/30/2021 17:06:50 - INFO - __main__ - Step 21758: {'lr': 0.00047833525233832356, 'samples': 4177536, 'steps': 21757, 'loss/train': 0.199010968208313} 08/30/2021 17:06:50 - INFO - __main__ - Step 21759: {'lr': 0.00047833309140429803, 'samples': 4177728, 'steps': 21758, 'loss/train': 1.6432427167892456} 08/30/2021 17:06:50 - INFO - __main__ - Step 21760: {'lr': 0.0004783309303673892, 'samples': 4177920, 'steps': 21759, 'loss/train': 1.7864922285079956} 08/30/2021 17:06:51 - INFO - __main__ - Step 21761: {'lr': 0.00047832876922759805, 'samples': 4178112, 'steps': 21760, 'loss/train': 1.6534661054611206} 08/30/2021 17:06:52 - INFO - __main__ - Step 21762: {'lr': 0.0004783266079849253, 'samples': 4178304, 'steps': 21761, 'loss/train': 1.9542009830474854} 08/30/2021 17:06:53 - INFO - __main__ - Step 21763: {'lr': 0.00047832444663937227, 'samples': 4178496, 'steps': 21762, 'loss/train': 1.3221291303634644} 08/30/2021 17:06:53 - INFO - __main__ - Step 21764: {'lr': 0.0004783222851909397, 'samples': 4178688, 'steps': 21763, 'loss/train': 5.238156795501709} 08/30/2021 17:06:53 - INFO - __main__ - Step 21765: {'lr': 0.0004783201236396286, 'samples': 4178880, 'steps': 21764, 'loss/train': 1.62040114402771} 08/30/2021 17:06:54 - INFO - __main__ - Step 21766: {'lr': 0.00047831796198544, 'samples': 4179072, 'steps': 21765, 'loss/train': 1.7173926830291748} 08/30/2021 17:06:54 - INFO - __main__ - Step 21767: {'lr': 0.0004783158002283749, 'samples': 4179264, 'steps': 21766, 'loss/train': 1.612707495689392} 08/30/2021 17:06:56 - INFO - __main__ - Step 21768: {'lr': 0.0004783136383684342, 'samples': 4179456, 'steps': 21767, 'loss/train': 1.9059386253356934} 08/30/2021 17:06:56 - INFO - __main__ - Step 21769: {'lr': 0.0004783114764056188, 'samples': 4179648, 'steps': 21768, 'loss/train': 1.3929764032363892} 08/30/2021 17:06:56 - INFO - __main__ - Step 21770: {'lr': 0.00047830931433992985, 'samples': 4179840, 'steps': 21769, 'loss/train': 0.8066627979278564} 08/30/2021 17:06:57 - INFO - __main__ - Step 21771: {'lr': 0.00047830715217136825, 'samples': 4180032, 'steps': 21770, 'loss/train': 2.010899305343628} 08/30/2021 17:06:57 - INFO - __main__ - Step 21772: {'lr': 0.000478304989899935, 'samples': 4180224, 'steps': 21771, 'loss/train': 0.7552194595336914} 08/30/2021 17:06:58 - INFO - __main__ - Step 21773: {'lr': 0.00047830282752563103, 'samples': 4180416, 'steps': 21772, 'loss/train': 1.7293847799301147} 08/30/2021 17:06:59 - INFO - __main__ - Step 21774: {'lr': 0.00047830066504845725, 'samples': 4180608, 'steps': 21773, 'loss/train': 1.309455394744873} 08/30/2021 17:06:59 - INFO - __main__ - Step 21775: {'lr': 0.0004782985024684148, 'samples': 4180800, 'steps': 21774, 'loss/train': 1.440053105354309} 08/30/2021 17:07:00 - INFO - __main__ - Step 21776: {'lr': 0.0004782963397855046, 'samples': 4180992, 'steps': 21775, 'loss/train': 1.169439673423767} 08/30/2021 17:07:00 - INFO - __main__ - Step 21777: {'lr': 0.00047829417699972747, 'samples': 4181184, 'steps': 21776, 'loss/train': 2.02445650100708} 08/30/2021 17:07:02 - INFO - __main__ - Step 21778: {'lr': 0.0004782920141110846, 'samples': 4181376, 'steps': 21777, 'loss/train': 1.6135485172271729} 08/30/2021 17:07:02 - INFO - __main__ - Step 21779: {'lr': 0.0004782898511195768, 'samples': 4181568, 'steps': 21778, 'loss/train': 0.9269253611564636} 08/30/2021 17:07:03 - INFO - __main__ - Step 21780: {'lr': 0.00047828768802520515, 'samples': 4181760, 'steps': 21779, 'loss/train': 1.4465060234069824} 08/30/2021 17:07:03 - INFO - __main__ - Step 21781: {'lr': 0.0004782855248279706, 'samples': 4181952, 'steps': 21780, 'loss/train': 1.769426703453064} 08/30/2021 17:07:03 - INFO - __main__ - Step 21782: {'lr': 0.0004782833615278741, 'samples': 4182144, 'steps': 21781, 'loss/train': 1.2966687679290771} 08/30/2021 17:07:05 - INFO - __main__ - Step 21783: {'lr': 0.00047828119812491664, 'samples': 4182336, 'steps': 21782, 'loss/train': 1.430395483970642} 08/30/2021 17:07:05 - INFO - __main__ - Step 21784: {'lr': 0.0004782790346190993, 'samples': 4182528, 'steps': 21783, 'loss/train': 1.4945639371871948} 08/30/2021 17:07:06 - INFO - __main__ - Step 21785: {'lr': 0.00047827687101042283, 'samples': 4182720, 'steps': 21784, 'loss/train': 2.0308988094329834} 08/30/2021 17:07:06 - INFO - __main__ - Step 21786: {'lr': 0.00047827470729888834, 'samples': 4182912, 'steps': 21785, 'loss/train': 1.586060643196106} 08/30/2021 17:07:06 - INFO - __main__ - Step 21787: {'lr': 0.0004782725434844968, 'samples': 4183104, 'steps': 21786, 'loss/train': 2.080684185028076} 08/30/2021 17:07:08 - INFO - __main__ - Step 21788: {'lr': 0.00047827037956724915, 'samples': 4183296, 'steps': 21787, 'loss/train': 0.839836835861206} 08/30/2021 17:07:09 - INFO - __main__ - Step 21789: {'lr': 0.00047826821554714644, 'samples': 4183488, 'steps': 21788, 'loss/train': 1.1939973831176758} 08/30/2021 17:07:09 - INFO - __main__ - Step 21790: {'lr': 0.00047826605142418954, 'samples': 4183680, 'steps': 21789, 'loss/train': 1.1964384317398071} 08/30/2021 17:07:10 - INFO - __main__ - Step 21791: {'lr': 0.0004782638871983795, 'samples': 4183872, 'steps': 21790, 'loss/train': 1.6358758211135864} 08/30/2021 17:07:10 - INFO - __main__ - Step 21792: {'lr': 0.0004782617228697173, 'samples': 4184064, 'steps': 21791, 'loss/train': 1.5515676736831665} 08/30/2021 17:07:11 - INFO - __main__ - Step 21793: {'lr': 0.0004782595584382039, 'samples': 4184256, 'steps': 21792, 'loss/train': 1.7221769094467163} 08/30/2021 17:07:12 - INFO - __main__ - Step 21794: {'lr': 0.0004782573939038402, 'samples': 4184448, 'steps': 21793, 'loss/train': 1.7550474405288696} 08/30/2021 17:07:12 - INFO - __main__ - Step 21795: {'lr': 0.0004782552292666273, 'samples': 4184640, 'steps': 21794, 'loss/train': 1.3632317781448364} 08/30/2021 17:07:13 - INFO - __main__ - Step 21796: {'lr': 0.0004782530645265661, 'samples': 4184832, 'steps': 21795, 'loss/train': 1.9573311805725098} 08/30/2021 17:07:13 - INFO - __main__ - Step 21797: {'lr': 0.0004782508996836576, 'samples': 4185024, 'steps': 21796, 'loss/train': 1.5223103761672974} 08/30/2021 17:07:13 - INFO - __main__ - Step 21798: {'lr': 0.00047824873473790275, 'samples': 4185216, 'steps': 21797, 'loss/train': 1.6803069114685059} 08/30/2021 17:07:15 - INFO - __main__ - Step 21799: {'lr': 0.0004782465696893025, 'samples': 4185408, 'steps': 21798, 'loss/train': 0.7478705644607544} 08/30/2021 17:07:15 - INFO - __main__ - Step 21800: {'lr': 0.0004782444045378579, 'samples': 4185600, 'steps': 21799, 'loss/train': 2.2432470321655273} 08/30/2021 17:07:16 - INFO - __main__ - Step 21801: {'lr': 0.00047824223928356993, 'samples': 4185792, 'steps': 21800, 'loss/train': 1.51249361038208} 08/30/2021 17:07:16 - INFO - __main__ - Step 21802: {'lr': 0.0004782400739264395, 'samples': 4185984, 'steps': 21801, 'loss/train': 1.9229987859725952} 08/30/2021 17:07:16 - INFO - __main__ - Step 21803: {'lr': 0.00047823790846646764, 'samples': 4186176, 'steps': 21802, 'loss/train': 1.9468880891799927} 08/30/2021 17:07:18 - INFO - __main__ - Step 21804: {'lr': 0.0004782357429036553, 'samples': 4186368, 'steps': 21803, 'loss/train': 1.4829293489456177} 08/30/2021 17:07:18 - INFO - __main__ - Step 21805: {'lr': 0.00047823357723800344, 'samples': 4186560, 'steps': 21804, 'loss/train': 1.7622202634811401} 08/30/2021 17:07:19 - INFO - __main__ - Step 21806: {'lr': 0.000478231411469513, 'samples': 4186752, 'steps': 21805, 'loss/train': 1.6974397897720337} 08/30/2021 17:07:19 - INFO - __main__ - Step 21807: {'lr': 0.000478229245598185, 'samples': 4186944, 'steps': 21806, 'loss/train': 0.7027131915092468} 08/30/2021 17:07:19 - INFO - __main__ - Step 21808: {'lr': 0.00047822707962402055, 'samples': 4187136, 'steps': 21807, 'loss/train': 1.691078543663025} 08/30/2021 17:07:21 - INFO - __main__ - Step 21809: {'lr': 0.00047822491354702044, 'samples': 4187328, 'steps': 21808, 'loss/train': 1.4254356622695923} 08/30/2021 17:07:21 - INFO - __main__ - Step 21810: {'lr': 0.0004782227473671857, 'samples': 4187520, 'steps': 21809, 'loss/train': 0.9605146646499634} 08/30/2021 17:07:22 - INFO - __main__ - Step 21811: {'lr': 0.00047822058108451727, 'samples': 4187712, 'steps': 21810, 'loss/train': 1.3175225257873535} 08/30/2021 17:07:22 - INFO - __main__ - Step 21812: {'lr': 0.0004782184146990162, 'samples': 4187904, 'steps': 21811, 'loss/train': 1.8008755445480347} 08/30/2021 17:07:22 - INFO - __main__ - Step 21813: {'lr': 0.00047821624821068346, 'samples': 4188096, 'steps': 21812, 'loss/train': 3.052218198776245} 08/30/2021 17:07:24 - INFO - __main__ - Step 21814: {'lr': 0.00047821408161952, 'samples': 4188288, 'steps': 21813, 'loss/train': 1.5098425149917603} 08/30/2021 17:07:24 - INFO - __main__ - Step 21815: {'lr': 0.00047821191492552676, 'samples': 4188480, 'steps': 21814, 'loss/train': 1.8102848529815674} 08/30/2021 17:07:25 - INFO - __main__ - Step 21816: {'lr': 0.00047820974812870477, 'samples': 4188672, 'steps': 21815, 'loss/train': 1.5876659154891968} 08/30/2021 17:07:25 - INFO - __main__ - Step 21817: {'lr': 0.00047820758122905493, 'samples': 4188864, 'steps': 21816, 'loss/train': 1.1264034509658813} 08/30/2021 17:07:25 - INFO - __main__ - Step 21818: {'lr': 0.0004782054142265784, 'samples': 4189056, 'steps': 21817, 'loss/train': 1.609885573387146} 08/30/2021 17:07:26 - INFO - __main__ - Step 21819: {'lr': 0.00047820324712127593, 'samples': 4189248, 'steps': 21818, 'loss/train': 1.475606083869934} 08/30/2021 17:07:27 - INFO - __main__ - Step 21820: {'lr': 0.0004782010799131487, 'samples': 4189440, 'steps': 21819, 'loss/train': 1.5146722793579102} 08/30/2021 17:07:28 - INFO - __main__ - Step 21821: {'lr': 0.0004781989126021975, 'samples': 4189632, 'steps': 21820, 'loss/train': 1.1020145416259766} 08/30/2021 17:07:28 - INFO - __main__ - Step 21822: {'lr': 0.00047819674518842335, 'samples': 4189824, 'steps': 21821, 'loss/train': 1.297472596168518} 08/30/2021 17:07:28 - INFO - __main__ - Step 21823: {'lr': 0.00047819457767182735, 'samples': 4190016, 'steps': 21822, 'loss/train': 1.6172099113464355} 08/30/2021 17:07:29 - INFO - __main__ - Step 21824: {'lr': 0.0004781924100524104, 'samples': 4190208, 'steps': 21823, 'loss/train': 1.5605764389038086} 08/30/2021 17:07:30 - INFO - __main__ - Step 21825: {'lr': 0.00047819024233017337, 'samples': 4190400, 'steps': 21824, 'loss/train': 1.5563044548034668} 08/30/2021 17:07:31 - INFO - __main__ - Step 21826: {'lr': 0.00047818807450511746, 'samples': 4190592, 'steps': 21825, 'loss/train': 1.235628366470337} 08/30/2021 17:07:31 - INFO - __main__ - Step 21827: {'lr': 0.00047818590657724345, 'samples': 4190784, 'steps': 21826, 'loss/train': 1.9041955471038818} 08/30/2021 17:07:31 - INFO - __main__ - Step 21828: {'lr': 0.0004781837385465524, 'samples': 4190976, 'steps': 21827, 'loss/train': 1.5375030040740967} 08/30/2021 17:07:32 - INFO - __main__ - Step 21829: {'lr': 0.00047818157041304535, 'samples': 4191168, 'steps': 21828, 'loss/train': 2.0281591415405273} 08/30/2021 17:07:33 - INFO - __main__ - Step 21830: {'lr': 0.00047817940217672315, 'samples': 4191360, 'steps': 21829, 'loss/train': 0.9340408444404602} 08/30/2021 17:07:34 - INFO - __main__ - Step 21831: {'lr': 0.0004781772338375868, 'samples': 4191552, 'steps': 21830, 'loss/train': 1.8971073627471924} 08/30/2021 17:07:34 - INFO - __main__ - Step 21832: {'lr': 0.0004781750653956374, 'samples': 4191744, 'steps': 21831, 'loss/train': 2.3435568809509277} 08/30/2021 17:07:34 - INFO - __main__ - Step 21833: {'lr': 0.00047817289685087575, 'samples': 4191936, 'steps': 21832, 'loss/train': 0.17955322563648224} 08/30/2021 17:07:35 - INFO - __main__ - Step 21834: {'lr': 0.00047817072820330287, 'samples': 4192128, 'steps': 21833, 'loss/train': 1.461944580078125} 08/30/2021 17:07:36 - INFO - __main__ - Step 21835: {'lr': 0.0004781685594529199, 'samples': 4192320, 'steps': 21834, 'loss/train': 1.583033800125122} 08/30/2021 17:07:36 - INFO - __main__ - Step 21836: {'lr': 0.00047816639059972767, 'samples': 4192512, 'steps': 21835, 'loss/train': 1.778618335723877} 08/30/2021 17:07:37 - INFO - __main__ - Step 21837: {'lr': 0.00047816422164372713, 'samples': 4192704, 'steps': 21836, 'loss/train': 0.9923926591873169} 08/30/2021 17:07:37 - INFO - __main__ - Step 21838: {'lr': 0.00047816205258491935, 'samples': 4192896, 'steps': 21837, 'loss/train': 1.445613145828247} 08/30/2021 17:07:38 - INFO - __main__ - Step 21839: {'lr': 0.0004781598834233053, 'samples': 4193088, 'steps': 21838, 'loss/train': 1.4672938585281372} 08/30/2021 17:07:40 - INFO - __main__ - Step 21840: {'lr': 0.0004781577141588859, 'samples': 4193280, 'steps': 21839, 'loss/train': 1.6474761962890625} 08/30/2021 17:07:40 - INFO - __main__ - Step 21841: {'lr': 0.0004781555447916621, 'samples': 4193472, 'steps': 21840, 'loss/train': 1.7598116397857666} 08/30/2021 17:07:40 - INFO - __main__ - Step 21842: {'lr': 0.000478153375321635, 'samples': 4193664, 'steps': 21841, 'loss/train': 0.5458323955535889} 08/30/2021 17:07:41 - INFO - __main__ - Step 21843: {'lr': 0.0004781512057488055, 'samples': 4193856, 'steps': 21842, 'loss/train': 1.0545837879180908} 08/30/2021 17:07:41 - INFO - __main__ - Step 21844: {'lr': 0.00047814903607317454, 'samples': 4194048, 'steps': 21843, 'loss/train': 1.4126092195510864} 08/30/2021 17:07:43 - INFO - __main__ - Step 21845: {'lr': 0.00047814686629474323, 'samples': 4194240, 'steps': 21844, 'loss/train': 1.4072014093399048} 08/30/2021 17:07:43 - INFO - __main__ - Step 21846: {'lr': 0.00047814469641351237, 'samples': 4194432, 'steps': 21845, 'loss/train': 1.3051915168762207} 08/30/2021 17:07:43 - INFO - __main__ - Step 21847: {'lr': 0.0004781425264294831, 'samples': 4194624, 'steps': 21846, 'loss/train': 1.7459301948547363} 08/30/2021 17:07:44 - INFO - __main__ - Step 21848: {'lr': 0.0004781403563426563, 'samples': 4194816, 'steps': 21847, 'loss/train': 1.3173969984054565} 08/30/2021 17:07:44 - INFO - __main__ - Step 21849: {'lr': 0.00047813818615303295, 'samples': 4195008, 'steps': 21848, 'loss/train': 1.407995343208313} 08/30/2021 17:07:46 - INFO - __main__ - Step 21850: {'lr': 0.00047813601586061414, 'samples': 4195200, 'steps': 21849, 'loss/train': 1.3913586139678955} 08/30/2021 17:07:46 - INFO - __main__ - Step 21851: {'lr': 0.0004781338454654007, 'samples': 4195392, 'steps': 21850, 'loss/train': 1.4758920669555664} 08/30/2021 17:07:46 - INFO - __main__ - Step 21852: {'lr': 0.00047813167496739363, 'samples': 4195584, 'steps': 21851, 'loss/train': 2.059255838394165} 08/30/2021 17:07:47 - INFO - __main__ - Step 21853: {'lr': 0.00047812950436659405, 'samples': 4195776, 'steps': 21852, 'loss/train': 1.5771533250808716} 08/30/2021 17:07:47 - INFO - __main__ - Step 21854: {'lr': 0.0004781273336630028, 'samples': 4195968, 'steps': 21853, 'loss/train': 2.0807173252105713} 08/30/2021 17:07:49 - INFO - __main__ - Step 21855: {'lr': 0.00047812516285662086, 'samples': 4196160, 'steps': 21854, 'loss/train': 1.947556972503662} 08/30/2021 17:07:50 - INFO - __main__ - Step 21856: {'lr': 0.00047812299194744924, 'samples': 4196352, 'steps': 21855, 'loss/train': 1.3786648511886597} 08/30/2021 17:07:50 - INFO - __main__ - Step 21857: {'lr': 0.0004781208209354889, 'samples': 4196544, 'steps': 21856, 'loss/train': 0.08374021202325821} 08/30/2021 17:07:50 - INFO - __main__ - Step 21858: {'lr': 0.00047811864982074087, 'samples': 4196736, 'steps': 21857, 'loss/train': 1.6885826587677002} 08/30/2021 17:07:51 - INFO - __main__ - Step 21859: {'lr': 0.0004781164786032061, 'samples': 4196928, 'steps': 21858, 'loss/train': 0.2487347275018692} 08/30/2021 17:07:51 - INFO - __main__ - Step 21860: {'lr': 0.0004781143072828856, 'samples': 4197120, 'steps': 21859, 'loss/train': 0.22958756983280182} 08/30/2021 17:07:51 - INFO - __main__ - Step 21861: {'lr': 0.00047811213585978023, 'samples': 4197312, 'steps': 21860, 'loss/train': 1.1175928115844727} 08/30/2021 17:07:53 - INFO - __main__ - Step 21862: {'lr': 0.0004781099643338911, 'samples': 4197504, 'steps': 21861, 'loss/train': 2.00122332572937} 08/30/2021 17:07:54 - INFO - __main__ - Step 21863: {'lr': 0.00047810779270521914, 'samples': 4197696, 'steps': 21862, 'loss/train': 1.7286481857299805} 08/30/2021 17:07:54 - INFO - __main__ - Step 21864: {'lr': 0.0004781056209737653, 'samples': 4197888, 'steps': 21863, 'loss/train': 0.907160222530365} 08/30/2021 17:07:54 - INFO - __main__ - Step 21865: {'lr': 0.00047810344913953065, 'samples': 4198080, 'steps': 21864, 'loss/train': 2.0779623985290527} 08/30/2021 17:07:55 - INFO - __main__ - Step 21866: {'lr': 0.0004781012772025161, 'samples': 4198272, 'steps': 21865, 'loss/train': 1.2352877855300903} 08/30/2021 17:07:56 - INFO - __main__ - Step 21867: {'lr': 0.0004780991051627226, 'samples': 4198464, 'steps': 21866, 'loss/train': 0.18139822781085968} 08/30/2021 17:07:57 - INFO - __main__ - Step 21868: {'lr': 0.0004780969330201511, 'samples': 4198656, 'steps': 21867, 'loss/train': 1.1665617227554321} 08/30/2021 17:07:57 - INFO - __main__ - Step 21869: {'lr': 0.0004780947607748027, 'samples': 4198848, 'steps': 21868, 'loss/train': 1.9979071617126465} 08/30/2021 17:07:57 - INFO - __main__ - Step 21870: {'lr': 0.00047809258842667837, 'samples': 4199040, 'steps': 21869, 'loss/train': 1.86331307888031} 08/30/2021 17:07:58 - INFO - __main__ - Step 21871: {'lr': 0.000478090415975779, 'samples': 4199232, 'steps': 21870, 'loss/train': 1.8044943809509277} 08/30/2021 17:07:58 - INFO - __main__ - Step 21872: {'lr': 0.00047808824342210565, 'samples': 4199424, 'steps': 21871, 'loss/train': 1.467484951019287} 08/30/2021 17:08:00 - INFO - __main__ - Step 21873: {'lr': 0.0004780860707656592, 'samples': 4199616, 'steps': 21872, 'loss/train': 1.7816983461380005} 08/30/2021 17:08:00 - INFO - __main__ - Step 21874: {'lr': 0.0004780838980064407, 'samples': 4199808, 'steps': 21873, 'loss/train': 1.5336304903030396} 08/30/2021 17:08:01 - INFO - __main__ - Step 21875: {'lr': 0.00047808172514445115, 'samples': 4200000, 'steps': 21874, 'loss/train': 0.0895189642906189} 08/30/2021 17:08:01 - INFO - __main__ - Step 21876: {'lr': 0.0004780795521796914, 'samples': 4200192, 'steps': 21875, 'loss/train': 1.2236469984054565} 08/30/2021 17:08:01 - INFO - __main__ - Step 21877: {'lr': 0.0004780773791121626, 'samples': 4200384, 'steps': 21876, 'loss/train': 1.1106677055358887} 08/30/2021 17:08:03 - INFO - __main__ - Step 21878: {'lr': 0.0004780752059418656, 'samples': 4200576, 'steps': 21877, 'loss/train': 1.9841495752334595} 08/30/2021 17:08:03 - INFO - __main__ - Step 21879: {'lr': 0.0004780730326688015, 'samples': 4200768, 'steps': 21878, 'loss/train': 1.4923685789108276} 08/30/2021 17:08:04 - INFO - __main__ - Step 21880: {'lr': 0.0004780708592929712, 'samples': 4200960, 'steps': 21879, 'loss/train': 1.6637871265411377} 08/30/2021 17:08:04 - INFO - __main__ - Step 21881: {'lr': 0.0004780686858143756, 'samples': 4201152, 'steps': 21880, 'loss/train': 1.4183932542800903} 08/30/2021 17:08:04 - INFO - __main__ - Step 21882: {'lr': 0.0004780665122330159, 'samples': 4201344, 'steps': 21881, 'loss/train': 1.4498711824417114} 08/30/2021 17:08:06 - INFO - __main__ - Step 21883: {'lr': 0.00047806433854889285, 'samples': 4201536, 'steps': 21882, 'loss/train': 1.8202253580093384} 08/30/2021 17:08:06 - INFO - __main__ - Step 21884: {'lr': 0.0004780621647620076, 'samples': 4201728, 'steps': 21883, 'loss/train': 1.8336007595062256} 08/30/2021 17:08:07 - INFO - __main__ - Step 21885: {'lr': 0.00047805999087236097, 'samples': 4201920, 'steps': 21884, 'loss/train': 1.5845669507980347} 08/30/2021 17:08:07 - INFO - __main__ - Step 21886: {'lr': 0.0004780578168799541, 'samples': 4202112, 'steps': 21885, 'loss/train': 2.684797763824463} 08/30/2021 17:08:07 - INFO - __main__ - Step 21887: {'lr': 0.00047805564278478787, 'samples': 4202304, 'steps': 21886, 'loss/train': 1.976189136505127} 08/30/2021 17:08:09 - INFO - __main__ - Step 21888: {'lr': 0.00047805346858686325, 'samples': 4202496, 'steps': 21887, 'loss/train': 0.3722270131111145} 08/30/2021 17:08:09 - INFO - __main__ - Step 21889: {'lr': 0.0004780512942861813, 'samples': 4202688, 'steps': 21888, 'loss/train': 1.7283111810684204} 08/30/2021 17:08:10 - INFO - __main__ - Step 21890: {'lr': 0.00047804911988274303, 'samples': 4202880, 'steps': 21889, 'loss/train': 1.2118431329727173} 08/30/2021 17:08:10 - INFO - __main__ - Step 21891: {'lr': 0.00047804694537654927, 'samples': 4203072, 'steps': 21890, 'loss/train': 1.284872055053711} 08/30/2021 17:08:11 - INFO - __main__ - Step 21892: {'lr': 0.00047804477076760106, 'samples': 4203264, 'steps': 21891, 'loss/train': 1.4628698825836182} 08/30/2021 17:08:12 - INFO - __main__ - Step 21893: {'lr': 0.0004780425960558994, 'samples': 4203456, 'steps': 21892, 'loss/train': 1.623253583908081} 08/30/2021 17:08:13 - INFO - __main__ - Step 21894: {'lr': 0.00047804042124144526, 'samples': 4203648, 'steps': 21893, 'loss/train': 1.5874764919281006} 08/30/2021 17:08:13 - INFO - __main__ - Step 21895: {'lr': 0.00047803824632423967, 'samples': 4203840, 'steps': 21894, 'loss/train': 2.083956480026245} 08/30/2021 17:08:13 - INFO - __main__ - Step 21896: {'lr': 0.0004780360713042835, 'samples': 4204032, 'steps': 21895, 'loss/train': 1.4926472902297974} 08/30/2021 17:08:14 - INFO - __main__ - Step 21897: {'lr': 0.0004780338961815779, 'samples': 4204224, 'steps': 21896, 'loss/train': 1.7445399761199951} 08/30/2021 17:08:16 - INFO - __main__ - Step 21898: {'lr': 0.00047803172095612365, 'samples': 4204416, 'steps': 21897, 'loss/train': 1.6326509714126587} 08/30/2021 17:08:16 - INFO - __main__ - Step 21899: {'lr': 0.00047802954562792185, 'samples': 4204608, 'steps': 21898, 'loss/train': 1.4807627201080322} 08/30/2021 17:08:16 - INFO - __main__ - Step 21900: {'lr': 0.0004780273701969734, 'samples': 4204800, 'steps': 21899, 'loss/train': 1.3924874067306519} 08/30/2021 17:08:17 - INFO - __main__ - Step 21901: {'lr': 0.00047802519466327945, 'samples': 4204992, 'steps': 21900, 'loss/train': 1.9246954917907715} 08/30/2021 17:08:17 - INFO - __main__ - Step 21902: {'lr': 0.00047802301902684076, 'samples': 4205184, 'steps': 21901, 'loss/train': 1.831890344619751} 08/30/2021 17:08:17 - INFO - __main__ - Step 21903: {'lr': 0.0004780208432876585, 'samples': 4205376, 'steps': 21902, 'loss/train': 1.668404221534729} 08/30/2021 17:08:19 - INFO - __main__ - Step 21904: {'lr': 0.00047801866744573353, 'samples': 4205568, 'steps': 21903, 'loss/train': 1.7075095176696777} 08/30/2021 17:08:20 - INFO - __main__ - Step 21905: {'lr': 0.00047801649150106684, 'samples': 4205760, 'steps': 21904, 'loss/train': 1.4642846584320068} 08/30/2021 17:08:20 - INFO - __main__ - Step 21906: {'lr': 0.00047801431545365947, 'samples': 4205952, 'steps': 21905, 'loss/train': 1.674008846282959} 08/30/2021 17:08:20 - INFO - __main__ - Step 21907: {'lr': 0.0004780121393035124, 'samples': 4206144, 'steps': 21906, 'loss/train': 1.1540557146072388} 08/30/2021 17:08:21 - INFO - __main__ - Step 21908: {'lr': 0.0004780099630506265, 'samples': 4206336, 'steps': 21907, 'loss/train': 1.779233694076538} 08/30/2021 17:08:22 - INFO - __main__ - Step 21909: {'lr': 0.0004780077866950029, 'samples': 4206528, 'steps': 21908, 'loss/train': 0.6303631067276001} 08/30/2021 17:08:23 - INFO - __main__ - Step 21910: {'lr': 0.00047800561023664246, 'samples': 4206720, 'steps': 21909, 'loss/train': 1.7209911346435547} 08/30/2021 17:08:23 - INFO - __main__ - Step 21911: {'lr': 0.0004780034336755462, 'samples': 4206912, 'steps': 21910, 'loss/train': 1.7233561277389526} 08/30/2021 17:08:23 - INFO - __main__ - Step 21912: {'lr': 0.00047800125701171517, 'samples': 4207104, 'steps': 21911, 'loss/train': 2.067147731781006} 08/30/2021 17:08:24 - INFO - __main__ - Step 21913: {'lr': 0.00047799908024515026, 'samples': 4207296, 'steps': 21912, 'loss/train': 1.0405805110931396} 08/30/2021 17:08:25 - INFO - __main__ - Step 21914: {'lr': 0.0004779969033758525, 'samples': 4207488, 'steps': 21913, 'loss/train': 1.331740379333496} 08/30/2021 17:08:26 - INFO - __main__ - Step 21915: {'lr': 0.00047799472640382287, 'samples': 4207680, 'steps': 21914, 'loss/train': 1.4365123510360718} 08/30/2021 17:08:26 - INFO - __main__ - Step 21916: {'lr': 0.0004779925493290623, 'samples': 4207872, 'steps': 21915, 'loss/train': 1.0958466529846191} 08/30/2021 17:08:27 - INFO - __main__ - Step 21917: {'lr': 0.00047799037215157184, 'samples': 4208064, 'steps': 21916, 'loss/train': 1.3608423471450806} 08/30/2021 17:08:27 - INFO - __main__ - Step 21918: {'lr': 0.0004779881948713524, 'samples': 4208256, 'steps': 21917, 'loss/train': 0.11266614496707916} 08/30/2021 17:08:28 - INFO - __main__ - Step 21919: {'lr': 0.000477986017488405, 'samples': 4208448, 'steps': 21918, 'loss/train': 1.7626110315322876} 08/30/2021 17:08:29 - INFO - __main__ - Step 21920: {'lr': 0.00047798384000273053, 'samples': 4208640, 'steps': 21919, 'loss/train': 0.45796090364456177} 08/30/2021 17:08:29 - INFO - __main__ - Step 21921: {'lr': 0.0004779816624143302, 'samples': 4208832, 'steps': 21920, 'loss/train': 1.6454553604125977} 08/30/2021 17:08:29 - INFO - __main__ - Step 21922: {'lr': 0.0004779794847232048, 'samples': 4209024, 'steps': 21921, 'loss/train': 2.0480148792266846} 08/30/2021 17:08:30 - INFO - __main__ - Step 21923: {'lr': 0.0004779773069293554, 'samples': 4209216, 'steps': 21922, 'loss/train': 1.4627642631530762} 08/30/2021 17:08:31 - INFO - __main__ - Step 21924: {'lr': 0.00047797512903278283, 'samples': 4209408, 'steps': 21923, 'loss/train': 1.6264673471450806} 08/30/2021 17:08:32 - INFO - __main__ - Step 21925: {'lr': 0.0004779729510334883, 'samples': 4209600, 'steps': 21924, 'loss/train': 1.714000940322876} 08/30/2021 17:08:32 - INFO - __main__ - Step 21926: {'lr': 0.0004779707729314726, 'samples': 4209792, 'steps': 21925, 'loss/train': 1.7017693519592285} 08/30/2021 17:08:33 - INFO - __main__ - Step 21927: {'lr': 0.0004779685947267369, 'samples': 4209984, 'steps': 21926, 'loss/train': 2.342733383178711} 08/30/2021 17:08:33 - INFO - __main__ - Step 21928: {'lr': 0.00047796641641928195, 'samples': 4210176, 'steps': 21927, 'loss/train': 1.6500569581985474} 08/30/2021 17:08:33 - INFO - __main__ - Step 21929: {'lr': 0.00047796423800910894, 'samples': 4210368, 'steps': 21928, 'loss/train': 1.351326823234558} 08/30/2021 17:08:35 - INFO - __main__ - Step 21930: {'lr': 0.00047796205949621873, 'samples': 4210560, 'steps': 21929, 'loss/train': 1.819567084312439} 08/30/2021 17:08:35 - INFO - __main__ - Step 21931: {'lr': 0.00047795988088061224, 'samples': 4210752, 'steps': 21930, 'loss/train': 2.0995278358459473} 08/30/2021 17:08:36 - INFO - __main__ - Step 21932: {'lr': 0.00047795770216229065, 'samples': 4210944, 'steps': 21931, 'loss/train': 1.5262372493743896} 08/30/2021 17:08:36 - INFO - __main__ - Step 21933: {'lr': 0.0004779555233412548, 'samples': 4211136, 'steps': 21932, 'loss/train': 1.0073091983795166} 08/30/2021 17:08:36 - INFO - __main__ - Step 21934: {'lr': 0.0004779533444175058, 'samples': 4211328, 'steps': 21933, 'loss/train': 1.5977104902267456} 08/30/2021 17:08:38 - INFO - __main__ - Step 21935: {'lr': 0.00047795116539104445, 'samples': 4211520, 'steps': 21934, 'loss/train': 1.2242472171783447} 08/30/2021 17:08:38 - INFO - __main__ - Step 21936: {'lr': 0.0004779489862618718, 'samples': 4211712, 'steps': 21935, 'loss/train': 1.6662166118621826} 08/30/2021 17:08:39 - INFO - __main__ - Step 21937: {'lr': 0.00047794680702998893, 'samples': 4211904, 'steps': 21936, 'loss/train': 0.9240788817405701} 08/30/2021 17:08:39 - INFO - __main__ - Step 21938: {'lr': 0.0004779446276953967, 'samples': 4212096, 'steps': 21937, 'loss/train': 0.2507948577404022} 08/30/2021 17:08:39 - INFO - __main__ - Step 21939: {'lr': 0.00047794244825809614, 'samples': 4212288, 'steps': 21938, 'loss/train': 1.4775242805480957} 08/30/2021 17:08:40 - INFO - __main__ - Step 21940: {'lr': 0.0004779402687180882, 'samples': 4212480, 'steps': 21939, 'loss/train': 1.4736164808273315} 08/30/2021 17:08:41 - INFO - __main__ - Step 21941: {'lr': 0.00047793808907537394, 'samples': 4212672, 'steps': 21940, 'loss/train': 1.6653746366500854} 08/30/2021 17:08:42 - INFO - __main__ - Step 21942: {'lr': 0.0004779359093299543, 'samples': 4212864, 'steps': 21941, 'loss/train': 1.8226401805877686} 08/30/2021 17:08:42 - INFO - __main__ - Step 21943: {'lr': 0.00047793372948183024, 'samples': 4213056, 'steps': 21942, 'loss/train': 1.7302875518798828} 08/30/2021 17:08:42 - INFO - __main__ - Step 21944: {'lr': 0.0004779315495310027, 'samples': 4213248, 'steps': 21943, 'loss/train': 1.924445629119873} 08/30/2021 17:08:43 - INFO - __main__ - Step 21945: {'lr': 0.00047792936947747285, 'samples': 4213440, 'steps': 21944, 'loss/train': 1.7569037675857544} 08/30/2021 17:08:44 - INFO - __main__ - Step 21946: {'lr': 0.00047792718932124147, 'samples': 4213632, 'steps': 21945, 'loss/train': 2.1364247798919678} 08/30/2021 17:08:45 - INFO - __main__ - Step 21947: {'lr': 0.00047792500906230963, 'samples': 4213824, 'steps': 21946, 'loss/train': 1.0786246061325073} 08/30/2021 17:08:45 - INFO - __main__ - Step 21948: {'lr': 0.00047792282870067827, 'samples': 4214016, 'steps': 21947, 'loss/train': 0.824955403804779} 08/30/2021 17:08:46 - INFO - __main__ - Step 21949: {'lr': 0.0004779206482363484, 'samples': 4214208, 'steps': 21948, 'loss/train': 2.175302267074585} 08/30/2021 17:08:46 - INFO - __main__ - Step 21950: {'lr': 0.000477918467669321, 'samples': 4214400, 'steps': 21949, 'loss/train': 1.7836651802062988} 08/30/2021 17:08:48 - INFO - __main__ - Step 21951: {'lr': 0.0004779162869995971, 'samples': 4214592, 'steps': 21950, 'loss/train': 1.2974724769592285} 08/30/2021 17:08:49 - INFO - __main__ - Step 21952: {'lr': 0.00047791410622717757, 'samples': 4214784, 'steps': 21951, 'loss/train': 1.5132735967636108} 08/30/2021 17:08:49 - INFO - __main__ - Step 21953: {'lr': 0.0004779119253520635, 'samples': 4214976, 'steps': 21952, 'loss/train': 1.8830792903900146} 08/30/2021 17:08:49 - INFO - __main__ - Step 21954: {'lr': 0.0004779097443742558, 'samples': 4215168, 'steps': 21953, 'loss/train': 1.4688997268676758} 08/30/2021 17:08:50 - INFO - __main__ - Step 21955: {'lr': 0.0004779075632937556, 'samples': 4215360, 'steps': 21954, 'loss/train': 1.3895879983901978} 08/30/2021 17:08:51 - INFO - __main__ - Step 21956: {'lr': 0.00047790538211056366, 'samples': 4215552, 'steps': 21955, 'loss/train': 1.9342215061187744} 08/30/2021 17:08:52 - INFO - __main__ - Step 21957: {'lr': 0.00047790320082468106, 'samples': 4215744, 'steps': 21956, 'loss/train': 1.418033242225647} 08/30/2021 17:08:52 - INFO - __main__ - Step 21958: {'lr': 0.00047790101943610884, 'samples': 4215936, 'steps': 21957, 'loss/train': 1.506151795387268} 08/30/2021 17:08:53 - INFO - __main__ - Step 21959: {'lr': 0.000477898837944848, 'samples': 4216128, 'steps': 21958, 'loss/train': 1.7700694799423218} 08/30/2021 17:08:53 - INFO - __main__ - Step 21960: {'lr': 0.0004778966563508994, 'samples': 4216320, 'steps': 21959, 'loss/train': 0.7527241110801697} 08/30/2021 17:08:53 - INFO - __main__ - Step 21961: {'lr': 0.00047789447465426406, 'samples': 4216512, 'steps': 21960, 'loss/train': 1.2421972751617432} 08/30/2021 17:08:55 - INFO - __main__ - Step 21962: {'lr': 0.000477892292854943, 'samples': 4216704, 'steps': 21961, 'loss/train': 2.6127634048461914} 08/30/2021 17:08:55 - INFO - __main__ - Step 21963: {'lr': 0.00047789011095293723, 'samples': 4216896, 'steps': 21962, 'loss/train': 1.4230536222457886} 08/30/2021 17:08:56 - INFO - __main__ - Step 21964: {'lr': 0.0004778879289482476, 'samples': 4217088, 'steps': 21963, 'loss/train': 1.4664710760116577} 08/30/2021 17:08:56 - INFO - __main__ - Step 21965: {'lr': 0.00047788574684087527, 'samples': 4217280, 'steps': 21964, 'loss/train': 0.14407892525196075} 08/30/2021 17:08:56 - INFO - __main__ - Step 21966: {'lr': 0.0004778835646308211, 'samples': 4217472, 'steps': 21965, 'loss/train': 1.5930671691894531} 08/30/2021 17:08:58 - INFO - __main__ - Step 21967: {'lr': 0.0004778813823180861, 'samples': 4217664, 'steps': 21966, 'loss/train': 1.876437783241272} 08/30/2021 17:08:58 - INFO - __main__ - Step 21968: {'lr': 0.0004778791999026713, 'samples': 4217856, 'steps': 21967, 'loss/train': 1.6596248149871826} 08/30/2021 17:08:59 - INFO - __main__ - Step 21969: {'lr': 0.0004778770173845777, 'samples': 4218048, 'steps': 21968, 'loss/train': 1.4142649173736572} 08/30/2021 17:08:59 - INFO - __main__ - Step 21970: {'lr': 0.00047787483476380613, 'samples': 4218240, 'steps': 21969, 'loss/train': 1.1690462827682495} 08/30/2021 17:08:59 - INFO - __main__ - Step 21971: {'lr': 0.0004778726520403577, 'samples': 4218432, 'steps': 21970, 'loss/train': 1.791285514831543} 08/30/2021 17:09:01 - INFO - __main__ - Step 21972: {'lr': 0.00047787046921423336, 'samples': 4218624, 'steps': 21971, 'loss/train': 1.278337836265564} 08/30/2021 17:09:01 - INFO - __main__ - Step 21973: {'lr': 0.00047786828628543416, 'samples': 4218816, 'steps': 21972, 'loss/train': 2.0375607013702393} 08/30/2021 17:09:02 - INFO - __main__ - Step 21974: {'lr': 0.00047786610325396096, 'samples': 4219008, 'steps': 21973, 'loss/train': 1.6423488855361938} 08/30/2021 17:09:02 - INFO - __main__ - Step 21975: {'lr': 0.0004778639201198149, 'samples': 4219200, 'steps': 21974, 'loss/train': 1.9463797807693481} 08/30/2021 17:09:03 - INFO - __main__ - Step 21976: {'lr': 0.00047786173688299684, 'samples': 4219392, 'steps': 21975, 'loss/train': 2.127964496612549} 08/30/2021 17:09:03 - INFO - __main__ - Step 21977: {'lr': 0.00047785955354350776, 'samples': 4219584, 'steps': 21976, 'loss/train': 1.3553804159164429} 08/30/2021 17:09:04 - INFO - __main__ - Step 21978: {'lr': 0.00047785737010134865, 'samples': 4219776, 'steps': 21977, 'loss/train': 1.9687639474868774} 08/30/2021 17:09:05 - INFO - __main__ - Step 21979: {'lr': 0.0004778551865565206, 'samples': 4219968, 'steps': 21978, 'loss/train': 0.9866222739219666} 08/30/2021 17:09:05 - INFO - __main__ - Step 21980: {'lr': 0.00047785300290902446, 'samples': 4220160, 'steps': 21979, 'loss/train': 1.6148606538772583} 08/30/2021 17:09:05 - INFO - __main__ - Step 21981: {'lr': 0.0004778508191588613, 'samples': 4220352, 'steps': 21980, 'loss/train': 1.819076657295227} 08/30/2021 17:09:06 - INFO - __main__ - Step 21982: {'lr': 0.00047784863530603213, 'samples': 4220544, 'steps': 21981, 'loss/train': 1.618833065032959} 08/30/2021 17:09:07 - INFO - __main__ - Step 21983: {'lr': 0.0004778464513505378, 'samples': 4220736, 'steps': 21982, 'loss/train': 1.7028850317001343} 08/30/2021 17:09:08 - INFO - __main__ - Step 21984: {'lr': 0.0004778442672923794, 'samples': 4220928, 'steps': 21983, 'loss/train': 1.8046437501907349} 08/30/2021 17:09:08 - INFO - __main__ - Step 21985: {'lr': 0.0004778420831315579, 'samples': 4221120, 'steps': 21984, 'loss/train': 1.4114447832107544} 08/30/2021 17:09:09 - INFO - __main__ - Step 21986: {'lr': 0.0004778398988680743, 'samples': 4221312, 'steps': 21985, 'loss/train': 1.4717018604278564} 08/30/2021 17:09:09 - INFO - __main__ - Step 21987: {'lr': 0.00047783771450192946, 'samples': 4221504, 'steps': 21986, 'loss/train': 1.534753441810608} 08/30/2021 17:09:10 - INFO - __main__ - Step 21988: {'lr': 0.00047783553003312456, 'samples': 4221696, 'steps': 21987, 'loss/train': 1.4537556171417236} 08/30/2021 17:09:11 - INFO - __main__ - Step 21989: {'lr': 0.00047783334546166046, 'samples': 4221888, 'steps': 21988, 'loss/train': 1.511865258216858} 08/30/2021 17:09:11 - INFO - __main__ - Step 21990: {'lr': 0.0004778311607875382, 'samples': 4222080, 'steps': 21989, 'loss/train': 1.6200644969940186} 08/30/2021 17:09:12 - INFO - __main__ - Step 21991: {'lr': 0.0004778289760107587, 'samples': 4222272, 'steps': 21990, 'loss/train': 1.7906439304351807} 08/30/2021 17:09:12 - INFO - __main__ - Step 21992: {'lr': 0.00047782679113132293, 'samples': 4222464, 'steps': 21991, 'loss/train': 0.6283571720123291} 08/30/2021 17:09:13 - INFO - __main__ - Step 21993: {'lr': 0.00047782460614923195, 'samples': 4222656, 'steps': 21992, 'loss/train': 1.5765588283538818} 08/30/2021 17:09:14 - INFO - __main__ - Step 21994: {'lr': 0.00047782242106448675, 'samples': 4222848, 'steps': 21993, 'loss/train': 2.792832851409912} 08/30/2021 17:09:14 - INFO - __main__ - Step 21995: {'lr': 0.00047782023587708826, 'samples': 4223040, 'steps': 21994, 'loss/train': 1.3331061601638794} 08/30/2021 17:09:15 - INFO - __main__ - Step 21996: {'lr': 0.0004778180505870375, 'samples': 4223232, 'steps': 21995, 'loss/train': 1.5808993577957153} 08/30/2021 17:09:15 - INFO - __main__ - Step 21997: {'lr': 0.0004778158651943355, 'samples': 4223424, 'steps': 21996, 'loss/train': 1.5907156467437744} 08/30/2021 17:09:16 - INFO - __main__ - Step 21998: {'lr': 0.0004778136796989831, 'samples': 4223616, 'steps': 21997, 'loss/train': 1.80043363571167} 08/30/2021 17:09:17 - INFO - __main__ - Step 21999: {'lr': 0.0004778114941009814, 'samples': 4223808, 'steps': 21998, 'loss/train': 1.2608749866485596} 08/30/2021 17:09:17 - INFO - __main__ - Step 22000: {'lr': 0.0004778093084003313, 'samples': 4224000, 'steps': 21999, 'loss/train': 0.8539326190948486} 08/30/2021 17:09:18 - INFO - __main__ - Step 22001: {'lr': 0.00047780712259703394, 'samples': 4224192, 'steps': 22000, 'loss/train': 1.4201937913894653} 08/30/2021 17:09:18 - INFO - __main__ - Step 22002: {'lr': 0.00047780493669109017, 'samples': 4224384, 'steps': 22001, 'loss/train': 1.4182732105255127} 08/30/2021 17:09:20 - INFO - __main__ - Step 22003: {'lr': 0.000477802750682501, 'samples': 4224576, 'steps': 22002, 'loss/train': 1.5219247341156006} 08/30/2021 17:09:20 - INFO - __main__ - Step 22004: {'lr': 0.0004778005645712674, 'samples': 4224768, 'steps': 22003, 'loss/train': 1.7167892456054688} 08/30/2021 17:09:20 - INFO - __main__ - Step 22005: {'lr': 0.00047779837835739043, 'samples': 4224960, 'steps': 22004, 'loss/train': 0.8052094578742981} 08/30/2021 17:09:21 - INFO - __main__ - Step 22006: {'lr': 0.000477796192040871, 'samples': 4225152, 'steps': 22005, 'loss/train': 1.5867869853973389} 08/30/2021 17:09:21 - INFO - __main__ - Step 22007: {'lr': 0.00047779400562171016, 'samples': 4225344, 'steps': 22006, 'loss/train': 1.7160247564315796} 08/30/2021 17:09:21 - INFO - __main__ - Step 22008: {'lr': 0.00047779181909990876, 'samples': 4225536, 'steps': 22007, 'loss/train': 1.509312391281128} 08/30/2021 17:09:23 - INFO - __main__ - Step 22009: {'lr': 0.000477789632475468, 'samples': 4225728, 'steps': 22008, 'loss/train': 1.5153206586837769} 08/30/2021 17:09:24 - INFO - __main__ - Step 22010: {'lr': 0.00047778744574838864, 'samples': 4225920, 'steps': 22009, 'loss/train': 2.194248676300049} 08/30/2021 17:09:24 - INFO - __main__ - Step 22011: {'lr': 0.00047778525891867187, 'samples': 4226112, 'steps': 22010, 'loss/train': 2.2969167232513428} 08/30/2021 17:09:25 - INFO - __main__ - Step 22012: {'lr': 0.00047778307198631856, 'samples': 4226304, 'steps': 22011, 'loss/train': 1.2941278219223022} 08/30/2021 17:09:25 - INFO - __main__ - Step 22013: {'lr': 0.00047778088495132963, 'samples': 4226496, 'steps': 22012, 'loss/train': 1.1696702241897583} 08/30/2021 17:09:26 - INFO - __main__ - Step 22014: {'lr': 0.0004777786978137062, 'samples': 4226688, 'steps': 22013, 'loss/train': 1.2197378873825073} 08/30/2021 17:09:27 - INFO - __main__ - Step 22015: {'lr': 0.00047777651057344915, 'samples': 4226880, 'steps': 22014, 'loss/train': 1.7497295141220093} 08/30/2021 17:09:27 - INFO - __main__ - Step 22016: {'lr': 0.0004777743232305596, 'samples': 4227072, 'steps': 22015, 'loss/train': 1.6060482263565063} 08/30/2021 17:09:28 - INFO - __main__ - Step 22017: {'lr': 0.00047777213578503844, 'samples': 4227264, 'steps': 22016, 'loss/train': 1.1682275533676147} 08/30/2021 17:09:28 - INFO - __main__ - Step 22018: {'lr': 0.0004777699482368867, 'samples': 4227456, 'steps': 22017, 'loss/train': 1.8457088470458984} 08/30/2021 17:09:29 - INFO - __main__ - Step 22019: {'lr': 0.00047776776058610525, 'samples': 4227648, 'steps': 22018, 'loss/train': 2.1102287769317627} 08/30/2021 17:09:30 - INFO - __main__ - Step 22020: {'lr': 0.0004777655728326952, 'samples': 4227840, 'steps': 22019, 'loss/train': 1.5147463083267212} 08/30/2021 17:09:30 - INFO - __main__ - Step 22021: {'lr': 0.0004777633849766575, 'samples': 4228032, 'steps': 22020, 'loss/train': 2.064711570739746} 08/30/2021 17:09:31 - INFO - __main__ - Step 22022: {'lr': 0.00047776119701799317, 'samples': 4228224, 'steps': 22021, 'loss/train': 1.7333000898361206} 08/30/2021 17:09:31 - INFO - __main__ - Step 22023: {'lr': 0.0004777590089567031, 'samples': 4228416, 'steps': 22022, 'loss/train': 1.8635295629501343} 08/30/2021 17:09:33 - INFO - __main__ - Step 22024: {'lr': 0.00047775682079278836, 'samples': 4228608, 'steps': 22023, 'loss/train': 1.6678019762039185} 08/30/2021 17:09:33 - INFO - __main__ - Step 22025: {'lr': 0.0004777546325262499, 'samples': 4228800, 'steps': 22024, 'loss/train': 1.0993646383285522} 08/30/2021 17:09:34 - INFO - __main__ - Step 22026: {'lr': 0.00047775244415708873, 'samples': 4228992, 'steps': 22025, 'loss/train': 1.463771104812622} 08/30/2021 17:09:34 - INFO - __main__ - Step 22027: {'lr': 0.0004777502556853058, 'samples': 4229184, 'steps': 22026, 'loss/train': 0.112718865275383} 08/30/2021 17:09:34 - INFO - __main__ - Step 22028: {'lr': 0.00047774806711090213, 'samples': 4229376, 'steps': 22027, 'loss/train': 1.41226065158844} 08/30/2021 17:09:36 - INFO - __main__ - Step 22029: {'lr': 0.0004777458784338787, 'samples': 4229568, 'steps': 22028, 'loss/train': 1.7554728984832764} 08/30/2021 17:09:36 - INFO - __main__ - Step 22030: {'lr': 0.00047774368965423653, 'samples': 4229760, 'steps': 22029, 'loss/train': 1.7022331953048706} 08/30/2021 17:09:36 - INFO - __main__ - Step 22031: {'lr': 0.0004777415007719765, 'samples': 4229952, 'steps': 22030, 'loss/train': 1.380596399307251} 08/30/2021 17:09:37 - INFO - __main__ - Step 22032: {'lr': 0.00047773931178709975, 'samples': 4230144, 'steps': 22031, 'loss/train': 1.567521333694458} 08/30/2021 17:09:37 - INFO - __main__ - Step 22033: {'lr': 0.00047773712269960714, 'samples': 4230336, 'steps': 22032, 'loss/train': 1.3691271543502808} 08/30/2021 17:09:39 - INFO - __main__ - Step 22034: {'lr': 0.00047773493350949963, 'samples': 4230528, 'steps': 22033, 'loss/train': 1.634064793586731} 08/30/2021 17:09:39 - INFO - __main__ - Step 22035: {'lr': 0.00047773274421677834, 'samples': 4230720, 'steps': 22034, 'loss/train': 0.20929567515850067} 08/30/2021 17:09:39 - INFO - __main__ - Step 22036: {'lr': 0.0004777305548214442, 'samples': 4230912, 'steps': 22035, 'loss/train': 1.8736116886138916} 08/30/2021 17:09:40 - INFO - __main__ - Step 22037: {'lr': 0.0004777283653234982, 'samples': 4231104, 'steps': 22036, 'loss/train': 1.4712235927581787} 08/30/2021 17:09:40 - INFO - __main__ - Step 22038: {'lr': 0.00047772617572294123, 'samples': 4231296, 'steps': 22037, 'loss/train': 1.524675726890564} 08/30/2021 17:09:41 - INFO - __main__ - Step 22039: {'lr': 0.0004777239860197744, 'samples': 4231488, 'steps': 22038, 'loss/train': 1.3708162307739258} 08/30/2021 17:09:42 - INFO - __main__ - Step 22040: {'lr': 0.0004777217962139987, 'samples': 4231680, 'steps': 22039, 'loss/train': 1.613618016242981} 08/30/2021 17:09:43 - INFO - __main__ - Step 22041: {'lr': 0.000477719606305615, 'samples': 4231872, 'steps': 22040, 'loss/train': 1.3604282140731812} 08/30/2021 17:09:43 - INFO - __main__ - Step 22042: {'lr': 0.0004777174162946244, 'samples': 4232064, 'steps': 22041, 'loss/train': 1.1682003736495972} 08/30/2021 17:09:43 - INFO - __main__ - Step 22043: {'lr': 0.0004777152261810279, 'samples': 4232256, 'steps': 22042, 'loss/train': 1.8293678760528564} 08/30/2021 17:09:44 - INFO - __main__ - Step 22044: {'lr': 0.0004777130359648263, 'samples': 4232448, 'steps': 22043, 'loss/train': 0.9608367681503296} 08/30/2021 17:09:45 - INFO - __main__ - Step 22045: {'lr': 0.0004777108456460208, 'samples': 4232640, 'steps': 22044, 'loss/train': 1.5555115938186646} 08/30/2021 17:09:46 - INFO - __main__ - Step 22046: {'lr': 0.00047770865522461233, 'samples': 4232832, 'steps': 22045, 'loss/train': 1.3933627605438232} 08/30/2021 17:09:46 - INFO - __main__ - Step 22047: {'lr': 0.0004777064647006018, 'samples': 4233024, 'steps': 22046, 'loss/train': 2.507596969604492} 08/30/2021 17:09:46 - INFO - __main__ - Step 22048: {'lr': 0.0004777042740739903, 'samples': 4233216, 'steps': 22047, 'loss/train': 1.6716880798339844} 08/30/2021 17:09:47 - INFO - __main__ - Step 22049: {'lr': 0.0004777020833447787, 'samples': 4233408, 'steps': 22048, 'loss/train': 0.8102055191993713} 08/30/2021 17:09:48 - INFO - __main__ - Step 22050: {'lr': 0.0004776998925129681, 'samples': 4233600, 'steps': 22049, 'loss/train': 1.6614139080047607} 08/30/2021 17:09:49 - INFO - __main__ - Step 22051: {'lr': 0.0004776977015785595, 'samples': 4233792, 'steps': 22050, 'loss/train': 1.5732864141464233} 08/30/2021 17:09:49 - INFO - __main__ - Step 22052: {'lr': 0.0004776955105415537, 'samples': 4233984, 'steps': 22051, 'loss/train': 1.7298601865768433} 08/30/2021 17:09:50 - INFO - __main__ - Step 22053: {'lr': 0.00047769331940195194, 'samples': 4234176, 'steps': 22052, 'loss/train': 1.2789348363876343} 08/30/2021 17:09:50 - INFO - __main__ - Step 22054: {'lr': 0.00047769112815975503, 'samples': 4234368, 'steps': 22053, 'loss/train': 2.008350133895874} 08/30/2021 17:09:50 - INFO - __main__ - Step 22055: {'lr': 0.00047768893681496397, 'samples': 4234560, 'steps': 22054, 'loss/train': 1.403056025505066} 08/30/2021 17:09:52 - INFO - __main__ - Step 22056: {'lr': 0.00047768674536757984, 'samples': 4234752, 'steps': 22055, 'loss/train': 1.2862383127212524} 08/30/2021 17:09:53 - INFO - __main__ - Step 22057: {'lr': 0.00047768455381760357, 'samples': 4234944, 'steps': 22056, 'loss/train': 2.275675058364868} 08/30/2021 17:09:53 - INFO - __main__ - Step 22058: {'lr': 0.00047768236216503613, 'samples': 4235136, 'steps': 22057, 'loss/train': 1.7179292440414429} 08/30/2021 17:09:53 - INFO - __main__ - Step 22059: {'lr': 0.00047768017040987856, 'samples': 4235328, 'steps': 22058, 'loss/train': 3.2524068355560303} 08/30/2021 17:09:54 - INFO - __main__ - Step 22060: {'lr': 0.0004776779785521318, 'samples': 4235520, 'steps': 22059, 'loss/train': 1.4430495500564575} 08/30/2021 17:09:56 - INFO - __main__ - Step 22061: {'lr': 0.0004776757865917969, 'samples': 4235712, 'steps': 22060, 'loss/train': 1.617902159690857} 08/30/2021 17:09:56 - INFO - __main__ - Step 22062: {'lr': 0.0004776735945288747, 'samples': 4235904, 'steps': 22061, 'loss/train': 1.906358242034912} 08/30/2021 17:09:56 - INFO - __main__ - Step 22063: {'lr': 0.00047767140236336635, 'samples': 4236096, 'steps': 22062, 'loss/train': 2.3241195678710938} 08/30/2021 17:09:57 - INFO - __main__ - Step 22064: {'lr': 0.00047766921009527284, 'samples': 4236288, 'steps': 22063, 'loss/train': 1.8307621479034424} 08/30/2021 17:09:57 - INFO - __main__ - Step 22065: {'lr': 0.00047766701772459505, 'samples': 4236480, 'steps': 22064, 'loss/train': 1.2524582147598267} 08/30/2021 17:09:57 - INFO - __main__ - Step 22066: {'lr': 0.00047766482525133405, 'samples': 4236672, 'steps': 22065, 'loss/train': 1.5745614767074585} 08/30/2021 17:09:59 - INFO - __main__ - Step 22067: {'lr': 0.00047766263267549073, 'samples': 4236864, 'steps': 22066, 'loss/train': 1.3962738513946533} 08/30/2021 17:09:59 - INFO - __main__ - Step 22068: {'lr': 0.0004776604399970661, 'samples': 4237056, 'steps': 22067, 'loss/train': 1.452945590019226} 08/30/2021 17:10:00 - INFO - __main__ - Step 22069: {'lr': 0.0004776582472160613, 'samples': 4237248, 'steps': 22068, 'loss/train': 1.9384219646453857} 08/30/2021 17:10:00 - INFO - __main__ - Step 22070: {'lr': 0.0004776560543324772, 'samples': 4237440, 'steps': 22069, 'loss/train': 1.5681068897247314} 08/30/2021 17:10:00 - INFO - __main__ - Step 22071: {'lr': 0.0004776538613463147, 'samples': 4237632, 'steps': 22070, 'loss/train': 2.144890069961548} 08/30/2021 17:10:02 - INFO - __main__ - Step 22072: {'lr': 0.00047765166825757487, 'samples': 4237824, 'steps': 22071, 'loss/train': 1.6291849613189697} 08/30/2021 17:10:03 - INFO - __main__ - Step 22073: {'lr': 0.00047764947506625887, 'samples': 4238016, 'steps': 22072, 'loss/train': 1.8141212463378906} 08/30/2021 17:10:03 - INFO - __main__ - Step 22074: {'lr': 0.00047764728177236736, 'samples': 4238208, 'steps': 22073, 'loss/train': 2.9622011184692383} 08/30/2021 17:10:03 - INFO - __main__ - Step 22075: {'lr': 0.0004776450883759016, 'samples': 4238400, 'steps': 22074, 'loss/train': 1.679767370223999} 08/30/2021 17:10:04 - INFO - __main__ - Step 22076: {'lr': 0.0004776428948768625, 'samples': 4238592, 'steps': 22075, 'loss/train': 0.6758951544761658} 08/30/2021 17:10:06 - INFO - __main__ - Step 22077: {'lr': 0.00047764070127525096, 'samples': 4238784, 'steps': 22076, 'loss/train': 1.738405704498291} 08/30/2021 17:10:07 - INFO - __main__ - Step 22078: {'lr': 0.00047763850757106803, 'samples': 4238976, 'steps': 22077, 'loss/train': 1.8547416925430298} 08/30/2021 17:10:07 - INFO - __main__ - Step 22079: {'lr': 0.0004776363137643147, 'samples': 4239168, 'steps': 22078, 'loss/train': 1.784899115562439} 08/30/2021 17:10:07 - INFO - __main__ - Step 22080: {'lr': 0.000477634119854992, 'samples': 4239360, 'steps': 22079, 'loss/train': 1.3763948678970337} 08/30/2021 17:10:08 - INFO - __main__ - Step 22081: {'lr': 0.00047763192584310087, 'samples': 4239552, 'steps': 22080, 'loss/train': 0.8035991787910461} 08/30/2021 17:10:08 - INFO - __main__ - Step 22082: {'lr': 0.0004776297317286423, 'samples': 4239744, 'steps': 22081, 'loss/train': 0.6462414264678955} 08/30/2021 17:10:09 - INFO - __main__ - Step 22083: {'lr': 0.00047762753751161725, 'samples': 4239936, 'steps': 22082, 'loss/train': 1.702309489250183} 08/30/2021 17:10:10 - INFO - __main__ - Step 22084: {'lr': 0.0004776253431920268, 'samples': 4240128, 'steps': 22083, 'loss/train': 1.4913526773452759} 08/30/2021 17:10:10 - INFO - __main__ - Step 22085: {'lr': 0.00047762314876987185, 'samples': 4240320, 'steps': 22084, 'loss/train': 0.9840775728225708} 08/30/2021 17:10:11 - INFO - __main__ - Step 22086: {'lr': 0.0004776209542451534, 'samples': 4240512, 'steps': 22085, 'loss/train': 1.5377213954925537} 08/30/2021 17:10:11 - INFO - __main__ - Step 22087: {'lr': 0.0004776187596178725, 'samples': 4240704, 'steps': 22086, 'loss/train': 2.0228564739227295} 08/30/2021 17:10:12 - INFO - __main__ - Step 22088: {'lr': 0.00047761656488803006, 'samples': 4240896, 'steps': 22087, 'loss/train': 1.4768586158752441} 08/30/2021 17:10:13 - INFO - __main__ - Step 22089: {'lr': 0.00047761437005562716, 'samples': 4241088, 'steps': 22088, 'loss/train': 1.665913462638855} 08/30/2021 17:10:13 - INFO - __main__ - Step 22090: {'lr': 0.00047761217512066475, 'samples': 4241280, 'steps': 22089, 'loss/train': 2.0579636096954346} 08/30/2021 17:10:14 - INFO - __main__ - Step 22091: {'lr': 0.0004776099800831437, 'samples': 4241472, 'steps': 22090, 'loss/train': 0.23284082114696503} 08/30/2021 17:10:14 - INFO - __main__ - Step 22092: {'lr': 0.0004776077849430652, 'samples': 4241664, 'steps': 22091, 'loss/train': 1.666582465171814} 08/30/2021 17:10:16 - INFO - __main__ - Step 22093: {'lr': 0.0004776055897004301, 'samples': 4241856, 'steps': 22092, 'loss/train': 1.771843433380127} 08/30/2021 17:10:16 - INFO - __main__ - Step 22094: {'lr': 0.0004776033943552395, 'samples': 4242048, 'steps': 22093, 'loss/train': 2.050999402999878} 08/30/2021 17:10:16 - INFO - __main__ - Step 22095: {'lr': 0.0004776011989074943, 'samples': 4242240, 'steps': 22094, 'loss/train': 2.2498724460601807} 08/30/2021 17:10:17 - INFO - __main__ - Step 22096: {'lr': 0.00047759900335719543, 'samples': 4242432, 'steps': 22095, 'loss/train': 1.6556576490402222} 08/30/2021 17:10:17 - INFO - __main__ - Step 22097: {'lr': 0.00047759680770434405, 'samples': 4242624, 'steps': 22096, 'loss/train': 1.60176420211792} 08/30/2021 17:10:18 - INFO - __main__ - Step 22098: {'lr': 0.00047759461194894103, 'samples': 4242816, 'steps': 22097, 'loss/train': 1.6094857454299927} 08/30/2021 17:10:19 - INFO - __main__ - Step 22099: {'lr': 0.00047759241609098734, 'samples': 4243008, 'steps': 22098, 'loss/train': 1.4421844482421875} 08/30/2021 17:10:19 - INFO - __main__ - Step 22100: {'lr': 0.00047759022013048417, 'samples': 4243200, 'steps': 22099, 'loss/train': 1.1010295152664185} 08/30/2021 17:10:20 - INFO - __main__ - Step 22101: {'lr': 0.00047758802406743217, 'samples': 4243392, 'steps': 22100, 'loss/train': 1.3330720663070679} 08/30/2021 17:10:20 - INFO - __main__ - Step 22102: {'lr': 0.0004775858279018326, 'samples': 4243584, 'steps': 22101, 'loss/train': 1.3838764429092407} 08/30/2021 17:10:21 - INFO - __main__ - Step 22103: {'lr': 0.0004775836316336864, 'samples': 4243776, 'steps': 22102, 'loss/train': 1.976652979850769} 08/30/2021 17:10:22 - INFO - __main__ - Step 22104: {'lr': 0.00047758143526299446, 'samples': 4243968, 'steps': 22103, 'loss/train': 1.4156880378723145} 08/30/2021 17:10:22 - INFO - __main__ - Step 22105: {'lr': 0.0004775792387897579, 'samples': 4244160, 'steps': 22104, 'loss/train': 2.0119359493255615} 08/30/2021 17:10:23 - INFO - __main__ - Step 22106: {'lr': 0.0004775770422139776, 'samples': 4244352, 'steps': 22105, 'loss/train': 1.8513189554214478} 08/30/2021 17:10:23 - INFO - __main__ - Step 22107: {'lr': 0.00047757484553565465, 'samples': 4244544, 'steps': 22106, 'loss/train': 1.8542102575302124} 08/30/2021 17:10:23 - INFO - __main__ - Step 22108: {'lr': 0.00047757264875478996, 'samples': 4244736, 'steps': 22107, 'loss/train': 2.1568729877471924} 08/30/2021 17:10:25 - INFO - __main__ - Step 22109: {'lr': 0.0004775704518713845, 'samples': 4244928, 'steps': 22108, 'loss/train': 1.6737103462219238} 08/30/2021 17:10:25 - INFO - __main__ - Step 22110: {'lr': 0.0004775682548854394, 'samples': 4245120, 'steps': 22109, 'loss/train': 2.2088537216186523} 08/30/2021 17:10:25 - INFO - __main__ - Step 22111: {'lr': 0.0004775660577969555, 'samples': 4245312, 'steps': 22110, 'loss/train': 1.5327880382537842} 08/30/2021 17:10:26 - INFO - __main__ - Step 22112: {'lr': 0.0004775638606059338, 'samples': 4245504, 'steps': 22111, 'loss/train': 3.1570706367492676} 08/30/2021 17:10:26 - INFO - __main__ - Step 22113: {'lr': 0.00047756166331237545, 'samples': 4245696, 'steps': 22112, 'loss/train': 1.7394119501113892} 08/30/2021 17:10:28 - INFO - __main__ - Step 22114: {'lr': 0.00047755946591628126, 'samples': 4245888, 'steps': 22113, 'loss/train': 1.5016783475875854} 08/30/2021 17:10:28 - INFO - __main__ - Step 22115: {'lr': 0.00047755726841765224, 'samples': 4246080, 'steps': 22114, 'loss/train': 1.730542540550232} 08/30/2021 17:10:28 - INFO - __main__ - Step 22116: {'lr': 0.0004775550708164895, 'samples': 4246272, 'steps': 22115, 'loss/train': 1.4529187679290771} 08/30/2021 17:10:29 - INFO - __main__ - Step 22117: {'lr': 0.00047755287311279394, 'samples': 4246464, 'steps': 22116, 'loss/train': 1.6635645627975464} 08/30/2021 17:10:29 - INFO - __main__ - Step 22118: {'lr': 0.00047755067530656656, 'samples': 4246656, 'steps': 22117, 'loss/train': 1.3346130847930908} 08/30/2021 17:10:31 - INFO - __main__ - Step 22119: {'lr': 0.00047754847739780835, 'samples': 4246848, 'steps': 22118, 'loss/train': 1.9994735717773438} 08/30/2021 17:10:32 - INFO - __main__ - Step 22120: {'lr': 0.0004775462793865203, 'samples': 4247040, 'steps': 22119, 'loss/train': 1.7999855279922485} 08/30/2021 17:10:32 - INFO - __main__ - Step 22121: {'lr': 0.00047754408127270346, 'samples': 4247232, 'steps': 22120, 'loss/train': 0.8281984925270081} 08/30/2021 17:10:32 - INFO - __main__ - Step 22122: {'lr': 0.0004775418830563587, 'samples': 4247424, 'steps': 22121, 'loss/train': 1.6985368728637695} 08/30/2021 17:10:33 - INFO - __main__ - Step 22123: {'lr': 0.0004775396847374871, 'samples': 4247616, 'steps': 22122, 'loss/train': 1.672114610671997} 08/30/2021 17:10:34 - INFO - __main__ - Step 22124: {'lr': 0.0004775374863160896, 'samples': 4247808, 'steps': 22123, 'loss/train': 1.8892408609390259} 08/30/2021 17:10:35 - INFO - __main__ - Step 22125: {'lr': 0.0004775352877921673, 'samples': 4248000, 'steps': 22124, 'loss/train': 1.277587652206421} 08/30/2021 17:10:35 - INFO - __main__ - Step 22126: {'lr': 0.000477533089165721, 'samples': 4248192, 'steps': 22125, 'loss/train': 1.4643505811691284} 08/30/2021 17:10:35 - INFO - __main__ - Step 22127: {'lr': 0.0004775308904367519, 'samples': 4248384, 'steps': 22126, 'loss/train': 4.364542007446289} 08/30/2021 17:10:36 - INFO - __main__ - Step 22128: {'lr': 0.0004775286916052609, 'samples': 4248576, 'steps': 22127, 'loss/train': 1.5798108577728271} 08/30/2021 17:10:38 - INFO - __main__ - Step 22129: {'lr': 0.00047752649267124894, 'samples': 4248768, 'steps': 22128, 'loss/train': 1.3072041273117065} 08/30/2021 17:10:38 - INFO - __main__ - Step 22130: {'lr': 0.0004775242936347171, 'samples': 4248960, 'steps': 22129, 'loss/train': 1.8408241271972656} 08/30/2021 17:10:39 - INFO - __main__ - Step 22131: {'lr': 0.0004775220944956662, 'samples': 4249152, 'steps': 22130, 'loss/train': 2.2044079303741455} 08/30/2021 17:10:39 - INFO - __main__ - Step 22132: {'lr': 0.00047751989525409745, 'samples': 4249344, 'steps': 22131, 'loss/train': 1.4526580572128296} 08/30/2021 17:10:39 - INFO - __main__ - Step 22133: {'lr': 0.0004775176959100117, 'samples': 4249536, 'steps': 22132, 'loss/train': 1.7001789808273315} 08/30/2021 17:10:41 - INFO - __main__ - Step 22134: {'lr': 0.00047751549646341007, 'samples': 4249728, 'steps': 22133, 'loss/train': 1.269938588142395} 08/30/2021 17:10:41 - INFO - __main__ - Step 22135: {'lr': 0.0004775132969142934, 'samples': 4249920, 'steps': 22134, 'loss/train': 1.303545355796814} 08/30/2021 17:10:42 - INFO - __main__ - Step 22136: {'lr': 0.00047751109726266273, 'samples': 4250112, 'steps': 22135, 'loss/train': 0.9846208095550537} 08/30/2021 17:10:42 - INFO - __main__ - Step 22137: {'lr': 0.00047750889750851913, 'samples': 4250304, 'steps': 22136, 'loss/train': 1.691420555114746} 08/30/2021 17:10:42 - INFO - __main__ - Step 22138: {'lr': 0.0004775066976518635, 'samples': 4250496, 'steps': 22137, 'loss/train': 1.7628076076507568} 08/30/2021 17:10:43 - INFO - __main__ - Step 22139: {'lr': 0.00047750449769269686, 'samples': 4250688, 'steps': 22138, 'loss/train': 1.920169711112976} 08/30/2021 17:10:44 - INFO - __main__ - Step 22140: {'lr': 0.0004775022976310203, 'samples': 4250880, 'steps': 22139, 'loss/train': 1.5844125747680664} 08/30/2021 17:10:45 - INFO - __main__ - Step 22141: {'lr': 0.0004775000974668345, 'samples': 4251072, 'steps': 22140, 'loss/train': 1.3784774541854858} 08/30/2021 17:10:45 - INFO - __main__ - Step 22142: {'lr': 0.00047749789720014085, 'samples': 4251264, 'steps': 22141, 'loss/train': 2.164243698120117} 08/30/2021 17:10:46 - INFO - __main__ - Step 22143: {'lr': 0.00047749569683094015, 'samples': 4251456, 'steps': 22142, 'loss/train': 1.156712293624878} 08/30/2021 17:10:46 - INFO - __main__ - Step 22144: {'lr': 0.00047749349635923334, 'samples': 4251648, 'steps': 22143, 'loss/train': 2.125542640686035} 08/30/2021 17:10:46 - INFO - __main__ - Step 22145: {'lr': 0.0004774912957850215, 'samples': 4251840, 'steps': 22144, 'loss/train': 0.0950431227684021} 08/30/2021 17:10:49 - INFO - __main__ - Step 22146: {'lr': 0.0004774890951083055, 'samples': 4252032, 'steps': 22145, 'loss/train': 1.0042872428894043} 08/30/2021 17:10:49 - INFO - __main__ - Step 22147: {'lr': 0.00047748689432908654, 'samples': 4252224, 'steps': 22146, 'loss/train': 1.9640812873840332} 08/30/2021 17:10:49 - INFO - __main__ - Step 22148: {'lr': 0.00047748469344736547, 'samples': 4252416, 'steps': 22147, 'loss/train': 1.8786741495132446} 08/30/2021 17:10:50 - INFO - __main__ - Step 22149: {'lr': 0.00047748249246314323, 'samples': 4252608, 'steps': 22148, 'loss/train': 1.8291820287704468} 08/30/2021 17:10:50 - INFO - __main__ - Step 22150: {'lr': 0.000477480291376421, 'samples': 4252800, 'steps': 22149, 'loss/train': 1.5574336051940918} 08/30/2021 17:10:50 - INFO - __main__ - Step 22151: {'lr': 0.0004774780901871996, 'samples': 4252992, 'steps': 22150, 'loss/train': 2.3067526817321777} 08/30/2021 17:10:52 - INFO - __main__ - Step 22152: {'lr': 0.0004774758888954801, 'samples': 4253184, 'steps': 22151, 'loss/train': 1.6837538480758667} 08/30/2021 17:10:52 - INFO - __main__ - Step 22153: {'lr': 0.00047747368750126345, 'samples': 4253376, 'steps': 22152, 'loss/train': 1.6451901197433472} 08/30/2021 17:10:53 - INFO - __main__ - Step 22154: {'lr': 0.0004774714860045507, 'samples': 4253568, 'steps': 22153, 'loss/train': 0.507257342338562} 08/30/2021 17:10:53 - INFO - __main__ - Step 22155: {'lr': 0.0004774692844053428, 'samples': 4253760, 'steps': 22154, 'loss/train': 1.1535602807998657} 08/30/2021 17:10:53 - INFO - __main__ - Step 22156: {'lr': 0.00047746708270364073, 'samples': 4253952, 'steps': 22155, 'loss/train': 1.8781384229660034} 08/30/2021 17:10:55 - INFO - __main__ - Step 22157: {'lr': 0.0004774648808994455, 'samples': 4254144, 'steps': 22156, 'loss/train': 1.3260270357131958} 08/30/2021 17:10:56 - INFO - __main__ - Step 22158: {'lr': 0.0004774626789927582, 'samples': 4254336, 'steps': 22157, 'loss/train': 1.7989898920059204} 08/30/2021 17:10:56 - INFO - __main__ - Step 22159: {'lr': 0.0004774604769835796, 'samples': 4254528, 'steps': 22158, 'loss/train': 0.3206104338169098} 08/30/2021 17:10:56 - INFO - __main__ - Step 22160: {'lr': 0.00047745827487191087, 'samples': 4254720, 'steps': 22159, 'loss/train': 1.4987117052078247} 08/30/2021 17:10:57 - INFO - __main__ - Step 22161: {'lr': 0.00047745607265775293, 'samples': 4254912, 'steps': 22160, 'loss/train': 2.027649164199829} 08/30/2021 17:10:57 - INFO - __main__ - Step 22162: {'lr': 0.0004774538703411069, 'samples': 4255104, 'steps': 22161, 'loss/train': 0.652060329914093} 08/30/2021 17:10:59 - INFO - __main__ - Step 22163: {'lr': 0.00047745166792197353, 'samples': 4255296, 'steps': 22162, 'loss/train': 1.7201666831970215} 08/30/2021 17:10:59 - INFO - __main__ - Step 22164: {'lr': 0.000477449465400354, 'samples': 4255488, 'steps': 22163, 'loss/train': 0.7782296538352966} 08/30/2021 17:10:59 - INFO - __main__ - Step 22165: {'lr': 0.00047744726277624926, 'samples': 4255680, 'steps': 22164, 'loss/train': 1.7708029747009277} 08/30/2021 17:11:00 - INFO - __main__ - Step 22166: {'lr': 0.00047744506004966024, 'samples': 4255872, 'steps': 22165, 'loss/train': 2.124933958053589} 08/30/2021 17:11:00 - INFO - __main__ - Step 22167: {'lr': 0.00047744285722058804, 'samples': 4256064, 'steps': 22166, 'loss/train': 1.7922090291976929} 08/30/2021 17:11:02 - INFO - __main__ - Step 22168: {'lr': 0.0004774406542890336, 'samples': 4256256, 'steps': 22167, 'loss/train': 1.4843497276306152} 08/30/2021 17:11:02 - INFO - __main__ - Step 22169: {'lr': 0.0004774384512549979, 'samples': 4256448, 'steps': 22168, 'loss/train': 1.8620972633361816} 08/30/2021 17:11:03 - INFO - __main__ - Step 22170: {'lr': 0.00047743624811848195, 'samples': 4256640, 'steps': 22169, 'loss/train': 1.7882907390594482} 08/30/2021 17:11:03 - INFO - __main__ - Step 22171: {'lr': 0.00047743404487948673, 'samples': 4256832, 'steps': 22170, 'loss/train': 1.7539762258529663} 08/30/2021 17:11:03 - INFO - __main__ - Step 22172: {'lr': 0.0004774318415380132, 'samples': 4257024, 'steps': 22171, 'loss/train': 1.9795050621032715} 08/30/2021 17:11:04 - INFO - __main__ - Step 22173: {'lr': 0.0004774296380940625, 'samples': 4257216, 'steps': 22172, 'loss/train': 1.0491347312927246} 08/30/2021 17:11:05 - INFO - __main__ - Step 22174: {'lr': 0.0004774274345476354, 'samples': 4257408, 'steps': 22173, 'loss/train': 2.025768280029297} 08/30/2021 17:11:06 - INFO - __main__ - Step 22175: {'lr': 0.00047742523089873304, 'samples': 4257600, 'steps': 22174, 'loss/train': 1.32821786403656} 08/30/2021 17:11:06 - INFO - __main__ - Step 22176: {'lr': 0.0004774230271473564, 'samples': 4257792, 'steps': 22175, 'loss/train': 1.7467927932739258} 08/30/2021 17:11:07 - INFO - __main__ - Step 22177: {'lr': 0.00047742082329350644, 'samples': 4257984, 'steps': 22176, 'loss/train': 1.1691381931304932} 08/30/2021 17:11:07 - INFO - __main__ - Step 22178: {'lr': 0.0004774186193371841, 'samples': 4258176, 'steps': 22177, 'loss/train': 2.0946285724639893} 08/30/2021 17:11:08 - INFO - __main__ - Step 22179: {'lr': 0.00047741641527839054, 'samples': 4258368, 'steps': 22178, 'loss/train': 1.907494306564331} 08/30/2021 17:11:09 - INFO - __main__ - Step 22180: {'lr': 0.00047741421111712666, 'samples': 4258560, 'steps': 22179, 'loss/train': 2.1550490856170654} 08/30/2021 17:11:09 - INFO - __main__ - Step 22181: {'lr': 0.00047741200685339337, 'samples': 4258752, 'steps': 22180, 'loss/train': 0.9798780679702759} 08/30/2021 17:11:10 - INFO - __main__ - Step 22182: {'lr': 0.0004774098024871918, 'samples': 4258944, 'steps': 22181, 'loss/train': 1.8367745876312256} 08/30/2021 17:11:10 - INFO - __main__ - Step 22183: {'lr': 0.00047740759801852284, 'samples': 4259136, 'steps': 22182, 'loss/train': 2.275071382522583} 08/30/2021 17:11:10 - INFO - __main__ - Step 22184: {'lr': 0.00047740539344738754, 'samples': 4259328, 'steps': 22183, 'loss/train': 1.5963722467422485} 08/30/2021 17:11:12 - INFO - __main__ - Step 22185: {'lr': 0.00047740318877378685, 'samples': 4259520, 'steps': 22184, 'loss/train': 5.944394111633301} 08/30/2021 17:11:13 - INFO - __main__ - Step 22186: {'lr': 0.00047740098399772185, 'samples': 4259712, 'steps': 22185, 'loss/train': 1.6890538930892944} 08/30/2021 17:11:13 - INFO - __main__ - Step 22187: {'lr': 0.0004773987791191935, 'samples': 4259904, 'steps': 22186, 'loss/train': 1.661117434501648} 08/30/2021 17:11:14 - INFO - __main__ - Step 22188: {'lr': 0.0004773965741382027, 'samples': 4260096, 'steps': 22187, 'loss/train': 1.3339636325836182} 08/30/2021 17:11:14 - INFO - __main__ - Step 22189: {'lr': 0.00047739436905475054, 'samples': 4260288, 'steps': 22188, 'loss/train': 1.8554155826568604} 08/30/2021 17:11:15 - INFO - __main__ - Step 22190: {'lr': 0.00047739216386883797, 'samples': 4260480, 'steps': 22189, 'loss/train': 2.088022470474243} 08/30/2021 17:11:16 - INFO - __main__ - Step 22191: {'lr': 0.000477389958580466, 'samples': 4260672, 'steps': 22190, 'loss/train': 1.8659831285476685} 08/30/2021 17:11:16 - INFO - __main__ - Step 22192: {'lr': 0.0004773877531896356, 'samples': 4260864, 'steps': 22191, 'loss/train': 1.602364182472229} 08/30/2021 17:11:16 - INFO - __main__ - Step 22193: {'lr': 0.00047738554769634784, 'samples': 4261056, 'steps': 22192, 'loss/train': 1.59539794921875} 08/30/2021 17:11:17 - INFO - __main__ - Step 22194: {'lr': 0.00047738334210060366, 'samples': 4261248, 'steps': 22193, 'loss/train': 2.3934431076049805} 08/30/2021 17:11:19 - INFO - __main__ - Step 22195: {'lr': 0.000477381136402404, 'samples': 4261440, 'steps': 22194, 'loss/train': 1.918354868888855} 08/30/2021 17:11:19 - INFO - __main__ - Step 22196: {'lr': 0.00047737893060175, 'samples': 4261632, 'steps': 22195, 'loss/train': 1.7233904600143433} 08/30/2021 17:11:19 - INFO - __main__ - Step 22197: {'lr': 0.00047737672469864246, 'samples': 4261824, 'steps': 22196, 'loss/train': 1.3757588863372803} 08/30/2021 17:11:20 - INFO - __main__ - Step 22198: {'lr': 0.0004773745186930825, 'samples': 4262016, 'steps': 22197, 'loss/train': 1.9363975524902344} 08/30/2021 17:11:20 - INFO - __main__ - Step 22199: {'lr': 0.00047737231258507116, 'samples': 4262208, 'steps': 22198, 'loss/train': 1.716389536857605} 08/30/2021 17:11:21 - INFO - __main__ - Step 22200: {'lr': 0.00047737010637460934, 'samples': 4262400, 'steps': 22199, 'loss/train': 1.666672706604004} 08/30/2021 17:11:21 - INFO - __main__ - Step 22201: {'lr': 0.00047736790006169794, 'samples': 4262592, 'steps': 22200, 'loss/train': 1.411740779876709} 08/30/2021 17:11:22 - INFO - __main__ - Step 22202: {'lr': 0.00047736569364633817, 'samples': 4262784, 'steps': 22201, 'loss/train': 1.2216259241104126} 08/30/2021 17:11:23 - INFO - __main__ - Step 22203: {'lr': 0.00047736348712853094, 'samples': 4262976, 'steps': 22202, 'loss/train': 2.133310556411743} 08/30/2021 17:11:23 - INFO - __main__ - Step 22204: {'lr': 0.0004773612805082772, 'samples': 4263168, 'steps': 22203, 'loss/train': 2.077293634414673} 08/30/2021 17:11:24 - INFO - __main__ - Step 22205: {'lr': 0.000477359073785578, 'samples': 4263360, 'steps': 22204, 'loss/train': 2.1532883644104004} 08/30/2021 17:11:24 - INFO - __main__ - Step 22206: {'lr': 0.00047735686696043434, 'samples': 4263552, 'steps': 22205, 'loss/train': 2.1496901512145996} 08/30/2021 17:11:25 - INFO - __main__ - Step 22207: {'lr': 0.0004773546600328471, 'samples': 4263744, 'steps': 22206, 'loss/train': 2.316821575164795} 08/30/2021 17:11:26 - INFO - __main__ - Step 22208: {'lr': 0.00047735245300281745, 'samples': 4263936, 'steps': 22207, 'loss/train': 1.21135413646698} 08/30/2021 17:11:26 - INFO - __main__ - Step 22209: {'lr': 0.00047735024587034625, 'samples': 4264128, 'steps': 22208, 'loss/train': 1.9529237747192383} 08/30/2021 17:11:27 - INFO - __main__ - Step 22210: {'lr': 0.00047734803863543453, 'samples': 4264320, 'steps': 22209, 'loss/train': 1.8628636598587036} 08/30/2021 17:11:27 - INFO - __main__ - Step 22211: {'lr': 0.00047734583129808327, 'samples': 4264512, 'steps': 22210, 'loss/train': 1.4725264310836792} 08/30/2021 17:11:27 - INFO - __main__ - Step 22212: {'lr': 0.00047734362385829356, 'samples': 4264704, 'steps': 22211, 'loss/train': 2.220416784286499} 08/30/2021 17:11:29 - INFO - __main__ - Step 22213: {'lr': 0.0004773414163160662, 'samples': 4264896, 'steps': 22212, 'loss/train': 1.9183039665222168} 08/30/2021 17:11:29 - INFO - __main__ - Step 22214: {'lr': 0.00047733920867140244, 'samples': 4265088, 'steps': 22213, 'loss/train': 1.4160573482513428} 08/30/2021 17:11:30 - INFO - __main__ - Step 22215: {'lr': 0.00047733700092430305, 'samples': 4265280, 'steps': 22214, 'loss/train': 1.6211538314819336} 08/30/2021 17:11:30 - INFO - __main__ - Step 22216: {'lr': 0.0004773347930747691, 'samples': 4265472, 'steps': 22215, 'loss/train': 3.273075819015503} 08/30/2021 17:11:30 - INFO - __main__ - Step 22217: {'lr': 0.0004773325851228017, 'samples': 4265664, 'steps': 22216, 'loss/train': 1.7557157278060913} 08/30/2021 17:11:32 - INFO - __main__ - Step 22218: {'lr': 0.00047733037706840166, 'samples': 4265856, 'steps': 22217, 'loss/train': 1.849313735961914} 08/30/2021 17:11:32 - INFO - __main__ - Step 22219: {'lr': 0.0004773281689115701, 'samples': 4266048, 'steps': 22218, 'loss/train': 2.089118480682373} 08/30/2021 17:11:32 - INFO - __main__ - Step 22220: {'lr': 0.000477325960652308, 'samples': 4266240, 'steps': 22219, 'loss/train': 1.6515716314315796} 08/30/2021 17:11:33 - INFO - __main__ - Step 22221: {'lr': 0.0004773237522906163, 'samples': 4266432, 'steps': 22220, 'loss/train': 2.2680416107177734} 08/30/2021 17:11:33 - INFO - __main__ - Step 22222: {'lr': 0.000477321543826496, 'samples': 4266624, 'steps': 22221, 'loss/train': 1.7360239028930664} 08/30/2021 17:11:35 - INFO - __main__ - Step 22223: {'lr': 0.00047731933525994814, 'samples': 4266816, 'steps': 22222, 'loss/train': 1.806036353111267} 08/30/2021 17:11:35 - INFO - __main__ - Step 22224: {'lr': 0.0004773171265909737, 'samples': 4267008, 'steps': 22223, 'loss/train': 1.579102873802185} 08/30/2021 17:11:36 - INFO - __main__ - Step 22225: {'lr': 0.00047731491781957366, 'samples': 4267200, 'steps': 22224, 'loss/train': 2.0978195667266846} 08/30/2021 17:11:36 - INFO - __main__ - Step 22226: {'lr': 0.0004773127089457491, 'samples': 4267392, 'steps': 22225, 'loss/train': 0.35885512828826904} 08/30/2021 17:11:36 - INFO - __main__ - Step 22227: {'lr': 0.0004773104999695008, 'samples': 4267584, 'steps': 22226, 'loss/train': 1.8843597173690796} 08/30/2021 17:11:38 - INFO - __main__ - Step 22228: {'lr': 0.00047730829089082994, 'samples': 4267776, 'steps': 22227, 'loss/train': 1.9311151504516602} 08/30/2021 17:11:39 - INFO - __main__ - Step 22229: {'lr': 0.00047730608170973754, 'samples': 4267968, 'steps': 22228, 'loss/train': 1.5460875034332275} 08/30/2021 17:11:39 - INFO - __main__ - Step 22230: {'lr': 0.00047730387242622446, 'samples': 4268160, 'steps': 22229, 'loss/train': 1.5039581060409546} 08/30/2021 17:11:39 - INFO - __main__ - Step 22231: {'lr': 0.00047730166304029185, 'samples': 4268352, 'steps': 22230, 'loss/train': 2.5621299743652344} 08/30/2021 17:11:40 - INFO - __main__ - Step 22232: {'lr': 0.0004772994535519405, 'samples': 4268544, 'steps': 22231, 'loss/train': 0.2551862299442291} 08/30/2021 17:11:41 - INFO - __main__ - Step 22233: {'lr': 0.0004772972439611716, 'samples': 4268736, 'steps': 22232, 'loss/train': 2.1080820560455322} 08/30/2021 17:11:41 - INFO - __main__ - Step 22234: {'lr': 0.00047729503426798605, 'samples': 4268928, 'steps': 22233, 'loss/train': 1.5359896421432495} 08/30/2021 17:11:42 - INFO - __main__ - Step 22235: {'lr': 0.0004772928244723849, 'samples': 4269120, 'steps': 22234, 'loss/train': 2.113858938217163} 08/30/2021 17:11:42 - INFO - __main__ - Step 22236: {'lr': 0.00047729061457436905, 'samples': 4269312, 'steps': 22235, 'loss/train': 1.3084994554519653} 08/30/2021 17:11:43 - INFO - __main__ - Step 22237: {'lr': 0.0004772884045739396, 'samples': 4269504, 'steps': 22236, 'loss/train': 1.6442188024520874} 08/30/2021 17:11:45 - INFO - __main__ - Step 22238: {'lr': 0.0004772861944710974, 'samples': 4269696, 'steps': 22237, 'loss/train': 1.5789165496826172} 08/30/2021 17:11:45 - INFO - __main__ - Step 22239: {'lr': 0.00047728398426584375, 'samples': 4269888, 'steps': 22238, 'loss/train': 1.1186904907226562} 08/30/2021 17:11:46 - INFO - __main__ - Step 22240: {'lr': 0.0004772817739581793, 'samples': 4270080, 'steps': 22239, 'loss/train': 1.960464358329773} 08/30/2021 17:11:46 - INFO - __main__ - Step 22241: {'lr': 0.0004772795635481052, 'samples': 4270272, 'steps': 22240, 'loss/train': 2.104534864425659} 08/30/2021 17:11:46 - INFO - __main__ - Step 22242: {'lr': 0.00047727735303562246, 'samples': 4270464, 'steps': 22241, 'loss/train': 1.1994812488555908} 08/30/2021 17:11:48 - INFO - __main__ - Step 22243: {'lr': 0.000477275142420732, 'samples': 4270656, 'steps': 22242, 'loss/train': 1.981293797492981} 08/30/2021 17:11:48 - INFO - __main__ - Step 22244: {'lr': 0.000477272931703435, 'samples': 4270848, 'steps': 22243, 'loss/train': 1.873092532157898} 08/30/2021 17:11:49 - INFO - __main__ - Step 22245: {'lr': 0.0004772707208837322, 'samples': 4271040, 'steps': 22244, 'loss/train': 2.0743179321289062} 08/30/2021 17:11:49 - INFO - __main__ - Step 22246: {'lr': 0.0004772685099616247, 'samples': 4271232, 'steps': 22245, 'loss/train': 1.9581387042999268} 08/30/2021 17:11:49 - INFO - __main__ - Step 22247: {'lr': 0.0004772662989371136, 'samples': 4271424, 'steps': 22246, 'loss/train': 1.8399993181228638} 08/30/2021 17:11:51 - INFO - __main__ - Step 22248: {'lr': 0.0004772640878101998, 'samples': 4271616, 'steps': 22247, 'loss/train': 0.4765205681324005} 08/30/2021 17:11:51 - INFO - __main__ - Step 22249: {'lr': 0.00047726187658088425, 'samples': 4271808, 'steps': 22248, 'loss/train': 0.857501208782196} 08/30/2021 17:11:52 - INFO - __main__ - Step 22250: {'lr': 0.0004772596652491681, 'samples': 4272000, 'steps': 22249, 'loss/train': 1.1813633441925049} 08/30/2021 17:11:52 - INFO - __main__ - Step 22251: {'lr': 0.0004772574538150522, 'samples': 4272192, 'steps': 22250, 'loss/train': 1.92146897315979} 08/30/2021 17:11:52 - INFO - __main__ - Step 22252: {'lr': 0.0004772552422785376, 'samples': 4272384, 'steps': 22251, 'loss/train': 1.3620665073394775} 08/30/2021 17:11:54 - INFO - __main__ - Step 22253: {'lr': 0.00047725303063962535, 'samples': 4272576, 'steps': 22252, 'loss/train': 1.442641019821167} 08/30/2021 17:11:54 - INFO - __main__ - Step 22254: {'lr': 0.00047725081889831626, 'samples': 4272768, 'steps': 22253, 'loss/train': 1.8525470495224} 08/30/2021 17:11:55 - INFO - __main__ - Step 22255: {'lr': 0.0004772486070546116, 'samples': 4272960, 'steps': 22254, 'loss/train': 1.4444137811660767} 08/30/2021 17:11:55 - INFO - __main__ - Step 22256: {'lr': 0.0004772463951085121, 'samples': 4273152, 'steps': 22255, 'loss/train': 1.7241592407226562} 08/30/2021 17:11:55 - INFO - __main__ - Step 22257: {'lr': 0.00047724418306001895, 'samples': 4273344, 'steps': 22256, 'loss/train': 1.6980116367340088} 08/30/2021 17:11:57 - INFO - __main__ - Step 22258: {'lr': 0.0004772419709091331, 'samples': 4273536, 'steps': 22257, 'loss/train': 1.1155540943145752} 08/30/2021 17:11:57 - INFO - __main__ - Step 22259: {'lr': 0.00047723975865585544, 'samples': 4273728, 'steps': 22258, 'loss/train': 0.32903313636779785} 08/30/2021 17:11:58 - INFO - __main__ - Step 22260: {'lr': 0.00047723754630018715, 'samples': 4273920, 'steps': 22259, 'loss/train': 2.0642480850219727} 08/30/2021 17:11:58 - INFO - __main__ - Step 22261: {'lr': 0.000477235333842129, 'samples': 4274112, 'steps': 22260, 'loss/train': 1.3852115869522095} 08/30/2021 17:11:58 - INFO - __main__ - Step 22262: {'lr': 0.00047723312128168226, 'samples': 4274304, 'steps': 22261, 'loss/train': 1.337482213973999} 08/30/2021 17:11:59 - INFO - __main__ - Step 22263: {'lr': 0.00047723090861884773, 'samples': 4274496, 'steps': 22262, 'loss/train': 2.026703357696533} 08/30/2021 17:12:00 - INFO - __main__ - Step 22264: {'lr': 0.00047722869585362646, 'samples': 4274688, 'steps': 22263, 'loss/train': 2.6244313716888428} 08/30/2021 17:12:01 - INFO - __main__ - Step 22265: {'lr': 0.0004772264829860194, 'samples': 4274880, 'steps': 22264, 'loss/train': 1.8513308763504028} 08/30/2021 17:12:01 - INFO - __main__ - Step 22266: {'lr': 0.00047722427001602765, 'samples': 4275072, 'steps': 22265, 'loss/train': 5.899032115936279} 08/30/2021 17:12:02 - INFO - __main__ - Step 22267: {'lr': 0.0004772220569436521, 'samples': 4275264, 'steps': 22266, 'loss/train': 1.5059112310409546} 08/30/2021 17:12:02 - INFO - __main__ - Step 22268: {'lr': 0.0004772198437688938, 'samples': 4275456, 'steps': 22267, 'loss/train': 1.5607255697250366} 08/30/2021 17:12:04 - INFO - __main__ - Step 22269: {'lr': 0.0004772176304917538, 'samples': 4275648, 'steps': 22268, 'loss/train': 1.8144924640655518} 08/30/2021 17:12:04 - INFO - __main__ - Step 22270: {'lr': 0.00047721541711223306, 'samples': 4275840, 'steps': 22269, 'loss/train': 1.739651083946228} 08/30/2021 17:12:04 - INFO - __main__ - Step 22271: {'lr': 0.00047721320363033247, 'samples': 4276032, 'steps': 22270, 'loss/train': 2.207659959793091} 08/30/2021 17:12:05 - INFO - __main__ - Step 22272: {'lr': 0.00047721099004605316, 'samples': 4276224, 'steps': 22271, 'loss/train': 1.5110259056091309} 08/30/2021 17:12:05 - INFO - __main__ - Step 22273: {'lr': 0.00047720877635939606, 'samples': 4276416, 'steps': 22272, 'loss/train': 1.3257867097854614} 08/30/2021 17:12:05 - INFO - __main__ - Step 22274: {'lr': 0.0004772065625703622, 'samples': 4276608, 'steps': 22273, 'loss/train': 1.6748912334442139} 08/30/2021 17:12:07 - INFO - __main__ - Step 22275: {'lr': 0.0004772043486789526, 'samples': 4276800, 'steps': 22274, 'loss/train': 1.8296105861663818} 08/30/2021 17:12:07 - INFO - __main__ - Step 22276: {'lr': 0.0004772021346851682, 'samples': 4276992, 'steps': 22275, 'loss/train': 1.589489221572876} 08/30/2021 17:12:08 - INFO - __main__ - Step 22277: {'lr': 0.00047719992058901006, 'samples': 4277184, 'steps': 22276, 'loss/train': 2.3670313358306885} 08/30/2021 17:12:08 - INFO - __main__ - Step 22278: {'lr': 0.0004771977063904791, 'samples': 4277376, 'steps': 22277, 'loss/train': 1.057492971420288} 08/30/2021 17:12:08 - INFO - __main__ - Step 22279: {'lr': 0.00047719549208957636, 'samples': 4277568, 'steps': 22278, 'loss/train': 1.414607048034668} 08/30/2021 17:12:10 - INFO - __main__ - Step 22280: {'lr': 0.0004771932776863028, 'samples': 4277760, 'steps': 22279, 'loss/train': 1.5459754467010498} 08/30/2021 17:12:10 - INFO - __main__ - Step 22281: {'lr': 0.0004771910631806595, 'samples': 4277952, 'steps': 22280, 'loss/train': 1.5766849517822266} 08/30/2021 17:12:11 - INFO - __main__ - Step 22282: {'lr': 0.00047718884857264745, 'samples': 4278144, 'steps': 22281, 'loss/train': 2.308119535446167} 08/30/2021 17:12:11 - INFO - __main__ - Step 22283: {'lr': 0.0004771866338622676, 'samples': 4278336, 'steps': 22282, 'loss/train': 1.3916943073272705} 08/30/2021 17:12:11 - INFO - __main__ - Step 22284: {'lr': 0.0004771844190495209, 'samples': 4278528, 'steps': 22283, 'loss/train': 1.7475589513778687} 08/30/2021 17:12:13 - INFO - __main__ - Step 22285: {'lr': 0.0004771822041344085, 'samples': 4278720, 'steps': 22284, 'loss/train': 1.9920268058776855} 08/30/2021 17:12:13 - INFO - __main__ - Step 22286: {'lr': 0.0004771799891169312, 'samples': 4278912, 'steps': 22285, 'loss/train': 1.6034091711044312} 08/30/2021 17:12:14 - INFO - __main__ - Step 22287: {'lr': 0.0004771777739970902, 'samples': 4279104, 'steps': 22286, 'loss/train': 1.5661957263946533} 08/30/2021 17:12:14 - INFO - __main__ - Step 22288: {'lr': 0.0004771755587748863, 'samples': 4279296, 'steps': 22287, 'loss/train': 1.2716710567474365} 08/30/2021 17:12:14 - INFO - __main__ - Step 22289: {'lr': 0.00047717334345032065, 'samples': 4279488, 'steps': 22288, 'loss/train': 1.3670454025268555} 08/30/2021 17:12:16 - INFO - __main__ - Step 22290: {'lr': 0.0004771711280233942, 'samples': 4279680, 'steps': 22289, 'loss/train': 2.0890448093414307} 08/30/2021 17:12:17 - INFO - __main__ - Step 22291: {'lr': 0.000477168912494108, 'samples': 4279872, 'steps': 22290, 'loss/train': 1.223692536354065} 08/30/2021 17:12:17 - INFO - __main__ - Step 22292: {'lr': 0.00047716669686246287, 'samples': 4280064, 'steps': 22291, 'loss/train': 2.1673696041107178} 08/30/2021 17:12:17 - INFO - __main__ - Step 22293: {'lr': 0.00047716448112846, 'samples': 4280256, 'steps': 22292, 'loss/train': 1.7638188600540161} 08/30/2021 17:12:18 - INFO - __main__ - Step 22294: {'lr': 0.00047716226529210035, 'samples': 4280448, 'steps': 22293, 'loss/train': 1.263674020767212} 08/30/2021 17:12:18 - INFO - __main__ - Step 22295: {'lr': 0.00047716004935338484, 'samples': 4280640, 'steps': 22294, 'loss/train': 2.0301637649536133} 08/30/2021 17:12:20 - INFO - __main__ - Step 22296: {'lr': 0.0004771578333123145, 'samples': 4280832, 'steps': 22295, 'loss/train': 0.1532074362039566} 08/30/2021 17:12:21 - INFO - __main__ - Step 22297: {'lr': 0.00047715561716889037, 'samples': 4281024, 'steps': 22296, 'loss/train': 1.6346476078033447} 08/30/2021 17:12:21 - INFO - __main__ - Step 22298: {'lr': 0.0004771534009231134, 'samples': 4281216, 'steps': 22297, 'loss/train': 1.932807445526123} 08/30/2021 17:12:22 - INFO - __main__ - Step 22299: {'lr': 0.00047715118457498473, 'samples': 4281408, 'steps': 22298, 'loss/train': 1.622165322303772} 08/30/2021 17:12:22 - INFO - __main__ - Step 22300: {'lr': 0.00047714896812450514, 'samples': 4281600, 'steps': 22299, 'loss/train': 1.7235090732574463} 08/30/2021 17:12:22 - INFO - __main__ - Step 22301: {'lr': 0.00047714675157167573, 'samples': 4281792, 'steps': 22300, 'loss/train': 1.7315394878387451} 08/30/2021 17:12:24 - INFO - __main__ - Step 22302: {'lr': 0.00047714453491649753, 'samples': 4281984, 'steps': 22301, 'loss/train': 1.458749532699585} 08/30/2021 17:12:24 - INFO - __main__ - Step 22303: {'lr': 0.00047714231815897145, 'samples': 4282176, 'steps': 22302, 'loss/train': 1.760093092918396} 08/30/2021 17:12:25 - INFO - __main__ - Step 22304: {'lr': 0.0004771401012990986, 'samples': 4282368, 'steps': 22303, 'loss/train': 1.0102078914642334} 08/30/2021 17:12:25 - INFO - __main__ - Step 22305: {'lr': 0.0004771378843368799, 'samples': 4282560, 'steps': 22304, 'loss/train': 0.8581253290176392} 08/30/2021 17:12:25 - INFO - __main__ - Step 22306: {'lr': 0.0004771356672723164, 'samples': 4282752, 'steps': 22305, 'loss/train': 1.1559330224990845} 08/30/2021 17:12:27 - INFO - __main__ - Step 22307: {'lr': 0.0004771334501054091, 'samples': 4282944, 'steps': 22306, 'loss/train': 1.6413648128509521} 08/30/2021 17:12:27 - INFO - __main__ - Step 22308: {'lr': 0.0004771312328361589, 'samples': 4283136, 'steps': 22307, 'loss/train': 1.3504822254180908} 08/30/2021 17:12:28 - INFO - __main__ - Step 22309: {'lr': 0.0004771290154645669, 'samples': 4283328, 'steps': 22308, 'loss/train': 1.6743515729904175} 08/30/2021 17:12:28 - INFO - __main__ - Step 22310: {'lr': 0.0004771267979906341, 'samples': 4283520, 'steps': 22309, 'loss/train': 1.1398613452911377} 08/30/2021 17:12:28 - INFO - __main__ - Step 22311: {'lr': 0.0004771245804143615, 'samples': 4283712, 'steps': 22310, 'loss/train': 1.9536066055297852} 08/30/2021 17:12:30 - INFO - __main__ - Step 22312: {'lr': 0.00047712236273574993, 'samples': 4283904, 'steps': 22311, 'loss/train': 1.4108941555023193} 08/30/2021 17:12:30 - INFO - __main__ - Step 22313: {'lr': 0.0004771201449548006, 'samples': 4284096, 'steps': 22312, 'loss/train': 2.030109167098999} 08/30/2021 17:12:31 - INFO - __main__ - Step 22314: {'lr': 0.0004771179270715145, 'samples': 4284288, 'steps': 22313, 'loss/train': 1.5843579769134521} 08/30/2021 17:12:31 - INFO - __main__ - Step 22315: {'lr': 0.0004771157090858925, 'samples': 4284480, 'steps': 22314, 'loss/train': 1.4762053489685059} 08/30/2021 17:12:31 - INFO - __main__ - Step 22316: {'lr': 0.00047711349099793565, 'samples': 4284672, 'steps': 22315, 'loss/train': 1.261612892150879} 08/30/2021 17:12:33 - INFO - __main__ - Step 22317: {'lr': 0.00047711127280764497, 'samples': 4284864, 'steps': 22316, 'loss/train': 1.734206199645996} 08/30/2021 17:12:34 - INFO - __main__ - Step 22318: {'lr': 0.0004771090545150215, 'samples': 4285056, 'steps': 22317, 'loss/train': 2.0448877811431885} 08/30/2021 17:12:34 - INFO - __main__ - Step 22319: {'lr': 0.00047710683612006623, 'samples': 4285248, 'steps': 22318, 'loss/train': 1.1970142126083374} 08/30/2021 17:12:34 - INFO - __main__ - Step 22320: {'lr': 0.00047710461762278, 'samples': 4285440, 'steps': 22319, 'loss/train': 1.1002840995788574} 08/30/2021 17:12:35 - INFO - __main__ - Step 22321: {'lr': 0.00047710239902316404, 'samples': 4285632, 'steps': 22320, 'loss/train': 1.3517085313796997} 08/30/2021 17:12:35 - INFO - __main__ - Step 22322: {'lr': 0.0004771001803212192, 'samples': 4285824, 'steps': 22321, 'loss/train': 0.12081053853034973} 08/30/2021 17:12:36 - INFO - __main__ - Step 22323: {'lr': 0.0004770979615169466, 'samples': 4286016, 'steps': 22322, 'loss/train': 1.2311862707138062} 08/30/2021 17:12:37 - INFO - __main__ - Step 22324: {'lr': 0.00047709574261034705, 'samples': 4286208, 'steps': 22323, 'loss/train': 1.5089372396469116} 08/30/2021 17:12:37 - INFO - __main__ - Step 22325: {'lr': 0.0004770935236014217, 'samples': 4286400, 'steps': 22324, 'loss/train': 1.385047435760498} 08/30/2021 17:12:38 - INFO - __main__ - Step 22326: {'lr': 0.00047709130449017154, 'samples': 4286592, 'steps': 22325, 'loss/train': 1.8321505784988403} 08/30/2021 17:12:38 - INFO - __main__ - Step 22327: {'lr': 0.0004770890852765975, 'samples': 4286784, 'steps': 22326, 'loss/train': 1.692516565322876} 08/30/2021 17:12:39 - INFO - __main__ - Step 22328: {'lr': 0.00047708686596070065, 'samples': 4286976, 'steps': 22327, 'loss/train': 1.6043461561203003} 08/30/2021 17:12:40 - INFO - __main__ - Step 22329: {'lr': 0.00047708464654248195, 'samples': 4287168, 'steps': 22328, 'loss/train': 3.0700507164001465} 08/30/2021 17:12:40 - INFO - __main__ - Step 22330: {'lr': 0.0004770824270219424, 'samples': 4287360, 'steps': 22329, 'loss/train': 1.9059228897094727} 08/30/2021 17:12:41 - INFO - __main__ - Step 22331: {'lr': 0.0004770802073990831, 'samples': 4287552, 'steps': 22330, 'loss/train': 1.1868107318878174} 08/30/2021 17:12:41 - INFO - __main__ - Step 22332: {'lr': 0.00047707798767390486, 'samples': 4287744, 'steps': 22331, 'loss/train': 1.798985481262207} 08/30/2021 17:12:41 - INFO - __main__ - Step 22333: {'lr': 0.00047707576784640883, 'samples': 4287936, 'steps': 22332, 'loss/train': 1.9564640522003174} 08/30/2021 17:12:43 - INFO - __main__ - Step 22334: {'lr': 0.00047707354791659594, 'samples': 4288128, 'steps': 22333, 'loss/train': 1.6558359861373901} 08/30/2021 17:12:44 - INFO - __main__ - Step 22335: {'lr': 0.0004770713278844672, 'samples': 4288320, 'steps': 22334, 'loss/train': 1.7436270713806152} 08/30/2021 17:12:44 - INFO - __main__ - Step 22336: {'lr': 0.00047706910775002363, 'samples': 4288512, 'steps': 22335, 'loss/train': 1.8189456462860107} 08/30/2021 17:12:44 - INFO - __main__ - Step 22337: {'lr': 0.0004770668875132663, 'samples': 4288704, 'steps': 22336, 'loss/train': 0.8251792192459106} 08/30/2021 17:12:45 - INFO - __main__ - Step 22338: {'lr': 0.00047706466717419607, 'samples': 4288896, 'steps': 22337, 'loss/train': 1.2290778160095215} 08/30/2021 17:12:46 - INFO - __main__ - Step 22339: {'lr': 0.000477062446732814, 'samples': 4289088, 'steps': 22338, 'loss/train': 1.2256410121917725} 08/30/2021 17:12:47 - INFO - __main__ - Step 22340: {'lr': 0.0004770602261891211, 'samples': 4289280, 'steps': 22339, 'loss/train': 1.7080248594284058} 08/30/2021 17:12:47 - INFO - __main__ - Step 22341: {'lr': 0.00047705800554311836, 'samples': 4289472, 'steps': 22340, 'loss/train': 2.1394202709198} 08/30/2021 17:12:47 - INFO - __main__ - Step 22342: {'lr': 0.0004770557847948068, 'samples': 4289664, 'steps': 22341, 'loss/train': 0.19599613547325134} 08/30/2021 17:12:48 - INFO - __main__ - Step 22343: {'lr': 0.0004770535639441874, 'samples': 4289856, 'steps': 22342, 'loss/train': 1.7449849843978882} 08/30/2021 17:12:50 - INFO - __main__ - Step 22344: {'lr': 0.0004770513429912612, 'samples': 4290048, 'steps': 22343, 'loss/train': 1.2627513408660889} 08/30/2021 17:12:50 - INFO - __main__ - Step 22345: {'lr': 0.0004770491219360291, 'samples': 4290240, 'steps': 22344, 'loss/train': 1.4885687828063965} 08/30/2021 17:12:50 - INFO - __main__ - Step 22346: {'lr': 0.00047704690077849223, 'samples': 4290432, 'steps': 22345, 'loss/train': 1.65871000289917} 08/30/2021 17:12:51 - INFO - __main__ - Step 22347: {'lr': 0.0004770446795186515, 'samples': 4290624, 'steps': 22346, 'loss/train': 1.5663443803787231} 08/30/2021 17:12:51 - INFO - __main__ - Step 22348: {'lr': 0.0004770424581565079, 'samples': 4290816, 'steps': 22347, 'loss/train': 1.3566665649414062} 08/30/2021 17:12:54 - INFO - __main__ - Step 22349: {'lr': 0.0004770402366920625, 'samples': 4291008, 'steps': 22348, 'loss/train': 0.32403233647346497} 08/30/2021 17:12:54 - INFO - __main__ - Step 22350: {'lr': 0.00047703801512531636, 'samples': 4291200, 'steps': 22349, 'loss/train': 1.629690170288086} 08/30/2021 17:12:55 - INFO - __main__ - Step 22351: {'lr': 0.00047703579345627036, 'samples': 4291392, 'steps': 22350, 'loss/train': 1.9505356550216675} 08/30/2021 17:12:55 - INFO - __main__ - Step 22352: {'lr': 0.00047703357168492544, 'samples': 4291584, 'steps': 22351, 'loss/train': 1.5575278997421265} 08/30/2021 17:12:55 - INFO - __main__ - Step 22353: {'lr': 0.0004770313498112828, 'samples': 4291776, 'steps': 22352, 'loss/train': 1.1776572465896606} 08/30/2021 17:12:56 - INFO - __main__ - Step 22354: {'lr': 0.0004770291278353433, 'samples': 4291968, 'steps': 22353, 'loss/train': 1.4709523916244507} 08/30/2021 17:12:56 - INFO - __main__ - Step 22355: {'lr': 0.00047702690575710796, 'samples': 4292160, 'steps': 22354, 'loss/train': 2.1087942123413086} 08/30/2021 17:12:58 - INFO - __main__ - Step 22356: {'lr': 0.0004770246835765778, 'samples': 4292352, 'steps': 22355, 'loss/train': 1.793090581893921} 08/30/2021 17:12:58 - INFO - __main__ - Step 22357: {'lr': 0.0004770224612937538, 'samples': 4292544, 'steps': 22356, 'loss/train': 1.7314915657043457} 08/30/2021 17:12:58 - INFO - __main__ - Step 22358: {'lr': 0.0004770202389086371, 'samples': 4292736, 'steps': 22357, 'loss/train': 1.6197714805603027} 08/30/2021 17:12:59 - INFO - __main__ - Step 22359: {'lr': 0.0004770180164212284, 'samples': 4292928, 'steps': 22358, 'loss/train': 2.251490831375122} 08/30/2021 17:12:59 - INFO - __main__ - Step 22360: {'lr': 0.00047701579383152906, 'samples': 4293120, 'steps': 22359, 'loss/train': 1.3303654193878174} 08/30/2021 17:13:01 - INFO - __main__ - Step 22361: {'lr': 0.0004770135711395398, 'samples': 4293312, 'steps': 22360, 'loss/train': 1.2282088994979858} 08/30/2021 17:13:01 - INFO - __main__ - Step 22362: {'lr': 0.0004770113483452618, 'samples': 4293504, 'steps': 22361, 'loss/train': 2.1275947093963623} 08/30/2021 17:13:02 - INFO - __main__ - Step 22363: {'lr': 0.00047700912544869595, 'samples': 4293696, 'steps': 22362, 'loss/train': 2.052558183670044} 08/30/2021 17:13:02 - INFO - __main__ - Step 22364: {'lr': 0.0004770069024498433, 'samples': 4293888, 'steps': 22363, 'loss/train': 1.709843635559082} 08/30/2021 17:13:02 - INFO - __main__ - Step 22365: {'lr': 0.00047700467934870484, 'samples': 4294080, 'steps': 22364, 'loss/train': 0.11012905836105347} 08/30/2021 17:13:05 - INFO - __main__ - Step 22366: {'lr': 0.0004770024561452816, 'samples': 4294272, 'steps': 22365, 'loss/train': 1.4906331300735474} 08/30/2021 17:13:05 - INFO - __main__ - Step 22367: {'lr': 0.0004770002328395745, 'samples': 4294464, 'steps': 22366, 'loss/train': 1.7107250690460205} 08/30/2021 17:13:05 - INFO - __main__ - Step 22368: {'lr': 0.00047699800943158454, 'samples': 4294656, 'steps': 22367, 'loss/train': 0.14216406643390656} 08/30/2021 17:13:06 - INFO - __main__ - Step 22369: {'lr': 0.0004769957859213129, 'samples': 4294848, 'steps': 22368, 'loss/train': 1.6559343338012695} 08/30/2021 17:13:06 - INFO - __main__ - Step 22370: {'lr': 0.00047699356230876047, 'samples': 4295040, 'steps': 22369, 'loss/train': 1.896594762802124} 08/30/2021 17:13:07 - INFO - __main__ - Step 22371: {'lr': 0.0004769913385939282, 'samples': 4295232, 'steps': 22370, 'loss/train': 1.1542118787765503} 08/30/2021 17:13:07 - INFO - __main__ - Step 22372: {'lr': 0.0004769891147768171, 'samples': 4295424, 'steps': 22371, 'loss/train': 2.6675169467926025} 08/30/2021 17:13:07 - INFO - __main__ - Step 22373: {'lr': 0.00047698689085742823, 'samples': 4295616, 'steps': 22372, 'loss/train': 1.9953951835632324} 08/30/2021 17:13:09 - INFO - __main__ - Step 22374: {'lr': 0.00047698466683576256, 'samples': 4295808, 'steps': 22373, 'loss/train': 1.745845913887024} 08/30/2021 17:13:09 - INFO - __main__ - Step 22375: {'lr': 0.0004769824427118211, 'samples': 4296000, 'steps': 22374, 'loss/train': 1.9689626693725586} 08/30/2021 17:13:09 - INFO - __main__ - Step 22376: {'lr': 0.00047698021848560494, 'samples': 4296192, 'steps': 22375, 'loss/train': 2.4756383895874023} 08/30/2021 17:13:10 - INFO - __main__ - Step 22377: {'lr': 0.0004769779941571149, 'samples': 4296384, 'steps': 22376, 'loss/train': 1.3743934631347656} 08/30/2021 17:13:10 - INFO - __main__ - Step 22378: {'lr': 0.00047697576972635213, 'samples': 4296576, 'steps': 22377, 'loss/train': 1.7336702346801758} 08/30/2021 17:13:12 - INFO - __main__ - Step 22379: {'lr': 0.0004769735451933176, 'samples': 4296768, 'steps': 22378, 'loss/train': 1.7430158853530884} 08/30/2021 17:13:12 - INFO - __main__ - Step 22380: {'lr': 0.0004769713205580122, 'samples': 4296960, 'steps': 22379, 'loss/train': 1.7553653717041016} 08/30/2021 17:13:12 - INFO - __main__ - Step 22381: {'lr': 0.0004769690958204371, 'samples': 4297152, 'steps': 22380, 'loss/train': 1.4760040044784546} 08/30/2021 17:13:13 - INFO - __main__ - Step 22382: {'lr': 0.0004769668709805932, 'samples': 4297344, 'steps': 22381, 'loss/train': 2.4359185695648193} 08/30/2021 17:13:13 - INFO - __main__ - Step 22383: {'lr': 0.0004769646460384816, 'samples': 4297536, 'steps': 22382, 'loss/train': 2.0891146659851074} 08/30/2021 17:13:15 - INFO - __main__ - Step 22384: {'lr': 0.00047696242099410307, 'samples': 4297728, 'steps': 22383, 'loss/train': 1.869328498840332} 08/30/2021 17:13:15 - INFO - __main__ - Step 22385: {'lr': 0.00047696019584745887, 'samples': 4297920, 'steps': 22384, 'loss/train': 1.9483591318130493} 08/30/2021 17:13:15 - INFO - __main__ - Step 22386: {'lr': 0.00047695797059854996, 'samples': 4298112, 'steps': 22385, 'loss/train': 1.746274471282959} 08/30/2021 17:13:16 - INFO - __main__ - Step 22387: {'lr': 0.0004769557452473772, 'samples': 4298304, 'steps': 22386, 'loss/train': 2.275529384613037} 08/30/2021 17:13:16 - INFO - __main__ - Step 22388: {'lr': 0.00047695351979394173, 'samples': 4298496, 'steps': 22387, 'loss/train': 1.8169291019439697} 08/30/2021 17:13:18 - INFO - __main__ - Step 22389: {'lr': 0.00047695129423824454, 'samples': 4298688, 'steps': 22388, 'loss/train': 2.1064412593841553} 08/30/2021 17:13:18 - INFO - __main__ - Step 22390: {'lr': 0.0004769490685802865, 'samples': 4298880, 'steps': 22389, 'loss/train': 1.5430718660354614} 08/30/2021 17:13:18 - INFO - __main__ - Step 22391: {'lr': 0.00047694684282006885, 'samples': 4299072, 'steps': 22390, 'loss/train': 1.8566498756408691} 08/30/2021 17:13:19 - INFO - __main__ - Step 22392: {'lr': 0.00047694461695759236, 'samples': 4299264, 'steps': 22391, 'loss/train': 1.4858124256134033} 08/30/2021 17:13:19 - INFO - __main__ - Step 22393: {'lr': 0.00047694239099285815, 'samples': 4299456, 'steps': 22392, 'loss/train': 1.1314911842346191} 08/30/2021 17:13:21 - INFO - __main__ - Step 22394: {'lr': 0.00047694016492586715, 'samples': 4299648, 'steps': 22393, 'loss/train': 1.2198786735534668} 08/30/2021 17:13:21 - INFO - __main__ - Step 22395: {'lr': 0.0004769379387566205, 'samples': 4299840, 'steps': 22394, 'loss/train': 2.0493226051330566} 08/30/2021 17:13:21 - INFO - __main__ - Step 22396: {'lr': 0.000476935712485119, 'samples': 4300032, 'steps': 22395, 'loss/train': 1.9728707075119019} 08/30/2021 17:13:22 - INFO - __main__ - Step 22397: {'lr': 0.0004769334861113639, 'samples': 4300224, 'steps': 22396, 'loss/train': 1.7758984565734863} 08/30/2021 17:13:22 - INFO - __main__ - Step 22398: {'lr': 0.000476931259635356, 'samples': 4300416, 'steps': 22397, 'loss/train': 1.9279731512069702} 08/30/2021 17:13:24 - INFO - __main__ - Step 22399: {'lr': 0.00047692903305709646, 'samples': 4300608, 'steps': 22398, 'loss/train': 1.7467641830444336} 08/30/2021 17:13:25 - INFO - __main__ - Step 22400: {'lr': 0.0004769268063765861, 'samples': 4300800, 'steps': 22399, 'loss/train': 1.9367769956588745} 08/30/2021 17:13:25 - INFO - __main__ - Step 22401: {'lr': 0.00047692457959382605, 'samples': 4300992, 'steps': 22400, 'loss/train': 2.1889874935150146} 08/30/2021 17:13:25 - INFO - __main__ - Step 22402: {'lr': 0.0004769223527088173, 'samples': 4301184, 'steps': 22401, 'loss/train': 3.266441583633423} 08/30/2021 17:13:26 - INFO - __main__ - Step 22403: {'lr': 0.00047692012572156086, 'samples': 4301376, 'steps': 22402, 'loss/train': 2.4790022373199463} 08/30/2021 17:13:26 - INFO - __main__ - Step 22404: {'lr': 0.00047691789863205764, 'samples': 4301568, 'steps': 22403, 'loss/train': 1.6065174341201782} 08/30/2021 17:13:26 - INFO - __main__ - Step 22405: {'lr': 0.0004769156714403088, 'samples': 4301760, 'steps': 22404, 'loss/train': 0.8410873413085938} 08/30/2021 17:13:28 - INFO - __main__ - Step 22406: {'lr': 0.0004769134441463152, 'samples': 4301952, 'steps': 22405, 'loss/train': 1.2901523113250732} 08/30/2021 17:13:29 - INFO - __main__ - Step 22407: {'lr': 0.0004769112167500779, 'samples': 4302144, 'steps': 22406, 'loss/train': 1.9885972738265991} 08/30/2021 17:13:29 - INFO - __main__ - Step 22408: {'lr': 0.00047690898925159796, 'samples': 4302336, 'steps': 22407, 'loss/train': 2.138716697692871} 08/30/2021 17:13:30 - INFO - __main__ - Step 22409: {'lr': 0.0004769067616508763, 'samples': 4302528, 'steps': 22408, 'loss/train': 1.79085111618042} 08/30/2021 17:13:30 - INFO - __main__ - Step 22410: {'lr': 0.00047690453394791393, 'samples': 4302720, 'steps': 22409, 'loss/train': 2.0332047939300537} 08/30/2021 17:13:30 - INFO - __main__ - Step 22411: {'lr': 0.0004769023061427119, 'samples': 4302912, 'steps': 22410, 'loss/train': 1.719641923904419} 08/30/2021 17:13:32 - INFO - __main__ - Step 22412: {'lr': 0.0004769000782352713, 'samples': 4303104, 'steps': 22411, 'loss/train': 2.0749473571777344} 08/30/2021 17:13:33 - INFO - __main__ - Step 22413: {'lr': 0.00047689785022559284, 'samples': 4303296, 'steps': 22412, 'loss/train': 2.0759830474853516} 08/30/2021 17:13:33 - INFO - __main__ - Step 22414: {'lr': 0.0004768956221136778, 'samples': 4303488, 'steps': 22413, 'loss/train': 1.7461432218551636} 08/30/2021 17:13:33 - INFO - __main__ - Step 22415: {'lr': 0.00047689339389952713, 'samples': 4303680, 'steps': 22414, 'loss/train': 1.7579646110534668} 08/30/2021 17:13:34 - INFO - __main__ - Step 22416: {'lr': 0.0004768911655831417, 'samples': 4303872, 'steps': 22415, 'loss/train': 2.2065553665161133} 08/30/2021 17:13:35 - INFO - __main__ - Step 22417: {'lr': 0.0004768889371645227, 'samples': 4304064, 'steps': 22416, 'loss/train': 1.7390761375427246} 08/30/2021 17:13:36 - INFO - __main__ - Step 22418: {'lr': 0.000476886708643671, 'samples': 4304256, 'steps': 22417, 'loss/train': 1.4862357378005981} 08/30/2021 17:13:36 - INFO - __main__ - Step 22419: {'lr': 0.0004768844800205877, 'samples': 4304448, 'steps': 22418, 'loss/train': 1.667893648147583} 08/30/2021 17:13:37 - INFO - __main__ - Step 22420: {'lr': 0.0004768822512952737, 'samples': 4304640, 'steps': 22419, 'loss/train': 1.1174753904342651} 08/30/2021 17:13:37 - INFO - __main__ - Step 22421: {'lr': 0.0004768800224677301, 'samples': 4304832, 'steps': 22420, 'loss/train': 1.2558841705322266} 08/30/2021 17:13:39 - INFO - __main__ - Step 22422: {'lr': 0.0004768777935379578, 'samples': 4305024, 'steps': 22421, 'loss/train': 1.9752498865127563} 08/30/2021 17:13:39 - INFO - __main__ - Step 22423: {'lr': 0.0004768755645059579, 'samples': 4305216, 'steps': 22422, 'loss/train': 1.7126777172088623} 08/30/2021 17:13:39 - INFO - __main__ - Step 22424: {'lr': 0.00047687333537173136, 'samples': 4305408, 'steps': 22423, 'loss/train': 1.5196870565414429} 08/30/2021 17:13:40 - INFO - __main__ - Step 22425: {'lr': 0.00047687110613527924, 'samples': 4305600, 'steps': 22424, 'loss/train': 2.162867307662964} 08/30/2021 17:13:40 - INFO - __main__ - Step 22426: {'lr': 0.00047686887679660253, 'samples': 4305792, 'steps': 22425, 'loss/train': 1.4038060903549194} 08/30/2021 17:13:42 - INFO - __main__ - Step 22427: {'lr': 0.0004768666473557021, 'samples': 4305984, 'steps': 22426, 'loss/train': 0.17870919406414032} 08/30/2021 17:13:42 - INFO - __main__ - Step 22428: {'lr': 0.0004768644178125791, 'samples': 4306176, 'steps': 22427, 'loss/train': 1.2794487476348877} 08/30/2021 17:13:43 - INFO - __main__ - Step 22429: {'lr': 0.0004768621881672345, 'samples': 4306368, 'steps': 22428, 'loss/train': 1.6502145528793335} 08/30/2021 17:13:43 - INFO - __main__ - Step 22430: {'lr': 0.00047685995841966936, 'samples': 4306560, 'steps': 22429, 'loss/train': 1.9061843156814575} 08/30/2021 17:13:43 - INFO - __main__ - Step 22431: {'lr': 0.0004768577285698845, 'samples': 4306752, 'steps': 22430, 'loss/train': 1.8811677694320679} 08/30/2021 17:13:45 - INFO - __main__ - Step 22432: {'lr': 0.00047685549861788113, 'samples': 4306944, 'steps': 22431, 'loss/train': 1.7884986400604248} 08/30/2021 17:13:45 - INFO - __main__ - Step 22433: {'lr': 0.0004768532685636602, 'samples': 4307136, 'steps': 22432, 'loss/train': 1.5401004552841187} 08/30/2021 17:13:46 - INFO - __main__ - Step 22434: {'lr': 0.0004768510384072226, 'samples': 4307328, 'steps': 22433, 'loss/train': 1.6148316860198975} 08/30/2021 17:13:46 - INFO - __main__ - Step 22435: {'lr': 0.0004768488081485695, 'samples': 4307520, 'steps': 22434, 'loss/train': 1.414378046989441} 08/30/2021 17:13:46 - INFO - __main__ - Step 22436: {'lr': 0.0004768465777877018, 'samples': 4307712, 'steps': 22435, 'loss/train': 1.9817149639129639} 08/30/2021 17:13:47 - INFO - __main__ - Step 22437: {'lr': 0.0004768443473246205, 'samples': 4307904, 'steps': 22436, 'loss/train': 1.8146398067474365} 08/30/2021 17:13:48 - INFO - __main__ - Step 22438: {'lr': 0.00047684211675932665, 'samples': 4308096, 'steps': 22437, 'loss/train': 1.8666608333587646} 08/30/2021 17:13:49 - INFO - __main__ - Step 22439: {'lr': 0.0004768398860918213, 'samples': 4308288, 'steps': 22438, 'loss/train': 2.1716370582580566} 08/30/2021 17:13:49 - INFO - __main__ - Step 22440: {'lr': 0.0004768376553221053, 'samples': 4308480, 'steps': 22439, 'loss/train': 1.9423466920852661} 08/30/2021 17:13:49 - INFO - __main__ - Step 22441: {'lr': 0.0004768354244501798, 'samples': 4308672, 'steps': 22440, 'loss/train': 1.6935824155807495} 08/30/2021 17:13:50 - INFO - __main__ - Step 22442: {'lr': 0.0004768331934760458, 'samples': 4308864, 'steps': 22441, 'loss/train': 1.7347948551177979} 08/30/2021 17:13:51 - INFO - __main__ - Step 22443: {'lr': 0.00047683096239970423, 'samples': 4309056, 'steps': 22442, 'loss/train': 1.7142823934555054} 08/30/2021 17:13:52 - INFO - __main__ - Step 22444: {'lr': 0.0004768287312211561, 'samples': 4309248, 'steps': 22443, 'loss/train': 0.21094796061515808} 08/30/2021 17:13:52 - INFO - __main__ - Step 22445: {'lr': 0.0004768264999404025, 'samples': 4309440, 'steps': 22444, 'loss/train': 1.8671423196792603} 08/30/2021 17:13:52 - INFO - __main__ - Step 22446: {'lr': 0.00047682426855744434, 'samples': 4309632, 'steps': 22445, 'loss/train': 1.7412782907485962} 08/30/2021 17:13:53 - INFO - __main__ - Step 22447: {'lr': 0.00047682203707228264, 'samples': 4309824, 'steps': 22446, 'loss/train': 1.6040568351745605} 08/30/2021 17:13:55 - INFO - __main__ - Step 22448: {'lr': 0.00047681980548491853, 'samples': 4310016, 'steps': 22447, 'loss/train': 1.5771088600158691} 08/30/2021 17:13:55 - INFO - __main__ - Step 22449: {'lr': 0.00047681757379535285, 'samples': 4310208, 'steps': 22448, 'loss/train': 1.3620716333389282} 08/30/2021 17:13:55 - INFO - __main__ - Step 22450: {'lr': 0.00047681534200358665, 'samples': 4310400, 'steps': 22449, 'loss/train': 1.7939502000808716} 08/30/2021 17:13:56 - INFO - __main__ - Step 22451: {'lr': 0.000476813110109621, 'samples': 4310592, 'steps': 22450, 'loss/train': 1.5142356157302856} 08/30/2021 17:13:56 - INFO - __main__ - Step 22452: {'lr': 0.0004768108781134568, 'samples': 4310784, 'steps': 22451, 'loss/train': 3.149855375289917} 08/30/2021 17:13:56 - INFO - __main__ - Step 22453: {'lr': 0.0004768086460150952, 'samples': 4310976, 'steps': 22452, 'loss/train': 1.7269551753997803} 08/30/2021 17:13:58 - INFO - __main__ - Step 22454: {'lr': 0.00047680641381453703, 'samples': 4311168, 'steps': 22453, 'loss/train': 0.6760121583938599} 08/30/2021 17:13:58 - INFO - __main__ - Step 22455: {'lr': 0.0004768041815117835, 'samples': 4311360, 'steps': 22454, 'loss/train': 1.962514042854309} 08/30/2021 17:13:59 - INFO - __main__ - Step 22456: {'lr': 0.00047680194910683545, 'samples': 4311552, 'steps': 22455, 'loss/train': 1.614229679107666} 08/30/2021 17:13:59 - INFO - __main__ - Step 22457: {'lr': 0.0004767997165996939, 'samples': 4311744, 'steps': 22456, 'loss/train': 1.7352981567382812} 08/30/2021 17:13:59 - INFO - __main__ - Step 22458: {'lr': 0.00047679748399035994, 'samples': 4311936, 'steps': 22457, 'loss/train': 1.9201675653457642} 08/30/2021 17:14:01 - INFO - __main__ - Step 22459: {'lr': 0.00047679525127883456, 'samples': 4312128, 'steps': 22458, 'loss/train': 2.225206136703491} 08/30/2021 17:14:01 - INFO - __main__ - Step 22460: {'lr': 0.0004767930184651187, 'samples': 4312320, 'steps': 22459, 'loss/train': 1.8964154720306396} 08/30/2021 17:14:02 - INFO - __main__ - Step 22461: {'lr': 0.0004767907855492134, 'samples': 4312512, 'steps': 22460, 'loss/train': 2.0226051807403564} 08/30/2021 17:14:02 - INFO - __main__ - Step 22462: {'lr': 0.0004767885525311197, 'samples': 4312704, 'steps': 22461, 'loss/train': 1.9483298063278198} 08/30/2021 17:14:02 - INFO - __main__ - Step 22463: {'lr': 0.0004767863194108386, 'samples': 4312896, 'steps': 22462, 'loss/train': 1.5516774654388428} 08/30/2021 17:14:04 - INFO - __main__ - Step 22464: {'lr': 0.000476784086188371, 'samples': 4313088, 'steps': 22463, 'loss/train': 2.108454465866089} 08/30/2021 17:14:05 - INFO - __main__ - Step 22465: {'lr': 0.00047678185286371803, 'samples': 4313280, 'steps': 22464, 'loss/train': 1.8621517419815063} 08/30/2021 17:14:05 - INFO - __main__ - Step 22466: {'lr': 0.0004767796194368807, 'samples': 4313472, 'steps': 22465, 'loss/train': 2.0400550365448} 08/30/2021 17:14:06 - INFO - __main__ - Step 22467: {'lr': 0.00047677738590786, 'samples': 4313664, 'steps': 22466, 'loss/train': 5.935624599456787} 08/30/2021 17:14:06 - INFO - __main__ - Step 22468: {'lr': 0.0004767751522766568, 'samples': 4313856, 'steps': 22467, 'loss/train': 1.3310096263885498} 08/30/2021 17:14:08 - INFO - __main__ - Step 22469: {'lr': 0.00047677291854327224, 'samples': 4314048, 'steps': 22468, 'loss/train': 1.2661097049713135} 08/30/2021 17:14:08 - INFO - __main__ - Step 22470: {'lr': 0.00047677068470770737, 'samples': 4314240, 'steps': 22469, 'loss/train': 1.8714877367019653} 08/30/2021 17:14:08 - INFO - __main__ - Step 22471: {'lr': 0.00047676845076996305, 'samples': 4314432, 'steps': 22470, 'loss/train': 1.7654696702957153} 08/30/2021 17:14:09 - INFO - __main__ - Step 22472: {'lr': 0.0004767662167300404, 'samples': 4314624, 'steps': 22471, 'loss/train': 0.48746439814567566} 08/30/2021 17:14:09 - INFO - __main__ - Step 22473: {'lr': 0.0004767639825879404, 'samples': 4314816, 'steps': 22472, 'loss/train': 1.8187942504882812} 08/30/2021 17:14:09 - INFO - __main__ - Step 22474: {'lr': 0.000476761748343664, 'samples': 4315008, 'steps': 22473, 'loss/train': 0.5924195647239685} 08/30/2021 17:14:11 - INFO - __main__ - Step 22475: {'lr': 0.00047675951399721235, 'samples': 4315200, 'steps': 22474, 'loss/train': 1.7742091417312622} 08/30/2021 17:14:11 - INFO - __main__ - Step 22476: {'lr': 0.0004767572795485863, 'samples': 4315392, 'steps': 22475, 'loss/train': 1.7919718027114868} 08/30/2021 17:14:12 - INFO - __main__ - Step 22477: {'lr': 0.00047675504499778695, 'samples': 4315584, 'steps': 22476, 'loss/train': 2.61266827583313} 08/30/2021 17:14:12 - INFO - __main__ - Step 22478: {'lr': 0.0004767528103448152, 'samples': 4315776, 'steps': 22477, 'loss/train': 1.3702067136764526} 08/30/2021 17:14:12 - INFO - __main__ - Step 22479: {'lr': 0.00047675057558967224, 'samples': 4315968, 'steps': 22478, 'loss/train': 1.984159231185913} 08/30/2021 17:14:14 - INFO - __main__ - Step 22480: {'lr': 0.0004767483407323589, 'samples': 4316160, 'steps': 22479, 'loss/train': 2.2095019817352295} 08/30/2021 17:14:14 - INFO - __main__ - Step 22481: {'lr': 0.00047674610577287625, 'samples': 4316352, 'steps': 22480, 'loss/train': 1.7467973232269287} 08/30/2021 17:14:15 - INFO - __main__ - Step 22482: {'lr': 0.00047674387071122536, 'samples': 4316544, 'steps': 22481, 'loss/train': 1.6091501712799072} 08/30/2021 17:14:15 - INFO - __main__ - Step 22483: {'lr': 0.0004767416355474071, 'samples': 4316736, 'steps': 22482, 'loss/train': 1.6895766258239746} 08/30/2021 17:14:15 - INFO - __main__ - Step 22484: {'lr': 0.00047673940028142265, 'samples': 4316928, 'steps': 22483, 'loss/train': 1.633849024772644} 08/30/2021 17:14:17 - INFO - __main__ - Step 22485: {'lr': 0.0004767371649132729, 'samples': 4317120, 'steps': 22484, 'loss/train': 1.660505771636963} 08/30/2021 17:14:17 - INFO - __main__ - Step 22486: {'lr': 0.00047673492944295883, 'samples': 4317312, 'steps': 22485, 'loss/train': 1.2509496212005615} 08/30/2021 17:14:18 - INFO - __main__ - Step 22487: {'lr': 0.0004767326938704816, 'samples': 4317504, 'steps': 22486, 'loss/train': 1.9188863039016724} 08/30/2021 17:14:18 - INFO - __main__ - Step 22488: {'lr': 0.00047673045819584197, 'samples': 4317696, 'steps': 22487, 'loss/train': 1.0761938095092773} 08/30/2021 17:14:18 - INFO - __main__ - Step 22489: {'lr': 0.0004767282224190412, 'samples': 4317888, 'steps': 22488, 'loss/train': 1.7531883716583252} 08/30/2021 17:14:20 - INFO - __main__ - Step 22490: {'lr': 0.00047672598654008015, 'samples': 4318080, 'steps': 22489, 'loss/train': 1.7927989959716797} 08/30/2021 17:14:20 - INFO - __main__ - Step 22491: {'lr': 0.0004767237505589599, 'samples': 4318272, 'steps': 22490, 'loss/train': 1.0618451833724976} 08/30/2021 17:14:21 - INFO - __main__ - Step 22492: {'lr': 0.0004767215144756814, 'samples': 4318464, 'steps': 22491, 'loss/train': 1.719399094581604} 08/30/2021 17:14:21 - INFO - __main__ - Step 22493: {'lr': 0.0004767192782902457, 'samples': 4318656, 'steps': 22492, 'loss/train': 1.0271601676940918} 08/30/2021 17:14:21 - INFO - __main__ - Step 22494: {'lr': 0.0004767170420026538, 'samples': 4318848, 'steps': 22493, 'loss/train': 0.9355188012123108} 08/30/2021 17:14:23 - INFO - __main__ - Step 22495: {'lr': 0.0004767148056129067, 'samples': 4319040, 'steps': 22494, 'loss/train': 2.2111897468566895} 08/30/2021 17:14:23 - INFO - __main__ - Step 22496: {'lr': 0.0004767125691210054, 'samples': 4319232, 'steps': 22495, 'loss/train': 1.777457356452942} 08/30/2021 17:14:24 - INFO - __main__ - Step 22497: {'lr': 0.00047671033252695083, 'samples': 4319424, 'steps': 22496, 'loss/train': 1.7731730937957764} 08/30/2021 17:14:24 - INFO - __main__ - Step 22498: {'lr': 0.0004767080958307442, 'samples': 4319616, 'steps': 22497, 'loss/train': 1.4276859760284424} 08/30/2021 17:14:24 - INFO - __main__ - Step 22499: {'lr': 0.0004767058590323864, 'samples': 4319808, 'steps': 22498, 'loss/train': 1.6239917278289795} 08/30/2021 17:14:26 - INFO - __main__ - Step 22500: {'lr': 0.00047670362213187833, 'samples': 4320000, 'steps': 22499, 'loss/train': 1.0119229555130005} 08/30/2021 17:14:27 - INFO - __main__ - Step 22501: {'lr': 0.0004767013851292212, 'samples': 4320192, 'steps': 22500, 'loss/train': 1.2648358345031738} 08/30/2021 17:14:27 - INFO - __main__ - Step 22502: {'lr': 0.0004766991480244159, 'samples': 4320384, 'steps': 22501, 'loss/train': 0.3033278286457062} 08/30/2021 17:14:28 - INFO - __main__ - Step 22503: {'lr': 0.0004766969108174635, 'samples': 4320576, 'steps': 22502, 'loss/train': 0.16322974860668182} 08/30/2021 17:14:28 - INFO - __main__ - Step 22504: {'lr': 0.0004766946735083649, 'samples': 4320768, 'steps': 22503, 'loss/train': 1.9770796298980713} 08/30/2021 17:14:30 - INFO - __main__ - Step 22505: {'lr': 0.0004766924360971212, 'samples': 4320960, 'steps': 22504, 'loss/train': 1.3510984182357788} 08/30/2021 17:14:30 - INFO - __main__ - Step 22506: {'lr': 0.00047669019858373343, 'samples': 4321152, 'steps': 22505, 'loss/train': 1.9653582572937012} 08/30/2021 17:14:30 - INFO - __main__ - Step 22507: {'lr': 0.00047668796096820247, 'samples': 4321344, 'steps': 22506, 'loss/train': 0.5082666277885437} 08/30/2021 17:14:31 - INFO - __main__ - Step 22508: {'lr': 0.00047668572325052953, 'samples': 4321536, 'steps': 22507, 'loss/train': 1.9479482173919678} 08/30/2021 17:14:31 - INFO - __main__ - Step 22509: {'lr': 0.00047668348543071536, 'samples': 4321728, 'steps': 22508, 'loss/train': 1.757729172706604} 08/30/2021 17:14:31 - INFO - __main__ - Step 22510: {'lr': 0.00047668124750876117, 'samples': 4321920, 'steps': 22509, 'loss/train': 3.3465144634246826} 08/30/2021 17:14:33 - INFO - __main__ - Step 22511: {'lr': 0.0004766790094846679, 'samples': 4322112, 'steps': 22510, 'loss/train': 2.3180856704711914} 08/30/2021 17:14:34 - INFO - __main__ - Step 22512: {'lr': 0.0004766767713584367, 'samples': 4322304, 'steps': 22511, 'loss/train': 1.4776660203933716} 08/30/2021 17:14:34 - INFO - __main__ - Step 22513: {'lr': 0.00047667453313006826, 'samples': 4322496, 'steps': 22512, 'loss/train': 1.8642196655273438} 08/30/2021 17:14:34 - INFO - __main__ - Step 22514: {'lr': 0.00047667229479956386, 'samples': 4322688, 'steps': 22513, 'loss/train': 1.3936805725097656} 08/30/2021 17:14:35 - INFO - __main__ - Step 22515: {'lr': 0.0004766700563669244, 'samples': 4322880, 'steps': 22514, 'loss/train': 1.9357175827026367} 08/30/2021 17:14:35 - INFO - __main__ - Step 22516: {'lr': 0.0004766678178321509, 'samples': 4323072, 'steps': 22515, 'loss/train': 0.9189608097076416} 08/30/2021 17:14:37 - INFO - __main__ - Step 22517: {'lr': 0.0004766655791952444, 'samples': 4323264, 'steps': 22516, 'loss/train': 1.9477885961532593} 08/30/2021 17:14:38 - INFO - __main__ - Step 22518: {'lr': 0.0004766633404562059, 'samples': 4323456, 'steps': 22517, 'loss/train': 0.5487386584281921} 08/30/2021 17:14:38 - INFO - __main__ - Step 22519: {'lr': 0.0004766611016150364, 'samples': 4323648, 'steps': 22518, 'loss/train': 1.230427861213684} 08/30/2021 17:14:38 - INFO - __main__ - Step 22520: {'lr': 0.00047665886267173686, 'samples': 4323840, 'steps': 22519, 'loss/train': 1.2861769199371338} 08/30/2021 17:14:39 - INFO - __main__ - Step 22521: {'lr': 0.00047665662362630836, 'samples': 4324032, 'steps': 22520, 'loss/train': 1.6450291872024536} 08/30/2021 17:14:40 - INFO - __main__ - Step 22522: {'lr': 0.00047665438447875186, 'samples': 4324224, 'steps': 22521, 'loss/train': 1.6257888078689575} 08/30/2021 17:14:41 - INFO - __main__ - Step 22523: {'lr': 0.0004766521452290684, 'samples': 4324416, 'steps': 22522, 'loss/train': 2.009296417236328} 08/30/2021 17:14:41 - INFO - __main__ - Step 22524: {'lr': 0.00047664990587725905, 'samples': 4324608, 'steps': 22523, 'loss/train': 1.138895034790039} 08/30/2021 17:14:41 - INFO - __main__ - Step 22525: {'lr': 0.0004766476664233247, 'samples': 4324800, 'steps': 22524, 'loss/train': 1.378551959991455} 08/30/2021 17:14:42 - INFO - __main__ - Step 22526: {'lr': 0.0004766454268672664, 'samples': 4324992, 'steps': 22525, 'loss/train': 1.2025744915008545} 08/30/2021 17:14:42 - INFO - __main__ - Step 22527: {'lr': 0.00047664318720908516, 'samples': 4325184, 'steps': 22526, 'loss/train': 2.2128894329071045} 08/30/2021 17:14:44 - INFO - __main__ - Step 22528: {'lr': 0.000476640947448782, 'samples': 4325376, 'steps': 22527, 'loss/train': 2.173571825027466} 08/30/2021 17:14:44 - INFO - __main__ - Step 22529: {'lr': 0.000476638707586358, 'samples': 4325568, 'steps': 22528, 'loss/train': 1.637187123298645} 08/30/2021 17:14:44 - INFO - __main__ - Step 22530: {'lr': 0.000476636467621814, 'samples': 4325760, 'steps': 22529, 'loss/train': 1.5273845195770264} 08/30/2021 17:14:45 - INFO - __main__ - Step 22531: {'lr': 0.00047663422755515113, 'samples': 4325952, 'steps': 22530, 'loss/train': 1.323721170425415} 08/30/2021 17:14:45 - INFO - __main__ - Step 22532: {'lr': 0.00047663198738637035, 'samples': 4326144, 'steps': 22531, 'loss/train': 1.6435048580169678} 08/30/2021 17:14:47 - INFO - __main__ - Step 22533: {'lr': 0.00047662974711547274, 'samples': 4326336, 'steps': 22532, 'loss/train': 1.8532849550247192} 08/30/2021 17:14:47 - INFO - __main__ - Step 22534: {'lr': 0.0004766275067424593, 'samples': 4326528, 'steps': 22533, 'loss/train': 1.458275318145752} 08/30/2021 17:14:47 - INFO - __main__ - Step 22535: {'lr': 0.0004766252662673309, 'samples': 4326720, 'steps': 22534, 'loss/train': 1.8849378824234009} 08/30/2021 17:14:48 - INFO - __main__ - Step 22536: {'lr': 0.0004766230256900887, 'samples': 4326912, 'steps': 22535, 'loss/train': 1.1653574705123901} 08/30/2021 17:14:48 - INFO - __main__ - Step 22537: {'lr': 0.0004766207850107337, 'samples': 4327104, 'steps': 22536, 'loss/train': 1.4604711532592773} 08/30/2021 17:14:50 - INFO - __main__ - Step 22538: {'lr': 0.00047661854422926674, 'samples': 4327296, 'steps': 22537, 'loss/train': 2.063953161239624} 08/30/2021 17:14:50 - INFO - __main__ - Step 22539: {'lr': 0.0004766163033456891, 'samples': 4327488, 'steps': 22538, 'loss/train': 1.9041965007781982} 08/30/2021 17:14:51 - INFO - __main__ - Step 22540: {'lr': 0.0004766140623600016, 'samples': 4327680, 'steps': 22539, 'loss/train': 1.9534395933151245} 08/30/2021 17:14:51 - INFO - __main__ - Step 22541: {'lr': 0.0004766118212722053, 'samples': 4327872, 'steps': 22540, 'loss/train': 0.12554432451725006} 08/30/2021 17:14:51 - INFO - __main__ - Step 22542: {'lr': 0.0004766095800823013, 'samples': 4328064, 'steps': 22541, 'loss/train': 2.0189404487609863} 08/30/2021 17:14:53 - INFO - __main__ - Step 22543: {'lr': 0.0004766073387902904, 'samples': 4328256, 'steps': 22542, 'loss/train': 0.27141886949539185} 08/30/2021 17:14:53 - INFO - __main__ - Step 22544: {'lr': 0.00047660509739617376, 'samples': 4328448, 'steps': 22543, 'loss/train': 1.2854547500610352} 08/30/2021 17:14:54 - INFO - __main__ - Step 22545: {'lr': 0.00047660285589995233, 'samples': 4328640, 'steps': 22544, 'loss/train': 1.238966703414917} 08/30/2021 17:14:54 - INFO - __main__ - Step 22546: {'lr': 0.0004766006143016272, 'samples': 4328832, 'steps': 22545, 'loss/train': 2.324779510498047} 08/30/2021 17:14:54 - INFO - __main__ - Step 22547: {'lr': 0.0004765983726011993, 'samples': 4329024, 'steps': 22546, 'loss/train': 1.4933652877807617} 08/30/2021 17:14:56 - INFO - __main__ - Step 22548: {'lr': 0.0004765961307986697, 'samples': 4329216, 'steps': 22547, 'loss/train': 1.3241190910339355} 08/30/2021 17:14:56 - INFO - __main__ - Step 22549: {'lr': 0.0004765938888940393, 'samples': 4329408, 'steps': 22548, 'loss/train': 1.0358211994171143} 08/30/2021 17:14:57 - INFO - __main__ - Step 22550: {'lr': 0.00047659164688730935, 'samples': 4329600, 'steps': 22549, 'loss/train': 1.617812156677246} 08/30/2021 17:14:57 - INFO - __main__ - Step 22551: {'lr': 0.00047658940477848056, 'samples': 4329792, 'steps': 22550, 'loss/train': 1.7339508533477783} 08/30/2021 17:14:57 - INFO - __main__ - Step 22552: {'lr': 0.00047658716256755414, 'samples': 4329984, 'steps': 22551, 'loss/train': 1.7117106914520264} 08/30/2021 17:14:58 - INFO - __main__ - Step 22553: {'lr': 0.00047658492025453106, 'samples': 4330176, 'steps': 22552, 'loss/train': 1.3234061002731323} 08/30/2021 17:14:59 - INFO - __main__ - Step 22554: {'lr': 0.00047658267783941223, 'samples': 4330368, 'steps': 22553, 'loss/train': 1.2777682542800903} 08/30/2021 17:14:59 - INFO - __main__ - Step 22555: {'lr': 0.0004765804353221988, 'samples': 4330560, 'steps': 22554, 'loss/train': 2.290679693222046} 08/30/2021 17:15:00 - INFO - __main__ - Step 22556: {'lr': 0.0004765781927028917, 'samples': 4330752, 'steps': 22555, 'loss/train': 1.369117259979248} 08/30/2021 17:15:00 - INFO - __main__ - Step 22557: {'lr': 0.000476575949981492, 'samples': 4330944, 'steps': 22556, 'loss/train': 1.2444427013397217} 08/30/2021 17:15:00 - INFO - __main__ - Step 22558: {'lr': 0.00047657370715800066, 'samples': 4331136, 'steps': 22557, 'loss/train': 2.076911687850952} 08/30/2021 17:15:02 - INFO - __main__ - Step 22559: {'lr': 0.0004765714642324187, 'samples': 4331328, 'steps': 22558, 'loss/train': 1.3288944959640503} 08/30/2021 17:15:02 - INFO - __main__ - Step 22560: {'lr': 0.0004765692212047471, 'samples': 4331520, 'steps': 22559, 'loss/train': 1.579010248184204} 08/30/2021 17:15:03 - INFO - __main__ - Step 22561: {'lr': 0.00047656697807498693, 'samples': 4331712, 'steps': 22560, 'loss/train': 1.5661537647247314} 08/30/2021 17:15:03 - INFO - __main__ - Step 22562: {'lr': 0.0004765647348431392, 'samples': 4331904, 'steps': 22561, 'loss/train': 1.6125584840774536} 08/30/2021 17:15:03 - INFO - __main__ - Step 22563: {'lr': 0.00047656249150920485, 'samples': 4332096, 'steps': 22562, 'loss/train': 2.1038525104522705} 08/30/2021 17:15:06 - INFO - __main__ - Step 22564: {'lr': 0.000476560248073185, 'samples': 4332288, 'steps': 22563, 'loss/train': 1.730812430381775} 08/30/2021 17:15:06 - INFO - __main__ - Step 22565: {'lr': 0.0004765580045350805, 'samples': 4332480, 'steps': 22564, 'loss/train': 1.7798317670822144} 08/30/2021 17:15:06 - INFO - __main__ - Step 22566: {'lr': 0.00047655576089489254, 'samples': 4332672, 'steps': 22565, 'loss/train': 1.7542918920516968} 08/30/2021 17:15:07 - INFO - __main__ - Step 22567: {'lr': 0.00047655351715262205, 'samples': 4332864, 'steps': 22566, 'loss/train': 1.4907829761505127} 08/30/2021 17:15:07 - INFO - __main__ - Step 22568: {'lr': 0.00047655127330827, 'samples': 4333056, 'steps': 22567, 'loss/train': 3.5989739894866943} 08/30/2021 17:15:07 - INFO - __main__ - Step 22569: {'lr': 0.00047654902936183745, 'samples': 4333248, 'steps': 22568, 'loss/train': 3.7340481281280518} 08/30/2021 17:15:08 - INFO - __main__ - Step 22570: {'lr': 0.00047654678531332544, 'samples': 4333440, 'steps': 22569, 'loss/train': 4.774858474731445} 08/30/2021 17:15:09 - INFO - __main__ - Step 22571: {'lr': 0.00047654454116273493, 'samples': 4333632, 'steps': 22570, 'loss/train': 1.9201209545135498} 08/30/2021 17:15:10 - INFO - __main__ - Step 22572: {'lr': 0.0004765422969100669, 'samples': 4333824, 'steps': 22571, 'loss/train': 1.6501644849777222} 08/30/2021 17:15:10 - INFO - __main__ - Step 22573: {'lr': 0.00047654005255532247, 'samples': 4334016, 'steps': 22572, 'loss/train': 1.9358325004577637} 08/30/2021 17:15:10 - INFO - __main__ - Step 22574: {'lr': 0.0004765378080985026, 'samples': 4334208, 'steps': 22573, 'loss/train': 1.5381373167037964} 08/30/2021 17:15:11 - INFO - __main__ - Step 22575: {'lr': 0.00047653556353960825, 'samples': 4334400, 'steps': 22574, 'loss/train': 1.7209357023239136} 08/30/2021 17:15:13 - INFO - __main__ - Step 22576: {'lr': 0.0004765333188786404, 'samples': 4334592, 'steps': 22575, 'loss/train': 1.5887960195541382} 08/30/2021 17:15:13 - INFO - __main__ - Step 22577: {'lr': 0.00047653107411560025, 'samples': 4334784, 'steps': 22576, 'loss/train': 2.440398931503296} 08/30/2021 17:15:14 - INFO - __main__ - Step 22578: {'lr': 0.00047652882925048863, 'samples': 4334976, 'steps': 22577, 'loss/train': 1.467909336090088} 08/30/2021 17:15:14 - INFO - __main__ - Step 22579: {'lr': 0.00047652658428330664, 'samples': 4335168, 'steps': 22578, 'loss/train': 1.7069509029388428} 08/30/2021 17:15:14 - INFO - __main__ - Step 22580: {'lr': 0.00047652433921405526, 'samples': 4335360, 'steps': 22579, 'loss/train': 1.4549226760864258} 08/30/2021 17:15:16 - INFO - __main__ - Step 22581: {'lr': 0.0004765220940427355, 'samples': 4335552, 'steps': 22580, 'loss/train': 1.1382648944854736} 08/30/2021 17:15:16 - INFO - __main__ - Step 22582: {'lr': 0.0004765198487693484, 'samples': 4335744, 'steps': 22581, 'loss/train': 1.7741187810897827} 08/30/2021 17:15:17 - INFO - __main__ - Step 22583: {'lr': 0.00047651760339389494, 'samples': 4335936, 'steps': 22582, 'loss/train': 3.3371052742004395} 08/30/2021 17:15:17 - INFO - __main__ - Step 22584: {'lr': 0.0004765153579163761, 'samples': 4336128, 'steps': 22583, 'loss/train': 0.11780780553817749} 08/30/2021 17:15:17 - INFO - __main__ - Step 22585: {'lr': 0.000476513112336793, 'samples': 4336320, 'steps': 22584, 'loss/train': 1.8284790515899658} 08/30/2021 17:15:18 - INFO - __main__ - Step 22586: {'lr': 0.00047651086665514655, 'samples': 4336512, 'steps': 22585, 'loss/train': 1.7586549520492554} 08/30/2021 17:15:19 - INFO - __main__ - Step 22587: {'lr': 0.00047650862087143787, 'samples': 4336704, 'steps': 22586, 'loss/train': 1.6524969339370728} 08/30/2021 17:15:20 - INFO - __main__ - Step 22588: {'lr': 0.0004765063749856678, 'samples': 4336896, 'steps': 22587, 'loss/train': 1.9591922760009766} 08/30/2021 17:15:20 - INFO - __main__ - Step 22589: {'lr': 0.00047650412899783747, 'samples': 4337088, 'steps': 22588, 'loss/train': 2.1798973083496094} 08/30/2021 17:15:21 - INFO - __main__ - Step 22590: {'lr': 0.0004765018829079479, 'samples': 4337280, 'steps': 22589, 'loss/train': 2.203218698501587} 08/30/2021 17:15:21 - INFO - __main__ - Step 22591: {'lr': 0.0004764996367160001, 'samples': 4337472, 'steps': 22590, 'loss/train': 1.7837680578231812} 08/30/2021 17:15:22 - INFO - __main__ - Step 22592: {'lr': 0.000476497390421995, 'samples': 4337664, 'steps': 22591, 'loss/train': 1.498328447341919} 08/30/2021 17:15:23 - INFO - __main__ - Step 22593: {'lr': 0.00047649514402593377, 'samples': 4337856, 'steps': 22592, 'loss/train': 1.4952605962753296} 08/30/2021 17:15:23 - INFO - __main__ - Step 22594: {'lr': 0.0004764928975278172, 'samples': 4338048, 'steps': 22593, 'loss/train': 1.6838277578353882} 08/30/2021 17:15:24 - INFO - __main__ - Step 22595: {'lr': 0.0004764906509276465, 'samples': 4338240, 'steps': 22594, 'loss/train': 2.1396031379699707} 08/30/2021 17:15:24 - INFO - __main__ - Step 22596: {'lr': 0.0004764884042254226, 'samples': 4338432, 'steps': 22595, 'loss/train': 1.8890920877456665} 08/30/2021 17:15:25 - INFO - __main__ - Step 22597: {'lr': 0.0004764861574211465, 'samples': 4338624, 'steps': 22596, 'loss/train': 1.6218863725662231} 08/30/2021 17:15:26 - INFO - __main__ - Step 22598: {'lr': 0.0004764839105148193, 'samples': 4338816, 'steps': 22597, 'loss/train': 1.2731597423553467} 08/30/2021 17:15:26 - INFO - __main__ - Step 22599: {'lr': 0.00047648166350644185, 'samples': 4339008, 'steps': 22598, 'loss/train': 1.2360286712646484} 08/30/2021 17:15:26 - INFO - __main__ - Step 22600: {'lr': 0.00047647941639601535, 'samples': 4339200, 'steps': 22599, 'loss/train': 1.8576124906539917} 08/30/2021 17:15:27 - INFO - __main__ - Step 22601: {'lr': 0.00047647716918354066, 'samples': 4339392, 'steps': 22600, 'loss/train': 2.1882736682891846} 08/30/2021 17:15:28 - INFO - __main__ - Step 22602: {'lr': 0.00047647492186901884, 'samples': 4339584, 'steps': 22601, 'loss/train': 2.1269142627716064} 08/30/2021 17:15:29 - INFO - __main__ - Step 22603: {'lr': 0.0004764726744524509, 'samples': 4339776, 'steps': 22602, 'loss/train': 1.6733989715576172} 08/30/2021 17:15:29 - INFO - __main__ - Step 22604: {'lr': 0.0004764704269338379, 'samples': 4339968, 'steps': 22603, 'loss/train': 1.9329251050949097} 08/30/2021 17:15:30 - INFO - __main__ - Step 22605: {'lr': 0.00047646817931318086, 'samples': 4340160, 'steps': 22604, 'loss/train': 1.058057427406311} 08/30/2021 17:15:30 - INFO - __main__ - Step 22606: {'lr': 0.0004764659315904807, 'samples': 4340352, 'steps': 22605, 'loss/train': 0.18052689731121063} 08/30/2021 17:15:32 - INFO - __main__ - Step 22607: {'lr': 0.0004764636837657385, 'samples': 4340544, 'steps': 22606, 'loss/train': 0.8237510919570923} 08/30/2021 17:15:32 - INFO - __main__ - Step 22608: {'lr': 0.0004764614358389553, 'samples': 4340736, 'steps': 22607, 'loss/train': 1.9010093212127686} 08/30/2021 17:15:33 - INFO - __main__ - Step 22609: {'lr': 0.00047645918781013196, 'samples': 4340928, 'steps': 22608, 'loss/train': 2.0348987579345703} 08/30/2021 17:15:33 - INFO - __main__ - Step 22610: {'lr': 0.0004764569396792697, 'samples': 4341120, 'steps': 22609, 'loss/train': 1.808739185333252} 08/30/2021 17:15:33 - INFO - __main__ - Step 22611: {'lr': 0.0004764546914463694, 'samples': 4341312, 'steps': 22610, 'loss/train': 0.1274918168783188} 08/30/2021 17:15:35 - INFO - __main__ - Step 22612: {'lr': 0.0004764524431114321, 'samples': 4341504, 'steps': 22611, 'loss/train': 1.0096627473831177} 08/30/2021 17:15:35 - INFO - __main__ - Step 22613: {'lr': 0.0004764501946744589, 'samples': 4341696, 'steps': 22612, 'loss/train': 1.1949007511138916} 08/30/2021 17:15:36 - INFO - __main__ - Step 22614: {'lr': 0.00047644794613545065, 'samples': 4341888, 'steps': 22613, 'loss/train': 1.3782620429992676} 08/30/2021 17:15:36 - INFO - __main__ - Step 22615: {'lr': 0.00047644569749440846, 'samples': 4342080, 'steps': 22614, 'loss/train': 1.6585488319396973} 08/30/2021 17:15:36 - INFO - __main__ - Step 22616: {'lr': 0.0004764434487513334, 'samples': 4342272, 'steps': 22615, 'loss/train': 1.5861353874206543} 08/30/2021 17:15:37 - INFO - __main__ - Step 22617: {'lr': 0.00047644119990622637, 'samples': 4342464, 'steps': 22616, 'loss/train': 2.112118721008301} 08/30/2021 17:15:38 - INFO - __main__ - Step 22618: {'lr': 0.0004764389509590884, 'samples': 4342656, 'steps': 22617, 'loss/train': 1.8465508222579956} 08/30/2021 17:15:39 - INFO - __main__ - Step 22619: {'lr': 0.0004764367019099206, 'samples': 4342848, 'steps': 22618, 'loss/train': 0.16180749237537384} 08/30/2021 17:15:39 - INFO - __main__ - Step 22620: {'lr': 0.0004764344527587239, 'samples': 4343040, 'steps': 22619, 'loss/train': 1.7559525966644287} 08/30/2021 17:15:39 - INFO - __main__ - Step 22621: {'lr': 0.00047643220350549934, 'samples': 4343232, 'steps': 22620, 'loss/train': 1.9561069011688232} 08/30/2021 17:15:40 - INFO - __main__ - Step 22622: {'lr': 0.0004764299541502478, 'samples': 4343424, 'steps': 22621, 'loss/train': 1.8269357681274414} 08/30/2021 17:15:41 - INFO - __main__ - Step 22623: {'lr': 0.0004764277046929706, 'samples': 4343616, 'steps': 22622, 'loss/train': 1.68116295337677} 08/30/2021 17:15:42 - INFO - __main__ - Step 22624: {'lr': 0.00047642545513366843, 'samples': 4343808, 'steps': 22623, 'loss/train': 0.982194185256958} 08/30/2021 17:15:42 - INFO - __main__ - Step 22625: {'lr': 0.0004764232054723425, 'samples': 4344000, 'steps': 22624, 'loss/train': 0.14288485050201416} 08/30/2021 17:15:43 - INFO - __main__ - Step 22626: {'lr': 0.0004764209557089938, 'samples': 4344192, 'steps': 22625, 'loss/train': 1.557816743850708} 08/30/2021 17:15:43 - INFO - __main__ - Step 22627: {'lr': 0.00047641870584362323, 'samples': 4344384, 'steps': 22626, 'loss/train': 1.734743595123291} 08/30/2021 17:15:45 - INFO - __main__ - Step 22628: {'lr': 0.00047641645587623196, 'samples': 4344576, 'steps': 22627, 'loss/train': 2.719785213470459} 08/30/2021 17:15:46 - INFO - __main__ - Step 22629: {'lr': 0.0004764142058068209, 'samples': 4344768, 'steps': 22628, 'loss/train': 1.2836214303970337} 08/30/2021 17:15:46 - INFO - __main__ - Step 22630: {'lr': 0.00047641195563539107, 'samples': 4344960, 'steps': 22629, 'loss/train': 1.551599383354187} 08/30/2021 17:15:47 - INFO - __main__ - Step 22631: {'lr': 0.0004764097053619435, 'samples': 4345152, 'steps': 22630, 'loss/train': 1.526296854019165} 08/30/2021 17:15:47 - INFO - __main__ - Step 22632: {'lr': 0.00047640745498647925, 'samples': 4345344, 'steps': 22631, 'loss/train': 3.1410653591156006} 08/30/2021 17:15:47 - INFO - __main__ - Step 22633: {'lr': 0.00047640520450899926, 'samples': 4345536, 'steps': 22632, 'loss/train': 3.2670083045959473} 08/30/2021 17:15:49 - INFO - __main__ - Step 22634: {'lr': 0.0004764029539295046, 'samples': 4345728, 'steps': 22633, 'loss/train': 1.6931003332138062} 08/30/2021 17:15:50 - INFO - __main__ - Step 22635: {'lr': 0.0004764007032479963, 'samples': 4345920, 'steps': 22634, 'loss/train': 1.7444283962249756} 08/30/2021 17:15:50 - INFO - __main__ - Step 22636: {'lr': 0.00047639845246447534, 'samples': 4346112, 'steps': 22635, 'loss/train': 1.6407912969589233} 08/30/2021 17:15:50 - INFO - __main__ - Step 22637: {'lr': 0.00047639620157894264, 'samples': 4346304, 'steps': 22636, 'loss/train': 1.3127738237380981} 08/30/2021 17:15:51 - INFO - __main__ - Step 22638: {'lr': 0.00047639395059139936, 'samples': 4346496, 'steps': 22637, 'loss/train': 1.869842767715454} 08/30/2021 17:15:51 - INFO - __main__ - Step 22639: {'lr': 0.0004763916995018465, 'samples': 4346688, 'steps': 22638, 'loss/train': 1.3320239782333374} 08/30/2021 17:15:53 - INFO - __main__ - Step 22640: {'lr': 0.00047638944831028497, 'samples': 4346880, 'steps': 22639, 'loss/train': 1.6166237592697144} 08/30/2021 17:15:53 - INFO - __main__ - Step 22641: {'lr': 0.00047638719701671587, 'samples': 4347072, 'steps': 22640, 'loss/train': 1.786665678024292} 08/30/2021 17:15:53 - INFO - __main__ - Step 22642: {'lr': 0.00047638494562114015, 'samples': 4347264, 'steps': 22641, 'loss/train': 1.4907608032226562} 08/30/2021 17:15:54 - INFO - __main__ - Step 22643: {'lr': 0.0004763826941235589, 'samples': 4347456, 'steps': 22642, 'loss/train': 1.1272971630096436} 08/30/2021 17:15:54 - INFO - __main__ - Step 22644: {'lr': 0.00047638044252397313, 'samples': 4347648, 'steps': 22643, 'loss/train': 1.7200355529785156} 08/30/2021 17:15:56 - INFO - __main__ - Step 22645: {'lr': 0.0004763781908223838, 'samples': 4347840, 'steps': 22644, 'loss/train': 1.3382102251052856} 08/30/2021 17:15:56 - INFO - __main__ - Step 22646: {'lr': 0.00047637593901879194, 'samples': 4348032, 'steps': 22645, 'loss/train': 1.9048612117767334} 08/30/2021 17:15:56 - INFO - __main__ - Step 22647: {'lr': 0.00047637368711319863, 'samples': 4348224, 'steps': 22646, 'loss/train': 1.7801023721694946} 08/30/2021 17:15:57 - INFO - __main__ - Step 22648: {'lr': 0.00047637143510560477, 'samples': 4348416, 'steps': 22647, 'loss/train': 1.4967598915100098} 08/30/2021 17:15:57 - INFO - __main__ - Step 22649: {'lr': 0.0004763691829960114, 'samples': 4348608, 'steps': 22648, 'loss/train': 1.8857465982437134} 08/30/2021 17:15:59 - INFO - __main__ - Step 22650: {'lr': 0.00047636693078441963, 'samples': 4348800, 'steps': 22649, 'loss/train': 1.1992545127868652} 08/30/2021 17:15:59 - INFO - __main__ - Step 22651: {'lr': 0.0004763646784708304, 'samples': 4348992, 'steps': 22650, 'loss/train': 0.19952024519443512} 08/30/2021 17:16:00 - INFO - __main__ - Step 22652: {'lr': 0.00047636242605524477, 'samples': 4349184, 'steps': 22651, 'loss/train': 1.5169461965560913} 08/30/2021 17:16:00 - INFO - __main__ - Step 22653: {'lr': 0.0004763601735376637, 'samples': 4349376, 'steps': 22652, 'loss/train': 1.5541881322860718} 08/30/2021 17:16:00 - INFO - __main__ - Step 22654: {'lr': 0.0004763579209180882, 'samples': 4349568, 'steps': 22653, 'loss/train': 1.364939570426941} 08/30/2021 17:16:02 - INFO - __main__ - Step 22655: {'lr': 0.00047635566819651936, 'samples': 4349760, 'steps': 22654, 'loss/train': 1.6734801530838013} 08/30/2021 17:16:03 - INFO - __main__ - Step 22656: {'lr': 0.00047635341537295814, 'samples': 4349952, 'steps': 22655, 'loss/train': 2.059765338897705} 08/30/2021 17:16:03 - INFO - __main__ - Step 22657: {'lr': 0.0004763511624474055, 'samples': 4350144, 'steps': 22656, 'loss/train': 2.098519802093506} 08/30/2021 17:16:03 - INFO - __main__ - Step 22658: {'lr': 0.00047634890941986263, 'samples': 4350336, 'steps': 22657, 'loss/train': 1.7504721879959106} 08/30/2021 17:16:04 - INFO - __main__ - Step 22659: {'lr': 0.00047634665629033035, 'samples': 4350528, 'steps': 22658, 'loss/train': 1.7271106243133545} 08/30/2021 17:16:05 - INFO - __main__ - Step 22660: {'lr': 0.00047634440305880976, 'samples': 4350720, 'steps': 22659, 'loss/train': 1.0989255905151367} 08/30/2021 17:16:05 - INFO - __main__ - Step 22661: {'lr': 0.0004763421497253019, 'samples': 4350912, 'steps': 22660, 'loss/train': 2.4688119888305664} 08/30/2021 17:16:06 - INFO - __main__ - Step 22662: {'lr': 0.0004763398962898078, 'samples': 4351104, 'steps': 22661, 'loss/train': 1.638301134109497} 08/30/2021 17:16:06 - INFO - __main__ - Step 22663: {'lr': 0.0004763376427523284, 'samples': 4351296, 'steps': 22662, 'loss/train': 1.5809268951416016} 08/30/2021 17:16:06 - INFO - __main__ - Step 22664: {'lr': 0.0004763353891128648, 'samples': 4351488, 'steps': 22663, 'loss/train': 1.5273466110229492} 08/30/2021 17:16:07 - INFO - __main__ - Step 22665: {'lr': 0.00047633313537141786, 'samples': 4351680, 'steps': 22664, 'loss/train': 1.8765552043914795} 08/30/2021 17:16:08 - INFO - __main__ - Step 22666: {'lr': 0.00047633088152798875, 'samples': 4351872, 'steps': 22665, 'loss/train': 1.879747748374939} 08/30/2021 17:16:09 - INFO - __main__ - Step 22667: {'lr': 0.00047632862758257845, 'samples': 4352064, 'steps': 22666, 'loss/train': 1.3156960010528564} 08/30/2021 17:16:09 - INFO - __main__ - Step 22668: {'lr': 0.0004763263735351879, 'samples': 4352256, 'steps': 22667, 'loss/train': 1.77305269241333} 08/30/2021 17:16:09 - INFO - __main__ - Step 22669: {'lr': 0.0004763241193858183, 'samples': 4352448, 'steps': 22668, 'loss/train': 2.2486209869384766} 08/30/2021 17:16:10 - INFO - __main__ - Step 22670: {'lr': 0.00047632186513447045, 'samples': 4352640, 'steps': 22669, 'loss/train': 1.4093332290649414} 08/30/2021 17:16:11 - INFO - __main__ - Step 22671: {'lr': 0.0004763196107811455, 'samples': 4352832, 'steps': 22670, 'loss/train': 1.8424217700958252} 08/30/2021 17:16:12 - INFO - __main__ - Step 22672: {'lr': 0.0004763173563258444, 'samples': 4353024, 'steps': 22671, 'loss/train': 1.6107220649719238} 08/30/2021 17:16:12 - INFO - __main__ - Step 22673: {'lr': 0.0004763151017685682, 'samples': 4353216, 'steps': 22672, 'loss/train': 1.0175189971923828} 08/30/2021 17:16:12 - INFO - __main__ - Step 22674: {'lr': 0.0004763128471093179, 'samples': 4353408, 'steps': 22673, 'loss/train': 1.0710530281066895} 08/30/2021 17:16:13 - INFO - __main__ - Step 22675: {'lr': 0.0004763105923480946, 'samples': 4353600, 'steps': 22674, 'loss/train': 1.3609719276428223} 08/30/2021 17:16:14 - INFO - __main__ - Step 22676: {'lr': 0.0004763083374848991, 'samples': 4353792, 'steps': 22675, 'loss/train': 1.3715710639953613} 08/30/2021 17:16:15 - INFO - __main__ - Step 22677: {'lr': 0.00047630608251973265, 'samples': 4353984, 'steps': 22676, 'loss/train': 2.1492466926574707} 08/30/2021 17:16:15 - INFO - __main__ - Step 22678: {'lr': 0.00047630382745259616, 'samples': 4354176, 'steps': 22677, 'loss/train': 1.9249857664108276} 08/30/2021 17:16:15 - INFO - __main__ - Step 22679: {'lr': 0.0004763015722834907, 'samples': 4354368, 'steps': 22678, 'loss/train': 1.978841781616211} 08/30/2021 17:16:16 - INFO - __main__ - Step 22680: {'lr': 0.00047629931701241715, 'samples': 4354560, 'steps': 22679, 'loss/train': 1.268255352973938} 08/30/2021 17:16:17 - INFO - __main__ - Step 22681: {'lr': 0.0004762970616393767, 'samples': 4354752, 'steps': 22680, 'loss/train': 1.7757965326309204} 08/30/2021 17:16:18 - INFO - __main__ - Step 22682: {'lr': 0.0004762948061643702, 'samples': 4354944, 'steps': 22681, 'loss/train': 0.6261685490608215} 08/30/2021 17:16:18 - INFO - __main__ - Step 22683: {'lr': 0.0004762925505873988, 'samples': 4355136, 'steps': 22682, 'loss/train': 2.0943148136138916} 08/30/2021 17:16:18 - INFO - __main__ - Step 22684: {'lr': 0.00047629029490846346, 'samples': 4355328, 'steps': 22683, 'loss/train': 0.6795475482940674} 08/30/2021 17:16:19 - INFO - __main__ - Step 22685: {'lr': 0.00047628803912756523, 'samples': 4355520, 'steps': 22684, 'loss/train': 1.8683626651763916} 08/30/2021 17:16:21 - INFO - __main__ - Step 22686: {'lr': 0.00047628578324470505, 'samples': 4355712, 'steps': 22685, 'loss/train': 1.8733292818069458} 08/30/2021 17:16:21 - INFO - __main__ - Step 22687: {'lr': 0.00047628352725988406, 'samples': 4355904, 'steps': 22686, 'loss/train': 1.759171724319458} 08/30/2021 17:16:21 - INFO - __main__ - Step 22688: {'lr': 0.0004762812711731032, 'samples': 4356096, 'steps': 22687, 'loss/train': 1.767892837524414} 08/30/2021 17:16:22 - INFO - __main__ - Step 22689: {'lr': 0.00047627901498436344, 'samples': 4356288, 'steps': 22688, 'loss/train': 1.8540290594100952} 08/30/2021 17:16:22 - INFO - __main__ - Step 22690: {'lr': 0.0004762767586936658, 'samples': 4356480, 'steps': 22689, 'loss/train': 1.75572669506073} 08/30/2021 17:16:24 - INFO - __main__ - Step 22691: {'lr': 0.00047627450230101144, 'samples': 4356672, 'steps': 22690, 'loss/train': 1.6989866495132446} 08/30/2021 17:16:24 - INFO - __main__ - Step 22692: {'lr': 0.0004762722458064013, 'samples': 4356864, 'steps': 22691, 'loss/train': 1.6670310497283936} 08/30/2021 17:16:24 - INFO - __main__ - Step 22693: {'lr': 0.0004762699892098363, 'samples': 4357056, 'steps': 22692, 'loss/train': 1.6908589601516724} 08/30/2021 17:16:25 - INFO - __main__ - Step 22694: {'lr': 0.0004762677325113176, 'samples': 4357248, 'steps': 22693, 'loss/train': 1.4345744848251343} 08/30/2021 17:16:25 - INFO - __main__ - Step 22695: {'lr': 0.0004762654757108461, 'samples': 4357440, 'steps': 22694, 'loss/train': 2.0730648040771484} 08/30/2021 17:16:26 - INFO - __main__ - Step 22696: {'lr': 0.00047626321880842287, 'samples': 4357632, 'steps': 22695, 'loss/train': 1.5803663730621338} 08/30/2021 17:16:27 - INFO - __main__ - Step 22697: {'lr': 0.00047626096180404895, 'samples': 4357824, 'steps': 22696, 'loss/train': 1.8902571201324463} 08/30/2021 17:16:27 - INFO - __main__ - Step 22698: {'lr': 0.0004762587046977253, 'samples': 4358016, 'steps': 22697, 'loss/train': 1.4248958826065063} 08/30/2021 17:16:28 - INFO - __main__ - Step 22699: {'lr': 0.000476256447489453, 'samples': 4358208, 'steps': 22698, 'loss/train': 1.7172247171401978} 08/30/2021 17:16:28 - INFO - __main__ - Step 22700: {'lr': 0.000476254190179233, 'samples': 4358400, 'steps': 22699, 'loss/train': 1.6442368030548096} 08/30/2021 17:16:30 - INFO - __main__ - Step 22701: {'lr': 0.0004762519327670664, 'samples': 4358592, 'steps': 22700, 'loss/train': 1.4775010347366333} 08/30/2021 17:16:30 - INFO - __main__ - Step 22702: {'lr': 0.0004762496752529541, 'samples': 4358784, 'steps': 22701, 'loss/train': 1.758837103843689} 08/30/2021 17:16:30 - INFO - __main__ - Step 22703: {'lr': 0.0004762474176368973, 'samples': 4358976, 'steps': 22702, 'loss/train': 1.3404951095581055} 08/30/2021 17:16:31 - INFO - __main__ - Step 22704: {'lr': 0.00047624515991889684, 'samples': 4359168, 'steps': 22703, 'loss/train': 2.242572546005249} 08/30/2021 17:16:31 - INFO - __main__ - Step 22705: {'lr': 0.00047624290209895384, 'samples': 4359360, 'steps': 22704, 'loss/train': 2.0615878105163574} 08/30/2021 17:16:33 - INFO - __main__ - Step 22706: {'lr': 0.00047624064417706917, 'samples': 4359552, 'steps': 22705, 'loss/train': 1.3389997482299805} 08/30/2021 17:16:34 - INFO - __main__ - Step 22707: {'lr': 0.00047623838615324407, 'samples': 4359744, 'steps': 22706, 'loss/train': 1.843644142150879} 08/30/2021 17:16:34 - INFO - __main__ - Step 22708: {'lr': 0.0004762361280274794, 'samples': 4359936, 'steps': 22707, 'loss/train': 1.8705817461013794} 08/30/2021 17:16:34 - INFO - __main__ - Step 22709: {'lr': 0.0004762338697997762, 'samples': 4360128, 'steps': 22708, 'loss/train': 1.4605693817138672} 08/30/2021 17:16:35 - INFO - __main__ - Step 22710: {'lr': 0.00047623161147013557, 'samples': 4360320, 'steps': 22709, 'loss/train': 1.4370949268341064} 08/30/2021 17:16:36 - INFO - __main__ - Step 22711: {'lr': 0.0004762293530385584, 'samples': 4360512, 'steps': 22710, 'loss/train': 0.1271795928478241} 08/30/2021 17:16:36 - INFO - __main__ - Step 22712: {'lr': 0.0004762270945050458, 'samples': 4360704, 'steps': 22711, 'loss/train': 2.282175064086914} 08/30/2021 17:16:37 - INFO - __main__ - Step 22713: {'lr': 0.00047622483586959877, 'samples': 4360896, 'steps': 22712, 'loss/train': 1.7745230197906494} 08/30/2021 17:16:37 - INFO - __main__ - Step 22714: {'lr': 0.00047622257713221826, 'samples': 4361088, 'steps': 22713, 'loss/train': 1.5097118616104126} 08/30/2021 17:16:38 - INFO - __main__ - Step 22715: {'lr': 0.00047622031829290545, 'samples': 4361280, 'steps': 22714, 'loss/train': 1.5611250400543213} 08/30/2021 17:16:39 - INFO - __main__ - Step 22716: {'lr': 0.0004762180593516612, 'samples': 4361472, 'steps': 22715, 'loss/train': 1.5972368717193604} 08/30/2021 17:16:40 - INFO - __main__ - Step 22717: {'lr': 0.0004762158003084867, 'samples': 4361664, 'steps': 22716, 'loss/train': 2.6648776531219482} 08/30/2021 17:16:40 - INFO - __main__ - Step 22718: {'lr': 0.0004762135411633827, 'samples': 4361856, 'steps': 22717, 'loss/train': 1.5549181699752808} 08/30/2021 17:16:40 - INFO - __main__ - Step 22719: {'lr': 0.0004762112819163504, 'samples': 4362048, 'steps': 22718, 'loss/train': 1.5840942859649658} 08/30/2021 17:16:41 - INFO - __main__ - Step 22720: {'lr': 0.0004762090225673908, 'samples': 4362240, 'steps': 22719, 'loss/train': 1.1802986860275269} 08/30/2021 17:16:41 - INFO - __main__ - Step 22721: {'lr': 0.0004762067631165049, 'samples': 4362432, 'steps': 22720, 'loss/train': 1.972393274307251} 08/30/2021 17:16:43 - INFO - __main__ - Step 22722: {'lr': 0.0004762045035636937, 'samples': 4362624, 'steps': 22721, 'loss/train': 0.8380379676818848} 08/30/2021 17:16:43 - INFO - __main__ - Step 22723: {'lr': 0.0004762022439089583, 'samples': 4362816, 'steps': 22722, 'loss/train': 1.7101861238479614} 08/30/2021 17:16:43 - INFO - __main__ - Step 22724: {'lr': 0.0004761999841522996, 'samples': 4363008, 'steps': 22723, 'loss/train': 2.1470186710357666} 08/30/2021 17:16:44 - INFO - __main__ - Step 22725: {'lr': 0.0004761977242937188, 'samples': 4363200, 'steps': 22724, 'loss/train': 1.7504310607910156} 08/30/2021 17:16:44 - INFO - __main__ - Step 22726: {'lr': 0.00047619546433321663, 'samples': 4363392, 'steps': 22725, 'loss/train': 1.112618327140808} 08/30/2021 17:16:46 - INFO - __main__ - Step 22727: {'lr': 0.00047619320427079437, 'samples': 4363584, 'steps': 22726, 'loss/train': 1.5926406383514404} 08/30/2021 17:16:46 - INFO - __main__ - Step 22728: {'lr': 0.00047619094410645293, 'samples': 4363776, 'steps': 22727, 'loss/train': 0.8259417414665222} 08/30/2021 17:16:47 - INFO - __main__ - Step 22729: {'lr': 0.0004761886838401933, 'samples': 4363968, 'steps': 22728, 'loss/train': 1.9355567693710327} 08/30/2021 17:16:47 - INFO - __main__ - Step 22730: {'lr': 0.0004761864234720166, 'samples': 4364160, 'steps': 22729, 'loss/train': 1.997549057006836} 08/30/2021 17:16:47 - INFO - __main__ - Step 22731: {'lr': 0.00047618416300192375, 'samples': 4364352, 'steps': 22730, 'loss/train': 1.2267361879348755} 08/30/2021 17:16:48 - INFO - __main__ - Step 22732: {'lr': 0.0004761819024299158, 'samples': 4364544, 'steps': 22731, 'loss/train': 1.8489607572555542} 08/30/2021 17:16:49 - INFO - __main__ - Step 22733: {'lr': 0.0004761796417559938, 'samples': 4364736, 'steps': 22732, 'loss/train': 1.7026993036270142} 08/30/2021 17:16:50 - INFO - __main__ - Step 22734: {'lr': 0.0004761773809801587, 'samples': 4364928, 'steps': 22733, 'loss/train': 1.4597245454788208} 08/30/2021 17:16:50 - INFO - __main__ - Step 22735: {'lr': 0.0004761751201024116, 'samples': 4365120, 'steps': 22734, 'loss/train': 1.5148273706436157} 08/30/2021 17:16:50 - INFO - __main__ - Step 22736: {'lr': 0.0004761728591227535, 'samples': 4365312, 'steps': 22735, 'loss/train': 1.2636899948120117} 08/30/2021 17:16:51 - INFO - __main__ - Step 22737: {'lr': 0.00047617059804118536, 'samples': 4365504, 'steps': 22736, 'loss/train': 1.7436262369155884} 08/30/2021 17:16:53 - INFO - __main__ - Step 22738: {'lr': 0.0004761683368577083, 'samples': 4365696, 'steps': 22737, 'loss/train': 1.5510469675064087} 08/30/2021 17:16:53 - INFO - __main__ - Step 22739: {'lr': 0.0004761660755723232, 'samples': 4365888, 'steps': 22738, 'loss/train': 1.2957271337509155} 08/30/2021 17:16:54 - INFO - __main__ - Step 22740: {'lr': 0.0004761638141850312, 'samples': 4366080, 'steps': 22739, 'loss/train': 1.8613446950912476} 08/30/2021 17:16:54 - INFO - __main__ - Step 22741: {'lr': 0.0004761615526958333, 'samples': 4366272, 'steps': 22740, 'loss/train': 1.8560149669647217} 08/30/2021 17:16:54 - INFO - __main__ - Step 22742: {'lr': 0.0004761592911047304, 'samples': 4366464, 'steps': 22741, 'loss/train': 1.860827922821045} 08/30/2021 17:16:56 - INFO - __main__ - Step 22743: {'lr': 0.00047615702941172366, 'samples': 4366656, 'steps': 22742, 'loss/train': 1.5457545518875122} 08/30/2021 17:16:56 - INFO - __main__ - Step 22744: {'lr': 0.0004761547676168141, 'samples': 4366848, 'steps': 22743, 'loss/train': 1.7188726663589478} 08/30/2021 17:16:57 - INFO - __main__ - Step 22745: {'lr': 0.0004761525057200027, 'samples': 4367040, 'steps': 22744, 'loss/train': 2.0277504920959473} 08/30/2021 17:16:57 - INFO - __main__ - Step 22746: {'lr': 0.00047615024372129033, 'samples': 4367232, 'steps': 22745, 'loss/train': 1.4906532764434814} 08/30/2021 17:16:57 - INFO - __main__ - Step 22747: {'lr': 0.0004761479816206783, 'samples': 4367424, 'steps': 22746, 'loss/train': 1.1546109914779663} 08/30/2021 17:16:59 - INFO - __main__ - Step 22748: {'lr': 0.00047614571941816743, 'samples': 4367616, 'steps': 22747, 'loss/train': 0.0923515036702156} 08/30/2021 17:16:59 - INFO - __main__ - Step 22749: {'lr': 0.00047614345711375874, 'samples': 4367808, 'steps': 22748, 'loss/train': 1.6979933977127075} 08/30/2021 17:17:00 - INFO - __main__ - Step 22750: {'lr': 0.0004761411947074533, 'samples': 4368000, 'steps': 22749, 'loss/train': 1.2950513362884521} 08/30/2021 17:17:00 - INFO - __main__ - Step 22751: {'lr': 0.00047613893219925217, 'samples': 4368192, 'steps': 22750, 'loss/train': 0.35021892189979553} 08/30/2021 17:17:00 - INFO - __main__ - Step 22752: {'lr': 0.00047613666958915636, 'samples': 4368384, 'steps': 22751, 'loss/train': 0.8060241937637329} 08/30/2021 17:17:02 - INFO - __main__ - Step 22753: {'lr': 0.0004761344068771668, 'samples': 4368576, 'steps': 22752, 'loss/train': 1.5739452838897705} 08/30/2021 17:17:02 - INFO - __main__ - Step 22754: {'lr': 0.0004761321440632846, 'samples': 4368768, 'steps': 22753, 'loss/train': 1.9471994638442993} 08/30/2021 17:17:03 - INFO - __main__ - Step 22755: {'lr': 0.00047612988114751074, 'samples': 4368960, 'steps': 22754, 'loss/train': 0.7910296320915222} 08/30/2021 17:17:03 - INFO - __main__ - Step 22756: {'lr': 0.00047612761812984626, 'samples': 4369152, 'steps': 22755, 'loss/train': 1.2983958721160889} 08/30/2021 17:17:03 - INFO - __main__ - Step 22757: {'lr': 0.00047612535501029215, 'samples': 4369344, 'steps': 22756, 'loss/train': 1.8251382112503052} 08/30/2021 17:17:04 - INFO - __main__ - Step 22758: {'lr': 0.0004761230917888494, 'samples': 4369536, 'steps': 22757, 'loss/train': 1.9290217161178589} 08/30/2021 17:17:05 - INFO - __main__ - Step 22759: {'lr': 0.00047612082846551913, 'samples': 4369728, 'steps': 22758, 'loss/train': 1.0281867980957031} 08/30/2021 17:17:06 - INFO - __main__ - Step 22760: {'lr': 0.0004761185650403023, 'samples': 4369920, 'steps': 22759, 'loss/train': 1.2882440090179443} 08/30/2021 17:17:06 - INFO - __main__ - Step 22761: {'lr': 0.0004761163015131999, 'samples': 4370112, 'steps': 22760, 'loss/train': 1.6148911714553833} 08/30/2021 17:17:07 - INFO - __main__ - Step 22762: {'lr': 0.00047611403788421305, 'samples': 4370304, 'steps': 22761, 'loss/train': 1.910568356513977} 08/30/2021 17:17:07 - INFO - __main__ - Step 22763: {'lr': 0.0004761117741533426, 'samples': 4370496, 'steps': 22762, 'loss/train': 1.8226226568222046} 08/30/2021 17:17:08 - INFO - __main__ - Step 22764: {'lr': 0.0004761095103205897, 'samples': 4370688, 'steps': 22763, 'loss/train': 1.7216705083847046} 08/30/2021 17:17:09 - INFO - __main__ - Step 22765: {'lr': 0.00047610724638595545, 'samples': 4370880, 'steps': 22764, 'loss/train': 0.06404563039541245} 08/30/2021 17:17:09 - INFO - __main__ - Step 22766: {'lr': 0.00047610498234944065, 'samples': 4371072, 'steps': 22765, 'loss/train': 1.3860447406768799} 08/30/2021 17:17:10 - INFO - __main__ - Step 22767: {'lr': 0.00047610271821104647, 'samples': 4371264, 'steps': 22766, 'loss/train': 1.1288124322891235} 08/30/2021 17:17:10 - INFO - __main__ - Step 22768: {'lr': 0.0004761004539707739, 'samples': 4371456, 'steps': 22767, 'loss/train': 1.9874215126037598} 08/30/2021 17:17:11 - INFO - __main__ - Step 22769: {'lr': 0.00047609818962862394, 'samples': 4371648, 'steps': 22768, 'loss/train': 1.9229989051818848} 08/30/2021 17:17:12 - INFO - __main__ - Step 22770: {'lr': 0.00047609592518459766, 'samples': 4371840, 'steps': 22769, 'loss/train': 1.4309335947036743} 08/30/2021 17:17:12 - INFO - __main__ - Step 22771: {'lr': 0.00047609366063869595, 'samples': 4372032, 'steps': 22770, 'loss/train': 1.706612467765808} 08/30/2021 17:17:13 - INFO - __main__ - Step 22772: {'lr': 0.00047609139599092006, 'samples': 4372224, 'steps': 22771, 'loss/train': 0.9627857208251953} 08/30/2021 17:17:13 - INFO - __main__ - Step 22773: {'lr': 0.0004760891312412708, 'samples': 4372416, 'steps': 22772, 'loss/train': 1.4608187675476074} 08/30/2021 17:17:14 - INFO - __main__ - Step 22774: {'lr': 0.0004760868663897493, 'samples': 4372608, 'steps': 22773, 'loss/train': 1.4157202243804932} 08/30/2021 17:17:15 - INFO - __main__ - Step 22775: {'lr': 0.0004760846014363565, 'samples': 4372800, 'steps': 22774, 'loss/train': 1.8349318504333496} 08/30/2021 17:17:15 - INFO - __main__ - Step 22776: {'lr': 0.0004760823363810935, 'samples': 4372992, 'steps': 22775, 'loss/train': 1.6829019784927368} 08/30/2021 17:17:16 - INFO - __main__ - Step 22777: {'lr': 0.0004760800712239612, 'samples': 4373184, 'steps': 22776, 'loss/train': 1.3641904592514038} 08/30/2021 17:17:16 - INFO - __main__ - Step 22778: {'lr': 0.0004760778059649609, 'samples': 4373376, 'steps': 22777, 'loss/train': 1.5136724710464478} 08/30/2021 17:17:17 - INFO - __main__ - Step 22779: {'lr': 0.0004760755406040933, 'samples': 4373568, 'steps': 22778, 'loss/train': 1.8314247131347656} 08/30/2021 17:17:18 - INFO - __main__ - Step 22780: {'lr': 0.00047607327514135955, 'samples': 4373760, 'steps': 22779, 'loss/train': 1.7004406452178955} 08/30/2021 17:17:18 - INFO - __main__ - Step 22781: {'lr': 0.00047607100957676067, 'samples': 4373952, 'steps': 22780, 'loss/train': 1.4628232717514038} 08/30/2021 17:17:19 - INFO - __main__ - Step 22782: {'lr': 0.0004760687439102977, 'samples': 4374144, 'steps': 22781, 'loss/train': 1.600130558013916} 08/30/2021 17:17:19 - INFO - __main__ - Step 22783: {'lr': 0.0004760664781419717, 'samples': 4374336, 'steps': 22782, 'loss/train': 1.2052366733551025} 08/30/2021 17:17:21 - INFO - __main__ - Step 22784: {'lr': 0.00047606421227178354, 'samples': 4374528, 'steps': 22783, 'loss/train': 1.670741081237793} 08/30/2021 17:17:21 - INFO - __main__ - Step 22785: {'lr': 0.0004760619462997343, 'samples': 4374720, 'steps': 22784, 'loss/train': 1.5195059776306152} 08/30/2021 17:17:22 - INFO - __main__ - Step 22786: {'lr': 0.00047605968022582513, 'samples': 4374912, 'steps': 22785, 'loss/train': 1.409189224243164} 08/30/2021 17:17:22 - INFO - __main__ - Step 22787: {'lr': 0.000476057414050057, 'samples': 4375104, 'steps': 22786, 'loss/train': 1.396681308746338} 08/30/2021 17:17:22 - INFO - __main__ - Step 22788: {'lr': 0.00047605514777243076, 'samples': 4375296, 'steps': 22787, 'loss/train': 1.1407527923583984} 08/30/2021 17:17:24 - INFO - __main__ - Step 22789: {'lr': 0.0004760528813929476, 'samples': 4375488, 'steps': 22788, 'loss/train': 0.10242465138435364} 08/30/2021 17:17:25 - INFO - __main__ - Step 22790: {'lr': 0.0004760506149116085, 'samples': 4375680, 'steps': 22789, 'loss/train': 1.7497690916061401} 08/30/2021 17:17:25 - INFO - __main__ - Step 22791: {'lr': 0.0004760483483284145, 'samples': 4375872, 'steps': 22790, 'loss/train': 2.0616135597229004} 08/30/2021 17:17:25 - INFO - __main__ - Step 22792: {'lr': 0.0004760460816433666, 'samples': 4376064, 'steps': 22791, 'loss/train': 1.7703133821487427} 08/30/2021 17:17:26 - INFO - __main__ - Step 22793: {'lr': 0.0004760438148564659, 'samples': 4376256, 'steps': 22792, 'loss/train': 1.3119556903839111} 08/30/2021 17:17:26 - INFO - __main__ - Step 22794: {'lr': 0.00047604154796771327, 'samples': 4376448, 'steps': 22793, 'loss/train': 1.9411065578460693} 08/30/2021 17:17:28 - INFO - __main__ - Step 22795: {'lr': 0.0004760392809771098, 'samples': 4376640, 'steps': 22794, 'loss/train': 1.8020325899124146} 08/30/2021 17:17:28 - INFO - __main__ - Step 22796: {'lr': 0.00047603701388465646, 'samples': 4376832, 'steps': 22795, 'loss/train': 2.1383056640625} 08/30/2021 17:17:28 - INFO - __main__ - Step 22797: {'lr': 0.0004760347466903544, 'samples': 4377024, 'steps': 22796, 'loss/train': 1.6379649639129639} 08/30/2021 17:17:29 - INFO - __main__ - Step 22798: {'lr': 0.0004760324793942046, 'samples': 4377216, 'steps': 22797, 'loss/train': 1.4360427856445312} 08/30/2021 17:17:29 - INFO - __main__ - Step 22799: {'lr': 0.000476030211996208, 'samples': 4377408, 'steps': 22798, 'loss/train': 0.5922221541404724} 08/30/2021 17:17:31 - INFO - __main__ - Step 22800: {'lr': 0.0004760279444963657, 'samples': 4377600, 'steps': 22799, 'loss/train': 1.4615356922149658} 08/30/2021 17:17:31 - INFO - __main__ - Step 22801: {'lr': 0.0004760256768946787, 'samples': 4377792, 'steps': 22800, 'loss/train': 1.6913899183273315} 08/30/2021 17:17:31 - INFO - __main__ - Step 22802: {'lr': 0.00047602340919114793, 'samples': 4377984, 'steps': 22801, 'loss/train': 1.722115159034729} 08/30/2021 17:17:32 - INFO - __main__ - Step 22803: {'lr': 0.00047602114138577464, 'samples': 4378176, 'steps': 22802, 'loss/train': 1.2216346263885498} 08/30/2021 17:17:32 - INFO - __main__ - Step 22804: {'lr': 0.00047601887347855965, 'samples': 4378368, 'steps': 22803, 'loss/train': 1.5958867073059082} 08/30/2021 17:17:34 - INFO - __main__ - Step 22805: {'lr': 0.00047601660546950396, 'samples': 4378560, 'steps': 22804, 'loss/train': 1.288720965385437} 08/30/2021 17:17:34 - INFO - __main__ - Step 22806: {'lr': 0.0004760143373586088, 'samples': 4378752, 'steps': 22805, 'loss/train': 1.337775707244873} 08/30/2021 17:17:35 - INFO - __main__ - Step 22807: {'lr': 0.000476012069145875, 'samples': 4378944, 'steps': 22806, 'loss/train': 1.4912784099578857} 08/30/2021 17:17:35 - INFO - __main__ - Step 22808: {'lr': 0.00047600980083130367, 'samples': 4379136, 'steps': 22807, 'loss/train': 0.16186995804309845} 08/30/2021 17:17:35 - INFO - __main__ - Step 22809: {'lr': 0.0004760075324148959, 'samples': 4379328, 'steps': 22808, 'loss/train': 2.0144107341766357} 08/30/2021 17:17:36 - INFO - __main__ - Step 22810: {'lr': 0.00047600526389665246, 'samples': 4379520, 'steps': 22809, 'loss/train': 1.2294877767562866} 08/30/2021 17:17:37 - INFO - __main__ - Step 22811: {'lr': 0.00047600299527657464, 'samples': 4379712, 'steps': 22810, 'loss/train': 1.824755072593689} 08/30/2021 17:17:38 - INFO - __main__ - Step 22812: {'lr': 0.0004760007265546633, 'samples': 4379904, 'steps': 22811, 'loss/train': 1.269286036491394} 08/30/2021 17:17:38 - INFO - __main__ - Step 22813: {'lr': 0.00047599845773091957, 'samples': 4380096, 'steps': 22812, 'loss/train': 1.4401121139526367} 08/30/2021 17:17:39 - INFO - __main__ - Step 22814: {'lr': 0.0004759961888053444, 'samples': 4380288, 'steps': 22813, 'loss/train': 2.1565186977386475} 08/30/2021 17:17:39 - INFO - __main__ - Step 22815: {'lr': 0.00047599391977793884, 'samples': 4380480, 'steps': 22814, 'loss/train': 1.5639879703521729} 08/30/2021 17:17:40 - INFO - __main__ - Step 22816: {'lr': 0.00047599165064870385, 'samples': 4380672, 'steps': 22815, 'loss/train': 3.1073622703552246} 08/30/2021 17:17:41 - INFO - __main__ - Step 22817: {'lr': 0.0004759893814176406, 'samples': 4380864, 'steps': 22816, 'loss/train': 0.3915186822414398} 08/30/2021 17:17:41 - INFO - __main__ - Step 22818: {'lr': 0.00047598711208475, 'samples': 4381056, 'steps': 22817, 'loss/train': 1.7690671682357788} 08/30/2021 17:17:41 - INFO - __main__ - Step 22819: {'lr': 0.00047598484265003307, 'samples': 4381248, 'steps': 22818, 'loss/train': 1.451126217842102} 08/30/2021 17:17:42 - INFO - __main__ - Step 22820: {'lr': 0.00047598257311349087, 'samples': 4381440, 'steps': 22819, 'loss/train': 1.9935786724090576} 08/30/2021 17:17:42 - INFO - __main__ - Step 22821: {'lr': 0.0004759803034751244, 'samples': 4381632, 'steps': 22820, 'loss/train': 1.9499880075454712} 08/30/2021 17:17:44 - INFO - __main__ - Step 22822: {'lr': 0.0004759780337349347, 'samples': 4381824, 'steps': 22821, 'loss/train': 1.7148023843765259} 08/30/2021 17:17:44 - INFO - __main__ - Step 22823: {'lr': 0.0004759757638929227, 'samples': 4382016, 'steps': 22822, 'loss/train': 5.891917705535889} 08/30/2021 17:17:44 - INFO - __main__ - Step 22824: {'lr': 0.00047597349394908967, 'samples': 4382208, 'steps': 22823, 'loss/train': 1.981136441230774} 08/30/2021 17:17:45 - INFO - __main__ - Step 22825: {'lr': 0.0004759712239034364, 'samples': 4382400, 'steps': 22824, 'loss/train': 1.6211497783660889} 08/30/2021 17:17:45 - INFO - __main__ - Step 22826: {'lr': 0.0004759689537559639, 'samples': 4382592, 'steps': 22825, 'loss/train': 1.9349123239517212} 08/30/2021 17:17:47 - INFO - __main__ - Step 22827: {'lr': 0.0004759666835066734, 'samples': 4382784, 'steps': 22826, 'loss/train': 1.3486504554748535} 08/30/2021 17:17:47 - INFO - __main__ - Step 22828: {'lr': 0.00047596441315556575, 'samples': 4382976, 'steps': 22827, 'loss/train': 2.139190196990967} 08/30/2021 17:17:48 - INFO - __main__ - Step 22829: {'lr': 0.00047596214270264204, 'samples': 4383168, 'steps': 22828, 'loss/train': 1.8058923482894897} 08/30/2021 17:17:48 - INFO - __main__ - Step 22830: {'lr': 0.00047595987214790324, 'samples': 4383360, 'steps': 22829, 'loss/train': 1.976863980293274} 08/30/2021 17:17:48 - INFO - __main__ - Step 22831: {'lr': 0.0004759576014913505, 'samples': 4383552, 'steps': 22830, 'loss/train': 0.43058809638023376} 08/30/2021 17:17:49 - INFO - __main__ - Step 22832: {'lr': 0.0004759553307329846, 'samples': 4383744, 'steps': 22831, 'loss/train': 2.1321988105773926} 08/30/2021 17:17:50 - INFO - __main__ - Step 22833: {'lr': 0.0004759530598728068, 'samples': 4383936, 'steps': 22832, 'loss/train': 1.539613962173462} 08/30/2021 17:17:51 - INFO - __main__ - Step 22834: {'lr': 0.000475950788910818, 'samples': 4384128, 'steps': 22833, 'loss/train': 1.6206520795822144} 08/30/2021 17:17:51 - INFO - __main__ - Step 22835: {'lr': 0.0004759485178470193, 'samples': 4384320, 'steps': 22834, 'loss/train': 1.404211401939392} 08/30/2021 17:17:51 - INFO - __main__ - Step 22836: {'lr': 0.0004759462466814117, 'samples': 4384512, 'steps': 22835, 'loss/train': 1.3100310564041138} 08/30/2021 17:17:52 - INFO - __main__ - Step 22837: {'lr': 0.0004759439754139962, 'samples': 4384704, 'steps': 22836, 'loss/train': 1.5406081676483154} 08/30/2021 17:17:53 - INFO - __main__ - Step 22838: {'lr': 0.0004759417040447738, 'samples': 4384896, 'steps': 22837, 'loss/train': 1.3121213912963867} 08/30/2021 17:17:54 - INFO - __main__ - Step 22839: {'lr': 0.00047593943257374563, 'samples': 4385088, 'steps': 22838, 'loss/train': 1.3830492496490479} 08/30/2021 17:17:54 - INFO - __main__ - Step 22840: {'lr': 0.00047593716100091253, 'samples': 4385280, 'steps': 22839, 'loss/train': 1.1399668455123901} 08/30/2021 17:17:55 - INFO - __main__ - Step 22841: {'lr': 0.00047593488932627567, 'samples': 4385472, 'steps': 22840, 'loss/train': 0.2697351276874542} 08/30/2021 17:17:55 - INFO - __main__ - Step 22842: {'lr': 0.00047593261754983607, 'samples': 4385664, 'steps': 22841, 'loss/train': 0.36397024989128113} 08/30/2021 17:17:55 - INFO - __main__ - Step 22843: {'lr': 0.00047593034567159465, 'samples': 4385856, 'steps': 22842, 'loss/train': 1.7801777124404907} 08/30/2021 17:17:57 - INFO - __main__ - Step 22844: {'lr': 0.00047592807369155256, 'samples': 4386048, 'steps': 22843, 'loss/train': 1.2506732940673828} 08/30/2021 17:17:57 - INFO - __main__ - Step 22845: {'lr': 0.0004759258016097108, 'samples': 4386240, 'steps': 22844, 'loss/train': 2.4678118228912354} 08/30/2021 17:17:58 - INFO - __main__ - Step 22846: {'lr': 0.0004759235294260703, 'samples': 4386432, 'steps': 22845, 'loss/train': 1.5825022459030151} 08/30/2021 17:17:58 - INFO - __main__ - Step 22847: {'lr': 0.0004759212571406321, 'samples': 4386624, 'steps': 22846, 'loss/train': 0.9864962697029114} 08/30/2021 17:17:58 - INFO - __main__ - Step 22848: {'lr': 0.00047591898475339735, 'samples': 4386816, 'steps': 22847, 'loss/train': 1.507699966430664} 08/30/2021 17:18:00 - INFO - __main__ - Step 22849: {'lr': 0.00047591671226436695, 'samples': 4387008, 'steps': 22848, 'loss/train': 1.8230257034301758} 08/30/2021 17:18:01 - INFO - __main__ - Step 22850: {'lr': 0.00047591443967354196, 'samples': 4387200, 'steps': 22849, 'loss/train': 1.8146308660507202} 08/30/2021 17:18:01 - INFO - __main__ - Step 22851: {'lr': 0.00047591216698092344, 'samples': 4387392, 'steps': 22850, 'loss/train': 1.4738590717315674} 08/30/2021 17:18:02 - INFO - __main__ - Step 22852: {'lr': 0.00047590989418651243, 'samples': 4387584, 'steps': 22851, 'loss/train': 1.4997490644454956} 08/30/2021 17:18:02 - INFO - __main__ - Step 22853: {'lr': 0.00047590762129030986, 'samples': 4387776, 'steps': 22852, 'loss/train': 2.373847723007202} 08/30/2021 17:18:04 - INFO - __main__ - Step 22854: {'lr': 0.00047590534829231675, 'samples': 4387968, 'steps': 22853, 'loss/train': 1.1073637008666992} 08/30/2021 17:18:04 - INFO - __main__ - Step 22855: {'lr': 0.00047590307519253423, 'samples': 4388160, 'steps': 22854, 'loss/train': 1.5946327447891235} 08/30/2021 17:18:05 - INFO - __main__ - Step 22856: {'lr': 0.00047590080199096324, 'samples': 4388352, 'steps': 22855, 'loss/train': 1.5366663932800293} 08/30/2021 17:18:05 - INFO - __main__ - Step 22857: {'lr': 0.00047589852868760486, 'samples': 4388544, 'steps': 22856, 'loss/train': 1.5052390098571777} 08/30/2021 17:18:05 - INFO - __main__ - Step 22858: {'lr': 0.00047589625528246006, 'samples': 4388736, 'steps': 22857, 'loss/train': 1.7839717864990234} 08/30/2021 17:18:07 - INFO - __main__ - Step 22859: {'lr': 0.0004758939817755299, 'samples': 4388928, 'steps': 22858, 'loss/train': 0.096491739153862} 08/30/2021 17:18:07 - INFO - __main__ - Step 22860: {'lr': 0.0004758917081668155, 'samples': 4389120, 'steps': 22859, 'loss/train': 1.6763114929199219} 08/30/2021 17:18:08 - INFO - __main__ - Step 22861: {'lr': 0.00047588943445631767, 'samples': 4389312, 'steps': 22860, 'loss/train': 1.6641391515731812} 08/30/2021 17:18:08 - INFO - __main__ - Step 22862: {'lr': 0.0004758871606440376, 'samples': 4389504, 'steps': 22861, 'loss/train': 2.582131862640381} 08/30/2021 17:18:08 - INFO - __main__ - Step 22863: {'lr': 0.0004758848867299762, 'samples': 4389696, 'steps': 22862, 'loss/train': 1.5989612340927124} 08/30/2021 17:18:10 - INFO - __main__ - Step 22864: {'lr': 0.0004758826127141346, 'samples': 4389888, 'steps': 22863, 'loss/train': 1.7373689413070679} 08/30/2021 17:18:10 - INFO - __main__ - Step 22865: {'lr': 0.00047588033859651376, 'samples': 4390080, 'steps': 22864, 'loss/train': 1.8764578104019165} 08/30/2021 17:18:11 - INFO - __main__ - Step 22866: {'lr': 0.00047587806437711475, 'samples': 4390272, 'steps': 22865, 'loss/train': 2.0728724002838135} 08/30/2021 17:18:11 - INFO - __main__ - Step 22867: {'lr': 0.0004758757900559385, 'samples': 4390464, 'steps': 22866, 'loss/train': 1.1344109773635864} 08/30/2021 17:18:11 - INFO - __main__ - Step 22868: {'lr': 0.0004758735156329862, 'samples': 4390656, 'steps': 22867, 'loss/train': 1.8590474128723145} 08/30/2021 17:18:12 - INFO - __main__ - Step 22869: {'lr': 0.00047587124110825874, 'samples': 4390848, 'steps': 22868, 'loss/train': 1.8620820045471191} 08/30/2021 17:18:13 - INFO - __main__ - Step 22870: {'lr': 0.00047586896648175715, 'samples': 4391040, 'steps': 22869, 'loss/train': 1.315921425819397} 08/30/2021 17:18:14 - INFO - __main__ - Step 22871: {'lr': 0.00047586669175348254, 'samples': 4391232, 'steps': 22870, 'loss/train': 1.1827940940856934} 08/30/2021 17:18:14 - INFO - __main__ - Step 22872: {'lr': 0.0004758644169234359, 'samples': 4391424, 'steps': 22871, 'loss/train': 1.5243394374847412} 08/30/2021 17:18:14 - INFO - __main__ - Step 22873: {'lr': 0.00047586214199161814, 'samples': 4391616, 'steps': 22872, 'loss/train': 1.2829667329788208} 08/30/2021 17:18:15 - INFO - __main__ - Step 22874: {'lr': 0.00047585986695803046, 'samples': 4391808, 'steps': 22873, 'loss/train': 1.6022831201553345} 08/30/2021 17:18:16 - INFO - __main__ - Step 22875: {'lr': 0.0004758575918226738, 'samples': 4392000, 'steps': 22874, 'loss/train': 2.4123387336730957} 08/30/2021 17:18:17 - INFO - __main__ - Step 22876: {'lr': 0.0004758553165855492, 'samples': 4392192, 'steps': 22875, 'loss/train': 1.2562882900238037} 08/30/2021 17:18:17 - INFO - __main__ - Step 22877: {'lr': 0.00047585304124665766, 'samples': 4392384, 'steps': 22876, 'loss/train': 2.1552555561065674} 08/30/2021 17:18:17 - INFO - __main__ - Step 22878: {'lr': 0.0004758507658060003, 'samples': 4392576, 'steps': 22877, 'loss/train': 1.7031769752502441} 08/30/2021 17:18:18 - INFO - __main__ - Step 22879: {'lr': 0.00047584849026357796, 'samples': 4392768, 'steps': 22878, 'loss/train': 1.3326934576034546} 08/30/2021 17:18:19 - INFO - __main__ - Step 22880: {'lr': 0.0004758462146193918, 'samples': 4392960, 'steps': 22879, 'loss/train': 1.129577875137329} 08/30/2021 17:18:20 - INFO - __main__ - Step 22881: {'lr': 0.00047584393887344285, 'samples': 4393152, 'steps': 22880, 'loss/train': 1.4693756103515625} 08/30/2021 17:18:20 - INFO - __main__ - Step 22882: {'lr': 0.00047584166302573204, 'samples': 4393344, 'steps': 22881, 'loss/train': 1.6039628982543945} 08/30/2021 17:18:20 - INFO - __main__ - Step 22883: {'lr': 0.0004758393870762606, 'samples': 4393536, 'steps': 22882, 'loss/train': 1.9116535186767578} 08/30/2021 17:18:21 - INFO - __main__ - Step 22884: {'lr': 0.00047583711102502934, 'samples': 4393728, 'steps': 22883, 'loss/train': 1.4598807096481323} 08/30/2021 17:18:22 - INFO - __main__ - Step 22885: {'lr': 0.0004758348348720393, 'samples': 4393920, 'steps': 22884, 'loss/train': 1.155315637588501} 08/30/2021 17:18:23 - INFO - __main__ - Step 22886: {'lr': 0.00047583255861729167, 'samples': 4394112, 'steps': 22885, 'loss/train': 1.7323552370071411} 08/30/2021 17:18:23 - INFO - __main__ - Step 22887: {'lr': 0.00047583028226078734, 'samples': 4394304, 'steps': 22886, 'loss/train': 1.7252373695373535} 08/30/2021 17:18:23 - INFO - __main__ - Step 22888: {'lr': 0.0004758280058025274, 'samples': 4394496, 'steps': 22887, 'loss/train': 1.758551836013794} 08/30/2021 17:18:24 - INFO - __main__ - Step 22889: {'lr': 0.00047582572924251276, 'samples': 4394688, 'steps': 22888, 'loss/train': 2.229707956314087} 08/30/2021 17:18:25 - INFO - __main__ - Step 22890: {'lr': 0.00047582345258074453, 'samples': 4394880, 'steps': 22889, 'loss/train': 1.6733328104019165} 08/30/2021 17:18:26 - INFO - __main__ - Step 22891: {'lr': 0.0004758211758172238, 'samples': 4395072, 'steps': 22890, 'loss/train': 1.8109558820724487} 08/30/2021 17:18:26 - INFO - __main__ - Step 22892: {'lr': 0.00047581889895195154, 'samples': 4395264, 'steps': 22891, 'loss/train': 2.3365039825439453} 08/30/2021 17:18:26 - INFO - __main__ - Step 22893: {'lr': 0.00047581662198492873, 'samples': 4395456, 'steps': 22892, 'loss/train': 1.775614619255066} 08/30/2021 17:18:27 - INFO - __main__ - Step 22894: {'lr': 0.0004758143449161565, 'samples': 4395648, 'steps': 22893, 'loss/train': 1.4363470077514648} 08/30/2021 17:18:27 - INFO - __main__ - Step 22895: {'lr': 0.00047581206774563575, 'samples': 4395840, 'steps': 22894, 'loss/train': 1.4303739070892334} 08/30/2021 17:18:28 - INFO - __main__ - Step 22896: {'lr': 0.0004758097904733676, 'samples': 4396032, 'steps': 22895, 'loss/train': 1.9553728103637695} 08/30/2021 17:18:29 - INFO - __main__ - Step 22897: {'lr': 0.000475807513099353, 'samples': 4396224, 'steps': 22896, 'loss/train': 1.7079744338989258} 08/30/2021 17:18:29 - INFO - __main__ - Step 22898: {'lr': 0.000475805235623593, 'samples': 4396416, 'steps': 22897, 'loss/train': 2.0140016078948975} 08/30/2021 17:18:30 - INFO - __main__ - Step 22899: {'lr': 0.0004758029580460887, 'samples': 4396608, 'steps': 22898, 'loss/train': 1.715692400932312} 08/30/2021 17:18:30 - INFO - __main__ - Step 22900: {'lr': 0.0004758006803668411, 'samples': 4396800, 'steps': 22899, 'loss/train': 1.5090689659118652} 08/30/2021 17:18:32 - INFO - __main__ - Step 22901: {'lr': 0.0004757984025858511, 'samples': 4396992, 'steps': 22900, 'loss/train': 1.0468246936798096} 08/30/2021 17:18:33 - INFO - __main__ - Step 22902: {'lr': 0.0004757961247031199, 'samples': 4397184, 'steps': 22901, 'loss/train': 0.2992228865623474} 08/30/2021 17:18:33 - INFO - __main__ - Step 22903: {'lr': 0.00047579384671864845, 'samples': 4397376, 'steps': 22902, 'loss/train': 1.5388532876968384} 08/30/2021 17:18:34 - INFO - __main__ - Step 22904: {'lr': 0.0004757915686324377, 'samples': 4397568, 'steps': 22903, 'loss/train': 1.5558629035949707} 08/30/2021 17:18:34 - INFO - __main__ - Step 22905: {'lr': 0.00047578929044448883, 'samples': 4397760, 'steps': 22904, 'loss/train': 1.2496048212051392} 08/30/2021 17:18:36 - INFO - __main__ - Step 22906: {'lr': 0.0004757870121548028, 'samples': 4397952, 'steps': 22905, 'loss/train': 2.200721263885498} 08/30/2021 17:18:36 - INFO - __main__ - Step 22907: {'lr': 0.0004757847337633806, 'samples': 4398144, 'steps': 22906, 'loss/train': 1.0412330627441406} 08/30/2021 17:18:36 - INFO - __main__ - Step 22908: {'lr': 0.0004757824552702232, 'samples': 4398336, 'steps': 22907, 'loss/train': 0.11058652400970459} 08/30/2021 17:18:37 - INFO - __main__ - Step 22909: {'lr': 0.0004757801766753318, 'samples': 4398528, 'steps': 22908, 'loss/train': 1.9616198539733887} 08/30/2021 17:18:37 - INFO - __main__ - Step 22910: {'lr': 0.00047577789797870743, 'samples': 4398720, 'steps': 22909, 'loss/train': 1.3215875625610352} 08/30/2021 17:18:37 - INFO - __main__ - Step 22911: {'lr': 0.0004757756191803508, 'samples': 4398912, 'steps': 22910, 'loss/train': 1.7832579612731934} 08/30/2021 17:18:39 - INFO - __main__ - Step 22912: {'lr': 0.0004757733402802633, 'samples': 4399104, 'steps': 22911, 'loss/train': 1.880214810371399} 08/30/2021 17:18:40 - INFO - __main__ - Step 22913: {'lr': 0.0004757710612784458, 'samples': 4399296, 'steps': 22912, 'loss/train': 0.1897026151418686} 08/30/2021 17:18:40 - INFO - __main__ - Step 22914: {'lr': 0.0004757687821748994, 'samples': 4399488, 'steps': 22913, 'loss/train': 1.9128143787384033} 08/30/2021 17:18:40 - INFO - __main__ - Step 22915: {'lr': 0.00047576650296962496, 'samples': 4399680, 'steps': 22914, 'loss/train': 1.9582329988479614} 08/30/2021 17:18:41 - INFO - __main__ - Step 22916: {'lr': 0.0004757642236626237, 'samples': 4399872, 'steps': 22915, 'loss/train': 1.375234842300415} 08/30/2021 17:18:42 - INFO - __main__ - Step 22917: {'lr': 0.00047576194425389654, 'samples': 4400064, 'steps': 22916, 'loss/train': 1.1546584367752075} 08/30/2021 17:18:43 - INFO - __main__ - Step 22918: {'lr': 0.00047575966474344445, 'samples': 4400256, 'steps': 22917, 'loss/train': 1.2885922193527222} 08/30/2021 17:18:43 - INFO - __main__ - Step 22919: {'lr': 0.00047575738513126867, 'samples': 4400448, 'steps': 22918, 'loss/train': 1.3296352624893188} 08/30/2021 17:18:43 - INFO - __main__ - Step 22920: {'lr': 0.00047575510541737, 'samples': 4400640, 'steps': 22919, 'loss/train': 1.962688684463501} 08/30/2021 17:18:44 - INFO - __main__ - Step 22921: {'lr': 0.0004757528256017496, 'samples': 4400832, 'steps': 22920, 'loss/train': 1.3125160932540894} 08/30/2021 17:18:45 - INFO - __main__ - Step 22922: {'lr': 0.00047575054568440846, 'samples': 4401024, 'steps': 22921, 'loss/train': 3.0557782649993896} 08/30/2021 17:18:46 - INFO - __main__ - Step 22923: {'lr': 0.00047574826566534764, 'samples': 4401216, 'steps': 22922, 'loss/train': 1.4462623596191406} 08/30/2021 17:18:46 - INFO - __main__ - Step 22924: {'lr': 0.0004757459855445681, 'samples': 4401408, 'steps': 22923, 'loss/train': 1.3010894060134888} 08/30/2021 17:18:46 - INFO - __main__ - Step 22925: {'lr': 0.0004757437053220709, 'samples': 4401600, 'steps': 22924, 'loss/train': 1.4071928262710571} 08/30/2021 17:18:47 - INFO - __main__ - Step 22926: {'lr': 0.0004757414249978571, 'samples': 4401792, 'steps': 22925, 'loss/train': 1.6209383010864258} 08/30/2021 17:18:47 - INFO - __main__ - Step 22927: {'lr': 0.0004757391445719277, 'samples': 4401984, 'steps': 22926, 'loss/train': 1.5751428604125977} 08/30/2021 17:18:49 - INFO - __main__ - Step 22928: {'lr': 0.00047573686404428365, 'samples': 4402176, 'steps': 22927, 'loss/train': 1.1744216680526733} 08/30/2021 17:18:49 - INFO - __main__ - Step 22929: {'lr': 0.0004757345834149261, 'samples': 4402368, 'steps': 22928, 'loss/train': 1.4119768142700195} 08/30/2021 17:18:50 - INFO - __main__ - Step 22930: {'lr': 0.00047573230268385604, 'samples': 4402560, 'steps': 22929, 'loss/train': 1.8124980926513672} 08/30/2021 17:18:50 - INFO - __main__ - Step 22931: {'lr': 0.0004757300218510745, 'samples': 4402752, 'steps': 22930, 'loss/train': 1.4101451635360718} 08/30/2021 17:18:50 - INFO - __main__ - Step 22932: {'lr': 0.00047572774091658243, 'samples': 4402944, 'steps': 22931, 'loss/train': 1.6242215633392334} 08/30/2021 17:18:52 - INFO - __main__ - Step 22933: {'lr': 0.000475725459880381, 'samples': 4403136, 'steps': 22932, 'loss/train': 1.5872819423675537} 08/30/2021 17:18:52 - INFO - __main__ - Step 22934: {'lr': 0.00047572317874247107, 'samples': 4403328, 'steps': 22933, 'loss/train': 1.8957769870758057} 08/30/2021 17:18:53 - INFO - __main__ - Step 22935: {'lr': 0.00047572089750285383, 'samples': 4403520, 'steps': 22934, 'loss/train': 1.7136831283569336} 08/30/2021 17:18:53 - INFO - __main__ - Step 22936: {'lr': 0.00047571861616153025, 'samples': 4403712, 'steps': 22935, 'loss/train': 1.3539509773254395} 08/30/2021 17:18:53 - INFO - __main__ - Step 22937: {'lr': 0.0004757163347185013, 'samples': 4403904, 'steps': 22936, 'loss/train': 1.2230592966079712} 08/30/2021 17:18:55 - INFO - __main__ - Step 22938: {'lr': 0.00047571405317376803, 'samples': 4404096, 'steps': 22937, 'loss/train': 2.0420732498168945} 08/30/2021 17:18:55 - INFO - __main__ - Step 22939: {'lr': 0.0004757117715273316, 'samples': 4404288, 'steps': 22938, 'loss/train': 1.3886237144470215} 08/30/2021 17:18:56 - INFO - __main__ - Step 22940: {'lr': 0.00047570948977919284, 'samples': 4404480, 'steps': 22939, 'loss/train': 1.8188010454177856} 08/30/2021 17:18:56 - INFO - __main__ - Step 22941: {'lr': 0.00047570720792935284, 'samples': 4404672, 'steps': 22940, 'loss/train': 1.5992809534072876} 08/30/2021 17:18:56 - INFO - __main__ - Step 22942: {'lr': 0.00047570492597781274, 'samples': 4404864, 'steps': 22941, 'loss/train': 1.5576814413070679} 08/30/2021 17:18:58 - INFO - __main__ - Step 22943: {'lr': 0.0004757026439245735, 'samples': 4405056, 'steps': 22942, 'loss/train': 1.3755614757537842} 08/30/2021 17:18:59 - INFO - __main__ - Step 22944: {'lr': 0.0004757003617696361, 'samples': 4405248, 'steps': 22943, 'loss/train': 1.7030465602874756} 08/30/2021 17:18:59 - INFO - __main__ - Step 22945: {'lr': 0.0004756980795130015, 'samples': 4405440, 'steps': 22944, 'loss/train': 1.8665271997451782} 08/30/2021 17:18:59 - INFO - __main__ - Step 22946: {'lr': 0.00047569579715467093, 'samples': 4405632, 'steps': 22945, 'loss/train': 1.5804766416549683} 08/30/2021 17:19:00 - INFO - __main__ - Step 22947: {'lr': 0.00047569351469464526, 'samples': 4405824, 'steps': 22946, 'loss/train': 1.5600886344909668} 08/30/2021 17:19:00 - INFO - __main__ - Step 22948: {'lr': 0.0004756912321329256, 'samples': 4406016, 'steps': 22947, 'loss/train': 0.07514391839504242} 08/30/2021 17:19:01 - INFO - __main__ - Step 22949: {'lr': 0.000475688949469513, 'samples': 4406208, 'steps': 22948, 'loss/train': 1.5531437397003174} 08/30/2021 17:19:02 - INFO - __main__ - Step 22950: {'lr': 0.0004756866667044084, 'samples': 4406400, 'steps': 22949, 'loss/train': 1.7941099405288696} 08/30/2021 17:19:02 - INFO - __main__ - Step 22951: {'lr': 0.0004756843838376128, 'samples': 4406592, 'steps': 22950, 'loss/train': 0.19485221803188324} 08/30/2021 17:19:03 - INFO - __main__ - Step 22952: {'lr': 0.0004756821008691274, 'samples': 4406784, 'steps': 22951, 'loss/train': 1.46951162815094} 08/30/2021 17:19:03 - INFO - __main__ - Step 22953: {'lr': 0.0004756798177989531, 'samples': 4406976, 'steps': 22952, 'loss/train': 1.5732104778289795} 08/30/2021 17:19:05 - INFO - __main__ - Step 22954: {'lr': 0.00047567753462709095, 'samples': 4407168, 'steps': 22953, 'loss/train': 1.7873196601867676} 08/30/2021 17:19:06 - INFO - __main__ - Step 22955: {'lr': 0.00047567525135354193, 'samples': 4407360, 'steps': 22954, 'loss/train': 1.5982166528701782} 08/30/2021 17:19:06 - INFO - __main__ - Step 22956: {'lr': 0.00047567296797830727, 'samples': 4407552, 'steps': 22955, 'loss/train': 1.9292433261871338} 08/30/2021 17:19:06 - INFO - __main__ - Step 22957: {'lr': 0.00047567068450138773, 'samples': 4407744, 'steps': 22956, 'loss/train': 1.453284740447998} 08/30/2021 17:19:07 - INFO - __main__ - Step 22958: {'lr': 0.0004756684009227845, 'samples': 4407936, 'steps': 22957, 'loss/train': 1.9705432653427124} 08/30/2021 17:19:08 - INFO - __main__ - Step 22959: {'lr': 0.0004756661172424986, 'samples': 4408128, 'steps': 22958, 'loss/train': 1.847352385520935} 08/30/2021 17:19:08 - INFO - __main__ - Step 22960: {'lr': 0.000475663833460531, 'samples': 4408320, 'steps': 22959, 'loss/train': 1.7003968954086304} 08/30/2021 17:19:09 - INFO - __main__ - Step 22961: {'lr': 0.00047566154957688275, 'samples': 4408512, 'steps': 22960, 'loss/train': 0.9619525671005249} 08/30/2021 17:19:09 - INFO - __main__ - Step 22962: {'lr': 0.0004756592655915549, 'samples': 4408704, 'steps': 22961, 'loss/train': 1.66960871219635} 08/30/2021 17:19:10 - INFO - __main__ - Step 22963: {'lr': 0.00047565698150454845, 'samples': 4408896, 'steps': 22962, 'loss/train': 1.9270974397659302} 08/30/2021 17:19:11 - INFO - __main__ - Step 22964: {'lr': 0.0004756546973158644, 'samples': 4409088, 'steps': 22963, 'loss/train': 1.7784135341644287} 08/30/2021 17:19:12 - INFO - __main__ - Step 22965: {'lr': 0.00047565241302550395, 'samples': 4409280, 'steps': 22964, 'loss/train': 1.859703540802002} 08/30/2021 17:19:12 - INFO - __main__ - Step 22966: {'lr': 0.0004756501286334679, 'samples': 4409472, 'steps': 22965, 'loss/train': 1.8214054107666016} 08/30/2021 17:19:13 - INFO - __main__ - Step 22967: {'lr': 0.0004756478441397575, 'samples': 4409664, 'steps': 22966, 'loss/train': 0.06283416599035263} 08/30/2021 17:19:13 - INFO - __main__ - Step 22968: {'lr': 0.0004756455595443735, 'samples': 4409856, 'steps': 22967, 'loss/train': 1.3767576217651367} 08/30/2021 17:19:13 - INFO - __main__ - Step 22969: {'lr': 0.00047564327484731725, 'samples': 4410048, 'steps': 22968, 'loss/train': 2.7831339836120605} 08/30/2021 17:19:15 - INFO - __main__ - Step 22970: {'lr': 0.0004756409900485895, 'samples': 4410240, 'steps': 22969, 'loss/train': 2.001856803894043} 08/30/2021 17:19:15 - INFO - __main__ - Step 22971: {'lr': 0.00047563870514819154, 'samples': 4410432, 'steps': 22970, 'loss/train': 1.5054091215133667} 08/30/2021 17:19:16 - INFO - __main__ - Step 22972: {'lr': 0.0004756364201461241, 'samples': 4410624, 'steps': 22971, 'loss/train': 2.18689227104187} 08/30/2021 17:19:16 - INFO - __main__ - Step 22973: {'lr': 0.00047563413504238847, 'samples': 4410816, 'steps': 22972, 'loss/train': 1.7257452011108398} 08/30/2021 17:19:16 - INFO - __main__ - Step 22974: {'lr': 0.0004756318498369855, 'samples': 4411008, 'steps': 22973, 'loss/train': 1.1092854738235474} 08/30/2021 17:19:18 - INFO - __main__ - Step 22975: {'lr': 0.0004756295645299164, 'samples': 4411200, 'steps': 22974, 'loss/train': 1.6956833600997925} 08/30/2021 17:19:18 - INFO - __main__ - Step 22976: {'lr': 0.00047562727912118206, 'samples': 4411392, 'steps': 22975, 'loss/train': 2.3967127799987793} 08/30/2021 17:19:19 - INFO - __main__ - Step 22977: {'lr': 0.00047562499361078356, 'samples': 4411584, 'steps': 22976, 'loss/train': 1.6982682943344116} 08/30/2021 17:19:19 - INFO - __main__ - Step 22978: {'lr': 0.00047562270799872186, 'samples': 4411776, 'steps': 22977, 'loss/train': 1.9491908550262451} 08/30/2021 17:19:19 - INFO - __main__ - Step 22979: {'lr': 0.00047562042228499815, 'samples': 4411968, 'steps': 22978, 'loss/train': 1.7589589357376099} 08/30/2021 17:19:21 - INFO - __main__ - Step 22980: {'lr': 0.00047561813646961325, 'samples': 4412160, 'steps': 22979, 'loss/train': 1.4948928356170654} 08/30/2021 17:19:21 - INFO - __main__ - Step 22981: {'lr': 0.0004756158505525684, 'samples': 4412352, 'steps': 22980, 'loss/train': 1.483370065689087} 08/30/2021 17:19:22 - INFO - __main__ - Step 22982: {'lr': 0.0004756135645338644, 'samples': 4412544, 'steps': 22981, 'loss/train': 1.978050708770752} 08/30/2021 17:19:22 - INFO - __main__ - Step 22983: {'lr': 0.00047561127841350256, 'samples': 4412736, 'steps': 22982, 'loss/train': 1.9036160707473755} 08/30/2021 17:19:22 - INFO - __main__ - Step 22984: {'lr': 0.0004756089921914837, 'samples': 4412928, 'steps': 22983, 'loss/train': 0.5567795038223267} 08/30/2021 17:19:23 - INFO - __main__ - Step 22985: {'lr': 0.00047560670586780886, 'samples': 4413120, 'steps': 22984, 'loss/train': 1.0332645177841187} 08/30/2021 17:19:24 - INFO - __main__ - Step 22986: {'lr': 0.0004756044194424792, 'samples': 4413312, 'steps': 22985, 'loss/train': 1.9853816032409668} 08/30/2021 17:19:25 - INFO - __main__ - Step 22987: {'lr': 0.0004756021329154956, 'samples': 4413504, 'steps': 22986, 'loss/train': 1.6890605688095093} 08/30/2021 17:19:25 - INFO - __main__ - Step 22988: {'lr': 0.0004755998462868592, 'samples': 4413696, 'steps': 22987, 'loss/train': 1.4336907863616943} 08/30/2021 17:19:25 - INFO - __main__ - Step 22989: {'lr': 0.00047559755955657097, 'samples': 4413888, 'steps': 22988, 'loss/train': 1.275169849395752} 08/30/2021 17:19:26 - INFO - __main__ - Step 22990: {'lr': 0.000475595272724632, 'samples': 4414080, 'steps': 22989, 'loss/train': 2.0036916732788086} 08/30/2021 17:19:27 - INFO - __main__ - Step 22991: {'lr': 0.00047559298579104325, 'samples': 4414272, 'steps': 22990, 'loss/train': 1.9356542825698853} 08/30/2021 17:19:27 - INFO - __main__ - Step 22992: {'lr': 0.00047559069875580573, 'samples': 4414464, 'steps': 22991, 'loss/train': 2.0371615886688232} 08/30/2021 17:19:28 - INFO - __main__ - Step 22993: {'lr': 0.00047558841161892063, 'samples': 4414656, 'steps': 22992, 'loss/train': 1.7100064754486084} 08/30/2021 17:19:28 - INFO - __main__ - Step 22994: {'lr': 0.00047558612438038887, 'samples': 4414848, 'steps': 22993, 'loss/train': 1.5306779146194458} 08/30/2021 17:19:29 - INFO - __main__ - Step 22995: {'lr': 0.00047558383704021136, 'samples': 4415040, 'steps': 22994, 'loss/train': 1.7773598432540894} 08/30/2021 17:19:30 - INFO - __main__ - Step 22996: {'lr': 0.00047558154959838935, 'samples': 4415232, 'steps': 22995, 'loss/train': 2.1924450397491455} 08/30/2021 17:19:31 - INFO - __main__ - Step 22997: {'lr': 0.0004755792620549237, 'samples': 4415424, 'steps': 22996, 'loss/train': 1.473719835281372} 08/30/2021 17:19:31 - INFO - __main__ - Step 22998: {'lr': 0.0004755769744098156, 'samples': 4415616, 'steps': 22997, 'loss/train': 1.3908065557479858} 08/30/2021 17:19:31 - INFO - __main__ - Step 22999: {'lr': 0.00047557468666306596, 'samples': 4415808, 'steps': 22998, 'loss/train': 1.2253528833389282} 08/30/2021 17:19:32 - INFO - __main__ - Step 23000: {'lr': 0.00047557239881467584, 'samples': 4416000, 'steps': 22999, 'loss/train': 1.6886320114135742} 08/30/2021 17:19:32 - INFO - __main__ - Step 23001: {'lr': 0.0004755701108646463, 'samples': 4416192, 'steps': 23000, 'loss/train': 5.877809524536133} 08/30/2021 17:19:33 - INFO - __main__ - Step 23002: {'lr': 0.0004755678228129784, 'samples': 4416384, 'steps': 23001, 'loss/train': 1.6232523918151855} 08/30/2021 17:19:34 - INFO - __main__ - Step 23003: {'lr': 0.000475565534659673, 'samples': 4416576, 'steps': 23002, 'loss/train': 0.8050466179847717} 08/30/2021 17:19:34 - INFO - __main__ - Step 23004: {'lr': 0.00047556324640473134, 'samples': 4416768, 'steps': 23003, 'loss/train': 1.570481300354004} 08/30/2021 17:19:35 - INFO - __main__ - Step 23005: {'lr': 0.0004755609580481543, 'samples': 4416960, 'steps': 23004, 'loss/train': 1.5985801219940186} 08/30/2021 17:19:35 - INFO - __main__ - Step 23006: {'lr': 0.00047555866958994296, 'samples': 4417152, 'steps': 23005, 'loss/train': 1.6451317071914673} 08/30/2021 17:19:36 - INFO - __main__ - Step 23007: {'lr': 0.00047555638103009845, 'samples': 4417344, 'steps': 23006, 'loss/train': 1.5482604503631592} 08/30/2021 17:19:37 - INFO - __main__ - Step 23008: {'lr': 0.0004755540923686217, 'samples': 4417536, 'steps': 23007, 'loss/train': 2.0507125854492188} 08/30/2021 17:19:37 - INFO - __main__ - Step 23009: {'lr': 0.0004755518036055137, 'samples': 4417728, 'steps': 23008, 'loss/train': 1.5620150566101074} 08/30/2021 17:19:38 - INFO - __main__ - Step 23010: {'lr': 0.0004755495147407756, 'samples': 4417920, 'steps': 23009, 'loss/train': 1.3272922039031982} 08/30/2021 17:19:38 - INFO - __main__ - Step 23011: {'lr': 0.00047554722577440833, 'samples': 4418112, 'steps': 23010, 'loss/train': 1.2647225856781006} 08/30/2021 17:19:40 - INFO - __main__ - Step 23012: {'lr': 0.00047554493670641296, 'samples': 4418304, 'steps': 23011, 'loss/train': 1.5204968452453613} 08/30/2021 17:19:40 - INFO - __main__ - Step 23013: {'lr': 0.0004755426475367905, 'samples': 4418496, 'steps': 23012, 'loss/train': 2.0286548137664795} 08/30/2021 17:19:41 - INFO - __main__ - Step 23014: {'lr': 0.00047554035826554206, 'samples': 4418688, 'steps': 23013, 'loss/train': 1.5546232461929321} 08/30/2021 17:19:41 - INFO - __main__ - Step 23015: {'lr': 0.0004755380688926686, 'samples': 4418880, 'steps': 23014, 'loss/train': 1.2495543956756592} 08/30/2021 17:19:42 - INFO - __main__ - Step 23016: {'lr': 0.00047553577941817114, 'samples': 4419072, 'steps': 23015, 'loss/train': 1.704040765762329} 08/30/2021 17:19:43 - INFO - __main__ - Step 23017: {'lr': 0.0004755334898420507, 'samples': 4419264, 'steps': 23016, 'loss/train': 1.5796982049942017} 08/30/2021 17:19:43 - INFO - __main__ - Step 23018: {'lr': 0.00047553120016430837, 'samples': 4419456, 'steps': 23017, 'loss/train': 2.387077808380127} 08/30/2021 17:19:44 - INFO - __main__ - Step 23019: {'lr': 0.0004755289103849453, 'samples': 4419648, 'steps': 23018, 'loss/train': 1.6557508707046509} 08/30/2021 17:19:44 - INFO - __main__ - Step 23020: {'lr': 0.0004755266205039622, 'samples': 4419840, 'steps': 23019, 'loss/train': 1.4642345905303955} 08/30/2021 17:19:44 - INFO - __main__ - Step 23021: {'lr': 0.00047552433052136034, 'samples': 4420032, 'steps': 23020, 'loss/train': 1.5368373394012451} 08/30/2021 17:19:46 - INFO - __main__ - Step 23022: {'lr': 0.00047552204043714076, 'samples': 4420224, 'steps': 23021, 'loss/train': 1.7309247255325317} 08/30/2021 17:19:46 - INFO - __main__ - Step 23023: {'lr': 0.0004755197502513043, 'samples': 4420416, 'steps': 23022, 'loss/train': 1.6309560537338257} 08/30/2021 17:19:47 - INFO - __main__ - Step 23024: {'lr': 0.00047551745996385233, 'samples': 4420608, 'steps': 23023, 'loss/train': 1.8825452327728271} 08/30/2021 17:19:47 - INFO - __main__ - Step 23025: {'lr': 0.00047551516957478545, 'samples': 4420800, 'steps': 23024, 'loss/train': 1.3205102682113647} 08/30/2021 17:19:47 - INFO - __main__ - Step 23026: {'lr': 0.0004755128790841051, 'samples': 4420992, 'steps': 23025, 'loss/train': 1.8629093170166016} 08/30/2021 17:19:48 - INFO - __main__ - Step 23027: {'lr': 0.000475510588491812, 'samples': 4421184, 'steps': 23026, 'loss/train': 1.561285138130188} 08/30/2021 17:19:49 - INFO - __main__ - Step 23028: {'lr': 0.00047550829779790735, 'samples': 4421376, 'steps': 23027, 'loss/train': 1.763322114944458} 08/30/2021 17:19:50 - INFO - __main__ - Step 23029: {'lr': 0.0004755060070023921, 'samples': 4421568, 'steps': 23028, 'loss/train': 1.6220554113388062} 08/30/2021 17:19:50 - INFO - __main__ - Step 23030: {'lr': 0.0004755037161052674, 'samples': 4421760, 'steps': 23029, 'loss/train': 1.757729172706604} 08/30/2021 17:19:50 - INFO - __main__ - Step 23031: {'lr': 0.00047550142510653415, 'samples': 4421952, 'steps': 23030, 'loss/train': 0.825249969959259} 08/30/2021 17:19:51 - INFO - __main__ - Step 23032: {'lr': 0.0004754991340061935, 'samples': 4422144, 'steps': 23031, 'loss/train': 1.0758825540542603} 08/30/2021 17:19:53 - INFO - __main__ - Step 23033: {'lr': 0.0004754968428042463, 'samples': 4422336, 'steps': 23032, 'loss/train': 1.6299127340316772} 08/30/2021 17:19:53 - INFO - __main__ - Step 23034: {'lr': 0.0004754945515006938, 'samples': 4422528, 'steps': 23033, 'loss/train': 1.7288877964019775} 08/30/2021 17:19:54 - INFO - __main__ - Step 23035: {'lr': 0.0004754922600955369, 'samples': 4422720, 'steps': 23034, 'loss/train': 1.4009493589401245} 08/30/2021 17:19:54 - INFO - __main__ - Step 23036: {'lr': 0.0004754899685887767, 'samples': 4422912, 'steps': 23035, 'loss/train': 1.2913403511047363} 08/30/2021 17:19:54 - INFO - __main__ - Step 23037: {'lr': 0.0004754876769804142, 'samples': 4423104, 'steps': 23036, 'loss/train': 1.4569898843765259} 08/30/2021 17:19:55 - INFO - __main__ - Step 23038: {'lr': 0.00047548538527045035, 'samples': 4423296, 'steps': 23037, 'loss/train': 0.17948797345161438} 08/30/2021 17:19:57 - INFO - __main__ - Step 23039: {'lr': 0.00047548309345888637, 'samples': 4423488, 'steps': 23038, 'loss/train': 0.34549573063850403} 08/30/2021 17:19:57 - INFO - __main__ - Step 23040: {'lr': 0.00047548080154572315, 'samples': 4423680, 'steps': 23039, 'loss/train': 1.16763436794281} 08/30/2021 17:19:58 - INFO - __main__ - Step 23041: {'lr': 0.00047547850953096174, 'samples': 4423872, 'steps': 23040, 'loss/train': 1.441243052482605} 08/30/2021 17:19:58 - INFO - __main__ - Step 23042: {'lr': 0.0004754762174146032, 'samples': 4424064, 'steps': 23041, 'loss/train': 1.9190456867218018} 08/30/2021 17:19:58 - INFO - __main__ - Step 23043: {'lr': 0.00047547392519664853, 'samples': 4424256, 'steps': 23042, 'loss/train': 2.913517713546753} 08/30/2021 17:19:59 - INFO - __main__ - Step 23044: {'lr': 0.0004754716328770988, 'samples': 4424448, 'steps': 23043, 'loss/train': 2.9844703674316406} 08/30/2021 17:20:00 - INFO - __main__ - Step 23045: {'lr': 0.00047546934045595516, 'samples': 4424640, 'steps': 23044, 'loss/train': 1.363848090171814} 08/30/2021 17:20:01 - INFO - __main__ - Step 23046: {'lr': 0.00047546704793321835, 'samples': 4424832, 'steps': 23045, 'loss/train': 1.8653638362884521} 08/30/2021 17:20:01 - INFO - __main__ - Step 23047: {'lr': 0.0004754647553088896, 'samples': 4425024, 'steps': 23046, 'loss/train': 1.5340021848678589} 08/30/2021 17:20:02 - INFO - __main__ - Step 23048: {'lr': 0.00047546246258297, 'samples': 4425216, 'steps': 23047, 'loss/train': 1.547456979751587} 08/30/2021 17:20:02 - INFO - __main__ - Step 23049: {'lr': 0.00047546016975546037, 'samples': 4425408, 'steps': 23048, 'loss/train': 0.10871273279190063} 08/30/2021 17:20:03 - INFO - __main__ - Step 23050: {'lr': 0.00047545787682636194, 'samples': 4425600, 'steps': 23049, 'loss/train': 1.824331283569336} 08/30/2021 17:20:04 - INFO - __main__ - Step 23051: {'lr': 0.00047545558379567565, 'samples': 4425792, 'steps': 23050, 'loss/train': 1.2129907608032227} 08/30/2021 17:20:04 - INFO - __main__ - Step 23052: {'lr': 0.00047545329066340256, 'samples': 4425984, 'steps': 23051, 'loss/train': 1.473488688468933} 08/30/2021 17:20:05 - INFO - __main__ - Step 23053: {'lr': 0.00047545099742954367, 'samples': 4426176, 'steps': 23052, 'loss/train': 1.6842970848083496} 08/30/2021 17:20:05 - INFO - __main__ - Step 23054: {'lr': 0.0004754487040941001, 'samples': 4426368, 'steps': 23053, 'loss/train': 1.7076953649520874} 08/30/2021 17:20:05 - INFO - __main__ - Step 23055: {'lr': 0.0004754464106570727, 'samples': 4426560, 'steps': 23054, 'loss/train': 1.6193013191223145} 08/30/2021 17:20:07 - INFO - __main__ - Step 23056: {'lr': 0.00047544411711846277, 'samples': 4426752, 'steps': 23055, 'loss/train': 1.618159294128418} 08/30/2021 17:20:07 - INFO - __main__ - Step 23057: {'lr': 0.00047544182347827114, 'samples': 4426944, 'steps': 23056, 'loss/train': 1.6489686965942383} 08/30/2021 17:20:08 - INFO - __main__ - Step 23058: {'lr': 0.0004754395297364989, 'samples': 4427136, 'steps': 23057, 'loss/train': 1.1632510423660278} 08/30/2021 17:20:08 - INFO - __main__ - Step 23059: {'lr': 0.0004754372358931471, 'samples': 4427328, 'steps': 23058, 'loss/train': 1.6978973150253296} 08/30/2021 17:20:08 - INFO - __main__ - Step 23060: {'lr': 0.00047543494194821675, 'samples': 4427520, 'steps': 23059, 'loss/train': 2.407747983932495} 08/30/2021 17:20:10 - INFO - __main__ - Step 23061: {'lr': 0.00047543264790170887, 'samples': 4427712, 'steps': 23060, 'loss/train': 1.26861572265625} 08/30/2021 17:20:10 - INFO - __main__ - Step 23062: {'lr': 0.00047543035375362453, 'samples': 4427904, 'steps': 23061, 'loss/train': 1.7939304113388062} 08/30/2021 17:20:11 - INFO - __main__ - Step 23063: {'lr': 0.00047542805950396476, 'samples': 4428096, 'steps': 23062, 'loss/train': 1.8011139631271362} 08/30/2021 17:20:11 - INFO - __main__ - Step 23064: {'lr': 0.00047542576515273064, 'samples': 4428288, 'steps': 23063, 'loss/train': 1.9798765182495117} 08/30/2021 17:20:11 - INFO - __main__ - Step 23065: {'lr': 0.0004754234706999231, 'samples': 4428480, 'steps': 23064, 'loss/train': 2.1380014419555664} 08/30/2021 17:20:13 - INFO - __main__ - Step 23066: {'lr': 0.0004754211761455432, 'samples': 4428672, 'steps': 23065, 'loss/train': 1.8568460941314697} 08/30/2021 17:20:14 - INFO - __main__ - Step 23067: {'lr': 0.000475418881489592, 'samples': 4428864, 'steps': 23066, 'loss/train': 2.2325549125671387} 08/30/2021 17:20:14 - INFO - __main__ - Step 23068: {'lr': 0.0004754165867320706, 'samples': 4429056, 'steps': 23067, 'loss/train': 1.2719651460647583} 08/30/2021 17:20:14 - INFO - __main__ - Step 23069: {'lr': 0.00047541429187297984, 'samples': 4429248, 'steps': 23068, 'loss/train': 0.6197928190231323} 08/30/2021 17:20:15 - INFO - __main__ - Step 23070: {'lr': 0.00047541199691232094, 'samples': 4429440, 'steps': 23069, 'loss/train': 1.4448164701461792} 08/30/2021 17:20:16 - INFO - __main__ - Step 23071: {'lr': 0.0004754097018500949, 'samples': 4429632, 'steps': 23070, 'loss/train': 1.665648102760315} 08/30/2021 17:20:17 - INFO - __main__ - Step 23072: {'lr': 0.0004754074066863027, 'samples': 4429824, 'steps': 23071, 'loss/train': 1.2831231355667114} 08/30/2021 17:20:17 - INFO - __main__ - Step 23073: {'lr': 0.0004754051114209454, 'samples': 4430016, 'steps': 23072, 'loss/train': 2.770606756210327} 08/30/2021 17:20:18 - INFO - __main__ - Step 23074: {'lr': 0.0004754028160540241, 'samples': 4430208, 'steps': 23073, 'loss/train': 1.4709585905075073} 08/30/2021 17:20:18 - INFO - __main__ - Step 23075: {'lr': 0.0004754005205855397, 'samples': 4430400, 'steps': 23074, 'loss/train': 1.0107523202896118} 08/30/2021 17:20:18 - INFO - __main__ - Step 23076: {'lr': 0.0004753982250154933, 'samples': 4430592, 'steps': 23075, 'loss/train': 1.0506287813186646} 08/30/2021 17:20:20 - INFO - __main__ - Step 23077: {'lr': 0.00047539592934388596, 'samples': 4430784, 'steps': 23076, 'loss/train': 1.9369217157363892} 08/30/2021 17:20:20 - INFO - __main__ - Step 23078: {'lr': 0.0004753936335707187, 'samples': 4430976, 'steps': 23077, 'loss/train': 1.4263718128204346} 08/30/2021 17:20:21 - INFO - __main__ - Step 23079: {'lr': 0.0004753913376959925, 'samples': 4431168, 'steps': 23078, 'loss/train': 1.7650058269500732} 08/30/2021 17:20:21 - INFO - __main__ - Step 23080: {'lr': 0.00047538904171970847, 'samples': 4431360, 'steps': 23079, 'loss/train': 0.5631402730941772} 08/30/2021 17:20:21 - INFO - __main__ - Step 23081: {'lr': 0.0004753867456418677, 'samples': 4431552, 'steps': 23080, 'loss/train': 1.8370333909988403} 08/30/2021 17:20:23 - INFO - __main__ - Step 23082: {'lr': 0.000475384449462471, 'samples': 4431744, 'steps': 23081, 'loss/train': 1.7785964012145996} 08/30/2021 17:20:24 - INFO - __main__ - Step 23083: {'lr': 0.00047538215318151955, 'samples': 4431936, 'steps': 23082, 'loss/train': 1.7811259031295776} 08/30/2021 17:20:24 - INFO - __main__ - Step 23084: {'lr': 0.0004753798567990145, 'samples': 4432128, 'steps': 23083, 'loss/train': 0.8969607949256897} 08/30/2021 17:20:24 - INFO - __main__ - Step 23085: {'lr': 0.00047537756031495673, 'samples': 4432320, 'steps': 23084, 'loss/train': 1.802507758140564} 08/30/2021 17:20:25 - INFO - __main__ - Step 23086: {'lr': 0.0004753752637293473, 'samples': 4432512, 'steps': 23085, 'loss/train': 1.6796890497207642} 08/30/2021 17:20:25 - INFO - __main__ - Step 23087: {'lr': 0.0004753729670421871, 'samples': 4432704, 'steps': 23086, 'loss/train': 1.564009428024292} 08/30/2021 17:20:27 - INFO - __main__ - Step 23088: {'lr': 0.0004753706702534775, 'samples': 4432896, 'steps': 23087, 'loss/train': 2.1037065982818604} 08/30/2021 17:20:27 - INFO - __main__ - Step 23089: {'lr': 0.0004753683733632193, 'samples': 4433088, 'steps': 23088, 'loss/train': 1.561545729637146} 08/30/2021 17:20:28 - INFO - __main__ - Step 23090: {'lr': 0.0004753660763714136, 'samples': 4433280, 'steps': 23089, 'loss/train': 1.6166492700576782} 08/30/2021 17:20:28 - INFO - __main__ - Step 23091: {'lr': 0.00047536377927806143, 'samples': 4433472, 'steps': 23090, 'loss/train': 1.104941487312317} 08/30/2021 17:20:28 - INFO - __main__ - Step 23092: {'lr': 0.0004753614820831638, 'samples': 4433664, 'steps': 23091, 'loss/train': 1.2165592908859253} 08/30/2021 17:20:29 - INFO - __main__ - Step 23093: {'lr': 0.0004753591847867218, 'samples': 4433856, 'steps': 23092, 'loss/train': 1.848177194595337} 08/30/2021 17:20:31 - INFO - __main__ - Step 23094: {'lr': 0.0004753568873887364, 'samples': 4434048, 'steps': 23093, 'loss/train': 1.8158068656921387} 08/30/2021 17:20:31 - INFO - __main__ - Step 23095: {'lr': 0.00047535458988920865, 'samples': 4434240, 'steps': 23094, 'loss/train': 0.7858121991157532} 08/30/2021 17:20:31 - INFO - __main__ - Step 23096: {'lr': 0.0004753522922881396, 'samples': 4434432, 'steps': 23095, 'loss/train': 0.13198018074035645} 08/30/2021 17:20:32 - INFO - __main__ - Step 23097: {'lr': 0.00047534999458553027, 'samples': 4434624, 'steps': 23096, 'loss/train': 1.726241111755371} 08/30/2021 17:20:32 - INFO - __main__ - Step 23098: {'lr': 0.00047534769678138177, 'samples': 4434816, 'steps': 23097, 'loss/train': 2.280733823776245} 08/30/2021 17:20:34 - INFO - __main__ - Step 23099: {'lr': 0.00047534539887569507, 'samples': 4435008, 'steps': 23098, 'loss/train': 1.5222843885421753} 08/30/2021 17:20:34 - INFO - __main__ - Step 23100: {'lr': 0.00047534310086847116, 'samples': 4435200, 'steps': 23099, 'loss/train': 2.4165260791778564} 08/30/2021 17:20:35 - INFO - __main__ - Step 23101: {'lr': 0.0004753408027597111, 'samples': 4435392, 'steps': 23100, 'loss/train': 1.8077912330627441} 08/30/2021 17:20:35 - INFO - __main__ - Step 23102: {'lr': 0.0004753385045494161, 'samples': 4435584, 'steps': 23101, 'loss/train': 1.6808812618255615} 08/30/2021 17:20:35 - INFO - __main__ - Step 23103: {'lr': 0.0004753362062375869, 'samples': 4435776, 'steps': 23102, 'loss/train': 1.5910356044769287} 08/30/2021 17:20:36 - INFO - __main__ - Step 23104: {'lr': 0.0004753339078242247, 'samples': 4435968, 'steps': 23103, 'loss/train': 1.5396397113800049} 08/30/2021 17:20:37 - INFO - __main__ - Step 23105: {'lr': 0.00047533160930933054, 'samples': 4436160, 'steps': 23104, 'loss/train': 1.3970762491226196} 08/30/2021 17:20:38 - INFO - __main__ - Step 23106: {'lr': 0.00047532931069290546, 'samples': 4436352, 'steps': 23105, 'loss/train': 2.041872978210449} 08/30/2021 17:20:38 - INFO - __main__ - Step 23107: {'lr': 0.00047532701197495043, 'samples': 4436544, 'steps': 23106, 'loss/train': 1.8742706775665283} 08/30/2021 17:20:39 - INFO - __main__ - Step 23108: {'lr': 0.00047532471315546654, 'samples': 4436736, 'steps': 23107, 'loss/train': 1.6420570611953735} 08/30/2021 17:20:39 - INFO - __main__ - Step 23109: {'lr': 0.00047532241423445487, 'samples': 4436928, 'steps': 23108, 'loss/train': 1.8693948984146118} 08/30/2021 17:20:40 - INFO - __main__ - Step 23110: {'lr': 0.00047532011521191634, 'samples': 4437120, 'steps': 23109, 'loss/train': 2.1753315925598145} 08/30/2021 17:20:41 - INFO - __main__ - Step 23111: {'lr': 0.00047531781608785203, 'samples': 4437312, 'steps': 23110, 'loss/train': 1.7467502355575562} 08/30/2021 17:20:41 - INFO - __main__ - Step 23112: {'lr': 0.00047531551686226303, 'samples': 4437504, 'steps': 23111, 'loss/train': 1.3459922075271606} 08/30/2021 17:20:42 - INFO - __main__ - Step 23113: {'lr': 0.00047531321753515026, 'samples': 4437696, 'steps': 23112, 'loss/train': 1.6046158075332642} 08/30/2021 17:20:42 - INFO - __main__ - Step 23114: {'lr': 0.0004753109181065149, 'samples': 4437888, 'steps': 23113, 'loss/train': 1.420710563659668} 08/30/2021 17:20:44 - INFO - __main__ - Step 23115: {'lr': 0.00047530861857635786, 'samples': 4438080, 'steps': 23114, 'loss/train': 2.168738603591919} 08/30/2021 17:20:44 - INFO - __main__ - Step 23116: {'lr': 0.00047530631894468034, 'samples': 4438272, 'steps': 23115, 'loss/train': 0.11286278069019318} 08/30/2021 17:20:44 - INFO - __main__ - Step 23117: {'lr': 0.0004753040192114831, 'samples': 4438464, 'steps': 23116, 'loss/train': 0.7792182564735413} 08/30/2021 17:20:45 - INFO - __main__ - Step 23118: {'lr': 0.00047530171937676754, 'samples': 4438656, 'steps': 23117, 'loss/train': 1.52216374874115} 08/30/2021 17:20:45 - INFO - __main__ - Step 23119: {'lr': 0.0004752994194405344, 'samples': 4438848, 'steps': 23118, 'loss/train': 1.2353326082229614} 08/30/2021 17:20:46 - INFO - __main__ - Step 23120: {'lr': 0.0004752971194027848, 'samples': 4439040, 'steps': 23119, 'loss/train': 1.8364794254302979} 08/30/2021 17:20:47 - INFO - __main__ - Step 23121: {'lr': 0.0004752948192635198, 'samples': 4439232, 'steps': 23120, 'loss/train': 1.6021615266799927} 08/30/2021 17:20:47 - INFO - __main__ - Step 23122: {'lr': 0.0004752925190227405, 'samples': 4439424, 'steps': 23121, 'loss/train': 1.5915093421936035} 08/30/2021 17:20:48 - INFO - __main__ - Step 23123: {'lr': 0.0004752902186804478, 'samples': 4439616, 'steps': 23122, 'loss/train': 1.4561430215835571} 08/30/2021 17:20:48 - INFO - __main__ - Step 23124: {'lr': 0.0004752879182366429, 'samples': 4439808, 'steps': 23123, 'loss/train': 2.071640968322754} 08/30/2021 17:20:50 - INFO - __main__ - Step 23125: {'lr': 0.0004752856176913266, 'samples': 4440000, 'steps': 23124, 'loss/train': 0.09368572384119034} 08/30/2021 17:20:50 - INFO - __main__ - Step 23126: {'lr': 0.0004752833170445001, 'samples': 4440192, 'steps': 23125, 'loss/train': 1.8942292928695679} 08/30/2021 17:20:51 - INFO - __main__ - Step 23127: {'lr': 0.0004752810162961645, 'samples': 4440384, 'steps': 23126, 'loss/train': 0.2813170254230499} 08/30/2021 17:20:51 - INFO - __main__ - Step 23128: {'lr': 0.0004752787154463207, 'samples': 4440576, 'steps': 23127, 'loss/train': 1.6915593147277832} 08/30/2021 17:20:51 - INFO - __main__ - Step 23129: {'lr': 0.0004752764144949698, 'samples': 4440768, 'steps': 23128, 'loss/train': 0.9356757402420044} 08/30/2021 17:20:53 - INFO - __main__ - Step 23130: {'lr': 0.0004752741134421128, 'samples': 4440960, 'steps': 23129, 'loss/train': 1.650490164756775} 08/30/2021 17:20:53 - INFO - __main__ - Step 23131: {'lr': 0.00047527181228775077, 'samples': 4441152, 'steps': 23130, 'loss/train': 1.3722552061080933} 08/30/2021 17:20:54 - INFO - __main__ - Step 23132: {'lr': 0.0004752695110318848, 'samples': 4441344, 'steps': 23131, 'loss/train': 1.715676188468933} 08/30/2021 17:20:54 - INFO - __main__ - Step 23133: {'lr': 0.00047526720967451573, 'samples': 4441536, 'steps': 23132, 'loss/train': 1.761802077293396} 08/30/2021 17:20:54 - INFO - __main__ - Step 23134: {'lr': 0.0004752649082156448, 'samples': 4441728, 'steps': 23133, 'loss/train': 1.4513990879058838} 08/30/2021 17:20:56 - INFO - __main__ - Step 23135: {'lr': 0.00047526260665527306, 'samples': 4441920, 'steps': 23134, 'loss/train': 1.4010471105575562} 08/30/2021 17:20:56 - INFO - __main__ - Step 23136: {'lr': 0.0004752603049934014, 'samples': 4442112, 'steps': 23135, 'loss/train': 1.3411589860916138} 08/30/2021 17:20:57 - INFO - __main__ - Step 23137: {'lr': 0.0004752580032300309, 'samples': 4442304, 'steps': 23136, 'loss/train': 1.944082498550415} 08/30/2021 17:20:57 - INFO - __main__ - Step 23138: {'lr': 0.0004752557013651626, 'samples': 4442496, 'steps': 23137, 'loss/train': 1.626043677330017} 08/30/2021 17:20:57 - INFO - __main__ - Step 23139: {'lr': 0.00047525339939879764, 'samples': 4442688, 'steps': 23138, 'loss/train': 1.9153451919555664} 08/30/2021 17:20:58 - INFO - __main__ - Step 23140: {'lr': 0.0004752510973309369, 'samples': 4442880, 'steps': 23139, 'loss/train': 1.190613031387329} 08/30/2021 17:20:59 - INFO - __main__ - Step 23141: {'lr': 0.00047524879516158155, 'samples': 4443072, 'steps': 23140, 'loss/train': 1.5332773923873901} 08/30/2021 17:21:00 - INFO - __main__ - Step 23142: {'lr': 0.00047524649289073254, 'samples': 4443264, 'steps': 23141, 'loss/train': 1.2286112308502197} 08/30/2021 17:21:00 - INFO - __main__ - Step 23143: {'lr': 0.00047524419051839093, 'samples': 4443456, 'steps': 23142, 'loss/train': 1.7234455347061157} 08/30/2021 17:21:00 - INFO - __main__ - Step 23144: {'lr': 0.00047524188804455776, 'samples': 4443648, 'steps': 23143, 'loss/train': 0.9118403196334839} 08/30/2021 17:21:01 - INFO - __main__ - Step 23145: {'lr': 0.0004752395854692341, 'samples': 4443840, 'steps': 23144, 'loss/train': 0.801737368106842} 08/30/2021 17:21:02 - INFO - __main__ - Step 23146: {'lr': 0.0004752372827924209, 'samples': 4444032, 'steps': 23145, 'loss/train': 1.4815832376480103} 08/30/2021 17:21:03 - INFO - __main__ - Step 23147: {'lr': 0.0004752349800141193, 'samples': 4444224, 'steps': 23146, 'loss/train': 0.1470886766910553} 08/30/2021 17:21:03 - INFO - __main__ - Step 23148: {'lr': 0.0004752326771343303, 'samples': 4444416, 'steps': 23147, 'loss/train': 1.0431610345840454} 08/30/2021 17:21:04 - INFO - __main__ - Step 23149: {'lr': 0.00047523037415305494, 'samples': 4444608, 'steps': 23148, 'loss/train': 1.5535979270935059} 08/30/2021 17:21:04 - INFO - __main__ - Step 23150: {'lr': 0.0004752280710702942, 'samples': 4444800, 'steps': 23149, 'loss/train': 1.115715742111206} 08/30/2021 17:21:04 - INFO - __main__ - Step 23151: {'lr': 0.0004752257678860492, 'samples': 4444992, 'steps': 23150, 'loss/train': 1.6098699569702148} 08/30/2021 17:21:06 - INFO - __main__ - Step 23152: {'lr': 0.00047522346460032093, 'samples': 4445184, 'steps': 23151, 'loss/train': 1.8715747594833374} 08/30/2021 17:21:07 - INFO - __main__ - Step 23153: {'lr': 0.0004752211612131104, 'samples': 4445376, 'steps': 23152, 'loss/train': 1.5347611904144287} 08/30/2021 17:21:07 - INFO - __main__ - Step 23154: {'lr': 0.00047521885772441874, 'samples': 4445568, 'steps': 23153, 'loss/train': 0.14605779945850372} 08/30/2021 17:21:07 - INFO - __main__ - Step 23155: {'lr': 0.00047521655413424705, 'samples': 4445760, 'steps': 23154, 'loss/train': 0.32538989186286926} 08/30/2021 17:21:08 - INFO - __main__ - Step 23156: {'lr': 0.0004752142504425961, 'samples': 4445952, 'steps': 23155, 'loss/train': 1.354323387145996} 08/30/2021 17:21:09 - INFO - __main__ - Step 23157: {'lr': 0.0004752119466494671, 'samples': 4446144, 'steps': 23156, 'loss/train': 1.461428165435791} 08/30/2021 17:21:09 - INFO - __main__ - Step 23158: {'lr': 0.0004752096427548611, 'samples': 4446336, 'steps': 23157, 'loss/train': 1.5017316341400146} 08/30/2021 17:21:10 - INFO - __main__ - Step 23159: {'lr': 0.00047520733875877906, 'samples': 4446528, 'steps': 23158, 'loss/train': 1.8959764242172241} 08/30/2021 17:21:10 - INFO - __main__ - Step 23160: {'lr': 0.00047520503466122216, 'samples': 4446720, 'steps': 23159, 'loss/train': 1.2578843832015991} 08/30/2021 17:21:11 - INFO - __main__ - Step 23161: {'lr': 0.0004752027304621913, 'samples': 4446912, 'steps': 23160, 'loss/train': 1.6839022636413574} 08/30/2021 17:21:12 - INFO - __main__ - Step 23162: {'lr': 0.0004752004261616876, 'samples': 4447104, 'steps': 23161, 'loss/train': 1.5024852752685547} 08/30/2021 17:21:12 - INFO - __main__ - Step 23163: {'lr': 0.000475198121759712, 'samples': 4447296, 'steps': 23162, 'loss/train': 1.121056079864502} 08/30/2021 17:21:13 - INFO - __main__ - Step 23164: {'lr': 0.0004751958172562656, 'samples': 4447488, 'steps': 23163, 'loss/train': 1.6009811162948608} 08/30/2021 17:21:13 - INFO - __main__ - Step 23165: {'lr': 0.00047519351265134954, 'samples': 4447680, 'steps': 23164, 'loss/train': 0.7221185564994812} 08/30/2021 17:21:14 - INFO - __main__ - Step 23166: {'lr': 0.00047519120794496466, 'samples': 4447872, 'steps': 23165, 'loss/train': 1.5631213188171387} 08/30/2021 17:21:15 - INFO - __main__ - Step 23167: {'lr': 0.00047518890313711217, 'samples': 4448064, 'steps': 23166, 'loss/train': 1.6122443675994873} 08/30/2021 17:21:16 - INFO - __main__ - Step 23168: {'lr': 0.000475186598227793, 'samples': 4448256, 'steps': 23167, 'loss/train': 1.6459945440292358} 08/30/2021 17:21:16 - INFO - __main__ - Step 23169: {'lr': 0.0004751842932170082, 'samples': 4448448, 'steps': 23168, 'loss/train': 2.0564258098602295} 08/30/2021 17:21:16 - INFO - __main__ - Step 23170: {'lr': 0.00047518198810475885, 'samples': 4448640, 'steps': 23169, 'loss/train': 1.6809388399124146} 08/30/2021 17:21:17 - INFO - __main__ - Step 23171: {'lr': 0.00047517968289104596, 'samples': 4448832, 'steps': 23170, 'loss/train': 1.9831767082214355} 08/30/2021 17:21:17 - INFO - __main__ - Step 23172: {'lr': 0.0004751773775758706, 'samples': 4449024, 'steps': 23171, 'loss/train': 3.460151195526123} 08/30/2021 17:21:19 - INFO - __main__ - Step 23173: {'lr': 0.00047517507215923376, 'samples': 4449216, 'steps': 23172, 'loss/train': 1.5345171689987183} 08/30/2021 17:21:19 - INFO - __main__ - Step 23174: {'lr': 0.00047517276664113653, 'samples': 4449408, 'steps': 23173, 'loss/train': 1.496776819229126} 08/30/2021 17:21:20 - INFO - __main__ - Step 23175: {'lr': 0.0004751704610215799, 'samples': 4449600, 'steps': 23174, 'loss/train': 2.006037950515747} 08/30/2021 17:21:20 - INFO - __main__ - Step 23176: {'lr': 0.000475168155300565, 'samples': 4449792, 'steps': 23175, 'loss/train': 1.4301276206970215} 08/30/2021 17:21:20 - INFO - __main__ - Step 23177: {'lr': 0.00047516584947809274, 'samples': 4449984, 'steps': 23176, 'loss/train': 1.7376550436019897} 08/30/2021 17:21:22 - INFO - __main__ - Step 23178: {'lr': 0.00047516354355416426, 'samples': 4450176, 'steps': 23177, 'loss/train': 1.3079065084457397} 08/30/2021 17:21:23 - INFO - __main__ - Step 23179: {'lr': 0.00047516123752878054, 'samples': 4450368, 'steps': 23178, 'loss/train': 2.0567970275878906} 08/30/2021 17:21:23 - INFO - __main__ - Step 23180: {'lr': 0.00047515893140194265, 'samples': 4450560, 'steps': 23179, 'loss/train': 1.5286344289779663} 08/30/2021 17:21:24 - INFO - __main__ - Step 23181: {'lr': 0.0004751566251736516, 'samples': 4450752, 'steps': 23180, 'loss/train': 1.5406385660171509} 08/30/2021 17:21:24 - INFO - __main__ - Step 23182: {'lr': 0.00047515431884390845, 'samples': 4450944, 'steps': 23181, 'loss/train': 0.1824532300233841} 08/30/2021 17:21:24 - INFO - __main__ - Step 23183: {'lr': 0.00047515201241271426, 'samples': 4451136, 'steps': 23182, 'loss/train': 1.3524411916732788} 08/30/2021 17:21:26 - INFO - __main__ - Step 23184: {'lr': 0.00047514970588007007, 'samples': 4451328, 'steps': 23183, 'loss/train': 1.7183396816253662} 08/30/2021 17:21:26 - INFO - __main__ - Step 23185: {'lr': 0.0004751473992459768, 'samples': 4451520, 'steps': 23184, 'loss/train': 1.3646972179412842} 08/30/2021 17:21:27 - INFO - __main__ - Step 23186: {'lr': 0.0004751450925104357, 'samples': 4451712, 'steps': 23185, 'loss/train': 2.6572694778442383} 08/30/2021 17:21:27 - INFO - __main__ - Step 23187: {'lr': 0.00047514278567344765, 'samples': 4451904, 'steps': 23186, 'loss/train': 1.613290786743164} 08/30/2021 17:21:27 - INFO - __main__ - Step 23188: {'lr': 0.00047514047873501374, 'samples': 4452096, 'steps': 23187, 'loss/train': 1.8051426410675049} 08/30/2021 17:21:29 - INFO - __main__ - Step 23189: {'lr': 0.000475138171695135, 'samples': 4452288, 'steps': 23188, 'loss/train': 1.572274088859558} 08/30/2021 17:21:29 - INFO - __main__ - Step 23190: {'lr': 0.00047513586455381245, 'samples': 4452480, 'steps': 23189, 'loss/train': 1.9939802885055542} 08/30/2021 17:21:30 - INFO - __main__ - Step 23191: {'lr': 0.00047513355731104717, 'samples': 4452672, 'steps': 23190, 'loss/train': 1.7568353414535522} 08/30/2021 17:21:30 - INFO - __main__ - Step 23192: {'lr': 0.0004751312499668402, 'samples': 4452864, 'steps': 23191, 'loss/train': 1.5489119291305542} 08/30/2021 17:21:30 - INFO - __main__ - Step 23193: {'lr': 0.00047512894252119256, 'samples': 4453056, 'steps': 23192, 'loss/train': 1.2617095708847046} 08/30/2021 17:21:32 - INFO - __main__ - Step 23194: {'lr': 0.0004751266349741053, 'samples': 4453248, 'steps': 23193, 'loss/train': 1.708428144454956} 08/30/2021 17:21:32 - INFO - __main__ - Step 23195: {'lr': 0.0004751243273255794, 'samples': 4453440, 'steps': 23194, 'loss/train': 0.8694499731063843} 08/30/2021 17:21:33 - INFO - __main__ - Step 23196: {'lr': 0.000475122019575616, 'samples': 4453632, 'steps': 23195, 'loss/train': 2.340193510055542} 08/30/2021 17:21:33 - INFO - __main__ - Step 23197: {'lr': 0.0004751197117242161, 'samples': 4453824, 'steps': 23196, 'loss/train': 1.6779906749725342} 08/30/2021 17:21:33 - INFO - __main__ - Step 23198: {'lr': 0.0004751174037713807, 'samples': 4454016, 'steps': 23197, 'loss/train': 1.6135693788528442} 08/30/2021 17:21:35 - INFO - __main__ - Step 23199: {'lr': 0.00047511509571711085, 'samples': 4454208, 'steps': 23198, 'loss/train': 1.5950708389282227} 08/30/2021 17:21:36 - INFO - __main__ - Step 23200: {'lr': 0.00047511278756140766, 'samples': 4454400, 'steps': 23199, 'loss/train': 1.4282525777816772} 08/30/2021 17:21:36 - INFO - __main__ - Step 23201: {'lr': 0.00047511047930427216, 'samples': 4454592, 'steps': 23200, 'loss/train': 1.557000994682312} 08/30/2021 17:21:36 - INFO - __main__ - Step 23202: {'lr': 0.00047510817094570526, 'samples': 4454784, 'steps': 23201, 'loss/train': 1.6131747961044312} 08/30/2021 17:21:37 - INFO - __main__ - Step 23203: {'lr': 0.00047510586248570815, 'samples': 4454976, 'steps': 23202, 'loss/train': 0.7795226573944092} 08/30/2021 17:21:38 - INFO - __main__ - Step 23204: {'lr': 0.00047510355392428176, 'samples': 4455168, 'steps': 23203, 'loss/train': 1.7070263624191284} 08/30/2021 17:21:39 - INFO - __main__ - Step 23205: {'lr': 0.00047510124526142723, 'samples': 4455360, 'steps': 23204, 'loss/train': 1.9022858142852783} 08/30/2021 17:21:39 - INFO - __main__ - Step 23206: {'lr': 0.00047509893649714554, 'samples': 4455552, 'steps': 23205, 'loss/train': 1.6807376146316528} 08/30/2021 17:21:39 - INFO - __main__ - Step 23207: {'lr': 0.00047509662763143775, 'samples': 4455744, 'steps': 23206, 'loss/train': 1.791644811630249} 08/30/2021 17:21:40 - INFO - __main__ - Step 23208: {'lr': 0.00047509431866430487, 'samples': 4455936, 'steps': 23207, 'loss/train': 1.6276882886886597} 08/30/2021 17:21:40 - INFO - __main__ - Step 23209: {'lr': 0.000475092009595748, 'samples': 4456128, 'steps': 23208, 'loss/train': 1.7554091215133667} 08/30/2021 17:21:41 - INFO - __main__ - Step 23210: {'lr': 0.0004750897004257681, 'samples': 4456320, 'steps': 23209, 'loss/train': 1.5933202505111694} 08/30/2021 17:21:42 - INFO - __main__ - Step 23211: {'lr': 0.0004750873911543663, 'samples': 4456512, 'steps': 23210, 'loss/train': 1.8493651151657104} 08/30/2021 17:21:42 - INFO - __main__ - Step 23212: {'lr': 0.00047508508178154354, 'samples': 4456704, 'steps': 23211, 'loss/train': 1.3049308061599731} 08/30/2021 17:21:43 - INFO - __main__ - Step 23213: {'lr': 0.00047508277230730095, 'samples': 4456896, 'steps': 23212, 'loss/train': 1.920776605606079} 08/30/2021 17:21:43 - INFO - __main__ - Step 23214: {'lr': 0.00047508046273163953, 'samples': 4457088, 'steps': 23213, 'loss/train': 1.2272385358810425} 08/30/2021 17:21:44 - INFO - __main__ - Step 23215: {'lr': 0.0004750781530545603, 'samples': 4457280, 'steps': 23214, 'loss/train': 1.6449463367462158} 08/30/2021 17:21:45 - INFO - __main__ - Step 23216: {'lr': 0.0004750758432760644, 'samples': 4457472, 'steps': 23215, 'loss/train': 1.731659173965454} 08/30/2021 17:21:45 - INFO - __main__ - Step 23217: {'lr': 0.0004750735333961527, 'samples': 4457664, 'steps': 23216, 'loss/train': 1.3513771295547485} 08/30/2021 17:21:45 - INFO - __main__ - Step 23218: {'lr': 0.00047507122341482644, 'samples': 4457856, 'steps': 23217, 'loss/train': 1.6106244325637817} 08/30/2021 17:21:46 - INFO - __main__ - Step 23219: {'lr': 0.00047506891333208654, 'samples': 4458048, 'steps': 23218, 'loss/train': 1.494199275970459} 08/30/2021 17:21:47 - INFO - __main__ - Step 23220: {'lr': 0.000475066603147934, 'samples': 4458240, 'steps': 23219, 'loss/train': 1.7515572309494019} 08/30/2021 17:21:48 - INFO - __main__ - Step 23221: {'lr': 0.00047506429286236997, 'samples': 4458432, 'steps': 23220, 'loss/train': 1.638920545578003} 08/30/2021 17:21:48 - INFO - __main__ - Step 23222: {'lr': 0.00047506198247539546, 'samples': 4458624, 'steps': 23221, 'loss/train': 1.7657824754714966} 08/30/2021 17:21:48 - INFO - __main__ - Step 23223: {'lr': 0.0004750596719870114, 'samples': 4458816, 'steps': 23222, 'loss/train': 1.6600230932235718} 08/30/2021 17:21:49 - INFO - __main__ - Step 23224: {'lr': 0.000475057361397219, 'samples': 4459008, 'steps': 23223, 'loss/train': 1.6566829681396484} 08/30/2021 17:21:50 - INFO - __main__ - Step 23225: {'lr': 0.0004750550507060192, 'samples': 4459200, 'steps': 23224, 'loss/train': 1.5358529090881348} 08/30/2021 17:21:51 - INFO - __main__ - Step 23226: {'lr': 0.0004750527399134131, 'samples': 4459392, 'steps': 23225, 'loss/train': 1.396316647529602} 08/30/2021 17:21:51 - INFO - __main__ - Step 23227: {'lr': 0.00047505042901940163, 'samples': 4459584, 'steps': 23226, 'loss/train': 1.651220679283142} 08/30/2021 17:21:51 - INFO - __main__ - Step 23228: {'lr': 0.00047504811802398603, 'samples': 4459776, 'steps': 23227, 'loss/train': 1.394845962524414} 08/30/2021 17:21:52 - INFO - __main__ - Step 23229: {'lr': 0.0004750458069271671, 'samples': 4459968, 'steps': 23228, 'loss/train': 0.3783375918865204} 08/30/2021 17:21:54 - INFO - __main__ - Step 23230: {'lr': 0.0004750434957289461, 'samples': 4460160, 'steps': 23229, 'loss/train': 1.5883769989013672} 08/30/2021 17:21:54 - INFO - __main__ - Step 23231: {'lr': 0.0004750411844293239, 'samples': 4460352, 'steps': 23230, 'loss/train': 1.9355220794677734} 08/30/2021 17:21:54 - INFO - __main__ - Step 23232: {'lr': 0.0004750388730283016, 'samples': 4460544, 'steps': 23231, 'loss/train': 1.310945749282837} 08/30/2021 17:21:55 - INFO - __main__ - Step 23233: {'lr': 0.0004750365615258804, 'samples': 4460736, 'steps': 23232, 'loss/train': 1.852506160736084} 08/30/2021 17:21:55 - INFO - __main__ - Step 23234: {'lr': 0.00047503424992206107, 'samples': 4460928, 'steps': 23233, 'loss/train': 1.3770300149917603} 08/30/2021 17:21:57 - INFO - __main__ - Step 23235: {'lr': 0.00047503193821684476, 'samples': 4461120, 'steps': 23234, 'loss/train': 1.3650484085083008} 08/30/2021 17:21:57 - INFO - __main__ - Step 23236: {'lr': 0.0004750296264102326, 'samples': 4461312, 'steps': 23235, 'loss/train': 1.575400710105896} 08/30/2021 17:21:57 - INFO - __main__ - Step 23237: {'lr': 0.0004750273145022256, 'samples': 4461504, 'steps': 23236, 'loss/train': 1.0140916109085083} 08/30/2021 17:21:58 - INFO - __main__ - Step 23238: {'lr': 0.00047502500249282464, 'samples': 4461696, 'steps': 23237, 'loss/train': 2.0177133083343506} 08/30/2021 17:21:58 - INFO - __main__ - Step 23239: {'lr': 0.000475022690382031, 'samples': 4461888, 'steps': 23238, 'loss/train': 1.9535596370697021} 08/30/2021 17:22:00 - INFO - __main__ - Step 23240: {'lr': 0.0004750203781698456, 'samples': 4462080, 'steps': 23239, 'loss/train': 1.9856034517288208} 08/30/2021 17:22:00 - INFO - __main__ - Step 23241: {'lr': 0.0004750180658562694, 'samples': 4462272, 'steps': 23240, 'loss/train': 0.20193614065647125} 08/30/2021 17:22:00 - INFO - __main__ - Step 23242: {'lr': 0.00047501575344130356, 'samples': 4462464, 'steps': 23241, 'loss/train': 1.469152808189392} 08/30/2021 17:22:01 - INFO - __main__ - Step 23243: {'lr': 0.00047501344092494915, 'samples': 4462656, 'steps': 23242, 'loss/train': 1.6817524433135986} 08/30/2021 17:22:01 - INFO - __main__ - Step 23244: {'lr': 0.0004750111283072071, 'samples': 4462848, 'steps': 23243, 'loss/train': 1.05733323097229} 08/30/2021 17:22:03 - INFO - __main__ - Step 23245: {'lr': 0.00047500881558807854, 'samples': 4463040, 'steps': 23244, 'loss/train': 1.526496410369873} 08/30/2021 17:22:04 - INFO - __main__ - Step 23246: {'lr': 0.00047500650276756455, 'samples': 4463232, 'steps': 23245, 'loss/train': 1.9825046062469482} 08/30/2021 17:22:04 - INFO - __main__ - Step 23247: {'lr': 0.00047500418984566594, 'samples': 4463424, 'steps': 23246, 'loss/train': 2.217878818511963} 08/30/2021 17:22:04 - INFO - __main__ - Step 23248: {'lr': 0.000475001876822384, 'samples': 4463616, 'steps': 23247, 'loss/train': 1.6152948141098022} 08/30/2021 17:22:05 - INFO - __main__ - Step 23249: {'lr': 0.00047499956369771967, 'samples': 4463808, 'steps': 23248, 'loss/train': 0.9902798533439636} 08/30/2021 17:22:05 - INFO - __main__ - Step 23250: {'lr': 0.00047499725047167406, 'samples': 4464000, 'steps': 23249, 'loss/train': 1.7276273965835571} 08/30/2021 17:22:05 - INFO - __main__ - Step 23251: {'lr': 0.0004749949371442481, 'samples': 4464192, 'steps': 23250, 'loss/train': 1.323229193687439} 08/30/2021 17:22:07 - INFO - __main__ - Step 23252: {'lr': 0.00047499262371544294, 'samples': 4464384, 'steps': 23251, 'loss/train': 2.0143301486968994} 08/30/2021 17:22:07 - INFO - __main__ - Step 23253: {'lr': 0.00047499031018525953, 'samples': 4464576, 'steps': 23252, 'loss/train': 1.3034156560897827} 08/30/2021 17:22:08 - INFO - __main__ - Step 23254: {'lr': 0.00047498799655369895, 'samples': 4464768, 'steps': 23253, 'loss/train': 1.3375436067581177} 08/30/2021 17:22:08 - INFO - __main__ - Step 23255: {'lr': 0.0004749856828207623, 'samples': 4464960, 'steps': 23254, 'loss/train': 2.0281713008880615} 08/30/2021 17:22:08 - INFO - __main__ - Step 23256: {'lr': 0.00047498336898645055, 'samples': 4465152, 'steps': 23255, 'loss/train': 1.6792418956756592} 08/30/2021 17:22:10 - INFO - __main__ - Step 23257: {'lr': 0.00047498105505076475, 'samples': 4465344, 'steps': 23256, 'loss/train': 0.7893033027648926} 08/30/2021 17:22:10 - INFO - __main__ - Step 23258: {'lr': 0.000474978741013706, 'samples': 4465536, 'steps': 23257, 'loss/train': 1.6571929454803467} 08/30/2021 17:22:11 - INFO - __main__ - Step 23259: {'lr': 0.0004749764268752753, 'samples': 4465728, 'steps': 23258, 'loss/train': 1.4134469032287598} 08/30/2021 17:22:11 - INFO - __main__ - Step 23260: {'lr': 0.0004749741126354736, 'samples': 4465920, 'steps': 23259, 'loss/train': 1.9693456888198853} 08/30/2021 17:22:11 - INFO - __main__ - Step 23261: {'lr': 0.00047497179829430217, 'samples': 4466112, 'steps': 23260, 'loss/train': 1.663743495941162} 08/30/2021 17:22:13 - INFO - __main__ - Step 23262: {'lr': 0.0004749694838517619, 'samples': 4466304, 'steps': 23261, 'loss/train': 1.4114000797271729} 08/30/2021 17:22:14 - INFO - __main__ - Step 23263: {'lr': 0.0004749671693078538, 'samples': 4466496, 'steps': 23262, 'loss/train': 1.3881969451904297} 08/30/2021 17:22:14 - INFO - __main__ - Step 23264: {'lr': 0.00047496485466257896, 'samples': 4466688, 'steps': 23263, 'loss/train': 0.1113017275929451} 08/30/2021 17:22:14 - INFO - __main__ - Step 23265: {'lr': 0.0004749625399159384, 'samples': 4466880, 'steps': 23264, 'loss/train': 1.3417302370071411} 08/30/2021 17:22:15 - INFO - __main__ - Step 23266: {'lr': 0.0004749602250679332, 'samples': 4467072, 'steps': 23265, 'loss/train': 0.23997275531291962} 08/30/2021 17:22:16 - INFO - __main__ - Step 23267: {'lr': 0.00047495791011856447, 'samples': 4467264, 'steps': 23266, 'loss/train': 0.29367148876190186} 08/30/2021 17:22:17 - INFO - __main__ - Step 23268: {'lr': 0.00047495559506783317, 'samples': 4467456, 'steps': 23267, 'loss/train': 1.3928866386413574} 08/30/2021 17:22:17 - INFO - __main__ - Step 23269: {'lr': 0.00047495327991574034, 'samples': 4467648, 'steps': 23268, 'loss/train': 1.7561638355255127} 08/30/2021 17:22:17 - INFO - __main__ - Step 23270: {'lr': 0.0004749509646622869, 'samples': 4467840, 'steps': 23269, 'loss/train': 1.2333191633224487} 08/30/2021 17:22:18 - INFO - __main__ - Step 23271: {'lr': 0.00047494864930747415, 'samples': 4468032, 'steps': 23270, 'loss/train': 1.8547008037567139} 08/30/2021 17:22:19 - INFO - __main__ - Step 23272: {'lr': 0.000474946333851303, 'samples': 4468224, 'steps': 23271, 'loss/train': 0.4618629515171051} 08/30/2021 17:22:20 - INFO - __main__ - Step 23273: {'lr': 0.0004749440182937745, 'samples': 4468416, 'steps': 23272, 'loss/train': 1.3728739023208618} 08/30/2021 17:22:20 - INFO - __main__ - Step 23274: {'lr': 0.0004749417026348897, 'samples': 4468608, 'steps': 23273, 'loss/train': 2.0360350608825684} 08/30/2021 17:22:20 - INFO - __main__ - Step 23275: {'lr': 0.0004749393868746497, 'samples': 4468800, 'steps': 23274, 'loss/train': 1.6930845975875854} 08/30/2021 17:22:21 - INFO - __main__ - Step 23276: {'lr': 0.0004749370710130554, 'samples': 4468992, 'steps': 23275, 'loss/train': 0.9200928211212158} 08/30/2021 17:22:22 - INFO - __main__ - Step 23277: {'lr': 0.00047493475505010793, 'samples': 4469184, 'steps': 23276, 'loss/train': 1.4903265237808228} 08/30/2021 17:22:23 - INFO - __main__ - Step 23278: {'lr': 0.0004749324389858083, 'samples': 4469376, 'steps': 23277, 'loss/train': 1.6839574575424194} 08/30/2021 17:22:23 - INFO - __main__ - Step 23279: {'lr': 0.00047493012282015767, 'samples': 4469568, 'steps': 23278, 'loss/train': 1.6174678802490234} 08/30/2021 17:22:23 - INFO - __main__ - Step 23280: {'lr': 0.00047492780655315693, 'samples': 4469760, 'steps': 23279, 'loss/train': 1.8059922456741333} 08/30/2021 17:22:24 - INFO - __main__ - Step 23281: {'lr': 0.00047492549018480725, 'samples': 4469952, 'steps': 23280, 'loss/train': 1.4149961471557617} 08/30/2021 17:22:25 - INFO - __main__ - Step 23282: {'lr': 0.00047492317371510955, 'samples': 4470144, 'steps': 23281, 'loss/train': 0.8420997858047485} 08/30/2021 17:22:26 - INFO - __main__ - Step 23283: {'lr': 0.00047492085714406497, 'samples': 4470336, 'steps': 23282, 'loss/train': 1.0607054233551025} 08/30/2021 17:22:26 - INFO - __main__ - Step 23284: {'lr': 0.00047491854047167453, 'samples': 4470528, 'steps': 23283, 'loss/train': 1.798923373222351} 08/30/2021 17:22:27 - INFO - __main__ - Step 23285: {'lr': 0.0004749162236979393, 'samples': 4470720, 'steps': 23284, 'loss/train': 1.8167866468429565} 08/30/2021 17:22:27 - INFO - __main__ - Step 23286: {'lr': 0.0004749139068228602, 'samples': 4470912, 'steps': 23285, 'loss/train': 1.3599193096160889} 08/30/2021 17:22:27 - INFO - __main__ - Step 23287: {'lr': 0.00047491158984643846, 'samples': 4471104, 'steps': 23286, 'loss/train': 2.153561592102051} 08/30/2021 17:22:30 - INFO - __main__ - Step 23288: {'lr': 0.0004749092727686749, 'samples': 4471296, 'steps': 23287, 'loss/train': 1.4420368671417236} 08/30/2021 17:22:30 - INFO - __main__ - Step 23289: {'lr': 0.00047490695558957083, 'samples': 4471488, 'steps': 23288, 'loss/train': 1.1183713674545288} 08/30/2021 17:22:31 - INFO - __main__ - Step 23290: {'lr': 0.00047490463830912713, 'samples': 4471680, 'steps': 23289, 'loss/train': 2.230461359024048} 08/30/2021 17:22:31 - INFO - __main__ - Step 23291: {'lr': 0.0004749023209273448, 'samples': 4471872, 'steps': 23290, 'loss/train': 2.1331839561462402} 08/30/2021 17:22:31 - INFO - __main__ - Step 23292: {'lr': 0.000474900003444225, 'samples': 4472064, 'steps': 23291, 'loss/train': 1.9077094793319702} 08/30/2021 17:22:33 - INFO - __main__ - Step 23293: {'lr': 0.0004748976858597687, 'samples': 4472256, 'steps': 23292, 'loss/train': 1.3912080526351929} 08/30/2021 17:22:33 - INFO - __main__ - Step 23294: {'lr': 0.00047489536817397706, 'samples': 4472448, 'steps': 23293, 'loss/train': 1.8662384748458862} 08/30/2021 17:22:34 - INFO - __main__ - Step 23295: {'lr': 0.00047489305038685094, 'samples': 4472640, 'steps': 23294, 'loss/train': 1.615684986114502} 08/30/2021 17:22:34 - INFO - __main__ - Step 23296: {'lr': 0.00047489073249839153, 'samples': 4472832, 'steps': 23295, 'loss/train': 1.5429795980453491} 08/30/2021 17:22:34 - INFO - __main__ - Step 23297: {'lr': 0.0004748884145085998, 'samples': 4473024, 'steps': 23296, 'loss/train': 1.2033603191375732} 08/30/2021 17:22:35 - INFO - __main__ - Step 23298: {'lr': 0.0004748860964174768, 'samples': 4473216, 'steps': 23297, 'loss/train': 1.162532925605774} 08/30/2021 17:22:36 - INFO - __main__ - Step 23299: {'lr': 0.00047488377822502365, 'samples': 4473408, 'steps': 23298, 'loss/train': 1.6472742557525635} 08/30/2021 17:22:37 - INFO - __main__ - Step 23300: {'lr': 0.00047488145993124134, 'samples': 4473600, 'steps': 23299, 'loss/train': 1.606379747390747} 08/30/2021 17:22:37 - INFO - __main__ - Step 23301: {'lr': 0.0004748791415361309, 'samples': 4473792, 'steps': 23300, 'loss/train': 1.5527448654174805} 08/30/2021 17:22:37 - INFO - __main__ - Step 23302: {'lr': 0.00047487682303969336, 'samples': 4473984, 'steps': 23301, 'loss/train': 1.3916690349578857} 08/30/2021 17:22:38 - INFO - __main__ - Step 23303: {'lr': 0.0004748745044419298, 'samples': 4474176, 'steps': 23302, 'loss/train': 0.8504519462585449} 08/30/2021 17:22:39 - INFO - __main__ - Step 23304: {'lr': 0.0004748721857428413, 'samples': 4474368, 'steps': 23303, 'loss/train': 2.007427215576172} 08/30/2021 17:22:40 - INFO - __main__ - Step 23305: {'lr': 0.00047486986694242887, 'samples': 4474560, 'steps': 23304, 'loss/train': 2.2359650135040283} 08/30/2021 17:22:40 - INFO - __main__ - Step 23306: {'lr': 0.0004748675480406934, 'samples': 4474752, 'steps': 23305, 'loss/train': 1.6426920890808105} 08/30/2021 17:22:40 - INFO - __main__ - Step 23307: {'lr': 0.0004748652290376363, 'samples': 4474944, 'steps': 23306, 'loss/train': 1.280753493309021} 08/30/2021 17:22:41 - INFO - __main__ - Step 23308: {'lr': 0.00047486290993325824, 'samples': 4475136, 'steps': 23307, 'loss/train': 1.0288336277008057} 08/30/2021 17:22:41 - INFO - __main__ - Step 23309: {'lr': 0.00047486059072756047, 'samples': 4475328, 'steps': 23308, 'loss/train': 1.8509293794631958} 08/30/2021 17:22:43 - INFO - __main__ - Step 23310: {'lr': 0.00047485827142054407, 'samples': 4475520, 'steps': 23309, 'loss/train': 1.7704225778579712} 08/30/2021 17:22:43 - INFO - __main__ - Step 23311: {'lr': 0.0004748559520122099, 'samples': 4475712, 'steps': 23310, 'loss/train': 1.6992249488830566} 08/30/2021 17:22:44 - INFO - __main__ - Step 23312: {'lr': 0.0004748536325025591, 'samples': 4475904, 'steps': 23311, 'loss/train': 1.788007378578186} 08/30/2021 17:22:44 - INFO - __main__ - Step 23313: {'lr': 0.0004748513128915928, 'samples': 4476096, 'steps': 23312, 'loss/train': 1.953972339630127} 08/30/2021 17:22:44 - INFO - __main__ - Step 23314: {'lr': 0.0004748489931793119, 'samples': 4476288, 'steps': 23313, 'loss/train': 1.7730237245559692} 08/30/2021 17:22:46 - INFO - __main__ - Step 23315: {'lr': 0.00047484667336571753, 'samples': 4476480, 'steps': 23314, 'loss/train': 1.0370426177978516} 08/30/2021 17:22:46 - INFO - __main__ - Step 23316: {'lr': 0.0004748443534508107, 'samples': 4476672, 'steps': 23315, 'loss/train': 2.3911044597625732} 08/30/2021 17:22:46 - INFO - __main__ - Step 23317: {'lr': 0.00047484203343459256, 'samples': 4476864, 'steps': 23316, 'loss/train': 1.7602030038833618} 08/30/2021 17:22:47 - INFO - __main__ - Step 23318: {'lr': 0.000474839713317064, 'samples': 4477056, 'steps': 23317, 'loss/train': 1.7041176557540894} 08/30/2021 17:22:47 - INFO - __main__ - Step 23319: {'lr': 0.00047483739309822615, 'samples': 4477248, 'steps': 23318, 'loss/train': 1.4947415590286255} 08/30/2021 17:22:49 - INFO - __main__ - Step 23320: {'lr': 0.00047483507277808, 'samples': 4477440, 'steps': 23319, 'loss/train': 1.7281042337417603} 08/30/2021 17:22:49 - INFO - __main__ - Step 23321: {'lr': 0.0004748327523566267, 'samples': 4477632, 'steps': 23320, 'loss/train': 1.1908296346664429} 08/30/2021 17:22:49 - INFO - __main__ - Step 23322: {'lr': 0.0004748304318338672, 'samples': 4477824, 'steps': 23321, 'loss/train': 0.6295861005783081} 08/30/2021 17:22:50 - INFO - __main__ - Step 23323: {'lr': 0.00047482811120980254, 'samples': 4478016, 'steps': 23322, 'loss/train': 1.4904004335403442} 08/30/2021 17:22:50 - INFO - __main__ - Step 23324: {'lr': 0.0004748257904844339, 'samples': 4478208, 'steps': 23323, 'loss/train': 0.9871253967285156} 08/30/2021 17:22:52 - INFO - __main__ - Step 23325: {'lr': 0.00047482346965776215, 'samples': 4478400, 'steps': 23324, 'loss/train': 1.551640510559082} 08/30/2021 17:22:52 - INFO - __main__ - Step 23326: {'lr': 0.0004748211487297884, 'samples': 4478592, 'steps': 23325, 'loss/train': 1.6661995649337769} 08/30/2021 17:22:52 - INFO - __main__ - Step 23327: {'lr': 0.00047481882770051377, 'samples': 4478784, 'steps': 23326, 'loss/train': 1.2789151668548584} 08/30/2021 17:22:53 - INFO - __main__ - Step 23328: {'lr': 0.00047481650656993924, 'samples': 4478976, 'steps': 23327, 'loss/train': 1.8919947147369385} 08/30/2021 17:22:53 - INFO - __main__ - Step 23329: {'lr': 0.00047481418533806586, 'samples': 4479168, 'steps': 23328, 'loss/train': 1.881327748298645} 08/30/2021 17:22:55 - INFO - __main__ - Step 23330: {'lr': 0.0004748118640048946, 'samples': 4479360, 'steps': 23329, 'loss/train': 1.0059058666229248} 08/30/2021 17:22:55 - INFO - __main__ - Step 23331: {'lr': 0.00047480954257042666, 'samples': 4479552, 'steps': 23330, 'loss/train': 1.5549612045288086} 08/30/2021 17:22:55 - INFO - __main__ - Step 23332: {'lr': 0.000474807221034663, 'samples': 4479744, 'steps': 23331, 'loss/train': 1.6566517353057861} 08/30/2021 17:22:56 - INFO - __main__ - Step 23333: {'lr': 0.0004748048993976046, 'samples': 4479936, 'steps': 23332, 'loss/train': 1.3243255615234375} 08/30/2021 17:22:56 - INFO - __main__ - Step 23334: {'lr': 0.0004748025776592527, 'samples': 4480128, 'steps': 23333, 'loss/train': 1.6638424396514893} 08/30/2021 17:22:58 - INFO - __main__ - Step 23335: {'lr': 0.00047480025581960817, 'samples': 4480320, 'steps': 23334, 'loss/train': 1.2825798988342285} 08/30/2021 17:22:58 - INFO - __main__ - Step 23336: {'lr': 0.0004747979338786721, 'samples': 4480512, 'steps': 23335, 'loss/train': 1.877795934677124} 08/30/2021 17:22:58 - INFO - __main__ - Step 23337: {'lr': 0.00047479561183644557, 'samples': 4480704, 'steps': 23336, 'loss/train': 1.6736769676208496} 08/30/2021 17:22:59 - INFO - __main__ - Step 23338: {'lr': 0.00047479328969292963, 'samples': 4480896, 'steps': 23337, 'loss/train': 1.8154802322387695} 08/30/2021 17:22:59 - INFO - __main__ - Step 23339: {'lr': 0.0004747909674481253, 'samples': 4481088, 'steps': 23338, 'loss/train': 1.9429608583450317} 08/30/2021 17:23:01 - INFO - __main__ - Step 23340: {'lr': 0.00047478864510203355, 'samples': 4481280, 'steps': 23339, 'loss/train': 1.302916169166565} 08/30/2021 17:23:01 - INFO - __main__ - Step 23341: {'lr': 0.0004747863226546556, 'samples': 4481472, 'steps': 23340, 'loss/train': 1.8804534673690796} 08/30/2021 17:23:02 - INFO - __main__ - Step 23342: {'lr': 0.0004747840001059923, 'samples': 4481664, 'steps': 23341, 'loss/train': 1.4982608556747437} 08/30/2021 17:23:02 - INFO - __main__ - Step 23343: {'lr': 0.00047478167745604495, 'samples': 4481856, 'steps': 23342, 'loss/train': 0.9054900407791138} 08/30/2021 17:23:02 - INFO - __main__ - Step 23344: {'lr': 0.00047477935470481434, 'samples': 4482048, 'steps': 23343, 'loss/train': 1.4744951725006104} 08/30/2021 17:23:04 - INFO - __main__ - Step 23345: {'lr': 0.00047477703185230157, 'samples': 4482240, 'steps': 23344, 'loss/train': 1.1306208372116089} 08/30/2021 17:23:04 - INFO - __main__ - Step 23346: {'lr': 0.00047477470889850784, 'samples': 4482432, 'steps': 23345, 'loss/train': 1.7451003789901733} 08/30/2021 17:23:05 - INFO - __main__ - Step 23347: {'lr': 0.00047477238584343407, 'samples': 4482624, 'steps': 23346, 'loss/train': 1.4920345544815063} 08/30/2021 17:23:05 - INFO - __main__ - Step 23348: {'lr': 0.00047477006268708134, 'samples': 4482816, 'steps': 23347, 'loss/train': 1.6318023204803467} 08/30/2021 17:23:05 - INFO - __main__ - Step 23349: {'lr': 0.00047476773942945063, 'samples': 4483008, 'steps': 23348, 'loss/train': 1.410489559173584} 08/30/2021 17:23:06 - INFO - __main__ - Step 23350: {'lr': 0.00047476541607054313, 'samples': 4483200, 'steps': 23349, 'loss/train': 1.4952244758605957} 08/30/2021 17:23:07 - INFO - __main__ - Step 23351: {'lr': 0.0004747630926103597, 'samples': 4483392, 'steps': 23350, 'loss/train': 1.6330492496490479} 08/30/2021 17:23:08 - INFO - __main__ - Step 23352: {'lr': 0.0004747607690489015, 'samples': 4483584, 'steps': 23351, 'loss/train': 1.2275327444076538} 08/30/2021 17:23:08 - INFO - __main__ - Step 23353: {'lr': 0.00047475844538616966, 'samples': 4483776, 'steps': 23352, 'loss/train': 1.9747304916381836} 08/30/2021 17:23:08 - INFO - __main__ - Step 23354: {'lr': 0.0004747561216221651, 'samples': 4483968, 'steps': 23353, 'loss/train': 1.918383240699768} 08/30/2021 17:23:09 - INFO - __main__ - Step 23355: {'lr': 0.0004747537977568889, 'samples': 4484160, 'steps': 23354, 'loss/train': 0.5475494265556335} 08/30/2021 17:23:11 - INFO - __main__ - Step 23356: {'lr': 0.00047475147379034206, 'samples': 4484352, 'steps': 23355, 'loss/train': 1.4513154029846191} 08/30/2021 17:23:11 - INFO - __main__ - Step 23357: {'lr': 0.0004747491497225257, 'samples': 4484544, 'steps': 23356, 'loss/train': 1.5879918336868286} 08/30/2021 17:23:12 - INFO - __main__ - Step 23358: {'lr': 0.00047474682555344083, 'samples': 4484736, 'steps': 23357, 'loss/train': 1.2888751029968262} 08/30/2021 17:23:12 - INFO - __main__ - Step 23359: {'lr': 0.00047474450128308853, 'samples': 4484928, 'steps': 23358, 'loss/train': 1.9676098823547363} 08/30/2021 17:23:13 - INFO - __main__ - Step 23360: {'lr': 0.0004747421769114698, 'samples': 4485120, 'steps': 23359, 'loss/train': 2.159215211868286} 08/30/2021 17:23:13 - INFO - __main__ - Step 23361: {'lr': 0.00047473985243858577, 'samples': 4485312, 'steps': 23360, 'loss/train': 1.4242740869522095} 08/30/2021 17:23:13 - INFO - __main__ - Step 23362: {'lr': 0.00047473752786443736, 'samples': 4485504, 'steps': 23361, 'loss/train': 1.536911129951477} 08/30/2021 17:23:15 - INFO - __main__ - Step 23363: {'lr': 0.0004747352031890257, 'samples': 4485696, 'steps': 23362, 'loss/train': 1.0240377187728882} 08/30/2021 17:23:15 - INFO - __main__ - Step 23364: {'lr': 0.0004747328784123519, 'samples': 4485888, 'steps': 23363, 'loss/train': 1.4924437999725342} 08/30/2021 17:23:16 - INFO - __main__ - Step 23365: {'lr': 0.00047473055353441685, 'samples': 4486080, 'steps': 23364, 'loss/train': 1.7939375638961792} 08/30/2021 17:23:16 - INFO - __main__ - Step 23366: {'lr': 0.0004747282285552217, 'samples': 4486272, 'steps': 23365, 'loss/train': 2.470353841781616} 08/30/2021 17:23:16 - INFO - __main__ - Step 23367: {'lr': 0.0004747259034747675, 'samples': 4486464, 'steps': 23366, 'loss/train': 2.460697889328003} 08/30/2021 17:23:18 - INFO - __main__ - Step 23368: {'lr': 0.00047472357829305524, 'samples': 4486656, 'steps': 23367, 'loss/train': 1.9643207788467407} 08/30/2021 17:23:18 - INFO - __main__ - Step 23369: {'lr': 0.0004747212530100861, 'samples': 4486848, 'steps': 23368, 'loss/train': 1.8857786655426025} 08/30/2021 17:23:19 - INFO - __main__ - Step 23370: {'lr': 0.0004747189276258609, 'samples': 4487040, 'steps': 23369, 'loss/train': 1.8279653787612915} 08/30/2021 17:23:19 - INFO - __main__ - Step 23371: {'lr': 0.0004747166021403809, 'samples': 4487232, 'steps': 23370, 'loss/train': 1.2541252374649048} 08/30/2021 17:23:19 - INFO - __main__ - Step 23372: {'lr': 0.000474714276553647, 'samples': 4487424, 'steps': 23371, 'loss/train': 1.3642388582229614} 08/30/2021 17:23:20 - INFO - __main__ - Step 23373: {'lr': 0.00047471195086566035, 'samples': 4487616, 'steps': 23372, 'loss/train': 1.1675230264663696} 08/30/2021 17:23:21 - INFO - __main__ - Step 23374: {'lr': 0.000474709625076422, 'samples': 4487808, 'steps': 23373, 'loss/train': 1.4698249101638794} 08/30/2021 17:23:22 - INFO - __main__ - Step 23375: {'lr': 0.0004747072991859329, 'samples': 4488000, 'steps': 23374, 'loss/train': 1.673593282699585} 08/30/2021 17:23:22 - INFO - __main__ - Step 23376: {'lr': 0.0004747049731941942, 'samples': 4488192, 'steps': 23375, 'loss/train': 1.6737829446792603} 08/30/2021 17:23:23 - INFO - __main__ - Step 23377: {'lr': 0.0004747026471012069, 'samples': 4488384, 'steps': 23376, 'loss/train': 1.8373947143554688} 08/30/2021 17:23:23 - INFO - __main__ - Step 23378: {'lr': 0.000474700320906972, 'samples': 4488576, 'steps': 23377, 'loss/train': 0.3915119171142578} 08/30/2021 17:23:25 - INFO - __main__ - Step 23379: {'lr': 0.0004746979946114907, 'samples': 4488768, 'steps': 23378, 'loss/train': 0.2655538320541382} 08/30/2021 17:23:25 - INFO - __main__ - Step 23380: {'lr': 0.000474695668214764, 'samples': 4488960, 'steps': 23379, 'loss/train': 2.253612995147705} 08/30/2021 17:23:25 - INFO - __main__ - Step 23381: {'lr': 0.00047469334171679266, 'samples': 4489152, 'steps': 23380, 'loss/train': 2.6099472045898438} 08/30/2021 17:23:26 - INFO - __main__ - Step 23382: {'lr': 0.00047469101511757815, 'samples': 4489344, 'steps': 23381, 'loss/train': 1.9087992906570435} 08/30/2021 17:23:26 - INFO - __main__ - Step 23383: {'lr': 0.00047468868841712134, 'samples': 4489536, 'steps': 23382, 'loss/train': 1.361952543258667} 08/30/2021 17:23:28 - INFO - __main__ - Step 23384: {'lr': 0.00047468636161542325, 'samples': 4489728, 'steps': 23383, 'loss/train': 1.7354804277420044} 08/30/2021 17:23:28 - INFO - __main__ - Step 23385: {'lr': 0.0004746840347124849, 'samples': 4489920, 'steps': 23384, 'loss/train': 1.5653932094573975} 08/30/2021 17:23:28 - INFO - __main__ - Step 23386: {'lr': 0.0004746817077083074, 'samples': 4490112, 'steps': 23385, 'loss/train': 2.235689163208008} 08/30/2021 17:23:29 - INFO - __main__ - Step 23387: {'lr': 0.00047467938060289185, 'samples': 4490304, 'steps': 23386, 'loss/train': 1.6533534526824951} 08/30/2021 17:23:29 - INFO - __main__ - Step 23388: {'lr': 0.0004746770533962391, 'samples': 4490496, 'steps': 23387, 'loss/train': 1.812745213508606} 08/30/2021 17:23:29 - INFO - __main__ - Step 23389: {'lr': 0.0004746747260883505, 'samples': 4490688, 'steps': 23388, 'loss/train': 1.734961748123169} 08/30/2021 17:23:31 - INFO - __main__ - Step 23390: {'lr': 0.0004746723986792268, 'samples': 4490880, 'steps': 23389, 'loss/train': 1.3688782453536987} 08/30/2021 17:23:31 - INFO - __main__ - Step 23391: {'lr': 0.0004746700711688693, 'samples': 4491072, 'steps': 23390, 'loss/train': 1.6471861600875854} 08/30/2021 17:23:32 - INFO - __main__ - Step 23392: {'lr': 0.0004746677435572789, 'samples': 4491264, 'steps': 23391, 'loss/train': 1.8662527799606323} 08/30/2021 17:23:32 - INFO - __main__ - Step 23393: {'lr': 0.00047466541584445667, 'samples': 4491456, 'steps': 23392, 'loss/train': 1.7130470275878906} 08/30/2021 17:23:32 - INFO - __main__ - Step 23394: {'lr': 0.0004746630880304037, 'samples': 4491648, 'steps': 23393, 'loss/train': 0.8440204858779907} 08/30/2021 17:23:34 - INFO - __main__ - Step 23395: {'lr': 0.0004746607601151209, 'samples': 4491840, 'steps': 23394, 'loss/train': 1.6433444023132324} 08/30/2021 17:23:35 - INFO - __main__ - Step 23396: {'lr': 0.0004746584320986096, 'samples': 4492032, 'steps': 23395, 'loss/train': 1.9183671474456787} 08/30/2021 17:23:35 - INFO - __main__ - Step 23397: {'lr': 0.0004746561039808706, 'samples': 4492224, 'steps': 23396, 'loss/train': 1.188535451889038} 08/30/2021 17:23:35 - INFO - __main__ - Step 23398: {'lr': 0.0004746537757619049, 'samples': 4492416, 'steps': 23397, 'loss/train': 1.4544490575790405} 08/30/2021 17:23:36 - INFO - __main__ - Step 23399: {'lr': 0.00047465144744171387, 'samples': 4492608, 'steps': 23398, 'loss/train': 1.52882719039917} 08/30/2021 17:23:37 - INFO - __main__ - Step 23400: {'lr': 0.0004746491190202983, 'samples': 4492800, 'steps': 23399, 'loss/train': 1.3295679092407227} 08/30/2021 17:23:38 - INFO - __main__ - Step 23401: {'lr': 0.00047464679049765926, 'samples': 4492992, 'steps': 23400, 'loss/train': 1.7973284721374512} 08/30/2021 17:23:38 - INFO - __main__ - Step 23402: {'lr': 0.00047464446187379787, 'samples': 4493184, 'steps': 23401, 'loss/train': 1.505181074142456} 08/30/2021 17:23:39 - INFO - __main__ - Step 23403: {'lr': 0.00047464213314871514, 'samples': 4493376, 'steps': 23402, 'loss/train': 1.8122906684875488} 08/30/2021 17:23:39 - INFO - __main__ - Step 23404: {'lr': 0.0004746398043224122, 'samples': 4493568, 'steps': 23403, 'loss/train': 1.5950868129730225} 08/30/2021 17:23:41 - INFO - __main__ - Step 23405: {'lr': 0.0004746374753948899, 'samples': 4493760, 'steps': 23404, 'loss/train': 1.5152009725570679} 08/30/2021 17:23:41 - INFO - __main__ - Step 23406: {'lr': 0.00047463514636614945, 'samples': 4493952, 'steps': 23405, 'loss/train': 1.8622397184371948} 08/30/2021 17:23:42 - INFO - __main__ - Step 23407: {'lr': 0.00047463281723619203, 'samples': 4494144, 'steps': 23406, 'loss/train': 0.7602947950363159} 08/30/2021 17:23:42 - INFO - __main__ - Step 23408: {'lr': 0.00047463048800501837, 'samples': 4494336, 'steps': 23407, 'loss/train': 1.307937741279602} 08/30/2021 17:23:42 - INFO - __main__ - Step 23409: {'lr': 0.00047462815867262967, 'samples': 4494528, 'steps': 23408, 'loss/train': 2.198789358139038} 08/30/2021 17:23:44 - INFO - __main__ - Step 23410: {'lr': 0.0004746258292390271, 'samples': 4494720, 'steps': 23409, 'loss/train': 1.6767184734344482} 08/30/2021 17:23:44 - INFO - __main__ - Step 23411: {'lr': 0.00047462349970421147, 'samples': 4494912, 'steps': 23410, 'loss/train': 1.3218573331832886} 08/30/2021 17:23:45 - INFO - __main__ - Step 23412: {'lr': 0.0004746211700681841, 'samples': 4495104, 'steps': 23411, 'loss/train': 1.3264437913894653} 08/30/2021 17:23:45 - INFO - __main__ - Step 23413: {'lr': 0.0004746188403309457, 'samples': 4495296, 'steps': 23412, 'loss/train': 1.8527815341949463} 08/30/2021 17:23:45 - INFO - __main__ - Step 23414: {'lr': 0.00047461651049249764, 'samples': 4495488, 'steps': 23413, 'loss/train': 1.2875312566757202} 08/30/2021 17:23:48 - INFO - __main__ - Step 23415: {'lr': 0.0004746141805528409, 'samples': 4495680, 'steps': 23414, 'loss/train': 1.7617915868759155} 08/30/2021 17:23:48 - INFO - __main__ - Step 23416: {'lr': 0.00047461185051197644, 'samples': 4495872, 'steps': 23415, 'loss/train': 1.4624656438827515} 08/30/2021 17:23:48 - INFO - __main__ - Step 23417: {'lr': 0.0004746095203699053, 'samples': 4496064, 'steps': 23416, 'loss/train': 5.8519086837768555} 08/30/2021 17:23:49 - INFO - __main__ - Step 23418: {'lr': 0.00047460719012662857, 'samples': 4496256, 'steps': 23417, 'loss/train': 4.7854485511779785} 08/30/2021 17:23:49 - INFO - __main__ - Step 23419: {'lr': 0.00047460485978214733, 'samples': 4496448, 'steps': 23418, 'loss/train': 5.4564738273620605} 08/30/2021 17:23:49 - INFO - __main__ - Step 23420: {'lr': 0.00047460252933646265, 'samples': 4496640, 'steps': 23419, 'loss/train': 4.870734691619873} 08/30/2021 17:23:50 - INFO - __main__ - Step 23421: {'lr': 0.0004746001987895755, 'samples': 4496832, 'steps': 23420, 'loss/train': 1.6050056219100952} 08/30/2021 17:23:51 - INFO - __main__ - Step 23422: {'lr': 0.00047459786814148697, 'samples': 4497024, 'steps': 23421, 'loss/train': 1.7520097494125366} 08/30/2021 17:23:52 - INFO - __main__ - Step 23423: {'lr': 0.0004745955373921981, 'samples': 4497216, 'steps': 23422, 'loss/train': 0.8850692510604858} 08/30/2021 17:23:52 - INFO - __main__ - Step 23424: {'lr': 0.0004745932065417099, 'samples': 4497408, 'steps': 23423, 'loss/train': 1.8354878425598145} 08/30/2021 17:23:52 - INFO - __main__ - Step 23425: {'lr': 0.00047459087559002355, 'samples': 4497600, 'steps': 23424, 'loss/train': 1.7539135217666626} 08/30/2021 17:23:53 - INFO - __main__ - Step 23426: {'lr': 0.00047458854453713995, 'samples': 4497792, 'steps': 23425, 'loss/train': 1.7263280153274536} 08/30/2021 17:23:54 - INFO - __main__ - Step 23427: {'lr': 0.0004745862133830603, 'samples': 4497984, 'steps': 23426, 'loss/train': 1.466227412223816} 08/30/2021 17:23:55 - INFO - __main__ - Step 23428: {'lr': 0.00047458388212778547, 'samples': 4498176, 'steps': 23427, 'loss/train': 1.9011969566345215} 08/30/2021 17:23:55 - INFO - __main__ - Step 23429: {'lr': 0.00047458155077131664, 'samples': 4498368, 'steps': 23428, 'loss/train': 0.665778636932373} 08/30/2021 17:23:56 - INFO - __main__ - Step 23430: {'lr': 0.0004745792193136549, 'samples': 4498560, 'steps': 23429, 'loss/train': 1.4582651853561401} 08/30/2021 17:23:56 - INFO - __main__ - Step 23431: {'lr': 0.00047457688775480114, 'samples': 4498752, 'steps': 23430, 'loss/train': 2.1060478687286377} 08/30/2021 17:23:56 - INFO - __main__ - Step 23432: {'lr': 0.0004745745560947565, 'samples': 4498944, 'steps': 23431, 'loss/train': 0.9793155789375305} 08/30/2021 17:23:58 - INFO - __main__ - Step 23433: {'lr': 0.0004745722243335221, 'samples': 4499136, 'steps': 23432, 'loss/train': 1.958113670349121} 08/30/2021 17:23:59 - INFO - __main__ - Step 23434: {'lr': 0.0004745698924710988, 'samples': 4499328, 'steps': 23433, 'loss/train': 1.1268386840820312} 08/30/2021 17:23:59 - INFO - __main__ - Step 23435: {'lr': 0.00047456756050748793, 'samples': 4499520, 'steps': 23434, 'loss/train': 2.3697609901428223} 08/30/2021 17:23:59 - INFO - __main__ - Step 23436: {'lr': 0.0004745652284426903, 'samples': 4499712, 'steps': 23435, 'loss/train': 2.8915159702301025} 08/30/2021 17:24:00 - INFO - __main__ - Step 23437: {'lr': 0.00047456289627670703, 'samples': 4499904, 'steps': 23436, 'loss/train': 1.2846698760986328} 08/30/2021 17:24:01 - INFO - __main__ - Step 23438: {'lr': 0.0004745605640095392, 'samples': 4500096, 'steps': 23437, 'loss/train': 1.5122549533843994} 08/30/2021 17:24:02 - INFO - __main__ - Step 23439: {'lr': 0.00047455823164118787, 'samples': 4500288, 'steps': 23438, 'loss/train': 2.0294601917266846} 08/30/2021 17:24:02 - INFO - __main__ - Step 23440: {'lr': 0.00047455589917165406, 'samples': 4500480, 'steps': 23439, 'loss/train': 1.3264708518981934} 08/30/2021 17:24:02 - INFO - __main__ - Step 23441: {'lr': 0.00047455356660093886, 'samples': 4500672, 'steps': 23440, 'loss/train': 1.8434523344039917} 08/30/2021 17:24:03 - INFO - __main__ - Step 23442: {'lr': 0.0004745512339290432, 'samples': 4500864, 'steps': 23441, 'loss/train': 1.5019114017486572} 08/30/2021 17:24:04 - INFO - __main__ - Step 23443: {'lr': 0.00047454890115596824, 'samples': 4501056, 'steps': 23442, 'loss/train': 1.7407407760620117} 08/30/2021 17:24:05 - INFO - __main__ - Step 23444: {'lr': 0.00047454656828171504, 'samples': 4501248, 'steps': 23443, 'loss/train': 1.4007312059402466} 08/30/2021 17:24:05 - INFO - __main__ - Step 23445: {'lr': 0.0004745442353062846, 'samples': 4501440, 'steps': 23444, 'loss/train': 1.9586397409439087} 08/30/2021 17:24:05 - INFO - __main__ - Step 23446: {'lr': 0.000474541902229678, 'samples': 4501632, 'steps': 23445, 'loss/train': 0.6901741623878479} 08/30/2021 17:24:06 - INFO - __main__ - Step 23447: {'lr': 0.0004745395690518963, 'samples': 4501824, 'steps': 23446, 'loss/train': 1.9121707677841187} 08/30/2021 17:24:07 - INFO - __main__ - Step 23448: {'lr': 0.0004745372357729405, 'samples': 4502016, 'steps': 23447, 'loss/train': 1.4843432903289795} 08/30/2021 17:24:08 - INFO - __main__ - Step 23449: {'lr': 0.0004745349023928117, 'samples': 4502208, 'steps': 23448, 'loss/train': 1.4363607168197632} 08/30/2021 17:24:08 - INFO - __main__ - Step 23450: {'lr': 0.000474532568911511, 'samples': 4502400, 'steps': 23449, 'loss/train': 3.3592400550842285} 08/30/2021 17:24:09 - INFO - __main__ - Step 23451: {'lr': 0.00047453023532903927, 'samples': 4502592, 'steps': 23450, 'loss/train': 0.9863831996917725} 08/30/2021 17:24:09 - INFO - __main__ - Step 23452: {'lr': 0.00047452790164539775, 'samples': 4502784, 'steps': 23451, 'loss/train': 1.3867384195327759} 08/30/2021 17:24:09 - INFO - __main__ - Step 23453: {'lr': 0.00047452556786058744, 'samples': 4502976, 'steps': 23452, 'loss/train': 2.2206199169158936} 08/30/2021 17:24:11 - INFO - __main__ - Step 23454: {'lr': 0.0004745232339746094, 'samples': 4503168, 'steps': 23453, 'loss/train': 1.588103175163269} 08/30/2021 17:24:12 - INFO - __main__ - Step 23455: {'lr': 0.00047452089998746463, 'samples': 4503360, 'steps': 23454, 'loss/train': 1.7924898862838745} 08/30/2021 17:24:12 - INFO - __main__ - Step 23456: {'lr': 0.0004745185658991541, 'samples': 4503552, 'steps': 23455, 'loss/train': 1.5315626859664917} 08/30/2021 17:24:12 - INFO - __main__ - Step 23457: {'lr': 0.0004745162317096791, 'samples': 4503744, 'steps': 23456, 'loss/train': 1.523364782333374} 08/30/2021 17:24:13 - INFO - __main__ - Step 23458: {'lr': 0.0004745138974190405, 'samples': 4503936, 'steps': 23457, 'loss/train': 1.3494212627410889} 08/30/2021 17:24:14 - INFO - __main__ - Step 23459: {'lr': 0.0004745115630272394, 'samples': 4504128, 'steps': 23458, 'loss/train': 1.3633402585983276} 08/30/2021 17:24:15 - INFO - __main__ - Step 23460: {'lr': 0.00047450922853427686, 'samples': 4504320, 'steps': 23459, 'loss/train': 0.2803743779659271} 08/30/2021 17:24:15 - INFO - __main__ - Step 23461: {'lr': 0.0004745068939401539, 'samples': 4504512, 'steps': 23460, 'loss/train': 1.6602718830108643} 08/30/2021 17:24:16 - INFO - __main__ - Step 23462: {'lr': 0.0004745045592448717, 'samples': 4504704, 'steps': 23461, 'loss/train': 1.833642840385437} 08/30/2021 17:24:16 - INFO - __main__ - Step 23463: {'lr': 0.00047450222444843105, 'samples': 4504896, 'steps': 23462, 'loss/train': 1.7407232522964478} 08/30/2021 17:24:18 - INFO - __main__ - Step 23464: {'lr': 0.0004744998895508333, 'samples': 4505088, 'steps': 23463, 'loss/train': 1.4313862323760986} 08/30/2021 17:24:18 - INFO - __main__ - Step 23465: {'lr': 0.0004744975545520793, 'samples': 4505280, 'steps': 23464, 'loss/train': 1.3955929279327393} 08/30/2021 17:24:18 - INFO - __main__ - Step 23466: {'lr': 0.00047449521945217016, 'samples': 4505472, 'steps': 23465, 'loss/train': 0.11742239445447922} 08/30/2021 17:24:19 - INFO - __main__ - Step 23467: {'lr': 0.00047449288425110693, 'samples': 4505664, 'steps': 23466, 'loss/train': 1.964247226715088} 08/30/2021 17:24:19 - INFO - __main__ - Step 23468: {'lr': 0.00047449054894889073, 'samples': 4505856, 'steps': 23467, 'loss/train': 1.281093716621399} 08/30/2021 17:24:21 - INFO - __main__ - Step 23469: {'lr': 0.00047448821354552253, 'samples': 4506048, 'steps': 23468, 'loss/train': 1.9166456460952759} 08/30/2021 17:24:21 - INFO - __main__ - Step 23470: {'lr': 0.0004744858780410034, 'samples': 4506240, 'steps': 23469, 'loss/train': 1.4999719858169556} 08/30/2021 17:24:22 - INFO - __main__ - Step 23471: {'lr': 0.0004744835424353344, 'samples': 4506432, 'steps': 23470, 'loss/train': 1.7396823167800903} 08/30/2021 17:24:22 - INFO - __main__ - Step 23472: {'lr': 0.00047448120672851653, 'samples': 4506624, 'steps': 23471, 'loss/train': 2.032892942428589} 08/30/2021 17:24:22 - INFO - __main__ - Step 23473: {'lr': 0.0004744788709205509, 'samples': 4506816, 'steps': 23472, 'loss/train': 1.2991772890090942} 08/30/2021 17:24:23 - INFO - __main__ - Step 23474: {'lr': 0.0004744765350114386, 'samples': 4507008, 'steps': 23473, 'loss/train': 1.8414204120635986} 08/30/2021 17:24:24 - INFO - __main__ - Step 23475: {'lr': 0.00047447419900118067, 'samples': 4507200, 'steps': 23474, 'loss/train': 2.0994033813476562} 08/30/2021 17:24:25 - INFO - __main__ - Step 23476: {'lr': 0.00047447186288977804, 'samples': 4507392, 'steps': 23475, 'loss/train': 1.974700689315796} 08/30/2021 17:24:25 - INFO - __main__ - Step 23477: {'lr': 0.0004744695266772319, 'samples': 4507584, 'steps': 23476, 'loss/train': 0.30462032556533813} 08/30/2021 17:24:26 - INFO - __main__ - Step 23478: {'lr': 0.00047446719036354324, 'samples': 4507776, 'steps': 23477, 'loss/train': 1.4962259531021118} 08/30/2021 17:24:26 - INFO - __main__ - Step 23479: {'lr': 0.0004744648539487132, 'samples': 4507968, 'steps': 23478, 'loss/train': 1.6455671787261963} 08/30/2021 17:24:28 - INFO - __main__ - Step 23480: {'lr': 0.00047446251743274263, 'samples': 4508160, 'steps': 23479, 'loss/train': 1.8071171045303345} 08/30/2021 17:24:28 - INFO - __main__ - Step 23481: {'lr': 0.0004744601808156328, 'samples': 4508352, 'steps': 23480, 'loss/train': 1.5873665809631348} 08/30/2021 17:24:29 - INFO - __main__ - Step 23482: {'lr': 0.00047445784409738467, 'samples': 4508544, 'steps': 23481, 'loss/train': 1.4687551259994507} 08/30/2021 17:24:29 - INFO - __main__ - Step 23483: {'lr': 0.0004744555072779993, 'samples': 4508736, 'steps': 23482, 'loss/train': 2.1719584465026855} 08/30/2021 17:24:30 - INFO - __main__ - Step 23484: {'lr': 0.0004744531703574777, 'samples': 4508928, 'steps': 23483, 'loss/train': 1.622030258178711} 08/30/2021 17:24:30 - INFO - __main__ - Step 23485: {'lr': 0.00047445083333582104, 'samples': 4509120, 'steps': 23484, 'loss/train': 0.7606672644615173} 08/30/2021 17:24:31 - INFO - __main__ - Step 23486: {'lr': 0.00047444849621303023, 'samples': 4509312, 'steps': 23485, 'loss/train': 0.7390870451927185} 08/30/2021 17:24:32 - INFO - __main__ - Step 23487: {'lr': 0.00047444615898910644, 'samples': 4509504, 'steps': 23486, 'loss/train': 1.55876624584198} 08/30/2021 17:24:32 - INFO - __main__ - Step 23488: {'lr': 0.00047444382166405067, 'samples': 4509696, 'steps': 23487, 'loss/train': 2.046896457672119} 08/30/2021 17:24:33 - INFO - __main__ - Step 23489: {'lr': 0.0004744414842378639, 'samples': 4509888, 'steps': 23488, 'loss/train': 1.255998134613037} 08/30/2021 17:24:33 - INFO - __main__ - Step 23490: {'lr': 0.0004744391467105473, 'samples': 4510080, 'steps': 23489, 'loss/train': 1.868764042854309} 08/30/2021 17:24:35 - INFO - __main__ - Step 23491: {'lr': 0.00047443680908210194, 'samples': 4510272, 'steps': 23490, 'loss/train': 2.182711362838745} 08/30/2021 17:24:36 - INFO - __main__ - Step 23492: {'lr': 0.00047443447135252876, 'samples': 4510464, 'steps': 23491, 'loss/train': 1.7871869802474976} 08/30/2021 17:24:36 - INFO - __main__ - Step 23493: {'lr': 0.0004744321335218289, 'samples': 4510656, 'steps': 23492, 'loss/train': 1.6534804105758667} 08/30/2021 17:24:36 - INFO - __main__ - Step 23494: {'lr': 0.0004744297955900034, 'samples': 4510848, 'steps': 23493, 'loss/train': 0.16427098214626312} 08/30/2021 17:24:37 - INFO - __main__ - Step 23495: {'lr': 0.00047442745755705326, 'samples': 4511040, 'steps': 23494, 'loss/train': 0.5807023048400879} 08/30/2021 17:24:38 - INFO - __main__ - Step 23496: {'lr': 0.00047442511942297953, 'samples': 4511232, 'steps': 23495, 'loss/train': 1.61563241481781} 08/30/2021 17:24:39 - INFO - __main__ - Step 23497: {'lr': 0.00047442278118778336, 'samples': 4511424, 'steps': 23496, 'loss/train': 1.7230396270751953} 08/30/2021 17:24:39 - INFO - __main__ - Step 23498: {'lr': 0.0004744204428514658, 'samples': 4511616, 'steps': 23497, 'loss/train': 1.6623622179031372} 08/30/2021 17:24:40 - INFO - __main__ - Step 23499: {'lr': 0.00047441810441402777, 'samples': 4511808, 'steps': 23498, 'loss/train': 0.14661931991577148} 08/30/2021 17:24:40 - INFO - __main__ - Step 23500: {'lr': 0.0004744157658754704, 'samples': 4512000, 'steps': 23499, 'loss/train': 1.5369865894317627} 08/30/2021 17:24:41 - INFO - __main__ - Step 23501: {'lr': 0.0004744134272357948, 'samples': 4512192, 'steps': 23500, 'loss/train': 1.2457892894744873} 08/30/2021 17:24:42 - INFO - __main__ - Step 23502: {'lr': 0.0004744110884950019, 'samples': 4512384, 'steps': 23501, 'loss/train': 1.8913642168045044} 08/30/2021 17:24:42 - INFO - __main__ - Step 23503: {'lr': 0.00047440874965309286, 'samples': 4512576, 'steps': 23502, 'loss/train': 1.378138542175293} 08/30/2021 17:24:42 - INFO - __main__ - Step 23504: {'lr': 0.00047440641071006874, 'samples': 4512768, 'steps': 23503, 'loss/train': 1.9634078741073608} 08/30/2021 17:24:43 - INFO - __main__ - Step 23505: {'lr': 0.00047440407166593056, 'samples': 4512960, 'steps': 23504, 'loss/train': 1.6665253639221191} 08/30/2021 17:24:45 - INFO - __main__ - Step 23506: {'lr': 0.0004744017325206793, 'samples': 4513152, 'steps': 23505, 'loss/train': 1.0028982162475586} 08/30/2021 17:24:45 - INFO - __main__ - Step 23507: {'lr': 0.00047439939327431613, 'samples': 4513344, 'steps': 23506, 'loss/train': 1.8394252061843872} 08/30/2021 17:24:46 - INFO - __main__ - Step 23508: {'lr': 0.0004743970539268421, 'samples': 4513536, 'steps': 23507, 'loss/train': 1.3555352687835693} 08/30/2021 17:24:46 - INFO - __main__ - Step 23509: {'lr': 0.00047439471447825813, 'samples': 4513728, 'steps': 23508, 'loss/train': 0.9830705523490906} 08/30/2021 17:24:46 - INFO - __main__ - Step 23510: {'lr': 0.00047439237492856543, 'samples': 4513920, 'steps': 23509, 'loss/train': 1.154396891593933} 08/30/2021 17:24:47 - INFO - __main__ - Step 23511: {'lr': 0.0004743900352777649, 'samples': 4514112, 'steps': 23510, 'loss/train': 1.7377116680145264} 08/30/2021 17:24:48 - INFO - __main__ - Step 23512: {'lr': 0.0004743876955258578, 'samples': 4514304, 'steps': 23511, 'loss/train': 1.7903070449829102} 08/30/2021 17:24:49 - INFO - __main__ - Step 23513: {'lr': 0.00047438535567284504, 'samples': 4514496, 'steps': 23512, 'loss/train': 2.2499351501464844} 08/30/2021 17:24:49 - INFO - __main__ - Step 23514: {'lr': 0.00047438301571872763, 'samples': 4514688, 'steps': 23513, 'loss/train': 1.4361882209777832} 08/30/2021 17:24:49 - INFO - __main__ - Step 23515: {'lr': 0.00047438067566350675, 'samples': 4514880, 'steps': 23514, 'loss/train': 1.3551257848739624} 08/30/2021 17:24:50 - INFO - __main__ - Step 23516: {'lr': 0.00047437833550718336, 'samples': 4515072, 'steps': 23515, 'loss/train': 1.4749128818511963} 08/30/2021 17:24:51 - INFO - __main__ - Step 23517: {'lr': 0.0004743759952497586, 'samples': 4515264, 'steps': 23516, 'loss/train': 1.697044849395752} 08/30/2021 17:24:52 - INFO - __main__ - Step 23518: {'lr': 0.0004743736548912334, 'samples': 4515456, 'steps': 23517, 'loss/train': 2.0789573192596436} 08/30/2021 17:24:52 - INFO - __main__ - Step 23519: {'lr': 0.00047437131443160897, 'samples': 4515648, 'steps': 23518, 'loss/train': 1.4848761558532715} 08/30/2021 17:24:52 - INFO - __main__ - Step 23520: {'lr': 0.0004743689738708863, 'samples': 4515840, 'steps': 23519, 'loss/train': 1.4723833799362183} 08/30/2021 17:24:53 - INFO - __main__ - Step 23521: {'lr': 0.0004743666332090664, 'samples': 4516032, 'steps': 23520, 'loss/train': 2.1788690090179443} 08/30/2021 17:24:54 - INFO - __main__ - Step 23522: {'lr': 0.00047436429244615037, 'samples': 4516224, 'steps': 23521, 'loss/train': 1.716915249824524} 08/30/2021 17:24:55 - INFO - __main__ - Step 23523: {'lr': 0.0004743619515821392, 'samples': 4516416, 'steps': 23522, 'loss/train': 1.7972381114959717} 08/30/2021 17:24:55 - INFO - __main__ - Step 23524: {'lr': 0.00047435961061703403, 'samples': 4516608, 'steps': 23523, 'loss/train': 1.5950313806533813} 08/30/2021 17:24:55 - INFO - __main__ - Step 23525: {'lr': 0.00047435726955083593, 'samples': 4516800, 'steps': 23524, 'loss/train': 1.8461427688598633} 08/30/2021 17:24:56 - INFO - __main__ - Step 23526: {'lr': 0.0004743549283835459, 'samples': 4516992, 'steps': 23525, 'loss/train': 1.5676671266555786} 08/30/2021 17:24:58 - INFO - __main__ - Step 23527: {'lr': 0.00047435258711516496, 'samples': 4517184, 'steps': 23526, 'loss/train': 1.7245956659317017} 08/30/2021 17:24:58 - INFO - __main__ - Step 23528: {'lr': 0.0004743502457456942, 'samples': 4517376, 'steps': 23527, 'loss/train': 1.6351948976516724} 08/30/2021 17:24:58 - INFO - __main__ - Step 23529: {'lr': 0.0004743479042751347, 'samples': 4517568, 'steps': 23528, 'loss/train': 1.687272310256958} 08/30/2021 17:24:59 - INFO - __main__ - Step 23530: {'lr': 0.0004743455627034875, 'samples': 4517760, 'steps': 23529, 'loss/train': 1.19921875} 08/30/2021 17:24:59 - INFO - __main__ - Step 23531: {'lr': 0.0004743432210307536, 'samples': 4517952, 'steps': 23530, 'loss/train': 0.26170551776885986} 08/30/2021 17:25:01 - INFO - __main__ - Step 23532: {'lr': 0.00047434087925693415, 'samples': 4518144, 'steps': 23531, 'loss/train': 1.4048240184783936} 08/30/2021 17:25:01 - INFO - __main__ - Step 23533: {'lr': 0.00047433853738203013, 'samples': 4518336, 'steps': 23532, 'loss/train': 0.34342679381370544} 08/30/2021 17:25:02 - INFO - __main__ - Step 23534: {'lr': 0.00047433619540604264, 'samples': 4518528, 'steps': 23533, 'loss/train': 0.4432034492492676} 08/30/2021 17:25:02 - INFO - __main__ - Step 23535: {'lr': 0.0004743338533289728, 'samples': 4518720, 'steps': 23534, 'loss/train': 1.9128985404968262} 08/30/2021 17:25:02 - INFO - __main__ - Step 23536: {'lr': 0.0004743315111508215, 'samples': 4518912, 'steps': 23535, 'loss/train': 1.51212477684021} 08/30/2021 17:25:03 - INFO - __main__ - Step 23537: {'lr': 0.00047432916887158995, 'samples': 4519104, 'steps': 23536, 'loss/train': 2.5439515113830566} 08/30/2021 17:25:05 - INFO - __main__ - Step 23538: {'lr': 0.00047432682649127913, 'samples': 4519296, 'steps': 23537, 'loss/train': 1.9498885869979858} 08/30/2021 17:25:05 - INFO - __main__ - Step 23539: {'lr': 0.00047432448400989004, 'samples': 4519488, 'steps': 23538, 'loss/train': 1.6660622358322144} 08/30/2021 17:25:05 - INFO - __main__ - Step 23540: {'lr': 0.0004743221414274238, 'samples': 4519680, 'steps': 23539, 'loss/train': 0.14143574237823486} 08/30/2021 17:25:06 - INFO - __main__ - Step 23541: {'lr': 0.00047431979874388154, 'samples': 4519872, 'steps': 23540, 'loss/train': 2.1670846939086914} 08/30/2021 17:25:06 - INFO - __main__ - Step 23542: {'lr': 0.0004743174559592642, 'samples': 4520064, 'steps': 23541, 'loss/train': 0.116717129945755} 08/30/2021 17:25:07 - INFO - __main__ - Step 23543: {'lr': 0.0004743151130735729, 'samples': 4520256, 'steps': 23542, 'loss/train': 0.14372417330741882} 08/30/2021 17:25:08 - INFO - __main__ - Step 23544: {'lr': 0.0004743127700868086, 'samples': 4520448, 'steps': 23543, 'loss/train': 0.09387094527482986} 08/30/2021 17:25:09 - INFO - __main__ - Step 23545: {'lr': 0.00047431042699897245, 'samples': 4520640, 'steps': 23544, 'loss/train': 1.1553503274917603} 08/30/2021 17:25:09 - INFO - __main__ - Step 23546: {'lr': 0.0004743080838100655, 'samples': 4520832, 'steps': 23545, 'loss/train': 1.2153754234313965} 08/30/2021 17:25:09 - INFO - __main__ - Step 23547: {'lr': 0.0004743057405200888, 'samples': 4521024, 'steps': 23546, 'loss/train': 2.096493721008301} 08/30/2021 17:25:10 - INFO - __main__ - Step 23548: {'lr': 0.0004743033971290434, 'samples': 4521216, 'steps': 23547, 'loss/train': 1.7743288278579712} 08/30/2021 17:25:11 - INFO - __main__ - Step 23549: {'lr': 0.00047430105363693034, 'samples': 4521408, 'steps': 23548, 'loss/train': 1.6424707174301147} 08/30/2021 17:25:12 - INFO - __main__ - Step 23550: {'lr': 0.0004742987100437507, 'samples': 4521600, 'steps': 23549, 'loss/train': 1.471112608909607} 08/30/2021 17:25:12 - INFO - __main__ - Step 23551: {'lr': 0.00047429636634950545, 'samples': 4521792, 'steps': 23550, 'loss/train': 1.3400425910949707} 08/30/2021 17:25:12 - INFO - __main__ - Step 23552: {'lr': 0.0004742940225541958, 'samples': 4521984, 'steps': 23551, 'loss/train': 1.497818112373352} 08/30/2021 17:25:13 - INFO - __main__ - Step 23553: {'lr': 0.0004742916786578227, 'samples': 4522176, 'steps': 23552, 'loss/train': 1.3833774328231812} 08/30/2021 17:25:14 - INFO - __main__ - Step 23554: {'lr': 0.00047428933466038726, 'samples': 4522368, 'steps': 23553, 'loss/train': 1.2099409103393555} 08/30/2021 17:25:15 - INFO - __main__ - Step 23555: {'lr': 0.00047428699056189047, 'samples': 4522560, 'steps': 23554, 'loss/train': 0.5132454633712769} 08/30/2021 17:25:15 - INFO - __main__ - Step 23556: {'lr': 0.0004742846463623334, 'samples': 4522752, 'steps': 23555, 'loss/train': 1.5360429286956787} 08/30/2021 17:25:15 - INFO - __main__ - Step 23557: {'lr': 0.0004742823020617172, 'samples': 4522944, 'steps': 23556, 'loss/train': 0.2798418700695038} 08/30/2021 17:25:16 - INFO - __main__ - Step 23558: {'lr': 0.0004742799576600427, 'samples': 4523136, 'steps': 23557, 'loss/train': 1.546321153640747} 08/30/2021 17:25:16 - INFO - __main__ - Step 23559: {'lr': 0.00047427761315731133, 'samples': 4523328, 'steps': 23558, 'loss/train': 1.2455106973648071} 08/30/2021 17:25:17 - INFO - __main__ - Step 23560: {'lr': 0.0004742752685535238, 'samples': 4523520, 'steps': 23559, 'loss/train': 1.5118094682693481} 08/30/2021 17:25:18 - INFO - __main__ - Step 23561: {'lr': 0.00047427292384868134, 'samples': 4523712, 'steps': 23560, 'loss/train': 1.2776174545288086} 08/30/2021 17:25:18 - INFO - __main__ - Step 23562: {'lr': 0.0004742705790427849, 'samples': 4523904, 'steps': 23561, 'loss/train': 1.1823251247406006} 08/30/2021 17:25:19 - INFO - __main__ - Step 23563: {'lr': 0.00047426823413583563, 'samples': 4524096, 'steps': 23562, 'loss/train': 1.9637054204940796} 08/30/2021 17:25:19 - INFO - __main__ - Step 23564: {'lr': 0.0004742658891278346, 'samples': 4524288, 'steps': 23563, 'loss/train': 1.7814786434173584} 08/30/2021 17:25:21 - INFO - __main__ - Step 23565: {'lr': 0.0004742635440187828, 'samples': 4524480, 'steps': 23564, 'loss/train': 1.6499422788619995} 08/30/2021 17:25:21 - INFO - __main__ - Step 23566: {'lr': 0.00047426119880868123, 'samples': 4524672, 'steps': 23565, 'loss/train': 1.9455660581588745} 08/30/2021 17:25:21 - INFO - __main__ - Step 23567: {'lr': 0.00047425885349753114, 'samples': 4524864, 'steps': 23566, 'loss/train': 1.504725456237793} 08/30/2021 17:25:22 - INFO - __main__ - Step 23568: {'lr': 0.0004742565080853334, 'samples': 4525056, 'steps': 23567, 'loss/train': 1.4364367723464966} 08/30/2021 17:25:22 - INFO - __main__ - Step 23569: {'lr': 0.00047425416257208916, 'samples': 4525248, 'steps': 23568, 'loss/train': 2.000889778137207} 08/30/2021 17:25:24 - INFO - __main__ - Step 23570: {'lr': 0.0004742518169577994, 'samples': 4525440, 'steps': 23569, 'loss/train': 0.8818508982658386} 08/30/2021 17:25:24 - INFO - __main__ - Step 23571: {'lr': 0.0004742494712424653, 'samples': 4525632, 'steps': 23570, 'loss/train': 1.1138865947723389} 08/30/2021 17:25:24 - INFO - __main__ - Step 23572: {'lr': 0.0004742471254260878, 'samples': 4525824, 'steps': 23571, 'loss/train': 2.152121067047119} 08/30/2021 17:25:25 - INFO - __main__ - Step 23573: {'lr': 0.0004742447795086681, 'samples': 4526016, 'steps': 23572, 'loss/train': 1.2545866966247559} 08/30/2021 17:25:25 - INFO - __main__ - Step 23574: {'lr': 0.00047424243349020705, 'samples': 4526208, 'steps': 23573, 'loss/train': 1.5952011346817017} 08/30/2021 17:25:27 - INFO - __main__ - Step 23575: {'lr': 0.0004742400873707059, 'samples': 4526400, 'steps': 23574, 'loss/train': 1.7012284994125366} 08/30/2021 17:25:28 - INFO - __main__ - Step 23576: {'lr': 0.0004742377411501656, 'samples': 4526592, 'steps': 23575, 'loss/train': 1.9678068161010742} 08/30/2021 17:25:28 - INFO - __main__ - Step 23577: {'lr': 0.00047423539482858724, 'samples': 4526784, 'steps': 23576, 'loss/train': 2.030181646347046} 08/30/2021 17:25:28 - INFO - __main__ - Step 23578: {'lr': 0.0004742330484059718, 'samples': 4526976, 'steps': 23577, 'loss/train': 1.1054855585098267} 08/30/2021 17:25:29 - INFO - __main__ - Step 23579: {'lr': 0.0004742307018823205, 'samples': 4527168, 'steps': 23578, 'loss/train': 1.9471453428268433} 08/30/2021 17:25:29 - INFO - __main__ - Step 23580: {'lr': 0.0004742283552576343, 'samples': 4527360, 'steps': 23579, 'loss/train': 1.2475463151931763} 08/30/2021 17:25:31 - INFO - __main__ - Step 23581: {'lr': 0.0004742260085319142, 'samples': 4527552, 'steps': 23580, 'loss/train': 1.7846564054489136} 08/30/2021 17:25:31 - INFO - __main__ - Step 23582: {'lr': 0.0004742236617051614, 'samples': 4527744, 'steps': 23581, 'loss/train': 1.6171941757202148} 08/30/2021 17:25:31 - INFO - __main__ - Step 23583: {'lr': 0.00047422131477737684, 'samples': 4527936, 'steps': 23582, 'loss/train': 1.8229527473449707} 08/30/2021 17:25:32 - INFO - __main__ - Step 23584: {'lr': 0.00047421896774856156, 'samples': 4528128, 'steps': 23583, 'loss/train': 1.7556407451629639} 08/30/2021 17:25:32 - INFO - __main__ - Step 23585: {'lr': 0.00047421662061871675, 'samples': 4528320, 'steps': 23584, 'loss/train': 1.4895778894424438} 08/30/2021 17:25:34 - INFO - __main__ - Step 23586: {'lr': 0.0004742142733878433, 'samples': 4528512, 'steps': 23585, 'loss/train': 2.789318561553955} 08/30/2021 17:25:34 - INFO - __main__ - Step 23587: {'lr': 0.0004742119260559424, 'samples': 4528704, 'steps': 23586, 'loss/train': 1.1185063123703003} 08/30/2021 17:25:35 - INFO - __main__ - Step 23588: {'lr': 0.0004742095786230152, 'samples': 4528896, 'steps': 23587, 'loss/train': 1.6517226696014404} 08/30/2021 17:25:35 - INFO - __main__ - Step 23589: {'lr': 0.00047420723108906247, 'samples': 4529088, 'steps': 23588, 'loss/train': 1.8413761854171753} 08/30/2021 17:25:35 - INFO - __main__ - Step 23590: {'lr': 0.0004742048834540855, 'samples': 4529280, 'steps': 23589, 'loss/train': 1.9400454759597778} 08/30/2021 17:25:36 - INFO - __main__ - Step 23591: {'lr': 0.0004742025357180852, 'samples': 4529472, 'steps': 23590, 'loss/train': 1.9612764120101929} 08/30/2021 17:25:37 - INFO - __main__ - Step 23592: {'lr': 0.00047420018788106274, 'samples': 4529664, 'steps': 23591, 'loss/train': 1.7768454551696777} 08/30/2021 17:25:38 - INFO - __main__ - Step 23593: {'lr': 0.00047419783994301915, 'samples': 4529856, 'steps': 23592, 'loss/train': 1.7378946542739868} 08/30/2021 17:25:38 - INFO - __main__ - Step 23594: {'lr': 0.0004741954919039554, 'samples': 4530048, 'steps': 23593, 'loss/train': 1.406349539756775} 08/30/2021 17:25:38 - INFO - __main__ - Step 23595: {'lr': 0.0004741931437638727, 'samples': 4530240, 'steps': 23594, 'loss/train': 1.4765241146087646} 08/30/2021 17:25:39 - INFO - __main__ - Step 23596: {'lr': 0.000474190795522772, 'samples': 4530432, 'steps': 23595, 'loss/train': 2.1187362670898438} 08/30/2021 17:25:40 - INFO - __main__ - Step 23597: {'lr': 0.00047418844718065433, 'samples': 4530624, 'steps': 23596, 'loss/train': 0.4812004864215851} 08/30/2021 17:25:41 - INFO - __main__ - Step 23598: {'lr': 0.0004741860987375209, 'samples': 4530816, 'steps': 23597, 'loss/train': 1.5386368036270142} 08/30/2021 17:25:41 - INFO - __main__ - Step 23599: {'lr': 0.00047418375019337263, 'samples': 4531008, 'steps': 23598, 'loss/train': 1.9456770420074463} 08/30/2021 17:25:41 - INFO - __main__ - Step 23600: {'lr': 0.00047418140154821065, 'samples': 4531200, 'steps': 23599, 'loss/train': 1.0276881456375122} 08/30/2021 17:25:42 - INFO - __main__ - Step 23601: {'lr': 0.00047417905280203594, 'samples': 4531392, 'steps': 23600, 'loss/train': 1.151970624923706} 08/30/2021 17:25:43 - INFO - __main__ - Step 23602: {'lr': 0.00047417670395484963, 'samples': 4531584, 'steps': 23601, 'loss/train': 1.806605339050293} 08/30/2021 17:25:44 - INFO - __main__ - Step 23603: {'lr': 0.0004741743550066527, 'samples': 4531776, 'steps': 23602, 'loss/train': 1.379116415977478} 08/30/2021 17:25:44 - INFO - __main__ - Step 23604: {'lr': 0.00047417200595744637, 'samples': 4531968, 'steps': 23603, 'loss/train': 1.7826013565063477} 08/30/2021 17:25:44 - INFO - __main__ - Step 23605: {'lr': 0.0004741696568072316, 'samples': 4532160, 'steps': 23604, 'loss/train': 1.6874490976333618} 08/30/2021 17:25:45 - INFO - __main__ - Step 23606: {'lr': 0.00047416730755600936, 'samples': 4532352, 'steps': 23605, 'loss/train': 1.602535605430603} 08/30/2021 17:25:46 - INFO - __main__ - Step 23607: {'lr': 0.0004741649582037808, 'samples': 4532544, 'steps': 23606, 'loss/train': 3.4111196994781494} 08/30/2021 17:25:47 - INFO - __main__ - Step 23608: {'lr': 0.000474162608750547, 'samples': 4532736, 'steps': 23607, 'loss/train': 1.413873314857483} 08/30/2021 17:25:47 - INFO - __main__ - Step 23609: {'lr': 0.000474160259196309, 'samples': 4532928, 'steps': 23608, 'loss/train': 1.287006139755249} 08/30/2021 17:25:48 - INFO - __main__ - Step 23610: {'lr': 0.0004741579095410678, 'samples': 4533120, 'steps': 23609, 'loss/train': 2.030071496963501} 08/30/2021 17:25:48 - INFO - __main__ - Step 23611: {'lr': 0.0004741555597848245, 'samples': 4533312, 'steps': 23610, 'loss/train': 2.079184055328369} 08/30/2021 17:25:50 - INFO - __main__ - Step 23612: {'lr': 0.00047415320992758025, 'samples': 4533504, 'steps': 23611, 'loss/train': 2.58381724357605} 08/30/2021 17:25:50 - INFO - __main__ - Step 23613: {'lr': 0.00047415085996933593, 'samples': 4533696, 'steps': 23612, 'loss/train': 1.6858973503112793} 08/30/2021 17:25:50 - INFO - __main__ - Step 23614: {'lr': 0.00047414850991009275, 'samples': 4533888, 'steps': 23613, 'loss/train': 1.6573758125305176} 08/30/2021 17:25:51 - INFO - __main__ - Step 23615: {'lr': 0.00047414615974985164, 'samples': 4534080, 'steps': 23614, 'loss/train': 1.5540821552276611} 08/30/2021 17:25:51 - INFO - __main__ - Step 23616: {'lr': 0.0004741438094886138, 'samples': 4534272, 'steps': 23615, 'loss/train': 1.774855375289917} 08/30/2021 17:25:51 - INFO - __main__ - Step 23617: {'lr': 0.00047414145912638017, 'samples': 4534464, 'steps': 23616, 'loss/train': 1.572225570678711} 08/30/2021 17:25:53 - INFO - __main__ - Step 23618: {'lr': 0.00047413910866315193, 'samples': 4534656, 'steps': 23617, 'loss/train': 1.414900541305542} 08/30/2021 17:25:53 - INFO - __main__ - Step 23619: {'lr': 0.00047413675809893, 'samples': 4534848, 'steps': 23618, 'loss/train': 1.2714629173278809} 08/30/2021 17:25:54 - INFO - __main__ - Step 23620: {'lr': 0.0004741344074337155, 'samples': 4535040, 'steps': 23619, 'loss/train': 1.5200704336166382} 08/30/2021 17:25:54 - INFO - __main__ - Step 23621: {'lr': 0.00047413205666750955, 'samples': 4535232, 'steps': 23620, 'loss/train': 1.6622098684310913} 08/30/2021 17:25:55 - INFO - __main__ - Step 23622: {'lr': 0.0004741297058003131, 'samples': 4535424, 'steps': 23621, 'loss/train': 2.0289008617401123} 08/30/2021 17:25:56 - INFO - __main__ - Step 23623: {'lr': 0.00047412735483212725, 'samples': 4535616, 'steps': 23622, 'loss/train': 1.5492668151855469} 08/30/2021 17:25:56 - INFO - __main__ - Step 23624: {'lr': 0.0004741250037629531, 'samples': 4535808, 'steps': 23623, 'loss/train': 1.347144603729248} 08/30/2021 17:25:57 - INFO - __main__ - Step 23625: {'lr': 0.00047412265259279176, 'samples': 4536000, 'steps': 23624, 'loss/train': 1.609100103378296} 08/30/2021 17:25:57 - INFO - __main__ - Step 23626: {'lr': 0.0004741203013216441, 'samples': 4536192, 'steps': 23625, 'loss/train': 1.5195554494857788} 08/30/2021 17:25:57 - INFO - __main__ - Step 23627: {'lr': 0.0004741179499495113, 'samples': 4536384, 'steps': 23626, 'loss/train': 1.8828595876693726} 08/30/2021 17:26:00 - INFO - __main__ - Step 23628: {'lr': 0.00047411559847639447, 'samples': 4536576, 'steps': 23627, 'loss/train': 1.3689078092575073} 08/30/2021 17:26:00 - INFO - __main__ - Step 23629: {'lr': 0.0004741132469022946, 'samples': 4536768, 'steps': 23628, 'loss/train': 6.122838973999023} 08/30/2021 17:26:01 - INFO - __main__ - Step 23630: {'lr': 0.00047411089522721275, 'samples': 4536960, 'steps': 23629, 'loss/train': 1.442733645439148} 08/30/2021 17:26:01 - INFO - __main__ - Step 23631: {'lr': 0.00047410854345114996, 'samples': 4537152, 'steps': 23630, 'loss/train': 1.2228111028671265} 08/30/2021 17:26:01 - INFO - __main__ - Step 23632: {'lr': 0.0004741061915741073, 'samples': 4537344, 'steps': 23631, 'loss/train': 2.2163054943084717} 08/30/2021 17:26:02 - INFO - __main__ - Step 23633: {'lr': 0.0004741038395960859, 'samples': 4537536, 'steps': 23632, 'loss/train': 0.09782514721155167} 08/30/2021 17:26:03 - INFO - __main__ - Step 23634: {'lr': 0.0004741014875170867, 'samples': 4537728, 'steps': 23633, 'loss/train': 2.023845672607422} 08/30/2021 17:26:04 - INFO - __main__ - Step 23635: {'lr': 0.0004740991353371109, 'samples': 4537920, 'steps': 23634, 'loss/train': 1.860496163368225} 08/30/2021 17:26:04 - INFO - __main__ - Step 23636: {'lr': 0.0004740967830561595, 'samples': 4538112, 'steps': 23635, 'loss/train': 1.764891505241394} 08/30/2021 17:26:04 - INFO - __main__ - Step 23637: {'lr': 0.0004740944306742335, 'samples': 4538304, 'steps': 23636, 'loss/train': 1.920194387435913} 08/30/2021 17:26:05 - INFO - __main__ - Step 23638: {'lr': 0.00047409207819133406, 'samples': 4538496, 'steps': 23637, 'loss/train': 1.4395520687103271} 08/30/2021 17:26:06 - INFO - __main__ - Step 23639: {'lr': 0.0004740897256074621, 'samples': 4538688, 'steps': 23638, 'loss/train': 1.7058806419372559} 08/30/2021 17:26:07 - INFO - __main__ - Step 23640: {'lr': 0.00047408737292261883, 'samples': 4538880, 'steps': 23639, 'loss/train': 1.8294278383255005} 08/30/2021 17:26:07 - INFO - __main__ - Step 23641: {'lr': 0.0004740850201368052, 'samples': 4539072, 'steps': 23640, 'loss/train': 1.08510160446167} 08/30/2021 17:26:07 - INFO - __main__ - Step 23642: {'lr': 0.00047408266725002234, 'samples': 4539264, 'steps': 23641, 'loss/train': 1.2237006425857544} 08/30/2021 17:26:08 - INFO - __main__ - Step 23643: {'lr': 0.00047408031426227136, 'samples': 4539456, 'steps': 23642, 'loss/train': 1.8229749202728271} 08/30/2021 17:26:09 - INFO - __main__ - Step 23644: {'lr': 0.0004740779611735532, 'samples': 4539648, 'steps': 23643, 'loss/train': 1.9241870641708374} 08/30/2021 17:26:10 - INFO - __main__ - Step 23645: {'lr': 0.00047407560798386894, 'samples': 4539840, 'steps': 23644, 'loss/train': 1.0174429416656494} 08/30/2021 17:26:10 - INFO - __main__ - Step 23646: {'lr': 0.00047407325469321973, 'samples': 4540032, 'steps': 23645, 'loss/train': 1.2745970487594604} 08/30/2021 17:26:10 - INFO - __main__ - Step 23647: {'lr': 0.0004740709013016065, 'samples': 4540224, 'steps': 23646, 'loss/train': 1.042733073234558} 08/30/2021 17:26:11 - INFO - __main__ - Step 23648: {'lr': 0.0004740685478090304, 'samples': 4540416, 'steps': 23647, 'loss/train': 1.7291159629821777} 08/30/2021 17:26:13 - INFO - __main__ - Step 23649: {'lr': 0.00047406619421549247, 'samples': 4540608, 'steps': 23648, 'loss/train': 1.4979697465896606} 08/30/2021 17:26:13 - INFO - __main__ - Step 23650: {'lr': 0.0004740638405209938, 'samples': 4540800, 'steps': 23649, 'loss/train': 1.1898342370986938} 08/30/2021 17:26:13 - INFO - __main__ - Step 23651: {'lr': 0.0004740614867255353, 'samples': 4540992, 'steps': 23650, 'loss/train': 0.5996770858764648} 08/30/2021 17:26:14 - INFO - __main__ - Step 23652: {'lr': 0.0004740591328291183, 'samples': 4541184, 'steps': 23651, 'loss/train': 1.409492015838623} 08/30/2021 17:26:14 - INFO - __main__ - Step 23653: {'lr': 0.0004740567788317437, 'samples': 4541376, 'steps': 23652, 'loss/train': 1.5661993026733398} 08/30/2021 17:26:14 - INFO - __main__ - Step 23654: {'lr': 0.00047405442473341246, 'samples': 4541568, 'steps': 23653, 'loss/train': 5.594666481018066} 08/30/2021 17:26:15 - INFO - __main__ - Step 23655: {'lr': 0.0004740520705341259, 'samples': 4541760, 'steps': 23654, 'loss/train': 6.806138515472412} 08/30/2021 17:26:16 - INFO - __main__ - Step 23656: {'lr': 0.0004740497162338848, 'samples': 4541952, 'steps': 23655, 'loss/train': 1.7770015001296997} 08/30/2021 17:26:17 - INFO - __main__ - Step 23657: {'lr': 0.00047404736183269045, 'samples': 4542144, 'steps': 23656, 'loss/train': 1.4531251192092896} 08/30/2021 17:26:17 - INFO - __main__ - Step 23658: {'lr': 0.0004740450073305438, 'samples': 4542336, 'steps': 23657, 'loss/train': 1.4769870042800903} 08/30/2021 17:26:17 - INFO - __main__ - Step 23659: {'lr': 0.00047404265272744586, 'samples': 4542528, 'steps': 23658, 'loss/train': 1.9212251901626587} 08/30/2021 17:26:18 - INFO - __main__ - Step 23660: {'lr': 0.0004740402980233978, 'samples': 4542720, 'steps': 23659, 'loss/train': 1.7518775463104248} 08/30/2021 17:26:19 - INFO - __main__ - Step 23661: {'lr': 0.00047403794321840064, 'samples': 4542912, 'steps': 23660, 'loss/train': 2.1008946895599365} 08/30/2021 17:26:20 - INFO - __main__ - Step 23662: {'lr': 0.0004740355883124555, 'samples': 4543104, 'steps': 23661, 'loss/train': 1.7716931104660034} 08/30/2021 17:26:20 - INFO - __main__ - Step 23663: {'lr': 0.0004740332333055633, 'samples': 4543296, 'steps': 23662, 'loss/train': 1.3145335912704468} 08/30/2021 17:26:20 - INFO - __main__ - Step 23664: {'lr': 0.00047403087819772517, 'samples': 4543488, 'steps': 23663, 'loss/train': 2.1947436332702637} 08/30/2021 17:26:21 - INFO - __main__ - Step 23665: {'lr': 0.0004740285229889423, 'samples': 4543680, 'steps': 23664, 'loss/train': 1.6230443716049194} 08/30/2021 17:26:22 - INFO - __main__ - Step 23666: {'lr': 0.0004740261676792155, 'samples': 4543872, 'steps': 23665, 'loss/train': 1.6724753379821777} 08/30/2021 17:26:23 - INFO - __main__ - Step 23667: {'lr': 0.00047402381226854606, 'samples': 4544064, 'steps': 23666, 'loss/train': 1.950594186782837} 08/30/2021 17:26:23 - INFO - __main__ - Step 23668: {'lr': 0.0004740214567569349, 'samples': 4544256, 'steps': 23667, 'loss/train': 1.1832435131072998} 08/30/2021 17:26:23 - INFO - __main__ - Step 23669: {'lr': 0.00047401910114438313, 'samples': 4544448, 'steps': 23668, 'loss/train': 0.7969381809234619} 08/30/2021 17:26:24 - INFO - __main__ - Step 23670: {'lr': 0.0004740167454308918, 'samples': 4544640, 'steps': 23669, 'loss/train': 1.410292148590088} 08/30/2021 17:26:25 - INFO - __main__ - Step 23671: {'lr': 0.00047401438961646206, 'samples': 4544832, 'steps': 23670, 'loss/train': 1.860082983970642} 08/30/2021 17:26:26 - INFO - __main__ - Step 23672: {'lr': 0.0004740120337010948, 'samples': 4545024, 'steps': 23671, 'loss/train': 1.6472742557525635} 08/30/2021 17:26:26 - INFO - __main__ - Step 23673: {'lr': 0.0004740096776847912, 'samples': 4545216, 'steps': 23672, 'loss/train': 0.9796372056007385} 08/30/2021 17:26:26 - INFO - __main__ - Step 23674: {'lr': 0.0004740073215675523, 'samples': 4545408, 'steps': 23673, 'loss/train': 1.9655559062957764} 08/30/2021 17:26:27 - INFO - __main__ - Step 23675: {'lr': 0.00047400496534937914, 'samples': 4545600, 'steps': 23674, 'loss/train': 1.719420075416565} 08/30/2021 17:26:27 - INFO - __main__ - Step 23676: {'lr': 0.00047400260903027283, 'samples': 4545792, 'steps': 23675, 'loss/train': 0.5504816770553589} 08/30/2021 17:26:29 - INFO - __main__ - Step 23677: {'lr': 0.0004740002526102344, 'samples': 4545984, 'steps': 23676, 'loss/train': 0.38618308305740356} 08/30/2021 17:26:29 - INFO - __main__ - Step 23678: {'lr': 0.0004739978960892649, 'samples': 4546176, 'steps': 23677, 'loss/train': 1.6172184944152832} 08/30/2021 17:26:30 - INFO - __main__ - Step 23679: {'lr': 0.0004739955394673654, 'samples': 4546368, 'steps': 23678, 'loss/train': 1.553303837776184} 08/30/2021 17:26:30 - INFO - __main__ - Step 23680: {'lr': 0.000473993182744537, 'samples': 4546560, 'steps': 23679, 'loss/train': 1.5233919620513916} 08/30/2021 17:26:30 - INFO - __main__ - Step 23681: {'lr': 0.0004739908259207807, 'samples': 4546752, 'steps': 23680, 'loss/train': 0.3007315993309021} 08/30/2021 17:26:32 - INFO - __main__ - Step 23682: {'lr': 0.00047398846899609755, 'samples': 4546944, 'steps': 23681, 'loss/train': 6.533685684204102} 08/30/2021 17:26:33 - INFO - __main__ - Step 23683: {'lr': 0.0004739861119704887, 'samples': 4547136, 'steps': 23682, 'loss/train': 1.275080919265747} 08/30/2021 17:26:33 - INFO - __main__ - Step 23684: {'lr': 0.00047398375484395517, 'samples': 4547328, 'steps': 23683, 'loss/train': 1.5425148010253906} 08/30/2021 17:26:33 - INFO - __main__ - Step 23685: {'lr': 0.00047398139761649794, 'samples': 4547520, 'steps': 23684, 'loss/train': 1.7344295978546143} 08/30/2021 17:26:34 - INFO - __main__ - Step 23686: {'lr': 0.00047397904028811824, 'samples': 4547712, 'steps': 23685, 'loss/train': 1.391536831855774} 08/30/2021 17:26:34 - INFO - __main__ - Step 23687: {'lr': 0.000473976682858817, 'samples': 4547904, 'steps': 23686, 'loss/train': 2.121718645095825} 08/30/2021 17:26:36 - INFO - __main__ - Step 23688: {'lr': 0.00047397432532859533, 'samples': 4548096, 'steps': 23687, 'loss/train': 1.1281750202178955} 08/30/2021 17:26:36 - INFO - __main__ - Step 23689: {'lr': 0.00047397196769745435, 'samples': 4548288, 'steps': 23688, 'loss/train': 1.6202231645584106} 08/30/2021 17:26:36 - INFO - __main__ - Step 23690: {'lr': 0.00047396960996539495, 'samples': 4548480, 'steps': 23689, 'loss/train': 1.5830765962600708} 08/30/2021 17:26:37 - INFO - __main__ - Step 23691: {'lr': 0.00047396725213241835, 'samples': 4548672, 'steps': 23690, 'loss/train': 1.1786617040634155} 08/30/2021 17:26:37 - INFO - __main__ - Step 23692: {'lr': 0.0004739648941985256, 'samples': 4548864, 'steps': 23691, 'loss/train': 1.6706563234329224} 08/30/2021 17:26:38 - INFO - __main__ - Step 23693: {'lr': 0.00047396253616371767, 'samples': 4549056, 'steps': 23692, 'loss/train': 1.6007726192474365} 08/30/2021 17:26:39 - INFO - __main__ - Step 23694: {'lr': 0.00047396017802799566, 'samples': 4549248, 'steps': 23693, 'loss/train': 1.8842920064926147} 08/30/2021 17:26:39 - INFO - __main__ - Step 23695: {'lr': 0.0004739578197913607, 'samples': 4549440, 'steps': 23694, 'loss/train': 1.7273802757263184} 08/30/2021 17:26:40 - INFO - __main__ - Step 23696: {'lr': 0.00047395546145381377, 'samples': 4549632, 'steps': 23695, 'loss/train': 1.6088329553604126} 08/30/2021 17:26:40 - INFO - __main__ - Step 23697: {'lr': 0.000473953103015356, 'samples': 4549824, 'steps': 23696, 'loss/train': 2.488471508026123} 08/30/2021 17:26:41 - INFO - __main__ - Step 23698: {'lr': 0.0004739507444759884, 'samples': 4550016, 'steps': 23697, 'loss/train': 1.784038782119751} 08/30/2021 17:26:42 - INFO - __main__ - Step 23699: {'lr': 0.0004739483858357121, 'samples': 4550208, 'steps': 23698, 'loss/train': 1.3716033697128296} 08/30/2021 17:26:42 - INFO - __main__ - Step 23700: {'lr': 0.00047394602709452806, 'samples': 4550400, 'steps': 23699, 'loss/train': 1.6060470342636108} 08/30/2021 17:26:43 - INFO - __main__ - Step 23701: {'lr': 0.0004739436682524373, 'samples': 4550592, 'steps': 23700, 'loss/train': 1.7302641868591309} 08/30/2021 17:26:43 - INFO - __main__ - Step 23702: {'lr': 0.00047394130930944115, 'samples': 4550784, 'steps': 23701, 'loss/train': 1.2669318914413452} 08/30/2021 17:26:45 - INFO - __main__ - Step 23703: {'lr': 0.0004739389502655404, 'samples': 4550976, 'steps': 23702, 'loss/train': 1.8177402019500732} 08/30/2021 17:26:45 - INFO - __main__ - Step 23704: {'lr': 0.0004739365911207363, 'samples': 4551168, 'steps': 23703, 'loss/train': 1.7356849908828735} 08/30/2021 17:26:45 - INFO - __main__ - Step 23705: {'lr': 0.0004739342318750297, 'samples': 4551360, 'steps': 23704, 'loss/train': 2.165408134460449} 08/30/2021 17:26:46 - INFO - __main__ - Step 23706: {'lr': 0.00047393187252842183, 'samples': 4551552, 'steps': 23705, 'loss/train': 1.984107255935669} 08/30/2021 17:26:46 - INFO - __main__ - Step 23707: {'lr': 0.0004739295130809138, 'samples': 4551744, 'steps': 23706, 'loss/train': 1.9873802661895752} 08/30/2021 17:26:47 - INFO - __main__ - Step 23708: {'lr': 0.0004739271535325065, 'samples': 4551936, 'steps': 23707, 'loss/train': 1.2757214307785034} 08/30/2021 17:26:48 - INFO - __main__ - Step 23709: {'lr': 0.00047392479388320106, 'samples': 4552128, 'steps': 23708, 'loss/train': 1.105953574180603} 08/30/2021 17:26:48 - INFO - __main__ - Step 23710: {'lr': 0.0004739224341329987, 'samples': 4552320, 'steps': 23709, 'loss/train': 1.5607233047485352} 08/30/2021 17:26:49 - INFO - __main__ - Step 23711: {'lr': 0.0004739200742819002, 'samples': 4552512, 'steps': 23710, 'loss/train': 2.1628360748291016} 08/30/2021 17:26:49 - INFO - __main__ - Step 23712: {'lr': 0.0004739177143299068, 'samples': 4552704, 'steps': 23711, 'loss/train': 1.4729646444320679} 08/30/2021 17:26:49 - INFO - __main__ - Step 23713: {'lr': 0.00047391535427701966, 'samples': 4552896, 'steps': 23712, 'loss/train': 1.4183703660964966} 08/30/2021 17:26:51 - INFO - __main__ - Step 23714: {'lr': 0.0004739129941232396, 'samples': 4553088, 'steps': 23713, 'loss/train': 1.4096698760986328} 08/30/2021 17:26:51 - INFO - __main__ - Step 23715: {'lr': 0.0004739106338685678, 'samples': 4553280, 'steps': 23714, 'loss/train': 1.3374930620193481} 08/30/2021 17:26:52 - INFO - __main__ - Step 23716: {'lr': 0.00047390827351300537, 'samples': 4553472, 'steps': 23715, 'loss/train': 1.6537529230117798} 08/30/2021 17:26:52 - INFO - __main__ - Step 23717: {'lr': 0.00047390591305655327, 'samples': 4553664, 'steps': 23716, 'loss/train': 1.4693373441696167} 08/30/2021 17:26:52 - INFO - __main__ - Step 23718: {'lr': 0.0004739035524992127, 'samples': 4553856, 'steps': 23717, 'loss/train': 1.6239254474639893} 08/30/2021 17:26:54 - INFO - __main__ - Step 23719: {'lr': 0.00047390119184098455, 'samples': 4554048, 'steps': 23718, 'loss/train': 1.8840086460113525} 08/30/2021 17:26:55 - INFO - __main__ - Step 23720: {'lr': 0.00047389883108187004, 'samples': 4554240, 'steps': 23719, 'loss/train': 0.38106250762939453} 08/30/2021 17:26:55 - INFO - __main__ - Step 23721: {'lr': 0.00047389647022187014, 'samples': 4554432, 'steps': 23720, 'loss/train': 1.8415324687957764} 08/30/2021 17:26:55 - INFO - __main__ - Step 23722: {'lr': 0.000473894109260986, 'samples': 4554624, 'steps': 23721, 'loss/train': 1.9239407777786255} 08/30/2021 17:26:56 - INFO - __main__ - Step 23723: {'lr': 0.00047389174819921856, 'samples': 4554816, 'steps': 23722, 'loss/train': 0.0727807879447937} 08/30/2021 17:26:56 - INFO - __main__ - Step 23724: {'lr': 0.000473889387036569, 'samples': 4555008, 'steps': 23723, 'loss/train': 1.2444167137145996} 08/30/2021 17:26:57 - INFO - __main__ - Step 23725: {'lr': 0.0004738870257730383, 'samples': 4555200, 'steps': 23724, 'loss/train': 1.8511418104171753} 08/30/2021 17:26:58 - INFO - __main__ - Step 23726: {'lr': 0.00047388466440862755, 'samples': 4555392, 'steps': 23725, 'loss/train': 1.8768689632415771} 08/30/2021 17:26:58 - INFO - __main__ - Step 23727: {'lr': 0.0004738823029433379, 'samples': 4555584, 'steps': 23726, 'loss/train': 1.9509973526000977} 08/30/2021 17:26:59 - INFO - __main__ - Step 23728: {'lr': 0.0004738799413771703, 'samples': 4555776, 'steps': 23727, 'loss/train': 1.3229200839996338} 08/30/2021 17:26:59 - INFO - __main__ - Step 23729: {'lr': 0.0004738775797101258, 'samples': 4555968, 'steps': 23728, 'loss/train': 1.505495548248291} 08/30/2021 17:27:01 - INFO - __main__ - Step 23730: {'lr': 0.0004738752179422056, 'samples': 4556160, 'steps': 23729, 'loss/train': 1.695680022239685} 08/30/2021 17:27:01 - INFO - __main__ - Step 23731: {'lr': 0.00047387285607341064, 'samples': 4556352, 'steps': 23730, 'loss/train': 1.7703814506530762} 08/30/2021 17:27:01 - INFO - __main__ - Step 23732: {'lr': 0.00047387049410374207, 'samples': 4556544, 'steps': 23731, 'loss/train': 1.450698971748352} 08/30/2021 17:27:02 - INFO - __main__ - Step 23733: {'lr': 0.00047386813203320084, 'samples': 4556736, 'steps': 23732, 'loss/train': 1.589904546737671} 08/30/2021 17:27:02 - INFO - __main__ - Step 23734: {'lr': 0.0004738657698617881, 'samples': 4556928, 'steps': 23733, 'loss/train': 1.4130483865737915} 08/30/2021 17:27:05 - INFO - __main__ - Step 23735: {'lr': 0.00047386340758950494, 'samples': 4557120, 'steps': 23734, 'loss/train': 1.88881254196167} 08/30/2021 17:27:05 - INFO - __main__ - Step 23736: {'lr': 0.0004738610452163523, 'samples': 4557312, 'steps': 23735, 'loss/train': 2.1662113666534424} 08/30/2021 17:27:05 - INFO - __main__ - Step 23737: {'lr': 0.00047385868274233144, 'samples': 4557504, 'steps': 23736, 'loss/train': 2.7109947204589844} 08/30/2021 17:27:06 - INFO - __main__ - Step 23738: {'lr': 0.0004738563201674432, 'samples': 4557696, 'steps': 23737, 'loss/train': 1.4272804260253906} 08/30/2021 17:27:06 - INFO - __main__ - Step 23739: {'lr': 0.00047385395749168885, 'samples': 4557888, 'steps': 23738, 'loss/train': 1.6467515230178833} 08/30/2021 17:27:06 - INFO - __main__ - Step 23740: {'lr': 0.00047385159471506936, 'samples': 4558080, 'steps': 23739, 'loss/train': 1.569273829460144} 08/30/2021 17:27:08 - INFO - __main__ - Step 23741: {'lr': 0.00047384923183758573, 'samples': 4558272, 'steps': 23740, 'loss/train': 0.1312096118927002} 08/30/2021 17:27:09 - INFO - __main__ - Step 23742: {'lr': 0.0004738468688592391, 'samples': 4558464, 'steps': 23741, 'loss/train': 1.763966679573059} 08/30/2021 17:27:09 - INFO - __main__ - Step 23743: {'lr': 0.00047384450578003055, 'samples': 4558656, 'steps': 23742, 'loss/train': 1.6272128820419312} 08/30/2021 17:27:09 - INFO - __main__ - Step 23744: {'lr': 0.00047384214259996117, 'samples': 4558848, 'steps': 23743, 'loss/train': 1.6774150133132935} 08/30/2021 17:27:10 - INFO - __main__ - Step 23745: {'lr': 0.0004738397793190319, 'samples': 4559040, 'steps': 23744, 'loss/train': 1.3481712341308594} 08/30/2021 17:27:11 - INFO - __main__ - Step 23746: {'lr': 0.00047383741593724386, 'samples': 4559232, 'steps': 23745, 'loss/train': 1.5829099416732788} 08/30/2021 17:27:12 - INFO - __main__ - Step 23747: {'lr': 0.0004738350524545982, 'samples': 4559424, 'steps': 23746, 'loss/train': 1.2665964365005493} 08/30/2021 17:27:12 - INFO - __main__ - Step 23748: {'lr': 0.0004738326888710959, 'samples': 4559616, 'steps': 23747, 'loss/train': 1.731207013130188} 08/30/2021 17:27:12 - INFO - __main__ - Step 23749: {'lr': 0.000473830325186738, 'samples': 4559808, 'steps': 23748, 'loss/train': 1.6543854475021362} 08/30/2021 17:27:13 - INFO - __main__ - Step 23750: {'lr': 0.0004738279614015257, 'samples': 4560000, 'steps': 23749, 'loss/train': 1.592079758644104} 08/30/2021 17:27:15 - INFO - __main__ - Step 23751: {'lr': 0.0004738255975154599, 'samples': 4560192, 'steps': 23750, 'loss/train': 1.4464178085327148} 08/30/2021 17:27:15 - INFO - __main__ - Step 23752: {'lr': 0.0004738232335285417, 'samples': 4560384, 'steps': 23751, 'loss/train': 1.5318843126296997} 08/30/2021 17:27:16 - INFO - __main__ - Step 23753: {'lr': 0.0004738208694407723, 'samples': 4560576, 'steps': 23752, 'loss/train': 1.4185625314712524} 08/30/2021 17:27:16 - INFO - __main__ - Step 23754: {'lr': 0.00047381850525215265, 'samples': 4560768, 'steps': 23753, 'loss/train': 0.732387363910675} 08/30/2021 17:27:16 - INFO - __main__ - Step 23755: {'lr': 0.0004738161409626838, 'samples': 4560960, 'steps': 23754, 'loss/train': 0.6555193066596985} 08/30/2021 17:27:18 - INFO - __main__ - Step 23756: {'lr': 0.0004738137765723669, 'samples': 4561152, 'steps': 23755, 'loss/train': 1.698353886604309} 08/30/2021 17:27:18 - INFO - __main__ - Step 23757: {'lr': 0.0004738114120812029, 'samples': 4561344, 'steps': 23756, 'loss/train': 1.4144833087921143} 08/30/2021 17:27:19 - INFO - __main__ - Step 23758: {'lr': 0.000473809047489193, 'samples': 4561536, 'steps': 23757, 'loss/train': 1.623138189315796} 08/30/2021 17:27:19 - INFO - __main__ - Step 23759: {'lr': 0.00047380668279633814, 'samples': 4561728, 'steps': 23758, 'loss/train': 1.5347778797149658} 08/30/2021 17:27:19 - INFO - __main__ - Step 23760: {'lr': 0.00047380431800263945, 'samples': 4561920, 'steps': 23759, 'loss/train': 1.3153525590896606} 08/30/2021 17:27:20 - INFO - __main__ - Step 23761: {'lr': 0.000473801953108098, 'samples': 4562112, 'steps': 23760, 'loss/train': 1.927691102027893} 08/30/2021 17:27:21 - INFO - __main__ - Step 23762: {'lr': 0.0004737995881127149, 'samples': 4562304, 'steps': 23761, 'loss/train': 1.7205820083618164} 08/30/2021 17:27:22 - INFO - __main__ - Step 23763: {'lr': 0.0004737972230164911, 'samples': 4562496, 'steps': 23762, 'loss/train': 1.9505927562713623} 08/30/2021 17:27:22 - INFO - __main__ - Step 23764: {'lr': 0.0004737948578194278, 'samples': 4562688, 'steps': 23763, 'loss/train': 1.2602747678756714} 08/30/2021 17:27:22 - INFO - __main__ - Step 23765: {'lr': 0.00047379249252152585, 'samples': 4562880, 'steps': 23764, 'loss/train': 1.6362367868423462} 08/30/2021 17:27:23 - INFO - __main__ - Step 23766: {'lr': 0.00047379012712278656, 'samples': 4563072, 'steps': 23765, 'loss/train': 1.6800568103790283} 08/30/2021 17:27:24 - INFO - __main__ - Step 23767: {'lr': 0.0004737877616232108, 'samples': 4563264, 'steps': 23766, 'loss/train': 0.21542313694953918} 08/30/2021 17:27:25 - INFO - __main__ - Step 23768: {'lr': 0.0004737853960227998, 'samples': 4563456, 'steps': 23767, 'loss/train': 1.5183273553848267} 08/30/2021 17:27:25 - INFO - __main__ - Step 23769: {'lr': 0.00047378303032155454, 'samples': 4563648, 'steps': 23768, 'loss/train': 0.9760209918022156} 08/30/2021 17:27:25 - INFO - __main__ - Step 23770: {'lr': 0.0004737806645194761, 'samples': 4563840, 'steps': 23769, 'loss/train': 1.4840788841247559} 08/30/2021 17:27:26 - INFO - __main__ - Step 23771: {'lr': 0.00047377829861656556, 'samples': 4564032, 'steps': 23770, 'loss/train': 1.7820886373519897} 08/30/2021 17:27:27 - INFO - __main__ - Step 23772: {'lr': 0.000473775932612824, 'samples': 4564224, 'steps': 23771, 'loss/train': 2.6842691898345947} 08/30/2021 17:27:28 - INFO - __main__ - Step 23773: {'lr': 0.00047377356650825245, 'samples': 4564416, 'steps': 23772, 'loss/train': 1.359667420387268} 08/30/2021 17:27:28 - INFO - __main__ - Step 23774: {'lr': 0.00047377120030285194, 'samples': 4564608, 'steps': 23773, 'loss/train': 1.8385834693908691} 08/30/2021 17:27:29 - INFO - __main__ - Step 23775: {'lr': 0.0004737688339966235, 'samples': 4564800, 'steps': 23774, 'loss/train': 2.1206347942352295} 08/30/2021 17:27:29 - INFO - __main__ - Step 23776: {'lr': 0.00047376646758956844, 'samples': 4564992, 'steps': 23775, 'loss/train': 2.2828104496002197} 08/30/2021 17:27:31 - INFO - __main__ - Step 23777: {'lr': 0.00047376410108168756, 'samples': 4565184, 'steps': 23776, 'loss/train': 1.7378520965576172} 08/30/2021 17:27:31 - INFO - __main__ - Step 23778: {'lr': 0.0004737617344729821, 'samples': 4565376, 'steps': 23777, 'loss/train': 1.6882611513137817} 08/30/2021 17:27:31 - INFO - __main__ - Step 23779: {'lr': 0.00047375936776345297, 'samples': 4565568, 'steps': 23778, 'loss/train': 1.908403754234314} 08/30/2021 17:27:32 - INFO - __main__ - Step 23780: {'lr': 0.00047375700095310136, 'samples': 4565760, 'steps': 23779, 'loss/train': 1.5699435472488403} 08/30/2021 17:27:32 - INFO - __main__ - Step 23781: {'lr': 0.0004737546340419283, 'samples': 4565952, 'steps': 23780, 'loss/train': 1.626193881034851} 08/30/2021 17:27:34 - INFO - __main__ - Step 23782: {'lr': 0.0004737522670299349, 'samples': 4566144, 'steps': 23781, 'loss/train': 1.1423419713974} 08/30/2021 17:27:34 - INFO - __main__ - Step 23783: {'lr': 0.00047374989991712214, 'samples': 4566336, 'steps': 23782, 'loss/train': 1.3004885911941528} 08/30/2021 17:27:34 - INFO - __main__ - Step 23784: {'lr': 0.00047374753270349113, 'samples': 4566528, 'steps': 23783, 'loss/train': 0.8821494579315186} 08/30/2021 17:27:35 - INFO - __main__ - Step 23785: {'lr': 0.00047374516538904287, 'samples': 4566720, 'steps': 23784, 'loss/train': 1.9171324968338013} 08/30/2021 17:27:35 - INFO - __main__ - Step 23786: {'lr': 0.0004737427979737786, 'samples': 4566912, 'steps': 23785, 'loss/train': 0.9794736504554749} 08/30/2021 17:27:35 - INFO - __main__ - Step 23787: {'lr': 0.0004737404304576992, 'samples': 4567104, 'steps': 23786, 'loss/train': 1.1728854179382324} 08/30/2021 17:27:37 - INFO - __main__ - Step 23788: {'lr': 0.0004737380628408059, 'samples': 4567296, 'steps': 23787, 'loss/train': 1.5640099048614502} 08/30/2021 17:27:37 - INFO - __main__ - Step 23789: {'lr': 0.00047373569512309963, 'samples': 4567488, 'steps': 23788, 'loss/train': 1.8454991579055786} 08/30/2021 17:27:38 - INFO - __main__ - Step 23790: {'lr': 0.0004737333273045815, 'samples': 4567680, 'steps': 23789, 'loss/train': 1.1946204900741577} 08/30/2021 17:27:38 - INFO - __main__ - Step 23791: {'lr': 0.00047373095938525256, 'samples': 4567872, 'steps': 23790, 'loss/train': 1.8148601055145264} 08/30/2021 17:27:38 - INFO - __main__ - Step 23792: {'lr': 0.0004737285913651139, 'samples': 4568064, 'steps': 23791, 'loss/train': 1.5275744199752808} 08/30/2021 17:27:40 - INFO - __main__ - Step 23793: {'lr': 0.0004737262232441667, 'samples': 4568256, 'steps': 23792, 'loss/train': 1.3972017765045166} 08/30/2021 17:27:41 - INFO - __main__ - Step 23794: {'lr': 0.00047372385502241176, 'samples': 4568448, 'steps': 23793, 'loss/train': 2.057589054107666} 08/30/2021 17:27:41 - INFO - __main__ - Step 23795: {'lr': 0.0004737214866998504, 'samples': 4568640, 'steps': 23794, 'loss/train': 1.5424411296844482} 08/30/2021 17:27:42 - INFO - __main__ - Step 23796: {'lr': 0.0004737191182764836, 'samples': 4568832, 'steps': 23795, 'loss/train': 0.7936122417449951} 08/30/2021 17:27:42 - INFO - __main__ - Step 23797: {'lr': 0.0004737167497523124, 'samples': 4569024, 'steps': 23796, 'loss/train': 1.339007019996643} 08/30/2021 17:27:44 - INFO - __main__ - Step 23798: {'lr': 0.0004737143811273379, 'samples': 4569216, 'steps': 23797, 'loss/train': 1.971666693687439} 08/30/2021 17:27:44 - INFO - __main__ - Step 23799: {'lr': 0.0004737120124015611, 'samples': 4569408, 'steps': 23798, 'loss/train': 1.2081353664398193} 08/30/2021 17:27:44 - INFO - __main__ - Step 23800: {'lr': 0.00047370964357498313, 'samples': 4569600, 'steps': 23799, 'loss/train': 1.5187081098556519} 08/30/2021 17:27:45 - INFO - __main__ - Step 23801: {'lr': 0.0004737072746476051, 'samples': 4569792, 'steps': 23800, 'loss/train': 2.2719743251800537} 08/30/2021 17:27:45 - INFO - __main__ - Step 23802: {'lr': 0.00047370490561942795, 'samples': 4569984, 'steps': 23801, 'loss/train': 1.1148394346237183} 08/30/2021 17:27:45 - INFO - __main__ - Step 23803: {'lr': 0.00047370253649045286, 'samples': 4570176, 'steps': 23802, 'loss/train': 0.7776064872741699} 08/30/2021 17:27:47 - INFO - __main__ - Step 23804: {'lr': 0.00047370016726068086, 'samples': 4570368, 'steps': 23803, 'loss/train': 1.7910127639770508} 08/30/2021 17:27:47 - INFO - __main__ - Step 23805: {'lr': 0.000473697797930113, 'samples': 4570560, 'steps': 23804, 'loss/train': 1.3740880489349365} 08/30/2021 17:27:48 - INFO - __main__ - Step 23806: {'lr': 0.00047369542849875037, 'samples': 4570752, 'steps': 23805, 'loss/train': 0.9818909764289856} 08/30/2021 17:27:48 - INFO - __main__ - Step 23807: {'lr': 0.0004736930589665941, 'samples': 4570944, 'steps': 23806, 'loss/train': 1.7987041473388672} 08/30/2021 17:27:48 - INFO - __main__ - Step 23808: {'lr': 0.0004736906893336451, 'samples': 4571136, 'steps': 23807, 'loss/train': 1.6192020177841187} 08/30/2021 17:27:50 - INFO - __main__ - Step 23809: {'lr': 0.00047368831959990453, 'samples': 4571328, 'steps': 23808, 'loss/train': 1.2590991258621216} 08/30/2021 17:27:51 - INFO - __main__ - Step 23810: {'lr': 0.0004736859497653735, 'samples': 4571520, 'steps': 23809, 'loss/train': 1.176614761352539} 08/30/2021 17:27:51 - INFO - __main__ - Step 23811: {'lr': 0.0004736835798300531, 'samples': 4571712, 'steps': 23810, 'loss/train': 1.0427967309951782} 08/30/2021 17:27:52 - INFO - __main__ - Step 23812: {'lr': 0.00047368120979394415, 'samples': 4571904, 'steps': 23811, 'loss/train': 1.492321252822876} 08/30/2021 17:27:52 - INFO - __main__ - Step 23813: {'lr': 0.000473678839657048, 'samples': 4572096, 'steps': 23812, 'loss/train': 1.3117263317108154} 08/30/2021 17:27:52 - INFO - __main__ - Step 23814: {'lr': 0.0004736764694193656, 'samples': 4572288, 'steps': 23813, 'loss/train': 0.9067861437797546} 08/30/2021 17:27:54 - INFO - __main__ - Step 23815: {'lr': 0.0004736740990808981, 'samples': 4572480, 'steps': 23814, 'loss/train': 2.07078218460083} 08/30/2021 17:27:54 - INFO - __main__ - Step 23816: {'lr': 0.0004736717286416464, 'samples': 4572672, 'steps': 23815, 'loss/train': 1.5327759981155396} 08/30/2021 17:27:54 - INFO - __main__ - Step 23817: {'lr': 0.0004736693581016117, 'samples': 4572864, 'steps': 23816, 'loss/train': 1.7998594045639038} 08/30/2021 17:27:55 - INFO - __main__ - Step 23818: {'lr': 0.00047366698746079507, 'samples': 4573056, 'steps': 23817, 'loss/train': 1.7322137355804443} 08/30/2021 17:27:55 - INFO - __main__ - Step 23819: {'lr': 0.0004736646167191975, 'samples': 4573248, 'steps': 23818, 'loss/train': 1.8632237911224365} 08/30/2021 17:27:57 - INFO - __main__ - Step 23820: {'lr': 0.00047366224587682017, 'samples': 4573440, 'steps': 23819, 'loss/train': 1.5942620038986206} 08/30/2021 17:27:57 - INFO - __main__ - Step 23821: {'lr': 0.000473659874933664, 'samples': 4573632, 'steps': 23820, 'loss/train': 1.4017938375473022} 08/30/2021 17:27:57 - INFO - __main__ - Step 23822: {'lr': 0.0004736575038897303, 'samples': 4573824, 'steps': 23821, 'loss/train': 1.2695995569229126} 08/30/2021 17:27:58 - INFO - __main__ - Step 23823: {'lr': 0.0004736551327450198, 'samples': 4574016, 'steps': 23822, 'loss/train': 1.5489740371704102} 08/30/2021 17:27:58 - INFO - __main__ - Step 23824: {'lr': 0.00047365276149953387, 'samples': 4574208, 'steps': 23823, 'loss/train': 1.4475749731063843} 08/30/2021 17:28:00 - INFO - __main__ - Step 23825: {'lr': 0.0004736503901532734, 'samples': 4574400, 'steps': 23824, 'loss/train': 1.526062250137329} 08/30/2021 17:28:00 - INFO - __main__ - Step 23826: {'lr': 0.00047364801870623954, 'samples': 4574592, 'steps': 23825, 'loss/train': 1.7532002925872803} 08/30/2021 17:28:00 - INFO - __main__ - Step 23827: {'lr': 0.00047364564715843326, 'samples': 4574784, 'steps': 23826, 'loss/train': 1.91557776927948} 08/30/2021 17:28:01 - INFO - __main__ - Step 23828: {'lr': 0.00047364327550985575, 'samples': 4574976, 'steps': 23827, 'loss/train': 2.0333333015441895} 08/30/2021 17:28:01 - INFO - __main__ - Step 23829: {'lr': 0.00047364090376050805, 'samples': 4575168, 'steps': 23828, 'loss/train': 1.6888744831085205} 08/30/2021 17:28:03 - INFO - __main__ - Step 23830: {'lr': 0.0004736385319103912, 'samples': 4575360, 'steps': 23829, 'loss/train': 1.4075181484222412} 08/30/2021 17:28:03 - INFO - __main__ - Step 23831: {'lr': 0.00047363615995950624, 'samples': 4575552, 'steps': 23830, 'loss/train': 1.7036877870559692} 08/30/2021 17:28:03 - INFO - __main__ - Step 23832: {'lr': 0.0004736337879078544, 'samples': 4575744, 'steps': 23831, 'loss/train': 1.2392202615737915} 08/30/2021 17:28:04 - INFO - __main__ - Step 23833: {'lr': 0.0004736314157554365, 'samples': 4575936, 'steps': 23832, 'loss/train': 1.7700579166412354} 08/30/2021 17:28:04 - INFO - __main__ - Step 23834: {'lr': 0.00047362904350225376, 'samples': 4576128, 'steps': 23833, 'loss/train': 0.9120385646820068} 08/30/2021 17:28:06 - INFO - __main__ - Step 23835: {'lr': 0.0004736266711483073, 'samples': 4576320, 'steps': 23834, 'loss/train': 0.18678513169288635} 08/30/2021 17:28:06 - INFO - __main__ - Step 23836: {'lr': 0.00047362429869359803, 'samples': 4576512, 'steps': 23835, 'loss/train': 1.412263035774231} 08/30/2021 17:28:07 - INFO - __main__ - Step 23837: {'lr': 0.0004736219261381271, 'samples': 4576704, 'steps': 23836, 'loss/train': 1.8080602884292603} 08/30/2021 17:28:07 - INFO - __main__ - Step 23838: {'lr': 0.0004736195534818956, 'samples': 4576896, 'steps': 23837, 'loss/train': 0.12009059637784958} 08/30/2021 17:28:07 - INFO - __main__ - Step 23839: {'lr': 0.00047361718072490457, 'samples': 4577088, 'steps': 23838, 'loss/train': 1.80378258228302} 08/30/2021 17:28:09 - INFO - __main__ - Step 23840: {'lr': 0.00047361480786715514, 'samples': 4577280, 'steps': 23839, 'loss/train': 1.8580217361450195} 08/30/2021 17:28:10 - INFO - __main__ - Step 23841: {'lr': 0.00047361243490864826, 'samples': 4577472, 'steps': 23840, 'loss/train': 1.0173853635787964} 08/30/2021 17:28:10 - INFO - __main__ - Step 23842: {'lr': 0.00047361006184938517, 'samples': 4577664, 'steps': 23841, 'loss/train': 1.4172651767730713} 08/30/2021 17:28:10 - INFO - __main__ - Step 23843: {'lr': 0.00047360768868936673, 'samples': 4577856, 'steps': 23842, 'loss/train': 0.18533694744110107} 08/30/2021 17:28:11 - INFO - __main__ - Step 23844: {'lr': 0.00047360531542859415, 'samples': 4578048, 'steps': 23843, 'loss/train': 2.061516046524048} 08/30/2021 17:28:11 - INFO - __main__ - Step 23845: {'lr': 0.00047360294206706845, 'samples': 4578240, 'steps': 23844, 'loss/train': 2.084402084350586} 08/30/2021 17:28:13 - INFO - __main__ - Step 23846: {'lr': 0.0004736005686047907, 'samples': 4578432, 'steps': 23845, 'loss/train': 1.6754575967788696} 08/30/2021 17:28:14 - INFO - __main__ - Step 23847: {'lr': 0.000473598195041762, 'samples': 4578624, 'steps': 23846, 'loss/train': 1.7514890432357788} 08/30/2021 17:28:14 - INFO - __main__ - Step 23848: {'lr': 0.0004735958213779835, 'samples': 4578816, 'steps': 23847, 'loss/train': 1.93454909324646} 08/30/2021 17:28:14 - INFO - __main__ - Step 23849: {'lr': 0.0004735934476134561, 'samples': 4579008, 'steps': 23848, 'loss/train': 1.8268200159072876} 08/30/2021 17:28:15 - INFO - __main__ - Step 23850: {'lr': 0.0004735910737481809, 'samples': 4579200, 'steps': 23849, 'loss/train': 1.6639269590377808} 08/30/2021 17:28:16 - INFO - __main__ - Step 23851: {'lr': 0.0004735886997821591, 'samples': 4579392, 'steps': 23850, 'loss/train': 1.5180392265319824} 08/30/2021 17:28:17 - INFO - __main__ - Step 23852: {'lr': 0.00047358632571539163, 'samples': 4579584, 'steps': 23851, 'loss/train': 1.6867505311965942} 08/30/2021 17:28:17 - INFO - __main__ - Step 23853: {'lr': 0.0004735839515478796, 'samples': 4579776, 'steps': 23852, 'loss/train': 1.8900582790374756} 08/30/2021 17:28:18 - INFO - __main__ - Step 23854: {'lr': 0.0004735815772796241, 'samples': 4579968, 'steps': 23853, 'loss/train': 1.4159471988677979} 08/30/2021 17:28:18 - INFO - __main__ - Step 23855: {'lr': 0.0004735792029106262, 'samples': 4580160, 'steps': 23854, 'loss/train': 1.7847771644592285} 08/30/2021 17:28:19 - INFO - __main__ - Step 23856: {'lr': 0.0004735768284408869, 'samples': 4580352, 'steps': 23855, 'loss/train': 1.3962061405181885} 08/30/2021 17:28:20 - INFO - __main__ - Step 23857: {'lr': 0.00047357445387040745, 'samples': 4580544, 'steps': 23856, 'loss/train': 1.7047101259231567} 08/30/2021 17:28:20 - INFO - __main__ - Step 23858: {'lr': 0.0004735720791991887, 'samples': 4580736, 'steps': 23857, 'loss/train': 1.3259724378585815} 08/30/2021 17:28:20 - INFO - __main__ - Step 23859: {'lr': 0.00047356970442723184, 'samples': 4580928, 'steps': 23858, 'loss/train': 1.4971916675567627} 08/30/2021 17:28:21 - INFO - __main__ - Step 23860: {'lr': 0.00047356732955453794, 'samples': 4581120, 'steps': 23859, 'loss/train': 1.8438758850097656} 08/30/2021 17:28:21 - INFO - __main__ - Step 23861: {'lr': 0.00047356495458110806, 'samples': 4581312, 'steps': 23860, 'loss/train': 1.6122157573699951} 08/30/2021 17:28:23 - INFO - __main__ - Step 23862: {'lr': 0.00047356257950694326, 'samples': 4581504, 'steps': 23861, 'loss/train': 1.2520089149475098} 08/30/2021 17:28:23 - INFO - __main__ - Step 23863: {'lr': 0.0004735602043320446, 'samples': 4581696, 'steps': 23862, 'loss/train': 0.912713885307312} 08/30/2021 17:28:24 - INFO - __main__ - Step 23864: {'lr': 0.0004735578290564132, 'samples': 4581888, 'steps': 23863, 'loss/train': 2.071293830871582} 08/30/2021 17:28:24 - INFO - __main__ - Step 23865: {'lr': 0.00047355545368005003, 'samples': 4582080, 'steps': 23864, 'loss/train': 0.1382804811000824} 08/30/2021 17:28:24 - INFO - __main__ - Step 23866: {'lr': 0.00047355307820295625, 'samples': 4582272, 'steps': 23865, 'loss/train': 0.18995091319084167} 08/30/2021 17:28:25 - INFO - __main__ - Step 23867: {'lr': 0.00047355070262513287, 'samples': 4582464, 'steps': 23866, 'loss/train': 0.23722438514232635} 08/30/2021 17:28:26 - INFO - __main__ - Step 23868: {'lr': 0.00047354832694658104, 'samples': 4582656, 'steps': 23867, 'loss/train': 1.927314043045044} 08/30/2021 17:28:27 - INFO - __main__ - Step 23869: {'lr': 0.0004735459511673018, 'samples': 4582848, 'steps': 23868, 'loss/train': 1.8384425640106201} 08/30/2021 17:28:27 - INFO - __main__ - Step 23870: {'lr': 0.0004735435752872962, 'samples': 4583040, 'steps': 23869, 'loss/train': 1.5113917589187622} 08/30/2021 17:28:27 - INFO - __main__ - Step 23871: {'lr': 0.00047354119930656524, 'samples': 4583232, 'steps': 23870, 'loss/train': 1.3223645687103271} 08/30/2021 17:28:28 - INFO - __main__ - Step 23872: {'lr': 0.0004735388232251101, 'samples': 4583424, 'steps': 23871, 'loss/train': 1.503225326538086} 08/30/2021 17:28:29 - INFO - __main__ - Step 23873: {'lr': 0.00047353644704293185, 'samples': 4583616, 'steps': 23872, 'loss/train': 1.4452446699142456} 08/30/2021 17:28:30 - INFO - __main__ - Step 23874: {'lr': 0.0004735340707600315, 'samples': 4583808, 'steps': 23873, 'loss/train': 1.406503438949585} 08/30/2021 17:28:30 - INFO - __main__ - Step 23875: {'lr': 0.0004735316943764102, 'samples': 4584000, 'steps': 23874, 'loss/train': 1.6812968254089355} 08/30/2021 17:28:30 - INFO - __main__ - Step 23876: {'lr': 0.0004735293178920689, 'samples': 4584192, 'steps': 23875, 'loss/train': 2.136699914932251} 08/30/2021 17:28:31 - INFO - __main__ - Step 23877: {'lr': 0.00047352694130700873, 'samples': 4584384, 'steps': 23876, 'loss/train': 0.8547267913818359} 08/30/2021 17:28:32 - INFO - __main__ - Step 23878: {'lr': 0.00047352456462123086, 'samples': 4584576, 'steps': 23877, 'loss/train': 1.6009595394134521} 08/30/2021 17:28:33 - INFO - __main__ - Step 23879: {'lr': 0.00047352218783473614, 'samples': 4584768, 'steps': 23878, 'loss/train': 0.06502050906419754} 08/30/2021 17:28:33 - INFO - __main__ - Step 23880: {'lr': 0.0004735198109475258, 'samples': 4584960, 'steps': 23879, 'loss/train': 2.0369484424591064} 08/30/2021 17:28:34 - INFO - __main__ - Step 23881: {'lr': 0.000473517433959601, 'samples': 4585152, 'steps': 23880, 'loss/train': 1.5942567586898804} 08/30/2021 17:28:34 - INFO - __main__ - Step 23882: {'lr': 0.00047351505687096257, 'samples': 4585344, 'steps': 23881, 'loss/train': 2.0245325565338135} 08/30/2021 17:28:36 - INFO - __main__ - Step 23883: {'lr': 0.00047351267968161176, 'samples': 4585536, 'steps': 23882, 'loss/train': 1.6382445096969604} 08/30/2021 17:28:36 - INFO - __main__ - Step 23884: {'lr': 0.0004735103023915496, 'samples': 4585728, 'steps': 23883, 'loss/train': 1.2688628435134888} 08/30/2021 17:28:37 - INFO - __main__ - Step 23885: {'lr': 0.0004735079250007771, 'samples': 4585920, 'steps': 23884, 'loss/train': 1.2023228406906128} 08/30/2021 17:28:37 - INFO - __main__ - Step 23886: {'lr': 0.00047350554750929543, 'samples': 4586112, 'steps': 23885, 'loss/train': 1.6293264627456665} 08/30/2021 17:28:37 - INFO - __main__ - Step 23887: {'lr': 0.0004735031699171055, 'samples': 4586304, 'steps': 23886, 'loss/train': 1.5460349321365356} 08/30/2021 17:28:39 - INFO - __main__ - Step 23888: {'lr': 0.0004735007922242086, 'samples': 4586496, 'steps': 23887, 'loss/train': 0.10107112675905228} 08/30/2021 17:28:39 - INFO - __main__ - Step 23889: {'lr': 0.0004734984144306057, 'samples': 4586688, 'steps': 23888, 'loss/train': 1.457375168800354} 08/30/2021 17:28:40 - INFO - __main__ - Step 23890: {'lr': 0.0004734960365362978, 'samples': 4586880, 'steps': 23889, 'loss/train': 1.3192206621170044} 08/30/2021 17:28:40 - INFO - __main__ - Step 23891: {'lr': 0.0004734936585412861, 'samples': 4587072, 'steps': 23890, 'loss/train': 1.0279250144958496} 08/30/2021 17:28:40 - INFO - __main__ - Step 23892: {'lr': 0.00047349128044557153, 'samples': 4587264, 'steps': 23891, 'loss/train': 1.7531778812408447} 08/30/2021 17:28:42 - INFO - __main__ - Step 23893: {'lr': 0.0004734889022491553, 'samples': 4587456, 'steps': 23892, 'loss/train': 1.7402050495147705} 08/30/2021 17:28:42 - INFO - __main__ - Step 23894: {'lr': 0.0004734865239520384, 'samples': 4587648, 'steps': 23893, 'loss/train': 1.4512770175933838} 08/30/2021 17:28:42 - INFO - __main__ - Step 23895: {'lr': 0.0004734841455542219, 'samples': 4587840, 'steps': 23894, 'loss/train': 1.7012555599212646} 08/30/2021 17:28:43 - INFO - __main__ - Step 23896: {'lr': 0.0004734817670557069, 'samples': 4588032, 'steps': 23895, 'loss/train': 0.9944023489952087} 08/30/2021 17:28:43 - INFO - __main__ - Step 23897: {'lr': 0.00047347938845649447, 'samples': 4588224, 'steps': 23896, 'loss/train': 1.2406022548675537} 08/30/2021 17:28:45 - INFO - __main__ - Step 23898: {'lr': 0.0004734770097565857, 'samples': 4588416, 'steps': 23897, 'loss/train': 1.8092373609542847} 08/30/2021 17:28:45 - INFO - __main__ - Step 23899: {'lr': 0.00047347463095598157, 'samples': 4588608, 'steps': 23898, 'loss/train': 2.0713953971862793} 08/30/2021 17:28:45 - INFO - __main__ - Step 23900: {'lr': 0.00047347225205468323, 'samples': 4588800, 'steps': 23899, 'loss/train': 1.4054807424545288} 08/30/2021 17:28:46 - INFO - __main__ - Step 23901: {'lr': 0.00047346987305269184, 'samples': 4588992, 'steps': 23900, 'loss/train': 1.2611148357391357} 08/30/2021 17:28:46 - INFO - __main__ - Step 23902: {'lr': 0.0004734674939500083, 'samples': 4589184, 'steps': 23901, 'loss/train': 1.083526372909546} 08/30/2021 17:28:46 - INFO - __main__ - Step 23903: {'lr': 0.0004734651147466338, 'samples': 4589376, 'steps': 23902, 'loss/train': 1.7088778018951416} 08/30/2021 17:28:48 - INFO - __main__ - Step 23904: {'lr': 0.00047346273544256927, 'samples': 4589568, 'steps': 23903, 'loss/train': 0.4893910884857178} 08/30/2021 17:28:49 - INFO - __main__ - Step 23905: {'lr': 0.00047346035603781597, 'samples': 4589760, 'steps': 23904, 'loss/train': 1.1126079559326172} 08/30/2021 17:28:49 - INFO - __main__ - Step 23906: {'lr': 0.00047345797653237486, 'samples': 4589952, 'steps': 23905, 'loss/train': 1.494066834449768} 08/30/2021 17:28:50 - INFO - __main__ - Step 23907: {'lr': 0.000473455596926247, 'samples': 4590144, 'steps': 23906, 'loss/train': 1.458207607269287} 08/30/2021 17:28:50 - INFO - __main__ - Step 23908: {'lr': 0.0004734532172194335, 'samples': 4590336, 'steps': 23907, 'loss/train': 1.5953456163406372} 08/30/2021 17:28:51 - INFO - __main__ - Step 23909: {'lr': 0.0004734508374119355, 'samples': 4590528, 'steps': 23908, 'loss/train': 1.9063292741775513} 08/30/2021 17:28:52 - INFO - __main__ - Step 23910: {'lr': 0.0004734484575037539, 'samples': 4590720, 'steps': 23909, 'loss/train': 1.5804921388626099} 08/30/2021 17:28:52 - INFO - __main__ - Step 23911: {'lr': 0.00047344607749489, 'samples': 4590912, 'steps': 23910, 'loss/train': 1.5822813510894775} 08/30/2021 17:28:53 - INFO - __main__ - Step 23912: {'lr': 0.00047344369738534466, 'samples': 4591104, 'steps': 23911, 'loss/train': 1.5705474615097046} 08/30/2021 17:28:53 - INFO - __main__ - Step 23913: {'lr': 0.000473441317175119, 'samples': 4591296, 'steps': 23912, 'loss/train': 2.1579926013946533} 08/30/2021 17:28:54 - INFO - __main__ - Step 23914: {'lr': 0.0004734389368642142, 'samples': 4591488, 'steps': 23913, 'loss/train': 1.5677502155303955} 08/30/2021 17:28:55 - INFO - __main__ - Step 23915: {'lr': 0.0004734365564526313, 'samples': 4591680, 'steps': 23914, 'loss/train': 1.2844774723052979} 08/30/2021 17:28:55 - INFO - __main__ - Step 23916: {'lr': 0.00047343417594037117, 'samples': 4591872, 'steps': 23915, 'loss/train': 1.2457770109176636} 08/30/2021 17:28:56 - INFO - __main__ - Step 23917: {'lr': 0.00047343179532743516, 'samples': 4592064, 'steps': 23916, 'loss/train': 1.7153592109680176} 08/30/2021 17:28:56 - INFO - __main__ - Step 23918: {'lr': 0.00047342941461382427, 'samples': 4592256, 'steps': 23917, 'loss/train': 1.7542444467544556} 08/30/2021 17:28:58 - INFO - __main__ - Step 23919: {'lr': 0.0004734270337995395, 'samples': 4592448, 'steps': 23918, 'loss/train': 1.5001026391983032} 08/30/2021 17:28:58 - INFO - __main__ - Step 23920: {'lr': 0.0004734246528845819, 'samples': 4592640, 'steps': 23919, 'loss/train': 1.0851719379425049} 08/30/2021 17:28:58 - INFO - __main__ - Step 23921: {'lr': 0.0004734222718689527, 'samples': 4592832, 'steps': 23920, 'loss/train': 1.639939308166504} 08/30/2021 17:28:59 - INFO - __main__ - Step 23922: {'lr': 0.0004734198907526528, 'samples': 4593024, 'steps': 23921, 'loss/train': 1.6189429759979248} 08/30/2021 17:28:59 - INFO - __main__ - Step 23923: {'lr': 0.00047341750953568335, 'samples': 4593216, 'steps': 23922, 'loss/train': 1.2667911052703857} 08/30/2021 17:29:01 - INFO - __main__ - Step 23924: {'lr': 0.0004734151282180454, 'samples': 4593408, 'steps': 23923, 'loss/train': 1.7822493314743042} 08/30/2021 17:29:01 - INFO - __main__ - Step 23925: {'lr': 0.0004734127467997401, 'samples': 4593600, 'steps': 23924, 'loss/train': 1.4168741703033447} 08/30/2021 17:29:01 - INFO - __main__ - Step 23926: {'lr': 0.0004734103652807684, 'samples': 4593792, 'steps': 23925, 'loss/train': 1.5136585235595703} 08/30/2021 17:29:02 - INFO - __main__ - Step 23927: {'lr': 0.0004734079836611315, 'samples': 4593984, 'steps': 23926, 'loss/train': 1.656827688217163} 08/30/2021 17:29:02 - INFO - __main__ - Step 23928: {'lr': 0.0004734056019408304, 'samples': 4594176, 'steps': 23927, 'loss/train': 1.1633803844451904} 08/30/2021 17:29:04 - INFO - __main__ - Step 23929: {'lr': 0.00047340322011986614, 'samples': 4594368, 'steps': 23928, 'loss/train': 1.5292781591415405} 08/30/2021 17:29:04 - INFO - __main__ - Step 23930: {'lr': 0.0004734008381982399, 'samples': 4594560, 'steps': 23929, 'loss/train': 1.594104290008545} 08/30/2021 17:29:05 - INFO - __main__ - Step 23931: {'lr': 0.0004733984561759527, 'samples': 4594752, 'steps': 23930, 'loss/train': 0.07521896809339523} 08/30/2021 17:29:05 - INFO - __main__ - Step 23932: {'lr': 0.0004733960740530055, 'samples': 4594944, 'steps': 23931, 'loss/train': 0.9714577198028564} 08/30/2021 17:29:05 - INFO - __main__ - Step 23933: {'lr': 0.0004733936918293995, 'samples': 4595136, 'steps': 23932, 'loss/train': 1.1091326475143433} 08/30/2021 17:29:06 - INFO - __main__ - Step 23934: {'lr': 0.0004733913095051358, 'samples': 4595328, 'steps': 23933, 'loss/train': 1.7921544313430786} 08/30/2021 17:29:07 - INFO - __main__ - Step 23935: {'lr': 0.0004733889270802154, 'samples': 4595520, 'steps': 23934, 'loss/train': 1.0680391788482666} 08/30/2021 17:29:08 - INFO - __main__ - Step 23936: {'lr': 0.00047338654455463935, 'samples': 4595712, 'steps': 23935, 'loss/train': 1.6875224113464355} 08/30/2021 17:29:08 - INFO - __main__ - Step 23937: {'lr': 0.00047338416192840887, 'samples': 4595904, 'steps': 23936, 'loss/train': 0.544355034828186} 08/30/2021 17:29:08 - INFO - __main__ - Step 23938: {'lr': 0.0004733817792015249, 'samples': 4596096, 'steps': 23937, 'loss/train': 1.8118723630905151} 08/30/2021 17:29:09 - INFO - __main__ - Step 23939: {'lr': 0.00047337939637398855, 'samples': 4596288, 'steps': 23938, 'loss/train': 0.7021389603614807} 08/30/2021 17:29:10 - INFO - __main__ - Step 23940: {'lr': 0.0004733770134458009, 'samples': 4596480, 'steps': 23939, 'loss/train': 1.6260449886322021} 08/30/2021 17:29:11 - INFO - __main__ - Step 23941: {'lr': 0.0004733746304169629, 'samples': 4596672, 'steps': 23940, 'loss/train': 1.067652702331543} 08/30/2021 17:29:11 - INFO - __main__ - Step 23942: {'lr': 0.0004733722472874759, 'samples': 4596864, 'steps': 23941, 'loss/train': 0.08660119771957397} 08/30/2021 17:29:12 - INFO - __main__ - Step 23943: {'lr': 0.0004733698640573407, 'samples': 4597056, 'steps': 23942, 'loss/train': 0.7692243456840515} 08/30/2021 17:29:12 - INFO - __main__ - Step 23944: {'lr': 0.0004733674807265585, 'samples': 4597248, 'steps': 23943, 'loss/train': 1.3763090372085571} 08/30/2021 17:29:14 - INFO - __main__ - Step 23945: {'lr': 0.0004733650972951304, 'samples': 4597440, 'steps': 23944, 'loss/train': 1.3232545852661133} 08/30/2021 17:29:14 - INFO - __main__ - Step 23946: {'lr': 0.0004733627137630574, 'samples': 4597632, 'steps': 23945, 'loss/train': 1.1721309423446655} 08/30/2021 17:29:14 - INFO - __main__ - Step 23947: {'lr': 0.00047336033013034063, 'samples': 4597824, 'steps': 23946, 'loss/train': 0.9328784346580505} 08/30/2021 17:29:15 - INFO - __main__ - Step 23948: {'lr': 0.00047335794639698117, 'samples': 4598016, 'steps': 23947, 'loss/train': 1.1213229894638062} 08/30/2021 17:29:15 - INFO - __main__ - Step 23949: {'lr': 0.00047335556256298, 'samples': 4598208, 'steps': 23948, 'loss/train': 1.6727445125579834} 08/30/2021 17:29:17 - INFO - __main__ - Step 23950: {'lr': 0.0004733531786283383, 'samples': 4598400, 'steps': 23949, 'loss/train': 1.4021284580230713} 08/30/2021 17:29:17 - INFO - __main__ - Step 23951: {'lr': 0.0004733507945930571, 'samples': 4598592, 'steps': 23950, 'loss/train': 1.8878673315048218} 08/30/2021 17:29:18 - INFO - __main__ - Step 23952: {'lr': 0.0004733484104571375, 'samples': 4598784, 'steps': 23951, 'loss/train': 1.5105644464492798} 08/30/2021 17:29:18 - INFO - __main__ - Step 23953: {'lr': 0.0004733460262205805, 'samples': 4598976, 'steps': 23952, 'loss/train': 2.0807597637176514} 08/30/2021 17:29:18 - INFO - __main__ - Step 23954: {'lr': 0.00047334364188338725, 'samples': 4599168, 'steps': 23953, 'loss/train': 1.6940207481384277} 08/30/2021 17:29:20 - INFO - __main__ - Step 23955: {'lr': 0.0004733412574455588, 'samples': 4599360, 'steps': 23954, 'loss/train': 1.5082449913024902} 08/30/2021 17:29:21 - INFO - __main__ - Step 23956: {'lr': 0.00047333887290709623, 'samples': 4599552, 'steps': 23955, 'loss/train': 1.1699519157409668} 08/30/2021 17:29:21 - INFO - __main__ - Step 23957: {'lr': 0.00047333648826800056, 'samples': 4599744, 'steps': 23956, 'loss/train': 1.5576560497283936} 08/30/2021 17:29:21 - INFO - __main__ - Step 23958: {'lr': 0.000473334103528273, 'samples': 4599936, 'steps': 23957, 'loss/train': 1.5029267072677612} 08/30/2021 17:29:22 - INFO - __main__ - Step 23959: {'lr': 0.00047333171868791453, 'samples': 4600128, 'steps': 23958, 'loss/train': 1.5009058713912964} 08/30/2021 17:29:23 - INFO - __main__ - Step 23960: {'lr': 0.00047332933374692623, 'samples': 4600320, 'steps': 23959, 'loss/train': 1.3994954824447632} 08/30/2021 17:29:24 - INFO - __main__ - Step 23961: {'lr': 0.0004733269487053091, 'samples': 4600512, 'steps': 23960, 'loss/train': 1.5259203910827637} 08/30/2021 17:29:24 - INFO - __main__ - Step 23962: {'lr': 0.0004733245635630644, 'samples': 4600704, 'steps': 23961, 'loss/train': 1.4005982875823975} 08/30/2021 17:29:24 - INFO - __main__ - Step 23963: {'lr': 0.000473322178320193, 'samples': 4600896, 'steps': 23962, 'loss/train': 1.6762452125549316} 08/30/2021 17:29:25 - INFO - __main__ - Step 23964: {'lr': 0.0004733197929766961, 'samples': 4601088, 'steps': 23963, 'loss/train': 1.6293858289718628} 08/30/2021 17:29:26 - INFO - __main__ - Step 23965: {'lr': 0.0004733174075325748, 'samples': 4601280, 'steps': 23964, 'loss/train': 1.3817896842956543} 08/30/2021 17:29:27 - INFO - __main__ - Step 23966: {'lr': 0.0004733150219878301, 'samples': 4601472, 'steps': 23965, 'loss/train': 1.376197099685669} 08/30/2021 17:29:27 - INFO - __main__ - Step 23967: {'lr': 0.00047331263634246314, 'samples': 4601664, 'steps': 23966, 'loss/train': 1.2290537357330322} 08/30/2021 17:29:27 - INFO - __main__ - Step 23968: {'lr': 0.0004733102505964749, 'samples': 4601856, 'steps': 23967, 'loss/train': 1.452670931816101} 08/30/2021 17:29:28 - INFO - __main__ - Step 23969: {'lr': 0.00047330786474986645, 'samples': 4602048, 'steps': 23968, 'loss/train': 1.2899892330169678} 08/30/2021 17:29:29 - INFO - __main__ - Step 23970: {'lr': 0.00047330547880263896, 'samples': 4602240, 'steps': 23969, 'loss/train': 1.491136908531189} 08/30/2021 17:29:30 - INFO - __main__ - Step 23971: {'lr': 0.00047330309275479354, 'samples': 4602432, 'steps': 23970, 'loss/train': 1.4215087890625} 08/30/2021 17:29:30 - INFO - __main__ - Step 23972: {'lr': 0.00047330070660633113, 'samples': 4602624, 'steps': 23971, 'loss/train': 1.8291187286376953} 08/30/2021 17:29:30 - INFO - __main__ - Step 23973: {'lr': 0.00047329832035725286, 'samples': 4602816, 'steps': 23972, 'loss/train': 1.5089482069015503} 08/30/2021 17:29:31 - INFO - __main__ - Step 23974: {'lr': 0.0004732959340075598, 'samples': 4603008, 'steps': 23973, 'loss/train': 1.8125065565109253} 08/30/2021 17:29:32 - INFO - __main__ - Step 23975: {'lr': 0.0004732935475572531, 'samples': 4603200, 'steps': 23974, 'loss/train': 1.5856719017028809} 08/30/2021 17:29:33 - INFO - __main__ - Step 23976: {'lr': 0.00047329116100633373, 'samples': 4603392, 'steps': 23975, 'loss/train': 2.2570695877075195} 08/30/2021 17:29:33 - INFO - __main__ - Step 23977: {'lr': 0.0004732887743548028, 'samples': 4603584, 'steps': 23976, 'loss/train': 1.0739967823028564} 08/30/2021 17:29:33 - INFO - __main__ - Step 23978: {'lr': 0.0004732863876026614, 'samples': 4603776, 'steps': 23977, 'loss/train': 1.5266087055206299} 08/30/2021 17:29:34 - INFO - __main__ - Step 23979: {'lr': 0.00047328400074991064, 'samples': 4603968, 'steps': 23978, 'loss/train': 0.9839372038841248} 08/30/2021 17:29:34 - INFO - __main__ - Step 23980: {'lr': 0.00047328161379655155, 'samples': 4604160, 'steps': 23979, 'loss/train': 0.6058788895606995} 08/30/2021 17:29:35 - INFO - __main__ - Step 23981: {'lr': 0.00047327922674258516, 'samples': 4604352, 'steps': 23980, 'loss/train': 1.6976488828659058} 08/30/2021 17:29:36 - INFO - __main__ - Step 23982: {'lr': 0.00047327683958801257, 'samples': 4604544, 'steps': 23981, 'loss/train': 1.3941693305969238} 08/30/2021 17:29:36 - INFO - __main__ - Step 23983: {'lr': 0.00047327445233283496, 'samples': 4604736, 'steps': 23982, 'loss/train': 1.415250539779663} 08/30/2021 17:29:37 - INFO - __main__ - Step 23984: {'lr': 0.0004732720649770533, 'samples': 4604928, 'steps': 23983, 'loss/train': 1.7057350873947144} 08/30/2021 17:29:37 - INFO - __main__ - Step 23985: {'lr': 0.00047326967752066876, 'samples': 4605120, 'steps': 23984, 'loss/train': 1.5120905637741089} 08/30/2021 17:29:39 - INFO - __main__ - Step 23986: {'lr': 0.0004732672899636822, 'samples': 4605312, 'steps': 23985, 'loss/train': 1.9327870607376099} 08/30/2021 17:29:40 - INFO - __main__ - Step 23987: {'lr': 0.00047326490230609495, 'samples': 4605504, 'steps': 23986, 'loss/train': 1.3406269550323486} 08/30/2021 17:29:40 - INFO - __main__ - Step 23988: {'lr': 0.000473262514547908, 'samples': 4605696, 'steps': 23987, 'loss/train': 0.6682289838790894} 08/30/2021 17:29:41 - INFO - __main__ - Step 23989: {'lr': 0.00047326012668912233, 'samples': 4605888, 'steps': 23988, 'loss/train': 0.570551335811615} 08/30/2021 17:29:41 - INFO - __main__ - Step 23990: {'lr': 0.0004732577387297391, 'samples': 4606080, 'steps': 23989, 'loss/train': 1.1935884952545166} 08/30/2021 17:29:41 - INFO - __main__ - Step 23991: {'lr': 0.00047325535066975946, 'samples': 4606272, 'steps': 23990, 'loss/train': 1.4759531021118164} 08/30/2021 17:29:43 - INFO - __main__ - Step 23992: {'lr': 0.0004732529625091843, 'samples': 4606464, 'steps': 23991, 'loss/train': 1.1583490371704102} 08/30/2021 17:29:43 - INFO - __main__ - Step 23993: {'lr': 0.0004732505742480149, 'samples': 4606656, 'steps': 23992, 'loss/train': 2.132206916809082} 08/30/2021 17:29:44 - INFO - __main__ - Step 23994: {'lr': 0.00047324818588625214, 'samples': 4606848, 'steps': 23993, 'loss/train': 1.8066595792770386} 08/30/2021 17:29:44 - INFO - __main__ - Step 23995: {'lr': 0.0004732457974238972, 'samples': 4607040, 'steps': 23994, 'loss/train': 2.031420946121216} 08/30/2021 17:29:44 - INFO - __main__ - Step 23996: {'lr': 0.0004732434088609512, 'samples': 4607232, 'steps': 23995, 'loss/train': 1.9712618589401245} 08/30/2021 17:29:46 - INFO - __main__ - Step 23997: {'lr': 0.00047324102019741514, 'samples': 4607424, 'steps': 23996, 'loss/train': 1.8564987182617188} 08/30/2021 17:29:46 - INFO - __main__ - Step 23998: {'lr': 0.00047323863143329016, 'samples': 4607616, 'steps': 23997, 'loss/train': 1.965773582458496} 08/30/2021 17:29:47 - INFO - __main__ - Step 23999: {'lr': 0.00047323624256857724, 'samples': 4607808, 'steps': 23998, 'loss/train': 1.5524145364761353} 08/30/2021 17:29:47 - INFO - __main__ - Step 24000: {'lr': 0.0004732338536032775, 'samples': 4608000, 'steps': 23999, 'loss/train': 1.7805531024932861} 08/30/2021 17:29:47 - INFO - __main__ - Step 24001: {'lr': 0.0004732314645373921, 'samples': 4608192, 'steps': 24000, 'loss/train': 1.941765308380127} 08/30/2021 17:29:49 - INFO - __main__ - Step 24002: {'lr': 0.0004732290753709221, 'samples': 4608384, 'steps': 24001, 'loss/train': 2.1082425117492676} 08/30/2021 17:29:49 - INFO - __main__ - Step 24003: {'lr': 0.0004732266861038684, 'samples': 4608576, 'steps': 24002, 'loss/train': 1.6280622482299805} 08/30/2021 17:29:50 - INFO - __main__ - Step 24004: {'lr': 0.0004732242967362322, 'samples': 4608768, 'steps': 24003, 'loss/train': 1.4950611591339111} 08/30/2021 17:29:50 - INFO - __main__ - Step 24005: {'lr': 0.00047322190726801464, 'samples': 4608960, 'steps': 24004, 'loss/train': 1.7071781158447266} 08/30/2021 17:29:50 - INFO - __main__ - Step 24006: {'lr': 0.0004732195176992167, 'samples': 4609152, 'steps': 24005, 'loss/train': 1.6114521026611328} 08/30/2021 17:29:52 - INFO - __main__ - Step 24007: {'lr': 0.0004732171280298395, 'samples': 4609344, 'steps': 24006, 'loss/train': 1.3769075870513916} 08/30/2021 17:29:52 - INFO - __main__ - Step 24008: {'lr': 0.0004732147382598842, 'samples': 4609536, 'steps': 24007, 'loss/train': 1.3611992597579956} 08/30/2021 17:29:53 - INFO - __main__ - Step 24009: {'lr': 0.00047321234838935164, 'samples': 4609728, 'steps': 24008, 'loss/train': 1.4643421173095703} 08/30/2021 17:29:53 - INFO - __main__ - Step 24010: {'lr': 0.0004732099584182431, 'samples': 4609920, 'steps': 24009, 'loss/train': 1.8271245956420898} 08/30/2021 17:29:53 - INFO - __main__ - Step 24011: {'lr': 0.00047320756834655955, 'samples': 4610112, 'steps': 24010, 'loss/train': 1.9192742109298706} 08/30/2021 17:29:56 - INFO - __main__ - Step 24012: {'lr': 0.0004732051781743022, 'samples': 4610304, 'steps': 24011, 'loss/train': 1.5685092210769653} 08/30/2021 17:29:56 - INFO - __main__ - Step 24013: {'lr': 0.00047320278790147197, 'samples': 4610496, 'steps': 24012, 'loss/train': 2.033869743347168} 08/30/2021 17:29:56 - INFO - __main__ - Step 24014: {'lr': 0.00047320039752807, 'samples': 4610688, 'steps': 24013, 'loss/train': 1.8639260530471802} 08/30/2021 17:29:57 - INFO - __main__ - Step 24015: {'lr': 0.0004731980070540974, 'samples': 4610880, 'steps': 24014, 'loss/train': 1.352035403251648} 08/30/2021 17:29:57 - INFO - __main__ - Step 24016: {'lr': 0.0004731956164795552, 'samples': 4611072, 'steps': 24015, 'loss/train': 1.722882628440857} 08/30/2021 17:29:57 - INFO - __main__ - Step 24017: {'lr': 0.0004731932258044446, 'samples': 4611264, 'steps': 24016, 'loss/train': 0.7408400177955627} 08/30/2021 17:29:59 - INFO - __main__ - Step 24018: {'lr': 0.00047319083502876647, 'samples': 4611456, 'steps': 24017, 'loss/train': 1.7358992099761963} 08/30/2021 17:29:59 - INFO - __main__ - Step 24019: {'lr': 0.00047318844415252204, 'samples': 4611648, 'steps': 24018, 'loss/train': 1.7989447116851807} 08/30/2021 17:30:00 - INFO - __main__ - Step 24020: {'lr': 0.00047318605317571227, 'samples': 4611840, 'steps': 24019, 'loss/train': 1.5153939723968506} 08/30/2021 17:30:00 - INFO - __main__ - Step 24021: {'lr': 0.0004731836620983384, 'samples': 4612032, 'steps': 24020, 'loss/train': 1.7799488306045532} 08/30/2021 17:30:00 - INFO - __main__ - Step 24022: {'lr': 0.00047318127092040144, 'samples': 4612224, 'steps': 24021, 'loss/train': 1.7262390851974487} 08/30/2021 17:30:02 - INFO - __main__ - Step 24023: {'lr': 0.00047317887964190233, 'samples': 4612416, 'steps': 24022, 'loss/train': 1.7322629690170288} 08/30/2021 17:30:02 - INFO - __main__ - Step 24024: {'lr': 0.00047317648826284233, 'samples': 4612608, 'steps': 24023, 'loss/train': 1.7015255689620972} 08/30/2021 17:30:03 - INFO - __main__ - Step 24025: {'lr': 0.0004731740967832224, 'samples': 4612800, 'steps': 24024, 'loss/train': 0.9546807408332825} 08/30/2021 17:30:03 - INFO - __main__ - Step 24026: {'lr': 0.00047317170520304373, 'samples': 4612992, 'steps': 24025, 'loss/train': 1.139951229095459} 08/30/2021 17:30:03 - INFO - __main__ - Step 24027: {'lr': 0.0004731693135223073, 'samples': 4613184, 'steps': 24026, 'loss/train': 1.8629801273345947} 08/30/2021 17:30:05 - INFO - __main__ - Step 24028: {'lr': 0.0004731669217410142, 'samples': 4613376, 'steps': 24027, 'loss/train': 1.068621039390564} 08/30/2021 17:30:05 - INFO - __main__ - Step 24029: {'lr': 0.0004731645298591656, 'samples': 4613568, 'steps': 24028, 'loss/train': 1.1456061601638794} 08/30/2021 17:30:06 - INFO - __main__ - Step 24030: {'lr': 0.0004731621378767624, 'samples': 4613760, 'steps': 24029, 'loss/train': 1.7382146120071411} 08/30/2021 17:30:06 - INFO - __main__ - Step 24031: {'lr': 0.0004731597457938059, 'samples': 4613952, 'steps': 24030, 'loss/train': 0.7456815242767334} 08/30/2021 17:30:06 - INFO - __main__ - Step 24032: {'lr': 0.000473157353610297, 'samples': 4614144, 'steps': 24031, 'loss/train': 1.714818000793457} 08/30/2021 17:30:08 - INFO - __main__ - Step 24033: {'lr': 0.0004731549613262368, 'samples': 4614336, 'steps': 24032, 'loss/train': 1.5012445449829102} 08/30/2021 17:30:09 - INFO - __main__ - Step 24034: {'lr': 0.0004731525689416265, 'samples': 4614528, 'steps': 24033, 'loss/train': 1.5666781663894653} 08/30/2021 17:30:09 - INFO - __main__ - Step 24035: {'lr': 0.0004731501764564671, 'samples': 4614720, 'steps': 24034, 'loss/train': 0.3431834876537323} 08/30/2021 17:30:10 - INFO - __main__ - Step 24036: {'lr': 0.00047314778387075963, 'samples': 4614912, 'steps': 24035, 'loss/train': 1.9771511554718018} 08/30/2021 17:30:10 - INFO - __main__ - Step 24037: {'lr': 0.00047314539118450516, 'samples': 4615104, 'steps': 24036, 'loss/train': 1.9900704622268677} 08/30/2021 17:30:12 - INFO - __main__ - Step 24038: {'lr': 0.0004731429983977049, 'samples': 4615296, 'steps': 24037, 'loss/train': 1.5211819410324097} 08/30/2021 17:30:12 - INFO - __main__ - Step 24039: {'lr': 0.00047314060551035983, 'samples': 4615488, 'steps': 24038, 'loss/train': 2.0710344314575195} 08/30/2021 17:30:12 - INFO - __main__ - Step 24040: {'lr': 0.00047313821252247104, 'samples': 4615680, 'steps': 24039, 'loss/train': 1.251976490020752} 08/30/2021 17:30:13 - INFO - __main__ - Step 24041: {'lr': 0.00047313581943403963, 'samples': 4615872, 'steps': 24040, 'loss/train': 0.08993315696716309} 08/30/2021 17:30:13 - INFO - __main__ - Step 24042: {'lr': 0.0004731334262450666, 'samples': 4616064, 'steps': 24041, 'loss/train': 2.274127244949341} 08/30/2021 17:30:15 - INFO - __main__ - Step 24043: {'lr': 0.00047313103295555317, 'samples': 4616256, 'steps': 24042, 'loss/train': 1.7268720865249634} 08/30/2021 17:30:15 - INFO - __main__ - Step 24044: {'lr': 0.0004731286395655003, 'samples': 4616448, 'steps': 24043, 'loss/train': 1.7036787271499634} 08/30/2021 17:30:15 - INFO - __main__ - Step 24045: {'lr': 0.00047312624607490913, 'samples': 4616640, 'steps': 24044, 'loss/train': 1.509076714515686} 08/30/2021 17:30:16 - INFO - __main__ - Step 24046: {'lr': 0.0004731238524837807, 'samples': 4616832, 'steps': 24045, 'loss/train': 0.5438427329063416} 08/30/2021 17:30:16 - INFO - __main__ - Step 24047: {'lr': 0.00047312145879211607, 'samples': 4617024, 'steps': 24046, 'loss/train': 1.9037859439849854} 08/30/2021 17:30:18 - INFO - __main__ - Step 24048: {'lr': 0.0004731190649999164, 'samples': 4617216, 'steps': 24047, 'loss/train': 1.426287293434143} 08/30/2021 17:30:18 - INFO - __main__ - Step 24049: {'lr': 0.0004731166711071827, 'samples': 4617408, 'steps': 24048, 'loss/train': 1.7205524444580078} 08/30/2021 17:30:18 - INFO - __main__ - Step 24050: {'lr': 0.0004731142771139161, 'samples': 4617600, 'steps': 24049, 'loss/train': 1.7110624313354492} 08/30/2021 17:30:19 - INFO - __main__ - Step 24051: {'lr': 0.00047311188302011766, 'samples': 4617792, 'steps': 24050, 'loss/train': 1.59541654586792} 08/30/2021 17:30:19 - INFO - __main__ - Step 24052: {'lr': 0.00047310948882578843, 'samples': 4617984, 'steps': 24051, 'loss/train': 1.8222190141677856} 08/30/2021 17:30:19 - INFO - __main__ - Step 24053: {'lr': 0.0004731070945309295, 'samples': 4618176, 'steps': 24052, 'loss/train': 1.5752980709075928} 08/30/2021 17:30:21 - INFO - __main__ - Step 24054: {'lr': 0.00047310470013554195, 'samples': 4618368, 'steps': 24053, 'loss/train': 1.4789464473724365} 08/30/2021 17:30:21 - INFO - __main__ - Step 24055: {'lr': 0.0004731023056396269, 'samples': 4618560, 'steps': 24054, 'loss/train': 1.7332782745361328} 08/30/2021 17:30:22 - INFO - __main__ - Step 24056: {'lr': 0.00047309991104318533, 'samples': 4618752, 'steps': 24055, 'loss/train': 1.697275161743164} 08/30/2021 17:30:22 - INFO - __main__ - Step 24057: {'lr': 0.00047309751634621845, 'samples': 4618944, 'steps': 24056, 'loss/train': 1.4491691589355469} 08/30/2021 17:30:22 - INFO - __main__ - Step 24058: {'lr': 0.0004730951215487272, 'samples': 4619136, 'steps': 24057, 'loss/train': 1.2856816053390503} 08/30/2021 17:30:24 - INFO - __main__ - Step 24059: {'lr': 0.0004730927266507128, 'samples': 4619328, 'steps': 24058, 'loss/train': 1.5663295984268188} 08/30/2021 17:30:24 - INFO - __main__ - Step 24060: {'lr': 0.00047309033165217617, 'samples': 4619520, 'steps': 24059, 'loss/train': 2.148709535598755} 08/30/2021 17:30:25 - INFO - __main__ - Step 24061: {'lr': 0.00047308793655311855, 'samples': 4619712, 'steps': 24060, 'loss/train': 1.327816128730774} 08/30/2021 17:30:25 - INFO - __main__ - Step 24062: {'lr': 0.000473085541353541, 'samples': 4619904, 'steps': 24061, 'loss/train': 1.5505187511444092} 08/30/2021 17:30:25 - INFO - __main__ - Step 24063: {'lr': 0.00047308314605344447, 'samples': 4620096, 'steps': 24062, 'loss/train': 1.7892699241638184} 08/30/2021 17:30:28 - INFO - __main__ - Step 24064: {'lr': 0.00047308075065283006, 'samples': 4620288, 'steps': 24063, 'loss/train': 0.2885242700576782} 08/30/2021 17:30:28 - INFO - __main__ - Step 24065: {'lr': 0.00047307835515169905, 'samples': 4620480, 'steps': 24064, 'loss/train': 1.5652493238449097} 08/30/2021 17:30:29 - INFO - __main__ - Step 24066: {'lr': 0.00047307595955005226, 'samples': 4620672, 'steps': 24065, 'loss/train': 1.5013893842697144} 08/30/2021 17:30:29 - INFO - __main__ - Step 24067: {'lr': 0.000473073563847891, 'samples': 4620864, 'steps': 24066, 'loss/train': 1.1477336883544922} 08/30/2021 17:30:29 - INFO - __main__ - Step 24068: {'lr': 0.0004730711680452161, 'samples': 4621056, 'steps': 24067, 'loss/train': 1.3155384063720703} 08/30/2021 17:30:30 - INFO - __main__ - Step 24069: {'lr': 0.00047306877214202885, 'samples': 4621248, 'steps': 24068, 'loss/train': 1.609187364578247} 08/30/2021 17:30:31 - INFO - __main__ - Step 24070: {'lr': 0.00047306637613833024, 'samples': 4621440, 'steps': 24069, 'loss/train': 0.14481352269649506} 08/30/2021 17:30:32 - INFO - __main__ - Step 24071: {'lr': 0.00047306398003412137, 'samples': 4621632, 'steps': 24070, 'loss/train': 1.548281192779541} 08/30/2021 17:30:32 - INFO - __main__ - Step 24072: {'lr': 0.00047306158382940327, 'samples': 4621824, 'steps': 24071, 'loss/train': 1.4533778429031372} 08/30/2021 17:30:32 - INFO - __main__ - Step 24073: {'lr': 0.0004730591875241771, 'samples': 4622016, 'steps': 24072, 'loss/train': 1.5265815258026123} 08/30/2021 17:30:33 - INFO - __main__ - Step 24074: {'lr': 0.0004730567911184439, 'samples': 4622208, 'steps': 24073, 'loss/train': 1.9236773252487183} 08/30/2021 17:30:34 - INFO - __main__ - Step 24075: {'lr': 0.00047305439461220477, 'samples': 4622400, 'steps': 24074, 'loss/train': 1.5820451974868774} 08/30/2021 17:30:35 - INFO - __main__ - Step 24076: {'lr': 0.00047305199800546077, 'samples': 4622592, 'steps': 24075, 'loss/train': 1.6401923894882202} 08/30/2021 17:30:35 - INFO - __main__ - Step 24077: {'lr': 0.00047304960129821295, 'samples': 4622784, 'steps': 24076, 'loss/train': 1.445767879486084} 08/30/2021 17:30:35 - INFO - __main__ - Step 24078: {'lr': 0.00047304720449046247, 'samples': 4622976, 'steps': 24077, 'loss/train': 1.603904366493225} 08/30/2021 17:30:36 - INFO - __main__ - Step 24079: {'lr': 0.0004730448075822103, 'samples': 4623168, 'steps': 24078, 'loss/train': 1.342221975326538} 08/30/2021 17:30:37 - INFO - __main__ - Step 24080: {'lr': 0.0004730424105734576, 'samples': 4623360, 'steps': 24079, 'loss/train': 1.8074901103973389} 08/30/2021 17:30:38 - INFO - __main__ - Step 24081: {'lr': 0.00047304001346420543, 'samples': 4623552, 'steps': 24080, 'loss/train': 1.4292932748794556} 08/30/2021 17:30:38 - INFO - __main__ - Step 24082: {'lr': 0.0004730376162544549, 'samples': 4623744, 'steps': 24081, 'loss/train': 1.706549048423767} 08/30/2021 17:30:38 - INFO - __main__ - Step 24083: {'lr': 0.00047303521894420707, 'samples': 4623936, 'steps': 24082, 'loss/train': 1.5007423162460327} 08/30/2021 17:30:39 - INFO - __main__ - Step 24084: {'lr': 0.00047303282153346297, 'samples': 4624128, 'steps': 24083, 'loss/train': 1.8951566219329834} 08/30/2021 17:30:40 - INFO - __main__ - Step 24085: {'lr': 0.00047303042402222373, 'samples': 4624320, 'steps': 24084, 'loss/train': 1.940564751625061} 08/30/2021 17:30:41 - INFO - __main__ - Step 24086: {'lr': 0.00047302802641049045, 'samples': 4624512, 'steps': 24085, 'loss/train': 1.6670588254928589} 08/30/2021 17:30:41 - INFO - __main__ - Step 24087: {'lr': 0.00047302562869826415, 'samples': 4624704, 'steps': 24086, 'loss/train': 1.5259641408920288} 08/30/2021 17:30:41 - INFO - __main__ - Step 24088: {'lr': 0.000473023230885546, 'samples': 4624896, 'steps': 24087, 'loss/train': 1.1554542779922485} 08/30/2021 17:30:42 - INFO - __main__ - Step 24089: {'lr': 0.00047302083297233693, 'samples': 4625088, 'steps': 24088, 'loss/train': 0.5441455245018005} 08/30/2021 17:30:43 - INFO - __main__ - Step 24090: {'lr': 0.0004730184349586382, 'samples': 4625280, 'steps': 24089, 'loss/train': 1.6687731742858887} 08/30/2021 17:30:44 - INFO - __main__ - Step 24091: {'lr': 0.0004730160368444507, 'samples': 4625472, 'steps': 24090, 'loss/train': 1.3922580480575562} 08/30/2021 17:30:44 - INFO - __main__ - Step 24092: {'lr': 0.00047301363862977574, 'samples': 4625664, 'steps': 24091, 'loss/train': 1.4776488542556763} 08/30/2021 17:30:44 - INFO - __main__ - Step 24093: {'lr': 0.00047301124031461425, 'samples': 4625856, 'steps': 24092, 'loss/train': 2.0109939575195312} 08/30/2021 17:30:45 - INFO - __main__ - Step 24094: {'lr': 0.00047300884189896734, 'samples': 4626048, 'steps': 24093, 'loss/train': 1.547519564628601} 08/30/2021 17:30:46 - INFO - __main__ - Step 24095: {'lr': 0.00047300644338283597, 'samples': 4626240, 'steps': 24094, 'loss/train': 1.7417045831680298} 08/30/2021 17:30:47 - INFO - __main__ - Step 24096: {'lr': 0.00047300404476622145, 'samples': 4626432, 'steps': 24095, 'loss/train': 1.456769585609436} 08/30/2021 17:30:47 - INFO - __main__ - Step 24097: {'lr': 0.0004730016460491247, 'samples': 4626624, 'steps': 24096, 'loss/train': 1.4040253162384033} 08/30/2021 17:30:47 - INFO - __main__ - Step 24098: {'lr': 0.00047299924723154686, 'samples': 4626816, 'steps': 24097, 'loss/train': 1.5261404514312744} 08/30/2021 17:30:48 - INFO - __main__ - Step 24099: {'lr': 0.000472996848313489, 'samples': 4627008, 'steps': 24098, 'loss/train': 1.7699613571166992} 08/30/2021 17:30:49 - INFO - __main__ - Step 24100: {'lr': 0.0004729944492949523, 'samples': 4627200, 'steps': 24099, 'loss/train': 1.2860987186431885} 08/30/2021 17:30:50 - INFO - __main__ - Step 24101: {'lr': 0.0004729920501759376, 'samples': 4627392, 'steps': 24100, 'loss/train': 1.514662742614746} 08/30/2021 17:30:50 - INFO - __main__ - Step 24102: {'lr': 0.0004729896509564462, 'samples': 4627584, 'steps': 24101, 'loss/train': 0.47807011008262634} 08/30/2021 17:30:50 - INFO - __main__ - Step 24103: {'lr': 0.00047298725163647903, 'samples': 4627776, 'steps': 24102, 'loss/train': 2.083526372909546} 08/30/2021 17:30:51 - INFO - __main__ - Step 24104: {'lr': 0.00047298485221603735, 'samples': 4627968, 'steps': 24103, 'loss/train': 1.6912801265716553} 08/30/2021 17:30:52 - INFO - __main__ - Step 24105: {'lr': 0.0004729824526951221, 'samples': 4628160, 'steps': 24104, 'loss/train': 1.7747036218643188} 08/30/2021 17:30:53 - INFO - __main__ - Step 24106: {'lr': 0.0004729800530737344, 'samples': 4628352, 'steps': 24105, 'loss/train': 1.7489311695098877} 08/30/2021 17:30:53 - INFO - __main__ - Step 24107: {'lr': 0.0004729776533518753, 'samples': 4628544, 'steps': 24106, 'loss/train': 1.7768486738204956} 08/30/2021 17:30:53 - INFO - __main__ - Step 24108: {'lr': 0.00047297525352954587, 'samples': 4628736, 'steps': 24107, 'loss/train': 0.32257765531539917} 08/30/2021 17:30:54 - INFO - __main__ - Step 24109: {'lr': 0.00047297285360674724, 'samples': 4628928, 'steps': 24108, 'loss/train': 1.5983144044876099} 08/30/2021 17:30:56 - INFO - __main__ - Step 24110: {'lr': 0.0004729704535834806, 'samples': 4629120, 'steps': 24109, 'loss/train': 0.20864179730415344} 08/30/2021 17:30:57 - INFO - __main__ - Step 24111: {'lr': 0.0004729680534597468, 'samples': 4629312, 'steps': 24110, 'loss/train': 1.459895372390747} 08/30/2021 17:30:57 - INFO - __main__ - Step 24112: {'lr': 0.0004729656532355471, 'samples': 4629504, 'steps': 24111, 'loss/train': 1.8617894649505615} 08/30/2021 17:30:57 - INFO - __main__ - Step 24113: {'lr': 0.00047296325291088247, 'samples': 4629696, 'steps': 24112, 'loss/train': 1.8113024234771729} 08/30/2021 17:30:58 - INFO - __main__ - Step 24114: {'lr': 0.00047296085248575405, 'samples': 4629888, 'steps': 24113, 'loss/train': 1.8138296604156494} 08/30/2021 17:30:58 - INFO - __main__ - Step 24115: {'lr': 0.000472958451960163, 'samples': 4630080, 'steps': 24114, 'loss/train': 1.3801623582839966} 08/30/2021 17:30:58 - INFO - __main__ - Step 24116: {'lr': 0.0004729560513341101, 'samples': 4630272, 'steps': 24115, 'loss/train': 0.46274125576019287} 08/30/2021 17:31:00 - INFO - __main__ - Step 24117: {'lr': 0.0004729536506075969, 'samples': 4630464, 'steps': 24116, 'loss/train': 1.6889135837554932} 08/30/2021 17:31:01 - INFO - __main__ - Step 24118: {'lr': 0.000472951249780624, 'samples': 4630656, 'steps': 24117, 'loss/train': 0.9251886010169983} 08/30/2021 17:31:01 - INFO - __main__ - Step 24119: {'lr': 0.0004729488488531928, 'samples': 4630848, 'steps': 24118, 'loss/train': 1.5236133337020874} 08/30/2021 17:31:01 - INFO - __main__ - Step 24120: {'lr': 0.00047294644782530437, 'samples': 4631040, 'steps': 24119, 'loss/train': 1.7088730335235596} 08/30/2021 17:31:02 - INFO - __main__ - Step 24121: {'lr': 0.0004729440466969596, 'samples': 4631232, 'steps': 24120, 'loss/train': 1.5327494144439697} 08/30/2021 17:31:03 - INFO - __main__ - Step 24122: {'lr': 0.00047294164546815977, 'samples': 4631424, 'steps': 24121, 'loss/train': 1.44022798538208} 08/30/2021 17:31:04 - INFO - __main__ - Step 24123: {'lr': 0.0004729392441389058, 'samples': 4631616, 'steps': 24122, 'loss/train': 1.5222587585449219} 08/30/2021 17:31:04 - INFO - __main__ - Step 24124: {'lr': 0.0004729368427091989, 'samples': 4631808, 'steps': 24123, 'loss/train': 1.7540864944458008} 08/30/2021 17:31:04 - INFO - __main__ - Step 24125: {'lr': 0.0004729344411790401, 'samples': 4632000, 'steps': 24124, 'loss/train': 1.841918706893921} 08/30/2021 17:31:05 - INFO - __main__ - Step 24126: {'lr': 0.00047293203954843036, 'samples': 4632192, 'steps': 24125, 'loss/train': 1.6288747787475586} 08/30/2021 17:31:05 - INFO - __main__ - Step 24127: {'lr': 0.000472929637817371, 'samples': 4632384, 'steps': 24126, 'loss/train': 2.0986011028289795} 08/30/2021 17:31:07 - INFO - __main__ - Step 24128: {'lr': 0.00047292723598586295, 'samples': 4632576, 'steps': 24127, 'loss/train': 1.5108201503753662} 08/30/2021 17:31:07 - INFO - __main__ - Step 24129: {'lr': 0.0004729248340539074, 'samples': 4632768, 'steps': 24128, 'loss/train': 2.7759737968444824} 08/30/2021 17:31:08 - INFO - __main__ - Step 24130: {'lr': 0.00047292243202150524, 'samples': 4632960, 'steps': 24129, 'loss/train': 1.0917391777038574} 08/30/2021 17:31:08 - INFO - __main__ - Step 24131: {'lr': 0.00047292002988865773, 'samples': 4633152, 'steps': 24130, 'loss/train': 1.4824484586715698} 08/30/2021 17:31:08 - INFO - __main__ - Step 24132: {'lr': 0.0004729176276553659, 'samples': 4633344, 'steps': 24131, 'loss/train': 2.507643938064575} 08/30/2021 17:31:10 - INFO - __main__ - Step 24133: {'lr': 0.00047291522532163084, 'samples': 4633536, 'steps': 24132, 'loss/train': 1.381656289100647} 08/30/2021 17:31:10 - INFO - __main__ - Step 24134: {'lr': 0.0004729128228874536, 'samples': 4633728, 'steps': 24133, 'loss/train': 1.7645857334136963} 08/30/2021 17:31:11 - INFO - __main__ - Step 24135: {'lr': 0.0004729104203528353, 'samples': 4633920, 'steps': 24134, 'loss/train': 1.740995168685913} 08/30/2021 17:31:11 - INFO - __main__ - Step 24136: {'lr': 0.0004729080177177769, 'samples': 4634112, 'steps': 24135, 'loss/train': 1.6431689262390137} 08/30/2021 17:31:11 - INFO - __main__ - Step 24137: {'lr': 0.0004729056149822797, 'samples': 4634304, 'steps': 24136, 'loss/train': 2.0831339359283447} 08/30/2021 17:31:13 - INFO - __main__ - Step 24138: {'lr': 0.0004729032121463447, 'samples': 4634496, 'steps': 24137, 'loss/train': 1.8646323680877686} 08/30/2021 17:31:13 - INFO - __main__ - Step 24139: {'lr': 0.00047290080920997285, 'samples': 4634688, 'steps': 24138, 'loss/train': 1.3936610221862793} 08/30/2021 17:31:14 - INFO - __main__ - Step 24140: {'lr': 0.0004728984061731654, 'samples': 4634880, 'steps': 24139, 'loss/train': 1.1847268342971802} 08/30/2021 17:31:14 - INFO - __main__ - Step 24141: {'lr': 0.00047289600303592334, 'samples': 4635072, 'steps': 24140, 'loss/train': 2.7018134593963623} 08/30/2021 17:31:14 - INFO - __main__ - Step 24142: {'lr': 0.00047289359979824774, 'samples': 4635264, 'steps': 24141, 'loss/train': 1.3059297800064087} 08/30/2021 17:31:15 - INFO - __main__ - Step 24143: {'lr': 0.0004728911964601398, 'samples': 4635456, 'steps': 24142, 'loss/train': 1.1995608806610107} 08/30/2021 17:31:16 - INFO - __main__ - Step 24144: {'lr': 0.00047288879302160046, 'samples': 4635648, 'steps': 24143, 'loss/train': 1.5299186706542969} 08/30/2021 17:31:17 - INFO - __main__ - Step 24145: {'lr': 0.000472886389482631, 'samples': 4635840, 'steps': 24144, 'loss/train': 1.3630061149597168} 08/30/2021 17:31:17 - INFO - __main__ - Step 24146: {'lr': 0.00047288398584323225, 'samples': 4636032, 'steps': 24145, 'loss/train': 1.2673616409301758} 08/30/2021 17:31:18 - INFO - __main__ - Step 24147: {'lr': 0.0004728815821034055, 'samples': 4636224, 'steps': 24146, 'loss/train': 1.2929073572158813} 08/30/2021 17:31:18 - INFO - __main__ - Step 24148: {'lr': 0.00047287917826315163, 'samples': 4636416, 'steps': 24147, 'loss/train': 1.5669113397598267} 08/30/2021 17:31:19 - INFO - __main__ - Step 24149: {'lr': 0.00047287677432247187, 'samples': 4636608, 'steps': 24148, 'loss/train': 1.558624267578125} 08/30/2021 17:31:20 - INFO - __main__ - Step 24150: {'lr': 0.0004728743702813674, 'samples': 4636800, 'steps': 24149, 'loss/train': 1.7655826807022095} 08/30/2021 17:31:20 - INFO - __main__ - Step 24151: {'lr': 0.00047287196613983906, 'samples': 4636992, 'steps': 24150, 'loss/train': 1.4004069566726685} 08/30/2021 17:31:21 - INFO - __main__ - Step 24152: {'lr': 0.00047286956189788803, 'samples': 4637184, 'steps': 24151, 'loss/train': 1.6315075159072876} 08/30/2021 17:31:21 - INFO - __main__ - Step 24153: {'lr': 0.0004728671575555155, 'samples': 4637376, 'steps': 24152, 'loss/train': 1.4012001752853394} 08/30/2021 17:31:23 - INFO - __main__ - Step 24154: {'lr': 0.00047286475311272244, 'samples': 4637568, 'steps': 24153, 'loss/train': 1.7974354028701782} 08/30/2021 17:31:23 - INFO - __main__ - Step 24155: {'lr': 0.00047286234856950995, 'samples': 4637760, 'steps': 24154, 'loss/train': 1.489810585975647} 08/30/2021 17:31:23 - INFO - __main__ - Step 24156: {'lr': 0.0004728599439258791, 'samples': 4637952, 'steps': 24155, 'loss/train': 0.9652630686759949} 08/30/2021 17:31:24 - INFO - __main__ - Step 24157: {'lr': 0.00047285753918183105, 'samples': 4638144, 'steps': 24156, 'loss/train': 1.7588778734207153} 08/30/2021 17:31:24 - INFO - __main__ - Step 24158: {'lr': 0.0004728551343373668, 'samples': 4638336, 'steps': 24157, 'loss/train': 1.049881935119629} 08/30/2021 17:31:26 - INFO - __main__ - Step 24159: {'lr': 0.0004728527293924875, 'samples': 4638528, 'steps': 24158, 'loss/train': 1.8188709020614624} 08/30/2021 17:31:26 - INFO - __main__ - Step 24160: {'lr': 0.0004728503243471941, 'samples': 4638720, 'steps': 24159, 'loss/train': 1.3873933553695679} 08/30/2021 17:31:26 - INFO - __main__ - Step 24161: {'lr': 0.00047284791920148786, 'samples': 4638912, 'steps': 24160, 'loss/train': 1.9750440120697021} 08/30/2021 17:31:27 - INFO - __main__ - Step 24162: {'lr': 0.0004728455139553698, 'samples': 4639104, 'steps': 24161, 'loss/train': 1.8615262508392334} 08/30/2021 17:31:27 - INFO - __main__ - Step 24163: {'lr': 0.00047284310860884097, 'samples': 4639296, 'steps': 24162, 'loss/train': 0.7791587114334106} 08/30/2021 17:31:27 - INFO - __main__ - Step 24164: {'lr': 0.0004728407031619025, 'samples': 4639488, 'steps': 24163, 'loss/train': 1.7196199893951416} 08/30/2021 17:31:29 - INFO - __main__ - Step 24165: {'lr': 0.00047283829761455545, 'samples': 4639680, 'steps': 24164, 'loss/train': 1.6915156841278076} 08/30/2021 17:31:29 - INFO - __main__ - Step 24166: {'lr': 0.00047283589196680083, 'samples': 4639872, 'steps': 24165, 'loss/train': 1.31031334400177} 08/30/2021 17:31:30 - INFO - __main__ - Step 24167: {'lr': 0.00047283348621863987, 'samples': 4640064, 'steps': 24166, 'loss/train': 2.1443991661071777} 08/30/2021 17:31:30 - INFO - __main__ - Step 24168: {'lr': 0.0004728310803700735, 'samples': 4640256, 'steps': 24167, 'loss/train': 1.0439376831054688} 08/30/2021 17:31:30 - INFO - __main__ - Step 24169: {'lr': 0.00047282867442110296, 'samples': 4640448, 'steps': 24168, 'loss/train': 1.2532795667648315} 08/30/2021 17:31:32 - INFO - __main__ - Step 24170: {'lr': 0.0004728262683717292, 'samples': 4640640, 'steps': 24169, 'loss/train': 1.6778916120529175} 08/30/2021 17:31:32 - INFO - __main__ - Step 24171: {'lr': 0.0004728238622219534, 'samples': 4640832, 'steps': 24170, 'loss/train': 0.9244217872619629} 08/30/2021 17:31:33 - INFO - __main__ - Step 24172: {'lr': 0.0004728214559717766, 'samples': 4641024, 'steps': 24171, 'loss/train': 1.2623051404953003} 08/30/2021 17:31:33 - INFO - __main__ - Step 24173: {'lr': 0.0004728190496211999, 'samples': 4641216, 'steps': 24172, 'loss/train': 0.8274864554405212} 08/30/2021 17:31:33 - INFO - __main__ - Step 24174: {'lr': 0.0004728166431702243, 'samples': 4641408, 'steps': 24173, 'loss/train': 0.09556277096271515} 08/30/2021 17:31:36 - INFO - __main__ - Step 24175: {'lr': 0.0004728142366188511, 'samples': 4641600, 'steps': 24174, 'loss/train': 1.373371958732605} 08/30/2021 17:31:36 - INFO - __main__ - Step 24176: {'lr': 0.0004728118299670812, 'samples': 4641792, 'steps': 24175, 'loss/train': 1.5632140636444092} 08/30/2021 17:31:36 - INFO - __main__ - Step 24177: {'lr': 0.0004728094232149156, 'samples': 4641984, 'steps': 24176, 'loss/train': 1.4556348323822021} 08/30/2021 17:31:37 - INFO - __main__ - Step 24178: {'lr': 0.0004728070163623557, 'samples': 4642176, 'steps': 24177, 'loss/train': 1.4671134948730469} 08/30/2021 17:31:37 - INFO - __main__ - Step 24179: {'lr': 0.00047280460940940224, 'samples': 4642368, 'steps': 24178, 'loss/train': 1.8795233964920044} 08/30/2021 17:31:39 - INFO - __main__ - Step 24180: {'lr': 0.00047280220235605653, 'samples': 4642560, 'steps': 24179, 'loss/train': 1.7222018241882324} 08/30/2021 17:31:39 - INFO - __main__ - Step 24181: {'lr': 0.00047279979520231956, 'samples': 4642752, 'steps': 24180, 'loss/train': 1.2071528434753418} 08/30/2021 17:31:40 - INFO - __main__ - Step 24182: {'lr': 0.0004727973879481925, 'samples': 4642944, 'steps': 24181, 'loss/train': 1.6211045980453491} 08/30/2021 17:31:40 - INFO - __main__ - Step 24183: {'lr': 0.0004727949805936763, 'samples': 4643136, 'steps': 24182, 'loss/train': 0.08287215232849121} 08/30/2021 17:31:40 - INFO - __main__ - Step 24184: {'lr': 0.00047279257313877216, 'samples': 4643328, 'steps': 24183, 'loss/train': 1.7023415565490723} 08/30/2021 17:31:42 - INFO - __main__ - Step 24185: {'lr': 0.00047279016558348107, 'samples': 4643520, 'steps': 24184, 'loss/train': 1.1026681661605835} 08/30/2021 17:31:42 - INFO - __main__ - Step 24186: {'lr': 0.00047278775792780424, 'samples': 4643712, 'steps': 24185, 'loss/train': 1.096640706062317} 08/30/2021 17:31:43 - INFO - __main__ - Step 24187: {'lr': 0.00047278535017174266, 'samples': 4643904, 'steps': 24186, 'loss/train': 1.5994592905044556} 08/30/2021 17:31:43 - INFO - __main__ - Step 24188: {'lr': 0.00047278294231529745, 'samples': 4644096, 'steps': 24187, 'loss/train': 1.5921953916549683} 08/30/2021 17:31:43 - INFO - __main__ - Step 24189: {'lr': 0.0004727805343584697, 'samples': 4644288, 'steps': 24188, 'loss/train': 2.005462646484375} 08/30/2021 17:31:44 - INFO - __main__ - Step 24190: {'lr': 0.00047277812630126044, 'samples': 4644480, 'steps': 24189, 'loss/train': 1.9981228113174438} 08/30/2021 17:31:45 - INFO - __main__ - Step 24191: {'lr': 0.0004727757181436708, 'samples': 4644672, 'steps': 24190, 'loss/train': 2.7588233947753906} 08/30/2021 17:31:46 - INFO - __main__ - Step 24192: {'lr': 0.0004727733098857019, 'samples': 4644864, 'steps': 24191, 'loss/train': 1.3896721601486206} 08/30/2021 17:31:46 - INFO - __main__ - Step 24193: {'lr': 0.0004727709015273547, 'samples': 4645056, 'steps': 24192, 'loss/train': 1.611689567565918} 08/30/2021 17:31:46 - INFO - __main__ - Step 24194: {'lr': 0.00047276849306863045, 'samples': 4645248, 'steps': 24193, 'loss/train': 1.6118241548538208} 08/30/2021 17:31:47 - INFO - __main__ - Step 24195: {'lr': 0.0004727660845095301, 'samples': 4645440, 'steps': 24194, 'loss/train': 1.285235047340393} 08/30/2021 17:31:48 - INFO - __main__ - Step 24196: {'lr': 0.0004727636758500548, 'samples': 4645632, 'steps': 24195, 'loss/train': 2.496720552444458} 08/30/2021 17:31:49 - INFO - __main__ - Step 24197: {'lr': 0.0004727612670902057, 'samples': 4645824, 'steps': 24196, 'loss/train': 1.511696457862854} 08/30/2021 17:31:49 - INFO - __main__ - Step 24198: {'lr': 0.0004727588582299837, 'samples': 4646016, 'steps': 24197, 'loss/train': 1.4814748764038086} 08/30/2021 17:31:50 - INFO - __main__ - Step 24199: {'lr': 0.00047275644926939004, 'samples': 4646208, 'steps': 24198, 'loss/train': 1.5196963548660278} 08/30/2021 17:31:50 - INFO - __main__ - Step 24200: {'lr': 0.0004727540402084258, 'samples': 4646400, 'steps': 24199, 'loss/train': 0.9592801332473755} 08/30/2021 17:31:52 - INFO - __main__ - Step 24201: {'lr': 0.00047275163104709196, 'samples': 4646592, 'steps': 24200, 'loss/train': 1.3029142618179321} 08/30/2021 17:31:52 - INFO - __main__ - Step 24202: {'lr': 0.0004727492217853897, 'samples': 4646784, 'steps': 24201, 'loss/train': 1.6478257179260254} 08/30/2021 17:31:53 - INFO - __main__ - Step 24203: {'lr': 0.0004727468124233201, 'samples': 4646976, 'steps': 24202, 'loss/train': 0.0755089670419693} 08/30/2021 17:31:53 - INFO - __main__ - Step 24204: {'lr': 0.0004727444029608842, 'samples': 4647168, 'steps': 24203, 'loss/train': 1.6308687925338745} 08/30/2021 17:31:53 - INFO - __main__ - Step 24205: {'lr': 0.0004727419933980831, 'samples': 4647360, 'steps': 24204, 'loss/train': 0.07464733719825745} 08/30/2021 17:31:54 - INFO - __main__ - Step 24206: {'lr': 0.00047273958373491795, 'samples': 4647552, 'steps': 24205, 'loss/train': 1.1177918910980225} 08/30/2021 17:31:55 - INFO - __main__ - Step 24207: {'lr': 0.0004727371739713897, 'samples': 4647744, 'steps': 24206, 'loss/train': 1.2107316255569458} 08/30/2021 17:31:56 - INFO - __main__ - Step 24208: {'lr': 0.0004727347641074996, 'samples': 4647936, 'steps': 24207, 'loss/train': 0.38301005959510803} 08/30/2021 17:31:56 - INFO - __main__ - Step 24209: {'lr': 0.0004727323541432486, 'samples': 4648128, 'steps': 24208, 'loss/train': 1.2750030755996704} 08/30/2021 17:31:56 - INFO - __main__ - Step 24210: {'lr': 0.0004727299440786378, 'samples': 4648320, 'steps': 24209, 'loss/train': 0.07609347999095917} 08/30/2021 17:31:57 - INFO - __main__ - Step 24211: {'lr': 0.0004727275339136684, 'samples': 4648512, 'steps': 24210, 'loss/train': 1.7404375076293945} 08/30/2021 17:31:58 - INFO - __main__ - Step 24212: {'lr': 0.0004727251236483414, 'samples': 4648704, 'steps': 24211, 'loss/train': 1.6821720600128174} 08/30/2021 17:31:59 - INFO - __main__ - Step 24213: {'lr': 0.0004727227132826579, 'samples': 4648896, 'steps': 24212, 'loss/train': 0.4785604774951935} 08/30/2021 17:31:59 - INFO - __main__ - Step 24214: {'lr': 0.00047272030281661894, 'samples': 4649088, 'steps': 24213, 'loss/train': 1.7701137065887451} 08/30/2021 17:31:59 - INFO - __main__ - Step 24215: {'lr': 0.0004727178922502257, 'samples': 4649280, 'steps': 24214, 'loss/train': 1.6530342102050781} 08/30/2021 17:32:00 - INFO - __main__ - Step 24216: {'lr': 0.00047271548158347917, 'samples': 4649472, 'steps': 24215, 'loss/train': 1.57979154586792} 08/30/2021 17:32:01 - INFO - __main__ - Step 24217: {'lr': 0.00047271307081638047, 'samples': 4649664, 'steps': 24216, 'loss/train': 1.8712079524993896} 08/30/2021 17:32:02 - INFO - __main__ - Step 24218: {'lr': 0.0004727106599489307, 'samples': 4649856, 'steps': 24217, 'loss/train': 1.3714122772216797} 08/30/2021 17:32:02 - INFO - __main__ - Step 24219: {'lr': 0.000472708248981131, 'samples': 4650048, 'steps': 24218, 'loss/train': 1.398590087890625} 08/30/2021 17:32:03 - INFO - __main__ - Step 24220: {'lr': 0.0004727058379129824, 'samples': 4650240, 'steps': 24219, 'loss/train': 2.153866767883301} 08/30/2021 17:32:03 - INFO - __main__ - Step 24221: {'lr': 0.00047270342674448593, 'samples': 4650432, 'steps': 24220, 'loss/train': 1.706506371498108} 08/30/2021 17:32:03 - INFO - __main__ - Step 24222: {'lr': 0.0004727010154756427, 'samples': 4650624, 'steps': 24221, 'loss/train': 1.6973432302474976} 08/30/2021 17:32:05 - INFO - __main__ - Step 24223: {'lr': 0.00047269860410645395, 'samples': 4650816, 'steps': 24222, 'loss/train': 0.9720464944839478} 08/30/2021 17:32:05 - INFO - __main__ - Step 24224: {'lr': 0.00047269619263692056, 'samples': 4651008, 'steps': 24223, 'loss/train': 1.3337974548339844} 08/30/2021 17:32:06 - INFO - __main__ - Step 24225: {'lr': 0.0004726937810670437, 'samples': 4651200, 'steps': 24224, 'loss/train': 1.5803866386413574} 08/30/2021 17:32:06 - INFO - __main__ - Step 24226: {'lr': 0.00047269136939682445, 'samples': 4651392, 'steps': 24225, 'loss/train': 2.019972801208496} 08/30/2021 17:32:06 - INFO - __main__ - Step 24227: {'lr': 0.00047268895762626396, 'samples': 4651584, 'steps': 24226, 'loss/train': 1.2218983173370361} 08/30/2021 17:32:08 - INFO - __main__ - Step 24228: {'lr': 0.00047268654575536326, 'samples': 4651776, 'steps': 24227, 'loss/train': 1.298556923866272} 08/30/2021 17:32:09 - INFO - __main__ - Step 24229: {'lr': 0.0004726841337841234, 'samples': 4651968, 'steps': 24228, 'loss/train': 1.2394062280654907} 08/30/2021 17:32:09 - INFO - __main__ - Step 24230: {'lr': 0.00047268172171254554, 'samples': 4652160, 'steps': 24229, 'loss/train': 0.9660944938659668} 08/30/2021 17:32:09 - INFO - __main__ - Step 24231: {'lr': 0.00047267930954063064, 'samples': 4652352, 'steps': 24230, 'loss/train': 1.059150218963623} 08/30/2021 17:32:10 - INFO - __main__ - Step 24232: {'lr': 0.00047267689726838004, 'samples': 4652544, 'steps': 24231, 'loss/train': 1.8086531162261963} 08/30/2021 17:32:12 - INFO - __main__ - Step 24233: {'lr': 0.00047267448489579455, 'samples': 4652736, 'steps': 24232, 'loss/train': 1.8478260040283203} 08/30/2021 17:32:12 - INFO - __main__ - Step 24234: {'lr': 0.00047267207242287536, 'samples': 4652928, 'steps': 24233, 'loss/train': 1.5857752561569214} 08/30/2021 17:32:12 - INFO - __main__ - Step 24235: {'lr': 0.0004726696598496236, 'samples': 4653120, 'steps': 24234, 'loss/train': 0.16051620244979858} 08/30/2021 17:32:13 - INFO - __main__ - Step 24236: {'lr': 0.0004726672471760404, 'samples': 4653312, 'steps': 24235, 'loss/train': 1.6289249658584595} 08/30/2021 17:32:13 - INFO - __main__ - Step 24237: {'lr': 0.0004726648344021267, 'samples': 4653504, 'steps': 24236, 'loss/train': 1.943662405014038} 08/30/2021 17:32:14 - INFO - __main__ - Step 24238: {'lr': 0.0004726624215278836, 'samples': 4653696, 'steps': 24237, 'loss/train': 1.3714585304260254} 08/30/2021 17:32:15 - INFO - __main__ - Step 24239: {'lr': 0.0004726600085533124, 'samples': 4653888, 'steps': 24238, 'loss/train': 0.8313621282577515} 08/30/2021 17:32:16 - INFO - __main__ - Step 24240: {'lr': 0.0004726575954784139, 'samples': 4654080, 'steps': 24239, 'loss/train': 1.6338189840316772} 08/30/2021 17:32:16 - INFO - __main__ - Step 24241: {'lr': 0.0004726551823031894, 'samples': 4654272, 'steps': 24240, 'loss/train': 0.32059958577156067} 08/30/2021 17:32:16 - INFO - __main__ - Step 24242: {'lr': 0.0004726527690276399, 'samples': 4654464, 'steps': 24241, 'loss/train': 1.0379594564437866} 08/30/2021 17:32:17 - INFO - __main__ - Step 24243: {'lr': 0.0004726503556517665, 'samples': 4654656, 'steps': 24242, 'loss/train': 0.9742986559867859} 08/30/2021 17:32:19 - INFO - __main__ - Step 24244: {'lr': 0.0004726479421755703, 'samples': 4654848, 'steps': 24243, 'loss/train': 1.7805272340774536} 08/30/2021 17:32:19 - INFO - __main__ - Step 24245: {'lr': 0.0004726455285990523, 'samples': 4655040, 'steps': 24244, 'loss/train': 1.415780782699585} 08/30/2021 17:32:20 - INFO - __main__ - Step 24246: {'lr': 0.00047264311492221375, 'samples': 4655232, 'steps': 24245, 'loss/train': 1.180909514427185} 08/30/2021 17:32:20 - INFO - __main__ - Step 24247: {'lr': 0.00047264070114505556, 'samples': 4655424, 'steps': 24246, 'loss/train': 1.2102290391921997} 08/30/2021 17:32:20 - INFO - __main__ - Step 24248: {'lr': 0.00047263828726757897, 'samples': 4655616, 'steps': 24247, 'loss/train': 1.481451153755188} 08/30/2021 17:32:21 - INFO - __main__ - Step 24249: {'lr': 0.00047263587328978495, 'samples': 4655808, 'steps': 24248, 'loss/train': 0.053167395293712616} 08/30/2021 17:32:22 - INFO - __main__ - Step 24250: {'lr': 0.00047263345921167473, 'samples': 4656000, 'steps': 24249, 'loss/train': 0.05923473462462425} 08/30/2021 17:32:23 - INFO - __main__ - Step 24251: {'lr': 0.00047263104503324926, 'samples': 4656192, 'steps': 24250, 'loss/train': 1.8162950277328491} 08/30/2021 17:32:23 - INFO - __main__ - Step 24252: {'lr': 0.00047262863075450966, 'samples': 4656384, 'steps': 24251, 'loss/train': 1.594192624092102} 08/30/2021 17:32:23 - INFO - __main__ - Step 24253: {'lr': 0.0004726262163754571, 'samples': 4656576, 'steps': 24252, 'loss/train': 1.113451361656189} 08/30/2021 17:32:24 - INFO - __main__ - Step 24254: {'lr': 0.00047262380189609253, 'samples': 4656768, 'steps': 24253, 'loss/train': 1.1306809186935425} 08/30/2021 17:32:25 - INFO - __main__ - Step 24255: {'lr': 0.0004726213873164171, 'samples': 4656960, 'steps': 24254, 'loss/train': 1.96120285987854} 08/30/2021 17:32:25 - INFO - __main__ - Step 24256: {'lr': 0.00047261897263643196, 'samples': 4657152, 'steps': 24255, 'loss/train': 1.1570863723754883} 08/30/2021 17:32:26 - INFO - __main__ - Step 24257: {'lr': 0.0004726165578561381, 'samples': 4657344, 'steps': 24256, 'loss/train': 1.8087940216064453} 08/30/2021 17:32:26 - INFO - __main__ - Step 24258: {'lr': 0.0004726141429755367, 'samples': 4657536, 'steps': 24257, 'loss/train': 1.9370120763778687} 08/30/2021 17:32:27 - INFO - __main__ - Step 24259: {'lr': 0.0004726117279946288, 'samples': 4657728, 'steps': 24258, 'loss/train': 1.0272470712661743} 08/30/2021 17:32:27 - INFO - __main__ - Step 24260: {'lr': 0.0004726093129134155, 'samples': 4657920, 'steps': 24259, 'loss/train': 1.2489008903503418} 08/30/2021 17:32:28 - INFO - __main__ - Step 24261: {'lr': 0.0004726068977318978, 'samples': 4658112, 'steps': 24260, 'loss/train': 1.3908486366271973} 08/30/2021 17:32:29 - INFO - __main__ - Step 24262: {'lr': 0.0004726044824500769, 'samples': 4658304, 'steps': 24261, 'loss/train': 1.5788671970367432} 08/30/2021 17:32:29 - INFO - __main__ - Step 24263: {'lr': 0.0004726020670679538, 'samples': 4658496, 'steps': 24262, 'loss/train': 1.5976192951202393} 08/30/2021 17:32:29 - INFO - __main__ - Step 24264: {'lr': 0.00047259965158552976, 'samples': 4658688, 'steps': 24263, 'loss/train': 1.7133711576461792} 08/30/2021 17:32:30 - INFO - __main__ - Step 24265: {'lr': 0.00047259723600280573, 'samples': 4658880, 'steps': 24264, 'loss/train': 1.972362756729126} 08/30/2021 17:32:31 - INFO - __main__ - Step 24266: {'lr': 0.0004725948203197828, 'samples': 4659072, 'steps': 24265, 'loss/train': 1.0435600280761719} 08/30/2021 17:32:32 - INFO - __main__ - Step 24267: {'lr': 0.0004725924045364621, 'samples': 4659264, 'steps': 24266, 'loss/train': 1.598348617553711} 08/30/2021 17:32:32 - INFO - __main__ - Step 24268: {'lr': 0.00047258998865284463, 'samples': 4659456, 'steps': 24267, 'loss/train': 1.8444726467132568} 08/30/2021 17:32:32 - INFO - __main__ - Step 24269: {'lr': 0.0004725875726689316, 'samples': 4659648, 'steps': 24268, 'loss/train': 1.5474190711975098} 08/30/2021 17:32:33 - INFO - __main__ - Step 24270: {'lr': 0.000472585156584724, 'samples': 4659840, 'steps': 24269, 'loss/train': 0.962842583656311} 08/30/2021 17:32:35 - INFO - __main__ - Step 24271: {'lr': 0.00047258274040022305, 'samples': 4660032, 'steps': 24270, 'loss/train': 1.7693638801574707} 08/30/2021 17:32:35 - INFO - __main__ - Step 24272: {'lr': 0.0004725803241154297, 'samples': 4660224, 'steps': 24271, 'loss/train': 1.7162286043167114} 08/30/2021 17:32:36 - INFO - __main__ - Step 24273: {'lr': 0.0004725779077303451, 'samples': 4660416, 'steps': 24272, 'loss/train': 1.45207679271698} 08/30/2021 17:32:36 - INFO - __main__ - Step 24274: {'lr': 0.0004725754912449703, 'samples': 4660608, 'steps': 24273, 'loss/train': 1.6680254936218262} 08/30/2021 17:32:36 - INFO - __main__ - Step 24275: {'lr': 0.0004725730746593064, 'samples': 4660800, 'steps': 24274, 'loss/train': 1.67513906955719} 08/30/2021 17:32:37 - INFO - __main__ - Step 24276: {'lr': 0.0004725706579733546, 'samples': 4660992, 'steps': 24275, 'loss/train': 0.5670360326766968} 08/30/2021 17:32:38 - INFO - __main__ - Step 24277: {'lr': 0.00047256824118711583, 'samples': 4661184, 'steps': 24276, 'loss/train': 0.58359295129776} 08/30/2021 17:32:39 - INFO - __main__ - Step 24278: {'lr': 0.00047256582430059126, 'samples': 4661376, 'steps': 24277, 'loss/train': 1.6768839359283447} 08/30/2021 17:32:39 - INFO - __main__ - Step 24279: {'lr': 0.00047256340731378194, 'samples': 4661568, 'steps': 24278, 'loss/train': 1.20183527469635} 08/30/2021 17:32:39 - INFO - __main__ - Step 24280: {'lr': 0.00047256099022668896, 'samples': 4661760, 'steps': 24279, 'loss/train': 1.9832605123519897} 08/30/2021 17:32:40 - INFO - __main__ - Step 24281: {'lr': 0.00047255857303931347, 'samples': 4661952, 'steps': 24280, 'loss/train': 1.5650697946548462} 08/30/2021 17:32:42 - INFO - __main__ - Step 24282: {'lr': 0.00047255615575165653, 'samples': 4662144, 'steps': 24281, 'loss/train': 1.5526493787765503} 08/30/2021 17:32:42 - INFO - __main__ - Step 24283: {'lr': 0.0004725537383637193, 'samples': 4662336, 'steps': 24282, 'loss/train': 1.8533439636230469} 08/30/2021 17:32:42 - INFO - __main__ - Step 24284: {'lr': 0.0004725513208755027, 'samples': 4662528, 'steps': 24283, 'loss/train': 1.8512705564498901} 08/30/2021 17:32:43 - INFO - __main__ - Step 24285: {'lr': 0.0004725489032870079, 'samples': 4662720, 'steps': 24284, 'loss/train': 1.6501190662384033} 08/30/2021 17:32:43 - INFO - __main__ - Step 24286: {'lr': 0.000472546485598236, 'samples': 4662912, 'steps': 24285, 'loss/train': 1.2825064659118652} 08/30/2021 17:32:45 - INFO - __main__ - Step 24287: {'lr': 0.0004725440678091881, 'samples': 4663104, 'steps': 24286, 'loss/train': 1.427514672279358} 08/30/2021 17:32:45 - INFO - __main__ - Step 24288: {'lr': 0.00047254164991986525, 'samples': 4663296, 'steps': 24287, 'loss/train': 1.4465891122817993} 08/30/2021 17:32:46 - INFO - __main__ - Step 24289: {'lr': 0.0004725392319302686, 'samples': 4663488, 'steps': 24288, 'loss/train': 1.5587409734725952} 08/30/2021 17:32:46 - INFO - __main__ - Step 24290: {'lr': 0.0004725368138403992, 'samples': 4663680, 'steps': 24289, 'loss/train': 2.178434371948242} 08/30/2021 17:32:46 - INFO - __main__ - Step 24291: {'lr': 0.00047253439565025815, 'samples': 4663872, 'steps': 24290, 'loss/train': 1.6974729299545288} 08/30/2021 17:32:47 - INFO - __main__ - Step 24292: {'lr': 0.00047253197735984653, 'samples': 4664064, 'steps': 24291, 'loss/train': 1.7663254737854004} 08/30/2021 17:32:48 - INFO - __main__ - Step 24293: {'lr': 0.00047252955896916546, 'samples': 4664256, 'steps': 24292, 'loss/train': 0.25294041633605957} 08/30/2021 17:32:49 - INFO - __main__ - Step 24294: {'lr': 0.000472527140478216, 'samples': 4664448, 'steps': 24293, 'loss/train': 1.2851003408432007} 08/30/2021 17:32:49 - INFO - __main__ - Step 24295: {'lr': 0.00047252472188699917, 'samples': 4664640, 'steps': 24294, 'loss/train': 1.701158046722412} 08/30/2021 17:32:49 - INFO - __main__ - Step 24296: {'lr': 0.0004725223031955162, 'samples': 4664832, 'steps': 24295, 'loss/train': 1.6793968677520752} 08/30/2021 17:32:50 - INFO - __main__ - Step 24297: {'lr': 0.0004725198844037681, 'samples': 4665024, 'steps': 24296, 'loss/train': 1.1335865259170532} 08/30/2021 17:32:51 - INFO - __main__ - Step 24298: {'lr': 0.00047251746551175603, 'samples': 4665216, 'steps': 24297, 'loss/train': 3.253445863723755} 08/30/2021 17:32:52 - INFO - __main__ - Step 24299: {'lr': 0.000472515046519481, 'samples': 4665408, 'steps': 24298, 'loss/train': 1.2532851696014404} 08/30/2021 17:32:52 - INFO - __main__ - Step 24300: {'lr': 0.000472512627426944, 'samples': 4665600, 'steps': 24299, 'loss/train': 1.5509803295135498} 08/30/2021 17:32:52 - INFO - __main__ - Step 24301: {'lr': 0.0004725102082341464, 'samples': 4665792, 'steps': 24300, 'loss/train': 1.648585319519043} 08/30/2021 17:32:53 - INFO - __main__ - Step 24302: {'lr': 0.00047250778894108905, 'samples': 4665984, 'steps': 24301, 'loss/train': 1.331283688545227} 08/30/2021 17:32:54 - INFO - __main__ - Step 24303: {'lr': 0.0004725053695477731, 'samples': 4666176, 'steps': 24302, 'loss/train': 1.0451349020004272} 08/30/2021 17:32:55 - INFO - __main__ - Step 24304: {'lr': 0.0004725029500541997, 'samples': 4666368, 'steps': 24303, 'loss/train': 2.3015499114990234} 08/30/2021 17:32:55 - INFO - __main__ - Step 24305: {'lr': 0.00047250053046036996, 'samples': 4666560, 'steps': 24304, 'loss/train': 1.9148674011230469} 08/30/2021 17:32:55 - INFO - __main__ - Step 24306: {'lr': 0.00047249811076628483, 'samples': 4666752, 'steps': 24305, 'loss/train': 1.507433533668518} 08/30/2021 17:32:56 - INFO - __main__ - Step 24307: {'lr': 0.00047249569097194554, 'samples': 4666944, 'steps': 24306, 'loss/train': 1.850820779800415} 08/30/2021 17:32:58 - INFO - __main__ - Step 24308: {'lr': 0.0004724932710773531, 'samples': 4667136, 'steps': 24307, 'loss/train': 1.5423920154571533} 08/30/2021 17:32:58 - INFO - __main__ - Step 24309: {'lr': 0.00047249085108250867, 'samples': 4667328, 'steps': 24308, 'loss/train': 1.714725375175476} 08/30/2021 17:32:59 - INFO - __main__ - Step 24310: {'lr': 0.0004724884309874132, 'samples': 4667520, 'steps': 24309, 'loss/train': 1.6923638582229614} 08/30/2021 17:32:59 - INFO - __main__ - Step 24311: {'lr': 0.00047248601079206797, 'samples': 4667712, 'steps': 24310, 'loss/train': 1.9769870042800903} 08/30/2021 17:32:59 - INFO - __main__ - Step 24312: {'lr': 0.0004724835904964739, 'samples': 4667904, 'steps': 24311, 'loss/train': 1.5941286087036133} 08/30/2021 17:33:00 - INFO - __main__ - Step 24313: {'lr': 0.0004724811701006322, 'samples': 4668096, 'steps': 24312, 'loss/train': 0.18794506788253784} 08/30/2021 17:33:01 - INFO - __main__ - Step 24314: {'lr': 0.00047247874960454394, 'samples': 4668288, 'steps': 24313, 'loss/train': 1.3424668312072754} 08/30/2021 17:33:02 - INFO - __main__ - Step 24315: {'lr': 0.0004724763290082102, 'samples': 4668480, 'steps': 24314, 'loss/train': 2.002727746963501} 08/30/2021 17:33:02 - INFO - __main__ - Step 24316: {'lr': 0.000472473908311632, 'samples': 4668672, 'steps': 24315, 'loss/train': 1.3826675415039062} 08/30/2021 17:33:02 - INFO - __main__ - Step 24317: {'lr': 0.0004724714875148105, 'samples': 4668864, 'steps': 24316, 'loss/train': 1.2146414518356323} 08/30/2021 17:33:03 - INFO - __main__ - Step 24318: {'lr': 0.0004724690666177468, 'samples': 4669056, 'steps': 24317, 'loss/train': 1.3559935092926025} 08/30/2021 17:33:04 - INFO - __main__ - Step 24319: {'lr': 0.00047246664562044193, 'samples': 4669248, 'steps': 24318, 'loss/train': 1.227448582649231} 08/30/2021 17:33:05 - INFO - __main__ - Step 24320: {'lr': 0.0004724642245228971, 'samples': 4669440, 'steps': 24319, 'loss/train': 1.6217232942581177} 08/30/2021 17:33:05 - INFO - __main__ - Step 24321: {'lr': 0.0004724618033251133, 'samples': 4669632, 'steps': 24320, 'loss/train': 2.008260726928711} 08/30/2021 17:33:05 - INFO - __main__ - Step 24322: {'lr': 0.0004724593820270916, 'samples': 4669824, 'steps': 24321, 'loss/train': 1.8731880187988281} 08/30/2021 17:33:06 - INFO - __main__ - Step 24323: {'lr': 0.00047245696062883316, 'samples': 4670016, 'steps': 24322, 'loss/train': 1.4362927675247192} 08/30/2021 17:33:07 - INFO - __main__ - Step 24324: {'lr': 0.0004724545391303391, 'samples': 4670208, 'steps': 24323, 'loss/train': 1.5768028497695923} 08/30/2021 17:33:08 - INFO - __main__ - Step 24325: {'lr': 0.0004724521175316103, 'samples': 4670400, 'steps': 24324, 'loss/train': 1.0141940116882324} 08/30/2021 17:33:08 - INFO - __main__ - Step 24326: {'lr': 0.0004724496958326482, 'samples': 4670592, 'steps': 24325, 'loss/train': 1.013269305229187} 08/30/2021 17:33:08 - INFO - __main__ - Step 24327: {'lr': 0.00047244727403345356, 'samples': 4670784, 'steps': 24326, 'loss/train': 1.1677967309951782} 08/30/2021 17:33:09 - INFO - __main__ - Step 24328: {'lr': 0.00047244485213402765, 'samples': 4670976, 'steps': 24327, 'loss/train': 1.6913164854049683} 08/30/2021 17:33:10 - INFO - __main__ - Step 24329: {'lr': 0.0004724424301343716, 'samples': 4671168, 'steps': 24328, 'loss/train': 1.6653810739517212} 08/30/2021 17:33:11 - INFO - __main__ - Step 24330: {'lr': 0.00047244000803448635, 'samples': 4671360, 'steps': 24329, 'loss/train': 0.9741966724395752} 08/30/2021 17:33:11 - INFO - __main__ - Step 24331: {'lr': 0.000472437585834373, 'samples': 4671552, 'steps': 24330, 'loss/train': 1.6117873191833496} 08/30/2021 17:33:12 - INFO - __main__ - Step 24332: {'lr': 0.00047243516353403283, 'samples': 4671744, 'steps': 24331, 'loss/train': 1.9478338956832886} 08/30/2021 17:33:12 - INFO - __main__ - Step 24333: {'lr': 0.0004724327411334668, 'samples': 4671936, 'steps': 24332, 'loss/train': 1.7630128860473633} 08/30/2021 17:33:12 - INFO - __main__ - Step 24334: {'lr': 0.00047243031863267594, 'samples': 4672128, 'steps': 24333, 'loss/train': 1.1125938892364502} 08/30/2021 17:33:14 - INFO - __main__ - Step 24335: {'lr': 0.0004724278960316615, 'samples': 4672320, 'steps': 24334, 'loss/train': 1.0044838190078735} 08/30/2021 17:33:14 - INFO - __main__ - Step 24336: {'lr': 0.00047242547333042434, 'samples': 4672512, 'steps': 24335, 'loss/train': 1.2330117225646973} 08/30/2021 17:33:15 - INFO - __main__ - Step 24337: {'lr': 0.0004724230505289658, 'samples': 4672704, 'steps': 24336, 'loss/train': 1.748183250427246} 08/30/2021 17:33:15 - INFO - __main__ - Step 24338: {'lr': 0.0004724206276272868, 'samples': 4672896, 'steps': 24337, 'loss/train': 1.4580626487731934} 08/30/2021 17:33:15 - INFO - __main__ - Step 24339: {'lr': 0.0004724182046253885, 'samples': 4673088, 'steps': 24338, 'loss/train': 0.9954025149345398} 08/30/2021 17:33:17 - INFO - __main__ - Step 24340: {'lr': 0.0004724157815232721, 'samples': 4673280, 'steps': 24339, 'loss/train': 1.7079565525054932} 08/30/2021 17:33:18 - INFO - __main__ - Step 24341: {'lr': 0.00047241335832093844, 'samples': 4673472, 'steps': 24340, 'loss/train': 1.7329707145690918} 08/30/2021 17:33:18 - INFO - __main__ - Step 24342: {'lr': 0.00047241093501838887, 'samples': 4673664, 'steps': 24341, 'loss/train': 1.664844274520874} 08/30/2021 17:33:19 - INFO - __main__ - Step 24343: {'lr': 0.00047240851161562433, 'samples': 4673856, 'steps': 24342, 'loss/train': 1.1673303842544556} 08/30/2021 17:33:19 - INFO - __main__ - Step 24344: {'lr': 0.00047240608811264595, 'samples': 4674048, 'steps': 24343, 'loss/train': 1.3469853401184082} 08/30/2021 17:33:21 - INFO - __main__ - Step 24345: {'lr': 0.0004724036645094548, 'samples': 4674240, 'steps': 24344, 'loss/train': 1.9298440217971802} 08/30/2021 17:33:21 - INFO - __main__ - Step 24346: {'lr': 0.00047240124080605197, 'samples': 4674432, 'steps': 24345, 'loss/train': 1.7860263586044312} 08/30/2021 17:33:21 - INFO - __main__ - Step 24347: {'lr': 0.0004723988170024386, 'samples': 4674624, 'steps': 24346, 'loss/train': 1.76042902469635} 08/30/2021 17:33:22 - INFO - __main__ - Step 24348: {'lr': 0.0004723963930986157, 'samples': 4674816, 'steps': 24347, 'loss/train': 1.1373618841171265} 08/30/2021 17:33:22 - INFO - __main__ - Step 24349: {'lr': 0.0004723939690945845, 'samples': 4675008, 'steps': 24348, 'loss/train': 0.9944627285003662} 08/30/2021 17:33:22 - INFO - __main__ - Step 24350: {'lr': 0.000472391544990346, 'samples': 4675200, 'steps': 24349, 'loss/train': 1.1673153638839722} 08/30/2021 17:33:24 - INFO - __main__ - Step 24351: {'lr': 0.0004723891207859012, 'samples': 4675392, 'steps': 24350, 'loss/train': 1.4055306911468506} 08/30/2021 17:33:24 - INFO - __main__ - Step 24352: {'lr': 0.00047238669648125146, 'samples': 4675584, 'steps': 24351, 'loss/train': 2.0462114810943604} 08/30/2021 17:33:25 - INFO - __main__ - Step 24353: {'lr': 0.00047238427207639755, 'samples': 4675776, 'steps': 24352, 'loss/train': 1.9095929861068726} 08/30/2021 17:33:25 - INFO - __main__ - Step 24354: {'lr': 0.0004723818475713408, 'samples': 4675968, 'steps': 24353, 'loss/train': 1.2838232517242432} 08/30/2021 17:33:25 - INFO - __main__ - Step 24355: {'lr': 0.00047237942296608223, 'samples': 4676160, 'steps': 24354, 'loss/train': 1.488679051399231} 08/30/2021 17:33:27 - INFO - __main__ - Step 24356: {'lr': 0.00047237699826062286, 'samples': 4676352, 'steps': 24355, 'loss/train': 1.953740119934082} 08/30/2021 17:33:27 - INFO - __main__ - Step 24357: {'lr': 0.0004723745734549639, 'samples': 4676544, 'steps': 24356, 'loss/train': 1.2457115650177002} 08/30/2021 17:33:28 - INFO - __main__ - Step 24358: {'lr': 0.0004723721485491064, 'samples': 4676736, 'steps': 24357, 'loss/train': 1.6974021196365356} 08/30/2021 17:33:28 - INFO - __main__ - Step 24359: {'lr': 0.0004723697235430514, 'samples': 4676928, 'steps': 24358, 'loss/train': 1.1630061864852905} 08/30/2021 17:33:29 - INFO - __main__ - Step 24360: {'lr': 0.0004723672984368, 'samples': 4677120, 'steps': 24359, 'loss/train': 2.0134353637695312} 08/30/2021 17:33:29 - INFO - __main__ - Step 24361: {'lr': 0.00047236487323035344, 'samples': 4677312, 'steps': 24360, 'loss/train': 1.538875699043274} 08/30/2021 17:33:30 - INFO - __main__ - Step 24362: {'lr': 0.00047236244792371265, 'samples': 4677504, 'steps': 24361, 'loss/train': 1.7127004861831665} 08/30/2021 17:33:31 - INFO - __main__ - Step 24363: {'lr': 0.0004723600225168787, 'samples': 4677696, 'steps': 24362, 'loss/train': 1.7155966758728027} 08/30/2021 17:33:31 - INFO - __main__ - Step 24364: {'lr': 0.0004723575970098528, 'samples': 4677888, 'steps': 24363, 'loss/train': 1.8337619304656982} 08/30/2021 17:33:31 - INFO - __main__ - Step 24365: {'lr': 0.00047235517140263605, 'samples': 4678080, 'steps': 24364, 'loss/train': 1.7331677675247192} 08/30/2021 17:33:32 - INFO - __main__ - Step 24366: {'lr': 0.00047235274569522946, 'samples': 4678272, 'steps': 24365, 'loss/train': 1.7484673261642456} 08/30/2021 17:33:33 - INFO - __main__ - Step 24367: {'lr': 0.0004723503198876341, 'samples': 4678464, 'steps': 24366, 'loss/train': 1.4265400171279907} 08/30/2021 17:33:34 - INFO - __main__ - Step 24368: {'lr': 0.0004723478939798512, 'samples': 4678656, 'steps': 24367, 'loss/train': 1.637850284576416} 08/30/2021 17:33:34 - INFO - __main__ - Step 24369: {'lr': 0.0004723454679718817, 'samples': 4678848, 'steps': 24368, 'loss/train': 1.5267797708511353} 08/30/2021 17:33:34 - INFO - __main__ - Step 24370: {'lr': 0.00047234304186372685, 'samples': 4679040, 'steps': 24369, 'loss/train': 1.452715277671814} 08/30/2021 17:33:35 - INFO - __main__ - Step 24371: {'lr': 0.00047234061565538753, 'samples': 4679232, 'steps': 24370, 'loss/train': 1.788153886795044} 08/30/2021 17:33:36 - INFO - __main__ - Step 24372: {'lr': 0.0004723381893468651, 'samples': 4679424, 'steps': 24371, 'loss/train': 1.638181209564209} 08/30/2021 17:33:37 - INFO - __main__ - Step 24373: {'lr': 0.00047233576293816045, 'samples': 4679616, 'steps': 24372, 'loss/train': 2.1719155311584473} 08/30/2021 17:33:37 - INFO - __main__ - Step 24374: {'lr': 0.00047233333642927465, 'samples': 4679808, 'steps': 24373, 'loss/train': 1.6320966482162476} 08/30/2021 17:33:37 - INFO - __main__ - Step 24375: {'lr': 0.000472330909820209, 'samples': 4680000, 'steps': 24374, 'loss/train': 2.1833300590515137} 08/30/2021 17:33:38 - INFO - __main__ - Step 24376: {'lr': 0.0004723284831109644, 'samples': 4680192, 'steps': 24375, 'loss/train': 1.494808554649353} 08/30/2021 17:33:39 - INFO - __main__ - Step 24377: {'lr': 0.0004723260563015421, 'samples': 4680384, 'steps': 24376, 'loss/train': 1.3499294519424438} 08/30/2021 17:33:40 - INFO - __main__ - Step 24378: {'lr': 0.00047232362939194305, 'samples': 4680576, 'steps': 24377, 'loss/train': 1.245821475982666} 08/30/2021 17:33:40 - INFO - __main__ - Step 24379: {'lr': 0.0004723212023821684, 'samples': 4680768, 'steps': 24378, 'loss/train': 1.4235199689865112} 08/30/2021 17:33:40 - INFO - __main__ - Step 24380: {'lr': 0.0004723187752722193, 'samples': 4680960, 'steps': 24379, 'loss/train': 1.8682743310928345} 08/30/2021 17:33:41 - INFO - __main__ - Step 24381: {'lr': 0.00047231634806209675, 'samples': 4681152, 'steps': 24380, 'loss/train': 1.592482328414917} 08/30/2021 17:33:42 - INFO - __main__ - Step 24382: {'lr': 0.0004723139207518019, 'samples': 4681344, 'steps': 24381, 'loss/train': 1.9671236276626587} 08/30/2021 17:33:43 - INFO - __main__ - Step 24383: {'lr': 0.00047231149334133577, 'samples': 4681536, 'steps': 24382, 'loss/train': 1.4625492095947266} 08/30/2021 17:33:43 - INFO - __main__ - Step 24384: {'lr': 0.00047230906583069953, 'samples': 4681728, 'steps': 24383, 'loss/train': 0.7411932945251465} 08/30/2021 17:33:44 - INFO - __main__ - Step 24385: {'lr': 0.0004723066382198943, 'samples': 4681920, 'steps': 24384, 'loss/train': 1.7482298612594604} 08/30/2021 17:33:44 - INFO - __main__ - Step 24386: {'lr': 0.00047230421050892116, 'samples': 4682112, 'steps': 24385, 'loss/train': 1.3088852167129517} 08/30/2021 17:33:46 - INFO - __main__ - Step 24387: {'lr': 0.00047230178269778105, 'samples': 4682304, 'steps': 24386, 'loss/train': 1.6270971298217773} 08/30/2021 17:33:46 - INFO - __main__ - Step 24388: {'lr': 0.00047229935478647524, 'samples': 4682496, 'steps': 24387, 'loss/train': 1.438279628753662} 08/30/2021 17:33:47 - INFO - __main__ - Step 24389: {'lr': 0.0004722969267750048, 'samples': 4682688, 'steps': 24388, 'loss/train': 0.08078933507204056} 08/30/2021 17:33:47 - INFO - __main__ - Step 24390: {'lr': 0.0004722944986633708, 'samples': 4682880, 'steps': 24389, 'loss/train': 1.1382778882980347} 08/30/2021 17:33:47 - INFO - __main__ - Step 24391: {'lr': 0.0004722920704515743, 'samples': 4683072, 'steps': 24390, 'loss/train': 1.44602370262146} 08/30/2021 17:33:48 - INFO - __main__ - Step 24392: {'lr': 0.00047228964213961647, 'samples': 4683264, 'steps': 24391, 'loss/train': 1.3812720775604248} 08/30/2021 17:33:48 - INFO - __main__ - Step 24393: {'lr': 0.00047228721372749826, 'samples': 4683456, 'steps': 24392, 'loss/train': 1.5855101346969604} 08/30/2021 17:33:50 - INFO - __main__ - Step 24394: {'lr': 0.000472284785215221, 'samples': 4683648, 'steps': 24393, 'loss/train': 1.642717957496643} 08/30/2021 17:33:51 - INFO - __main__ - Step 24395: {'lr': 0.0004722823566027855, 'samples': 4683840, 'steps': 24394, 'loss/train': 1.7613502740859985} 08/30/2021 17:33:51 - INFO - __main__ - Step 24396: {'lr': 0.00047227992789019316, 'samples': 4684032, 'steps': 24395, 'loss/train': 1.6548693180084229} 08/30/2021 17:33:51 - INFO - __main__ - Step 24397: {'lr': 0.0004722774990774448, 'samples': 4684224, 'steps': 24396, 'loss/train': 1.6467336416244507} 08/30/2021 17:33:52 - INFO - __main__ - Step 24398: {'lr': 0.00047227507016454163, 'samples': 4684416, 'steps': 24397, 'loss/train': 1.679891586303711} 08/30/2021 17:33:53 - INFO - __main__ - Step 24399: {'lr': 0.00047227264115148475, 'samples': 4684608, 'steps': 24398, 'loss/train': 1.6772023439407349} 08/30/2021 17:33:54 - INFO - __main__ - Step 24400: {'lr': 0.00047227021203827523, 'samples': 4684800, 'steps': 24399, 'loss/train': 1.7842049598693848} 08/30/2021 17:33:54 - INFO - __main__ - Step 24401: {'lr': 0.0004722677828249142, 'samples': 4684992, 'steps': 24400, 'loss/train': 1.0591225624084473} 08/30/2021 17:33:54 - INFO - __main__ - Step 24402: {'lr': 0.0004722653535114028, 'samples': 4685184, 'steps': 24401, 'loss/train': 1.6557775735855103} 08/30/2021 17:33:55 - INFO - __main__ - Step 24403: {'lr': 0.00047226292409774205, 'samples': 4685376, 'steps': 24402, 'loss/train': 0.9989805817604065} 08/30/2021 17:33:56 - INFO - __main__ - Step 24404: {'lr': 0.00047226049458393306, 'samples': 4685568, 'steps': 24403, 'loss/train': 1.0077651739120483} 08/30/2021 17:33:57 - INFO - __main__ - Step 24405: {'lr': 0.0004722580649699768, 'samples': 4685760, 'steps': 24404, 'loss/train': 1.518217921257019} 08/30/2021 17:33:57 - INFO - __main__ - Step 24406: {'lr': 0.00047225563525587463, 'samples': 4685952, 'steps': 24405, 'loss/train': 1.2954621315002441} 08/30/2021 17:33:57 - INFO - __main__ - Step 24407: {'lr': 0.0004722532054416274, 'samples': 4686144, 'steps': 24406, 'loss/train': 2.0343549251556396} 08/30/2021 17:33:58 - INFO - __main__ - Step 24408: {'lr': 0.0004722507755272364, 'samples': 4686336, 'steps': 24407, 'loss/train': 1.5305819511413574} 08/30/2021 17:33:58 - INFO - __main__ - Step 24409: {'lr': 0.0004722483455127026, 'samples': 4686528, 'steps': 24408, 'loss/train': 1.5015907287597656} 08/30/2021 17:34:00 - INFO - __main__ - Step 24410: {'lr': 0.000472245915398027, 'samples': 4686720, 'steps': 24409, 'loss/train': 0.2329707145690918} 08/30/2021 17:34:00 - INFO - __main__ - Step 24411: {'lr': 0.0004722434851832109, 'samples': 4686912, 'steps': 24410, 'loss/train': 0.9077503085136414} 08/30/2021 17:34:00 - INFO - __main__ - Step 24412: {'lr': 0.00047224105486825543, 'samples': 4687104, 'steps': 24411, 'loss/train': 1.0722583532333374} 08/30/2021 17:34:01 - INFO - __main__ - Step 24413: {'lr': 0.0004722386244531615, 'samples': 4687296, 'steps': 24412, 'loss/train': 1.7993780374526978} 08/30/2021 17:34:01 - INFO - __main__ - Step 24414: {'lr': 0.0004722361939379302, 'samples': 4687488, 'steps': 24413, 'loss/train': 0.5120288133621216} 08/30/2021 17:34:03 - INFO - __main__ - Step 24415: {'lr': 0.0004722337633225627, 'samples': 4687680, 'steps': 24414, 'loss/train': 1.5795621871948242} 08/30/2021 17:34:03 - INFO - __main__ - Step 24416: {'lr': 0.0004722313326070602, 'samples': 4687872, 'steps': 24415, 'loss/train': 1.7287003993988037} 08/30/2021 17:34:04 - INFO - __main__ - Step 24417: {'lr': 0.00047222890179142365, 'samples': 4688064, 'steps': 24416, 'loss/train': 1.6448042392730713} 08/30/2021 17:34:04 - INFO - __main__ - Step 24418: {'lr': 0.00047222647087565413, 'samples': 4688256, 'steps': 24417, 'loss/train': 1.8849087953567505} 08/30/2021 17:34:04 - INFO - __main__ - Step 24419: {'lr': 0.0004722240398597528, 'samples': 4688448, 'steps': 24418, 'loss/train': 1.5503348112106323} 08/30/2021 17:34:06 - INFO - __main__ - Step 24420: {'lr': 0.0004722216087437208, 'samples': 4688640, 'steps': 24419, 'loss/train': 1.3734948635101318} 08/30/2021 17:34:06 - INFO - __main__ - Step 24421: {'lr': 0.0004722191775275592, 'samples': 4688832, 'steps': 24420, 'loss/train': 1.6976292133331299} 08/30/2021 17:34:07 - INFO - __main__ - Step 24422: {'lr': 0.00047221674621126896, 'samples': 4689024, 'steps': 24421, 'loss/train': 1.557907223701477} 08/30/2021 17:34:07 - INFO - __main__ - Step 24423: {'lr': 0.0004722143147948513, 'samples': 4689216, 'steps': 24422, 'loss/train': 1.8630753755569458} 08/30/2021 17:34:07 - INFO - __main__ - Step 24424: {'lr': 0.0004722118832783074, 'samples': 4689408, 'steps': 24423, 'loss/train': 1.3790898323059082} 08/30/2021 17:34:09 - INFO - __main__ - Step 24425: {'lr': 0.0004722094516616382, 'samples': 4689600, 'steps': 24424, 'loss/train': 1.4910532236099243} 08/30/2021 17:34:09 - INFO - __main__ - Step 24426: {'lr': 0.0004722070199448448, 'samples': 4689792, 'steps': 24425, 'loss/train': 1.119583010673523} 08/30/2021 17:34:10 - INFO - __main__ - Step 24427: {'lr': 0.00047220458812792846, 'samples': 4689984, 'steps': 24426, 'loss/train': 1.6967073678970337} 08/30/2021 17:34:10 - INFO - __main__ - Step 24428: {'lr': 0.00047220215621089005, 'samples': 4690176, 'steps': 24427, 'loss/train': 1.7348392009735107} 08/30/2021 17:34:10 - INFO - __main__ - Step 24429: {'lr': 0.00047219972419373083, 'samples': 4690368, 'steps': 24428, 'loss/train': 2.005463123321533} 08/30/2021 17:34:11 - INFO - __main__ - Step 24430: {'lr': 0.00047219729207645183, 'samples': 4690560, 'steps': 24429, 'loss/train': 1.2426892518997192} 08/30/2021 17:34:12 - INFO - __main__ - Step 24431: {'lr': 0.0004721948598590542, 'samples': 4690752, 'steps': 24430, 'loss/train': 1.5733124017715454} 08/30/2021 17:34:12 - INFO - __main__ - Step 24432: {'lr': 0.0004721924275415389, 'samples': 4690944, 'steps': 24431, 'loss/train': 1.5471230745315552} 08/30/2021 17:34:13 - INFO - __main__ - Step 24433: {'lr': 0.0004721899951239072, 'samples': 4691136, 'steps': 24432, 'loss/train': 1.5222989320755005} 08/30/2021 17:34:13 - INFO - __main__ - Step 24434: {'lr': 0.0004721875626061601, 'samples': 4691328, 'steps': 24433, 'loss/train': 1.4067974090576172} 08/30/2021 17:34:14 - INFO - __main__ - Step 24435: {'lr': 0.00047218512998829874, 'samples': 4691520, 'steps': 24434, 'loss/train': 2.027573823928833} 08/30/2021 17:34:15 - INFO - __main__ - Step 24436: {'lr': 0.00047218269727032413, 'samples': 4691712, 'steps': 24435, 'loss/train': 0.8910576701164246} 08/30/2021 17:34:15 - INFO - __main__ - Step 24437: {'lr': 0.00047218026445223745, 'samples': 4691904, 'steps': 24436, 'loss/train': 1.7636796236038208} 08/30/2021 17:34:16 - INFO - __main__ - Step 24438: {'lr': 0.0004721778315340398, 'samples': 4692096, 'steps': 24437, 'loss/train': 2.344608783721924} 08/30/2021 17:34:16 - INFO - __main__ - Step 24439: {'lr': 0.0004721753985157322, 'samples': 4692288, 'steps': 24438, 'loss/train': 1.692981243133545} 08/30/2021 17:34:17 - INFO - __main__ - Step 24440: {'lr': 0.0004721729653973158, 'samples': 4692480, 'steps': 24439, 'loss/train': 1.5303928852081299} 08/30/2021 17:34:19 - INFO - __main__ - Step 24441: {'lr': 0.0004721705321787917, 'samples': 4692672, 'steps': 24440, 'loss/train': 1.9622113704681396} 08/30/2021 17:34:20 - INFO - __main__ - Step 24442: {'lr': 0.00047216809886016097, 'samples': 4692864, 'steps': 24441, 'loss/train': 1.4492759704589844} 08/30/2021 17:34:20 - INFO - __main__ - Step 24443: {'lr': 0.0004721656654414248, 'samples': 4693056, 'steps': 24442, 'loss/train': 2.025129795074463} 08/30/2021 17:34:20 - INFO - __main__ - Step 24444: {'lr': 0.00047216323192258416, 'samples': 4693248, 'steps': 24443, 'loss/train': 1.435434103012085} 08/30/2021 17:34:21 - INFO - __main__ - Step 24445: {'lr': 0.0004721607983036401, 'samples': 4693440, 'steps': 24444, 'loss/train': 1.6196428537368774} 08/30/2021 17:34:21 - INFO - __main__ - Step 24446: {'lr': 0.00047215836458459393, 'samples': 4693632, 'steps': 24445, 'loss/train': 1.436138391494751} 08/30/2021 17:34:23 - INFO - __main__ - Step 24447: {'lr': 0.00047215593076544663, 'samples': 4693824, 'steps': 24446, 'loss/train': 1.5719879865646362} 08/30/2021 17:34:23 - INFO - __main__ - Step 24448: {'lr': 0.0004721534968461992, 'samples': 4694016, 'steps': 24447, 'loss/train': 2.2825469970703125} 08/30/2021 17:34:24 - INFO - __main__ - Step 24449: {'lr': 0.00047215106282685296, 'samples': 4694208, 'steps': 24448, 'loss/train': 1.108061671257019} 08/30/2021 17:34:24 - INFO - __main__ - Step 24450: {'lr': 0.0004721486287074088, 'samples': 4694400, 'steps': 24449, 'loss/train': 1.4066286087036133} 08/30/2021 17:34:25 - INFO - __main__ - Step 24451: {'lr': 0.0004721461944878679, 'samples': 4694592, 'steps': 24450, 'loss/train': 1.2571030855178833} 08/30/2021 17:34:26 - INFO - __main__ - Step 24452: {'lr': 0.00047214376016823143, 'samples': 4694784, 'steps': 24451, 'loss/train': 1.665950894355774} 08/30/2021 17:34:27 - INFO - __main__ - Step 24453: {'lr': 0.0004721413257485003, 'samples': 4694976, 'steps': 24452, 'loss/train': 1.733527421951294} 08/30/2021 17:34:27 - INFO - __main__ - Step 24454: {'lr': 0.0004721388912286758, 'samples': 4695168, 'steps': 24453, 'loss/train': 2.084660768508911} 08/30/2021 17:34:27 - INFO - __main__ - Step 24455: {'lr': 0.0004721364566087589, 'samples': 4695360, 'steps': 24454, 'loss/train': 1.8475679159164429} 08/30/2021 17:34:28 - INFO - __main__ - Step 24456: {'lr': 0.00047213402188875077, 'samples': 4695552, 'steps': 24455, 'loss/train': 1.7513166666030884} 08/30/2021 17:34:29 - INFO - __main__ - Step 24457: {'lr': 0.00047213158706865246, 'samples': 4695744, 'steps': 24456, 'loss/train': 1.285531759262085} 08/30/2021 17:34:30 - INFO - __main__ - Step 24458: {'lr': 0.000472129152148465, 'samples': 4695936, 'steps': 24457, 'loss/train': 1.658231496810913} 08/30/2021 17:34:30 - INFO - __main__ - Step 24459: {'lr': 0.0004721267171281897, 'samples': 4696128, 'steps': 24458, 'loss/train': 0.07067694514989853} 08/30/2021 17:34:30 - INFO - __main__ - Step 24460: {'lr': 0.00047212428200782744, 'samples': 4696320, 'steps': 24459, 'loss/train': 1.6212053298950195} 08/30/2021 17:34:31 - INFO - __main__ - Step 24461: {'lr': 0.00047212184678737946, 'samples': 4696512, 'steps': 24460, 'loss/train': 1.081878423690796} 08/30/2021 17:34:31 - INFO - __main__ - Step 24462: {'lr': 0.00047211941146684677, 'samples': 4696704, 'steps': 24461, 'loss/train': 0.767326295375824} 08/30/2021 17:34:32 - INFO - __main__ - Step 24463: {'lr': 0.00047211697604623056, 'samples': 4696896, 'steps': 24462, 'loss/train': 1.8081620931625366} 08/30/2021 17:34:33 - INFO - __main__ - Step 24464: {'lr': 0.0004721145405255318, 'samples': 4697088, 'steps': 24463, 'loss/train': 1.461976408958435} 08/30/2021 17:34:33 - INFO - __main__ - Step 24465: {'lr': 0.00047211210490475167, 'samples': 4697280, 'steps': 24464, 'loss/train': 1.7162853479385376} 08/30/2021 17:34:34 - INFO - __main__ - Step 24466: {'lr': 0.0004721096691838913, 'samples': 4697472, 'steps': 24465, 'loss/train': 1.5274393558502197} 08/30/2021 17:34:34 - INFO - __main__ - Step 24467: {'lr': 0.00047210723336295167, 'samples': 4697664, 'steps': 24466, 'loss/train': 1.5892138481140137} 08/30/2021 17:34:36 - INFO - __main__ - Step 24468: {'lr': 0.00047210479744193404, 'samples': 4697856, 'steps': 24467, 'loss/train': 1.749915361404419} 08/30/2021 17:34:36 - INFO - __main__ - Step 24469: {'lr': 0.0004721023614208393, 'samples': 4698048, 'steps': 24468, 'loss/train': 1.882742166519165} 08/30/2021 17:34:36 - INFO - __main__ - Step 24470: {'lr': 0.0004720999252996687, 'samples': 4698240, 'steps': 24469, 'loss/train': 1.774699330329895} 08/30/2021 17:34:37 - INFO - __main__ - Step 24471: {'lr': 0.00047209748907842337, 'samples': 4698432, 'steps': 24470, 'loss/train': 1.6665769815444946} 08/30/2021 17:34:37 - INFO - __main__ - Step 24472: {'lr': 0.0004720950527571043, 'samples': 4698624, 'steps': 24471, 'loss/train': 1.5818909406661987} 08/30/2021 17:34:39 - INFO - __main__ - Step 24473: {'lr': 0.0004720926163357126, 'samples': 4698816, 'steps': 24472, 'loss/train': 1.6217882633209229} 08/30/2021 17:34:40 - INFO - __main__ - Step 24474: {'lr': 0.0004720901798142494, 'samples': 4699008, 'steps': 24473, 'loss/train': 1.221812129020691} 08/30/2021 17:34:40 - INFO - __main__ - Step 24475: {'lr': 0.00047208774319271586, 'samples': 4699200, 'steps': 24474, 'loss/train': 1.7934091091156006} 08/30/2021 17:34:40 - INFO - __main__ - Step 24476: {'lr': 0.00047208530647111294, 'samples': 4699392, 'steps': 24475, 'loss/train': 1.7955983877182007} 08/30/2021 17:34:41 - INFO - __main__ - Step 24477: {'lr': 0.0004720828696494418, 'samples': 4699584, 'steps': 24476, 'loss/train': 1.424503207206726} 08/30/2021 17:34:41 - INFO - __main__ - Step 24478: {'lr': 0.00047208043272770354, 'samples': 4699776, 'steps': 24477, 'loss/train': 0.26392412185668945} 08/30/2021 17:34:42 - INFO - __main__ - Step 24479: {'lr': 0.0004720779957058993, 'samples': 4699968, 'steps': 24478, 'loss/train': 1.5823725461959839} 08/30/2021 17:34:43 - INFO - __main__ - Step 24480: {'lr': 0.0004720755585840302, 'samples': 4700160, 'steps': 24479, 'loss/train': 1.8605295419692993} 08/30/2021 17:34:43 - INFO - __main__ - Step 24481: {'lr': 0.0004720731213620972, 'samples': 4700352, 'steps': 24480, 'loss/train': 1.994153618812561} 08/30/2021 17:34:44 - INFO - __main__ - Step 24482: {'lr': 0.00047207068404010147, 'samples': 4700544, 'steps': 24481, 'loss/train': 2.2493860721588135} 08/30/2021 17:34:44 - INFO - __main__ - Step 24483: {'lr': 0.00047206824661804415, 'samples': 4700736, 'steps': 24482, 'loss/train': 2.090334892272949} 08/30/2021 17:34:44 - INFO - __main__ - Step 24484: {'lr': 0.0004720658090959263, 'samples': 4700928, 'steps': 24483, 'loss/train': 1.520559310913086} 08/30/2021 17:34:46 - INFO - __main__ - Step 24485: {'lr': 0.000472063371473749, 'samples': 4701120, 'steps': 24484, 'loss/train': 1.8299134969711304} 08/30/2021 17:34:46 - INFO - __main__ - Step 24486: {'lr': 0.0004720609337515134, 'samples': 4701312, 'steps': 24485, 'loss/train': 1.7684216499328613} 08/30/2021 17:34:47 - INFO - __main__ - Step 24487: {'lr': 0.00047205849592922057, 'samples': 4701504, 'steps': 24486, 'loss/train': 1.4957983493804932} 08/30/2021 17:34:47 - INFO - __main__ - Step 24488: {'lr': 0.00047205605800687154, 'samples': 4701696, 'steps': 24487, 'loss/train': 1.4721304178237915} 08/30/2021 17:34:47 - INFO - __main__ - Step 24489: {'lr': 0.0004720536199844676, 'samples': 4701888, 'steps': 24488, 'loss/train': 1.8148545026779175} 08/30/2021 17:34:49 - INFO - __main__ - Step 24490: {'lr': 0.00047205118186200963, 'samples': 4702080, 'steps': 24489, 'loss/train': 1.6523698568344116} 08/30/2021 17:34:49 - INFO - __main__ - Step 24491: {'lr': 0.00047204874363949886, 'samples': 4702272, 'steps': 24490, 'loss/train': 1.5222666263580322} 08/30/2021 17:34:50 - INFO - __main__ - Step 24492: {'lr': 0.00047204630531693634, 'samples': 4702464, 'steps': 24491, 'loss/train': 1.5540434122085571} 08/30/2021 17:34:50 - INFO - __main__ - Step 24493: {'lr': 0.0004720438668943232, 'samples': 4702656, 'steps': 24492, 'loss/train': 1.5921696424484253} 08/30/2021 17:34:50 - INFO - __main__ - Step 24494: {'lr': 0.0004720414283716605, 'samples': 4702848, 'steps': 24493, 'loss/train': 1.4510645866394043} 08/30/2021 17:34:52 - INFO - __main__ - Step 24495: {'lr': 0.00047203898974894934, 'samples': 4703040, 'steps': 24494, 'loss/train': 1.844099998474121} 08/30/2021 17:34:52 - INFO - __main__ - Step 24496: {'lr': 0.0004720365510261909, 'samples': 4703232, 'steps': 24495, 'loss/train': 1.3378582000732422} 08/30/2021 17:34:53 - INFO - __main__ - Step 24497: {'lr': 0.00047203411220338615, 'samples': 4703424, 'steps': 24496, 'loss/train': 1.5024641752243042} 08/30/2021 17:34:53 - INFO - __main__ - Step 24498: {'lr': 0.00047203167328053634, 'samples': 4703616, 'steps': 24497, 'loss/train': 1.207093358039856} 08/30/2021 17:34:53 - INFO - __main__ - Step 24499: {'lr': 0.0004720292342576423, 'samples': 4703808, 'steps': 24498, 'loss/train': 1.2374742031097412} 08/30/2021 17:34:55 - INFO - __main__ - Step 24500: {'lr': 0.0004720267951347055, 'samples': 4704000, 'steps': 24499, 'loss/train': 1.4379520416259766} 08/30/2021 17:34:55 - INFO - __main__ - Step 24501: {'lr': 0.00047202435591172677, 'samples': 4704192, 'steps': 24500, 'loss/train': 1.6501487493515015} 08/30/2021 17:34:56 - INFO - __main__ - Step 24502: {'lr': 0.00047202191658870737, 'samples': 4704384, 'steps': 24501, 'loss/train': 1.4039591550827026} 08/30/2021 17:34:56 - INFO - __main__ - Step 24503: {'lr': 0.00047201947716564826, 'samples': 4704576, 'steps': 24502, 'loss/train': 1.4813679456710815} 08/30/2021 17:34:56 - INFO - __main__ - Step 24504: {'lr': 0.00047201703764255057, 'samples': 4704768, 'steps': 24503, 'loss/train': 1.0740585327148438} 08/30/2021 17:34:58 - INFO - __main__ - Step 24505: {'lr': 0.0004720145980194155, 'samples': 4704960, 'steps': 24504, 'loss/train': 1.3868985176086426} 08/30/2021 17:34:59 - INFO - __main__ - Step 24506: {'lr': 0.000472012158296244, 'samples': 4705152, 'steps': 24505, 'loss/train': 1.3370076417922974} 08/30/2021 17:34:59 - INFO - __main__ - Step 24507: {'lr': 0.0004720097184730373, 'samples': 4705344, 'steps': 24506, 'loss/train': 1.75924551486969} 08/30/2021 17:34:59 - INFO - __main__ - Step 24508: {'lr': 0.00047200727854979644, 'samples': 4705536, 'steps': 24507, 'loss/train': 1.5830689668655396} 08/30/2021 17:35:00 - INFO - __main__ - Step 24509: {'lr': 0.00047200483852652257, 'samples': 4705728, 'steps': 24508, 'loss/train': 1.1779227256774902} 08/30/2021 17:35:01 - INFO - __main__ - Step 24510: {'lr': 0.0004720023984032167, 'samples': 4705920, 'steps': 24509, 'loss/train': 0.502585768699646} 08/30/2021 17:35:02 - INFO - __main__ - Step 24511: {'lr': 0.00047199995817987997, 'samples': 4706112, 'steps': 24510, 'loss/train': 0.9358653426170349} 08/30/2021 17:35:02 - INFO - __main__ - Step 24512: {'lr': 0.00047199751785651346, 'samples': 4706304, 'steps': 24511, 'loss/train': 1.063664436340332} 08/30/2021 17:35:02 - INFO - __main__ - Step 24513: {'lr': 0.0004719950774331183, 'samples': 4706496, 'steps': 24512, 'loss/train': 2.2083916664123535} 08/30/2021 17:35:03 - INFO - __main__ - Step 24514: {'lr': 0.00047199263690969563, 'samples': 4706688, 'steps': 24513, 'loss/train': 1.5452370643615723} 08/30/2021 17:35:04 - INFO - __main__ - Step 24515: {'lr': 0.00047199019628624647, 'samples': 4706880, 'steps': 24514, 'loss/train': 1.8068499565124512} 08/30/2021 17:35:05 - INFO - __main__ - Step 24516: {'lr': 0.00047198775556277195, 'samples': 4707072, 'steps': 24515, 'loss/train': 1.927861213684082} 08/30/2021 17:35:05 - INFO - __main__ - Step 24517: {'lr': 0.0004719853147392732, 'samples': 4707264, 'steps': 24516, 'loss/train': 1.4510259628295898} 08/30/2021 17:35:05 - INFO - __main__ - Step 24518: {'lr': 0.0004719828738157512, 'samples': 4707456, 'steps': 24517, 'loss/train': 1.6395998001098633} 08/30/2021 17:35:06 - INFO - __main__ - Step 24519: {'lr': 0.0004719804327922073, 'samples': 4707648, 'steps': 24518, 'loss/train': 1.6449280977249146} 08/30/2021 17:35:07 - INFO - __main__ - Step 24520: {'lr': 0.00047197799166864233, 'samples': 4707840, 'steps': 24519, 'loss/train': 1.774253249168396} 08/30/2021 17:35:08 - INFO - __main__ - Step 24521: {'lr': 0.00047197555044505756, 'samples': 4708032, 'steps': 24520, 'loss/train': 1.4616219997406006} 08/30/2021 17:35:08 - INFO - __main__ - Step 24522: {'lr': 0.000471973109121454, 'samples': 4708224, 'steps': 24521, 'loss/train': 1.4657056331634521} 08/30/2021 17:35:08 - INFO - __main__ - Step 24523: {'lr': 0.00047197066769783284, 'samples': 4708416, 'steps': 24522, 'loss/train': 1.2063186168670654} 08/30/2021 17:35:09 - INFO - __main__ - Step 24524: {'lr': 0.000471968226174195, 'samples': 4708608, 'steps': 24523, 'loss/train': 0.091896653175354} 08/30/2021 17:35:10 - INFO - __main__ - Step 24525: {'lr': 0.00047196578455054175, 'samples': 4708800, 'steps': 24524, 'loss/train': 0.9957613348960876} 08/30/2021 17:35:11 - INFO - __main__ - Step 24526: {'lr': 0.00047196334282687414, 'samples': 4708992, 'steps': 24525, 'loss/train': 1.7564043998718262} 08/30/2021 17:35:11 - INFO - __main__ - Step 24527: {'lr': 0.00047196090100319333, 'samples': 4709184, 'steps': 24526, 'loss/train': 1.4603902101516724} 08/30/2021 17:35:12 - INFO - __main__ - Step 24528: {'lr': 0.00047195845907950035, 'samples': 4709376, 'steps': 24527, 'loss/train': 1.472461223602295} 08/30/2021 17:35:12 - INFO - __main__ - Step 24529: {'lr': 0.0004719560170557963, 'samples': 4709568, 'steps': 24528, 'loss/train': 1.436963677406311} 08/30/2021 17:35:13 - INFO - __main__ - Step 24530: {'lr': 0.0004719535749320823, 'samples': 4709760, 'steps': 24529, 'loss/train': 0.232659712433815} 08/30/2021 17:35:14 - INFO - __main__ - Step 24531: {'lr': 0.0004719511327083594, 'samples': 4709952, 'steps': 24530, 'loss/train': 0.26898905634880066} 08/30/2021 17:35:14 - INFO - __main__ - Step 24532: {'lr': 0.0004719486903846288, 'samples': 4710144, 'steps': 24531, 'loss/train': 1.497463583946228} 08/30/2021 17:35:15 - INFO - __main__ - Step 24533: {'lr': 0.0004719462479608915, 'samples': 4710336, 'steps': 24532, 'loss/train': 1.2646433115005493} 08/30/2021 17:35:15 - INFO - __main__ - Step 24534: {'lr': 0.0004719438054371487, 'samples': 4710528, 'steps': 24533, 'loss/train': 1.1970287561416626} 08/30/2021 17:35:15 - INFO - __main__ - Step 24535: {'lr': 0.00047194136281340137, 'samples': 4710720, 'steps': 24534, 'loss/train': 1.7726329565048218} 08/30/2021 17:35:17 - INFO - __main__ - Step 24536: {'lr': 0.00047193892008965077, 'samples': 4710912, 'steps': 24535, 'loss/train': 1.4720901250839233} 08/30/2021 17:35:17 - INFO - __main__ - Step 24537: {'lr': 0.0004719364772658978, 'samples': 4711104, 'steps': 24536, 'loss/train': 1.4312533140182495} 08/30/2021 17:35:18 - INFO - __main__ - Step 24538: {'lr': 0.00047193403434214385, 'samples': 4711296, 'steps': 24537, 'loss/train': 1.2726963758468628} 08/30/2021 17:35:18 - INFO - __main__ - Step 24539: {'lr': 0.0004719315913183897, 'samples': 4711488, 'steps': 24538, 'loss/train': 1.411854863166809} 08/30/2021 17:35:18 - INFO - __main__ - Step 24540: {'lr': 0.0004719291481946367, 'samples': 4711680, 'steps': 24539, 'loss/train': 1.7104921340942383} 08/30/2021 17:35:20 - INFO - __main__ - Step 24541: {'lr': 0.00047192670497088577, 'samples': 4711872, 'steps': 24540, 'loss/train': 1.3718091249465942} 08/30/2021 17:35:20 - INFO - __main__ - Step 24542: {'lr': 0.0004719242616471381, 'samples': 4712064, 'steps': 24541, 'loss/train': 1.6246330738067627} 08/30/2021 17:35:21 - INFO - __main__ - Step 24543: {'lr': 0.00047192181822339484, 'samples': 4712256, 'steps': 24542, 'loss/train': 1.1429835557937622} 08/30/2021 17:35:21 - INFO - __main__ - Step 24544: {'lr': 0.000471919374699657, 'samples': 4712448, 'steps': 24543, 'loss/train': 1.4758931398391724} 08/30/2021 17:35:21 - INFO - __main__ - Step 24545: {'lr': 0.0004719169310759257, 'samples': 4712640, 'steps': 24544, 'loss/train': 5.920523166656494} 08/30/2021 17:35:23 - INFO - __main__ - Step 24546: {'lr': 0.0004719144873522021, 'samples': 4712832, 'steps': 24545, 'loss/train': 1.7054550647735596} 08/30/2021 17:35:23 - INFO - __main__ - Step 24547: {'lr': 0.0004719120435284872, 'samples': 4713024, 'steps': 24546, 'loss/train': 1.2541141510009766} 08/30/2021 17:35:24 - INFO - __main__ - Step 24548: {'lr': 0.0004719095996047822, 'samples': 4713216, 'steps': 24547, 'loss/train': 1.8921313285827637} 08/30/2021 17:35:24 - INFO - __main__ - Step 24549: {'lr': 0.0004719071555810881, 'samples': 4713408, 'steps': 24548, 'loss/train': 1.8774735927581787} 08/30/2021 17:35:25 - INFO - __main__ - Step 24550: {'lr': 0.00047190471145740616, 'samples': 4713600, 'steps': 24549, 'loss/train': 0.6641445159912109} 08/30/2021 17:35:25 - INFO - __main__ - Step 24551: {'lr': 0.0004719022672337373, 'samples': 4713792, 'steps': 24550, 'loss/train': 0.7229032516479492} 08/30/2021 17:35:26 - INFO - __main__ - Step 24552: {'lr': 0.0004718998229100827, 'samples': 4713984, 'steps': 24551, 'loss/train': 1.1109299659729004} 08/30/2021 17:35:27 - INFO - __main__ - Step 24553: {'lr': 0.00047189737848644356, 'samples': 4714176, 'steps': 24552, 'loss/train': 1.7704217433929443} 08/30/2021 17:35:27 - INFO - __main__ - Step 24554: {'lr': 0.0004718949339628208, 'samples': 4714368, 'steps': 24553, 'loss/train': 1.3112504482269287} 08/30/2021 17:35:28 - INFO - __main__ - Step 24555: {'lr': 0.0004718924893392156, 'samples': 4714560, 'steps': 24554, 'loss/train': 1.695735216140747} 08/30/2021 17:35:28 - INFO - __main__ - Step 24556: {'lr': 0.0004718900446156291, 'samples': 4714752, 'steps': 24555, 'loss/train': 1.3627787828445435} 08/30/2021 17:35:30 - INFO - __main__ - Step 24557: {'lr': 0.00047188759979206236, 'samples': 4714944, 'steps': 24556, 'loss/train': 1.5065007209777832} 08/30/2021 17:35:30 - INFO - __main__ - Step 24558: {'lr': 0.00047188515486851646, 'samples': 4715136, 'steps': 24557, 'loss/train': 1.5328236818313599} 08/30/2021 17:35:31 - INFO - __main__ - Step 24559: {'lr': 0.0004718827098449926, 'samples': 4715328, 'steps': 24558, 'loss/train': 1.2341324090957642} 08/30/2021 17:35:31 - INFO - __main__ - Step 24560: {'lr': 0.00047188026472149184, 'samples': 4715520, 'steps': 24559, 'loss/train': 2.171665906906128} 08/30/2021 17:35:31 - INFO - __main__ - Step 24561: {'lr': 0.0004718778194980151, 'samples': 4715712, 'steps': 24560, 'loss/train': 1.7486183643341064} 08/30/2021 17:35:33 - INFO - __main__ - Step 24562: {'lr': 0.00047187537417456375, 'samples': 4715904, 'steps': 24561, 'loss/train': 1.7060445547103882} 08/30/2021 17:35:33 - INFO - __main__ - Step 24563: {'lr': 0.00047187292875113874, 'samples': 4716096, 'steps': 24562, 'loss/train': 2.457808017730713} 08/30/2021 17:35:34 - INFO - __main__ - Step 24564: {'lr': 0.0004718704832277413, 'samples': 4716288, 'steps': 24563, 'loss/train': 1.622470736503601} 08/30/2021 17:35:34 - INFO - __main__ - Step 24565: {'lr': 0.0004718680376043724, 'samples': 4716480, 'steps': 24564, 'loss/train': 1.4234267473220825} 08/30/2021 17:35:34 - INFO - __main__ - Step 24566: {'lr': 0.00047186559188103314, 'samples': 4716672, 'steps': 24565, 'loss/train': 1.6230226755142212} 08/30/2021 17:35:36 - INFO - __main__ - Step 24567: {'lr': 0.00047186314605772466, 'samples': 4716864, 'steps': 24566, 'loss/train': 1.4558249711990356} 08/30/2021 17:35:36 - INFO - __main__ - Step 24568: {'lr': 0.00047186070013444814, 'samples': 4717056, 'steps': 24567, 'loss/train': 1.0605478286743164} 08/30/2021 17:35:37 - INFO - __main__ - Step 24569: {'lr': 0.00047185825411120454, 'samples': 4717248, 'steps': 24568, 'loss/train': 1.3696558475494385} 08/30/2021 17:35:37 - INFO - __main__ - Step 24570: {'lr': 0.0004718558079879951, 'samples': 4717440, 'steps': 24569, 'loss/train': 1.3347958326339722} 08/30/2021 17:35:37 - INFO - __main__ - Step 24571: {'lr': 0.00047185336176482084, 'samples': 4717632, 'steps': 24570, 'loss/train': 1.8632763624191284} 08/30/2021 17:35:39 - INFO - __main__ - Step 24572: {'lr': 0.00047185091544168286, 'samples': 4717824, 'steps': 24571, 'loss/train': 1.8458465337753296} 08/30/2021 17:35:39 - INFO - __main__ - Step 24573: {'lr': 0.00047184846901858225, 'samples': 4718016, 'steps': 24572, 'loss/train': 0.7646589279174805} 08/30/2021 17:35:40 - INFO - __main__ - Step 24574: {'lr': 0.0004718460224955202, 'samples': 4718208, 'steps': 24573, 'loss/train': 1.0524741411209106} 08/30/2021 17:35:40 - INFO - __main__ - Step 24575: {'lr': 0.0004718435758724977, 'samples': 4718400, 'steps': 24574, 'loss/train': 1.3564406633377075} 08/30/2021 17:35:40 - INFO - __main__ - Step 24576: {'lr': 0.000471841129149516, 'samples': 4718592, 'steps': 24575, 'loss/train': 1.1782338619232178} 08/30/2021 17:35:41 - INFO - __main__ - Step 24577: {'lr': 0.000471838682326576, 'samples': 4718784, 'steps': 24576, 'loss/train': 1.1804299354553223} 08/30/2021 17:35:42 - INFO - __main__ - Step 24578: {'lr': 0.000471836235403679, 'samples': 4718976, 'steps': 24577, 'loss/train': 1.9783321619033813} 08/30/2021 17:35:43 - INFO - __main__ - Step 24579: {'lr': 0.000471833788380826, 'samples': 4719168, 'steps': 24578, 'loss/train': 1.8166775703430176} 08/30/2021 17:35:43 - INFO - __main__ - Step 24580: {'lr': 0.0004718313412580181, 'samples': 4719360, 'steps': 24579, 'loss/train': 1.8016951084136963} 08/30/2021 17:35:43 - INFO - __main__ - Step 24581: {'lr': 0.0004718288940352564, 'samples': 4719552, 'steps': 24580, 'loss/train': 1.562361717224121} 08/30/2021 17:35:44 - INFO - __main__ - Step 24582: {'lr': 0.00047182644671254207, 'samples': 4719744, 'steps': 24581, 'loss/train': 3.886920213699341} 08/30/2021 17:35:45 - INFO - __main__ - Step 24583: {'lr': 0.0004718239992898761, 'samples': 4719936, 'steps': 24582, 'loss/train': 1.9974838495254517} 08/30/2021 17:35:46 - INFO - __main__ - Step 24584: {'lr': 0.00047182155176725974, 'samples': 4720128, 'steps': 24583, 'loss/train': 1.6186575889587402} 08/30/2021 17:35:46 - INFO - __main__ - Step 24585: {'lr': 0.00047181910414469396, 'samples': 4720320, 'steps': 24584, 'loss/train': 1.5206100940704346} 08/30/2021 17:35:46 - INFO - __main__ - Step 24586: {'lr': 0.0004718166564221799, 'samples': 4720512, 'steps': 24585, 'loss/train': 1.3282649517059326} 08/30/2021 17:35:47 - INFO - __main__ - Step 24587: {'lr': 0.0004718142085997187, 'samples': 4720704, 'steps': 24586, 'loss/train': 1.8367680311203003} 08/30/2021 17:35:48 - INFO - __main__ - Step 24588: {'lr': 0.0004718117606773115, 'samples': 4720896, 'steps': 24587, 'loss/train': 1.4244365692138672} 08/30/2021 17:35:49 - INFO - __main__ - Step 24589: {'lr': 0.0004718093126549592, 'samples': 4721088, 'steps': 24588, 'loss/train': 3.3588130474090576} 08/30/2021 17:35:49 - INFO - __main__ - Step 24590: {'lr': 0.0004718068645326632, 'samples': 4721280, 'steps': 24589, 'loss/train': 2.0005922317504883} 08/30/2021 17:35:50 - INFO - __main__ - Step 24591: {'lr': 0.0004718044163104244, 'samples': 4721472, 'steps': 24590, 'loss/train': 1.963279366493225} 08/30/2021 17:35:50 - INFO - __main__ - Step 24592: {'lr': 0.0004718019679882439, 'samples': 4721664, 'steps': 24591, 'loss/train': 1.429451584815979} 08/30/2021 17:35:51 - INFO - __main__ - Step 24593: {'lr': 0.0004717995195661229, 'samples': 4721856, 'steps': 24592, 'loss/train': 1.9033617973327637} 08/30/2021 17:35:52 - INFO - __main__ - Step 24594: {'lr': 0.00047179707104406243, 'samples': 4722048, 'steps': 24593, 'loss/train': 1.8315582275390625} 08/30/2021 17:35:52 - INFO - __main__ - Step 24595: {'lr': 0.0004717946224220637, 'samples': 4722240, 'steps': 24594, 'loss/train': 1.625569224357605} 08/30/2021 17:35:53 - INFO - __main__ - Step 24596: {'lr': 0.0004717921737001276, 'samples': 4722432, 'steps': 24595, 'loss/train': 1.7163532972335815} 08/30/2021 17:35:53 - INFO - __main__ - Step 24597: {'lr': 0.0004717897248782555, 'samples': 4722624, 'steps': 24596, 'loss/train': 1.384665846824646} 08/30/2021 17:35:55 - INFO - __main__ - Step 24598: {'lr': 0.0004717872759564483, 'samples': 4722816, 'steps': 24597, 'loss/train': 1.6244404315948486} 08/30/2021 17:35:55 - INFO - __main__ - Step 24599: {'lr': 0.00047178482693470723, 'samples': 4723008, 'steps': 24598, 'loss/train': 1.0666124820709229} 08/30/2021 17:35:56 - INFO - __main__ - Step 24600: {'lr': 0.0004717823778130333, 'samples': 4723200, 'steps': 24599, 'loss/train': 1.7034012079238892} 08/30/2021 17:35:56 - INFO - __main__ - Step 24601: {'lr': 0.0004717799285914276, 'samples': 4723392, 'steps': 24600, 'loss/train': 0.16433797776699066} 08/30/2021 17:35:56 - INFO - __main__ - Step 24602: {'lr': 0.00047177747926989134, 'samples': 4723584, 'steps': 24601, 'loss/train': 2.712157726287842} 08/30/2021 17:35:57 - INFO - __main__ - Step 24603: {'lr': 0.00047177502984842556, 'samples': 4723776, 'steps': 24602, 'loss/train': 1.598645806312561} 08/30/2021 17:35:58 - INFO - __main__ - Step 24604: {'lr': 0.0004717725803270314, 'samples': 4723968, 'steps': 24603, 'loss/train': 1.755679965019226} 08/30/2021 17:35:59 - INFO - __main__ - Step 24605: {'lr': 0.00047177013070570997, 'samples': 4724160, 'steps': 24604, 'loss/train': 1.4169636964797974} 08/30/2021 17:35:59 - INFO - __main__ - Step 24606: {'lr': 0.00047176768098446234, 'samples': 4724352, 'steps': 24605, 'loss/train': 1.1529072523117065} 08/30/2021 17:36:00 - INFO - __main__ - Step 24607: {'lr': 0.0004717652311632895, 'samples': 4724544, 'steps': 24606, 'loss/train': 1.3863716125488281} 08/30/2021 17:36:00 - INFO - __main__ - Step 24608: {'lr': 0.00047176278124219276, 'samples': 4724736, 'steps': 24607, 'loss/train': 1.675790786743164} 08/30/2021 17:36:02 - INFO - __main__ - Step 24609: {'lr': 0.0004717603312211731, 'samples': 4724928, 'steps': 24608, 'loss/train': 0.26380455493927} 08/30/2021 17:36:02 - INFO - __main__ - Step 24610: {'lr': 0.0004717578811002317, 'samples': 4725120, 'steps': 24609, 'loss/train': 1.3129373788833618} 08/30/2021 17:36:02 - INFO - __main__ - Step 24611: {'lr': 0.00047175543087936954, 'samples': 4725312, 'steps': 24610, 'loss/train': 1.8768680095672607} 08/30/2021 17:36:03 - INFO - __main__ - Step 24612: {'lr': 0.0004717529805585879, 'samples': 4725504, 'steps': 24611, 'loss/train': 1.6882539987564087} 08/30/2021 17:36:03 - INFO - __main__ - Step 24613: {'lr': 0.0004717505301378877, 'samples': 4725696, 'steps': 24612, 'loss/train': 1.4596537351608276} 08/30/2021 17:36:05 - INFO - __main__ - Step 24614: {'lr': 0.0004717480796172702, 'samples': 4725888, 'steps': 24613, 'loss/train': 1.701680064201355} 08/30/2021 17:36:06 - INFO - __main__ - Step 24615: {'lr': 0.00047174562899673645, 'samples': 4726080, 'steps': 24614, 'loss/train': 1.0368670225143433} 08/30/2021 17:36:06 - INFO - __main__ - Step 24616: {'lr': 0.0004717431782762875, 'samples': 4726272, 'steps': 24615, 'loss/train': 1.6600544452667236} 08/30/2021 17:36:06 - INFO - __main__ - Step 24617: {'lr': 0.0004717407274559245, 'samples': 4726464, 'steps': 24616, 'loss/train': 1.3087135553359985} 08/30/2021 17:36:07 - INFO - __main__ - Step 24618: {'lr': 0.0004717382765356485, 'samples': 4726656, 'steps': 24617, 'loss/train': 1.6702946424484253} 08/30/2021 17:36:09 - INFO - __main__ - Step 24619: {'lr': 0.0004717358255154607, 'samples': 4726848, 'steps': 24618, 'loss/train': 1.688079595565796} 08/30/2021 17:36:09 - INFO - __main__ - Step 24620: {'lr': 0.0004717333743953622, 'samples': 4727040, 'steps': 24619, 'loss/train': 1.955341100692749} 08/30/2021 17:36:10 - INFO - __main__ - Step 24621: {'lr': 0.00047173092317535404, 'samples': 4727232, 'steps': 24620, 'loss/train': 8.874281883239746} 08/30/2021 17:36:10 - INFO - __main__ - Step 24622: {'lr': 0.0004717284718554373, 'samples': 4727424, 'steps': 24621, 'loss/train': 2.65262508392334} 08/30/2021 17:36:10 - INFO - __main__ - Step 24623: {'lr': 0.00047172602043561317, 'samples': 4727616, 'steps': 24622, 'loss/train': 2.1952600479125977} 08/30/2021 17:36:11 - INFO - __main__ - Step 24624: {'lr': 0.00047172356891588273, 'samples': 4727808, 'steps': 24623, 'loss/train': 2.558573007583618} 08/30/2021 17:36:12 - INFO - __main__ - Step 24625: {'lr': 0.0004717211172962471, 'samples': 4728000, 'steps': 24624, 'loss/train': 2.1402010917663574} 08/30/2021 17:36:13 - INFO - __main__ - Step 24626: {'lr': 0.0004717186655767073, 'samples': 4728192, 'steps': 24625, 'loss/train': 2.7358956336975098} 08/30/2021 17:36:13 - INFO - __main__ - Step 24627: {'lr': 0.0004717162137572645, 'samples': 4728384, 'steps': 24626, 'loss/train': 2.4930129051208496} 08/30/2021 17:36:13 - INFO - __main__ - Step 24628: {'lr': 0.0004717137618379198, 'samples': 4728576, 'steps': 24627, 'loss/train': 1.7966632843017578} 08/30/2021 17:36:14 - INFO - __main__ - Step 24629: {'lr': 0.0004717113098186743, 'samples': 4728768, 'steps': 24628, 'loss/train': 1.99289870262146} 08/30/2021 17:36:15 - INFO - __main__ - Step 24630: {'lr': 0.00047170885769952907, 'samples': 4728960, 'steps': 24629, 'loss/train': 1.6715341806411743} 08/30/2021 17:36:15 - INFO - __main__ - Step 24631: {'lr': 0.00047170640548048525, 'samples': 4729152, 'steps': 24630, 'loss/train': 1.4821505546569824} 08/30/2021 17:36:16 - INFO - __main__ - Step 24632: {'lr': 0.000471703953161544, 'samples': 4729344, 'steps': 24631, 'loss/train': 1.797239065170288} 08/30/2021 17:36:16 - INFO - __main__ - Step 24633: {'lr': 0.00047170150074270635, 'samples': 4729536, 'steps': 24632, 'loss/train': 1.791114091873169} 08/30/2021 17:36:17 - INFO - __main__ - Step 24634: {'lr': 0.0004716990482239735, 'samples': 4729728, 'steps': 24633, 'loss/train': 1.8352652788162231} 08/30/2021 17:36:18 - INFO - __main__ - Step 24635: {'lr': 0.0004716965956053463, 'samples': 4729920, 'steps': 24634, 'loss/train': 2.2326345443725586} 08/30/2021 17:36:19 - INFO - __main__ - Step 24636: {'lr': 0.00047169414288682616, 'samples': 4730112, 'steps': 24635, 'loss/train': 2.186173677444458} 08/30/2021 17:36:19 - INFO - __main__ - Step 24637: {'lr': 0.0004716916900684141, 'samples': 4730304, 'steps': 24636, 'loss/train': 1.9529016017913818} 08/30/2021 17:36:19 - INFO - __main__ - Step 24638: {'lr': 0.00047168923715011103, 'samples': 4730496, 'steps': 24637, 'loss/train': 2.344886064529419} 08/30/2021 17:36:20 - INFO - __main__ - Step 24639: {'lr': 0.00047168678413191833, 'samples': 4730688, 'steps': 24638, 'loss/train': 1.982452630996704} 08/30/2021 17:36:21 - INFO - __main__ - Step 24640: {'lr': 0.00047168433101383694, 'samples': 4730880, 'steps': 24639, 'loss/train': 1.9556173086166382} 08/30/2021 17:36:22 - INFO - __main__ - Step 24641: {'lr': 0.000471681877795868, 'samples': 4731072, 'steps': 24640, 'loss/train': 1.4128801822662354} 08/30/2021 17:36:22 - INFO - __main__ - Step 24642: {'lr': 0.0004716794244780127, 'samples': 4731264, 'steps': 24641, 'loss/train': 2.0736827850341797} 08/30/2021 17:36:22 - INFO - __main__ - Step 24643: {'lr': 0.0004716769710602721, 'samples': 4731456, 'steps': 24642, 'loss/train': 2.4431746006011963} 08/30/2021 17:36:23 - INFO - __main__ - Step 24644: {'lr': 0.00047167451754264714, 'samples': 4731648, 'steps': 24643, 'loss/train': 1.5567020177841187} 08/30/2021 17:36:23 - INFO - __main__ - Step 24645: {'lr': 0.0004716720639251392, 'samples': 4731840, 'steps': 24644, 'loss/train': 2.360151767730713} 08/30/2021 17:36:24 - INFO - __main__ - Step 24646: {'lr': 0.0004716696102077491, 'samples': 4732032, 'steps': 24645, 'loss/train': 1.8170424699783325} 08/30/2021 17:36:25 - INFO - __main__ - Step 24647: {'lr': 0.0004716671563904782, 'samples': 4732224, 'steps': 24646, 'loss/train': 2.0453975200653076} 08/30/2021 17:36:25 - INFO - __main__ - Step 24648: {'lr': 0.0004716647024733275, 'samples': 4732416, 'steps': 24647, 'loss/train': 1.7449759244918823} 08/30/2021 17:36:26 - INFO - __main__ - Step 24649: {'lr': 0.00047166224845629804, 'samples': 4732608, 'steps': 24648, 'loss/train': 1.9197039604187012} 08/30/2021 17:36:26 - INFO - __main__ - Step 24650: {'lr': 0.000471659794339391, 'samples': 4732800, 'steps': 24649, 'loss/train': 1.9616122245788574} 08/30/2021 17:36:28 - INFO - __main__ - Step 24651: {'lr': 0.00047165734012260754, 'samples': 4732992, 'steps': 24650, 'loss/train': 2.1116483211517334} 08/30/2021 17:36:28 - INFO - __main__ - Step 24652: {'lr': 0.0004716548858059486, 'samples': 4733184, 'steps': 24651, 'loss/train': 1.3150659799575806} 08/30/2021 17:36:28 - INFO - __main__ - Step 24653: {'lr': 0.0004716524313894155, 'samples': 4733376, 'steps': 24652, 'loss/train': 1.4902786016464233} 08/30/2021 17:36:29 - INFO - __main__ - Step 24654: {'lr': 0.0004716499768730092, 'samples': 4733568, 'steps': 24653, 'loss/train': 1.7323554754257202} 08/30/2021 17:36:29 - INFO - __main__ - Step 24655: {'lr': 0.0004716475222567308, 'samples': 4733760, 'steps': 24654, 'loss/train': 1.4266170263290405} 08/30/2021 17:36:31 - INFO - __main__ - Step 24656: {'lr': 0.0004716450675405815, 'samples': 4733952, 'steps': 24655, 'loss/train': 2.019360303878784} 08/30/2021 17:36:31 - INFO - __main__ - Step 24657: {'lr': 0.0004716426127245623, 'samples': 4734144, 'steps': 24656, 'loss/train': 1.9479265213012695} 08/30/2021 17:36:31 - INFO - __main__ - Step 24658: {'lr': 0.00047164015780867444, 'samples': 4734336, 'steps': 24657, 'loss/train': 1.0647599697113037} 08/30/2021 17:36:32 - INFO - __main__ - Step 24659: {'lr': 0.0004716377027929189, 'samples': 4734528, 'steps': 24658, 'loss/train': 1.8619252443313599} 08/30/2021 17:36:32 - INFO - __main__ - Step 24660: {'lr': 0.00047163524767729684, 'samples': 4734720, 'steps': 24659, 'loss/train': 1.6403992176055908} 08/30/2021 17:36:32 - INFO - __main__ - Step 24661: {'lr': 0.0004716327924618093, 'samples': 4734912, 'steps': 24660, 'loss/train': 0.9954274296760559} 08/30/2021 17:36:35 - INFO - __main__ - Step 24662: {'lr': 0.0004716303371464575, 'samples': 4735104, 'steps': 24661, 'loss/train': 1.2608269453048706} 08/30/2021 17:36:35 - INFO - __main__ - Step 24663: {'lr': 0.0004716278817312425, 'samples': 4735296, 'steps': 24662, 'loss/train': 1.1998200416564941} 08/30/2021 17:36:35 - INFO - __main__ - Step 24664: {'lr': 0.0004716254262161653, 'samples': 4735488, 'steps': 24663, 'loss/train': 3.4208500385284424} 08/30/2021 17:36:36 - INFO - __main__ - Step 24665: {'lr': 0.00047162297060122726, 'samples': 4735680, 'steps': 24664, 'loss/train': 1.499505639076233} 08/30/2021 17:36:36 - INFO - __main__ - Step 24666: {'lr': 0.0004716205148864292, 'samples': 4735872, 'steps': 24665, 'loss/train': 1.7700446844100952} 08/30/2021 17:36:38 - INFO - __main__ - Step 24667: {'lr': 0.0004716180590717724, 'samples': 4736064, 'steps': 24666, 'loss/train': 2.8480496406555176} 08/30/2021 17:36:38 - INFO - __main__ - Step 24668: {'lr': 0.0004716156031572579, 'samples': 4736256, 'steps': 24667, 'loss/train': 1.711680293083191} 08/30/2021 17:36:38 - INFO - __main__ - Step 24669: {'lr': 0.00047161314714288697, 'samples': 4736448, 'steps': 24668, 'loss/train': 1.791342854499817} 08/30/2021 17:36:39 - INFO - __main__ - Step 24670: {'lr': 0.00047161069102866037, 'samples': 4736640, 'steps': 24669, 'loss/train': 2.0235402584075928} 08/30/2021 17:36:39 - INFO - __main__ - Step 24671: {'lr': 0.00047160823481457955, 'samples': 4736832, 'steps': 24670, 'loss/train': 1.6442534923553467} 08/30/2021 17:36:41 - INFO - __main__ - Step 24672: {'lr': 0.0004716057785006454, 'samples': 4737024, 'steps': 24671, 'loss/train': 2.016108274459839} 08/30/2021 17:36:41 - INFO - __main__ - Step 24673: {'lr': 0.00047160332208685915, 'samples': 4737216, 'steps': 24672, 'loss/train': 1.0705252885818481} 08/30/2021 17:36:42 - INFO - __main__ - Step 24674: {'lr': 0.00047160086557322185, 'samples': 4737408, 'steps': 24673, 'loss/train': 1.2105544805526733} 08/30/2021 17:36:42 - INFO - __main__ - Step 24675: {'lr': 0.0004715984089597346, 'samples': 4737600, 'steps': 24674, 'loss/train': 1.826501727104187} 08/30/2021 17:36:42 - INFO - __main__ - Step 24676: {'lr': 0.00047159595224639854, 'samples': 4737792, 'steps': 24675, 'loss/train': 0.3165826201438904} 08/30/2021 17:36:44 - INFO - __main__ - Step 24677: {'lr': 0.00047159349543321477, 'samples': 4737984, 'steps': 24676, 'loss/train': 2.6708781719207764} 08/30/2021 17:36:44 - INFO - __main__ - Step 24678: {'lr': 0.00047159103852018443, 'samples': 4738176, 'steps': 24677, 'loss/train': 2.4192936420440674} 08/30/2021 17:36:45 - INFO - __main__ - Step 24679: {'lr': 0.00047158858150730856, 'samples': 4738368, 'steps': 24678, 'loss/train': 1.0226179361343384} 08/30/2021 17:36:45 - INFO - __main__ - Step 24680: {'lr': 0.00047158612439458824, 'samples': 4738560, 'steps': 24679, 'loss/train': 1.7899672985076904} 08/30/2021 17:36:45 - INFO - __main__ - Step 24681: {'lr': 0.00047158366718202466, 'samples': 4738752, 'steps': 24680, 'loss/train': 1.428963541984558} 08/30/2021 17:36:47 - INFO - __main__ - Step 24682: {'lr': 0.00047158120986961897, 'samples': 4738944, 'steps': 24681, 'loss/train': 3.1310064792633057} 08/30/2021 17:36:47 - INFO - __main__ - Step 24683: {'lr': 0.00047157875245737213, 'samples': 4739136, 'steps': 24682, 'loss/train': 1.679357886314392} 08/30/2021 17:36:48 - INFO - __main__ - Step 24684: {'lr': 0.0004715762949452853, 'samples': 4739328, 'steps': 24683, 'loss/train': 1.8991272449493408} 08/30/2021 17:36:48 - INFO - __main__ - Step 24685: {'lr': 0.0004715738373333597, 'samples': 4739520, 'steps': 24684, 'loss/train': 2.5505757331848145} 08/30/2021 17:36:48 - INFO - __main__ - Step 24686: {'lr': 0.00047157137962159626, 'samples': 4739712, 'steps': 24685, 'loss/train': 1.6282877922058105} 08/30/2021 17:36:50 - INFO - __main__ - Step 24687: {'lr': 0.00047156892180999624, 'samples': 4739904, 'steps': 24686, 'loss/train': 1.6711379289627075} 08/30/2021 17:36:50 - INFO - __main__ - Step 24688: {'lr': 0.0004715664638985606, 'samples': 4740096, 'steps': 24687, 'loss/train': 1.3490301370620728} 08/30/2021 17:36:51 - INFO - __main__ - Step 24689: {'lr': 0.00047156400588729066, 'samples': 4740288, 'steps': 24688, 'loss/train': 1.1491557359695435} 08/30/2021 17:36:51 - INFO - __main__ - Step 24690: {'lr': 0.0004715615477761873, 'samples': 4740480, 'steps': 24689, 'loss/train': 1.516879677772522} 08/30/2021 17:36:51 - INFO - __main__ - Step 24691: {'lr': 0.00047155908956525173, 'samples': 4740672, 'steps': 24690, 'loss/train': 1.952373743057251} 08/30/2021 17:36:53 - INFO - __main__ - Step 24692: {'lr': 0.00047155663125448514, 'samples': 4740864, 'steps': 24691, 'loss/train': 1.933780550956726} 08/30/2021 17:36:53 - INFO - __main__ - Step 24693: {'lr': 0.00047155417284388846, 'samples': 4741056, 'steps': 24692, 'loss/train': 1.5821880102157593} 08/30/2021 17:36:54 - INFO - __main__ - Step 24694: {'lr': 0.0004715517143334629, 'samples': 4741248, 'steps': 24693, 'loss/train': 1.258436918258667} 08/30/2021 17:36:54 - INFO - __main__ - Step 24695: {'lr': 0.00047154925572320957, 'samples': 4741440, 'steps': 24694, 'loss/train': 1.8043732643127441} 08/30/2021 17:36:54 - INFO - __main__ - Step 24696: {'lr': 0.00047154679701312953, 'samples': 4741632, 'steps': 24695, 'loss/train': 1.8346304893493652} 08/30/2021 17:36:56 - INFO - __main__ - Step 24697: {'lr': 0.00047154433820322395, 'samples': 4741824, 'steps': 24696, 'loss/train': 1.851894736289978} 08/30/2021 17:36:57 - INFO - __main__ - Step 24698: {'lr': 0.0004715418792934939, 'samples': 4742016, 'steps': 24697, 'loss/train': 0.8953798413276672} 08/30/2021 17:36:57 - INFO - __main__ - Step 24699: {'lr': 0.00047153942028394056, 'samples': 4742208, 'steps': 24698, 'loss/train': 1.6787607669830322} 08/30/2021 17:36:57 - INFO - __main__ - Step 24700: {'lr': 0.0004715369611745649, 'samples': 4742400, 'steps': 24699, 'loss/train': 0.9864576458930969} 08/30/2021 17:36:58 - INFO - __main__ - Step 24701: {'lr': 0.00047153450196536816, 'samples': 4742592, 'steps': 24700, 'loss/train': 1.7255611419677734} 08/30/2021 17:36:58 - INFO - __main__ - Step 24702: {'lr': 0.00047153204265635136, 'samples': 4742784, 'steps': 24701, 'loss/train': 1.9156755208969116} 08/30/2021 17:37:00 - INFO - __main__ - Step 24703: {'lr': 0.0004715295832475156, 'samples': 4742976, 'steps': 24702, 'loss/train': 0.8458746075630188} 08/30/2021 17:37:00 - INFO - __main__ - Step 24704: {'lr': 0.0004715271237388621, 'samples': 4743168, 'steps': 24703, 'loss/train': 2.1463427543640137} 08/30/2021 17:37:01 - INFO - __main__ - Step 24705: {'lr': 0.00047152466413039187, 'samples': 4743360, 'steps': 24704, 'loss/train': 1.0671817064285278} 08/30/2021 17:37:01 - INFO - __main__ - Step 24706: {'lr': 0.000471522204422106, 'samples': 4743552, 'steps': 24705, 'loss/train': 1.732177972793579} 08/30/2021 17:37:01 - INFO - __main__ - Step 24707: {'lr': 0.0004715197446140057, 'samples': 4743744, 'steps': 24706, 'loss/train': 1.5347830057144165} 08/30/2021 17:37:03 - INFO - __main__ - Step 24708: {'lr': 0.000471517284706092, 'samples': 4743936, 'steps': 24707, 'loss/train': 0.5448461174964905} 08/30/2021 17:37:04 - INFO - __main__ - Step 24709: {'lr': 0.0004715148246983661, 'samples': 4744128, 'steps': 24708, 'loss/train': 1.5225915908813477} 08/30/2021 17:37:04 - INFO - __main__ - Step 24710: {'lr': 0.000471512364590829, 'samples': 4744320, 'steps': 24709, 'loss/train': 2.057853937149048} 08/30/2021 17:37:05 - INFO - __main__ - Step 24711: {'lr': 0.0004715099043834818, 'samples': 4744512, 'steps': 24710, 'loss/train': 1.7252074480056763} 08/30/2021 17:37:05 - INFO - __main__ - Step 24712: {'lr': 0.00047150744407632565, 'samples': 4744704, 'steps': 24711, 'loss/train': 1.6189361810684204} 08/30/2021 17:37:05 - INFO - __main__ - Step 24713: {'lr': 0.00047150498366936165, 'samples': 4744896, 'steps': 24712, 'loss/train': 1.311771035194397} 08/30/2021 17:37:07 - INFO - __main__ - Step 24714: {'lr': 0.000471502523162591, 'samples': 4745088, 'steps': 24713, 'loss/train': 0.9976238012313843} 08/30/2021 17:37:07 - INFO - __main__ - Step 24715: {'lr': 0.00047150006255601475, 'samples': 4745280, 'steps': 24714, 'loss/train': 1.0881123542785645} 08/30/2021 17:37:08 - INFO - __main__ - Step 24716: {'lr': 0.00047149760184963385, 'samples': 4745472, 'steps': 24715, 'loss/train': 1.610553503036499} 08/30/2021 17:37:08 - INFO - __main__ - Step 24717: {'lr': 0.0004714951410434497, 'samples': 4745664, 'steps': 24716, 'loss/train': 1.5979219675064087} 08/30/2021 17:37:08 - INFO - __main__ - Step 24718: {'lr': 0.00047149268013746317, 'samples': 4745856, 'steps': 24717, 'loss/train': 1.687117576599121} 08/30/2021 17:37:09 - INFO - __main__ - Step 24719: {'lr': 0.00047149021913167545, 'samples': 4746048, 'steps': 24718, 'loss/train': 1.535128116607666} 08/30/2021 17:37:11 - INFO - __main__ - Step 24720: {'lr': 0.0004714877580260877, 'samples': 4746240, 'steps': 24719, 'loss/train': 0.8547623157501221} 08/30/2021 17:37:11 - INFO - __main__ - Step 24721: {'lr': 0.00047148529682070094, 'samples': 4746432, 'steps': 24720, 'loss/train': 1.5548758506774902} 08/30/2021 17:37:12 - INFO - __main__ - Step 24722: {'lr': 0.00047148283551551643, 'samples': 4746624, 'steps': 24721, 'loss/train': 1.661041021347046} 08/30/2021 17:37:12 - INFO - __main__ - Step 24723: {'lr': 0.000471480374110535, 'samples': 4746816, 'steps': 24722, 'loss/train': 1.4511311054229736} 08/30/2021 17:37:12 - INFO - __main__ - Step 24724: {'lr': 0.00047147791260575804, 'samples': 4747008, 'steps': 24723, 'loss/train': 2.2207934856414795} 08/30/2021 17:37:14 - INFO - __main__ - Step 24725: {'lr': 0.0004714754510011866, 'samples': 4747200, 'steps': 24724, 'loss/train': 1.2171140909194946} 08/30/2021 17:37:14 - INFO - __main__ - Step 24726: {'lr': 0.0004714729892968216, 'samples': 4747392, 'steps': 24725, 'loss/train': 1.4494720697402954} 08/30/2021 17:37:15 - INFO - __main__ - Step 24727: {'lr': 0.0004714705274926644, 'samples': 4747584, 'steps': 24726, 'loss/train': 1.689841389656067} 08/30/2021 17:37:15 - INFO - __main__ - Step 24728: {'lr': 0.00047146806558871594, 'samples': 4747776, 'steps': 24727, 'loss/train': 2.315096139907837} 08/30/2021 17:37:15 - INFO - __main__ - Step 24729: {'lr': 0.0004714656035849774, 'samples': 4747968, 'steps': 24728, 'loss/train': 2.113011598587036} 08/30/2021 17:37:17 - INFO - __main__ - Step 24730: {'lr': 0.00047146314148144986, 'samples': 4748160, 'steps': 24729, 'loss/train': 1.8264377117156982} 08/30/2021 17:37:17 - INFO - __main__ - Step 24731: {'lr': 0.00047146067927813454, 'samples': 4748352, 'steps': 24730, 'loss/train': 1.8549612760543823} 08/30/2021 17:37:18 - INFO - __main__ - Step 24732: {'lr': 0.00047145821697503235, 'samples': 4748544, 'steps': 24731, 'loss/train': 1.5308011770248413} 08/30/2021 17:37:18 - INFO - __main__ - Step 24733: {'lr': 0.00047145575457214453, 'samples': 4748736, 'steps': 24732, 'loss/train': 2.0067386627197266} 08/30/2021 17:37:18 - INFO - __main__ - Step 24734: {'lr': 0.00047145329206947216, 'samples': 4748928, 'steps': 24733, 'loss/train': 2.21530818939209} 08/30/2021 17:37:20 - INFO - __main__ - Step 24735: {'lr': 0.0004714508294670164, 'samples': 4749120, 'steps': 24734, 'loss/train': 1.8082433938980103} 08/30/2021 17:37:21 - INFO - __main__ - Step 24736: {'lr': 0.00047144836676477823, 'samples': 4749312, 'steps': 24735, 'loss/train': 1.5817692279815674} 08/30/2021 17:37:21 - INFO - __main__ - Step 24737: {'lr': 0.00047144590396275895, 'samples': 4749504, 'steps': 24736, 'loss/train': 1.4714477062225342} 08/30/2021 17:37:21 - INFO - __main__ - Step 24738: {'lr': 0.0004714434410609595, 'samples': 4749696, 'steps': 24737, 'loss/train': 1.575246810913086} 08/30/2021 17:37:22 - INFO - __main__ - Step 24739: {'lr': 0.00047144097805938104, 'samples': 4749888, 'steps': 24738, 'loss/train': 2.1753039360046387} 08/30/2021 17:37:23 - INFO - __main__ - Step 24740: {'lr': 0.0004714385149580247, 'samples': 4750080, 'steps': 24739, 'loss/train': 1.9992939233779907} 08/30/2021 17:37:24 - INFO - __main__ - Step 24741: {'lr': 0.0004714360517568916, 'samples': 4750272, 'steps': 24740, 'loss/train': 1.570160984992981} 08/30/2021 17:37:24 - INFO - __main__ - Step 24742: {'lr': 0.00047143358845598283, 'samples': 4750464, 'steps': 24741, 'loss/train': 1.3570243120193481} 08/30/2021 17:37:25 - INFO - __main__ - Step 24743: {'lr': 0.0004714311250552995, 'samples': 4750656, 'steps': 24742, 'loss/train': 1.7493219375610352} 08/30/2021 17:37:25 - INFO - __main__ - Step 24744: {'lr': 0.0004714286615548427, 'samples': 4750848, 'steps': 24743, 'loss/train': 1.5323597192764282} 08/30/2021 17:37:25 - INFO - __main__ - Step 24745: {'lr': 0.00047142619795461363, 'samples': 4751040, 'steps': 24744, 'loss/train': 1.1970270872116089} 08/30/2021 17:37:27 - INFO - __main__ - Step 24746: {'lr': 0.0004714237342546133, 'samples': 4751232, 'steps': 24745, 'loss/train': 0.1257409304380417} 08/30/2021 17:37:27 - INFO - __main__ - Step 24747: {'lr': 0.0004714212704548428, 'samples': 4751424, 'steps': 24746, 'loss/train': 1.4161252975463867} 08/30/2021 17:37:28 - INFO - __main__ - Step 24748: {'lr': 0.0004714188065553033, 'samples': 4751616, 'steps': 24747, 'loss/train': 1.1785532236099243} 08/30/2021 17:37:28 - INFO - __main__ - Step 24749: {'lr': 0.000471416342555996, 'samples': 4751808, 'steps': 24748, 'loss/train': 1.6573036909103394} 08/30/2021 17:37:28 - INFO - __main__ - Step 24750: {'lr': 0.00047141387845692174, 'samples': 4752000, 'steps': 24749, 'loss/train': 1.5083427429199219} 08/30/2021 17:37:30 - INFO - __main__ - Step 24751: {'lr': 0.0004714114142580819, 'samples': 4752192, 'steps': 24750, 'loss/train': 1.8364665508270264} 08/30/2021 17:37:30 - INFO - __main__ - Step 24752: {'lr': 0.00047140894995947755, 'samples': 4752384, 'steps': 24751, 'loss/train': 1.4609259366989136} 08/30/2021 17:37:31 - INFO - __main__ - Step 24753: {'lr': 0.00047140648556110966, 'samples': 4752576, 'steps': 24752, 'loss/train': 0.3895515501499176} 08/30/2021 17:37:31 - INFO - __main__ - Step 24754: {'lr': 0.00047140402106297946, 'samples': 4752768, 'steps': 24753, 'loss/train': 0.6205389499664307} 08/30/2021 17:37:31 - INFO - __main__ - Step 24755: {'lr': 0.000471401556465088, 'samples': 4752960, 'steps': 24754, 'loss/train': 1.293762445449829} 08/30/2021 17:37:33 - INFO - __main__ - Step 24756: {'lr': 0.00047139909176743643, 'samples': 4753152, 'steps': 24755, 'loss/train': 2.1234817504882812} 08/30/2021 17:37:33 - INFO - __main__ - Step 24757: {'lr': 0.0004713966269700259, 'samples': 4753344, 'steps': 24756, 'loss/train': 1.7344706058502197} 08/30/2021 17:37:34 - INFO - __main__ - Step 24758: {'lr': 0.0004713941620728574, 'samples': 4753536, 'steps': 24757, 'loss/train': 1.5988022089004517} 08/30/2021 17:37:34 - INFO - __main__ - Step 24759: {'lr': 0.0004713916970759321, 'samples': 4753728, 'steps': 24758, 'loss/train': 1.777037262916565} 08/30/2021 17:37:34 - INFO - __main__ - Step 24760: {'lr': 0.0004713892319792512, 'samples': 4753920, 'steps': 24759, 'loss/train': 2.254842758178711} 08/30/2021 17:37:35 - INFO - __main__ - Step 24761: {'lr': 0.00047138676678281564, 'samples': 4754112, 'steps': 24760, 'loss/train': 1.8314911127090454} 08/30/2021 17:37:36 - INFO - __main__ - Step 24762: {'lr': 0.00047138430148662666, 'samples': 4754304, 'steps': 24761, 'loss/train': 1.539853572845459} 08/30/2021 17:37:37 - INFO - __main__ - Step 24763: {'lr': 0.0004713818360906853, 'samples': 4754496, 'steps': 24762, 'loss/train': 1.1455368995666504} 08/30/2021 17:37:37 - INFO - __main__ - Step 24764: {'lr': 0.0004713793705949927, 'samples': 4754688, 'steps': 24763, 'loss/train': 1.1345278024673462} 08/30/2021 17:37:37 - INFO - __main__ - Step 24765: {'lr': 0.00047137690499955, 'samples': 4754880, 'steps': 24764, 'loss/train': 1.9125782251358032} 08/30/2021 17:37:38 - INFO - __main__ - Step 24766: {'lr': 0.0004713744393043583, 'samples': 4755072, 'steps': 24765, 'loss/train': 1.405653715133667} 08/30/2021 17:37:39 - INFO - __main__ - Step 24767: {'lr': 0.00047137197350941864, 'samples': 4755264, 'steps': 24766, 'loss/train': 2.287050485610962} 08/30/2021 17:37:40 - INFO - __main__ - Step 24768: {'lr': 0.0004713695076147322, 'samples': 4755456, 'steps': 24767, 'loss/train': 1.530613899230957} 08/30/2021 17:37:40 - INFO - __main__ - Step 24769: {'lr': 0.0004713670416203001, 'samples': 4755648, 'steps': 24768, 'loss/train': 1.371817708015442} 08/30/2021 17:37:40 - INFO - __main__ - Step 24770: {'lr': 0.00047136457552612344, 'samples': 4755840, 'steps': 24769, 'loss/train': 1.6049026250839233} 08/30/2021 17:37:41 - INFO - __main__ - Step 24771: {'lr': 0.00047136210933220325, 'samples': 4756032, 'steps': 24770, 'loss/train': 1.4269808530807495} 08/30/2021 17:37:43 - INFO - __main__ - Step 24772: {'lr': 0.0004713596430385408, 'samples': 4756224, 'steps': 24771, 'loss/train': 1.1746535301208496} 08/30/2021 17:37:43 - INFO - __main__ - Step 24773: {'lr': 0.00047135717664513704, 'samples': 4756416, 'steps': 24772, 'loss/train': 1.168184518814087} 08/30/2021 17:37:43 - INFO - __main__ - Step 24774: {'lr': 0.00047135471015199315, 'samples': 4756608, 'steps': 24773, 'loss/train': 2.0779831409454346} 08/30/2021 17:37:44 - INFO - __main__ - Step 24775: {'lr': 0.00047135224355911035, 'samples': 4756800, 'steps': 24774, 'loss/train': 1.5183665752410889} 08/30/2021 17:37:44 - INFO - __main__ - Step 24776: {'lr': 0.0004713497768664895, 'samples': 4756992, 'steps': 24775, 'loss/train': 1.5069047212600708} 08/30/2021 17:37:45 - INFO - __main__ - Step 24777: {'lr': 0.00047134731007413195, 'samples': 4757184, 'steps': 24776, 'loss/train': 1.4242967367172241} 08/30/2021 17:37:46 - INFO - __main__ - Step 24778: {'lr': 0.0004713448431820387, 'samples': 4757376, 'steps': 24777, 'loss/train': 1.7829294204711914} 08/30/2021 17:37:46 - INFO - __main__ - Step 24779: {'lr': 0.00047134237619021085, 'samples': 4757568, 'steps': 24778, 'loss/train': 1.5085433721542358} 08/30/2021 17:37:47 - INFO - __main__ - Step 24780: {'lr': 0.00047133990909864953, 'samples': 4757760, 'steps': 24779, 'loss/train': 1.993310809135437} 08/30/2021 17:37:47 - INFO - __main__ - Step 24781: {'lr': 0.0004713374419073559, 'samples': 4757952, 'steps': 24780, 'loss/train': 0.9177327156066895} 08/30/2021 17:37:49 - INFO - __main__ - Step 24782: {'lr': 0.000471334974616331, 'samples': 4758144, 'steps': 24781, 'loss/train': 1.706955075263977} 08/30/2021 17:37:49 - INFO - __main__ - Step 24783: {'lr': 0.0004713325072255761, 'samples': 4758336, 'steps': 24782, 'loss/train': 0.8460226655006409} 08/30/2021 17:37:49 - INFO - __main__ - Step 24784: {'lr': 0.000471330039735092, 'samples': 4758528, 'steps': 24783, 'loss/train': 2.2417311668395996} 08/30/2021 17:37:50 - INFO - __main__ - Step 24785: {'lr': 0.0004713275721448801, 'samples': 4758720, 'steps': 24784, 'loss/train': 1.4460208415985107} 08/30/2021 17:37:50 - INFO - __main__ - Step 24786: {'lr': 0.0004713251044549414, 'samples': 4758912, 'steps': 24785, 'loss/train': 1.573750376701355} 08/30/2021 17:37:52 - INFO - __main__ - Step 24787: {'lr': 0.000471322636665277, 'samples': 4759104, 'steps': 24786, 'loss/train': 1.1347050666809082} 08/30/2021 17:37:52 - INFO - __main__ - Step 24788: {'lr': 0.0004713201687758881, 'samples': 4759296, 'steps': 24787, 'loss/train': 1.8069311380386353} 08/30/2021 17:37:53 - INFO - __main__ - Step 24789: {'lr': 0.00047131770078677574, 'samples': 4759488, 'steps': 24788, 'loss/train': 1.2345600128173828} 08/30/2021 17:37:53 - INFO - __main__ - Step 24790: {'lr': 0.000471315232697941, 'samples': 4759680, 'steps': 24789, 'loss/train': 1.3568607568740845} 08/30/2021 17:37:53 - INFO - __main__ - Step 24791: {'lr': 0.000471312764509385, 'samples': 4759872, 'steps': 24790, 'loss/train': 1.601361870765686} 08/30/2021 17:37:55 - INFO - __main__ - Step 24792: {'lr': 0.0004713102962211089, 'samples': 4760064, 'steps': 24791, 'loss/train': 1.5752657651901245} 08/30/2021 17:37:55 - INFO - __main__ - Step 24793: {'lr': 0.0004713078278331138, 'samples': 4760256, 'steps': 24792, 'loss/train': 1.6407828330993652} 08/30/2021 17:37:55 - INFO - __main__ - Step 24794: {'lr': 0.00047130535934540086, 'samples': 4760448, 'steps': 24793, 'loss/train': 1.9434902667999268} 08/30/2021 17:37:56 - INFO - __main__ - Step 24795: {'lr': 0.00047130289075797107, 'samples': 4760640, 'steps': 24794, 'loss/train': 1.1096513271331787} 08/30/2021 17:37:56 - INFO - __main__ - Step 24796: {'lr': 0.0004713004220708257, 'samples': 4760832, 'steps': 24795, 'loss/train': 1.5200589895248413} 08/30/2021 17:37:56 - INFO - __main__ - Step 24797: {'lr': 0.0004712979532839656, 'samples': 4761024, 'steps': 24796, 'loss/train': 1.271109700202942} 08/30/2021 17:37:58 - INFO - __main__ - Step 24798: {'lr': 0.00047129548439739225, 'samples': 4761216, 'steps': 24797, 'loss/train': 1.5104845762252808} 08/30/2021 17:37:58 - INFO - __main__ - Step 24799: {'lr': 0.0004712930154111065, 'samples': 4761408, 'steps': 24798, 'loss/train': 1.9404298067092896} 08/30/2021 17:37:59 - INFO - __main__ - Step 24800: {'lr': 0.00047129054632510947, 'samples': 4761600, 'steps': 24799, 'loss/train': 1.883735179901123} 08/30/2021 17:37:59 - INFO - __main__ - Step 24801: {'lr': 0.00047128807713940244, 'samples': 4761792, 'steps': 24800, 'loss/train': 1.948649287223816} 08/30/2021 17:38:00 - INFO - __main__ - Step 24802: {'lr': 0.00047128560785398633, 'samples': 4761984, 'steps': 24801, 'loss/train': 1.259140968322754} 08/30/2021 17:38:01 - INFO - __main__ - Step 24803: {'lr': 0.0004712831384688624, 'samples': 4762176, 'steps': 24802, 'loss/train': 1.251665472984314} 08/30/2021 17:38:01 - INFO - __main__ - Step 24804: {'lr': 0.00047128066898403166, 'samples': 4762368, 'steps': 24803, 'loss/train': 1.5575450658798218} 08/30/2021 17:38:02 - INFO - __main__ - Step 24805: {'lr': 0.00047127819939949534, 'samples': 4762560, 'steps': 24804, 'loss/train': 1.2906776666641235} 08/30/2021 17:38:02 - INFO - __main__ - Step 24806: {'lr': 0.00047127572971525437, 'samples': 4762752, 'steps': 24805, 'loss/train': 1.4693801403045654} 08/30/2021 17:38:02 - INFO - __main__ - Step 24807: {'lr': 0.00047127325993131006, 'samples': 4762944, 'steps': 24806, 'loss/train': 1.3121047019958496} 08/30/2021 17:38:04 - INFO - __main__ - Step 24808: {'lr': 0.0004712707900476634, 'samples': 4763136, 'steps': 24807, 'loss/train': 1.6688311100006104} 08/30/2021 17:38:04 - INFO - __main__ - Step 24809: {'lr': 0.00047126832006431555, 'samples': 4763328, 'steps': 24808, 'loss/train': 1.9442788362503052} 08/30/2021 17:38:05 - INFO - __main__ - Step 24810: {'lr': 0.00047126584998126756, 'samples': 4763520, 'steps': 24809, 'loss/train': 1.3375706672668457} 08/30/2021 17:38:05 - INFO - __main__ - Step 24811: {'lr': 0.0004712633797985206, 'samples': 4763712, 'steps': 24810, 'loss/train': 1.653232216835022} 08/30/2021 17:38:05 - INFO - __main__ - Step 24812: {'lr': 0.0004712609095160758, 'samples': 4763904, 'steps': 24811, 'loss/train': 1.692129373550415} 08/30/2021 17:38:07 - INFO - __main__ - Step 24813: {'lr': 0.0004712584391339343, 'samples': 4764096, 'steps': 24812, 'loss/train': 1.700097680091858} 08/30/2021 17:38:07 - INFO - __main__ - Step 24814: {'lr': 0.0004712559686520971, 'samples': 4764288, 'steps': 24813, 'loss/train': 1.7158104181289673} 08/30/2021 17:38:08 - INFO - __main__ - Step 24815: {'lr': 0.0004712534980705654, 'samples': 4764480, 'steps': 24814, 'loss/train': 2.4246253967285156} 08/30/2021 17:38:08 - INFO - __main__ - Step 24816: {'lr': 0.0004712510273893402, 'samples': 4764672, 'steps': 24815, 'loss/train': 1.4810903072357178} 08/30/2021 17:38:08 - INFO - __main__ - Step 24817: {'lr': 0.00047124855660842283, 'samples': 4764864, 'steps': 24816, 'loss/train': 0.9266908168792725} 08/30/2021 17:38:10 - INFO - __main__ - Step 24818: {'lr': 0.00047124608572781426, 'samples': 4765056, 'steps': 24817, 'loss/train': 1.8865001201629639} 08/30/2021 17:38:10 - INFO - __main__ - Step 24819: {'lr': 0.0004712436147475155, 'samples': 4765248, 'steps': 24818, 'loss/train': 1.4311137199401855} 08/30/2021 17:38:11 - INFO - __main__ - Step 24820: {'lr': 0.0004712411436675279, 'samples': 4765440, 'steps': 24819, 'loss/train': 0.7995826601982117} 08/30/2021 17:38:11 - INFO - __main__ - Step 24821: {'lr': 0.0004712386724878524, 'samples': 4765632, 'steps': 24820, 'loss/train': 0.9235925674438477} 08/30/2021 17:38:11 - INFO - __main__ - Step 24822: {'lr': 0.0004712362012084902, 'samples': 4765824, 'steps': 24821, 'loss/train': 1.8593734502792358} 08/30/2021 17:38:13 - INFO - __main__ - Step 24823: {'lr': 0.00047123372982944237, 'samples': 4766016, 'steps': 24822, 'loss/train': 1.6541578769683838} 08/30/2021 17:38:14 - INFO - __main__ - Step 24824: {'lr': 0.00047123125835071004, 'samples': 4766208, 'steps': 24823, 'loss/train': 1.3145304918289185} 08/30/2021 17:38:14 - INFO - __main__ - Step 24825: {'lr': 0.00047122878677229426, 'samples': 4766400, 'steps': 24824, 'loss/train': 2.6243112087249756} 08/30/2021 17:38:15 - INFO - __main__ - Step 24826: {'lr': 0.0004712263150941962, 'samples': 4766592, 'steps': 24825, 'loss/train': 1.3207083940505981} 08/30/2021 17:38:15 - INFO - __main__ - Step 24827: {'lr': 0.0004712238433164171, 'samples': 4766784, 'steps': 24826, 'loss/train': 0.24122515320777893} 08/30/2021 17:38:15 - INFO - __main__ - Step 24828: {'lr': 0.00047122137143895785, 'samples': 4766976, 'steps': 24827, 'loss/train': 2.5779922008514404} 08/30/2021 17:38:18 - INFO - __main__ - Step 24829: {'lr': 0.0004712188994618197, 'samples': 4767168, 'steps': 24828, 'loss/train': 1.5170645713806152} 08/30/2021 17:38:18 - INFO - __main__ - Step 24830: {'lr': 0.0004712164273850037, 'samples': 4767360, 'steps': 24829, 'loss/train': 1.8882523775100708} 08/30/2021 17:38:19 - INFO - __main__ - Step 24831: {'lr': 0.00047121395520851103, 'samples': 4767552, 'steps': 24830, 'loss/train': 1.510980248451233} 08/30/2021 17:38:19 - INFO - __main__ - Step 24832: {'lr': 0.00047121148293234274, 'samples': 4767744, 'steps': 24831, 'loss/train': 1.9384924173355103} 08/30/2021 17:38:19 - INFO - __main__ - Step 24833: {'lr': 0.00047120901055649995, 'samples': 4767936, 'steps': 24832, 'loss/train': 1.7600089311599731} 08/30/2021 17:38:20 - INFO - __main__ - Step 24834: {'lr': 0.0004712065380809838, 'samples': 4768128, 'steps': 24833, 'loss/train': 1.4324185848236084} 08/30/2021 17:38:21 - INFO - __main__ - Step 24835: {'lr': 0.0004712040655057954, 'samples': 4768320, 'steps': 24834, 'loss/train': 0.06933899223804474} 08/30/2021 17:38:22 - INFO - __main__ - Step 24836: {'lr': 0.0004712015928309359, 'samples': 4768512, 'steps': 24835, 'loss/train': 1.336204171180725} 08/30/2021 17:38:22 - INFO - __main__ - Step 24837: {'lr': 0.0004711991200564064, 'samples': 4768704, 'steps': 24836, 'loss/train': 2.059105157852173} 08/30/2021 17:38:22 - INFO - __main__ - Step 24838: {'lr': 0.0004711966471822079, 'samples': 4768896, 'steps': 24837, 'loss/train': 1.3179295063018799} 08/30/2021 17:38:23 - INFO - __main__ - Step 24839: {'lr': 0.00047119417420834163, 'samples': 4769088, 'steps': 24838, 'loss/train': 1.1504651308059692} 08/30/2021 17:38:24 - INFO - __main__ - Step 24840: {'lr': 0.00047119170113480867, 'samples': 4769280, 'steps': 24839, 'loss/train': 2.1416375637054443} 08/30/2021 17:38:25 - INFO - __main__ - Step 24841: {'lr': 0.00047118922796161026, 'samples': 4769472, 'steps': 24840, 'loss/train': 1.8710228204727173} 08/30/2021 17:38:25 - INFO - __main__ - Step 24842: {'lr': 0.00047118675468874727, 'samples': 4769664, 'steps': 24841, 'loss/train': 1.23186194896698} 08/30/2021 17:38:25 - INFO - __main__ - Step 24843: {'lr': 0.00047118428131622095, 'samples': 4769856, 'steps': 24842, 'loss/train': 1.758584976196289} 08/30/2021 17:38:26 - INFO - __main__ - Step 24844: {'lr': 0.00047118180784403243, 'samples': 4770048, 'steps': 24843, 'loss/train': 2.0206093788146973} 08/30/2021 17:38:26 - INFO - __main__ - Step 24845: {'lr': 0.0004711793342721828, 'samples': 4770240, 'steps': 24844, 'loss/train': 1.0911056995391846} 08/30/2021 17:38:28 - INFO - __main__ - Step 24846: {'lr': 0.00047117686060067315, 'samples': 4770432, 'steps': 24845, 'loss/train': 2.045301675796509} 08/30/2021 17:38:28 - INFO - __main__ - Step 24847: {'lr': 0.00047117438682950467, 'samples': 4770624, 'steps': 24846, 'loss/train': 0.5238175988197327} 08/30/2021 17:38:29 - INFO - __main__ - Step 24848: {'lr': 0.0004711719129586784, 'samples': 4770816, 'steps': 24847, 'loss/train': 1.743025302886963} 08/30/2021 17:38:29 - INFO - __main__ - Step 24849: {'lr': 0.0004711694389881955, 'samples': 4771008, 'steps': 24848, 'loss/train': 1.199263334274292} 08/30/2021 17:38:29 - INFO - __main__ - Step 24850: {'lr': 0.000471166964918057, 'samples': 4771200, 'steps': 24849, 'loss/train': 1.631496787071228} 08/30/2021 17:38:31 - INFO - __main__ - Step 24851: {'lr': 0.0004711644907482641, 'samples': 4771392, 'steps': 24850, 'loss/train': 1.8362065553665161} 08/30/2021 17:38:31 - INFO - __main__ - Step 24852: {'lr': 0.00047116201647881794, 'samples': 4771584, 'steps': 24851, 'loss/train': 1.4992926120758057} 08/30/2021 17:38:32 - INFO - __main__ - Step 24853: {'lr': 0.00047115954210971955, 'samples': 4771776, 'steps': 24852, 'loss/train': 1.4682295322418213} 08/30/2021 17:38:32 - INFO - __main__ - Step 24854: {'lr': 0.0004711570676409701, 'samples': 4771968, 'steps': 24853, 'loss/train': 1.775540828704834} 08/30/2021 17:38:32 - INFO - __main__ - Step 24855: {'lr': 0.0004711545930725707, 'samples': 4772160, 'steps': 24854, 'loss/train': 1.4458611011505127} 08/30/2021 17:38:34 - INFO - __main__ - Step 24856: {'lr': 0.0004711521184045224, 'samples': 4772352, 'steps': 24855, 'loss/train': 1.4048656225204468} 08/30/2021 17:38:34 - INFO - __main__ - Step 24857: {'lr': 0.0004711496436368264, 'samples': 4772544, 'steps': 24856, 'loss/train': 2.022448778152466} 08/30/2021 17:38:35 - INFO - __main__ - Step 24858: {'lr': 0.00047114716876948384, 'samples': 4772736, 'steps': 24857, 'loss/train': 1.2480905055999756} 08/30/2021 17:38:35 - INFO - __main__ - Step 24859: {'lr': 0.0004711446938024957, 'samples': 4772928, 'steps': 24858, 'loss/train': 0.9936212301254272} 08/30/2021 17:38:35 - INFO - __main__ - Step 24860: {'lr': 0.00047114221873586316, 'samples': 4773120, 'steps': 24859, 'loss/train': 1.71892249584198} 08/30/2021 17:38:37 - INFO - __main__ - Step 24861: {'lr': 0.00047113974356958744, 'samples': 4773312, 'steps': 24860, 'loss/train': 1.7533053159713745} 08/30/2021 17:38:37 - INFO - __main__ - Step 24862: {'lr': 0.0004711372683036695, 'samples': 4773504, 'steps': 24861, 'loss/train': 2.017672538757324} 08/30/2021 17:38:38 - INFO - __main__ - Step 24863: {'lr': 0.0004711347929381105, 'samples': 4773696, 'steps': 24862, 'loss/train': 1.5883532762527466} 08/30/2021 17:38:38 - INFO - __main__ - Step 24864: {'lr': 0.00047113231747291165, 'samples': 4773888, 'steps': 24863, 'loss/train': 1.5586352348327637} 08/30/2021 17:38:38 - INFO - __main__ - Step 24865: {'lr': 0.0004711298419080739, 'samples': 4774080, 'steps': 24864, 'loss/train': 1.341946005821228} 08/30/2021 17:38:40 - INFO - __main__ - Step 24866: {'lr': 0.00047112736624359855, 'samples': 4774272, 'steps': 24865, 'loss/train': 1.8073546886444092} 08/30/2021 17:38:40 - INFO - __main__ - Step 24867: {'lr': 0.00047112489047948655, 'samples': 4774464, 'steps': 24866, 'loss/train': 1.7532434463500977} 08/30/2021 17:38:41 - INFO - __main__ - Step 24868: {'lr': 0.00047112241461573913, 'samples': 4774656, 'steps': 24867, 'loss/train': 1.4599817991256714} 08/30/2021 17:38:41 - INFO - __main__ - Step 24869: {'lr': 0.0004711199386523573, 'samples': 4774848, 'steps': 24868, 'loss/train': 1.343593716621399} 08/30/2021 17:38:41 - INFO - __main__ - Step 24870: {'lr': 0.0004711174625893423, 'samples': 4775040, 'steps': 24869, 'loss/train': 1.7296785116195679} 08/30/2021 17:38:43 - INFO - __main__ - Step 24871: {'lr': 0.00047111498642669517, 'samples': 4775232, 'steps': 24870, 'loss/train': 1.6996002197265625} 08/30/2021 17:38:43 - INFO - __main__ - Step 24872: {'lr': 0.00047111251016441704, 'samples': 4775424, 'steps': 24871, 'loss/train': 2.030810832977295} 08/30/2021 17:38:44 - INFO - __main__ - Step 24873: {'lr': 0.0004711100338025089, 'samples': 4775616, 'steps': 24872, 'loss/train': 0.7744000554084778} 08/30/2021 17:38:44 - INFO - __main__ - Step 24874: {'lr': 0.00047110755734097216, 'samples': 4775808, 'steps': 24873, 'loss/train': 1.6111209392547607} 08/30/2021 17:38:44 - INFO - __main__ - Step 24875: {'lr': 0.00047110508077980774, 'samples': 4776000, 'steps': 24874, 'loss/train': 1.3004311323165894} 08/30/2021 17:38:46 - INFO - __main__ - Step 24876: {'lr': 0.00047110260411901674, 'samples': 4776192, 'steps': 24875, 'loss/train': 1.915921926498413} 08/30/2021 17:38:46 - INFO - __main__ - Step 24877: {'lr': 0.0004711001273586003, 'samples': 4776384, 'steps': 24876, 'loss/train': 1.6893506050109863} 08/30/2021 17:38:47 - INFO - __main__ - Step 24878: {'lr': 0.0004710976504985596, 'samples': 4776576, 'steps': 24877, 'loss/train': 2.1351051330566406} 08/30/2021 17:38:47 - INFO - __main__ - Step 24879: {'lr': 0.00047109517353889575, 'samples': 4776768, 'steps': 24878, 'loss/train': 1.200385332107544} 08/30/2021 17:38:47 - INFO - __main__ - Step 24880: {'lr': 0.0004710926964796097, 'samples': 4776960, 'steps': 24879, 'loss/train': 1.736669898033142} 08/30/2021 17:38:50 - INFO - __main__ - Step 24881: {'lr': 0.00047109021932070284, 'samples': 4777152, 'steps': 24880, 'loss/train': 1.8226144313812256} 08/30/2021 17:38:50 - INFO - __main__ - Step 24882: {'lr': 0.00047108774206217605, 'samples': 4777344, 'steps': 24881, 'loss/train': 1.485541582107544} 08/30/2021 17:38:50 - INFO - __main__ - Step 24883: {'lr': 0.00047108526470403055, 'samples': 4777536, 'steps': 24882, 'loss/train': 1.3955153226852417} 08/30/2021 17:38:51 - INFO - __main__ - Step 24884: {'lr': 0.0004710827872462674, 'samples': 4777728, 'steps': 24883, 'loss/train': 1.0091819763183594} 08/30/2021 17:38:51 - INFO - __main__ - Step 24885: {'lr': 0.00047108030968888784, 'samples': 4777920, 'steps': 24884, 'loss/train': 1.0975103378295898} 08/30/2021 17:38:51 - INFO - __main__ - Step 24886: {'lr': 0.00047107783203189285, 'samples': 4778112, 'steps': 24885, 'loss/train': 2.1459314823150635} 08/30/2021 17:38:53 - INFO - __main__ - Step 24887: {'lr': 0.0004710753542752836, 'samples': 4778304, 'steps': 24886, 'loss/train': 1.6431077718734741} 08/30/2021 17:38:53 - INFO - __main__ - Step 24888: {'lr': 0.0004710728764190612, 'samples': 4778496, 'steps': 24887, 'loss/train': 1.7486584186553955} 08/30/2021 17:38:54 - INFO - __main__ - Step 24889: {'lr': 0.0004710703984632268, 'samples': 4778688, 'steps': 24888, 'loss/train': 1.5060125589370728} 08/30/2021 17:38:54 - INFO - __main__ - Step 24890: {'lr': 0.0004710679204077815, 'samples': 4778880, 'steps': 24889, 'loss/train': 1.759198546409607} 08/30/2021 17:38:55 - INFO - __main__ - Step 24891: {'lr': 0.0004710654422527264, 'samples': 4779072, 'steps': 24890, 'loss/train': 1.566688060760498} 08/30/2021 17:38:56 - INFO - __main__ - Step 24892: {'lr': 0.0004710629639980626, 'samples': 4779264, 'steps': 24891, 'loss/train': 1.099583387374878} 08/30/2021 17:38:57 - INFO - __main__ - Step 24893: {'lr': 0.0004710604856437912, 'samples': 4779456, 'steps': 24892, 'loss/train': 1.08847975730896} 08/30/2021 17:38:57 - INFO - __main__ - Step 24894: {'lr': 0.00047105800718991343, 'samples': 4779648, 'steps': 24893, 'loss/train': 1.5162407159805298} 08/30/2021 17:38:57 - INFO - __main__ - Step 24895: {'lr': 0.0004710555286364303, 'samples': 4779840, 'steps': 24894, 'loss/train': 1.71968412399292} 08/30/2021 17:38:58 - INFO - __main__ - Step 24896: {'lr': 0.000471053049983343, 'samples': 4780032, 'steps': 24895, 'loss/train': 1.7614107131958008} 08/30/2021 17:39:00 - INFO - __main__ - Step 24897: {'lr': 0.0004710505712306526, 'samples': 4780224, 'steps': 24896, 'loss/train': 0.6114704608917236} 08/30/2021 17:39:00 - INFO - __main__ - Step 24898: {'lr': 0.00047104809237836023, 'samples': 4780416, 'steps': 24897, 'loss/train': 1.1677278280258179} 08/30/2021 17:39:00 - INFO - __main__ - Step 24899: {'lr': 0.0004710456134264669, 'samples': 4780608, 'steps': 24898, 'loss/train': 2.2039995193481445} 08/30/2021 17:39:01 - INFO - __main__ - Step 24900: {'lr': 0.0004710431343749739, 'samples': 4780800, 'steps': 24899, 'loss/train': 1.7204174995422363} 08/30/2021 17:39:01 - INFO - __main__ - Step 24901: {'lr': 0.0004710406552238823, 'samples': 4780992, 'steps': 24900, 'loss/train': 1.0888166427612305} 08/30/2021 17:39:02 - INFO - __main__ - Step 24902: {'lr': 0.0004710381759731932, 'samples': 4781184, 'steps': 24901, 'loss/train': 1.6266021728515625} 08/30/2021 17:39:03 - INFO - __main__ - Step 24903: {'lr': 0.0004710356966229077, 'samples': 4781376, 'steps': 24902, 'loss/train': 1.5151076316833496} 08/30/2021 17:39:03 - INFO - __main__ - Step 24904: {'lr': 0.00047103321717302684, 'samples': 4781568, 'steps': 24903, 'loss/train': 0.9552773833274841} 08/30/2021 17:39:04 - INFO - __main__ - Step 24905: {'lr': 0.00047103073762355186, 'samples': 4781760, 'steps': 24904, 'loss/train': 1.417817234992981} 08/30/2021 17:39:04 - INFO - __main__ - Step 24906: {'lr': 0.0004710282579744839, 'samples': 4781952, 'steps': 24905, 'loss/train': 1.8440959453582764} 08/30/2021 17:39:06 - INFO - __main__ - Step 24907: {'lr': 0.000471025778225824, 'samples': 4782144, 'steps': 24906, 'loss/train': 1.4775582551956177} 08/30/2021 17:39:06 - INFO - __main__ - Step 24908: {'lr': 0.0004710232983775733, 'samples': 4782336, 'steps': 24907, 'loss/train': 1.6019210815429688} 08/30/2021 17:39:06 - INFO - __main__ - Step 24909: {'lr': 0.0004710208184297329, 'samples': 4782528, 'steps': 24908, 'loss/train': 0.8739994168281555} 08/30/2021 17:39:07 - INFO - __main__ - Step 24910: {'lr': 0.0004710183383823039, 'samples': 4782720, 'steps': 24909, 'loss/train': 1.1203923225402832} 08/30/2021 17:39:07 - INFO - __main__ - Step 24911: {'lr': 0.00047101585823528745, 'samples': 4782912, 'steps': 24910, 'loss/train': 1.5857607126235962} 08/30/2021 17:39:08 - INFO - __main__ - Step 24912: {'lr': 0.0004710133779886847, 'samples': 4783104, 'steps': 24911, 'loss/train': 1.714115023612976} 08/30/2021 17:39:09 - INFO - __main__ - Step 24913: {'lr': 0.00047101089764249674, 'samples': 4783296, 'steps': 24912, 'loss/train': 1.8911681175231934} 08/30/2021 17:39:10 - INFO - __main__ - Step 24914: {'lr': 0.0004710084171967246, 'samples': 4783488, 'steps': 24913, 'loss/train': 2.1133487224578857} 08/30/2021 17:39:10 - INFO - __main__ - Step 24915: {'lr': 0.00047100593665136946, 'samples': 4783680, 'steps': 24914, 'loss/train': 2.4652905464172363} 08/30/2021 17:39:10 - INFO - __main__ - Step 24916: {'lr': 0.0004710034560064326, 'samples': 4783872, 'steps': 24915, 'loss/train': 1.652906060218811} 08/30/2021 17:39:11 - INFO - __main__ - Step 24917: {'lr': 0.00047100097526191486, 'samples': 4784064, 'steps': 24916, 'loss/train': 1.570051908493042} 08/30/2021 17:39:12 - INFO - __main__ - Step 24918: {'lr': 0.0004709984944178176, 'samples': 4784256, 'steps': 24917, 'loss/train': 0.9035937190055847} 08/30/2021 17:39:12 - INFO - __main__ - Step 24919: {'lr': 0.0004709960134741418, 'samples': 4784448, 'steps': 24918, 'loss/train': 1.7699795961380005} 08/30/2021 17:39:13 - INFO - __main__ - Step 24920: {'lr': 0.00047099353243088856, 'samples': 4784640, 'steps': 24919, 'loss/train': 1.5828999280929565} 08/30/2021 17:39:13 - INFO - __main__ - Step 24921: {'lr': 0.00047099105128805906, 'samples': 4784832, 'steps': 24920, 'loss/train': 1.346340537071228} 08/30/2021 17:39:14 - INFO - __main__ - Step 24922: {'lr': 0.00047098857004565444, 'samples': 4785024, 'steps': 24921, 'loss/train': 1.6656728982925415} 08/30/2021 17:39:15 - INFO - __main__ - Step 24923: {'lr': 0.00047098608870367576, 'samples': 4785216, 'steps': 24922, 'loss/train': 1.6750472784042358} 08/30/2021 17:39:15 - INFO - __main__ - Step 24924: {'lr': 0.00047098360726212406, 'samples': 4785408, 'steps': 24923, 'loss/train': 1.434363603591919} 08/30/2021 17:39:16 - INFO - __main__ - Step 24925: {'lr': 0.0004709811257210007, 'samples': 4785600, 'steps': 24924, 'loss/train': 1.6387243270874023} 08/30/2021 17:39:16 - INFO - __main__ - Step 24926: {'lr': 0.0004709786440803066, 'samples': 4785792, 'steps': 24925, 'loss/train': 1.2350859642028809} 08/30/2021 17:39:16 - INFO - __main__ - Step 24927: {'lr': 0.00047097616234004295, 'samples': 4785984, 'steps': 24926, 'loss/train': 1.7146450281143188} 08/30/2021 17:39:18 - INFO - __main__ - Step 24928: {'lr': 0.00047097368050021083, 'samples': 4786176, 'steps': 24927, 'loss/train': 1.990890383720398} 08/30/2021 17:39:18 - INFO - __main__ - Step 24929: {'lr': 0.0004709711985608114, 'samples': 4786368, 'steps': 24928, 'loss/train': 1.1382001638412476} 08/30/2021 17:39:19 - INFO - __main__ - Step 24930: {'lr': 0.0004709687165218457, 'samples': 4786560, 'steps': 24929, 'loss/train': 1.7983508110046387} 08/30/2021 17:39:19 - INFO - __main__ - Step 24931: {'lr': 0.00047096623438331497, 'samples': 4786752, 'steps': 24930, 'loss/train': 1.7613146305084229} 08/30/2021 17:39:19 - INFO - __main__ - Step 24932: {'lr': 0.00047096375214522026, 'samples': 4786944, 'steps': 24931, 'loss/train': 1.2897993326187134} 08/30/2021 17:39:21 - INFO - __main__ - Step 24933: {'lr': 0.0004709612698075627, 'samples': 4787136, 'steps': 24932, 'loss/train': 1.6820757389068604} 08/30/2021 17:39:21 - INFO - __main__ - Step 24934: {'lr': 0.00047095878737034335, 'samples': 4787328, 'steps': 24933, 'loss/train': 1.4690594673156738} 08/30/2021 17:39:22 - INFO - __main__ - Step 24935: {'lr': 0.00047095630483356336, 'samples': 4787520, 'steps': 24934, 'loss/train': 1.6006884574890137} 08/30/2021 17:39:22 - INFO - __main__ - Step 24936: {'lr': 0.00047095382219722396, 'samples': 4787712, 'steps': 24935, 'loss/train': 2.2609922885894775} 08/30/2021 17:39:22 - INFO - __main__ - Step 24937: {'lr': 0.0004709513394613261, 'samples': 4787904, 'steps': 24936, 'loss/train': 0.47464871406555176} 08/30/2021 17:39:25 - INFO - __main__ - Step 24938: {'lr': 0.00047094885662587104, 'samples': 4788096, 'steps': 24937, 'loss/train': 1.642889142036438} 08/30/2021 17:39:25 - INFO - __main__ - Step 24939: {'lr': 0.0004709463736908598, 'samples': 4788288, 'steps': 24938, 'loss/train': 1.1965306997299194} 08/30/2021 17:39:26 - INFO - __main__ - Step 24940: {'lr': 0.0004709438906562935, 'samples': 4788480, 'steps': 24939, 'loss/train': 1.2444170713424683} 08/30/2021 17:39:26 - INFO - __main__ - Step 24941: {'lr': 0.0004709414075221734, 'samples': 4788672, 'steps': 24940, 'loss/train': 1.7122747898101807} 08/30/2021 17:39:26 - INFO - __main__ - Step 24942: {'lr': 0.0004709389242885004, 'samples': 4788864, 'steps': 24941, 'loss/train': 1.6825224161148071} 08/30/2021 17:39:27 - INFO - __main__ - Step 24943: {'lr': 0.00047093644095527574, 'samples': 4789056, 'steps': 24942, 'loss/train': 1.1214473247528076} 08/30/2021 17:39:28 - INFO - __main__ - Step 24944: {'lr': 0.00047093395752250056, 'samples': 4789248, 'steps': 24943, 'loss/train': 4.759702205657959} 08/30/2021 17:39:28 - INFO - __main__ - Step 24945: {'lr': 0.000470931473990176, 'samples': 4789440, 'steps': 24944, 'loss/train': 1.3784898519515991} 08/30/2021 17:39:29 - INFO - __main__ - Step 24946: {'lr': 0.00047092899035830303, 'samples': 4789632, 'steps': 24945, 'loss/train': 1.405518651008606} 08/30/2021 17:39:29 - INFO - __main__ - Step 24947: {'lr': 0.00047092650662688295, 'samples': 4789824, 'steps': 24946, 'loss/train': 2.6035568714141846} 08/30/2021 17:39:30 - INFO - __main__ - Step 24948: {'lr': 0.00047092402279591674, 'samples': 4790016, 'steps': 24947, 'loss/train': 1.7906999588012695} 08/30/2021 17:39:31 - INFO - __main__ - Step 24949: {'lr': 0.00047092153886540554, 'samples': 4790208, 'steps': 24948, 'loss/train': 1.128928303718567} 08/30/2021 17:39:32 - INFO - __main__ - Step 24950: {'lr': 0.0004709190548353506, 'samples': 4790400, 'steps': 24949, 'loss/train': 1.5134373903274536} 08/30/2021 17:39:32 - INFO - __main__ - Step 24951: {'lr': 0.0004709165707057529, 'samples': 4790592, 'steps': 24950, 'loss/train': 0.7753484845161438} 08/30/2021 17:39:33 - INFO - __main__ - Step 24952: {'lr': 0.0004709140864766136, 'samples': 4790784, 'steps': 24951, 'loss/train': 1.4935215711593628} 08/30/2021 17:39:33 - INFO - __main__ - Step 24953: {'lr': 0.0004709116021479338, 'samples': 4790976, 'steps': 24952, 'loss/train': 1.3633826971054077} 08/30/2021 17:39:34 - INFO - __main__ - Step 24954: {'lr': 0.00047090911771971466, 'samples': 4791168, 'steps': 24953, 'loss/train': 1.789441466331482} 08/30/2021 17:39:35 - INFO - __main__ - Step 24955: {'lr': 0.0004709066331919573, 'samples': 4791360, 'steps': 24954, 'loss/train': 0.17537353932857513} 08/30/2021 17:39:36 - INFO - __main__ - Step 24956: {'lr': 0.0004709041485646628, 'samples': 4791552, 'steps': 24955, 'loss/train': 0.8306893110275269} 08/30/2021 17:39:36 - INFO - __main__ - Step 24957: {'lr': 0.0004709016638378323, 'samples': 4791744, 'steps': 24956, 'loss/train': 1.2651863098144531} 08/30/2021 17:39:36 - INFO - __main__ - Step 24958: {'lr': 0.00047089917901146694, 'samples': 4791936, 'steps': 24957, 'loss/train': 1.9289519786834717} 08/30/2021 17:39:37 - INFO - __main__ - Step 24959: {'lr': 0.0004708966940855678, 'samples': 4792128, 'steps': 24958, 'loss/train': 1.972502589225769} 08/30/2021 17:39:38 - INFO - __main__ - Step 24960: {'lr': 0.00047089420906013603, 'samples': 4792320, 'steps': 24959, 'loss/train': 1.3213255405426025} 08/30/2021 17:39:38 - INFO - __main__ - Step 24961: {'lr': 0.0004708917239351727, 'samples': 4792512, 'steps': 24960, 'loss/train': 2.070970058441162} 08/30/2021 17:39:39 - INFO - __main__ - Step 24962: {'lr': 0.000470889238710679, 'samples': 4792704, 'steps': 24961, 'loss/train': 1.6014602184295654} 08/30/2021 17:39:39 - INFO - __main__ - Step 24963: {'lr': 0.00047088675338665596, 'samples': 4792896, 'steps': 24962, 'loss/train': 1.116607666015625} 08/30/2021 17:39:40 - INFO - __main__ - Step 24964: {'lr': 0.00047088426796310486, 'samples': 4793088, 'steps': 24963, 'loss/train': 1.4058283567428589} 08/30/2021 17:39:41 - INFO - __main__ - Step 24965: {'lr': 0.00047088178244002665, 'samples': 4793280, 'steps': 24964, 'loss/train': 1.330124855041504} 08/30/2021 17:39:41 - INFO - __main__ - Step 24966: {'lr': 0.00047087929681742253, 'samples': 4793472, 'steps': 24965, 'loss/train': 1.7067776918411255} 08/30/2021 17:39:42 - INFO - __main__ - Step 24967: {'lr': 0.00047087681109529364, 'samples': 4793664, 'steps': 24966, 'loss/train': 1.6116641759872437} 08/30/2021 17:39:42 - INFO - __main__ - Step 24968: {'lr': 0.00047087432527364106, 'samples': 4793856, 'steps': 24967, 'loss/train': 1.295219898223877} 08/30/2021 17:39:43 - INFO - __main__ - Step 24969: {'lr': 0.0004708718393524659, 'samples': 4794048, 'steps': 24968, 'loss/train': 1.5851590633392334} 08/30/2021 17:39:44 - INFO - __main__ - Step 24970: {'lr': 0.0004708693533317693, 'samples': 4794240, 'steps': 24969, 'loss/train': 0.9088825583457947} 08/30/2021 17:39:44 - INFO - __main__ - Step 24971: {'lr': 0.00047086686721155237, 'samples': 4794432, 'steps': 24970, 'loss/train': 1.8053698539733887} 08/30/2021 17:39:45 - INFO - __main__ - Step 24972: {'lr': 0.00047086438099181615, 'samples': 4794624, 'steps': 24971, 'loss/train': 1.4603807926177979} 08/30/2021 17:39:45 - INFO - __main__ - Step 24973: {'lr': 0.00047086189467256194, 'samples': 4794816, 'steps': 24972, 'loss/train': 1.676476001739502} 08/30/2021 17:39:46 - INFO - __main__ - Step 24974: {'lr': 0.0004708594082537908, 'samples': 4795008, 'steps': 24973, 'loss/train': 1.2030974626541138} 08/30/2021 17:39:46 - INFO - __main__ - Step 24975: {'lr': 0.00047085692173550375, 'samples': 4795200, 'steps': 24974, 'loss/train': 1.249074101448059} 08/30/2021 17:39:47 - INFO - __main__ - Step 24976: {'lr': 0.00047085443511770206, 'samples': 4795392, 'steps': 24975, 'loss/train': 1.3432697057724} 08/30/2021 17:39:48 - INFO - __main__ - Step 24977: {'lr': 0.0004708519484003867, 'samples': 4795584, 'steps': 24976, 'loss/train': 1.0533641576766968} 08/30/2021 17:39:48 - INFO - __main__ - Step 24978: {'lr': 0.0004708494615835589, 'samples': 4795776, 'steps': 24977, 'loss/train': 1.8369439840316772} 08/30/2021 17:39:49 - INFO - __main__ - Step 24979: {'lr': 0.00047084697466721973, 'samples': 4795968, 'steps': 24978, 'loss/train': 1.2232842445373535} 08/30/2021 17:39:49 - INFO - __main__ - Step 24980: {'lr': 0.0004708444876513703, 'samples': 4796160, 'steps': 24979, 'loss/train': 1.6410752534866333} 08/30/2021 17:39:50 - INFO - __main__ - Step 24981: {'lr': 0.0004708420005360118, 'samples': 4796352, 'steps': 24980, 'loss/train': 0.9991140365600586} 08/30/2021 17:39:51 - INFO - __main__ - Step 24982: {'lr': 0.0004708395133211452, 'samples': 4796544, 'steps': 24981, 'loss/train': 1.582206130027771} 08/30/2021 17:39:51 - INFO - __main__ - Step 24983: {'lr': 0.0004708370260067718, 'samples': 4796736, 'steps': 24982, 'loss/train': 1.5868440866470337} 08/30/2021 17:39:51 - INFO - __main__ - Step 24984: {'lr': 0.00047083453859289267, 'samples': 4796928, 'steps': 24983, 'loss/train': 1.836672067642212} 08/30/2021 17:39:52 - INFO - __main__ - Step 24985: {'lr': 0.00047083205107950886, 'samples': 4797120, 'steps': 24984, 'loss/train': 1.5847891569137573} 08/30/2021 17:39:53 - INFO - __main__ - Step 24986: {'lr': 0.00047082956346662153, 'samples': 4797312, 'steps': 24985, 'loss/train': 0.21408843994140625} 08/30/2021 17:39:54 - INFO - __main__ - Step 24987: {'lr': 0.00047082707575423177, 'samples': 4797504, 'steps': 24986, 'loss/train': 1.650818943977356} 08/30/2021 17:39:54 - INFO - __main__ - Step 24988: {'lr': 0.00047082458794234087, 'samples': 4797696, 'steps': 24987, 'loss/train': 1.6033084392547607} 08/30/2021 17:39:54 - INFO - __main__ - Step 24989: {'lr': 0.0004708221000309497, 'samples': 4797888, 'steps': 24988, 'loss/train': 1.9122878313064575} 08/30/2021 17:39:55 - INFO - __main__ - Step 24990: {'lr': 0.0004708196120200595, 'samples': 4798080, 'steps': 24989, 'loss/train': 1.5654484033584595} 08/30/2021 17:39:56 - INFO - __main__ - Step 24991: {'lr': 0.0004708171239096715, 'samples': 4798272, 'steps': 24990, 'loss/train': 1.3105615377426147} 08/30/2021 17:39:57 - INFO - __main__ - Step 24992: {'lr': 0.00047081463569978655, 'samples': 4798464, 'steps': 24991, 'loss/train': 1.3675084114074707} 08/30/2021 17:39:57 - INFO - __main__ - Step 24993: {'lr': 0.00047081214739040606, 'samples': 4798656, 'steps': 24992, 'loss/train': 1.4760974645614624} 08/30/2021 17:39:58 - INFO - __main__ - Step 24994: {'lr': 0.000470809658981531, 'samples': 4798848, 'steps': 24993, 'loss/train': 2.2376883029937744} 08/30/2021 17:39:58 - INFO - __main__ - Step 24995: {'lr': 0.00047080717047316245, 'samples': 4799040, 'steps': 24994, 'loss/train': 1.4054299592971802} 08/30/2021 17:39:59 - INFO - __main__ - Step 24996: {'lr': 0.0004708046818653017, 'samples': 4799232, 'steps': 24995, 'loss/train': 1.6642056703567505} 08/30/2021 17:40:00 - INFO - __main__ - Step 24997: {'lr': 0.0004708021931579497, 'samples': 4799424, 'steps': 24996, 'loss/train': 1.3085339069366455} 08/30/2021 17:40:00 - INFO - __main__ - Step 24998: {'lr': 0.00047079970435110765, 'samples': 4799616, 'steps': 24997, 'loss/train': 1.699511170387268} 08/30/2021 17:40:01 - INFO - __main__ - Step 24999: {'lr': 0.0004707972154447766, 'samples': 4799808, 'steps': 24998, 'loss/train': 4.631608963012695} 08/30/2021 17:40:01 - INFO - __main__ - Step 25000: {'lr': 0.00047079472643895784, 'samples': 4800000, 'steps': 24999, 'loss/train': 1.5615689754486084} 08/30/2021 17:40:01 - INFO - __main__ - Step 25001: {'lr': 0.00047079223733365234, 'samples': 4800192, 'steps': 25000, 'loss/train': 1.6584721803665161} 08/30/2021 17:40:03 - INFO - __main__ - Step 25002: {'lr': 0.0004707897481288612, 'samples': 4800384, 'steps': 25001, 'loss/train': 1.011987328529358} 08/30/2021 17:40:03 - INFO - __main__ - Step 25003: {'lr': 0.00047078725882458575, 'samples': 4800576, 'steps': 25002, 'loss/train': 1.2912969589233398} 08/30/2021 17:40:04 - INFO - __main__ - Step 25004: {'lr': 0.0004707847694208269, 'samples': 4800768, 'steps': 25003, 'loss/train': 1.742913007736206} 08/30/2021 17:40:04 - INFO - __main__ - Step 25005: {'lr': 0.0004707822799175858, 'samples': 4800960, 'steps': 25004, 'loss/train': 1.720575213432312} 08/30/2021 17:40:04 - INFO - __main__ - Step 25006: {'lr': 0.00047077979031486363, 'samples': 4801152, 'steps': 25005, 'loss/train': 1.5674479007720947} 08/30/2021 17:40:06 - INFO - __main__ - Step 25007: {'lr': 0.0004707773006126615, 'samples': 4801344, 'steps': 25006, 'loss/train': 1.6338114738464355} 08/30/2021 17:40:07 - INFO - __main__ - Step 25008: {'lr': 0.0004707748108109805, 'samples': 4801536, 'steps': 25007, 'loss/train': 1.4947255849838257} 08/30/2021 17:40:07 - INFO - __main__ - Step 25009: {'lr': 0.0004707723209098218, 'samples': 4801728, 'steps': 25008, 'loss/train': 1.4501467943191528} 08/30/2021 17:40:08 - INFO - __main__ - Step 25010: {'lr': 0.0004707698309091865, 'samples': 4801920, 'steps': 25009, 'loss/train': 1.4030537605285645} 08/30/2021 17:40:08 - INFO - __main__ - Step 25011: {'lr': 0.00047076734080907576, 'samples': 4802112, 'steps': 25010, 'loss/train': 1.7794524431228638} 08/30/2021 17:40:09 - INFO - __main__ - Step 25012: {'lr': 0.0004707648506094906, 'samples': 4802304, 'steps': 25011, 'loss/train': 1.6770697832107544} 08/30/2021 17:40:10 - INFO - __main__ - Step 25013: {'lr': 0.0004707623603104322, 'samples': 4802496, 'steps': 25012, 'loss/train': 1.873600721359253} 08/30/2021 17:40:10 - INFO - __main__ - Step 25014: {'lr': 0.0004707598699119018, 'samples': 4802688, 'steps': 25013, 'loss/train': 1.5718786716461182} 08/30/2021 17:40:11 - INFO - __main__ - Step 25015: {'lr': 0.0004707573794139003, 'samples': 4802880, 'steps': 25014, 'loss/train': 1.6327112913131714} 08/30/2021 17:40:11 - INFO - __main__ - Step 25016: {'lr': 0.0004707548888164289, 'samples': 4803072, 'steps': 25015, 'loss/train': 1.7203716039657593} 08/30/2021 17:40:12 - INFO - __main__ - Step 25017: {'lr': 0.0004707523981194889, 'samples': 4803264, 'steps': 25016, 'loss/train': 1.2609792947769165} 08/30/2021 17:40:13 - INFO - __main__ - Step 25018: {'lr': 0.00047074990732308116, 'samples': 4803456, 'steps': 25017, 'loss/train': 1.330159068107605} 08/30/2021 17:40:13 - INFO - __main__ - Step 25019: {'lr': 0.00047074741642720694, 'samples': 4803648, 'steps': 25018, 'loss/train': 1.607756495475769} 08/30/2021 17:40:14 - INFO - __main__ - Step 25020: {'lr': 0.0004707449254318673, 'samples': 4803840, 'steps': 25019, 'loss/train': 1.688234567642212} 08/30/2021 17:40:14 - INFO - __main__ - Step 25021: {'lr': 0.0004707424343370635, 'samples': 4804032, 'steps': 25020, 'loss/train': 1.5290659666061401} 08/30/2021 17:40:16 - INFO - __main__ - Step 25022: {'lr': 0.00047073994314279647, 'samples': 4804224, 'steps': 25021, 'loss/train': 1.3709489107131958} 08/30/2021 17:40:16 - INFO - __main__ - Step 25023: {'lr': 0.0004707374518490675, 'samples': 4804416, 'steps': 25022, 'loss/train': 1.2842025756835938} 08/30/2021 17:40:16 - INFO - __main__ - Step 25024: {'lr': 0.0004707349604558776, 'samples': 4804608, 'steps': 25023, 'loss/train': 1.225508451461792} 08/30/2021 17:40:17 - INFO - __main__ - Step 25025: {'lr': 0.00047073246896322797, 'samples': 4804800, 'steps': 25024, 'loss/train': 2.0839381217956543} 08/30/2021 17:40:17 - INFO - __main__ - Step 25026: {'lr': 0.00047072997737111966, 'samples': 4804992, 'steps': 25025, 'loss/train': 1.4561882019042969} 08/30/2021 17:40:17 - INFO - __main__ - Step 25027: {'lr': 0.0004707274856795538, 'samples': 4805184, 'steps': 25026, 'loss/train': 1.6024748086929321} 08/30/2021 17:40:19 - INFO - __main__ - Step 25028: {'lr': 0.00047072499388853164, 'samples': 4805376, 'steps': 25027, 'loss/train': 1.900529146194458} 08/30/2021 17:40:19 - INFO - __main__ - Step 25029: {'lr': 0.0004707225019980541, 'samples': 4805568, 'steps': 25028, 'loss/train': 1.4839271306991577} 08/30/2021 17:40:20 - INFO - __main__ - Step 25030: {'lr': 0.00047072001000812247, 'samples': 4805760, 'steps': 25029, 'loss/train': 1.487958312034607} 08/30/2021 17:40:20 - INFO - __main__ - Step 25031: {'lr': 0.00047071751791873774, 'samples': 4805952, 'steps': 25030, 'loss/train': 1.3906569480895996} 08/30/2021 17:40:20 - INFO - __main__ - Step 25032: {'lr': 0.0004707150257299012, 'samples': 4806144, 'steps': 25031, 'loss/train': 1.6489684581756592} 08/30/2021 17:40:22 - INFO - __main__ - Step 25033: {'lr': 0.0004707125334416138, 'samples': 4806336, 'steps': 25032, 'loss/train': 1.3826849460601807} 08/30/2021 17:40:23 - INFO - __main__ - Step 25034: {'lr': 0.00047071004105387677, 'samples': 4806528, 'steps': 25033, 'loss/train': 1.9108388423919678} 08/30/2021 17:40:23 - INFO - __main__ - Step 25035: {'lr': 0.00047070754856669115, 'samples': 4806720, 'steps': 25034, 'loss/train': 1.31353759765625} 08/30/2021 17:40:24 - INFO - __main__ - Step 25036: {'lr': 0.0004707050559800582, 'samples': 4806912, 'steps': 25035, 'loss/train': 1.1166515350341797} 08/30/2021 17:40:24 - INFO - __main__ - Step 25037: {'lr': 0.00047070256329397893, 'samples': 4807104, 'steps': 25036, 'loss/train': 0.8583371639251709} 08/30/2021 17:40:24 - INFO - __main__ - Step 25038: {'lr': 0.0004707000705084545, 'samples': 4807296, 'steps': 25037, 'loss/train': 0.057708073407411575} 08/30/2021 17:40:26 - INFO - __main__ - Step 25039: {'lr': 0.000470697577623486, 'samples': 4807488, 'steps': 25038, 'loss/train': 1.9112403392791748} 08/30/2021 17:40:26 - INFO - __main__ - Step 25040: {'lr': 0.0004706950846390746, 'samples': 4807680, 'steps': 25039, 'loss/train': 1.9506802558898926} 08/30/2021 17:40:27 - INFO - __main__ - Step 25041: {'lr': 0.00047069259155522135, 'samples': 4807872, 'steps': 25040, 'loss/train': 1.3299362659454346} 08/30/2021 17:40:27 - INFO - __main__ - Step 25042: {'lr': 0.0004706900983719274, 'samples': 4808064, 'steps': 25041, 'loss/train': 2.207509756088257} 08/30/2021 17:40:27 - INFO - __main__ - Step 25043: {'lr': 0.000470687605089194, 'samples': 4808256, 'steps': 25042, 'loss/train': 1.5854017734527588} 08/30/2021 17:40:29 - INFO - __main__ - Step 25044: {'lr': 0.0004706851117070221, 'samples': 4808448, 'steps': 25043, 'loss/train': 1.9118982553482056} 08/30/2021 17:40:29 - INFO - __main__ - Step 25045: {'lr': 0.0004706826182254129, 'samples': 4808640, 'steps': 25044, 'loss/train': 1.6057268381118774} 08/30/2021 17:40:30 - INFO - __main__ - Step 25046: {'lr': 0.0004706801246443676, 'samples': 4808832, 'steps': 25045, 'loss/train': 1.7143179178237915} 08/30/2021 17:40:30 - INFO - __main__ - Step 25047: {'lr': 0.00047067763096388717, 'samples': 4809024, 'steps': 25046, 'loss/train': 1.1472886800765991} 08/30/2021 17:40:30 - INFO - __main__ - Step 25048: {'lr': 0.00047067513718397283, 'samples': 4809216, 'steps': 25047, 'loss/train': 1.8607536554336548} 08/30/2021 17:40:32 - INFO - __main__ - Step 25049: {'lr': 0.0004706726433046256, 'samples': 4809408, 'steps': 25048, 'loss/train': 1.89994478225708} 08/30/2021 17:40:32 - INFO - __main__ - Step 25050: {'lr': 0.00047067014932584674, 'samples': 4809600, 'steps': 25049, 'loss/train': 1.3649753332138062} 08/30/2021 17:40:33 - INFO - __main__ - Step 25051: {'lr': 0.0004706676552476373, 'samples': 4809792, 'steps': 25050, 'loss/train': 1.4867832660675049} 08/30/2021 17:40:33 - INFO - __main__ - Step 25052: {'lr': 0.0004706651610699985, 'samples': 4809984, 'steps': 25051, 'loss/train': 1.2261881828308105} 08/30/2021 17:40:33 - INFO - __main__ - Step 25053: {'lr': 0.00047066266679293125, 'samples': 4810176, 'steps': 25052, 'loss/train': 0.8619534969329834} 08/30/2021 17:40:34 - INFO - __main__ - Step 25054: {'lr': 0.0004706601724164369, 'samples': 4810368, 'steps': 25053, 'loss/train': 2.069847583770752} 08/30/2021 17:40:35 - INFO - __main__ - Step 25055: {'lr': 0.0004706576779405165, 'samples': 4810560, 'steps': 25054, 'loss/train': 1.9539846181869507} 08/30/2021 17:40:36 - INFO - __main__ - Step 25056: {'lr': 0.0004706551833651711, 'samples': 4810752, 'steps': 25055, 'loss/train': 0.2109277993440628} 08/30/2021 17:40:36 - INFO - __main__ - Step 25057: {'lr': 0.0004706526886904019, 'samples': 4810944, 'steps': 25056, 'loss/train': 1.317997694015503} 08/30/2021 17:40:37 - INFO - __main__ - Step 25058: {'lr': 0.00047065019391621, 'samples': 4811136, 'steps': 25057, 'loss/train': 1.2071038484573364} 08/30/2021 17:40:37 - INFO - __main__ - Step 25059: {'lr': 0.0004706476990425965, 'samples': 4811328, 'steps': 25058, 'loss/train': 1.1856105327606201} 08/30/2021 17:40:38 - INFO - __main__ - Step 25060: {'lr': 0.0004706452040695626, 'samples': 4811520, 'steps': 25059, 'loss/train': 1.4010510444641113} 08/30/2021 17:40:39 - INFO - __main__ - Step 25061: {'lr': 0.0004706427089971093, 'samples': 4811712, 'steps': 25060, 'loss/train': 1.15224027633667} 08/30/2021 17:40:39 - INFO - __main__ - Step 25062: {'lr': 0.0004706402138252379, 'samples': 4811904, 'steps': 25061, 'loss/train': 1.3296509981155396} 08/30/2021 17:40:39 - INFO - __main__ - Step 25063: {'lr': 0.00047063771855394935, 'samples': 4812096, 'steps': 25062, 'loss/train': 2.1697821617126465} 08/30/2021 17:40:40 - INFO - __main__ - Step 25064: {'lr': 0.00047063522318324484, 'samples': 4812288, 'steps': 25063, 'loss/train': 1.5971816778182983} 08/30/2021 17:40:42 - INFO - __main__ - Step 25065: {'lr': 0.00047063272771312556, 'samples': 4812480, 'steps': 25064, 'loss/train': 1.9891161918640137} 08/30/2021 17:40:43 - INFO - __main__ - Step 25066: {'lr': 0.0004706302321435926, 'samples': 4812672, 'steps': 25065, 'loss/train': 1.7171852588653564} 08/30/2021 17:40:43 - INFO - __main__ - Step 25067: {'lr': 0.00047062773647464694, 'samples': 4812864, 'steps': 25066, 'loss/train': 1.5297914743423462} 08/30/2021 17:40:43 - INFO - __main__ - Step 25068: {'lr': 0.00047062524070628993, 'samples': 4813056, 'steps': 25067, 'loss/train': 1.6285282373428345} 08/30/2021 17:40:44 - INFO - __main__ - Step 25069: {'lr': 0.00047062274483852253, 'samples': 4813248, 'steps': 25068, 'loss/train': 1.307554841041565} 08/30/2021 17:40:45 - INFO - __main__ - Step 25070: {'lr': 0.000470620248871346, 'samples': 4813440, 'steps': 25069, 'loss/train': 0.15752136707305908} 08/30/2021 17:40:46 - INFO - __main__ - Step 25071: {'lr': 0.00047061775280476134, 'samples': 4813632, 'steps': 25070, 'loss/train': 0.3412875831127167} 08/30/2021 17:40:46 - INFO - __main__ - Step 25072: {'lr': 0.0004706152566387697, 'samples': 4813824, 'steps': 25071, 'loss/train': 2.12052583694458} 08/30/2021 17:40:46 - INFO - __main__ - Step 25073: {'lr': 0.0004706127603733723, 'samples': 4814016, 'steps': 25072, 'loss/train': 0.8742642402648926} 08/30/2021 17:40:47 - INFO - __main__ - Step 25074: {'lr': 0.00047061026400857015, 'samples': 4814208, 'steps': 25073, 'loss/train': 0.27285999059677124} 08/30/2021 17:40:49 - INFO - __main__ - Step 25075: {'lr': 0.0004706077675443644, 'samples': 4814400, 'steps': 25074, 'loss/train': 1.3892403841018677} 08/30/2021 17:40:49 - INFO - __main__ - Step 25076: {'lr': 0.00047060527098075625, 'samples': 4814592, 'steps': 25075, 'loss/train': 1.2786834239959717} 08/30/2021 17:40:50 - INFO - __main__ - Step 25077: {'lr': 0.0004706027743177467, 'samples': 4814784, 'steps': 25076, 'loss/train': 1.3125505447387695} 08/30/2021 17:40:50 - INFO - __main__ - Step 25078: {'lr': 0.000470600277555337, 'samples': 4814976, 'steps': 25077, 'loss/train': 1.3752082586288452} 08/30/2021 17:40:50 - INFO - __main__ - Step 25079: {'lr': 0.0004705977806935282, 'samples': 4815168, 'steps': 25078, 'loss/train': 1.3756707906723022} 08/30/2021 17:40:51 - INFO - __main__ - Step 25080: {'lr': 0.00047059528373232147, 'samples': 4815360, 'steps': 25079, 'loss/train': 2.5226731300354004} 08/30/2021 17:40:52 - INFO - __main__ - Step 25081: {'lr': 0.0004705927866717179, 'samples': 4815552, 'steps': 25080, 'loss/train': 1.7651067972183228} 08/30/2021 17:40:53 - INFO - __main__ - Step 25082: {'lr': 0.0004705902895117186, 'samples': 4815744, 'steps': 25081, 'loss/train': 1.9038233757019043} 08/30/2021 17:40:53 - INFO - __main__ - Step 25083: {'lr': 0.00047058779225232474, 'samples': 4815936, 'steps': 25082, 'loss/train': 1.8142799139022827} 08/30/2021 17:40:53 - INFO - __main__ - Step 25084: {'lr': 0.0004705852948935374, 'samples': 4816128, 'steps': 25083, 'loss/train': 1.6670634746551514} 08/30/2021 17:40:54 - INFO - __main__ - Step 25085: {'lr': 0.00047058279743535775, 'samples': 4816320, 'steps': 25084, 'loss/train': 1.678105115890503} 08/30/2021 17:40:55 - INFO - __main__ - Step 25086: {'lr': 0.0004705802998777869, 'samples': 4816512, 'steps': 25085, 'loss/train': 1.5790992975234985} 08/30/2021 17:40:56 - INFO - __main__ - Step 25087: {'lr': 0.0004705778022208259, 'samples': 4816704, 'steps': 25086, 'loss/train': 1.2291311025619507} 08/30/2021 17:40:56 - INFO - __main__ - Step 25088: {'lr': 0.000470575304464476, 'samples': 4816896, 'steps': 25087, 'loss/train': 1.6294530630111694} 08/30/2021 17:40:57 - INFO - __main__ - Step 25089: {'lr': 0.00047057280660873835, 'samples': 4817088, 'steps': 25088, 'loss/train': 1.641780972480774} 08/30/2021 17:40:57 - INFO - __main__ - Step 25090: {'lr': 0.00047057030865361397, 'samples': 4817280, 'steps': 25089, 'loss/train': 1.677525520324707} 08/30/2021 17:40:59 - INFO - __main__ - Step 25091: {'lr': 0.0004705678105991039, 'samples': 4817472, 'steps': 25090, 'loss/train': 0.21901018917560577} 08/30/2021 17:40:59 - INFO - __main__ - Step 25092: {'lr': 0.00047056531244520945, 'samples': 4817664, 'steps': 25091, 'loss/train': 0.9002791047096252} 08/30/2021 17:41:00 - INFO - __main__ - Step 25093: {'lr': 0.0004705628141919317, 'samples': 4817856, 'steps': 25092, 'loss/train': 0.9649285674095154} 08/30/2021 17:41:00 - INFO - __main__ - Step 25094: {'lr': 0.00047056031583927175, 'samples': 4818048, 'steps': 25093, 'loss/train': 1.1545499563217163} 08/30/2021 17:41:00 - INFO - __main__ - Step 25095: {'lr': 0.00047055781738723063, 'samples': 4818240, 'steps': 25094, 'loss/train': 1.1860684156417847} 08/30/2021 17:41:02 - INFO - __main__ - Step 25096: {'lr': 0.0004705553188358096, 'samples': 4818432, 'steps': 25095, 'loss/train': 1.0877487659454346} 08/30/2021 17:41:02 - INFO - __main__ - Step 25097: {'lr': 0.00047055282018500976, 'samples': 4818624, 'steps': 25096, 'loss/train': 1.5303350687026978} 08/30/2021 17:41:03 - INFO - __main__ - Step 25098: {'lr': 0.0004705503214348323, 'samples': 4818816, 'steps': 25097, 'loss/train': 1.5555001497268677} 08/30/2021 17:41:03 - INFO - __main__ - Step 25099: {'lr': 0.0004705478225852782, 'samples': 4819008, 'steps': 25098, 'loss/train': 1.4041889905929565} 08/30/2021 17:41:03 - INFO - __main__ - Step 25100: {'lr': 0.0004705453236363486, 'samples': 4819200, 'steps': 25099, 'loss/train': 2.064286947250366} 08/30/2021 17:41:04 - INFO - __main__ - Step 25101: {'lr': 0.00047054282458804477, 'samples': 4819392, 'steps': 25100, 'loss/train': 1.1360825300216675} 08/30/2021 17:41:05 - INFO - __main__ - Step 25102: {'lr': 0.0004705403254403677, 'samples': 4819584, 'steps': 25101, 'loss/train': 1.521355152130127} 08/30/2021 17:41:06 - INFO - __main__ - Step 25103: {'lr': 0.0004705378261933186, 'samples': 4819776, 'steps': 25102, 'loss/train': 0.9425626993179321} 08/30/2021 17:41:06 - INFO - __main__ - Step 25104: {'lr': 0.0004705353268468985, 'samples': 4819968, 'steps': 25103, 'loss/train': 1.4939793348312378} 08/30/2021 17:41:06 - INFO - __main__ - Step 25105: {'lr': 0.00047053282740110863, 'samples': 4820160, 'steps': 25104, 'loss/train': 1.3788909912109375} 08/30/2021 17:41:07 - INFO - __main__ - Step 25106: {'lr': 0.00047053032785595005, 'samples': 4820352, 'steps': 25105, 'loss/train': 1.9078004360198975} 08/30/2021 17:41:09 - INFO - __main__ - Step 25107: {'lr': 0.0004705278282114239, 'samples': 4820544, 'steps': 25106, 'loss/train': 1.6420369148254395} 08/30/2021 17:41:09 - INFO - __main__ - Step 25108: {'lr': 0.0004705253284675314, 'samples': 4820736, 'steps': 25107, 'loss/train': 1.7942553758621216} 08/30/2021 17:41:09 - INFO - __main__ - Step 25109: {'lr': 0.00047052282862427355, 'samples': 4820928, 'steps': 25108, 'loss/train': 1.8953509330749512} 08/30/2021 17:41:10 - INFO - __main__ - Step 25110: {'lr': 0.0004705203286816514, 'samples': 4821120, 'steps': 25109, 'loss/train': 1.2782175540924072} 08/30/2021 17:41:10 - INFO - __main__ - Step 25111: {'lr': 0.0004705178286396663, 'samples': 4821312, 'steps': 25110, 'loss/train': 1.3305717706680298} 08/30/2021 17:41:10 - INFO - __main__ - Step 25112: {'lr': 0.0004705153284983192, 'samples': 4821504, 'steps': 25111, 'loss/train': 0.05513116344809532} 08/30/2021 17:41:12 - INFO - __main__ - Step 25113: {'lr': 0.00047051282825761145, 'samples': 4821696, 'steps': 25112, 'loss/train': 1.161117672920227} 08/30/2021 17:41:12 - INFO - __main__ - Step 25114: {'lr': 0.0004705103279175439, 'samples': 4821888, 'steps': 25113, 'loss/train': 1.6258196830749512} 08/30/2021 17:41:13 - INFO - __main__ - Step 25115: {'lr': 0.0004705078274781178, 'samples': 4822080, 'steps': 25114, 'loss/train': 1.7940661907196045} 08/30/2021 17:41:13 - INFO - __main__ - Step 25116: {'lr': 0.0004705053269393343, 'samples': 4822272, 'steps': 25115, 'loss/train': 0.8398537635803223} 08/30/2021 17:41:13 - INFO - __main__ - Step 25117: {'lr': 0.00047050282630119444, 'samples': 4822464, 'steps': 25116, 'loss/train': 1.5013272762298584} 08/30/2021 17:41:15 - INFO - __main__ - Step 25118: {'lr': 0.0004705003255636995, 'samples': 4822656, 'steps': 25117, 'loss/train': 1.9050203561782837} 08/30/2021 17:41:16 - INFO - __main__ - Step 25119: {'lr': 0.0004704978247268505, 'samples': 4822848, 'steps': 25118, 'loss/train': 0.638746440410614} 08/30/2021 17:41:16 - INFO - __main__ - Step 25120: {'lr': 0.0004704953237906485, 'samples': 4823040, 'steps': 25119, 'loss/train': 1.5404378175735474} 08/30/2021 17:41:17 - INFO - __main__ - Step 25121: {'lr': 0.0004704928227550949, 'samples': 4823232, 'steps': 25120, 'loss/train': 1.76178777217865} 08/30/2021 17:41:17 - INFO - __main__ - Step 25122: {'lr': 0.00047049032162019044, 'samples': 4823424, 'steps': 25121, 'loss/train': 1.4631903171539307} 08/30/2021 17:41:19 - INFO - __main__ - Step 25123: {'lr': 0.0004704878203859365, 'samples': 4823616, 'steps': 25122, 'loss/train': 0.8127224445343018} 08/30/2021 17:41:19 - INFO - __main__ - Step 25124: {'lr': 0.0004704853190523342, 'samples': 4823808, 'steps': 25123, 'loss/train': 1.4740229845046997} 08/30/2021 17:41:19 - INFO - __main__ - Step 25125: {'lr': 0.00047048281761938456, 'samples': 4824000, 'steps': 25124, 'loss/train': 1.1336865425109863} 08/30/2021 17:41:20 - INFO - __main__ - Step 25126: {'lr': 0.00047048031608708875, 'samples': 4824192, 'steps': 25125, 'loss/train': 1.0112028121948242} 08/30/2021 17:41:20 - INFO - __main__ - Step 25127: {'lr': 0.000470477814455448, 'samples': 4824384, 'steps': 25126, 'loss/train': 1.4916080236434937} 08/30/2021 17:41:22 - INFO - __main__ - Step 25128: {'lr': 0.0004704753127244633, 'samples': 4824576, 'steps': 25127, 'loss/train': 0.8901615142822266} 08/30/2021 17:41:22 - INFO - __main__ - Step 25129: {'lr': 0.0004704728108941358, 'samples': 4824768, 'steps': 25128, 'loss/train': 1.0653492212295532} 08/30/2021 17:41:22 - INFO - __main__ - Step 25130: {'lr': 0.00047047030896446665, 'samples': 4824960, 'steps': 25129, 'loss/train': 1.1029903888702393} 08/30/2021 17:41:23 - INFO - __main__ - Step 25131: {'lr': 0.000470467806935457, 'samples': 4825152, 'steps': 25130, 'loss/train': 1.9126156568527222} 08/30/2021 17:41:23 - INFO - __main__ - Step 25132: {'lr': 0.000470465304807108, 'samples': 4825344, 'steps': 25131, 'loss/train': 1.6000009775161743} 08/30/2021 17:41:25 - INFO - __main__ - Step 25133: {'lr': 0.00047046280257942067, 'samples': 4825536, 'steps': 25132, 'loss/train': 1.7084357738494873} 08/30/2021 17:41:25 - INFO - __main__ - Step 25134: {'lr': 0.0004704603002523962, 'samples': 4825728, 'steps': 25133, 'loss/train': 1.66991126537323} 08/30/2021 17:41:25 - INFO - __main__ - Step 25135: {'lr': 0.00047045779782603584, 'samples': 4825920, 'steps': 25134, 'loss/train': 1.288764476776123} 08/30/2021 17:41:26 - INFO - __main__ - Step 25136: {'lr': 0.0004704552953003405, 'samples': 4826112, 'steps': 25135, 'loss/train': 1.651648759841919} 08/30/2021 17:41:26 - INFO - __main__ - Step 25137: {'lr': 0.0004704527926753114, 'samples': 4826304, 'steps': 25136, 'loss/train': 2.0784590244293213} 08/30/2021 17:41:28 - INFO - __main__ - Step 25138: {'lr': 0.00047045028995094967, 'samples': 4826496, 'steps': 25137, 'loss/train': 1.7070115804672241} 08/30/2021 17:41:28 - INFO - __main__ - Step 25139: {'lr': 0.0004704477871272564, 'samples': 4826688, 'steps': 25138, 'loss/train': 1.3351141214370728} 08/30/2021 17:41:28 - INFO - __main__ - Step 25140: {'lr': 0.0004704452842042329, 'samples': 4826880, 'steps': 25139, 'loss/train': 1.4742670059204102} 08/30/2021 17:41:29 - INFO - __main__ - Step 25141: {'lr': 0.00047044278118188004, 'samples': 4827072, 'steps': 25140, 'loss/train': 1.3778868913650513} 08/30/2021 17:41:29 - INFO - __main__ - Step 25142: {'lr': 0.00047044027806019914, 'samples': 4827264, 'steps': 25141, 'loss/train': 1.4661959409713745} 08/30/2021 17:41:31 - INFO - __main__ - Step 25143: {'lr': 0.0004704377748391912, 'samples': 4827456, 'steps': 25142, 'loss/train': 2.056394577026367} 08/30/2021 17:41:31 - INFO - __main__ - Step 25144: {'lr': 0.0004704352715188574, 'samples': 4827648, 'steps': 25143, 'loss/train': 1.6076358556747437} 08/30/2021 17:41:31 - INFO - __main__ - Step 25145: {'lr': 0.0004704327680991989, 'samples': 4827840, 'steps': 25144, 'loss/train': 1.732292890548706} 08/30/2021 17:41:32 - INFO - __main__ - Step 25146: {'lr': 0.00047043026458021677, 'samples': 4828032, 'steps': 25145, 'loss/train': 1.7129887342453003} 08/30/2021 17:41:32 - INFO - __main__ - Step 25147: {'lr': 0.0004704277609619122, 'samples': 4828224, 'steps': 25146, 'loss/train': 1.8288956880569458} 08/30/2021 17:41:34 - INFO - __main__ - Step 25148: {'lr': 0.0004704252572442862, 'samples': 4828416, 'steps': 25147, 'loss/train': 0.5143375992774963} 08/30/2021 17:41:34 - INFO - __main__ - Step 25149: {'lr': 0.00047042275342734006, 'samples': 4828608, 'steps': 25148, 'loss/train': 1.0501458644866943} 08/30/2021 17:41:35 - INFO - __main__ - Step 25150: {'lr': 0.0004704202495110748, 'samples': 4828800, 'steps': 25149, 'loss/train': 0.18096794188022614} 08/30/2021 17:41:35 - INFO - __main__ - Step 25151: {'lr': 0.00047041774549549156, 'samples': 4828992, 'steps': 25150, 'loss/train': 0.6156520843505859} 08/30/2021 17:41:35 - INFO - __main__ - Step 25152: {'lr': 0.00047041524138059153, 'samples': 4829184, 'steps': 25151, 'loss/train': 1.241715908050537} 08/30/2021 17:41:36 - INFO - __main__ - Step 25153: {'lr': 0.00047041273716637576, 'samples': 4829376, 'steps': 25152, 'loss/train': 1.6219685077667236} 08/30/2021 17:41:37 - INFO - __main__ - Step 25154: {'lr': 0.00047041023285284545, 'samples': 4829568, 'steps': 25153, 'loss/train': 1.4883368015289307} 08/30/2021 17:41:37 - INFO - __main__ - Step 25155: {'lr': 0.0004704077284400017, 'samples': 4829760, 'steps': 25154, 'loss/train': 1.6693414449691772} 08/30/2021 17:41:38 - INFO - __main__ - Step 25156: {'lr': 0.0004704052239278456, 'samples': 4829952, 'steps': 25155, 'loss/train': 1.5799920558929443} 08/30/2021 17:41:38 - INFO - __main__ - Step 25157: {'lr': 0.00047040271931637824, 'samples': 4830144, 'steps': 25156, 'loss/train': 1.7024641036987305} 08/30/2021 17:41:38 - INFO - __main__ - Step 25158: {'lr': 0.0004704002146056009, 'samples': 4830336, 'steps': 25157, 'loss/train': 1.5750199556350708} 08/30/2021 17:41:40 - INFO - __main__ - Step 25159: {'lr': 0.0004703977097955146, 'samples': 4830528, 'steps': 25158, 'loss/train': 1.4540636539459229} 08/30/2021 17:41:41 - INFO - __main__ - Step 25160: {'lr': 0.0004703952048861204, 'samples': 4830720, 'steps': 25159, 'loss/train': 1.2269320487976074} 08/30/2021 17:41:41 - INFO - __main__ - Step 25161: {'lr': 0.00047039269987741967, 'samples': 4830912, 'steps': 25160, 'loss/train': 1.3916511535644531} 08/30/2021 17:41:41 - INFO - __main__ - Step 25162: {'lr': 0.0004703901947694134, 'samples': 4831104, 'steps': 25161, 'loss/train': 1.8600291013717651} 08/30/2021 17:41:42 - INFO - __main__ - Step 25163: {'lr': 0.0004703876895621025, 'samples': 4831296, 'steps': 25162, 'loss/train': 1.2141042947769165} 08/30/2021 17:41:43 - INFO - __main__ - Step 25164: {'lr': 0.0004703851842554885, 'samples': 4831488, 'steps': 25163, 'loss/train': 1.958831787109375} 08/30/2021 17:41:44 - INFO - __main__ - Step 25165: {'lr': 0.0004703826788495723, 'samples': 4831680, 'steps': 25164, 'loss/train': 1.3399730920791626} 08/30/2021 17:41:44 - INFO - __main__ - Step 25166: {'lr': 0.00047038017334435504, 'samples': 4831872, 'steps': 25165, 'loss/train': 0.9132199883460999} 08/30/2021 17:41:44 - INFO - __main__ - Step 25167: {'lr': 0.00047037766773983794, 'samples': 4832064, 'steps': 25166, 'loss/train': 1.8331776857376099} 08/30/2021 17:41:45 - INFO - __main__ - Step 25168: {'lr': 0.00047037516203602195, 'samples': 4832256, 'steps': 25167, 'loss/train': 1.5712714195251465} 08/30/2021 17:41:46 - INFO - __main__ - Step 25169: {'lr': 0.0004703726562329084, 'samples': 4832448, 'steps': 25168, 'loss/train': 1.8494906425476074} 08/30/2021 17:41:47 - INFO - __main__ - Step 25170: {'lr': 0.0004703701503304983, 'samples': 4832640, 'steps': 25169, 'loss/train': 0.22215215861797333} 08/30/2021 17:41:47 - INFO - __main__ - Step 25171: {'lr': 0.0004703676443287928, 'samples': 4832832, 'steps': 25170, 'loss/train': 1.6323357820510864} 08/30/2021 17:41:47 - INFO - __main__ - Step 25172: {'lr': 0.000470365138227793, 'samples': 4833024, 'steps': 25171, 'loss/train': 0.9610714912414551} 08/30/2021 17:41:48 - INFO - __main__ - Step 25173: {'lr': 0.0004703626320275002, 'samples': 4833216, 'steps': 25172, 'loss/train': 1.2970154285430908} 08/30/2021 17:41:48 - INFO - __main__ - Step 25174: {'lr': 0.0004703601257279153, 'samples': 4833408, 'steps': 25173, 'loss/train': 2.189345598220825} 08/30/2021 17:41:50 - INFO - __main__ - Step 25175: {'lr': 0.0004703576193290395, 'samples': 4833600, 'steps': 25174, 'loss/train': 1.9523824453353882} 08/30/2021 17:41:51 - INFO - __main__ - Step 25176: {'lr': 0.0004703551128308741, 'samples': 4833792, 'steps': 25175, 'loss/train': 1.7613623142242432} 08/30/2021 17:41:51 - INFO - __main__ - Step 25177: {'lr': 0.00047035260623341996, 'samples': 4833984, 'steps': 25176, 'loss/train': 1.345569133758545} 08/30/2021 17:41:51 - INFO - __main__ - Step 25178: {'lr': 0.0004703500995366784, 'samples': 4834176, 'steps': 25177, 'loss/train': 1.8932678699493408} 08/30/2021 17:41:52 - INFO - __main__ - Step 25179: {'lr': 0.00047034759274065043, 'samples': 4834368, 'steps': 25178, 'loss/train': 1.2226879596710205} 08/30/2021 17:41:53 - INFO - __main__ - Step 25180: {'lr': 0.00047034508584533724, 'samples': 4834560, 'steps': 25179, 'loss/train': 1.2147520780563354} 08/30/2021 17:41:53 - INFO - __main__ - Step 25181: {'lr': 0.00047034257885074, 'samples': 4834752, 'steps': 25180, 'loss/train': 1.4377487897872925} 08/30/2021 17:41:54 - INFO - __main__ - Step 25182: {'lr': 0.00047034007175685976, 'samples': 4834944, 'steps': 25181, 'loss/train': 1.7231919765472412} 08/30/2021 17:41:54 - INFO - __main__ - Step 25183: {'lr': 0.0004703375645636977, 'samples': 4835136, 'steps': 25182, 'loss/train': 1.3159558773040771} 08/30/2021 17:41:54 - INFO - __main__ - Step 25184: {'lr': 0.0004703350572712549, 'samples': 4835328, 'steps': 25183, 'loss/train': 1.1757681369781494} 08/30/2021 17:41:56 - INFO - __main__ - Step 25185: {'lr': 0.00047033254987953254, 'samples': 4835520, 'steps': 25184, 'loss/train': 1.2443501949310303} 08/30/2021 17:41:57 - INFO - __main__ - Step 25186: {'lr': 0.0004703300423885318, 'samples': 4835712, 'steps': 25185, 'loss/train': 1.4792664051055908} 08/30/2021 17:41:57 - INFO - __main__ - Step 25187: {'lr': 0.0004703275347982536, 'samples': 4835904, 'steps': 25186, 'loss/train': 1.8373013734817505} 08/30/2021 17:41:57 - INFO - __main__ - Step 25188: {'lr': 0.00047032502710869935, 'samples': 4836096, 'steps': 25187, 'loss/train': 1.3806008100509644} 08/30/2021 17:41:58 - INFO - __main__ - Step 25189: {'lr': 0.00047032251931987, 'samples': 4836288, 'steps': 25188, 'loss/train': 1.3953410387039185} 08/30/2021 17:42:00 - INFO - __main__ - Step 25190: {'lr': 0.0004703200114317667, 'samples': 4836480, 'steps': 25189, 'loss/train': 1.228415608406067} 08/30/2021 17:42:00 - INFO - __main__ - Step 25191: {'lr': 0.0004703175034443906, 'samples': 4836672, 'steps': 25190, 'loss/train': 1.8546063899993896} 08/30/2021 17:42:00 - INFO - __main__ - Step 25192: {'lr': 0.00047031499535774284, 'samples': 4836864, 'steps': 25191, 'loss/train': 1.718413233757019} 08/30/2021 17:42:01 - INFO - __main__ - Step 25193: {'lr': 0.00047031248717182455, 'samples': 4837056, 'steps': 25192, 'loss/train': 1.4340121746063232} 08/30/2021 17:42:01 - INFO - __main__ - Step 25194: {'lr': 0.00047030997888663687, 'samples': 4837248, 'steps': 25193, 'loss/train': 0.7193629145622253} 08/30/2021 17:42:01 - INFO - __main__ - Step 25195: {'lr': 0.00047030747050218094, 'samples': 4837440, 'steps': 25194, 'loss/train': 1.7720571756362915} 08/30/2021 17:42:02 - INFO - __main__ - Step 25196: {'lr': 0.0004703049620184578, 'samples': 4837632, 'steps': 25195, 'loss/train': 1.7892900705337524} 08/30/2021 17:42:03 - INFO - __main__ - Step 25197: {'lr': 0.0004703024534354686, 'samples': 4837824, 'steps': 25196, 'loss/train': 2.4770662784576416} 08/30/2021 17:42:04 - INFO - __main__ - Step 25198: {'lr': 0.0004702999447532146, 'samples': 4838016, 'steps': 25197, 'loss/train': 1.5416127443313599} 08/30/2021 17:42:04 - INFO - __main__ - Step 25199: {'lr': 0.00047029743597169684, 'samples': 4838208, 'steps': 25198, 'loss/train': 1.4073939323425293} 08/30/2021 17:42:04 - INFO - __main__ - Step 25200: {'lr': 0.0004702949270909164, 'samples': 4838400, 'steps': 25199, 'loss/train': 1.692219614982605} 08/30/2021 17:42:05 - INFO - __main__ - Step 25201: {'lr': 0.0004702924181108745, 'samples': 4838592, 'steps': 25200, 'loss/train': 1.675784945487976} 08/30/2021 17:42:06 - INFO - __main__ - Step 25202: {'lr': 0.00047028990903157233, 'samples': 4838784, 'steps': 25201, 'loss/train': 1.6392043828964233} 08/30/2021 17:42:07 - INFO - __main__ - Step 25203: {'lr': 0.0004702873998530108, 'samples': 4838976, 'steps': 25202, 'loss/train': 1.324642300605774} 08/30/2021 17:42:07 - INFO - __main__ - Step 25204: {'lr': 0.0004702848905751912, 'samples': 4839168, 'steps': 25203, 'loss/train': 1.2755097150802612} 08/30/2021 17:42:08 - INFO - __main__ - Step 25205: {'lr': 0.0004702823811981146, 'samples': 4839360, 'steps': 25204, 'loss/train': 0.1903872936964035} 08/30/2021 17:42:08 - INFO - __main__ - Step 25206: {'lr': 0.0004702798717217822, 'samples': 4839552, 'steps': 25205, 'loss/train': 1.8723169565200806} 08/30/2021 17:42:09 - INFO - __main__ - Step 25207: {'lr': 0.0004702773621461951, 'samples': 4839744, 'steps': 25206, 'loss/train': 1.4872665405273438} 08/30/2021 17:42:10 - INFO - __main__ - Step 25208: {'lr': 0.0004702748524713544, 'samples': 4839936, 'steps': 25207, 'loss/train': 1.4404301643371582} 08/30/2021 17:42:10 - INFO - __main__ - Step 25209: {'lr': 0.00047027234269726123, 'samples': 4840128, 'steps': 25208, 'loss/train': 1.5485769510269165} 08/30/2021 17:42:11 - INFO - __main__ - Step 25210: {'lr': 0.0004702698328239167, 'samples': 4840320, 'steps': 25209, 'loss/train': 1.690459132194519} 08/30/2021 17:42:11 - INFO - __main__ - Step 25211: {'lr': 0.0004702673228513221, 'samples': 4840512, 'steps': 25210, 'loss/train': 1.505952000617981} 08/30/2021 17:42:12 - INFO - __main__ - Step 25212: {'lr': 0.00047026481277947835, 'samples': 4840704, 'steps': 25211, 'loss/train': 1.7400099039077759} 08/30/2021 17:42:13 - INFO - __main__ - Step 25213: {'lr': 0.0004702623026083867, 'samples': 4840896, 'steps': 25212, 'loss/train': 1.3989006280899048} 08/30/2021 17:42:13 - INFO - __main__ - Step 25214: {'lr': 0.00047025979233804825, 'samples': 4841088, 'steps': 25213, 'loss/train': 1.509686827659607} 08/30/2021 17:42:14 - INFO - __main__ - Step 25215: {'lr': 0.00047025728196846417, 'samples': 4841280, 'steps': 25214, 'loss/train': 1.5531995296478271} 08/30/2021 17:42:14 - INFO - __main__ - Step 25216: {'lr': 0.0004702547714996355, 'samples': 4841472, 'steps': 25215, 'loss/train': 1.4401838779449463} 08/30/2021 17:42:15 - INFO - __main__ - Step 25217: {'lr': 0.00047025226093156346, 'samples': 4841664, 'steps': 25216, 'loss/train': 1.3402336835861206} 08/30/2021 17:42:16 - INFO - __main__ - Step 25218: {'lr': 0.0004702497502642492, 'samples': 4841856, 'steps': 25217, 'loss/train': 1.020683765411377} 08/30/2021 17:42:16 - INFO - __main__ - Step 25219: {'lr': 0.0004702472394976938, 'samples': 4842048, 'steps': 25218, 'loss/train': 1.6742174625396729} 08/30/2021 17:42:17 - INFO - __main__ - Step 25220: {'lr': 0.0004702447286318983, 'samples': 4842240, 'steps': 25219, 'loss/train': 1.570212721824646} 08/30/2021 17:42:17 - INFO - __main__ - Step 25221: {'lr': 0.0004702422176668639, 'samples': 4842432, 'steps': 25220, 'loss/train': 1.4703494310379028} 08/30/2021 17:42:18 - INFO - __main__ - Step 25222: {'lr': 0.00047023970660259193, 'samples': 4842624, 'steps': 25221, 'loss/train': 1.8031941652297974} 08/30/2021 17:42:19 - INFO - __main__ - Step 25223: {'lr': 0.0004702371954390832, 'samples': 4842816, 'steps': 25222, 'loss/train': 1.4215047359466553} 08/30/2021 17:42:19 - INFO - __main__ - Step 25224: {'lr': 0.00047023468417633905, 'samples': 4843008, 'steps': 25223, 'loss/train': 0.1384240835905075} 08/30/2021 17:42:20 - INFO - __main__ - Step 25225: {'lr': 0.0004702321728143605, 'samples': 4843200, 'steps': 25224, 'loss/train': 1.4457356929779053} 08/30/2021 17:42:20 - INFO - __main__ - Step 25226: {'lr': 0.0004702296613531488, 'samples': 4843392, 'steps': 25225, 'loss/train': 1.6307753324508667} 08/30/2021 17:42:20 - INFO - __main__ - Step 25227: {'lr': 0.00047022714979270497, 'samples': 4843584, 'steps': 25226, 'loss/train': 1.2742396593093872} 08/30/2021 17:42:22 - INFO - __main__ - Step 25228: {'lr': 0.0004702246381330302, 'samples': 4843776, 'steps': 25227, 'loss/train': 1.5508121252059937} 08/30/2021 17:42:23 - INFO - __main__ - Step 25229: {'lr': 0.00047022212637412553, 'samples': 4843968, 'steps': 25228, 'loss/train': 1.4460803270339966} 08/30/2021 17:42:23 - INFO - __main__ - Step 25230: {'lr': 0.00047021961451599226, 'samples': 4844160, 'steps': 25229, 'loss/train': 1.8290355205535889} 08/30/2021 17:42:24 - INFO - __main__ - Step 25231: {'lr': 0.00047021710255863144, 'samples': 4844352, 'steps': 25230, 'loss/train': 1.8114560842514038} 08/30/2021 17:42:24 - INFO - __main__ - Step 25232: {'lr': 0.0004702145905020442, 'samples': 4844544, 'steps': 25231, 'loss/train': 1.5833290815353394} 08/30/2021 17:42:26 - INFO - __main__ - Step 25233: {'lr': 0.0004702120783462316, 'samples': 4844736, 'steps': 25232, 'loss/train': 1.5759029388427734} 08/30/2021 17:42:26 - INFO - __main__ - Step 25234: {'lr': 0.00047020956609119483, 'samples': 4844928, 'steps': 25233, 'loss/train': 1.5939463376998901} 08/30/2021 17:42:27 - INFO - __main__ - Step 25235: {'lr': 0.0004702070537369351, 'samples': 4845120, 'steps': 25234, 'loss/train': 1.4793111085891724} 08/30/2021 17:42:27 - INFO - __main__ - Step 25236: {'lr': 0.00047020454128345333, 'samples': 4845312, 'steps': 25235, 'loss/train': 1.8605574369430542} 08/30/2021 17:42:27 - INFO - __main__ - Step 25237: {'lr': 0.00047020202873075093, 'samples': 4845504, 'steps': 25236, 'loss/train': 1.7368876934051514} 08/30/2021 17:42:29 - INFO - __main__ - Step 25238: {'lr': 0.00047019951607882884, 'samples': 4845696, 'steps': 25237, 'loss/train': 1.234832525253296} 08/30/2021 17:42:29 - INFO - __main__ - Step 25239: {'lr': 0.0004701970033276882, 'samples': 4845888, 'steps': 25238, 'loss/train': 1.7299489974975586} 08/30/2021 17:42:30 - INFO - __main__ - Step 25240: {'lr': 0.0004701944904773303, 'samples': 4846080, 'steps': 25239, 'loss/train': 1.5737006664276123} 08/30/2021 17:42:30 - INFO - __main__ - Step 25241: {'lr': 0.0004701919775277561, 'samples': 4846272, 'steps': 25240, 'loss/train': 1.537653923034668} 08/30/2021 17:42:30 - INFO - __main__ - Step 25242: {'lr': 0.0004701894644789668, 'samples': 4846464, 'steps': 25241, 'loss/train': 1.1209821701049805} 08/30/2021 17:42:31 - INFO - __main__ - Step 25243: {'lr': 0.0004701869513309635, 'samples': 4846656, 'steps': 25242, 'loss/train': 2.0428268909454346} 08/30/2021 17:42:32 - INFO - __main__ - Step 25244: {'lr': 0.0004701844380837474, 'samples': 4846848, 'steps': 25243, 'loss/train': 1.5601223707199097} 08/30/2021 17:42:33 - INFO - __main__ - Step 25245: {'lr': 0.00047018192473731956, 'samples': 4847040, 'steps': 25244, 'loss/train': 1.5865105390548706} 08/30/2021 17:42:33 - INFO - __main__ - Step 25246: {'lr': 0.0004701794112916812, 'samples': 4847232, 'steps': 25245, 'loss/train': 1.503543496131897} 08/30/2021 17:42:34 - INFO - __main__ - Step 25247: {'lr': 0.00047017689774683325, 'samples': 4847424, 'steps': 25246, 'loss/train': 0.28209388256073} 08/30/2021 17:42:34 - INFO - __main__ - Step 25248: {'lr': 0.0004701743841027771, 'samples': 4847616, 'steps': 25247, 'loss/train': 0.06271487474441528} 08/30/2021 17:42:34 - INFO - __main__ - Step 25249: {'lr': 0.0004701718703595138, 'samples': 4847808, 'steps': 25248, 'loss/train': 2.7639365196228027} 08/30/2021 17:42:36 - INFO - __main__ - Step 25250: {'lr': 0.0004701693565170444, 'samples': 4848000, 'steps': 25249, 'loss/train': 1.5656744241714478} 08/30/2021 17:42:36 - INFO - __main__ - Step 25251: {'lr': 0.0004701668425753701, 'samples': 4848192, 'steps': 25250, 'loss/train': 1.3499870300292969} 08/30/2021 17:42:37 - INFO - __main__ - Step 25252: {'lr': 0.000470164328534492, 'samples': 4848384, 'steps': 25251, 'loss/train': 1.202694296836853} 08/30/2021 17:42:37 - INFO - __main__ - Step 25253: {'lr': 0.00047016181439441126, 'samples': 4848576, 'steps': 25252, 'loss/train': 1.1313468217849731} 08/30/2021 17:42:37 - INFO - __main__ - Step 25254: {'lr': 0.000470159300155129, 'samples': 4848768, 'steps': 25253, 'loss/train': 1.4647761583328247} 08/30/2021 17:42:39 - INFO - __main__ - Step 25255: {'lr': 0.00047015678581664635, 'samples': 4848960, 'steps': 25254, 'loss/train': 1.358678936958313} 08/30/2021 17:42:39 - INFO - __main__ - Step 25256: {'lr': 0.00047015427137896446, 'samples': 4849152, 'steps': 25255, 'loss/train': 1.532971978187561} 08/30/2021 17:42:40 - INFO - __main__ - Step 25257: {'lr': 0.0004701517568420844, 'samples': 4849344, 'steps': 25256, 'loss/train': 1.8707044124603271} 08/30/2021 17:42:40 - INFO - __main__ - Step 25258: {'lr': 0.0004701492422060074, 'samples': 4849536, 'steps': 25257, 'loss/train': 1.8581136465072632} 08/30/2021 17:42:40 - INFO - __main__ - Step 25259: {'lr': 0.0004701467274707346, 'samples': 4849728, 'steps': 25258, 'loss/train': 1.7593551874160767} 08/30/2021 17:42:42 - INFO - __main__ - Step 25260: {'lr': 0.0004701442126362671, 'samples': 4849920, 'steps': 25259, 'loss/train': 1.5137451887130737} 08/30/2021 17:42:42 - INFO - __main__ - Step 25261: {'lr': 0.0004701416977026059, 'samples': 4850112, 'steps': 25260, 'loss/train': 1.8200294971466064} 08/30/2021 17:42:43 - INFO - __main__ - Step 25262: {'lr': 0.0004701391826697523, 'samples': 4850304, 'steps': 25261, 'loss/train': 1.3076450824737549} 08/30/2021 17:42:43 - INFO - __main__ - Step 25263: {'lr': 0.00047013666753770736, 'samples': 4850496, 'steps': 25262, 'loss/train': 1.9197431802749634} 08/30/2021 17:42:43 - INFO - __main__ - Step 25264: {'lr': 0.00047013415230647227, 'samples': 4850688, 'steps': 25263, 'loss/train': 1.3357831239700317} 08/30/2021 17:42:44 - INFO - __main__ - Step 25265: {'lr': 0.0004701316369760481, 'samples': 4850880, 'steps': 25264, 'loss/train': 1.7137293815612793} 08/30/2021 17:42:45 - INFO - __main__ - Step 25266: {'lr': 0.00047012912154643607, 'samples': 4851072, 'steps': 25265, 'loss/train': 1.2234370708465576} 08/30/2021 17:42:46 - INFO - __main__ - Step 25267: {'lr': 0.0004701266060176372, 'samples': 4851264, 'steps': 25266, 'loss/train': 1.6347157955169678} 08/30/2021 17:42:46 - INFO - __main__ - Step 25268: {'lr': 0.00047012409038965267, 'samples': 4851456, 'steps': 25267, 'loss/train': 0.9743822813034058} 08/30/2021 17:42:47 - INFO - __main__ - Step 25269: {'lr': 0.0004701215746624836, 'samples': 4851648, 'steps': 25268, 'loss/train': 1.2258555889129639} 08/30/2021 17:42:47 - INFO - __main__ - Step 25270: {'lr': 0.0004701190588361312, 'samples': 4851840, 'steps': 25269, 'loss/train': 1.1441996097564697} 08/30/2021 17:42:48 - INFO - __main__ - Step 25271: {'lr': 0.0004701165429105966, 'samples': 4852032, 'steps': 25270, 'loss/train': 1.479071021080017} 08/30/2021 17:42:49 - INFO - __main__ - Step 25272: {'lr': 0.0004701140268858808, 'samples': 4852224, 'steps': 25271, 'loss/train': 1.2729097604751587} 08/30/2021 17:42:49 - INFO - __main__ - Step 25273: {'lr': 0.000470111510761985, 'samples': 4852416, 'steps': 25272, 'loss/train': 1.414404273033142} 08/30/2021 17:42:49 - INFO - __main__ - Step 25274: {'lr': 0.0004701089945389104, 'samples': 4852608, 'steps': 25273, 'loss/train': 1.2719674110412598} 08/30/2021 17:42:50 - INFO - __main__ - Step 25275: {'lr': 0.00047010647821665803, 'samples': 4852800, 'steps': 25274, 'loss/train': 1.6211355924606323} 08/30/2021 17:42:52 - INFO - __main__ - Step 25276: {'lr': 0.0004701039617952291, 'samples': 4852992, 'steps': 25275, 'loss/train': 1.2120165824890137} 08/30/2021 17:42:52 - INFO - __main__ - Step 25277: {'lr': 0.00047010144527462474, 'samples': 4853184, 'steps': 25276, 'loss/train': 1.619185209274292} 08/30/2021 17:42:53 - INFO - __main__ - Step 25278: {'lr': 0.00047009892865484607, 'samples': 4853376, 'steps': 25277, 'loss/train': 1.2005964517593384} 08/30/2021 17:42:53 - INFO - __main__ - Step 25279: {'lr': 0.00047009641193589423, 'samples': 4853568, 'steps': 25278, 'loss/train': 1.9050300121307373} 08/30/2021 17:42:53 - INFO - __main__ - Step 25280: {'lr': 0.00047009389511777036, 'samples': 4853760, 'steps': 25279, 'loss/train': 1.250523328781128} 08/30/2021 17:42:54 - INFO - __main__ - Step 25281: {'lr': 0.0004700913782004755, 'samples': 4853952, 'steps': 25280, 'loss/train': 0.06701329350471497} 08/30/2021 17:42:56 - INFO - __main__ - Step 25282: {'lr': 0.00047008886118401084, 'samples': 4854144, 'steps': 25281, 'loss/train': 0.11463990062475204} 08/30/2021 17:42:57 - INFO - __main__ - Step 25283: {'lr': 0.0004700863440683776, 'samples': 4854336, 'steps': 25282, 'loss/train': 1.488193392753601} 08/30/2021 17:42:57 - INFO - __main__ - Step 25284: {'lr': 0.00047008382685357686, 'samples': 4854528, 'steps': 25283, 'loss/train': 1.741093635559082} 08/30/2021 17:42:58 - INFO - __main__ - Step 25285: {'lr': 0.0004700813095396098, 'samples': 4854720, 'steps': 25284, 'loss/train': 0.9684827327728271} 08/30/2021 17:42:58 - INFO - __main__ - Step 25286: {'lr': 0.00047007879212647744, 'samples': 4854912, 'steps': 25285, 'loss/train': 2.1591384410858154} 08/30/2021 17:42:58 - INFO - __main__ - Step 25287: {'lr': 0.0004700762746141809, 'samples': 4855104, 'steps': 25286, 'loss/train': 0.5560943484306335} 08/30/2021 17:42:59 - INFO - __main__ - Step 25288: {'lr': 0.0004700737570027214, 'samples': 4855296, 'steps': 25287, 'loss/train': 0.5318044424057007} 08/30/2021 17:43:00 - INFO - __main__ - Step 25289: {'lr': 0.00047007123929210015, 'samples': 4855488, 'steps': 25288, 'loss/train': 1.8834632635116577} 08/30/2021 17:43:01 - INFO - __main__ - Step 25290: {'lr': 0.00047006872148231814, 'samples': 4855680, 'steps': 25289, 'loss/train': 1.5034270286560059} 08/30/2021 17:43:01 - INFO - __main__ - Step 25291: {'lr': 0.0004700662035733766, 'samples': 4855872, 'steps': 25290, 'loss/train': 1.0896543264389038} 08/30/2021 17:43:01 - INFO - __main__ - Step 25292: {'lr': 0.0004700636855652766, 'samples': 4856064, 'steps': 25291, 'loss/train': 1.7092068195343018} 08/30/2021 17:43:02 - INFO - __main__ - Step 25293: {'lr': 0.0004700611674580193, 'samples': 4856256, 'steps': 25292, 'loss/train': 1.38180410861969} 08/30/2021 17:43:03 - INFO - __main__ - Step 25294: {'lr': 0.0004700586492516058, 'samples': 4856448, 'steps': 25293, 'loss/train': 1.4817906618118286} 08/30/2021 17:43:04 - INFO - __main__ - Step 25295: {'lr': 0.00047005613094603727, 'samples': 4856640, 'steps': 25294, 'loss/train': 1.761993169784546} 08/30/2021 17:43:04 - INFO - __main__ - Step 25296: {'lr': 0.0004700536125413149, 'samples': 4856832, 'steps': 25295, 'loss/train': 1.5468003749847412} 08/30/2021 17:43:04 - INFO - __main__ - Step 25297: {'lr': 0.00047005109403743976, 'samples': 4857024, 'steps': 25296, 'loss/train': 1.3205429315567017} 08/30/2021 17:43:05 - INFO - __main__ - Step 25298: {'lr': 0.00047004857543441294, 'samples': 4857216, 'steps': 25297, 'loss/train': 1.649469256401062} 08/30/2021 17:43:06 - INFO - __main__ - Step 25299: {'lr': 0.00047004605673223567, 'samples': 4857408, 'steps': 25298, 'loss/train': 1.7398124933242798} 08/30/2021 17:43:07 - INFO - __main__ - Step 25300: {'lr': 0.00047004353793090903, 'samples': 4857600, 'steps': 25299, 'loss/train': 1.5071388483047485} 08/30/2021 17:43:07 - INFO - __main__ - Step 25301: {'lr': 0.00047004101903043416, 'samples': 4857792, 'steps': 25300, 'loss/train': 2.0160562992095947} 08/30/2021 17:43:07 - INFO - __main__ - Step 25302: {'lr': 0.00047003850003081215, 'samples': 4857984, 'steps': 25301, 'loss/train': 1.5995603799819946} 08/30/2021 17:43:08 - INFO - __main__ - Step 25303: {'lr': 0.0004700359809320443, 'samples': 4858176, 'steps': 25302, 'loss/train': 1.3620502948760986} 08/30/2021 17:43:09 - INFO - __main__ - Step 25304: {'lr': 0.0004700334617341316, 'samples': 4858368, 'steps': 25303, 'loss/train': 1.541378378868103} 08/30/2021 17:43:10 - INFO - __main__ - Step 25305: {'lr': 0.0004700309424370752, 'samples': 4858560, 'steps': 25304, 'loss/train': 1.3634676933288574} 08/30/2021 17:43:10 - INFO - __main__ - Step 25306: {'lr': 0.00047002842304087625, 'samples': 4858752, 'steps': 25305, 'loss/train': 1.8207916021347046} 08/30/2021 17:43:10 - INFO - __main__ - Step 25307: {'lr': 0.00047002590354553586, 'samples': 4858944, 'steps': 25306, 'loss/train': 1.3307744264602661} 08/30/2021 17:43:11 - INFO - __main__ - Step 25308: {'lr': 0.00047002338395105527, 'samples': 4859136, 'steps': 25307, 'loss/train': 1.7076677083969116} 08/30/2021 17:43:12 - INFO - __main__ - Step 25309: {'lr': 0.00047002086425743545, 'samples': 4859328, 'steps': 25308, 'loss/train': 1.6849370002746582} 08/30/2021 17:43:13 - INFO - __main__ - Step 25310: {'lr': 0.0004700183444646776, 'samples': 4859520, 'steps': 25309, 'loss/train': 1.9664829969406128} 08/30/2021 17:43:13 - INFO - __main__ - Step 25311: {'lr': 0.000470015824572783, 'samples': 4859712, 'steps': 25310, 'loss/train': 1.1894611120224} 08/30/2021 17:43:13 - INFO - __main__ - Step 25312: {'lr': 0.00047001330458175264, 'samples': 4859904, 'steps': 25311, 'loss/train': 1.2179572582244873} 08/30/2021 17:43:14 - INFO - __main__ - Step 25313: {'lr': 0.0004700107844915876, 'samples': 4860096, 'steps': 25312, 'loss/train': 1.4157882928848267} 08/30/2021 17:43:15 - INFO - __main__ - Step 25314: {'lr': 0.00047000826430228915, 'samples': 4860288, 'steps': 25313, 'loss/train': 1.395578145980835} 08/30/2021 17:43:16 - INFO - __main__ - Step 25315: {'lr': 0.00047000574401385835, 'samples': 4860480, 'steps': 25314, 'loss/train': 1.1564863920211792} 08/30/2021 17:43:16 - INFO - __main__ - Step 25316: {'lr': 0.0004700032236262964, 'samples': 4860672, 'steps': 25315, 'loss/train': 1.2295942306518555} 08/30/2021 17:43:16 - INFO - __main__ - Step 25317: {'lr': 0.00047000070313960436, 'samples': 4860864, 'steps': 25316, 'loss/train': 1.541870355606079} 08/30/2021 17:43:17 - INFO - __main__ - Step 25318: {'lr': 0.00046999818255378335, 'samples': 4861056, 'steps': 25317, 'loss/train': 1.2594361305236816} 08/30/2021 17:43:17 - INFO - __main__ - Step 25319: {'lr': 0.00046999566186883466, 'samples': 4861248, 'steps': 25318, 'loss/train': 1.2627118825912476} 08/30/2021 17:43:19 - INFO - __main__ - Step 25320: {'lr': 0.0004699931410847592, 'samples': 4861440, 'steps': 25319, 'loss/train': 2.373678684234619} 08/30/2021 17:43:19 - INFO - __main__ - Step 25321: {'lr': 0.00046999062020155834, 'samples': 4861632, 'steps': 25320, 'loss/train': 1.7835915088653564} 08/30/2021 17:43:19 - INFO - __main__ - Step 25322: {'lr': 0.00046998809921923305, 'samples': 4861824, 'steps': 25321, 'loss/train': 1.5494893789291382} 08/30/2021 17:43:20 - INFO - __main__ - Step 25323: {'lr': 0.0004699855781377845, 'samples': 4862016, 'steps': 25322, 'loss/train': 1.909134030342102} 08/30/2021 17:43:20 - INFO - __main__ - Step 25324: {'lr': 0.0004699830569572139, 'samples': 4862208, 'steps': 25323, 'loss/train': 1.4210063219070435} 08/30/2021 17:43:22 - INFO - __main__ - Step 25325: {'lr': 0.00046998053567752225, 'samples': 4862400, 'steps': 25324, 'loss/train': 1.3654412031173706} 08/30/2021 17:43:22 - INFO - __main__ - Step 25326: {'lr': 0.0004699780142987108, 'samples': 4862592, 'steps': 25325, 'loss/train': 1.767876386642456} 08/30/2021 17:43:23 - INFO - __main__ - Step 25327: {'lr': 0.0004699754928207807, 'samples': 4862784, 'steps': 25326, 'loss/train': 1.529049038887024} 08/30/2021 17:43:23 - INFO - __main__ - Step 25328: {'lr': 0.00046997297124373293, 'samples': 4862976, 'steps': 25327, 'loss/train': 1.7410838603973389} 08/30/2021 17:43:23 - INFO - __main__ - Step 25329: {'lr': 0.00046997044956756883, 'samples': 4863168, 'steps': 25328, 'loss/train': 2.0541467666625977} 08/30/2021 17:43:25 - INFO - __main__ - Step 25330: {'lr': 0.00046996792779228935, 'samples': 4863360, 'steps': 25329, 'loss/train': 1.0298115015029907} 08/30/2021 17:43:25 - INFO - __main__ - Step 25331: {'lr': 0.00046996540591789584, 'samples': 4863552, 'steps': 25330, 'loss/train': 1.5683554410934448} 08/30/2021 17:43:26 - INFO - __main__ - Step 25332: {'lr': 0.00046996288394438924, 'samples': 4863744, 'steps': 25331, 'loss/train': 1.9218753576278687} 08/30/2021 17:43:26 - INFO - __main__ - Step 25333: {'lr': 0.00046996036187177073, 'samples': 4863936, 'steps': 25332, 'loss/train': 1.5016952753067017} 08/30/2021 17:43:26 - INFO - __main__ - Step 25334: {'lr': 0.0004699578397000415, 'samples': 4864128, 'steps': 25333, 'loss/train': 1.7984638214111328} 08/30/2021 17:43:27 - INFO - __main__ - Step 25335: {'lr': 0.00046995531742920264, 'samples': 4864320, 'steps': 25334, 'loss/train': 1.4689041376113892} 08/30/2021 17:43:28 - INFO - __main__ - Step 25336: {'lr': 0.00046995279505925535, 'samples': 4864512, 'steps': 25335, 'loss/train': 2.0290894508361816} 08/30/2021 17:43:29 - INFO - __main__ - Step 25337: {'lr': 0.00046995027259020075, 'samples': 4864704, 'steps': 25336, 'loss/train': 0.7744262218475342} 08/30/2021 17:43:29 - INFO - __main__ - Step 25338: {'lr': 0.00046994775002203994, 'samples': 4864896, 'steps': 25337, 'loss/train': 1.737314224243164} 08/30/2021 17:43:29 - INFO - __main__ - Step 25339: {'lr': 0.000469945227354774, 'samples': 4865088, 'steps': 25338, 'loss/train': 1.1786948442459106} 08/30/2021 17:43:30 - INFO - __main__ - Step 25340: {'lr': 0.00046994270458840416, 'samples': 4865280, 'steps': 25339, 'loss/train': 1.2766237258911133} 08/30/2021 17:43:32 - INFO - __main__ - Step 25341: {'lr': 0.0004699401817229316, 'samples': 4865472, 'steps': 25340, 'loss/train': 5.965412139892578} 08/30/2021 17:43:32 - INFO - __main__ - Step 25342: {'lr': 0.0004699376587583573, 'samples': 4865664, 'steps': 25341, 'loss/train': 1.4611304998397827} 08/30/2021 17:43:33 - INFO - __main__ - Step 25343: {'lr': 0.0004699351356946825, 'samples': 4865856, 'steps': 25342, 'loss/train': 1.7490977048873901} 08/30/2021 17:43:33 - INFO - __main__ - Step 25344: {'lr': 0.00046993261253190833, 'samples': 4866048, 'steps': 25343, 'loss/train': 0.5217673182487488} 08/30/2021 17:43:33 - INFO - __main__ - Step 25345: {'lr': 0.000469930089270036, 'samples': 4866240, 'steps': 25344, 'loss/train': 1.523060917854309} 08/30/2021 17:43:35 - INFO - __main__ - Step 25346: {'lr': 0.0004699275659090665, 'samples': 4866432, 'steps': 25345, 'loss/train': 1.999556064605713} 08/30/2021 17:43:35 - INFO - __main__ - Step 25347: {'lr': 0.000469925042449001, 'samples': 4866624, 'steps': 25346, 'loss/train': 1.2873411178588867} 08/30/2021 17:43:35 - INFO - __main__ - Step 25348: {'lr': 0.0004699225188898407, 'samples': 4866816, 'steps': 25347, 'loss/train': 1.5357632637023926} 08/30/2021 17:43:36 - INFO - __main__ - Step 25349: {'lr': 0.00046991999523158666, 'samples': 4867008, 'steps': 25348, 'loss/train': 2.1388795375823975} 08/30/2021 17:43:36 - INFO - __main__ - Step 25350: {'lr': 0.0004699174714742401, 'samples': 4867200, 'steps': 25349, 'loss/train': 1.9474326372146606} 08/30/2021 17:43:38 - INFO - __main__ - Step 25351: {'lr': 0.0004699149476178022, 'samples': 4867392, 'steps': 25350, 'loss/train': 1.4059033393859863} 08/30/2021 17:43:38 - INFO - __main__ - Step 25352: {'lr': 0.00046991242366227395, 'samples': 4867584, 'steps': 25351, 'loss/train': 1.1270959377288818} 08/30/2021 17:43:39 - INFO - __main__ - Step 25353: {'lr': 0.0004699098996076565, 'samples': 4867776, 'steps': 25352, 'loss/train': 1.432145595550537} 08/30/2021 17:43:39 - INFO - __main__ - Step 25354: {'lr': 0.0004699073754539511, 'samples': 4867968, 'steps': 25353, 'loss/train': 3.1782290935516357} 08/30/2021 17:43:39 - INFO - __main__ - Step 25355: {'lr': 0.0004699048512011588, 'samples': 4868160, 'steps': 25354, 'loss/train': 1.304602026939392} 08/30/2021 17:43:40 - INFO - __main__ - Step 25356: {'lr': 0.0004699023268492808, 'samples': 4868352, 'steps': 25355, 'loss/train': 1.4980871677398682} 08/30/2021 17:43:41 - INFO - __main__ - Step 25357: {'lr': 0.0004698998023983182, 'samples': 4868544, 'steps': 25356, 'loss/train': 1.8318673372268677} 08/30/2021 17:43:42 - INFO - __main__ - Step 25358: {'lr': 0.0004698972778482722, 'samples': 4868736, 'steps': 25357, 'loss/train': 0.9058358073234558} 08/30/2021 17:43:42 - INFO - __main__ - Step 25359: {'lr': 0.0004698947531991438, 'samples': 4868928, 'steps': 25358, 'loss/train': 2.269063711166382} 08/30/2021 17:43:42 - INFO - __main__ - Step 25360: {'lr': 0.0004698922284509342, 'samples': 4869120, 'steps': 25359, 'loss/train': 1.332290768623352} 08/30/2021 17:43:43 - INFO - __main__ - Step 25361: {'lr': 0.00046988970360364456, 'samples': 4869312, 'steps': 25360, 'loss/train': 0.07109788060188293} 08/30/2021 17:43:44 - INFO - __main__ - Step 25362: {'lr': 0.0004698871786572761, 'samples': 4869504, 'steps': 25361, 'loss/train': 1.6190969944000244} 08/30/2021 17:43:45 - INFO - __main__ - Step 25363: {'lr': 0.0004698846536118298, 'samples': 4869696, 'steps': 25362, 'loss/train': 1.6887255907058716} 08/30/2021 17:43:45 - INFO - __main__ - Step 25364: {'lr': 0.00046988212846730686, 'samples': 4869888, 'steps': 25363, 'loss/train': 0.9800006747245789} 08/30/2021 17:43:46 - INFO - __main__ - Step 25365: {'lr': 0.0004698796032237085, 'samples': 4870080, 'steps': 25364, 'loss/train': 1.5346888303756714} 08/30/2021 17:43:46 - INFO - __main__ - Step 25366: {'lr': 0.0004698770778810357, 'samples': 4870272, 'steps': 25365, 'loss/train': 1.5946332216262817} 08/30/2021 17:43:47 - INFO - __main__ - Step 25367: {'lr': 0.00046987455243928974, 'samples': 4870464, 'steps': 25366, 'loss/train': 0.903740644454956} 08/30/2021 17:43:48 - INFO - __main__ - Step 25368: {'lr': 0.00046987202689847165, 'samples': 4870656, 'steps': 25367, 'loss/train': 1.2486778497695923} 08/30/2021 17:43:48 - INFO - __main__ - Step 25369: {'lr': 0.00046986950125858264, 'samples': 4870848, 'steps': 25368, 'loss/train': 0.8976453542709351} 08/30/2021 17:43:48 - INFO - __main__ - Step 25370: {'lr': 0.0004698669755196239, 'samples': 4871040, 'steps': 25369, 'loss/train': 0.5826310515403748} 08/30/2021 17:43:49 - INFO - __main__ - Step 25371: {'lr': 0.0004698644496815964, 'samples': 4871232, 'steps': 25370, 'loss/train': 1.3482331037521362} 08/30/2021 17:43:49 - INFO - __main__ - Step 25372: {'lr': 0.0004698619237445013, 'samples': 4871424, 'steps': 25371, 'loss/train': 1.227567195892334} 08/30/2021 17:43:51 - INFO - __main__ - Step 25373: {'lr': 0.00046985939770834, 'samples': 4871616, 'steps': 25372, 'loss/train': 1.7992637157440186} 08/30/2021 17:43:51 - INFO - __main__ - Step 25374: {'lr': 0.0004698568715731133, 'samples': 4871808, 'steps': 25373, 'loss/train': 1.4941823482513428} 08/30/2021 17:43:51 - INFO - __main__ - Step 25375: {'lr': 0.00046985434533882255, 'samples': 4872000, 'steps': 25374, 'loss/train': 1.5480879545211792} 08/30/2021 17:43:52 - INFO - __main__ - Step 25376: {'lr': 0.00046985181900546883, 'samples': 4872192, 'steps': 25375, 'loss/train': 1.8641072511672974} 08/30/2021 17:43:52 - INFO - __main__ - Step 25377: {'lr': 0.0004698492925730532, 'samples': 4872384, 'steps': 25376, 'loss/train': 0.9216536283493042} 08/30/2021 17:43:54 - INFO - __main__ - Step 25378: {'lr': 0.00046984676604157696, 'samples': 4872576, 'steps': 25377, 'loss/train': 1.636277198791504} 08/30/2021 17:43:54 - INFO - __main__ - Step 25379: {'lr': 0.0004698442394110411, 'samples': 4872768, 'steps': 25378, 'loss/train': 1.1136679649353027} 08/30/2021 17:43:54 - INFO - __main__ - Step 25380: {'lr': 0.0004698417126814468, 'samples': 4872960, 'steps': 25379, 'loss/train': 1.6927865743637085} 08/30/2021 17:43:55 - INFO - __main__ - Step 25381: {'lr': 0.0004698391858527953, 'samples': 4873152, 'steps': 25380, 'loss/train': 1.4523926973342896} 08/30/2021 17:43:55 - INFO - __main__ - Step 25382: {'lr': 0.0004698366589250876, 'samples': 4873344, 'steps': 25381, 'loss/train': 0.926530122756958} 08/30/2021 17:43:57 - INFO - __main__ - Step 25383: {'lr': 0.0004698341318983249, 'samples': 4873536, 'steps': 25382, 'loss/train': 1.1641733646392822} 08/30/2021 17:43:57 - INFO - __main__ - Step 25384: {'lr': 0.00046983160477250837, 'samples': 4873728, 'steps': 25383, 'loss/train': 1.6348788738250732} 08/30/2021 17:43:57 - INFO - __main__ - Step 25385: {'lr': 0.00046982907754763905, 'samples': 4873920, 'steps': 25384, 'loss/train': 1.8218257427215576} 08/30/2021 17:43:58 - INFO - __main__ - Step 25386: {'lr': 0.0004698265502237182, 'samples': 4874112, 'steps': 25385, 'loss/train': 1.2216225862503052} 08/30/2021 17:43:58 - INFO - __main__ - Step 25387: {'lr': 0.0004698240228007469, 'samples': 4874304, 'steps': 25386, 'loss/train': 1.2502230405807495} 08/30/2021 17:44:00 - INFO - __main__ - Step 25388: {'lr': 0.0004698214952787262, 'samples': 4874496, 'steps': 25387, 'loss/train': 1.3003475666046143} 08/30/2021 17:44:00 - INFO - __main__ - Step 25389: {'lr': 0.0004698189676576574, 'samples': 4874688, 'steps': 25388, 'loss/train': 1.8169384002685547} 08/30/2021 17:44:00 - INFO - __main__ - Step 25390: {'lr': 0.00046981643993754155, 'samples': 4874880, 'steps': 25389, 'loss/train': 1.12261962890625} 08/30/2021 17:44:01 - INFO - __main__ - Step 25391: {'lr': 0.0004698139121183798, 'samples': 4875072, 'steps': 25390, 'loss/train': 0.12249408662319183} 08/30/2021 17:44:01 - INFO - __main__ - Step 25392: {'lr': 0.00046981138420017335, 'samples': 4875264, 'steps': 25391, 'loss/train': 1.4036651849746704} 08/30/2021 17:44:03 - INFO - __main__ - Step 25393: {'lr': 0.00046980885618292317, 'samples': 4875456, 'steps': 25392, 'loss/train': 1.4431445598602295} 08/30/2021 17:44:04 - INFO - __main__ - Step 25394: {'lr': 0.0004698063280666306, 'samples': 4875648, 'steps': 25393, 'loss/train': 1.2885441780090332} 08/30/2021 17:44:04 - INFO - __main__ - Step 25395: {'lr': 0.0004698037998512966, 'samples': 4875840, 'steps': 25394, 'loss/train': 1.0415525436401367} 08/30/2021 17:44:04 - INFO - __main__ - Step 25396: {'lr': 0.00046980127153692256, 'samples': 4876032, 'steps': 25395, 'loss/train': 0.9374186992645264} 08/30/2021 17:44:05 - INFO - __main__ - Step 25397: {'lr': 0.00046979874312350935, 'samples': 4876224, 'steps': 25396, 'loss/train': 1.3083512783050537} 08/30/2021 17:44:06 - INFO - __main__ - Step 25398: {'lr': 0.00046979621461105817, 'samples': 4876416, 'steps': 25397, 'loss/train': 2.505147933959961} 08/30/2021 17:44:07 - INFO - __main__ - Step 25399: {'lr': 0.0004697936859995703, 'samples': 4876608, 'steps': 25398, 'loss/train': 1.09427809715271} 08/30/2021 17:44:07 - INFO - __main__ - Step 25400: {'lr': 0.00046979115728904675, 'samples': 4876800, 'steps': 25399, 'loss/train': 1.5842044353485107} 08/30/2021 17:44:07 - INFO - __main__ - Step 25401: {'lr': 0.0004697886284794887, 'samples': 4876992, 'steps': 25400, 'loss/train': 1.6713145971298218} 08/30/2021 17:44:08 - INFO - __main__ - Step 25402: {'lr': 0.00046978609957089724, 'samples': 4877184, 'steps': 25401, 'loss/train': 1.7712210416793823} 08/30/2021 17:44:09 - INFO - __main__ - Step 25403: {'lr': 0.0004697835705632736, 'samples': 4877376, 'steps': 25402, 'loss/train': 1.5067243576049805} 08/30/2021 17:44:10 - INFO - __main__ - Step 25404: {'lr': 0.00046978104145661885, 'samples': 4877568, 'steps': 25403, 'loss/train': 1.6991065740585327} 08/30/2021 17:44:10 - INFO - __main__ - Step 25405: {'lr': 0.00046977851225093423, 'samples': 4877760, 'steps': 25404, 'loss/train': 1.6329655647277832} 08/30/2021 17:44:10 - INFO - __main__ - Step 25406: {'lr': 0.0004697759829462207, 'samples': 4877952, 'steps': 25405, 'loss/train': 0.882095217704773} 08/30/2021 17:44:11 - INFO - __main__ - Step 25407: {'lr': 0.0004697734535424796, 'samples': 4878144, 'steps': 25406, 'loss/train': 1.3212653398513794} 08/30/2021 17:44:12 - INFO - __main__ - Step 25408: {'lr': 0.0004697709240397119, 'samples': 4878336, 'steps': 25407, 'loss/train': 1.644166111946106} 08/30/2021 17:44:13 - INFO - __main__ - Step 25409: {'lr': 0.00046976839443791887, 'samples': 4878528, 'steps': 25408, 'loss/train': 1.7067017555236816} 08/30/2021 17:44:13 - INFO - __main__ - Step 25410: {'lr': 0.00046976586473710156, 'samples': 4878720, 'steps': 25409, 'loss/train': 1.8410892486572266} 08/30/2021 17:44:13 - INFO - __main__ - Step 25411: {'lr': 0.0004697633349372611, 'samples': 4878912, 'steps': 25410, 'loss/train': 1.5275639295578003} 08/30/2021 17:44:14 - INFO - __main__ - Step 25412: {'lr': 0.00046976080503839874, 'samples': 4879104, 'steps': 25411, 'loss/train': 1.1855192184448242} 08/30/2021 17:44:14 - INFO - __main__ - Step 25413: {'lr': 0.0004697582750405155, 'samples': 4879296, 'steps': 25412, 'loss/train': 1.9466181993484497} 08/30/2021 17:44:15 - INFO - __main__ - Step 25414: {'lr': 0.00046975574494361263, 'samples': 4879488, 'steps': 25413, 'loss/train': 1.5716698169708252} 08/30/2021 17:44:16 - INFO - __main__ - Step 25415: {'lr': 0.00046975321474769115, 'samples': 4879680, 'steps': 25414, 'loss/train': 1.5435230731964111} 08/30/2021 17:44:16 - INFO - __main__ - Step 25416: {'lr': 0.0004697506844527523, 'samples': 4879872, 'steps': 25415, 'loss/train': 1.956175446510315} 08/30/2021 17:44:17 - INFO - __main__ - Step 25417: {'lr': 0.0004697481540587972, 'samples': 4880064, 'steps': 25416, 'loss/train': 1.6351418495178223} 08/30/2021 17:44:18 - INFO - __main__ - Step 25418: {'lr': 0.00046974562356582694, 'samples': 4880256, 'steps': 25417, 'loss/train': 1.8114688396453857} 08/30/2021 17:44:19 - INFO - __main__ - Step 25419: {'lr': 0.0004697430929738427, 'samples': 4880448, 'steps': 25418, 'loss/train': 1.5406980514526367} 08/30/2021 17:44:19 - INFO - __main__ - Step 25420: {'lr': 0.0004697405622828456, 'samples': 4880640, 'steps': 25419, 'loss/train': 1.1471892595291138} 08/30/2021 17:44:19 - INFO - __main__ - Step 25421: {'lr': 0.00046973803149283686, 'samples': 4880832, 'steps': 25420, 'loss/train': 1.5557366609573364} 08/30/2021 17:44:20 - INFO - __main__ - Step 25422: {'lr': 0.0004697355006038175, 'samples': 4881024, 'steps': 25421, 'loss/train': 1.213868498802185} 08/30/2021 17:44:20 - INFO - __main__ - Step 25423: {'lr': 0.0004697329696157887, 'samples': 4881216, 'steps': 25422, 'loss/train': 1.227020502090454} 08/30/2021 17:44:22 - INFO - __main__ - Step 25424: {'lr': 0.00046973043852875163, 'samples': 4881408, 'steps': 25423, 'loss/train': 1.4905178546905518} 08/30/2021 17:44:22 - INFO - __main__ - Step 25425: {'lr': 0.00046972790734270745, 'samples': 4881600, 'steps': 25424, 'loss/train': 1.2755528688430786} 08/30/2021 17:44:23 - INFO - __main__ - Step 25426: {'lr': 0.0004697253760576572, 'samples': 4881792, 'steps': 25425, 'loss/train': 0.5819177627563477} 08/30/2021 17:44:23 - INFO - __main__ - Step 25427: {'lr': 0.00046972284467360217, 'samples': 4881984, 'steps': 25426, 'loss/train': 2.251990795135498} 08/30/2021 17:44:23 - INFO - __main__ - Step 25428: {'lr': 0.0004697203131905433, 'samples': 4882176, 'steps': 25427, 'loss/train': 1.4739199876785278} 08/30/2021 17:44:25 - INFO - __main__ - Step 25429: {'lr': 0.00046971778160848196, 'samples': 4882368, 'steps': 25428, 'loss/train': 1.7662568092346191} 08/30/2021 17:44:25 - INFO - __main__ - Step 25430: {'lr': 0.0004697152499274191, 'samples': 4882560, 'steps': 25429, 'loss/train': 1.4754798412322998} 08/30/2021 17:44:26 - INFO - __main__ - Step 25431: {'lr': 0.00046971271814735593, 'samples': 4882752, 'steps': 25430, 'loss/train': 1.8401789665222168} 08/30/2021 17:44:26 - INFO - __main__ - Step 25432: {'lr': 0.0004697101862682936, 'samples': 4882944, 'steps': 25431, 'loss/train': 1.6103200912475586} 08/30/2021 17:44:26 - INFO - __main__ - Step 25433: {'lr': 0.00046970765429023336, 'samples': 4883136, 'steps': 25432, 'loss/train': 1.4708747863769531} 08/30/2021 17:44:27 - INFO - __main__ - Step 25434: {'lr': 0.00046970512221317616, 'samples': 4883328, 'steps': 25433, 'loss/train': 2.0800564289093018} 08/30/2021 17:44:28 - INFO - __main__ - Step 25435: {'lr': 0.00046970259003712323, 'samples': 4883520, 'steps': 25434, 'loss/train': 1.524448275566101} 08/30/2021 17:44:29 - INFO - __main__ - Step 25436: {'lr': 0.00046970005776207575, 'samples': 4883712, 'steps': 25435, 'loss/train': 1.4247024059295654} 08/30/2021 17:44:29 - INFO - __main__ - Step 25437: {'lr': 0.00046969752538803477, 'samples': 4883904, 'steps': 25436, 'loss/train': 1.6538536548614502} 08/30/2021 17:44:29 - INFO - __main__ - Step 25438: {'lr': 0.0004696949929150015, 'samples': 4884096, 'steps': 25437, 'loss/train': 1.7013219594955444} 08/30/2021 17:44:30 - INFO - __main__ - Step 25439: {'lr': 0.00046969246034297697, 'samples': 4884288, 'steps': 25438, 'loss/train': 1.6243163347244263} 08/30/2021 17:44:32 - INFO - __main__ - Step 25440: {'lr': 0.0004696899276719625, 'samples': 4884480, 'steps': 25439, 'loss/train': 1.6684882640838623} 08/30/2021 17:44:32 - INFO - __main__ - Step 25441: {'lr': 0.0004696873949019591, 'samples': 4884672, 'steps': 25440, 'loss/train': 1.020603895187378} 08/30/2021 17:44:32 - INFO - __main__ - Step 25442: {'lr': 0.000469684862032968, 'samples': 4884864, 'steps': 25441, 'loss/train': 1.7380231618881226} 08/30/2021 17:44:33 - INFO - __main__ - Step 25443: {'lr': 0.0004696823290649902, 'samples': 4885056, 'steps': 25442, 'loss/train': 1.3856931924819946} 08/30/2021 17:44:33 - INFO - __main__ - Step 25444: {'lr': 0.000469679795998027, 'samples': 4885248, 'steps': 25443, 'loss/train': 1.4510107040405273} 08/30/2021 17:44:35 - INFO - __main__ - Step 25445: {'lr': 0.00046967726283207945, 'samples': 4885440, 'steps': 25444, 'loss/train': 0.13812634348869324} 08/30/2021 17:44:36 - INFO - __main__ - Step 25446: {'lr': 0.0004696747295671487, 'samples': 4885632, 'steps': 25445, 'loss/train': 2.291543960571289} 08/30/2021 17:44:36 - INFO - __main__ - Step 25447: {'lr': 0.000469672196203236, 'samples': 4885824, 'steps': 25446, 'loss/train': 1.3286209106445312} 08/30/2021 17:44:36 - INFO - __main__ - Step 25448: {'lr': 0.0004696696627403423, 'samples': 4886016, 'steps': 25447, 'loss/train': 1.4469770193099976} 08/30/2021 17:44:37 - INFO - __main__ - Step 25449: {'lr': 0.00046966712917846887, 'samples': 4886208, 'steps': 25448, 'loss/train': 1.811905860900879} 08/30/2021 17:44:38 - INFO - __main__ - Step 25450: {'lr': 0.00046966459551761684, 'samples': 4886400, 'steps': 25449, 'loss/train': 1.3242791891098022} 08/30/2021 17:44:39 - INFO - __main__ - Step 25451: {'lr': 0.00046966206175778723, 'samples': 4886592, 'steps': 25450, 'loss/train': 1.4418113231658936} 08/30/2021 17:44:39 - INFO - __main__ - Step 25452: {'lr': 0.0004696595278989814, 'samples': 4886784, 'steps': 25451, 'loss/train': 0.7630012035369873} 08/30/2021 17:44:39 - INFO - __main__ - Step 25453: {'lr': 0.00046965699394120033, 'samples': 4886976, 'steps': 25452, 'loss/train': 1.5333282947540283} 08/30/2021 17:44:40 - INFO - __main__ - Step 25454: {'lr': 0.0004696544598844452, 'samples': 4887168, 'steps': 25453, 'loss/train': 1.9732431173324585} 08/30/2021 17:44:40 - INFO - __main__ - Step 25455: {'lr': 0.00046965192572871723, 'samples': 4887360, 'steps': 25454, 'loss/train': 2.340667486190796} 08/30/2021 17:44:42 - INFO - __main__ - Step 25456: {'lr': 0.0004696493914740174, 'samples': 4887552, 'steps': 25455, 'loss/train': 1.558553695678711} 08/30/2021 17:44:42 - INFO - __main__ - Step 25457: {'lr': 0.00046964685712034697, 'samples': 4887744, 'steps': 25456, 'loss/train': 1.2132066488265991} 08/30/2021 17:44:42 - INFO - __main__ - Step 25458: {'lr': 0.00046964432266770713, 'samples': 4887936, 'steps': 25457, 'loss/train': 1.4271546602249146} 08/30/2021 17:44:43 - INFO - __main__ - Step 25459: {'lr': 0.0004696417881160989, 'samples': 4888128, 'steps': 25458, 'loss/train': 1.5363397598266602} 08/30/2021 17:44:43 - INFO - __main__ - Step 25460: {'lr': 0.0004696392534655234, 'samples': 4888320, 'steps': 25459, 'loss/train': 1.0493687391281128} 08/30/2021 17:44:45 - INFO - __main__ - Step 25461: {'lr': 0.0004696367187159819, 'samples': 4888512, 'steps': 25460, 'loss/train': 1.2178057432174683} 08/30/2021 17:44:45 - INFO - __main__ - Step 25462: {'lr': 0.00046963418386747547, 'samples': 4888704, 'steps': 25461, 'loss/train': 1.4813568592071533} 08/30/2021 17:44:46 - INFO - __main__ - Step 25463: {'lr': 0.0004696316489200053, 'samples': 4888896, 'steps': 25462, 'loss/train': 1.36184823513031} 08/30/2021 17:44:46 - INFO - __main__ - Step 25464: {'lr': 0.00046962911387357246, 'samples': 4889088, 'steps': 25463, 'loss/train': 1.0938376188278198} 08/30/2021 17:44:46 - INFO - __main__ - Step 25465: {'lr': 0.0004696265787281782, 'samples': 4889280, 'steps': 25464, 'loss/train': 1.818878412246704} 08/30/2021 17:44:48 - INFO - __main__ - Step 25466: {'lr': 0.0004696240434838235, 'samples': 4889472, 'steps': 25465, 'loss/train': 1.3407108783721924} 08/30/2021 17:44:48 - INFO - __main__ - Step 25467: {'lr': 0.00046962150814050963, 'samples': 4889664, 'steps': 25466, 'loss/train': 0.990451455116272} 08/30/2021 17:44:49 - INFO - __main__ - Step 25468: {'lr': 0.0004696189726982377, 'samples': 4889856, 'steps': 25467, 'loss/train': 1.6361366510391235} 08/30/2021 17:44:49 - INFO - __main__ - Step 25469: {'lr': 0.00046961643715700885, 'samples': 4890048, 'steps': 25468, 'loss/train': 1.463179111480713} 08/30/2021 17:44:49 - INFO - __main__ - Step 25470: {'lr': 0.00046961390151682426, 'samples': 4890240, 'steps': 25469, 'loss/train': 2.0250563621520996} 08/30/2021 17:44:51 - INFO - __main__ - Step 25471: {'lr': 0.000469611365777685, 'samples': 4890432, 'steps': 25470, 'loss/train': 1.1111315488815308} 08/30/2021 17:44:51 - INFO - __main__ - Step 25472: {'lr': 0.0004696088299395922, 'samples': 4890624, 'steps': 25471, 'loss/train': 1.9752123355865479} 08/30/2021 17:44:52 - INFO - __main__ - Step 25473: {'lr': 0.0004696062940025471, 'samples': 4890816, 'steps': 25472, 'loss/train': 1.439778447151184} 08/30/2021 17:44:52 - INFO - __main__ - Step 25474: {'lr': 0.0004696037579665509, 'samples': 4891008, 'steps': 25473, 'loss/train': 1.630651593208313} 08/30/2021 17:44:52 - INFO - __main__ - Step 25475: {'lr': 0.00046960122183160446, 'samples': 4891200, 'steps': 25474, 'loss/train': 1.4994152784347534} 08/30/2021 17:44:54 - INFO - __main__ - Step 25476: {'lr': 0.00046959868559770914, 'samples': 4891392, 'steps': 25475, 'loss/train': 0.9759613871574402} 08/30/2021 17:44:54 - INFO - __main__ - Step 25477: {'lr': 0.00046959614926486606, 'samples': 4891584, 'steps': 25476, 'loss/train': 0.8181150555610657} 08/30/2021 17:44:55 - INFO - __main__ - Step 25478: {'lr': 0.00046959361283307636, 'samples': 4891776, 'steps': 25477, 'loss/train': 2.7366108894348145} 08/30/2021 17:44:55 - INFO - __main__ - Step 25479: {'lr': 0.0004695910763023412, 'samples': 4891968, 'steps': 25478, 'loss/train': 1.9911137819290161} 08/30/2021 17:44:55 - INFO - __main__ - Step 25480: {'lr': 0.0004695885396726616, 'samples': 4892160, 'steps': 25479, 'loss/train': 1.0219414234161377} 08/30/2021 17:44:56 - INFO - __main__ - Step 25481: {'lr': 0.00046958600294403887, 'samples': 4892352, 'steps': 25480, 'loss/train': 1.419118046760559} 08/30/2021 17:44:57 - INFO - __main__ - Step 25482: {'lr': 0.000469583466116474, 'samples': 4892544, 'steps': 25481, 'loss/train': 1.3893498182296753} 08/30/2021 17:44:58 - INFO - __main__ - Step 25483: {'lr': 0.00046958092918996823, 'samples': 4892736, 'steps': 25482, 'loss/train': 0.8322604298591614} 08/30/2021 17:44:58 - INFO - __main__ - Step 25484: {'lr': 0.0004695783921645227, 'samples': 4892928, 'steps': 25483, 'loss/train': 2.1924386024475098} 08/30/2021 17:44:59 - INFO - __main__ - Step 25485: {'lr': 0.00046957585504013853, 'samples': 4893120, 'steps': 25484, 'loss/train': 1.9128268957138062} 08/30/2021 17:44:59 - INFO - __main__ - Step 25486: {'lr': 0.0004695733178168169, 'samples': 4893312, 'steps': 25485, 'loss/train': 1.4193248748779297} 08/30/2021 17:45:00 - INFO - __main__ - Step 25487: {'lr': 0.00046957078049455895, 'samples': 4893504, 'steps': 25486, 'loss/train': 0.7644988894462585} 08/30/2021 17:45:01 - INFO - __main__ - Step 25488: {'lr': 0.00046956824307336565, 'samples': 4893696, 'steps': 25487, 'loss/train': 1.4632740020751953} 08/30/2021 17:45:01 - INFO - __main__ - Step 25489: {'lr': 0.0004695657055532384, 'samples': 4893888, 'steps': 25488, 'loss/train': 1.8015514612197876} 08/30/2021 17:45:02 - INFO - __main__ - Step 25490: {'lr': 0.0004695631679341782, 'samples': 4894080, 'steps': 25489, 'loss/train': 1.416368842124939} 08/30/2021 17:45:02 - INFO - __main__ - Step 25491: {'lr': 0.0004695606302161862, 'samples': 4894272, 'steps': 25490, 'loss/train': 1.3531547784805298} 08/30/2021 17:45:04 - INFO - __main__ - Step 25492: {'lr': 0.0004695580923992636, 'samples': 4894464, 'steps': 25491, 'loss/train': 1.4158116579055786} 08/30/2021 17:45:04 - INFO - __main__ - Step 25493: {'lr': 0.0004695555544834116, 'samples': 4894656, 'steps': 25492, 'loss/train': 1.2660306692123413} 08/30/2021 17:45:04 - INFO - __main__ - Step 25494: {'lr': 0.00046955301646863114, 'samples': 4894848, 'steps': 25493, 'loss/train': 1.0336216688156128} 08/30/2021 17:45:05 - INFO - __main__ - Step 25495: {'lr': 0.0004695504783549235, 'samples': 4895040, 'steps': 25494, 'loss/train': 1.3519583940505981} 08/30/2021 17:45:05 - INFO - __main__ - Step 25496: {'lr': 0.0004695479401422898, 'samples': 4895232, 'steps': 25495, 'loss/train': 1.8910647630691528} 08/30/2021 17:45:07 - INFO - __main__ - Step 25497: {'lr': 0.0004695454018307312, 'samples': 4895424, 'steps': 25496, 'loss/train': 1.2742998600006104} 08/30/2021 17:45:08 - INFO - __main__ - Step 25498: {'lr': 0.0004695428634202488, 'samples': 4895616, 'steps': 25497, 'loss/train': 1.496669888496399} 08/30/2021 17:45:08 - INFO - __main__ - Step 25499: {'lr': 0.0004695403249108438, 'samples': 4895808, 'steps': 25498, 'loss/train': 1.51729416847229} 08/30/2021 17:45:08 - INFO - __main__ - Step 25500: {'lr': 0.0004695377863025173, 'samples': 4896000, 'steps': 25499, 'loss/train': 0.8094951510429382} 08/30/2021 17:45:09 - INFO - __main__ - Step 25501: {'lr': 0.00046953524759527055, 'samples': 4896192, 'steps': 25500, 'loss/train': 1.338602900505066} 08/30/2021 17:45:10 - INFO - __main__ - Step 25502: {'lr': 0.0004695327087891045, 'samples': 4896384, 'steps': 25501, 'loss/train': 0.6852303147315979} 08/30/2021 17:45:11 - INFO - __main__ - Step 25503: {'lr': 0.00046953016988402044, 'samples': 4896576, 'steps': 25502, 'loss/train': 1.0759178400039673} 08/30/2021 17:45:11 - INFO - __main__ - Step 25504: {'lr': 0.0004695276308800194, 'samples': 4896768, 'steps': 25503, 'loss/train': 1.9079062938690186} 08/30/2021 17:45:11 - INFO - __main__ - Step 25505: {'lr': 0.00046952509177710267, 'samples': 4896960, 'steps': 25504, 'loss/train': 1.7435216903686523} 08/30/2021 17:45:12 - INFO - __main__ - Step 25506: {'lr': 0.00046952255257527134, 'samples': 4897152, 'steps': 25505, 'loss/train': 1.421472430229187} 08/30/2021 17:45:12 - INFO - __main__ - Step 25507: {'lr': 0.0004695200132745265, 'samples': 4897344, 'steps': 25506, 'loss/train': 0.0785176008939743} 08/30/2021 17:45:14 - INFO - __main__ - Step 25508: {'lr': 0.00046951747387486933, 'samples': 4897536, 'steps': 25507, 'loss/train': 1.4423470497131348} 08/30/2021 17:45:14 - INFO - __main__ - Step 25509: {'lr': 0.00046951493437630097, 'samples': 4897728, 'steps': 25508, 'loss/train': 1.6386562585830688} 08/30/2021 17:45:15 - INFO - __main__ - Step 25510: {'lr': 0.0004695123947788226, 'samples': 4897920, 'steps': 25509, 'loss/train': 1.7119576930999756} 08/30/2021 17:45:15 - INFO - __main__ - Step 25511: {'lr': 0.0004695098550824353, 'samples': 4898112, 'steps': 25510, 'loss/train': 1.0653730630874634} 08/30/2021 17:45:15 - INFO - __main__ - Step 25512: {'lr': 0.0004695073152871403, 'samples': 4898304, 'steps': 25511, 'loss/train': 1.4548927545547485} 08/30/2021 17:45:17 - INFO - __main__ - Step 25513: {'lr': 0.00046950477539293864, 'samples': 4898496, 'steps': 25512, 'loss/train': 1.291247844696045} 08/30/2021 17:45:17 - INFO - __main__ - Step 25514: {'lr': 0.0004695022353998315, 'samples': 4898688, 'steps': 25513, 'loss/train': 0.42855507135391235} 08/30/2021 17:45:18 - INFO - __main__ - Step 25515: {'lr': 0.0004694996953078201, 'samples': 4898880, 'steps': 25514, 'loss/train': 1.4016495943069458} 08/30/2021 17:45:18 - INFO - __main__ - Step 25516: {'lr': 0.0004694971551169055, 'samples': 4899072, 'steps': 25515, 'loss/train': 2.0857272148132324} 08/30/2021 17:45:18 - INFO - __main__ - Step 25517: {'lr': 0.00046949461482708875, 'samples': 4899264, 'steps': 25516, 'loss/train': 1.2822951078414917} 08/30/2021 17:45:20 - INFO - __main__ - Step 25518: {'lr': 0.0004694920744383713, 'samples': 4899456, 'steps': 25517, 'loss/train': 2.0646729469299316} 08/30/2021 17:45:20 - INFO - __main__ - Step 25519: {'lr': 0.000469489533950754, 'samples': 4899648, 'steps': 25518, 'loss/train': 1.6781165599822998} 08/30/2021 17:45:21 - INFO - __main__ - Step 25520: {'lr': 0.00046948699336423817, 'samples': 4899840, 'steps': 25519, 'loss/train': 2.136193037033081} 08/30/2021 17:45:21 - INFO - __main__ - Step 25521: {'lr': 0.0004694844526788248, 'samples': 4900032, 'steps': 25520, 'loss/train': 1.3668781518936157} 08/30/2021 17:45:21 - INFO - __main__ - Step 25522: {'lr': 0.0004694819118945152, 'samples': 4900224, 'steps': 25521, 'loss/train': 1.7951041460037231} 08/30/2021 17:45:22 - INFO - __main__ - Step 25523: {'lr': 0.00046947937101131046, 'samples': 4900416, 'steps': 25522, 'loss/train': 1.076138973236084} 08/30/2021 17:45:23 - INFO - __main__ - Step 25524: {'lr': 0.0004694768300292116, 'samples': 4900608, 'steps': 25523, 'loss/train': 0.799167811870575} 08/30/2021 17:45:24 - INFO - __main__ - Step 25525: {'lr': 0.0004694742889482199, 'samples': 4900800, 'steps': 25524, 'loss/train': 1.3842781782150269} 08/30/2021 17:45:24 - INFO - __main__ - Step 25526: {'lr': 0.0004694717477683365, 'samples': 4900992, 'steps': 25525, 'loss/train': 1.9871892929077148} 08/30/2021 17:45:25 - INFO - __main__ - Step 25527: {'lr': 0.0004694692064895625, 'samples': 4901184, 'steps': 25526, 'loss/train': 1.5205962657928467} 08/30/2021 17:45:25 - INFO - __main__ - Step 25528: {'lr': 0.0004694666651118991, 'samples': 4901376, 'steps': 25527, 'loss/train': 0.9289355278015137} 08/30/2021 17:45:27 - INFO - __main__ - Step 25529: {'lr': 0.00046946412363534735, 'samples': 4901568, 'steps': 25528, 'loss/train': 1.7455404996871948} 08/30/2021 17:45:28 - INFO - __main__ - Step 25530: {'lr': 0.0004694615820599085, 'samples': 4901760, 'steps': 25529, 'loss/train': 0.96571284532547} 08/30/2021 17:45:28 - INFO - __main__ - Step 25531: {'lr': 0.00046945904038558364, 'samples': 4901952, 'steps': 25530, 'loss/train': 1.6810768842697144} 08/30/2021 17:45:28 - INFO - __main__ - Step 25532: {'lr': 0.00046945649861237387, 'samples': 4902144, 'steps': 25531, 'loss/train': 2.0984668731689453} 08/30/2021 17:45:29 - INFO - __main__ - Step 25533: {'lr': 0.00046945395674028047, 'samples': 4902336, 'steps': 25532, 'loss/train': 1.5089911222457886} 08/30/2021 17:45:29 - INFO - __main__ - Step 25534: {'lr': 0.0004694514147693044, 'samples': 4902528, 'steps': 25533, 'loss/train': 1.3756768703460693} 08/30/2021 17:45:31 - INFO - __main__ - Step 25535: {'lr': 0.000469448872699447, 'samples': 4902720, 'steps': 25534, 'loss/train': 0.13290277123451233} 08/30/2021 17:45:31 - INFO - __main__ - Step 25536: {'lr': 0.0004694463305307093, 'samples': 4902912, 'steps': 25535, 'loss/train': 1.2443565130233765} 08/30/2021 17:45:31 - INFO - __main__ - Step 25537: {'lr': 0.00046944378826309244, 'samples': 4903104, 'steps': 25536, 'loss/train': 1.7121107578277588} 08/30/2021 17:45:32 - INFO - __main__ - Step 25538: {'lr': 0.00046944124589659765, 'samples': 4903296, 'steps': 25537, 'loss/train': 1.3854635953903198} 08/30/2021 17:45:32 - INFO - __main__ - Step 25539: {'lr': 0.00046943870343122595, 'samples': 4903488, 'steps': 25538, 'loss/train': 1.3788626194000244} 08/30/2021 17:45:34 - INFO - __main__ - Step 25540: {'lr': 0.0004694361608669786, 'samples': 4903680, 'steps': 25539, 'loss/train': 1.0962517261505127} 08/30/2021 17:45:34 - INFO - __main__ - Step 25541: {'lr': 0.0004694336182038567, 'samples': 4903872, 'steps': 25540, 'loss/train': 1.5978034734725952} 08/30/2021 17:45:34 - INFO - __main__ - Step 25542: {'lr': 0.00046943107544186144, 'samples': 4904064, 'steps': 25541, 'loss/train': 1.7243266105651855} 08/30/2021 17:45:35 - INFO - __main__ - Step 25543: {'lr': 0.0004694285325809938, 'samples': 4904256, 'steps': 25542, 'loss/train': 1.7463313341140747} 08/30/2021 17:45:35 - INFO - __main__ - Step 25544: {'lr': 0.00046942598962125515, 'samples': 4904448, 'steps': 25543, 'loss/train': 1.8773432970046997} 08/30/2021 17:45:37 - INFO - __main__ - Step 25545: {'lr': 0.00046942344656264657, 'samples': 4904640, 'steps': 25544, 'loss/train': 1.6174808740615845} 08/30/2021 17:45:38 - INFO - __main__ - Step 25546: {'lr': 0.0004694209034051691, 'samples': 4904832, 'steps': 25545, 'loss/train': 1.2789280414581299} 08/30/2021 17:45:38 - INFO - __main__ - Step 25547: {'lr': 0.00046941836014882394, 'samples': 4905024, 'steps': 25546, 'loss/train': 0.8335281610488892} 08/30/2021 17:45:38 - INFO - __main__ - Step 25548: {'lr': 0.00046941581679361234, 'samples': 4905216, 'steps': 25547, 'loss/train': 0.897831380367279} 08/30/2021 17:45:39 - INFO - __main__ - Step 25549: {'lr': 0.00046941327333953526, 'samples': 4905408, 'steps': 25548, 'loss/train': 1.5635565519332886} 08/30/2021 17:45:39 - INFO - __main__ - Step 25550: {'lr': 0.00046941072978659397, 'samples': 4905600, 'steps': 25549, 'loss/train': 1.523878574371338} 08/30/2021 17:45:40 - INFO - __main__ - Step 25551: {'lr': 0.00046940818613478964, 'samples': 4905792, 'steps': 25550, 'loss/train': 0.07167031615972519} 08/30/2021 17:45:41 - INFO - __main__ - Step 25552: {'lr': 0.0004694056423841233, 'samples': 4905984, 'steps': 25551, 'loss/train': 1.5276508331298828} 08/30/2021 17:45:41 - INFO - __main__ - Step 25553: {'lr': 0.00046940309853459625, 'samples': 4906176, 'steps': 25552, 'loss/train': 1.7026442289352417} 08/30/2021 17:45:42 - INFO - __main__ - Step 25554: {'lr': 0.00046940055458620945, 'samples': 4906368, 'steps': 25553, 'loss/train': 1.2607771158218384} 08/30/2021 17:45:42 - INFO - __main__ - Step 25555: {'lr': 0.0004693980105389642, 'samples': 4906560, 'steps': 25554, 'loss/train': 1.650815725326538} 08/30/2021 17:45:44 - INFO - __main__ - Step 25556: {'lr': 0.00046939546639286156, 'samples': 4906752, 'steps': 25555, 'loss/train': 1.2766176462173462} 08/30/2021 17:45:44 - INFO - __main__ - Step 25557: {'lr': 0.00046939292214790275, 'samples': 4906944, 'steps': 25556, 'loss/train': 1.824107050895691} 08/30/2021 17:45:45 - INFO - __main__ - Step 25558: {'lr': 0.0004693903778040889, 'samples': 4907136, 'steps': 25557, 'loss/train': 1.6804702281951904} 08/30/2021 17:45:45 - INFO - __main__ - Step 25559: {'lr': 0.0004693878333614211, 'samples': 4907328, 'steps': 25558, 'loss/train': 0.14626309275627136} 08/30/2021 17:45:45 - INFO - __main__ - Step 25560: {'lr': 0.0004693852888199005, 'samples': 4907520, 'steps': 25559, 'loss/train': 1.5664700269699097} 08/30/2021 17:45:47 - INFO - __main__ - Step 25561: {'lr': 0.0004693827441795283, 'samples': 4907712, 'steps': 25560, 'loss/train': 1.2916374206542969} 08/30/2021 17:45:47 - INFO - __main__ - Step 25562: {'lr': 0.00046938019944030556, 'samples': 4907904, 'steps': 25561, 'loss/train': 1.253320574760437} 08/30/2021 17:45:48 - INFO - __main__ - Step 25563: {'lr': 0.00046937765460223357, 'samples': 4908096, 'steps': 25562, 'loss/train': 1.8996003866195679} 08/30/2021 17:45:48 - INFO - __main__ - Step 25564: {'lr': 0.0004693751096653134, 'samples': 4908288, 'steps': 25563, 'loss/train': 1.5907924175262451} 08/30/2021 17:45:48 - INFO - __main__ - Step 25565: {'lr': 0.00046937256462954615, 'samples': 4908480, 'steps': 25564, 'loss/train': 1.7696524858474731} 08/30/2021 17:45:50 - INFO - __main__ - Step 25566: {'lr': 0.00046937001949493294, 'samples': 4908672, 'steps': 25565, 'loss/train': 1.5918571949005127} 08/30/2021 17:45:50 - INFO - __main__ - Step 25567: {'lr': 0.0004693674742614751, 'samples': 4908864, 'steps': 25566, 'loss/train': 1.2720521688461304} 08/30/2021 17:45:51 - INFO - __main__ - Step 25568: {'lr': 0.0004693649289291736, 'samples': 4909056, 'steps': 25567, 'loss/train': 1.2477308511734009} 08/30/2021 17:45:51 - INFO - __main__ - Step 25569: {'lr': 0.0004693623834980297, 'samples': 4909248, 'steps': 25568, 'loss/train': 0.08667182177305222} 08/30/2021 17:45:52 - INFO - __main__ - Step 25570: {'lr': 0.00046935983796804443, 'samples': 4909440, 'steps': 25569, 'loss/train': 1.7546091079711914} 08/30/2021 17:45:52 - INFO - __main__ - Step 25571: {'lr': 0.000469357292339219, 'samples': 4909632, 'steps': 25570, 'loss/train': 2.3846867084503174} 08/30/2021 17:45:54 - INFO - __main__ - Step 25572: {'lr': 0.00046935474661155465, 'samples': 4909824, 'steps': 25571, 'loss/train': 1.219957947731018} 08/30/2021 17:45:54 - INFO - __main__ - Step 25573: {'lr': 0.00046935220078505235, 'samples': 4910016, 'steps': 25572, 'loss/train': 2.4779434204101562} 08/30/2021 17:45:54 - INFO - __main__ - Step 25574: {'lr': 0.00046934965485971337, 'samples': 4910208, 'steps': 25573, 'loss/train': 1.1145262718200684} 08/30/2021 17:45:55 - INFO - __main__ - Step 25575: {'lr': 0.00046934710883553884, 'samples': 4910400, 'steps': 25574, 'loss/train': 0.08766800910234451} 08/30/2021 17:45:55 - INFO - __main__ - Step 25576: {'lr': 0.00046934456271252985, 'samples': 4910592, 'steps': 25575, 'loss/train': 1.6031591892242432} 08/30/2021 17:45:57 - INFO - __main__ - Step 25577: {'lr': 0.0004693420164906876, 'samples': 4910784, 'steps': 25576, 'loss/train': 1.3525570631027222} 08/30/2021 17:45:57 - INFO - __main__ - Step 25578: {'lr': 0.0004693394701700132, 'samples': 4910976, 'steps': 25577, 'loss/train': 1.410264015197754} 08/30/2021 17:45:58 - INFO - __main__ - Step 25579: {'lr': 0.00046933692375050783, 'samples': 4911168, 'steps': 25578, 'loss/train': 1.3000317811965942} 08/30/2021 17:45:58 - INFO - __main__ - Step 25580: {'lr': 0.00046933437723217265, 'samples': 4911360, 'steps': 25579, 'loss/train': 1.3320658206939697} 08/30/2021 17:45:58 - INFO - __main__ - Step 25581: {'lr': 0.0004693318306150087, 'samples': 4911552, 'steps': 25580, 'loss/train': 0.5477054119110107} 08/30/2021 17:46:00 - INFO - __main__ - Step 25582: {'lr': 0.0004693292838990173, 'samples': 4911744, 'steps': 25581, 'loss/train': 1.3790009021759033} 08/30/2021 17:46:01 - INFO - __main__ - Step 25583: {'lr': 0.0004693267370841995, 'samples': 4911936, 'steps': 25582, 'loss/train': 1.1315293312072754} 08/30/2021 17:46:01 - INFO - __main__ - Step 25584: {'lr': 0.00046932419017055646, 'samples': 4912128, 'steps': 25583, 'loss/train': 1.6476805210113525} 08/30/2021 17:46:01 - INFO - __main__ - Step 25585: {'lr': 0.0004693216431580893, 'samples': 4912320, 'steps': 25584, 'loss/train': 1.3029710054397583} 08/30/2021 17:46:02 - INFO - __main__ - Step 25586: {'lr': 0.00046931909604679925, 'samples': 4912512, 'steps': 25585, 'loss/train': 1.1572575569152832} 08/30/2021 17:46:03 - INFO - __main__ - Step 25587: {'lr': 0.0004693165488366873, 'samples': 4912704, 'steps': 25586, 'loss/train': 1.7142897844314575} 08/30/2021 17:46:04 - INFO - __main__ - Step 25588: {'lr': 0.00046931400152775473, 'samples': 4912896, 'steps': 25587, 'loss/train': 1.4758199453353882} 08/30/2021 17:46:04 - INFO - __main__ - Step 25589: {'lr': 0.00046931145412000265, 'samples': 4913088, 'steps': 25588, 'loss/train': 1.551531434059143} 08/30/2021 17:46:04 - INFO - __main__ - Step 25590: {'lr': 0.00046930890661343226, 'samples': 4913280, 'steps': 25589, 'loss/train': 1.546036720275879} 08/30/2021 17:46:05 - INFO - __main__ - Step 25591: {'lr': 0.00046930635900804466, 'samples': 4913472, 'steps': 25590, 'loss/train': 1.1229722499847412} 08/30/2021 17:46:06 - INFO - __main__ - Step 25592: {'lr': 0.0004693038113038409, 'samples': 4913664, 'steps': 25591, 'loss/train': 1.2015138864517212} 08/30/2021 17:46:07 - INFO - __main__ - Step 25593: {'lr': 0.0004693012635008224, 'samples': 4913856, 'steps': 25592, 'loss/train': 1.4687280654907227} 08/30/2021 17:46:07 - INFO - __main__ - Step 25594: {'lr': 0.00046929871559898994, 'samples': 4914048, 'steps': 25593, 'loss/train': 1.2752095460891724} 08/30/2021 17:46:07 - INFO - __main__ - Step 25595: {'lr': 0.00046929616759834505, 'samples': 4914240, 'steps': 25594, 'loss/train': 1.6353528499603271} 08/30/2021 17:46:08 - INFO - __main__ - Step 25596: {'lr': 0.00046929361949888857, 'samples': 4914432, 'steps': 25595, 'loss/train': 1.7392250299453735} 08/30/2021 17:46:09 - INFO - __main__ - Step 25597: {'lr': 0.00046929107130062176, 'samples': 4914624, 'steps': 25596, 'loss/train': 1.8298649787902832} 08/30/2021 17:46:10 - INFO - __main__ - Step 25598: {'lr': 0.00046928852300354585, 'samples': 4914816, 'steps': 25597, 'loss/train': 1.7110896110534668} 08/30/2021 17:46:10 - INFO - __main__ - Step 25599: {'lr': 0.0004692859746076619, 'samples': 4915008, 'steps': 25598, 'loss/train': 1.1671812534332275} 08/30/2021 17:46:11 - INFO - __main__ - Step 25600: {'lr': 0.00046928342611297105, 'samples': 4915200, 'steps': 25599, 'loss/train': 1.6852355003356934} 08/30/2021 17:46:11 - INFO - __main__ - Step 25601: {'lr': 0.00046928087751947444, 'samples': 4915392, 'steps': 25600, 'loss/train': 0.975641131401062} 08/30/2021 17:46:12 - INFO - __main__ - Step 25602: {'lr': 0.00046927832882717323, 'samples': 4915584, 'steps': 25601, 'loss/train': 1.9378066062927246} 08/30/2021 17:46:13 - INFO - __main__ - Step 25603: {'lr': 0.0004692757800360687, 'samples': 4915776, 'steps': 25602, 'loss/train': 1.595958948135376} 08/30/2021 17:46:13 - INFO - __main__ - Step 25604: {'lr': 0.0004692732311461618, 'samples': 4915968, 'steps': 25603, 'loss/train': 1.5733797550201416} 08/30/2021 17:46:13 - INFO - __main__ - Step 25605: {'lr': 0.0004692706821574538, 'samples': 4916160, 'steps': 25604, 'loss/train': 1.6840075254440308} 08/30/2021 17:46:14 - INFO - __main__ - Step 25606: {'lr': 0.00046926813306994586, 'samples': 4916352, 'steps': 25605, 'loss/train': 1.3816670179367065} 08/30/2021 17:46:15 - INFO - __main__ - Step 25607: {'lr': 0.00046926558388363904, 'samples': 4916544, 'steps': 25606, 'loss/train': 1.2792718410491943} 08/30/2021 17:46:16 - INFO - __main__ - Step 25608: {'lr': 0.00046926303459853447, 'samples': 4916736, 'steps': 25607, 'loss/train': 1.5633635520935059} 08/30/2021 17:46:16 - INFO - __main__ - Step 25609: {'lr': 0.00046926048521463344, 'samples': 4916928, 'steps': 25608, 'loss/train': 1.4930192232131958} 08/30/2021 17:46:16 - INFO - __main__ - Step 25610: {'lr': 0.000469257935731937, 'samples': 4917120, 'steps': 25609, 'loss/train': 1.3920789957046509} 08/30/2021 17:46:17 - INFO - __main__ - Step 25611: {'lr': 0.0004692553861504463, 'samples': 4917312, 'steps': 25610, 'loss/train': 1.2099542617797852} 08/30/2021 17:46:17 - INFO - __main__ - Step 25612: {'lr': 0.00046925283647016253, 'samples': 4917504, 'steps': 25611, 'loss/train': 0.5829740762710571} 08/30/2021 17:46:19 - INFO - __main__ - Step 25613: {'lr': 0.0004692502866910868, 'samples': 4917696, 'steps': 25612, 'loss/train': 1.332496166229248} 08/30/2021 17:46:20 - INFO - __main__ - Step 25614: {'lr': 0.0004692477368132203, 'samples': 4917888, 'steps': 25613, 'loss/train': 2.0153746604919434} 08/30/2021 17:46:20 - INFO - __main__ - Step 25615: {'lr': 0.0004692451868365641, 'samples': 4918080, 'steps': 25614, 'loss/train': 1.5743674039840698} 08/30/2021 17:46:21 - INFO - __main__ - Step 25616: {'lr': 0.00046924263676111945, 'samples': 4918272, 'steps': 25615, 'loss/train': 1.4915242195129395} 08/30/2021 17:46:21 - INFO - __main__ - Step 25617: {'lr': 0.00046924008658688745, 'samples': 4918464, 'steps': 25616, 'loss/train': 1.3996468782424927} 08/30/2021 17:46:22 - INFO - __main__ - Step 25618: {'lr': 0.00046923753631386924, 'samples': 4918656, 'steps': 25617, 'loss/train': 2.0151290893554688} 08/30/2021 17:46:23 - INFO - __main__ - Step 25619: {'lr': 0.0004692349859420659, 'samples': 4918848, 'steps': 25618, 'loss/train': 1.116296648979187} 08/30/2021 17:46:23 - INFO - __main__ - Step 25620: {'lr': 0.00046923243547147874, 'samples': 4919040, 'steps': 25619, 'loss/train': 1.6149743795394897} 08/30/2021 17:46:24 - INFO - __main__ - Step 25621: {'lr': 0.0004692298849021088, 'samples': 4919232, 'steps': 25620, 'loss/train': 1.7254117727279663} 08/30/2021 17:46:24 - INFO - __main__ - Step 25622: {'lr': 0.00046922733423395736, 'samples': 4919424, 'steps': 25621, 'loss/train': 0.910541296005249} 08/30/2021 17:46:25 - INFO - __main__ - Step 25623: {'lr': 0.0004692247834670253, 'samples': 4919616, 'steps': 25622, 'loss/train': 1.3471633195877075} 08/30/2021 17:46:26 - INFO - __main__ - Step 25624: {'lr': 0.000469222232601314, 'samples': 4919808, 'steps': 25623, 'loss/train': 1.6275146007537842} 08/30/2021 17:46:26 - INFO - __main__ - Step 25625: {'lr': 0.0004692196816368246, 'samples': 4920000, 'steps': 25624, 'loss/train': 0.9021770358085632} 08/30/2021 17:46:27 - INFO - __main__ - Step 25626: {'lr': 0.00046921713057355817, 'samples': 4920192, 'steps': 25625, 'loss/train': 1.6000720262527466} 08/30/2021 17:46:27 - INFO - __main__ - Step 25627: {'lr': 0.0004692145794115159, 'samples': 4920384, 'steps': 25626, 'loss/train': 2.384751081466675} 08/30/2021 17:46:29 - INFO - __main__ - Step 25628: {'lr': 0.00046921202815069883, 'samples': 4920576, 'steps': 25627, 'loss/train': 0.963126003742218} 08/30/2021 17:46:29 - INFO - __main__ - Step 25629: {'lr': 0.00046920947679110833, 'samples': 4920768, 'steps': 25628, 'loss/train': 1.5333893299102783} 08/30/2021 17:46:30 - INFO - __main__ - Step 25630: {'lr': 0.00046920692533274533, 'samples': 4920960, 'steps': 25629, 'loss/train': 5.969575881958008} 08/30/2021 17:46:30 - INFO - __main__ - Step 25631: {'lr': 0.0004692043737756111, 'samples': 4921152, 'steps': 25630, 'loss/train': 5.858996391296387} 08/30/2021 17:46:30 - INFO - __main__ - Step 25632: {'lr': 0.00046920182211970677, 'samples': 4921344, 'steps': 25631, 'loss/train': 1.7322770357131958} 08/30/2021 17:46:31 - INFO - __main__ - Step 25633: {'lr': 0.00046919927036503353, 'samples': 4921536, 'steps': 25632, 'loss/train': 1.5119572877883911} 08/30/2021 17:46:31 - INFO - __main__ - Step 25634: {'lr': 0.0004691967185115924, 'samples': 4921728, 'steps': 25633, 'loss/train': 1.7821234464645386} 08/30/2021 17:46:33 - INFO - __main__ - Step 25635: {'lr': 0.00046919416655938465, 'samples': 4921920, 'steps': 25634, 'loss/train': 1.7719392776489258} 08/30/2021 17:46:33 - INFO - __main__ - Step 25636: {'lr': 0.0004691916145084113, 'samples': 4922112, 'steps': 25635, 'loss/train': 1.672731876373291} 08/30/2021 17:46:34 - INFO - __main__ - Step 25637: {'lr': 0.0004691890623586737, 'samples': 4922304, 'steps': 25636, 'loss/train': 1.2098770141601562} 08/30/2021 17:46:34 - INFO - __main__ - Step 25638: {'lr': 0.00046918651011017287, 'samples': 4922496, 'steps': 25637, 'loss/train': 1.5956040620803833} 08/30/2021 17:46:34 - INFO - __main__ - Step 25639: {'lr': 0.00046918395776290997, 'samples': 4922688, 'steps': 25638, 'loss/train': 1.457015037536621} 08/30/2021 17:46:36 - INFO - __main__ - Step 25640: {'lr': 0.0004691814053168861, 'samples': 4922880, 'steps': 25639, 'loss/train': 1.3072255849838257} 08/30/2021 17:46:36 - INFO - __main__ - Step 25641: {'lr': 0.0004691788527721026, 'samples': 4923072, 'steps': 25640, 'loss/train': 1.556615948677063} 08/30/2021 17:46:37 - INFO - __main__ - Step 25642: {'lr': 0.0004691763001285604, 'samples': 4923264, 'steps': 25641, 'loss/train': 1.2920417785644531} 08/30/2021 17:46:37 - INFO - __main__ - Step 25643: {'lr': 0.0004691737473862607, 'samples': 4923456, 'steps': 25642, 'loss/train': 1.911281704902649} 08/30/2021 17:46:37 - INFO - __main__ - Step 25644: {'lr': 0.00046917119454520487, 'samples': 4923648, 'steps': 25643, 'loss/train': 1.6087640523910522} 08/30/2021 17:46:39 - INFO - __main__ - Step 25645: {'lr': 0.00046916864160539376, 'samples': 4923840, 'steps': 25644, 'loss/train': 1.8666285276412964} 08/30/2021 17:46:39 - INFO - __main__ - Step 25646: {'lr': 0.00046916608856682865, 'samples': 4924032, 'steps': 25645, 'loss/train': 1.5911983251571655} 08/30/2021 17:46:40 - INFO - __main__ - Step 25647: {'lr': 0.0004691635354295106, 'samples': 4924224, 'steps': 25646, 'loss/train': 1.169861912727356} 08/30/2021 17:46:40 - INFO - __main__ - Step 25648: {'lr': 0.00046916098219344093, 'samples': 4924416, 'steps': 25647, 'loss/train': 1.3354626893997192} 08/30/2021 17:46:40 - INFO - __main__ - Step 25649: {'lr': 0.0004691584288586207, 'samples': 4924608, 'steps': 25648, 'loss/train': 1.26406729221344} 08/30/2021 17:46:42 - INFO - __main__ - Step 25650: {'lr': 0.0004691558754250511, 'samples': 4924800, 'steps': 25649, 'loss/train': 1.3049681186676025} 08/30/2021 17:46:42 - INFO - __main__ - Step 25651: {'lr': 0.0004691533218927332, 'samples': 4924992, 'steps': 25650, 'loss/train': 1.289215326309204} 08/30/2021 17:46:43 - INFO - __main__ - Step 25652: {'lr': 0.00046915076826166814, 'samples': 4925184, 'steps': 25651, 'loss/train': 1.2583330869674683} 08/30/2021 17:46:43 - INFO - __main__ - Step 25653: {'lr': 0.0004691482145318572, 'samples': 4925376, 'steps': 25652, 'loss/train': 1.0070675611495972} 08/30/2021 17:46:43 - INFO - __main__ - Step 25654: {'lr': 0.00046914566070330144, 'samples': 4925568, 'steps': 25653, 'loss/train': 1.2272132635116577} 08/30/2021 17:46:44 - INFO - __main__ - Step 25655: {'lr': 0.00046914310677600204, 'samples': 4925760, 'steps': 25654, 'loss/train': 1.4363913536071777} 08/30/2021 17:46:45 - INFO - __main__ - Step 25656: {'lr': 0.00046914055274996017, 'samples': 4925952, 'steps': 25655, 'loss/train': 1.8204822540283203} 08/30/2021 17:46:46 - INFO - __main__ - Step 25657: {'lr': 0.00046913799862517686, 'samples': 4926144, 'steps': 25656, 'loss/train': 1.3860546350479126} 08/30/2021 17:46:46 - INFO - __main__ - Step 25658: {'lr': 0.0004691354444016534, 'samples': 4926336, 'steps': 25657, 'loss/train': 1.6931554079055786} 08/30/2021 17:46:46 - INFO - __main__ - Step 25659: {'lr': 0.00046913289007939087, 'samples': 4926528, 'steps': 25658, 'loss/train': 1.4370806217193604} 08/30/2021 17:46:47 - INFO - __main__ - Step 25660: {'lr': 0.00046913033565839046, 'samples': 4926720, 'steps': 25659, 'loss/train': 1.4942413568496704} 08/30/2021 17:46:49 - INFO - __main__ - Step 25661: {'lr': 0.0004691277811386533, 'samples': 4926912, 'steps': 25660, 'loss/train': 1.5427632331848145} 08/30/2021 17:46:49 - INFO - __main__ - Step 25662: {'lr': 0.0004691252265201805, 'samples': 4927104, 'steps': 25661, 'loss/train': 1.3137925863265991} 08/30/2021 17:46:50 - INFO - __main__ - Step 25663: {'lr': 0.00046912267180297337, 'samples': 4927296, 'steps': 25662, 'loss/train': 0.063136987388134} 08/30/2021 17:46:50 - INFO - __main__ - Step 25664: {'lr': 0.0004691201169870328, 'samples': 4927488, 'steps': 25663, 'loss/train': 2.225656509399414} 08/30/2021 17:46:50 - INFO - __main__ - Step 25665: {'lr': 0.00046911756207236024, 'samples': 4927680, 'steps': 25664, 'loss/train': 1.6347001791000366} 08/30/2021 17:46:51 - INFO - __main__ - Step 25666: {'lr': 0.0004691150070589566, 'samples': 4927872, 'steps': 25665, 'loss/train': 1.7294188737869263} 08/30/2021 17:46:53 - INFO - __main__ - Step 25667: {'lr': 0.00046911245194682306, 'samples': 4928064, 'steps': 25666, 'loss/train': 1.6906583309173584} 08/30/2021 17:46:53 - INFO - __main__ - Step 25668: {'lr': 0.00046910989673596093, 'samples': 4928256, 'steps': 25667, 'loss/train': 1.4899779558181763} 08/30/2021 17:46:53 - INFO - __main__ - Step 25669: {'lr': 0.00046910734142637124, 'samples': 4928448, 'steps': 25668, 'loss/train': 1.5659645795822144} 08/30/2021 17:46:54 - INFO - __main__ - Step 25670: {'lr': 0.00046910478601805514, 'samples': 4928640, 'steps': 25669, 'loss/train': 1.0884144306182861} 08/30/2021 17:46:54 - INFO - __main__ - Step 25671: {'lr': 0.0004691022305110138, 'samples': 4928832, 'steps': 25670, 'loss/train': 1.4707077741622925} 08/30/2021 17:46:56 - INFO - __main__ - Step 25672: {'lr': 0.0004690996749052484, 'samples': 4929024, 'steps': 25671, 'loss/train': 1.7564407587051392} 08/30/2021 17:46:56 - INFO - __main__ - Step 25673: {'lr': 0.00046909711920076, 'samples': 4929216, 'steps': 25672, 'loss/train': 2.032792091369629} 08/30/2021 17:46:56 - INFO - __main__ - Step 25674: {'lr': 0.0004690945633975499, 'samples': 4929408, 'steps': 25673, 'loss/train': 1.2514983415603638} 08/30/2021 17:46:57 - INFO - __main__ - Step 25675: {'lr': 0.00046909200749561914, 'samples': 4929600, 'steps': 25674, 'loss/train': 1.769295334815979} 08/30/2021 17:46:57 - INFO - __main__ - Step 25676: {'lr': 0.00046908945149496897, 'samples': 4929792, 'steps': 25675, 'loss/train': 1.2579846382141113} 08/30/2021 17:46:59 - INFO - __main__ - Step 25677: {'lr': 0.00046908689539560034, 'samples': 4929984, 'steps': 25676, 'loss/train': 1.221014380455017} 08/30/2021 17:46:59 - INFO - __main__ - Step 25678: {'lr': 0.0004690843391975146, 'samples': 4930176, 'steps': 25677, 'loss/train': 1.0823017358779907} 08/30/2021 17:47:00 - INFO - __main__ - Step 25679: {'lr': 0.0004690817829007129, 'samples': 4930368, 'steps': 25678, 'loss/train': 1.5751724243164062} 08/30/2021 17:47:00 - INFO - __main__ - Step 25680: {'lr': 0.00046907922650519623, 'samples': 4930560, 'steps': 25679, 'loss/train': 0.8998758792877197} 08/30/2021 17:47:00 - INFO - __main__ - Step 25681: {'lr': 0.0004690766700109659, 'samples': 4930752, 'steps': 25680, 'loss/train': 1.2231260538101196} 08/30/2021 17:47:02 - INFO - __main__ - Step 25682: {'lr': 0.00046907411341802295, 'samples': 4930944, 'steps': 25681, 'loss/train': 1.7166142463684082} 08/30/2021 17:47:02 - INFO - __main__ - Step 25683: {'lr': 0.0004690715567263687, 'samples': 4931136, 'steps': 25682, 'loss/train': 1.4265334606170654} 08/30/2021 17:47:03 - INFO - __main__ - Step 25684: {'lr': 0.00046906899993600406, 'samples': 4931328, 'steps': 25683, 'loss/train': 0.09770724177360535} 08/30/2021 17:47:03 - INFO - __main__ - Step 25685: {'lr': 0.00046906644304693033, 'samples': 4931520, 'steps': 25684, 'loss/train': 1.1788661479949951} 08/30/2021 17:47:03 - INFO - __main__ - Step 25686: {'lr': 0.0004690638860591487, 'samples': 4931712, 'steps': 25685, 'loss/train': 1.6538797616958618} 08/30/2021 17:47:04 - INFO - __main__ - Step 25687: {'lr': 0.00046906132897266026, 'samples': 4931904, 'steps': 25686, 'loss/train': 1.9894604682922363} 08/30/2021 17:47:05 - INFO - __main__ - Step 25688: {'lr': 0.00046905877178746614, 'samples': 4932096, 'steps': 25687, 'loss/train': 1.5378966331481934} 08/30/2021 17:47:06 - INFO - __main__ - Step 25689: {'lr': 0.0004690562145035675, 'samples': 4932288, 'steps': 25688, 'loss/train': 1.540313720703125} 08/30/2021 17:47:06 - INFO - __main__ - Step 25690: {'lr': 0.00046905365712096553, 'samples': 4932480, 'steps': 25689, 'loss/train': 1.1325825452804565} 08/30/2021 17:47:06 - INFO - __main__ - Step 25691: {'lr': 0.0004690510996396614, 'samples': 4932672, 'steps': 25690, 'loss/train': 1.6712768077850342} 08/30/2021 17:47:07 - INFO - __main__ - Step 25692: {'lr': 0.0004690485420596561, 'samples': 4932864, 'steps': 25691, 'loss/train': 1.5641427040100098} 08/30/2021 17:47:08 - INFO - __main__ - Step 25693: {'lr': 0.000469045984380951, 'samples': 4933056, 'steps': 25692, 'loss/train': 1.4656329154968262} 08/30/2021 17:47:09 - INFO - __main__ - Step 25694: {'lr': 0.0004690434266035471, 'samples': 4933248, 'steps': 25693, 'loss/train': 1.7872800827026367} 08/30/2021 17:47:09 - INFO - __main__ - Step 25695: {'lr': 0.00046904086872744577, 'samples': 4933440, 'steps': 25694, 'loss/train': 1.1971526145935059} 08/30/2021 17:47:10 - INFO - __main__ - Step 25696: {'lr': 0.0004690383107526479, 'samples': 4933632, 'steps': 25695, 'loss/train': 1.3781235218048096} 08/30/2021 17:47:10 - INFO - __main__ - Step 25697: {'lr': 0.0004690357526791547, 'samples': 4933824, 'steps': 25696, 'loss/train': 0.2671090066432953} 08/30/2021 17:47:11 - INFO - __main__ - Step 25698: {'lr': 0.00046903319450696744, 'samples': 4934016, 'steps': 25697, 'loss/train': 1.2729966640472412} 08/30/2021 17:47:12 - INFO - __main__ - Step 25699: {'lr': 0.00046903063623608714, 'samples': 4934208, 'steps': 25698, 'loss/train': 1.397875189781189} 08/30/2021 17:47:12 - INFO - __main__ - Step 25700: {'lr': 0.00046902807786651507, 'samples': 4934400, 'steps': 25699, 'loss/train': 1.6402528285980225} 08/30/2021 17:47:13 - INFO - __main__ - Step 25701: {'lr': 0.00046902551939825236, 'samples': 4934592, 'steps': 25700, 'loss/train': 1.5903586149215698} 08/30/2021 17:47:13 - INFO - __main__ - Step 25702: {'lr': 0.00046902296083130003, 'samples': 4934784, 'steps': 25701, 'loss/train': 1.797283411026001} 08/30/2021 17:47:14 - INFO - __main__ - Step 25703: {'lr': 0.00046902040216565945, 'samples': 4934976, 'steps': 25702, 'loss/train': 1.37621009349823} 08/30/2021 17:47:15 - INFO - __main__ - Step 25704: {'lr': 0.0004690178434013316, 'samples': 4935168, 'steps': 25703, 'loss/train': 1.568002700805664} 08/30/2021 17:47:15 - INFO - __main__ - Step 25705: {'lr': 0.00046901528453831764, 'samples': 4935360, 'steps': 25704, 'loss/train': 2.126760482788086} 08/30/2021 17:47:16 - INFO - __main__ - Step 25706: {'lr': 0.0004690127255766188, 'samples': 4935552, 'steps': 25705, 'loss/train': 1.5658352375030518} 08/30/2021 17:47:16 - INFO - __main__ - Step 25707: {'lr': 0.0004690101665162362, 'samples': 4935744, 'steps': 25706, 'loss/train': 1.1048375368118286} 08/30/2021 17:47:17 - INFO - __main__ - Step 25708: {'lr': 0.00046900760735717103, 'samples': 4935936, 'steps': 25707, 'loss/train': 1.774127721786499} 08/30/2021 17:47:18 - INFO - __main__ - Step 25709: {'lr': 0.00046900504809942433, 'samples': 4936128, 'steps': 25708, 'loss/train': 1.4984357357025146} 08/30/2021 17:47:18 - INFO - __main__ - Step 25710: {'lr': 0.00046900248874299746, 'samples': 4936320, 'steps': 25709, 'loss/train': 1.3653550148010254} 08/30/2021 17:47:18 - INFO - __main__ - Step 25711: {'lr': 0.0004689999292878914, 'samples': 4936512, 'steps': 25710, 'loss/train': 1.5078903436660767} 08/30/2021 17:47:19 - INFO - __main__ - Step 25712: {'lr': 0.00046899736973410734, 'samples': 4936704, 'steps': 25711, 'loss/train': 3.89837384223938} 08/30/2021 17:47:19 - INFO - __main__ - Step 25713: {'lr': 0.0004689948100816465, 'samples': 4936896, 'steps': 25712, 'loss/train': 1.0883709192276} 08/30/2021 17:47:21 - INFO - __main__ - Step 25714: {'lr': 0.00046899225033050985, 'samples': 4937088, 'steps': 25713, 'loss/train': 1.235689401626587} 08/30/2021 17:47:21 - INFO - __main__ - Step 25715: {'lr': 0.0004689896904806987, 'samples': 4937280, 'steps': 25714, 'loss/train': 0.9609364867210388} 08/30/2021 17:47:22 - INFO - __main__ - Step 25716: {'lr': 0.0004689871305322143, 'samples': 4937472, 'steps': 25715, 'loss/train': 0.1189139187335968} 08/30/2021 17:47:22 - INFO - __main__ - Step 25717: {'lr': 0.0004689845704850576, 'samples': 4937664, 'steps': 25716, 'loss/train': 1.5079913139343262} 08/30/2021 17:47:22 - INFO - __main__ - Step 25718: {'lr': 0.0004689820103392298, 'samples': 4937856, 'steps': 25717, 'loss/train': 0.09478290379047394} 08/30/2021 17:47:24 - INFO - __main__ - Step 25719: {'lr': 0.0004689794500947321, 'samples': 4938048, 'steps': 25718, 'loss/train': 1.803954839706421} 08/30/2021 17:47:25 - INFO - __main__ - Step 25720: {'lr': 0.0004689768897515657, 'samples': 4938240, 'steps': 25719, 'loss/train': 1.8638983964920044} 08/30/2021 17:47:25 - INFO - __main__ - Step 25721: {'lr': 0.0004689743293097316, 'samples': 4938432, 'steps': 25720, 'loss/train': 0.07366359978914261} 08/30/2021 17:47:26 - INFO - __main__ - Step 25722: {'lr': 0.0004689717687692311, 'samples': 4938624, 'steps': 25721, 'loss/train': 0.05595998093485832} 08/30/2021 17:47:26 - INFO - __main__ - Step 25723: {'lr': 0.0004689692081300653, 'samples': 4938816, 'steps': 25722, 'loss/train': 1.9962135553359985} 08/30/2021 17:47:28 - INFO - __main__ - Step 25724: {'lr': 0.0004689666473922354, 'samples': 4939008, 'steps': 25723, 'loss/train': 1.1417449712753296} 08/30/2021 17:47:28 - INFO - __main__ - Step 25725: {'lr': 0.0004689640865557424, 'samples': 4939200, 'steps': 25724, 'loss/train': 2.1349759101867676} 08/30/2021 17:47:28 - INFO - __main__ - Step 25726: {'lr': 0.0004689615256205876, 'samples': 4939392, 'steps': 25725, 'loss/train': 1.6161985397338867} 08/30/2021 17:47:29 - INFO - __main__ - Step 25727: {'lr': 0.0004689589645867721, 'samples': 4939584, 'steps': 25726, 'loss/train': 1.3147382736206055} 08/30/2021 17:47:29 - INFO - __main__ - Step 25728: {'lr': 0.0004689564034542971, 'samples': 4939776, 'steps': 25727, 'loss/train': 1.0522000789642334} 08/30/2021 17:47:31 - INFO - __main__ - Step 25729: {'lr': 0.00046895384222316375, 'samples': 4939968, 'steps': 25728, 'loss/train': 0.741268515586853} 08/30/2021 17:47:31 - INFO - __main__ - Step 25730: {'lr': 0.0004689512808933731, 'samples': 4940160, 'steps': 25729, 'loss/train': 1.3964345455169678} 08/30/2021 17:47:31 - INFO - __main__ - Step 25731: {'lr': 0.0004689487194649265, 'samples': 4940352, 'steps': 25730, 'loss/train': 1.5941787958145142} 08/30/2021 17:47:32 - INFO - __main__ - Step 25732: {'lr': 0.0004689461579378249, 'samples': 4940544, 'steps': 25731, 'loss/train': 0.07148110121488571} 08/30/2021 17:47:32 - INFO - __main__ - Step 25733: {'lr': 0.0004689435963120696, 'samples': 4940736, 'steps': 25732, 'loss/train': 1.2390637397766113} 08/30/2021 17:47:34 - INFO - __main__ - Step 25734: {'lr': 0.00046894103458766163, 'samples': 4940928, 'steps': 25733, 'loss/train': 1.6882007122039795} 08/30/2021 17:47:34 - INFO - __main__ - Step 25735: {'lr': 0.0004689384727646022, 'samples': 4941120, 'steps': 25734, 'loss/train': 1.6453152894973755} 08/30/2021 17:47:34 - INFO - __main__ - Step 25736: {'lr': 0.00046893591084289256, 'samples': 4941312, 'steps': 25735, 'loss/train': 1.415347933769226} 08/30/2021 17:47:35 - INFO - __main__ - Step 25737: {'lr': 0.0004689333488225337, 'samples': 4941504, 'steps': 25736, 'loss/train': 2.184805393218994} 08/30/2021 17:47:35 - INFO - __main__ - Step 25738: {'lr': 0.00046893078670352686, 'samples': 4941696, 'steps': 25737, 'loss/train': 1.5168434381484985} 08/30/2021 17:47:37 - INFO - __main__ - Step 25739: {'lr': 0.0004689282244858732, 'samples': 4941888, 'steps': 25738, 'loss/train': 1.8757611513137817} 08/30/2021 17:47:37 - INFO - __main__ - Step 25740: {'lr': 0.00046892566216957387, 'samples': 4942080, 'steps': 25739, 'loss/train': 0.890189528465271} 08/30/2021 17:47:37 - INFO - __main__ - Step 25741: {'lr': 0.00046892309975463, 'samples': 4942272, 'steps': 25740, 'loss/train': 0.6732057332992554} 08/30/2021 17:47:38 - INFO - __main__ - Step 25742: {'lr': 0.0004689205372410427, 'samples': 4942464, 'steps': 25741, 'loss/train': 1.7113462686538696} 08/30/2021 17:47:38 - INFO - __main__ - Step 25743: {'lr': 0.00046891797462881327, 'samples': 4942656, 'steps': 25742, 'loss/train': 1.5250897407531738} 08/30/2021 17:47:40 - INFO - __main__ - Step 25744: {'lr': 0.0004689154119179427, 'samples': 4942848, 'steps': 25743, 'loss/train': 0.9668641090393066} 08/30/2021 17:47:40 - INFO - __main__ - Step 25745: {'lr': 0.00046891284910843237, 'samples': 4943040, 'steps': 25744, 'loss/train': 1.6589901447296143} 08/30/2021 17:47:40 - INFO - __main__ - Step 25746: {'lr': 0.0004689102862002832, 'samples': 4943232, 'steps': 25745, 'loss/train': 1.1028515100479126} 08/30/2021 17:47:41 - INFO - __main__ - Step 25747: {'lr': 0.00046890772319349637, 'samples': 4943424, 'steps': 25746, 'loss/train': 0.047654375433921814} 08/30/2021 17:47:41 - INFO - __main__ - Step 25748: {'lr': 0.00046890516008807315, 'samples': 4943616, 'steps': 25747, 'loss/train': 1.8506273031234741} 08/30/2021 17:47:43 - INFO - __main__ - Step 25749: {'lr': 0.0004689025968840147, 'samples': 4943808, 'steps': 25748, 'loss/train': 1.621748447418213} 08/30/2021 17:47:43 - INFO - __main__ - Step 25750: {'lr': 0.00046890003358132204, 'samples': 4944000, 'steps': 25749, 'loss/train': 0.8986481428146362} 08/30/2021 17:47:43 - INFO - __main__ - Step 25751: {'lr': 0.0004688974701799964, 'samples': 4944192, 'steps': 25750, 'loss/train': 1.985831379890442} 08/30/2021 17:47:44 - INFO - __main__ - Step 25752: {'lr': 0.00046889490668003896, 'samples': 4944384, 'steps': 25751, 'loss/train': 1.158137321472168} 08/30/2021 17:47:44 - INFO - __main__ - Step 25753: {'lr': 0.0004688923430814509, 'samples': 4944576, 'steps': 25752, 'loss/train': 2.002857208251953} 08/30/2021 17:47:44 - INFO - __main__ - Step 25754: {'lr': 0.00046888977938423326, 'samples': 4944768, 'steps': 25753, 'loss/train': 1.1062910556793213} 08/30/2021 17:47:46 - INFO - __main__ - Step 25755: {'lr': 0.00046888721558838734, 'samples': 4944960, 'steps': 25754, 'loss/train': 1.763000249862671} 08/30/2021 17:47:46 - INFO - __main__ - Step 25756: {'lr': 0.00046888465169391414, 'samples': 4945152, 'steps': 25755, 'loss/train': 1.028965711593628} 08/30/2021 17:47:47 - INFO - __main__ - Step 25757: {'lr': 0.00046888208770081493, 'samples': 4945344, 'steps': 25756, 'loss/train': 1.6193593740463257} 08/30/2021 17:47:47 - INFO - __main__ - Step 25758: {'lr': 0.0004688795236090908, 'samples': 4945536, 'steps': 25757, 'loss/train': 1.2246124744415283} 08/30/2021 17:47:47 - INFO - __main__ - Step 25759: {'lr': 0.000468876959418743, 'samples': 4945728, 'steps': 25758, 'loss/train': 1.90020751953125} 08/30/2021 17:47:49 - INFO - __main__ - Step 25760: {'lr': 0.0004688743951297726, 'samples': 4945920, 'steps': 25759, 'loss/train': 1.3285982608795166} 08/30/2021 17:47:49 - INFO - __main__ - Step 25761: {'lr': 0.0004688718307421807, 'samples': 4946112, 'steps': 25760, 'loss/train': 0.6641785502433777} 08/30/2021 17:47:50 - INFO - __main__ - Step 25762: {'lr': 0.0004688692662559686, 'samples': 4946304, 'steps': 25761, 'loss/train': 1.5299488306045532} 08/30/2021 17:47:50 - INFO - __main__ - Step 25763: {'lr': 0.00046886670167113734, 'samples': 4946496, 'steps': 25762, 'loss/train': 1.4613096714019775} 08/30/2021 17:47:50 - INFO - __main__ - Step 25764: {'lr': 0.00046886413698768816, 'samples': 4946688, 'steps': 25763, 'loss/train': 1.715574860572815} 08/30/2021 17:47:52 - INFO - __main__ - Step 25765: {'lr': 0.0004688615722056222, 'samples': 4946880, 'steps': 25764, 'loss/train': 1.7326476573944092} 08/30/2021 17:47:52 - INFO - __main__ - Step 25766: {'lr': 0.00046885900732494053, 'samples': 4947072, 'steps': 25765, 'loss/train': 1.8465771675109863} 08/30/2021 17:47:53 - INFO - __main__ - Step 25767: {'lr': 0.0004688564423456444, 'samples': 4947264, 'steps': 25766, 'loss/train': 2.3126943111419678} 08/30/2021 17:47:53 - INFO - __main__ - Step 25768: {'lr': 0.00046885387726773494, 'samples': 4947456, 'steps': 25767, 'loss/train': 1.471281886100769} 08/30/2021 17:47:53 - INFO - __main__ - Step 25769: {'lr': 0.0004688513120912133, 'samples': 4947648, 'steps': 25768, 'loss/train': 1.0972404479980469} 08/30/2021 17:47:55 - INFO - __main__ - Step 25770: {'lr': 0.0004688487468160806, 'samples': 4947840, 'steps': 25769, 'loss/train': 1.7421773672103882} 08/30/2021 17:47:55 - INFO - __main__ - Step 25771: {'lr': 0.000468846181442338, 'samples': 4948032, 'steps': 25770, 'loss/train': 1.0144166946411133} 08/30/2021 17:47:56 - INFO - __main__ - Step 25772: {'lr': 0.0004688436159699868, 'samples': 4948224, 'steps': 25771, 'loss/train': 1.7927099466323853} 08/30/2021 17:47:56 - INFO - __main__ - Step 25773: {'lr': 0.000468841050399028, 'samples': 4948416, 'steps': 25772, 'loss/train': 1.3223836421966553} 08/30/2021 17:47:56 - INFO - __main__ - Step 25774: {'lr': 0.0004688384847294628, 'samples': 4948608, 'steps': 25773, 'loss/train': 1.6288995742797852} 08/30/2021 17:47:58 - INFO - __main__ - Step 25775: {'lr': 0.0004688359189612923, 'samples': 4948800, 'steps': 25774, 'loss/train': 0.46493470668792725} 08/30/2021 17:47:59 - INFO - __main__ - Step 25776: {'lr': 0.0004688333530945178, 'samples': 4948992, 'steps': 25775, 'loss/train': 1.0550819635391235} 08/30/2021 17:47:59 - INFO - __main__ - Step 25777: {'lr': 0.0004688307871291403, 'samples': 4949184, 'steps': 25776, 'loss/train': 1.7852526903152466} 08/30/2021 17:47:59 - INFO - __main__ - Step 25778: {'lr': 0.0004688282210651611, 'samples': 4949376, 'steps': 25777, 'loss/train': 1.324590802192688} 08/30/2021 17:48:00 - INFO - __main__ - Step 25779: {'lr': 0.00046882565490258125, 'samples': 4949568, 'steps': 25778, 'loss/train': 1.9621769189834595} 08/30/2021 17:48:00 - INFO - __main__ - Step 25780: {'lr': 0.0004688230886414019, 'samples': 4949760, 'steps': 25779, 'loss/train': 1.7752286195755005} 08/30/2021 17:48:02 - INFO - __main__ - Step 25781: {'lr': 0.0004688205222816242, 'samples': 4949952, 'steps': 25780, 'loss/train': 1.5793185234069824} 08/30/2021 17:48:02 - INFO - __main__ - Step 25782: {'lr': 0.00046881795582324944, 'samples': 4950144, 'steps': 25781, 'loss/train': 1.5692440271377563} 08/30/2021 17:48:03 - INFO - __main__ - Step 25783: {'lr': 0.00046881538926627864, 'samples': 4950336, 'steps': 25782, 'loss/train': 1.4250872135162354} 08/30/2021 17:48:03 - INFO - __main__ - Step 25784: {'lr': 0.000468812822610713, 'samples': 4950528, 'steps': 25783, 'loss/train': 1.7000045776367188} 08/30/2021 17:48:03 - INFO - __main__ - Step 25785: {'lr': 0.00046881025585655367, 'samples': 4950720, 'steps': 25784, 'loss/train': 1.6478009223937988} 08/30/2021 17:48:05 - INFO - __main__ - Step 25786: {'lr': 0.0004688076890038019, 'samples': 4950912, 'steps': 25785, 'loss/train': 3.8902199268341064} 08/30/2021 17:48:05 - INFO - __main__ - Step 25787: {'lr': 0.00046880512205245867, 'samples': 4951104, 'steps': 25786, 'loss/train': 1.7694299221038818} 08/30/2021 17:48:06 - INFO - __main__ - Step 25788: {'lr': 0.00046880255500252526, 'samples': 4951296, 'steps': 25787, 'loss/train': 1.4008413553237915} 08/30/2021 17:48:06 - INFO - __main__ - Step 25789: {'lr': 0.0004687999878540028, 'samples': 4951488, 'steps': 25788, 'loss/train': 1.402262568473816} 08/30/2021 17:48:06 - INFO - __main__ - Step 25790: {'lr': 0.00046879742060689243, 'samples': 4951680, 'steps': 25789, 'loss/train': 1.4390090703964233} 08/30/2021 17:48:08 - INFO - __main__ - Step 25791: {'lr': 0.0004687948532611953, 'samples': 4951872, 'steps': 25790, 'loss/train': 1.5752841234207153} 08/30/2021 17:48:08 - INFO - __main__ - Step 25792: {'lr': 0.0004687922858169126, 'samples': 4952064, 'steps': 25791, 'loss/train': 1.81866455078125} 08/30/2021 17:48:09 - INFO - __main__ - Step 25793: {'lr': 0.0004687897182740455, 'samples': 4952256, 'steps': 25792, 'loss/train': 1.4577043056488037} 08/30/2021 17:48:09 - INFO - __main__ - Step 25794: {'lr': 0.0004687871506325951, 'samples': 4952448, 'steps': 25793, 'loss/train': 1.6696598529815674} 08/30/2021 17:48:09 - INFO - __main__ - Step 25795: {'lr': 0.00046878458289256264, 'samples': 4952640, 'steps': 25794, 'loss/train': 1.4243284463882446} 08/30/2021 17:48:11 - INFO - __main__ - Step 25796: {'lr': 0.00046878201505394913, 'samples': 4952832, 'steps': 25795, 'loss/train': 1.4257913827896118} 08/30/2021 17:48:12 - INFO - __main__ - Step 25797: {'lr': 0.0004687794471167559, 'samples': 4953024, 'steps': 25796, 'loss/train': 1.295582890510559} 08/30/2021 17:48:12 - INFO - __main__ - Step 25798: {'lr': 0.00046877687908098396, 'samples': 4953216, 'steps': 25797, 'loss/train': 1.5752441883087158} 08/30/2021 17:48:12 - INFO - __main__ - Step 25799: {'lr': 0.0004687743109466346, 'samples': 4953408, 'steps': 25798, 'loss/train': 0.2516460716724396} 08/30/2021 17:48:13 - INFO - __main__ - Step 25800: {'lr': 0.00046877174271370894, 'samples': 4953600, 'steps': 25799, 'loss/train': 1.274735927581787} 08/30/2021 17:48:14 - INFO - __main__ - Step 25801: {'lr': 0.000468769174382208, 'samples': 4953792, 'steps': 25800, 'loss/train': 0.0804050862789154} 08/30/2021 17:48:14 - INFO - __main__ - Step 25802: {'lr': 0.0004687666059521331, 'samples': 4953984, 'steps': 25801, 'loss/train': 1.858128547668457} 08/30/2021 17:48:15 - INFO - __main__ - Step 25803: {'lr': 0.0004687640374234854, 'samples': 4954176, 'steps': 25802, 'loss/train': 1.530103087425232} 08/30/2021 17:48:15 - INFO - __main__ - Step 25804: {'lr': 0.0004687614687962659, 'samples': 4954368, 'steps': 25803, 'loss/train': 0.8512210845947266} 08/30/2021 17:48:16 - INFO - __main__ - Step 25805: {'lr': 0.0004687589000704759, 'samples': 4954560, 'steps': 25804, 'loss/train': 1.9007976055145264} 08/30/2021 17:48:18 - INFO - __main__ - Step 25806: {'lr': 0.0004687563312461165, 'samples': 4954752, 'steps': 25805, 'loss/train': 1.5209821462631226} 08/30/2021 17:48:18 - INFO - __main__ - Step 25807: {'lr': 0.00046875376232318887, 'samples': 4954944, 'steps': 25806, 'loss/train': 1.3787906169891357} 08/30/2021 17:48:19 - INFO - __main__ - Step 25808: {'lr': 0.00046875119330169426, 'samples': 4955136, 'steps': 25807, 'loss/train': 0.5449550747871399} 08/30/2021 17:48:19 - INFO - __main__ - Step 25809: {'lr': 0.00046874862418163363, 'samples': 4955328, 'steps': 25808, 'loss/train': 0.5622909069061279} 08/30/2021 17:48:19 - INFO - __main__ - Step 25810: {'lr': 0.00046874605496300824, 'samples': 4955520, 'steps': 25809, 'loss/train': 1.6267250776290894} 08/30/2021 17:48:20 - INFO - __main__ - Step 25811: {'lr': 0.00046874348564581933, 'samples': 4955712, 'steps': 25810, 'loss/train': 1.5047783851623535} 08/30/2021 17:48:20 - INFO - __main__ - Step 25812: {'lr': 0.00046874091623006793, 'samples': 4955904, 'steps': 25811, 'loss/train': 1.4574873447418213} 08/30/2021 17:48:22 - INFO - __main__ - Step 25813: {'lr': 0.0004687383467157553, 'samples': 4956096, 'steps': 25812, 'loss/train': 1.5586751699447632} 08/30/2021 17:48:22 - INFO - __main__ - Step 25814: {'lr': 0.0004687357771028825, 'samples': 4956288, 'steps': 25813, 'loss/train': 1.671359658241272} 08/30/2021 17:48:22 - INFO - __main__ - Step 25815: {'lr': 0.00046873320739145073, 'samples': 4956480, 'steps': 25814, 'loss/train': 1.4551055431365967} 08/30/2021 17:48:23 - INFO - __main__ - Step 25816: {'lr': 0.0004687306375814612, 'samples': 4956672, 'steps': 25815, 'loss/train': 1.6281694173812866} 08/30/2021 17:48:23 - INFO - __main__ - Step 25817: {'lr': 0.000468728067672915, 'samples': 4956864, 'steps': 25816, 'loss/train': 1.8594871759414673} 08/30/2021 17:48:25 - INFO - __main__ - Step 25818: {'lr': 0.00046872549766581326, 'samples': 4957056, 'steps': 25817, 'loss/train': 1.5035878419876099} 08/30/2021 17:48:25 - INFO - __main__ - Step 25819: {'lr': 0.00046872292756015724, 'samples': 4957248, 'steps': 25818, 'loss/train': 1.4658355712890625} 08/30/2021 17:48:25 - INFO - __main__ - Step 25820: {'lr': 0.000468720357355948, 'samples': 4957440, 'steps': 25819, 'loss/train': 1.4506713151931763} 08/30/2021 17:48:26 - INFO - __main__ - Step 25821: {'lr': 0.00046871778705318673, 'samples': 4957632, 'steps': 25820, 'loss/train': 1.3372007608413696} 08/30/2021 17:48:26 - INFO - __main__ - Step 25822: {'lr': 0.0004687152166518747, 'samples': 4957824, 'steps': 25821, 'loss/train': 2.044471502304077} 08/30/2021 17:48:28 - INFO - __main__ - Step 25823: {'lr': 0.0004687126461520128, 'samples': 4958016, 'steps': 25822, 'loss/train': 1.5280523300170898} 08/30/2021 17:48:28 - INFO - __main__ - Step 25824: {'lr': 0.0004687100755536025, 'samples': 4958208, 'steps': 25823, 'loss/train': 1.6051236391067505} 08/30/2021 17:48:29 - INFO - __main__ - Step 25825: {'lr': 0.00046870750485664484, 'samples': 4958400, 'steps': 25824, 'loss/train': 0.11616300791501999} 08/30/2021 17:48:29 - INFO - __main__ - Step 25826: {'lr': 0.00046870493406114084, 'samples': 4958592, 'steps': 25825, 'loss/train': 1.6234893798828125} 08/30/2021 17:48:29 - INFO - __main__ - Step 25827: {'lr': 0.0004687023631670918, 'samples': 4958784, 'steps': 25826, 'loss/train': 1.6770555973052979} 08/30/2021 17:48:31 - INFO - __main__ - Step 25828: {'lr': 0.0004686997921744989, 'samples': 4958976, 'steps': 25827, 'loss/train': 0.9241091012954712} 08/30/2021 17:48:32 - INFO - __main__ - Step 25829: {'lr': 0.0004686972210833632, 'samples': 4959168, 'steps': 25828, 'loss/train': 0.8609564900398254} 08/30/2021 17:48:32 - INFO - __main__ - Step 25830: {'lr': 0.0004686946498936859, 'samples': 4959360, 'steps': 25829, 'loss/train': 0.9588181972503662} 08/30/2021 17:48:33 - INFO - __main__ - Step 25831: {'lr': 0.00046869207860546826, 'samples': 4959552, 'steps': 25830, 'loss/train': 1.30747652053833} 08/30/2021 17:48:33 - INFO - __main__ - Step 25832: {'lr': 0.00046868950721871126, 'samples': 4959744, 'steps': 25831, 'loss/train': 0.08194424957036972} 08/30/2021 17:48:35 - INFO - __main__ - Step 25833: {'lr': 0.00046868693573341616, 'samples': 4959936, 'steps': 25832, 'loss/train': 1.5127626657485962} 08/30/2021 17:48:35 - INFO - __main__ - Step 25834: {'lr': 0.00046868436414958405, 'samples': 4960128, 'steps': 25833, 'loss/train': 1.5270503759384155} 08/30/2021 17:48:35 - INFO - __main__ - Step 25835: {'lr': 0.00046868179246721623, 'samples': 4960320, 'steps': 25834, 'loss/train': 1.227791428565979} 08/30/2021 17:48:36 - INFO - __main__ - Step 25836: {'lr': 0.00046867922068631374, 'samples': 4960512, 'steps': 25835, 'loss/train': 1.333652377128601} 08/30/2021 17:48:36 - INFO - __main__ - Step 25837: {'lr': 0.00046867664880687775, 'samples': 4960704, 'steps': 25836, 'loss/train': 1.6279029846191406} 08/30/2021 17:48:37 - INFO - __main__ - Step 25838: {'lr': 0.00046867407682890937, 'samples': 4960896, 'steps': 25837, 'loss/train': 2.670116662979126} 08/30/2021 17:48:38 - INFO - __main__ - Step 25839: {'lr': 0.00046867150475240994, 'samples': 4961088, 'steps': 25838, 'loss/train': 1.530759334564209} 08/30/2021 17:48:39 - INFO - __main__ - Step 25840: {'lr': 0.0004686689325773805, 'samples': 4961280, 'steps': 25839, 'loss/train': 0.8202062845230103} 08/30/2021 17:48:39 - INFO - __main__ - Step 25841: {'lr': 0.00046866636030382217, 'samples': 4961472, 'steps': 25840, 'loss/train': 0.588380753993988} 08/30/2021 17:48:40 - INFO - __main__ - Step 25842: {'lr': 0.00046866378793173616, 'samples': 4961664, 'steps': 25841, 'loss/train': 0.047773007303476334} 08/30/2021 17:48:40 - INFO - __main__ - Step 25843: {'lr': 0.0004686612154611236, 'samples': 4961856, 'steps': 25842, 'loss/train': 0.8975650668144226} 08/30/2021 17:48:40 - INFO - __main__ - Step 25844: {'lr': 0.0004686586428919857, 'samples': 4962048, 'steps': 25843, 'loss/train': 1.4415950775146484} 08/30/2021 17:48:42 - INFO - __main__ - Step 25845: {'lr': 0.00046865607022432356, 'samples': 4962240, 'steps': 25844, 'loss/train': 1.4818027019500732} 08/30/2021 17:48:43 - INFO - __main__ - Step 25846: {'lr': 0.00046865349745813835, 'samples': 4962432, 'steps': 25845, 'loss/train': 0.41203126311302185} 08/30/2021 17:48:43 - INFO - __main__ - Step 25847: {'lr': 0.00046865092459343126, 'samples': 4962624, 'steps': 25846, 'loss/train': 0.39638659358024597} 08/30/2021 17:48:43 - INFO - __main__ - Step 25848: {'lr': 0.00046864835163020353, 'samples': 4962816, 'steps': 25847, 'loss/train': 3.1060988903045654} 08/30/2021 17:48:44 - INFO - __main__ - Step 25849: {'lr': 0.00046864577856845613, 'samples': 4963008, 'steps': 25848, 'loss/train': 1.3016031980514526} 08/30/2021 17:48:45 - INFO - __main__ - Step 25850: {'lr': 0.0004686432054081904, 'samples': 4963200, 'steps': 25849, 'loss/train': 1.7076200246810913} 08/30/2021 17:48:46 - INFO - __main__ - Step 25851: {'lr': 0.00046864063214940735, 'samples': 4963392, 'steps': 25850, 'loss/train': 1.5625218152999878} 08/30/2021 17:48:46 - INFO - __main__ - Step 25852: {'lr': 0.0004686380587921082, 'samples': 4963584, 'steps': 25851, 'loss/train': 1.1658756732940674} 08/30/2021 17:48:46 - INFO - __main__ - Step 25853: {'lr': 0.00046863548533629406, 'samples': 4963776, 'steps': 25852, 'loss/train': 1.4682843685150146} 08/30/2021 17:48:47 - INFO - __main__ - Step 25854: {'lr': 0.00046863291178196625, 'samples': 4963968, 'steps': 25853, 'loss/train': 1.3993884325027466} 08/30/2021 17:48:48 - INFO - __main__ - Step 25855: {'lr': 0.0004686303381291258, 'samples': 4964160, 'steps': 25854, 'loss/train': 1.115661382675171} 08/30/2021 17:48:49 - INFO - __main__ - Step 25856: {'lr': 0.00046862776437777386, 'samples': 4964352, 'steps': 25855, 'loss/train': 1.8204008340835571} 08/30/2021 17:48:49 - INFO - __main__ - Step 25857: {'lr': 0.00046862519052791166, 'samples': 4964544, 'steps': 25856, 'loss/train': 1.7891380786895752} 08/30/2021 17:48:49 - INFO - __main__ - Step 25858: {'lr': 0.00046862261657954033, 'samples': 4964736, 'steps': 25857, 'loss/train': 1.8477543592453003} 08/30/2021 17:48:50 - INFO - __main__ - Step 25859: {'lr': 0.000468620042532661, 'samples': 4964928, 'steps': 25858, 'loss/train': 1.9821393489837646} 08/30/2021 17:48:50 - INFO - __main__ - Step 25860: {'lr': 0.0004686174683872748, 'samples': 4965120, 'steps': 25859, 'loss/train': 1.1302052736282349} 08/30/2021 17:48:52 - INFO - __main__ - Step 25861: {'lr': 0.00046861489414338304, 'samples': 4965312, 'steps': 25860, 'loss/train': 1.3140689134597778} 08/30/2021 17:48:52 - INFO - __main__ - Step 25862: {'lr': 0.0004686123198009867, 'samples': 4965504, 'steps': 25861, 'loss/train': 1.688848853111267} 08/30/2021 17:48:52 - INFO - __main__ - Step 25863: {'lr': 0.00046860974536008706, 'samples': 4965696, 'steps': 25862, 'loss/train': 2.353419065475464} 08/30/2021 17:48:53 - INFO - __main__ - Step 25864: {'lr': 0.0004686071708206853, 'samples': 4965888, 'steps': 25863, 'loss/train': 1.376936912536621} 08/30/2021 17:48:53 - INFO - __main__ - Step 25865: {'lr': 0.0004686045961827824, 'samples': 4966080, 'steps': 25864, 'loss/train': 1.745242714881897} 08/30/2021 17:48:55 - INFO - __main__ - Step 25866: {'lr': 0.00046860202144637976, 'samples': 4966272, 'steps': 25865, 'loss/train': 1.4062267541885376} 08/30/2021 17:48:55 - INFO - __main__ - Step 25867: {'lr': 0.00046859944661147837, 'samples': 4966464, 'steps': 25866, 'loss/train': 1.6638727188110352} 08/30/2021 17:48:55 - INFO - __main__ - Step 25868: {'lr': 0.00046859687167807943, 'samples': 4966656, 'steps': 25867, 'loss/train': 1.9906589984893799} 08/30/2021 17:48:56 - INFO - __main__ - Step 25869: {'lr': 0.0004685942966461841, 'samples': 4966848, 'steps': 25868, 'loss/train': 0.9553824663162231} 08/30/2021 17:48:56 - INFO - __main__ - Step 25870: {'lr': 0.00046859172151579354, 'samples': 4967040, 'steps': 25869, 'loss/train': 1.0746548175811768} 08/30/2021 17:48:58 - INFO - __main__ - Step 25871: {'lr': 0.00046858914628690896, 'samples': 4967232, 'steps': 25870, 'loss/train': 1.5431541204452515} 08/30/2021 17:48:58 - INFO - __main__ - Step 25872: {'lr': 0.0004685865709595315, 'samples': 4967424, 'steps': 25871, 'loss/train': 0.1604749858379364} 08/30/2021 17:48:59 - INFO - __main__ - Step 25873: {'lr': 0.00046858399553366224, 'samples': 4967616, 'steps': 25872, 'loss/train': 0.8738030791282654} 08/30/2021 17:48:59 - INFO - __main__ - Step 25874: {'lr': 0.0004685814200093025, 'samples': 4967808, 'steps': 25873, 'loss/train': 1.4320909976959229} 08/30/2021 17:48:59 - INFO - __main__ - Step 25875: {'lr': 0.00046857884438645327, 'samples': 4968000, 'steps': 25874, 'loss/train': 1.1554865837097168} 08/30/2021 17:49:01 - INFO - __main__ - Step 25876: {'lr': 0.0004685762686651158, 'samples': 4968192, 'steps': 25875, 'loss/train': 1.8846144676208496} 08/30/2021 17:49:02 - INFO - __main__ - Step 25877: {'lr': 0.0004685736928452913, 'samples': 4968384, 'steps': 25876, 'loss/train': 0.9436670541763306} 08/30/2021 17:49:02 - INFO - __main__ - Step 25878: {'lr': 0.00046857111692698083, 'samples': 4968576, 'steps': 25877, 'loss/train': 1.8042160272598267} 08/30/2021 17:49:02 - INFO - __main__ - Step 25879: {'lr': 0.0004685685409101855, 'samples': 4968768, 'steps': 25878, 'loss/train': 1.3830060958862305} 08/30/2021 17:49:03 - INFO - __main__ - Step 25880: {'lr': 0.00046856596479490667, 'samples': 4968960, 'steps': 25879, 'loss/train': 0.16645364463329315} 08/30/2021 17:49:05 - INFO - __main__ - Step 25881: {'lr': 0.0004685633885811453, 'samples': 4969152, 'steps': 25880, 'loss/train': 1.3824928998947144} 08/30/2021 17:49:05 - INFO - __main__ - Step 25882: {'lr': 0.0004685608122689027, 'samples': 4969344, 'steps': 25881, 'loss/train': 0.9586479663848877} 08/30/2021 17:49:06 - INFO - __main__ - Step 25883: {'lr': 0.00046855823585818004, 'samples': 4969536, 'steps': 25882, 'loss/train': 1.8196073770523071} 08/30/2021 17:49:06 - INFO - __main__ - Step 25884: {'lr': 0.0004685556593489783, 'samples': 4969728, 'steps': 25883, 'loss/train': 1.5329629182815552} 08/30/2021 17:49:06 - INFO - __main__ - Step 25885: {'lr': 0.0004685530827412988, 'samples': 4969920, 'steps': 25884, 'loss/train': 1.9199702739715576} 08/30/2021 17:49:08 - INFO - __main__ - Step 25886: {'lr': 0.0004685505060351426, 'samples': 4970112, 'steps': 25885, 'loss/train': 0.08527534455060959} 08/30/2021 17:49:08 - INFO - __main__ - Step 25887: {'lr': 0.00046854792923051094, 'samples': 4970304, 'steps': 25886, 'loss/train': 1.6177213191986084} 08/30/2021 17:49:09 - INFO - __main__ - Step 25888: {'lr': 0.00046854535232740505, 'samples': 4970496, 'steps': 25887, 'loss/train': 1.8536111116409302} 08/30/2021 17:49:09 - INFO - __main__ - Step 25889: {'lr': 0.00046854277532582585, 'samples': 4970688, 'steps': 25888, 'loss/train': 1.2673453092575073} 08/30/2021 17:49:10 - INFO - __main__ - Step 25890: {'lr': 0.0004685401982257747, 'samples': 4970880, 'steps': 25889, 'loss/train': 1.2118864059448242} 08/30/2021 17:49:11 - INFO - __main__ - Step 25891: {'lr': 0.0004685376210272527, 'samples': 4971072, 'steps': 25890, 'loss/train': 1.2783883810043335} 08/30/2021 17:49:11 - INFO - __main__ - Step 25892: {'lr': 0.00046853504373026107, 'samples': 4971264, 'steps': 25891, 'loss/train': 1.3913556337356567} 08/30/2021 17:49:12 - INFO - __main__ - Step 25893: {'lr': 0.00046853246633480087, 'samples': 4971456, 'steps': 25892, 'loss/train': 0.5311654806137085} 08/30/2021 17:49:12 - INFO - __main__ - Step 25894: {'lr': 0.0004685298888408733, 'samples': 4971648, 'steps': 25893, 'loss/train': 1.2150635719299316} 08/30/2021 17:49:13 - INFO - __main__ - Step 25895: {'lr': 0.0004685273112484796, 'samples': 4971840, 'steps': 25894, 'loss/train': 1.3217010498046875} 08/30/2021 17:49:14 - INFO - __main__ - Step 25896: {'lr': 0.0004685247335576209, 'samples': 4972032, 'steps': 25895, 'loss/train': 1.5537326335906982} 08/30/2021 17:49:15 - INFO - __main__ - Step 25897: {'lr': 0.00046852215576829824, 'samples': 4972224, 'steps': 25896, 'loss/train': 2.15730881690979} 08/30/2021 17:49:15 - INFO - __main__ - Step 25898: {'lr': 0.0004685195778805129, 'samples': 4972416, 'steps': 25897, 'loss/train': 1.7009484767913818} 08/30/2021 17:49:15 - INFO - __main__ - Step 25899: {'lr': 0.000468516999894266, 'samples': 4972608, 'steps': 25898, 'loss/train': 1.350884199142456} 08/30/2021 17:49:16 - INFO - __main__ - Step 25900: {'lr': 0.0004685144218095587, 'samples': 4972800, 'steps': 25899, 'loss/train': 1.6464431285858154} 08/30/2021 17:49:16 - INFO - __main__ - Step 25901: {'lr': 0.00046851184362639223, 'samples': 4972992, 'steps': 25900, 'loss/train': 1.436650037765503} 08/30/2021 17:49:18 - INFO - __main__ - Step 25902: {'lr': 0.0004685092653447676, 'samples': 4973184, 'steps': 25901, 'loss/train': 1.5484634637832642} 08/30/2021 17:49:18 - INFO - __main__ - Step 25903: {'lr': 0.00046850668696468614, 'samples': 4973376, 'steps': 25902, 'loss/train': 1.5408024787902832} 08/30/2021 17:49:19 - INFO - __main__ - Step 25904: {'lr': 0.0004685041084861489, 'samples': 4973568, 'steps': 25903, 'loss/train': 1.5481486320495605} 08/30/2021 17:49:19 - INFO - __main__ - Step 25905: {'lr': 0.00046850152990915705, 'samples': 4973760, 'steps': 25904, 'loss/train': 2.10436749458313} 08/30/2021 17:49:19 - INFO - __main__ - Step 25906: {'lr': 0.0004684989512337119, 'samples': 4973952, 'steps': 25905, 'loss/train': 1.1209992170333862} 08/30/2021 17:49:21 - INFO - __main__ - Step 25907: {'lr': 0.00046849637245981434, 'samples': 4974144, 'steps': 25906, 'loss/train': 1.4587196111679077} 08/30/2021 17:49:21 - INFO - __main__ - Step 25908: {'lr': 0.0004684937935874658, 'samples': 4974336, 'steps': 25907, 'loss/train': 1.7507963180541992} 08/30/2021 17:49:22 - INFO - __main__ - Step 25909: {'lr': 0.00046849121461666734, 'samples': 4974528, 'steps': 25908, 'loss/train': 1.6651357412338257} 08/30/2021 17:49:22 - INFO - __main__ - Step 25910: {'lr': 0.00046848863554742006, 'samples': 4974720, 'steps': 25909, 'loss/train': 0.44157132506370544} 08/30/2021 17:49:22 - INFO - __main__ - Step 25911: {'lr': 0.0004684860563797252, 'samples': 4974912, 'steps': 25910, 'loss/train': 1.385323166847229} 08/30/2021 17:49:24 - INFO - __main__ - Step 25912: {'lr': 0.00046848347711358384, 'samples': 4975104, 'steps': 25911, 'loss/train': 1.5163391828536987} 08/30/2021 17:49:24 - INFO - __main__ - Step 25913: {'lr': 0.0004684808977489973, 'samples': 4975296, 'steps': 25912, 'loss/train': 1.2386027574539185} 08/30/2021 17:49:25 - INFO - __main__ - Step 25914: {'lr': 0.00046847831828596647, 'samples': 4975488, 'steps': 25913, 'loss/train': 1.4422698020935059} 08/30/2021 17:49:25 - INFO - __main__ - Step 25915: {'lr': 0.0004684757387244928, 'samples': 4975680, 'steps': 25914, 'loss/train': 1.869231104850769} 08/30/2021 17:49:25 - INFO - __main__ - Step 25916: {'lr': 0.00046847315906457733, 'samples': 4975872, 'steps': 25915, 'loss/train': 1.5322262048721313} 08/30/2021 17:49:27 - INFO - __main__ - Step 25917: {'lr': 0.0004684705793062212, 'samples': 4976064, 'steps': 25916, 'loss/train': 1.3759723901748657} 08/30/2021 17:49:27 - INFO - __main__ - Step 25918: {'lr': 0.00046846799944942564, 'samples': 4976256, 'steps': 25917, 'loss/train': 1.4368705749511719} 08/30/2021 17:49:28 - INFO - __main__ - Step 25919: {'lr': 0.00046846541949419177, 'samples': 4976448, 'steps': 25918, 'loss/train': 0.6463767886161804} 08/30/2021 17:49:28 - INFO - __main__ - Step 25920: {'lr': 0.00046846283944052073, 'samples': 4976640, 'steps': 25919, 'loss/train': 1.723982334136963} 08/30/2021 17:49:28 - INFO - __main__ - Step 25921: {'lr': 0.0004684602592884136, 'samples': 4976832, 'steps': 25920, 'loss/train': 0.3706967830657959} 08/30/2021 17:49:30 - INFO - __main__ - Step 25922: {'lr': 0.0004684576790378718, 'samples': 4977024, 'steps': 25921, 'loss/train': 1.5728548765182495} 08/30/2021 17:49:31 - INFO - __main__ - Step 25923: {'lr': 0.00046845509868889625, 'samples': 4977216, 'steps': 25922, 'loss/train': 1.5348352193832397} 08/30/2021 17:49:31 - INFO - __main__ - Step 25924: {'lr': 0.00046845251824148825, 'samples': 4977408, 'steps': 25923, 'loss/train': 1.6719447374343872} 08/30/2021 17:49:31 - INFO - __main__ - Step 25925: {'lr': 0.0004684499376956489, 'samples': 4977600, 'steps': 25924, 'loss/train': 0.8076337575912476} 08/30/2021 17:49:32 - INFO - __main__ - Step 25926: {'lr': 0.00046844735705137944, 'samples': 4977792, 'steps': 25925, 'loss/train': 1.2432372570037842} 08/30/2021 17:49:32 - INFO - __main__ - Step 25927: {'lr': 0.0004684447763086809, 'samples': 4977984, 'steps': 25926, 'loss/train': 1.2376854419708252} 08/30/2021 17:49:34 - INFO - __main__ - Step 25928: {'lr': 0.00046844219546755454, 'samples': 4978176, 'steps': 25927, 'loss/train': 2.077136754989624} 08/30/2021 17:49:34 - INFO - __main__ - Step 25929: {'lr': 0.0004684396145280014, 'samples': 4978368, 'steps': 25928, 'loss/train': 1.3480955362319946} 08/30/2021 17:49:34 - INFO - __main__ - Step 25930: {'lr': 0.00046843703349002286, 'samples': 4978560, 'steps': 25929, 'loss/train': 1.5316728353500366} 08/30/2021 17:49:35 - INFO - __main__ - Step 25931: {'lr': 0.00046843445235361994, 'samples': 4978752, 'steps': 25930, 'loss/train': 0.6487564444541931} 08/30/2021 17:49:35 - INFO - __main__ - Step 25932: {'lr': 0.0004684318711187938, 'samples': 4978944, 'steps': 25931, 'loss/train': 0.9000486135482788} 08/30/2021 17:49:37 - INFO - __main__ - Step 25933: {'lr': 0.0004684292897855457, 'samples': 4979136, 'steps': 25932, 'loss/train': 1.7701318264007568} 08/30/2021 17:49:37 - INFO - __main__ - Step 25934: {'lr': 0.00046842670835387667, 'samples': 4979328, 'steps': 25933, 'loss/train': 1.7426519393920898} 08/30/2021 17:49:38 - INFO - __main__ - Step 25935: {'lr': 0.00046842412682378796, 'samples': 4979520, 'steps': 25934, 'loss/train': 2.0687735080718994} 08/30/2021 17:49:38 - INFO - __main__ - Step 25936: {'lr': 0.0004684215451952807, 'samples': 4979712, 'steps': 25935, 'loss/train': 0.18766005337238312} 08/30/2021 17:49:38 - INFO - __main__ - Step 25937: {'lr': 0.000468418963468356, 'samples': 4979904, 'steps': 25936, 'loss/train': 0.8473954200744629} 08/30/2021 17:49:40 - INFO - __main__ - Step 25938: {'lr': 0.0004684163816430152, 'samples': 4980096, 'steps': 25937, 'loss/train': 1.2398358583450317} 08/30/2021 17:49:41 - INFO - __main__ - Step 25939: {'lr': 0.00046841379971925923, 'samples': 4980288, 'steps': 25938, 'loss/train': 2.2545342445373535} 08/30/2021 17:49:41 - INFO - __main__ - Step 25940: {'lr': 0.0004684112176970895, 'samples': 4980480, 'steps': 25939, 'loss/train': 0.9708952307701111} 08/30/2021 17:49:42 - INFO - __main__ - Step 25941: {'lr': 0.0004684086355765069, 'samples': 4980672, 'steps': 25940, 'loss/train': 1.5442172288894653} 08/30/2021 17:49:42 - INFO - __main__ - Step 25942: {'lr': 0.00046840605335751284, 'samples': 4980864, 'steps': 25941, 'loss/train': 0.12289529293775558} 08/30/2021 17:49:42 - INFO - __main__ - Step 25943: {'lr': 0.0004684034710401084, 'samples': 4981056, 'steps': 25942, 'loss/train': 1.1677873134613037} 08/30/2021 17:49:44 - INFO - __main__ - Step 25944: {'lr': 0.00046840088862429465, 'samples': 4981248, 'steps': 25943, 'loss/train': 0.9567702412605286} 08/30/2021 17:49:44 - INFO - __main__ - Step 25945: {'lr': 0.00046839830611007297, 'samples': 4981440, 'steps': 25944, 'loss/train': 1.7980859279632568} 08/30/2021 17:49:44 - INFO - __main__ - Step 25946: {'lr': 0.00046839572349744417, 'samples': 4981632, 'steps': 25945, 'loss/train': 1.9469941854476929} 08/30/2021 17:49:45 - INFO - __main__ - Step 25947: {'lr': 0.0004683931407864098, 'samples': 4981824, 'steps': 25946, 'loss/train': 1.7215113639831543} 08/30/2021 17:49:45 - INFO - __main__ - Step 25948: {'lr': 0.0004683905579769708, 'samples': 4982016, 'steps': 25947, 'loss/train': 1.8378640413284302} 08/30/2021 17:49:47 - INFO - __main__ - Step 25949: {'lr': 0.0004683879750691283, 'samples': 4982208, 'steps': 25948, 'loss/train': 1.6385730504989624} 08/30/2021 17:49:47 - INFO - __main__ - Step 25950: {'lr': 0.00046838539206288366, 'samples': 4982400, 'steps': 25949, 'loss/train': 0.9481050968170166} 08/30/2021 17:49:48 - INFO - __main__ - Step 25951: {'lr': 0.00046838280895823795, 'samples': 4982592, 'steps': 25950, 'loss/train': 1.8381636142730713} 08/30/2021 17:49:48 - INFO - __main__ - Step 25952: {'lr': 0.0004683802257551922, 'samples': 4982784, 'steps': 25951, 'loss/train': 0.21413718163967133} 08/30/2021 17:49:48 - INFO - __main__ - Step 25953: {'lr': 0.00046837764245374777, 'samples': 4982976, 'steps': 25952, 'loss/train': 1.6276837587356567} 08/30/2021 17:49:50 - INFO - __main__ - Step 25954: {'lr': 0.0004683750590539057, 'samples': 4983168, 'steps': 25953, 'loss/train': 1.499752163887024} 08/30/2021 17:49:51 - INFO - __main__ - Step 25955: {'lr': 0.00046837247555566727, 'samples': 4983360, 'steps': 25954, 'loss/train': 1.5714073181152344} 08/30/2021 17:49:51 - INFO - __main__ - Step 25956: {'lr': 0.00046836989195903344, 'samples': 4983552, 'steps': 25955, 'loss/train': 1.6329160928726196} 08/30/2021 17:49:51 - INFO - __main__ - Step 25957: {'lr': 0.00046836730826400565, 'samples': 4983744, 'steps': 25956, 'loss/train': 0.05928225815296173} 08/30/2021 17:49:52 - INFO - __main__ - Step 25958: {'lr': 0.00046836472447058485, 'samples': 4983936, 'steps': 25957, 'loss/train': 1.316361427307129} 08/30/2021 17:49:52 - INFO - __main__ - Step 25959: {'lr': 0.0004683621405787723, 'samples': 4984128, 'steps': 25958, 'loss/train': 1.761487364768982} 08/30/2021 17:49:54 - INFO - __main__ - Step 25960: {'lr': 0.0004683595565885691, 'samples': 4984320, 'steps': 25959, 'loss/train': 1.3059948682785034} 08/30/2021 17:49:54 - INFO - __main__ - Step 25961: {'lr': 0.0004683569724999765, 'samples': 4984512, 'steps': 25960, 'loss/train': 1.4094239473342896} 08/30/2021 17:49:54 - INFO - __main__ - Step 25962: {'lr': 0.0004683543883129956, 'samples': 4984704, 'steps': 25961, 'loss/train': 1.1170181035995483} 08/30/2021 17:49:55 - INFO - __main__ - Step 25963: {'lr': 0.00046835180402762756, 'samples': 4984896, 'steps': 25962, 'loss/train': 1.4737088680267334} 08/30/2021 17:49:55 - INFO - __main__ - Step 25964: {'lr': 0.00046834921964387363, 'samples': 4985088, 'steps': 25963, 'loss/train': 1.6293675899505615} 08/30/2021 17:49:57 - INFO - __main__ - Step 25965: {'lr': 0.0004683466351617348, 'samples': 4985280, 'steps': 25964, 'loss/train': 1.4512293338775635} 08/30/2021 17:49:57 - INFO - __main__ - Step 25966: {'lr': 0.00046834405058121244, 'samples': 4985472, 'steps': 25965, 'loss/train': 1.2718610763549805} 08/30/2021 17:49:58 - INFO - __main__ - Step 25967: {'lr': 0.0004683414659023076, 'samples': 4985664, 'steps': 25966, 'loss/train': 1.3894829750061035} 08/30/2021 17:49:58 - INFO - __main__ - Step 25968: {'lr': 0.0004683388811250214, 'samples': 4985856, 'steps': 25967, 'loss/train': 0.07728894799947739} 08/30/2021 17:49:58 - INFO - __main__ - Step 25969: {'lr': 0.0004683362962493552, 'samples': 4986048, 'steps': 25968, 'loss/train': 1.0849885940551758} 08/30/2021 17:50:00 - INFO - __main__ - Step 25970: {'lr': 0.00046833371127530995, 'samples': 4986240, 'steps': 25969, 'loss/train': 1.3206024169921875} 08/30/2021 17:50:00 - INFO - __main__ - Step 25971: {'lr': 0.00046833112620288684, 'samples': 4986432, 'steps': 25970, 'loss/train': 1.8398730754852295} 08/30/2021 17:50:01 - INFO - __main__ - Step 25972: {'lr': 0.0004683285410320872, 'samples': 4986624, 'steps': 25971, 'loss/train': 1.4553896188735962} 08/30/2021 17:50:01 - INFO - __main__ - Step 25973: {'lr': 0.000468325955762912, 'samples': 4986816, 'steps': 25972, 'loss/train': 2.4145243167877197} 08/30/2021 17:50:01 - INFO - __main__ - Step 25974: {'lr': 0.0004683233703953626, 'samples': 4987008, 'steps': 25973, 'loss/train': 0.05586782097816467} 08/30/2021 17:50:03 - INFO - __main__ - Step 25975: {'lr': 0.00046832078492944, 'samples': 4987200, 'steps': 25974, 'loss/train': 1.1521482467651367} 08/30/2021 17:50:04 - INFO - __main__ - Step 25976: {'lr': 0.0004683181993651454, 'samples': 4987392, 'steps': 25975, 'loss/train': 1.6343966722488403} 08/30/2021 17:50:04 - INFO - __main__ - Step 25977: {'lr': 0.0004683156137024801, 'samples': 4987584, 'steps': 25976, 'loss/train': 1.1978342533111572} 08/30/2021 17:50:05 - INFO - __main__ - Step 25978: {'lr': 0.00046831302794144504, 'samples': 4987776, 'steps': 25977, 'loss/train': 1.5771232843399048} 08/30/2021 17:50:05 - INFO - __main__ - Step 25979: {'lr': 0.00046831044208204154, 'samples': 4987968, 'steps': 25978, 'loss/train': 0.8119454383850098} 08/30/2021 17:50:05 - INFO - __main__ - Step 25980: {'lr': 0.0004683078561242707, 'samples': 4988160, 'steps': 25979, 'loss/train': 1.2827008962631226} 08/30/2021 17:50:06 - INFO - __main__ - Step 25981: {'lr': 0.00046830527006813373, 'samples': 4988352, 'steps': 25980, 'loss/train': 1.6679977178573608} 08/30/2021 17:50:07 - INFO - __main__ - Step 25982: {'lr': 0.00046830268391363176, 'samples': 4988544, 'steps': 25981, 'loss/train': 1.65229332447052} 08/30/2021 17:50:08 - INFO - __main__ - Step 25983: {'lr': 0.0004683000976607659, 'samples': 4988736, 'steps': 25982, 'loss/train': 1.8264904022216797} 08/30/2021 17:50:08 - INFO - __main__ - Step 25984: {'lr': 0.00046829751130953747, 'samples': 4988928, 'steps': 25983, 'loss/train': 1.3469122648239136} 08/30/2021 17:50:08 - INFO - __main__ - Step 25985: {'lr': 0.0004682949248599476, 'samples': 4989120, 'steps': 25984, 'loss/train': 1.5895007848739624} 08/30/2021 17:50:09 - INFO - __main__ - Step 25986: {'lr': 0.0004682923383119973, 'samples': 4989312, 'steps': 25985, 'loss/train': 1.8001866340637207} 08/30/2021 17:50:10 - INFO - __main__ - Step 25987: {'lr': 0.0004682897516656879, 'samples': 4989504, 'steps': 25986, 'loss/train': 1.8371360301971436} 08/30/2021 17:50:11 - INFO - __main__ - Step 25988: {'lr': 0.00046828716492102043, 'samples': 4989696, 'steps': 25987, 'loss/train': 1.1633650064468384} 08/30/2021 17:50:11 - INFO - __main__ - Step 25989: {'lr': 0.0004682845780779962, 'samples': 4989888, 'steps': 25988, 'loss/train': 1.2397024631500244} 08/30/2021 17:50:11 - INFO - __main__ - Step 25990: {'lr': 0.00046828199113661627, 'samples': 4990080, 'steps': 25989, 'loss/train': 1.7234729528427124} 08/30/2021 17:50:12 - INFO - __main__ - Step 25991: {'lr': 0.0004682794040968819, 'samples': 4990272, 'steps': 25990, 'loss/train': 1.2466639280319214} 08/30/2021 17:50:14 - INFO - __main__ - Step 25992: {'lr': 0.0004682768169587942, 'samples': 4990464, 'steps': 25991, 'loss/train': 1.100614070892334} 08/30/2021 17:50:15 - INFO - __main__ - Step 25993: {'lr': 0.0004682742297223543, 'samples': 4990656, 'steps': 25992, 'loss/train': 1.6922521591186523} 08/30/2021 17:50:15 - INFO - __main__ - Step 25994: {'lr': 0.00046827164238756337, 'samples': 4990848, 'steps': 25993, 'loss/train': 0.9433560371398926} 08/30/2021 17:50:15 - INFO - __main__ - Step 25995: {'lr': 0.00046826905495442263, 'samples': 4991040, 'steps': 25994, 'loss/train': 0.9941039681434631} 08/30/2021 17:50:16 - INFO - __main__ - Step 25996: {'lr': 0.00046826646742293326, 'samples': 4991232, 'steps': 25995, 'loss/train': 1.782634973526001} 08/30/2021 17:50:16 - INFO - __main__ - Step 25997: {'lr': 0.00046826387979309635, 'samples': 4991424, 'steps': 25996, 'loss/train': 3.086235761642456} 08/30/2021 17:50:18 - INFO - __main__ - Step 25998: {'lr': 0.0004682612920649131, 'samples': 4991616, 'steps': 25997, 'loss/train': 0.8794245719909668} 08/30/2021 17:50:18 - INFO - __main__ - Step 25999: {'lr': 0.00046825870423838466, 'samples': 4991808, 'steps': 25998, 'loss/train': 0.8561205863952637} 08/30/2021 17:50:18 - INFO - __main__ - Step 26000: {'lr': 0.00046825611631351227, 'samples': 4992000, 'steps': 25999, 'loss/train': 0.7992864847183228} 08/30/2021 17:50:19 - INFO - __main__ - Step 26001: {'lr': 0.00046825352829029705, 'samples': 4992192, 'steps': 26000, 'loss/train': 1.2635619640350342} 08/30/2021 17:50:19 - INFO - __main__ - Step 26002: {'lr': 0.00046825094016874014, 'samples': 4992384, 'steps': 26001, 'loss/train': 0.7718640565872192} 08/30/2021 17:50:21 - INFO - __main__ - Step 26003: {'lr': 0.00046824835194884273, 'samples': 4992576, 'steps': 26002, 'loss/train': 2.029985189437866} 08/30/2021 17:50:21 - INFO - __main__ - Step 26004: {'lr': 0.0004682457636306059, 'samples': 4992768, 'steps': 26003, 'loss/train': 0.8590334057807922} 08/30/2021 17:50:22 - INFO - __main__ - Step 26005: {'lr': 0.000468243175214031, 'samples': 4992960, 'steps': 26004, 'loss/train': 1.890396237373352} 08/30/2021 17:50:22 - INFO - __main__ - Step 26006: {'lr': 0.00046824058669911906, 'samples': 4993152, 'steps': 26005, 'loss/train': 1.6611837148666382} 08/30/2021 17:50:22 - INFO - __main__ - Step 26007: {'lr': 0.00046823799808587126, 'samples': 4993344, 'steps': 26006, 'loss/train': 1.3633774518966675} 08/30/2021 17:50:23 - INFO - __main__ - Step 26008: {'lr': 0.00046823540937428876, 'samples': 4993536, 'steps': 26007, 'loss/train': 1.5682960748672485} 08/30/2021 17:50:24 - INFO - __main__ - Step 26009: {'lr': 0.0004682328205643728, 'samples': 4993728, 'steps': 26008, 'loss/train': 1.2900131940841675} 08/30/2021 17:50:25 - INFO - __main__ - Step 26010: {'lr': 0.00046823023165612455, 'samples': 4993920, 'steps': 26009, 'loss/train': 1.6659449338912964} 08/30/2021 17:50:25 - INFO - __main__ - Step 26011: {'lr': 0.000468227642649545, 'samples': 4994112, 'steps': 26010, 'loss/train': 1.5601441860198975} 08/30/2021 17:50:25 - INFO - __main__ - Step 26012: {'lr': 0.00046822505354463553, 'samples': 4994304, 'steps': 26011, 'loss/train': 1.3833215236663818} 08/30/2021 17:50:26 - INFO - __main__ - Step 26013: {'lr': 0.0004682224643413972, 'samples': 4994496, 'steps': 26012, 'loss/train': 1.6717795133590698} 08/30/2021 17:50:27 - INFO - __main__ - Step 26014: {'lr': 0.0004682198750398312, 'samples': 4994688, 'steps': 26013, 'loss/train': 1.347379446029663} 08/30/2021 17:50:28 - INFO - __main__ - Step 26015: {'lr': 0.00046821728563993867, 'samples': 4994880, 'steps': 26014, 'loss/train': 0.42934542894363403} 08/30/2021 17:50:28 - INFO - __main__ - Step 26016: {'lr': 0.0004682146961417208, 'samples': 4995072, 'steps': 26015, 'loss/train': 1.59308922290802} 08/30/2021 17:50:28 - INFO - __main__ - Step 26017: {'lr': 0.00046821210654517874, 'samples': 4995264, 'steps': 26016, 'loss/train': 1.338724970817566} 08/30/2021 17:50:29 - INFO - __main__ - Step 26018: {'lr': 0.0004682095168503137, 'samples': 4995456, 'steps': 26017, 'loss/train': 1.399625539779663} 08/30/2021 17:50:30 - INFO - __main__ - Step 26019: {'lr': 0.00046820692705712685, 'samples': 4995648, 'steps': 26018, 'loss/train': 1.3258057832717896} 08/30/2021 17:50:31 - INFO - __main__ - Step 26020: {'lr': 0.00046820433716561927, 'samples': 4995840, 'steps': 26019, 'loss/train': 0.8071329593658447} 08/30/2021 17:50:31 - INFO - __main__ - Step 26021: {'lr': 0.0004682017471757922, 'samples': 4996032, 'steps': 26020, 'loss/train': 1.1271674633026123} 08/30/2021 17:50:32 - INFO - __main__ - Step 26022: {'lr': 0.0004681991570876468, 'samples': 4996224, 'steps': 26021, 'loss/train': 1.7399072647094727} 08/30/2021 17:50:32 - INFO - __main__ - Step 26023: {'lr': 0.00046819656690118424, 'samples': 4996416, 'steps': 26022, 'loss/train': 0.3772258162498474} 08/30/2021 17:50:32 - INFO - __main__ - Step 26024: {'lr': 0.00046819397661640563, 'samples': 4996608, 'steps': 26023, 'loss/train': 1.1453603506088257} 08/30/2021 17:50:34 - INFO - __main__ - Step 26025: {'lr': 0.0004681913862333122, 'samples': 4996800, 'steps': 26024, 'loss/train': 1.5894954204559326} 08/30/2021 17:50:34 - INFO - __main__ - Step 26026: {'lr': 0.0004681887957519051, 'samples': 4996992, 'steps': 26025, 'loss/train': 1.5680606365203857} 08/30/2021 17:50:35 - INFO - __main__ - Step 26027: {'lr': 0.00046818620517218544, 'samples': 4997184, 'steps': 26026, 'loss/train': 1.8114136457443237} 08/30/2021 17:50:35 - INFO - __main__ - Step 26028: {'lr': 0.00046818361449415456, 'samples': 4997376, 'steps': 26027, 'loss/train': 1.4232066869735718} 08/30/2021 17:50:35 - INFO - __main__ - Step 26029: {'lr': 0.00046818102371781343, 'samples': 4997568, 'steps': 26028, 'loss/train': 1.4627221822738647} 08/30/2021 17:50:37 - INFO - __main__ - Step 26030: {'lr': 0.0004681784328431633, 'samples': 4997760, 'steps': 26029, 'loss/train': 1.7061995267868042} 08/30/2021 17:50:37 - INFO - __main__ - Step 26031: {'lr': 0.0004681758418702054, 'samples': 4997952, 'steps': 26030, 'loss/train': 1.5513299703598022} 08/30/2021 17:50:37 - INFO - __main__ - Step 26032: {'lr': 0.0004681732507989408, 'samples': 4998144, 'steps': 26031, 'loss/train': 1.32917320728302} 08/30/2021 17:50:38 - INFO - __main__ - Step 26033: {'lr': 0.00046817065962937067, 'samples': 4998336, 'steps': 26032, 'loss/train': 1.118119478225708} 08/30/2021 17:50:38 - INFO - __main__ - Step 26034: {'lr': 0.00046816806836149624, 'samples': 4998528, 'steps': 26033, 'loss/train': 1.4400163888931274} 08/30/2021 17:50:40 - INFO - __main__ - Step 26035: {'lr': 0.00046816547699531866, 'samples': 4998720, 'steps': 26034, 'loss/train': 1.7957981824874878} 08/30/2021 17:50:40 - INFO - __main__ - Step 26036: {'lr': 0.000468162885530839, 'samples': 4998912, 'steps': 26035, 'loss/train': 1.4501303434371948} 08/30/2021 17:50:40 - INFO - __main__ - Step 26037: {'lr': 0.00046816029396805857, 'samples': 4999104, 'steps': 26036, 'loss/train': 1.2901222705841064} 08/30/2021 17:50:41 - INFO - __main__ - Step 26038: {'lr': 0.00046815770230697844, 'samples': 4999296, 'steps': 26037, 'loss/train': 1.858233094215393} 08/30/2021 17:50:41 - INFO - __main__ - Step 26039: {'lr': 0.0004681551105475999, 'samples': 4999488, 'steps': 26038, 'loss/train': 1.8129796981811523} 08/30/2021 17:50:41 - INFO - __main__ - Step 26040: {'lr': 0.0004681525186899239, 'samples': 4999680, 'steps': 26039, 'loss/train': 1.7217713594436646} 08/30/2021 17:50:43 - INFO - __main__ - Step 26041: {'lr': 0.00046814992673395185, 'samples': 4999872, 'steps': 26040, 'loss/train': 1.1990773677825928} 08/30/2021 17:50:44 - INFO - __main__ - Step 26042: {'lr': 0.0004681473346796848, 'samples': 5000064, 'steps': 26041, 'loss/train': 1.7544848918914795} 08/30/2021 17:50:44 - INFO - __main__ - Step 26043: {'lr': 0.0004681447425271239, 'samples': 5000256, 'steps': 26042, 'loss/train': 1.2271026372909546} 08/30/2021 17:50:44 - INFO - __main__ - Step 26044: {'lr': 0.0004681421502762704, 'samples': 5000448, 'steps': 26043, 'loss/train': 1.074222207069397} 08/30/2021 17:50:45 - INFO - __main__ - Step 26045: {'lr': 0.0004681395579271253, 'samples': 5000640, 'steps': 26044, 'loss/train': 2.0768239498138428} 08/30/2021 17:50:47 - INFO - __main__ - Step 26046: {'lr': 0.00046813696547969, 'samples': 5000832, 'steps': 26045, 'loss/train': 1.8352888822555542} 08/30/2021 17:50:48 - INFO - __main__ - Step 26047: {'lr': 0.00046813437293396543, 'samples': 5001024, 'steps': 26046, 'loss/train': 1.2411599159240723} 08/30/2021 17:50:48 - INFO - __main__ - Step 26048: {'lr': 0.000468131780289953, 'samples': 5001216, 'steps': 26047, 'loss/train': 4.784865379333496} 08/30/2021 17:50:48 - INFO - __main__ - Step 26049: {'lr': 0.00046812918754765364, 'samples': 5001408, 'steps': 26048, 'loss/train': 2.1499345302581787} 08/30/2021 17:50:49 - INFO - __main__ - Step 26050: {'lr': 0.00046812659470706877, 'samples': 5001600, 'steps': 26049, 'loss/train': 1.6595525741577148} 08/30/2021 17:50:49 - INFO - __main__ - Step 26051: {'lr': 0.0004681240017681993, 'samples': 5001792, 'steps': 26050, 'loss/train': 0.07554569095373154} 08/30/2021 17:50:51 - INFO - __main__ - Step 26052: {'lr': 0.00046812140873104657, 'samples': 5001984, 'steps': 26051, 'loss/train': 0.09549978375434875} 08/30/2021 17:50:51 - INFO - __main__ - Step 26053: {'lr': 0.00046811881559561167, 'samples': 5002176, 'steps': 26052, 'loss/train': 1.808426856994629} 08/30/2021 17:50:51 - INFO - __main__ - Step 26054: {'lr': 0.00046811622236189585, 'samples': 5002368, 'steps': 26053, 'loss/train': 2.0313563346862793} 08/30/2021 17:50:52 - INFO - __main__ - Step 26055: {'lr': 0.0004681136290299002, 'samples': 5002560, 'steps': 26054, 'loss/train': 1.5682562589645386} 08/30/2021 17:50:52 - INFO - __main__ - Step 26056: {'lr': 0.00046811103559962585, 'samples': 5002752, 'steps': 26055, 'loss/train': 1.0956287384033203} 08/30/2021 17:50:54 - INFO - __main__ - Step 26057: {'lr': 0.00046810844207107415, 'samples': 5002944, 'steps': 26056, 'loss/train': 1.8528767824172974} 08/30/2021 17:50:54 - INFO - __main__ - Step 26058: {'lr': 0.0004681058484442461, 'samples': 5003136, 'steps': 26057, 'loss/train': 1.6794477701187134} 08/30/2021 17:50:54 - INFO - __main__ - Step 26059: {'lr': 0.00046810325471914295, 'samples': 5003328, 'steps': 26058, 'loss/train': 1.7115200757980347} 08/30/2021 17:50:55 - INFO - __main__ - Step 26060: {'lr': 0.00046810066089576573, 'samples': 5003520, 'steps': 26059, 'loss/train': 1.1765812635421753} 08/30/2021 17:50:55 - INFO - __main__ - Step 26061: {'lr': 0.00046809806697411583, 'samples': 5003712, 'steps': 26060, 'loss/train': 2.1888034343719482} 08/30/2021 17:50:55 - INFO - __main__ - Step 26062: {'lr': 0.0004680954729541942, 'samples': 5003904, 'steps': 26061, 'loss/train': 1.1539087295532227} 08/30/2021 17:50:57 - INFO - __main__ - Step 26063: {'lr': 0.00046809287883600227, 'samples': 5004096, 'steps': 26062, 'loss/train': 2.0836567878723145} 08/30/2021 17:50:57 - INFO - __main__ - Step 26064: {'lr': 0.00046809028461954093, 'samples': 5004288, 'steps': 26063, 'loss/train': 1.8824714422225952} 08/30/2021 17:50:58 - INFO - __main__ - Step 26065: {'lr': 0.00046808769030481153, 'samples': 5004480, 'steps': 26064, 'loss/train': 1.9013277292251587} 08/30/2021 17:50:58 - INFO - __main__ - Step 26066: {'lr': 0.00046808509589181513, 'samples': 5004672, 'steps': 26065, 'loss/train': 1.2778221368789673} 08/30/2021 17:50:58 - INFO - __main__ - Step 26067: {'lr': 0.00046808250138055305, 'samples': 5004864, 'steps': 26066, 'loss/train': 1.5713587999343872} 08/30/2021 17:51:00 - INFO - __main__ - Step 26068: {'lr': 0.0004680799067710263, 'samples': 5005056, 'steps': 26067, 'loss/train': 1.123359203338623} 08/30/2021 17:51:00 - INFO - __main__ - Step 26069: {'lr': 0.00046807731206323605, 'samples': 5005248, 'steps': 26068, 'loss/train': 1.8972338438034058} 08/30/2021 17:51:01 - INFO - __main__ - Step 26070: {'lr': 0.00046807471725718357, 'samples': 5005440, 'steps': 26069, 'loss/train': 1.82386314868927} 08/30/2021 17:51:01 - INFO - __main__ - Step 26071: {'lr': 0.00046807212235287, 'samples': 5005632, 'steps': 26070, 'loss/train': 2.1682937145233154} 08/30/2021 17:51:01 - INFO - __main__ - Step 26072: {'lr': 0.0004680695273502965, 'samples': 5005824, 'steps': 26071, 'loss/train': 1.6509768962860107} 08/30/2021 17:51:03 - INFO - __main__ - Step 26073: {'lr': 0.00046806693224946426, 'samples': 5006016, 'steps': 26072, 'loss/train': 1.665516972541809} 08/30/2021 17:51:03 - INFO - __main__ - Step 26074: {'lr': 0.00046806433705037445, 'samples': 5006208, 'steps': 26073, 'loss/train': 1.6082911491394043} 08/30/2021 17:51:04 - INFO - __main__ - Step 26075: {'lr': 0.00046806174175302806, 'samples': 5006400, 'steps': 26074, 'loss/train': 1.735235571861267} 08/30/2021 17:51:04 - INFO - __main__ - Step 26076: {'lr': 0.00046805914635742656, 'samples': 5006592, 'steps': 26075, 'loss/train': 1.4829130172729492} 08/30/2021 17:51:04 - INFO - __main__ - Step 26077: {'lr': 0.0004680565508635709, 'samples': 5006784, 'steps': 26076, 'loss/train': 1.7443983554840088} 08/30/2021 17:51:06 - INFO - __main__ - Step 26078: {'lr': 0.00046805395527146237, 'samples': 5006976, 'steps': 26077, 'loss/train': 1.7859952449798584} 08/30/2021 17:51:06 - INFO - __main__ - Step 26079: {'lr': 0.0004680513595811021, 'samples': 5007168, 'steps': 26078, 'loss/train': 2.150747060775757} 08/30/2021 17:51:07 - INFO - __main__ - Step 26080: {'lr': 0.0004680487637924912, 'samples': 5007360, 'steps': 26079, 'loss/train': 1.501441478729248} 08/30/2021 17:51:07 - INFO - __main__ - Step 26081: {'lr': 0.0004680461679056309, 'samples': 5007552, 'steps': 26080, 'loss/train': 1.599752426147461} 08/30/2021 17:51:07 - INFO - __main__ - Step 26082: {'lr': 0.00046804357192052246, 'samples': 5007744, 'steps': 26081, 'loss/train': 1.835063099861145} 08/30/2021 17:51:08 - INFO - __main__ - Step 26083: {'lr': 0.00046804097583716685, 'samples': 5007936, 'steps': 26082, 'loss/train': 1.6404485702514648} 08/30/2021 17:51:09 - INFO - __main__ - Step 26084: {'lr': 0.0004680383796555654, 'samples': 5008128, 'steps': 26083, 'loss/train': 1.8288980722427368} 08/30/2021 17:51:10 - INFO - __main__ - Step 26085: {'lr': 0.00046803578337571917, 'samples': 5008320, 'steps': 26084, 'loss/train': 1.72828209400177} 08/30/2021 17:51:10 - INFO - __main__ - Step 26086: {'lr': 0.00046803318699762937, 'samples': 5008512, 'steps': 26085, 'loss/train': 1.5738255977630615} 08/30/2021 17:51:10 - INFO - __main__ - Step 26087: {'lr': 0.0004680305905212972, 'samples': 5008704, 'steps': 26086, 'loss/train': 1.195892095565796} 08/30/2021 17:51:11 - INFO - __main__ - Step 26088: {'lr': 0.0004680279939467238, 'samples': 5008896, 'steps': 26087, 'loss/train': 1.6134518384933472} 08/30/2021 17:51:12 - INFO - __main__ - Step 26089: {'lr': 0.00046802539727391033, 'samples': 5009088, 'steps': 26088, 'loss/train': 1.4556657075881958} 08/30/2021 17:51:13 - INFO - __main__ - Step 26090: {'lr': 0.0004680228005028581, 'samples': 5009280, 'steps': 26089, 'loss/train': 1.530471682548523} 08/30/2021 17:51:13 - INFO - __main__ - Step 26091: {'lr': 0.000468020203633568, 'samples': 5009472, 'steps': 26090, 'loss/train': 1.8344494104385376} 08/30/2021 17:51:13 - INFO - __main__ - Step 26092: {'lr': 0.0004680176066660415, 'samples': 5009664, 'steps': 26091, 'loss/train': 1.8249365091323853} 08/30/2021 17:51:14 - INFO - __main__ - Step 26093: {'lr': 0.00046801500960027957, 'samples': 5009856, 'steps': 26092, 'loss/train': 1.8713473081588745} 08/30/2021 17:51:15 - INFO - __main__ - Step 26094: {'lr': 0.00046801241243628344, 'samples': 5010048, 'steps': 26093, 'loss/train': 1.3450409173965454} 08/30/2021 17:51:16 - INFO - __main__ - Step 26095: {'lr': 0.00046800981517405426, 'samples': 5010240, 'steps': 26094, 'loss/train': 1.082474708557129} 08/30/2021 17:51:16 - INFO - __main__ - Step 26096: {'lr': 0.0004680072178135932, 'samples': 5010432, 'steps': 26095, 'loss/train': 2.279996871948242} 08/30/2021 17:51:17 - INFO - __main__ - Step 26097: {'lr': 0.00046800462035490156, 'samples': 5010624, 'steps': 26096, 'loss/train': 0.10333873331546783} 08/30/2021 17:51:17 - INFO - __main__ - Step 26098: {'lr': 0.0004680020227979803, 'samples': 5010816, 'steps': 26097, 'loss/train': 1.4143881797790527} 08/30/2021 17:51:18 - INFO - __main__ - Step 26099: {'lr': 0.0004679994251428308, 'samples': 5011008, 'steps': 26098, 'loss/train': 0.8577102422714233} 08/30/2021 17:51:19 - INFO - __main__ - Step 26100: {'lr': 0.00046799682738945397, 'samples': 5011200, 'steps': 26099, 'loss/train': 1.9826905727386475} 08/30/2021 17:51:19 - INFO - __main__ - Step 26101: {'lr': 0.00046799422953785124, 'samples': 5011392, 'steps': 26100, 'loss/train': 0.7031465768814087} 08/30/2021 17:51:20 - INFO - __main__ - Step 26102: {'lr': 0.00046799163158802365, 'samples': 5011584, 'steps': 26101, 'loss/train': 0.7783217430114746} 08/30/2021 17:51:20 - INFO - __main__ - Step 26103: {'lr': 0.00046798903353997243, 'samples': 5011776, 'steps': 26102, 'loss/train': 1.5363852977752686} 08/30/2021 17:51:22 - INFO - __main__ - Step 26104: {'lr': 0.0004679864353936987, 'samples': 5011968, 'steps': 26103, 'loss/train': 1.148025393486023} 08/30/2021 17:51:23 - INFO - __main__ - Step 26105: {'lr': 0.0004679838371492036, 'samples': 5012160, 'steps': 26104, 'loss/train': 1.8366453647613525} 08/30/2021 17:51:23 - INFO - __main__ - Step 26106: {'lr': 0.00046798123880648833, 'samples': 5012352, 'steps': 26105, 'loss/train': 0.735233724117279} 08/30/2021 17:51:23 - INFO - __main__ - Step 26107: {'lr': 0.0004679786403655542, 'samples': 5012544, 'steps': 26106, 'loss/train': 0.5969606637954712} 08/30/2021 17:51:24 - INFO - __main__ - Step 26108: {'lr': 0.0004679760418264021, 'samples': 5012736, 'steps': 26107, 'loss/train': 1.3180538415908813} 08/30/2021 17:51:25 - INFO - __main__ - Step 26109: {'lr': 0.00046797344318903343, 'samples': 5012928, 'steps': 26108, 'loss/train': 1.8988051414489746} 08/30/2021 17:51:26 - INFO - __main__ - Step 26110: {'lr': 0.0004679708444534493, 'samples': 5013120, 'steps': 26109, 'loss/train': 1.5253174304962158} 08/30/2021 17:51:26 - INFO - __main__ - Step 26111: {'lr': 0.0004679682456196509, 'samples': 5013312, 'steps': 26110, 'loss/train': 0.9396080374717712} 08/30/2021 17:51:26 - INFO - __main__ - Step 26112: {'lr': 0.0004679656466876393, 'samples': 5013504, 'steps': 26111, 'loss/train': 1.5866893529891968} 08/30/2021 17:51:27 - INFO - __main__ - Step 26113: {'lr': 0.00046796304765741583, 'samples': 5013696, 'steps': 26112, 'loss/train': 1.6055492162704468} 08/30/2021 17:51:27 - INFO - __main__ - Step 26114: {'lr': 0.00046796044852898144, 'samples': 5013888, 'steps': 26113, 'loss/train': 1.7148551940917969} 08/30/2021 17:51:28 - INFO - __main__ - Step 26115: {'lr': 0.0004679578493023375, 'samples': 5014080, 'steps': 26114, 'loss/train': 1.5810562372207642} 08/30/2021 17:51:29 - INFO - __main__ - Step 26116: {'lr': 0.00046795524997748515, 'samples': 5014272, 'steps': 26115, 'loss/train': 1.0068461894989014} 08/30/2021 17:51:29 - INFO - __main__ - Step 26117: {'lr': 0.0004679526505544256, 'samples': 5014464, 'steps': 26116, 'loss/train': 1.168715000152588} 08/30/2021 17:51:30 - INFO - __main__ - Step 26118: {'lr': 0.0004679500510331598, 'samples': 5014656, 'steps': 26117, 'loss/train': 2.080726385116577} 08/30/2021 17:51:30 - INFO - __main__ - Step 26119: {'lr': 0.00046794745141368917, 'samples': 5014848, 'steps': 26118, 'loss/train': 1.7851732969284058} 08/30/2021 17:51:32 - INFO - __main__ - Step 26120: {'lr': 0.00046794485169601474, 'samples': 5015040, 'steps': 26119, 'loss/train': 1.5185885429382324} 08/30/2021 17:51:32 - INFO - __main__ - Step 26121: {'lr': 0.00046794225188013773, 'samples': 5015232, 'steps': 26120, 'loss/train': 1.8581764698028564} 08/30/2021 17:51:32 - INFO - __main__ - Step 26122: {'lr': 0.00046793965196605927, 'samples': 5015424, 'steps': 26121, 'loss/train': 1.7707773447036743} 08/30/2021 17:51:33 - INFO - __main__ - Step 26123: {'lr': 0.00046793705195378066, 'samples': 5015616, 'steps': 26122, 'loss/train': 1.5318524837493896} 08/30/2021 17:51:33 - INFO - __main__ - Step 26124: {'lr': 0.0004679344518433029, 'samples': 5015808, 'steps': 26123, 'loss/train': 1.4481995105743408} 08/30/2021 17:51:35 - INFO - __main__ - Step 26125: {'lr': 0.0004679318516346273, 'samples': 5016000, 'steps': 26124, 'loss/train': 1.2897790670394897} 08/30/2021 17:51:35 - INFO - __main__ - Step 26126: {'lr': 0.0004679292513277549, 'samples': 5016192, 'steps': 26125, 'loss/train': 1.6501446962356567} 08/30/2021 17:51:35 - INFO - __main__ - Step 26127: {'lr': 0.0004679266509226869, 'samples': 5016384, 'steps': 26126, 'loss/train': 1.3101930618286133} 08/30/2021 17:51:36 - INFO - __main__ - Step 26128: {'lr': 0.0004679240504194246, 'samples': 5016576, 'steps': 26127, 'loss/train': 1.645825982093811} 08/30/2021 17:51:36 - INFO - __main__ - Step 26129: {'lr': 0.00046792144981796905, 'samples': 5016768, 'steps': 26128, 'loss/train': 0.7791157364845276} 08/30/2021 17:51:38 - INFO - __main__ - Step 26130: {'lr': 0.0004679188491183215, 'samples': 5016960, 'steps': 26129, 'loss/train': 1.2416889667510986} 08/30/2021 17:51:38 - INFO - __main__ - Step 26131: {'lr': 0.00046791624832048307, 'samples': 5017152, 'steps': 26130, 'loss/train': 1.7181764841079712} 08/30/2021 17:51:39 - INFO - __main__ - Step 26132: {'lr': 0.0004679136474244549, 'samples': 5017344, 'steps': 26131, 'loss/train': 1.6692501306533813} 08/30/2021 17:51:39 - INFO - __main__ - Step 26133: {'lr': 0.00046791104643023823, 'samples': 5017536, 'steps': 26132, 'loss/train': 1.8287296295166016} 08/30/2021 17:51:39 - INFO - __main__ - Step 26134: {'lr': 0.0004679084453378342, 'samples': 5017728, 'steps': 26133, 'loss/train': 0.9401084780693054} 08/30/2021 17:51:41 - INFO - __main__ - Step 26135: {'lr': 0.00046790584414724404, 'samples': 5017920, 'steps': 26134, 'loss/train': 1.7611048221588135} 08/30/2021 17:51:41 - INFO - __main__ - Step 26136: {'lr': 0.0004679032428584687, 'samples': 5018112, 'steps': 26135, 'loss/train': 1.5844484567642212} 08/30/2021 17:51:42 - INFO - __main__ - Step 26137: {'lr': 0.0004679006414715097, 'samples': 5018304, 'steps': 26136, 'loss/train': 0.9440152645111084} 08/30/2021 17:51:42 - INFO - __main__ - Step 26138: {'lr': 0.00046789803998636796, 'samples': 5018496, 'steps': 26137, 'loss/train': 2.4105002880096436} 08/30/2021 17:51:42 - INFO - __main__ - Step 26139: {'lr': 0.0004678954384030448, 'samples': 5018688, 'steps': 26138, 'loss/train': 1.4241313934326172} 08/30/2021 17:51:44 - INFO - __main__ - Step 26140: {'lr': 0.00046789283672154125, 'samples': 5018880, 'steps': 26139, 'loss/train': 0.9175655841827393} 08/30/2021 17:51:44 - INFO - __main__ - Step 26141: {'lr': 0.00046789023494185855, 'samples': 5019072, 'steps': 26140, 'loss/train': 1.0826953649520874} 08/30/2021 17:51:45 - INFO - __main__ - Step 26142: {'lr': 0.0004678876330639978, 'samples': 5019264, 'steps': 26141, 'loss/train': 1.167996883392334} 08/30/2021 17:51:45 - INFO - __main__ - Step 26143: {'lr': 0.0004678850310879604, 'samples': 5019456, 'steps': 26142, 'loss/train': 1.8836358785629272} 08/30/2021 17:51:45 - INFO - __main__ - Step 26144: {'lr': 0.0004678824290137473, 'samples': 5019648, 'steps': 26143, 'loss/train': 1.3544318675994873} 08/30/2021 17:51:47 - INFO - __main__ - Step 26145: {'lr': 0.0004678798268413597, 'samples': 5019840, 'steps': 26144, 'loss/train': 1.3764623403549194} 08/30/2021 17:51:47 - INFO - __main__ - Step 26146: {'lr': 0.00046787722457079887, 'samples': 5020032, 'steps': 26145, 'loss/train': 1.5148603916168213} 08/30/2021 17:51:48 - INFO - __main__ - Step 26147: {'lr': 0.00046787462220206587, 'samples': 5020224, 'steps': 26146, 'loss/train': 1.8436599969863892} 08/30/2021 17:51:48 - INFO - __main__ - Step 26148: {'lr': 0.00046787201973516195, 'samples': 5020416, 'steps': 26147, 'loss/train': 0.5548301339149475} 08/30/2021 17:51:48 - INFO - __main__ - Step 26149: {'lr': 0.00046786941717008823, 'samples': 5020608, 'steps': 26148, 'loss/train': 0.637928307056427} 08/30/2021 17:51:49 - INFO - __main__ - Step 26150: {'lr': 0.00046786681450684597, 'samples': 5020800, 'steps': 26149, 'loss/train': 2.0019750595092773} 08/30/2021 17:51:50 - INFO - __main__ - Step 26151: {'lr': 0.00046786421174543625, 'samples': 5020992, 'steps': 26150, 'loss/train': 1.213064193725586} 08/30/2021 17:51:51 - INFO - __main__ - Step 26152: {'lr': 0.0004678616088858603, 'samples': 5021184, 'steps': 26151, 'loss/train': 1.6105926036834717} 08/30/2021 17:51:51 - INFO - __main__ - Step 26153: {'lr': 0.0004678590059281193, 'samples': 5021376, 'steps': 26152, 'loss/train': 1.7457095384597778} 08/30/2021 17:51:51 - INFO - __main__ - Step 26154: {'lr': 0.0004678564028722143, 'samples': 5021568, 'steps': 26153, 'loss/train': 2.446765184402466} 08/30/2021 17:51:52 - INFO - __main__ - Step 26155: {'lr': 0.0004678537997181467, 'samples': 5021760, 'steps': 26154, 'loss/train': 1.2729811668395996} 08/30/2021 17:51:54 - INFO - __main__ - Step 26156: {'lr': 0.00046785119646591746, 'samples': 5021952, 'steps': 26155, 'loss/train': 1.7035256624221802} 08/30/2021 17:51:54 - INFO - __main__ - Step 26157: {'lr': 0.0004678485931155278, 'samples': 5022144, 'steps': 26156, 'loss/train': 1.5122156143188477} 08/30/2021 17:51:55 - INFO - __main__ - Step 26158: {'lr': 0.000467845989666979, 'samples': 5022336, 'steps': 26157, 'loss/train': 1.3289146423339844} 08/30/2021 17:51:55 - INFO - __main__ - Step 26159: {'lr': 0.0004678433861202721, 'samples': 5022528, 'steps': 26158, 'loss/train': 1.6197569370269775} 08/30/2021 17:51:55 - INFO - __main__ - Step 26160: {'lr': 0.0004678407824754083, 'samples': 5022720, 'steps': 26159, 'loss/train': 1.7705466747283936} 08/30/2021 17:51:56 - INFO - __main__ - Step 26161: {'lr': 0.00046783817873238885, 'samples': 5022912, 'steps': 26160, 'loss/train': 0.09180153906345367} 08/30/2021 17:51:57 - INFO - __main__ - Step 26162: {'lr': 0.0004678355748912149, 'samples': 5023104, 'steps': 26161, 'loss/train': 0.6512777209281921} 08/30/2021 17:51:58 - INFO - __main__ - Step 26163: {'lr': 0.0004678329709518876, 'samples': 5023296, 'steps': 26162, 'loss/train': 1.0051910877227783} 08/30/2021 17:51:58 - INFO - __main__ - Step 26164: {'lr': 0.0004678303669144081, 'samples': 5023488, 'steps': 26163, 'loss/train': 1.294397234916687} 08/30/2021 17:51:58 - INFO - __main__ - Step 26165: {'lr': 0.0004678277627787776, 'samples': 5023680, 'steps': 26164, 'loss/train': 0.5985181927680969} 08/30/2021 17:51:59 - INFO - __main__ - Step 26166: {'lr': 0.0004678251585449973, 'samples': 5023872, 'steps': 26165, 'loss/train': 1.6224207878112793} 08/30/2021 17:52:00 - INFO - __main__ - Step 26167: {'lr': 0.0004678225542130683, 'samples': 5024064, 'steps': 26166, 'loss/train': 1.5821278095245361} 08/30/2021 17:52:01 - INFO - __main__ - Step 26168: {'lr': 0.0004678199497829919, 'samples': 5024256, 'steps': 26167, 'loss/train': 1.2952234745025635} 08/30/2021 17:52:01 - INFO - __main__ - Step 26169: {'lr': 0.0004678173452547691, 'samples': 5024448, 'steps': 26168, 'loss/train': 1.4567570686340332} 08/30/2021 17:52:01 - INFO - __main__ - Step 26170: {'lr': 0.00046781474062840126, 'samples': 5024640, 'steps': 26169, 'loss/train': 1.1379626989364624} 08/30/2021 17:52:02 - INFO - __main__ - Step 26171: {'lr': 0.0004678121359038894, 'samples': 5024832, 'steps': 26170, 'loss/train': 1.627280831336975} 08/30/2021 17:52:04 - INFO - __main__ - Step 26172: {'lr': 0.0004678095310812347, 'samples': 5025024, 'steps': 26171, 'loss/train': 0.38083937764167786} 08/30/2021 17:52:04 - INFO - __main__ - Step 26173: {'lr': 0.0004678069261604384, 'samples': 5025216, 'steps': 26172, 'loss/train': 1.146022081375122} 08/30/2021 17:52:05 - INFO - __main__ - Step 26174: {'lr': 0.00046780432114150173, 'samples': 5025408, 'steps': 26173, 'loss/train': 1.4485677480697632} 08/30/2021 17:52:05 - INFO - __main__ - Step 26175: {'lr': 0.0004678017160244258, 'samples': 5025600, 'steps': 26174, 'loss/train': 1.5082147121429443} 08/30/2021 17:52:05 - INFO - __main__ - Step 26176: {'lr': 0.00046779911080921166, 'samples': 5025792, 'steps': 26175, 'loss/train': 2.016350269317627} 08/30/2021 17:52:06 - INFO - __main__ - Step 26177: {'lr': 0.00046779650549586075, 'samples': 5025984, 'steps': 26176, 'loss/train': 1.5053982734680176} 08/30/2021 17:52:07 - INFO - __main__ - Step 26178: {'lr': 0.000467793900084374, 'samples': 5026176, 'steps': 26177, 'loss/train': 0.363174706697464} 08/30/2021 17:52:08 - INFO - __main__ - Step 26179: {'lr': 0.0004677912945747527, 'samples': 5026368, 'steps': 26178, 'loss/train': 2.0944387912750244} 08/30/2021 17:52:08 - INFO - __main__ - Step 26180: {'lr': 0.000467788688966998, 'samples': 5026560, 'steps': 26179, 'loss/train': 1.557246446609497} 08/30/2021 17:52:08 - INFO - __main__ - Step 26181: {'lr': 0.00046778608326111104, 'samples': 5026752, 'steps': 26180, 'loss/train': 2.4179751873016357} 08/30/2021 17:52:09 - INFO - __main__ - Step 26182: {'lr': 0.00046778347745709317, 'samples': 5026944, 'steps': 26181, 'loss/train': 1.5029606819152832} 08/30/2021 17:52:10 - INFO - __main__ - Step 26183: {'lr': 0.0004677808715549453, 'samples': 5027136, 'steps': 26182, 'loss/train': 0.08202935755252838} 08/30/2021 17:52:11 - INFO - __main__ - Step 26184: {'lr': 0.0004677782655546687, 'samples': 5027328, 'steps': 26183, 'loss/train': 2.0947749614715576} 08/30/2021 17:52:11 - INFO - __main__ - Step 26185: {'lr': 0.00046777565945626463, 'samples': 5027520, 'steps': 26184, 'loss/train': 0.14571039378643036} 08/30/2021 17:52:12 - INFO - __main__ - Step 26186: {'lr': 0.0004677730532597343, 'samples': 5027712, 'steps': 26185, 'loss/train': 0.664777398109436} 08/30/2021 17:52:12 - INFO - __main__ - Step 26187: {'lr': 0.00046777044696507867, 'samples': 5027904, 'steps': 26186, 'loss/train': 1.4623806476593018} 08/30/2021 17:52:14 - INFO - __main__ - Step 26188: {'lr': 0.00046776784057229906, 'samples': 5028096, 'steps': 26187, 'loss/train': 1.3610191345214844} 08/30/2021 17:52:14 - INFO - __main__ - Step 26189: {'lr': 0.00046776523408139666, 'samples': 5028288, 'steps': 26188, 'loss/train': 1.5496939420700073} 08/30/2021 17:52:14 - INFO - __main__ - Step 26190: {'lr': 0.0004677626274923726, 'samples': 5028480, 'steps': 26189, 'loss/train': 1.611902117729187} 08/30/2021 17:52:15 - INFO - __main__ - Step 26191: {'lr': 0.000467760020805228, 'samples': 5028672, 'steps': 26190, 'loss/train': 1.2484333515167236} 08/30/2021 17:52:15 - INFO - __main__ - Step 26192: {'lr': 0.0004677574140199642, 'samples': 5028864, 'steps': 26191, 'loss/train': 1.459053635597229} 08/30/2021 17:52:16 - INFO - __main__ - Step 26193: {'lr': 0.00046775480713658215, 'samples': 5029056, 'steps': 26192, 'loss/train': 1.6826428174972534} 08/30/2021 17:52:17 - INFO - __main__ - Step 26194: {'lr': 0.00046775220015508325, 'samples': 5029248, 'steps': 26193, 'loss/train': 1.5191541910171509} 08/30/2021 17:52:17 - INFO - __main__ - Step 26195: {'lr': 0.0004677495930754685, 'samples': 5029440, 'steps': 26194, 'loss/train': 1.6067183017730713} 08/30/2021 17:52:18 - INFO - __main__ - Step 26196: {'lr': 0.0004677469858977391, 'samples': 5029632, 'steps': 26195, 'loss/train': 1.3620458841323853} 08/30/2021 17:52:18 - INFO - __main__ - Step 26197: {'lr': 0.00046774437862189634, 'samples': 5029824, 'steps': 26196, 'loss/train': 1.465554118156433} 08/30/2021 17:52:19 - INFO - __main__ - Step 26198: {'lr': 0.00046774177124794136, 'samples': 5030016, 'steps': 26197, 'loss/train': 0.8533470034599304} 08/30/2021 17:52:20 - INFO - __main__ - Step 26199: {'lr': 0.00046773916377587524, 'samples': 5030208, 'steps': 26198, 'loss/train': 1.480251431465149} 08/30/2021 17:52:20 - INFO - __main__ - Step 26200: {'lr': 0.00046773655620569924, 'samples': 5030400, 'steps': 26199, 'loss/train': 1.3872203826904297} 08/30/2021 17:52:20 - INFO - __main__ - Step 26201: {'lr': 0.0004677339485374145, 'samples': 5030592, 'steps': 26200, 'loss/train': 1.836183786392212} 08/30/2021 17:52:21 - INFO - __main__ - Step 26202: {'lr': 0.00046773134077102217, 'samples': 5030784, 'steps': 26201, 'loss/train': 1.560879111289978} 08/30/2021 17:52:22 - INFO - __main__ - Step 26203: {'lr': 0.00046772873290652344, 'samples': 5030976, 'steps': 26202, 'loss/train': 1.932642936706543} 08/30/2021 17:52:23 - INFO - __main__ - Step 26204: {'lr': 0.0004677261249439196, 'samples': 5031168, 'steps': 26203, 'loss/train': 1.487125039100647} 08/30/2021 17:52:23 - INFO - __main__ - Step 26205: {'lr': 0.0004677235168832117, 'samples': 5031360, 'steps': 26204, 'loss/train': 0.585166871547699} 08/30/2021 17:52:24 - INFO - __main__ - Step 26206: {'lr': 0.0004677209087244009, 'samples': 5031552, 'steps': 26205, 'loss/train': 1.2288188934326172} 08/30/2021 17:52:24 - INFO - __main__ - Step 26207: {'lr': 0.0004677183004674884, 'samples': 5031744, 'steps': 26206, 'loss/train': 1.764260172843933} 08/30/2021 17:52:24 - INFO - __main__ - Step 26208: {'lr': 0.00046771569211247546, 'samples': 5031936, 'steps': 26207, 'loss/train': 1.874774694442749} 08/30/2021 17:52:27 - INFO - __main__ - Step 26209: {'lr': 0.00046771308365936315, 'samples': 5032128, 'steps': 26208, 'loss/train': 1.7931764125823975} 08/30/2021 17:52:27 - INFO - __main__ - Step 26210: {'lr': 0.00046771047510815267, 'samples': 5032320, 'steps': 26209, 'loss/train': 1.2996633052825928} 08/30/2021 17:52:27 - INFO - __main__ - Step 26211: {'lr': 0.0004677078664588452, 'samples': 5032512, 'steps': 26210, 'loss/train': 1.447281002998352} 08/30/2021 17:52:28 - INFO - __main__ - Step 26212: {'lr': 0.000467705257711442, 'samples': 5032704, 'steps': 26211, 'loss/train': 1.5091127157211304} 08/30/2021 17:52:28 - INFO - __main__ - Step 26213: {'lr': 0.0004677026488659441, 'samples': 5032896, 'steps': 26212, 'loss/train': 1.8863173723220825} 08/30/2021 17:52:29 - INFO - __main__ - Step 26214: {'lr': 0.0004677000399223528, 'samples': 5033088, 'steps': 26213, 'loss/train': 2.09542179107666} 08/30/2021 17:52:30 - INFO - __main__ - Step 26215: {'lr': 0.0004676974308806692, 'samples': 5033280, 'steps': 26214, 'loss/train': 1.9482330083847046} 08/30/2021 17:52:30 - INFO - __main__ - Step 26216: {'lr': 0.00046769482174089446, 'samples': 5033472, 'steps': 26215, 'loss/train': 1.2161154747009277} 08/30/2021 17:52:31 - INFO - __main__ - Step 26217: {'lr': 0.00046769221250302984, 'samples': 5033664, 'steps': 26216, 'loss/train': 0.5359983444213867} 08/30/2021 17:52:31 - INFO - __main__ - Step 26218: {'lr': 0.0004676896031670764, 'samples': 5033856, 'steps': 26217, 'loss/train': 1.6811681985855103} 08/30/2021 17:52:32 - INFO - __main__ - Step 26219: {'lr': 0.00046768699373303546, 'samples': 5034048, 'steps': 26218, 'loss/train': 1.6467416286468506} 08/30/2021 17:52:33 - INFO - __main__ - Step 26220: {'lr': 0.00046768438420090807, 'samples': 5034240, 'steps': 26219, 'loss/train': 1.2183287143707275} 08/30/2021 17:52:33 - INFO - __main__ - Step 26221: {'lr': 0.0004676817745706955, 'samples': 5034432, 'steps': 26220, 'loss/train': 1.2806841135025024} 08/30/2021 17:52:34 - INFO - __main__ - Step 26222: {'lr': 0.0004676791648423989, 'samples': 5034624, 'steps': 26221, 'loss/train': 1.8384215831756592} 08/30/2021 17:52:34 - INFO - __main__ - Step 26223: {'lr': 0.00046767655501601935, 'samples': 5034816, 'steps': 26222, 'loss/train': 1.3472853899002075} 08/30/2021 17:52:36 - INFO - __main__ - Step 26224: {'lr': 0.0004676739450915581, 'samples': 5035008, 'steps': 26223, 'loss/train': 1.0090837478637695} 08/30/2021 17:52:36 - INFO - __main__ - Step 26225: {'lr': 0.0004676713350690164, 'samples': 5035200, 'steps': 26224, 'loss/train': 1.7016509771347046} 08/30/2021 17:52:36 - INFO - __main__ - Step 26226: {'lr': 0.0004676687249483953, 'samples': 5035392, 'steps': 26225, 'loss/train': 2.773500919342041} 08/30/2021 17:52:37 - INFO - __main__ - Step 26227: {'lr': 0.0004676661147296961, 'samples': 5035584, 'steps': 26226, 'loss/train': 1.444489598274231} 08/30/2021 17:52:37 - INFO - __main__ - Step 26228: {'lr': 0.00046766350441291985, 'samples': 5035776, 'steps': 26227, 'loss/train': 1.0572092533111572} 08/30/2021 17:52:39 - INFO - __main__ - Step 26229: {'lr': 0.00046766089399806775, 'samples': 5035968, 'steps': 26228, 'loss/train': 0.6948620080947876} 08/30/2021 17:52:39 - INFO - __main__ - Step 26230: {'lr': 0.0004676582834851411, 'samples': 5036160, 'steps': 26229, 'loss/train': 1.6123915910720825} 08/30/2021 17:52:39 - INFO - __main__ - Step 26231: {'lr': 0.0004676556728741409, 'samples': 5036352, 'steps': 26230, 'loss/train': 0.19862884283065796} 08/30/2021 17:52:40 - INFO - __main__ - Step 26232: {'lr': 0.0004676530621650685, 'samples': 5036544, 'steps': 26231, 'loss/train': 1.3207002878189087} 08/30/2021 17:52:40 - INFO - __main__ - Step 26233: {'lr': 0.00046765045135792495, 'samples': 5036736, 'steps': 26232, 'loss/train': 2.133751153945923} 08/30/2021 17:52:42 - INFO - __main__ - Step 26234: {'lr': 0.00046764784045271146, 'samples': 5036928, 'steps': 26233, 'loss/train': 1.8287540674209595} 08/30/2021 17:52:42 - INFO - __main__ - Step 26235: {'lr': 0.0004676452294494292, 'samples': 5037120, 'steps': 26234, 'loss/train': 1.5834941864013672} 08/30/2021 17:52:42 - INFO - __main__ - Step 26236: {'lr': 0.00046764261834807944, 'samples': 5037312, 'steps': 26235, 'loss/train': 2.87629771232605} 08/30/2021 17:52:43 - INFO - __main__ - Step 26237: {'lr': 0.0004676400071486632, 'samples': 5037504, 'steps': 26236, 'loss/train': 2.2349281311035156} 08/30/2021 17:52:43 - INFO - __main__ - Step 26238: {'lr': 0.0004676373958511817, 'samples': 5037696, 'steps': 26237, 'loss/train': 1.0710747241973877} 08/30/2021 17:52:45 - INFO - __main__ - Step 26239: {'lr': 0.00046763478445563617, 'samples': 5037888, 'steps': 26238, 'loss/train': 2.6107187271118164} 08/30/2021 17:52:45 - INFO - __main__ - Step 26240: {'lr': 0.0004676321729620278, 'samples': 5038080, 'steps': 26239, 'loss/train': 1.5706325769424438} 08/30/2021 17:52:46 - INFO - __main__ - Step 26241: {'lr': 0.0004676295613703577, 'samples': 5038272, 'steps': 26240, 'loss/train': 1.8564623594284058} 08/30/2021 17:52:46 - INFO - __main__ - Step 26242: {'lr': 0.00046762694968062706, 'samples': 5038464, 'steps': 26241, 'loss/train': 1.5979385375976562} 08/30/2021 17:52:46 - INFO - __main__ - Step 26243: {'lr': 0.0004676243378928371, 'samples': 5038656, 'steps': 26242, 'loss/train': 2.0918338298797607} 08/30/2021 17:52:47 - INFO - __main__ - Step 26244: {'lr': 0.000467621726006989, 'samples': 5038848, 'steps': 26243, 'loss/train': 0.6312897205352783} 08/30/2021 17:52:48 - INFO - __main__ - Step 26245: {'lr': 0.0004676191140230839, 'samples': 5039040, 'steps': 26244, 'loss/train': 1.396957516670227} 08/30/2021 17:52:49 - INFO - __main__ - Step 26246: {'lr': 0.0004676165019411229, 'samples': 5039232, 'steps': 26245, 'loss/train': 1.4047967195510864} 08/30/2021 17:52:49 - INFO - __main__ - Step 26247: {'lr': 0.00046761388976110737, 'samples': 5039424, 'steps': 26246, 'loss/train': 1.378141164779663} 08/30/2021 17:52:49 - INFO - __main__ - Step 26248: {'lr': 0.00046761127748303833, 'samples': 5039616, 'steps': 26247, 'loss/train': 1.552869439125061} 08/30/2021 17:52:50 - INFO - __main__ - Step 26249: {'lr': 0.000467608665106917, 'samples': 5039808, 'steps': 26248, 'loss/train': 1.6121121644973755} 08/30/2021 17:52:51 - INFO - __main__ - Step 26250: {'lr': 0.0004676060526327446, 'samples': 5040000, 'steps': 26249, 'loss/train': 1.5323083400726318} 08/30/2021 17:52:52 - INFO - __main__ - Step 26251: {'lr': 0.00046760344006052223, 'samples': 5040192, 'steps': 26250, 'loss/train': 1.0000609159469604} 08/30/2021 17:52:52 - INFO - __main__ - Step 26252: {'lr': 0.00046760082739025113, 'samples': 5040384, 'steps': 26251, 'loss/train': 1.5879063606262207} 08/30/2021 17:52:52 - INFO - __main__ - Step 26253: {'lr': 0.0004675982146219324, 'samples': 5040576, 'steps': 26252, 'loss/train': 0.24589650332927704} 08/30/2021 17:52:53 - INFO - __main__ - Step 26254: {'lr': 0.00046759560175556737, 'samples': 5040768, 'steps': 26253, 'loss/train': 1.4122611284255981} 08/30/2021 17:52:54 - INFO - __main__ - Step 26255: {'lr': 0.0004675929887911571, 'samples': 5040960, 'steps': 26254, 'loss/train': 1.3601524829864502} 08/30/2021 17:52:55 - INFO - __main__ - Step 26256: {'lr': 0.0004675903757287027, 'samples': 5041152, 'steps': 26255, 'loss/train': 1.5401798486709595} 08/30/2021 17:52:55 - INFO - __main__ - Step 26257: {'lr': 0.0004675877625682055, 'samples': 5041344, 'steps': 26256, 'loss/train': 1.829728126525879} 08/30/2021 17:52:55 - INFO - __main__ - Step 26258: {'lr': 0.00046758514930966664, 'samples': 5041536, 'steps': 26257, 'loss/train': 1.5436458587646484} 08/30/2021 17:52:56 - INFO - __main__ - Step 26259: {'lr': 0.0004675825359530872, 'samples': 5041728, 'steps': 26258, 'loss/train': 1.1547647714614868} 08/30/2021 17:52:58 - INFO - __main__ - Step 26260: {'lr': 0.0004675799224984685, 'samples': 5041920, 'steps': 26259, 'loss/train': 1.8499315977096558} 08/30/2021 17:52:58 - INFO - __main__ - Step 26261: {'lr': 0.00046757730894581164, 'samples': 5042112, 'steps': 26260, 'loss/train': 1.8405916690826416} 08/30/2021 17:52:58 - INFO - __main__ - Step 26262: {'lr': 0.00046757469529511777, 'samples': 5042304, 'steps': 26261, 'loss/train': 1.6968600749969482} 08/30/2021 17:52:59 - INFO - __main__ - Step 26263: {'lr': 0.0004675720815463881, 'samples': 5042496, 'steps': 26262, 'loss/train': 1.6263556480407715} 08/30/2021 17:52:59 - INFO - __main__ - Step 26264: {'lr': 0.00046756946769962375, 'samples': 5042688, 'steps': 26263, 'loss/train': 1.757317066192627} 08/30/2021 17:53:01 - INFO - __main__ - Step 26265: {'lr': 0.000467566853754826, 'samples': 5042880, 'steps': 26264, 'loss/train': 1.6671481132507324} 08/30/2021 17:53:01 - INFO - __main__ - Step 26266: {'lr': 0.00046756423971199603, 'samples': 5043072, 'steps': 26265, 'loss/train': 1.3835176229476929} 08/30/2021 17:53:02 - INFO - __main__ - Step 26267: {'lr': 0.0004675616255711349, 'samples': 5043264, 'steps': 26266, 'loss/train': 5.911319732666016} 08/30/2021 17:53:02 - INFO - __main__ - Step 26268: {'lr': 0.0004675590113322439, 'samples': 5043456, 'steps': 26267, 'loss/train': 1.204235315322876} 08/30/2021 17:53:02 - INFO - __main__ - Step 26269: {'lr': 0.00046755639699532414, 'samples': 5043648, 'steps': 26268, 'loss/train': 1.2118866443634033} 08/30/2021 17:53:03 - INFO - __main__ - Step 26270: {'lr': 0.00046755378256037685, 'samples': 5043840, 'steps': 26269, 'loss/train': 1.761609435081482} 08/30/2021 17:53:04 - INFO - __main__ - Step 26271: {'lr': 0.00046755116802740316, 'samples': 5044032, 'steps': 26270, 'loss/train': 1.9451550245285034} 08/30/2021 17:53:05 - INFO - __main__ - Step 26272: {'lr': 0.00046754855339640436, 'samples': 5044224, 'steps': 26271, 'loss/train': 0.941116213798523} 08/30/2021 17:53:05 - INFO - __main__ - Step 26273: {'lr': 0.00046754593866738144, 'samples': 5044416, 'steps': 26272, 'loss/train': 1.11298668384552} 08/30/2021 17:53:06 - INFO - __main__ - Step 26274: {'lr': 0.0004675433238403357, 'samples': 5044608, 'steps': 26273, 'loss/train': 1.162381887435913} 08/30/2021 17:53:06 - INFO - __main__ - Step 26275: {'lr': 0.0004675407089152683, 'samples': 5044800, 'steps': 26274, 'loss/train': 1.1345688104629517} 08/30/2021 17:53:06 - INFO - __main__ - Step 26276: {'lr': 0.00046753809389218036, 'samples': 5044992, 'steps': 26275, 'loss/train': 1.559865117073059} 08/30/2021 17:53:08 - INFO - __main__ - Step 26277: {'lr': 0.0004675354787710732, 'samples': 5045184, 'steps': 26276, 'loss/train': 1.0282788276672363} 08/30/2021 17:53:08 - INFO - __main__ - Step 26278: {'lr': 0.0004675328635519479, 'samples': 5045376, 'steps': 26277, 'loss/train': 0.7387611269950867} 08/30/2021 17:53:08 - INFO - __main__ - Step 26279: {'lr': 0.0004675302482348056, 'samples': 5045568, 'steps': 26278, 'loss/train': 1.364940881729126} 08/30/2021 17:53:09 - INFO - __main__ - Step 26280: {'lr': 0.00046752763281964757, 'samples': 5045760, 'steps': 26279, 'loss/train': 1.4897438287734985} 08/30/2021 17:53:09 - INFO - __main__ - Step 26281: {'lr': 0.0004675250173064749, 'samples': 5045952, 'steps': 26280, 'loss/train': 1.7558190822601318} 08/30/2021 17:53:11 - INFO - __main__ - Step 26282: {'lr': 0.0004675224016952888, 'samples': 5046144, 'steps': 26281, 'loss/train': 1.4290552139282227} 08/30/2021 17:53:11 - INFO - __main__ - Step 26283: {'lr': 0.00046751978598609056, 'samples': 5046336, 'steps': 26282, 'loss/train': 1.4846059083938599} 08/30/2021 17:53:11 - INFO - __main__ - Step 26284: {'lr': 0.00046751717017888116, 'samples': 5046528, 'steps': 26283, 'loss/train': 1.951148509979248} 08/30/2021 17:53:12 - INFO - __main__ - Step 26285: {'lr': 0.00046751455427366194, 'samples': 5046720, 'steps': 26284, 'loss/train': 1.6930569410324097} 08/30/2021 17:53:12 - INFO - __main__ - Step 26286: {'lr': 0.00046751193827043405, 'samples': 5046912, 'steps': 26285, 'loss/train': 1.0926343202590942} 08/30/2021 17:53:14 - INFO - __main__ - Step 26287: {'lr': 0.0004675093221691985, 'samples': 5047104, 'steps': 26286, 'loss/train': 1.2144969701766968} 08/30/2021 17:53:14 - INFO - __main__ - Step 26288: {'lr': 0.0004675067059699567, 'samples': 5047296, 'steps': 26287, 'loss/train': 1.193758249282837} 08/30/2021 17:53:15 - INFO - __main__ - Step 26289: {'lr': 0.00046750408967270973, 'samples': 5047488, 'steps': 26288, 'loss/train': 1.3849986791610718} 08/30/2021 17:53:15 - INFO - __main__ - Step 26290: {'lr': 0.0004675014732774588, 'samples': 5047680, 'steps': 26289, 'loss/train': 1.406269907951355} 08/30/2021 17:53:15 - INFO - __main__ - Step 26291: {'lr': 0.000467498856784205, 'samples': 5047872, 'steps': 26290, 'loss/train': 1.1837278604507446} 08/30/2021 17:53:17 - INFO - __main__ - Step 26292: {'lr': 0.0004674962401929496, 'samples': 5048064, 'steps': 26291, 'loss/train': 1.9569282531738281} 08/30/2021 17:53:17 - INFO - __main__ - Step 26293: {'lr': 0.0004674936235036938, 'samples': 5048256, 'steps': 26292, 'loss/train': 1.192387580871582} 08/30/2021 17:53:18 - INFO - __main__ - Step 26294: {'lr': 0.00046749100671643866, 'samples': 5048448, 'steps': 26293, 'loss/train': 0.874843418598175} 08/30/2021 17:53:18 - INFO - __main__ - Step 26295: {'lr': 0.00046748838983118546, 'samples': 5048640, 'steps': 26294, 'loss/train': 0.8066315650939941} 08/30/2021 17:53:18 - INFO - __main__ - Step 26296: {'lr': 0.00046748577284793535, 'samples': 5048832, 'steps': 26295, 'loss/train': 1.4623510837554932} 08/30/2021 17:53:20 - INFO - __main__ - Step 26297: {'lr': 0.00046748315576668946, 'samples': 5049024, 'steps': 26296, 'loss/train': 1.4491009712219238} 08/30/2021 17:53:20 - INFO - __main__ - Step 26298: {'lr': 0.0004674805385874491, 'samples': 5049216, 'steps': 26297, 'loss/train': 2.0263445377349854} 08/30/2021 17:53:21 - INFO - __main__ - Step 26299: {'lr': 0.0004674779213102153, 'samples': 5049408, 'steps': 26298, 'loss/train': 0.7796643972396851} 08/30/2021 17:53:21 - INFO - __main__ - Step 26300: {'lr': 0.00046747530393498934, 'samples': 5049600, 'steps': 26299, 'loss/train': 5.412769317626953} 08/30/2021 17:53:21 - INFO - __main__ - Step 26301: {'lr': 0.0004674726864617723, 'samples': 5049792, 'steps': 26300, 'loss/train': 1.9228533506393433} 08/30/2021 17:53:22 - INFO - __main__ - Step 26302: {'lr': 0.00046747006889056556, 'samples': 5049984, 'steps': 26301, 'loss/train': 2.1370584964752197} 08/30/2021 17:53:23 - INFO - __main__ - Step 26303: {'lr': 0.00046746745122137, 'samples': 5050176, 'steps': 26302, 'loss/train': 1.3682295083999634} 08/30/2021 17:53:24 - INFO - __main__ - Step 26304: {'lr': 0.000467464833454187, 'samples': 5050368, 'steps': 26303, 'loss/train': 1.6545788049697876} 08/30/2021 17:53:24 - INFO - __main__ - Step 26305: {'lr': 0.0004674622155890178, 'samples': 5050560, 'steps': 26304, 'loss/train': 1.717965006828308} 08/30/2021 17:53:25 - INFO - __main__ - Step 26306: {'lr': 0.00046745959762586344, 'samples': 5050752, 'steps': 26305, 'loss/train': 0.475311279296875} 08/30/2021 17:53:25 - INFO - __main__ - Step 26307: {'lr': 0.0004674569795647251, 'samples': 5050944, 'steps': 26306, 'loss/train': 1.924486756324768} 08/30/2021 17:53:27 - INFO - __main__ - Step 26308: {'lr': 0.00046745436140560397, 'samples': 5051136, 'steps': 26307, 'loss/train': 1.3409497737884521} 08/30/2021 17:53:27 - INFO - __main__ - Step 26309: {'lr': 0.00046745174314850136, 'samples': 5051328, 'steps': 26308, 'loss/train': 1.4483742713928223} 08/30/2021 17:53:27 - INFO - __main__ - Step 26310: {'lr': 0.00046744912479341826, 'samples': 5051520, 'steps': 26309, 'loss/train': 0.8104193806648254} 08/30/2021 17:53:28 - INFO - __main__ - Step 26311: {'lr': 0.00046744650634035603, 'samples': 5051712, 'steps': 26310, 'loss/train': 1.873723030090332} 08/30/2021 17:53:28 - INFO - __main__ - Step 26312: {'lr': 0.0004674438877893157, 'samples': 5051904, 'steps': 26311, 'loss/train': 2.0275466442108154} 08/30/2021 17:53:29 - INFO - __main__ - Step 26313: {'lr': 0.0004674412691402985, 'samples': 5052096, 'steps': 26312, 'loss/train': 1.306639552116394} 08/30/2021 17:53:30 - INFO - __main__ - Step 26314: {'lr': 0.00046743865039330565, 'samples': 5052288, 'steps': 26313, 'loss/train': 1.2984265089035034} 08/30/2021 17:53:30 - INFO - __main__ - Step 26315: {'lr': 0.00046743603154833827, 'samples': 5052480, 'steps': 26314, 'loss/train': 0.90952467918396} 08/30/2021 17:53:31 - INFO - __main__ - Step 26316: {'lr': 0.00046743341260539756, 'samples': 5052672, 'steps': 26315, 'loss/train': 1.4084138870239258} 08/30/2021 17:53:31 - INFO - __main__ - Step 26317: {'lr': 0.00046743079356448476, 'samples': 5052864, 'steps': 26316, 'loss/train': 1.8966929912567139} 08/30/2021 17:53:33 - INFO - __main__ - Step 26318: {'lr': 0.000467428174425601, 'samples': 5053056, 'steps': 26317, 'loss/train': 1.3839093446731567} 08/30/2021 17:53:33 - INFO - __main__ - Step 26319: {'lr': 0.0004674255551887474, 'samples': 5053248, 'steps': 26318, 'loss/train': 1.144919753074646} 08/30/2021 17:53:34 - INFO - __main__ - Step 26320: {'lr': 0.0004674229358539253, 'samples': 5053440, 'steps': 26319, 'loss/train': 1.1010702848434448} 08/30/2021 17:53:34 - INFO - __main__ - Step 26321: {'lr': 0.0004674203164211357, 'samples': 5053632, 'steps': 26320, 'loss/train': 1.3001075983047485} 08/30/2021 17:53:34 - INFO - __main__ - Step 26322: {'lr': 0.00046741769689037985, 'samples': 5053824, 'steps': 26321, 'loss/train': 1.4087958335876465} 08/30/2021 17:53:36 - INFO - __main__ - Step 26323: {'lr': 0.0004674150772616589, 'samples': 5054016, 'steps': 26322, 'loss/train': 1.2034153938293457} 08/30/2021 17:53:36 - INFO - __main__ - Step 26324: {'lr': 0.0004674124575349742, 'samples': 5054208, 'steps': 26323, 'loss/train': 1.8088667392730713} 08/30/2021 17:53:37 - INFO - __main__ - Step 26325: {'lr': 0.00046740983771032674, 'samples': 5054400, 'steps': 26324, 'loss/train': 5.845498085021973} 08/30/2021 17:53:37 - INFO - __main__ - Step 26326: {'lr': 0.0004674072177877178, 'samples': 5054592, 'steps': 26325, 'loss/train': 1.6823536157608032} 08/30/2021 17:53:37 - INFO - __main__ - Step 26327: {'lr': 0.0004674045977671484, 'samples': 5054784, 'steps': 26326, 'loss/train': 1.9012107849121094} 08/30/2021 17:53:38 - INFO - __main__ - Step 26328: {'lr': 0.00046740197764862, 'samples': 5054976, 'steps': 26327, 'loss/train': 2.1735944747924805} 08/30/2021 17:53:39 - INFO - __main__ - Step 26329: {'lr': 0.00046739935743213344, 'samples': 5055168, 'steps': 26328, 'loss/train': 1.2146939039230347} 08/30/2021 17:53:40 - INFO - __main__ - Step 26330: {'lr': 0.00046739673711769026, 'samples': 5055360, 'steps': 26329, 'loss/train': 1.8299793004989624} 08/30/2021 17:53:40 - INFO - __main__ - Step 26331: {'lr': 0.0004673941167052914, 'samples': 5055552, 'steps': 26330, 'loss/train': 1.4739185571670532} 08/30/2021 17:53:41 - INFO - __main__ - Step 26332: {'lr': 0.0004673914961949381, 'samples': 5055744, 'steps': 26331, 'loss/train': 2.0954718589782715} 08/30/2021 17:53:41 - INFO - __main__ - Step 26333: {'lr': 0.0004673888755866316, 'samples': 5055936, 'steps': 26332, 'loss/train': 0.09940269589424133} 08/30/2021 17:53:42 - INFO - __main__ - Step 26334: {'lr': 0.0004673862548803729, 'samples': 5056128, 'steps': 26333, 'loss/train': 2.0142016410827637} 08/30/2021 17:53:43 - INFO - __main__ - Step 26335: {'lr': 0.0004673836340761634, 'samples': 5056320, 'steps': 26334, 'loss/train': 1.219390630722046} 08/30/2021 17:53:43 - INFO - __main__ - Step 26336: {'lr': 0.00046738101317400415, 'samples': 5056512, 'steps': 26335, 'loss/train': 1.3998562097549438} 08/30/2021 17:53:44 - INFO - __main__ - Step 26337: {'lr': 0.00046737839217389645, 'samples': 5056704, 'steps': 26336, 'loss/train': 0.6932715773582458} 08/30/2021 17:53:44 - INFO - __main__ - Step 26338: {'lr': 0.0004673757710758413, 'samples': 5056896, 'steps': 26337, 'loss/train': 1.809666395187378} 08/30/2021 17:53:46 - INFO - __main__ - Step 26339: {'lr': 0.00046737314987984, 'samples': 5057088, 'steps': 26338, 'loss/train': 1.7099965810775757} 08/30/2021 17:53:46 - INFO - __main__ - Step 26340: {'lr': 0.0004673705285858938, 'samples': 5057280, 'steps': 26339, 'loss/train': 1.4753388166427612} 08/30/2021 17:53:47 - INFO - __main__ - Step 26341: {'lr': 0.00046736790719400373, 'samples': 5057472, 'steps': 26340, 'loss/train': 1.5072438716888428} 08/30/2021 17:53:47 - INFO - __main__ - Step 26342: {'lr': 0.000467365285704171, 'samples': 5057664, 'steps': 26341, 'loss/train': 1.5418766736984253} 08/30/2021 17:53:48 - INFO - __main__ - Step 26343: {'lr': 0.00046736266411639694, 'samples': 5057856, 'steps': 26342, 'loss/train': 1.4100966453552246} 08/30/2021 17:53:49 - INFO - __main__ - Step 26344: {'lr': 0.00046736004243068255, 'samples': 5058048, 'steps': 26343, 'loss/train': 0.12519323825836182} 08/30/2021 17:53:50 - INFO - __main__ - Step 26345: {'lr': 0.00046735742064702904, 'samples': 5058240, 'steps': 26344, 'loss/train': 1.8921748399734497} 08/30/2021 17:53:50 - INFO - __main__ - Step 26346: {'lr': 0.00046735479876543765, 'samples': 5058432, 'steps': 26345, 'loss/train': 1.4676744937896729} 08/30/2021 17:53:51 - INFO - __main__ - Step 26347: {'lr': 0.00046735217678590957, 'samples': 5058624, 'steps': 26346, 'loss/train': 0.17673909664154053} 08/30/2021 17:53:51 - INFO - __main__ - Step 26348: {'lr': 0.00046734955470844594, 'samples': 5058816, 'steps': 26347, 'loss/train': 1.8397572040557861} 08/30/2021 17:53:51 - INFO - __main__ - Step 26349: {'lr': 0.00046734693253304795, 'samples': 5059008, 'steps': 26348, 'loss/train': 1.236518144607544} 08/30/2021 17:53:53 - INFO - __main__ - Step 26350: {'lr': 0.0004673443102597168, 'samples': 5059200, 'steps': 26349, 'loss/train': 1.5384405851364136} 08/30/2021 17:53:53 - INFO - __main__ - Step 26351: {'lr': 0.00046734168788845363, 'samples': 5059392, 'steps': 26350, 'loss/train': 1.015964150428772} 08/30/2021 17:53:54 - INFO - __main__ - Step 26352: {'lr': 0.00046733906541925963, 'samples': 5059584, 'steps': 26351, 'loss/train': 0.9438610076904297} 08/30/2021 17:53:54 - INFO - __main__ - Step 26353: {'lr': 0.00046733644285213604, 'samples': 5059776, 'steps': 26352, 'loss/train': 1.6680570840835571} 08/30/2021 17:53:54 - INFO - __main__ - Step 26354: {'lr': 0.00046733382018708405, 'samples': 5059968, 'steps': 26353, 'loss/train': 1.1922476291656494} 08/30/2021 17:53:56 - INFO - __main__ - Step 26355: {'lr': 0.00046733119742410476, 'samples': 5060160, 'steps': 26354, 'loss/train': 1.4690243005752563} 08/30/2021 17:53:56 - INFO - __main__ - Step 26356: {'lr': 0.0004673285745631993, 'samples': 5060352, 'steps': 26355, 'loss/train': 1.4539414644241333} 08/30/2021 17:53:57 - INFO - __main__ - Step 26357: {'lr': 0.000467325951604369, 'samples': 5060544, 'steps': 26356, 'loss/train': 2.1293528079986572} 08/30/2021 17:53:57 - INFO - __main__ - Step 26358: {'lr': 0.00046732332854761507, 'samples': 5060736, 'steps': 26357, 'loss/train': 1.4316747188568115} 08/30/2021 17:53:57 - INFO - __main__ - Step 26359: {'lr': 0.00046732070539293847, 'samples': 5060928, 'steps': 26358, 'loss/train': 1.9339829683303833} 08/30/2021 17:53:59 - INFO - __main__ - Step 26360: {'lr': 0.0004673180821403405, 'samples': 5061120, 'steps': 26359, 'loss/train': 3.5390784740448} 08/30/2021 17:53:59 - INFO - __main__ - Step 26361: {'lr': 0.00046731545878982253, 'samples': 5061312, 'steps': 26360, 'loss/train': 1.214211344718933} 08/30/2021 17:54:00 - INFO - __main__ - Step 26362: {'lr': 0.0004673128353413854, 'samples': 5061504, 'steps': 26361, 'loss/train': 1.7859796285629272} 08/30/2021 17:54:00 - INFO - __main__ - Step 26363: {'lr': 0.00046731021179503054, 'samples': 5061696, 'steps': 26362, 'loss/train': 5.96531343460083} 08/30/2021 17:54:00 - INFO - __main__ - Step 26364: {'lr': 0.00046730758815075903, 'samples': 5061888, 'steps': 26363, 'loss/train': 1.6871147155761719} 08/30/2021 17:54:01 - INFO - __main__ - Step 26365: {'lr': 0.0004673049644085721, 'samples': 5062080, 'steps': 26364, 'loss/train': 1.836182951927185} 08/30/2021 17:54:02 - INFO - __main__ - Step 26366: {'lr': 0.00046730234056847084, 'samples': 5062272, 'steps': 26365, 'loss/train': 1.4646716117858887} 08/30/2021 17:54:03 - INFO - __main__ - Step 26367: {'lr': 0.00046729971663045654, 'samples': 5062464, 'steps': 26366, 'loss/train': 0.11875174939632416} 08/30/2021 17:54:03 - INFO - __main__ - Step 26368: {'lr': 0.00046729709259453033, 'samples': 5062656, 'steps': 26367, 'loss/train': 0.17010241746902466} 08/30/2021 17:54:04 - INFO - __main__ - Step 26369: {'lr': 0.0004672944684606934, 'samples': 5062848, 'steps': 26368, 'loss/train': 2.159951686859131} 08/30/2021 17:54:04 - INFO - __main__ - Step 26370: {'lr': 0.000467291844228947, 'samples': 5063040, 'steps': 26369, 'loss/train': 1.3013253211975098} 08/30/2021 17:54:05 - INFO - __main__ - Step 26371: {'lr': 0.00046728921989929215, 'samples': 5063232, 'steps': 26370, 'loss/train': 1.547684669494629} 08/30/2021 17:54:06 - INFO - __main__ - Step 26372: {'lr': 0.0004672865954717301, 'samples': 5063424, 'steps': 26371, 'loss/train': 1.6107161045074463} 08/30/2021 17:54:06 - INFO - __main__ - Step 26373: {'lr': 0.00046728397094626217, 'samples': 5063616, 'steps': 26372, 'loss/train': 1.6851725578308105} 08/30/2021 17:54:06 - INFO - __main__ - Step 26374: {'lr': 0.0004672813463228894, 'samples': 5063808, 'steps': 26373, 'loss/train': 1.5158199071884155} 08/30/2021 17:54:07 - INFO - __main__ - Step 26375: {'lr': 0.00046727872160161305, 'samples': 5064000, 'steps': 26374, 'loss/train': 1.4802353382110596} 08/30/2021 17:54:09 - INFO - __main__ - Step 26376: {'lr': 0.0004672760967824342, 'samples': 5064192, 'steps': 26375, 'loss/train': 1.8279871940612793} 08/30/2021 17:54:09 - INFO - __main__ - Step 26377: {'lr': 0.0004672734718653541, 'samples': 5064384, 'steps': 26376, 'loss/train': 0.11590936779975891} 08/30/2021 17:54:10 - INFO - __main__ - Step 26378: {'lr': 0.00046727084685037394, 'samples': 5064576, 'steps': 26377, 'loss/train': 3.5200276374816895} 08/30/2021 17:54:10 - INFO - __main__ - Step 26379: {'lr': 0.00046726822173749497, 'samples': 5064768, 'steps': 26378, 'loss/train': 1.3514212369918823} 08/30/2021 17:54:11 - INFO - __main__ - Step 26380: {'lr': 0.0004672655965267182, 'samples': 5064960, 'steps': 26379, 'loss/train': 1.2324953079223633} 08/30/2021 17:54:12 - INFO - __main__ - Step 26381: {'lr': 0.0004672629712180448, 'samples': 5065152, 'steps': 26380, 'loss/train': 1.6526532173156738} 08/30/2021 17:54:13 - INFO - __main__ - Step 26382: {'lr': 0.00046726034581147624, 'samples': 5065344, 'steps': 26381, 'loss/train': 0.951452910900116} 08/30/2021 17:54:13 - INFO - __main__ - Step 26383: {'lr': 0.0004672577203070135, 'samples': 5065536, 'steps': 26382, 'loss/train': 1.8518738746643066} 08/30/2021 17:54:13 - INFO - __main__ - Step 26384: {'lr': 0.0004672550947046577, 'samples': 5065728, 'steps': 26383, 'loss/train': 0.9917610883712769} 08/30/2021 17:54:14 - INFO - __main__ - Step 26385: {'lr': 0.0004672524690044102, 'samples': 5065920, 'steps': 26384, 'loss/train': 2.4184682369232178} 08/30/2021 17:54:14 - INFO - __main__ - Step 26386: {'lr': 0.000467249843206272, 'samples': 5066112, 'steps': 26385, 'loss/train': 1.4285353422164917} 08/30/2021 17:54:15 - INFO - __main__ - Step 26387: {'lr': 0.00046724721731024446, 'samples': 5066304, 'steps': 26386, 'loss/train': 1.8097509145736694} 08/30/2021 17:54:16 - INFO - __main__ - Step 26388: {'lr': 0.00046724459131632854, 'samples': 5066496, 'steps': 26387, 'loss/train': 1.3934749364852905} 08/30/2021 17:54:16 - INFO - __main__ - Step 26389: {'lr': 0.00046724196522452565, 'samples': 5066688, 'steps': 26388, 'loss/train': 1.9031007289886475} 08/30/2021 17:54:17 - INFO - __main__ - Step 26390: {'lr': 0.00046723933903483687, 'samples': 5066880, 'steps': 26389, 'loss/train': 1.7344425916671753} 08/30/2021 17:54:17 - INFO - __main__ - Step 26391: {'lr': 0.00046723671274726344, 'samples': 5067072, 'steps': 26390, 'loss/train': 1.6269930601119995} 08/30/2021 17:54:18 - INFO - __main__ - Step 26392: {'lr': 0.00046723408636180645, 'samples': 5067264, 'steps': 26391, 'loss/train': 1.904179334640503} 08/30/2021 17:54:19 - INFO - __main__ - Step 26393: {'lr': 0.00046723145987846715, 'samples': 5067456, 'steps': 26392, 'loss/train': 1.6348963975906372} 08/30/2021 17:54:19 - INFO - __main__ - Step 26394: {'lr': 0.00046722883329724667, 'samples': 5067648, 'steps': 26393, 'loss/train': 1.3784867525100708} 08/30/2021 17:54:19 - INFO - __main__ - Step 26395: {'lr': 0.0004672262066181463, 'samples': 5067840, 'steps': 26394, 'loss/train': 1.7997623682022095} 08/30/2021 17:54:20 - INFO - __main__ - Step 26396: {'lr': 0.00046722357984116717, 'samples': 5068032, 'steps': 26395, 'loss/train': 1.4385432004928589} 08/30/2021 17:54:21 - INFO - __main__ - Step 26397: {'lr': 0.0004672209529663103, 'samples': 5068224, 'steps': 26396, 'loss/train': 1.9246010780334473} 08/30/2021 17:54:22 - INFO - __main__ - Step 26398: {'lr': 0.00046721832599357717, 'samples': 5068416, 'steps': 26397, 'loss/train': 1.470102071762085} 08/30/2021 17:54:22 - INFO - __main__ - Step 26399: {'lr': 0.00046721569892296875, 'samples': 5068608, 'steps': 26398, 'loss/train': 1.6469706296920776} 08/30/2021 17:54:22 - INFO - __main__ - Step 26400: {'lr': 0.00046721307175448626, 'samples': 5068800, 'steps': 26399, 'loss/train': 1.223879337310791} 08/30/2021 17:54:23 - INFO - __main__ - Step 26401: {'lr': 0.000467210444488131, 'samples': 5068992, 'steps': 26400, 'loss/train': 0.6934109330177307} 08/30/2021 17:54:25 - INFO - __main__ - Step 26402: {'lr': 0.000467207817123904, 'samples': 5069184, 'steps': 26401, 'loss/train': 1.8567276000976562} 08/30/2021 17:54:25 - INFO - __main__ - Step 26403: {'lr': 0.0004672051896618065, 'samples': 5069376, 'steps': 26402, 'loss/train': 0.9742704033851624} 08/30/2021 17:54:25 - INFO - __main__ - Step 26404: {'lr': 0.0004672025621018397, 'samples': 5069568, 'steps': 26403, 'loss/train': 0.0499262660741806} 08/30/2021 17:54:26 - INFO - __main__ - Step 26405: {'lr': 0.00046719993444400477, 'samples': 5069760, 'steps': 26404, 'loss/train': 1.4353646039962769} 08/30/2021 17:54:26 - INFO - __main__ - Step 26406: {'lr': 0.00046719730668830293, 'samples': 5069952, 'steps': 26405, 'loss/train': 1.8499877452850342} 08/30/2021 17:54:27 - INFO - __main__ - Step 26407: {'lr': 0.0004671946788347353, 'samples': 5070144, 'steps': 26406, 'loss/train': 1.4248777627944946} 08/30/2021 17:54:27 - INFO - __main__ - Step 26408: {'lr': 0.00046719205088330317, 'samples': 5070336, 'steps': 26407, 'loss/train': 1.6838206052780151} 08/30/2021 17:54:28 - INFO - __main__ - Step 26409: {'lr': 0.0004671894228340076, 'samples': 5070528, 'steps': 26408, 'loss/train': 1.920997977256775} 08/30/2021 17:54:29 - INFO - __main__ - Step 26410: {'lr': 0.0004671867946868499, 'samples': 5070720, 'steps': 26409, 'loss/train': 1.8226802349090576} 08/30/2021 17:54:29 - INFO - __main__ - Step 26411: {'lr': 0.000467184166441831, 'samples': 5070912, 'steps': 26410, 'loss/train': 1.7642099857330322} 08/30/2021 17:54:29 - INFO - __main__ - Step 26412: {'lr': 0.0004671815380989525, 'samples': 5071104, 'steps': 26411, 'loss/train': 0.9808248281478882} 08/30/2021 17:54:30 - INFO - __main__ - Step 26413: {'lr': 0.0004671789096582152, 'samples': 5071296, 'steps': 26412, 'loss/train': 1.769890546798706} 08/30/2021 17:54:32 - INFO - __main__ - Step 26414: {'lr': 0.00046717628111962045, 'samples': 5071488, 'steps': 26413, 'loss/train': 1.6621394157409668} 08/30/2021 17:54:32 - INFO - __main__ - Step 26415: {'lr': 0.00046717365248316947, 'samples': 5071680, 'steps': 26414, 'loss/train': 1.7568658590316772} 08/30/2021 17:54:33 - INFO - __main__ - Step 26416: {'lr': 0.00046717102374886334, 'samples': 5071872, 'steps': 26415, 'loss/train': 0.8884730935096741} 08/30/2021 17:54:33 - INFO - __main__ - Step 26417: {'lr': 0.0004671683949167033, 'samples': 5072064, 'steps': 26416, 'loss/train': 1.5018233060836792} 08/30/2021 17:54:33 - INFO - __main__ - Step 26418: {'lr': 0.0004671657659866906, 'samples': 5072256, 'steps': 26417, 'loss/train': 2.1330373287200928} 08/30/2021 17:54:34 - INFO - __main__ - Step 26419: {'lr': 0.00046716313695882626, 'samples': 5072448, 'steps': 26418, 'loss/train': 0.3153764307498932} 08/30/2021 17:54:36 - INFO - __main__ - Step 26420: {'lr': 0.00046716050783311166, 'samples': 5072640, 'steps': 26419, 'loss/train': 0.04831329733133316} 08/30/2021 17:54:36 - INFO - __main__ - Step 26421: {'lr': 0.00046715787860954785, 'samples': 5072832, 'steps': 26420, 'loss/train': 1.573830008506775} 08/30/2021 17:54:36 - INFO - __main__ - Step 26422: {'lr': 0.000467155249288136, 'samples': 5073024, 'steps': 26421, 'loss/train': 1.1698150634765625} 08/30/2021 17:54:37 - INFO - __main__ - Step 26423: {'lr': 0.00046715261986887734, 'samples': 5073216, 'steps': 26422, 'loss/train': 1.5478065013885498} 08/30/2021 17:54:37 - INFO - __main__ - Step 26424: {'lr': 0.0004671499903517732, 'samples': 5073408, 'steps': 26423, 'loss/train': 1.3033256530761719} 08/30/2021 17:54:39 - INFO - __main__ - Step 26425: {'lr': 0.00046714736073682453, 'samples': 5073600, 'steps': 26424, 'loss/train': 0.21836160123348236} 08/30/2021 17:54:39 - INFO - __main__ - Step 26426: {'lr': 0.00046714473102403255, 'samples': 5073792, 'steps': 26425, 'loss/train': 1.481293797492981} 08/30/2021 17:54:39 - INFO - __main__ - Step 26427: {'lr': 0.0004671421012133986, 'samples': 5073984, 'steps': 26426, 'loss/train': 1.5887008905410767} 08/30/2021 17:54:40 - INFO - __main__ - Step 26428: {'lr': 0.00046713947130492373, 'samples': 5074176, 'steps': 26427, 'loss/train': 1.770939826965332} 08/30/2021 17:54:40 - INFO - __main__ - Step 26429: {'lr': 0.0004671368412986091, 'samples': 5074368, 'steps': 26428, 'loss/train': 1.5196409225463867} 08/30/2021 17:54:43 - INFO - __main__ - Step 26430: {'lr': 0.0004671342111944561, 'samples': 5074560, 'steps': 26429, 'loss/train': 1.2715877294540405} 08/30/2021 17:54:44 - INFO - __main__ - Step 26431: {'lr': 0.00046713158099246564, 'samples': 5074752, 'steps': 26430, 'loss/train': 1.879807710647583} 08/30/2021 17:54:44 - INFO - __main__ - Step 26432: {'lr': 0.00046712895069263917, 'samples': 5074944, 'steps': 26431, 'loss/train': 1.8316450119018555} 08/30/2021 17:54:44 - INFO - __main__ - Step 26433: {'lr': 0.00046712632029497766, 'samples': 5075136, 'steps': 26432, 'loss/train': 1.1785908937454224} 08/30/2021 17:54:45 - INFO - __main__ - Step 26434: {'lr': 0.0004671236897994824, 'samples': 5075328, 'steps': 26433, 'loss/train': 1.2271547317504883} 08/30/2021 17:54:45 - INFO - __main__ - Step 26435: {'lr': 0.00046712105920615455, 'samples': 5075520, 'steps': 26434, 'loss/train': 2.026353120803833} 08/30/2021 17:54:45 - INFO - __main__ - Step 26436: {'lr': 0.00046711842851499533, 'samples': 5075712, 'steps': 26435, 'loss/train': 3.067622661590576} 08/30/2021 17:54:46 - INFO - __main__ - Step 26437: {'lr': 0.0004671157977260059, 'samples': 5075904, 'steps': 26436, 'loss/train': 1.6393345594406128} 08/30/2021 17:54:47 - INFO - __main__ - Step 26438: {'lr': 0.0004671131668391874, 'samples': 5076096, 'steps': 26437, 'loss/train': 0.8563994765281677} 08/30/2021 17:54:48 - INFO - __main__ - Step 26439: {'lr': 0.00046711053585454104, 'samples': 5076288, 'steps': 26438, 'loss/train': 1.2317432165145874} 08/30/2021 17:54:48 - INFO - __main__ - Step 26440: {'lr': 0.0004671079047720681, 'samples': 5076480, 'steps': 26439, 'loss/train': 1.503592610359192} 08/30/2021 17:54:49 - INFO - __main__ - Step 26441: {'lr': 0.00046710527359176957, 'samples': 5076672, 'steps': 26440, 'loss/train': 1.7058897018432617} 08/30/2021 17:54:49 - INFO - __main__ - Step 26442: {'lr': 0.0004671026423136469, 'samples': 5076864, 'steps': 26441, 'loss/train': 1.1538952589035034} 08/30/2021 17:54:50 - INFO - __main__ - Step 26443: {'lr': 0.00046710001093770107, 'samples': 5077056, 'steps': 26442, 'loss/train': 1.1952552795410156} 08/30/2021 17:54:51 - INFO - __main__ - Step 26444: {'lr': 0.0004670973794639333, 'samples': 5077248, 'steps': 26443, 'loss/train': 1.5073482990264893} 08/30/2021 17:54:51 - INFO - __main__ - Step 26445: {'lr': 0.0004670947478923447, 'samples': 5077440, 'steps': 26444, 'loss/train': 1.3746172189712524} 08/30/2021 17:54:52 - INFO - __main__ - Step 26446: {'lr': 0.00046709211622293677, 'samples': 5077632, 'steps': 26445, 'loss/train': 1.3588981628417969} 08/30/2021 17:54:52 - INFO - __main__ - Step 26447: {'lr': 0.00046708948445571037, 'samples': 5077824, 'steps': 26446, 'loss/train': 1.8258367776870728} 08/30/2021 17:54:54 - INFO - __main__ - Step 26448: {'lr': 0.0004670868525906668, 'samples': 5078016, 'steps': 26447, 'loss/train': 1.0081768035888672} 08/30/2021 17:54:55 - INFO - __main__ - Step 26449: {'lr': 0.00046708422062780725, 'samples': 5078208, 'steps': 26448, 'loss/train': 1.5623821020126343} 08/30/2021 17:54:55 - INFO - __main__ - Step 26450: {'lr': 0.0004670815885671329, 'samples': 5078400, 'steps': 26449, 'loss/train': 1.381220817565918} 08/30/2021 17:54:56 - INFO - __main__ - Step 26451: {'lr': 0.00046707895640864494, 'samples': 5078592, 'steps': 26450, 'loss/train': 0.7613924145698547} 08/30/2021 17:54:56 - INFO - __main__ - Step 26452: {'lr': 0.0004670763241523446, 'samples': 5078784, 'steps': 26451, 'loss/train': 0.6841173768043518} 08/30/2021 17:54:56 - INFO - __main__ - Step 26453: {'lr': 0.00046707369179823294, 'samples': 5078976, 'steps': 26452, 'loss/train': 0.5758198499679565} 08/30/2021 17:54:57 - INFO - __main__ - Step 26454: {'lr': 0.00046707105934631123, 'samples': 5079168, 'steps': 26453, 'loss/train': 0.5321375727653503} 08/30/2021 17:54:58 - INFO - __main__ - Step 26455: {'lr': 0.00046706842679658067, 'samples': 5079360, 'steps': 26454, 'loss/train': 1.0598952770233154} 08/30/2021 17:54:59 - INFO - __main__ - Step 26456: {'lr': 0.0004670657941490425, 'samples': 5079552, 'steps': 26455, 'loss/train': 0.2264997810125351} 08/30/2021 17:54:59 - INFO - __main__ - Step 26457: {'lr': 0.00046706316140369774, 'samples': 5079744, 'steps': 26456, 'loss/train': 1.4735705852508545} 08/30/2021 17:54:59 - INFO - __main__ - Step 26458: {'lr': 0.0004670605285605477, 'samples': 5079936, 'steps': 26457, 'loss/train': 1.39555025100708} 08/30/2021 17:55:00 - INFO - __main__ - Step 26459: {'lr': 0.0004670578956195935, 'samples': 5080128, 'steps': 26458, 'loss/train': 1.5469558238983154} 08/30/2021 17:55:01 - INFO - __main__ - Step 26460: {'lr': 0.00046705526258083643, 'samples': 5080320, 'steps': 26459, 'loss/train': 1.3662614822387695} 08/30/2021 17:55:02 - INFO - __main__ - Step 26461: {'lr': 0.0004670526294442775, 'samples': 5080512, 'steps': 26460, 'loss/train': 1.7535197734832764} 08/30/2021 17:55:02 - INFO - __main__ - Step 26462: {'lr': 0.0004670499962099181, 'samples': 5080704, 'steps': 26461, 'loss/train': 2.2103404998779297} 08/30/2021 17:55:02 - INFO - __main__ - Step 26463: {'lr': 0.0004670473628777593, 'samples': 5080896, 'steps': 26462, 'loss/train': 1.1556077003479004} 08/30/2021 17:55:03 - INFO - __main__ - Step 26464: {'lr': 0.0004670447294478023, 'samples': 5081088, 'steps': 26463, 'loss/train': 1.4666619300842285} 08/30/2021 17:55:04 - INFO - __main__ - Step 26465: {'lr': 0.0004670420959200483, 'samples': 5081280, 'steps': 26464, 'loss/train': 1.7490825653076172} 08/30/2021 17:55:05 - INFO - __main__ - Step 26466: {'lr': 0.00046703946229449846, 'samples': 5081472, 'steps': 26465, 'loss/train': 1.3428783416748047} 08/30/2021 17:55:05 - INFO - __main__ - Step 26467: {'lr': 0.00046703682857115406, 'samples': 5081664, 'steps': 26466, 'loss/train': 1.2313660383224487} 08/30/2021 17:55:06 - INFO - __main__ - Step 26468: {'lr': 0.0004670341947500161, 'samples': 5081856, 'steps': 26467, 'loss/train': 1.5175172090530396} 08/30/2021 17:55:06 - INFO - __main__ - Step 26469: {'lr': 0.00046703156083108597, 'samples': 5082048, 'steps': 26468, 'loss/train': 1.4003242254257202} 08/30/2021 17:55:07 - INFO - __main__ - Step 26470: {'lr': 0.0004670289268143647, 'samples': 5082240, 'steps': 26469, 'loss/train': 0.4863508343696594} 08/30/2021 17:55:08 - INFO - __main__ - Step 26471: {'lr': 0.0004670262926998536, 'samples': 5082432, 'steps': 26470, 'loss/train': 1.4212708473205566} 08/30/2021 17:55:08 - INFO - __main__ - Step 26472: {'lr': 0.00046702365848755377, 'samples': 5082624, 'steps': 26471, 'loss/train': 1.6410430669784546} 08/30/2021 17:55:08 - INFO - __main__ - Step 26473: {'lr': 0.0004670210241774664, 'samples': 5082816, 'steps': 26472, 'loss/train': 1.008784294128418} 08/30/2021 17:55:09 - INFO - __main__ - Step 26474: {'lr': 0.0004670183897695928, 'samples': 5083008, 'steps': 26473, 'loss/train': 1.7928823232650757} 08/30/2021 17:55:10 - INFO - __main__ - Step 26475: {'lr': 0.00046701575526393395, 'samples': 5083200, 'steps': 26474, 'loss/train': 1.339598536491394} 08/30/2021 17:55:11 - INFO - __main__ - Step 26476: {'lr': 0.00046701312066049126, 'samples': 5083392, 'steps': 26475, 'loss/train': 1.4918270111083984} 08/30/2021 17:55:11 - INFO - __main__ - Step 26477: {'lr': 0.00046701048595926574, 'samples': 5083584, 'steps': 26476, 'loss/train': 2.120662212371826} 08/30/2021 17:55:12 - INFO - __main__ - Step 26478: {'lr': 0.00046700785116025867, 'samples': 5083776, 'steps': 26477, 'loss/train': 1.672579050064087} 08/30/2021 17:55:12 - INFO - __main__ - Step 26479: {'lr': 0.0004670052162634712, 'samples': 5083968, 'steps': 26478, 'loss/train': 1.7572641372680664} 08/30/2021 17:55:12 - INFO - __main__ - Step 26480: {'lr': 0.0004670025812689045, 'samples': 5084160, 'steps': 26479, 'loss/train': 1.507641315460205} 08/30/2021 17:55:14 - INFO - __main__ - Step 26481: {'lr': 0.00046699994617655985, 'samples': 5084352, 'steps': 26480, 'loss/train': 1.281359314918518} 08/30/2021 17:55:14 - INFO - __main__ - Step 26482: {'lr': 0.0004669973109864383, 'samples': 5084544, 'steps': 26481, 'loss/train': 1.397874116897583} 08/30/2021 17:55:14 - INFO - __main__ - Step 26483: {'lr': 0.00046699467569854115, 'samples': 5084736, 'steps': 26482, 'loss/train': 1.1106603145599365} 08/30/2021 17:55:15 - INFO - __main__ - Step 26484: {'lr': 0.0004669920403128696, 'samples': 5084928, 'steps': 26483, 'loss/train': 1.7543003559112549} 08/30/2021 17:55:15 - INFO - __main__ - Step 26485: {'lr': 0.00046698940482942466, 'samples': 5085120, 'steps': 26484, 'loss/train': 1.2458912134170532} 08/30/2021 17:55:17 - INFO - __main__ - Step 26486: {'lr': 0.0004669867692482077, 'samples': 5085312, 'steps': 26485, 'loss/train': 1.9360105991363525} 08/30/2021 17:55:18 - INFO - __main__ - Step 26487: {'lr': 0.00046698413356921985, 'samples': 5085504, 'steps': 26486, 'loss/train': 0.9060123562812805} 08/30/2021 17:55:18 - INFO - __main__ - Step 26488: {'lr': 0.00046698149779246235, 'samples': 5085696, 'steps': 26487, 'loss/train': 1.7709970474243164} 08/30/2021 17:55:18 - INFO - __main__ - Step 26489: {'lr': 0.0004669788619179363, 'samples': 5085888, 'steps': 26488, 'loss/train': 1.8481642007827759} 08/30/2021 17:55:19 - INFO - __main__ - Step 26490: {'lr': 0.0004669762259456429, 'samples': 5086080, 'steps': 26489, 'loss/train': 1.6907516717910767} 08/30/2021 17:55:20 - INFO - __main__ - Step 26491: {'lr': 0.00046697358987558336, 'samples': 5086272, 'steps': 26490, 'loss/train': 1.2334203720092773} 08/30/2021 17:55:21 - INFO - __main__ - Step 26492: {'lr': 0.0004669709537077589, 'samples': 5086464, 'steps': 26491, 'loss/train': 1.840136170387268} 08/30/2021 17:55:21 - INFO - __main__ - Step 26493: {'lr': 0.00046696831744217065, 'samples': 5086656, 'steps': 26492, 'loss/train': 0.9647053480148315} 08/30/2021 17:55:21 - INFO - __main__ - Step 26494: {'lr': 0.0004669656810788199, 'samples': 5086848, 'steps': 26493, 'loss/train': 1.555384635925293} 08/30/2021 17:55:22 - INFO - __main__ - Step 26495: {'lr': 0.0004669630446177077, 'samples': 5087040, 'steps': 26494, 'loss/train': 0.9002858400344849} 08/30/2021 17:55:24 - INFO - __main__ - Step 26496: {'lr': 0.0004669604080588352, 'samples': 5087232, 'steps': 26495, 'loss/train': 2.0909271240234375} 08/30/2021 17:55:24 - INFO - __main__ - Step 26497: {'lr': 0.0004669577714022039, 'samples': 5087424, 'steps': 26496, 'loss/train': 1.7274521589279175} 08/30/2021 17:55:24 - INFO - __main__ - Step 26498: {'lr': 0.00046695513464781456, 'samples': 5087616, 'steps': 26497, 'loss/train': 1.4134820699691772} 08/30/2021 17:55:25 - INFO - __main__ - Step 26499: {'lr': 0.00046695249779566875, 'samples': 5087808, 'steps': 26498, 'loss/train': 1.7090868949890137} 08/30/2021 17:55:25 - INFO - __main__ - Step 26500: {'lr': 0.0004669498608457674, 'samples': 5088000, 'steps': 26499, 'loss/train': 2.725168466567993} 08/30/2021 17:55:25 - INFO - __main__ - Step 26501: {'lr': 0.0004669472237981118, 'samples': 5088192, 'steps': 26500, 'loss/train': 1.5974403619766235} 08/30/2021 17:55:27 - INFO - __main__ - Step 26502: {'lr': 0.00046694458665270315, 'samples': 5088384, 'steps': 26501, 'loss/train': 1.7336952686309814} 08/30/2021 17:55:28 - INFO - __main__ - Step 26503: {'lr': 0.0004669419494095426, 'samples': 5088576, 'steps': 26502, 'loss/train': 1.2236595153808594} 08/30/2021 17:55:28 - INFO - __main__ - Step 26504: {'lr': 0.0004669393120686314, 'samples': 5088768, 'steps': 26503, 'loss/train': 1.8604410886764526} 08/30/2021 17:55:28 - INFO - __main__ - Step 26505: {'lr': 0.0004669366746299707, 'samples': 5088960, 'steps': 26504, 'loss/train': 4.852655410766602} 08/30/2021 17:55:29 - INFO - __main__ - Step 26506: {'lr': 0.00046693403709356163, 'samples': 5089152, 'steps': 26505, 'loss/train': 1.74601149559021} 08/30/2021 17:55:29 - INFO - __main__ - Step 26507: {'lr': 0.00046693139945940546, 'samples': 5089344, 'steps': 26506, 'loss/train': 1.7411202192306519} 08/30/2021 17:55:31 - INFO - __main__ - Step 26508: {'lr': 0.0004669287617275033, 'samples': 5089536, 'steps': 26507, 'loss/train': 2.4722275733947754} 08/30/2021 17:55:31 - INFO - __main__ - Step 26509: {'lr': 0.0004669261238978564, 'samples': 5089728, 'steps': 26508, 'loss/train': 1.3681408166885376} 08/30/2021 17:55:31 - INFO - __main__ - Step 26510: {'lr': 0.00046692348597046596, 'samples': 5089920, 'steps': 26509, 'loss/train': 1.345752239227295} 08/30/2021 17:55:32 - INFO - __main__ - Step 26511: {'lr': 0.0004669208479453332, 'samples': 5090112, 'steps': 26510, 'loss/train': 1.8200063705444336} 08/30/2021 17:55:32 - INFO - __main__ - Step 26512: {'lr': 0.00046691820982245913, 'samples': 5090304, 'steps': 26511, 'loss/train': 1.7139945030212402} 08/30/2021 17:55:34 - INFO - __main__ - Step 26513: {'lr': 0.00046691557160184516, 'samples': 5090496, 'steps': 26512, 'loss/train': 1.4040721654891968} 08/30/2021 17:55:34 - INFO - __main__ - Step 26514: {'lr': 0.0004669129332834923, 'samples': 5090688, 'steps': 26513, 'loss/train': 1.6137622594833374} 08/30/2021 17:55:34 - INFO - __main__ - Step 26515: {'lr': 0.0004669102948674019, 'samples': 5090880, 'steps': 26514, 'loss/train': 1.3544131517410278} 08/30/2021 17:55:35 - INFO - __main__ - Step 26516: {'lr': 0.000466907656353575, 'samples': 5091072, 'steps': 26515, 'loss/train': 1.6316208839416504} 08/30/2021 17:55:35 - INFO - __main__ - Step 26517: {'lr': 0.0004669050177420129, 'samples': 5091264, 'steps': 26516, 'loss/train': 1.7549480199813843} 08/30/2021 17:55:35 - INFO - __main__ - Step 26518: {'lr': 0.0004669023790327168, 'samples': 5091456, 'steps': 26517, 'loss/train': 1.9351155757904053} 08/30/2021 17:55:37 - INFO - __main__ - Step 26519: {'lr': 0.0004668997402256877, 'samples': 5091648, 'steps': 26518, 'loss/train': 1.75971519947052} 08/30/2021 17:55:37 - INFO - __main__ - Step 26520: {'lr': 0.00046689710132092704, 'samples': 5091840, 'steps': 26519, 'loss/train': 1.475289225578308} 08/30/2021 17:55:38 - INFO - __main__ - Step 26521: {'lr': 0.00046689446231843585, 'samples': 5092032, 'steps': 26520, 'loss/train': 0.4546389579772949} 08/30/2021 17:55:38 - INFO - __main__ - Step 26522: {'lr': 0.0004668918232182153, 'samples': 5092224, 'steps': 26521, 'loss/train': 1.20957612991333} 08/30/2021 17:55:38 - INFO - __main__ - Step 26523: {'lr': 0.0004668891840202668, 'samples': 5092416, 'steps': 26522, 'loss/train': 1.6378568410873413} 08/30/2021 17:55:40 - INFO - __main__ - Step 26524: {'lr': 0.00046688654472459124, 'samples': 5092608, 'steps': 26523, 'loss/train': 1.5544283390045166} 08/30/2021 17:55:41 - INFO - __main__ - Step 26525: {'lr': 0.00046688390533119003, 'samples': 5092800, 'steps': 26524, 'loss/train': 1.7190724611282349} 08/30/2021 17:55:41 - INFO - __main__ - Step 26526: {'lr': 0.00046688126584006425, 'samples': 5092992, 'steps': 26525, 'loss/train': 2.415898323059082} 08/30/2021 17:55:41 - INFO - __main__ - Step 26527: {'lr': 0.00046687862625121505, 'samples': 5093184, 'steps': 26526, 'loss/train': 1.759015679359436} 08/30/2021 17:55:42 - INFO - __main__ - Step 26528: {'lr': 0.0004668759865646438, 'samples': 5093376, 'steps': 26527, 'loss/train': 0.3155175745487213} 08/30/2021 17:55:43 - INFO - __main__ - Step 26529: {'lr': 0.00046687334678035153, 'samples': 5093568, 'steps': 26528, 'loss/train': 1.1815344095230103} 08/30/2021 17:55:44 - INFO - __main__ - Step 26530: {'lr': 0.00046687070689833943, 'samples': 5093760, 'steps': 26529, 'loss/train': 1.4764231443405151} 08/30/2021 17:55:44 - INFO - __main__ - Step 26531: {'lr': 0.00046686806691860884, 'samples': 5093952, 'steps': 26530, 'loss/train': 1.9032479524612427} 08/30/2021 17:55:44 - INFO - __main__ - Step 26532: {'lr': 0.00046686542684116073, 'samples': 5094144, 'steps': 26531, 'loss/train': 1.7096304893493652} 08/30/2021 17:55:45 - INFO - __main__ - Step 26533: {'lr': 0.00046686278666599647, 'samples': 5094336, 'steps': 26532, 'loss/train': 1.3388385772705078} 08/30/2021 17:55:46 - INFO - __main__ - Step 26534: {'lr': 0.0004668601463931172, 'samples': 5094528, 'steps': 26533, 'loss/train': 1.315308928489685} 08/30/2021 17:55:47 - INFO - __main__ - Step 26535: {'lr': 0.00046685750602252406, 'samples': 5094720, 'steps': 26534, 'loss/train': 1.5765104293823242} 08/30/2021 17:55:47 - INFO - __main__ - Step 26536: {'lr': 0.0004668548655542183, 'samples': 5094912, 'steps': 26535, 'loss/train': 1.4822983741760254} 08/30/2021 17:55:47 - INFO - __main__ - Step 26537: {'lr': 0.000466852224988201, 'samples': 5095104, 'steps': 26536, 'loss/train': 0.7185746431350708} 08/30/2021 17:55:48 - INFO - __main__ - Step 26538: {'lr': 0.00046684958432447355, 'samples': 5095296, 'steps': 26537, 'loss/train': 1.265125036239624} 08/30/2021 17:55:50 - INFO - __main__ - Step 26539: {'lr': 0.00046684694356303693, 'samples': 5095488, 'steps': 26538, 'loss/train': 1.5037517547607422} 08/30/2021 17:55:50 - INFO - __main__ - Step 26540: {'lr': 0.0004668443027038925, 'samples': 5095680, 'steps': 26539, 'loss/train': 2.094182252883911} 08/30/2021 17:55:50 - INFO - __main__ - Step 26541: {'lr': 0.00046684166174704134, 'samples': 5095872, 'steps': 26540, 'loss/train': 1.6000418663024902} 08/30/2021 17:55:51 - INFO - __main__ - Step 26542: {'lr': 0.00046683902069248465, 'samples': 5096064, 'steps': 26541, 'loss/train': 1.3042372465133667} 08/30/2021 17:55:51 - INFO - __main__ - Step 26543: {'lr': 0.0004668363795402237, 'samples': 5096256, 'steps': 26542, 'loss/train': 1.4274382591247559} 08/30/2021 17:55:53 - INFO - __main__ - Step 26544: {'lr': 0.00046683373829025954, 'samples': 5096448, 'steps': 26543, 'loss/train': 1.6654459238052368} 08/30/2021 17:55:53 - INFO - __main__ - Step 26545: {'lr': 0.0004668310969425935, 'samples': 5096640, 'steps': 26544, 'loss/train': 1.9225696325302124} 08/30/2021 17:55:53 - INFO - __main__ - Step 26546: {'lr': 0.00046682845549722677, 'samples': 5096832, 'steps': 26545, 'loss/train': 1.6828829050064087} 08/30/2021 17:55:54 - INFO - __main__ - Step 26547: {'lr': 0.0004668258139541604, 'samples': 5097024, 'steps': 26546, 'loss/train': 2.350262403488159} 08/30/2021 17:55:54 - INFO - __main__ - Step 26548: {'lr': 0.00046682317231339565, 'samples': 5097216, 'steps': 26547, 'loss/train': 1.8005173206329346} 08/30/2021 17:55:56 - INFO - __main__ - Step 26549: {'lr': 0.00046682053057493377, 'samples': 5097408, 'steps': 26548, 'loss/train': 1.7175638675689697} 08/30/2021 17:55:56 - INFO - __main__ - Step 26550: {'lr': 0.00046681788873877595, 'samples': 5097600, 'steps': 26549, 'loss/train': 1.4173011779785156} 08/30/2021 17:55:57 - INFO - __main__ - Step 26551: {'lr': 0.00046681524680492327, 'samples': 5097792, 'steps': 26550, 'loss/train': 2.0777764320373535} 08/30/2021 17:55:57 - INFO - __main__ - Step 26552: {'lr': 0.00046681260477337693, 'samples': 5097984, 'steps': 26551, 'loss/train': 0.9717393517494202} 08/30/2021 17:55:57 - INFO - __main__ - Step 26553: {'lr': 0.0004668099626441383, 'samples': 5098176, 'steps': 26552, 'loss/train': 4.609521389007568} 08/30/2021 17:55:58 - INFO - __main__ - Step 26554: {'lr': 0.00046680732041720836, 'samples': 5098368, 'steps': 26553, 'loss/train': 1.4219341278076172} 08/30/2021 17:55:59 - INFO - __main__ - Step 26555: {'lr': 0.0004668046780925884, 'samples': 5098560, 'steps': 26554, 'loss/train': 1.711804747581482} 08/30/2021 17:56:00 - INFO - __main__ - Step 26556: {'lr': 0.0004668020356702796, 'samples': 5098752, 'steps': 26555, 'loss/train': 1.7388359308242798} 08/30/2021 17:56:00 - INFO - __main__ - Step 26557: {'lr': 0.0004667993931502832, 'samples': 5098944, 'steps': 26556, 'loss/train': 1.4576250314712524} 08/30/2021 17:56:00 - INFO - __main__ - Step 26558: {'lr': 0.00046679675053260027, 'samples': 5099136, 'steps': 26557, 'loss/train': 2.0638508796691895} 08/30/2021 17:56:01 - INFO - __main__ - Step 26559: {'lr': 0.00046679410781723206, 'samples': 5099328, 'steps': 26558, 'loss/train': 1.4840946197509766} 08/30/2021 17:56:02 - INFO - __main__ - Step 26560: {'lr': 0.0004667914650041799, 'samples': 5099520, 'steps': 26559, 'loss/train': 2.2055389881134033} 08/30/2021 17:56:03 - INFO - __main__ - Step 26561: {'lr': 0.00046678882209344474, 'samples': 5099712, 'steps': 26560, 'loss/train': 1.8977118730545044} 08/30/2021 17:56:03 - INFO - __main__ - Step 26562: {'lr': 0.00046678617908502785, 'samples': 5099904, 'steps': 26561, 'loss/train': 0.975948691368103} 08/30/2021 17:56:04 - INFO - __main__ - Step 26563: {'lr': 0.00046678353597893053, 'samples': 5100096, 'steps': 26562, 'loss/train': 0.4861288368701935} 08/30/2021 17:56:04 - INFO - __main__ - Step 26564: {'lr': 0.0004667808927751539, 'samples': 5100288, 'steps': 26563, 'loss/train': 0.9822503924369812} 08/30/2021 17:56:06 - INFO - __main__ - Step 26565: {'lr': 0.00046677824947369907, 'samples': 5100480, 'steps': 26564, 'loss/train': 1.2419246435165405} 08/30/2021 17:56:06 - INFO - __main__ - Step 26566: {'lr': 0.0004667756060745674, 'samples': 5100672, 'steps': 26565, 'loss/train': 1.6193146705627441} 08/30/2021 17:56:06 - INFO - __main__ - Step 26567: {'lr': 0.0004667729625777599, 'samples': 5100864, 'steps': 26566, 'loss/train': 1.7757670879364014} 08/30/2021 17:56:07 - INFO - __main__ - Step 26568: {'lr': 0.0004667703189832779, 'samples': 5101056, 'steps': 26567, 'loss/train': 1.699609637260437} 08/30/2021 17:56:07 - INFO - __main__ - Step 26569: {'lr': 0.00046676767529112254, 'samples': 5101248, 'steps': 26568, 'loss/train': 1.9243919849395752} 08/30/2021 17:56:07 - INFO - __main__ - Step 26570: {'lr': 0.000466765031501295, 'samples': 5101440, 'steps': 26569, 'loss/train': 1.4580461978912354} 08/30/2021 17:56:09 - INFO - __main__ - Step 26571: {'lr': 0.0004667623876137965, 'samples': 5101632, 'steps': 26570, 'loss/train': 1.9228307008743286} 08/30/2021 17:56:09 - INFO - __main__ - Step 26572: {'lr': 0.00046675974362862815, 'samples': 5101824, 'steps': 26571, 'loss/train': 1.4032305479049683} 08/30/2021 17:56:10 - INFO - __main__ - Step 26573: {'lr': 0.00046675709954579125, 'samples': 5102016, 'steps': 26572, 'loss/train': 1.2667769193649292} 08/30/2021 17:56:10 - INFO - __main__ - Step 26574: {'lr': 0.0004667544553652869, 'samples': 5102208, 'steps': 26573, 'loss/train': 1.661678671836853} 08/30/2021 17:56:10 - INFO - __main__ - Step 26575: {'lr': 0.0004667518110871164, 'samples': 5102400, 'steps': 26574, 'loss/train': 0.1847216784954071} 08/30/2021 17:56:12 - INFO - __main__ - Step 26576: {'lr': 0.0004667491667112809, 'samples': 5102592, 'steps': 26575, 'loss/train': 0.9313610196113586} 08/30/2021 17:56:12 - INFO - __main__ - Step 26577: {'lr': 0.0004667465222377815, 'samples': 5102784, 'steps': 26576, 'loss/train': 1.1827235221862793} 08/30/2021 17:56:13 - INFO - __main__ - Step 26578: {'lr': 0.0004667438776666195, 'samples': 5102976, 'steps': 26577, 'loss/train': 1.0463329553604126} 08/30/2021 17:56:13 - INFO - __main__ - Step 26579: {'lr': 0.00046674123299779603, 'samples': 5103168, 'steps': 26578, 'loss/train': 1.9854336977005005} 08/30/2021 17:56:13 - INFO - __main__ - Step 26580: {'lr': 0.0004667385882313123, 'samples': 5103360, 'steps': 26579, 'loss/train': 0.7418782711029053} 08/30/2021 17:56:15 - INFO - __main__ - Step 26581: {'lr': 0.0004667359433671695, 'samples': 5103552, 'steps': 26580, 'loss/train': 1.5804579257965088} 08/30/2021 17:56:15 - INFO - __main__ - Step 26582: {'lr': 0.0004667332984053689, 'samples': 5103744, 'steps': 26581, 'loss/train': 1.3505744934082031} 08/30/2021 17:56:16 - INFO - __main__ - Step 26583: {'lr': 0.00046673065334591155, 'samples': 5103936, 'steps': 26582, 'loss/train': 1.6267030239105225} 08/30/2021 17:56:16 - INFO - __main__ - Step 26584: {'lr': 0.00046672800818879873, 'samples': 5104128, 'steps': 26583, 'loss/train': 1.9608153104782104} 08/30/2021 17:56:16 - INFO - __main__ - Step 26585: {'lr': 0.0004667253629340316, 'samples': 5104320, 'steps': 26584, 'loss/train': 1.3606011867523193} 08/30/2021 17:56:17 - INFO - __main__ - Step 26586: {'lr': 0.0004667227175816114, 'samples': 5104512, 'steps': 26585, 'loss/train': 1.891992449760437} 08/30/2021 17:56:18 - INFO - __main__ - Step 26587: {'lr': 0.0004667200721315393, 'samples': 5104704, 'steps': 26586, 'loss/train': 1.6568644046783447} 08/30/2021 17:56:19 - INFO - __main__ - Step 26588: {'lr': 0.00046671742658381646, 'samples': 5104896, 'steps': 26587, 'loss/train': 1.5922542810440063} 08/30/2021 17:56:19 - INFO - __main__ - Step 26589: {'lr': 0.000466714780938444, 'samples': 5105088, 'steps': 26588, 'loss/train': 0.1373966485261917} 08/30/2021 17:56:20 - INFO - __main__ - Step 26590: {'lr': 0.0004667121351954233, 'samples': 5105280, 'steps': 26589, 'loss/train': 1.6285159587860107} 08/30/2021 17:56:20 - INFO - __main__ - Step 26591: {'lr': 0.00046670948935475544, 'samples': 5105472, 'steps': 26590, 'loss/train': 1.7560625076293945} 08/30/2021 17:56:21 - INFO - __main__ - Step 26592: {'lr': 0.00046670684341644167, 'samples': 5105664, 'steps': 26591, 'loss/train': 1.802418828010559} 08/30/2021 17:56:22 - INFO - __main__ - Step 26593: {'lr': 0.0004667041973804831, 'samples': 5105856, 'steps': 26592, 'loss/train': 1.8346643447875977} 08/30/2021 17:56:22 - INFO - __main__ - Step 26594: {'lr': 0.00046670155124688096, 'samples': 5106048, 'steps': 26593, 'loss/train': 2.776232957839966} 08/30/2021 17:56:23 - INFO - __main__ - Step 26595: {'lr': 0.00046669890501563636, 'samples': 5106240, 'steps': 26594, 'loss/train': 0.9451594948768616} 08/30/2021 17:56:23 - INFO - __main__ - Step 26596: {'lr': 0.0004666962586867507, 'samples': 5106432, 'steps': 26595, 'loss/train': 1.706702709197998} 08/30/2021 17:56:25 - INFO - __main__ - Step 26597: {'lr': 0.000466693612260225, 'samples': 5106624, 'steps': 26596, 'loss/train': 2.128802537918091} 08/30/2021 17:56:26 - INFO - __main__ - Step 26598: {'lr': 0.00046669096573606053, 'samples': 5106816, 'steps': 26597, 'loss/train': 1.3077977895736694} 08/30/2021 17:56:26 - INFO - __main__ - Step 26599: {'lr': 0.00046668831911425844, 'samples': 5107008, 'steps': 26598, 'loss/train': 0.24058596789836884} 08/30/2021 17:56:26 - INFO - __main__ - Step 26600: {'lr': 0.00046668567239481994, 'samples': 5107200, 'steps': 26599, 'loss/train': 1.5694202184677124} 08/30/2021 17:56:27 - INFO - __main__ - Step 26601: {'lr': 0.0004666830255777462, 'samples': 5107392, 'steps': 26600, 'loss/train': 1.5089735984802246} 08/30/2021 17:56:28 - INFO - __main__ - Step 26602: {'lr': 0.00046668037866303845, 'samples': 5107584, 'steps': 26601, 'loss/train': 1.3394880294799805} 08/30/2021 17:56:29 - INFO - __main__ - Step 26603: {'lr': 0.0004666777316506979, 'samples': 5107776, 'steps': 26602, 'loss/train': 1.7052606344223022} 08/30/2021 17:56:29 - INFO - __main__ - Step 26604: {'lr': 0.00046667508454072566, 'samples': 5107968, 'steps': 26603, 'loss/train': 1.8480103015899658} 08/30/2021 17:56:29 - INFO - __main__ - Step 26605: {'lr': 0.00046667243733312296, 'samples': 5108160, 'steps': 26604, 'loss/train': 1.675742745399475} 08/30/2021 17:56:30 - INFO - __main__ - Step 26606: {'lr': 0.000466669790027891, 'samples': 5108352, 'steps': 26605, 'loss/train': 1.3788155317306519} 08/30/2021 17:56:31 - INFO - __main__ - Step 26607: {'lr': 0.00046666714262503107, 'samples': 5108544, 'steps': 26606, 'loss/train': 1.5237983465194702} 08/30/2021 17:56:32 - INFO - __main__ - Step 26608: {'lr': 0.00046666449512454416, 'samples': 5108736, 'steps': 26607, 'loss/train': 1.323991060256958} 08/30/2021 17:56:32 - INFO - __main__ - Step 26609: {'lr': 0.0004666618475264316, 'samples': 5108928, 'steps': 26608, 'loss/train': 1.3702112436294556} 08/30/2021 17:56:32 - INFO - __main__ - Step 26610: {'lr': 0.0004666591998306946, 'samples': 5109120, 'steps': 26609, 'loss/train': 1.3449513912200928} 08/30/2021 17:56:33 - INFO - __main__ - Step 26611: {'lr': 0.0004666565520373343, 'samples': 5109312, 'steps': 26610, 'loss/train': 1.2981202602386475} 08/30/2021 17:56:33 - INFO - __main__ - Step 26612: {'lr': 0.00046665390414635184, 'samples': 5109504, 'steps': 26611, 'loss/train': 1.5928764343261719} 08/30/2021 17:56:34 - INFO - __main__ - Step 26613: {'lr': 0.0004666512561577485, 'samples': 5109696, 'steps': 26612, 'loss/train': 1.3780946731567383} 08/30/2021 17:56:35 - INFO - __main__ - Step 26614: {'lr': 0.0004666486080715255, 'samples': 5109888, 'steps': 26613, 'loss/train': 1.5655570030212402} 08/30/2021 17:56:35 - INFO - __main__ - Step 26615: {'lr': 0.0004666459598876839, 'samples': 5110080, 'steps': 26614, 'loss/train': 1.0367977619171143} 08/30/2021 17:56:36 - INFO - __main__ - Step 26616: {'lr': 0.000466643311606225, 'samples': 5110272, 'steps': 26615, 'loss/train': 1.6685724258422852} 08/30/2021 17:56:36 - INFO - __main__ - Step 26617: {'lr': 0.00046664066322715006, 'samples': 5110464, 'steps': 26616, 'loss/train': 1.5906468629837036} 08/30/2021 17:56:38 - INFO - __main__ - Step 26618: {'lr': 0.00046663801475046004, 'samples': 5110656, 'steps': 26617, 'loss/train': 1.2674009799957275} 08/30/2021 17:56:38 - INFO - __main__ - Step 26619: {'lr': 0.0004666353661761563, 'samples': 5110848, 'steps': 26618, 'loss/train': 1.5779671669006348} 08/30/2021 17:56:39 - INFO - __main__ - Step 26620: {'lr': 0.0004666327175042401, 'samples': 5111040, 'steps': 26619, 'loss/train': 0.14954562485218048} 08/30/2021 17:56:39 - INFO - __main__ - Step 26621: {'lr': 0.00046663006873471247, 'samples': 5111232, 'steps': 26620, 'loss/train': 1.7937462329864502} 08/30/2021 17:56:39 - INFO - __main__ - Step 26622: {'lr': 0.00046662741986757463, 'samples': 5111424, 'steps': 26621, 'loss/train': 1.360806941986084} 08/30/2021 17:56:41 - INFO - __main__ - Step 26623: {'lr': 0.0004666247709028279, 'samples': 5111616, 'steps': 26622, 'loss/train': 1.251752257347107} 08/30/2021 17:56:41 - INFO - __main__ - Step 26624: {'lr': 0.00046662212184047334, 'samples': 5111808, 'steps': 26623, 'loss/train': 1.4638067483901978} 08/30/2021 17:56:42 - INFO - __main__ - Step 26625: {'lr': 0.0004666194726805122, 'samples': 5112000, 'steps': 26624, 'loss/train': 0.9021357297897339} 08/30/2021 17:56:42 - INFO - __main__ - Step 26626: {'lr': 0.0004666168234229457, 'samples': 5112192, 'steps': 26625, 'loss/train': 2.011953592300415} 08/30/2021 17:56:42 - INFO - __main__ - Step 26627: {'lr': 0.000466614174067775, 'samples': 5112384, 'steps': 26626, 'loss/train': 0.7863146066665649} 08/30/2021 17:56:44 - INFO - __main__ - Step 26628: {'lr': 0.00046661152461500126, 'samples': 5112576, 'steps': 26627, 'loss/train': 2.0708909034729004} 08/30/2021 17:56:45 - INFO - __main__ - Step 26629: {'lr': 0.0004666088750646257, 'samples': 5112768, 'steps': 26628, 'loss/train': 1.9464064836502075} 08/30/2021 17:56:45 - INFO - __main__ - Step 26630: {'lr': 0.0004666062254166496, 'samples': 5112960, 'steps': 26629, 'loss/train': 0.6118735671043396} 08/30/2021 17:56:45 - INFO - __main__ - Step 26631: {'lr': 0.000466603575671074, 'samples': 5113152, 'steps': 26630, 'loss/train': 1.2635018825531006} 08/30/2021 17:56:46 - INFO - __main__ - Step 26632: {'lr': 0.00046660092582790025, 'samples': 5113344, 'steps': 26631, 'loss/train': 1.6213116645812988} 08/30/2021 17:56:46 - INFO - __main__ - Step 26633: {'lr': 0.0004665982758871294, 'samples': 5113536, 'steps': 26632, 'loss/train': 1.2657393217086792} 08/30/2021 17:56:48 - INFO - __main__ - Step 26634: {'lr': 0.0004665956258487627, 'samples': 5113728, 'steps': 26633, 'loss/train': 1.2259384393692017} 08/30/2021 17:56:48 - INFO - __main__ - Step 26635: {'lr': 0.0004665929757128014, 'samples': 5113920, 'steps': 26634, 'loss/train': 1.1367225646972656} 08/30/2021 17:56:48 - INFO - __main__ - Step 26636: {'lr': 0.0004665903254792466, 'samples': 5114112, 'steps': 26635, 'loss/train': 1.2556160688400269} 08/30/2021 17:56:49 - INFO - __main__ - Step 26637: {'lr': 0.0004665876751480996, 'samples': 5114304, 'steps': 26636, 'loss/train': 1.492944359779358} 08/30/2021 17:56:49 - INFO - __main__ - Step 26638: {'lr': 0.0004665850247193615, 'samples': 5114496, 'steps': 26637, 'loss/train': 1.5703942775726318} 08/30/2021 17:56:51 - INFO - __main__ - Step 26639: {'lr': 0.0004665823741930335, 'samples': 5114688, 'steps': 26638, 'loss/train': 1.1665278673171997} 08/30/2021 17:56:51 - INFO - __main__ - Step 26640: {'lr': 0.00046657972356911696, 'samples': 5114880, 'steps': 26639, 'loss/train': 0.4462893307209015} 08/30/2021 17:56:51 - INFO - __main__ - Step 26641: {'lr': 0.00046657707284761274, 'samples': 5115072, 'steps': 26640, 'loss/train': 1.648575782775879} 08/30/2021 17:56:52 - INFO - __main__ - Step 26642: {'lr': 0.0004665744220285224, 'samples': 5115264, 'steps': 26641, 'loss/train': 1.681076169013977} 08/30/2021 17:56:52 - INFO - __main__ - Step 26643: {'lr': 0.0004665717711118469, 'samples': 5115456, 'steps': 26642, 'loss/train': 2.1270596981048584} 08/30/2021 17:56:54 - INFO - __main__ - Step 26644: {'lr': 0.00046656912009758743, 'samples': 5115648, 'steps': 26643, 'loss/train': 1.60477614402771} 08/30/2021 17:56:54 - INFO - __main__ - Step 26645: {'lr': 0.0004665664689857454, 'samples': 5115840, 'steps': 26644, 'loss/train': 1.2852739095687866} 08/30/2021 17:56:55 - INFO - __main__ - Step 26646: {'lr': 0.00046656381777632173, 'samples': 5116032, 'steps': 26645, 'loss/train': 1.433002233505249} 08/30/2021 17:56:55 - INFO - __main__ - Step 26647: {'lr': 0.0004665611664693178, 'samples': 5116224, 'steps': 26646, 'loss/train': 0.8877944350242615} 08/30/2021 17:56:55 - INFO - __main__ - Step 26648: {'lr': 0.0004665585150647348, 'samples': 5116416, 'steps': 26647, 'loss/train': 0.9069812893867493} 08/30/2021 17:56:57 - INFO - __main__ - Step 26649: {'lr': 0.0004665558635625738, 'samples': 5116608, 'steps': 26648, 'loss/train': 1.624466896057129} 08/30/2021 17:56:57 - INFO - __main__ - Step 26650: {'lr': 0.00046655321196283604, 'samples': 5116800, 'steps': 26649, 'loss/train': 1.2025951147079468} 08/30/2021 17:56:58 - INFO - __main__ - Step 26651: {'lr': 0.00046655056026552287, 'samples': 5116992, 'steps': 26650, 'loss/train': 1.448067307472229} 08/30/2021 17:56:58 - INFO - __main__ - Step 26652: {'lr': 0.0004665479084706353, 'samples': 5117184, 'steps': 26651, 'loss/train': 1.4956330060958862} 08/30/2021 17:56:58 - INFO - __main__ - Step 26653: {'lr': 0.00046654525657817457, 'samples': 5117376, 'steps': 26652, 'loss/train': 1.2684885263442993} 08/30/2021 17:57:00 - INFO - __main__ - Step 26654: {'lr': 0.0004665426045881419, 'samples': 5117568, 'steps': 26653, 'loss/train': 1.571487307548523} 08/30/2021 17:57:01 - INFO - __main__ - Step 26655: {'lr': 0.00046653995250053843, 'samples': 5117760, 'steps': 26654, 'loss/train': 1.648902416229248} 08/30/2021 17:57:01 - INFO - __main__ - Step 26656: {'lr': 0.00046653730031536545, 'samples': 5117952, 'steps': 26655, 'loss/train': 0.6627792119979858} 08/30/2021 17:57:02 - INFO - __main__ - Step 26657: {'lr': 0.0004665346480326241, 'samples': 5118144, 'steps': 26656, 'loss/train': 1.4905503988265991} 08/30/2021 17:57:02 - INFO - __main__ - Step 26658: {'lr': 0.00046653199565231554, 'samples': 5118336, 'steps': 26657, 'loss/train': 1.935055136680603} 08/30/2021 17:57:03 - INFO - __main__ - Step 26659: {'lr': 0.00046652934317444104, 'samples': 5118528, 'steps': 26658, 'loss/train': 1.2012574672698975} 08/30/2021 17:57:04 - INFO - __main__ - Step 26660: {'lr': 0.00046652669059900174, 'samples': 5118720, 'steps': 26659, 'loss/train': 1.693825364112854} 08/30/2021 17:57:04 - INFO - __main__ - Step 26661: {'lr': 0.0004665240379259989, 'samples': 5118912, 'steps': 26660, 'loss/train': 2.019569158554077} 08/30/2021 17:57:05 - INFO - __main__ - Step 26662: {'lr': 0.00046652138515543366, 'samples': 5119104, 'steps': 26661, 'loss/train': 1.3235939741134644} 08/30/2021 17:57:05 - INFO - __main__ - Step 26663: {'lr': 0.00046651873228730715, 'samples': 5119296, 'steps': 26662, 'loss/train': 0.3999435007572174} 08/30/2021 17:57:05 - INFO - __main__ - Step 26664: {'lr': 0.0004665160793216207, 'samples': 5119488, 'steps': 26663, 'loss/train': 1.3439934253692627} 08/30/2021 17:57:07 - INFO - __main__ - Step 26665: {'lr': 0.00046651342625837544, 'samples': 5119680, 'steps': 26664, 'loss/train': 1.6201248168945312} 08/30/2021 17:57:07 - INFO - __main__ - Step 26666: {'lr': 0.00046651077309757256, 'samples': 5119872, 'steps': 26665, 'loss/train': 1.9719942808151245} 08/30/2021 17:57:08 - INFO - __main__ - Step 26667: {'lr': 0.0004665081198392133, 'samples': 5120064, 'steps': 26666, 'loss/train': 1.5221664905548096} 08/30/2021 17:57:08 - INFO - __main__ - Step 26668: {'lr': 0.0004665054664832988, 'samples': 5120256, 'steps': 26667, 'loss/train': 1.5162558555603027} 08/30/2021 17:57:08 - INFO - __main__ - Step 26669: {'lr': 0.00046650281302983024, 'samples': 5120448, 'steps': 26668, 'loss/train': 1.4170496463775635} 08/30/2021 17:57:10 - INFO - __main__ - Step 26670: {'lr': 0.00046650015947880886, 'samples': 5120640, 'steps': 26669, 'loss/train': 1.8704843521118164} 08/30/2021 17:57:10 - INFO - __main__ - Step 26671: {'lr': 0.00046649750583023595, 'samples': 5120832, 'steps': 26670, 'loss/train': 1.5668845176696777} 08/30/2021 17:57:11 - INFO - __main__ - Step 26672: {'lr': 0.00046649485208411244, 'samples': 5121024, 'steps': 26671, 'loss/train': 1.3336966037750244} 08/30/2021 17:57:11 - INFO - __main__ - Step 26673: {'lr': 0.00046649219824043984, 'samples': 5121216, 'steps': 26672, 'loss/train': 1.2383750677108765} 08/30/2021 17:57:11 - INFO - __main__ - Step 26674: {'lr': 0.00046648954429921914, 'samples': 5121408, 'steps': 26673, 'loss/train': 1.6487102508544922} 08/30/2021 17:57:13 - INFO - __main__ - Step 26675: {'lr': 0.00046648689026045157, 'samples': 5121600, 'steps': 26674, 'loss/train': 1.3962541818618774} 08/30/2021 17:57:13 - INFO - __main__ - Step 26676: {'lr': 0.0004664842361241384, 'samples': 5121792, 'steps': 26675, 'loss/train': 1.617918848991394} 08/30/2021 17:57:14 - INFO - __main__ - Step 26677: {'lr': 0.00046648158189028073, 'samples': 5121984, 'steps': 26676, 'loss/train': 1.6024278402328491} 08/30/2021 17:57:14 - INFO - __main__ - Step 26678: {'lr': 0.0004664789275588798, 'samples': 5122176, 'steps': 26677, 'loss/train': 1.7752492427825928} 08/30/2021 17:57:14 - INFO - __main__ - Step 26679: {'lr': 0.0004664762731299368, 'samples': 5122368, 'steps': 26678, 'loss/train': 0.10728741437196732} 08/30/2021 17:57:16 - INFO - __main__ - Step 26680: {'lr': 0.00046647361860345293, 'samples': 5122560, 'steps': 26679, 'loss/train': 1.3969312906265259} 08/30/2021 17:57:16 - INFO - __main__ - Step 26681: {'lr': 0.00046647096397942945, 'samples': 5122752, 'steps': 26680, 'loss/train': 1.6737064123153687} 08/30/2021 17:57:17 - INFO - __main__ - Step 26682: {'lr': 0.0004664683092578674, 'samples': 5122944, 'steps': 26681, 'loss/train': 1.1327248811721802} 08/30/2021 17:57:17 - INFO - __main__ - Step 26683: {'lr': 0.00046646565443876815, 'samples': 5123136, 'steps': 26682, 'loss/train': 1.356799602508545} 08/30/2021 17:57:17 - INFO - __main__ - Step 26684: {'lr': 0.00046646299952213277, 'samples': 5123328, 'steps': 26683, 'loss/train': 0.6211066842079163} 08/30/2021 17:57:19 - INFO - __main__ - Step 26685: {'lr': 0.00046646034450796255, 'samples': 5123520, 'steps': 26684, 'loss/train': 2.2446956634521484} 08/30/2021 17:57:19 - INFO - __main__ - Step 26686: {'lr': 0.0004664576893962586, 'samples': 5123712, 'steps': 26685, 'loss/train': 1.8335237503051758} 08/30/2021 17:57:20 - INFO - __main__ - Step 26687: {'lr': 0.0004664550341870222, 'samples': 5123904, 'steps': 26686, 'loss/train': 1.1680623292922974} 08/30/2021 17:57:20 - INFO - __main__ - Step 26688: {'lr': 0.00046645237888025444, 'samples': 5124096, 'steps': 26687, 'loss/train': 2.169955253601074} 08/30/2021 17:57:20 - INFO - __main__ - Step 26689: {'lr': 0.0004664497234759566, 'samples': 5124288, 'steps': 26688, 'loss/train': 0.5427646040916443} 08/30/2021 17:57:21 - INFO - __main__ - Step 26690: {'lr': 0.00046644706797412984, 'samples': 5124480, 'steps': 26689, 'loss/train': 1.4893057346343994} 08/30/2021 17:57:22 - INFO - __main__ - Step 26691: {'lr': 0.00046644441237477544, 'samples': 5124672, 'steps': 26690, 'loss/train': 1.658414602279663} 08/30/2021 17:57:23 - INFO - __main__ - Step 26692: {'lr': 0.00046644175667789444, 'samples': 5124864, 'steps': 26691, 'loss/train': 1.52473783493042} 08/30/2021 17:57:23 - INFO - __main__ - Step 26693: {'lr': 0.00046643910088348817, 'samples': 5125056, 'steps': 26692, 'loss/train': 0.9235119819641113} 08/30/2021 17:57:23 - INFO - __main__ - Step 26694: {'lr': 0.0004664364449915578, 'samples': 5125248, 'steps': 26693, 'loss/train': 1.717477560043335} 08/30/2021 17:57:24 - INFO - __main__ - Step 26695: {'lr': 0.0004664337890021044, 'samples': 5125440, 'steps': 26694, 'loss/train': 1.2940359115600586} 08/30/2021 17:57:25 - INFO - __main__ - Step 26696: {'lr': 0.0004664311329151294, 'samples': 5125632, 'steps': 26695, 'loss/train': 1.9891644716262817} 08/30/2021 17:57:26 - INFO - __main__ - Step 26697: {'lr': 0.0004664284767306338, 'samples': 5125824, 'steps': 26696, 'loss/train': 1.8456469774246216} 08/30/2021 17:57:26 - INFO - __main__ - Step 26698: {'lr': 0.0004664258204486189, 'samples': 5126016, 'steps': 26697, 'loss/train': 1.663969874382019} 08/30/2021 17:57:27 - INFO - __main__ - Step 26699: {'lr': 0.0004664231640690859, 'samples': 5126208, 'steps': 26698, 'loss/train': 1.5915356874465942} 08/30/2021 17:57:27 - INFO - __main__ - Step 26700: {'lr': 0.0004664205075920359, 'samples': 5126400, 'steps': 26699, 'loss/train': 1.0144003629684448} 08/30/2021 17:57:29 - INFO - __main__ - Step 26701: {'lr': 0.0004664178510174702, 'samples': 5126592, 'steps': 26700, 'loss/train': 1.863483190536499} 08/30/2021 17:57:30 - INFO - __main__ - Step 26702: {'lr': 0.0004664151943453899, 'samples': 5126784, 'steps': 26701, 'loss/train': 1.5355284214019775} 08/30/2021 17:57:30 - INFO - __main__ - Step 26703: {'lr': 0.0004664125375757963, 'samples': 5126976, 'steps': 26702, 'loss/train': 1.4345295429229736} 08/30/2021 17:57:30 - INFO - __main__ - Step 26704: {'lr': 0.00046640988070869053, 'samples': 5127168, 'steps': 26703, 'loss/train': 1.6513216495513916} 08/30/2021 17:57:31 - INFO - __main__ - Step 26705: {'lr': 0.00046640722374407384, 'samples': 5127360, 'steps': 26704, 'loss/train': 1.3768072128295898} 08/30/2021 17:57:31 - INFO - __main__ - Step 26706: {'lr': 0.00046640456668194737, 'samples': 5127552, 'steps': 26705, 'loss/train': 1.8468369245529175} 08/30/2021 17:57:32 - INFO - __main__ - Step 26707: {'lr': 0.0004664019095223123, 'samples': 5127744, 'steps': 26706, 'loss/train': 2.6544859409332275} 08/30/2021 17:57:33 - INFO - __main__ - Step 26708: {'lr': 0.00046639925226517, 'samples': 5127936, 'steps': 26707, 'loss/train': 1.6677361726760864} 08/30/2021 17:57:33 - INFO - __main__ - Step 26709: {'lr': 0.0004663965949105214, 'samples': 5128128, 'steps': 26708, 'loss/train': 1.158858060836792} 08/30/2021 17:57:34 - INFO - __main__ - Step 26710: {'lr': 0.0004663939374583679, 'samples': 5128320, 'steps': 26709, 'loss/train': 1.6500035524368286} 08/30/2021 17:57:34 - INFO - __main__ - Step 26711: {'lr': 0.00046639127990871055, 'samples': 5128512, 'steps': 26710, 'loss/train': 1.7814421653747559} 08/30/2021 17:57:36 - INFO - __main__ - Step 26712: {'lr': 0.00046638862226155075, 'samples': 5128704, 'steps': 26711, 'loss/train': 1.1269235610961914} 08/30/2021 17:57:36 - INFO - __main__ - Step 26713: {'lr': 0.0004663859645168895, 'samples': 5128896, 'steps': 26712, 'loss/train': 1.0910543203353882} 08/30/2021 17:57:36 - INFO - __main__ - Step 26714: {'lr': 0.00046638330667472805, 'samples': 5129088, 'steps': 26713, 'loss/train': 1.7232025861740112} 08/30/2021 17:57:37 - INFO - __main__ - Step 26715: {'lr': 0.0004663806487350677, 'samples': 5129280, 'steps': 26714, 'loss/train': 1.5871376991271973} 08/30/2021 17:57:37 - INFO - __main__ - Step 26716: {'lr': 0.00046637799069790953, 'samples': 5129472, 'steps': 26715, 'loss/train': 0.08858071267604828} 08/30/2021 17:57:39 - INFO - __main__ - Step 26717: {'lr': 0.00046637533256325476, 'samples': 5129664, 'steps': 26716, 'loss/train': 1.5392704010009766} 08/30/2021 17:57:39 - INFO - __main__ - Step 26718: {'lr': 0.0004663726743311046, 'samples': 5129856, 'steps': 26717, 'loss/train': 1.4603545665740967} 08/30/2021 17:57:40 - INFO - __main__ - Step 26719: {'lr': 0.00046637001600146027, 'samples': 5130048, 'steps': 26718, 'loss/train': 0.09331375360488892} 08/30/2021 17:57:40 - INFO - __main__ - Step 26720: {'lr': 0.000466367357574323, 'samples': 5130240, 'steps': 26719, 'loss/train': 1.9333102703094482} 08/30/2021 17:57:41 - INFO - __main__ - Step 26721: {'lr': 0.00046636469904969387, 'samples': 5130432, 'steps': 26720, 'loss/train': 1.365154504776001} 08/30/2021 17:57:41 - INFO - __main__ - Step 26722: {'lr': 0.0004663620404275741, 'samples': 5130624, 'steps': 26721, 'loss/train': 1.0078293085098267} 08/30/2021 17:57:42 - INFO - __main__ - Step 26723: {'lr': 0.00046635938170796505, 'samples': 5130816, 'steps': 26722, 'loss/train': 1.0311357975006104} 08/30/2021 17:57:43 - INFO - __main__ - Step 26724: {'lr': 0.00046635672289086774, 'samples': 5131008, 'steps': 26723, 'loss/train': 1.319662094116211} 08/30/2021 17:57:43 - INFO - __main__ - Step 26725: {'lr': 0.00046635406397628346, 'samples': 5131200, 'steps': 26724, 'loss/train': 1.5365781784057617} 08/30/2021 17:57:44 - INFO - __main__ - Step 26726: {'lr': 0.00046635140496421336, 'samples': 5131392, 'steps': 26725, 'loss/train': 1.5976406335830688} 08/30/2021 17:57:44 - INFO - __main__ - Step 26727: {'lr': 0.0004663487458546586, 'samples': 5131584, 'steps': 26726, 'loss/train': 1.6156132221221924} 08/30/2021 17:57:45 - INFO - __main__ - Step 26728: {'lr': 0.0004663460866476205, 'samples': 5131776, 'steps': 26727, 'loss/train': 1.5820831060409546} 08/30/2021 17:57:46 - INFO - __main__ - Step 26729: {'lr': 0.00046634342734310023, 'samples': 5131968, 'steps': 26728, 'loss/train': 1.461832880973816} 08/30/2021 17:57:46 - INFO - __main__ - Step 26730: {'lr': 0.0004663407679410988, 'samples': 5132160, 'steps': 26729, 'loss/train': 0.21380048990249634} 08/30/2021 17:57:47 - INFO - __main__ - Step 26731: {'lr': 0.0004663381084416177, 'samples': 5132352, 'steps': 26730, 'loss/train': 1.8571300506591797} 08/30/2021 17:57:47 - INFO - __main__ - Step 26732: {'lr': 0.00046633544884465796, 'samples': 5132544, 'steps': 26731, 'loss/train': 1.300208330154419} 08/30/2021 17:57:48 - INFO - __main__ - Step 26733: {'lr': 0.0004663327891502208, 'samples': 5132736, 'steps': 26732, 'loss/train': 0.3474135100841522} 08/30/2021 17:57:49 - INFO - __main__ - Step 26734: {'lr': 0.0004663301293583073, 'samples': 5132928, 'steps': 26733, 'loss/train': 1.2446075677871704} 08/30/2021 17:57:49 - INFO - __main__ - Step 26735: {'lr': 0.000466327469468919, 'samples': 5133120, 'steps': 26734, 'loss/train': 1.6891194581985474} 08/30/2021 17:57:50 - INFO - __main__ - Step 26736: {'lr': 0.0004663248094820567, 'samples': 5133312, 'steps': 26735, 'loss/train': 1.2903902530670166} 08/30/2021 17:57:50 - INFO - __main__ - Step 26737: {'lr': 0.00046632214939772187, 'samples': 5133504, 'steps': 26736, 'loss/train': 1.6359522342681885} 08/30/2021 17:57:52 - INFO - __main__ - Step 26738: {'lr': 0.0004663194892159156, 'samples': 5133696, 'steps': 26737, 'loss/train': 1.2313135862350464} 08/30/2021 17:57:52 - INFO - __main__ - Step 26739: {'lr': 0.0004663168289366391, 'samples': 5133888, 'steps': 26738, 'loss/train': 1.1805410385131836} 08/30/2021 17:57:52 - INFO - __main__ - Step 26740: {'lr': 0.0004663141685598936, 'samples': 5134080, 'steps': 26739, 'loss/train': 4.346454620361328} 08/30/2021 17:57:53 - INFO - __main__ - Step 26741: {'lr': 0.00046631150808568026, 'samples': 5134272, 'steps': 26740, 'loss/train': 1.359296441078186} 08/30/2021 17:57:53 - INFO - __main__ - Step 26742: {'lr': 0.00046630884751400024, 'samples': 5134464, 'steps': 26741, 'loss/train': 1.4907121658325195} 08/30/2021 17:57:53 - INFO - __main__ - Step 26743: {'lr': 0.0004663061868448548, 'samples': 5134656, 'steps': 26742, 'loss/train': 1.8572890758514404} 08/30/2021 17:57:55 - INFO - __main__ - Step 26744: {'lr': 0.0004663035260782452, 'samples': 5134848, 'steps': 26743, 'loss/train': 1.7632564306259155} 08/30/2021 17:57:55 - INFO - __main__ - Step 26745: {'lr': 0.0004663008652141726, 'samples': 5135040, 'steps': 26744, 'loss/train': 1.5466748476028442} 08/30/2021 17:57:56 - INFO - __main__ - Step 26746: {'lr': 0.00046629820425263805, 'samples': 5135232, 'steps': 26745, 'loss/train': 1.1536327600479126} 08/30/2021 17:57:56 - INFO - __main__ - Step 26747: {'lr': 0.00046629554319364293, 'samples': 5135424, 'steps': 26746, 'loss/train': 1.0963774919509888} 08/30/2021 17:57:56 - INFO - __main__ - Step 26748: {'lr': 0.00046629288203718834, 'samples': 5135616, 'steps': 26747, 'loss/train': 1.7901570796966553} 08/30/2021 17:57:58 - INFO - __main__ - Step 26749: {'lr': 0.00046629022078327557, 'samples': 5135808, 'steps': 26748, 'loss/train': 1.4945642948150635} 08/30/2021 17:57:58 - INFO - __main__ - Step 26750: {'lr': 0.0004662875594319057, 'samples': 5136000, 'steps': 26749, 'loss/train': 1.3612560033798218} 08/30/2021 17:57:59 - INFO - __main__ - Step 26751: {'lr': 0.00046628489798308006, 'samples': 5136192, 'steps': 26750, 'loss/train': 1.6134798526763916} 08/30/2021 17:57:59 - INFO - __main__ - Step 26752: {'lr': 0.0004662822364367997, 'samples': 5136384, 'steps': 26751, 'loss/train': 1.331142783164978} 08/30/2021 17:57:59 - INFO - __main__ - Step 26753: {'lr': 0.000466279574793066, 'samples': 5136576, 'steps': 26752, 'loss/train': 1.8044636249542236} 08/30/2021 17:58:01 - INFO - __main__ - Step 26754: {'lr': 0.00046627691305188004, 'samples': 5136768, 'steps': 26753, 'loss/train': 0.5285789966583252} 08/30/2021 17:58:02 - INFO - __main__ - Step 26755: {'lr': 0.00046627425121324294, 'samples': 5136960, 'steps': 26754, 'loss/train': 2.230715751647949} 08/30/2021 17:58:02 - INFO - __main__ - Step 26756: {'lr': 0.0004662715892771561, 'samples': 5137152, 'steps': 26755, 'loss/train': 1.5442594289779663} 08/30/2021 17:58:03 - INFO - __main__ - Step 26757: {'lr': 0.0004662689272436206, 'samples': 5137344, 'steps': 26756, 'loss/train': 1.7846076488494873} 08/30/2021 17:58:03 - INFO - __main__ - Step 26758: {'lr': 0.00046626626511263764, 'samples': 5137536, 'steps': 26757, 'loss/train': 0.08230098336935043} 08/30/2021 17:58:03 - INFO - __main__ - Step 26759: {'lr': 0.00046626360288420845, 'samples': 5137728, 'steps': 26758, 'loss/train': 1.536605715751648} 08/30/2021 17:58:05 - INFO - __main__ - Step 26760: {'lr': 0.00046626094055833426, 'samples': 5137920, 'steps': 26759, 'loss/train': 1.6113698482513428} 08/30/2021 17:58:06 - INFO - __main__ - Step 26761: {'lr': 0.0004662582781350161, 'samples': 5138112, 'steps': 26760, 'loss/train': 1.4732036590576172} 08/30/2021 17:58:06 - INFO - __main__ - Step 26762: {'lr': 0.00046625561561425543, 'samples': 5138304, 'steps': 26761, 'loss/train': 1.2604283094406128} 08/30/2021 17:58:06 - INFO - __main__ - Step 26763: {'lr': 0.00046625295299605323, 'samples': 5138496, 'steps': 26762, 'loss/train': 1.4922982454299927} 08/30/2021 17:58:07 - INFO - __main__ - Step 26764: {'lr': 0.0004662502902804109, 'samples': 5138688, 'steps': 26763, 'loss/train': 1.4694780111312866} 08/30/2021 17:58:07 - INFO - __main__ - Step 26765: {'lr': 0.0004662476274673294, 'samples': 5138880, 'steps': 26764, 'loss/train': 1.683996319770813} 08/30/2021 17:58:09 - INFO - __main__ - Step 26766: {'lr': 0.00046624496455681006, 'samples': 5139072, 'steps': 26765, 'loss/train': 1.5728793144226074} 08/30/2021 17:58:09 - INFO - __main__ - Step 26767: {'lr': 0.00046624230154885415, 'samples': 5139264, 'steps': 26766, 'loss/train': 1.5897480249404907} 08/30/2021 17:58:10 - INFO - __main__ - Step 26768: {'lr': 0.0004662396384434627, 'samples': 5139456, 'steps': 26767, 'loss/train': 1.5656379461288452} 08/30/2021 17:58:10 - INFO - __main__ - Step 26769: {'lr': 0.00046623697524063713, 'samples': 5139648, 'steps': 26768, 'loss/train': 1.7227659225463867} 08/30/2021 17:58:10 - INFO - __main__ - Step 26770: {'lr': 0.00046623431194037847, 'samples': 5139840, 'steps': 26769, 'loss/train': 1.4630969762802124} 08/30/2021 17:58:12 - INFO - __main__ - Step 26771: {'lr': 0.000466231648542688, 'samples': 5140032, 'steps': 26770, 'loss/train': 1.9150218963623047} 08/30/2021 17:58:12 - INFO - __main__ - Step 26772: {'lr': 0.0004662289850475668, 'samples': 5140224, 'steps': 26771, 'loss/train': 1.0994112491607666} 08/30/2021 17:58:13 - INFO - __main__ - Step 26773: {'lr': 0.0004662263214550162, 'samples': 5140416, 'steps': 26772, 'loss/train': 1.8346391916275024} 08/30/2021 17:58:13 - INFO - __main__ - Step 26774: {'lr': 0.00046622365776503735, 'samples': 5140608, 'steps': 26773, 'loss/train': 1.2081940174102783} 08/30/2021 17:58:14 - INFO - __main__ - Step 26775: {'lr': 0.0004662209939776315, 'samples': 5140800, 'steps': 26774, 'loss/train': 1.7097142934799194} 08/30/2021 17:58:15 - INFO - __main__ - Step 26776: {'lr': 0.0004662183300927997, 'samples': 5140992, 'steps': 26775, 'loss/train': 1.4779356718063354} 08/30/2021 17:58:16 - INFO - __main__ - Step 26777: {'lr': 0.0004662156661105433, 'samples': 5141184, 'steps': 26776, 'loss/train': 1.3889614343643188} 08/30/2021 17:58:16 - INFO - __main__ - Step 26778: {'lr': 0.0004662130020308635, 'samples': 5141376, 'steps': 26777, 'loss/train': 1.6845752000808716} 08/30/2021 17:58:16 - INFO - __main__ - Step 26779: {'lr': 0.00046621033785376146, 'samples': 5141568, 'steps': 26778, 'loss/train': 1.0824769735336304} 08/30/2021 17:58:17 - INFO - __main__ - Step 26780: {'lr': 0.00046620767357923834, 'samples': 5141760, 'steps': 26779, 'loss/train': 1.6082614660263062} 08/30/2021 17:58:18 - INFO - __main__ - Step 26781: {'lr': 0.0004662050092072954, 'samples': 5141952, 'steps': 26780, 'loss/train': 1.775464653968811} 08/30/2021 17:58:19 - INFO - __main__ - Step 26782: {'lr': 0.0004662023447379338, 'samples': 5142144, 'steps': 26781, 'loss/train': 1.8717602491378784} 08/30/2021 17:58:19 - INFO - __main__ - Step 26783: {'lr': 0.0004661996801711548, 'samples': 5142336, 'steps': 26782, 'loss/train': 1.1960712671279907} 08/30/2021 17:58:19 - INFO - __main__ - Step 26784: {'lr': 0.0004661970155069595, 'samples': 5142528, 'steps': 26783, 'loss/train': 1.3057440519332886} 08/30/2021 17:58:20 - INFO - __main__ - Step 26785: {'lr': 0.00046619435074534923, 'samples': 5142720, 'steps': 26784, 'loss/train': 1.7113823890686035} 08/30/2021 17:58:22 - INFO - __main__ - Step 26786: {'lr': 0.0004661916858863251, 'samples': 5142912, 'steps': 26785, 'loss/train': 1.7824463844299316} 08/30/2021 17:58:22 - INFO - __main__ - Step 26787: {'lr': 0.00046618902092988824, 'samples': 5143104, 'steps': 26786, 'loss/train': 1.6778502464294434} 08/30/2021 17:58:22 - INFO - __main__ - Step 26788: {'lr': 0.00046618635587604006, 'samples': 5143296, 'steps': 26787, 'loss/train': 0.2964571714401245} 08/30/2021 17:58:23 - INFO - __main__ - Step 26789: {'lr': 0.00046618369072478163, 'samples': 5143488, 'steps': 26788, 'loss/train': 1.3270459175109863} 08/30/2021 17:58:23 - INFO - __main__ - Step 26790: {'lr': 0.0004661810254761141, 'samples': 5143680, 'steps': 26789, 'loss/train': 0.05226729065179825} 08/30/2021 17:58:23 - INFO - __main__ - Step 26791: {'lr': 0.0004661783601300388, 'samples': 5143872, 'steps': 26790, 'loss/train': 1.418766975402832} 08/30/2021 17:58:25 - INFO - __main__ - Step 26792: {'lr': 0.00046617569468655686, 'samples': 5144064, 'steps': 26791, 'loss/train': 1.2048664093017578} 08/30/2021 17:58:25 - INFO - __main__ - Step 26793: {'lr': 0.00046617302914566945, 'samples': 5144256, 'steps': 26792, 'loss/train': 0.2802641987800598} 08/30/2021 17:58:26 - INFO - __main__ - Step 26794: {'lr': 0.00046617036350737786, 'samples': 5144448, 'steps': 26793, 'loss/train': 2.003206729888916} 08/30/2021 17:58:26 - INFO - __main__ - Step 26795: {'lr': 0.0004661676977716832, 'samples': 5144640, 'steps': 26794, 'loss/train': 1.377181887626648} 08/30/2021 17:58:26 - INFO - __main__ - Step 26796: {'lr': 0.0004661650319385867, 'samples': 5144832, 'steps': 26795, 'loss/train': 1.4903490543365479} 08/30/2021 17:58:28 - INFO - __main__ - Step 26797: {'lr': 0.0004661623660080896, 'samples': 5145024, 'steps': 26796, 'loss/train': 1.5612714290618896} 08/30/2021 17:58:28 - INFO - __main__ - Step 26798: {'lr': 0.000466159699980193, 'samples': 5145216, 'steps': 26797, 'loss/train': 2.395564556121826} 08/30/2021 17:58:29 - INFO - __main__ - Step 26799: {'lr': 0.0004661570338548983, 'samples': 5145408, 'steps': 26798, 'loss/train': 1.3965349197387695} 08/30/2021 17:58:29 - INFO - __main__ - Step 26800: {'lr': 0.00046615436763220645, 'samples': 5145600, 'steps': 26799, 'loss/train': 1.2196152210235596} 08/30/2021 17:58:29 - INFO - __main__ - Step 26801: {'lr': 0.0004661517013121189, 'samples': 5145792, 'steps': 26800, 'loss/train': 1.6071802377700806} 08/30/2021 17:58:31 - INFO - __main__ - Step 26802: {'lr': 0.00046614903489463667, 'samples': 5145984, 'steps': 26801, 'loss/train': 1.6098366975784302} 08/30/2021 17:58:31 - INFO - __main__ - Step 26803: {'lr': 0.000466146368379761, 'samples': 5146176, 'steps': 26802, 'loss/train': 1.8973139524459839} 08/30/2021 17:58:32 - INFO - __main__ - Step 26804: {'lr': 0.0004661437017674931, 'samples': 5146368, 'steps': 26803, 'loss/train': 1.0908960103988647} 08/30/2021 17:58:32 - INFO - __main__ - Step 26805: {'lr': 0.00046614103505783423, 'samples': 5146560, 'steps': 26804, 'loss/train': 1.4314018487930298} 08/30/2021 17:58:32 - INFO - __main__ - Step 26806: {'lr': 0.0004661383682507856, 'samples': 5146752, 'steps': 26805, 'loss/train': 1.9222533702850342} 08/30/2021 17:58:34 - INFO - __main__ - Step 26807: {'lr': 0.00046613570134634825, 'samples': 5146944, 'steps': 26806, 'loss/train': 1.7310898303985596} 08/30/2021 17:58:34 - INFO - __main__ - Step 26808: {'lr': 0.00046613303434452346, 'samples': 5147136, 'steps': 26807, 'loss/train': 1.17205810546875} 08/30/2021 17:58:35 - INFO - __main__ - Step 26809: {'lr': 0.00046613036724531254, 'samples': 5147328, 'steps': 26808, 'loss/train': 0.9658483862876892} 08/30/2021 17:58:35 - INFO - __main__ - Step 26810: {'lr': 0.00046612770004871663, 'samples': 5147520, 'steps': 26809, 'loss/train': 1.5939700603485107} 08/30/2021 17:58:35 - INFO - __main__ - Step 26811: {'lr': 0.00046612503275473687, 'samples': 5147712, 'steps': 26810, 'loss/train': 1.7550020217895508} 08/30/2021 17:58:37 - INFO - __main__ - Step 26812: {'lr': 0.00046612236536337456, 'samples': 5147904, 'steps': 26811, 'loss/train': 1.9856510162353516} 08/30/2021 17:58:38 - INFO - __main__ - Step 26813: {'lr': 0.00046611969787463083, 'samples': 5148096, 'steps': 26812, 'loss/train': 4.578228950500488} 08/30/2021 17:58:38 - INFO - __main__ - Step 26814: {'lr': 0.00046611703028850683, 'samples': 5148288, 'steps': 26813, 'loss/train': 1.394594430923462} 08/30/2021 17:58:38 - INFO - __main__ - Step 26815: {'lr': 0.00046611436260500386, 'samples': 5148480, 'steps': 26814, 'loss/train': 1.1023682355880737} 08/30/2021 17:58:39 - INFO - __main__ - Step 26816: {'lr': 0.00046611169482412305, 'samples': 5148672, 'steps': 26815, 'loss/train': 1.971582055091858} 08/30/2021 17:58:39 - INFO - __main__ - Step 26817: {'lr': 0.00046610902694586576, 'samples': 5148864, 'steps': 26816, 'loss/train': 0.7202461957931519} 08/30/2021 17:58:41 - INFO - __main__ - Step 26818: {'lr': 0.00046610635897023303, 'samples': 5149056, 'steps': 26817, 'loss/train': 1.480725646018982} 08/30/2021 17:58:41 - INFO - __main__ - Step 26819: {'lr': 0.0004661036908972261, 'samples': 5149248, 'steps': 26818, 'loss/train': 2.1650359630584717} 08/30/2021 17:58:41 - INFO - __main__ - Step 26820: {'lr': 0.0004661010227268462, 'samples': 5149440, 'steps': 26819, 'loss/train': 1.171453595161438} 08/30/2021 17:58:42 - INFO - __main__ - Step 26821: {'lr': 0.0004660983544590944, 'samples': 5149632, 'steps': 26820, 'loss/train': 1.4449701309204102} 08/30/2021 17:58:42 - INFO - __main__ - Step 26822: {'lr': 0.0004660956860939722, 'samples': 5149824, 'steps': 26821, 'loss/train': 1.9287570714950562} 08/30/2021 17:58:44 - INFO - __main__ - Step 26823: {'lr': 0.0004660930176314805, 'samples': 5150016, 'steps': 26822, 'loss/train': 1.3852072954177856} 08/30/2021 17:58:44 - INFO - __main__ - Step 26824: {'lr': 0.0004660903490716206, 'samples': 5150208, 'steps': 26823, 'loss/train': 1.145975112915039} 08/30/2021 17:58:44 - INFO - __main__ - Step 26825: {'lr': 0.0004660876804143938, 'samples': 5150400, 'steps': 26824, 'loss/train': 1.3981616497039795} 08/30/2021 17:58:45 - INFO - __main__ - Step 26826: {'lr': 0.0004660850116598012, 'samples': 5150592, 'steps': 26825, 'loss/train': 1.5617139339447021} 08/30/2021 17:58:45 - INFO - __main__ - Step 26827: {'lr': 0.00046608234280784406, 'samples': 5150784, 'steps': 26826, 'loss/train': 1.561122179031372} 08/30/2021 17:58:47 - INFO - __main__ - Step 26828: {'lr': 0.0004660796738585235, 'samples': 5150976, 'steps': 26827, 'loss/train': 1.611430287361145} 08/30/2021 17:58:47 - INFO - __main__ - Step 26829: {'lr': 0.0004660770048118408, 'samples': 5151168, 'steps': 26828, 'loss/train': 1.7318994998931885} 08/30/2021 17:58:47 - INFO - __main__ - Step 26830: {'lr': 0.00046607433566779713, 'samples': 5151360, 'steps': 26829, 'loss/train': 1.8213824033737183} 08/30/2021 17:58:48 - INFO - __main__ - Step 26831: {'lr': 0.00046607166642639365, 'samples': 5151552, 'steps': 26830, 'loss/train': 1.9512497186660767} 08/30/2021 17:58:48 - INFO - __main__ - Step 26832: {'lr': 0.00046606899708763174, 'samples': 5151744, 'steps': 26831, 'loss/train': 1.0352290868759155} 08/30/2021 17:58:50 - INFO - __main__ - Step 26833: {'lr': 0.0004660663276515124, 'samples': 5151936, 'steps': 26832, 'loss/train': 1.424996256828308} 08/30/2021 17:58:50 - INFO - __main__ - Step 26834: {'lr': 0.00046606365811803686, 'samples': 5152128, 'steps': 26833, 'loss/train': 1.511102557182312} 08/30/2021 17:58:50 - INFO - __main__ - Step 26835: {'lr': 0.0004660609884872064, 'samples': 5152320, 'steps': 26834, 'loss/train': 1.5556164979934692} 08/30/2021 17:58:51 - INFO - __main__ - Step 26836: {'lr': 0.00046605831875902215, 'samples': 5152512, 'steps': 26835, 'loss/train': 1.4919860363006592} 08/30/2021 17:58:51 - INFO - __main__ - Step 26837: {'lr': 0.00046605564893348545, 'samples': 5152704, 'steps': 26836, 'loss/train': 1.5208078622817993} 08/30/2021 17:58:52 - INFO - __main__ - Step 26838: {'lr': 0.0004660529790105974, 'samples': 5152896, 'steps': 26837, 'loss/train': 1.2910549640655518} 08/30/2021 17:58:53 - INFO - __main__ - Step 26839: {'lr': 0.00046605030899035915, 'samples': 5153088, 'steps': 26838, 'loss/train': 1.374462366104126} 08/30/2021 17:58:53 - INFO - __main__ - Step 26840: {'lr': 0.000466047638872772, 'samples': 5153280, 'steps': 26839, 'loss/train': 2.2235822677612305} 08/30/2021 17:58:54 - INFO - __main__ - Step 26841: {'lr': 0.0004660449686578371, 'samples': 5153472, 'steps': 26840, 'loss/train': 1.8461415767669678} 08/30/2021 17:58:54 - INFO - __main__ - Step 26842: {'lr': 0.0004660422983455557, 'samples': 5153664, 'steps': 26841, 'loss/train': 1.227088451385498} 08/30/2021 17:58:56 - INFO - __main__ - Step 26843: {'lr': 0.0004660396279359289, 'samples': 5153856, 'steps': 26842, 'loss/train': 1.391221284866333} 08/30/2021 17:58:56 - INFO - __main__ - Step 26844: {'lr': 0.000466036957428958, 'samples': 5154048, 'steps': 26843, 'loss/train': 1.4195990562438965} 08/30/2021 17:58:57 - INFO - __main__ - Step 26845: {'lr': 0.0004660342868246442, 'samples': 5154240, 'steps': 26844, 'loss/train': 1.849786400794983} 08/30/2021 17:58:57 - INFO - __main__ - Step 26846: {'lr': 0.0004660316161229887, 'samples': 5154432, 'steps': 26845, 'loss/train': 0.9779144525527954} 08/30/2021 17:58:57 - INFO - __main__ - Step 26847: {'lr': 0.00046602894532399275, 'samples': 5154624, 'steps': 26846, 'loss/train': 1.4024840593338013} 08/30/2021 17:58:59 - INFO - __main__ - Step 26848: {'lr': 0.00046602627442765744, 'samples': 5154816, 'steps': 26847, 'loss/train': 1.672475814819336} 08/30/2021 17:58:59 - INFO - __main__ - Step 26849: {'lr': 0.00046602360343398397, 'samples': 5155008, 'steps': 26848, 'loss/train': 2.846569061279297} 08/30/2021 17:58:59 - INFO - __main__ - Step 26850: {'lr': 0.0004660209323429736, 'samples': 5155200, 'steps': 26849, 'loss/train': 1.5409947633743286} 08/30/2021 17:59:00 - INFO - __main__ - Step 26851: {'lr': 0.0004660182611546276, 'samples': 5155392, 'steps': 26850, 'loss/train': 1.9352277517318726} 08/30/2021 17:59:00 - INFO - __main__ - Step 26852: {'lr': 0.0004660155898689471, 'samples': 5155584, 'steps': 26851, 'loss/train': 1.462173581123352} 08/30/2021 17:59:01 - INFO - __main__ - Step 26853: {'lr': 0.0004660129184859332, 'samples': 5155776, 'steps': 26852, 'loss/train': 1.3452694416046143} 08/30/2021 17:59:02 - INFO - __main__ - Step 26854: {'lr': 0.00046601024700558736, 'samples': 5155968, 'steps': 26853, 'loss/train': 1.82614004611969} 08/30/2021 17:59:02 - INFO - __main__ - Step 26855: {'lr': 0.0004660075754279105, 'samples': 5156160, 'steps': 26854, 'loss/train': 0.9493875503540039} 08/30/2021 17:59:03 - INFO - __main__ - Step 26856: {'lr': 0.00046600490375290406, 'samples': 5156352, 'steps': 26855, 'loss/train': 1.6828885078430176} 08/30/2021 17:59:03 - INFO - __main__ - Step 26857: {'lr': 0.0004660022319805691, 'samples': 5156544, 'steps': 26856, 'loss/train': 1.6080266237258911} 08/30/2021 17:59:03 - INFO - __main__ - Step 26858: {'lr': 0.0004659995601109069, 'samples': 5156736, 'steps': 26857, 'loss/train': 1.231449007987976} 08/30/2021 17:59:05 - INFO - __main__ - Step 26859: {'lr': 0.0004659968881439186, 'samples': 5156928, 'steps': 26858, 'loss/train': 0.4787122309207916} 08/30/2021 17:59:06 - INFO - __main__ - Step 26860: {'lr': 0.00046599421607960545, 'samples': 5157120, 'steps': 26859, 'loss/train': 1.3173683881759644} 08/30/2021 17:59:06 - INFO - __main__ - Step 26861: {'lr': 0.0004659915439179686, 'samples': 5157312, 'steps': 26860, 'loss/train': 0.1036704033613205} 08/30/2021 17:59:06 - INFO - __main__ - Step 26862: {'lr': 0.0004659888716590094, 'samples': 5157504, 'steps': 26861, 'loss/train': 1.4828739166259766} 08/30/2021 17:59:07 - INFO - __main__ - Step 26863: {'lr': 0.00046598619930272883, 'samples': 5157696, 'steps': 26862, 'loss/train': 1.2362053394317627} 08/30/2021 17:59:08 - INFO - __main__ - Step 26864: {'lr': 0.00046598352684912824, 'samples': 5157888, 'steps': 26863, 'loss/train': 1.6815341711044312} 08/30/2021 17:59:09 - INFO - __main__ - Step 26865: {'lr': 0.0004659808542982088, 'samples': 5158080, 'steps': 26864, 'loss/train': 1.1082732677459717} 08/30/2021 17:59:09 - INFO - __main__ - Step 26866: {'lr': 0.0004659781816499718, 'samples': 5158272, 'steps': 26865, 'loss/train': 1.7296682596206665} 08/30/2021 17:59:09 - INFO - __main__ - Step 26867: {'lr': 0.0004659755089044183, 'samples': 5158464, 'steps': 26866, 'loss/train': 1.1451698541641235} 08/30/2021 17:59:10 - INFO - __main__ - Step 26868: {'lr': 0.00046597283606154957, 'samples': 5158656, 'steps': 26867, 'loss/train': 1.3216966390609741} 08/30/2021 17:59:12 - INFO - __main__ - Step 26869: {'lr': 0.0004659701631213668, 'samples': 5158848, 'steps': 26868, 'loss/train': 0.9072578549385071} 08/30/2021 17:59:12 - INFO - __main__ - Step 26870: {'lr': 0.00046596749008387124, 'samples': 5159040, 'steps': 26869, 'loss/train': 1.7794842720031738} 08/30/2021 17:59:13 - INFO - __main__ - Step 26871: {'lr': 0.00046596481694906403, 'samples': 5159232, 'steps': 26870, 'loss/train': 1.610386610031128} 08/30/2021 17:59:13 - INFO - __main__ - Step 26872: {'lr': 0.00046596214371694643, 'samples': 5159424, 'steps': 26871, 'loss/train': 1.3272669315338135} 08/30/2021 17:59:13 - INFO - __main__ - Step 26873: {'lr': 0.00046595947038751963, 'samples': 5159616, 'steps': 26872, 'loss/train': 1.3920873403549194} 08/30/2021 17:59:15 - INFO - __main__ - Step 26874: {'lr': 0.00046595679696078476, 'samples': 5159808, 'steps': 26873, 'loss/train': 2.0769612789154053} 08/30/2021 17:59:15 - INFO - __main__ - Step 26875: {'lr': 0.00046595412343674317, 'samples': 5160000, 'steps': 26874, 'loss/train': 1.1637133359909058} 08/30/2021 17:59:15 - INFO - __main__ - Step 26876: {'lr': 0.00046595144981539596, 'samples': 5160192, 'steps': 26875, 'loss/train': 1.4622235298156738} 08/30/2021 17:59:16 - INFO - __main__ - Step 26877: {'lr': 0.00046594877609674437, 'samples': 5160384, 'steps': 26876, 'loss/train': 1.3788200616836548} 08/30/2021 17:59:16 - INFO - __main__ - Step 26878: {'lr': 0.00046594610228078954, 'samples': 5160576, 'steps': 26877, 'loss/train': 1.8409117460250854} 08/30/2021 17:59:18 - INFO - __main__ - Step 26879: {'lr': 0.00046594342836753276, 'samples': 5160768, 'steps': 26878, 'loss/train': 1.4835433959960938} 08/30/2021 17:59:18 - INFO - __main__ - Step 26880: {'lr': 0.0004659407543569752, 'samples': 5160960, 'steps': 26879, 'loss/train': 0.2934632897377014} 08/30/2021 17:59:19 - INFO - __main__ - Step 26881: {'lr': 0.0004659380802491181, 'samples': 5161152, 'steps': 26880, 'loss/train': 0.262529581785202} 08/30/2021 17:59:19 - INFO - __main__ - Step 26882: {'lr': 0.00046593540604396256, 'samples': 5161344, 'steps': 26881, 'loss/train': 1.2058743238449097} 08/30/2021 17:59:19 - INFO - __main__ - Step 26883: {'lr': 0.00046593273174150995, 'samples': 5161536, 'steps': 26882, 'loss/train': 1.7408865690231323} 08/30/2021 17:59:20 - INFO - __main__ - Step 26884: {'lr': 0.0004659300573417613, 'samples': 5161728, 'steps': 26883, 'loss/train': 0.8488700985908508} 08/30/2021 17:59:22 - INFO - __main__ - Step 26885: {'lr': 0.00046592738284471794, 'samples': 5161920, 'steps': 26884, 'loss/train': 1.6995694637298584} 08/30/2021 17:59:22 - INFO - __main__ - Step 26886: {'lr': 0.000465924708250381, 'samples': 5162112, 'steps': 26885, 'loss/train': 1.3161303997039795} 08/30/2021 17:59:22 - INFO - __main__ - Step 26887: {'lr': 0.00046592203355875177, 'samples': 5162304, 'steps': 26886, 'loss/train': 1.1734241247177124} 08/30/2021 17:59:23 - INFO - __main__ - Step 26888: {'lr': 0.00046591935876983136, 'samples': 5162496, 'steps': 26887, 'loss/train': 0.04021792858839035} 08/30/2021 17:59:23 - INFO - __main__ - Step 26889: {'lr': 0.0004659166838836211, 'samples': 5162688, 'steps': 26888, 'loss/train': 1.476667046546936} 08/30/2021 17:59:24 - INFO - __main__ - Step 26890: {'lr': 0.000465914008900122, 'samples': 5162880, 'steps': 26889, 'loss/train': 2.0075557231903076} 08/30/2021 17:59:25 - INFO - __main__ - Step 26891: {'lr': 0.00046591133381933546, 'samples': 5163072, 'steps': 26890, 'loss/train': 1.437656044960022} 08/30/2021 17:59:26 - INFO - __main__ - Step 26892: {'lr': 0.0004659086586412626, 'samples': 5163264, 'steps': 26891, 'loss/train': 0.061180729418992996} 08/30/2021 17:59:26 - INFO - __main__ - Step 26893: {'lr': 0.0004659059833659046, 'samples': 5163456, 'steps': 26892, 'loss/train': 0.9740949869155884} 08/30/2021 17:59:26 - INFO - __main__ - Step 26894: {'lr': 0.0004659033079932627, 'samples': 5163648, 'steps': 26893, 'loss/train': 2.013864278793335} 08/30/2021 17:59:27 - INFO - __main__ - Step 26895: {'lr': 0.00046590063252333806, 'samples': 5163840, 'steps': 26894, 'loss/train': 1.2683641910552979} 08/30/2021 17:59:28 - INFO - __main__ - Step 26896: {'lr': 0.000465897956956132, 'samples': 5164032, 'steps': 26895, 'loss/train': 0.9575828313827515} 08/30/2021 17:59:29 - INFO - __main__ - Step 26897: {'lr': 0.0004658952812916456, 'samples': 5164224, 'steps': 26896, 'loss/train': 1.3946799039840698} 08/30/2021 17:59:29 - INFO - __main__ - Step 26898: {'lr': 0.0004658926055298802, 'samples': 5164416, 'steps': 26897, 'loss/train': 1.4117990732192993} 08/30/2021 17:59:29 - INFO - __main__ - Step 26899: {'lr': 0.0004658899296708369, 'samples': 5164608, 'steps': 26898, 'loss/train': 1.3764944076538086} 08/30/2021 17:59:30 - INFO - __main__ - Step 26900: {'lr': 0.00046588725371451685, 'samples': 5164800, 'steps': 26899, 'loss/train': 1.512864589691162} 08/30/2021 17:59:31 - INFO - __main__ - Step 26901: {'lr': 0.00046588457766092134, 'samples': 5164992, 'steps': 26900, 'loss/train': 1.5008000135421753} 08/30/2021 17:59:31 - INFO - __main__ - Step 26902: {'lr': 0.00046588190151005163, 'samples': 5165184, 'steps': 26901, 'loss/train': 1.5895146131515503} 08/30/2021 17:59:32 - INFO - __main__ - Step 26903: {'lr': 0.00046587922526190883, 'samples': 5165376, 'steps': 26902, 'loss/train': 1.352649211883545} 08/30/2021 17:59:32 - INFO - __main__ - Step 26904: {'lr': 0.00046587654891649423, 'samples': 5165568, 'steps': 26903, 'loss/train': 2.2640106678009033} 08/30/2021 17:59:32 - INFO - __main__ - Step 26905: {'lr': 0.00046587387247380897, 'samples': 5165760, 'steps': 26904, 'loss/train': 1.7070716619491577} 08/30/2021 17:59:34 - INFO - __main__ - Step 26906: {'lr': 0.00046587119593385424, 'samples': 5165952, 'steps': 26905, 'loss/train': 1.495260238647461} 08/30/2021 17:59:34 - INFO - __main__ - Step 26907: {'lr': 0.00046586851929663134, 'samples': 5166144, 'steps': 26906, 'loss/train': 1.2227405309677124} 08/30/2021 17:59:35 - INFO - __main__ - Step 26908: {'lr': 0.00046586584256214135, 'samples': 5166336, 'steps': 26907, 'loss/train': 1.274914026260376} 08/30/2021 17:59:35 - INFO - __main__ - Step 26909: {'lr': 0.0004658631657303856, 'samples': 5166528, 'steps': 26908, 'loss/train': 0.8560934662818909} 08/30/2021 17:59:36 - INFO - __main__ - Step 26910: {'lr': 0.0004658604888013652, 'samples': 5166720, 'steps': 26909, 'loss/train': 1.6615206003189087} 08/30/2021 17:59:36 - INFO - __main__ - Step 26911: {'lr': 0.00046585781177508137, 'samples': 5166912, 'steps': 26910, 'loss/train': 2.079286813735962} 08/30/2021 17:59:38 - INFO - __main__ - Step 26912: {'lr': 0.0004658551346515354, 'samples': 5167104, 'steps': 26911, 'loss/train': 0.07465283572673798} 08/30/2021 17:59:38 - INFO - __main__ - Step 26913: {'lr': 0.00046585245743072833, 'samples': 5167296, 'steps': 26912, 'loss/train': 1.620635986328125} 08/30/2021 17:59:39 - INFO - __main__ - Step 26914: {'lr': 0.0004658497801126616, 'samples': 5167488, 'steps': 26913, 'loss/train': 1.3414040803909302} 08/30/2021 17:59:39 - INFO - __main__ - Step 26915: {'lr': 0.00046584710269733623, 'samples': 5167680, 'steps': 26914, 'loss/train': 1.435752272605896} 08/30/2021 17:59:39 - INFO - __main__ - Step 26916: {'lr': 0.00046584442518475354, 'samples': 5167872, 'steps': 26915, 'loss/train': 1.3708261251449585} 08/30/2021 17:59:41 - INFO - __main__ - Step 26917: {'lr': 0.0004658417475749146, 'samples': 5168064, 'steps': 26916, 'loss/train': 0.06692387163639069} 08/30/2021 17:59:41 - INFO - __main__ - Step 26918: {'lr': 0.00046583906986782074, 'samples': 5168256, 'steps': 26917, 'loss/train': 1.6083214282989502} 08/30/2021 17:59:42 - INFO - __main__ - Step 26919: {'lr': 0.0004658363920634732, 'samples': 5168448, 'steps': 26918, 'loss/train': 1.3549399375915527} 08/30/2021 17:59:42 - INFO - __main__ - Step 26920: {'lr': 0.000465833714161873, 'samples': 5168640, 'steps': 26919, 'loss/train': 1.7720448970794678} 08/30/2021 17:59:42 - INFO - __main__ - Step 26921: {'lr': 0.00046583103616302146, 'samples': 5168832, 'steps': 26920, 'loss/train': 0.20303179323673248} 08/30/2021 17:59:43 - INFO - __main__ - Step 26922: {'lr': 0.0004658283580669198, 'samples': 5169024, 'steps': 26921, 'loss/train': 1.0080013275146484} 08/30/2021 17:59:45 - INFO - __main__ - Step 26923: {'lr': 0.0004658256798735693, 'samples': 5169216, 'steps': 26922, 'loss/train': 1.368169903755188} 08/30/2021 17:59:45 - INFO - __main__ - Step 26924: {'lr': 0.000465823001582971, 'samples': 5169408, 'steps': 26923, 'loss/train': 1.1282775402069092} 08/30/2021 17:59:46 - INFO - __main__ - Step 26925: {'lr': 0.00046582032319512624, 'samples': 5169600, 'steps': 26924, 'loss/train': 2.120058536529541} 08/30/2021 17:59:46 - INFO - __main__ - Step 26926: {'lr': 0.00046581764471003605, 'samples': 5169792, 'steps': 26925, 'loss/train': 1.5686094760894775} 08/30/2021 17:59:46 - INFO - __main__ - Step 26927: {'lr': 0.0004658149661277019, 'samples': 5169984, 'steps': 26926, 'loss/train': 1.1897062063217163} 08/30/2021 17:59:48 - INFO - __main__ - Step 26928: {'lr': 0.0004658122874481248, 'samples': 5170176, 'steps': 26927, 'loss/train': 1.6875969171524048} 08/30/2021 17:59:48 - INFO - __main__ - Step 26929: {'lr': 0.000465809608671306, 'samples': 5170368, 'steps': 26928, 'loss/train': 1.5299280881881714} 08/30/2021 17:59:49 - INFO - __main__ - Step 26930: {'lr': 0.0004658069297972467, 'samples': 5170560, 'steps': 26929, 'loss/train': 1.452596664428711} 08/30/2021 17:59:49 - INFO - __main__ - Step 26931: {'lr': 0.00046580425082594823, 'samples': 5170752, 'steps': 26930, 'loss/train': 1.6443637609481812} 08/30/2021 17:59:49 - INFO - __main__ - Step 26932: {'lr': 0.00046580157175741155, 'samples': 5170944, 'steps': 26931, 'loss/train': 1.6452678442001343} 08/30/2021 17:59:51 - INFO - __main__ - Step 26933: {'lr': 0.0004657988925916381, 'samples': 5171136, 'steps': 26932, 'loss/train': 1.4347848892211914} 08/30/2021 17:59:51 - INFO - __main__ - Step 26934: {'lr': 0.000465796213328629, 'samples': 5171328, 'steps': 26933, 'loss/train': 1.8302736282348633} 08/30/2021 17:59:52 - INFO - __main__ - Step 26935: {'lr': 0.00046579353396838545, 'samples': 5171520, 'steps': 26934, 'loss/train': 1.3067013025283813} 08/30/2021 17:59:52 - INFO - __main__ - Step 26936: {'lr': 0.00046579085451090864, 'samples': 5171712, 'steps': 26935, 'loss/train': 2.155531406402588} 08/30/2021 17:59:52 - INFO - __main__ - Step 26937: {'lr': 0.00046578817495619983, 'samples': 5171904, 'steps': 26936, 'loss/train': 1.717665672302246} 08/30/2021 17:59:54 - INFO - __main__ - Step 26938: {'lr': 0.0004657854953042602, 'samples': 5172096, 'steps': 26937, 'loss/train': 1.2332600355148315} 08/30/2021 17:59:55 - INFO - __main__ - Step 26939: {'lr': 0.00046578281555509094, 'samples': 5172288, 'steps': 26938, 'loss/train': 1.4292773008346558} 08/30/2021 17:59:55 - INFO - __main__ - Step 26940: {'lr': 0.00046578013570869325, 'samples': 5172480, 'steps': 26939, 'loss/train': 0.8554905652999878} 08/30/2021 17:59:55 - INFO - __main__ - Step 26941: {'lr': 0.00046577745576506844, 'samples': 5172672, 'steps': 26940, 'loss/train': 1.1735535860061646} 08/30/2021 17:59:56 - INFO - __main__ - Step 26942: {'lr': 0.00046577477572421757, 'samples': 5172864, 'steps': 26941, 'loss/train': 1.6115187406539917} 08/30/2021 17:59:57 - INFO - __main__ - Step 26943: {'lr': 0.0004657720955861419, 'samples': 5173056, 'steps': 26942, 'loss/train': 1.2197036743164062} 08/30/2021 17:59:58 - INFO - __main__ - Step 26944: {'lr': 0.00046576941535084274, 'samples': 5173248, 'steps': 26943, 'loss/train': 1.4582329988479614} 08/30/2021 17:59:58 - INFO - __main__ - Step 26945: {'lr': 0.0004657667350183211, 'samples': 5173440, 'steps': 26944, 'loss/train': 1.435172200202942} 08/30/2021 17:59:58 - INFO - __main__ - Step 26946: {'lr': 0.00046576405458857836, 'samples': 5173632, 'steps': 26945, 'loss/train': 1.965851068496704} 08/30/2021 17:59:59 - INFO - __main__ - Step 26947: {'lr': 0.0004657613740616157, 'samples': 5173824, 'steps': 26946, 'loss/train': 1.4533733129501343} 08/30/2021 18:00:00 - INFO - __main__ - Step 26948: {'lr': 0.0004657586934374342, 'samples': 5174016, 'steps': 26947, 'loss/train': 2.0454695224761963} 08/30/2021 18:00:01 - INFO - __main__ - Step 26949: {'lr': 0.0004657560127160352, 'samples': 5174208, 'steps': 26948, 'loss/train': 0.8816270232200623} 08/30/2021 18:00:01 - INFO - __main__ - Step 26950: {'lr': 0.00046575333189741993, 'samples': 5174400, 'steps': 26949, 'loss/train': 1.6166325807571411} 08/30/2021 18:00:01 - INFO - __main__ - Step 26951: {'lr': 0.00046575065098158945, 'samples': 5174592, 'steps': 26950, 'loss/train': 1.4760130643844604} 08/30/2021 18:00:02 - INFO - __main__ - Step 26952: {'lr': 0.0004657479699685451, 'samples': 5174784, 'steps': 26951, 'loss/train': 1.284529447555542} 08/30/2021 18:00:03 - INFO - __main__ - Step 26953: {'lr': 0.00046574528885828803, 'samples': 5174976, 'steps': 26952, 'loss/train': 1.1363043785095215} 08/30/2021 18:00:04 - INFO - __main__ - Step 26954: {'lr': 0.0004657426076508195, 'samples': 5175168, 'steps': 26953, 'loss/train': 0.8876258134841919} 08/30/2021 18:00:04 - INFO - __main__ - Step 26955: {'lr': 0.00046573992634614064, 'samples': 5175360, 'steps': 26954, 'loss/train': 1.6934928894042969} 08/30/2021 18:00:04 - INFO - __main__ - Step 26956: {'lr': 0.00046573724494425274, 'samples': 5175552, 'steps': 26955, 'loss/train': 1.5810352563858032} 08/30/2021 18:00:05 - INFO - __main__ - Step 26957: {'lr': 0.00046573456344515694, 'samples': 5175744, 'steps': 26956, 'loss/train': 1.250922679901123} 08/30/2021 18:00:06 - INFO - __main__ - Step 26958: {'lr': 0.00046573188184885445, 'samples': 5175936, 'steps': 26957, 'loss/train': 1.3188906908035278} 08/30/2021 18:00:07 - INFO - __main__ - Step 26959: {'lr': 0.0004657292001553465, 'samples': 5176128, 'steps': 26958, 'loss/train': 0.06328149139881134} 08/30/2021 18:00:07 - INFO - __main__ - Step 26960: {'lr': 0.0004657265183646344, 'samples': 5176320, 'steps': 26959, 'loss/train': 1.6511822938919067} 08/30/2021 18:00:07 - INFO - __main__ - Step 26961: {'lr': 0.00046572383647671913, 'samples': 5176512, 'steps': 26960, 'loss/train': 1.7765454053878784} 08/30/2021 18:00:08 - INFO - __main__ - Step 26962: {'lr': 0.0004657211544916021, 'samples': 5176704, 'steps': 26961, 'loss/train': 0.3017668128013611} 08/30/2021 18:00:08 - INFO - __main__ - Step 26963: {'lr': 0.00046571847240928444, 'samples': 5176896, 'steps': 26962, 'loss/train': 1.1066577434539795} 08/30/2021 18:00:10 - INFO - __main__ - Step 26964: {'lr': 0.0004657157902297674, 'samples': 5177088, 'steps': 26963, 'loss/train': 1.6019381284713745} 08/30/2021 18:00:10 - INFO - __main__ - Step 26965: {'lr': 0.00046571310795305213, 'samples': 5177280, 'steps': 26964, 'loss/train': 1.538810133934021} 08/30/2021 18:00:10 - INFO - __main__ - Step 26966: {'lr': 0.0004657104255791398, 'samples': 5177472, 'steps': 26965, 'loss/train': 1.459782600402832} 08/30/2021 18:00:11 - INFO - __main__ - Step 26967: {'lr': 0.0004657077431080317, 'samples': 5177664, 'steps': 26966, 'loss/train': 0.059555113315582275} 08/30/2021 18:00:11 - INFO - __main__ - Step 26968: {'lr': 0.00046570506053972906, 'samples': 5177856, 'steps': 26967, 'loss/train': 0.24769888818264008} 08/30/2021 18:00:13 - INFO - __main__ - Step 26969: {'lr': 0.000465702377874233, 'samples': 5178048, 'steps': 26968, 'loss/train': 1.255476474761963} 08/30/2021 18:00:13 - INFO - __main__ - Step 26970: {'lr': 0.00046569969511154485, 'samples': 5178240, 'steps': 26969, 'loss/train': 1.66780424118042} 08/30/2021 18:00:13 - INFO - __main__ - Step 26971: {'lr': 0.0004656970122516657, 'samples': 5178432, 'steps': 26970, 'loss/train': 1.5754352807998657} 08/30/2021 18:00:14 - INFO - __main__ - Step 26972: {'lr': 0.0004656943292945968, 'samples': 5178624, 'steps': 26971, 'loss/train': 1.924007773399353} 08/30/2021 18:00:14 - INFO - __main__ - Step 26973: {'lr': 0.0004656916462403394, 'samples': 5178816, 'steps': 26972, 'loss/train': 1.4658902883529663} 08/30/2021 18:00:17 - INFO - __main__ - Step 26974: {'lr': 0.0004656889630888946, 'samples': 5179008, 'steps': 26973, 'loss/train': 2.0741961002349854} 08/30/2021 18:00:18 - INFO - __main__ - Step 26975: {'lr': 0.0004656862798402638, 'samples': 5179200, 'steps': 26974, 'loss/train': 1.6244912147521973} 08/30/2021 18:00:18 - INFO - __main__ - Step 26976: {'lr': 0.00046568359649444796, 'samples': 5179392, 'steps': 26975, 'loss/train': 1.8216925859451294} 08/30/2021 18:00:18 - INFO - __main__ - Step 26977: {'lr': 0.0004656809130514485, 'samples': 5179584, 'steps': 26976, 'loss/train': 1.8022947311401367} 08/30/2021 18:00:19 - INFO - __main__ - Step 26978: {'lr': 0.00046567822951126646, 'samples': 5179776, 'steps': 26977, 'loss/train': 1.8025085926055908} 08/30/2021 18:00:19 - INFO - __main__ - Step 26979: {'lr': 0.00046567554587390324, 'samples': 5179968, 'steps': 26978, 'loss/train': 1.7827305793762207} 08/30/2021 18:00:19 - INFO - __main__ - Step 26980: {'lr': 0.00046567286213935994, 'samples': 5180160, 'steps': 26979, 'loss/train': 1.6404439210891724} 08/30/2021 18:00:20 - INFO - __main__ - Step 26981: {'lr': 0.00046567017830763776, 'samples': 5180352, 'steps': 26980, 'loss/train': 1.7375833988189697} 08/30/2021 18:00:22 - INFO - __main__ - Step 26982: {'lr': 0.0004656674943787379, 'samples': 5180544, 'steps': 26981, 'loss/train': 1.5636651515960693} 08/30/2021 18:00:22 - INFO - __main__ - Step 26983: {'lr': 0.0004656648103526616, 'samples': 5180736, 'steps': 26982, 'loss/train': 1.382455825805664} 08/30/2021 18:00:23 - INFO - __main__ - Step 26984: {'lr': 0.00046566212622941005, 'samples': 5180928, 'steps': 26983, 'loss/train': 1.688787579536438} 08/30/2021 18:00:23 - INFO - __main__ - Step 26985: {'lr': 0.00046565944200898453, 'samples': 5181120, 'steps': 26984, 'loss/train': 1.9001823663711548} 08/30/2021 18:00:23 - INFO - __main__ - Step 26986: {'lr': 0.00046565675769138614, 'samples': 5181312, 'steps': 26985, 'loss/train': 0.9823494553565979} 08/30/2021 18:00:25 - INFO - __main__ - Step 26987: {'lr': 0.00046565407327661614, 'samples': 5181504, 'steps': 26986, 'loss/train': 1.2785985469818115} 08/30/2021 18:00:25 - INFO - __main__ - Step 26988: {'lr': 0.0004656513887646758, 'samples': 5181696, 'steps': 26987, 'loss/train': 0.9510458707809448} 08/30/2021 18:00:26 - INFO - __main__ - Step 26989: {'lr': 0.00046564870415556625, 'samples': 5181888, 'steps': 26988, 'loss/train': 1.7741374969482422} 08/30/2021 18:00:26 - INFO - __main__ - Step 26990: {'lr': 0.0004656460194492887, 'samples': 5182080, 'steps': 26989, 'loss/train': 1.8898942470550537} 08/30/2021 18:00:26 - INFO - __main__ - Step 26991: {'lr': 0.0004656433346458444, 'samples': 5182272, 'steps': 26990, 'loss/train': 1.4533418416976929} 08/30/2021 18:00:28 - INFO - __main__ - Step 26992: {'lr': 0.0004656406497452345, 'samples': 5182464, 'steps': 26991, 'loss/train': 0.4570915102958679} 08/30/2021 18:00:29 - INFO - __main__ - Step 26993: {'lr': 0.0004656379647474603, 'samples': 5182656, 'steps': 26992, 'loss/train': 1.7154120206832886} 08/30/2021 18:00:29 - INFO - __main__ - Step 26994: {'lr': 0.0004656352796525229, 'samples': 5182848, 'steps': 26993, 'loss/train': 1.6002998352050781} 08/30/2021 18:00:29 - INFO - __main__ - Step 26995: {'lr': 0.0004656325944604236, 'samples': 5183040, 'steps': 26994, 'loss/train': 2.3379414081573486} 08/30/2021 18:00:30 - INFO - __main__ - Step 26996: {'lr': 0.00046562990917116366, 'samples': 5183232, 'steps': 26995, 'loss/train': 2.3268332481384277} 08/30/2021 18:00:30 - INFO - __main__ - Step 26997: {'lr': 0.0004656272237847441, 'samples': 5183424, 'steps': 26996, 'loss/train': 1.5761443376541138} 08/30/2021 18:00:31 - INFO - __main__ - Step 26998: {'lr': 0.0004656245383011663, 'samples': 5183616, 'steps': 26997, 'loss/train': 1.7556006908416748} 08/30/2021 18:00:32 - INFO - __main__ - Step 26999: {'lr': 0.00046562185272043137, 'samples': 5183808, 'steps': 26998, 'loss/train': 1.1383898258209229} 08/30/2021 18:00:32 - INFO - __main__ - Step 27000: {'lr': 0.00046561916704254057, 'samples': 5184000, 'steps': 26999, 'loss/train': 1.391679048538208} 08/30/2021 18:00:33 - INFO - __main__ - Step 27001: {'lr': 0.0004656164812674951, 'samples': 5184192, 'steps': 27000, 'loss/train': 1.0219672918319702} 08/30/2021 18:00:33 - INFO - __main__ - Step 27002: {'lr': 0.00046561379539529626, 'samples': 5184384, 'steps': 27001, 'loss/train': 1.7161716222763062} 08/30/2021 18:00:34 - INFO - __main__ - Step 27003: {'lr': 0.0004656111094259451, 'samples': 5184576, 'steps': 27002, 'loss/train': 1.537265658378601} 08/30/2021 18:00:35 - INFO - __main__ - Step 27004: {'lr': 0.0004656084233594429, 'samples': 5184768, 'steps': 27003, 'loss/train': 1.6356860399246216} 08/30/2021 18:00:35 - INFO - __main__ - Step 27005: {'lr': 0.0004656057371957908, 'samples': 5184960, 'steps': 27004, 'loss/train': 1.807446837425232} 08/30/2021 18:00:36 - INFO - __main__ - Step 27006: {'lr': 0.00046560305093499015, 'samples': 5185152, 'steps': 27005, 'loss/train': 1.366638422012329} 08/30/2021 18:00:36 - INFO - __main__ - Step 27007: {'lr': 0.00046560036457704215, 'samples': 5185344, 'steps': 27006, 'loss/train': 1.4681525230407715} 08/30/2021 18:00:37 - INFO - __main__ - Step 27008: {'lr': 0.00046559767812194786, 'samples': 5185536, 'steps': 27007, 'loss/train': 1.4224255084991455} 08/30/2021 18:00:38 - INFO - __main__ - Step 27009: {'lr': 0.0004655949915697086, 'samples': 5185728, 'steps': 27008, 'loss/train': 1.3201313018798828} 08/30/2021 18:00:38 - INFO - __main__ - Step 27010: {'lr': 0.0004655923049203256, 'samples': 5185920, 'steps': 27009, 'loss/train': 1.4706474542617798} 08/30/2021 18:00:39 - INFO - __main__ - Step 27011: {'lr': 0.00046558961817380005, 'samples': 5186112, 'steps': 27010, 'loss/train': 2.05584454536438} 08/30/2021 18:00:39 - INFO - __main__ - Step 27012: {'lr': 0.00046558693133013306, 'samples': 5186304, 'steps': 27011, 'loss/train': 1.6807987689971924} 08/30/2021 18:00:39 - INFO - __main__ - Step 27013: {'lr': 0.000465584244389326, 'samples': 5186496, 'steps': 27012, 'loss/train': 1.2257968187332153} 08/30/2021 18:00:41 - INFO - __main__ - Step 27014: {'lr': 0.00046558155735137996, 'samples': 5186688, 'steps': 27013, 'loss/train': 1.448624610900879} 08/30/2021 18:00:41 - INFO - __main__ - Step 27015: {'lr': 0.00046557887021629623, 'samples': 5186880, 'steps': 27014, 'loss/train': 1.1582815647125244} 08/30/2021 18:00:41 - INFO - __main__ - Step 27016: {'lr': 0.000465576182984076, 'samples': 5187072, 'steps': 27015, 'loss/train': 2.0148961544036865} 08/30/2021 18:00:42 - INFO - __main__ - Step 27017: {'lr': 0.0004655734956547204, 'samples': 5187264, 'steps': 27016, 'loss/train': 1.5241016149520874} 08/30/2021 18:00:42 - INFO - __main__ - Step 27018: {'lr': 0.00046557080822823076, 'samples': 5187456, 'steps': 27017, 'loss/train': 1.4491941928863525} 08/30/2021 18:00:44 - INFO - __main__ - Step 27019: {'lr': 0.0004655681207046083, 'samples': 5187648, 'steps': 27018, 'loss/train': 0.8379098176956177} 08/30/2021 18:00:44 - INFO - __main__ - Step 27020: {'lr': 0.0004655654330838541, 'samples': 5187840, 'steps': 27019, 'loss/train': 1.3857444524765015} 08/30/2021 18:00:44 - INFO - __main__ - Step 27021: {'lr': 0.00046556274536596945, 'samples': 5188032, 'steps': 27020, 'loss/train': 1.6075927019119263} 08/30/2021 18:00:45 - INFO - __main__ - Step 27022: {'lr': 0.00046556005755095555, 'samples': 5188224, 'steps': 27021, 'loss/train': 1.4196367263793945} 08/30/2021 18:00:45 - INFO - __main__ - Step 27023: {'lr': 0.00046555736963881355, 'samples': 5188416, 'steps': 27022, 'loss/train': 1.0890384912490845} 08/30/2021 18:00:47 - INFO - __main__ - Step 27024: {'lr': 0.0004655546816295448, 'samples': 5188608, 'steps': 27023, 'loss/train': 1.5265403985977173} 08/30/2021 18:00:47 - INFO - __main__ - Step 27025: {'lr': 0.0004655519935231505, 'samples': 5188800, 'steps': 27024, 'loss/train': 1.6783900260925293} 08/30/2021 18:00:47 - INFO - __main__ - Step 27026: {'lr': 0.00046554930531963166, 'samples': 5188992, 'steps': 27025, 'loss/train': 1.0980746746063232} 08/30/2021 18:00:48 - INFO - __main__ - Step 27027: {'lr': 0.0004655466170189897, 'samples': 5189184, 'steps': 27026, 'loss/train': 1.1677947044372559} 08/30/2021 18:00:48 - INFO - __main__ - Step 27028: {'lr': 0.0004655439286212257, 'samples': 5189376, 'steps': 27027, 'loss/train': 1.392407774925232} 08/30/2021 18:00:50 - INFO - __main__ - Step 27029: {'lr': 0.00046554124012634105, 'samples': 5189568, 'steps': 27028, 'loss/train': 1.6881626844406128} 08/30/2021 18:00:50 - INFO - __main__ - Step 27030: {'lr': 0.0004655385515343368, 'samples': 5189760, 'steps': 27029, 'loss/train': 1.3778564929962158} 08/30/2021 18:00:51 - INFO - __main__ - Step 27031: {'lr': 0.0004655358628452142, 'samples': 5189952, 'steps': 27030, 'loss/train': 1.9335951805114746} 08/30/2021 18:00:51 - INFO - __main__ - Step 27032: {'lr': 0.00046553317405897444, 'samples': 5190144, 'steps': 27031, 'loss/train': 1.3064842224121094} 08/30/2021 18:00:51 - INFO - __main__ - Step 27033: {'lr': 0.0004655304851756188, 'samples': 5190336, 'steps': 27032, 'loss/train': 1.3732681274414062} 08/30/2021 18:00:53 - INFO - __main__ - Step 27034: {'lr': 0.0004655277961951484, 'samples': 5190528, 'steps': 27033, 'loss/train': 1.7316031455993652} 08/30/2021 18:00:54 - INFO - __main__ - Step 27035: {'lr': 0.00046552510711756444, 'samples': 5190720, 'steps': 27034, 'loss/train': 1.9706547260284424} 08/30/2021 18:00:54 - INFO - __main__ - Step 27036: {'lr': 0.0004655224179428683, 'samples': 5190912, 'steps': 27035, 'loss/train': 1.7437993288040161} 08/30/2021 18:00:54 - INFO - __main__ - Step 27037: {'lr': 0.00046551972867106106, 'samples': 5191104, 'steps': 27036, 'loss/train': 1.3878881931304932} 08/30/2021 18:00:55 - INFO - __main__ - Step 27038: {'lr': 0.00046551703930214393, 'samples': 5191296, 'steps': 27037, 'loss/train': 1.2605842351913452} 08/30/2021 18:00:56 - INFO - __main__ - Step 27039: {'lr': 0.00046551434983611823, 'samples': 5191488, 'steps': 27038, 'loss/train': 1.619400143623352} 08/30/2021 18:00:57 - INFO - __main__ - Step 27040: {'lr': 0.00046551166027298505, 'samples': 5191680, 'steps': 27039, 'loss/train': 1.4501162767410278} 08/30/2021 18:00:57 - INFO - __main__ - Step 27041: {'lr': 0.0004655089706127456, 'samples': 5191872, 'steps': 27040, 'loss/train': 1.5991936922073364} 08/30/2021 18:00:57 - INFO - __main__ - Step 27042: {'lr': 0.00046550628085540114, 'samples': 5192064, 'steps': 27041, 'loss/train': 1.3747488260269165} 08/30/2021 18:00:58 - INFO - __main__ - Step 27043: {'lr': 0.0004655035910009529, 'samples': 5192256, 'steps': 27042, 'loss/train': 1.0718268156051636} 08/30/2021 18:00:58 - INFO - __main__ - Step 27044: {'lr': 0.00046550090104940207, 'samples': 5192448, 'steps': 27043, 'loss/train': 1.4601668119430542} 08/30/2021 18:00:59 - INFO - __main__ - Step 27045: {'lr': 0.00046549821100074987, 'samples': 5192640, 'steps': 27044, 'loss/train': 1.5553958415985107} 08/30/2021 18:01:00 - INFO - __main__ - Step 27046: {'lr': 0.0004654955208549975, 'samples': 5192832, 'steps': 27045, 'loss/train': 0.8060368895530701} 08/30/2021 18:01:00 - INFO - __main__ - Step 27047: {'lr': 0.0004654928306121461, 'samples': 5193024, 'steps': 27046, 'loss/train': 1.4210699796676636} 08/30/2021 18:01:00 - INFO - __main__ - Step 27048: {'lr': 0.000465490140272197, 'samples': 5193216, 'steps': 27047, 'loss/train': 1.130094289779663} 08/30/2021 18:01:01 - INFO - __main__ - Step 27049: {'lr': 0.00046548744983515133, 'samples': 5193408, 'steps': 27048, 'loss/train': 1.4835467338562012} 08/30/2021 18:01:02 - INFO - __main__ - Step 27050: {'lr': 0.0004654847593010104, 'samples': 5193600, 'steps': 27049, 'loss/train': 1.7109342813491821} 08/30/2021 18:01:03 - INFO - __main__ - Step 27051: {'lr': 0.0004654820686697754, 'samples': 5193792, 'steps': 27050, 'loss/train': 1.5904674530029297} 08/30/2021 18:01:03 - INFO - __main__ - Step 27052: {'lr': 0.00046547937794144743, 'samples': 5193984, 'steps': 27051, 'loss/train': 0.756737470626831} 08/30/2021 18:01:03 - INFO - __main__ - Step 27053: {'lr': 0.00046547668711602774, 'samples': 5194176, 'steps': 27052, 'loss/train': 2.063991069793701} 08/30/2021 18:01:04 - INFO - __main__ - Step 27054: {'lr': 0.0004654739961935177, 'samples': 5194368, 'steps': 27053, 'loss/train': 1.1815845966339111} 08/30/2021 18:01:06 - INFO - __main__ - Step 27055: {'lr': 0.0004654713051739183, 'samples': 5194560, 'steps': 27054, 'loss/train': 1.8301626443862915} 08/30/2021 18:01:06 - INFO - __main__ - Step 27056: {'lr': 0.000465468614057231, 'samples': 5194752, 'steps': 27055, 'loss/train': 1.7003332376480103} 08/30/2021 18:01:06 - INFO - __main__ - Step 27057: {'lr': 0.0004654659228434567, 'samples': 5194944, 'steps': 27056, 'loss/train': 1.5856363773345947} 08/30/2021 18:01:07 - INFO - __main__ - Step 27058: {'lr': 0.00046546323153259686, 'samples': 5195136, 'steps': 27057, 'loss/train': 0.06997363269329071} 08/30/2021 18:01:07 - INFO - __main__ - Step 27059: {'lr': 0.00046546054012465253, 'samples': 5195328, 'steps': 27058, 'loss/train': 1.8706170320510864} 08/30/2021 18:01:09 - INFO - __main__ - Step 27060: {'lr': 0.00046545784861962516, 'samples': 5195520, 'steps': 27059, 'loss/train': 1.5879230499267578} 08/30/2021 18:01:09 - INFO - __main__ - Step 27061: {'lr': 0.00046545515701751567, 'samples': 5195712, 'steps': 27060, 'loss/train': 1.664392113685608} 08/30/2021 18:01:10 - INFO - __main__ - Step 27062: {'lr': 0.00046545246531832547, 'samples': 5195904, 'steps': 27061, 'loss/train': 1.0261359214782715} 08/30/2021 18:01:10 - INFO - __main__ - Step 27063: {'lr': 0.0004654497735220557, 'samples': 5196096, 'steps': 27062, 'loss/train': 1.1374526023864746} 08/30/2021 18:01:10 - INFO - __main__ - Step 27064: {'lr': 0.0004654470816287076, 'samples': 5196288, 'steps': 27063, 'loss/train': 1.4947664737701416} 08/30/2021 18:01:12 - INFO - __main__ - Step 27065: {'lr': 0.0004654443896382824, 'samples': 5196480, 'steps': 27064, 'loss/train': 1.6301007270812988} 08/30/2021 18:01:13 - INFO - __main__ - Step 27066: {'lr': 0.0004654416975507812, 'samples': 5196672, 'steps': 27065, 'loss/train': 1.6354727745056152} 08/30/2021 18:01:13 - INFO - __main__ - Step 27067: {'lr': 0.0004654390053662053, 'samples': 5196864, 'steps': 27066, 'loss/train': 1.7120006084442139} 08/30/2021 18:01:13 - INFO - __main__ - Step 27068: {'lr': 0.000465436313084556, 'samples': 5197056, 'steps': 27067, 'loss/train': 0.16369417309761047} 08/30/2021 18:01:14 - INFO - __main__ - Step 27069: {'lr': 0.0004654336207058344, 'samples': 5197248, 'steps': 27068, 'loss/train': 0.050382111221551895} 08/30/2021 18:01:14 - INFO - __main__ - Step 27070: {'lr': 0.0004654309282300416, 'samples': 5197440, 'steps': 27069, 'loss/train': 1.7151918411254883} 08/30/2021 18:01:16 - INFO - __main__ - Step 27071: {'lr': 0.00046542823565717914, 'samples': 5197632, 'steps': 27070, 'loss/train': 1.1886026859283447} 08/30/2021 18:01:16 - INFO - __main__ - Step 27072: {'lr': 0.00046542554298724793, 'samples': 5197824, 'steps': 27071, 'loss/train': 2.072775363922119} 08/30/2021 18:01:17 - INFO - __main__ - Step 27073: {'lr': 0.00046542285022024935, 'samples': 5198016, 'steps': 27072, 'loss/train': 1.4394422769546509} 08/30/2021 18:01:17 - INFO - __main__ - Step 27074: {'lr': 0.0004654201573561845, 'samples': 5198208, 'steps': 27073, 'loss/train': 1.8477309942245483} 08/30/2021 18:01:17 - INFO - __main__ - Step 27075: {'lr': 0.00046541746439505467, 'samples': 5198400, 'steps': 27074, 'loss/train': 1.052707314491272} 08/30/2021 18:01:19 - INFO - __main__ - Step 27076: {'lr': 0.00046541477133686107, 'samples': 5198592, 'steps': 27075, 'loss/train': 1.182202696800232} 08/30/2021 18:01:19 - INFO - __main__ - Step 27077: {'lr': 0.0004654120781816049, 'samples': 5198784, 'steps': 27076, 'loss/train': 1.7987797260284424} 08/30/2021 18:01:20 - INFO - __main__ - Step 27078: {'lr': 0.00046540938492928735, 'samples': 5198976, 'steps': 27077, 'loss/train': 0.34112757444381714} 08/30/2021 18:01:20 - INFO - __main__ - Step 27079: {'lr': 0.0004654066915799097, 'samples': 5199168, 'steps': 27078, 'loss/train': 1.1117234230041504} 08/30/2021 18:01:20 - INFO - __main__ - Step 27080: {'lr': 0.000465403998133473, 'samples': 5199360, 'steps': 27079, 'loss/train': 1.4834051132202148} 08/30/2021 18:01:22 - INFO - __main__ - Step 27081: {'lr': 0.0004654013045899788, 'samples': 5199552, 'steps': 27080, 'loss/train': 1.434158444404602} 08/30/2021 18:01:22 - INFO - __main__ - Step 27082: {'lr': 0.00046539861094942794, 'samples': 5199744, 'steps': 27081, 'loss/train': 1.2534668445587158} 08/30/2021 18:01:23 - INFO - __main__ - Step 27083: {'lr': 0.00046539591721182175, 'samples': 5199936, 'steps': 27082, 'loss/train': 1.9246628284454346} 08/30/2021 18:01:23 - INFO - __main__ - Step 27084: {'lr': 0.00046539322337716153, 'samples': 5200128, 'steps': 27083, 'loss/train': 3.3916218280792236} 08/30/2021 18:01:23 - INFO - __main__ - Step 27085: {'lr': 0.00046539052944544846, 'samples': 5200320, 'steps': 27084, 'loss/train': 1.1483354568481445} 08/30/2021 18:01:26 - INFO - __main__ - Step 27086: {'lr': 0.0004653878354166838, 'samples': 5200512, 'steps': 27085, 'loss/train': 0.10694511234760284} 08/30/2021 18:01:26 - INFO - __main__ - Step 27087: {'lr': 0.0004653851412908686, 'samples': 5200704, 'steps': 27086, 'loss/train': 1.6052772998809814} 08/30/2021 18:01:27 - INFO - __main__ - Step 27088: {'lr': 0.0004653824470680043, 'samples': 5200896, 'steps': 27087, 'loss/train': 1.2588305473327637} 08/30/2021 18:01:27 - INFO - __main__ - Step 27089: {'lr': 0.00046537975274809186, 'samples': 5201088, 'steps': 27088, 'loss/train': 0.16034357249736786} 08/30/2021 18:01:27 - INFO - __main__ - Step 27090: {'lr': 0.0004653770583311327, 'samples': 5201280, 'steps': 27089, 'loss/train': 1.302323579788208} 08/30/2021 18:01:29 - INFO - __main__ - Step 27091: {'lr': 0.00046537436381712796, 'samples': 5201472, 'steps': 27090, 'loss/train': 1.091360330581665} 08/30/2021 18:01:29 - INFO - __main__ - Step 27092: {'lr': 0.00046537166920607886, 'samples': 5201664, 'steps': 27091, 'loss/train': 1.9743883609771729} 08/30/2021 18:01:30 - INFO - __main__ - Step 27093: {'lr': 0.00046536897449798656, 'samples': 5201856, 'steps': 27092, 'loss/train': 1.6381726264953613} 08/30/2021 18:01:30 - INFO - __main__ - Step 27094: {'lr': 0.00046536627969285236, 'samples': 5202048, 'steps': 27093, 'loss/train': 1.96189546585083} 08/30/2021 18:01:30 - INFO - __main__ - Step 27095: {'lr': 0.0004653635847906774, 'samples': 5202240, 'steps': 27094, 'loss/train': 1.8539103269577026} 08/30/2021 18:01:31 - INFO - __main__ - Step 27096: {'lr': 0.000465360889791463, 'samples': 5202432, 'steps': 27095, 'loss/train': 1.4487504959106445} 08/30/2021 18:01:32 - INFO - __main__ - Step 27097: {'lr': 0.0004653581946952103, 'samples': 5202624, 'steps': 27096, 'loss/train': 2.0275697708129883} 08/30/2021 18:01:33 - INFO - __main__ - Step 27098: {'lr': 0.0004653554995019205, 'samples': 5202816, 'steps': 27097, 'loss/train': 1.635689377784729} 08/30/2021 18:01:33 - INFO - __main__ - Step 27099: {'lr': 0.0004653528042115948, 'samples': 5203008, 'steps': 27098, 'loss/train': 1.2576196193695068} 08/30/2021 18:01:33 - INFO - __main__ - Step 27100: {'lr': 0.0004653501088242345, 'samples': 5203200, 'steps': 27099, 'loss/train': 1.8818833827972412} 08/30/2021 18:01:34 - INFO - __main__ - Step 27101: {'lr': 0.0004653474133398408, 'samples': 5203392, 'steps': 27100, 'loss/train': 1.4839212894439697} 08/30/2021 18:01:35 - INFO - __main__ - Step 27102: {'lr': 0.00046534471775841474, 'samples': 5203584, 'steps': 27101, 'loss/train': 0.7570738196372986} 08/30/2021 18:01:36 - INFO - __main__ - Step 27103: {'lr': 0.0004653420220799578, 'samples': 5203776, 'steps': 27102, 'loss/train': 0.6034243702888489} 08/30/2021 18:01:36 - INFO - __main__ - Step 27104: {'lr': 0.000465339326304471, 'samples': 5203968, 'steps': 27103, 'loss/train': 0.27861687541007996} 08/30/2021 18:01:37 - INFO - __main__ - Step 27105: {'lr': 0.0004653366304319556, 'samples': 5204160, 'steps': 27104, 'loss/train': 1.9334520101547241} 08/30/2021 18:01:37 - INFO - __main__ - Step 27106: {'lr': 0.0004653339344624129, 'samples': 5204352, 'steps': 27105, 'loss/train': 1.6144770383834839} 08/30/2021 18:01:38 - INFO - __main__ - Step 27107: {'lr': 0.00046533123839584406, 'samples': 5204544, 'steps': 27106, 'loss/train': 0.9711307883262634} 08/30/2021 18:01:39 - INFO - __main__ - Step 27108: {'lr': 0.0004653285422322503, 'samples': 5204736, 'steps': 27107, 'loss/train': 2.1607308387756348} 08/30/2021 18:01:39 - INFO - __main__ - Step 27109: {'lr': 0.00046532584597163275, 'samples': 5204928, 'steps': 27108, 'loss/train': 1.4216431379318237} 08/30/2021 18:01:40 - INFO - __main__ - Step 27110: {'lr': 0.0004653231496139927, 'samples': 5205120, 'steps': 27109, 'loss/train': 1.1179980039596558} 08/30/2021 18:01:40 - INFO - __main__ - Step 27111: {'lr': 0.0004653204531593315, 'samples': 5205312, 'steps': 27110, 'loss/train': 1.4066784381866455} 08/30/2021 18:01:42 - INFO - __main__ - Step 27112: {'lr': 0.0004653177566076501, 'samples': 5205504, 'steps': 27111, 'loss/train': 1.4669851064682007} 08/30/2021 18:01:42 - INFO - __main__ - Step 27113: {'lr': 0.0004653150599589498, 'samples': 5205696, 'steps': 27112, 'loss/train': 2.0896048545837402} 08/30/2021 18:01:42 - INFO - __main__ - Step 27114: {'lr': 0.0004653123632132319, 'samples': 5205888, 'steps': 27113, 'loss/train': 2.693441867828369} 08/30/2021 18:01:43 - INFO - __main__ - Step 27115: {'lr': 0.0004653096663704976, 'samples': 5206080, 'steps': 27114, 'loss/train': 1.4360371828079224} 08/30/2021 18:01:43 - INFO - __main__ - Step 27116: {'lr': 0.0004653069694307481, 'samples': 5206272, 'steps': 27115, 'loss/train': 1.2330105304718018} 08/30/2021 18:01:44 - INFO - __main__ - Step 27117: {'lr': 0.00046530427239398453, 'samples': 5206464, 'steps': 27116, 'loss/train': 1.0283563137054443} 08/30/2021 18:01:45 - INFO - __main__ - Step 27118: {'lr': 0.0004653015752602082, 'samples': 5206656, 'steps': 27117, 'loss/train': 1.6964225769042969} 08/30/2021 18:01:45 - INFO - __main__ - Step 27119: {'lr': 0.0004652988780294204, 'samples': 5206848, 'steps': 27118, 'loss/train': 1.095198392868042} 08/30/2021 18:01:46 - INFO - __main__ - Step 27120: {'lr': 0.00046529618070162215, 'samples': 5207040, 'steps': 27119, 'loss/train': 1.318901777267456} 08/30/2021 18:01:46 - INFO - __main__ - Step 27121: {'lr': 0.00046529348327681476, 'samples': 5207232, 'steps': 27120, 'loss/train': 1.682550311088562} 08/30/2021 18:01:46 - INFO - __main__ - Step 27122: {'lr': 0.0004652907857549995, 'samples': 5207424, 'steps': 27121, 'loss/train': 1.5472487211227417} 08/30/2021 18:01:48 - INFO - __main__ - Step 27123: {'lr': 0.0004652880881361775, 'samples': 5207616, 'steps': 27122, 'loss/train': 0.8448706865310669} 08/30/2021 18:01:48 - INFO - __main__ - Step 27124: {'lr': 0.00046528539042035, 'samples': 5207808, 'steps': 27123, 'loss/train': 1.7188612222671509} 08/30/2021 18:01:49 - INFO - __main__ - Step 27125: {'lr': 0.0004652826926075183, 'samples': 5208000, 'steps': 27124, 'loss/train': 1.3044096231460571} 08/30/2021 18:01:49 - INFO - __main__ - Step 27126: {'lr': 0.00046527999469768346, 'samples': 5208192, 'steps': 27125, 'loss/train': 1.2946099042892456} 08/30/2021 18:01:49 - INFO - __main__ - Step 27127: {'lr': 0.0004652772966908468, 'samples': 5208384, 'steps': 27126, 'loss/train': 1.1339104175567627} 08/30/2021 18:01:51 - INFO - __main__ - Step 27128: {'lr': 0.0004652745985870095, 'samples': 5208576, 'steps': 27127, 'loss/train': 1.3347536325454712} 08/30/2021 18:01:51 - INFO - __main__ - Step 27129: {'lr': 0.0004652719003861728, 'samples': 5208768, 'steps': 27128, 'loss/train': 1.338863730430603} 08/30/2021 18:01:52 - INFO - __main__ - Step 27130: {'lr': 0.0004652692020883379, 'samples': 5208960, 'steps': 27129, 'loss/train': 0.1407596915960312} 08/30/2021 18:01:52 - INFO - __main__ - Step 27131: {'lr': 0.00046526650369350605, 'samples': 5209152, 'steps': 27130, 'loss/train': 1.8553941249847412} 08/30/2021 18:01:53 - INFO - __main__ - Step 27132: {'lr': 0.0004652638052016784, 'samples': 5209344, 'steps': 27131, 'loss/train': 1.689576268196106} 08/30/2021 18:01:54 - INFO - __main__ - Step 27133: {'lr': 0.00046526110661285615, 'samples': 5209536, 'steps': 27132, 'loss/train': 1.757028341293335} 08/30/2021 18:01:55 - INFO - __main__ - Step 27134: {'lr': 0.00046525840792704064, 'samples': 5209728, 'steps': 27133, 'loss/train': 2.376382350921631} 08/30/2021 18:01:55 - INFO - __main__ - Step 27135: {'lr': 0.000465255709144233, 'samples': 5209920, 'steps': 27134, 'loss/train': 1.4509390592575073} 08/30/2021 18:01:55 - INFO - __main__ - Step 27136: {'lr': 0.00046525301026443443, 'samples': 5210112, 'steps': 27135, 'loss/train': 1.6816036701202393} 08/30/2021 18:01:56 - INFO - __main__ - Step 27137: {'lr': 0.0004652503112876463, 'samples': 5210304, 'steps': 27136, 'loss/train': 1.2493385076522827} 08/30/2021 18:01:57 - INFO - __main__ - Step 27138: {'lr': 0.00046524761221386956, 'samples': 5210496, 'steps': 27137, 'loss/train': 1.4471927881240845} 08/30/2021 18:01:58 - INFO - __main__ - Step 27139: {'lr': 0.0004652449130431056, 'samples': 5210688, 'steps': 27138, 'loss/train': 1.7560170888900757} 08/30/2021 18:01:58 - INFO - __main__ - Step 27140: {'lr': 0.00046524221377535564, 'samples': 5210880, 'steps': 27139, 'loss/train': 1.0139490365982056} 08/30/2021 18:01:58 - INFO - __main__ - Step 27141: {'lr': 0.00046523951441062087, 'samples': 5211072, 'steps': 27140, 'loss/train': 1.6119662523269653} 08/30/2021 18:01:59 - INFO - __main__ - Step 27142: {'lr': 0.0004652368149489024, 'samples': 5211264, 'steps': 27141, 'loss/train': 1.7705886363983154} 08/30/2021 18:02:01 - INFO - __main__ - Step 27143: {'lr': 0.0004652341153902016, 'samples': 5211456, 'steps': 27142, 'loss/train': 1.0436846017837524} 08/30/2021 18:02:01 - INFO - __main__ - Step 27144: {'lr': 0.00046523141573451965, 'samples': 5211648, 'steps': 27143, 'loss/train': 0.8901267051696777} 08/30/2021 18:02:02 - INFO - __main__ - Step 27145: {'lr': 0.0004652287159818577, 'samples': 5211840, 'steps': 27144, 'loss/train': 1.3173696994781494} 08/30/2021 18:02:02 - INFO - __main__ - Step 27146: {'lr': 0.00046522601613221704, 'samples': 5212032, 'steps': 27145, 'loss/train': 1.683090329170227} 08/30/2021 18:02:02 - INFO - __main__ - Step 27147: {'lr': 0.0004652233161855989, 'samples': 5212224, 'steps': 27146, 'loss/train': 1.6737595796585083} 08/30/2021 18:02:04 - INFO - __main__ - Step 27148: {'lr': 0.0004652206161420044, 'samples': 5212416, 'steps': 27147, 'loss/train': 1.9634326696395874} 08/30/2021 18:02:04 - INFO - __main__ - Step 27149: {'lr': 0.00046521791600143483, 'samples': 5212608, 'steps': 27148, 'loss/train': 1.0778173208236694} 08/30/2021 18:02:05 - INFO - __main__ - Step 27150: {'lr': 0.00046521521576389134, 'samples': 5212800, 'steps': 27149, 'loss/train': 1.6184779405593872} 08/30/2021 18:02:05 - INFO - __main__ - Step 27151: {'lr': 0.00046521251542937524, 'samples': 5212992, 'steps': 27150, 'loss/train': 1.2396254539489746} 08/30/2021 18:02:05 - INFO - __main__ - Step 27152: {'lr': 0.0004652098149978877, 'samples': 5213184, 'steps': 27151, 'loss/train': 1.4671834707260132} 08/30/2021 18:02:06 - INFO - __main__ - Step 27153: {'lr': 0.00046520711446943, 'samples': 5213376, 'steps': 27152, 'loss/train': 1.4779397249221802} 08/30/2021 18:02:07 - INFO - __main__ - Step 27154: {'lr': 0.0004652044138440032, 'samples': 5213568, 'steps': 27153, 'loss/train': 1.2149711847305298} 08/30/2021 18:02:08 - INFO - __main__ - Step 27155: {'lr': 0.00046520171312160863, 'samples': 5213760, 'steps': 27154, 'loss/train': 1.5334635972976685} 08/30/2021 18:02:08 - INFO - __main__ - Step 27156: {'lr': 0.00046519901230224756, 'samples': 5213952, 'steps': 27155, 'loss/train': 1.6847068071365356} 08/30/2021 18:02:08 - INFO - __main__ - Step 27157: {'lr': 0.000465196311385921, 'samples': 5214144, 'steps': 27156, 'loss/train': 1.1634342670440674} 08/30/2021 18:02:09 - INFO - __main__ - Step 27158: {'lr': 0.0004651936103726304, 'samples': 5214336, 'steps': 27157, 'loss/train': 1.6953181028366089} 08/30/2021 18:02:10 - INFO - __main__ - Step 27159: {'lr': 0.0004651909092623769, 'samples': 5214528, 'steps': 27158, 'loss/train': 1.682037115097046} 08/30/2021 18:02:11 - INFO - __main__ - Step 27160: {'lr': 0.00046518820805516165, 'samples': 5214720, 'steps': 27159, 'loss/train': 2.1666359901428223} 08/30/2021 18:02:11 - INFO - __main__ - Step 27161: {'lr': 0.0004651855067509859, 'samples': 5214912, 'steps': 27160, 'loss/train': 0.923642635345459} 08/30/2021 18:02:11 - INFO - __main__ - Step 27162: {'lr': 0.0004651828053498509, 'samples': 5215104, 'steps': 27161, 'loss/train': 0.15039899945259094} 08/30/2021 18:02:12 - INFO - __main__ - Step 27163: {'lr': 0.0004651801038517579, 'samples': 5215296, 'steps': 27162, 'loss/train': 1.6620742082595825} 08/30/2021 18:02:13 - INFO - __main__ - Step 27164: {'lr': 0.000465177402256708, 'samples': 5215488, 'steps': 27163, 'loss/train': 1.2420668601989746} 08/30/2021 18:02:14 - INFO - __main__ - Step 27165: {'lr': 0.00046517470056470244, 'samples': 5215680, 'steps': 27164, 'loss/train': 1.8143824338912964} 08/30/2021 18:02:14 - INFO - __main__ - Step 27166: {'lr': 0.00046517199877574257, 'samples': 5215872, 'steps': 27165, 'loss/train': 1.2720283269882202} 08/30/2021 18:02:14 - INFO - __main__ - Step 27167: {'lr': 0.0004651692968898295, 'samples': 5216064, 'steps': 27166, 'loss/train': 1.4383347034454346} 08/30/2021 18:02:15 - INFO - __main__ - Step 27168: {'lr': 0.00046516659490696444, 'samples': 5216256, 'steps': 27167, 'loss/train': 1.142825722694397} 08/30/2021 18:02:16 - INFO - __main__ - Step 27169: {'lr': 0.0004651638928271487, 'samples': 5216448, 'steps': 27168, 'loss/train': 1.1730382442474365} 08/30/2021 18:02:17 - INFO - __main__ - Step 27170: {'lr': 0.00046516119065038335, 'samples': 5216640, 'steps': 27169, 'loss/train': 1.4490641355514526} 08/30/2021 18:02:17 - INFO - __main__ - Step 27171: {'lr': 0.00046515848837666975, 'samples': 5216832, 'steps': 27170, 'loss/train': 1.3089524507522583} 08/30/2021 18:02:17 - INFO - __main__ - Step 27172: {'lr': 0.00046515578600600895, 'samples': 5217024, 'steps': 27171, 'loss/train': 1.6375516653060913} 08/30/2021 18:02:18 - INFO - __main__ - Step 27173: {'lr': 0.0004651530835384024, 'samples': 5217216, 'steps': 27172, 'loss/train': 0.993874192237854} 08/30/2021 18:02:20 - INFO - __main__ - Step 27174: {'lr': 0.0004651503809738511, 'samples': 5217408, 'steps': 27173, 'loss/train': 1.8553403615951538} 08/30/2021 18:02:20 - INFO - __main__ - Step 27175: {'lr': 0.0004651476783123564, 'samples': 5217600, 'steps': 27174, 'loss/train': 0.7931986451148987} 08/30/2021 18:02:20 - INFO - __main__ - Step 27176: {'lr': 0.00046514497555391946, 'samples': 5217792, 'steps': 27175, 'loss/train': 1.2725205421447754} 08/30/2021 18:02:21 - INFO - __main__ - Step 27177: {'lr': 0.0004651422726985415, 'samples': 5217984, 'steps': 27176, 'loss/train': 1.2557040452957153} 08/30/2021 18:02:21 - INFO - __main__ - Step 27178: {'lr': 0.00046513956974622377, 'samples': 5218176, 'steps': 27177, 'loss/train': 1.3666027784347534} 08/30/2021 18:02:21 - INFO - __main__ - Step 27179: {'lr': 0.00046513686669696756, 'samples': 5218368, 'steps': 27178, 'loss/train': 1.3838618993759155} 08/30/2021 18:02:23 - INFO - __main__ - Step 27180: {'lr': 0.00046513416355077386, 'samples': 5218560, 'steps': 27179, 'loss/train': 0.4842136800289154} 08/30/2021 18:02:23 - INFO - __main__ - Step 27181: {'lr': 0.0004651314603076441, 'samples': 5218752, 'steps': 27180, 'loss/train': 0.9858081936836243} 08/30/2021 18:02:24 - INFO - __main__ - Step 27182: {'lr': 0.00046512875696757937, 'samples': 5218944, 'steps': 27181, 'loss/train': 1.5500998497009277} 08/30/2021 18:02:24 - INFO - __main__ - Step 27183: {'lr': 0.00046512605353058096, 'samples': 5219136, 'steps': 27182, 'loss/train': 1.9521722793579102} 08/30/2021 18:02:24 - INFO - __main__ - Step 27184: {'lr': 0.00046512334999665006, 'samples': 5219328, 'steps': 27183, 'loss/train': 1.0258973836898804} 08/30/2021 18:02:26 - INFO - __main__ - Step 27185: {'lr': 0.000465120646365788, 'samples': 5219520, 'steps': 27184, 'loss/train': 1.4164693355560303} 08/30/2021 18:02:26 - INFO - __main__ - Step 27186: {'lr': 0.0004651179426379958, 'samples': 5219712, 'steps': 27185, 'loss/train': 1.3320482969284058} 08/30/2021 18:02:27 - INFO - __main__ - Step 27187: {'lr': 0.00046511523881327476, 'samples': 5219904, 'steps': 27186, 'loss/train': 1.5076208114624023} 08/30/2021 18:02:27 - INFO - __main__ - Step 27188: {'lr': 0.00046511253489162616, 'samples': 5220096, 'steps': 27187, 'loss/train': 1.540059208869934} 08/30/2021 18:02:27 - INFO - __main__ - Step 27189: {'lr': 0.00046510983087305114, 'samples': 5220288, 'steps': 27188, 'loss/train': 1.2916322946548462} 08/30/2021 18:02:29 - INFO - __main__ - Step 27190: {'lr': 0.00046510712675755094, 'samples': 5220480, 'steps': 27189, 'loss/train': 1.959316611289978} 08/30/2021 18:02:29 - INFO - __main__ - Step 27191: {'lr': 0.00046510442254512686, 'samples': 5220672, 'steps': 27190, 'loss/train': 1.4867103099822998} 08/30/2021 18:02:30 - INFO - __main__ - Step 27192: {'lr': 0.00046510171823578, 'samples': 5220864, 'steps': 27191, 'loss/train': 1.876558542251587} 08/30/2021 18:02:30 - INFO - __main__ - Step 27193: {'lr': 0.0004650990138295116, 'samples': 5221056, 'steps': 27192, 'loss/train': 1.6605374813079834} 08/30/2021 18:02:30 - INFO - __main__ - Step 27194: {'lr': 0.00046509630932632293, 'samples': 5221248, 'steps': 27193, 'loss/train': 1.2944283485412598} 08/30/2021 18:02:31 - INFO - __main__ - Step 27195: {'lr': 0.0004650936047262152, 'samples': 5221440, 'steps': 27194, 'loss/train': 1.754934310913086} 08/30/2021 18:02:33 - INFO - __main__ - Step 27196: {'lr': 0.0004650909000291895, 'samples': 5221632, 'steps': 27195, 'loss/train': 0.21176883578300476} 08/30/2021 18:02:33 - INFO - __main__ - Step 27197: {'lr': 0.00046508819523524724, 'samples': 5221824, 'steps': 27196, 'loss/train': 1.88222336769104} 08/30/2021 18:02:33 - INFO - __main__ - Step 27198: {'lr': 0.0004650854903443896, 'samples': 5222016, 'steps': 27197, 'loss/train': 1.7587685585021973} 08/30/2021 18:02:34 - INFO - __main__ - Step 27199: {'lr': 0.00046508278535661775, 'samples': 5222208, 'steps': 27198, 'loss/train': 1.02782142162323} 08/30/2021 18:02:34 - INFO - __main__ - Step 27200: {'lr': 0.00046508008027193286, 'samples': 5222400, 'steps': 27199, 'loss/train': 1.965057373046875} 08/30/2021 18:02:36 - INFO - __main__ - Step 27201: {'lr': 0.0004650773750903363, 'samples': 5222592, 'steps': 27200, 'loss/train': 1.212222695350647} 08/30/2021 18:02:36 - INFO - __main__ - Step 27202: {'lr': 0.0004650746698118291, 'samples': 5222784, 'steps': 27201, 'loss/train': 1.7200069427490234} 08/30/2021 18:02:36 - INFO - __main__ - Step 27203: {'lr': 0.0004650719644364126, 'samples': 5222976, 'steps': 27202, 'loss/train': 1.4639238119125366} 08/30/2021 18:02:37 - INFO - __main__ - Step 27204: {'lr': 0.000465069258964088, 'samples': 5223168, 'steps': 27203, 'loss/train': 1.1928578615188599} 08/30/2021 18:02:37 - INFO - __main__ - Step 27205: {'lr': 0.0004650665533948565, 'samples': 5223360, 'steps': 27204, 'loss/train': 1.671126127243042} 08/30/2021 18:02:39 - INFO - __main__ - Step 27206: {'lr': 0.00046506384772871935, 'samples': 5223552, 'steps': 27205, 'loss/train': 1.2450087070465088} 08/30/2021 18:02:39 - INFO - __main__ - Step 27207: {'lr': 0.0004650611419656777, 'samples': 5223744, 'steps': 27206, 'loss/train': 1.1245115995407104} 08/30/2021 18:02:39 - INFO - __main__ - Step 27208: {'lr': 0.0004650584361057328, 'samples': 5223936, 'steps': 27207, 'loss/train': 0.17484788596630096} 08/30/2021 18:02:40 - INFO - __main__ - Step 27209: {'lr': 0.00046505573014888604, 'samples': 5224128, 'steps': 27208, 'loss/train': 1.763199806213379} 08/30/2021 18:02:40 - INFO - __main__ - Step 27210: {'lr': 0.0004650530240951383, 'samples': 5224320, 'steps': 27209, 'loss/train': 1.5048365592956543} 08/30/2021 18:02:42 - INFO - __main__ - Step 27211: {'lr': 0.0004650503179444911, 'samples': 5224512, 'steps': 27210, 'loss/train': 1.3131428956985474} 08/30/2021 18:02:42 - INFO - __main__ - Step 27212: {'lr': 0.00046504761169694555, 'samples': 5224704, 'steps': 27211, 'loss/train': 1.455526351928711} 08/30/2021 18:02:42 - INFO - __main__ - Step 27213: {'lr': 0.0004650449053525028, 'samples': 5224896, 'steps': 27212, 'loss/train': 1.5415327548980713} 08/30/2021 18:02:43 - INFO - __main__ - Step 27214: {'lr': 0.00046504219891116416, 'samples': 5225088, 'steps': 27213, 'loss/train': 1.2887331247329712} 08/30/2021 18:02:43 - INFO - __main__ - Step 27215: {'lr': 0.0004650394923729309, 'samples': 5225280, 'steps': 27214, 'loss/train': 1.2204267978668213} 08/30/2021 18:02:45 - INFO - __main__ - Step 27216: {'lr': 0.00046503678573780403, 'samples': 5225472, 'steps': 27215, 'loss/train': 1.389278531074524} 08/30/2021 18:02:45 - INFO - __main__ - Step 27217: {'lr': 0.000465034079005785, 'samples': 5225664, 'steps': 27216, 'loss/train': 2.055776596069336} 08/30/2021 18:02:46 - INFO - __main__ - Step 27218: {'lr': 0.00046503137217687485, 'samples': 5225856, 'steps': 27217, 'loss/train': 0.0949811041355133} 08/30/2021 18:02:46 - INFO - __main__ - Step 27219: {'lr': 0.0004650286652510749, 'samples': 5226048, 'steps': 27218, 'loss/train': 1.3490337133407593} 08/30/2021 18:02:46 - INFO - __main__ - Step 27220: {'lr': 0.0004650259582283864, 'samples': 5226240, 'steps': 27219, 'loss/train': 1.026698112487793} 08/30/2021 18:02:48 - INFO - __main__ - Step 27221: {'lr': 0.0004650232511088105, 'samples': 5226432, 'steps': 27220, 'loss/train': 1.5688090324401855} 08/30/2021 18:02:48 - INFO - __main__ - Step 27222: {'lr': 0.00046502054389234844, 'samples': 5226624, 'steps': 27221, 'loss/train': 1.7997719049453735} 08/30/2021 18:02:49 - INFO - __main__ - Step 27223: {'lr': 0.0004650178365790014, 'samples': 5226816, 'steps': 27222, 'loss/train': 0.0738530382514} 08/30/2021 18:02:49 - INFO - __main__ - Step 27224: {'lr': 0.0004650151291687707, 'samples': 5227008, 'steps': 27223, 'loss/train': 1.3296082019805908} 08/30/2021 18:02:49 - INFO - __main__ - Step 27225: {'lr': 0.00046501242166165747, 'samples': 5227200, 'steps': 27224, 'loss/train': 1.095910906791687} 08/30/2021 18:02:51 - INFO - __main__ - Step 27226: {'lr': 0.000465009714057663, 'samples': 5227392, 'steps': 27225, 'loss/train': 1.1816964149475098} 08/30/2021 18:02:51 - INFO - __main__ - Step 27227: {'lr': 0.00046500700635678844, 'samples': 5227584, 'steps': 27226, 'loss/train': 1.519883155822754} 08/30/2021 18:02:52 - INFO - __main__ - Step 27228: {'lr': 0.000465004298559035, 'samples': 5227776, 'steps': 27227, 'loss/train': 1.5541470050811768} 08/30/2021 18:02:52 - INFO - __main__ - Step 27229: {'lr': 0.00046500159066440404, 'samples': 5227968, 'steps': 27228, 'loss/train': 1.4665356874465942} 08/30/2021 18:02:52 - INFO - __main__ - Step 27230: {'lr': 0.0004649988826728966, 'samples': 5228160, 'steps': 27229, 'loss/train': 0.8733643889427185} 08/30/2021 18:02:53 - INFO - __main__ - Step 27231: {'lr': 0.000464996174584514, 'samples': 5228352, 'steps': 27230, 'loss/train': 1.6681219339370728} 08/30/2021 18:02:54 - INFO - __main__ - Step 27232: {'lr': 0.00046499346639925746, 'samples': 5228544, 'steps': 27231, 'loss/train': 1.3323636054992676} 08/30/2021 18:02:55 - INFO - __main__ - Step 27233: {'lr': 0.0004649907581171282, 'samples': 5228736, 'steps': 27232, 'loss/train': 1.2746250629425049} 08/30/2021 18:02:55 - INFO - __main__ - Step 27234: {'lr': 0.00046498804973812735, 'samples': 5228928, 'steps': 27233, 'loss/train': 1.0236037969589233} 08/30/2021 18:02:56 - INFO - __main__ - Step 27235: {'lr': 0.00046498534126225625, 'samples': 5229120, 'steps': 27234, 'loss/train': 1.393905520439148} 08/30/2021 18:02:56 - INFO - __main__ - Step 27236: {'lr': 0.0004649826326895161, 'samples': 5229312, 'steps': 27235, 'loss/train': 1.0438834428787231} 08/30/2021 18:02:57 - INFO - __main__ - Step 27237: {'lr': 0.0004649799240199081, 'samples': 5229504, 'steps': 27236, 'loss/train': 0.7269102931022644} 08/30/2021 18:02:58 - INFO - __main__ - Step 27238: {'lr': 0.0004649772152534334, 'samples': 5229696, 'steps': 27237, 'loss/train': 1.5188666582107544} 08/30/2021 18:02:58 - INFO - __main__ - Step 27239: {'lr': 0.0004649745063900933, 'samples': 5229888, 'steps': 27238, 'loss/train': 1.9725725650787354} 08/30/2021 18:02:58 - INFO - __main__ - Step 27240: {'lr': 0.000464971797429889, 'samples': 5230080, 'steps': 27239, 'loss/train': 1.210260033607483} 08/30/2021 18:02:59 - INFO - __main__ - Step 27241: {'lr': 0.00046496908837282173, 'samples': 5230272, 'steps': 27240, 'loss/train': 1.168676495552063} 08/30/2021 18:03:00 - INFO - __main__ - Step 27242: {'lr': 0.00046496637921889276, 'samples': 5230464, 'steps': 27241, 'loss/train': 1.859948992729187} 08/30/2021 18:03:01 - INFO - __main__ - Step 27243: {'lr': 0.0004649636699681031, 'samples': 5230656, 'steps': 27242, 'loss/train': 1.5435638427734375} 08/30/2021 18:03:01 - INFO - __main__ - Step 27244: {'lr': 0.00046496096062045427, 'samples': 5230848, 'steps': 27243, 'loss/train': 1.488871693611145} 08/30/2021 18:03:02 - INFO - __main__ - Step 27245: {'lr': 0.00046495825117594735, 'samples': 5231040, 'steps': 27244, 'loss/train': 1.4715319871902466} 08/30/2021 18:03:02 - INFO - __main__ - Step 27246: {'lr': 0.0004649555416345835, 'samples': 5231232, 'steps': 27245, 'loss/train': 1.8495218753814697} 08/30/2021 18:03:04 - INFO - __main__ - Step 27247: {'lr': 0.0004649528319963641, 'samples': 5231424, 'steps': 27246, 'loss/train': 1.6618481874465942} 08/30/2021 18:03:04 - INFO - __main__ - Step 27248: {'lr': 0.0004649501222612901, 'samples': 5231616, 'steps': 27247, 'loss/train': 1.2079572677612305} 08/30/2021 18:03:05 - INFO - __main__ - Step 27249: {'lr': 0.000464947412429363, 'samples': 5231808, 'steps': 27248, 'loss/train': 1.9796838760375977} 08/30/2021 18:03:05 - INFO - __main__ - Step 27250: {'lr': 0.000464944702500584, 'samples': 5232000, 'steps': 27249, 'loss/train': 1.690522313117981} 08/30/2021 18:03:05 - INFO - __main__ - Step 27251: {'lr': 0.0004649419924749541, 'samples': 5232192, 'steps': 27250, 'loss/train': 1.7213099002838135} 08/30/2021 18:03:06 - INFO - __main__ - Step 27252: {'lr': 0.0004649392823524746, 'samples': 5232384, 'steps': 27251, 'loss/train': 0.9100295901298523} 08/30/2021 18:03:07 - INFO - __main__ - Step 27253: {'lr': 0.0004649365721331469, 'samples': 5232576, 'steps': 27252, 'loss/train': 1.5809015035629272} 08/30/2021 18:03:08 - INFO - __main__ - Step 27254: {'lr': 0.00046493386181697206, 'samples': 5232768, 'steps': 27253, 'loss/train': 1.7417445182800293} 08/30/2021 18:03:08 - INFO - __main__ - Step 27255: {'lr': 0.00046493115140395136, 'samples': 5232960, 'steps': 27254, 'loss/train': 1.5555888414382935} 08/30/2021 18:03:08 - INFO - __main__ - Step 27256: {'lr': 0.000464928440894086, 'samples': 5233152, 'steps': 27255, 'loss/train': 1.2720096111297607} 08/30/2021 18:03:09 - INFO - __main__ - Step 27257: {'lr': 0.00046492573028737716, 'samples': 5233344, 'steps': 27256, 'loss/train': 1.5129177570343018} 08/30/2021 18:03:10 - INFO - __main__ - Step 27258: {'lr': 0.0004649230195838261, 'samples': 5233536, 'steps': 27257, 'loss/train': 1.2692806720733643} 08/30/2021 18:03:11 - INFO - __main__ - Step 27259: {'lr': 0.00046492030878343406, 'samples': 5233728, 'steps': 27258, 'loss/train': 1.562685251235962} 08/30/2021 18:03:11 - INFO - __main__ - Step 27260: {'lr': 0.00046491759788620227, 'samples': 5233920, 'steps': 27259, 'loss/train': 1.3309409618377686} 08/30/2021 18:03:12 - INFO - __main__ - Step 27261: {'lr': 0.0004649148868921319, 'samples': 5234112, 'steps': 27260, 'loss/train': 1.4846631288528442} 08/30/2021 18:03:12 - INFO - __main__ - Step 27262: {'lr': 0.00046491217580122427, 'samples': 5234304, 'steps': 27261, 'loss/train': 1.4535695314407349} 08/30/2021 18:03:14 - INFO - __main__ - Step 27263: {'lr': 0.00046490946461348045, 'samples': 5234496, 'steps': 27262, 'loss/train': 0.7473717927932739} 08/30/2021 18:03:14 - INFO - __main__ - Step 27264: {'lr': 0.00046490675332890177, 'samples': 5234688, 'steps': 27263, 'loss/train': 0.19532035291194916} 08/30/2021 18:03:14 - INFO - __main__ - Step 27265: {'lr': 0.00046490404194748935, 'samples': 5234880, 'steps': 27264, 'loss/train': 1.9025545120239258} 08/30/2021 18:03:15 - INFO - __main__ - Step 27266: {'lr': 0.00046490133046924457, 'samples': 5235072, 'steps': 27265, 'loss/train': 0.9349351525306702} 08/30/2021 18:03:15 - INFO - __main__ - Step 27267: {'lr': 0.0004648986188941685, 'samples': 5235264, 'steps': 27266, 'loss/train': 0.78515625} 08/30/2021 18:03:16 - INFO - __main__ - Step 27268: {'lr': 0.0004648959072222625, 'samples': 5235456, 'steps': 27267, 'loss/train': 1.3551311492919922} 08/30/2021 18:03:17 - INFO - __main__ - Step 27269: {'lr': 0.0004648931954535277, 'samples': 5235648, 'steps': 27268, 'loss/train': 1.1315070390701294} 08/30/2021 18:03:17 - INFO - __main__ - Step 27270: {'lr': 0.0004648904835879654, 'samples': 5235840, 'steps': 27269, 'loss/train': 1.0739414691925049} 08/30/2021 18:03:18 - INFO - __main__ - Step 27271: {'lr': 0.0004648877716255766, 'samples': 5236032, 'steps': 27270, 'loss/train': 1.052010178565979} 08/30/2021 18:03:18 - INFO - __main__ - Step 27272: {'lr': 0.00046488505956636286, 'samples': 5236224, 'steps': 27271, 'loss/train': 0.9770748019218445} 08/30/2021 18:03:20 - INFO - __main__ - Step 27273: {'lr': 0.0004648823474103251, 'samples': 5236416, 'steps': 27272, 'loss/train': 1.6778689622879028} 08/30/2021 18:03:20 - INFO - __main__ - Step 27274: {'lr': 0.0004648796351574648, 'samples': 5236608, 'steps': 27273, 'loss/train': 1.8462250232696533} 08/30/2021 18:03:20 - INFO - __main__ - Step 27275: {'lr': 0.0004648769228077829, 'samples': 5236800, 'steps': 27274, 'loss/train': 1.6655688285827637} 08/30/2021 18:03:21 - INFO - __main__ - Step 27276: {'lr': 0.00046487421036128085, 'samples': 5236992, 'steps': 27275, 'loss/train': 1.4138898849487305} 08/30/2021 18:03:21 - INFO - __main__ - Step 27277: {'lr': 0.00046487149781795976, 'samples': 5237184, 'steps': 27276, 'loss/train': 0.10334265977144241} 08/30/2021 18:03:21 - INFO - __main__ - Step 27278: {'lr': 0.00046486878517782094, 'samples': 5237376, 'steps': 27277, 'loss/train': 1.682212471961975} 08/30/2021 18:03:23 - INFO - __main__ - Step 27279: {'lr': 0.0004648660724408656, 'samples': 5237568, 'steps': 27278, 'loss/train': 1.694521427154541} 08/30/2021 18:03:23 - INFO - __main__ - Step 27280: {'lr': 0.00046486335960709485, 'samples': 5237760, 'steps': 27279, 'loss/train': 1.7350554466247559} 08/30/2021 18:03:24 - INFO - __main__ - Step 27281: {'lr': 0.00046486064667651, 'samples': 5237952, 'steps': 27280, 'loss/train': 1.4675053358078003} 08/30/2021 18:03:24 - INFO - __main__ - Step 27282: {'lr': 0.0004648579336491123, 'samples': 5238144, 'steps': 27281, 'loss/train': 1.6293554306030273} 08/30/2021 18:03:24 - INFO - __main__ - Step 27283: {'lr': 0.0004648552205249029, 'samples': 5238336, 'steps': 27282, 'loss/train': 1.2510106563568115} 08/30/2021 18:03:26 - INFO - __main__ - Step 27284: {'lr': 0.000464852507303883, 'samples': 5238528, 'steps': 27283, 'loss/train': 2.3260385990142822} 08/30/2021 18:03:26 - INFO - __main__ - Step 27285: {'lr': 0.0004648497939860539, 'samples': 5238720, 'steps': 27284, 'loss/train': 1.5813488960266113} 08/30/2021 18:03:27 - INFO - __main__ - Step 27286: {'lr': 0.0004648470805714169, 'samples': 5238912, 'steps': 27285, 'loss/train': 1.4133464097976685} 08/30/2021 18:03:27 - INFO - __main__ - Step 27287: {'lr': 0.00046484436705997303, 'samples': 5239104, 'steps': 27286, 'loss/train': 1.6518265008926392} 08/30/2021 18:03:27 - INFO - __main__ - Step 27288: {'lr': 0.0004648416534517236, 'samples': 5239296, 'steps': 27287, 'loss/train': 1.3845692873001099} 08/30/2021 18:03:29 - INFO - __main__ - Step 27289: {'lr': 0.00046483893974666983, 'samples': 5239488, 'steps': 27288, 'loss/train': 3.8499529361724854} 08/30/2021 18:03:30 - INFO - __main__ - Step 27290: {'lr': 0.000464836225944813, 'samples': 5239680, 'steps': 27289, 'loss/train': 2.0362470149993896} 08/30/2021 18:03:30 - INFO - __main__ - Step 27291: {'lr': 0.00046483351204615423, 'samples': 5239872, 'steps': 27290, 'loss/train': 1.3258978128433228} 08/30/2021 18:03:30 - INFO - __main__ - Step 27292: {'lr': 0.0004648307980506948, 'samples': 5240064, 'steps': 27291, 'loss/train': 1.7532356977462769} 08/30/2021 18:03:31 - INFO - __main__ - Step 27293: {'lr': 0.00046482808395843594, 'samples': 5240256, 'steps': 27292, 'loss/train': 0.10539980977773666} 08/30/2021 18:03:31 - INFO - __main__ - Step 27294: {'lr': 0.0004648253697693789, 'samples': 5240448, 'steps': 27293, 'loss/train': 0.046046182513237} 08/30/2021 18:03:32 - INFO - __main__ - Step 27295: {'lr': 0.0004648226554835248, 'samples': 5240640, 'steps': 27294, 'loss/train': 1.7988481521606445} 08/30/2021 18:03:33 - INFO - __main__ - Step 27296: {'lr': 0.000464819941100875, 'samples': 5240832, 'steps': 27295, 'loss/train': 1.3836617469787598} 08/30/2021 18:03:33 - INFO - __main__ - Step 27297: {'lr': 0.00046481722662143057, 'samples': 5241024, 'steps': 27296, 'loss/train': 1.6231448650360107} 08/30/2021 18:03:34 - INFO - __main__ - Step 27298: {'lr': 0.0004648145120451929, 'samples': 5241216, 'steps': 27297, 'loss/train': 1.3917350769042969} 08/30/2021 18:03:34 - INFO - __main__ - Step 27299: {'lr': 0.000464811797372163, 'samples': 5241408, 'steps': 27298, 'loss/train': 1.4628976583480835} 08/30/2021 18:03:36 - INFO - __main__ - Step 27300: {'lr': 0.00046480908260234234, 'samples': 5241600, 'steps': 27299, 'loss/train': 1.3640955686569214} 08/30/2021 18:03:36 - INFO - __main__ - Step 27301: {'lr': 0.0004648063677357319, 'samples': 5241792, 'steps': 27300, 'loss/train': 0.8540429472923279} 08/30/2021 18:03:36 - INFO - __main__ - Step 27302: {'lr': 0.00046480365277233316, 'samples': 5241984, 'steps': 27301, 'loss/train': 1.4378702640533447} 08/30/2021 18:03:37 - INFO - __main__ - Step 27303: {'lr': 0.00046480093771214716, 'samples': 5242176, 'steps': 27302, 'loss/train': 1.3795442581176758} 08/30/2021 18:03:37 - INFO - __main__ - Step 27304: {'lr': 0.0004647982225551751, 'samples': 5242368, 'steps': 27303, 'loss/train': 1.8644474744796753} 08/30/2021 18:03:39 - INFO - __main__ - Step 27305: {'lr': 0.0004647955073014184, 'samples': 5242560, 'steps': 27304, 'loss/train': 1.4457502365112305} 08/30/2021 18:03:39 - INFO - __main__ - Step 27306: {'lr': 0.00046479279195087804, 'samples': 5242752, 'steps': 27305, 'loss/train': 0.8158540725708008} 08/30/2021 18:03:40 - INFO - __main__ - Step 27307: {'lr': 0.0004647900765035554, 'samples': 5242944, 'steps': 27306, 'loss/train': 1.3061364889144897} 08/30/2021 18:03:40 - INFO - __main__ - Step 27308: {'lr': 0.0004647873609594517, 'samples': 5243136, 'steps': 27307, 'loss/train': 1.8341137170791626} 08/30/2021 18:03:40 - INFO - __main__ - Step 27309: {'lr': 0.0004647846453185681, 'samples': 5243328, 'steps': 27308, 'loss/train': 1.4347705841064453} 08/30/2021 18:03:42 - INFO - __main__ - Step 27310: {'lr': 0.0004647819295809059, 'samples': 5243520, 'steps': 27309, 'loss/train': 1.2835569381713867} 08/30/2021 18:03:43 - INFO - __main__ - Step 27311: {'lr': 0.00046477921374646624, 'samples': 5243712, 'steps': 27310, 'loss/train': 1.5727505683898926} 08/30/2021 18:03:43 - INFO - __main__ - Step 27312: {'lr': 0.0004647764978152503, 'samples': 5243904, 'steps': 27311, 'loss/train': 1.3658605813980103} 08/30/2021 18:03:43 - INFO - __main__ - Step 27313: {'lr': 0.0004647737817872595, 'samples': 5244096, 'steps': 27312, 'loss/train': 0.8591522574424744} 08/30/2021 18:03:44 - INFO - __main__ - Step 27314: {'lr': 0.0004647710656624949, 'samples': 5244288, 'steps': 27313, 'loss/train': 1.8187135457992554} 08/30/2021 18:03:45 - INFO - __main__ - Step 27315: {'lr': 0.0004647683494409578, 'samples': 5244480, 'steps': 27314, 'loss/train': 1.6067172288894653} 08/30/2021 18:03:45 - INFO - __main__ - Step 27316: {'lr': 0.0004647656331226494, 'samples': 5244672, 'steps': 27315, 'loss/train': 1.51498281955719} 08/30/2021 18:03:46 - INFO - __main__ - Step 27317: {'lr': 0.0004647629167075709, 'samples': 5244864, 'steps': 27316, 'loss/train': 1.5694047212600708} 08/30/2021 18:03:46 - INFO - __main__ - Step 27318: {'lr': 0.00046476020019572354, 'samples': 5245056, 'steps': 27317, 'loss/train': 1.5925524234771729} 08/30/2021 18:03:46 - INFO - __main__ - Step 27319: {'lr': 0.00046475748358710856, 'samples': 5245248, 'steps': 27318, 'loss/train': 1.0620713233947754} 08/30/2021 18:03:47 - INFO - __main__ - Step 27320: {'lr': 0.0004647547668817271, 'samples': 5245440, 'steps': 27319, 'loss/train': 1.2808213233947754} 08/30/2021 18:03:49 - INFO - __main__ - Step 27321: {'lr': 0.00046475205007958054, 'samples': 5245632, 'steps': 27320, 'loss/train': 1.625947117805481} 08/30/2021 18:03:49 - INFO - __main__ - Step 27322: {'lr': 0.00046474933318067004, 'samples': 5245824, 'steps': 27321, 'loss/train': 1.7700499296188354} 08/30/2021 18:03:49 - INFO - __main__ - Step 27323: {'lr': 0.0004647466161849968, 'samples': 5246016, 'steps': 27322, 'loss/train': 1.7060738801956177} 08/30/2021 18:03:50 - INFO - __main__ - Step 27324: {'lr': 0.000464743899092562, 'samples': 5246208, 'steps': 27323, 'loss/train': 1.4622997045516968} 08/30/2021 18:03:50 - INFO - __main__ - Step 27325: {'lr': 0.0004647411819033669, 'samples': 5246400, 'steps': 27324, 'loss/train': 0.04158177599310875} 08/30/2021 18:03:50 - INFO - __main__ - Step 27326: {'lr': 0.00046473846461741276, 'samples': 5246592, 'steps': 27325, 'loss/train': 1.4114559888839722} 08/30/2021 18:03:52 - INFO - __main__ - Step 27327: {'lr': 0.0004647357472347008, 'samples': 5246784, 'steps': 27326, 'loss/train': 1.964754343032837} 08/30/2021 18:03:52 - INFO - __main__ - Step 27328: {'lr': 0.00046473302975523224, 'samples': 5246976, 'steps': 27327, 'loss/train': 1.4276273250579834} 08/30/2021 18:03:53 - INFO - __main__ - Step 27329: {'lr': 0.0004647303121790082, 'samples': 5247168, 'steps': 27328, 'loss/train': 1.6231714487075806} 08/30/2021 18:03:53 - INFO - __main__ - Step 27330: {'lr': 0.0004647275945060301, 'samples': 5247360, 'steps': 27329, 'loss/train': 1.151721715927124} 08/30/2021 18:03:53 - INFO - __main__ - Step 27331: {'lr': 0.000464724876736299, 'samples': 5247552, 'steps': 27330, 'loss/train': 2.5251708030700684} 08/30/2021 18:03:55 - INFO - __main__ - Step 27332: {'lr': 0.00046472215886981616, 'samples': 5247744, 'steps': 27331, 'loss/train': 0.6353248953819275} 08/30/2021 18:03:55 - INFO - __main__ - Step 27333: {'lr': 0.00046471944090658294, 'samples': 5247936, 'steps': 27332, 'loss/train': 1.8478977680206299} 08/30/2021 18:03:56 - INFO - __main__ - Step 27334: {'lr': 0.0004647167228466004, 'samples': 5248128, 'steps': 27333, 'loss/train': 0.6284403800964355} 08/30/2021 18:03:56 - INFO - __main__ - Step 27335: {'lr': 0.0004647140046898697, 'samples': 5248320, 'steps': 27334, 'loss/train': 1.6182653903961182} 08/30/2021 18:03:56 - INFO - __main__ - Step 27336: {'lr': 0.0004647112864363923, 'samples': 5248512, 'steps': 27335, 'loss/train': 1.2258281707763672} 08/30/2021 18:03:58 - INFO - __main__ - Step 27337: {'lr': 0.00046470856808616934, 'samples': 5248704, 'steps': 27336, 'loss/train': 1.7995223999023438} 08/30/2021 18:03:58 - INFO - __main__ - Step 27338: {'lr': 0.0004647058496392019, 'samples': 5248896, 'steps': 27337, 'loss/train': 0.9250343441963196} 08/30/2021 18:03:59 - INFO - __main__ - Step 27339: {'lr': 0.0004647031310954914, 'samples': 5249088, 'steps': 27338, 'loss/train': 1.7553257942199707} 08/30/2021 18:03:59 - INFO - __main__ - Step 27340: {'lr': 0.00046470041245503895, 'samples': 5249280, 'steps': 27339, 'loss/train': 1.399047613143921} 08/30/2021 18:03:59 - INFO - __main__ - Step 27341: {'lr': 0.0004646976937178459, 'samples': 5249472, 'steps': 27340, 'loss/train': 2.1510541439056396} 08/30/2021 18:04:01 - INFO - __main__ - Step 27342: {'lr': 0.0004646949748839132, 'samples': 5249664, 'steps': 27341, 'loss/train': 0.9165777564048767} 08/30/2021 18:04:01 - INFO - __main__ - Step 27343: {'lr': 0.0004646922559532424, 'samples': 5249856, 'steps': 27342, 'loss/train': 1.3690391778945923} 08/30/2021 18:04:02 - INFO - __main__ - Step 27344: {'lr': 0.0004646895369258345, 'samples': 5250048, 'steps': 27343, 'loss/train': 0.8818331360816956} 08/30/2021 18:04:02 - INFO - __main__ - Step 27345: {'lr': 0.00046468681780169086, 'samples': 5250240, 'steps': 27344, 'loss/train': 1.3514323234558105} 08/30/2021 18:04:02 - INFO - __main__ - Step 27346: {'lr': 0.0004646840985808126, 'samples': 5250432, 'steps': 27345, 'loss/train': 1.0465266704559326} 08/30/2021 18:04:04 - INFO - __main__ - Step 27347: {'lr': 0.0004646813792632011, 'samples': 5250624, 'steps': 27346, 'loss/train': 1.541799545288086} 08/30/2021 18:04:04 - INFO - __main__ - Step 27348: {'lr': 0.00046467865984885736, 'samples': 5250816, 'steps': 27347, 'loss/train': 1.7342004776000977} 08/30/2021 18:04:05 - INFO - __main__ - Step 27349: {'lr': 0.0004646759403377828, 'samples': 5251008, 'steps': 27348, 'loss/train': 1.3066784143447876} 08/30/2021 18:04:05 - INFO - __main__ - Step 27350: {'lr': 0.00046467322072997865, 'samples': 5251200, 'steps': 27349, 'loss/train': 1.6642979383468628} 08/30/2021 18:04:05 - INFO - __main__ - Step 27351: {'lr': 0.00046467050102544594, 'samples': 5251392, 'steps': 27350, 'loss/train': 1.3448563814163208} 08/30/2021 18:04:06 - INFO - __main__ - Step 27352: {'lr': 0.0004646677812241861, 'samples': 5251584, 'steps': 27351, 'loss/train': 1.191585659980774} 08/30/2021 18:04:07 - INFO - __main__ - Step 27353: {'lr': 0.0004646650613262001, 'samples': 5251776, 'steps': 27352, 'loss/train': 0.6744791865348816} 08/30/2021 18:04:08 - INFO - __main__ - Step 27354: {'lr': 0.00046466234133148957, 'samples': 5251968, 'steps': 27353, 'loss/train': 1.1724281311035156} 08/30/2021 18:04:08 - INFO - __main__ - Step 27355: {'lr': 0.00046465962124005535, 'samples': 5252160, 'steps': 27354, 'loss/train': 1.4432481527328491} 08/30/2021 18:04:08 - INFO - __main__ - Step 27356: {'lr': 0.0004646569010518988, 'samples': 5252352, 'steps': 27355, 'loss/train': 1.5820986032485962} 08/30/2021 18:04:09 - INFO - __main__ - Step 27357: {'lr': 0.00046465418076702125, 'samples': 5252544, 'steps': 27356, 'loss/train': 1.2430405616760254} 08/30/2021 18:04:11 - INFO - __main__ - Step 27358: {'lr': 0.00046465146038542375, 'samples': 5252736, 'steps': 27357, 'loss/train': 1.4338152408599854} 08/30/2021 18:04:11 - INFO - __main__ - Step 27359: {'lr': 0.0004646487399071077, 'samples': 5252928, 'steps': 27358, 'loss/train': 1.0728802680969238} 08/30/2021 18:04:12 - INFO - __main__ - Step 27360: {'lr': 0.00046464601933207417, 'samples': 5253120, 'steps': 27359, 'loss/train': 1.418859839439392} 08/30/2021 18:04:12 - INFO - __main__ - Step 27361: {'lr': 0.0004646432986603245, 'samples': 5253312, 'steps': 27360, 'loss/train': 1.0611650943756104} 08/30/2021 18:04:12 - INFO - __main__ - Step 27362: {'lr': 0.00046464057789185985, 'samples': 5253504, 'steps': 27361, 'loss/train': 0.5609676241874695} 08/30/2021 18:04:15 - INFO - __main__ - Step 27363: {'lr': 0.00046463785702668156, 'samples': 5253696, 'steps': 27362, 'loss/train': 2.100377082824707} 08/30/2021 18:04:15 - INFO - __main__ - Step 27364: {'lr': 0.0004646351360647907, 'samples': 5253888, 'steps': 27363, 'loss/train': 1.3934309482574463} 08/30/2021 18:04:16 - INFO - __main__ - Step 27365: {'lr': 0.00046463241500618846, 'samples': 5254080, 'steps': 27364, 'loss/train': 1.6407395601272583} 08/30/2021 18:04:16 - INFO - __main__ - Step 27366: {'lr': 0.00046462969385087626, 'samples': 5254272, 'steps': 27365, 'loss/train': 1.9130204916000366} 08/30/2021 18:04:16 - INFO - __main__ - Step 27367: {'lr': 0.00046462697259885523, 'samples': 5254464, 'steps': 27366, 'loss/train': 3.333629846572876} 08/30/2021 18:04:17 - INFO - __main__ - Step 27368: {'lr': 0.0004646242512501266, 'samples': 5254656, 'steps': 27367, 'loss/train': 2.2948241233825684} 08/30/2021 18:04:18 - INFO - __main__ - Step 27369: {'lr': 0.0004646215298046916, 'samples': 5254848, 'steps': 27368, 'loss/train': 2.367582082748413} 08/30/2021 18:04:19 - INFO - __main__ - Step 27370: {'lr': 0.00046461880826255143, 'samples': 5255040, 'steps': 27369, 'loss/train': 1.4502631425857544} 08/30/2021 18:04:19 - INFO - __main__ - Step 27371: {'lr': 0.00046461608662370734, 'samples': 5255232, 'steps': 27370, 'loss/train': 1.9257307052612305} 08/30/2021 18:04:19 - INFO - __main__ - Step 27372: {'lr': 0.0004646133648881606, 'samples': 5255424, 'steps': 27371, 'loss/train': 1.5148178339004517} 08/30/2021 18:04:20 - INFO - __main__ - Step 27373: {'lr': 0.00046461064305591235, 'samples': 5255616, 'steps': 27372, 'loss/train': 1.9873127937316895} 08/30/2021 18:04:20 - INFO - __main__ - Step 27374: {'lr': 0.00046460792112696384, 'samples': 5255808, 'steps': 27373, 'loss/train': 0.8149328231811523} 08/30/2021 18:04:21 - INFO - __main__ - Step 27375: {'lr': 0.0004646051991013163, 'samples': 5256000, 'steps': 27374, 'loss/train': 1.8680310249328613} 08/30/2021 18:04:22 - INFO - __main__ - Step 27376: {'lr': 0.000464602476978971, 'samples': 5256192, 'steps': 27375, 'loss/train': 0.9939104318618774} 08/30/2021 18:04:22 - INFO - __main__ - Step 27377: {'lr': 0.00046459975475992914, 'samples': 5256384, 'steps': 27376, 'loss/train': 1.577289342880249} 08/30/2021 18:04:23 - INFO - __main__ - Step 27378: {'lr': 0.00046459703244419194, 'samples': 5256576, 'steps': 27377, 'loss/train': 1.6684318780899048} 08/30/2021 18:04:23 - INFO - __main__ - Step 27379: {'lr': 0.0004645943100317606, 'samples': 5256768, 'steps': 27378, 'loss/train': 1.620996356010437} 08/30/2021 18:04:25 - INFO - __main__ - Step 27380: {'lr': 0.00046459158752263643, 'samples': 5256960, 'steps': 27379, 'loss/train': 1.4244303703308105} 08/30/2021 18:04:25 - INFO - __main__ - Step 27381: {'lr': 0.0004645888649168205, 'samples': 5257152, 'steps': 27380, 'loss/train': 1.8420264720916748} 08/30/2021 18:04:25 - INFO - __main__ - Step 27382: {'lr': 0.0004645861422143143, 'samples': 5257344, 'steps': 27381, 'loss/train': 1.68105149269104} 08/30/2021 18:04:26 - INFO - __main__ - Step 27383: {'lr': 0.0004645834194151187, 'samples': 5257536, 'steps': 27382, 'loss/train': 1.6556614637374878} 08/30/2021 18:04:26 - INFO - __main__ - Step 27384: {'lr': 0.0004645806965192353, 'samples': 5257728, 'steps': 27383, 'loss/train': 1.6255290508270264} 08/30/2021 18:04:28 - INFO - __main__ - Step 27385: {'lr': 0.000464577973526665, 'samples': 5257920, 'steps': 27384, 'loss/train': 1.6095224618911743} 08/30/2021 18:04:28 - INFO - __main__ - Step 27386: {'lr': 0.00046457525043740926, 'samples': 5258112, 'steps': 27385, 'loss/train': 1.5118950605392456} 08/30/2021 18:04:29 - INFO - __main__ - Step 27387: {'lr': 0.0004645725272514693, 'samples': 5258304, 'steps': 27386, 'loss/train': 1.5710792541503906} 08/30/2021 18:04:29 - INFO - __main__ - Step 27388: {'lr': 0.0004645698039688461, 'samples': 5258496, 'steps': 27387, 'loss/train': 1.990828514099121} 08/30/2021 18:04:29 - INFO - __main__ - Step 27389: {'lr': 0.00046456708058954116, 'samples': 5258688, 'steps': 27388, 'loss/train': 1.6931428909301758} 08/30/2021 18:04:31 - INFO - __main__ - Step 27390: {'lr': 0.0004645643571135556, 'samples': 5258880, 'steps': 27389, 'loss/train': 1.568619966506958} 08/30/2021 18:04:31 - INFO - __main__ - Step 27391: {'lr': 0.00046456163354089065, 'samples': 5259072, 'steps': 27390, 'loss/train': 1.7756857872009277} 08/30/2021 18:04:31 - INFO - __main__ - Step 27392: {'lr': 0.00046455890987154747, 'samples': 5259264, 'steps': 27391, 'loss/train': 2.837989330291748} 08/30/2021 18:04:32 - INFO - __main__ - Step 27393: {'lr': 0.0004645561861055274, 'samples': 5259456, 'steps': 27392, 'loss/train': 1.8848211765289307} 08/30/2021 18:04:32 - INFO - __main__ - Step 27394: {'lr': 0.00046455346224283167, 'samples': 5259648, 'steps': 27393, 'loss/train': 0.8997451663017273} 08/30/2021 18:04:34 - INFO - __main__ - Step 27395: {'lr': 0.00046455073828346137, 'samples': 5259840, 'steps': 27394, 'loss/train': 1.7699164152145386} 08/30/2021 18:04:34 - INFO - __main__ - Step 27396: {'lr': 0.0004645480142274179, 'samples': 5260032, 'steps': 27395, 'loss/train': 1.2306593656539917} 08/30/2021 18:04:34 - INFO - __main__ - Step 27397: {'lr': 0.0004645452900747024, 'samples': 5260224, 'steps': 27396, 'loss/train': 1.6315412521362305} 08/30/2021 18:04:35 - INFO - __main__ - Step 27398: {'lr': 0.00046454256582531604, 'samples': 5260416, 'steps': 27397, 'loss/train': 2.2044410705566406} 08/30/2021 18:04:35 - INFO - __main__ - Step 27399: {'lr': 0.0004645398414792602, 'samples': 5260608, 'steps': 27398, 'loss/train': 0.7364284992218018} 08/30/2021 18:04:37 - INFO - __main__ - Step 27400: {'lr': 0.000464537117036536, 'samples': 5260800, 'steps': 27399, 'loss/train': 1.4160264730453491} 08/30/2021 18:04:37 - INFO - __main__ - Step 27401: {'lr': 0.00046453439249714466, 'samples': 5260992, 'steps': 27400, 'loss/train': 2.031721830368042} 08/30/2021 18:04:37 - INFO - __main__ - Step 27402: {'lr': 0.00046453166786108736, 'samples': 5261184, 'steps': 27401, 'loss/train': 1.9949887990951538} 08/30/2021 18:04:38 - INFO - __main__ - Step 27403: {'lr': 0.00046452894312836547, 'samples': 5261376, 'steps': 27402, 'loss/train': 1.9851300716400146} 08/30/2021 18:04:38 - INFO - __main__ - Step 27404: {'lr': 0.0004645262182989802, 'samples': 5261568, 'steps': 27403, 'loss/train': 1.0105459690093994} 08/30/2021 18:04:40 - INFO - __main__ - Step 27405: {'lr': 0.0004645234933729327, 'samples': 5261760, 'steps': 27404, 'loss/train': 0.06788698583841324} 08/30/2021 18:04:40 - INFO - __main__ - Step 27406: {'lr': 0.00046452076835022416, 'samples': 5261952, 'steps': 27405, 'loss/train': 1.4818108081817627} 08/30/2021 18:04:41 - INFO - __main__ - Step 27407: {'lr': 0.0004645180432308559, 'samples': 5262144, 'steps': 27406, 'loss/train': 1.0781244039535522} 08/30/2021 18:04:41 - INFO - __main__ - Step 27408: {'lr': 0.00046451531801482913, 'samples': 5262336, 'steps': 27407, 'loss/train': 1.3619756698608398} 08/30/2021 18:04:41 - INFO - __main__ - Step 27409: {'lr': 0.00046451259270214505, 'samples': 5262528, 'steps': 27408, 'loss/train': 1.224409580230713} 08/30/2021 18:04:42 - INFO - __main__ - Step 27410: {'lr': 0.00046450986729280495, 'samples': 5262720, 'steps': 27409, 'loss/train': 1.8427653312683105} 08/30/2021 18:04:43 - INFO - __main__ - Step 27411: {'lr': 0.00046450714178680996, 'samples': 5262912, 'steps': 27410, 'loss/train': 1.615390658378601} 08/30/2021 18:04:44 - INFO - __main__ - Step 27412: {'lr': 0.0004645044161841614, 'samples': 5263104, 'steps': 27411, 'loss/train': 1.1181161403656006} 08/30/2021 18:04:44 - INFO - __main__ - Step 27413: {'lr': 0.00046450169048486045, 'samples': 5263296, 'steps': 27412, 'loss/train': 1.1217595338821411} 08/30/2021 18:04:44 - INFO - __main__ - Step 27414: {'lr': 0.0004644989646889084, 'samples': 5263488, 'steps': 27413, 'loss/train': 1.69459068775177} 08/30/2021 18:04:45 - INFO - __main__ - Step 27415: {'lr': 0.0004644962387963063, 'samples': 5263680, 'steps': 27414, 'loss/train': 1.5929012298583984} 08/30/2021 18:04:47 - INFO - __main__ - Step 27416: {'lr': 0.0004644935128070556, 'samples': 5263872, 'steps': 27415, 'loss/train': 1.9933714866638184} 08/30/2021 18:04:47 - INFO - __main__ - Step 27417: {'lr': 0.0004644907867211574, 'samples': 5264064, 'steps': 27416, 'loss/train': 1.4617135524749756} 08/30/2021 18:04:47 - INFO - __main__ - Step 27418: {'lr': 0.000464488060538613, 'samples': 5264256, 'steps': 27417, 'loss/train': 1.5432010889053345} 08/30/2021 18:04:48 - INFO - __main__ - Step 27419: {'lr': 0.0004644853342594235, 'samples': 5264448, 'steps': 27418, 'loss/train': 1.5122867822647095} 08/30/2021 18:04:48 - INFO - __main__ - Step 27420: {'lr': 0.0004644826078835903, 'samples': 5264640, 'steps': 27419, 'loss/train': 1.713381290435791} 08/30/2021 18:04:50 - INFO - __main__ - Step 27421: {'lr': 0.00046447988141111457, 'samples': 5264832, 'steps': 27420, 'loss/train': 1.7288973331451416} 08/30/2021 18:04:50 - INFO - __main__ - Step 27422: {'lr': 0.0004644771548419975, 'samples': 5265024, 'steps': 27421, 'loss/train': 1.3567960262298584} 08/30/2021 18:04:51 - INFO - __main__ - Step 27423: {'lr': 0.0004644744281762403, 'samples': 5265216, 'steps': 27422, 'loss/train': 2.2251620292663574} 08/30/2021 18:04:51 - INFO - __main__ - Step 27424: {'lr': 0.0004644717014138442, 'samples': 5265408, 'steps': 27423, 'loss/train': 1.5661921501159668} 08/30/2021 18:04:51 - INFO - __main__ - Step 27425: {'lr': 0.0004644689745548105, 'samples': 5265600, 'steps': 27424, 'loss/train': 0.5250753164291382} 08/30/2021 18:04:53 - INFO - __main__ - Step 27426: {'lr': 0.00046446624759914043, 'samples': 5265792, 'steps': 27425, 'loss/train': 1.2815206050872803} 08/30/2021 18:04:53 - INFO - __main__ - Step 27427: {'lr': 0.0004644635205468351, 'samples': 5265984, 'steps': 27426, 'loss/train': 1.7290304899215698} 08/30/2021 18:04:54 - INFO - __main__ - Step 27428: {'lr': 0.00046446079339789587, 'samples': 5266176, 'steps': 27427, 'loss/train': 1.6286661624908447} 08/30/2021 18:04:54 - INFO - __main__ - Step 27429: {'lr': 0.0004644580661523239, 'samples': 5266368, 'steps': 27428, 'loss/train': 1.294432520866394} 08/30/2021 18:04:54 - INFO - __main__ - Step 27430: {'lr': 0.00046445533881012043, 'samples': 5266560, 'steps': 27429, 'loss/train': 1.2775497436523438} 08/30/2021 18:04:56 - INFO - __main__ - Step 27431: {'lr': 0.0004644526113712867, 'samples': 5266752, 'steps': 27430, 'loss/train': 1.9153541326522827} 08/30/2021 18:04:57 - INFO - __main__ - Step 27432: {'lr': 0.00046444988383582394, 'samples': 5266944, 'steps': 27431, 'loss/train': 1.5451918840408325} 08/30/2021 18:04:57 - INFO - __main__ - Step 27433: {'lr': 0.0004644471562037333, 'samples': 5267136, 'steps': 27432, 'loss/train': 0.24773718416690826} 08/30/2021 18:04:57 - INFO - __main__ - Step 27434: {'lr': 0.0004644444284750162, 'samples': 5267328, 'steps': 27433, 'loss/train': 1.4150580167770386} 08/30/2021 18:04:58 - INFO - __main__ - Step 27435: {'lr': 0.0004644417006496737, 'samples': 5267520, 'steps': 27434, 'loss/train': 1.601648211479187} 08/30/2021 18:04:59 - INFO - __main__ - Step 27436: {'lr': 0.0004644389727277071, 'samples': 5267712, 'steps': 27435, 'loss/train': 1.2211816310882568} 08/30/2021 18:05:00 - INFO - __main__ - Step 27437: {'lr': 0.00046443624470911754, 'samples': 5267904, 'steps': 27436, 'loss/train': 1.636705994606018} 08/30/2021 18:05:00 - INFO - __main__ - Step 27438: {'lr': 0.00046443351659390637, 'samples': 5268096, 'steps': 27437, 'loss/train': 1.3936412334442139} 08/30/2021 18:05:01 - INFO - __main__ - Step 27439: {'lr': 0.00046443078838207474, 'samples': 5268288, 'steps': 27438, 'loss/train': 1.8843578100204468} 08/30/2021 18:05:01 - INFO - __main__ - Step 27440: {'lr': 0.00046442806007362394, 'samples': 5268480, 'steps': 27439, 'loss/train': 1.2439494132995605} 08/30/2021 18:05:01 - INFO - __main__ - Step 27441: {'lr': 0.00046442533166855517, 'samples': 5268672, 'steps': 27440, 'loss/train': 0.8290183544158936} 08/30/2021 18:05:03 - INFO - __main__ - Step 27442: {'lr': 0.00046442260316686957, 'samples': 5268864, 'steps': 27441, 'loss/train': 1.4382227659225464} 08/30/2021 18:05:03 - INFO - __main__ - Step 27443: {'lr': 0.0004644198745685685, 'samples': 5269056, 'steps': 27442, 'loss/train': 1.6046395301818848} 08/30/2021 18:05:04 - INFO - __main__ - Step 27444: {'lr': 0.00046441714587365317, 'samples': 5269248, 'steps': 27443, 'loss/train': 2.005960464477539} 08/30/2021 18:05:04 - INFO - __main__ - Step 27445: {'lr': 0.00046441441708212477, 'samples': 5269440, 'steps': 27444, 'loss/train': 2.0347695350646973} 08/30/2021 18:05:04 - INFO - __main__ - Step 27446: {'lr': 0.00046441168819398457, 'samples': 5269632, 'steps': 27445, 'loss/train': 1.2989490032196045} 08/30/2021 18:05:06 - INFO - __main__ - Step 27447: {'lr': 0.0004644089592092338, 'samples': 5269824, 'steps': 27446, 'loss/train': 1.4103548526763916} 08/30/2021 18:05:07 - INFO - __main__ - Step 27448: {'lr': 0.0004644062301278735, 'samples': 5270016, 'steps': 27447, 'loss/train': 1.3690731525421143} 08/30/2021 18:05:07 - INFO - __main__ - Step 27449: {'lr': 0.0004644035009499052, 'samples': 5270208, 'steps': 27448, 'loss/train': 1.497934103012085} 08/30/2021 18:05:07 - INFO - __main__ - Step 27450: {'lr': 0.0004644007716753299, 'samples': 5270400, 'steps': 27449, 'loss/train': 1.3804068565368652} 08/30/2021 18:05:08 - INFO - __main__ - Step 27451: {'lr': 0.00046439804230414904, 'samples': 5270592, 'steps': 27450, 'loss/train': 1.993382215499878} 08/30/2021 18:05:09 - INFO - __main__ - Step 27452: {'lr': 0.0004643953128363637, 'samples': 5270784, 'steps': 27451, 'loss/train': 0.4664199650287628} 08/30/2021 18:05:10 - INFO - __main__ - Step 27453: {'lr': 0.0004643925832719751, 'samples': 5270976, 'steps': 27452, 'loss/train': 1.0037028789520264} 08/30/2021 18:05:10 - INFO - __main__ - Step 27454: {'lr': 0.0004643898536109845, 'samples': 5271168, 'steps': 27453, 'loss/train': 1.2655574083328247} 08/30/2021 18:05:10 - INFO - __main__ - Step 27455: {'lr': 0.0004643871238533931, 'samples': 5271360, 'steps': 27454, 'loss/train': 1.277710199356079} 08/30/2021 18:05:11 - INFO - __main__ - Step 27456: {'lr': 0.0004643843939992022, 'samples': 5271552, 'steps': 27455, 'loss/train': 1.315433144569397} 08/30/2021 18:05:11 - INFO - __main__ - Step 27457: {'lr': 0.0004643816640484131, 'samples': 5271744, 'steps': 27456, 'loss/train': 1.73223876953125} 08/30/2021 18:05:13 - INFO - __main__ - Step 27458: {'lr': 0.0004643789340010268, 'samples': 5271936, 'steps': 27457, 'loss/train': 1.7017115354537964} 08/30/2021 18:05:13 - INFO - __main__ - Step 27459: {'lr': 0.00046437620385704476, 'samples': 5272128, 'steps': 27458, 'loss/train': 1.2132965326309204} 08/30/2021 18:05:13 - INFO - __main__ - Step 27460: {'lr': 0.0004643734736164681, 'samples': 5272320, 'steps': 27459, 'loss/train': 1.5949082374572754} 08/30/2021 18:05:14 - INFO - __main__ - Step 27461: {'lr': 0.00046437074327929795, 'samples': 5272512, 'steps': 27460, 'loss/train': 1.6055718660354614} 08/30/2021 18:05:14 - INFO - __main__ - Step 27462: {'lr': 0.0004643680128455358, 'samples': 5272704, 'steps': 27461, 'loss/train': 1.2206093072891235} 08/30/2021 18:05:15 - INFO - __main__ - Step 27463: {'lr': 0.00046436528231518263, 'samples': 5272896, 'steps': 27462, 'loss/train': 1.6541802883148193} 08/30/2021 18:05:16 - INFO - __main__ - Step 27464: {'lr': 0.0004643625516882398, 'samples': 5273088, 'steps': 27463, 'loss/train': 0.5171638131141663} 08/30/2021 18:05:16 - INFO - __main__ - Step 27465: {'lr': 0.0004643598209647085, 'samples': 5273280, 'steps': 27464, 'loss/train': 1.495107650756836} 08/30/2021 18:05:17 - INFO - __main__ - Step 27466: {'lr': 0.00046435709014459, 'samples': 5273472, 'steps': 27465, 'loss/train': 0.47101113200187683} 08/30/2021 18:05:17 - INFO - __main__ - Step 27467: {'lr': 0.0004643543592278855, 'samples': 5273664, 'steps': 27466, 'loss/train': 1.4665911197662354} 08/30/2021 18:05:19 - INFO - __main__ - Step 27468: {'lr': 0.0004643516282145962, 'samples': 5273856, 'steps': 27467, 'loss/train': 1.4858365058898926} 08/30/2021 18:05:20 - INFO - __main__ - Step 27469: {'lr': 0.0004643488971047234, 'samples': 5274048, 'steps': 27468, 'loss/train': 1.8858387470245361} 08/30/2021 18:05:20 - INFO - __main__ - Step 27470: {'lr': 0.0004643461658982683, 'samples': 5274240, 'steps': 27469, 'loss/train': 1.5373194217681885} 08/30/2021 18:05:20 - INFO - __main__ - Step 27471: {'lr': 0.00046434343459523207, 'samples': 5274432, 'steps': 27470, 'loss/train': 1.1708983182907104} 08/30/2021 18:05:21 - INFO - __main__ - Step 27472: {'lr': 0.00046434070319561604, 'samples': 5274624, 'steps': 27471, 'loss/train': 2.240302324295044} 08/30/2021 18:05:21 - INFO - __main__ - Step 27473: {'lr': 0.0004643379716994214, 'samples': 5274816, 'steps': 27472, 'loss/train': 1.2890220880508423} 08/30/2021 18:05:23 - INFO - __main__ - Step 27474: {'lr': 0.0004643352401066494, 'samples': 5275008, 'steps': 27473, 'loss/train': 1.1141462326049805} 08/30/2021 18:05:23 - INFO - __main__ - Step 27475: {'lr': 0.00046433250841730123, 'samples': 5275200, 'steps': 27474, 'loss/train': 1.5007108449935913} 08/30/2021 18:05:23 - INFO - __main__ - Step 27476: {'lr': 0.0004643297766313781, 'samples': 5275392, 'steps': 27475, 'loss/train': 0.09506670385599136} 08/30/2021 18:05:24 - INFO - __main__ - Step 27477: {'lr': 0.0004643270447488813, 'samples': 5275584, 'steps': 27476, 'loss/train': 1.9615954160690308} 08/30/2021 18:05:24 - INFO - __main__ - Step 27478: {'lr': 0.000464324312769812, 'samples': 5275776, 'steps': 27477, 'loss/train': 0.7599114179611206} 08/30/2021 18:05:25 - INFO - __main__ - Step 27479: {'lr': 0.0004643215806941716, 'samples': 5275968, 'steps': 27478, 'loss/train': 1.615844488143921} 08/30/2021 18:05:26 - INFO - __main__ - Step 27480: {'lr': 0.00046431884852196105, 'samples': 5276160, 'steps': 27479, 'loss/train': 1.6542208194732666} 08/30/2021 18:05:26 - INFO - __main__ - Step 27481: {'lr': 0.0004643161162531818, 'samples': 5276352, 'steps': 27480, 'loss/train': 0.086514413356781} 08/30/2021 18:05:27 - INFO - __main__ - Step 27482: {'lr': 0.00046431338388783504, 'samples': 5276544, 'steps': 27481, 'loss/train': 1.6083823442459106} 08/30/2021 18:05:27 - INFO - __main__ - Step 27483: {'lr': 0.000464310651425922, 'samples': 5276736, 'steps': 27482, 'loss/train': 1.7101365327835083} 08/30/2021 18:05:28 - INFO - __main__ - Step 27484: {'lr': 0.00046430791886744384, 'samples': 5276928, 'steps': 27483, 'loss/train': 1.96410071849823} 08/30/2021 18:05:29 - INFO - __main__ - Step 27485: {'lr': 0.0004643051862124018, 'samples': 5277120, 'steps': 27484, 'loss/train': 1.3670763969421387} 08/30/2021 18:05:29 - INFO - __main__ - Step 27486: {'lr': 0.0004643024534607973, 'samples': 5277312, 'steps': 27485, 'loss/train': 1.7785871028900146} 08/30/2021 18:05:30 - INFO - __main__ - Step 27487: {'lr': 0.00046429972061263125, 'samples': 5277504, 'steps': 27486, 'loss/train': 1.5298993587493896} 08/30/2021 18:05:30 - INFO - __main__ - Step 27488: {'lr': 0.0004642969876679051, 'samples': 5277696, 'steps': 27487, 'loss/train': 1.6133230924606323} 08/30/2021 18:05:32 - INFO - __main__ - Step 27489: {'lr': 0.00046429425462662, 'samples': 5277888, 'steps': 27488, 'loss/train': 1.0676636695861816} 08/30/2021 18:05:32 - INFO - __main__ - Step 27490: {'lr': 0.00046429152148877727, 'samples': 5278080, 'steps': 27489, 'loss/train': 0.8648391962051392} 08/30/2021 18:05:32 - INFO - __main__ - Step 27491: {'lr': 0.00046428878825437815, 'samples': 5278272, 'steps': 27490, 'loss/train': 1.1295976638793945} 08/30/2021 18:05:33 - INFO - __main__ - Step 27492: {'lr': 0.00046428605492342367, 'samples': 5278464, 'steps': 27491, 'loss/train': 1.5803020000457764} 08/30/2021 18:05:33 - INFO - __main__ - Step 27493: {'lr': 0.00046428332149591535, 'samples': 5278656, 'steps': 27492, 'loss/train': 1.3380845785140991} 08/30/2021 18:05:35 - INFO - __main__ - Step 27494: {'lr': 0.0004642805879718541, 'samples': 5278848, 'steps': 27493, 'loss/train': 0.903255820274353} 08/30/2021 18:05:35 - INFO - __main__ - Step 27495: {'lr': 0.00046427785435124147, 'samples': 5279040, 'steps': 27494, 'loss/train': 1.5985044240951538} 08/30/2021 18:05:35 - INFO - __main__ - Step 27496: {'lr': 0.0004642751206340785, 'samples': 5279232, 'steps': 27495, 'loss/train': 1.9975924491882324} 08/30/2021 18:05:36 - INFO - __main__ - Step 27497: {'lr': 0.00046427238682036643, 'samples': 5279424, 'steps': 27496, 'loss/train': 1.249411940574646} 08/30/2021 18:05:36 - INFO - __main__ - Step 27498: {'lr': 0.0004642696529101066, 'samples': 5279616, 'steps': 27497, 'loss/train': 2.1159005165100098} 08/30/2021 18:05:38 - INFO - __main__ - Step 27499: {'lr': 0.0004642669189033001, 'samples': 5279808, 'steps': 27498, 'loss/train': 1.5861256122589111} 08/30/2021 18:05:38 - INFO - __main__ - Step 27500: {'lr': 0.0004642641847999483, 'samples': 5280000, 'steps': 27499, 'loss/train': 1.195245623588562} 08/30/2021 18:05:39 - INFO - __main__ - Step 27501: {'lr': 0.0004642614506000523, 'samples': 5280192, 'steps': 27500, 'loss/train': 1.4239248037338257} 08/30/2021 18:05:39 - INFO - __main__ - Step 27502: {'lr': 0.00046425871630361343, 'samples': 5280384, 'steps': 27501, 'loss/train': 0.8084686398506165} 08/30/2021 18:05:39 - INFO - __main__ - Step 27503: {'lr': 0.0004642559819106329, 'samples': 5280576, 'steps': 27502, 'loss/train': 0.9394906759262085} 08/30/2021 18:05:41 - INFO - __main__ - Step 27504: {'lr': 0.0004642532474211119, 'samples': 5280768, 'steps': 27503, 'loss/train': 0.7073948979377747} 08/30/2021 18:05:41 - INFO - __main__ - Step 27505: {'lr': 0.0004642505128350517, 'samples': 5280960, 'steps': 27504, 'loss/train': 1.5602253675460815} 08/30/2021 18:05:42 - INFO - __main__ - Step 27506: {'lr': 0.00046424777815245354, 'samples': 5281152, 'steps': 27505, 'loss/train': 1.404266595840454} 08/30/2021 18:05:42 - INFO - __main__ - Step 27507: {'lr': 0.0004642450433733186, 'samples': 5281344, 'steps': 27506, 'loss/train': 1.1671524047851562} 08/30/2021 18:05:42 - INFO - __main__ - Step 27508: {'lr': 0.0004642423084976482, 'samples': 5281536, 'steps': 27507, 'loss/train': 1.3224974870681763} 08/30/2021 18:05:43 - INFO - __main__ - Step 27509: {'lr': 0.0004642395735254435, 'samples': 5281728, 'steps': 27508, 'loss/train': 1.2267792224884033} 08/30/2021 18:05:44 - INFO - __main__ - Step 27510: {'lr': 0.0004642368384567058, 'samples': 5281920, 'steps': 27509, 'loss/train': 1.0123409032821655} 08/30/2021 18:05:45 - INFO - __main__ - Step 27511: {'lr': 0.0004642341032914362, 'samples': 5282112, 'steps': 27510, 'loss/train': 1.685687780380249} 08/30/2021 18:05:45 - INFO - __main__ - Step 27512: {'lr': 0.00046423136802963607, 'samples': 5282304, 'steps': 27511, 'loss/train': 1.1748380661010742} 08/30/2021 18:05:45 - INFO - __main__ - Step 27513: {'lr': 0.0004642286326713065, 'samples': 5282496, 'steps': 27512, 'loss/train': 0.4168582260608673} 08/30/2021 18:05:46 - INFO - __main__ - Step 27514: {'lr': 0.000464225897216449, 'samples': 5282688, 'steps': 27513, 'loss/train': 1.7291203737258911} 08/30/2021 18:05:47 - INFO - __main__ - Step 27515: {'lr': 0.0004642231616650645, 'samples': 5282880, 'steps': 27514, 'loss/train': 1.0879120826721191} 08/30/2021 18:05:48 - INFO - __main__ - Step 27516: {'lr': 0.00046422042601715433, 'samples': 5283072, 'steps': 27515, 'loss/train': 1.5452195405960083} 08/30/2021 18:05:48 - INFO - __main__ - Step 27517: {'lr': 0.00046421769027271974, 'samples': 5283264, 'steps': 27516, 'loss/train': 1.001875638961792} 08/30/2021 18:05:48 - INFO - __main__ - Step 27518: {'lr': 0.00046421495443176204, 'samples': 5283456, 'steps': 27517, 'loss/train': 1.0665472745895386} 08/30/2021 18:05:49 - INFO - __main__ - Step 27519: {'lr': 0.0004642122184942824, 'samples': 5283648, 'steps': 27518, 'loss/train': 1.7137739658355713} 08/30/2021 18:05:49 - INFO - __main__ - Step 27520: {'lr': 0.00046420948246028194, 'samples': 5283840, 'steps': 27519, 'loss/train': 1.6226041316986084} 08/30/2021 18:05:51 - INFO - __main__ - Step 27521: {'lr': 0.000464206746329762, 'samples': 5284032, 'steps': 27520, 'loss/train': 0.6680510640144348} 08/30/2021 18:05:52 - INFO - __main__ - Step 27522: {'lr': 0.00046420401010272385, 'samples': 5284224, 'steps': 27521, 'loss/train': 0.7357050776481628} 08/30/2021 18:05:52 - INFO - __main__ - Step 27523: {'lr': 0.00046420127377916863, 'samples': 5284416, 'steps': 27522, 'loss/train': 1.5431907176971436} 08/30/2021 18:05:53 - INFO - __main__ - Step 27524: {'lr': 0.0004641985373590977, 'samples': 5284608, 'steps': 27523, 'loss/train': 1.854203224182129} 08/30/2021 18:05:53 - INFO - __main__ - Step 27525: {'lr': 0.00046419580084251224, 'samples': 5284800, 'steps': 27524, 'loss/train': 1.321053147315979} 08/30/2021 18:05:55 - INFO - __main__ - Step 27526: {'lr': 0.0004641930642294133, 'samples': 5284992, 'steps': 27525, 'loss/train': 1.2070436477661133} 08/30/2021 18:05:55 - INFO - __main__ - Step 27527: {'lr': 0.0004641903275198024, 'samples': 5285184, 'steps': 27526, 'loss/train': 1.359650731086731} 08/30/2021 18:05:56 - INFO - __main__ - Step 27528: {'lr': 0.0004641875907136806, 'samples': 5285376, 'steps': 27527, 'loss/train': 2.0673930644989014} 08/30/2021 18:05:56 - INFO - __main__ - Step 27529: {'lr': 0.0004641848538110492, 'samples': 5285568, 'steps': 27528, 'loss/train': 1.2977995872497559} 08/30/2021 18:05:56 - INFO - __main__ - Step 27530: {'lr': 0.00046418211681190937, 'samples': 5285760, 'steps': 27529, 'loss/train': 0.6407142877578735} 08/30/2021 18:05:57 - INFO - __main__ - Step 27531: {'lr': 0.00046417937971626245, 'samples': 5285952, 'steps': 27530, 'loss/train': 1.3707348108291626} 08/30/2021 18:05:59 - INFO - __main__ - Step 27532: {'lr': 0.0004641766425241095, 'samples': 5286144, 'steps': 27531, 'loss/train': 1.8964557647705078} 08/30/2021 18:05:59 - INFO - __main__ - Step 27533: {'lr': 0.000464173905235452, 'samples': 5286336, 'steps': 27532, 'loss/train': 1.7082087993621826} 08/30/2021 18:06:00 - INFO - __main__ - Step 27534: {'lr': 0.0004641711678502909, 'samples': 5286528, 'steps': 27533, 'loss/train': 0.717869758605957} 08/30/2021 18:06:00 - INFO - __main__ - Step 27535: {'lr': 0.00046416843036862766, 'samples': 5286720, 'steps': 27534, 'loss/train': 1.10735023021698} 08/30/2021 18:06:00 - INFO - __main__ - Step 27536: {'lr': 0.0004641656927904634, 'samples': 5286912, 'steps': 27535, 'loss/train': 1.5429867506027222} 08/30/2021 18:06:01 - INFO - __main__ - Step 27537: {'lr': 0.00046416295511579944, 'samples': 5287104, 'steps': 27536, 'loss/train': 1.511547565460205} 08/30/2021 18:06:02 - INFO - __main__ - Step 27538: {'lr': 0.0004641602173446369, 'samples': 5287296, 'steps': 27537, 'loss/train': 1.8700331449508667} 08/30/2021 18:06:03 - INFO - __main__ - Step 27539: {'lr': 0.00046415747947697704, 'samples': 5287488, 'steps': 27538, 'loss/train': 1.083155870437622} 08/30/2021 18:06:03 - INFO - __main__ - Step 27540: {'lr': 0.00046415474151282124, 'samples': 5287680, 'steps': 27539, 'loss/train': 1.6107252836227417} 08/30/2021 18:06:04 - INFO - __main__ - Step 27541: {'lr': 0.0004641520034521705, 'samples': 5287872, 'steps': 27540, 'loss/train': 1.9646943807601929} 08/30/2021 18:06:04 - INFO - __main__ - Step 27542: {'lr': 0.0004641492652950262, 'samples': 5288064, 'steps': 27541, 'loss/train': 1.8504058122634888} 08/30/2021 18:06:06 - INFO - __main__ - Step 27543: {'lr': 0.0004641465270413896, 'samples': 5288256, 'steps': 27542, 'loss/train': 1.7035349607467651} 08/30/2021 18:06:06 - INFO - __main__ - Step 27544: {'lr': 0.00046414378869126185, 'samples': 5288448, 'steps': 27543, 'loss/train': 1.5890493392944336} 08/30/2021 18:06:06 - INFO - __main__ - Step 27545: {'lr': 0.0004641410502446442, 'samples': 5288640, 'steps': 27544, 'loss/train': 1.467052698135376} 08/30/2021 18:06:07 - INFO - __main__ - Step 27546: {'lr': 0.00046413831170153785, 'samples': 5288832, 'steps': 27545, 'loss/train': 1.6460683345794678} 08/30/2021 18:06:07 - INFO - __main__ - Step 27547: {'lr': 0.0004641355730619442, 'samples': 5289024, 'steps': 27546, 'loss/train': 1.3892771005630493} 08/30/2021 18:06:08 - INFO - __main__ - Step 27548: {'lr': 0.0004641328343258643, 'samples': 5289216, 'steps': 27547, 'loss/train': 1.299553632736206} 08/30/2021 18:06:09 - INFO - __main__ - Step 27549: {'lr': 0.00046413009549329946, 'samples': 5289408, 'steps': 27548, 'loss/train': 1.835012435913086} 08/30/2021 18:06:09 - INFO - __main__ - Step 27550: {'lr': 0.0004641273565642509, 'samples': 5289600, 'steps': 27549, 'loss/train': 1.6101205348968506} 08/30/2021 18:06:10 - INFO - __main__ - Step 27551: {'lr': 0.0004641246175387198, 'samples': 5289792, 'steps': 27550, 'loss/train': 1.294134497642517} 08/30/2021 18:06:10 - INFO - __main__ - Step 27552: {'lr': 0.0004641218784167075, 'samples': 5289984, 'steps': 27551, 'loss/train': 1.0548399686813354} 08/30/2021 18:06:11 - INFO - __main__ - Step 27553: {'lr': 0.0004641191391982152, 'samples': 5290176, 'steps': 27552, 'loss/train': 0.045883212238550186} 08/30/2021 18:06:12 - INFO - __main__ - Step 27554: {'lr': 0.00046411639988324407, 'samples': 5290368, 'steps': 27553, 'loss/train': 1.2484043836593628} 08/30/2021 18:06:12 - INFO - __main__ - Step 27555: {'lr': 0.00046411366047179547, 'samples': 5290560, 'steps': 27554, 'loss/train': 1.6914410591125488} 08/30/2021 18:06:13 - INFO - __main__ - Step 27556: {'lr': 0.00046411092096387054, 'samples': 5290752, 'steps': 27555, 'loss/train': 1.036177396774292} 08/30/2021 18:06:13 - INFO - __main__ - Step 27557: {'lr': 0.0004641081813594705, 'samples': 5290944, 'steps': 27556, 'loss/train': 1.6183223724365234} 08/30/2021 18:06:14 - INFO - __main__ - Step 27558: {'lr': 0.0004641054416585966, 'samples': 5291136, 'steps': 27557, 'loss/train': 1.4377225637435913} 08/30/2021 18:06:15 - INFO - __main__ - Step 27559: {'lr': 0.00046410270186125014, 'samples': 5291328, 'steps': 27558, 'loss/train': 1.66042959690094} 08/30/2021 18:06:15 - INFO - __main__ - Step 27560: {'lr': 0.0004640999619674323, 'samples': 5291520, 'steps': 27559, 'loss/train': 1.374444603919983} 08/30/2021 18:06:16 - INFO - __main__ - Step 27561: {'lr': 0.0004640972219771443, 'samples': 5291712, 'steps': 27560, 'loss/train': 1.6468956470489502} 08/30/2021 18:06:16 - INFO - __main__ - Step 27562: {'lr': 0.00046409448189038737, 'samples': 5291904, 'steps': 27561, 'loss/train': 0.9795956611633301} 08/30/2021 18:06:16 - INFO - __main__ - Step 27563: {'lr': 0.00046409174170716284, 'samples': 5292096, 'steps': 27562, 'loss/train': 1.2625643014907837} 08/30/2021 18:06:18 - INFO - __main__ - Step 27564: {'lr': 0.0004640890014274718, 'samples': 5292288, 'steps': 27563, 'loss/train': 1.4325306415557861} 08/30/2021 18:06:18 - INFO - __main__ - Step 27565: {'lr': 0.0004640862610513156, 'samples': 5292480, 'steps': 27564, 'loss/train': 1.565487265586853} 08/30/2021 18:06:19 - INFO - __main__ - Step 27566: {'lr': 0.00046408352057869545, 'samples': 5292672, 'steps': 27565, 'loss/train': 1.7046473026275635} 08/30/2021 18:06:19 - INFO - __main__ - Step 27567: {'lr': 0.0004640807800096126, 'samples': 5292864, 'steps': 27566, 'loss/train': 1.3343174457550049} 08/30/2021 18:06:19 - INFO - __main__ - Step 27568: {'lr': 0.0004640780393440682, 'samples': 5293056, 'steps': 27567, 'loss/train': 1.3126369714736938} 08/30/2021 18:06:21 - INFO - __main__ - Step 27569: {'lr': 0.0004640752985820635, 'samples': 5293248, 'steps': 27568, 'loss/train': 1.5438686609268188} 08/30/2021 18:06:21 - INFO - __main__ - Step 27570: {'lr': 0.0004640725577235998, 'samples': 5293440, 'steps': 27569, 'loss/train': 1.6290587186813354} 08/30/2021 18:06:22 - INFO - __main__ - Step 27571: {'lr': 0.00046406981676867836, 'samples': 5293632, 'steps': 27570, 'loss/train': 1.1571675539016724} 08/30/2021 18:06:22 - INFO - __main__ - Step 27572: {'lr': 0.00046406707571730035, 'samples': 5293824, 'steps': 27571, 'loss/train': 1.7105413675308228} 08/30/2021 18:06:22 - INFO - __main__ - Step 27573: {'lr': 0.000464064334569467, 'samples': 5294016, 'steps': 27572, 'loss/train': 1.4792060852050781} 08/30/2021 18:06:23 - INFO - __main__ - Step 27574: {'lr': 0.00046406159332517956, 'samples': 5294208, 'steps': 27573, 'loss/train': 1.5216033458709717} 08/30/2021 18:06:24 - INFO - __main__ - Step 27575: {'lr': 0.00046405885198443926, 'samples': 5294400, 'steps': 27574, 'loss/train': 1.0698562860488892} 08/30/2021 18:06:25 - INFO - __main__ - Step 27576: {'lr': 0.00046405611054724737, 'samples': 5294592, 'steps': 27575, 'loss/train': 0.6250839829444885} 08/30/2021 18:06:25 - INFO - __main__ - Step 27577: {'lr': 0.00046405336901360507, 'samples': 5294784, 'steps': 27576, 'loss/train': 1.4426932334899902} 08/30/2021 18:06:26 - INFO - __main__ - Step 27578: {'lr': 0.00046405062738351366, 'samples': 5294976, 'steps': 27577, 'loss/train': 1.29835844039917} 08/30/2021 18:06:26 - INFO - __main__ - Step 27579: {'lr': 0.00046404788565697434, 'samples': 5295168, 'steps': 27578, 'loss/train': 1.392787218093872} 08/30/2021 18:06:29 - INFO - __main__ - Step 27580: {'lr': 0.00046404514383398835, 'samples': 5295360, 'steps': 27579, 'loss/train': 1.0488930940628052} 08/30/2021 18:06:29 - INFO - __main__ - Step 27581: {'lr': 0.0004640424019145568, 'samples': 5295552, 'steps': 27580, 'loss/train': 1.4656857252120972} 08/30/2021 18:06:29 - INFO - __main__ - Step 27582: {'lr': 0.00046403965989868124, 'samples': 5295744, 'steps': 27581, 'loss/train': 1.8126304149627686} 08/30/2021 18:06:30 - INFO - __main__ - Step 27583: {'lr': 0.0004640369177863626, 'samples': 5295936, 'steps': 27582, 'loss/train': 7.011992454528809} 08/30/2021 18:06:30 - INFO - __main__ - Step 27584: {'lr': 0.00046403417557760226, 'samples': 5296128, 'steps': 27583, 'loss/train': 6.432428359985352} 08/30/2021 18:06:30 - INFO - __main__ - Step 27585: {'lr': 0.00046403143327240136, 'samples': 5296320, 'steps': 27584, 'loss/train': 1.8334565162658691} 08/30/2021 18:06:32 - INFO - __main__ - Step 27586: {'lr': 0.00046402869087076127, 'samples': 5296512, 'steps': 27585, 'loss/train': 1.7581672668457031} 08/30/2021 18:06:32 - INFO - __main__ - Step 27587: {'lr': 0.00046402594837268314, 'samples': 5296704, 'steps': 27586, 'loss/train': 1.6860690116882324} 08/30/2021 18:06:33 - INFO - __main__ - Step 27588: {'lr': 0.0004640232057781682, 'samples': 5296896, 'steps': 27587, 'loss/train': 1.6744991540908813} 08/30/2021 18:06:33 - INFO - __main__ - Step 27589: {'lr': 0.00046402046308721776, 'samples': 5297088, 'steps': 27588, 'loss/train': 1.4241410493850708} 08/30/2021 18:06:33 - INFO - __main__ - Step 27590: {'lr': 0.0004640177202998329, 'samples': 5297280, 'steps': 27589, 'loss/train': 1.7457475662231445} 08/30/2021 18:06:35 - INFO - __main__ - Step 27591: {'lr': 0.00046401497741601505, 'samples': 5297472, 'steps': 27590, 'loss/train': 1.491798996925354} 08/30/2021 18:06:35 - INFO - __main__ - Step 27592: {'lr': 0.00046401223443576537, 'samples': 5297664, 'steps': 27591, 'loss/train': 1.9089938402175903} 08/30/2021 18:06:36 - INFO - __main__ - Step 27593: {'lr': 0.00046400949135908497, 'samples': 5297856, 'steps': 27592, 'loss/train': 1.1968921422958374} 08/30/2021 18:06:36 - INFO - __main__ - Step 27594: {'lr': 0.0004640067481859753, 'samples': 5298048, 'steps': 27593, 'loss/train': 1.713312029838562} 08/30/2021 18:06:36 - INFO - __main__ - Step 27595: {'lr': 0.00046400400491643744, 'samples': 5298240, 'steps': 27594, 'loss/train': 1.557417392730713} 08/30/2021 18:06:38 - INFO - __main__ - Step 27596: {'lr': 0.00046400126155047265, 'samples': 5298432, 'steps': 27595, 'loss/train': 1.3746501207351685} 08/30/2021 18:06:38 - INFO - __main__ - Step 27597: {'lr': 0.0004639985180880822, 'samples': 5298624, 'steps': 27596, 'loss/train': 1.3247319459915161} 08/30/2021 18:06:39 - INFO - __main__ - Step 27598: {'lr': 0.0004639957745292674, 'samples': 5298816, 'steps': 27597, 'loss/train': 2.03164005279541} 08/30/2021 18:06:39 - INFO - __main__ - Step 27599: {'lr': 0.00046399303087402935, 'samples': 5299008, 'steps': 27598, 'loss/train': 2.0356204509735107} 08/30/2021 18:06:39 - INFO - __main__ - Step 27600: {'lr': 0.00046399028712236935, 'samples': 5299200, 'steps': 27599, 'loss/train': 1.4001091718673706} 08/30/2021 18:06:40 - INFO - __main__ - Step 27601: {'lr': 0.0004639875432742886, 'samples': 5299392, 'steps': 27600, 'loss/train': 1.5931395292282104} 08/30/2021 18:06:41 - INFO - __main__ - Step 27602: {'lr': 0.0004639847993297884, 'samples': 5299584, 'steps': 27601, 'loss/train': 1.3520549535751343} 08/30/2021 18:06:42 - INFO - __main__ - Step 27603: {'lr': 0.00046398205528886994, 'samples': 5299776, 'steps': 27602, 'loss/train': 1.39707350730896} 08/30/2021 18:06:42 - INFO - __main__ - Step 27604: {'lr': 0.00046397931115153444, 'samples': 5299968, 'steps': 27603, 'loss/train': 1.2671536207199097} 08/30/2021 18:06:42 - INFO - __main__ - Step 27605: {'lr': 0.0004639765669177833, 'samples': 5300160, 'steps': 27604, 'loss/train': 1.5328627824783325} 08/30/2021 18:06:43 - INFO - __main__ - Step 27606: {'lr': 0.00046397382258761744, 'samples': 5300352, 'steps': 27605, 'loss/train': 1.51702082157135} 08/30/2021 18:06:44 - INFO - __main__ - Step 27607: {'lr': 0.0004639710781610384, 'samples': 5300544, 'steps': 27606, 'loss/train': 1.5836141109466553} 08/30/2021 18:06:45 - INFO - __main__ - Step 27608: {'lr': 0.00046396833363804724, 'samples': 5300736, 'steps': 27607, 'loss/train': 1.9068845510482788} 08/30/2021 18:06:45 - INFO - __main__ - Step 27609: {'lr': 0.00046396558901864527, 'samples': 5300928, 'steps': 27608, 'loss/train': 1.3824971914291382} 08/30/2021 18:06:45 - INFO - __main__ - Step 27610: {'lr': 0.0004639628443028337, 'samples': 5301120, 'steps': 27609, 'loss/train': 1.9928569793701172} 08/30/2021 18:06:46 - INFO - __main__ - Step 27611: {'lr': 0.0004639600994906138, 'samples': 5301312, 'steps': 27610, 'loss/train': 1.3614623546600342} 08/30/2021 18:06:47 - INFO - __main__ - Step 27612: {'lr': 0.00046395735458198674, 'samples': 5301504, 'steps': 27611, 'loss/train': 1.3806707859039307} 08/30/2021 18:06:48 - INFO - __main__ - Step 27613: {'lr': 0.0004639546095769538, 'samples': 5301696, 'steps': 27612, 'loss/train': 1.3501548767089844} 08/30/2021 18:06:48 - INFO - __main__ - Step 27614: {'lr': 0.00046395186447551617, 'samples': 5301888, 'steps': 27613, 'loss/train': 1.0119539499282837} 08/30/2021 18:06:48 - INFO - __main__ - Step 27615: {'lr': 0.00046394911927767526, 'samples': 5302080, 'steps': 27614, 'loss/train': 1.538619875907898} 08/30/2021 18:06:49 - INFO - __main__ - Step 27616: {'lr': 0.0004639463739834321, 'samples': 5302272, 'steps': 27615, 'loss/train': 1.4405438899993896} 08/30/2021 18:06:50 - INFO - __main__ - Step 27617: {'lr': 0.00046394362859278793, 'samples': 5302464, 'steps': 27616, 'loss/train': 1.3817137479782104} 08/30/2021 18:06:51 - INFO - __main__ - Step 27618: {'lr': 0.00046394088310574416, 'samples': 5302656, 'steps': 27617, 'loss/train': 1.5324381589889526} 08/30/2021 18:06:51 - INFO - __main__ - Step 27619: {'lr': 0.000463938137522302, 'samples': 5302848, 'steps': 27618, 'loss/train': 0.08424973487854004} 08/30/2021 18:06:52 - INFO - __main__ - Step 27620: {'lr': 0.00046393539184246246, 'samples': 5303040, 'steps': 27619, 'loss/train': 2.311727523803711} 08/30/2021 18:06:52 - INFO - __main__ - Step 27621: {'lr': 0.000463932646066227, 'samples': 5303232, 'steps': 27620, 'loss/train': 1.9144822359085083} 08/30/2021 18:06:54 - INFO - __main__ - Step 27622: {'lr': 0.0004639299001935968, 'samples': 5303424, 'steps': 27621, 'loss/train': 2.442072629928589} 08/30/2021 18:06:54 - INFO - __main__ - Step 27623: {'lr': 0.0004639271542245731, 'samples': 5303616, 'steps': 27622, 'loss/train': 1.1727242469787598} 08/30/2021 18:06:55 - INFO - __main__ - Step 27624: {'lr': 0.000463924408159157, 'samples': 5303808, 'steps': 27623, 'loss/train': 1.5860928297042847} 08/30/2021 18:06:55 - INFO - __main__ - Step 27625: {'lr': 0.00046392166199735, 'samples': 5304000, 'steps': 27624, 'loss/train': 4.4631733894348145} 08/30/2021 18:06:55 - INFO - __main__ - Step 27626: {'lr': 0.00046391891573915325, 'samples': 5304192, 'steps': 27625, 'loss/train': 1.963142991065979} 08/30/2021 18:06:56 - INFO - __main__ - Step 27627: {'lr': 0.0004639161693845678, 'samples': 5304384, 'steps': 27626, 'loss/train': 1.4789601564407349} 08/30/2021 18:06:58 - INFO - __main__ - Step 27628: {'lr': 0.0004639134229335951, 'samples': 5304576, 'steps': 27627, 'loss/train': 1.5334399938583374} 08/30/2021 18:06:58 - INFO - __main__ - Step 27629: {'lr': 0.0004639106763862363, 'samples': 5304768, 'steps': 27628, 'loss/train': 2.497802495956421} 08/30/2021 18:06:59 - INFO - __main__ - Step 27630: {'lr': 0.00046390792974249263, 'samples': 5304960, 'steps': 27629, 'loss/train': 1.5521652698516846} 08/30/2021 18:06:59 - INFO - __main__ - Step 27631: {'lr': 0.00046390518300236535, 'samples': 5305152, 'steps': 27630, 'loss/train': 0.13609883189201355} 08/30/2021 18:07:00 - INFO - __main__ - Step 27632: {'lr': 0.0004639024361658557, 'samples': 5305344, 'steps': 27631, 'loss/train': 1.7635130882263184} 08/30/2021 18:07:00 - INFO - __main__ - Step 27633: {'lr': 0.00046389968923296496, 'samples': 5305536, 'steps': 27632, 'loss/train': 0.6495070457458496} 08/30/2021 18:07:00 - INFO - __main__ - Step 27634: {'lr': 0.0004638969422036943, 'samples': 5305728, 'steps': 27633, 'loss/train': 0.4948667287826538} 08/30/2021 18:07:02 - INFO - __main__ - Step 27635: {'lr': 0.00046389419507804493, 'samples': 5305920, 'steps': 27634, 'loss/train': 0.7599722146987915} 08/30/2021 18:07:03 - INFO - __main__ - Step 27636: {'lr': 0.00046389144785601813, 'samples': 5306112, 'steps': 27635, 'loss/train': 1.4174884557724} 08/30/2021 18:07:03 - INFO - __main__ - Step 27637: {'lr': 0.0004638887005376152, 'samples': 5306304, 'steps': 27636, 'loss/train': 1.350616693496704} 08/30/2021 18:07:03 - INFO - __main__ - Step 27638: {'lr': 0.0004638859531228373, 'samples': 5306496, 'steps': 27637, 'loss/train': 1.6200162172317505} 08/30/2021 18:07:04 - INFO - __main__ - Step 27639: {'lr': 0.00046388320561168567, 'samples': 5306688, 'steps': 27638, 'loss/train': 1.3006216287612915} 08/30/2021 18:07:05 - INFO - __main__ - Step 27640: {'lr': 0.00046388045800416157, 'samples': 5306880, 'steps': 27639, 'loss/train': 1.7380802631378174} 08/30/2021 18:07:06 - INFO - __main__ - Step 27641: {'lr': 0.00046387771030026627, 'samples': 5307072, 'steps': 27640, 'loss/train': 1.850737452507019} 08/30/2021 18:07:06 - INFO - __main__ - Step 27642: {'lr': 0.00046387496250000095, 'samples': 5307264, 'steps': 27641, 'loss/train': 1.9918535947799683} 08/30/2021 18:07:06 - INFO - __main__ - Step 27643: {'lr': 0.0004638722146033669, 'samples': 5307456, 'steps': 27642, 'loss/train': 1.4941896200180054} 08/30/2021 18:07:07 - INFO - __main__ - Step 27644: {'lr': 0.0004638694666103653, 'samples': 5307648, 'steps': 27643, 'loss/train': 2.074228525161743} 08/30/2021 18:07:08 - INFO - __main__ - Step 27645: {'lr': 0.00046386671852099743, 'samples': 5307840, 'steps': 27644, 'loss/train': 1.5714284181594849} 08/30/2021 18:07:09 - INFO - __main__ - Step 27646: {'lr': 0.0004638639703352645, 'samples': 5308032, 'steps': 27645, 'loss/train': 1.7330057621002197} 08/30/2021 18:07:09 - INFO - __main__ - Step 27647: {'lr': 0.00046386122205316783, 'samples': 5308224, 'steps': 27646, 'loss/train': 1.4205405712127686} 08/30/2021 18:07:09 - INFO - __main__ - Step 27648: {'lr': 0.0004638584736747085, 'samples': 5308416, 'steps': 27647, 'loss/train': 1.7681492567062378} 08/30/2021 18:07:10 - INFO - __main__ - Step 27649: {'lr': 0.00046385572519988793, 'samples': 5308608, 'steps': 27648, 'loss/train': 1.0372158288955688} 08/30/2021 18:07:11 - INFO - __main__ - Step 27650: {'lr': 0.00046385297662870716, 'samples': 5308800, 'steps': 27649, 'loss/train': 1.9399640560150146} 08/30/2021 18:07:12 - INFO - __main__ - Step 27651: {'lr': 0.00046385022796116766, 'samples': 5308992, 'steps': 27650, 'loss/train': 1.3714888095855713} 08/30/2021 18:07:12 - INFO - __main__ - Step 27652: {'lr': 0.0004638474791972705, 'samples': 5309184, 'steps': 27651, 'loss/train': 1.6928040981292725} 08/30/2021 18:07:12 - INFO - __main__ - Step 27653: {'lr': 0.000463844730337017, 'samples': 5309376, 'steps': 27652, 'loss/train': 0.8629988431930542} 08/30/2021 18:07:13 - INFO - __main__ - Step 27654: {'lr': 0.00046384198138040825, 'samples': 5309568, 'steps': 27653, 'loss/train': 1.1709786653518677} 08/30/2021 18:07:14 - INFO - __main__ - Step 27655: {'lr': 0.00046383923232744565, 'samples': 5309760, 'steps': 27654, 'loss/train': 1.6784054040908813} 08/30/2021 18:07:15 - INFO - __main__ - Step 27656: {'lr': 0.00046383648317813045, 'samples': 5309952, 'steps': 27655, 'loss/train': 1.5674488544464111} 08/30/2021 18:07:15 - INFO - __main__ - Step 27657: {'lr': 0.0004638337339324638, 'samples': 5310144, 'steps': 27656, 'loss/train': 0.7143456935882568} 08/30/2021 18:07:16 - INFO - __main__ - Step 27658: {'lr': 0.00046383098459044697, 'samples': 5310336, 'steps': 27657, 'loss/train': 1.4924540519714355} 08/30/2021 18:07:16 - INFO - __main__ - Step 27659: {'lr': 0.0004638282351520812, 'samples': 5310528, 'steps': 27658, 'loss/train': 1.1130164861679077} 08/30/2021 18:07:18 - INFO - __main__ - Step 27660: {'lr': 0.00046382548561736773, 'samples': 5310720, 'steps': 27659, 'loss/train': 1.682997226715088} 08/30/2021 18:07:18 - INFO - __main__ - Step 27661: {'lr': 0.0004638227359863078, 'samples': 5310912, 'steps': 27660, 'loss/train': 1.1483876705169678} 08/30/2021 18:07:18 - INFO - __main__ - Step 27662: {'lr': 0.0004638199862589026, 'samples': 5311104, 'steps': 27661, 'loss/train': 1.8646984100341797} 08/30/2021 18:07:19 - INFO - __main__ - Step 27663: {'lr': 0.0004638172364351535, 'samples': 5311296, 'steps': 27662, 'loss/train': 1.0410184860229492} 08/30/2021 18:07:19 - INFO - __main__ - Step 27664: {'lr': 0.00046381448651506153, 'samples': 5311488, 'steps': 27663, 'loss/train': 1.3917937278747559} 08/30/2021 18:07:21 - INFO - __main__ - Step 27665: {'lr': 0.00046381173649862815, 'samples': 5311680, 'steps': 27664, 'loss/train': 1.5901403427124023} 08/30/2021 18:07:21 - INFO - __main__ - Step 27666: {'lr': 0.00046380898638585447, 'samples': 5311872, 'steps': 27665, 'loss/train': 1.7387356758117676} 08/30/2021 18:07:22 - INFO - __main__ - Step 27667: {'lr': 0.0004638062361767418, 'samples': 5312064, 'steps': 27666, 'loss/train': 0.9809238314628601} 08/30/2021 18:07:22 - INFO - __main__ - Step 27668: {'lr': 0.00046380348587129127, 'samples': 5312256, 'steps': 27667, 'loss/train': 1.879568099975586} 08/30/2021 18:07:22 - INFO - __main__ - Step 27669: {'lr': 0.0004638007354695042, 'samples': 5312448, 'steps': 27668, 'loss/train': 2.2002036571502686} 08/30/2021 18:07:23 - INFO - __main__ - Step 27670: {'lr': 0.0004637979849713818, 'samples': 5312640, 'steps': 27669, 'loss/train': 1.5881483554840088} 08/30/2021 18:07:25 - INFO - __main__ - Step 27671: {'lr': 0.0004637952343769254, 'samples': 5312832, 'steps': 27670, 'loss/train': 1.7404872179031372} 08/30/2021 18:07:25 - INFO - __main__ - Step 27672: {'lr': 0.00046379248368613615, 'samples': 5313024, 'steps': 27671, 'loss/train': 1.6770353317260742} 08/30/2021 18:07:25 - INFO - __main__ - Step 27673: {'lr': 0.0004637897328990153, 'samples': 5313216, 'steps': 27672, 'loss/train': 1.2560689449310303} 08/30/2021 18:07:26 - INFO - __main__ - Step 27674: {'lr': 0.000463786982015564, 'samples': 5313408, 'steps': 27673, 'loss/train': 1.4442033767700195} 08/30/2021 18:07:26 - INFO - __main__ - Step 27675: {'lr': 0.00046378423103578373, 'samples': 5313600, 'steps': 27674, 'loss/train': 1.6111303567886353} 08/30/2021 18:07:28 - INFO - __main__ - Step 27676: {'lr': 0.0004637814799596755, 'samples': 5313792, 'steps': 27675, 'loss/train': 0.23090513050556183} 08/30/2021 18:07:28 - INFO - __main__ - Step 27677: {'lr': 0.00046377872878724066, 'samples': 5313984, 'steps': 27676, 'loss/train': 1.3465864658355713} 08/30/2021 18:07:29 - INFO - __main__ - Step 27678: {'lr': 0.0004637759775184804, 'samples': 5314176, 'steps': 27677, 'loss/train': 0.9396185278892517} 08/30/2021 18:07:29 - INFO - __main__ - Step 27679: {'lr': 0.000463773226153396, 'samples': 5314368, 'steps': 27678, 'loss/train': 1.0420961380004883} 08/30/2021 18:07:29 - INFO - __main__ - Step 27680: {'lr': 0.00046377047469198875, 'samples': 5314560, 'steps': 27679, 'loss/train': 0.2202690839767456} 08/30/2021 18:07:30 - INFO - __main__ - Step 27681: {'lr': 0.00046376772313425974, 'samples': 5314752, 'steps': 27680, 'loss/train': 1.2297792434692383} 08/30/2021 18:07:31 - INFO - __main__ - Step 27682: {'lr': 0.0004637649714802102, 'samples': 5314944, 'steps': 27681, 'loss/train': 1.2670255899429321} 08/30/2021 18:07:32 - INFO - __main__ - Step 27683: {'lr': 0.0004637622197298417, 'samples': 5315136, 'steps': 27682, 'loss/train': 1.1371203660964966} 08/30/2021 18:07:32 - INFO - __main__ - Step 27684: {'lr': 0.000463759467883155, 'samples': 5315328, 'steps': 27683, 'loss/train': 1.7195202112197876} 08/30/2021 18:07:32 - INFO - __main__ - Step 27685: {'lr': 0.0004637567159401518, 'samples': 5315520, 'steps': 27684, 'loss/train': 2.2589163780212402} 08/30/2021 18:07:33 - INFO - __main__ - Step 27686: {'lr': 0.00046375396390083303, 'samples': 5315712, 'steps': 27685, 'loss/train': 1.4878872632980347} 08/30/2021 18:07:35 - INFO - __main__ - Step 27687: {'lr': 0.0004637512117652, 'samples': 5315904, 'steps': 27686, 'loss/train': 0.6817157864570618} 08/30/2021 18:07:35 - INFO - __main__ - Step 27688: {'lr': 0.00046374845953325394, 'samples': 5316096, 'steps': 27687, 'loss/train': 1.3332120180130005} 08/30/2021 18:07:36 - INFO - __main__ - Step 27689: {'lr': 0.0004637457072049962, 'samples': 5316288, 'steps': 27688, 'loss/train': 1.6221702098846436} 08/30/2021 18:07:36 - INFO - __main__ - Step 27690: {'lr': 0.0004637429547804279, 'samples': 5316480, 'steps': 27689, 'loss/train': 0.9120870232582092} 08/30/2021 18:07:36 - INFO - __main__ - Step 27691: {'lr': 0.0004637402022595503, 'samples': 5316672, 'steps': 27690, 'loss/train': 3.143947124481201} 08/30/2021 18:07:38 - INFO - __main__ - Step 27692: {'lr': 0.0004637374496423647, 'samples': 5316864, 'steps': 27691, 'loss/train': 1.8292323350906372} 08/30/2021 18:07:39 - INFO - __main__ - Step 27693: {'lr': 0.0004637346969288723, 'samples': 5317056, 'steps': 27692, 'loss/train': 1.2111611366271973} 08/30/2021 18:07:39 - INFO - __main__ - Step 27694: {'lr': 0.0004637319441190743, 'samples': 5317248, 'steps': 27693, 'loss/train': 1.5030843019485474} 08/30/2021 18:07:39 - INFO - __main__ - Step 27695: {'lr': 0.00046372919121297207, 'samples': 5317440, 'steps': 27694, 'loss/train': 1.5317778587341309} 08/30/2021 18:07:40 - INFO - __main__ - Step 27696: {'lr': 0.0004637264382105667, 'samples': 5317632, 'steps': 27695, 'loss/train': 6.138783931732178} 08/30/2021 18:07:40 - INFO - __main__ - Step 27697: {'lr': 0.00046372368511185953, 'samples': 5317824, 'steps': 27696, 'loss/train': 1.5839647054672241} 08/30/2021 18:07:41 - INFO - __main__ - Step 27698: {'lr': 0.0004637209319168517, 'samples': 5318016, 'steps': 27697, 'loss/train': 1.3210899829864502} 08/30/2021 18:07:42 - INFO - __main__ - Step 27699: {'lr': 0.0004637181786255446, 'samples': 5318208, 'steps': 27698, 'loss/train': 1.011793613433838} 08/30/2021 18:07:42 - INFO - __main__ - Step 27700: {'lr': 0.0004637154252379394, 'samples': 5318400, 'steps': 27699, 'loss/train': 1.6124320030212402} 08/30/2021 18:07:42 - INFO - __main__ - Step 27701: {'lr': 0.00046371267175403724, 'samples': 5318592, 'steps': 27700, 'loss/train': 1.9815433025360107} 08/30/2021 18:07:43 - INFO - __main__ - Step 27702: {'lr': 0.0004637099181738395, 'samples': 5318784, 'steps': 27701, 'loss/train': 1.3882966041564941} 08/30/2021 18:07:44 - INFO - __main__ - Step 27703: {'lr': 0.00046370716449734733, 'samples': 5318976, 'steps': 27702, 'loss/train': 1.6488699913024902} 08/30/2021 18:07:45 - INFO - __main__ - Step 27704: {'lr': 0.00046370441072456206, 'samples': 5319168, 'steps': 27703, 'loss/train': 1.132298231124878} 08/30/2021 18:07:45 - INFO - __main__ - Step 27705: {'lr': 0.00046370165685548484, 'samples': 5319360, 'steps': 27704, 'loss/train': 1.264633297920227} 08/30/2021 18:07:45 - INFO - __main__ - Step 27706: {'lr': 0.00046369890289011696, 'samples': 5319552, 'steps': 27705, 'loss/train': 1.7231214046478271} 08/30/2021 18:07:46 - INFO - __main__ - Step 27707: {'lr': 0.0004636961488284597, 'samples': 5319744, 'steps': 27706, 'loss/train': 1.0639294385910034} 08/30/2021 18:07:47 - INFO - __main__ - Step 27708: {'lr': 0.0004636933946705142, 'samples': 5319936, 'steps': 27707, 'loss/train': 1.6238598823547363} 08/30/2021 18:07:48 - INFO - __main__ - Step 27709: {'lr': 0.00046369064041628175, 'samples': 5320128, 'steps': 27708, 'loss/train': 1.059350609779358} 08/30/2021 18:07:48 - INFO - __main__ - Step 27710: {'lr': 0.00046368788606576363, 'samples': 5320320, 'steps': 27709, 'loss/train': 0.749843418598175} 08/30/2021 18:07:48 - INFO - __main__ - Step 27711: {'lr': 0.00046368513161896104, 'samples': 5320512, 'steps': 27710, 'loss/train': 0.402189701795578} 08/30/2021 18:07:49 - INFO - __main__ - Step 27712: {'lr': 0.0004636823770758752, 'samples': 5320704, 'steps': 27711, 'loss/train': 2.0030534267425537} 08/30/2021 18:07:49 - INFO - __main__ - Step 27713: {'lr': 0.0004636796224365074, 'samples': 5320896, 'steps': 27712, 'loss/train': 0.44293150305747986} 08/30/2021 18:07:51 - INFO - __main__ - Step 27714: {'lr': 0.0004636768677008588, 'samples': 5321088, 'steps': 27713, 'loss/train': 1.1427805423736572} 08/30/2021 18:07:51 - INFO - __main__ - Step 27715: {'lr': 0.0004636741128689308, 'samples': 5321280, 'steps': 27714, 'loss/train': 1.3262362480163574} 08/30/2021 18:07:52 - INFO - __main__ - Step 27716: {'lr': 0.00046367135794072445, 'samples': 5321472, 'steps': 27715, 'loss/train': 1.7071841955184937} 08/30/2021 18:07:52 - INFO - __main__ - Step 27717: {'lr': 0.0004636686029162411, 'samples': 5321664, 'steps': 27716, 'loss/train': 1.0002169609069824} 08/30/2021 18:07:52 - INFO - __main__ - Step 27718: {'lr': 0.000463665847795482, 'samples': 5321856, 'steps': 27717, 'loss/train': 1.683854341506958} 08/30/2021 18:07:54 - INFO - __main__ - Step 27719: {'lr': 0.0004636630925784484, 'samples': 5322048, 'steps': 27718, 'loss/train': 1.710624098777771} 08/30/2021 18:07:54 - INFO - __main__ - Step 27720: {'lr': 0.0004636603372651415, 'samples': 5322240, 'steps': 27719, 'loss/train': 1.7615082263946533} 08/30/2021 18:07:54 - INFO - __main__ - Step 27721: {'lr': 0.0004636575818555625, 'samples': 5322432, 'steps': 27720, 'loss/train': 1.3039824962615967} 08/30/2021 18:07:55 - INFO - __main__ - Step 27722: {'lr': 0.00046365482634971275, 'samples': 5322624, 'steps': 27721, 'loss/train': 1.5380810499191284} 08/30/2021 18:07:55 - INFO - __main__ - Step 27723: {'lr': 0.00046365207074759344, 'samples': 5322816, 'steps': 27722, 'loss/train': 1.315588355064392} 08/30/2021 18:07:57 - INFO - __main__ - Step 27724: {'lr': 0.0004636493150492057, 'samples': 5323008, 'steps': 27723, 'loss/train': 1.7833211421966553} 08/30/2021 18:07:57 - INFO - __main__ - Step 27725: {'lr': 0.00046364655925455094, 'samples': 5323200, 'steps': 27724, 'loss/train': 1.352582335472107} 08/30/2021 18:07:57 - INFO - __main__ - Step 27726: {'lr': 0.0004636438033636303, 'samples': 5323392, 'steps': 27725, 'loss/train': 1.3288015127182007} 08/30/2021 18:07:58 - INFO - __main__ - Step 27727: {'lr': 0.00046364104737644515, 'samples': 5323584, 'steps': 27726, 'loss/train': 1.1080595254898071} 08/30/2021 18:07:58 - INFO - __main__ - Step 27728: {'lr': 0.00046363829129299655, 'samples': 5323776, 'steps': 27727, 'loss/train': 1.3275203704833984} 08/30/2021 18:08:00 - INFO - __main__ - Step 27729: {'lr': 0.0004636355351132859, 'samples': 5323968, 'steps': 27728, 'loss/train': 1.7928476333618164} 08/30/2021 18:08:00 - INFO - __main__ - Step 27730: {'lr': 0.00046363277883731437, 'samples': 5324160, 'steps': 27729, 'loss/train': 1.2326266765594482} 08/30/2021 18:08:01 - INFO - __main__ - Step 27731: {'lr': 0.0004636300224650831, 'samples': 5324352, 'steps': 27730, 'loss/train': 1.0478222370147705} 08/30/2021 18:08:01 - INFO - __main__ - Step 27732: {'lr': 0.00046362726599659355, 'samples': 5324544, 'steps': 27731, 'loss/train': 1.4498744010925293} 08/30/2021 18:08:01 - INFO - __main__ - Step 27733: {'lr': 0.0004636245094318468, 'samples': 5324736, 'steps': 27732, 'loss/train': 1.5391539335250854} 08/30/2021 18:08:03 - INFO - __main__ - Step 27734: {'lr': 0.0004636217527708442, 'samples': 5324928, 'steps': 27733, 'loss/train': 1.9058687686920166} 08/30/2021 18:08:03 - INFO - __main__ - Step 27735: {'lr': 0.0004636189960135869, 'samples': 5325120, 'steps': 27734, 'loss/train': 1.4752416610717773} 08/30/2021 18:08:04 - INFO - __main__ - Step 27736: {'lr': 0.0004636162391600761, 'samples': 5325312, 'steps': 27735, 'loss/train': 1.8577532768249512} 08/30/2021 18:08:04 - INFO - __main__ - Step 27737: {'lr': 0.00046361348221031316, 'samples': 5325504, 'steps': 27736, 'loss/train': 1.8980063199996948} 08/30/2021 18:08:04 - INFO - __main__ - Step 27738: {'lr': 0.00046361072516429936, 'samples': 5325696, 'steps': 27737, 'loss/train': 1.3145451545715332} 08/30/2021 18:08:06 - INFO - __main__ - Step 27739: {'lr': 0.0004636079680220358, 'samples': 5325888, 'steps': 27738, 'loss/train': 4.672932147979736} 08/30/2021 18:08:06 - INFO - __main__ - Step 27740: {'lr': 0.0004636052107835238, 'samples': 5326080, 'steps': 27739, 'loss/train': 1.2719616889953613} 08/30/2021 18:08:07 - INFO - __main__ - Step 27741: {'lr': 0.0004636024534487646, 'samples': 5326272, 'steps': 27740, 'loss/train': 1.4490892887115479} 08/30/2021 18:08:07 - INFO - __main__ - Step 27742: {'lr': 0.0004635996960177594, 'samples': 5326464, 'steps': 27741, 'loss/train': 0.4310019612312317} 08/30/2021 18:08:07 - INFO - __main__ - Step 27743: {'lr': 0.0004635969384905095, 'samples': 5326656, 'steps': 27742, 'loss/train': 1.8816343545913696} 08/30/2021 18:08:10 - INFO - __main__ - Step 27744: {'lr': 0.0004635941808670161, 'samples': 5326848, 'steps': 27743, 'loss/train': 1.5247331857681274} 08/30/2021 18:08:10 - INFO - __main__ - Step 27745: {'lr': 0.00046359142314728047, 'samples': 5327040, 'steps': 27744, 'loss/train': 1.325038194656372} 08/30/2021 18:08:10 - INFO - __main__ - Step 27746: {'lr': 0.00046358866533130385, 'samples': 5327232, 'steps': 27745, 'loss/train': 1.7034525871276855} 08/30/2021 18:08:11 - INFO - __main__ - Step 27747: {'lr': 0.00046358590741908744, 'samples': 5327424, 'steps': 27746, 'loss/train': 0.06704515218734741} 08/30/2021 18:08:11 - INFO - __main__ - Step 27748: {'lr': 0.0004635831494106325, 'samples': 5327616, 'steps': 27747, 'loss/train': 1.8906948566436768} 08/30/2021 18:08:11 - INFO - __main__ - Step 27749: {'lr': 0.0004635803913059404, 'samples': 5327808, 'steps': 27748, 'loss/train': 1.3078497648239136} 08/30/2021 18:08:13 - INFO - __main__ - Step 27750: {'lr': 0.00046357763310501216, 'samples': 5328000, 'steps': 27749, 'loss/train': 0.392612099647522} 08/30/2021 18:08:13 - INFO - __main__ - Step 27751: {'lr': 0.0004635748748078492, 'samples': 5328192, 'steps': 27750, 'loss/train': 1.9263042211532593} 08/30/2021 18:08:14 - INFO - __main__ - Step 27752: {'lr': 0.0004635721164144526, 'samples': 5328384, 'steps': 27751, 'loss/train': 1.4707145690917969} 08/30/2021 18:08:14 - INFO - __main__ - Step 27753: {'lr': 0.0004635693579248238, 'samples': 5328576, 'steps': 27752, 'loss/train': 1.5500909090042114} 08/30/2021 18:08:14 - INFO - __main__ - Step 27754: {'lr': 0.00046356659933896393, 'samples': 5328768, 'steps': 27753, 'loss/train': 1.6524235010147095} 08/30/2021 18:08:16 - INFO - __main__ - Step 27755: {'lr': 0.0004635638406568742, 'samples': 5328960, 'steps': 27754, 'loss/train': 1.7313227653503418} 08/30/2021 18:08:16 - INFO - __main__ - Step 27756: {'lr': 0.00046356108187855594, 'samples': 5329152, 'steps': 27755, 'loss/train': 1.8637701272964478} 08/30/2021 18:08:17 - INFO - __main__ - Step 27757: {'lr': 0.00046355832300401035, 'samples': 5329344, 'steps': 27756, 'loss/train': 2.080235481262207} 08/30/2021 18:08:17 - INFO - __main__ - Step 27758: {'lr': 0.0004635555640332386, 'samples': 5329536, 'steps': 27757, 'loss/train': 0.8100613951683044} 08/30/2021 18:08:17 - INFO - __main__ - Step 27759: {'lr': 0.0004635528049662421, 'samples': 5329728, 'steps': 27758, 'loss/train': 1.736909031867981} 08/30/2021 18:08:19 - INFO - __main__ - Step 27760: {'lr': 0.000463550045803022, 'samples': 5329920, 'steps': 27759, 'loss/train': 1.4985519647598267} 08/30/2021 18:08:19 - INFO - __main__ - Step 27761: {'lr': 0.00046354728654357947, 'samples': 5330112, 'steps': 27760, 'loss/train': 1.5650149583816528} 08/30/2021 18:08:20 - INFO - __main__ - Step 27762: {'lr': 0.00046354452718791586, 'samples': 5330304, 'steps': 27761, 'loss/train': 1.3432813882827759} 08/30/2021 18:08:20 - INFO - __main__ - Step 27763: {'lr': 0.0004635417677360324, 'samples': 5330496, 'steps': 27762, 'loss/train': 1.792452096939087} 08/30/2021 18:08:21 - INFO - __main__ - Step 27764: {'lr': 0.0004635390081879303, 'samples': 5330688, 'steps': 27763, 'loss/train': 1.4342265129089355} 08/30/2021 18:08:22 - INFO - __main__ - Step 27765: {'lr': 0.0004635362485436109, 'samples': 5330880, 'steps': 27764, 'loss/train': 1.653233289718628} 08/30/2021 18:08:22 - INFO - __main__ - Step 27766: {'lr': 0.00046353348880307524, 'samples': 5331072, 'steps': 27765, 'loss/train': 0.8268206715583801} 08/30/2021 18:08:23 - INFO - __main__ - Step 27767: {'lr': 0.0004635307289663248, 'samples': 5331264, 'steps': 27766, 'loss/train': 1.4286202192306519} 08/30/2021 18:08:23 - INFO - __main__ - Step 27768: {'lr': 0.0004635279690333606, 'samples': 5331456, 'steps': 27767, 'loss/train': 1.7019968032836914} 08/30/2021 18:08:23 - INFO - __main__ - Step 27769: {'lr': 0.00046352520900418403, 'samples': 5331648, 'steps': 27768, 'loss/train': 1.6425319910049438} 08/30/2021 18:08:24 - INFO - __main__ - Step 27770: {'lr': 0.00046352244887879623, 'samples': 5331840, 'steps': 27769, 'loss/train': 1.5490469932556152} 08/30/2021 18:08:25 - INFO - __main__ - Step 27771: {'lr': 0.0004635196886571986, 'samples': 5332032, 'steps': 27770, 'loss/train': 1.528705358505249} 08/30/2021 18:08:26 - INFO - __main__ - Step 27772: {'lr': 0.0004635169283393923, 'samples': 5332224, 'steps': 27771, 'loss/train': 1.4694417715072632} 08/30/2021 18:08:26 - INFO - __main__ - Step 27773: {'lr': 0.0004635141679253785, 'samples': 5332416, 'steps': 27772, 'loss/train': 1.395058512687683} 08/30/2021 18:08:27 - INFO - __main__ - Step 27774: {'lr': 0.0004635114074151586, 'samples': 5332608, 'steps': 27773, 'loss/train': 1.6506497859954834} 08/30/2021 18:08:27 - INFO - __main__ - Step 27775: {'lr': 0.00046350864680873375, 'samples': 5332800, 'steps': 27774, 'loss/train': 1.5567878484725952} 08/30/2021 18:08:29 - INFO - __main__ - Step 27776: {'lr': 0.0004635058861061051, 'samples': 5332992, 'steps': 27775, 'loss/train': 0.40147650241851807} 08/30/2021 18:08:30 - INFO - __main__ - Step 27777: {'lr': 0.00046350312530727403, 'samples': 5333184, 'steps': 27776, 'loss/train': 1.261691689491272} 08/30/2021 18:08:30 - INFO - __main__ - Step 27778: {'lr': 0.00046350036441224175, 'samples': 5333376, 'steps': 27777, 'loss/train': 0.7986395955085754} 08/30/2021 18:08:30 - INFO - __main__ - Step 27779: {'lr': 0.00046349760342100955, 'samples': 5333568, 'steps': 27778, 'loss/train': 0.9109395146369934} 08/30/2021 18:08:31 - INFO - __main__ - Step 27780: {'lr': 0.00046349484233357854, 'samples': 5333760, 'steps': 27779, 'loss/train': 0.8990795016288757} 08/30/2021 18:08:31 - INFO - __main__ - Step 27781: {'lr': 0.0004634920811499501, 'samples': 5333952, 'steps': 27780, 'loss/train': 1.3686414957046509} 08/30/2021 18:08:32 - INFO - __main__ - Step 27782: {'lr': 0.00046348931987012543, 'samples': 5334144, 'steps': 27781, 'loss/train': 1.518345594406128} 08/30/2021 18:08:33 - INFO - __main__ - Step 27783: {'lr': 0.00046348655849410577, 'samples': 5334336, 'steps': 27782, 'loss/train': 1.1290329694747925} 08/30/2021 18:08:33 - INFO - __main__ - Step 27784: {'lr': 0.0004634837970218924, 'samples': 5334528, 'steps': 27783, 'loss/train': 1.4776440858840942} 08/30/2021 18:08:34 - INFO - __main__ - Step 27785: {'lr': 0.0004634810354534864, 'samples': 5334720, 'steps': 27784, 'loss/train': 1.881790280342102} 08/30/2021 18:08:34 - INFO - __main__ - Step 27786: {'lr': 0.0004634782737888892, 'samples': 5334912, 'steps': 27785, 'loss/train': 1.4031047821044922} 08/30/2021 18:08:35 - INFO - __main__ - Step 27787: {'lr': 0.000463475512028102, 'samples': 5335104, 'steps': 27786, 'loss/train': 1.4787510633468628} 08/30/2021 18:08:36 - INFO - __main__ - Step 27788: {'lr': 0.000463472750171126, 'samples': 5335296, 'steps': 27787, 'loss/train': 0.08194834738969803} 08/30/2021 18:08:36 - INFO - __main__ - Step 27789: {'lr': 0.0004634699882179625, 'samples': 5335488, 'steps': 27788, 'loss/train': 1.0469577312469482} 08/30/2021 18:08:37 - INFO - __main__ - Step 27790: {'lr': 0.0004634672261686127, 'samples': 5335680, 'steps': 27789, 'loss/train': 1.6386882066726685} 08/30/2021 18:08:37 - INFO - __main__ - Step 27791: {'lr': 0.0004634644640230779, 'samples': 5335872, 'steps': 27790, 'loss/train': 0.704902708530426} 08/30/2021 18:08:39 - INFO - __main__ - Step 27792: {'lr': 0.0004634617017813593, 'samples': 5336064, 'steps': 27791, 'loss/train': 1.4183684587478638} 08/30/2021 18:08:39 - INFO - __main__ - Step 27793: {'lr': 0.00046345893944345806, 'samples': 5336256, 'steps': 27792, 'loss/train': 2.2018020153045654} 08/30/2021 18:08:39 - INFO - __main__ - Step 27794: {'lr': 0.00046345617700937564, 'samples': 5336448, 'steps': 27793, 'loss/train': 1.7258145809173584} 08/30/2021 18:08:40 - INFO - __main__ - Step 27795: {'lr': 0.0004634534144791131, 'samples': 5336640, 'steps': 27794, 'loss/train': 0.2126784771680832} 08/30/2021 18:08:40 - INFO - __main__ - Step 27796: {'lr': 0.0004634506518526718, 'samples': 5336832, 'steps': 27795, 'loss/train': 1.3140028715133667} 08/30/2021 18:08:40 - INFO - __main__ - Step 27797: {'lr': 0.00046344788913005286, 'samples': 5337024, 'steps': 27796, 'loss/train': 1.5470367670059204} 08/30/2021 18:08:42 - INFO - __main__ - Step 27798: {'lr': 0.00046344512631125756, 'samples': 5337216, 'steps': 27797, 'loss/train': 1.9504424333572388} 08/30/2021 18:08:43 - INFO - __main__ - Step 27799: {'lr': 0.00046344236339628724, 'samples': 5337408, 'steps': 27798, 'loss/train': 0.5643483400344849} 08/30/2021 18:08:43 - INFO - __main__ - Step 27800: {'lr': 0.0004634396003851431, 'samples': 5337600, 'steps': 27799, 'loss/train': 1.915980577468872} 08/30/2021 18:08:43 - INFO - __main__ - Step 27801: {'lr': 0.00046343683727782635, 'samples': 5337792, 'steps': 27800, 'loss/train': 1.5329633951187134} 08/30/2021 18:08:44 - INFO - __main__ - Step 27802: {'lr': 0.0004634340740743382, 'samples': 5337984, 'steps': 27801, 'loss/train': 1.385451078414917} 08/30/2021 18:08:46 - INFO - __main__ - Step 27803: {'lr': 0.00046343131077468, 'samples': 5338176, 'steps': 27802, 'loss/train': 0.9860138893127441} 08/30/2021 18:08:46 - INFO - __main__ - Step 27804: {'lr': 0.00046342854737885296, 'samples': 5338368, 'steps': 27803, 'loss/train': 1.3522201776504517} 08/30/2021 18:08:46 - INFO - __main__ - Step 27805: {'lr': 0.00046342578388685837, 'samples': 5338560, 'steps': 27804, 'loss/train': 1.868133544921875} 08/30/2021 18:08:47 - INFO - __main__ - Step 27806: {'lr': 0.0004634230202986973, 'samples': 5338752, 'steps': 27805, 'loss/train': 1.3344823122024536} 08/30/2021 18:08:47 - INFO - __main__ - Step 27807: {'lr': 0.0004634202566143712, 'samples': 5338944, 'steps': 27806, 'loss/train': 1.7863492965698242} 08/30/2021 18:08:49 - INFO - __main__ - Step 27808: {'lr': 0.00046341749283388117, 'samples': 5339136, 'steps': 27807, 'loss/train': 1.4219354391098022} 08/30/2021 18:08:49 - INFO - __main__ - Step 27809: {'lr': 0.0004634147289572285, 'samples': 5339328, 'steps': 27808, 'loss/train': 1.2044622898101807} 08/30/2021 18:08:49 - INFO - __main__ - Step 27810: {'lr': 0.00046341196498441453, 'samples': 5339520, 'steps': 27809, 'loss/train': 1.3901963233947754} 08/30/2021 18:08:50 - INFO - __main__ - Step 27811: {'lr': 0.0004634092009154403, 'samples': 5339712, 'steps': 27810, 'loss/train': 1.82839834690094} 08/30/2021 18:08:50 - INFO - __main__ - Step 27812: {'lr': 0.0004634064367503072, 'samples': 5339904, 'steps': 27811, 'loss/train': 0.2811654508113861} 08/30/2021 18:08:52 - INFO - __main__ - Step 27813: {'lr': 0.00046340367248901655, 'samples': 5340096, 'steps': 27812, 'loss/train': 1.6390193700790405} 08/30/2021 18:08:52 - INFO - __main__ - Step 27814: {'lr': 0.00046340090813156944, 'samples': 5340288, 'steps': 27813, 'loss/train': 1.7161142826080322} 08/30/2021 18:08:53 - INFO - __main__ - Step 27815: {'lr': 0.00046339814367796716, 'samples': 5340480, 'steps': 27814, 'loss/train': 1.2551450729370117} 08/30/2021 18:08:53 - INFO - __main__ - Step 27816: {'lr': 0.00046339537912821094, 'samples': 5340672, 'steps': 27815, 'loss/train': 2.1397149562835693} 08/30/2021 18:08:53 - INFO - __main__ - Step 27817: {'lr': 0.0004633926144823022, 'samples': 5340864, 'steps': 27816, 'loss/train': 1.7750980854034424} 08/30/2021 18:08:54 - INFO - __main__ - Step 27818: {'lr': 0.0004633898497402419, 'samples': 5341056, 'steps': 27817, 'loss/train': 1.7932462692260742} 08/30/2021 18:08:55 - INFO - __main__ - Step 27819: {'lr': 0.0004633870849020314, 'samples': 5341248, 'steps': 27818, 'loss/train': 0.15541088581085205} 08/30/2021 18:08:56 - INFO - __main__ - Step 27820: {'lr': 0.00046338431996767205, 'samples': 5341440, 'steps': 27819, 'loss/train': 5.489909648895264} 08/30/2021 18:08:56 - INFO - __main__ - Step 27821: {'lr': 0.00046338155493716503, 'samples': 5341632, 'steps': 27820, 'loss/train': 1.8474998474121094} 08/30/2021 18:08:56 - INFO - __main__ - Step 27822: {'lr': 0.0004633787898105115, 'samples': 5341824, 'steps': 27821, 'loss/train': 1.2274061441421509} 08/30/2021 18:08:57 - INFO - __main__ - Step 27823: {'lr': 0.0004633760245877129, 'samples': 5342016, 'steps': 27822, 'loss/train': 1.5886231660842896} 08/30/2021 18:08:58 - INFO - __main__ - Step 27824: {'lr': 0.0004633732592687703, 'samples': 5342208, 'steps': 27823, 'loss/train': 0.9894622564315796} 08/30/2021 18:08:59 - INFO - __main__ - Step 27825: {'lr': 0.00046337049385368495, 'samples': 5342400, 'steps': 27824, 'loss/train': 1.9861916303634644} 08/30/2021 18:08:59 - INFO - __main__ - Step 27826: {'lr': 0.00046336772834245824, 'samples': 5342592, 'steps': 27825, 'loss/train': 1.5195856094360352} 08/30/2021 18:08:59 - INFO - __main__ - Step 27827: {'lr': 0.0004633649627350912, 'samples': 5342784, 'steps': 27826, 'loss/train': 1.1240161657333374} 08/30/2021 18:09:00 - INFO - __main__ - Step 27828: {'lr': 0.00046336219703158526, 'samples': 5342976, 'steps': 27827, 'loss/train': 1.9857053756713867} 08/30/2021 18:09:02 - INFO - __main__ - Step 27829: {'lr': 0.00046335943123194164, 'samples': 5343168, 'steps': 27828, 'loss/train': 1.4039204120635986} 08/30/2021 18:09:02 - INFO - __main__ - Step 27830: {'lr': 0.0004633566653361615, 'samples': 5343360, 'steps': 27829, 'loss/train': 1.4734183549880981} 08/30/2021 18:09:03 - INFO - __main__ - Step 27831: {'lr': 0.0004633538993442462, 'samples': 5343552, 'steps': 27830, 'loss/train': 1.527032732963562} 08/30/2021 18:09:03 - INFO - __main__ - Step 27832: {'lr': 0.00046335113325619685, 'samples': 5343744, 'steps': 27831, 'loss/train': 1.4288867712020874} 08/30/2021 18:09:03 - INFO - __main__ - Step 27833: {'lr': 0.00046334836707201486, 'samples': 5343936, 'steps': 27832, 'loss/train': 1.7638781070709229} 08/30/2021 18:09:04 - INFO - __main__ - Step 27834: {'lr': 0.0004633456007917013, 'samples': 5344128, 'steps': 27833, 'loss/train': 1.0613548755645752} 08/30/2021 18:09:04 - INFO - __main__ - Step 27835: {'lr': 0.0004633428344152576, 'samples': 5344320, 'steps': 27834, 'loss/train': 1.0412993431091309} 08/30/2021 18:09:06 - INFO - __main__ - Step 27836: {'lr': 0.0004633400679426848, 'samples': 5344512, 'steps': 27835, 'loss/train': 1.024503231048584} 08/30/2021 18:09:06 - INFO - __main__ - Step 27837: {'lr': 0.00046333730137398433, 'samples': 5344704, 'steps': 27836, 'loss/train': 0.8051562309265137} 08/30/2021 18:09:07 - INFO - __main__ - Step 27838: {'lr': 0.00046333453470915736, 'samples': 5344896, 'steps': 27837, 'loss/train': 0.09756675362586975} 08/30/2021 18:09:07 - INFO - __main__ - Step 27839: {'lr': 0.0004633317679482051, 'samples': 5345088, 'steps': 27838, 'loss/train': 1.6739451885223389} 08/30/2021 18:09:07 - INFO - __main__ - Step 27840: {'lr': 0.00046332900109112893, 'samples': 5345280, 'steps': 27839, 'loss/train': 1.2744837999343872} 08/30/2021 18:09:09 - INFO - __main__ - Step 27841: {'lr': 0.0004633262341379299, 'samples': 5345472, 'steps': 27840, 'loss/train': 1.4695515632629395} 08/30/2021 18:09:09 - INFO - __main__ - Step 27842: {'lr': 0.0004633234670886094, 'samples': 5345664, 'steps': 27841, 'loss/train': 1.4233691692352295} 08/30/2021 18:09:10 - INFO - __main__ - Step 27843: {'lr': 0.0004633206999431686, 'samples': 5345856, 'steps': 27842, 'loss/train': 1.7822850942611694} 08/30/2021 18:09:10 - INFO - __main__ - Step 27844: {'lr': 0.00046331793270160885, 'samples': 5346048, 'steps': 27843, 'loss/train': 1.6514739990234375} 08/30/2021 18:09:10 - INFO - __main__ - Step 27845: {'lr': 0.0004633151653639314, 'samples': 5346240, 'steps': 27844, 'loss/train': 2.3348324298858643} 08/30/2021 18:09:12 - INFO - __main__ - Step 27846: {'lr': 0.00046331239793013726, 'samples': 5346432, 'steps': 27845, 'loss/train': 1.9039591550827026} 08/30/2021 18:09:12 - INFO - __main__ - Step 27847: {'lr': 0.0004633096304002279, 'samples': 5346624, 'steps': 27846, 'loss/train': 1.19235360622406} 08/30/2021 18:09:13 - INFO - __main__ - Step 27848: {'lr': 0.00046330686277420454, 'samples': 5346816, 'steps': 27847, 'loss/train': 1.4089248180389404} 08/30/2021 18:09:13 - INFO - __main__ - Step 27849: {'lr': 0.00046330409505206837, 'samples': 5347008, 'steps': 27848, 'loss/train': 1.5183302164077759} 08/30/2021 18:09:13 - INFO - __main__ - Step 27850: {'lr': 0.00046330132723382066, 'samples': 5347200, 'steps': 27849, 'loss/train': 1.5850435495376587} 08/30/2021 18:09:15 - INFO - __main__ - Step 27851: {'lr': 0.0004632985593194627, 'samples': 5347392, 'steps': 27850, 'loss/train': 1.0716716051101685} 08/30/2021 18:09:15 - INFO - __main__ - Step 27852: {'lr': 0.00046329579130899567, 'samples': 5347584, 'steps': 27851, 'loss/train': 1.5987440347671509} 08/30/2021 18:09:16 - INFO - __main__ - Step 27853: {'lr': 0.0004632930232024209, 'samples': 5347776, 'steps': 27852, 'loss/train': 1.7953028678894043} 08/30/2021 18:09:16 - INFO - __main__ - Step 27854: {'lr': 0.0004632902549997395, 'samples': 5347968, 'steps': 27853, 'loss/train': 1.2598515748977661} 08/30/2021 18:09:16 - INFO - __main__ - Step 27855: {'lr': 0.00046328748670095287, 'samples': 5348160, 'steps': 27854, 'loss/train': 1.3424211740493774} 08/30/2021 18:09:18 - INFO - __main__ - Step 27856: {'lr': 0.0004632847183060622, 'samples': 5348352, 'steps': 27855, 'loss/train': 1.6653623580932617} 08/30/2021 18:09:19 - INFO - __main__ - Step 27857: {'lr': 0.0004632819498150688, 'samples': 5348544, 'steps': 27856, 'loss/train': 1.4488108158111572} 08/30/2021 18:09:19 - INFO - __main__ - Step 27858: {'lr': 0.00046327918122797363, 'samples': 5348736, 'steps': 27857, 'loss/train': 1.2262461185455322} 08/30/2021 18:09:20 - INFO - __main__ - Step 27859: {'lr': 0.00046327641254477833, 'samples': 5348928, 'steps': 27858, 'loss/train': 1.7536661624908447} 08/30/2021 18:09:20 - INFO - __main__ - Step 27860: {'lr': 0.00046327364376548384, 'samples': 5349120, 'steps': 27859, 'loss/train': 0.9308289885520935} 08/30/2021 18:09:21 - INFO - __main__ - Step 27861: {'lr': 0.0004632708748900917, 'samples': 5349312, 'steps': 27860, 'loss/train': 1.4292386770248413} 08/30/2021 18:09:22 - INFO - __main__ - Step 27862: {'lr': 0.00046326810591860285, 'samples': 5349504, 'steps': 27861, 'loss/train': 1.91312575340271} 08/30/2021 18:09:22 - INFO - __main__ - Step 27863: {'lr': 0.0004632653368510187, 'samples': 5349696, 'steps': 27862, 'loss/train': 1.5734388828277588} 08/30/2021 18:09:23 - INFO - __main__ - Step 27864: {'lr': 0.00046326256768734053, 'samples': 5349888, 'steps': 27863, 'loss/train': 1.2745591402053833} 08/30/2021 18:09:23 - INFO - __main__ - Step 27865: {'lr': 0.0004632597984275695, 'samples': 5350080, 'steps': 27864, 'loss/train': 0.9460969567298889} 08/30/2021 18:09:23 - INFO - __main__ - Step 27866: {'lr': 0.00046325702907170697, 'samples': 5350272, 'steps': 27865, 'loss/train': 1.5940924882888794} 08/30/2021 18:09:25 - INFO - __main__ - Step 27867: {'lr': 0.000463254259619754, 'samples': 5350464, 'steps': 27866, 'loss/train': 1.37678861618042} 08/30/2021 18:09:25 - INFO - __main__ - Step 27868: {'lr': 0.000463251490071712, 'samples': 5350656, 'steps': 27867, 'loss/train': 1.644361138343811} 08/30/2021 18:09:26 - INFO - __main__ - Step 27869: {'lr': 0.0004632487204275822, 'samples': 5350848, 'steps': 27868, 'loss/train': 1.1219329833984375} 08/30/2021 18:09:26 - INFO - __main__ - Step 27870: {'lr': 0.0004632459506873658, 'samples': 5351040, 'steps': 27869, 'loss/train': 1.184278964996338} 08/30/2021 18:09:26 - INFO - __main__ - Step 27871: {'lr': 0.0004632431808510641, 'samples': 5351232, 'steps': 27870, 'loss/train': 1.9152334928512573} 08/30/2021 18:09:28 - INFO - __main__ - Step 27872: {'lr': 0.0004632404109186782, 'samples': 5351424, 'steps': 27871, 'loss/train': 1.5471254587173462} 08/30/2021 18:09:28 - INFO - __main__ - Step 27873: {'lr': 0.0004632376408902096, 'samples': 5351616, 'steps': 27872, 'loss/train': 1.623543620109558} 08/30/2021 18:09:29 - INFO - __main__ - Step 27874: {'lr': 0.0004632348707656593, 'samples': 5351808, 'steps': 27873, 'loss/train': 1.6411412954330444} 08/30/2021 18:09:29 - INFO - __main__ - Step 27875: {'lr': 0.00046323210054502874, 'samples': 5352000, 'steps': 27874, 'loss/train': 1.30329167842865} 08/30/2021 18:09:29 - INFO - __main__ - Step 27876: {'lr': 0.00046322933022831903, 'samples': 5352192, 'steps': 27875, 'loss/train': 1.4236921072006226} 08/30/2021 18:09:31 - INFO - __main__ - Step 27877: {'lr': 0.0004632265598155315, 'samples': 5352384, 'steps': 27876, 'loss/train': 1.4609565734863281} 08/30/2021 18:09:31 - INFO - __main__ - Step 27878: {'lr': 0.00046322378930666736, 'samples': 5352576, 'steps': 27877, 'loss/train': 1.5716593265533447} 08/30/2021 18:09:32 - INFO - __main__ - Step 27879: {'lr': 0.0004632210187017278, 'samples': 5352768, 'steps': 27878, 'loss/train': 0.8533258438110352} 08/30/2021 18:09:32 - INFO - __main__ - Step 27880: {'lr': 0.00046321824800071425, 'samples': 5352960, 'steps': 27879, 'loss/train': 1.2530912160873413} 08/30/2021 18:09:32 - INFO - __main__ - Step 27881: {'lr': 0.0004632154772036279, 'samples': 5353152, 'steps': 27880, 'loss/train': 1.4827314615249634} 08/30/2021 18:09:34 - INFO - __main__ - Step 27882: {'lr': 0.0004632127063104698, 'samples': 5353344, 'steps': 27881, 'loss/train': 1.599303126335144} 08/30/2021 18:09:34 - INFO - __main__ - Step 27883: {'lr': 0.00046320993532124137, 'samples': 5353536, 'steps': 27882, 'loss/train': 1.5524917840957642} 08/30/2021 18:09:35 - INFO - __main__ - Step 27884: {'lr': 0.0004632071642359439, 'samples': 5353728, 'steps': 27883, 'loss/train': 1.8457468748092651} 08/30/2021 18:09:35 - INFO - __main__ - Step 27885: {'lr': 0.0004632043930545785, 'samples': 5353920, 'steps': 27884, 'loss/train': 0.07377669960260391} 08/30/2021 18:09:35 - INFO - __main__ - Step 27886: {'lr': 0.00046320162177714653, 'samples': 5354112, 'steps': 27885, 'loss/train': 1.8720864057540894} 08/30/2021 18:09:37 - INFO - __main__ - Step 27887: {'lr': 0.00046319885040364925, 'samples': 5354304, 'steps': 27886, 'loss/train': 1.5645158290863037} 08/30/2021 18:09:38 - INFO - __main__ - Step 27888: {'lr': 0.00046319607893408776, 'samples': 5354496, 'steps': 27887, 'loss/train': 1.0230780839920044} 08/30/2021 18:09:38 - INFO - __main__ - Step 27889: {'lr': 0.0004631933073684635, 'samples': 5354688, 'steps': 27888, 'loss/train': 0.8020130395889282} 08/30/2021 18:09:38 - INFO - __main__ - Step 27890: {'lr': 0.00046319053570677754, 'samples': 5354880, 'steps': 27889, 'loss/train': 1.6323224306106567} 08/30/2021 18:09:39 - INFO - __main__ - Step 27891: {'lr': 0.0004631877639490313, 'samples': 5355072, 'steps': 27890, 'loss/train': 1.1596242189407349} 08/30/2021 18:09:40 - INFO - __main__ - Step 27892: {'lr': 0.0004631849920952259, 'samples': 5355264, 'steps': 27891, 'loss/train': 1.720773458480835} 08/30/2021 18:09:40 - INFO - __main__ - Step 27893: {'lr': 0.0004631822201453626, 'samples': 5355456, 'steps': 27892, 'loss/train': 1.4729856252670288} 08/30/2021 18:09:41 - INFO - __main__ - Step 27894: {'lr': 0.0004631794480994427, 'samples': 5355648, 'steps': 27893, 'loss/train': 1.6313401460647583} 08/30/2021 18:09:41 - INFO - __main__ - Step 27895: {'lr': 0.0004631766759574675, 'samples': 5355840, 'steps': 27894, 'loss/train': 0.4398038983345032} 08/30/2021 18:09:42 - INFO - __main__ - Step 27896: {'lr': 0.0004631739037194381, 'samples': 5356032, 'steps': 27895, 'loss/train': 1.3815815448760986} 08/30/2021 18:09:43 - INFO - __main__ - Step 27897: {'lr': 0.00046317113138535584, 'samples': 5356224, 'steps': 27896, 'loss/train': 1.543875813484192} 08/30/2021 18:09:44 - INFO - __main__ - Step 27898: {'lr': 0.0004631683589552219, 'samples': 5356416, 'steps': 27897, 'loss/train': 1.45516836643219} 08/30/2021 18:09:44 - INFO - __main__ - Step 27899: {'lr': 0.00046316558642903774, 'samples': 5356608, 'steps': 27898, 'loss/train': 1.6084994077682495} 08/30/2021 18:09:44 - INFO - __main__ - Step 27900: {'lr': 0.0004631628138068043, 'samples': 5356800, 'steps': 27899, 'loss/train': 1.3844728469848633} 08/30/2021 18:09:45 - INFO - __main__ - Step 27901: {'lr': 0.00046316004108852305, 'samples': 5356992, 'steps': 27900, 'loss/train': 1.730255365371704} 08/30/2021 18:09:45 - INFO - __main__ - Step 27902: {'lr': 0.0004631572682741952, 'samples': 5357184, 'steps': 27901, 'loss/train': 1.5052891969680786} 08/30/2021 18:09:47 - INFO - __main__ - Step 27903: {'lr': 0.0004631544953638219, 'samples': 5357376, 'steps': 27902, 'loss/train': 0.9532438516616821} 08/30/2021 18:09:47 - INFO - __main__ - Step 27904: {'lr': 0.00046315172235740455, 'samples': 5357568, 'steps': 27903, 'loss/train': 0.07877084612846375} 08/30/2021 18:09:47 - INFO - __main__ - Step 27905: {'lr': 0.0004631489492549443, 'samples': 5357760, 'steps': 27904, 'loss/train': 1.857937216758728} 08/30/2021 18:09:48 - INFO - __main__ - Step 27906: {'lr': 0.00046314617605644243, 'samples': 5357952, 'steps': 27905, 'loss/train': 1.09197199344635} 08/30/2021 18:09:48 - INFO - __main__ - Step 27907: {'lr': 0.0004631434027619001, 'samples': 5358144, 'steps': 27906, 'loss/train': 0.6468884944915771} 08/30/2021 18:09:50 - INFO - __main__ - Step 27908: {'lr': 0.0004631406293713188, 'samples': 5358336, 'steps': 27907, 'loss/train': 0.38434073328971863} 08/30/2021 18:09:51 - INFO - __main__ - Step 27909: {'lr': 0.0004631378558846995, 'samples': 5358528, 'steps': 27908, 'loss/train': 1.4693931341171265} 08/30/2021 18:09:51 - INFO - __main__ - Step 27910: {'lr': 0.00046313508230204364, 'samples': 5358720, 'steps': 27909, 'loss/train': 1.861594319343567} 08/30/2021 18:09:51 - INFO - __main__ - Step 27911: {'lr': 0.00046313230862335235, 'samples': 5358912, 'steps': 27910, 'loss/train': 1.4517710208892822} 08/30/2021 18:09:52 - INFO - __main__ - Step 27912: {'lr': 0.000463129534848627, 'samples': 5359104, 'steps': 27911, 'loss/train': 1.1970484256744385} 08/30/2021 18:09:53 - INFO - __main__ - Step 27913: {'lr': 0.0004631267609778687, 'samples': 5359296, 'steps': 27912, 'loss/train': 1.354780912399292} 08/30/2021 18:09:54 - INFO - __main__ - Step 27914: {'lr': 0.0004631239870110788, 'samples': 5359488, 'steps': 27913, 'loss/train': 0.8847267031669617} 08/30/2021 18:09:54 - INFO - __main__ - Step 27915: {'lr': 0.00046312121294825846, 'samples': 5359680, 'steps': 27914, 'loss/train': 2.010751485824585} 08/30/2021 18:09:54 - INFO - __main__ - Step 27916: {'lr': 0.00046311843878940904, 'samples': 5359872, 'steps': 27915, 'loss/train': 1.421433925628662} 08/30/2021 18:09:55 - INFO - __main__ - Step 27917: {'lr': 0.0004631156645345318, 'samples': 5360064, 'steps': 27916, 'loss/train': 1.6389130353927612} 08/30/2021 18:09:56 - INFO - __main__ - Step 27918: {'lr': 0.0004631128901836278, 'samples': 5360256, 'steps': 27917, 'loss/train': 2.283113479614258} 08/30/2021 18:09:57 - INFO - __main__ - Step 27919: {'lr': 0.0004631101157366985, 'samples': 5360448, 'steps': 27918, 'loss/train': 0.6903948187828064} 08/30/2021 18:09:57 - INFO - __main__ - Step 27920: {'lr': 0.0004631073411937451, 'samples': 5360640, 'steps': 27919, 'loss/train': 1.649309515953064} 08/30/2021 18:09:57 - INFO - __main__ - Step 27921: {'lr': 0.00046310456655476875, 'samples': 5360832, 'steps': 27920, 'loss/train': 1.745056390762329} 08/30/2021 18:09:58 - INFO - __main__ - Step 27922: {'lr': 0.0004631017918197709, 'samples': 5361024, 'steps': 27921, 'loss/train': 1.7016445398330688} 08/30/2021 18:09:59 - INFO - __main__ - Step 27923: {'lr': 0.00046309901698875244, 'samples': 5361216, 'steps': 27922, 'loss/train': 1.6440163850784302} 08/30/2021 18:10:00 - INFO - __main__ - Step 27924: {'lr': 0.00046309624206171505, 'samples': 5361408, 'steps': 27923, 'loss/train': 2.148451328277588} 08/30/2021 18:10:00 - INFO - __main__ - Step 27925: {'lr': 0.00046309346703865973, 'samples': 5361600, 'steps': 27924, 'loss/train': 1.5376533269882202} 08/30/2021 18:10:00 - INFO - __main__ - Step 27926: {'lr': 0.00046309069191958775, 'samples': 5361792, 'steps': 27925, 'loss/train': 1.7108235359191895} 08/30/2021 18:10:01 - INFO - __main__ - Step 27927: {'lr': 0.00046308791670450033, 'samples': 5361984, 'steps': 27926, 'loss/train': 1.6991583108901978} 08/30/2021 18:10:02 - INFO - __main__ - Step 27928: {'lr': 0.00046308514139339896, 'samples': 5362176, 'steps': 27927, 'loss/train': 1.648048758506775} 08/30/2021 18:10:03 - INFO - __main__ - Step 27929: {'lr': 0.0004630823659862846, 'samples': 5362368, 'steps': 27928, 'loss/train': 1.1558430194854736} 08/30/2021 18:10:03 - INFO - __main__ - Step 27930: {'lr': 0.0004630795904831586, 'samples': 5362560, 'steps': 27929, 'loss/train': 1.4804942607879639} 08/30/2021 18:10:03 - INFO - __main__ - Step 27931: {'lr': 0.0004630768148840223, 'samples': 5362752, 'steps': 27930, 'loss/train': 0.8264032006263733} 08/30/2021 18:10:04 - INFO - __main__ - Step 27932: {'lr': 0.0004630740391888768, 'samples': 5362944, 'steps': 27931, 'loss/train': 1.671456217765808} 08/30/2021 18:10:04 - INFO - __main__ - Step 27933: {'lr': 0.0004630712633977234, 'samples': 5363136, 'steps': 27932, 'loss/train': 1.25258469581604} 08/30/2021 18:10:05 - INFO - __main__ - Step 27934: {'lr': 0.00046306848751056346, 'samples': 5363328, 'steps': 27933, 'loss/train': 0.786181628704071} 08/30/2021 18:10:06 - INFO - __main__ - Step 27935: {'lr': 0.0004630657115273981, 'samples': 5363520, 'steps': 27934, 'loss/train': 1.7340360879898071} 08/30/2021 18:10:06 - INFO - __main__ - Step 27936: {'lr': 0.0004630629354482286, 'samples': 5363712, 'steps': 27935, 'loss/train': 1.613985538482666} 08/30/2021 18:10:07 - INFO - __main__ - Step 27937: {'lr': 0.00046306015927305633, 'samples': 5363904, 'steps': 27936, 'loss/train': 1.5055582523345947} 08/30/2021 18:10:07 - INFO - __main__ - Step 27938: {'lr': 0.0004630573830018824, 'samples': 5364096, 'steps': 27937, 'loss/train': 0.9066299200057983} 08/30/2021 18:10:08 - INFO - __main__ - Step 27939: {'lr': 0.00046305460663470803, 'samples': 5364288, 'steps': 27938, 'loss/train': 1.687584638595581} 08/30/2021 18:10:09 - INFO - __main__ - Step 27940: {'lr': 0.0004630518301715346, 'samples': 5364480, 'steps': 27939, 'loss/train': 1.1913965940475464} 08/30/2021 18:10:09 - INFO - __main__ - Step 27941: {'lr': 0.00046304905361236335, 'samples': 5364672, 'steps': 27940, 'loss/train': 1.8258600234985352} 08/30/2021 18:10:09 - INFO - __main__ - Step 27942: {'lr': 0.00046304627695719535, 'samples': 5364864, 'steps': 27941, 'loss/train': 1.5701454877853394} 08/30/2021 18:10:10 - INFO - __main__ - Step 27943: {'lr': 0.0004630435002060321, 'samples': 5365056, 'steps': 27942, 'loss/train': 1.3512667417526245} 08/30/2021 18:10:12 - INFO - __main__ - Step 27944: {'lr': 0.0004630407233588747, 'samples': 5365248, 'steps': 27943, 'loss/train': 1.5550307035446167} 08/30/2021 18:10:12 - INFO - __main__ - Step 27945: {'lr': 0.00046303794641572445, 'samples': 5365440, 'steps': 27944, 'loss/train': 1.9324413537979126} 08/30/2021 18:10:12 - INFO - __main__ - Step 27946: {'lr': 0.0004630351693765825, 'samples': 5365632, 'steps': 27945, 'loss/train': 1.4949580430984497} 08/30/2021 18:10:13 - INFO - __main__ - Step 27947: {'lr': 0.0004630323922414503, 'samples': 5365824, 'steps': 27946, 'loss/train': 1.6540135145187378} 08/30/2021 18:10:13 - INFO - __main__ - Step 27948: {'lr': 0.00046302961501032896, 'samples': 5366016, 'steps': 27947, 'loss/train': 1.3547570705413818} 08/30/2021 18:10:15 - INFO - __main__ - Step 27949: {'lr': 0.00046302683768321973, 'samples': 5366208, 'steps': 27948, 'loss/train': 0.8375091552734375} 08/30/2021 18:10:15 - INFO - __main__ - Step 27950: {'lr': 0.00046302406026012396, 'samples': 5366400, 'steps': 27949, 'loss/train': 1.5853266716003418} 08/30/2021 18:10:16 - INFO - __main__ - Step 27951: {'lr': 0.0004630212827410428, 'samples': 5366592, 'steps': 27950, 'loss/train': 2.0909345149993896} 08/30/2021 18:10:16 - INFO - __main__ - Step 27952: {'lr': 0.00046301850512597755, 'samples': 5366784, 'steps': 27951, 'loss/train': 1.000041127204895} 08/30/2021 18:10:16 - INFO - __main__ - Step 27953: {'lr': 0.0004630157274149294, 'samples': 5366976, 'steps': 27952, 'loss/train': 1.8751729726791382} 08/30/2021 18:10:18 - INFO - __main__ - Step 27954: {'lr': 0.0004630129496078997, 'samples': 5367168, 'steps': 27953, 'loss/train': 1.3810734748840332} 08/30/2021 18:10:18 - INFO - __main__ - Step 27955: {'lr': 0.00046301017170488965, 'samples': 5367360, 'steps': 27954, 'loss/train': 1.148566484451294} 08/30/2021 18:10:19 - INFO - __main__ - Step 27956: {'lr': 0.0004630073937059005, 'samples': 5367552, 'steps': 27955, 'loss/train': 0.05812060460448265} 08/30/2021 18:10:19 - INFO - __main__ - Step 27957: {'lr': 0.0004630046156109334, 'samples': 5367744, 'steps': 27956, 'loss/train': 0.6879861354827881} 08/30/2021 18:10:19 - INFO - __main__ - Step 27958: {'lr': 0.0004630018374199899, 'samples': 5367936, 'steps': 27957, 'loss/train': 1.4244699478149414} 08/30/2021 18:10:21 - INFO - __main__ - Step 27959: {'lr': 0.00046299905913307096, 'samples': 5368128, 'steps': 27958, 'loss/train': 1.2281049489974976} 08/30/2021 18:10:22 - INFO - __main__ - Step 27960: {'lr': 0.00046299628075017785, 'samples': 5368320, 'steps': 27959, 'loss/train': 1.7666549682617188} 08/30/2021 18:10:22 - INFO - __main__ - Step 27961: {'lr': 0.000462993502271312, 'samples': 5368512, 'steps': 27960, 'loss/train': 1.5040251016616821} 08/30/2021 18:10:22 - INFO - __main__ - Step 27962: {'lr': 0.00046299072369647453, 'samples': 5368704, 'steps': 27961, 'loss/train': 1.8474175930023193} 08/30/2021 18:10:23 - INFO - __main__ - Step 27963: {'lr': 0.00046298794502566676, 'samples': 5368896, 'steps': 27962, 'loss/train': 1.0150020122528076} 08/30/2021 18:10:24 - INFO - __main__ - Step 27964: {'lr': 0.0004629851662588899, 'samples': 5369088, 'steps': 27963, 'loss/train': 1.4271022081375122} 08/30/2021 18:10:25 - INFO - __main__ - Step 27965: {'lr': 0.00046298238739614524, 'samples': 5369280, 'steps': 27964, 'loss/train': 1.410161018371582} 08/30/2021 18:10:25 - INFO - __main__ - Step 27966: {'lr': 0.0004629796084374339, 'samples': 5369472, 'steps': 27965, 'loss/train': 1.77895987033844} 08/30/2021 18:10:25 - INFO - __main__ - Step 27967: {'lr': 0.00046297682938275733, 'samples': 5369664, 'steps': 27966, 'loss/train': 1.7697396278381348} 08/30/2021 18:10:26 - INFO - __main__ - Step 27968: {'lr': 0.0004629740502321167, 'samples': 5369856, 'steps': 27967, 'loss/train': 1.216433048248291} 08/30/2021 18:10:27 - INFO - __main__ - Step 27969: {'lr': 0.00046297127098551317, 'samples': 5370048, 'steps': 27968, 'loss/train': 1.5631228685379028} 08/30/2021 18:10:28 - INFO - __main__ - Step 27970: {'lr': 0.00046296849164294816, 'samples': 5370240, 'steps': 27969, 'loss/train': 1.7805249691009521} 08/30/2021 18:10:28 - INFO - __main__ - Step 27971: {'lr': 0.00046296571220442274, 'samples': 5370432, 'steps': 27970, 'loss/train': 1.0356769561767578} 08/30/2021 18:10:28 - INFO - __main__ - Step 27972: {'lr': 0.00046296293266993833, 'samples': 5370624, 'steps': 27971, 'loss/train': 1.3386609554290771} 08/30/2021 18:10:29 - INFO - __main__ - Step 27973: {'lr': 0.00046296015303949606, 'samples': 5370816, 'steps': 27972, 'loss/train': 1.3475388288497925} 08/30/2021 18:10:29 - INFO - __main__ - Step 27974: {'lr': 0.0004629573733130973, 'samples': 5371008, 'steps': 27973, 'loss/train': 1.4497339725494385} 08/30/2021 18:10:31 - INFO - __main__ - Step 27975: {'lr': 0.00046295459349074316, 'samples': 5371200, 'steps': 27974, 'loss/train': 1.2262866497039795} 08/30/2021 18:10:31 - INFO - __main__ - Step 27976: {'lr': 0.000462951813572435, 'samples': 5371392, 'steps': 27975, 'loss/train': 0.8015449643135071} 08/30/2021 18:10:31 - INFO - __main__ - Step 27977: {'lr': 0.00046294903355817397, 'samples': 5371584, 'steps': 27976, 'loss/train': 1.5901968479156494} 08/30/2021 18:10:32 - INFO - __main__ - Step 27978: {'lr': 0.0004629462534479615, 'samples': 5371776, 'steps': 27977, 'loss/train': 1.8777004480361938} 08/30/2021 18:10:32 - INFO - __main__ - Step 27979: {'lr': 0.0004629434732417986, 'samples': 5371968, 'steps': 27978, 'loss/train': 1.5026010274887085} 08/30/2021 18:10:34 - INFO - __main__ - Step 27980: {'lr': 0.0004629406929396868, 'samples': 5372160, 'steps': 27979, 'loss/train': 1.3599811792373657} 08/30/2021 18:10:34 - INFO - __main__ - Step 27981: {'lr': 0.00046293791254162713, 'samples': 5372352, 'steps': 27980, 'loss/train': 1.7414216995239258} 08/30/2021 18:10:35 - INFO - __main__ - Step 27982: {'lr': 0.0004629351320476209, 'samples': 5372544, 'steps': 27981, 'loss/train': 1.5243333578109741} 08/30/2021 18:10:35 - INFO - __main__ - Step 27983: {'lr': 0.00046293235145766955, 'samples': 5372736, 'steps': 27982, 'loss/train': 1.3205631971359253} 08/30/2021 18:10:35 - INFO - __main__ - Step 27984: {'lr': 0.000462929570771774, 'samples': 5372928, 'steps': 27983, 'loss/train': 1.3177266120910645} 08/30/2021 18:10:36 - INFO - __main__ - Step 27985: {'lr': 0.0004629267899899358, 'samples': 5373120, 'steps': 27984, 'loss/train': 0.0660424679517746} 08/30/2021 18:10:37 - INFO - __main__ - Step 27986: {'lr': 0.00046292400911215594, 'samples': 5373312, 'steps': 27985, 'loss/train': 0.288720041513443} 08/30/2021 18:10:38 - INFO - __main__ - Step 27987: {'lr': 0.00046292122813843586, 'samples': 5373504, 'steps': 27986, 'loss/train': 1.9169349670410156} 08/30/2021 18:10:38 - INFO - __main__ - Step 27988: {'lr': 0.00046291844706877674, 'samples': 5373696, 'steps': 27987, 'loss/train': 0.8314317464828491} 08/30/2021 18:10:38 - INFO - __main__ - Step 27989: {'lr': 0.0004629156659031799, 'samples': 5373888, 'steps': 27988, 'loss/train': 1.9417732954025269} 08/30/2021 18:10:39 - INFO - __main__ - Step 27990: {'lr': 0.0004629128846416465, 'samples': 5374080, 'steps': 27989, 'loss/train': 1.337670087814331} 08/30/2021 18:10:40 - INFO - __main__ - Step 27991: {'lr': 0.00046291010328417784, 'samples': 5374272, 'steps': 27990, 'loss/train': 1.6752270460128784} 08/30/2021 18:10:41 - INFO - __main__ - Step 27992: {'lr': 0.0004629073218307752, 'samples': 5374464, 'steps': 27991, 'loss/train': 1.6669642925262451} 08/30/2021 18:10:41 - INFO - __main__ - Step 27993: {'lr': 0.0004629045402814398, 'samples': 5374656, 'steps': 27992, 'loss/train': 1.9049948453903198} 08/30/2021 18:10:41 - INFO - __main__ - Step 27994: {'lr': 0.0004629017586361729, 'samples': 5374848, 'steps': 27993, 'loss/train': 0.12876975536346436} 08/30/2021 18:10:42 - INFO - __main__ - Step 27995: {'lr': 0.0004628989768949757, 'samples': 5375040, 'steps': 27994, 'loss/train': 1.8217722177505493} 08/30/2021 18:10:44 - INFO - __main__ - Step 27996: {'lr': 0.0004628961950578496, 'samples': 5375232, 'steps': 27995, 'loss/train': 1.3383779525756836} 08/30/2021 18:10:44 - INFO - __main__ - Step 27997: {'lr': 0.00046289341312479574, 'samples': 5375424, 'steps': 27996, 'loss/train': 1.4796178340911865} 08/30/2021 18:10:44 - INFO - __main__ - Step 27998: {'lr': 0.0004628906310958153, 'samples': 5375616, 'steps': 27997, 'loss/train': 1.280945062637329} 08/30/2021 18:10:45 - INFO - __main__ - Step 27999: {'lr': 0.00046288784897090973, 'samples': 5375808, 'steps': 27998, 'loss/train': 1.3560783863067627} 08/30/2021 18:10:45 - INFO - __main__ - Step 28000: {'lr': 0.00046288506675008014, 'samples': 5376000, 'steps': 27999, 'loss/train': 1.3295682668685913} 08/30/2021 18:10:45 - INFO - __main__ - Step 28001: {'lr': 0.0004628822844333278, 'samples': 5376192, 'steps': 28000, 'loss/train': 0.049830805510282516} 08/30/2021 18:10:47 - INFO - __main__ - Step 28002: {'lr': 0.0004628795020206541, 'samples': 5376384, 'steps': 28001, 'loss/train': 1.1427934169769287} 08/30/2021 18:10:47 - INFO - __main__ - Step 28003: {'lr': 0.00046287671951206004, 'samples': 5376576, 'steps': 28002, 'loss/train': 1.6543828248977661} 08/30/2021 18:10:48 - INFO - __main__ - Step 28004: {'lr': 0.0004628739369075471, 'samples': 5376768, 'steps': 28003, 'loss/train': 1.4621587991714478} 08/30/2021 18:10:48 - INFO - __main__ - Step 28005: {'lr': 0.00046287115420711643, 'samples': 5376960, 'steps': 28004, 'loss/train': 1.7530735731124878} 08/30/2021 18:10:48 - INFO - __main__ - Step 28006: {'lr': 0.00046286837141076934, 'samples': 5377152, 'steps': 28005, 'loss/train': 1.7326995134353638} 08/30/2021 18:10:50 - INFO - __main__ - Step 28007: {'lr': 0.0004628655885185069, 'samples': 5377344, 'steps': 28006, 'loss/train': 1.432509422302246} 08/30/2021 18:10:50 - INFO - __main__ - Step 28008: {'lr': 0.00046286280553033067, 'samples': 5377536, 'steps': 28007, 'loss/train': 1.2272719144821167} 08/30/2021 18:10:51 - INFO - __main__ - Step 28009: {'lr': 0.0004628600224462417, 'samples': 5377728, 'steps': 28008, 'loss/train': 1.5074902772903442} 08/30/2021 18:10:51 - INFO - __main__ - Step 28010: {'lr': 0.00046285723926624126, 'samples': 5377920, 'steps': 28009, 'loss/train': 1.5878270864486694} 08/30/2021 18:10:51 - INFO - __main__ - Step 28011: {'lr': 0.00046285445599033063, 'samples': 5378112, 'steps': 28010, 'loss/train': 1.471692681312561} 08/30/2021 18:10:54 - INFO - __main__ - Step 28012: {'lr': 0.00046285167261851114, 'samples': 5378304, 'steps': 28011, 'loss/train': 1.634076714515686} 08/30/2021 18:10:54 - INFO - __main__ - Step 28013: {'lr': 0.00046284888915078384, 'samples': 5378496, 'steps': 28012, 'loss/train': 1.475229024887085} 08/30/2021 18:10:54 - INFO - __main__ - Step 28014: {'lr': 0.00046284610558715024, 'samples': 5378688, 'steps': 28013, 'loss/train': 0.9592087268829346} 08/30/2021 18:10:55 - INFO - __main__ - Step 28015: {'lr': 0.00046284332192761136, 'samples': 5378880, 'steps': 28014, 'loss/train': 1.7823725938796997} 08/30/2021 18:10:55 - INFO - __main__ - Step 28016: {'lr': 0.0004628405381721686, 'samples': 5379072, 'steps': 28015, 'loss/train': 0.370857298374176} 08/30/2021 18:10:57 - INFO - __main__ - Step 28017: {'lr': 0.00046283775432082327, 'samples': 5379264, 'steps': 28016, 'loss/train': 0.9909529685974121} 08/30/2021 18:10:57 - INFO - __main__ - Step 28018: {'lr': 0.0004628349703735765, 'samples': 5379456, 'steps': 28017, 'loss/train': 1.7473207712173462} 08/30/2021 18:10:57 - INFO - __main__ - Step 28019: {'lr': 0.0004628321863304295, 'samples': 5379648, 'steps': 28018, 'loss/train': 1.4742985963821411} 08/30/2021 18:10:58 - INFO - __main__ - Step 28020: {'lr': 0.00046282940219138366, 'samples': 5379840, 'steps': 28019, 'loss/train': 0.8732110857963562} 08/30/2021 18:10:58 - INFO - __main__ - Step 28021: {'lr': 0.0004628266179564401, 'samples': 5380032, 'steps': 28020, 'loss/train': 0.06682850420475006} 08/30/2021 18:11:00 - INFO - __main__ - Step 28022: {'lr': 0.0004628238336256002, 'samples': 5380224, 'steps': 28021, 'loss/train': 1.029103398323059} 08/30/2021 18:11:00 - INFO - __main__ - Step 28023: {'lr': 0.0004628210491988652, 'samples': 5380416, 'steps': 28022, 'loss/train': 0.6956168413162231} 08/30/2021 18:11:00 - INFO - __main__ - Step 28024: {'lr': 0.0004628182646762363, 'samples': 5380608, 'steps': 28023, 'loss/train': 1.4460898637771606} 08/30/2021 18:11:01 - INFO - __main__ - Step 28025: {'lr': 0.00046281548005771476, 'samples': 5380800, 'steps': 28024, 'loss/train': 1.5885947942733765} 08/30/2021 18:11:01 - INFO - __main__ - Step 28026: {'lr': 0.0004628126953433018, 'samples': 5380992, 'steps': 28025, 'loss/train': 0.1988345831632614} 08/30/2021 18:11:03 - INFO - __main__ - Step 28027: {'lr': 0.00046280991053299883, 'samples': 5381184, 'steps': 28026, 'loss/train': 1.525325059890747} 08/30/2021 18:11:03 - INFO - __main__ - Step 28028: {'lr': 0.00046280712562680695, 'samples': 5381376, 'steps': 28027, 'loss/train': 1.526443600654602} 08/30/2021 18:11:03 - INFO - __main__ - Step 28029: {'lr': 0.0004628043406247274, 'samples': 5381568, 'steps': 28028, 'loss/train': 1.3917332887649536} 08/30/2021 18:11:04 - INFO - __main__ - Step 28030: {'lr': 0.0004628015555267616, 'samples': 5381760, 'steps': 28029, 'loss/train': 1.0822982788085938} 08/30/2021 18:11:04 - INFO - __main__ - Step 28031: {'lr': 0.00046279877033291063, 'samples': 5381952, 'steps': 28030, 'loss/train': 1.3407223224639893} 08/30/2021 18:11:04 - INFO - __main__ - Step 28032: {'lr': 0.0004627959850431759, 'samples': 5382144, 'steps': 28031, 'loss/train': 1.6693180799484253} 08/30/2021 18:11:06 - INFO - __main__ - Step 28033: {'lr': 0.0004627931996575585, 'samples': 5382336, 'steps': 28032, 'loss/train': 1.3858481645584106} 08/30/2021 18:11:06 - INFO - __main__ - Step 28034: {'lr': 0.0004627904141760598, 'samples': 5382528, 'steps': 28033, 'loss/train': 1.325707197189331} 08/30/2021 18:11:07 - INFO - __main__ - Step 28035: {'lr': 0.000462787628598681, 'samples': 5382720, 'steps': 28034, 'loss/train': 1.443479299545288} 08/30/2021 18:11:07 - INFO - __main__ - Step 28036: {'lr': 0.00046278484292542346, 'samples': 5382912, 'steps': 28035, 'loss/train': 1.2646863460540771} 08/30/2021 18:11:07 - INFO - __main__ - Step 28037: {'lr': 0.0004627820571562883, 'samples': 5383104, 'steps': 28036, 'loss/train': 0.8303531408309937} 08/30/2021 18:11:09 - INFO - __main__ - Step 28038: {'lr': 0.0004627792712912768, 'samples': 5383296, 'steps': 28037, 'loss/train': 1.3916767835617065} 08/30/2021 18:11:10 - INFO - __main__ - Step 28039: {'lr': 0.0004627764853303902, 'samples': 5383488, 'steps': 28038, 'loss/train': 1.7772756814956665} 08/30/2021 18:11:10 - INFO - __main__ - Step 28040: {'lr': 0.00046277369927362987, 'samples': 5383680, 'steps': 28039, 'loss/train': 0.15569743514060974} 08/30/2021 18:11:10 - INFO - __main__ - Step 28041: {'lr': 0.00046277091312099704, 'samples': 5383872, 'steps': 28040, 'loss/train': 0.9434666633605957} 08/30/2021 18:11:11 - INFO - __main__ - Step 28042: {'lr': 0.00046276812687249283, 'samples': 5384064, 'steps': 28041, 'loss/train': 2.144589900970459} 08/30/2021 18:11:12 - INFO - __main__ - Step 28043: {'lr': 0.00046276534052811863, 'samples': 5384256, 'steps': 28042, 'loss/train': 1.721571683883667} 08/30/2021 18:11:13 - INFO - __main__ - Step 28044: {'lr': 0.00046276255408787565, 'samples': 5384448, 'steps': 28043, 'loss/train': 2.0207138061523438} 08/30/2021 18:11:13 - INFO - __main__ - Step 28045: {'lr': 0.0004627597675517652, 'samples': 5384640, 'steps': 28044, 'loss/train': 1.3871874809265137} 08/30/2021 18:11:13 - INFO - __main__ - Step 28046: {'lr': 0.00046275698091978836, 'samples': 5384832, 'steps': 28045, 'loss/train': 1.3740190267562866} 08/30/2021 18:11:14 - INFO - __main__ - Step 28047: {'lr': 0.0004627541941919466, 'samples': 5385024, 'steps': 28046, 'loss/train': 1.1003849506378174} 08/30/2021 18:11:15 - INFO - __main__ - Step 28048: {'lr': 0.00046275140736824104, 'samples': 5385216, 'steps': 28047, 'loss/train': 1.3855782747268677} 08/30/2021 18:11:16 - INFO - __main__ - Step 28049: {'lr': 0.000462748620448673, 'samples': 5385408, 'steps': 28048, 'loss/train': 1.782700538635254} 08/30/2021 18:11:16 - INFO - __main__ - Step 28050: {'lr': 0.0004627458334332437, 'samples': 5385600, 'steps': 28049, 'loss/train': 1.8163042068481445} 08/30/2021 18:11:16 - INFO - __main__ - Step 28051: {'lr': 0.0004627430463219544, 'samples': 5385792, 'steps': 28050, 'loss/train': 1.3694815635681152} 08/30/2021 18:11:17 - INFO - __main__ - Step 28052: {'lr': 0.0004627402591148064, 'samples': 5385984, 'steps': 28051, 'loss/train': 1.3943809270858765} 08/30/2021 18:11:19 - INFO - __main__ - Step 28053: {'lr': 0.0004627374718118009, 'samples': 5386176, 'steps': 28052, 'loss/train': 1.8527545928955078} 08/30/2021 18:11:19 - INFO - __main__ - Step 28054: {'lr': 0.0004627346844129392, 'samples': 5386368, 'steps': 28053, 'loss/train': 1.161802887916565} 08/30/2021 18:11:19 - INFO - __main__ - Step 28055: {'lr': 0.0004627318969182225, 'samples': 5386560, 'steps': 28054, 'loss/train': 0.08127857744693756} 08/30/2021 18:11:20 - INFO - __main__ - Step 28056: {'lr': 0.0004627291093276521, 'samples': 5386752, 'steps': 28055, 'loss/train': 1.6853795051574707} 08/30/2021 18:11:20 - INFO - __main__ - Step 28057: {'lr': 0.0004627263216412292, 'samples': 5386944, 'steps': 28056, 'loss/train': 0.6058462858200073} 08/30/2021 18:11:20 - INFO - __main__ - Step 28058: {'lr': 0.00046272353385895515, 'samples': 5387136, 'steps': 28057, 'loss/train': 1.2188124656677246} 08/30/2021 18:11:22 - INFO - __main__ - Step 28059: {'lr': 0.0004627207459808312, 'samples': 5387328, 'steps': 28058, 'loss/train': 1.4666595458984375} 08/30/2021 18:11:22 - INFO - __main__ - Step 28060: {'lr': 0.00046271795800685854, 'samples': 5387520, 'steps': 28059, 'loss/train': 1.025999903678894} 08/30/2021 18:11:23 - INFO - __main__ - Step 28061: {'lr': 0.00046271516993703844, 'samples': 5387712, 'steps': 28060, 'loss/train': 1.3338897228240967} 08/30/2021 18:11:23 - INFO - __main__ - Step 28062: {'lr': 0.00046271238177137216, 'samples': 5387904, 'steps': 28061, 'loss/train': 1.6672204732894897} 08/30/2021 18:11:23 - INFO - __main__ - Step 28063: {'lr': 0.00046270959350986095, 'samples': 5388096, 'steps': 28062, 'loss/train': 1.9613392353057861} 08/30/2021 18:11:25 - INFO - __main__ - Step 28064: {'lr': 0.0004627068051525061, 'samples': 5388288, 'steps': 28063, 'loss/train': 1.6687133312225342} 08/30/2021 18:11:25 - INFO - __main__ - Step 28065: {'lr': 0.00046270401669930885, 'samples': 5388480, 'steps': 28064, 'loss/train': 2.189272165298462} 08/30/2021 18:11:26 - INFO - __main__ - Step 28066: {'lr': 0.0004627012281502704, 'samples': 5388672, 'steps': 28065, 'loss/train': 1.5187551975250244} 08/30/2021 18:11:26 - INFO - __main__ - Step 28067: {'lr': 0.00046269843950539214, 'samples': 5388864, 'steps': 28066, 'loss/train': 0.9895861148834229} 08/30/2021 18:11:26 - INFO - __main__ - Step 28068: {'lr': 0.00046269565076467517, 'samples': 5389056, 'steps': 28067, 'loss/train': 1.294631004333496} 08/30/2021 18:11:28 - INFO - __main__ - Step 28069: {'lr': 0.0004626928619281209, 'samples': 5389248, 'steps': 28068, 'loss/train': 1.447240948677063} 08/30/2021 18:11:29 - INFO - __main__ - Step 28070: {'lr': 0.0004626900729957305, 'samples': 5389440, 'steps': 28069, 'loss/train': 0.9354313015937805} 08/30/2021 18:11:29 - INFO - __main__ - Step 28071: {'lr': 0.00046268728396750515, 'samples': 5389632, 'steps': 28070, 'loss/train': 1.1724275350570679} 08/30/2021 18:11:29 - INFO - __main__ - Step 28072: {'lr': 0.0004626844948434462, 'samples': 5389824, 'steps': 28071, 'loss/train': 1.544147253036499} 08/30/2021 18:11:30 - INFO - __main__ - Step 28073: {'lr': 0.00046268170562355497, 'samples': 5390016, 'steps': 28072, 'loss/train': 0.8086039423942566} 08/30/2021 18:11:30 - INFO - __main__ - Step 28074: {'lr': 0.0004626789163078327, 'samples': 5390208, 'steps': 28073, 'loss/train': 2.0508766174316406} 08/30/2021 18:11:32 - INFO - __main__ - Step 28075: {'lr': 0.00046267612689628046, 'samples': 5390400, 'steps': 28074, 'loss/train': 1.5743684768676758} 08/30/2021 18:11:32 - INFO - __main__ - Step 28076: {'lr': 0.00046267333738889973, 'samples': 5390592, 'steps': 28075, 'loss/train': 1.4540815353393555} 08/30/2021 18:11:33 - INFO - __main__ - Step 28077: {'lr': 0.00046267054778569163, 'samples': 5390784, 'steps': 28076, 'loss/train': 1.152719497680664} 08/30/2021 18:11:33 - INFO - __main__ - Step 28078: {'lr': 0.0004626677580866574, 'samples': 5390976, 'steps': 28077, 'loss/train': 1.2343814373016357} 08/30/2021 18:11:33 - INFO - __main__ - Step 28079: {'lr': 0.00046266496829179847, 'samples': 5391168, 'steps': 28078, 'loss/train': 1.8133282661437988} 08/30/2021 18:11:35 - INFO - __main__ - Step 28080: {'lr': 0.0004626621784011159, 'samples': 5391360, 'steps': 28079, 'loss/train': 1.8737905025482178} 08/30/2021 18:11:35 - INFO - __main__ - Step 28081: {'lr': 0.0004626593884146111, 'samples': 5391552, 'steps': 28080, 'loss/train': 1.972983956336975} 08/30/2021 18:11:36 - INFO - __main__ - Step 28082: {'lr': 0.00046265659833228523, 'samples': 5391744, 'steps': 28081, 'loss/train': 1.348278522491455} 08/30/2021 18:11:36 - INFO - __main__ - Step 28083: {'lr': 0.0004626538081541396, 'samples': 5391936, 'steps': 28082, 'loss/train': 1.663896918296814} 08/30/2021 18:11:36 - INFO - __main__ - Step 28084: {'lr': 0.00046265101788017543, 'samples': 5392128, 'steps': 28083, 'loss/train': 1.6296148300170898} 08/30/2021 18:11:38 - INFO - __main__ - Step 28085: {'lr': 0.00046264822751039406, 'samples': 5392320, 'steps': 28084, 'loss/train': 1.5372482538223267} 08/30/2021 18:11:38 - INFO - __main__ - Step 28086: {'lr': 0.00046264543704479654, 'samples': 5392512, 'steps': 28085, 'loss/train': 1.3979026079177856} 08/30/2021 18:11:38 - INFO - __main__ - Step 28087: {'lr': 0.0004626426464833844, 'samples': 5392704, 'steps': 28086, 'loss/train': 1.364237666130066} 08/30/2021 18:11:39 - INFO - __main__ - Step 28088: {'lr': 0.0004626398558261586, 'samples': 5392896, 'steps': 28087, 'loss/train': 1.6765680313110352} 08/30/2021 18:11:39 - INFO - __main__ - Step 28089: {'lr': 0.00046263706507312073, 'samples': 5393088, 'steps': 28088, 'loss/train': 1.1328810453414917} 08/30/2021 18:11:41 - INFO - __main__ - Step 28090: {'lr': 0.00046263427422427183, 'samples': 5393280, 'steps': 28089, 'loss/train': 1.327867865562439} 08/30/2021 18:11:41 - INFO - __main__ - Step 28091: {'lr': 0.00046263148327961324, 'samples': 5393472, 'steps': 28090, 'loss/train': 1.3953214883804321} 08/30/2021 18:11:42 - INFO - __main__ - Step 28092: {'lr': 0.00046262869223914613, 'samples': 5393664, 'steps': 28091, 'loss/train': 1.0453213453292847} 08/30/2021 18:11:42 - INFO - __main__ - Step 28093: {'lr': 0.00046262590110287183, 'samples': 5393856, 'steps': 28092, 'loss/train': 1.854308843612671} 08/30/2021 18:11:42 - INFO - __main__ - Step 28094: {'lr': 0.00046262310987079156, 'samples': 5394048, 'steps': 28093, 'loss/train': 1.4553587436676025} 08/30/2021 18:11:44 - INFO - __main__ - Step 28095: {'lr': 0.0004626203185429066, 'samples': 5394240, 'steps': 28094, 'loss/train': 1.2204734086990356} 08/30/2021 18:11:45 - INFO - __main__ - Step 28096: {'lr': 0.00046261752711921825, 'samples': 5394432, 'steps': 28095, 'loss/train': 1.5668973922729492} 08/30/2021 18:11:45 - INFO - __main__ - Step 28097: {'lr': 0.00046261473559972764, 'samples': 5394624, 'steps': 28096, 'loss/train': 1.6996465921401978} 08/30/2021 18:11:45 - INFO - __main__ - Step 28098: {'lr': 0.00046261194398443617, 'samples': 5394816, 'steps': 28097, 'loss/train': 1.5285561084747314} 08/30/2021 18:11:46 - INFO - __main__ - Step 28099: {'lr': 0.00046260915227334503, 'samples': 5395008, 'steps': 28098, 'loss/train': 1.1275972127914429} 08/30/2021 18:11:47 - INFO - __main__ - Step 28100: {'lr': 0.0004626063604664555, 'samples': 5395200, 'steps': 28099, 'loss/train': 0.4824984073638916} 08/30/2021 18:11:48 - INFO - __main__ - Step 28101: {'lr': 0.00046260356856376884, 'samples': 5395392, 'steps': 28100, 'loss/train': 1.8263745307922363} 08/30/2021 18:11:48 - INFO - __main__ - Step 28102: {'lr': 0.0004626007765652862, 'samples': 5395584, 'steps': 28101, 'loss/train': 1.334649920463562} 08/30/2021 18:11:48 - INFO - __main__ - Step 28103: {'lr': 0.00046259798447100903, 'samples': 5395776, 'steps': 28102, 'loss/train': 0.9247645735740662} 08/30/2021 18:11:49 - INFO - __main__ - Step 28104: {'lr': 0.0004625951922809385, 'samples': 5395968, 'steps': 28103, 'loss/train': 1.1381335258483887} 08/30/2021 18:11:50 - INFO - __main__ - Step 28105: {'lr': 0.0004625923999950758, 'samples': 5396160, 'steps': 28104, 'loss/train': 1.7762413024902344} 08/30/2021 18:11:51 - INFO - __main__ - Step 28106: {'lr': 0.0004625896076134222, 'samples': 5396352, 'steps': 28105, 'loss/train': 1.751448154449463} 08/30/2021 18:11:51 - INFO - __main__ - Step 28107: {'lr': 0.00046258681513597913, 'samples': 5396544, 'steps': 28106, 'loss/train': 1.4575424194335938} 08/30/2021 18:11:51 - INFO - __main__ - Step 28108: {'lr': 0.0004625840225627476, 'samples': 5396736, 'steps': 28107, 'loss/train': 1.5888158082962036} 08/30/2021 18:11:52 - INFO - __main__ - Step 28109: {'lr': 0.0004625812298937291, 'samples': 5396928, 'steps': 28108, 'loss/train': 1.4933538436889648} 08/30/2021 18:11:53 - INFO - __main__ - Step 28110: {'lr': 0.0004625784371289247, 'samples': 5397120, 'steps': 28109, 'loss/train': 1.0874392986297607} 08/30/2021 18:11:54 - INFO - __main__ - Step 28111: {'lr': 0.00046257564426833574, 'samples': 5397312, 'steps': 28110, 'loss/train': 2.6032867431640625} 08/30/2021 18:11:54 - INFO - __main__ - Step 28112: {'lr': 0.0004625728513119635, 'samples': 5397504, 'steps': 28111, 'loss/train': 0.4529555141925812} 08/30/2021 18:11:54 - INFO - __main__ - Step 28113: {'lr': 0.0004625700582598092, 'samples': 5397696, 'steps': 28112, 'loss/train': 1.5608940124511719} 08/30/2021 18:11:55 - INFO - __main__ - Step 28114: {'lr': 0.00046256726511187407, 'samples': 5397888, 'steps': 28113, 'loss/train': 1.8138625621795654} 08/30/2021 18:11:56 - INFO - __main__ - Step 28115: {'lr': 0.0004625644718681595, 'samples': 5398080, 'steps': 28114, 'loss/train': 1.496962070465088} 08/30/2021 18:11:57 - INFO - __main__ - Step 28116: {'lr': 0.0004625616785286666, 'samples': 5398272, 'steps': 28115, 'loss/train': 1.181666612625122} 08/30/2021 18:11:57 - INFO - __main__ - Step 28117: {'lr': 0.0004625588850933967, 'samples': 5398464, 'steps': 28116, 'loss/train': 1.881162166595459} 08/30/2021 18:11:58 - INFO - __main__ - Step 28118: {'lr': 0.00046255609156235105, 'samples': 5398656, 'steps': 28117, 'loss/train': 1.7869846820831299} 08/30/2021 18:11:58 - INFO - __main__ - Step 28119: {'lr': 0.0004625532979355309, 'samples': 5398848, 'steps': 28118, 'loss/train': 1.6022080183029175} 08/30/2021 18:11:58 - INFO - __main__ - Step 28120: {'lr': 0.00046255050421293756, 'samples': 5399040, 'steps': 28119, 'loss/train': 1.5461374521255493} 08/30/2021 18:12:00 - INFO - __main__ - Step 28121: {'lr': 0.0004625477103945722, 'samples': 5399232, 'steps': 28120, 'loss/train': 1.3789361715316772} 08/30/2021 18:12:01 - INFO - __main__ - Step 28122: {'lr': 0.00046254491648043604, 'samples': 5399424, 'steps': 28121, 'loss/train': 0.5235848426818848} 08/30/2021 18:12:01 - INFO - __main__ - Step 28123: {'lr': 0.00046254212247053055, 'samples': 5399616, 'steps': 28122, 'loss/train': 1.7202489376068115} 08/30/2021 18:12:01 - INFO - __main__ - Step 28124: {'lr': 0.0004625393283648568, 'samples': 5399808, 'steps': 28123, 'loss/train': 1.5611282587051392} 08/30/2021 18:12:02 - INFO - __main__ - Step 28125: {'lr': 0.0004625365341634161, 'samples': 5400000, 'steps': 28124, 'loss/train': 1.266133427619934} 08/30/2021 18:12:03 - INFO - __main__ - Step 28126: {'lr': 0.00046253373986620985, 'samples': 5400192, 'steps': 28125, 'loss/train': 1.058297872543335} 08/30/2021 18:12:04 - INFO - __main__ - Step 28127: {'lr': 0.00046253094547323904, 'samples': 5400384, 'steps': 28126, 'loss/train': 1.3797509670257568} 08/30/2021 18:12:04 - INFO - __main__ - Step 28128: {'lr': 0.0004625281509845051, 'samples': 5400576, 'steps': 28127, 'loss/train': 1.6242307424545288} 08/30/2021 18:12:04 - INFO - __main__ - Step 28129: {'lr': 0.0004625253564000092, 'samples': 5400768, 'steps': 28128, 'loss/train': 0.6565216183662415} 08/30/2021 18:12:05 - INFO - __main__ - Step 28130: {'lr': 0.00046252256171975273, 'samples': 5400960, 'steps': 28129, 'loss/train': 1.4239695072174072} 08/30/2021 18:12:06 - INFO - __main__ - Step 28131: {'lr': 0.0004625197669437368, 'samples': 5401152, 'steps': 28130, 'loss/train': 2.020134449005127} 08/30/2021 18:12:07 - INFO - __main__ - Step 28132: {'lr': 0.0004625169720719628, 'samples': 5401344, 'steps': 28131, 'loss/train': 1.8320237398147583} 08/30/2021 18:12:07 - INFO - __main__ - Step 28133: {'lr': 0.0004625141771044319, 'samples': 5401536, 'steps': 28132, 'loss/train': 1.5916252136230469} 08/30/2021 18:12:08 - INFO - __main__ - Step 28134: {'lr': 0.0004625113820411454, 'samples': 5401728, 'steps': 28133, 'loss/train': 1.3905489444732666} 08/30/2021 18:12:08 - INFO - __main__ - Step 28135: {'lr': 0.0004625085868821046, 'samples': 5401920, 'steps': 28134, 'loss/train': 1.620387077331543} 08/30/2021 18:12:09 - INFO - __main__ - Step 28136: {'lr': 0.0004625057916273107, 'samples': 5402112, 'steps': 28135, 'loss/train': 1.5118495225906372} 08/30/2021 18:12:10 - INFO - __main__ - Step 28137: {'lr': 0.00046250299627676486, 'samples': 5402304, 'steps': 28136, 'loss/train': 1.7144805192947388} 08/30/2021 18:12:10 - INFO - __main__ - Step 28138: {'lr': 0.0004625002008304685, 'samples': 5402496, 'steps': 28137, 'loss/train': 0.9722861051559448} 08/30/2021 18:12:11 - INFO - __main__ - Step 28139: {'lr': 0.00046249740528842286, 'samples': 5402688, 'steps': 28138, 'loss/train': 1.4861527681350708} 08/30/2021 18:12:11 - INFO - __main__ - Step 28140: {'lr': 0.00046249460965062917, 'samples': 5402880, 'steps': 28139, 'loss/train': 0.9521327018737793} 08/30/2021 18:12:11 - INFO - __main__ - Step 28141: {'lr': 0.0004624918139170887, 'samples': 5403072, 'steps': 28140, 'loss/train': 1.579189658164978} 08/30/2021 18:12:13 - INFO - __main__ - Step 28142: {'lr': 0.0004624890180878027, 'samples': 5403264, 'steps': 28141, 'loss/train': 2.330486297607422} 08/30/2021 18:12:13 - INFO - __main__ - Step 28143: {'lr': 0.00046248622216277235, 'samples': 5403456, 'steps': 28142, 'loss/train': 1.2355427742004395} 08/30/2021 18:12:13 - INFO - __main__ - Step 28144: {'lr': 0.0004624834261419991, 'samples': 5403648, 'steps': 28143, 'loss/train': 1.6283841133117676} 08/30/2021 18:12:14 - INFO - __main__ - Step 28145: {'lr': 0.000462480630025484, 'samples': 5403840, 'steps': 28144, 'loss/train': 0.5533981323242188} 08/30/2021 18:12:14 - INFO - __main__ - Step 28146: {'lr': 0.0004624778338132285, 'samples': 5404032, 'steps': 28145, 'loss/train': 1.2688381671905518} 08/30/2021 18:12:16 - INFO - __main__ - Step 28147: {'lr': 0.0004624750375052337, 'samples': 5404224, 'steps': 28146, 'loss/train': 1.3087410926818848} 08/30/2021 18:12:17 - INFO - __main__ - Step 28148: {'lr': 0.0004624722411015009, 'samples': 5404416, 'steps': 28147, 'loss/train': 1.15404212474823} 08/30/2021 18:12:17 - INFO - __main__ - Step 28149: {'lr': 0.0004624694446020314, 'samples': 5404608, 'steps': 28148, 'loss/train': 1.3155434131622314} 08/30/2021 18:12:17 - INFO - __main__ - Step 28150: {'lr': 0.0004624666480068265, 'samples': 5404800, 'steps': 28149, 'loss/train': 0.2286374717950821} 08/30/2021 18:12:18 - INFO - __main__ - Step 28151: {'lr': 0.0004624638513158874, 'samples': 5404992, 'steps': 28150, 'loss/train': 1.9606057405471802} 08/30/2021 18:12:19 - INFO - __main__ - Step 28152: {'lr': 0.0004624610545292154, 'samples': 5405184, 'steps': 28151, 'loss/train': 1.2808737754821777} 08/30/2021 18:12:20 - INFO - __main__ - Step 28153: {'lr': 0.00046245825764681166, 'samples': 5405376, 'steps': 28152, 'loss/train': 2.141594409942627} 08/30/2021 18:12:20 - INFO - __main__ - Step 28154: {'lr': 0.0004624554606686775, 'samples': 5405568, 'steps': 28153, 'loss/train': 1.5030946731567383} 08/30/2021 18:12:21 - INFO - __main__ - Step 28155: {'lr': 0.0004624526635948142, 'samples': 5405760, 'steps': 28154, 'loss/train': 0.11189009994268417} 08/30/2021 18:12:21 - INFO - __main__ - Step 28156: {'lr': 0.000462449866425223, 'samples': 5405952, 'steps': 28155, 'loss/train': 0.05983877554535866} 08/30/2021 18:12:21 - INFO - __main__ - Step 28157: {'lr': 0.0004624470691599052, 'samples': 5406144, 'steps': 28156, 'loss/train': 1.673291802406311} 08/30/2021 18:12:23 - INFO - __main__ - Step 28158: {'lr': 0.00046244427179886207, 'samples': 5406336, 'steps': 28157, 'loss/train': 1.4050617218017578} 08/30/2021 18:12:23 - INFO - __main__ - Step 28159: {'lr': 0.0004624414743420947, 'samples': 5406528, 'steps': 28158, 'loss/train': 2.366166353225708} 08/30/2021 18:12:24 - INFO - __main__ - Step 28160: {'lr': 0.00046243867678960463, 'samples': 5406720, 'steps': 28159, 'loss/train': 1.3358148336410522} 08/30/2021 18:12:24 - INFO - __main__ - Step 28161: {'lr': 0.00046243587914139285, 'samples': 5406912, 'steps': 28160, 'loss/train': 1.6666492223739624} 08/30/2021 18:12:24 - INFO - __main__ - Step 28162: {'lr': 0.00046243308139746076, 'samples': 5407104, 'steps': 28161, 'loss/train': 1.4736043214797974} 08/30/2021 18:12:26 - INFO - __main__ - Step 28163: {'lr': 0.00046243028355780967, 'samples': 5407296, 'steps': 28162, 'loss/train': 1.0821442604064941} 08/30/2021 18:12:26 - INFO - __main__ - Step 28164: {'lr': 0.00046242748562244076, 'samples': 5407488, 'steps': 28163, 'loss/train': 0.5729638934135437} 08/30/2021 18:12:27 - INFO - __main__ - Step 28165: {'lr': 0.00046242468759135523, 'samples': 5407680, 'steps': 28164, 'loss/train': 1.7088289260864258} 08/30/2021 18:12:27 - INFO - __main__ - Step 28166: {'lr': 0.00046242188946455444, 'samples': 5407872, 'steps': 28165, 'loss/train': 1.187338948249817} 08/30/2021 18:12:28 - INFO - __main__ - Step 28167: {'lr': 0.0004624190912420397, 'samples': 5408064, 'steps': 28166, 'loss/train': 1.3360848426818848} 08/30/2021 18:12:29 - INFO - __main__ - Step 28168: {'lr': 0.0004624162929238121, 'samples': 5408256, 'steps': 28167, 'loss/train': 1.753943920135498} 08/30/2021 18:12:30 - INFO - __main__ - Step 28169: {'lr': 0.000462413494509873, 'samples': 5408448, 'steps': 28168, 'loss/train': 1.607373833656311} 08/30/2021 18:12:30 - INFO - __main__ - Step 28170: {'lr': 0.0004624106960002237, 'samples': 5408640, 'steps': 28169, 'loss/train': 1.3224910497665405} 08/30/2021 18:12:30 - INFO - __main__ - Step 28171: {'lr': 0.0004624078973948654, 'samples': 5408832, 'steps': 28170, 'loss/train': 0.07940766960382462} 08/30/2021 18:12:31 - INFO - __main__ - Step 28172: {'lr': 0.00046240509869379943, 'samples': 5409024, 'steps': 28171, 'loss/train': 1.4734846353530884} 08/30/2021 18:12:31 - INFO - __main__ - Step 28173: {'lr': 0.00046240229989702697, 'samples': 5409216, 'steps': 28172, 'loss/train': 1.5718226432800293} 08/30/2021 18:12:33 - INFO - __main__ - Step 28174: {'lr': 0.0004623995010045493, 'samples': 5409408, 'steps': 28173, 'loss/train': 1.8593250513076782} 08/30/2021 18:12:34 - INFO - __main__ - Step 28175: {'lr': 0.0004623967020163677, 'samples': 5409600, 'steps': 28174, 'loss/train': 1.6550480127334595} 08/30/2021 18:12:34 - INFO - __main__ - Step 28176: {'lr': 0.0004623939029324834, 'samples': 5409792, 'steps': 28175, 'loss/train': 1.3389935493469238} 08/30/2021 18:12:34 - INFO - __main__ - Step 28177: {'lr': 0.0004623911037528977, 'samples': 5409984, 'steps': 28176, 'loss/train': 1.6478055715560913} 08/30/2021 18:12:35 - INFO - __main__ - Step 28178: {'lr': 0.00046238830447761184, 'samples': 5410176, 'steps': 28177, 'loss/train': 1.7442591190338135} 08/30/2021 18:12:35 - INFO - __main__ - Step 28179: {'lr': 0.0004623855051066271, 'samples': 5410368, 'steps': 28178, 'loss/train': 1.2677836418151855} 08/30/2021 18:12:37 - INFO - __main__ - Step 28180: {'lr': 0.00046238270563994465, 'samples': 5410560, 'steps': 28179, 'loss/train': 1.6171486377716064} 08/30/2021 18:12:38 - INFO - __main__ - Step 28181: {'lr': 0.00046237990607756596, 'samples': 5410752, 'steps': 28180, 'loss/train': 1.4700666666030884} 08/30/2021 18:12:38 - INFO - __main__ - Step 28182: {'lr': 0.0004623771064194921, 'samples': 5410944, 'steps': 28181, 'loss/train': 0.5983209609985352} 08/30/2021 18:12:38 - INFO - __main__ - Step 28183: {'lr': 0.0004623743066657244, 'samples': 5411136, 'steps': 28182, 'loss/train': 0.4780607223510742} 08/30/2021 18:12:39 - INFO - __main__ - Step 28184: {'lr': 0.00046237150681626414, 'samples': 5411328, 'steps': 28183, 'loss/train': 0.4769774377346039} 08/30/2021 18:12:39 - INFO - __main__ - Step 28185: {'lr': 0.00046236870687111254, 'samples': 5411520, 'steps': 28184, 'loss/train': 1.4490569829940796} 08/30/2021 18:12:41 - INFO - __main__ - Step 28186: {'lr': 0.0004623659068302708, 'samples': 5411712, 'steps': 28185, 'loss/train': 0.22667363286018372} 08/30/2021 18:12:41 - INFO - __main__ - Step 28187: {'lr': 0.00046236310669374035, 'samples': 5411904, 'steps': 28186, 'loss/train': 2.009615898132324} 08/30/2021 18:12:41 - INFO - __main__ - Step 28188: {'lr': 0.0004623603064615223, 'samples': 5412096, 'steps': 28187, 'loss/train': 0.99207603931427} 08/30/2021 18:12:42 - INFO - __main__ - Step 28189: {'lr': 0.000462357506133618, 'samples': 5412288, 'steps': 28188, 'loss/train': 1.8395366668701172} 08/30/2021 18:12:42 - INFO - __main__ - Step 28190: {'lr': 0.00046235470571002877, 'samples': 5412480, 'steps': 28189, 'loss/train': 1.4065794944763184} 08/30/2021 18:12:42 - INFO - __main__ - Step 28191: {'lr': 0.00046235190519075564, 'samples': 5412672, 'steps': 28190, 'loss/train': 1.8146851062774658} 08/30/2021 18:12:44 - INFO - __main__ - Step 28192: {'lr': 0.00046234910457580014, 'samples': 5412864, 'steps': 28191, 'loss/train': 1.6898690462112427} 08/30/2021 18:12:45 - INFO - __main__ - Step 28193: {'lr': 0.0004623463038651633, 'samples': 5413056, 'steps': 28192, 'loss/train': 0.153415709733963} 08/30/2021 18:12:45 - INFO - __main__ - Step 28194: {'lr': 0.0004623435030588466, 'samples': 5413248, 'steps': 28193, 'loss/train': 1.0885311365127563} 08/30/2021 18:12:45 - INFO - __main__ - Step 28195: {'lr': 0.00046234070215685116, 'samples': 5413440, 'steps': 28194, 'loss/train': 1.56862473487854} 08/30/2021 18:12:46 - INFO - __main__ - Step 28196: {'lr': 0.0004623379011591782, 'samples': 5413632, 'steps': 28195, 'loss/train': 0.537412703037262} 08/30/2021 18:12:47 - INFO - __main__ - Step 28197: {'lr': 0.00046233510006582913, 'samples': 5413824, 'steps': 28196, 'loss/train': 1.6278892755508423} 08/30/2021 18:12:48 - INFO - __main__ - Step 28198: {'lr': 0.00046233229887680517, 'samples': 5414016, 'steps': 28197, 'loss/train': 2.501605749130249} 08/30/2021 18:12:48 - INFO - __main__ - Step 28199: {'lr': 0.00046232949759210753, 'samples': 5414208, 'steps': 28198, 'loss/train': 1.147364854812622} 08/30/2021 18:12:48 - INFO - __main__ - Step 28200: {'lr': 0.00046232669621173745, 'samples': 5414400, 'steps': 28199, 'loss/train': 1.6096371412277222} 08/30/2021 18:12:49 - INFO - __main__ - Step 28201: {'lr': 0.00046232389473569623, 'samples': 5414592, 'steps': 28200, 'loss/train': 1.3819606304168701} 08/30/2021 18:12:50 - INFO - __main__ - Step 28202: {'lr': 0.0004623210931639852, 'samples': 5414784, 'steps': 28201, 'loss/train': 2.25793719291687} 08/30/2021 18:12:51 - INFO - __main__ - Step 28203: {'lr': 0.00046231829149660553, 'samples': 5414976, 'steps': 28202, 'loss/train': 1.1932913064956665} 08/30/2021 18:12:51 - INFO - __main__ - Step 28204: {'lr': 0.00046231548973355854, 'samples': 5415168, 'steps': 28203, 'loss/train': 1.3090009689331055} 08/30/2021 18:12:51 - INFO - __main__ - Step 28205: {'lr': 0.00046231268787484545, 'samples': 5415360, 'steps': 28204, 'loss/train': 2.3537867069244385} 08/30/2021 18:12:52 - INFO - __main__ - Step 28206: {'lr': 0.0004623098859204675, 'samples': 5415552, 'steps': 28205, 'loss/train': 1.8150583505630493} 08/30/2021 18:12:53 - INFO - __main__ - Step 28207: {'lr': 0.00046230708387042603, 'samples': 5415744, 'steps': 28206, 'loss/train': 1.7018022537231445} 08/30/2021 18:12:54 - INFO - __main__ - Step 28208: {'lr': 0.0004623042817247223, 'samples': 5415936, 'steps': 28207, 'loss/train': 1.6013038158416748} 08/30/2021 18:12:54 - INFO - __main__ - Step 28209: {'lr': 0.00046230147948335746, 'samples': 5416128, 'steps': 28208, 'loss/train': 1.664321780204773} 08/30/2021 18:12:54 - INFO - __main__ - Step 28210: {'lr': 0.0004622986771463329, 'samples': 5416320, 'steps': 28209, 'loss/train': 1.4428523778915405} 08/30/2021 18:12:55 - INFO - __main__ - Step 28211: {'lr': 0.0004622958747136498, 'samples': 5416512, 'steps': 28210, 'loss/train': 1.4926539659500122} 08/30/2021 18:12:56 - INFO - __main__ - Step 28212: {'lr': 0.00046229307218530945, 'samples': 5416704, 'steps': 28211, 'loss/train': 1.5020993947982788} 08/30/2021 18:12:57 - INFO - __main__ - Step 28213: {'lr': 0.0004622902695613131, 'samples': 5416896, 'steps': 28212, 'loss/train': 1.1484891176223755} 08/30/2021 18:12:57 - INFO - __main__ - Step 28214: {'lr': 0.00046228746684166214, 'samples': 5417088, 'steps': 28213, 'loss/train': 1.8509457111358643} 08/30/2021 18:12:57 - INFO - __main__ - Step 28215: {'lr': 0.00046228466402635764, 'samples': 5417280, 'steps': 28214, 'loss/train': 1.9831180572509766} 08/30/2021 18:12:58 - INFO - __main__ - Step 28216: {'lr': 0.0004622818611154009, 'samples': 5417472, 'steps': 28215, 'loss/train': 1.021217942237854} 08/30/2021 18:12:58 - INFO - __main__ - Step 28217: {'lr': 0.00046227905810879334, 'samples': 5417664, 'steps': 28216, 'loss/train': 0.9175899028778076} 08/30/2021 18:13:00 - INFO - __main__ - Step 28218: {'lr': 0.0004622762550065361, 'samples': 5417856, 'steps': 28217, 'loss/train': 1.1760281324386597} 08/30/2021 18:13:00 - INFO - __main__ - Step 28219: {'lr': 0.0004622734518086304, 'samples': 5418048, 'steps': 28218, 'loss/train': 1.3560354709625244} 08/30/2021 18:13:01 - INFO - __main__ - Step 28220: {'lr': 0.0004622706485150776, 'samples': 5418240, 'steps': 28219, 'loss/train': 1.9772204160690308} 08/30/2021 18:13:01 - INFO - __main__ - Step 28221: {'lr': 0.0004622678451258788, 'samples': 5418432, 'steps': 28220, 'loss/train': 2.1146113872528076} 08/30/2021 18:13:01 - INFO - __main__ - Step 28222: {'lr': 0.00046226504164103557, 'samples': 5418624, 'steps': 28221, 'loss/train': 1.2535582780838013} 08/30/2021 18:13:03 - INFO - __main__ - Step 28223: {'lr': 0.0004622622380605489, 'samples': 5418816, 'steps': 28222, 'loss/train': 0.22345010936260223} 08/30/2021 18:13:03 - INFO - __main__ - Step 28224: {'lr': 0.0004622594343844201, 'samples': 5419008, 'steps': 28223, 'loss/train': 1.1060556173324585} 08/30/2021 18:13:04 - INFO - __main__ - Step 28225: {'lr': 0.00046225663061265056, 'samples': 5419200, 'steps': 28224, 'loss/train': 1.5601060390472412} 08/30/2021 18:13:04 - INFO - __main__ - Step 28226: {'lr': 0.0004622538267452414, 'samples': 5419392, 'steps': 28225, 'loss/train': 1.9933298826217651} 08/30/2021 18:13:04 - INFO - __main__ - Step 28227: {'lr': 0.00046225102278219394, 'samples': 5419584, 'steps': 28226, 'loss/train': 1.4421290159225464} 08/30/2021 18:13:07 - INFO - __main__ - Step 28228: {'lr': 0.0004622482187235094, 'samples': 5419776, 'steps': 28227, 'loss/train': 1.6272094249725342} 08/30/2021 18:13:07 - INFO - __main__ - Step 28229: {'lr': 0.00046224541456918916, 'samples': 5419968, 'steps': 28228, 'loss/train': 1.554030418395996} 08/30/2021 18:13:07 - INFO - __main__ - Step 28230: {'lr': 0.0004622426103192344, 'samples': 5420160, 'steps': 28229, 'loss/train': 1.3759022951126099} 08/30/2021 18:13:08 - INFO - __main__ - Step 28231: {'lr': 0.00046223980597364647, 'samples': 5420352, 'steps': 28230, 'loss/train': 1.3608697652816772} 08/30/2021 18:13:08 - INFO - __main__ - Step 28232: {'lr': 0.0004622370015324264, 'samples': 5420544, 'steps': 28231, 'loss/train': 2.0276691913604736} 08/30/2021 18:13:08 - INFO - __main__ - Step 28233: {'lr': 0.0004622341969955757, 'samples': 5420736, 'steps': 28232, 'loss/train': 1.8577359914779663} 08/30/2021 18:13:10 - INFO - __main__ - Step 28234: {'lr': 0.00046223139236309553, 'samples': 5420928, 'steps': 28233, 'loss/train': 0.9461192488670349} 08/30/2021 18:13:11 - INFO - __main__ - Step 28235: {'lr': 0.0004622285876349872, 'samples': 5421120, 'steps': 28234, 'loss/train': 0.7482120990753174} 08/30/2021 18:13:11 - INFO - __main__ - Step 28236: {'lr': 0.00046222578281125194, 'samples': 5421312, 'steps': 28235, 'loss/train': 1.4742566347122192} 08/30/2021 18:13:11 - INFO - __main__ - Step 28237: {'lr': 0.0004622229778918909, 'samples': 5421504, 'steps': 28236, 'loss/train': 0.9649300575256348} 08/30/2021 18:13:12 - INFO - __main__ - Step 28238: {'lr': 0.00046222017287690566, 'samples': 5421696, 'steps': 28237, 'loss/train': 1.6385213136672974} 08/30/2021 18:13:14 - INFO - __main__ - Step 28239: {'lr': 0.00046221736776629713, 'samples': 5421888, 'steps': 28238, 'loss/train': 1.564038872718811} 08/30/2021 18:13:14 - INFO - __main__ - Step 28240: {'lr': 0.0004622145625600668, 'samples': 5422080, 'steps': 28239, 'loss/train': 1.3118025064468384} 08/30/2021 18:13:15 - INFO - __main__ - Step 28241: {'lr': 0.00046221175725821585, 'samples': 5422272, 'steps': 28240, 'loss/train': 1.225050687789917} 08/30/2021 18:13:15 - INFO - __main__ - Step 28242: {'lr': 0.00046220895186074553, 'samples': 5422464, 'steps': 28241, 'loss/train': 1.1002739667892456} 08/30/2021 18:13:15 - INFO - __main__ - Step 28243: {'lr': 0.0004622061463676572, 'samples': 5422656, 'steps': 28242, 'loss/train': 1.6412336826324463} 08/30/2021 18:13:16 - INFO - __main__ - Step 28244: {'lr': 0.000462203340778952, 'samples': 5422848, 'steps': 28243, 'loss/train': 1.8457484245300293} 08/30/2021 18:13:16 - INFO - __main__ - Step 28245: {'lr': 0.0004622005350946312, 'samples': 5423040, 'steps': 28244, 'loss/train': 0.09960411489009857} 08/30/2021 18:13:17 - INFO - __main__ - Step 28246: {'lr': 0.00046219772931469617, 'samples': 5423232, 'steps': 28245, 'loss/train': 1.8270965814590454} 08/30/2021 18:13:18 - INFO - __main__ - Step 28247: {'lr': 0.00046219492343914815, 'samples': 5423424, 'steps': 28246, 'loss/train': 1.3844245672225952} 08/30/2021 18:13:18 - INFO - __main__ - Step 28248: {'lr': 0.00046219211746798835, 'samples': 5423616, 'steps': 28247, 'loss/train': 1.5090340375900269} 08/30/2021 18:13:19 - INFO - __main__ - Step 28249: {'lr': 0.000462189311401218, 'samples': 5423808, 'steps': 28248, 'loss/train': 1.3838329315185547} 08/30/2021 18:13:20 - INFO - __main__ - Step 28250: {'lr': 0.0004621865052388385, 'samples': 5424000, 'steps': 28249, 'loss/train': 1.3188226222991943} 08/30/2021 18:13:20 - INFO - __main__ - Step 28251: {'lr': 0.00046218369898085097, 'samples': 5424192, 'steps': 28250, 'loss/train': 0.8289266228675842} 08/30/2021 18:13:21 - INFO - __main__ - Step 28252: {'lr': 0.0004621808926272568, 'samples': 5424384, 'steps': 28251, 'loss/train': 1.43550705909729} 08/30/2021 18:13:21 - INFO - __main__ - Step 28253: {'lr': 0.0004621780861780572, 'samples': 5424576, 'steps': 28252, 'loss/train': 1.619834303855896} 08/30/2021 18:13:21 - INFO - __main__ - Step 28254: {'lr': 0.00046217527963325335, 'samples': 5424768, 'steps': 28253, 'loss/train': 1.370830774307251} 08/30/2021 18:13:22 - INFO - __main__ - Step 28255: {'lr': 0.00046217247299284666, 'samples': 5424960, 'steps': 28254, 'loss/train': 1.5683119297027588} 08/30/2021 18:13:23 - INFO - __main__ - Step 28256: {'lr': 0.00046216966625683834, 'samples': 5425152, 'steps': 28255, 'loss/train': 1.78057861328125} 08/30/2021 18:13:24 - INFO - __main__ - Step 28257: {'lr': 0.00046216685942522957, 'samples': 5425344, 'steps': 28256, 'loss/train': 1.5489559173583984} 08/30/2021 18:13:24 - INFO - __main__ - Step 28258: {'lr': 0.00046216405249802176, 'samples': 5425536, 'steps': 28257, 'loss/train': 0.8627528548240662} 08/30/2021 18:13:25 - INFO - __main__ - Step 28259: {'lr': 0.000462161245475216, 'samples': 5425728, 'steps': 28258, 'loss/train': 1.8499099016189575} 08/30/2021 18:13:25 - INFO - __main__ - Step 28260: {'lr': 0.0004621584383568137, 'samples': 5425920, 'steps': 28259, 'loss/train': 1.62791907787323} 08/30/2021 18:13:27 - INFO - __main__ - Step 28261: {'lr': 0.00046215563114281613, 'samples': 5426112, 'steps': 28260, 'loss/train': 1.87300443649292} 08/30/2021 18:13:27 - INFO - __main__ - Step 28262: {'lr': 0.0004621528238332245, 'samples': 5426304, 'steps': 28261, 'loss/train': 1.4125200510025024} 08/30/2021 18:13:28 - INFO - __main__ - Step 28263: {'lr': 0.00046215001642804, 'samples': 5426496, 'steps': 28262, 'loss/train': 1.8862314224243164} 08/30/2021 18:13:28 - INFO - __main__ - Step 28264: {'lr': 0.0004621472089272641, 'samples': 5426688, 'steps': 28263, 'loss/train': 1.7736948728561401} 08/30/2021 18:13:28 - INFO - __main__ - Step 28265: {'lr': 0.0004621444013308979, 'samples': 5426880, 'steps': 28264, 'loss/train': 0.8786599636077881} 08/30/2021 18:13:30 - INFO - __main__ - Step 28266: {'lr': 0.00046214159363894264, 'samples': 5427072, 'steps': 28265, 'loss/train': 1.8863425254821777} 08/30/2021 18:13:30 - INFO - __main__ - Step 28267: {'lr': 0.0004621387858513997, 'samples': 5427264, 'steps': 28266, 'loss/train': 1.5940356254577637} 08/30/2021 18:13:31 - INFO - __main__ - Step 28268: {'lr': 0.0004621359779682703, 'samples': 5427456, 'steps': 28267, 'loss/train': 1.152202844619751} 08/30/2021 18:13:31 - INFO - __main__ - Step 28269: {'lr': 0.0004621331699895557, 'samples': 5427648, 'steps': 28268, 'loss/train': 1.841621994972229} 08/30/2021 18:13:31 - INFO - __main__ - Step 28270: {'lr': 0.00046213036191525714, 'samples': 5427840, 'steps': 28269, 'loss/train': 1.209489107131958} 08/30/2021 18:13:33 - INFO - __main__ - Step 28271: {'lr': 0.00046212755374537594, 'samples': 5428032, 'steps': 28270, 'loss/train': 2.1603636741638184} 08/30/2021 18:13:34 - INFO - __main__ - Step 28272: {'lr': 0.0004621247454799133, 'samples': 5428224, 'steps': 28271, 'loss/train': 2.1762497425079346} 08/30/2021 18:13:34 - INFO - __main__ - Step 28273: {'lr': 0.0004621219371188706, 'samples': 5428416, 'steps': 28272, 'loss/train': 1.7961615324020386} 08/30/2021 18:13:34 - INFO - __main__ - Step 28274: {'lr': 0.0004621191286622489, 'samples': 5428608, 'steps': 28273, 'loss/train': 1.6145116090774536} 08/30/2021 18:13:35 - INFO - __main__ - Step 28275: {'lr': 0.00046211632011004973, 'samples': 5428800, 'steps': 28274, 'loss/train': 1.9258496761322021} 08/30/2021 18:13:35 - INFO - __main__ - Step 28276: {'lr': 0.0004621135114622742, 'samples': 5428992, 'steps': 28275, 'loss/train': 1.7441402673721313} 08/30/2021 18:13:37 - INFO - __main__ - Step 28277: {'lr': 0.00046211070271892353, 'samples': 5429184, 'steps': 28276, 'loss/train': 1.7774789333343506} 08/30/2021 18:13:37 - INFO - __main__ - Step 28278: {'lr': 0.00046210789387999906, 'samples': 5429376, 'steps': 28277, 'loss/train': 1.2015700340270996} 08/30/2021 18:13:37 - INFO - __main__ - Step 28279: {'lr': 0.00046210508494550206, 'samples': 5429568, 'steps': 28278, 'loss/train': 1.683435082435608} 08/30/2021 18:13:38 - INFO - __main__ - Step 28280: {'lr': 0.0004621022759154338, 'samples': 5429760, 'steps': 28279, 'loss/train': 1.4273407459259033} 08/30/2021 18:13:38 - INFO - __main__ - Step 28281: {'lr': 0.0004620994667897955, 'samples': 5429952, 'steps': 28280, 'loss/train': 1.6851435899734497} 08/30/2021 18:13:40 - INFO - __main__ - Step 28282: {'lr': 0.0004620966575685885, 'samples': 5430144, 'steps': 28281, 'loss/train': 1.733172059059143} 08/30/2021 18:13:40 - INFO - __main__ - Step 28283: {'lr': 0.000462093848251814, 'samples': 5430336, 'steps': 28282, 'loss/train': 2.0656027793884277} 08/30/2021 18:13:40 - INFO - __main__ - Step 28284: {'lr': 0.00046209103883947323, 'samples': 5430528, 'steps': 28283, 'loss/train': 2.0980305671691895} 08/30/2021 18:13:41 - INFO - __main__ - Step 28285: {'lr': 0.00046208822933156756, 'samples': 5430720, 'steps': 28284, 'loss/train': 0.9545504450798035} 08/30/2021 18:13:41 - INFO - __main__ - Step 28286: {'lr': 0.00046208541972809824, 'samples': 5430912, 'steps': 28285, 'loss/train': 1.118975281715393} 08/30/2021 18:13:43 - INFO - __main__ - Step 28287: {'lr': 0.00046208261002906643, 'samples': 5431104, 'steps': 28286, 'loss/train': 1.6077806949615479} 08/30/2021 18:13:44 - INFO - __main__ - Step 28288: {'lr': 0.00046207980023447347, 'samples': 5431296, 'steps': 28287, 'loss/train': 1.4952181577682495} 08/30/2021 18:13:44 - INFO - __main__ - Step 28289: {'lr': 0.0004620769903443207, 'samples': 5431488, 'steps': 28288, 'loss/train': 1.4617315530776978} 08/30/2021 18:13:44 - INFO - __main__ - Step 28290: {'lr': 0.00046207418035860927, 'samples': 5431680, 'steps': 28289, 'loss/train': 1.4859063625335693} 08/30/2021 18:13:45 - INFO - __main__ - Step 28291: {'lr': 0.00046207137027734046, 'samples': 5431872, 'steps': 28290, 'loss/train': 1.8514564037322998} 08/30/2021 18:13:47 - INFO - __main__ - Step 28292: {'lr': 0.00046206856010051555, 'samples': 5432064, 'steps': 28291, 'loss/train': 2.224961757659912} 08/30/2021 18:13:47 - INFO - __main__ - Step 28293: {'lr': 0.0004620657498281359, 'samples': 5432256, 'steps': 28292, 'loss/train': 0.8435643911361694} 08/30/2021 18:13:47 - INFO - __main__ - Step 28294: {'lr': 0.0004620629394602027, 'samples': 5432448, 'steps': 28293, 'loss/train': 1.0814980268478394} 08/30/2021 18:13:48 - INFO - __main__ - Step 28295: {'lr': 0.00046206012899671715, 'samples': 5432640, 'steps': 28294, 'loss/train': 1.6488440036773682} 08/30/2021 18:13:48 - INFO - __main__ - Step 28296: {'lr': 0.00046205731843768056, 'samples': 5432832, 'steps': 28295, 'loss/train': 0.16759580373764038} 08/30/2021 18:13:48 - INFO - __main__ - Step 28297: {'lr': 0.0004620545077830942, 'samples': 5433024, 'steps': 28296, 'loss/train': 1.2041758298873901} 08/30/2021 18:13:50 - INFO - __main__ - Step 28298: {'lr': 0.00046205169703295945, 'samples': 5433216, 'steps': 28297, 'loss/train': 0.05389319732785225} 08/30/2021 18:13:50 - INFO - __main__ - Step 28299: {'lr': 0.00046204888618727743, 'samples': 5433408, 'steps': 28298, 'loss/train': 1.9713691473007202} 08/30/2021 18:13:51 - INFO - __main__ - Step 28300: {'lr': 0.00046204607524604944, 'samples': 5433600, 'steps': 28299, 'loss/train': 1.9003307819366455} 08/30/2021 18:13:51 - INFO - __main__ - Step 28301: {'lr': 0.0004620432642092768, 'samples': 5433792, 'steps': 28300, 'loss/train': 1.5967423915863037} 08/30/2021 18:13:51 - INFO - __main__ - Step 28302: {'lr': 0.00046204045307696065, 'samples': 5433984, 'steps': 28301, 'loss/train': 1.4647635221481323} 08/30/2021 18:13:53 - INFO - __main__ - Step 28303: {'lr': 0.0004620376418491024, 'samples': 5434176, 'steps': 28302, 'loss/train': 1.2555168867111206} 08/30/2021 18:13:53 - INFO - __main__ - Step 28304: {'lr': 0.0004620348305257033, 'samples': 5434368, 'steps': 28303, 'loss/train': 1.426172137260437} 08/30/2021 18:13:54 - INFO - __main__ - Step 28305: {'lr': 0.00046203201910676453, 'samples': 5434560, 'steps': 28304, 'loss/train': 2.701510429382324} 08/30/2021 18:13:54 - INFO - __main__ - Step 28306: {'lr': 0.0004620292075922874, 'samples': 5434752, 'steps': 28305, 'loss/train': 0.5252964496612549} 08/30/2021 18:13:55 - INFO - __main__ - Step 28307: {'lr': 0.0004620263959822732, 'samples': 5434944, 'steps': 28306, 'loss/train': 1.3321943283081055} 08/30/2021 18:13:56 - INFO - __main__ - Step 28308: {'lr': 0.00046202358427672313, 'samples': 5435136, 'steps': 28307, 'loss/train': 1.5458296537399292} 08/30/2021 18:13:56 - INFO - __main__ - Step 28309: {'lr': 0.0004620207724756386, 'samples': 5435328, 'steps': 28308, 'loss/train': 2.0445430278778076} 08/30/2021 18:13:57 - INFO - __main__ - Step 28310: {'lr': 0.0004620179605790207, 'samples': 5435520, 'steps': 28309, 'loss/train': 1.6305828094482422} 08/30/2021 18:13:57 - INFO - __main__ - Step 28311: {'lr': 0.00046201514858687075, 'samples': 5435712, 'steps': 28310, 'loss/train': 1.4723097085952759} 08/30/2021 18:13:57 - INFO - __main__ - Step 28312: {'lr': 0.00046201233649919015, 'samples': 5435904, 'steps': 28311, 'loss/train': 1.7970898151397705} 08/30/2021 18:13:58 - INFO - __main__ - Step 28313: {'lr': 0.00046200952431598, 'samples': 5436096, 'steps': 28312, 'loss/train': 1.403132438659668} 08/30/2021 18:13:59 - INFO - __main__ - Step 28314: {'lr': 0.00046200671203724166, 'samples': 5436288, 'steps': 28313, 'loss/train': 1.559372067451477} 08/30/2021 18:14:00 - INFO - __main__ - Step 28315: {'lr': 0.00046200389966297633, 'samples': 5436480, 'steps': 28314, 'loss/train': 1.3774646520614624} 08/30/2021 18:14:00 - INFO - __main__ - Step 28316: {'lr': 0.00046200108719318537, 'samples': 5436672, 'steps': 28315, 'loss/train': 1.62782883644104} 08/30/2021 18:14:01 - INFO - __main__ - Step 28317: {'lr': 0.0004619982746278699, 'samples': 5436864, 'steps': 28316, 'loss/train': 1.450161099433899} 08/30/2021 18:14:01 - INFO - __main__ - Step 28318: {'lr': 0.00046199546196703134, 'samples': 5437056, 'steps': 28317, 'loss/train': 1.4043141603469849} 08/30/2021 18:14:02 - INFO - __main__ - Step 28319: {'lr': 0.0004619926492106709, 'samples': 5437248, 'steps': 28318, 'loss/train': 1.6663156747817993} 08/30/2021 18:14:03 - INFO - __main__ - Step 28320: {'lr': 0.0004619898363587899, 'samples': 5437440, 'steps': 28319, 'loss/train': 1.7252740859985352} 08/30/2021 18:14:03 - INFO - __main__ - Step 28321: {'lr': 0.00046198702341138944, 'samples': 5437632, 'steps': 28320, 'loss/train': 1.3548163175582886} 08/30/2021 18:14:04 - INFO - __main__ - Step 28322: {'lr': 0.00046198421036847093, 'samples': 5437824, 'steps': 28321, 'loss/train': 1.4695861339569092} 08/30/2021 18:14:04 - INFO - __main__ - Step 28323: {'lr': 0.00046198139723003563, 'samples': 5438016, 'steps': 28322, 'loss/train': 1.5358189344406128} 08/30/2021 18:14:05 - INFO - __main__ - Step 28324: {'lr': 0.00046197858399608477, 'samples': 5438208, 'steps': 28323, 'loss/train': 1.2871755361557007} 08/30/2021 18:14:06 - INFO - __main__ - Step 28325: {'lr': 0.00046197577066661965, 'samples': 5438400, 'steps': 28324, 'loss/train': 1.3666163682937622} 08/30/2021 18:14:06 - INFO - __main__ - Step 28326: {'lr': 0.0004619729572416415, 'samples': 5438592, 'steps': 28325, 'loss/train': 2.72617244720459} 08/30/2021 18:14:07 - INFO - __main__ - Step 28327: {'lr': 0.0004619701437211516, 'samples': 5438784, 'steps': 28326, 'loss/train': 1.4934099912643433} 08/30/2021 18:14:07 - INFO - __main__ - Step 28328: {'lr': 0.00046196733010515125, 'samples': 5438976, 'steps': 28327, 'loss/train': 1.6686969995498657} 08/30/2021 18:14:08 - INFO - __main__ - Step 28329: {'lr': 0.0004619645163936417, 'samples': 5439168, 'steps': 28328, 'loss/train': 1.957667350769043} 08/30/2021 18:14:09 - INFO - __main__ - Step 28330: {'lr': 0.0004619617025866242, 'samples': 5439360, 'steps': 28329, 'loss/train': 1.5146355628967285} 08/30/2021 18:14:09 - INFO - __main__ - Step 28331: {'lr': 0.00046195888868409994, 'samples': 5439552, 'steps': 28330, 'loss/train': 1.9308141469955444} 08/30/2021 18:14:10 - INFO - __main__ - Step 28332: {'lr': 0.0004619560746860704, 'samples': 5439744, 'steps': 28331, 'loss/train': 1.9257309436798096} 08/30/2021 18:14:10 - INFO - __main__ - Step 28333: {'lr': 0.0004619532605925366, 'samples': 5439936, 'steps': 28332, 'loss/train': 1.0161665678024292} 08/30/2021 18:14:10 - INFO - __main__ - Step 28334: {'lr': 0.00046195044640350003, 'samples': 5440128, 'steps': 28333, 'loss/train': 1.4778785705566406} 08/30/2021 18:14:12 - INFO - __main__ - Step 28335: {'lr': 0.00046194763211896187, 'samples': 5440320, 'steps': 28334, 'loss/train': 1.8597382307052612} 08/30/2021 18:14:12 - INFO - __main__ - Step 28336: {'lr': 0.0004619448177389233, 'samples': 5440512, 'steps': 28335, 'loss/train': 1.4075936079025269} 08/30/2021 18:14:13 - INFO - __main__ - Step 28337: {'lr': 0.0004619420032633857, 'samples': 5440704, 'steps': 28336, 'loss/train': 2.8559982776641846} 08/30/2021 18:14:13 - INFO - __main__ - Step 28338: {'lr': 0.0004619391886923503, 'samples': 5440896, 'steps': 28337, 'loss/train': 1.4946178197860718} 08/30/2021 18:14:13 - INFO - __main__ - Step 28339: {'lr': 0.0004619363740258184, 'samples': 5441088, 'steps': 28338, 'loss/train': 0.7726243138313293} 08/30/2021 18:14:15 - INFO - __main__ - Step 28340: {'lr': 0.00046193355926379124, 'samples': 5441280, 'steps': 28339, 'loss/train': 1.4866501092910767} 08/30/2021 18:14:16 - INFO - __main__ - Step 28341: {'lr': 0.00046193074440627, 'samples': 5441472, 'steps': 28340, 'loss/train': 1.4543671607971191} 08/30/2021 18:14:16 - INFO - __main__ - Step 28342: {'lr': 0.0004619279294532561, 'samples': 5441664, 'steps': 28341, 'loss/train': 1.950999140739441} 08/30/2021 18:14:16 - INFO - __main__ - Step 28343: {'lr': 0.00046192511440475083, 'samples': 5441856, 'steps': 28342, 'loss/train': 1.2707509994506836} 08/30/2021 18:14:17 - INFO - __main__ - Step 28344: {'lr': 0.00046192229926075526, 'samples': 5442048, 'steps': 28343, 'loss/train': 1.6523293256759644} 08/30/2021 18:14:18 - INFO - __main__ - Step 28345: {'lr': 0.0004619194840212708, 'samples': 5442240, 'steps': 28344, 'loss/train': 1.6364619731903076} 08/30/2021 18:14:19 - INFO - __main__ - Step 28346: {'lr': 0.0004619166686862987, 'samples': 5442432, 'steps': 28345, 'loss/train': 1.5701013803482056} 08/30/2021 18:14:19 - INFO - __main__ - Step 28347: {'lr': 0.0004619138532558402, 'samples': 5442624, 'steps': 28346, 'loss/train': 1.5248124599456787} 08/30/2021 18:14:19 - INFO - __main__ - Step 28348: {'lr': 0.00046191103772989664, 'samples': 5442816, 'steps': 28347, 'loss/train': 1.0147887468338013} 08/30/2021 18:14:20 - INFO - __main__ - Step 28349: {'lr': 0.00046190822210846917, 'samples': 5443008, 'steps': 28348, 'loss/train': 1.3319716453552246} 08/30/2021 18:14:21 - INFO - __main__ - Step 28350: {'lr': 0.0004619054063915592, 'samples': 5443200, 'steps': 28349, 'loss/train': 1.3324525356292725} 08/30/2021 18:14:22 - INFO - __main__ - Step 28351: {'lr': 0.00046190259057916786, 'samples': 5443392, 'steps': 28350, 'loss/train': 0.8180599212646484} 08/30/2021 18:14:22 - INFO - __main__ - Step 28352: {'lr': 0.0004618997746712965, 'samples': 5443584, 'steps': 28351, 'loss/train': 1.5923995971679688} 08/30/2021 18:14:22 - INFO - __main__ - Step 28353: {'lr': 0.00046189695866794635, 'samples': 5443776, 'steps': 28352, 'loss/train': 1.2761247158050537} 08/30/2021 18:14:23 - INFO - __main__ - Step 28354: {'lr': 0.00046189414256911875, 'samples': 5443968, 'steps': 28353, 'loss/train': 2.637528419494629} 08/30/2021 18:14:25 - INFO - __main__ - Step 28355: {'lr': 0.0004618913263748149, 'samples': 5444160, 'steps': 28354, 'loss/train': 1.7462899684906006} 08/30/2021 18:14:25 - INFO - __main__ - Step 28356: {'lr': 0.0004618885100850361, 'samples': 5444352, 'steps': 28355, 'loss/train': 1.6216866970062256} 08/30/2021 18:14:26 - INFO - __main__ - Step 28357: {'lr': 0.0004618856936997836, 'samples': 5444544, 'steps': 28356, 'loss/train': 1.2861307859420776} 08/30/2021 18:14:26 - INFO - __main__ - Step 28358: {'lr': 0.0004618828772190586, 'samples': 5444736, 'steps': 28357, 'loss/train': 1.8551957607269287} 08/30/2021 18:14:26 - INFO - __main__ - Step 28359: {'lr': 0.0004618800606428626, 'samples': 5444928, 'steps': 28358, 'loss/train': 1.779967188835144} 08/30/2021 18:14:27 - INFO - __main__ - Step 28360: {'lr': 0.00046187724397119657, 'samples': 5445120, 'steps': 28359, 'loss/train': 1.662474513053894} 08/30/2021 18:14:29 - INFO - __main__ - Step 28361: {'lr': 0.000461874427204062, 'samples': 5445312, 'steps': 28360, 'loss/train': 1.8396095037460327} 08/30/2021 18:14:29 - INFO - __main__ - Step 28362: {'lr': 0.00046187161034146, 'samples': 5445504, 'steps': 28361, 'loss/train': 1.1978753805160522} 08/30/2021 18:14:29 - INFO - __main__ - Step 28363: {'lr': 0.00046186879338339207, 'samples': 5445696, 'steps': 28362, 'loss/train': 1.5329073667526245} 08/30/2021 18:14:30 - INFO - __main__ - Step 28364: {'lr': 0.0004618659763298592, 'samples': 5445888, 'steps': 28363, 'loss/train': 1.1845771074295044} 08/30/2021 18:14:30 - INFO - __main__ - Step 28365: {'lr': 0.00046186315918086285, 'samples': 5446080, 'steps': 28364, 'loss/train': 1.5781322717666626} 08/30/2021 18:14:30 - INFO - __main__ - Step 28366: {'lr': 0.0004618603419364042, 'samples': 5446272, 'steps': 28365, 'loss/train': 1.47245192527771} 08/30/2021 18:14:32 - INFO - __main__ - Step 28367: {'lr': 0.00046185752459648456, 'samples': 5446464, 'steps': 28366, 'loss/train': 0.07523348927497864} 08/30/2021 18:14:33 - INFO - __main__ - Step 28368: {'lr': 0.00046185470716110516, 'samples': 5446656, 'steps': 28367, 'loss/train': 1.4055206775665283} 08/30/2021 18:14:33 - INFO - __main__ - Step 28369: {'lr': 0.00046185188963026734, 'samples': 5446848, 'steps': 28368, 'loss/train': 3.3890609741210938} 08/30/2021 18:14:33 - INFO - __main__ - Step 28370: {'lr': 0.0004618490720039723, 'samples': 5447040, 'steps': 28369, 'loss/train': 1.3116455078125} 08/30/2021 18:14:34 - INFO - __main__ - Step 28371: {'lr': 0.0004618462542822214, 'samples': 5447232, 'steps': 28370, 'loss/train': 1.5488499402999878} 08/30/2021 18:14:34 - INFO - __main__ - Step 28372: {'lr': 0.0004618434364650158, 'samples': 5447424, 'steps': 28371, 'loss/train': 1.957581639289856} 08/30/2021 18:14:36 - INFO - __main__ - Step 28373: {'lr': 0.00046184061855235683, 'samples': 5447616, 'steps': 28372, 'loss/train': 1.416306495666504} 08/30/2021 18:14:36 - INFO - __main__ - Step 28374: {'lr': 0.00046183780054424574, 'samples': 5447808, 'steps': 28373, 'loss/train': 1.3398233652114868} 08/30/2021 18:14:36 - INFO - __main__ - Step 28375: {'lr': 0.00046183498244068376, 'samples': 5448000, 'steps': 28374, 'loss/train': 1.2787036895751953} 08/30/2021 18:14:37 - INFO - __main__ - Step 28376: {'lr': 0.00046183216424167226, 'samples': 5448192, 'steps': 28375, 'loss/train': 1.8297516107559204} 08/30/2021 18:14:37 - INFO - __main__ - Step 28377: {'lr': 0.0004618293459472124, 'samples': 5448384, 'steps': 28376, 'loss/train': 1.5445353984832764} 08/30/2021 18:14:39 - INFO - __main__ - Step 28378: {'lr': 0.0004618265275573056, 'samples': 5448576, 'steps': 28377, 'loss/train': 2.1174182891845703} 08/30/2021 18:14:39 - INFO - __main__ - Step 28379: {'lr': 0.00046182370907195294, 'samples': 5448768, 'steps': 28378, 'loss/train': 1.0556801557540894} 08/30/2021 18:14:40 - INFO - __main__ - Step 28380: {'lr': 0.00046182089049115585, 'samples': 5448960, 'steps': 28379, 'loss/train': 4.267399787902832} 08/30/2021 18:14:40 - INFO - __main__ - Step 28381: {'lr': 0.0004618180718149155, 'samples': 5449152, 'steps': 28380, 'loss/train': 1.6334525346755981} 08/30/2021 18:14:40 - INFO - __main__ - Step 28382: {'lr': 0.00046181525304323325, 'samples': 5449344, 'steps': 28381, 'loss/train': 1.448195219039917} 08/30/2021 18:14:42 - INFO - __main__ - Step 28383: {'lr': 0.0004618124341761102, 'samples': 5449536, 'steps': 28382, 'loss/train': 1.6182572841644287} 08/30/2021 18:14:42 - INFO - __main__ - Step 28384: {'lr': 0.0004618096152135478, 'samples': 5449728, 'steps': 28383, 'loss/train': 2.207749366760254} 08/30/2021 18:14:42 - INFO - __main__ - Step 28385: {'lr': 0.00046180679615554735, 'samples': 5449920, 'steps': 28384, 'loss/train': 2.3146650791168213} 08/30/2021 18:14:43 - INFO - __main__ - Step 28386: {'lr': 0.00046180397700210985, 'samples': 5450112, 'steps': 28385, 'loss/train': 1.8278053998947144} 08/30/2021 18:14:43 - INFO - __main__ - Step 28387: {'lr': 0.0004618011577532368, 'samples': 5450304, 'steps': 28386, 'loss/train': 1.7210609912872314} 08/30/2021 18:14:45 - INFO - __main__ - Step 28388: {'lr': 0.0004617983384089295, 'samples': 5450496, 'steps': 28387, 'loss/train': 1.3940378427505493} 08/30/2021 18:14:45 - INFO - __main__ - Step 28389: {'lr': 0.00046179551896918916, 'samples': 5450688, 'steps': 28388, 'loss/train': 0.582719624042511} 08/30/2021 18:14:46 - INFO - __main__ - Step 28390: {'lr': 0.00046179269943401693, 'samples': 5450880, 'steps': 28389, 'loss/train': 2.3339428901672363} 08/30/2021 18:14:46 - INFO - __main__ - Step 28391: {'lr': 0.00046178987980341414, 'samples': 5451072, 'steps': 28390, 'loss/train': 1.3789128065109253} 08/30/2021 18:14:47 - INFO - __main__ - Step 28392: {'lr': 0.00046178706007738227, 'samples': 5451264, 'steps': 28391, 'loss/train': 0.16868636012077332} 08/30/2021 18:14:47 - INFO - __main__ - Step 28393: {'lr': 0.0004617842402559223, 'samples': 5451456, 'steps': 28392, 'loss/train': 0.0908598005771637} 08/30/2021 18:14:48 - INFO - __main__ - Step 28394: {'lr': 0.0004617814203390356, 'samples': 5451648, 'steps': 28393, 'loss/train': 2.0442283153533936} 08/30/2021 18:14:49 - INFO - __main__ - Step 28395: {'lr': 0.0004617786003267235, 'samples': 5451840, 'steps': 28394, 'loss/train': 1.7698763608932495} 08/30/2021 18:14:49 - INFO - __main__ - Step 28396: {'lr': 0.00046177578021898717, 'samples': 5452032, 'steps': 28395, 'loss/train': 0.9512029886245728} 08/30/2021 18:14:50 - INFO - __main__ - Step 28397: {'lr': 0.000461772960015828, 'samples': 5452224, 'steps': 28396, 'loss/train': 1.8937252759933472} 08/30/2021 18:14:50 - INFO - __main__ - Step 28398: {'lr': 0.00046177013971724723, 'samples': 5452416, 'steps': 28397, 'loss/train': 2.0061144828796387} 08/30/2021 18:14:50 - INFO - __main__ - Step 28399: {'lr': 0.00046176731932324604, 'samples': 5452608, 'steps': 28398, 'loss/train': 1.6485087871551514} 08/30/2021 18:14:52 - INFO - __main__ - Step 28400: {'lr': 0.0004617644988338258, 'samples': 5452800, 'steps': 28399, 'loss/train': 1.1261181831359863} 08/30/2021 18:14:53 - INFO - __main__ - Step 28401: {'lr': 0.0004617616782489877, 'samples': 5452992, 'steps': 28400, 'loss/train': 0.9156551957130432} 08/30/2021 18:14:53 - INFO - __main__ - Step 28402: {'lr': 0.00046175885756873314, 'samples': 5453184, 'steps': 28401, 'loss/train': 0.07958393543958664} 08/30/2021 18:14:54 - INFO - __main__ - Step 28403: {'lr': 0.00046175603679306324, 'samples': 5453376, 'steps': 28402, 'loss/train': 1.9514942169189453} 08/30/2021 18:14:54 - INFO - __main__ - Step 28404: {'lr': 0.0004617532159219794, 'samples': 5453568, 'steps': 28403, 'loss/train': 1.5115739107131958} 08/30/2021 18:14:55 - INFO - __main__ - Step 28405: {'lr': 0.0004617503949554828, 'samples': 5453760, 'steps': 28404, 'loss/train': 2.2763118743896484} 08/30/2021 18:14:56 - INFO - __main__ - Step 28406: {'lr': 0.0004617475738935747, 'samples': 5453952, 'steps': 28405, 'loss/train': 1.9992116689682007} 08/30/2021 18:14:56 - INFO - __main__ - Step 28407: {'lr': 0.0004617447527362564, 'samples': 5454144, 'steps': 28406, 'loss/train': 1.4851759672164917} 08/30/2021 18:14:57 - INFO - __main__ - Step 28408: {'lr': 0.00046174193148352914, 'samples': 5454336, 'steps': 28407, 'loss/train': 1.3432347774505615} 08/30/2021 18:14:57 - INFO - __main__ - Step 28409: {'lr': 0.00046173911013539437, 'samples': 5454528, 'steps': 28408, 'loss/train': 2.709536075592041} 08/30/2021 18:14:58 - INFO - __main__ - Step 28410: {'lr': 0.0004617362886918531, 'samples': 5454720, 'steps': 28409, 'loss/train': 1.2044527530670166} 08/30/2021 18:14:59 - INFO - __main__ - Step 28411: {'lr': 0.0004617334671529069, 'samples': 5454912, 'steps': 28410, 'loss/train': 2.171020030975342} 08/30/2021 18:14:59 - INFO - __main__ - Step 28412: {'lr': 0.0004617306455185567, 'samples': 5455104, 'steps': 28411, 'loss/train': 1.7233283519744873} 08/30/2021 18:15:00 - INFO - __main__ - Step 28413: {'lr': 0.00046172782378880404, 'samples': 5455296, 'steps': 28412, 'loss/train': 1.5373201370239258} 08/30/2021 18:15:00 - INFO - __main__ - Step 28414: {'lr': 0.00046172500196364996, 'samples': 5455488, 'steps': 28413, 'loss/train': 1.5885015726089478} 08/30/2021 18:15:02 - INFO - __main__ - Step 28415: {'lr': 0.000461722180043096, 'samples': 5455680, 'steps': 28414, 'loss/train': 1.087518572807312} 08/30/2021 18:15:02 - INFO - __main__ - Step 28416: {'lr': 0.0004617193580271433, 'samples': 5455872, 'steps': 28415, 'loss/train': 1.7424510717391968} 08/30/2021 18:15:03 - INFO - __main__ - Step 28417: {'lr': 0.000461716535915793, 'samples': 5456064, 'steps': 28416, 'loss/train': 1.5177549123764038} 08/30/2021 18:15:03 - INFO - __main__ - Step 28418: {'lr': 0.0004617137137090466, 'samples': 5456256, 'steps': 28417, 'loss/train': 1.6655724048614502} 08/30/2021 18:15:03 - INFO - __main__ - Step 28419: {'lr': 0.0004617108914069052, 'samples': 5456448, 'steps': 28418, 'loss/train': 1.6813396215438843} 08/30/2021 18:15:04 - INFO - __main__ - Step 28420: {'lr': 0.0004617080690093701, 'samples': 5456640, 'steps': 28419, 'loss/train': 0.90381920337677} 08/30/2021 18:15:05 - INFO - __main__ - Step 28421: {'lr': 0.00046170524651644276, 'samples': 5456832, 'steps': 28420, 'loss/train': 1.3693146705627441} 08/30/2021 18:15:06 - INFO - __main__ - Step 28422: {'lr': 0.00046170242392812425, 'samples': 5457024, 'steps': 28421, 'loss/train': 1.5474826097488403} 08/30/2021 18:15:06 - INFO - __main__ - Step 28423: {'lr': 0.0004616996012444158, 'samples': 5457216, 'steps': 28422, 'loss/train': 2.1661765575408936} 08/30/2021 18:15:06 - INFO - __main__ - Step 28424: {'lr': 0.00046169677846531884, 'samples': 5457408, 'steps': 28423, 'loss/train': 1.5340081453323364} 08/30/2021 18:15:07 - INFO - __main__ - Step 28425: {'lr': 0.0004616939555908346, 'samples': 5457600, 'steps': 28424, 'loss/train': 1.557504415512085} 08/30/2021 18:15:08 - INFO - __main__ - Step 28426: {'lr': 0.0004616911326209643, 'samples': 5457792, 'steps': 28425, 'loss/train': 2.089592456817627} 08/30/2021 18:15:09 - INFO - __main__ - Step 28427: {'lr': 0.0004616883095557092, 'samples': 5457984, 'steps': 28426, 'loss/train': 1.8241089582443237} 08/30/2021 18:15:09 - INFO - __main__ - Step 28428: {'lr': 0.0004616854863950707, 'samples': 5458176, 'steps': 28427, 'loss/train': 0.5400580167770386} 08/30/2021 18:15:09 - INFO - __main__ - Step 28429: {'lr': 0.00046168266313904995, 'samples': 5458368, 'steps': 28428, 'loss/train': 2.1024491786956787} 08/30/2021 18:15:10 - INFO - __main__ - Step 28430: {'lr': 0.00046167983978764827, 'samples': 5458560, 'steps': 28429, 'loss/train': 1.6214874982833862} 08/30/2021 18:15:11 - INFO - __main__ - Step 28431: {'lr': 0.0004616770163408669, 'samples': 5458752, 'steps': 28430, 'loss/train': 1.847511649131775} 08/30/2021 18:15:12 - INFO - __main__ - Step 28432: {'lr': 0.00046167419279870715, 'samples': 5458944, 'steps': 28431, 'loss/train': 1.8810951709747314} 08/30/2021 18:15:12 - INFO - __main__ - Step 28433: {'lr': 0.00046167136916117025, 'samples': 5459136, 'steps': 28432, 'loss/train': 1.4094552993774414} 08/30/2021 18:15:12 - INFO - __main__ - Step 28434: {'lr': 0.00046166854542825756, 'samples': 5459328, 'steps': 28433, 'loss/train': 1.757566213607788} 08/30/2021 18:15:13 - INFO - __main__ - Step 28435: {'lr': 0.0004616657215999702, 'samples': 5459520, 'steps': 28434, 'loss/train': 1.060879111289978} 08/30/2021 18:15:14 - INFO - __main__ - Step 28436: {'lr': 0.0004616628976763096, 'samples': 5459712, 'steps': 28435, 'loss/train': 1.269731044769287} 08/30/2021 18:15:14 - INFO - __main__ - Step 28437: {'lr': 0.0004616600736572769, 'samples': 5459904, 'steps': 28436, 'loss/train': 1.401597261428833} 08/30/2021 18:15:15 - INFO - __main__ - Step 28438: {'lr': 0.0004616572495428735, 'samples': 5460096, 'steps': 28437, 'loss/train': 1.4698482751846313} 08/30/2021 18:15:15 - INFO - __main__ - Step 28439: {'lr': 0.0004616544253331006, 'samples': 5460288, 'steps': 28438, 'loss/train': 0.9774594902992249} 08/30/2021 18:15:15 - INFO - __main__ - Step 28440: {'lr': 0.00046165160102795943, 'samples': 5460480, 'steps': 28439, 'loss/train': 1.3149068355560303} 08/30/2021 18:15:17 - INFO - __main__ - Step 28441: {'lr': 0.0004616487766274514, 'samples': 5460672, 'steps': 28440, 'loss/train': 1.6768009662628174} 08/30/2021 18:15:18 - INFO - __main__ - Step 28442: {'lr': 0.0004616459521315777, 'samples': 5460864, 'steps': 28441, 'loss/train': 1.2131375074386597} 08/30/2021 18:15:18 - INFO - __main__ - Step 28443: {'lr': 0.0004616431275403395, 'samples': 5461056, 'steps': 28442, 'loss/train': 1.0739957094192505} 08/30/2021 18:15:18 - INFO - __main__ - Step 28444: {'lr': 0.0004616403028537382, 'samples': 5461248, 'steps': 28443, 'loss/train': 3.931757926940918} 08/30/2021 18:15:19 - INFO - __main__ - Step 28445: {'lr': 0.0004616374780717751, 'samples': 5461440, 'steps': 28444, 'loss/train': 1.139050841331482} 08/30/2021 18:15:19 - INFO - __main__ - Step 28446: {'lr': 0.0004616346531944514, 'samples': 5461632, 'steps': 28445, 'loss/train': 1.621245265007019} 08/30/2021 18:15:21 - INFO - __main__ - Step 28447: {'lr': 0.00046163182822176835, 'samples': 5461824, 'steps': 28446, 'loss/train': 1.4106972217559814} 08/30/2021 18:15:21 - INFO - __main__ - Step 28448: {'lr': 0.0004616290031537273, 'samples': 5462016, 'steps': 28447, 'loss/train': 0.29630017280578613} 08/30/2021 18:15:21 - INFO - __main__ - Step 28449: {'lr': 0.0004616261779903295, 'samples': 5462208, 'steps': 28448, 'loss/train': 1.1605528593063354} 08/30/2021 18:15:22 - INFO - __main__ - Step 28450: {'lr': 0.0004616233527315762, 'samples': 5462400, 'steps': 28449, 'loss/train': 1.7201234102249146} 08/30/2021 18:15:22 - INFO - __main__ - Step 28451: {'lr': 0.0004616205273774686, 'samples': 5462592, 'steps': 28450, 'loss/train': 1.6046078205108643} 08/30/2021 18:15:22 - INFO - __main__ - Step 28452: {'lr': 0.00046161770192800817, 'samples': 5462784, 'steps': 28451, 'loss/train': 1.3255046606063843} 08/30/2021 18:15:24 - INFO - __main__ - Step 28453: {'lr': 0.000461614876383196, 'samples': 5462976, 'steps': 28452, 'loss/train': 1.2627551555633545} 08/30/2021 18:15:25 - INFO - __main__ - Step 28454: {'lr': 0.0004616120507430335, 'samples': 5463168, 'steps': 28453, 'loss/train': 1.7005821466445923} 08/30/2021 18:15:25 - INFO - __main__ - Step 28455: {'lr': 0.00046160922500752176, 'samples': 5463360, 'steps': 28454, 'loss/train': 0.6630153656005859} 08/30/2021 18:15:25 - INFO - __main__ - Step 28456: {'lr': 0.0004616063991766623, 'samples': 5463552, 'steps': 28455, 'loss/train': 1.7326027154922485} 08/30/2021 18:15:26 - INFO - __main__ - Step 28457: {'lr': 0.0004616035732504562, 'samples': 5463744, 'steps': 28456, 'loss/train': 1.629073143005371} 08/30/2021 18:15:27 - INFO - __main__ - Step 28458: {'lr': 0.0004616007472289048, 'samples': 5463936, 'steps': 28457, 'loss/train': 1.4131532907485962} 08/30/2021 18:15:28 - INFO - __main__ - Step 28459: {'lr': 0.00046159792111200937, 'samples': 5464128, 'steps': 28458, 'loss/train': 1.3037713766098022} 08/30/2021 18:15:28 - INFO - __main__ - Step 28460: {'lr': 0.0004615950948997711, 'samples': 5464320, 'steps': 28459, 'loss/train': 1.4961373805999756} 08/30/2021 18:15:29 - INFO - __main__ - Step 28461: {'lr': 0.0004615922685921915, 'samples': 5464512, 'steps': 28460, 'loss/train': 1.4120932817459106} 08/30/2021 18:15:29 - INFO - __main__ - Step 28462: {'lr': 0.0004615894421892716, 'samples': 5464704, 'steps': 28461, 'loss/train': 1.5001535415649414} 08/30/2021 18:15:31 - INFO - __main__ - Step 28463: {'lr': 0.0004615866156910128, 'samples': 5464896, 'steps': 28462, 'loss/train': 1.1565515995025635} 08/30/2021 18:15:31 - INFO - __main__ - Step 28464: {'lr': 0.00046158378909741626, 'samples': 5465088, 'steps': 28463, 'loss/train': 2.036403179168701} 08/30/2021 18:15:31 - INFO - __main__ - Step 28465: {'lr': 0.00046158096240848343, 'samples': 5465280, 'steps': 28464, 'loss/train': 1.703019618988037} 08/30/2021 18:15:32 - INFO - __main__ - Step 28466: {'lr': 0.00046157813562421545, 'samples': 5465472, 'steps': 28465, 'loss/train': 1.6842516660690308} 08/30/2021 18:15:32 - INFO - __main__ - Step 28467: {'lr': 0.0004615753087446136, 'samples': 5465664, 'steps': 28466, 'loss/train': 1.8737887144088745} 08/30/2021 18:15:34 - INFO - __main__ - Step 28468: {'lr': 0.00046157248176967915, 'samples': 5465856, 'steps': 28467, 'loss/train': 1.8135250806808472} 08/30/2021 18:15:34 - INFO - __main__ - Step 28469: {'lr': 0.0004615696546994135, 'samples': 5466048, 'steps': 28468, 'loss/train': 1.4749095439910889} 08/30/2021 18:15:35 - INFO - __main__ - Step 28470: {'lr': 0.00046156682753381774, 'samples': 5466240, 'steps': 28469, 'loss/train': 1.223831295967102} 08/30/2021 18:15:35 - INFO - __main__ - Step 28471: {'lr': 0.0004615640002728932, 'samples': 5466432, 'steps': 28470, 'loss/train': 1.4210262298583984} 08/30/2021 18:15:35 - INFO - __main__ - Step 28472: {'lr': 0.00046156117291664133, 'samples': 5466624, 'steps': 28471, 'loss/train': 1.3265413045883179} 08/30/2021 18:15:36 - INFO - __main__ - Step 28473: {'lr': 0.0004615583454650632, 'samples': 5466816, 'steps': 28472, 'loss/train': 1.6798558235168457} 08/30/2021 18:15:37 - INFO - __main__ - Step 28474: {'lr': 0.00046155551791816007, 'samples': 5467008, 'steps': 28473, 'loss/train': 0.0545647032558918} 08/30/2021 18:15:38 - INFO - __main__ - Step 28475: {'lr': 0.00046155269027593337, 'samples': 5467200, 'steps': 28474, 'loss/train': 1.4392448663711548} 08/30/2021 18:15:38 - INFO - __main__ - Step 28476: {'lr': 0.00046154986253838426, 'samples': 5467392, 'steps': 28475, 'loss/train': 1.3955795764923096} 08/30/2021 18:15:38 - INFO - __main__ - Step 28477: {'lr': 0.00046154703470551405, 'samples': 5467584, 'steps': 28476, 'loss/train': 1.797864556312561} 08/30/2021 18:15:39 - INFO - __main__ - Step 28478: {'lr': 0.000461544206777324, 'samples': 5467776, 'steps': 28477, 'loss/train': 0.6715664267539978} 08/30/2021 18:15:40 - INFO - __main__ - Step 28479: {'lr': 0.00046154137875381547, 'samples': 5467968, 'steps': 28478, 'loss/train': 1.7450462579727173} 08/30/2021 18:15:41 - INFO - __main__ - Step 28480: {'lr': 0.00046153855063498964, 'samples': 5468160, 'steps': 28479, 'loss/train': 1.654579758644104} 08/30/2021 18:15:41 - INFO - __main__ - Step 28481: {'lr': 0.00046153572242084776, 'samples': 5468352, 'steps': 28480, 'loss/train': 1.3318246603012085} 08/30/2021 18:15:41 - INFO - __main__ - Step 28482: {'lr': 0.0004615328941113911, 'samples': 5468544, 'steps': 28481, 'loss/train': 1.3417713642120361} 08/30/2021 18:15:42 - INFO - __main__ - Step 28483: {'lr': 0.00046153006570662106, 'samples': 5468736, 'steps': 28482, 'loss/train': 1.5684040784835815} 08/30/2021 18:15:43 - INFO - __main__ - Step 28484: {'lr': 0.0004615272372065388, 'samples': 5468928, 'steps': 28483, 'loss/train': 1.7049928903579712} 08/30/2021 18:15:44 - INFO - __main__ - Step 28485: {'lr': 0.0004615244086111456, 'samples': 5469120, 'steps': 28484, 'loss/train': 1.32969331741333} 08/30/2021 18:15:44 - INFO - __main__ - Step 28486: {'lr': 0.00046152157992044283, 'samples': 5469312, 'steps': 28485, 'loss/train': 1.4608381986618042} 08/30/2021 18:15:44 - INFO - __main__ - Step 28487: {'lr': 0.0004615187511344316, 'samples': 5469504, 'steps': 28486, 'loss/train': 1.3725831508636475} 08/30/2021 18:15:45 - INFO - __main__ - Step 28488: {'lr': 0.00046151592225311347, 'samples': 5469696, 'steps': 28487, 'loss/train': 1.6761726140975952} 08/30/2021 18:15:46 - INFO - __main__ - Step 28489: {'lr': 0.0004615130932764894, 'samples': 5469888, 'steps': 28488, 'loss/train': 1.3599092960357666} 08/30/2021 18:15:46 - INFO - __main__ - Step 28490: {'lr': 0.0004615102642045608, 'samples': 5470080, 'steps': 28489, 'loss/train': 1.5636268854141235} 08/30/2021 18:15:47 - INFO - __main__ - Step 28491: {'lr': 0.00046150743503732897, 'samples': 5470272, 'steps': 28490, 'loss/train': 1.3444204330444336} 08/30/2021 18:15:47 - INFO - __main__ - Step 28492: {'lr': 0.0004615046057747951, 'samples': 5470464, 'steps': 28491, 'loss/train': 1.6677089929580688} 08/30/2021 18:15:48 - INFO - __main__ - Step 28493: {'lr': 0.0004615017764169606, 'samples': 5470656, 'steps': 28492, 'loss/train': 1.0866971015930176} 08/30/2021 18:15:49 - INFO - __main__ - Step 28494: {'lr': 0.00046149894696382655, 'samples': 5470848, 'steps': 28493, 'loss/train': 1.7957838773727417} 08/30/2021 18:15:50 - INFO - __main__ - Step 28495: {'lr': 0.00046149611741539445, 'samples': 5471040, 'steps': 28494, 'loss/train': 1.851419448852539} 08/30/2021 18:15:50 - INFO - __main__ - Step 28496: {'lr': 0.00046149328777166543, 'samples': 5471232, 'steps': 28495, 'loss/train': 1.5098599195480347} 08/30/2021 18:15:50 - INFO - __main__ - Step 28497: {'lr': 0.0004614904580326408, 'samples': 5471424, 'steps': 28496, 'loss/train': 1.1656744480133057} 08/30/2021 18:15:51 - INFO - __main__ - Step 28498: {'lr': 0.0004614876281983218, 'samples': 5471616, 'steps': 28497, 'loss/train': 2.112806797027588} 08/30/2021 18:15:51 - INFO - __main__ - Step 28499: {'lr': 0.0004614847982687097, 'samples': 5471808, 'steps': 28498, 'loss/train': 0.9596072435379028} 08/30/2021 18:15:53 - INFO - __main__ - Step 28500: {'lr': 0.0004614819682438059, 'samples': 5472000, 'steps': 28499, 'loss/train': 1.330038070678711} 08/30/2021 18:15:53 - INFO - __main__ - Step 28501: {'lr': 0.00046147913812361155, 'samples': 5472192, 'steps': 28500, 'loss/train': 0.7673311233520508} 08/30/2021 18:15:53 - INFO - __main__ - Step 28502: {'lr': 0.000461476307908128, 'samples': 5472384, 'steps': 28501, 'loss/train': 0.8263532519340515} 08/30/2021 18:15:54 - INFO - __main__ - Step 28503: {'lr': 0.00046147347759735647, 'samples': 5472576, 'steps': 28502, 'loss/train': 1.9476468563079834} 08/30/2021 18:15:54 - INFO - __main__ - Step 28504: {'lr': 0.00046147064719129823, 'samples': 5472768, 'steps': 28503, 'loss/train': 1.6908648014068604} 08/30/2021 18:15:56 - INFO - __main__ - Step 28505: {'lr': 0.00046146781668995456, 'samples': 5472960, 'steps': 28504, 'loss/train': 1.075881004333496} 08/30/2021 18:15:57 - INFO - __main__ - Step 28506: {'lr': 0.0004614649860933268, 'samples': 5473152, 'steps': 28505, 'loss/train': 1.9262429475784302} 08/30/2021 18:15:57 - INFO - __main__ - Step 28507: {'lr': 0.0004614621554014162, 'samples': 5473344, 'steps': 28506, 'loss/train': 1.8057692050933838} 08/30/2021 18:15:58 - INFO - __main__ - Step 28508: {'lr': 0.00046145932461422396, 'samples': 5473536, 'steps': 28507, 'loss/train': 1.4998582601547241} 08/30/2021 18:15:58 - INFO - __main__ - Step 28509: {'lr': 0.00046145649373175145, 'samples': 5473728, 'steps': 28508, 'loss/train': 1.477571725845337} 08/30/2021 18:15:58 - INFO - __main__ - Step 28510: {'lr': 0.0004614536627539999, 'samples': 5473920, 'steps': 28509, 'loss/train': 1.7403695583343506} 08/30/2021 18:16:00 - INFO - __main__ - Step 28511: {'lr': 0.0004614508316809706, 'samples': 5474112, 'steps': 28510, 'loss/train': 2.421569347381592} 08/30/2021 18:16:00 - INFO - __main__ - Step 28512: {'lr': 0.00046144800051266477, 'samples': 5474304, 'steps': 28511, 'loss/train': 1.2638709545135498} 08/30/2021 18:16:01 - INFO - __main__ - Step 28513: {'lr': 0.00046144516924908377, 'samples': 5474496, 'steps': 28512, 'loss/train': 1.592155933380127} 08/30/2021 18:16:01 - INFO - __main__ - Step 28514: {'lr': 0.0004614423378902289, 'samples': 5474688, 'steps': 28513, 'loss/train': 1.9909541606903076} 08/30/2021 18:16:01 - INFO - __main__ - Step 28515: {'lr': 0.0004614395064361013, 'samples': 5474880, 'steps': 28514, 'loss/train': 0.7892037630081177} 08/30/2021 18:16:03 - INFO - __main__ - Step 28516: {'lr': 0.00046143667488670226, 'samples': 5475072, 'steps': 28515, 'loss/train': 1.0137324333190918} 08/30/2021 18:16:04 - INFO - __main__ - Step 28517: {'lr': 0.00046143384324203325, 'samples': 5475264, 'steps': 28516, 'loss/train': 1.8772464990615845} 08/30/2021 18:16:04 - INFO - __main__ - Step 28518: {'lr': 0.00046143101150209533, 'samples': 5475456, 'steps': 28517, 'loss/train': 0.062400247901678085} 08/30/2021 18:16:04 - INFO - __main__ - Step 28519: {'lr': 0.0004614281796668899, 'samples': 5475648, 'steps': 28518, 'loss/train': 1.7559754848480225} 08/30/2021 18:16:05 - INFO - __main__ - Step 28520: {'lr': 0.0004614253477364182, 'samples': 5475840, 'steps': 28519, 'loss/train': 1.6631942987442017} 08/30/2021 18:16:05 - INFO - __main__ - Step 28521: {'lr': 0.0004614225157106815, 'samples': 5476032, 'steps': 28520, 'loss/train': 1.5449906587600708} 08/30/2021 18:16:06 - INFO - __main__ - Step 28522: {'lr': 0.00046141968358968103, 'samples': 5476224, 'steps': 28521, 'loss/train': 2.165684223175049} 08/30/2021 18:16:07 - INFO - __main__ - Step 28523: {'lr': 0.00046141685137341814, 'samples': 5476416, 'steps': 28522, 'loss/train': 1.218667984008789} 08/30/2021 18:16:07 - INFO - __main__ - Step 28524: {'lr': 0.00046141401906189404, 'samples': 5476608, 'steps': 28523, 'loss/train': 1.5562207698822021} 08/30/2021 18:16:07 - INFO - __main__ - Step 28525: {'lr': 0.0004614111866551101, 'samples': 5476800, 'steps': 28524, 'loss/train': 1.8598761558532715} 08/30/2021 18:16:08 - INFO - __main__ - Step 28526: {'lr': 0.0004614083541530675, 'samples': 5476992, 'steps': 28525, 'loss/train': 1.8451690673828125} 08/30/2021 18:16:09 - INFO - __main__ - Step 28527: {'lr': 0.00046140552155576767, 'samples': 5477184, 'steps': 28526, 'loss/train': 1.7072362899780273} 08/30/2021 18:16:10 - INFO - __main__ - Step 28528: {'lr': 0.0004614026888632116, 'samples': 5477376, 'steps': 28527, 'loss/train': 1.3507329225540161} 08/30/2021 18:16:10 - INFO - __main__ - Step 28529: {'lr': 0.00046139985607540087, 'samples': 5477568, 'steps': 28528, 'loss/train': 1.6900264024734497} 08/30/2021 18:16:10 - INFO - __main__ - Step 28530: {'lr': 0.00046139702319233656, 'samples': 5477760, 'steps': 28529, 'loss/train': 1.7837227582931519} 08/30/2021 18:16:11 - INFO - __main__ - Step 28531: {'lr': 0.00046139419021402005, 'samples': 5477952, 'steps': 28530, 'loss/train': 1.7546217441558838} 08/30/2021 18:16:11 - INFO - __main__ - Step 28532: {'lr': 0.00046139135714045253, 'samples': 5478144, 'steps': 28531, 'loss/train': 1.699596881866455} 08/30/2021 18:16:13 - INFO - __main__ - Step 28533: {'lr': 0.00046138852397163547, 'samples': 5478336, 'steps': 28532, 'loss/train': 1.8266007900238037} 08/30/2021 18:16:13 - INFO - __main__ - Step 28534: {'lr': 0.00046138569070756984, 'samples': 5478528, 'steps': 28533, 'loss/train': 0.06760618835687637} 08/30/2021 18:16:14 - INFO - __main__ - Step 28535: {'lr': 0.00046138285734825715, 'samples': 5478720, 'steps': 28534, 'loss/train': 1.34406578540802} 08/30/2021 18:16:14 - INFO - __main__ - Step 28536: {'lr': 0.0004613800238936986, 'samples': 5478912, 'steps': 28535, 'loss/train': 1.4671729803085327} 08/30/2021 18:16:14 - INFO - __main__ - Step 28537: {'lr': 0.0004613771903438955, 'samples': 5479104, 'steps': 28536, 'loss/train': 1.3227908611297607} 08/30/2021 18:16:16 - INFO - __main__ - Step 28538: {'lr': 0.00046137435669884897, 'samples': 5479296, 'steps': 28537, 'loss/train': 1.5423678159713745} 08/30/2021 18:16:17 - INFO - __main__ - Step 28539: {'lr': 0.00046137152295856054, 'samples': 5479488, 'steps': 28538, 'loss/train': 0.17428183555603027} 08/30/2021 18:16:17 - INFO - __main__ - Step 28540: {'lr': 0.0004613686891230313, 'samples': 5479680, 'steps': 28539, 'loss/train': 1.2126985788345337} 08/30/2021 18:16:17 - INFO - __main__ - Step 28541: {'lr': 0.0004613658551922627, 'samples': 5479872, 'steps': 28540, 'loss/train': 2.0219058990478516} 08/30/2021 18:16:18 - INFO - __main__ - Step 28542: {'lr': 0.0004613630211662558, 'samples': 5480064, 'steps': 28541, 'loss/train': 1.5777045488357544} 08/30/2021 18:16:19 - INFO - __main__ - Step 28543: {'lr': 0.00046136018704501203, 'samples': 5480256, 'steps': 28542, 'loss/train': 1.443447232246399} 08/30/2021 18:16:19 - INFO - __main__ - Step 28544: {'lr': 0.00046135735282853263, 'samples': 5480448, 'steps': 28543, 'loss/train': 1.5230565071105957} 08/30/2021 18:16:20 - INFO - __main__ - Step 28545: {'lr': 0.0004613545185168188, 'samples': 5480640, 'steps': 28544, 'loss/train': 1.427353024482727} 08/30/2021 18:16:20 - INFO - __main__ - Step 28546: {'lr': 0.0004613516841098719, 'samples': 5480832, 'steps': 28545, 'loss/train': 2.22821307182312} 08/30/2021 18:16:21 - INFO - __main__ - Step 28547: {'lr': 0.0004613488496076933, 'samples': 5481024, 'steps': 28546, 'loss/train': 1.7149930000305176} 08/30/2021 18:16:22 - INFO - __main__ - Step 28548: {'lr': 0.00046134601501028404, 'samples': 5481216, 'steps': 28547, 'loss/train': 1.4018101692199707} 08/30/2021 18:16:23 - INFO - __main__ - Step 28549: {'lr': 0.0004613431803176456, 'samples': 5481408, 'steps': 28548, 'loss/train': 0.6721023321151733} 08/30/2021 18:16:23 - INFO - __main__ - Step 28550: {'lr': 0.00046134034552977924, 'samples': 5481600, 'steps': 28549, 'loss/train': 1.870675802230835} 08/30/2021 18:16:23 - INFO - __main__ - Step 28551: {'lr': 0.00046133751064668605, 'samples': 5481792, 'steps': 28550, 'loss/train': 1.046642780303955} 08/30/2021 18:16:24 - INFO - __main__ - Step 28552: {'lr': 0.0004613346756683675, 'samples': 5481984, 'steps': 28551, 'loss/train': 1.702518343925476} 08/30/2021 18:16:25 - INFO - __main__ - Step 28553: {'lr': 0.0004613318405948248, 'samples': 5482176, 'steps': 28552, 'loss/train': 1.886941909790039} 08/30/2021 18:16:26 - INFO - __main__ - Step 28554: {'lr': 0.00046132900542605925, 'samples': 5482368, 'steps': 28553, 'loss/train': 1.116611123085022} 08/30/2021 18:16:26 - INFO - __main__ - Step 28555: {'lr': 0.0004613261701620721, 'samples': 5482560, 'steps': 28554, 'loss/train': 1.2434521913528442} 08/30/2021 18:16:26 - INFO - __main__ - Step 28556: {'lr': 0.0004613233348028646, 'samples': 5482752, 'steps': 28555, 'loss/train': 0.9997589588165283} 08/30/2021 18:16:27 - INFO - __main__ - Step 28557: {'lr': 0.0004613204993484381, 'samples': 5482944, 'steps': 28556, 'loss/train': 1.574049472808838} 08/30/2021 18:16:29 - INFO - __main__ - Step 28558: {'lr': 0.00046131766379879386, 'samples': 5483136, 'steps': 28557, 'loss/train': 1.684670329093933} 08/30/2021 18:16:29 - INFO - __main__ - Step 28559: {'lr': 0.0004613148281539331, 'samples': 5483328, 'steps': 28558, 'loss/train': 1.2109357118606567} 08/30/2021 18:16:30 - INFO - __main__ - Step 28560: {'lr': 0.00046131199241385726, 'samples': 5483520, 'steps': 28559, 'loss/train': 1.1717592477798462} 08/30/2021 18:16:30 - INFO - __main__ - Step 28561: {'lr': 0.0004613091565785673, 'samples': 5483712, 'steps': 28560, 'loss/train': 1.4759520292282104} 08/30/2021 18:16:30 - INFO - __main__ - Step 28562: {'lr': 0.0004613063206480649, 'samples': 5483904, 'steps': 28561, 'loss/train': 1.250970482826233} 08/30/2021 18:16:31 - INFO - __main__ - Step 28563: {'lr': 0.000461303484622351, 'samples': 5484096, 'steps': 28562, 'loss/train': 1.0326673984527588} 08/30/2021 18:16:32 - INFO - __main__ - Step 28564: {'lr': 0.00046130064850142703, 'samples': 5484288, 'steps': 28563, 'loss/train': 1.2959872484207153} 08/30/2021 18:16:33 - INFO - __main__ - Step 28565: {'lr': 0.0004612978122852942, 'samples': 5484480, 'steps': 28564, 'loss/train': 2.220444440841675} 08/30/2021 18:16:33 - INFO - __main__ - Step 28566: {'lr': 0.000461294975973954, 'samples': 5484672, 'steps': 28565, 'loss/train': 1.4092081785202026} 08/30/2021 18:16:34 - INFO - __main__ - Step 28567: {'lr': 0.0004612921395674074, 'samples': 5484864, 'steps': 28566, 'loss/train': 1.0749324560165405} 08/30/2021 18:16:34 - INFO - __main__ - Step 28568: {'lr': 0.0004612893030656559, 'samples': 5485056, 'steps': 28567, 'loss/train': 0.9329726099967957} 08/30/2021 18:16:36 - INFO - __main__ - Step 28569: {'lr': 0.0004612864664687007, 'samples': 5485248, 'steps': 28568, 'loss/train': 1.4765939712524414} 08/30/2021 18:16:36 - INFO - __main__ - Step 28570: {'lr': 0.0004612836297765429, 'samples': 5485440, 'steps': 28569, 'loss/train': 1.9534573554992676} 08/30/2021 18:16:37 - INFO - __main__ - Step 28571: {'lr': 0.00046128079298918414, 'samples': 5485632, 'steps': 28570, 'loss/train': 0.09738225489854813} 08/30/2021 18:16:37 - INFO - __main__ - Step 28572: {'lr': 0.00046127795610662547, 'samples': 5485824, 'steps': 28571, 'loss/train': 0.056263361126184464} 08/30/2021 18:16:37 - INFO - __main__ - Step 28573: {'lr': 0.0004612751191288682, 'samples': 5486016, 'steps': 28572, 'loss/train': 2.102567434310913} 08/30/2021 18:16:38 - INFO - __main__ - Step 28574: {'lr': 0.00046127228205591366, 'samples': 5486208, 'steps': 28573, 'loss/train': 0.9623347520828247} 08/30/2021 18:16:39 - INFO - __main__ - Step 28575: {'lr': 0.0004612694448877631, 'samples': 5486400, 'steps': 28574, 'loss/train': 0.7900848984718323} 08/30/2021 18:16:40 - INFO - __main__ - Step 28576: {'lr': 0.00046126660762441774, 'samples': 5486592, 'steps': 28575, 'loss/train': 1.0455816984176636} 08/30/2021 18:16:40 - INFO - __main__ - Step 28577: {'lr': 0.00046126377026587897, 'samples': 5486784, 'steps': 28576, 'loss/train': 1.4658417701721191} 08/30/2021 18:16:40 - INFO - __main__ - Step 28578: {'lr': 0.0004612609328121479, 'samples': 5486976, 'steps': 28577, 'loss/train': 0.8452721834182739} 08/30/2021 18:16:41 - INFO - __main__ - Step 28579: {'lr': 0.000461258095263226, 'samples': 5487168, 'steps': 28578, 'loss/train': 1.8922438621520996} 08/30/2021 18:16:43 - INFO - __main__ - Step 28580: {'lr': 0.00046125525761911445, 'samples': 5487360, 'steps': 28579, 'loss/train': 2.147704839706421} 08/30/2021 18:16:43 - INFO - __main__ - Step 28581: {'lr': 0.00046125241987981445, 'samples': 5487552, 'steps': 28580, 'loss/train': 1.194510817527771} 08/30/2021 18:16:44 - INFO - __main__ - Step 28582: {'lr': 0.0004612495820453275, 'samples': 5487744, 'steps': 28581, 'loss/train': 1.61212956905365} 08/30/2021 18:16:44 - INFO - __main__ - Step 28583: {'lr': 0.0004612467441156547, 'samples': 5487936, 'steps': 28582, 'loss/train': 1.9254000186920166} 08/30/2021 18:16:44 - INFO - __main__ - Step 28584: {'lr': 0.00046124390609079735, 'samples': 5488128, 'steps': 28583, 'loss/train': 1.859422206878662} 08/30/2021 18:16:45 - INFO - __main__ - Step 28585: {'lr': 0.00046124106797075683, 'samples': 5488320, 'steps': 28584, 'loss/train': 1.4304039478302002} 08/30/2021 18:16:46 - INFO - __main__ - Step 28586: {'lr': 0.00046123822975553425, 'samples': 5488512, 'steps': 28585, 'loss/train': 0.14914561808109283} 08/30/2021 18:16:47 - INFO - __main__ - Step 28587: {'lr': 0.00046123539144513103, 'samples': 5488704, 'steps': 28586, 'loss/train': 1.3258082866668701} 08/30/2021 18:16:47 - INFO - __main__ - Step 28588: {'lr': 0.00046123255303954835, 'samples': 5488896, 'steps': 28587, 'loss/train': 1.047844409942627} 08/30/2021 18:16:47 - INFO - __main__ - Step 28589: {'lr': 0.0004612297145387876, 'samples': 5489088, 'steps': 28588, 'loss/train': 1.5251235961914062} 08/30/2021 18:16:48 - INFO - __main__ - Step 28590: {'lr': 0.00046122687594285, 'samples': 5489280, 'steps': 28589, 'loss/train': 1.2259701490402222} 08/30/2021 18:16:49 - INFO - __main__ - Step 28591: {'lr': 0.0004612240372517368, 'samples': 5489472, 'steps': 28590, 'loss/train': 1.267090916633606} 08/30/2021 18:16:50 - INFO - __main__ - Step 28592: {'lr': 0.00046122119846544936, 'samples': 5489664, 'steps': 28591, 'loss/train': 1.0689455270767212} 08/30/2021 18:16:50 - INFO - __main__ - Step 28593: {'lr': 0.00046121835958398883, 'samples': 5489856, 'steps': 28592, 'loss/train': 1.6659600734710693} 08/30/2021 18:16:50 - INFO - __main__ - Step 28594: {'lr': 0.0004612155206073566, 'samples': 5490048, 'steps': 28593, 'loss/train': 1.393333911895752} 08/30/2021 18:16:51 - INFO - __main__ - Step 28595: {'lr': 0.000461212681535554, 'samples': 5490240, 'steps': 28594, 'loss/train': 1.847856879234314} 08/30/2021 18:16:51 - INFO - __main__ - Step 28596: {'lr': 0.0004612098423685821, 'samples': 5490432, 'steps': 28595, 'loss/train': 1.8090723752975464} 08/30/2021 18:16:53 - INFO - __main__ - Step 28597: {'lr': 0.0004612070031064424, 'samples': 5490624, 'steps': 28596, 'loss/train': 1.2842819690704346} 08/30/2021 18:16:54 - INFO - __main__ - Step 28598: {'lr': 0.000461204163749136, 'samples': 5490816, 'steps': 28597, 'loss/train': 1.440927505493164} 08/30/2021 18:16:54 - INFO - __main__ - Step 28599: {'lr': 0.0004612013242966643, 'samples': 5491008, 'steps': 28598, 'loss/train': 1.4508466720581055} 08/30/2021 18:16:54 - INFO - __main__ - Step 28600: {'lr': 0.0004611984847490285, 'samples': 5491200, 'steps': 28599, 'loss/train': 2.039684534072876} 08/30/2021 18:16:55 - INFO - __main__ - Step 28601: {'lr': 0.00046119564510623, 'samples': 5491392, 'steps': 28600, 'loss/train': 1.1459662914276123} 08/30/2021 18:16:57 - INFO - __main__ - Step 28602: {'lr': 0.00046119280536827, 'samples': 5491584, 'steps': 28601, 'loss/train': 9.737241744995117} 08/30/2021 18:16:57 - INFO - __main__ - Step 28603: {'lr': 0.0004611899655351497, 'samples': 5491776, 'steps': 28602, 'loss/train': 1.809079647064209} 08/30/2021 18:16:57 - INFO - __main__ - Step 28604: {'lr': 0.0004611871256068705, 'samples': 5491968, 'steps': 28603, 'loss/train': 1.655714988708496} 08/30/2021 18:16:58 - INFO - __main__ - Step 28605: {'lr': 0.0004611842855834336, 'samples': 5492160, 'steps': 28604, 'loss/train': 1.823891520500183} 08/30/2021 18:16:58 - INFO - __main__ - Step 28606: {'lr': 0.00046118144546484043, 'samples': 5492352, 'steps': 28605, 'loss/train': 0.7643401026725769} 08/30/2021 18:16:58 - INFO - __main__ - Step 28607: {'lr': 0.0004611786052510921, 'samples': 5492544, 'steps': 28606, 'loss/train': 1.5874062776565552} 08/30/2021 18:17:00 - INFO - __main__ - Step 28608: {'lr': 0.0004611757649421899, 'samples': 5492736, 'steps': 28607, 'loss/train': 1.956817626953125} 08/30/2021 18:17:01 - INFO - __main__ - Step 28609: {'lr': 0.0004611729245381352, 'samples': 5492928, 'steps': 28608, 'loss/train': 1.2808642387390137} 08/30/2021 18:17:01 - INFO - __main__ - Step 28610: {'lr': 0.00046117008403892925, 'samples': 5493120, 'steps': 28609, 'loss/train': 1.8965907096862793} 08/30/2021 18:17:01 - INFO - __main__ - Step 28611: {'lr': 0.0004611672434445733, 'samples': 5493312, 'steps': 28610, 'loss/train': 1.635274052619934} 08/30/2021 18:17:02 - INFO - __main__ - Step 28612: {'lr': 0.0004611644027550687, 'samples': 5493504, 'steps': 28611, 'loss/train': 1.6674134731292725} 08/30/2021 18:17:03 - INFO - __main__ - Step 28613: {'lr': 0.00046116156197041657, 'samples': 5493696, 'steps': 28612, 'loss/train': 1.4661076068878174} 08/30/2021 18:17:04 - INFO - __main__ - Step 28614: {'lr': 0.0004611587210906184, 'samples': 5493888, 'steps': 28613, 'loss/train': 1.6048845052719116} 08/30/2021 18:17:04 - INFO - __main__ - Step 28615: {'lr': 0.0004611558801156753, 'samples': 5494080, 'steps': 28614, 'loss/train': 0.12729088962078094} 08/30/2021 18:17:04 - INFO - __main__ - Step 28616: {'lr': 0.0004611530390455887, 'samples': 5494272, 'steps': 28615, 'loss/train': 1.6169594526290894} 08/30/2021 18:17:05 - INFO - __main__ - Step 28617: {'lr': 0.00046115019788035974, 'samples': 5494464, 'steps': 28616, 'loss/train': 1.4557987451553345} 08/30/2021 18:17:07 - INFO - __main__ - Step 28618: {'lr': 0.00046114735661998975, 'samples': 5494656, 'steps': 28617, 'loss/train': 2.5542166233062744} 08/30/2021 18:17:07 - INFO - __main__ - Step 28619: {'lr': 0.0004611445152644801, 'samples': 5494848, 'steps': 28618, 'loss/train': 0.11091788113117218} 08/30/2021 18:17:08 - INFO - __main__ - Step 28620: {'lr': 0.00046114167381383186, 'samples': 5495040, 'steps': 28619, 'loss/train': 1.2085102796554565} 08/30/2021 18:17:08 - INFO - __main__ - Step 28621: {'lr': 0.0004611388322680465, 'samples': 5495232, 'steps': 28620, 'loss/train': 1.140795111656189} 08/30/2021 18:17:08 - INFO - __main__ - Step 28622: {'lr': 0.0004611359906271253, 'samples': 5495424, 'steps': 28621, 'loss/train': 1.7540414333343506} 08/30/2021 18:17:10 - INFO - __main__ - Step 28623: {'lr': 0.0004611331488910694, 'samples': 5495616, 'steps': 28622, 'loss/train': 1.9007771015167236} 08/30/2021 18:17:10 - INFO - __main__ - Step 28624: {'lr': 0.00046113030705988026, 'samples': 5495808, 'steps': 28623, 'loss/train': 1.7109884023666382} 08/30/2021 18:17:11 - INFO - __main__ - Step 28625: {'lr': 0.000461127465133559, 'samples': 5496000, 'steps': 28624, 'loss/train': 1.7091494798660278} 08/30/2021 18:17:11 - INFO - __main__ - Step 28626: {'lr': 0.0004611246231121069, 'samples': 5496192, 'steps': 28625, 'loss/train': 1.8191943168640137} 08/30/2021 18:17:12 - INFO - __main__ - Step 28627: {'lr': 0.00046112178099552535, 'samples': 5496384, 'steps': 28626, 'loss/train': 1.2781901359558105} 08/30/2021 18:17:13 - INFO - __main__ - Step 28628: {'lr': 0.0004611189387838156, 'samples': 5496576, 'steps': 28627, 'loss/train': 0.9486587047576904} 08/30/2021 18:17:13 - INFO - __main__ - Step 28629: {'lr': 0.00046111609647697893, 'samples': 5496768, 'steps': 28628, 'loss/train': 0.8507620692253113} 08/30/2021 18:17:14 - INFO - __main__ - Step 28630: {'lr': 0.0004611132540750166, 'samples': 5496960, 'steps': 28629, 'loss/train': 2.0000696182250977} 08/30/2021 18:17:14 - INFO - __main__ - Step 28631: {'lr': 0.00046111041157792987, 'samples': 5497152, 'steps': 28630, 'loss/train': 1.7961006164550781} 08/30/2021 18:17:14 - INFO - __main__ - Step 28632: {'lr': 0.00046110756898572, 'samples': 5497344, 'steps': 28631, 'loss/train': 1.5291951894760132} 08/30/2021 18:17:15 - INFO - __main__ - Step 28633: {'lr': 0.0004611047262983884, 'samples': 5497536, 'steps': 28632, 'loss/train': 1.3961063623428345} 08/30/2021 18:17:16 - INFO - __main__ - Step 28634: {'lr': 0.00046110188351593625, 'samples': 5497728, 'steps': 28633, 'loss/train': 1.6091190576553345} 08/30/2021 18:17:17 - INFO - __main__ - Step 28635: {'lr': 0.0004610990406383648, 'samples': 5497920, 'steps': 28634, 'loss/train': 0.5210306644439697} 08/30/2021 18:17:17 - INFO - __main__ - Step 28636: {'lr': 0.00046109619766567547, 'samples': 5498112, 'steps': 28635, 'loss/train': 1.5592787265777588} 08/30/2021 18:17:18 - INFO - __main__ - Step 28637: {'lr': 0.0004610933545978694, 'samples': 5498304, 'steps': 28636, 'loss/train': 0.9747006297111511} 08/30/2021 18:17:18 - INFO - __main__ - Step 28638: {'lr': 0.0004610905114349478, 'samples': 5498496, 'steps': 28637, 'loss/train': 1.6787627935409546} 08/30/2021 18:17:19 - INFO - __main__ - Step 28639: {'lr': 0.0004610876681769123, 'samples': 5498688, 'steps': 28638, 'loss/train': 1.808143973350525} 08/30/2021 18:17:20 - INFO - __main__ - Step 28640: {'lr': 0.0004610848248237638, 'samples': 5498880, 'steps': 28639, 'loss/train': 1.4617542028427124} 08/30/2021 18:17:20 - INFO - __main__ - Step 28641: {'lr': 0.00046108198137550377, 'samples': 5499072, 'steps': 28640, 'loss/train': 1.4664337635040283} 08/30/2021 18:17:21 - INFO - __main__ - Step 28642: {'lr': 0.0004610791378321335, 'samples': 5499264, 'steps': 28641, 'loss/train': 1.9164260625839233} 08/30/2021 18:17:21 - INFO - __main__ - Step 28643: {'lr': 0.0004610762941936542, 'samples': 5499456, 'steps': 28642, 'loss/train': 1.7378405332565308} 08/30/2021 18:17:23 - INFO - __main__ - Step 28644: {'lr': 0.0004610734504600671, 'samples': 5499648, 'steps': 28643, 'loss/train': 1.5796711444854736} 08/30/2021 18:17:23 - INFO - __main__ - Step 28645: {'lr': 0.00046107060663137366, 'samples': 5499840, 'steps': 28644, 'loss/train': 1.4716848134994507} 08/30/2021 18:17:23 - INFO - __main__ - Step 28646: {'lr': 0.00046106776270757506, 'samples': 5500032, 'steps': 28645, 'loss/train': 1.6572840213775635} 08/30/2021 18:17:24 - INFO - __main__ - Step 28647: {'lr': 0.0004610649186886725, 'samples': 5500224, 'steps': 28646, 'loss/train': 1.657213568687439} 08/30/2021 18:17:24 - INFO - __main__ - Step 28648: {'lr': 0.00046106207457466744, 'samples': 5500416, 'steps': 28647, 'loss/train': 1.7196182012557983} 08/30/2021 18:17:26 - INFO - __main__ - Step 28649: {'lr': 0.0004610592303655611, 'samples': 5500608, 'steps': 28648, 'loss/train': 1.4266602993011475} 08/30/2021 18:17:26 - INFO - __main__ - Step 28650: {'lr': 0.0004610563860613546, 'samples': 5500800, 'steps': 28649, 'loss/train': 2.1116340160369873} 08/30/2021 18:17:27 - INFO - __main__ - Step 28651: {'lr': 0.00046105354166204937, 'samples': 5500992, 'steps': 28650, 'loss/train': 1.671355962753296} 08/30/2021 18:17:27 - INFO - __main__ - Step 28652: {'lr': 0.00046105069716764676, 'samples': 5501184, 'steps': 28651, 'loss/train': 0.30662935972213745} 08/30/2021 18:17:27 - INFO - __main__ - Step 28653: {'lr': 0.00046104785257814786, 'samples': 5501376, 'steps': 28652, 'loss/train': 1.6948570013046265} 08/30/2021 18:17:28 - INFO - __main__ - Step 28654: {'lr': 0.0004610450078935541, 'samples': 5501568, 'steps': 28653, 'loss/train': 1.4901260137557983} 08/30/2021 18:17:29 - INFO - __main__ - Step 28655: {'lr': 0.00046104216311386676, 'samples': 5501760, 'steps': 28654, 'loss/train': 1.6524717807769775} 08/30/2021 18:17:30 - INFO - __main__ - Step 28656: {'lr': 0.000461039318239087, 'samples': 5501952, 'steps': 28655, 'loss/train': 1.4687788486480713} 08/30/2021 18:17:30 - INFO - __main__ - Step 28657: {'lr': 0.00046103647326921625, 'samples': 5502144, 'steps': 28656, 'loss/train': 1.4570131301879883} 08/30/2021 18:17:30 - INFO - __main__ - Step 28658: {'lr': 0.00046103362820425567, 'samples': 5502336, 'steps': 28657, 'loss/train': 0.17846554517745972} 08/30/2021 18:17:31 - INFO - __main__ - Step 28659: {'lr': 0.00046103078304420665, 'samples': 5502528, 'steps': 28658, 'loss/train': 1.890275239944458} 08/30/2021 18:17:32 - INFO - __main__ - Step 28660: {'lr': 0.0004610279377890704, 'samples': 5502720, 'steps': 28659, 'loss/train': 1.4584637880325317} 08/30/2021 18:17:33 - INFO - __main__ - Step 28661: {'lr': 0.00046102509243884813, 'samples': 5502912, 'steps': 28660, 'loss/train': 1.3846909999847412} 08/30/2021 18:17:33 - INFO - __main__ - Step 28662: {'lr': 0.0004610222469935413, 'samples': 5503104, 'steps': 28661, 'loss/train': 1.1878535747528076} 08/30/2021 18:17:33 - INFO - __main__ - Step 28663: {'lr': 0.000461019401453151, 'samples': 5503296, 'steps': 28662, 'loss/train': 1.9918683767318726} 08/30/2021 18:17:34 - INFO - __main__ - Step 28664: {'lr': 0.00046101655581767874, 'samples': 5503488, 'steps': 28663, 'loss/train': 1.6148306131362915} 08/30/2021 18:17:35 - INFO - __main__ - Step 28665: {'lr': 0.0004610137100871257, 'samples': 5503680, 'steps': 28664, 'loss/train': 2.0255563259124756} 08/30/2021 18:17:36 - INFO - __main__ - Step 28666: {'lr': 0.00046101086426149297, 'samples': 5503872, 'steps': 28665, 'loss/train': 1.5599926710128784} 08/30/2021 18:17:36 - INFO - __main__ - Step 28667: {'lr': 0.0004610080183407821, 'samples': 5504064, 'steps': 28666, 'loss/train': 1.6037590503692627} 08/30/2021 18:17:36 - INFO - __main__ - Step 28668: {'lr': 0.0004610051723249943, 'samples': 5504256, 'steps': 28667, 'loss/train': 1.7684967517852783} 08/30/2021 18:17:37 - INFO - __main__ - Step 28669: {'lr': 0.0004610023262141308, 'samples': 5504448, 'steps': 28668, 'loss/train': 1.2390328645706177} 08/30/2021 18:17:39 - INFO - __main__ - Step 28670: {'lr': 0.00046099948000819294, 'samples': 5504640, 'steps': 28669, 'loss/train': 0.09077593684196472} 08/30/2021 18:17:40 - INFO - __main__ - Step 28671: {'lr': 0.0004609966337071819, 'samples': 5504832, 'steps': 28670, 'loss/train': 1.1359988451004028} 08/30/2021 18:17:40 - INFO - __main__ - Step 28672: {'lr': 0.00046099378731109906, 'samples': 5505024, 'steps': 28671, 'loss/train': 0.1055753082036972} 08/30/2021 18:17:40 - INFO - __main__ - Step 28673: {'lr': 0.00046099094081994565, 'samples': 5505216, 'steps': 28672, 'loss/train': 1.326877474784851} 08/30/2021 18:17:41 - INFO - __main__ - Step 28674: {'lr': 0.000460988094233723, 'samples': 5505408, 'steps': 28673, 'loss/train': 1.7359426021575928} 08/30/2021 18:17:42 - INFO - __main__ - Step 28675: {'lr': 0.00046098524755243246, 'samples': 5505600, 'steps': 28674, 'loss/train': 2.0015597343444824} 08/30/2021 18:17:43 - INFO - __main__ - Step 28676: {'lr': 0.0004609824007760751, 'samples': 5505792, 'steps': 28675, 'loss/train': 1.6945456266403198} 08/30/2021 18:17:43 - INFO - __main__ - Step 28677: {'lr': 0.0004609795539046524, 'samples': 5505984, 'steps': 28676, 'loss/train': 1.8516099452972412} 08/30/2021 18:17:43 - INFO - __main__ - Step 28678: {'lr': 0.0004609767069381655, 'samples': 5506176, 'steps': 28677, 'loss/train': 0.09904380142688751} 08/30/2021 18:17:44 - INFO - __main__ - Step 28679: {'lr': 0.00046097385987661576, 'samples': 5506368, 'steps': 28678, 'loss/train': 1.4202141761779785} 08/30/2021 18:17:46 - INFO - __main__ - Step 28680: {'lr': 0.00046097101272000454, 'samples': 5506560, 'steps': 28679, 'loss/train': 1.6175774335861206} 08/30/2021 18:17:46 - INFO - __main__ - Step 28681: {'lr': 0.0004609681654683329, 'samples': 5506752, 'steps': 28680, 'loss/train': 0.10689815133810043} 08/30/2021 18:17:46 - INFO - __main__ - Step 28682: {'lr': 0.0004609653181216024, 'samples': 5506944, 'steps': 28681, 'loss/train': 1.893286108970642} 08/30/2021 18:17:47 - INFO - __main__ - Step 28683: {'lr': 0.0004609624706798141, 'samples': 5507136, 'steps': 28682, 'loss/train': 1.6242172718048096} 08/30/2021 18:17:47 - INFO - __main__ - Step 28684: {'lr': 0.00046095962314296934, 'samples': 5507328, 'steps': 28683, 'loss/train': 1.661780834197998} 08/30/2021 18:17:49 - INFO - __main__ - Step 28685: {'lr': 0.00046095677551106953, 'samples': 5507520, 'steps': 28684, 'loss/train': 1.8052581548690796} 08/30/2021 18:17:49 - INFO - __main__ - Step 28686: {'lr': 0.00046095392778411576, 'samples': 5507712, 'steps': 28685, 'loss/train': 1.7522753477096558} 08/30/2021 18:17:49 - INFO - __main__ - Step 28687: {'lr': 0.0004609510799621095, 'samples': 5507904, 'steps': 28686, 'loss/train': 0.726565420627594} 08/30/2021 18:17:50 - INFO - __main__ - Step 28688: {'lr': 0.0004609482320450519, 'samples': 5508096, 'steps': 28687, 'loss/train': 1.686182975769043} 08/30/2021 18:17:50 - INFO - __main__ - Step 28689: {'lr': 0.00046094538403294416, 'samples': 5508288, 'steps': 28688, 'loss/train': 2.193859100341797} 08/30/2021 18:17:51 - INFO - __main__ - Step 28690: {'lr': 0.00046094253592578784, 'samples': 5508480, 'steps': 28689, 'loss/train': 2.0816071033477783} 08/30/2021 18:17:52 - INFO - __main__ - Step 28691: {'lr': 0.000460939687723584, 'samples': 5508672, 'steps': 28690, 'loss/train': 1.7358242273330688} 08/30/2021 18:17:52 - INFO - __main__ - Step 28692: {'lr': 0.000460936839426334, 'samples': 5508864, 'steps': 28691, 'loss/train': 1.5767308473587036} 08/30/2021 18:17:53 - INFO - __main__ - Step 28693: {'lr': 0.00046093399103403913, 'samples': 5509056, 'steps': 28692, 'loss/train': 1.9537839889526367} 08/30/2021 18:17:53 - INFO - __main__ - Step 28694: {'lr': 0.00046093114254670066, 'samples': 5509248, 'steps': 28693, 'loss/train': 0.5270798206329346} 08/30/2021 18:17:55 - INFO - __main__ - Step 28695: {'lr': 0.0004609282939643199, 'samples': 5509440, 'steps': 28694, 'loss/train': 1.5301392078399658} 08/30/2021 18:17:55 - INFO - __main__ - Step 28696: {'lr': 0.00046092544528689806, 'samples': 5509632, 'steps': 28695, 'loss/train': 1.502647876739502} 08/30/2021 18:17:55 - INFO - __main__ - Step 28697: {'lr': 0.0004609225965144365, 'samples': 5509824, 'steps': 28696, 'loss/train': 1.330797791481018} 08/30/2021 18:17:56 - INFO - __main__ - Step 28698: {'lr': 0.00046091974764693645, 'samples': 5510016, 'steps': 28697, 'loss/train': 1.330105185508728} 08/30/2021 18:17:56 - INFO - __main__ - Step 28699: {'lr': 0.0004609168986843992, 'samples': 5510208, 'steps': 28698, 'loss/train': 1.7887258529663086} 08/30/2021 18:17:56 - INFO - __main__ - Step 28700: {'lr': 0.000460914049626826, 'samples': 5510400, 'steps': 28699, 'loss/train': 2.4512386322021484} 08/30/2021 18:17:58 - INFO - __main__ - Step 28701: {'lr': 0.0004609112004742183, 'samples': 5510592, 'steps': 28700, 'loss/train': 1.8095072507858276} 08/30/2021 18:17:59 - INFO - __main__ - Step 28702: {'lr': 0.0004609083512265773, 'samples': 5510784, 'steps': 28701, 'loss/train': 1.917091727256775} 08/30/2021 18:17:59 - INFO - __main__ - Step 28703: {'lr': 0.0004609055018839041, 'samples': 5510976, 'steps': 28702, 'loss/train': 1.2911368608474731} 08/30/2021 18:17:59 - INFO - __main__ - Step 28704: {'lr': 0.0004609026524462002, 'samples': 5511168, 'steps': 28703, 'loss/train': 0.9765636324882507} 08/30/2021 18:18:00 - INFO - __main__ - Step 28705: {'lr': 0.00046089980291346685, 'samples': 5511360, 'steps': 28704, 'loss/train': 1.4764583110809326} 08/30/2021 18:18:00 - INFO - __main__ - Step 28706: {'lr': 0.00046089695328570523, 'samples': 5511552, 'steps': 28705, 'loss/train': 1.5844409465789795} 08/30/2021 18:18:02 - INFO - __main__ - Step 28707: {'lr': 0.0004608941035629168, 'samples': 5511744, 'steps': 28706, 'loss/train': 1.1635280847549438} 08/30/2021 18:18:02 - INFO - __main__ - Step 28708: {'lr': 0.0004608912537451027, 'samples': 5511936, 'steps': 28707, 'loss/train': 1.0059483051300049} 08/30/2021 18:18:02 - INFO - __main__ - Step 28709: {'lr': 0.0004608884038322642, 'samples': 5512128, 'steps': 28708, 'loss/train': 2.412945032119751} 08/30/2021 18:18:03 - INFO - __main__ - Step 28710: {'lr': 0.00046088555382440275, 'samples': 5512320, 'steps': 28709, 'loss/train': 1.2494611740112305} 08/30/2021 18:18:03 - INFO - __main__ - Step 28711: {'lr': 0.0004608827037215194, 'samples': 5512512, 'steps': 28710, 'loss/train': 1.1306918859481812} 08/30/2021 18:18:04 - INFO - __main__ - Step 28712: {'lr': 0.0004608798535236156, 'samples': 5512704, 'steps': 28711, 'loss/train': 1.6654123067855835} 08/30/2021 18:18:05 - INFO - __main__ - Step 28713: {'lr': 0.0004608770032306926, 'samples': 5512896, 'steps': 28712, 'loss/train': 1.8448811769485474} 08/30/2021 18:18:05 - INFO - __main__ - Step 28714: {'lr': 0.0004608741528427517, 'samples': 5513088, 'steps': 28713, 'loss/train': 1.4382745027542114} 08/30/2021 18:18:06 - INFO - __main__ - Step 28715: {'lr': 0.0004608713023597941, 'samples': 5513280, 'steps': 28714, 'loss/train': 1.543492317199707} 08/30/2021 18:18:06 - INFO - __main__ - Step 28716: {'lr': 0.00046086845178182123, 'samples': 5513472, 'steps': 28715, 'loss/train': 1.132645845413208} 08/30/2021 18:18:08 - INFO - __main__ - Step 28717: {'lr': 0.00046086560110883423, 'samples': 5513664, 'steps': 28716, 'loss/train': 1.647782325744629} 08/30/2021 18:18:08 - INFO - __main__ - Step 28718: {'lr': 0.00046086275034083453, 'samples': 5513856, 'steps': 28717, 'loss/train': 1.545560359954834} 08/30/2021 18:18:09 - INFO - __main__ - Step 28719: {'lr': 0.00046085989947782327, 'samples': 5514048, 'steps': 28718, 'loss/train': 1.9469356536865234} 08/30/2021 18:18:09 - INFO - __main__ - Step 28720: {'lr': 0.00046085704851980174, 'samples': 5514240, 'steps': 28719, 'loss/train': 0.14269833266735077} 08/30/2021 18:18:09 - INFO - __main__ - Step 28721: {'lr': 0.00046085419746677136, 'samples': 5514432, 'steps': 28720, 'loss/train': 1.31236732006073} 08/30/2021 18:18:11 - INFO - __main__ - Step 28722: {'lr': 0.00046085134631873326, 'samples': 5514624, 'steps': 28721, 'loss/train': 1.4599498510360718} 08/30/2021 18:18:11 - INFO - __main__ - Step 28723: {'lr': 0.0004608484950756888, 'samples': 5514816, 'steps': 28722, 'loss/train': 1.5662461519241333} 08/30/2021 18:18:11 - INFO - __main__ - Step 28724: {'lr': 0.0004608456437376393, 'samples': 5515008, 'steps': 28723, 'loss/train': 1.6499756574630737} 08/30/2021 18:18:12 - INFO - __main__ - Step 28725: {'lr': 0.000460842792304586, 'samples': 5515200, 'steps': 28724, 'loss/train': 1.1057729721069336} 08/30/2021 18:18:12 - INFO - __main__ - Step 28726: {'lr': 0.00046083994077653024, 'samples': 5515392, 'steps': 28725, 'loss/train': 1.292879581451416} 08/30/2021 18:18:14 - INFO - __main__ - Step 28727: {'lr': 0.0004608370891534732, 'samples': 5515584, 'steps': 28726, 'loss/train': 1.3703200817108154} 08/30/2021 18:18:15 - INFO - __main__ - Step 28728: {'lr': 0.0004608342374354162, 'samples': 5515776, 'steps': 28727, 'loss/train': 1.7802619934082031} 08/30/2021 18:18:15 - INFO - __main__ - Step 28729: {'lr': 0.0004608313856223606, 'samples': 5515968, 'steps': 28728, 'loss/train': 2.003765106201172} 08/30/2021 18:18:16 - INFO - __main__ - Step 28730: {'lr': 0.00046082853371430754, 'samples': 5516160, 'steps': 28729, 'loss/train': 1.603506088256836} 08/30/2021 18:18:16 - INFO - __main__ - Step 28731: {'lr': 0.0004608256817112585, 'samples': 5516352, 'steps': 28730, 'loss/train': 1.374673843383789} 08/30/2021 18:18:17 - INFO - __main__ - Step 28732: {'lr': 0.00046082282961321466, 'samples': 5516544, 'steps': 28731, 'loss/train': 1.6801224946975708} 08/30/2021 18:18:18 - INFO - __main__ - Step 28733: {'lr': 0.00046081997742017725, 'samples': 5516736, 'steps': 28732, 'loss/train': 1.1425230503082275} 08/30/2021 18:18:18 - INFO - __main__ - Step 28734: {'lr': 0.00046081712513214757, 'samples': 5516928, 'steps': 28733, 'loss/train': 1.9179368019104004} 08/30/2021 18:18:19 - INFO - __main__ - Step 28735: {'lr': 0.0004608142727491271, 'samples': 5517120, 'steps': 28734, 'loss/train': 1.8448516130447388} 08/30/2021 18:18:19 - INFO - __main__ - Step 28736: {'lr': 0.00046081142027111683, 'samples': 5517312, 'steps': 28735, 'loss/train': 1.168526530265808} 08/30/2021 18:18:21 - INFO - __main__ - Step 28737: {'lr': 0.0004608085676981182, 'samples': 5517504, 'steps': 28736, 'loss/train': 1.8542293310165405} 08/30/2021 18:18:21 - INFO - __main__ - Step 28738: {'lr': 0.0004608057150301326, 'samples': 5517696, 'steps': 28737, 'loss/train': 0.9919119477272034} 08/30/2021 18:18:21 - INFO - __main__ - Step 28739: {'lr': 0.00046080286226716106, 'samples': 5517888, 'steps': 28738, 'loss/train': 0.2748536765575409} 08/30/2021 18:18:22 - INFO - __main__ - Step 28740: {'lr': 0.00046080000940920506, 'samples': 5518080, 'steps': 28739, 'loss/train': 1.6069672107696533} 08/30/2021 18:18:22 - INFO - __main__ - Step 28741: {'lr': 0.00046079715645626584, 'samples': 5518272, 'steps': 28740, 'loss/train': 0.7914718389511108} 08/30/2021 18:18:23 - INFO - __main__ - Step 28742: {'lr': 0.00046079430340834467, 'samples': 5518464, 'steps': 28741, 'loss/train': 1.358385443687439} 08/30/2021 18:18:24 - INFO - __main__ - Step 28743: {'lr': 0.00046079145026544277, 'samples': 5518656, 'steps': 28742, 'loss/train': 1.2105307579040527} 08/30/2021 18:18:24 - INFO - __main__ - Step 28744: {'lr': 0.0004607885970275616, 'samples': 5518848, 'steps': 28743, 'loss/train': 1.393981695175171} 08/30/2021 18:18:25 - INFO - __main__ - Step 28745: {'lr': 0.0004607857436947023, 'samples': 5519040, 'steps': 28744, 'loss/train': 1.690173864364624} 08/30/2021 18:18:25 - INFO - __main__ - Step 28746: {'lr': 0.00046078289026686616, 'samples': 5519232, 'steps': 28745, 'loss/train': 1.5842844247817993} 08/30/2021 18:18:25 - INFO - __main__ - Step 28747: {'lr': 0.00046078003674405457, 'samples': 5519424, 'steps': 28746, 'loss/train': 1.2636808156967163} 08/30/2021 18:18:27 - INFO - __main__ - Step 28748: {'lr': 0.0004607771831262687, 'samples': 5519616, 'steps': 28747, 'loss/train': 0.9195443391799927} 08/30/2021 18:18:27 - INFO - __main__ - Step 28749: {'lr': 0.00046077432941350993, 'samples': 5519808, 'steps': 28748, 'loss/train': 1.424353837966919} 08/30/2021 18:18:28 - INFO - __main__ - Step 28750: {'lr': 0.00046077147560577943, 'samples': 5520000, 'steps': 28749, 'loss/train': 1.416340947151184} 08/30/2021 18:18:28 - INFO - __main__ - Step 28751: {'lr': 0.0004607686217030786, 'samples': 5520192, 'steps': 28750, 'loss/train': 1.5812209844589233} 08/30/2021 18:18:28 - INFO - __main__ - Step 28752: {'lr': 0.00046076576770540865, 'samples': 5520384, 'steps': 28751, 'loss/train': 1.2292712926864624} 08/30/2021 18:18:30 - INFO - __main__ - Step 28753: {'lr': 0.00046076291361277097, 'samples': 5520576, 'steps': 28752, 'loss/train': 1.74449622631073} 08/30/2021 18:18:31 - INFO - __main__ - Step 28754: {'lr': 0.00046076005942516666, 'samples': 5520768, 'steps': 28753, 'loss/train': 1.7540959119796753} 08/30/2021 18:18:31 - INFO - __main__ - Step 28755: {'lr': 0.0004607572051425972, 'samples': 5520960, 'steps': 28754, 'loss/train': 1.4322564601898193} 08/30/2021 18:18:32 - INFO - __main__ - Step 28756: {'lr': 0.00046075435076506376, 'samples': 5521152, 'steps': 28755, 'loss/train': 0.1628573089838028} 08/30/2021 18:18:32 - INFO - __main__ - Step 28757: {'lr': 0.0004607514962925677, 'samples': 5521344, 'steps': 28756, 'loss/train': 1.1711376905441284} 08/30/2021 18:18:33 - INFO - __main__ - Step 28758: {'lr': 0.00046074864172511025, 'samples': 5521536, 'steps': 28757, 'loss/train': 0.9528539776802063} 08/30/2021 18:18:34 - INFO - __main__ - Step 28759: {'lr': 0.0004607457870626928, 'samples': 5521728, 'steps': 28758, 'loss/train': 1.6156426668167114} 08/30/2021 18:18:34 - INFO - __main__ - Step 28760: {'lr': 0.0004607429323053164, 'samples': 5521920, 'steps': 28759, 'loss/train': 1.670474648475647} 08/30/2021 18:18:34 - INFO - __main__ - Step 28761: {'lr': 0.0004607400774529825, 'samples': 5522112, 'steps': 28760, 'loss/train': 1.3794561624526978} 08/30/2021 18:18:35 - INFO - __main__ - Step 28762: {'lr': 0.0004607372225056925, 'samples': 5522304, 'steps': 28761, 'loss/train': 1.0120388269424438} 08/30/2021 18:18:36 - INFO - __main__ - Step 28763: {'lr': 0.00046073436746344744, 'samples': 5522496, 'steps': 28762, 'loss/train': 1.1292396783828735} 08/30/2021 18:18:37 - INFO - __main__ - Step 28764: {'lr': 0.0004607315123262488, 'samples': 5522688, 'steps': 28763, 'loss/train': 1.728515625} 08/30/2021 18:18:37 - INFO - __main__ - Step 28765: {'lr': 0.0004607286570940977, 'samples': 5522880, 'steps': 28764, 'loss/train': 1.4552578926086426} 08/30/2021 18:18:37 - INFO - __main__ - Step 28766: {'lr': 0.0004607258017669956, 'samples': 5523072, 'steps': 28765, 'loss/train': 1.4807502031326294} 08/30/2021 18:18:38 - INFO - __main__ - Step 28767: {'lr': 0.0004607229463449437, 'samples': 5523264, 'steps': 28766, 'loss/train': 1.7356168031692505} 08/30/2021 18:18:38 - INFO - __main__ - Step 28768: {'lr': 0.00046072009082794333, 'samples': 5523456, 'steps': 28767, 'loss/train': 1.394574522972107} 08/30/2021 18:18:40 - INFO - __main__ - Step 28769: {'lr': 0.00046071723521599563, 'samples': 5523648, 'steps': 28768, 'loss/train': 1.4062213897705078} 08/30/2021 18:18:40 - INFO - __main__ - Step 28770: {'lr': 0.000460714379509102, 'samples': 5523840, 'steps': 28769, 'loss/train': 1.4895013570785522} 08/30/2021 18:18:40 - INFO - __main__ - Step 28771: {'lr': 0.0004607115237072638, 'samples': 5524032, 'steps': 28770, 'loss/train': 1.6866536140441895} 08/30/2021 18:18:41 - INFO - __main__ - Step 28772: {'lr': 0.00046070866781048225, 'samples': 5524224, 'steps': 28771, 'loss/train': 0.6956020593643188} 08/30/2021 18:18:41 - INFO - __main__ - Step 28773: {'lr': 0.0004607058118187586, 'samples': 5524416, 'steps': 28772, 'loss/train': 1.3922953605651855} 08/30/2021 18:18:43 - INFO - __main__ - Step 28774: {'lr': 0.00046070295573209406, 'samples': 5524608, 'steps': 28773, 'loss/train': 1.3464394807815552} 08/30/2021 18:18:43 - INFO - __main__ - Step 28775: {'lr': 0.00046070009955049017, 'samples': 5524800, 'steps': 28774, 'loss/train': 1.44407057762146} 08/30/2021 18:18:43 - INFO - __main__ - Step 28776: {'lr': 0.000460697243273948, 'samples': 5524992, 'steps': 28775, 'loss/train': 1.6780152320861816} 08/30/2021 18:18:44 - INFO - __main__ - Step 28777: {'lr': 0.0004606943869024689, 'samples': 5525184, 'steps': 28776, 'loss/train': 1.5969003438949585} 08/30/2021 18:18:44 - INFO - __main__ - Step 28778: {'lr': 0.0004606915304360542, 'samples': 5525376, 'steps': 28777, 'loss/train': 2.0217835903167725} 08/30/2021 18:18:46 - INFO - __main__ - Step 28779: {'lr': 0.00046068867387470507, 'samples': 5525568, 'steps': 28778, 'loss/train': 1.3903378248214722} 08/30/2021 18:18:47 - INFO - __main__ - Step 28780: {'lr': 0.00046068581721842294, 'samples': 5525760, 'steps': 28779, 'loss/train': 1.7632614374160767} 08/30/2021 18:18:47 - INFO - __main__ - Step 28781: {'lr': 0.00046068296046720904, 'samples': 5525952, 'steps': 28780, 'loss/train': 1.5530871152877808} 08/30/2021 18:18:48 - INFO - __main__ - Step 28782: {'lr': 0.0004606801036210646, 'samples': 5526144, 'steps': 28781, 'loss/train': 1.5877370834350586} 08/30/2021 18:18:48 - INFO - __main__ - Step 28783: {'lr': 0.000460677246679991, 'samples': 5526336, 'steps': 28782, 'loss/train': 0.5917261242866516} 08/30/2021 18:18:49 - INFO - __main__ - Step 28784: {'lr': 0.00046067438964398944, 'samples': 5526528, 'steps': 28783, 'loss/train': 1.719201683998108} 08/30/2021 18:18:50 - INFO - __main__ - Step 28785: {'lr': 0.00046067153251306127, 'samples': 5526720, 'steps': 28784, 'loss/train': 0.9624534249305725} 08/30/2021 18:18:50 - INFO - __main__ - Step 28786: {'lr': 0.0004606686752872078, 'samples': 5526912, 'steps': 28785, 'loss/train': 1.9532489776611328} 08/30/2021 18:18:50 - INFO - __main__ - Step 28787: {'lr': 0.0004606658179664302, 'samples': 5527104, 'steps': 28786, 'loss/train': 1.748219609260559} 08/30/2021 18:18:51 - INFO - __main__ - Step 28788: {'lr': 0.00046066296055072986, 'samples': 5527296, 'steps': 28787, 'loss/train': 1.2918643951416016} 08/30/2021 18:18:52 - INFO - __main__ - Step 28789: {'lr': 0.0004606601030401081, 'samples': 5527488, 'steps': 28788, 'loss/train': 1.6055225133895874} 08/30/2021 18:18:53 - INFO - __main__ - Step 28790: {'lr': 0.0004606572454345661, 'samples': 5527680, 'steps': 28789, 'loss/train': 2.2760958671569824} 08/30/2021 18:18:53 - INFO - __main__ - Step 28791: {'lr': 0.0004606543877341052, 'samples': 5527872, 'steps': 28790, 'loss/train': 1.3080912828445435} 08/30/2021 18:18:54 - INFO - __main__ - Step 28792: {'lr': 0.00046065152993872665, 'samples': 5528064, 'steps': 28791, 'loss/train': 0.6149696111679077} 08/30/2021 18:18:54 - INFO - __main__ - Step 28793: {'lr': 0.0004606486720484318, 'samples': 5528256, 'steps': 28792, 'loss/train': 1.9276411533355713} 08/30/2021 18:18:55 - INFO - __main__ - Step 28794: {'lr': 0.0004606458140632219, 'samples': 5528448, 'steps': 28793, 'loss/train': 1.213881015777588} 08/30/2021 18:18:56 - INFO - __main__ - Step 28795: {'lr': 0.0004606429559830982, 'samples': 5528640, 'steps': 28794, 'loss/train': 1.8192152976989746} 08/30/2021 18:18:56 - INFO - __main__ - Step 28796: {'lr': 0.00046064009780806217, 'samples': 5528832, 'steps': 28795, 'loss/train': 1.3204809427261353} 08/30/2021 18:18:57 - INFO - __main__ - Step 28797: {'lr': 0.0004606372395381149, 'samples': 5529024, 'steps': 28796, 'loss/train': 1.1457908153533936} 08/30/2021 18:18:57 - INFO - __main__ - Step 28798: {'lr': 0.0004606343811732577, 'samples': 5529216, 'steps': 28797, 'loss/train': 1.4433735609054565} 08/30/2021 18:18:58 - INFO - __main__ - Step 28799: {'lr': 0.0004606315227134919, 'samples': 5529408, 'steps': 28798, 'loss/train': 1.2644931077957153} 08/30/2021 18:18:59 - INFO - __main__ - Step 28800: {'lr': 0.0004606286641588188, 'samples': 5529600, 'steps': 28799, 'loss/train': 1.5006144046783447} 08/30/2021 18:18:59 - INFO - __main__ - Step 28801: {'lr': 0.0004606258055092397, 'samples': 5529792, 'steps': 28800, 'loss/train': 1.426822304725647} 08/30/2021 18:19:00 - INFO - __main__ - Step 28802: {'lr': 0.00046062294676475584, 'samples': 5529984, 'steps': 28801, 'loss/train': 1.4379661083221436} 08/30/2021 18:19:00 - INFO - __main__ - Step 28803: {'lr': 0.0004606200879253685, 'samples': 5530176, 'steps': 28802, 'loss/train': 1.4996684789657593} 08/30/2021 18:19:02 - INFO - __main__ - Step 28804: {'lr': 0.00046061722899107905, 'samples': 5530368, 'steps': 28803, 'loss/train': 1.2916420698165894} 08/30/2021 18:19:02 - INFO - __main__ - Step 28805: {'lr': 0.0004606143699618888, 'samples': 5530560, 'steps': 28804, 'loss/train': 1.4700864553451538} 08/30/2021 18:19:02 - INFO - __main__ - Step 28806: {'lr': 0.00046061151083779886, 'samples': 5530752, 'steps': 28805, 'loss/train': 1.9744372367858887} 08/30/2021 18:19:03 - INFO - __main__ - Step 28807: {'lr': 0.0004606086516188106, 'samples': 5530944, 'steps': 28806, 'loss/train': 1.173879861831665} 08/30/2021 18:19:03 - INFO - __main__ - Step 28808: {'lr': 0.00046060579230492533, 'samples': 5531136, 'steps': 28807, 'loss/train': 1.6978788375854492} 08/30/2021 18:19:04 - INFO - __main__ - Step 28809: {'lr': 0.0004606029328961444, 'samples': 5531328, 'steps': 28808, 'loss/train': 1.7924799919128418} 08/30/2021 18:19:05 - INFO - __main__ - Step 28810: {'lr': 0.000460600073392469, 'samples': 5531520, 'steps': 28809, 'loss/train': 1.2540429830551147} 08/30/2021 18:19:05 - INFO - __main__ - Step 28811: {'lr': 0.00046059721379390053, 'samples': 5531712, 'steps': 28810, 'loss/train': 0.6633529663085938} 08/30/2021 18:19:06 - INFO - __main__ - Step 28812: {'lr': 0.0004605943541004401, 'samples': 5531904, 'steps': 28811, 'loss/train': 1.1641274690628052} 08/30/2021 18:19:06 - INFO - __main__ - Step 28813: {'lr': 0.00046059149431208914, 'samples': 5532096, 'steps': 28812, 'loss/train': 1.72393000125885} 08/30/2021 18:19:06 - INFO - __main__ - Step 28814: {'lr': 0.0004605886344288489, 'samples': 5532288, 'steps': 28813, 'loss/train': 1.344095230102539} 08/30/2021 18:19:08 - INFO - __main__ - Step 28815: {'lr': 0.0004605857744507207, 'samples': 5532480, 'steps': 28814, 'loss/train': 1.4743280410766602} 08/30/2021 18:19:08 - INFO - __main__ - Step 28816: {'lr': 0.00046058291437770584, 'samples': 5532672, 'steps': 28815, 'loss/train': 1.1923967599868774} 08/30/2021 18:19:09 - INFO - __main__ - Step 28817: {'lr': 0.0004605800542098054, 'samples': 5532864, 'steps': 28816, 'loss/train': 1.0488197803497314} 08/30/2021 18:19:09 - INFO - __main__ - Step 28818: {'lr': 0.00046057719394702103, 'samples': 5533056, 'steps': 28817, 'loss/train': 1.435438632965088} 08/30/2021 18:19:09 - INFO - __main__ - Step 28819: {'lr': 0.00046057433358935373, 'samples': 5533248, 'steps': 28818, 'loss/train': 0.1840985119342804} 08/30/2021 18:19:11 - INFO - __main__ - Step 28820: {'lr': 0.0004605714731368049, 'samples': 5533440, 'steps': 28819, 'loss/train': 1.9750401973724365} 08/30/2021 18:19:12 - INFO - __main__ - Step 28821: {'lr': 0.0004605686125893758, 'samples': 5533632, 'steps': 28820, 'loss/train': 1.3374357223510742} 08/30/2021 18:19:12 - INFO - __main__ - Step 28822: {'lr': 0.00046056575194706773, 'samples': 5533824, 'steps': 28821, 'loss/train': 0.9989317655563354} 08/30/2021 18:19:12 - INFO - __main__ - Step 28823: {'lr': 0.000460562891209882, 'samples': 5534016, 'steps': 28822, 'loss/train': 1.727424144744873} 08/30/2021 18:19:13 - INFO - __main__ - Step 28824: {'lr': 0.0004605600303778199, 'samples': 5534208, 'steps': 28823, 'loss/train': 1.3220311403274536} 08/30/2021 18:19:13 - INFO - __main__ - Step 28825: {'lr': 0.0004605571694508827, 'samples': 5534400, 'steps': 28824, 'loss/train': 1.4859980344772339} 08/30/2021 18:19:14 - INFO - __main__ - Step 28826: {'lr': 0.0004605543084290716, 'samples': 5534592, 'steps': 28825, 'loss/train': 1.5253325700759888} 08/30/2021 18:19:15 - INFO - __main__ - Step 28827: {'lr': 0.00046055144731238805, 'samples': 5534784, 'steps': 28826, 'loss/train': 1.4258514642715454} 08/30/2021 18:19:15 - INFO - __main__ - Step 28828: {'lr': 0.00046054858610083325, 'samples': 5534976, 'steps': 28827, 'loss/train': 1.5617334842681885} 08/30/2021 18:19:16 - INFO - __main__ - Step 28829: {'lr': 0.0004605457247944086, 'samples': 5535168, 'steps': 28828, 'loss/train': 1.6477042436599731} 08/30/2021 18:19:16 - INFO - __main__ - Step 28830: {'lr': 0.0004605428633931152, 'samples': 5535360, 'steps': 28829, 'loss/train': 1.5681991577148438} 08/30/2021 18:19:18 - INFO - __main__ - Step 28831: {'lr': 0.00046054000189695444, 'samples': 5535552, 'steps': 28830, 'loss/train': 1.8616143465042114} 08/30/2021 18:19:18 - INFO - __main__ - Step 28832: {'lr': 0.00046053714030592764, 'samples': 5535744, 'steps': 28831, 'loss/train': 5.211965084075928} 08/30/2021 18:19:19 - INFO - __main__ - Step 28833: {'lr': 0.0004605342786200359, 'samples': 5535936, 'steps': 28832, 'loss/train': 5.299749374389648} 08/30/2021 18:19:19 - INFO - __main__ - Step 28834: {'lr': 0.0004605314168392809, 'samples': 5536128, 'steps': 28833, 'loss/train': 1.5922120809555054} 08/30/2021 18:19:19 - INFO - __main__ - Step 28835: {'lr': 0.00046052855496366354, 'samples': 5536320, 'steps': 28834, 'loss/train': 2.2216432094573975} 08/30/2021 18:19:20 - INFO - __main__ - Step 28836: {'lr': 0.0004605256929931853, 'samples': 5536512, 'steps': 28835, 'loss/train': 1.0870556831359863} 08/30/2021 18:19:22 - INFO - __main__ - Step 28837: {'lr': 0.0004605228309278474, 'samples': 5536704, 'steps': 28836, 'loss/train': 1.584465503692627} 08/30/2021 18:19:22 - INFO - __main__ - Step 28838: {'lr': 0.0004605199687676512, 'samples': 5536896, 'steps': 28837, 'loss/train': 1.690821886062622} 08/30/2021 18:19:23 - INFO - __main__ - Step 28839: {'lr': 0.00046051710651259797, 'samples': 5537088, 'steps': 28838, 'loss/train': 1.9488508701324463} 08/30/2021 18:19:23 - INFO - __main__ - Step 28840: {'lr': 0.00046051424416268896, 'samples': 5537280, 'steps': 28839, 'loss/train': 1.453596591949463} 08/30/2021 18:19:23 - INFO - __main__ - Step 28841: {'lr': 0.0004605113817179255, 'samples': 5537472, 'steps': 28840, 'loss/train': 1.7849009037017822} 08/30/2021 18:19:25 - INFO - __main__ - Step 28842: {'lr': 0.00046050851917830884, 'samples': 5537664, 'steps': 28841, 'loss/train': 1.0420764684677124} 08/30/2021 18:19:25 - INFO - __main__ - Step 28843: {'lr': 0.00046050565654384023, 'samples': 5537856, 'steps': 28842, 'loss/train': 1.6934154033660889} 08/30/2021 18:19:26 - INFO - __main__ - Step 28844: {'lr': 0.0004605027938145211, 'samples': 5538048, 'steps': 28843, 'loss/train': 1.946616768836975} 08/30/2021 18:19:26 - INFO - __main__ - Step 28845: {'lr': 0.0004604999309903526, 'samples': 5538240, 'steps': 28844, 'loss/train': 1.6108081340789795} 08/30/2021 18:19:26 - INFO - __main__ - Step 28846: {'lr': 0.0004604970680713362, 'samples': 5538432, 'steps': 28845, 'loss/train': 2.1126925945281982} 08/30/2021 18:19:27 - INFO - __main__ - Step 28847: {'lr': 0.00046049420505747294, 'samples': 5538624, 'steps': 28846, 'loss/train': 1.4479706287384033} 08/30/2021 18:19:28 - INFO - __main__ - Step 28848: {'lr': 0.0004604913419487643, 'samples': 5538816, 'steps': 28847, 'loss/train': 1.1913269758224487} 08/30/2021 18:19:29 - INFO - __main__ - Step 28849: {'lr': 0.00046048847874521144, 'samples': 5539008, 'steps': 28848, 'loss/train': 1.337689995765686} 08/30/2021 18:19:29 - INFO - __main__ - Step 28850: {'lr': 0.00046048561544681575, 'samples': 5539200, 'steps': 28849, 'loss/train': 1.0054725408554077} 08/30/2021 18:19:29 - INFO - __main__ - Step 28851: {'lr': 0.00046048275205357855, 'samples': 5539392, 'steps': 28850, 'loss/train': 1.068784475326538} 08/30/2021 18:19:30 - INFO - __main__ - Step 28852: {'lr': 0.00046047988856550104, 'samples': 5539584, 'steps': 28851, 'loss/train': 1.2208802700042725} 08/30/2021 18:19:31 - INFO - __main__ - Step 28853: {'lr': 0.00046047702498258446, 'samples': 5539776, 'steps': 28852, 'loss/train': 1.698395848274231} 08/30/2021 18:19:32 - INFO - __main__ - Step 28854: {'lr': 0.00046047416130483033, 'samples': 5539968, 'steps': 28853, 'loss/train': 1.7481921911239624} 08/30/2021 18:19:32 - INFO - __main__ - Step 28855: {'lr': 0.00046047129753223973, 'samples': 5540160, 'steps': 28854, 'loss/train': 1.0832093954086304} 08/30/2021 18:19:32 - INFO - __main__ - Step 28856: {'lr': 0.0004604684336648139, 'samples': 5540352, 'steps': 28855, 'loss/train': 1.8524690866470337} 08/30/2021 18:19:33 - INFO - __main__ - Step 28857: {'lr': 0.00046046556970255435, 'samples': 5540544, 'steps': 28856, 'loss/train': 1.2693358659744263} 08/30/2021 18:19:34 - INFO - __main__ - Step 28858: {'lr': 0.0004604627056454622, 'samples': 5540736, 'steps': 28857, 'loss/train': 1.1964995861053467} 08/30/2021 18:19:34 - INFO - __main__ - Step 28859: {'lr': 0.00046045984149353894, 'samples': 5540928, 'steps': 28858, 'loss/train': 1.4220203161239624} 08/30/2021 18:19:35 - INFO - __main__ - Step 28860: {'lr': 0.0004604569772467856, 'samples': 5541120, 'steps': 28859, 'loss/train': 1.0095555782318115} 08/30/2021 18:19:35 - INFO - __main__ - Step 28861: {'lr': 0.00046045411290520364, 'samples': 5541312, 'steps': 28860, 'loss/train': 1.8971298933029175} 08/30/2021 18:19:36 - INFO - __main__ - Step 28862: {'lr': 0.00046045124846879427, 'samples': 5541504, 'steps': 28861, 'loss/train': 1.142421007156372} 08/30/2021 18:19:37 - INFO - __main__ - Step 28863: {'lr': 0.00046044838393755885, 'samples': 5541696, 'steps': 28862, 'loss/train': 1.459968090057373} 08/30/2021 18:19:38 - INFO - __main__ - Step 28864: {'lr': 0.00046044551931149856, 'samples': 5541888, 'steps': 28863, 'loss/train': 0.4833144247531891} 08/30/2021 18:19:38 - INFO - __main__ - Step 28865: {'lr': 0.0004604426545906149, 'samples': 5542080, 'steps': 28864, 'loss/train': 1.4947117567062378} 08/30/2021 18:19:38 - INFO - __main__ - Step 28866: {'lr': 0.0004604397897749089, 'samples': 5542272, 'steps': 28865, 'loss/train': 1.7568550109863281} 08/30/2021 18:19:39 - INFO - __main__ - Step 28867: {'lr': 0.00046043692486438207, 'samples': 5542464, 'steps': 28866, 'loss/train': 1.0612441301345825} 08/30/2021 18:19:40 - INFO - __main__ - Step 28868: {'lr': 0.00046043405985903555, 'samples': 5542656, 'steps': 28867, 'loss/train': 1.6154786348342896} 08/30/2021 18:19:41 - INFO - __main__ - Step 28869: {'lr': 0.00046043119475887073, 'samples': 5542848, 'steps': 28868, 'loss/train': 1.5218857526779175} 08/30/2021 18:19:41 - INFO - __main__ - Step 28870: {'lr': 0.0004604283295638888, 'samples': 5543040, 'steps': 28869, 'loss/train': 1.3188573122024536} 08/30/2021 18:19:42 - INFO - __main__ - Step 28871: {'lr': 0.00046042546427409116, 'samples': 5543232, 'steps': 28870, 'loss/train': 0.7918139696121216} 08/30/2021 18:19:42 - INFO - __main__ - Step 28872: {'lr': 0.000460422598889479, 'samples': 5543424, 'steps': 28871, 'loss/train': 1.4799987077713013} 08/30/2021 18:19:43 - INFO - __main__ - Step 28873: {'lr': 0.0004604197334100537, 'samples': 5543616, 'steps': 28872, 'loss/train': 1.4581646919250488} 08/30/2021 18:19:44 - INFO - __main__ - Step 28874: {'lr': 0.0004604168678358166, 'samples': 5543808, 'steps': 28873, 'loss/train': 1.1605101823806763} 08/30/2021 18:19:44 - INFO - __main__ - Step 28875: {'lr': 0.00046041400216676874, 'samples': 5544000, 'steps': 28874, 'loss/train': 1.4286561012268066} 08/30/2021 18:19:45 - INFO - __main__ - Step 28876: {'lr': 0.0004604111364029118, 'samples': 5544192, 'steps': 28875, 'loss/train': 1.7455028295516968} 08/30/2021 18:19:45 - INFO - __main__ - Step 28877: {'lr': 0.0004604082705442466, 'samples': 5544384, 'steps': 28876, 'loss/train': 1.7974566221237183} 08/30/2021 18:19:46 - INFO - __main__ - Step 28878: {'lr': 0.00046040540459077483, 'samples': 5544576, 'steps': 28877, 'loss/train': 0.9158125519752502} 08/30/2021 18:19:47 - INFO - __main__ - Step 28879: {'lr': 0.0004604025385424976, 'samples': 5544768, 'steps': 28878, 'loss/train': 1.5195859670639038} 08/30/2021 18:19:47 - INFO - __main__ - Step 28880: {'lr': 0.00046039967239941626, 'samples': 5544960, 'steps': 28879, 'loss/train': 1.4470536708831787} 08/30/2021 18:19:48 - INFO - __main__ - Step 28881: {'lr': 0.000460396806161532, 'samples': 5545152, 'steps': 28880, 'loss/train': 1.6458234786987305} 08/30/2021 18:19:48 - INFO - __main__ - Step 28882: {'lr': 0.0004603939398288463, 'samples': 5545344, 'steps': 28881, 'loss/train': 1.1609463691711426} 08/30/2021 18:19:49 - INFO - __main__ - Step 28883: {'lr': 0.00046039107340136023, 'samples': 5545536, 'steps': 28882, 'loss/train': 1.6444604396820068} 08/30/2021 18:19:50 - INFO - __main__ - Step 28884: {'lr': 0.00046038820687907523, 'samples': 5545728, 'steps': 28883, 'loss/train': 1.0269838571548462} 08/30/2021 18:19:50 - INFO - __main__ - Step 28885: {'lr': 0.0004603853402619925, 'samples': 5545920, 'steps': 28884, 'loss/train': 1.2960134744644165} 08/30/2021 18:19:51 - INFO - __main__ - Step 28886: {'lr': 0.00046038247355011347, 'samples': 5546112, 'steps': 28885, 'loss/train': 1.117455005645752} 08/30/2021 18:19:51 - INFO - __main__ - Step 28887: {'lr': 0.00046037960674343925, 'samples': 5546304, 'steps': 28886, 'loss/train': 0.9311093688011169} 08/30/2021 18:19:51 - INFO - __main__ - Step 28888: {'lr': 0.0004603767398419713, 'samples': 5546496, 'steps': 28887, 'loss/train': 1.880321741104126} 08/30/2021 18:19:54 - INFO - __main__ - Step 28889: {'lr': 0.0004603738728457109, 'samples': 5546688, 'steps': 28888, 'loss/train': 1.6211706399917603} 08/30/2021 18:19:54 - INFO - __main__ - Step 28890: {'lr': 0.0004603710057546592, 'samples': 5546880, 'steps': 28889, 'loss/train': 0.2054881751537323} 08/30/2021 18:19:55 - INFO - __main__ - Step 28891: {'lr': 0.0004603681385688175, 'samples': 5547072, 'steps': 28890, 'loss/train': 0.07243458181619644} 08/30/2021 18:19:55 - INFO - __main__ - Step 28892: {'lr': 0.00046036527128818724, 'samples': 5547264, 'steps': 28891, 'loss/train': 1.0678194761276245} 08/30/2021 18:19:55 - INFO - __main__ - Step 28893: {'lr': 0.0004603624039127696, 'samples': 5547456, 'steps': 28892, 'loss/train': 1.3182927370071411} 08/30/2021 18:19:56 - INFO - __main__ - Step 28894: {'lr': 0.00046035953644256596, 'samples': 5547648, 'steps': 28893, 'loss/train': 1.3891026973724365} 08/30/2021 18:19:57 - INFO - __main__ - Step 28895: {'lr': 0.00046035666887757755, 'samples': 5547840, 'steps': 28894, 'loss/train': 0.2706478536128998} 08/30/2021 18:19:58 - INFO - __main__ - Step 28896: {'lr': 0.00046035380121780563, 'samples': 5548032, 'steps': 28895, 'loss/train': 0.8166786432266235} 08/30/2021 18:19:58 - INFO - __main__ - Step 28897: {'lr': 0.0004603509334632515, 'samples': 5548224, 'steps': 28896, 'loss/train': 1.5154094696044922} 08/30/2021 18:19:58 - INFO - __main__ - Step 28898: {'lr': 0.00046034806561391655, 'samples': 5548416, 'steps': 28897, 'loss/train': 1.4594331979751587} 08/30/2021 18:19:59 - INFO - __main__ - Step 28899: {'lr': 0.000460345197669802, 'samples': 5548608, 'steps': 28898, 'loss/train': 1.543952465057373} 08/30/2021 18:19:59 - INFO - __main__ - Step 28900: {'lr': 0.0004603423296309092, 'samples': 5548800, 'steps': 28899, 'loss/train': 1.7093851566314697} 08/30/2021 18:20:01 - INFO - __main__ - Step 28901: {'lr': 0.0004603394614972393, 'samples': 5548992, 'steps': 28900, 'loss/train': 1.3952860832214355} 08/30/2021 18:20:01 - INFO - __main__ - Step 28902: {'lr': 0.00046033659326879373, 'samples': 5549184, 'steps': 28901, 'loss/train': 2.4770402908325195} 08/30/2021 18:20:02 - INFO - __main__ - Step 28903: {'lr': 0.00046033372494557373, 'samples': 5549376, 'steps': 28902, 'loss/train': 0.9451573491096497} 08/30/2021 18:20:02 - INFO - __main__ - Step 28904: {'lr': 0.00046033085652758053, 'samples': 5549568, 'steps': 28903, 'loss/train': 0.03911512717604637} 08/30/2021 18:20:02 - INFO - __main__ - Step 28905: {'lr': 0.00046032798801481564, 'samples': 5549760, 'steps': 28904, 'loss/train': 1.26829993724823} 08/30/2021 18:20:03 - INFO - __main__ - Step 28906: {'lr': 0.0004603251194072801, 'samples': 5549952, 'steps': 28905, 'loss/train': 1.5318100452423096} 08/30/2021 18:20:04 - INFO - __main__ - Step 28907: {'lr': 0.0004603222507049754, 'samples': 5550144, 'steps': 28906, 'loss/train': 1.6907885074615479} 08/30/2021 18:20:05 - INFO - __main__ - Step 28908: {'lr': 0.00046031938190790254, 'samples': 5550336, 'steps': 28907, 'loss/train': 1.842464804649353} 08/30/2021 18:20:05 - INFO - __main__ - Step 28909: {'lr': 0.0004603165130160633, 'samples': 5550528, 'steps': 28908, 'loss/train': 1.7786346673965454} 08/30/2021 18:20:05 - INFO - __main__ - Step 28910: {'lr': 0.0004603136440294584, 'samples': 5550720, 'steps': 28909, 'loss/train': 1.5675617456436157} 08/30/2021 18:20:06 - INFO - __main__ - Step 28911: {'lr': 0.0004603107749480896, 'samples': 5550912, 'steps': 28910, 'loss/train': 1.4550175666809082} 08/30/2021 18:20:07 - INFO - __main__ - Step 28912: {'lr': 0.0004603079057719579, 'samples': 5551104, 'steps': 28911, 'loss/train': 1.8844538927078247} 08/30/2021 18:20:08 - INFO - __main__ - Step 28913: {'lr': 0.0004603050365010648, 'samples': 5551296, 'steps': 28912, 'loss/train': 1.815502405166626} 08/30/2021 18:20:08 - INFO - __main__ - Step 28914: {'lr': 0.00046030216713541147, 'samples': 5551488, 'steps': 28913, 'loss/train': 1.5247673988342285} 08/30/2021 18:20:08 - INFO - __main__ - Step 28915: {'lr': 0.00046029929767499924, 'samples': 5551680, 'steps': 28914, 'loss/train': 1.4302256107330322} 08/30/2021 18:20:09 - INFO - __main__ - Step 28916: {'lr': 0.0004602964281198293, 'samples': 5551872, 'steps': 28915, 'loss/train': 1.7288661003112793} 08/30/2021 18:20:10 - INFO - __main__ - Step 28917: {'lr': 0.0004602935584699031, 'samples': 5552064, 'steps': 28916, 'loss/train': 1.8400119543075562} 08/30/2021 18:20:11 - INFO - __main__ - Step 28918: {'lr': 0.00046029068872522185, 'samples': 5552256, 'steps': 28917, 'loss/train': 1.44405198097229} 08/30/2021 18:20:11 - INFO - __main__ - Step 28919: {'lr': 0.0004602878188857869, 'samples': 5552448, 'steps': 28918, 'loss/train': 1.474245548248291} 08/30/2021 18:20:11 - INFO - __main__ - Step 28920: {'lr': 0.0004602849489515995, 'samples': 5552640, 'steps': 28919, 'loss/train': 1.9890936613082886} 08/30/2021 18:20:12 - INFO - __main__ - Step 28921: {'lr': 0.00046028207892266095, 'samples': 5552832, 'steps': 28920, 'loss/train': 1.5841706991195679} 08/30/2021 18:20:13 - INFO - __main__ - Step 28922: {'lr': 0.00046027920879897243, 'samples': 5553024, 'steps': 28921, 'loss/train': 0.14850802719593048} 08/30/2021 18:20:14 - INFO - __main__ - Step 28923: {'lr': 0.00046027633858053554, 'samples': 5553216, 'steps': 28922, 'loss/train': 1.1777100563049316} 08/30/2021 18:20:14 - INFO - __main__ - Step 28924: {'lr': 0.0004602734682673512, 'samples': 5553408, 'steps': 28923, 'loss/train': 1.2692878246307373} 08/30/2021 18:20:14 - INFO - __main__ - Step 28925: {'lr': 0.0004602705978594209, 'samples': 5553600, 'steps': 28924, 'loss/train': 1.4671497344970703} 08/30/2021 18:20:15 - INFO - __main__ - Step 28926: {'lr': 0.00046026772735674606, 'samples': 5553792, 'steps': 28925, 'loss/train': 1.2502681016921997} 08/30/2021 18:20:16 - INFO - __main__ - Step 28927: {'lr': 0.00046026485675932765, 'samples': 5553984, 'steps': 28926, 'loss/train': 1.571979284286499} 08/30/2021 18:20:17 - INFO - __main__ - Step 28928: {'lr': 0.0004602619860671672, 'samples': 5554176, 'steps': 28927, 'loss/train': 0.8823884129524231} 08/30/2021 18:20:17 - INFO - __main__ - Step 28929: {'lr': 0.000460259115280266, 'samples': 5554368, 'steps': 28928, 'loss/train': 2.0176033973693848} 08/30/2021 18:20:17 - INFO - __main__ - Step 28930: {'lr': 0.00046025624439862523, 'samples': 5554560, 'steps': 28929, 'loss/train': 1.8027647733688354} 08/30/2021 18:20:18 - INFO - __main__ - Step 28931: {'lr': 0.0004602533734222463, 'samples': 5554752, 'steps': 28930, 'loss/train': 1.4804277420043945} 08/30/2021 18:20:18 - INFO - __main__ - Step 28932: {'lr': 0.00046025050235113036, 'samples': 5554944, 'steps': 28931, 'loss/train': 1.4038063287734985} 08/30/2021 18:20:20 - INFO - __main__ - Step 28933: {'lr': 0.00046024763118527885, 'samples': 5555136, 'steps': 28932, 'loss/train': 1.8037775754928589} 08/30/2021 18:20:20 - INFO - __main__ - Step 28934: {'lr': 0.00046024475992469295, 'samples': 5555328, 'steps': 28933, 'loss/train': 1.4444252252578735} 08/30/2021 18:20:20 - INFO - __main__ - Step 28935: {'lr': 0.0004602418885693741, 'samples': 5555520, 'steps': 28934, 'loss/train': 1.142490029335022} 08/30/2021 18:20:21 - INFO - __main__ - Step 28936: {'lr': 0.0004602390171193234, 'samples': 5555712, 'steps': 28935, 'loss/train': 1.1529531478881836} 08/30/2021 18:20:21 - INFO - __main__ - Step 28937: {'lr': 0.0004602361455745423, 'samples': 5555904, 'steps': 28936, 'loss/train': 1.541255235671997} 08/30/2021 18:20:23 - INFO - __main__ - Step 28938: {'lr': 0.000460233273935032, 'samples': 5556096, 'steps': 28937, 'loss/train': 1.4332858324050903} 08/30/2021 18:20:23 - INFO - __main__ - Step 28939: {'lr': 0.00046023040220079383, 'samples': 5556288, 'steps': 28938, 'loss/train': 1.8582457304000854} 08/30/2021 18:20:23 - INFO - __main__ - Step 28940: {'lr': 0.00046022753037182915, 'samples': 5556480, 'steps': 28939, 'loss/train': 1.4308955669403076} 08/30/2021 18:20:24 - INFO - __main__ - Step 28941: {'lr': 0.0004602246584481391, 'samples': 5556672, 'steps': 28940, 'loss/train': 2.558939218521118} 08/30/2021 18:20:24 - INFO - __main__ - Step 28942: {'lr': 0.00046022178642972513, 'samples': 5556864, 'steps': 28941, 'loss/train': 0.9509792327880859} 08/30/2021 18:20:26 - INFO - __main__ - Step 28943: {'lr': 0.00046021891431658845, 'samples': 5557056, 'steps': 28942, 'loss/train': 1.919646143913269} 08/30/2021 18:20:27 - INFO - __main__ - Step 28944: {'lr': 0.00046021604210873035, 'samples': 5557248, 'steps': 28943, 'loss/train': 0.7934926748275757} 08/30/2021 18:20:27 - INFO - __main__ - Step 28945: {'lr': 0.0004602131698061521, 'samples': 5557440, 'steps': 28944, 'loss/train': 1.622161626815796} 08/30/2021 18:20:27 - INFO - __main__ - Step 28946: {'lr': 0.0004602102974088551, 'samples': 5557632, 'steps': 28945, 'loss/train': 0.7455008029937744} 08/30/2021 18:20:28 - INFO - __main__ - Step 28947: {'lr': 0.00046020742491684067, 'samples': 5557824, 'steps': 28946, 'loss/train': 1.1160584688186646} 08/30/2021 18:20:29 - INFO - __main__ - Step 28948: {'lr': 0.0004602045523301099, 'samples': 5558016, 'steps': 28947, 'loss/train': 2.048121213912964} 08/30/2021 18:20:30 - INFO - __main__ - Step 28949: {'lr': 0.0004602016796486642, 'samples': 5558208, 'steps': 28948, 'loss/train': 1.2027957439422607} 08/30/2021 18:20:30 - INFO - __main__ - Step 28950: {'lr': 0.00046019880687250494, 'samples': 5558400, 'steps': 28949, 'loss/train': 1.0947144031524658} 08/30/2021 18:20:30 - INFO - __main__ - Step 28951: {'lr': 0.0004601959340016333, 'samples': 5558592, 'steps': 28950, 'loss/train': 0.3539426922798157} 08/30/2021 18:20:31 - INFO - __main__ - Step 28952: {'lr': 0.0004601930610360506, 'samples': 5558784, 'steps': 28951, 'loss/train': 1.6546393632888794} 08/30/2021 18:20:32 - INFO - __main__ - Step 28953: {'lr': 0.0004601901879757582, 'samples': 5558976, 'steps': 28952, 'loss/train': 1.4125444889068604} 08/30/2021 18:20:33 - INFO - __main__ - Step 28954: {'lr': 0.0004601873148207573, 'samples': 5559168, 'steps': 28953, 'loss/train': 1.53622305393219} 08/30/2021 18:20:33 - INFO - __main__ - Step 28955: {'lr': 0.00046018444157104924, 'samples': 5559360, 'steps': 28954, 'loss/train': 1.8789094686508179} 08/30/2021 18:20:33 - INFO - __main__ - Step 28956: {'lr': 0.0004601815682266353, 'samples': 5559552, 'steps': 28955, 'loss/train': 0.9152023196220398} 08/30/2021 18:20:34 - INFO - __main__ - Step 28957: {'lr': 0.00046017869478751685, 'samples': 5559744, 'steps': 28956, 'loss/train': 1.435634970664978} 08/30/2021 18:20:36 - INFO - __main__ - Step 28958: {'lr': 0.00046017582125369505, 'samples': 5559936, 'steps': 28957, 'loss/train': 2.5206053256988525} 08/30/2021 18:20:36 - INFO - __main__ - Step 28959: {'lr': 0.00046017294762517127, 'samples': 5560128, 'steps': 28958, 'loss/train': 1.719394564628601} 08/30/2021 18:20:36 - INFO - __main__ - Step 28960: {'lr': 0.0004601700739019469, 'samples': 5560320, 'steps': 28959, 'loss/train': 1.458498477935791} 08/30/2021 18:20:37 - INFO - __main__ - Step 28961: {'lr': 0.000460167200084023, 'samples': 5560512, 'steps': 28960, 'loss/train': 0.8339565992355347} 08/30/2021 18:20:37 - INFO - __main__ - Step 28962: {'lr': 0.00046016432617140113, 'samples': 5560704, 'steps': 28961, 'loss/train': 1.3075861930847168} 08/30/2021 18:20:38 - INFO - __main__ - Step 28963: {'lr': 0.0004601614521640824, 'samples': 5560896, 'steps': 28962, 'loss/train': 1.3877896070480347} 08/30/2021 18:20:38 - INFO - __main__ - Step 28964: {'lr': 0.00046015857806206816, 'samples': 5561088, 'steps': 28963, 'loss/train': 0.10883594304323196} 08/30/2021 18:20:40 - INFO - __main__ - Step 28965: {'lr': 0.0004601557038653597, 'samples': 5561280, 'steps': 28964, 'loss/train': 0.3230167329311371} 08/30/2021 18:20:40 - INFO - __main__ - Step 28966: {'lr': 0.0004601528295739583, 'samples': 5561472, 'steps': 28965, 'loss/train': 0.9901770353317261} 08/30/2021 18:20:40 - INFO - __main__ - Step 28967: {'lr': 0.00046014995518786536, 'samples': 5561664, 'steps': 28966, 'loss/train': 2.1910712718963623} 08/30/2021 18:20:41 - INFO - __main__ - Step 28968: {'lr': 0.000460147080707082, 'samples': 5561856, 'steps': 28967, 'loss/train': 1.1445995569229126} 08/30/2021 18:20:41 - INFO - __main__ - Step 28969: {'lr': 0.00046014420613160967, 'samples': 5562048, 'steps': 28968, 'loss/train': 1.4583795070648193} 08/30/2021 18:20:42 - INFO - __main__ - Step 28970: {'lr': 0.00046014133146144966, 'samples': 5562240, 'steps': 28969, 'loss/train': 1.804777979850769} 08/30/2021 18:20:43 - INFO - __main__ - Step 28971: {'lr': 0.0004601384566966031, 'samples': 5562432, 'steps': 28970, 'loss/train': 1.1418389081954956} 08/30/2021 18:20:43 - INFO - __main__ - Step 28972: {'lr': 0.0004601355818370714, 'samples': 5562624, 'steps': 28971, 'loss/train': 1.0044198036193848} 08/30/2021 18:20:44 - INFO - __main__ - Step 28973: {'lr': 0.0004601327068828559, 'samples': 5562816, 'steps': 28972, 'loss/train': 1.4819682836532593} 08/30/2021 18:20:44 - INFO - __main__ - Step 28974: {'lr': 0.0004601298318339578, 'samples': 5563008, 'steps': 28973, 'loss/train': 1.3393051624298096} 08/30/2021 18:20:46 - INFO - __main__ - Step 28975: {'lr': 0.0004601269566903785, 'samples': 5563200, 'steps': 28974, 'loss/train': 0.6184431910514832} 08/30/2021 18:20:46 - INFO - __main__ - Step 28976: {'lr': 0.0004601240814521192, 'samples': 5563392, 'steps': 28975, 'loss/train': 1.1198714971542358} 08/30/2021 18:20:47 - INFO - __main__ - Step 28977: {'lr': 0.00046012120611918126, 'samples': 5563584, 'steps': 28976, 'loss/train': 2.6182427406311035} 08/30/2021 18:20:47 - INFO - __main__ - Step 28978: {'lr': 0.0004601183306915659, 'samples': 5563776, 'steps': 28977, 'loss/train': 0.9519802927970886} 08/30/2021 18:20:47 - INFO - __main__ - Step 28979: {'lr': 0.0004601154551692745, 'samples': 5563968, 'steps': 28978, 'loss/train': 1.9191051721572876} 08/30/2021 18:20:48 - INFO - __main__ - Step 28980: {'lr': 0.00046011257955230826, 'samples': 5564160, 'steps': 28979, 'loss/train': 1.1937226057052612} 08/30/2021 18:20:49 - INFO - __main__ - Step 28981: {'lr': 0.00046010970384066863, 'samples': 5564352, 'steps': 28980, 'loss/train': 0.980539083480835} 08/30/2021 18:20:50 - INFO - __main__ - Step 28982: {'lr': 0.00046010682803435674, 'samples': 5564544, 'steps': 28981, 'loss/train': 1.0843158960342407} 08/30/2021 18:20:50 - INFO - __main__ - Step 28983: {'lr': 0.000460103952133374, 'samples': 5564736, 'steps': 28982, 'loss/train': 1.4898028373718262} 08/30/2021 18:20:50 - INFO - __main__ - Step 28984: {'lr': 0.00046010107613772154, 'samples': 5564928, 'steps': 28983, 'loss/train': 1.7888057231903076} 08/30/2021 18:20:51 - INFO - __main__ - Step 28985: {'lr': 0.0004600982000474009, 'samples': 5565120, 'steps': 28984, 'loss/train': 1.3882951736450195} 08/30/2021 18:20:53 - INFO - __main__ - Step 28986: {'lr': 0.0004600953238624133, 'samples': 5565312, 'steps': 28985, 'loss/train': 1.7313249111175537} 08/30/2021 18:20:53 - INFO - __main__ - Step 28987: {'lr': 0.00046009244758275986, 'samples': 5565504, 'steps': 28986, 'loss/train': 1.7693266868591309} 08/30/2021 18:20:54 - INFO - __main__ - Step 28988: {'lr': 0.0004600895712084421, 'samples': 5565696, 'steps': 28987, 'loss/train': 0.8204891085624695} 08/30/2021 18:20:54 - INFO - __main__ - Step 28989: {'lr': 0.0004600866947394611, 'samples': 5565888, 'steps': 28988, 'loss/train': 1.4293334484100342} 08/30/2021 18:20:54 - INFO - __main__ - Step 28990: {'lr': 0.0004600838181758184, 'samples': 5566080, 'steps': 28989, 'loss/train': 0.9987662434577942} 08/30/2021 18:20:55 - INFO - __main__ - Step 28991: {'lr': 0.00046008094151751513, 'samples': 5566272, 'steps': 28990, 'loss/train': 1.6933869123458862} 08/30/2021 18:20:56 - INFO - __main__ - Step 28992: {'lr': 0.0004600780647645526, 'samples': 5566464, 'steps': 28991, 'loss/train': 0.10519556701183319} 08/30/2021 18:20:57 - INFO - __main__ - Step 28993: {'lr': 0.0004600751879169321, 'samples': 5566656, 'steps': 28992, 'loss/train': 1.2371454238891602} 08/30/2021 18:20:57 - INFO - __main__ - Step 28994: {'lr': 0.00046007231097465505, 'samples': 5566848, 'steps': 28993, 'loss/train': 1.0152714252471924} 08/30/2021 18:20:57 - INFO - __main__ - Step 28995: {'lr': 0.00046006943393772274, 'samples': 5567040, 'steps': 28994, 'loss/train': 1.2526971101760864} 08/30/2021 18:20:58 - INFO - __main__ - Step 28996: {'lr': 0.00046006655680613616, 'samples': 5567232, 'steps': 28995, 'loss/train': 1.8520199060440063} 08/30/2021 18:20:59 - INFO - __main__ - Step 28997: {'lr': 0.00046006367957989705, 'samples': 5567424, 'steps': 28996, 'loss/train': 1.6551318168640137} 08/30/2021 18:21:00 - INFO - __main__ - Step 28998: {'lr': 0.0004600608022590064, 'samples': 5567616, 'steps': 28997, 'loss/train': 1.4023603200912476} 08/30/2021 18:21:00 - INFO - __main__ - Step 28999: {'lr': 0.0004600579248434655, 'samples': 5567808, 'steps': 28998, 'loss/train': 1.3744001388549805} 08/30/2021 18:21:01 - INFO - __main__ - Step 29000: {'lr': 0.0004600550473332759, 'samples': 5568000, 'steps': 28999, 'loss/train': 5.890665531158447} 08/30/2021 18:21:01 - INFO - __main__ - Step 29001: {'lr': 0.0004600521697284386, 'samples': 5568192, 'steps': 29000, 'loss/train': 1.5829437971115112} 08/30/2021 18:21:01 - INFO - __main__ - Step 29002: {'lr': 0.0004600492920289551, 'samples': 5568384, 'steps': 29001, 'loss/train': 1.630038857460022} 08/30/2021 18:21:03 - INFO - __main__ - Step 29003: {'lr': 0.00046004641423482665, 'samples': 5568576, 'steps': 29002, 'loss/train': 1.9166052341461182} 08/30/2021 18:21:04 - INFO - __main__ - Step 29004: {'lr': 0.00046004353634605447, 'samples': 5568768, 'steps': 29003, 'loss/train': 1.3703222274780273} 08/30/2021 18:21:04 - INFO - __main__ - Step 29005: {'lr': 0.00046004065836263995, 'samples': 5568960, 'steps': 29004, 'loss/train': 1.461896300315857} 08/30/2021 18:21:04 - INFO - __main__ - Step 29006: {'lr': 0.00046003778028458434, 'samples': 5569152, 'steps': 29005, 'loss/train': 1.6786259412765503} 08/30/2021 18:21:05 - INFO - __main__ - Step 29007: {'lr': 0.00046003490211188894, 'samples': 5569344, 'steps': 29006, 'loss/train': 1.2999341487884521} 08/30/2021 18:21:06 - INFO - __main__ - Step 29008: {'lr': 0.00046003202384455505, 'samples': 5569536, 'steps': 29007, 'loss/train': 0.8424675464630127} 08/30/2021 18:21:07 - INFO - __main__ - Step 29009: {'lr': 0.000460029145482584, 'samples': 5569728, 'steps': 29008, 'loss/train': 1.7033573389053345} 08/30/2021 18:21:07 - INFO - __main__ - Step 29010: {'lr': 0.00046002626702597706, 'samples': 5569920, 'steps': 29009, 'loss/train': 1.7456250190734863} 08/30/2021 18:21:07 - INFO - __main__ - Step 29011: {'lr': 0.00046002338847473545, 'samples': 5570112, 'steps': 29010, 'loss/train': 1.8192698955535889} 08/30/2021 18:21:08 - INFO - __main__ - Step 29012: {'lr': 0.0004600205098288606, 'samples': 5570304, 'steps': 29011, 'loss/train': 1.402625560760498} 08/30/2021 18:21:09 - INFO - __main__ - Step 29013: {'lr': 0.00046001763108835384, 'samples': 5570496, 'steps': 29012, 'loss/train': 0.7089826464653015} 08/30/2021 18:21:10 - INFO - __main__ - Step 29014: {'lr': 0.0004600147522532162, 'samples': 5570688, 'steps': 29013, 'loss/train': 2.035728931427002} 08/30/2021 18:21:10 - INFO - __main__ - Step 29015: {'lr': 0.0004600118733234493, 'samples': 5570880, 'steps': 29014, 'loss/train': 1.5968133211135864} 08/30/2021 18:21:10 - INFO - __main__ - Step 29016: {'lr': 0.0004600089942990542, 'samples': 5571072, 'steps': 29015, 'loss/train': 1.2618802785873413} 08/30/2021 18:21:11 - INFO - __main__ - Step 29017: {'lr': 0.00046000611518003234, 'samples': 5571264, 'steps': 29016, 'loss/train': 1.3774456977844238} 08/30/2021 18:21:11 - INFO - __main__ - Step 29018: {'lr': 0.00046000323596638495, 'samples': 5571456, 'steps': 29017, 'loss/train': 1.3386033773422241} 08/30/2021 18:21:13 - INFO - __main__ - Step 29019: {'lr': 0.0004600003566581133, 'samples': 5571648, 'steps': 29018, 'loss/train': 1.303830623626709} 08/30/2021 18:21:13 - INFO - __main__ - Step 29020: {'lr': 0.00045999747725521876, 'samples': 5571840, 'steps': 29019, 'loss/train': 1.6431649923324585} 08/30/2021 18:21:14 - INFO - __main__ - Step 29021: {'lr': 0.0004599945977577026, 'samples': 5572032, 'steps': 29020, 'loss/train': 0.18844221532344818} 08/30/2021 18:21:14 - INFO - __main__ - Step 29022: {'lr': 0.0004599917181655661, 'samples': 5572224, 'steps': 29021, 'loss/train': 2.0019733905792236} 08/30/2021 18:21:14 - INFO - __main__ - Step 29023: {'lr': 0.00045998883847881057, 'samples': 5572416, 'steps': 29022, 'loss/train': 1.8991312980651855} 08/30/2021 18:21:16 - INFO - __main__ - Step 29024: {'lr': 0.00045998595869743735, 'samples': 5572608, 'steps': 29023, 'loss/train': 1.6134456396102905} 08/30/2021 18:21:16 - INFO - __main__ - Step 29025: {'lr': 0.0004599830788214477, 'samples': 5572800, 'steps': 29024, 'loss/train': 0.056618429720401764} 08/30/2021 18:21:17 - INFO - __main__ - Step 29026: {'lr': 0.0004599801988508429, 'samples': 5572992, 'steps': 29025, 'loss/train': 1.6746482849121094} 08/30/2021 18:21:17 - INFO - __main__ - Step 29027: {'lr': 0.00045997731878562423, 'samples': 5573184, 'steps': 29026, 'loss/train': 1.0732512474060059} 08/30/2021 18:21:18 - INFO - __main__ - Step 29028: {'lr': 0.000459974438625793, 'samples': 5573376, 'steps': 29027, 'loss/train': 1.6636924743652344} 08/30/2021 18:21:19 - INFO - __main__ - Step 29029: {'lr': 0.0004599715583713506, 'samples': 5573568, 'steps': 29028, 'loss/train': 2.3188862800598145} 08/30/2021 18:21:20 - INFO - __main__ - Step 29030: {'lr': 0.00045996867802229824, 'samples': 5573760, 'steps': 29029, 'loss/train': 1.6132086515426636} 08/30/2021 18:21:20 - INFO - __main__ - Step 29031: {'lr': 0.0004599657975786372, 'samples': 5573952, 'steps': 29030, 'loss/train': 0.8914322257041931} 08/30/2021 18:21:20 - INFO - __main__ - Step 29032: {'lr': 0.00045996291704036884, 'samples': 5574144, 'steps': 29031, 'loss/train': 1.1770182847976685} 08/30/2021 18:21:21 - INFO - __main__ - Step 29033: {'lr': 0.00045996003640749446, 'samples': 5574336, 'steps': 29032, 'loss/train': 1.8061771392822266} 08/30/2021 18:21:21 - INFO - __main__ - Step 29034: {'lr': 0.0004599571556800153, 'samples': 5574528, 'steps': 29033, 'loss/train': 1.0761033296585083} 08/30/2021 18:21:23 - INFO - __main__ - Step 29035: {'lr': 0.00045995427485793263, 'samples': 5574720, 'steps': 29034, 'loss/train': 4.809989929199219} 08/30/2021 18:21:23 - INFO - __main__ - Step 29036: {'lr': 0.00045995139394124784, 'samples': 5574912, 'steps': 29035, 'loss/train': 1.8105863332748413} 08/30/2021 18:21:24 - INFO - __main__ - Step 29037: {'lr': 0.0004599485129299622, 'samples': 5575104, 'steps': 29036, 'loss/train': 1.9833271503448486} 08/30/2021 18:21:24 - INFO - __main__ - Step 29038: {'lr': 0.000459945631824077, 'samples': 5575296, 'steps': 29037, 'loss/train': 2.1372933387756348} 08/30/2021 18:21:24 - INFO - __main__ - Step 29039: {'lr': 0.0004599427506235936, 'samples': 5575488, 'steps': 29038, 'loss/train': 1.6469768285751343} 08/30/2021 18:21:26 - INFO - __main__ - Step 29040: {'lr': 0.0004599398693285132, 'samples': 5575680, 'steps': 29039, 'loss/train': 1.6811004877090454} 08/30/2021 18:21:26 - INFO - __main__ - Step 29041: {'lr': 0.0004599369879388371, 'samples': 5575872, 'steps': 29040, 'loss/train': 2.101963996887207} 08/30/2021 18:21:27 - INFO - __main__ - Step 29042: {'lr': 0.0004599341064545666, 'samples': 5576064, 'steps': 29041, 'loss/train': 1.8116940259933472} 08/30/2021 18:21:27 - INFO - __main__ - Step 29043: {'lr': 0.00045993122487570303, 'samples': 5576256, 'steps': 29042, 'loss/train': 1.2629058361053467} 08/30/2021 18:21:27 - INFO - __main__ - Step 29044: {'lr': 0.00045992834320224773, 'samples': 5576448, 'steps': 29043, 'loss/train': 1.6439467668533325} 08/30/2021 18:21:29 - INFO - __main__ - Step 29045: {'lr': 0.000459925461434202, 'samples': 5576640, 'steps': 29044, 'loss/train': 1.284886121749878} 08/30/2021 18:21:29 - INFO - __main__ - Step 29046: {'lr': 0.00045992257957156704, 'samples': 5576832, 'steps': 29045, 'loss/train': 1.5194182395935059} 08/30/2021 18:21:29 - INFO - __main__ - Step 29047: {'lr': 0.00045991969761434426, 'samples': 5577024, 'steps': 29046, 'loss/train': 0.9067851305007935} 08/30/2021 18:21:30 - INFO - __main__ - Step 29048: {'lr': 0.0004599168155625348, 'samples': 5577216, 'steps': 29047, 'loss/train': 1.4850435256958008} 08/30/2021 18:21:30 - INFO - __main__ - Step 29049: {'lr': 0.00045991393341614017, 'samples': 5577408, 'steps': 29048, 'loss/train': 1.5920634269714355} 08/30/2021 18:21:32 - INFO - __main__ - Step 29050: {'lr': 0.0004599110511751615, 'samples': 5577600, 'steps': 29049, 'loss/train': 2.0021350383758545} 08/30/2021 18:21:32 - INFO - __main__ - Step 29051: {'lr': 0.0004599081688396002, 'samples': 5577792, 'steps': 29050, 'loss/train': 1.9680159091949463} 08/30/2021 18:21:32 - INFO - __main__ - Step 29052: {'lr': 0.0004599052864094575, 'samples': 5577984, 'steps': 29051, 'loss/train': 1.4609522819519043} 08/30/2021 18:21:33 - INFO - __main__ - Step 29053: {'lr': 0.0004599024038847347, 'samples': 5578176, 'steps': 29052, 'loss/train': 1.6223266124725342} 08/30/2021 18:21:33 - INFO - __main__ - Step 29054: {'lr': 0.0004598995212654331, 'samples': 5578368, 'steps': 29053, 'loss/train': 1.5891494750976562} 08/30/2021 18:21:35 - INFO - __main__ - Step 29055: {'lr': 0.0004598966385515541, 'samples': 5578560, 'steps': 29054, 'loss/train': 1.203086018562317} 08/30/2021 18:21:36 - INFO - __main__ - Step 29056: {'lr': 0.00045989375574309875, 'samples': 5578752, 'steps': 29055, 'loss/train': 1.7755188941955566} 08/30/2021 18:21:36 - INFO - __main__ - Step 29057: {'lr': 0.00045989087284006863, 'samples': 5578944, 'steps': 29056, 'loss/train': 1.4583615064620972} 08/30/2021 18:21:36 - INFO - __main__ - Step 29058: {'lr': 0.00045988798984246496, 'samples': 5579136, 'steps': 29057, 'loss/train': 1.4929167032241821} 08/30/2021 18:21:37 - INFO - __main__ - Step 29059: {'lr': 0.0004598851067502889, 'samples': 5579328, 'steps': 29058, 'loss/train': 0.9355854392051697} 08/30/2021 18:21:37 - INFO - __main__ - Step 29060: {'lr': 0.00045988222356354186, 'samples': 5579520, 'steps': 29059, 'loss/train': 1.2193325757980347} 08/30/2021 18:21:39 - INFO - __main__ - Step 29061: {'lr': 0.00045987934028222515, 'samples': 5579712, 'steps': 29060, 'loss/train': 1.1979621648788452} 08/30/2021 18:21:39 - INFO - __main__ - Step 29062: {'lr': 0.00045987645690634003, 'samples': 5579904, 'steps': 29061, 'loss/train': 0.2693827152252197} 08/30/2021 18:21:39 - INFO - __main__ - Step 29063: {'lr': 0.0004598735734358879, 'samples': 5580096, 'steps': 29062, 'loss/train': 1.5783582925796509} 08/30/2021 18:21:40 - INFO - __main__ - Step 29064: {'lr': 0.0004598706898708699, 'samples': 5580288, 'steps': 29063, 'loss/train': 0.9061970710754395} 08/30/2021 18:21:40 - INFO - __main__ - Step 29065: {'lr': 0.00045986780621128743, 'samples': 5580480, 'steps': 29064, 'loss/train': 1.7659823894500732} 08/30/2021 18:21:42 - INFO - __main__ - Step 29066: {'lr': 0.00045986492245714175, 'samples': 5580672, 'steps': 29065, 'loss/train': 1.4529715776443481} 08/30/2021 18:21:42 - INFO - __main__ - Step 29067: {'lr': 0.0004598620386084342, 'samples': 5580864, 'steps': 29066, 'loss/train': 1.672145962715149} 08/30/2021 18:21:42 - INFO - __main__ - Step 29068: {'lr': 0.00045985915466516605, 'samples': 5581056, 'steps': 29067, 'loss/train': 1.891939640045166} 08/30/2021 18:21:43 - INFO - __main__ - Step 29069: {'lr': 0.0004598562706273386, 'samples': 5581248, 'steps': 29068, 'loss/train': 1.370741367340088} 08/30/2021 18:21:43 - INFO - __main__ - Step 29070: {'lr': 0.0004598533864949531, 'samples': 5581440, 'steps': 29069, 'loss/train': 1.5381206274032593} 08/30/2021 18:21:45 - INFO - __main__ - Step 29071: {'lr': 0.00045985050226801097, 'samples': 5581632, 'steps': 29070, 'loss/train': 1.79341459274292} 08/30/2021 18:21:45 - INFO - __main__ - Step 29072: {'lr': 0.0004598476179465134, 'samples': 5581824, 'steps': 29071, 'loss/train': 1.566278338432312} 08/30/2021 18:21:46 - INFO - __main__ - Step 29073: {'lr': 0.00045984473353046174, 'samples': 5582016, 'steps': 29072, 'loss/train': 2.284355401992798} 08/30/2021 18:21:46 - INFO - __main__ - Step 29074: {'lr': 0.00045984184901985735, 'samples': 5582208, 'steps': 29073, 'loss/train': 0.9142330288887024} 08/30/2021 18:21:46 - INFO - __main__ - Step 29075: {'lr': 0.00045983896441470143, 'samples': 5582400, 'steps': 29074, 'loss/train': 0.06127826124429703} 08/30/2021 18:21:48 - INFO - __main__ - Step 29076: {'lr': 0.00045983607971499527, 'samples': 5582592, 'steps': 29075, 'loss/train': 1.9395575523376465} 08/30/2021 18:21:48 - INFO - __main__ - Step 29077: {'lr': 0.0004598331949207402, 'samples': 5582784, 'steps': 29076, 'loss/train': 0.9161554574966431} 08/30/2021 18:21:49 - INFO - __main__ - Step 29078: {'lr': 0.00045983031003193756, 'samples': 5582976, 'steps': 29077, 'loss/train': 1.269913911819458} 08/30/2021 18:21:49 - INFO - __main__ - Step 29079: {'lr': 0.0004598274250485886, 'samples': 5583168, 'steps': 29078, 'loss/train': 1.933900237083435} 08/30/2021 18:21:49 - INFO - __main__ - Step 29080: {'lr': 0.00045982453997069463, 'samples': 5583360, 'steps': 29079, 'loss/train': 1.6913996934890747} 08/30/2021 18:21:50 - INFO - __main__ - Step 29081: {'lr': 0.00045982165479825697, 'samples': 5583552, 'steps': 29080, 'loss/train': 0.9966526627540588} 08/30/2021 18:21:51 - INFO - __main__ - Step 29082: {'lr': 0.000459818769531277, 'samples': 5583744, 'steps': 29081, 'loss/train': 1.1565251350402832} 08/30/2021 18:21:52 - INFO - __main__ - Step 29083: {'lr': 0.00045981588416975583, 'samples': 5583936, 'steps': 29082, 'loss/train': 1.4232019186019897} 08/30/2021 18:21:52 - INFO - __main__ - Step 29084: {'lr': 0.00045981299871369484, 'samples': 5584128, 'steps': 29083, 'loss/train': 1.2171101570129395} 08/30/2021 18:21:53 - INFO - __main__ - Step 29085: {'lr': 0.0004598101131630954, 'samples': 5584320, 'steps': 29084, 'loss/train': 0.9350250363349915} 08/30/2021 18:21:53 - INFO - __main__ - Step 29086: {'lr': 0.0004598072275179588, 'samples': 5584512, 'steps': 29085, 'loss/train': 1.704522728919983} 08/30/2021 18:21:54 - INFO - __main__ - Step 29087: {'lr': 0.00045980434177828625, 'samples': 5584704, 'steps': 29086, 'loss/train': 0.9867247343063354} 08/30/2021 18:21:55 - INFO - __main__ - Step 29088: {'lr': 0.00045980145594407907, 'samples': 5584896, 'steps': 29087, 'loss/train': 1.415088176727295} 08/30/2021 18:21:55 - INFO - __main__ - Step 29089: {'lr': 0.00045979857001533867, 'samples': 5585088, 'steps': 29088, 'loss/train': 0.9071172475814819} 08/30/2021 18:21:56 - INFO - __main__ - Step 29090: {'lr': 0.0004597956839920662, 'samples': 5585280, 'steps': 29089, 'loss/train': 2.0894312858581543} 08/30/2021 18:21:56 - INFO - __main__ - Step 29091: {'lr': 0.00045979279787426307, 'samples': 5585472, 'steps': 29090, 'loss/train': 1.352568507194519} 08/30/2021 18:21:57 - INFO - __main__ - Step 29092: {'lr': 0.00045978991166193057, 'samples': 5585664, 'steps': 29091, 'loss/train': 0.5328934192657471} 08/30/2021 18:21:58 - INFO - __main__ - Step 29093: {'lr': 0.0004597870253550699, 'samples': 5585856, 'steps': 29092, 'loss/train': 1.7023544311523438} 08/30/2021 18:21:58 - INFO - __main__ - Step 29094: {'lr': 0.0004597841389536825, 'samples': 5586048, 'steps': 29093, 'loss/train': 1.6095505952835083} 08/30/2021 18:21:58 - INFO - __main__ - Step 29095: {'lr': 0.00045978125245776957, 'samples': 5586240, 'steps': 29094, 'loss/train': 1.1898564100265503} 08/30/2021 18:21:59 - INFO - __main__ - Step 29096: {'lr': 0.00045977836586733246, 'samples': 5586432, 'steps': 29095, 'loss/train': 1.627050518989563} 08/30/2021 18:22:00 - INFO - __main__ - Step 29097: {'lr': 0.00045977547918237243, 'samples': 5586624, 'steps': 29096, 'loss/train': 1.6160439252853394} 08/30/2021 18:22:01 - INFO - __main__ - Step 29098: {'lr': 0.0004597725924028908, 'samples': 5586816, 'steps': 29097, 'loss/train': 2.4444825649261475} 08/30/2021 18:22:01 - INFO - __main__ - Step 29099: {'lr': 0.00045976970552888896, 'samples': 5587008, 'steps': 29098, 'loss/train': 1.269550085067749} 08/30/2021 18:22:01 - INFO - __main__ - Step 29100: {'lr': 0.00045976681856036805, 'samples': 5587200, 'steps': 29099, 'loss/train': 1.4420042037963867} 08/30/2021 18:22:02 - INFO - __main__ - Step 29101: {'lr': 0.00045976393149732943, 'samples': 5587392, 'steps': 29100, 'loss/train': 1.3307113647460938} 08/30/2021 18:22:04 - INFO - __main__ - Step 29102: {'lr': 0.0004597610443397745, 'samples': 5587584, 'steps': 29101, 'loss/train': 1.515670657157898} 08/30/2021 18:22:04 - INFO - __main__ - Step 29103: {'lr': 0.0004597581570877044, 'samples': 5587776, 'steps': 29102, 'loss/train': 1.5040066242218018} 08/30/2021 18:22:05 - INFO - __main__ - Step 29104: {'lr': 0.00045975526974112056, 'samples': 5587968, 'steps': 29103, 'loss/train': 1.9000853300094604} 08/30/2021 18:22:05 - INFO - __main__ - Step 29105: {'lr': 0.0004597523823000243, 'samples': 5588160, 'steps': 29104, 'loss/train': 1.9205955266952515} 08/30/2021 18:22:05 - INFO - __main__ - Step 29106: {'lr': 0.0004597494947644167, 'samples': 5588352, 'steps': 29105, 'loss/train': 0.8787484169006348} 08/30/2021 18:22:06 - INFO - __main__ - Step 29107: {'lr': 0.0004597466071342993, 'samples': 5588544, 'steps': 29106, 'loss/train': 0.05248590558767319} 08/30/2021 18:22:08 - INFO - __main__ - Step 29108: {'lr': 0.0004597437194096733, 'samples': 5588736, 'steps': 29107, 'loss/train': 1.3961764574050903} 08/30/2021 18:22:08 - INFO - __main__ - Step 29109: {'lr': 0.00045974083159054, 'samples': 5588928, 'steps': 29108, 'loss/train': 1.5835131406784058} 08/30/2021 18:22:09 - INFO - __main__ - Step 29110: {'lr': 0.0004597379436769008, 'samples': 5589120, 'steps': 29109, 'loss/train': 1.570286750793457} 08/30/2021 18:22:09 - INFO - __main__ - Step 29111: {'lr': 0.00045973505566875684, 'samples': 5589312, 'steps': 29110, 'loss/train': 1.2224258184432983} 08/30/2021 18:22:09 - INFO - __main__ - Step 29112: {'lr': 0.00045973216756610945, 'samples': 5589504, 'steps': 29111, 'loss/train': 2.063640832901001} 08/30/2021 18:22:11 - INFO - __main__ - Step 29113: {'lr': 0.00045972927936896007, 'samples': 5589696, 'steps': 29112, 'loss/train': 1.0846408605575562} 08/30/2021 18:22:11 - INFO - __main__ - Step 29114: {'lr': 0.0004597263910773099, 'samples': 5589888, 'steps': 29113, 'loss/train': 1.6578137874603271} 08/30/2021 18:22:12 - INFO - __main__ - Step 29115: {'lr': 0.0004597235026911603, 'samples': 5590080, 'steps': 29114, 'loss/train': 1.6081702709197998} 08/30/2021 18:22:12 - INFO - __main__ - Step 29116: {'lr': 0.0004597206142105124, 'samples': 5590272, 'steps': 29115, 'loss/train': 1.46647310256958} 08/30/2021 18:22:12 - INFO - __main__ - Step 29117: {'lr': 0.0004597177256353677, 'samples': 5590464, 'steps': 29116, 'loss/train': 1.7984187602996826} 08/30/2021 18:22:14 - INFO - __main__ - Step 29118: {'lr': 0.0004597148369657275, 'samples': 5590656, 'steps': 29117, 'loss/train': 2.0254669189453125} 08/30/2021 18:22:14 - INFO - __main__ - Step 29119: {'lr': 0.0004597119482015929, 'samples': 5590848, 'steps': 29118, 'loss/train': 1.6421504020690918} 08/30/2021 18:22:15 - INFO - __main__ - Step 29120: {'lr': 0.00045970905934296537, 'samples': 5591040, 'steps': 29119, 'loss/train': 1.6421531438827515} 08/30/2021 18:22:15 - INFO - __main__ - Step 29121: {'lr': 0.0004597061703898462, 'samples': 5591232, 'steps': 29120, 'loss/train': 1.3585336208343506} 08/30/2021 18:22:15 - INFO - __main__ - Step 29122: {'lr': 0.0004597032813422367, 'samples': 5591424, 'steps': 29121, 'loss/train': 1.2464593648910522} 08/30/2021 18:22:17 - INFO - __main__ - Step 29123: {'lr': 0.00045970039220013804, 'samples': 5591616, 'steps': 29122, 'loss/train': 1.6743971109390259} 08/30/2021 18:22:17 - INFO - __main__ - Step 29124: {'lr': 0.00045969750296355173, 'samples': 5591808, 'steps': 29123, 'loss/train': 1.6649267673492432} 08/30/2021 18:22:18 - INFO - __main__ - Step 29125: {'lr': 0.0004596946136324789, 'samples': 5592000, 'steps': 29124, 'loss/train': 1.6004528999328613} 08/30/2021 18:22:18 - INFO - __main__ - Step 29126: {'lr': 0.0004596917242069209, 'samples': 5592192, 'steps': 29125, 'loss/train': 2.043062686920166} 08/30/2021 18:22:18 - INFO - __main__ - Step 29127: {'lr': 0.00045968883468687906, 'samples': 5592384, 'steps': 29126, 'loss/train': 1.749453067779541} 08/30/2021 18:22:19 - INFO - __main__ - Step 29128: {'lr': 0.00045968594507235467, 'samples': 5592576, 'steps': 29127, 'loss/train': 1.4296698570251465} 08/30/2021 18:22:20 - INFO - __main__ - Step 29129: {'lr': 0.00045968305536334906, 'samples': 5592768, 'steps': 29128, 'loss/train': 1.8172740936279297} 08/30/2021 18:22:21 - INFO - __main__ - Step 29130: {'lr': 0.00045968016555986347, 'samples': 5592960, 'steps': 29129, 'loss/train': 1.2048875093460083} 08/30/2021 18:22:21 - INFO - __main__ - Step 29131: {'lr': 0.0004596772756618992, 'samples': 5593152, 'steps': 29130, 'loss/train': 0.16799619793891907} 08/30/2021 18:22:21 - INFO - __main__ - Step 29132: {'lr': 0.0004596743856694576, 'samples': 5593344, 'steps': 29131, 'loss/train': 1.5724396705627441} 08/30/2021 18:22:22 - INFO - __main__ - Step 29133: {'lr': 0.00045967149558254, 'samples': 5593536, 'steps': 29132, 'loss/train': 1.320733666419983} 08/30/2021 18:22:23 - INFO - __main__ - Step 29134: {'lr': 0.0004596686054011476, 'samples': 5593728, 'steps': 29133, 'loss/train': 1.5041048526763916} 08/30/2021 18:22:24 - INFO - __main__ - Step 29135: {'lr': 0.0004596657151252819, 'samples': 5593920, 'steps': 29134, 'loss/train': 1.3871675729751587} 08/30/2021 18:22:24 - INFO - __main__ - Step 29136: {'lr': 0.0004596628247549439, 'samples': 5594112, 'steps': 29135, 'loss/train': 1.1521623134613037} 08/30/2021 18:22:24 - INFO - __main__ - Step 29137: {'lr': 0.00045965993429013507, 'samples': 5594304, 'steps': 29136, 'loss/train': 1.2652631998062134} 08/30/2021 18:22:25 - INFO - __main__ - Step 29138: {'lr': 0.0004596570437308568, 'samples': 5594496, 'steps': 29137, 'loss/train': 1.6733323335647583} 08/30/2021 18:22:26 - INFO - __main__ - Step 29139: {'lr': 0.0004596541530771103, 'samples': 5594688, 'steps': 29138, 'loss/train': 1.4596182107925415} 08/30/2021 18:22:27 - INFO - __main__ - Step 29140: {'lr': 0.0004596512623288969, 'samples': 5594880, 'steps': 29139, 'loss/train': 1.0607844591140747} 08/30/2021 18:22:27 - INFO - __main__ - Step 29141: {'lr': 0.00045964837148621776, 'samples': 5595072, 'steps': 29140, 'loss/train': 1.5667705535888672} 08/30/2021 18:22:27 - INFO - __main__ - Step 29142: {'lr': 0.00045964548054907434, 'samples': 5595264, 'steps': 29141, 'loss/train': 1.7079411745071411} 08/30/2021 18:22:28 - INFO - __main__ - Step 29143: {'lr': 0.00045964258951746795, 'samples': 5595456, 'steps': 29142, 'loss/train': 1.4324219226837158} 08/30/2021 18:22:29 - INFO - __main__ - Step 29144: {'lr': 0.0004596396983913998, 'samples': 5595648, 'steps': 29143, 'loss/train': 1.4762330055236816} 08/30/2021 18:22:30 - INFO - __main__ - Step 29145: {'lr': 0.00045963680717087124, 'samples': 5595840, 'steps': 29144, 'loss/train': 0.9415585994720459} 08/30/2021 18:22:30 - INFO - __main__ - Step 29146: {'lr': 0.0004596339158558835, 'samples': 5596032, 'steps': 29145, 'loss/train': 1.843888759613037} 08/30/2021 18:22:30 - INFO - __main__ - Step 29147: {'lr': 0.0004596310244464381, 'samples': 5596224, 'steps': 29146, 'loss/train': 1.2072358131408691} 08/30/2021 18:22:31 - INFO - __main__ - Step 29148: {'lr': 0.0004596281329425361, 'samples': 5596416, 'steps': 29147, 'loss/train': 1.0851892232894897} 08/30/2021 18:22:32 - INFO - __main__ - Step 29149: {'lr': 0.0004596252413441789, 'samples': 5596608, 'steps': 29148, 'loss/train': 1.4955570697784424} 08/30/2021 18:22:33 - INFO - __main__ - Step 29150: {'lr': 0.00045962234965136783, 'samples': 5596800, 'steps': 29149, 'loss/train': 2.4021732807159424} 08/30/2021 18:22:33 - INFO - __main__ - Step 29151: {'lr': 0.0004596194578641042, 'samples': 5596992, 'steps': 29150, 'loss/train': 1.2575191259384155} 08/30/2021 18:22:33 - INFO - __main__ - Step 29152: {'lr': 0.00045961656598238925, 'samples': 5597184, 'steps': 29151, 'loss/train': 1.2860348224639893} 08/30/2021 18:22:34 - INFO - __main__ - Step 29153: {'lr': 0.00045961367400622436, 'samples': 5597376, 'steps': 29152, 'loss/train': 1.8073841333389282} 08/30/2021 18:22:35 - INFO - __main__ - Step 29154: {'lr': 0.00045961078193561066, 'samples': 5597568, 'steps': 29153, 'loss/train': 1.476631760597229} 08/30/2021 18:22:36 - INFO - __main__ - Step 29155: {'lr': 0.00045960788977054967, 'samples': 5597760, 'steps': 29154, 'loss/train': 1.0465525388717651} 08/30/2021 18:22:36 - INFO - __main__ - Step 29156: {'lr': 0.0004596049975110426, 'samples': 5597952, 'steps': 29155, 'loss/train': 1.152707576751709} 08/30/2021 18:22:36 - INFO - __main__ - Step 29157: {'lr': 0.00045960210515709064, 'samples': 5598144, 'steps': 29156, 'loss/train': 0.7667427062988281} 08/30/2021 18:22:37 - INFO - __main__ - Step 29158: {'lr': 0.0004595992127086953, 'samples': 5598336, 'steps': 29157, 'loss/train': 1.2475523948669434} 08/30/2021 18:22:37 - INFO - __main__ - Step 29159: {'lr': 0.00045959632016585774, 'samples': 5598528, 'steps': 29158, 'loss/train': 1.6949416399002075} 08/30/2021 18:22:39 - INFO - __main__ - Step 29160: {'lr': 0.0004595934275285794, 'samples': 5598720, 'steps': 29159, 'loss/train': 1.3139251470565796} 08/30/2021 18:22:39 - INFO - __main__ - Step 29161: {'lr': 0.00045959053479686143, 'samples': 5598912, 'steps': 29160, 'loss/train': 1.4462741613388062} 08/30/2021 18:22:40 - INFO - __main__ - Step 29162: {'lr': 0.0004595876419707052, 'samples': 5599104, 'steps': 29161, 'loss/train': 1.3975965976715088} 08/30/2021 18:22:40 - INFO - __main__ - Step 29163: {'lr': 0.00045958474905011205, 'samples': 5599296, 'steps': 29162, 'loss/train': 1.3741061687469482} 08/30/2021 18:22:40 - INFO - __main__ - Step 29164: {'lr': 0.0004595818560350832, 'samples': 5599488, 'steps': 29163, 'loss/train': 1.5134464502334595} 08/30/2021 18:22:42 - INFO - __main__ - Step 29165: {'lr': 0.00045957896292562003, 'samples': 5599680, 'steps': 29164, 'loss/train': 0.25229430198669434} 08/30/2021 18:22:43 - INFO - __main__ - Step 29166: {'lr': 0.0004595760697217238, 'samples': 5599872, 'steps': 29165, 'loss/train': 0.8913015723228455} 08/30/2021 18:22:43 - INFO - __main__ - Step 29167: {'lr': 0.0004595731764233958, 'samples': 5600064, 'steps': 29166, 'loss/train': 1.661893367767334} 08/30/2021 18:22:43 - INFO - __main__ - Step 29168: {'lr': 0.0004595702830306374, 'samples': 5600256, 'steps': 29167, 'loss/train': 1.9168347120285034} 08/30/2021 18:22:44 - INFO - __main__ - Step 29169: {'lr': 0.0004595673895434498, 'samples': 5600448, 'steps': 29168, 'loss/train': 0.8361132144927979} 08/30/2021 18:22:45 - INFO - __main__ - Step 29170: {'lr': 0.00045956449596183446, 'samples': 5600640, 'steps': 29169, 'loss/train': 1.3470408916473389} 08/30/2021 18:22:46 - INFO - __main__ - Step 29171: {'lr': 0.00045956160228579257, 'samples': 5600832, 'steps': 29170, 'loss/train': 1.165398120880127} 08/30/2021 18:22:46 - INFO - __main__ - Step 29172: {'lr': 0.00045955870851532545, 'samples': 5601024, 'steps': 29171, 'loss/train': 1.80191171169281} 08/30/2021 18:22:46 - INFO - __main__ - Step 29173: {'lr': 0.0004595558146504344, 'samples': 5601216, 'steps': 29172, 'loss/train': 2.0715763568878174} 08/30/2021 18:22:47 - INFO - __main__ - Step 29174: {'lr': 0.0004595529206911207, 'samples': 5601408, 'steps': 29173, 'loss/train': 1.1101596355438232} 08/30/2021 18:22:48 - INFO - __main__ - Step 29175: {'lr': 0.00045955002663738574, 'samples': 5601600, 'steps': 29174, 'loss/train': 0.09882716089487076} 08/30/2021 18:22:49 - INFO - __main__ - Step 29176: {'lr': 0.0004595471324892307, 'samples': 5601792, 'steps': 29175, 'loss/train': 1.6886543035507202} 08/30/2021 18:22:49 - INFO - __main__ - Step 29177: {'lr': 0.00045954423824665704, 'samples': 5601984, 'steps': 29176, 'loss/train': 1.2996711730957031} 08/30/2021 18:22:49 - INFO - __main__ - Step 29178: {'lr': 0.00045954134390966593, 'samples': 5602176, 'steps': 29177, 'loss/train': 1.4013592004776} 08/30/2021 18:22:50 - INFO - __main__ - Step 29179: {'lr': 0.00045953844947825876, 'samples': 5602368, 'steps': 29178, 'loss/train': 1.9827604293823242} 08/30/2021 18:22:52 - INFO - __main__ - Step 29180: {'lr': 0.0004595355549524368, 'samples': 5602560, 'steps': 29179, 'loss/train': 1.980088233947754} 08/30/2021 18:22:52 - INFO - __main__ - Step 29181: {'lr': 0.0004595326603322013, 'samples': 5602752, 'steps': 29180, 'loss/train': 1.4789692163467407} 08/30/2021 18:22:52 - INFO - __main__ - Step 29182: {'lr': 0.00045952976561755365, 'samples': 5602944, 'steps': 29181, 'loss/train': 1.647566556930542} 08/30/2021 18:22:53 - INFO - __main__ - Step 29183: {'lr': 0.00045952687080849517, 'samples': 5603136, 'steps': 29182, 'loss/train': 0.47545647621154785} 08/30/2021 18:22:53 - INFO - __main__ - Step 29184: {'lr': 0.000459523975905027, 'samples': 5603328, 'steps': 29183, 'loss/train': 1.475440502166748} 08/30/2021 18:22:53 - INFO - __main__ - Step 29185: {'lr': 0.0004595210809071506, 'samples': 5603520, 'steps': 29184, 'loss/train': 0.9235596656799316} 08/30/2021 18:22:55 - INFO - __main__ - Step 29186: {'lr': 0.0004595181858148673, 'samples': 5603712, 'steps': 29185, 'loss/train': 1.172926664352417} 08/30/2021 18:22:55 - INFO - __main__ - Step 29187: {'lr': 0.00045951529062817834, 'samples': 5603904, 'steps': 29186, 'loss/train': 2.1116085052490234} 08/30/2021 18:22:56 - INFO - __main__ - Step 29188: {'lr': 0.00045951239534708496, 'samples': 5604096, 'steps': 29187, 'loss/train': 0.9593750238418579} 08/30/2021 18:22:56 - INFO - __main__ - Step 29189: {'lr': 0.0004595094999715885, 'samples': 5604288, 'steps': 29188, 'loss/train': 1.3687018156051636} 08/30/2021 18:22:56 - INFO - __main__ - Step 29190: {'lr': 0.00045950660450169034, 'samples': 5604480, 'steps': 29189, 'loss/train': 1.3395719528198242} 08/30/2021 18:22:58 - INFO - __main__ - Step 29191: {'lr': 0.0004595037089373918, 'samples': 5604672, 'steps': 29190, 'loss/train': 1.7803689241409302} 08/30/2021 18:22:59 - INFO - __main__ - Step 29192: {'lr': 0.000459500813278694, 'samples': 5604864, 'steps': 29191, 'loss/train': 1.9081834554672241} 08/30/2021 18:22:59 - INFO - __main__ - Step 29193: {'lr': 0.0004594979175255984, 'samples': 5605056, 'steps': 29192, 'loss/train': 1.6339938640594482} 08/30/2021 18:22:59 - INFO - __main__ - Step 29194: {'lr': 0.0004594950216781063, 'samples': 5605248, 'steps': 29193, 'loss/train': 1.5923702716827393} 08/30/2021 18:23:00 - INFO - __main__ - Step 29195: {'lr': 0.000459492125736219, 'samples': 5605440, 'steps': 29194, 'loss/train': 1.3523986339569092} 08/30/2021 18:23:00 - INFO - __main__ - Step 29196: {'lr': 0.00045948922969993777, 'samples': 5605632, 'steps': 29195, 'loss/train': 1.2019221782684326} 08/30/2021 18:23:02 - INFO - __main__ - Step 29197: {'lr': 0.0004594863335692639, 'samples': 5605824, 'steps': 29196, 'loss/train': 1.6492379903793335} 08/30/2021 18:23:02 - INFO - __main__ - Step 29198: {'lr': 0.00045948343734419873, 'samples': 5606016, 'steps': 29197, 'loss/train': 1.7129063606262207} 08/30/2021 18:23:03 - INFO - __main__ - Step 29199: {'lr': 0.00045948054102474357, 'samples': 5606208, 'steps': 29198, 'loss/train': 1.426788091659546} 08/30/2021 18:23:03 - INFO - __main__ - Step 29200: {'lr': 0.00045947764461089967, 'samples': 5606400, 'steps': 29199, 'loss/train': 0.5952116847038269} 08/30/2021 18:23:03 - INFO - __main__ - Step 29201: {'lr': 0.00045947474810266844, 'samples': 5606592, 'steps': 29200, 'loss/train': 1.5822315216064453} 08/30/2021 18:23:05 - INFO - __main__ - Step 29202: {'lr': 0.00045947185150005106, 'samples': 5606784, 'steps': 29201, 'loss/train': 2.031177520751953} 08/30/2021 18:23:05 - INFO - __main__ - Step 29203: {'lr': 0.0004594689548030489, 'samples': 5606976, 'steps': 29202, 'loss/train': 1.9758672714233398} 08/30/2021 18:23:06 - INFO - __main__ - Step 29204: {'lr': 0.0004594660580116633, 'samples': 5607168, 'steps': 29203, 'loss/train': 1.39204740524292} 08/30/2021 18:23:06 - INFO - __main__ - Step 29205: {'lr': 0.00045946316112589546, 'samples': 5607360, 'steps': 29204, 'loss/train': 1.5581611394882202} 08/30/2021 18:23:06 - INFO - __main__ - Step 29206: {'lr': 0.0004594602641457468, 'samples': 5607552, 'steps': 29205, 'loss/train': 1.5157995223999023} 08/30/2021 18:23:08 - INFO - __main__ - Step 29207: {'lr': 0.0004594573670712186, 'samples': 5607744, 'steps': 29206, 'loss/train': 1.6905176639556885} 08/30/2021 18:23:08 - INFO - __main__ - Step 29208: {'lr': 0.0004594544699023121, 'samples': 5607936, 'steps': 29207, 'loss/train': 1.2826634645462036} 08/30/2021 18:23:09 - INFO - __main__ - Step 29209: {'lr': 0.0004594515726390287, 'samples': 5608128, 'steps': 29208, 'loss/train': 0.9444410800933838} 08/30/2021 18:23:09 - INFO - __main__ - Step 29210: {'lr': 0.00045944867528136956, 'samples': 5608320, 'steps': 29209, 'loss/train': 1.087119460105896} 08/30/2021 18:23:09 - INFO - __main__ - Step 29211: {'lr': 0.00045944577782933615, 'samples': 5608512, 'steps': 29210, 'loss/train': 1.0510333776474} 08/30/2021 18:23:10 - INFO - __main__ - Step 29212: {'lr': 0.0004594428802829297, 'samples': 5608704, 'steps': 29211, 'loss/train': 1.255640983581543} 08/30/2021 18:23:11 - INFO - __main__ - Step 29213: {'lr': 0.00045943998264215153, 'samples': 5608896, 'steps': 29212, 'loss/train': 1.7238624095916748} 08/30/2021 18:23:12 - INFO - __main__ - Step 29214: {'lr': 0.0004594370849070029, 'samples': 5609088, 'steps': 29213, 'loss/train': 1.659794569015503} 08/30/2021 18:23:12 - INFO - __main__ - Step 29215: {'lr': 0.00045943418707748517, 'samples': 5609280, 'steps': 29214, 'loss/train': 1.7247980833053589} 08/30/2021 18:23:12 - INFO - __main__ - Step 29216: {'lr': 0.00045943128915359966, 'samples': 5609472, 'steps': 29215, 'loss/train': 1.1598666906356812} 08/30/2021 18:23:13 - INFO - __main__ - Step 29217: {'lr': 0.0004594283911353476, 'samples': 5609664, 'steps': 29216, 'loss/train': 1.5883209705352783} 08/30/2021 18:23:15 - INFO - __main__ - Step 29218: {'lr': 0.0004594254930227303, 'samples': 5609856, 'steps': 29217, 'loss/train': 1.5780142545700073} 08/30/2021 18:23:15 - INFO - __main__ - Step 29219: {'lr': 0.0004594225948157492, 'samples': 5610048, 'steps': 29218, 'loss/train': 1.6981172561645508} 08/30/2021 18:23:16 - INFO - __main__ - Step 29220: {'lr': 0.0004594196965144054, 'samples': 5610240, 'steps': 29219, 'loss/train': 1.4002854824066162} 08/30/2021 18:23:16 - INFO - __main__ - Step 29221: {'lr': 0.0004594167981187004, 'samples': 5610432, 'steps': 29220, 'loss/train': 1.4901771545410156} 08/30/2021 18:23:16 - INFO - __main__ - Step 29222: {'lr': 0.00045941389962863546, 'samples': 5610624, 'steps': 29221, 'loss/train': 1.5295490026474} 08/30/2021 18:23:18 - INFO - __main__ - Step 29223: {'lr': 0.00045941100104421176, 'samples': 5610816, 'steps': 29222, 'loss/train': 1.678505539894104} 08/30/2021 18:23:18 - INFO - __main__ - Step 29224: {'lr': 0.0004594081023654307, 'samples': 5611008, 'steps': 29223, 'loss/train': 1.438895344734192} 08/30/2021 18:23:19 - INFO - __main__ - Step 29225: {'lr': 0.00045940520359229366, 'samples': 5611200, 'steps': 29224, 'loss/train': 1.273938536643982} 08/30/2021 18:23:19 - INFO - __main__ - Step 29226: {'lr': 0.0004594023047248018, 'samples': 5611392, 'steps': 29225, 'loss/train': 1.7192295789718628} 08/30/2021 18:23:19 - INFO - __main__ - Step 29227: {'lr': 0.0004593994057629565, 'samples': 5611584, 'steps': 29226, 'loss/train': 1.2510654926300049} 08/30/2021 18:23:21 - INFO - __main__ - Step 29228: {'lr': 0.000459396506706759, 'samples': 5611776, 'steps': 29227, 'loss/train': 0.9602096676826477} 08/30/2021 18:23:21 - INFO - __main__ - Step 29229: {'lr': 0.00045939360755621074, 'samples': 5611968, 'steps': 29228, 'loss/train': 1.667063593864441} 08/30/2021 18:23:22 - INFO - __main__ - Step 29230: {'lr': 0.00045939070831131293, 'samples': 5612160, 'steps': 29229, 'loss/train': 1.843064546585083} 08/30/2021 18:23:22 - INFO - __main__ - Step 29231: {'lr': 0.00045938780897206686, 'samples': 5612352, 'steps': 29230, 'loss/train': 1.830507755279541} 08/30/2021 18:23:22 - INFO - __main__ - Step 29232: {'lr': 0.000459384909538474, 'samples': 5612544, 'steps': 29231, 'loss/train': 1.4795317649841309} 08/30/2021 18:23:24 - INFO - __main__ - Step 29233: {'lr': 0.00045938201001053546, 'samples': 5612736, 'steps': 29232, 'loss/train': 1.0575584173202515} 08/30/2021 18:23:24 - INFO - __main__ - Step 29234: {'lr': 0.00045937911038825257, 'samples': 5612928, 'steps': 29233, 'loss/train': 1.151182770729065} 08/30/2021 18:23:24 - INFO - __main__ - Step 29235: {'lr': 0.00045937621067162674, 'samples': 5613120, 'steps': 29234, 'loss/train': 1.608346700668335} 08/30/2021 18:23:25 - INFO - __main__ - Step 29236: {'lr': 0.0004593733108606592, 'samples': 5613312, 'steps': 29235, 'loss/train': 1.6283247470855713} 08/30/2021 18:23:25 - INFO - __main__ - Step 29237: {'lr': 0.00045937041095535125, 'samples': 5613504, 'steps': 29236, 'loss/train': 0.992626965045929} 08/30/2021 18:23:27 - INFO - __main__ - Step 29238: {'lr': 0.00045936751095570426, 'samples': 5613696, 'steps': 29237, 'loss/train': 1.8615106344223022} 08/30/2021 18:23:27 - INFO - __main__ - Step 29239: {'lr': 0.0004593646108617195, 'samples': 5613888, 'steps': 29238, 'loss/train': 1.2490863800048828} 08/30/2021 18:23:28 - INFO - __main__ - Step 29240: {'lr': 0.00045936171067339826, 'samples': 5614080, 'steps': 29239, 'loss/train': 0.8721458911895752} 08/30/2021 18:23:28 - INFO - __main__ - Step 29241: {'lr': 0.0004593588103907419, 'samples': 5614272, 'steps': 29240, 'loss/train': 1.4577882289886475} 08/30/2021 18:23:28 - INFO - __main__ - Step 29242: {'lr': 0.00045935591001375163, 'samples': 5614464, 'steps': 29241, 'loss/train': 1.1836299896240234} 08/30/2021 18:23:30 - INFO - __main__ - Step 29243: {'lr': 0.0004593530095424289, 'samples': 5614656, 'steps': 29242, 'loss/train': 1.4437614679336548} 08/30/2021 18:23:30 - INFO - __main__ - Step 29244: {'lr': 0.0004593501089767749, 'samples': 5614848, 'steps': 29243, 'loss/train': 1.8363823890686035} 08/30/2021 18:23:31 - INFO - __main__ - Step 29245: {'lr': 0.00045934720831679093, 'samples': 5615040, 'steps': 29244, 'loss/train': 1.7396713495254517} 08/30/2021 18:23:31 - INFO - __main__ - Step 29246: {'lr': 0.00045934430756247835, 'samples': 5615232, 'steps': 29245, 'loss/train': 1.134104609489441} 08/30/2021 18:23:31 - INFO - __main__ - Step 29247: {'lr': 0.0004593414067138385, 'samples': 5615424, 'steps': 29246, 'loss/train': 1.3727607727050781} 08/30/2021 18:23:33 - INFO - __main__ - Step 29248: {'lr': 0.0004593385057708726, 'samples': 5615616, 'steps': 29247, 'loss/train': 2.2144601345062256} 08/30/2021 18:23:33 - INFO - __main__ - Step 29249: {'lr': 0.00045933560473358206, 'samples': 5615808, 'steps': 29248, 'loss/train': 0.8779964447021484} 08/30/2021 18:23:34 - INFO - __main__ - Step 29250: {'lr': 0.00045933270360196804, 'samples': 5616000, 'steps': 29249, 'loss/train': 0.9211687445640564} 08/30/2021 18:23:34 - INFO - __main__ - Step 29251: {'lr': 0.00045932980237603196, 'samples': 5616192, 'steps': 29250, 'loss/train': 1.9939184188842773} 08/30/2021 18:23:34 - INFO - __main__ - Step 29252: {'lr': 0.0004593269010557751, 'samples': 5616384, 'steps': 29251, 'loss/train': 1.875595211982727} 08/30/2021 18:23:36 - INFO - __main__ - Step 29253: {'lr': 0.00045932399964119884, 'samples': 5616576, 'steps': 29252, 'loss/train': 0.7005326151847839} 08/30/2021 18:23:36 - INFO - __main__ - Step 29254: {'lr': 0.00045932109813230437, 'samples': 5616768, 'steps': 29253, 'loss/train': 0.7504449486732483} 08/30/2021 18:23:37 - INFO - __main__ - Step 29255: {'lr': 0.00045931819652909303, 'samples': 5616960, 'steps': 29254, 'loss/train': 1.004144310951233} 08/30/2021 18:23:37 - INFO - __main__ - Step 29256: {'lr': 0.0004593152948315661, 'samples': 5617152, 'steps': 29255, 'loss/train': 2.0227677822113037} 08/30/2021 18:23:37 - INFO - __main__ - Step 29257: {'lr': 0.000459312393039725, 'samples': 5617344, 'steps': 29256, 'loss/train': 1.3434467315673828} 08/30/2021 18:23:39 - INFO - __main__ - Step 29258: {'lr': 0.0004593094911535709, 'samples': 5617536, 'steps': 29257, 'loss/train': 1.2487927675247192} 08/30/2021 18:23:39 - INFO - __main__ - Step 29259: {'lr': 0.00045930658917310525, 'samples': 5617728, 'steps': 29258, 'loss/train': 1.1003031730651855} 08/30/2021 18:23:40 - INFO - __main__ - Step 29260: {'lr': 0.0004593036870983293, 'samples': 5617920, 'steps': 29259, 'loss/train': 0.5249273777008057} 08/30/2021 18:23:40 - INFO - __main__ - Step 29261: {'lr': 0.0004593007849292442, 'samples': 5618112, 'steps': 29260, 'loss/train': 1.3971539735794067} 08/30/2021 18:23:40 - INFO - __main__ - Step 29262: {'lr': 0.0004592978826658515, 'samples': 5618304, 'steps': 29261, 'loss/train': 1.1266720294952393} 08/30/2021 18:23:41 - INFO - __main__ - Step 29263: {'lr': 0.0004592949803081524, 'samples': 5618496, 'steps': 29262, 'loss/train': 1.3973729610443115} 08/30/2021 18:23:42 - INFO - __main__ - Step 29264: {'lr': 0.0004592920778561481, 'samples': 5618688, 'steps': 29263, 'loss/train': 1.573115587234497} 08/30/2021 18:23:43 - INFO - __main__ - Step 29265: {'lr': 0.00045928917530984014, 'samples': 5618880, 'steps': 29264, 'loss/train': 1.5579097270965576} 08/30/2021 18:23:43 - INFO - __main__ - Step 29266: {'lr': 0.00045928627266922974, 'samples': 5619072, 'steps': 29265, 'loss/train': 1.3227323293685913} 08/30/2021 18:23:43 - INFO - __main__ - Step 29267: {'lr': 0.0004592833699343181, 'samples': 5619264, 'steps': 29266, 'loss/train': 1.3814913034439087} 08/30/2021 18:23:44 - INFO - __main__ - Step 29268: {'lr': 0.0004592804671051066, 'samples': 5619456, 'steps': 29267, 'loss/train': 1.4172732830047607} 08/30/2021 18:23:46 - INFO - __main__ - Step 29269: {'lr': 0.0004592775641815966, 'samples': 5619648, 'steps': 29268, 'loss/train': 1.255063772201538} 08/30/2021 18:23:46 - INFO - __main__ - Step 29270: {'lr': 0.0004592746611637893, 'samples': 5619840, 'steps': 29269, 'loss/train': 1.000472068786621} 08/30/2021 18:23:46 - INFO - __main__ - Step 29271: {'lr': 0.00045927175805168607, 'samples': 5620032, 'steps': 29270, 'loss/train': 1.4347294569015503} 08/30/2021 18:23:47 - INFO - __main__ - Step 29272: {'lr': 0.00045926885484528823, 'samples': 5620224, 'steps': 29271, 'loss/train': 1.3716964721679688} 08/30/2021 18:23:47 - INFO - __main__ - Step 29273: {'lr': 0.0004592659515445971, 'samples': 5620416, 'steps': 29272, 'loss/train': 1.3793617486953735} 08/30/2021 18:23:49 - INFO - __main__ - Step 29274: {'lr': 0.00045926304814961397, 'samples': 5620608, 'steps': 29273, 'loss/train': 2.1355173587799072} 08/30/2021 18:23:49 - INFO - __main__ - Step 29275: {'lr': 0.00045926014466034004, 'samples': 5620800, 'steps': 29274, 'loss/train': 1.9838016033172607} 08/30/2021 18:23:49 - INFO - __main__ - Step 29276: {'lr': 0.0004592572410767768, 'samples': 5620992, 'steps': 29275, 'loss/train': 1.316576600074768} 08/30/2021 18:23:50 - INFO - __main__ - Step 29277: {'lr': 0.0004592543373989255, 'samples': 5621184, 'steps': 29276, 'loss/train': 1.364548921585083} 08/30/2021 18:23:50 - INFO - __main__ - Step 29278: {'lr': 0.0004592514336267874, 'samples': 5621376, 'steps': 29277, 'loss/train': 0.8687638640403748} 08/30/2021 18:23:52 - INFO - __main__ - Step 29279: {'lr': 0.0004592485297603638, 'samples': 5621568, 'steps': 29278, 'loss/train': 1.6683703660964966} 08/30/2021 18:23:52 - INFO - __main__ - Step 29280: {'lr': 0.0004592456257996561, 'samples': 5621760, 'steps': 29279, 'loss/train': 1.223831295967102} 08/30/2021 18:23:53 - INFO - __main__ - Step 29281: {'lr': 0.0004592427217446655, 'samples': 5621952, 'steps': 29280, 'loss/train': 1.568655014038086} 08/30/2021 18:23:53 - INFO - __main__ - Step 29282: {'lr': 0.00045923981759539336, 'samples': 5622144, 'steps': 29281, 'loss/train': 0.8661690950393677} 08/30/2021 18:23:53 - INFO - __main__ - Step 29283: {'lr': 0.000459236913351841, 'samples': 5622336, 'steps': 29282, 'loss/train': 2.0108747482299805} 08/30/2021 18:23:54 - INFO - __main__ - Step 29284: {'lr': 0.0004592340090140097, 'samples': 5622528, 'steps': 29283, 'loss/train': 0.9387965202331543} 08/30/2021 18:23:55 - INFO - __main__ - Step 29285: {'lr': 0.0004592311045819008, 'samples': 5622720, 'steps': 29284, 'loss/train': 1.8075882196426392} 08/30/2021 18:23:56 - INFO - __main__ - Step 29286: {'lr': 0.00045922820005551556, 'samples': 5622912, 'steps': 29285, 'loss/train': 0.9452568292617798} 08/30/2021 18:23:56 - INFO - __main__ - Step 29287: {'lr': 0.0004592252954348554, 'samples': 5623104, 'steps': 29286, 'loss/train': 1.3390796184539795} 08/30/2021 18:23:56 - INFO - __main__ - Step 29288: {'lr': 0.0004592223907199215, 'samples': 5623296, 'steps': 29287, 'loss/train': 1.1554780006408691} 08/30/2021 18:23:57 - INFO - __main__ - Step 29289: {'lr': 0.0004592194859107153, 'samples': 5623488, 'steps': 29288, 'loss/train': 1.4837032556533813} 08/30/2021 18:23:58 - INFO - __main__ - Step 29290: {'lr': 0.0004592165810072379, 'samples': 5623680, 'steps': 29289, 'loss/train': 1.022546648979187} 08/30/2021 18:23:58 - INFO - __main__ - Step 29291: {'lr': 0.00045921367600949077, 'samples': 5623872, 'steps': 29290, 'loss/train': 2.0431230068206787} 08/30/2021 18:23:59 - INFO - __main__ - Step 29292: {'lr': 0.0004592107709174752, 'samples': 5624064, 'steps': 29291, 'loss/train': 1.0799243450164795} 08/30/2021 18:23:59 - INFO - __main__ - Step 29293: {'lr': 0.0004592078657311925, 'samples': 5624256, 'steps': 29292, 'loss/train': 1.9466733932495117} 08/30/2021 18:24:00 - INFO - __main__ - Step 29294: {'lr': 0.000459204960450644, 'samples': 5624448, 'steps': 29293, 'loss/train': 1.696338415145874} 08/30/2021 18:24:01 - INFO - __main__ - Step 29295: {'lr': 0.0004592020550758309, 'samples': 5624640, 'steps': 29294, 'loss/train': 1.9128203392028809} 08/30/2021 18:24:02 - INFO - __main__ - Step 29296: {'lr': 0.0004591991496067546, 'samples': 5624832, 'steps': 29295, 'loss/train': 0.7891136407852173} 08/30/2021 18:24:02 - INFO - __main__ - Step 29297: {'lr': 0.00045919624404341643, 'samples': 5625024, 'steps': 29296, 'loss/train': 0.862982988357544} 08/30/2021 18:24:02 - INFO - __main__ - Step 29298: {'lr': 0.00045919333838581757, 'samples': 5625216, 'steps': 29297, 'loss/train': 1.9168561697006226} 08/30/2021 18:24:03 - INFO - __main__ - Step 29299: {'lr': 0.00045919043263395953, 'samples': 5625408, 'steps': 29298, 'loss/train': 2.242788076400757} 08/30/2021 18:24:05 - INFO - __main__ - Step 29300: {'lr': 0.00045918752678784344, 'samples': 5625600, 'steps': 29299, 'loss/train': 0.987244725227356} 08/30/2021 18:24:05 - INFO - __main__ - Step 29301: {'lr': 0.0004591846208474707, 'samples': 5625792, 'steps': 29300, 'loss/train': 1.4617302417755127} 08/30/2021 18:24:05 - INFO - __main__ - Step 29302: {'lr': 0.00045918171481284256, 'samples': 5625984, 'steps': 29301, 'loss/train': 1.0888047218322754} 08/30/2021 18:24:06 - INFO - __main__ - Step 29303: {'lr': 0.0004591788086839604, 'samples': 5626176, 'steps': 29302, 'loss/train': 1.3656442165374756} 08/30/2021 18:24:06 - INFO - __main__ - Step 29304: {'lr': 0.0004591759024608255, 'samples': 5626368, 'steps': 29303, 'loss/train': 0.27926814556121826} 08/30/2021 18:24:08 - INFO - __main__ - Step 29305: {'lr': 0.0004591729961434392, 'samples': 5626560, 'steps': 29304, 'loss/train': 0.8646825551986694} 08/30/2021 18:24:08 - INFO - __main__ - Step 29306: {'lr': 0.00045917008973180273, 'samples': 5626752, 'steps': 29305, 'loss/train': 1.7475866079330444} 08/30/2021 18:24:09 - INFO - __main__ - Step 29307: {'lr': 0.0004591671832259174, 'samples': 5626944, 'steps': 29306, 'loss/train': 1.5658386945724487} 08/30/2021 18:24:09 - INFO - __main__ - Step 29308: {'lr': 0.00045916427662578464, 'samples': 5627136, 'steps': 29307, 'loss/train': 1.567349910736084} 08/30/2021 18:24:09 - INFO - __main__ - Step 29309: {'lr': 0.00045916136993140574, 'samples': 5627328, 'steps': 29308, 'loss/train': 1.929797649383545} 08/30/2021 18:24:11 - INFO - __main__ - Step 29310: {'lr': 0.00045915846314278187, 'samples': 5627520, 'steps': 29309, 'loss/train': 1.587865948677063} 08/30/2021 18:24:11 - INFO - __main__ - Step 29311: {'lr': 0.0004591555562599144, 'samples': 5627712, 'steps': 29310, 'loss/train': 1.904259443283081} 08/30/2021 18:24:11 - INFO - __main__ - Step 29312: {'lr': 0.00045915264928280476, 'samples': 5627904, 'steps': 29311, 'loss/train': 0.4572484493255615} 08/30/2021 18:24:12 - INFO - __main__ - Step 29313: {'lr': 0.00045914974221145403, 'samples': 5628096, 'steps': 29312, 'loss/train': 1.4013017416000366} 08/30/2021 18:24:12 - INFO - __main__ - Step 29314: {'lr': 0.00045914683504586374, 'samples': 5628288, 'steps': 29313, 'loss/train': 1.0001164674758911} 08/30/2021 18:24:13 - INFO - __main__ - Step 29315: {'lr': 0.0004591439277860351, 'samples': 5628480, 'steps': 29314, 'loss/train': 1.1321221590042114} 08/30/2021 18:24:14 - INFO - __main__ - Step 29316: {'lr': 0.00045914102043196947, 'samples': 5628672, 'steps': 29315, 'loss/train': 1.1323622465133667} 08/30/2021 18:24:14 - INFO - __main__ - Step 29317: {'lr': 0.00045913811298366804, 'samples': 5628864, 'steps': 29316, 'loss/train': 0.9505067467689514} 08/30/2021 18:24:15 - INFO - __main__ - Step 29318: {'lr': 0.0004591352054411323, 'samples': 5629056, 'steps': 29317, 'loss/train': 1.6290580034255981} 08/30/2021 18:24:15 - INFO - __main__ - Step 29319: {'lr': 0.00045913229780436337, 'samples': 5629248, 'steps': 29318, 'loss/train': 1.8942209482192993} 08/30/2021 18:24:16 - INFO - __main__ - Step 29320: {'lr': 0.00045912939007336273, 'samples': 5629440, 'steps': 29319, 'loss/train': 1.6758254766464233} 08/30/2021 18:24:17 - INFO - __main__ - Step 29321: {'lr': 0.0004591264822481316, 'samples': 5629632, 'steps': 29320, 'loss/train': 1.3814494609832764} 08/30/2021 18:24:17 - INFO - __main__ - Step 29322: {'lr': 0.00045912357432867124, 'samples': 5629824, 'steps': 29321, 'loss/train': 1.2043546438217163} 08/30/2021 18:24:18 - INFO - __main__ - Step 29323: {'lr': 0.00045912066631498304, 'samples': 5630016, 'steps': 29322, 'loss/train': 2.0598459243774414} 08/30/2021 18:24:18 - INFO - __main__ - Step 29324: {'lr': 0.00045911775820706835, 'samples': 5630208, 'steps': 29323, 'loss/train': 0.9047432541847229} 08/30/2021 18:24:18 - INFO - __main__ - Step 29325: {'lr': 0.0004591148500049284, 'samples': 5630400, 'steps': 29324, 'loss/train': 0.9984139800071716} 08/30/2021 18:24:21 - INFO - __main__ - Step 29326: {'lr': 0.00045911194170856454, 'samples': 5630592, 'steps': 29325, 'loss/train': 1.636504888534546} 08/30/2021 18:24:21 - INFO - __main__ - Step 29327: {'lr': 0.00045910903331797807, 'samples': 5630784, 'steps': 29326, 'loss/train': 2.1306819915771484} 08/30/2021 18:24:22 - INFO - __main__ - Step 29328: {'lr': 0.00045910612483317025, 'samples': 5630976, 'steps': 29327, 'loss/train': 1.4284075498580933} 08/30/2021 18:24:22 - INFO - __main__ - Step 29329: {'lr': 0.00045910321625414245, 'samples': 5631168, 'steps': 29328, 'loss/train': 1.2354590892791748} 08/30/2021 18:24:22 - INFO - __main__ - Step 29330: {'lr': 0.00045910030758089597, 'samples': 5631360, 'steps': 29329, 'loss/train': 1.5467263460159302} 08/30/2021 18:24:24 - INFO - __main__ - Step 29331: {'lr': 0.00045909739881343215, 'samples': 5631552, 'steps': 29330, 'loss/train': 1.8582510948181152} 08/30/2021 18:24:24 - INFO - __main__ - Step 29332: {'lr': 0.00045909448995175224, 'samples': 5631744, 'steps': 29331, 'loss/train': 1.2985451221466064} 08/30/2021 18:24:25 - INFO - __main__ - Step 29333: {'lr': 0.00045909158099585756, 'samples': 5631936, 'steps': 29332, 'loss/train': 1.6099449396133423} 08/30/2021 18:24:25 - INFO - __main__ - Step 29334: {'lr': 0.00045908867194574955, 'samples': 5632128, 'steps': 29333, 'loss/train': 2.1385371685028076} 08/30/2021 18:24:25 - INFO - __main__ - Step 29335: {'lr': 0.00045908576280142925, 'samples': 5632320, 'steps': 29334, 'loss/train': 1.5409995317459106} 08/30/2021 18:24:26 - INFO - __main__ - Step 29336: {'lr': 0.00045908285356289824, 'samples': 5632512, 'steps': 29335, 'loss/train': 1.1011066436767578} 08/30/2021 18:24:27 - INFO - __main__ - Step 29337: {'lr': 0.0004590799442301577, 'samples': 5632704, 'steps': 29336, 'loss/train': 1.2381199598312378} 08/30/2021 18:24:28 - INFO - __main__ - Step 29338: {'lr': 0.00045907703480320894, 'samples': 5632896, 'steps': 29337, 'loss/train': 1.1147611141204834} 08/30/2021 18:24:28 - INFO - __main__ - Step 29339: {'lr': 0.0004590741252820533, 'samples': 5633088, 'steps': 29338, 'loss/train': 1.4083908796310425} 08/30/2021 18:24:29 - INFO - __main__ - Step 29340: {'lr': 0.00045907121566669216, 'samples': 5633280, 'steps': 29339, 'loss/train': 1.5535962581634521} 08/30/2021 18:24:29 - INFO - __main__ - Step 29341: {'lr': 0.0004590683059571267, 'samples': 5633472, 'steps': 29340, 'loss/train': 1.7197771072387695} 08/30/2021 18:24:30 - INFO - __main__ - Step 29342: {'lr': 0.0004590653961533582, 'samples': 5633664, 'steps': 29341, 'loss/train': 1.7851433753967285} 08/30/2021 18:24:31 - INFO - __main__ - Step 29343: {'lr': 0.00045906248625538816, 'samples': 5633856, 'steps': 29342, 'loss/train': 1.4537101984024048} 08/30/2021 18:24:31 - INFO - __main__ - Step 29344: {'lr': 0.00045905957626321775, 'samples': 5634048, 'steps': 29343, 'loss/train': 1.348261833190918} 08/30/2021 18:24:32 - INFO - __main__ - Step 29345: {'lr': 0.0004590566661768484, 'samples': 5634240, 'steps': 29344, 'loss/train': 1.3653773069381714} 08/30/2021 18:24:32 - INFO - __main__ - Step 29346: {'lr': 0.00045905375599628127, 'samples': 5634432, 'steps': 29345, 'loss/train': 0.8258079290390015} 08/30/2021 18:24:33 - INFO - __main__ - Step 29347: {'lr': 0.00045905084572151774, 'samples': 5634624, 'steps': 29346, 'loss/train': 1.3003286123275757} 08/30/2021 18:24:34 - INFO - __main__ - Step 29348: {'lr': 0.0004590479353525591, 'samples': 5634816, 'steps': 29347, 'loss/train': 1.6447889804840088} 08/30/2021 18:24:34 - INFO - __main__ - Step 29349: {'lr': 0.00045904502488940677, 'samples': 5635008, 'steps': 29348, 'loss/train': 1.581138253211975} 08/30/2021 18:24:35 - INFO - __main__ - Step 29350: {'lr': 0.0004590421143320619, 'samples': 5635200, 'steps': 29349, 'loss/train': 1.915869116783142} 08/30/2021 18:24:35 - INFO - __main__ - Step 29351: {'lr': 0.0004590392036805259, 'samples': 5635392, 'steps': 29350, 'loss/train': 1.9172983169555664} 08/30/2021 18:24:35 - INFO - __main__ - Step 29352: {'lr': 0.0004590362929348001, 'samples': 5635584, 'steps': 29351, 'loss/train': 2.118647336959839} 08/30/2021 18:24:37 - INFO - __main__ - Step 29353: {'lr': 0.00045903338209488575, 'samples': 5635776, 'steps': 29352, 'loss/train': 1.2624213695526123} 08/30/2021 18:24:37 - INFO - __main__ - Step 29354: {'lr': 0.0004590304711607842, 'samples': 5635968, 'steps': 29353, 'loss/train': 0.9841771721839905} 08/30/2021 18:24:38 - INFO - __main__ - Step 29355: {'lr': 0.0004590275601324967, 'samples': 5636160, 'steps': 29354, 'loss/train': 1.7141315937042236} 08/30/2021 18:24:38 - INFO - __main__ - Step 29356: {'lr': 0.0004590246490100246, 'samples': 5636352, 'steps': 29355, 'loss/train': 1.6033127307891846} 08/30/2021 18:24:38 - INFO - __main__ - Step 29357: {'lr': 0.00045902173779336925, 'samples': 5636544, 'steps': 29356, 'loss/train': 1.4778285026550293} 08/30/2021 18:24:40 - INFO - __main__ - Step 29358: {'lr': 0.0004590188264825319, 'samples': 5636736, 'steps': 29357, 'loss/train': 1.6052192449569702} 08/30/2021 18:24:41 - INFO - __main__ - Step 29359: {'lr': 0.00045901591507751393, 'samples': 5636928, 'steps': 29358, 'loss/train': 3.5689525604248047} 08/30/2021 18:24:41 - INFO - __main__ - Step 29360: {'lr': 0.00045901300357831666, 'samples': 5637120, 'steps': 29359, 'loss/train': 9.343769073486328} 08/30/2021 18:24:41 - INFO - __main__ - Step 29361: {'lr': 0.00045901009198494124, 'samples': 5637312, 'steps': 29360, 'loss/train': 1.572585940361023} 08/30/2021 18:24:42 - INFO - __main__ - Step 29362: {'lr': 0.0004590071802973892, 'samples': 5637504, 'steps': 29361, 'loss/train': 1.0418428182601929} 08/30/2021 18:24:42 - INFO - __main__ - Step 29363: {'lr': 0.0004590042685156617, 'samples': 5637696, 'steps': 29362, 'loss/train': 1.0124503374099731} 08/30/2021 18:24:43 - INFO - __main__ - Step 29364: {'lr': 0.0004590013566397601, 'samples': 5637888, 'steps': 29363, 'loss/train': 1.5964131355285645} 08/30/2021 18:24:44 - INFO - __main__ - Step 29365: {'lr': 0.00045899844466968574, 'samples': 5638080, 'steps': 29364, 'loss/train': 1.4689416885375977} 08/30/2021 18:24:44 - INFO - __main__ - Step 29366: {'lr': 0.00045899553260543986, 'samples': 5638272, 'steps': 29365, 'loss/train': 1.0361446142196655} 08/30/2021 18:24:45 - INFO - __main__ - Step 29367: {'lr': 0.0004589926204470238, 'samples': 5638464, 'steps': 29366, 'loss/train': 1.4815704822540283} 08/30/2021 18:24:45 - INFO - __main__ - Step 29368: {'lr': 0.000458989708194439, 'samples': 5638656, 'steps': 29367, 'loss/train': 1.4048242568969727} 08/30/2021 18:24:45 - INFO - __main__ - Step 29369: {'lr': 0.0004589867958476866, 'samples': 5638848, 'steps': 29368, 'loss/train': 1.5980817079544067} 08/30/2021 18:24:47 - INFO - __main__ - Step 29370: {'lr': 0.000458983883406768, 'samples': 5639040, 'steps': 29369, 'loss/train': 1.6755766868591309} 08/30/2021 18:24:48 - INFO - __main__ - Step 29371: {'lr': 0.0004589809708716844, 'samples': 5639232, 'steps': 29370, 'loss/train': 1.5317788124084473} 08/30/2021 18:24:48 - INFO - __main__ - Step 29372: {'lr': 0.0004589780582424373, 'samples': 5639424, 'steps': 29371, 'loss/train': 1.7573219537734985} 08/30/2021 18:24:48 - INFO - __main__ - Step 29373: {'lr': 0.00045897514551902785, 'samples': 5639616, 'steps': 29372, 'loss/train': 1.8937082290649414} 08/30/2021 18:24:49 - INFO - __main__ - Step 29374: {'lr': 0.0004589722327014575, 'samples': 5639808, 'steps': 29373, 'loss/train': 0.046694349497556686} 08/30/2021 18:24:50 - INFO - __main__ - Step 29375: {'lr': 0.0004589693197897274, 'samples': 5640000, 'steps': 29374, 'loss/train': 1.5517034530639648} 08/30/2021 18:24:51 - INFO - __main__ - Step 29376: {'lr': 0.0004589664067838389, 'samples': 5640192, 'steps': 29375, 'loss/train': 1.9797797203063965} 08/30/2021 18:24:51 - INFO - __main__ - Step 29377: {'lr': 0.00045896349368379356, 'samples': 5640384, 'steps': 29376, 'loss/train': 1.8868993520736694} 08/30/2021 18:24:51 - INFO - __main__ - Step 29378: {'lr': 0.00045896058048959233, 'samples': 5640576, 'steps': 29377, 'loss/train': 1.7486587762832642} 08/30/2021 18:24:52 - INFO - __main__ - Step 29379: {'lr': 0.00045895766720123677, 'samples': 5640768, 'steps': 29378, 'loss/train': 1.639821171760559} 08/30/2021 18:24:52 - INFO - __main__ - Step 29380: {'lr': 0.0004589547538187281, 'samples': 5640960, 'steps': 29379, 'loss/train': 1.2783039808273315} 08/30/2021 18:24:54 - INFO - __main__ - Step 29381: {'lr': 0.0004589518403420676, 'samples': 5641152, 'steps': 29380, 'loss/train': 1.9844601154327393} 08/30/2021 18:24:54 - INFO - __main__ - Step 29382: {'lr': 0.00045894892677125667, 'samples': 5641344, 'steps': 29381, 'loss/train': 0.6697326302528381} 08/30/2021 18:24:54 - INFO - __main__ - Step 29383: {'lr': 0.0004589460131062965, 'samples': 5641536, 'steps': 29382, 'loss/train': 1.7014347314834595} 08/30/2021 18:24:55 - INFO - __main__ - Step 29384: {'lr': 0.00045894309934718853, 'samples': 5641728, 'steps': 29383, 'loss/train': 1.9141618013381958} 08/30/2021 18:24:55 - INFO - __main__ - Step 29385: {'lr': 0.00045894018549393404, 'samples': 5641920, 'steps': 29384, 'loss/train': 1.6436084508895874} 08/30/2021 18:24:57 - INFO - __main__ - Step 29386: {'lr': 0.0004589372715465343, 'samples': 5642112, 'steps': 29385, 'loss/train': 1.6123789548873901} 08/30/2021 18:24:57 - INFO - __main__ - Step 29387: {'lr': 0.0004589343575049907, 'samples': 5642304, 'steps': 29386, 'loss/train': 0.6841147541999817} 08/30/2021 18:24:58 - INFO - __main__ - Step 29388: {'lr': 0.0004589314433693044, 'samples': 5642496, 'steps': 29387, 'loss/train': 1.6462756395339966} 08/30/2021 18:24:58 - INFO - __main__ - Step 29389: {'lr': 0.0004589285291394769, 'samples': 5642688, 'steps': 29388, 'loss/train': 3.1464827060699463} 08/30/2021 18:24:58 - INFO - __main__ - Step 29390: {'lr': 0.00045892561481550943, 'samples': 5642880, 'steps': 29389, 'loss/train': 1.0138169527053833} 08/30/2021 18:25:00 - INFO - __main__ - Step 29391: {'lr': 0.0004589227003974032, 'samples': 5643072, 'steps': 29390, 'loss/train': 1.6912964582443237} 08/30/2021 18:25:00 - INFO - __main__ - Step 29392: {'lr': 0.00045891978588515975, 'samples': 5643264, 'steps': 29391, 'loss/train': 2.052468776702881} 08/30/2021 18:25:01 - INFO - __main__ - Step 29393: {'lr': 0.0004589168712787802, 'samples': 5643456, 'steps': 29392, 'loss/train': 1.9062495231628418} 08/30/2021 18:25:01 - INFO - __main__ - Step 29394: {'lr': 0.00045891395657826595, 'samples': 5643648, 'steps': 29393, 'loss/train': 1.2196245193481445} 08/30/2021 18:25:01 - INFO - __main__ - Step 29395: {'lr': 0.0004589110417836183, 'samples': 5643840, 'steps': 29394, 'loss/train': 1.4842808246612549} 08/30/2021 18:25:03 - INFO - __main__ - Step 29396: {'lr': 0.0004589081268948386, 'samples': 5644032, 'steps': 29395, 'loss/train': 1.4386818408966064} 08/30/2021 18:25:04 - INFO - __main__ - Step 29397: {'lr': 0.00045890521191192807, 'samples': 5644224, 'steps': 29396, 'loss/train': 0.10482214391231537} 08/30/2021 18:25:04 - INFO - __main__ - Step 29398: {'lr': 0.0004589022968348881, 'samples': 5644416, 'steps': 29397, 'loss/train': 1.5119930505752563} 08/30/2021 18:25:04 - INFO - __main__ - Step 29399: {'lr': 0.0004588993816637199, 'samples': 5644608, 'steps': 29398, 'loss/train': 1.028935194015503} 08/30/2021 18:25:05 - INFO - __main__ - Step 29400: {'lr': 0.00045889646639842496, 'samples': 5644800, 'steps': 29399, 'loss/train': 1.5866012573242188} 08/30/2021 18:25:06 - INFO - __main__ - Step 29401: {'lr': 0.0004588935510390045, 'samples': 5644992, 'steps': 29400, 'loss/train': 1.3974342346191406} 08/30/2021 18:25:07 - INFO - __main__ - Step 29402: {'lr': 0.00045889063558545974, 'samples': 5645184, 'steps': 29401, 'loss/train': 1.3678932189941406} 08/30/2021 18:25:07 - INFO - __main__ - Step 29403: {'lr': 0.0004588877200377921, 'samples': 5645376, 'steps': 29402, 'loss/train': 2.091094970703125} 08/30/2021 18:25:07 - INFO - __main__ - Step 29404: {'lr': 0.000458884804396003, 'samples': 5645568, 'steps': 29403, 'loss/train': 0.39705920219421387} 08/30/2021 18:25:08 - INFO - __main__ - Step 29405: {'lr': 0.0004588818886600935, 'samples': 5645760, 'steps': 29404, 'loss/train': 1.5316617488861084} 08/30/2021 18:25:09 - INFO - __main__ - Step 29406: {'lr': 0.00045887897283006506, 'samples': 5645952, 'steps': 29405, 'loss/train': 1.222008228302002} 08/30/2021 18:25:10 - INFO - __main__ - Step 29407: {'lr': 0.00045887605690591904, 'samples': 5646144, 'steps': 29406, 'loss/train': 1.6904852390289307} 08/30/2021 18:25:10 - INFO - __main__ - Step 29408: {'lr': 0.0004588731408876566, 'samples': 5646336, 'steps': 29407, 'loss/train': 1.104187250137329} 08/30/2021 18:25:11 - INFO - __main__ - Step 29409: {'lr': 0.00045887022477527923, 'samples': 5646528, 'steps': 29408, 'loss/train': 0.0872500017285347} 08/30/2021 18:25:11 - INFO - __main__ - Step 29410: {'lr': 0.0004588673085687881, 'samples': 5646720, 'steps': 29409, 'loss/train': 3.6997017860412598} 08/30/2021 18:25:11 - INFO - __main__ - Step 29411: {'lr': 0.00045886439226818464, 'samples': 5646912, 'steps': 29410, 'loss/train': 1.5496467351913452} 08/30/2021 18:25:13 - INFO - __main__ - Step 29412: {'lr': 0.0004588614758734701, 'samples': 5647104, 'steps': 29411, 'loss/train': 1.7699309587478638} 08/30/2021 18:25:14 - INFO - __main__ - Step 29413: {'lr': 0.0004588585593846458, 'samples': 5647296, 'steps': 29412, 'loss/train': 0.24823713302612305} 08/30/2021 18:25:14 - INFO - __main__ - Step 29414: {'lr': 0.000458855642801713, 'samples': 5647488, 'steps': 29413, 'loss/train': 1.5737879276275635} 08/30/2021 18:25:14 - INFO - __main__ - Step 29415: {'lr': 0.00045885272612467313, 'samples': 5647680, 'steps': 29414, 'loss/train': 0.5294879078865051} 08/30/2021 18:25:15 - INFO - __main__ - Step 29416: {'lr': 0.0004588498093535274, 'samples': 5647872, 'steps': 29415, 'loss/train': 1.0835024118423462} 08/30/2021 18:25:15 - INFO - __main__ - Step 29417: {'lr': 0.0004588468924882772, 'samples': 5648064, 'steps': 29416, 'loss/train': 1.8900400400161743} 08/30/2021 18:25:17 - INFO - __main__ - Step 29418: {'lr': 0.0004588439755289238, 'samples': 5648256, 'steps': 29417, 'loss/train': 1.8867288827896118} 08/30/2021 18:25:18 - INFO - __main__ - Step 29419: {'lr': 0.00045884105847546853, 'samples': 5648448, 'steps': 29418, 'loss/train': 1.3944100141525269} 08/30/2021 18:25:18 - INFO - __main__ - Step 29420: {'lr': 0.00045883814132791274, 'samples': 5648640, 'steps': 29419, 'loss/train': 1.8383020162582397} 08/30/2021 18:25:18 - INFO - __main__ - Step 29421: {'lr': 0.0004588352240862577, 'samples': 5648832, 'steps': 29420, 'loss/train': 1.4362998008728027} 08/30/2021 18:25:19 - INFO - __main__ - Step 29422: {'lr': 0.0004588323067505047, 'samples': 5649024, 'steps': 29421, 'loss/train': 1.4182742834091187} 08/30/2021 18:25:20 - INFO - __main__ - Step 29423: {'lr': 0.00045882938932065504, 'samples': 5649216, 'steps': 29422, 'loss/train': 1.8948737382888794} 08/30/2021 18:25:21 - INFO - __main__ - Step 29424: {'lr': 0.0004588264717967101, 'samples': 5649408, 'steps': 29423, 'loss/train': 1.822411060333252} 08/30/2021 18:25:21 - INFO - __main__ - Step 29425: {'lr': 0.00045882355417867124, 'samples': 5649600, 'steps': 29424, 'loss/train': 0.877035915851593} 08/30/2021 18:25:21 - INFO - __main__ - Step 29426: {'lr': 0.00045882063646653966, 'samples': 5649792, 'steps': 29425, 'loss/train': 0.966000497341156} 08/30/2021 18:25:22 - INFO - __main__ - Step 29427: {'lr': 0.00045881771866031673, 'samples': 5649984, 'steps': 29426, 'loss/train': 1.2050514221191406} 08/30/2021 18:25:23 - INFO - __main__ - Step 29428: {'lr': 0.00045881480076000376, 'samples': 5650176, 'steps': 29427, 'loss/train': 1.1730661392211914} 08/30/2021 18:25:24 - INFO - __main__ - Step 29429: {'lr': 0.00045881188276560204, 'samples': 5650368, 'steps': 29428, 'loss/train': 1.0626200437545776} 08/30/2021 18:25:24 - INFO - __main__ - Step 29430: {'lr': 0.000458808964677113, 'samples': 5650560, 'steps': 29429, 'loss/train': 1.5473029613494873} 08/30/2021 18:25:24 - INFO - __main__ - Step 29431: {'lr': 0.00045880604649453774, 'samples': 5650752, 'steps': 29430, 'loss/train': 1.8532428741455078} 08/30/2021 18:25:25 - INFO - __main__ - Step 29432: {'lr': 0.00045880312821787775, 'samples': 5650944, 'steps': 29431, 'loss/train': 1.6421610116958618} 08/30/2021 18:25:26 - INFO - __main__ - Step 29433: {'lr': 0.00045880020984713434, 'samples': 5651136, 'steps': 29432, 'loss/train': 1.980318546295166} 08/30/2021 18:25:27 - INFO - __main__ - Step 29434: {'lr': 0.0004587972913823087, 'samples': 5651328, 'steps': 29433, 'loss/train': 1.8178534507751465} 08/30/2021 18:25:27 - INFO - __main__ - Step 29435: {'lr': 0.00045879437282340225, 'samples': 5651520, 'steps': 29434, 'loss/train': 1.2301417589187622} 08/30/2021 18:25:27 - INFO - __main__ - Step 29436: {'lr': 0.00045879145417041623, 'samples': 5651712, 'steps': 29435, 'loss/train': 1.4887574911117554} 08/30/2021 18:25:28 - INFO - __main__ - Step 29437: {'lr': 0.0004587885354233521, 'samples': 5651904, 'steps': 29436, 'loss/train': 1.3315002918243408} 08/30/2021 18:25:29 - INFO - __main__ - Step 29438: {'lr': 0.0004587856165822111, 'samples': 5652096, 'steps': 29437, 'loss/train': 1.6939550638198853} 08/30/2021 18:25:30 - INFO - __main__ - Step 29439: {'lr': 0.0004587826976469944, 'samples': 5652288, 'steps': 29438, 'loss/train': 1.3654032945632935} 08/30/2021 18:25:30 - INFO - __main__ - Step 29440: {'lr': 0.0004587797786177035, 'samples': 5652480, 'steps': 29439, 'loss/train': 1.600990891456604} 08/30/2021 18:25:30 - INFO - __main__ - Step 29441: {'lr': 0.0004587768594943396, 'samples': 5652672, 'steps': 29440, 'loss/train': 1.4263916015625} 08/30/2021 18:25:31 - INFO - __main__ - Step 29442: {'lr': 0.00045877394027690413, 'samples': 5652864, 'steps': 29441, 'loss/train': 1.4905107021331787} 08/30/2021 18:25:31 - INFO - __main__ - Step 29443: {'lr': 0.0004587710209653984, 'samples': 5653056, 'steps': 29442, 'loss/train': 1.9826242923736572} 08/30/2021 18:25:32 - INFO - __main__ - Step 29444: {'lr': 0.0004587681015598235, 'samples': 5653248, 'steps': 29443, 'loss/train': 1.6064846515655518} 08/30/2021 18:25:33 - INFO - __main__ - Step 29445: {'lr': 0.00045876518206018103, 'samples': 5653440, 'steps': 29444, 'loss/train': 1.5464205741882324} 08/30/2021 18:25:33 - INFO - __main__ - Step 29446: {'lr': 0.00045876226246647226, 'samples': 5653632, 'steps': 29445, 'loss/train': 1.4796415567398071} 08/30/2021 18:25:34 - INFO - __main__ - Step 29447: {'lr': 0.0004587593427786983, 'samples': 5653824, 'steps': 29446, 'loss/train': 0.5536571741104126} 08/30/2021 18:25:34 - INFO - __main__ - Step 29448: {'lr': 0.0004587564229968606, 'samples': 5654016, 'steps': 29447, 'loss/train': 1.7594894170761108} 08/30/2021 18:25:35 - INFO - __main__ - Step 29449: {'lr': 0.00045875350312096053, 'samples': 5654208, 'steps': 29448, 'loss/train': 1.3968859910964966} 08/30/2021 18:25:36 - INFO - __main__ - Step 29450: {'lr': 0.0004587505831509994, 'samples': 5654400, 'steps': 29449, 'loss/train': 1.7576875686645508} 08/30/2021 18:25:36 - INFO - __main__ - Step 29451: {'lr': 0.0004587476630869784, 'samples': 5654592, 'steps': 29450, 'loss/train': 1.3094887733459473} 08/30/2021 18:25:37 - INFO - __main__ - Step 29452: {'lr': 0.000458744742928899, 'samples': 5654784, 'steps': 29451, 'loss/train': 1.0282065868377686} 08/30/2021 18:25:37 - INFO - __main__ - Step 29453: {'lr': 0.00045874182267676236, 'samples': 5654976, 'steps': 29452, 'loss/train': 1.4678053855895996} 08/30/2021 18:25:39 - INFO - __main__ - Step 29454: {'lr': 0.0004587389023305699, 'samples': 5655168, 'steps': 29453, 'loss/train': 1.8546245098114014} 08/30/2021 18:25:39 - INFO - __main__ - Step 29455: {'lr': 0.00045873598189032295, 'samples': 5655360, 'steps': 29454, 'loss/train': 0.6133260130882263} 08/30/2021 18:25:39 - INFO - __main__ - Step 29456: {'lr': 0.00045873306135602276, 'samples': 5655552, 'steps': 29455, 'loss/train': 1.0019116401672363} 08/30/2021 18:25:40 - INFO - __main__ - Step 29457: {'lr': 0.00045873014072767064, 'samples': 5655744, 'steps': 29456, 'loss/train': 0.6915490627288818} 08/30/2021 18:25:40 - INFO - __main__ - Step 29458: {'lr': 0.000458727220005268, 'samples': 5655936, 'steps': 29457, 'loss/train': 1.015907645225525} 08/30/2021 18:25:40 - INFO - __main__ - Step 29459: {'lr': 0.00045872429918881606, 'samples': 5656128, 'steps': 29458, 'loss/train': 0.957791268825531} 08/30/2021 18:25:42 - INFO - __main__ - Step 29460: {'lr': 0.00045872137827831616, 'samples': 5656320, 'steps': 29459, 'loss/train': 1.2022985219955444} 08/30/2021 18:25:42 - INFO - __main__ - Step 29461: {'lr': 0.00045871845727376973, 'samples': 5656512, 'steps': 29460, 'loss/train': 1.2923895120620728} 08/30/2021 18:25:43 - INFO - __main__ - Step 29462: {'lr': 0.0004587155361751778, 'samples': 5656704, 'steps': 29461, 'loss/train': 0.9164935350418091} 08/30/2021 18:25:43 - INFO - __main__ - Step 29463: {'lr': 0.000458712614982542, 'samples': 5656896, 'steps': 29462, 'loss/train': 1.6710330247879028} 08/30/2021 18:25:43 - INFO - __main__ - Step 29464: {'lr': 0.00045870969369586346, 'samples': 5657088, 'steps': 29463, 'loss/train': 2.187263011932373} 08/30/2021 18:25:45 - INFO - __main__ - Step 29465: {'lr': 0.00045870677231514356, 'samples': 5657280, 'steps': 29464, 'loss/train': 1.160699486732483} 08/30/2021 18:25:45 - INFO - __main__ - Step 29466: {'lr': 0.0004587038508403837, 'samples': 5657472, 'steps': 29465, 'loss/train': 1.2791696786880493} 08/30/2021 18:25:46 - INFO - __main__ - Step 29467: {'lr': 0.000458700929271585, 'samples': 5657664, 'steps': 29466, 'loss/train': 1.6932755708694458} 08/30/2021 18:25:46 - INFO - __main__ - Step 29468: {'lr': 0.0004586980076087489, 'samples': 5657856, 'steps': 29467, 'loss/train': 1.0619211196899414} 08/30/2021 18:25:46 - INFO - __main__ - Step 29469: {'lr': 0.0004586950858518767, 'samples': 5658048, 'steps': 29468, 'loss/train': 0.9249522686004639} 08/30/2021 18:25:48 - INFO - __main__ - Step 29470: {'lr': 0.0004586921640009697, 'samples': 5658240, 'steps': 29469, 'loss/train': 1.277970790863037} 08/30/2021 18:25:49 - INFO - __main__ - Step 29471: {'lr': 0.0004586892420560294, 'samples': 5658432, 'steps': 29470, 'loss/train': 1.4958105087280273} 08/30/2021 18:25:49 - INFO - __main__ - Step 29472: {'lr': 0.0004586863200170567, 'samples': 5658624, 'steps': 29471, 'loss/train': 1.5742889642715454} 08/30/2021 18:25:50 - INFO - __main__ - Step 29473: {'lr': 0.00045868339788405333, 'samples': 5658816, 'steps': 29472, 'loss/train': 1.2178361415863037} 08/30/2021 18:25:50 - INFO - __main__ - Step 29474: {'lr': 0.0004586804756570204, 'samples': 5659008, 'steps': 29473, 'loss/train': 0.9887757301330566} 08/30/2021 18:25:52 - INFO - __main__ - Step 29475: {'lr': 0.0004586775533359592, 'samples': 5659200, 'steps': 29474, 'loss/train': 1.120389461517334} 08/30/2021 18:25:52 - INFO - __main__ - Step 29476: {'lr': 0.00045867463092087116, 'samples': 5659392, 'steps': 29475, 'loss/train': 1.218640923500061} 08/30/2021 18:25:52 - INFO - __main__ - Step 29477: {'lr': 0.00045867170841175755, 'samples': 5659584, 'steps': 29476, 'loss/train': 1.182020902633667} 08/30/2021 18:25:53 - INFO - __main__ - Step 29478: {'lr': 0.0004586687858086197, 'samples': 5659776, 'steps': 29477, 'loss/train': 0.715477466583252} 08/30/2021 18:25:53 - INFO - __main__ - Step 29479: {'lr': 0.0004586658631114589, 'samples': 5659968, 'steps': 29478, 'loss/train': 1.6136478185653687} 08/30/2021 18:25:55 - INFO - __main__ - Step 29480: {'lr': 0.0004586629403202765, 'samples': 5660160, 'steps': 29479, 'loss/train': 1.5179307460784912} 08/30/2021 18:25:55 - INFO - __main__ - Step 29481: {'lr': 0.0004586600174350738, 'samples': 5660352, 'steps': 29480, 'loss/train': 0.09195207059383392} 08/30/2021 18:25:56 - INFO - __main__ - Step 29482: {'lr': 0.0004586570944558521, 'samples': 5660544, 'steps': 29481, 'loss/train': 1.2771415710449219} 08/30/2021 18:25:56 - INFO - __main__ - Step 29483: {'lr': 0.00045865417138261276, 'samples': 5660736, 'steps': 29482, 'loss/train': 0.06736479699611664} 08/30/2021 18:25:56 - INFO - __main__ - Step 29484: {'lr': 0.00045865124821535704, 'samples': 5660928, 'steps': 29483, 'loss/train': 0.6730112433433533} 08/30/2021 18:25:58 - INFO - __main__ - Step 29485: {'lr': 0.00045864832495408624, 'samples': 5661120, 'steps': 29484, 'loss/train': 2.730788230895996} 08/30/2021 18:25:59 - INFO - __main__ - Step 29486: {'lr': 0.0004586454015988019, 'samples': 5661312, 'steps': 29485, 'loss/train': 0.9634883403778076} 08/30/2021 18:25:59 - INFO - __main__ - Step 29487: {'lr': 0.000458642478149505, 'samples': 5661504, 'steps': 29486, 'loss/train': 1.6337947845458984} 08/30/2021 18:25:59 - INFO - __main__ - Step 29488: {'lr': 0.00045863955460619707, 'samples': 5661696, 'steps': 29487, 'loss/train': 1.7172850370407104} 08/30/2021 18:26:00 - INFO - __main__ - Step 29489: {'lr': 0.0004586366309688793, 'samples': 5661888, 'steps': 29488, 'loss/train': 0.0479944609105587} 08/30/2021 18:26:00 - INFO - __main__ - Step 29490: {'lr': 0.00045863370723755315, 'samples': 5662080, 'steps': 29489, 'loss/train': 0.6843440532684326} 08/30/2021 18:26:01 - INFO - __main__ - Step 29491: {'lr': 0.00045863078341221993, 'samples': 5662272, 'steps': 29490, 'loss/train': 1.3027055263519287} 08/30/2021 18:26:02 - INFO - __main__ - Step 29492: {'lr': 0.0004586278594928808, 'samples': 5662464, 'steps': 29491, 'loss/train': 0.09501402080059052} 08/30/2021 18:26:02 - INFO - __main__ - Step 29493: {'lr': 0.0004586249354795372, 'samples': 5662656, 'steps': 29492, 'loss/train': 1.4198743104934692} 08/30/2021 18:26:03 - INFO - __main__ - Step 29494: {'lr': 0.0004586220113721905, 'samples': 5662848, 'steps': 29493, 'loss/train': 1.2894880771636963} 08/30/2021 18:26:03 - INFO - __main__ - Step 29495: {'lr': 0.0004586190871708419, 'samples': 5663040, 'steps': 29494, 'loss/train': 1.7419530153274536} 08/30/2021 18:26:03 - INFO - __main__ - Step 29496: {'lr': 0.0004586161628754927, 'samples': 5663232, 'steps': 29495, 'loss/train': 1.8950157165527344} 08/30/2021 18:26:06 - INFO - __main__ - Step 29497: {'lr': 0.0004586132384861443, 'samples': 5663424, 'steps': 29496, 'loss/train': 0.32504117488861084} 08/30/2021 18:26:06 - INFO - __main__ - Step 29498: {'lr': 0.000458610314002798, 'samples': 5663616, 'steps': 29497, 'loss/train': 1.5534977912902832} 08/30/2021 18:26:07 - INFO - __main__ - Step 29499: {'lr': 0.0004586073894254551, 'samples': 5663808, 'steps': 29498, 'loss/train': 1.144694447517395} 08/30/2021 18:26:07 - INFO - __main__ - Step 29500: {'lr': 0.000458604464754117, 'samples': 5664000, 'steps': 29499, 'loss/train': 1.829520583152771} 08/30/2021 18:26:07 - INFO - __main__ - Step 29501: {'lr': 0.0004586015399887849, 'samples': 5664192, 'steps': 29500, 'loss/train': 0.6112343668937683} 08/30/2021 18:26:08 - INFO - __main__ - Step 29502: {'lr': 0.0004585986151294602, 'samples': 5664384, 'steps': 29501, 'loss/train': 0.5225926637649536} 08/30/2021 18:26:09 - INFO - __main__ - Step 29503: {'lr': 0.0004585956901761441, 'samples': 5664576, 'steps': 29502, 'loss/train': 0.5445204377174377} 08/30/2021 18:26:10 - INFO - __main__ - Step 29504: {'lr': 0.00045859276512883807, 'samples': 5664768, 'steps': 29503, 'loss/train': 1.7337385416030884} 08/30/2021 18:26:10 - INFO - __main__ - Step 29505: {'lr': 0.00045858983998754336, 'samples': 5664960, 'steps': 29504, 'loss/train': 1.2972288131713867} 08/30/2021 18:26:10 - INFO - __main__ - Step 29506: {'lr': 0.0004585869147522612, 'samples': 5665152, 'steps': 29505, 'loss/train': 1.3692007064819336} 08/30/2021 18:26:11 - INFO - __main__ - Step 29507: {'lr': 0.00045858398942299306, 'samples': 5665344, 'steps': 29506, 'loss/train': 2.033146858215332} 08/30/2021 18:26:12 - INFO - __main__ - Step 29508: {'lr': 0.0004585810639997402, 'samples': 5665536, 'steps': 29507, 'loss/train': 1.3620285987854004} 08/30/2021 18:26:13 - INFO - __main__ - Step 29509: {'lr': 0.0004585781384825039, 'samples': 5665728, 'steps': 29508, 'loss/train': 1.6803773641586304} 08/30/2021 18:26:13 - INFO - __main__ - Step 29510: {'lr': 0.00045857521287128556, 'samples': 5665920, 'steps': 29509, 'loss/train': 0.9989269971847534} 08/30/2021 18:26:13 - INFO - __main__ - Step 29511: {'lr': 0.0004585722871660864, 'samples': 5666112, 'steps': 29510, 'loss/train': 1.6287176609039307} 08/30/2021 18:26:14 - INFO - __main__ - Step 29512: {'lr': 0.0004585693613669078, 'samples': 5666304, 'steps': 29511, 'loss/train': 1.455241322517395} 08/30/2021 18:26:15 - INFO - __main__ - Step 29513: {'lr': 0.0004585664354737511, 'samples': 5666496, 'steps': 29512, 'loss/train': 1.7103053331375122} 08/30/2021 18:26:16 - INFO - __main__ - Step 29514: {'lr': 0.0004585635094866175, 'samples': 5666688, 'steps': 29513, 'loss/train': 1.5950748920440674} 08/30/2021 18:26:16 - INFO - __main__ - Step 29515: {'lr': 0.0004585605834055084, 'samples': 5666880, 'steps': 29514, 'loss/train': 0.6312817335128784} 08/30/2021 18:26:16 - INFO - __main__ - Step 29516: {'lr': 0.00045855765723042526, 'samples': 5667072, 'steps': 29515, 'loss/train': 1.4721404314041138} 08/30/2021 18:26:17 - INFO - __main__ - Step 29517: {'lr': 0.00045855473096136914, 'samples': 5667264, 'steps': 29516, 'loss/train': 1.3437658548355103} 08/30/2021 18:26:18 - INFO - __main__ - Step 29518: {'lr': 0.00045855180459834153, 'samples': 5667456, 'steps': 29517, 'loss/train': 1.1570112705230713} 08/30/2021 18:26:19 - INFO - __main__ - Step 29519: {'lr': 0.0004585488781413437, 'samples': 5667648, 'steps': 29518, 'loss/train': 1.4586642980575562} 08/30/2021 18:26:19 - INFO - __main__ - Step 29520: {'lr': 0.00045854595159037695, 'samples': 5667840, 'steps': 29519, 'loss/train': 1.6733678579330444} 08/30/2021 18:26:19 - INFO - __main__ - Step 29521: {'lr': 0.0004585430249454425, 'samples': 5668032, 'steps': 29520, 'loss/train': 1.654155969619751} 08/30/2021 18:26:20 - INFO - __main__ - Step 29522: {'lr': 0.000458540098206542, 'samples': 5668224, 'steps': 29521, 'loss/train': 1.9122824668884277} 08/30/2021 18:26:21 - INFO - __main__ - Step 29523: {'lr': 0.00045853717137367634, 'samples': 5668416, 'steps': 29522, 'loss/train': 1.2130546569824219} 08/30/2021 18:26:22 - INFO - __main__ - Step 29524: {'lr': 0.0004585342444468471, 'samples': 5668608, 'steps': 29523, 'loss/train': 1.0073513984680176} 08/30/2021 18:26:22 - INFO - __main__ - Step 29525: {'lr': 0.00045853131742605563, 'samples': 5668800, 'steps': 29524, 'loss/train': 1.2143741846084595} 08/30/2021 18:26:22 - INFO - __main__ - Step 29526: {'lr': 0.0004585283903113031, 'samples': 5668992, 'steps': 29525, 'loss/train': 1.5078721046447754} 08/30/2021 18:26:23 - INFO - __main__ - Step 29527: {'lr': 0.00045852546310259093, 'samples': 5669184, 'steps': 29526, 'loss/train': 1.5619242191314697} 08/30/2021 18:26:23 - INFO - __main__ - Step 29528: {'lr': 0.00045852253579992043, 'samples': 5669376, 'steps': 29527, 'loss/train': 1.0531502962112427} 08/30/2021 18:26:25 - INFO - __main__ - Step 29529: {'lr': 0.0004585196084032928, 'samples': 5669568, 'steps': 29528, 'loss/train': 1.3731187582015991} 08/30/2021 18:26:26 - INFO - __main__ - Step 29530: {'lr': 0.0004585166809127095, 'samples': 5669760, 'steps': 29529, 'loss/train': 1.3357107639312744} 08/30/2021 18:26:26 - INFO - __main__ - Step 29531: {'lr': 0.0004585137533281718, 'samples': 5669952, 'steps': 29530, 'loss/train': 0.8998951315879822} 08/30/2021 18:26:27 - INFO - __main__ - Step 29532: {'lr': 0.00045851082564968103, 'samples': 5670144, 'steps': 29531, 'loss/train': 1.4392424821853638} 08/30/2021 18:26:27 - INFO - __main__ - Step 29533: {'lr': 0.0004585078978772385, 'samples': 5670336, 'steps': 29532, 'loss/train': 1.5617882013320923} 08/30/2021 18:26:29 - INFO - __main__ - Step 29534: {'lr': 0.0004585049700108455, 'samples': 5670528, 'steps': 29533, 'loss/train': 1.0490193367004395} 08/30/2021 18:26:29 - INFO - __main__ - Step 29535: {'lr': 0.00045850204205050344, 'samples': 5670720, 'steps': 29534, 'loss/train': 1.2691662311553955} 08/30/2021 18:26:30 - INFO - __main__ - Step 29536: {'lr': 0.0004584991139962135, 'samples': 5670912, 'steps': 29535, 'loss/train': 1.3712712526321411} 08/30/2021 18:26:30 - INFO - __main__ - Step 29537: {'lr': 0.00045849618584797717, 'samples': 5671104, 'steps': 29536, 'loss/train': 1.5839011669158936} 08/30/2021 18:26:30 - INFO - __main__ - Step 29538: {'lr': 0.0004584932576057956, 'samples': 5671296, 'steps': 29537, 'loss/train': 0.07783497124910355} 08/30/2021 18:26:31 - INFO - __main__ - Step 29539: {'lr': 0.00045849032926967016, 'samples': 5671488, 'steps': 29538, 'loss/train': 0.04371124133467674} 08/30/2021 18:26:32 - INFO - __main__ - Step 29540: {'lr': 0.0004584874008396023, 'samples': 5671680, 'steps': 29539, 'loss/train': 1.6364810466766357} 08/30/2021 18:26:33 - INFO - __main__ - Step 29541: {'lr': 0.00045848447231559315, 'samples': 5671872, 'steps': 29540, 'loss/train': 1.350569248199463} 08/30/2021 18:26:33 - INFO - __main__ - Step 29542: {'lr': 0.00045848154369764415, 'samples': 5672064, 'steps': 29541, 'loss/train': 1.412458896636963} 08/30/2021 18:26:33 - INFO - __main__ - Step 29543: {'lr': 0.0004584786149857566, 'samples': 5672256, 'steps': 29542, 'loss/train': 1.7077301740646362} 08/30/2021 18:26:34 - INFO - __main__ - Step 29544: {'lr': 0.00045847568617993174, 'samples': 5672448, 'steps': 29543, 'loss/train': 1.4265661239624023} 08/30/2021 18:26:35 - INFO - __main__ - Step 29545: {'lr': 0.000458472757280171, 'samples': 5672640, 'steps': 29544, 'loss/train': 1.2461732625961304} 08/30/2021 18:26:36 - INFO - __main__ - Step 29546: {'lr': 0.0004584698282864757, 'samples': 5672832, 'steps': 29545, 'loss/train': 0.269072026014328} 08/30/2021 18:26:36 - INFO - __main__ - Step 29547: {'lr': 0.000458466899198847, 'samples': 5673024, 'steps': 29546, 'loss/train': 0.7153891324996948} 08/30/2021 18:26:36 - INFO - __main__ - Step 29548: {'lr': 0.0004584639700172863, 'samples': 5673216, 'steps': 29547, 'loss/train': 1.3654835224151611} 08/30/2021 18:26:37 - INFO - __main__ - Step 29549: {'lr': 0.00045846104074179504, 'samples': 5673408, 'steps': 29548, 'loss/train': 2.0023417472839355} 08/30/2021 18:26:37 - INFO - __main__ - Step 29550: {'lr': 0.00045845811137237445, 'samples': 5673600, 'steps': 29549, 'loss/train': 1.5485824346542358} 08/30/2021 18:26:39 - INFO - __main__ - Step 29551: {'lr': 0.0004584551819090259, 'samples': 5673792, 'steps': 29550, 'loss/train': 0.6402052640914917} 08/30/2021 18:26:39 - INFO - __main__ - Step 29552: {'lr': 0.0004584522523517506, 'samples': 5673984, 'steps': 29551, 'loss/train': 1.4533443450927734} 08/30/2021 18:26:40 - INFO - __main__ - Step 29553: {'lr': 0.00045844932270054997, 'samples': 5674176, 'steps': 29552, 'loss/train': 1.2149449586868286} 08/30/2021 18:26:40 - INFO - __main__ - Step 29554: {'lr': 0.00045844639295542525, 'samples': 5674368, 'steps': 29553, 'loss/train': 0.05344089865684509} 08/30/2021 18:26:40 - INFO - __main__ - Step 29555: {'lr': 0.0004584434631163779, 'samples': 5674560, 'steps': 29554, 'loss/train': 3.456982135772705} 08/30/2021 18:26:41 - INFO - __main__ - Step 29556: {'lr': 0.000458440533183409, 'samples': 5674752, 'steps': 29555, 'loss/train': 2.0972509384155273} 08/30/2021 18:26:42 - INFO - __main__ - Step 29557: {'lr': 0.0004584376031565201, 'samples': 5674944, 'steps': 29556, 'loss/train': 1.2078018188476562} 08/30/2021 18:26:43 - INFO - __main__ - Step 29558: {'lr': 0.0004584346730357124, 'samples': 5675136, 'steps': 29557, 'loss/train': 1.2920725345611572} 08/30/2021 18:26:43 - INFO - __main__ - Step 29559: {'lr': 0.0004584317428209872, 'samples': 5675328, 'steps': 29558, 'loss/train': 0.9063498377799988} 08/30/2021 18:26:43 - INFO - __main__ - Step 29560: {'lr': 0.0004584288125123459, 'samples': 5675520, 'steps': 29559, 'loss/train': 0.9930772185325623} 08/30/2021 18:26:44 - INFO - __main__ - Step 29561: {'lr': 0.0004584258821097899, 'samples': 5675712, 'steps': 29560, 'loss/train': 1.6734131574630737} 08/30/2021 18:26:45 - INFO - __main__ - Step 29562: {'lr': 0.0004584229516133203, 'samples': 5675904, 'steps': 29561, 'loss/train': 1.4462260007858276} 08/30/2021 18:26:46 - INFO - __main__ - Step 29563: {'lr': 0.00045842002102293856, 'samples': 5676096, 'steps': 29562, 'loss/train': 1.4785751104354858} 08/30/2021 18:26:46 - INFO - __main__ - Step 29564: {'lr': 0.000458417090338646, 'samples': 5676288, 'steps': 29563, 'loss/train': 2.1335296630859375} 08/30/2021 18:26:46 - INFO - __main__ - Step 29565: {'lr': 0.00045841415956044394, 'samples': 5676480, 'steps': 29564, 'loss/train': 1.2591972351074219} 08/30/2021 18:26:47 - INFO - __main__ - Step 29566: {'lr': 0.0004584112286883336, 'samples': 5676672, 'steps': 29565, 'loss/train': 0.08477567136287689} 08/30/2021 18:26:48 - INFO - __main__ - Step 29567: {'lr': 0.0004584082977223164, 'samples': 5676864, 'steps': 29566, 'loss/train': 1.3854612112045288} 08/30/2021 18:26:48 - INFO - __main__ - Step 29568: {'lr': 0.0004584053666623937, 'samples': 5677056, 'steps': 29567, 'loss/train': 1.5562198162078857} 08/30/2021 18:26:49 - INFO - __main__ - Step 29569: {'lr': 0.00045840243550856666, 'samples': 5677248, 'steps': 29568, 'loss/train': 1.6854863166809082} 08/30/2021 18:26:49 - INFO - __main__ - Step 29570: {'lr': 0.00045839950426083677, 'samples': 5677440, 'steps': 29569, 'loss/train': 1.2686117887496948} 08/30/2021 18:26:50 - INFO - __main__ - Step 29571: {'lr': 0.0004583965729192052, 'samples': 5677632, 'steps': 29570, 'loss/train': 1.0729773044586182} 08/30/2021 18:26:51 - INFO - __main__ - Step 29572: {'lr': 0.00045839364148367345, 'samples': 5677824, 'steps': 29571, 'loss/train': 1.7262150049209595} 08/30/2021 18:26:52 - INFO - __main__ - Step 29573: {'lr': 0.00045839070995424273, 'samples': 5678016, 'steps': 29572, 'loss/train': 1.5303738117218018} 08/30/2021 18:26:52 - INFO - __main__ - Step 29574: {'lr': 0.00045838777833091425, 'samples': 5678208, 'steps': 29573, 'loss/train': 1.3324564695358276} 08/30/2021 18:26:53 - INFO - __main__ - Step 29575: {'lr': 0.00045838484661368963, 'samples': 5678400, 'steps': 29574, 'loss/train': 1.9263807535171509} 08/30/2021 18:26:53 - INFO - __main__ - Step 29576: {'lr': 0.00045838191480256985, 'samples': 5678592, 'steps': 29575, 'loss/train': 0.2690824866294861} 08/30/2021 18:26:53 - INFO - __main__ - Step 29577: {'lr': 0.00045837898289755654, 'samples': 5678784, 'steps': 29576, 'loss/train': 0.047330599278211594} 08/30/2021 18:26:55 - INFO - __main__ - Step 29578: {'lr': 0.0004583760508986508, 'samples': 5678976, 'steps': 29577, 'loss/train': 1.3086485862731934} 08/30/2021 18:26:55 - INFO - __main__ - Step 29579: {'lr': 0.000458373118805854, 'samples': 5679168, 'steps': 29578, 'loss/train': 1.364263653755188} 08/30/2021 18:26:56 - INFO - __main__ - Step 29580: {'lr': 0.00045837018661916754, 'samples': 5679360, 'steps': 29579, 'loss/train': 1.464563250541687} 08/30/2021 18:26:56 - INFO - __main__ - Step 29581: {'lr': 0.00045836725433859266, 'samples': 5679552, 'steps': 29580, 'loss/train': 1.7931222915649414} 08/30/2021 18:26:56 - INFO - __main__ - Step 29582: {'lr': 0.0004583643219641307, 'samples': 5679744, 'steps': 29581, 'loss/train': 1.1459400653839111} 08/30/2021 18:26:59 - INFO - __main__ - Step 29583: {'lr': 0.00045836138949578297, 'samples': 5679936, 'steps': 29582, 'loss/train': 1.4620206356048584} 08/30/2021 18:26:59 - INFO - __main__ - Step 29584: {'lr': 0.00045835845693355096, 'samples': 5680128, 'steps': 29583, 'loss/train': 1.4040746688842773} 08/30/2021 18:26:59 - INFO - __main__ - Step 29585: {'lr': 0.00045835552427743567, 'samples': 5680320, 'steps': 29584, 'loss/train': 1.2760283946990967} 08/30/2021 18:27:00 - INFO - __main__ - Step 29586: {'lr': 0.00045835259152743866, 'samples': 5680512, 'steps': 29585, 'loss/train': 1.6704434156417847} 08/30/2021 18:27:00 - INFO - __main__ - Step 29587: {'lr': 0.0004583496586835612, 'samples': 5680704, 'steps': 29586, 'loss/train': 0.11828450858592987} 08/30/2021 18:27:01 - INFO - __main__ - Step 29588: {'lr': 0.0004583467257458046, 'samples': 5680896, 'steps': 29587, 'loss/train': 1.6639827489852905} 08/30/2021 18:27:02 - INFO - __main__ - Step 29589: {'lr': 0.00045834379271417013, 'samples': 5681088, 'steps': 29588, 'loss/train': 1.6343023777008057} 08/30/2021 18:27:02 - INFO - __main__ - Step 29590: {'lr': 0.0004583408595886592, 'samples': 5681280, 'steps': 29589, 'loss/train': 1.898882508277893} 08/30/2021 18:27:03 - INFO - __main__ - Step 29591: {'lr': 0.0004583379263692732, 'samples': 5681472, 'steps': 29590, 'loss/train': 2.0787954330444336} 08/30/2021 18:27:03 - INFO - __main__ - Step 29592: {'lr': 0.0004583349930560132, 'samples': 5681664, 'steps': 29591, 'loss/train': 2.2682175636291504} 08/30/2021 18:27:06 - INFO - __main__ - Step 29593: {'lr': 0.0004583320596488807, 'samples': 5681856, 'steps': 29592, 'loss/train': 1.465067982673645} 08/30/2021 18:27:06 - INFO - __main__ - Step 29594: {'lr': 0.000458329126147877, 'samples': 5682048, 'steps': 29593, 'loss/train': 1.508357048034668} 08/30/2021 18:27:06 - INFO - __main__ - Step 29595: {'lr': 0.00045832619255300344, 'samples': 5682240, 'steps': 29594, 'loss/train': 1.2611652612686157} 08/30/2021 18:27:07 - INFO - __main__ - Step 29596: {'lr': 0.00045832325886426125, 'samples': 5682432, 'steps': 29595, 'loss/train': 1.4101680517196655} 08/30/2021 18:27:07 - INFO - __main__ - Step 29597: {'lr': 0.0004583203250816518, 'samples': 5682624, 'steps': 29596, 'loss/train': 0.9930189847946167} 08/30/2021 18:27:07 - INFO - __main__ - Step 29598: {'lr': 0.0004583173912051765, 'samples': 5682816, 'steps': 29597, 'loss/train': 0.9272570610046387} 08/30/2021 18:27:08 - INFO - __main__ - Step 29599: {'lr': 0.00045831445723483656, 'samples': 5683008, 'steps': 29598, 'loss/train': 0.8228551745414734} 08/30/2021 18:27:08 - INFO - __main__ - Step 29600: {'lr': 0.0004583115231706334, 'samples': 5683200, 'steps': 29599, 'loss/train': 0.8430296182632446} 08/30/2021 18:27:10 - INFO - __main__ - Step 29601: {'lr': 0.0004583085890125682, 'samples': 5683392, 'steps': 29600, 'loss/train': 0.9320297241210938} 08/30/2021 18:27:10 - INFO - __main__ - Step 29602: {'lr': 0.0004583056547606424, 'samples': 5683584, 'steps': 29601, 'loss/train': 1.4654074907302856} 08/30/2021 18:27:10 - INFO - __main__ - Step 29603: {'lr': 0.0004583027204148573, 'samples': 5683776, 'steps': 29602, 'loss/train': 1.8659985065460205} 08/30/2021 18:27:11 - INFO - __main__ - Step 29604: {'lr': 0.0004582997859752142, 'samples': 5683968, 'steps': 29603, 'loss/train': 1.5351128578186035} 08/30/2021 18:27:11 - INFO - __main__ - Step 29605: {'lr': 0.0004582968514417144, 'samples': 5684160, 'steps': 29604, 'loss/train': 1.4761664867401123} 08/30/2021 18:27:14 - INFO - __main__ - Step 29606: {'lr': 0.00045829391681435926, 'samples': 5684352, 'steps': 29605, 'loss/train': 1.10630464553833} 08/30/2021 18:27:14 - INFO - __main__ - Step 29607: {'lr': 0.0004582909820931501, 'samples': 5684544, 'steps': 29606, 'loss/train': 1.7708563804626465} 08/30/2021 18:27:15 - INFO - __main__ - Step 29608: {'lr': 0.00045828804727808824, 'samples': 5684736, 'steps': 29607, 'loss/train': 1.4790401458740234} 08/30/2021 18:27:15 - INFO - __main__ - Step 29609: {'lr': 0.000458285112369175, 'samples': 5684928, 'steps': 29608, 'loss/train': 1.481463074684143} 08/30/2021 18:27:15 - INFO - __main__ - Step 29610: {'lr': 0.0004582821773664118, 'samples': 5685120, 'steps': 29609, 'loss/train': 1.332221269607544} 08/30/2021 18:27:16 - INFO - __main__ - Step 29611: {'lr': 0.0004582792422697997, 'samples': 5685312, 'steps': 29610, 'loss/train': 1.6628471612930298} 08/30/2021 18:27:16 - INFO - __main__ - Step 29612: {'lr': 0.0004582763070793403, 'samples': 5685504, 'steps': 29611, 'loss/train': 2.3646347522735596} 08/30/2021 18:27:18 - INFO - __main__ - Step 29613: {'lr': 0.0004582733717950347, 'samples': 5685696, 'steps': 29612, 'loss/train': 5.348879337310791} 08/30/2021 18:27:18 - INFO - __main__ - Step 29614: {'lr': 0.00045827043641688444, 'samples': 5685888, 'steps': 29613, 'loss/train': 2.010775327682495} 08/30/2021 18:27:18 - INFO - __main__ - Step 29615: {'lr': 0.00045826750094489065, 'samples': 5686080, 'steps': 29614, 'loss/train': 1.7838435173034668} 08/30/2021 18:27:19 - INFO - __main__ - Step 29616: {'lr': 0.00045826456537905483, 'samples': 5686272, 'steps': 29615, 'loss/train': 1.4085440635681152} 08/30/2021 18:27:19 - INFO - __main__ - Step 29617: {'lr': 0.0004582616297193781, 'samples': 5686464, 'steps': 29616, 'loss/train': 1.5924851894378662} 08/30/2021 18:27:19 - INFO - __main__ - Step 29618: {'lr': 0.000458258693965862, 'samples': 5686656, 'steps': 29617, 'loss/train': 1.6739227771759033} 08/30/2021 18:27:21 - INFO - __main__ - Step 29619: {'lr': 0.0004582557581185077, 'samples': 5686848, 'steps': 29618, 'loss/train': 1.4708425998687744} 08/30/2021 18:27:21 - INFO - __main__ - Step 29620: {'lr': 0.00045825282217731655, 'samples': 5687040, 'steps': 29619, 'loss/train': 1.946986436843872} 08/30/2021 18:27:22 - INFO - __main__ - Step 29621: {'lr': 0.00045824988614228995, 'samples': 5687232, 'steps': 29620, 'loss/train': 2.37992262840271} 08/30/2021 18:27:22 - INFO - __main__ - Step 29622: {'lr': 0.0004582469500134292, 'samples': 5687424, 'steps': 29621, 'loss/train': 1.5118401050567627} 08/30/2021 18:27:22 - INFO - __main__ - Step 29623: {'lr': 0.00045824401379073544, 'samples': 5687616, 'steps': 29622, 'loss/train': 1.385564923286438} 08/30/2021 18:27:24 - INFO - __main__ - Step 29624: {'lr': 0.0004582410774742103, 'samples': 5687808, 'steps': 29623, 'loss/train': 1.0063823461532593} 08/30/2021 18:27:25 - INFO - __main__ - Step 29625: {'lr': 0.00045823814106385485, 'samples': 5688000, 'steps': 29624, 'loss/train': 1.956981897354126} 08/30/2021 18:27:25 - INFO - __main__ - Step 29626: {'lr': 0.0004582352045596705, 'samples': 5688192, 'steps': 29625, 'loss/train': 1.6747437715530396} 08/30/2021 18:27:26 - INFO - __main__ - Step 29627: {'lr': 0.0004582322679616586, 'samples': 5688384, 'steps': 29626, 'loss/train': 1.8953553438186646} 08/30/2021 18:27:26 - INFO - __main__ - Step 29628: {'lr': 0.0004582293312698205, 'samples': 5688576, 'steps': 29627, 'loss/train': 1.556592583656311} 08/30/2021 18:27:26 - INFO - __main__ - Step 29629: {'lr': 0.00045822639448415736, 'samples': 5688768, 'steps': 29628, 'loss/train': 2.9476187229156494} 08/30/2021 18:27:28 - INFO - __main__ - Step 29630: {'lr': 0.0004582234576046707, 'samples': 5688960, 'steps': 29629, 'loss/train': 0.1175139769911766} 08/30/2021 18:27:28 - INFO - __main__ - Step 29631: {'lr': 0.00045822052063136177, 'samples': 5689152, 'steps': 29630, 'loss/train': 1.4863507747650146} 08/30/2021 18:27:29 - INFO - __main__ - Step 29632: {'lr': 0.0004582175835642319, 'samples': 5689344, 'steps': 29631, 'loss/train': 1.4567972421646118} 08/30/2021 18:27:29 - INFO - __main__ - Step 29633: {'lr': 0.0004582146464032824, 'samples': 5689536, 'steps': 29632, 'loss/train': 2.4604380130767822} 08/30/2021 18:27:29 - INFO - __main__ - Step 29634: {'lr': 0.0004582117091485145, 'samples': 5689728, 'steps': 29633, 'loss/train': 1.3318003416061401} 08/30/2021 18:27:31 - INFO - __main__ - Step 29635: {'lr': 0.0004582087717999297, 'samples': 5689920, 'steps': 29634, 'loss/train': 1.550450325012207} 08/30/2021 18:27:31 - INFO - __main__ - Step 29636: {'lr': 0.0004582058343575292, 'samples': 5690112, 'steps': 29635, 'loss/train': 1.9619405269622803} 08/30/2021 18:27:32 - INFO - __main__ - Step 29637: {'lr': 0.00045820289682131437, 'samples': 5690304, 'steps': 29636, 'loss/train': 1.9311447143554688} 08/30/2021 18:27:32 - INFO - __main__ - Step 29638: {'lr': 0.0004581999591912865, 'samples': 5690496, 'steps': 29637, 'loss/train': 1.916884183883667} 08/30/2021 18:27:32 - INFO - __main__ - Step 29639: {'lr': 0.000458197021467447, 'samples': 5690688, 'steps': 29638, 'loss/train': 1.9588192701339722} 08/30/2021 18:27:34 - INFO - __main__ - Step 29640: {'lr': 0.00045819408364979714, 'samples': 5690880, 'steps': 29639, 'loss/train': 1.8672581911087036} 08/30/2021 18:27:34 - INFO - __main__ - Step 29641: {'lr': 0.0004581911457383382, 'samples': 5691072, 'steps': 29640, 'loss/train': 1.2657244205474854} 08/30/2021 18:27:35 - INFO - __main__ - Step 29642: {'lr': 0.0004581882077330716, 'samples': 5691264, 'steps': 29641, 'loss/train': 2.0068185329437256} 08/30/2021 18:27:35 - INFO - __main__ - Step 29643: {'lr': 0.0004581852696339985, 'samples': 5691456, 'steps': 29642, 'loss/train': 1.3693592548370361} 08/30/2021 18:27:35 - INFO - __main__ - Step 29644: {'lr': 0.00045818233144112044, 'samples': 5691648, 'steps': 29643, 'loss/train': 1.9072682857513428} 08/30/2021 18:27:37 - INFO - __main__ - Step 29645: {'lr': 0.00045817939315443855, 'samples': 5691840, 'steps': 29644, 'loss/train': 1.1360223293304443} 08/30/2021 18:27:38 - INFO - __main__ - Step 29646: {'lr': 0.0004581764547739543, 'samples': 5692032, 'steps': 29645, 'loss/train': 1.7882003784179688} 08/30/2021 18:27:38 - INFO - __main__ - Step 29647: {'lr': 0.00045817351629966896, 'samples': 5692224, 'steps': 29646, 'loss/train': 2.02164626121521} 08/30/2021 18:27:38 - INFO - __main__ - Step 29648: {'lr': 0.00045817057773158375, 'samples': 5692416, 'steps': 29647, 'loss/train': 1.7786821126937866} 08/30/2021 18:27:39 - INFO - __main__ - Step 29649: {'lr': 0.0004581676390697002, 'samples': 5692608, 'steps': 29648, 'loss/train': 1.0712475776672363} 08/30/2021 18:27:40 - INFO - __main__ - Step 29650: {'lr': 0.00045816470031401945, 'samples': 5692800, 'steps': 29649, 'loss/train': 0.9194968938827515} 08/30/2021 18:27:41 - INFO - __main__ - Step 29651: {'lr': 0.00045816176146454296, 'samples': 5692992, 'steps': 29650, 'loss/train': 1.670853614807129} 08/30/2021 18:27:41 - INFO - __main__ - Step 29652: {'lr': 0.00045815882252127197, 'samples': 5693184, 'steps': 29651, 'loss/train': 0.986540675163269} 08/30/2021 18:27:41 - INFO - __main__ - Step 29653: {'lr': 0.0004581558834842078, 'samples': 5693376, 'steps': 29652, 'loss/train': 1.2599154710769653} 08/30/2021 18:27:42 - INFO - __main__ - Step 29654: {'lr': 0.00045815294435335184, 'samples': 5693568, 'steps': 29653, 'loss/train': 1.7173832654953003} 08/30/2021 18:27:43 - INFO - __main__ - Step 29655: {'lr': 0.0004581500051287053, 'samples': 5693760, 'steps': 29654, 'loss/train': 1.1453946828842163} 08/30/2021 18:27:44 - INFO - __main__ - Step 29656: {'lr': 0.00045814706581026967, 'samples': 5693952, 'steps': 29655, 'loss/train': 1.1144442558288574} 08/30/2021 18:27:44 - INFO - __main__ - Step 29657: {'lr': 0.0004581441263980461, 'samples': 5694144, 'steps': 29656, 'loss/train': 0.86360764503479} 08/30/2021 18:27:44 - INFO - __main__ - Step 29658: {'lr': 0.0004581411868920361, 'samples': 5694336, 'steps': 29657, 'loss/train': 1.7170466184616089} 08/30/2021 18:27:45 - INFO - __main__ - Step 29659: {'lr': 0.00045813824729224085, 'samples': 5694528, 'steps': 29658, 'loss/train': 1.596787452697754} 08/30/2021 18:27:45 - INFO - __main__ - Step 29660: {'lr': 0.0004581353075986617, 'samples': 5694720, 'steps': 29659, 'loss/train': 1.4135023355484009} 08/30/2021 18:27:47 - INFO - __main__ - Step 29661: {'lr': 0.00045813236781129996, 'samples': 5694912, 'steps': 29660, 'loss/train': 1.6739174127578735} 08/30/2021 18:27:47 - INFO - __main__ - Step 29662: {'lr': 0.00045812942793015707, 'samples': 5695104, 'steps': 29661, 'loss/train': 1.202912449836731} 08/30/2021 18:27:47 - INFO - __main__ - Step 29663: {'lr': 0.0004581264879552342, 'samples': 5695296, 'steps': 29662, 'loss/train': 0.19049958884716034} 08/30/2021 18:27:48 - INFO - __main__ - Step 29664: {'lr': 0.00045812354788653275, 'samples': 5695488, 'steps': 29663, 'loss/train': 1.0727471113204956} 08/30/2021 18:27:48 - INFO - __main__ - Step 29665: {'lr': 0.00045812060772405403, 'samples': 5695680, 'steps': 29664, 'loss/train': 1.5303667783737183} 08/30/2021 18:27:50 - INFO - __main__ - Step 29666: {'lr': 0.0004581176674677995, 'samples': 5695872, 'steps': 29665, 'loss/train': 1.313496708869934} 08/30/2021 18:27:50 - INFO - __main__ - Step 29667: {'lr': 0.00045811472711777026, 'samples': 5696064, 'steps': 29666, 'loss/train': 1.6279692649841309} 08/30/2021 18:27:50 - INFO - __main__ - Step 29668: {'lr': 0.0004581117866739677, 'samples': 5696256, 'steps': 29667, 'loss/train': 1.3790535926818848} 08/30/2021 18:27:51 - INFO - __main__ - Step 29669: {'lr': 0.00045810884613639325, 'samples': 5696448, 'steps': 29668, 'loss/train': 1.1239794492721558} 08/30/2021 18:27:51 - INFO - __main__ - Step 29670: {'lr': 0.00045810590550504816, 'samples': 5696640, 'steps': 29669, 'loss/train': 1.9284592866897583} 08/30/2021 18:27:53 - INFO - __main__ - Step 29671: {'lr': 0.0004581029647799337, 'samples': 5696832, 'steps': 29670, 'loss/train': 1.4202970266342163} 08/30/2021 18:27:53 - INFO - __main__ - Step 29672: {'lr': 0.0004581000239610513, 'samples': 5697024, 'steps': 29671, 'loss/train': 1.2471117973327637} 08/30/2021 18:27:53 - INFO - __main__ - Step 29673: {'lr': 0.0004580970830484023, 'samples': 5697216, 'steps': 29672, 'loss/train': 1.6633930206298828} 08/30/2021 18:27:54 - INFO - __main__ - Step 29674: {'lr': 0.00045809414204198785, 'samples': 5697408, 'steps': 29673, 'loss/train': 1.426016926765442} 08/30/2021 18:27:54 - INFO - __main__ - Step 29675: {'lr': 0.00045809120094180946, 'samples': 5697600, 'steps': 29674, 'loss/train': 1.453947901725769} 08/30/2021 18:27:56 - INFO - __main__ - Step 29676: {'lr': 0.00045808825974786834, 'samples': 5697792, 'steps': 29675, 'loss/train': 1.6104342937469482} 08/30/2021 18:27:56 - INFO - __main__ - Step 29677: {'lr': 0.0004580853184601659, 'samples': 5697984, 'steps': 29676, 'loss/train': 1.46486234664917} 08/30/2021 18:27:57 - INFO - __main__ - Step 29678: {'lr': 0.0004580823770787034, 'samples': 5698176, 'steps': 29677, 'loss/train': 1.7360520362854004} 08/30/2021 18:27:57 - INFO - __main__ - Step 29679: {'lr': 0.0004580794356034822, 'samples': 5698368, 'steps': 29678, 'loss/train': 1.6491705179214478} 08/30/2021 18:27:57 - INFO - __main__ - Step 29680: {'lr': 0.0004580764940345036, 'samples': 5698560, 'steps': 29679, 'loss/train': 1.6530210971832275} 08/30/2021 18:27:59 - INFO - __main__ - Step 29681: {'lr': 0.00045807355237176896, 'samples': 5698752, 'steps': 29680, 'loss/train': 1.5946695804595947} 08/30/2021 18:27:59 - INFO - __main__ - Step 29682: {'lr': 0.0004580706106152796, 'samples': 5698944, 'steps': 29681, 'loss/train': 1.322835922241211} 08/30/2021 18:28:00 - INFO - __main__ - Step 29683: {'lr': 0.00045806766876503683, 'samples': 5699136, 'steps': 29682, 'loss/train': 2.5335166454315186} 08/30/2021 18:28:00 - INFO - __main__ - Step 29684: {'lr': 0.000458064726821042, 'samples': 5699328, 'steps': 29683, 'loss/train': 1.5357316732406616} 08/30/2021 18:28:00 - INFO - __main__ - Step 29685: {'lr': 0.0004580617847832964, 'samples': 5699520, 'steps': 29684, 'loss/train': 1.5088759660720825} 08/30/2021 18:28:02 - INFO - __main__ - Step 29686: {'lr': 0.0004580588426518013, 'samples': 5699712, 'steps': 29685, 'loss/train': 1.354177474975586} 08/30/2021 18:28:02 - INFO - __main__ - Step 29687: {'lr': 0.0004580559004265582, 'samples': 5699904, 'steps': 29686, 'loss/train': 1.7243818044662476} 08/30/2021 18:28:03 - INFO - __main__ - Step 29688: {'lr': 0.0004580529581075683, 'samples': 5700096, 'steps': 29687, 'loss/train': 1.3967630863189697} 08/30/2021 18:28:03 - INFO - __main__ - Step 29689: {'lr': 0.0004580500156948329, 'samples': 5700288, 'steps': 29688, 'loss/train': 1.497321367263794} 08/30/2021 18:28:03 - INFO - __main__ - Step 29690: {'lr': 0.0004580470731883534, 'samples': 5700480, 'steps': 29689, 'loss/train': 1.810050129890442} 08/30/2021 18:28:04 - INFO - __main__ - Step 29691: {'lr': 0.0004580441305881311, 'samples': 5700672, 'steps': 29690, 'loss/train': 0.927593469619751} 08/30/2021 18:28:05 - INFO - __main__ - Step 29692: {'lr': 0.0004580411878941673, 'samples': 5700864, 'steps': 29691, 'loss/train': 2.807532548904419} 08/30/2021 18:28:06 - INFO - __main__ - Step 29693: {'lr': 0.0004580382451064634, 'samples': 5701056, 'steps': 29692, 'loss/train': 1.5563640594482422} 08/30/2021 18:28:06 - INFO - __main__ - Step 29694: {'lr': 0.00045803530222502065, 'samples': 5701248, 'steps': 29693, 'loss/train': 1.595654010772705} 08/30/2021 18:28:07 - INFO - __main__ - Step 29695: {'lr': 0.0004580323592498404, 'samples': 5701440, 'steps': 29694, 'loss/train': 1.2515085935592651} 08/30/2021 18:28:07 - INFO - __main__ - Step 29696: {'lr': 0.00045802941618092397, 'samples': 5701632, 'steps': 29695, 'loss/train': 0.2638806700706482} 08/30/2021 18:28:09 - INFO - __main__ - Step 29697: {'lr': 0.0004580264730182727, 'samples': 5701824, 'steps': 29696, 'loss/train': 1.4753319025039673} 08/30/2021 18:28:10 - INFO - __main__ - Step 29698: {'lr': 0.000458023529761888, 'samples': 5702016, 'steps': 29697, 'loss/train': 1.6588515043258667} 08/30/2021 18:28:10 - INFO - __main__ - Step 29699: {'lr': 0.00045802058641177104, 'samples': 5702208, 'steps': 29698, 'loss/train': 1.7861418724060059} 08/30/2021 18:28:10 - INFO - __main__ - Step 29700: {'lr': 0.00045801764296792317, 'samples': 5702400, 'steps': 29699, 'loss/train': 1.6370424032211304} 08/30/2021 18:28:11 - INFO - __main__ - Step 29701: {'lr': 0.0004580146994303458, 'samples': 5702592, 'steps': 29700, 'loss/train': 1.1859413385391235} 08/30/2021 18:28:12 - INFO - __main__ - Step 29702: {'lr': 0.0004580117557990402, 'samples': 5702784, 'steps': 29701, 'loss/train': 1.4897328615188599} 08/30/2021 18:28:13 - INFO - __main__ - Step 29703: {'lr': 0.0004580088120740077, 'samples': 5702976, 'steps': 29702, 'loss/train': 1.4795736074447632} 08/30/2021 18:28:13 - INFO - __main__ - Step 29704: {'lr': 0.0004580058682552497, 'samples': 5703168, 'steps': 29703, 'loss/train': 2.0447490215301514} 08/30/2021 18:28:13 - INFO - __main__ - Step 29705: {'lr': 0.00045800292434276736, 'samples': 5703360, 'steps': 29704, 'loss/train': 1.5913904905319214} 08/30/2021 18:28:14 - INFO - __main__ - Step 29706: {'lr': 0.0004579999803365622, 'samples': 5703552, 'steps': 29705, 'loss/train': 1.6796106100082397} 08/30/2021 18:28:15 - INFO - __main__ - Step 29707: {'lr': 0.00045799703623663546, 'samples': 5703744, 'steps': 29706, 'loss/train': 1.5506706237792969} 08/30/2021 18:28:16 - INFO - __main__ - Step 29708: {'lr': 0.00045799409204298844, 'samples': 5703936, 'steps': 29707, 'loss/train': 1.0952070951461792} 08/30/2021 18:28:16 - INFO - __main__ - Step 29709: {'lr': 0.00045799114775562245, 'samples': 5704128, 'steps': 29708, 'loss/train': 1.8405007123947144} 08/30/2021 18:28:16 - INFO - __main__ - Step 29710: {'lr': 0.00045798820337453894, 'samples': 5704320, 'steps': 29709, 'loss/train': 1.6173516511917114} 08/30/2021 18:28:17 - INFO - __main__ - Step 29711: {'lr': 0.00045798525889973905, 'samples': 5704512, 'steps': 29710, 'loss/train': 1.2189722061157227} 08/30/2021 18:28:18 - INFO - __main__ - Step 29712: {'lr': 0.00045798231433122436, 'samples': 5704704, 'steps': 29711, 'loss/train': 1.2220425605773926} 08/30/2021 18:28:19 - INFO - __main__ - Step 29713: {'lr': 0.00045797936966899595, 'samples': 5704896, 'steps': 29712, 'loss/train': 1.3528696298599243} 08/30/2021 18:28:19 - INFO - __main__ - Step 29714: {'lr': 0.00045797642491305523, 'samples': 5705088, 'steps': 29713, 'loss/train': 1.8279149532318115} 08/30/2021 18:28:19 - INFO - __main__ - Step 29715: {'lr': 0.0004579734800634036, 'samples': 5705280, 'steps': 29714, 'loss/train': 1.3975285291671753} 08/30/2021 18:28:20 - INFO - __main__ - Step 29716: {'lr': 0.0004579705351200423, 'samples': 5705472, 'steps': 29715, 'loss/train': 1.6372387409210205} 08/30/2021 18:28:21 - INFO - __main__ - Step 29717: {'lr': 0.0004579675900829727, 'samples': 5705664, 'steps': 29716, 'loss/train': 1.507022738456726} 08/30/2021 18:28:22 - INFO - __main__ - Step 29718: {'lr': 0.00045796464495219614, 'samples': 5705856, 'steps': 29717, 'loss/train': 1.4987457990646362} 08/30/2021 18:28:22 - INFO - __main__ - Step 29719: {'lr': 0.00045796169972771387, 'samples': 5706048, 'steps': 29718, 'loss/train': 1.08888840675354} 08/30/2021 18:28:23 - INFO - __main__ - Step 29720: {'lr': 0.00045795875440952726, 'samples': 5706240, 'steps': 29719, 'loss/train': 1.1902862787246704} 08/30/2021 18:28:23 - INFO - __main__ - Step 29721: {'lr': 0.00045795580899763767, 'samples': 5706432, 'steps': 29720, 'loss/train': 1.6228948831558228} 08/30/2021 18:28:23 - INFO - __main__ - Step 29722: {'lr': 0.00045795286349204633, 'samples': 5706624, 'steps': 29721, 'loss/train': 1.4023505449295044} 08/30/2021 18:28:25 - INFO - __main__ - Step 29723: {'lr': 0.0004579499178927547, 'samples': 5706816, 'steps': 29722, 'loss/train': 1.3119184970855713} 08/30/2021 18:28:25 - INFO - __main__ - Step 29724: {'lr': 0.0004579469721997641, 'samples': 5707008, 'steps': 29723, 'loss/train': 1.5725725889205933} 08/30/2021 18:28:26 - INFO - __main__ - Step 29725: {'lr': 0.0004579440264130758, 'samples': 5707200, 'steps': 29724, 'loss/train': 1.6831140518188477} 08/30/2021 18:28:26 - INFO - __main__ - Step 29726: {'lr': 0.000457941080532691, 'samples': 5707392, 'steps': 29725, 'loss/train': 1.8906539678573608} 08/30/2021 18:28:26 - INFO - __main__ - Step 29727: {'lr': 0.0004579381345586113, 'samples': 5707584, 'steps': 29726, 'loss/train': 1.6148093938827515} 08/30/2021 18:28:28 - INFO - __main__ - Step 29728: {'lr': 0.0004579351884908378, 'samples': 5707776, 'steps': 29727, 'loss/train': 1.54594886302948} 08/30/2021 18:28:28 - INFO - __main__ - Step 29729: {'lr': 0.00045793224232937193, 'samples': 5707968, 'steps': 29728, 'loss/train': 1.3913178443908691} 08/30/2021 18:28:29 - INFO - __main__ - Step 29730: {'lr': 0.0004579292960742151, 'samples': 5708160, 'steps': 29729, 'loss/train': 1.354109764099121} 08/30/2021 18:28:29 - INFO - __main__ - Step 29731: {'lr': 0.0004579263497253684, 'samples': 5708352, 'steps': 29730, 'loss/train': 2.0978946685791016} 08/30/2021 18:28:29 - INFO - __main__ - Step 29732: {'lr': 0.00045792340328283334, 'samples': 5708544, 'steps': 29731, 'loss/train': 1.5430909395217896} 08/30/2021 18:28:31 - INFO - __main__ - Step 29733: {'lr': 0.0004579204567466112, 'samples': 5708736, 'steps': 29732, 'loss/train': 1.5453301668167114} 08/30/2021 18:28:31 - INFO - __main__ - Step 29734: {'lr': 0.0004579175101167033, 'samples': 5708928, 'steps': 29733, 'loss/train': 1.5608700513839722} 08/30/2021 18:28:32 - INFO - __main__ - Step 29735: {'lr': 0.000457914563393111, 'samples': 5709120, 'steps': 29734, 'loss/train': 0.512084424495697} 08/30/2021 18:28:32 - INFO - __main__ - Step 29736: {'lr': 0.00045791161657583555, 'samples': 5709312, 'steps': 29735, 'loss/train': 1.3737982511520386} 08/30/2021 18:28:32 - INFO - __main__ - Step 29737: {'lr': 0.00045790866966487843, 'samples': 5709504, 'steps': 29736, 'loss/train': 0.9926096796989441} 08/30/2021 18:28:34 - INFO - __main__ - Step 29738: {'lr': 0.0004579057226602408, 'samples': 5709696, 'steps': 29737, 'loss/train': 0.20578551292419434} 08/30/2021 18:28:34 - INFO - __main__ - Step 29739: {'lr': 0.00045790277556192414, 'samples': 5709888, 'steps': 29738, 'loss/train': 1.2388333082199097} 08/30/2021 18:28:35 - INFO - __main__ - Step 29740: {'lr': 0.0004578998283699296, 'samples': 5710080, 'steps': 29739, 'loss/train': 1.7845193147659302} 08/30/2021 18:28:35 - INFO - __main__ - Step 29741: {'lr': 0.0004578968810842586, 'samples': 5710272, 'steps': 29740, 'loss/train': 1.3406702280044556} 08/30/2021 18:28:35 - INFO - __main__ - Step 29742: {'lr': 0.0004578939337049126, 'samples': 5710464, 'steps': 29741, 'loss/train': 1.8162589073181152} 08/30/2021 18:28:37 - INFO - __main__ - Step 29743: {'lr': 0.0004578909862318927, 'samples': 5710656, 'steps': 29742, 'loss/train': 0.7952150702476501} 08/30/2021 18:28:37 - INFO - __main__ - Step 29744: {'lr': 0.00045788803866520037, 'samples': 5710848, 'steps': 29743, 'loss/train': 2.365987539291382} 08/30/2021 18:28:38 - INFO - __main__ - Step 29745: {'lr': 0.0004578850910048369, 'samples': 5711040, 'steps': 29744, 'loss/train': 1.553279161453247} 08/30/2021 18:28:38 - INFO - __main__ - Step 29746: {'lr': 0.0004578821432508036, 'samples': 5711232, 'steps': 29745, 'loss/train': 1.640616774559021} 08/30/2021 18:28:38 - INFO - __main__ - Step 29747: {'lr': 0.00045787919540310175, 'samples': 5711424, 'steps': 29746, 'loss/train': 1.5358890295028687} 08/30/2021 18:28:39 - INFO - __main__ - Step 29748: {'lr': 0.0004578762474617328, 'samples': 5711616, 'steps': 29747, 'loss/train': 1.5220602750778198} 08/30/2021 18:28:40 - INFO - __main__ - Step 29749: {'lr': 0.00045787329942669803, 'samples': 5711808, 'steps': 29748, 'loss/train': 1.587807059288025} 08/30/2021 18:28:41 - INFO - __main__ - Step 29750: {'lr': 0.0004578703512979988, 'samples': 5712000, 'steps': 29749, 'loss/train': 1.354875087738037} 08/30/2021 18:28:41 - INFO - __main__ - Step 29751: {'lr': 0.00045786740307563633, 'samples': 5712192, 'steps': 29750, 'loss/train': 1.7917624711990356} 08/30/2021 18:28:41 - INFO - __main__ - Step 29752: {'lr': 0.000457864454759612, 'samples': 5712384, 'steps': 29751, 'loss/train': 2.8033447265625} 08/30/2021 18:28:42 - INFO - __main__ - Step 29753: {'lr': 0.00045786150634992716, 'samples': 5712576, 'steps': 29752, 'loss/train': 1.4662129878997803} 08/30/2021 18:28:44 - INFO - __main__ - Step 29754: {'lr': 0.0004578585578465833, 'samples': 5712768, 'steps': 29753, 'loss/train': 1.7054139375686646} 08/30/2021 18:28:44 - INFO - __main__ - Step 29755: {'lr': 0.00045785560924958135, 'samples': 5712960, 'steps': 29754, 'loss/train': 1.5506590604782104} 08/30/2021 18:28:45 - INFO - __main__ - Step 29756: {'lr': 0.00045785266055892296, 'samples': 5713152, 'steps': 29755, 'loss/train': 0.8969353437423706} 08/30/2021 18:28:45 - INFO - __main__ - Step 29757: {'lr': 0.0004578497117746094, 'samples': 5713344, 'steps': 29756, 'loss/train': 1.6206135749816895} 08/30/2021 18:28:45 - INFO - __main__ - Step 29758: {'lr': 0.00045784676289664194, 'samples': 5713536, 'steps': 29757, 'loss/train': 2.000650405883789} 08/30/2021 18:28:47 - INFO - __main__ - Step 29759: {'lr': 0.00045784381392502193, 'samples': 5713728, 'steps': 29758, 'loss/train': 1.9538886547088623} 08/30/2021 18:28:47 - INFO - __main__ - Step 29760: {'lr': 0.00045784086485975076, 'samples': 5713920, 'steps': 29759, 'loss/train': 1.460592269897461} 08/30/2021 18:28:48 - INFO - __main__ - Step 29761: {'lr': 0.00045783791570082956, 'samples': 5714112, 'steps': 29760, 'loss/train': 1.3283790349960327} 08/30/2021 18:28:48 - INFO - __main__ - Step 29762: {'lr': 0.00045783496644825997, 'samples': 5714304, 'steps': 29761, 'loss/train': 1.9077951908111572} 08/30/2021 18:28:48 - INFO - __main__ - Step 29763: {'lr': 0.000457832017102043, 'samples': 5714496, 'steps': 29762, 'loss/train': 1.3710795640945435} 08/30/2021 18:28:50 - INFO - __main__ - Step 29764: {'lr': 0.00045782906766218026, 'samples': 5714688, 'steps': 29763, 'loss/train': 1.4096707105636597} 08/30/2021 18:28:50 - INFO - __main__ - Step 29765: {'lr': 0.00045782611812867285, 'samples': 5714880, 'steps': 29764, 'loss/train': 1.261650562286377} 08/30/2021 18:28:51 - INFO - __main__ - Step 29766: {'lr': 0.0004578231685015223, 'samples': 5715072, 'steps': 29765, 'loss/train': 1.4897416830062866} 08/30/2021 18:28:51 - INFO - __main__ - Step 29767: {'lr': 0.00045782021878072976, 'samples': 5715264, 'steps': 29766, 'loss/train': 1.155381202697754} 08/30/2021 18:28:51 - INFO - __main__ - Step 29768: {'lr': 0.0004578172689662967, 'samples': 5715456, 'steps': 29767, 'loss/train': 1.8191925287246704} 08/30/2021 18:28:53 - INFO - __main__ - Step 29769: {'lr': 0.0004578143190582243, 'samples': 5715648, 'steps': 29768, 'loss/train': 1.3403890132904053} 08/30/2021 18:28:53 - INFO - __main__ - Step 29770: {'lr': 0.000457811369056514, 'samples': 5715840, 'steps': 29769, 'loss/train': 1.5078458786010742} 08/30/2021 18:28:53 - INFO - __main__ - Step 29771: {'lr': 0.0004578084189611671, 'samples': 5716032, 'steps': 29770, 'loss/train': 1.5487326383590698} 08/30/2021 18:28:54 - INFO - __main__ - Step 29772: {'lr': 0.000457805468772185, 'samples': 5716224, 'steps': 29771, 'loss/train': 1.6098134517669678} 08/30/2021 18:28:54 - INFO - __main__ - Step 29773: {'lr': 0.00045780251848956887, 'samples': 5716416, 'steps': 29772, 'loss/train': 0.9175944924354553} 08/30/2021 18:28:56 - INFO - __main__ - Step 29774: {'lr': 0.0004577995681133202, 'samples': 5716608, 'steps': 29773, 'loss/train': 1.8215703964233398} 08/30/2021 18:28:56 - INFO - __main__ - Step 29775: {'lr': 0.00045779661764344025, 'samples': 5716800, 'steps': 29774, 'loss/train': 1.6772704124450684} 08/30/2021 18:28:56 - INFO - __main__ - Step 29776: {'lr': 0.0004577936670799303, 'samples': 5716992, 'steps': 29775, 'loss/train': 1.6390513181686401} 08/30/2021 18:28:57 - INFO - __main__ - Step 29777: {'lr': 0.00045779071642279177, 'samples': 5717184, 'steps': 29776, 'loss/train': 1.5799801349639893} 08/30/2021 18:28:57 - INFO - __main__ - Step 29778: {'lr': 0.00045778776567202597, 'samples': 5717376, 'steps': 29777, 'loss/train': 1.326113224029541} 08/30/2021 18:28:57 - INFO - __main__ - Step 29779: {'lr': 0.0004577848148276341, 'samples': 5717568, 'steps': 29778, 'loss/train': 1.3282570838928223} 08/30/2021 18:28:59 - INFO - __main__ - Step 29780: {'lr': 0.00045778186388961776, 'samples': 5717760, 'steps': 29779, 'loss/train': 1.3016703128814697} 08/30/2021 18:28:59 - INFO - __main__ - Step 29781: {'lr': 0.000457778912857978, 'samples': 5717952, 'steps': 29780, 'loss/train': 1.7542059421539307} 08/30/2021 18:29:00 - INFO - __main__ - Step 29782: {'lr': 0.0004577759617327163, 'samples': 5718144, 'steps': 29781, 'loss/train': 1.3037378787994385} 08/30/2021 18:29:00 - INFO - __main__ - Step 29783: {'lr': 0.000457773010513834, 'samples': 5718336, 'steps': 29782, 'loss/train': 1.2276067733764648} 08/30/2021 18:29:00 - INFO - __main__ - Step 29784: {'lr': 0.0004577700592013323, 'samples': 5718528, 'steps': 29783, 'loss/train': 1.6257506608963013} 08/30/2021 18:29:02 - INFO - __main__ - Step 29785: {'lr': 0.0004577671077952127, 'samples': 5718720, 'steps': 29784, 'loss/train': 1.7140051126480103} 08/30/2021 18:29:03 - INFO - __main__ - Step 29786: {'lr': 0.0004577641562954764, 'samples': 5718912, 'steps': 29785, 'loss/train': 0.15526026487350464} 08/30/2021 18:29:03 - INFO - __main__ - Step 29787: {'lr': 0.00045776120470212477, 'samples': 5719104, 'steps': 29786, 'loss/train': 1.3239808082580566} 08/30/2021 18:29:03 - INFO - __main__ - Step 29788: {'lr': 0.00045775825301515923, 'samples': 5719296, 'steps': 29787, 'loss/train': 1.4864088296890259} 08/30/2021 18:29:04 - INFO - __main__ - Step 29789: {'lr': 0.00045775530123458096, 'samples': 5719488, 'steps': 29788, 'loss/train': 2.255086898803711} 08/30/2021 18:29:05 - INFO - __main__ - Step 29790: {'lr': 0.00045775234936039133, 'samples': 5719680, 'steps': 29789, 'loss/train': 1.44126558303833} 08/30/2021 18:29:05 - INFO - __main__ - Step 29791: {'lr': 0.00045774939739259173, 'samples': 5719872, 'steps': 29790, 'loss/train': 1.770522117614746} 08/30/2021 18:29:06 - INFO - __main__ - Step 29792: {'lr': 0.0004577464453311835, 'samples': 5720064, 'steps': 29791, 'loss/train': 0.2801794409751892} 08/30/2021 18:29:06 - INFO - __main__ - Step 29793: {'lr': 0.00045774349317616786, 'samples': 5720256, 'steps': 29792, 'loss/train': 1.2711302042007446} 08/30/2021 18:29:07 - INFO - __main__ - Step 29794: {'lr': 0.00045774054092754624, 'samples': 5720448, 'steps': 29793, 'loss/train': 1.5915980339050293} 08/30/2021 18:29:08 - INFO - __main__ - Step 29795: {'lr': 0.00045773758858531997, 'samples': 5720640, 'steps': 29794, 'loss/train': 1.4245502948760986} 08/30/2021 18:29:09 - INFO - __main__ - Step 29796: {'lr': 0.0004577346361494903, 'samples': 5720832, 'steps': 29795, 'loss/train': 0.8146663904190063} 08/30/2021 18:29:09 - INFO - __main__ - Step 29797: {'lr': 0.0004577316836200586, 'samples': 5721024, 'steps': 29796, 'loss/train': 0.95196133852005} 08/30/2021 18:29:09 - INFO - __main__ - Step 29798: {'lr': 0.0004577287309970262, 'samples': 5721216, 'steps': 29797, 'loss/train': 0.8967983722686768} 08/30/2021 18:29:10 - INFO - __main__ - Step 29799: {'lr': 0.0004577257782803945, 'samples': 5721408, 'steps': 29798, 'loss/train': 1.5457720756530762} 08/30/2021 18:29:11 - INFO - __main__ - Step 29800: {'lr': 0.00045772282547016475, 'samples': 5721600, 'steps': 29799, 'loss/train': 1.2335726022720337} 08/30/2021 18:29:12 - INFO - __main__ - Step 29801: {'lr': 0.0004577198725663383, 'samples': 5721792, 'steps': 29800, 'loss/train': 1.3536510467529297} 08/30/2021 18:29:12 - INFO - __main__ - Step 29802: {'lr': 0.00045771691956891645, 'samples': 5721984, 'steps': 29801, 'loss/train': 1.571109652519226} 08/30/2021 18:29:12 - INFO - __main__ - Step 29803: {'lr': 0.00045771396647790053, 'samples': 5722176, 'steps': 29802, 'loss/train': 0.9780459403991699} 08/30/2021 18:29:13 - INFO - __main__ - Step 29804: {'lr': 0.00045771101329329195, 'samples': 5722368, 'steps': 29803, 'loss/train': 1.5371843576431274} 08/30/2021 18:29:13 - INFO - __main__ - Step 29805: {'lr': 0.00045770806001509205, 'samples': 5722560, 'steps': 29804, 'loss/train': 1.6407279968261719} 08/30/2021 18:29:15 - INFO - __main__ - Step 29806: {'lr': 0.00045770510664330203, 'samples': 5722752, 'steps': 29805, 'loss/train': 3.0229039192199707} 08/30/2021 18:29:16 - INFO - __main__ - Step 29807: {'lr': 0.0004577021531779233, 'samples': 5722944, 'steps': 29806, 'loss/train': 1.6292167901992798} 08/30/2021 18:29:16 - INFO - __main__ - Step 29808: {'lr': 0.00045769919961895716, 'samples': 5723136, 'steps': 29807, 'loss/train': 1.7189383506774902} 08/30/2021 18:29:17 - INFO - __main__ - Step 29809: {'lr': 0.000457696245966405, 'samples': 5723328, 'steps': 29808, 'loss/train': 1.4111695289611816} 08/30/2021 18:29:17 - INFO - __main__ - Step 29810: {'lr': 0.0004576932922202681, 'samples': 5723520, 'steps': 29809, 'loss/train': 1.9019224643707275} 08/30/2021 18:29:19 - INFO - __main__ - Step 29811: {'lr': 0.00045769033838054783, 'samples': 5723712, 'steps': 29810, 'loss/train': 1.5190767049789429} 08/30/2021 18:29:19 - INFO - __main__ - Step 29812: {'lr': 0.0004576873844472455, 'samples': 5723904, 'steps': 29811, 'loss/train': 1.2523224353790283} 08/30/2021 18:29:19 - INFO - __main__ - Step 29813: {'lr': 0.00045768443042036247, 'samples': 5724096, 'steps': 29812, 'loss/train': 1.69696843624115} 08/30/2021 18:29:20 - INFO - __main__ - Step 29814: {'lr': 0.0004576814762999, 'samples': 5724288, 'steps': 29813, 'loss/train': 0.5058253407478333} 08/30/2021 18:29:20 - INFO - __main__ - Step 29815: {'lr': 0.00045767852208585945, 'samples': 5724480, 'steps': 29814, 'loss/train': 1.6717995405197144} 08/30/2021 18:29:21 - INFO - __main__ - Step 29816: {'lr': 0.00045767556777824217, 'samples': 5724672, 'steps': 29815, 'loss/train': 1.5186625719070435} 08/30/2021 18:29:22 - INFO - __main__ - Step 29817: {'lr': 0.00045767261337704946, 'samples': 5724864, 'steps': 29816, 'loss/train': 1.3946292400360107} 08/30/2021 18:29:22 - INFO - __main__ - Step 29818: {'lr': 0.00045766965888228273, 'samples': 5725056, 'steps': 29817, 'loss/train': 1.4422296285629272} 08/30/2021 18:29:23 - INFO - __main__ - Step 29819: {'lr': 0.00045766670429394317, 'samples': 5725248, 'steps': 29818, 'loss/train': 1.076311469078064} 08/30/2021 18:29:23 - INFO - __main__ - Step 29820: {'lr': 0.00045766374961203236, 'samples': 5725440, 'steps': 29819, 'loss/train': 1.0208680629730225} 08/30/2021 18:29:25 - INFO - __main__ - Step 29821: {'lr': 0.0004576607948365513, 'samples': 5725632, 'steps': 29820, 'loss/train': 1.6473058462142944} 08/30/2021 18:29:25 - INFO - __main__ - Step 29822: {'lr': 0.0004576578399675015, 'samples': 5725824, 'steps': 29821, 'loss/train': 1.4750052690505981} 08/30/2021 18:29:25 - INFO - __main__ - Step 29823: {'lr': 0.00045765488500488437, 'samples': 5726016, 'steps': 29822, 'loss/train': 1.0241910219192505} 08/30/2021 18:29:26 - INFO - __main__ - Step 29824: {'lr': 0.0004576519299487012, 'samples': 5726208, 'steps': 29823, 'loss/train': 1.5517184734344482} 08/30/2021 18:29:26 - INFO - __main__ - Step 29825: {'lr': 0.00045764897479895315, 'samples': 5726400, 'steps': 29824, 'loss/train': 1.3328709602355957} 08/30/2021 18:29:28 - INFO - __main__ - Step 29826: {'lr': 0.0004576460195556418, 'samples': 5726592, 'steps': 29825, 'loss/train': 1.3228015899658203} 08/30/2021 18:29:28 - INFO - __main__ - Step 29827: {'lr': 0.0004576430642187682, 'samples': 5726784, 'steps': 29826, 'loss/train': 1.466692328453064} 08/30/2021 18:29:28 - INFO - __main__ - Step 29828: {'lr': 0.00045764010878833396, 'samples': 5726976, 'steps': 29827, 'loss/train': 1.0952364206314087} 08/30/2021 18:29:29 - INFO - __main__ - Step 29829: {'lr': 0.00045763715326434023, 'samples': 5727168, 'steps': 29828, 'loss/train': 1.3330249786376953} 08/30/2021 18:29:29 - INFO - __main__ - Step 29830: {'lr': 0.0004576341976467884, 'samples': 5727360, 'steps': 29829, 'loss/train': 1.300980567932129} 08/30/2021 18:29:29 - INFO - __main__ - Step 29831: {'lr': 0.00045763124193567983, 'samples': 5727552, 'steps': 29830, 'loss/train': 1.2432913780212402} 08/30/2021 18:29:31 - INFO - __main__ - Step 29832: {'lr': 0.0004576282861310158, 'samples': 5727744, 'steps': 29831, 'loss/train': 1.5756326913833618} 08/30/2021 18:29:31 - INFO - __main__ - Step 29833: {'lr': 0.00045762533023279773, 'samples': 5727936, 'steps': 29832, 'loss/train': 1.3727688789367676} 08/30/2021 18:29:32 - INFO - __main__ - Step 29834: {'lr': 0.00045762237424102687, 'samples': 5728128, 'steps': 29833, 'loss/train': 1.3507001399993896} 08/30/2021 18:29:32 - INFO - __main__ - Step 29835: {'lr': 0.0004576194181557045, 'samples': 5728320, 'steps': 29834, 'loss/train': 1.5258768796920776} 08/30/2021 18:29:32 - INFO - __main__ - Step 29836: {'lr': 0.00045761646197683216, 'samples': 5728512, 'steps': 29835, 'loss/train': 1.6856153011322021} 08/30/2021 18:29:34 - INFO - __main__ - Step 29837: {'lr': 0.00045761350570441096, 'samples': 5728704, 'steps': 29836, 'loss/train': 1.1569122076034546} 08/30/2021 18:29:34 - INFO - __main__ - Step 29838: {'lr': 0.0004576105493384423, 'samples': 5728896, 'steps': 29837, 'loss/train': 1.3239467144012451} 08/30/2021 18:29:35 - INFO - __main__ - Step 29839: {'lr': 0.00045760759287892755, 'samples': 5729088, 'steps': 29838, 'loss/train': 0.49414050579071045} 08/30/2021 18:29:35 - INFO - __main__ - Step 29840: {'lr': 0.000457604636325868, 'samples': 5729280, 'steps': 29839, 'loss/train': 1.2491590976715088} 08/30/2021 18:29:35 - INFO - __main__ - Step 29841: {'lr': 0.00045760167967926504, 'samples': 5729472, 'steps': 29840, 'loss/train': 1.202050805091858} 08/30/2021 18:29:37 - INFO - __main__ - Step 29842: {'lr': 0.00045759872293911995, 'samples': 5729664, 'steps': 29841, 'loss/train': 1.5716712474822998} 08/30/2021 18:29:37 - INFO - __main__ - Step 29843: {'lr': 0.00045759576610543407, 'samples': 5729856, 'steps': 29842, 'loss/train': 1.3601289987564087} 08/30/2021 18:29:38 - INFO - __main__ - Step 29844: {'lr': 0.0004575928091782088, 'samples': 5730048, 'steps': 29843, 'loss/train': 1.9324127435684204} 08/30/2021 18:29:38 - INFO - __main__ - Step 29845: {'lr': 0.00045758985215744536, 'samples': 5730240, 'steps': 29844, 'loss/train': 1.5306636095046997} 08/30/2021 18:29:38 - INFO - __main__ - Step 29846: {'lr': 0.0004575868950431452, 'samples': 5730432, 'steps': 29845, 'loss/train': 1.7896960973739624} 08/30/2021 18:29:40 - INFO - __main__ - Step 29847: {'lr': 0.0004575839378353095, 'samples': 5730624, 'steps': 29846, 'loss/train': 1.4041900634765625} 08/30/2021 18:29:40 - INFO - __main__ - Step 29848: {'lr': 0.0004575809805339397, 'samples': 5730816, 'steps': 29847, 'loss/train': 0.7040590047836304} 08/30/2021 18:29:41 - INFO - __main__ - Step 29849: {'lr': 0.0004575780231390371, 'samples': 5731008, 'steps': 29848, 'loss/train': 0.7328097820281982} 08/30/2021 18:29:41 - INFO - __main__ - Step 29850: {'lr': 0.0004575750656506031, 'samples': 5731200, 'steps': 29849, 'loss/train': 1.475000262260437} 08/30/2021 18:29:41 - INFO - __main__ - Step 29851: {'lr': 0.00045757210806863895, 'samples': 5731392, 'steps': 29850, 'loss/train': 0.813751757144928} 08/30/2021 18:29:43 - INFO - __main__ - Step 29852: {'lr': 0.0004575691503931461, 'samples': 5731584, 'steps': 29851, 'loss/train': 1.2440426349639893} 08/30/2021 18:29:43 - INFO - __main__ - Step 29853: {'lr': 0.00045756619262412565, 'samples': 5731776, 'steps': 29852, 'loss/train': 1.576850175857544} 08/30/2021 18:29:44 - INFO - __main__ - Step 29854: {'lr': 0.0004575632347615791, 'samples': 5731968, 'steps': 29853, 'loss/train': 1.7223079204559326} 08/30/2021 18:29:44 - INFO - __main__ - Step 29855: {'lr': 0.0004575602768055078, 'samples': 5732160, 'steps': 29854, 'loss/train': 1.3341399431228638} 08/30/2021 18:29:44 - INFO - __main__ - Step 29856: {'lr': 0.00045755731875591303, 'samples': 5732352, 'steps': 29855, 'loss/train': 0.9654378294944763} 08/30/2021 18:29:47 - INFO - __main__ - Step 29857: {'lr': 0.0004575543606127961, 'samples': 5732544, 'steps': 29856, 'loss/train': 1.348114252090454} 08/30/2021 18:29:47 - INFO - __main__ - Step 29858: {'lr': 0.0004575514023761585, 'samples': 5732736, 'steps': 29857, 'loss/train': 1.888065218925476} 08/30/2021 18:29:48 - INFO - __main__ - Step 29859: {'lr': 0.00045754844404600136, 'samples': 5732928, 'steps': 29858, 'loss/train': 2.2803468704223633} 08/30/2021 18:29:48 - INFO - __main__ - Step 29860: {'lr': 0.00045754548562232605, 'samples': 5733120, 'steps': 29859, 'loss/train': 1.4766547679901123} 08/30/2021 18:29:48 - INFO - __main__ - Step 29861: {'lr': 0.00045754252710513397, 'samples': 5733312, 'steps': 29860, 'loss/train': 1.2961032390594482} 08/30/2021 18:29:49 - INFO - __main__ - Step 29862: {'lr': 0.00045753956849442647, 'samples': 5733504, 'steps': 29861, 'loss/train': 1.358559250831604} 08/30/2021 18:29:50 - INFO - __main__ - Step 29863: {'lr': 0.00045753660979020485, 'samples': 5733696, 'steps': 29862, 'loss/train': 1.7077391147613525} 08/30/2021 18:29:51 - INFO - __main__ - Step 29864: {'lr': 0.0004575336509924704, 'samples': 5733888, 'steps': 29863, 'loss/train': 1.4787989854812622} 08/30/2021 18:29:51 - INFO - __main__ - Step 29865: {'lr': 0.0004575306921012245, 'samples': 5734080, 'steps': 29864, 'loss/train': 2.005549907684326} 08/30/2021 18:29:51 - INFO - __main__ - Step 29866: {'lr': 0.00045752773311646846, 'samples': 5734272, 'steps': 29865, 'loss/train': 1.8861044645309448} 08/30/2021 18:29:52 - INFO - __main__ - Step 29867: {'lr': 0.0004575247740382037, 'samples': 5734464, 'steps': 29866, 'loss/train': 1.520192265510559} 08/30/2021 18:29:52 - INFO - __main__ - Step 29868: {'lr': 0.0004575218148664314, 'samples': 5734656, 'steps': 29867, 'loss/train': 0.6959830522537231} 08/30/2021 18:29:54 - INFO - __main__ - Step 29869: {'lr': 0.00045751885560115294, 'samples': 5734848, 'steps': 29868, 'loss/train': 1.4108071327209473} 08/30/2021 18:29:54 - INFO - __main__ - Step 29870: {'lr': 0.0004575158962423698, 'samples': 5735040, 'steps': 29869, 'loss/train': 2.066143751144409} 08/30/2021 18:29:55 - INFO - __main__ - Step 29871: {'lr': 0.0004575129367900831, 'samples': 5735232, 'steps': 29870, 'loss/train': 1.474915623664856} 08/30/2021 18:29:55 - INFO - __main__ - Step 29872: {'lr': 0.0004575099772442943, 'samples': 5735424, 'steps': 29871, 'loss/train': 1.578248143196106} 08/30/2021 18:29:55 - INFO - __main__ - Step 29873: {'lr': 0.0004575070176050047, 'samples': 5735616, 'steps': 29872, 'loss/train': 0.0819786787033081} 08/30/2021 18:29:57 - INFO - __main__ - Step 29874: {'lr': 0.00045750405787221566, 'samples': 5735808, 'steps': 29873, 'loss/train': 2.4636528491973877} 08/30/2021 18:29:57 - INFO - __main__ - Step 29875: {'lr': 0.0004575010980459285, 'samples': 5736000, 'steps': 29874, 'loss/train': 1.9061830043792725} 08/30/2021 18:29:58 - INFO - __main__ - Step 29876: {'lr': 0.0004574981381261445, 'samples': 5736192, 'steps': 29875, 'loss/train': 1.2713805437088013} 08/30/2021 18:29:58 - INFO - __main__ - Step 29877: {'lr': 0.0004574951781128651, 'samples': 5736384, 'steps': 29876, 'loss/train': 1.6363621950149536} 08/30/2021 18:29:59 - INFO - __main__ - Step 29878: {'lr': 0.0004574922180060915, 'samples': 5736576, 'steps': 29877, 'loss/train': 1.4786618947982788} 08/30/2021 18:30:00 - INFO - __main__ - Step 29879: {'lr': 0.0004574892578058252, 'samples': 5736768, 'steps': 29878, 'loss/train': 1.4830291271209717} 08/30/2021 18:30:01 - INFO - __main__ - Step 29880: {'lr': 0.0004574862975120674, 'samples': 5736960, 'steps': 29879, 'loss/train': 1.4662595987319946} 08/30/2021 18:30:01 - INFO - __main__ - Step 29881: {'lr': 0.0004574833371248195, 'samples': 5737152, 'steps': 29880, 'loss/train': 2.465188503265381} 08/30/2021 18:30:01 - INFO - __main__ - Step 29882: {'lr': 0.00045748037664408275, 'samples': 5737344, 'steps': 29881, 'loss/train': 1.308503270149231} 08/30/2021 18:30:02 - INFO - __main__ - Step 29883: {'lr': 0.0004574774160698586, 'samples': 5737536, 'steps': 29882, 'loss/train': 0.6008021831512451} 08/30/2021 18:30:03 - INFO - __main__ - Step 29884: {'lr': 0.00045747445540214826, 'samples': 5737728, 'steps': 29883, 'loss/train': 1.2538586854934692} 08/30/2021 18:30:04 - INFO - __main__ - Step 29885: {'lr': 0.00045747149464095324, 'samples': 5737920, 'steps': 29884, 'loss/train': 1.5160785913467407} 08/30/2021 18:30:04 - INFO - __main__ - Step 29886: {'lr': 0.00045746853378627467, 'samples': 5738112, 'steps': 29885, 'loss/train': 1.453216791152954} 08/30/2021 18:30:04 - INFO - __main__ - Step 29887: {'lr': 0.000457465572838114, 'samples': 5738304, 'steps': 29886, 'loss/train': 1.4027401208877563} 08/30/2021 18:30:05 - INFO - __main__ - Step 29888: {'lr': 0.0004574626117964726, 'samples': 5738496, 'steps': 29887, 'loss/train': 1.1967679262161255} 08/30/2021 18:30:05 - INFO - __main__ - Step 29889: {'lr': 0.00045745965066135163, 'samples': 5738688, 'steps': 29888, 'loss/train': 1.338134527206421} 08/30/2021 18:30:07 - INFO - __main__ - Step 29890: {'lr': 0.00045745668943275266, 'samples': 5738880, 'steps': 29889, 'loss/train': 1.9230146408081055} 08/30/2021 18:30:07 - INFO - __main__ - Step 29891: {'lr': 0.00045745372811067687, 'samples': 5739072, 'steps': 29890, 'loss/train': 0.5520074963569641} 08/30/2021 18:30:07 - INFO - __main__ - Step 29892: {'lr': 0.00045745076669512566, 'samples': 5739264, 'steps': 29891, 'loss/train': 1.6947280168533325} 08/30/2021 18:30:08 - INFO - __main__ - Step 29893: {'lr': 0.0004574478051861003, 'samples': 5739456, 'steps': 29892, 'loss/train': 1.720933198928833} 08/30/2021 18:30:08 - INFO - __main__ - Step 29894: {'lr': 0.00045744484358360216, 'samples': 5739648, 'steps': 29893, 'loss/train': 1.9582308530807495} 08/30/2021 18:30:09 - INFO - __main__ - Step 29895: {'lr': 0.0004574418818876326, 'samples': 5739840, 'steps': 29894, 'loss/train': 0.9471269845962524} 08/30/2021 18:30:10 - INFO - __main__ - Step 29896: {'lr': 0.0004574389200981929, 'samples': 5740032, 'steps': 29895, 'loss/train': 1.3663339614868164} 08/30/2021 18:30:10 - INFO - __main__ - Step 29897: {'lr': 0.00045743595821528437, 'samples': 5740224, 'steps': 29896, 'loss/train': 1.9239739179611206} 08/30/2021 18:30:11 - INFO - __main__ - Step 29898: {'lr': 0.0004574329962389085, 'samples': 5740416, 'steps': 29897, 'loss/train': 1.5327961444854736} 08/30/2021 18:30:11 - INFO - __main__ - Step 29899: {'lr': 0.0004574300341690665, 'samples': 5740608, 'steps': 29898, 'loss/train': 1.6033366918563843} 08/30/2021 18:30:12 - INFO - __main__ - Step 29900: {'lr': 0.00045742707200575975, 'samples': 5740800, 'steps': 29899, 'loss/train': 1.089516282081604} 08/30/2021 18:30:13 - INFO - __main__ - Step 29901: {'lr': 0.00045742410974898947, 'samples': 5740992, 'steps': 29900, 'loss/train': 1.4063479900360107} 08/30/2021 18:30:13 - INFO - __main__ - Step 29902: {'lr': 0.0004574211473987571, 'samples': 5741184, 'steps': 29901, 'loss/train': 1.282423496246338} 08/30/2021 18:30:13 - INFO - __main__ - Step 29903: {'lr': 0.00045741818495506403, 'samples': 5741376, 'steps': 29902, 'loss/train': 1.4164947271347046} 08/30/2021 18:30:14 - INFO - __main__ - Step 29904: {'lr': 0.0004574152224179115, 'samples': 5741568, 'steps': 29903, 'loss/train': 1.2825496196746826} 08/30/2021 18:30:15 - INFO - __main__ - Step 29905: {'lr': 0.0004574122597873008, 'samples': 5741760, 'steps': 29904, 'loss/train': 1.7941032648086548} 08/30/2021 18:30:16 - INFO - __main__ - Step 29906: {'lr': 0.0004574092970632335, 'samples': 5741952, 'steps': 29905, 'loss/train': 1.6563183069229126} 08/30/2021 18:30:16 - INFO - __main__ - Step 29907: {'lr': 0.00045740633424571064, 'samples': 5742144, 'steps': 29906, 'loss/train': 0.6336389183998108} 08/30/2021 18:30:17 - INFO - __main__ - Step 29908: {'lr': 0.00045740337133473374, 'samples': 5742336, 'steps': 29907, 'loss/train': 1.3014731407165527} 08/30/2021 18:30:17 - INFO - __main__ - Step 29909: {'lr': 0.00045740040833030404, 'samples': 5742528, 'steps': 29908, 'loss/train': 1.1213966608047485} 08/30/2021 18:30:20 - INFO - __main__ - Step 29910: {'lr': 0.00045739744523242294, 'samples': 5742720, 'steps': 29909, 'loss/train': 1.2861236333847046} 08/30/2021 18:30:21 - INFO - __main__ - Step 29911: {'lr': 0.0004573944820410918, 'samples': 5742912, 'steps': 29910, 'loss/train': 1.6103925704956055} 08/30/2021 18:30:21 - INFO - __main__ - Step 29912: {'lr': 0.0004573915187563118, 'samples': 5743104, 'steps': 29911, 'loss/train': 1.726737141609192} 08/30/2021 18:30:21 - INFO - __main__ - Step 29913: {'lr': 0.00045738855537808443, 'samples': 5743296, 'steps': 29912, 'loss/train': 1.719698190689087} 08/30/2021 18:30:22 - INFO - __main__ - Step 29914: {'lr': 0.000457385591906411, 'samples': 5743488, 'steps': 29913, 'loss/train': 1.1147890090942383} 08/30/2021 18:30:22 - INFO - __main__ - Step 29915: {'lr': 0.00045738262834129283, 'samples': 5743680, 'steps': 29914, 'loss/train': 1.87599515914917} 08/30/2021 18:30:22 - INFO - __main__ - Step 29916: {'lr': 0.0004573796646827312, 'samples': 5743872, 'steps': 29915, 'loss/train': 1.8886315822601318} 08/30/2021 18:30:23 - INFO - __main__ - Step 29917: {'lr': 0.0004573767009307276, 'samples': 5744064, 'steps': 29916, 'loss/train': 1.277214527130127} 08/30/2021 18:30:24 - INFO - __main__ - Step 29918: {'lr': 0.0004573737370852831, 'samples': 5744256, 'steps': 29917, 'loss/train': 2.1520116329193115} 08/30/2021 18:30:25 - INFO - __main__ - Step 29919: {'lr': 0.0004573707731463993, 'samples': 5744448, 'steps': 29918, 'loss/train': 1.8385660648345947} 08/30/2021 18:30:25 - INFO - __main__ - Step 29920: {'lr': 0.00045736780911407736, 'samples': 5744640, 'steps': 29919, 'loss/train': 1.6175665855407715} 08/30/2021 18:30:25 - INFO - __main__ - Step 29921: {'lr': 0.00045736484498831877, 'samples': 5744832, 'steps': 29920, 'loss/train': 1.7936135530471802} 08/30/2021 18:30:26 - INFO - __main__ - Step 29922: {'lr': 0.0004573618807691248, 'samples': 5745024, 'steps': 29921, 'loss/train': 1.5341824293136597} 08/30/2021 18:30:27 - INFO - __main__ - Step 29923: {'lr': 0.0004573589164564966, 'samples': 5745216, 'steps': 29922, 'loss/train': 1.5022945404052734} 08/30/2021 18:30:28 - INFO - __main__ - Step 29924: {'lr': 0.00045735595205043583, 'samples': 5745408, 'steps': 29923, 'loss/train': 1.0516347885131836} 08/30/2021 18:30:28 - INFO - __main__ - Step 29925: {'lr': 0.00045735298755094364, 'samples': 5745600, 'steps': 29924, 'loss/train': 1.4194567203521729} 08/30/2021 18:30:29 - INFO - __main__ - Step 29926: {'lr': 0.00045735002295802137, 'samples': 5745792, 'steps': 29925, 'loss/train': 1.909565806388855} 08/30/2021 18:30:29 - INFO - __main__ - Step 29927: {'lr': 0.00045734705827167035, 'samples': 5745984, 'steps': 29926, 'loss/train': 1.2392679452896118} 08/30/2021 18:30:31 - INFO - __main__ - Step 29928: {'lr': 0.000457344093491892, 'samples': 5746176, 'steps': 29927, 'loss/train': 0.4013739824295044} 08/30/2021 18:30:31 - INFO - __main__ - Step 29929: {'lr': 0.00045734112861868753, 'samples': 5746368, 'steps': 29928, 'loss/train': 1.5148979425430298} 08/30/2021 18:30:32 - INFO - __main__ - Step 29930: {'lr': 0.0004573381636520584, 'samples': 5746560, 'steps': 29929, 'loss/train': 0.2414027750492096} 08/30/2021 18:30:32 - INFO - __main__ - Step 29931: {'lr': 0.0004573351985920059, 'samples': 5746752, 'steps': 29930, 'loss/train': 0.13806553184986115} 08/30/2021 18:30:32 - INFO - __main__ - Step 29932: {'lr': 0.0004573322334385314, 'samples': 5746944, 'steps': 29931, 'loss/train': 0.06139226257801056} 08/30/2021 18:30:33 - INFO - __main__ - Step 29933: {'lr': 0.0004573292681916361, 'samples': 5747136, 'steps': 29932, 'loss/train': 2.4596898555755615} 08/30/2021 18:30:34 - INFO - __main__ - Step 29934: {'lr': 0.0004573263028513214, 'samples': 5747328, 'steps': 29933, 'loss/train': 1.724640130996704} 08/30/2021 18:30:35 - INFO - __main__ - Step 29935: {'lr': 0.0004573233374175888, 'samples': 5747520, 'steps': 29934, 'loss/train': 1.6728287935256958} 08/30/2021 18:30:35 - INFO - __main__ - Step 29936: {'lr': 0.0004573203718904394, 'samples': 5747712, 'steps': 29935, 'loss/train': 1.489703893661499} 08/30/2021 18:30:36 - INFO - __main__ - Step 29937: {'lr': 0.00045731740626987473, 'samples': 5747904, 'steps': 29936, 'loss/train': 1.1529443264007568} 08/30/2021 18:30:36 - INFO - __main__ - Step 29938: {'lr': 0.00045731444055589597, 'samples': 5748096, 'steps': 29937, 'loss/train': 1.6943330764770508} 08/30/2021 18:30:36 - INFO - __main__ - Step 29939: {'lr': 0.0004573114747485045, 'samples': 5748288, 'steps': 29938, 'loss/train': 1.0642552375793457} 08/30/2021 18:30:38 - INFO - __main__ - Step 29940: {'lr': 0.0004573085088477017, 'samples': 5748480, 'steps': 29939, 'loss/train': 1.3704547882080078} 08/30/2021 18:30:38 - INFO - __main__ - Step 29941: {'lr': 0.0004573055428534889, 'samples': 5748672, 'steps': 29940, 'loss/train': 1.265084981918335} 08/30/2021 18:30:39 - INFO - __main__ - Step 29942: {'lr': 0.00045730257676586747, 'samples': 5748864, 'steps': 29941, 'loss/train': 1.354390025138855} 08/30/2021 18:30:39 - INFO - __main__ - Step 29943: {'lr': 0.0004572996105848386, 'samples': 5749056, 'steps': 29942, 'loss/train': 1.4503631591796875} 08/30/2021 18:30:39 - INFO - __main__ - Step 29944: {'lr': 0.0004572966443104038, 'samples': 5749248, 'steps': 29943, 'loss/train': 1.7153041362762451} 08/30/2021 18:30:41 - INFO - __main__ - Step 29945: {'lr': 0.00045729367794256434, 'samples': 5749440, 'steps': 29944, 'loss/train': 0.713683009147644} 08/30/2021 18:30:41 - INFO - __main__ - Step 29946: {'lr': 0.0004572907114813215, 'samples': 5749632, 'steps': 29945, 'loss/train': 1.6766033172607422} 08/30/2021 18:30:42 - INFO - __main__ - Step 29947: {'lr': 0.0004572877449266767, 'samples': 5749824, 'steps': 29946, 'loss/train': 1.700985074043274} 08/30/2021 18:30:42 - INFO - __main__ - Step 29948: {'lr': 0.0004572847782786312, 'samples': 5750016, 'steps': 29947, 'loss/train': 1.3387649059295654} 08/30/2021 18:30:42 - INFO - __main__ - Step 29949: {'lr': 0.0004572818115371864, 'samples': 5750208, 'steps': 29948, 'loss/train': 1.493436574935913} 08/30/2021 18:30:44 - INFO - __main__ - Step 29950: {'lr': 0.0004572788447023436, 'samples': 5750400, 'steps': 29949, 'loss/train': 1.8604241609573364} 08/30/2021 18:30:44 - INFO - __main__ - Step 29951: {'lr': 0.00045727587777410415, 'samples': 5750592, 'steps': 29950, 'loss/train': 1.41011381149292} 08/30/2021 18:30:45 - INFO - __main__ - Step 29952: {'lr': 0.00045727291075246937, 'samples': 5750784, 'steps': 29951, 'loss/train': 1.568453073501587} 08/30/2021 18:30:45 - INFO - __main__ - Step 29953: {'lr': 0.0004572699436374407, 'samples': 5750976, 'steps': 29952, 'loss/train': 2.2069711685180664} 08/30/2021 18:30:45 - INFO - __main__ - Step 29954: {'lr': 0.00045726697642901925, 'samples': 5751168, 'steps': 29953, 'loss/train': 0.19367405772209167} 08/30/2021 18:30:47 - INFO - __main__ - Step 29955: {'lr': 0.0004572640091272066, 'samples': 5751360, 'steps': 29954, 'loss/train': 1.5525058507919312} 08/30/2021 18:30:48 - INFO - __main__ - Step 29956: {'lr': 0.000457261041732004, 'samples': 5751552, 'steps': 29955, 'loss/train': 1.349680781364441} 08/30/2021 18:30:48 - INFO - __main__ - Step 29957: {'lr': 0.0004572580742434127, 'samples': 5751744, 'steps': 29956, 'loss/train': 1.949102759361267} 08/30/2021 18:30:48 - INFO - __main__ - Step 29958: {'lr': 0.00045725510666143424, 'samples': 5751936, 'steps': 29957, 'loss/train': 1.4559065103530884} 08/30/2021 18:30:49 - INFO - __main__ - Step 29959: {'lr': 0.0004572521389860697, 'samples': 5752128, 'steps': 29958, 'loss/train': 1.6270986795425415} 08/30/2021 18:30:50 - INFO - __main__ - Step 29960: {'lr': 0.00045724917121732055, 'samples': 5752320, 'steps': 29959, 'loss/train': 1.2723875045776367} 08/30/2021 18:30:51 - INFO - __main__ - Step 29961: {'lr': 0.0004572462033551882, 'samples': 5752512, 'steps': 29960, 'loss/train': 2.9785878658294678} 08/30/2021 18:30:51 - INFO - __main__ - Step 29962: {'lr': 0.00045724323539967385, 'samples': 5752704, 'steps': 29961, 'loss/train': 1.342309832572937} 08/30/2021 18:30:51 - INFO - __main__ - Step 29963: {'lr': 0.00045724026735077886, 'samples': 5752896, 'steps': 29962, 'loss/train': 1.3100159168243408} 08/30/2021 18:30:52 - INFO - __main__ - Step 29964: {'lr': 0.00045723729920850464, 'samples': 5753088, 'steps': 29963, 'loss/train': 1.652289628982544} 08/30/2021 18:30:54 - INFO - __main__ - Step 29965: {'lr': 0.00045723433097285247, 'samples': 5753280, 'steps': 29964, 'loss/train': 1.4638392925262451} 08/30/2021 18:30:55 - INFO - __main__ - Step 29966: {'lr': 0.0004572313626438238, 'samples': 5753472, 'steps': 29965, 'loss/train': 1.4360930919647217} 08/30/2021 18:30:55 - INFO - __main__ - Step 29967: {'lr': 0.00045722839422141984, 'samples': 5753664, 'steps': 29966, 'loss/train': 1.658735990524292} 08/30/2021 18:30:55 - INFO - __main__ - Step 29968: {'lr': 0.000457225425705642, 'samples': 5753856, 'steps': 29967, 'loss/train': 1.8419651985168457} 08/30/2021 18:30:56 - INFO - __main__ - Step 29969: {'lr': 0.0004572224570964915, 'samples': 5754048, 'steps': 29968, 'loss/train': 1.4746346473693848} 08/30/2021 18:30:56 - INFO - __main__ - Step 29970: {'lr': 0.0004572194883939697, 'samples': 5754240, 'steps': 29969, 'loss/train': 0.20525215566158295} 08/30/2021 18:30:58 - INFO - __main__ - Step 29971: {'lr': 0.0004572165195980781, 'samples': 5754432, 'steps': 29970, 'loss/train': 1.2932289838790894} 08/30/2021 18:30:59 - INFO - __main__ - Step 29972: {'lr': 0.0004572135507088179, 'samples': 5754624, 'steps': 29971, 'loss/train': 1.5811430215835571} 08/30/2021 18:30:59 - INFO - __main__ - Step 29973: {'lr': 0.00045721058172619043, 'samples': 5754816, 'steps': 29972, 'loss/train': 0.12158104032278061} 08/30/2021 18:30:59 - INFO - __main__ - Step 29974: {'lr': 0.0004572076126501972, 'samples': 5755008, 'steps': 29973, 'loss/train': 1.4291597604751587} 08/30/2021 18:31:00 - INFO - __main__ - Step 29975: {'lr': 0.00045720464348083937, 'samples': 5755200, 'steps': 29974, 'loss/train': 1.1311383247375488} 08/30/2021 18:31:00 - INFO - __main__ - Step 29976: {'lr': 0.0004572016742181182, 'samples': 5755392, 'steps': 29975, 'loss/train': 2.0455069541931152} 08/30/2021 18:31:02 - INFO - __main__ - Step 29977: {'lr': 0.0004571987048620353, 'samples': 5755584, 'steps': 29976, 'loss/train': 1.865699052810669} 08/30/2021 18:31:02 - INFO - __main__ - Step 29978: {'lr': 0.0004571957354125918, 'samples': 5755776, 'steps': 29977, 'loss/train': 1.4434974193572998} 08/30/2021 18:31:03 - INFO - __main__ - Step 29979: {'lr': 0.00045719276586978907, 'samples': 5755968, 'steps': 29978, 'loss/train': 1.4251376390457153} 08/30/2021 18:31:03 - INFO - __main__ - Step 29980: {'lr': 0.00045718979623362855, 'samples': 5756160, 'steps': 29979, 'loss/train': 2.0122334957122803} 08/30/2021 18:31:04 - INFO - __main__ - Step 29981: {'lr': 0.00045718682650411146, 'samples': 5756352, 'steps': 29980, 'loss/train': 1.199205994606018} 08/30/2021 18:31:05 - INFO - __main__ - Step 29982: {'lr': 0.0004571838566812392, 'samples': 5756544, 'steps': 29981, 'loss/train': 0.8048202991485596} 08/30/2021 18:31:05 - INFO - __main__ - Step 29983: {'lr': 0.00045718088676501305, 'samples': 5756736, 'steps': 29982, 'loss/train': 1.4998470544815063} 08/30/2021 18:31:06 - INFO - __main__ - Step 29984: {'lr': 0.0004571779167554344, 'samples': 5756928, 'steps': 29983, 'loss/train': 1.5507581233978271} 08/30/2021 18:31:06 - INFO - __main__ - Step 29985: {'lr': 0.0004571749466525046, 'samples': 5757120, 'steps': 29984, 'loss/train': 0.9107785224914551} 08/30/2021 18:31:06 - INFO - __main__ - Step 29986: {'lr': 0.000457171976456225, 'samples': 5757312, 'steps': 29985, 'loss/train': 1.2444286346435547} 08/30/2021 18:31:08 - INFO - __main__ - Step 29987: {'lr': 0.00045716900616659686, 'samples': 5757504, 'steps': 29986, 'loss/train': 1.2106409072875977} 08/30/2021 18:31:08 - INFO - __main__ - Step 29988: {'lr': 0.00045716603578362157, 'samples': 5757696, 'steps': 29987, 'loss/train': 1.3851398229599} 08/30/2021 18:31:09 - INFO - __main__ - Step 29989: {'lr': 0.00045716306530730043, 'samples': 5757888, 'steps': 29988, 'loss/train': 1.0019110441207886} 08/30/2021 18:31:09 - INFO - __main__ - Step 29990: {'lr': 0.00045716009473763486, 'samples': 5758080, 'steps': 29989, 'loss/train': 1.4916727542877197} 08/30/2021 18:31:09 - INFO - __main__ - Step 29991: {'lr': 0.0004571571240746262, 'samples': 5758272, 'steps': 29990, 'loss/train': 1.093345046043396} 08/30/2021 18:31:10 - INFO - __main__ - Step 29992: {'lr': 0.00045715415331827564, 'samples': 5758464, 'steps': 29991, 'loss/train': 1.9349569082260132} 08/30/2021 18:31:11 - INFO - __main__ - Step 29993: {'lr': 0.00045715118246858466, 'samples': 5758656, 'steps': 29992, 'loss/train': 1.2344725131988525} 08/30/2021 18:31:12 - INFO - __main__ - Step 29994: {'lr': 0.0004571482115255545, 'samples': 5758848, 'steps': 29993, 'loss/train': 2.0704667568206787} 08/30/2021 18:31:12 - INFO - __main__ - Step 29995: {'lr': 0.0004571452404891866, 'samples': 5759040, 'steps': 29994, 'loss/train': 1.8195703029632568} 08/30/2021 18:31:12 - INFO - __main__ - Step 29996: {'lr': 0.0004571422693594822, 'samples': 5759232, 'steps': 29995, 'loss/train': 1.6077555418014526} 08/30/2021 18:31:14 - INFO - __main__ - Step 29997: {'lr': 0.00045713929813644274, 'samples': 5759424, 'steps': 29996, 'loss/train': 2.4970226287841797} 08/30/2021 18:31:14 - INFO - __main__ - Step 29998: {'lr': 0.0004571363268200695, 'samples': 5759616, 'steps': 29997, 'loss/train': 1.3227806091308594} 08/30/2021 18:31:15 - INFO - __main__ - Step 29999: {'lr': 0.0004571333554103638, 'samples': 5759808, 'steps': 29998, 'loss/train': 1.6352428197860718} 08/30/2021 18:31:15 - INFO - __main__ - Step 30000: {'lr': 0.0004571303839073271, 'samples': 5760000, 'steps': 29999, 'loss/train': 1.503125548362732} 08/30/2021 18:31:15 - INFO - __main__ - Evaluating model checkpoint 08/30/2021 18:40:00 - INFO - __main__ - Step 30000: {'loss/eval': 1.3865768909454346, 'perplexity': 4.0011305809021} 08/30/2021 18:40:00 - INFO - __main__ - Saving model checkpoint 08/30/2021 18:40:12 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20210830_131354-2654p8r7/logs/debug-internal.log', 'wandb/run-20210830_131354-2654p8r7/run-2654p8r7.wandb']. This may take a bit of time if the files are large. 08/30/2021 18:41:13 - INFO - __main__ - Step 30001: {'lr': 0.00045712741231096054, 'samples': 5760192, 'steps': 30000, 'loss/train': 0.998179018497467} 08/30/2021 18:41:14 - INFO - __main__ - Step 30002: {'lr': 0.0004571244406212656, 'samples': 5760384, 'steps': 30001, 'loss/train': 1.0569742918014526} 08/30/2021 18:41:16 - INFO - __main__ - Step 30003: {'lr': 0.00045712146883824357, 'samples': 5760576, 'steps': 30002, 'loss/train': 1.2649835348129272} 08/30/2021 18:41:16 - INFO - __main__ - Step 30004: {'lr': 0.00045711849696189585, 'samples': 5760768, 'steps': 30003, 'loss/train': 0.07835978269577026} 08/30/2021 18:41:17 - INFO - __main__ - Step 30005: {'lr': 0.0004571155249922237, 'samples': 5760960, 'steps': 30004, 'loss/train': 1.3939626216888428} 08/30/2021 18:41:17 - INFO - __main__ - Step 30006: {'lr': 0.00045711255292922847, 'samples': 5761152, 'steps': 30005, 'loss/train': 0.06290615350008011} 08/30/2021 18:41:17 - INFO - __main__ - Step 30007: {'lr': 0.00045710958077291156, 'samples': 5761344, 'steps': 30006, 'loss/train': 1.1841553449630737} 08/30/2021 18:41:18 - INFO - __main__ - Step 30008: {'lr': 0.00045710660852327423, 'samples': 5761536, 'steps': 30007, 'loss/train': 1.169217824935913} 08/30/2021 18:41:19 - INFO - __main__ - Step 30009: {'lr': 0.00045710363618031783, 'samples': 5761728, 'steps': 30008, 'loss/train': 1.5474317073822021} 08/30/2021 18:41:20 - INFO - __main__ - Step 30010: {'lr': 0.0004571006637440438, 'samples': 5761920, 'steps': 30009, 'loss/train': 1.7704938650131226} 08/30/2021 18:41:20 - INFO - __main__ - Step 30011: {'lr': 0.00045709769121445335, 'samples': 5762112, 'steps': 30010, 'loss/train': 1.5660245418548584} 08/30/2021 18:41:20 - INFO - __main__ - Step 30012: {'lr': 0.00045709471859154793, 'samples': 5762304, 'steps': 30011, 'loss/train': 1.7349765300750732} 08/30/2021 18:41:21 - INFO - __main__ - Step 30013: {'lr': 0.0004570917458753288, 'samples': 5762496, 'steps': 30012, 'loss/train': 0.6215084195137024} 08/30/2021 18:41:22 - INFO - __main__ - Step 30014: {'lr': 0.00045708877306579733, 'samples': 5762688, 'steps': 30013, 'loss/train': 1.8880693912506104} 08/30/2021 18:41:23 - INFO - __main__ - Step 30015: {'lr': 0.00045708580016295486, 'samples': 5762880, 'steps': 30014, 'loss/train': 1.5370018482208252} 08/30/2021 18:41:23 - INFO - __main__ - Step 30016: {'lr': 0.0004570828271668027, 'samples': 5763072, 'steps': 30015, 'loss/train': 1.483174443244934} 08/30/2021 18:41:23 - INFO - __main__ - Step 30017: {'lr': 0.0004570798540773422, 'samples': 5763264, 'steps': 30016, 'loss/train': 1.1573729515075684} 08/30/2021 18:41:24 - INFO - __main__ - Step 30018: {'lr': 0.0004570768808945748, 'samples': 5763456, 'steps': 30017, 'loss/train': 1.114778995513916} 08/30/2021 18:41:26 - INFO - __main__ - Step 30019: {'lr': 0.00045707390761850163, 'samples': 5763648, 'steps': 30018, 'loss/train': 1.649596095085144} 08/30/2021 18:41:26 - INFO - __main__ - Step 30020: {'lr': 0.00045707093424912426, 'samples': 5763840, 'steps': 30019, 'loss/train': 1.4206477403640747} 08/30/2021 18:41:27 - INFO - __main__ - Step 30021: {'lr': 0.00045706796078644386, 'samples': 5764032, 'steps': 30020, 'loss/train': 1.3503787517547607} 08/30/2021 18:41:27 - INFO - __main__ - Step 30022: {'lr': 0.00045706498723046185, 'samples': 5764224, 'steps': 30021, 'loss/train': 0.04716811329126358} 08/30/2021 18:41:27 - INFO - __main__ - Step 30023: {'lr': 0.0004570620135811795, 'samples': 5764416, 'steps': 30022, 'loss/train': 0.066108338534832} 08/30/2021 18:41:28 - INFO - __main__ - Step 30024: {'lr': 0.0004570590398385983, 'samples': 5764608, 'steps': 30023, 'loss/train': 0.515494167804718} 08/30/2021 18:41:30 - INFO - __main__ - Step 30025: {'lr': 0.0004570560660027194, 'samples': 5764800, 'steps': 30024, 'loss/train': 1.3453384637832642} 08/30/2021 18:41:31 - INFO - __main__ - Step 30026: {'lr': 0.00045705309207354433, 'samples': 5764992, 'steps': 30025, 'loss/train': 1.5587120056152344} 08/30/2021 18:41:31 - INFO - __main__ - Step 30027: {'lr': 0.00045705011805107426, 'samples': 5765184, 'steps': 30026, 'loss/train': 0.08149411529302597} 08/30/2021 18:41:31 - INFO - __main__ - Step 30028: {'lr': 0.00045704714393531064, 'samples': 5765376, 'steps': 30027, 'loss/train': 1.3082835674285889} 08/30/2021 18:41:32 - INFO - __main__ - Step 30029: {'lr': 0.00045704416972625474, 'samples': 5765568, 'steps': 30028, 'loss/train': 1.4769291877746582} 08/30/2021 18:41:33 - INFO - __main__ - Step 30030: {'lr': 0.000457041195423908, 'samples': 5765760, 'steps': 30029, 'loss/train': 1.6035698652267456} 08/30/2021 18:41:34 - INFO - __main__ - Step 30031: {'lr': 0.0004570382210282716, 'samples': 5765952, 'steps': 30030, 'loss/train': 0.7443256378173828} 08/30/2021 18:41:34 - INFO - __main__ - Step 30032: {'lr': 0.00045703524653934705, 'samples': 5766144, 'steps': 30031, 'loss/train': 1.4345024824142456} 08/30/2021 18:41:34 - INFO - __main__ - Step 30033: {'lr': 0.0004570322719571355, 'samples': 5766336, 'steps': 30032, 'loss/train': 1.4624621868133545} 08/30/2021 18:41:35 - INFO - __main__ - Step 30034: {'lr': 0.00045702929728163845, 'samples': 5766528, 'steps': 30033, 'loss/train': 0.891118049621582} 08/30/2021 18:41:36 - INFO - __main__ - Step 30035: {'lr': 0.00045702632251285727, 'samples': 5766720, 'steps': 30034, 'loss/train': 1.084511637687683} 08/30/2021 18:41:37 - INFO - __main__ - Step 30036: {'lr': 0.0004570233476507931, 'samples': 5766912, 'steps': 30035, 'loss/train': 1.583155632019043} 08/30/2021 18:41:37 - INFO - __main__ - Step 30037: {'lr': 0.0004570203726954475, 'samples': 5767104, 'steps': 30036, 'loss/train': 1.0263639688491821} 08/30/2021 18:41:38 - INFO - __main__ - Step 30038: {'lr': 0.0004570173976468217, 'samples': 5767296, 'steps': 30037, 'loss/train': 1.6417723894119263} 08/30/2021 18:41:38 - INFO - __main__ - Step 30039: {'lr': 0.0004570144225049171, 'samples': 5767488, 'steps': 30038, 'loss/train': 0.33097851276397705} 08/30/2021 18:41:38 - INFO - __main__ - Step 30040: {'lr': 0.00045701144726973487, 'samples': 5767680, 'steps': 30039, 'loss/train': 1.404439926147461} 08/30/2021 18:41:40 - INFO - __main__ - Step 30041: {'lr': 0.0004570084719412766, 'samples': 5767872, 'steps': 30040, 'loss/train': 1.8676258325576782} 08/30/2021 18:41:40 - INFO - __main__ - Step 30042: {'lr': 0.00045700549651954344, 'samples': 5768064, 'steps': 30041, 'loss/train': 2.0991251468658447} 08/30/2021 18:41:41 - INFO - __main__ - Step 30043: {'lr': 0.0004570025210045368, 'samples': 5768256, 'steps': 30042, 'loss/train': 1.5457230806350708} 08/30/2021 18:41:41 - INFO - __main__ - Step 30044: {'lr': 0.00045699954539625803, 'samples': 5768448, 'steps': 30043, 'loss/train': 0.7517519593238831} 08/30/2021 18:41:41 - INFO - __main__ - Step 30045: {'lr': 0.0004569965696947085, 'samples': 5768640, 'steps': 30044, 'loss/train': 0.6729482412338257} 08/30/2021 18:41:43 - INFO - __main__ - Step 30046: {'lr': 0.00045699359389988944, 'samples': 5768832, 'steps': 30045, 'loss/train': 1.2487704753875732} 08/30/2021 18:41:43 - INFO - __main__ - Step 30047: {'lr': 0.0004569906180118023, 'samples': 5769024, 'steps': 30046, 'loss/train': 2.0153775215148926} 08/30/2021 18:41:44 - INFO - __main__ - Step 30048: {'lr': 0.0004569876420304484, 'samples': 5769216, 'steps': 30047, 'loss/train': 1.7277010679244995} 08/30/2021 18:41:44 - INFO - __main__ - Step 30049: {'lr': 0.000456984665955829, 'samples': 5769408, 'steps': 30048, 'loss/train': 1.4386290311813354} 08/30/2021 18:41:44 - INFO - __main__ - Step 30050: {'lr': 0.00045698168978794553, 'samples': 5769600, 'steps': 30049, 'loss/train': 2.3809890747070312} 08/30/2021 18:41:46 - INFO - __main__ - Step 30051: {'lr': 0.0004569787135267993, 'samples': 5769792, 'steps': 30050, 'loss/train': 1.340345859527588} 08/30/2021 18:41:46 - INFO - __main__ - Step 30052: {'lr': 0.00045697573717239174, 'samples': 5769984, 'steps': 30051, 'loss/train': 1.8033154010772705} 08/30/2021 18:41:47 - INFO - __main__ - Step 30053: {'lr': 0.0004569727607247239, 'samples': 5770176, 'steps': 30052, 'loss/train': 1.4956620931625366} 08/30/2021 18:41:47 - INFO - __main__ - Step 30054: {'lr': 0.00045696978418379754, 'samples': 5770368, 'steps': 30053, 'loss/train': 1.053975224494934} 08/30/2021 18:41:48 - INFO - __main__ - Step 30055: {'lr': 0.0004569668075496137, 'samples': 5770560, 'steps': 30054, 'loss/train': 1.7737561464309692} 08/30/2021 18:41:49 - INFO - __main__ - Step 30056: {'lr': 0.00045696383082217387, 'samples': 5770752, 'steps': 30055, 'loss/train': 1.7106996774673462} 08/30/2021 18:41:50 - INFO - __main__ - Step 30057: {'lr': 0.00045696085400147925, 'samples': 5770944, 'steps': 30056, 'loss/train': 1.1695518493652344} 08/30/2021 18:41:50 - INFO - __main__ - Step 30058: {'lr': 0.00045695787708753126, 'samples': 5771136, 'steps': 30057, 'loss/train': 1.4438533782958984} 08/30/2021 18:41:50 - INFO - __main__ - Step 30059: {'lr': 0.0004569549000803313, 'samples': 5771328, 'steps': 30058, 'loss/train': 1.486721158027649} 08/30/2021 18:41:51 - INFO - __main__ - Step 30060: {'lr': 0.00045695192297988066, 'samples': 5771520, 'steps': 30059, 'loss/train': 1.2105164527893066} 08/30/2021 18:41:52 - INFO - __main__ - Step 30061: {'lr': 0.00045694894578618064, 'samples': 5771712, 'steps': 30060, 'loss/train': 1.2889257669448853} 08/30/2021 18:41:53 - INFO - __main__ - Step 30062: {'lr': 0.00045694596849923263, 'samples': 5771904, 'steps': 30061, 'loss/train': 1.5918667316436768} 08/30/2021 18:41:53 - INFO - __main__ - Step 30063: {'lr': 0.0004569429911190379, 'samples': 5772096, 'steps': 30062, 'loss/train': 2.0897765159606934} 08/30/2021 18:41:54 - INFO - __main__ - Step 30064: {'lr': 0.00045694001364559797, 'samples': 5772288, 'steps': 30063, 'loss/train': 1.5740864276885986} 08/30/2021 18:41:54 - INFO - __main__ - Step 30065: {'lr': 0.00045693703607891403, 'samples': 5772480, 'steps': 30064, 'loss/train': 1.585219144821167} 08/30/2021 18:41:55 - INFO - __main__ - Step 30066: {'lr': 0.0004569340584189874, 'samples': 5772672, 'steps': 30065, 'loss/train': 1.149450421333313} 08/30/2021 18:41:56 - INFO - __main__ - Step 30067: {'lr': 0.0004569310806658195, 'samples': 5772864, 'steps': 30066, 'loss/train': 1.5242985486984253} 08/30/2021 18:41:56 - INFO - __main__ - Step 30068: {'lr': 0.0004569281028194117, 'samples': 5773056, 'steps': 30067, 'loss/train': 1.5530261993408203} 08/30/2021 18:41:57 - INFO - __main__ - Step 30069: {'lr': 0.0004569251248797652, 'samples': 5773248, 'steps': 30068, 'loss/train': 1.6106735467910767} 08/30/2021 18:41:57 - INFO - __main__ - Step 30070: {'lr': 0.0004569221468468815, 'samples': 5773440, 'steps': 30069, 'loss/train': 1.7459301948547363} 08/30/2021 18:41:58 - INFO - __main__ - Step 30071: {'lr': 0.0004569191687207618, 'samples': 5773632, 'steps': 30070, 'loss/train': 1.5610826015472412} 08/30/2021 18:41:59 - INFO - __main__ - Step 30072: {'lr': 0.0004569161905014076, 'samples': 5773824, 'steps': 30071, 'loss/train': 1.1051338911056519} 08/30/2021 18:41:59 - INFO - __main__ - Step 30073: {'lr': 0.0004569132121888201, 'samples': 5774016, 'steps': 30072, 'loss/train': 1.6672340631484985} 08/30/2021 18:42:00 - INFO - __main__ - Step 30074: {'lr': 0.0004569102337830007, 'samples': 5774208, 'steps': 30073, 'loss/train': 1.3058487176895142} 08/30/2021 18:42:00 - INFO - __main__ - Step 30075: {'lr': 0.00045690725528395077, 'samples': 5774400, 'steps': 30074, 'loss/train': 1.5243455171585083} 08/30/2021 18:42:01 - INFO - __main__ - Step 30076: {'lr': 0.0004569042766916717, 'samples': 5774592, 'steps': 30075, 'loss/train': 1.4671909809112549} 08/30/2021 18:42:02 - INFO - __main__ - Step 30077: {'lr': 0.0004569012980061646, 'samples': 5774784, 'steps': 30076, 'loss/train': 1.5543147325515747} 08/30/2021 18:42:02 - INFO - __main__ - Step 30078: {'lr': 0.00045689831922743107, 'samples': 5774976, 'steps': 30077, 'loss/train': 1.1969438791275024} 08/30/2021 18:42:03 - INFO - __main__ - Step 30079: {'lr': 0.0004568953403554723, 'samples': 5775168, 'steps': 30078, 'loss/train': 0.6715759038925171} 08/30/2021 18:42:03 - INFO - __main__ - Step 30080: {'lr': 0.0004568923613902897, 'samples': 5775360, 'steps': 30079, 'loss/train': 1.2134110927581787} 08/30/2021 18:42:05 - INFO - __main__ - Step 30081: {'lr': 0.0004568893823318846, 'samples': 5775552, 'steps': 30080, 'loss/train': 1.4327408075332642} 08/30/2021 18:42:06 - INFO - __main__ - Step 30082: {'lr': 0.0004568864031802583, 'samples': 5775744, 'steps': 30081, 'loss/train': 1.0073317289352417} 08/30/2021 18:42:06 - INFO - __main__ - Step 30083: {'lr': 0.00045688342393541227, 'samples': 5775936, 'steps': 30082, 'loss/train': 2.255936622619629} 08/30/2021 18:42:06 - INFO - __main__ - Step 30084: {'lr': 0.00045688044459734766, 'samples': 5776128, 'steps': 30083, 'loss/train': 0.9807066917419434} 08/30/2021 18:42:07 - INFO - __main__ - Step 30085: {'lr': 0.000456877465166066, 'samples': 5776320, 'steps': 30084, 'loss/train': 1.2674349546432495} 08/30/2021 18:42:08 - INFO - __main__ - Step 30086: {'lr': 0.0004568744856415685, 'samples': 5776512, 'steps': 30085, 'loss/train': 0.4089215397834778} 08/30/2021 18:42:09 - INFO - __main__ - Step 30087: {'lr': 0.0004568715060238565, 'samples': 5776704, 'steps': 30086, 'loss/train': 1.612135887145996} 08/30/2021 18:42:09 - INFO - __main__ - Step 30088: {'lr': 0.0004568685263129315, 'samples': 5776896, 'steps': 30087, 'loss/train': 1.5005519390106201} 08/30/2021 18:42:09 - INFO - __main__ - Step 30089: {'lr': 0.00045686554650879464, 'samples': 5777088, 'steps': 30088, 'loss/train': 0.9640678763389587} 08/30/2021 18:42:10 - INFO - __main__ - Step 30090: {'lr': 0.0004568625666114474, 'samples': 5777280, 'steps': 30089, 'loss/train': 0.14149634540081024} 08/30/2021 18:42:10 - INFO - __main__ - Step 30091: {'lr': 0.00045685958662089113, 'samples': 5777472, 'steps': 30090, 'loss/train': 1.920926570892334} 08/30/2021 18:42:12 - INFO - __main__ - Step 30092: {'lr': 0.000456856606537127, 'samples': 5777664, 'steps': 30091, 'loss/train': 1.578325629234314} 08/30/2021 18:42:13 - INFO - __main__ - Step 30093: {'lr': 0.00045685362636015657, 'samples': 5777856, 'steps': 30092, 'loss/train': 0.09030758589506149} 08/30/2021 18:42:13 - INFO - __main__ - Step 30094: {'lr': 0.00045685064608998107, 'samples': 5778048, 'steps': 30093, 'loss/train': 1.5328689813613892} 08/30/2021 18:42:13 - INFO - __main__ - Step 30095: {'lr': 0.00045684766572660185, 'samples': 5778240, 'steps': 30094, 'loss/train': 1.6309140920639038} 08/30/2021 18:42:14 - INFO - __main__ - Step 30096: {'lr': 0.0004568446852700203, 'samples': 5778432, 'steps': 30095, 'loss/train': 1.8274109363555908} 08/30/2021 18:42:14 - INFO - __main__ - Step 30097: {'lr': 0.00045684170472023766, 'samples': 5778624, 'steps': 30096, 'loss/train': 0.9138599038124084} 08/30/2021 18:42:15 - INFO - __main__ - Step 30098: {'lr': 0.00045683872407725534, 'samples': 5778816, 'steps': 30097, 'loss/train': 0.04247663542628288} 08/30/2021 18:42:16 - INFO - __main__ - Step 30099: {'lr': 0.00045683574334107473, 'samples': 5779008, 'steps': 30098, 'loss/train': 0.7867898344993591} 08/30/2021 18:42:16 - INFO - __main__ - Step 30100: {'lr': 0.00045683276251169713, 'samples': 5779200, 'steps': 30099, 'loss/train': 1.4865630865097046} 08/30/2021 18:42:17 - INFO - __main__ - Step 30101: {'lr': 0.00045682978158912384, 'samples': 5779392, 'steps': 30100, 'loss/train': 1.869196891784668} 08/30/2021 18:42:17 - INFO - __main__ - Step 30102: {'lr': 0.0004568268005733562, 'samples': 5779584, 'steps': 30101, 'loss/train': 1.3848079442977905} 08/30/2021 18:42:17 - INFO - __main__ - Step 30103: {'lr': 0.0004568238194643958, 'samples': 5779776, 'steps': 30102, 'loss/train': 1.322537899017334} 08/30/2021 18:42:19 - INFO - __main__ - Step 30104: {'lr': 0.00045682083826224356, 'samples': 5779968, 'steps': 30103, 'loss/train': 2.3614344596862793} 08/30/2021 18:42:19 - INFO - __main__ - Step 30105: {'lr': 0.00045681785696690113, 'samples': 5780160, 'steps': 30104, 'loss/train': 1.1650716066360474} 08/30/2021 18:42:20 - INFO - __main__ - Step 30106: {'lr': 0.0004568148755783698, 'samples': 5780352, 'steps': 30105, 'loss/train': 0.8741475343704224} 08/30/2021 18:42:20 - INFO - __main__ - Step 30107: {'lr': 0.00045681189409665083, 'samples': 5780544, 'steps': 30106, 'loss/train': 1.3587108850479126} 08/30/2021 18:42:20 - INFO - __main__ - Step 30108: {'lr': 0.00045680891252174557, 'samples': 5780736, 'steps': 30107, 'loss/train': 2.155973434448242} 08/30/2021 18:42:22 - INFO - __main__ - Step 30109: {'lr': 0.0004568059308536554, 'samples': 5780928, 'steps': 30108, 'loss/train': 0.974151074886322} 08/30/2021 18:42:22 - INFO - __main__ - Step 30110: {'lr': 0.00045680294909238175, 'samples': 5781120, 'steps': 30109, 'loss/train': 1.5513627529144287} 08/30/2021 18:42:23 - INFO - __main__ - Step 30111: {'lr': 0.00045679996723792585, 'samples': 5781312, 'steps': 30110, 'loss/train': 0.06620944291353226} 08/30/2021 18:42:23 - INFO - __main__ - Step 30112: {'lr': 0.00045679698529028906, 'samples': 5781504, 'steps': 30111, 'loss/train': 1.436975121498108} 08/30/2021 18:42:23 - INFO - __main__ - Step 30113: {'lr': 0.00045679400324947274, 'samples': 5781696, 'steps': 30112, 'loss/train': 1.0639758110046387} 08/30/2021 18:42:25 - INFO - __main__ - Step 30114: {'lr': 0.00045679102111547825, 'samples': 5781888, 'steps': 30113, 'loss/train': 1.4798959493637085} 08/30/2021 18:42:25 - INFO - __main__ - Step 30115: {'lr': 0.00045678803888830687, 'samples': 5782080, 'steps': 30114, 'loss/train': 1.3769304752349854} 08/30/2021 18:42:26 - INFO - __main__ - Step 30116: {'lr': 0.0004567850565679601, 'samples': 5782272, 'steps': 30115, 'loss/train': 1.1682536602020264} 08/30/2021 18:42:26 - INFO - __main__ - Step 30117: {'lr': 0.00045678207415443913, 'samples': 5782464, 'steps': 30116, 'loss/train': 0.8671473860740662} 08/30/2021 18:42:26 - INFO - __main__ - Step 30118: {'lr': 0.0004567790916477453, 'samples': 5782656, 'steps': 30117, 'loss/train': 1.9146126508712769} 08/30/2021 18:42:28 - INFO - __main__ - Step 30119: {'lr': 0.00045677610904788004, 'samples': 5782848, 'steps': 30118, 'loss/train': 1.7721564769744873} 08/30/2021 18:42:29 - INFO - __main__ - Step 30120: {'lr': 0.00045677312635484466, 'samples': 5783040, 'steps': 30119, 'loss/train': 1.2302154302597046} 08/30/2021 18:42:29 - INFO - __main__ - Step 30121: {'lr': 0.00045677014356864043, 'samples': 5783232, 'steps': 30120, 'loss/train': 1.424653172492981} 08/30/2021 18:42:30 - INFO - __main__ - Step 30122: {'lr': 0.0004567671606892688, 'samples': 5783424, 'steps': 30121, 'loss/train': 1.5457096099853516} 08/30/2021 18:42:30 - INFO - __main__ - Step 30123: {'lr': 0.00045676417771673116, 'samples': 5783616, 'steps': 30122, 'loss/train': 1.249524474143982} 08/30/2021 18:42:30 - INFO - __main__ - Step 30124: {'lr': 0.0004567611946510287, 'samples': 5783808, 'steps': 30123, 'loss/train': 0.048977646976709366} 08/30/2021 18:42:32 - INFO - __main__ - Step 30125: {'lr': 0.00045675821149216285, 'samples': 5784000, 'steps': 30124, 'loss/train': 1.342484474182129} 08/30/2021 18:42:32 - INFO - __main__ - Step 30126: {'lr': 0.00045675522824013495, 'samples': 5784192, 'steps': 30125, 'loss/train': 1.2320334911346436} 08/30/2021 18:42:33 - INFO - __main__ - Step 30127: {'lr': 0.00045675224489494633, 'samples': 5784384, 'steps': 30126, 'loss/train': 1.5247381925582886} 08/30/2021 18:42:33 - INFO - __main__ - Step 30128: {'lr': 0.00045674926145659834, 'samples': 5784576, 'steps': 30127, 'loss/train': 1.5194438695907593} 08/30/2021 18:42:33 - INFO - __main__ - Step 30129: {'lr': 0.0004567462779250923, 'samples': 5784768, 'steps': 30128, 'loss/train': 1.0988644361495972} 08/30/2021 18:42:35 - INFO - __main__ - Step 30130: {'lr': 0.0004567432943004296, 'samples': 5784960, 'steps': 30129, 'loss/train': 1.6423465013504028} 08/30/2021 18:42:35 - INFO - __main__ - Step 30131: {'lr': 0.00045674031058261157, 'samples': 5785152, 'steps': 30130, 'loss/train': 0.9279747009277344} 08/30/2021 18:42:36 - INFO - __main__ - Step 30132: {'lr': 0.0004567373267716395, 'samples': 5785344, 'steps': 30131, 'loss/train': 1.577731966972351} 08/30/2021 18:42:36 - INFO - __main__ - Step 30133: {'lr': 0.0004567343428675148, 'samples': 5785536, 'steps': 30132, 'loss/train': 0.08979174494743347} 08/30/2021 18:42:36 - INFO - __main__ - Step 30134: {'lr': 0.00045673135887023874, 'samples': 5785728, 'steps': 30133, 'loss/train': 1.2370126247406006} 08/30/2021 18:42:39 - INFO - __main__ - Step 30135: {'lr': 0.0004567283747798128, 'samples': 5785920, 'steps': 30134, 'loss/train': 1.1754133701324463} 08/30/2021 18:42:39 - INFO - __main__ - Step 30136: {'lr': 0.0004567253905962383, 'samples': 5786112, 'steps': 30135, 'loss/train': 1.1998401880264282} 08/30/2021 18:42:39 - INFO - __main__ - Step 30137: {'lr': 0.00045672240631951645, 'samples': 5786304, 'steps': 30136, 'loss/train': 1.383865475654602} 08/30/2021 18:42:40 - INFO - __main__ - Step 30138: {'lr': 0.0004567194219496487, 'samples': 5786496, 'steps': 30137, 'loss/train': 1.4130598306655884} 08/30/2021 18:42:40 - INFO - __main__ - Step 30139: {'lr': 0.0004567164374866363, 'samples': 5786688, 'steps': 30138, 'loss/train': 1.578806757926941} 08/30/2021 18:42:42 - INFO - __main__ - Step 30140: {'lr': 0.00045671345293048075, 'samples': 5786880, 'steps': 30139, 'loss/train': 1.3131394386291504} 08/30/2021 18:42:42 - INFO - __main__ - Step 30141: {'lr': 0.00045671046828118324, 'samples': 5787072, 'steps': 30140, 'loss/train': 1.7229034900665283} 08/30/2021 18:42:42 - INFO - __main__ - Step 30142: {'lr': 0.0004567074835387452, 'samples': 5787264, 'steps': 30141, 'loss/train': 1.0348509550094604} 08/30/2021 18:42:43 - INFO - __main__ - Step 30143: {'lr': 0.000456704498703168, 'samples': 5787456, 'steps': 30142, 'loss/train': 1.679243564605713} 08/30/2021 18:42:43 - INFO - __main__ - Step 30144: {'lr': 0.0004567015137744529, 'samples': 5787648, 'steps': 30143, 'loss/train': 1.3586660623550415} 08/30/2021 18:42:45 - INFO - __main__ - Step 30145: {'lr': 0.00045669852875260134, 'samples': 5787840, 'steps': 30144, 'loss/train': 1.4935890436172485} 08/30/2021 18:42:45 - INFO - __main__ - Step 30146: {'lr': 0.00045669554363761454, 'samples': 5788032, 'steps': 30145, 'loss/train': 1.7534693479537964} 08/30/2021 18:42:45 - INFO - __main__ - Step 30147: {'lr': 0.0004566925584294939, 'samples': 5788224, 'steps': 30146, 'loss/train': 1.4882893562316895} 08/30/2021 18:42:46 - INFO - __main__ - Step 30148: {'lr': 0.00045668957312824086, 'samples': 5788416, 'steps': 30147, 'loss/train': 1.5803802013397217} 08/30/2021 18:42:46 - INFO - __main__ - Step 30149: {'lr': 0.00045668658773385663, 'samples': 5788608, 'steps': 30148, 'loss/train': 1.4983325004577637} 08/30/2021 18:42:48 - INFO - __main__ - Step 30150: {'lr': 0.00045668360224634263, 'samples': 5788800, 'steps': 30149, 'loss/train': 1.3118733167648315} 08/30/2021 18:42:48 - INFO - __main__ - Step 30151: {'lr': 0.00045668061666570027, 'samples': 5788992, 'steps': 30150, 'loss/train': 1.634933352470398} 08/30/2021 18:42:48 - INFO - __main__ - Step 30152: {'lr': 0.0004566776309919307, 'samples': 5789184, 'steps': 30151, 'loss/train': 1.7133467197418213} 08/30/2021 18:42:49 - INFO - __main__ - Step 30153: {'lr': 0.0004566746452250354, 'samples': 5789376, 'steps': 30152, 'loss/train': 1.4850605726242065} 08/30/2021 18:42:49 - INFO - __main__ - Step 30154: {'lr': 0.00045667165936501573, 'samples': 5789568, 'steps': 30153, 'loss/train': 1.2529581785202026} 08/30/2021 18:42:51 - INFO - __main__ - Step 30155: {'lr': 0.000456668673411873, 'samples': 5789760, 'steps': 30154, 'loss/train': 1.7884093523025513} 08/30/2021 18:42:51 - INFO - __main__ - Step 30156: {'lr': 0.00045666568736560853, 'samples': 5789952, 'steps': 30155, 'loss/train': 2.024064779281616} 08/30/2021 18:42:51 - INFO - __main__ - Step 30157: {'lr': 0.0004566627012262238, 'samples': 5790144, 'steps': 30156, 'loss/train': 1.4978951215744019} 08/30/2021 18:42:52 - INFO - __main__ - Step 30158: {'lr': 0.0004566597149937199, 'samples': 5790336, 'steps': 30157, 'loss/train': 1.2400438785552979} 08/30/2021 18:42:52 - INFO - __main__ - Step 30159: {'lr': 0.00045665672866809835, 'samples': 5790528, 'steps': 30158, 'loss/train': 1.5105055570602417} 08/30/2021 18:42:52 - INFO - __main__ - Step 30160: {'lr': 0.0004566537422493605, 'samples': 5790720, 'steps': 30159, 'loss/train': 1.6243542432785034} 08/30/2021 18:42:54 - INFO - __main__ - Step 30161: {'lr': 0.00045665075573750764, 'samples': 5790912, 'steps': 30160, 'loss/train': 0.8696616888046265} 08/30/2021 18:42:55 - INFO - __main__ - Step 30162: {'lr': 0.00045664776913254115, 'samples': 5791104, 'steps': 30161, 'loss/train': 1.4763052463531494} 08/30/2021 18:42:55 - INFO - __main__ - Step 30163: {'lr': 0.0004566447824344624, 'samples': 5791296, 'steps': 30162, 'loss/train': 1.5289149284362793} 08/30/2021 18:42:55 - INFO - __main__ - Step 30164: {'lr': 0.00045664179564327266, 'samples': 5791488, 'steps': 30163, 'loss/train': 1.2755883932113647} 08/30/2021 18:42:56 - INFO - __main__ - Step 30165: {'lr': 0.00045663880875897325, 'samples': 5791680, 'steps': 30164, 'loss/train': 1.2715866565704346} 08/30/2021 18:42:57 - INFO - __main__ - Step 30166: {'lr': 0.00045663582178156564, 'samples': 5791872, 'steps': 30165, 'loss/train': 1.1453654766082764} 08/30/2021 18:42:58 - INFO - __main__ - Step 30167: {'lr': 0.00045663283471105115, 'samples': 5792064, 'steps': 30166, 'loss/train': 1.3923983573913574} 08/30/2021 18:42:58 - INFO - __main__ - Step 30168: {'lr': 0.00045662984754743106, 'samples': 5792256, 'steps': 30167, 'loss/train': 1.6533193588256836} 08/30/2021 18:42:58 - INFO - __main__ - Step 30169: {'lr': 0.00045662686029070674, 'samples': 5792448, 'steps': 30168, 'loss/train': 1.6843254566192627} 08/30/2021 18:42:59 - INFO - __main__ - Step 30170: {'lr': 0.0004566238729408796, 'samples': 5792640, 'steps': 30169, 'loss/train': 0.06722897291183472} 08/30/2021 18:43:00 - INFO - __main__ - Step 30171: {'lr': 0.00045662088549795087, 'samples': 5792832, 'steps': 30170, 'loss/train': 1.1034841537475586} 08/30/2021 18:43:01 - INFO - __main__ - Step 30172: {'lr': 0.000456617897961922, 'samples': 5793024, 'steps': 30171, 'loss/train': 1.658542513847351} 08/30/2021 18:43:01 - INFO - __main__ - Step 30173: {'lr': 0.00045661491033279427, 'samples': 5793216, 'steps': 30172, 'loss/train': 0.5844011902809143} 08/30/2021 18:43:01 - INFO - __main__ - Step 30174: {'lr': 0.00045661192261056905, 'samples': 5793408, 'steps': 30173, 'loss/train': 2.0529794692993164} 08/30/2021 18:43:02 - INFO - __main__ - Step 30175: {'lr': 0.00045660893479524767, 'samples': 5793600, 'steps': 30174, 'loss/train': 1.4518444538116455} 08/30/2021 18:43:02 - INFO - __main__ - Step 30176: {'lr': 0.00045660594688683154, 'samples': 5793792, 'steps': 30175, 'loss/train': 1.4589122533798218} 08/30/2021 18:43:03 - INFO - __main__ - Step 30177: {'lr': 0.00045660295888532196, 'samples': 5793984, 'steps': 30176, 'loss/train': 1.7479100227355957} 08/30/2021 18:43:04 - INFO - __main__ - Step 30178: {'lr': 0.00045659997079072024, 'samples': 5794176, 'steps': 30177, 'loss/train': 1.6250731945037842} 08/30/2021 18:43:04 - INFO - __main__ - Step 30179: {'lr': 0.00045659698260302773, 'samples': 5794368, 'steps': 30178, 'loss/train': 1.00252103805542} 08/30/2021 18:43:04 - INFO - __main__ - Step 30180: {'lr': 0.00045659399432224583, 'samples': 5794560, 'steps': 30179, 'loss/train': 1.6312451362609863} 08/30/2021 18:43:05 - INFO - __main__ - Step 30181: {'lr': 0.00045659100594837586, 'samples': 5794752, 'steps': 30180, 'loss/train': 0.9336314797401428} 08/30/2021 18:43:06 - INFO - __main__ - Step 30182: {'lr': 0.0004565880174814192, 'samples': 5794944, 'steps': 30181, 'loss/train': 1.6134107112884521} 08/30/2021 18:43:07 - INFO - __main__ - Step 30183: {'lr': 0.0004565850289213772, 'samples': 5795136, 'steps': 30182, 'loss/train': 1.3392689228057861} 08/30/2021 18:43:07 - INFO - __main__ - Step 30184: {'lr': 0.0004565820402682511, 'samples': 5795328, 'steps': 30183, 'loss/train': 1.3019702434539795} 08/30/2021 18:43:08 - INFO - __main__ - Step 30185: {'lr': 0.00045657905152204236, 'samples': 5795520, 'steps': 30184, 'loss/train': 1.1344388723373413} 08/30/2021 18:43:08 - INFO - __main__ - Step 30186: {'lr': 0.0004565760626827523, 'samples': 5795712, 'steps': 30185, 'loss/train': 1.4040650129318237} 08/30/2021 18:43:09 - INFO - __main__ - Step 30187: {'lr': 0.00045657307375038226, 'samples': 5795904, 'steps': 30186, 'loss/train': 1.4295676946640015} 08/30/2021 18:43:10 - INFO - __main__ - Step 30188: {'lr': 0.00045657008472493356, 'samples': 5796096, 'steps': 30187, 'loss/train': 1.5498725175857544} 08/30/2021 18:43:10 - INFO - __main__ - Step 30189: {'lr': 0.0004565670956064075, 'samples': 5796288, 'steps': 30188, 'loss/train': 1.233457326889038} 08/30/2021 18:43:11 - INFO - __main__ - Step 30190: {'lr': 0.00045656410639480563, 'samples': 5796480, 'steps': 30189, 'loss/train': 1.3556773662567139} 08/30/2021 18:43:11 - INFO - __main__ - Step 30191: {'lr': 0.00045656111709012906, 'samples': 5796672, 'steps': 30190, 'loss/train': 1.4870336055755615} 08/30/2021 18:43:13 - INFO - __main__ - Step 30192: {'lr': 0.00045655812769237927, 'samples': 5796864, 'steps': 30191, 'loss/train': 1.584865689277649} 08/30/2021 18:43:13 - INFO - __main__ - Step 30193: {'lr': 0.00045655513820155755, 'samples': 5797056, 'steps': 30192, 'loss/train': 1.6792405843734741} 08/30/2021 18:43:14 - INFO - __main__ - Step 30194: {'lr': 0.00045655214861766525, 'samples': 5797248, 'steps': 30193, 'loss/train': 1.3730969429016113} 08/30/2021 18:43:14 - INFO - __main__ - Step 30195: {'lr': 0.0004565491589407038, 'samples': 5797440, 'steps': 30194, 'loss/train': 1.281630277633667} 08/30/2021 18:43:14 - INFO - __main__ - Step 30196: {'lr': 0.0004565461691706745, 'samples': 5797632, 'steps': 30195, 'loss/train': 1.7849072217941284} 08/30/2021 18:43:16 - INFO - __main__ - Step 30197: {'lr': 0.0004565431793075786, 'samples': 5797824, 'steps': 30196, 'loss/train': 1.6919240951538086} 08/30/2021 18:43:16 - INFO - __main__ - Step 30198: {'lr': 0.0004565401893514176, 'samples': 5798016, 'steps': 30197, 'loss/train': 1.2529618740081787} 08/30/2021 18:43:17 - INFO - __main__ - Step 30199: {'lr': 0.0004565371993021927, 'samples': 5798208, 'steps': 30198, 'loss/train': 1.8620270490646362} 08/30/2021 18:43:17 - INFO - __main__ - Step 30200: {'lr': 0.00045653420915990546, 'samples': 5798400, 'steps': 30199, 'loss/train': 0.07246321439743042} 08/30/2021 18:43:18 - INFO - __main__ - Step 30201: {'lr': 0.000456531218924557, 'samples': 5798592, 'steps': 30200, 'loss/train': 1.1189396381378174} 08/30/2021 18:43:19 - INFO - __main__ - Step 30202: {'lr': 0.0004565282285961488, 'samples': 5798784, 'steps': 30201, 'loss/train': 1.650571346282959} 08/30/2021 18:43:20 - INFO - __main__ - Step 30203: {'lr': 0.0004565252381746821, 'samples': 5798976, 'steps': 30202, 'loss/train': 1.138083577156067} 08/30/2021 18:43:20 - INFO - __main__ - Step 30204: {'lr': 0.0004565222476601584, 'samples': 5799168, 'steps': 30203, 'loss/train': 1.4301347732543945} 08/30/2021 18:43:20 - INFO - __main__ - Step 30205: {'lr': 0.0004565192570525789, 'samples': 5799360, 'steps': 30204, 'loss/train': 1.7329448461532593} 08/30/2021 18:43:21 - INFO - __main__ - Step 30206: {'lr': 0.00045651626635194497, 'samples': 5799552, 'steps': 30205, 'loss/train': 1.1468639373779297} 08/30/2021 18:43:21 - INFO - __main__ - Step 30207: {'lr': 0.0004565132755582581, 'samples': 5799744, 'steps': 30206, 'loss/train': 1.754542350769043} 08/30/2021 18:43:22 - INFO - __main__ - Step 30208: {'lr': 0.0004565102846715195, 'samples': 5799936, 'steps': 30207, 'loss/train': 1.1099430322647095} 08/30/2021 18:43:23 - INFO - __main__ - Step 30209: {'lr': 0.0004565072936917305, 'samples': 5800128, 'steps': 30208, 'loss/train': 0.9972745180130005} 08/30/2021 18:43:23 - INFO - __main__ - Step 30210: {'lr': 0.0004565043026188926, 'samples': 5800320, 'steps': 30209, 'loss/train': 1.6816481351852417} 08/30/2021 18:43:24 - INFO - __main__ - Step 30211: {'lr': 0.000456501311453007, 'samples': 5800512, 'steps': 30210, 'loss/train': 1.667494297027588} 08/30/2021 18:43:24 - INFO - __main__ - Step 30212: {'lr': 0.00045649832019407504, 'samples': 5800704, 'steps': 30211, 'loss/train': 0.8554044961929321} 08/30/2021 18:43:26 - INFO - __main__ - Step 30213: {'lr': 0.0004564953288420982, 'samples': 5800896, 'steps': 30212, 'loss/train': 1.314995288848877} 08/30/2021 18:43:26 - INFO - __main__ - Step 30214: {'lr': 0.00045649233739707774, 'samples': 5801088, 'steps': 30213, 'loss/train': 1.822932243347168} 08/30/2021 18:43:27 - INFO - __main__ - Step 30215: {'lr': 0.00045648934585901496, 'samples': 5801280, 'steps': 30214, 'loss/train': 2.0202341079711914} 08/30/2021 18:43:27 - INFO - __main__ - Step 30216: {'lr': 0.0004564863542279113, 'samples': 5801472, 'steps': 30215, 'loss/train': 1.5291169881820679} 08/30/2021 18:43:27 - INFO - __main__ - Step 30217: {'lr': 0.0004564833625037681, 'samples': 5801664, 'steps': 30216, 'loss/train': 0.048660457134246826} 08/30/2021 18:43:28 - INFO - __main__ - Step 30218: {'lr': 0.00045648037068658667, 'samples': 5801856, 'steps': 30217, 'loss/train': 0.1317969411611557} 08/30/2021 18:43:29 - INFO - __main__ - Step 30219: {'lr': 0.00045647737877636834, 'samples': 5802048, 'steps': 30218, 'loss/train': 1.5373785495758057} 08/30/2021 18:43:30 - INFO - __main__ - Step 30220: {'lr': 0.0004564743867731145, 'samples': 5802240, 'steps': 30219, 'loss/train': 1.494742512702942} 08/30/2021 18:43:30 - INFO - __main__ - Step 30221: {'lr': 0.0004564713946768265, 'samples': 5802432, 'steps': 30220, 'loss/train': 1.335472583770752} 08/30/2021 18:43:30 - INFO - __main__ - Step 30222: {'lr': 0.0004564684024875057, 'samples': 5802624, 'steps': 30221, 'loss/train': 1.1151351928710938} 08/30/2021 18:43:31 - INFO - __main__ - Step 30223: {'lr': 0.0004564654102051534, 'samples': 5802816, 'steps': 30222, 'loss/train': 2.1353673934936523} 08/30/2021 18:43:33 - INFO - __main__ - Step 30224: {'lr': 0.000456462417829771, 'samples': 5803008, 'steps': 30223, 'loss/train': 1.6881850957870483} 08/30/2021 18:43:33 - INFO - __main__ - Step 30225: {'lr': 0.0004564594253613598, 'samples': 5803200, 'steps': 30224, 'loss/train': 1.6358420848846436} 08/30/2021 18:43:33 - INFO - __main__ - Step 30226: {'lr': 0.0004564564327999211, 'samples': 5803392, 'steps': 30225, 'loss/train': 1.6034457683563232} 08/30/2021 18:43:34 - INFO - __main__ - Step 30227: {'lr': 0.00045645344014545643, 'samples': 5803584, 'steps': 30226, 'loss/train': 1.9370226860046387} 08/30/2021 18:43:34 - INFO - __main__ - Step 30228: {'lr': 0.00045645044739796694, 'samples': 5803776, 'steps': 30227, 'loss/train': 0.7137978076934814} 08/30/2021 18:43:36 - INFO - __main__ - Step 30229: {'lr': 0.00045644745455745414, 'samples': 5803968, 'steps': 30228, 'loss/train': 1.1334476470947266} 08/30/2021 18:43:36 - INFO - __main__ - Step 30230: {'lr': 0.0004564444616239193, 'samples': 5804160, 'steps': 30229, 'loss/train': 1.7633591890335083} 08/30/2021 18:43:37 - INFO - __main__ - Step 30231: {'lr': 0.0004564414685973637, 'samples': 5804352, 'steps': 30230, 'loss/train': 2.0532965660095215} 08/30/2021 18:43:37 - INFO - __main__ - Step 30232: {'lr': 0.0004564384754777888, 'samples': 5804544, 'steps': 30231, 'loss/train': 0.8657008409500122} 08/30/2021 18:43:37 - INFO - __main__ - Step 30233: {'lr': 0.00045643548226519587, 'samples': 5804736, 'steps': 30232, 'loss/train': 1.361954927444458} 08/30/2021 18:43:39 - INFO - __main__ - Step 30234: {'lr': 0.00045643248895958636, 'samples': 5804928, 'steps': 30233, 'loss/train': 1.7255884408950806} 08/30/2021 18:43:40 - INFO - __main__ - Step 30235: {'lr': 0.00045642949556096146, 'samples': 5805120, 'steps': 30234, 'loss/train': 1.2330719232559204} 08/30/2021 18:43:40 - INFO - __main__ - Step 30236: {'lr': 0.0004564265020693227, 'samples': 5805312, 'steps': 30235, 'loss/train': 1.0297609567642212} 08/30/2021 18:43:40 - INFO - __main__ - Step 30237: {'lr': 0.0004564235084846713, 'samples': 5805504, 'steps': 30236, 'loss/train': 0.3304782509803772} 08/30/2021 18:43:41 - INFO - __main__ - Step 30238: {'lr': 0.00045642051480700873, 'samples': 5805696, 'steps': 30237, 'loss/train': 1.4655193090438843} 08/30/2021 18:43:43 - INFO - __main__ - Step 30239: {'lr': 0.0004564175210363362, 'samples': 5805888, 'steps': 30238, 'loss/train': 1.2773939371109009} 08/30/2021 18:43:43 - INFO - __main__ - Step 30240: {'lr': 0.00045641452717265507, 'samples': 5806080, 'steps': 30239, 'loss/train': 1.745729923248291} 08/30/2021 18:43:43 - INFO - __main__ - Step 30241: {'lr': 0.00045641153321596687, 'samples': 5806272, 'steps': 30240, 'loss/train': 1.2591203451156616} 08/30/2021 18:43:44 - INFO - __main__ - Step 30242: {'lr': 0.0004564085391662727, 'samples': 5806464, 'steps': 30241, 'loss/train': 1.8606942892074585} 08/30/2021 18:43:44 - INFO - __main__ - Step 30243: {'lr': 0.00045640554502357413, 'samples': 5806656, 'steps': 30242, 'loss/train': 1.4952788352966309} 08/30/2021 18:43:45 - INFO - __main__ - Step 30244: {'lr': 0.0004564025507878723, 'samples': 5806848, 'steps': 30243, 'loss/train': 0.05463343858718872} 08/30/2021 18:43:46 - INFO - __main__ - Step 30245: {'lr': 0.00045639955645916875, 'samples': 5807040, 'steps': 30244, 'loss/train': 1.0868946313858032} 08/30/2021 18:43:47 - INFO - __main__ - Step 30246: {'lr': 0.0004563965620374647, 'samples': 5807232, 'steps': 30245, 'loss/train': 1.633384108543396} 08/30/2021 18:43:47 - INFO - __main__ - Step 30247: {'lr': 0.0004563935675227615, 'samples': 5807424, 'steps': 30246, 'loss/train': 2.012517213821411} 08/30/2021 18:43:48 - INFO - __main__ - Step 30248: {'lr': 0.00045639057291506065, 'samples': 5807616, 'steps': 30247, 'loss/train': 1.6251734495162964} 08/30/2021 18:43:48 - INFO - __main__ - Step 30249: {'lr': 0.0004563875782143633, 'samples': 5807808, 'steps': 30248, 'loss/train': 1.6240020990371704} 08/30/2021 18:43:50 - INFO - __main__ - Step 30250: {'lr': 0.000456384583420671, 'samples': 5808000, 'steps': 30249, 'loss/train': 1.500151515007019} 08/30/2021 18:43:50 - INFO - __main__ - Step 30251: {'lr': 0.0004563815885339849, 'samples': 5808192, 'steps': 30250, 'loss/train': 1.3753119707107544} 08/30/2021 18:43:50 - INFO - __main__ - Step 30252: {'lr': 0.00045637859355430647, 'samples': 5808384, 'steps': 30251, 'loss/train': 3.035808801651001} 08/30/2021 18:43:51 - INFO - __main__ - Step 30253: {'lr': 0.000456375598481637, 'samples': 5808576, 'steps': 30252, 'loss/train': 1.6513733863830566} 08/30/2021 18:43:51 - INFO - __main__ - Step 30254: {'lr': 0.00045637260331597793, 'samples': 5808768, 'steps': 30253, 'loss/train': 1.4726425409317017} 08/30/2021 18:43:52 - INFO - __main__ - Step 30255: {'lr': 0.00045636960805733054, 'samples': 5808960, 'steps': 30254, 'loss/train': 1.8462722301483154} 08/30/2021 18:43:53 - INFO - __main__ - Step 30256: {'lr': 0.0004563666127056961, 'samples': 5809152, 'steps': 30255, 'loss/train': 1.6160821914672852} 08/30/2021 18:43:54 - INFO - __main__ - Step 30257: {'lr': 0.0004563636172610761, 'samples': 5809344, 'steps': 30256, 'loss/train': 1.7190073728561401} 08/30/2021 18:43:54 - INFO - __main__ - Step 30258: {'lr': 0.00045636062172347186, 'samples': 5809536, 'steps': 30257, 'loss/train': 1.7073683738708496} 08/30/2021 18:43:55 - INFO - __main__ - Step 30259: {'lr': 0.0004563576260928847, 'samples': 5809728, 'steps': 30258, 'loss/train': 1.3867048025131226} 08/30/2021 18:43:55 - INFO - __main__ - Step 30260: {'lr': 0.000456354630369316, 'samples': 5809920, 'steps': 30259, 'loss/train': 1.340516448020935} 08/30/2021 18:43:57 - INFO - __main__ - Step 30261: {'lr': 0.00045635163455276707, 'samples': 5810112, 'steps': 30260, 'loss/train': 1.2688188552856445} 08/30/2021 18:43:57 - INFO - __main__ - Step 30262: {'lr': 0.0004563486386432393, 'samples': 5810304, 'steps': 30261, 'loss/train': 1.3179888725280762} 08/30/2021 18:43:57 - INFO - __main__ - Step 30263: {'lr': 0.00045634564264073396, 'samples': 5810496, 'steps': 30262, 'loss/train': 1.367193579673767} 08/30/2021 18:43:58 - INFO - __main__ - Step 30264: {'lr': 0.0004563426465452525, 'samples': 5810688, 'steps': 30263, 'loss/train': 2.21877121925354} 08/30/2021 18:43:58 - INFO - __main__ - Step 30265: {'lr': 0.00045633965035679614, 'samples': 5810880, 'steps': 30264, 'loss/train': 1.3574408292770386} 08/30/2021 18:44:00 - INFO - __main__ - Step 30266: {'lr': 0.0004563366540753664, 'samples': 5811072, 'steps': 30265, 'loss/train': 0.5013177990913391} 08/30/2021 18:44:00 - INFO - __main__ - Step 30267: {'lr': 0.00045633365770096456, 'samples': 5811264, 'steps': 30266, 'loss/train': 1.197783350944519} 08/30/2021 18:44:00 - INFO - __main__ - Step 30268: {'lr': 0.000456330661233592, 'samples': 5811456, 'steps': 30267, 'loss/train': 1.3258761167526245} 08/30/2021 18:44:01 - INFO - __main__ - Step 30269: {'lr': 0.00045632766467324995, 'samples': 5811648, 'steps': 30268, 'loss/train': 1.1505438089370728} 08/30/2021 18:44:01 - INFO - __main__ - Step 30270: {'lr': 0.0004563246680199398, 'samples': 5811840, 'steps': 30269, 'loss/train': 1.3651236295700073} 08/30/2021 18:44:03 - INFO - __main__ - Step 30271: {'lr': 0.000456321671273663, 'samples': 5812032, 'steps': 30270, 'loss/train': 1.547912359237671} 08/30/2021 18:44:03 - INFO - __main__ - Step 30272: {'lr': 0.00045631867443442084, 'samples': 5812224, 'steps': 30271, 'loss/train': 1.3571466207504272} 08/30/2021 18:44:03 - INFO - __main__ - Step 30273: {'lr': 0.00045631567750221465, 'samples': 5812416, 'steps': 30272, 'loss/train': 0.5563685894012451} 08/30/2021 18:44:04 - INFO - __main__ - Step 30274: {'lr': 0.0004563126804770458, 'samples': 5812608, 'steps': 30273, 'loss/train': 0.21116133034229279} 08/30/2021 18:44:04 - INFO - __main__ - Step 30275: {'lr': 0.00045630968335891564, 'samples': 5812800, 'steps': 30274, 'loss/train': 1.1514426469802856} 08/30/2021 18:44:06 - INFO - __main__ - Step 30276: {'lr': 0.00045630668614782553, 'samples': 5812992, 'steps': 30275, 'loss/train': 1.4305827617645264} 08/30/2021 18:44:06 - INFO - __main__ - Step 30277: {'lr': 0.0004563036888437768, 'samples': 5813184, 'steps': 30276, 'loss/train': 1.6732763051986694} 08/30/2021 18:44:07 - INFO - __main__ - Step 30278: {'lr': 0.0004563006914467709, 'samples': 5813376, 'steps': 30277, 'loss/train': 1.6876115798950195} 08/30/2021 18:44:07 - INFO - __main__ - Step 30279: {'lr': 0.000456297693956809, 'samples': 5813568, 'steps': 30278, 'loss/train': 2.2432475090026855} 08/30/2021 18:44:07 - INFO - __main__ - Step 30280: {'lr': 0.0004562946963738925, 'samples': 5813760, 'steps': 30279, 'loss/train': 0.1259242445230484} 08/30/2021 18:44:09 - INFO - __main__ - Step 30281: {'lr': 0.0004562916986980229, 'samples': 5813952, 'steps': 30280, 'loss/train': 1.3225913047790527} 08/30/2021 18:44:09 - INFO - __main__ - Step 30282: {'lr': 0.0004562887009292014, 'samples': 5814144, 'steps': 30281, 'loss/train': 1.4863812923431396} 08/30/2021 18:44:10 - INFO - __main__ - Step 30283: {'lr': 0.0004562857030674293, 'samples': 5814336, 'steps': 30282, 'loss/train': 2.1995954513549805} 08/30/2021 18:44:10 - INFO - __main__ - Step 30284: {'lr': 0.0004562827051127082, 'samples': 5814528, 'steps': 30283, 'loss/train': 1.700416088104248} 08/30/2021 18:44:10 - INFO - __main__ - Step 30285: {'lr': 0.0004562797070650392, 'samples': 5814720, 'steps': 30284, 'loss/train': 1.8413176536560059} 08/30/2021 18:44:11 - INFO - __main__ - Step 30286: {'lr': 0.00045627670892442376, 'samples': 5814912, 'steps': 30285, 'loss/train': 1.8634073734283447} 08/30/2021 18:44:12 - INFO - __main__ - Step 30287: {'lr': 0.0004562737106908632, 'samples': 5815104, 'steps': 30286, 'loss/train': 0.5496020913124084} 08/30/2021 18:44:13 - INFO - __main__ - Step 30288: {'lr': 0.00045627071236435896, 'samples': 5815296, 'steps': 30287, 'loss/train': 1.1342387199401855} 08/30/2021 18:44:13 - INFO - __main__ - Step 30289: {'lr': 0.0004562677139449123, 'samples': 5815488, 'steps': 30288, 'loss/train': 1.2350637912750244} 08/30/2021 18:44:13 - INFO - __main__ - Step 30290: {'lr': 0.0004562647154325246, 'samples': 5815680, 'steps': 30289, 'loss/train': 1.3664730787277222} 08/30/2021 18:44:14 - INFO - __main__ - Step 30291: {'lr': 0.0004562617168271971, 'samples': 5815872, 'steps': 30290, 'loss/train': 1.5584747791290283} 08/30/2021 18:44:15 - INFO - __main__ - Step 30292: {'lr': 0.0004562587181289314, 'samples': 5816064, 'steps': 30291, 'loss/train': 1.0992379188537598} 08/30/2021 18:44:16 - INFO - __main__ - Step 30293: {'lr': 0.00045625571933772857, 'samples': 5816256, 'steps': 30292, 'loss/train': 1.3232252597808838} 08/30/2021 18:44:16 - INFO - __main__ - Step 30294: {'lr': 0.0004562527204535902, 'samples': 5816448, 'steps': 30293, 'loss/train': 1.5896888971328735} 08/30/2021 18:44:16 - INFO - __main__ - Step 30295: {'lr': 0.00045624972147651746, 'samples': 5816640, 'steps': 30294, 'loss/train': 1.650687336921692} 08/30/2021 18:44:17 - INFO - __main__ - Step 30296: {'lr': 0.00045624672240651183, 'samples': 5816832, 'steps': 30295, 'loss/train': 1.091670274734497} 08/30/2021 18:44:19 - INFO - __main__ - Step 30297: {'lr': 0.00045624372324357457, 'samples': 5817024, 'steps': 30296, 'loss/train': 1.6191810369491577} 08/30/2021 18:44:19 - INFO - __main__ - Step 30298: {'lr': 0.0004562407239877071, 'samples': 5817216, 'steps': 30297, 'loss/train': 1.0923471450805664} 08/30/2021 18:44:20 - INFO - __main__ - Step 30299: {'lr': 0.0004562377246389108, 'samples': 5817408, 'steps': 30298, 'loss/train': 1.4671701192855835} 08/30/2021 18:44:20 - INFO - __main__ - Step 30300: {'lr': 0.00045623472519718683, 'samples': 5817600, 'steps': 30299, 'loss/train': 1.7130595445632935} 08/30/2021 18:44:20 - INFO - __main__ - Step 30301: {'lr': 0.00045623172566253676, 'samples': 5817792, 'steps': 30300, 'loss/train': 1.9406265020370483} 08/30/2021 18:44:22 - INFO - __main__ - Step 30302: {'lr': 0.00045622872603496184, 'samples': 5817984, 'steps': 30301, 'loss/train': 1.835220217704773} 08/30/2021 18:44:22 - INFO - __main__ - Step 30303: {'lr': 0.0004562257263144635, 'samples': 5818176, 'steps': 30302, 'loss/train': 1.2928903102874756} 08/30/2021 18:44:23 - INFO - __main__ - Step 30304: {'lr': 0.0004562227265010429, 'samples': 5818368, 'steps': 30303, 'loss/train': 1.152180552482605} 08/30/2021 18:44:23 - INFO - __main__ - Step 30305: {'lr': 0.00045621972659470156, 'samples': 5818560, 'steps': 30304, 'loss/train': 1.1183836460113525} 08/30/2021 18:44:23 - INFO - __main__ - Step 30306: {'lr': 0.0004562167265954409, 'samples': 5818752, 'steps': 30305, 'loss/train': 1.7545011043548584} 08/30/2021 18:44:25 - INFO - __main__ - Step 30307: {'lr': 0.000456213726503262, 'samples': 5818944, 'steps': 30306, 'loss/train': 1.2700676918029785} 08/30/2021 18:44:25 - INFO - __main__ - Step 30308: {'lr': 0.0004562107263181665, 'samples': 5819136, 'steps': 30307, 'loss/train': 1.3349676132202148} 08/30/2021 18:44:26 - INFO - __main__ - Step 30309: {'lr': 0.0004562077260401556, 'samples': 5819328, 'steps': 30308, 'loss/train': 1.5274112224578857} 08/30/2021 18:44:26 - INFO - __main__ - Step 30310: {'lr': 0.00045620472566923064, 'samples': 5819520, 'steps': 30309, 'loss/train': 1.1159486770629883} 08/30/2021 18:44:26 - INFO - __main__ - Step 30311: {'lr': 0.0004562017252053931, 'samples': 5819712, 'steps': 30310, 'loss/train': 2.038820505142212} 08/30/2021 18:44:27 - INFO - __main__ - Step 30312: {'lr': 0.0004561987246486442, 'samples': 5819904, 'steps': 30311, 'loss/train': 1.2197567224502563} 08/30/2021 18:44:28 - INFO - __main__ - Step 30313: {'lr': 0.00045619572399898534, 'samples': 5820096, 'steps': 30312, 'loss/train': 1.556435227394104} 08/30/2021 18:44:29 - INFO - __main__ - Step 30314: {'lr': 0.0004561927232564179, 'samples': 5820288, 'steps': 30313, 'loss/train': 2.0947604179382324} 08/30/2021 18:44:29 - INFO - __main__ - Step 30315: {'lr': 0.00045618972242094313, 'samples': 5820480, 'steps': 30314, 'loss/train': 1.6830512285232544} 08/30/2021 18:44:30 - INFO - __main__ - Step 30316: {'lr': 0.00045618672149256244, 'samples': 5820672, 'steps': 30315, 'loss/train': 4.369750499725342} 08/30/2021 18:44:30 - INFO - __main__ - Step 30317: {'lr': 0.0004561837204712773, 'samples': 5820864, 'steps': 30316, 'loss/train': 1.4061806201934814} 08/30/2021 18:44:31 - INFO - __main__ - Step 30318: {'lr': 0.0004561807193570888, 'samples': 5821056, 'steps': 30317, 'loss/train': 1.1020888090133667} 08/30/2021 18:44:32 - INFO - __main__ - Step 30319: {'lr': 0.0004561777181499986, 'samples': 5821248, 'steps': 30318, 'loss/train': 1.3973207473754883} 08/30/2021 18:44:32 - INFO - __main__ - Step 30320: {'lr': 0.00045617471685000785, 'samples': 5821440, 'steps': 30319, 'loss/train': 1.3725110292434692} 08/30/2021 18:44:33 - INFO - __main__ - Step 30321: {'lr': 0.00045617171545711793, 'samples': 5821632, 'steps': 30320, 'loss/train': 1.4897971153259277} 08/30/2021 18:44:33 - INFO - __main__ - Step 30322: {'lr': 0.0004561687139713302, 'samples': 5821824, 'steps': 30321, 'loss/train': 1.5724416971206665} 08/30/2021 18:44:34 - INFO - __main__ - Step 30323: {'lr': 0.00045616571239264614, 'samples': 5822016, 'steps': 30322, 'loss/train': 3.423105239868164} 08/30/2021 18:44:35 - INFO - __main__ - Step 30324: {'lr': 0.0004561627107210669, 'samples': 5822208, 'steps': 30323, 'loss/train': 1.1945616006851196} 08/30/2021 18:44:35 - INFO - __main__ - Step 30325: {'lr': 0.00045615970895659393, 'samples': 5822400, 'steps': 30324, 'loss/train': 1.3767011165618896} 08/30/2021 18:44:36 - INFO - __main__ - Step 30326: {'lr': 0.00045615670709922855, 'samples': 5822592, 'steps': 30325, 'loss/train': 1.2165873050689697} 08/30/2021 18:44:36 - INFO - __main__ - Step 30327: {'lr': 0.0004561537051489722, 'samples': 5822784, 'steps': 30326, 'loss/train': 1.6331738233566284} 08/30/2021 18:44:38 - INFO - __main__ - Step 30328: {'lr': 0.00045615070310582617, 'samples': 5822976, 'steps': 30327, 'loss/train': 1.5106899738311768} 08/30/2021 18:44:38 - INFO - __main__ - Step 30329: {'lr': 0.00045614770096979177, 'samples': 5823168, 'steps': 30328, 'loss/train': 1.4452539682388306} 08/30/2021 18:44:39 - INFO - __main__ - Step 30330: {'lr': 0.0004561446987408704, 'samples': 5823360, 'steps': 30329, 'loss/train': 1.6874357461929321} 08/30/2021 18:44:39 - INFO - __main__ - Step 30331: {'lr': 0.00045614169641906344, 'samples': 5823552, 'steps': 30330, 'loss/train': 1.418391466140747} 08/30/2021 18:44:39 - INFO - __main__ - Step 30332: {'lr': 0.00045613869400437223, 'samples': 5823744, 'steps': 30331, 'loss/train': 1.51357102394104} 08/30/2021 18:44:40 - INFO - __main__ - Step 30333: {'lr': 0.000456135691496798, 'samples': 5823936, 'steps': 30332, 'loss/train': 2.1403818130493164} 08/30/2021 18:44:41 - INFO - __main__ - Step 30334: {'lr': 0.0004561326888963423, 'samples': 5824128, 'steps': 30333, 'loss/train': 0.5983277559280396} 08/30/2021 18:44:42 - INFO - __main__ - Step 30335: {'lr': 0.0004561296862030064, 'samples': 5824320, 'steps': 30334, 'loss/train': 2.2367749214172363} 08/30/2021 18:44:42 - INFO - __main__ - Step 30336: {'lr': 0.00045612668341679164, 'samples': 5824512, 'steps': 30335, 'loss/train': 1.6840192079544067} 08/30/2021 18:44:42 - INFO - __main__ - Step 30337: {'lr': 0.0004561236805376994, 'samples': 5824704, 'steps': 30336, 'loss/train': 1.0896717309951782} 08/30/2021 18:44:43 - INFO - __main__ - Step 30338: {'lr': 0.00045612067756573097, 'samples': 5824896, 'steps': 30337, 'loss/train': 1.8446327447891235} 08/30/2021 18:44:44 - INFO - __main__ - Step 30339: {'lr': 0.0004561176745008877, 'samples': 5825088, 'steps': 30338, 'loss/train': 1.6288559436798096} 08/30/2021 18:44:45 - INFO - __main__ - Step 30340: {'lr': 0.000456114671343171, 'samples': 5825280, 'steps': 30339, 'loss/train': 0.8107740879058838} 08/30/2021 18:44:45 - INFO - __main__ - Step 30341: {'lr': 0.00045611166809258227, 'samples': 5825472, 'steps': 30340, 'loss/train': 1.2054505348205566} 08/30/2021 18:44:45 - INFO - __main__ - Step 30342: {'lr': 0.0004561086647491227, 'samples': 5825664, 'steps': 30341, 'loss/train': 1.3367034196853638} 08/30/2021 18:44:46 - INFO - __main__ - Step 30343: {'lr': 0.00045610566131279386, 'samples': 5825856, 'steps': 30342, 'loss/train': 1.408198356628418} 08/30/2021 18:44:47 - INFO - __main__ - Step 30344: {'lr': 0.00045610265778359696, 'samples': 5826048, 'steps': 30343, 'loss/train': 2.10677433013916} 08/30/2021 18:44:48 - INFO - __main__ - Step 30345: {'lr': 0.00045609965416153333, 'samples': 5826240, 'steps': 30344, 'loss/train': 1.135197401046753} 08/30/2021 18:44:48 - INFO - __main__ - Step 30346: {'lr': 0.0004560966504466044, 'samples': 5826432, 'steps': 30345, 'loss/train': 1.3828952312469482} 08/30/2021 18:44:48 - INFO - __main__ - Step 30347: {'lr': 0.00045609364663881153, 'samples': 5826624, 'steps': 30346, 'loss/train': 0.8147543668746948} 08/30/2021 18:44:49 - INFO - __main__ - Step 30348: {'lr': 0.000456090642738156, 'samples': 5826816, 'steps': 30347, 'loss/train': 1.7437959909439087} 08/30/2021 18:44:49 - INFO - __main__ - Step 30349: {'lr': 0.00045608763874463925, 'samples': 5827008, 'steps': 30348, 'loss/train': 1.5902305841445923} 08/30/2021 18:44:51 - INFO - __main__ - Step 30350: {'lr': 0.00045608463465826257, 'samples': 5827200, 'steps': 30349, 'loss/train': 1.5159223079681396} 08/30/2021 18:44:51 - INFO - __main__ - Step 30351: {'lr': 0.0004560816304790274, 'samples': 5827392, 'steps': 30350, 'loss/train': 1.2611470222473145} 08/30/2021 18:44:51 - INFO - __main__ - Step 30352: {'lr': 0.0004560786262069349, 'samples': 5827584, 'steps': 30351, 'loss/train': 1.564341425895691} 08/30/2021 18:44:52 - INFO - __main__ - Step 30353: {'lr': 0.00045607562184198666, 'samples': 5827776, 'steps': 30352, 'loss/train': 1.856213927268982} 08/30/2021 18:44:52 - INFO - __main__ - Step 30354: {'lr': 0.00045607261738418384, 'samples': 5827968, 'steps': 30353, 'loss/train': 1.079045295715332} 08/30/2021 18:44:54 - INFO - __main__ - Step 30355: {'lr': 0.00045606961283352793, 'samples': 5828160, 'steps': 30354, 'loss/train': 1.1943246126174927} 08/30/2021 18:44:55 - INFO - __main__ - Step 30356: {'lr': 0.0004560666081900202, 'samples': 5828352, 'steps': 30355, 'loss/train': 1.3076484203338623} 08/30/2021 18:44:55 - INFO - __main__ - Step 30357: {'lr': 0.00045606360345366203, 'samples': 5828544, 'steps': 30356, 'loss/train': 2.0070269107818604} 08/30/2021 18:44:55 - INFO - __main__ - Step 30358: {'lr': 0.00045606059862445485, 'samples': 5828736, 'steps': 30357, 'loss/train': 1.4410141706466675} 08/30/2021 18:44:56 - INFO - __main__ - Step 30359: {'lr': 0.0004560575937023999, 'samples': 5828928, 'steps': 30358, 'loss/train': 1.287891149520874} 08/30/2021 18:44:56 - INFO - __main__ - Step 30360: {'lr': 0.0004560545886874986, 'samples': 5829120, 'steps': 30359, 'loss/train': 1.121692180633545} 08/30/2021 18:44:58 - INFO - __main__ - Step 30361: {'lr': 0.00045605158357975225, 'samples': 5829312, 'steps': 30360, 'loss/train': 0.9509807825088501} 08/30/2021 18:44:58 - INFO - __main__ - Step 30362: {'lr': 0.00045604857837916224, 'samples': 5829504, 'steps': 30361, 'loss/train': 1.219749927520752} 08/30/2021 18:44:58 - INFO - __main__ - Step 30363: {'lr': 0.0004560455730857299, 'samples': 5829696, 'steps': 30362, 'loss/train': 1.771064043045044} 08/30/2021 18:44:59 - INFO - __main__ - Step 30364: {'lr': 0.0004560425676994566, 'samples': 5829888, 'steps': 30363, 'loss/train': 2.072871208190918} 08/30/2021 18:44:59 - INFO - __main__ - Step 30365: {'lr': 0.00045603956222034384, 'samples': 5830080, 'steps': 30364, 'loss/train': 1.4741034507751465} 08/30/2021 18:45:00 - INFO - __main__ - Step 30366: {'lr': 0.0004560365566483927, 'samples': 5830272, 'steps': 30365, 'loss/train': 1.9049711227416992} 08/30/2021 18:45:01 - INFO - __main__ - Step 30367: {'lr': 0.00045603355098360466, 'samples': 5830464, 'steps': 30366, 'loss/train': 1.1554251909255981} 08/30/2021 18:45:01 - INFO - __main__ - Step 30368: {'lr': 0.00045603054522598107, 'samples': 5830656, 'steps': 30367, 'loss/train': 1.33742094039917} 08/30/2021 18:45:02 - INFO - __main__ - Step 30369: {'lr': 0.0004560275393755233, 'samples': 5830848, 'steps': 30368, 'loss/train': 1.3915207386016846} 08/30/2021 18:45:02 - INFO - __main__ - Step 30370: {'lr': 0.0004560245334322328, 'samples': 5831040, 'steps': 30369, 'loss/train': 1.3620425462722778} 08/30/2021 18:45:03 - INFO - __main__ - Step 30371: {'lr': 0.00045602152739611075, 'samples': 5831232, 'steps': 30370, 'loss/train': 1.658311367034912} 08/30/2021 18:45:04 - INFO - __main__ - Step 30372: {'lr': 0.0004560185212671586, 'samples': 5831424, 'steps': 30371, 'loss/train': 1.6842811107635498} 08/30/2021 18:45:04 - INFO - __main__ - Step 30373: {'lr': 0.00045601551504537765, 'samples': 5831616, 'steps': 30372, 'loss/train': 1.5125207901000977} 08/30/2021 18:45:05 - INFO - __main__ - Step 30374: {'lr': 0.0004560125087307693, 'samples': 5831808, 'steps': 30373, 'loss/train': 1.4070923328399658} 08/30/2021 18:45:05 - INFO - __main__ - Step 30375: {'lr': 0.00045600950232333495, 'samples': 5832000, 'steps': 30374, 'loss/train': 1.6056480407714844} 08/30/2021 18:45:07 - INFO - __main__ - Step 30376: {'lr': 0.00045600649582307586, 'samples': 5832192, 'steps': 30375, 'loss/train': 1.4013153314590454} 08/30/2021 18:45:07 - INFO - __main__ - Step 30377: {'lr': 0.00045600348922999334, 'samples': 5832384, 'steps': 30376, 'loss/train': 2.0876340866088867} 08/30/2021 18:45:07 - INFO - __main__ - Step 30378: {'lr': 0.0004560004825440889, 'samples': 5832576, 'steps': 30377, 'loss/train': 1.4471242427825928} 08/30/2021 18:45:08 - INFO - __main__ - Step 30379: {'lr': 0.0004559974757653639, 'samples': 5832768, 'steps': 30378, 'loss/train': 1.370341420173645} 08/30/2021 18:45:08 - INFO - __main__ - Step 30380: {'lr': 0.0004559944688938195, 'samples': 5832960, 'steps': 30379, 'loss/train': 0.9219102263450623} 08/30/2021 18:45:10 - INFO - __main__ - Step 30381: {'lr': 0.0004559914619294572, 'samples': 5833152, 'steps': 30380, 'loss/train': 1.3011467456817627} 08/30/2021 18:45:10 - INFO - __main__ - Step 30382: {'lr': 0.00045598845487227835, 'samples': 5833344, 'steps': 30381, 'loss/train': 1.8089731931686401} 08/30/2021 18:45:10 - INFO - __main__ - Step 30383: {'lr': 0.0004559854477222842, 'samples': 5833536, 'steps': 30382, 'loss/train': 0.9662899971008301} 08/30/2021 18:45:11 - INFO - __main__ - Step 30384: {'lr': 0.0004559824404794763, 'samples': 5833728, 'steps': 30383, 'loss/train': 1.0928486585617065} 08/30/2021 18:45:11 - INFO - __main__ - Step 30385: {'lr': 0.0004559794331438558, 'samples': 5833920, 'steps': 30384, 'loss/train': 1.5999665260314941} 08/30/2021 18:45:13 - INFO - __main__ - Step 30386: {'lr': 0.0004559764257154242, 'samples': 5834112, 'steps': 30385, 'loss/train': 1.3363968133926392} 08/30/2021 18:45:13 - INFO - __main__ - Step 30387: {'lr': 0.0004559734181941828, 'samples': 5834304, 'steps': 30386, 'loss/train': 0.4445675015449524} 08/30/2021 18:45:14 - INFO - __main__ - Step 30388: {'lr': 0.0004559704105801329, 'samples': 5834496, 'steps': 30387, 'loss/train': 0.03256768360733986} 08/30/2021 18:45:14 - INFO - __main__ - Step 30389: {'lr': 0.00045596740287327597, 'samples': 5834688, 'steps': 30388, 'loss/train': 1.8979212045669556} 08/30/2021 18:45:14 - INFO - __main__ - Step 30390: {'lr': 0.0004559643950736133, 'samples': 5834880, 'steps': 30389, 'loss/train': 1.4951472282409668} 08/30/2021 18:45:15 - INFO - __main__ - Step 30391: {'lr': 0.00045596138718114626, 'samples': 5835072, 'steps': 30390, 'loss/train': 1.3925122022628784} 08/30/2021 18:45:16 - INFO - __main__ - Step 30392: {'lr': 0.00045595837919587616, 'samples': 5835264, 'steps': 30391, 'loss/train': 1.2257037162780762} 08/30/2021 18:45:17 - INFO - __main__ - Step 30393: {'lr': 0.0004559553711178044, 'samples': 5835456, 'steps': 30392, 'loss/train': 1.2412104606628418} 08/30/2021 18:45:17 - INFO - __main__ - Step 30394: {'lr': 0.00045595236294693236, 'samples': 5835648, 'steps': 30393, 'loss/train': 1.705388069152832} 08/30/2021 18:45:17 - INFO - __main__ - Step 30395: {'lr': 0.00045594935468326137, 'samples': 5835840, 'steps': 30394, 'loss/train': 1.5520269870758057} 08/30/2021 18:45:18 - INFO - __main__ - Step 30396: {'lr': 0.00045594634632679275, 'samples': 5836032, 'steps': 30395, 'loss/train': 1.4333055019378662} 08/30/2021 18:45:19 - INFO - __main__ - Step 30397: {'lr': 0.0004559433378775278, 'samples': 5836224, 'steps': 30396, 'loss/train': 1.3411235809326172} 08/30/2021 18:45:20 - INFO - __main__ - Step 30398: {'lr': 0.00045594032933546813, 'samples': 5836416, 'steps': 30397, 'loss/train': 1.3540788888931274} 08/30/2021 18:45:20 - INFO - __main__ - Step 30399: {'lr': 0.00045593732070061484, 'samples': 5836608, 'steps': 30398, 'loss/train': 2.5351898670196533} 08/30/2021 18:45:20 - INFO - __main__ - Step 30400: {'lr': 0.00045593431197296934, 'samples': 5836800, 'steps': 30399, 'loss/train': 1.4136940240859985} 08/30/2021 18:45:21 - INFO - __main__ - Step 30401: {'lr': 0.00045593130315253305, 'samples': 5836992, 'steps': 30400, 'loss/train': 1.7455699443817139} 08/30/2021 18:45:21 - INFO - __main__ - Step 30402: {'lr': 0.0004559282942393073, 'samples': 5837184, 'steps': 30401, 'loss/train': 1.6552643775939941} 08/30/2021 18:45:22 - INFO - __main__ - Step 30403: {'lr': 0.00045592528523329346, 'samples': 5837376, 'steps': 30402, 'loss/train': 1.1807719469070435} 08/30/2021 18:45:23 - INFO - __main__ - Step 30404: {'lr': 0.0004559222761344928, 'samples': 5837568, 'steps': 30403, 'loss/train': 1.7294528484344482} 08/30/2021 18:45:23 - INFO - __main__ - Step 30405: {'lr': 0.0004559192669429068, 'samples': 5837760, 'steps': 30404, 'loss/train': 0.8706862926483154} 08/30/2021 18:45:24 - INFO - __main__ - Step 30406: {'lr': 0.0004559162576585367, 'samples': 5837952, 'steps': 30405, 'loss/train': 1.2970597743988037} 08/30/2021 18:45:24 - INFO - __main__ - Step 30407: {'lr': 0.00045591324828138396, 'samples': 5838144, 'steps': 30406, 'loss/train': 0.31338775157928467} 08/30/2021 18:45:26 - INFO - __main__ - Step 30408: {'lr': 0.0004559102388114499, 'samples': 5838336, 'steps': 30407, 'loss/train': 1.484430193901062} 08/30/2021 18:45:27 - INFO - __main__ - Step 30409: {'lr': 0.00045590722924873585, 'samples': 5838528, 'steps': 30408, 'loss/train': 1.5280474424362183} 08/30/2021 18:45:27 - INFO - __main__ - Step 30410: {'lr': 0.00045590421959324314, 'samples': 5838720, 'steps': 30409, 'loss/train': 1.1062175035476685} 08/30/2021 18:45:27 - INFO - __main__ - Step 30411: {'lr': 0.0004559012098449732, 'samples': 5838912, 'steps': 30410, 'loss/train': 1.1596845388412476} 08/30/2021 18:45:28 - INFO - __main__ - Step 30412: {'lr': 0.00045589820000392736, 'samples': 5839104, 'steps': 30411, 'loss/train': 1.6687703132629395} 08/30/2021 18:45:29 - INFO - __main__ - Step 30413: {'lr': 0.00045589519007010695, 'samples': 5839296, 'steps': 30412, 'loss/train': 1.4259675741195679} 08/30/2021 18:45:30 - INFO - __main__ - Step 30414: {'lr': 0.0004558921800435133, 'samples': 5839488, 'steps': 30413, 'loss/train': 1.2854440212249756} 08/30/2021 18:45:30 - INFO - __main__ - Step 30415: {'lr': 0.00045588916992414784, 'samples': 5839680, 'steps': 30414, 'loss/train': 0.9629214406013489} 08/30/2021 18:45:30 - INFO - __main__ - Step 30416: {'lr': 0.0004558861597120119, 'samples': 5839872, 'steps': 30415, 'loss/train': 1.0737756490707397} 08/30/2021 18:45:31 - INFO - __main__ - Step 30417: {'lr': 0.00045588314940710683, 'samples': 5840064, 'steps': 30416, 'loss/train': 1.508437156677246} 08/30/2021 18:45:32 - INFO - __main__ - Step 30418: {'lr': 0.00045588013900943404, 'samples': 5840256, 'steps': 30417, 'loss/train': 1.1975007057189941} 08/30/2021 18:45:33 - INFO - __main__ - Step 30419: {'lr': 0.0004558771285189948, 'samples': 5840448, 'steps': 30418, 'loss/train': 2.858619213104248} 08/30/2021 18:45:33 - INFO - __main__ - Step 30420: {'lr': 0.00045587411793579047, 'samples': 5840640, 'steps': 30419, 'loss/train': 1.9410632848739624} 08/30/2021 18:45:33 - INFO - __main__ - Step 30421: {'lr': 0.0004558711072598225, 'samples': 5840832, 'steps': 30420, 'loss/train': 1.23379647731781} 08/30/2021 18:45:34 - INFO - __main__ - Step 30422: {'lr': 0.0004558680964910922, 'samples': 5841024, 'steps': 30421, 'loss/train': 0.27774685621261597} 08/30/2021 18:45:35 - INFO - __main__ - Step 30423: {'lr': 0.0004558650856296008, 'samples': 5841216, 'steps': 30422, 'loss/train': 2.0526790618896484} 08/30/2021 18:45:36 - INFO - __main__ - Step 30424: {'lr': 0.0004558620746753499, 'samples': 5841408, 'steps': 30423, 'loss/train': 1.662615418434143} 08/30/2021 18:45:36 - INFO - __main__ - Step 30425: {'lr': 0.00045585906362834063, 'samples': 5841600, 'steps': 30424, 'loss/train': 1.230448842048645} 08/30/2021 18:45:36 - INFO - __main__ - Step 30426: {'lr': 0.00045585605248857456, 'samples': 5841792, 'steps': 30425, 'loss/train': 1.2588797807693481} 08/30/2021 18:45:37 - INFO - __main__ - Step 30427: {'lr': 0.00045585304125605276, 'samples': 5841984, 'steps': 30426, 'loss/train': 1.6771354675292969} 08/30/2021 18:45:37 - INFO - __main__ - Step 30428: {'lr': 0.0004558500299307768, 'samples': 5842176, 'steps': 30427, 'loss/train': 1.565519094467163} 08/30/2021 18:45:39 - INFO - __main__ - Step 30429: {'lr': 0.00045584701851274814, 'samples': 5842368, 'steps': 30428, 'loss/train': 0.7025896906852722} 08/30/2021 18:45:39 - INFO - __main__ - Step 30430: {'lr': 0.0004558440070019678, 'samples': 5842560, 'steps': 30429, 'loss/train': 0.9535374641418457} 08/30/2021 18:45:40 - INFO - __main__ - Step 30431: {'lr': 0.0004558409953984375, 'samples': 5842752, 'steps': 30430, 'loss/train': 1.8976178169250488} 08/30/2021 18:45:40 - INFO - __main__ - Step 30432: {'lr': 0.00045583798370215837, 'samples': 5842944, 'steps': 30431, 'loss/train': 1.605116605758667} 08/30/2021 18:45:40 - INFO - __main__ - Step 30433: {'lr': 0.00045583497191313175, 'samples': 5843136, 'steps': 30432, 'loss/train': 1.421343445777893} 08/30/2021 18:45:42 - INFO - __main__ - Step 30434: {'lr': 0.00045583196003135906, 'samples': 5843328, 'steps': 30433, 'loss/train': 1.241392970085144} 08/30/2021 18:45:42 - INFO - __main__ - Step 30435: {'lr': 0.0004558289480568417, 'samples': 5843520, 'steps': 30434, 'loss/train': 1.3463464975357056} 08/30/2021 18:45:43 - INFO - __main__ - Step 30436: {'lr': 0.00045582593598958107, 'samples': 5843712, 'steps': 30435, 'loss/train': 1.0346914529800415} 08/30/2021 18:45:43 - INFO - __main__ - Step 30437: {'lr': 0.00045582292382957836, 'samples': 5843904, 'steps': 30436, 'loss/train': 1.015781283378601} 08/30/2021 18:45:43 - INFO - __main__ - Step 30438: {'lr': 0.000455819911576835, 'samples': 5844096, 'steps': 30437, 'loss/train': 0.68913334608078} 08/30/2021 18:45:45 - INFO - __main__ - Step 30439: {'lr': 0.00045581689923135247, 'samples': 5844288, 'steps': 30438, 'loss/train': 1.3282723426818848} 08/30/2021 18:45:45 - INFO - __main__ - Step 30440: {'lr': 0.00045581388679313194, 'samples': 5844480, 'steps': 30439, 'loss/train': 1.3578760623931885} 08/30/2021 18:45:46 - INFO - __main__ - Step 30441: {'lr': 0.0004558108742621748, 'samples': 5844672, 'steps': 30440, 'loss/train': 1.2686543464660645} 08/30/2021 18:45:46 - INFO - __main__ - Step 30442: {'lr': 0.00045580786163848254, 'samples': 5844864, 'steps': 30441, 'loss/train': 1.8725361824035645} 08/30/2021 18:45:47 - INFO - __main__ - Step 30443: {'lr': 0.00045580484892205643, 'samples': 5845056, 'steps': 30442, 'loss/train': 0.21499814093112946} 08/30/2021 18:45:48 - INFO - __main__ - Step 30444: {'lr': 0.0004558018361128978, 'samples': 5845248, 'steps': 30443, 'loss/train': 1.5177667140960693} 08/30/2021 18:45:48 - INFO - __main__ - Step 30445: {'lr': 0.0004557988232110081, 'samples': 5845440, 'steps': 30444, 'loss/train': 1.489311933517456} 08/30/2021 18:45:49 - INFO - __main__ - Step 30446: {'lr': 0.00045579581021638855, 'samples': 5845632, 'steps': 30445, 'loss/train': 1.3952984809875488} 08/30/2021 18:45:49 - INFO - __main__ - Step 30447: {'lr': 0.00045579279712904057, 'samples': 5845824, 'steps': 30446, 'loss/train': 1.918003797531128} 08/30/2021 18:45:49 - INFO - __main__ - Step 30448: {'lr': 0.00045578978394896565, 'samples': 5846016, 'steps': 30447, 'loss/train': 1.2355464696884155} 08/30/2021 18:45:51 - INFO - __main__ - Step 30449: {'lr': 0.00045578677067616494, 'samples': 5846208, 'steps': 30448, 'loss/train': 1.6813616752624512} 08/30/2021 18:45:52 - INFO - __main__ - Step 30450: {'lr': 0.0004557837573106399, 'samples': 5846400, 'steps': 30449, 'loss/train': 1.2796074151992798} 08/30/2021 18:45:52 - INFO - __main__ - Step 30451: {'lr': 0.0004557807438523919, 'samples': 5846592, 'steps': 30450, 'loss/train': 6.387538433074951} 08/30/2021 18:45:53 - INFO - __main__ - Step 30452: {'lr': 0.00045577773030142224, 'samples': 5846784, 'steps': 30451, 'loss/train': 1.488860011100769} 08/30/2021 18:45:53 - INFO - __main__ - Step 30453: {'lr': 0.0004557747166577323, 'samples': 5846976, 'steps': 30452, 'loss/train': 1.4834585189819336} 08/30/2021 18:45:53 - INFO - __main__ - Step 30454: {'lr': 0.0004557717029213234, 'samples': 5847168, 'steps': 30453, 'loss/train': 1.0458354949951172} 08/30/2021 18:45:54 - INFO - __main__ - Step 30455: {'lr': 0.00045576868909219704, 'samples': 5847360, 'steps': 30454, 'loss/train': 0.03212663531303406} 08/30/2021 18:45:55 - INFO - __main__ - Step 30456: {'lr': 0.0004557656751703544, 'samples': 5847552, 'steps': 30455, 'loss/train': 1.2394939661026} 08/30/2021 18:45:55 - INFO - __main__ - Step 30457: {'lr': 0.000455762661155797, 'samples': 5847744, 'steps': 30456, 'loss/train': 1.448106050491333} 08/30/2021 18:45:56 - INFO - __main__ - Step 30458: {'lr': 0.0004557596470485261, 'samples': 5847936, 'steps': 30457, 'loss/train': 1.1777966022491455} 08/30/2021 18:45:56 - INFO - __main__ - Step 30459: {'lr': 0.0004557566328485431, 'samples': 5848128, 'steps': 30458, 'loss/train': 1.5696755647659302} 08/30/2021 18:45:57 - INFO - __main__ - Step 30460: {'lr': 0.00045575361855584927, 'samples': 5848320, 'steps': 30459, 'loss/train': 1.4418385028839111} 08/30/2021 18:45:59 - INFO - __main__ - Step 30461: {'lr': 0.00045575060417044614, 'samples': 5848512, 'steps': 30460, 'loss/train': 1.3801296949386597} 08/30/2021 18:45:59 - INFO - __main__ - Step 30462: {'lr': 0.0004557475896923349, 'samples': 5848704, 'steps': 30461, 'loss/train': 1.2891565561294556} 08/30/2021 18:46:00 - INFO - __main__ - Step 30463: {'lr': 0.0004557445751215169, 'samples': 5848896, 'steps': 30462, 'loss/train': 0.852066695690155} 08/30/2021 18:46:00 - INFO - __main__ - Step 30464: {'lr': 0.00045574156045799367, 'samples': 5849088, 'steps': 30463, 'loss/train': 1.145896077156067} 08/30/2021 18:46:00 - INFO - __main__ - Step 30465: {'lr': 0.0004557385457017664, 'samples': 5849280, 'steps': 30464, 'loss/train': 0.06214486062526703} 08/30/2021 18:46:02 - INFO - __main__ - Step 30466: {'lr': 0.0004557355308528366, 'samples': 5849472, 'steps': 30465, 'loss/train': 1.7655445337295532} 08/30/2021 18:46:02 - INFO - __main__ - Step 30467: {'lr': 0.00045573251591120545, 'samples': 5849664, 'steps': 30466, 'loss/train': 1.5356248617172241} 08/30/2021 18:46:03 - INFO - __main__ - Step 30468: {'lr': 0.00045572950087687447, 'samples': 5849856, 'steps': 30467, 'loss/train': 0.8759242296218872} 08/30/2021 18:46:03 - INFO - __main__ - Step 30469: {'lr': 0.0004557264857498449, 'samples': 5850048, 'steps': 30468, 'loss/train': 1.3312257528305054} 08/30/2021 18:46:03 - INFO - __main__ - Step 30470: {'lr': 0.0004557234705301182, 'samples': 5850240, 'steps': 30469, 'loss/train': 1.327883005142212} 08/30/2021 18:46:05 - INFO - __main__ - Step 30471: {'lr': 0.0004557204552176957, 'samples': 5850432, 'steps': 30470, 'loss/train': 1.6778514385223389} 08/30/2021 18:46:06 - INFO - __main__ - Step 30472: {'lr': 0.0004557174398125786, 'samples': 5850624, 'steps': 30471, 'loss/train': 2.120680332183838} 08/30/2021 18:46:06 - INFO - __main__ - Step 30473: {'lr': 0.00045571442431476856, 'samples': 5850816, 'steps': 30472, 'loss/train': 0.0953216403722763} 08/30/2021 18:46:06 - INFO - __main__ - Step 30474: {'lr': 0.0004557114087242667, 'samples': 5851008, 'steps': 30473, 'loss/train': 0.33750244975090027} 08/30/2021 18:46:07 - INFO - __main__ - Step 30475: {'lr': 0.0004557083930410745, 'samples': 5851200, 'steps': 30474, 'loss/train': 1.6529700756072998} 08/30/2021 18:46:08 - INFO - __main__ - Step 30476: {'lr': 0.0004557053772651932, 'samples': 5851392, 'steps': 30475, 'loss/train': 1.3859875202178955} 08/30/2021 18:46:09 - INFO - __main__ - Step 30477: {'lr': 0.00045570236139662426, 'samples': 5851584, 'steps': 30476, 'loss/train': 1.657836675643921} 08/30/2021 18:46:09 - INFO - __main__ - Step 30478: {'lr': 0.000455699345435369, 'samples': 5851776, 'steps': 30477, 'loss/train': 0.9254941344261169} 08/30/2021 18:46:09 - INFO - __main__ - Step 30479: {'lr': 0.0004556963293814288, 'samples': 5851968, 'steps': 30478, 'loss/train': 1.3769621849060059} 08/30/2021 18:46:10 - INFO - __main__ - Step 30480: {'lr': 0.000455693313234805, 'samples': 5852160, 'steps': 30479, 'loss/train': 1.717210054397583} 08/30/2021 18:46:11 - INFO - __main__ - Step 30481: {'lr': 0.000455690296995499, 'samples': 5852352, 'steps': 30480, 'loss/train': 1.1527591943740845} 08/30/2021 18:46:12 - INFO - __main__ - Step 30482: {'lr': 0.00045568728066351205, 'samples': 5852544, 'steps': 30481, 'loss/train': 1.7294851541519165} 08/30/2021 18:46:12 - INFO - __main__ - Step 30483: {'lr': 0.0004556842642388457, 'samples': 5852736, 'steps': 30482, 'loss/train': 1.99919855594635} 08/30/2021 18:46:12 - INFO - __main__ - Step 30484: {'lr': 0.0004556812477215011, 'samples': 5852928, 'steps': 30483, 'loss/train': 1.4838645458221436} 08/30/2021 18:46:13 - INFO - __main__ - Step 30485: {'lr': 0.0004556782311114798, 'samples': 5853120, 'steps': 30484, 'loss/train': 1.397320032119751} 08/30/2021 18:46:14 - INFO - __main__ - Step 30486: {'lr': 0.00045567521440878294, 'samples': 5853312, 'steps': 30485, 'loss/train': 0.9859090447425842} 08/30/2021 18:46:15 - INFO - __main__ - Step 30487: {'lr': 0.000455672197613412, 'samples': 5853504, 'steps': 30486, 'loss/train': 1.4842674732208252} 08/30/2021 18:46:15 - INFO - __main__ - Step 30488: {'lr': 0.00045566918072536844, 'samples': 5853696, 'steps': 30487, 'loss/train': 1.6535218954086304} 08/30/2021 18:46:15 - INFO - __main__ - Step 30489: {'lr': 0.00045566616374465355, 'samples': 5853888, 'steps': 30488, 'loss/train': 1.4215378761291504} 08/30/2021 18:46:16 - INFO - __main__ - Step 30490: {'lr': 0.0004556631466712686, 'samples': 5854080, 'steps': 30489, 'loss/train': 1.4654356241226196} 08/30/2021 18:46:17 - INFO - __main__ - Step 30491: {'lr': 0.00045566012950521497, 'samples': 5854272, 'steps': 30490, 'loss/train': 1.2836042642593384} 08/30/2021 18:46:18 - INFO - __main__ - Step 30492: {'lr': 0.0004556571122464941, 'samples': 5854464, 'steps': 30491, 'loss/train': 0.877436101436615} 08/30/2021 18:46:18 - INFO - __main__ - Step 30493: {'lr': 0.0004556540948951073, 'samples': 5854656, 'steps': 30492, 'loss/train': 1.3347598314285278} 08/30/2021 18:46:18 - INFO - __main__ - Step 30494: {'lr': 0.00045565107745105594, 'samples': 5854848, 'steps': 30493, 'loss/train': 1.2189784049987793} 08/30/2021 18:46:19 - INFO - __main__ - Step 30495: {'lr': 0.00045564805991434135, 'samples': 5855040, 'steps': 30494, 'loss/train': 0.9045740365982056} 08/30/2021 18:46:19 - INFO - __main__ - Step 30496: {'lr': 0.00045564504228496494, 'samples': 5855232, 'steps': 30495, 'loss/train': 1.2949351072311401} 08/30/2021 18:46:21 - INFO - __main__ - Step 30497: {'lr': 0.0004556420245629281, 'samples': 5855424, 'steps': 30496, 'loss/train': 1.397195816040039} 08/30/2021 18:46:21 - INFO - __main__ - Step 30498: {'lr': 0.00045563900674823205, 'samples': 5855616, 'steps': 30497, 'loss/train': 1.7661831378936768} 08/30/2021 18:46:21 - INFO - __main__ - Step 30499: {'lr': 0.0004556359888408783, 'samples': 5855808, 'steps': 30498, 'loss/train': 1.0134663581848145} 08/30/2021 18:46:22 - INFO - __main__ - Step 30500: {'lr': 0.00045563297084086807, 'samples': 5856000, 'steps': 30499, 'loss/train': 1.4503636360168457} 08/30/2021 18:46:22 - INFO - __main__ - Step 30501: {'lr': 0.00045562995274820285, 'samples': 5856192, 'steps': 30500, 'loss/train': 0.9922452569007874} 08/30/2021 18:46:24 - INFO - __main__ - Step 30502: {'lr': 0.00045562693456288394, 'samples': 5856384, 'steps': 30501, 'loss/train': 2.010448455810547} 08/30/2021 18:46:24 - INFO - __main__ - Step 30503: {'lr': 0.00045562391628491274, 'samples': 5856576, 'steps': 30502, 'loss/train': 1.1344683170318604} 08/30/2021 18:46:24 - INFO - __main__ - Step 30504: {'lr': 0.00045562089791429056, 'samples': 5856768, 'steps': 30503, 'loss/train': 1.7426371574401855} 08/30/2021 18:46:25 - INFO - __main__ - Step 30505: {'lr': 0.00045561787945101875, 'samples': 5856960, 'steps': 30504, 'loss/train': 1.4198999404907227} 08/30/2021 18:46:25 - INFO - __main__ - Step 30506: {'lr': 0.0004556148608950987, 'samples': 5857152, 'steps': 30505, 'loss/train': 1.4265637397766113} 08/30/2021 18:46:27 - INFO - __main__ - Step 30507: {'lr': 0.0004556118422465319, 'samples': 5857344, 'steps': 30506, 'loss/train': 1.5557074546813965} 08/30/2021 18:46:27 - INFO - __main__ - Step 30508: {'lr': 0.00045560882350531936, 'samples': 5857536, 'steps': 30507, 'loss/train': 1.7879557609558105} 08/30/2021 18:46:28 - INFO - __main__ - Step 30509: {'lr': 0.00045560580467146275, 'samples': 5857728, 'steps': 30508, 'loss/train': 1.1841042041778564} 08/30/2021 18:46:28 - INFO - __main__ - Step 30510: {'lr': 0.00045560278574496334, 'samples': 5857920, 'steps': 30509, 'loss/train': 1.4868690967559814} 08/30/2021 18:46:28 - INFO - __main__ - Step 30511: {'lr': 0.0004555997667258225, 'samples': 5858112, 'steps': 30510, 'loss/train': 1.1867871284484863} 08/30/2021 18:46:30 - INFO - __main__ - Step 30512: {'lr': 0.0004555967476140416, 'samples': 5858304, 'steps': 30511, 'loss/train': 1.388865351676941} 08/30/2021 18:46:31 - INFO - __main__ - Step 30513: {'lr': 0.00045559372840962186, 'samples': 5858496, 'steps': 30512, 'loss/train': 1.6118932962417603} 08/30/2021 18:46:31 - INFO - __main__ - Step 30514: {'lr': 0.00045559070911256486, 'samples': 5858688, 'steps': 30513, 'loss/train': 1.347998023033142} 08/30/2021 18:46:31 - INFO - __main__ - Step 30515: {'lr': 0.00045558768972287183, 'samples': 5858880, 'steps': 30514, 'loss/train': 2.067528486251831} 08/30/2021 18:46:32 - INFO - __main__ - Step 30516: {'lr': 0.0004555846702405442, 'samples': 5859072, 'steps': 30515, 'loss/train': 1.5631417036056519} 08/30/2021 18:46:34 - INFO - __main__ - Step 30517: {'lr': 0.0004555816506655832, 'samples': 5859264, 'steps': 30516, 'loss/train': 1.0549486875534058} 08/30/2021 18:46:34 - INFO - __main__ - Step 30518: {'lr': 0.00045557863099799034, 'samples': 5859456, 'steps': 30517, 'loss/train': 1.077292799949646} 08/30/2021 18:46:35 - INFO - __main__ - Step 30519: {'lr': 0.000455575611237767, 'samples': 5859648, 'steps': 30518, 'loss/train': 0.03098430298268795} 08/30/2021 18:46:35 - INFO - __main__ - Step 30520: {'lr': 0.00045557259138491435, 'samples': 5859840, 'steps': 30519, 'loss/train': 1.6459323167800903} 08/30/2021 18:46:35 - INFO - __main__ - Step 30521: {'lr': 0.0004555695714394339, 'samples': 5860032, 'steps': 30520, 'loss/train': 1.690779209136963} 08/30/2021 18:46:36 - INFO - __main__ - Step 30522: {'lr': 0.00045556655140132696, 'samples': 5860224, 'steps': 30521, 'loss/train': 0.7677645087242126} 08/30/2021 18:46:36 - INFO - __main__ - Step 30523: {'lr': 0.00045556353127059493, 'samples': 5860416, 'steps': 30522, 'loss/train': 0.35487547516822815} 08/30/2021 18:46:38 - INFO - __main__ - Step 30524: {'lr': 0.0004555605110472391, 'samples': 5860608, 'steps': 30523, 'loss/train': 0.0684698075056076} 08/30/2021 18:46:38 - INFO - __main__ - Step 30525: {'lr': 0.0004555574907312609, 'samples': 5860800, 'steps': 30524, 'loss/train': 2.669593095779419} 08/30/2021 18:46:39 - INFO - __main__ - Step 30526: {'lr': 0.00045555447032266167, 'samples': 5860992, 'steps': 30525, 'loss/train': 0.06736353784799576} 08/30/2021 18:46:39 - INFO - __main__ - Step 30527: {'lr': 0.0004555514498214428, 'samples': 5861184, 'steps': 30526, 'loss/train': 0.20482386648654938} 08/30/2021 18:46:39 - INFO - __main__ - Step 30528: {'lr': 0.0004555484292276055, 'samples': 5861376, 'steps': 30527, 'loss/train': 1.2516772747039795} 08/30/2021 18:46:41 - INFO - __main__ - Step 30529: {'lr': 0.0004555454085411514, 'samples': 5861568, 'steps': 30528, 'loss/train': 1.602391242980957} 08/30/2021 18:46:41 - INFO - __main__ - Step 30530: {'lr': 0.0004555423877620817, 'samples': 5861760, 'steps': 30529, 'loss/train': 1.408811330795288} 08/30/2021 18:46:42 - INFO - __main__ - Step 30531: {'lr': 0.00045553936689039765, 'samples': 5861952, 'steps': 30530, 'loss/train': 1.4809492826461792} 08/30/2021 18:46:42 - INFO - __main__ - Step 30532: {'lr': 0.00045553634592610084, 'samples': 5862144, 'steps': 30531, 'loss/train': 1.6968696117401123} 08/30/2021 18:46:42 - INFO - __main__ - Step 30533: {'lr': 0.00045553332486919246, 'samples': 5862336, 'steps': 30532, 'loss/train': 1.3688582181930542} 08/30/2021 18:46:44 - INFO - __main__ - Step 30534: {'lr': 0.000455530303719674, 'samples': 5862528, 'steps': 30533, 'loss/train': 1.5412429571151733} 08/30/2021 18:46:45 - INFO - __main__ - Step 30535: {'lr': 0.00045552728247754673, 'samples': 5862720, 'steps': 30534, 'loss/train': 1.7840511798858643} 08/30/2021 18:46:45 - INFO - __main__ - Step 30536: {'lr': 0.000455524261142812, 'samples': 5862912, 'steps': 30535, 'loss/train': 1.3917664289474487} 08/30/2021 18:46:45 - INFO - __main__ - Step 30537: {'lr': 0.00045552123971547123, 'samples': 5863104, 'steps': 30536, 'loss/train': 1.1540929079055786} 08/30/2021 18:46:46 - INFO - __main__ - Step 30538: {'lr': 0.00045551821819552575, 'samples': 5863296, 'steps': 30537, 'loss/train': 1.5662599802017212} 08/30/2021 18:46:46 - INFO - __main__ - Step 30539: {'lr': 0.0004555151965829769, 'samples': 5863488, 'steps': 30538, 'loss/train': 2.3214945793151855} 08/30/2021 18:46:46 - INFO - __main__ - Step 30540: {'lr': 0.0004555121748778261, 'samples': 5863680, 'steps': 30539, 'loss/train': 1.051978349685669} 08/30/2021 18:46:48 - INFO - __main__ - Step 30541: {'lr': 0.0004555091530800748, 'samples': 5863872, 'steps': 30540, 'loss/train': 0.8701170086860657} 08/30/2021 18:46:49 - INFO - __main__ - Step 30542: {'lr': 0.0004555061311897241, 'samples': 5864064, 'steps': 30541, 'loss/train': 1.3463091850280762} 08/30/2021 18:46:49 - INFO - __main__ - Step 30543: {'lr': 0.0004555031092067756, 'samples': 5864256, 'steps': 30542, 'loss/train': 2.326798439025879} 08/30/2021 18:46:50 - INFO - __main__ - Step 30544: {'lr': 0.00045550008713123047, 'samples': 5864448, 'steps': 30543, 'loss/train': 1.2083103656768799} 08/30/2021 18:46:50 - INFO - __main__ - Step 30545: {'lr': 0.00045549706496309027, 'samples': 5864640, 'steps': 30544, 'loss/train': 1.6895496845245361} 08/30/2021 18:46:50 - INFO - __main__ - Step 30546: {'lr': 0.0004554940427023562, 'samples': 5864832, 'steps': 30545, 'loss/train': 6.210311412811279} 08/30/2021 18:46:52 - INFO - __main__ - Step 30547: {'lr': 0.00045549102034902973, 'samples': 5865024, 'steps': 30546, 'loss/train': 6.09959602355957} 08/30/2021 18:46:53 - INFO - __main__ - Step 30548: {'lr': 0.0004554879979031121, 'samples': 5865216, 'steps': 30547, 'loss/train': 2.1539881229400635} 08/30/2021 18:46:53 - INFO - __main__ - Step 30549: {'lr': 0.00045548497536460487, 'samples': 5865408, 'steps': 30548, 'loss/train': 1.7157001495361328} 08/30/2021 18:46:54 - INFO - __main__ - Step 30550: {'lr': 0.00045548195273350926, 'samples': 5865600, 'steps': 30549, 'loss/train': 0.7891212701797485} 08/30/2021 18:46:54 - INFO - __main__ - Step 30551: {'lr': 0.0004554789300098265, 'samples': 5865792, 'steps': 30550, 'loss/train': 1.369751214981079} 08/30/2021 18:46:54 - INFO - __main__ - Step 30552: {'lr': 0.00045547590719355823, 'samples': 5865984, 'steps': 30551, 'loss/train': 1.878090500831604} 08/30/2021 18:46:56 - INFO - __main__ - Step 30553: {'lr': 0.00045547288428470574, 'samples': 5866176, 'steps': 30552, 'loss/train': 1.9719336032867432} 08/30/2021 18:46:56 - INFO - __main__ - Step 30554: {'lr': 0.0004554698612832703, 'samples': 5866368, 'steps': 30553, 'loss/train': 1.7289650440216064} 08/30/2021 18:46:57 - INFO - __main__ - Step 30555: {'lr': 0.00045546683818925327, 'samples': 5866560, 'steps': 30554, 'loss/train': 1.6674176454544067} 08/30/2021 18:46:57 - INFO - __main__ - Step 30556: {'lr': 0.000455463815002656, 'samples': 5866752, 'steps': 30555, 'loss/train': 1.6973453760147095} 08/30/2021 18:46:57 - INFO - __main__ - Step 30557: {'lr': 0.00045546079172348, 'samples': 5866944, 'steps': 30556, 'loss/train': 1.1133997440338135} 08/30/2021 18:46:59 - INFO - __main__ - Step 30558: {'lr': 0.00045545776835172647, 'samples': 5867136, 'steps': 30557, 'loss/train': 1.8632644414901733} 08/30/2021 18:46:59 - INFO - __main__ - Step 30559: {'lr': 0.00045545474488739693, 'samples': 5867328, 'steps': 30558, 'loss/train': 1.7757090330123901} 08/30/2021 18:47:00 - INFO - __main__ - Step 30560: {'lr': 0.0004554517213304926, 'samples': 5867520, 'steps': 30559, 'loss/train': 1.501355528831482} 08/30/2021 18:47:00 - INFO - __main__ - Step 30561: {'lr': 0.00045544869768101486, 'samples': 5867712, 'steps': 30560, 'loss/train': 1.4714609384536743} 08/30/2021 18:47:00 - INFO - __main__ - Step 30562: {'lr': 0.0004554456739389652, 'samples': 5867904, 'steps': 30561, 'loss/train': 1.2786227464675903} 08/30/2021 18:47:02 - INFO - __main__ - Step 30563: {'lr': 0.00045544265010434484, 'samples': 5868096, 'steps': 30562, 'loss/train': 1.601311445236206} 08/30/2021 18:47:03 - INFO - __main__ - Step 30564: {'lr': 0.0004554396261771552, 'samples': 5868288, 'steps': 30563, 'loss/train': 0.894614040851593} 08/30/2021 18:47:03 - INFO - __main__ - Step 30565: {'lr': 0.00045543660215739755, 'samples': 5868480, 'steps': 30564, 'loss/train': 0.070391945540905} 08/30/2021 18:47:04 - INFO - __main__ - Step 30566: {'lr': 0.00045543357804507344, 'samples': 5868672, 'steps': 30565, 'loss/train': 0.0783257707953453} 08/30/2021 18:47:04 - INFO - __main__ - Step 30567: {'lr': 0.00045543055384018405, 'samples': 5868864, 'steps': 30566, 'loss/train': 1.2704730033874512} 08/30/2021 18:47:04 - INFO - __main__ - Step 30568: {'lr': 0.0004554275295427309, 'samples': 5869056, 'steps': 30567, 'loss/train': 2.2178378105163574} 08/30/2021 18:47:05 - INFO - __main__ - Step 30569: {'lr': 0.0004554245051527153, 'samples': 5869248, 'steps': 30568, 'loss/train': 1.5451369285583496} 08/30/2021 18:47:06 - INFO - __main__ - Step 30570: {'lr': 0.0004554214806701384, 'samples': 5869440, 'steps': 30569, 'loss/train': 1.0610790252685547} 08/30/2021 18:47:07 - INFO - __main__ - Step 30571: {'lr': 0.000455418456095002, 'samples': 5869632, 'steps': 30570, 'loss/train': 0.13574184477329254} 08/30/2021 18:47:07 - INFO - __main__ - Step 30572: {'lr': 0.000455415431427307, 'samples': 5869824, 'steps': 30571, 'loss/train': 1.4240336418151855} 08/30/2021 18:47:08 - INFO - __main__ - Step 30573: {'lr': 0.00045541240666705516, 'samples': 5870016, 'steps': 30572, 'loss/train': 1.0464187860488892} 08/30/2021 18:47:08 - INFO - __main__ - Step 30574: {'lr': 0.0004554093818142475, 'samples': 5870208, 'steps': 30573, 'loss/train': 1.1992316246032715} 08/30/2021 18:47:10 - INFO - __main__ - Step 30575: {'lr': 0.0004554063568688857, 'samples': 5870400, 'steps': 30574, 'loss/train': 0.9268847107887268} 08/30/2021 18:47:11 - INFO - __main__ - Step 30576: {'lr': 0.0004554033318309708, 'samples': 5870592, 'steps': 30575, 'loss/train': 1.431304931640625} 08/30/2021 18:47:11 - INFO - __main__ - Step 30577: {'lr': 0.00045540030670050447, 'samples': 5870784, 'steps': 30576, 'loss/train': 0.63565593957901} 08/30/2021 18:47:11 - INFO - __main__ - Step 30578: {'lr': 0.0004553972814774878, 'samples': 5870976, 'steps': 30577, 'loss/train': 1.849929928779602} 08/30/2021 18:47:12 - INFO - __main__ - Step 30579: {'lr': 0.00045539425616192243, 'samples': 5871168, 'steps': 30578, 'loss/train': 1.5432122945785522} 08/30/2021 18:47:13 - INFO - __main__ - Step 30580: {'lr': 0.0004553912307538095, 'samples': 5871360, 'steps': 30579, 'loss/train': 1.8094135522842407} 08/30/2021 18:47:14 - INFO - __main__ - Step 30581: {'lr': 0.0004553882052531504, 'samples': 5871552, 'steps': 30580, 'loss/train': 0.36771920323371887} 08/30/2021 18:47:14 - INFO - __main__ - Step 30582: {'lr': 0.00045538517965994663, 'samples': 5871744, 'steps': 30581, 'loss/train': 1.361254334449768} 08/30/2021 18:47:14 - INFO - __main__ - Step 30583: {'lr': 0.0004553821539741994, 'samples': 5871936, 'steps': 30582, 'loss/train': 2.047004222869873} 08/30/2021 18:47:15 - INFO - __main__ - Step 30584: {'lr': 0.0004553791281959102, 'samples': 5872128, 'steps': 30583, 'loss/train': 0.8175615072250366} 08/30/2021 18:47:16 - INFO - __main__ - Step 30585: {'lr': 0.00045537610232508033, 'samples': 5872320, 'steps': 30584, 'loss/train': 2.0487401485443115} 08/30/2021 18:47:17 - INFO - __main__ - Step 30586: {'lr': 0.0004553730763617111, 'samples': 5872512, 'steps': 30585, 'loss/train': 1.3200666904449463} 08/30/2021 18:47:17 - INFO - __main__ - Step 30587: {'lr': 0.000455370050305804, 'samples': 5872704, 'steps': 30586, 'loss/train': 1.4460279941558838} 08/30/2021 18:47:17 - INFO - __main__ - Step 30588: {'lr': 0.0004553670241573603, 'samples': 5872896, 'steps': 30587, 'loss/train': 1.4460350275039673} 08/30/2021 18:47:18 - INFO - __main__ - Step 30589: {'lr': 0.00045536399791638133, 'samples': 5873088, 'steps': 30588, 'loss/train': 1.5300310850143433} 08/30/2021 18:47:19 - INFO - __main__ - Step 30590: {'lr': 0.0004553609715828686, 'samples': 5873280, 'steps': 30589, 'loss/train': 1.2519655227661133} 08/30/2021 18:47:20 - INFO - __main__ - Step 30591: {'lr': 0.00045535794515682334, 'samples': 5873472, 'steps': 30590, 'loss/train': 1.3778111934661865} 08/30/2021 18:47:20 - INFO - __main__ - Step 30592: {'lr': 0.00045535491863824695, 'samples': 5873664, 'steps': 30591, 'loss/train': 1.2975655794143677} 08/30/2021 18:47:20 - INFO - __main__ - Step 30593: {'lr': 0.0004553518920271408, 'samples': 5873856, 'steps': 30592, 'loss/train': 1.4341940879821777} 08/30/2021 18:47:21 - INFO - __main__ - Step 30594: {'lr': 0.00045534886532350627, 'samples': 5874048, 'steps': 30593, 'loss/train': 1.7200616598129272} 08/30/2021 18:47:22 - INFO - __main__ - Step 30595: {'lr': 0.00045534583852734474, 'samples': 5874240, 'steps': 30594, 'loss/train': 1.616725206375122} 08/30/2021 18:47:23 - INFO - __main__ - Step 30596: {'lr': 0.00045534281163865756, 'samples': 5874432, 'steps': 30595, 'loss/train': 0.9719061851501465} 08/30/2021 18:47:23 - INFO - __main__ - Step 30597: {'lr': 0.000455339784657446, 'samples': 5874624, 'steps': 30596, 'loss/train': 1.596483826637268} 08/30/2021 18:47:23 - INFO - __main__ - Step 30598: {'lr': 0.0004553367575837115, 'samples': 5874816, 'steps': 30597, 'loss/train': 1.2679634094238281} 08/30/2021 18:47:24 - INFO - __main__ - Step 30599: {'lr': 0.00045533373041745545, 'samples': 5875008, 'steps': 30598, 'loss/train': 1.1390831470489502} 08/30/2021 18:47:24 - INFO - __main__ - Step 30600: {'lr': 0.00045533070315867917, 'samples': 5875200, 'steps': 30599, 'loss/train': 1.7121864557266235} 08/30/2021 18:47:26 - INFO - __main__ - Step 30601: {'lr': 0.0004553276758073841, 'samples': 5875392, 'steps': 30600, 'loss/train': 1.8994885683059692} 08/30/2021 18:47:26 - INFO - __main__ - Step 30602: {'lr': 0.00045532464836357155, 'samples': 5875584, 'steps': 30601, 'loss/train': 1.7125836610794067} 08/30/2021 18:47:26 - INFO - __main__ - Step 30603: {'lr': 0.0004553216208272428, 'samples': 5875776, 'steps': 30602, 'loss/train': 1.7440612316131592} 08/30/2021 18:47:27 - INFO - __main__ - Step 30604: {'lr': 0.0004553185931983994, 'samples': 5875968, 'steps': 30603, 'loss/train': 1.6306486129760742} 08/30/2021 18:47:27 - INFO - __main__ - Step 30605: {'lr': 0.00045531556547704255, 'samples': 5876160, 'steps': 30604, 'loss/train': 1.2530897855758667} 08/30/2021 18:47:29 - INFO - __main__ - Step 30606: {'lr': 0.00045531253766317373, 'samples': 5876352, 'steps': 30605, 'loss/train': 1.349639654159546} 08/30/2021 18:47:29 - INFO - __main__ - Step 30607: {'lr': 0.0004553095097567942, 'samples': 5876544, 'steps': 30606, 'loss/train': 1.7893048524856567} 08/30/2021 18:47:30 - INFO - __main__ - Step 30608: {'lr': 0.0004553064817579053, 'samples': 5876736, 'steps': 30607, 'loss/train': 1.4117324352264404} 08/30/2021 18:47:30 - INFO - __main__ - Step 30609: {'lr': 0.0004553034536665086, 'samples': 5876928, 'steps': 30608, 'loss/train': 0.6804377436637878} 08/30/2021 18:47:30 - INFO - __main__ - Step 30610: {'lr': 0.0004553004254826053, 'samples': 5877120, 'steps': 30609, 'loss/train': 0.7034269571304321} 08/30/2021 18:47:32 - INFO - __main__ - Step 30611: {'lr': 0.0004552973972061967, 'samples': 5877312, 'steps': 30610, 'loss/train': 0.9731603860855103} 08/30/2021 18:47:33 - INFO - __main__ - Step 30612: {'lr': 0.00045529436883728436, 'samples': 5877504, 'steps': 30611, 'loss/train': 1.7750425338745117} 08/30/2021 18:47:33 - INFO - __main__ - Step 30613: {'lr': 0.0004552913403758695, 'samples': 5877696, 'steps': 30612, 'loss/train': 1.576848030090332} 08/30/2021 18:47:33 - INFO - __main__ - Step 30614: {'lr': 0.00045528831182195355, 'samples': 5877888, 'steps': 30613, 'loss/train': 1.0929534435272217} 08/30/2021 18:47:34 - INFO - __main__ - Step 30615: {'lr': 0.00045528528317553786, 'samples': 5878080, 'steps': 30614, 'loss/train': 1.2400987148284912} 08/30/2021 18:47:35 - INFO - __main__ - Step 30616: {'lr': 0.0004552822544366238, 'samples': 5878272, 'steps': 30615, 'loss/train': 1.3178428411483765} 08/30/2021 18:47:35 - INFO - __main__ - Step 30617: {'lr': 0.00045527922560521274, 'samples': 5878464, 'steps': 30616, 'loss/train': 1.4441092014312744} 08/30/2021 18:47:36 - INFO - __main__ - Step 30618: {'lr': 0.0004552761966813059, 'samples': 5878656, 'steps': 30617, 'loss/train': 0.24038703739643097} 08/30/2021 18:47:36 - INFO - __main__ - Step 30619: {'lr': 0.00045527316766490487, 'samples': 5878848, 'steps': 30618, 'loss/train': 1.0963329076766968} 08/30/2021 18:47:37 - INFO - __main__ - Step 30620: {'lr': 0.000455270138556011, 'samples': 5879040, 'steps': 30619, 'loss/train': 1.7947168350219727} 08/30/2021 18:47:38 - INFO - __main__ - Step 30621: {'lr': 0.00045526710935462543, 'samples': 5879232, 'steps': 30620, 'loss/train': 0.8949249982833862} 08/30/2021 18:47:38 - INFO - __main__ - Step 30622: {'lr': 0.00045526408006074973, 'samples': 5879424, 'steps': 30621, 'loss/train': 1.1506030559539795} 08/30/2021 18:47:39 - INFO - __main__ - Step 30623: {'lr': 0.00045526105067438525, 'samples': 5879616, 'steps': 30622, 'loss/train': 1.6091824769973755} 08/30/2021 18:47:39 - INFO - __main__ - Step 30624: {'lr': 0.00045525802119553323, 'samples': 5879808, 'steps': 30623, 'loss/train': 0.46725350618362427} 08/30/2021 18:47:39 - INFO - __main__ - Step 30625: {'lr': 0.0004552549916241951, 'samples': 5880000, 'steps': 30624, 'loss/train': 0.8923364281654358} 08/30/2021 18:47:42 - INFO - __main__ - Step 30626: {'lr': 0.0004552519619603723, 'samples': 5880192, 'steps': 30625, 'loss/train': 0.7296211123466492} 08/30/2021 18:47:42 - INFO - __main__ - Step 30627: {'lr': 0.00045524893220406617, 'samples': 5880384, 'steps': 30626, 'loss/train': 1.4573044776916504} 08/30/2021 18:47:43 - INFO - __main__ - Step 30628: {'lr': 0.00045524590235527796, 'samples': 5880576, 'steps': 30627, 'loss/train': 1.6401554346084595} 08/30/2021 18:47:43 - INFO - __main__ - Step 30629: {'lr': 0.0004552428724140091, 'samples': 5880768, 'steps': 30628, 'loss/train': 1.5434536933898926} 08/30/2021 18:47:43 - INFO - __main__ - Step 30630: {'lr': 0.000455239842380261, 'samples': 5880960, 'steps': 30629, 'loss/train': 0.11715385317802429} 08/30/2021 18:47:44 - INFO - __main__ - Step 30631: {'lr': 0.000455236812254035, 'samples': 5881152, 'steps': 30630, 'loss/train': 1.755092978477478} 08/30/2021 18:47:45 - INFO - __main__ - Step 30632: {'lr': 0.0004552337820353325, 'samples': 5881344, 'steps': 30631, 'loss/train': 1.6778576374053955} 08/30/2021 18:47:46 - INFO - __main__ - Step 30633: {'lr': 0.00045523075172415476, 'samples': 5881536, 'steps': 30632, 'loss/train': 1.6777456998825073} 08/30/2021 18:47:46 - INFO - __main__ - Step 30634: {'lr': 0.0004552277213205032, 'samples': 5881728, 'steps': 30633, 'loss/train': 1.7205262184143066} 08/30/2021 18:47:46 - INFO - __main__ - Step 30635: {'lr': 0.0004552246908243792, 'samples': 5881920, 'steps': 30634, 'loss/train': 1.7409580945968628} 08/30/2021 18:47:47 - INFO - __main__ - Step 30636: {'lr': 0.00045522166023578413, 'samples': 5882112, 'steps': 30635, 'loss/train': 1.3704737424850464} 08/30/2021 18:47:48 - INFO - __main__ - Step 30637: {'lr': 0.0004552186295547194, 'samples': 5882304, 'steps': 30636, 'loss/train': 1.5701302289962769} 08/30/2021 18:47:49 - INFO - __main__ - Step 30638: {'lr': 0.0004552155987811863, 'samples': 5882496, 'steps': 30637, 'loss/train': 1.1240133047103882} 08/30/2021 18:47:49 - INFO - __main__ - Step 30639: {'lr': 0.00045521256791518616, 'samples': 5882688, 'steps': 30638, 'loss/train': 1.3252633810043335} 08/30/2021 18:47:50 - INFO - __main__ - Step 30640: {'lr': 0.0004552095369567205, 'samples': 5882880, 'steps': 30639, 'loss/train': 1.6989467144012451} 08/30/2021 18:47:50 - INFO - __main__ - Step 30641: {'lr': 0.00045520650590579056, 'samples': 5883072, 'steps': 30640, 'loss/train': 1.7590097188949585} 08/30/2021 18:47:52 - INFO - __main__ - Step 30642: {'lr': 0.00045520347476239763, 'samples': 5883264, 'steps': 30641, 'loss/train': 1.7956620454788208} 08/30/2021 18:47:52 - INFO - __main__ - Step 30643: {'lr': 0.00045520044352654335, 'samples': 5883456, 'steps': 30642, 'loss/train': 1.5946303606033325} 08/30/2021 18:47:52 - INFO - __main__ - Step 30644: {'lr': 0.0004551974121982288, 'samples': 5883648, 'steps': 30643, 'loss/train': 0.7562167048454285} 08/30/2021 18:47:53 - INFO - __main__ - Step 30645: {'lr': 0.00045519438077745543, 'samples': 5883840, 'steps': 30644, 'loss/train': 2.0622270107269287} 08/30/2021 18:47:53 - INFO - __main__ - Step 30646: {'lr': 0.0004551913492642248, 'samples': 5884032, 'steps': 30645, 'loss/train': 1.2649282217025757} 08/30/2021 18:47:55 - INFO - __main__ - Step 30647: {'lr': 0.00045518831765853796, 'samples': 5884224, 'steps': 30646, 'loss/train': 2.056971788406372} 08/30/2021 18:47:55 - INFO - __main__ - Step 30648: {'lr': 0.0004551852859603965, 'samples': 5884416, 'steps': 30647, 'loss/train': 0.9747715592384338} 08/30/2021 18:47:55 - INFO - __main__ - Step 30649: {'lr': 0.0004551822541698017, 'samples': 5884608, 'steps': 30648, 'loss/train': 1.5507370233535767} 08/30/2021 18:47:56 - INFO - __main__ - Step 30650: {'lr': 0.0004551792222867549, 'samples': 5884800, 'steps': 30649, 'loss/train': 1.4265443086624146} 08/30/2021 18:47:56 - INFO - __main__ - Step 30651: {'lr': 0.0004551761903112576, 'samples': 5884992, 'steps': 30650, 'loss/train': 1.2638945579528809} 08/30/2021 18:47:56 - INFO - __main__ - Step 30652: {'lr': 0.000455173158243311, 'samples': 5885184, 'steps': 30651, 'loss/train': 1.5258312225341797} 08/30/2021 18:47:58 - INFO - __main__ - Step 30653: {'lr': 0.0004551701260829166, 'samples': 5885376, 'steps': 30652, 'loss/train': 1.4410654306411743} 08/30/2021 18:47:59 - INFO - __main__ - Step 30654: {'lr': 0.00045516709383007563, 'samples': 5885568, 'steps': 30653, 'loss/train': 1.0258395671844482} 08/30/2021 18:47:59 - INFO - __main__ - Step 30655: {'lr': 0.0004551640614847896, 'samples': 5885760, 'steps': 30654, 'loss/train': 0.9390184879302979} 08/30/2021 18:47:59 - INFO - __main__ - Step 30656: {'lr': 0.00045516102904705983, 'samples': 5885952, 'steps': 30655, 'loss/train': 0.891115665435791} 08/30/2021 18:48:00 - INFO - __main__ - Step 30657: {'lr': 0.0004551579965168876, 'samples': 5886144, 'steps': 30656, 'loss/train': 1.3206318616867065} 08/30/2021 18:48:01 - INFO - __main__ - Step 30658: {'lr': 0.00045515496389427433, 'samples': 5886336, 'steps': 30657, 'loss/train': 1.5702022314071655} 08/30/2021 18:48:02 - INFO - __main__ - Step 30659: {'lr': 0.0004551519311792215, 'samples': 5886528, 'steps': 30658, 'loss/train': 1.701112985610962} 08/30/2021 18:48:02 - INFO - __main__ - Step 30660: {'lr': 0.00045514889837173025, 'samples': 5886720, 'steps': 30659, 'loss/train': 0.7067428231239319} 08/30/2021 18:48:02 - INFO - __main__ - Step 30661: {'lr': 0.00045514586547180214, 'samples': 5886912, 'steps': 30660, 'loss/train': 1.7332934141159058} 08/30/2021 18:48:03 - INFO - __main__ - Step 30662: {'lr': 0.0004551428324794385, 'samples': 5887104, 'steps': 30661, 'loss/train': 1.528985619544983} 08/30/2021 18:48:04 - INFO - __main__ - Step 30663: {'lr': 0.00045513979939464056, 'samples': 5887296, 'steps': 30662, 'loss/train': 1.7021403312683105} 08/30/2021 18:48:05 - INFO - __main__ - Step 30664: {'lr': 0.0004551367662174099, 'samples': 5887488, 'steps': 30663, 'loss/train': 1.4849344491958618} 08/30/2021 18:48:05 - INFO - __main__ - Step 30665: {'lr': 0.0004551337329477477, 'samples': 5887680, 'steps': 30664, 'loss/train': 1.1916885375976562} 08/30/2021 18:48:05 - INFO - __main__ - Step 30666: {'lr': 0.00045513069958565545, 'samples': 5887872, 'steps': 30665, 'loss/train': 1.1948695182800293} 08/30/2021 18:48:06 - INFO - __main__ - Step 30667: {'lr': 0.00045512766613113457, 'samples': 5888064, 'steps': 30666, 'loss/train': 1.4168646335601807} 08/30/2021 18:48:07 - INFO - __main__ - Step 30668: {'lr': 0.00045512463258418615, 'samples': 5888256, 'steps': 30667, 'loss/train': 1.3707149028778076} 08/30/2021 18:48:07 - INFO - __main__ - Step 30669: {'lr': 0.00045512159894481183, 'samples': 5888448, 'steps': 30668, 'loss/train': 0.6929999589920044} 08/30/2021 18:48:08 - INFO - __main__ - Step 30670: {'lr': 0.00045511856521301286, 'samples': 5888640, 'steps': 30669, 'loss/train': 1.3104997873306274} 08/30/2021 18:48:08 - INFO - __main__ - Step 30671: {'lr': 0.0004551155313887906, 'samples': 5888832, 'steps': 30670, 'loss/train': 1.3301658630371094} 08/30/2021 18:48:08 - INFO - __main__ - Step 30672: {'lr': 0.0004551124974721465, 'samples': 5889024, 'steps': 30671, 'loss/train': 1.4518308639526367} 08/30/2021 18:48:10 - INFO - __main__ - Step 30673: {'lr': 0.00045510946346308186, 'samples': 5889216, 'steps': 30672, 'loss/train': 1.6256787776947021} 08/30/2021 18:48:10 - INFO - __main__ - Step 30674: {'lr': 0.0004551064293615981, 'samples': 5889408, 'steps': 30673, 'loss/train': 1.4367645978927612} 08/30/2021 18:48:11 - INFO - __main__ - Step 30675: {'lr': 0.00045510339516769647, 'samples': 5889600, 'steps': 30674, 'loss/train': 1.4962762594223022} 08/30/2021 18:48:11 - INFO - __main__ - Step 30676: {'lr': 0.0004551003608813784, 'samples': 5889792, 'steps': 30675, 'loss/train': 1.5136266946792603} 08/30/2021 18:48:12 - INFO - __main__ - Step 30677: {'lr': 0.00045509732650264535, 'samples': 5889984, 'steps': 30676, 'loss/train': 1.123766303062439} 08/30/2021 18:48:14 - INFO - __main__ - Step 30678: {'lr': 0.00045509429203149856, 'samples': 5890176, 'steps': 30677, 'loss/train': 1.3877636194229126} 08/30/2021 18:48:14 - INFO - __main__ - Step 30679: {'lr': 0.00045509125746793946, 'samples': 5890368, 'steps': 30678, 'loss/train': 1.4114665985107422} 08/30/2021 18:48:14 - INFO - __main__ - Step 30680: {'lr': 0.00045508822281196937, 'samples': 5890560, 'steps': 30679, 'loss/train': 1.6636769771575928} 08/30/2021 18:48:15 - INFO - __main__ - Step 30681: {'lr': 0.0004550851880635898, 'samples': 5890752, 'steps': 30680, 'loss/train': 1.3811922073364258} 08/30/2021 18:48:15 - INFO - __main__ - Step 30682: {'lr': 0.0004550821532228019, 'samples': 5890944, 'steps': 30681, 'loss/train': 1.508966088294983} 08/30/2021 18:48:15 - INFO - __main__ - Step 30683: {'lr': 0.00045507911828960717, 'samples': 5891136, 'steps': 30682, 'loss/train': 1.3214455842971802} 08/30/2021 18:48:17 - INFO - __main__ - Step 30684: {'lr': 0.000455076083264007, 'samples': 5891328, 'steps': 30683, 'loss/train': 1.7156789302825928} 08/30/2021 18:48:17 - INFO - __main__ - Step 30685: {'lr': 0.0004550730481460027, 'samples': 5891520, 'steps': 30684, 'loss/train': 1.3713898658752441} 08/30/2021 18:48:18 - INFO - __main__ - Step 30686: {'lr': 0.0004550700129355956, 'samples': 5891712, 'steps': 30685, 'loss/train': 1.6096270084381104} 08/30/2021 18:48:18 - INFO - __main__ - Step 30687: {'lr': 0.0004550669776327871, 'samples': 5891904, 'steps': 30686, 'loss/train': 1.3394801616668701} 08/30/2021 18:48:18 - INFO - __main__ - Step 30688: {'lr': 0.00045506394223757867, 'samples': 5892096, 'steps': 30687, 'loss/train': 1.3650274276733398} 08/30/2021 18:48:20 - INFO - __main__ - Step 30689: {'lr': 0.00045506090674997157, 'samples': 5892288, 'steps': 30688, 'loss/train': 1.1812090873718262} 08/30/2021 18:48:21 - INFO - __main__ - Step 30690: {'lr': 0.00045505787116996714, 'samples': 5892480, 'steps': 30689, 'loss/train': 1.7855641841888428} 08/30/2021 18:48:21 - INFO - __main__ - Step 30691: {'lr': 0.0004550548354975669, 'samples': 5892672, 'steps': 30690, 'loss/train': 0.6450674533843994} 08/30/2021 18:48:21 - INFO - __main__ - Step 30692: {'lr': 0.000455051799732772, 'samples': 5892864, 'steps': 30691, 'loss/train': 1.6922450065612793} 08/30/2021 18:48:22 - INFO - __main__ - Step 30693: {'lr': 0.000455048763875584, 'samples': 5893056, 'steps': 30692, 'loss/train': 1.6246510744094849} 08/30/2021 18:48:23 - INFO - __main__ - Step 30694: {'lr': 0.00045504572792600415, 'samples': 5893248, 'steps': 30693, 'loss/train': 1.4271252155303955} 08/30/2021 18:48:24 - INFO - __main__ - Step 30695: {'lr': 0.00045504269188403386, 'samples': 5893440, 'steps': 30694, 'loss/train': 1.8969249725341797} 08/30/2021 18:48:24 - INFO - __main__ - Step 30696: {'lr': 0.00045503965574967447, 'samples': 5893632, 'steps': 30695, 'loss/train': 1.5949009656906128} 08/30/2021 18:48:24 - INFO - __main__ - Step 30697: {'lr': 0.0004550366195229274, 'samples': 5893824, 'steps': 30696, 'loss/train': 1.5189149379730225} 08/30/2021 18:48:25 - INFO - __main__ - Step 30698: {'lr': 0.00045503358320379405, 'samples': 5894016, 'steps': 30697, 'loss/train': 1.1654564142227173} 08/30/2021 18:48:26 - INFO - __main__ - Step 30699: {'lr': 0.00045503054679227567, 'samples': 5894208, 'steps': 30698, 'loss/train': 1.540948510169983} 08/30/2021 18:48:27 - INFO - __main__ - Step 30700: {'lr': 0.00045502751028837367, 'samples': 5894400, 'steps': 30699, 'loss/train': 2.7859644889831543} 08/30/2021 18:48:27 - INFO - __main__ - Step 30701: {'lr': 0.00045502447369208957, 'samples': 5894592, 'steps': 30700, 'loss/train': 1.3823413848876953} 08/30/2021 18:48:27 - INFO - __main__ - Step 30702: {'lr': 0.00045502143700342445, 'samples': 5894784, 'steps': 30701, 'loss/train': 1.1010650396347046} 08/30/2021 18:48:28 - INFO - __main__ - Step 30703: {'lr': 0.0004550184002223799, 'samples': 5894976, 'steps': 30702, 'loss/train': 1.6398025751113892} 08/30/2021 18:48:28 - INFO - __main__ - Step 30704: {'lr': 0.0004550153633489572, 'samples': 5895168, 'steps': 30703, 'loss/train': 2.0717668533325195} 08/30/2021 18:48:30 - INFO - __main__ - Step 30705: {'lr': 0.0004550123263831578, 'samples': 5895360, 'steps': 30704, 'loss/train': 1.3576658964157104} 08/30/2021 18:48:30 - INFO - __main__ - Step 30706: {'lr': 0.0004550092893249829, 'samples': 5895552, 'steps': 30705, 'loss/train': 0.08371548354625702} 08/30/2021 18:48:31 - INFO - __main__ - Step 30707: {'lr': 0.00045500625217443404, 'samples': 5895744, 'steps': 30706, 'loss/train': 0.07402755320072174} 08/30/2021 18:48:31 - INFO - __main__ - Step 30708: {'lr': 0.0004550032149315125, 'samples': 5895936, 'steps': 30707, 'loss/train': 1.021190881729126} 08/30/2021 18:48:31 - INFO - __main__ - Step 30709: {'lr': 0.00045500017759621974, 'samples': 5896128, 'steps': 30708, 'loss/train': 0.8101719617843628} 08/30/2021 18:48:33 - INFO - __main__ - Step 30710: {'lr': 0.00045499714016855705, 'samples': 5896320, 'steps': 30709, 'loss/train': 1.648227334022522} 08/30/2021 18:48:33 - INFO - __main__ - Step 30711: {'lr': 0.0004549941026485258, 'samples': 5896512, 'steps': 30710, 'loss/train': 1.285312294960022} 08/30/2021 18:48:34 - INFO - __main__ - Step 30712: {'lr': 0.00045499106503612733, 'samples': 5896704, 'steps': 30711, 'loss/train': 0.16413173079490662} 08/30/2021 18:48:34 - INFO - __main__ - Step 30713: {'lr': 0.00045498802733136306, 'samples': 5896896, 'steps': 30712, 'loss/train': 1.5749156475067139} 08/30/2021 18:48:34 - INFO - __main__ - Step 30714: {'lr': 0.0004549849895342344, 'samples': 5897088, 'steps': 30713, 'loss/train': 1.2998645305633545} 08/30/2021 18:48:36 - INFO - __main__ - Step 30715: {'lr': 0.00045498195164474264, 'samples': 5897280, 'steps': 30714, 'loss/train': 1.4540531635284424} 08/30/2021 18:48:36 - INFO - __main__ - Step 30716: {'lr': 0.00045497891366288914, 'samples': 5897472, 'steps': 30715, 'loss/train': 0.9984238743782043} 08/30/2021 18:48:37 - INFO - __main__ - Step 30717: {'lr': 0.0004549758755886754, 'samples': 5897664, 'steps': 30716, 'loss/train': 1.2595840692520142} 08/30/2021 18:48:37 - INFO - __main__ - Step 30718: {'lr': 0.00045497283742210263, 'samples': 5897856, 'steps': 30717, 'loss/train': 1.497979760169983} 08/30/2021 18:48:37 - INFO - __main__ - Step 30719: {'lr': 0.0004549697991631722, 'samples': 5898048, 'steps': 30718, 'loss/train': 1.5174351930618286} 08/30/2021 18:48:39 - INFO - __main__ - Step 30720: {'lr': 0.0004549667608118856, 'samples': 5898240, 'steps': 30719, 'loss/train': 1.0492194890975952} 08/30/2021 18:48:39 - INFO - __main__ - Step 30721: {'lr': 0.0004549637223682441, 'samples': 5898432, 'steps': 30720, 'loss/train': 1.41859769821167} 08/30/2021 18:48:40 - INFO - __main__ - Step 30722: {'lr': 0.0004549606838322492, 'samples': 5898624, 'steps': 30721, 'loss/train': 0.7829442620277405} 08/30/2021 18:48:40 - INFO - __main__ - Step 30723: {'lr': 0.00045495764520390216, 'samples': 5898816, 'steps': 30722, 'loss/train': 1.7781620025634766} 08/30/2021 18:48:41 - INFO - __main__ - Step 30724: {'lr': 0.0004549546064832043, 'samples': 5899008, 'steps': 30723, 'loss/train': 1.6704813241958618} 08/30/2021 18:48:41 - INFO - __main__ - Step 30725: {'lr': 0.0004549515676701571, 'samples': 5899200, 'steps': 30724, 'loss/train': 1.4118534326553345} 08/30/2021 18:48:42 - INFO - __main__ - Step 30726: {'lr': 0.0004549485287647619, 'samples': 5899392, 'steps': 30725, 'loss/train': 1.3349955081939697} 08/30/2021 18:48:43 - INFO - __main__ - Step 30727: {'lr': 0.00045494548976702, 'samples': 5899584, 'steps': 30726, 'loss/train': 1.1516207456588745} 08/30/2021 18:48:43 - INFO - __main__ - Step 30728: {'lr': 0.0004549424506769329, 'samples': 5899776, 'steps': 30727, 'loss/train': 1.6635746955871582} 08/30/2021 18:48:44 - INFO - __main__ - Step 30729: {'lr': 0.00045493941149450185, 'samples': 5899968, 'steps': 30728, 'loss/train': 1.3222459554672241} 08/30/2021 18:48:44 - INFO - __main__ - Step 30730: {'lr': 0.00045493637221972826, 'samples': 5900160, 'steps': 30729, 'loss/train': 1.2599328756332397} 08/30/2021 18:48:45 - INFO - __main__ - Step 30731: {'lr': 0.0004549333328526135, 'samples': 5900352, 'steps': 30730, 'loss/train': 1.7270764112472534} 08/30/2021 18:48:46 - INFO - __main__ - Step 30732: {'lr': 0.0004549302933931589, 'samples': 5900544, 'steps': 30731, 'loss/train': 1.7319059371948242} 08/30/2021 18:48:46 - INFO - __main__ - Step 30733: {'lr': 0.000454927253841366, 'samples': 5900736, 'steps': 30732, 'loss/train': 1.3709053993225098} 08/30/2021 18:48:47 - INFO - __main__ - Step 30734: {'lr': 0.00045492421419723595, 'samples': 5900928, 'steps': 30733, 'loss/train': 1.575917363166809} 08/30/2021 18:48:47 - INFO - __main__ - Step 30735: {'lr': 0.00045492117446077027, 'samples': 5901120, 'steps': 30734, 'loss/train': 1.0894339084625244} 08/30/2021 18:48:49 - INFO - __main__ - Step 30736: {'lr': 0.0004549181346319702, 'samples': 5901312, 'steps': 30735, 'loss/train': 1.6368627548217773} 08/30/2021 18:48:50 - INFO - __main__ - Step 30737: {'lr': 0.00045491509471083717, 'samples': 5901504, 'steps': 30736, 'loss/train': 1.760408878326416} 08/30/2021 18:48:50 - INFO - __main__ - Step 30738: {'lr': 0.00045491205469737263, 'samples': 5901696, 'steps': 30737, 'loss/train': 0.0563410185277462} 08/30/2021 18:48:50 - INFO - __main__ - Step 30739: {'lr': 0.00045490901459157787, 'samples': 5901888, 'steps': 30738, 'loss/train': 0.8755281567573547} 08/30/2021 18:48:51 - INFO - __main__ - Step 30740: {'lr': 0.0004549059743934543, 'samples': 5902080, 'steps': 30739, 'loss/train': 2.1990723609924316} 08/30/2021 18:48:51 - INFO - __main__ - Step 30741: {'lr': 0.00045490293410300315, 'samples': 5902272, 'steps': 30740, 'loss/train': 1.7682366371154785} 08/30/2021 18:48:53 - INFO - __main__ - Step 30742: {'lr': 0.000454899893720226, 'samples': 5902464, 'steps': 30741, 'loss/train': 1.7818737030029297} 08/30/2021 18:48:53 - INFO - __main__ - Step 30743: {'lr': 0.000454896853245124, 'samples': 5902656, 'steps': 30742, 'loss/train': 1.4426699876785278} 08/30/2021 18:48:54 - INFO - __main__ - Step 30744: {'lr': 0.00045489381267769873, 'samples': 5902848, 'steps': 30743, 'loss/train': 2.0978569984436035} 08/30/2021 18:48:54 - INFO - __main__ - Step 30745: {'lr': 0.00045489077201795147, 'samples': 5903040, 'steps': 30744, 'loss/train': 0.0938764363527298} 08/30/2021 18:48:54 - INFO - __main__ - Step 30746: {'lr': 0.0004548877312658836, 'samples': 5903232, 'steps': 30745, 'loss/train': 0.2202833890914917} 08/30/2021 18:48:56 - INFO - __main__ - Step 30747: {'lr': 0.0004548846904214964, 'samples': 5903424, 'steps': 30746, 'loss/train': 0.2757856845855713} 08/30/2021 18:48:57 - INFO - __main__ - Step 30748: {'lr': 0.00045488164948479144, 'samples': 5903616, 'steps': 30747, 'loss/train': 5.178355693817139} 08/30/2021 18:48:57 - INFO - __main__ - Step 30749: {'lr': 0.0004548786084557699, 'samples': 5903808, 'steps': 30748, 'loss/train': 2.07846999168396} 08/30/2021 18:48:58 - INFO - __main__ - Step 30750: {'lr': 0.00045487556733443327, 'samples': 5904000, 'steps': 30749, 'loss/train': 2.0349440574645996} 08/30/2021 18:48:58 - INFO - __main__ - Step 30751: {'lr': 0.0004548725261207828, 'samples': 5904192, 'steps': 30750, 'loss/train': 1.6126673221588135} 08/30/2021 18:49:00 - INFO - __main__ - Step 30752: {'lr': 0.0004548694848148199, 'samples': 5904384, 'steps': 30751, 'loss/train': 1.5104974508285522} 08/30/2021 18:49:00 - INFO - __main__ - Step 30753: {'lr': 0.0004548664434165461, 'samples': 5904576, 'steps': 30752, 'loss/train': 1.4509780406951904} 08/30/2021 18:49:00 - INFO - __main__ - Step 30754: {'lr': 0.0004548634019259625, 'samples': 5904768, 'steps': 30753, 'loss/train': 1.9487842321395874} 08/30/2021 18:49:01 - INFO - __main__ - Step 30755: {'lr': 0.0004548603603430708, 'samples': 5904960, 'steps': 30754, 'loss/train': 1.8448978662490845} 08/30/2021 18:49:01 - INFO - __main__ - Step 30756: {'lr': 0.00045485731866787206, 'samples': 5905152, 'steps': 30755, 'loss/train': 2.021697759628296} 08/30/2021 18:49:01 - INFO - __main__ - Step 30757: {'lr': 0.00045485427690036774, 'samples': 5905344, 'steps': 30756, 'loss/train': 1.3422011137008667} 08/30/2021 18:49:03 - INFO - __main__ - Step 30758: {'lr': 0.0004548512350405593, 'samples': 5905536, 'steps': 30757, 'loss/train': 2.2996208667755127} 08/30/2021 18:49:04 - INFO - __main__ - Step 30759: {'lr': 0.00045484819308844806, 'samples': 5905728, 'steps': 30758, 'loss/train': 0.22292634844779968} 08/30/2021 18:49:04 - INFO - __main__ - Step 30760: {'lr': 0.00045484515104403535, 'samples': 5905920, 'steps': 30759, 'loss/train': 1.8509353399276733} 08/30/2021 18:49:04 - INFO - __main__ - Step 30761: {'lr': 0.00045484210890732257, 'samples': 5906112, 'steps': 30760, 'loss/train': 4.3263840675354} 08/30/2021 18:49:05 - INFO - __main__ - Step 30762: {'lr': 0.0004548390666783111, 'samples': 5906304, 'steps': 30761, 'loss/train': 1.7753716707229614} 08/30/2021 18:49:06 - INFO - __main__ - Step 30763: {'lr': 0.00045483602435700233, 'samples': 5906496, 'steps': 30762, 'loss/train': 1.623103380203247} 08/30/2021 18:49:07 - INFO - __main__ - Step 30764: {'lr': 0.0004548329819433976, 'samples': 5906688, 'steps': 30763, 'loss/train': 1.4231101274490356} 08/30/2021 18:49:07 - INFO - __main__ - Step 30765: {'lr': 0.00045482993943749835, 'samples': 5906880, 'steps': 30764, 'loss/train': 1.7214608192443848} 08/30/2021 18:49:07 - INFO - __main__ - Step 30766: {'lr': 0.0004548268968393058, 'samples': 5907072, 'steps': 30765, 'loss/train': 1.5821691751480103} 08/30/2021 18:49:08 - INFO - __main__ - Step 30767: {'lr': 0.0004548238541488214, 'samples': 5907264, 'steps': 30766, 'loss/train': 1.4154331684112549} 08/30/2021 18:49:09 - INFO - __main__ - Step 30768: {'lr': 0.00045482081136604665, 'samples': 5907456, 'steps': 30767, 'loss/train': 2.2561757564544678} 08/30/2021 18:49:10 - INFO - __main__ - Step 30769: {'lr': 0.0004548177684909827, 'samples': 5907648, 'steps': 30768, 'loss/train': 2.097651481628418} 08/30/2021 18:49:10 - INFO - __main__ - Step 30770: {'lr': 0.0004548147255236311, 'samples': 5907840, 'steps': 30769, 'loss/train': 1.6543786525726318} 08/30/2021 18:49:11 - INFO - __main__ - Step 30771: {'lr': 0.0004548116824639931, 'samples': 5908032, 'steps': 30770, 'loss/train': 0.8371409177780151} 08/30/2021 18:49:11 - INFO - __main__ - Step 30772: {'lr': 0.00045480863931207004, 'samples': 5908224, 'steps': 30771, 'loss/train': 1.294622540473938} 08/30/2021 18:49:12 - INFO - __main__ - Step 30773: {'lr': 0.0004548055960678635, 'samples': 5908416, 'steps': 30772, 'loss/train': 0.9668754935264587} 08/30/2021 18:49:13 - INFO - __main__ - Step 30774: {'lr': 0.0004548025527313746, 'samples': 5908608, 'steps': 30773, 'loss/train': 1.2499743700027466} 08/30/2021 18:49:13 - INFO - __main__ - Step 30775: {'lr': 0.00045479950930260495, 'samples': 5908800, 'steps': 30774, 'loss/train': 1.503238320350647} 08/30/2021 18:49:13 - INFO - __main__ - Step 30776: {'lr': 0.0004547964657815558, 'samples': 5908992, 'steps': 30775, 'loss/train': 2.233491897583008} 08/30/2021 18:49:14 - INFO - __main__ - Step 30777: {'lr': 0.0004547934221682284, 'samples': 5909184, 'steps': 30776, 'loss/train': 1.6315377950668335} 08/30/2021 18:49:15 - INFO - __main__ - Step 30778: {'lr': 0.00045479037846262436, 'samples': 5909376, 'steps': 30777, 'loss/train': 1.4964544773101807} 08/30/2021 18:49:16 - INFO - __main__ - Step 30779: {'lr': 0.00045478733466474487, 'samples': 5909568, 'steps': 30778, 'loss/train': 1.3854427337646484} 08/30/2021 18:49:16 - INFO - __main__ - Step 30780: {'lr': 0.0004547842907745914, 'samples': 5909760, 'steps': 30779, 'loss/train': 2.303678512573242} 08/30/2021 18:49:16 - INFO - __main__ - Step 30781: {'lr': 0.00045478124679216523, 'samples': 5909952, 'steps': 30780, 'loss/train': 0.6042447686195374} 08/30/2021 18:49:17 - INFO - __main__ - Step 30782: {'lr': 0.00045477820271746784, 'samples': 5910144, 'steps': 30781, 'loss/train': 1.8237941265106201} 08/30/2021 18:49:18 - INFO - __main__ - Step 30783: {'lr': 0.00045477515855050056, 'samples': 5910336, 'steps': 30782, 'loss/train': 1.467685341835022} 08/30/2021 18:49:19 - INFO - __main__ - Step 30784: {'lr': 0.0004547721142912647, 'samples': 5910528, 'steps': 30783, 'loss/train': 1.4459495544433594} 08/30/2021 18:49:19 - INFO - __main__ - Step 30785: {'lr': 0.00045476906993976177, 'samples': 5910720, 'steps': 30784, 'loss/train': 1.0934888124465942} 08/30/2021 18:49:19 - INFO - __main__ - Step 30786: {'lr': 0.000454766025495993, 'samples': 5910912, 'steps': 30785, 'loss/train': 1.7733380794525146} 08/30/2021 18:49:20 - INFO - __main__ - Step 30787: {'lr': 0.00045476298095995985, 'samples': 5911104, 'steps': 30786, 'loss/train': 1.3310542106628418} 08/30/2021 18:49:21 - INFO - __main__ - Step 30788: {'lr': 0.00045475993633166357, 'samples': 5911296, 'steps': 30787, 'loss/train': 2.087355375289917} 08/30/2021 18:49:22 - INFO - __main__ - Step 30789: {'lr': 0.00045475689161110565, 'samples': 5911488, 'steps': 30788, 'loss/train': 1.472395658493042} 08/30/2021 18:49:22 - INFO - __main__ - Step 30790: {'lr': 0.0004547538467982876, 'samples': 5911680, 'steps': 30789, 'loss/train': 1.384239673614502} 08/30/2021 18:49:22 - INFO - __main__ - Step 30791: {'lr': 0.00045475080189321044, 'samples': 5911872, 'steps': 30790, 'loss/train': 1.9620822668075562} 08/30/2021 18:49:23 - INFO - __main__ - Step 30792: {'lr': 0.00045474775689587576, 'samples': 5912064, 'steps': 30791, 'loss/train': 0.883018434047699} 08/30/2021 18:49:25 - INFO - __main__ - Step 30793: {'lr': 0.00045474471180628496, 'samples': 5912256, 'steps': 30792, 'loss/train': 1.6669585704803467} 08/30/2021 18:49:25 - INFO - __main__ - Step 30794: {'lr': 0.0004547416666244393, 'samples': 5912448, 'steps': 30793, 'loss/train': 1.5542956590652466} 08/30/2021 18:49:25 - INFO - __main__ - Step 30795: {'lr': 0.00045473862135034026, 'samples': 5912640, 'steps': 30794, 'loss/train': 2.344510078430176} 08/30/2021 18:49:26 - INFO - __main__ - Step 30796: {'lr': 0.0004547355759839891, 'samples': 5912832, 'steps': 30795, 'loss/train': 1.3065285682678223} 08/30/2021 18:49:26 - INFO - __main__ - Step 30797: {'lr': 0.00045473253052538725, 'samples': 5913024, 'steps': 30796, 'loss/train': 1.646628737449646} 08/30/2021 18:49:26 - INFO - __main__ - Step 30798: {'lr': 0.00045472948497453613, 'samples': 5913216, 'steps': 30797, 'loss/train': 0.9493818879127502} 08/30/2021 18:49:28 - INFO - __main__ - Step 30799: {'lr': 0.00045472643933143703, 'samples': 5913408, 'steps': 30798, 'loss/train': 1.842537760734558} 08/30/2021 18:49:28 - INFO - __main__ - Step 30800: {'lr': 0.0004547233935960914, 'samples': 5913600, 'steps': 30799, 'loss/train': 1.8786332607269287} 08/30/2021 18:49:29 - INFO - __main__ - Step 30801: {'lr': 0.00045472034776850045, 'samples': 5913792, 'steps': 30800, 'loss/train': 1.1885528564453125} 08/30/2021 18:49:29 - INFO - __main__ - Step 30802: {'lr': 0.0004547173018486658, 'samples': 5913984, 'steps': 30801, 'loss/train': 1.4817523956298828} 08/30/2021 18:49:30 - INFO - __main__ - Step 30803: {'lr': 0.0004547142558365887, 'samples': 5914176, 'steps': 30802, 'loss/train': 1.4305671453475952} 08/30/2021 18:49:31 - INFO - __main__ - Step 30804: {'lr': 0.0004547112097322704, 'samples': 5914368, 'steps': 30803, 'loss/train': 1.8907513618469238} 08/30/2021 18:49:32 - INFO - __main__ - Step 30805: {'lr': 0.00045470816353571244, 'samples': 5914560, 'steps': 30804, 'loss/train': 2.446058988571167} 08/30/2021 18:49:32 - INFO - __main__ - Step 30806: {'lr': 0.00045470511724691613, 'samples': 5914752, 'steps': 30805, 'loss/train': 1.7583787441253662} 08/30/2021 18:49:32 - INFO - __main__ - Step 30807: {'lr': 0.0004547020708658829, 'samples': 5914944, 'steps': 30806, 'loss/train': 2.3162994384765625} 08/30/2021 18:49:33 - INFO - __main__ - Step 30808: {'lr': 0.000454699024392614, 'samples': 5915136, 'steps': 30807, 'loss/train': 1.706202507019043} 08/30/2021 18:49:35 - INFO - __main__ - Step 30809: {'lr': 0.0004546959778271109, 'samples': 5915328, 'steps': 30808, 'loss/train': 1.5376631021499634} 08/30/2021 18:49:35 - INFO - __main__ - Step 30810: {'lr': 0.00045469293116937504, 'samples': 5915520, 'steps': 30809, 'loss/train': 1.5420583486557007} 08/30/2021 18:49:36 - INFO - __main__ - Step 30811: {'lr': 0.0004546898844194076, 'samples': 5915712, 'steps': 30810, 'loss/train': 2.193227529525757} 08/30/2021 18:49:36 - INFO - __main__ - Step 30812: {'lr': 0.00045468683757721005, 'samples': 5915904, 'steps': 30811, 'loss/train': 1.6837040185928345} 08/30/2021 18:49:36 - INFO - __main__ - Step 30813: {'lr': 0.0004546837906427839, 'samples': 5916096, 'steps': 30812, 'loss/train': 0.13308674097061157} 08/30/2021 18:49:38 - INFO - __main__ - Step 30814: {'lr': 0.00045468074361613026, 'samples': 5916288, 'steps': 30813, 'loss/train': 1.2525848150253296} 08/30/2021 18:49:38 - INFO - __main__ - Step 30815: {'lr': 0.0004546776964972507, 'samples': 5916480, 'steps': 30814, 'loss/train': 1.945178508758545} 08/30/2021 18:49:38 - INFO - __main__ - Step 30816: {'lr': 0.00045467464928614657, 'samples': 5916672, 'steps': 30815, 'loss/train': 6.111526012420654} 08/30/2021 18:49:39 - INFO - __main__ - Step 30817: {'lr': 0.0004546716019828191, 'samples': 5916864, 'steps': 30816, 'loss/train': 1.3960533142089844} 08/30/2021 18:49:39 - INFO - __main__ - Step 30818: {'lr': 0.00045466855458726975, 'samples': 5917056, 'steps': 30817, 'loss/train': 2.6399331092834473} 08/30/2021 18:49:40 - INFO - __main__ - Step 30819: {'lr': 0.0004546655070995, 'samples': 5917248, 'steps': 30818, 'loss/train': 1.5689665079116821} 08/30/2021 18:49:41 - INFO - __main__ - Step 30820: {'lr': 0.0004546624595195111, 'samples': 5917440, 'steps': 30819, 'loss/train': 0.791919469833374} 08/30/2021 18:49:42 - INFO - __main__ - Step 30821: {'lr': 0.0004546594118473044, 'samples': 5917632, 'steps': 30820, 'loss/train': 1.7441242933273315} 08/30/2021 18:49:43 - INFO - __main__ - Step 30822: {'lr': 0.0004546563640828814, 'samples': 5917824, 'steps': 30821, 'loss/train': 1.2575478553771973} 08/30/2021 18:49:43 - INFO - __main__ - Step 30823: {'lr': 0.0004546533162262434, 'samples': 5918016, 'steps': 30822, 'loss/train': 1.7007139921188354} 08/30/2021 18:49:43 - INFO - __main__ - Step 30824: {'lr': 0.00045465026827739175, 'samples': 5918208, 'steps': 30823, 'loss/train': 1.6082549095153809} 08/30/2021 18:49:44 - INFO - __main__ - Step 30825: {'lr': 0.00045464722023632784, 'samples': 5918400, 'steps': 30824, 'loss/train': 1.9467318058013916} 08/30/2021 18:49:45 - INFO - __main__ - Step 30826: {'lr': 0.00045464417210305303, 'samples': 5918592, 'steps': 30825, 'loss/train': 1.5734565258026123} 08/30/2021 18:49:45 - INFO - __main__ - Step 30827: {'lr': 0.0004546411238775687, 'samples': 5918784, 'steps': 30826, 'loss/train': 1.1093934774398804} 08/30/2021 18:49:46 - INFO - __main__ - Step 30828: {'lr': 0.00045463807555987633, 'samples': 5918976, 'steps': 30827, 'loss/train': 1.1093077659606934} 08/30/2021 18:49:46 - INFO - __main__ - Step 30829: {'lr': 0.0004546350271499772, 'samples': 5919168, 'steps': 30828, 'loss/train': 1.193590760231018} 08/30/2021 18:49:47 - INFO - __main__ - Step 30830: {'lr': 0.0004546319786478726, 'samples': 5919360, 'steps': 30829, 'loss/train': 2.011993646621704} 08/30/2021 18:49:48 - INFO - __main__ - Step 30831: {'lr': 0.000454628930053564, 'samples': 5919552, 'steps': 30830, 'loss/train': 1.3023673295974731} 08/30/2021 18:49:48 - INFO - __main__ - Step 30832: {'lr': 0.0004546258813670528, 'samples': 5919744, 'steps': 30831, 'loss/train': 1.8731135129928589} 08/30/2021 18:49:49 - INFO - __main__ - Step 30833: {'lr': 0.0004546228325883403, 'samples': 5919936, 'steps': 30832, 'loss/train': 1.9937634468078613} 08/30/2021 18:49:49 - INFO - __main__ - Step 30834: {'lr': 0.00045461978371742794, 'samples': 5920128, 'steps': 30833, 'loss/train': 1.5370526313781738} 08/30/2021 18:49:50 - INFO - __main__ - Step 30835: {'lr': 0.00045461673475431704, 'samples': 5920320, 'steps': 30834, 'loss/train': 1.700066089630127} 08/30/2021 18:49:50 - INFO - __main__ - Step 30836: {'lr': 0.00045461368569900895, 'samples': 5920512, 'steps': 30835, 'loss/train': 0.6655746102333069} 08/30/2021 18:49:51 - INFO - __main__ - Step 30837: {'lr': 0.0004546106365515052, 'samples': 5920704, 'steps': 30836, 'loss/train': 1.4005099534988403} 08/30/2021 18:49:52 - INFO - __main__ - Step 30838: {'lr': 0.000454607587311807, 'samples': 5920896, 'steps': 30837, 'loss/train': 1.4010639190673828} 08/30/2021 18:49:52 - INFO - __main__ - Step 30839: {'lr': 0.00045460453797991577, 'samples': 5921088, 'steps': 30838, 'loss/train': 2.6396536827087402} 08/30/2021 18:49:52 - INFO - __main__ - Step 30840: {'lr': 0.00045460148855583295, 'samples': 5921280, 'steps': 30839, 'loss/train': 0.8429959416389465} 08/30/2021 18:49:53 - INFO - __main__ - Step 30841: {'lr': 0.00045459843903955977, 'samples': 5921472, 'steps': 30840, 'loss/train': 2.4020378589630127} 08/30/2021 18:49:54 - INFO - __main__ - Step 30842: {'lr': 0.00045459538943109774, 'samples': 5921664, 'steps': 30841, 'loss/train': 2.0796077251434326} 08/30/2021 18:49:55 - INFO - __main__ - Step 30843: {'lr': 0.0004545923397304482, 'samples': 5921856, 'steps': 30842, 'loss/train': 1.5825914144515991} 08/30/2021 18:49:55 - INFO - __main__ - Step 30844: {'lr': 0.0004545892899376125, 'samples': 5922048, 'steps': 30843, 'loss/train': 1.1890977621078491} 08/30/2021 18:49:56 - INFO - __main__ - Step 30845: {'lr': 0.000454586240052592, 'samples': 5922240, 'steps': 30844, 'loss/train': 1.7922642230987549} 08/30/2021 18:49:56 - INFO - __main__ - Step 30846: {'lr': 0.00045458319007538804, 'samples': 5922432, 'steps': 30845, 'loss/train': 0.11606493592262268} 08/30/2021 18:49:58 - INFO - __main__ - Step 30847: {'lr': 0.00045458014000600213, 'samples': 5922624, 'steps': 30846, 'loss/train': 2.962897300720215} 08/30/2021 18:49:58 - INFO - __main__ - Step 30848: {'lr': 0.00045457708984443556, 'samples': 5922816, 'steps': 30847, 'loss/train': 1.8580104112625122} 08/30/2021 18:49:59 - INFO - __main__ - Step 30849: {'lr': 0.0004545740395906897, 'samples': 5923008, 'steps': 30848, 'loss/train': 1.2826155424118042} 08/30/2021 18:49:59 - INFO - __main__ - Step 30850: {'lr': 0.0004545709892447659, 'samples': 5923200, 'steps': 30849, 'loss/train': 1.5987087488174438} 08/30/2021 18:49:59 - INFO - __main__ - Step 30851: {'lr': 0.00045456793880666556, 'samples': 5923392, 'steps': 30850, 'loss/train': 1.9053318500518799} 08/30/2021 18:50:01 - INFO - __main__ - Step 30852: {'lr': 0.0004545648882763902, 'samples': 5923584, 'steps': 30851, 'loss/train': 2.3845627307891846} 08/30/2021 18:50:01 - INFO - __main__ - Step 30853: {'lr': 0.0004545618376539409, 'samples': 5923776, 'steps': 30852, 'loss/train': 1.5275685787200928} 08/30/2021 18:50:02 - INFO - __main__ - Step 30854: {'lr': 0.0004545587869393193, 'samples': 5923968, 'steps': 30853, 'loss/train': 1.8131331205368042} 08/30/2021 18:50:02 - INFO - __main__ - Step 30855: {'lr': 0.00045455573613252667, 'samples': 5924160, 'steps': 30854, 'loss/train': 1.545103907585144} 08/30/2021 18:50:02 - INFO - __main__ - Step 30856: {'lr': 0.0004545526852335643, 'samples': 5924352, 'steps': 30855, 'loss/train': 0.4495946764945984} 08/30/2021 18:50:03 - INFO - __main__ - Step 30857: {'lr': 0.0004545496342424337, 'samples': 5924544, 'steps': 30856, 'loss/train': 1.836046814918518} 08/30/2021 18:50:04 - INFO - __main__ - Step 30858: {'lr': 0.00045454658315913617, 'samples': 5924736, 'steps': 30857, 'loss/train': 1.7491945028305054} 08/30/2021 18:50:05 - INFO - __main__ - Step 30859: {'lr': 0.0004545435319836731, 'samples': 5924928, 'steps': 30858, 'loss/train': 1.735776662826538} 08/30/2021 18:50:05 - INFO - __main__ - Step 30860: {'lr': 0.00045454048071604593, 'samples': 5925120, 'steps': 30859, 'loss/train': 1.489484190940857} 08/30/2021 18:50:05 - INFO - __main__ - Step 30861: {'lr': 0.0004545374293562559, 'samples': 5925312, 'steps': 30860, 'loss/train': 1.7237929105758667} 08/30/2021 18:50:06 - INFO - __main__ - Step 30862: {'lr': 0.00045453437790430446, 'samples': 5925504, 'steps': 30861, 'loss/train': 1.4091020822525024} 08/30/2021 18:50:07 - INFO - __main__ - Step 30863: {'lr': 0.000454531326360193, 'samples': 5925696, 'steps': 30862, 'loss/train': 1.1842780113220215} 08/30/2021 18:50:08 - INFO - __main__ - Step 30864: {'lr': 0.00045452827472392286, 'samples': 5925888, 'steps': 30863, 'loss/train': 1.3570895195007324} 08/30/2021 18:50:08 - INFO - __main__ - Step 30865: {'lr': 0.0004545252229954955, 'samples': 5926080, 'steps': 30864, 'loss/train': 1.746134638786316} 08/30/2021 18:50:08 - INFO - __main__ - Step 30866: {'lr': 0.00045452217117491225, 'samples': 5926272, 'steps': 30865, 'loss/train': 1.3915296792984009} 08/30/2021 18:50:09 - INFO - __main__ - Step 30867: {'lr': 0.00045451911926217437, 'samples': 5926464, 'steps': 30866, 'loss/train': 2.1020700931549072} 08/30/2021 18:50:10 - INFO - __main__ - Step 30868: {'lr': 0.00045451606725728337, 'samples': 5926656, 'steps': 30867, 'loss/train': 1.5282713174819946} 08/30/2021 18:50:11 - INFO - __main__ - Step 30869: {'lr': 0.0004545130151602406, 'samples': 5926848, 'steps': 30868, 'loss/train': 1.4010648727416992} 08/30/2021 18:50:11 - INFO - __main__ - Step 30870: {'lr': 0.00045450996297104743, 'samples': 5927040, 'steps': 30869, 'loss/train': 1.5088531970977783} 08/30/2021 18:50:11 - INFO - __main__ - Step 30871: {'lr': 0.00045450691068970515, 'samples': 5927232, 'steps': 30870, 'loss/train': 1.042020559310913} 08/30/2021 18:50:12 - INFO - __main__ - Step 30872: {'lr': 0.00045450385831621534, 'samples': 5927424, 'steps': 30871, 'loss/train': 0.8496931195259094} 08/30/2021 18:50:13 - INFO - __main__ - Step 30873: {'lr': 0.0004545008058505792, 'samples': 5927616, 'steps': 30872, 'loss/train': 1.6761102676391602} 08/30/2021 18:50:14 - INFO - __main__ - Step 30874: {'lr': 0.0004544977532927981, 'samples': 5927808, 'steps': 30873, 'loss/train': 1.7711992263793945} 08/30/2021 18:50:14 - INFO - __main__ - Step 30875: {'lr': 0.0004544947006428735, 'samples': 5928000, 'steps': 30874, 'loss/train': 1.7140474319458008} 08/30/2021 18:50:14 - INFO - __main__ - Step 30876: {'lr': 0.00045449164790080675, 'samples': 5928192, 'steps': 30875, 'loss/train': 2.2052786350250244} 08/30/2021 18:50:15 - INFO - __main__ - Step 30877: {'lr': 0.00045448859506659926, 'samples': 5928384, 'steps': 30876, 'loss/train': 1.2395455837249756} 08/30/2021 18:50:16 - INFO - __main__ - Step 30878: {'lr': 0.0004544855421402523, 'samples': 5928576, 'steps': 30877, 'loss/train': 0.8298559188842773} 08/30/2021 18:50:17 - INFO - __main__ - Step 30879: {'lr': 0.00045448248912176726, 'samples': 5928768, 'steps': 30878, 'loss/train': 1.4166877269744873} 08/30/2021 18:50:17 - INFO - __main__ - Step 30880: {'lr': 0.00045447943601114563, 'samples': 5928960, 'steps': 30879, 'loss/train': 1.4694899320602417} 08/30/2021 18:50:17 - INFO - __main__ - Step 30881: {'lr': 0.00045447638280838877, 'samples': 5929152, 'steps': 30880, 'loss/train': 2.2456774711608887} 08/30/2021 18:50:18 - INFO - __main__ - Step 30882: {'lr': 0.000454473329513498, 'samples': 5929344, 'steps': 30881, 'loss/train': 1.9202115535736084} 08/30/2021 18:50:19 - INFO - __main__ - Step 30883: {'lr': 0.0004544702761264746, 'samples': 5929536, 'steps': 30882, 'loss/train': 1.6379255056381226} 08/30/2021 18:50:20 - INFO - __main__ - Step 30884: {'lr': 0.0004544672226473201, 'samples': 5929728, 'steps': 30883, 'loss/train': 1.4454952478408813} 08/30/2021 18:50:20 - INFO - __main__ - Step 30885: {'lr': 0.00045446416907603585, 'samples': 5929920, 'steps': 30884, 'loss/train': 0.6298514008522034} 08/30/2021 18:50:21 - INFO - __main__ - Step 30886: {'lr': 0.00045446111541262317, 'samples': 5930112, 'steps': 30885, 'loss/train': 1.408557653427124} 08/30/2021 18:50:21 - INFO - __main__ - Step 30887: {'lr': 0.0004544580616570835, 'samples': 5930304, 'steps': 30886, 'loss/train': 1.8558675050735474} 08/30/2021 18:50:21 - INFO - __main__ - Step 30888: {'lr': 0.0004544550078094182, 'samples': 5930496, 'steps': 30887, 'loss/train': 2.537599563598633} 08/30/2021 18:50:23 - INFO - __main__ - Step 30889: {'lr': 0.00045445195386962855, 'samples': 5930688, 'steps': 30888, 'loss/train': 1.8573321104049683} 08/30/2021 18:50:23 - INFO - __main__ - Step 30890: {'lr': 0.0004544488998377161, 'samples': 5930880, 'steps': 30889, 'loss/train': 1.3963596820831299} 08/30/2021 18:50:23 - INFO - __main__ - Step 30891: {'lr': 0.000454445845713682, 'samples': 5931072, 'steps': 30890, 'loss/train': 1.4934232234954834} 08/30/2021 18:50:24 - INFO - __main__ - Step 30892: {'lr': 0.0004544427914975279, 'samples': 5931264, 'steps': 30891, 'loss/train': 1.6173315048217773} 08/30/2021 18:50:24 - INFO - __main__ - Step 30893: {'lr': 0.0004544397371892549, 'samples': 5931456, 'steps': 30892, 'loss/train': 1.3055099248886108} 08/30/2021 18:50:26 - INFO - __main__ - Step 30894: {'lr': 0.00045443668278886463, 'samples': 5931648, 'steps': 30893, 'loss/train': 2.3843724727630615} 08/30/2021 18:50:26 - INFO - __main__ - Step 30895: {'lr': 0.00045443362829635826, 'samples': 5931840, 'steps': 30894, 'loss/train': 1.3252021074295044} 08/30/2021 18:50:27 - INFO - __main__ - Step 30896: {'lr': 0.00045443057371173727, 'samples': 5932032, 'steps': 30895, 'loss/train': 1.3170150518417358} 08/30/2021 18:50:27 - INFO - __main__ - Step 30897: {'lr': 0.00045442751903500305, 'samples': 5932224, 'steps': 30896, 'loss/train': 1.4374134540557861} 08/30/2021 18:50:27 - INFO - __main__ - Step 30898: {'lr': 0.0004544244642661569, 'samples': 5932416, 'steps': 30897, 'loss/train': 1.7875052690505981} 08/30/2021 18:50:29 - INFO - __main__ - Step 30899: {'lr': 0.00045442140940520027, 'samples': 5932608, 'steps': 30898, 'loss/train': 1.4098151922225952} 08/30/2021 18:50:30 - INFO - __main__ - Step 30900: {'lr': 0.0004544183544521345, 'samples': 5932800, 'steps': 30899, 'loss/train': 1.2480617761611938} 08/30/2021 18:50:30 - INFO - __main__ - Step 30901: {'lr': 0.00045441529940696104, 'samples': 5932992, 'steps': 30900, 'loss/train': 0.08100544661283493} 08/30/2021 18:50:31 - INFO - __main__ - Step 30902: {'lr': 0.0004544122442696811, 'samples': 5933184, 'steps': 30901, 'loss/train': 1.4734858274459839} 08/30/2021 18:50:31 - INFO - __main__ - Step 30903: {'lr': 0.0004544091890402962, 'samples': 5933376, 'steps': 30902, 'loss/train': 5.889724254608154} 08/30/2021 18:50:31 - INFO - __main__ - Step 30904: {'lr': 0.0004544061337188077, 'samples': 5933568, 'steps': 30903, 'loss/train': 1.1169508695602417} 08/30/2021 18:50:33 - INFO - __main__ - Step 30905: {'lr': 0.0004544030783052169, 'samples': 5933760, 'steps': 30904, 'loss/train': 1.4590866565704346} 08/30/2021 18:50:33 - INFO - __main__ - Step 30906: {'lr': 0.0004544000227995253, 'samples': 5933952, 'steps': 30905, 'loss/train': 1.4959120750427246} 08/30/2021 18:50:34 - INFO - __main__ - Step 30907: {'lr': 0.00045439696720173405, 'samples': 5934144, 'steps': 30906, 'loss/train': 1.5704470872879028} 08/30/2021 18:50:34 - INFO - __main__ - Step 30908: {'lr': 0.00045439391151184483, 'samples': 5934336, 'steps': 30907, 'loss/train': 0.8742191195487976} 08/30/2021 18:50:34 - INFO - __main__ - Step 30909: {'lr': 0.0004543908557298588, 'samples': 5934528, 'steps': 30908, 'loss/train': 6.299698829650879} 08/30/2021 18:50:36 - INFO - __main__ - Step 30910: {'lr': 0.0004543877998557775, 'samples': 5934720, 'steps': 30909, 'loss/train': 1.4043680429458618} 08/30/2021 18:50:36 - INFO - __main__ - Step 30911: {'lr': 0.00045438474388960205, 'samples': 5934912, 'steps': 30910, 'loss/train': 1.7212448120117188} 08/30/2021 18:50:37 - INFO - __main__ - Step 30912: {'lr': 0.0004543816878313341, 'samples': 5935104, 'steps': 30911, 'loss/train': 0.9468260407447815} 08/30/2021 18:50:37 - INFO - __main__ - Step 30913: {'lr': 0.0004543786316809749, 'samples': 5935296, 'steps': 30912, 'loss/train': 1.539900302886963} 08/30/2021 18:50:37 - INFO - __main__ - Step 30914: {'lr': 0.0004543755754385258, 'samples': 5935488, 'steps': 30913, 'loss/train': 1.3757702112197876} 08/30/2021 18:50:39 - INFO - __main__ - Step 30915: {'lr': 0.00045437251910398824, 'samples': 5935680, 'steps': 30914, 'loss/train': 1.5696769952774048} 08/30/2021 18:50:39 - INFO - __main__ - Step 30916: {'lr': 0.00045436946267736364, 'samples': 5935872, 'steps': 30915, 'loss/train': 1.4715920686721802} 08/30/2021 18:50:40 - INFO - __main__ - Step 30917: {'lr': 0.0004543664061586532, 'samples': 5936064, 'steps': 30916, 'loss/train': 1.9693139791488647} 08/30/2021 18:50:40 - INFO - __main__ - Step 30918: {'lr': 0.00045436334954785854, 'samples': 5936256, 'steps': 30917, 'loss/train': 1.5209686756134033} 08/30/2021 18:50:40 - INFO - __main__ - Step 30919: {'lr': 0.0004543602928449808, 'samples': 5936448, 'steps': 30918, 'loss/train': 1.678979516029358} 08/30/2021 18:50:42 - INFO - __main__ - Step 30920: {'lr': 0.00045435723605002156, 'samples': 5936640, 'steps': 30919, 'loss/train': 1.150206208229065} 08/30/2021 18:50:43 - INFO - __main__ - Step 30921: {'lr': 0.00045435417916298205, 'samples': 5936832, 'steps': 30920, 'loss/train': 1.7728164196014404} 08/30/2021 18:50:43 - INFO - __main__ - Step 30922: {'lr': 0.00045435112218386364, 'samples': 5937024, 'steps': 30921, 'loss/train': 1.5260149240493774} 08/30/2021 18:50:43 - INFO - __main__ - Step 30923: {'lr': 0.00045434806511266784, 'samples': 5937216, 'steps': 30922, 'loss/train': 1.8596521615982056} 08/30/2021 18:50:44 - INFO - __main__ - Step 30924: {'lr': 0.0004543450079493959, 'samples': 5937408, 'steps': 30923, 'loss/train': 1.4759269952774048} 08/30/2021 18:50:44 - INFO - __main__ - Step 30925: {'lr': 0.0004543419506940494, 'samples': 5937600, 'steps': 30924, 'loss/train': 1.5433435440063477} 08/30/2021 18:50:46 - INFO - __main__ - Step 30926: {'lr': 0.0004543388933466294, 'samples': 5937792, 'steps': 30925, 'loss/train': 1.554054617881775} 08/30/2021 18:50:46 - INFO - __main__ - Step 30927: {'lr': 0.00045433583590713756, 'samples': 5937984, 'steps': 30926, 'loss/train': 1.2592685222625732} 08/30/2021 18:50:46 - INFO - __main__ - Step 30928: {'lr': 0.0004543327783755751, 'samples': 5938176, 'steps': 30927, 'loss/train': 1.513053297996521} 08/30/2021 18:50:47 - INFO - __main__ - Step 30929: {'lr': 0.0004543297207519434, 'samples': 5938368, 'steps': 30928, 'loss/train': 1.5072624683380127} 08/30/2021 18:50:47 - INFO - __main__ - Step 30930: {'lr': 0.0004543266630362439, 'samples': 5938560, 'steps': 30929, 'loss/train': 1.7903330326080322} 08/30/2021 18:50:49 - INFO - __main__ - Step 30931: {'lr': 0.00045432360522847803, 'samples': 5938752, 'steps': 30930, 'loss/train': 1.0317519903182983} 08/30/2021 18:50:49 - INFO - __main__ - Step 30932: {'lr': 0.000454320547328647, 'samples': 5938944, 'steps': 30931, 'loss/train': 1.5009169578552246} 08/30/2021 18:50:49 - INFO - __main__ - Step 30933: {'lr': 0.00045431748933675236, 'samples': 5939136, 'steps': 30932, 'loss/train': 1.7834892272949219} 08/30/2021 18:50:50 - INFO - __main__ - Step 30934: {'lr': 0.00045431443125279534, 'samples': 5939328, 'steps': 30933, 'loss/train': 1.3241400718688965} 08/30/2021 18:50:50 - INFO - __main__ - Step 30935: {'lr': 0.00045431137307677753, 'samples': 5939520, 'steps': 30934, 'loss/train': 1.6047395467758179} 08/30/2021 18:50:50 - INFO - __main__ - Step 30936: {'lr': 0.00045430831480870005, 'samples': 5939712, 'steps': 30935, 'loss/train': 2.9298365116119385} 08/30/2021 18:50:52 - INFO - __main__ - Step 30937: {'lr': 0.0004543052564485644, 'samples': 5939904, 'steps': 30936, 'loss/train': 1.4615219831466675} 08/30/2021 18:50:53 - INFO - __main__ - Step 30938: {'lr': 0.00045430219799637197, 'samples': 5940096, 'steps': 30937, 'loss/train': 1.4555654525756836} 08/30/2021 18:50:53 - INFO - __main__ - Step 30939: {'lr': 0.0004542991394521241, 'samples': 5940288, 'steps': 30938, 'loss/train': 0.75577712059021} 08/30/2021 18:50:54 - INFO - __main__ - Step 30940: {'lr': 0.00045429608081582216, 'samples': 5940480, 'steps': 30939, 'loss/train': 1.7842686176300049} 08/30/2021 18:50:54 - INFO - __main__ - Step 30941: {'lr': 0.0004542930220874677, 'samples': 5940672, 'steps': 30940, 'loss/train': 1.5237113237380981} 08/30/2021 18:50:54 - INFO - __main__ - Step 30942: {'lr': 0.00045428996326706185, 'samples': 5940864, 'steps': 30941, 'loss/train': 1.1260379552841187} 08/30/2021 18:50:56 - INFO - __main__ - Step 30943: {'lr': 0.0004542869043546061, 'samples': 5941056, 'steps': 30942, 'loss/train': 0.05700213089585304} 08/30/2021 18:50:56 - INFO - __main__ - Step 30944: {'lr': 0.0004542838453501018, 'samples': 5941248, 'steps': 30943, 'loss/train': 1.2519384622573853} 08/30/2021 18:50:57 - INFO - __main__ - Step 30945: {'lr': 0.0004542807862535504, 'samples': 5941440, 'steps': 30944, 'loss/train': 1.4879227876663208} 08/30/2021 18:50:57 - INFO - __main__ - Step 30946: {'lr': 0.0004542777270649533, 'samples': 5941632, 'steps': 30945, 'loss/train': 1.4120968580245972} 08/30/2021 18:50:57 - INFO - __main__ - Step 30947: {'lr': 0.0004542746677843117, 'samples': 5941824, 'steps': 30946, 'loss/train': 1.5219526290893555} 08/30/2021 18:50:59 - INFO - __main__ - Step 30948: {'lr': 0.0004542716084116271, 'samples': 5942016, 'steps': 30947, 'loss/train': 1.6526983976364136} 08/30/2021 18:50:59 - INFO - __main__ - Step 30949: {'lr': 0.0004542685489469008, 'samples': 5942208, 'steps': 30948, 'loss/train': 1.6261321306228638} 08/30/2021 18:51:00 - INFO - __main__ - Step 30950: {'lr': 0.0004542654893901344, 'samples': 5942400, 'steps': 30949, 'loss/train': 1.5929393768310547} 08/30/2021 18:51:00 - INFO - __main__ - Step 30951: {'lr': 0.00045426242974132904, 'samples': 5942592, 'steps': 30950, 'loss/train': 1.4672390222549438} 08/30/2021 18:51:00 - INFO - __main__ - Step 30952: {'lr': 0.0004542593700004862, 'samples': 5942784, 'steps': 30951, 'loss/train': 0.5524551272392273} 08/30/2021 18:51:02 - INFO - __main__ - Step 30953: {'lr': 0.0004542563101676072, 'samples': 5942976, 'steps': 30952, 'loss/train': 2.3349385261535645} 08/30/2021 18:51:03 - INFO - __main__ - Step 30954: {'lr': 0.0004542532502426935, 'samples': 5943168, 'steps': 30953, 'loss/train': 1.7408747673034668} 08/30/2021 18:51:03 - INFO - __main__ - Step 30955: {'lr': 0.0004542501902257464, 'samples': 5943360, 'steps': 30954, 'loss/train': 0.8640762567520142} 08/30/2021 18:51:03 - INFO - __main__ - Step 30956: {'lr': 0.0004542471301167673, 'samples': 5943552, 'steps': 30955, 'loss/train': 1.533851146697998} 08/30/2021 18:51:04 - INFO - __main__ - Step 30957: {'lr': 0.0004542440699157577, 'samples': 5943744, 'steps': 30956, 'loss/train': 1.377493143081665} 08/30/2021 18:51:04 - INFO - __main__ - Step 30958: {'lr': 0.00045424100962271883, 'samples': 5943936, 'steps': 30957, 'loss/train': 0.5838767290115356} 08/30/2021 18:51:06 - INFO - __main__ - Step 30959: {'lr': 0.00045423794923765204, 'samples': 5944128, 'steps': 30958, 'loss/train': 1.1220017671585083} 08/30/2021 18:51:06 - INFO - __main__ - Step 30960: {'lr': 0.00045423488876055883, 'samples': 5944320, 'steps': 30959, 'loss/train': 1.49917471408844} 08/30/2021 18:51:06 - INFO - __main__ - Step 30961: {'lr': 0.00045423182819144054, 'samples': 5944512, 'steps': 30960, 'loss/train': 1.4788119792938232} 08/30/2021 18:51:07 - INFO - __main__ - Step 30962: {'lr': 0.00045422876753029853, 'samples': 5944704, 'steps': 30961, 'loss/train': 2.0732154846191406} 08/30/2021 18:51:07 - INFO - __main__ - Step 30963: {'lr': 0.0004542257067771342, 'samples': 5944896, 'steps': 30962, 'loss/train': 1.7146772146224976} 08/30/2021 18:51:09 - INFO - __main__ - Step 30964: {'lr': 0.0004542226459319489, 'samples': 5945088, 'steps': 30963, 'loss/train': 1.3630406856536865} 08/30/2021 18:51:09 - INFO - __main__ - Step 30965: {'lr': 0.000454219584994744, 'samples': 5945280, 'steps': 30964, 'loss/train': 1.5847492218017578} 08/30/2021 18:51:09 - INFO - __main__ - Step 30966: {'lr': 0.00045421652396552094, 'samples': 5945472, 'steps': 30965, 'loss/train': 1.6061770915985107} 08/30/2021 18:51:10 - INFO - __main__ - Step 30967: {'lr': 0.0004542134628442811, 'samples': 5945664, 'steps': 30966, 'loss/train': 1.8897978067398071} 08/30/2021 18:51:10 - INFO - __main__ - Step 30968: {'lr': 0.0004542104016310258, 'samples': 5945856, 'steps': 30967, 'loss/train': 1.4476398229599} 08/30/2021 18:51:12 - INFO - __main__ - Step 30969: {'lr': 0.0004542073403257564, 'samples': 5946048, 'steps': 30968, 'loss/train': 1.5867505073547363} 08/30/2021 18:51:12 - INFO - __main__ - Step 30970: {'lr': 0.0004542042789284744, 'samples': 5946240, 'steps': 30969, 'loss/train': 0.815251886844635} 08/30/2021 18:51:13 - INFO - __main__ - Step 30971: {'lr': 0.0004542012174391811, 'samples': 5946432, 'steps': 30970, 'loss/train': 1.3785136938095093} 08/30/2021 18:51:13 - INFO - __main__ - Step 30972: {'lr': 0.0004541981558578778, 'samples': 5946624, 'steps': 30971, 'loss/train': 1.2928060293197632} 08/30/2021 18:51:14 - INFO - __main__ - Step 30973: {'lr': 0.00045419509418456603, 'samples': 5946816, 'steps': 30972, 'loss/train': 0.06197367236018181} 08/30/2021 18:51:14 - INFO - __main__ - Step 30974: {'lr': 0.00045419203241924705, 'samples': 5947008, 'steps': 30973, 'loss/train': 0.049440354108810425} 08/30/2021 18:51:15 - INFO - __main__ - Step 30975: {'lr': 0.00045418897056192234, 'samples': 5947200, 'steps': 30974, 'loss/train': 1.4731558561325073} 08/30/2021 18:51:16 - INFO - __main__ - Step 30976: {'lr': 0.00045418590861259317, 'samples': 5947392, 'steps': 30975, 'loss/train': 1.7465013265609741} 08/30/2021 18:51:16 - INFO - __main__ - Step 30977: {'lr': 0.0004541828465712611, 'samples': 5947584, 'steps': 30976, 'loss/train': 2.1222403049468994} 08/30/2021 18:51:17 - INFO - __main__ - Step 30978: {'lr': 0.0004541797844379273, 'samples': 5947776, 'steps': 30977, 'loss/train': 1.5453827381134033} 08/30/2021 18:51:17 - INFO - __main__ - Step 30979: {'lr': 0.0004541767222125932, 'samples': 5947968, 'steps': 30978, 'loss/train': 0.9147385358810425} 08/30/2021 18:51:18 - INFO - __main__ - Step 30980: {'lr': 0.0004541736598952603, 'samples': 5948160, 'steps': 30979, 'loss/train': 1.868829607963562} 08/30/2021 18:51:19 - INFO - __main__ - Step 30981: {'lr': 0.0004541705974859298, 'samples': 5948352, 'steps': 30980, 'loss/train': 1.7710955142974854} 08/30/2021 18:51:19 - INFO - __main__ - Step 30982: {'lr': 0.0004541675349846033, 'samples': 5948544, 'steps': 30981, 'loss/train': 1.6964755058288574} 08/30/2021 18:51:20 - INFO - __main__ - Step 30983: {'lr': 0.000454164472391282, 'samples': 5948736, 'steps': 30982, 'loss/train': 1.7199519872665405} 08/30/2021 18:51:20 - INFO - __main__ - Step 30984: {'lr': 0.00045416140970596736, 'samples': 5948928, 'steps': 30983, 'loss/train': 1.543184518814087} 08/30/2021 18:51:21 - INFO - __main__ - Step 30985: {'lr': 0.0004541583469286607, 'samples': 5949120, 'steps': 30984, 'loss/train': 1.5816707611083984} 08/30/2021 18:51:22 - INFO - __main__ - Step 30986: {'lr': 0.00045415528405936347, 'samples': 5949312, 'steps': 30985, 'loss/train': 0.5726720690727234} 08/30/2021 18:51:22 - INFO - __main__ - Step 30987: {'lr': 0.000454152221098077, 'samples': 5949504, 'steps': 30986, 'loss/train': 2.082681179046631} 08/30/2021 18:51:23 - INFO - __main__ - Step 30988: {'lr': 0.0004541491580448027, 'samples': 5949696, 'steps': 30987, 'loss/train': 0.43030846118927} 08/30/2021 18:51:23 - INFO - __main__ - Step 30989: {'lr': 0.00045414609489954195, 'samples': 5949888, 'steps': 30988, 'loss/train': 1.1053502559661865} 08/30/2021 18:51:24 - INFO - __main__ - Step 30990: {'lr': 0.00045414303166229616, 'samples': 5950080, 'steps': 30989, 'loss/train': 1.3367358446121216} 08/30/2021 18:51:25 - INFO - __main__ - Step 30991: {'lr': 0.0004541399683330666, 'samples': 5950272, 'steps': 30990, 'loss/train': 1.6095401048660278} 08/30/2021 18:51:25 - INFO - __main__ - Step 30992: {'lr': 0.00045413690491185476, 'samples': 5950464, 'steps': 30991, 'loss/train': 1.5008652210235596} 08/30/2021 18:51:25 - INFO - __main__ - Step 30993: {'lr': 0.00045413384139866196, 'samples': 5950656, 'steps': 30992, 'loss/train': 1.0580347776412964} 08/30/2021 18:51:26 - INFO - __main__ - Step 30994: {'lr': 0.0004541307777934896, 'samples': 5950848, 'steps': 30993, 'loss/train': 1.4069619178771973} 08/30/2021 18:51:27 - INFO - __main__ - Step 30995: {'lr': 0.00045412771409633905, 'samples': 5951040, 'steps': 30994, 'loss/train': 1.3995437622070312} 08/30/2021 18:51:28 - INFO - __main__ - Step 30996: {'lr': 0.0004541246503072117, 'samples': 5951232, 'steps': 30995, 'loss/train': 1.1555570363998413} 08/30/2021 18:51:28 - INFO - __main__ - Step 30997: {'lr': 0.000454121586426109, 'samples': 5951424, 'steps': 30996, 'loss/train': 0.0732298418879509} 08/30/2021 18:51:28 - INFO - __main__ - Step 30998: {'lr': 0.0004541185224530322, 'samples': 5951616, 'steps': 30997, 'loss/train': 1.7845025062561035} 08/30/2021 18:51:29 - INFO - __main__ - Step 30999: {'lr': 0.00045411545838798273, 'samples': 5951808, 'steps': 30998, 'loss/train': 2.0827035903930664} 08/30/2021 18:51:31 - INFO - __main__ - Step 31000: {'lr': 0.00045411239423096206, 'samples': 5952000, 'steps': 30999, 'loss/train': 1.3978526592254639} 08/30/2021 18:51:31 - INFO - __main__ - Step 31001: {'lr': 0.0004541093299819714, 'samples': 5952192, 'steps': 31000, 'loss/train': 1.2286460399627686} 08/30/2021 18:51:31 - INFO - __main__ - Step 31002: {'lr': 0.0004541062656410123, 'samples': 5952384, 'steps': 31001, 'loss/train': 1.4909310340881348} 08/30/2021 18:51:32 - INFO - __main__ - Step 31003: {'lr': 0.000454103201208086, 'samples': 5952576, 'steps': 31002, 'loss/train': 1.0090872049331665} 08/30/2021 18:51:32 - INFO - __main__ - Step 31004: {'lr': 0.00045410013668319404, 'samples': 5952768, 'steps': 31003, 'loss/train': 1.0905442237854004} 08/30/2021 18:51:34 - INFO - __main__ - Step 31005: {'lr': 0.00045409707206633764, 'samples': 5952960, 'steps': 31004, 'loss/train': 1.5193109512329102} 08/30/2021 18:51:34 - INFO - __main__ - Step 31006: {'lr': 0.0004540940073575183, 'samples': 5953152, 'steps': 31005, 'loss/train': 1.1039931774139404} 08/30/2021 18:51:35 - INFO - __main__ - Step 31007: {'lr': 0.00045409094255673734, 'samples': 5953344, 'steps': 31006, 'loss/train': 0.048871610313653946} 08/30/2021 18:51:35 - INFO - __main__ - Step 31008: {'lr': 0.00045408787766399605, 'samples': 5953536, 'steps': 31007, 'loss/train': 1.1516616344451904} 08/30/2021 18:51:36 - INFO - __main__ - Step 31009: {'lr': 0.00045408481267929604, 'samples': 5953728, 'steps': 31008, 'loss/train': 1.1795395612716675} 08/30/2021 18:51:36 - INFO - __main__ - Step 31010: {'lr': 0.0004540817476026385, 'samples': 5953920, 'steps': 31009, 'loss/train': 1.6250652074813843} 08/30/2021 18:51:38 - INFO - __main__ - Step 31011: {'lr': 0.00045407868243402483, 'samples': 5954112, 'steps': 31010, 'loss/train': 1.7105629444122314} 08/30/2021 18:51:39 - INFO - __main__ - Step 31012: {'lr': 0.0004540756171734565, 'samples': 5954304, 'steps': 31011, 'loss/train': 1.6094919443130493} 08/30/2021 18:51:39 - INFO - __main__ - Step 31013: {'lr': 0.0004540725518209349, 'samples': 5954496, 'steps': 31012, 'loss/train': 1.7254704236984253} 08/30/2021 18:51:40 - INFO - __main__ - Step 31014: {'lr': 0.0004540694863764613, 'samples': 5954688, 'steps': 31013, 'loss/train': 1.6626132726669312} 08/30/2021 18:51:40 - INFO - __main__ - Step 31015: {'lr': 0.0004540664208400371, 'samples': 5954880, 'steps': 31014, 'loss/train': 1.1268343925476074} 08/30/2021 18:51:40 - INFO - __main__ - Step 31016: {'lr': 0.0004540633552116638, 'samples': 5955072, 'steps': 31015, 'loss/train': 0.9672594666481018} 08/30/2021 18:51:42 - INFO - __main__ - Step 31017: {'lr': 0.0004540602894913427, 'samples': 5955264, 'steps': 31016, 'loss/train': 1.5981063842773438} 08/30/2021 18:51:42 - INFO - __main__ - Step 31018: {'lr': 0.0004540572236790751, 'samples': 5955456, 'steps': 31017, 'loss/train': 1.673006534576416} 08/30/2021 18:51:43 - INFO - __main__ - Step 31019: {'lr': 0.0004540541577748625, 'samples': 5955648, 'steps': 31018, 'loss/train': 1.6203272342681885} 08/30/2021 18:51:43 - INFO - __main__ - Step 31020: {'lr': 0.0004540510917787063, 'samples': 5955840, 'steps': 31019, 'loss/train': 1.5703866481781006} 08/30/2021 18:51:43 - INFO - __main__ - Step 31021: {'lr': 0.00045404802569060776, 'samples': 5956032, 'steps': 31020, 'loss/train': 1.4292266368865967} 08/30/2021 18:51:45 - INFO - __main__ - Step 31022: {'lr': 0.00045404495951056835, 'samples': 5956224, 'steps': 31021, 'loss/train': 0.05232563614845276} 08/30/2021 18:51:46 - INFO - __main__ - Step 31023: {'lr': 0.00045404189323858946, 'samples': 5956416, 'steps': 31022, 'loss/train': 1.0030027627944946} 08/30/2021 18:51:46 - INFO - __main__ - Step 31024: {'lr': 0.0004540388268746724, 'samples': 5956608, 'steps': 31023, 'loss/train': 1.4967166185379028} 08/30/2021 18:51:46 - INFO - __main__ - Step 31025: {'lr': 0.0004540357604188186, 'samples': 5956800, 'steps': 31024, 'loss/train': 1.2149097919464111} 08/30/2021 18:51:47 - INFO - __main__ - Step 31026: {'lr': 0.0004540326938710295, 'samples': 5956992, 'steps': 31025, 'loss/train': 1.8220106363296509} 08/30/2021 18:51:48 - INFO - __main__ - Step 31027: {'lr': 0.0004540296272313064, 'samples': 5957184, 'steps': 31026, 'loss/train': 1.1777232885360718} 08/30/2021 18:51:48 - INFO - __main__ - Step 31028: {'lr': 0.00045402656049965055, 'samples': 5957376, 'steps': 31027, 'loss/train': 1.8113280534744263} 08/30/2021 18:51:49 - INFO - __main__ - Step 31029: {'lr': 0.0004540234936760636, 'samples': 5957568, 'steps': 31028, 'loss/train': 0.05803866684436798} 08/30/2021 18:51:49 - INFO - __main__ - Step 31030: {'lr': 0.00045402042676054684, 'samples': 5957760, 'steps': 31029, 'loss/train': 1.611311912536621} 08/30/2021 18:51:50 - INFO - __main__ - Step 31031: {'lr': 0.0004540173597531015, 'samples': 5957952, 'steps': 31030, 'loss/train': 1.4595378637313843} 08/30/2021 18:51:51 - INFO - __main__ - Step 31032: {'lr': 0.00045401429265372925, 'samples': 5958144, 'steps': 31031, 'loss/train': 1.6035057306289673} 08/30/2021 18:51:52 - INFO - __main__ - Step 31033: {'lr': 0.0004540112254624312, 'samples': 5958336, 'steps': 31032, 'loss/train': 1.3567496538162231} 08/30/2021 18:51:52 - INFO - __main__ - Step 31034: {'lr': 0.0004540081581792089, 'samples': 5958528, 'steps': 31033, 'loss/train': 1.5247254371643066} 08/30/2021 18:51:52 - INFO - __main__ - Step 31035: {'lr': 0.0004540050908040636, 'samples': 5958720, 'steps': 31034, 'loss/train': 1.4087685346603394} 08/30/2021 18:51:53 - INFO - __main__ - Step 31036: {'lr': 0.0004540020233369968, 'samples': 5958912, 'steps': 31035, 'loss/train': 1.0668528079986572} 08/30/2021 18:51:53 - INFO - __main__ - Step 31037: {'lr': 0.00045399895577800985, 'samples': 5959104, 'steps': 31036, 'loss/train': 1.4852564334869385} 08/30/2021 18:51:55 - INFO - __main__ - Step 31038: {'lr': 0.00045399588812710415, 'samples': 5959296, 'steps': 31037, 'loss/train': 1.8841310739517212} 08/30/2021 18:51:55 - INFO - __main__ - Step 31039: {'lr': 0.0004539928203842809, 'samples': 5959488, 'steps': 31038, 'loss/train': 1.509718894958496} 08/30/2021 18:51:56 - INFO - __main__ - Step 31040: {'lr': 0.0004539897525495418, 'samples': 5959680, 'steps': 31039, 'loss/train': 1.5329985618591309} 08/30/2021 18:51:56 - INFO - __main__ - Step 31041: {'lr': 0.0004539866846228879, 'samples': 5959872, 'steps': 31040, 'loss/train': 0.9507527947425842} 08/30/2021 18:51:56 - INFO - __main__ - Step 31042: {'lr': 0.0004539836166043209, 'samples': 5960064, 'steps': 31041, 'loss/train': 2.8790485858917236} 08/30/2021 18:51:57 - INFO - __main__ - Step 31043: {'lr': 0.00045398054849384197, 'samples': 5960256, 'steps': 31042, 'loss/train': 1.3953723907470703} 08/30/2021 18:51:58 - INFO - __main__ - Step 31044: {'lr': 0.0004539774802914526, 'samples': 5960448, 'steps': 31043, 'loss/train': 0.906587541103363} 08/30/2021 18:51:59 - INFO - __main__ - Step 31045: {'lr': 0.00045397441199715406, 'samples': 5960640, 'steps': 31044, 'loss/train': 1.4648103713989258} 08/30/2021 18:51:59 - INFO - __main__ - Step 31046: {'lr': 0.0004539713436109478, 'samples': 5960832, 'steps': 31045, 'loss/train': 1.0116899013519287} 08/30/2021 18:51:59 - INFO - __main__ - Step 31047: {'lr': 0.0004539682751328352, 'samples': 5961024, 'steps': 31046, 'loss/train': 0.8836275935173035} 08/30/2021 18:52:00 - INFO - __main__ - Step 31048: {'lr': 0.0004539652065628177, 'samples': 5961216, 'steps': 31047, 'loss/train': 1.0747270584106445} 08/30/2021 18:52:01 - INFO - __main__ - Step 31049: {'lr': 0.00045396213790089657, 'samples': 5961408, 'steps': 31048, 'loss/train': 1.699660062789917} 08/30/2021 18:52:02 - INFO - __main__ - Step 31050: {'lr': 0.0004539590691470733, 'samples': 5961600, 'steps': 31049, 'loss/train': 1.7925145626068115} 08/30/2021 18:52:02 - INFO - __main__ - Step 31051: {'lr': 0.0004539560003013492, 'samples': 5961792, 'steps': 31050, 'loss/train': 1.9361777305603027} 08/30/2021 18:52:02 - INFO - __main__ - Step 31052: {'lr': 0.0004539529313637256, 'samples': 5961984, 'steps': 31051, 'loss/train': 0.6117641925811768} 08/30/2021 18:52:03 - INFO - __main__ - Step 31053: {'lr': 0.0004539498623342041, 'samples': 5962176, 'steps': 31052, 'loss/train': 1.6726100444793701} 08/30/2021 18:52:03 - INFO - __main__ - Step 31054: {'lr': 0.0004539467932127858, 'samples': 5962368, 'steps': 31053, 'loss/train': 1.8790496587753296} 08/30/2021 18:52:05 - INFO - __main__ - Step 31055: {'lr': 0.00045394372399947225, 'samples': 5962560, 'steps': 31054, 'loss/train': 1.194793939590454} 08/30/2021 18:52:05 - INFO - __main__ - Step 31056: {'lr': 0.0004539406546942649, 'samples': 5962752, 'steps': 31055, 'loss/train': 1.072791576385498} 08/30/2021 18:52:06 - INFO - __main__ - Step 31057: {'lr': 0.00045393758529716497, 'samples': 5962944, 'steps': 31056, 'loss/train': 1.4414101839065552} 08/30/2021 18:52:06 - INFO - __main__ - Step 31058: {'lr': 0.0004539345158081739, 'samples': 5963136, 'steps': 31057, 'loss/train': 1.4591870307922363} 08/30/2021 18:52:06 - INFO - __main__ - Step 31059: {'lr': 0.0004539314462272931, 'samples': 5963328, 'steps': 31058, 'loss/train': 0.067268967628479} 08/30/2021 18:52:08 - INFO - __main__ - Step 31060: {'lr': 0.0004539283765545239, 'samples': 5963520, 'steps': 31059, 'loss/train': 1.6859824657440186} 08/30/2021 18:52:08 - INFO - __main__ - Step 31061: {'lr': 0.00045392530678986775, 'samples': 5963712, 'steps': 31060, 'loss/train': 1.5808331966400146} 08/30/2021 18:52:09 - INFO - __main__ - Step 31062: {'lr': 0.00045392223693332604, 'samples': 5963904, 'steps': 31061, 'loss/train': 1.3589439392089844} 08/30/2021 18:52:09 - INFO - __main__ - Step 31063: {'lr': 0.0004539191669849001, 'samples': 5964096, 'steps': 31062, 'loss/train': 1.4981449842453003} 08/30/2021 18:52:09 - INFO - __main__ - Step 31064: {'lr': 0.0004539160969445913, 'samples': 5964288, 'steps': 31063, 'loss/train': 1.7644106149673462} 08/30/2021 18:52:11 - INFO - __main__ - Step 31065: {'lr': 0.0004539130268124011, 'samples': 5964480, 'steps': 31064, 'loss/train': 2.0092480182647705} 08/30/2021 18:52:12 - INFO - __main__ - Step 31066: {'lr': 0.0004539099565883308, 'samples': 5964672, 'steps': 31065, 'loss/train': 1.1268682479858398} 08/30/2021 18:52:12 - INFO - __main__ - Step 31067: {'lr': 0.0004539068862723818, 'samples': 5964864, 'steps': 31066, 'loss/train': 1.950039029121399} 08/30/2021 18:52:12 - INFO - __main__ - Step 31068: {'lr': 0.0004539038158645555, 'samples': 5965056, 'steps': 31067, 'loss/train': 1.7845966815948486} 08/30/2021 18:52:13 - INFO - __main__ - Step 31069: {'lr': 0.00045390074536485336, 'samples': 5965248, 'steps': 31068, 'loss/train': 1.6465349197387695} 08/30/2021 18:52:15 - INFO - __main__ - Step 31070: {'lr': 0.00045389767477327657, 'samples': 5965440, 'steps': 31069, 'loss/train': 1.3320573568344116} 08/30/2021 18:52:15 - INFO - __main__ - Step 31071: {'lr': 0.00045389460408982676, 'samples': 5965632, 'steps': 31070, 'loss/train': 1.6265623569488525} 08/30/2021 18:52:15 - INFO - __main__ - Step 31072: {'lr': 0.0004538915333145052, 'samples': 5965824, 'steps': 31071, 'loss/train': 1.2257441282272339} 08/30/2021 18:52:16 - INFO - __main__ - Step 31073: {'lr': 0.00045388846244731314, 'samples': 5966016, 'steps': 31072, 'loss/train': 1.6296617984771729} 08/30/2021 18:52:16 - INFO - __main__ - Step 31074: {'lr': 0.00045388539148825214, 'samples': 5966208, 'steps': 31073, 'loss/train': 0.9754083156585693} 08/30/2021 18:52:18 - INFO - __main__ - Step 31075: {'lr': 0.0004538823204373235, 'samples': 5966400, 'steps': 31074, 'loss/train': 2.2619900703430176} 08/30/2021 18:52:18 - INFO - __main__ - Step 31076: {'lr': 0.00045387924929452873, 'samples': 5966592, 'steps': 31075, 'loss/train': 1.3385144472122192} 08/30/2021 18:52:18 - INFO - __main__ - Step 31077: {'lr': 0.000453876178059869, 'samples': 5966784, 'steps': 31076, 'loss/train': 0.9936423897743225} 08/30/2021 18:52:19 - INFO - __main__ - Step 31078: {'lr': 0.0004538731067333459, 'samples': 5966976, 'steps': 31077, 'loss/train': 1.4712036848068237} 08/30/2021 18:52:19 - INFO - __main__ - Step 31079: {'lr': 0.00045387003531496064, 'samples': 5967168, 'steps': 31078, 'loss/train': 1.9899890422821045} 08/30/2021 18:52:21 - INFO - __main__ - Step 31080: {'lr': 0.00045386696380471473, 'samples': 5967360, 'steps': 31079, 'loss/train': 0.9737958312034607} 08/30/2021 18:52:21 - INFO - __main__ - Step 31081: {'lr': 0.0004538638922026095, 'samples': 5967552, 'steps': 31080, 'loss/train': 1.493228554725647} 08/30/2021 18:52:22 - INFO - __main__ - Step 31082: {'lr': 0.0004538608205086464, 'samples': 5967744, 'steps': 31081, 'loss/train': 1.5865614414215088} 08/30/2021 18:52:22 - INFO - __main__ - Step 31083: {'lr': 0.0004538577487228267, 'samples': 5967936, 'steps': 31082, 'loss/train': 3.5823469161987305} 08/30/2021 18:52:22 - INFO - __main__ - Step 31084: {'lr': 0.00045385467684515193, 'samples': 5968128, 'steps': 31083, 'loss/train': 1.3502602577209473} 08/30/2021 18:52:23 - INFO - __main__ - Step 31085: {'lr': 0.0004538516048756233, 'samples': 5968320, 'steps': 31084, 'loss/train': 1.6726070642471313} 08/30/2021 18:52:24 - INFO - __main__ - Step 31086: {'lr': 0.00045384853281424235, 'samples': 5968512, 'steps': 31085, 'loss/train': 1.6115013360977173} 08/30/2021 18:52:25 - INFO - __main__ - Step 31087: {'lr': 0.0004538454606610103, 'samples': 5968704, 'steps': 31086, 'loss/train': 1.8925801515579224} 08/30/2021 18:52:25 - INFO - __main__ - Step 31088: {'lr': 0.0004538423884159287, 'samples': 5968896, 'steps': 31087, 'loss/train': 1.3612579107284546} 08/30/2021 18:52:25 - INFO - __main__ - Step 31089: {'lr': 0.0004538393160789988, 'samples': 5969088, 'steps': 31088, 'loss/train': 1.130507469177246} 08/30/2021 18:52:26 - INFO - __main__ - Step 31090: {'lr': 0.0004538362436502221, 'samples': 5969280, 'steps': 31089, 'loss/train': 1.4128400087356567} 08/30/2021 18:52:27 - INFO - __main__ - Step 31091: {'lr': 0.00045383317112959997, 'samples': 5969472, 'steps': 31090, 'loss/train': 1.4794267416000366} 08/30/2021 18:52:28 - INFO - __main__ - Step 31092: {'lr': 0.0004538300985171337, 'samples': 5969664, 'steps': 31091, 'loss/train': 0.6922190189361572} 08/30/2021 18:52:28 - INFO - __main__ - Step 31093: {'lr': 0.00045382702581282477, 'samples': 5969856, 'steps': 31092, 'loss/train': 1.3636902570724487} 08/30/2021 18:52:28 - INFO - __main__ - Step 31094: {'lr': 0.0004538239530166745, 'samples': 5970048, 'steps': 31093, 'loss/train': 1.274987816810608} 08/30/2021 18:52:29 - INFO - __main__ - Step 31095: {'lr': 0.0004538208801286843, 'samples': 5970240, 'steps': 31094, 'loss/train': 1.672188401222229} 08/30/2021 18:52:30 - INFO - __main__ - Step 31096: {'lr': 0.0004538178071488556, 'samples': 5970432, 'steps': 31095, 'loss/train': 1.1953009366989136} 08/30/2021 18:52:31 - INFO - __main__ - Step 31097: {'lr': 0.00045381473407718963, 'samples': 5970624, 'steps': 31096, 'loss/train': 0.9305090308189392} 08/30/2021 18:52:31 - INFO - __main__ - Step 31098: {'lr': 0.000453811660913688, 'samples': 5970816, 'steps': 31097, 'loss/train': 1.1199299097061157} 08/30/2021 18:52:31 - INFO - __main__ - Step 31099: {'lr': 0.000453808587658352, 'samples': 5971008, 'steps': 31098, 'loss/train': 1.1736019849777222} 08/30/2021 18:52:32 - INFO - __main__ - Step 31100: {'lr': 0.0004538055143111829, 'samples': 5971200, 'steps': 31099, 'loss/train': 1.5111671686172485} 08/30/2021 18:52:33 - INFO - __main__ - Step 31101: {'lr': 0.00045380244087218224, 'samples': 5971392, 'steps': 31100, 'loss/train': 1.2263879776000977} 08/30/2021 18:52:34 - INFO - __main__ - Step 31102: {'lr': 0.0004537993673413513, 'samples': 5971584, 'steps': 31101, 'loss/train': 1.2177152633666992} 08/30/2021 18:52:34 - INFO - __main__ - Step 31103: {'lr': 0.0004537962937186916, 'samples': 5971776, 'steps': 31102, 'loss/train': 5.836368560791016} 08/30/2021 18:52:35 - INFO - __main__ - Step 31104: {'lr': 0.00045379322000420433, 'samples': 5971968, 'steps': 31103, 'loss/train': 1.0182262659072876} 08/30/2021 18:52:35 - INFO - __main__ - Step 31105: {'lr': 0.00045379014619789106, 'samples': 5972160, 'steps': 31104, 'loss/train': 0.6063989996910095} 08/30/2021 18:52:35 - INFO - __main__ - Step 31106: {'lr': 0.00045378707229975303, 'samples': 5972352, 'steps': 31105, 'loss/train': 1.6027045249938965} 08/30/2021 18:52:37 - INFO - __main__ - Step 31107: {'lr': 0.0004537839983097917, 'samples': 5972544, 'steps': 31106, 'loss/train': 1.9376516342163086} 08/30/2021 18:52:38 - INFO - __main__ - Step 31108: {'lr': 0.0004537809242280085, 'samples': 5972736, 'steps': 31107, 'loss/train': 1.4661369323730469} 08/30/2021 18:52:38 - INFO - __main__ - Step 31109: {'lr': 0.0004537778500544047, 'samples': 5972928, 'steps': 31108, 'loss/train': 1.029530644416809} 08/30/2021 18:52:38 - INFO - __main__ - Step 31110: {'lr': 0.0004537747757889817, 'samples': 5973120, 'steps': 31109, 'loss/train': 0.9133874177932739} 08/30/2021 18:52:39 - INFO - __main__ - Step 31111: {'lr': 0.0004537717014317411, 'samples': 5973312, 'steps': 31110, 'loss/train': 1.3333266973495483} 08/30/2021 18:52:39 - INFO - __main__ - Step 31112: {'lr': 0.00045376862698268393, 'samples': 5973504, 'steps': 31111, 'loss/train': 0.038941286504268646} 08/30/2021 18:52:41 - INFO - __main__ - Step 31113: {'lr': 0.0004537655524418119, 'samples': 5973696, 'steps': 31112, 'loss/train': 1.2564735412597656} 08/30/2021 18:52:41 - INFO - __main__ - Step 31114: {'lr': 0.00045376247780912616, 'samples': 5973888, 'steps': 31113, 'loss/train': 1.5433170795440674} 08/30/2021 18:52:42 - INFO - __main__ - Step 31115: {'lr': 0.00045375940308462826, 'samples': 5974080, 'steps': 31114, 'loss/train': 1.9497753381729126} 08/30/2021 18:52:42 - INFO - __main__ - Step 31116: {'lr': 0.00045375632826831947, 'samples': 5974272, 'steps': 31115, 'loss/train': 1.3061171770095825} 08/30/2021 18:52:42 - INFO - __main__ - Step 31117: {'lr': 0.00045375325336020124, 'samples': 5974464, 'steps': 31116, 'loss/train': 1.7052353620529175} 08/30/2021 18:52:44 - INFO - __main__ - Step 31118: {'lr': 0.000453750178360275, 'samples': 5974656, 'steps': 31117, 'loss/train': 1.971119999885559} 08/30/2021 18:52:45 - INFO - __main__ - Step 31119: {'lr': 0.00045374710326854194, 'samples': 5974848, 'steps': 31118, 'loss/train': 1.877492904663086} 08/30/2021 18:52:45 - INFO - __main__ - Step 31120: {'lr': 0.0004537440280850037, 'samples': 5975040, 'steps': 31119, 'loss/train': 1.414506435394287} 08/30/2021 18:52:46 - INFO - __main__ - Step 31121: {'lr': 0.00045374095280966147, 'samples': 5975232, 'steps': 31120, 'loss/train': 1.2564905881881714} 08/30/2021 18:52:46 - INFO - __main__ - Step 31122: {'lr': 0.00045373787744251677, 'samples': 5975424, 'steps': 31121, 'loss/train': 1.7289631366729736} 08/30/2021 18:52:48 - INFO - __main__ - Step 31123: {'lr': 0.0004537348019835709, 'samples': 5975616, 'steps': 31122, 'loss/train': 2.0682358741760254} 08/30/2021 18:52:48 - INFO - __main__ - Step 31124: {'lr': 0.0004537317264328252, 'samples': 5975808, 'steps': 31123, 'loss/train': 1.8440382480621338} 08/30/2021 18:52:49 - INFO - __main__ - Step 31125: {'lr': 0.00045372865079028123, 'samples': 5976000, 'steps': 31124, 'loss/train': 1.3663311004638672} 08/30/2021 18:52:49 - INFO - __main__ - Step 31126: {'lr': 0.00045372557505594024, 'samples': 5976192, 'steps': 31125, 'loss/train': 1.004639744758606} 08/30/2021 18:52:49 - INFO - __main__ - Step 31127: {'lr': 0.0004537224992298037, 'samples': 5976384, 'steps': 31126, 'loss/train': 1.444261908531189} 08/30/2021 18:52:51 - INFO - __main__ - Step 31128: {'lr': 0.00045371942331187286, 'samples': 5976576, 'steps': 31127, 'loss/train': 1.231874704360962} 08/30/2021 18:52:52 - INFO - __main__ - Step 31129: {'lr': 0.00045371634730214923, 'samples': 5976768, 'steps': 31128, 'loss/train': 1.3735706806182861} 08/30/2021 18:52:52 - INFO - __main__ - Step 31130: {'lr': 0.00045371327120063417, 'samples': 5976960, 'steps': 31129, 'loss/train': 1.311033844947815} 08/30/2021 18:52:52 - INFO - __main__ - Step 31131: {'lr': 0.00045371019500732904, 'samples': 5977152, 'steps': 31130, 'loss/train': 1.4586528539657593} 08/30/2021 18:52:53 - INFO - __main__ - Step 31132: {'lr': 0.00045370711872223525, 'samples': 5977344, 'steps': 31131, 'loss/train': 1.6951950788497925} 08/30/2021 18:52:54 - INFO - __main__ - Step 31133: {'lr': 0.00045370404234535414, 'samples': 5977536, 'steps': 31132, 'loss/train': 1.6540215015411377} 08/30/2021 18:52:55 - INFO - __main__ - Step 31134: {'lr': 0.00045370096587668714, 'samples': 5977728, 'steps': 31133, 'loss/train': 1.3159565925598145} 08/30/2021 18:52:55 - INFO - __main__ - Step 31135: {'lr': 0.0004536978893162357, 'samples': 5977920, 'steps': 31134, 'loss/train': 1.6009652614593506} 08/30/2021 18:52:56 - INFO - __main__ - Step 31136: {'lr': 0.000453694812664001, 'samples': 5978112, 'steps': 31135, 'loss/train': 0.08150231093168259} 08/30/2021 18:52:56 - INFO - __main__ - Step 31137: {'lr': 0.00045369173591998466, 'samples': 5978304, 'steps': 31136, 'loss/train': 1.1977040767669678} 08/30/2021 18:52:58 - INFO - __main__ - Step 31138: {'lr': 0.00045368865908418794, 'samples': 5978496, 'steps': 31137, 'loss/train': 1.5556244850158691} 08/30/2021 18:52:58 - INFO - __main__ - Step 31139: {'lr': 0.00045368558215661225, 'samples': 5978688, 'steps': 31138, 'loss/train': 0.7230245471000671} 08/30/2021 18:52:58 - INFO - __main__ - Step 31140: {'lr': 0.00045368250513725896, 'samples': 5978880, 'steps': 31139, 'loss/train': 1.637417197227478} 08/30/2021 18:52:59 - INFO - __main__ - Step 31141: {'lr': 0.00045367942802612953, 'samples': 5979072, 'steps': 31140, 'loss/train': 1.6077171564102173} 08/30/2021 18:52:59 - INFO - __main__ - Step 31142: {'lr': 0.0004536763508232252, 'samples': 5979264, 'steps': 31141, 'loss/train': 1.339439034461975} 08/30/2021 18:52:59 - INFO - __main__ - Step 31143: {'lr': 0.0004536732735285476, 'samples': 5979456, 'steps': 31142, 'loss/train': 5.863194465637207} 08/30/2021 18:53:01 - INFO - __main__ - Step 31144: {'lr': 0.00045367019614209783, 'samples': 5979648, 'steps': 31143, 'loss/train': 1.6931700706481934} 08/30/2021 18:53:02 - INFO - __main__ - Step 31145: {'lr': 0.0004536671186638775, 'samples': 5979840, 'steps': 31144, 'loss/train': 0.042302314192056656} 08/30/2021 18:53:02 - INFO - __main__ - Step 31146: {'lr': 0.0004536640410938879, 'samples': 5980032, 'steps': 31145, 'loss/train': 0.03146910294890404} 08/30/2021 18:53:02 - INFO - __main__ - Step 31147: {'lr': 0.00045366096343213034, 'samples': 5980224, 'steps': 31146, 'loss/train': 2.091280698776245} 08/30/2021 18:53:03 - INFO - __main__ - Step 31148: {'lr': 0.0004536578856786064, 'samples': 5980416, 'steps': 31147, 'loss/train': 0.04584484174847603} 08/30/2021 18:53:03 - INFO - __main__ - Step 31149: {'lr': 0.0004536548078333172, 'samples': 5980608, 'steps': 31148, 'loss/train': 1.5256032943725586} 08/30/2021 18:53:05 - INFO - __main__ - Step 31150: {'lr': 0.0004536517298962645, 'samples': 5980800, 'steps': 31149, 'loss/train': 1.3211700916290283} 08/30/2021 18:53:05 - INFO - __main__ - Step 31151: {'lr': 0.00045364865186744936, 'samples': 5980992, 'steps': 31150, 'loss/train': 1.3922449350357056} 08/30/2021 18:53:06 - INFO - __main__ - Step 31152: {'lr': 0.0004536455737468733, 'samples': 5981184, 'steps': 31151, 'loss/train': 1.3153488636016846} 08/30/2021 18:53:06 - INFO - __main__ - Step 31153: {'lr': 0.00045364249553453764, 'samples': 5981376, 'steps': 31152, 'loss/train': 1.6068469285964966} 08/30/2021 18:53:06 - INFO - __main__ - Step 31154: {'lr': 0.00045363941723044386, 'samples': 5981568, 'steps': 31153, 'loss/train': 0.43992772698402405} 08/30/2021 18:53:08 - INFO - __main__ - Step 31155: {'lr': 0.0004536363388345933, 'samples': 5981760, 'steps': 31154, 'loss/train': 0.6110499501228333} 08/30/2021 18:53:08 - INFO - __main__ - Step 31156: {'lr': 0.0004536332603469873, 'samples': 5981952, 'steps': 31155, 'loss/train': 2.086655378341675} 08/30/2021 18:53:09 - INFO - __main__ - Step 31157: {'lr': 0.0004536301817676274, 'samples': 5982144, 'steps': 31156, 'loss/train': 1.5639941692352295} 08/30/2021 18:53:09 - INFO - __main__ - Step 31158: {'lr': 0.0004536271030965148, 'samples': 5982336, 'steps': 31157, 'loss/train': 1.645655632019043} 08/30/2021 18:53:09 - INFO - __main__ - Step 31159: {'lr': 0.00045362402433365094, 'samples': 5982528, 'steps': 31158, 'loss/train': 0.9686564207077026} 08/30/2021 18:53:11 - INFO - __main__ - Step 31160: {'lr': 0.0004536209454790373, 'samples': 5982720, 'steps': 31159, 'loss/train': 1.864017367362976} 08/30/2021 18:53:12 - INFO - __main__ - Step 31161: {'lr': 0.00045361786653267517, 'samples': 5982912, 'steps': 31160, 'loss/train': 0.12420680373907089} 08/30/2021 18:53:12 - INFO - __main__ - Step 31162: {'lr': 0.00045361478749456595, 'samples': 5983104, 'steps': 31161, 'loss/train': 3.0237133502960205} 08/30/2021 18:53:12 - INFO - __main__ - Step 31163: {'lr': 0.0004536117083647111, 'samples': 5983296, 'steps': 31162, 'loss/train': 1.8580105304718018} 08/30/2021 18:53:13 - INFO - __main__ - Step 31164: {'lr': 0.00045360862914311194, 'samples': 5983488, 'steps': 31163, 'loss/train': 1.566408634185791} 08/30/2021 18:53:13 - INFO - __main__ - Step 31165: {'lr': 0.0004536055498297699, 'samples': 5983680, 'steps': 31164, 'loss/train': 1.535684585571289} 08/30/2021 18:53:15 - INFO - __main__ - Step 31166: {'lr': 0.00045360247042468635, 'samples': 5983872, 'steps': 31165, 'loss/train': 1.7129974365234375} 08/30/2021 18:53:15 - INFO - __main__ - Step 31167: {'lr': 0.0004535993909278626, 'samples': 5984064, 'steps': 31166, 'loss/train': 0.8563997149467468} 08/30/2021 18:53:16 - INFO - __main__ - Step 31168: {'lr': 0.00045359631133930016, 'samples': 5984256, 'steps': 31167, 'loss/train': 0.9915846586227417} 08/30/2021 18:53:16 - INFO - __main__ - Step 31169: {'lr': 0.0004535932316590003, 'samples': 5984448, 'steps': 31168, 'loss/train': 1.1800521612167358} 08/30/2021 18:53:16 - INFO - __main__ - Step 31170: {'lr': 0.00045359015188696457, 'samples': 5984640, 'steps': 31169, 'loss/train': 1.218472957611084} 08/30/2021 18:53:18 - INFO - __main__ - Step 31171: {'lr': 0.00045358707202319414, 'samples': 5984832, 'steps': 31170, 'loss/train': 0.2905478775501251} 08/30/2021 18:53:18 - INFO - __main__ - Step 31172: {'lr': 0.0004535839920676906, 'samples': 5985024, 'steps': 31171, 'loss/train': 1.4037226438522339} 08/30/2021 18:53:19 - INFO - __main__ - Step 31173: {'lr': 0.0004535809120204553, 'samples': 5985216, 'steps': 31172, 'loss/train': 1.6890603303909302} 08/30/2021 18:53:19 - INFO - __main__ - Step 31174: {'lr': 0.0004535778318814895, 'samples': 5985408, 'steps': 31173, 'loss/train': 2.3607726097106934} 08/30/2021 18:53:19 - INFO - __main__ - Step 31175: {'lr': 0.0004535747516507947, 'samples': 5985600, 'steps': 31174, 'loss/train': 1.3518590927124023} 08/30/2021 18:53:21 - INFO - __main__ - Step 31176: {'lr': 0.00045357167132837223, 'samples': 5985792, 'steps': 31175, 'loss/train': 1.698056697845459} 08/30/2021 18:53:22 - INFO - __main__ - Step 31177: {'lr': 0.00045356859091422354, 'samples': 5985984, 'steps': 31176, 'loss/train': 1.3519233465194702} 08/30/2021 18:53:22 - INFO - __main__ - Step 31178: {'lr': 0.00045356551040835, 'samples': 5986176, 'steps': 31177, 'loss/train': 1.9519325494766235} 08/30/2021 18:53:23 - INFO - __main__ - Step 31179: {'lr': 0.0004535624298107529, 'samples': 5986368, 'steps': 31178, 'loss/train': 0.7612841129302979} 08/30/2021 18:53:23 - INFO - __main__ - Step 31180: {'lr': 0.00045355934912143383, 'samples': 5986560, 'steps': 31179, 'loss/train': 1.4055265188217163} 08/30/2021 18:53:25 - INFO - __main__ - Step 31181: {'lr': 0.00045355626834039394, 'samples': 5986752, 'steps': 31180, 'loss/train': 1.1429792642593384} 08/30/2021 18:53:25 - INFO - __main__ - Step 31182: {'lr': 0.00045355318746763477, 'samples': 5986944, 'steps': 31181, 'loss/train': 1.7932724952697754} 08/30/2021 18:53:25 - INFO - __main__ - Step 31183: {'lr': 0.0004535501065031577, 'samples': 5987136, 'steps': 31182, 'loss/train': 1.4591612815856934} 08/30/2021 18:53:26 - INFO - __main__ - Step 31184: {'lr': 0.0004535470254469641, 'samples': 5987328, 'steps': 31183, 'loss/train': 1.613660216331482} 08/30/2021 18:53:26 - INFO - __main__ - Step 31185: {'lr': 0.00045354394429905534, 'samples': 5987520, 'steps': 31184, 'loss/train': 1.0812500715255737} 08/30/2021 18:53:26 - INFO - __main__ - Step 31186: {'lr': 0.0004535408630594328, 'samples': 5987712, 'steps': 31185, 'loss/train': 1.4802604913711548} 08/30/2021 18:53:28 - INFO - __main__ - Step 31187: {'lr': 0.0004535377817280979, 'samples': 5987904, 'steps': 31186, 'loss/train': 1.2999248504638672} 08/30/2021 18:53:29 - INFO - __main__ - Step 31188: {'lr': 0.0004535347003050521, 'samples': 5988096, 'steps': 31187, 'loss/train': 1.9061965942382812} 08/30/2021 18:53:29 - INFO - __main__ - Step 31189: {'lr': 0.0004535316187902966, 'samples': 5988288, 'steps': 31188, 'loss/train': 1.8329979181289673} 08/30/2021 18:53:29 - INFO - __main__ - Step 31190: {'lr': 0.00045352853718383287, 'samples': 5988480, 'steps': 31189, 'loss/train': 1.17955482006073} 08/30/2021 18:53:30 - INFO - __main__ - Step 31191: {'lr': 0.00045352545548566235, 'samples': 5988672, 'steps': 31190, 'loss/train': 0.9641557931900024} 08/30/2021 18:53:31 - INFO - __main__ - Step 31192: {'lr': 0.00045352237369578643, 'samples': 5988864, 'steps': 31191, 'loss/train': 1.7571990489959717} 08/30/2021 18:53:32 - INFO - __main__ - Step 31193: {'lr': 0.00045351929181420647, 'samples': 5989056, 'steps': 31192, 'loss/train': 1.1081897020339966} 08/30/2021 18:53:32 - INFO - __main__ - Step 31194: {'lr': 0.0004535162098409238, 'samples': 5989248, 'steps': 31193, 'loss/train': 1.587311029434204} 08/30/2021 18:53:32 - INFO - __main__ - Step 31195: {'lr': 0.00045351312777593995, 'samples': 5989440, 'steps': 31194, 'loss/train': 1.9999451637268066} 08/30/2021 18:53:33 - INFO - __main__ - Step 31196: {'lr': 0.0004535100456192562, 'samples': 5989632, 'steps': 31195, 'loss/train': 1.288652777671814} 08/30/2021 18:53:34 - INFO - __main__ - Step 31197: {'lr': 0.00045350696337087396, 'samples': 5989824, 'steps': 31196, 'loss/train': 2.101027250289917} 08/30/2021 18:53:35 - INFO - __main__ - Step 31198: {'lr': 0.0004535038810307946, 'samples': 5990016, 'steps': 31197, 'loss/train': 1.3536226749420166} 08/30/2021 18:53:35 - INFO - __main__ - Step 31199: {'lr': 0.00045350079859901956, 'samples': 5990208, 'steps': 31198, 'loss/train': 0.947283148765564} 08/30/2021 18:53:35 - INFO - __main__ - Step 31200: {'lr': 0.00045349771607555017, 'samples': 5990400, 'steps': 31199, 'loss/train': 1.8714150190353394} 08/30/2021 18:53:36 - INFO - __main__ - Step 31201: {'lr': 0.0004534946334603879, 'samples': 5990592, 'steps': 31200, 'loss/train': 1.0475910902023315} 08/30/2021 18:53:37 - INFO - __main__ - Step 31202: {'lr': 0.000453491550753534, 'samples': 5990784, 'steps': 31201, 'loss/train': 1.507918119430542} 08/30/2021 18:53:38 - INFO - __main__ - Step 31203: {'lr': 0.00045348846795499, 'samples': 5990976, 'steps': 31202, 'loss/train': 1.7241178750991821} 08/30/2021 18:53:38 - INFO - __main__ - Step 31204: {'lr': 0.0004534853850647572, 'samples': 5991168, 'steps': 31203, 'loss/train': 1.460509181022644} 08/30/2021 18:53:39 - INFO - __main__ - Step 31205: {'lr': 0.00045348230208283716, 'samples': 5991360, 'steps': 31204, 'loss/train': 1.3862348794937134} 08/30/2021 18:53:39 - INFO - __main__ - Step 31206: {'lr': 0.000453479219009231, 'samples': 5991552, 'steps': 31205, 'loss/train': 1.6321722269058228} 08/30/2021 18:53:40 - INFO - __main__ - Step 31207: {'lr': 0.00045347613584394034, 'samples': 5991744, 'steps': 31206, 'loss/train': 0.8021978139877319} 08/30/2021 18:53:41 - INFO - __main__ - Step 31208: {'lr': 0.0004534730525869664, 'samples': 5991936, 'steps': 31207, 'loss/train': 1.1721975803375244} 08/30/2021 18:53:41 - INFO - __main__ - Step 31209: {'lr': 0.0004534699692383106, 'samples': 5992128, 'steps': 31208, 'loss/train': 0.846610963344574} 08/30/2021 18:53:42 - INFO - __main__ - Step 31210: {'lr': 0.00045346688579797444, 'samples': 5992320, 'steps': 31209, 'loss/train': 0.8035076856613159} 08/30/2021 18:53:42 - INFO - __main__ - Step 31211: {'lr': 0.0004534638022659592, 'samples': 5992512, 'steps': 31210, 'loss/train': 1.509392499923706} 08/30/2021 18:53:43 - INFO - __main__ - Step 31212: {'lr': 0.00045346071864226634, 'samples': 5992704, 'steps': 31211, 'loss/train': 1.76493239402771} 08/30/2021 18:53:44 - INFO - __main__ - Step 31213: {'lr': 0.0004534576349268973, 'samples': 5992896, 'steps': 31212, 'loss/train': 1.8032407760620117} 08/30/2021 18:53:44 - INFO - __main__ - Step 31214: {'lr': 0.00045345455111985326, 'samples': 5993088, 'steps': 31213, 'loss/train': 1.8356369733810425} 08/30/2021 18:53:44 - INFO - __main__ - Step 31215: {'lr': 0.0004534514672211358, 'samples': 5993280, 'steps': 31214, 'loss/train': 1.2564467191696167} 08/30/2021 18:53:45 - INFO - __main__ - Step 31216: {'lr': 0.0004534483832307462, 'samples': 5993472, 'steps': 31215, 'loss/train': 1.5392696857452393} 08/30/2021 18:53:46 - INFO - __main__ - Step 31217: {'lr': 0.00045344529914868593, 'samples': 5993664, 'steps': 31216, 'loss/train': 1.8809454441070557} 08/30/2021 18:53:47 - INFO - __main__ - Step 31218: {'lr': 0.0004534422149749564, 'samples': 5993856, 'steps': 31217, 'loss/train': 1.578195333480835} 08/30/2021 18:53:47 - INFO - __main__ - Step 31219: {'lr': 0.0004534391307095589, 'samples': 5994048, 'steps': 31218, 'loss/train': 1.394371509552002} 08/30/2021 18:53:47 - INFO - __main__ - Step 31220: {'lr': 0.0004534360463524948, 'samples': 5994240, 'steps': 31219, 'loss/train': 0.3241921663284302} 08/30/2021 18:53:48 - INFO - __main__ - Step 31221: {'lr': 0.00045343296190376566, 'samples': 5994432, 'steps': 31220, 'loss/train': 1.0528323650360107} 08/30/2021 18:53:48 - INFO - __main__ - Step 31222: {'lr': 0.0004534298773633727, 'samples': 5994624, 'steps': 31221, 'loss/train': 1.6575772762298584} 08/30/2021 18:53:50 - INFO - __main__ - Step 31223: {'lr': 0.00045342679273131743, 'samples': 5994816, 'steps': 31222, 'loss/train': 1.2128381729125977} 08/30/2021 18:53:50 - INFO - __main__ - Step 31224: {'lr': 0.0004534237080076011, 'samples': 5995008, 'steps': 31223, 'loss/train': 1.5789028406143188} 08/30/2021 18:53:51 - INFO - __main__ - Step 31225: {'lr': 0.0004534206231922253, 'samples': 5995200, 'steps': 31224, 'loss/train': 1.637815237045288} 08/30/2021 18:53:51 - INFO - __main__ - Step 31226: {'lr': 0.0004534175382851913, 'samples': 5995392, 'steps': 31225, 'loss/train': 0.10047882050275803} 08/30/2021 18:53:52 - INFO - __main__ - Step 31227: {'lr': 0.0004534144532865004, 'samples': 5995584, 'steps': 31226, 'loss/train': 1.4280861616134644} 08/30/2021 18:53:53 - INFO - __main__ - Step 31228: {'lr': 0.00045341136819615415, 'samples': 5995776, 'steps': 31227, 'loss/train': 1.901550531387329} 08/30/2021 18:53:53 - INFO - __main__ - Step 31229: {'lr': 0.0004534082830141538, 'samples': 5995968, 'steps': 31228, 'loss/train': 1.124707818031311} 08/30/2021 18:53:54 - INFO - __main__ - Step 31230: {'lr': 0.00045340519774050093, 'samples': 5996160, 'steps': 31229, 'loss/train': 1.548142671585083} 08/30/2021 18:53:54 - INFO - __main__ - Step 31231: {'lr': 0.0004534021123751968, 'samples': 5996352, 'steps': 31230, 'loss/train': 1.187740683555603} 08/30/2021 18:53:54 - INFO - __main__ - Step 31232: {'lr': 0.00045339902691824275, 'samples': 5996544, 'steps': 31231, 'loss/train': 0.921841561794281} 08/30/2021 18:53:57 - INFO - __main__ - Step 31233: {'lr': 0.0004533959413696402, 'samples': 5996736, 'steps': 31232, 'loss/train': 1.111497163772583} 08/30/2021 18:53:57 - INFO - __main__ - Step 31234: {'lr': 0.0004533928557293907, 'samples': 5996928, 'steps': 31233, 'loss/train': 1.761494755744934} 08/30/2021 18:53:57 - INFO - __main__ - Step 31235: {'lr': 0.00045338976999749546, 'samples': 5997120, 'steps': 31234, 'loss/train': 5.979400157928467} 08/30/2021 18:53:58 - INFO - __main__ - Step 31236: {'lr': 0.00045338668417395595, 'samples': 5997312, 'steps': 31235, 'loss/train': 1.8501466512680054} 08/30/2021 18:53:58 - INFO - __main__ - Step 31237: {'lr': 0.0004533835982587735, 'samples': 5997504, 'steps': 31236, 'loss/train': 1.6291043758392334} 08/30/2021 18:54:00 - INFO - __main__ - Step 31238: {'lr': 0.00045338051225194954, 'samples': 5997696, 'steps': 31237, 'loss/train': 0.855450451374054} 08/30/2021 18:54:00 - INFO - __main__ - Step 31239: {'lr': 0.0004533774261534855, 'samples': 5997888, 'steps': 31238, 'loss/train': 1.2634632587432861} 08/30/2021 18:54:01 - INFO - __main__ - Step 31240: {'lr': 0.00045337433996338274, 'samples': 5998080, 'steps': 31239, 'loss/train': 1.4583642482757568} 08/30/2021 18:54:01 - INFO - __main__ - Step 31241: {'lr': 0.0004533712536816426, 'samples': 5998272, 'steps': 31240, 'loss/train': 1.8149352073669434} 08/30/2021 18:54:01 - INFO - __main__ - Step 31242: {'lr': 0.0004533681673082665, 'samples': 5998464, 'steps': 31241, 'loss/train': 1.7026433944702148} 08/30/2021 18:54:03 - INFO - __main__ - Step 31243: {'lr': 0.00045336508084325587, 'samples': 5998656, 'steps': 31242, 'loss/train': 1.615867018699646} 08/30/2021 18:54:04 - INFO - __main__ - Step 31244: {'lr': 0.0004533619942866121, 'samples': 5998848, 'steps': 31243, 'loss/train': 2.039458990097046} 08/30/2021 18:54:04 - INFO - __main__ - Step 31245: {'lr': 0.00045335890763833646, 'samples': 5999040, 'steps': 31244, 'loss/train': 1.0180801153182983} 08/30/2021 18:54:04 - INFO - __main__ - Step 31246: {'lr': 0.0004533558208984305, 'samples': 5999232, 'steps': 31245, 'loss/train': 0.043132055550813675} 08/30/2021 18:54:05 - INFO - __main__ - Step 31247: {'lr': 0.0004533527340668956, 'samples': 5999424, 'steps': 31246, 'loss/train': 1.7107980251312256} 08/30/2021 18:54:05 - INFO - __main__ - Step 31248: {'lr': 0.000453349647143733, 'samples': 5999616, 'steps': 31247, 'loss/train': 1.1968151330947876} 08/30/2021 18:54:07 - INFO - __main__ - Step 31249: {'lr': 0.00045334656012894424, 'samples': 5999808, 'steps': 31248, 'loss/train': 1.3520599603652954} 08/30/2021 18:54:07 - INFO - __main__ - Step 31250: {'lr': 0.00045334347302253064, 'samples': 6000000, 'steps': 31249, 'loss/train': 1.1168391704559326} 08/30/2021 18:54:07 - INFO - __main__ - Step 31251: {'lr': 0.00045334038582449355, 'samples': 6000192, 'steps': 31250, 'loss/train': 1.3352669477462769} 08/30/2021 18:54:08 - INFO - __main__ - Step 31252: {'lr': 0.0004533372985348345, 'samples': 6000384, 'steps': 31251, 'loss/train': 1.621696949005127} 08/30/2021 18:54:08 - INFO - __main__ - Step 31253: {'lr': 0.00045333421115355477, 'samples': 6000576, 'steps': 31252, 'loss/train': 1.339316487312317} 08/30/2021 18:54:08 - INFO - __main__ - Step 31254: {'lr': 0.00045333112368065585, 'samples': 6000768, 'steps': 31253, 'loss/train': 1.694393515586853} 08/30/2021 18:54:10 - INFO - __main__ - Step 31255: {'lr': 0.00045332803611613896, 'samples': 6000960, 'steps': 31254, 'loss/train': 0.0778266042470932} 08/30/2021 18:54:10 - INFO - __main__ - Step 31256: {'lr': 0.00045332494846000564, 'samples': 6001152, 'steps': 31255, 'loss/train': 1.0283511877059937} 08/30/2021 18:54:11 - INFO - __main__ - Step 31257: {'lr': 0.00045332186071225724, 'samples': 6001344, 'steps': 31256, 'loss/train': 1.4047452211380005} 08/30/2021 18:54:11 - INFO - __main__ - Step 31258: {'lr': 0.00045331877287289516, 'samples': 6001536, 'steps': 31257, 'loss/train': 1.6048741340637207} 08/30/2021 18:54:11 - INFO - __main__ - Step 31259: {'lr': 0.00045331568494192076, 'samples': 6001728, 'steps': 31258, 'loss/train': 0.8484418392181396} 08/30/2021 18:54:13 - INFO - __main__ - Step 31260: {'lr': 0.00045331259691933545, 'samples': 6001920, 'steps': 31259, 'loss/train': 6.402412414550781} 08/30/2021 18:54:13 - INFO - __main__ - Step 31261: {'lr': 0.00045330950880514065, 'samples': 6002112, 'steps': 31260, 'loss/train': 1.2930322885513306} 08/30/2021 18:54:14 - INFO - __main__ - Step 31262: {'lr': 0.0004533064205993377, 'samples': 6002304, 'steps': 31261, 'loss/train': 1.5986852645874023} 08/30/2021 18:54:14 - INFO - __main__ - Step 31263: {'lr': 0.000453303332301928, 'samples': 6002496, 'steps': 31262, 'loss/train': 1.3185456991195679} 08/30/2021 18:54:14 - INFO - __main__ - Step 31264: {'lr': 0.00045330024391291294, 'samples': 6002688, 'steps': 31263, 'loss/train': 1.3373768329620361} 08/30/2021 18:54:16 - INFO - __main__ - Step 31265: {'lr': 0.00045329715543229396, 'samples': 6002880, 'steps': 31264, 'loss/train': 1.2572249174118042} 08/30/2021 18:54:16 - INFO - __main__ - Step 31266: {'lr': 0.0004532940668600724, 'samples': 6003072, 'steps': 31265, 'loss/train': 1.8223615884780884} 08/30/2021 18:54:17 - INFO - __main__ - Step 31267: {'lr': 0.00045329097819624966, 'samples': 6003264, 'steps': 31266, 'loss/train': 1.4032493829727173} 08/30/2021 18:54:17 - INFO - __main__ - Step 31268: {'lr': 0.00045328788944082717, 'samples': 6003456, 'steps': 31267, 'loss/train': 1.6533368825912476} 08/30/2021 18:54:17 - INFO - __main__ - Step 31269: {'lr': 0.0004532848005938063, 'samples': 6003648, 'steps': 31268, 'loss/train': 1.693549394607544} 08/30/2021 18:54:19 - INFO - __main__ - Step 31270: {'lr': 0.0004532817116551884, 'samples': 6003840, 'steps': 31269, 'loss/train': 1.7190295457839966} 08/30/2021 18:54:20 - INFO - __main__ - Step 31271: {'lr': 0.00045327862262497495, 'samples': 6004032, 'steps': 31270, 'loss/train': 1.8468612432479858} 08/30/2021 18:54:20 - INFO - __main__ - Step 31272: {'lr': 0.00045327553350316726, 'samples': 6004224, 'steps': 31271, 'loss/train': 0.09141149371862411} 08/30/2021 18:54:20 - INFO - __main__ - Step 31273: {'lr': 0.00045327244428976677, 'samples': 6004416, 'steps': 31272, 'loss/train': 1.839314579963684} 08/30/2021 18:54:21 - INFO - __main__ - Step 31274: {'lr': 0.00045326935498477477, 'samples': 6004608, 'steps': 31273, 'loss/train': 1.3692504167556763} 08/30/2021 18:54:22 - INFO - __main__ - Step 31275: {'lr': 0.00045326626558819284, 'samples': 6004800, 'steps': 31274, 'loss/train': 1.6184078454971313} 08/30/2021 18:54:23 - INFO - __main__ - Step 31276: {'lr': 0.00045326317610002223, 'samples': 6004992, 'steps': 31275, 'loss/train': 1.3882378339767456} 08/30/2021 18:54:23 - INFO - __main__ - Step 31277: {'lr': 0.00045326008652026435, 'samples': 6005184, 'steps': 31276, 'loss/train': 1.4430707693099976} 08/30/2021 18:54:24 - INFO - __main__ - Step 31278: {'lr': 0.00045325699684892065, 'samples': 6005376, 'steps': 31277, 'loss/train': 1.4224860668182373} 08/30/2021 18:54:24 - INFO - __main__ - Step 31279: {'lr': 0.00045325390708599245, 'samples': 6005568, 'steps': 31278, 'loss/train': 1.0058977603912354} 08/30/2021 18:54:26 - INFO - __main__ - Step 31280: {'lr': 0.0004532508172314812, 'samples': 6005760, 'steps': 31279, 'loss/train': 1.684635043144226} 08/30/2021 18:54:26 - INFO - __main__ - Step 31281: {'lr': 0.0004532477272853882, 'samples': 6005952, 'steps': 31280, 'loss/train': 1.741889476776123} 08/30/2021 18:54:26 - INFO - __main__ - Step 31282: {'lr': 0.000453244637247715, 'samples': 6006144, 'steps': 31281, 'loss/train': 1.5113399028778076} 08/30/2021 18:54:27 - INFO - __main__ - Step 31283: {'lr': 0.0004532415471184629, 'samples': 6006336, 'steps': 31282, 'loss/train': 1.4530400037765503} 08/30/2021 18:54:27 - INFO - __main__ - Step 31284: {'lr': 0.0004532384568976332, 'samples': 6006528, 'steps': 31283, 'loss/train': 0.9999569654464722} 08/30/2021 18:54:27 - INFO - __main__ - Step 31285: {'lr': 0.00045323536658522747, 'samples': 6006720, 'steps': 31284, 'loss/train': 0.04194250330328941} 08/30/2021 18:54:29 - INFO - __main__ - Step 31286: {'lr': 0.00045323227618124695, 'samples': 6006912, 'steps': 31285, 'loss/train': 1.6435213088989258} 08/30/2021 18:54:30 - INFO - __main__ - Step 31287: {'lr': 0.00045322918568569315, 'samples': 6007104, 'steps': 31286, 'loss/train': 0.9105099439620972} 08/30/2021 18:54:30 - INFO - __main__ - Step 31288: {'lr': 0.0004532260950985675, 'samples': 6007296, 'steps': 31287, 'loss/train': 1.2265020608901978} 08/30/2021 18:54:31 - INFO - __main__ - Step 31289: {'lr': 0.0004532230044198712, 'samples': 6007488, 'steps': 31288, 'loss/train': 1.3852030038833618} 08/30/2021 18:54:31 - INFO - __main__ - Step 31290: {'lr': 0.00045321991364960577, 'samples': 6007680, 'steps': 31289, 'loss/train': 1.4569660425186157} 08/30/2021 18:54:33 - INFO - __main__ - Step 31291: {'lr': 0.00045321682278777253, 'samples': 6007872, 'steps': 31290, 'loss/train': 1.7157217264175415} 08/30/2021 18:54:33 - INFO - __main__ - Step 31292: {'lr': 0.00045321373183437305, 'samples': 6008064, 'steps': 31291, 'loss/train': 1.6974905729293823} 08/30/2021 18:54:34 - INFO - __main__ - Step 31293: {'lr': 0.0004532106407894085, 'samples': 6008256, 'steps': 31292, 'loss/train': 1.9059391021728516} 08/30/2021 18:54:34 - INFO - __main__ - Step 31294: {'lr': 0.0004532075496528804, 'samples': 6008448, 'steps': 31293, 'loss/train': 2.8428099155426025} 08/30/2021 18:54:34 - INFO - __main__ - Step 31295: {'lr': 0.0004532044584247901, 'samples': 6008640, 'steps': 31294, 'loss/train': 1.1328047513961792} 08/30/2021 18:54:36 - INFO - __main__ - Step 31296: {'lr': 0.00045320136710513907, 'samples': 6008832, 'steps': 31295, 'loss/train': 1.3786119222640991} 08/30/2021 18:54:36 - INFO - __main__ - Step 31297: {'lr': 0.00045319827569392855, 'samples': 6009024, 'steps': 31296, 'loss/train': 1.9237794876098633} 08/30/2021 18:54:37 - INFO - __main__ - Step 31298: {'lr': 0.00045319518419116014, 'samples': 6009216, 'steps': 31297, 'loss/train': 1.0042014122009277} 08/30/2021 18:54:37 - INFO - __main__ - Step 31299: {'lr': 0.00045319209259683503, 'samples': 6009408, 'steps': 31298, 'loss/train': 3.9404237270355225} 08/30/2021 18:54:37 - INFO - __main__ - Step 31300: {'lr': 0.0004531890009109547, 'samples': 6009600, 'steps': 31299, 'loss/train': 0.8712418079376221} 08/30/2021 18:54:38 - INFO - __main__ - Step 31301: {'lr': 0.0004531859091335205, 'samples': 6009792, 'steps': 31300, 'loss/train': 1.7124570608139038} 08/30/2021 18:54:39 - INFO - __main__ - Step 31302: {'lr': 0.00045318281726453393, 'samples': 6009984, 'steps': 31301, 'loss/train': 1.4082034826278687} 08/30/2021 18:54:40 - INFO - __main__ - Step 31303: {'lr': 0.00045317972530399634, 'samples': 6010176, 'steps': 31302, 'loss/train': 1.479798674583435} 08/30/2021 18:54:40 - INFO - __main__ - Step 31304: {'lr': 0.00045317663325190904, 'samples': 6010368, 'steps': 31303, 'loss/train': 0.6503819823265076} 08/30/2021 18:54:40 - INFO - __main__ - Step 31305: {'lr': 0.00045317354110827344, 'samples': 6010560, 'steps': 31304, 'loss/train': 1.4694414138793945} 08/30/2021 18:54:41 - INFO - __main__ - Step 31306: {'lr': 0.0004531704488730911, 'samples': 6010752, 'steps': 31305, 'loss/train': 1.2119567394256592} 08/30/2021 18:54:43 - INFO - __main__ - Step 31307: {'lr': 0.0004531673565463632, 'samples': 6010944, 'steps': 31306, 'loss/train': 1.1974531412124634} 08/30/2021 18:54:44 - INFO - __main__ - Step 31308: {'lr': 0.0004531642641280913, 'samples': 6011136, 'steps': 31307, 'loss/train': 2.1453826427459717} 08/30/2021 18:54:44 - INFO - __main__ - Step 31309: {'lr': 0.0004531611716182767, 'samples': 6011328, 'steps': 31308, 'loss/train': 1.3563406467437744} 08/30/2021 18:54:44 - INFO - __main__ - Step 31310: {'lr': 0.0004531580790169207, 'samples': 6011520, 'steps': 31309, 'loss/train': 1.5168622732162476} 08/30/2021 18:54:45 - INFO - __main__ - Step 31311: {'lr': 0.00045315498632402494, 'samples': 6011712, 'steps': 31310, 'loss/train': 1.71764075756073} 08/30/2021 18:54:45 - INFO - __main__ - Step 31312: {'lr': 0.0004531518935395906, 'samples': 6011904, 'steps': 31311, 'loss/train': 1.6577080488204956} 08/30/2021 18:54:45 - INFO - __main__ - Step 31313: {'lr': 0.00045314880066361923, 'samples': 6012096, 'steps': 31312, 'loss/train': 1.8008569478988647} 08/30/2021 18:54:47 - INFO - __main__ - Step 31314: {'lr': 0.00045314570769611207, 'samples': 6012288, 'steps': 31313, 'loss/train': 1.7289601564407349} 08/30/2021 18:54:47 - INFO - __main__ - Step 31315: {'lr': 0.00045314261463707064, 'samples': 6012480, 'steps': 31314, 'loss/train': 0.739951491355896} 08/30/2021 18:54:48 - INFO - __main__ - Step 31316: {'lr': 0.00045313952148649626, 'samples': 6012672, 'steps': 31315, 'loss/train': 1.1222769021987915} 08/30/2021 18:54:48 - INFO - __main__ - Step 31317: {'lr': 0.0004531364282443904, 'samples': 6012864, 'steps': 31316, 'loss/train': 1.603251338005066} 08/30/2021 18:54:48 - INFO - __main__ - Step 31318: {'lr': 0.00045313333491075433, 'samples': 6013056, 'steps': 31317, 'loss/train': 1.1627026796340942} 08/30/2021 18:54:50 - INFO - __main__ - Step 31319: {'lr': 0.0004531302414855895, 'samples': 6013248, 'steps': 31318, 'loss/train': 1.9969780445098877} 08/30/2021 18:54:50 - INFO - __main__ - Step 31320: {'lr': 0.0004531271479688974, 'samples': 6013440, 'steps': 31319, 'loss/train': 1.1127108335494995} 08/30/2021 18:54:51 - INFO - __main__ - Step 31321: {'lr': 0.00045312405436067927, 'samples': 6013632, 'steps': 31320, 'loss/train': 1.810063362121582} 08/30/2021 18:54:51 - INFO - __main__ - Step 31322: {'lr': 0.00045312096066093654, 'samples': 6013824, 'steps': 31321, 'loss/train': 1.625144600868225} 08/30/2021 18:54:52 - INFO - __main__ - Step 31323: {'lr': 0.0004531178668696707, 'samples': 6014016, 'steps': 31322, 'loss/train': 1.8409335613250732} 08/30/2021 18:54:53 - INFO - __main__ - Step 31324: {'lr': 0.00045311477298688306, 'samples': 6014208, 'steps': 31323, 'loss/train': 1.6044880151748657} 08/30/2021 18:54:54 - INFO - __main__ - Step 31325: {'lr': 0.0004531116790125751, 'samples': 6014400, 'steps': 31324, 'loss/train': 0.9908980131149292} 08/30/2021 18:54:54 - INFO - __main__ - Step 31326: {'lr': 0.00045310858494674813, 'samples': 6014592, 'steps': 31325, 'loss/train': 2.1294140815734863} 08/30/2021 18:54:54 - INFO - __main__ - Step 31327: {'lr': 0.00045310549078940356, 'samples': 6014784, 'steps': 31326, 'loss/train': 4.76400899887085} 08/30/2021 18:54:55 - INFO - __main__ - Step 31328: {'lr': 0.00045310239654054274, 'samples': 6014976, 'steps': 31327, 'loss/train': 1.372968077659607} 08/30/2021 18:54:55 - INFO - __main__ - Step 31329: {'lr': 0.0004530993022001672, 'samples': 6015168, 'steps': 31328, 'loss/train': 1.0646507740020752} 08/30/2021 18:54:57 - INFO - __main__ - Step 31330: {'lr': 0.00045309620776827817, 'samples': 6015360, 'steps': 31329, 'loss/train': 1.1996066570281982} 08/30/2021 18:54:57 - INFO - __main__ - Step 31331: {'lr': 0.00045309311324487713, 'samples': 6015552, 'steps': 31330, 'loss/train': 1.597009539604187} 08/30/2021 18:54:58 - INFO - __main__ - Step 31332: {'lr': 0.0004530900186299655, 'samples': 6015744, 'steps': 31331, 'loss/train': 1.5069334506988525} 08/30/2021 18:54:58 - INFO - __main__ - Step 31333: {'lr': 0.0004530869239235446, 'samples': 6015936, 'steps': 31332, 'loss/train': 1.3375705480575562} 08/30/2021 18:54:58 - INFO - __main__ - Step 31334: {'lr': 0.0004530838291256159, 'samples': 6016128, 'steps': 31333, 'loss/train': 1.0631095170974731} 08/30/2021 18:55:00 - INFO - __main__ - Step 31335: {'lr': 0.0004530807342361807, 'samples': 6016320, 'steps': 31334, 'loss/train': 0.0816582441329956} 08/30/2021 18:55:00 - INFO - __main__ - Step 31336: {'lr': 0.0004530776392552406, 'samples': 6016512, 'steps': 31335, 'loss/train': 1.9605308771133423} 08/30/2021 18:55:00 - INFO - __main__ - Step 31337: {'lr': 0.0004530745441827967, 'samples': 6016704, 'steps': 31336, 'loss/train': 2.09440016746521} 08/30/2021 18:55:01 - INFO - __main__ - Step 31338: {'lr': 0.0004530714490188506, 'samples': 6016896, 'steps': 31337, 'loss/train': 1.6025139093399048} 08/30/2021 18:55:01 - INFO - __main__ - Step 31339: {'lr': 0.00045306835376340366, 'samples': 6017088, 'steps': 31338, 'loss/train': 1.575194001197815} 08/30/2021 18:55:03 - INFO - __main__ - Step 31340: {'lr': 0.00045306525841645723, 'samples': 6017280, 'steps': 31339, 'loss/train': 1.8693315982818604} 08/30/2021 18:55:04 - INFO - __main__ - Step 31341: {'lr': 0.0004530621629780127, 'samples': 6017472, 'steps': 31340, 'loss/train': 0.5270640254020691} 08/30/2021 18:55:04 - INFO - __main__ - Step 31342: {'lr': 0.00045305906744807156, 'samples': 6017664, 'steps': 31341, 'loss/train': 1.7819008827209473} 08/30/2021 18:55:05 - INFO - __main__ - Step 31343: {'lr': 0.0004530559718266351, 'samples': 6017856, 'steps': 31342, 'loss/train': 1.6175544261932373} 08/30/2021 18:55:05 - INFO - __main__ - Step 31344: {'lr': 0.0004530528761137047, 'samples': 6018048, 'steps': 31343, 'loss/train': 1.6291863918304443} 08/30/2021 18:55:06 - INFO - __main__ - Step 31345: {'lr': 0.0004530497803092819, 'samples': 6018240, 'steps': 31344, 'loss/train': 0.08060912042856216} 08/30/2021 18:55:07 - INFO - __main__ - Step 31346: {'lr': 0.000453046684413368, 'samples': 6018432, 'steps': 31345, 'loss/train': 0.9258426427841187} 08/30/2021 18:55:07 - INFO - __main__ - Step 31347: {'lr': 0.0004530435884259644, 'samples': 6018624, 'steps': 31346, 'loss/train': 1.0339792966842651} 08/30/2021 18:55:07 - INFO - __main__ - Step 31348: {'lr': 0.0004530404923470724, 'samples': 6018816, 'steps': 31347, 'loss/train': 1.7208458185195923} 08/30/2021 18:55:08 - INFO - __main__ - Step 31349: {'lr': 0.0004530373961766935, 'samples': 6019008, 'steps': 31348, 'loss/train': 1.387402892112732} 08/30/2021 18:55:09 - INFO - __main__ - Step 31350: {'lr': 0.00045303429991482914, 'samples': 6019200, 'steps': 31349, 'loss/train': 2.0206618309020996} 08/30/2021 18:55:10 - INFO - __main__ - Step 31351: {'lr': 0.00045303120356148067, 'samples': 6019392, 'steps': 31350, 'loss/train': 1.4462023973464966} 08/30/2021 18:55:10 - INFO - __main__ - Step 31352: {'lr': 0.00045302810711664944, 'samples': 6019584, 'steps': 31351, 'loss/train': 1.499739408493042} 08/30/2021 18:55:10 - INFO - __main__ - Step 31353: {'lr': 0.00045302501058033687, 'samples': 6019776, 'steps': 31352, 'loss/train': 2.4195618629455566} 08/30/2021 18:55:11 - INFO - __main__ - Step 31354: {'lr': 0.0004530219139525444, 'samples': 6019968, 'steps': 31353, 'loss/train': 1.561851978302002} 08/30/2021 18:55:12 - INFO - __main__ - Step 31355: {'lr': 0.0004530188172332733, 'samples': 6020160, 'steps': 31354, 'loss/train': 1.1478394269943237} 08/30/2021 18:55:13 - INFO - __main__ - Step 31356: {'lr': 0.00045301572042252516, 'samples': 6020352, 'steps': 31355, 'loss/train': 1.4215891361236572} 08/30/2021 18:55:13 - INFO - __main__ - Step 31357: {'lr': 0.00045301262352030123, 'samples': 6020544, 'steps': 31356, 'loss/train': 1.1591626405715942} 08/30/2021 18:55:13 - INFO - __main__ - Step 31358: {'lr': 0.00045300952652660296, 'samples': 6020736, 'steps': 31357, 'loss/train': 1.556175708770752} 08/30/2021 18:55:14 - INFO - __main__ - Step 31359: {'lr': 0.0004530064294414317, 'samples': 6020928, 'steps': 31358, 'loss/train': 1.4957365989685059} 08/30/2021 18:55:15 - INFO - __main__ - Step 31360: {'lr': 0.00045300333226478887, 'samples': 6021120, 'steps': 31359, 'loss/train': 1.3405539989471436} 08/30/2021 18:55:16 - INFO - __main__ - Step 31361: {'lr': 0.0004530002349966759, 'samples': 6021312, 'steps': 31360, 'loss/train': 2.0852339267730713} 08/30/2021 18:55:16 - INFO - __main__ - Step 31362: {'lr': 0.0004529971376370941, 'samples': 6021504, 'steps': 31361, 'loss/train': 2.0898191928863525} 08/30/2021 18:55:17 - INFO - __main__ - Step 31363: {'lr': 0.00045299404018604494, 'samples': 6021696, 'steps': 31362, 'loss/train': 1.0498466491699219} 08/30/2021 18:55:17 - INFO - __main__ - Step 31364: {'lr': 0.00045299094264352987, 'samples': 6021888, 'steps': 31363, 'loss/train': 1.621506929397583} 08/30/2021 18:55:17 - INFO - __main__ - Step 31365: {'lr': 0.00045298784500955014, 'samples': 6022080, 'steps': 31364, 'loss/train': 0.7947888374328613} 08/30/2021 18:55:19 - INFO - __main__ - Step 31366: {'lr': 0.0004529847472841073, 'samples': 6022272, 'steps': 31365, 'loss/train': 0.6868574619293213} 08/30/2021 18:55:19 - INFO - __main__ - Step 31367: {'lr': 0.00045298164946720254, 'samples': 6022464, 'steps': 31366, 'loss/train': 1.34158194065094} 08/30/2021 18:55:20 - INFO - __main__ - Step 31368: {'lr': 0.0004529785515588375, 'samples': 6022656, 'steps': 31367, 'loss/train': 3.5043113231658936} 08/30/2021 18:55:20 - INFO - __main__ - Step 31369: {'lr': 0.00045297545355901336, 'samples': 6022848, 'steps': 31368, 'loss/train': 2.601215124130249} 08/30/2021 18:55:20 - INFO - __main__ - Step 31370: {'lr': 0.00045297235546773175, 'samples': 6023040, 'steps': 31369, 'loss/train': 1.8250067234039307} 08/30/2021 18:55:22 - INFO - __main__ - Step 31371: {'lr': 0.0004529692572849938, 'samples': 6023232, 'steps': 31370, 'loss/train': 1.4554429054260254} 08/30/2021 18:55:22 - INFO - __main__ - Step 31372: {'lr': 0.00045296615901080107, 'samples': 6023424, 'steps': 31371, 'loss/train': 2.171494960784912} 08/30/2021 18:55:23 - INFO - __main__ - Step 31373: {'lr': 0.00045296306064515493, 'samples': 6023616, 'steps': 31372, 'loss/train': 0.9765689373016357} 08/30/2021 18:55:23 - INFO - __main__ - Step 31374: {'lr': 0.0004529599621880567, 'samples': 6023808, 'steps': 31373, 'loss/train': 0.9462294578552246} 08/30/2021 18:55:23 - INFO - __main__ - Step 31375: {'lr': 0.00045295686363950796, 'samples': 6024000, 'steps': 31374, 'loss/train': 1.7525094747543335} 08/30/2021 18:55:24 - INFO - __main__ - Step 31376: {'lr': 0.0004529537649995099, 'samples': 6024192, 'steps': 31375, 'loss/train': 1.6631157398223877} 08/30/2021 18:55:25 - INFO - __main__ - Step 31377: {'lr': 0.0004529506662680641, 'samples': 6024384, 'steps': 31376, 'loss/train': 1.1652833223342896} 08/30/2021 18:55:26 - INFO - __main__ - Step 31378: {'lr': 0.00045294756744517173, 'samples': 6024576, 'steps': 31377, 'loss/train': 1.4136176109313965} 08/30/2021 18:55:26 - INFO - __main__ - Step 31379: {'lr': 0.00045294446853083446, 'samples': 6024768, 'steps': 31378, 'loss/train': 0.5691795945167542} 08/30/2021 18:55:26 - INFO - __main__ - Step 31380: {'lr': 0.00045294136952505346, 'samples': 6024960, 'steps': 31379, 'loss/train': 1.966015338897705} 08/30/2021 18:55:27 - INFO - __main__ - Step 31381: {'lr': 0.0004529382704278302, 'samples': 6025152, 'steps': 31380, 'loss/train': 1.1273294687271118} 08/30/2021 18:55:29 - INFO - __main__ - Step 31382: {'lr': 0.0004529351712391661, 'samples': 6025344, 'steps': 31381, 'loss/train': 1.627261757850647} 08/30/2021 18:55:29 - INFO - __main__ - Step 31383: {'lr': 0.0004529320719590626, 'samples': 6025536, 'steps': 31382, 'loss/train': 1.3488986492156982} 08/30/2021 18:55:30 - INFO - __main__ - Step 31384: {'lr': 0.00045292897258752095, 'samples': 6025728, 'steps': 31383, 'loss/train': 0.031087197363376617} 08/30/2021 18:55:30 - INFO - __main__ - Step 31385: {'lr': 0.0004529258731245427, 'samples': 6025920, 'steps': 31384, 'loss/train': 1.359673023223877} 08/30/2021 18:55:30 - INFO - __main__ - Step 31386: {'lr': 0.0004529227735701291, 'samples': 6026112, 'steps': 31385, 'loss/train': 1.7532901763916016} 08/30/2021 18:55:31 - INFO - __main__ - Step 31387: {'lr': 0.00045291967392428175, 'samples': 6026304, 'steps': 31386, 'loss/train': 1.397007942199707} 08/30/2021 18:55:32 - INFO - __main__ - Step 31388: {'lr': 0.0004529165741870018, 'samples': 6026496, 'steps': 31387, 'loss/train': 2.2244186401367188} 08/30/2021 18:55:32 - INFO - __main__ - Step 31389: {'lr': 0.00045291347435829087, 'samples': 6026688, 'steps': 31388, 'loss/train': 1.6940562725067139} 08/30/2021 18:55:33 - INFO - __main__ - Step 31390: {'lr': 0.0004529103744381503, 'samples': 6026880, 'steps': 31389, 'loss/train': 1.3574824333190918} 08/30/2021 18:55:33 - INFO - __main__ - Step 31391: {'lr': 0.0004529072744265813, 'samples': 6027072, 'steps': 31390, 'loss/train': 0.9527828693389893} 08/30/2021 18:55:34 - INFO - __main__ - Step 31392: {'lr': 0.00045290417432358553, 'samples': 6027264, 'steps': 31391, 'loss/train': 1.5479423999786377} 08/30/2021 18:55:35 - INFO - __main__ - Step 31393: {'lr': 0.00045290107412916425, 'samples': 6027456, 'steps': 31392, 'loss/train': 1.2887177467346191} 08/30/2021 18:55:36 - INFO - __main__ - Step 31394: {'lr': 0.0004528979738433189, 'samples': 6027648, 'steps': 31393, 'loss/train': 1.2290927171707153} 08/30/2021 18:55:36 - INFO - __main__ - Step 31395: {'lr': 0.00045289487346605075, 'samples': 6027840, 'steps': 31394, 'loss/train': 1.4486130475997925} 08/30/2021 18:55:37 - INFO - __main__ - Step 31396: {'lr': 0.0004528917729973614, 'samples': 6028032, 'steps': 31395, 'loss/train': 2.506225824356079} 08/30/2021 18:55:37 - INFO - __main__ - Step 31397: {'lr': 0.00045288867243725207, 'samples': 6028224, 'steps': 31396, 'loss/train': 1.55485999584198} 08/30/2021 18:55:39 - INFO - __main__ - Step 31398: {'lr': 0.00045288557178572433, 'samples': 6028416, 'steps': 31397, 'loss/train': 1.430517315864563} 08/30/2021 18:55:39 - INFO - __main__ - Step 31399: {'lr': 0.00045288247104277937, 'samples': 6028608, 'steps': 31398, 'loss/train': 1.623408317565918} 08/30/2021 18:55:39 - INFO - __main__ - Step 31400: {'lr': 0.0004528793702084187, 'samples': 6028800, 'steps': 31399, 'loss/train': 1.3323373794555664} 08/30/2021 18:55:40 - INFO - __main__ - Step 31401: {'lr': 0.0004528762692826439, 'samples': 6028992, 'steps': 31400, 'loss/train': 2.479332208633423} 08/30/2021 18:55:40 - INFO - __main__ - Step 31402: {'lr': 0.000452873168265456, 'samples': 6029184, 'steps': 31401, 'loss/train': 1.2642860412597656} 08/30/2021 18:55:42 - INFO - __main__ - Step 31403: {'lr': 0.00045287006715685665, 'samples': 6029376, 'steps': 31402, 'loss/train': 0.9872164726257324} 08/30/2021 18:55:42 - INFO - __main__ - Step 31404: {'lr': 0.0004528669659568472, 'samples': 6029568, 'steps': 31403, 'loss/train': 0.9204387068748474} 08/30/2021 18:55:42 - INFO - __main__ - Step 31405: {'lr': 0.00045286386466542896, 'samples': 6029760, 'steps': 31404, 'loss/train': 1.208727240562439} 08/30/2021 18:55:43 - INFO - __main__ - Step 31406: {'lr': 0.0004528607632826034, 'samples': 6029952, 'steps': 31405, 'loss/train': 0.7143217325210571} 08/30/2021 18:55:43 - INFO - __main__ - Step 31407: {'lr': 0.00045285766180837197, 'samples': 6030144, 'steps': 31406, 'loss/train': 1.926500916481018} 08/30/2021 18:55:45 - INFO - __main__ - Step 31408: {'lr': 0.000452854560242736, 'samples': 6030336, 'steps': 31407, 'loss/train': 1.125378966331482} 08/30/2021 18:55:45 - INFO - __main__ - Step 31409: {'lr': 0.0004528514585856968, 'samples': 6030528, 'steps': 31408, 'loss/train': 1.475826621055603} 08/30/2021 18:55:46 - INFO - __main__ - Step 31410: {'lr': 0.0004528483568372559, 'samples': 6030720, 'steps': 31409, 'loss/train': 1.1945854425430298} 08/30/2021 18:55:46 - INFO - __main__ - Step 31411: {'lr': 0.00045284525499741474, 'samples': 6030912, 'steps': 31410, 'loss/train': 1.4862995147705078} 08/30/2021 18:55:46 - INFO - __main__ - Step 31412: {'lr': 0.0004528421530661746, 'samples': 6031104, 'steps': 31411, 'loss/train': 1.360161542892456} 08/30/2021 18:55:47 - INFO - __main__ - Step 31413: {'lr': 0.0004528390510435368, 'samples': 6031296, 'steps': 31412, 'loss/train': 2.8024587631225586} 08/30/2021 18:55:48 - INFO - __main__ - Step 31414: {'lr': 0.0004528359489295031, 'samples': 6031488, 'steps': 31413, 'loss/train': 1.5121667385101318} 08/30/2021 18:55:49 - INFO - __main__ - Step 31415: {'lr': 0.00045283284672407444, 'samples': 6031680, 'steps': 31414, 'loss/train': 1.7138633728027344} 08/30/2021 18:55:49 - INFO - __main__ - Step 31416: {'lr': 0.0004528297444272525, 'samples': 6031872, 'steps': 31415, 'loss/train': 1.478971004486084} 08/30/2021 18:55:49 - INFO - __main__ - Step 31417: {'lr': 0.0004528266420390386, 'samples': 6032064, 'steps': 31416, 'loss/train': 1.2854008674621582} 08/30/2021 18:55:50 - INFO - __main__ - Step 31418: {'lr': 0.00045282353955943417, 'samples': 6032256, 'steps': 31417, 'loss/train': 1.2074687480926514} 08/30/2021 18:55:51 - INFO - __main__ - Step 31419: {'lr': 0.00045282043698844054, 'samples': 6032448, 'steps': 31418, 'loss/train': 1.638526439666748} 08/30/2021 18:55:52 - INFO - __main__ - Step 31420: {'lr': 0.0004528173343260592, 'samples': 6032640, 'steps': 31419, 'loss/train': 0.10108483582735062} 08/30/2021 18:55:52 - INFO - __main__ - Step 31421: {'lr': 0.0004528142315722915, 'samples': 6032832, 'steps': 31420, 'loss/train': 1.5083378553390503} 08/30/2021 18:55:52 - INFO - __main__ - Step 31422: {'lr': 0.0004528111287271388, 'samples': 6033024, 'steps': 31421, 'loss/train': 1.3909136056900024} 08/30/2021 18:55:53 - INFO - __main__ - Step 31423: {'lr': 0.00045280802579060253, 'samples': 6033216, 'steps': 31422, 'loss/train': 0.7654160857200623} 08/30/2021 18:55:55 - INFO - __main__ - Step 31424: {'lr': 0.00045280492276268414, 'samples': 6033408, 'steps': 31423, 'loss/train': 1.332148551940918} 08/30/2021 18:55:55 - INFO - __main__ - Step 31425: {'lr': 0.0004528018196433849, 'samples': 6033600, 'steps': 31424, 'loss/train': 1.2332581281661987} 08/30/2021 18:55:55 - INFO - __main__ - Step 31426: {'lr': 0.0004527987164327063, 'samples': 6033792, 'steps': 31425, 'loss/train': 0.6418870091438293} 08/30/2021 18:55:56 - INFO - __main__ - Step 31427: {'lr': 0.0004527956131306498, 'samples': 6033984, 'steps': 31426, 'loss/train': 0.9826205372810364} 08/30/2021 18:55:56 - INFO - __main__ - Step 31428: {'lr': 0.0004527925097372168, 'samples': 6034176, 'steps': 31427, 'loss/train': 1.4369760751724243} 08/30/2021 18:55:56 - INFO - __main__ - Step 31429: {'lr': 0.0004527894062524084, 'samples': 6034368, 'steps': 31428, 'loss/train': 1.886527180671692} 08/30/2021 18:55:58 - INFO - __main__ - Step 31430: {'lr': 0.00045278630267622637, 'samples': 6034560, 'steps': 31429, 'loss/train': 1.3181524276733398} 08/30/2021 18:55:58 - INFO - __main__ - Step 31431: {'lr': 0.0004527831990086719, 'samples': 6034752, 'steps': 31430, 'loss/train': 1.613345742225647} 08/30/2021 18:55:59 - INFO - __main__ - Step 31432: {'lr': 0.0004527800952497465, 'samples': 6034944, 'steps': 31431, 'loss/train': 1.1999479532241821} 08/30/2021 18:55:59 - INFO - __main__ - Step 31433: {'lr': 0.0004527769913994515, 'samples': 6035136, 'steps': 31432, 'loss/train': 0.2586987614631653} 08/30/2021 18:55:59 - INFO - __main__ - Step 31434: {'lr': 0.00045277388745778836, 'samples': 6035328, 'steps': 31433, 'loss/train': 1.6988682746887207} 08/30/2021 18:56:01 - INFO - __main__ - Step 31435: {'lr': 0.00045277078342475835, 'samples': 6035520, 'steps': 31434, 'loss/train': 1.606391191482544} 08/30/2021 18:56:01 - INFO - __main__ - Step 31436: {'lr': 0.000452767679300363, 'samples': 6035712, 'steps': 31435, 'loss/train': 1.1598868370056152} 08/30/2021 18:56:02 - INFO - __main__ - Step 31437: {'lr': 0.00045276457508460367, 'samples': 6035904, 'steps': 31436, 'loss/train': 1.789568543434143} 08/30/2021 18:56:02 - INFO - __main__ - Step 31438: {'lr': 0.00045276147077748176, 'samples': 6036096, 'steps': 31437, 'loss/train': 1.4439555406570435} 08/30/2021 18:56:02 - INFO - __main__ - Step 31439: {'lr': 0.0004527583663789986, 'samples': 6036288, 'steps': 31438, 'loss/train': 1.4716142416000366} 08/30/2021 18:56:04 - INFO - __main__ - Step 31440: {'lr': 0.0004527552618891557, 'samples': 6036480, 'steps': 31439, 'loss/train': 1.370036244392395} 08/30/2021 18:56:04 - INFO - __main__ - Step 31441: {'lr': 0.0004527521573079544, 'samples': 6036672, 'steps': 31440, 'loss/train': 1.1786279678344727} 08/30/2021 18:56:05 - INFO - __main__ - Step 31442: {'lr': 0.0004527490526353961, 'samples': 6036864, 'steps': 31441, 'loss/train': 1.855455994606018} 08/30/2021 18:56:05 - INFO - __main__ - Step 31443: {'lr': 0.0004527459478714822, 'samples': 6037056, 'steps': 31442, 'loss/train': 0.9614437818527222} 08/30/2021 18:56:05 - INFO - __main__ - Step 31444: {'lr': 0.00045274284301621414, 'samples': 6037248, 'steps': 31443, 'loss/train': 1.296837568283081} 08/30/2021 18:56:07 - INFO - __main__ - Step 31445: {'lr': 0.00045273973806959325, 'samples': 6037440, 'steps': 31444, 'loss/train': 0.8728410005569458} 08/30/2021 18:56:07 - INFO - __main__ - Step 31446: {'lr': 0.00045273663303162096, 'samples': 6037632, 'steps': 31445, 'loss/train': 1.9406379461288452} 08/30/2021 18:56:08 - INFO - __main__ - Step 31447: {'lr': 0.00045273352790229873, 'samples': 6037824, 'steps': 31446, 'loss/train': 1.4328932762145996} 08/30/2021 18:56:08 - INFO - __main__ - Step 31448: {'lr': 0.0004527304226816278, 'samples': 6038016, 'steps': 31447, 'loss/train': 1.1640315055847168} 08/30/2021 18:56:08 - INFO - __main__ - Step 31449: {'lr': 0.0004527273173696097, 'samples': 6038208, 'steps': 31448, 'loss/train': 1.3157843351364136} 08/30/2021 18:56:10 - INFO - __main__ - Step 31450: {'lr': 0.0004527242119662458, 'samples': 6038400, 'steps': 31449, 'loss/train': 1.4977264404296875} 08/30/2021 18:56:11 - INFO - __main__ - Step 31451: {'lr': 0.00045272110647153754, 'samples': 6038592, 'steps': 31450, 'loss/train': 1.9133837223052979} 08/30/2021 18:56:11 - INFO - __main__ - Step 31452: {'lr': 0.00045271800088548625, 'samples': 6038784, 'steps': 31451, 'loss/train': 1.0430338382720947} 08/30/2021 18:56:12 - INFO - __main__ - Step 31453: {'lr': 0.00045271489520809337, 'samples': 6038976, 'steps': 31452, 'loss/train': 0.23288923501968384} 08/30/2021 18:56:12 - INFO - __main__ - Step 31454: {'lr': 0.0004527117894393603, 'samples': 6039168, 'steps': 31453, 'loss/train': 1.496104121208191} 08/30/2021 18:56:12 - INFO - __main__ - Step 31455: {'lr': 0.0004527086835792884, 'samples': 6039360, 'steps': 31454, 'loss/train': 1.5991955995559692} 08/30/2021 18:56:14 - INFO - __main__ - Step 31456: {'lr': 0.0004527055776278791, 'samples': 6039552, 'steps': 31455, 'loss/train': 2.231074094772339} 08/30/2021 18:56:14 - INFO - __main__ - Step 31457: {'lr': 0.00045270247158513377, 'samples': 6039744, 'steps': 31456, 'loss/train': 1.1377114057540894} 08/30/2021 18:56:15 - INFO - __main__ - Step 31458: {'lr': 0.00045269936545105384, 'samples': 6039936, 'steps': 31457, 'loss/train': 1.273699164390564} 08/30/2021 18:56:15 - INFO - __main__ - Step 31459: {'lr': 0.0004526962592256407, 'samples': 6040128, 'steps': 31458, 'loss/train': 1.3193888664245605} 08/30/2021 18:56:15 - INFO - __main__ - Step 31460: {'lr': 0.00045269315290889583, 'samples': 6040320, 'steps': 31459, 'loss/train': 1.9876859188079834} 08/30/2021 18:56:17 - INFO - __main__ - Step 31461: {'lr': 0.00045269004650082045, 'samples': 6040512, 'steps': 31460, 'loss/train': 1.8289393186569214} 08/30/2021 18:56:17 - INFO - __main__ - Step 31462: {'lr': 0.0004526869400014162, 'samples': 6040704, 'steps': 31461, 'loss/train': 1.0538196563720703} 08/30/2021 18:56:18 - INFO - __main__ - Step 31463: {'lr': 0.0004526838334106842, 'samples': 6040896, 'steps': 31462, 'loss/train': 2.3195483684539795} 08/30/2021 18:56:18 - INFO - __main__ - Step 31464: {'lr': 0.000452680726728626, 'samples': 6041088, 'steps': 31463, 'loss/train': 1.1052652597427368} 08/30/2021 18:56:18 - INFO - __main__ - Step 31465: {'lr': 0.00045267761995524314, 'samples': 6041280, 'steps': 31464, 'loss/train': 1.0972288846969604} 08/30/2021 18:56:20 - INFO - __main__ - Step 31466: {'lr': 0.00045267451309053677, 'samples': 6041472, 'steps': 31465, 'loss/train': 1.22018563747406} 08/30/2021 18:56:21 - INFO - __main__ - Step 31467: {'lr': 0.0004526714061345084, 'samples': 6041664, 'steps': 31466, 'loss/train': 1.823421835899353} 08/30/2021 18:56:21 - INFO - __main__ - Step 31468: {'lr': 0.0004526682990871593, 'samples': 6041856, 'steps': 31467, 'loss/train': 1.3162624835968018} 08/30/2021 18:56:21 - INFO - __main__ - Step 31469: {'lr': 0.0004526651919484912, 'samples': 6042048, 'steps': 31468, 'loss/train': 1.4950264692306519} 08/30/2021 18:56:22 - INFO - __main__ - Step 31470: {'lr': 0.00045266208471850516, 'samples': 6042240, 'steps': 31469, 'loss/train': 1.1708528995513916} 08/30/2021 18:56:23 - INFO - __main__ - Step 31471: {'lr': 0.00045265897739720277, 'samples': 6042432, 'steps': 31470, 'loss/train': 1.3910452127456665} 08/30/2021 18:56:24 - INFO - __main__ - Step 31472: {'lr': 0.00045265586998458534, 'samples': 6042624, 'steps': 31471, 'loss/train': 1.279205322265625} 08/30/2021 18:56:24 - INFO - __main__ - Step 31473: {'lr': 0.00045265276248065436, 'samples': 6042816, 'steps': 31472, 'loss/train': 1.2575830221176147} 08/30/2021 18:56:24 - INFO - __main__ - Step 31474: {'lr': 0.0004526496548854111, 'samples': 6043008, 'steps': 31473, 'loss/train': 1.222016453742981} 08/30/2021 18:56:25 - INFO - __main__ - Step 31475: {'lr': 0.000452646547198857, 'samples': 6043200, 'steps': 31474, 'loss/train': 1.686367392539978} 08/30/2021 18:56:25 - INFO - __main__ - Step 31476: {'lr': 0.0004526434394209936, 'samples': 6043392, 'steps': 31475, 'loss/train': 1.1926203966140747} 08/30/2021 18:56:27 - INFO - __main__ - Step 31477: {'lr': 0.00045264033155182216, 'samples': 6043584, 'steps': 31476, 'loss/train': 1.3968989849090576} 08/30/2021 18:56:27 - INFO - __main__ - Step 31478: {'lr': 0.0004526372235913441, 'samples': 6043776, 'steps': 31477, 'loss/train': 0.8984674215316772} 08/30/2021 18:56:27 - INFO - __main__ - Step 31479: {'lr': 0.0004526341155395608, 'samples': 6043968, 'steps': 31478, 'loss/train': 1.6023017168045044} 08/30/2021 18:56:28 - INFO - __main__ - Step 31480: {'lr': 0.00045263100739647373, 'samples': 6044160, 'steps': 31479, 'loss/train': 1.2159675359725952} 08/30/2021 18:56:28 - INFO - __main__ - Step 31481: {'lr': 0.00045262789916208424, 'samples': 6044352, 'steps': 31480, 'loss/train': 0.6490748524665833} 08/30/2021 18:56:30 - INFO - __main__ - Step 31482: {'lr': 0.00045262479083639376, 'samples': 6044544, 'steps': 31481, 'loss/train': 0.8157838582992554} 08/30/2021 18:56:30 - INFO - __main__ - Step 31483: {'lr': 0.0004526216824194037, 'samples': 6044736, 'steps': 31482, 'loss/train': 2.0911879539489746} 08/30/2021 18:56:30 - INFO - __main__ - Step 31484: {'lr': 0.00045261857391111536, 'samples': 6044928, 'steps': 31483, 'loss/train': 1.2063584327697754} 08/30/2021 18:56:31 - INFO - __main__ - Step 31485: {'lr': 0.0004526154653115303, 'samples': 6045120, 'steps': 31484, 'loss/train': 1.706596851348877} 08/30/2021 18:56:31 - INFO - __main__ - Step 31486: {'lr': 0.0004526123566206498, 'samples': 6045312, 'steps': 31485, 'loss/train': 0.9205894470214844} 08/30/2021 18:56:33 - INFO - __main__ - Step 31487: {'lr': 0.0004526092478384753, 'samples': 6045504, 'steps': 31486, 'loss/train': 1.7218198776245117} 08/30/2021 18:56:33 - INFO - __main__ - Step 31488: {'lr': 0.00045260613896500827, 'samples': 6045696, 'steps': 31487, 'loss/train': 1.2149503231048584} 08/30/2021 18:56:33 - INFO - __main__ - Step 31489: {'lr': 0.00045260303000024994, 'samples': 6045888, 'steps': 31488, 'loss/train': 1.7236899137496948} 08/30/2021 18:56:34 - INFO - __main__ - Step 31490: {'lr': 0.0004525999209442018, 'samples': 6046080, 'steps': 31489, 'loss/train': 1.7597769498825073} 08/30/2021 18:56:34 - INFO - __main__ - Step 31491: {'lr': 0.0004525968117968653, 'samples': 6046272, 'steps': 31490, 'loss/train': 0.8732706308364868} 08/30/2021 18:56:34 - INFO - __main__ - Step 31492: {'lr': 0.00045259370255824183, 'samples': 6046464, 'steps': 31491, 'loss/train': 5.7229084968566895} 08/30/2021 18:56:36 - INFO - __main__ - Step 31493: {'lr': 0.0004525905932283327, 'samples': 6046656, 'steps': 31492, 'loss/train': 1.1895314455032349} 08/30/2021 18:56:37 - INFO - __main__ - Step 31494: {'lr': 0.00045258748380713943, 'samples': 6046848, 'steps': 31493, 'loss/train': 1.7025678157806396} 08/30/2021 18:56:37 - INFO - __main__ - Step 31495: {'lr': 0.00045258437429466337, 'samples': 6047040, 'steps': 31494, 'loss/train': 1.4857701063156128} 08/30/2021 18:56:37 - INFO - __main__ - Step 31496: {'lr': 0.0004525812646909059, 'samples': 6047232, 'steps': 31495, 'loss/train': 0.993442952632904} 08/30/2021 18:56:38 - INFO - __main__ - Step 31497: {'lr': 0.0004525781549958684, 'samples': 6047424, 'steps': 31496, 'loss/train': 1.1009951829910278} 08/30/2021 18:56:39 - INFO - __main__ - Step 31498: {'lr': 0.0004525750452095524, 'samples': 6047616, 'steps': 31497, 'loss/train': 1.534775972366333} 08/30/2021 18:56:40 - INFO - __main__ - Step 31499: {'lr': 0.00045257193533195916, 'samples': 6047808, 'steps': 31498, 'loss/train': 1.2641210556030273} 08/30/2021 18:56:40 - INFO - __main__ - Step 31500: {'lr': 0.0004525688253630901, 'samples': 6048000, 'steps': 31499, 'loss/train': 1.6611754894256592} 08/30/2021 18:56:40 - INFO - __main__ - Step 31501: {'lr': 0.00045256571530294664, 'samples': 6048192, 'steps': 31500, 'loss/train': 1.4023146629333496} 08/30/2021 18:56:41 - INFO - __main__ - Step 31502: {'lr': 0.0004525626051515302, 'samples': 6048384, 'steps': 31501, 'loss/train': 1.5561954975128174} 08/30/2021 18:56:42 - INFO - __main__ - Step 31503: {'lr': 0.0004525594949088423, 'samples': 6048576, 'steps': 31502, 'loss/train': 2.238656520843506} 08/30/2021 18:56:43 - INFO - __main__ - Step 31504: {'lr': 0.00045255638457488415, 'samples': 6048768, 'steps': 31503, 'loss/train': 0.05404098704457283} 08/30/2021 18:56:43 - INFO - __main__ - Step 31505: {'lr': 0.0004525532741496572, 'samples': 6048960, 'steps': 31504, 'loss/train': 1.7800315618515015} 08/30/2021 18:56:43 - INFO - __main__ - Step 31506: {'lr': 0.0004525501636331628, 'samples': 6049152, 'steps': 31505, 'loss/train': 1.8348767757415771} 08/30/2021 18:56:44 - INFO - __main__ - Step 31507: {'lr': 0.00045254705302540257, 'samples': 6049344, 'steps': 31506, 'loss/train': 1.6852188110351562} 08/30/2021 18:56:46 - INFO - __main__ - Step 31508: {'lr': 0.00045254394232637765, 'samples': 6049536, 'steps': 31507, 'loss/train': 1.7218661308288574} 08/30/2021 18:56:46 - INFO - __main__ - Step 31509: {'lr': 0.0004525408315360896, 'samples': 6049728, 'steps': 31508, 'loss/train': 1.3552794456481934} 08/30/2021 18:56:47 - INFO - __main__ - Step 31510: {'lr': 0.00045253772065453977, 'samples': 6049920, 'steps': 31509, 'loss/train': 1.0921895503997803} 08/30/2021 18:56:47 - INFO - __main__ - Step 31511: {'lr': 0.00045253460968172957, 'samples': 6050112, 'steps': 31510, 'loss/train': 1.7306175231933594} 08/30/2021 18:56:47 - INFO - __main__ - Step 31512: {'lr': 0.0004525314986176604, 'samples': 6050304, 'steps': 31511, 'loss/train': 0.8179535865783691} 08/30/2021 18:56:49 - INFO - __main__ - Step 31513: {'lr': 0.0004525283874623336, 'samples': 6050496, 'steps': 31512, 'loss/train': 1.351931095123291} 08/30/2021 18:56:50 - INFO - __main__ - Step 31514: {'lr': 0.00045252527621575075, 'samples': 6050688, 'steps': 31513, 'loss/train': 1.6400539875030518} 08/30/2021 18:56:50 - INFO - __main__ - Step 31515: {'lr': 0.0004525221648779131, 'samples': 6050880, 'steps': 31514, 'loss/train': 1.9648393392562866} 08/30/2021 18:56:50 - INFO - __main__ - Step 31516: {'lr': 0.00045251905344882205, 'samples': 6051072, 'steps': 31515, 'loss/train': 1.9522805213928223} 08/30/2021 18:56:51 - INFO - __main__ - Step 31517: {'lr': 0.000452515941928479, 'samples': 6051264, 'steps': 31516, 'loss/train': 1.3978352546691895} 08/30/2021 18:56:51 - INFO - __main__ - Step 31518: {'lr': 0.0004525128303168855, 'samples': 6051456, 'steps': 31517, 'loss/train': 1.381455421447754} 08/30/2021 18:56:52 - INFO - __main__ - Step 31519: {'lr': 0.00045250971861404276, 'samples': 6051648, 'steps': 31518, 'loss/train': 1.6752939224243164} 08/30/2021 18:56:53 - INFO - __main__ - Step 31520: {'lr': 0.0004525066068199523, 'samples': 6051840, 'steps': 31519, 'loss/train': 1.2719836235046387} 08/30/2021 18:56:53 - INFO - __main__ - Step 31521: {'lr': 0.0004525034949346155, 'samples': 6052032, 'steps': 31520, 'loss/train': 1.4441601037979126} 08/30/2021 18:56:54 - INFO - __main__ - Step 31522: {'lr': 0.0004525003829580337, 'samples': 6052224, 'steps': 31521, 'loss/train': 2.3608810901641846} 08/30/2021 18:56:54 - INFO - __main__ - Step 31523: {'lr': 0.0004524972708902084, 'samples': 6052416, 'steps': 31522, 'loss/train': 1.4365335702896118} 08/30/2021 18:56:56 - INFO - __main__ - Step 31524: {'lr': 0.0004524941587311409, 'samples': 6052608, 'steps': 31523, 'loss/train': 1.589581847190857} 08/30/2021 18:56:56 - INFO - __main__ - Step 31525: {'lr': 0.0004524910464808327, 'samples': 6052800, 'steps': 31524, 'loss/train': 1.5015918016433716} 08/30/2021 18:56:56 - INFO - __main__ - Step 31526: {'lr': 0.00045248793413928514, 'samples': 6052992, 'steps': 31525, 'loss/train': 1.3970669507980347} 08/30/2021 18:56:57 - INFO - __main__ - Step 31527: {'lr': 0.0004524848217064997, 'samples': 6053184, 'steps': 31526, 'loss/train': 1.0029394626617432} 08/30/2021 18:56:57 - INFO - __main__ - Step 31528: {'lr': 0.0004524817091824777, 'samples': 6053376, 'steps': 31527, 'loss/train': 1.034461259841919} 08/30/2021 18:56:59 - INFO - __main__ - Step 31529: {'lr': 0.00045247859656722056, 'samples': 6053568, 'steps': 31528, 'loss/train': 1.2880207300186157} 08/30/2021 18:56:59 - INFO - __main__ - Step 31530: {'lr': 0.0004524754838607297, 'samples': 6053760, 'steps': 31529, 'loss/train': 1.7482061386108398} 08/30/2021 18:56:59 - INFO - __main__ - Step 31531: {'lr': 0.0004524723710630064, 'samples': 6053952, 'steps': 31530, 'loss/train': 1.3517693281173706} 08/30/2021 18:57:00 - INFO - __main__ - Step 31532: {'lr': 0.0004524692581740523, 'samples': 6054144, 'steps': 31531, 'loss/train': 1.4645726680755615} 08/30/2021 18:57:00 - INFO - __main__ - Step 31533: {'lr': 0.00045246614519386865, 'samples': 6054336, 'steps': 31532, 'loss/train': 1.362823247909546} 08/30/2021 18:57:02 - INFO - __main__ - Step 31534: {'lr': 0.0004524630321224569, 'samples': 6054528, 'steps': 31533, 'loss/train': 1.1384767293930054} 08/30/2021 18:57:02 - INFO - __main__ - Step 31535: {'lr': 0.0004524599189598183, 'samples': 6054720, 'steps': 31534, 'loss/train': 1.7595208883285522} 08/30/2021 18:57:03 - INFO - __main__ - Step 31536: {'lr': 0.0004524568057059545, 'samples': 6054912, 'steps': 31535, 'loss/train': 1.2609013319015503} 08/30/2021 18:57:03 - INFO - __main__ - Step 31537: {'lr': 0.00045245369236086673, 'samples': 6055104, 'steps': 31536, 'loss/train': 1.063708782196045} 08/30/2021 18:57:03 - INFO - __main__ - Step 31538: {'lr': 0.00045245057892455653, 'samples': 6055296, 'steps': 31537, 'loss/train': 1.398468255996704} 08/30/2021 18:57:05 - INFO - __main__ - Step 31539: {'lr': 0.0004524474653970252, 'samples': 6055488, 'steps': 31538, 'loss/train': 1.3290035724639893} 08/30/2021 18:57:05 - INFO - __main__ - Step 31540: {'lr': 0.00045244435177827413, 'samples': 6055680, 'steps': 31539, 'loss/train': 0.9209257960319519} 08/30/2021 18:57:06 - INFO - __main__ - Step 31541: {'lr': 0.00045244123806830486, 'samples': 6055872, 'steps': 31540, 'loss/train': 2.057265520095825} 08/30/2021 18:57:06 - INFO - __main__ - Step 31542: {'lr': 0.00045243812426711856, 'samples': 6056064, 'steps': 31541, 'loss/train': 1.5249072313308716} 08/30/2021 18:57:06 - INFO - __main__ - Step 31543: {'lr': 0.0004524350103747168, 'samples': 6056256, 'steps': 31542, 'loss/train': 1.7326353788375854} 08/30/2021 18:57:07 - INFO - __main__ - Step 31544: {'lr': 0.00045243189639110093, 'samples': 6056448, 'steps': 31543, 'loss/train': 1.630940318107605} 08/30/2021 18:57:09 - INFO - __main__ - Step 31545: {'lr': 0.00045242878231627247, 'samples': 6056640, 'steps': 31544, 'loss/train': 1.7212327718734741} 08/30/2021 18:57:09 - INFO - __main__ - Step 31546: {'lr': 0.0004524256681502327, 'samples': 6056832, 'steps': 31545, 'loss/train': 1.0421826839447021} 08/30/2021 18:57:10 - INFO - __main__ - Step 31547: {'lr': 0.0004524225538929829, 'samples': 6057024, 'steps': 31546, 'loss/train': 1.0967950820922852} 08/30/2021 18:57:10 - INFO - __main__ - Step 31548: {'lr': 0.0004524194395445248, 'samples': 6057216, 'steps': 31547, 'loss/train': 1.576261281967163} 08/30/2021 18:57:10 - INFO - __main__ - Step 31549: {'lr': 0.0004524163251048595, 'samples': 6057408, 'steps': 31548, 'loss/train': 1.1451524496078491} 08/30/2021 18:57:11 - INFO - __main__ - Step 31550: {'lr': 0.0004524132105739886, 'samples': 6057600, 'steps': 31549, 'loss/train': 0.09778346121311188} 08/30/2021 18:57:12 - INFO - __main__ - Step 31551: {'lr': 0.0004524100959519134, 'samples': 6057792, 'steps': 31550, 'loss/train': 0.08346326649188995} 08/30/2021 18:57:13 - INFO - __main__ - Step 31552: {'lr': 0.00045240698123863535, 'samples': 6057984, 'steps': 31551, 'loss/train': 2.0149972438812256} 08/30/2021 18:57:13 - INFO - __main__ - Step 31553: {'lr': 0.0004524038664341558, 'samples': 6058176, 'steps': 31552, 'loss/train': 1.7667441368103027} 08/30/2021 18:57:13 - INFO - __main__ - Step 31554: {'lr': 0.00045240075153847625, 'samples': 6058368, 'steps': 31553, 'loss/train': 1.8250231742858887} 08/30/2021 18:57:14 - INFO - __main__ - Step 31555: {'lr': 0.00045239763655159805, 'samples': 6058560, 'steps': 31554, 'loss/train': 1.6269919872283936} 08/30/2021 18:57:15 - INFO - __main__ - Step 31556: {'lr': 0.00045239452147352257, 'samples': 6058752, 'steps': 31555, 'loss/train': 1.7754318714141846} 08/30/2021 18:57:16 - INFO - __main__ - Step 31557: {'lr': 0.0004523914063042512, 'samples': 6058944, 'steps': 31556, 'loss/train': 1.6464051008224487} 08/30/2021 18:57:16 - INFO - __main__ - Step 31558: {'lr': 0.00045238829104378545, 'samples': 6059136, 'steps': 31557, 'loss/train': 2.1267404556274414} 08/30/2021 18:57:16 - INFO - __main__ - Step 31559: {'lr': 0.0004523851756921266, 'samples': 6059328, 'steps': 31558, 'loss/train': 1.0851868391036987} 08/30/2021 18:57:17 - INFO - __main__ - Step 31560: {'lr': 0.00045238206024927614, 'samples': 6059520, 'steps': 31559, 'loss/train': 1.1838688850402832} 08/30/2021 18:57:19 - INFO - __main__ - Step 31561: {'lr': 0.00045237894471523543, 'samples': 6059712, 'steps': 31560, 'loss/train': 1.5186291933059692} 08/30/2021 18:57:20 - INFO - __main__ - Step 31562: {'lr': 0.00045237582909000594, 'samples': 6059904, 'steps': 31561, 'loss/train': 1.5224990844726562} 08/30/2021 18:57:20 - INFO - __main__ - Step 31563: {'lr': 0.00045237271337358897, 'samples': 6060096, 'steps': 31562, 'loss/train': 0.7331939935684204} 08/30/2021 18:57:20 - INFO - __main__ - Step 31564: {'lr': 0.00045236959756598605, 'samples': 6060288, 'steps': 31563, 'loss/train': 1.7170697450637817} 08/30/2021 18:57:21 - INFO - __main__ - Step 31565: {'lr': 0.0004523664816671985, 'samples': 6060480, 'steps': 31564, 'loss/train': 1.411661982536316} 08/30/2021 18:57:22 - INFO - __main__ - Step 31566: {'lr': 0.0004523633656772277, 'samples': 6060672, 'steps': 31565, 'loss/train': 1.6969722509384155} 08/30/2021 18:57:23 - INFO - __main__ - Step 31567: {'lr': 0.00045236024959607505, 'samples': 6060864, 'steps': 31566, 'loss/train': 1.627051591873169} 08/30/2021 18:57:23 - INFO - __main__ - Step 31568: {'lr': 0.00045235713342374207, 'samples': 6061056, 'steps': 31567, 'loss/train': 1.966498851776123} 08/30/2021 18:57:23 - INFO - __main__ - Step 31569: {'lr': 0.00045235401716023, 'samples': 6061248, 'steps': 31568, 'loss/train': 1.27817702293396} 08/30/2021 18:57:24 - INFO - __main__ - Step 31570: {'lr': 0.0004523509008055404, 'samples': 6061440, 'steps': 31569, 'loss/train': 0.9885744452476501} 08/30/2021 18:57:24 - INFO - __main__ - Step 31571: {'lr': 0.0004523477843596746, 'samples': 6061632, 'steps': 31570, 'loss/train': 1.8031383752822876} 08/30/2021 18:57:26 - INFO - __main__ - Step 31572: {'lr': 0.00045234466782263403, 'samples': 6061824, 'steps': 31571, 'loss/train': 1.3130309581756592} 08/30/2021 18:57:26 - INFO - __main__ - Step 31573: {'lr': 0.00045234155119442, 'samples': 6062016, 'steps': 31572, 'loss/train': 1.1655257940292358} 08/30/2021 18:57:26 - INFO - __main__ - Step 31574: {'lr': 0.00045233843447503407, 'samples': 6062208, 'steps': 31573, 'loss/train': 1.9268194437026978} 08/30/2021 18:57:27 - INFO - __main__ - Step 31575: {'lr': 0.00045233531766447757, 'samples': 6062400, 'steps': 31574, 'loss/train': 1.5363763570785522} 08/30/2021 18:57:27 - INFO - __main__ - Step 31576: {'lr': 0.00045233220076275186, 'samples': 6062592, 'steps': 31575, 'loss/train': 1.273422122001648} 08/30/2021 18:57:29 - INFO - __main__ - Step 31577: {'lr': 0.0004523290837698583, 'samples': 6062784, 'steps': 31576, 'loss/train': 1.2363674640655518} 08/30/2021 18:57:29 - INFO - __main__ - Step 31578: {'lr': 0.0004523259666857985, 'samples': 6062976, 'steps': 31577, 'loss/train': 2.001171827316284} 08/30/2021 18:57:29 - INFO - __main__ - Step 31579: {'lr': 0.00045232284951057366, 'samples': 6063168, 'steps': 31578, 'loss/train': 2.232010841369629} 08/30/2021 18:57:30 - INFO - __main__ - Step 31580: {'lr': 0.00045231973224418533, 'samples': 6063360, 'steps': 31579, 'loss/train': 1.2469266653060913} 08/30/2021 18:57:30 - INFO - __main__ - Step 31581: {'lr': 0.00045231661488663485, 'samples': 6063552, 'steps': 31580, 'loss/train': 1.5800751447677612} 08/30/2021 18:57:32 - INFO - __main__ - Step 31582: {'lr': 0.0004523134974379236, 'samples': 6063744, 'steps': 31581, 'loss/train': 1.8041555881500244} 08/30/2021 18:57:32 - INFO - __main__ - Step 31583: {'lr': 0.000452310379898053, 'samples': 6063936, 'steps': 31582, 'loss/train': 1.0503699779510498} 08/30/2021 18:57:32 - INFO - __main__ - Step 31584: {'lr': 0.00045230726226702444, 'samples': 6064128, 'steps': 31583, 'loss/train': 1.2031890153884888} 08/30/2021 18:57:33 - INFO - __main__ - Step 31585: {'lr': 0.0004523041445448394, 'samples': 6064320, 'steps': 31584, 'loss/train': 1.5853074789047241} 08/30/2021 18:57:33 - INFO - __main__ - Step 31586: {'lr': 0.00045230102673149923, 'samples': 6064512, 'steps': 31585, 'loss/train': 1.3289752006530762} 08/30/2021 18:57:35 - INFO - __main__ - Step 31587: {'lr': 0.00045229790882700535, 'samples': 6064704, 'steps': 31586, 'loss/train': 0.9187049269676208} 08/30/2021 18:57:35 - INFO - __main__ - Step 31588: {'lr': 0.00045229479083135917, 'samples': 6064896, 'steps': 31587, 'loss/train': 1.7024964094161987} 08/30/2021 18:57:35 - INFO - __main__ - Step 31589: {'lr': 0.000452291672744562, 'samples': 6065088, 'steps': 31588, 'loss/train': 1.8442749977111816} 08/30/2021 18:57:36 - INFO - __main__ - Step 31590: {'lr': 0.0004522885545666153, 'samples': 6065280, 'steps': 31589, 'loss/train': 0.8489173054695129} 08/30/2021 18:57:36 - INFO - __main__ - Step 31591: {'lr': 0.0004522854362975206, 'samples': 6065472, 'steps': 31590, 'loss/train': 1.4772372245788574} 08/30/2021 18:57:38 - INFO - __main__ - Step 31592: {'lr': 0.00045228231793727924, 'samples': 6065664, 'steps': 31591, 'loss/train': 1.51474928855896} 08/30/2021 18:57:39 - INFO - __main__ - Step 31593: {'lr': 0.00045227919948589247, 'samples': 6065856, 'steps': 31592, 'loss/train': 1.716181755065918} 08/30/2021 18:57:39 - INFO - __main__ - Step 31594: {'lr': 0.0004522760809433619, 'samples': 6066048, 'steps': 31593, 'loss/train': 0.03369634971022606} 08/30/2021 18:57:39 - INFO - __main__ - Step 31595: {'lr': 0.0004522729623096888, 'samples': 6066240, 'steps': 31594, 'loss/train': 0.9508997201919556} 08/30/2021 18:57:40 - INFO - __main__ - Step 31596: {'lr': 0.0004522698435848747, 'samples': 6066432, 'steps': 31595, 'loss/train': 1.5020116567611694} 08/30/2021 18:57:40 - INFO - __main__ - Step 31597: {'lr': 0.0004522667247689208, 'samples': 6066624, 'steps': 31596, 'loss/train': 1.4500706195831299} 08/30/2021 18:57:40 - INFO - __main__ - Step 31598: {'lr': 0.0004522636058618287, 'samples': 6066816, 'steps': 31597, 'loss/train': 1.1037218570709229} 08/30/2021 18:57:42 - INFO - __main__ - Step 31599: {'lr': 0.0004522604868635998, 'samples': 6067008, 'steps': 31598, 'loss/train': 1.8208473920822144} 08/30/2021 18:57:42 - INFO - __main__ - Step 31600: {'lr': 0.0004522573677742353, 'samples': 6067200, 'steps': 31599, 'loss/train': 1.5743062496185303} 08/30/2021 18:57:43 - INFO - __main__ - Step 31601: {'lr': 0.0004522542485937369, 'samples': 6067392, 'steps': 31600, 'loss/train': 0.9678654074668884} 08/30/2021 18:57:43 - INFO - __main__ - Step 31602: {'lr': 0.0004522511293221058, 'samples': 6067584, 'steps': 31601, 'loss/train': 1.4245835542678833} 08/30/2021 18:57:43 - INFO - __main__ - Step 31603: {'lr': 0.00045224800995934345, 'samples': 6067776, 'steps': 31602, 'loss/train': 1.0812561511993408} 08/30/2021 18:57:45 - INFO - __main__ - Step 31604: {'lr': 0.00045224489050545125, 'samples': 6067968, 'steps': 31603, 'loss/train': 1.6551666259765625} 08/30/2021 18:57:46 - INFO - __main__ - Step 31605: {'lr': 0.0004522417709604306, 'samples': 6068160, 'steps': 31604, 'loss/train': 1.3745955228805542} 08/30/2021 18:57:46 - INFO - __main__ - Step 31606: {'lr': 0.000452238651324283, 'samples': 6068352, 'steps': 31605, 'loss/train': 1.4644901752471924} 08/30/2021 18:57:46 - INFO - __main__ - Step 31607: {'lr': 0.0004522355315970098, 'samples': 6068544, 'steps': 31606, 'loss/train': 0.9497048258781433} 08/30/2021 18:57:47 - INFO - __main__ - Step 31608: {'lr': 0.0004522324117786123, 'samples': 6068736, 'steps': 31607, 'loss/train': 1.3428709506988525} 08/30/2021 18:57:48 - INFO - __main__ - Step 31609: {'lr': 0.0004522292918690921, 'samples': 6068928, 'steps': 31608, 'loss/train': 1.5631051063537598} 08/30/2021 18:57:49 - INFO - __main__ - Step 31610: {'lr': 0.0004522261718684504, 'samples': 6069120, 'steps': 31609, 'loss/train': 1.394026279449463} 08/30/2021 18:57:49 - INFO - __main__ - Step 31611: {'lr': 0.00045222305177668875, 'samples': 6069312, 'steps': 31610, 'loss/train': 1.3956263065338135} 08/30/2021 18:57:49 - INFO - __main__ - Step 31612: {'lr': 0.00045221993159380857, 'samples': 6069504, 'steps': 31611, 'loss/train': 1.617452621459961} 08/30/2021 18:57:50 - INFO - __main__ - Step 31613: {'lr': 0.00045221681131981116, 'samples': 6069696, 'steps': 31612, 'loss/train': 1.3847172260284424} 08/30/2021 18:57:52 - INFO - __main__ - Step 31614: {'lr': 0.00045221369095469795, 'samples': 6069888, 'steps': 31613, 'loss/train': 1.5455043315887451} 08/30/2021 18:57:52 - INFO - __main__ - Step 31615: {'lr': 0.00045221057049847044, 'samples': 6070080, 'steps': 31614, 'loss/train': 0.05985480174422264} 08/30/2021 18:57:53 - INFO - __main__ - Step 31616: {'lr': 0.0004522074499511299, 'samples': 6070272, 'steps': 31615, 'loss/train': 1.373349666595459} 08/30/2021 18:57:53 - INFO - __main__ - Step 31617: {'lr': 0.0004522043293126778, 'samples': 6070464, 'steps': 31616, 'loss/train': 1.349117398262024} 08/30/2021 18:57:53 - INFO - __main__ - Step 31618: {'lr': 0.00045220120858311557, 'samples': 6070656, 'steps': 31617, 'loss/train': 1.4376928806304932} 08/30/2021 18:57:55 - INFO - __main__ - Step 31619: {'lr': 0.0004521980877624446, 'samples': 6070848, 'steps': 31618, 'loss/train': 2.031606912612915} 08/30/2021 18:57:56 - INFO - __main__ - Step 31620: {'lr': 0.0004521949668506663, 'samples': 6071040, 'steps': 31619, 'loss/train': 0.059158165007829666} 08/30/2021 18:57:56 - INFO - __main__ - Step 31621: {'lr': 0.00045219184584778207, 'samples': 6071232, 'steps': 31620, 'loss/train': 1.1033680438995361} 08/30/2021 18:57:57 - INFO - __main__ - Step 31622: {'lr': 0.0004521887247537933, 'samples': 6071424, 'steps': 31621, 'loss/train': 1.3772066831588745} 08/30/2021 18:57:57 - INFO - __main__ - Step 31623: {'lr': 0.00045218560356870144, 'samples': 6071616, 'steps': 31622, 'loss/train': 1.6896253824234009} 08/30/2021 18:57:57 - INFO - __main__ - Step 31624: {'lr': 0.0004521824822925078, 'samples': 6071808, 'steps': 31623, 'loss/train': 0.02434605173766613} 08/30/2021 18:57:59 - INFO - __main__ - Step 31625: {'lr': 0.00045217936092521396, 'samples': 6072000, 'steps': 31624, 'loss/train': 1.350623607635498} 08/30/2021 18:57:59 - INFO - __main__ - Step 31626: {'lr': 0.00045217623946682114, 'samples': 6072192, 'steps': 31625, 'loss/train': 1.9136111736297607} 08/30/2021 18:58:00 - INFO - __main__ - Step 31627: {'lr': 0.00045217311791733084, 'samples': 6072384, 'steps': 31626, 'loss/train': 1.8074136972427368} 08/30/2021 18:58:00 - INFO - __main__ - Step 31628: {'lr': 0.00045216999627674436, 'samples': 6072576, 'steps': 31627, 'loss/train': 1.3274154663085938} 08/30/2021 18:58:00 - INFO - __main__ - Step 31629: {'lr': 0.0004521668745450633, 'samples': 6072768, 'steps': 31628, 'loss/train': 1.2185918092727661} 08/30/2021 18:58:02 - INFO - __main__ - Step 31630: {'lr': 0.00045216375272228907, 'samples': 6072960, 'steps': 31629, 'loss/train': 1.561006784439087} 08/30/2021 18:58:03 - INFO - __main__ - Step 31631: {'lr': 0.00045216063080842287, 'samples': 6073152, 'steps': 31630, 'loss/train': 0.7294368743896484} 08/30/2021 18:58:03 - INFO - __main__ - Step 31632: {'lr': 0.00045215750880346617, 'samples': 6073344, 'steps': 31631, 'loss/train': 1.4684414863586426} 08/30/2021 18:58:03 - INFO - __main__ - Step 31633: {'lr': 0.00045215438670742045, 'samples': 6073536, 'steps': 31632, 'loss/train': 2.2386507987976074} 08/30/2021 18:58:04 - INFO - __main__ - Step 31634: {'lr': 0.00045215126452028705, 'samples': 6073728, 'steps': 31633, 'loss/train': 1.715134859085083} 08/30/2021 18:58:05 - INFO - __main__ - Step 31635: {'lr': 0.00045214814224206744, 'samples': 6073920, 'steps': 31634, 'loss/train': 1.5047531127929688} 08/30/2021 18:58:06 - INFO - __main__ - Step 31636: {'lr': 0.00045214501987276304, 'samples': 6074112, 'steps': 31635, 'loss/train': 1.7091227769851685} 08/30/2021 18:58:06 - INFO - __main__ - Step 31637: {'lr': 0.0004521418974123751, 'samples': 6074304, 'steps': 31636, 'loss/train': 1.8161869049072266} 08/30/2021 18:58:06 - INFO - __main__ - Step 31638: {'lr': 0.00045213877486090524, 'samples': 6074496, 'steps': 31637, 'loss/train': 1.9217665195465088} 08/30/2021 18:58:07 - INFO - __main__ - Step 31639: {'lr': 0.00045213565221835473, 'samples': 6074688, 'steps': 31638, 'loss/train': 1.0621533393859863} 08/30/2021 18:58:08 - INFO - __main__ - Step 31640: {'lr': 0.00045213252948472505, 'samples': 6074880, 'steps': 31639, 'loss/train': 1.606001853942871} 08/30/2021 18:58:09 - INFO - __main__ - Step 31641: {'lr': 0.0004521294066600175, 'samples': 6075072, 'steps': 31640, 'loss/train': 0.17081789672374725} 08/30/2021 18:58:09 - INFO - __main__ - Step 31642: {'lr': 0.0004521262837442336, 'samples': 6075264, 'steps': 31641, 'loss/train': 1.6975547075271606} 08/30/2021 18:58:09 - INFO - __main__ - Step 31643: {'lr': 0.0004521231607373747, 'samples': 6075456, 'steps': 31642, 'loss/train': 1.6854227781295776} 08/30/2021 18:58:10 - INFO - __main__ - Step 31644: {'lr': 0.00045212003763944226, 'samples': 6075648, 'steps': 31643, 'loss/train': 0.9941006302833557} 08/30/2021 18:58:11 - INFO - __main__ - Step 31645: {'lr': 0.00045211691445043765, 'samples': 6075840, 'steps': 31644, 'loss/train': 1.147262692451477} 08/30/2021 18:58:12 - INFO - __main__ - Step 31646: {'lr': 0.0004521137911703622, 'samples': 6076032, 'steps': 31645, 'loss/train': 1.5758424997329712} 08/30/2021 18:58:12 - INFO - __main__ - Step 31647: {'lr': 0.0004521106677992175, 'samples': 6076224, 'steps': 31646, 'loss/train': 1.4871608018875122} 08/30/2021 18:58:12 - INFO - __main__ - Step 31648: {'lr': 0.0004521075443370048, 'samples': 6076416, 'steps': 31647, 'loss/train': 1.315496563911438} 08/30/2021 18:58:13 - INFO - __main__ - Step 31649: {'lr': 0.0004521044207837256, 'samples': 6076608, 'steps': 31648, 'loss/train': 1.3405646085739136} 08/30/2021 18:58:13 - INFO - __main__ - Step 31650: {'lr': 0.0004521012971393812, 'samples': 6076800, 'steps': 31649, 'loss/train': 1.6827404499053955} 08/30/2021 18:58:14 - INFO - __main__ - Step 31651: {'lr': 0.0004520981734039731, 'samples': 6076992, 'steps': 31650, 'loss/train': 1.050052523612976} 08/30/2021 18:58:15 - INFO - __main__ - Step 31652: {'lr': 0.0004520950495775027, 'samples': 6077184, 'steps': 31651, 'loss/train': 0.9302839636802673} 08/30/2021 18:58:15 - INFO - __main__ - Step 31653: {'lr': 0.00045209192565997137, 'samples': 6077376, 'steps': 31652, 'loss/train': 1.246191382408142} 08/30/2021 18:58:16 - INFO - __main__ - Step 31654: {'lr': 0.00045208880165138054, 'samples': 6077568, 'steps': 31653, 'loss/train': 1.934869408607483} 08/30/2021 18:58:16 - INFO - __main__ - Step 31655: {'lr': 0.0004520856775517316, 'samples': 6077760, 'steps': 31654, 'loss/train': 1.8992890119552612} 08/30/2021 18:58:17 - INFO - __main__ - Step 31656: {'lr': 0.00045208255336102597, 'samples': 6077952, 'steps': 31655, 'loss/train': 1.8047153949737549} 08/30/2021 18:58:18 - INFO - __main__ - Step 31657: {'lr': 0.0004520794290792651, 'samples': 6078144, 'steps': 31656, 'loss/train': 2.0793232917785645} 08/30/2021 18:58:18 - INFO - __main__ - Step 31658: {'lr': 0.0004520763047064503, 'samples': 6078336, 'steps': 31657, 'loss/train': 1.329634189605713} 08/30/2021 18:58:19 - INFO - __main__ - Step 31659: {'lr': 0.0004520731802425831, 'samples': 6078528, 'steps': 31658, 'loss/train': 2.406625270843506} 08/30/2021 18:58:19 - INFO - __main__ - Step 31660: {'lr': 0.0004520700556876648, 'samples': 6078720, 'steps': 31659, 'loss/train': 1.5261276960372925} 08/30/2021 18:58:21 - INFO - __main__ - Step 31661: {'lr': 0.0004520669310416969, 'samples': 6078912, 'steps': 31660, 'loss/train': 1.557644248008728} 08/30/2021 18:58:21 - INFO - __main__ - Step 31662: {'lr': 0.0004520638063046807, 'samples': 6079104, 'steps': 31661, 'loss/train': 0.18460960686206818} 08/30/2021 18:58:22 - INFO - __main__ - Step 31663: {'lr': 0.0004520606814766177, 'samples': 6079296, 'steps': 31662, 'loss/train': 1.4834038019180298} 08/30/2021 18:58:22 - INFO - __main__ - Step 31664: {'lr': 0.00045205755655750924, 'samples': 6079488, 'steps': 31663, 'loss/train': 1.5257419347763062} 08/30/2021 18:58:22 - INFO - __main__ - Step 31665: {'lr': 0.0004520544315473568, 'samples': 6079680, 'steps': 31664, 'loss/train': 1.2246757745742798} 08/30/2021 18:58:24 - INFO - __main__ - Step 31666: {'lr': 0.00045205130644616177, 'samples': 6079872, 'steps': 31665, 'loss/train': 1.3707243204116821} 08/30/2021 18:58:24 - INFO - __main__ - Step 31667: {'lr': 0.0004520481812539255, 'samples': 6080064, 'steps': 31666, 'loss/train': 1.2511168718338013} 08/30/2021 18:58:25 - INFO - __main__ - Step 31668: {'lr': 0.00045204505597064943, 'samples': 6080256, 'steps': 31667, 'loss/train': 1.4564611911773682} 08/30/2021 18:58:25 - INFO - __main__ - Step 31669: {'lr': 0.00045204193059633505, 'samples': 6080448, 'steps': 31668, 'loss/train': 1.3521690368652344} 08/30/2021 18:58:25 - INFO - __main__ - Step 31670: {'lr': 0.0004520388051309836, 'samples': 6080640, 'steps': 31669, 'loss/train': 1.8957232236862183} 08/30/2021 18:58:27 - INFO - __main__ - Step 31671: {'lr': 0.00045203567957459657, 'samples': 6080832, 'steps': 31670, 'loss/train': 1.3604124784469604} 08/30/2021 18:58:28 - INFO - __main__ - Step 31672: {'lr': 0.00045203255392717545, 'samples': 6081024, 'steps': 31671, 'loss/train': 1.3457673788070679} 08/30/2021 18:58:28 - INFO - __main__ - Step 31673: {'lr': 0.00045202942818872157, 'samples': 6081216, 'steps': 31672, 'loss/train': 0.9692102074623108} 08/30/2021 18:58:29 - INFO - __main__ - Step 31674: {'lr': 0.0004520263023592363, 'samples': 6081408, 'steps': 31673, 'loss/train': 1.018338918685913} 08/30/2021 18:58:29 - INFO - __main__ - Step 31675: {'lr': 0.00045202317643872113, 'samples': 6081600, 'steps': 31674, 'loss/train': 1.7192820310592651} 08/30/2021 18:58:30 - INFO - __main__ - Step 31676: {'lr': 0.00045202005042717743, 'samples': 6081792, 'steps': 31675, 'loss/train': 1.3942060470581055} 08/30/2021 18:58:31 - INFO - __main__ - Step 31677: {'lr': 0.0004520169243246066, 'samples': 6081984, 'steps': 31676, 'loss/train': 0.8433346748352051} 08/30/2021 18:58:31 - INFO - __main__ - Step 31678: {'lr': 0.0004520137981310101, 'samples': 6082176, 'steps': 31677, 'loss/train': 1.0872691869735718} 08/30/2021 18:58:32 - INFO - __main__ - Step 31679: {'lr': 0.0004520106718463893, 'samples': 6082368, 'steps': 31678, 'loss/train': 1.5257447957992554} 08/30/2021 18:58:32 - INFO - __main__ - Step 31680: {'lr': 0.0004520075454707456, 'samples': 6082560, 'steps': 31679, 'loss/train': 1.4212603569030762} 08/30/2021 18:58:32 - INFO - __main__ - Step 31681: {'lr': 0.0004520044190040804, 'samples': 6082752, 'steps': 31680, 'loss/train': 0.8837733864784241} 08/30/2021 18:58:34 - INFO - __main__ - Step 31682: {'lr': 0.0004520012924463951, 'samples': 6082944, 'steps': 31681, 'loss/train': 1.139052152633667} 08/30/2021 18:58:34 - INFO - __main__ - Step 31683: {'lr': 0.0004519981657976912, 'samples': 6083136, 'steps': 31682, 'loss/train': 1.3233985900878906} 08/30/2021 18:58:35 - INFO - __main__ - Step 31684: {'lr': 0.00045199503905797, 'samples': 6083328, 'steps': 31683, 'loss/train': 1.5957056283950806} 08/30/2021 18:58:35 - INFO - __main__ - Step 31685: {'lr': 0.0004519919122272329, 'samples': 6083520, 'steps': 31684, 'loss/train': 1.5648043155670166} 08/30/2021 18:58:35 - INFO - __main__ - Step 31686: {'lr': 0.00045198878530548146, 'samples': 6083712, 'steps': 31685, 'loss/train': 1.677486538887024} 08/30/2021 18:58:37 - INFO - __main__ - Step 31687: {'lr': 0.0004519856582927169, 'samples': 6083904, 'steps': 31686, 'loss/train': 1.679205060005188} 08/30/2021 18:58:38 - INFO - __main__ - Step 31688: {'lr': 0.00045198253118894084, 'samples': 6084096, 'steps': 31687, 'loss/train': 1.8955087661743164} 08/30/2021 18:58:38 - INFO - __main__ - Step 31689: {'lr': 0.0004519794039941545, 'samples': 6084288, 'steps': 31688, 'loss/train': 1.417022943496704} 08/30/2021 18:58:39 - INFO - __main__ - Step 31690: {'lr': 0.0004519762767083593, 'samples': 6084480, 'steps': 31689, 'loss/train': 1.5744907855987549} 08/30/2021 18:58:39 - INFO - __main__ - Step 31691: {'lr': 0.00045197314933155677, 'samples': 6084672, 'steps': 31690, 'loss/train': 1.6208579540252686} 08/30/2021 18:58:40 - INFO - __main__ - Step 31692: {'lr': 0.0004519700218637482, 'samples': 6084864, 'steps': 31691, 'loss/train': 1.584664225578308} 08/30/2021 18:58:41 - INFO - __main__ - Step 31693: {'lr': 0.00045196689430493516, 'samples': 6085056, 'steps': 31692, 'loss/train': 1.574609637260437} 08/30/2021 18:58:41 - INFO - __main__ - Step 31694: {'lr': 0.00045196376665511883, 'samples': 6085248, 'steps': 31693, 'loss/train': 1.546935796737671} 08/30/2021 18:58:42 - INFO - __main__ - Step 31695: {'lr': 0.00045196063891430086, 'samples': 6085440, 'steps': 31694, 'loss/train': 1.5212210416793823} 08/30/2021 18:58:42 - INFO - __main__ - Step 31696: {'lr': 0.0004519575110824825, 'samples': 6085632, 'steps': 31695, 'loss/train': 1.4790048599243164} 08/30/2021 18:58:43 - INFO - __main__ - Step 31697: {'lr': 0.0004519543831596652, 'samples': 6085824, 'steps': 31696, 'loss/train': 1.2932026386260986} 08/30/2021 18:58:44 - INFO - __main__ - Step 31698: {'lr': 0.0004519512551458503, 'samples': 6086016, 'steps': 31697, 'loss/train': 1.4547592401504517} 08/30/2021 18:58:45 - INFO - __main__ - Step 31699: {'lr': 0.0004519481270410394, 'samples': 6086208, 'steps': 31698, 'loss/train': 0.1433655023574829} 08/30/2021 18:58:45 - INFO - __main__ - Step 31700: {'lr': 0.00045194499884523376, 'samples': 6086400, 'steps': 31699, 'loss/train': 0.35211166739463806} 08/30/2021 18:58:46 - INFO - __main__ - Step 31701: {'lr': 0.0004519418705584348, 'samples': 6086592, 'steps': 31700, 'loss/train': 1.0860755443572998} 08/30/2021 18:58:46 - INFO - __main__ - Step 31702: {'lr': 0.0004519387421806439, 'samples': 6086784, 'steps': 31701, 'loss/train': 1.586506724357605} 08/30/2021 18:58:46 - INFO - __main__ - Step 31703: {'lr': 0.0004519356137118625, 'samples': 6086976, 'steps': 31702, 'loss/train': 1.771864414215088} 08/30/2021 18:58:48 - INFO - __main__ - Step 31704: {'lr': 0.00045193248515209216, 'samples': 6087168, 'steps': 31703, 'loss/train': 1.4260754585266113} 08/30/2021 18:58:48 - INFO - __main__ - Step 31705: {'lr': 0.0004519293565013341, 'samples': 6087360, 'steps': 31704, 'loss/train': 1.7522869110107422} 08/30/2021 18:58:49 - INFO - __main__ - Step 31706: {'lr': 0.0004519262277595898, 'samples': 6087552, 'steps': 31705, 'loss/train': 1.347668170928955} 08/30/2021 18:58:49 - INFO - __main__ - Step 31707: {'lr': 0.0004519230989268606, 'samples': 6087744, 'steps': 31706, 'loss/train': 1.5464115142822266} 08/30/2021 18:58:49 - INFO - __main__ - Step 31708: {'lr': 0.000451919970003148, 'samples': 6087936, 'steps': 31707, 'loss/train': 1.296976089477539} 08/30/2021 18:58:51 - INFO - __main__ - Step 31709: {'lr': 0.0004519168409884534, 'samples': 6088128, 'steps': 31708, 'loss/train': 1.6748765707015991} 08/30/2021 18:58:51 - INFO - __main__ - Step 31710: {'lr': 0.00045191371188277817, 'samples': 6088320, 'steps': 31709, 'loss/train': 1.7006301879882812} 08/30/2021 18:58:52 - INFO - __main__ - Step 31711: {'lr': 0.0004519105826861237, 'samples': 6088512, 'steps': 31710, 'loss/train': 1.3849173784255981} 08/30/2021 18:58:52 - INFO - __main__ - Step 31712: {'lr': 0.0004519074533984915, 'samples': 6088704, 'steps': 31711, 'loss/train': 1.2888586521148682} 08/30/2021 18:58:52 - INFO - __main__ - Step 31713: {'lr': 0.0004519043240198829, 'samples': 6088896, 'steps': 31712, 'loss/train': 1.2900900840759277} 08/30/2021 18:58:54 - INFO - __main__ - Step 31714: {'lr': 0.0004519011945502993, 'samples': 6089088, 'steps': 31713, 'loss/train': 1.9359652996063232} 08/30/2021 18:58:55 - INFO - __main__ - Step 31715: {'lr': 0.00045189806498974216, 'samples': 6089280, 'steps': 31714, 'loss/train': 0.8847703337669373} 08/30/2021 18:58:55 - INFO - __main__ - Step 31716: {'lr': 0.00045189493533821285, 'samples': 6089472, 'steps': 31715, 'loss/train': 1.570649266242981} 08/30/2021 18:58:55 - INFO - __main__ - Step 31717: {'lr': 0.0004518918055957128, 'samples': 6089664, 'steps': 31716, 'loss/train': 1.5662107467651367} 08/30/2021 18:58:56 - INFO - __main__ - Step 31718: {'lr': 0.0004518886757622435, 'samples': 6089856, 'steps': 31717, 'loss/train': 1.7837783098220825} 08/30/2021 18:58:56 - INFO - __main__ - Step 31719: {'lr': 0.0004518855458378062, 'samples': 6090048, 'steps': 31718, 'loss/train': 1.583587408065796} 08/30/2021 18:58:58 - INFO - __main__ - Step 31720: {'lr': 0.0004518824158224023, 'samples': 6090240, 'steps': 31719, 'loss/train': 2.0281319618225098} 08/30/2021 18:58:58 - INFO - __main__ - Step 31721: {'lr': 0.00045187928571603343, 'samples': 6090432, 'steps': 31720, 'loss/train': 1.341612458229065} 08/30/2021 18:58:58 - INFO - __main__ - Step 31722: {'lr': 0.0004518761555187008, 'samples': 6090624, 'steps': 31721, 'loss/train': 1.3035047054290771} 08/30/2021 18:58:59 - INFO - __main__ - Step 31723: {'lr': 0.00045187302523040597, 'samples': 6090816, 'steps': 31722, 'loss/train': 1.4077343940734863} 08/30/2021 18:58:59 - INFO - __main__ - Step 31724: {'lr': 0.00045186989485115014, 'samples': 6091008, 'steps': 31723, 'loss/train': 1.2675732374191284} 08/30/2021 18:59:01 - INFO - __main__ - Step 31725: {'lr': 0.000451866764380935, 'samples': 6091200, 'steps': 31724, 'loss/train': 1.6097421646118164} 08/30/2021 18:59:02 - INFO - __main__ - Step 31726: {'lr': 0.0004518636338197617, 'samples': 6091392, 'steps': 31725, 'loss/train': 1.6313509941101074} 08/30/2021 18:59:02 - INFO - __main__ - Step 31727: {'lr': 0.00045186050316763186, 'samples': 6091584, 'steps': 31726, 'loss/train': 1.7014423608779907} 08/30/2021 18:59:02 - INFO - __main__ - Step 31728: {'lr': 0.0004518573724245467, 'samples': 6091776, 'steps': 31727, 'loss/train': 1.5814265012741089} 08/30/2021 18:59:03 - INFO - __main__ - Step 31729: {'lr': 0.00045185424159050776, 'samples': 6091968, 'steps': 31728, 'loss/train': 1.6253712177276611} 08/30/2021 18:59:04 - INFO - __main__ - Step 31730: {'lr': 0.00045185111066551643, 'samples': 6092160, 'steps': 31729, 'loss/train': 1.3151179552078247} 08/30/2021 18:59:05 - INFO - __main__ - Step 31731: {'lr': 0.0004518479796495741, 'samples': 6092352, 'steps': 31730, 'loss/train': 0.9944483041763306} 08/30/2021 18:59:05 - INFO - __main__ - Step 31732: {'lr': 0.00045184484854268216, 'samples': 6092544, 'steps': 31731, 'loss/train': 1.4920777082443237} 08/30/2021 18:59:05 - INFO - __main__ - Step 31733: {'lr': 0.00045184171734484203, 'samples': 6092736, 'steps': 31732, 'loss/train': 1.7822221517562866} 08/30/2021 18:59:06 - INFO - __main__ - Step 31734: {'lr': 0.00045183858605605517, 'samples': 6092928, 'steps': 31733, 'loss/train': 1.2142447233200073} 08/30/2021 18:59:07 - INFO - __main__ - Step 31735: {'lr': 0.00045183545467632295, 'samples': 6093120, 'steps': 31734, 'loss/train': 1.3074018955230713} 08/30/2021 18:59:08 - INFO - __main__ - Step 31736: {'lr': 0.0004518323232056468, 'samples': 6093312, 'steps': 31735, 'loss/train': 0.9198724031448364} 08/30/2021 18:59:08 - INFO - __main__ - Step 31737: {'lr': 0.0004518291916440281, 'samples': 6093504, 'steps': 31736, 'loss/train': 1.4412691593170166} 08/30/2021 18:59:08 - INFO - __main__ - Step 31738: {'lr': 0.0004518260599914683, 'samples': 6093696, 'steps': 31737, 'loss/train': 1.4064964056015015} 08/30/2021 18:59:09 - INFO - __main__ - Step 31739: {'lr': 0.0004518229282479688, 'samples': 6093888, 'steps': 31738, 'loss/train': 1.5702183246612549} 08/30/2021 18:59:11 - INFO - __main__ - Step 31740: {'lr': 0.000451819796413531, 'samples': 6094080, 'steps': 31739, 'loss/train': 1.7810715436935425} 08/30/2021 18:59:11 - INFO - __main__ - Step 31741: {'lr': 0.0004518166644881563, 'samples': 6094272, 'steps': 31740, 'loss/train': 1.648104190826416} 08/30/2021 18:59:12 - INFO - __main__ - Step 31742: {'lr': 0.0004518135324718461, 'samples': 6094464, 'steps': 31741, 'loss/train': 1.4135750532150269} 08/30/2021 18:59:12 - INFO - __main__ - Step 31743: {'lr': 0.00045181040036460185, 'samples': 6094656, 'steps': 31742, 'loss/train': 1.8138679265975952} 08/30/2021 18:59:13 - INFO - __main__ - Step 31744: {'lr': 0.0004518072681664249, 'samples': 6094848, 'steps': 31743, 'loss/train': 1.2215015888214111} 08/30/2021 18:59:13 - INFO - __main__ - Step 31745: {'lr': 0.0004518041358773168, 'samples': 6095040, 'steps': 31744, 'loss/train': 1.128543496131897} 08/30/2021 18:59:14 - INFO - __main__ - Step 31746: {'lr': 0.0004518010034972788, 'samples': 6095232, 'steps': 31745, 'loss/train': 1.211618423461914} 08/30/2021 18:59:15 - INFO - __main__ - Step 31747: {'lr': 0.0004517978710263124, 'samples': 6095424, 'steps': 31746, 'loss/train': 1.0471305847167969} 08/30/2021 18:59:15 - INFO - __main__ - Step 31748: {'lr': 0.0004517947384644191, 'samples': 6095616, 'steps': 31747, 'loss/train': 1.3916995525360107} 08/30/2021 18:59:16 - INFO - __main__ - Step 31749: {'lr': 0.00045179160581160005, 'samples': 6095808, 'steps': 31748, 'loss/train': 1.2283918857574463} 08/30/2021 18:59:16 - INFO - __main__ - Step 31750: {'lr': 0.0004517884730678569, 'samples': 6096000, 'steps': 31749, 'loss/train': 1.175004005432129} 08/30/2021 18:59:16 - INFO - __main__ - Step 31751: {'lr': 0.00045178534023319097, 'samples': 6096192, 'steps': 31750, 'loss/train': 1.2510666847229004} 08/30/2021 18:59:18 - INFO - __main__ - Step 31752: {'lr': 0.00045178220730760367, 'samples': 6096384, 'steps': 31751, 'loss/train': 2.866900682449341} 08/30/2021 18:59:18 - INFO - __main__ - Step 31753: {'lr': 0.0004517790742910964, 'samples': 6096576, 'steps': 31752, 'loss/train': 1.5635515451431274} 08/30/2021 18:59:19 - INFO - __main__ - Step 31754: {'lr': 0.0004517759411836706, 'samples': 6096768, 'steps': 31753, 'loss/train': 1.7726420164108276} 08/30/2021 18:59:19 - INFO - __main__ - Step 31755: {'lr': 0.0004517728079853277, 'samples': 6096960, 'steps': 31754, 'loss/train': 1.9591432809829712} 08/30/2021 18:59:19 - INFO - __main__ - Step 31756: {'lr': 0.0004517696746960691, 'samples': 6097152, 'steps': 31755, 'loss/train': 1.5650672912597656} 08/30/2021 18:59:21 - INFO - __main__ - Step 31757: {'lr': 0.00045176654131589617, 'samples': 6097344, 'steps': 31756, 'loss/train': 0.24385832250118256} 08/30/2021 18:59:21 - INFO - __main__ - Step 31758: {'lr': 0.0004517634078448103, 'samples': 6097536, 'steps': 31757, 'loss/train': 1.4693056344985962} 08/30/2021 18:59:22 - INFO - __main__ - Step 31759: {'lr': 0.0004517602742828131, 'samples': 6097728, 'steps': 31758, 'loss/train': 1.4630427360534668} 08/30/2021 18:59:22 - INFO - __main__ - Step 31760: {'lr': 0.0004517571406299057, 'samples': 6097920, 'steps': 31759, 'loss/train': 2.1614649295806885} 08/30/2021 18:59:23 - INFO - __main__ - Step 31761: {'lr': 0.0004517540068860897, 'samples': 6098112, 'steps': 31760, 'loss/train': 1.2102993726730347} 08/30/2021 18:59:24 - INFO - __main__ - Step 31762: {'lr': 0.0004517508730513664, 'samples': 6098304, 'steps': 31761, 'loss/train': 1.5794097185134888} 08/30/2021 18:59:24 - INFO - __main__ - Step 31763: {'lr': 0.00045174773912573735, 'samples': 6098496, 'steps': 31762, 'loss/train': 1.3294028043746948} 08/30/2021 18:59:25 - INFO - __main__ - Step 31764: {'lr': 0.00045174460510920386, 'samples': 6098688, 'steps': 31763, 'loss/train': 1.0927268266677856} 08/30/2021 18:59:25 - INFO - __main__ - Step 31765: {'lr': 0.00045174147100176734, 'samples': 6098880, 'steps': 31764, 'loss/train': 1.4281386137008667} 08/30/2021 18:59:26 - INFO - __main__ - Step 31766: {'lr': 0.00045173833680342925, 'samples': 6099072, 'steps': 31765, 'loss/train': 1.6285591125488281} 08/30/2021 18:59:26 - INFO - __main__ - Step 31767: {'lr': 0.00045173520251419095, 'samples': 6099264, 'steps': 31766, 'loss/train': 2.077353000640869} 08/30/2021 18:59:27 - INFO - __main__ - Step 31768: {'lr': 0.0004517320681340539, 'samples': 6099456, 'steps': 31767, 'loss/train': 1.163082242012024} 08/30/2021 18:59:28 - INFO - __main__ - Step 31769: {'lr': 0.0004517289336630195, 'samples': 6099648, 'steps': 31768, 'loss/train': 1.5306695699691772} 08/30/2021 18:59:28 - INFO - __main__ - Step 31770: {'lr': 0.0004517257991010891, 'samples': 6099840, 'steps': 31769, 'loss/train': 1.7428069114685059} 08/30/2021 18:59:28 - INFO - __main__ - Step 31771: {'lr': 0.0004517226644482642, 'samples': 6100032, 'steps': 31770, 'loss/train': 1.2836638689041138} 08/30/2021 18:59:29 - INFO - __main__ - Step 31772: {'lr': 0.00045171952970454623, 'samples': 6100224, 'steps': 31771, 'loss/train': 1.0561379194259644} 08/30/2021 18:59:30 - INFO - __main__ - Step 31773: {'lr': 0.0004517163948699365, 'samples': 6100416, 'steps': 31772, 'loss/train': 1.876664638519287} 08/30/2021 18:59:31 - INFO - __main__ - Step 31774: {'lr': 0.00045171325994443644, 'samples': 6100608, 'steps': 31773, 'loss/train': 1.8266552686691284} 08/30/2021 18:59:31 - INFO - __main__ - Step 31775: {'lr': 0.00045171012492804753, 'samples': 6100800, 'steps': 31774, 'loss/train': 1.3269596099853516} 08/30/2021 18:59:32 - INFO - __main__ - Step 31776: {'lr': 0.0004517069898207712, 'samples': 6100992, 'steps': 31775, 'loss/train': 1.5919526815414429} 08/30/2021 18:59:32 - INFO - __main__ - Step 31777: {'lr': 0.00045170385462260876, 'samples': 6101184, 'steps': 31776, 'loss/train': 0.6725611090660095} 08/30/2021 18:59:35 - INFO - __main__ - Step 31778: {'lr': 0.0004517007193335617, 'samples': 6101376, 'steps': 31777, 'loss/train': 1.7358683347702026} 08/30/2021 18:59:35 - INFO - __main__ - Step 31779: {'lr': 0.0004516975839536314, 'samples': 6101568, 'steps': 31778, 'loss/train': 0.10978332161903381} 08/30/2021 18:59:36 - INFO - __main__ - Step 31780: {'lr': 0.0004516944484828193, 'samples': 6101760, 'steps': 31779, 'loss/train': 0.9555991888046265} 08/30/2021 18:59:36 - INFO - __main__ - Step 31781: {'lr': 0.0004516913129211268, 'samples': 6101952, 'steps': 31780, 'loss/train': 1.1444238424301147} 08/30/2021 18:59:36 - INFO - __main__ - Step 31782: {'lr': 0.00045168817726855525, 'samples': 6102144, 'steps': 31781, 'loss/train': 4.335629940032959} 08/30/2021 18:59:37 - INFO - __main__ - Step 31783: {'lr': 0.0004516850415251061, 'samples': 6102336, 'steps': 31782, 'loss/train': 4.193833351135254} 08/30/2021 18:59:38 - INFO - __main__ - Step 31784: {'lr': 0.0004516819056907809, 'samples': 6102528, 'steps': 31783, 'loss/train': 1.4793989658355713} 08/30/2021 18:59:39 - INFO - __main__ - Step 31785: {'lr': 0.0004516787697655809, 'samples': 6102720, 'steps': 31784, 'loss/train': 1.823095440864563} 08/30/2021 18:59:39 - INFO - __main__ - Step 31786: {'lr': 0.0004516756337495075, 'samples': 6102912, 'steps': 31785, 'loss/train': 1.108152985572815} 08/30/2021 18:59:39 - INFO - __main__ - Step 31787: {'lr': 0.0004516724976425622, 'samples': 6103104, 'steps': 31786, 'loss/train': 1.6836150884628296} 08/30/2021 18:59:40 - INFO - __main__ - Step 31788: {'lr': 0.0004516693614447464, 'samples': 6103296, 'steps': 31787, 'loss/train': 1.3794578313827515} 08/30/2021 18:59:41 - INFO - __main__ - Step 31789: {'lr': 0.0004516662251560615, 'samples': 6103488, 'steps': 31788, 'loss/train': 1.2366358041763306} 08/30/2021 18:59:42 - INFO - __main__ - Step 31790: {'lr': 0.0004516630887765089, 'samples': 6103680, 'steps': 31789, 'loss/train': 1.6831117868423462} 08/30/2021 18:59:42 - INFO - __main__ - Step 31791: {'lr': 0.00045165995230609003, 'samples': 6103872, 'steps': 31790, 'loss/train': 1.8927607536315918} 08/30/2021 18:59:42 - INFO - __main__ - Step 31792: {'lr': 0.0004516568157448063, 'samples': 6104064, 'steps': 31791, 'loss/train': 1.3940768241882324} 08/30/2021 18:59:43 - INFO - __main__ - Step 31793: {'lr': 0.00045165367909265916, 'samples': 6104256, 'steps': 31792, 'loss/train': 1.6035305261611938} 08/30/2021 18:59:44 - INFO - __main__ - Step 31794: {'lr': 0.00045165054234964984, 'samples': 6104448, 'steps': 31793, 'loss/train': 1.8415007591247559} 08/30/2021 18:59:45 - INFO - __main__ - Step 31795: {'lr': 0.0004516474055157801, 'samples': 6104640, 'steps': 31794, 'loss/train': 1.4146981239318848} 08/30/2021 18:59:45 - INFO - __main__ - Step 31796: {'lr': 0.000451644268591051, 'samples': 6104832, 'steps': 31795, 'loss/train': 1.3608078956604004} 08/30/2021 18:59:45 - INFO - __main__ - Step 31797: {'lr': 0.00045164113157546414, 'samples': 6105024, 'steps': 31796, 'loss/train': 1.3972551822662354} 08/30/2021 18:59:46 - INFO - __main__ - Step 31798: {'lr': 0.0004516379944690209, 'samples': 6105216, 'steps': 31797, 'loss/train': 0.08837572485208511} 08/30/2021 18:59:47 - INFO - __main__ - Step 31799: {'lr': 0.0004516348572717227, 'samples': 6105408, 'steps': 31798, 'loss/train': 1.6503653526306152} 08/30/2021 18:59:48 - INFO - __main__ - Step 31800: {'lr': 0.000451631719983571, 'samples': 6105600, 'steps': 31799, 'loss/train': 1.1910794973373413} 08/30/2021 18:59:48 - INFO - __main__ - Step 31801: {'lr': 0.00045162858260456705, 'samples': 6105792, 'steps': 31800, 'loss/train': 1.2666096687316895} 08/30/2021 18:59:48 - INFO - __main__ - Step 31802: {'lr': 0.0004516254451347125, 'samples': 6105984, 'steps': 31801, 'loss/train': 1.1145057678222656} 08/30/2021 18:59:49 - INFO - __main__ - Step 31803: {'lr': 0.0004516223075740085, 'samples': 6106176, 'steps': 31802, 'loss/train': 1.3834974765777588} 08/30/2021 18:59:49 - INFO - __main__ - Step 31804: {'lr': 0.00045161916992245664, 'samples': 6106368, 'steps': 31803, 'loss/train': 1.6630232334136963} 08/30/2021 18:59:51 - INFO - __main__ - Step 31805: {'lr': 0.0004516160321800584, 'samples': 6106560, 'steps': 31804, 'loss/train': 1.3498830795288086} 08/30/2021 18:59:51 - INFO - __main__ - Step 31806: {'lr': 0.000451612894346815, 'samples': 6106752, 'steps': 31805, 'loss/train': 1.8217791318893433} 08/30/2021 18:59:51 - INFO - __main__ - Step 31807: {'lr': 0.00045160975642272795, 'samples': 6106944, 'steps': 31806, 'loss/train': 0.37964287400245667} 08/30/2021 18:59:52 - INFO - __main__ - Step 31808: {'lr': 0.0004516066184077986, 'samples': 6107136, 'steps': 31807, 'loss/train': 2.2806687355041504} 08/30/2021 18:59:52 - INFO - __main__ - Step 31809: {'lr': 0.0004516034803020285, 'samples': 6107328, 'steps': 31808, 'loss/train': 2.123850107192993} 08/30/2021 18:59:54 - INFO - __main__ - Step 31810: {'lr': 0.0004516003421054189, 'samples': 6107520, 'steps': 31809, 'loss/train': 1.3058465719223022} 08/30/2021 18:59:54 - INFO - __main__ - Step 31811: {'lr': 0.0004515972038179714, 'samples': 6107712, 'steps': 31810, 'loss/train': 1.8727264404296875} 08/30/2021 18:59:54 - INFO - __main__ - Step 31812: {'lr': 0.0004515940654396872, 'samples': 6107904, 'steps': 31811, 'loss/train': 1.3117345571517944} 08/30/2021 18:59:55 - INFO - __main__ - Step 31813: {'lr': 0.00045159092697056794, 'samples': 6108096, 'steps': 31812, 'loss/train': 1.0136164426803589} 08/30/2021 18:59:55 - INFO - __main__ - Step 31814: {'lr': 0.00045158778841061483, 'samples': 6108288, 'steps': 31813, 'loss/train': 1.5322074890136719} 08/30/2021 18:59:57 - INFO - __main__ - Step 31815: {'lr': 0.0004515846497598294, 'samples': 6108480, 'steps': 31814, 'loss/train': 1.6552120447158813} 08/30/2021 18:59:58 - INFO - __main__ - Step 31816: {'lr': 0.000451581511018213, 'samples': 6108672, 'steps': 31815, 'loss/train': 1.793156385421753} 08/30/2021 18:59:58 - INFO - __main__ - Step 31817: {'lr': 0.00045157837218576713, 'samples': 6108864, 'steps': 31816, 'loss/train': 0.9958736300468445} 08/30/2021 18:59:58 - INFO - __main__ - Step 31818: {'lr': 0.00045157523326249316, 'samples': 6109056, 'steps': 31817, 'loss/train': 1.0163085460662842} 08/30/2021 18:59:59 - INFO - __main__ - Step 31819: {'lr': 0.00045157209424839253, 'samples': 6109248, 'steps': 31818, 'loss/train': 1.5546318292617798} 08/30/2021 19:00:00 - INFO - __main__ - Step 31820: {'lr': 0.0004515689551434665, 'samples': 6109440, 'steps': 31819, 'loss/train': 1.1910486221313477} 08/30/2021 19:00:01 - INFO - __main__ - Step 31821: {'lr': 0.00045156581594771675, 'samples': 6109632, 'steps': 31820, 'loss/train': 2.004864454269409} 08/30/2021 19:00:01 - INFO - __main__ - Step 31822: {'lr': 0.00045156267666114446, 'samples': 6109824, 'steps': 31821, 'loss/train': 1.709044337272644} 08/30/2021 19:00:01 - INFO - __main__ - Step 31823: {'lr': 0.0004515595372837512, 'samples': 6110016, 'steps': 31822, 'loss/train': 0.6816454529762268} 08/30/2021 19:00:02 - INFO - __main__ - Step 31824: {'lr': 0.00045155639781553825, 'samples': 6110208, 'steps': 31823, 'loss/train': 1.6261194944381714} 08/30/2021 19:00:03 - INFO - __main__ - Step 31825: {'lr': 0.00045155325825650715, 'samples': 6110400, 'steps': 31824, 'loss/train': 0.8188231587409973} 08/30/2021 19:00:03 - INFO - __main__ - Step 31826: {'lr': 0.00045155011860665927, 'samples': 6110592, 'steps': 31825, 'loss/train': 1.6089593172073364} 08/30/2021 19:00:04 - INFO - __main__ - Step 31827: {'lr': 0.00045154697886599606, 'samples': 6110784, 'steps': 31826, 'loss/train': 1.368036150932312} 08/30/2021 19:00:04 - INFO - __main__ - Step 31828: {'lr': 0.0004515438390345188, 'samples': 6110976, 'steps': 31827, 'loss/train': 1.291267991065979} 08/30/2021 19:00:05 - INFO - __main__ - Step 31829: {'lr': 0.00045154069911222905, 'samples': 6111168, 'steps': 31828, 'loss/train': 1.6703388690948486} 08/30/2021 19:00:06 - INFO - __main__ - Step 31830: {'lr': 0.0004515375590991281, 'samples': 6111360, 'steps': 31829, 'loss/train': 1.500475287437439} 08/30/2021 19:00:06 - INFO - __main__ - Step 31831: {'lr': 0.0004515344189952175, 'samples': 6111552, 'steps': 31830, 'loss/train': 1.0839345455169678} 08/30/2021 19:00:07 - INFO - __main__ - Step 31832: {'lr': 0.0004515312788004986, 'samples': 6111744, 'steps': 31831, 'loss/train': 1.6793702840805054} 08/30/2021 19:00:07 - INFO - __main__ - Step 31833: {'lr': 0.00045152813851497274, 'samples': 6111936, 'steps': 31832, 'loss/train': 1.1811480522155762} 08/30/2021 19:00:07 - INFO - __main__ - Step 31834: {'lr': 0.0004515249981386416, 'samples': 6112128, 'steps': 31833, 'loss/train': 1.714882254600525} 08/30/2021 19:00:08 - INFO - __main__ - Step 31835: {'lr': 0.0004515218576715062, 'samples': 6112320, 'steps': 31834, 'loss/train': 1.9581176042556763} 08/30/2021 19:00:10 - INFO - __main__ - Step 31836: {'lr': 0.00045151871711356827, 'samples': 6112512, 'steps': 31835, 'loss/train': 0.9482317566871643} 08/30/2021 19:00:10 - INFO - __main__ - Step 31837: {'lr': 0.0004515155764648291, 'samples': 6112704, 'steps': 31836, 'loss/train': 0.9607094526290894} 08/30/2021 19:00:11 - INFO - __main__ - Step 31838: {'lr': 0.0004515124357252901, 'samples': 6112896, 'steps': 31837, 'loss/train': 1.5487853288650513} 08/30/2021 19:00:11 - INFO - __main__ - Step 31839: {'lr': 0.0004515092948949527, 'samples': 6113088, 'steps': 31838, 'loss/train': 1.579304575920105} 08/30/2021 19:00:11 - INFO - __main__ - Step 31840: {'lr': 0.00045150615397381835, 'samples': 6113280, 'steps': 31839, 'loss/train': 1.076081395149231} 08/30/2021 19:00:13 - INFO - __main__ - Step 31841: {'lr': 0.0004515030129618884, 'samples': 6113472, 'steps': 31840, 'loss/train': 1.2970243692398071} 08/30/2021 19:00:13 - INFO - __main__ - Step 31842: {'lr': 0.0004514998718591643, 'samples': 6113664, 'steps': 31841, 'loss/train': 1.2793632745742798} 08/30/2021 19:00:14 - INFO - __main__ - Step 31843: {'lr': 0.0004514967306656475, 'samples': 6113856, 'steps': 31842, 'loss/train': 1.1665675640106201} 08/30/2021 19:00:14 - INFO - __main__ - Step 31844: {'lr': 0.0004514935893813394, 'samples': 6114048, 'steps': 31843, 'loss/train': 1.4917482137680054} 08/30/2021 19:00:14 - INFO - __main__ - Step 31845: {'lr': 0.00045149044800624135, 'samples': 6114240, 'steps': 31844, 'loss/train': 1.6520767211914062} 08/30/2021 19:00:16 - INFO - __main__ - Step 31846: {'lr': 0.0004514873065403549, 'samples': 6114432, 'steps': 31845, 'loss/train': 1.6882444620132446} 08/30/2021 19:00:16 - INFO - __main__ - Step 31847: {'lr': 0.0004514841649836813, 'samples': 6114624, 'steps': 31846, 'loss/train': 1.551079273223877} 08/30/2021 19:00:17 - INFO - __main__ - Step 31848: {'lr': 0.000451481023336222, 'samples': 6114816, 'steps': 31847, 'loss/train': 1.6473387479782104} 08/30/2021 19:00:17 - INFO - __main__ - Step 31849: {'lr': 0.0004514778815979785, 'samples': 6115008, 'steps': 31848, 'loss/train': 2.3100783824920654} 08/30/2021 19:00:17 - INFO - __main__ - Step 31850: {'lr': 0.0004514747397689522, 'samples': 6115200, 'steps': 31849, 'loss/train': 1.0601561069488525} 08/30/2021 19:00:19 - INFO - __main__ - Step 31851: {'lr': 0.0004514715978491445, 'samples': 6115392, 'steps': 31850, 'loss/train': 1.2394394874572754} 08/30/2021 19:00:20 - INFO - __main__ - Step 31852: {'lr': 0.0004514684558385568, 'samples': 6115584, 'steps': 31851, 'loss/train': 1.2615773677825928} 08/30/2021 19:00:20 - INFO - __main__ - Step 31853: {'lr': 0.0004514653137371905, 'samples': 6115776, 'steps': 31852, 'loss/train': 1.584965705871582} 08/30/2021 19:00:20 - INFO - __main__ - Step 31854: {'lr': 0.000451462171545047, 'samples': 6115968, 'steps': 31853, 'loss/train': 2.1311557292938232} 08/30/2021 19:00:21 - INFO - __main__ - Step 31855: {'lr': 0.00045145902926212785, 'samples': 6116160, 'steps': 31854, 'loss/train': 1.3710522651672363} 08/30/2021 19:00:22 - INFO - __main__ - Step 31856: {'lr': 0.0004514558868884343, 'samples': 6116352, 'steps': 31855, 'loss/train': 0.2669915556907654} 08/30/2021 19:00:23 - INFO - __main__ - Step 31857: {'lr': 0.00045145274442396786, 'samples': 6116544, 'steps': 31856, 'loss/train': 1.2853583097457886} 08/30/2021 19:00:23 - INFO - __main__ - Step 31858: {'lr': 0.00045144960186872996, 'samples': 6116736, 'steps': 31857, 'loss/train': 1.2335361242294312} 08/30/2021 19:00:24 - INFO - __main__ - Step 31859: {'lr': 0.0004514464592227219, 'samples': 6116928, 'steps': 31858, 'loss/train': 0.09652159363031387} 08/30/2021 19:00:24 - INFO - __main__ - Step 31860: {'lr': 0.0004514433164859453, 'samples': 6117120, 'steps': 31859, 'loss/train': 1.68108332157135} 08/30/2021 19:00:25 - INFO - __main__ - Step 31861: {'lr': 0.0004514401736584013, 'samples': 6117312, 'steps': 31860, 'loss/train': 1.659725546836853} 08/30/2021 19:00:26 - INFO - __main__ - Step 31862: {'lr': 0.0004514370307400916, 'samples': 6117504, 'steps': 31861, 'loss/train': 1.3923143148422241} 08/30/2021 19:00:26 - INFO - __main__ - Step 31863: {'lr': 0.00045143388773101733, 'samples': 6117696, 'steps': 31862, 'loss/train': 1.657745361328125} 08/30/2021 19:00:26 - INFO - __main__ - Step 31864: {'lr': 0.0004514307446311802, 'samples': 6117888, 'steps': 31863, 'loss/train': 1.300657868385315} 08/30/2021 19:00:27 - INFO - __main__ - Step 31865: {'lr': 0.0004514276014405814, 'samples': 6118080, 'steps': 31864, 'loss/train': 1.5859194993972778} 08/30/2021 19:00:28 - INFO - __main__ - Step 31866: {'lr': 0.00045142445815922244, 'samples': 6118272, 'steps': 31865, 'loss/train': 0.8749393224716187} 08/30/2021 19:00:29 - INFO - __main__ - Step 31867: {'lr': 0.0004514213147871047, 'samples': 6118464, 'steps': 31866, 'loss/train': 2.030456781387329} 08/30/2021 19:00:29 - INFO - __main__ - Step 31868: {'lr': 0.00045141817132422974, 'samples': 6118656, 'steps': 31867, 'loss/train': 1.5580260753631592} 08/30/2021 19:00:30 - INFO - __main__ - Step 31869: {'lr': 0.0004514150277705988, 'samples': 6118848, 'steps': 31868, 'loss/train': 0.9957576990127563} 08/30/2021 19:00:30 - INFO - __main__ - Step 31870: {'lr': 0.0004514118841262133, 'samples': 6119040, 'steps': 31869, 'loss/train': 1.6301734447479248} 08/30/2021 19:00:32 - INFO - __main__ - Step 31871: {'lr': 0.0004514087403910748, 'samples': 6119232, 'steps': 31870, 'loss/train': 1.6173347234725952} 08/30/2021 19:00:32 - INFO - __main__ - Step 31872: {'lr': 0.00045140559656518456, 'samples': 6119424, 'steps': 31871, 'loss/train': 1.7911888360977173} 08/30/2021 19:00:33 - INFO - __main__ - Step 31873: {'lr': 0.0004514024526485441, 'samples': 6119616, 'steps': 31872, 'loss/train': 1.1246349811553955} 08/30/2021 19:00:33 - INFO - __main__ - Step 31874: {'lr': 0.0004513993086411548, 'samples': 6119808, 'steps': 31873, 'loss/train': 1.5424352884292603} 08/30/2021 19:00:33 - INFO - __main__ - Step 31875: {'lr': 0.00045139616454301806, 'samples': 6120000, 'steps': 31874, 'loss/train': 1.4392929077148438} 08/30/2021 19:00:34 - INFO - __main__ - Step 31876: {'lr': 0.00045139302035413534, 'samples': 6120192, 'steps': 31875, 'loss/train': 1.192819356918335} 08/30/2021 19:00:36 - INFO - __main__ - Step 31877: {'lr': 0.00045138987607450803, 'samples': 6120384, 'steps': 31876, 'loss/train': 0.19190813601016998} 08/30/2021 19:00:36 - INFO - __main__ - Step 31878: {'lr': 0.00045138673170413756, 'samples': 6120576, 'steps': 31877, 'loss/train': 0.6537971496582031} 08/30/2021 19:00:36 - INFO - __main__ - Step 31879: {'lr': 0.0004513835872430253, 'samples': 6120768, 'steps': 31878, 'loss/train': 1.7221940755844116} 08/30/2021 19:00:37 - INFO - __main__ - Step 31880: {'lr': 0.0004513804426911727, 'samples': 6120960, 'steps': 31879, 'loss/train': 1.7095563411712646} 08/30/2021 19:00:37 - INFO - __main__ - Step 31881: {'lr': 0.00045137729804858124, 'samples': 6121152, 'steps': 31880, 'loss/train': 1.5729342699050903} 08/30/2021 19:00:37 - INFO - __main__ - Step 31882: {'lr': 0.00045137415331525225, 'samples': 6121344, 'steps': 31881, 'loss/train': 0.029747415333986282} 08/30/2021 19:00:39 - INFO - __main__ - Step 31883: {'lr': 0.0004513710084911872, 'samples': 6121536, 'steps': 31882, 'loss/train': 1.4356582164764404} 08/30/2021 19:00:39 - INFO - __main__ - Step 31884: {'lr': 0.00045136786357638736, 'samples': 6121728, 'steps': 31883, 'loss/train': 1.625819206237793} 08/30/2021 19:00:40 - INFO - __main__ - Step 31885: {'lr': 0.00045136471857085435, 'samples': 6121920, 'steps': 31884, 'loss/train': 0.17441563308238983} 08/30/2021 19:00:40 - INFO - __main__ - Step 31886: {'lr': 0.0004513615734745895, 'samples': 6122112, 'steps': 31885, 'loss/train': 1.51893949508667} 08/30/2021 19:00:40 - INFO - __main__ - Step 31887: {'lr': 0.00045135842828759426, 'samples': 6122304, 'steps': 31886, 'loss/train': 1.7774583101272583} 08/30/2021 19:00:41 - INFO - __main__ - Step 31888: {'lr': 0.00045135528300987006, 'samples': 6122496, 'steps': 31887, 'loss/train': 1.7723816633224487} 08/30/2021 19:00:43 - INFO - __main__ - Step 31889: {'lr': 0.00045135213764141814, 'samples': 6122688, 'steps': 31888, 'loss/train': 1.4298135042190552} 08/30/2021 19:00:43 - INFO - __main__ - Step 31890: {'lr': 0.00045134899218224014, 'samples': 6122880, 'steps': 31889, 'loss/train': 1.2692198753356934} 08/30/2021 19:00:44 - INFO - __main__ - Step 31891: {'lr': 0.0004513458466323374, 'samples': 6123072, 'steps': 31890, 'loss/train': 1.3574681282043457} 08/30/2021 19:00:44 - INFO - __main__ - Step 31892: {'lr': 0.0004513427009917113, 'samples': 6123264, 'steps': 31891, 'loss/train': 1.485721468925476} 08/30/2021 19:00:44 - INFO - __main__ - Step 31893: {'lr': 0.0004513395552603633, 'samples': 6123456, 'steps': 31892, 'loss/train': 1.3511744737625122} 08/30/2021 19:00:46 - INFO - __main__ - Step 31894: {'lr': 0.0004513364094382948, 'samples': 6123648, 'steps': 31893, 'loss/train': 2.151597738265991} 08/30/2021 19:00:46 - INFO - __main__ - Step 31895: {'lr': 0.00045133326352550724, 'samples': 6123840, 'steps': 31894, 'loss/train': 1.3925540447235107} 08/30/2021 19:00:47 - INFO - __main__ - Step 31896: {'lr': 0.000451330117522002, 'samples': 6124032, 'steps': 31895, 'loss/train': 1.5076276063919067} 08/30/2021 19:00:47 - INFO - __main__ - Step 31897: {'lr': 0.00045132697142778044, 'samples': 6124224, 'steps': 31896, 'loss/train': 1.6899641752243042} 08/30/2021 19:00:47 - INFO - __main__ - Step 31898: {'lr': 0.0004513238252428442, 'samples': 6124416, 'steps': 31897, 'loss/train': 1.2655805349349976} 08/30/2021 19:00:49 - INFO - __main__ - Step 31899: {'lr': 0.0004513206789671945, 'samples': 6124608, 'steps': 31898, 'loss/train': 1.8990840911865234} 08/30/2021 19:00:49 - INFO - __main__ - Step 31900: {'lr': 0.00045131753260083276, 'samples': 6124800, 'steps': 31899, 'loss/train': 1.9302457571029663} 08/30/2021 19:00:50 - INFO - __main__ - Step 31901: {'lr': 0.0004513143861437605, 'samples': 6124992, 'steps': 31900, 'loss/train': 0.4033149778842926} 08/30/2021 19:00:50 - INFO - __main__ - Step 31902: {'lr': 0.00045131123959597905, 'samples': 6125184, 'steps': 31901, 'loss/train': 1.51475191116333} 08/30/2021 19:00:50 - INFO - __main__ - Step 31903: {'lr': 0.0004513080929574899, 'samples': 6125376, 'steps': 31902, 'loss/train': 1.2061400413513184} 08/30/2021 19:00:52 - INFO - __main__ - Step 31904: {'lr': 0.0004513049462282943, 'samples': 6125568, 'steps': 31903, 'loss/train': 1.6666240692138672} 08/30/2021 19:00:52 - INFO - __main__ - Step 31905: {'lr': 0.00045130179940839395, 'samples': 6125760, 'steps': 31904, 'loss/train': 0.5576969981193542} 08/30/2021 19:00:53 - INFO - __main__ - Step 31906: {'lr': 0.00045129865249779, 'samples': 6125952, 'steps': 31905, 'loss/train': 1.1238410472869873} 08/30/2021 19:00:53 - INFO - __main__ - Step 31907: {'lr': 0.0004512955054964841, 'samples': 6126144, 'steps': 31906, 'loss/train': 1.5824025869369507} 08/30/2021 19:00:53 - INFO - __main__ - Step 31908: {'lr': 0.0004512923584044775, 'samples': 6126336, 'steps': 31907, 'loss/train': 1.0010976791381836} 08/30/2021 19:00:55 - INFO - __main__ - Step 31909: {'lr': 0.0004512892112217717, 'samples': 6126528, 'steps': 31908, 'loss/train': 1.430724859237671} 08/30/2021 19:00:55 - INFO - __main__ - Step 31910: {'lr': 0.00045128606394836805, 'samples': 6126720, 'steps': 31909, 'loss/train': 1.8850479125976562} 08/30/2021 19:00:56 - INFO - __main__ - Step 31911: {'lr': 0.00045128291658426796, 'samples': 6126912, 'steps': 31910, 'loss/train': 1.333143949508667} 08/30/2021 19:00:56 - INFO - __main__ - Step 31912: {'lr': 0.00045127976912947296, 'samples': 6127104, 'steps': 31911, 'loss/train': 1.5215591192245483} 08/30/2021 19:00:56 - INFO - __main__ - Step 31913: {'lr': 0.00045127662158398434, 'samples': 6127296, 'steps': 31912, 'loss/train': 1.4688621759414673} 08/30/2021 19:00:58 - INFO - __main__ - Step 31914: {'lr': 0.00045127347394780367, 'samples': 6127488, 'steps': 31913, 'loss/train': 1.9251075983047485} 08/30/2021 19:00:59 - INFO - __main__ - Step 31915: {'lr': 0.00045127032622093225, 'samples': 6127680, 'steps': 31914, 'loss/train': 0.5122542977333069} 08/30/2021 19:00:59 - INFO - __main__ - Step 31916: {'lr': 0.0004512671784033715, 'samples': 6127872, 'steps': 31915, 'loss/train': 1.3557204008102417} 08/30/2021 19:00:59 - INFO - __main__ - Step 31917: {'lr': 0.00045126403049512286, 'samples': 6128064, 'steps': 31916, 'loss/train': 1.2790255546569824} 08/30/2021 19:01:00 - INFO - __main__ - Step 31918: {'lr': 0.0004512608824961878, 'samples': 6128256, 'steps': 31917, 'loss/train': 1.243576169013977} 08/30/2021 19:01:00 - INFO - __main__ - Step 31919: {'lr': 0.00045125773440656756, 'samples': 6128448, 'steps': 31918, 'loss/train': 0.7762052416801453} 08/30/2021 19:01:02 - INFO - __main__ - Step 31920: {'lr': 0.0004512545862262638, 'samples': 6128640, 'steps': 31919, 'loss/train': 1.8772687911987305} 08/30/2021 19:01:02 - INFO - __main__ - Step 31921: {'lr': 0.0004512514379552779, 'samples': 6128832, 'steps': 31920, 'loss/train': 1.234052300453186} 08/30/2021 19:01:03 - INFO - __main__ - Step 31922: {'lr': 0.0004512482895936111, 'samples': 6129024, 'steps': 31921, 'loss/train': 0.22858773171901703} 08/30/2021 19:01:03 - INFO - __main__ - Step 31923: {'lr': 0.00045124514114126493, 'samples': 6129216, 'steps': 31922, 'loss/train': 1.7342108488082886} 08/30/2021 19:01:03 - INFO - __main__ - Step 31924: {'lr': 0.0004512419925982408, 'samples': 6129408, 'steps': 31923, 'loss/train': 0.8498665690422058} 08/30/2021 19:01:05 - INFO - __main__ - Step 31925: {'lr': 0.0004512388439645402, 'samples': 6129600, 'steps': 31924, 'loss/train': 0.8713580965995789} 08/30/2021 19:01:05 - INFO - __main__ - Step 31926: {'lr': 0.00045123569524016446, 'samples': 6129792, 'steps': 31925, 'loss/train': 1.5903257131576538} 08/30/2021 19:01:06 - INFO - __main__ - Step 31927: {'lr': 0.00045123254642511504, 'samples': 6129984, 'steps': 31926, 'loss/train': 1.119911789894104} 08/30/2021 19:01:06 - INFO - __main__ - Step 31928: {'lr': 0.0004512293975193933, 'samples': 6130176, 'steps': 31927, 'loss/train': 1.2339699268341064} 08/30/2021 19:01:06 - INFO - __main__ - Step 31929: {'lr': 0.0004512262485230007, 'samples': 6130368, 'steps': 31928, 'loss/train': 1.7451261281967163} 08/30/2021 19:01:08 - INFO - __main__ - Step 31930: {'lr': 0.00045122309943593865, 'samples': 6130560, 'steps': 31929, 'loss/train': 1.791560411453247} 08/30/2021 19:01:09 - INFO - __main__ - Step 31931: {'lr': 0.0004512199502582086, 'samples': 6130752, 'steps': 31930, 'loss/train': 1.3058853149414062} 08/30/2021 19:01:09 - INFO - __main__ - Step 31932: {'lr': 0.00045121680098981186, 'samples': 6130944, 'steps': 31931, 'loss/train': 0.13204734027385712} 08/30/2021 19:01:09 - INFO - __main__ - Step 31933: {'lr': 0.00045121365163075007, 'samples': 6131136, 'steps': 31932, 'loss/train': 0.034868452697992325} 08/30/2021 19:01:10 - INFO - __main__ - Step 31934: {'lr': 0.0004512105021810244, 'samples': 6131328, 'steps': 31933, 'loss/train': 1.3254988193511963} 08/30/2021 19:01:10 - INFO - __main__ - Step 31935: {'lr': 0.0004512073526406365, 'samples': 6131520, 'steps': 31934, 'loss/train': 1.6102142333984375} 08/30/2021 19:01:12 - INFO - __main__ - Step 31936: {'lr': 0.0004512042030095876, 'samples': 6131712, 'steps': 31935, 'loss/train': 1.2111961841583252} 08/30/2021 19:01:12 - INFO - __main__ - Step 31937: {'lr': 0.0004512010532878792, 'samples': 6131904, 'steps': 31936, 'loss/train': 1.2480688095092773} 08/30/2021 19:01:12 - INFO - __main__ - Step 31938: {'lr': 0.0004511979034755127, 'samples': 6132096, 'steps': 31937, 'loss/train': 1.541494369506836} 08/30/2021 19:01:13 - INFO - __main__ - Step 31939: {'lr': 0.0004511947535724895, 'samples': 6132288, 'steps': 31938, 'loss/train': 1.8874555826187134} 08/30/2021 19:01:13 - INFO - __main__ - Step 31940: {'lr': 0.00045119160357881105, 'samples': 6132480, 'steps': 31939, 'loss/train': 2.018998622894287} 08/30/2021 19:01:15 - INFO - __main__ - Step 31941: {'lr': 0.0004511884534944789, 'samples': 6132672, 'steps': 31940, 'loss/train': 1.4498368501663208} 08/30/2021 19:01:15 - INFO - __main__ - Step 31942: {'lr': 0.0004511853033194942, 'samples': 6132864, 'steps': 31941, 'loss/train': 2.2000842094421387} 08/30/2021 19:01:16 - INFO - __main__ - Step 31943: {'lr': 0.00045118215305385855, 'samples': 6133056, 'steps': 31942, 'loss/train': 1.9984976053237915} 08/30/2021 19:01:16 - INFO - __main__ - Step 31944: {'lr': 0.0004511790026975733, 'samples': 6133248, 'steps': 31943, 'loss/train': 5.456791400909424} 08/30/2021 19:01:16 - INFO - __main__ - Step 31945: {'lr': 0.00045117585225063996, 'samples': 6133440, 'steps': 31944, 'loss/train': 1.6796048879623413} 08/30/2021 19:01:18 - INFO - __main__ - Step 31946: {'lr': 0.0004511727017130598, 'samples': 6133632, 'steps': 31945, 'loss/train': 1.5475685596466064} 08/30/2021 19:01:19 - INFO - __main__ - Step 31947: {'lr': 0.00045116955108483436, 'samples': 6133824, 'steps': 31946, 'loss/train': 1.6737676858901978} 08/30/2021 19:01:19 - INFO - __main__ - Step 31948: {'lr': 0.00045116640036596507, 'samples': 6134016, 'steps': 31947, 'loss/train': 1.1156933307647705} 08/30/2021 19:01:20 - INFO - __main__ - Step 31949: {'lr': 0.0004511632495564533, 'samples': 6134208, 'steps': 31948, 'loss/train': 0.9910598993301392} 08/30/2021 19:01:20 - INFO - __main__ - Step 31950: {'lr': 0.00045116009865630034, 'samples': 6134400, 'steps': 31949, 'loss/train': 1.533393144607544} 08/30/2021 19:01:21 - INFO - __main__ - Step 31951: {'lr': 0.0004511569476655079, 'samples': 6134592, 'steps': 31950, 'loss/train': 1.2653424739837646} 08/30/2021 19:01:22 - INFO - __main__ - Step 31952: {'lr': 0.00045115379658407717, 'samples': 6134784, 'steps': 31951, 'loss/train': 1.8291164636611938} 08/30/2021 19:01:22 - INFO - __main__ - Step 31953: {'lr': 0.0004511506454120097, 'samples': 6134976, 'steps': 31952, 'loss/train': 1.805966854095459} 08/30/2021 19:01:23 - INFO - __main__ - Step 31954: {'lr': 0.00045114749414930676, 'samples': 6135168, 'steps': 31953, 'loss/train': 1.410210371017456} 08/30/2021 19:01:23 - INFO - __main__ - Step 31955: {'lr': 0.00045114434279596994, 'samples': 6135360, 'steps': 31954, 'loss/train': 1.5953606367111206} 08/30/2021 19:01:25 - INFO - __main__ - Step 31956: {'lr': 0.0004511411913520006, 'samples': 6135552, 'steps': 31955, 'loss/train': 1.5507489442825317} 08/30/2021 19:01:25 - INFO - __main__ - Step 31957: {'lr': 0.0004511380398174001, 'samples': 6135744, 'steps': 31956, 'loss/train': 0.03353830799460411} 08/30/2021 19:01:26 - INFO - __main__ - Step 31958: {'lr': 0.00045113488819216983, 'samples': 6135936, 'steps': 31957, 'loss/train': 0.0318821482360363} 08/30/2021 19:01:26 - INFO - __main__ - Step 31959: {'lr': 0.00045113173647631143, 'samples': 6136128, 'steps': 31958, 'loss/train': 0.9165999889373779} 08/30/2021 19:01:27 - INFO - __main__ - Step 31960: {'lr': 0.0004511285846698261, 'samples': 6136320, 'steps': 31959, 'loss/train': 1.3535188436508179} 08/30/2021 19:01:27 - INFO - __main__ - Step 31961: {'lr': 0.0004511254327727153, 'samples': 6136512, 'steps': 31960, 'loss/train': 1.6394740343093872} 08/30/2021 19:01:28 - INFO - __main__ - Step 31962: {'lr': 0.00045112228078498053, 'samples': 6136704, 'steps': 31961, 'loss/train': 1.3872450590133667} 08/30/2021 19:01:29 - INFO - __main__ - Step 31963: {'lr': 0.0004511191287066232, 'samples': 6136896, 'steps': 31962, 'loss/train': 1.816772222518921} 08/30/2021 19:01:29 - INFO - __main__ - Step 31964: {'lr': 0.00045111597653764456, 'samples': 6137088, 'steps': 31963, 'loss/train': 0.8778124451637268} 08/30/2021 19:01:30 - INFO - __main__ - Step 31965: {'lr': 0.00045111282427804636, 'samples': 6137280, 'steps': 31964, 'loss/train': 1.6676661968231201} 08/30/2021 19:01:30 - INFO - __main__ - Step 31966: {'lr': 0.0004511096719278297, 'samples': 6137472, 'steps': 31965, 'loss/train': 0.8720130324363708} 08/30/2021 19:01:30 - INFO - __main__ - Step 31967: {'lr': 0.0004511065194869961, 'samples': 6137664, 'steps': 31966, 'loss/train': 1.5493005514144897} 08/30/2021 19:01:32 - INFO - __main__ - Step 31968: {'lr': 0.00045110336695554707, 'samples': 6137856, 'steps': 31967, 'loss/train': 1.0071051120758057} 08/30/2021 19:01:33 - INFO - __main__ - Step 31969: {'lr': 0.0004511002143334839, 'samples': 6138048, 'steps': 31968, 'loss/train': 1.5522947311401367} 08/30/2021 19:01:33 - INFO - __main__ - Step 31970: {'lr': 0.0004510970616208081, 'samples': 6138240, 'steps': 31969, 'loss/train': 1.0230203866958618} 08/30/2021 19:01:33 - INFO - __main__ - Step 31971: {'lr': 0.0004510939088175211, 'samples': 6138432, 'steps': 31970, 'loss/train': 0.026159143075346947} 08/30/2021 19:01:34 - INFO - __main__ - Step 31972: {'lr': 0.00045109075592362433, 'samples': 6138624, 'steps': 31971, 'loss/train': 1.4281119108200073} 08/30/2021 19:01:34 - INFO - __main__ - Step 31973: {'lr': 0.0004510876029391191, 'samples': 6138816, 'steps': 31972, 'loss/train': 1.5089854001998901} 08/30/2021 19:01:36 - INFO - __main__ - Step 31974: {'lr': 0.00045108444986400687, 'samples': 6139008, 'steps': 31973, 'loss/train': 1.476694107055664} 08/30/2021 19:01:36 - INFO - __main__ - Step 31975: {'lr': 0.0004510812966982892, 'samples': 6139200, 'steps': 31974, 'loss/train': 1.355631947517395} 08/30/2021 19:01:36 - INFO - __main__ - Step 31976: {'lr': 0.0004510781434419673, 'samples': 6139392, 'steps': 31975, 'loss/train': 1.3529835939407349} 08/30/2021 19:01:37 - INFO - __main__ - Step 31977: {'lr': 0.0004510749900950427, 'samples': 6139584, 'steps': 31976, 'loss/train': 1.140531301498413} 08/30/2021 19:01:38 - INFO - __main__ - Step 31978: {'lr': 0.00045107183665751686, 'samples': 6139776, 'steps': 31977, 'loss/train': 1.628603219985962} 08/30/2021 19:01:39 - INFO - __main__ - Step 31979: {'lr': 0.00045106868312939116, 'samples': 6139968, 'steps': 31978, 'loss/train': 1.0013000965118408} 08/30/2021 19:01:39 - INFO - __main__ - Step 31980: {'lr': 0.0004510655295106669, 'samples': 6140160, 'steps': 31979, 'loss/train': 1.6773079633712769} 08/30/2021 19:01:39 - INFO - __main__ - Step 31981: {'lr': 0.00045106237580134573, 'samples': 6140352, 'steps': 31980, 'loss/train': 1.6410744190216064} 08/30/2021 19:01:40 - INFO - __main__ - Step 31982: {'lr': 0.000451059222001429, 'samples': 6140544, 'steps': 31981, 'loss/train': 1.2098348140716553} 08/30/2021 19:01:40 - INFO - __main__ - Step 31983: {'lr': 0.0004510560681109179, 'samples': 6140736, 'steps': 31982, 'loss/train': 0.9411579966545105} 08/30/2021 19:01:42 - INFO - __main__ - Step 31984: {'lr': 0.0004510529141298142, 'samples': 6140928, 'steps': 31983, 'loss/train': 1.4893128871917725} 08/30/2021 19:01:42 - INFO - __main__ - Step 31985: {'lr': 0.00045104976005811917, 'samples': 6141120, 'steps': 31984, 'loss/train': 1.3210407495498657} 08/30/2021 19:01:42 - INFO - __main__ - Step 31986: {'lr': 0.00045104660589583413, 'samples': 6141312, 'steps': 31985, 'loss/train': 1.7088764905929565} 08/30/2021 19:01:43 - INFO - __main__ - Step 31987: {'lr': 0.0004510434516429606, 'samples': 6141504, 'steps': 31986, 'loss/train': 1.774092197418213} 08/30/2021 19:01:43 - INFO - __main__ - Step 31988: {'lr': 0.0004510402972995, 'samples': 6141696, 'steps': 31987, 'loss/train': 1.4240888357162476} 08/30/2021 19:01:45 - INFO - __main__ - Step 31989: {'lr': 0.0004510371428654538, 'samples': 6141888, 'steps': 31988, 'loss/train': 1.5147643089294434} 08/30/2021 19:01:46 - INFO - __main__ - Step 31990: {'lr': 0.00045103398834082334, 'samples': 6142080, 'steps': 31989, 'loss/train': 1.8578299283981323} 08/30/2021 19:01:46 - INFO - __main__ - Step 31991: {'lr': 0.00045103083372561003, 'samples': 6142272, 'steps': 31990, 'loss/train': 2.1569173336029053} 08/30/2021 19:01:47 - INFO - __main__ - Step 31992: {'lr': 0.0004510276790198153, 'samples': 6142464, 'steps': 31991, 'loss/train': 1.225195050239563} 08/30/2021 19:01:47 - INFO - __main__ - Step 31993: {'lr': 0.00045102452422344065, 'samples': 6142656, 'steps': 31992, 'loss/train': 1.461816668510437} 08/30/2021 19:01:47 - INFO - __main__ - Step 31994: {'lr': 0.0004510213693364875, 'samples': 6142848, 'steps': 31993, 'loss/train': 1.9749394655227661} 08/30/2021 19:01:48 - INFO - __main__ - Step 31995: {'lr': 0.0004510182143589572, 'samples': 6143040, 'steps': 31994, 'loss/train': 0.16042234003543854} 08/30/2021 19:01:48 - INFO - __main__ - Step 31996: {'lr': 0.0004510150592908511, 'samples': 6143232, 'steps': 31995, 'loss/train': 0.06669739633798599} 08/30/2021 19:01:50 - INFO - __main__ - Step 31997: {'lr': 0.00045101190413217085, 'samples': 6143424, 'steps': 31996, 'loss/train': 0.023171178996562958} 08/30/2021 19:01:51 - INFO - __main__ - Step 31998: {'lr': 0.0004510087488829177, 'samples': 6143616, 'steps': 31997, 'loss/train': 1.195980191230774} 08/30/2021 19:01:51 - INFO - __main__ - Step 31999: {'lr': 0.000451005593543093, 'samples': 6143808, 'steps': 31998, 'loss/train': 1.0919106006622314} 08/30/2021 19:01:51 - INFO - __main__ - Step 32000: {'lr': 0.00045100243811269834, 'samples': 6144000, 'steps': 31999, 'loss/train': 2.045699119567871} 08/30/2021 19:01:52 - INFO - __main__ - Step 32001: {'lr': 0.00045099928259173516, 'samples': 6144192, 'steps': 32000, 'loss/train': 1.139817237854004} 08/30/2021 19:01:53 - INFO - __main__ - Step 32002: {'lr': 0.0004509961269802048, 'samples': 6144384, 'steps': 32001, 'loss/train': 0.9346404075622559} 08/30/2021 19:01:54 - INFO - __main__ - Step 32003: {'lr': 0.00045099297127810855, 'samples': 6144576, 'steps': 32002, 'loss/train': 1.5782743692398071} 08/30/2021 19:01:54 - INFO - __main__ - Step 32004: {'lr': 0.0004509898154854481, 'samples': 6144768, 'steps': 32003, 'loss/train': 2.0786890983581543} 08/30/2021 19:01:55 - INFO - __main__ - Step 32005: {'lr': 0.00045098665960222474, 'samples': 6144960, 'steps': 32004, 'loss/train': 0.2444913387298584} 08/30/2021 19:01:55 - INFO - __main__ - Step 32006: {'lr': 0.00045098350362843975, 'samples': 6145152, 'steps': 32005, 'loss/train': 1.8713760375976562} 08/30/2021 19:01:57 - INFO - __main__ - Step 32007: {'lr': 0.0004509803475640948, 'samples': 6145344, 'steps': 32006, 'loss/train': 1.7312630414962769} 08/30/2021 19:01:57 - INFO - __main__ - Step 32008: {'lr': 0.00045097719140919126, 'samples': 6145536, 'steps': 32007, 'loss/train': 1.240100622177124} 08/30/2021 19:01:57 - INFO - __main__ - Step 32009: {'lr': 0.0004509740351637304, 'samples': 6145728, 'steps': 32008, 'loss/train': 1.5063472986221313} 08/30/2021 19:01:58 - INFO - __main__ - Step 32010: {'lr': 0.0004509708788277138, 'samples': 6145920, 'steps': 32009, 'loss/train': 1.406972050666809} 08/30/2021 19:01:58 - INFO - __main__ - Step 32011: {'lr': 0.0004509677224011428, 'samples': 6146112, 'steps': 32010, 'loss/train': 0.5182023048400879} 08/30/2021 19:01:59 - INFO - __main__ - Step 32012: {'lr': 0.00045096456588401883, 'samples': 6146304, 'steps': 32011, 'loss/train': 1.0053365230560303} 08/30/2021 19:02:00 - INFO - __main__ - Step 32013: {'lr': 0.0004509614092763434, 'samples': 6146496, 'steps': 32012, 'loss/train': 1.512039303779602} 08/30/2021 19:02:00 - INFO - __main__ - Step 32014: {'lr': 0.00045095825257811776, 'samples': 6146688, 'steps': 32013, 'loss/train': 1.7275587320327759} 08/30/2021 19:02:01 - INFO - __main__ - Step 32015: {'lr': 0.00045095509578934353, 'samples': 6146880, 'steps': 32014, 'loss/train': 1.5785534381866455} 08/30/2021 19:02:01 - INFO - __main__ - Step 32016: {'lr': 0.00045095193891002194, 'samples': 6147072, 'steps': 32015, 'loss/train': 1.0299241542816162} 08/30/2021 19:02:03 - INFO - __main__ - Step 32017: {'lr': 0.00045094878194015456, 'samples': 6147264, 'steps': 32016, 'loss/train': 1.275549292564392} 08/30/2021 19:02:03 - INFO - __main__ - Step 32018: {'lr': 0.0004509456248797428, 'samples': 6147456, 'steps': 32017, 'loss/train': 1.5068910121917725} 08/30/2021 19:02:03 - INFO - __main__ - Step 32019: {'lr': 0.000450942467728788, 'samples': 6147648, 'steps': 32018, 'loss/train': 1.353131890296936} 08/30/2021 19:02:04 - INFO - __main__ - Step 32020: {'lr': 0.00045093931048729156, 'samples': 6147840, 'steps': 32019, 'loss/train': 1.4195904731750488} 08/30/2021 19:02:04 - INFO - __main__ - Step 32021: {'lr': 0.00045093615315525506, 'samples': 6148032, 'steps': 32020, 'loss/train': 2.2784926891326904} 08/30/2021 19:02:06 - INFO - __main__ - Step 32022: {'lr': 0.00045093299573267977, 'samples': 6148224, 'steps': 32021, 'loss/train': 1.4593552350997925} 08/30/2021 19:02:06 - INFO - __main__ - Step 32023: {'lr': 0.00045092983821956725, 'samples': 6148416, 'steps': 32022, 'loss/train': 1.4830538034439087} 08/30/2021 19:02:07 - INFO - __main__ - Step 32024: {'lr': 0.00045092668061591875, 'samples': 6148608, 'steps': 32023, 'loss/train': 1.3781323432922363} 08/30/2021 19:02:07 - INFO - __main__ - Step 32025: {'lr': 0.00045092352292173585, 'samples': 6148800, 'steps': 32024, 'loss/train': 1.6769580841064453} 08/30/2021 19:02:07 - INFO - __main__ - Step 32026: {'lr': 0.00045092036513701985, 'samples': 6148992, 'steps': 32025, 'loss/train': 1.435570240020752} 08/30/2021 19:02:08 - INFO - __main__ - Step 32027: {'lr': 0.0004509172072617723, 'samples': 6149184, 'steps': 32026, 'loss/train': 1.203198790550232} 08/30/2021 19:02:09 - INFO - __main__ - Step 32028: {'lr': 0.00045091404929599455, 'samples': 6149376, 'steps': 32027, 'loss/train': 0.8941290378570557} 08/30/2021 19:02:10 - INFO - __main__ - Step 32029: {'lr': 0.00045091089123968796, 'samples': 6149568, 'steps': 32028, 'loss/train': 1.23170006275177} 08/30/2021 19:02:10 - INFO - __main__ - Step 32030: {'lr': 0.0004509077330928541, 'samples': 6149760, 'steps': 32029, 'loss/train': 1.4482344388961792} 08/30/2021 19:02:11 - INFO - __main__ - Step 32031: {'lr': 0.0004509045748554943, 'samples': 6149952, 'steps': 32030, 'loss/train': 3.8524041175842285} 08/30/2021 19:02:11 - INFO - __main__ - Step 32032: {'lr': 0.00045090141652760995, 'samples': 6150144, 'steps': 32031, 'loss/train': 0.08425921946763992} 08/30/2021 19:02:12 - INFO - __main__ - Step 32033: {'lr': 0.0004508982581092026, 'samples': 6150336, 'steps': 32032, 'loss/train': 0.8093934059143066} 08/30/2021 19:02:13 - INFO - __main__ - Step 32034: {'lr': 0.00045089509960027354, 'samples': 6150528, 'steps': 32033, 'loss/train': 2.8101725578308105} 08/30/2021 19:02:13 - INFO - __main__ - Step 32035: {'lr': 0.00045089194100082433, 'samples': 6150720, 'steps': 32034, 'loss/train': 1.4310811758041382} 08/30/2021 19:02:14 - INFO - __main__ - Step 32036: {'lr': 0.00045088878231085616, 'samples': 6150912, 'steps': 32035, 'loss/train': 1.7447528839111328} 08/30/2021 19:02:14 - INFO - __main__ - Step 32037: {'lr': 0.00045088562353037077, 'samples': 6151104, 'steps': 32036, 'loss/train': 1.4019067287445068} 08/30/2021 19:02:16 - INFO - __main__ - Step 32038: {'lr': 0.00045088246465936936, 'samples': 6151296, 'steps': 32037, 'loss/train': 1.4390467405319214} 08/30/2021 19:02:16 - INFO - __main__ - Step 32039: {'lr': 0.0004508793056978534, 'samples': 6151488, 'steps': 32038, 'loss/train': 1.354805588722229} 08/30/2021 19:02:16 - INFO - __main__ - Step 32040: {'lr': 0.00045087614664582424, 'samples': 6151680, 'steps': 32039, 'loss/train': 1.8440057039260864} 08/30/2021 19:02:17 - INFO - __main__ - Step 32041: {'lr': 0.0004508729875032834, 'samples': 6151872, 'steps': 32040, 'loss/train': 1.1266757249832153} 08/30/2021 19:02:17 - INFO - __main__ - Step 32042: {'lr': 0.0004508698282702324, 'samples': 6152064, 'steps': 32041, 'loss/train': 1.6667054891586304} 08/30/2021 19:02:17 - INFO - __main__ - Step 32043: {'lr': 0.0004508666689466725, 'samples': 6152256, 'steps': 32042, 'loss/train': 1.7821850776672363} 08/30/2021 19:02:19 - INFO - __main__ - Step 32044: {'lr': 0.00045086350953260526, 'samples': 6152448, 'steps': 32043, 'loss/train': 1.315334439277649} 08/30/2021 19:02:20 - INFO - __main__ - Step 32045: {'lr': 0.0004508603500280319, 'samples': 6152640, 'steps': 32044, 'loss/train': 1.6057698726654053} 08/30/2021 19:02:20 - INFO - __main__ - Step 32046: {'lr': 0.00045085719043295406, 'samples': 6152832, 'steps': 32045, 'loss/train': 1.2984144687652588} 08/30/2021 19:02:20 - INFO - __main__ - Step 32047: {'lr': 0.00045085403074737295, 'samples': 6153024, 'steps': 32046, 'loss/train': 1.811688780784607} 08/30/2021 19:02:21 - INFO - __main__ - Step 32048: {'lr': 0.0004508508709712902, 'samples': 6153216, 'steps': 32047, 'loss/train': 1.1277586221694946} 08/30/2021 19:02:22 - INFO - __main__ - Step 32049: {'lr': 0.00045084771110470717, 'samples': 6153408, 'steps': 32048, 'loss/train': 2.0934958457946777} 08/30/2021 19:02:22 - INFO - __main__ - Step 32050: {'lr': 0.00045084455114762525, 'samples': 6153600, 'steps': 32049, 'loss/train': 1.2152059078216553} 08/30/2021 19:02:23 - INFO - __main__ - Step 32051: {'lr': 0.00045084139110004585, 'samples': 6153792, 'steps': 32050, 'loss/train': 1.2711853981018066} 08/30/2021 19:02:23 - INFO - __main__ - Step 32052: {'lr': 0.0004508382309619704, 'samples': 6153984, 'steps': 32051, 'loss/train': 2.048680067062378} 08/30/2021 19:02:23 - INFO - __main__ - Step 32053: {'lr': 0.0004508350707334004, 'samples': 6154176, 'steps': 32052, 'loss/train': 2.0509331226348877} 08/30/2021 19:02:24 - INFO - __main__ - Step 32054: {'lr': 0.00045083191041433713, 'samples': 6154368, 'steps': 32053, 'loss/train': 2.210904836654663} 08/30/2021 19:02:26 - INFO - __main__ - Step 32055: {'lr': 0.00045082875000478214, 'samples': 6154560, 'steps': 32054, 'loss/train': 1.6762771606445312} 08/30/2021 19:02:26 - INFO - __main__ - Step 32056: {'lr': 0.0004508255895047368, 'samples': 6154752, 'steps': 32055, 'loss/train': 0.9115856885910034} 08/30/2021 19:02:27 - INFO - __main__ - Step 32057: {'lr': 0.0004508224289142026, 'samples': 6154944, 'steps': 32056, 'loss/train': 0.8742789030075073} 08/30/2021 19:02:27 - INFO - __main__ - Step 32058: {'lr': 0.0004508192682331809, 'samples': 6155136, 'steps': 32057, 'loss/train': 1.793533444404602} 08/30/2021 19:02:28 - INFO - __main__ - Step 32059: {'lr': 0.0004508161074616731, 'samples': 6155328, 'steps': 32058, 'loss/train': 1.273215413093567} 08/30/2021 19:02:29 - INFO - __main__ - Step 32060: {'lr': 0.0004508129465996806, 'samples': 6155520, 'steps': 32059, 'loss/train': 0.08419208973646164} 08/30/2021 19:02:30 - INFO - __main__ - Step 32061: {'lr': 0.00045080978564720505, 'samples': 6155712, 'steps': 32060, 'loss/train': 0.8683608174324036} 08/30/2021 19:02:30 - INFO - __main__ - Step 32062: {'lr': 0.0004508066246042476, 'samples': 6155904, 'steps': 32061, 'loss/train': 1.8320715427398682} 08/30/2021 19:02:30 - INFO - __main__ - Step 32063: {'lr': 0.0004508034634708098, 'samples': 6156096, 'steps': 32062, 'loss/train': 1.0917303562164307} 08/30/2021 19:02:31 - INFO - __main__ - Step 32064: {'lr': 0.0004508003022468931, 'samples': 6156288, 'steps': 32063, 'loss/train': 0.8496731519699097} 08/30/2021 19:02:32 - INFO - __main__ - Step 32065: {'lr': 0.00045079714093249887, 'samples': 6156480, 'steps': 32064, 'loss/train': 1.7927823066711426} 08/30/2021 19:02:33 - INFO - __main__ - Step 32066: {'lr': 0.00045079397952762845, 'samples': 6156672, 'steps': 32065, 'loss/train': 1.335373044013977} 08/30/2021 19:02:33 - INFO - __main__ - Step 32067: {'lr': 0.0004507908180322835, 'samples': 6156864, 'steps': 32066, 'loss/train': 1.1555590629577637} 08/30/2021 19:02:33 - INFO - __main__ - Step 32068: {'lr': 0.00045078765644646524, 'samples': 6157056, 'steps': 32067, 'loss/train': 1.8896679878234863} 08/30/2021 19:02:34 - INFO - __main__ - Step 32069: {'lr': 0.00045078449477017516, 'samples': 6157248, 'steps': 32068, 'loss/train': 1.0979979038238525} 08/30/2021 19:02:36 - INFO - __main__ - Step 32070: {'lr': 0.0004507813330034147, 'samples': 6157440, 'steps': 32069, 'loss/train': 1.8681769371032715} 08/30/2021 19:02:36 - INFO - __main__ - Step 32071: {'lr': 0.00045077817114618526, 'samples': 6157632, 'steps': 32070, 'loss/train': 1.4490727186203003} 08/30/2021 19:02:36 - INFO - __main__ - Step 32072: {'lr': 0.00045077500919848826, 'samples': 6157824, 'steps': 32071, 'loss/train': 1.6575084924697876} 08/30/2021 19:02:37 - INFO - __main__ - Step 32073: {'lr': 0.00045077184716032516, 'samples': 6158016, 'steps': 32072, 'loss/train': 1.455581545829773} 08/30/2021 19:02:37 - INFO - __main__ - Step 32074: {'lr': 0.0004507686850316973, 'samples': 6158208, 'steps': 32073, 'loss/train': 1.3231428861618042} 08/30/2021 19:02:37 - INFO - __main__ - Step 32075: {'lr': 0.00045076552281260625, 'samples': 6158400, 'steps': 32074, 'loss/train': 0.9537262320518494} 08/30/2021 19:02:39 - INFO - __main__ - Step 32076: {'lr': 0.0004507623605030533, 'samples': 6158592, 'steps': 32075, 'loss/train': 5.491367340087891} 08/30/2021 19:02:39 - INFO - __main__ - Step 32077: {'lr': 0.00045075919810304, 'samples': 6158784, 'steps': 32076, 'loss/train': 1.324520468711853} 08/30/2021 19:02:40 - INFO - __main__ - Step 32078: {'lr': 0.0004507560356125676, 'samples': 6158976, 'steps': 32077, 'loss/train': 1.9875439405441284} 08/30/2021 19:02:40 - INFO - __main__ - Step 32079: {'lr': 0.0004507528730316377, 'samples': 6159168, 'steps': 32078, 'loss/train': 1.4204699993133545} 08/30/2021 19:02:40 - INFO - __main__ - Step 32080: {'lr': 0.0004507497103602517, 'samples': 6159360, 'steps': 32079, 'loss/train': 1.8378013372421265} 08/30/2021 19:02:42 - INFO - __main__ - Step 32081: {'lr': 0.00045074654759841087, 'samples': 6159552, 'steps': 32080, 'loss/train': 1.4169636964797974} 08/30/2021 19:02:43 - INFO - __main__ - Step 32082: {'lr': 0.00045074338474611683, 'samples': 6159744, 'steps': 32081, 'loss/train': 1.7404274940490723} 08/30/2021 19:02:43 - INFO - __main__ - Step 32083: {'lr': 0.00045074022180337085, 'samples': 6159936, 'steps': 32082, 'loss/train': 0.18177993595600128} 08/30/2021 19:02:43 - INFO - __main__ - Step 32084: {'lr': 0.0004507370587701745, 'samples': 6160128, 'steps': 32083, 'loss/train': 1.4592140913009644} 08/30/2021 19:02:44 - INFO - __main__ - Step 32085: {'lr': 0.000450733895646529, 'samples': 6160320, 'steps': 32084, 'loss/train': 1.0784831047058105} 08/30/2021 19:02:45 - INFO - __main__ - Step 32086: {'lr': 0.00045073073243243603, 'samples': 6160512, 'steps': 32085, 'loss/train': 1.1648410558700562} 08/30/2021 19:02:45 - INFO - __main__ - Step 32087: {'lr': 0.0004507275691278968, 'samples': 6160704, 'steps': 32086, 'loss/train': 1.5367395877838135} 08/30/2021 19:02:46 - INFO - __main__ - Step 32088: {'lr': 0.00045072440573291293, 'samples': 6160896, 'steps': 32087, 'loss/train': 0.9820032119750977} 08/30/2021 19:02:46 - INFO - __main__ - Step 32089: {'lr': 0.0004507212422474857, 'samples': 6161088, 'steps': 32088, 'loss/train': 1.3043065071105957} 08/30/2021 19:02:46 - INFO - __main__ - Step 32090: {'lr': 0.0004507180786716165, 'samples': 6161280, 'steps': 32089, 'loss/train': 1.593130350112915} 08/30/2021 19:02:48 - INFO - __main__ - Step 32091: {'lr': 0.00045071491500530694, 'samples': 6161472, 'steps': 32090, 'loss/train': 1.9413312673568726} 08/30/2021 19:02:48 - INFO - __main__ - Step 32092: {'lr': 0.0004507117512485582, 'samples': 6161664, 'steps': 32091, 'loss/train': 1.3542094230651855} 08/30/2021 19:02:49 - INFO - __main__ - Step 32093: {'lr': 0.000450708587401372, 'samples': 6161856, 'steps': 32092, 'loss/train': 1.2892329692840576} 08/30/2021 19:02:49 - INFO - __main__ - Step 32094: {'lr': 0.0004507054234637495, 'samples': 6162048, 'steps': 32093, 'loss/train': 1.6318327188491821} 08/30/2021 19:02:49 - INFO - __main__ - Step 32095: {'lr': 0.0004507022594356922, 'samples': 6162240, 'steps': 32094, 'loss/train': 1.459619164466858} 08/30/2021 19:02:51 - INFO - __main__ - Step 32096: {'lr': 0.00045069909531720166, 'samples': 6162432, 'steps': 32095, 'loss/train': 1.9088743925094604} 08/30/2021 19:02:51 - INFO - __main__ - Step 32097: {'lr': 0.0004506959311082792, 'samples': 6162624, 'steps': 32096, 'loss/train': 2.1389622688293457} 08/30/2021 19:02:52 - INFO - __main__ - Step 32098: {'lr': 0.00045069276680892624, 'samples': 6162816, 'steps': 32097, 'loss/train': 1.6033211946487427} 08/30/2021 19:02:52 - INFO - __main__ - Step 32099: {'lr': 0.00045068960241914413, 'samples': 6163008, 'steps': 32098, 'loss/train': 1.2506165504455566} 08/30/2021 19:02:52 - INFO - __main__ - Step 32100: {'lr': 0.00045068643793893447, 'samples': 6163200, 'steps': 32099, 'loss/train': 1.2278567552566528} 08/30/2021 19:02:54 - INFO - __main__ - Step 32101: {'lr': 0.0004506832733682986, 'samples': 6163392, 'steps': 32100, 'loss/train': 0.6025732159614563} 08/30/2021 19:02:55 - INFO - __main__ - Step 32102: {'lr': 0.00045068010870723783, 'samples': 6163584, 'steps': 32101, 'loss/train': 0.7777771353721619} 08/30/2021 19:02:55 - INFO - __main__ - Step 32103: {'lr': 0.00045067694395575385, 'samples': 6163776, 'steps': 32102, 'loss/train': 1.4369356632232666} 08/30/2021 19:02:55 - INFO - __main__ - Step 32104: {'lr': 0.0004506737791138479, 'samples': 6163968, 'steps': 32103, 'loss/train': 1.3069368600845337} 08/30/2021 19:02:56 - INFO - __main__ - Step 32105: {'lr': 0.00045067061418152136, 'samples': 6164160, 'steps': 32104, 'loss/train': 1.2212883234024048} 08/30/2021 19:02:58 - INFO - __main__ - Step 32106: {'lr': 0.00045066744915877585, 'samples': 6164352, 'steps': 32105, 'loss/train': 1.1055688858032227} 08/30/2021 19:02:58 - INFO - __main__ - Step 32107: {'lr': 0.0004506642840456126, 'samples': 6164544, 'steps': 32106, 'loss/train': 1.4533751010894775} 08/30/2021 19:02:58 - INFO - __main__ - Step 32108: {'lr': 0.00045066111884203315, 'samples': 6164736, 'steps': 32107, 'loss/train': 1.2181884050369263} 08/30/2021 19:02:59 - INFO - __main__ - Step 32109: {'lr': 0.0004506579535480389, 'samples': 6164928, 'steps': 32108, 'loss/train': 1.562153935432434} 08/30/2021 19:02:59 - INFO - __main__ - Step 32110: {'lr': 0.00045065478816363124, 'samples': 6165120, 'steps': 32109, 'loss/train': 1.656476616859436} 08/30/2021 19:03:01 - INFO - __main__ - Step 32111: {'lr': 0.00045065162268881164, 'samples': 6165312, 'steps': 32110, 'loss/train': 1.3008641004562378} 08/30/2021 19:03:01 - INFO - __main__ - Step 32112: {'lr': 0.0004506484571235816, 'samples': 6165504, 'steps': 32111, 'loss/train': 1.7591400146484375} 08/30/2021 19:03:02 - INFO - __main__ - Step 32113: {'lr': 0.00045064529146794234, 'samples': 6165696, 'steps': 32112, 'loss/train': 1.3816057443618774} 08/30/2021 19:03:02 - INFO - __main__ - Step 32114: {'lr': 0.0004506421257218955, 'samples': 6165888, 'steps': 32113, 'loss/train': 3.6256494522094727} 08/30/2021 19:03:02 - INFO - __main__ - Step 32115: {'lr': 0.00045063895988544235, 'samples': 6166080, 'steps': 32114, 'loss/train': 1.3191349506378174} 08/30/2021 19:03:03 - INFO - __main__ - Step 32116: {'lr': 0.00045063579395858444, 'samples': 6166272, 'steps': 32115, 'loss/train': 1.3613029718399048} 08/30/2021 19:03:04 - INFO - __main__ - Step 32117: {'lr': 0.0004506326279413231, 'samples': 6166464, 'steps': 32116, 'loss/train': 1.834302306175232} 08/30/2021 19:03:05 - INFO - __main__ - Step 32118: {'lr': 0.0004506294618336598, 'samples': 6166656, 'steps': 32117, 'loss/train': 0.11802104115486145} 08/30/2021 19:03:05 - INFO - __main__ - Step 32119: {'lr': 0.00045062629563559595, 'samples': 6166848, 'steps': 32118, 'loss/train': 1.7002917528152466} 08/30/2021 19:03:06 - INFO - __main__ - Step 32120: {'lr': 0.00045062312934713303, 'samples': 6167040, 'steps': 32119, 'loss/train': 1.4887988567352295} 08/30/2021 19:03:06 - INFO - __main__ - Step 32121: {'lr': 0.00045061996296827237, 'samples': 6167232, 'steps': 32120, 'loss/train': 1.649009346961975} 08/30/2021 19:03:08 - INFO - __main__ - Step 32122: {'lr': 0.00045061679649901543, 'samples': 6167424, 'steps': 32121, 'loss/train': 2.261502265930176} 08/30/2021 19:03:08 - INFO - __main__ - Step 32123: {'lr': 0.00045061362993936374, 'samples': 6167616, 'steps': 32122, 'loss/train': 1.179837703704834} 08/30/2021 19:03:08 - INFO - __main__ - Step 32124: {'lr': 0.0004506104632893185, 'samples': 6167808, 'steps': 32123, 'loss/train': 1.4686287641525269} 08/30/2021 19:03:09 - INFO - __main__ - Step 32125: {'lr': 0.00045060729654888143, 'samples': 6168000, 'steps': 32124, 'loss/train': 1.6186310052871704} 08/30/2021 19:03:09 - INFO - __main__ - Step 32126: {'lr': 0.00045060412971805375, 'samples': 6168192, 'steps': 32125, 'loss/train': 1.0545690059661865} 08/30/2021 19:03:11 - INFO - __main__ - Step 32127: {'lr': 0.00045060096279683694, 'samples': 6168384, 'steps': 32126, 'loss/train': 0.5160688757896423} 08/30/2021 19:03:11 - INFO - __main__ - Step 32128: {'lr': 0.0004505977957852325, 'samples': 6168576, 'steps': 32127, 'loss/train': 1.461456298828125} 08/30/2021 19:03:11 - INFO - __main__ - Step 32129: {'lr': 0.00045059462868324177, 'samples': 6168768, 'steps': 32128, 'loss/train': 0.7838690280914307} 08/30/2021 19:03:12 - INFO - __main__ - Step 32130: {'lr': 0.00045059146149086605, 'samples': 6168960, 'steps': 32129, 'loss/train': 0.9849536418914795} 08/30/2021 19:03:12 - INFO - __main__ - Step 32131: {'lr': 0.00045058829420810707, 'samples': 6169152, 'steps': 32130, 'loss/train': 0.9749042391777039} 08/30/2021 19:03:14 - INFO - __main__ - Step 32132: {'lr': 0.00045058512683496607, 'samples': 6169344, 'steps': 32131, 'loss/train': 1.6814159154891968} 08/30/2021 19:03:14 - INFO - __main__ - Step 32133: {'lr': 0.00045058195937144446, 'samples': 6169536, 'steps': 32132, 'loss/train': 1.3760607242584229} 08/30/2021 19:03:14 - INFO - __main__ - Step 32134: {'lr': 0.00045057879181754375, 'samples': 6169728, 'steps': 32133, 'loss/train': 1.2447855472564697} 08/30/2021 19:03:15 - INFO - __main__ - Step 32135: {'lr': 0.0004505756241732653, 'samples': 6169920, 'steps': 32134, 'loss/train': 1.3355622291564941} 08/30/2021 19:03:15 - INFO - __main__ - Step 32136: {'lr': 0.0004505724564386106, 'samples': 6170112, 'steps': 32135, 'loss/train': 1.7124855518341064} 08/30/2021 19:03:17 - INFO - __main__ - Step 32137: {'lr': 0.00045056928861358106, 'samples': 6170304, 'steps': 32136, 'loss/train': 1.301585078239441} 08/30/2021 19:03:17 - INFO - __main__ - Step 32138: {'lr': 0.000450566120698178, 'samples': 6170496, 'steps': 32137, 'loss/train': 1.8446447849273682} 08/30/2021 19:03:17 - INFO - __main__ - Step 32139: {'lr': 0.0004505629526924031, 'samples': 6170688, 'steps': 32138, 'loss/train': 1.005651593208313} 08/30/2021 19:03:18 - INFO - __main__ - Step 32140: {'lr': 0.0004505597845962575, 'samples': 6170880, 'steps': 32139, 'loss/train': 1.6745375394821167} 08/30/2021 19:03:18 - INFO - __main__ - Step 32141: {'lr': 0.0004505566164097428, 'samples': 6171072, 'steps': 32140, 'loss/train': 1.7593958377838135} 08/30/2021 19:03:20 - INFO - __main__ - Step 32142: {'lr': 0.0004505534481328604, 'samples': 6171264, 'steps': 32141, 'loss/train': 1.1630038022994995} 08/30/2021 19:03:20 - INFO - __main__ - Step 32143: {'lr': 0.0004505502797656117, 'samples': 6171456, 'steps': 32142, 'loss/train': 1.2246348857879639} 08/30/2021 19:03:21 - INFO - __main__ - Step 32144: {'lr': 0.00045054711130799806, 'samples': 6171648, 'steps': 32143, 'loss/train': 1.1393463611602783} 08/30/2021 19:03:21 - INFO - __main__ - Step 32145: {'lr': 0.00045054394276002106, 'samples': 6171840, 'steps': 32144, 'loss/train': 1.0095564126968384} 08/30/2021 19:03:21 - INFO - __main__ - Step 32146: {'lr': 0.00045054077412168215, 'samples': 6172032, 'steps': 32145, 'loss/train': 0.8614693880081177} 08/30/2021 19:03:22 - INFO - __main__ - Step 32147: {'lr': 0.0004505376053929825, 'samples': 6172224, 'steps': 32146, 'loss/train': 1.3967212438583374} 08/30/2021 19:03:24 - INFO - __main__ - Step 32148: {'lr': 0.0004505344365739238, 'samples': 6172416, 'steps': 32147, 'loss/train': 1.4298518896102905} 08/30/2021 19:03:24 - INFO - __main__ - Step 32149: {'lr': 0.0004505312676645073, 'samples': 6172608, 'steps': 32148, 'loss/train': 1.7533395290374756} 08/30/2021 19:03:24 - INFO - __main__ - Step 32150: {'lr': 0.00045052809866473454, 'samples': 6172800, 'steps': 32149, 'loss/train': 1.2677139043807983} 08/30/2021 19:03:25 - INFO - __main__ - Step 32151: {'lr': 0.00045052492957460696, 'samples': 6172992, 'steps': 32150, 'loss/train': 2.278658390045166} 08/30/2021 19:03:25 - INFO - __main__ - Step 32152: {'lr': 0.00045052176039412587, 'samples': 6173184, 'steps': 32151, 'loss/train': 1.4786430597305298} 08/30/2021 19:03:25 - INFO - __main__ - Step 32153: {'lr': 0.0004505185911232928, 'samples': 6173376, 'steps': 32152, 'loss/train': 0.9608216881752014} 08/30/2021 19:03:27 - INFO - __main__ - Step 32154: {'lr': 0.00045051542176210914, 'samples': 6173568, 'steps': 32153, 'loss/train': 1.5493953227996826} 08/30/2021 19:03:28 - INFO - __main__ - Step 32155: {'lr': 0.0004505122523105764, 'samples': 6173760, 'steps': 32154, 'loss/train': 1.5346219539642334} 08/30/2021 19:03:28 - INFO - __main__ - Step 32156: {'lr': 0.00045050908276869585, 'samples': 6173952, 'steps': 32155, 'loss/train': 1.8279955387115479} 08/30/2021 19:03:28 - INFO - __main__ - Step 32157: {'lr': 0.0004505059131364689, 'samples': 6174144, 'steps': 32156, 'loss/train': 1.3577688932418823} 08/30/2021 19:03:29 - INFO - __main__ - Step 32158: {'lr': 0.00045050274341389726, 'samples': 6174336, 'steps': 32157, 'loss/train': 1.3958837985992432} 08/30/2021 19:03:31 - INFO - __main__ - Step 32159: {'lr': 0.00045049957360098207, 'samples': 6174528, 'steps': 32158, 'loss/train': 1.30253267288208} 08/30/2021 19:03:31 - INFO - __main__ - Step 32160: {'lr': 0.0004504964036977249, 'samples': 6174720, 'steps': 32159, 'loss/train': 3.0469815731048584} 08/30/2021 19:03:32 - INFO - __main__ - Step 32161: {'lr': 0.00045049323370412723, 'samples': 6174912, 'steps': 32160, 'loss/train': 1.4968340396881104} 08/30/2021 19:03:32 - INFO - __main__ - Step 32162: {'lr': 0.0004504900636201903, 'samples': 6175104, 'steps': 32161, 'loss/train': 1.395896315574646} 08/30/2021 19:03:32 - INFO - __main__ - Step 32163: {'lr': 0.00045048689344591566, 'samples': 6175296, 'steps': 32162, 'loss/train': 1.3904894590377808} 08/30/2021 19:03:34 - INFO - __main__ - Step 32164: {'lr': 0.0004504837231813047, 'samples': 6175488, 'steps': 32163, 'loss/train': 1.5604084730148315} 08/30/2021 19:03:34 - INFO - __main__ - Step 32165: {'lr': 0.0004504805528263589, 'samples': 6175680, 'steps': 32164, 'loss/train': 1.279072642326355} 08/30/2021 19:03:35 - INFO - __main__ - Step 32166: {'lr': 0.00045047738238107967, 'samples': 6175872, 'steps': 32165, 'loss/train': 1.3723299503326416} 08/30/2021 19:03:35 - INFO - __main__ - Step 32167: {'lr': 0.00045047421184546844, 'samples': 6176064, 'steps': 32166, 'loss/train': 1.8364002704620361} 08/30/2021 19:03:35 - INFO - __main__ - Step 32168: {'lr': 0.0004504710412195265, 'samples': 6176256, 'steps': 32167, 'loss/train': 1.8371309041976929} 08/30/2021 19:03:36 - INFO - __main__ - Step 32169: {'lr': 0.00045046787050325555, 'samples': 6176448, 'steps': 32168, 'loss/train': 1.905853509902954} 08/30/2021 19:03:37 - INFO - __main__ - Step 32170: {'lr': 0.0004504646996966568, 'samples': 6176640, 'steps': 32169, 'loss/train': 1.547277569770813} 08/30/2021 19:03:38 - INFO - __main__ - Step 32171: {'lr': 0.0004504615287997318, 'samples': 6176832, 'steps': 32170, 'loss/train': 1.544297456741333} 08/30/2021 19:03:38 - INFO - __main__ - Step 32172: {'lr': 0.00045045835781248184, 'samples': 6177024, 'steps': 32171, 'loss/train': 1.3578882217407227} 08/30/2021 19:03:38 - INFO - __main__ - Step 32173: {'lr': 0.0004504551867349085, 'samples': 6177216, 'steps': 32172, 'loss/train': 1.6245187520980835} 08/30/2021 19:03:40 - INFO - __main__ - Step 32174: {'lr': 0.0004504520155670131, 'samples': 6177408, 'steps': 32173, 'loss/train': 1.0880186557769775} 08/30/2021 19:03:40 - INFO - __main__ - Step 32175: {'lr': 0.0004504488443087972, 'samples': 6177600, 'steps': 32174, 'loss/train': 1.7720310688018799} 08/30/2021 19:03:41 - INFO - __main__ - Step 32176: {'lr': 0.00045044567296026206, 'samples': 6177792, 'steps': 32175, 'loss/train': 1.6322996616363525} 08/30/2021 19:03:41 - INFO - __main__ - Step 32177: {'lr': 0.0004504425015214092, 'samples': 6177984, 'steps': 32176, 'loss/train': 1.562922716140747} 08/30/2021 19:03:42 - INFO - __main__ - Step 32178: {'lr': 0.00045043932999224015, 'samples': 6178176, 'steps': 32177, 'loss/train': 1.3139508962631226} 08/30/2021 19:03:42 - INFO - __main__ - Step 32179: {'lr': 0.00045043615837275607, 'samples': 6178368, 'steps': 32178, 'loss/train': 1.8337661027908325} 08/30/2021 19:03:44 - INFO - __main__ - Step 32180: {'lr': 0.0004504329866629586, 'samples': 6178560, 'steps': 32179, 'loss/train': 1.4523018598556519} 08/30/2021 19:03:44 - INFO - __main__ - Step 32181: {'lr': 0.0004504298148628492, 'samples': 6178752, 'steps': 32180, 'loss/train': 1.5806210041046143} 08/30/2021 19:03:44 - INFO - __main__ - Step 32182: {'lr': 0.0004504266429724292, 'samples': 6178944, 'steps': 32181, 'loss/train': 0.7032216787338257} 08/30/2021 19:03:45 - INFO - __main__ - Step 32183: {'lr': 0.0004504234709917, 'samples': 6179136, 'steps': 32182, 'loss/train': 1.7409673929214478} 08/30/2021 19:03:45 - INFO - __main__ - Step 32184: {'lr': 0.00045042029892066306, 'samples': 6179328, 'steps': 32183, 'loss/train': 1.07532799243927} 08/30/2021 19:03:47 - INFO - __main__ - Step 32185: {'lr': 0.00045041712675931983, 'samples': 6179520, 'steps': 32184, 'loss/train': 1.0329475402832031} 08/30/2021 19:03:47 - INFO - __main__ - Step 32186: {'lr': 0.0004504139545076717, 'samples': 6179712, 'steps': 32185, 'loss/train': 0.66080242395401} 08/30/2021 19:03:47 - INFO - __main__ - Step 32187: {'lr': 0.0004504107821657203, 'samples': 6179904, 'steps': 32186, 'loss/train': 1.7955132722854614} 08/30/2021 19:03:48 - INFO - __main__ - Step 32188: {'lr': 0.00045040760973346673, 'samples': 6180096, 'steps': 32187, 'loss/train': 1.5316449403762817} 08/30/2021 19:03:48 - INFO - __main__ - Step 32189: {'lr': 0.00045040443721091266, 'samples': 6180288, 'steps': 32188, 'loss/train': 1.0864976644515991} 08/30/2021 19:03:50 - INFO - __main__ - Step 32190: {'lr': 0.0004504012645980594, 'samples': 6180480, 'steps': 32189, 'loss/train': 1.294631838798523} 08/30/2021 19:03:50 - INFO - __main__ - Step 32191: {'lr': 0.0004503980918949085, 'samples': 6180672, 'steps': 32190, 'loss/train': 1.7163926362991333} 08/30/2021 19:03:51 - INFO - __main__ - Step 32192: {'lr': 0.00045039491910146124, 'samples': 6180864, 'steps': 32191, 'loss/train': 1.713707447052002} 08/30/2021 19:03:51 - INFO - __main__ - Step 32193: {'lr': 0.00045039174621771915, 'samples': 6181056, 'steps': 32192, 'loss/train': 1.825025200843811} 08/30/2021 19:03:51 - INFO - __main__ - Step 32194: {'lr': 0.00045038857324368367, 'samples': 6181248, 'steps': 32193, 'loss/train': 1.7011688947677612} 08/30/2021 19:03:52 - INFO - __main__ - Step 32195: {'lr': 0.0004503854001793561, 'samples': 6181440, 'steps': 32194, 'loss/train': 1.7963701486587524} 08/30/2021 19:03:53 - INFO - __main__ - Step 32196: {'lr': 0.00045038222702473797, 'samples': 6181632, 'steps': 32195, 'loss/train': 2.0165152549743652} 08/30/2021 19:03:54 - INFO - __main__ - Step 32197: {'lr': 0.0004503790537798308, 'samples': 6181824, 'steps': 32196, 'loss/train': 0.3313131332397461} 08/30/2021 19:03:54 - INFO - __main__ - Step 32198: {'lr': 0.00045037588044463586, 'samples': 6182016, 'steps': 32197, 'loss/train': 0.11049621552228928} 08/30/2021 19:03:55 - INFO - __main__ - Step 32199: {'lr': 0.00045037270701915464, 'samples': 6182208, 'steps': 32198, 'loss/train': 1.2803524732589722} 08/30/2021 19:03:55 - INFO - __main__ - Step 32200: {'lr': 0.0004503695335033885, 'samples': 6182400, 'steps': 32199, 'loss/train': 0.9892556667327881} 08/30/2021 19:03:56 - INFO - __main__ - Step 32201: {'lr': 0.00045036635989733904, 'samples': 6182592, 'steps': 32200, 'loss/train': 0.8140304684638977} 08/30/2021 19:03:57 - INFO - __main__ - Step 32202: {'lr': 0.0004503631862010076, 'samples': 6182784, 'steps': 32201, 'loss/train': 1.8580771684646606} 08/30/2021 19:03:57 - INFO - __main__ - Step 32203: {'lr': 0.0004503600124143955, 'samples': 6182976, 'steps': 32202, 'loss/train': 1.266331434249878} 08/30/2021 19:03:58 - INFO - __main__ - Step 32204: {'lr': 0.0004503568385375043, 'samples': 6183168, 'steps': 32203, 'loss/train': 1.3279629945755005} 08/30/2021 19:03:58 - INFO - __main__ - Step 32205: {'lr': 0.00045035366457033546, 'samples': 6183360, 'steps': 32204, 'loss/train': 1.6388986110687256} 08/30/2021 19:03:59 - INFO - __main__ - Step 32206: {'lr': 0.00045035049051289037, 'samples': 6183552, 'steps': 32205, 'loss/train': 1.7536370754241943} 08/30/2021 19:04:00 - INFO - __main__ - Step 32207: {'lr': 0.00045034731636517036, 'samples': 6183744, 'steps': 32206, 'loss/train': 1.0209001302719116} 08/30/2021 19:04:00 - INFO - __main__ - Step 32208: {'lr': 0.0004503441421271769, 'samples': 6183936, 'steps': 32207, 'loss/train': 1.4281094074249268} 08/30/2021 19:04:01 - INFO - __main__ - Step 32209: {'lr': 0.0004503409677989115, 'samples': 6184128, 'steps': 32208, 'loss/train': 0.953923761844635} 08/30/2021 19:04:01 - INFO - __main__ - Step 32210: {'lr': 0.00045033779338037565, 'samples': 6184320, 'steps': 32209, 'loss/train': 1.758366346359253} 08/30/2021 19:04:02 - INFO - __main__ - Step 32211: {'lr': 0.0004503346188715706, 'samples': 6184512, 'steps': 32210, 'loss/train': 1.7811731100082397} 08/30/2021 19:04:03 - INFO - __main__ - Step 32212: {'lr': 0.0004503314442724979, 'samples': 6184704, 'steps': 32211, 'loss/train': 1.2624577283859253} 08/30/2021 19:04:03 - INFO - __main__ - Step 32213: {'lr': 0.0004503282695831589, 'samples': 6184896, 'steps': 32212, 'loss/train': 1.461298942565918} 08/30/2021 19:04:04 - INFO - __main__ - Step 32214: {'lr': 0.0004503250948035551, 'samples': 6185088, 'steps': 32213, 'loss/train': 1.3856780529022217} 08/30/2021 19:04:04 - INFO - __main__ - Step 32215: {'lr': 0.0004503219199336879, 'samples': 6185280, 'steps': 32214, 'loss/train': 1.2113443613052368} 08/30/2021 19:04:06 - INFO - __main__ - Step 32216: {'lr': 0.00045031874497355876, 'samples': 6185472, 'steps': 32215, 'loss/train': 2.051064968109131} 08/30/2021 19:04:07 - INFO - __main__ - Step 32217: {'lr': 0.000450315569923169, 'samples': 6185664, 'steps': 32216, 'loss/train': 1.9358235597610474} 08/30/2021 19:04:07 - INFO - __main__ - Step 32218: {'lr': 0.00045031239478252017, 'samples': 6185856, 'steps': 32217, 'loss/train': 1.1065044403076172} 08/30/2021 19:04:07 - INFO - __main__ - Step 32219: {'lr': 0.00045030921955161373, 'samples': 6186048, 'steps': 32218, 'loss/train': 1.314040184020996} 08/30/2021 19:04:08 - INFO - __main__ - Step 32220: {'lr': 0.000450306044230451, 'samples': 6186240, 'steps': 32219, 'loss/train': 0.8560385704040527} 08/30/2021 19:04:08 - INFO - __main__ - Step 32221: {'lr': 0.0004503028688190335, 'samples': 6186432, 'steps': 32220, 'loss/train': 1.723817229270935} 08/30/2021 19:04:10 - INFO - __main__ - Step 32222: {'lr': 0.00045029969331736254, 'samples': 6186624, 'steps': 32221, 'loss/train': 1.112336277961731} 08/30/2021 19:04:10 - INFO - __main__ - Step 32223: {'lr': 0.00045029651772543965, 'samples': 6186816, 'steps': 32222, 'loss/train': 1.5397037267684937} 08/30/2021 19:04:11 - INFO - __main__ - Step 32224: {'lr': 0.0004502933420432662, 'samples': 6187008, 'steps': 32223, 'loss/train': 0.10595818608999252} 08/30/2021 19:04:11 - INFO - __main__ - Step 32225: {'lr': 0.0004502901662708437, 'samples': 6187200, 'steps': 32224, 'loss/train': 1.8684959411621094} 08/30/2021 19:04:11 - INFO - __main__ - Step 32226: {'lr': 0.0004502869904081736, 'samples': 6187392, 'steps': 32225, 'loss/train': 1.5043412446975708} 08/30/2021 19:04:13 - INFO - __main__ - Step 32227: {'lr': 0.00045028381445525725, 'samples': 6187584, 'steps': 32226, 'loss/train': 1.1438548564910889} 08/30/2021 19:04:13 - INFO - __main__ - Step 32228: {'lr': 0.0004502806384120961, 'samples': 6187776, 'steps': 32227, 'loss/train': 0.6093456745147705} 08/30/2021 19:04:14 - INFO - __main__ - Step 32229: {'lr': 0.0004502774622786915, 'samples': 6187968, 'steps': 32228, 'loss/train': 1.0948002338409424} 08/30/2021 19:04:14 - INFO - __main__ - Step 32230: {'lr': 0.00045027428605504507, 'samples': 6188160, 'steps': 32229, 'loss/train': 1.5128430128097534} 08/30/2021 19:04:14 - INFO - __main__ - Step 32231: {'lr': 0.00045027110974115814, 'samples': 6188352, 'steps': 32230, 'loss/train': 1.4795303344726562} 08/30/2021 19:04:17 - INFO - __main__ - Step 32232: {'lr': 0.0004502679333370321, 'samples': 6188544, 'steps': 32231, 'loss/train': 1.8321692943572998} 08/30/2021 19:04:17 - INFO - __main__ - Step 32233: {'lr': 0.0004502647568426684, 'samples': 6188736, 'steps': 32232, 'loss/train': 1.2319809198379517} 08/30/2021 19:04:17 - INFO - __main__ - Step 32234: {'lr': 0.0004502615802580685, 'samples': 6188928, 'steps': 32233, 'loss/train': 0.9736570715904236} 08/30/2021 19:04:18 - INFO - __main__ - Step 32235: {'lr': 0.0004502584035832338, 'samples': 6189120, 'steps': 32234, 'loss/train': 1.2968236207962036} 08/30/2021 19:04:18 - INFO - __main__ - Step 32236: {'lr': 0.00045025522681816586, 'samples': 6189312, 'steps': 32235, 'loss/train': 1.3304810523986816} 08/30/2021 19:04:19 - INFO - __main__ - Step 32237: {'lr': 0.0004502520499628659, 'samples': 6189504, 'steps': 32236, 'loss/train': 1.0280253887176514} 08/30/2021 19:04:20 - INFO - __main__ - Step 32238: {'lr': 0.00045024887301733555, 'samples': 6189696, 'steps': 32237, 'loss/train': 0.15719056129455566} 08/30/2021 19:04:20 - INFO - __main__ - Step 32239: {'lr': 0.0004502456959815761, 'samples': 6189888, 'steps': 32238, 'loss/train': 1.4826220273971558} 08/30/2021 19:04:21 - INFO - __main__ - Step 32240: {'lr': 0.000450242518855589, 'samples': 6190080, 'steps': 32239, 'loss/train': 1.3655624389648438} 08/30/2021 19:04:21 - INFO - __main__ - Step 32241: {'lr': 0.00045023934163937565, 'samples': 6190272, 'steps': 32240, 'loss/train': 1.304955244064331} 08/30/2021 19:04:21 - INFO - __main__ - Step 32242: {'lr': 0.00045023616433293763, 'samples': 6190464, 'steps': 32241, 'loss/train': 1.8752590417861938} 08/30/2021 19:04:23 - INFO - __main__ - Step 32243: {'lr': 0.00045023298693627626, 'samples': 6190656, 'steps': 32242, 'loss/train': 1.9656401872634888} 08/30/2021 19:04:23 - INFO - __main__ - Step 32244: {'lr': 0.000450229809449393, 'samples': 6190848, 'steps': 32243, 'loss/train': 1.1609612703323364} 08/30/2021 19:04:24 - INFO - __main__ - Step 32245: {'lr': 0.00045022663187228927, 'samples': 6191040, 'steps': 32244, 'loss/train': 1.9598662853240967} 08/30/2021 19:04:24 - INFO - __main__ - Step 32246: {'lr': 0.0004502234542049666, 'samples': 6191232, 'steps': 32245, 'loss/train': 1.390787959098816} 08/30/2021 19:04:24 - INFO - __main__ - Step 32247: {'lr': 0.00045022027644742624, 'samples': 6191424, 'steps': 32246, 'loss/train': 1.2588329315185547} 08/30/2021 19:04:26 - INFO - __main__ - Step 32248: {'lr': 0.0004502170985996697, 'samples': 6191616, 'steps': 32247, 'loss/train': 1.6045222282409668} 08/30/2021 19:04:27 - INFO - __main__ - Step 32249: {'lr': 0.00045021392066169844, 'samples': 6191808, 'steps': 32248, 'loss/train': 1.5523520708084106} 08/30/2021 19:04:27 - INFO - __main__ - Step 32250: {'lr': 0.0004502107426335139, 'samples': 6192000, 'steps': 32249, 'loss/train': 0.8603515625} 08/30/2021 19:04:27 - INFO - __main__ - Step 32251: {'lr': 0.0004502075645151175, 'samples': 6192192, 'steps': 32250, 'loss/train': 1.7081907987594604} 08/30/2021 19:04:28 - INFO - __main__ - Step 32252: {'lr': 0.0004502043863065106, 'samples': 6192384, 'steps': 32251, 'loss/train': 0.9449916481971741} 08/30/2021 19:04:28 - INFO - __main__ - Step 32253: {'lr': 0.00045020120800769474, 'samples': 6192576, 'steps': 32252, 'loss/train': 1.5930087566375732} 08/30/2021 19:04:29 - INFO - __main__ - Step 32254: {'lr': 0.0004501980296186713, 'samples': 6192768, 'steps': 32253, 'loss/train': 1.470438003540039} 08/30/2021 19:04:30 - INFO - __main__ - Step 32255: {'lr': 0.0004501948511394417, 'samples': 6192960, 'steps': 32254, 'loss/train': 1.4525355100631714} 08/30/2021 19:04:30 - INFO - __main__ - Step 32256: {'lr': 0.0004501916725700074, 'samples': 6193152, 'steps': 32255, 'loss/train': 1.394317626953125} 08/30/2021 19:04:31 - INFO - __main__ - Step 32257: {'lr': 0.00045018849391036987, 'samples': 6193344, 'steps': 32256, 'loss/train': 1.58014976978302} 08/30/2021 19:04:31 - INFO - __main__ - Step 32258: {'lr': 0.00045018531516053046, 'samples': 6193536, 'steps': 32257, 'loss/train': 0.9133492708206177} 08/30/2021 19:04:32 - INFO - __main__ - Step 32259: {'lr': 0.0004501821363204906, 'samples': 6193728, 'steps': 32258, 'loss/train': 1.1269924640655518} 08/30/2021 19:04:33 - INFO - __main__ - Step 32260: {'lr': 0.00045017895739025185, 'samples': 6193920, 'steps': 32259, 'loss/train': 1.0067967176437378} 08/30/2021 19:04:33 - INFO - __main__ - Step 32261: {'lr': 0.0004501757783698154, 'samples': 6194112, 'steps': 32260, 'loss/train': 1.3653923273086548} 08/30/2021 19:04:33 - INFO - __main__ - Step 32262: {'lr': 0.00045017259925918295, 'samples': 6194304, 'steps': 32261, 'loss/train': 0.9848375916481018} 08/30/2021 19:04:34 - INFO - __main__ - Step 32263: {'lr': 0.0004501694200583558, 'samples': 6194496, 'steps': 32262, 'loss/train': 1.7003496885299683} 08/30/2021 19:04:35 - INFO - __main__ - Step 32264: {'lr': 0.0004501662407673354, 'samples': 6194688, 'steps': 32263, 'loss/train': 1.3231052160263062} 08/30/2021 19:04:36 - INFO - __main__ - Step 32265: {'lr': 0.00045016306138612313, 'samples': 6194880, 'steps': 32264, 'loss/train': 1.0903302431106567} 08/30/2021 19:04:36 - INFO - __main__ - Step 32266: {'lr': 0.0004501598819147205, 'samples': 6195072, 'steps': 32265, 'loss/train': 1.4201833009719849} 08/30/2021 19:04:36 - INFO - __main__ - Step 32267: {'lr': 0.00045015670235312895, 'samples': 6195264, 'steps': 32266, 'loss/train': 2.0665924549102783} 08/30/2021 19:04:37 - INFO - __main__ - Step 32268: {'lr': 0.0004501535227013498, 'samples': 6195456, 'steps': 32267, 'loss/train': 1.9269461631774902} 08/30/2021 19:04:39 - INFO - __main__ - Step 32269: {'lr': 0.0004501503429593846, 'samples': 6195648, 'steps': 32268, 'loss/train': 1.0294262170791626} 08/30/2021 19:04:39 - INFO - __main__ - Step 32270: {'lr': 0.0004501471631272348, 'samples': 6195840, 'steps': 32269, 'loss/train': 1.0452120304107666} 08/30/2021 19:04:40 - INFO - __main__ - Step 32271: {'lr': 0.00045014398320490173, 'samples': 6196032, 'steps': 32270, 'loss/train': 1.3407011032104492} 08/30/2021 19:04:40 - INFO - __main__ - Step 32272: {'lr': 0.00045014080319238686, 'samples': 6196224, 'steps': 32271, 'loss/train': 1.2327735424041748} 08/30/2021 19:04:40 - INFO - __main__ - Step 32273: {'lr': 0.00045013762308969164, 'samples': 6196416, 'steps': 32272, 'loss/train': 1.2885394096374512} 08/30/2021 19:04:41 - INFO - __main__ - Step 32274: {'lr': 0.00045013444289681757, 'samples': 6196608, 'steps': 32273, 'loss/train': 1.5427135229110718} 08/30/2021 19:04:42 - INFO - __main__ - Step 32275: {'lr': 0.0004501312626137659, 'samples': 6196800, 'steps': 32274, 'loss/train': 1.1621025800704956} 08/30/2021 19:04:43 - INFO - __main__ - Step 32276: {'lr': 0.0004501280822405382, 'samples': 6196992, 'steps': 32275, 'loss/train': 1.6799015998840332} 08/30/2021 19:04:43 - INFO - __main__ - Step 32277: {'lr': 0.00045012490177713586, 'samples': 6197184, 'steps': 32276, 'loss/train': 1.6742160320281982} 08/30/2021 19:04:43 - INFO - __main__ - Step 32278: {'lr': 0.00045012172122356036, 'samples': 6197376, 'steps': 32277, 'loss/train': 0.9062545299530029} 08/30/2021 19:04:44 - INFO - __main__ - Step 32279: {'lr': 0.0004501185405798131, 'samples': 6197568, 'steps': 32278, 'loss/train': 1.3616219758987427} 08/30/2021 19:04:45 - INFO - __main__ - Step 32280: {'lr': 0.00045011535984589544, 'samples': 6197760, 'steps': 32279, 'loss/train': 1.1179317235946655} 08/30/2021 19:04:46 - INFO - __main__ - Step 32281: {'lr': 0.000450112179021809, 'samples': 6197952, 'steps': 32280, 'loss/train': 1.7102910280227661} 08/30/2021 19:04:46 - INFO - __main__ - Step 32282: {'lr': 0.00045010899810755506, 'samples': 6198144, 'steps': 32281, 'loss/train': 1.355440378189087} 08/30/2021 19:04:46 - INFO - __main__ - Step 32283: {'lr': 0.00045010581710313506, 'samples': 6198336, 'steps': 32282, 'loss/train': 1.5274758338928223} 08/30/2021 19:04:47 - INFO - __main__ - Step 32284: {'lr': 0.0004501026360085505, 'samples': 6198528, 'steps': 32283, 'loss/train': 1.785041332244873} 08/30/2021 19:04:48 - INFO - __main__ - Step 32285: {'lr': 0.0004500994548238028, 'samples': 6198720, 'steps': 32284, 'loss/train': 1.2113220691680908} 08/30/2021 19:04:49 - INFO - __main__ - Step 32286: {'lr': 0.00045009627354889337, 'samples': 6198912, 'steps': 32285, 'loss/train': 0.9600415825843811} 08/30/2021 19:04:49 - INFO - __main__ - Step 32287: {'lr': 0.0004500930921838236, 'samples': 6199104, 'steps': 32286, 'loss/train': 1.620591640472412} 08/30/2021 19:04:49 - INFO - __main__ - Step 32288: {'lr': 0.000450089910728595, 'samples': 6199296, 'steps': 32287, 'loss/train': 1.697812795639038} 08/30/2021 19:04:50 - INFO - __main__ - Step 32289: {'lr': 0.0004500867291832089, 'samples': 6199488, 'steps': 32288, 'loss/train': 1.4883240461349487} 08/30/2021 19:04:51 - INFO - __main__ - Step 32290: {'lr': 0.00045008354754766687, 'samples': 6199680, 'steps': 32289, 'loss/train': 1.4518771171569824} 08/30/2021 19:04:52 - INFO - __main__ - Step 32291: {'lr': 0.0004500803658219703, 'samples': 6199872, 'steps': 32290, 'loss/train': 1.5694080591201782} 08/30/2021 19:04:52 - INFO - __main__ - Step 32292: {'lr': 0.0004500771840061206, 'samples': 6200064, 'steps': 32291, 'loss/train': 1.7950413227081299} 08/30/2021 19:04:52 - INFO - __main__ - Step 32293: {'lr': 0.00045007400210011925, 'samples': 6200256, 'steps': 32292, 'loss/train': 1.6159052848815918} 08/30/2021 19:04:53 - INFO - __main__ - Step 32294: {'lr': 0.0004500708201039676, 'samples': 6200448, 'steps': 32293, 'loss/train': 1.9774682521820068} 08/30/2021 19:04:54 - INFO - __main__ - Step 32295: {'lr': 0.0004500676380176671, 'samples': 6200640, 'steps': 32294, 'loss/train': 2.228645086288452} 08/30/2021 19:04:55 - INFO - __main__ - Step 32296: {'lr': 0.00045006445584121923, 'samples': 6200832, 'steps': 32295, 'loss/train': 1.2370656728744507} 08/30/2021 19:04:55 - INFO - __main__ - Step 32297: {'lr': 0.00045006127357462533, 'samples': 6201024, 'steps': 32296, 'loss/train': 0.9634670615196228} 08/30/2021 19:04:55 - INFO - __main__ - Step 32298: {'lr': 0.000450058091217887, 'samples': 6201216, 'steps': 32297, 'loss/train': 1.016331434249878} 08/30/2021 19:04:56 - INFO - __main__ - Step 32299: {'lr': 0.0004500549087710056, 'samples': 6201408, 'steps': 32298, 'loss/train': 1.5722503662109375} 08/30/2021 19:04:57 - INFO - __main__ - Step 32300: {'lr': 0.0004500517262339825, 'samples': 6201600, 'steps': 32299, 'loss/train': 1.2954716682434082} 08/30/2021 19:04:58 - INFO - __main__ - Step 32301: {'lr': 0.0004500485436068191, 'samples': 6201792, 'steps': 32300, 'loss/train': 1.697182059288025} 08/30/2021 19:04:58 - INFO - __main__ - Step 32302: {'lr': 0.0004500453608895171, 'samples': 6201984, 'steps': 32301, 'loss/train': 1.104217290878296} 08/30/2021 19:04:58 - INFO - __main__ - Step 32303: {'lr': 0.00045004217808207757, 'samples': 6202176, 'steps': 32302, 'loss/train': 1.3325445652008057} 08/30/2021 19:04:59 - INFO - __main__ - Step 32304: {'lr': 0.0004500389951845022, 'samples': 6202368, 'steps': 32303, 'loss/train': 0.8305303454399109} 08/30/2021 19:05:00 - INFO - __main__ - Step 32305: {'lr': 0.00045003581219679235, 'samples': 6202560, 'steps': 32304, 'loss/train': 1.7760523557662964} 08/30/2021 19:05:01 - INFO - __main__ - Step 32306: {'lr': 0.00045003262911894943, 'samples': 6202752, 'steps': 32305, 'loss/train': 1.6123363971710205} 08/30/2021 19:05:01 - INFO - __main__ - Step 32307: {'lr': 0.00045002944595097494, 'samples': 6202944, 'steps': 32306, 'loss/train': 1.5623363256454468} 08/30/2021 19:05:02 - INFO - __main__ - Step 32308: {'lr': 0.00045002626269287024, 'samples': 6203136, 'steps': 32307, 'loss/train': 1.1931275129318237} 08/30/2021 19:05:02 - INFO - __main__ - Step 32309: {'lr': 0.00045002307934463673, 'samples': 6203328, 'steps': 32308, 'loss/train': 1.2309906482696533} 08/30/2021 19:05:03 - INFO - __main__ - Step 32310: {'lr': 0.000450019895906276, 'samples': 6203520, 'steps': 32309, 'loss/train': 1.2578767538070679} 08/30/2021 19:05:04 - INFO - __main__ - Step 32311: {'lr': 0.0004500167123777894, 'samples': 6203712, 'steps': 32310, 'loss/train': 1.2556978464126587} 08/30/2021 19:05:04 - INFO - __main__ - Step 32312: {'lr': 0.00045001352875917824, 'samples': 6203904, 'steps': 32311, 'loss/train': 1.2942194938659668} 08/30/2021 19:05:05 - INFO - __main__ - Step 32313: {'lr': 0.00045001034505044415, 'samples': 6204096, 'steps': 32312, 'loss/train': 1.7812371253967285} 08/30/2021 19:05:05 - INFO - __main__ - Step 32314: {'lr': 0.00045000716125158846, 'samples': 6204288, 'steps': 32313, 'loss/train': 0.655072033405304} 08/30/2021 19:05:07 - INFO - __main__ - Step 32315: {'lr': 0.0004500039773626127, 'samples': 6204480, 'steps': 32314, 'loss/train': 1.0961158275604248} 08/30/2021 19:05:07 - INFO - __main__ - Step 32316: {'lr': 0.00045000079338351805, 'samples': 6204672, 'steps': 32315, 'loss/train': 1.4331393241882324} 08/30/2021 19:05:07 - INFO - __main__ - Step 32317: {'lr': 0.0004499976093143063, 'samples': 6204864, 'steps': 32316, 'loss/train': 1.7492982149124146} 08/30/2021 19:05:08 - INFO - __main__ - Step 32318: {'lr': 0.00044999442515497866, 'samples': 6205056, 'steps': 32317, 'loss/train': 1.6471707820892334} 08/30/2021 19:05:08 - INFO - __main__ - Step 32319: {'lr': 0.0004499912409055367, 'samples': 6205248, 'steps': 32318, 'loss/train': 1.87456214427948} 08/30/2021 19:05:08 - INFO - __main__ - Step 32320: {'lr': 0.0004499880565659816, 'samples': 6205440, 'steps': 32319, 'loss/train': 1.618486762046814} 08/30/2021 19:05:10 - INFO - __main__ - Step 32321: {'lr': 0.0004499848721363151, 'samples': 6205632, 'steps': 32320, 'loss/train': 2.046422243118286} 08/30/2021 19:05:10 - INFO - __main__ - Step 32322: {'lr': 0.0004499816876165385, 'samples': 6205824, 'steps': 32321, 'loss/train': 1.8166916370391846} 08/30/2021 19:05:11 - INFO - __main__ - Step 32323: {'lr': 0.0004499785030066532, 'samples': 6206016, 'steps': 32322, 'loss/train': 1.499638557434082} 08/30/2021 19:05:11 - INFO - __main__ - Step 32324: {'lr': 0.00044997531830666073, 'samples': 6206208, 'steps': 32323, 'loss/train': 1.3961131572723389} 08/30/2021 19:05:12 - INFO - __main__ - Step 32325: {'lr': 0.00044997213351656237, 'samples': 6206400, 'steps': 32324, 'loss/train': 1.3398165702819824} 08/30/2021 19:05:13 - INFO - __main__ - Step 32326: {'lr': 0.00044996894863635965, 'samples': 6206592, 'steps': 32325, 'loss/train': 1.6897411346435547} 08/30/2021 19:05:14 - INFO - __main__ - Step 32327: {'lr': 0.00044996576366605415, 'samples': 6206784, 'steps': 32326, 'loss/train': 1.694573163986206} 08/30/2021 19:05:14 - INFO - __main__ - Step 32328: {'lr': 0.00044996257860564705, 'samples': 6206976, 'steps': 32327, 'loss/train': 0.9707368016242981} 08/30/2021 19:05:15 - INFO - __main__ - Step 32329: {'lr': 0.0004499593934551399, 'samples': 6207168, 'steps': 32328, 'loss/train': 1.1863114833831787} 08/30/2021 19:05:15 - INFO - __main__ - Step 32330: {'lr': 0.00044995620821453416, 'samples': 6207360, 'steps': 32329, 'loss/train': 1.5414466857910156} 08/30/2021 19:05:15 - INFO - __main__ - Step 32331: {'lr': 0.00044995302288383123, 'samples': 6207552, 'steps': 32330, 'loss/train': 1.4557552337646484} 08/30/2021 19:05:17 - INFO - __main__ - Step 32332: {'lr': 0.0004499498374630325, 'samples': 6207744, 'steps': 32331, 'loss/train': 1.3470616340637207} 08/30/2021 19:05:17 - INFO - __main__ - Step 32333: {'lr': 0.0004499466519521396, 'samples': 6207936, 'steps': 32332, 'loss/train': 1.6630051136016846} 08/30/2021 19:05:18 - INFO - __main__ - Step 32334: {'lr': 0.00044994346635115367, 'samples': 6208128, 'steps': 32333, 'loss/train': 1.2623929977416992} 08/30/2021 19:05:18 - INFO - __main__ - Step 32335: {'lr': 0.00044994028066007636, 'samples': 6208320, 'steps': 32334, 'loss/train': 1.2785216569900513} 08/30/2021 19:05:18 - INFO - __main__ - Step 32336: {'lr': 0.00044993709487890906, 'samples': 6208512, 'steps': 32335, 'loss/train': 1.877227783203125} 08/30/2021 19:05:20 - INFO - __main__ - Step 32337: {'lr': 0.0004499339090076532, 'samples': 6208704, 'steps': 32336, 'loss/train': 1.3354116678237915} 08/30/2021 19:05:21 - INFO - __main__ - Step 32338: {'lr': 0.0004499307230463102, 'samples': 6208896, 'steps': 32337, 'loss/train': 1.001396656036377} 08/30/2021 19:05:21 - INFO - __main__ - Step 32339: {'lr': 0.0004499275369948814, 'samples': 6209088, 'steps': 32338, 'loss/train': 1.76034677028656} 08/30/2021 19:05:21 - INFO - __main__ - Step 32340: {'lr': 0.0004499243508533685, 'samples': 6209280, 'steps': 32339, 'loss/train': 1.459526538848877} 08/30/2021 19:05:22 - INFO - __main__ - Step 32341: {'lr': 0.0004499211646217727, 'samples': 6209472, 'steps': 32340, 'loss/train': 1.0437450408935547} 08/30/2021 19:05:24 - INFO - __main__ - Step 32342: {'lr': 0.00044991797830009543, 'samples': 6209664, 'steps': 32341, 'loss/train': 1.3831251859664917} 08/30/2021 19:05:24 - INFO - __main__ - Step 32343: {'lr': 0.00044991479188833826, 'samples': 6209856, 'steps': 32342, 'loss/train': 1.2098065614700317} 08/30/2021 19:05:24 - INFO - __main__ - Step 32344: {'lr': 0.0004499116053865026, 'samples': 6210048, 'steps': 32343, 'loss/train': 1.765133261680603} 08/30/2021 19:05:25 - INFO - __main__ - Step 32345: {'lr': 0.0004499084187945899, 'samples': 6210240, 'steps': 32344, 'loss/train': 1.629771113395691} 08/30/2021 19:05:25 - INFO - __main__ - Step 32346: {'lr': 0.0004499052321126015, 'samples': 6210432, 'steps': 32345, 'loss/train': 1.3455970287322998} 08/30/2021 19:05:26 - INFO - __main__ - Step 32347: {'lr': 0.0004499020453405388, 'samples': 6210624, 'steps': 32346, 'loss/train': 2.2916319370269775} 08/30/2021 19:05:27 - INFO - __main__ - Step 32348: {'lr': 0.00044989885847840344, 'samples': 6210816, 'steps': 32347, 'loss/train': 1.4424232244491577} 08/30/2021 19:05:27 - INFO - __main__ - Step 32349: {'lr': 0.0004498956715261967, 'samples': 6211008, 'steps': 32348, 'loss/train': 1.686930775642395} 08/30/2021 19:05:28 - INFO - __main__ - Step 32350: {'lr': 0.00044989248448392007, 'samples': 6211200, 'steps': 32349, 'loss/train': 1.4522360563278198} 08/30/2021 19:05:28 - INFO - __main__ - Step 32351: {'lr': 0.000449889297351575, 'samples': 6211392, 'steps': 32350, 'loss/train': 1.6329680681228638} 08/30/2021 19:05:29 - INFO - __main__ - Step 32352: {'lr': 0.0004498861101291628, 'samples': 6211584, 'steps': 32351, 'loss/train': 1.6544710397720337} 08/30/2021 19:05:30 - INFO - __main__ - Step 32353: {'lr': 0.0004498829228166851, 'samples': 6211776, 'steps': 32352, 'loss/train': 1.9228895902633667} 08/30/2021 19:05:30 - INFO - __main__ - Step 32354: {'lr': 0.0004498797354141432, 'samples': 6211968, 'steps': 32353, 'loss/train': 1.1937665939331055} 08/30/2021 19:05:31 - INFO - __main__ - Step 32355: {'lr': 0.00044987654792153853, 'samples': 6212160, 'steps': 32354, 'loss/train': 1.3680614233016968} 08/30/2021 19:05:31 - INFO - __main__ - Step 32356: {'lr': 0.0004498733603388726, 'samples': 6212352, 'steps': 32355, 'loss/train': 1.1955623626708984} 08/30/2021 19:05:31 - INFO - __main__ - Step 32357: {'lr': 0.00044987017266614684, 'samples': 6212544, 'steps': 32356, 'loss/train': 1.751094102859497} 08/30/2021 19:05:33 - INFO - __main__ - Step 32358: {'lr': 0.00044986698490336263, 'samples': 6212736, 'steps': 32357, 'loss/train': 1.5925571918487549} 08/30/2021 19:05:33 - INFO - __main__ - Step 32359: {'lr': 0.0004498637970505215, 'samples': 6212928, 'steps': 32358, 'loss/train': 0.42507418990135193} 08/30/2021 19:05:34 - INFO - __main__ - Step 32360: {'lr': 0.0004498606091076248, 'samples': 6213120, 'steps': 32359, 'loss/train': 1.2136996984481812} 08/30/2021 19:05:34 - INFO - __main__ - Step 32361: {'lr': 0.000449857421074674, 'samples': 6213312, 'steps': 32360, 'loss/train': 0.5065601468086243} 08/30/2021 19:05:34 - INFO - __main__ - Step 32362: {'lr': 0.0004498542329516705, 'samples': 6213504, 'steps': 32361, 'loss/train': 0.4492747187614441} 08/30/2021 19:05:36 - INFO - __main__ - Step 32363: {'lr': 0.00044985104473861583, 'samples': 6213696, 'steps': 32362, 'loss/train': 0.775355875492096} 08/30/2021 19:05:36 - INFO - __main__ - Step 32364: {'lr': 0.0004498478564355113, 'samples': 6213888, 'steps': 32363, 'loss/train': 1.3830183744430542} 08/30/2021 19:05:37 - INFO - __main__ - Step 32365: {'lr': 0.0004498446680423584, 'samples': 6214080, 'steps': 32364, 'loss/train': 1.978040337562561} 08/30/2021 19:05:37 - INFO - __main__ - Step 32366: {'lr': 0.0004498414795591586, 'samples': 6214272, 'steps': 32365, 'loss/train': 1.566407322883606} 08/30/2021 19:05:38 - INFO - __main__ - Step 32367: {'lr': 0.00044983829098591336, 'samples': 6214464, 'steps': 32366, 'loss/train': 1.6484313011169434} 08/30/2021 19:05:38 - INFO - __main__ - Step 32368: {'lr': 0.00044983510232262405, 'samples': 6214656, 'steps': 32367, 'loss/train': 1.1499813795089722} 08/30/2021 19:05:39 - INFO - __main__ - Step 32369: {'lr': 0.0004498319135692921, 'samples': 6214848, 'steps': 32368, 'loss/train': 0.07914281636476517} 08/30/2021 19:05:40 - INFO - __main__ - Step 32370: {'lr': 0.00044982872472591897, 'samples': 6215040, 'steps': 32369, 'loss/train': 1.7727489471435547} 08/30/2021 19:05:40 - INFO - __main__ - Step 32371: {'lr': 0.00044982553579250606, 'samples': 6215232, 'steps': 32370, 'loss/train': 1.999704360961914} 08/30/2021 19:05:41 - INFO - __main__ - Step 32372: {'lr': 0.0004498223467690549, 'samples': 6215424, 'steps': 32371, 'loss/train': 0.9826949834823608} 08/30/2021 19:05:41 - INFO - __main__ - Step 32373: {'lr': 0.0004498191576555669, 'samples': 6215616, 'steps': 32372, 'loss/train': 1.6569430828094482} 08/30/2021 19:05:43 - INFO - __main__ - Step 32374: {'lr': 0.00044981596845204344, 'samples': 6215808, 'steps': 32373, 'loss/train': 0.6701174974441528} 08/30/2021 19:05:43 - INFO - __main__ - Step 32375: {'lr': 0.00044981277915848595, 'samples': 6216000, 'steps': 32374, 'loss/train': 1.1777806282043457} 08/30/2021 19:05:44 - INFO - __main__ - Step 32376: {'lr': 0.00044980958977489593, 'samples': 6216192, 'steps': 32375, 'loss/train': 1.3061331510543823} 08/30/2021 19:05:44 - INFO - __main__ - Step 32377: {'lr': 0.00044980640030127484, 'samples': 6216384, 'steps': 32376, 'loss/train': 1.466526746749878} 08/30/2021 19:05:45 - INFO - __main__ - Step 32378: {'lr': 0.00044980321073762405, 'samples': 6216576, 'steps': 32377, 'loss/train': 1.1577993631362915} 08/30/2021 19:05:46 - INFO - __main__ - Step 32379: {'lr': 0.00044980002108394496, 'samples': 6216768, 'steps': 32378, 'loss/train': 1.4330931901931763} 08/30/2021 19:05:46 - INFO - __main__ - Step 32380: {'lr': 0.0004497968313402391, 'samples': 6216960, 'steps': 32379, 'loss/train': 0.7249764800071716} 08/30/2021 19:05:47 - INFO - __main__ - Step 32381: {'lr': 0.00044979364150650794, 'samples': 6217152, 'steps': 32380, 'loss/train': 1.683530569076538} 08/30/2021 19:05:47 - INFO - __main__ - Step 32382: {'lr': 0.00044979045158275273, 'samples': 6217344, 'steps': 32381, 'loss/train': 1.51314377784729} 08/30/2021 19:05:48 - INFO - __main__ - Step 32383: {'lr': 0.0004497872615689751, 'samples': 6217536, 'steps': 32382, 'loss/train': 0.9352617859840393} 08/30/2021 19:05:49 - INFO - __main__ - Step 32384: {'lr': 0.00044978407146517634, 'samples': 6217728, 'steps': 32383, 'loss/train': 1.4616782665252686} 08/30/2021 19:05:50 - INFO - __main__ - Step 32385: {'lr': 0.0004497808812713581, 'samples': 6217920, 'steps': 32384, 'loss/train': 1.418293833732605} 08/30/2021 19:05:50 - INFO - __main__ - Step 32386: {'lr': 0.00044977769098752154, 'samples': 6218112, 'steps': 32385, 'loss/train': 1.1720964908599854} 08/30/2021 19:05:50 - INFO - __main__ - Step 32387: {'lr': 0.0004497745006136683, 'samples': 6218304, 'steps': 32386, 'loss/train': 1.2890551090240479} 08/30/2021 19:05:51 - INFO - __main__ - Step 32388: {'lr': 0.00044977131014979974, 'samples': 6218496, 'steps': 32387, 'loss/train': 1.3431979417800903} 08/30/2021 19:05:52 - INFO - __main__ - Step 32389: {'lr': 0.0004497681195959173, 'samples': 6218688, 'steps': 32388, 'loss/train': 1.47535240650177} 08/30/2021 19:05:53 - INFO - __main__ - Step 32390: {'lr': 0.0004497649289520224, 'samples': 6218880, 'steps': 32389, 'loss/train': 1.7538362741470337} 08/30/2021 19:05:53 - INFO - __main__ - Step 32391: {'lr': 0.00044976173821811654, 'samples': 6219072, 'steps': 32390, 'loss/train': 1.627745270729065} 08/30/2021 19:05:53 - INFO - __main__ - Step 32392: {'lr': 0.0004497585473942011, 'samples': 6219264, 'steps': 32391, 'loss/train': 1.3706724643707275} 08/30/2021 19:05:54 - INFO - __main__ - Step 32393: {'lr': 0.0004497553564802776, 'samples': 6219456, 'steps': 32392, 'loss/train': 1.976728081703186} 08/30/2021 19:05:55 - INFO - __main__ - Step 32394: {'lr': 0.0004497521654763474, 'samples': 6219648, 'steps': 32393, 'loss/train': 0.543554961681366} 08/30/2021 19:05:56 - INFO - __main__ - Step 32395: {'lr': 0.0004497489743824119, 'samples': 6219840, 'steps': 32394, 'loss/train': 1.6516635417938232} 08/30/2021 19:05:56 - INFO - __main__ - Step 32396: {'lr': 0.0004497457831984727, 'samples': 6220032, 'steps': 32395, 'loss/train': 1.149714708328247} 08/30/2021 19:05:56 - INFO - __main__ - Step 32397: {'lr': 0.00044974259192453103, 'samples': 6220224, 'steps': 32396, 'loss/train': 1.8064905405044556} 08/30/2021 19:05:57 - INFO - __main__ - Step 32398: {'lr': 0.0004497394005605885, 'samples': 6220416, 'steps': 32397, 'loss/train': 1.2958773374557495} 08/30/2021 19:05:57 - INFO - __main__ - Step 32399: {'lr': 0.00044973620910664645, 'samples': 6220608, 'steps': 32398, 'loss/train': 0.8186208605766296} 08/30/2021 19:05:59 - INFO - __main__ - Step 32400: {'lr': 0.00044973301756270635, 'samples': 6220800, 'steps': 32399, 'loss/train': 1.544405221939087} 08/30/2021 19:06:00 - INFO - __main__ - Step 32401: {'lr': 0.0004497298259287696, 'samples': 6220992, 'steps': 32400, 'loss/train': 0.8137536644935608} 08/30/2021 19:06:00 - INFO - __main__ - Step 32402: {'lr': 0.00044972663420483774, 'samples': 6221184, 'steps': 32401, 'loss/train': 1.0207865238189697} 08/30/2021 19:06:00 - INFO - __main__ - Step 32403: {'lr': 0.00044972344239091206, 'samples': 6221376, 'steps': 32402, 'loss/train': 1.5676817893981934} 08/30/2021 19:06:01 - INFO - __main__ - Step 32404: {'lr': 0.0004497202504869941, 'samples': 6221568, 'steps': 32403, 'loss/train': 1.5129809379577637} 08/30/2021 19:06:02 - INFO - __main__ - Step 32405: {'lr': 0.0004497170584930853, 'samples': 6221760, 'steps': 32404, 'loss/train': 1.7797439098358154} 08/30/2021 19:06:03 - INFO - __main__ - Step 32406: {'lr': 0.0004497138664091871, 'samples': 6221952, 'steps': 32405, 'loss/train': 1.3799606561660767} 08/30/2021 19:06:03 - INFO - __main__ - Step 32407: {'lr': 0.00044971067423530087, 'samples': 6222144, 'steps': 32406, 'loss/train': 1.6371674537658691} 08/30/2021 19:06:03 - INFO - __main__ - Step 32408: {'lr': 0.0004497074819714281, 'samples': 6222336, 'steps': 32407, 'loss/train': 1.2462704181671143} 08/30/2021 19:06:04 - INFO - __main__ - Step 32409: {'lr': 0.00044970428961757026, 'samples': 6222528, 'steps': 32408, 'loss/train': 0.6013548374176025} 08/30/2021 19:06:05 - INFO - __main__ - Step 32410: {'lr': 0.00044970109717372864, 'samples': 6222720, 'steps': 32409, 'loss/train': 1.535630702972412} 08/30/2021 19:06:06 - INFO - __main__ - Step 32411: {'lr': 0.0004496979046399049, 'samples': 6222912, 'steps': 32410, 'loss/train': 1.3093996047973633} 08/30/2021 19:06:06 - INFO - __main__ - Step 32412: {'lr': 0.00044969471201610037, 'samples': 6223104, 'steps': 32411, 'loss/train': 1.1339932680130005} 08/30/2021 19:06:06 - INFO - __main__ - Step 32413: {'lr': 0.00044969151930231643, 'samples': 6223296, 'steps': 32412, 'loss/train': 0.5679135918617249} 08/30/2021 19:06:07 - INFO - __main__ - Step 32414: {'lr': 0.00044968832649855455, 'samples': 6223488, 'steps': 32413, 'loss/train': 1.6796916723251343} 08/30/2021 19:06:08 - INFO - __main__ - Step 32415: {'lr': 0.00044968513360481624, 'samples': 6223680, 'steps': 32414, 'loss/train': 1.1908469200134277} 08/30/2021 19:06:09 - INFO - __main__ - Step 32416: {'lr': 0.0004496819406211029, 'samples': 6223872, 'steps': 32415, 'loss/train': 1.2527387142181396} 08/30/2021 19:06:09 - INFO - __main__ - Step 32417: {'lr': 0.0004496787475474159, 'samples': 6224064, 'steps': 32416, 'loss/train': 1.3246748447418213} 08/30/2021 19:06:09 - INFO - __main__ - Step 32418: {'lr': 0.00044967555438375675, 'samples': 6224256, 'steps': 32417, 'loss/train': 1.19204843044281} 08/30/2021 19:06:10 - INFO - __main__ - Step 32419: {'lr': 0.0004496723611301269, 'samples': 6224448, 'steps': 32418, 'loss/train': 1.3817065954208374} 08/30/2021 19:06:11 - INFO - __main__ - Step 32420: {'lr': 0.00044966916778652776, 'samples': 6224640, 'steps': 32419, 'loss/train': 1.2285152673721313} 08/30/2021 19:06:12 - INFO - __main__ - Step 32421: {'lr': 0.0004496659743529608, 'samples': 6224832, 'steps': 32420, 'loss/train': 1.3928989171981812} 08/30/2021 19:06:12 - INFO - __main__ - Step 32422: {'lr': 0.00044966278082942746, 'samples': 6225024, 'steps': 32421, 'loss/train': 1.7617006301879883} 08/30/2021 19:06:12 - INFO - __main__ - Step 32423: {'lr': 0.000449659587215929, 'samples': 6225216, 'steps': 32422, 'loss/train': 0.9510110020637512} 08/30/2021 19:06:13 - INFO - __main__ - Step 32424: {'lr': 0.0004496563935124672, 'samples': 6225408, 'steps': 32423, 'loss/train': 1.676318645477295} 08/30/2021 19:06:15 - INFO - __main__ - Step 32425: {'lr': 0.0004496531997190432, 'samples': 6225600, 'steps': 32424, 'loss/train': 1.7138748168945312} 08/30/2021 19:06:15 - INFO - __main__ - Step 32426: {'lr': 0.0004496500058356586, 'samples': 6225792, 'steps': 32425, 'loss/train': 1.4112449884414673} 08/30/2021 19:06:16 - INFO - __main__ - Step 32427: {'lr': 0.00044964681186231473, 'samples': 6225984, 'steps': 32426, 'loss/train': 1.050158977508545} 08/30/2021 19:06:16 - INFO - __main__ - Step 32428: {'lr': 0.0004496436177990131, 'samples': 6226176, 'steps': 32427, 'loss/train': 1.6112520694732666} 08/30/2021 19:06:16 - INFO - __main__ - Step 32429: {'lr': 0.0004496404236457552, 'samples': 6226368, 'steps': 32428, 'loss/train': 1.1650753021240234} 08/30/2021 19:06:17 - INFO - __main__ - Step 32430: {'lr': 0.0004496372294025424, 'samples': 6226560, 'steps': 32429, 'loss/train': 1.639077067375183} 08/30/2021 19:06:18 - INFO - __main__ - Step 32431: {'lr': 0.00044963403506937603, 'samples': 6226752, 'steps': 32430, 'loss/train': 1.2142544984817505} 08/30/2021 19:06:19 - INFO - __main__ - Step 32432: {'lr': 0.00044963084064625775, 'samples': 6226944, 'steps': 32431, 'loss/train': 0.5049042701721191} 08/30/2021 19:06:19 - INFO - __main__ - Step 32433: {'lr': 0.00044962764613318886, 'samples': 6227136, 'steps': 32432, 'loss/train': 1.779929280281067} 08/30/2021 19:06:20 - INFO - __main__ - Step 32434: {'lr': 0.00044962445153017087, 'samples': 6227328, 'steps': 32433, 'loss/train': 1.0560500621795654} 08/30/2021 19:06:20 - INFO - __main__ - Step 32435: {'lr': 0.00044962125683720513, 'samples': 6227520, 'steps': 32434, 'loss/train': 0.12484985589981079} 08/30/2021 19:06:22 - INFO - __main__ - Step 32436: {'lr': 0.0004496180620542931, 'samples': 6227712, 'steps': 32435, 'loss/train': 1.6861265897750854} 08/30/2021 19:06:22 - INFO - __main__ - Step 32437: {'lr': 0.00044961486718143634, 'samples': 6227904, 'steps': 32436, 'loss/train': 1.753557801246643} 08/30/2021 19:06:23 - INFO - __main__ - Step 32438: {'lr': 0.0004496116722186362, 'samples': 6228096, 'steps': 32437, 'loss/train': 1.2478522062301636} 08/30/2021 19:06:23 - INFO - __main__ - Step 32439: {'lr': 0.00044960847716589403, 'samples': 6228288, 'steps': 32438, 'loss/train': 1.1716833114624023} 08/30/2021 19:06:23 - INFO - __main__ - Step 32440: {'lr': 0.00044960528202321143, 'samples': 6228480, 'steps': 32439, 'loss/train': 1.759860873222351} 08/30/2021 19:06:25 - INFO - __main__ - Step 32441: {'lr': 0.0004496020867905898, 'samples': 6228672, 'steps': 32440, 'loss/train': 1.1499463319778442} 08/30/2021 19:06:26 - INFO - __main__ - Step 32442: {'lr': 0.00044959889146803047, 'samples': 6228864, 'steps': 32441, 'loss/train': 1.2256149053573608} 08/30/2021 19:06:26 - INFO - __main__ - Step 32443: {'lr': 0.00044959569605553494, 'samples': 6229056, 'steps': 32442, 'loss/train': 1.6094967126846313} 08/30/2021 19:06:26 - INFO - __main__ - Step 32444: {'lr': 0.00044959250055310473, 'samples': 6229248, 'steps': 32443, 'loss/train': 0.06210010498762131} 08/30/2021 19:06:27 - INFO - __main__ - Step 32445: {'lr': 0.00044958930496074125, 'samples': 6229440, 'steps': 32444, 'loss/train': 0.2832689583301544} 08/30/2021 19:06:27 - INFO - __main__ - Step 32446: {'lr': 0.0004495861092784459, 'samples': 6229632, 'steps': 32445, 'loss/train': 0.2639256715774536} 08/30/2021 19:06:29 - INFO - __main__ - Step 32447: {'lr': 0.00044958291350622007, 'samples': 6229824, 'steps': 32446, 'loss/train': 1.1941344738006592} 08/30/2021 19:06:29 - INFO - __main__ - Step 32448: {'lr': 0.0004495797176440653, 'samples': 6230016, 'steps': 32447, 'loss/train': 0.17134426534175873} 08/30/2021 19:06:29 - INFO - __main__ - Step 32449: {'lr': 0.000449576521691983, 'samples': 6230208, 'steps': 32448, 'loss/train': 1.2336848974227905} 08/30/2021 19:06:30 - INFO - __main__ - Step 32450: {'lr': 0.00044957332564997453, 'samples': 6230400, 'steps': 32449, 'loss/train': 0.7291089296340942} 08/30/2021 19:06:30 - INFO - __main__ - Step 32451: {'lr': 0.0004495701295180414, 'samples': 6230592, 'steps': 32450, 'loss/train': 1.2721360921859741} 08/30/2021 19:06:32 - INFO - __main__ - Step 32452: {'lr': 0.0004495669332961852, 'samples': 6230784, 'steps': 32451, 'loss/train': 2.9824435710906982} 08/30/2021 19:06:32 - INFO - __main__ - Step 32453: {'lr': 0.0004495637369844071, 'samples': 6230976, 'steps': 32452, 'loss/train': 1.7732491493225098} 08/30/2021 19:06:33 - INFO - __main__ - Step 32454: {'lr': 0.0004495605405827087, 'samples': 6231168, 'steps': 32453, 'loss/train': 0.0652928575873375} 08/30/2021 19:06:33 - INFO - __main__ - Step 32455: {'lr': 0.00044955734409109135, 'samples': 6231360, 'steps': 32454, 'loss/train': 1.4207961559295654} 08/30/2021 19:06:33 - INFO - __main__ - Step 32456: {'lr': 0.0004495541475095566, 'samples': 6231552, 'steps': 32455, 'loss/train': 0.33647459745407104} 08/30/2021 19:06:35 - INFO - __main__ - Step 32457: {'lr': 0.0004495509508381058, 'samples': 6231744, 'steps': 32456, 'loss/train': 1.2550816535949707} 08/30/2021 19:06:35 - INFO - __main__ - Step 32458: {'lr': 0.00044954775407674035, 'samples': 6231936, 'steps': 32457, 'loss/train': 0.05562262982130051} 08/30/2021 19:06:36 - INFO - __main__ - Step 32459: {'lr': 0.00044954455722546186, 'samples': 6232128, 'steps': 32458, 'loss/train': 1.3769316673278809} 08/30/2021 19:06:36 - INFO - __main__ - Step 32460: {'lr': 0.0004495413602842716, 'samples': 6232320, 'steps': 32459, 'loss/train': 0.7638034224510193} 08/30/2021 19:06:37 - INFO - __main__ - Step 32461: {'lr': 0.00044953816325317116, 'samples': 6232512, 'steps': 32460, 'loss/train': 1.360421061515808} 08/30/2021 19:06:38 - INFO - __main__ - Step 32462: {'lr': 0.0004495349661321618, 'samples': 6232704, 'steps': 32461, 'loss/train': 1.007704734802246} 08/30/2021 19:06:39 - INFO - __main__ - Step 32463: {'lr': 0.0004495317689212452, 'samples': 6232896, 'steps': 32462, 'loss/train': 1.2015819549560547} 08/30/2021 19:06:39 - INFO - __main__ - Step 32464: {'lr': 0.0004495285716204226, 'samples': 6233088, 'steps': 32463, 'loss/train': 1.8444645404815674} 08/30/2021 19:06:39 - INFO - __main__ - Step 32465: {'lr': 0.00044952537422969545, 'samples': 6233280, 'steps': 32464, 'loss/train': 1.3284454345703125} 08/30/2021 19:06:40 - INFO - __main__ - Step 32466: {'lr': 0.0004495221767490653, 'samples': 6233472, 'steps': 32465, 'loss/train': 1.1120922565460205} 08/30/2021 19:06:41 - INFO - __main__ - Step 32467: {'lr': 0.00044951897917853355, 'samples': 6233664, 'steps': 32466, 'loss/train': 0.06854413449764252} 08/30/2021 19:06:42 - INFO - __main__ - Step 32468: {'lr': 0.0004495157815181016, 'samples': 6233856, 'steps': 32467, 'loss/train': 0.7765848636627197} 08/30/2021 19:06:42 - INFO - __main__ - Step 32469: {'lr': 0.00044951258376777094, 'samples': 6234048, 'steps': 32468, 'loss/train': 1.8528486490249634} 08/30/2021 19:06:42 - INFO - __main__ - Step 32470: {'lr': 0.00044950938592754297, 'samples': 6234240, 'steps': 32469, 'loss/train': 1.3980793952941895} 08/30/2021 19:06:43 - INFO - __main__ - Step 32471: {'lr': 0.00044950618799741913, 'samples': 6234432, 'steps': 32470, 'loss/train': 1.1394309997558594} 08/30/2021 19:06:44 - INFO - __main__ - Step 32472: {'lr': 0.0004495029899774009, 'samples': 6234624, 'steps': 32471, 'loss/train': 1.2558962106704712} 08/30/2021 19:06:45 - INFO - __main__ - Step 32473: {'lr': 0.00044949979186748967, 'samples': 6234816, 'steps': 32472, 'loss/train': 2.0109009742736816} 08/30/2021 19:06:45 - INFO - __main__ - Step 32474: {'lr': 0.00044949659366768697, 'samples': 6235008, 'steps': 32473, 'loss/train': 0.9980002641677856} 08/30/2021 19:06:45 - INFO - __main__ - Step 32475: {'lr': 0.00044949339537799415, 'samples': 6235200, 'steps': 32474, 'loss/train': 1.5778969526290894} 08/30/2021 19:06:46 - INFO - __main__ - Step 32476: {'lr': 0.0004494901969984127, 'samples': 6235392, 'steps': 32475, 'loss/train': 0.5476223826408386} 08/30/2021 19:06:46 - INFO - __main__ - Step 32477: {'lr': 0.000449486998528944, 'samples': 6235584, 'steps': 32476, 'loss/train': 1.2054213285446167} 08/30/2021 19:06:48 - INFO - __main__ - Step 32478: {'lr': 0.00044948379996958963, 'samples': 6235776, 'steps': 32477, 'loss/train': 1.63673734664917} 08/30/2021 19:06:48 - INFO - __main__ - Step 32479: {'lr': 0.00044948060132035087, 'samples': 6235968, 'steps': 32478, 'loss/train': 1.4490669965744019} 08/30/2021 19:06:48 - INFO - __main__ - Step 32480: {'lr': 0.00044947740258122925, 'samples': 6236160, 'steps': 32479, 'loss/train': 1.7334442138671875} 08/30/2021 19:06:49 - INFO - __main__ - Step 32481: {'lr': 0.00044947420375222614, 'samples': 6236352, 'steps': 32480, 'loss/train': 1.7896943092346191} 08/30/2021 19:06:49 - INFO - __main__ - Step 32482: {'lr': 0.00044947100483334315, 'samples': 6236544, 'steps': 32481, 'loss/train': 1.3345435857772827} 08/30/2021 19:06:51 - INFO - __main__ - Step 32483: {'lr': 0.0004494678058245815, 'samples': 6236736, 'steps': 32482, 'loss/train': 1.724750280380249} 08/30/2021 19:06:52 - INFO - __main__ - Step 32484: {'lr': 0.00044946460672594277, 'samples': 6236928, 'steps': 32483, 'loss/train': 1.6925795078277588} 08/30/2021 19:06:52 - INFO - __main__ - Step 32485: {'lr': 0.0004494614075374283, 'samples': 6237120, 'steps': 32484, 'loss/train': 0.7055851221084595} 08/30/2021 19:06:52 - INFO - __main__ - Step 32486: {'lr': 0.0004494582082590397, 'samples': 6237312, 'steps': 32485, 'loss/train': 1.414989948272705} 08/30/2021 19:06:53 - INFO - __main__ - Step 32487: {'lr': 0.0004494550088907783, 'samples': 6237504, 'steps': 32486, 'loss/train': 1.0751837491989136} 08/30/2021 19:06:54 - INFO - __main__ - Step 32488: {'lr': 0.00044945180943264544, 'samples': 6237696, 'steps': 32487, 'loss/train': 4.433512210845947} 08/30/2021 19:06:55 - INFO - __main__ - Step 32489: {'lr': 0.00044944860988464276, 'samples': 6237888, 'steps': 32488, 'loss/train': 1.269638180732727} 08/30/2021 19:06:55 - INFO - __main__ - Step 32490: {'lr': 0.0004494454102467716, 'samples': 6238080, 'steps': 32489, 'loss/train': 0.6475194692611694} 08/30/2021 19:06:55 - INFO - __main__ - Step 32491: {'lr': 0.00044944221051903345, 'samples': 6238272, 'steps': 32490, 'loss/train': 1.8564822673797607} 08/30/2021 19:06:56 - INFO - __main__ - Step 32492: {'lr': 0.0004494390107014297, 'samples': 6238464, 'steps': 32491, 'loss/train': 1.597392201423645} 08/30/2021 19:06:58 - INFO - __main__ - Step 32493: {'lr': 0.0004494358107939618, 'samples': 6238656, 'steps': 32492, 'loss/train': 1.403234839439392} 08/30/2021 19:06:58 - INFO - __main__ - Step 32494: {'lr': 0.0004494326107966311, 'samples': 6238848, 'steps': 32493, 'loss/train': 2.514643430709839} 08/30/2021 19:06:59 - INFO - __main__ - Step 32495: {'lr': 0.0004494294107094393, 'samples': 6239040, 'steps': 32494, 'loss/train': 1.3124140501022339} 08/30/2021 19:06:59 - INFO - __main__ - Step 32496: {'lr': 0.00044942621053238764, 'samples': 6239232, 'steps': 32495, 'loss/train': 1.5863598585128784} 08/30/2021 19:06:59 - INFO - __main__ - Step 32497: {'lr': 0.00044942301026547755, 'samples': 6239424, 'steps': 32496, 'loss/train': 2.784682035446167} 08/30/2021 19:07:00 - INFO - __main__ - Step 32498: {'lr': 0.0004494198099087106, 'samples': 6239616, 'steps': 32497, 'loss/train': 3.2850253582000732} 08/30/2021 19:07:01 - INFO - __main__ - Step 32499: {'lr': 0.00044941660946208806, 'samples': 6239808, 'steps': 32498, 'loss/train': 1.7977617979049683} 08/30/2021 19:07:02 - INFO - __main__ - Step 32500: {'lr': 0.00044941340892561154, 'samples': 6240000, 'steps': 32499, 'loss/train': 1.5849515199661255} 08/30/2021 19:07:02 - INFO - __main__ - Step 32501: {'lr': 0.00044941020829928247, 'samples': 6240192, 'steps': 32500, 'loss/train': 1.777456521987915} 08/30/2021 19:07:03 - INFO - __main__ - Step 32502: {'lr': 0.00044940700758310214, 'samples': 6240384, 'steps': 32501, 'loss/train': 1.5699900388717651} 08/30/2021 19:07:03 - INFO - __main__ - Step 32503: {'lr': 0.00044940380677707214, 'samples': 6240576, 'steps': 32502, 'loss/train': 3.2387187480926514} 08/30/2021 19:07:04 - INFO - __main__ - Step 32504: {'lr': 0.00044940060588119393, 'samples': 6240768, 'steps': 32503, 'loss/train': 1.9758620262145996} 08/30/2021 19:07:05 - INFO - __main__ - Step 32505: {'lr': 0.00044939740489546875, 'samples': 6240960, 'steps': 32504, 'loss/train': 0.7341508865356445} 08/30/2021 19:07:05 - INFO - __main__ - Step 32506: {'lr': 0.0004493942038198983, 'samples': 6241152, 'steps': 32505, 'loss/train': 0.7989136576652527} 08/30/2021 19:07:06 - INFO - __main__ - Step 32507: {'lr': 0.0004493910026544838, 'samples': 6241344, 'steps': 32506, 'loss/train': 1.3034539222717285} 08/30/2021 19:07:06 - INFO - __main__ - Step 32508: {'lr': 0.0004493878013992268, 'samples': 6241536, 'steps': 32507, 'loss/train': 1.39571213722229} 08/30/2021 19:07:06 - INFO - __main__ - Step 32509: {'lr': 0.0004493846000541287, 'samples': 6241728, 'steps': 32508, 'loss/train': 1.5410791635513306} 08/30/2021 19:07:08 - INFO - __main__ - Step 32510: {'lr': 0.00044938139861919115, 'samples': 6241920, 'steps': 32509, 'loss/train': 1.5987144708633423} 08/30/2021 19:07:08 - INFO - __main__ - Step 32511: {'lr': 0.00044937819709441523, 'samples': 6242112, 'steps': 32510, 'loss/train': 0.9097114205360413} 08/30/2021 19:07:09 - INFO - __main__ - Step 32512: {'lr': 0.00044937499547980265, 'samples': 6242304, 'steps': 32511, 'loss/train': 1.3840765953063965} 08/30/2021 19:07:09 - INFO - __main__ - Step 32513: {'lr': 0.00044937179377535475, 'samples': 6242496, 'steps': 32512, 'loss/train': 1.3453541994094849} 08/30/2021 19:07:09 - INFO - __main__ - Step 32514: {'lr': 0.00044936859198107306, 'samples': 6242688, 'steps': 32513, 'loss/train': 0.22491967678070068} 08/30/2021 19:07:11 - INFO - __main__ - Step 32515: {'lr': 0.0004493653900969589, 'samples': 6242880, 'steps': 32514, 'loss/train': 1.1304253339767456} 08/30/2021 19:07:11 - INFO - __main__ - Step 32516: {'lr': 0.0004493621881230138, 'samples': 6243072, 'steps': 32515, 'loss/train': 0.940894603729248} 08/30/2021 19:07:11 - INFO - __main__ - Step 32517: {'lr': 0.00044935898605923916, 'samples': 6243264, 'steps': 32516, 'loss/train': 1.7782803773880005} 08/30/2021 19:07:12 - INFO - __main__ - Step 32518: {'lr': 0.0004493557839056364, 'samples': 6243456, 'steps': 32517, 'loss/train': 1.2063217163085938} 08/30/2021 19:07:12 - INFO - __main__ - Step 32519: {'lr': 0.00044935258166220704, 'samples': 6243648, 'steps': 32518, 'loss/train': 1.2444733381271362} 08/30/2021 19:07:14 - INFO - __main__ - Step 32520: {'lr': 0.00044934937932895246, 'samples': 6243840, 'steps': 32519, 'loss/train': 1.6143519878387451} 08/30/2021 19:07:15 - INFO - __main__ - Step 32521: {'lr': 0.0004493461769058742, 'samples': 6244032, 'steps': 32520, 'loss/train': 0.03852095082402229} 08/30/2021 19:07:15 - INFO - __main__ - Step 32522: {'lr': 0.00044934297439297357, 'samples': 6244224, 'steps': 32521, 'loss/train': 1.912291169166565} 08/30/2021 19:07:15 - INFO - __main__ - Step 32523: {'lr': 0.0004493397717902521, 'samples': 6244416, 'steps': 32522, 'loss/train': 2.0182244777679443} 08/30/2021 19:07:16 - INFO - __main__ - Step 32524: {'lr': 0.00044933656909771117, 'samples': 6244608, 'steps': 32523, 'loss/train': 1.686921238899231} 08/30/2021 19:07:16 - INFO - __main__ - Step 32525: {'lr': 0.00044933336631535224, 'samples': 6244800, 'steps': 32524, 'loss/train': 1.5616185665130615} 08/30/2021 19:07:17 - INFO - __main__ - Step 32526: {'lr': 0.0004493301634431768, 'samples': 6244992, 'steps': 32525, 'loss/train': 1.2322211265563965} 08/30/2021 19:07:18 - INFO - __main__ - Step 32527: {'lr': 0.0004493269604811863, 'samples': 6245184, 'steps': 32526, 'loss/train': 1.4644622802734375} 08/30/2021 19:07:18 - INFO - __main__ - Step 32528: {'lr': 0.000449323757429382, 'samples': 6245376, 'steps': 32527, 'loss/train': 1.7634228467941284} 08/30/2021 19:07:19 - INFO - __main__ - Step 32529: {'lr': 0.00044932055428776566, 'samples': 6245568, 'steps': 32528, 'loss/train': 1.3370349407196045} 08/30/2021 19:07:19 - INFO - __main__ - Step 32530: {'lr': 0.00044931735105633853, 'samples': 6245760, 'steps': 32529, 'loss/train': 0.9920026063919067} 08/30/2021 19:07:21 - INFO - __main__ - Step 32531: {'lr': 0.00044931414773510207, 'samples': 6245952, 'steps': 32530, 'loss/train': 1.1733609437942505} 08/30/2021 19:07:21 - INFO - __main__ - Step 32532: {'lr': 0.00044931094432405766, 'samples': 6246144, 'steps': 32531, 'loss/train': 2.2634294033050537} 08/30/2021 19:07:21 - INFO - __main__ - Step 32533: {'lr': 0.00044930774082320684, 'samples': 6246336, 'steps': 32532, 'loss/train': 0.9710589647293091} 08/30/2021 19:07:22 - INFO - __main__ - Step 32534: {'lr': 0.00044930453723255107, 'samples': 6246528, 'steps': 32533, 'loss/train': 1.5638251304626465} 08/30/2021 19:07:22 - INFO - __main__ - Step 32535: {'lr': 0.0004493013335520917, 'samples': 6246720, 'steps': 32534, 'loss/train': 0.7228960990905762} 08/30/2021 19:07:24 - INFO - __main__ - Step 32536: {'lr': 0.00044929812978183024, 'samples': 6246912, 'steps': 32535, 'loss/train': 1.6448959112167358} 08/30/2021 19:07:25 - INFO - __main__ - Step 32537: {'lr': 0.0004492949259217681, 'samples': 6247104, 'steps': 32536, 'loss/train': 1.9606547355651855} 08/30/2021 19:07:25 - INFO - __main__ - Step 32538: {'lr': 0.00044929172197190684, 'samples': 6247296, 'steps': 32537, 'loss/train': 2.0524723529815674} 08/30/2021 19:07:26 - INFO - __main__ - Step 32539: {'lr': 0.00044928851793224765, 'samples': 6247488, 'steps': 32538, 'loss/train': 1.821181297302246} 08/30/2021 19:07:26 - INFO - __main__ - Step 32540: {'lr': 0.00044928531380279224, 'samples': 6247680, 'steps': 32539, 'loss/train': 3.168372869491577} 08/30/2021 19:07:27 - INFO - __main__ - Step 32541: {'lr': 0.00044928210958354196, 'samples': 6247872, 'steps': 32540, 'loss/train': 1.0670064687728882} 08/30/2021 19:07:28 - INFO - __main__ - Step 32542: {'lr': 0.0004492789052744982, 'samples': 6248064, 'steps': 32541, 'loss/train': 1.429789662361145} 08/30/2021 19:07:28 - INFO - __main__ - Step 32543: {'lr': 0.0004492757008756624, 'samples': 6248256, 'steps': 32542, 'loss/train': 2.3521363735198975} 08/30/2021 19:07:29 - INFO - __main__ - Step 32544: {'lr': 0.0004492724963870361, 'samples': 6248448, 'steps': 32543, 'loss/train': 1.5605545043945312} 08/30/2021 19:07:29 - INFO - __main__ - Step 32545: {'lr': 0.00044926929180862064, 'samples': 6248640, 'steps': 32544, 'loss/train': 1.149708867073059} 08/30/2021 19:07:30 - INFO - __main__ - Step 32546: {'lr': 0.00044926608714041763, 'samples': 6248832, 'steps': 32545, 'loss/train': 1.1772730350494385} 08/30/2021 19:07:31 - INFO - __main__ - Step 32547: {'lr': 0.0004492628823824282, 'samples': 6249024, 'steps': 32546, 'loss/train': 1.9210500717163086} 08/30/2021 19:07:31 - INFO - __main__ - Step 32548: {'lr': 0.0004492596775346541, 'samples': 6249216, 'steps': 32547, 'loss/train': 1.6220155954360962} 08/30/2021 19:07:31 - INFO - __main__ - Step 32549: {'lr': 0.0004492564725970967, 'samples': 6249408, 'steps': 32548, 'loss/train': 1.5211739540100098} 08/30/2021 19:07:32 - INFO - __main__ - Step 32550: {'lr': 0.00044925326756975736, 'samples': 6249600, 'steps': 32549, 'loss/train': 1.5514802932739258} 08/30/2021 19:07:34 - INFO - __main__ - Step 32551: {'lr': 0.00044925006245263757, 'samples': 6249792, 'steps': 32550, 'loss/train': 1.7511314153671265} 08/30/2021 19:07:34 - INFO - __main__ - Step 32552: {'lr': 0.0004492468572457388, 'samples': 6249984, 'steps': 32551, 'loss/train': 1.5107816457748413} 08/30/2021 19:07:35 - INFO - __main__ - Step 32553: {'lr': 0.0004492436519490625, 'samples': 6250176, 'steps': 32552, 'loss/train': 1.1585731506347656} 08/30/2021 19:07:35 - INFO - __main__ - Step 32554: {'lr': 0.00044924044656260997, 'samples': 6250368, 'steps': 32553, 'loss/train': 1.3378500938415527} 08/30/2021 19:07:35 - INFO - __main__ - Step 32555: {'lr': 0.00044923724108638285, 'samples': 6250560, 'steps': 32554, 'loss/train': 1.756518006324768} 08/30/2021 19:07:36 - INFO - __main__ - Step 32556: {'lr': 0.00044923403552038255, 'samples': 6250752, 'steps': 32555, 'loss/train': 0.6435486674308777} 08/30/2021 19:07:37 - INFO - __main__ - Step 32557: {'lr': 0.0004492308298646104, 'samples': 6250944, 'steps': 32556, 'loss/train': 1.7105737924575806} 08/30/2021 19:07:38 - INFO - __main__ - Step 32558: {'lr': 0.0004492276241190679, 'samples': 6251136, 'steps': 32557, 'loss/train': 1.5998950004577637} 08/30/2021 19:07:38 - INFO - __main__ - Step 32559: {'lr': 0.0004492244182837565, 'samples': 6251328, 'steps': 32558, 'loss/train': 1.4155688285827637} 08/30/2021 19:07:38 - INFO - __main__ - Step 32560: {'lr': 0.00044922121235867776, 'samples': 6251520, 'steps': 32559, 'loss/train': 0.2900150418281555} 08/30/2021 19:07:39 - INFO - __main__ - Step 32561: {'lr': 0.00044921800634383294, 'samples': 6251712, 'steps': 32560, 'loss/train': 1.712533950805664} 08/30/2021 19:07:40 - INFO - __main__ - Step 32562: {'lr': 0.0004492148002392235, 'samples': 6251904, 'steps': 32561, 'loss/train': 1.4608594179153442} 08/30/2021 19:07:41 - INFO - __main__ - Step 32563: {'lr': 0.000449211594044851, 'samples': 6252096, 'steps': 32562, 'loss/train': 0.9620749950408936} 08/30/2021 19:07:41 - INFO - __main__ - Step 32564: {'lr': 0.0004492083877607168, 'samples': 6252288, 'steps': 32563, 'loss/train': 1.4404035806655884} 08/30/2021 19:07:41 - INFO - __main__ - Step 32565: {'lr': 0.00044920518138682244, 'samples': 6252480, 'steps': 32564, 'loss/train': 1.1728283166885376} 08/30/2021 19:07:42 - INFO - __main__ - Step 32566: {'lr': 0.00044920197492316925, 'samples': 6252672, 'steps': 32565, 'loss/train': 2.2622733116149902} 08/30/2021 19:07:43 - INFO - __main__ - Step 32567: {'lr': 0.00044919876836975876, 'samples': 6252864, 'steps': 32566, 'loss/train': 1.2195172309875488} 08/30/2021 19:07:44 - INFO - __main__ - Step 32568: {'lr': 0.0004491955617265924, 'samples': 6253056, 'steps': 32567, 'loss/train': 1.522727131843567} 08/30/2021 19:07:44 - INFO - __main__ - Step 32569: {'lr': 0.0004491923549936715, 'samples': 6253248, 'steps': 32568, 'loss/train': 2.150005578994751} 08/30/2021 19:07:44 - INFO - __main__ - Step 32570: {'lr': 0.0004491891481709977, 'samples': 6253440, 'steps': 32569, 'loss/train': 1.6076627969741821} 08/30/2021 19:07:45 - INFO - __main__ - Step 32571: {'lr': 0.0004491859412585723, 'samples': 6253632, 'steps': 32570, 'loss/train': 1.4843344688415527} 08/30/2021 19:07:46 - INFO - __main__ - Step 32572: {'lr': 0.0004491827342563968, 'samples': 6253824, 'steps': 32571, 'loss/train': 1.1950907707214355} 08/30/2021 19:07:47 - INFO - __main__ - Step 32573: {'lr': 0.0004491795271644726, 'samples': 6254016, 'steps': 32572, 'loss/train': 1.4974056482315063} 08/30/2021 19:07:47 - INFO - __main__ - Step 32574: {'lr': 0.0004491763199828012, 'samples': 6254208, 'steps': 32573, 'loss/train': 1.8395887613296509} 08/30/2021 19:07:47 - INFO - __main__ - Step 32575: {'lr': 0.00044917311271138393, 'samples': 6254400, 'steps': 32574, 'loss/train': 1.5923187732696533} 08/30/2021 19:07:48 - INFO - __main__ - Step 32576: {'lr': 0.00044916990535022244, 'samples': 6254592, 'steps': 32575, 'loss/train': 1.4547021389007568} 08/30/2021 19:07:48 - INFO - __main__ - Step 32577: {'lr': 0.00044916669789931806, 'samples': 6254784, 'steps': 32576, 'loss/train': 1.4893746376037598} 08/30/2021 19:07:50 - INFO - __main__ - Step 32578: {'lr': 0.0004491634903586722, 'samples': 6254976, 'steps': 32577, 'loss/train': 1.569621205329895} 08/30/2021 19:07:50 - INFO - __main__ - Step 32579: {'lr': 0.00044916028272828636, 'samples': 6255168, 'steps': 32578, 'loss/train': 1.984078288078308} 08/30/2021 19:07:50 - INFO - __main__ - Step 32580: {'lr': 0.00044915707500816206, 'samples': 6255360, 'steps': 32579, 'loss/train': 1.2185784578323364} 08/30/2021 19:07:51 - INFO - __main__ - Step 32581: {'lr': 0.0004491538671983005, 'samples': 6255552, 'steps': 32580, 'loss/train': 1.5167152881622314} 08/30/2021 19:07:51 - INFO - __main__ - Step 32582: {'lr': 0.00044915065929870335, 'samples': 6255744, 'steps': 32581, 'loss/train': 1.9794422388076782} 08/30/2021 19:07:53 - INFO - __main__ - Step 32583: {'lr': 0.00044914745130937204, 'samples': 6255936, 'steps': 32582, 'loss/train': 1.558671236038208} 08/30/2021 19:07:53 - INFO - __main__ - Step 32584: {'lr': 0.0004491442432303079, 'samples': 6256128, 'steps': 32583, 'loss/train': 1.2898389101028442} 08/30/2021 19:07:53 - INFO - __main__ - Step 32585: {'lr': 0.0004491410350615124, 'samples': 6256320, 'steps': 32584, 'loss/train': 1.0016385316848755} 08/30/2021 19:07:54 - INFO - __main__ - Step 32586: {'lr': 0.0004491378268029871, 'samples': 6256512, 'steps': 32585, 'loss/train': 0.8425077199935913} 08/30/2021 19:07:54 - INFO - __main__ - Step 32587: {'lr': 0.00044913461845473335, 'samples': 6256704, 'steps': 32586, 'loss/train': 1.7002413272857666} 08/30/2021 19:07:56 - INFO - __main__ - Step 32588: {'lr': 0.0004491314100167526, 'samples': 6256896, 'steps': 32587, 'loss/train': 1.3290108442306519} 08/30/2021 19:07:57 - INFO - __main__ - Step 32589: {'lr': 0.00044912820148904634, 'samples': 6257088, 'steps': 32588, 'loss/train': 1.3872827291488647} 08/30/2021 19:07:57 - INFO - __main__ - Step 32590: {'lr': 0.0004491249928716159, 'samples': 6257280, 'steps': 32589, 'loss/train': 1.028517723083496} 08/30/2021 19:07:57 - INFO - __main__ - Step 32591: {'lr': 0.0004491217841644629, 'samples': 6257472, 'steps': 32590, 'loss/train': 1.346028447151184} 08/30/2021 19:07:58 - INFO - __main__ - Step 32592: {'lr': 0.0004491185753675886, 'samples': 6257664, 'steps': 32591, 'loss/train': 1.70199716091156} 08/30/2021 19:07:59 - INFO - __main__ - Step 32593: {'lr': 0.0004491153664809947, 'samples': 6257856, 'steps': 32592, 'loss/train': 1.3674789667129517} 08/30/2021 19:08:00 - INFO - __main__ - Step 32594: {'lr': 0.00044911215750468236, 'samples': 6258048, 'steps': 32593, 'loss/train': 1.2177053689956665} 08/30/2021 19:08:00 - INFO - __main__ - Step 32595: {'lr': 0.0004491089484386531, 'samples': 6258240, 'steps': 32594, 'loss/train': 0.9989675283432007} 08/30/2021 19:08:01 - INFO - __main__ - Step 32596: {'lr': 0.0004491057392829086, 'samples': 6258432, 'steps': 32595, 'loss/train': 1.5146898031234741} 08/30/2021 19:08:01 - INFO - __main__ - Step 32597: {'lr': 0.00044910253003745007, 'samples': 6258624, 'steps': 32596, 'loss/train': 1.4629703760147095} 08/30/2021 19:08:01 - INFO - __main__ - Step 32598: {'lr': 0.00044909932070227887, 'samples': 6258816, 'steps': 32597, 'loss/train': 1.366084337234497} 08/30/2021 19:08:03 - INFO - __main__ - Step 32599: {'lr': 0.00044909611127739676, 'samples': 6259008, 'steps': 32598, 'loss/train': 1.5730016231536865} 08/30/2021 19:08:03 - INFO - __main__ - Step 32600: {'lr': 0.00044909290176280495, 'samples': 6259200, 'steps': 32599, 'loss/train': 1.157251238822937} 08/30/2021 19:08:03 - INFO - __main__ - Step 32601: {'lr': 0.00044908969215850495, 'samples': 6259392, 'steps': 32600, 'loss/train': 1.4529815912246704} 08/30/2021 19:08:04 - INFO - __main__ - Step 32602: {'lr': 0.0004490864824644982, 'samples': 6259584, 'steps': 32601, 'loss/train': 1.7107728719711304} 08/30/2021 19:08:04 - INFO - __main__ - Step 32603: {'lr': 0.0004490832726807862, 'samples': 6259776, 'steps': 32602, 'loss/train': 0.7558012008666992} 08/30/2021 19:08:06 - INFO - __main__ - Step 32604: {'lr': 0.0004490800628073703, 'samples': 6259968, 'steps': 32603, 'loss/train': 1.6195636987686157} 08/30/2021 19:08:07 - INFO - __main__ - Step 32605: {'lr': 0.000449076852844252, 'samples': 6260160, 'steps': 32604, 'loss/train': 1.308281660079956} 08/30/2021 19:08:07 - INFO - __main__ - Step 32606: {'lr': 0.0004490736427914327, 'samples': 6260352, 'steps': 32605, 'loss/train': 0.5588341355323792} 08/30/2021 19:08:07 - INFO - __main__ - Step 32607: {'lr': 0.000449070432648914, 'samples': 6260544, 'steps': 32606, 'loss/train': 0.08983058482408524} 08/30/2021 19:08:08 - INFO - __main__ - Step 32608: {'lr': 0.0004490672224166972, 'samples': 6260736, 'steps': 32607, 'loss/train': 1.482445240020752} 08/30/2021 19:08:08 - INFO - __main__ - Step 32609: {'lr': 0.00044906401209478367, 'samples': 6260928, 'steps': 32608, 'loss/train': 1.5608757734298706} 08/30/2021 19:08:09 - INFO - __main__ - Step 32610: {'lr': 0.00044906080168317507, 'samples': 6261120, 'steps': 32609, 'loss/train': 1.0697720050811768} 08/30/2021 19:08:10 - INFO - __main__ - Step 32611: {'lr': 0.0004490575911818727, 'samples': 6261312, 'steps': 32610, 'loss/train': 1.4957313537597656} 08/30/2021 19:08:10 - INFO - __main__ - Step 32612: {'lr': 0.0004490543805908781, 'samples': 6261504, 'steps': 32611, 'loss/train': 0.7550933957099915} 08/30/2021 19:08:11 - INFO - __main__ - Step 32613: {'lr': 0.00044905116991019264, 'samples': 6261696, 'steps': 32612, 'loss/train': 1.474701166152954} 08/30/2021 19:08:11 - INFO - __main__ - Step 32614: {'lr': 0.00044904795913981775, 'samples': 6261888, 'steps': 32613, 'loss/train': 1.4788645505905151} 08/30/2021 19:08:12 - INFO - __main__ - Step 32615: {'lr': 0.00044904474827975506, 'samples': 6262080, 'steps': 32614, 'loss/train': 1.5367071628570557} 08/30/2021 19:08:13 - INFO - __main__ - Step 32616: {'lr': 0.00044904153733000575, 'samples': 6262272, 'steps': 32615, 'loss/train': 1.407670259475708} 08/30/2021 19:08:13 - INFO - __main__ - Step 32617: {'lr': 0.0004490383262905714, 'samples': 6262464, 'steps': 32616, 'loss/train': 1.796865463256836} 08/30/2021 19:08:14 - INFO - __main__ - Step 32618: {'lr': 0.00044903511516145353, 'samples': 6262656, 'steps': 32617, 'loss/train': 1.2737195491790771} 08/30/2021 19:08:14 - INFO - __main__ - Step 32619: {'lr': 0.0004490319039426535, 'samples': 6262848, 'steps': 32618, 'loss/train': 2.0644729137420654} 08/30/2021 19:08:15 - INFO - __main__ - Step 32620: {'lr': 0.0004490286926341727, 'samples': 6263040, 'steps': 32619, 'loss/train': 1.6587156057357788} 08/30/2021 19:08:16 - INFO - __main__ - Step 32621: {'lr': 0.0004490254812360126, 'samples': 6263232, 'steps': 32620, 'loss/train': 1.367366909980774} 08/30/2021 19:08:16 - INFO - __main__ - Step 32622: {'lr': 0.0004490222697481748, 'samples': 6263424, 'steps': 32621, 'loss/train': 1.2552974224090576} 08/30/2021 19:08:17 - INFO - __main__ - Step 32623: {'lr': 0.00044901905817066055, 'samples': 6263616, 'steps': 32622, 'loss/train': 1.7514386177062988} 08/30/2021 19:08:17 - INFO - __main__ - Step 32624: {'lr': 0.00044901584650347147, 'samples': 6263808, 'steps': 32623, 'loss/train': 0.8660169839859009} 08/30/2021 19:08:19 - INFO - __main__ - Step 32625: {'lr': 0.00044901263474660894, 'samples': 6264000, 'steps': 32624, 'loss/train': 1.4739148616790771} 08/30/2021 19:08:19 - INFO - __main__ - Step 32626: {'lr': 0.0004490094229000743, 'samples': 6264192, 'steps': 32625, 'loss/train': 1.7914471626281738} 08/30/2021 19:08:19 - INFO - __main__ - Step 32627: {'lr': 0.00044900621096386904, 'samples': 6264384, 'steps': 32626, 'loss/train': 1.9467860460281372} 08/30/2021 19:08:20 - INFO - __main__ - Step 32628: {'lr': 0.00044900299893799476, 'samples': 6264576, 'steps': 32627, 'loss/train': 1.9788882732391357} 08/30/2021 19:08:20 - INFO - __main__ - Step 32629: {'lr': 0.0004489997868224528, 'samples': 6264768, 'steps': 32628, 'loss/train': 1.5747175216674805} 08/30/2021 19:08:21 - INFO - __main__ - Step 32630: {'lr': 0.00044899657461724453, 'samples': 6264960, 'steps': 32629, 'loss/train': 1.2320046424865723} 08/30/2021 19:08:22 - INFO - __main__ - Step 32631: {'lr': 0.00044899336232237156, 'samples': 6265152, 'steps': 32630, 'loss/train': 1.4974302053451538} 08/30/2021 19:08:22 - INFO - __main__ - Step 32632: {'lr': 0.0004489901499378352, 'samples': 6265344, 'steps': 32631, 'loss/train': 1.7678385972976685} 08/30/2021 19:08:23 - INFO - __main__ - Step 32633: {'lr': 0.00044898693746363695, 'samples': 6265536, 'steps': 32632, 'loss/train': 1.7455347776412964} 08/30/2021 19:08:23 - INFO - __main__ - Step 32634: {'lr': 0.00044898372489977825, 'samples': 6265728, 'steps': 32633, 'loss/train': 1.287279486656189} 08/30/2021 19:08:23 - INFO - __main__ - Step 32635: {'lr': 0.0004489805122462606, 'samples': 6265920, 'steps': 32634, 'loss/train': 0.9113028645515442} 08/30/2021 19:08:25 - INFO - __main__ - Step 32636: {'lr': 0.0004489772995030853, 'samples': 6266112, 'steps': 32635, 'loss/train': 1.7554665803909302} 08/30/2021 19:08:25 - INFO - __main__ - Step 32637: {'lr': 0.00044897408667025397, 'samples': 6266304, 'steps': 32636, 'loss/train': 1.6604429483413696} 08/30/2021 19:08:26 - INFO - __main__ - Step 32638: {'lr': 0.000448970873747768, 'samples': 6266496, 'steps': 32637, 'loss/train': 1.1881701946258545} 08/30/2021 19:08:26 - INFO - __main__ - Step 32639: {'lr': 0.0004489676607356288, 'samples': 6266688, 'steps': 32638, 'loss/train': 1.8800278902053833} 08/30/2021 19:08:26 - INFO - __main__ - Step 32640: {'lr': 0.00044896444763383787, 'samples': 6266880, 'steps': 32639, 'loss/train': 1.0191476345062256} 08/30/2021 19:08:28 - INFO - __main__ - Step 32641: {'lr': 0.00044896123444239654, 'samples': 6267072, 'steps': 32640, 'loss/train': 1.2555551528930664} 08/30/2021 19:08:28 - INFO - __main__ - Step 32642: {'lr': 0.00044895802116130644, 'samples': 6267264, 'steps': 32641, 'loss/train': 1.476691722869873} 08/30/2021 19:08:29 - INFO - __main__ - Step 32643: {'lr': 0.0004489548077905689, 'samples': 6267456, 'steps': 32642, 'loss/train': 1.2697087526321411} 08/30/2021 19:08:29 - INFO - __main__ - Step 32644: {'lr': 0.0004489515943301854, 'samples': 6267648, 'steps': 32643, 'loss/train': 1.302669644355774} 08/30/2021 19:08:29 - INFO - __main__ - Step 32645: {'lr': 0.0004489483807801574, 'samples': 6267840, 'steps': 32644, 'loss/train': 1.1378012895584106} 08/30/2021 19:08:31 - INFO - __main__ - Step 32646: {'lr': 0.00044894516714048626, 'samples': 6268032, 'steps': 32645, 'loss/train': 1.2294268608093262} 08/30/2021 19:08:32 - INFO - __main__ - Step 32647: {'lr': 0.0004489419534111736, 'samples': 6268224, 'steps': 32646, 'loss/train': 1.510994791984558} 08/30/2021 19:08:32 - INFO - __main__ - Step 32648: {'lr': 0.0004489387395922207, 'samples': 6268416, 'steps': 32647, 'loss/train': 0.47757887840270996} 08/30/2021 19:08:33 - INFO - __main__ - Step 32649: {'lr': 0.00044893552568362903, 'samples': 6268608, 'steps': 32648, 'loss/train': 1.4998905658721924} 08/30/2021 19:08:33 - INFO - __main__ - Step 32650: {'lr': 0.0004489323116854002, 'samples': 6268800, 'steps': 32649, 'loss/train': 1.0956974029541016} 08/30/2021 19:08:35 - INFO - __main__ - Step 32651: {'lr': 0.00044892909759753545, 'samples': 6268992, 'steps': 32650, 'loss/train': 0.9286983013153076} 08/30/2021 19:08:35 - INFO - __main__ - Step 32652: {'lr': 0.00044892588342003637, 'samples': 6269184, 'steps': 32651, 'loss/train': 0.6986061930656433} 08/30/2021 19:08:35 - INFO - __main__ - Step 32653: {'lr': 0.00044892266915290435, 'samples': 6269376, 'steps': 32652, 'loss/train': 0.6714340448379517} 08/30/2021 19:08:36 - INFO - __main__ - Step 32654: {'lr': 0.00044891945479614084, 'samples': 6269568, 'steps': 32653, 'loss/train': 1.2851635217666626} 08/30/2021 19:08:36 - INFO - __main__ - Step 32655: {'lr': 0.00044891624034974726, 'samples': 6269760, 'steps': 32654, 'loss/train': 1.1897081136703491} 08/30/2021 19:08:37 - INFO - __main__ - Step 32656: {'lr': 0.00044891302581372513, 'samples': 6269952, 'steps': 32655, 'loss/train': 0.8642836809158325} 08/30/2021 19:08:38 - INFO - __main__ - Step 32657: {'lr': 0.00044890981118807585, 'samples': 6270144, 'steps': 32656, 'loss/train': 1.5977660417556763} 08/30/2021 19:08:38 - INFO - __main__ - Step 32658: {'lr': 0.00044890659647280084, 'samples': 6270336, 'steps': 32657, 'loss/train': 1.3554693460464478} 08/30/2021 19:08:39 - INFO - __main__ - Step 32659: {'lr': 0.0004489033816679016, 'samples': 6270528, 'steps': 32658, 'loss/train': 1.808934211730957} 08/30/2021 19:08:39 - INFO - __main__ - Step 32660: {'lr': 0.0004489001667733796, 'samples': 6270720, 'steps': 32659, 'loss/train': 0.5968970060348511} 08/30/2021 19:08:39 - INFO - __main__ - Step 32661: {'lr': 0.0004488969517892363, 'samples': 6270912, 'steps': 32660, 'loss/train': 1.2042478322982788} 08/30/2021 19:08:42 - INFO - __main__ - Step 32662: {'lr': 0.000448893736715473, 'samples': 6271104, 'steps': 32661, 'loss/train': 1.426439642906189} 08/30/2021 19:08:42 - INFO - __main__ - Step 32663: {'lr': 0.0004488905215520913, 'samples': 6271296, 'steps': 32662, 'loss/train': 1.2710903882980347} 08/30/2021 19:08:43 - INFO - __main__ - Step 32664: {'lr': 0.00044888730629909256, 'samples': 6271488, 'steps': 32663, 'loss/train': 1.1173428297042847} 08/30/2021 19:08:43 - INFO - __main__ - Step 32665: {'lr': 0.00044888409095647833, 'samples': 6271680, 'steps': 32664, 'loss/train': 0.5026143789291382} 08/30/2021 19:08:43 - INFO - __main__ - Step 32666: {'lr': 0.00044888087552424997, 'samples': 6271872, 'steps': 32665, 'loss/train': 0.801002025604248} 08/30/2021 19:08:44 - INFO - __main__ - Step 32667: {'lr': 0.00044887766000240893, 'samples': 6272064, 'steps': 32666, 'loss/train': 1.8869332075119019} 08/30/2021 19:08:45 - INFO - __main__ - Step 32668: {'lr': 0.0004488744443909567, 'samples': 6272256, 'steps': 32667, 'loss/train': 0.6987221837043762} 08/30/2021 19:08:45 - INFO - __main__ - Step 32669: {'lr': 0.0004488712286898947, 'samples': 6272448, 'steps': 32668, 'loss/train': 0.9386299252510071} 08/30/2021 19:08:46 - INFO - __main__ - Step 32670: {'lr': 0.0004488680128992244, 'samples': 6272640, 'steps': 32669, 'loss/train': 1.3432233333587646} 08/30/2021 19:08:46 - INFO - __main__ - Step 32671: {'lr': 0.00044886479701894736, 'samples': 6272832, 'steps': 32670, 'loss/train': 1.2272197008132935} 08/30/2021 19:08:47 - INFO - __main__ - Step 32672: {'lr': 0.00044886158104906476, 'samples': 6273024, 'steps': 32671, 'loss/train': 1.0744589567184448} 08/30/2021 19:08:47 - INFO - __main__ - Step 32673: {'lr': 0.0004488583649895782, 'samples': 6273216, 'steps': 32672, 'loss/train': 1.8242857456207275} 08/30/2021 19:08:48 - INFO - __main__ - Step 32674: {'lr': 0.00044885514884048926, 'samples': 6273408, 'steps': 32673, 'loss/train': 1.1331464052200317} 08/30/2021 19:08:49 - INFO - __main__ - Step 32675: {'lr': 0.0004488519326017991, 'samples': 6273600, 'steps': 32674, 'loss/train': 1.195969820022583} 08/30/2021 19:08:49 - INFO - __main__ - Step 32676: {'lr': 0.0004488487162735094, 'samples': 6273792, 'steps': 32675, 'loss/train': 1.6875015497207642} 08/30/2021 19:08:49 - INFO - __main__ - Step 32677: {'lr': 0.00044884549985562165, 'samples': 6273984, 'steps': 32676, 'loss/train': 1.3573211431503296} 08/30/2021 19:08:50 - INFO - __main__ - Step 32678: {'lr': 0.000448842283348137, 'samples': 6274176, 'steps': 32677, 'loss/train': 1.196877360343933} 08/30/2021 19:08:51 - INFO - __main__ - Step 32679: {'lr': 0.0004488390667510572, 'samples': 6274368, 'steps': 32678, 'loss/train': 1.146606683731079} 08/30/2021 19:08:52 - INFO - __main__ - Step 32680: {'lr': 0.00044883585006438354, 'samples': 6274560, 'steps': 32679, 'loss/train': 1.2461488246917725} 08/30/2021 19:08:52 - INFO - __main__ - Step 32681: {'lr': 0.0004488326332881175, 'samples': 6274752, 'steps': 32680, 'loss/train': 1.4318525791168213} 08/30/2021 19:08:52 - INFO - __main__ - Step 32682: {'lr': 0.0004488294164222606, 'samples': 6274944, 'steps': 32681, 'loss/train': 1.6273961067199707} 08/30/2021 19:08:53 - INFO - __main__ - Step 32683: {'lr': 0.0004488261994668142, 'samples': 6275136, 'steps': 32682, 'loss/train': 1.14664888381958} 08/30/2021 19:08:54 - INFO - __main__ - Step 32684: {'lr': 0.00044882298242177976, 'samples': 6275328, 'steps': 32683, 'loss/train': 1.650382161140442} 08/30/2021 19:08:55 - INFO - __main__ - Step 32685: {'lr': 0.00044881976528715877, 'samples': 6275520, 'steps': 32684, 'loss/train': 1.581041693687439} 08/30/2021 19:08:55 - INFO - __main__ - Step 32686: {'lr': 0.0004488165480629527, 'samples': 6275712, 'steps': 32685, 'loss/train': 1.138535976409912} 08/30/2021 19:08:56 - INFO - __main__ - Step 32687: {'lr': 0.00044881333074916287, 'samples': 6275904, 'steps': 32686, 'loss/train': 1.7488389015197754} 08/30/2021 19:08:56 - INFO - __main__ - Step 32688: {'lr': 0.00044881011334579093, 'samples': 6276096, 'steps': 32687, 'loss/train': 1.5472015142440796} 08/30/2021 19:08:57 - INFO - __main__ - Step 32689: {'lr': 0.0004488068958528382, 'samples': 6276288, 'steps': 32688, 'loss/train': 2.2534351348876953} 08/30/2021 19:08:58 - INFO - __main__ - Step 32690: {'lr': 0.0004488036782703061, 'samples': 6276480, 'steps': 32689, 'loss/train': 1.339576244354248} 08/30/2021 19:08:58 - INFO - __main__ - Step 32691: {'lr': 0.00044880046059819615, 'samples': 6276672, 'steps': 32690, 'loss/train': 1.3722784519195557} 08/30/2021 19:08:59 - INFO - __main__ - Step 32692: {'lr': 0.00044879724283650976, 'samples': 6276864, 'steps': 32691, 'loss/train': 1.4898552894592285} 08/30/2021 19:08:59 - INFO - __main__ - Step 32693: {'lr': 0.0004487940249852484, 'samples': 6277056, 'steps': 32692, 'loss/train': 1.76902174949646} 08/30/2021 19:09:00 - INFO - __main__ - Step 32694: {'lr': 0.0004487908070444136, 'samples': 6277248, 'steps': 32693, 'loss/train': 0.06002538278698921} 08/30/2021 19:09:01 - INFO - __main__ - Step 32695: {'lr': 0.00044878758901400665, 'samples': 6277440, 'steps': 32694, 'loss/train': 0.45922979712486267} 08/30/2021 19:09:01 - INFO - __main__ - Step 32696: {'lr': 0.00044878437089402906, 'samples': 6277632, 'steps': 32695, 'loss/train': 1.806343913078308} 08/30/2021 19:09:02 - INFO - __main__ - Step 32697: {'lr': 0.0004487811526844824, 'samples': 6277824, 'steps': 32696, 'loss/train': 1.1682636737823486} 08/30/2021 19:09:02 - INFO - __main__ - Step 32698: {'lr': 0.0004487779343853679, 'samples': 6278016, 'steps': 32697, 'loss/train': 1.624447226524353} 08/30/2021 19:09:04 - INFO - __main__ - Step 32699: {'lr': 0.00044877471599668716, 'samples': 6278208, 'steps': 32698, 'loss/train': 0.7771300077438354} 08/30/2021 19:09:05 - INFO - __main__ - Step 32700: {'lr': 0.00044877149751844164, 'samples': 6278400, 'steps': 32699, 'loss/train': 2.180201768875122} 08/30/2021 19:09:05 - INFO - __main__ - Step 32701: {'lr': 0.00044876827895063277, 'samples': 6278592, 'steps': 32700, 'loss/train': 1.3569248914718628} 08/30/2021 19:09:05 - INFO - __main__ - Step 32702: {'lr': 0.0004487650602932619, 'samples': 6278784, 'steps': 32701, 'loss/train': 1.5192692279815674} 08/30/2021 19:09:06 - INFO - __main__ - Step 32703: {'lr': 0.00044876184154633066, 'samples': 6278976, 'steps': 32702, 'loss/train': 1.6608797311782837} 08/30/2021 19:09:07 - INFO - __main__ - Step 32704: {'lr': 0.00044875862270984035, 'samples': 6279168, 'steps': 32703, 'loss/train': 1.514662742614746} 08/30/2021 19:09:08 - INFO - __main__ - Step 32705: {'lr': 0.0004487554037837925, 'samples': 6279360, 'steps': 32704, 'loss/train': 2.7525267601013184} 08/30/2021 19:09:08 - INFO - __main__ - Step 32706: {'lr': 0.00044875218476818845, 'samples': 6279552, 'steps': 32705, 'loss/train': 1.8895959854125977} 08/30/2021 19:09:08 - INFO - __main__ - Step 32707: {'lr': 0.0004487489656630298, 'samples': 6279744, 'steps': 32706, 'loss/train': 0.6508373022079468} 08/30/2021 19:09:09 - INFO - __main__ - Step 32708: {'lr': 0.00044874574646831794, 'samples': 6279936, 'steps': 32707, 'loss/train': 0.9525187611579895} 08/30/2021 19:09:09 - INFO - __main__ - Step 32709: {'lr': 0.0004487425271840543, 'samples': 6280128, 'steps': 32708, 'loss/train': 2.010841131210327} 08/30/2021 19:09:10 - INFO - __main__ - Step 32710: {'lr': 0.0004487393078102403, 'samples': 6280320, 'steps': 32709, 'loss/train': 1.357568383216858} 08/30/2021 19:09:11 - INFO - __main__ - Step 32711: {'lr': 0.00044873608834687754, 'samples': 6280512, 'steps': 32710, 'loss/train': 1.5007696151733398} 08/30/2021 19:09:11 - INFO - __main__ - Step 32712: {'lr': 0.00044873286879396724, 'samples': 6280704, 'steps': 32711, 'loss/train': 1.4705638885498047} 08/30/2021 19:09:12 - INFO - __main__ - Step 32713: {'lr': 0.00044872964915151106, 'samples': 6280896, 'steps': 32712, 'loss/train': 1.5984336137771606} 08/30/2021 19:09:12 - INFO - __main__ - Step 32714: {'lr': 0.00044872642941951035, 'samples': 6281088, 'steps': 32713, 'loss/train': 1.1912426948547363} 08/30/2021 19:09:13 - INFO - __main__ - Step 32715: {'lr': 0.0004487232095979666, 'samples': 6281280, 'steps': 32714, 'loss/train': 1.02670419216156} 08/30/2021 19:09:14 - INFO - __main__ - Step 32716: {'lr': 0.0004487199896868812, 'samples': 6281472, 'steps': 32715, 'loss/train': 1.3977181911468506} 08/30/2021 19:09:14 - INFO - __main__ - Step 32717: {'lr': 0.00044871676968625564, 'samples': 6281664, 'steps': 32716, 'loss/train': 1.223524808883667} 08/30/2021 19:09:15 - INFO - __main__ - Step 32718: {'lr': 0.00044871354959609135, 'samples': 6281856, 'steps': 32717, 'loss/train': 1.7086668014526367} 08/30/2021 19:09:15 - INFO - __main__ - Step 32719: {'lr': 0.00044871032941638984, 'samples': 6282048, 'steps': 32718, 'loss/train': 1.1339046955108643} 08/30/2021 19:09:16 - INFO - __main__ - Step 32720: {'lr': 0.00044870710914715254, 'samples': 6282240, 'steps': 32719, 'loss/train': 1.5099304914474487} 08/30/2021 19:09:17 - INFO - __main__ - Step 32721: {'lr': 0.00044870388878838084, 'samples': 6282432, 'steps': 32720, 'loss/train': 0.7428812384605408} 08/30/2021 19:09:17 - INFO - __main__ - Step 32722: {'lr': 0.00044870066834007627, 'samples': 6282624, 'steps': 32721, 'loss/train': 1.6752691268920898} 08/30/2021 19:09:18 - INFO - __main__ - Step 32723: {'lr': 0.0004486974478022402, 'samples': 6282816, 'steps': 32722, 'loss/train': 1.742810845375061} 08/30/2021 19:09:18 - INFO - __main__ - Step 32724: {'lr': 0.0004486942271748742, 'samples': 6283008, 'steps': 32723, 'loss/train': 1.631355881690979} 08/30/2021 19:09:20 - INFO - __main__ - Step 32725: {'lr': 0.0004486910064579796, 'samples': 6283200, 'steps': 32724, 'loss/train': 0.8716088533401489} 08/30/2021 19:09:20 - INFO - __main__ - Step 32726: {'lr': 0.00044868778565155783, 'samples': 6283392, 'steps': 32725, 'loss/train': 1.4294098615646362} 08/30/2021 19:09:20 - INFO - __main__ - Step 32727: {'lr': 0.00044868456475561047, 'samples': 6283584, 'steps': 32726, 'loss/train': 0.9342978596687317} 08/30/2021 19:09:21 - INFO - __main__ - Step 32728: {'lr': 0.0004486813437701389, 'samples': 6283776, 'steps': 32727, 'loss/train': 0.8733958005905151} 08/30/2021 19:09:21 - INFO - __main__ - Step 32729: {'lr': 0.0004486781226951446, 'samples': 6283968, 'steps': 32728, 'loss/train': 1.2319986820220947} 08/30/2021 19:09:23 - INFO - __main__ - Step 32730: {'lr': 0.000448674901530629, 'samples': 6284160, 'steps': 32729, 'loss/train': 1.865423560142517} 08/30/2021 19:09:23 - INFO - __main__ - Step 32731: {'lr': 0.00044867168027659356, 'samples': 6284352, 'steps': 32730, 'loss/train': 0.0932878777384758} 08/30/2021 19:09:23 - INFO - __main__ - Step 32732: {'lr': 0.00044866845893303973, 'samples': 6284544, 'steps': 32731, 'loss/train': 1.4628554582595825} 08/30/2021 19:09:24 - INFO - __main__ - Step 32733: {'lr': 0.00044866523749996897, 'samples': 6284736, 'steps': 32732, 'loss/train': 1.3478153944015503} 08/30/2021 19:09:24 - INFO - __main__ - Step 32734: {'lr': 0.0004486620159773827, 'samples': 6284928, 'steps': 32733, 'loss/train': 0.9551073312759399} 08/30/2021 19:09:26 - INFO - __main__ - Step 32735: {'lr': 0.0004486587943652823, 'samples': 6285120, 'steps': 32734, 'loss/train': 1.3273606300354004} 08/30/2021 19:09:26 - INFO - __main__ - Step 32736: {'lr': 0.00044865557266366953, 'samples': 6285312, 'steps': 32735, 'loss/train': 1.0841439962387085} 08/30/2021 19:09:27 - INFO - __main__ - Step 32737: {'lr': 0.0004486523508725454, 'samples': 6285504, 'steps': 32736, 'loss/train': 1.8125394582748413} 08/30/2021 19:09:27 - INFO - __main__ - Step 32738: {'lr': 0.00044864912899191174, 'samples': 6285696, 'steps': 32737, 'loss/train': 1.1985185146331787} 08/30/2021 19:09:27 - INFO - __main__ - Step 32739: {'lr': 0.00044864590702176977, 'samples': 6285888, 'steps': 32738, 'loss/train': 0.8871357440948486} 08/30/2021 19:09:29 - INFO - __main__ - Step 32740: {'lr': 0.000448642684962121, 'samples': 6286080, 'steps': 32739, 'loss/train': 1.1493544578552246} 08/30/2021 19:09:30 - INFO - __main__ - Step 32741: {'lr': 0.000448639462812967, 'samples': 6286272, 'steps': 32740, 'loss/train': 1.3475017547607422} 08/30/2021 19:09:30 - INFO - __main__ - Step 32742: {'lr': 0.0004486362405743091, 'samples': 6286464, 'steps': 32741, 'loss/train': 1.44907808303833} 08/30/2021 19:09:31 - INFO - __main__ - Step 32743: {'lr': 0.0004486330182461487, 'samples': 6286656, 'steps': 32742, 'loss/train': 1.7825427055358887} 08/30/2021 19:09:31 - INFO - __main__ - Step 32744: {'lr': 0.0004486297958284874, 'samples': 6286848, 'steps': 32743, 'loss/train': 0.12823890149593353} 08/30/2021 19:09:31 - INFO - __main__ - Step 32745: {'lr': 0.0004486265733213265, 'samples': 6287040, 'steps': 32744, 'loss/train': 1.411868929862976} 08/30/2021 19:09:32 - INFO - __main__ - Step 32746: {'lr': 0.00044862335072466767, 'samples': 6287232, 'steps': 32745, 'loss/train': 4.230576992034912} 08/30/2021 19:09:33 - INFO - __main__ - Step 32747: {'lr': 0.00044862012803851203, 'samples': 6287424, 'steps': 32746, 'loss/train': 8.016744613647461} 08/30/2021 19:09:34 - INFO - __main__ - Step 32748: {'lr': 0.00044861690526286135, 'samples': 6287616, 'steps': 32747, 'loss/train': 1.3422104120254517} 08/30/2021 19:09:34 - INFO - __main__ - Step 32749: {'lr': 0.00044861368239771694, 'samples': 6287808, 'steps': 32748, 'loss/train': 2.1091575622558594} 08/30/2021 19:09:34 - INFO - __main__ - Step 32750: {'lr': 0.00044861045944308026, 'samples': 6288000, 'steps': 32749, 'loss/train': 1.341341257095337} 08/30/2021 19:09:35 - INFO - __main__ - Step 32751: {'lr': 0.0004486072363989528, 'samples': 6288192, 'steps': 32750, 'loss/train': 1.4784268140792847} 08/30/2021 19:09:37 - INFO - __main__ - Step 32752: {'lr': 0.00044860401326533595, 'samples': 6288384, 'steps': 32751, 'loss/train': 1.5603610277175903} 08/30/2021 19:09:37 - INFO - __main__ - Step 32753: {'lr': 0.0004486007900422312, 'samples': 6288576, 'steps': 32752, 'loss/train': 1.4333299398422241} 08/30/2021 19:09:38 - INFO - __main__ - Step 32754: {'lr': 0.00044859756672964, 'samples': 6288768, 'steps': 32753, 'loss/train': 1.936609148979187} 08/30/2021 19:09:38 - INFO - __main__ - Step 32755: {'lr': 0.00044859434332756383, 'samples': 6288960, 'steps': 32754, 'loss/train': 1.333675742149353} 08/30/2021 19:09:38 - INFO - __main__ - Step 32756: {'lr': 0.0004485911198360041, 'samples': 6289152, 'steps': 32755, 'loss/train': 1.4803684949874878} 08/30/2021 19:09:40 - INFO - __main__ - Step 32757: {'lr': 0.0004485878962549622, 'samples': 6289344, 'steps': 32756, 'loss/train': 0.38887861371040344} 08/30/2021 19:09:40 - INFO - __main__ - Step 32758: {'lr': 0.0004485846725844398, 'samples': 6289536, 'steps': 32757, 'loss/train': 1.8522518873214722} 08/30/2021 19:09:41 - INFO - __main__ - Step 32759: {'lr': 0.0004485814488244381, 'samples': 6289728, 'steps': 32758, 'loss/train': 0.8544082641601562} 08/30/2021 19:09:41 - INFO - __main__ - Step 32760: {'lr': 0.0004485782249749587, 'samples': 6289920, 'steps': 32759, 'loss/train': 1.5086592435836792} 08/30/2021 19:09:41 - INFO - __main__ - Step 32761: {'lr': 0.00044857500103600304, 'samples': 6290112, 'steps': 32760, 'loss/train': 1.417419672012329} 08/30/2021 19:09:42 - INFO - __main__ - Step 32762: {'lr': 0.00044857177700757247, 'samples': 6290304, 'steps': 32761, 'loss/train': 0.10837419331073761} 08/30/2021 19:09:43 - INFO - __main__ - Step 32763: {'lr': 0.00044856855288966856, 'samples': 6290496, 'steps': 32762, 'loss/train': 0.42357853055000305} 08/30/2021 19:09:44 - INFO - __main__ - Step 32764: {'lr': 0.0004485653286822927, 'samples': 6290688, 'steps': 32763, 'loss/train': 1.54203462600708} 08/30/2021 19:09:44 - INFO - __main__ - Step 32765: {'lr': 0.0004485621043854465, 'samples': 6290880, 'steps': 32764, 'loss/train': 1.643184781074524} 08/30/2021 19:09:44 - INFO - __main__ - Step 32766: {'lr': 0.0004485588799991311, 'samples': 6291072, 'steps': 32765, 'loss/train': 1.0635567903518677} 08/30/2021 19:09:45 - INFO - __main__ - Step 32767: {'lr': 0.0004485556555233483, 'samples': 6291264, 'steps': 32766, 'loss/train': 0.9965192079544067} 08/30/2021 19:09:46 - INFO - __main__ - Step 32768: {'lr': 0.0004485524309580993, 'samples': 6291456, 'steps': 32767, 'loss/train': 1.7073910236358643} 08/30/2021 19:09:47 - INFO - __main__ - Step 32769: {'lr': 0.0004485492063033856, 'samples': 6291648, 'steps': 32768, 'loss/train': 1.0999629497528076} 08/30/2021 19:09:47 - INFO - __main__ - Step 32770: {'lr': 0.0004485459815592087, 'samples': 6291840, 'steps': 32769, 'loss/train': 1.7776328325271606} 08/30/2021 19:09:47 - INFO - __main__ - Step 32771: {'lr': 0.0004485427567255701, 'samples': 6292032, 'steps': 32770, 'loss/train': 0.7569795846939087} 08/30/2021 19:09:48 - INFO - __main__ - Step 32772: {'lr': 0.0004485395318024712, 'samples': 6292224, 'steps': 32771, 'loss/train': 1.0346463918685913} 08/30/2021 19:09:49 - INFO - __main__ - Step 32773: {'lr': 0.00044853630678991344, 'samples': 6292416, 'steps': 32772, 'loss/train': 1.0680031776428223} 08/30/2021 19:09:50 - INFO - __main__ - Step 32774: {'lr': 0.00044853308168789824, 'samples': 6292608, 'steps': 32773, 'loss/train': 1.6477960348129272} 08/30/2021 19:09:50 - INFO - __main__ - Step 32775: {'lr': 0.00044852985649642714, 'samples': 6292800, 'steps': 32774, 'loss/train': 1.2744946479797363} 08/30/2021 19:09:50 - INFO - __main__ - Step 32776: {'lr': 0.0004485266312155015, 'samples': 6292992, 'steps': 32775, 'loss/train': 1.7531893253326416} 08/30/2021 19:09:51 - INFO - __main__ - Step 32777: {'lr': 0.00044852340584512285, 'samples': 6293184, 'steps': 32776, 'loss/train': 1.0807465314865112} 08/30/2021 19:09:52 - INFO - __main__ - Step 32778: {'lr': 0.00044852018038529264, 'samples': 6293376, 'steps': 32777, 'loss/train': 2.2647616863250732} 08/30/2021 19:09:53 - INFO - __main__ - Step 32779: {'lr': 0.00044851695483601227, 'samples': 6293568, 'steps': 32778, 'loss/train': 1.55298912525177} 08/30/2021 19:09:53 - INFO - __main__ - Step 32780: {'lr': 0.0004485137291972833, 'samples': 6293760, 'steps': 32779, 'loss/train': 1.605798363685608} 08/30/2021 19:09:53 - INFO - __main__ - Step 32781: {'lr': 0.00044851050346910706, 'samples': 6293952, 'steps': 32780, 'loss/train': 1.4963539838790894} 08/30/2021 19:09:54 - INFO - __main__ - Step 32782: {'lr': 0.00044850727765148504, 'samples': 6294144, 'steps': 32781, 'loss/train': 1.1368192434310913} 08/30/2021 19:09:55 - INFO - __main__ - Step 32783: {'lr': 0.00044850405174441866, 'samples': 6294336, 'steps': 32782, 'loss/train': 1.5403021574020386} 08/30/2021 19:09:56 - INFO - __main__ - Step 32784: {'lr': 0.00044850082574790945, 'samples': 6294528, 'steps': 32783, 'loss/train': 0.9672999382019043} 08/30/2021 19:09:56 - INFO - __main__ - Step 32785: {'lr': 0.0004484975996619589, 'samples': 6294720, 'steps': 32784, 'loss/train': 1.37628173828125} 08/30/2021 19:09:56 - INFO - __main__ - Step 32786: {'lr': 0.0004484943734865683, 'samples': 6294912, 'steps': 32785, 'loss/train': 1.615965723991394} 08/30/2021 19:09:57 - INFO - __main__ - Step 32787: {'lr': 0.0004484911472217392, 'samples': 6295104, 'steps': 32786, 'loss/train': 0.8111220002174377} 08/30/2021 19:09:58 - INFO - __main__ - Step 32788: {'lr': 0.0004484879208674731, 'samples': 6295296, 'steps': 32787, 'loss/train': 1.3192120790481567} 08/30/2021 19:09:59 - INFO - __main__ - Step 32789: {'lr': 0.0004484846944237714, 'samples': 6295488, 'steps': 32788, 'loss/train': 1.085790753364563} 08/30/2021 19:09:59 - INFO - __main__ - Step 32790: {'lr': 0.0004484814678906355, 'samples': 6295680, 'steps': 32789, 'loss/train': 1.0670602321624756} 08/30/2021 19:09:59 - INFO - __main__ - Step 32791: {'lr': 0.00044847824126806703, 'samples': 6295872, 'steps': 32790, 'loss/train': 1.282948613166809} 08/30/2021 19:10:00 - INFO - __main__ - Step 32792: {'lr': 0.0004484750145560672, 'samples': 6296064, 'steps': 32791, 'loss/train': 0.8721528649330139} 08/30/2021 19:10:02 - INFO - __main__ - Step 32793: {'lr': 0.0004484717877546377, 'samples': 6296256, 'steps': 32792, 'loss/train': 1.582984447479248} 08/30/2021 19:10:02 - INFO - __main__ - Step 32794: {'lr': 0.0004484685608637798, 'samples': 6296448, 'steps': 32793, 'loss/train': 0.7589924931526184} 08/30/2021 19:10:02 - INFO - __main__ - Step 32795: {'lr': 0.00044846533388349507, 'samples': 6296640, 'steps': 32794, 'loss/train': 1.3637824058532715} 08/30/2021 19:10:03 - INFO - __main__ - Step 32796: {'lr': 0.00044846210681378487, 'samples': 6296832, 'steps': 32795, 'loss/train': 0.041862208396196365} 08/30/2021 19:10:03 - INFO - __main__ - Step 32797: {'lr': 0.00044845887965465076, 'samples': 6297024, 'steps': 32796, 'loss/train': 0.030864065513014793} 08/30/2021 19:10:04 - INFO - __main__ - Step 32798: {'lr': 0.0004484556524060941, 'samples': 6297216, 'steps': 32797, 'loss/train': 1.4275683164596558} 08/30/2021 19:10:05 - INFO - __main__ - Step 32799: {'lr': 0.00044845242506811646, 'samples': 6297408, 'steps': 32798, 'loss/train': 2.122243881225586} 08/30/2021 19:10:05 - INFO - __main__ - Step 32800: {'lr': 0.0004484491976407192, 'samples': 6297600, 'steps': 32799, 'loss/train': 1.2846108675003052} 08/30/2021 19:10:06 - INFO - __main__ - Step 32801: {'lr': 0.00044844597012390374, 'samples': 6297792, 'steps': 32800, 'loss/train': 1.277563214302063} 08/30/2021 19:10:06 - INFO - __main__ - Step 32802: {'lr': 0.0004484427425176716, 'samples': 6297984, 'steps': 32801, 'loss/train': 1.9680557250976562} 08/30/2021 19:10:06 - INFO - __main__ - Step 32803: {'lr': 0.0004484395148220243, 'samples': 6298176, 'steps': 32802, 'loss/train': 1.4853097200393677} 08/30/2021 19:10:07 - INFO - __main__ - Step 32804: {'lr': 0.000448436287036963, 'samples': 6298368, 'steps': 32803, 'loss/train': 1.9306087493896484} 08/30/2021 19:10:08 - INFO - __main__ - Step 32805: {'lr': 0.0004484330591624896, 'samples': 6298560, 'steps': 32804, 'loss/train': 1.0610910654067993} 08/30/2021 19:10:09 - INFO - __main__ - Step 32806: {'lr': 0.00044842983119860525, 'samples': 6298752, 'steps': 32805, 'loss/train': 1.5891335010528564} 08/30/2021 19:10:09 - INFO - __main__ - Step 32807: {'lr': 0.00044842660314531145, 'samples': 6298944, 'steps': 32806, 'loss/train': 1.5910804271697998} 08/30/2021 19:10:09 - INFO - __main__ - Step 32808: {'lr': 0.0004484233750026098, 'samples': 6299136, 'steps': 32807, 'loss/train': 1.2846381664276123} 08/30/2021 19:10:10 - INFO - __main__ - Step 32809: {'lr': 0.00044842014677050145, 'samples': 6299328, 'steps': 32808, 'loss/train': 2.3574535846710205} 08/30/2021 19:10:12 - INFO - __main__ - Step 32810: {'lr': 0.0004484169184489882, 'samples': 6299520, 'steps': 32809, 'loss/train': 1.4643610715866089} 08/30/2021 19:10:13 - INFO - __main__ - Step 32811: {'lr': 0.0004484136900380713, 'samples': 6299712, 'steps': 32810, 'loss/train': 0.11108077317476273} 08/30/2021 19:10:13 - INFO - __main__ - Step 32812: {'lr': 0.00044841046153775224, 'samples': 6299904, 'steps': 32811, 'loss/train': 1.1247373819351196} 08/30/2021 19:10:13 - INFO - __main__ - Step 32813: {'lr': 0.0004484072329480325, 'samples': 6300096, 'steps': 32812, 'loss/train': 1.5413495302200317} 08/30/2021 19:10:14 - INFO - __main__ - Step 32814: {'lr': 0.00044840400426891347, 'samples': 6300288, 'steps': 32813, 'loss/train': 1.8364087343215942} 08/30/2021 19:10:15 - INFO - __main__ - Step 32815: {'lr': 0.00044840077550039676, 'samples': 6300480, 'steps': 32814, 'loss/train': 2.443309783935547} 08/30/2021 19:10:16 - INFO - __main__ - Step 32816: {'lr': 0.0004483975466424837, 'samples': 6300672, 'steps': 32815, 'loss/train': 1.6044660806655884} 08/30/2021 19:10:16 - INFO - __main__ - Step 32817: {'lr': 0.0004483943176951757, 'samples': 6300864, 'steps': 32816, 'loss/train': 1.4346952438354492} 08/30/2021 19:10:16 - INFO - __main__ - Step 32818: {'lr': 0.0004483910886584743, 'samples': 6301056, 'steps': 32817, 'loss/train': 0.5182101726531982} 08/30/2021 19:10:17 - INFO - __main__ - Step 32819: {'lr': 0.00044838785953238094, 'samples': 6301248, 'steps': 32818, 'loss/train': 1.564134120941162} 08/30/2021 19:10:18 - INFO - __main__ - Step 32820: {'lr': 0.0004483846303168971, 'samples': 6301440, 'steps': 32819, 'loss/train': 5.843997478485107} 08/30/2021 19:10:19 - INFO - __main__ - Step 32821: {'lr': 0.0004483814010120242, 'samples': 6301632, 'steps': 32820, 'loss/train': 0.6713508367538452} 08/30/2021 19:10:19 - INFO - __main__ - Step 32822: {'lr': 0.00044837817161776366, 'samples': 6301824, 'steps': 32821, 'loss/train': 1.1678550243377686} 08/30/2021 19:10:19 - INFO - __main__ - Step 32823: {'lr': 0.000448374942134117, 'samples': 6302016, 'steps': 32822, 'loss/train': 1.200532078742981} 08/30/2021 19:10:20 - INFO - __main__ - Step 32824: {'lr': 0.0004483717125610857, 'samples': 6302208, 'steps': 32823, 'loss/train': 1.3769738674163818} 08/30/2021 19:10:21 - INFO - __main__ - Step 32825: {'lr': 0.0004483684828986712, 'samples': 6302400, 'steps': 32824, 'loss/train': 0.6602734327316284} 08/30/2021 19:10:22 - INFO - __main__ - Step 32826: {'lr': 0.00044836525314687477, 'samples': 6302592, 'steps': 32825, 'loss/train': 1.5529022216796875} 08/30/2021 19:10:22 - INFO - __main__ - Step 32827: {'lr': 0.0004483620233056981, 'samples': 6302784, 'steps': 32826, 'loss/train': 1.3596118688583374} 08/30/2021 19:10:23 - INFO - __main__ - Step 32828: {'lr': 0.00044835879337514254, 'samples': 6302976, 'steps': 32827, 'loss/train': 0.3349132835865021} 08/30/2021 19:10:23 - INFO - __main__ - Step 32829: {'lr': 0.0004483555633552096, 'samples': 6303168, 'steps': 32828, 'loss/train': 1.4111298322677612} 08/30/2021 19:10:23 - INFO - __main__ - Step 32830: {'lr': 0.00044835233324590077, 'samples': 6303360, 'steps': 32829, 'loss/train': 1.9994674921035767} 08/30/2021 19:10:25 - INFO - __main__ - Step 32831: {'lr': 0.0004483491030472173, 'samples': 6303552, 'steps': 32830, 'loss/train': 1.2204504013061523} 08/30/2021 19:10:25 - INFO - __main__ - Step 32832: {'lr': 0.00044834587275916084, 'samples': 6303744, 'steps': 32831, 'loss/train': 1.4277275800704956} 08/30/2021 19:10:25 - INFO - __main__ - Step 32833: {'lr': 0.00044834264238173283, 'samples': 6303936, 'steps': 32832, 'loss/train': 1.8300209045410156} 08/30/2021 19:10:26 - INFO - __main__ - Step 32834: {'lr': 0.00044833941191493463, 'samples': 6304128, 'steps': 32833, 'loss/train': 1.5082029104232788} 08/30/2021 19:10:26 - INFO - __main__ - Step 32835: {'lr': 0.0004483361813587678, 'samples': 6304320, 'steps': 32834, 'loss/train': 1.2829923629760742} 08/30/2021 19:10:28 - INFO - __main__ - Step 32836: {'lr': 0.0004483329507132337, 'samples': 6304512, 'steps': 32835, 'loss/train': 1.0331817865371704} 08/30/2021 19:10:28 - INFO - __main__ - Step 32837: {'lr': 0.0004483297199783338, 'samples': 6304704, 'steps': 32836, 'loss/train': 1.5563338994979858} 08/30/2021 19:10:28 - INFO - __main__ - Step 32838: {'lr': 0.0004483264891540697, 'samples': 6304896, 'steps': 32837, 'loss/train': 1.225629210472107} 08/30/2021 19:10:29 - INFO - __main__ - Step 32839: {'lr': 0.00044832325824044274, 'samples': 6305088, 'steps': 32838, 'loss/train': 1.5003451108932495} 08/30/2021 19:10:29 - INFO - __main__ - Step 32840: {'lr': 0.0004483200272374543, 'samples': 6305280, 'steps': 32839, 'loss/train': 1.928655743598938} 08/30/2021 19:10:31 - INFO - __main__ - Step 32841: {'lr': 0.0004483167961451059, 'samples': 6305472, 'steps': 32840, 'loss/train': 0.3928397297859192} 08/30/2021 19:10:31 - INFO - __main__ - Step 32842: {'lr': 0.00044831356496339913, 'samples': 6305664, 'steps': 32841, 'loss/train': 0.057061389088630676} 08/30/2021 19:10:31 - INFO - __main__ - Step 32843: {'lr': 0.0004483103336923352, 'samples': 6305856, 'steps': 32842, 'loss/train': 0.6988543272018433} 08/30/2021 19:10:32 - INFO - __main__ - Step 32844: {'lr': 0.00044830710233191573, 'samples': 6306048, 'steps': 32843, 'loss/train': 0.26205503940582275} 08/30/2021 19:10:32 - INFO - __main__ - Step 32845: {'lr': 0.0004483038708821422, 'samples': 6306240, 'steps': 32844, 'loss/train': 1.4207615852355957} 08/30/2021 19:10:34 - INFO - __main__ - Step 32846: {'lr': 0.00044830063934301603, 'samples': 6306432, 'steps': 32845, 'loss/train': 1.0527763366699219} 08/30/2021 19:10:34 - INFO - __main__ - Step 32847: {'lr': 0.0004482974077145385, 'samples': 6306624, 'steps': 32846, 'loss/train': 1.5359408855438232} 08/30/2021 19:10:35 - INFO - __main__ - Step 32848: {'lr': 0.0004482941759967113, 'samples': 6306816, 'steps': 32847, 'loss/train': 2.462907552719116} 08/30/2021 19:10:35 - INFO - __main__ - Step 32849: {'lr': 0.00044829094418953586, 'samples': 6307008, 'steps': 32848, 'loss/train': 1.7602477073669434} 08/30/2021 19:10:35 - INFO - __main__ - Step 32850: {'lr': 0.00044828771229301354, 'samples': 6307200, 'steps': 32849, 'loss/train': 1.3864902257919312} 08/30/2021 19:10:37 - INFO - __main__ - Step 32851: {'lr': 0.0004482844803071458, 'samples': 6307392, 'steps': 32850, 'loss/train': 1.4359735250473022} 08/30/2021 19:10:37 - INFO - __main__ - Step 32852: {'lr': 0.00044828124823193417, 'samples': 6307584, 'steps': 32851, 'loss/train': 1.408004879951477} 08/30/2021 19:10:38 - INFO - __main__ - Step 32853: {'lr': 0.00044827801606738004, 'samples': 6307776, 'steps': 32852, 'loss/train': 0.5277725458145142} 08/30/2021 19:10:38 - INFO - __main__ - Step 32854: {'lr': 0.00044827478381348495, 'samples': 6307968, 'steps': 32853, 'loss/train': 1.0319784879684448} 08/30/2021 19:10:38 - INFO - __main__ - Step 32855: {'lr': 0.00044827155147025025, 'samples': 6308160, 'steps': 32854, 'loss/train': 1.5729713439941406} 08/30/2021 19:10:40 - INFO - __main__ - Step 32856: {'lr': 0.00044826831903767745, 'samples': 6308352, 'steps': 32855, 'loss/train': 1.4462401866912842} 08/30/2021 19:10:41 - INFO - __main__ - Step 32857: {'lr': 0.000448265086515768, 'samples': 6308544, 'steps': 32856, 'loss/train': 1.4757256507873535} 08/30/2021 19:10:41 - INFO - __main__ - Step 32858: {'lr': 0.0004482618539045234, 'samples': 6308736, 'steps': 32857, 'loss/train': 1.4521393775939941} 08/30/2021 19:10:41 - INFO - __main__ - Step 32859: {'lr': 0.00044825862120394504, 'samples': 6308928, 'steps': 32858, 'loss/train': 1.6196850538253784} 08/30/2021 19:10:42 - INFO - __main__ - Step 32860: {'lr': 0.00044825538841403444, 'samples': 6309120, 'steps': 32859, 'loss/train': 1.2773644924163818} 08/30/2021 19:10:42 - INFO - __main__ - Step 32861: {'lr': 0.000448252155534793, 'samples': 6309312, 'steps': 32860, 'loss/train': 0.028032349422574043} 08/30/2021 19:10:44 - INFO - __main__ - Step 32862: {'lr': 0.0004482489225662222, 'samples': 6309504, 'steps': 32861, 'loss/train': 1.7170188426971436} 08/30/2021 19:10:45 - INFO - __main__ - Step 32863: {'lr': 0.00044824568950832343, 'samples': 6309696, 'steps': 32862, 'loss/train': 1.2952020168304443} 08/30/2021 19:10:45 - INFO - __main__ - Step 32864: {'lr': 0.0004482424563610983, 'samples': 6309888, 'steps': 32863, 'loss/train': 1.0653008222579956} 08/30/2021 19:10:45 - INFO - __main__ - Step 32865: {'lr': 0.00044823922312454815, 'samples': 6310080, 'steps': 32864, 'loss/train': 1.279534101486206} 08/30/2021 19:10:46 - INFO - __main__ - Step 32866: {'lr': 0.00044823598979867445, 'samples': 6310272, 'steps': 32865, 'loss/train': 1.3014886379241943} 08/30/2021 19:10:46 - INFO - __main__ - Step 32867: {'lr': 0.0004482327563834787, 'samples': 6310464, 'steps': 32866, 'loss/train': 1.071877121925354} 08/30/2021 19:10:48 - INFO - __main__ - Step 32868: {'lr': 0.00044822952287896237, 'samples': 6310656, 'steps': 32867, 'loss/train': 1.4732680320739746} 08/30/2021 19:10:48 - INFO - __main__ - Step 32869: {'lr': 0.00044822628928512675, 'samples': 6310848, 'steps': 32868, 'loss/train': 1.6002378463745117} 08/30/2021 19:10:48 - INFO - __main__ - Step 32870: {'lr': 0.0004482230556019735, 'samples': 6311040, 'steps': 32869, 'loss/train': 1.1972324848175049} 08/30/2021 19:10:49 - INFO - __main__ - Step 32871: {'lr': 0.00044821982182950405, 'samples': 6311232, 'steps': 32870, 'loss/train': 1.9368282556533813} 08/30/2021 19:10:49 - INFO - __main__ - Step 32872: {'lr': 0.0004482165879677197, 'samples': 6311424, 'steps': 32871, 'loss/train': 1.9383968114852905} 08/30/2021 19:10:51 - INFO - __main__ - Step 32873: {'lr': 0.0004482133540166221, 'samples': 6311616, 'steps': 32872, 'loss/train': 2.573394775390625} 08/30/2021 19:10:52 - INFO - __main__ - Step 32874: {'lr': 0.00044821011997621255, 'samples': 6311808, 'steps': 32873, 'loss/train': 0.07509901374578476} 08/30/2021 19:10:52 - INFO - __main__ - Step 32875: {'lr': 0.0004482068858464926, 'samples': 6312000, 'steps': 32874, 'loss/train': 1.333949089050293} 08/30/2021 19:10:52 - INFO - __main__ - Step 32876: {'lr': 0.00044820365162746373, 'samples': 6312192, 'steps': 32875, 'loss/train': 0.07692991942167282} 08/30/2021 19:10:53 - INFO - __main__ - Step 32877: {'lr': 0.00044820041731912733, 'samples': 6312384, 'steps': 32876, 'loss/train': 0.05485493317246437} 08/30/2021 19:10:53 - INFO - __main__ - Step 32878: {'lr': 0.0004481971829214848, 'samples': 6312576, 'steps': 32877, 'loss/train': 1.114728569984436} 08/30/2021 19:10:55 - INFO - __main__ - Step 32879: {'lr': 0.0004481939484345378, 'samples': 6312768, 'steps': 32878, 'loss/train': 1.8709505796432495} 08/30/2021 19:10:55 - INFO - __main__ - Step 32880: {'lr': 0.0004481907138582876, 'samples': 6312960, 'steps': 32879, 'loss/train': 1.565878987312317} 08/30/2021 19:10:56 - INFO - __main__ - Step 32881: {'lr': 0.00044818747919273574, 'samples': 6313152, 'steps': 32880, 'loss/train': 1.45503568649292} 08/30/2021 19:10:56 - INFO - __main__ - Step 32882: {'lr': 0.0004481842444378837, 'samples': 6313344, 'steps': 32881, 'loss/train': 1.6048507690429688} 08/30/2021 19:10:56 - INFO - __main__ - Step 32883: {'lr': 0.0004481810095937329, 'samples': 6313536, 'steps': 32882, 'loss/train': 1.7029558420181274} 08/30/2021 19:10:57 - INFO - __main__ - Step 32884: {'lr': 0.00044817777466028467, 'samples': 6313728, 'steps': 32883, 'loss/train': 1.2898426055908203} 08/30/2021 19:10:58 - INFO - __main__ - Step 32885: {'lr': 0.0004481745396375407, 'samples': 6313920, 'steps': 32884, 'loss/train': 0.8254020810127258} 08/30/2021 19:10:59 - INFO - __main__ - Step 32886: {'lr': 0.0004481713045255023, 'samples': 6314112, 'steps': 32885, 'loss/train': 2.064681053161621} 08/30/2021 19:10:59 - INFO - __main__ - Step 32887: {'lr': 0.000448168069324171, 'samples': 6314304, 'steps': 32886, 'loss/train': 1.5842360258102417} 08/30/2021 19:10:59 - INFO - __main__ - Step 32888: {'lr': 0.0004481648340335482, 'samples': 6314496, 'steps': 32887, 'loss/train': 1.7877769470214844} 08/30/2021 19:11:00 - INFO - __main__ - Step 32889: {'lr': 0.0004481615986536354, 'samples': 6314688, 'steps': 32888, 'loss/train': 2.089043378829956} 08/30/2021 19:11:01 - INFO - __main__ - Step 32890: {'lr': 0.000448158363184434, 'samples': 6314880, 'steps': 32889, 'loss/train': 1.4092888832092285} 08/30/2021 19:11:02 - INFO - __main__ - Step 32891: {'lr': 0.00044815512762594556, 'samples': 6315072, 'steps': 32890, 'loss/train': 1.306431531906128} 08/30/2021 19:11:02 - INFO - __main__ - Step 32892: {'lr': 0.00044815189197817143, 'samples': 6315264, 'steps': 32891, 'loss/train': 1.7321676015853882} 08/30/2021 19:11:03 - INFO - __main__ - Step 32893: {'lr': 0.0004481486562411131, 'samples': 6315456, 'steps': 32892, 'loss/train': 1.692110300064087} 08/30/2021 19:11:03 - INFO - __main__ - Step 32894: {'lr': 0.0004481454204147721, 'samples': 6315648, 'steps': 32893, 'loss/train': 1.518251895904541} 08/30/2021 19:11:05 - INFO - __main__ - Step 32895: {'lr': 0.0004481421844991498, 'samples': 6315840, 'steps': 32894, 'loss/train': 1.3641338348388672} 08/30/2021 19:11:05 - INFO - __main__ - Step 32896: {'lr': 0.00044813894849424777, 'samples': 6316032, 'steps': 32895, 'loss/train': 1.3225665092468262} 08/30/2021 19:11:05 - INFO - __main__ - Step 32897: {'lr': 0.0004481357124000672, 'samples': 6316224, 'steps': 32896, 'loss/train': 1.2750303745269775} 08/30/2021 19:11:06 - INFO - __main__ - Step 32898: {'lr': 0.0004481324762166099, 'samples': 6316416, 'steps': 32897, 'loss/train': 2.331758975982666} 08/30/2021 19:11:06 - INFO - __main__ - Step 32899: {'lr': 0.0004481292399438771, 'samples': 6316608, 'steps': 32898, 'loss/train': 1.3119992017745972} 08/30/2021 19:11:08 - INFO - __main__ - Step 32900: {'lr': 0.0004481260035818704, 'samples': 6316800, 'steps': 32899, 'loss/train': 2.2424676418304443} 08/30/2021 19:11:08 - INFO - __main__ - Step 32901: {'lr': 0.00044812276713059106, 'samples': 6316992, 'steps': 32900, 'loss/train': 1.5014487504959106} 08/30/2021 19:11:08 - INFO - __main__ - Step 32902: {'lr': 0.00044811953059004073, 'samples': 6317184, 'steps': 32901, 'loss/train': 1.6551412343978882} 08/30/2021 19:11:09 - INFO - __main__ - Step 32903: {'lr': 0.0004481162939602208, 'samples': 6317376, 'steps': 32902, 'loss/train': 1.285164713859558} 08/30/2021 19:11:09 - INFO - __main__ - Step 32904: {'lr': 0.0004481130572411327, 'samples': 6317568, 'steps': 32903, 'loss/train': 1.6648117303848267} 08/30/2021 19:11:10 - INFO - __main__ - Step 32905: {'lr': 0.00044810982043277795, 'samples': 6317760, 'steps': 32904, 'loss/train': 0.7461702823638916} 08/30/2021 19:11:11 - INFO - __main__ - Step 32906: {'lr': 0.0004481065835351579, 'samples': 6317952, 'steps': 32905, 'loss/train': 0.8383270502090454} 08/30/2021 19:11:12 - INFO - __main__ - Step 32907: {'lr': 0.0004481033465482741, 'samples': 6318144, 'steps': 32906, 'loss/train': 1.3237212896347046} 08/30/2021 19:11:12 - INFO - __main__ - Step 32908: {'lr': 0.00044810010947212803, 'samples': 6318336, 'steps': 32907, 'loss/train': 1.6517670154571533} 08/30/2021 19:11:13 - INFO - __main__ - Step 32909: {'lr': 0.00044809687230672115, 'samples': 6318528, 'steps': 32908, 'loss/train': 2.0691163539886475} 08/30/2021 19:11:13 - INFO - __main__ - Step 32910: {'lr': 0.0004480936350520548, 'samples': 6318720, 'steps': 32909, 'loss/train': 3.0470848083496094} 08/30/2021 19:11:13 - INFO - __main__ - Step 32911: {'lr': 0.0004480903977081305, 'samples': 6318912, 'steps': 32910, 'loss/train': 1.6182889938354492} 08/30/2021 19:11:15 - INFO - __main__ - Step 32912: {'lr': 0.00044808716027494973, 'samples': 6319104, 'steps': 32911, 'loss/train': 1.622750997543335} 08/30/2021 19:11:15 - INFO - __main__ - Step 32913: {'lr': 0.000448083922752514, 'samples': 6319296, 'steps': 32912, 'loss/train': 1.1536993980407715} 08/30/2021 19:11:16 - INFO - __main__ - Step 32914: {'lr': 0.00044808068514082467, 'samples': 6319488, 'steps': 32913, 'loss/train': 1.4181472063064575} 08/30/2021 19:11:16 - INFO - __main__ - Step 32915: {'lr': 0.0004480774474398832, 'samples': 6319680, 'steps': 32914, 'loss/train': 1.9158234596252441} 08/30/2021 19:11:16 - INFO - __main__ - Step 32916: {'lr': 0.00044807420964969113, 'samples': 6319872, 'steps': 32915, 'loss/train': 1.9926166534423828} 08/30/2021 19:11:18 - INFO - __main__ - Step 32917: {'lr': 0.0004480709717702499, 'samples': 6320064, 'steps': 32916, 'loss/train': 2.0427207946777344} 08/30/2021 19:11:19 - INFO - __main__ - Step 32918: {'lr': 0.000448067733801561, 'samples': 6320256, 'steps': 32917, 'loss/train': 1.439934253692627} 08/30/2021 19:11:19 - INFO - __main__ - Step 32919: {'lr': 0.00044806449574362575, 'samples': 6320448, 'steps': 32918, 'loss/train': 1.6649162769317627} 08/30/2021 19:11:19 - INFO - __main__ - Step 32920: {'lr': 0.00044806125759644567, 'samples': 6320640, 'steps': 32919, 'loss/train': 1.4974573850631714} 08/30/2021 19:11:20 - INFO - __main__ - Step 32921: {'lr': 0.00044805801936002225, 'samples': 6320832, 'steps': 32920, 'loss/train': 7.483266353607178} 08/30/2021 19:11:20 - INFO - __main__ - Step 32922: {'lr': 0.00044805478103435707, 'samples': 6321024, 'steps': 32921, 'loss/train': 1.9284188747406006} 08/30/2021 19:11:22 - INFO - __main__ - Step 32923: {'lr': 0.0004480515426194513, 'samples': 6321216, 'steps': 32922, 'loss/train': 1.7512258291244507} 08/30/2021 19:11:23 - INFO - __main__ - Step 32924: {'lr': 0.0004480483041153066, 'samples': 6321408, 'steps': 32923, 'loss/train': 2.1436784267425537} 08/30/2021 19:11:23 - INFO - __main__ - Step 32925: {'lr': 0.00044804506552192447, 'samples': 6321600, 'steps': 32924, 'loss/train': 1.8077055215835571} 08/30/2021 19:11:23 - INFO - __main__ - Step 32926: {'lr': 0.0004480418268393062, 'samples': 6321792, 'steps': 32925, 'loss/train': 1.9932621717453003} 08/30/2021 19:11:24 - INFO - __main__ - Step 32927: {'lr': 0.0004480385880674534, 'samples': 6321984, 'steps': 32926, 'loss/train': 1.8775341510772705} 08/30/2021 19:11:26 - INFO - __main__ - Step 32928: {'lr': 0.00044803534920636744, 'samples': 6322176, 'steps': 32927, 'loss/train': 1.1780743598937988} 08/30/2021 19:11:26 - INFO - __main__ - Step 32929: {'lr': 0.00044803211025604985, 'samples': 6322368, 'steps': 32928, 'loss/train': 1.2579072713851929} 08/30/2021 19:11:26 - INFO - __main__ - Step 32930: {'lr': 0.000448028871216502, 'samples': 6322560, 'steps': 32929, 'loss/train': 0.7032141089439392} 08/30/2021 19:11:27 - INFO - __main__ - Step 32931: {'lr': 0.0004480256320877254, 'samples': 6322752, 'steps': 32930, 'loss/train': 0.545499324798584} 08/30/2021 19:11:27 - INFO - __main__ - Step 32932: {'lr': 0.00044802239286972147, 'samples': 6322944, 'steps': 32931, 'loss/train': 1.4685508012771606} 08/30/2021 19:11:27 - INFO - __main__ - Step 32933: {'lr': 0.0004480191535624918, 'samples': 6323136, 'steps': 32932, 'loss/train': 0.3264021575450897} 08/30/2021 19:11:29 - INFO - __main__ - Step 32934: {'lr': 0.0004480159141660377, 'samples': 6323328, 'steps': 32933, 'loss/train': 0.9525347948074341} 08/30/2021 19:11:30 - INFO - __main__ - Step 32935: {'lr': 0.00044801267468036064, 'samples': 6323520, 'steps': 32934, 'loss/train': 1.7658441066741943} 08/30/2021 19:11:30 - INFO - __main__ - Step 32936: {'lr': 0.0004480094351054622, 'samples': 6323712, 'steps': 32935, 'loss/train': 1.2192119359970093} 08/30/2021 19:11:30 - INFO - __main__ - Step 32937: {'lr': 0.00044800619544134375, 'samples': 6323904, 'steps': 32936, 'loss/train': 1.8914642333984375} 08/30/2021 19:11:31 - INFO - __main__ - Step 32938: {'lr': 0.00044800295568800673, 'samples': 6324096, 'steps': 32937, 'loss/train': 2.274127721786499} 08/30/2021 19:11:31 - INFO - __main__ - Step 32939: {'lr': 0.0004479997158454526, 'samples': 6324288, 'steps': 32938, 'loss/train': 3.3844077587127686} 08/30/2021 19:11:32 - INFO - __main__ - Step 32940: {'lr': 0.00044799647591368296, 'samples': 6324480, 'steps': 32939, 'loss/train': 1.9486433267593384} 08/30/2021 19:11:33 - INFO - __main__ - Step 32941: {'lr': 0.00044799323589269914, 'samples': 6324672, 'steps': 32940, 'loss/train': 1.6158136129379272} 08/30/2021 19:11:33 - INFO - __main__ - Step 32942: {'lr': 0.00044798999578250255, 'samples': 6324864, 'steps': 32941, 'loss/train': 1.310711145401001} 08/30/2021 19:11:34 - INFO - __main__ - Step 32943: {'lr': 0.0004479867555830948, 'samples': 6325056, 'steps': 32942, 'loss/train': 1.3904486894607544} 08/30/2021 19:11:34 - INFO - __main__ - Step 32944: {'lr': 0.0004479835152944772, 'samples': 6325248, 'steps': 32943, 'loss/train': 1.6982293128967285} 08/30/2021 19:11:35 - INFO - __main__ - Step 32945: {'lr': 0.00044798027491665135, 'samples': 6325440, 'steps': 32944, 'loss/train': 1.9827361106872559} 08/30/2021 19:11:36 - INFO - __main__ - Step 32946: {'lr': 0.00044797703444961857, 'samples': 6325632, 'steps': 32945, 'loss/train': 1.3845924139022827} 08/30/2021 19:11:36 - INFO - __main__ - Step 32947: {'lr': 0.00044797379389338045, 'samples': 6325824, 'steps': 32946, 'loss/train': 2.106088876724243} 08/30/2021 19:11:37 - INFO - __main__ - Step 32948: {'lr': 0.0004479705532479384, 'samples': 6326016, 'steps': 32947, 'loss/train': 1.5674136877059937} 08/30/2021 19:11:37 - INFO - __main__ - Step 32949: {'lr': 0.0004479673125132938, 'samples': 6326208, 'steps': 32948, 'loss/train': 1.493359088897705} 08/30/2021 19:11:39 - INFO - __main__ - Step 32950: {'lr': 0.0004479640716894483, 'samples': 6326400, 'steps': 32949, 'loss/train': 1.832162857055664} 08/30/2021 19:11:39 - INFO - __main__ - Step 32951: {'lr': 0.00044796083077640314, 'samples': 6326592, 'steps': 32950, 'loss/train': 1.3775365352630615} 08/30/2021 19:11:39 - INFO - __main__ - Step 32952: {'lr': 0.00044795758977416, 'samples': 6326784, 'steps': 32951, 'loss/train': 1.848576307296753} 08/30/2021 19:11:40 - INFO - __main__ - Step 32953: {'lr': 0.0004479543486827201, 'samples': 6326976, 'steps': 32952, 'loss/train': 1.3696128129959106} 08/30/2021 19:11:40 - INFO - __main__ - Step 32954: {'lr': 0.0004479511075020851, 'samples': 6327168, 'steps': 32953, 'loss/train': 1.454092025756836} 08/30/2021 19:11:42 - INFO - __main__ - Step 32955: {'lr': 0.00044794786623225636, 'samples': 6327360, 'steps': 32954, 'loss/train': 1.6693100929260254} 08/30/2021 19:11:42 - INFO - __main__ - Step 32956: {'lr': 0.0004479446248732354, 'samples': 6327552, 'steps': 32955, 'loss/train': 1.5475125312805176} 08/30/2021 19:11:43 - INFO - __main__ - Step 32957: {'lr': 0.00044794138342502354, 'samples': 6327744, 'steps': 32956, 'loss/train': 1.6520280838012695} 08/30/2021 19:11:43 - INFO - __main__ - Step 32958: {'lr': 0.0004479381418876225, 'samples': 6327936, 'steps': 32957, 'loss/train': 1.093580722808838} 08/30/2021 19:11:43 - INFO - __main__ - Step 32959: {'lr': 0.00044793490026103346, 'samples': 6328128, 'steps': 32958, 'loss/train': 1.9214324951171875} 08/30/2021 19:11:44 - INFO - __main__ - Step 32960: {'lr': 0.0004479316585452581, 'samples': 6328320, 'steps': 32959, 'loss/train': 1.2760549783706665} 08/30/2021 19:11:45 - INFO - __main__ - Step 32961: {'lr': 0.0004479284167402977, 'samples': 6328512, 'steps': 32960, 'loss/train': 0.21415410935878754} 08/30/2021 19:11:46 - INFO - __main__ - Step 32962: {'lr': 0.00044792517484615384, 'samples': 6328704, 'steps': 32961, 'loss/train': 1.455647349357605} 08/30/2021 19:11:46 - INFO - __main__ - Step 32963: {'lr': 0.000447921932862828, 'samples': 6328896, 'steps': 32962, 'loss/train': 1.6069492101669312} 08/30/2021 19:11:46 - INFO - __main__ - Step 32964: {'lr': 0.00044791869079032154, 'samples': 6329088, 'steps': 32963, 'loss/train': 0.2214856892824173} 08/30/2021 19:11:47 - INFO - __main__ - Step 32965: {'lr': 0.000447915448628636, 'samples': 6329280, 'steps': 32964, 'loss/train': 1.82004714012146} 08/30/2021 19:11:48 - INFO - __main__ - Step 32966: {'lr': 0.0004479122063777728, 'samples': 6329472, 'steps': 32965, 'loss/train': 1.7380435466766357} 08/30/2021 19:11:49 - INFO - __main__ - Step 32967: {'lr': 0.0004479089640377334, 'samples': 6329664, 'steps': 32966, 'loss/train': 1.6890532970428467} 08/30/2021 19:11:49 - INFO - __main__ - Step 32968: {'lr': 0.00044790572160851926, 'samples': 6329856, 'steps': 32967, 'loss/train': 1.6374168395996094} 08/30/2021 19:11:49 - INFO - __main__ - Step 32969: {'lr': 0.00044790247909013195, 'samples': 6330048, 'steps': 32968, 'loss/train': 1.3972340822219849} 08/30/2021 19:11:50 - INFO - __main__ - Step 32970: {'lr': 0.0004478992364825728, 'samples': 6330240, 'steps': 32969, 'loss/train': 2.006917953491211} 08/30/2021 19:11:51 - INFO - __main__ - Step 32971: {'lr': 0.00044789599378584324, 'samples': 6330432, 'steps': 32970, 'loss/train': 2.019718647003174} 08/30/2021 19:11:52 - INFO - __main__ - Step 32972: {'lr': 0.0004478927509999449, 'samples': 6330624, 'steps': 32971, 'loss/train': 1.4682337045669556} 08/30/2021 19:11:52 - INFO - __main__ - Step 32973: {'lr': 0.00044788950812487907, 'samples': 6330816, 'steps': 32972, 'loss/train': 1.6100172996520996} 08/30/2021 19:11:53 - INFO - __main__ - Step 32974: {'lr': 0.0004478862651606472, 'samples': 6331008, 'steps': 32973, 'loss/train': 1.8336241245269775} 08/30/2021 19:11:53 - INFO - __main__ - Step 32975: {'lr': 0.000447883022107251, 'samples': 6331200, 'steps': 32974, 'loss/train': 0.11317329853773117} 08/30/2021 19:11:55 - INFO - __main__ - Step 32976: {'lr': 0.00044787977896469167, 'samples': 6331392, 'steps': 32975, 'loss/train': 1.674653172492981} 08/30/2021 19:11:56 - INFO - __main__ - Step 32977: {'lr': 0.0004478765357329708, 'samples': 6331584, 'steps': 32976, 'loss/train': 0.08602840453386307} 08/30/2021 19:11:56 - INFO - __main__ - Step 32978: {'lr': 0.0004478732924120897, 'samples': 6331776, 'steps': 32977, 'loss/train': 5.00439977645874} 08/30/2021 19:11:56 - INFO - __main__ - Step 32979: {'lr': 0.0004478700490020501, 'samples': 6331968, 'steps': 32978, 'loss/train': 1.5188087224960327} 08/30/2021 19:11:57 - INFO - __main__ - Step 32980: {'lr': 0.0004478668055028533, 'samples': 6332160, 'steps': 32979, 'loss/train': 1.8274298906326294} 08/30/2021 19:11:58 - INFO - __main__ - Step 32981: {'lr': 0.0004478635619145007, 'samples': 6332352, 'steps': 32980, 'loss/train': 0.07970250397920609} 08/30/2021 19:11:59 - INFO - __main__ - Step 32982: {'lr': 0.00044786031823699384, 'samples': 6332544, 'steps': 32981, 'loss/train': 0.8789415955543518} 08/30/2021 19:11:59 - INFO - __main__ - Step 32983: {'lr': 0.0004478570744703342, 'samples': 6332736, 'steps': 32982, 'loss/train': 2.237499475479126} 08/30/2021 19:12:00 - INFO - __main__ - Step 32984: {'lr': 0.00044785383061452324, 'samples': 6332928, 'steps': 32983, 'loss/train': 1.8818144798278809} 08/30/2021 19:12:00 - INFO - __main__ - Step 32985: {'lr': 0.00044785058666956234, 'samples': 6333120, 'steps': 32984, 'loss/train': 1.673393726348877} 08/30/2021 19:12:02 - INFO - __main__ - Step 32986: {'lr': 0.000447847342635453, 'samples': 6333312, 'steps': 32985, 'loss/train': 1.3741319179534912} 08/30/2021 19:12:02 - INFO - __main__ - Step 32987: {'lr': 0.00044784409851219675, 'samples': 6333504, 'steps': 32986, 'loss/train': 1.6277153491973877} 08/30/2021 19:12:02 - INFO - __main__ - Step 32988: {'lr': 0.00044784085429979504, 'samples': 6333696, 'steps': 32987, 'loss/train': 1.3665305376052856} 08/30/2021 19:12:03 - INFO - __main__ - Step 32989: {'lr': 0.00044783760999824926, 'samples': 6333888, 'steps': 32988, 'loss/train': 1.4518558979034424} 08/30/2021 19:12:03 - INFO - __main__ - Step 32990: {'lr': 0.00044783436560756086, 'samples': 6334080, 'steps': 32989, 'loss/train': 1.3715745210647583} 08/30/2021 19:12:05 - INFO - __main__ - Step 32991: {'lr': 0.00044783112112773137, 'samples': 6334272, 'steps': 32990, 'loss/train': 0.1078360378742218} 08/30/2021 19:12:06 - INFO - __main__ - Step 32992: {'lr': 0.0004478278765587623, 'samples': 6334464, 'steps': 32991, 'loss/train': 1.7439976930618286} 08/30/2021 19:12:06 - INFO - __main__ - Step 32993: {'lr': 0.000447824631900655, 'samples': 6334656, 'steps': 32992, 'loss/train': 1.2109761238098145} 08/30/2021 19:12:06 - INFO - __main__ - Step 32994: {'lr': 0.00044782138715341094, 'samples': 6334848, 'steps': 32993, 'loss/train': 1.4433255195617676} 08/30/2021 19:12:07 - INFO - __main__ - Step 32995: {'lr': 0.00044781814231703164, 'samples': 6335040, 'steps': 32994, 'loss/train': 0.19289101660251617} 08/30/2021 19:12:07 - INFO - __main__ - Step 32996: {'lr': 0.00044781489739151856, 'samples': 6335232, 'steps': 32995, 'loss/train': 0.1301116943359375} 08/30/2021 19:12:07 - INFO - __main__ - Step 32997: {'lr': 0.00044781165237687306, 'samples': 6335424, 'steps': 32996, 'loss/train': 1.980476975440979} 08/30/2021 19:12:09 - INFO - __main__ - Step 32998: {'lr': 0.00044780840727309676, 'samples': 6335616, 'steps': 32997, 'loss/train': 1.5653765201568604} 08/30/2021 19:12:10 - INFO - __main__ - Step 32999: {'lr': 0.000447805162080191, 'samples': 6335808, 'steps': 32998, 'loss/train': 1.941420555114746} 08/30/2021 19:12:10 - INFO - __main__ - Step 33000: {'lr': 0.0004478019167981573, 'samples': 6336000, 'steps': 32999, 'loss/train': 2.404331922531128} 08/30/2021 19:12:10 - INFO - __main__ - Step 33001: {'lr': 0.00044779867142699713, 'samples': 6336192, 'steps': 33000, 'loss/train': 1.3778611421585083} 08/30/2021 19:12:11 - INFO - __main__ - Step 33002: {'lr': 0.0004477954259667119, 'samples': 6336384, 'steps': 33001, 'loss/train': 0.4002549648284912} 08/30/2021 19:12:12 - INFO - __main__ - Step 33003: {'lr': 0.00044779218041730314, 'samples': 6336576, 'steps': 33002, 'loss/train': 1.8848958015441895} 08/30/2021 19:12:13 - INFO - __main__ - Step 33004: {'lr': 0.00044778893477877225, 'samples': 6336768, 'steps': 33003, 'loss/train': 1.8599143028259277} 08/30/2021 19:12:13 - INFO - __main__ - Step 33005: {'lr': 0.0004477856890511207, 'samples': 6336960, 'steps': 33004, 'loss/train': 2.093334436416626} 08/30/2021 19:12:13 - INFO - __main__ - Step 33006: {'lr': 0.00044778244323435, 'samples': 6337152, 'steps': 33005, 'loss/train': 0.7927687764167786} 08/30/2021 19:12:14 - INFO - __main__ - Step 33007: {'lr': 0.0004477791973284616, 'samples': 6337344, 'steps': 33006, 'loss/train': 1.536917805671692} 08/30/2021 19:12:15 - INFO - __main__ - Step 33008: {'lr': 0.00044777595133345686, 'samples': 6337536, 'steps': 33007, 'loss/train': 2.1827054023742676} 08/30/2021 19:12:16 - INFO - __main__ - Step 33009: {'lr': 0.0004477727052493374, 'samples': 6337728, 'steps': 33008, 'loss/train': 1.6933008432388306} 08/30/2021 19:12:16 - INFO - __main__ - Step 33010: {'lr': 0.0004477694590761046, 'samples': 6337920, 'steps': 33009, 'loss/train': 1.3053333759307861} 08/30/2021 19:12:16 - INFO - __main__ - Step 33011: {'lr': 0.00044776621281375994, 'samples': 6338112, 'steps': 33010, 'loss/train': 1.5660881996154785} 08/30/2021 19:12:17 - INFO - __main__ - Step 33012: {'lr': 0.00044776296646230487, 'samples': 6338304, 'steps': 33011, 'loss/train': 1.2377856969833374} 08/30/2021 19:12:18 - INFO - __main__ - Step 33013: {'lr': 0.00044775972002174085, 'samples': 6338496, 'steps': 33012, 'loss/train': 1.8807965517044067} 08/30/2021 19:12:19 - INFO - __main__ - Step 33014: {'lr': 0.0004477564734920694, 'samples': 6338688, 'steps': 33013, 'loss/train': 2.111697196960449} 08/30/2021 19:12:19 - INFO - __main__ - Step 33015: {'lr': 0.0004477532268732919, 'samples': 6338880, 'steps': 33014, 'loss/train': 1.398719072341919} 08/30/2021 19:12:19 - INFO - __main__ - Step 33016: {'lr': 0.00044774998016540977, 'samples': 6339072, 'steps': 33015, 'loss/train': 1.5961471796035767} 08/30/2021 19:12:20 - INFO - __main__ - Step 33017: {'lr': 0.00044774673336842464, 'samples': 6339264, 'steps': 33016, 'loss/train': 1.4610909223556519} 08/30/2021 19:12:21 - INFO - __main__ - Step 33018: {'lr': 0.0004477434864823379, 'samples': 6339456, 'steps': 33017, 'loss/train': 1.4359678030014038} 08/30/2021 19:12:22 - INFO - __main__ - Step 33019: {'lr': 0.00044774023950715095, 'samples': 6339648, 'steps': 33018, 'loss/train': 1.4415203332901} 08/30/2021 19:12:22 - INFO - __main__ - Step 33020: {'lr': 0.0004477369924428653, 'samples': 6339840, 'steps': 33019, 'loss/train': 2.5177664756774902} 08/30/2021 19:12:23 - INFO - __main__ - Step 33021: {'lr': 0.0004477337452894824, 'samples': 6340032, 'steps': 33020, 'loss/train': 1.6190192699432373} 08/30/2021 19:12:23 - INFO - __main__ - Step 33022: {'lr': 0.0004477304980470038, 'samples': 6340224, 'steps': 33021, 'loss/train': 1.6459637880325317} 08/30/2021 19:12:23 - INFO - __main__ - Step 33023: {'lr': 0.0004477272507154308, 'samples': 6340416, 'steps': 33022, 'loss/train': 1.5261080265045166} 08/30/2021 19:12:25 - INFO - __main__ - Step 33024: {'lr': 0.00044772400329476505, 'samples': 6340608, 'steps': 33023, 'loss/train': 1.8532192707061768} 08/30/2021 19:12:25 - INFO - __main__ - Step 33025: {'lr': 0.0004477207557850078, 'samples': 6340800, 'steps': 33024, 'loss/train': 2.0004000663757324} 08/30/2021 19:12:26 - INFO - __main__ - Step 33026: {'lr': 0.00044771750818616067, 'samples': 6340992, 'steps': 33025, 'loss/train': 1.6905608177185059} 08/30/2021 19:12:26 - INFO - __main__ - Step 33027: {'lr': 0.0004477142604982251, 'samples': 6341184, 'steps': 33026, 'loss/train': 1.8551526069641113} 08/30/2021 19:12:26 - INFO - __main__ - Step 33028: {'lr': 0.0004477110127212025, 'samples': 6341376, 'steps': 33027, 'loss/train': 1.2083057165145874} 08/30/2021 19:12:28 - INFO - __main__ - Step 33029: {'lr': 0.00044770776485509445, 'samples': 6341568, 'steps': 33028, 'loss/train': 1.5260268449783325} 08/30/2021 19:12:28 - INFO - __main__ - Step 33030: {'lr': 0.00044770451689990227, 'samples': 6341760, 'steps': 33029, 'loss/train': 5.980719089508057} 08/30/2021 19:12:29 - INFO - __main__ - Step 33031: {'lr': 0.0004477012688556275, 'samples': 6341952, 'steps': 33030, 'loss/train': 1.6847401857376099} 08/30/2021 19:12:29 - INFO - __main__ - Step 33032: {'lr': 0.0004476980207222716, 'samples': 6342144, 'steps': 33031, 'loss/train': 1.6102837324142456} 08/30/2021 19:12:29 - INFO - __main__ - Step 33033: {'lr': 0.00044769477249983596, 'samples': 6342336, 'steps': 33032, 'loss/train': 2.2273123264312744} 08/30/2021 19:12:32 - INFO - __main__ - Step 33034: {'lr': 0.00044769152418832215, 'samples': 6342528, 'steps': 33033, 'loss/train': 1.6433876752853394} 08/30/2021 19:12:32 - INFO - __main__ - Step 33035: {'lr': 0.00044768827578773164, 'samples': 6342720, 'steps': 33034, 'loss/train': 2.5449917316436768} 08/30/2021 19:12:32 - INFO - __main__ - Step 33036: {'lr': 0.00044768502729806574, 'samples': 6342912, 'steps': 33035, 'loss/train': 0.0667106881737709} 08/30/2021 19:12:33 - INFO - __main__ - Step 33037: {'lr': 0.0004476817787193261, 'samples': 6343104, 'steps': 33036, 'loss/train': 1.247261881828308} 08/30/2021 19:12:33 - INFO - __main__ - Step 33038: {'lr': 0.0004476785300515141, 'samples': 6343296, 'steps': 33037, 'loss/train': 1.3547941446304321} 08/30/2021 19:12:33 - INFO - __main__ - Step 33039: {'lr': 0.0004476752812946312, 'samples': 6343488, 'steps': 33038, 'loss/train': 1.5243659019470215} 08/30/2021 19:12:35 - INFO - __main__ - Step 33040: {'lr': 0.0004476720324486788, 'samples': 6343680, 'steps': 33039, 'loss/train': 1.8858058452606201} 08/30/2021 19:12:36 - INFO - __main__ - Step 33041: {'lr': 0.0004476687835136585, 'samples': 6343872, 'steps': 33040, 'loss/train': 1.2914764881134033} 08/30/2021 19:12:36 - INFO - __main__ - Step 33042: {'lr': 0.0004476655344895717, 'samples': 6344064, 'steps': 33041, 'loss/train': 1.6910029649734497} 08/30/2021 19:12:36 - INFO - __main__ - Step 33043: {'lr': 0.0004476622853764198, 'samples': 6344256, 'steps': 33042, 'loss/train': 1.7504358291625977} 08/30/2021 19:12:37 - INFO - __main__ - Step 33044: {'lr': 0.00044765903617420436, 'samples': 6344448, 'steps': 33043, 'loss/train': 1.9688754081726074} 08/30/2021 19:12:38 - INFO - __main__ - Step 33045: {'lr': 0.00044765578688292686, 'samples': 6344640, 'steps': 33044, 'loss/train': 0.7051455974578857} 08/30/2021 19:12:39 - INFO - __main__ - Step 33046: {'lr': 0.0004476525375025886, 'samples': 6344832, 'steps': 33045, 'loss/train': 1.9232351779937744} 08/30/2021 19:12:39 - INFO - __main__ - Step 33047: {'lr': 0.00044764928803319126, 'samples': 6345024, 'steps': 33046, 'loss/train': 1.4300377368927002} 08/30/2021 19:12:39 - INFO - __main__ - Step 33048: {'lr': 0.00044764603847473615, 'samples': 6345216, 'steps': 33047, 'loss/train': 0.5969157218933105} 08/30/2021 19:12:40 - INFO - __main__ - Step 33049: {'lr': 0.0004476427888272248, 'samples': 6345408, 'steps': 33048, 'loss/train': 1.9350742101669312} 08/30/2021 19:12:41 - INFO - __main__ - Step 33050: {'lr': 0.0004476395390906586, 'samples': 6345600, 'steps': 33049, 'loss/train': 1.226161241531372} 08/30/2021 19:12:42 - INFO - __main__ - Step 33051: {'lr': 0.0004476362892650392, 'samples': 6345792, 'steps': 33050, 'loss/train': 1.5873152017593384} 08/30/2021 19:12:42 - INFO - __main__ - Step 33052: {'lr': 0.0004476330393503678, 'samples': 6345984, 'steps': 33051, 'loss/train': 1.6476330757141113} 08/30/2021 19:12:43 - INFO - __main__ - Step 33053: {'lr': 0.0004476297893466461, 'samples': 6346176, 'steps': 33052, 'loss/train': 1.7915680408477783} 08/30/2021 19:12:43 - INFO - __main__ - Step 33054: {'lr': 0.0004476265392538754, 'samples': 6346368, 'steps': 33053, 'loss/train': 1.0926499366760254} 08/30/2021 19:12:43 - INFO - __main__ - Step 33055: {'lr': 0.0004476232890720573, 'samples': 6346560, 'steps': 33054, 'loss/train': 1.1330680847167969} 08/30/2021 19:12:45 - INFO - __main__ - Step 33056: {'lr': 0.0004476200388011932, 'samples': 6346752, 'steps': 33055, 'loss/train': 1.607593059539795} 08/30/2021 19:12:46 - INFO - __main__ - Step 33057: {'lr': 0.0004476167884412845, 'samples': 6346944, 'steps': 33056, 'loss/train': 1.01962149143219} 08/30/2021 19:12:46 - INFO - __main__ - Step 33058: {'lr': 0.00044761353799233273, 'samples': 6347136, 'steps': 33057, 'loss/train': 0.11563754081726074} 08/30/2021 19:12:46 - INFO - __main__ - Step 33059: {'lr': 0.00044761028745433934, 'samples': 6347328, 'steps': 33058, 'loss/train': 0.08049215376377106} 08/30/2021 19:12:47 - INFO - __main__ - Step 33060: {'lr': 0.00044760703682730584, 'samples': 6347520, 'steps': 33059, 'loss/train': 1.53285551071167} 08/30/2021 19:12:47 - INFO - __main__ - Step 33061: {'lr': 0.00044760378611123365, 'samples': 6347712, 'steps': 33060, 'loss/train': 1.7963281869888306} 08/30/2021 19:12:48 - INFO - __main__ - Step 33062: {'lr': 0.0004476005353061242, 'samples': 6347904, 'steps': 33061, 'loss/train': 1.6620819568634033} 08/30/2021 19:12:49 - INFO - __main__ - Step 33063: {'lr': 0.00044759728441197904, 'samples': 6348096, 'steps': 33062, 'loss/train': 1.6632779836654663} 08/30/2021 19:12:49 - INFO - __main__ - Step 33064: {'lr': 0.0004475940334287996, 'samples': 6348288, 'steps': 33063, 'loss/train': 1.3440567255020142} 08/30/2021 19:12:50 - INFO - __main__ - Step 33065: {'lr': 0.0004475907823565873, 'samples': 6348480, 'steps': 33064, 'loss/train': 0.9957197904586792} 08/30/2021 19:12:50 - INFO - __main__ - Step 33066: {'lr': 0.00044758753119534373, 'samples': 6348672, 'steps': 33065, 'loss/train': 1.9893556833267212} 08/30/2021 19:12:51 - INFO - __main__ - Step 33067: {'lr': 0.0004475842799450702, 'samples': 6348864, 'steps': 33066, 'loss/train': 1.7364380359649658} 08/30/2021 19:12:52 - INFO - __main__ - Step 33068: {'lr': 0.0004475810286057682, 'samples': 6349056, 'steps': 33067, 'loss/train': 1.8391367197036743} 08/30/2021 19:12:52 - INFO - __main__ - Step 33069: {'lr': 0.0004475777771774393, 'samples': 6349248, 'steps': 33068, 'loss/train': 1.7055121660232544} 08/30/2021 19:12:53 - INFO - __main__ - Step 33070: {'lr': 0.00044757452566008497, 'samples': 6349440, 'steps': 33069, 'loss/train': 1.9024608135223389} 08/30/2021 19:12:53 - INFO - __main__ - Step 33071: {'lr': 0.00044757127405370645, 'samples': 6349632, 'steps': 33070, 'loss/train': 1.6867916584014893} 08/30/2021 19:12:55 - INFO - __main__ - Step 33072: {'lr': 0.00044756802235830544, 'samples': 6349824, 'steps': 33071, 'loss/train': 1.8088105916976929} 08/30/2021 19:12:55 - INFO - __main__ - Step 33073: {'lr': 0.00044756477057388336, 'samples': 6350016, 'steps': 33072, 'loss/train': 1.2027164697647095} 08/30/2021 19:12:55 - INFO - __main__ - Step 33074: {'lr': 0.0004475615187004416, 'samples': 6350208, 'steps': 33073, 'loss/train': 0.9536260366439819} 08/30/2021 19:12:56 - INFO - __main__ - Step 33075: {'lr': 0.0004475582667379817, 'samples': 6350400, 'steps': 33074, 'loss/train': 1.1013617515563965} 08/30/2021 19:12:56 - INFO - __main__ - Step 33076: {'lr': 0.0004475550146865051, 'samples': 6350592, 'steps': 33075, 'loss/train': 1.854211688041687} 08/30/2021 19:12:58 - INFO - __main__ - Step 33077: {'lr': 0.00044755176254601323, 'samples': 6350784, 'steps': 33076, 'loss/train': 1.4084270000457764} 08/30/2021 19:12:58 - INFO - __main__ - Step 33078: {'lr': 0.00044754851031650756, 'samples': 6350976, 'steps': 33077, 'loss/train': 1.800654649734497} 08/30/2021 19:12:58 - INFO - __main__ - Step 33079: {'lr': 0.0004475452579979896, 'samples': 6351168, 'steps': 33078, 'loss/train': 1.0381743907928467} 08/30/2021 19:12:59 - INFO - __main__ - Step 33080: {'lr': 0.00044754200559046076, 'samples': 6351360, 'steps': 33079, 'loss/train': 1.8039509057998657} 08/30/2021 19:12:59 - INFO - __main__ - Step 33081: {'lr': 0.0004475387530939226, 'samples': 6351552, 'steps': 33080, 'loss/train': 1.8570154905319214} 08/30/2021 19:13:00 - INFO - __main__ - Step 33082: {'lr': 0.00044753550050837654, 'samples': 6351744, 'steps': 33081, 'loss/train': 1.701557993888855} 08/30/2021 19:13:01 - INFO - __main__ - Step 33083: {'lr': 0.00044753224783382394, 'samples': 6351936, 'steps': 33082, 'loss/train': 1.9021730422973633} 08/30/2021 19:13:01 - INFO - __main__ - Step 33084: {'lr': 0.00044752899507026646, 'samples': 6352128, 'steps': 33083, 'loss/train': 2.026737689971924} 08/30/2021 19:13:02 - INFO - __main__ - Step 33085: {'lr': 0.00044752574221770537, 'samples': 6352320, 'steps': 33084, 'loss/train': 1.6364058256149292} 08/30/2021 19:13:02 - INFO - __main__ - Step 33086: {'lr': 0.0004475224892761423, 'samples': 6352512, 'steps': 33085, 'loss/train': 1.3327927589416504} 08/30/2021 19:13:04 - INFO - __main__ - Step 33087: {'lr': 0.00044751923624557866, 'samples': 6352704, 'steps': 33086, 'loss/train': 0.6286283731460571} 08/30/2021 19:13:05 - INFO - __main__ - Step 33088: {'lr': 0.0004475159831260158, 'samples': 6352896, 'steps': 33087, 'loss/train': 1.3041417598724365} 08/30/2021 19:13:05 - INFO - __main__ - Step 33089: {'lr': 0.00044751272991745537, 'samples': 6353088, 'steps': 33088, 'loss/train': 3.555285930633545} 08/30/2021 19:13:05 - INFO - __main__ - Step 33090: {'lr': 0.00044750947661989873, 'samples': 6353280, 'steps': 33089, 'loss/train': 1.0919694900512695} 08/30/2021 19:13:06 - INFO - __main__ - Step 33091: {'lr': 0.0004475062232333474, 'samples': 6353472, 'steps': 33090, 'loss/train': 1.493559718132019} 08/30/2021 19:13:06 - INFO - __main__ - Step 33092: {'lr': 0.00044750296975780277, 'samples': 6353664, 'steps': 33091, 'loss/train': 1.5346654653549194} 08/30/2021 19:13:08 - INFO - __main__ - Step 33093: {'lr': 0.00044749971619326633, 'samples': 6353856, 'steps': 33092, 'loss/train': 1.525938868522644} 08/30/2021 19:13:08 - INFO - __main__ - Step 33094: {'lr': 0.0004474964625397396, 'samples': 6354048, 'steps': 33093, 'loss/train': 1.625862956047058} 08/30/2021 19:13:08 - INFO - __main__ - Step 33095: {'lr': 0.000447493208797224, 'samples': 6354240, 'steps': 33094, 'loss/train': 1.7917357683181763} 08/30/2021 19:13:09 - INFO - __main__ - Step 33096: {'lr': 0.00044748995496572105, 'samples': 6354432, 'steps': 33095, 'loss/train': 1.6030538082122803} 08/30/2021 19:13:09 - INFO - __main__ - Step 33097: {'lr': 0.0004474867010452321, 'samples': 6354624, 'steps': 33096, 'loss/train': 1.8729901313781738} 08/30/2021 19:13:10 - INFO - __main__ - Step 33098: {'lr': 0.0004474834470357587, 'samples': 6354816, 'steps': 33097, 'loss/train': 1.107359528541565} 08/30/2021 19:13:11 - INFO - __main__ - Step 33099: {'lr': 0.00044748019293730236, 'samples': 6355008, 'steps': 33098, 'loss/train': 0.8696691393852234} 08/30/2021 19:13:11 - INFO - __main__ - Step 33100: {'lr': 0.0004474769387498645, 'samples': 6355200, 'steps': 33099, 'loss/train': 1.7910774946212769} 08/30/2021 19:13:12 - INFO - __main__ - Step 33101: {'lr': 0.0004474736844734465, 'samples': 6355392, 'steps': 33100, 'loss/train': 1.6372565031051636} 08/30/2021 19:13:12 - INFO - __main__ - Step 33102: {'lr': 0.00044747043010805, 'samples': 6355584, 'steps': 33101, 'loss/train': 1.4538310766220093} 08/30/2021 19:13:13 - INFO - __main__ - Step 33103: {'lr': 0.0004474671756536763, 'samples': 6355776, 'steps': 33102, 'loss/train': 1.3681963682174683} 08/30/2021 19:13:14 - INFO - __main__ - Step 33104: {'lr': 0.00044746392111032695, 'samples': 6355968, 'steps': 33103, 'loss/train': 1.4618077278137207} 08/30/2021 19:13:14 - INFO - __main__ - Step 33105: {'lr': 0.00044746066647800343, 'samples': 6356160, 'steps': 33104, 'loss/train': 0.48403170704841614} 08/30/2021 19:13:15 - INFO - __main__ - Step 33106: {'lr': 0.0004474574117567072, 'samples': 6356352, 'steps': 33105, 'loss/train': 1.8794381618499756} 08/30/2021 19:13:15 - INFO - __main__ - Step 33107: {'lr': 0.00044745415694643964, 'samples': 6356544, 'steps': 33106, 'loss/train': 1.640065312385559} 08/30/2021 19:13:16 - INFO - __main__ - Step 33108: {'lr': 0.0004474509020472023, 'samples': 6356736, 'steps': 33107, 'loss/train': 0.6567052602767944} 08/30/2021 19:13:17 - INFO - __main__ - Step 33109: {'lr': 0.0004474476470589967, 'samples': 6356928, 'steps': 33108, 'loss/train': 1.7657300233840942} 08/30/2021 19:13:17 - INFO - __main__ - Step 33110: {'lr': 0.0004474443919818241, 'samples': 6357120, 'steps': 33109, 'loss/train': 1.5498692989349365} 08/30/2021 19:13:18 - INFO - __main__ - Step 33111: {'lr': 0.0004474411368156862, 'samples': 6357312, 'steps': 33110, 'loss/train': 1.566171407699585} 08/30/2021 19:13:18 - INFO - __main__ - Step 33112: {'lr': 0.00044743788156058437, 'samples': 6357504, 'steps': 33111, 'loss/train': 1.715635061264038} 08/30/2021 19:13:19 - INFO - __main__ - Step 33113: {'lr': 0.00044743462621652007, 'samples': 6357696, 'steps': 33112, 'loss/train': 0.8535028696060181} 08/30/2021 19:13:20 - INFO - __main__ - Step 33114: {'lr': 0.0004474313707834947, 'samples': 6357888, 'steps': 33113, 'loss/train': 1.1664762496948242} 08/30/2021 19:13:20 - INFO - __main__ - Step 33115: {'lr': 0.00044742811526150996, 'samples': 6358080, 'steps': 33114, 'loss/train': 1.467318058013916} 08/30/2021 19:13:21 - INFO - __main__ - Step 33116: {'lr': 0.000447424859650567, 'samples': 6358272, 'steps': 33115, 'loss/train': 1.5273271799087524} 08/30/2021 19:13:21 - INFO - __main__ - Step 33117: {'lr': 0.00044742160395066756, 'samples': 6358464, 'steps': 33116, 'loss/train': 1.3869233131408691} 08/30/2021 19:13:22 - INFO - __main__ - Step 33118: {'lr': 0.0004474183481618129, 'samples': 6358656, 'steps': 33117, 'loss/train': 1.1732172966003418} 08/30/2021 19:13:23 - INFO - __main__ - Step 33119: {'lr': 0.00044741509228400465, 'samples': 6358848, 'steps': 33118, 'loss/train': 1.6598488092422485} 08/30/2021 19:13:23 - INFO - __main__ - Step 33120: {'lr': 0.0004474118363172441, 'samples': 6359040, 'steps': 33119, 'loss/train': 0.9198315739631653} 08/30/2021 19:13:24 - INFO - __main__ - Step 33121: {'lr': 0.000447408580261533, 'samples': 6359232, 'steps': 33120, 'loss/train': 0.8731750845909119} 08/30/2021 19:13:24 - INFO - __main__ - Step 33122: {'lr': 0.0004474053241168725, 'samples': 6359424, 'steps': 33121, 'loss/train': 1.7959306240081787} 08/30/2021 19:13:24 - INFO - __main__ - Step 33123: {'lr': 0.00044740206788326423, 'samples': 6359616, 'steps': 33122, 'loss/train': 1.8095154762268066} 08/30/2021 19:13:26 - INFO - __main__ - Step 33124: {'lr': 0.0004473988115607097, 'samples': 6359808, 'steps': 33123, 'loss/train': 2.0089199542999268} 08/30/2021 19:13:26 - INFO - __main__ - Step 33125: {'lr': 0.00044739555514921025, 'samples': 6360000, 'steps': 33124, 'loss/train': 0.3015340268611908} 08/30/2021 19:13:27 - INFO - __main__ - Step 33126: {'lr': 0.0004473922986487674, 'samples': 6360192, 'steps': 33125, 'loss/train': 1.557114601135254} 08/30/2021 19:13:27 - INFO - __main__ - Step 33127: {'lr': 0.00044738904205938264, 'samples': 6360384, 'steps': 33126, 'loss/train': 0.9553331136703491} 08/30/2021 19:13:27 - INFO - __main__ - Step 33128: {'lr': 0.00044738578538105746, 'samples': 6360576, 'steps': 33127, 'loss/train': 1.7851487398147583} 08/30/2021 19:13:29 - INFO - __main__ - Step 33129: {'lr': 0.0004473825286137933, 'samples': 6360768, 'steps': 33128, 'loss/train': 0.785422682762146} 08/30/2021 19:13:29 - INFO - __main__ - Step 33130: {'lr': 0.0004473792717575915, 'samples': 6360960, 'steps': 33129, 'loss/train': 1.3046597242355347} 08/30/2021 19:13:30 - INFO - __main__ - Step 33131: {'lr': 0.00044737601481245376, 'samples': 6361152, 'steps': 33130, 'loss/train': 1.1152418851852417} 08/30/2021 19:13:30 - INFO - __main__ - Step 33132: {'lr': 0.00044737275777838136, 'samples': 6361344, 'steps': 33131, 'loss/train': 1.2857109308242798} 08/30/2021 19:13:30 - INFO - __main__ - Step 33133: {'lr': 0.0004473695006553759, 'samples': 6361536, 'steps': 33132, 'loss/train': 1.2026758193969727} 08/30/2021 19:13:32 - INFO - __main__ - Step 33134: {'lr': 0.0004473662434434388, 'samples': 6361728, 'steps': 33133, 'loss/train': 1.7568212747573853} 08/30/2021 19:13:32 - INFO - __main__ - Step 33135: {'lr': 0.00044736298614257144, 'samples': 6361920, 'steps': 33134, 'loss/train': 1.3744275569915771} 08/30/2021 19:13:33 - INFO - __main__ - Step 33136: {'lr': 0.0004473597287527754, 'samples': 6362112, 'steps': 33135, 'loss/train': 1.0194183588027954} 08/30/2021 19:13:33 - INFO - __main__ - Step 33137: {'lr': 0.00044735647127405216, 'samples': 6362304, 'steps': 33136, 'loss/train': 0.7607768774032593} 08/30/2021 19:13:33 - INFO - __main__ - Step 33138: {'lr': 0.00044735321370640316, 'samples': 6362496, 'steps': 33137, 'loss/train': 0.8930467367172241} 08/30/2021 19:13:35 - INFO - __main__ - Step 33139: {'lr': 0.00044734995604982973, 'samples': 6362688, 'steps': 33138, 'loss/train': 1.7041476964950562} 08/30/2021 19:13:36 - INFO - __main__ - Step 33140: {'lr': 0.0004473466983043335, 'samples': 6362880, 'steps': 33139, 'loss/train': 1.528459072113037} 08/30/2021 19:13:36 - INFO - __main__ - Step 33141: {'lr': 0.0004473434404699159, 'samples': 6363072, 'steps': 33140, 'loss/train': 1.6524134874343872} 08/30/2021 19:13:37 - INFO - __main__ - Step 33142: {'lr': 0.00044734018254657845, 'samples': 6363264, 'steps': 33141, 'loss/train': 1.5705945491790771} 08/30/2021 19:13:37 - INFO - __main__ - Step 33143: {'lr': 0.00044733692453432253, 'samples': 6363456, 'steps': 33142, 'loss/train': 0.06174716725945473} 08/30/2021 19:13:37 - INFO - __main__ - Step 33144: {'lr': 0.00044733366643314956, 'samples': 6363648, 'steps': 33143, 'loss/train': 1.6433777809143066} 08/30/2021 19:13:39 - INFO - __main__ - Step 33145: {'lr': 0.00044733040824306117, 'samples': 6363840, 'steps': 33144, 'loss/train': 4.694973468780518} 08/30/2021 19:13:39 - INFO - __main__ - Step 33146: {'lr': 0.00044732714996405866, 'samples': 6364032, 'steps': 33145, 'loss/train': 1.737661600112915} 08/30/2021 19:13:40 - INFO - __main__ - Step 33147: {'lr': 0.0004473238915961436, 'samples': 6364224, 'steps': 33146, 'loss/train': 1.7607970237731934} 08/30/2021 19:13:40 - INFO - __main__ - Step 33148: {'lr': 0.0004473206331393175, 'samples': 6364416, 'steps': 33147, 'loss/train': 1.1441699266433716} 08/30/2021 19:13:40 - INFO - __main__ - Step 33149: {'lr': 0.0004473173745935818, 'samples': 6364608, 'steps': 33148, 'loss/train': 1.3013454675674438} 08/30/2021 19:13:42 - INFO - __main__ - Step 33150: {'lr': 0.00044731411595893785, 'samples': 6364800, 'steps': 33149, 'loss/train': 1.5090206861495972} 08/30/2021 19:13:42 - INFO - __main__ - Step 33151: {'lr': 0.00044731085723538725, 'samples': 6364992, 'steps': 33150, 'loss/train': 0.9398083686828613} 08/30/2021 19:13:43 - INFO - __main__ - Step 33152: {'lr': 0.00044730759842293136, 'samples': 6365184, 'steps': 33151, 'loss/train': 0.03872733935713768} 08/30/2021 19:13:43 - INFO - __main__ - Step 33153: {'lr': 0.0004473043395215718, 'samples': 6365376, 'steps': 33152, 'loss/train': 1.6674392223358154} 08/30/2021 19:13:43 - INFO - __main__ - Step 33154: {'lr': 0.00044730108053130986, 'samples': 6365568, 'steps': 33153, 'loss/train': 0.07804340124130249} 08/30/2021 19:13:44 - INFO - __main__ - Step 33155: {'lr': 0.00044729782145214717, 'samples': 6365760, 'steps': 33154, 'loss/train': 1.7033551931381226} 08/30/2021 19:13:45 - INFO - __main__ - Step 33156: {'lr': 0.00044729456228408506, 'samples': 6365952, 'steps': 33155, 'loss/train': 1.7550445795059204} 08/30/2021 19:13:46 - INFO - __main__ - Step 33157: {'lr': 0.00044729130302712504, 'samples': 6366144, 'steps': 33156, 'loss/train': 1.3517141342163086} 08/30/2021 19:13:46 - INFO - __main__ - Step 33158: {'lr': 0.00044728804368126873, 'samples': 6366336, 'steps': 33157, 'loss/train': 1.6131904125213623} 08/30/2021 19:13:46 - INFO - __main__ - Step 33159: {'lr': 0.00044728478424651744, 'samples': 6366528, 'steps': 33158, 'loss/train': 1.727964162826538} 08/30/2021 19:13:47 - INFO - __main__ - Step 33160: {'lr': 0.0004472815247228726, 'samples': 6366720, 'steps': 33159, 'loss/train': 1.8815282583236694} 08/30/2021 19:13:48 - INFO - __main__ - Step 33161: {'lr': 0.00044727826511033577, 'samples': 6366912, 'steps': 33160, 'loss/train': 1.420610785484314} 08/30/2021 19:13:49 - INFO - __main__ - Step 33162: {'lr': 0.0004472750054089084, 'samples': 6367104, 'steps': 33161, 'loss/train': 1.2006685733795166} 08/30/2021 19:13:49 - INFO - __main__ - Step 33163: {'lr': 0.00044727174561859194, 'samples': 6367296, 'steps': 33162, 'loss/train': 1.788468599319458} 08/30/2021 19:13:49 - INFO - __main__ - Step 33164: {'lr': 0.00044726848573938796, 'samples': 6367488, 'steps': 33163, 'loss/train': 1.9293099641799927} 08/30/2021 19:13:50 - INFO - __main__ - Step 33165: {'lr': 0.0004472652257712978, 'samples': 6367680, 'steps': 33164, 'loss/train': 0.9755367636680603} 08/30/2021 19:13:51 - INFO - __main__ - Step 33166: {'lr': 0.0004472619657143229, 'samples': 6367872, 'steps': 33165, 'loss/train': 0.9931578636169434} 08/30/2021 19:13:52 - INFO - __main__ - Step 33167: {'lr': 0.00044725870556846495, 'samples': 6368064, 'steps': 33166, 'loss/train': 1.3051424026489258} 08/30/2021 19:13:52 - INFO - __main__ - Step 33168: {'lr': 0.00044725544533372516, 'samples': 6368256, 'steps': 33167, 'loss/train': 1.2481558322906494} 08/30/2021 19:13:52 - INFO - __main__ - Step 33169: {'lr': 0.00044725218501010514, 'samples': 6368448, 'steps': 33168, 'loss/train': 0.6757267713546753} 08/30/2021 19:13:53 - INFO - __main__ - Step 33170: {'lr': 0.0004472489245976063, 'samples': 6368640, 'steps': 33169, 'loss/train': 0.685947835445404} 08/30/2021 19:13:54 - INFO - __main__ - Step 33171: {'lr': 0.00044724566409623013, 'samples': 6368832, 'steps': 33170, 'loss/train': 1.1848844289779663} 08/30/2021 19:13:55 - INFO - __main__ - Step 33172: {'lr': 0.0004472424035059782, 'samples': 6369024, 'steps': 33171, 'loss/train': 1.8384292125701904} 08/30/2021 19:13:55 - INFO - __main__ - Step 33173: {'lr': 0.0004472391428268518, 'samples': 6369216, 'steps': 33172, 'loss/train': 1.9851698875427246} 08/30/2021 19:13:56 - INFO - __main__ - Step 33174: {'lr': 0.00044723588205885254, 'samples': 6369408, 'steps': 33173, 'loss/train': 1.1953809261322021} 08/30/2021 19:13:56 - INFO - __main__ - Step 33175: {'lr': 0.00044723262120198177, 'samples': 6369600, 'steps': 33174, 'loss/train': 0.8316321969032288} 08/30/2021 19:13:56 - INFO - __main__ - Step 33176: {'lr': 0.00044722936025624107, 'samples': 6369792, 'steps': 33175, 'loss/train': 1.3860183954238892} 08/30/2021 19:13:58 - INFO - __main__ - Step 33177: {'lr': 0.00044722609922163184, 'samples': 6369984, 'steps': 33176, 'loss/train': 1.6508485078811646} 08/30/2021 19:13:58 - INFO - __main__ - Step 33178: {'lr': 0.0004472228380981556, 'samples': 6370176, 'steps': 33177, 'loss/train': 1.204204797744751} 08/30/2021 19:13:59 - INFO - __main__ - Step 33179: {'lr': 0.0004472195768858138, 'samples': 6370368, 'steps': 33178, 'loss/train': 1.1181594133377075} 08/30/2021 19:13:59 - INFO - __main__ - Step 33180: {'lr': 0.0004472163155846078, 'samples': 6370560, 'steps': 33179, 'loss/train': 1.6790850162506104} 08/30/2021 19:13:59 - INFO - __main__ - Step 33181: {'lr': 0.0004472130541945393, 'samples': 6370752, 'steps': 33180, 'loss/train': 0.7559379935264587} 08/30/2021 19:14:01 - INFO - __main__ - Step 33182: {'lr': 0.00044720979271560963, 'samples': 6370944, 'steps': 33181, 'loss/train': 1.9271368980407715} 08/30/2021 19:14:02 - INFO - __main__ - Step 33183: {'lr': 0.00044720653114782024, 'samples': 6371136, 'steps': 33182, 'loss/train': 1.4622468948364258} 08/30/2021 19:14:02 - INFO - __main__ - Step 33184: {'lr': 0.0004472032694911726, 'samples': 6371328, 'steps': 33183, 'loss/train': 1.2617207765579224} 08/30/2021 19:14:02 - INFO - __main__ - Step 33185: {'lr': 0.0004472000077456683, 'samples': 6371520, 'steps': 33184, 'loss/train': 0.11245016753673553} 08/30/2021 19:14:03 - INFO - __main__ - Step 33186: {'lr': 0.0004471967459113086, 'samples': 6371712, 'steps': 33185, 'loss/train': 0.10119623690843582} 08/30/2021 19:14:03 - INFO - __main__ - Step 33187: {'lr': 0.0004471934839880951, 'samples': 6371904, 'steps': 33186, 'loss/train': 1.5234103202819824} 08/30/2021 19:14:05 - INFO - __main__ - Step 33188: {'lr': 0.00044719022197602933, 'samples': 6372096, 'steps': 33187, 'loss/train': 1.8250043392181396} 08/30/2021 19:14:05 - INFO - __main__ - Step 33189: {'lr': 0.0004471869598751127, 'samples': 6372288, 'steps': 33188, 'loss/train': 1.4584451913833618} 08/30/2021 19:14:05 - INFO - __main__ - Step 33190: {'lr': 0.0004471836976853466, 'samples': 6372480, 'steps': 33189, 'loss/train': 1.17582368850708} 08/30/2021 19:14:06 - INFO - __main__ - Step 33191: {'lr': 0.00044718043540673257, 'samples': 6372672, 'steps': 33190, 'loss/train': 1.610975742340088} 08/30/2021 19:14:06 - INFO - __main__ - Step 33192: {'lr': 0.0004471771730392722, 'samples': 6372864, 'steps': 33191, 'loss/train': 1.50669527053833} 08/30/2021 19:14:08 - INFO - __main__ - Step 33193: {'lr': 0.0004471739105829667, 'samples': 6373056, 'steps': 33192, 'loss/train': 1.185469150543213} 08/30/2021 19:14:08 - INFO - __main__ - Step 33194: {'lr': 0.00044717064803781773, 'samples': 6373248, 'steps': 33193, 'loss/train': 1.8157325983047485} 08/30/2021 19:14:08 - INFO - __main__ - Step 33195: {'lr': 0.00044716738540382674, 'samples': 6373440, 'steps': 33194, 'loss/train': 1.206169605255127} 08/30/2021 19:14:09 - INFO - __main__ - Step 33196: {'lr': 0.0004471641226809951, 'samples': 6373632, 'steps': 33195, 'loss/train': 1.158311128616333} 08/30/2021 19:14:09 - INFO - __main__ - Step 33197: {'lr': 0.0004471608598693244, 'samples': 6373824, 'steps': 33196, 'loss/train': 0.8852444291114807} 08/30/2021 19:14:11 - INFO - __main__ - Step 33198: {'lr': 0.000447157596968816, 'samples': 6374016, 'steps': 33197, 'loss/train': 1.7501740455627441} 08/30/2021 19:14:12 - INFO - __main__ - Step 33199: {'lr': 0.0004471543339794715, 'samples': 6374208, 'steps': 33198, 'loss/train': 1.9281806945800781} 08/30/2021 19:14:12 - INFO - __main__ - Step 33200: {'lr': 0.00044715107090129223, 'samples': 6374400, 'steps': 33199, 'loss/train': 1.703927993774414} 08/30/2021 19:14:12 - INFO - __main__ - Step 33201: {'lr': 0.00044714780773427975, 'samples': 6374592, 'steps': 33200, 'loss/train': 1.4577666521072388} 08/30/2021 19:14:13 - INFO - __main__ - Step 33202: {'lr': 0.00044714454447843555, 'samples': 6374784, 'steps': 33201, 'loss/train': 1.494301676750183} 08/30/2021 19:14:14 - INFO - __main__ - Step 33203: {'lr': 0.0004471412811337611, 'samples': 6374976, 'steps': 33202, 'loss/train': 1.0275992155075073} 08/30/2021 19:14:15 - INFO - __main__ - Step 33204: {'lr': 0.00044713801770025774, 'samples': 6375168, 'steps': 33203, 'loss/train': 1.3882516622543335} 08/30/2021 19:14:15 - INFO - __main__ - Step 33205: {'lr': 0.00044713475417792705, 'samples': 6375360, 'steps': 33204, 'loss/train': 1.3328049182891846} 08/30/2021 19:14:15 - INFO - __main__ - Step 33206: {'lr': 0.0004471314905667705, 'samples': 6375552, 'steps': 33205, 'loss/train': 0.15638910233974457} 08/30/2021 19:14:16 - INFO - __main__ - Step 33207: {'lr': 0.00044712822686678955, 'samples': 6375744, 'steps': 33206, 'loss/train': 0.6004116535186768} 08/30/2021 19:14:17 - INFO - __main__ - Step 33208: {'lr': 0.00044712496307798566, 'samples': 6375936, 'steps': 33207, 'loss/train': 1.4914157390594482} 08/30/2021 19:14:18 - INFO - __main__ - Step 33209: {'lr': 0.0004471216992003603, 'samples': 6376128, 'steps': 33208, 'loss/train': 1.911248803138733} 08/30/2021 19:14:18 - INFO - __main__ - Step 33210: {'lr': 0.0004471184352339149, 'samples': 6376320, 'steps': 33209, 'loss/train': 1.4934022426605225} 08/30/2021 19:14:18 - INFO - __main__ - Step 33211: {'lr': 0.00044711517117865105, 'samples': 6376512, 'steps': 33210, 'loss/train': 1.5583490133285522} 08/30/2021 19:14:19 - INFO - __main__ - Step 33212: {'lr': 0.00044711190703457005, 'samples': 6376704, 'steps': 33211, 'loss/train': 1.6493061780929565} 08/30/2021 19:14:20 - INFO - __main__ - Step 33213: {'lr': 0.00044710864280167353, 'samples': 6376896, 'steps': 33212, 'loss/train': 0.8273021578788757} 08/30/2021 19:14:21 - INFO - __main__ - Step 33214: {'lr': 0.0004471053784799629, 'samples': 6377088, 'steps': 33213, 'loss/train': 1.4777802228927612} 08/30/2021 19:14:21 - INFO - __main__ - Step 33215: {'lr': 0.0004471021140694396, 'samples': 6377280, 'steps': 33214, 'loss/train': 1.8512877225875854} 08/30/2021 19:14:21 - INFO - __main__ - Step 33216: {'lr': 0.0004470988495701052, 'samples': 6377472, 'steps': 33215, 'loss/train': 1.847663402557373} 08/30/2021 19:14:22 - INFO - __main__ - Step 33217: {'lr': 0.00044709558498196104, 'samples': 6377664, 'steps': 33216, 'loss/train': 1.509377121925354} 08/30/2021 19:14:24 - INFO - __main__ - Step 33218: {'lr': 0.00044709232030500865, 'samples': 6377856, 'steps': 33217, 'loss/train': 1.7002356052398682} 08/30/2021 19:14:25 - INFO - __main__ - Step 33219: {'lr': 0.0004470890555392495, 'samples': 6378048, 'steps': 33218, 'loss/train': 1.758070707321167} 08/30/2021 19:14:25 - INFO - __main__ - Step 33220: {'lr': 0.00044708579068468505, 'samples': 6378240, 'steps': 33219, 'loss/train': 0.9826855063438416} 08/30/2021 19:14:25 - INFO - __main__ - Step 33221: {'lr': 0.0004470825257413168, 'samples': 6378432, 'steps': 33220, 'loss/train': 1.587417483329773} 08/30/2021 19:14:26 - INFO - __main__ - Step 33222: {'lr': 0.00044707926070914624, 'samples': 6378624, 'steps': 33221, 'loss/train': 1.5655951499938965} 08/30/2021 19:14:26 - INFO - __main__ - Step 33223: {'lr': 0.0004470759955881748, 'samples': 6378816, 'steps': 33222, 'loss/train': 1.2147775888442993} 08/30/2021 19:14:27 - INFO - __main__ - Step 33224: {'lr': 0.0004470727303784039, 'samples': 6379008, 'steps': 33223, 'loss/train': 0.6486656069755554} 08/30/2021 19:14:27 - INFO - __main__ - Step 33225: {'lr': 0.00044706946507983513, 'samples': 6379200, 'steps': 33224, 'loss/train': 0.3323737680912018} 08/30/2021 19:14:29 - INFO - __main__ - Step 33226: {'lr': 0.00044706619969246984, 'samples': 6379392, 'steps': 33225, 'loss/train': 0.5406600832939148} 08/30/2021 19:14:29 - INFO - __main__ - Step 33227: {'lr': 0.0004470629342163096, 'samples': 6379584, 'steps': 33226, 'loss/train': 2.0734059810638428} 08/30/2021 19:14:30 - INFO - __main__ - Step 33228: {'lr': 0.00044705966865135583, 'samples': 6379776, 'steps': 33227, 'loss/train': 1.4940927028656006} 08/30/2021 19:14:30 - INFO - __main__ - Step 33229: {'lr': 0.00044705640299761004, 'samples': 6379968, 'steps': 33228, 'loss/train': 1.134113073348999} 08/30/2021 19:14:30 - INFO - __main__ - Step 33230: {'lr': 0.0004470531372550736, 'samples': 6380160, 'steps': 33229, 'loss/train': 1.7533130645751953} 08/30/2021 19:14:31 - INFO - __main__ - Step 33231: {'lr': 0.00044704987142374814, 'samples': 6380352, 'steps': 33230, 'loss/train': 1.9926685094833374} 08/30/2021 19:14:32 - INFO - __main__ - Step 33232: {'lr': 0.00044704660550363507, 'samples': 6380544, 'steps': 33231, 'loss/train': 1.6889886856079102} 08/30/2021 19:14:33 - INFO - __main__ - Step 33233: {'lr': 0.00044704333949473576, 'samples': 6380736, 'steps': 33232, 'loss/train': 1.570174217224121} 08/30/2021 19:14:33 - INFO - __main__ - Step 33234: {'lr': 0.0004470400733970518, 'samples': 6380928, 'steps': 33233, 'loss/train': 1.585200548171997} 08/30/2021 19:14:33 - INFO - __main__ - Step 33235: {'lr': 0.0004470368072105846, 'samples': 6381120, 'steps': 33234, 'loss/train': 1.4171451330184937} 08/30/2021 19:14:34 - INFO - __main__ - Step 33236: {'lr': 0.00044703354093533564, 'samples': 6381312, 'steps': 33235, 'loss/train': 1.796724796295166} 08/30/2021 19:14:35 - INFO - __main__ - Step 33237: {'lr': 0.0004470302745713065, 'samples': 6381504, 'steps': 33236, 'loss/train': 1.452254056930542} 08/30/2021 19:14:36 - INFO - __main__ - Step 33238: {'lr': 0.0004470270081184985, 'samples': 6381696, 'steps': 33237, 'loss/train': 0.17575830221176147} 08/30/2021 19:14:36 - INFO - __main__ - Step 33239: {'lr': 0.00044702374157691316, 'samples': 6381888, 'steps': 33238, 'loss/train': 1.8308111429214478} 08/30/2021 19:14:37 - INFO - __main__ - Step 33240: {'lr': 0.00044702047494655194, 'samples': 6382080, 'steps': 33239, 'loss/train': 1.3223453760147095} 08/30/2021 19:14:37 - INFO - __main__ - Step 33241: {'lr': 0.0004470172082274164, 'samples': 6382272, 'steps': 33240, 'loss/train': 1.7049347162246704} 08/30/2021 19:14:38 - INFO - __main__ - Step 33242: {'lr': 0.0004470139414195079, 'samples': 6382464, 'steps': 33241, 'loss/train': 1.6486618518829346} 08/30/2021 19:14:39 - INFO - __main__ - Step 33243: {'lr': 0.00044701067452282796, 'samples': 6382656, 'steps': 33242, 'loss/train': 1.2168083190917969} 08/30/2021 19:14:39 - INFO - __main__ - Step 33244: {'lr': 0.00044700740753737806, 'samples': 6382848, 'steps': 33243, 'loss/train': 1.190751075744629} 08/30/2021 19:14:39 - INFO - __main__ - Step 33245: {'lr': 0.0004470041404631597, 'samples': 6383040, 'steps': 33244, 'loss/train': 1.361646056175232} 08/30/2021 19:14:40 - INFO - __main__ - Step 33246: {'lr': 0.0004470008733001742, 'samples': 6383232, 'steps': 33245, 'loss/train': 1.2804499864578247} 08/30/2021 19:14:41 - INFO - __main__ - Step 33247: {'lr': 0.0004469976060484233, 'samples': 6383424, 'steps': 33246, 'loss/train': 1.667539358139038} 08/30/2021 19:14:42 - INFO - __main__ - Step 33248: {'lr': 0.00044699433870790817, 'samples': 6383616, 'steps': 33247, 'loss/train': 1.0871059894561768} 08/30/2021 19:14:42 - INFO - __main__ - Step 33249: {'lr': 0.00044699107127863056, 'samples': 6383808, 'steps': 33248, 'loss/train': 1.4582699537277222} 08/30/2021 19:14:43 - INFO - __main__ - Step 33250: {'lr': 0.0004469878037605917, 'samples': 6384000, 'steps': 33249, 'loss/train': 1.6328154802322388} 08/30/2021 19:14:43 - INFO - __main__ - Step 33251: {'lr': 0.0004469845361537933, 'samples': 6384192, 'steps': 33250, 'loss/train': 1.2056998014450073} 08/30/2021 19:14:45 - INFO - __main__ - Step 33252: {'lr': 0.0004469812684582366, 'samples': 6384384, 'steps': 33251, 'loss/train': 1.3030999898910522} 08/30/2021 19:14:45 - INFO - __main__ - Step 33253: {'lr': 0.00044697800067392327, 'samples': 6384576, 'steps': 33252, 'loss/train': 1.153661847114563} 08/30/2021 19:14:46 - INFO - __main__ - Step 33254: {'lr': 0.00044697473280085455, 'samples': 6384768, 'steps': 33253, 'loss/train': 2.4470200538635254} 08/30/2021 19:14:46 - INFO - __main__ - Step 33255: {'lr': 0.0004469714648390322, 'samples': 6384960, 'steps': 33254, 'loss/train': 1.557395100593567} 08/30/2021 19:14:46 - INFO - __main__ - Step 33256: {'lr': 0.00044696819678845744, 'samples': 6385152, 'steps': 33255, 'loss/train': 1.9589415788650513} 08/30/2021 19:14:48 - INFO - __main__ - Step 33257: {'lr': 0.000446964928649132, 'samples': 6385344, 'steps': 33256, 'loss/train': 1.4761420488357544} 08/30/2021 19:14:48 - INFO - __main__ - Step 33258: {'lr': 0.00044696166042105704, 'samples': 6385536, 'steps': 33257, 'loss/train': 2.0367982387542725} 08/30/2021 19:14:49 - INFO - __main__ - Step 33259: {'lr': 0.0004469583921042343, 'samples': 6385728, 'steps': 33258, 'loss/train': 1.4333654642105103} 08/30/2021 19:14:49 - INFO - __main__ - Step 33260: {'lr': 0.0004469551236986651, 'samples': 6385920, 'steps': 33259, 'loss/train': 1.6459969282150269} 08/30/2021 19:14:49 - INFO - __main__ - Step 33261: {'lr': 0.00044695185520435087, 'samples': 6386112, 'steps': 33260, 'loss/train': 1.6131266355514526} 08/30/2021 19:14:51 - INFO - __main__ - Step 33262: {'lr': 0.00044694858662129333, 'samples': 6386304, 'steps': 33261, 'loss/train': 1.306576132774353} 08/30/2021 19:14:52 - INFO - __main__ - Step 33263: {'lr': 0.0004469453179494938, 'samples': 6386496, 'steps': 33262, 'loss/train': 2.506016731262207} 08/30/2021 19:14:52 - INFO - __main__ - Step 33264: {'lr': 0.00044694204918895367, 'samples': 6386688, 'steps': 33263, 'loss/train': 0.9850426912307739} 08/30/2021 19:14:52 - INFO - __main__ - Step 33265: {'lr': 0.0004469387803396745, 'samples': 6386880, 'steps': 33264, 'loss/train': 1.1219128370285034} 08/30/2021 19:14:53 - INFO - __main__ - Step 33266: {'lr': 0.0004469355114016577, 'samples': 6387072, 'steps': 33265, 'loss/train': 1.5980356931686401} 08/30/2021 19:14:53 - INFO - __main__ - Step 33267: {'lr': 0.00044693224237490485, 'samples': 6387264, 'steps': 33266, 'loss/train': 0.9002454280853271} 08/30/2021 19:14:55 - INFO - __main__ - Step 33268: {'lr': 0.00044692897325941737, 'samples': 6387456, 'steps': 33267, 'loss/train': 1.5177640914916992} 08/30/2021 19:14:55 - INFO - __main__ - Step 33269: {'lr': 0.00044692570405519683, 'samples': 6387648, 'steps': 33268, 'loss/train': 1.3533560037612915} 08/30/2021 19:14:56 - INFO - __main__ - Step 33270: {'lr': 0.0004469224347622445, 'samples': 6387840, 'steps': 33269, 'loss/train': 1.006487488746643} 08/30/2021 19:14:56 - INFO - __main__ - Step 33271: {'lr': 0.000446919165380562, 'samples': 6388032, 'steps': 33270, 'loss/train': 2.077798366546631} 08/30/2021 19:14:56 - INFO - __main__ - Step 33272: {'lr': 0.0004469158959101507, 'samples': 6388224, 'steps': 33271, 'loss/train': 1.2345467805862427} 08/30/2021 19:14:58 - INFO - __main__ - Step 33273: {'lr': 0.00044691262635101223, 'samples': 6388416, 'steps': 33272, 'loss/train': 1.2836799621582031} 08/30/2021 19:14:58 - INFO - __main__ - Step 33274: {'lr': 0.0004469093567031479, 'samples': 6388608, 'steps': 33273, 'loss/train': 1.395310401916504} 08/30/2021 19:14:59 - INFO - __main__ - Step 33275: {'lr': 0.00044690608696655923, 'samples': 6388800, 'steps': 33274, 'loss/train': 1.5411368608474731} 08/30/2021 19:14:59 - INFO - __main__ - Step 33276: {'lr': 0.0004469028171412478, 'samples': 6388992, 'steps': 33275, 'loss/train': 1.7975809574127197} 08/30/2021 19:14:59 - INFO - __main__ - Step 33277: {'lr': 0.00044689954722721494, 'samples': 6389184, 'steps': 33276, 'loss/train': 1.0257220268249512} 08/30/2021 19:15:01 - INFO - __main__ - Step 33278: {'lr': 0.0004468962772244622, 'samples': 6389376, 'steps': 33277, 'loss/train': 1.6012530326843262} 08/30/2021 19:15:02 - INFO - __main__ - Step 33279: {'lr': 0.00044689300713299105, 'samples': 6389568, 'steps': 33278, 'loss/train': 1.7047499418258667} 08/30/2021 19:15:02 - INFO - __main__ - Step 33280: {'lr': 0.0004468897369528029, 'samples': 6389760, 'steps': 33279, 'loss/train': 1.1045327186584473} 08/30/2021 19:15:02 - INFO - __main__ - Step 33281: {'lr': 0.00044688646668389933, 'samples': 6389952, 'steps': 33280, 'loss/train': 1.786787509918213} 08/30/2021 19:15:03 - INFO - __main__ - Step 33282: {'lr': 0.0004468831963262817, 'samples': 6390144, 'steps': 33281, 'loss/train': 1.5973328351974487} 08/30/2021 19:15:03 - INFO - __main__ - Step 33283: {'lr': 0.00044687992587995155, 'samples': 6390336, 'steps': 33282, 'loss/train': 0.1498529613018036} 08/30/2021 19:15:03 - INFO - __main__ - Step 33284: {'lr': 0.0004468766553449104, 'samples': 6390528, 'steps': 33283, 'loss/train': 0.24845431745052338} 08/30/2021 19:15:05 - INFO - __main__ - Step 33285: {'lr': 0.00044687338472115964, 'samples': 6390720, 'steps': 33284, 'loss/train': 1.4345593452453613} 08/30/2021 19:15:06 - INFO - __main__ - Step 33286: {'lr': 0.00044687011400870074, 'samples': 6390912, 'steps': 33285, 'loss/train': 1.9823952913284302} 08/30/2021 19:15:06 - INFO - __main__ - Step 33287: {'lr': 0.00044686684320753524, 'samples': 6391104, 'steps': 33286, 'loss/train': 1.325752854347229} 08/30/2021 19:15:06 - INFO - __main__ - Step 33288: {'lr': 0.00044686357231766454, 'samples': 6391296, 'steps': 33287, 'loss/train': 1.2607601881027222} 08/30/2021 19:15:07 - INFO - __main__ - Step 33289: {'lr': 0.00044686030133909017, 'samples': 6391488, 'steps': 33288, 'loss/train': 0.15953637659549713} 08/30/2021 19:15:08 - INFO - __main__ - Step 33290: {'lr': 0.00044685703027181364, 'samples': 6391680, 'steps': 33289, 'loss/train': 1.1410908699035645} 08/30/2021 19:15:09 - INFO - __main__ - Step 33291: {'lr': 0.0004468537591158363, 'samples': 6391872, 'steps': 33290, 'loss/train': 1.593532681465149} 08/30/2021 19:15:09 - INFO - __main__ - Step 33292: {'lr': 0.0004468504878711597, 'samples': 6392064, 'steps': 33291, 'loss/train': 1.307927131652832} 08/30/2021 19:15:09 - INFO - __main__ - Step 33293: {'lr': 0.00044684721653778537, 'samples': 6392256, 'steps': 33292, 'loss/train': 1.2437483072280884} 08/30/2021 19:15:10 - INFO - __main__ - Step 33294: {'lr': 0.00044684394511571463, 'samples': 6392448, 'steps': 33293, 'loss/train': 1.0610694885253906} 08/30/2021 19:15:11 - INFO - __main__ - Step 33295: {'lr': 0.00044684067360494905, 'samples': 6392640, 'steps': 33294, 'loss/train': 1.6670525074005127} 08/30/2021 19:15:12 - INFO - __main__ - Step 33296: {'lr': 0.00044683740200549015, 'samples': 6392832, 'steps': 33295, 'loss/train': 2.364126205444336} 08/30/2021 19:15:12 - INFO - __main__ - Step 33297: {'lr': 0.00044683413031733945, 'samples': 6393024, 'steps': 33296, 'loss/train': 0.9930689930915833} 08/30/2021 19:15:13 - INFO - __main__ - Step 33298: {'lr': 0.00044683085854049814, 'samples': 6393216, 'steps': 33297, 'loss/train': 2.525376558303833} 08/30/2021 19:15:13 - INFO - __main__ - Step 33299: {'lr': 0.00044682758667496806, 'samples': 6393408, 'steps': 33298, 'loss/train': 1.4268330335617065} 08/30/2021 19:15:14 - INFO - __main__ - Step 33300: {'lr': 0.00044682431472075035, 'samples': 6393600, 'steps': 33299, 'loss/train': 1.1879383325576782} 08/30/2021 19:15:15 - INFO - __main__ - Step 33301: {'lr': 0.00044682104267784674, 'samples': 6393792, 'steps': 33300, 'loss/train': 1.0189604759216309} 08/30/2021 19:15:15 - INFO - __main__ - Step 33302: {'lr': 0.0004468177705462585, 'samples': 6393984, 'steps': 33301, 'loss/train': 1.785483956336975} 08/30/2021 19:15:16 - INFO - __main__ - Step 33303: {'lr': 0.0004468144983259873, 'samples': 6394176, 'steps': 33302, 'loss/train': 1.0390609502792358} 08/30/2021 19:15:16 - INFO - __main__ - Step 33304: {'lr': 0.0004468112260170345, 'samples': 6394368, 'steps': 33303, 'loss/train': 1.4747045040130615} 08/30/2021 19:15:16 - INFO - __main__ - Step 33305: {'lr': 0.0004468079536194016, 'samples': 6394560, 'steps': 33304, 'loss/train': 1.726773977279663} 08/30/2021 19:15:18 - INFO - __main__ - Step 33306: {'lr': 0.00044680468113309006, 'samples': 6394752, 'steps': 33305, 'loss/train': 0.07333415001630783} 08/30/2021 19:15:19 - INFO - __main__ - Step 33307: {'lr': 0.0004468014085581014, 'samples': 6394944, 'steps': 33306, 'loss/train': 1.6688435077667236} 08/30/2021 19:15:19 - INFO - __main__ - Step 33308: {'lr': 0.0004467981358944371, 'samples': 6395136, 'steps': 33307, 'loss/train': 1.917307734489441} 08/30/2021 19:15:20 - INFO - __main__ - Step 33309: {'lr': 0.0004467948631420985, 'samples': 6395328, 'steps': 33308, 'loss/train': 1.5020296573638916} 08/30/2021 19:15:20 - INFO - __main__ - Step 33310: {'lr': 0.0004467915903010872, 'samples': 6395520, 'steps': 33309, 'loss/train': 1.3082365989685059} 08/30/2021 19:15:21 - INFO - __main__ - Step 33311: {'lr': 0.0004467883173714047, 'samples': 6395712, 'steps': 33310, 'loss/train': 1.3763829469680786} 08/30/2021 19:15:22 - INFO - __main__ - Step 33312: {'lr': 0.0004467850443530523, 'samples': 6395904, 'steps': 33311, 'loss/train': 2.2396857738494873} 08/30/2021 19:15:22 - INFO - __main__ - Step 33313: {'lr': 0.0004467817712460317, 'samples': 6396096, 'steps': 33312, 'loss/train': 1.550471305847168} 08/30/2021 19:15:23 - INFO - __main__ - Step 33314: {'lr': 0.00044677849805034424, 'samples': 6396288, 'steps': 33313, 'loss/train': 0.40899306535720825} 08/30/2021 19:15:23 - INFO - __main__ - Step 33315: {'lr': 0.0004467752247659914, 'samples': 6396480, 'steps': 33314, 'loss/train': 1.336354374885559} 08/30/2021 19:15:25 - INFO - __main__ - Step 33316: {'lr': 0.00044677195139297476, 'samples': 6396672, 'steps': 33315, 'loss/train': 1.3725905418395996} 08/30/2021 19:15:25 - INFO - __main__ - Step 33317: {'lr': 0.00044676867793129574, 'samples': 6396864, 'steps': 33316, 'loss/train': 1.360742211341858} 08/30/2021 19:15:26 - INFO - __main__ - Step 33318: {'lr': 0.00044676540438095565, 'samples': 6397056, 'steps': 33317, 'loss/train': 1.090036153793335} 08/30/2021 19:15:26 - INFO - __main__ - Step 33319: {'lr': 0.0004467621307419562, 'samples': 6397248, 'steps': 33318, 'loss/train': 0.1322993040084839} 08/30/2021 19:15:26 - INFO - __main__ - Step 33320: {'lr': 0.00044675885701429873, 'samples': 6397440, 'steps': 33319, 'loss/train': 0.9064639210700989} 08/30/2021 19:15:27 - INFO - __main__ - Step 33321: {'lr': 0.00044675558319798477, 'samples': 6397632, 'steps': 33320, 'loss/train': 1.3307347297668457} 08/30/2021 19:15:28 - INFO - __main__ - Step 33322: {'lr': 0.00044675230929301575, 'samples': 6397824, 'steps': 33321, 'loss/train': 0.08482823520898819} 08/30/2021 19:15:29 - INFO - __main__ - Step 33323: {'lr': 0.0004467490352993932, 'samples': 6398016, 'steps': 33322, 'loss/train': 1.1504961252212524} 08/30/2021 19:15:29 - INFO - __main__ - Step 33324: {'lr': 0.00044674576121711855, 'samples': 6398208, 'steps': 33323, 'loss/train': 1.6718014478683472} 08/30/2021 19:15:29 - INFO - __main__ - Step 33325: {'lr': 0.00044674248704619333, 'samples': 6398400, 'steps': 33324, 'loss/train': 1.4017398357391357} 08/30/2021 19:15:30 - INFO - __main__ - Step 33326: {'lr': 0.000446739212786619, 'samples': 6398592, 'steps': 33325, 'loss/train': 1.4466516971588135} 08/30/2021 19:15:32 - INFO - __main__ - Step 33327: {'lr': 0.000446735938438397, 'samples': 6398784, 'steps': 33326, 'loss/train': 1.4872729778289795} 08/30/2021 19:15:32 - INFO - __main__ - Step 33328: {'lr': 0.0004467326640015288, 'samples': 6398976, 'steps': 33327, 'loss/train': 1.0688589811325073} 08/30/2021 19:15:32 - INFO - __main__ - Step 33329: {'lr': 0.00044672938947601593, 'samples': 6399168, 'steps': 33328, 'loss/train': 1.420457124710083} 08/30/2021 19:15:33 - INFO - __main__ - Step 33330: {'lr': 0.00044672611486185976, 'samples': 6399360, 'steps': 33329, 'loss/train': 0.26510173082351685} 08/30/2021 19:15:33 - INFO - __main__ - Step 33331: {'lr': 0.0004467228401590619, 'samples': 6399552, 'steps': 33330, 'loss/train': 0.49148648977279663} 08/30/2021 19:15:33 - INFO - __main__ - Step 33332: {'lr': 0.00044671956536762375, 'samples': 6399744, 'steps': 33331, 'loss/train': 1.4820618629455566} 08/30/2021 19:15:35 - INFO - __main__ - Step 33333: {'lr': 0.00044671629048754683, 'samples': 6399936, 'steps': 33332, 'loss/train': 1.438414216041565} 08/30/2021 19:15:35 - INFO - __main__ - Step 33334: {'lr': 0.00044671301551883253, 'samples': 6400128, 'steps': 33333, 'loss/train': 1.1546604633331299} 08/30/2021 19:15:36 - INFO - __main__ - Step 33335: {'lr': 0.0004467097404614824, 'samples': 6400320, 'steps': 33334, 'loss/train': 1.3472340106964111} 08/30/2021 19:15:36 - INFO - __main__ - Step 33336: {'lr': 0.0004467064653154979, 'samples': 6400512, 'steps': 33335, 'loss/train': 1.4244062900543213} 08/30/2021 19:15:36 - INFO - __main__ - Step 33337: {'lr': 0.0004467031900808805, 'samples': 6400704, 'steps': 33336, 'loss/train': 1.1101934909820557} 08/30/2021 19:15:38 - INFO - __main__ - Step 33338: {'lr': 0.00044669991475763173, 'samples': 6400896, 'steps': 33337, 'loss/train': 1.6133058071136475} 08/30/2021 19:15:39 - INFO - __main__ - Step 33339: {'lr': 0.00044669663934575294, 'samples': 6401088, 'steps': 33338, 'loss/train': 0.6731969118118286} 08/30/2021 19:15:39 - INFO - __main__ - Step 33340: {'lr': 0.0004466933638452457, 'samples': 6401280, 'steps': 33339, 'loss/train': 1.2125256061553955} 08/30/2021 19:15:39 - INFO - __main__ - Step 33341: {'lr': 0.0004466900882561115, 'samples': 6401472, 'steps': 33340, 'loss/train': 1.2524387836456299} 08/30/2021 19:15:40 - INFO - __main__ - Step 33342: {'lr': 0.00044668681257835173, 'samples': 6401664, 'steps': 33341, 'loss/train': 1.8785761594772339} 08/30/2021 19:15:41 - INFO - __main__ - Step 33343: {'lr': 0.00044668353681196794, 'samples': 6401856, 'steps': 33342, 'loss/train': 1.8011149168014526} 08/30/2021 19:15:42 - INFO - __main__ - Step 33344: {'lr': 0.0004466802609569616, 'samples': 6402048, 'steps': 33343, 'loss/train': 1.8663297891616821} 08/30/2021 19:15:42 - INFO - __main__ - Step 33345: {'lr': 0.00044667698501333415, 'samples': 6402240, 'steps': 33344, 'loss/train': 1.5840978622436523} 08/30/2021 19:15:42 - INFO - __main__ - Step 33346: {'lr': 0.0004466737089810871, 'samples': 6402432, 'steps': 33345, 'loss/train': 1.02379310131073} 08/30/2021 19:15:43 - INFO - __main__ - Step 33347: {'lr': 0.00044667043286022193, 'samples': 6402624, 'steps': 33346, 'loss/train': 1.5514895915985107} 08/30/2021 19:15:45 - INFO - __main__ - Step 33348: {'lr': 0.00044666715665074, 'samples': 6402816, 'steps': 33347, 'loss/train': 2.2234818935394287} 08/30/2021 19:15:46 - INFO - __main__ - Step 33349: {'lr': 0.0004466638803526429, 'samples': 6403008, 'steps': 33348, 'loss/train': 1.400463342666626} 08/30/2021 19:15:46 - INFO - __main__ - Step 33350: {'lr': 0.0004466606039659322, 'samples': 6403200, 'steps': 33349, 'loss/train': 1.4251716136932373} 08/30/2021 19:15:46 - INFO - __main__ - Step 33351: {'lr': 0.0004466573274906092, 'samples': 6403392, 'steps': 33350, 'loss/train': 1.7673977613449097} 08/30/2021 19:15:47 - INFO - __main__ - Step 33352: {'lr': 0.0004466540509266754, 'samples': 6403584, 'steps': 33351, 'loss/train': 1.280025601387024} 08/30/2021 19:15:47 - INFO - __main__ - Step 33353: {'lr': 0.0004466507742741325, 'samples': 6403776, 'steps': 33352, 'loss/train': 3.522418975830078} 08/30/2021 19:15:47 - INFO - __main__ - Step 33354: {'lr': 0.0004466474975329816, 'samples': 6403968, 'steps': 33353, 'loss/train': 3.0891058444976807} 08/30/2021 19:15:49 - INFO - __main__ - Step 33355: {'lr': 0.0004466442207032244, 'samples': 6404160, 'steps': 33354, 'loss/train': 1.6727930307388306} 08/30/2021 19:15:49 - INFO - __main__ - Step 33356: {'lr': 0.00044664094378486243, 'samples': 6404352, 'steps': 33355, 'loss/train': 1.574659824371338} 08/30/2021 19:15:50 - INFO - __main__ - Step 33357: {'lr': 0.00044663766677789706, 'samples': 6404544, 'steps': 33356, 'loss/train': 1.6382181644439697} 08/30/2021 19:15:50 - INFO - __main__ - Step 33358: {'lr': 0.0004466343896823297, 'samples': 6404736, 'steps': 33357, 'loss/train': 1.435111403465271} 08/30/2021 19:15:50 - INFO - __main__ - Step 33359: {'lr': 0.000446631112498162, 'samples': 6404928, 'steps': 33358, 'loss/train': 1.0055221319198608} 08/30/2021 19:15:52 - INFO - __main__ - Step 33360: {'lr': 0.0004466278352253954, 'samples': 6405120, 'steps': 33359, 'loss/train': 1.7547920942306519} 08/30/2021 19:15:52 - INFO - __main__ - Step 33361: {'lr': 0.00044662455786403124, 'samples': 6405312, 'steps': 33360, 'loss/train': 1.5736093521118164} 08/30/2021 19:15:53 - INFO - __main__ - Step 33362: {'lr': 0.0004466212804140711, 'samples': 6405504, 'steps': 33361, 'loss/train': 0.19409291446208954} 08/30/2021 19:15:53 - INFO - __main__ - Step 33363: {'lr': 0.00044661800287551653, 'samples': 6405696, 'steps': 33362, 'loss/train': 0.8882451057434082} 08/30/2021 19:15:53 - INFO - __main__ - Step 33364: {'lr': 0.00044661472524836886, 'samples': 6405888, 'steps': 33363, 'loss/train': 1.423277497291565} 08/30/2021 19:15:55 - INFO - __main__ - Step 33365: {'lr': 0.00044661144753262963, 'samples': 6406080, 'steps': 33364, 'loss/train': 1.437907338142395} 08/30/2021 19:15:56 - INFO - __main__ - Step 33366: {'lr': 0.0004466081697283003, 'samples': 6406272, 'steps': 33365, 'loss/train': 2.14711856842041} 08/30/2021 19:15:56 - INFO - __main__ - Step 33367: {'lr': 0.00044660489183538237, 'samples': 6406464, 'steps': 33366, 'loss/train': 1.8020535707473755} 08/30/2021 19:15:57 - INFO - __main__ - Step 33368: {'lr': 0.0004466016138538773, 'samples': 6406656, 'steps': 33367, 'loss/train': 1.4772429466247559} 08/30/2021 19:15:57 - INFO - __main__ - Step 33369: {'lr': 0.0004465983357837866, 'samples': 6406848, 'steps': 33368, 'loss/train': 0.9149893522262573} 08/30/2021 19:15:57 - INFO - __main__ - Step 33370: {'lr': 0.00044659505762511176, 'samples': 6407040, 'steps': 33369, 'loss/train': 1.0663551092147827} 08/30/2021 19:15:59 - INFO - __main__ - Step 33371: {'lr': 0.00044659177937785417, 'samples': 6407232, 'steps': 33370, 'loss/train': 1.4070308208465576} 08/30/2021 19:15:59 - INFO - __main__ - Step 33372: {'lr': 0.0004465885010420154, 'samples': 6407424, 'steps': 33371, 'loss/train': 1.8669415712356567} 08/30/2021 19:16:00 - INFO - __main__ - Step 33373: {'lr': 0.0004465852226175968, 'samples': 6407616, 'steps': 33372, 'loss/train': 1.2759586572647095} 08/30/2021 19:16:00 - INFO - __main__ - Step 33374: {'lr': 0.00044658194410460004, 'samples': 6407808, 'steps': 33373, 'loss/train': 0.9852572083473206} 08/30/2021 19:16:00 - INFO - __main__ - Step 33375: {'lr': 0.0004465786655030264, 'samples': 6408000, 'steps': 33374, 'loss/train': 1.6221834421157837} 08/30/2021 19:16:02 - INFO - __main__ - Step 33376: {'lr': 0.00044657538681287746, 'samples': 6408192, 'steps': 33375, 'loss/train': 1.563546061515808} 08/30/2021 19:16:02 - INFO - __main__ - Step 33377: {'lr': 0.0004465721080341547, 'samples': 6408384, 'steps': 33376, 'loss/train': 1.5885995626449585} 08/30/2021 19:16:03 - INFO - __main__ - Step 33378: {'lr': 0.0004465688291668596, 'samples': 6408576, 'steps': 33377, 'loss/train': 1.658616304397583} 08/30/2021 19:16:03 - INFO - __main__ - Step 33379: {'lr': 0.00044656555021099363, 'samples': 6408768, 'steps': 33378, 'loss/train': 1.3255548477172852} 08/30/2021 19:16:03 - INFO - __main__ - Step 33380: {'lr': 0.00044656227116655824, 'samples': 6408960, 'steps': 33379, 'loss/train': 1.3153778314590454} 08/30/2021 19:16:05 - INFO - __main__ - Step 33381: {'lr': 0.00044655899203355486, 'samples': 6409152, 'steps': 33380, 'loss/train': 1.401679515838623} 08/30/2021 19:16:05 - INFO - __main__ - Step 33382: {'lr': 0.0004465557128119852, 'samples': 6409344, 'steps': 33381, 'loss/train': 1.3784312009811401} 08/30/2021 19:16:06 - INFO - __main__ - Step 33383: {'lr': 0.00044655243350185037, 'samples': 6409536, 'steps': 33382, 'loss/train': 1.7505137920379639} 08/30/2021 19:16:06 - INFO - __main__ - Step 33384: {'lr': 0.0004465491541031522, 'samples': 6409728, 'steps': 33383, 'loss/train': 1.6893738508224487} 08/30/2021 19:16:06 - INFO - __main__ - Step 33385: {'lr': 0.00044654587461589193, 'samples': 6409920, 'steps': 33384, 'loss/train': 1.365661859512329} 08/30/2021 19:16:08 - INFO - __main__ - Step 33386: {'lr': 0.0004465425950400711, 'samples': 6410112, 'steps': 33385, 'loss/train': 2.1446902751922607} 08/30/2021 19:16:08 - INFO - __main__ - Step 33387: {'lr': 0.00044653931537569125, 'samples': 6410304, 'steps': 33386, 'loss/train': 2.165961742401123} 08/30/2021 19:16:09 - INFO - __main__ - Step 33388: {'lr': 0.0004465360356227538, 'samples': 6410496, 'steps': 33387, 'loss/train': 1.543939232826233} 08/30/2021 19:16:09 - INFO - __main__ - Step 33389: {'lr': 0.0004465327557812603, 'samples': 6410688, 'steps': 33388, 'loss/train': 1.596062183380127} 08/30/2021 19:16:09 - INFO - __main__ - Step 33390: {'lr': 0.0004465294758512121, 'samples': 6410880, 'steps': 33389, 'loss/train': 1.463299036026001} 08/30/2021 19:16:11 - INFO - __main__ - Step 33391: {'lr': 0.0004465261958326108, 'samples': 6411072, 'steps': 33390, 'loss/train': 0.7451184391975403} 08/30/2021 19:16:11 - INFO - __main__ - Step 33392: {'lr': 0.0004465229157254578, 'samples': 6411264, 'steps': 33391, 'loss/train': 1.6218186616897583} 08/30/2021 19:16:12 - INFO - __main__ - Step 33393: {'lr': 0.0004465196355297546, 'samples': 6411456, 'steps': 33392, 'loss/train': 0.9780051708221436} 08/30/2021 19:16:12 - INFO - __main__ - Step 33394: {'lr': 0.0004465163552455027, 'samples': 6411648, 'steps': 33393, 'loss/train': 1.819261908531189} 08/30/2021 19:16:12 - INFO - __main__ - Step 33395: {'lr': 0.0004465130748727036, 'samples': 6411840, 'steps': 33394, 'loss/train': 2.0825252532958984} 08/30/2021 19:16:14 - INFO - __main__ - Step 33396: {'lr': 0.0004465097944113587, 'samples': 6412032, 'steps': 33395, 'loss/train': 1.670664668083191} 08/30/2021 19:16:14 - INFO - __main__ - Step 33397: {'lr': 0.00044650651386146954, 'samples': 6412224, 'steps': 33396, 'loss/train': 2.0088019371032715} 08/30/2021 19:16:15 - INFO - __main__ - Step 33398: {'lr': 0.00044650323322303757, 'samples': 6412416, 'steps': 33397, 'loss/train': 0.9385988116264343} 08/30/2021 19:16:15 - INFO - __main__ - Step 33399: {'lr': 0.0004464999524960642, 'samples': 6412608, 'steps': 33398, 'loss/train': 1.6312021017074585} 08/30/2021 19:16:15 - INFO - __main__ - Step 33400: {'lr': 0.0004464966716805511, 'samples': 6412800, 'steps': 33399, 'loss/train': 1.5122473239898682} 08/30/2021 19:16:17 - INFO - __main__ - Step 33401: {'lr': 0.0004464933907764996, 'samples': 6412992, 'steps': 33400, 'loss/train': 1.7289127111434937} 08/30/2021 19:16:17 - INFO - __main__ - Step 33402: {'lr': 0.0004464901097839112, 'samples': 6413184, 'steps': 33401, 'loss/train': 1.416804313659668} 08/30/2021 19:16:18 - INFO - __main__ - Step 33403: {'lr': 0.00044648682870278733, 'samples': 6413376, 'steps': 33402, 'loss/train': 1.2345597743988037} 08/30/2021 19:16:18 - INFO - __main__ - Step 33404: {'lr': 0.0004464835475331296, 'samples': 6413568, 'steps': 33403, 'loss/train': 1.0464625358581543} 08/30/2021 19:16:18 - INFO - __main__ - Step 33405: {'lr': 0.0004464802662749394, 'samples': 6413760, 'steps': 33404, 'loss/train': 1.4701182842254639} 08/30/2021 19:16:19 - INFO - __main__ - Step 33406: {'lr': 0.00044647698492821826, 'samples': 6413952, 'steps': 33405, 'loss/train': 1.5553449392318726} 08/30/2021 19:16:21 - INFO - __main__ - Step 33407: {'lr': 0.00044647370349296757, 'samples': 6414144, 'steps': 33406, 'loss/train': 2.0070667266845703} 08/30/2021 19:16:21 - INFO - __main__ - Step 33408: {'lr': 0.00044647042196918884, 'samples': 6414336, 'steps': 33407, 'loss/train': 1.4474754333496094} 08/30/2021 19:16:21 - INFO - __main__ - Step 33409: {'lr': 0.00044646714035688365, 'samples': 6414528, 'steps': 33408, 'loss/train': 1.617448091506958} 08/30/2021 19:16:22 - INFO - __main__ - Step 33410: {'lr': 0.00044646385865605335, 'samples': 6414720, 'steps': 33409, 'loss/train': 0.08607909083366394} 08/30/2021 19:16:22 - INFO - __main__ - Step 33411: {'lr': 0.0004464605768666995, 'samples': 6414912, 'steps': 33410, 'loss/train': 1.1770544052124023} 08/30/2021 19:16:22 - INFO - __main__ - Step 33412: {'lr': 0.0004464572949888235, 'samples': 6415104, 'steps': 33411, 'loss/train': 1.3189491033554077} 08/30/2021 19:16:24 - INFO - __main__ - Step 33413: {'lr': 0.0004464540130224268, 'samples': 6415296, 'steps': 33412, 'loss/train': 2.448939800262451} 08/30/2021 19:16:24 - INFO - __main__ - Step 33414: {'lr': 0.0004464507309675111, 'samples': 6415488, 'steps': 33413, 'loss/train': 0.8867089152336121} 08/30/2021 19:16:25 - INFO - __main__ - Step 33415: {'lr': 0.00044644744882407767, 'samples': 6415680, 'steps': 33414, 'loss/train': 1.3510990142822266} 08/30/2021 19:16:25 - INFO - __main__ - Step 33416: {'lr': 0.00044644416659212806, 'samples': 6415872, 'steps': 33415, 'loss/train': 1.515901803970337} 08/30/2021 19:16:25 - INFO - __main__ - Step 33417: {'lr': 0.00044644088427166375, 'samples': 6416064, 'steps': 33416, 'loss/train': 1.6699684858322144} 08/30/2021 19:16:27 - INFO - __main__ - Step 33418: {'lr': 0.00044643760186268615, 'samples': 6416256, 'steps': 33417, 'loss/train': 1.7504702806472778} 08/30/2021 19:16:28 - INFO - __main__ - Step 33419: {'lr': 0.00044643431936519683, 'samples': 6416448, 'steps': 33418, 'loss/train': 0.22187237441539764} 08/30/2021 19:16:28 - INFO - __main__ - Step 33420: {'lr': 0.00044643103677919726, 'samples': 6416640, 'steps': 33419, 'loss/train': 1.1697900295257568} 08/30/2021 19:16:29 - INFO - __main__ - Step 33421: {'lr': 0.00044642775410468896, 'samples': 6416832, 'steps': 33420, 'loss/train': 1.303484320640564} 08/30/2021 19:16:29 - INFO - __main__ - Step 33422: {'lr': 0.00044642447134167316, 'samples': 6417024, 'steps': 33421, 'loss/train': 1.6225663423538208} 08/30/2021 19:16:30 - INFO - __main__ - Step 33423: {'lr': 0.00044642118849015167, 'samples': 6417216, 'steps': 33422, 'loss/train': 1.4180470705032349} 08/30/2021 19:16:31 - INFO - __main__ - Step 33424: {'lr': 0.0004464179055501258, 'samples': 6417408, 'steps': 33423, 'loss/train': 1.0804719924926758} 08/30/2021 19:16:31 - INFO - __main__ - Step 33425: {'lr': 0.00044641462252159705, 'samples': 6417600, 'steps': 33424, 'loss/train': 1.3525092601776123} 08/30/2021 19:16:32 - INFO - __main__ - Step 33426: {'lr': 0.0004464113394045669, 'samples': 6417792, 'steps': 33425, 'loss/train': 1.0800803899765015} 08/30/2021 19:16:32 - INFO - __main__ - Step 33427: {'lr': 0.00044640805619903677, 'samples': 6417984, 'steps': 33426, 'loss/train': 1.8649523258209229} 08/30/2021 19:16:33 - INFO - __main__ - Step 33428: {'lr': 0.00044640477290500824, 'samples': 6418176, 'steps': 33427, 'loss/train': 1.5345628261566162} 08/30/2021 19:16:34 - INFO - __main__ - Step 33429: {'lr': 0.00044640148952248285, 'samples': 6418368, 'steps': 33428, 'loss/train': 1.6082801818847656} 08/30/2021 19:16:34 - INFO - __main__ - Step 33430: {'lr': 0.00044639820605146184, 'samples': 6418560, 'steps': 33429, 'loss/train': 0.3826752007007599} 08/30/2021 19:16:35 - INFO - __main__ - Step 33431: {'lr': 0.0004463949224919469, 'samples': 6418752, 'steps': 33430, 'loss/train': 1.5160101652145386} 08/30/2021 19:16:35 - INFO - __main__ - Step 33432: {'lr': 0.0004463916388439394, 'samples': 6418944, 'steps': 33431, 'loss/train': 1.416867733001709} 08/30/2021 19:16:37 - INFO - __main__ - Step 33433: {'lr': 0.00044638835510744094, 'samples': 6419136, 'steps': 33432, 'loss/train': 1.493934154510498} 08/30/2021 19:16:37 - INFO - __main__ - Step 33434: {'lr': 0.0004463850712824528, 'samples': 6419328, 'steps': 33433, 'loss/train': 1.8534473180770874} 08/30/2021 19:16:37 - INFO - __main__ - Step 33435: {'lr': 0.0004463817873689766, 'samples': 6419520, 'steps': 33434, 'loss/train': 0.8413693904876709} 08/30/2021 19:16:38 - INFO - __main__ - Step 33436: {'lr': 0.00044637850336701386, 'samples': 6419712, 'steps': 33435, 'loss/train': 1.0658906698226929} 08/30/2021 19:16:38 - INFO - __main__ - Step 33437: {'lr': 0.000446375219276566, 'samples': 6419904, 'steps': 33436, 'loss/train': 1.5574675798416138} 08/30/2021 19:16:40 - INFO - __main__ - Step 33438: {'lr': 0.0004463719350976344, 'samples': 6420096, 'steps': 33437, 'loss/train': 1.6721071004867554} 08/30/2021 19:16:40 - INFO - __main__ - Step 33439: {'lr': 0.0004463686508302207, 'samples': 6420288, 'steps': 33438, 'loss/train': 2.0010766983032227} 08/30/2021 19:16:41 - INFO - __main__ - Step 33440: {'lr': 0.00044636536647432636, 'samples': 6420480, 'steps': 33439, 'loss/train': 1.5309076309204102} 08/30/2021 19:16:41 - INFO - __main__ - Step 33441: {'lr': 0.00044636208202995277, 'samples': 6420672, 'steps': 33440, 'loss/train': 1.2251158952713013} 08/30/2021 19:16:41 - INFO - __main__ - Step 33442: {'lr': 0.0004463587974971014, 'samples': 6420864, 'steps': 33441, 'loss/train': 1.3289397954940796} 08/30/2021 19:16:43 - INFO - __main__ - Step 33443: {'lr': 0.0004463555128757739, 'samples': 6421056, 'steps': 33442, 'loss/train': 1.108396291732788} 08/30/2021 19:16:43 - INFO - __main__ - Step 33444: {'lr': 0.00044635222816597153, 'samples': 6421248, 'steps': 33443, 'loss/train': 1.6361125707626343} 08/30/2021 19:16:44 - INFO - __main__ - Step 33445: {'lr': 0.0004463489433676959, 'samples': 6421440, 'steps': 33444, 'loss/train': 1.3167794942855835} 08/30/2021 19:16:44 - INFO - __main__ - Step 33446: {'lr': 0.00044634565848094854, 'samples': 6421632, 'steps': 33445, 'loss/train': 1.4385465383529663} 08/30/2021 19:16:44 - INFO - __main__ - Step 33447: {'lr': 0.0004463423735057308, 'samples': 6421824, 'steps': 33446, 'loss/train': 1.1506036520004272} 08/30/2021 19:16:46 - INFO - __main__ - Step 33448: {'lr': 0.00044633908844204424, 'samples': 6422016, 'steps': 33447, 'loss/train': 2.2047119140625} 08/30/2021 19:16:46 - INFO - __main__ - Step 33449: {'lr': 0.0004463358032898903, 'samples': 6422208, 'steps': 33448, 'loss/train': 2.0550198554992676} 08/30/2021 19:16:47 - INFO - __main__ - Step 33450: {'lr': 0.00044633251804927044, 'samples': 6422400, 'steps': 33449, 'loss/train': 2.321042537689209} 08/30/2021 19:16:47 - INFO - __main__ - Step 33451: {'lr': 0.0004463292327201862, 'samples': 6422592, 'steps': 33450, 'loss/train': 1.3362419605255127} 08/30/2021 19:16:47 - INFO - __main__ - Step 33452: {'lr': 0.0004463259473026391, 'samples': 6422784, 'steps': 33451, 'loss/train': 1.324425458908081} 08/30/2021 19:16:48 - INFO - __main__ - Step 33453: {'lr': 0.0004463226617966305, 'samples': 6422976, 'steps': 33452, 'loss/train': 1.8268342018127441} 08/30/2021 19:16:49 - INFO - __main__ - Step 33454: {'lr': 0.00044631937620216196, 'samples': 6423168, 'steps': 33453, 'loss/train': 0.6967935562133789} 08/30/2021 19:16:50 - INFO - __main__ - Step 33455: {'lr': 0.00044631609051923494, 'samples': 6423360, 'steps': 33454, 'loss/train': 1.1998844146728516} 08/30/2021 19:16:50 - INFO - __main__ - Step 33456: {'lr': 0.00044631280474785086, 'samples': 6423552, 'steps': 33455, 'loss/train': 1.1822856664657593} 08/30/2021 19:16:50 - INFO - __main__ - Step 33457: {'lr': 0.0004463095188880113, 'samples': 6423744, 'steps': 33456, 'loss/train': 1.3683770895004272} 08/30/2021 19:16:51 - INFO - __main__ - Step 33458: {'lr': 0.00044630623293971775, 'samples': 6423936, 'steps': 33457, 'loss/train': 1.5302542448043823} 08/30/2021 19:16:52 - INFO - __main__ - Step 33459: {'lr': 0.0004463029469029716, 'samples': 6424128, 'steps': 33458, 'loss/train': 1.4877132177352905} 08/30/2021 19:16:53 - INFO - __main__ - Step 33460: {'lr': 0.0004462996607777743, 'samples': 6424320, 'steps': 33459, 'loss/train': 1.5018351078033447} 08/30/2021 19:16:53 - INFO - __main__ - Step 33461: {'lr': 0.00044629637456412754, 'samples': 6424512, 'steps': 33460, 'loss/train': 1.179540991783142} 08/30/2021 19:16:53 - INFO - __main__ - Step 33462: {'lr': 0.0004462930882620325, 'samples': 6424704, 'steps': 33461, 'loss/train': 1.7101011276245117} 08/30/2021 19:16:54 - INFO - __main__ - Step 33463: {'lr': 0.0004462898018714909, 'samples': 6424896, 'steps': 33462, 'loss/train': 1.0568920373916626} 08/30/2021 19:16:55 - INFO - __main__ - Step 33464: {'lr': 0.0004462865153925042, 'samples': 6425088, 'steps': 33463, 'loss/train': 1.4088925123214722} 08/30/2021 19:16:56 - INFO - __main__ - Step 33465: {'lr': 0.00044628322882507375, 'samples': 6425280, 'steps': 33464, 'loss/train': 1.9408656358718872} 08/30/2021 19:16:56 - INFO - __main__ - Step 33466: {'lr': 0.0004462799421692012, 'samples': 6425472, 'steps': 33465, 'loss/train': 1.1031192541122437} 08/30/2021 19:16:56 - INFO - __main__ - Step 33467: {'lr': 0.0004462766554248878, 'samples': 6425664, 'steps': 33466, 'loss/train': 1.4469138383865356} 08/30/2021 19:16:57 - INFO - __main__ - Step 33468: {'lr': 0.0004462733685921353, 'samples': 6425856, 'steps': 33467, 'loss/train': 1.2693172693252563} 08/30/2021 19:16:59 - INFO - __main__ - Step 33469: {'lr': 0.000446270081670945, 'samples': 6426048, 'steps': 33468, 'loss/train': 1.5170141458511353} 08/30/2021 19:17:00 - INFO - __main__ - Step 33470: {'lr': 0.0004462667946613184, 'samples': 6426240, 'steps': 33469, 'loss/train': 1.2980009317398071} 08/30/2021 19:17:00 - INFO - __main__ - Step 33471: {'lr': 0.00044626350756325707, 'samples': 6426432, 'steps': 33470, 'loss/train': 1.7524052858352661} 08/30/2021 19:17:00 - INFO - __main__ - Step 33472: {'lr': 0.0004462602203767624, 'samples': 6426624, 'steps': 33471, 'loss/train': 5.986457824707031} 08/30/2021 19:17:01 - INFO - __main__ - Step 33473: {'lr': 0.0004462569331018359, 'samples': 6426816, 'steps': 33472, 'loss/train': 5.9101128578186035} 08/30/2021 19:17:01 - INFO - __main__ - Step 33474: {'lr': 0.00044625364573847904, 'samples': 6427008, 'steps': 33473, 'loss/train': 1.7787965536117554} 08/30/2021 19:17:03 - INFO - __main__ - Step 33475: {'lr': 0.0004462503582866933, 'samples': 6427200, 'steps': 33474, 'loss/train': 1.9519734382629395} 08/30/2021 19:17:03 - INFO - __main__ - Step 33476: {'lr': 0.00044624707074648017, 'samples': 6427392, 'steps': 33475, 'loss/train': 1.2446976900100708} 08/30/2021 19:17:03 - INFO - __main__ - Step 33477: {'lr': 0.0004462437831178412, 'samples': 6427584, 'steps': 33476, 'loss/train': 1.5538004636764526} 08/30/2021 19:17:04 - INFO - __main__ - Step 33478: {'lr': 0.00044624049540077784, 'samples': 6427776, 'steps': 33477, 'loss/train': 1.4938383102416992} 08/30/2021 19:17:04 - INFO - __main__ - Step 33479: {'lr': 0.0004462372075952914, 'samples': 6427968, 'steps': 33478, 'loss/train': 1.6635462045669556} 08/30/2021 19:17:04 - INFO - __main__ - Step 33480: {'lr': 0.0004462339197013836, 'samples': 6428160, 'steps': 33479, 'loss/train': 1.6248817443847656} 08/30/2021 19:17:06 - INFO - __main__ - Step 33481: {'lr': 0.00044623063171905585, 'samples': 6428352, 'steps': 33480, 'loss/train': 1.0170185565948486} 08/30/2021 19:17:07 - INFO - __main__ - Step 33482: {'lr': 0.0004462273436483095, 'samples': 6428544, 'steps': 33481, 'loss/train': 1.661685585975647} 08/30/2021 19:17:07 - INFO - __main__ - Step 33483: {'lr': 0.00044622405548914627, 'samples': 6428736, 'steps': 33482, 'loss/train': 0.83110511302948} 08/30/2021 19:17:07 - INFO - __main__ - Step 33484: {'lr': 0.00044622076724156747, 'samples': 6428928, 'steps': 33483, 'loss/train': 1.1491162776947021} 08/30/2021 19:17:08 - INFO - __main__ - Step 33485: {'lr': 0.00044621747890557454, 'samples': 6429120, 'steps': 33484, 'loss/train': 0.08648316562175751} 08/30/2021 19:17:09 - INFO - __main__ - Step 33486: {'lr': 0.0004462141904811691, 'samples': 6429312, 'steps': 33485, 'loss/train': 1.4600337743759155} 08/30/2021 19:17:10 - INFO - __main__ - Step 33487: {'lr': 0.00044621090196835254, 'samples': 6429504, 'steps': 33486, 'loss/train': 2.0368728637695312} 08/30/2021 19:17:10 - INFO - __main__ - Step 33488: {'lr': 0.00044620761336712646, 'samples': 6429696, 'steps': 33487, 'loss/train': 2.0213589668273926} 08/30/2021 19:17:10 - INFO - __main__ - Step 33489: {'lr': 0.00044620432467749215, 'samples': 6429888, 'steps': 33488, 'loss/train': 1.6966632604599} 08/30/2021 19:17:11 - INFO - __main__ - Step 33490: {'lr': 0.0004462010358994513, 'samples': 6430080, 'steps': 33489, 'loss/train': 1.3306323289871216} 08/30/2021 19:17:12 - INFO - __main__ - Step 33491: {'lr': 0.0004461977470330052, 'samples': 6430272, 'steps': 33490, 'loss/train': 1.3611665964126587} 08/30/2021 19:17:13 - INFO - __main__ - Step 33492: {'lr': 0.00044619445807815545, 'samples': 6430464, 'steps': 33491, 'loss/train': 1.854926347732544} 08/30/2021 19:17:13 - INFO - __main__ - Step 33493: {'lr': 0.00044619116903490356, 'samples': 6430656, 'steps': 33492, 'loss/train': 0.38408511877059937} 08/30/2021 19:17:13 - INFO - __main__ - Step 33494: {'lr': 0.00044618787990325086, 'samples': 6430848, 'steps': 33493, 'loss/train': 1.6721330881118774} 08/30/2021 19:17:14 - INFO - __main__ - Step 33495: {'lr': 0.000446184590683199, 'samples': 6431040, 'steps': 33494, 'loss/train': 1.2868119478225708} 08/30/2021 19:17:15 - INFO - __main__ - Step 33496: {'lr': 0.00044618130137474935, 'samples': 6431232, 'steps': 33495, 'loss/train': 1.422435998916626} 08/30/2021 19:17:16 - INFO - __main__ - Step 33497: {'lr': 0.0004461780119779034, 'samples': 6431424, 'steps': 33496, 'loss/train': 1.496319055557251} 08/30/2021 19:17:16 - INFO - __main__ - Step 33498: {'lr': 0.0004461747224926628, 'samples': 6431616, 'steps': 33497, 'loss/train': 0.8715442419052124} 08/30/2021 19:17:16 - INFO - __main__ - Step 33499: {'lr': 0.0004461714329190288, 'samples': 6431808, 'steps': 33498, 'loss/train': 1.5960817337036133} 08/30/2021 19:17:17 - INFO - __main__ - Step 33500: {'lr': 0.00044616814325700293, 'samples': 6432000, 'steps': 33499, 'loss/train': 0.6516277194023132} 08/30/2021 19:17:18 - INFO - __main__ - Step 33501: {'lr': 0.0004461648535065869, 'samples': 6432192, 'steps': 33500, 'loss/train': 1.010624885559082} 08/30/2021 19:17:19 - INFO - __main__ - Step 33502: {'lr': 0.0004461615636677818, 'samples': 6432384, 'steps': 33501, 'loss/train': 1.2123264074325562} 08/30/2021 19:17:19 - INFO - __main__ - Step 33503: {'lr': 0.0004461582737405895, 'samples': 6432576, 'steps': 33502, 'loss/train': 1.5560311079025269} 08/30/2021 19:17:19 - INFO - __main__ - Step 33504: {'lr': 0.00044615498372501116, 'samples': 6432768, 'steps': 33503, 'loss/train': 1.3471797704696655} 08/30/2021 19:17:20 - INFO - __main__ - Step 33505: {'lr': 0.00044615169362104856, 'samples': 6432960, 'steps': 33504, 'loss/train': 1.5496647357940674} 08/30/2021 19:17:21 - INFO - __main__ - Step 33506: {'lr': 0.00044614840342870293, 'samples': 6433152, 'steps': 33505, 'loss/train': 1.0810092687606812} 08/30/2021 19:17:22 - INFO - __main__ - Step 33507: {'lr': 0.0004461451131479759, 'samples': 6433344, 'steps': 33506, 'loss/train': 1.672833800315857} 08/30/2021 19:17:22 - INFO - __main__ - Step 33508: {'lr': 0.0004461418227788689, 'samples': 6433536, 'steps': 33507, 'loss/train': 1.437759280204773} 08/30/2021 19:17:23 - INFO - __main__ - Step 33509: {'lr': 0.00044613853232138343, 'samples': 6433728, 'steps': 33508, 'loss/train': 1.7411867380142212} 08/30/2021 19:17:23 - INFO - __main__ - Step 33510: {'lr': 0.0004461352417755209, 'samples': 6433920, 'steps': 33509, 'loss/train': 1.44561767578125} 08/30/2021 19:17:23 - INFO - __main__ - Step 33511: {'lr': 0.0004461319511412829, 'samples': 6434112, 'steps': 33510, 'loss/train': 1.9419852495193481} 08/30/2021 19:17:25 - INFO - __main__ - Step 33512: {'lr': 0.00044612866041867093, 'samples': 6434304, 'steps': 33511, 'loss/train': 0.6615219712257385} 08/30/2021 19:17:26 - INFO - __main__ - Step 33513: {'lr': 0.0004461253696076863, 'samples': 6434496, 'steps': 33512, 'loss/train': 2.077902317047119} 08/30/2021 19:17:26 - INFO - __main__ - Step 33514: {'lr': 0.00044612207870833073, 'samples': 6434688, 'steps': 33513, 'loss/train': 0.9714586138725281} 08/30/2021 19:17:26 - INFO - __main__ - Step 33515: {'lr': 0.0004461187877206055, 'samples': 6434880, 'steps': 33514, 'loss/train': 1.8643016815185547} 08/30/2021 19:17:27 - INFO - __main__ - Step 33516: {'lr': 0.00044611549664451216, 'samples': 6435072, 'steps': 33515, 'loss/train': 1.7042568922042847} 08/30/2021 19:17:28 - INFO - __main__ - Step 33517: {'lr': 0.0004461122054800522, 'samples': 6435264, 'steps': 33516, 'loss/train': 1.6835029125213623} 08/30/2021 19:17:29 - INFO - __main__ - Step 33518: {'lr': 0.00044610891422722714, 'samples': 6435456, 'steps': 33517, 'loss/train': 1.140123963356018} 08/30/2021 19:17:29 - INFO - __main__ - Step 33519: {'lr': 0.00044610562288603846, 'samples': 6435648, 'steps': 33518, 'loss/train': 1.3658342361450195} 08/30/2021 19:17:29 - INFO - __main__ - Step 33520: {'lr': 0.00044610233145648756, 'samples': 6435840, 'steps': 33519, 'loss/train': 2.090968370437622} 08/30/2021 19:17:30 - INFO - __main__ - Step 33521: {'lr': 0.00044609903993857603, 'samples': 6436032, 'steps': 33520, 'loss/train': 1.7515610456466675} 08/30/2021 19:17:31 - INFO - __main__ - Step 33522: {'lr': 0.0004460957483323052, 'samples': 6436224, 'steps': 33521, 'loss/train': 2.3323111534118652} 08/30/2021 19:17:32 - INFO - __main__ - Step 33523: {'lr': 0.0004460924566376767, 'samples': 6436416, 'steps': 33522, 'loss/train': 1.9491584300994873} 08/30/2021 19:17:32 - INFO - __main__ - Step 33524: {'lr': 0.00044608916485469195, 'samples': 6436608, 'steps': 33523, 'loss/train': 0.9474073052406311} 08/30/2021 19:17:32 - INFO - __main__ - Step 33525: {'lr': 0.0004460858729833525, 'samples': 6436800, 'steps': 33524, 'loss/train': 1.5902125835418701} 08/30/2021 19:17:33 - INFO - __main__ - Step 33526: {'lr': 0.0004460825810236598, 'samples': 6436992, 'steps': 33525, 'loss/train': 1.3268276453018188} 08/30/2021 19:17:34 - INFO - __main__ - Step 33527: {'lr': 0.00044607928897561524, 'samples': 6437184, 'steps': 33526, 'loss/train': 1.4679911136627197} 08/30/2021 19:17:35 - INFO - __main__ - Step 33528: {'lr': 0.0004460759968392204, 'samples': 6437376, 'steps': 33527, 'loss/train': 1.366976261138916} 08/30/2021 19:17:35 - INFO - __main__ - Step 33529: {'lr': 0.0004460727046144768, 'samples': 6437568, 'steps': 33528, 'loss/train': 1.1873396635055542} 08/30/2021 19:17:36 - INFO - __main__ - Step 33530: {'lr': 0.00044606941230138574, 'samples': 6437760, 'steps': 33529, 'loss/train': 1.4000188112258911} 08/30/2021 19:17:36 - INFO - __main__ - Step 33531: {'lr': 0.0004460661198999489, 'samples': 6437952, 'steps': 33530, 'loss/train': 1.60287606716156} 08/30/2021 19:17:37 - INFO - __main__ - Step 33532: {'lr': 0.0004460628274101677, 'samples': 6438144, 'steps': 33531, 'loss/train': 1.2830095291137695} 08/30/2021 19:17:38 - INFO - __main__ - Step 33533: {'lr': 0.0004460595348320436, 'samples': 6438336, 'steps': 33532, 'loss/train': 1.4931893348693848} 08/30/2021 19:17:38 - INFO - __main__ - Step 33534: {'lr': 0.0004460562421655782, 'samples': 6438528, 'steps': 33533, 'loss/train': 1.1894075870513916} 08/30/2021 19:17:39 - INFO - __main__ - Step 33535: {'lr': 0.0004460529494107727, 'samples': 6438720, 'steps': 33534, 'loss/train': 1.116638422012329} 08/30/2021 19:17:39 - INFO - __main__ - Step 33536: {'lr': 0.00044604965656762884, 'samples': 6438912, 'steps': 33535, 'loss/train': 1.6395421028137207} 08/30/2021 19:17:40 - INFO - __main__ - Step 33537: {'lr': 0.0004460463636361481, 'samples': 6439104, 'steps': 33536, 'loss/train': 1.503105640411377} 08/30/2021 19:17:41 - INFO - __main__ - Step 33538: {'lr': 0.00044604307061633187, 'samples': 6439296, 'steps': 33537, 'loss/train': 1.4628092050552368} 08/30/2021 19:17:41 - INFO - __main__ - Step 33539: {'lr': 0.0004460397775081816, 'samples': 6439488, 'steps': 33538, 'loss/train': 0.7604972720146179} 08/30/2021 19:17:42 - INFO - __main__ - Step 33540: {'lr': 0.00044603648431169884, 'samples': 6439680, 'steps': 33539, 'loss/train': 1.6785184144973755} 08/30/2021 19:17:42 - INFO - __main__ - Step 33541: {'lr': 0.0004460331910268851, 'samples': 6439872, 'steps': 33540, 'loss/train': 1.0894722938537598} 08/30/2021 19:17:43 - INFO - __main__ - Step 33542: {'lr': 0.0004460298976537418, 'samples': 6440064, 'steps': 33541, 'loss/train': 1.0590217113494873} 08/30/2021 19:17:44 - INFO - __main__ - Step 33543: {'lr': 0.00044602660419227046, 'samples': 6440256, 'steps': 33542, 'loss/train': 1.2171657085418701} 08/30/2021 19:17:44 - INFO - __main__ - Step 33544: {'lr': 0.0004460233106424726, 'samples': 6440448, 'steps': 33543, 'loss/train': 2.1229300498962402} 08/30/2021 19:17:45 - INFO - __main__ - Step 33545: {'lr': 0.00044602001700434963, 'samples': 6440640, 'steps': 33544, 'loss/train': 1.7850686311721802} 08/30/2021 19:17:45 - INFO - __main__ - Step 33546: {'lr': 0.00044601672327790304, 'samples': 6440832, 'steps': 33545, 'loss/train': 1.6989439725875854} 08/30/2021 19:17:45 - INFO - __main__ - Step 33547: {'lr': 0.00044601342946313437, 'samples': 6441024, 'steps': 33546, 'loss/train': 1.5467450618743896} 08/30/2021 19:17:47 - INFO - __main__ - Step 33548: {'lr': 0.0004460101355600451, 'samples': 6441216, 'steps': 33547, 'loss/train': 1.662822961807251} 08/30/2021 19:17:47 - INFO - __main__ - Step 33549: {'lr': 0.0004460068415686366, 'samples': 6441408, 'steps': 33548, 'loss/train': 0.7413464784622192} 08/30/2021 19:17:48 - INFO - __main__ - Step 33550: {'lr': 0.0004460035474889105, 'samples': 6441600, 'steps': 33549, 'loss/train': 1.6940312385559082} 08/30/2021 19:17:48 - INFO - __main__ - Step 33551: {'lr': 0.00044600025332086824, 'samples': 6441792, 'steps': 33550, 'loss/train': 1.6477826833724976} 08/30/2021 19:17:48 - INFO - __main__ - Step 33552: {'lr': 0.0004459969590645113, 'samples': 6441984, 'steps': 33551, 'loss/train': 1.9770739078521729} 08/30/2021 19:17:50 - INFO - __main__ - Step 33553: {'lr': 0.000445993664719841, 'samples': 6442176, 'steps': 33552, 'loss/train': 1.5966130495071411} 08/30/2021 19:17:50 - INFO - __main__ - Step 33554: {'lr': 0.0004459903702868592, 'samples': 6442368, 'steps': 33553, 'loss/train': 1.5315237045288086} 08/30/2021 19:17:51 - INFO - __main__ - Step 33555: {'lr': 0.00044598707576556706, 'samples': 6442560, 'steps': 33554, 'loss/train': 1.59503173828125} 08/30/2021 19:17:51 - INFO - __main__ - Step 33556: {'lr': 0.00044598378115596614, 'samples': 6442752, 'steps': 33555, 'loss/train': 1.8892861604690552} 08/30/2021 19:17:51 - INFO - __main__ - Step 33557: {'lr': 0.000445980486458058, 'samples': 6442944, 'steps': 33556, 'loss/train': 1.628419041633606} 08/30/2021 19:17:53 - INFO - __main__ - Step 33558: {'lr': 0.0004459771916718441, 'samples': 6443136, 'steps': 33557, 'loss/train': 0.602741003036499} 08/30/2021 19:17:54 - INFO - __main__ - Step 33559: {'lr': 0.0004459738967973258, 'samples': 6443328, 'steps': 33558, 'loss/train': 0.1294114738702774} 08/30/2021 19:17:54 - INFO - __main__ - Step 33560: {'lr': 0.00044597060183450477, 'samples': 6443520, 'steps': 33559, 'loss/train': 1.6607118844985962} 08/30/2021 19:17:54 - INFO - __main__ - Step 33561: {'lr': 0.00044596730678338236, 'samples': 6443712, 'steps': 33560, 'loss/train': 1.4046095609664917} 08/30/2021 19:17:55 - INFO - __main__ - Step 33562: {'lr': 0.0004459640116439602, 'samples': 6443904, 'steps': 33561, 'loss/train': 1.2720739841461182} 08/30/2021 19:17:56 - INFO - __main__ - Step 33563: {'lr': 0.0004459607164162396, 'samples': 6444096, 'steps': 33562, 'loss/train': 0.976750373840332} 08/30/2021 19:17:57 - INFO - __main__ - Step 33564: {'lr': 0.00044595742110022216, 'samples': 6444288, 'steps': 33563, 'loss/train': 1.6367906332015991} 08/30/2021 19:17:57 - INFO - __main__ - Step 33565: {'lr': 0.00044595412569590934, 'samples': 6444480, 'steps': 33564, 'loss/train': 1.6431139707565308} 08/30/2021 19:17:57 - INFO - __main__ - Step 33566: {'lr': 0.0004459508302033025, 'samples': 6444672, 'steps': 33565, 'loss/train': 1.485739827156067} 08/30/2021 19:17:58 - INFO - __main__ - Step 33567: {'lr': 0.00044594753462240335, 'samples': 6444864, 'steps': 33566, 'loss/train': 1.5362398624420166} 08/30/2021 19:17:59 - INFO - __main__ - Step 33568: {'lr': 0.0004459442389532132, 'samples': 6445056, 'steps': 33567, 'loss/train': 0.3389038145542145} 08/30/2021 19:18:00 - INFO - __main__ - Step 33569: {'lr': 0.0004459409431957337, 'samples': 6445248, 'steps': 33568, 'loss/train': 1.1762274503707886} 08/30/2021 19:18:00 - INFO - __main__ - Step 33570: {'lr': 0.00044593764734996615, 'samples': 6445440, 'steps': 33569, 'loss/train': 1.5141596794128418} 08/30/2021 19:18:00 - INFO - __main__ - Step 33571: {'lr': 0.00044593435141591215, 'samples': 6445632, 'steps': 33570, 'loss/train': 1.363669514656067} 08/30/2021 19:18:01 - INFO - __main__ - Step 33572: {'lr': 0.00044593105539357313, 'samples': 6445824, 'steps': 33571, 'loss/train': 1.764335036277771} 08/30/2021 19:18:02 - INFO - __main__ - Step 33573: {'lr': 0.00044592775928295063, 'samples': 6446016, 'steps': 33572, 'loss/train': 1.2118182182312012} 08/30/2021 19:18:03 - INFO - __main__ - Step 33574: {'lr': 0.0004459244630840461, 'samples': 6446208, 'steps': 33573, 'loss/train': 1.42490553855896} 08/30/2021 19:18:03 - INFO - __main__ - Step 33575: {'lr': 0.000445921166796861, 'samples': 6446400, 'steps': 33574, 'loss/train': 1.322339653968811} 08/30/2021 19:18:03 - INFO - __main__ - Step 33576: {'lr': 0.00044591787042139684, 'samples': 6446592, 'steps': 33575, 'loss/train': 1.9720096588134766} 08/30/2021 19:18:04 - INFO - __main__ - Step 33577: {'lr': 0.0004459145739576552, 'samples': 6446784, 'steps': 33576, 'loss/train': 1.5571340322494507} 08/30/2021 19:18:04 - INFO - __main__ - Step 33578: {'lr': 0.0004459112774056374, 'samples': 6446976, 'steps': 33577, 'loss/train': 0.08507446944713593} 08/30/2021 19:18:06 - INFO - __main__ - Step 33579: {'lr': 0.000445907980765345, 'samples': 6447168, 'steps': 33578, 'loss/train': 0.137797549366951} 08/30/2021 19:18:07 - INFO - __main__ - Step 33580: {'lr': 0.00044590468403677954, 'samples': 6447360, 'steps': 33579, 'loss/train': 1.6683679819107056} 08/30/2021 19:18:07 - INFO - __main__ - Step 33581: {'lr': 0.00044590138721994243, 'samples': 6447552, 'steps': 33580, 'loss/train': 0.0656447559595108} 08/30/2021 19:18:08 - INFO - __main__ - Step 33582: {'lr': 0.00044589809031483517, 'samples': 6447744, 'steps': 33581, 'loss/train': 1.7217763662338257} 08/30/2021 19:18:08 - INFO - __main__ - Step 33583: {'lr': 0.0004458947933214592, 'samples': 6447936, 'steps': 33582, 'loss/train': 1.8664904832839966} 08/30/2021 19:18:09 - INFO - __main__ - Step 33584: {'lr': 0.0004458914962398162, 'samples': 6448128, 'steps': 33583, 'loss/train': 1.1735714673995972} 08/30/2021 19:18:10 - INFO - __main__ - Step 33585: {'lr': 0.0004458881990699074, 'samples': 6448320, 'steps': 33584, 'loss/train': 1.5449466705322266} 08/30/2021 19:18:10 - INFO - __main__ - Step 33586: {'lr': 0.00044588490181173435, 'samples': 6448512, 'steps': 33585, 'loss/train': 0.9304819107055664} 08/30/2021 19:18:10 - INFO - __main__ - Step 33587: {'lr': 0.0004458816044652987, 'samples': 6448704, 'steps': 33586, 'loss/train': 1.712382435798645} 08/30/2021 19:18:11 - INFO - __main__ - Step 33588: {'lr': 0.00044587830703060176, 'samples': 6448896, 'steps': 33587, 'loss/train': 1.574870228767395} 08/30/2021 19:18:12 - INFO - __main__ - Step 33589: {'lr': 0.00044587500950764514, 'samples': 6449088, 'steps': 33588, 'loss/train': 1.2343231439590454} 08/30/2021 19:18:13 - INFO - __main__ - Step 33590: {'lr': 0.0004458717118964302, 'samples': 6449280, 'steps': 33589, 'loss/train': 1.4308565855026245} 08/30/2021 19:18:13 - INFO - __main__ - Step 33591: {'lr': 0.0004458684141969585, 'samples': 6449472, 'steps': 33590, 'loss/train': 0.8971796631813049} 08/30/2021 19:18:14 - INFO - __main__ - Step 33592: {'lr': 0.0004458651164092315, 'samples': 6449664, 'steps': 33591, 'loss/train': 1.4396170377731323} 08/30/2021 19:18:14 - INFO - __main__ - Step 33593: {'lr': 0.00044586181853325076, 'samples': 6449856, 'steps': 33592, 'loss/train': 1.6373296976089478} 08/30/2021 19:18:15 - INFO - __main__ - Step 33594: {'lr': 0.0004458585205690177, 'samples': 6450048, 'steps': 33593, 'loss/train': 1.636523723602295} 08/30/2021 19:18:16 - INFO - __main__ - Step 33595: {'lr': 0.0004458552225165338, 'samples': 6450240, 'steps': 33594, 'loss/train': 1.4056764841079712} 08/30/2021 19:18:16 - INFO - __main__ - Step 33596: {'lr': 0.00044585192437580044, 'samples': 6450432, 'steps': 33595, 'loss/train': 1.401124119758606} 08/30/2021 19:18:17 - INFO - __main__ - Step 33597: {'lr': 0.0004458486261468194, 'samples': 6450624, 'steps': 33596, 'loss/train': 1.8220943212509155} 08/30/2021 19:18:17 - INFO - __main__ - Step 33598: {'lr': 0.0004458453278295919, 'samples': 6450816, 'steps': 33597, 'loss/train': 1.9699482917785645} 08/30/2021 19:18:18 - INFO - __main__ - Step 33599: {'lr': 0.00044584202942411956, 'samples': 6451008, 'steps': 33598, 'loss/train': 1.4828118085861206} 08/30/2021 19:18:19 - INFO - __main__ - Step 33600: {'lr': 0.00044583873093040376, 'samples': 6451200, 'steps': 33599, 'loss/train': 1.154546856880188} 08/30/2021 19:18:19 - INFO - __main__ - Step 33601: {'lr': 0.00044583543234844616, 'samples': 6451392, 'steps': 33600, 'loss/train': 1.019271731376648} 08/30/2021 19:18:20 - INFO - __main__ - Step 33602: {'lr': 0.00044583213367824806, 'samples': 6451584, 'steps': 33601, 'loss/train': 1.2273890972137451} 08/30/2021 19:18:20 - INFO - __main__ - Step 33603: {'lr': 0.00044582883491981097, 'samples': 6451776, 'steps': 33602, 'loss/train': 1.2579402923583984} 08/30/2021 19:18:21 - INFO - __main__ - Step 33604: {'lr': 0.0004458255360731365, 'samples': 6451968, 'steps': 33603, 'loss/train': 1.7824475765228271} 08/30/2021 19:18:22 - INFO - __main__ - Step 33605: {'lr': 0.00044582223713822606, 'samples': 6452160, 'steps': 33604, 'loss/train': 1.8708246946334839} 08/30/2021 19:18:22 - INFO - __main__ - Step 33606: {'lr': 0.0004458189381150811, 'samples': 6452352, 'steps': 33605, 'loss/train': 1.6141432523727417} 08/30/2021 19:18:23 - INFO - __main__ - Step 33607: {'lr': 0.00044581563900370326, 'samples': 6452544, 'steps': 33606, 'loss/train': 1.4116876125335693} 08/30/2021 19:18:23 - INFO - __main__ - Step 33608: {'lr': 0.0004458123398040938, 'samples': 6452736, 'steps': 33607, 'loss/train': 1.2242189645767212} 08/30/2021 19:18:25 - INFO - __main__ - Step 33609: {'lr': 0.0004458090405162544, 'samples': 6452928, 'steps': 33608, 'loss/train': 1.7578891515731812} 08/30/2021 19:18:25 - INFO - __main__ - Step 33610: {'lr': 0.0004458057411401864, 'samples': 6453120, 'steps': 33609, 'loss/train': 0.0835859552025795} 08/30/2021 19:18:25 - INFO - __main__ - Step 33611: {'lr': 0.00044580244167589136, 'samples': 6453312, 'steps': 33610, 'loss/train': 1.689874291419983} 08/30/2021 19:18:26 - INFO - __main__ - Step 33612: {'lr': 0.00044579914212337083, 'samples': 6453504, 'steps': 33611, 'loss/train': 1.5564651489257812} 08/30/2021 19:18:26 - INFO - __main__ - Step 33613: {'lr': 0.00044579584248262617, 'samples': 6453696, 'steps': 33612, 'loss/train': 1.5197362899780273} 08/30/2021 19:18:28 - INFO - __main__ - Step 33614: {'lr': 0.0004457925427536589, 'samples': 6453888, 'steps': 33613, 'loss/train': 1.3100367784500122} 08/30/2021 19:18:28 - INFO - __main__ - Step 33615: {'lr': 0.0004457892429364706, 'samples': 6454080, 'steps': 33614, 'loss/train': 1.5002819299697876} 08/30/2021 19:18:28 - INFO - __main__ - Step 33616: {'lr': 0.00044578594303106266, 'samples': 6454272, 'steps': 33615, 'loss/train': 1.2887840270996094} 08/30/2021 19:18:29 - INFO - __main__ - Step 33617: {'lr': 0.00044578264303743654, 'samples': 6454464, 'steps': 33616, 'loss/train': 1.5096867084503174} 08/30/2021 19:18:29 - INFO - __main__ - Step 33618: {'lr': 0.00044577934295559387, 'samples': 6454656, 'steps': 33617, 'loss/train': 0.6373361945152283} 08/30/2021 19:18:29 - INFO - __main__ - Step 33619: {'lr': 0.000445776042785536, 'samples': 6454848, 'steps': 33618, 'loss/train': 1.3112380504608154} 08/30/2021 19:18:31 - INFO - __main__ - Step 33620: {'lr': 0.00044577274252726454, 'samples': 6455040, 'steps': 33619, 'loss/train': 1.7142326831817627} 08/30/2021 19:18:31 - INFO - __main__ - Step 33621: {'lr': 0.00044576944218078075, 'samples': 6455232, 'steps': 33620, 'loss/train': 1.010748028755188} 08/30/2021 19:18:32 - INFO - __main__ - Step 33622: {'lr': 0.00044576614174608644, 'samples': 6455424, 'steps': 33621, 'loss/train': 1.9477105140686035} 08/30/2021 19:18:32 - INFO - __main__ - Step 33623: {'lr': 0.0004457628412231828, 'samples': 6455616, 'steps': 33622, 'loss/train': 0.5873215198516846} 08/30/2021 19:18:32 - INFO - __main__ - Step 33624: {'lr': 0.0004457595406120715, 'samples': 6455808, 'steps': 33623, 'loss/train': 1.3149832487106323} 08/30/2021 19:18:34 - INFO - __main__ - Step 33625: {'lr': 0.000445756239912754, 'samples': 6456000, 'steps': 33624, 'loss/train': 1.191064476966858} 08/30/2021 19:18:34 - INFO - __main__ - Step 33626: {'lr': 0.00044575293912523173, 'samples': 6456192, 'steps': 33625, 'loss/train': 1.6719938516616821} 08/30/2021 19:18:35 - INFO - __main__ - Step 33627: {'lr': 0.0004457496382495062, 'samples': 6456384, 'steps': 33626, 'loss/train': 1.5137373208999634} 08/30/2021 19:18:35 - INFO - __main__ - Step 33628: {'lr': 0.00044574633728557887, 'samples': 6456576, 'steps': 33627, 'loss/train': 1.7458797693252563} 08/30/2021 19:18:35 - INFO - __main__ - Step 33629: {'lr': 0.0004457430362334513, 'samples': 6456768, 'steps': 33628, 'loss/train': 1.588250994682312} 08/30/2021 19:18:37 - INFO - __main__ - Step 33630: {'lr': 0.00044573973509312494, 'samples': 6456960, 'steps': 33629, 'loss/train': 1.6230896711349487} 08/30/2021 19:18:37 - INFO - __main__ - Step 33631: {'lr': 0.00044573643386460127, 'samples': 6457152, 'steps': 33630, 'loss/train': 1.3803664445877075} 08/30/2021 19:18:38 - INFO - __main__ - Step 33632: {'lr': 0.00044573313254788176, 'samples': 6457344, 'steps': 33631, 'loss/train': 1.405279517173767} 08/30/2021 19:18:38 - INFO - __main__ - Step 33633: {'lr': 0.00044572983114296794, 'samples': 6457536, 'steps': 33632, 'loss/train': 1.3801747560501099} 08/30/2021 19:18:38 - INFO - __main__ - Step 33634: {'lr': 0.00044572652964986126, 'samples': 6457728, 'steps': 33633, 'loss/train': 1.7407443523406982} 08/30/2021 19:18:40 - INFO - __main__ - Step 33635: {'lr': 0.0004457232280685633, 'samples': 6457920, 'steps': 33634, 'loss/train': 1.8664658069610596} 08/30/2021 19:18:41 - INFO - __main__ - Step 33636: {'lr': 0.0004457199263990754, 'samples': 6458112, 'steps': 33635, 'loss/train': 1.5581839084625244} 08/30/2021 19:18:41 - INFO - __main__ - Step 33637: {'lr': 0.0004457166246413992, 'samples': 6458304, 'steps': 33636, 'loss/train': 1.475074291229248} 08/30/2021 19:18:42 - INFO - __main__ - Step 33638: {'lr': 0.000445713322795536, 'samples': 6458496, 'steps': 33637, 'loss/train': 2.033583164215088} 08/30/2021 19:18:42 - INFO - __main__ - Step 33639: {'lr': 0.0004457100208614875, 'samples': 6458688, 'steps': 33638, 'loss/train': 1.7355316877365112} 08/30/2021 19:18:43 - INFO - __main__ - Step 33640: {'lr': 0.00044570671883925497, 'samples': 6458880, 'steps': 33639, 'loss/train': 1.048525333404541} 08/30/2021 19:18:44 - INFO - __main__ - Step 33641: {'lr': 0.00044570341672884006, 'samples': 6459072, 'steps': 33640, 'loss/train': 1.741182804107666} 08/30/2021 19:18:44 - INFO - __main__ - Step 33642: {'lr': 0.0004457001145302443, 'samples': 6459264, 'steps': 33641, 'loss/train': 1.8247840404510498} 08/30/2021 19:18:45 - INFO - __main__ - Step 33643: {'lr': 0.00044569681224346897, 'samples': 6459456, 'steps': 33642, 'loss/train': 1.3121438026428223} 08/30/2021 19:18:45 - INFO - __main__ - Step 33644: {'lr': 0.0004456935098685158, 'samples': 6459648, 'steps': 33643, 'loss/train': 1.1755136251449585} 08/30/2021 19:18:46 - INFO - __main__ - Step 33645: {'lr': 0.000445690207405386, 'samples': 6459840, 'steps': 33644, 'loss/train': 1.9052174091339111} 08/30/2021 19:18:47 - INFO - __main__ - Step 33646: {'lr': 0.00044568690485408125, 'samples': 6460032, 'steps': 33645, 'loss/train': 2.1132073402404785} 08/30/2021 19:18:47 - INFO - __main__ - Step 33647: {'lr': 0.0004456836022146031, 'samples': 6460224, 'steps': 33646, 'loss/train': 1.7295184135437012} 08/30/2021 19:18:48 - INFO - __main__ - Step 33648: {'lr': 0.00044568029948695287, 'samples': 6460416, 'steps': 33647, 'loss/train': 1.062779188156128} 08/30/2021 19:18:48 - INFO - __main__ - Step 33649: {'lr': 0.0004456769966711321, 'samples': 6460608, 'steps': 33648, 'loss/train': 1.621753215789795} 08/30/2021 19:18:50 - INFO - __main__ - Step 33650: {'lr': 0.00044567369376714226, 'samples': 6460800, 'steps': 33649, 'loss/train': 1.470309853553772} 08/30/2021 19:18:50 - INFO - __main__ - Step 33651: {'lr': 0.00044567039077498497, 'samples': 6460992, 'steps': 33650, 'loss/train': 1.4786673784255981} 08/30/2021 19:18:50 - INFO - __main__ - Step 33652: {'lr': 0.00044566708769466155, 'samples': 6461184, 'steps': 33651, 'loss/train': 1.9077013731002808} 08/30/2021 19:18:51 - INFO - __main__ - Step 33653: {'lr': 0.00044566378452617363, 'samples': 6461376, 'steps': 33652, 'loss/train': 1.3045562505722046} 08/30/2021 19:18:51 - INFO - __main__ - Step 33654: {'lr': 0.0004456604812695226, 'samples': 6461568, 'steps': 33653, 'loss/train': 0.2149282991886139} 08/30/2021 19:18:51 - INFO - __main__ - Step 33655: {'lr': 0.0004456571779247099, 'samples': 6461760, 'steps': 33654, 'loss/train': 2.1666784286499023} 08/30/2021 19:18:53 - INFO - __main__ - Step 33656: {'lr': 0.0004456538744917372, 'samples': 6461952, 'steps': 33655, 'loss/train': 2.077083110809326} 08/30/2021 19:18:53 - INFO - __main__ - Step 33657: {'lr': 0.0004456505709706059, 'samples': 6462144, 'steps': 33656, 'loss/train': 1.508438229560852} 08/30/2021 19:18:54 - INFO - __main__ - Step 33658: {'lr': 0.0004456472673613174, 'samples': 6462336, 'steps': 33657, 'loss/train': 1.0288509130477905} 08/30/2021 19:18:54 - INFO - __main__ - Step 33659: {'lr': 0.00044564396366387327, 'samples': 6462528, 'steps': 33658, 'loss/train': 1.1481804847717285} 08/30/2021 19:18:55 - INFO - __main__ - Step 33660: {'lr': 0.000445640659878275, 'samples': 6462720, 'steps': 33659, 'loss/train': 1.3931019306182861} 08/30/2021 19:18:56 - INFO - __main__ - Step 33661: {'lr': 0.00044563735600452407, 'samples': 6462912, 'steps': 33660, 'loss/train': 1.7889535427093506} 08/30/2021 19:18:57 - INFO - __main__ - Step 33662: {'lr': 0.000445634052042622, 'samples': 6463104, 'steps': 33661, 'loss/train': 1.5299344062805176} 08/30/2021 19:18:57 - INFO - __main__ - Step 33663: {'lr': 0.00044563074799257015, 'samples': 6463296, 'steps': 33662, 'loss/train': 1.7181077003479004} 08/30/2021 19:18:57 - INFO - __main__ - Step 33664: {'lr': 0.0004456274438543702, 'samples': 6463488, 'steps': 33663, 'loss/train': 1.537021517753601} 08/30/2021 19:18:58 - INFO - __main__ - Step 33665: {'lr': 0.0004456241396280234, 'samples': 6463680, 'steps': 33664, 'loss/train': 1.6002298593521118} 08/30/2021 19:18:59 - INFO - __main__ - Step 33666: {'lr': 0.00044562083531353154, 'samples': 6463872, 'steps': 33665, 'loss/train': 1.5957136154174805} 08/30/2021 19:19:00 - INFO - __main__ - Step 33667: {'lr': 0.00044561753091089585, 'samples': 6464064, 'steps': 33666, 'loss/train': 1.194705843925476} 08/30/2021 19:19:00 - INFO - __main__ - Step 33668: {'lr': 0.00044561422642011794, 'samples': 6464256, 'steps': 33667, 'loss/train': 1.3724820613861084} 08/30/2021 19:19:01 - INFO - __main__ - Step 33669: {'lr': 0.00044561092184119933, 'samples': 6464448, 'steps': 33668, 'loss/train': 0.5602323412895203} 08/30/2021 19:19:01 - INFO - __main__ - Step 33670: {'lr': 0.00044560761717414143, 'samples': 6464640, 'steps': 33669, 'loss/train': 1.494260311126709} 08/30/2021 19:19:01 - INFO - __main__ - Step 33671: {'lr': 0.0004456043124189458, 'samples': 6464832, 'steps': 33670, 'loss/train': 2.1510260105133057} 08/30/2021 19:19:03 - INFO - __main__ - Step 33672: {'lr': 0.00044560100757561386, 'samples': 6465024, 'steps': 33671, 'loss/train': 1.2402567863464355} 08/30/2021 19:19:03 - INFO - __main__ - Step 33673: {'lr': 0.000445597702644147, 'samples': 6465216, 'steps': 33672, 'loss/train': 1.3177675008773804} 08/30/2021 19:19:03 - INFO - __main__ - Step 33674: {'lr': 0.000445594397624547, 'samples': 6465408, 'steps': 33673, 'loss/train': 1.3417434692382812} 08/30/2021 19:19:04 - INFO - __main__ - Step 33675: {'lr': 0.0004455910925168151, 'samples': 6465600, 'steps': 33674, 'loss/train': 0.6625871658325195} 08/30/2021 19:19:04 - INFO - __main__ - Step 33676: {'lr': 0.0004455877873209529, 'samples': 6465792, 'steps': 33675, 'loss/train': 1.4782607555389404} 08/30/2021 19:19:06 - INFO - __main__ - Step 33677: {'lr': 0.00044558448203696184, 'samples': 6465984, 'steps': 33676, 'loss/train': 1.2957102060317993} 08/30/2021 19:19:06 - INFO - __main__ - Step 33678: {'lr': 0.0004455811766648434, 'samples': 6466176, 'steps': 33677, 'loss/train': 1.493072748184204} 08/30/2021 19:19:06 - INFO - __main__ - Step 33679: {'lr': 0.0004455778712045992, 'samples': 6466368, 'steps': 33678, 'loss/train': 0.9289096593856812} 08/30/2021 19:19:07 - INFO - __main__ - Step 33680: {'lr': 0.0004455745656562306, 'samples': 6466560, 'steps': 33679, 'loss/train': 1.2810266017913818} 08/30/2021 19:19:07 - INFO - __main__ - Step 33681: {'lr': 0.000445571260019739, 'samples': 6466752, 'steps': 33680, 'loss/train': 1.046522855758667} 08/30/2021 19:19:09 - INFO - __main__ - Step 33682: {'lr': 0.00044556795429512617, 'samples': 6466944, 'steps': 33681, 'loss/train': 1.375369906425476} 08/30/2021 19:19:09 - INFO - __main__ - Step 33683: {'lr': 0.0004455646484823933, 'samples': 6467136, 'steps': 33682, 'loss/train': 1.3770354986190796} 08/30/2021 19:19:10 - INFO - __main__ - Step 33684: {'lr': 0.00044556134258154215, 'samples': 6467328, 'steps': 33683, 'loss/train': 1.6346420049667358} 08/30/2021 19:19:10 - INFO - __main__ - Step 33685: {'lr': 0.000445558036592574, 'samples': 6467520, 'steps': 33684, 'loss/train': 0.8800514340400696} 08/30/2021 19:19:10 - INFO - __main__ - Step 33686: {'lr': 0.0004455547305154904, 'samples': 6467712, 'steps': 33685, 'loss/train': 1.3120747804641724} 08/30/2021 19:19:13 - INFO - __main__ - Step 33687: {'lr': 0.00044555142435029284, 'samples': 6467904, 'steps': 33686, 'loss/train': 1.90951406955719} 08/30/2021 19:19:13 - INFO - __main__ - Step 33688: {'lr': 0.0004455481180969829, 'samples': 6468096, 'steps': 33687, 'loss/train': 1.4036403894424438} 08/30/2021 19:19:13 - INFO - __main__ - Step 33689: {'lr': 0.00044554481175556194, 'samples': 6468288, 'steps': 33688, 'loss/train': 1.8362884521484375} 08/30/2021 19:19:14 - INFO - __main__ - Step 33690: {'lr': 0.00044554150532603154, 'samples': 6468480, 'steps': 33689, 'loss/train': 1.3188564777374268} 08/30/2021 19:19:14 - INFO - __main__ - Step 33691: {'lr': 0.00044553819880839313, 'samples': 6468672, 'steps': 33690, 'loss/train': 0.12286171317100525} 08/30/2021 19:19:16 - INFO - __main__ - Step 33692: {'lr': 0.0004455348922026483, 'samples': 6468864, 'steps': 33691, 'loss/train': 1.4504883289337158} 08/30/2021 19:19:16 - INFO - __main__ - Step 33693: {'lr': 0.00044553158550879833, 'samples': 6469056, 'steps': 33692, 'loss/train': 0.966931939125061} 08/30/2021 19:19:17 - INFO - __main__ - Step 33694: {'lr': 0.00044552827872684493, 'samples': 6469248, 'steps': 33693, 'loss/train': 0.05195411294698715} 08/30/2021 19:19:17 - INFO - __main__ - Step 33695: {'lr': 0.00044552497185678953, 'samples': 6469440, 'steps': 33694, 'loss/train': 1.4305965900421143} 08/30/2021 19:19:17 - INFO - __main__ - Step 33696: {'lr': 0.00044552166489863354, 'samples': 6469632, 'steps': 33695, 'loss/train': 1.919219732284546} 08/30/2021 19:19:18 - INFO - __main__ - Step 33697: {'lr': 0.0004455183578523785, 'samples': 6469824, 'steps': 33696, 'loss/train': 0.6313751935958862} 08/30/2021 19:19:19 - INFO - __main__ - Step 33698: {'lr': 0.00044551505071802587, 'samples': 6470016, 'steps': 33697, 'loss/train': 1.5120868682861328} 08/30/2021 19:19:20 - INFO - __main__ - Step 33699: {'lr': 0.00044551174349557733, 'samples': 6470208, 'steps': 33698, 'loss/train': 1.5390487909317017} 08/30/2021 19:19:20 - INFO - __main__ - Step 33700: {'lr': 0.0004455084361850341, 'samples': 6470400, 'steps': 33699, 'loss/train': 1.6729403734207153} 08/30/2021 19:19:20 - INFO - __main__ - Step 33701: {'lr': 0.00044550512878639784, 'samples': 6470592, 'steps': 33700, 'loss/train': 2.4788177013397217} 08/30/2021 19:19:21 - INFO - __main__ - Step 33702: {'lr': 0.0004455018212996699, 'samples': 6470784, 'steps': 33701, 'loss/train': 1.4816921949386597} 08/30/2021 19:19:22 - INFO - __main__ - Step 33703: {'lr': 0.0004454985137248519, 'samples': 6470976, 'steps': 33702, 'loss/train': 1.4157847166061401} 08/30/2021 19:19:23 - INFO - __main__ - Step 33704: {'lr': 0.00044549520606194525, 'samples': 6471168, 'steps': 33703, 'loss/train': 1.1378756761550903} 08/30/2021 19:19:23 - INFO - __main__ - Step 33705: {'lr': 0.00044549189831095157, 'samples': 6471360, 'steps': 33704, 'loss/train': 1.4806702136993408} 08/30/2021 19:19:23 - INFO - __main__ - Step 33706: {'lr': 0.0004454885904718722, 'samples': 6471552, 'steps': 33705, 'loss/train': 0.7380875945091248} 08/30/2021 19:19:24 - INFO - __main__ - Step 33707: {'lr': 0.0004454852825447087, 'samples': 6471744, 'steps': 33706, 'loss/train': 1.4180727005004883} 08/30/2021 19:19:25 - INFO - __main__ - Step 33708: {'lr': 0.0004454819745294625, 'samples': 6471936, 'steps': 33707, 'loss/train': 0.8957964777946472} 08/30/2021 19:19:26 - INFO - __main__ - Step 33709: {'lr': 0.0004454786664261352, 'samples': 6472128, 'steps': 33708, 'loss/train': 1.1599117517471313} 08/30/2021 19:19:26 - INFO - __main__ - Step 33710: {'lr': 0.0004454753582347282, 'samples': 6472320, 'steps': 33709, 'loss/train': 1.262404203414917} 08/30/2021 19:19:26 - INFO - __main__ - Step 33711: {'lr': 0.00044547204995524305, 'samples': 6472512, 'steps': 33710, 'loss/train': 1.4879599809646606} 08/30/2021 19:19:27 - INFO - __main__ - Step 33712: {'lr': 0.00044546874158768115, 'samples': 6472704, 'steps': 33711, 'loss/train': 1.5151615142822266} 08/30/2021 19:19:28 - INFO - __main__ - Step 33713: {'lr': 0.00044546543313204415, 'samples': 6472896, 'steps': 33712, 'loss/train': 0.8803406953811646} 08/30/2021 19:19:29 - INFO - __main__ - Step 33714: {'lr': 0.00044546212458833334, 'samples': 6473088, 'steps': 33713, 'loss/train': 1.1372411251068115} 08/30/2021 19:19:29 - INFO - __main__ - Step 33715: {'lr': 0.00044545881595655035, 'samples': 6473280, 'steps': 33714, 'loss/train': 0.08176945894956589} 08/30/2021 19:19:29 - INFO - __main__ - Step 33716: {'lr': 0.00044545550723669664, 'samples': 6473472, 'steps': 33715, 'loss/train': 1.5716156959533691} 08/30/2021 19:19:30 - INFO - __main__ - Step 33717: {'lr': 0.00044545219842877373, 'samples': 6473664, 'steps': 33716, 'loss/train': 1.4744352102279663} 08/30/2021 19:19:31 - INFO - __main__ - Step 33718: {'lr': 0.000445448889532783, 'samples': 6473856, 'steps': 33717, 'loss/train': 1.3616046905517578} 08/30/2021 19:19:32 - INFO - __main__ - Step 33719: {'lr': 0.0004454455805487261, 'samples': 6474048, 'steps': 33718, 'loss/train': 1.614224910736084} 08/30/2021 19:19:32 - INFO - __main__ - Step 33720: {'lr': 0.0004454422714766043, 'samples': 6474240, 'steps': 33719, 'loss/train': 0.05675714835524559} 08/30/2021 19:19:32 - INFO - __main__ - Step 33721: {'lr': 0.00044543896231641935, 'samples': 6474432, 'steps': 33720, 'loss/train': 2.077928304672241} 08/30/2021 19:19:33 - INFO - __main__ - Step 33722: {'lr': 0.00044543565306817256, 'samples': 6474624, 'steps': 33721, 'loss/train': 1.4743558168411255} 08/30/2021 19:19:35 - INFO - __main__ - Step 33723: {'lr': 0.00044543234373186556, 'samples': 6474816, 'steps': 33722, 'loss/train': 1.5818597078323364} 08/30/2021 19:19:35 - INFO - __main__ - Step 33724: {'lr': 0.0004454290343074997, 'samples': 6475008, 'steps': 33723, 'loss/train': 1.5008740425109863} 08/30/2021 19:19:35 - INFO - __main__ - Step 33725: {'lr': 0.00044542572479507655, 'samples': 6475200, 'steps': 33724, 'loss/train': 1.813492774963379} 08/30/2021 19:19:36 - INFO - __main__ - Step 33726: {'lr': 0.00044542241519459757, 'samples': 6475392, 'steps': 33725, 'loss/train': 0.9517505764961243} 08/30/2021 19:19:36 - INFO - __main__ - Step 33727: {'lr': 0.0004454191055060643, 'samples': 6475584, 'steps': 33726, 'loss/train': 0.1324375718832016} 08/30/2021 19:19:36 - INFO - __main__ - Step 33728: {'lr': 0.00044541579572947814, 'samples': 6475776, 'steps': 33727, 'loss/train': 1.6306759119033813} 08/30/2021 19:19:38 - INFO - __main__ - Step 33729: {'lr': 0.0004454124858648407, 'samples': 6475968, 'steps': 33728, 'loss/train': 1.452009916305542} 08/30/2021 19:19:39 - INFO - __main__ - Step 33730: {'lr': 0.00044540917591215335, 'samples': 6476160, 'steps': 33729, 'loss/train': 1.190197229385376} 08/30/2021 19:19:39 - INFO - __main__ - Step 33731: {'lr': 0.0004454058658714177, 'samples': 6476352, 'steps': 33730, 'loss/train': 0.9651709198951721} 08/30/2021 19:19:40 - INFO - __main__ - Step 33732: {'lr': 0.0004454025557426351, 'samples': 6476544, 'steps': 33731, 'loss/train': 1.937745451927185} 08/30/2021 19:19:40 - INFO - __main__ - Step 33733: {'lr': 0.00044539924552580723, 'samples': 6476736, 'steps': 33732, 'loss/train': 0.1663772165775299} 08/30/2021 19:19:40 - INFO - __main__ - Step 33734: {'lr': 0.0004453959352209354, 'samples': 6476928, 'steps': 33733, 'loss/train': 0.07754461467266083} 08/30/2021 19:19:42 - INFO - __main__ - Step 33735: {'lr': 0.0004453926248280212, 'samples': 6477120, 'steps': 33734, 'loss/train': 0.19635151326656342} 08/30/2021 19:19:42 - INFO - __main__ - Step 33736: {'lr': 0.0004453893143470661, 'samples': 6477312, 'steps': 33735, 'loss/train': 1.0328118801116943} 08/30/2021 19:19:43 - INFO - __main__ - Step 33737: {'lr': 0.0004453860037780716, 'samples': 6477504, 'steps': 33736, 'loss/train': 1.5382918119430542} 08/30/2021 19:19:43 - INFO - __main__ - Step 33738: {'lr': 0.00044538269312103916, 'samples': 6477696, 'steps': 33737, 'loss/train': 1.445682406425476} 08/30/2021 19:19:43 - INFO - __main__ - Step 33739: {'lr': 0.00044537938237597033, 'samples': 6477888, 'steps': 33738, 'loss/train': 2.663958787918091} 08/30/2021 19:19:45 - INFO - __main__ - Step 33740: {'lr': 0.00044537607154286645, 'samples': 6478080, 'steps': 33739, 'loss/train': 1.6115236282348633} 08/30/2021 19:19:46 - INFO - __main__ - Step 33741: {'lr': 0.00044537276062172926, 'samples': 6478272, 'steps': 33740, 'loss/train': 1.5073665380477905} 08/30/2021 19:19:46 - INFO - __main__ - Step 33742: {'lr': 0.0004453694496125601, 'samples': 6478464, 'steps': 33741, 'loss/train': 1.6848793029785156} 08/30/2021 19:19:47 - INFO - __main__ - Step 33743: {'lr': 0.0004453661385153604, 'samples': 6478656, 'steps': 33742, 'loss/train': 1.5976946353912354} 08/30/2021 19:19:47 - INFO - __main__ - Step 33744: {'lr': 0.0004453628273301318, 'samples': 6478848, 'steps': 33743, 'loss/train': 1.7621325254440308} 08/30/2021 19:19:49 - INFO - __main__ - Step 33745: {'lr': 0.0004453595160568757, 'samples': 6479040, 'steps': 33744, 'loss/train': 1.7771892547607422} 08/30/2021 19:19:49 - INFO - __main__ - Step 33746: {'lr': 0.0004453562046955937, 'samples': 6479232, 'steps': 33745, 'loss/train': 1.5560173988342285} 08/30/2021 19:19:50 - INFO - __main__ - Step 33747: {'lr': 0.00044535289324628704, 'samples': 6479424, 'steps': 33746, 'loss/train': 1.5462055206298828} 08/30/2021 19:19:50 - INFO - __main__ - Step 33748: {'lr': 0.00044534958170895753, 'samples': 6479616, 'steps': 33747, 'loss/train': 1.2782315015792847} 08/30/2021 19:19:50 - INFO - __main__ - Step 33749: {'lr': 0.0004453462700836064, 'samples': 6479808, 'steps': 33748, 'loss/train': 1.7661064863204956} 08/30/2021 19:19:51 - INFO - __main__ - Step 33750: {'lr': 0.0004453429583702353, 'samples': 6480000, 'steps': 33749, 'loss/train': 1.7305666208267212} 08/30/2021 19:19:52 - INFO - __main__ - Step 33751: {'lr': 0.0004453396465688457, 'samples': 6480192, 'steps': 33750, 'loss/train': 1.7367297410964966} 08/30/2021 19:19:53 - INFO - __main__ - Step 33752: {'lr': 0.00044533633467943906, 'samples': 6480384, 'steps': 33751, 'loss/train': 1.937293291091919} 08/30/2021 19:19:53 - INFO - __main__ - Step 33753: {'lr': 0.00044533302270201693, 'samples': 6480576, 'steps': 33752, 'loss/train': 1.6584053039550781} 08/30/2021 19:19:53 - INFO - __main__ - Step 33754: {'lr': 0.00044532971063658067, 'samples': 6480768, 'steps': 33753, 'loss/train': 1.6454256772994995} 08/30/2021 19:19:54 - INFO - __main__ - Step 33755: {'lr': 0.00044532639848313187, 'samples': 6480960, 'steps': 33754, 'loss/train': 2.291076898574829} 08/30/2021 19:19:55 - INFO - __main__ - Step 33756: {'lr': 0.0004453230862416721, 'samples': 6481152, 'steps': 33755, 'loss/train': 1.3033268451690674} 08/30/2021 19:19:56 - INFO - __main__ - Step 33757: {'lr': 0.00044531977391220267, 'samples': 6481344, 'steps': 33756, 'loss/train': 1.6153513193130493} 08/30/2021 19:19:56 - INFO - __main__ - Step 33758: {'lr': 0.00044531646149472516, 'samples': 6481536, 'steps': 33757, 'loss/train': 1.5686980485916138} 08/30/2021 19:19:56 - INFO - __main__ - Step 33759: {'lr': 0.00044531314898924116, 'samples': 6481728, 'steps': 33758, 'loss/train': 1.573486089706421} 08/30/2021 19:19:57 - INFO - __main__ - Step 33760: {'lr': 0.00044530983639575193, 'samples': 6481920, 'steps': 33759, 'loss/train': 1.5041369199752808} 08/30/2021 19:19:57 - INFO - __main__ - Step 33761: {'lr': 0.00044530652371425916, 'samples': 6482112, 'steps': 33760, 'loss/train': 1.0164790153503418} 08/30/2021 19:19:58 - INFO - __main__ - Step 33762: {'lr': 0.00044530321094476434, 'samples': 6482304, 'steps': 33761, 'loss/train': 1.2703678607940674} 08/30/2021 19:19:59 - INFO - __main__ - Step 33763: {'lr': 0.0004452998980872689, 'samples': 6482496, 'steps': 33762, 'loss/train': 1.3127743005752563} 08/30/2021 19:19:59 - INFO - __main__ - Step 33764: {'lr': 0.0004452965851417743, 'samples': 6482688, 'steps': 33763, 'loss/train': 1.2908152341842651} 08/30/2021 19:20:00 - INFO - __main__ - Step 33765: {'lr': 0.000445293272108282, 'samples': 6482880, 'steps': 33764, 'loss/train': 1.3670977354049683} 08/30/2021 19:20:00 - INFO - __main__ - Step 33766: {'lr': 0.0004452899589867937, 'samples': 6483072, 'steps': 33765, 'loss/train': 0.9376664757728577} 08/30/2021 19:20:01 - INFO - __main__ - Step 33767: {'lr': 0.00044528664577731073, 'samples': 6483264, 'steps': 33766, 'loss/train': 1.3679068088531494} 08/30/2021 19:20:02 - INFO - __main__ - Step 33768: {'lr': 0.00044528333247983456, 'samples': 6483456, 'steps': 33767, 'loss/train': 1.1519654989242554} 08/30/2021 19:20:02 - INFO - __main__ - Step 33769: {'lr': 0.0004452800190943667, 'samples': 6483648, 'steps': 33768, 'loss/train': 1.5699752569198608} 08/30/2021 19:20:03 - INFO - __main__ - Step 33770: {'lr': 0.0004452767056209087, 'samples': 6483840, 'steps': 33769, 'loss/train': 1.7179687023162842} 08/30/2021 19:20:03 - INFO - __main__ - Step 33771: {'lr': 0.0004452733920594621, 'samples': 6484032, 'steps': 33770, 'loss/train': 1.6127049922943115} 08/30/2021 19:20:04 - INFO - __main__ - Step 33772: {'lr': 0.0004452700784100283, 'samples': 6484224, 'steps': 33771, 'loss/train': 1.8528072834014893} 08/30/2021 19:20:05 - INFO - __main__ - Step 33773: {'lr': 0.0004452667646726088, 'samples': 6484416, 'steps': 33772, 'loss/train': 1.8164608478546143} 08/30/2021 19:20:05 - INFO - __main__ - Step 33774: {'lr': 0.0004452634508472051, 'samples': 6484608, 'steps': 33773, 'loss/train': 1.3129944801330566} 08/30/2021 19:20:05 - INFO - __main__ - Step 33775: {'lr': 0.0004452601369338187, 'samples': 6484800, 'steps': 33774, 'loss/train': 1.7763618230819702} 08/30/2021 19:20:06 - INFO - __main__ - Step 33776: {'lr': 0.00044525682293245107, 'samples': 6484992, 'steps': 33775, 'loss/train': 1.6041359901428223} 08/30/2021 19:20:08 - INFO - __main__ - Step 33777: {'lr': 0.0004452535088431038, 'samples': 6485184, 'steps': 33776, 'loss/train': 1.4973009824752808} 08/30/2021 19:20:08 - INFO - __main__ - Step 33778: {'lr': 0.00044525019466577824, 'samples': 6485376, 'steps': 33777, 'loss/train': 1.0766139030456543} 08/30/2021 19:20:08 - INFO - __main__ - Step 33779: {'lr': 0.000445246880400476, 'samples': 6485568, 'steps': 33778, 'loss/train': 0.960921585559845} 08/30/2021 19:20:09 - INFO - __main__ - Step 33780: {'lr': 0.0004452435660471985, 'samples': 6485760, 'steps': 33779, 'loss/train': 1.4789167642593384} 08/30/2021 19:20:09 - INFO - __main__ - Step 33781: {'lr': 0.00044524025160594735, 'samples': 6485952, 'steps': 33780, 'loss/train': 1.0589964389801025} 08/30/2021 19:20:09 - INFO - __main__ - Step 33782: {'lr': 0.00044523693707672384, 'samples': 6486144, 'steps': 33781, 'loss/train': 0.41785523295402527} 08/30/2021 19:20:11 - INFO - __main__ - Step 33783: {'lr': 0.0004452336224595296, 'samples': 6486336, 'steps': 33782, 'loss/train': 0.31878143548965454} 08/30/2021 19:20:11 - INFO - __main__ - Step 33784: {'lr': 0.00044523030775436617, 'samples': 6486528, 'steps': 33783, 'loss/train': 1.0572500228881836} 08/30/2021 19:20:12 - INFO - __main__ - Step 33785: {'lr': 0.00044522699296123495, 'samples': 6486720, 'steps': 33784, 'loss/train': 1.9437154531478882} 08/30/2021 19:20:12 - INFO - __main__ - Step 33786: {'lr': 0.0004452236780801374, 'samples': 6486912, 'steps': 33785, 'loss/train': 0.8700249195098877} 08/30/2021 19:20:12 - INFO - __main__ - Step 33787: {'lr': 0.00044522036311107514, 'samples': 6487104, 'steps': 33786, 'loss/train': 1.5943043231964111} 08/30/2021 19:20:14 - INFO - __main__ - Step 33788: {'lr': 0.0004452170480540496, 'samples': 6487296, 'steps': 33787, 'loss/train': 1.2318328619003296} 08/30/2021 19:20:14 - INFO - __main__ - Step 33789: {'lr': 0.0004452137329090622, 'samples': 6487488, 'steps': 33788, 'loss/train': 1.3939425945281982} 08/30/2021 19:20:15 - INFO - __main__ - Step 33790: {'lr': 0.0004452104176761146, 'samples': 6487680, 'steps': 33789, 'loss/train': 0.7296445965766907} 08/30/2021 19:20:15 - INFO - __main__ - Step 33791: {'lr': 0.0004452071023552081, 'samples': 6487872, 'steps': 33790, 'loss/train': 1.9287878274917603} 08/30/2021 19:20:15 - INFO - __main__ - Step 33792: {'lr': 0.0004452037869463443, 'samples': 6488064, 'steps': 33791, 'loss/train': 1.9356757402420044} 08/30/2021 19:20:17 - INFO - __main__ - Step 33793: {'lr': 0.0004452004714495248, 'samples': 6488256, 'steps': 33792, 'loss/train': 1.3879512548446655} 08/30/2021 19:20:18 - INFO - __main__ - Step 33794: {'lr': 0.00044519715586475083, 'samples': 6488448, 'steps': 33793, 'loss/train': 1.3470523357391357} 08/30/2021 19:20:18 - INFO - __main__ - Step 33795: {'lr': 0.0004451938401920241, 'samples': 6488640, 'steps': 33794, 'loss/train': 1.2987070083618164} 08/30/2021 19:20:19 - INFO - __main__ - Step 33796: {'lr': 0.0004451905244313461, 'samples': 6488832, 'steps': 33795, 'loss/train': 1.2954049110412598} 08/30/2021 19:20:19 - INFO - __main__ - Step 33797: {'lr': 0.0004451872085827182, 'samples': 6489024, 'steps': 33796, 'loss/train': 1.325581669807434} 08/30/2021 19:20:21 - INFO - __main__ - Step 33798: {'lr': 0.000445183892646142, 'samples': 6489216, 'steps': 33797, 'loss/train': 1.8152703046798706} 08/30/2021 19:20:21 - INFO - __main__ - Step 33799: {'lr': 0.0004451805766216189, 'samples': 6489408, 'steps': 33798, 'loss/train': 1.5288186073303223} 08/30/2021 19:20:21 - INFO - __main__ - Step 33800: {'lr': 0.00044517726050915044, 'samples': 6489600, 'steps': 33799, 'loss/train': 0.8148971199989319} 08/30/2021 19:20:22 - INFO - __main__ - Step 33801: {'lr': 0.0004451739443087381, 'samples': 6489792, 'steps': 33800, 'loss/train': 1.640548825263977} 08/30/2021 19:20:22 - INFO - __main__ - Step 33802: {'lr': 0.0004451706280203834, 'samples': 6489984, 'steps': 33801, 'loss/train': 0.9394887685775757} 08/30/2021 19:20:22 - INFO - __main__ - Step 33803: {'lr': 0.0004451673116440879, 'samples': 6490176, 'steps': 33802, 'loss/train': 1.5112522840499878} 08/30/2021 19:20:24 - INFO - __main__ - Step 33804: {'lr': 0.00044516399517985296, 'samples': 6490368, 'steps': 33803, 'loss/train': 0.540610134601593} 08/30/2021 19:20:25 - INFO - __main__ - Step 33805: {'lr': 0.00044516067862768015, 'samples': 6490560, 'steps': 33804, 'loss/train': 1.5167460441589355} 08/30/2021 19:20:25 - INFO - __main__ - Step 33806: {'lr': 0.00044515736198757095, 'samples': 6490752, 'steps': 33805, 'loss/train': 1.2457060813903809} 08/30/2021 19:20:25 - INFO - __main__ - Step 33807: {'lr': 0.0004451540452595268, 'samples': 6490944, 'steps': 33806, 'loss/train': 1.23661470413208} 08/30/2021 19:20:26 - INFO - __main__ - Step 33808: {'lr': 0.0004451507284435494, 'samples': 6491136, 'steps': 33807, 'loss/train': 2.0407135486602783} 08/30/2021 19:20:27 - INFO - __main__ - Step 33809: {'lr': 0.00044514741153964, 'samples': 6491328, 'steps': 33808, 'loss/train': 1.6382018327713013} 08/30/2021 19:20:28 - INFO - __main__ - Step 33810: {'lr': 0.00044514409454780016, 'samples': 6491520, 'steps': 33809, 'loss/train': 1.1615650653839111} 08/30/2021 19:20:28 - INFO - __main__ - Step 33811: {'lr': 0.0004451407774680314, 'samples': 6491712, 'steps': 33810, 'loss/train': 1.409875750541687} 08/30/2021 19:20:28 - INFO - __main__ - Step 33812: {'lr': 0.0004451374603003353, 'samples': 6491904, 'steps': 33811, 'loss/train': 1.489293098449707} 08/30/2021 19:20:29 - INFO - __main__ - Step 33813: {'lr': 0.0004451341430447132, 'samples': 6492096, 'steps': 33812, 'loss/train': 1.573107123374939} 08/30/2021 19:20:30 - INFO - __main__ - Step 33814: {'lr': 0.0004451308257011667, 'samples': 6492288, 'steps': 33813, 'loss/train': 2.4382524490356445} 08/30/2021 19:20:31 - INFO - __main__ - Step 33815: {'lr': 0.00044512750826969724, 'samples': 6492480, 'steps': 33814, 'loss/train': 1.6215991973876953} 08/30/2021 19:20:31 - INFO - __main__ - Step 33816: {'lr': 0.0004451241907503063, 'samples': 6492672, 'steps': 33815, 'loss/train': 0.7824227213859558} 08/30/2021 19:20:31 - INFO - __main__ - Step 33817: {'lr': 0.0004451208731429954, 'samples': 6492864, 'steps': 33816, 'loss/train': 2.214453935623169} 08/30/2021 19:20:32 - INFO - __main__ - Step 33818: {'lr': 0.00044511755544776615, 'samples': 6493056, 'steps': 33817, 'loss/train': 1.2359373569488525} 08/30/2021 19:20:33 - INFO - __main__ - Step 33819: {'lr': 0.0004451142376646199, 'samples': 6493248, 'steps': 33818, 'loss/train': 1.2238761186599731} 08/30/2021 19:20:34 - INFO - __main__ - Step 33820: {'lr': 0.0004451109197935582, 'samples': 6493440, 'steps': 33819, 'loss/train': 1.313556432723999} 08/30/2021 19:20:34 - INFO - __main__ - Step 33821: {'lr': 0.0004451076018345824, 'samples': 6493632, 'steps': 33820, 'loss/train': 1.0907546281814575} 08/30/2021 19:20:34 - INFO - __main__ - Step 33822: {'lr': 0.0004451042837876943, 'samples': 6493824, 'steps': 33821, 'loss/train': 0.6498135924339294} 08/30/2021 19:20:35 - INFO - __main__ - Step 33823: {'lr': 0.00044510096565289513, 'samples': 6494016, 'steps': 33822, 'loss/train': 1.1190437078475952} 08/30/2021 19:20:35 - INFO - __main__ - Step 33824: {'lr': 0.0004450976474301865, 'samples': 6494208, 'steps': 33823, 'loss/train': 1.8094733953475952} 08/30/2021 19:20:37 - INFO - __main__ - Step 33825: {'lr': 0.0004450943291195698, 'samples': 6494400, 'steps': 33824, 'loss/train': 1.167904019355774} 08/30/2021 19:20:37 - INFO - __main__ - Step 33826: {'lr': 0.0004450910107210467, 'samples': 6494592, 'steps': 33825, 'loss/train': 1.4186716079711914} 08/30/2021 19:20:37 - INFO - __main__ - Step 33827: {'lr': 0.00044508769223461863, 'samples': 6494784, 'steps': 33826, 'loss/train': 1.2514773607254028} 08/30/2021 19:20:38 - INFO - __main__ - Step 33828: {'lr': 0.00044508437366028695, 'samples': 6494976, 'steps': 33827, 'loss/train': 1.443077564239502} 08/30/2021 19:20:38 - INFO - __main__ - Step 33829: {'lr': 0.00044508105499805337, 'samples': 6495168, 'steps': 33828, 'loss/train': 1.3630058765411377} 08/30/2021 19:20:40 - INFO - __main__ - Step 33830: {'lr': 0.0004450777362479192, 'samples': 6495360, 'steps': 33829, 'loss/train': 1.7333565950393677} 08/30/2021 19:20:41 - INFO - __main__ - Step 33831: {'lr': 0.000445074417409886, 'samples': 6495552, 'steps': 33830, 'loss/train': 0.054648514837026596} 08/30/2021 19:20:41 - INFO - __main__ - Step 33832: {'lr': 0.0004450710984839553, 'samples': 6495744, 'steps': 33831, 'loss/train': 0.23711515963077545} 08/30/2021 19:20:41 - INFO - __main__ - Step 33833: {'lr': 0.00044506777947012863, 'samples': 6495936, 'steps': 33832, 'loss/train': 1.3185186386108398} 08/30/2021 19:20:42 - INFO - __main__ - Step 33834: {'lr': 0.0004450644603684074, 'samples': 6496128, 'steps': 33833, 'loss/train': 1.3689053058624268} 08/30/2021 19:20:42 - INFO - __main__ - Step 33835: {'lr': 0.0004450611411787931, 'samples': 6496320, 'steps': 33834, 'loss/train': 0.941810131072998} 08/30/2021 19:20:43 - INFO - __main__ - Step 33836: {'lr': 0.0004450578219012873, 'samples': 6496512, 'steps': 33835, 'loss/train': 1.574400782585144} 08/30/2021 19:20:44 - INFO - __main__ - Step 33837: {'lr': 0.00044505450253589144, 'samples': 6496704, 'steps': 33836, 'loss/train': 1.5366309881210327} 08/30/2021 19:20:44 - INFO - __main__ - Step 33838: {'lr': 0.00044505118308260693, 'samples': 6496896, 'steps': 33837, 'loss/train': 1.4238420724868774} 08/30/2021 19:20:44 - INFO - __main__ - Step 33839: {'lr': 0.0004450478635414355, 'samples': 6497088, 'steps': 33838, 'loss/train': 1.624822974205017} 08/30/2021 19:20:45 - INFO - __main__ - Step 33840: {'lr': 0.0004450445439123785, 'samples': 6497280, 'steps': 33839, 'loss/train': 1.6758664846420288} 08/30/2021 19:20:47 - INFO - __main__ - Step 33841: {'lr': 0.0004450412241954374, 'samples': 6497472, 'steps': 33840, 'loss/train': 1.5433599948883057} 08/30/2021 19:20:47 - INFO - __main__ - Step 33842: {'lr': 0.00044503790439061374, 'samples': 6497664, 'steps': 33841, 'loss/train': 1.4497911930084229} 08/30/2021 19:20:48 - INFO - __main__ - Step 33843: {'lr': 0.000445034584497909, 'samples': 6497856, 'steps': 33842, 'loss/train': 1.3877265453338623} 08/30/2021 19:20:48 - INFO - __main__ - Step 33844: {'lr': 0.00044503126451732474, 'samples': 6498048, 'steps': 33843, 'loss/train': 1.2756401300430298} 08/30/2021 19:20:48 - INFO - __main__ - Step 33845: {'lr': 0.00044502794444886234, 'samples': 6498240, 'steps': 33844, 'loss/train': 1.6663813591003418} 08/30/2021 19:20:50 - INFO - __main__ - Step 33846: {'lr': 0.00044502462429252336, 'samples': 6498432, 'steps': 33845, 'loss/train': 1.2357209920883179} 08/30/2021 19:20:50 - INFO - __main__ - Step 33847: {'lr': 0.0004450213040483093, 'samples': 6498624, 'steps': 33846, 'loss/train': 1.3075966835021973} 08/30/2021 19:20:51 - INFO - __main__ - Step 33848: {'lr': 0.00044501798371622173, 'samples': 6498816, 'steps': 33847, 'loss/train': 1.6986846923828125} 08/30/2021 19:20:51 - INFO - __main__ - Step 33849: {'lr': 0.00044501466329626197, 'samples': 6499008, 'steps': 33848, 'loss/train': 0.8778390288352966} 08/30/2021 19:20:52 - INFO - __main__ - Step 33850: {'lr': 0.0004450113427884317, 'samples': 6499200, 'steps': 33849, 'loss/train': 1.942723274230957} 08/30/2021 19:20:53 - INFO - __main__ - Step 33851: {'lr': 0.00044500802219273224, 'samples': 6499392, 'steps': 33850, 'loss/train': 1.6642335653305054} 08/30/2021 19:20:53 - INFO - __main__ - Step 33852: {'lr': 0.00044500470150916514, 'samples': 6499584, 'steps': 33851, 'loss/train': 1.373314380645752} 08/30/2021 19:20:54 - INFO - __main__ - Step 33853: {'lr': 0.000445001380737732, 'samples': 6499776, 'steps': 33852, 'loss/train': 1.4638320207595825} 08/30/2021 19:20:54 - INFO - __main__ - Step 33854: {'lr': 0.0004449980598784343, 'samples': 6499968, 'steps': 33853, 'loss/train': 1.5324115753173828} 08/30/2021 19:20:54 - INFO - __main__ - Step 33855: {'lr': 0.0004449947389312734, 'samples': 6500160, 'steps': 33854, 'loss/train': 1.6708019971847534} 08/30/2021 19:20:56 - INFO - __main__ - Step 33856: {'lr': 0.00044499141789625086, 'samples': 6500352, 'steps': 33855, 'loss/train': 1.95577073097229} 08/30/2021 19:20:56 - INFO - __main__ - Step 33857: {'lr': 0.0004449880967733683, 'samples': 6500544, 'steps': 33856, 'loss/train': 1.1643824577331543} 08/30/2021 19:20:57 - INFO - __main__ - Step 33858: {'lr': 0.0004449847755626271, 'samples': 6500736, 'steps': 33857, 'loss/train': 1.5369292497634888} 08/30/2021 19:20:57 - INFO - __main__ - Step 33859: {'lr': 0.0004449814542640287, 'samples': 6500928, 'steps': 33858, 'loss/train': 1.41264009475708} 08/30/2021 19:20:57 - INFO - __main__ - Step 33860: {'lr': 0.0004449781328775746, 'samples': 6501120, 'steps': 33859, 'loss/train': 1.3092153072357178} 08/30/2021 19:20:58 - INFO - __main__ - Step 33861: {'lr': 0.0004449748114032665, 'samples': 6501312, 'steps': 33860, 'loss/train': 0.6003842949867249} 08/30/2021 19:20:59 - INFO - __main__ - Step 33862: {'lr': 0.00044497148984110567, 'samples': 6501504, 'steps': 33861, 'loss/train': 1.4862371683120728} 08/30/2021 19:21:00 - INFO - __main__ - Step 33863: {'lr': 0.00044496816819109377, 'samples': 6501696, 'steps': 33862, 'loss/train': 1.1522754430770874} 08/30/2021 19:21:00 - INFO - __main__ - Step 33864: {'lr': 0.0004449648464532322, 'samples': 6501888, 'steps': 33863, 'loss/train': 1.1018861532211304} 08/30/2021 19:21:00 - INFO - __main__ - Step 33865: {'lr': 0.0004449615246275225, 'samples': 6502080, 'steps': 33864, 'loss/train': 1.5629613399505615} 08/30/2021 19:21:01 - INFO - __main__ - Step 33866: {'lr': 0.000444958202713966, 'samples': 6502272, 'steps': 33865, 'loss/train': 1.4350067377090454} 08/30/2021 19:21:02 - INFO - __main__ - Step 33867: {'lr': 0.0004449548807125645, 'samples': 6502464, 'steps': 33866, 'loss/train': 0.46062156558036804} 08/30/2021 19:21:03 - INFO - __main__ - Step 33868: {'lr': 0.0004449515586233193, 'samples': 6502656, 'steps': 33867, 'loss/train': 1.584196925163269} 08/30/2021 19:21:03 - INFO - __main__ - Step 33869: {'lr': 0.0004449482364462319, 'samples': 6502848, 'steps': 33868, 'loss/train': 1.4910050630569458} 08/30/2021 19:21:04 - INFO - __main__ - Step 33870: {'lr': 0.0004449449141813039, 'samples': 6503040, 'steps': 33869, 'loss/train': 1.3369876146316528} 08/30/2021 19:21:04 - INFO - __main__ - Step 33871: {'lr': 0.00044494159182853667, 'samples': 6503232, 'steps': 33870, 'loss/train': 1.728448748588562} 08/30/2021 19:21:06 - INFO - __main__ - Step 33872: {'lr': 0.0004449382693879318, 'samples': 6503424, 'steps': 33871, 'loss/train': 1.382724404335022} 08/30/2021 19:21:06 - INFO - __main__ - Step 33873: {'lr': 0.0004449349468594908, 'samples': 6503616, 'steps': 33872, 'loss/train': 0.988279402256012} 08/30/2021 19:21:06 - INFO - __main__ - Step 33874: {'lr': 0.000444931624243215, 'samples': 6503808, 'steps': 33873, 'loss/train': 1.8086014986038208} 08/30/2021 19:21:07 - INFO - __main__ - Step 33875: {'lr': 0.0004449283015391061, 'samples': 6504000, 'steps': 33874, 'loss/train': 1.2181453704833984} 08/30/2021 19:21:07 - INFO - __main__ - Step 33876: {'lr': 0.0004449249787471655, 'samples': 6504192, 'steps': 33875, 'loss/train': 1.516812801361084} 08/30/2021 19:21:09 - INFO - __main__ - Step 33877: {'lr': 0.0004449216558673947, 'samples': 6504384, 'steps': 33876, 'loss/train': 1.0998013019561768} 08/30/2021 19:21:09 - INFO - __main__ - Step 33878: {'lr': 0.0004449183328997952, 'samples': 6504576, 'steps': 33877, 'loss/train': 0.8791530728340149} 08/30/2021 19:21:09 - INFO - __main__ - Step 33879: {'lr': 0.0004449150098443685, 'samples': 6504768, 'steps': 33878, 'loss/train': 2.1546788215637207} 08/30/2021 19:21:10 - INFO - __main__ - Step 33880: {'lr': 0.00044491168670111615, 'samples': 6504960, 'steps': 33879, 'loss/train': 0.9371464252471924} 08/30/2021 19:21:10 - INFO - __main__ - Step 33881: {'lr': 0.0004449083634700396, 'samples': 6505152, 'steps': 33880, 'loss/train': 1.1692291498184204} 08/30/2021 19:21:10 - INFO - __main__ - Step 33882: {'lr': 0.00044490504015114033, 'samples': 6505344, 'steps': 33881, 'loss/train': 1.299615502357483} 08/30/2021 19:21:12 - INFO - __main__ - Step 33883: {'lr': 0.0004449017167444198, 'samples': 6505536, 'steps': 33882, 'loss/train': 0.9115594625473022} 08/30/2021 19:21:12 - INFO - __main__ - Step 33884: {'lr': 0.0004448983932498797, 'samples': 6505728, 'steps': 33883, 'loss/train': 1.4423195123672485} 08/30/2021 19:21:13 - INFO - __main__ - Step 33885: {'lr': 0.00044489506966752127, 'samples': 6505920, 'steps': 33884, 'loss/train': 1.28299880027771} 08/30/2021 19:21:13 - INFO - __main__ - Step 33886: {'lr': 0.00044489174599734614, 'samples': 6506112, 'steps': 33885, 'loss/train': 1.0047564506530762} 08/30/2021 19:21:13 - INFO - __main__ - Step 33887: {'lr': 0.0004448884222393559, 'samples': 6506304, 'steps': 33886, 'loss/train': 1.4295834302902222} 08/30/2021 19:21:15 - INFO - __main__ - Step 33888: {'lr': 0.00044488509839355183, 'samples': 6506496, 'steps': 33887, 'loss/train': 1.3253395557403564} 08/30/2021 19:21:15 - INFO - __main__ - Step 33889: {'lr': 0.00044488177445993563, 'samples': 6506688, 'steps': 33888, 'loss/train': 0.05622369050979614} 08/30/2021 19:21:16 - INFO - __main__ - Step 33890: {'lr': 0.0004448784504385086, 'samples': 6506880, 'steps': 33889, 'loss/train': 1.813767433166504} 08/30/2021 19:21:16 - INFO - __main__ - Step 33891: {'lr': 0.0004448751263292724, 'samples': 6507072, 'steps': 33890, 'loss/train': 1.5589590072631836} 08/30/2021 19:21:17 - INFO - __main__ - Step 33892: {'lr': 0.0004448718021322285, 'samples': 6507264, 'steps': 33891, 'loss/train': 1.0483603477478027} 08/30/2021 19:21:19 - INFO - __main__ - Step 33893: {'lr': 0.0004448684778473784, 'samples': 6507456, 'steps': 33892, 'loss/train': 1.525713324546814} 08/30/2021 19:21:19 - INFO - __main__ - Step 33894: {'lr': 0.0004448651534747235, 'samples': 6507648, 'steps': 33893, 'loss/train': 0.850823700428009} 08/30/2021 19:21:20 - INFO - __main__ - Step 33895: {'lr': 0.0004448618290142654, 'samples': 6507840, 'steps': 33894, 'loss/train': 0.07434050738811493} 08/30/2021 19:21:20 - INFO - __main__ - Step 33896: {'lr': 0.0004448585044660055, 'samples': 6508032, 'steps': 33895, 'loss/train': 1.6688246726989746} 08/30/2021 19:21:20 - INFO - __main__ - Step 33897: {'lr': 0.0004448551798299455, 'samples': 6508224, 'steps': 33896, 'loss/train': 1.5972011089324951} 08/30/2021 19:21:22 - INFO - __main__ - Step 33898: {'lr': 0.00044485185510608665, 'samples': 6508416, 'steps': 33897, 'loss/train': 2.083176851272583} 08/30/2021 19:21:22 - INFO - __main__ - Step 33899: {'lr': 0.0004448485302944306, 'samples': 6508608, 'steps': 33898, 'loss/train': 1.6384687423706055} 08/30/2021 19:21:22 - INFO - __main__ - Step 33900: {'lr': 0.0004448452053949789, 'samples': 6508800, 'steps': 33899, 'loss/train': 1.5330208539962769} 08/30/2021 19:21:23 - INFO - __main__ - Step 33901: {'lr': 0.0004448418804077328, 'samples': 6508992, 'steps': 33900, 'loss/train': 1.2696808576583862} 08/30/2021 19:21:23 - INFO - __main__ - Step 33902: {'lr': 0.000444838555332694, 'samples': 6509184, 'steps': 33901, 'loss/train': 0.5143625140190125} 08/30/2021 19:21:25 - INFO - __main__ - Step 33903: {'lr': 0.000444835230169864, 'samples': 6509376, 'steps': 33902, 'loss/train': 1.4817063808441162} 08/30/2021 19:21:26 - INFO - __main__ - Step 33904: {'lr': 0.00044483190491924427, 'samples': 6509568, 'steps': 33903, 'loss/train': 1.420440673828125} 08/30/2021 19:21:26 - INFO - __main__ - Step 33905: {'lr': 0.0004448285795808362, 'samples': 6509760, 'steps': 33904, 'loss/train': 0.03294937685132027} 08/30/2021 19:21:26 - INFO - __main__ - Step 33906: {'lr': 0.00044482525415464144, 'samples': 6509952, 'steps': 33905, 'loss/train': 1.353139877319336} 08/30/2021 19:21:27 - INFO - __main__ - Step 33907: {'lr': 0.0004448219286406614, 'samples': 6510144, 'steps': 33906, 'loss/train': 1.360242247581482} 08/30/2021 19:21:27 - INFO - __main__ - Step 33908: {'lr': 0.00044481860303889766, 'samples': 6510336, 'steps': 33907, 'loss/train': 1.3502663373947144} 08/30/2021 19:21:27 - INFO - __main__ - Step 33909: {'lr': 0.0004448152773493516, 'samples': 6510528, 'steps': 33908, 'loss/train': 1.4947407245635986} 08/30/2021 19:21:29 - INFO - __main__ - Step 33910: {'lr': 0.0004448119515720248, 'samples': 6510720, 'steps': 33909, 'loss/train': 0.18104121088981628} 08/30/2021 19:21:29 - INFO - __main__ - Step 33911: {'lr': 0.0004448086257069187, 'samples': 6510912, 'steps': 33910, 'loss/train': 1.7081741094589233} 08/30/2021 19:21:30 - INFO - __main__ - Step 33912: {'lr': 0.00044480529975403496, 'samples': 6511104, 'steps': 33911, 'loss/train': 0.7345178127288818} 08/30/2021 19:21:30 - INFO - __main__ - Step 33913: {'lr': 0.00044480197371337484, 'samples': 6511296, 'steps': 33912, 'loss/train': 1.319288730621338} 08/30/2021 19:21:30 - INFO - __main__ - Step 33914: {'lr': 0.00044479864758494004, 'samples': 6511488, 'steps': 33913, 'loss/train': 1.6771048307418823} 08/30/2021 19:21:32 - INFO - __main__ - Step 33915: {'lr': 0.0004447953213687319, 'samples': 6511680, 'steps': 33914, 'loss/train': 1.0491857528686523} 08/30/2021 19:21:33 - INFO - __main__ - Step 33916: {'lr': 0.00044479199506475205, 'samples': 6511872, 'steps': 33915, 'loss/train': 1.7016457319259644} 08/30/2021 19:21:33 - INFO - __main__ - Step 33917: {'lr': 0.0004447886686730019, 'samples': 6512064, 'steps': 33916, 'loss/train': 1.3642207384109497} 08/30/2021 19:21:34 - INFO - __main__ - Step 33918: {'lr': 0.00044478534219348297, 'samples': 6512256, 'steps': 33917, 'loss/train': 1.7083402872085571} 08/30/2021 19:21:34 - INFO - __main__ - Step 33919: {'lr': 0.0004447820156261968, 'samples': 6512448, 'steps': 33918, 'loss/train': 0.025473570451140404} 08/30/2021 19:21:34 - INFO - __main__ - Step 33920: {'lr': 0.0004447786889711449, 'samples': 6512640, 'steps': 33919, 'loss/train': 1.494349718093872} 08/30/2021 19:21:36 - INFO - __main__ - Step 33921: {'lr': 0.00044477536222832867, 'samples': 6512832, 'steps': 33920, 'loss/train': 0.8877117037773132} 08/30/2021 19:21:36 - INFO - __main__ - Step 33922: {'lr': 0.0004447720353977497, 'samples': 6513024, 'steps': 33921, 'loss/train': 1.5002405643463135} 08/30/2021 19:21:36 - INFO - __main__ - Step 33923: {'lr': 0.0004447687084794094, 'samples': 6513216, 'steps': 33922, 'loss/train': 1.2252342700958252} 08/30/2021 19:21:37 - INFO - __main__ - Step 33924: {'lr': 0.00044476538147330934, 'samples': 6513408, 'steps': 33923, 'loss/train': 1.5719655752182007} 08/30/2021 19:21:37 - INFO - __main__ - Step 33925: {'lr': 0.00044476205437945105, 'samples': 6513600, 'steps': 33924, 'loss/train': 1.2667392492294312} 08/30/2021 19:21:38 - INFO - __main__ - Step 33926: {'lr': 0.0004447587271978359, 'samples': 6513792, 'steps': 33925, 'loss/train': 1.179510474205017} 08/30/2021 19:21:39 - INFO - __main__ - Step 33927: {'lr': 0.0004447553999284656, 'samples': 6513984, 'steps': 33926, 'loss/train': 1.2825231552124023} 08/30/2021 19:21:39 - INFO - __main__ - Step 33928: {'lr': 0.00044475207257134143, 'samples': 6514176, 'steps': 33927, 'loss/train': 0.1595047265291214} 08/30/2021 19:21:40 - INFO - __main__ - Step 33929: {'lr': 0.000444748745126465, 'samples': 6514368, 'steps': 33928, 'loss/train': 1.1425038576126099} 08/30/2021 19:21:40 - INFO - __main__ - Step 33930: {'lr': 0.0004447454175938378, 'samples': 6514560, 'steps': 33929, 'loss/train': 1.4913631677627563} 08/30/2021 19:21:40 - INFO - __main__ - Step 33931: {'lr': 0.00044474208997346133, 'samples': 6514752, 'steps': 33930, 'loss/train': 1.6583921909332275} 08/30/2021 19:21:42 - INFO - __main__ - Step 33932: {'lr': 0.00044473876226533703, 'samples': 6514944, 'steps': 33931, 'loss/train': 1.4317001104354858} 08/30/2021 19:21:43 - INFO - __main__ - Step 33933: {'lr': 0.0004447354344694665, 'samples': 6515136, 'steps': 33932, 'loss/train': 1.5071940422058105} 08/30/2021 19:21:43 - INFO - __main__ - Step 33934: {'lr': 0.0004447321065858512, 'samples': 6515328, 'steps': 33933, 'loss/train': 1.394973874092102} 08/30/2021 19:21:43 - INFO - __main__ - Step 33935: {'lr': 0.00044472877861449257, 'samples': 6515520, 'steps': 33934, 'loss/train': 1.2846614122390747} 08/30/2021 19:21:44 - INFO - __main__ - Step 33936: {'lr': 0.00044472545055539213, 'samples': 6515712, 'steps': 33935, 'loss/train': 1.419373631477356} 08/30/2021 19:21:45 - INFO - __main__ - Step 33937: {'lr': 0.00044472212240855155, 'samples': 6515904, 'steps': 33936, 'loss/train': 0.9835194945335388} 08/30/2021 19:21:46 - INFO - __main__ - Step 33938: {'lr': 0.0004447187941739721, 'samples': 6516096, 'steps': 33937, 'loss/train': 1.4644720554351807} 08/30/2021 19:21:46 - INFO - __main__ - Step 33939: {'lr': 0.00044471546585165536, 'samples': 6516288, 'steps': 33938, 'loss/train': 0.8359298706054688} 08/30/2021 19:21:46 - INFO - __main__ - Step 33940: {'lr': 0.0004447121374416028, 'samples': 6516480, 'steps': 33939, 'loss/train': 1.2722243070602417} 08/30/2021 19:21:47 - INFO - __main__ - Step 33941: {'lr': 0.000444708808943816, 'samples': 6516672, 'steps': 33940, 'loss/train': 1.3056972026824951} 08/30/2021 19:21:48 - INFO - __main__ - Step 33942: {'lr': 0.00044470548035829637, 'samples': 6516864, 'steps': 33941, 'loss/train': 1.6970505714416504} 08/30/2021 19:21:49 - INFO - __main__ - Step 33943: {'lr': 0.00044470215168504554, 'samples': 6517056, 'steps': 33942, 'loss/train': 1.3225524425506592} 08/30/2021 19:21:49 - INFO - __main__ - Step 33944: {'lr': 0.0004446988229240648, 'samples': 6517248, 'steps': 33943, 'loss/train': 1.0484739542007446} 08/30/2021 19:21:49 - INFO - __main__ - Step 33945: {'lr': 0.00044469549407535593, 'samples': 6517440, 'steps': 33944, 'loss/train': 1.7722183465957642} 08/30/2021 19:21:50 - INFO - __main__ - Step 33946: {'lr': 0.0004446921651389202, 'samples': 6517632, 'steps': 33945, 'loss/train': 1.5921233892440796} 08/30/2021 19:21:52 - INFO - __main__ - Step 33947: {'lr': 0.00044468883611475913, 'samples': 6517824, 'steps': 33946, 'loss/train': 0.10728372633457184} 08/30/2021 19:21:53 - INFO - __main__ - Step 33948: {'lr': 0.00044468550700287436, 'samples': 6518016, 'steps': 33947, 'loss/train': 0.5068848133087158} 08/30/2021 19:21:53 - INFO - __main__ - Step 33949: {'lr': 0.00044468217780326724, 'samples': 6518208, 'steps': 33948, 'loss/train': 1.8218778371810913} 08/30/2021 19:21:53 - INFO - __main__ - Step 33950: {'lr': 0.0004446788485159393, 'samples': 6518400, 'steps': 33949, 'loss/train': 0.08906268328428268} 08/30/2021 19:21:54 - INFO - __main__ - Step 33951: {'lr': 0.00044467551914089223, 'samples': 6518592, 'steps': 33950, 'loss/train': 0.2462569922208786} 08/30/2021 19:21:54 - INFO - __main__ - Step 33952: {'lr': 0.0004446721896781273, 'samples': 6518784, 'steps': 33951, 'loss/train': 1.1991685628890991} 08/30/2021 19:21:56 - INFO - __main__ - Step 33953: {'lr': 0.00044466886012764603, 'samples': 6518976, 'steps': 33952, 'loss/train': 1.5038806200027466} 08/30/2021 19:21:56 - INFO - __main__ - Step 33954: {'lr': 0.00044466553048944996, 'samples': 6519168, 'steps': 33953, 'loss/train': 1.138209342956543} 08/30/2021 19:21:56 - INFO - __main__ - Step 33955: {'lr': 0.0004446622007635407, 'samples': 6519360, 'steps': 33954, 'loss/train': 1.7388213872909546} 08/30/2021 19:21:57 - INFO - __main__ - Step 33956: {'lr': 0.0004446588709499196, 'samples': 6519552, 'steps': 33955, 'loss/train': 1.270929217338562} 08/30/2021 19:21:57 - INFO - __main__ - Step 33957: {'lr': 0.00044465554104858817, 'samples': 6519744, 'steps': 33956, 'loss/train': 0.06287913024425507} 08/30/2021 19:21:59 - INFO - __main__ - Step 33958: {'lr': 0.0004446522110595481, 'samples': 6519936, 'steps': 33957, 'loss/train': 0.047152016311883926} 08/30/2021 19:21:59 - INFO - __main__ - Step 33959: {'lr': 0.00044464888098280067, 'samples': 6520128, 'steps': 33958, 'loss/train': 1.2860584259033203} 08/30/2021 19:22:00 - INFO - __main__ - Step 33960: {'lr': 0.00044464555081834745, 'samples': 6520320, 'steps': 33959, 'loss/train': 1.2669841051101685} 08/30/2021 19:22:00 - INFO - __main__ - Step 33961: {'lr': 0.00044464222056618996, 'samples': 6520512, 'steps': 33960, 'loss/train': 1.0910521745681763} 08/30/2021 19:22:00 - INFO - __main__ - Step 33962: {'lr': 0.00044463889022632963, 'samples': 6520704, 'steps': 33961, 'loss/train': 2.0555191040039062} 08/30/2021 19:22:01 - INFO - __main__ - Step 33963: {'lr': 0.0004446355597987681, 'samples': 6520896, 'steps': 33962, 'loss/train': 1.3677674531936646} 08/30/2021 19:22:02 - INFO - __main__ - Step 33964: {'lr': 0.00044463222928350677, 'samples': 6521088, 'steps': 33963, 'loss/train': 0.23425672948360443} 08/30/2021 19:22:03 - INFO - __main__ - Step 33965: {'lr': 0.0004446288986805471, 'samples': 6521280, 'steps': 33964, 'loss/train': 1.3336637020111084} 08/30/2021 19:22:03 - INFO - __main__ - Step 33966: {'lr': 0.0004446255679898907, 'samples': 6521472, 'steps': 33965, 'loss/train': 1.368518590927124} 08/30/2021 19:22:03 - INFO - __main__ - Step 33967: {'lr': 0.000444622237211539, 'samples': 6521664, 'steps': 33966, 'loss/train': 0.08844552934169769} 08/30/2021 19:22:04 - INFO - __main__ - Step 33968: {'lr': 0.00044461890634549364, 'samples': 6521856, 'steps': 33967, 'loss/train': 1.519295334815979} 08/30/2021 19:22:06 - INFO - __main__ - Step 33969: {'lr': 0.00044461557539175587, 'samples': 6522048, 'steps': 33968, 'loss/train': 1.3855935335159302} 08/30/2021 19:22:06 - INFO - __main__ - Step 33970: {'lr': 0.0004446122443503274, 'samples': 6522240, 'steps': 33969, 'loss/train': 1.117292881011963} 08/30/2021 19:22:06 - INFO - __main__ - Step 33971: {'lr': 0.00044460891322120963, 'samples': 6522432, 'steps': 33970, 'loss/train': 0.1941833198070526} 08/30/2021 19:22:07 - INFO - __main__ - Step 33972: {'lr': 0.000444605582004404, 'samples': 6522624, 'steps': 33971, 'loss/train': 1.6087018251419067} 08/30/2021 19:22:07 - INFO - __main__ - Step 33973: {'lr': 0.0004446022506999122, 'samples': 6522816, 'steps': 33972, 'loss/train': 2.2581584453582764} 08/30/2021 19:22:08 - INFO - __main__ - Step 33974: {'lr': 0.0004445989193077356, 'samples': 6523008, 'steps': 33973, 'loss/train': 1.6441208124160767} 08/30/2021 19:22:09 - INFO - __main__ - Step 33975: {'lr': 0.0004445955878278758, 'samples': 6523200, 'steps': 33974, 'loss/train': 1.8568898439407349} 08/30/2021 19:22:09 - INFO - __main__ - Step 33976: {'lr': 0.00044459225626033413, 'samples': 6523392, 'steps': 33975, 'loss/train': 1.6220955848693848} 08/30/2021 19:22:10 - INFO - __main__ - Step 33977: {'lr': 0.00044458892460511225, 'samples': 6523584, 'steps': 33976, 'loss/train': 1.4792912006378174} 08/30/2021 19:22:10 - INFO - __main__ - Step 33978: {'lr': 0.0004445855928622116, 'samples': 6523776, 'steps': 33977, 'loss/train': 2.175816774368286} 08/30/2021 19:22:12 - INFO - __main__ - Step 33979: {'lr': 0.00044458226103163365, 'samples': 6523968, 'steps': 33978, 'loss/train': 1.5777018070220947} 08/30/2021 19:22:12 - INFO - __main__ - Step 33980: {'lr': 0.0004445789291133799, 'samples': 6524160, 'steps': 33979, 'loss/train': 1.580352544784546} 08/30/2021 19:22:12 - INFO - __main__ - Step 33981: {'lr': 0.0004445755971074519, 'samples': 6524352, 'steps': 33980, 'loss/train': 2.261376142501831} 08/30/2021 19:22:13 - INFO - __main__ - Step 33982: {'lr': 0.0004445722650138512, 'samples': 6524544, 'steps': 33981, 'loss/train': 1.8368432521820068} 08/30/2021 19:22:13 - INFO - __main__ - Step 33983: {'lr': 0.00044456893283257925, 'samples': 6524736, 'steps': 33982, 'loss/train': 1.5508798360824585} 08/30/2021 19:22:14 - INFO - __main__ - Step 33984: {'lr': 0.00044456560056363746, 'samples': 6524928, 'steps': 33983, 'loss/train': 0.5090582966804504} 08/30/2021 19:22:15 - INFO - __main__ - Step 33985: {'lr': 0.0004445622682070275, 'samples': 6525120, 'steps': 33984, 'loss/train': 0.8270739912986755} 08/30/2021 19:22:15 - INFO - __main__ - Step 33986: {'lr': 0.00044455893576275077, 'samples': 6525312, 'steps': 33985, 'loss/train': 1.4644569158554077} 08/30/2021 19:22:16 - INFO - __main__ - Step 33987: {'lr': 0.00044455560323080874, 'samples': 6525504, 'steps': 33986, 'loss/train': 1.3766546249389648} 08/30/2021 19:22:16 - INFO - __main__ - Step 33988: {'lr': 0.00044455227061120296, 'samples': 6525696, 'steps': 33987, 'loss/train': 1.5774089097976685} 08/30/2021 19:22:16 - INFO - __main__ - Step 33989: {'lr': 0.000444548937903935, 'samples': 6525888, 'steps': 33988, 'loss/train': 1.5354235172271729} 08/30/2021 19:22:18 - INFO - __main__ - Step 33990: {'lr': 0.0004445456051090062, 'samples': 6526080, 'steps': 33989, 'loss/train': 1.2000242471694946} 08/30/2021 19:22:18 - INFO - __main__ - Step 33991: {'lr': 0.0004445422722264182, 'samples': 6526272, 'steps': 33990, 'loss/train': 0.47508615255355835} 08/30/2021 19:22:19 - INFO - __main__ - Step 33992: {'lr': 0.0004445389392561724, 'samples': 6526464, 'steps': 33991, 'loss/train': 1.2503502368927002} 08/30/2021 19:22:19 - INFO - __main__ - Step 33993: {'lr': 0.0004445356061982704, 'samples': 6526656, 'steps': 33992, 'loss/train': 1.4229282140731812} 08/30/2021 19:22:19 - INFO - __main__ - Step 33994: {'lr': 0.0004445322730527137, 'samples': 6526848, 'steps': 33993, 'loss/train': 1.8668755292892456} 08/30/2021 19:22:21 - INFO - __main__ - Step 33995: {'lr': 0.0004445289398195037, 'samples': 6527040, 'steps': 33994, 'loss/train': 0.2902545630931854} 08/30/2021 19:22:22 - INFO - __main__ - Step 33996: {'lr': 0.000444525606498642, 'samples': 6527232, 'steps': 33995, 'loss/train': 1.4460036754608154} 08/30/2021 19:22:22 - INFO - __main__ - Step 33997: {'lr': 0.00044452227309013003, 'samples': 6527424, 'steps': 33996, 'loss/train': 1.8232755661010742} 08/30/2021 19:22:23 - INFO - __main__ - Step 33998: {'lr': 0.0004445189395939694, 'samples': 6527616, 'steps': 33997, 'loss/train': 1.5057605504989624} 08/30/2021 19:22:23 - INFO - __main__ - Step 33999: {'lr': 0.0004445156060101614, 'samples': 6527808, 'steps': 33998, 'loss/train': 1.542720913887024} 08/30/2021 19:22:23 - INFO - __main__ - Step 34000: {'lr': 0.0004445122723387077, 'samples': 6528000, 'steps': 33999, 'loss/train': 1.302803635597229} 08/30/2021 19:22:25 - INFO - __main__ - Step 34001: {'lr': 0.0004445089385796099, 'samples': 6528192, 'steps': 34000, 'loss/train': 0.2338247150182724} 08/30/2021 19:22:26 - INFO - __main__ - Step 34002: {'lr': 0.0004445056047328693, 'samples': 6528384, 'steps': 34001, 'loss/train': 0.7542929649353027} 08/30/2021 19:22:26 - INFO - __main__ - Step 34003: {'lr': 0.0004445022707984874, 'samples': 6528576, 'steps': 34002, 'loss/train': 1.3637045621871948} 08/30/2021 19:22:27 - INFO - __main__ - Step 34004: {'lr': 0.0004444989367764659, 'samples': 6528768, 'steps': 34003, 'loss/train': 1.511135458946228} 08/30/2021 19:22:27 - INFO - __main__ - Step 34005: {'lr': 0.0004444956026668061, 'samples': 6528960, 'steps': 34004, 'loss/train': 1.450154423713684} 08/30/2021 19:22:29 - INFO - __main__ - Step 34006: {'lr': 0.00044449226846950964, 'samples': 6529152, 'steps': 34005, 'loss/train': 1.5379148721694946} 08/30/2021 19:22:29 - INFO - __main__ - Step 34007: {'lr': 0.00044448893418457794, 'samples': 6529344, 'steps': 34006, 'loss/train': 1.2722413539886475} 08/30/2021 19:22:29 - INFO - __main__ - Step 34008: {'lr': 0.00044448559981201256, 'samples': 6529536, 'steps': 34007, 'loss/train': 0.3601374626159668} 08/30/2021 19:22:30 - INFO - __main__ - Step 34009: {'lr': 0.00044448226535181485, 'samples': 6529728, 'steps': 34008, 'loss/train': 0.41265320777893066} 08/30/2021 19:22:30 - INFO - __main__ - Step 34010: {'lr': 0.0004444789308039865, 'samples': 6529920, 'steps': 34009, 'loss/train': 1.9307525157928467} 08/30/2021 19:22:30 - INFO - __main__ - Step 34011: {'lr': 0.00044447559616852893, 'samples': 6530112, 'steps': 34010, 'loss/train': 2.2137908935546875} 08/30/2021 19:22:32 - INFO - __main__ - Step 34012: {'lr': 0.0004444722614454437, 'samples': 6530304, 'steps': 34011, 'loss/train': 1.3125523328781128} 08/30/2021 19:22:33 - INFO - __main__ - Step 34013: {'lr': 0.00044446892663473227, 'samples': 6530496, 'steps': 34012, 'loss/train': 1.557146668434143} 08/30/2021 19:22:33 - INFO - __main__ - Step 34014: {'lr': 0.0004444655917363961, 'samples': 6530688, 'steps': 34013, 'loss/train': 1.4590916633605957} 08/30/2021 19:22:33 - INFO - __main__ - Step 34015: {'lr': 0.00044446225675043684, 'samples': 6530880, 'steps': 34014, 'loss/train': 1.444432020187378} 08/30/2021 19:22:34 - INFO - __main__ - Step 34016: {'lr': 0.0004444589216768558, 'samples': 6531072, 'steps': 34015, 'loss/train': 1.8459526300430298} 08/30/2021 19:22:35 - INFO - __main__ - Step 34017: {'lr': 0.0004444555865156545, 'samples': 6531264, 'steps': 34016, 'loss/train': 0.11406456679105759} 08/30/2021 19:22:36 - INFO - __main__ - Step 34018: {'lr': 0.0004444522512668346, 'samples': 6531456, 'steps': 34017, 'loss/train': 1.6628382205963135} 08/30/2021 19:22:36 - INFO - __main__ - Step 34019: {'lr': 0.0004444489159303976, 'samples': 6531648, 'steps': 34018, 'loss/train': 1.4332411289215088} 08/30/2021 19:22:36 - INFO - __main__ - Step 34020: {'lr': 0.0004444455805063448, 'samples': 6531840, 'steps': 34019, 'loss/train': 0.9525831937789917} 08/30/2021 19:22:37 - INFO - __main__ - Step 34021: {'lr': 0.00044444224499467784, 'samples': 6532032, 'steps': 34020, 'loss/train': 1.7560033798217773} 08/30/2021 19:22:38 - INFO - __main__ - Step 34022: {'lr': 0.0004444389093953982, 'samples': 6532224, 'steps': 34021, 'loss/train': 1.7731221914291382} 08/30/2021 19:22:39 - INFO - __main__ - Step 34023: {'lr': 0.00044443557370850743, 'samples': 6532416, 'steps': 34022, 'loss/train': 1.5227303504943848} 08/30/2021 19:22:39 - INFO - __main__ - Step 34024: {'lr': 0.00044443223793400695, 'samples': 6532608, 'steps': 34023, 'loss/train': 5.8248372077941895} 08/30/2021 19:22:39 - INFO - __main__ - Step 34025: {'lr': 0.0004444289020718983, 'samples': 6532800, 'steps': 34024, 'loss/train': 1.6655195951461792} 08/30/2021 19:22:40 - INFO - __main__ - Step 34026: {'lr': 0.000444425566122183, 'samples': 6532992, 'steps': 34025, 'loss/train': 1.2167819738388062} 08/30/2021 19:22:42 - INFO - __main__ - Step 34027: {'lr': 0.0004444222300848626, 'samples': 6533184, 'steps': 34026, 'loss/train': 1.4032080173492432} 08/30/2021 19:22:42 - INFO - __main__ - Step 34028: {'lr': 0.00044441889395993844, 'samples': 6533376, 'steps': 34027, 'loss/train': 0.5165640711784363} 08/30/2021 19:22:42 - INFO - __main__ - Step 34029: {'lr': 0.00044441555774741215, 'samples': 6533568, 'steps': 34028, 'loss/train': 1.2656562328338623} 08/30/2021 19:22:43 - INFO - __main__ - Step 34030: {'lr': 0.00044441222144728525, 'samples': 6533760, 'steps': 34029, 'loss/train': 1.4361112117767334} 08/30/2021 19:22:43 - INFO - __main__ - Step 34031: {'lr': 0.00044440888505955926, 'samples': 6533952, 'steps': 34030, 'loss/train': 1.6054483652114868} 08/30/2021 19:22:45 - INFO - __main__ - Step 34032: {'lr': 0.00044440554858423553, 'samples': 6534144, 'steps': 34031, 'loss/train': 0.17834961414337158} 08/30/2021 19:22:45 - INFO - __main__ - Step 34033: {'lr': 0.0004444022120213157, 'samples': 6534336, 'steps': 34032, 'loss/train': 1.5666649341583252} 08/30/2021 19:22:45 - INFO - __main__ - Step 34034: {'lr': 0.00044439887537080116, 'samples': 6534528, 'steps': 34033, 'loss/train': 0.9417108297348022} 08/30/2021 19:22:46 - INFO - __main__ - Step 34035: {'lr': 0.00044439553863269356, 'samples': 6534720, 'steps': 34034, 'loss/train': 1.5861077308654785} 08/30/2021 19:22:46 - INFO - __main__ - Step 34036: {'lr': 0.00044439220180699434, 'samples': 6534912, 'steps': 34035, 'loss/train': 1.1958444118499756} 08/30/2021 19:22:47 - INFO - __main__ - Step 34037: {'lr': 0.00044438886489370493, 'samples': 6535104, 'steps': 34036, 'loss/train': 0.8025926351547241} 08/30/2021 19:22:48 - INFO - __main__ - Step 34038: {'lr': 0.00044438552789282694, 'samples': 6535296, 'steps': 34037, 'loss/train': 1.6437263488769531} 08/30/2021 19:22:49 - INFO - __main__ - Step 34039: {'lr': 0.00044438219080436184, 'samples': 6535488, 'steps': 34038, 'loss/train': 1.6665632724761963} 08/30/2021 19:22:49 - INFO - __main__ - Step 34040: {'lr': 0.0004443788536283111, 'samples': 6535680, 'steps': 34039, 'loss/train': 0.49048101902008057} 08/30/2021 19:22:49 - INFO - __main__ - Step 34041: {'lr': 0.0004443755163646762, 'samples': 6535872, 'steps': 34040, 'loss/train': 1.439178466796875} 08/30/2021 19:22:50 - INFO - __main__ - Step 34042: {'lr': 0.00044437217901345885, 'samples': 6536064, 'steps': 34041, 'loss/train': 1.6291260719299316} 08/30/2021 19:22:52 - INFO - __main__ - Step 34043: {'lr': 0.0004443688415746602, 'samples': 6536256, 'steps': 34042, 'loss/train': 0.7658398747444153} 08/30/2021 19:22:52 - INFO - __main__ - Step 34044: {'lr': 0.00044436550404828207, 'samples': 6536448, 'steps': 34043, 'loss/train': 1.4731136560440063} 08/30/2021 19:22:53 - INFO - __main__ - Step 34045: {'lr': 0.0004443621664343258, 'samples': 6536640, 'steps': 34044, 'loss/train': 1.4982048273086548} 08/30/2021 19:22:53 - INFO - __main__ - Step 34046: {'lr': 0.000444358828732793, 'samples': 6536832, 'steps': 34045, 'loss/train': 1.6950299739837646} 08/30/2021 19:22:53 - INFO - __main__ - Step 34047: {'lr': 0.000444355490943685, 'samples': 6537024, 'steps': 34046, 'loss/train': 0.6983802318572998} 08/30/2021 19:22:54 - INFO - __main__ - Step 34048: {'lr': 0.0004443521530670035, 'samples': 6537216, 'steps': 34047, 'loss/train': 1.171935796737671} 08/30/2021 19:22:55 - INFO - __main__ - Step 34049: {'lr': 0.00044434881510274995, 'samples': 6537408, 'steps': 34048, 'loss/train': 0.9457870125770569} 08/30/2021 19:22:56 - INFO - __main__ - Step 34050: {'lr': 0.00044434547705092574, 'samples': 6537600, 'steps': 34049, 'loss/train': 1.1059062480926514} 08/30/2021 19:22:56 - INFO - __main__ - Step 34051: {'lr': 0.0004443421389115325, 'samples': 6537792, 'steps': 34050, 'loss/train': 0.15285541117191315} 08/30/2021 19:22:57 - INFO - __main__ - Step 34052: {'lr': 0.00044433880068457166, 'samples': 6537984, 'steps': 34051, 'loss/train': 1.0612382888793945} 08/30/2021 19:22:57 - INFO - __main__ - Step 34053: {'lr': 0.0004443354623700447, 'samples': 6538176, 'steps': 34052, 'loss/train': 1.487714171409607} 08/30/2021 19:22:58 - INFO - __main__ - Step 34054: {'lr': 0.0004443321239679533, 'samples': 6538368, 'steps': 34053, 'loss/train': 0.6798129677772522} 08/30/2021 19:22:59 - INFO - __main__ - Step 34055: {'lr': 0.0004443287854782988, 'samples': 6538560, 'steps': 34054, 'loss/train': 1.1008055210113525} 08/30/2021 19:22:59 - INFO - __main__ - Step 34056: {'lr': 0.0004443254469010828, 'samples': 6538752, 'steps': 34055, 'loss/train': 1.6925904750823975} 08/30/2021 19:23:00 - INFO - __main__ - Step 34057: {'lr': 0.0004443221082363067, 'samples': 6538944, 'steps': 34056, 'loss/train': 1.514134407043457} 08/30/2021 19:23:00 - INFO - __main__ - Step 34058: {'lr': 0.000444318769483972, 'samples': 6539136, 'steps': 34057, 'loss/train': 1.9152193069458008} 08/30/2021 19:23:02 - INFO - __main__ - Step 34059: {'lr': 0.0004443154306440803, 'samples': 6539328, 'steps': 34058, 'loss/train': 1.9796053171157837} 08/30/2021 19:23:03 - INFO - __main__ - Step 34060: {'lr': 0.00044431209171663313, 'samples': 6539520, 'steps': 34059, 'loss/train': 0.25463294982910156} 08/30/2021 19:23:03 - INFO - __main__ - Step 34061: {'lr': 0.00044430875270163185, 'samples': 6539712, 'steps': 34060, 'loss/train': 1.1701732873916626} 08/30/2021 19:23:03 - INFO - __main__ - Step 34062: {'lr': 0.00044430541359907804, 'samples': 6539904, 'steps': 34061, 'loss/train': 1.5943013429641724} 08/30/2021 19:23:04 - INFO - __main__ - Step 34063: {'lr': 0.0004443020744089733, 'samples': 6540096, 'steps': 34062, 'loss/train': 1.3849632740020752} 08/30/2021 19:23:04 - INFO - __main__ - Step 34064: {'lr': 0.00044429873513131897, 'samples': 6540288, 'steps': 34063, 'loss/train': 1.2737693786621094} 08/30/2021 19:23:05 - INFO - __main__ - Step 34065: {'lr': 0.00044429539576611664, 'samples': 6540480, 'steps': 34064, 'loss/train': 2.0899105072021484} 08/30/2021 19:23:06 - INFO - __main__ - Step 34066: {'lr': 0.0004442920563133678, 'samples': 6540672, 'steps': 34065, 'loss/train': 1.907918930053711} 08/30/2021 19:23:06 - INFO - __main__ - Step 34067: {'lr': 0.000444288716773074, 'samples': 6540864, 'steps': 34066, 'loss/train': 1.8460075855255127} 08/30/2021 19:23:07 - INFO - __main__ - Step 34068: {'lr': 0.00044428537714523664, 'samples': 6541056, 'steps': 34067, 'loss/train': 1.53731107711792} 08/30/2021 19:23:07 - INFO - __main__ - Step 34069: {'lr': 0.00044428203742985734, 'samples': 6541248, 'steps': 34068, 'loss/train': 1.5715285539627075} 08/30/2021 19:23:09 - INFO - __main__ - Step 34070: {'lr': 0.0004442786976269375, 'samples': 6541440, 'steps': 34069, 'loss/train': 0.991809070110321} 08/30/2021 19:23:09 - INFO - __main__ - Step 34071: {'lr': 0.0004442753577364788, 'samples': 6541632, 'steps': 34070, 'loss/train': 1.6136173009872437} 08/30/2021 19:23:10 - INFO - __main__ - Step 34072: {'lr': 0.00044427201775848246, 'samples': 6541824, 'steps': 34071, 'loss/train': 1.2435650825500488} 08/30/2021 19:23:10 - INFO - __main__ - Step 34073: {'lr': 0.0004442686776929502, 'samples': 6542016, 'steps': 34072, 'loss/train': 2.152937412261963} 08/30/2021 19:23:10 - INFO - __main__ - Step 34074: {'lr': 0.0004442653375398835, 'samples': 6542208, 'steps': 34073, 'loss/train': 0.43778541684150696} 08/30/2021 19:23:12 - INFO - __main__ - Step 34075: {'lr': 0.0004442619972992838, 'samples': 6542400, 'steps': 34074, 'loss/train': 1.5430192947387695} 08/30/2021 19:23:12 - INFO - __main__ - Step 34076: {'lr': 0.00044425865697115266, 'samples': 6542592, 'steps': 34075, 'loss/train': 1.7967345714569092} 08/30/2021 19:23:13 - INFO - __main__ - Step 34077: {'lr': 0.00044425531655549157, 'samples': 6542784, 'steps': 34076, 'loss/train': 0.9645836353302002} 08/30/2021 19:23:13 - INFO - __main__ - Step 34078: {'lr': 0.0004442519760523021, 'samples': 6542976, 'steps': 34077, 'loss/train': 1.2653108835220337} 08/30/2021 19:23:13 - INFO - __main__ - Step 34079: {'lr': 0.00044424863546158554, 'samples': 6543168, 'steps': 34078, 'loss/train': 1.6694822311401367} 08/30/2021 19:23:14 - INFO - __main__ - Step 34080: {'lr': 0.00044424529478334364, 'samples': 6543360, 'steps': 34079, 'loss/train': 1.5284863710403442} 08/30/2021 19:23:16 - INFO - __main__ - Step 34081: {'lr': 0.0004442419540175778, 'samples': 6543552, 'steps': 34080, 'loss/train': 0.1475307047367096} 08/30/2021 19:23:16 - INFO - __main__ - Step 34082: {'lr': 0.0004442386131642895, 'samples': 6543744, 'steps': 34081, 'loss/train': 1.412103533744812} 08/30/2021 19:23:16 - INFO - __main__ - Step 34083: {'lr': 0.0004442352722234803, 'samples': 6543936, 'steps': 34082, 'loss/train': 1.4961471557617188} 08/30/2021 19:23:17 - INFO - __main__ - Step 34084: {'lr': 0.0004442319311951517, 'samples': 6544128, 'steps': 34083, 'loss/train': 1.8522720336914062} 08/30/2021 19:23:17 - INFO - __main__ - Step 34085: {'lr': 0.00044422859007930515, 'samples': 6544320, 'steps': 34084, 'loss/train': 1.3261008262634277} 08/30/2021 19:23:18 - INFO - __main__ - Step 34086: {'lr': 0.00044422524887594223, 'samples': 6544512, 'steps': 34085, 'loss/train': 0.7102405428886414} 08/30/2021 19:23:19 - INFO - __main__ - Step 34087: {'lr': 0.0004442219075850644, 'samples': 6544704, 'steps': 34086, 'loss/train': 1.4017736911773682} 08/30/2021 19:23:19 - INFO - __main__ - Step 34088: {'lr': 0.0004442185662066731, 'samples': 6544896, 'steps': 34087, 'loss/train': 0.9071478843688965} 08/30/2021 19:23:20 - INFO - __main__ - Step 34089: {'lr': 0.00044421522474077, 'samples': 6545088, 'steps': 34088, 'loss/train': 0.7296309471130371} 08/30/2021 19:23:20 - INFO - __main__ - Step 34090: {'lr': 0.0004442118831873565, 'samples': 6545280, 'steps': 34089, 'loss/train': 1.5598859786987305} 08/30/2021 19:23:21 - INFO - __main__ - Step 34091: {'lr': 0.00044420854154643413, 'samples': 6545472, 'steps': 34090, 'loss/train': 1.604191541671753} 08/30/2021 19:23:22 - INFO - __main__ - Step 34092: {'lr': 0.00044420519981800446, 'samples': 6545664, 'steps': 34091, 'loss/train': 1.550437331199646} 08/30/2021 19:23:22 - INFO - __main__ - Step 34093: {'lr': 0.0004442018580020688, 'samples': 6545856, 'steps': 34092, 'loss/train': 1.6765708923339844} 08/30/2021 19:23:23 - INFO - __main__ - Step 34094: {'lr': 0.0004441985160986288, 'samples': 6546048, 'steps': 34093, 'loss/train': 1.8748102188110352} 08/30/2021 19:23:23 - INFO - __main__ - Step 34095: {'lr': 0.00044419517410768594, 'samples': 6546240, 'steps': 34094, 'loss/train': 1.2102035284042358} 08/30/2021 19:23:24 - INFO - __main__ - Step 34096: {'lr': 0.0004441918320292418, 'samples': 6546432, 'steps': 34095, 'loss/train': 1.571191430091858} 08/30/2021 19:23:25 - INFO - __main__ - Step 34097: {'lr': 0.00044418848986329775, 'samples': 6546624, 'steps': 34096, 'loss/train': 1.576714277267456} 08/30/2021 19:23:25 - INFO - __main__ - Step 34098: {'lr': 0.0004441851476098554, 'samples': 6546816, 'steps': 34097, 'loss/train': 1.3400318622589111} 08/30/2021 19:23:26 - INFO - __main__ - Step 34099: {'lr': 0.0004441818052689162, 'samples': 6547008, 'steps': 34098, 'loss/train': 1.7222793102264404} 08/30/2021 19:23:26 - INFO - __main__ - Step 34100: {'lr': 0.0004441784628404817, 'samples': 6547200, 'steps': 34099, 'loss/train': 1.5035686492919922} 08/30/2021 19:23:27 - INFO - __main__ - Step 34101: {'lr': 0.0004441751203245533, 'samples': 6547392, 'steps': 34100, 'loss/train': 1.8330358266830444} 08/30/2021 19:23:28 - INFO - __main__ - Step 34102: {'lr': 0.0004441717777211327, 'samples': 6547584, 'steps': 34101, 'loss/train': 2.1723060607910156} 08/30/2021 19:23:28 - INFO - __main__ - Step 34103: {'lr': 0.00044416843503022126, 'samples': 6547776, 'steps': 34102, 'loss/train': 1.5225306749343872} 08/30/2021 19:23:29 - INFO - __main__ - Step 34104: {'lr': 0.00044416509225182044, 'samples': 6547968, 'steps': 34103, 'loss/train': 1.1453888416290283} 08/30/2021 19:23:29 - INFO - __main__ - Step 34105: {'lr': 0.0004441617493859319, 'samples': 6548160, 'steps': 34104, 'loss/train': 1.463390827178955} 08/30/2021 19:23:30 - INFO - __main__ - Step 34106: {'lr': 0.0004441584064325571, 'samples': 6548352, 'steps': 34105, 'loss/train': 1.5844244956970215} 08/30/2021 19:23:31 - INFO - __main__ - Step 34107: {'lr': 0.0004441550633916975, 'samples': 6548544, 'steps': 34106, 'loss/train': 1.9017499685287476} 08/30/2021 19:23:32 - INFO - __main__ - Step 34108: {'lr': 0.0004441517202633546, 'samples': 6548736, 'steps': 34107, 'loss/train': 1.7990669012069702} 08/30/2021 19:23:32 - INFO - __main__ - Step 34109: {'lr': 0.0004441483770475299, 'samples': 6548928, 'steps': 34108, 'loss/train': 1.2839605808258057} 08/30/2021 19:23:33 - INFO - __main__ - Step 34110: {'lr': 0.000444145033744225, 'samples': 6549120, 'steps': 34109, 'loss/train': 1.3546086549758911} 08/30/2021 19:23:33 - INFO - __main__ - Step 34111: {'lr': 0.0004441416903534413, 'samples': 6549312, 'steps': 34110, 'loss/train': 0.17416894435882568} 08/30/2021 19:23:35 - INFO - __main__ - Step 34112: {'lr': 0.00044413834687518034, 'samples': 6549504, 'steps': 34111, 'loss/train': 1.389888048171997} 08/30/2021 19:23:35 - INFO - __main__ - Step 34113: {'lr': 0.00044413500330944366, 'samples': 6549696, 'steps': 34112, 'loss/train': 1.502997636795044} 08/30/2021 19:23:36 - INFO - __main__ - Step 34114: {'lr': 0.00044413165965623275, 'samples': 6549888, 'steps': 34113, 'loss/train': 1.8994534015655518} 08/30/2021 19:23:36 - INFO - __main__ - Step 34115: {'lr': 0.00044412831591554916, 'samples': 6550080, 'steps': 34114, 'loss/train': 1.4599614143371582} 08/30/2021 19:23:36 - INFO - __main__ - Step 34116: {'lr': 0.0004441249720873942, 'samples': 6550272, 'steps': 34115, 'loss/train': 1.1991057395935059} 08/30/2021 19:23:37 - INFO - __main__ - Step 34117: {'lr': 0.00044412162817176966, 'samples': 6550464, 'steps': 34116, 'loss/train': 0.8302178382873535} 08/30/2021 19:23:38 - INFO - __main__ - Step 34118: {'lr': 0.00044411828416867684, 'samples': 6550656, 'steps': 34117, 'loss/train': 1.6284816265106201} 08/30/2021 19:23:39 - INFO - __main__ - Step 34119: {'lr': 0.00044411494007811736, 'samples': 6550848, 'steps': 34118, 'loss/train': 1.1236224174499512} 08/30/2021 19:23:39 - INFO - __main__ - Step 34120: {'lr': 0.00044411159590009263, 'samples': 6551040, 'steps': 34119, 'loss/train': 1.3370686769485474} 08/30/2021 19:23:40 - INFO - __main__ - Step 34121: {'lr': 0.0004441082516346043, 'samples': 6551232, 'steps': 34120, 'loss/train': 1.8110923767089844} 08/30/2021 19:23:40 - INFO - __main__ - Step 34122: {'lr': 0.0004441049072816537, 'samples': 6551424, 'steps': 34121, 'loss/train': 1.2732646465301514} 08/30/2021 19:23:41 - INFO - __main__ - Step 34123: {'lr': 0.0004441015628412425, 'samples': 6551616, 'steps': 34122, 'loss/train': 1.7347229719161987} 08/30/2021 19:23:42 - INFO - __main__ - Step 34124: {'lr': 0.0004440982183133721, 'samples': 6551808, 'steps': 34123, 'loss/train': 1.4055626392364502} 08/30/2021 19:23:42 - INFO - __main__ - Step 34125: {'lr': 0.00044409487369804395, 'samples': 6552000, 'steps': 34124, 'loss/train': 1.4072000980377197} 08/30/2021 19:23:43 - INFO - __main__ - Step 34126: {'lr': 0.00044409152899525973, 'samples': 6552192, 'steps': 34125, 'loss/train': 1.2079187631607056} 08/30/2021 19:23:43 - INFO - __main__ - Step 34127: {'lr': 0.00044408818420502085, 'samples': 6552384, 'steps': 34126, 'loss/train': 1.6269725561141968} 08/30/2021 19:23:45 - INFO - __main__ - Step 34128: {'lr': 0.00044408483932732886, 'samples': 6552576, 'steps': 34127, 'loss/train': 1.5361895561218262} 08/30/2021 19:23:45 - INFO - __main__ - Step 34129: {'lr': 0.00044408149436218523, 'samples': 6552768, 'steps': 34128, 'loss/train': 1.7371842861175537} 08/30/2021 19:23:45 - INFO - __main__ - Step 34130: {'lr': 0.00044407814930959137, 'samples': 6552960, 'steps': 34129, 'loss/train': 1.6486812829971313} 08/30/2021 19:23:46 - INFO - __main__ - Step 34131: {'lr': 0.000444074804169549, 'samples': 6553152, 'steps': 34130, 'loss/train': 2.4829702377319336} 08/30/2021 19:23:46 - INFO - __main__ - Step 34132: {'lr': 0.00044407145894205947, 'samples': 6553344, 'steps': 34131, 'loss/train': 0.819826066493988} 08/30/2021 19:23:48 - INFO - __main__ - Step 34133: {'lr': 0.0004440681136271244, 'samples': 6553536, 'steps': 34132, 'loss/train': 1.3111553192138672} 08/30/2021 19:23:48 - INFO - __main__ - Step 34134: {'lr': 0.0004440647682247452, 'samples': 6553728, 'steps': 34133, 'loss/train': 1.255419135093689} 08/30/2021 19:23:49 - INFO - __main__ - Step 34135: {'lr': 0.00044406142273492334, 'samples': 6553920, 'steps': 34134, 'loss/train': 1.1177340745925903} 08/30/2021 19:23:49 - INFO - __main__ - Step 34136: {'lr': 0.00044405807715766047, 'samples': 6554112, 'steps': 34135, 'loss/train': 1.4886301755905151} 08/30/2021 19:23:49 - INFO - __main__ - Step 34137: {'lr': 0.00044405473149295804, 'samples': 6554304, 'steps': 34136, 'loss/train': 1.3253486156463623} 08/30/2021 19:23:51 - INFO - __main__ - Step 34138: {'lr': 0.0004440513857408175, 'samples': 6554496, 'steps': 34137, 'loss/train': 1.618687391281128} 08/30/2021 19:23:51 - INFO - __main__ - Step 34139: {'lr': 0.0004440480399012404, 'samples': 6554688, 'steps': 34138, 'loss/train': 1.6538251638412476} 08/30/2021 19:23:52 - INFO - __main__ - Step 34140: {'lr': 0.00044404469397422823, 'samples': 6554880, 'steps': 34139, 'loss/train': 1.6019890308380127} 08/30/2021 19:23:52 - INFO - __main__ - Step 34141: {'lr': 0.00044404134795978257, 'samples': 6555072, 'steps': 34140, 'loss/train': 1.201795220375061} 08/30/2021 19:23:52 - INFO - __main__ - Step 34142: {'lr': 0.0004440380018579049, 'samples': 6555264, 'steps': 34141, 'loss/train': 1.527990460395813} 08/30/2021 19:23:54 - INFO - __main__ - Step 34143: {'lr': 0.00044403465566859656, 'samples': 6555456, 'steps': 34142, 'loss/train': 1.0799099206924438} 08/30/2021 19:23:54 - INFO - __main__ - Step 34144: {'lr': 0.0004440313093918593, 'samples': 6555648, 'steps': 34143, 'loss/train': 1.9859564304351807} 08/30/2021 19:23:55 - INFO - __main__ - Step 34145: {'lr': 0.00044402796302769453, 'samples': 6555840, 'steps': 34144, 'loss/train': 0.777617335319519} 08/30/2021 19:23:55 - INFO - __main__ - Step 34146: {'lr': 0.0004440246165761037, 'samples': 6556032, 'steps': 34145, 'loss/train': 1.4875977039337158} 08/30/2021 19:23:55 - INFO - __main__ - Step 34147: {'lr': 0.00044402127003708846, 'samples': 6556224, 'steps': 34146, 'loss/train': 1.2050319910049438} 08/30/2021 19:23:57 - INFO - __main__ - Step 34148: {'lr': 0.0004440179234106502, 'samples': 6556416, 'steps': 34147, 'loss/train': 1.2090332508087158} 08/30/2021 19:23:57 - INFO - __main__ - Step 34149: {'lr': 0.00044401457669679043, 'samples': 6556608, 'steps': 34148, 'loss/train': 0.9860490560531616} 08/30/2021 19:23:58 - INFO - __main__ - Step 34150: {'lr': 0.0004440112298955107, 'samples': 6556800, 'steps': 34149, 'loss/train': 2.4779458045959473} 08/30/2021 19:23:58 - INFO - __main__ - Step 34151: {'lr': 0.0004440078830068125, 'samples': 6556992, 'steps': 34150, 'loss/train': 1.4247993230819702} 08/30/2021 19:23:58 - INFO - __main__ - Step 34152: {'lr': 0.00044400453603069727, 'samples': 6557184, 'steps': 34151, 'loss/train': 0.5688244104385376} 08/30/2021 19:24:00 - INFO - __main__ - Step 34153: {'lr': 0.0004440011889671667, 'samples': 6557376, 'steps': 34152, 'loss/train': 1.5328048467636108} 08/30/2021 19:24:00 - INFO - __main__ - Step 34154: {'lr': 0.00044399784181622216, 'samples': 6557568, 'steps': 34153, 'loss/train': 2.024057626724243} 08/30/2021 19:24:01 - INFO - __main__ - Step 34155: {'lr': 0.0004439944945778651, 'samples': 6557760, 'steps': 34154, 'loss/train': 1.7221916913986206} 08/30/2021 19:24:01 - INFO - __main__ - Step 34156: {'lr': 0.0004439911472520972, 'samples': 6557952, 'steps': 34155, 'loss/train': 1.5092796087265015} 08/30/2021 19:24:01 - INFO - __main__ - Step 34157: {'lr': 0.0004439877998389199, 'samples': 6558144, 'steps': 34156, 'loss/train': 1.34806227684021} 08/30/2021 19:24:03 - INFO - __main__ - Step 34158: {'lr': 0.0004439844523383346, 'samples': 6558336, 'steps': 34157, 'loss/train': 1.026733160018921} 08/30/2021 19:24:04 - INFO - __main__ - Step 34159: {'lr': 0.000443981104750343, 'samples': 6558528, 'steps': 34158, 'loss/train': 1.7693021297454834} 08/30/2021 19:24:04 - INFO - __main__ - Step 34160: {'lr': 0.0004439777570749465, 'samples': 6558720, 'steps': 34159, 'loss/train': 1.5494612455368042} 08/30/2021 19:24:04 - INFO - __main__ - Step 34161: {'lr': 0.0004439744093121465, 'samples': 6558912, 'steps': 34160, 'loss/train': 0.18620210886001587} 08/30/2021 19:24:05 - INFO - __main__ - Step 34162: {'lr': 0.00044397106146194473, 'samples': 6559104, 'steps': 34161, 'loss/train': 1.3535797595977783} 08/30/2021 19:24:05 - INFO - __main__ - Step 34163: {'lr': 0.00044396771352434256, 'samples': 6559296, 'steps': 34162, 'loss/train': 1.4653098583221436} 08/30/2021 19:24:06 - INFO - __main__ - Step 34164: {'lr': 0.00044396436549934155, 'samples': 6559488, 'steps': 34163, 'loss/train': 1.4813244342803955} 08/30/2021 19:24:07 - INFO - __main__ - Step 34165: {'lr': 0.00044396101738694316, 'samples': 6559680, 'steps': 34164, 'loss/train': 1.4787218570709229} 08/30/2021 19:24:07 - INFO - __main__ - Step 34166: {'lr': 0.000443957669187149, 'samples': 6559872, 'steps': 34165, 'loss/train': 1.663667917251587} 08/30/2021 19:24:08 - INFO - __main__ - Step 34167: {'lr': 0.0004439543208999604, 'samples': 6560064, 'steps': 34166, 'loss/train': 1.3167599439620972} 08/30/2021 19:24:08 - INFO - __main__ - Step 34168: {'lr': 0.00044395097252537905, 'samples': 6560256, 'steps': 34167, 'loss/train': 1.2871379852294922} 08/30/2021 19:24:10 - INFO - __main__ - Step 34169: {'lr': 0.0004439476240634064, 'samples': 6560448, 'steps': 34168, 'loss/train': 1.1371201276779175} 08/30/2021 19:24:10 - INFO - __main__ - Step 34170: {'lr': 0.00044394427551404386, 'samples': 6560640, 'steps': 34169, 'loss/train': 1.474199652671814} 08/30/2021 19:24:11 - INFO - __main__ - Step 34171: {'lr': 0.00044394092687729305, 'samples': 6560832, 'steps': 34170, 'loss/train': 1.9667190313339233} 08/30/2021 19:24:11 - INFO - __main__ - Step 34172: {'lr': 0.0004439375781531555, 'samples': 6561024, 'steps': 34171, 'loss/train': 1.244231104850769} 08/30/2021 19:24:11 - INFO - __main__ - Step 34173: {'lr': 0.00044393422934163265, 'samples': 6561216, 'steps': 34172, 'loss/train': 1.9117591381072998} 08/30/2021 19:24:13 - INFO - __main__ - Step 34174: {'lr': 0.000443930880442726, 'samples': 6561408, 'steps': 34173, 'loss/train': 1.083193063735962} 08/30/2021 19:24:13 - INFO - __main__ - Step 34175: {'lr': 0.0004439275314564371, 'samples': 6561600, 'steps': 34174, 'loss/train': 1.7774274349212646} 08/30/2021 19:24:14 - INFO - __main__ - Step 34176: {'lr': 0.0004439241823827674, 'samples': 6561792, 'steps': 34175, 'loss/train': 1.2330737113952637} 08/30/2021 19:24:14 - INFO - __main__ - Step 34177: {'lr': 0.0004439208332217186, 'samples': 6561984, 'steps': 34176, 'loss/train': 1.119931936264038} 08/30/2021 19:24:14 - INFO - __main__ - Step 34178: {'lr': 0.00044391748397329194, 'samples': 6562176, 'steps': 34177, 'loss/train': 1.6856865882873535} 08/30/2021 19:24:16 - INFO - __main__ - Step 34179: {'lr': 0.0004439141346374891, 'samples': 6562368, 'steps': 34178, 'loss/train': 1.6810458898544312} 08/30/2021 19:24:17 - INFO - __main__ - Step 34180: {'lr': 0.0004439107852143115, 'samples': 6562560, 'steps': 34179, 'loss/train': 1.2703230381011963} 08/30/2021 19:24:17 - INFO - __main__ - Step 34181: {'lr': 0.0004439074357037607, 'samples': 6562752, 'steps': 34180, 'loss/train': 1.591692328453064} 08/30/2021 19:24:17 - INFO - __main__ - Step 34182: {'lr': 0.0004439040861058383, 'samples': 6562944, 'steps': 34181, 'loss/train': 1.7475205659866333} 08/30/2021 19:24:18 - INFO - __main__ - Step 34183: {'lr': 0.00044390073642054564, 'samples': 6563136, 'steps': 34182, 'loss/train': 0.2079470306634903} 08/30/2021 19:24:18 - INFO - __main__ - Step 34184: {'lr': 0.00044389738664788424, 'samples': 6563328, 'steps': 34183, 'loss/train': 0.30054929852485657} 08/30/2021 19:24:20 - INFO - __main__ - Step 34185: {'lr': 0.00044389403678785576, 'samples': 6563520, 'steps': 34184, 'loss/train': 1.2066550254821777} 08/30/2021 19:24:20 - INFO - __main__ - Step 34186: {'lr': 0.0004438906868404616, 'samples': 6563712, 'steps': 34185, 'loss/train': 1.898586630821228} 08/30/2021 19:24:21 - INFO - __main__ - Step 34187: {'lr': 0.00044388733680570324, 'samples': 6563904, 'steps': 34186, 'loss/train': 1.0105535984039307} 08/30/2021 19:24:21 - INFO - __main__ - Step 34188: {'lr': 0.00044388398668358234, 'samples': 6564096, 'steps': 34187, 'loss/train': 0.5083702206611633} 08/30/2021 19:24:21 - INFO - __main__ - Step 34189: {'lr': 0.00044388063647410016, 'samples': 6564288, 'steps': 34188, 'loss/train': 1.2549986839294434} 08/30/2021 19:24:22 - INFO - __main__ - Step 34190: {'lr': 0.00044387728617725845, 'samples': 6564480, 'steps': 34189, 'loss/train': 0.02863602340221405} 08/30/2021 19:24:23 - INFO - __main__ - Step 34191: {'lr': 0.0004438739357930586, 'samples': 6564672, 'steps': 34190, 'loss/train': 1.8983687162399292} 08/30/2021 19:24:24 - INFO - __main__ - Step 34192: {'lr': 0.00044387058532150217, 'samples': 6564864, 'steps': 34191, 'loss/train': 1.122631549835205} 08/30/2021 19:24:24 - INFO - __main__ - Step 34193: {'lr': 0.0004438672347625907, 'samples': 6565056, 'steps': 34192, 'loss/train': 1.2891201972961426} 08/30/2021 19:24:24 - INFO - __main__ - Step 34194: {'lr': 0.0004438638841163255, 'samples': 6565248, 'steps': 34193, 'loss/train': 1.9356719255447388} 08/30/2021 19:24:25 - INFO - __main__ - Step 34195: {'lr': 0.0004438605333827083, 'samples': 6565440, 'steps': 34194, 'loss/train': 1.4864017963409424} 08/30/2021 19:24:26 - INFO - __main__ - Step 34196: {'lr': 0.00044385718256174055, 'samples': 6565632, 'steps': 34195, 'loss/train': 1.7286392450332642} 08/30/2021 19:24:27 - INFO - __main__ - Step 34197: {'lr': 0.0004438538316534237, 'samples': 6565824, 'steps': 34196, 'loss/train': 1.7241981029510498} 08/30/2021 19:24:27 - INFO - __main__ - Step 34198: {'lr': 0.0004438504806577594, 'samples': 6566016, 'steps': 34197, 'loss/train': 1.3779321908950806} 08/30/2021 19:24:27 - INFO - __main__ - Step 34199: {'lr': 0.000443847129574749, 'samples': 6566208, 'steps': 34198, 'loss/train': 2.177377462387085} 08/30/2021 19:24:28 - INFO - __main__ - Step 34200: {'lr': 0.0004438437784043941, 'samples': 6566400, 'steps': 34199, 'loss/train': 0.8560999035835266} 08/30/2021 19:24:28 - INFO - __main__ - Step 34201: {'lr': 0.00044384042714669614, 'samples': 6566592, 'steps': 34200, 'loss/train': 1.8695520162582397} 08/30/2021 19:24:30 - INFO - __main__ - Step 34202: {'lr': 0.0004438370758016567, 'samples': 6566784, 'steps': 34201, 'loss/train': 1.9796277284622192} 08/30/2021 19:24:30 - INFO - __main__ - Step 34203: {'lr': 0.00044383372436927727, 'samples': 6566976, 'steps': 34202, 'loss/train': 1.2149608135223389} 08/30/2021 19:24:31 - INFO - __main__ - Step 34204: {'lr': 0.00044383037284955937, 'samples': 6567168, 'steps': 34203, 'loss/train': 0.474067747592926} 08/30/2021 19:24:31 - INFO - __main__ - Step 34205: {'lr': 0.00044382702124250444, 'samples': 6567360, 'steps': 34204, 'loss/train': 0.06754706054925919} 08/30/2021 19:24:31 - INFO - __main__ - Step 34206: {'lr': 0.0004438236695481141, 'samples': 6567552, 'steps': 34205, 'loss/train': 1.4249253273010254} 08/30/2021 19:24:33 - INFO - __main__ - Step 34207: {'lr': 0.00044382031776638974, 'samples': 6567744, 'steps': 34206, 'loss/train': 1.7205047607421875} 08/30/2021 19:24:33 - INFO - __main__ - Step 34208: {'lr': 0.000443816965897333, 'samples': 6567936, 'steps': 34207, 'loss/train': 1.0833297967910767} 08/30/2021 19:24:34 - INFO - __main__ - Step 34209: {'lr': 0.0004438136139409453, 'samples': 6568128, 'steps': 34208, 'loss/train': 2.3178319931030273} 08/30/2021 19:24:34 - INFO - __main__ - Step 34210: {'lr': 0.00044381026189722824, 'samples': 6568320, 'steps': 34209, 'loss/train': 1.1204833984375} 08/30/2021 19:24:34 - INFO - __main__ - Step 34211: {'lr': 0.0004438069097661832, 'samples': 6568512, 'steps': 34210, 'loss/train': 1.4572902917861938} 08/30/2021 19:24:36 - INFO - __main__ - Step 34212: {'lr': 0.0004438035575478118, 'samples': 6568704, 'steps': 34211, 'loss/train': 0.03854339197278023} 08/30/2021 19:24:37 - INFO - __main__ - Step 34213: {'lr': 0.0004438002052421154, 'samples': 6568896, 'steps': 34212, 'loss/train': 1.9920425415039062} 08/30/2021 19:24:37 - INFO - __main__ - Step 34214: {'lr': 0.00044379685284909575, 'samples': 6569088, 'steps': 34213, 'loss/train': 1.115020751953125} 08/30/2021 19:24:37 - INFO - __main__ - Step 34215: {'lr': 0.00044379350036875413, 'samples': 6569280, 'steps': 34214, 'loss/train': 1.7330234050750732} 08/30/2021 19:24:38 - INFO - __main__ - Step 34216: {'lr': 0.00044379014780109217, 'samples': 6569472, 'steps': 34215, 'loss/train': 0.030922777950763702} 08/30/2021 19:24:38 - INFO - __main__ - Step 34217: {'lr': 0.00044378679514611144, 'samples': 6569664, 'steps': 34216, 'loss/train': 0.03244650363922119} 08/30/2021 19:24:39 - INFO - __main__ - Step 34218: {'lr': 0.0004437834424038133, 'samples': 6569856, 'steps': 34217, 'loss/train': 1.6112648248672485} 08/30/2021 19:24:40 - INFO - __main__ - Step 34219: {'lr': 0.00044378008957419936, 'samples': 6570048, 'steps': 34218, 'loss/train': 1.5600571632385254} 08/30/2021 19:24:40 - INFO - __main__ - Step 34220: {'lr': 0.00044377673665727105, 'samples': 6570240, 'steps': 34219, 'loss/train': 1.6179169416427612} 08/30/2021 19:24:41 - INFO - __main__ - Step 34221: {'lr': 0.00044377338365303, 'samples': 6570432, 'steps': 34220, 'loss/train': 1.8349685668945312} 08/30/2021 19:24:41 - INFO - __main__ - Step 34222: {'lr': 0.00044377003056147757, 'samples': 6570624, 'steps': 34221, 'loss/train': 1.8525657653808594} 08/30/2021 19:24:43 - INFO - __main__ - Step 34223: {'lr': 0.00044376667738261545, 'samples': 6570816, 'steps': 34222, 'loss/train': 1.5012279748916626} 08/30/2021 19:24:44 - INFO - __main__ - Step 34224: {'lr': 0.000443763324116445, 'samples': 6571008, 'steps': 34223, 'loss/train': 1.5951707363128662} 08/30/2021 19:24:44 - INFO - __main__ - Step 34225: {'lr': 0.00044375997076296774, 'samples': 6571200, 'steps': 34224, 'loss/train': 1.2798352241516113} 08/30/2021 19:24:45 - INFO - __main__ - Step 34226: {'lr': 0.0004437566173221853, 'samples': 6571392, 'steps': 34225, 'loss/train': 0.09263995289802551} 08/30/2021 19:24:45 - INFO - __main__ - Step 34227: {'lr': 0.0004437532637940991, 'samples': 6571584, 'steps': 34226, 'loss/train': 1.4912067651748657} 08/30/2021 19:24:46 - INFO - __main__ - Step 34228: {'lr': 0.0004437499101787107, 'samples': 6571776, 'steps': 34227, 'loss/train': 1.5270442962646484} 08/30/2021 19:24:47 - INFO - __main__ - Step 34229: {'lr': 0.00044374655647602153, 'samples': 6571968, 'steps': 34228, 'loss/train': 0.8537130951881409} 08/30/2021 19:24:47 - INFO - __main__ - Step 34230: {'lr': 0.0004437432026860332, 'samples': 6572160, 'steps': 34229, 'loss/train': 1.00099515914917} 08/30/2021 19:24:48 - INFO - __main__ - Step 34231: {'lr': 0.00044373984880874705, 'samples': 6572352, 'steps': 34230, 'loss/train': 1.547523021697998} 08/30/2021 19:24:48 - INFO - __main__ - Step 34232: {'lr': 0.0004437364948441649, 'samples': 6572544, 'steps': 34231, 'loss/train': 0.5179018974304199} 08/30/2021 19:24:50 - INFO - __main__ - Step 34233: {'lr': 0.00044373314079228796, 'samples': 6572736, 'steps': 34232, 'loss/train': 1.007223129272461} 08/30/2021 19:24:50 - INFO - __main__ - Step 34234: {'lr': 0.0004437297866531179, 'samples': 6572928, 'steps': 34233, 'loss/train': 1.3493837118148804} 08/30/2021 19:24:50 - INFO - __main__ - Step 34235: {'lr': 0.0004437264324266561, 'samples': 6573120, 'steps': 34234, 'loss/train': 1.7975345849990845} 08/30/2021 19:24:51 - INFO - __main__ - Step 34236: {'lr': 0.00044372307811290425, 'samples': 6573312, 'steps': 34235, 'loss/train': 2.090087890625} 08/30/2021 19:24:51 - INFO - __main__ - Step 34237: {'lr': 0.00044371972371186374, 'samples': 6573504, 'steps': 34236, 'loss/train': 0.9617405533790588} 08/30/2021 19:24:52 - INFO - __main__ - Step 34238: {'lr': 0.0004437163692235361, 'samples': 6573696, 'steps': 34237, 'loss/train': 1.2290090322494507} 08/30/2021 19:24:53 - INFO - __main__ - Step 34239: {'lr': 0.0004437130146479229, 'samples': 6573888, 'steps': 34238, 'loss/train': 1.1606254577636719} 08/30/2021 19:24:53 - INFO - __main__ - Step 34240: {'lr': 0.00044370965998502554, 'samples': 6574080, 'steps': 34239, 'loss/train': 1.639793038368225} 08/30/2021 19:24:54 - INFO - __main__ - Step 34241: {'lr': 0.0004437063052348457, 'samples': 6574272, 'steps': 34240, 'loss/train': 0.46614667773246765} 08/30/2021 19:24:54 - INFO - __main__ - Step 34242: {'lr': 0.0004437029503973847, 'samples': 6574464, 'steps': 34241, 'loss/train': 0.9633070826530457} 08/30/2021 19:24:54 - INFO - __main__ - Step 34243: {'lr': 0.00044369959547264416, 'samples': 6574656, 'steps': 34242, 'loss/train': 1.1773043870925903} 08/30/2021 19:24:56 - INFO - __main__ - Step 34244: {'lr': 0.0004436962404606255, 'samples': 6574848, 'steps': 34243, 'loss/train': 1.3718786239624023} 08/30/2021 19:24:57 - INFO - __main__ - Step 34245: {'lr': 0.0004436928853613304, 'samples': 6575040, 'steps': 34244, 'loss/train': 1.1644132137298584} 08/30/2021 19:24:57 - INFO - __main__ - Step 34246: {'lr': 0.0004436895301747602, 'samples': 6575232, 'steps': 34245, 'loss/train': 0.13820725679397583} 08/30/2021 19:24:57 - INFO - __main__ - Step 34247: {'lr': 0.00044368617490091655, 'samples': 6575424, 'steps': 34246, 'loss/train': 1.9280463457107544} 08/30/2021 19:24:58 - INFO - __main__ - Step 34248: {'lr': 0.0004436828195398009, 'samples': 6575616, 'steps': 34247, 'loss/train': 1.2685279846191406} 08/30/2021 19:24:59 - INFO - __main__ - Step 34249: {'lr': 0.0004436794640914148, 'samples': 6575808, 'steps': 34248, 'loss/train': 1.8469264507293701} 08/30/2021 19:25:00 - INFO - __main__ - Step 34250: {'lr': 0.00044367610855575965, 'samples': 6576000, 'steps': 34249, 'loss/train': 1.165789008140564} 08/30/2021 19:25:00 - INFO - __main__ - Step 34251: {'lr': 0.00044367275293283705, 'samples': 6576192, 'steps': 34250, 'loss/train': 1.6584229469299316} 08/30/2021 19:25:00 - INFO - __main__ - Step 34252: {'lr': 0.00044366939722264843, 'samples': 6576384, 'steps': 34251, 'loss/train': 1.1459347009658813} 08/30/2021 19:25:01 - INFO - __main__ - Step 34253: {'lr': 0.00044366604142519547, 'samples': 6576576, 'steps': 34252, 'loss/train': 1.487842082977295} 08/30/2021 19:25:02 - INFO - __main__ - Step 34254: {'lr': 0.0004436626855404796, 'samples': 6576768, 'steps': 34253, 'loss/train': 1.770192265510559} 08/30/2021 19:25:03 - INFO - __main__ - Step 34255: {'lr': 0.0004436593295685022, 'samples': 6576960, 'steps': 34254, 'loss/train': 1.1421363353729248} 08/30/2021 19:25:03 - INFO - __main__ - Step 34256: {'lr': 0.00044365597350926495, 'samples': 6577152, 'steps': 34255, 'loss/train': 1.4245450496673584} 08/30/2021 19:25:03 - INFO - __main__ - Step 34257: {'lr': 0.0004436526173627693, 'samples': 6577344, 'steps': 34256, 'loss/train': 1.275696873664856} 08/30/2021 19:25:04 - INFO - __main__ - Step 34258: {'lr': 0.00044364926112901675, 'samples': 6577536, 'steps': 34257, 'loss/train': 1.6342436075210571} 08/30/2021 19:25:06 - INFO - __main__ - Step 34259: {'lr': 0.0004436459048080089, 'samples': 6577728, 'steps': 34258, 'loss/train': 1.5422656536102295} 08/30/2021 19:25:07 - INFO - __main__ - Step 34260: {'lr': 0.00044364254839974717, 'samples': 6577920, 'steps': 34259, 'loss/train': 1.8504722118377686} 08/30/2021 19:25:07 - INFO - __main__ - Step 34261: {'lr': 0.0004436391919042331, 'samples': 6578112, 'steps': 34260, 'loss/train': 1.1316170692443848} 08/30/2021 19:25:07 - INFO - __main__ - Step 34262: {'lr': 0.00044363583532146814, 'samples': 6578304, 'steps': 34261, 'loss/train': 1.1465259790420532} 08/30/2021 19:25:08 - INFO - __main__ - Step 34263: {'lr': 0.0004436324786514538, 'samples': 6578496, 'steps': 34262, 'loss/train': 1.1065312623977661} 08/30/2021 19:25:08 - INFO - __main__ - Step 34264: {'lr': 0.0004436291218941918, 'samples': 6578688, 'steps': 34263, 'loss/train': 2.729570150375366} 08/30/2021 19:25:08 - INFO - __main__ - Step 34265: {'lr': 0.00044362576504968344, 'samples': 6578880, 'steps': 34264, 'loss/train': 2.7487316131591797} 08/30/2021 19:25:10 - INFO - __main__ - Step 34266: {'lr': 0.0004436224081179303, 'samples': 6579072, 'steps': 34265, 'loss/train': 1.3740428686141968} 08/30/2021 19:25:10 - INFO - __main__ - Step 34267: {'lr': 0.00044361905109893397, 'samples': 6579264, 'steps': 34266, 'loss/train': 1.0996173620224} 08/30/2021 19:25:11 - INFO - __main__ - Step 34268: {'lr': 0.00044361569399269574, 'samples': 6579456, 'steps': 34267, 'loss/train': 1.31764817237854} 08/30/2021 19:25:11 - INFO - __main__ - Step 34269: {'lr': 0.0004436123367992174, 'samples': 6579648, 'steps': 34268, 'loss/train': 1.7479370832443237} 08/30/2021 19:25:11 - INFO - __main__ - Step 34270: {'lr': 0.0004436089795185003, 'samples': 6579840, 'steps': 34269, 'loss/train': 1.315965175628662} 08/30/2021 19:25:13 - INFO - __main__ - Step 34271: {'lr': 0.0004436056221505459, 'samples': 6580032, 'steps': 34270, 'loss/train': 1.4850128889083862} 08/30/2021 19:25:14 - INFO - __main__ - Step 34272: {'lr': 0.00044360226469535583, 'samples': 6580224, 'steps': 34271, 'loss/train': 1.6063331365585327} 08/30/2021 19:25:14 - INFO - __main__ - Step 34273: {'lr': 0.0004435989071529316, 'samples': 6580416, 'steps': 34272, 'loss/train': 1.93623685836792} 08/30/2021 19:25:14 - INFO - __main__ - Step 34274: {'lr': 0.0004435955495232746, 'samples': 6580608, 'steps': 34273, 'loss/train': 1.8147273063659668} 08/30/2021 19:25:15 - INFO - __main__ - Step 34275: {'lr': 0.00044359219180638656, 'samples': 6580800, 'steps': 34274, 'loss/train': 0.036472879350185394} 08/30/2021 19:25:15 - INFO - __main__ - Step 34276: {'lr': 0.0004435888340022688, 'samples': 6580992, 'steps': 34275, 'loss/train': 0.8034371137619019} 08/30/2021 19:25:15 - INFO - __main__ - Step 34277: {'lr': 0.0004435854761109229, 'samples': 6581184, 'steps': 34276, 'loss/train': 2.220669984817505} 08/30/2021 19:25:17 - INFO - __main__ - Step 34278: {'lr': 0.00044358211813235046, 'samples': 6581376, 'steps': 34277, 'loss/train': 1.5848262310028076} 08/30/2021 19:25:18 - INFO - __main__ - Step 34279: {'lr': 0.0004435787600665528, 'samples': 6581568, 'steps': 34278, 'loss/train': 0.13611367344856262} 08/30/2021 19:25:18 - INFO - __main__ - Step 34280: {'lr': 0.0004435754019135315, 'samples': 6581760, 'steps': 34279, 'loss/train': 1.5251275300979614} 08/30/2021 19:25:18 - INFO - __main__ - Step 34281: {'lr': 0.0004435720436732882, 'samples': 6581952, 'steps': 34280, 'loss/train': 0.6050376296043396} 08/30/2021 19:25:19 - INFO - __main__ - Step 34282: {'lr': 0.0004435686853458243, 'samples': 6582144, 'steps': 34281, 'loss/train': 1.4607545137405396} 08/30/2021 19:25:21 - INFO - __main__ - Step 34283: {'lr': 0.0004435653269311414, 'samples': 6582336, 'steps': 34282, 'loss/train': 1.279322624206543} 08/30/2021 19:25:21 - INFO - __main__ - Step 34284: {'lr': 0.00044356196842924086, 'samples': 6582528, 'steps': 34283, 'loss/train': 1.5130841732025146} 08/30/2021 19:25:21 - INFO - __main__ - Step 34285: {'lr': 0.0004435586098401243, 'samples': 6582720, 'steps': 34284, 'loss/train': 1.7569422721862793} 08/30/2021 19:25:22 - INFO - __main__ - Step 34286: {'lr': 0.00044355525116379326, 'samples': 6582912, 'steps': 34285, 'loss/train': 2.2513930797576904} 08/30/2021 19:25:22 - INFO - __main__ - Step 34287: {'lr': 0.00044355189240024917, 'samples': 6583104, 'steps': 34286, 'loss/train': 1.1448408365249634} 08/30/2021 19:25:24 - INFO - __main__ - Step 34288: {'lr': 0.00044354853354949353, 'samples': 6583296, 'steps': 34287, 'loss/train': 1.3231486082077026} 08/30/2021 19:25:24 - INFO - __main__ - Step 34289: {'lr': 0.000443545174611528, 'samples': 6583488, 'steps': 34288, 'loss/train': 1.7273366451263428} 08/30/2021 19:25:24 - INFO - __main__ - Step 34290: {'lr': 0.000443541815586354, 'samples': 6583680, 'steps': 34289, 'loss/train': 1.305019497871399} 08/30/2021 19:25:25 - INFO - __main__ - Step 34291: {'lr': 0.0004435384564739729, 'samples': 6583872, 'steps': 34290, 'loss/train': 1.125197172164917} 08/30/2021 19:25:25 - INFO - __main__ - Step 34292: {'lr': 0.00044353509727438657, 'samples': 6584064, 'steps': 34291, 'loss/train': 0.8574925065040588} 08/30/2021 19:25:27 - INFO - __main__ - Step 34293: {'lr': 0.00044353173798759616, 'samples': 6584256, 'steps': 34292, 'loss/train': 1.1615010499954224} 08/30/2021 19:25:27 - INFO - __main__ - Step 34294: {'lr': 0.0004435283786136034, 'samples': 6584448, 'steps': 34293, 'loss/train': 1.2592524290084839} 08/30/2021 19:25:27 - INFO - __main__ - Step 34295: {'lr': 0.0004435250191524097, 'samples': 6584640, 'steps': 34294, 'loss/train': 1.0597270727157593} 08/30/2021 19:25:28 - INFO - __main__ - Step 34296: {'lr': 0.0004435216596040167, 'samples': 6584832, 'steps': 34295, 'loss/train': 1.015820860862732} 08/30/2021 19:25:28 - INFO - __main__ - Step 34297: {'lr': 0.00044351829996842575, 'samples': 6585024, 'steps': 34296, 'loss/train': 1.4411613941192627} 08/30/2021 19:25:30 - INFO - __main__ - Step 34298: {'lr': 0.00044351494024563845, 'samples': 6585216, 'steps': 34297, 'loss/train': 1.0451772212982178} 08/30/2021 19:25:30 - INFO - __main__ - Step 34299: {'lr': 0.0004435115804356563, 'samples': 6585408, 'steps': 34298, 'loss/train': 1.1034191846847534} 08/30/2021 19:25:30 - INFO - __main__ - Step 34300: {'lr': 0.0004435082205384808, 'samples': 6585600, 'steps': 34299, 'loss/train': 1.4241681098937988} 08/30/2021 19:25:31 - INFO - __main__ - Step 34301: {'lr': 0.00044350486055411354, 'samples': 6585792, 'steps': 34300, 'loss/train': 1.849123477935791} 08/30/2021 19:25:31 - INFO - __main__ - Step 34302: {'lr': 0.000443501500482556, 'samples': 6585984, 'steps': 34301, 'loss/train': 1.3144383430480957} 08/30/2021 19:25:33 - INFO - __main__ - Step 34303: {'lr': 0.0004434981403238096, 'samples': 6586176, 'steps': 34302, 'loss/train': 1.4229683876037598} 08/30/2021 19:25:33 - INFO - __main__ - Step 34304: {'lr': 0.0004434947800778759, 'samples': 6586368, 'steps': 34303, 'loss/train': 1.4115080833435059} 08/30/2021 19:25:34 - INFO - __main__ - Step 34305: {'lr': 0.0004434914197447565, 'samples': 6586560, 'steps': 34304, 'loss/train': 1.8310561180114746} 08/30/2021 19:25:34 - INFO - __main__ - Step 34306: {'lr': 0.0004434880593244528, 'samples': 6586752, 'steps': 34305, 'loss/train': 1.541959524154663} 08/30/2021 19:25:34 - INFO - __main__ - Step 34307: {'lr': 0.0004434846988169664, 'samples': 6586944, 'steps': 34306, 'loss/train': 1.6055432558059692} 08/30/2021 19:25:35 - INFO - __main__ - Step 34308: {'lr': 0.0004434813382222989, 'samples': 6587136, 'steps': 34307, 'loss/train': 1.0402737855911255} 08/30/2021 19:25:36 - INFO - __main__ - Step 34309: {'lr': 0.0004434779775404515, 'samples': 6587328, 'steps': 34308, 'loss/train': 1.6550846099853516} 08/30/2021 19:25:37 - INFO - __main__ - Step 34310: {'lr': 0.000443474616771426, 'samples': 6587520, 'steps': 34309, 'loss/train': 1.699147343635559} 08/30/2021 19:25:37 - INFO - __main__ - Step 34311: {'lr': 0.00044347125591522377, 'samples': 6587712, 'steps': 34310, 'loss/train': 1.4277589321136475} 08/30/2021 19:25:37 - INFO - __main__ - Step 34312: {'lr': 0.00044346789497184643, 'samples': 6587904, 'steps': 34311, 'loss/train': 1.2638791799545288} 08/30/2021 19:25:38 - INFO - __main__ - Step 34313: {'lr': 0.0004434645339412954, 'samples': 6588096, 'steps': 34312, 'loss/train': 1.0181409120559692} 08/30/2021 19:25:39 - INFO - __main__ - Step 34314: {'lr': 0.0004434611728235722, 'samples': 6588288, 'steps': 34313, 'loss/train': 1.0525574684143066} 08/30/2021 19:25:40 - INFO - __main__ - Step 34315: {'lr': 0.0004434578116186785, 'samples': 6588480, 'steps': 34314, 'loss/train': 1.6535593271255493} 08/30/2021 19:25:40 - INFO - __main__ - Step 34316: {'lr': 0.00044345445032661565, 'samples': 6588672, 'steps': 34315, 'loss/train': 1.7786425352096558} 08/30/2021 19:25:40 - INFO - __main__ - Step 34317: {'lr': 0.0004434510889473852, 'samples': 6588864, 'steps': 34316, 'loss/train': 1.1568361520767212} 08/30/2021 19:25:41 - INFO - __main__ - Step 34318: {'lr': 0.00044344772748098867, 'samples': 6589056, 'steps': 34317, 'loss/train': 0.9997491240501404} 08/30/2021 19:25:42 - INFO - __main__ - Step 34319: {'lr': 0.00044344436592742755, 'samples': 6589248, 'steps': 34318, 'loss/train': 1.6291216611862183} 08/30/2021 19:25:43 - INFO - __main__ - Step 34320: {'lr': 0.0004434410042867034, 'samples': 6589440, 'steps': 34319, 'loss/train': 1.8541678190231323} 08/30/2021 19:25:43 - INFO - __main__ - Step 34321: {'lr': 0.0004434376425588178, 'samples': 6589632, 'steps': 34320, 'loss/train': 1.3037652969360352} 08/30/2021 19:25:43 - INFO - __main__ - Step 34322: {'lr': 0.00044343428074377207, 'samples': 6589824, 'steps': 34321, 'loss/train': 1.7471519708633423} 08/30/2021 19:25:44 - INFO - __main__ - Step 34323: {'lr': 0.0004434309188415679, 'samples': 6590016, 'steps': 34322, 'loss/train': 1.3369140625} 08/30/2021 19:25:45 - INFO - __main__ - Step 34324: {'lr': 0.0004434275568522067, 'samples': 6590208, 'steps': 34323, 'loss/train': 0.4033282995223999} 08/30/2021 19:25:46 - INFO - __main__ - Step 34325: {'lr': 0.0004434241947756901, 'samples': 6590400, 'steps': 34324, 'loss/train': 1.3243719339370728} 08/30/2021 19:25:46 - INFO - __main__ - Step 34326: {'lr': 0.0004434208326120195, 'samples': 6590592, 'steps': 34325, 'loss/train': 1.038028359413147} 08/30/2021 19:25:47 - INFO - __main__ - Step 34327: {'lr': 0.0004434174703611964, 'samples': 6590784, 'steps': 34326, 'loss/train': 0.9112753868103027} 08/30/2021 19:25:47 - INFO - __main__ - Step 34328: {'lr': 0.00044341410802322247, 'samples': 6590976, 'steps': 34327, 'loss/train': 1.6747767925262451} 08/30/2021 19:25:47 - INFO - __main__ - Step 34329: {'lr': 0.00044341074559809903, 'samples': 6591168, 'steps': 34328, 'loss/train': 1.0039563179016113} 08/30/2021 19:25:48 - INFO - __main__ - Step 34330: {'lr': 0.00044340738308582775, 'samples': 6591360, 'steps': 34329, 'loss/train': 0.03337034955620766} 08/30/2021 19:25:49 - INFO - __main__ - Step 34331: {'lr': 0.0004434040204864101, 'samples': 6591552, 'steps': 34330, 'loss/train': 1.483001470565796} 08/30/2021 19:25:50 - INFO - __main__ - Step 34332: {'lr': 0.00044340065779984757, 'samples': 6591744, 'steps': 34331, 'loss/train': 1.5729074478149414} 08/30/2021 19:25:50 - INFO - __main__ - Step 34333: {'lr': 0.0004433972950261417, 'samples': 6591936, 'steps': 34332, 'loss/train': 1.3920680284500122} 08/30/2021 19:25:50 - INFO - __main__ - Step 34334: {'lr': 0.00044339393216529394, 'samples': 6592128, 'steps': 34333, 'loss/train': 0.399932324886322} 08/30/2021 19:25:51 - INFO - __main__ - Step 34335: {'lr': 0.00044339056921730593, 'samples': 6592320, 'steps': 34334, 'loss/train': 1.3992620706558228} 08/30/2021 19:25:53 - INFO - __main__ - Step 34336: {'lr': 0.000443387206182179, 'samples': 6592512, 'steps': 34335, 'loss/train': 1.3509875535964966} 08/30/2021 19:25:53 - INFO - __main__ - Step 34337: {'lr': 0.0004433838430599149, 'samples': 6592704, 'steps': 34336, 'loss/train': 1.7384206056594849} 08/30/2021 19:25:54 - INFO - __main__ - Step 34338: {'lr': 0.000443380479850515, 'samples': 6592896, 'steps': 34337, 'loss/train': 1.2571719884872437} 08/30/2021 19:25:54 - INFO - __main__ - Step 34339: {'lr': 0.00044337711655398083, 'samples': 6593088, 'steps': 34338, 'loss/train': 1.735754132270813} 08/30/2021 19:25:54 - INFO - __main__ - Step 34340: {'lr': 0.00044337375317031393, 'samples': 6593280, 'steps': 34339, 'loss/train': 1.4142794609069824} 08/30/2021 19:25:56 - INFO - __main__ - Step 34341: {'lr': 0.0004433703896995157, 'samples': 6593472, 'steps': 34340, 'loss/train': 1.5877922773361206} 08/30/2021 19:25:56 - INFO - __main__ - Step 34342: {'lr': 0.0004433670261415879, 'samples': 6593664, 'steps': 34341, 'loss/train': 1.3526380062103271} 08/30/2021 19:25:57 - INFO - __main__ - Step 34343: {'lr': 0.0004433636624965318, 'samples': 6593856, 'steps': 34342, 'loss/train': 1.3758047819137573} 08/30/2021 19:25:57 - INFO - __main__ - Step 34344: {'lr': 0.0004433602987643491, 'samples': 6594048, 'steps': 34343, 'loss/train': 2.0959386825561523} 08/30/2021 19:25:57 - INFO - __main__ - Step 34345: {'lr': 0.00044335693494504115, 'samples': 6594240, 'steps': 34344, 'loss/train': 1.9930661916732788} 08/30/2021 19:25:59 - INFO - __main__ - Step 34346: {'lr': 0.00044335357103860964, 'samples': 6594432, 'steps': 34345, 'loss/train': 1.3216766119003296} 08/30/2021 19:25:59 - INFO - __main__ - Step 34347: {'lr': 0.0004433502070450559, 'samples': 6594624, 'steps': 34346, 'loss/train': 1.0442615747451782} 08/30/2021 19:25:59 - INFO - __main__ - Step 34348: {'lr': 0.0004433468429643816, 'samples': 6594816, 'steps': 34347, 'loss/train': 1.3631224632263184} 08/30/2021 19:26:00 - INFO - __main__ - Step 34349: {'lr': 0.00044334347879658817, 'samples': 6595008, 'steps': 34348, 'loss/train': 1.4799100160598755} 08/30/2021 19:26:00 - INFO - __main__ - Step 34350: {'lr': 0.0004433401145416771, 'samples': 6595200, 'steps': 34349, 'loss/train': 1.4209132194519043} 08/30/2021 19:26:01 - INFO - __main__ - Step 34351: {'lr': 0.00044333675019965, 'samples': 6595392, 'steps': 34350, 'loss/train': 0.5847344994544983} 08/30/2021 19:26:02 - INFO - __main__ - Step 34352: {'lr': 0.00044333338577050844, 'samples': 6595584, 'steps': 34351, 'loss/train': 0.5432370901107788} 08/30/2021 19:26:02 - INFO - __main__ - Step 34353: {'lr': 0.0004433300212542537, 'samples': 6595776, 'steps': 34352, 'loss/train': 1.5141524076461792} 08/30/2021 19:26:03 - INFO - __main__ - Step 34354: {'lr': 0.00044332665665088755, 'samples': 6595968, 'steps': 34353, 'loss/train': 0.999143660068512} 08/30/2021 19:26:03 - INFO - __main__ - Step 34355: {'lr': 0.00044332329196041133, 'samples': 6596160, 'steps': 34354, 'loss/train': 1.7645156383514404} 08/30/2021 19:26:03 - INFO - __main__ - Step 34356: {'lr': 0.0004433199271828267, 'samples': 6596352, 'steps': 34355, 'loss/train': 1.7707819938659668} 08/30/2021 19:26:05 - INFO - __main__ - Step 34357: {'lr': 0.0004433165623181349, 'samples': 6596544, 'steps': 34356, 'loss/train': 0.4831221103668213} 08/30/2021 19:26:05 - INFO - __main__ - Step 34358: {'lr': 0.0004433131973663378, 'samples': 6596736, 'steps': 34357, 'loss/train': 1.2558364868164062} 08/30/2021 19:26:06 - INFO - __main__ - Step 34359: {'lr': 0.0004433098323274367, 'samples': 6596928, 'steps': 34358, 'loss/train': 1.8244661092758179} 08/30/2021 19:26:06 - INFO - __main__ - Step 34360: {'lr': 0.00044330646720143317, 'samples': 6597120, 'steps': 34359, 'loss/train': 1.5290697813034058} 08/30/2021 19:26:06 - INFO - __main__ - Step 34361: {'lr': 0.0004433031019883288, 'samples': 6597312, 'steps': 34360, 'loss/train': 1.1753313541412354} 08/30/2021 19:26:08 - INFO - __main__ - Step 34362: {'lr': 0.00044329973668812497, 'samples': 6597504, 'steps': 34361, 'loss/train': 1.4041204452514648} 08/30/2021 19:26:08 - INFO - __main__ - Step 34363: {'lr': 0.00044329637130082324, 'samples': 6597696, 'steps': 34362, 'loss/train': 1.5539454221725464} 08/30/2021 19:26:09 - INFO - __main__ - Step 34364: {'lr': 0.00044329300582642516, 'samples': 6597888, 'steps': 34363, 'loss/train': 0.8712891936302185} 08/30/2021 19:26:09 - INFO - __main__ - Step 34365: {'lr': 0.0004432896402649323, 'samples': 6598080, 'steps': 34364, 'loss/train': 1.9170267581939697} 08/30/2021 19:26:09 - INFO - __main__ - Step 34366: {'lr': 0.0004432862746163461, 'samples': 6598272, 'steps': 34365, 'loss/train': 1.5498980283737183} 08/30/2021 19:26:11 - INFO - __main__ - Step 34367: {'lr': 0.000443282908880668, 'samples': 6598464, 'steps': 34366, 'loss/train': 1.7895435094833374} 08/30/2021 19:26:11 - INFO - __main__ - Step 34368: {'lr': 0.00044327954305789963, 'samples': 6598656, 'steps': 34367, 'loss/train': 1.296325922012329} 08/30/2021 19:26:12 - INFO - __main__ - Step 34369: {'lr': 0.0004432761771480426, 'samples': 6598848, 'steps': 34368, 'loss/train': 1.6100263595581055} 08/30/2021 19:26:12 - INFO - __main__ - Step 34370: {'lr': 0.0004432728111510982, 'samples': 6599040, 'steps': 34369, 'loss/train': 1.3352285623550415} 08/30/2021 19:26:12 - INFO - __main__ - Step 34371: {'lr': 0.000443269445067068, 'samples': 6599232, 'steps': 34370, 'loss/train': 1.4644743204116821} 08/30/2021 19:26:14 - INFO - __main__ - Step 34372: {'lr': 0.0004432660788959537, 'samples': 6599424, 'steps': 34371, 'loss/train': 0.0805610790848732} 08/30/2021 19:26:14 - INFO - __main__ - Step 34373: {'lr': 0.00044326271263775657, 'samples': 6599616, 'steps': 34372, 'loss/train': 1.8947086334228516} 08/30/2021 19:26:15 - INFO - __main__ - Step 34374: {'lr': 0.0004432593462924783, 'samples': 6599808, 'steps': 34373, 'loss/train': 1.1238963603973389} 08/30/2021 19:26:15 - INFO - __main__ - Step 34375: {'lr': 0.0004432559798601203, 'samples': 6600000, 'steps': 34374, 'loss/train': 0.7812830209732056} 08/30/2021 19:26:15 - INFO - __main__ - Step 34376: {'lr': 0.0004432526133406842, 'samples': 6600192, 'steps': 34375, 'loss/train': 0.54055255651474} 08/30/2021 19:26:17 - INFO - __main__ - Step 34377: {'lr': 0.0004432492467341715, 'samples': 6600384, 'steps': 34376, 'loss/train': 1.493737816810608} 08/30/2021 19:26:17 - INFO - __main__ - Step 34378: {'lr': 0.00044324588004058364, 'samples': 6600576, 'steps': 34377, 'loss/train': 1.344374179840088} 08/30/2021 19:26:18 - INFO - __main__ - Step 34379: {'lr': 0.00044324251325992214, 'samples': 6600768, 'steps': 34378, 'loss/train': 1.3997677564620972} 08/30/2021 19:26:18 - INFO - __main__ - Step 34380: {'lr': 0.0004432391463921885, 'samples': 6600960, 'steps': 34379, 'loss/train': 1.1257917881011963} 08/30/2021 19:26:18 - INFO - __main__ - Step 34381: {'lr': 0.00044323577943738437, 'samples': 6601152, 'steps': 34380, 'loss/train': 1.6540206670761108} 08/30/2021 19:26:20 - INFO - __main__ - Step 34382: {'lr': 0.00044323241239551113, 'samples': 6601344, 'steps': 34381, 'loss/train': 1.5172102451324463} 08/30/2021 19:26:20 - INFO - __main__ - Step 34383: {'lr': 0.0004432290452665704, 'samples': 6601536, 'steps': 34382, 'loss/train': 1.7449623346328735} 08/30/2021 19:26:21 - INFO - __main__ - Step 34384: {'lr': 0.00044322567805056356, 'samples': 6601728, 'steps': 34383, 'loss/train': 1.4433776140213013} 08/30/2021 19:26:21 - INFO - __main__ - Step 34385: {'lr': 0.00044322231074749225, 'samples': 6601920, 'steps': 34384, 'loss/train': 1.4767518043518066} 08/30/2021 19:26:21 - INFO - __main__ - Step 34386: {'lr': 0.0004432189433573579, 'samples': 6602112, 'steps': 34385, 'loss/train': 1.5803310871124268} 08/30/2021 19:26:22 - INFO - __main__ - Step 34387: {'lr': 0.00044321557588016214, 'samples': 6602304, 'steps': 34386, 'loss/train': 1.4494335651397705} 08/30/2021 19:26:23 - INFO - __main__ - Step 34388: {'lr': 0.0004432122083159065, 'samples': 6602496, 'steps': 34387, 'loss/train': 1.1938616037368774} 08/30/2021 19:26:24 - INFO - __main__ - Step 34389: {'lr': 0.0004432088406645922, 'samples': 6602688, 'steps': 34388, 'loss/train': 1.8994015455245972} 08/30/2021 19:26:24 - INFO - __main__ - Step 34390: {'lr': 0.00044320547292622114, 'samples': 6602880, 'steps': 34389, 'loss/train': 1.6787949800491333} 08/30/2021 19:26:25 - INFO - __main__ - Step 34391: {'lr': 0.0004432021051007946, 'samples': 6603072, 'steps': 34390, 'loss/train': 1.8606735467910767} 08/30/2021 19:26:25 - INFO - __main__ - Step 34392: {'lr': 0.00044319873718831425, 'samples': 6603264, 'steps': 34391, 'loss/train': 0.8606879115104675} 08/30/2021 19:26:27 - INFO - __main__ - Step 34393: {'lr': 0.00044319536918878156, 'samples': 6603456, 'steps': 34392, 'loss/train': 0.12102912366390228} 08/30/2021 19:26:27 - INFO - __main__ - Step 34394: {'lr': 0.00044319200110219794, 'samples': 6603648, 'steps': 34393, 'loss/train': 1.3255921602249146} 08/30/2021 19:26:28 - INFO - __main__ - Step 34395: {'lr': 0.000443188632928565, 'samples': 6603840, 'steps': 34394, 'loss/train': 2.069284200668335} 08/30/2021 19:26:28 - INFO - __main__ - Step 34396: {'lr': 0.0004431852646678842, 'samples': 6604032, 'steps': 34395, 'loss/train': 0.936872661113739} 08/30/2021 19:26:28 - INFO - __main__ - Step 34397: {'lr': 0.00044318189632015716, 'samples': 6604224, 'steps': 34396, 'loss/train': 1.3372077941894531} 08/30/2021 19:26:30 - INFO - __main__ - Step 34398: {'lr': 0.0004431785278853853, 'samples': 6604416, 'steps': 34397, 'loss/train': 1.3406580686569214} 08/30/2021 19:26:30 - INFO - __main__ - Step 34399: {'lr': 0.0004431751593635702, 'samples': 6604608, 'steps': 34398, 'loss/train': 1.3278084993362427} 08/30/2021 19:26:31 - INFO - __main__ - Step 34400: {'lr': 0.00044317179075471335, 'samples': 6604800, 'steps': 34399, 'loss/train': 0.38800692558288574} 08/30/2021 19:26:31 - INFO - __main__ - Step 34401: {'lr': 0.00044316842205881625, 'samples': 6604992, 'steps': 34400, 'loss/train': 1.2890698909759521} 08/30/2021 19:26:31 - INFO - __main__ - Step 34402: {'lr': 0.00044316505327588054, 'samples': 6605184, 'steps': 34401, 'loss/train': 0.9331830143928528} 08/30/2021 19:26:33 - INFO - __main__ - Step 34403: {'lr': 0.00044316168440590757, 'samples': 6605376, 'steps': 34402, 'loss/train': 1.6600427627563477} 08/30/2021 19:26:33 - INFO - __main__ - Step 34404: {'lr': 0.00044315831544889886, 'samples': 6605568, 'steps': 34403, 'loss/train': 1.3622405529022217} 08/30/2021 19:26:34 - INFO - __main__ - Step 34405: {'lr': 0.0004431549464048561, 'samples': 6605760, 'steps': 34404, 'loss/train': 1.027209997177124} 08/30/2021 19:26:34 - INFO - __main__ - Step 34406: {'lr': 0.0004431515772737806, 'samples': 6605952, 'steps': 34405, 'loss/train': 1.2644612789154053} 08/30/2021 19:26:34 - INFO - __main__ - Step 34407: {'lr': 0.000443148208055674, 'samples': 6606144, 'steps': 34406, 'loss/train': 1.3569592237472534} 08/30/2021 19:26:36 - INFO - __main__ - Step 34408: {'lr': 0.0004431448387505379, 'samples': 6606336, 'steps': 34407, 'loss/train': 1.3876062631607056} 08/30/2021 19:26:37 - INFO - __main__ - Step 34409: {'lr': 0.00044314146935837365, 'samples': 6606528, 'steps': 34408, 'loss/train': 1.5231746435165405} 08/30/2021 19:26:37 - INFO - __main__ - Step 34410: {'lr': 0.0004431380998791828, 'samples': 6606720, 'steps': 34409, 'loss/train': 1.3941922187805176} 08/30/2021 19:26:37 - INFO - __main__ - Step 34411: {'lr': 0.0004431347303129669, 'samples': 6606912, 'steps': 34410, 'loss/train': 0.9178640842437744} 08/30/2021 19:26:38 - INFO - __main__ - Step 34412: {'lr': 0.00044313136065972754, 'samples': 6607104, 'steps': 34411, 'loss/train': 0.030487028881907463} 08/30/2021 19:26:38 - INFO - __main__ - Step 34413: {'lr': 0.0004431279909194661, 'samples': 6607296, 'steps': 34412, 'loss/train': 1.2436041831970215} 08/30/2021 19:26:40 - INFO - __main__ - Step 34414: {'lr': 0.00044312462109218423, 'samples': 6607488, 'steps': 34413, 'loss/train': 1.8023035526275635} 08/30/2021 19:26:40 - INFO - __main__ - Step 34415: {'lr': 0.0004431212511778834, 'samples': 6607680, 'steps': 34414, 'loss/train': 1.4230846166610718} 08/30/2021 19:26:41 - INFO - __main__ - Step 34416: {'lr': 0.000443117881176565, 'samples': 6607872, 'steps': 34415, 'loss/train': 1.2220278978347778} 08/30/2021 19:26:41 - INFO - __main__ - Step 34417: {'lr': 0.00044311451108823075, 'samples': 6608064, 'steps': 34416, 'loss/train': 1.4115710258483887} 08/30/2021 19:26:41 - INFO - __main__ - Step 34418: {'lr': 0.00044311114091288205, 'samples': 6608256, 'steps': 34417, 'loss/train': 1.3294082880020142} 08/30/2021 19:26:43 - INFO - __main__ - Step 34419: {'lr': 0.0004431077706505205, 'samples': 6608448, 'steps': 34418, 'loss/train': 1.5514307022094727} 08/30/2021 19:26:43 - INFO - __main__ - Step 34420: {'lr': 0.0004431044003011475, 'samples': 6608640, 'steps': 34419, 'loss/train': 0.8480591177940369} 08/30/2021 19:26:43 - INFO - __main__ - Step 34421: {'lr': 0.00044310102986476463, 'samples': 6608832, 'steps': 34420, 'loss/train': 1.857121229171753} 08/30/2021 19:26:44 - INFO - __main__ - Step 34422: {'lr': 0.0004430976593413735, 'samples': 6609024, 'steps': 34421, 'loss/train': 1.5511581897735596} 08/30/2021 19:26:44 - INFO - __main__ - Step 34423: {'lr': 0.0004430942887309755, 'samples': 6609216, 'steps': 34422, 'loss/train': 1.3938441276550293} 08/30/2021 19:26:46 - INFO - __main__ - Step 34424: {'lr': 0.00044309091803357216, 'samples': 6609408, 'steps': 34423, 'loss/train': 1.754330039024353} 08/30/2021 19:26:46 - INFO - __main__ - Step 34425: {'lr': 0.0004430875472491651, 'samples': 6609600, 'steps': 34424, 'loss/train': 3.110199213027954} 08/30/2021 19:26:47 - INFO - __main__ - Step 34426: {'lr': 0.0004430841763777557, 'samples': 6609792, 'steps': 34425, 'loss/train': 1.2199982404708862} 08/30/2021 19:26:47 - INFO - __main__ - Step 34427: {'lr': 0.0004430808054193456, 'samples': 6609984, 'steps': 34426, 'loss/train': 1.3279060125350952} 08/30/2021 19:26:47 - INFO - __main__ - Step 34428: {'lr': 0.00044307743437393623, 'samples': 6610176, 'steps': 34427, 'loss/train': 1.2195956707000732} 08/30/2021 19:26:48 - INFO - __main__ - Step 34429: {'lr': 0.0004430740632415292, 'samples': 6610368, 'steps': 34428, 'loss/train': 1.2849218845367432} 08/30/2021 19:26:49 - INFO - __main__ - Step 34430: {'lr': 0.0004430706920221259, 'samples': 6610560, 'steps': 34429, 'loss/train': 0.079468734562397} 08/30/2021 19:26:50 - INFO - __main__ - Step 34431: {'lr': 0.00044306732071572796, 'samples': 6610752, 'steps': 34430, 'loss/train': 1.4782328605651855} 08/30/2021 19:26:50 - INFO - __main__ - Step 34432: {'lr': 0.00044306394932233694, 'samples': 6610944, 'steps': 34431, 'loss/train': 1.4525034427642822} 08/30/2021 19:26:50 - INFO - __main__ - Step 34433: {'lr': 0.0004430605778419542, 'samples': 6611136, 'steps': 34432, 'loss/train': 0.5215873718261719} 08/30/2021 19:26:51 - INFO - __main__ - Step 34434: {'lr': 0.00044305720627458136, 'samples': 6611328, 'steps': 34433, 'loss/train': 1.5125080347061157} 08/30/2021 19:26:52 - INFO - __main__ - Step 34435: {'lr': 0.00044305383462022, 'samples': 6611520, 'steps': 34434, 'loss/train': 0.8998143672943115} 08/30/2021 19:26:53 - INFO - __main__ - Step 34436: {'lr': 0.0004430504628788714, 'samples': 6611712, 'steps': 34435, 'loss/train': 1.93230402469635} 08/30/2021 19:26:53 - INFO - __main__ - Step 34437: {'lr': 0.0004430470910505373, 'samples': 6611904, 'steps': 34436, 'loss/train': 1.4839353561401367} 08/30/2021 19:26:53 - INFO - __main__ - Step 34438: {'lr': 0.00044304371913521926, 'samples': 6612096, 'steps': 34437, 'loss/train': 0.6594424247741699} 08/30/2021 19:26:54 - INFO - __main__ - Step 34439: {'lr': 0.0004430403471329186, 'samples': 6612288, 'steps': 34438, 'loss/train': 1.6658412218093872} 08/30/2021 19:26:55 - INFO - __main__ - Step 34440: {'lr': 0.0004430369750436369, 'samples': 6612480, 'steps': 34439, 'loss/train': 1.7098740339279175} 08/30/2021 19:26:56 - INFO - __main__ - Step 34441: {'lr': 0.0004430336028673758, 'samples': 6612672, 'steps': 34440, 'loss/train': 1.4242730140686035} 08/30/2021 19:26:56 - INFO - __main__ - Step 34442: {'lr': 0.00044303023060413677, 'samples': 6612864, 'steps': 34441, 'loss/train': 1.324416160583496} 08/30/2021 19:26:56 - INFO - __main__ - Step 34443: {'lr': 0.0004430268582539212, 'samples': 6613056, 'steps': 34442, 'loss/train': 1.3261427879333496} 08/30/2021 19:26:57 - INFO - __main__ - Step 34444: {'lr': 0.0004430234858167308, 'samples': 6613248, 'steps': 34443, 'loss/train': 1.37202787399292} 08/30/2021 19:26:59 - INFO - __main__ - Step 34445: {'lr': 0.000443020113292567, 'samples': 6613440, 'steps': 34444, 'loss/train': 1.631679892539978} 08/30/2021 19:26:59 - INFO - __main__ - Step 34446: {'lr': 0.0004430167406814312, 'samples': 6613632, 'steps': 34445, 'loss/train': 1.7860093116760254} 08/30/2021 19:26:59 - INFO - __main__ - Step 34447: {'lr': 0.0004430133679833251, 'samples': 6613824, 'steps': 34446, 'loss/train': 1.346189022064209} 08/30/2021 19:27:00 - INFO - __main__ - Step 34448: {'lr': 0.00044300999519825016, 'samples': 6614016, 'steps': 34447, 'loss/train': 1.6412649154663086} 08/30/2021 19:27:00 - INFO - __main__ - Step 34449: {'lr': 0.00044300662232620784, 'samples': 6614208, 'steps': 34448, 'loss/train': 1.8074865341186523} 08/30/2021 19:27:02 - INFO - __main__ - Step 34450: {'lr': 0.0004430032493671998, 'samples': 6614400, 'steps': 34449, 'loss/train': 0.7451086044311523} 08/30/2021 19:27:02 - INFO - __main__ - Step 34451: {'lr': 0.0004429998763212274, 'samples': 6614592, 'steps': 34450, 'loss/train': 1.337473750114441} 08/30/2021 19:27:03 - INFO - __main__ - Step 34452: {'lr': 0.00044299650318829233, 'samples': 6614784, 'steps': 34451, 'loss/train': 1.1569933891296387} 08/30/2021 19:27:03 - INFO - __main__ - Step 34453: {'lr': 0.0004429931299683959, 'samples': 6614976, 'steps': 34452, 'loss/train': 1.5492223501205444} 08/30/2021 19:27:03 - INFO - __main__ - Step 34454: {'lr': 0.0004429897566615398, 'samples': 6615168, 'steps': 34453, 'loss/train': 1.2494310140609741} 08/30/2021 19:27:04 - INFO - __main__ - Step 34455: {'lr': 0.0004429863832677255, 'samples': 6615360, 'steps': 34454, 'loss/train': 1.5201736688613892} 08/30/2021 19:27:05 - INFO - __main__ - Step 34456: {'lr': 0.0004429830097869545, 'samples': 6615552, 'steps': 34455, 'loss/train': 0.14513061940670013} 08/30/2021 19:27:06 - INFO - __main__ - Step 34457: {'lr': 0.0004429796362192283, 'samples': 6615744, 'steps': 34456, 'loss/train': 1.0094025135040283} 08/30/2021 19:27:06 - INFO - __main__ - Step 34458: {'lr': 0.0004429762625645485, 'samples': 6615936, 'steps': 34457, 'loss/train': 1.3376976251602173} 08/30/2021 19:27:06 - INFO - __main__ - Step 34459: {'lr': 0.0004429728888229166, 'samples': 6616128, 'steps': 34458, 'loss/train': 1.3319414854049683} 08/30/2021 19:27:07 - INFO - __main__ - Step 34460: {'lr': 0.000442969514994334, 'samples': 6616320, 'steps': 34459, 'loss/train': 1.7238891124725342} 08/30/2021 19:27:09 - INFO - __main__ - Step 34461: {'lr': 0.0004429661410788024, 'samples': 6616512, 'steps': 34460, 'loss/train': 1.6685853004455566} 08/30/2021 19:27:09 - INFO - __main__ - Step 34462: {'lr': 0.00044296276707632323, 'samples': 6616704, 'steps': 34461, 'loss/train': 1.4678622484207153} 08/30/2021 19:27:10 - INFO - __main__ - Step 34463: {'lr': 0.000442959392986898, 'samples': 6616896, 'steps': 34462, 'loss/train': 1.3602629899978638} 08/30/2021 19:27:10 - INFO - __main__ - Step 34464: {'lr': 0.0004429560188105282, 'samples': 6617088, 'steps': 34463, 'loss/train': 1.3855806589126587} 08/30/2021 19:27:10 - INFO - __main__ - Step 34465: {'lr': 0.00044295264454721544, 'samples': 6617280, 'steps': 34464, 'loss/train': 0.08018211275339127} 08/30/2021 19:27:11 - INFO - __main__ - Step 34466: {'lr': 0.0004429492701969612, 'samples': 6617472, 'steps': 34465, 'loss/train': 0.2471642941236496} 08/30/2021 19:27:12 - INFO - __main__ - Step 34467: {'lr': 0.00044294589575976696, 'samples': 6617664, 'steps': 34466, 'loss/train': 1.3627315759658813} 08/30/2021 19:27:13 - INFO - __main__ - Step 34468: {'lr': 0.00044294252123563434, 'samples': 6617856, 'steps': 34467, 'loss/train': 1.3598071336746216} 08/30/2021 19:27:13 - INFO - __main__ - Step 34469: {'lr': 0.00044293914662456475, 'samples': 6618048, 'steps': 34468, 'loss/train': 1.3098459243774414} 08/30/2021 19:27:13 - INFO - __main__ - Step 34470: {'lr': 0.00044293577192655977, 'samples': 6618240, 'steps': 34469, 'loss/train': 1.1171422004699707} 08/30/2021 19:27:14 - INFO - __main__ - Step 34471: {'lr': 0.0004429323971416209, 'samples': 6618432, 'steps': 34470, 'loss/train': 1.1799956560134888} 08/30/2021 19:27:15 - INFO - __main__ - Step 34472: {'lr': 0.0004429290222697497, 'samples': 6618624, 'steps': 34471, 'loss/train': 1.2923181056976318} 08/30/2021 19:27:16 - INFO - __main__ - Step 34473: {'lr': 0.0004429256473109476, 'samples': 6618816, 'steps': 34472, 'loss/train': 1.2467824220657349} 08/30/2021 19:27:16 - INFO - __main__ - Step 34474: {'lr': 0.0004429222722652162, 'samples': 6619008, 'steps': 34473, 'loss/train': 0.024378672242164612} 08/30/2021 19:27:17 - INFO - __main__ - Step 34475: {'lr': 0.0004429188971325571, 'samples': 6619200, 'steps': 34474, 'loss/train': 1.4998093843460083} 08/30/2021 19:27:17 - INFO - __main__ - Step 34476: {'lr': 0.00044291552191297155, 'samples': 6619392, 'steps': 34475, 'loss/train': 1.4220741987228394} 08/30/2021 19:27:17 - INFO - __main__ - Step 34477: {'lr': 0.0004429121466064614, 'samples': 6619584, 'steps': 34476, 'loss/train': 2.0970053672790527} 08/30/2021 19:27:19 - INFO - __main__ - Step 34478: {'lr': 0.0004429087712130279, 'samples': 6619776, 'steps': 34477, 'loss/train': 1.473771572113037} 08/30/2021 19:27:19 - INFO - __main__ - Step 34479: {'lr': 0.00044290539573267276, 'samples': 6619968, 'steps': 34478, 'loss/train': 1.2748184204101562} 08/30/2021 19:27:20 - INFO - __main__ - Step 34480: {'lr': 0.00044290202016539736, 'samples': 6620160, 'steps': 34479, 'loss/train': 1.4546483755111694} 08/30/2021 19:27:20 - INFO - __main__ - Step 34481: {'lr': 0.0004428986445112033, 'samples': 6620352, 'steps': 34480, 'loss/train': 1.1653300523757935} 08/30/2021 19:27:21 - INFO - __main__ - Step 34482: {'lr': 0.00044289526877009213, 'samples': 6620544, 'steps': 34481, 'loss/train': 1.4459903240203857} 08/30/2021 19:27:21 - INFO - __main__ - Step 34483: {'lr': 0.00044289189294206534, 'samples': 6620736, 'steps': 34482, 'loss/train': 1.0771769285202026} 08/30/2021 19:27:22 - INFO - __main__ - Step 34484: {'lr': 0.0004428885170271244, 'samples': 6620928, 'steps': 34483, 'loss/train': 1.309779405593872} 08/30/2021 19:27:23 - INFO - __main__ - Step 34485: {'lr': 0.0004428851410252709, 'samples': 6621120, 'steps': 34484, 'loss/train': 1.2912912368774414} 08/30/2021 19:27:23 - INFO - __main__ - Step 34486: {'lr': 0.0004428817649365063, 'samples': 6621312, 'steps': 34485, 'loss/train': 0.8086441159248352} 08/30/2021 19:27:24 - INFO - __main__ - Step 34487: {'lr': 0.0004428783887608321, 'samples': 6621504, 'steps': 34486, 'loss/train': 1.2254034280776978} 08/30/2021 19:27:24 - INFO - __main__ - Step 34488: {'lr': 0.00044287501249824996, 'samples': 6621696, 'steps': 34487, 'loss/train': 1.6118260622024536} 08/30/2021 19:27:26 - INFO - __main__ - Step 34489: {'lr': 0.0004428716361487613, 'samples': 6621888, 'steps': 34488, 'loss/train': 4.752957820892334} 08/30/2021 19:27:26 - INFO - __main__ - Step 34490: {'lr': 0.0004428682597123677, 'samples': 6622080, 'steps': 34489, 'loss/train': 0.2814444601535797} 08/30/2021 19:27:26 - INFO - __main__ - Step 34491: {'lr': 0.0004428648831890705, 'samples': 6622272, 'steps': 34490, 'loss/train': 1.516649603843689} 08/30/2021 19:27:27 - INFO - __main__ - Step 34492: {'lr': 0.0004428615065788715, 'samples': 6622464, 'steps': 34491, 'loss/train': 1.6049208641052246} 08/30/2021 19:27:27 - INFO - __main__ - Step 34493: {'lr': 0.00044285812988177197, 'samples': 6622656, 'steps': 34492, 'loss/train': 1.1035348176956177} 08/30/2021 19:27:29 - INFO - __main__ - Step 34494: {'lr': 0.0004428547530977736, 'samples': 6622848, 'steps': 34493, 'loss/train': 1.8791131973266602} 08/30/2021 19:27:29 - INFO - __main__ - Step 34495: {'lr': 0.0004428513762268779, 'samples': 6623040, 'steps': 34494, 'loss/train': 0.6788734793663025} 08/30/2021 19:27:29 - INFO - __main__ - Step 34496: {'lr': 0.00044284799926908627, 'samples': 6623232, 'steps': 34495, 'loss/train': 1.5275757312774658} 08/30/2021 19:27:30 - INFO - __main__ - Step 34497: {'lr': 0.0004428446222244004, 'samples': 6623424, 'steps': 34496, 'loss/train': 1.2486664056777954} 08/30/2021 19:27:30 - INFO - __main__ - Step 34498: {'lr': 0.0004428412450928216, 'samples': 6623616, 'steps': 34497, 'loss/train': 1.8646252155303955} 08/30/2021 19:27:32 - INFO - __main__ - Step 34499: {'lr': 0.00044283786787435156, 'samples': 6623808, 'steps': 34498, 'loss/train': 2.15881085395813} 08/30/2021 19:27:33 - INFO - __main__ - Step 34500: {'lr': 0.0004428344905689917, 'samples': 6624000, 'steps': 34499, 'loss/train': 1.4565550088882446} 08/30/2021 19:27:33 - INFO - __main__ - Step 34501: {'lr': 0.0004428311131767437, 'samples': 6624192, 'steps': 34500, 'loss/train': 1.437974452972412} 08/30/2021 19:27:33 - INFO - __main__ - Step 34502: {'lr': 0.0004428277356976089, 'samples': 6624384, 'steps': 34501, 'loss/train': 2.451415777206421} 08/30/2021 19:27:34 - INFO - __main__ - Step 34503: {'lr': 0.0004428243581315889, 'samples': 6624576, 'steps': 34502, 'loss/train': 1.4674867391586304} 08/30/2021 19:27:35 - INFO - __main__ - Step 34504: {'lr': 0.0004428209804786853, 'samples': 6624768, 'steps': 34503, 'loss/train': 0.14034180343151093} 08/30/2021 19:27:36 - INFO - __main__ - Step 34505: {'lr': 0.0004428176027388995, 'samples': 6624960, 'steps': 34504, 'loss/train': 1.5051461458206177} 08/30/2021 19:27:36 - INFO - __main__ - Step 34506: {'lr': 0.0004428142249122331, 'samples': 6625152, 'steps': 34505, 'loss/train': 1.3033932447433472} 08/30/2021 19:27:36 - INFO - __main__ - Step 34507: {'lr': 0.00044281084699868747, 'samples': 6625344, 'steps': 34506, 'loss/train': 1.6993290185928345} 08/30/2021 19:27:37 - INFO - __main__ - Step 34508: {'lr': 0.0004428074689982643, 'samples': 6625536, 'steps': 34507, 'loss/train': 1.1897045373916626} 08/30/2021 19:27:37 - INFO - __main__ - Step 34509: {'lr': 0.0004428040909109651, 'samples': 6625728, 'steps': 34508, 'loss/train': 1.6434334516525269} 08/30/2021 19:27:39 - INFO - __main__ - Step 34510: {'lr': 0.00044280071273679133, 'samples': 6625920, 'steps': 34509, 'loss/train': 0.6318305134773254} 08/30/2021 19:27:39 - INFO - __main__ - Step 34511: {'lr': 0.00044279733447574456, 'samples': 6626112, 'steps': 34510, 'loss/train': 1.4127222299575806} 08/30/2021 19:27:39 - INFO - __main__ - Step 34512: {'lr': 0.00044279395612782625, 'samples': 6626304, 'steps': 34511, 'loss/train': 1.2508999109268188} 08/30/2021 19:27:40 - INFO - __main__ - Step 34513: {'lr': 0.0004427905776930379, 'samples': 6626496, 'steps': 34512, 'loss/train': 1.570178508758545} 08/30/2021 19:27:40 - INFO - __main__ - Step 34514: {'lr': 0.0004427871991713812, 'samples': 6626688, 'steps': 34513, 'loss/train': 1.290770411491394} 08/30/2021 19:27:42 - INFO - __main__ - Step 34515: {'lr': 0.0004427838205628575, 'samples': 6626880, 'steps': 34514, 'loss/train': 1.4480304718017578} 08/30/2021 19:27:42 - INFO - __main__ - Step 34516: {'lr': 0.0004427804418674684, 'samples': 6627072, 'steps': 34515, 'loss/train': 1.6381162405014038} 08/30/2021 19:27:42 - INFO - __main__ - Step 34517: {'lr': 0.00044277706308521543, 'samples': 6627264, 'steps': 34516, 'loss/train': 1.5167180299758911} 08/30/2021 19:27:43 - INFO - __main__ - Step 34518: {'lr': 0.0004427736842161001, 'samples': 6627456, 'steps': 34517, 'loss/train': 1.8896290063858032} 08/30/2021 19:27:43 - INFO - __main__ - Step 34519: {'lr': 0.00044277030526012386, 'samples': 6627648, 'steps': 34518, 'loss/train': 1.2373080253601074} 08/30/2021 19:27:45 - INFO - __main__ - Step 34520: {'lr': 0.0004427669262172883, 'samples': 6627840, 'steps': 34519, 'loss/train': 1.4679688215255737} 08/30/2021 19:27:45 - INFO - __main__ - Step 34521: {'lr': 0.000442763547087595, 'samples': 6628032, 'steps': 34520, 'loss/train': 2.0088555812835693} 08/30/2021 19:27:46 - INFO - __main__ - Step 34522: {'lr': 0.00044276016787104535, 'samples': 6628224, 'steps': 34521, 'loss/train': 1.9846179485321045} 08/30/2021 19:27:46 - INFO - __main__ - Step 34523: {'lr': 0.000442756788567641, 'samples': 6628416, 'steps': 34522, 'loss/train': 0.6158360242843628} 08/30/2021 19:27:46 - INFO - __main__ - Step 34524: {'lr': 0.0004427534091773834, 'samples': 6628608, 'steps': 34523, 'loss/train': 1.708936333656311} 08/30/2021 19:27:48 - INFO - __main__ - Step 34525: {'lr': 0.00044275002970027403, 'samples': 6628800, 'steps': 34524, 'loss/train': 1.1619412899017334} 08/30/2021 19:27:49 - INFO - __main__ - Step 34526: {'lr': 0.00044274665013631457, 'samples': 6628992, 'steps': 34525, 'loss/train': 1.3224120140075684} 08/30/2021 19:27:49 - INFO - __main__ - Step 34527: {'lr': 0.0004427432704855064, 'samples': 6629184, 'steps': 34526, 'loss/train': 1.686940312385559} 08/30/2021 19:27:49 - INFO - __main__ - Step 34528: {'lr': 0.000442739890747851, 'samples': 6629376, 'steps': 34527, 'loss/train': 0.1830187737941742} 08/30/2021 19:27:50 - INFO - __main__ - Step 34529: {'lr': 0.0004427365109233502, 'samples': 6629568, 'steps': 34528, 'loss/train': 0.5719832181930542} 08/30/2021 19:27:50 - INFO - __main__ - Step 34530: {'lr': 0.00044273313101200507, 'samples': 6629760, 'steps': 34529, 'loss/train': 1.2203422784805298} 08/30/2021 19:27:51 - INFO - __main__ - Step 34531: {'lr': 0.00044272975101381754, 'samples': 6629952, 'steps': 34530, 'loss/train': 1.482810616493225} 08/30/2021 19:27:52 - INFO - __main__ - Step 34532: {'lr': 0.0004427263709287889, 'samples': 6630144, 'steps': 34531, 'loss/train': 1.3061579465866089} 08/30/2021 19:27:52 - INFO - __main__ - Step 34533: {'lr': 0.00044272299075692067, 'samples': 6630336, 'steps': 34532, 'loss/train': 1.6461799144744873} 08/30/2021 19:27:53 - INFO - __main__ - Step 34534: {'lr': 0.0004427196104982145, 'samples': 6630528, 'steps': 34533, 'loss/train': 1.2202532291412354} 08/30/2021 19:27:53 - INFO - __main__ - Step 34535: {'lr': 0.0004427162301526718, 'samples': 6630720, 'steps': 34534, 'loss/train': 1.492713451385498} 08/30/2021 19:27:54 - INFO - __main__ - Step 34536: {'lr': 0.0004427128497202941, 'samples': 6630912, 'steps': 34535, 'loss/train': 0.9139453768730164} 08/30/2021 19:27:55 - INFO - __main__ - Step 34537: {'lr': 0.00044270946920108305, 'samples': 6631104, 'steps': 34536, 'loss/train': 0.5907489061355591} 08/30/2021 19:27:55 - INFO - __main__ - Step 34538: {'lr': 0.00044270608859504006, 'samples': 6631296, 'steps': 34537, 'loss/train': 1.5253498554229736} 08/30/2021 19:27:56 - INFO - __main__ - Step 34539: {'lr': 0.0004427027079021667, 'samples': 6631488, 'steps': 34538, 'loss/train': 1.3501640558242798} 08/30/2021 19:27:56 - INFO - __main__ - Step 34540: {'lr': 0.0004426993271224645, 'samples': 6631680, 'steps': 34539, 'loss/train': 1.6406875848770142} 08/30/2021 19:27:57 - INFO - __main__ - Step 34541: {'lr': 0.0004426959462559349, 'samples': 6631872, 'steps': 34540, 'loss/train': 1.1325690746307373} 08/30/2021 19:27:58 - INFO - __main__ - Step 34542: {'lr': 0.0004426925653025795, 'samples': 6632064, 'steps': 34541, 'loss/train': 1.8664443492889404} 08/30/2021 19:27:58 - INFO - __main__ - Step 34543: {'lr': 0.0004426891842623998, 'samples': 6632256, 'steps': 34542, 'loss/train': 1.5031765699386597} 08/30/2021 19:27:58 - INFO - __main__ - Step 34544: {'lr': 0.0004426858031353973, 'samples': 6632448, 'steps': 34543, 'loss/train': 1.265485167503357} 08/30/2021 19:27:59 - INFO - __main__ - Step 34545: {'lr': 0.0004426824219215736, 'samples': 6632640, 'steps': 34544, 'loss/train': 1.4783307313919067} 08/30/2021 19:28:00 - INFO - __main__ - Step 34546: {'lr': 0.00044267904062093014, 'samples': 6632832, 'steps': 34545, 'loss/train': 0.8809460997581482} 08/30/2021 19:28:01 - INFO - __main__ - Step 34547: {'lr': 0.0004426756592334685, 'samples': 6633024, 'steps': 34546, 'loss/train': 1.5961167812347412} 08/30/2021 19:28:01 - INFO - __main__ - Step 34548: {'lr': 0.0004426722777591902, 'samples': 6633216, 'steps': 34547, 'loss/train': 0.769387423992157} 08/30/2021 19:28:01 - INFO - __main__ - Step 34549: {'lr': 0.00044266889619809665, 'samples': 6633408, 'steps': 34548, 'loss/train': 1.2212328910827637} 08/30/2021 19:28:02 - INFO - __main__ - Step 34550: {'lr': 0.00044266551455018953, 'samples': 6633600, 'steps': 34549, 'loss/train': 1.6502959728240967} 08/30/2021 19:28:04 - INFO - __main__ - Step 34551: {'lr': 0.0004426621328154703, 'samples': 6633792, 'steps': 34550, 'loss/train': 1.1621997356414795} 08/30/2021 19:28:04 - INFO - __main__ - Step 34552: {'lr': 0.0004426587509939405, 'samples': 6633984, 'steps': 34551, 'loss/train': 1.7934597730636597} 08/30/2021 19:28:04 - INFO - __main__ - Step 34553: {'lr': 0.0004426553690856016, 'samples': 6634176, 'steps': 34552, 'loss/train': 1.1838699579238892} 08/30/2021 19:28:05 - INFO - __main__ - Step 34554: {'lr': 0.0004426519870904552, 'samples': 6634368, 'steps': 34553, 'loss/train': 1.638792634010315} 08/30/2021 19:28:05 - INFO - __main__ - Step 34555: {'lr': 0.0004426486050085028, 'samples': 6634560, 'steps': 34554, 'loss/train': 2.1602914333343506} 08/30/2021 19:28:07 - INFO - __main__ - Step 34556: {'lr': 0.0004426452228397458, 'samples': 6634752, 'steps': 34555, 'loss/train': 1.1738427877426147} 08/30/2021 19:28:07 - INFO - __main__ - Step 34557: {'lr': 0.000442641840584186, 'samples': 6634944, 'steps': 34556, 'loss/train': 2.541248321533203} 08/30/2021 19:28:08 - INFO - __main__ - Step 34558: {'lr': 0.00044263845824182467, 'samples': 6635136, 'steps': 34557, 'loss/train': 1.4648534059524536} 08/30/2021 19:28:08 - INFO - __main__ - Step 34559: {'lr': 0.0004426350758126634, 'samples': 6635328, 'steps': 34558, 'loss/train': 2.1016812324523926} 08/30/2021 19:28:08 - INFO - __main__ - Step 34560: {'lr': 0.0004426316932967038, 'samples': 6635520, 'steps': 34559, 'loss/train': 1.349694013595581} 08/30/2021 19:28:10 - INFO - __main__ - Step 34561: {'lr': 0.0004426283106939473, 'samples': 6635712, 'steps': 34560, 'loss/train': 1.9669362306594849} 08/30/2021 19:28:10 - INFO - __main__ - Step 34562: {'lr': 0.00044262492800439547, 'samples': 6635904, 'steps': 34561, 'loss/train': 1.9280204772949219} 08/30/2021 19:28:11 - INFO - __main__ - Step 34563: {'lr': 0.00044262154522804986, 'samples': 6636096, 'steps': 34562, 'loss/train': 1.3438531160354614} 08/30/2021 19:28:11 - INFO - __main__ - Step 34564: {'lr': 0.00044261816236491186, 'samples': 6636288, 'steps': 34563, 'loss/train': 0.960212230682373} 08/30/2021 19:28:11 - INFO - __main__ - Step 34565: {'lr': 0.00044261477941498316, 'samples': 6636480, 'steps': 34564, 'loss/train': 1.8634120225906372} 08/30/2021 19:28:13 - INFO - __main__ - Step 34566: {'lr': 0.0004426113963782652, 'samples': 6636672, 'steps': 34565, 'loss/train': 1.4474068880081177} 08/30/2021 19:28:13 - INFO - __main__ - Step 34567: {'lr': 0.00044260801325475953, 'samples': 6636864, 'steps': 34566, 'loss/train': 1.5259560346603394} 08/30/2021 19:28:14 - INFO - __main__ - Step 34568: {'lr': 0.0004426046300444676, 'samples': 6637056, 'steps': 34567, 'loss/train': 1.513583779335022} 08/30/2021 19:28:14 - INFO - __main__ - Step 34569: {'lr': 0.000442601246747391, 'samples': 6637248, 'steps': 34568, 'loss/train': 0.9271699786186218} 08/30/2021 19:28:14 - INFO - __main__ - Step 34570: {'lr': 0.0004425978633635313, 'samples': 6637440, 'steps': 34569, 'loss/train': 1.5802444219589233} 08/30/2021 19:28:15 - INFO - __main__ - Step 34571: {'lr': 0.0004425944798928899, 'samples': 6637632, 'steps': 34570, 'loss/train': 0.8644600510597229} 08/30/2021 19:28:16 - INFO - __main__ - Step 34572: {'lr': 0.0004425910963354685, 'samples': 6637824, 'steps': 34571, 'loss/train': 1.5983903408050537} 08/30/2021 19:28:17 - INFO - __main__ - Step 34573: {'lr': 0.0004425877126912685, 'samples': 6638016, 'steps': 34572, 'loss/train': 1.1706236600875854} 08/30/2021 19:28:17 - INFO - __main__ - Step 34574: {'lr': 0.00044258432896029145, 'samples': 6638208, 'steps': 34573, 'loss/train': 1.072049617767334} 08/30/2021 19:28:17 - INFO - __main__ - Step 34575: {'lr': 0.00044258094514253876, 'samples': 6638400, 'steps': 34574, 'loss/train': 1.3613985776901245} 08/30/2021 19:28:18 - INFO - __main__ - Step 34576: {'lr': 0.00044257756123801216, 'samples': 6638592, 'steps': 34575, 'loss/train': 1.8122700452804565} 08/30/2021 19:28:19 - INFO - __main__ - Step 34577: {'lr': 0.0004425741772467131, 'samples': 6638784, 'steps': 34576, 'loss/train': 1.3815467357635498} 08/30/2021 19:28:20 - INFO - __main__ - Step 34578: {'lr': 0.0004425707931686431, 'samples': 6638976, 'steps': 34577, 'loss/train': 0.6512845754623413} 08/30/2021 19:28:20 - INFO - __main__ - Step 34579: {'lr': 0.00044256740900380364, 'samples': 6639168, 'steps': 34578, 'loss/train': 0.5899108648300171} 08/30/2021 19:28:20 - INFO - __main__ - Step 34580: {'lr': 0.0004425640247521963, 'samples': 6639360, 'steps': 34579, 'loss/train': 1.639444351196289} 08/30/2021 19:28:21 - INFO - __main__ - Step 34581: {'lr': 0.00044256064041382255, 'samples': 6639552, 'steps': 34580, 'loss/train': 1.121112585067749} 08/30/2021 19:28:22 - INFO - __main__ - Step 34582: {'lr': 0.0004425572559886839, 'samples': 6639744, 'steps': 34581, 'loss/train': 1.2499206066131592} 08/30/2021 19:28:23 - INFO - __main__ - Step 34583: {'lr': 0.00044255387147678206, 'samples': 6639936, 'steps': 34582, 'loss/train': 0.7356665134429932} 08/30/2021 19:28:23 - INFO - __main__ - Step 34584: {'lr': 0.0004425504868781183, 'samples': 6640128, 'steps': 34583, 'loss/train': 0.6532497406005859} 08/30/2021 19:28:24 - INFO - __main__ - Step 34585: {'lr': 0.0004425471021926943, 'samples': 6640320, 'steps': 34584, 'loss/train': 1.4160295724868774} 08/30/2021 19:28:24 - INFO - __main__ - Step 34586: {'lr': 0.0004425437174205115, 'samples': 6640512, 'steps': 34585, 'loss/train': 1.1702860593795776} 08/30/2021 19:28:26 - INFO - __main__ - Step 34587: {'lr': 0.00044254033256157154, 'samples': 6640704, 'steps': 34586, 'loss/train': 1.3929725885391235} 08/30/2021 19:28:26 - INFO - __main__ - Step 34588: {'lr': 0.0004425369476158759, 'samples': 6640896, 'steps': 34587, 'loss/train': 1.1652488708496094} 08/30/2021 19:28:26 - INFO - __main__ - Step 34589: {'lr': 0.000442533562583426, 'samples': 6641088, 'steps': 34588, 'loss/train': 1.1288782358169556} 08/30/2021 19:28:27 - INFO - __main__ - Step 34590: {'lr': 0.00044253017746422355, 'samples': 6641280, 'steps': 34589, 'loss/train': 1.6927356719970703} 08/30/2021 19:28:27 - INFO - __main__ - Step 34591: {'lr': 0.00044252679225826984, 'samples': 6641472, 'steps': 34590, 'loss/train': 2.002218246459961} 08/30/2021 19:28:28 - INFO - __main__ - Step 34592: {'lr': 0.0004425234069655666, 'samples': 6641664, 'steps': 34591, 'loss/train': 2.097356081008911} 08/30/2021 19:28:29 - INFO - __main__ - Step 34593: {'lr': 0.0004425200215861153, 'samples': 6641856, 'steps': 34592, 'loss/train': 1.1375408172607422} 08/30/2021 19:28:29 - INFO - __main__ - Step 34594: {'lr': 0.00044251663611991743, 'samples': 6642048, 'steps': 34593, 'loss/train': 1.5154321193695068} 08/30/2021 19:28:30 - INFO - __main__ - Step 34595: {'lr': 0.0004425132505669745, 'samples': 6642240, 'steps': 34594, 'loss/train': 1.4113093614578247} 08/30/2021 19:28:30 - INFO - __main__ - Step 34596: {'lr': 0.00044250986492728805, 'samples': 6642432, 'steps': 34595, 'loss/train': 2.0654656887054443} 08/30/2021 19:28:31 - INFO - __main__ - Step 34597: {'lr': 0.0004425064792008597, 'samples': 6642624, 'steps': 34596, 'loss/train': 1.338316798210144} 08/30/2021 19:28:32 - INFO - __main__ - Step 34598: {'lr': 0.0004425030933876909, 'samples': 6642816, 'steps': 34597, 'loss/train': 1.8056979179382324} 08/30/2021 19:28:32 - INFO - __main__ - Step 34599: {'lr': 0.0004424997074877831, 'samples': 6643008, 'steps': 34598, 'loss/train': 1.3419913053512573} 08/30/2021 19:28:33 - INFO - __main__ - Step 34600: {'lr': 0.00044249632150113806, 'samples': 6643200, 'steps': 34599, 'loss/train': 1.241982102394104} 08/30/2021 19:28:33 - INFO - __main__ - Step 34601: {'lr': 0.000442492935427757, 'samples': 6643392, 'steps': 34600, 'loss/train': 1.4011131525039673} 08/30/2021 19:28:33 - INFO - __main__ - Step 34602: {'lr': 0.00044248954926764164, 'samples': 6643584, 'steps': 34601, 'loss/train': 1.1405445337295532} 08/30/2021 19:28:35 - INFO - __main__ - Step 34603: {'lr': 0.0004424861630207935, 'samples': 6643776, 'steps': 34602, 'loss/train': 1.6157505512237549} 08/30/2021 19:28:35 - INFO - __main__ - Step 34604: {'lr': 0.00044248277668721396, 'samples': 6643968, 'steps': 34603, 'loss/train': 1.084503412246704} 08/30/2021 19:28:35 - INFO - __main__ - Step 34605: {'lr': 0.00044247939026690475, 'samples': 6644160, 'steps': 34604, 'loss/train': 1.842009425163269} 08/30/2021 19:28:36 - INFO - __main__ - Step 34606: {'lr': 0.0004424760037598673, 'samples': 6644352, 'steps': 34605, 'loss/train': 1.3989065885543823} 08/30/2021 19:28:36 - INFO - __main__ - Step 34607: {'lr': 0.00044247261716610307, 'samples': 6644544, 'steps': 34606, 'loss/train': 1.432049036026001} 08/30/2021 19:28:38 - INFO - __main__ - Step 34608: {'lr': 0.0004424692304856136, 'samples': 6644736, 'steps': 34607, 'loss/train': 1.508874773979187} 08/30/2021 19:28:39 - INFO - __main__ - Step 34609: {'lr': 0.0004424658437184006, 'samples': 6644928, 'steps': 34608, 'loss/train': 2.344315528869629} 08/30/2021 19:28:39 - INFO - __main__ - Step 34610: {'lr': 0.0004424624568644654, 'samples': 6645120, 'steps': 34609, 'loss/train': 1.7382147312164307} 08/30/2021 19:28:39 - INFO - __main__ - Step 34611: {'lr': 0.00044245906992380955, 'samples': 6645312, 'steps': 34610, 'loss/train': 1.5767616033554077} 08/30/2021 19:28:40 - INFO - __main__ - Step 34612: {'lr': 0.0004424556828964347, 'samples': 6645504, 'steps': 34611, 'loss/train': 1.6449493169784546} 08/30/2021 19:28:41 - INFO - __main__ - Step 34613: {'lr': 0.0004424522957823422, 'samples': 6645696, 'steps': 34612, 'loss/train': 1.6256276369094849} 08/30/2021 19:28:42 - INFO - __main__ - Step 34614: {'lr': 0.00044244890858153376, 'samples': 6645888, 'steps': 34613, 'loss/train': 0.7414907813072205} 08/30/2021 19:28:42 - INFO - __main__ - Step 34615: {'lr': 0.00044244552129401075, 'samples': 6646080, 'steps': 34614, 'loss/train': 1.420929193496704} 08/30/2021 19:28:43 - INFO - __main__ - Step 34616: {'lr': 0.0004424421339197747, 'samples': 6646272, 'steps': 34615, 'loss/train': 1.387358546257019} 08/30/2021 19:28:43 - INFO - __main__ - Step 34617: {'lr': 0.00044243874645882733, 'samples': 6646464, 'steps': 34616, 'loss/train': 1.2828692197799683} 08/30/2021 19:28:45 - INFO - __main__ - Step 34618: {'lr': 0.0004424353589111699, 'samples': 6646656, 'steps': 34617, 'loss/train': 1.1269830465316772} 08/30/2021 19:28:46 - INFO - __main__ - Step 34619: {'lr': 0.0004424319712768041, 'samples': 6646848, 'steps': 34618, 'loss/train': 0.9125427007675171} 08/30/2021 19:28:46 - INFO - __main__ - Step 34620: {'lr': 0.00044242858355573143, 'samples': 6647040, 'steps': 34619, 'loss/train': 0.7687682509422302} 08/30/2021 19:28:46 - INFO - __main__ - Step 34621: {'lr': 0.00044242519574795347, 'samples': 6647232, 'steps': 34620, 'loss/train': 0.03656759113073349} 08/30/2021 19:28:47 - INFO - __main__ - Step 34622: {'lr': 0.00044242180785347164, 'samples': 6647424, 'steps': 34621, 'loss/train': 0.030534954741597176} 08/30/2021 19:28:47 - INFO - __main__ - Step 34623: {'lr': 0.00044241841987228747, 'samples': 6647616, 'steps': 34622, 'loss/train': 1.1314226388931274} 08/30/2021 19:28:47 - INFO - __main__ - Step 34624: {'lr': 0.00044241503180440263, 'samples': 6647808, 'steps': 34623, 'loss/train': 1.2687695026397705} 08/30/2021 19:28:49 - INFO - __main__ - Step 34625: {'lr': 0.0004424116436498185, 'samples': 6648000, 'steps': 34624, 'loss/train': 0.9782544374465942} 08/30/2021 19:28:49 - INFO - __main__ - Step 34626: {'lr': 0.0004424082554085366, 'samples': 6648192, 'steps': 34625, 'loss/train': 1.5050990581512451} 08/30/2021 19:28:50 - INFO - __main__ - Step 34627: {'lr': 0.0004424048670805586, 'samples': 6648384, 'steps': 34626, 'loss/train': 1.2192565202713013} 08/30/2021 19:28:50 - INFO - __main__ - Step 34628: {'lr': 0.0004424014786658859, 'samples': 6648576, 'steps': 34627, 'loss/train': 0.9493632912635803} 08/30/2021 19:28:51 - INFO - __main__ - Step 34629: {'lr': 0.00044239809016452, 'samples': 6648768, 'steps': 34628, 'loss/train': 1.5128798484802246} 08/30/2021 19:28:52 - INFO - __main__ - Step 34630: {'lr': 0.00044239470157646254, 'samples': 6648960, 'steps': 34629, 'loss/train': 1.3421119451522827} 08/30/2021 19:28:53 - INFO - __main__ - Step 34631: {'lr': 0.000442391312901715, 'samples': 6649152, 'steps': 34630, 'loss/train': 1.1037216186523438} 08/30/2021 19:28:53 - INFO - __main__ - Step 34632: {'lr': 0.0004423879241402788, 'samples': 6649344, 'steps': 34631, 'loss/train': 1.7800251245498657} 08/30/2021 19:28:53 - INFO - __main__ - Step 34633: {'lr': 0.00044238453529215575, 'samples': 6649536, 'steps': 34632, 'loss/train': 1.9754528999328613} 08/30/2021 19:28:54 - INFO - __main__ - Step 34634: {'lr': 0.00044238114635734713, 'samples': 6649728, 'steps': 34633, 'loss/train': 1.574794888496399} 08/30/2021 19:28:54 - INFO - __main__ - Step 34635: {'lr': 0.0004423777573358545, 'samples': 6649920, 'steps': 34634, 'loss/train': 1.3289318084716797} 08/30/2021 19:28:56 - INFO - __main__ - Step 34636: {'lr': 0.0004423743682276794, 'samples': 6650112, 'steps': 34635, 'loss/train': 1.5770080089569092} 08/30/2021 19:28:56 - INFO - __main__ - Step 34637: {'lr': 0.0004423709790328235, 'samples': 6650304, 'steps': 34636, 'loss/train': 1.1990138292312622} 08/30/2021 19:28:57 - INFO - __main__ - Step 34638: {'lr': 0.0004423675897512881, 'samples': 6650496, 'steps': 34637, 'loss/train': 0.026132598519325256} 08/30/2021 19:28:57 - INFO - __main__ - Step 34639: {'lr': 0.0004423642003830748, 'samples': 6650688, 'steps': 34638, 'loss/train': 1.4408581256866455} 08/30/2021 19:28:57 - INFO - __main__ - Step 34640: {'lr': 0.00044236081092818527, 'samples': 6650880, 'steps': 34639, 'loss/train': 1.650970220565796} 08/30/2021 19:28:59 - INFO - __main__ - Step 34641: {'lr': 0.00044235742138662085, 'samples': 6651072, 'steps': 34640, 'loss/train': 2.1028692722320557} 08/30/2021 19:28:59 - INFO - __main__ - Step 34642: {'lr': 0.0004423540317583832, 'samples': 6651264, 'steps': 34641, 'loss/train': 2.193288564682007} 08/30/2021 19:28:59 - INFO - __main__ - Step 34643: {'lr': 0.00044235064204347377, 'samples': 6651456, 'steps': 34642, 'loss/train': 1.4730808734893799} 08/30/2021 19:29:00 - INFO - __main__ - Step 34644: {'lr': 0.0004423472522418941, 'samples': 6651648, 'steps': 34643, 'loss/train': 1.362569808959961} 08/30/2021 19:29:00 - INFO - __main__ - Step 34645: {'lr': 0.0004423438623536457, 'samples': 6651840, 'steps': 34644, 'loss/train': 1.7961080074310303} 08/30/2021 19:29:01 - INFO - __main__ - Step 34646: {'lr': 0.0004423404723787301, 'samples': 6652032, 'steps': 34645, 'loss/train': 1.3881537914276123} 08/30/2021 19:29:02 - INFO - __main__ - Step 34647: {'lr': 0.000442337082317149, 'samples': 6652224, 'steps': 34646, 'loss/train': 1.1188929080963135} 08/30/2021 19:29:02 - INFO - __main__ - Step 34648: {'lr': 0.0004423336921689036, 'samples': 6652416, 'steps': 34647, 'loss/train': 1.5280674695968628} 08/30/2021 19:29:03 - INFO - __main__ - Step 34649: {'lr': 0.0004423303019339957, 'samples': 6652608, 'steps': 34648, 'loss/train': 1.7794148921966553} 08/30/2021 19:29:03 - INFO - __main__ - Step 34650: {'lr': 0.0004423269116124267, 'samples': 6652800, 'steps': 34649, 'loss/train': 1.3994988203048706} 08/30/2021 19:29:04 - INFO - __main__ - Step 34651: {'lr': 0.0004423235212041982, 'samples': 6652992, 'steps': 34650, 'loss/train': 1.0937551259994507} 08/30/2021 19:29:05 - INFO - __main__ - Step 34652: {'lr': 0.00044232013070931165, 'samples': 6653184, 'steps': 34651, 'loss/train': 1.5449656248092651} 08/30/2021 19:29:06 - INFO - __main__ - Step 34653: {'lr': 0.00044231674012776864, 'samples': 6653376, 'steps': 34652, 'loss/train': 1.0204274654388428} 08/30/2021 19:29:06 - INFO - __main__ - Step 34654: {'lr': 0.0004423133494595707, 'samples': 6653568, 'steps': 34653, 'loss/train': 1.695006012916565} 08/30/2021 19:29:06 - INFO - __main__ - Step 34655: {'lr': 0.00044230995870471923, 'samples': 6653760, 'steps': 34654, 'loss/train': 1.1935582160949707} 08/30/2021 19:29:07 - INFO - __main__ - Step 34656: {'lr': 0.000442306567863216, 'samples': 6653952, 'steps': 34655, 'loss/train': 1.6298872232437134} 08/30/2021 19:29:08 - INFO - __main__ - Step 34657: {'lr': 0.00044230317693506226, 'samples': 6654144, 'steps': 34656, 'loss/train': 1.2420439720153809} 08/30/2021 19:29:09 - INFO - __main__ - Step 34658: {'lr': 0.00044229978592025975, 'samples': 6654336, 'steps': 34657, 'loss/train': 2.5009686946868896} 08/30/2021 19:29:09 - INFO - __main__ - Step 34659: {'lr': 0.00044229639481881, 'samples': 6654528, 'steps': 34658, 'loss/train': 1.510106086730957} 08/30/2021 19:29:10 - INFO - __main__ - Step 34660: {'lr': 0.00044229300363071434, 'samples': 6654720, 'steps': 34659, 'loss/train': 1.1639480590820312} 08/30/2021 19:29:10 - INFO - __main__ - Step 34661: {'lr': 0.0004422896123559744, 'samples': 6654912, 'steps': 34660, 'loss/train': 1.5406805276870728} 08/30/2021 19:29:12 - INFO - __main__ - Step 34662: {'lr': 0.00044228622099459183, 'samples': 6655104, 'steps': 34661, 'loss/train': 1.7438578605651855} 08/30/2021 19:29:12 - INFO - __main__ - Step 34663: {'lr': 0.000442282829546568, 'samples': 6655296, 'steps': 34662, 'loss/train': 1.529159426689148} 08/30/2021 19:29:13 - INFO - __main__ - Step 34664: {'lr': 0.00044227943801190454, 'samples': 6655488, 'steps': 34663, 'loss/train': 1.7015680074691772} 08/30/2021 19:29:13 - INFO - __main__ - Step 34665: {'lr': 0.0004422760463906029, 'samples': 6655680, 'steps': 34664, 'loss/train': 1.2366178035736084} 08/30/2021 19:29:13 - INFO - __main__ - Step 34666: {'lr': 0.00044227265468266464, 'samples': 6655872, 'steps': 34665, 'loss/train': 1.1760388612747192} 08/30/2021 19:29:15 - INFO - __main__ - Step 34667: {'lr': 0.0004422692628880913, 'samples': 6656064, 'steps': 34666, 'loss/train': 1.7349165678024292} 08/30/2021 19:29:16 - INFO - __main__ - Step 34668: {'lr': 0.00044226587100688436, 'samples': 6656256, 'steps': 34667, 'loss/train': 0.10080096125602722} 08/30/2021 19:29:16 - INFO - __main__ - Step 34669: {'lr': 0.0004422624790390454, 'samples': 6656448, 'steps': 34668, 'loss/train': 1.257863998413086} 08/30/2021 19:29:16 - INFO - __main__ - Step 34670: {'lr': 0.000442259086984576, 'samples': 6656640, 'steps': 34669, 'loss/train': 1.5491306781768799} 08/30/2021 19:29:17 - INFO - __main__ - Step 34671: {'lr': 0.00044225569484347753, 'samples': 6656832, 'steps': 34670, 'loss/train': 0.8068243861198425} 08/30/2021 19:29:17 - INFO - __main__ - Step 34672: {'lr': 0.00044225230261575165, 'samples': 6657024, 'steps': 34671, 'loss/train': 1.4714633226394653} 08/30/2021 19:29:19 - INFO - __main__ - Step 34673: {'lr': 0.00044224891030139986, 'samples': 6657216, 'steps': 34672, 'loss/train': 0.9917858242988586} 08/30/2021 19:29:19 - INFO - __main__ - Step 34674: {'lr': 0.0004422455179004237, 'samples': 6657408, 'steps': 34673, 'loss/train': 0.6558176279067993} 08/30/2021 19:29:20 - INFO - __main__ - Step 34675: {'lr': 0.00044224212541282463, 'samples': 6657600, 'steps': 34674, 'loss/train': 1.201133370399475} 08/30/2021 19:29:20 - INFO - __main__ - Step 34676: {'lr': 0.0004422387328386042, 'samples': 6657792, 'steps': 34675, 'loss/train': 1.5372264385223389} 08/30/2021 19:29:20 - INFO - __main__ - Step 34677: {'lr': 0.000442235340177764, 'samples': 6657984, 'steps': 34676, 'loss/train': 1.5975207090377808} 08/30/2021 19:29:22 - INFO - __main__ - Step 34678: {'lr': 0.00044223194743030556, 'samples': 6658176, 'steps': 34677, 'loss/train': 2.0032284259796143} 08/30/2021 19:29:22 - INFO - __main__ - Step 34679: {'lr': 0.00044222855459623034, 'samples': 6658368, 'steps': 34678, 'loss/train': 0.6564019322395325} 08/30/2021 19:29:23 - INFO - __main__ - Step 34680: {'lr': 0.00044222516167553985, 'samples': 6658560, 'steps': 34679, 'loss/train': 1.6180073022842407} 08/30/2021 19:29:23 - INFO - __main__ - Step 34681: {'lr': 0.0004422217686682357, 'samples': 6658752, 'steps': 34680, 'loss/train': 1.4621936082839966} 08/30/2021 19:29:23 - INFO - __main__ - Step 34682: {'lr': 0.00044221837557431945, 'samples': 6658944, 'steps': 34681, 'loss/train': 1.28822922706604} 08/30/2021 19:29:25 - INFO - __main__ - Step 34683: {'lr': 0.00044221498239379247, 'samples': 6659136, 'steps': 34682, 'loss/train': 0.9522958397865295} 08/30/2021 19:29:25 - INFO - __main__ - Step 34684: {'lr': 0.0004422115891266565, 'samples': 6659328, 'steps': 34683, 'loss/train': 1.7374886274337769} 08/30/2021 19:29:26 - INFO - __main__ - Step 34685: {'lr': 0.00044220819577291283, 'samples': 6659520, 'steps': 34684, 'loss/train': 0.7801975607872009} 08/30/2021 19:29:26 - INFO - __main__ - Step 34686: {'lr': 0.00044220480233256315, 'samples': 6659712, 'steps': 34685, 'loss/train': 1.4226176738739014} 08/30/2021 19:29:26 - INFO - __main__ - Step 34687: {'lr': 0.00044220140880560897, 'samples': 6659904, 'steps': 34686, 'loss/train': 1.1236802339553833} 08/30/2021 19:29:28 - INFO - __main__ - Step 34688: {'lr': 0.0004421980151920518, 'samples': 6660096, 'steps': 34687, 'loss/train': 1.602264165878296} 08/30/2021 19:29:28 - INFO - __main__ - Step 34689: {'lr': 0.00044219462149189313, 'samples': 6660288, 'steps': 34688, 'loss/train': 0.8838433027267456} 08/30/2021 19:29:29 - INFO - __main__ - Step 34690: {'lr': 0.0004421912277051346, 'samples': 6660480, 'steps': 34689, 'loss/train': 1.0139211416244507} 08/30/2021 19:29:29 - INFO - __main__ - Step 34691: {'lr': 0.00044218783383177763, 'samples': 6660672, 'steps': 34690, 'loss/train': 1.5555403232574463} 08/30/2021 19:29:29 - INFO - __main__ - Step 34692: {'lr': 0.00044218443987182384, 'samples': 6660864, 'steps': 34691, 'loss/train': 0.9847817420959473} 08/30/2021 19:29:31 - INFO - __main__ - Step 34693: {'lr': 0.0004421810458252746, 'samples': 6661056, 'steps': 34692, 'loss/train': 1.9286046028137207} 08/30/2021 19:29:32 - INFO - __main__ - Step 34694: {'lr': 0.00044217765169213166, 'samples': 6661248, 'steps': 34693, 'loss/train': 1.5308654308319092} 08/30/2021 19:29:32 - INFO - __main__ - Step 34695: {'lr': 0.00044217425747239636, 'samples': 6661440, 'steps': 34694, 'loss/train': 1.2886213064193726} 08/30/2021 19:29:32 - INFO - __main__ - Step 34696: {'lr': 0.00044217086316607033, 'samples': 6661632, 'steps': 34695, 'loss/train': 1.4247550964355469} 08/30/2021 19:29:33 - INFO - __main__ - Step 34697: {'lr': 0.00044216746877315504, 'samples': 6661824, 'steps': 34696, 'loss/train': 1.329972505569458} 08/30/2021 19:29:33 - INFO - __main__ - Step 34698: {'lr': 0.0004421640742936521, 'samples': 6662016, 'steps': 34697, 'loss/train': 1.5331666469573975} 08/30/2021 19:29:35 - INFO - __main__ - Step 34699: {'lr': 0.000442160679727563, 'samples': 6662208, 'steps': 34698, 'loss/train': 0.4324115812778473} 08/30/2021 19:29:35 - INFO - __main__ - Step 34700: {'lr': 0.0004421572850748893, 'samples': 6662400, 'steps': 34699, 'loss/train': 0.7966052293777466} 08/30/2021 19:29:36 - INFO - __main__ - Step 34701: {'lr': 0.00044215389033563235, 'samples': 6662592, 'steps': 34700, 'loss/train': 0.16638953983783722} 08/30/2021 19:29:36 - INFO - __main__ - Step 34702: {'lr': 0.00044215049550979394, 'samples': 6662784, 'steps': 34701, 'loss/train': 0.6518832445144653} 08/30/2021 19:29:36 - INFO - __main__ - Step 34703: {'lr': 0.0004421471005973755, 'samples': 6662976, 'steps': 34702, 'loss/train': 1.5585709810256958} 08/30/2021 19:29:38 - INFO - __main__ - Step 34704: {'lr': 0.0004421437055983785, 'samples': 6663168, 'steps': 34703, 'loss/train': 0.5413429737091064} 08/30/2021 19:29:38 - INFO - __main__ - Step 34705: {'lr': 0.0004421403105128045, 'samples': 6663360, 'steps': 34704, 'loss/train': 1.3705461025238037} 08/30/2021 19:29:39 - INFO - __main__ - Step 34706: {'lr': 0.00044213691534065503, 'samples': 6663552, 'steps': 34705, 'loss/train': 1.6387416124343872} 08/30/2021 19:29:39 - INFO - __main__ - Step 34707: {'lr': 0.0004421335200819316, 'samples': 6663744, 'steps': 34706, 'loss/train': 1.3581836223602295} 08/30/2021 19:29:39 - INFO - __main__ - Step 34708: {'lr': 0.00044213012473663584, 'samples': 6663936, 'steps': 34707, 'loss/train': 1.6423312425613403} 08/30/2021 19:29:41 - INFO - __main__ - Step 34709: {'lr': 0.0004421267293047692, 'samples': 6664128, 'steps': 34708, 'loss/train': 0.08500602096319199} 08/30/2021 19:29:41 - INFO - __main__ - Step 34710: {'lr': 0.0004421233337863332, 'samples': 6664320, 'steps': 34709, 'loss/train': 1.0537681579589844} 08/30/2021 19:29:42 - INFO - __main__ - Step 34711: {'lr': 0.0004421199381813293, 'samples': 6664512, 'steps': 34710, 'loss/train': 1.7350077629089355} 08/30/2021 19:29:42 - INFO - __main__ - Step 34712: {'lr': 0.0004421165424897593, 'samples': 6664704, 'steps': 34711, 'loss/train': 1.7634326219558716} 08/30/2021 19:29:42 - INFO - __main__ - Step 34713: {'lr': 0.00044211314671162446, 'samples': 6664896, 'steps': 34712, 'loss/train': 1.4969698190689087} 08/30/2021 19:29:45 - INFO - __main__ - Step 34714: {'lr': 0.0004421097508469264, 'samples': 6665088, 'steps': 34713, 'loss/train': 1.0224230289459229} 08/30/2021 19:29:45 - INFO - __main__ - Step 34715: {'lr': 0.0004421063548956666, 'samples': 6665280, 'steps': 34714, 'loss/train': 1.5540722608566284} 08/30/2021 19:29:45 - INFO - __main__ - Step 34716: {'lr': 0.0004421029588578468, 'samples': 6665472, 'steps': 34715, 'loss/train': 1.6547048091888428} 08/30/2021 19:29:46 - INFO - __main__ - Step 34717: {'lr': 0.00044209956273346816, 'samples': 6665664, 'steps': 34716, 'loss/train': 1.0293141603469849} 08/30/2021 19:29:46 - INFO - __main__ - Step 34718: {'lr': 0.0004420961665225326, 'samples': 6665856, 'steps': 34717, 'loss/train': 1.2696518898010254} 08/30/2021 19:29:46 - INFO - __main__ - Step 34719: {'lr': 0.0004420927702250414, 'samples': 6666048, 'steps': 34718, 'loss/train': 1.9864994287490845} 08/30/2021 19:29:48 - INFO - __main__ - Step 34720: {'lr': 0.00044208937384099614, 'samples': 6666240, 'steps': 34719, 'loss/train': 1.6231191158294678} 08/30/2021 19:29:49 - INFO - __main__ - Step 34721: {'lr': 0.0004420859773703985, 'samples': 6666432, 'steps': 34720, 'loss/train': 1.2206162214279175} 08/30/2021 19:29:49 - INFO - __main__ - Step 34722: {'lr': 0.0004420825808132497, 'samples': 6666624, 'steps': 34721, 'loss/train': 2.1539533138275146} 08/30/2021 19:29:49 - INFO - __main__ - Step 34723: {'lr': 0.0004420791841695515, 'samples': 6666816, 'steps': 34722, 'loss/train': 0.10320522636175156} 08/30/2021 19:29:50 - INFO - __main__ - Step 34724: {'lr': 0.00044207578743930544, 'samples': 6667008, 'steps': 34723, 'loss/train': 1.749796986579895} 08/30/2021 19:29:52 - INFO - __main__ - Step 34725: {'lr': 0.00044207239062251297, 'samples': 6667200, 'steps': 34724, 'loss/train': 1.0909737348556519} 08/30/2021 19:29:52 - INFO - __main__ - Step 34726: {'lr': 0.00044206899371917563, 'samples': 6667392, 'steps': 34725, 'loss/train': 1.5443371534347534} 08/30/2021 19:29:52 - INFO - __main__ - Step 34727: {'lr': 0.00044206559672929505, 'samples': 6667584, 'steps': 34726, 'loss/train': 0.7401970624923706} 08/30/2021 19:29:53 - INFO - __main__ - Step 34728: {'lr': 0.00044206219965287253, 'samples': 6667776, 'steps': 34727, 'loss/train': 0.5476230382919312} 08/30/2021 19:29:53 - INFO - __main__ - Step 34729: {'lr': 0.0004420588024899098, 'samples': 6667968, 'steps': 34728, 'loss/train': 1.7276771068572998} 08/30/2021 19:29:55 - INFO - __main__ - Step 34730: {'lr': 0.00044205540524040846, 'samples': 6668160, 'steps': 34729, 'loss/train': 1.187868356704712} 08/30/2021 19:29:55 - INFO - __main__ - Step 34731: {'lr': 0.0004420520079043698, 'samples': 6668352, 'steps': 34730, 'loss/train': 1.0180031061172485} 08/30/2021 19:29:55 - INFO - __main__ - Step 34732: {'lr': 0.00044204861048179544, 'samples': 6668544, 'steps': 34731, 'loss/train': 1.392545223236084} 08/30/2021 19:29:56 - INFO - __main__ - Step 34733: {'lr': 0.000442045212972687, 'samples': 6668736, 'steps': 34732, 'loss/train': 1.2085925340652466} 08/30/2021 19:29:56 - INFO - __main__ - Step 34734: {'lr': 0.00044204181537704594, 'samples': 6668928, 'steps': 34733, 'loss/train': 2.0333735942840576} 08/30/2021 19:29:58 - INFO - __main__ - Step 34735: {'lr': 0.0004420384176948738, 'samples': 6669120, 'steps': 34734, 'loss/train': 1.894636631011963} 08/30/2021 19:29:58 - INFO - __main__ - Step 34736: {'lr': 0.0004420350199261721, 'samples': 6669312, 'steps': 34735, 'loss/train': 1.0695494413375854} 08/30/2021 19:29:58 - INFO - __main__ - Step 34737: {'lr': 0.0004420316220709424, 'samples': 6669504, 'steps': 34736, 'loss/train': 0.819586455821991} 08/30/2021 19:29:59 - INFO - __main__ - Step 34738: {'lr': 0.0004420282241291862, 'samples': 6669696, 'steps': 34737, 'loss/train': 1.361747145652771} 08/30/2021 19:29:59 - INFO - __main__ - Step 34739: {'lr': 0.0004420248261009051, 'samples': 6669888, 'steps': 34738, 'loss/train': 1.8967548608779907} 08/30/2021 19:29:59 - INFO - __main__ - Step 34740: {'lr': 0.0004420214279861005, 'samples': 6670080, 'steps': 34739, 'loss/train': 1.2004952430725098} 08/30/2021 19:30:01 - INFO - __main__ - Step 34741: {'lr': 0.000442018029784774, 'samples': 6670272, 'steps': 34740, 'loss/train': 0.9303376078605652} 08/30/2021 19:30:01 - INFO - __main__ - Step 34742: {'lr': 0.00044201463149692725, 'samples': 6670464, 'steps': 34741, 'loss/train': 1.6795202493667603} 08/30/2021 19:30:02 - INFO - __main__ - Step 34743: {'lr': 0.0004420112331225616, 'samples': 6670656, 'steps': 34742, 'loss/train': 1.0386409759521484} 08/30/2021 19:30:02 - INFO - __main__ - Step 34744: {'lr': 0.0004420078346616786, 'samples': 6670848, 'steps': 34743, 'loss/train': 1.1938104629516602} 08/30/2021 19:30:02 - INFO - __main__ - Step 34745: {'lr': 0.00044200443611427985, 'samples': 6671040, 'steps': 34744, 'loss/train': 1.588404893875122} 08/30/2021 19:30:04 - INFO - __main__ - Step 34746: {'lr': 0.000442001037480367, 'samples': 6671232, 'steps': 34745, 'loss/train': 1.9168548583984375} 08/30/2021 19:30:05 - INFO - __main__ - Step 34747: {'lr': 0.0004419976387599413, 'samples': 6671424, 'steps': 34746, 'loss/train': 1.2247517108917236} 08/30/2021 19:30:05 - INFO - __main__ - Step 34748: {'lr': 0.0004419942399530045, 'samples': 6671616, 'steps': 34747, 'loss/train': 0.9280975461006165} 08/30/2021 19:30:05 - INFO - __main__ - Step 34749: {'lr': 0.000441990841059558, 'samples': 6671808, 'steps': 34748, 'loss/train': 0.09358397126197815} 08/30/2021 19:30:06 - INFO - __main__ - Step 34750: {'lr': 0.0004419874420796034, 'samples': 6672000, 'steps': 34749, 'loss/train': 0.6446064114570618} 08/30/2021 19:30:07 - INFO - __main__ - Step 34751: {'lr': 0.00044198404301314223, 'samples': 6672192, 'steps': 34750, 'loss/train': 0.6184068918228149} 08/30/2021 19:30:08 - INFO - __main__ - Step 34752: {'lr': 0.000441980643860176, 'samples': 6672384, 'steps': 34751, 'loss/train': 1.9865344762802124} 08/30/2021 19:30:08 - INFO - __main__ - Step 34753: {'lr': 0.0004419772446207063, 'samples': 6672576, 'steps': 34752, 'loss/train': 1.5299996137619019} 08/30/2021 19:30:08 - INFO - __main__ - Step 34754: {'lr': 0.0004419738452947346, 'samples': 6672768, 'steps': 34753, 'loss/train': 1.5365554094314575} 08/30/2021 19:30:09 - INFO - __main__ - Step 34755: {'lr': 0.00044197044588226245, 'samples': 6672960, 'steps': 34754, 'loss/train': 1.6013884544372559} 08/30/2021 19:30:09 - INFO - __main__ - Step 34756: {'lr': 0.00044196704638329134, 'samples': 6673152, 'steps': 34755, 'loss/train': 1.6902989149093628} 08/30/2021 19:30:10 - INFO - __main__ - Step 34757: {'lr': 0.00044196364679782284, 'samples': 6673344, 'steps': 34756, 'loss/train': 1.1759026050567627} 08/30/2021 19:30:11 - INFO - __main__ - Step 34758: {'lr': 0.00044196024712585854, 'samples': 6673536, 'steps': 34757, 'loss/train': 1.1638102531433105} 08/30/2021 19:30:11 - INFO - __main__ - Step 34759: {'lr': 0.0004419568473673999, 'samples': 6673728, 'steps': 34758, 'loss/train': 1.7615946531295776} 08/30/2021 19:30:12 - INFO - __main__ - Step 34760: {'lr': 0.00044195344752244844, 'samples': 6673920, 'steps': 34759, 'loss/train': 1.3740109205245972} 08/30/2021 19:30:12 - INFO - __main__ - Step 34761: {'lr': 0.0004419500475910057, 'samples': 6674112, 'steps': 34760, 'loss/train': 1.8068288564682007} 08/30/2021 19:30:14 - INFO - __main__ - Step 34762: {'lr': 0.0004419466475730732, 'samples': 6674304, 'steps': 34761, 'loss/train': 1.335292935371399} 08/30/2021 19:30:14 - INFO - __main__ - Step 34763: {'lr': 0.00044194324746865265, 'samples': 6674496, 'steps': 34762, 'loss/train': 1.5998960733413696} 08/30/2021 19:30:14 - INFO - __main__ - Step 34764: {'lr': 0.00044193984727774533, 'samples': 6674688, 'steps': 34763, 'loss/train': 1.4881980419158936} 08/30/2021 19:30:15 - INFO - __main__ - Step 34765: {'lr': 0.0004419364470003529, 'samples': 6674880, 'steps': 34764, 'loss/train': 0.8375330567359924} 08/30/2021 19:30:15 - INFO - __main__ - Step 34766: {'lr': 0.00044193304663647684, 'samples': 6675072, 'steps': 34765, 'loss/train': 1.299536943435669} 08/30/2021 19:30:17 - INFO - __main__ - Step 34767: {'lr': 0.00044192964618611875, 'samples': 6675264, 'steps': 34766, 'loss/train': 1.460287094116211} 08/30/2021 19:30:17 - INFO - __main__ - Step 34768: {'lr': 0.0004419262456492801, 'samples': 6675456, 'steps': 34767, 'loss/train': 1.5032386779785156} 08/30/2021 19:30:17 - INFO - __main__ - Step 34769: {'lr': 0.0004419228450259625, 'samples': 6675648, 'steps': 34768, 'loss/train': 1.292349934577942} 08/30/2021 19:30:18 - INFO - __main__ - Step 34770: {'lr': 0.00044191944431616734, 'samples': 6675840, 'steps': 34769, 'loss/train': 1.1969331502914429} 08/30/2021 19:30:18 - INFO - __main__ - Step 34771: {'lr': 0.0004419160435198963, 'samples': 6676032, 'steps': 34770, 'loss/train': 1.389635682106018} 08/30/2021 19:30:20 - INFO - __main__ - Step 34772: {'lr': 0.00044191264263715083, 'samples': 6676224, 'steps': 34771, 'loss/train': 1.2823338508605957} 08/30/2021 19:30:21 - INFO - __main__ - Step 34773: {'lr': 0.00044190924166793245, 'samples': 6676416, 'steps': 34772, 'loss/train': 1.0687317848205566} 08/30/2021 19:30:21 - INFO - __main__ - Step 34774: {'lr': 0.00044190584061224277, 'samples': 6676608, 'steps': 34773, 'loss/train': 0.6831493973731995} 08/30/2021 19:30:22 - INFO - __main__ - Step 34775: {'lr': 0.0004419024394700833, 'samples': 6676800, 'steps': 34774, 'loss/train': 1.4117400646209717} 08/30/2021 19:30:22 - INFO - __main__ - Step 34776: {'lr': 0.0004418990382414555, 'samples': 6676992, 'steps': 34775, 'loss/train': 1.9957515001296997} 08/30/2021 19:30:22 - INFO - __main__ - Step 34777: {'lr': 0.000441895636926361, 'samples': 6677184, 'steps': 34776, 'loss/train': 1.2460740804672241} 08/30/2021 19:30:24 - INFO - __main__ - Step 34778: {'lr': 0.0004418922355248013, 'samples': 6677376, 'steps': 34777, 'loss/train': 2.4083032608032227} 08/30/2021 19:30:24 - INFO - __main__ - Step 34779: {'lr': 0.00044188883403677783, 'samples': 6677568, 'steps': 34778, 'loss/train': 1.159144401550293} 08/30/2021 19:30:25 - INFO - __main__ - Step 34780: {'lr': 0.0004418854324622923, 'samples': 6677760, 'steps': 34779, 'loss/train': 0.7860084176063538} 08/30/2021 19:30:25 - INFO - __main__ - Step 34781: {'lr': 0.0004418820308013461, 'samples': 6677952, 'steps': 34780, 'loss/train': 0.6624705195426941} 08/30/2021 19:30:25 - INFO - __main__ - Step 34782: {'lr': 0.0004418786290539408, 'samples': 6678144, 'steps': 34781, 'loss/train': 1.468929409980774} 08/30/2021 19:30:27 - INFO - __main__ - Step 34783: {'lr': 0.000441875227220078, 'samples': 6678336, 'steps': 34782, 'loss/train': 1.6640392541885376} 08/30/2021 19:30:27 - INFO - __main__ - Step 34784: {'lr': 0.00044187182529975924, 'samples': 6678528, 'steps': 34783, 'loss/train': 1.5427321195602417} 08/30/2021 19:30:28 - INFO - __main__ - Step 34785: {'lr': 0.00044186842329298594, 'samples': 6678720, 'steps': 34784, 'loss/train': 1.402348518371582} 08/30/2021 19:30:28 - INFO - __main__ - Step 34786: {'lr': 0.0004418650211997596, 'samples': 6678912, 'steps': 34785, 'loss/train': 0.3444991707801819} 08/30/2021 19:30:28 - INFO - __main__ - Step 34787: {'lr': 0.00044186161902008193, 'samples': 6679104, 'steps': 34786, 'loss/train': 0.8967769742012024} 08/30/2021 19:30:30 - INFO - __main__ - Step 34788: {'lr': 0.0004418582167539544, 'samples': 6679296, 'steps': 34787, 'loss/train': 0.791840672492981} 08/30/2021 19:30:30 - INFO - __main__ - Step 34789: {'lr': 0.00044185481440137846, 'samples': 6679488, 'steps': 34788, 'loss/train': 1.4772237539291382} 08/30/2021 19:30:31 - INFO - __main__ - Step 34790: {'lr': 0.0004418514119623557, 'samples': 6679680, 'steps': 34789, 'loss/train': 1.569371223449707} 08/30/2021 19:30:31 - INFO - __main__ - Step 34791: {'lr': 0.00044184800943688774, 'samples': 6679872, 'steps': 34790, 'loss/train': 1.5514798164367676} 08/30/2021 19:30:31 - INFO - __main__ - Step 34792: {'lr': 0.00044184460682497595, 'samples': 6680064, 'steps': 34791, 'loss/train': 1.2580409049987793} 08/30/2021 19:30:33 - INFO - __main__ - Step 34793: {'lr': 0.00044184120412662196, 'samples': 6680256, 'steps': 34792, 'loss/train': 1.6579335927963257} 08/30/2021 19:30:34 - INFO - __main__ - Step 34794: {'lr': 0.00044183780134182725, 'samples': 6680448, 'steps': 34793, 'loss/train': 1.4819539785385132} 08/30/2021 19:30:34 - INFO - __main__ - Step 34795: {'lr': 0.0004418343984705935, 'samples': 6680640, 'steps': 34794, 'loss/train': 1.9057198762893677} 08/30/2021 19:30:34 - INFO - __main__ - Step 34796: {'lr': 0.000441830995512922, 'samples': 6680832, 'steps': 34795, 'loss/train': 1.8886874914169312} 08/30/2021 19:30:35 - INFO - __main__ - Step 34797: {'lr': 0.00044182759246881446, 'samples': 6681024, 'steps': 34796, 'loss/train': 0.026153258979320526} 08/30/2021 19:30:35 - INFO - __main__ - Step 34798: {'lr': 0.0004418241893382724, 'samples': 6681216, 'steps': 34797, 'loss/train': 1.4936158657073975} 08/30/2021 19:30:35 - INFO - __main__ - Step 34799: {'lr': 0.0004418207861212973, 'samples': 6681408, 'steps': 34798, 'loss/train': 1.608742594718933} 08/30/2021 19:30:37 - INFO - __main__ - Step 34800: {'lr': 0.0004418173828178906, 'samples': 6681600, 'steps': 34799, 'loss/train': 1.6500439643859863} 08/30/2021 19:30:37 - INFO - __main__ - Step 34801: {'lr': 0.0004418139794280541, 'samples': 6681792, 'steps': 34800, 'loss/train': 1.565674066543579} 08/30/2021 19:30:38 - INFO - __main__ - Step 34802: {'lr': 0.0004418105759517892, 'samples': 6681984, 'steps': 34801, 'loss/train': 1.2757917642593384} 08/30/2021 19:30:38 - INFO - __main__ - Step 34803: {'lr': 0.0004418071723890973, 'samples': 6682176, 'steps': 34802, 'loss/train': 1.5636024475097656} 08/30/2021 19:30:39 - INFO - __main__ - Step 34804: {'lr': 0.0004418037687399801, 'samples': 6682368, 'steps': 34803, 'loss/train': 0.6732167601585388} 08/30/2021 19:30:40 - INFO - __main__ - Step 34805: {'lr': 0.0004418003650044391, 'samples': 6682560, 'steps': 34804, 'loss/train': 1.4263074398040771} 08/30/2021 19:30:41 - INFO - __main__ - Step 34806: {'lr': 0.0004417969611824758, 'samples': 6682752, 'steps': 34805, 'loss/train': 1.2235455513000488} 08/30/2021 19:30:41 - INFO - __main__ - Step 34807: {'lr': 0.00044179355727409173, 'samples': 6682944, 'steps': 34806, 'loss/train': 1.2955653667449951} 08/30/2021 19:30:41 - INFO - __main__ - Step 34808: {'lr': 0.00044179015327928847, 'samples': 6683136, 'steps': 34807, 'loss/train': 1.1689554452896118} 08/30/2021 19:30:42 - INFO - __main__ - Step 34809: {'lr': 0.0004417867491980675, 'samples': 6683328, 'steps': 34808, 'loss/train': 1.5134466886520386} 08/30/2021 19:30:43 - INFO - __main__ - Step 34810: {'lr': 0.0004417833450304304, 'samples': 6683520, 'steps': 34809, 'loss/train': 1.5974912643432617} 08/30/2021 19:30:44 - INFO - __main__ - Step 34811: {'lr': 0.0004417799407763786, 'samples': 6683712, 'steps': 34810, 'loss/train': 0.7585117220878601} 08/30/2021 19:30:44 - INFO - __main__ - Step 34812: {'lr': 0.00044177653643591387, 'samples': 6683904, 'steps': 34811, 'loss/train': 1.289052963256836} 08/30/2021 19:30:44 - INFO - __main__ - Step 34813: {'lr': 0.00044177313200903745, 'samples': 6684096, 'steps': 34812, 'loss/train': 1.6717332601547241} 08/30/2021 19:30:45 - INFO - __main__ - Step 34814: {'lr': 0.0004417697274957511, 'samples': 6684288, 'steps': 34813, 'loss/train': 1.3906093835830688} 08/30/2021 19:30:46 - INFO - __main__ - Step 34815: {'lr': 0.0004417663228960562, 'samples': 6684480, 'steps': 34814, 'loss/train': 1.7551484107971191} 08/30/2021 19:30:47 - INFO - __main__ - Step 34816: {'lr': 0.0004417629182099545, 'samples': 6684672, 'steps': 34815, 'loss/train': 1.8394625186920166} 08/30/2021 19:30:47 - INFO - __main__ - Step 34817: {'lr': 0.00044175951343744725, 'samples': 6684864, 'steps': 34816, 'loss/train': 1.7801318168640137} 08/30/2021 19:30:47 - INFO - __main__ - Step 34818: {'lr': 0.0004417561085785362, 'samples': 6685056, 'steps': 34817, 'loss/train': 1.6029207706451416} 08/30/2021 19:30:48 - INFO - __main__ - Step 34819: {'lr': 0.0004417527036332227, 'samples': 6685248, 'steps': 34818, 'loss/train': 1.453639268875122} 08/30/2021 19:30:49 - INFO - __main__ - Step 34820: {'lr': 0.0004417492986015085, 'samples': 6685440, 'steps': 34819, 'loss/train': 1.3046061992645264} 08/30/2021 19:30:50 - INFO - __main__ - Step 34821: {'lr': 0.000441745893483395, 'samples': 6685632, 'steps': 34820, 'loss/train': 1.7073967456817627} 08/30/2021 19:30:50 - INFO - __main__ - Step 34822: {'lr': 0.00044174248827888376, 'samples': 6685824, 'steps': 34821, 'loss/train': 1.296985149383545} 08/30/2021 19:30:50 - INFO - __main__ - Step 34823: {'lr': 0.00044173908298797627, 'samples': 6686016, 'steps': 34822, 'loss/train': 1.2004714012145996} 08/30/2021 19:30:51 - INFO - __main__ - Step 34824: {'lr': 0.0004417356776106741, 'samples': 6686208, 'steps': 34823, 'loss/train': 1.5317583084106445} 08/30/2021 19:30:51 - INFO - __main__ - Step 34825: {'lr': 0.00044173227214697885, 'samples': 6686400, 'steps': 34824, 'loss/train': 1.8565694093704224} 08/30/2021 19:30:52 - INFO - __main__ - Step 34826: {'lr': 0.000441728866596892, 'samples': 6686592, 'steps': 34825, 'loss/train': 1.6611049175262451} 08/30/2021 19:30:53 - INFO - __main__ - Step 34827: {'lr': 0.00044172546096041504, 'samples': 6686784, 'steps': 34826, 'loss/train': 0.2876690626144409} 08/30/2021 19:30:53 - INFO - __main__ - Step 34828: {'lr': 0.0004417220552375496, 'samples': 6686976, 'steps': 34827, 'loss/train': 1.161854863166809} 08/30/2021 19:30:54 - INFO - __main__ - Step 34829: {'lr': 0.00044171864942829707, 'samples': 6687168, 'steps': 34828, 'loss/train': 1.7079987525939941} 08/30/2021 19:30:54 - INFO - __main__ - Step 34830: {'lr': 0.0004417152435326591, 'samples': 6687360, 'steps': 34829, 'loss/train': 1.3795909881591797} 08/30/2021 19:30:56 - INFO - __main__ - Step 34831: {'lr': 0.00044171183755063726, 'samples': 6687552, 'steps': 34830, 'loss/train': 1.8254364728927612} 08/30/2021 19:30:56 - INFO - __main__ - Step 34832: {'lr': 0.00044170843148223305, 'samples': 6687744, 'steps': 34831, 'loss/train': 1.633926510810852} 08/30/2021 19:30:57 - INFO - __main__ - Step 34833: {'lr': 0.0004417050253274479, 'samples': 6687936, 'steps': 34832, 'loss/train': 2.0371410846710205} 08/30/2021 19:30:57 - INFO - __main__ - Step 34834: {'lr': 0.00044170161908628345, 'samples': 6688128, 'steps': 34833, 'loss/train': 1.4808772802352905} 08/30/2021 19:30:58 - INFO - __main__ - Step 34835: {'lr': 0.0004416982127587412, 'samples': 6688320, 'steps': 34834, 'loss/train': 1.7261383533477783} 08/30/2021 19:30:59 - INFO - __main__ - Step 34836: {'lr': 0.00044169480634482274, 'samples': 6688512, 'steps': 34835, 'loss/train': 1.6901108026504517} 08/30/2021 19:30:59 - INFO - __main__ - Step 34837: {'lr': 0.0004416913998445294, 'samples': 6688704, 'steps': 34836, 'loss/train': 2.1727051734924316} 08/30/2021 19:31:00 - INFO - __main__ - Step 34838: {'lr': 0.000441687993257863, 'samples': 6688896, 'steps': 34837, 'loss/train': 1.5491070747375488} 08/30/2021 19:31:00 - INFO - __main__ - Step 34839: {'lr': 0.000441684586584825, 'samples': 6689088, 'steps': 34838, 'loss/train': 1.0219261646270752} 08/30/2021 19:31:01 - INFO - __main__ - Step 34840: {'lr': 0.0004416811798254168, 'samples': 6689280, 'steps': 34839, 'loss/train': 1.4175992012023926} 08/30/2021 19:31:02 - INFO - __main__ - Step 34841: {'lr': 0.00044167777297964006, 'samples': 6689472, 'steps': 34840, 'loss/train': 1.086851954460144} 08/30/2021 19:31:03 - INFO - __main__ - Step 34842: {'lr': 0.0004416743660474962, 'samples': 6689664, 'steps': 34841, 'loss/train': 1.172855257987976} 08/30/2021 19:31:03 - INFO - __main__ - Step 34843: {'lr': 0.0004416709590289869, 'samples': 6689856, 'steps': 34842, 'loss/train': 1.4749000072479248} 08/30/2021 19:31:04 - INFO - __main__ - Step 34844: {'lr': 0.00044166755192411364, 'samples': 6690048, 'steps': 34843, 'loss/train': 1.4386703968048096} 08/30/2021 19:31:04 - INFO - __main__ - Step 34845: {'lr': 0.00044166414473287784, 'samples': 6690240, 'steps': 34844, 'loss/train': 3.9213595390319824} 08/30/2021 19:31:04 - INFO - __main__ - Step 34846: {'lr': 0.0004416607374552812, 'samples': 6690432, 'steps': 34845, 'loss/train': 1.2432138919830322} 08/30/2021 19:31:06 - INFO - __main__ - Step 34847: {'lr': 0.00044165733009132524, 'samples': 6690624, 'steps': 34846, 'loss/train': 1.974619746208191} 08/30/2021 19:31:06 - INFO - __main__ - Step 34848: {'lr': 0.00044165392264101136, 'samples': 6690816, 'steps': 34847, 'loss/train': 2.2524802684783936} 08/30/2021 19:31:06 - INFO - __main__ - Step 34849: {'lr': 0.0004416505151043412, 'samples': 6691008, 'steps': 34848, 'loss/train': 1.4525641202926636} 08/30/2021 19:31:07 - INFO - __main__ - Step 34850: {'lr': 0.0004416471074813163, 'samples': 6691200, 'steps': 34849, 'loss/train': 1.4050114154815674} 08/30/2021 19:31:08 - INFO - __main__ - Step 34851: {'lr': 0.0004416436997719382, 'samples': 6691392, 'steps': 34850, 'loss/train': 1.9952603578567505} 08/30/2021 19:31:09 - INFO - __main__ - Step 34852: {'lr': 0.0004416402919762084, 'samples': 6691584, 'steps': 34851, 'loss/train': 1.2240517139434814} 08/30/2021 19:31:09 - INFO - __main__ - Step 34853: {'lr': 0.00044163688409412833, 'samples': 6691776, 'steps': 34852, 'loss/train': 1.0828030109405518} 08/30/2021 19:31:09 - INFO - __main__ - Step 34854: {'lr': 0.0004416334761256997, 'samples': 6691968, 'steps': 34853, 'loss/train': 1.1099767684936523} 08/30/2021 19:31:10 - INFO - __main__ - Step 34855: {'lr': 0.000441630068070924, 'samples': 6692160, 'steps': 34854, 'loss/train': 1.4822251796722412} 08/30/2021 19:31:10 - INFO - __main__ - Step 34856: {'lr': 0.0004416266599298028, 'samples': 6692352, 'steps': 34855, 'loss/train': 1.3974529504776} 08/30/2021 19:31:12 - INFO - __main__ - Step 34857: {'lr': 0.00044162325170233745, 'samples': 6692544, 'steps': 34856, 'loss/train': 1.701670527458191} 08/30/2021 19:31:12 - INFO - __main__ - Step 34858: {'lr': 0.00044161984338852967, 'samples': 6692736, 'steps': 34857, 'loss/train': 1.397925615310669} 08/30/2021 19:31:12 - INFO - __main__ - Step 34859: {'lr': 0.000441616434988381, 'samples': 6692928, 'steps': 34858, 'loss/train': 1.7587172985076904} 08/30/2021 19:31:13 - INFO - __main__ - Step 34860: {'lr': 0.00044161302650189295, 'samples': 6693120, 'steps': 34859, 'loss/train': 1.7492303848266602} 08/30/2021 19:31:13 - INFO - __main__ - Step 34861: {'lr': 0.00044160961792906694, 'samples': 6693312, 'steps': 34860, 'loss/train': 0.9920586943626404} 08/30/2021 19:31:15 - INFO - __main__ - Step 34862: {'lr': 0.00044160620926990456, 'samples': 6693504, 'steps': 34861, 'loss/train': 1.1697667837142944} 08/30/2021 19:31:15 - INFO - __main__ - Step 34863: {'lr': 0.0004416028005244075, 'samples': 6693696, 'steps': 34862, 'loss/train': 1.527687430381775} 08/30/2021 19:31:15 - INFO - __main__ - Step 34864: {'lr': 0.0004415993916925771, 'samples': 6693888, 'steps': 34863, 'loss/train': 1.2309246063232422} 08/30/2021 19:31:16 - INFO - __main__ - Step 34865: {'lr': 0.000441595982774415, 'samples': 6694080, 'steps': 34864, 'loss/train': 1.2404483556747437} 08/30/2021 19:31:16 - INFO - __main__ - Step 34866: {'lr': 0.00044159257376992267, 'samples': 6694272, 'steps': 34865, 'loss/train': 0.95048588514328} 08/30/2021 19:31:17 - INFO - __main__ - Step 34867: {'lr': 0.0004415891646791017, 'samples': 6694464, 'steps': 34866, 'loss/train': 1.4146426916122437} 08/30/2021 19:31:18 - INFO - __main__ - Step 34868: {'lr': 0.0004415857555019536, 'samples': 6694656, 'steps': 34867, 'loss/train': 1.2230663299560547} 08/30/2021 19:31:18 - INFO - __main__ - Step 34869: {'lr': 0.00044158234623847993, 'samples': 6694848, 'steps': 34868, 'loss/train': 1.3979012966156006} 08/30/2021 19:31:19 - INFO - __main__ - Step 34870: {'lr': 0.00044157893688868223, 'samples': 6695040, 'steps': 34869, 'loss/train': 1.5737814903259277} 08/30/2021 19:31:19 - INFO - __main__ - Step 34871: {'lr': 0.00044157552745256203, 'samples': 6695232, 'steps': 34870, 'loss/train': 1.2867834568023682} 08/30/2021 19:31:21 - INFO - __main__ - Step 34872: {'lr': 0.0004415721179301208, 'samples': 6695424, 'steps': 34871, 'loss/train': 1.8243038654327393} 08/30/2021 19:31:21 - INFO - __main__ - Step 34873: {'lr': 0.00044156870832136015, 'samples': 6695616, 'steps': 34872, 'loss/train': 1.4083529710769653} 08/30/2021 19:31:22 - INFO - __main__ - Step 34874: {'lr': 0.00044156529862628157, 'samples': 6695808, 'steps': 34873, 'loss/train': 1.1257758140563965} 08/30/2021 19:31:22 - INFO - __main__ - Step 34875: {'lr': 0.00044156188884488667, 'samples': 6696000, 'steps': 34874, 'loss/train': 0.5940538644790649} 08/30/2021 19:31:22 - INFO - __main__ - Step 34876: {'lr': 0.0004415584789771769, 'samples': 6696192, 'steps': 34875, 'loss/train': 1.5871161222457886} 08/30/2021 19:31:24 - INFO - __main__ - Step 34877: {'lr': 0.0004415550690231539, 'samples': 6696384, 'steps': 34876, 'loss/train': 1.7959715127944946} 08/30/2021 19:31:24 - INFO - __main__ - Step 34878: {'lr': 0.0004415516589828191, 'samples': 6696576, 'steps': 34877, 'loss/train': 1.8214266300201416} 08/30/2021 19:31:25 - INFO - __main__ - Step 34879: {'lr': 0.00044154824885617405, 'samples': 6696768, 'steps': 34878, 'loss/train': 1.333667278289795} 08/30/2021 19:31:25 - INFO - __main__ - Step 34880: {'lr': 0.0004415448386432204, 'samples': 6696960, 'steps': 34879, 'loss/train': 1.5091241598129272} 08/30/2021 19:31:25 - INFO - __main__ - Step 34881: {'lr': 0.00044154142834395947, 'samples': 6697152, 'steps': 34880, 'loss/train': 1.980600118637085} 08/30/2021 19:31:27 - INFO - __main__ - Step 34882: {'lr': 0.00044153801795839296, 'samples': 6697344, 'steps': 34881, 'loss/train': 1.2688275575637817} 08/30/2021 19:31:28 - INFO - __main__ - Step 34883: {'lr': 0.00044153460748652245, 'samples': 6697536, 'steps': 34882, 'loss/train': 1.6996781826019287} 08/30/2021 19:31:28 - INFO - __main__ - Step 34884: {'lr': 0.00044153119692834944, 'samples': 6697728, 'steps': 34883, 'loss/train': 1.1240493059158325} 08/30/2021 19:31:29 - INFO - __main__ - Step 34885: {'lr': 0.0004415277862838753, 'samples': 6697920, 'steps': 34884, 'loss/train': 1.2142804861068726} 08/30/2021 19:31:29 - INFO - __main__ - Step 34886: {'lr': 0.00044152437555310174, 'samples': 6698112, 'steps': 34885, 'loss/train': 1.9530127048492432} 08/30/2021 19:31:30 - INFO - __main__ - Step 34887: {'lr': 0.00044152096473603025, 'samples': 6698304, 'steps': 34886, 'loss/train': 1.6505686044692993} 08/30/2021 19:31:31 - INFO - __main__ - Step 34888: {'lr': 0.00044151755383266234, 'samples': 6698496, 'steps': 34887, 'loss/train': 1.431886076927185} 08/30/2021 19:31:31 - INFO - __main__ - Step 34889: {'lr': 0.0004415141428429997, 'samples': 6698688, 'steps': 34888, 'loss/train': 1.5804921388626099} 08/30/2021 19:31:32 - INFO - __main__ - Step 34890: {'lr': 0.0004415107317670436, 'samples': 6698880, 'steps': 34889, 'loss/train': 1.5146671533584595} 08/30/2021 19:31:32 - INFO - __main__ - Step 34891: {'lr': 0.0004415073206047958, 'samples': 6699072, 'steps': 34890, 'loss/train': 1.518310308456421} 08/30/2021 19:31:33 - INFO - __main__ - Step 34892: {'lr': 0.0004415039093562577, 'samples': 6699264, 'steps': 34891, 'loss/train': 0.8351407051086426} 08/30/2021 19:31:34 - INFO - __main__ - Step 34893: {'lr': 0.00044150049802143095, 'samples': 6699456, 'steps': 34892, 'loss/train': 0.9097894430160522} 08/30/2021 19:31:34 - INFO - __main__ - Step 34894: {'lr': 0.00044149708660031704, 'samples': 6699648, 'steps': 34893, 'loss/train': 1.442458987236023} 08/30/2021 19:31:35 - INFO - __main__ - Step 34895: {'lr': 0.0004414936750929174, 'samples': 6699840, 'steps': 34894, 'loss/train': 1.6313551664352417} 08/30/2021 19:31:35 - INFO - __main__ - Step 34896: {'lr': 0.0004414902634992338, 'samples': 6700032, 'steps': 34895, 'loss/train': 1.3373081684112549} 08/30/2021 19:31:35 - INFO - __main__ - Step 34897: {'lr': 0.0004414868518192675, 'samples': 6700224, 'steps': 34896, 'loss/train': 1.1038962602615356} 08/30/2021 19:31:37 - INFO - __main__ - Step 34898: {'lr': 0.0004414834400530203, 'samples': 6700416, 'steps': 34897, 'loss/train': 0.8443583250045776} 08/30/2021 19:31:37 - INFO - __main__ - Step 34899: {'lr': 0.00044148002820049354, 'samples': 6700608, 'steps': 34898, 'loss/train': 1.4998301267623901} 08/30/2021 19:31:37 - INFO - __main__ - Step 34900: {'lr': 0.00044147661626168887, 'samples': 6700800, 'steps': 34899, 'loss/train': 1.3775559663772583} 08/30/2021 19:31:38 - INFO - __main__ - Step 34901: {'lr': 0.0004414732042366078, 'samples': 6700992, 'steps': 34900, 'loss/train': 2.135401964187622} 08/30/2021 19:31:38 - INFO - __main__ - Step 34902: {'lr': 0.00044146979212525184, 'samples': 6701184, 'steps': 34901, 'loss/train': 1.555981993675232} 08/30/2021 19:31:40 - INFO - __main__ - Step 34903: {'lr': 0.0004414663799276225, 'samples': 6701376, 'steps': 34902, 'loss/train': 1.308225393295288} 08/30/2021 19:31:40 - INFO - __main__ - Step 34904: {'lr': 0.0004414629676437214, 'samples': 6701568, 'steps': 34903, 'loss/train': 1.3855127096176147} 08/30/2021 19:31:40 - INFO - __main__ - Step 34905: {'lr': 0.00044145955527355007, 'samples': 6701760, 'steps': 34904, 'loss/train': 1.6369949579238892} 08/30/2021 19:31:41 - INFO - __main__ - Step 34906: {'lr': 0.00044145614281711, 'samples': 6701952, 'steps': 34905, 'loss/train': 1.4939477443695068} 08/30/2021 19:31:41 - INFO - __main__ - Step 34907: {'lr': 0.00044145273027440275, 'samples': 6702144, 'steps': 34906, 'loss/train': 0.7918360233306885} 08/30/2021 19:31:43 - INFO - __main__ - Step 34908: {'lr': 0.0004414493176454298, 'samples': 6702336, 'steps': 34907, 'loss/train': 1.0705316066741943} 08/30/2021 19:31:43 - INFO - __main__ - Step 34909: {'lr': 0.0004414459049301929, 'samples': 6702528, 'steps': 34908, 'loss/train': 1.296346664428711} 08/30/2021 19:31:43 - INFO - __main__ - Step 34910: {'lr': 0.00044144249212869327, 'samples': 6702720, 'steps': 34909, 'loss/train': 1.7491952180862427} 08/30/2021 19:31:44 - INFO - __main__ - Step 34911: {'lr': 0.0004414390792409326, 'samples': 6702912, 'steps': 34910, 'loss/train': 1.4354376792907715} 08/30/2021 19:31:44 - INFO - __main__ - Step 34912: {'lr': 0.0004414356662669126, 'samples': 6703104, 'steps': 34911, 'loss/train': 1.414766788482666} 08/30/2021 19:31:46 - INFO - __main__ - Step 34913: {'lr': 0.0004414322532066345, 'samples': 6703296, 'steps': 34912, 'loss/train': 1.2923349142074585} 08/30/2021 19:31:46 - INFO - __main__ - Step 34914: {'lr': 0.0004414288400601, 'samples': 6703488, 'steps': 34913, 'loss/train': 1.2957944869995117} 08/30/2021 19:31:47 - INFO - __main__ - Step 34915: {'lr': 0.0004414254268273107, 'samples': 6703680, 'steps': 34914, 'loss/train': 1.2687324285507202} 08/30/2021 19:31:47 - INFO - __main__ - Step 34916: {'lr': 0.0004414220135082679, 'samples': 6703872, 'steps': 34915, 'loss/train': 1.5417463779449463} 08/30/2021 19:31:47 - INFO - __main__ - Step 34917: {'lr': 0.0004414186001029734, 'samples': 6704064, 'steps': 34916, 'loss/train': 2.081559896469116} 08/30/2021 19:31:49 - INFO - __main__ - Step 34918: {'lr': 0.00044141518661142864, 'samples': 6704256, 'steps': 34917, 'loss/train': 1.0758578777313232} 08/30/2021 19:31:49 - INFO - __main__ - Step 34919: {'lr': 0.0004414117730336351, 'samples': 6704448, 'steps': 34918, 'loss/train': 1.3303520679473877} 08/30/2021 19:31:50 - INFO - __main__ - Step 34920: {'lr': 0.0004414083593695944, 'samples': 6704640, 'steps': 34919, 'loss/train': 1.7778058052062988} 08/30/2021 19:31:50 - INFO - __main__ - Step 34921: {'lr': 0.0004414049456193081, 'samples': 6704832, 'steps': 34920, 'loss/train': 1.1302248239517212} 08/30/2021 19:31:50 - INFO - __main__ - Step 34922: {'lr': 0.00044140153178277765, 'samples': 6705024, 'steps': 34921, 'loss/train': 1.0757726430892944} 08/30/2021 19:31:51 - INFO - __main__ - Step 34923: {'lr': 0.0004413981178600046, 'samples': 6705216, 'steps': 34922, 'loss/train': 1.4501041173934937} 08/30/2021 19:31:52 - INFO - __main__ - Step 34924: {'lr': 0.00044139470385099047, 'samples': 6705408, 'steps': 34923, 'loss/train': 0.9826469421386719} 08/30/2021 19:31:53 - INFO - __main__ - Step 34925: {'lr': 0.0004413912897557369, 'samples': 6705600, 'steps': 34924, 'loss/train': 1.6712535619735718} 08/30/2021 19:31:53 - INFO - __main__ - Step 34926: {'lr': 0.0004413878755742454, 'samples': 6705792, 'steps': 34925, 'loss/train': 1.4016990661621094} 08/30/2021 19:31:53 - INFO - __main__ - Step 34927: {'lr': 0.00044138446130651736, 'samples': 6705984, 'steps': 34926, 'loss/train': 1.0843738317489624} 08/30/2021 19:31:54 - INFO - __main__ - Step 34928: {'lr': 0.00044138104695255455, 'samples': 6706176, 'steps': 34927, 'loss/train': 1.0599063634872437} 08/30/2021 19:31:55 - INFO - __main__ - Step 34929: {'lr': 0.00044137763251235837, 'samples': 6706368, 'steps': 34928, 'loss/train': 1.0353928804397583} 08/30/2021 19:31:56 - INFO - __main__ - Step 34930: {'lr': 0.0004413742179859304, 'samples': 6706560, 'steps': 34929, 'loss/train': 1.6535227298736572} 08/30/2021 19:31:56 - INFO - __main__ - Step 34931: {'lr': 0.00044137080337327205, 'samples': 6706752, 'steps': 34930, 'loss/train': 1.1370371580123901} 08/30/2021 19:31:56 - INFO - __main__ - Step 34932: {'lr': 0.000441367388674385, 'samples': 6706944, 'steps': 34931, 'loss/train': 1.3399639129638672} 08/30/2021 19:31:57 - INFO - __main__ - Step 34933: {'lr': 0.00044136397388927083, 'samples': 6707136, 'steps': 34932, 'loss/train': 1.2659764289855957} 08/30/2021 19:31:59 - INFO - __main__ - Step 34934: {'lr': 0.000441360559017931, 'samples': 6707328, 'steps': 34933, 'loss/train': 1.408302664756775} 08/30/2021 19:31:59 - INFO - __main__ - Step 34935: {'lr': 0.00044135714406036696, 'samples': 6707520, 'steps': 34934, 'loss/train': 0.8814275860786438} 08/30/2021 19:32:00 - INFO - __main__ - Step 34936: {'lr': 0.00044135372901658046, 'samples': 6707712, 'steps': 34935, 'loss/train': 1.4974032640457153} 08/30/2021 19:32:00 - INFO - __main__ - Step 34937: {'lr': 0.0004413503138865729, 'samples': 6707904, 'steps': 34936, 'loss/train': 1.4900633096694946} 08/30/2021 19:32:00 - INFO - __main__ - Step 34938: {'lr': 0.00044134689867034583, 'samples': 6708096, 'steps': 34937, 'loss/train': 1.1023952960968018} 08/30/2021 19:32:02 - INFO - __main__ - Step 34939: {'lr': 0.00044134348336790074, 'samples': 6708288, 'steps': 34938, 'loss/train': 1.4308836460113525} 08/30/2021 19:32:02 - INFO - __main__ - Step 34940: {'lr': 0.0004413400679792393, 'samples': 6708480, 'steps': 34939, 'loss/train': 1.3813395500183105} 08/30/2021 19:32:03 - INFO - __main__ - Step 34941: {'lr': 0.00044133665250436295, 'samples': 6708672, 'steps': 34940, 'loss/train': 1.0480033159255981} 08/30/2021 19:32:03 - INFO - __main__ - Step 34942: {'lr': 0.00044133323694327324, 'samples': 6708864, 'steps': 34941, 'loss/train': 1.8553470373153687} 08/30/2021 19:32:03 - INFO - __main__ - Step 34943: {'lr': 0.0004413298212959718, 'samples': 6709056, 'steps': 34942, 'loss/train': 0.9769366383552551} 08/30/2021 19:32:05 - INFO - __main__ - Step 34944: {'lr': 0.00044132640556246, 'samples': 6709248, 'steps': 34943, 'loss/train': 1.2747609615325928} 08/30/2021 19:32:05 - INFO - __main__ - Step 34945: {'lr': 0.00044132298974273955, 'samples': 6709440, 'steps': 34944, 'loss/train': 1.2658013105392456} 08/30/2021 19:32:06 - INFO - __main__ - Step 34946: {'lr': 0.00044131957383681186, 'samples': 6709632, 'steps': 34945, 'loss/train': 1.5538816452026367} 08/30/2021 19:32:06 - INFO - __main__ - Step 34947: {'lr': 0.0004413161578446785, 'samples': 6709824, 'steps': 34946, 'loss/train': 1.8017503023147583} 08/30/2021 19:32:07 - INFO - __main__ - Step 34948: {'lr': 0.00044131274176634113, 'samples': 6710016, 'steps': 34947, 'loss/train': 1.155334234237671} 08/30/2021 19:32:08 - INFO - __main__ - Step 34949: {'lr': 0.00044130932560180114, 'samples': 6710208, 'steps': 34948, 'loss/train': 0.075958751142025} 08/30/2021 19:32:09 - INFO - __main__ - Step 34950: {'lr': 0.0004413059093510601, 'samples': 6710400, 'steps': 34949, 'loss/train': 1.3488863706588745} 08/30/2021 19:32:09 - INFO - __main__ - Step 34951: {'lr': 0.00044130249301411957, 'samples': 6710592, 'steps': 34950, 'loss/train': 0.6622664928436279} 08/30/2021 19:32:09 - INFO - __main__ - Step 34952: {'lr': 0.0004412990765909811, 'samples': 6710784, 'steps': 34951, 'loss/train': 0.07370854169130325} 08/30/2021 19:32:10 - INFO - __main__ - Step 34953: {'lr': 0.0004412956600816462, 'samples': 6710976, 'steps': 34952, 'loss/train': 1.2174763679504395} 08/30/2021 19:32:10 - INFO - __main__ - Step 34954: {'lr': 0.00044129224348611644, 'samples': 6711168, 'steps': 34953, 'loss/train': 1.7220250368118286} 08/30/2021 19:32:12 - INFO - __main__ - Step 34955: {'lr': 0.0004412888268043934, 'samples': 6711360, 'steps': 34954, 'loss/train': 0.035442106425762177} 08/30/2021 19:32:12 - INFO - __main__ - Step 34956: {'lr': 0.0004412854100364785, 'samples': 6711552, 'steps': 34955, 'loss/train': 1.458470344543457} 08/30/2021 19:32:13 - INFO - __main__ - Step 34957: {'lr': 0.0004412819931823734, 'samples': 6711744, 'steps': 34956, 'loss/train': 1.0985313653945923} 08/30/2021 19:32:13 - INFO - __main__ - Step 34958: {'lr': 0.0004412785762420795, 'samples': 6711936, 'steps': 34957, 'loss/train': 1.5779829025268555} 08/30/2021 19:32:13 - INFO - __main__ - Step 34959: {'lr': 0.0004412751592155985, 'samples': 6712128, 'steps': 34958, 'loss/train': 1.0971028804779053} 08/30/2021 19:32:15 - INFO - __main__ - Step 34960: {'lr': 0.00044127174210293186, 'samples': 6712320, 'steps': 34959, 'loss/train': 1.132872223854065} 08/30/2021 19:32:15 - INFO - __main__ - Step 34961: {'lr': 0.0004412683249040811, 'samples': 6712512, 'steps': 34960, 'loss/train': 1.2651100158691406} 08/30/2021 19:32:16 - INFO - __main__ - Step 34962: {'lr': 0.0004412649076190478, 'samples': 6712704, 'steps': 34961, 'loss/train': 1.420601725578308} 08/30/2021 19:32:16 - INFO - __main__ - Step 34963: {'lr': 0.00044126149024783346, 'samples': 6712896, 'steps': 34962, 'loss/train': 1.4611116647720337} 08/30/2021 19:32:16 - INFO - __main__ - Step 34964: {'lr': 0.0004412580727904396, 'samples': 6713088, 'steps': 34963, 'loss/train': 1.36281418800354} 08/30/2021 19:32:18 - INFO - __main__ - Step 34965: {'lr': 0.0004412546552468679, 'samples': 6713280, 'steps': 34964, 'loss/train': 1.1717272996902466} 08/30/2021 19:32:18 - INFO - __main__ - Step 34966: {'lr': 0.00044125123761711975, 'samples': 6713472, 'steps': 34965, 'loss/train': 1.4397194385528564} 08/30/2021 19:32:19 - INFO - __main__ - Step 34967: {'lr': 0.00044124781990119677, 'samples': 6713664, 'steps': 34966, 'loss/train': 1.1725163459777832} 08/30/2021 19:32:19 - INFO - __main__ - Step 34968: {'lr': 0.0004412444020991004, 'samples': 6713856, 'steps': 34967, 'loss/train': 0.12758542597293854} 08/30/2021 19:32:19 - INFO - __main__ - Step 34969: {'lr': 0.0004412409842108324, 'samples': 6714048, 'steps': 34968, 'loss/train': 1.1853598356246948} 08/30/2021 19:32:21 - INFO - __main__ - Step 34970: {'lr': 0.0004412375662363941, 'samples': 6714240, 'steps': 34969, 'loss/train': 0.9862979650497437} 08/30/2021 19:32:21 - INFO - __main__ - Step 34971: {'lr': 0.00044123414817578705, 'samples': 6714432, 'steps': 34970, 'loss/train': 1.3713527917861938} 08/30/2021 19:32:22 - INFO - __main__ - Step 34972: {'lr': 0.00044123073002901286, 'samples': 6714624, 'steps': 34971, 'loss/train': 1.966863751411438} 08/30/2021 19:32:22 - INFO - __main__ - Step 34973: {'lr': 0.0004412273117960731, 'samples': 6714816, 'steps': 34972, 'loss/train': 1.3497530221939087} 08/30/2021 19:32:22 - INFO - __main__ - Step 34974: {'lr': 0.00044122389347696925, 'samples': 6715008, 'steps': 34973, 'loss/train': 1.4592618942260742} 08/30/2021 19:32:24 - INFO - __main__ - Step 34975: {'lr': 0.0004412204750717028, 'samples': 6715200, 'steps': 34974, 'loss/train': 1.2592018842697144} 08/30/2021 19:32:25 - INFO - __main__ - Step 34976: {'lr': 0.00044121705658027545, 'samples': 6715392, 'steps': 34975, 'loss/train': 0.8790485858917236} 08/30/2021 19:32:25 - INFO - __main__ - Step 34977: {'lr': 0.00044121363800268853, 'samples': 6715584, 'steps': 34976, 'loss/train': 1.33357572555542} 08/30/2021 19:32:25 - INFO - __main__ - Step 34978: {'lr': 0.0004412102193389438, 'samples': 6715776, 'steps': 34977, 'loss/train': 1.4491406679153442} 08/30/2021 19:32:26 - INFO - __main__ - Step 34979: {'lr': 0.0004412068005890427, 'samples': 6715968, 'steps': 34978, 'loss/train': 1.7957377433776855} 08/30/2021 19:32:26 - INFO - __main__ - Step 34980: {'lr': 0.0004412033817529867, 'samples': 6716160, 'steps': 34979, 'loss/train': 3.723341703414917} 08/30/2021 19:32:28 - INFO - __main__ - Step 34981: {'lr': 0.0004411999628307775, 'samples': 6716352, 'steps': 34980, 'loss/train': 2.0891482830047607} 08/30/2021 19:32:28 - INFO - __main__ - Step 34982: {'lr': 0.0004411965438224164, 'samples': 6716544, 'steps': 34981, 'loss/train': 2.0819387435913086} 08/30/2021 19:32:29 - INFO - __main__ - Step 34983: {'lr': 0.0004411931247279052, 'samples': 6716736, 'steps': 34982, 'loss/train': 1.2802892923355103} 08/30/2021 19:32:29 - INFO - __main__ - Step 34984: {'lr': 0.00044118970554724523, 'samples': 6716928, 'steps': 34983, 'loss/train': 0.2615245580673218} 08/30/2021 19:32:29 - INFO - __main__ - Step 34985: {'lr': 0.0004411862862804382, 'samples': 6717120, 'steps': 34984, 'loss/train': 1.3118356466293335} 08/30/2021 19:32:31 - INFO - __main__ - Step 34986: {'lr': 0.0004411828669274856, 'samples': 6717312, 'steps': 34985, 'loss/train': 0.8165215253829956} 08/30/2021 19:32:31 - INFO - __main__ - Step 34987: {'lr': 0.0004411794474883889, 'samples': 6717504, 'steps': 34986, 'loss/train': 1.1048524379730225} 08/30/2021 19:32:32 - INFO - __main__ - Step 34988: {'lr': 0.0004411760279631497, 'samples': 6717696, 'steps': 34987, 'loss/train': 1.797042727470398} 08/30/2021 19:32:32 - INFO - __main__ - Step 34989: {'lr': 0.0004411726083517696, 'samples': 6717888, 'steps': 34988, 'loss/train': 1.6182481050491333} 08/30/2021 19:32:32 - INFO - __main__ - Step 34990: {'lr': 0.00044116918865425004, 'samples': 6718080, 'steps': 34989, 'loss/train': 5.43362283706665} 08/30/2021 19:32:34 - INFO - __main__ - Step 34991: {'lr': 0.00044116576887059255, 'samples': 6718272, 'steps': 34990, 'loss/train': 1.5861461162567139} 08/30/2021 19:32:35 - INFO - __main__ - Step 34992: {'lr': 0.0004411623490007988, 'samples': 6718464, 'steps': 34991, 'loss/train': 1.012242078781128} 08/30/2021 19:32:35 - INFO - __main__ - Step 34993: {'lr': 0.0004411589290448701, 'samples': 6718656, 'steps': 34992, 'loss/train': 1.86570143699646} 08/30/2021 19:32:35 - INFO - __main__ - Step 34994: {'lr': 0.0004411555090028082, 'samples': 6718848, 'steps': 34993, 'loss/train': 1.142942190170288} 08/30/2021 19:32:36 - INFO - __main__ - Step 34995: {'lr': 0.00044115208887461464, 'samples': 6719040, 'steps': 34994, 'loss/train': 1.1457595825195312} 08/30/2021 19:32:37 - INFO - __main__ - Step 34996: {'lr': 0.00044114866866029086, 'samples': 6719232, 'steps': 34995, 'loss/train': 1.43965744972229} 08/30/2021 19:32:38 - INFO - __main__ - Step 34997: {'lr': 0.00044114524835983844, 'samples': 6719424, 'steps': 34996, 'loss/train': 1.3998771905899048} 08/30/2021 19:32:38 - INFO - __main__ - Step 34998: {'lr': 0.00044114182797325884, 'samples': 6719616, 'steps': 34997, 'loss/train': 1.418233871459961} 08/30/2021 19:32:38 - INFO - __main__ - Step 34999: {'lr': 0.0004411384075005538, 'samples': 6719808, 'steps': 34998, 'loss/train': 1.4251606464385986} 08/30/2021 19:32:39 - INFO - __main__ - Step 35000: {'lr': 0.0004411349869417247, 'samples': 6720000, 'steps': 34999, 'loss/train': 1.608568787574768} 08/30/2021 19:32:39 - INFO - __main__ - Step 35001: {'lr': 0.00044113156629677313, 'samples': 6720192, 'steps': 35000, 'loss/train': 1.2498257160186768} 08/30/2021 19:32:40 - INFO - __main__ - Step 35002: {'lr': 0.00044112814556570066, 'samples': 6720384, 'steps': 35001, 'loss/train': 1.1979851722717285} 08/30/2021 19:32:41 - INFO - __main__ - Step 35003: {'lr': 0.00044112472474850875, 'samples': 6720576, 'steps': 35002, 'loss/train': 1.4907722473144531} 08/30/2021 19:32:41 - INFO - __main__ - Step 35004: {'lr': 0.000441121303845199, 'samples': 6720768, 'steps': 35003, 'loss/train': 1.3451606035232544} 08/30/2021 19:32:42 - INFO - __main__ - Step 35005: {'lr': 0.0004411178828557729, 'samples': 6720960, 'steps': 35004, 'loss/train': 1.400999665260315} 08/30/2021 19:32:42 - INFO - __main__ - Step 35006: {'lr': 0.00044111446178023205, 'samples': 6721152, 'steps': 35005, 'loss/train': 1.5949101448059082} 08/30/2021 19:32:44 - INFO - __main__ - Step 35007: {'lr': 0.000441111040618578, 'samples': 6721344, 'steps': 35006, 'loss/train': 1.2730093002319336} 08/30/2021 19:32:44 - INFO - __main__ - Step 35008: {'lr': 0.0004411076193708122, 'samples': 6721536, 'steps': 35007, 'loss/train': 1.6350964307785034} 08/30/2021 19:32:45 - INFO - __main__ - Step 35009: {'lr': 0.00044110419803693635, 'samples': 6721728, 'steps': 35008, 'loss/train': 0.588362455368042} 08/30/2021 19:32:45 - INFO - __main__ - Step 35010: {'lr': 0.00044110077661695194, 'samples': 6721920, 'steps': 35009, 'loss/train': 0.6230650544166565} 08/30/2021 19:32:45 - INFO - __main__ - Step 35011: {'lr': 0.00044109735511086036, 'samples': 6722112, 'steps': 35010, 'loss/train': 0.5072710514068604} 08/30/2021 19:32:47 - INFO - __main__ - Step 35012: {'lr': 0.00044109393351866324, 'samples': 6722304, 'steps': 35011, 'loss/train': 1.3631649017333984} 08/30/2021 19:32:47 - INFO - __main__ - Step 35013: {'lr': 0.0004410905118403622, 'samples': 6722496, 'steps': 35012, 'loss/train': 2.4922847747802734} 08/30/2021 19:32:48 - INFO - __main__ - Step 35014: {'lr': 0.0004410870900759587, 'samples': 6722688, 'steps': 35013, 'loss/train': 1.4231981039047241} 08/30/2021 19:32:48 - INFO - __main__ - Step 35015: {'lr': 0.0004410836682254543, 'samples': 6722880, 'steps': 35014, 'loss/train': 1.2394388914108276} 08/30/2021 19:32:48 - INFO - __main__ - Step 35016: {'lr': 0.0004410802462888506, 'samples': 6723072, 'steps': 35015, 'loss/train': 1.2930346727371216} 08/30/2021 19:32:50 - INFO - __main__ - Step 35017: {'lr': 0.00044107682426614903, 'samples': 6723264, 'steps': 35016, 'loss/train': 1.2831521034240723} 08/30/2021 19:32:50 - INFO - __main__ - Step 35018: {'lr': 0.00044107340215735125, 'samples': 6723456, 'steps': 35017, 'loss/train': 0.6018421649932861} 08/30/2021 19:32:51 - INFO - __main__ - Step 35019: {'lr': 0.00044106997996245866, 'samples': 6723648, 'steps': 35018, 'loss/train': 1.442072868347168} 08/30/2021 19:32:51 - INFO - __main__ - Step 35020: {'lr': 0.000441066557681473, 'samples': 6723840, 'steps': 35019, 'loss/train': 1.624201774597168} 08/30/2021 19:32:51 - INFO - __main__ - Step 35021: {'lr': 0.00044106313531439565, 'samples': 6724032, 'steps': 35020, 'loss/train': 1.4344145059585571} 08/30/2021 19:32:53 - INFO - __main__ - Step 35022: {'lr': 0.00044105971286122816, 'samples': 6724224, 'steps': 35021, 'loss/train': 1.5966792106628418} 08/30/2021 19:32:53 - INFO - __main__ - Step 35023: {'lr': 0.00044105629032197214, 'samples': 6724416, 'steps': 35022, 'loss/train': 1.3417925834655762} 08/30/2021 19:32:54 - INFO - __main__ - Step 35024: {'lr': 0.0004410528676966291, 'samples': 6724608, 'steps': 35023, 'loss/train': 1.6505361795425415} 08/30/2021 19:32:54 - INFO - __main__ - Step 35025: {'lr': 0.00044104944498520054, 'samples': 6724800, 'steps': 35024, 'loss/train': 1.2967965602874756} 08/30/2021 19:32:54 - INFO - __main__ - Step 35026: {'lr': 0.00044104602218768805, 'samples': 6724992, 'steps': 35025, 'loss/train': 1.8254172801971436} 08/30/2021 19:32:56 - INFO - __main__ - Step 35027: {'lr': 0.0004410425993040933, 'samples': 6725184, 'steps': 35026, 'loss/train': 0.9522691369056702} 08/30/2021 19:32:56 - INFO - __main__ - Step 35028: {'lr': 0.0004410391763344176, 'samples': 6725376, 'steps': 35027, 'loss/train': 0.9665768146514893} 08/30/2021 19:32:57 - INFO - __main__ - Step 35029: {'lr': 0.00044103575327866264, 'samples': 6725568, 'steps': 35028, 'loss/train': 1.1050482988357544} 08/30/2021 19:32:57 - INFO - __main__ - Step 35030: {'lr': 0.0004410323301368299, 'samples': 6725760, 'steps': 35029, 'loss/train': 1.7607635259628296} 08/30/2021 19:32:57 - INFO - __main__ - Step 35031: {'lr': 0.0004410289069089209, 'samples': 6725952, 'steps': 35030, 'loss/train': 0.9335264563560486} 08/30/2021 19:32:59 - INFO - __main__ - Step 35032: {'lr': 0.0004410254835949372, 'samples': 6726144, 'steps': 35031, 'loss/train': 0.9821897745132446} 08/30/2021 19:32:59 - INFO - __main__ - Step 35033: {'lr': 0.00044102206019488045, 'samples': 6726336, 'steps': 35032, 'loss/train': 0.6056498289108276} 08/30/2021 19:33:00 - INFO - __main__ - Step 35034: {'lr': 0.00044101863670875207, 'samples': 6726528, 'steps': 35033, 'loss/train': 1.4131925106048584} 08/30/2021 19:33:00 - INFO - __main__ - Step 35035: {'lr': 0.0004410152131365536, 'samples': 6726720, 'steps': 35034, 'loss/train': 1.3641514778137207} 08/30/2021 19:33:00 - INFO - __main__ - Step 35036: {'lr': 0.00044101178947828667, 'samples': 6726912, 'steps': 35035, 'loss/train': 0.9625906944274902} 08/30/2021 19:33:01 - INFO - __main__ - Step 35037: {'lr': 0.0004410083657339528, 'samples': 6727104, 'steps': 35036, 'loss/train': 2.07183837890625} 08/30/2021 19:33:02 - INFO - __main__ - Step 35038: {'lr': 0.00044100494190355347, 'samples': 6727296, 'steps': 35037, 'loss/train': 0.5002424120903015} 08/30/2021 19:33:03 - INFO - __main__ - Step 35039: {'lr': 0.0004410015179870903, 'samples': 6727488, 'steps': 35038, 'loss/train': 1.127249836921692} 08/30/2021 19:33:03 - INFO - __main__ - Step 35040: {'lr': 0.0004409980939845647, 'samples': 6727680, 'steps': 35039, 'loss/train': 1.3199843168258667} 08/30/2021 19:33:03 - INFO - __main__ - Step 35041: {'lr': 0.00044099466989597837, 'samples': 6727872, 'steps': 35040, 'loss/train': 1.1282857656478882} 08/30/2021 19:33:04 - INFO - __main__ - Step 35042: {'lr': 0.00044099124572133283, 'samples': 6728064, 'steps': 35041, 'loss/train': 1.9509625434875488} 08/30/2021 19:33:06 - INFO - __main__ - Step 35043: {'lr': 0.00044098782146062955, 'samples': 6728256, 'steps': 35042, 'loss/train': 1.8122310638427734} 08/30/2021 19:33:06 - INFO - __main__ - Step 35044: {'lr': 0.00044098439711387006, 'samples': 6728448, 'steps': 35043, 'loss/train': 1.501436710357666} 08/30/2021 19:33:07 - INFO - __main__ - Step 35045: {'lr': 0.000440980972681056, 'samples': 6728640, 'steps': 35044, 'loss/train': 1.2846965789794922} 08/30/2021 19:33:07 - INFO - __main__ - Step 35046: {'lr': 0.0004409775481621888, 'samples': 6728832, 'steps': 35045, 'loss/train': 1.9868472814559937} 08/30/2021 19:33:07 - INFO - __main__ - Step 35047: {'lr': 0.0004409741235572701, 'samples': 6729024, 'steps': 35046, 'loss/train': 1.2437779903411865} 08/30/2021 19:33:09 - INFO - __main__ - Step 35048: {'lr': 0.0004409706988663015, 'samples': 6729216, 'steps': 35047, 'loss/train': 1.5886855125427246} 08/30/2021 19:33:09 - INFO - __main__ - Step 35049: {'lr': 0.00044096727408928426, 'samples': 6729408, 'steps': 35048, 'loss/train': 1.4767874479293823} 08/30/2021 19:33:10 - INFO - __main__ - Step 35050: {'lr': 0.0004409638492262202, 'samples': 6729600, 'steps': 35049, 'loss/train': 2.264859676361084} 08/30/2021 19:33:10 - INFO - __main__ - Step 35051: {'lr': 0.0004409604242771108, 'samples': 6729792, 'steps': 35050, 'loss/train': 1.2183133363723755} 08/30/2021 19:33:10 - INFO - __main__ - Step 35052: {'lr': 0.0004409569992419576, 'samples': 6729984, 'steps': 35051, 'loss/train': 1.7627239227294922} 08/30/2021 19:33:12 - INFO - __main__ - Step 35053: {'lr': 0.0004409535741207621, 'samples': 6730176, 'steps': 35052, 'loss/train': 1.620200514793396} 08/30/2021 19:33:12 - INFO - __main__ - Step 35054: {'lr': 0.00044095014891352584, 'samples': 6730368, 'steps': 35053, 'loss/train': 1.8186169862747192} 08/30/2021 19:33:12 - INFO - __main__ - Step 35055: {'lr': 0.0004409467236202505, 'samples': 6730560, 'steps': 35054, 'loss/train': 1.1668120622634888} 08/30/2021 19:33:13 - INFO - __main__ - Step 35056: {'lr': 0.0004409432982409374, 'samples': 6730752, 'steps': 35055, 'loss/train': 1.3651800155639648} 08/30/2021 19:33:13 - INFO - __main__ - Step 35057: {'lr': 0.0004409398727755882, 'samples': 6730944, 'steps': 35056, 'loss/train': 0.658411979675293} 08/30/2021 19:33:15 - INFO - __main__ - Step 35058: {'lr': 0.00044093644722420445, 'samples': 6731136, 'steps': 35057, 'loss/train': 1.2759971618652344} 08/30/2021 19:33:15 - INFO - __main__ - Step 35059: {'lr': 0.00044093302158678766, 'samples': 6731328, 'steps': 35058, 'loss/train': 1.3347318172454834} 08/30/2021 19:33:16 - INFO - __main__ - Step 35060: {'lr': 0.0004409295958633394, 'samples': 6731520, 'steps': 35059, 'loss/train': 0.04077564552426338} 08/30/2021 19:33:16 - INFO - __main__ - Step 35061: {'lr': 0.00044092617005386125, 'samples': 6731712, 'steps': 35060, 'loss/train': 0.03668401390314102} 08/30/2021 19:33:17 - INFO - __main__ - Step 35062: {'lr': 0.00044092274415835473, 'samples': 6731904, 'steps': 35061, 'loss/train': 1.5081043243408203} 08/30/2021 19:33:17 - INFO - __main__ - Step 35063: {'lr': 0.0004409193181768213, 'samples': 6732096, 'steps': 35062, 'loss/train': 1.809552550315857} 08/30/2021 19:33:18 - INFO - __main__ - Step 35064: {'lr': 0.00044091589210926266, 'samples': 6732288, 'steps': 35063, 'loss/train': 1.3295716047286987} 08/30/2021 19:33:19 - INFO - __main__ - Step 35065: {'lr': 0.00044091246595568025, 'samples': 6732480, 'steps': 35064, 'loss/train': 1.4741064310073853} 08/30/2021 19:33:19 - INFO - __main__ - Step 35066: {'lr': 0.00044090903971607555, 'samples': 6732672, 'steps': 35065, 'loss/train': 1.6967097520828247} 08/30/2021 19:33:20 - INFO - __main__ - Step 35067: {'lr': 0.0004409056133904502, 'samples': 6732864, 'steps': 35066, 'loss/train': 1.4284765720367432} 08/30/2021 19:33:20 - INFO - __main__ - Step 35068: {'lr': 0.00044090218697880577, 'samples': 6733056, 'steps': 35067, 'loss/train': 1.3743704557418823} 08/30/2021 19:33:21 - INFO - __main__ - Step 35069: {'lr': 0.0004408987604811437, 'samples': 6733248, 'steps': 35068, 'loss/train': 1.3716342449188232} 08/30/2021 19:33:22 - INFO - __main__ - Step 35070: {'lr': 0.00044089533389746573, 'samples': 6733440, 'steps': 35069, 'loss/train': 1.1787060499191284} 08/30/2021 19:33:22 - INFO - __main__ - Step 35071: {'lr': 0.00044089190722777316, 'samples': 6733632, 'steps': 35070, 'loss/train': 1.353332281112671} 08/30/2021 19:33:23 - INFO - __main__ - Step 35072: {'lr': 0.00044088848047206763, 'samples': 6733824, 'steps': 35071, 'loss/train': 1.9297947883605957} 08/30/2021 19:33:23 - INFO - __main__ - Step 35073: {'lr': 0.0004408850536303507, 'samples': 6734016, 'steps': 35072, 'loss/train': 1.4050127267837524} 08/30/2021 19:33:24 - INFO - __main__ - Step 35074: {'lr': 0.000440881626702624, 'samples': 6734208, 'steps': 35073, 'loss/train': 1.686198353767395} 08/30/2021 19:33:25 - INFO - __main__ - Step 35075: {'lr': 0.00044087819968888887, 'samples': 6734400, 'steps': 35074, 'loss/train': 1.3090829849243164} 08/30/2021 19:33:25 - INFO - __main__ - Step 35076: {'lr': 0.00044087477258914696, 'samples': 6734592, 'steps': 35075, 'loss/train': 1.817962884902954} 08/30/2021 19:33:25 - INFO - __main__ - Step 35077: {'lr': 0.00044087134540339996, 'samples': 6734784, 'steps': 35076, 'loss/train': 1.5255579948425293} 08/30/2021 19:33:26 - INFO - __main__ - Step 35078: {'lr': 0.00044086791813164916, 'samples': 6734976, 'steps': 35077, 'loss/train': 1.0958340167999268} 08/30/2021 19:33:27 - INFO - __main__ - Step 35079: {'lr': 0.00044086449077389636, 'samples': 6735168, 'steps': 35078, 'loss/train': 1.1610349416732788} 08/30/2021 19:33:28 - INFO - __main__ - Step 35080: {'lr': 0.0004408610633301428, 'samples': 6735360, 'steps': 35079, 'loss/train': 1.8730825185775757} 08/30/2021 19:33:28 - INFO - __main__ - Step 35081: {'lr': 0.00044085763580039027, 'samples': 6735552, 'steps': 35080, 'loss/train': 1.4571410417556763} 08/30/2021 19:33:29 - INFO - __main__ - Step 35082: {'lr': 0.0004408542081846402, 'samples': 6735744, 'steps': 35081, 'loss/train': 1.156598687171936} 08/30/2021 19:33:29 - INFO - __main__ - Step 35083: {'lr': 0.0004408507804828942, 'samples': 6735936, 'steps': 35082, 'loss/train': 0.732154130935669} 08/30/2021 19:33:29 - INFO - __main__ - Step 35084: {'lr': 0.00044084735269515375, 'samples': 6736128, 'steps': 35083, 'loss/train': 1.5006557703018188} 08/30/2021 19:33:31 - INFO - __main__ - Step 35085: {'lr': 0.0004408439248214205, 'samples': 6736320, 'steps': 35084, 'loss/train': 1.4012720584869385} 08/30/2021 19:33:31 - INFO - __main__ - Step 35086: {'lr': 0.00044084049686169584, 'samples': 6736512, 'steps': 35085, 'loss/train': 2.148707389831543} 08/30/2021 19:33:32 - INFO - __main__ - Step 35087: {'lr': 0.00044083706881598147, 'samples': 6736704, 'steps': 35086, 'loss/train': 1.2792222499847412} 08/30/2021 19:33:32 - INFO - __main__ - Step 35088: {'lr': 0.00044083364068427875, 'samples': 6736896, 'steps': 35087, 'loss/train': 0.6709632873535156} 08/30/2021 19:33:32 - INFO - __main__ - Step 35089: {'lr': 0.0004408302124665894, 'samples': 6737088, 'steps': 35088, 'loss/train': 1.5113765001296997} 08/30/2021 19:33:34 - INFO - __main__ - Step 35090: {'lr': 0.00044082678416291495, 'samples': 6737280, 'steps': 35089, 'loss/train': 0.6331438422203064} 08/30/2021 19:33:34 - INFO - __main__ - Step 35091: {'lr': 0.00044082335577325685, 'samples': 6737472, 'steps': 35090, 'loss/train': 1.594581127166748} 08/30/2021 19:33:34 - INFO - __main__ - Step 35092: {'lr': 0.0004408199272976167, 'samples': 6737664, 'steps': 35091, 'loss/train': 1.5178340673446655} 08/30/2021 19:33:35 - INFO - __main__ - Step 35093: {'lr': 0.00044081649873599604, 'samples': 6737856, 'steps': 35092, 'loss/train': 1.6615768671035767} 08/30/2021 19:33:35 - INFO - __main__ - Step 35094: {'lr': 0.0004408130700883964, 'samples': 6738048, 'steps': 35093, 'loss/train': 1.477236270904541} 08/30/2021 19:33:38 - INFO - __main__ - Step 35095: {'lr': 0.0004408096413548193, 'samples': 6738240, 'steps': 35094, 'loss/train': 0.9638330340385437} 08/30/2021 19:33:38 - INFO - __main__ - Step 35096: {'lr': 0.00044080621253526637, 'samples': 6738432, 'steps': 35095, 'loss/train': 0.21695414185523987} 08/30/2021 19:33:38 - INFO - __main__ - Step 35097: {'lr': 0.00044080278362973913, 'samples': 6738624, 'steps': 35096, 'loss/train': 0.15020699799060822} 08/30/2021 19:33:39 - INFO - __main__ - Step 35098: {'lr': 0.00044079935463823904, 'samples': 6738816, 'steps': 35097, 'loss/train': 1.3352291584014893} 08/30/2021 19:33:39 - INFO - __main__ - Step 35099: {'lr': 0.00044079592556076774, 'samples': 6739008, 'steps': 35098, 'loss/train': 1.5562607049942017} 08/30/2021 19:33:40 - INFO - __main__ - Step 35100: {'lr': 0.00044079249639732664, 'samples': 6739200, 'steps': 35099, 'loss/train': 1.4374668598175049} 08/30/2021 19:33:41 - INFO - __main__ - Step 35101: {'lr': 0.00044078906714791757, 'samples': 6739392, 'steps': 35100, 'loss/train': 0.06896452605724335} 08/30/2021 19:33:42 - INFO - __main__ - Step 35102: {'lr': 0.0004407856378125418, 'samples': 6739584, 'steps': 35101, 'loss/train': 1.990705966949463} 08/30/2021 19:33:42 - INFO - __main__ - Step 35103: {'lr': 0.00044078220839120086, 'samples': 6739776, 'steps': 35102, 'loss/train': 1.762894868850708} 08/30/2021 19:33:42 - INFO - __main__ - Step 35104: {'lr': 0.0004407787788838966, 'samples': 6739968, 'steps': 35103, 'loss/train': 1.6660062074661255} 08/30/2021 19:33:43 - INFO - __main__ - Step 35105: {'lr': 0.00044077534929063024, 'samples': 6740160, 'steps': 35104, 'loss/train': 1.545969843864441} 08/30/2021 19:33:44 - INFO - __main__ - Step 35106: {'lr': 0.00044077191961140337, 'samples': 6740352, 'steps': 35105, 'loss/train': 1.2282251119613647} 08/30/2021 19:33:45 - INFO - __main__ - Step 35107: {'lr': 0.00044076848984621775, 'samples': 6740544, 'steps': 35106, 'loss/train': 1.5219817161560059} 08/30/2021 19:33:45 - INFO - __main__ - Step 35108: {'lr': 0.00044076505999507474, 'samples': 6740736, 'steps': 35107, 'loss/train': 1.2070413827896118} 08/30/2021 19:33:45 - INFO - __main__ - Step 35109: {'lr': 0.00044076163005797597, 'samples': 6740928, 'steps': 35108, 'loss/train': 1.923166275024414} 08/30/2021 19:33:46 - INFO - __main__ - Step 35110: {'lr': 0.00044075820003492295, 'samples': 6741120, 'steps': 35109, 'loss/train': 1.5452156066894531} 08/30/2021 19:33:46 - INFO - __main__ - Step 35111: {'lr': 0.0004407547699259173, 'samples': 6741312, 'steps': 35110, 'loss/train': 2.220792770385742} 08/30/2021 19:33:48 - INFO - __main__ - Step 35112: {'lr': 0.0004407513397309604, 'samples': 6741504, 'steps': 35111, 'loss/train': 0.9561098217964172} 08/30/2021 19:33:48 - INFO - __main__ - Step 35113: {'lr': 0.0004407479094500539, 'samples': 6741696, 'steps': 35112, 'loss/train': 1.100181221961975} 08/30/2021 19:33:48 - INFO - __main__ - Step 35114: {'lr': 0.00044074447908319935, 'samples': 6741888, 'steps': 35113, 'loss/train': 1.4713833332061768} 08/30/2021 19:33:49 - INFO - __main__ - Step 35115: {'lr': 0.0004407410486303983, 'samples': 6742080, 'steps': 35114, 'loss/train': 1.253598690032959} 08/30/2021 19:33:49 - INFO - __main__ - Step 35116: {'lr': 0.0004407376180916522, 'samples': 6742272, 'steps': 35115, 'loss/train': 2.0496363639831543} 08/30/2021 19:33:50 - INFO - __main__ - Step 35117: {'lr': 0.0004407341874669627, 'samples': 6742464, 'steps': 35116, 'loss/train': 1.3307188749313354} 08/30/2021 19:33:51 - INFO - __main__ - Step 35118: {'lr': 0.00044073075675633134, 'samples': 6742656, 'steps': 35117, 'loss/train': 1.5264326333999634} 08/30/2021 19:33:51 - INFO - __main__ - Step 35119: {'lr': 0.0004407273259597597, 'samples': 6742848, 'steps': 35118, 'loss/train': 1.7594091892242432} 08/30/2021 19:33:52 - INFO - __main__ - Step 35120: {'lr': 0.0004407238950772492, 'samples': 6743040, 'steps': 35119, 'loss/train': 1.0203707218170166} 08/30/2021 19:33:52 - INFO - __main__ - Step 35121: {'lr': 0.00044072046410880143, 'samples': 6743232, 'steps': 35120, 'loss/train': 0.8387742042541504} 08/30/2021 19:33:53 - INFO - __main__ - Step 35122: {'lr': 0.000440717033054418, 'samples': 6743424, 'steps': 35121, 'loss/train': 1.977790117263794} 08/30/2021 19:33:54 - INFO - __main__ - Step 35123: {'lr': 0.0004407136019141005, 'samples': 6743616, 'steps': 35122, 'loss/train': 1.3198071718215942} 08/30/2021 19:33:54 - INFO - __main__ - Step 35124: {'lr': 0.0004407101706878502, 'samples': 6743808, 'steps': 35123, 'loss/train': 1.3572293519973755} 08/30/2021 19:33:55 - INFO - __main__ - Step 35125: {'lr': 0.000440706739375669, 'samples': 6744000, 'steps': 35124, 'loss/train': 1.7889180183410645} 08/30/2021 19:33:55 - INFO - __main__ - Step 35126: {'lr': 0.00044070330797755825, 'samples': 6744192, 'steps': 35125, 'loss/train': 1.328520655632019} 08/30/2021 19:33:57 - INFO - __main__ - Step 35127: {'lr': 0.0004406998764935195, 'samples': 6744384, 'steps': 35126, 'loss/train': 1.3321994543075562} 08/30/2021 19:33:57 - INFO - __main__ - Step 35128: {'lr': 0.0004406964449235544, 'samples': 6744576, 'steps': 35127, 'loss/train': 5.919016361236572} 08/30/2021 19:33:58 - INFO - __main__ - Step 35129: {'lr': 0.00044069301326766434, 'samples': 6744768, 'steps': 35128, 'loss/train': 5.838839054107666} 08/30/2021 19:33:58 - INFO - __main__ - Step 35130: {'lr': 0.00044068958152585104, 'samples': 6744960, 'steps': 35129, 'loss/train': 1.1469359397888184} 08/30/2021 19:33:59 - INFO - __main__ - Step 35131: {'lr': 0.00044068614969811586, 'samples': 6745152, 'steps': 35130, 'loss/train': 1.4037948846817017} 08/30/2021 19:33:59 - INFO - __main__ - Step 35132: {'lr': 0.0004406827177844605, 'samples': 6745344, 'steps': 35131, 'loss/train': 0.8167937994003296} 08/30/2021 19:34:01 - INFO - __main__ - Step 35133: {'lr': 0.00044067928578488645, 'samples': 6745536, 'steps': 35132, 'loss/train': 0.22708335518836975} 08/30/2021 19:34:01 - INFO - __main__ - Step 35134: {'lr': 0.0004406758536993952, 'samples': 6745728, 'steps': 35133, 'loss/train': 1.5980310440063477} 08/30/2021 19:34:01 - INFO - __main__ - Step 35135: {'lr': 0.00044067242152798843, 'samples': 6745920, 'steps': 35134, 'loss/train': 1.1887896060943604} 08/30/2021 19:34:02 - INFO - __main__ - Step 35136: {'lr': 0.00044066898927066757, 'samples': 6746112, 'steps': 35135, 'loss/train': 0.8095821738243103} 08/30/2021 19:34:02 - INFO - __main__ - Step 35137: {'lr': 0.0004406655569274342, 'samples': 6746304, 'steps': 35136, 'loss/train': 1.610980749130249} 08/30/2021 19:34:02 - INFO - __main__ - Step 35138: {'lr': 0.0004406621244982899, 'samples': 6746496, 'steps': 35137, 'loss/train': 1.263929843902588} 08/30/2021 19:34:04 - INFO - __main__ - Step 35139: {'lr': 0.00044065869198323614, 'samples': 6746688, 'steps': 35138, 'loss/train': 1.789681077003479} 08/30/2021 19:34:04 - INFO - __main__ - Step 35140: {'lr': 0.0004406552593822746, 'samples': 6746880, 'steps': 35139, 'loss/train': 1.6807105541229248} 08/30/2021 19:34:05 - INFO - __main__ - Step 35141: {'lr': 0.00044065182669540665, 'samples': 6747072, 'steps': 35140, 'loss/train': 1.8546452522277832} 08/30/2021 19:34:05 - INFO - __main__ - Step 35142: {'lr': 0.000440648393922634, 'samples': 6747264, 'steps': 35141, 'loss/train': 1.3173348903656006} 08/30/2021 19:34:07 - INFO - __main__ - Step 35143: {'lr': 0.0004406449610639581, 'samples': 6747456, 'steps': 35142, 'loss/train': 1.7653255462646484} 08/30/2021 19:34:07 - INFO - __main__ - Step 35144: {'lr': 0.0004406415281193805, 'samples': 6747648, 'steps': 35143, 'loss/train': 1.690947413444519} 08/30/2021 19:34:07 - INFO - __main__ - Step 35145: {'lr': 0.0004406380950889027, 'samples': 6747840, 'steps': 35144, 'loss/train': 0.0914091095328331} 08/30/2021 19:34:08 - INFO - __main__ - Step 35146: {'lr': 0.0004406346619725265, 'samples': 6748032, 'steps': 35145, 'loss/train': 2.2457568645477295} 08/30/2021 19:34:08 - INFO - __main__ - Step 35147: {'lr': 0.00044063122877025315, 'samples': 6748224, 'steps': 35146, 'loss/train': 0.06289371848106384} 08/30/2021 19:34:08 - INFO - __main__ - Step 35148: {'lr': 0.0004406277954820843, 'samples': 6748416, 'steps': 35147, 'loss/train': 1.475255012512207} 08/30/2021 19:34:10 - INFO - __main__ - Step 35149: {'lr': 0.0004406243621080216, 'samples': 6748608, 'steps': 35148, 'loss/train': 1.5640921592712402} 08/30/2021 19:34:10 - INFO - __main__ - Step 35150: {'lr': 0.00044062092864806634, 'samples': 6748800, 'steps': 35149, 'loss/train': 1.2072811126708984} 08/30/2021 19:34:11 - INFO - __main__ - Step 35151: {'lr': 0.00044061749510222037, 'samples': 6748992, 'steps': 35150, 'loss/train': 2.398737907409668} 08/30/2021 19:34:11 - INFO - __main__ - Step 35152: {'lr': 0.00044061406147048504, 'samples': 6749184, 'steps': 35151, 'loss/train': 1.7054141759872437} 08/30/2021 19:34:11 - INFO - __main__ - Step 35153: {'lr': 0.000440610627752862, 'samples': 6749376, 'steps': 35152, 'loss/train': 1.2718210220336914} 08/30/2021 19:34:13 - INFO - __main__ - Step 35154: {'lr': 0.00044060719394935265, 'samples': 6749568, 'steps': 35153, 'loss/train': 1.265812873840332} 08/30/2021 19:34:14 - INFO - __main__ - Step 35155: {'lr': 0.0004406037600599588, 'samples': 6749760, 'steps': 35154, 'loss/train': 1.229170560836792} 08/30/2021 19:34:14 - INFO - __main__ - Step 35156: {'lr': 0.0004406003260846817, 'samples': 6749952, 'steps': 35155, 'loss/train': 1.4863605499267578} 08/30/2021 19:34:15 - INFO - __main__ - Step 35157: {'lr': 0.0004405968920235231, 'samples': 6750144, 'steps': 35156, 'loss/train': 0.9780787229537964} 08/30/2021 19:34:15 - INFO - __main__ - Step 35158: {'lr': 0.0004405934578764845, 'samples': 6750336, 'steps': 35157, 'loss/train': 1.421268343925476} 08/30/2021 19:34:17 - INFO - __main__ - Step 35159: {'lr': 0.0004405900236435674, 'samples': 6750528, 'steps': 35158, 'loss/train': 1.925866961479187} 08/30/2021 19:34:17 - INFO - __main__ - Step 35160: {'lr': 0.00044058658932477336, 'samples': 6750720, 'steps': 35159, 'loss/train': 0.5766004323959351} 08/30/2021 19:34:18 - INFO - __main__ - Step 35161: {'lr': 0.0004405831549201039, 'samples': 6750912, 'steps': 35160, 'loss/train': 1.8874460458755493} 08/30/2021 19:34:18 - INFO - __main__ - Step 35162: {'lr': 0.0004405797204295607, 'samples': 6751104, 'steps': 35161, 'loss/train': 1.2231470346450806} 08/30/2021 19:34:18 - INFO - __main__ - Step 35163: {'lr': 0.0004405762858531451, 'samples': 6751296, 'steps': 35162, 'loss/train': 1.5750610828399658} 08/30/2021 19:34:20 - INFO - __main__ - Step 35164: {'lr': 0.00044057285119085887, 'samples': 6751488, 'steps': 35163, 'loss/train': 1.4553025960922241} 08/30/2021 19:34:20 - INFO - __main__ - Step 35165: {'lr': 0.0004405694164427035, 'samples': 6751680, 'steps': 35164, 'loss/train': 1.443730354309082} 08/30/2021 19:34:21 - INFO - __main__ - Step 35166: {'lr': 0.0004405659816086804, 'samples': 6751872, 'steps': 35165, 'loss/train': 1.6259300708770752} 08/30/2021 19:34:21 - INFO - __main__ - Step 35167: {'lr': 0.00044056254668879127, 'samples': 6752064, 'steps': 35166, 'loss/train': 2.0701069831848145} 08/30/2021 19:34:21 - INFO - __main__ - Step 35168: {'lr': 0.00044055911168303753, 'samples': 6752256, 'steps': 35167, 'loss/train': 2.03838849067688} 08/30/2021 19:34:22 - INFO - __main__ - Step 35169: {'lr': 0.00044055567659142083, 'samples': 6752448, 'steps': 35168, 'loss/train': 1.6455274820327759} 08/30/2021 19:34:23 - INFO - __main__ - Step 35170: {'lr': 0.0004405522414139427, 'samples': 6752640, 'steps': 35169, 'loss/train': 1.3178457021713257} 08/30/2021 19:34:24 - INFO - __main__ - Step 35171: {'lr': 0.0004405488061506047, 'samples': 6752832, 'steps': 35170, 'loss/train': 1.2635177373886108} 08/30/2021 19:34:24 - INFO - __main__ - Step 35172: {'lr': 0.0004405453708014082, 'samples': 6753024, 'steps': 35171, 'loss/train': 0.6742770075798035} 08/30/2021 19:34:24 - INFO - __main__ - Step 35173: {'lr': 0.00044054193536635503, 'samples': 6753216, 'steps': 35172, 'loss/train': 1.4755159616470337} 08/30/2021 19:34:25 - INFO - __main__ - Step 35174: {'lr': 0.00044053849984544653, 'samples': 6753408, 'steps': 35173, 'loss/train': 1.1763559579849243} 08/30/2021 19:34:26 - INFO - __main__ - Step 35175: {'lr': 0.0004405350642386844, 'samples': 6753600, 'steps': 35174, 'loss/train': 1.9033881425857544} 08/30/2021 19:34:27 - INFO - __main__ - Step 35176: {'lr': 0.00044053162854607004, 'samples': 6753792, 'steps': 35175, 'loss/train': 0.8928601145744324} 08/30/2021 19:34:27 - INFO - __main__ - Step 35177: {'lr': 0.0004405281927676051, 'samples': 6753984, 'steps': 35176, 'loss/train': 1.3737467527389526} 08/30/2021 19:34:28 - INFO - __main__ - Step 35178: {'lr': 0.0004405247569032911, 'samples': 6754176, 'steps': 35177, 'loss/train': 1.949627161026001} 08/30/2021 19:34:28 - INFO - __main__ - Step 35179: {'lr': 0.00044052132095312956, 'samples': 6754368, 'steps': 35178, 'loss/train': 1.8561934232711792} 08/30/2021 19:34:30 - INFO - __main__ - Step 35180: {'lr': 0.0004405178849171221, 'samples': 6754560, 'steps': 35179, 'loss/train': 0.24839358031749725} 08/30/2021 19:34:30 - INFO - __main__ - Step 35181: {'lr': 0.00044051444879527013, 'samples': 6754752, 'steps': 35180, 'loss/train': 0.61899334192276} 08/30/2021 19:34:31 - INFO - __main__ - Step 35182: {'lr': 0.00044051101258757544, 'samples': 6754944, 'steps': 35181, 'loss/train': 1.483779788017273} 08/30/2021 19:34:31 - INFO - __main__ - Step 35183: {'lr': 0.0004405075762940393, 'samples': 6755136, 'steps': 35182, 'loss/train': 0.9080450534820557} 08/30/2021 19:34:31 - INFO - __main__ - Step 35184: {'lr': 0.00044050413991466344, 'samples': 6755328, 'steps': 35183, 'loss/train': 1.2553569078445435} 08/30/2021 19:34:33 - INFO - __main__ - Step 35185: {'lr': 0.0004405007034494494, 'samples': 6755520, 'steps': 35184, 'loss/train': 2.0483922958374023} 08/30/2021 19:34:33 - INFO - __main__ - Step 35186: {'lr': 0.00044049726689839854, 'samples': 6755712, 'steps': 35185, 'loss/train': 0.9954208135604858} 08/30/2021 19:34:34 - INFO - __main__ - Step 35187: {'lr': 0.0004404938302615126, 'samples': 6755904, 'steps': 35186, 'loss/train': 1.5959469079971313} 08/30/2021 19:34:34 - INFO - __main__ - Step 35188: {'lr': 0.00044049039353879317, 'samples': 6756096, 'steps': 35187, 'loss/train': 1.2983096837997437} 08/30/2021 19:34:34 - INFO - __main__ - Step 35189: {'lr': 0.00044048695673024166, 'samples': 6756288, 'steps': 35188, 'loss/train': 1.1405982971191406} 08/30/2021 19:34:35 - INFO - __main__ - Step 35190: {'lr': 0.00044048351983585966, 'samples': 6756480, 'steps': 35189, 'loss/train': 4.97883939743042} 08/30/2021 19:34:36 - INFO - __main__ - Step 35191: {'lr': 0.00044048008285564865, 'samples': 6756672, 'steps': 35190, 'loss/train': 0.626621425151825} 08/30/2021 19:34:37 - INFO - __main__ - Step 35192: {'lr': 0.0004404766457896104, 'samples': 6756864, 'steps': 35191, 'loss/train': 1.7165340185165405} 08/30/2021 19:34:37 - INFO - __main__ - Step 35193: {'lr': 0.0004404732086377462, 'samples': 6757056, 'steps': 35192, 'loss/train': 1.673938274383545} 08/30/2021 19:34:37 - INFO - __main__ - Step 35194: {'lr': 0.00044046977140005774, 'samples': 6757248, 'steps': 35193, 'loss/train': 1.4433075189590454} 08/30/2021 19:34:38 - INFO - __main__ - Step 35195: {'lr': 0.00044046633407654657, 'samples': 6757440, 'steps': 35194, 'loss/train': 1.6284478902816772} 08/30/2021 19:34:39 - INFO - __main__ - Step 35196: {'lr': 0.0004404628966672142, 'samples': 6757632, 'steps': 35195, 'loss/train': 1.6464027166366577} 08/30/2021 19:34:40 - INFO - __main__ - Step 35197: {'lr': 0.0004404594591720622, 'samples': 6757824, 'steps': 35196, 'loss/train': 1.9045639038085938} 08/30/2021 19:34:40 - INFO - __main__ - Step 35198: {'lr': 0.00044045602159109207, 'samples': 6758016, 'steps': 35197, 'loss/train': 1.601232647895813} 08/30/2021 19:34:41 - INFO - __main__ - Step 35199: {'lr': 0.0004404525839243054, 'samples': 6758208, 'steps': 35198, 'loss/train': 1.32688307762146} 08/30/2021 19:34:41 - INFO - __main__ - Step 35200: {'lr': 0.00044044914617170374, 'samples': 6758400, 'steps': 35199, 'loss/train': 1.6576082706451416} 08/30/2021 19:34:42 - INFO - __main__ - Step 35201: {'lr': 0.00044044570833328865, 'samples': 6758592, 'steps': 35200, 'loss/train': 1.3306043148040771} 08/30/2021 19:34:43 - INFO - __main__ - Step 35202: {'lr': 0.00044044227040906166, 'samples': 6758784, 'steps': 35201, 'loss/train': 0.914250373840332} 08/30/2021 19:34:43 - INFO - __main__ - Step 35203: {'lr': 0.00044043883239902425, 'samples': 6758976, 'steps': 35202, 'loss/train': 2.131357431411743} 08/30/2021 19:34:44 - INFO - __main__ - Step 35204: {'lr': 0.00044043539430317814, 'samples': 6759168, 'steps': 35203, 'loss/train': 1.3784360885620117} 08/30/2021 19:34:44 - INFO - __main__ - Step 35205: {'lr': 0.00044043195612152475, 'samples': 6759360, 'steps': 35204, 'loss/train': 1.1162667274475098} 08/30/2021 19:34:46 - INFO - __main__ - Step 35206: {'lr': 0.0004404285178540657, 'samples': 6759552, 'steps': 35205, 'loss/train': 1.7808799743652344} 08/30/2021 19:34:46 - INFO - __main__ - Step 35207: {'lr': 0.0004404250795008024, 'samples': 6759744, 'steps': 35206, 'loss/train': 1.4750785827636719} 08/30/2021 19:34:47 - INFO - __main__ - Step 35208: {'lr': 0.00044042164106173655, 'samples': 6759936, 'steps': 35207, 'loss/train': 1.5423390865325928} 08/30/2021 19:34:47 - INFO - __main__ - Step 35209: {'lr': 0.00044041820253686964, 'samples': 6760128, 'steps': 35208, 'loss/train': 1.6783699989318848} 08/30/2021 19:34:47 - INFO - __main__ - Step 35210: {'lr': 0.0004404147639262032, 'samples': 6760320, 'steps': 35209, 'loss/train': 1.6512147188186646} 08/30/2021 19:34:49 - INFO - __main__ - Step 35211: {'lr': 0.00044041132522973885, 'samples': 6760512, 'steps': 35210, 'loss/train': 2.347942352294922} 08/30/2021 19:34:50 - INFO - __main__ - Step 35212: {'lr': 0.0004404078864474781, 'samples': 6760704, 'steps': 35211, 'loss/train': 1.5213650465011597} 08/30/2021 19:34:50 - INFO - __main__ - Step 35213: {'lr': 0.00044040444757942245, 'samples': 6760896, 'steps': 35212, 'loss/train': 0.9378730654716492} 08/30/2021 19:34:50 - INFO - __main__ - Step 35214: {'lr': 0.00044040100862557355, 'samples': 6761088, 'steps': 35213, 'loss/train': 0.8650201559066772} 08/30/2021 19:34:51 - INFO - __main__ - Step 35215: {'lr': 0.00044039756958593287, 'samples': 6761280, 'steps': 35214, 'loss/train': 1.0497382879257202} 08/30/2021 19:34:51 - INFO - __main__ - Step 35216: {'lr': 0.000440394130460502, 'samples': 6761472, 'steps': 35215, 'loss/train': 1.380338191986084} 08/30/2021 19:34:53 - INFO - __main__ - Step 35217: {'lr': 0.00044039069124928245, 'samples': 6761664, 'steps': 35216, 'loss/train': 0.4927540719509125} 08/30/2021 19:34:53 - INFO - __main__ - Step 35218: {'lr': 0.0004403872519522758, 'samples': 6761856, 'steps': 35217, 'loss/train': 1.8464901447296143} 08/30/2021 19:34:53 - INFO - __main__ - Step 35219: {'lr': 0.00044038381256948357, 'samples': 6762048, 'steps': 35218, 'loss/train': 1.7989280223846436} 08/30/2021 19:34:54 - INFO - __main__ - Step 35220: {'lr': 0.00044038037310090736, 'samples': 6762240, 'steps': 35219, 'loss/train': 1.262181043624878} 08/30/2021 19:34:54 - INFO - __main__ - Step 35221: {'lr': 0.00044037693354654863, 'samples': 6762432, 'steps': 35220, 'loss/train': 0.2169027179479599} 08/30/2021 19:34:55 - INFO - __main__ - Step 35222: {'lr': 0.0004403734939064091, 'samples': 6762624, 'steps': 35221, 'loss/train': 1.6021244525909424} 08/30/2021 19:34:56 - INFO - __main__ - Step 35223: {'lr': 0.00044037005418049016, 'samples': 6762816, 'steps': 35222, 'loss/train': 0.7446139454841614} 08/30/2021 19:34:56 - INFO - __main__ - Step 35224: {'lr': 0.00044036661436879334, 'samples': 6763008, 'steps': 35223, 'loss/train': 1.6979058980941772} 08/30/2021 19:34:57 - INFO - __main__ - Step 35225: {'lr': 0.00044036317447132035, 'samples': 6763200, 'steps': 35224, 'loss/train': 1.5907671451568604} 08/30/2021 19:34:57 - INFO - __main__ - Step 35226: {'lr': 0.00044035973448807266, 'samples': 6763392, 'steps': 35225, 'loss/train': 1.5446741580963135} 08/30/2021 19:34:57 - INFO - __main__ - Step 35227: {'lr': 0.00044035629441905173, 'samples': 6763584, 'steps': 35226, 'loss/train': 1.255882740020752} 08/30/2021 19:34:59 - INFO - __main__ - Step 35228: {'lr': 0.0004403528542642592, 'samples': 6763776, 'steps': 35227, 'loss/train': 1.9746030569076538} 08/30/2021 19:34:59 - INFO - __main__ - Step 35229: {'lr': 0.00044034941402369666, 'samples': 6763968, 'steps': 35228, 'loss/train': 0.7388115525245667} 08/30/2021 19:35:00 - INFO - __main__ - Step 35230: {'lr': 0.0004403459736973656, 'samples': 6764160, 'steps': 35229, 'loss/train': 1.0392111539840698} 08/30/2021 19:35:00 - INFO - __main__ - Step 35231: {'lr': 0.00044034253328526765, 'samples': 6764352, 'steps': 35230, 'loss/train': 1.14803946018219} 08/30/2021 19:35:00 - INFO - __main__ - Step 35232: {'lr': 0.00044033909278740416, 'samples': 6764544, 'steps': 35231, 'loss/train': 1.5649964809417725} 08/30/2021 19:35:02 - INFO - __main__ - Step 35233: {'lr': 0.0004403356522037769, 'samples': 6764736, 'steps': 35232, 'loss/train': 1.1752593517303467} 08/30/2021 19:35:02 - INFO - __main__ - Step 35234: {'lr': 0.00044033221153438727, 'samples': 6764928, 'steps': 35233, 'loss/train': 1.9982519149780273} 08/30/2021 19:35:03 - INFO - __main__ - Step 35235: {'lr': 0.00044032877077923696, 'samples': 6765120, 'steps': 35234, 'loss/train': 1.9026896953582764} 08/30/2021 19:35:03 - INFO - __main__ - Step 35236: {'lr': 0.0004403253299383274, 'samples': 6765312, 'steps': 35235, 'loss/train': 1.168999195098877} 08/30/2021 19:35:03 - INFO - __main__ - Step 35237: {'lr': 0.00044032188901166016, 'samples': 6765504, 'steps': 35236, 'loss/train': 1.1683205366134644} 08/30/2021 19:35:05 - INFO - __main__ - Step 35238: {'lr': 0.0004403184479992368, 'samples': 6765696, 'steps': 35237, 'loss/train': 2.364229917526245} 08/30/2021 19:35:05 - INFO - __main__ - Step 35239: {'lr': 0.000440315006901059, 'samples': 6765888, 'steps': 35238, 'loss/train': 1.3106727600097656} 08/30/2021 19:35:06 - INFO - __main__ - Step 35240: {'lr': 0.00044031156571712807, 'samples': 6766080, 'steps': 35239, 'loss/train': 1.5884283781051636} 08/30/2021 19:35:06 - INFO - __main__ - Step 35241: {'lr': 0.0004403081244474457, 'samples': 6766272, 'steps': 35240, 'loss/train': 1.3158551454544067} 08/30/2021 19:35:06 - INFO - __main__ - Step 35242: {'lr': 0.00044030468309201354, 'samples': 6766464, 'steps': 35241, 'loss/train': 1.2236522436141968} 08/30/2021 19:35:08 - INFO - __main__ - Step 35243: {'lr': 0.0004403012416508329, 'samples': 6766656, 'steps': 35242, 'loss/train': 1.473706603050232} 08/30/2021 19:35:09 - INFO - __main__ - Step 35244: {'lr': 0.00044029780012390553, 'samples': 6766848, 'steps': 35243, 'loss/train': 1.4110535383224487} 08/30/2021 19:35:09 - INFO - __main__ - Step 35245: {'lr': 0.0004402943585112329, 'samples': 6767040, 'steps': 35244, 'loss/train': 0.09369825571775436} 08/30/2021 19:35:09 - INFO - __main__ - Step 35246: {'lr': 0.0004402909168128165, 'samples': 6767232, 'steps': 35245, 'loss/train': 1.7193278074264526} 08/30/2021 19:35:10 - INFO - __main__ - Step 35247: {'lr': 0.00044028747502865794, 'samples': 6767424, 'steps': 35246, 'loss/train': 1.5147919654846191} 08/30/2021 19:35:11 - INFO - __main__ - Step 35248: {'lr': 0.0004402840331587589, 'samples': 6767616, 'steps': 35247, 'loss/train': 1.8174281120300293} 08/30/2021 19:35:12 - INFO - __main__ - Step 35249: {'lr': 0.0004402805912031207, 'samples': 6767808, 'steps': 35248, 'loss/train': 0.8487445712089539} 08/30/2021 19:35:12 - INFO - __main__ - Step 35250: {'lr': 0.0004402771491617451, 'samples': 6768000, 'steps': 35249, 'loss/train': 0.7927405834197998} 08/30/2021 19:35:12 - INFO - __main__ - Step 35251: {'lr': 0.0004402737070346335, 'samples': 6768192, 'steps': 35250, 'loss/train': 0.988335132598877} 08/30/2021 19:35:13 - INFO - __main__ - Step 35252: {'lr': 0.0004402702648217875, 'samples': 6768384, 'steps': 35251, 'loss/train': 1.369179129600525} 08/30/2021 19:35:13 - INFO - __main__ - Step 35253: {'lr': 0.00044026682252320864, 'samples': 6768576, 'steps': 35252, 'loss/train': 3.055659532546997} 08/30/2021 19:35:15 - INFO - __main__ - Step 35254: {'lr': 0.00044026338013889853, 'samples': 6768768, 'steps': 35253, 'loss/train': 1.8225443363189697} 08/30/2021 19:35:15 - INFO - __main__ - Step 35255: {'lr': 0.00044025993766885866, 'samples': 6768960, 'steps': 35254, 'loss/train': 1.828208565711975} 08/30/2021 19:35:16 - INFO - __main__ - Step 35256: {'lr': 0.00044025649511309064, 'samples': 6769152, 'steps': 35255, 'loss/train': 1.041124939918518} 08/30/2021 19:35:16 - INFO - __main__ - Step 35257: {'lr': 0.00044025305247159585, 'samples': 6769344, 'steps': 35256, 'loss/train': 1.5535945892333984} 08/30/2021 19:35:16 - INFO - __main__ - Step 35258: {'lr': 0.00044024960974437606, 'samples': 6769536, 'steps': 35257, 'loss/train': 0.07975805550813675} 08/30/2021 19:35:18 - INFO - __main__ - Step 35259: {'lr': 0.0004402461669314327, 'samples': 6769728, 'steps': 35258, 'loss/train': 1.6203875541687012} 08/30/2021 19:35:18 - INFO - __main__ - Step 35260: {'lr': 0.0004402427240327674, 'samples': 6769920, 'steps': 35259, 'loss/train': 1.3997536897659302} 08/30/2021 19:35:19 - INFO - __main__ - Step 35261: {'lr': 0.0004402392810483816, 'samples': 6770112, 'steps': 35260, 'loss/train': 1.4612407684326172} 08/30/2021 19:35:19 - INFO - __main__ - Step 35262: {'lr': 0.000440235837978277, 'samples': 6770304, 'steps': 35261, 'loss/train': 0.9268139600753784} 08/30/2021 19:35:20 - INFO - __main__ - Step 35263: {'lr': 0.00044023239482245504, 'samples': 6770496, 'steps': 35262, 'loss/train': 1.2010623216629028} 08/30/2021 19:35:21 - INFO - __main__ - Step 35264: {'lr': 0.0004402289515809172, 'samples': 6770688, 'steps': 35263, 'loss/train': 1.7011468410491943} 08/30/2021 19:35:22 - INFO - __main__ - Step 35265: {'lr': 0.00044022550825366526, 'samples': 6770880, 'steps': 35264, 'loss/train': 1.3645305633544922} 08/30/2021 19:35:22 - INFO - __main__ - Step 35266: {'lr': 0.0004402220648407006, 'samples': 6771072, 'steps': 35265, 'loss/train': 1.9016871452331543} 08/30/2021 19:35:22 - INFO - __main__ - Step 35267: {'lr': 0.00044021862134202485, 'samples': 6771264, 'steps': 35266, 'loss/train': 1.0431255102157593} 08/30/2021 19:35:23 - INFO - __main__ - Step 35268: {'lr': 0.00044021517775763943, 'samples': 6771456, 'steps': 35267, 'loss/train': 0.5561128258705139} 08/30/2021 19:35:25 - INFO - __main__ - Step 35269: {'lr': 0.00044021173408754604, 'samples': 6771648, 'steps': 35268, 'loss/train': 1.310693621635437} 08/30/2021 19:35:25 - INFO - __main__ - Step 35270: {'lr': 0.00044020829033174615, 'samples': 6771840, 'steps': 35269, 'loss/train': 1.2678537368774414} 08/30/2021 19:35:26 - INFO - __main__ - Step 35271: {'lr': 0.0004402048464902414, 'samples': 6772032, 'steps': 35270, 'loss/train': 0.8126941919326782} 08/30/2021 19:35:26 - INFO - __main__ - Step 35272: {'lr': 0.0004402014025630332, 'samples': 6772224, 'steps': 35271, 'loss/train': 1.036738395690918} 08/30/2021 19:35:26 - INFO - __main__ - Step 35273: {'lr': 0.00044019795855012325, 'samples': 6772416, 'steps': 35272, 'loss/train': 1.1602281332015991} 08/30/2021 19:35:27 - INFO - __main__ - Step 35274: {'lr': 0.00044019451445151305, 'samples': 6772608, 'steps': 35273, 'loss/train': 1.720868468284607} 08/30/2021 19:35:28 - INFO - __main__ - Step 35275: {'lr': 0.00044019107026720404, 'samples': 6772800, 'steps': 35274, 'loss/train': 1.3801974058151245} 08/30/2021 19:35:29 - INFO - __main__ - Step 35276: {'lr': 0.00044018762599719796, 'samples': 6772992, 'steps': 35275, 'loss/train': 1.4340863227844238} 08/30/2021 19:35:29 - INFO - __main__ - Step 35277: {'lr': 0.0004401841816414962, 'samples': 6773184, 'steps': 35276, 'loss/train': 1.6542479991912842} 08/30/2021 19:35:29 - INFO - __main__ - Step 35278: {'lr': 0.0004401807372001004, 'samples': 6773376, 'steps': 35277, 'loss/train': 0.8494566082954407} 08/30/2021 19:35:30 - INFO - __main__ - Step 35279: {'lr': 0.0004401772926730122, 'samples': 6773568, 'steps': 35278, 'loss/train': 1.38467276096344} 08/30/2021 19:35:31 - INFO - __main__ - Step 35280: {'lr': 0.0004401738480602329, 'samples': 6773760, 'steps': 35279, 'loss/train': 1.4366095066070557} 08/30/2021 19:35:32 - INFO - __main__ - Step 35281: {'lr': 0.0004401704033617643, 'samples': 6773952, 'steps': 35280, 'loss/train': 0.13203176856040955} 08/30/2021 19:35:32 - INFO - __main__ - Step 35282: {'lr': 0.0004401669585776078, 'samples': 6774144, 'steps': 35281, 'loss/train': 1.0327534675598145} 08/30/2021 19:35:33 - INFO - __main__ - Step 35283: {'lr': 0.000440163513707765, 'samples': 6774336, 'steps': 35282, 'loss/train': 1.26374351978302} 08/30/2021 19:35:33 - INFO - __main__ - Step 35284: {'lr': 0.00044016006875223745, 'samples': 6774528, 'steps': 35283, 'loss/train': 1.0519497394561768} 08/30/2021 19:35:35 - INFO - __main__ - Step 35285: {'lr': 0.00044015662371102676, 'samples': 6774720, 'steps': 35284, 'loss/train': 1.084066390991211} 08/30/2021 19:35:36 - INFO - __main__ - Step 35286: {'lr': 0.0004401531785841344, 'samples': 6774912, 'steps': 35285, 'loss/train': 2.0477452278137207} 08/30/2021 19:35:36 - INFO - __main__ - Step 35287: {'lr': 0.00044014973337156197, 'samples': 6775104, 'steps': 35286, 'loss/train': 1.5073790550231934} 08/30/2021 19:35:37 - INFO - __main__ - Step 35288: {'lr': 0.0004401462880733109, 'samples': 6775296, 'steps': 35287, 'loss/train': 0.7509042620658875} 08/30/2021 19:35:37 - INFO - __main__ - Step 35289: {'lr': 0.000440142842689383, 'samples': 6775488, 'steps': 35288, 'loss/train': 0.5955594778060913} 08/30/2021 19:35:37 - INFO - __main__ - Step 35290: {'lr': 0.00044013939721977957, 'samples': 6775680, 'steps': 35289, 'loss/train': 0.4908735156059265} 08/30/2021 19:35:38 - INFO - __main__ - Step 35291: {'lr': 0.0004401359516645023, 'samples': 6775872, 'steps': 35290, 'loss/train': 1.3419342041015625} 08/30/2021 19:35:39 - INFO - __main__ - Step 35292: {'lr': 0.0004401325060235527, 'samples': 6776064, 'steps': 35291, 'loss/train': 5.298120021820068} 08/30/2021 19:35:40 - INFO - __main__ - Step 35293: {'lr': 0.00044012906029693236, 'samples': 6776256, 'steps': 35292, 'loss/train': 1.2927677631378174} 08/30/2021 19:35:40 - INFO - __main__ - Step 35294: {'lr': 0.0004401256144846427, 'samples': 6776448, 'steps': 35293, 'loss/train': 1.2110918760299683} 08/30/2021 19:35:40 - INFO - __main__ - Step 35295: {'lr': 0.0004401221685866854, 'samples': 6776640, 'steps': 35294, 'loss/train': 2.1023428440093994} 08/30/2021 19:35:41 - INFO - __main__ - Step 35296: {'lr': 0.00044011872260306205, 'samples': 6776832, 'steps': 35295, 'loss/train': 1.1127710342407227} 08/30/2021 19:35:42 - INFO - __main__ - Step 35297: {'lr': 0.00044011527653377416, 'samples': 6777024, 'steps': 35296, 'loss/train': 1.0868569612503052} 08/30/2021 19:35:43 - INFO - __main__ - Step 35298: {'lr': 0.0004401118303788232, 'samples': 6777216, 'steps': 35297, 'loss/train': 1.801560640335083} 08/30/2021 19:35:43 - INFO - __main__ - Step 35299: {'lr': 0.00044010838413821075, 'samples': 6777408, 'steps': 35298, 'loss/train': 1.542335033416748} 08/30/2021 19:35:43 - INFO - __main__ - Step 35300: {'lr': 0.0004401049378119384, 'samples': 6777600, 'steps': 35299, 'loss/train': 0.08990535140037537} 08/30/2021 19:35:44 - INFO - __main__ - Step 35301: {'lr': 0.0004401014914000078, 'samples': 6777792, 'steps': 35300, 'loss/train': 0.26383742690086365} 08/30/2021 19:35:44 - INFO - __main__ - Step 35302: {'lr': 0.00044009804490242026, 'samples': 6777984, 'steps': 35301, 'loss/train': 1.709259033203125} 08/30/2021 19:35:46 - INFO - __main__ - Step 35303: {'lr': 0.00044009459831917755, 'samples': 6778176, 'steps': 35302, 'loss/train': 1.717235803604126} 08/30/2021 19:35:47 - INFO - __main__ - Step 35304: {'lr': 0.00044009115165028113, 'samples': 6778368, 'steps': 35303, 'loss/train': 0.8929498791694641} 08/30/2021 19:35:47 - INFO - __main__ - Step 35305: {'lr': 0.0004400877048957326, 'samples': 6778560, 'steps': 35304, 'loss/train': 1.6270958185195923} 08/30/2021 19:35:47 - INFO - __main__ - Step 35306: {'lr': 0.00044008425805553347, 'samples': 6778752, 'steps': 35305, 'loss/train': 1.4239238500595093} 08/30/2021 19:35:48 - INFO - __main__ - Step 35307: {'lr': 0.00044008081112968537, 'samples': 6778944, 'steps': 35306, 'loss/train': 1.2555062770843506} 08/30/2021 19:35:49 - INFO - __main__ - Step 35308: {'lr': 0.0004400773641181897, 'samples': 6779136, 'steps': 35307, 'loss/train': 1.2234728336334229} 08/30/2021 19:35:50 - INFO - __main__ - Step 35309: {'lr': 0.0004400739170210481, 'samples': 6779328, 'steps': 35308, 'loss/train': 1.640255093574524} 08/30/2021 19:35:50 - INFO - __main__ - Step 35310: {'lr': 0.00044007046983826213, 'samples': 6779520, 'steps': 35309, 'loss/train': 0.27572792768478394} 08/30/2021 19:35:51 - INFO - __main__ - Step 35311: {'lr': 0.0004400670225698333, 'samples': 6779712, 'steps': 35310, 'loss/train': 1.57471764087677} 08/30/2021 19:35:51 - INFO - __main__ - Step 35312: {'lr': 0.00044006357521576334, 'samples': 6779904, 'steps': 35311, 'loss/train': 1.2589054107666016} 08/30/2021 19:35:53 - INFO - __main__ - Step 35313: {'lr': 0.0004400601277760536, 'samples': 6780096, 'steps': 35312, 'loss/train': 2.064746618270874} 08/30/2021 19:35:53 - INFO - __main__ - Step 35314: {'lr': 0.0004400566802507057, 'samples': 6780288, 'steps': 35313, 'loss/train': 1.9095836877822876} 08/30/2021 19:35:53 - INFO - __main__ - Step 35315: {'lr': 0.0004400532326397211, 'samples': 6780480, 'steps': 35314, 'loss/train': 1.270258903503418} 08/30/2021 19:35:54 - INFO - __main__ - Step 35316: {'lr': 0.00044004978494310154, 'samples': 6780672, 'steps': 35315, 'loss/train': 1.4586715698242188} 08/30/2021 19:35:54 - INFO - __main__ - Step 35317: {'lr': 0.00044004633716084854, 'samples': 6780864, 'steps': 35316, 'loss/train': 2.2896289825439453} 08/30/2021 19:35:56 - INFO - __main__ - Step 35318: {'lr': 0.0004400428892929635, 'samples': 6781056, 'steps': 35317, 'loss/train': 1.3984524011611938} 08/30/2021 19:35:56 - INFO - __main__ - Step 35319: {'lr': 0.00044003944133944804, 'samples': 6781248, 'steps': 35318, 'loss/train': 1.5508476495742798} 08/30/2021 19:35:56 - INFO - __main__ - Step 35320: {'lr': 0.00044003599330030385, 'samples': 6781440, 'steps': 35319, 'loss/train': 1.4566360712051392} 08/30/2021 19:35:57 - INFO - __main__ - Step 35321: {'lr': 0.00044003254517553225, 'samples': 6781632, 'steps': 35320, 'loss/train': 1.2995983362197876} 08/30/2021 19:35:57 - INFO - __main__ - Step 35322: {'lr': 0.000440029096965135, 'samples': 6781824, 'steps': 35321, 'loss/train': 1.6833568811416626} 08/30/2021 19:35:58 - INFO - __main__ - Step 35323: {'lr': 0.0004400256486691135, 'samples': 6782016, 'steps': 35322, 'loss/train': 1.4694782495498657} 08/30/2021 19:35:59 - INFO - __main__ - Step 35324: {'lr': 0.0004400222002874695, 'samples': 6782208, 'steps': 35323, 'loss/train': 1.3471918106079102} 08/30/2021 19:36:00 - INFO - __main__ - Step 35325: {'lr': 0.0004400187518202043, 'samples': 6782400, 'steps': 35324, 'loss/train': 1.5700156688690186} 08/30/2021 19:36:00 - INFO - __main__ - Step 35326: {'lr': 0.00044001530326731966, 'samples': 6782592, 'steps': 35325, 'loss/train': 1.4041510820388794} 08/30/2021 19:36:00 - INFO - __main__ - Step 35327: {'lr': 0.00044001185462881707, 'samples': 6782784, 'steps': 35326, 'loss/train': 1.5778844356536865} 08/30/2021 19:36:01 - INFO - __main__ - Step 35328: {'lr': 0.000440008405904698, 'samples': 6782976, 'steps': 35327, 'loss/train': 1.3653637170791626} 08/30/2021 19:36:02 - INFO - __main__ - Step 35329: {'lr': 0.0004400049570949641, 'samples': 6783168, 'steps': 35328, 'loss/train': 1.2845649719238281} 08/30/2021 19:36:02 - INFO - __main__ - Step 35330: {'lr': 0.0004400015081996169, 'samples': 6783360, 'steps': 35329, 'loss/train': 1.058379888534546} 08/30/2021 19:36:03 - INFO - __main__ - Step 35331: {'lr': 0.000439998059218658, 'samples': 6783552, 'steps': 35330, 'loss/train': 1.6161878108978271} 08/30/2021 19:36:03 - INFO - __main__ - Step 35332: {'lr': 0.0004399946101520889, 'samples': 6783744, 'steps': 35331, 'loss/train': 0.4192153215408325} 08/30/2021 19:36:04 - INFO - __main__ - Step 35333: {'lr': 0.0004399911609999111, 'samples': 6783936, 'steps': 35332, 'loss/train': 1.5687097311019897} 08/30/2021 19:36:05 - INFO - __main__ - Step 35334: {'lr': 0.0004399877117621262, 'samples': 6784128, 'steps': 35333, 'loss/train': 1.4547446966171265} 08/30/2021 19:36:05 - INFO - __main__ - Step 35335: {'lr': 0.0004399842624387358, 'samples': 6784320, 'steps': 35334, 'loss/train': 1.9110000133514404} 08/30/2021 19:36:06 - INFO - __main__ - Step 35336: {'lr': 0.0004399808130297415, 'samples': 6784512, 'steps': 35335, 'loss/train': 1.5049439668655396} 08/30/2021 19:36:06 - INFO - __main__ - Step 35337: {'lr': 0.0004399773635351446, 'samples': 6784704, 'steps': 35336, 'loss/train': 1.6948868036270142} 08/30/2021 19:36:06 - INFO - __main__ - Step 35338: {'lr': 0.000439973913954947, 'samples': 6784896, 'steps': 35337, 'loss/train': 1.647794246673584} 08/30/2021 19:36:08 - INFO - __main__ - Step 35339: {'lr': 0.00043997046428915, 'samples': 6785088, 'steps': 35338, 'loss/train': 0.6966094374656677} 08/30/2021 19:36:08 - INFO - __main__ - Step 35340: {'lr': 0.00043996701453775526, 'samples': 6785280, 'steps': 35339, 'loss/train': 1.6490147113800049} 08/30/2021 19:36:09 - INFO - __main__ - Step 35341: {'lr': 0.0004399635647007643, 'samples': 6785472, 'steps': 35340, 'loss/train': 1.4258105754852295} 08/30/2021 19:36:09 - INFO - __main__ - Step 35342: {'lr': 0.00043996011477817875, 'samples': 6785664, 'steps': 35341, 'loss/train': 0.9135576486587524} 08/30/2021 19:36:10 - INFO - __main__ - Step 35343: {'lr': 0.0004399566647700001, 'samples': 6785856, 'steps': 35342, 'loss/train': 1.7830604314804077} 08/30/2021 19:36:12 - INFO - __main__ - Step 35344: {'lr': 0.00043995321467622984, 'samples': 6786048, 'steps': 35343, 'loss/train': 1.1424063444137573} 08/30/2021 19:36:12 - INFO - __main__ - Step 35345: {'lr': 0.00043994976449686964, 'samples': 6786240, 'steps': 35344, 'loss/train': 1.5647335052490234} 08/30/2021 19:36:12 - INFO - __main__ - Step 35346: {'lr': 0.000439946314231921, 'samples': 6786432, 'steps': 35345, 'loss/train': 0.2106710523366928} 08/30/2021 19:36:13 - INFO - __main__ - Step 35347: {'lr': 0.00043994286388138545, 'samples': 6786624, 'steps': 35346, 'loss/train': 1.7119828462600708} 08/30/2021 19:36:13 - INFO - __main__ - Step 35348: {'lr': 0.00043993941344526455, 'samples': 6786816, 'steps': 35347, 'loss/train': 1.407097578048706} 08/30/2021 19:36:14 - INFO - __main__ - Step 35349: {'lr': 0.00043993596292356, 'samples': 6787008, 'steps': 35348, 'loss/train': 1.2357357740402222} 08/30/2021 19:36:15 - INFO - __main__ - Step 35350: {'lr': 0.00043993251231627315, 'samples': 6787200, 'steps': 35349, 'loss/train': 1.7043943405151367} 08/30/2021 19:36:16 - INFO - __main__ - Step 35351: {'lr': 0.00043992906162340563, 'samples': 6787392, 'steps': 35350, 'loss/train': 1.9289575815200806} 08/30/2021 19:36:16 - INFO - __main__ - Step 35352: {'lr': 0.00043992561084495906, 'samples': 6787584, 'steps': 35351, 'loss/train': 2.431380033493042} 08/30/2021 19:36:16 - INFO - __main__ - Step 35353: {'lr': 0.0004399221599809349, 'samples': 6787776, 'steps': 35352, 'loss/train': 1.7876442670822144} 08/30/2021 19:36:17 - INFO - __main__ - Step 35354: {'lr': 0.0004399187090313348, 'samples': 6787968, 'steps': 35353, 'loss/train': 1.2761778831481934} 08/30/2021 19:36:19 - INFO - __main__ - Step 35355: {'lr': 0.00043991525799616017, 'samples': 6788160, 'steps': 35354, 'loss/train': 1.2068582773208618} 08/30/2021 19:36:19 - INFO - __main__ - Step 35356: {'lr': 0.0004399118068754127, 'samples': 6788352, 'steps': 35355, 'loss/train': 2.0843570232391357} 08/30/2021 19:36:20 - INFO - __main__ - Step 35357: {'lr': 0.0004399083556690939, 'samples': 6788544, 'steps': 35356, 'loss/train': 1.4274187088012695} 08/30/2021 19:36:20 - INFO - __main__ - Step 35358: {'lr': 0.0004399049043772053, 'samples': 6788736, 'steps': 35357, 'loss/train': 0.705751895904541} 08/30/2021 19:36:20 - INFO - __main__ - Step 35359: {'lr': 0.00043990145299974853, 'samples': 6788928, 'steps': 35358, 'loss/train': 1.1702861785888672} 08/30/2021 19:36:22 - INFO - __main__ - Step 35360: {'lr': 0.0004398980015367251, 'samples': 6789120, 'steps': 35359, 'loss/train': 1.231582760810852} 08/30/2021 19:36:22 - INFO - __main__ - Step 35361: {'lr': 0.00043989454998813655, 'samples': 6789312, 'steps': 35360, 'loss/train': 0.36591726541519165} 08/30/2021 19:36:23 - INFO - __main__ - Step 35362: {'lr': 0.00043989109835398444, 'samples': 6789504, 'steps': 35361, 'loss/train': 1.3209960460662842} 08/30/2021 19:36:23 - INFO - __main__ - Step 35363: {'lr': 0.0004398876466342703, 'samples': 6789696, 'steps': 35362, 'loss/train': 1.8163431882858276} 08/30/2021 19:36:24 - INFO - __main__ - Step 35364: {'lr': 0.0004398841948289958, 'samples': 6789888, 'steps': 35363, 'loss/train': 1.3110448122024536} 08/30/2021 19:36:24 - INFO - __main__ - Step 35365: {'lr': 0.0004398807429381623, 'samples': 6790080, 'steps': 35364, 'loss/train': 0.049749474972486496} 08/30/2021 19:36:26 - INFO - __main__ - Step 35366: {'lr': 0.0004398772909617715, 'samples': 6790272, 'steps': 35365, 'loss/train': 1.8331133127212524} 08/30/2021 19:36:27 - INFO - __main__ - Step 35367: {'lr': 0.00043987383889982495, 'samples': 6790464, 'steps': 35366, 'loss/train': 1.2132179737091064} 08/30/2021 19:36:27 - INFO - __main__ - Step 35368: {'lr': 0.00043987038675232415, 'samples': 6790656, 'steps': 35367, 'loss/train': 1.374467134475708} 08/30/2021 19:36:28 - INFO - __main__ - Step 35369: {'lr': 0.00043986693451927074, 'samples': 6790848, 'steps': 35368, 'loss/train': 0.34419572353363037} 08/30/2021 19:36:28 - INFO - __main__ - Step 35370: {'lr': 0.0004398634822006662, 'samples': 6791040, 'steps': 35369, 'loss/train': 0.25599876046180725} 08/30/2021 19:36:28 - INFO - __main__ - Step 35371: {'lr': 0.0004398600297965121, 'samples': 6791232, 'steps': 35370, 'loss/train': 1.0565998554229736} 08/30/2021 19:36:30 - INFO - __main__ - Step 35372: {'lr': 0.00043985657730680997, 'samples': 6791424, 'steps': 35371, 'loss/train': 1.3926738500595093} 08/30/2021 19:36:30 - INFO - __main__ - Step 35373: {'lr': 0.00043985312473156143, 'samples': 6791616, 'steps': 35372, 'loss/train': 1.0037105083465576} 08/30/2021 19:36:31 - INFO - __main__ - Step 35374: {'lr': 0.000439849672070768, 'samples': 6791808, 'steps': 35373, 'loss/train': 0.936872124671936} 08/30/2021 19:36:31 - INFO - __main__ - Step 35375: {'lr': 0.00043984621932443115, 'samples': 6792000, 'steps': 35374, 'loss/train': 1.5440009832382202} 08/30/2021 19:36:31 - INFO - __main__ - Step 35376: {'lr': 0.0004398427664925526, 'samples': 6792192, 'steps': 35375, 'loss/train': 1.294872760772705} 08/30/2021 19:36:32 - INFO - __main__ - Step 35377: {'lr': 0.0004398393135751338, 'samples': 6792384, 'steps': 35376, 'loss/train': 1.6850001811981201} 08/30/2021 19:36:33 - INFO - __main__ - Step 35378: {'lr': 0.0004398358605721764, 'samples': 6792576, 'steps': 35377, 'loss/train': 0.7377321720123291} 08/30/2021 19:36:34 - INFO - __main__ - Step 35379: {'lr': 0.00043983240748368186, 'samples': 6792768, 'steps': 35378, 'loss/train': 1.3044615983963013} 08/30/2021 19:36:34 - INFO - __main__ - Step 35380: {'lr': 0.0004398289543096518, 'samples': 6792960, 'steps': 35379, 'loss/train': 1.5079270601272583} 08/30/2021 19:36:34 - INFO - __main__ - Step 35381: {'lr': 0.0004398255010500877, 'samples': 6793152, 'steps': 35380, 'loss/train': 1.6334177255630493} 08/30/2021 19:36:35 - INFO - __main__ - Step 35382: {'lr': 0.00043982204770499114, 'samples': 6793344, 'steps': 35381, 'loss/train': 0.9073518514633179} 08/30/2021 19:36:36 - INFO - __main__ - Step 35383: {'lr': 0.0004398185942743637, 'samples': 6793536, 'steps': 35382, 'loss/train': 1.200181484222412} 08/30/2021 19:36:36 - INFO - __main__ - Step 35384: {'lr': 0.00043981514075820693, 'samples': 6793728, 'steps': 35383, 'loss/train': 0.6204242706298828} 08/30/2021 19:36:37 - INFO - __main__ - Step 35385: {'lr': 0.0004398116871565224, 'samples': 6793920, 'steps': 35384, 'loss/train': 0.8892233967781067} 08/30/2021 19:36:37 - INFO - __main__ - Step 35386: {'lr': 0.0004398082334693116, 'samples': 6794112, 'steps': 35385, 'loss/train': 1.8526052236557007} 08/30/2021 19:36:38 - INFO - __main__ - Step 35387: {'lr': 0.0004398047796965762, 'samples': 6794304, 'steps': 35386, 'loss/train': 1.7854810953140259} 08/30/2021 19:36:39 - INFO - __main__ - Step 35388: {'lr': 0.0004398013258383177, 'samples': 6794496, 'steps': 35387, 'loss/train': 1.622938632965088} 08/30/2021 19:36:40 - INFO - __main__ - Step 35389: {'lr': 0.0004397978718945377, 'samples': 6794688, 'steps': 35388, 'loss/train': 1.3173573017120361} 08/30/2021 19:36:40 - INFO - __main__ - Step 35390: {'lr': 0.0004397944178652376, 'samples': 6794880, 'steps': 35389, 'loss/train': 1.4173136949539185} 08/30/2021 19:36:40 - INFO - __main__ - Step 35391: {'lr': 0.0004397909637504191, 'samples': 6795072, 'steps': 35390, 'loss/train': 2.6413254737854004} 08/30/2021 19:36:41 - INFO - __main__ - Step 35392: {'lr': 0.00043978750955008374, 'samples': 6795264, 'steps': 35391, 'loss/train': 0.8653263449668884} 08/30/2021 19:36:42 - INFO - __main__ - Step 35393: {'lr': 0.00043978405526423305, 'samples': 6795456, 'steps': 35392, 'loss/train': 1.6237744092941284} 08/30/2021 19:36:43 - INFO - __main__ - Step 35394: {'lr': 0.0004397806008928686, 'samples': 6795648, 'steps': 35393, 'loss/train': 1.0248075723648071} 08/30/2021 19:36:43 - INFO - __main__ - Step 35395: {'lr': 0.00043977714643599194, 'samples': 6795840, 'steps': 35394, 'loss/train': 0.43009302020072937} 08/30/2021 19:36:44 - INFO - __main__ - Step 35396: {'lr': 0.0004397736918936046, 'samples': 6796032, 'steps': 35395, 'loss/train': 1.2525368928909302} 08/30/2021 19:36:44 - INFO - __main__ - Step 35397: {'lr': 0.0004397702372657082, 'samples': 6796224, 'steps': 35396, 'loss/train': 1.5758581161499023} 08/30/2021 19:36:45 - INFO - __main__ - Step 35398: {'lr': 0.00043976678255230417, 'samples': 6796416, 'steps': 35397, 'loss/train': 1.3603363037109375} 08/30/2021 19:36:46 - INFO - __main__ - Step 35399: {'lr': 0.0004397633277533942, 'samples': 6796608, 'steps': 35398, 'loss/train': 0.6953346729278564} 08/30/2021 19:36:46 - INFO - __main__ - Step 35400: {'lr': 0.0004397598728689799, 'samples': 6796800, 'steps': 35399, 'loss/train': 1.5138709545135498} 08/30/2021 19:36:47 - INFO - __main__ - Step 35401: {'lr': 0.0004397564178990626, 'samples': 6796992, 'steps': 35400, 'loss/train': 1.2172725200653076} 08/30/2021 19:36:47 - INFO - __main__ - Step 35402: {'lr': 0.0004397529628436441, 'samples': 6797184, 'steps': 35401, 'loss/train': 0.9983571767807007} 08/30/2021 19:36:49 - INFO - __main__ - Step 35403: {'lr': 0.0004397495077027258, 'samples': 6797376, 'steps': 35402, 'loss/train': 0.9644858241081238} 08/30/2021 19:36:49 - INFO - __main__ - Step 35404: {'lr': 0.0004397460524763093, 'samples': 6797568, 'steps': 35403, 'loss/train': 1.7141958475112915} 08/30/2021 19:36:49 - INFO - __main__ - Step 35405: {'lr': 0.00043974259716439613, 'samples': 6797760, 'steps': 35404, 'loss/train': 1.1593409776687622} 08/30/2021 19:36:50 - INFO - __main__ - Step 35406: {'lr': 0.0004397391417669878, 'samples': 6797952, 'steps': 35405, 'loss/train': 1.45179283618927} 08/30/2021 19:36:50 - INFO - __main__ - Step 35407: {'lr': 0.0004397356862840861, 'samples': 6798144, 'steps': 35406, 'loss/train': 1.4605265855789185} 08/30/2021 19:36:52 - INFO - __main__ - Step 35408: {'lr': 0.00043973223071569234, 'samples': 6798336, 'steps': 35407, 'loss/train': 1.7734060287475586} 08/30/2021 19:36:52 - INFO - __main__ - Step 35409: {'lr': 0.0004397287750618082, 'samples': 6798528, 'steps': 35408, 'loss/train': 0.7091401219367981} 08/30/2021 19:36:52 - INFO - __main__ - Step 35410: {'lr': 0.00043972531932243516, 'samples': 6798720, 'steps': 35409, 'loss/train': 2.148045063018799} 08/30/2021 19:36:53 - INFO - __main__ - Step 35411: {'lr': 0.00043972186349757484, 'samples': 6798912, 'steps': 35410, 'loss/train': 1.3229072093963623} 08/30/2021 19:36:53 - INFO - __main__ - Step 35412: {'lr': 0.0004397184075872288, 'samples': 6799104, 'steps': 35411, 'loss/train': 1.3060005903244019} 08/30/2021 19:36:53 - INFO - __main__ - Step 35413: {'lr': 0.0004397149515913985, 'samples': 6799296, 'steps': 35412, 'loss/train': 1.6305447816848755} 08/30/2021 19:36:55 - INFO - __main__ - Step 35414: {'lr': 0.0004397114955100856, 'samples': 6799488, 'steps': 35413, 'loss/train': 1.6426652669906616} 08/30/2021 19:36:56 - INFO - __main__ - Step 35415: {'lr': 0.00043970803934329167, 'samples': 6799680, 'steps': 35414, 'loss/train': 1.3134020566940308} 08/30/2021 19:36:56 - INFO - __main__ - Step 35416: {'lr': 0.00043970458309101825, 'samples': 6799872, 'steps': 35415, 'loss/train': 0.20792165398597717} 08/30/2021 19:36:57 - INFO - __main__ - Step 35417: {'lr': 0.0004397011267532668, 'samples': 6800064, 'steps': 35416, 'loss/train': 1.2112113237380981} 08/30/2021 19:36:57 - INFO - __main__ - Step 35418: {'lr': 0.00043969767033003894, 'samples': 6800256, 'steps': 35417, 'loss/train': 1.7336615324020386} 08/30/2021 19:36:58 - INFO - __main__ - Step 35419: {'lr': 0.0004396942138213363, 'samples': 6800448, 'steps': 35418, 'loss/train': 1.6246439218521118} 08/30/2021 19:36:59 - INFO - __main__ - Step 35420: {'lr': 0.00043969075722716033, 'samples': 6800640, 'steps': 35419, 'loss/train': 1.69806706905365} 08/30/2021 19:36:59 - INFO - __main__ - Step 35421: {'lr': 0.0004396873005475127, 'samples': 6800832, 'steps': 35420, 'loss/train': 1.445824384689331} 08/30/2021 19:37:00 - INFO - __main__ - Step 35422: {'lr': 0.00043968384378239477, 'samples': 6801024, 'steps': 35421, 'loss/train': 1.4318392276763916} 08/30/2021 19:37:00 - INFO - __main__ - Step 35423: {'lr': 0.00043968038693180834, 'samples': 6801216, 'steps': 35422, 'loss/train': 1.7666666507720947} 08/30/2021 19:37:02 - INFO - __main__ - Step 35424: {'lr': 0.00043967692999575484, 'samples': 6801408, 'steps': 35423, 'loss/train': 1.677564024925232} 08/30/2021 19:37:02 - INFO - __main__ - Step 35425: {'lr': 0.00043967347297423575, 'samples': 6801600, 'steps': 35424, 'loss/train': 0.8641349673271179} 08/30/2021 19:37:02 - INFO - __main__ - Step 35426: {'lr': 0.0004396700158672528, 'samples': 6801792, 'steps': 35425, 'loss/train': 2.300177574157715} 08/30/2021 19:37:03 - INFO - __main__ - Step 35427: {'lr': 0.0004396665586748075, 'samples': 6801984, 'steps': 35426, 'loss/train': 1.1048344373703003} 08/30/2021 19:37:03 - INFO - __main__ - Step 35428: {'lr': 0.0004396631013969013, 'samples': 6802176, 'steps': 35427, 'loss/train': 0.26490673422813416} 08/30/2021 19:37:05 - INFO - __main__ - Step 35429: {'lr': 0.0004396596440335359, 'samples': 6802368, 'steps': 35428, 'loss/train': 1.4350842237472534} 08/30/2021 19:37:05 - INFO - __main__ - Step 35430: {'lr': 0.00043965618658471276, 'samples': 6802560, 'steps': 35429, 'loss/train': 1.8680329322814941} 08/30/2021 19:37:05 - INFO - __main__ - Step 35431: {'lr': 0.0004396527290504334, 'samples': 6802752, 'steps': 35430, 'loss/train': 0.5671683549880981} 08/30/2021 19:37:06 - INFO - __main__ - Step 35432: {'lr': 0.00043964927143069955, 'samples': 6802944, 'steps': 35431, 'loss/train': 1.3406174182891846} 08/30/2021 19:37:06 - INFO - __main__ - Step 35433: {'lr': 0.0004396458137255126, 'samples': 6803136, 'steps': 35432, 'loss/train': 0.07098355144262314} 08/30/2021 19:37:07 - INFO - __main__ - Step 35434: {'lr': 0.0004396423559348742, 'samples': 6803328, 'steps': 35433, 'loss/train': 1.6706665754318237} 08/30/2021 19:37:08 - INFO - __main__ - Step 35435: {'lr': 0.0004396388980587859, 'samples': 6803520, 'steps': 35434, 'loss/train': 1.9187897443771362} 08/30/2021 19:37:08 - INFO - __main__ - Step 35436: {'lr': 0.0004396354400972492, 'samples': 6803712, 'steps': 35435, 'loss/train': 1.5230586528778076} 08/30/2021 19:37:09 - INFO - __main__ - Step 35437: {'lr': 0.0004396319820502657, 'samples': 6803904, 'steps': 35436, 'loss/train': 1.3035917282104492} 08/30/2021 19:37:09 - INFO - __main__ - Step 35438: {'lr': 0.000439628523917837, 'samples': 6804096, 'steps': 35437, 'loss/train': 1.4326589107513428} 08/30/2021 19:37:10 - INFO - __main__ - Step 35439: {'lr': 0.0004396250656999646, 'samples': 6804288, 'steps': 35438, 'loss/train': 1.3794828653335571} 08/30/2021 19:37:11 - INFO - __main__ - Step 35440: {'lr': 0.00043962160739665, 'samples': 6804480, 'steps': 35439, 'loss/train': 1.1045030355453491} 08/30/2021 19:37:11 - INFO - __main__ - Step 35441: {'lr': 0.0004396181490078949, 'samples': 6804672, 'steps': 35440, 'loss/train': 0.6782146096229553} 08/30/2021 19:37:12 - INFO - __main__ - Step 35442: {'lr': 0.0004396146905337008, 'samples': 6804864, 'steps': 35441, 'loss/train': 1.210057258605957} 08/30/2021 19:37:12 - INFO - __main__ - Step 35443: {'lr': 0.0004396112319740692, 'samples': 6805056, 'steps': 35442, 'loss/train': 1.6531317234039307} 08/30/2021 19:37:13 - INFO - __main__ - Step 35444: {'lr': 0.0004396077733290017, 'samples': 6805248, 'steps': 35443, 'loss/train': 1.5051201581954956} 08/30/2021 19:37:14 - INFO - __main__ - Step 35445: {'lr': 0.00043960431459849993, 'samples': 6805440, 'steps': 35444, 'loss/train': 1.4708025455474854} 08/30/2021 19:37:14 - INFO - __main__ - Step 35446: {'lr': 0.00043960085578256537, 'samples': 6805632, 'steps': 35445, 'loss/train': 1.2306946516036987} 08/30/2021 19:37:15 - INFO - __main__ - Step 35447: {'lr': 0.0004395973968811995, 'samples': 6805824, 'steps': 35446, 'loss/train': 1.0647679567337036} 08/30/2021 19:37:15 - INFO - __main__ - Step 35448: {'lr': 0.00043959393789440407, 'samples': 6806016, 'steps': 35447, 'loss/train': 1.2634668350219727} 08/30/2021 19:37:15 - INFO - __main__ - Step 35449: {'lr': 0.0004395904788221805, 'samples': 6806208, 'steps': 35448, 'loss/train': 1.3179101943969727} 08/30/2021 19:37:17 - INFO - __main__ - Step 35450: {'lr': 0.00043958701966453033, 'samples': 6806400, 'steps': 35449, 'loss/train': 1.3771743774414062} 08/30/2021 19:37:17 - INFO - __main__ - Step 35451: {'lr': 0.00043958356042145524, 'samples': 6806592, 'steps': 35450, 'loss/train': 1.5681291818618774} 08/30/2021 19:37:18 - INFO - __main__ - Step 35452: {'lr': 0.0004395801010929567, 'samples': 6806784, 'steps': 35451, 'loss/train': 1.4143986701965332} 08/30/2021 19:37:18 - INFO - __main__ - Step 35453: {'lr': 0.0004395766416790363, 'samples': 6806976, 'steps': 35452, 'loss/train': 1.2842624187469482} 08/30/2021 19:37:18 - INFO - __main__ - Step 35454: {'lr': 0.0004395731821796956, 'samples': 6807168, 'steps': 35453, 'loss/train': 1.5339900255203247} 08/30/2021 19:37:20 - INFO - __main__ - Step 35455: {'lr': 0.00043956972259493615, 'samples': 6807360, 'steps': 35454, 'loss/train': 1.3370405435562134} 08/30/2021 19:37:20 - INFO - __main__ - Step 35456: {'lr': 0.0004395662629247595, 'samples': 6807552, 'steps': 35455, 'loss/train': 1.2923717498779297} 08/30/2021 19:37:21 - INFO - __main__ - Step 35457: {'lr': 0.0004395628031691672, 'samples': 6807744, 'steps': 35456, 'loss/train': 0.9794766902923584} 08/30/2021 19:37:21 - INFO - __main__ - Step 35458: {'lr': 0.00043955934332816083, 'samples': 6807936, 'steps': 35457, 'loss/train': 1.4066797494888306} 08/30/2021 19:37:21 - INFO - __main__ - Step 35459: {'lr': 0.00043955588340174195, 'samples': 6808128, 'steps': 35458, 'loss/train': 1.0689204931259155} 08/30/2021 19:37:23 - INFO - __main__ - Step 35460: {'lr': 0.00043955242338991217, 'samples': 6808320, 'steps': 35459, 'loss/train': 1.3036293983459473} 08/30/2021 19:37:23 - INFO - __main__ - Step 35461: {'lr': 0.0004395489632926729, 'samples': 6808512, 'steps': 35460, 'loss/train': 1.0542709827423096} 08/30/2021 19:37:24 - INFO - __main__ - Step 35462: {'lr': 0.0004395455031100258, 'samples': 6808704, 'steps': 35461, 'loss/train': 1.4861023426055908} 08/30/2021 19:37:24 - INFO - __main__ - Step 35463: {'lr': 0.0004395420428419725, 'samples': 6808896, 'steps': 35462, 'loss/train': 0.8354753851890564} 08/30/2021 19:37:25 - INFO - __main__ - Step 35464: {'lr': 0.0004395385824885144, 'samples': 6809088, 'steps': 35463, 'loss/train': 1.276066780090332} 08/30/2021 19:37:27 - INFO - __main__ - Step 35465: {'lr': 0.0004395351220496532, 'samples': 6809280, 'steps': 35464, 'loss/train': 2.0710320472717285} 08/30/2021 19:37:27 - INFO - __main__ - Step 35466: {'lr': 0.00043953166152539035, 'samples': 6809472, 'steps': 35465, 'loss/train': 1.3038617372512817} 08/30/2021 19:37:27 - INFO - __main__ - Step 35467: {'lr': 0.00043952820091572753, 'samples': 6809664, 'steps': 35466, 'loss/train': 1.283642292022705} 08/30/2021 19:37:28 - INFO - __main__ - Step 35468: {'lr': 0.0004395247402206662, 'samples': 6809856, 'steps': 35467, 'loss/train': 1.750546932220459} 08/30/2021 19:37:28 - INFO - __main__ - Step 35469: {'lr': 0.0004395212794402079, 'samples': 6810048, 'steps': 35468, 'loss/train': 1.957651138305664} 08/30/2021 19:37:29 - INFO - __main__ - Step 35470: {'lr': 0.00043951781857435424, 'samples': 6810240, 'steps': 35469, 'loss/train': 1.3968238830566406} 08/30/2021 19:37:30 - INFO - __main__ - Step 35471: {'lr': 0.00043951435762310686, 'samples': 6810432, 'steps': 35470, 'loss/train': 1.20931875705719} 08/30/2021 19:37:30 - INFO - __main__ - Step 35472: {'lr': 0.0004395108965864671, 'samples': 6810624, 'steps': 35471, 'loss/train': 1.7945719957351685} 08/30/2021 19:37:31 - INFO - __main__ - Step 35473: {'lr': 0.00043950743546443676, 'samples': 6810816, 'steps': 35472, 'loss/train': 1.374839186668396} 08/30/2021 19:37:31 - INFO - __main__ - Step 35474: {'lr': 0.0004395039742570173, 'samples': 6811008, 'steps': 35473, 'loss/train': 1.3714797496795654} 08/30/2021 19:37:33 - INFO - __main__ - Step 35475: {'lr': 0.00043950051296421023, 'samples': 6811200, 'steps': 35474, 'loss/train': 1.2336626052856445} 08/30/2021 19:37:33 - INFO - __main__ - Step 35476: {'lr': 0.00043949705158601715, 'samples': 6811392, 'steps': 35475, 'loss/train': 0.9487754702568054} 08/30/2021 19:37:33 - INFO - __main__ - Step 35477: {'lr': 0.00043949359012243963, 'samples': 6811584, 'steps': 35476, 'loss/train': 0.9743692278862} 08/30/2021 19:37:34 - INFO - __main__ - Step 35478: {'lr': 0.00043949012857347924, 'samples': 6811776, 'steps': 35477, 'loss/train': 1.6047486066818237} 08/30/2021 19:37:34 - INFO - __main__ - Step 35479: {'lr': 0.0004394866669391375, 'samples': 6811968, 'steps': 35478, 'loss/train': 1.0453120470046997} 08/30/2021 19:37:36 - INFO - __main__ - Step 35480: {'lr': 0.00043948320521941596, 'samples': 6812160, 'steps': 35479, 'loss/train': 1.099510908126831} 08/30/2021 19:37:36 - INFO - __main__ - Step 35481: {'lr': 0.00043947974341431627, 'samples': 6812352, 'steps': 35480, 'loss/train': 1.6088054180145264} 08/30/2021 19:37:36 - INFO - __main__ - Step 35482: {'lr': 0.0004394762815238399, 'samples': 6812544, 'steps': 35481, 'loss/train': 1.281843662261963} 08/30/2021 19:37:37 - INFO - __main__ - Step 35483: {'lr': 0.00043947281954798844, 'samples': 6812736, 'steps': 35482, 'loss/train': 1.0731096267700195} 08/30/2021 19:37:37 - INFO - __main__ - Step 35484: {'lr': 0.0004394693574867635, 'samples': 6812928, 'steps': 35483, 'loss/train': 1.6933749914169312} 08/30/2021 19:37:37 - INFO - __main__ - Step 35485: {'lr': 0.0004394658953401666, 'samples': 6813120, 'steps': 35484, 'loss/train': 1.4031773805618286} 08/30/2021 19:37:39 - INFO - __main__ - Step 35486: {'lr': 0.0004394624331081992, 'samples': 6813312, 'steps': 35485, 'loss/train': 1.0322613716125488} 08/30/2021 19:37:39 - INFO - __main__ - Step 35487: {'lr': 0.00043945897079086295, 'samples': 6813504, 'steps': 35486, 'loss/train': 1.3490275144577026} 08/30/2021 19:37:40 - INFO - __main__ - Step 35488: {'lr': 0.00043945550838815953, 'samples': 6813696, 'steps': 35487, 'loss/train': 1.5497703552246094} 08/30/2021 19:37:40 - INFO - __main__ - Step 35489: {'lr': 0.00043945204590009027, 'samples': 6813888, 'steps': 35488, 'loss/train': 2.1221632957458496} 08/30/2021 19:37:40 - INFO - __main__ - Step 35490: {'lr': 0.0004394485833266569, 'samples': 6814080, 'steps': 35489, 'loss/train': 1.2926548719406128} 08/30/2021 19:37:42 - INFO - __main__ - Step 35491: {'lr': 0.0004394451206678609, 'samples': 6814272, 'steps': 35490, 'loss/train': 1.2890409231185913} 08/30/2021 19:37:42 - INFO - __main__ - Step 35492: {'lr': 0.00043944165792370385, 'samples': 6814464, 'steps': 35491, 'loss/train': 1.413093090057373} 08/30/2021 19:37:43 - INFO - __main__ - Step 35493: {'lr': 0.00043943819509418723, 'samples': 6814656, 'steps': 35492, 'loss/train': 1.5966626405715942} 08/30/2021 19:37:43 - INFO - __main__ - Step 35494: {'lr': 0.00043943473217931283, 'samples': 6814848, 'steps': 35493, 'loss/train': 1.3935346603393555} 08/30/2021 19:37:43 - INFO - __main__ - Step 35495: {'lr': 0.0004394312691790821, 'samples': 6815040, 'steps': 35494, 'loss/train': 1.2111256122589111} 08/30/2021 19:37:45 - INFO - __main__ - Step 35496: {'lr': 0.00043942780609349636, 'samples': 6815232, 'steps': 35495, 'loss/train': 1.3922882080078125} 08/30/2021 19:37:45 - INFO - __main__ - Step 35497: {'lr': 0.0004394243429225575, 'samples': 6815424, 'steps': 35496, 'loss/train': 1.4599941968917847} 08/30/2021 19:37:46 - INFO - __main__ - Step 35498: {'lr': 0.0004394208796662669, 'samples': 6815616, 'steps': 35497, 'loss/train': 1.6065566539764404} 08/30/2021 19:37:46 - INFO - __main__ - Step 35499: {'lr': 0.00043941741632462625, 'samples': 6815808, 'steps': 35498, 'loss/train': 1.4144123792648315} 08/30/2021 19:37:46 - INFO - __main__ - Step 35500: {'lr': 0.000439413952897637, 'samples': 6816000, 'steps': 35499, 'loss/train': 1.3598979711532593} 08/30/2021 19:37:48 - INFO - __main__ - Step 35501: {'lr': 0.0004394104893853007, 'samples': 6816192, 'steps': 35500, 'loss/train': 1.4200773239135742} 08/30/2021 19:37:49 - INFO - __main__ - Step 35502: {'lr': 0.00043940702578761906, 'samples': 6816384, 'steps': 35501, 'loss/train': 1.4697645902633667} 08/30/2021 19:37:49 - INFO - __main__ - Step 35503: {'lr': 0.00043940356210459344, 'samples': 6816576, 'steps': 35502, 'loss/train': 1.477472186088562} 08/30/2021 19:37:49 - INFO - __main__ - Step 35504: {'lr': 0.0004394000983362255, 'samples': 6816768, 'steps': 35503, 'loss/train': 1.402300477027893} 08/30/2021 19:37:50 - INFO - __main__ - Step 35505: {'lr': 0.0004393966344825168, 'samples': 6816960, 'steps': 35504, 'loss/train': 1.4279059171676636} 08/30/2021 19:37:51 - INFO - __main__ - Step 35506: {'lr': 0.00043939317054346894, 'samples': 6817152, 'steps': 35505, 'loss/train': 0.35592007637023926} 08/30/2021 19:37:52 - INFO - __main__ - Step 35507: {'lr': 0.00043938970651908346, 'samples': 6817344, 'steps': 35506, 'loss/train': 1.366572618484497} 08/30/2021 19:37:52 - INFO - __main__ - Step 35508: {'lr': 0.0004393862424093619, 'samples': 6817536, 'steps': 35507, 'loss/train': 0.6412873268127441} 08/30/2021 19:37:52 - INFO - __main__ - Step 35509: {'lr': 0.0004393827782143057, 'samples': 6817728, 'steps': 35508, 'loss/train': 1.8807237148284912} 08/30/2021 19:37:53 - INFO - __main__ - Step 35510: {'lr': 0.00043937931393391667, 'samples': 6817920, 'steps': 35509, 'loss/train': 0.8151328563690186} 08/30/2021 19:37:54 - INFO - __main__ - Step 35511: {'lr': 0.0004393758495681962, 'samples': 6818112, 'steps': 35510, 'loss/train': 1.8052244186401367} 08/30/2021 19:37:55 - INFO - __main__ - Step 35512: {'lr': 0.0004393723851171459, 'samples': 6818304, 'steps': 35511, 'loss/train': 1.8337180614471436} 08/30/2021 19:37:55 - INFO - __main__ - Step 35513: {'lr': 0.0004393689205807673, 'samples': 6818496, 'steps': 35512, 'loss/train': 1.5067464113235474} 08/30/2021 19:37:55 - INFO - __main__ - Step 35514: {'lr': 0.00043936545595906206, 'samples': 6818688, 'steps': 35513, 'loss/train': 4.344979286193848} 08/30/2021 19:37:56 - INFO - __main__ - Step 35515: {'lr': 0.00043936199125203156, 'samples': 6818880, 'steps': 35514, 'loss/train': 0.9031326770782471} 08/30/2021 19:37:57 - INFO - __main__ - Step 35516: {'lr': 0.00043935852645967755, 'samples': 6819072, 'steps': 35515, 'loss/train': 1.792057752609253} 08/30/2021 19:37:57 - INFO - __main__ - Step 35517: {'lr': 0.00043935506158200143, 'samples': 6819264, 'steps': 35516, 'loss/train': 1.351317286491394} 08/30/2021 19:37:58 - INFO - __main__ - Step 35518: {'lr': 0.000439351596619005, 'samples': 6819456, 'steps': 35517, 'loss/train': 1.123411774635315} 08/30/2021 19:37:58 - INFO - __main__ - Step 35519: {'lr': 0.00043934813157068956, 'samples': 6819648, 'steps': 35518, 'loss/train': 1.02517569065094} 08/30/2021 19:37:59 - INFO - __main__ - Step 35520: {'lr': 0.00043934466643705673, 'samples': 6819840, 'steps': 35519, 'loss/train': 0.5735183954238892} 08/30/2021 19:38:00 - INFO - __main__ - Step 35521: {'lr': 0.00043934120121810814, 'samples': 6820032, 'steps': 35520, 'loss/train': 1.282111644744873} 08/30/2021 19:38:01 - INFO - __main__ - Step 35522: {'lr': 0.0004393377359138454, 'samples': 6820224, 'steps': 35521, 'loss/train': 1.5309820175170898} 08/30/2021 19:38:01 - INFO - __main__ - Step 35523: {'lr': 0.00043933427052426986, 'samples': 6820416, 'steps': 35522, 'loss/train': 1.2699809074401855} 08/30/2021 19:38:02 - INFO - __main__ - Step 35524: {'lr': 0.00043933080504938337, 'samples': 6820608, 'steps': 35523, 'loss/train': 1.2430779933929443} 08/30/2021 19:38:02 - INFO - __main__ - Step 35525: {'lr': 0.00043932733948918724, 'samples': 6820800, 'steps': 35524, 'loss/train': 1.4439725875854492} 08/30/2021 19:38:03 - INFO - __main__ - Step 35526: {'lr': 0.0004393238738436832, 'samples': 6820992, 'steps': 35525, 'loss/train': 1.9710932970046997} 08/30/2021 19:38:04 - INFO - __main__ - Step 35527: {'lr': 0.00043932040811287264, 'samples': 6821184, 'steps': 35526, 'loss/train': 1.4086105823516846} 08/30/2021 19:38:04 - INFO - __main__ - Step 35528: {'lr': 0.0004393169422967573, 'samples': 6821376, 'steps': 35527, 'loss/train': 1.0004055500030518} 08/30/2021 19:38:05 - INFO - __main__ - Step 35529: {'lr': 0.0004393134763953387, 'samples': 6821568, 'steps': 35528, 'loss/train': 0.9425281286239624} 08/30/2021 19:38:05 - INFO - __main__ - Step 35530: {'lr': 0.00043931001040861835, 'samples': 6821760, 'steps': 35529, 'loss/train': 1.9139232635498047} 08/30/2021 19:38:06 - INFO - __main__ - Step 35531: {'lr': 0.00043930654433659775, 'samples': 6821952, 'steps': 35530, 'loss/train': 1.7550944089889526} 08/30/2021 19:38:07 - INFO - __main__ - Step 35532: {'lr': 0.0004393030781792787, 'samples': 6822144, 'steps': 35531, 'loss/train': 1.1504539251327515} 08/30/2021 19:38:07 - INFO - __main__ - Step 35533: {'lr': 0.00043929961193666246, 'samples': 6822336, 'steps': 35532, 'loss/train': 1.4087321758270264} 08/30/2021 19:38:08 - INFO - __main__ - Step 35534: {'lr': 0.0004392961456087508, 'samples': 6822528, 'steps': 35533, 'loss/train': 0.4733916223049164} 08/30/2021 19:38:08 - INFO - __main__ - Step 35535: {'lr': 0.00043929267919554516, 'samples': 6822720, 'steps': 35534, 'loss/train': 1.3361679315567017} 08/30/2021 19:38:08 - INFO - __main__ - Step 35536: {'lr': 0.00043928921269704725, 'samples': 6822912, 'steps': 35535, 'loss/train': 1.0247011184692383} 08/30/2021 19:38:10 - INFO - __main__ - Step 35537: {'lr': 0.00043928574611325845, 'samples': 6823104, 'steps': 35536, 'loss/train': 1.9099128246307373} 08/30/2021 19:38:10 - INFO - __main__ - Step 35538: {'lr': 0.00043928227944418046, 'samples': 6823296, 'steps': 35537, 'loss/train': 0.7634215354919434} 08/30/2021 19:38:11 - INFO - __main__ - Step 35539: {'lr': 0.00043927881268981484, 'samples': 6823488, 'steps': 35538, 'loss/train': 1.7309541702270508} 08/30/2021 19:38:11 - INFO - __main__ - Step 35540: {'lr': 0.00043927534585016305, 'samples': 6823680, 'steps': 35539, 'loss/train': 1.7048053741455078} 08/30/2021 19:38:11 - INFO - __main__ - Step 35541: {'lr': 0.0004392718789252267, 'samples': 6823872, 'steps': 35540, 'loss/train': 1.5013402700424194} 08/30/2021 19:38:13 - INFO - __main__ - Step 35542: {'lr': 0.0004392684119150074, 'samples': 6824064, 'steps': 35541, 'loss/train': 1.8228617906570435} 08/30/2021 19:38:13 - INFO - __main__ - Step 35543: {'lr': 0.0004392649448195066, 'samples': 6824256, 'steps': 35542, 'loss/train': 1.3826454877853394} 08/30/2021 19:38:14 - INFO - __main__ - Step 35544: {'lr': 0.000439261477638726, 'samples': 6824448, 'steps': 35543, 'loss/train': 1.5281010866165161} 08/30/2021 19:38:14 - INFO - __main__ - Step 35545: {'lr': 0.0004392580103726671, 'samples': 6824640, 'steps': 35544, 'loss/train': 2.0254573822021484} 08/30/2021 19:38:14 - INFO - __main__ - Step 35546: {'lr': 0.0004392545430213315, 'samples': 6824832, 'steps': 35545, 'loss/train': 1.2443621158599854} 08/30/2021 19:38:16 - INFO - __main__ - Step 35547: {'lr': 0.00043925107558472065, 'samples': 6825024, 'steps': 35546, 'loss/train': 0.5305963754653931} 08/30/2021 19:38:16 - INFO - __main__ - Step 35548: {'lr': 0.0004392476080628363, 'samples': 6825216, 'steps': 35547, 'loss/train': 0.9291126728057861} 08/30/2021 19:38:17 - INFO - __main__ - Step 35549: {'lr': 0.00043924414045567973, 'samples': 6825408, 'steps': 35548, 'loss/train': 1.429993748664856} 08/30/2021 19:38:17 - INFO - __main__ - Step 35550: {'lr': 0.00043924067276325274, 'samples': 6825600, 'steps': 35549, 'loss/train': 0.35420963168144226} 08/30/2021 19:38:18 - INFO - __main__ - Step 35551: {'lr': 0.0004392372049855569, 'samples': 6825792, 'steps': 35550, 'loss/train': 1.6251249313354492} 08/30/2021 19:38:19 - INFO - __main__ - Step 35552: {'lr': 0.0004392337371225936, 'samples': 6825984, 'steps': 35551, 'loss/train': 1.0503017902374268} 08/30/2021 19:38:19 - INFO - __main__ - Step 35553: {'lr': 0.0004392302691743645, 'samples': 6826176, 'steps': 35552, 'loss/train': 0.13708476722240448} 08/30/2021 19:38:20 - INFO - __main__ - Step 35554: {'lr': 0.0004392268011408712, 'samples': 6826368, 'steps': 35553, 'loss/train': 1.3462666273117065} 08/30/2021 19:38:20 - INFO - __main__ - Step 35555: {'lr': 0.0004392233330221152, 'samples': 6826560, 'steps': 35554, 'loss/train': 1.2558846473693848} 08/30/2021 19:38:21 - INFO - __main__ - Step 35556: {'lr': 0.0004392198648180981, 'samples': 6826752, 'steps': 35555, 'loss/train': 0.604512095451355} 08/30/2021 19:38:22 - INFO - __main__ - Step 35557: {'lr': 0.0004392163965288215, 'samples': 6826944, 'steps': 35556, 'loss/train': 1.3461673259735107} 08/30/2021 19:38:23 - INFO - __main__ - Step 35558: {'lr': 0.0004392129281542868, 'samples': 6827136, 'steps': 35557, 'loss/train': 1.3256924152374268} 08/30/2021 19:38:23 - INFO - __main__ - Step 35559: {'lr': 0.00043920945969449577, 'samples': 6827328, 'steps': 35558, 'loss/train': 1.069580078125} 08/30/2021 19:38:23 - INFO - __main__ - Step 35560: {'lr': 0.0004392059911494498, 'samples': 6827520, 'steps': 35559, 'loss/train': 1.2970229387283325} 08/30/2021 19:38:24 - INFO - __main__ - Step 35561: {'lr': 0.0004392025225191506, 'samples': 6827712, 'steps': 35560, 'loss/train': 1.1350421905517578} 08/30/2021 19:38:24 - INFO - __main__ - Step 35562: {'lr': 0.0004391990538035996, 'samples': 6827904, 'steps': 35561, 'loss/train': 1.411685585975647} 08/30/2021 19:38:26 - INFO - __main__ - Step 35563: {'lr': 0.00043919558500279845, 'samples': 6828096, 'steps': 35562, 'loss/train': 1.0079528093338013} 08/30/2021 19:38:26 - INFO - __main__ - Step 35564: {'lr': 0.0004391921161167487, 'samples': 6828288, 'steps': 35563, 'loss/train': 1.3235201835632324} 08/30/2021 19:38:26 - INFO - __main__ - Step 35565: {'lr': 0.00043918864714545194, 'samples': 6828480, 'steps': 35564, 'loss/train': 1.5277256965637207} 08/30/2021 19:38:27 - INFO - __main__ - Step 35566: {'lr': 0.00043918517808890964, 'samples': 6828672, 'steps': 35565, 'loss/train': 1.6159189939498901} 08/30/2021 19:38:27 - INFO - __main__ - Step 35567: {'lr': 0.0004391817089471234, 'samples': 6828864, 'steps': 35566, 'loss/train': 1.0270401239395142} 08/30/2021 19:38:29 - INFO - __main__ - Step 35568: {'lr': 0.0004391782397200949, 'samples': 6829056, 'steps': 35567, 'loss/train': 1.0426150560379028} 08/30/2021 19:38:29 - INFO - __main__ - Step 35569: {'lr': 0.0004391747704078255, 'samples': 6829248, 'steps': 35568, 'loss/train': 1.212659478187561} 08/30/2021 19:38:29 - INFO - __main__ - Step 35570: {'lr': 0.0004391713010103169, 'samples': 6829440, 'steps': 35569, 'loss/train': 1.590492844581604} 08/30/2021 19:38:30 - INFO - __main__ - Step 35571: {'lr': 0.0004391678315275706, 'samples': 6829632, 'steps': 35570, 'loss/train': 1.5762189626693726} 08/30/2021 19:38:30 - INFO - __main__ - Step 35572: {'lr': 0.00043916436195958825, 'samples': 6829824, 'steps': 35571, 'loss/train': 1.54468834400177} 08/30/2021 19:38:32 - INFO - __main__ - Step 35573: {'lr': 0.00043916089230637133, 'samples': 6830016, 'steps': 35572, 'loss/train': 1.7828104496002197} 08/30/2021 19:38:32 - INFO - __main__ - Step 35574: {'lr': 0.0004391574225679215, 'samples': 6830208, 'steps': 35573, 'loss/train': 1.7065386772155762} 08/30/2021 19:38:33 - INFO - __main__ - Step 35575: {'lr': 0.0004391539527442401, 'samples': 6830400, 'steps': 35574, 'loss/train': 0.7366040349006653} 08/30/2021 19:38:33 - INFO - __main__ - Step 35576: {'lr': 0.000439150482835329, 'samples': 6830592, 'steps': 35575, 'loss/train': 1.237656593322754} 08/30/2021 19:38:33 - INFO - __main__ - Step 35577: {'lr': 0.0004391470128411895, 'samples': 6830784, 'steps': 35576, 'loss/train': 1.1078851222991943} 08/30/2021 19:38:35 - INFO - __main__ - Step 35578: {'lr': 0.00043914354276182335, 'samples': 6830976, 'steps': 35577, 'loss/train': 1.0219086408615112} 08/30/2021 19:38:36 - INFO - __main__ - Step 35579: {'lr': 0.00043914007259723196, 'samples': 6831168, 'steps': 35578, 'loss/train': 1.4273958206176758} 08/30/2021 19:38:36 - INFO - __main__ - Step 35580: {'lr': 0.000439136602347417, 'samples': 6831360, 'steps': 35579, 'loss/train': 1.1936569213867188} 08/30/2021 19:38:36 - INFO - __main__ - Step 35581: {'lr': 0.00043913313201238017, 'samples': 6831552, 'steps': 35580, 'loss/train': 0.10602215677499771} 08/30/2021 19:38:37 - INFO - __main__ - Step 35582: {'lr': 0.00043912966159212263, 'samples': 6831744, 'steps': 35581, 'loss/train': 1.244699239730835} 08/30/2021 19:38:38 - INFO - __main__ - Step 35583: {'lr': 0.0004391261910866463, 'samples': 6831936, 'steps': 35582, 'loss/train': 1.4847512245178223} 08/30/2021 19:38:39 - INFO - __main__ - Step 35584: {'lr': 0.0004391227204959526, 'samples': 6832128, 'steps': 35583, 'loss/train': 1.280083179473877} 08/30/2021 19:38:39 - INFO - __main__ - Step 35585: {'lr': 0.00043911924982004315, 'samples': 6832320, 'steps': 35584, 'loss/train': 1.2352662086486816} 08/30/2021 19:38:40 - INFO - __main__ - Step 35586: {'lr': 0.0004391157790589195, 'samples': 6832512, 'steps': 35585, 'loss/train': 1.0446867942810059} 08/30/2021 19:38:40 - INFO - __main__ - Step 35587: {'lr': 0.00043911230821258313, 'samples': 6832704, 'steps': 35586, 'loss/train': 1.8367719650268555} 08/30/2021 19:38:41 - INFO - __main__ - Step 35588: {'lr': 0.00043910883728103575, 'samples': 6832896, 'steps': 35587, 'loss/train': 0.08733471482992172} 08/30/2021 19:38:42 - INFO - __main__ - Step 35589: {'lr': 0.0004391053662642788, 'samples': 6833088, 'steps': 35588, 'loss/train': 1.8498398065567017} 08/30/2021 19:38:42 - INFO - __main__ - Step 35590: {'lr': 0.00043910189516231386, 'samples': 6833280, 'steps': 35589, 'loss/train': 1.3803876638412476} 08/30/2021 19:38:43 - INFO - __main__ - Step 35591: {'lr': 0.00043909842397514255, 'samples': 6833472, 'steps': 35590, 'loss/train': 1.363560438156128} 08/30/2021 19:38:43 - INFO - __main__ - Step 35592: {'lr': 0.00043909495270276646, 'samples': 6833664, 'steps': 35591, 'loss/train': 1.172803282737732} 08/30/2021 19:38:45 - INFO - __main__ - Step 35593: {'lr': 0.00043909148134518703, 'samples': 6833856, 'steps': 35592, 'loss/train': 1.4856820106506348} 08/30/2021 19:38:45 - INFO - __main__ - Step 35594: {'lr': 0.0004390880099024059, 'samples': 6834048, 'steps': 35593, 'loss/train': 2.113456964492798} 08/30/2021 19:38:45 - INFO - __main__ - Step 35595: {'lr': 0.00043908453837442464, 'samples': 6834240, 'steps': 35594, 'loss/train': 1.9697480201721191} 08/30/2021 19:38:46 - INFO - __main__ - Step 35596: {'lr': 0.0004390810667612448, 'samples': 6834432, 'steps': 35595, 'loss/train': 1.910926103591919} 08/30/2021 19:38:46 - INFO - __main__ - Step 35597: {'lr': 0.00043907759506286797, 'samples': 6834624, 'steps': 35596, 'loss/train': 0.06204963102936745} 08/30/2021 19:38:47 - INFO - __main__ - Step 35598: {'lr': 0.00043907412327929575, 'samples': 6834816, 'steps': 35597, 'loss/train': 1.398746132850647} 08/30/2021 19:38:48 - INFO - __main__ - Step 35599: {'lr': 0.00043907065141052953, 'samples': 6835008, 'steps': 35598, 'loss/train': 1.45152747631073} 08/30/2021 19:38:48 - INFO - __main__ - Step 35600: {'lr': 0.00043906717945657104, 'samples': 6835200, 'steps': 35599, 'loss/train': 1.3819210529327393} 08/30/2021 19:38:49 - INFO - __main__ - Step 35601: {'lr': 0.00043906370741742185, 'samples': 6835392, 'steps': 35600, 'loss/train': 1.8691887855529785} 08/30/2021 19:38:49 - INFO - __main__ - Step 35602: {'lr': 0.0004390602352930834, 'samples': 6835584, 'steps': 35601, 'loss/train': 0.9794334173202515} 08/30/2021 19:38:49 - INFO - __main__ - Step 35603: {'lr': 0.00043905676308355734, 'samples': 6835776, 'steps': 35602, 'loss/train': 1.4168742895126343} 08/30/2021 19:38:51 - INFO - __main__ - Step 35604: {'lr': 0.00043905329078884527, 'samples': 6835968, 'steps': 35603, 'loss/train': 1.2644916772842407} 08/30/2021 19:38:52 - INFO - __main__ - Step 35605: {'lr': 0.00043904981840894863, 'samples': 6836160, 'steps': 35604, 'loss/train': 0.6998332738876343} 08/30/2021 19:38:52 - INFO - __main__ - Step 35606: {'lr': 0.0004390463459438691, 'samples': 6836352, 'steps': 35605, 'loss/train': 1.3609315156936646} 08/30/2021 19:38:52 - INFO - __main__ - Step 35607: {'lr': 0.0004390428733936082, 'samples': 6836544, 'steps': 35606, 'loss/train': 0.7326480150222778} 08/30/2021 19:38:53 - INFO - __main__ - Step 35608: {'lr': 0.0004390394007581675, 'samples': 6836736, 'steps': 35607, 'loss/train': 0.12532192468643188} 08/30/2021 19:38:55 - INFO - __main__ - Step 35609: {'lr': 0.00043903592803754856, 'samples': 6836928, 'steps': 35608, 'loss/train': 1.637898325920105} 08/30/2021 19:38:55 - INFO - __main__ - Step 35610: {'lr': 0.00043903245523175296, 'samples': 6837120, 'steps': 35609, 'loss/train': 0.8914738297462463} 08/30/2021 19:38:55 - INFO - __main__ - Step 35611: {'lr': 0.00043902898234078223, 'samples': 6837312, 'steps': 35610, 'loss/train': 1.0995962619781494} 08/30/2021 19:38:56 - INFO - __main__ - Step 35612: {'lr': 0.000439025509364638, 'samples': 6837504, 'steps': 35611, 'loss/train': 1.6563763618469238} 08/30/2021 19:38:56 - INFO - __main__ - Step 35613: {'lr': 0.0004390220363033217, 'samples': 6837696, 'steps': 35612, 'loss/train': 1.5935888290405273} 08/30/2021 19:38:57 - INFO - __main__ - Step 35614: {'lr': 0.0004390185631568351, 'samples': 6837888, 'steps': 35613, 'loss/train': 0.7934514880180359} 08/30/2021 19:38:58 - INFO - __main__ - Step 35615: {'lr': 0.00043901508992517956, 'samples': 6838080, 'steps': 35614, 'loss/train': 1.4886112213134766} 08/30/2021 19:38:58 - INFO - __main__ - Step 35616: {'lr': 0.0004390116166083568, 'samples': 6838272, 'steps': 35615, 'loss/train': 1.094867467880249} 08/30/2021 19:38:59 - INFO - __main__ - Step 35617: {'lr': 0.00043900814320636827, 'samples': 6838464, 'steps': 35616, 'loss/train': 1.63827383518219} 08/30/2021 19:38:59 - INFO - __main__ - Step 35618: {'lr': 0.00043900466971921563, 'samples': 6838656, 'steps': 35617, 'loss/train': 1.4104467630386353} 08/30/2021 19:39:01 - INFO - __main__ - Step 35619: {'lr': 0.00043900119614690043, 'samples': 6838848, 'steps': 35618, 'loss/train': 1.210228443145752} 08/30/2021 19:39:01 - INFO - __main__ - Step 35620: {'lr': 0.00043899772248942413, 'samples': 6839040, 'steps': 35619, 'loss/train': 1.6693419218063354} 08/30/2021 19:39:01 - INFO - __main__ - Step 35621: {'lr': 0.0004389942487467884, 'samples': 6839232, 'steps': 35620, 'loss/train': 1.3732359409332275} 08/30/2021 19:39:02 - INFO - __main__ - Step 35622: {'lr': 0.00043899077491899485, 'samples': 6839424, 'steps': 35621, 'loss/train': 0.9131094217300415} 08/30/2021 19:39:02 - INFO - __main__ - Step 35623: {'lr': 0.0004389873010060449, 'samples': 6839616, 'steps': 35622, 'loss/train': 1.4173331260681152} 08/30/2021 19:39:02 - INFO - __main__ - Step 35624: {'lr': 0.00043898382700794015, 'samples': 6839808, 'steps': 35623, 'loss/train': 0.9711362719535828} 08/30/2021 19:39:04 - INFO - __main__ - Step 35625: {'lr': 0.0004389803529246823, 'samples': 6840000, 'steps': 35624, 'loss/train': 1.642768144607544} 08/30/2021 19:39:05 - INFO - __main__ - Step 35626: {'lr': 0.00043897687875627277, 'samples': 6840192, 'steps': 35625, 'loss/train': 1.5010039806365967} 08/30/2021 19:39:05 - INFO - __main__ - Step 35627: {'lr': 0.00043897340450271317, 'samples': 6840384, 'steps': 35626, 'loss/train': 1.1777400970458984} 08/30/2021 19:39:05 - INFO - __main__ - Step 35628: {'lr': 0.0004389699301640051, 'samples': 6840576, 'steps': 35627, 'loss/train': 1.7789735794067383} 08/30/2021 19:39:06 - INFO - __main__ - Step 35629: {'lr': 0.00043896645574015004, 'samples': 6840768, 'steps': 35628, 'loss/train': 1.2212371826171875} 08/30/2021 19:39:07 - INFO - __main__ - Step 35630: {'lr': 0.00043896298123114965, 'samples': 6840960, 'steps': 35629, 'loss/train': 1.5458974838256836} 08/30/2021 19:39:08 - INFO - __main__ - Step 35631: {'lr': 0.00043895950663700546, 'samples': 6841152, 'steps': 35630, 'loss/train': 1.691313624382019} 08/30/2021 19:39:08 - INFO - __main__ - Step 35632: {'lr': 0.000438956031957719, 'samples': 6841344, 'steps': 35631, 'loss/train': 1.8477039337158203} 08/30/2021 19:39:09 - INFO - __main__ - Step 35633: {'lr': 0.0004389525571932919, 'samples': 6841536, 'steps': 35632, 'loss/train': 1.50918710231781} 08/30/2021 19:39:09 - INFO - __main__ - Step 35634: {'lr': 0.00043894908234372564, 'samples': 6841728, 'steps': 35633, 'loss/train': 1.189761996269226} 08/30/2021 19:39:10 - INFO - __main__ - Step 35635: {'lr': 0.0004389456074090219, 'samples': 6841920, 'steps': 35634, 'loss/train': 0.9537816643714905} 08/30/2021 19:39:11 - INFO - __main__ - Step 35636: {'lr': 0.0004389421323891822, 'samples': 6842112, 'steps': 35635, 'loss/train': 1.7430158853530884} 08/30/2021 19:39:11 - INFO - __main__ - Step 35637: {'lr': 0.000438938657284208, 'samples': 6842304, 'steps': 35636, 'loss/train': 0.8309873342514038} 08/30/2021 19:39:12 - INFO - __main__ - Step 35638: {'lr': 0.000438935182094101, 'samples': 6842496, 'steps': 35637, 'loss/train': 1.4525035619735718} 08/30/2021 19:39:12 - INFO - __main__ - Step 35639: {'lr': 0.0004389317068188628, 'samples': 6842688, 'steps': 35638, 'loss/train': 1.3033227920532227} 08/30/2021 19:39:13 - INFO - __main__ - Step 35640: {'lr': 0.0004389282314584948, 'samples': 6842880, 'steps': 35639, 'loss/train': 0.8959699273109436} 08/30/2021 19:39:14 - INFO - __main__ - Step 35641: {'lr': 0.0004389247560129987, 'samples': 6843072, 'steps': 35640, 'loss/train': 1.357480525970459} 08/30/2021 19:39:14 - INFO - __main__ - Step 35642: {'lr': 0.000438921280482376, 'samples': 6843264, 'steps': 35641, 'loss/train': 1.4794636964797974} 08/30/2021 19:39:15 - INFO - __main__ - Step 35643: {'lr': 0.00043891780486662825, 'samples': 6843456, 'steps': 35642, 'loss/train': 1.3781284093856812} 08/30/2021 19:39:15 - INFO - __main__ - Step 35644: {'lr': 0.00043891432916575714, 'samples': 6843648, 'steps': 35643, 'loss/train': 1.154592514038086} 08/30/2021 19:39:16 - INFO - __main__ - Step 35645: {'lr': 0.0004389108533797641, 'samples': 6843840, 'steps': 35644, 'loss/train': 0.9701963663101196} 08/30/2021 19:39:17 - INFO - __main__ - Step 35646: {'lr': 0.00043890737750865074, 'samples': 6844032, 'steps': 35645, 'loss/train': 3.0385804176330566} 08/30/2021 19:39:17 - INFO - __main__ - Step 35647: {'lr': 0.0004389039015524186, 'samples': 6844224, 'steps': 35646, 'loss/train': 1.477814793586731} 08/30/2021 19:39:17 - INFO - __main__ - Step 35648: {'lr': 0.0004389004255110693, 'samples': 6844416, 'steps': 35647, 'loss/train': 1.7936725616455078} 08/30/2021 19:39:18 - INFO - __main__ - Step 35649: {'lr': 0.0004388969493846044, 'samples': 6844608, 'steps': 35648, 'loss/train': 1.4018914699554443} 08/30/2021 19:39:18 - INFO - __main__ - Step 35650: {'lr': 0.00043889347317302543, 'samples': 6844800, 'steps': 35649, 'loss/train': 1.39692223072052} 08/30/2021 19:39:20 - INFO - __main__ - Step 35651: {'lr': 0.000438889996876334, 'samples': 6844992, 'steps': 35650, 'loss/train': 1.7134805917739868} 08/30/2021 19:39:20 - INFO - __main__ - Step 35652: {'lr': 0.00043888652049453163, 'samples': 6845184, 'steps': 35651, 'loss/train': 1.6207311153411865} 08/30/2021 19:39:20 - INFO - __main__ - Step 35653: {'lr': 0.0004388830440276199, 'samples': 6845376, 'steps': 35652, 'loss/train': 1.9511761665344238} 08/30/2021 19:39:21 - INFO - __main__ - Step 35654: {'lr': 0.0004388795674756004, 'samples': 6845568, 'steps': 35653, 'loss/train': 1.9038118124008179} 08/30/2021 19:39:21 - INFO - __main__ - Step 35655: {'lr': 0.0004388760908384747, 'samples': 6845760, 'steps': 35654, 'loss/train': 1.5171244144439697} 08/30/2021 19:39:23 - INFO - __main__ - Step 35656: {'lr': 0.00043887261411624433, 'samples': 6845952, 'steps': 35655, 'loss/train': 1.7236616611480713} 08/30/2021 19:39:23 - INFO - __main__ - Step 35657: {'lr': 0.00043886913730891087, 'samples': 6846144, 'steps': 35656, 'loss/train': 1.7457900047302246} 08/30/2021 19:39:24 - INFO - __main__ - Step 35658: {'lr': 0.00043886566041647593, 'samples': 6846336, 'steps': 35657, 'loss/train': 2.3147151470184326} 08/30/2021 19:39:24 - INFO - __main__ - Step 35659: {'lr': 0.000438862183438941, 'samples': 6846528, 'steps': 35658, 'loss/train': 1.4650671482086182} 08/30/2021 19:39:24 - INFO - __main__ - Step 35660: {'lr': 0.00043885870637630763, 'samples': 6846720, 'steps': 35659, 'loss/train': 1.3873176574707031} 08/30/2021 19:39:26 - INFO - __main__ - Step 35661: {'lr': 0.00043885522922857757, 'samples': 6846912, 'steps': 35660, 'loss/train': 1.3182965517044067} 08/30/2021 19:39:26 - INFO - __main__ - Step 35662: {'lr': 0.00043885175199575216, 'samples': 6847104, 'steps': 35661, 'loss/train': 1.821889877319336} 08/30/2021 19:39:27 - INFO - __main__ - Step 35663: {'lr': 0.00043884827467783303, 'samples': 6847296, 'steps': 35662, 'loss/train': 1.2539817094802856} 08/30/2021 19:39:27 - INFO - __main__ - Step 35664: {'lr': 0.00043884479727482193, 'samples': 6847488, 'steps': 35663, 'loss/train': 1.7631292343139648} 08/30/2021 19:39:27 - INFO - __main__ - Step 35665: {'lr': 0.00043884131978672014, 'samples': 6847680, 'steps': 35664, 'loss/train': 1.445492148399353} 08/30/2021 19:39:28 - INFO - __main__ - Step 35666: {'lr': 0.00043883784221352947, 'samples': 6847872, 'steps': 35665, 'loss/train': 1.5081000328063965} 08/30/2021 19:39:29 - INFO - __main__ - Step 35667: {'lr': 0.00043883436455525125, 'samples': 6848064, 'steps': 35666, 'loss/train': 1.2931530475616455} 08/30/2021 19:39:30 - INFO - __main__ - Step 35668: {'lr': 0.0004388308868118873, 'samples': 6848256, 'steps': 35667, 'loss/train': 1.7521008253097534} 08/30/2021 19:39:30 - INFO - __main__ - Step 35669: {'lr': 0.00043882740898343905, 'samples': 6848448, 'steps': 35668, 'loss/train': 1.2962530851364136} 08/30/2021 19:39:30 - INFO - __main__ - Step 35670: {'lr': 0.00043882393106990804, 'samples': 6848640, 'steps': 35669, 'loss/train': 1.1387592554092407} 08/30/2021 19:39:31 - INFO - __main__ - Step 35671: {'lr': 0.0004388204530712959, 'samples': 6848832, 'steps': 35670, 'loss/train': 1.1954197883605957} 08/30/2021 19:39:32 - INFO - __main__ - Step 35672: {'lr': 0.0004388169749876042, 'samples': 6849024, 'steps': 35671, 'loss/train': 1.3102842569351196} 08/30/2021 19:39:33 - INFO - __main__ - Step 35673: {'lr': 0.0004388134968188344, 'samples': 6849216, 'steps': 35672, 'loss/train': 1.5865390300750732} 08/30/2021 19:39:33 - INFO - __main__ - Step 35674: {'lr': 0.00043881001856498823, 'samples': 6849408, 'steps': 35673, 'loss/train': 0.9513254165649414} 08/30/2021 19:39:33 - INFO - __main__ - Step 35675: {'lr': 0.0004388065402260672, 'samples': 6849600, 'steps': 35674, 'loss/train': 1.3794844150543213} 08/30/2021 19:39:34 - INFO - __main__ - Step 35676: {'lr': 0.0004388030618020729, 'samples': 6849792, 'steps': 35675, 'loss/train': 1.8563107252120972} 08/30/2021 19:39:35 - INFO - __main__ - Step 35677: {'lr': 0.0004387995832930067, 'samples': 6849984, 'steps': 35676, 'loss/train': 1.1908576488494873} 08/30/2021 19:39:36 - INFO - __main__ - Step 35678: {'lr': 0.00043879610469887043, 'samples': 6850176, 'steps': 35677, 'loss/train': 0.9676467180252075} 08/30/2021 19:39:36 - INFO - __main__ - Step 35679: {'lr': 0.00043879262601966544, 'samples': 6850368, 'steps': 35678, 'loss/train': 1.0132702589035034} 08/30/2021 19:39:37 - INFO - __main__ - Step 35680: {'lr': 0.00043878914725539356, 'samples': 6850560, 'steps': 35679, 'loss/train': 1.7388083934783936} 08/30/2021 19:39:37 - INFO - __main__ - Step 35681: {'lr': 0.00043878566840605606, 'samples': 6850752, 'steps': 35680, 'loss/train': 1.4481080770492554} 08/30/2021 19:39:37 - INFO - __main__ - Step 35682: {'lr': 0.0004387821894716547, 'samples': 6850944, 'steps': 35681, 'loss/train': 1.6208693981170654} 08/30/2021 19:39:39 - INFO - __main__ - Step 35683: {'lr': 0.000438778710452191, 'samples': 6851136, 'steps': 35682, 'loss/train': 1.1175706386566162} 08/30/2021 19:39:40 - INFO - __main__ - Step 35684: {'lr': 0.00043877523134766664, 'samples': 6851328, 'steps': 35683, 'loss/train': 0.6959826946258545} 08/30/2021 19:39:40 - INFO - __main__ - Step 35685: {'lr': 0.0004387717521580829, 'samples': 6851520, 'steps': 35684, 'loss/train': 1.755468726158142} 08/30/2021 19:39:41 - INFO - __main__ - Step 35686: {'lr': 0.00043876827288344156, 'samples': 6851712, 'steps': 35685, 'loss/train': 1.4296605587005615} 08/30/2021 19:39:41 - INFO - __main__ - Step 35687: {'lr': 0.00043876479352374423, 'samples': 6851904, 'steps': 35686, 'loss/train': 0.0532398484647274} 08/30/2021 19:39:42 - INFO - __main__ - Step 35688: {'lr': 0.00043876131407899233, 'samples': 6852096, 'steps': 35687, 'loss/train': 1.791062593460083} 08/30/2021 19:39:43 - INFO - __main__ - Step 35689: {'lr': 0.00043875783454918753, 'samples': 6852288, 'steps': 35688, 'loss/train': 1.7844648361206055} 08/30/2021 19:39:43 - INFO - __main__ - Step 35690: {'lr': 0.00043875435493433135, 'samples': 6852480, 'steps': 35689, 'loss/train': 1.4128694534301758} 08/30/2021 19:39:44 - INFO - __main__ - Step 35691: {'lr': 0.00043875087523442537, 'samples': 6852672, 'steps': 35690, 'loss/train': 1.6357346773147583} 08/30/2021 19:39:44 - INFO - __main__ - Step 35692: {'lr': 0.0004387473954494712, 'samples': 6852864, 'steps': 35691, 'loss/train': 1.2960482835769653} 08/30/2021 19:39:45 - INFO - __main__ - Step 35693: {'lr': 0.00043874391557947027, 'samples': 6853056, 'steps': 35692, 'loss/train': 1.777909517288208} 08/30/2021 19:39:46 - INFO - __main__ - Step 35694: {'lr': 0.0004387404356244243, 'samples': 6853248, 'steps': 35693, 'loss/train': 1.472602128982544} 08/30/2021 19:39:46 - INFO - __main__ - Step 35695: {'lr': 0.0004387369555843348, 'samples': 6853440, 'steps': 35694, 'loss/train': 1.805136799812317} 08/30/2021 19:39:47 - INFO - __main__ - Step 35696: {'lr': 0.00043873347545920333, 'samples': 6853632, 'steps': 35695, 'loss/train': 1.1814404726028442} 08/30/2021 19:39:47 - INFO - __main__ - Step 35697: {'lr': 0.00043872999524903147, 'samples': 6853824, 'steps': 35696, 'loss/train': 1.2362682819366455} 08/30/2021 19:39:48 - INFO - __main__ - Step 35698: {'lr': 0.00043872651495382076, 'samples': 6854016, 'steps': 35697, 'loss/train': 1.357146978378296} 08/30/2021 19:39:49 - INFO - __main__ - Step 35699: {'lr': 0.00043872303457357287, 'samples': 6854208, 'steps': 35698, 'loss/train': 1.2132716178894043} 08/30/2021 19:39:49 - INFO - __main__ - Step 35700: {'lr': 0.0004387195541082892, 'samples': 6854400, 'steps': 35699, 'loss/train': 1.2962244749069214} 08/30/2021 19:39:50 - INFO - __main__ - Step 35701: {'lr': 0.0004387160735579715, 'samples': 6854592, 'steps': 35700, 'loss/train': 1.7019201517105103} 08/30/2021 19:39:50 - INFO - __main__ - Step 35702: {'lr': 0.0004387125929226212, 'samples': 6854784, 'steps': 35701, 'loss/train': 1.5078734159469604} 08/30/2021 19:39:51 - INFO - __main__ - Step 35703: {'lr': 0.00043870911220224, 'samples': 6854976, 'steps': 35702, 'loss/train': 0.39509594440460205} 08/30/2021 19:39:52 - INFO - __main__ - Step 35704: {'lr': 0.0004387056313968293, 'samples': 6855168, 'steps': 35703, 'loss/train': 1.2451130151748657} 08/30/2021 19:39:52 - INFO - __main__ - Step 35705: {'lr': 0.00043870215050639073, 'samples': 6855360, 'steps': 35704, 'loss/train': 1.6831550598144531} 08/30/2021 19:39:53 - INFO - __main__ - Step 35706: {'lr': 0.00043869866953092593, 'samples': 6855552, 'steps': 35705, 'loss/train': 1.6268436908721924} 08/30/2021 19:39:53 - INFO - __main__ - Step 35707: {'lr': 0.00043869518847043643, 'samples': 6855744, 'steps': 35706, 'loss/train': 1.4169487953186035} 08/30/2021 19:39:55 - INFO - __main__ - Step 35708: {'lr': 0.0004386917073249237, 'samples': 6855936, 'steps': 35707, 'loss/train': 0.739641547203064} 08/30/2021 19:39:56 - INFO - __main__ - Step 35709: {'lr': 0.00043868822609438953, 'samples': 6856128, 'steps': 35708, 'loss/train': 0.949308454990387} 08/30/2021 19:39:56 - INFO - __main__ - Step 35710: {'lr': 0.00043868474477883523, 'samples': 6856320, 'steps': 35709, 'loss/train': 0.5304680466651917} 08/30/2021 19:39:56 - INFO - __main__ - Step 35711: {'lr': 0.0004386812633782626, 'samples': 6856512, 'steps': 35710, 'loss/train': 0.6883789300918579} 08/30/2021 19:39:57 - INFO - __main__ - Step 35712: {'lr': 0.00043867778189267306, 'samples': 6856704, 'steps': 35711, 'loss/train': 3.0548501014709473} 08/30/2021 19:39:57 - INFO - __main__ - Step 35713: {'lr': 0.0004386743003220682, 'samples': 6856896, 'steps': 35712, 'loss/train': 0.6495181322097778} 08/30/2021 19:39:58 - INFO - __main__ - Step 35714: {'lr': 0.0004386708186664496, 'samples': 6857088, 'steps': 35713, 'loss/train': 1.6035770177841187} 08/30/2021 19:39:59 - INFO - __main__ - Step 35715: {'lr': 0.00043866733692581896, 'samples': 6857280, 'steps': 35714, 'loss/train': 1.4421180486679077} 08/30/2021 19:39:59 - INFO - __main__ - Step 35716: {'lr': 0.0004386638551001777, 'samples': 6857472, 'steps': 35715, 'loss/train': 1.022769570350647} 08/30/2021 19:39:59 - INFO - __main__ - Step 35717: {'lr': 0.00043866037318952735, 'samples': 6857664, 'steps': 35716, 'loss/train': 1.398125171661377} 08/30/2021 19:40:00 - INFO - __main__ - Step 35718: {'lr': 0.0004386568911938695, 'samples': 6857856, 'steps': 35717, 'loss/train': 1.2186522483825684} 08/30/2021 19:40:01 - INFO - __main__ - Step 35719: {'lr': 0.0004386534091132059, 'samples': 6858048, 'steps': 35718, 'loss/train': 1.1770780086517334} 08/30/2021 19:40:02 - INFO - __main__ - Step 35720: {'lr': 0.0004386499269475379, 'samples': 6858240, 'steps': 35719, 'loss/train': 1.588206171989441} 08/30/2021 19:40:02 - INFO - __main__ - Step 35721: {'lr': 0.00043864644469686717, 'samples': 6858432, 'steps': 35720, 'loss/train': 1.0388907194137573} 08/30/2021 19:40:02 - INFO - __main__ - Step 35722: {'lr': 0.0004386429623611953, 'samples': 6858624, 'steps': 35721, 'loss/train': 0.9350224733352661} 08/30/2021 19:40:03 - INFO - __main__ - Step 35723: {'lr': 0.0004386394799405238, 'samples': 6858816, 'steps': 35722, 'loss/train': 1.7079821825027466} 08/30/2021 19:40:05 - INFO - __main__ - Step 35724: {'lr': 0.00043863599743485416, 'samples': 6859008, 'steps': 35723, 'loss/train': 2.0020370483398438} 08/30/2021 19:40:05 - INFO - __main__ - Step 35725: {'lr': 0.0004386325148441882, 'samples': 6859200, 'steps': 35724, 'loss/train': 0.5875958800315857} 08/30/2021 19:40:06 - INFO - __main__ - Step 35726: {'lr': 0.00043862903216852723, 'samples': 6859392, 'steps': 35725, 'loss/train': 1.4427247047424316} 08/30/2021 19:40:06 - INFO - __main__ - Step 35727: {'lr': 0.00043862554940787303, 'samples': 6859584, 'steps': 35726, 'loss/train': 1.0599899291992188} 08/30/2021 19:40:07 - INFO - __main__ - Step 35728: {'lr': 0.000438622066562227, 'samples': 6859776, 'steps': 35727, 'loss/train': 0.7915924191474915} 08/30/2021 19:40:07 - INFO - __main__ - Step 35729: {'lr': 0.0004386185836315908, 'samples': 6859968, 'steps': 35728, 'loss/train': 1.872920036315918} 08/30/2021 19:40:08 - INFO - __main__ - Step 35730: {'lr': 0.0004386151006159659, 'samples': 6860160, 'steps': 35729, 'loss/train': 1.6561102867126465} 08/30/2021 19:40:09 - INFO - __main__ - Step 35731: {'lr': 0.00043861161751535406, 'samples': 6860352, 'steps': 35730, 'loss/train': 1.4359028339385986} 08/30/2021 19:40:09 - INFO - __main__ - Step 35732: {'lr': 0.0004386081343297567, 'samples': 6860544, 'steps': 35731, 'loss/train': 0.752839982509613} 08/30/2021 19:40:10 - INFO - __main__ - Step 35733: {'lr': 0.0004386046510591754, 'samples': 6860736, 'steps': 35732, 'loss/train': 1.461084246635437} 08/30/2021 19:40:10 - INFO - __main__ - Step 35734: {'lr': 0.0004386011677036118, 'samples': 6860928, 'steps': 35733, 'loss/train': 1.8140510320663452} 08/30/2021 19:40:12 - INFO - __main__ - Step 35735: {'lr': 0.00043859768426306737, 'samples': 6861120, 'steps': 35734, 'loss/train': 1.5535871982574463} 08/30/2021 19:40:13 - INFO - __main__ - Step 35736: {'lr': 0.00043859420073754377, 'samples': 6861312, 'steps': 35735, 'loss/train': 1.768283724784851} 08/30/2021 19:40:13 - INFO - __main__ - Step 35737: {'lr': 0.0004385907171270425, 'samples': 6861504, 'steps': 35736, 'loss/train': 1.4834998846054077} 08/30/2021 19:40:13 - INFO - __main__ - Step 35738: {'lr': 0.00043858723343156514, 'samples': 6861696, 'steps': 35737, 'loss/train': 0.43895164132118225} 08/30/2021 19:40:14 - INFO - __main__ - Step 35739: {'lr': 0.00043858374965111336, 'samples': 6861888, 'steps': 35738, 'loss/train': 1.659919023513794} 08/30/2021 19:40:15 - INFO - __main__ - Step 35740: {'lr': 0.00043858026578568864, 'samples': 6862080, 'steps': 35739, 'loss/train': 1.2154282331466675} 08/30/2021 19:40:16 - INFO - __main__ - Step 35741: {'lr': 0.00043857678183529256, 'samples': 6862272, 'steps': 35740, 'loss/train': 0.04095795005559921} 08/30/2021 19:40:16 - INFO - __main__ - Step 35742: {'lr': 0.0004385732977999266, 'samples': 6862464, 'steps': 35741, 'loss/train': 0.859963595867157} 08/30/2021 19:40:16 - INFO - __main__ - Step 35743: {'lr': 0.0004385698136795926, 'samples': 6862656, 'steps': 35742, 'loss/train': 1.576748013496399} 08/30/2021 19:40:17 - INFO - __main__ - Step 35744: {'lr': 0.00043856632947429175, 'samples': 6862848, 'steps': 35743, 'loss/train': 1.3742958307266235} 08/30/2021 19:40:18 - INFO - __main__ - Step 35745: {'lr': 0.00043856284518402594, 'samples': 6863040, 'steps': 35744, 'loss/train': 1.1338467597961426} 08/30/2021 19:40:19 - INFO - __main__ - Step 35746: {'lr': 0.00043855936080879667, 'samples': 6863232, 'steps': 35745, 'loss/train': 1.1429330110549927} 08/30/2021 19:40:19 - INFO - __main__ - Step 35747: {'lr': 0.0004385558763486053, 'samples': 6863424, 'steps': 35746, 'loss/train': 0.5309433937072754} 08/30/2021 19:40:19 - INFO - __main__ - Step 35748: {'lr': 0.00043855239180345376, 'samples': 6863616, 'steps': 35747, 'loss/train': 1.1584179401397705} 08/30/2021 19:40:20 - INFO - __main__ - Step 35749: {'lr': 0.00043854890717334326, 'samples': 6863808, 'steps': 35748, 'loss/train': 1.578368067741394} 08/30/2021 19:40:20 - INFO - __main__ - Step 35750: {'lr': 0.00043854542245827554, 'samples': 6864000, 'steps': 35749, 'loss/train': 2.151776075363159} 08/30/2021 19:40:22 - INFO - __main__ - Step 35751: {'lr': 0.00043854193765825223, 'samples': 6864192, 'steps': 35750, 'loss/train': 1.8846768140792847} 08/30/2021 19:40:22 - INFO - __main__ - Step 35752: {'lr': 0.00043853845277327485, 'samples': 6864384, 'steps': 35751, 'loss/train': 0.6006564497947693} 08/30/2021 19:40:22 - INFO - __main__ - Step 35753: {'lr': 0.0004385349678033449, 'samples': 6864576, 'steps': 35752, 'loss/train': 1.1803851127624512} 08/30/2021 19:40:23 - INFO - __main__ - Step 35754: {'lr': 0.000438531482748464, 'samples': 6864768, 'steps': 35753, 'loss/train': 1.5470081567764282} 08/30/2021 19:40:24 - INFO - __main__ - Step 35755: {'lr': 0.00043852799760863375, 'samples': 6864960, 'steps': 35754, 'loss/train': 1.0977510213851929} 08/30/2021 19:40:25 - INFO - __main__ - Step 35756: {'lr': 0.0004385245123838557, 'samples': 6865152, 'steps': 35755, 'loss/train': 0.8566994071006775} 08/30/2021 19:40:25 - INFO - __main__ - Step 35757: {'lr': 0.00043852102707413144, 'samples': 6865344, 'steps': 35756, 'loss/train': 1.259803295135498} 08/30/2021 19:40:25 - INFO - __main__ - Step 35758: {'lr': 0.00043851754167946244, 'samples': 6865536, 'steps': 35757, 'loss/train': 1.8018505573272705} 08/30/2021 19:40:26 - INFO - __main__ - Step 35759: {'lr': 0.00043851405619985037, 'samples': 6865728, 'steps': 35758, 'loss/train': 0.9264659285545349} 08/30/2021 19:40:26 - INFO - __main__ - Step 35760: {'lr': 0.00043851057063529675, 'samples': 6865920, 'steps': 35759, 'loss/train': 0.7205207347869873} 08/30/2021 19:40:28 - INFO - __main__ - Step 35761: {'lr': 0.00043850708498580326, 'samples': 6866112, 'steps': 35760, 'loss/train': 0.5752424001693726} 08/30/2021 19:40:29 - INFO - __main__ - Step 35762: {'lr': 0.00043850359925137126, 'samples': 6866304, 'steps': 35761, 'loss/train': 1.7855188846588135} 08/30/2021 19:40:29 - INFO - __main__ - Step 35763: {'lr': 0.0004385001134320026, 'samples': 6866496, 'steps': 35762, 'loss/train': 1.1552997827529907} 08/30/2021 19:40:30 - INFO - __main__ - Step 35764: {'lr': 0.0004384966275276986, 'samples': 6866688, 'steps': 35763, 'loss/train': 1.2471599578857422} 08/30/2021 19:40:30 - INFO - __main__ - Step 35765: {'lr': 0.00043849314153846094, 'samples': 6866880, 'steps': 35764, 'loss/train': 1.1940642595291138} 08/30/2021 19:40:30 - INFO - __main__ - Step 35766: {'lr': 0.0004384896554642912, 'samples': 6867072, 'steps': 35765, 'loss/train': 1.9924455881118774} 08/30/2021 19:40:31 - INFO - __main__ - Step 35767: {'lr': 0.00043848616930519094, 'samples': 6867264, 'steps': 35766, 'loss/train': 1.452562928199768} 08/30/2021 19:40:32 - INFO - __main__ - Step 35768: {'lr': 0.0004384826830611617, 'samples': 6867456, 'steps': 35767, 'loss/train': 1.4745227098464966} 08/30/2021 19:40:33 - INFO - __main__ - Step 35769: {'lr': 0.00043847919673220504, 'samples': 6867648, 'steps': 35768, 'loss/train': 2.126126289367676} 08/30/2021 19:40:33 - INFO - __main__ - Step 35770: {'lr': 0.00043847571031832257, 'samples': 6867840, 'steps': 35769, 'loss/train': 0.12559567391872406} 08/30/2021 19:40:33 - INFO - __main__ - Step 35771: {'lr': 0.0004384722238195159, 'samples': 6868032, 'steps': 35770, 'loss/train': 0.0725589394569397} 08/30/2021 19:40:34 - INFO - __main__ - Step 35772: {'lr': 0.0004384687372357865, 'samples': 6868224, 'steps': 35771, 'loss/train': 1.2416489124298096} 08/30/2021 19:40:35 - INFO - __main__ - Step 35773: {'lr': 0.000438465250567136, 'samples': 6868416, 'steps': 35772, 'loss/train': 1.4894640445709229} 08/30/2021 19:40:36 - INFO - __main__ - Step 35774: {'lr': 0.00043846176381356607, 'samples': 6868608, 'steps': 35773, 'loss/train': 0.7272209525108337} 08/30/2021 19:40:36 - INFO - __main__ - Step 35775: {'lr': 0.000438458276975078, 'samples': 6868800, 'steps': 35774, 'loss/train': 1.644163727760315} 08/30/2021 19:40:37 - INFO - __main__ - Step 35776: {'lr': 0.0004384547900516737, 'samples': 6868992, 'steps': 35775, 'loss/train': 1.6450856924057007} 08/30/2021 19:40:37 - INFO - __main__ - Step 35777: {'lr': 0.00043845130304335454, 'samples': 6869184, 'steps': 35776, 'loss/train': 1.7167104482650757} 08/30/2021 19:40:39 - INFO - __main__ - Step 35778: {'lr': 0.00043844781595012204, 'samples': 6869376, 'steps': 35777, 'loss/train': 1.3521348237991333} 08/30/2021 19:40:39 - INFO - __main__ - Step 35779: {'lr': 0.0004384443287719779, 'samples': 6869568, 'steps': 35778, 'loss/train': 1.14707612991333} 08/30/2021 19:40:39 - INFO - __main__ - Step 35780: {'lr': 0.0004384408415089237, 'samples': 6869760, 'steps': 35779, 'loss/train': 1.990094542503357} 08/30/2021 19:40:40 - INFO - __main__ - Step 35781: {'lr': 0.000438437354160961, 'samples': 6869952, 'steps': 35780, 'loss/train': 1.4677101373672485} 08/30/2021 19:40:40 - INFO - __main__ - Step 35782: {'lr': 0.00043843386672809127, 'samples': 6870144, 'steps': 35781, 'loss/train': 1.3196239471435547} 08/30/2021 19:40:42 - INFO - __main__ - Step 35783: {'lr': 0.00043843037921031616, 'samples': 6870336, 'steps': 35782, 'loss/train': 1.3968104124069214} 08/30/2021 19:40:42 - INFO - __main__ - Step 35784: {'lr': 0.00043842689160763723, 'samples': 6870528, 'steps': 35783, 'loss/train': 0.9303664565086365} 08/30/2021 19:40:43 - INFO - __main__ - Step 35785: {'lr': 0.00043842340392005605, 'samples': 6870720, 'steps': 35784, 'loss/train': 1.709263801574707} 08/30/2021 19:40:43 - INFO - __main__ - Step 35786: {'lr': 0.00043841991614757415, 'samples': 6870912, 'steps': 35785, 'loss/train': 1.9071567058563232} 08/30/2021 19:40:43 - INFO - __main__ - Step 35787: {'lr': 0.00043841642829019325, 'samples': 6871104, 'steps': 35786, 'loss/train': 1.302585244178772} 08/30/2021 19:40:45 - INFO - __main__ - Step 35788: {'lr': 0.00043841294034791466, 'samples': 6871296, 'steps': 35787, 'loss/train': 0.9638983011245728} 08/30/2021 19:40:46 - INFO - __main__ - Step 35789: {'lr': 0.0004384094523207403, 'samples': 6871488, 'steps': 35788, 'loss/train': 1.3495556116104126} 08/30/2021 19:40:46 - INFO - __main__ - Step 35790: {'lr': 0.0004384059642086714, 'samples': 6871680, 'steps': 35789, 'loss/train': 1.5559329986572266} 08/30/2021 19:40:47 - INFO - __main__ - Step 35791: {'lr': 0.00043840247601170966, 'samples': 6871872, 'steps': 35790, 'loss/train': 1.0083070993423462} 08/30/2021 19:40:47 - INFO - __main__ - Step 35792: {'lr': 0.0004383989877298568, 'samples': 6872064, 'steps': 35791, 'loss/train': 1.7565701007843018} 08/30/2021 19:40:47 - INFO - __main__ - Step 35793: {'lr': 0.0004383954993631142, 'samples': 6872256, 'steps': 35792, 'loss/train': 1.2921377420425415} 08/30/2021 19:40:49 - INFO - __main__ - Step 35794: {'lr': 0.0004383920109114835, 'samples': 6872448, 'steps': 35793, 'loss/train': 0.9689278602600098} 08/30/2021 19:40:49 - INFO - __main__ - Step 35795: {'lr': 0.00043838852237496626, 'samples': 6872640, 'steps': 35794, 'loss/train': 1.3755950927734375} 08/30/2021 19:40:50 - INFO - __main__ - Step 35796: {'lr': 0.000438385033753564, 'samples': 6872832, 'steps': 35795, 'loss/train': 1.233426570892334} 08/30/2021 19:40:50 - INFO - __main__ - Step 35797: {'lr': 0.00043838154504727847, 'samples': 6873024, 'steps': 35796, 'loss/train': 1.0053900480270386} 08/30/2021 19:40:50 - INFO - __main__ - Step 35798: {'lr': 0.00043837805625611105, 'samples': 6873216, 'steps': 35797, 'loss/train': 1.2939139604568481} 08/30/2021 19:40:52 - INFO - __main__ - Step 35799: {'lr': 0.0004383745673800634, 'samples': 6873408, 'steps': 35798, 'loss/train': 1.6685645580291748} 08/30/2021 19:40:53 - INFO - __main__ - Step 35800: {'lr': 0.000438371078419137, 'samples': 6873600, 'steps': 35799, 'loss/train': 1.132985234260559} 08/30/2021 19:40:53 - INFO - __main__ - Step 35801: {'lr': 0.00043836758937333366, 'samples': 6873792, 'steps': 35800, 'loss/train': 2.439655065536499} 08/30/2021 19:40:53 - INFO - __main__ - Step 35802: {'lr': 0.0004383641002426547, 'samples': 6873984, 'steps': 35801, 'loss/train': 1.5419939756393433} 08/30/2021 19:40:54 - INFO - __main__ - Step 35803: {'lr': 0.0004383606110271018, 'samples': 6874176, 'steps': 35802, 'loss/train': 0.8653266429901123} 08/30/2021 19:40:55 - INFO - __main__ - Step 35804: {'lr': 0.00043835712172667643, 'samples': 6874368, 'steps': 35803, 'loss/train': 1.158326506614685} 08/30/2021 19:40:55 - INFO - __main__ - Step 35805: {'lr': 0.00043835363234138037, 'samples': 6874560, 'steps': 35804, 'loss/train': 1.425804853439331} 08/30/2021 19:40:56 - INFO - __main__ - Step 35806: {'lr': 0.00043835014287121497, 'samples': 6874752, 'steps': 35805, 'loss/train': 1.483182668685913} 08/30/2021 19:40:56 - INFO - __main__ - Step 35807: {'lr': 0.00043834665331618196, 'samples': 6874944, 'steps': 35806, 'loss/train': 1.5690828561782837} 08/30/2021 19:40:56 - INFO - __main__ - Step 35808: {'lr': 0.00043834316367628287, 'samples': 6875136, 'steps': 35807, 'loss/train': 1.5251847505569458} 08/30/2021 19:40:57 - INFO - __main__ - Step 35809: {'lr': 0.0004383396739515192, 'samples': 6875328, 'steps': 35808, 'loss/train': 1.4956177473068237} 08/30/2021 19:40:58 - INFO - __main__ - Step 35810: {'lr': 0.00043833618414189265, 'samples': 6875520, 'steps': 35809, 'loss/train': 1.3618067502975464} 08/30/2021 19:40:59 - INFO - __main__ - Step 35811: {'lr': 0.0004383326942474046, 'samples': 6875712, 'steps': 35810, 'loss/train': 1.365071415901184} 08/30/2021 19:40:59 - INFO - __main__ - Step 35812: {'lr': 0.0004383292042680569, 'samples': 6875904, 'steps': 35811, 'loss/train': 1.2887581586837769} 08/30/2021 19:41:00 - INFO - __main__ - Step 35813: {'lr': 0.0004383257142038509, 'samples': 6876096, 'steps': 35812, 'loss/train': 0.8633568286895752} 08/30/2021 19:41:00 - INFO - __main__ - Step 35814: {'lr': 0.0004383222240547882, 'samples': 6876288, 'steps': 35813, 'loss/train': 1.455997109413147} 08/30/2021 19:41:02 - INFO - __main__ - Step 35815: {'lr': 0.00043831873382087043, 'samples': 6876480, 'steps': 35814, 'loss/train': 0.11450637131929398} 08/30/2021 19:41:02 - INFO - __main__ - Step 35816: {'lr': 0.0004383152435020992, 'samples': 6876672, 'steps': 35815, 'loss/train': 0.9193439483642578} 08/30/2021 19:41:03 - INFO - __main__ - Step 35817: {'lr': 0.0004383117530984759, 'samples': 6876864, 'steps': 35816, 'loss/train': 0.11300406605005264} 08/30/2021 19:41:03 - INFO - __main__ - Step 35818: {'lr': 0.0004383082626100024, 'samples': 6877056, 'steps': 35817, 'loss/train': 1.0652726888656616} 08/30/2021 19:41:03 - INFO - __main__ - Step 35819: {'lr': 0.00043830477203668, 'samples': 6877248, 'steps': 35818, 'loss/train': 1.4916833639144897} 08/30/2021 19:41:05 - INFO - __main__ - Step 35820: {'lr': 0.0004383012813785104, 'samples': 6877440, 'steps': 35819, 'loss/train': 0.8225932121276855} 08/30/2021 19:41:05 - INFO - __main__ - Step 35821: {'lr': 0.00043829779063549515, 'samples': 6877632, 'steps': 35820, 'loss/train': 1.8141981363296509} 08/30/2021 19:41:06 - INFO - __main__ - Step 35822: {'lr': 0.0004382942998076358, 'samples': 6877824, 'steps': 35821, 'loss/train': 0.8098313808441162} 08/30/2021 19:41:06 - INFO - __main__ - Step 35823: {'lr': 0.000438290808894934, 'samples': 6878016, 'steps': 35822, 'loss/train': 0.7846266031265259} 08/30/2021 19:41:07 - INFO - __main__ - Step 35824: {'lr': 0.0004382873178973912, 'samples': 6878208, 'steps': 35823, 'loss/train': 1.348767876625061} 08/30/2021 19:41:08 - INFO - __main__ - Step 35825: {'lr': 0.00043828382681500907, 'samples': 6878400, 'steps': 35824, 'loss/train': 1.2977933883666992} 08/30/2021 19:41:08 - INFO - __main__ - Step 35826: {'lr': 0.0004382803356477891, 'samples': 6878592, 'steps': 35825, 'loss/train': 1.1374726295471191} 08/30/2021 19:41:09 - INFO - __main__ - Step 35827: {'lr': 0.000438276844395733, 'samples': 6878784, 'steps': 35826, 'loss/train': 1.7101885080337524} 08/30/2021 19:41:09 - INFO - __main__ - Step 35828: {'lr': 0.0004382733530588422, 'samples': 6878976, 'steps': 35827, 'loss/train': 1.4890118837356567} 08/30/2021 19:41:09 - INFO - __main__ - Step 35829: {'lr': 0.00043826986163711835, 'samples': 6879168, 'steps': 35828, 'loss/train': 1.2416892051696777} 08/30/2021 19:41:10 - INFO - __main__ - Step 35830: {'lr': 0.000438266370130563, 'samples': 6879360, 'steps': 35829, 'loss/train': 1.267130970954895} 08/30/2021 19:41:11 - INFO - __main__ - Step 35831: {'lr': 0.0004382628785391778, 'samples': 6879552, 'steps': 35830, 'loss/train': 2.0122570991516113} 08/30/2021 19:41:12 - INFO - __main__ - Step 35832: {'lr': 0.00043825938686296417, 'samples': 6879744, 'steps': 35831, 'loss/train': 1.7289721965789795} 08/30/2021 19:41:12 - INFO - __main__ - Step 35833: {'lr': 0.00043825589510192376, 'samples': 6879936, 'steps': 35832, 'loss/train': 1.301513671875} 08/30/2021 19:41:12 - INFO - __main__ - Step 35834: {'lr': 0.0004382524032560582, 'samples': 6880128, 'steps': 35833, 'loss/train': 1.5454095602035522} 08/30/2021 19:41:13 - INFO - __main__ - Step 35835: {'lr': 0.000438248911325369, 'samples': 6880320, 'steps': 35834, 'loss/train': 1.5459630489349365} 08/30/2021 19:41:14 - INFO - __main__ - Step 35836: {'lr': 0.00043824541930985775, 'samples': 6880512, 'steps': 35835, 'loss/train': 1.6328880786895752} 08/30/2021 19:41:15 - INFO - __main__ - Step 35837: {'lr': 0.0004382419272095259, 'samples': 6880704, 'steps': 35836, 'loss/train': 1.4368534088134766} 08/30/2021 19:41:15 - INFO - __main__ - Step 35838: {'lr': 0.00043823843502437533, 'samples': 6880896, 'steps': 35837, 'loss/train': 0.6696494221687317} 08/30/2021 19:41:15 - INFO - __main__ - Step 35839: {'lr': 0.00043823494275440733, 'samples': 6881088, 'steps': 35838, 'loss/train': 1.1786456108093262} 08/30/2021 19:41:16 - INFO - __main__ - Step 35840: {'lr': 0.0004382314503996236, 'samples': 6881280, 'steps': 35839, 'loss/train': 0.8219661116600037} 08/30/2021 19:41:18 - INFO - __main__ - Step 35841: {'lr': 0.0004382279579600256, 'samples': 6881472, 'steps': 35840, 'loss/train': 1.1060184240341187} 08/30/2021 19:41:18 - INFO - __main__ - Step 35842: {'lr': 0.0004382244654356151, 'samples': 6881664, 'steps': 35841, 'loss/train': 0.7607479095458984} 08/30/2021 19:41:19 - INFO - __main__ - Step 35843: {'lr': 0.0004382209728263935, 'samples': 6881856, 'steps': 35842, 'loss/train': 1.6023942232131958} 08/30/2021 19:41:19 - INFO - __main__ - Step 35844: {'lr': 0.0004382174801323624, 'samples': 6882048, 'steps': 35843, 'loss/train': 0.7133591175079346} 08/30/2021 19:41:19 - INFO - __main__ - Step 35845: {'lr': 0.00043821398735352344, 'samples': 6882240, 'steps': 35844, 'loss/train': 1.059515118598938} 08/30/2021 19:41:20 - INFO - __main__ - Step 35846: {'lr': 0.0004382104944898782, 'samples': 6882432, 'steps': 35845, 'loss/train': 1.2639186382293701} 08/30/2021 19:41:21 - INFO - __main__ - Step 35847: {'lr': 0.00043820700154142825, 'samples': 6882624, 'steps': 35846, 'loss/train': 1.8837535381317139} 08/30/2021 19:41:22 - INFO - __main__ - Step 35848: {'lr': 0.00043820350850817504, 'samples': 6882816, 'steps': 35847, 'loss/train': 1.5463966131210327} 08/30/2021 19:41:22 - INFO - __main__ - Step 35849: {'lr': 0.00043820001539012025, 'samples': 6883008, 'steps': 35848, 'loss/train': 1.0958948135375977} 08/30/2021 19:41:23 - INFO - __main__ - Step 35850: {'lr': 0.00043819652218726545, 'samples': 6883200, 'steps': 35849, 'loss/train': 1.5311769247055054} 08/30/2021 19:41:23 - INFO - __main__ - Step 35851: {'lr': 0.0004381930288996122, 'samples': 6883392, 'steps': 35850, 'loss/train': 1.0675137042999268} 08/30/2021 19:41:25 - INFO - __main__ - Step 35852: {'lr': 0.0004381895355271621, 'samples': 6883584, 'steps': 35851, 'loss/train': 1.3081263303756714} 08/30/2021 19:41:25 - INFO - __main__ - Step 35853: {'lr': 0.00043818604206991664, 'samples': 6883776, 'steps': 35852, 'loss/train': 1.055031418800354} 08/30/2021 19:41:25 - INFO - __main__ - Step 35854: {'lr': 0.0004381825485278775, 'samples': 6883968, 'steps': 35853, 'loss/train': 1.10634183883667} 08/30/2021 19:41:26 - INFO - __main__ - Step 35855: {'lr': 0.00043817905490104613, 'samples': 6884160, 'steps': 35854, 'loss/train': 1.2523554563522339} 08/30/2021 19:41:26 - INFO - __main__ - Step 35856: {'lr': 0.00043817556118942426, 'samples': 6884352, 'steps': 35855, 'loss/train': 1.5465097427368164} 08/30/2021 19:41:28 - INFO - __main__ - Step 35857: {'lr': 0.0004381720673930134, 'samples': 6884544, 'steps': 35856, 'loss/train': 1.6932920217514038} 08/30/2021 19:41:29 - INFO - __main__ - Step 35858: {'lr': 0.00043816857351181503, 'samples': 6884736, 'steps': 35857, 'loss/train': 1.629940390586853} 08/30/2021 19:41:29 - INFO - __main__ - Step 35859: {'lr': 0.0004381650795458309, 'samples': 6884928, 'steps': 35858, 'loss/train': 1.8170835971832275} 08/30/2021 19:41:29 - INFO - __main__ - Step 35860: {'lr': 0.0004381615854950625, 'samples': 6885120, 'steps': 35859, 'loss/train': 1.8068844079971313} 08/30/2021 19:41:30 - INFO - __main__ - Step 35861: {'lr': 0.0004381580913595113, 'samples': 6885312, 'steps': 35860, 'loss/train': 3.2505946159362793} 08/30/2021 19:41:30 - INFO - __main__ - Step 35862: {'lr': 0.000438154597139179, 'samples': 6885504, 'steps': 35861, 'loss/train': 1.0914829969406128} 08/30/2021 19:41:31 - INFO - __main__ - Step 35863: {'lr': 0.0004381511028340671, 'samples': 6885696, 'steps': 35862, 'loss/train': 1.1033549308776855} 08/30/2021 19:41:32 - INFO - __main__ - Step 35864: {'lr': 0.0004381476084441773, 'samples': 6885888, 'steps': 35863, 'loss/train': 0.7790926694869995} 08/30/2021 19:41:32 - INFO - __main__ - Step 35865: {'lr': 0.00043814411396951103, 'samples': 6886080, 'steps': 35864, 'loss/train': 1.744763970375061} 08/30/2021 19:41:33 - INFO - __main__ - Step 35866: {'lr': 0.00043814061941007, 'samples': 6886272, 'steps': 35865, 'loss/train': 1.042218565940857} 08/30/2021 19:41:33 - INFO - __main__ - Step 35867: {'lr': 0.00043813712476585564, 'samples': 6886464, 'steps': 35866, 'loss/train': 1.3351562023162842} 08/30/2021 19:41:33 - INFO - __main__ - Step 35868: {'lr': 0.00043813363003686963, 'samples': 6886656, 'steps': 35867, 'loss/train': 1.7624542713165283} 08/30/2021 19:41:35 - INFO - __main__ - Step 35869: {'lr': 0.00043813013522311353, 'samples': 6886848, 'steps': 35868, 'loss/train': 1.4124177694320679} 08/30/2021 19:41:36 - INFO - __main__ - Step 35870: {'lr': 0.0004381266403245888, 'samples': 6887040, 'steps': 35869, 'loss/train': 2.866715669631958} 08/30/2021 19:41:36 - INFO - __main__ - Step 35871: {'lr': 0.00043812314534129716, 'samples': 6887232, 'steps': 35870, 'loss/train': 1.3953862190246582} 08/30/2021 19:41:36 - INFO - __main__ - Step 35872: {'lr': 0.0004381196502732402, 'samples': 6887424, 'steps': 35871, 'loss/train': 1.0986944437026978} 08/30/2021 19:41:37 - INFO - __main__ - Step 35873: {'lr': 0.00043811615512041934, 'samples': 6887616, 'steps': 35872, 'loss/train': 1.6316261291503906} 08/30/2021 19:41:37 - INFO - __main__ - Step 35874: {'lr': 0.00043811265988283625, 'samples': 6887808, 'steps': 35873, 'loss/train': 1.1859568357467651} 08/30/2021 19:41:39 - INFO - __main__ - Step 35875: {'lr': 0.00043810916456049257, 'samples': 6888000, 'steps': 35874, 'loss/train': 1.3458808660507202} 08/30/2021 19:41:39 - INFO - __main__ - Step 35876: {'lr': 0.00043810566915338965, 'samples': 6888192, 'steps': 35875, 'loss/train': 0.6165096759796143} 08/30/2021 19:41:40 - INFO - __main__ - Step 35877: {'lr': 0.0004381021736615294, 'samples': 6888384, 'steps': 35876, 'loss/train': 0.7613841891288757} 08/30/2021 19:41:40 - INFO - __main__ - Step 35878: {'lr': 0.0004380986780849131, 'samples': 6888576, 'steps': 35877, 'loss/train': 1.8748672008514404} 08/30/2021 19:41:40 - INFO - __main__ - Step 35879: {'lr': 0.0004380951824235425, 'samples': 6888768, 'steps': 35878, 'loss/train': 1.521654725074768} 08/30/2021 19:41:42 - INFO - __main__ - Step 35880: {'lr': 0.00043809168667741907, 'samples': 6888960, 'steps': 35879, 'loss/train': 1.4347739219665527} 08/30/2021 19:41:42 - INFO - __main__ - Step 35881: {'lr': 0.0004380881908465445, 'samples': 6889152, 'steps': 35880, 'loss/train': 1.4354737997055054} 08/30/2021 19:41:43 - INFO - __main__ - Step 35882: {'lr': 0.0004380846949309202, 'samples': 6889344, 'steps': 35881, 'loss/train': 1.3781572580337524} 08/30/2021 19:41:43 - INFO - __main__ - Step 35883: {'lr': 0.00043808119893054787, 'samples': 6889536, 'steps': 35882, 'loss/train': 1.5532004833221436} 08/30/2021 19:41:43 - INFO - __main__ - Step 35884: {'lr': 0.0004380777028454291, 'samples': 6889728, 'steps': 35883, 'loss/train': 0.8596472144126892} 08/30/2021 19:41:45 - INFO - __main__ - Step 35885: {'lr': 0.0004380742066755654, 'samples': 6889920, 'steps': 35884, 'loss/train': 1.613647699356079} 08/30/2021 19:41:46 - INFO - __main__ - Step 35886: {'lr': 0.0004380707104209583, 'samples': 6890112, 'steps': 35885, 'loss/train': 0.04353176802396774} 08/30/2021 19:41:46 - INFO - __main__ - Step 35887: {'lr': 0.0004380672140816095, 'samples': 6890304, 'steps': 35886, 'loss/train': 0.8171952962875366} 08/30/2021 19:41:46 - INFO - __main__ - Step 35888: {'lr': 0.0004380637176575205, 'samples': 6890496, 'steps': 35887, 'loss/train': 2.121934652328491} 08/30/2021 19:41:47 - INFO - __main__ - Step 35889: {'lr': 0.00043806022114869294, 'samples': 6890688, 'steps': 35888, 'loss/train': 1.5538878440856934} 08/30/2021 19:41:47 - INFO - __main__ - Step 35890: {'lr': 0.0004380567245551282, 'samples': 6890880, 'steps': 35889, 'loss/train': 1.1371572017669678} 08/30/2021 19:41:49 - INFO - __main__ - Step 35891: {'lr': 0.0004380532278768282, 'samples': 6891072, 'steps': 35890, 'loss/train': 1.6110029220581055} 08/30/2021 19:41:49 - INFO - __main__ - Step 35892: {'lr': 0.0004380497311137942, 'samples': 6891264, 'steps': 35891, 'loss/train': 1.6960369348526} 08/30/2021 19:41:49 - INFO - __main__ - Step 35893: {'lr': 0.00043804623426602784, 'samples': 6891456, 'steps': 35892, 'loss/train': 1.629783272743225} 08/30/2021 19:41:50 - INFO - __main__ - Step 35894: {'lr': 0.00043804273733353085, 'samples': 6891648, 'steps': 35893, 'loss/train': 1.7936067581176758} 08/30/2021 19:41:50 - INFO - __main__ - Step 35895: {'lr': 0.0004380392403163047, 'samples': 6891840, 'steps': 35894, 'loss/train': 1.4328663349151611} 08/30/2021 19:41:52 - INFO - __main__ - Step 35896: {'lr': 0.00043803574321435093, 'samples': 6892032, 'steps': 35895, 'loss/train': 1.5266427993774414} 08/30/2021 19:41:53 - INFO - __main__ - Step 35897: {'lr': 0.00043803224602767115, 'samples': 6892224, 'steps': 35896, 'loss/train': 1.4053335189819336} 08/30/2021 19:41:53 - INFO - __main__ - Step 35898: {'lr': 0.000438028748756267, 'samples': 6892416, 'steps': 35897, 'loss/train': 1.304561734199524} 08/30/2021 19:41:54 - INFO - __main__ - Step 35899: {'lr': 0.00043802525140013994, 'samples': 6892608, 'steps': 35898, 'loss/train': 1.5983912944793701} 08/30/2021 19:41:54 - INFO - __main__ - Step 35900: {'lr': 0.00043802175395929156, 'samples': 6892800, 'steps': 35899, 'loss/train': 1.329479694366455} 08/30/2021 19:41:55 - INFO - __main__ - Step 35901: {'lr': 0.00043801825643372363, 'samples': 6892992, 'steps': 35900, 'loss/train': 0.9093522429466248} 08/30/2021 19:41:56 - INFO - __main__ - Step 35902: {'lr': 0.00043801475882343743, 'samples': 6893184, 'steps': 35901, 'loss/train': 1.4933193922042847} 08/30/2021 19:41:56 - INFO - __main__ - Step 35903: {'lr': 0.0004380112611284347, 'samples': 6893376, 'steps': 35902, 'loss/train': 1.4038033485412598} 08/30/2021 19:41:57 - INFO - __main__ - Step 35904: {'lr': 0.00043800776334871705, 'samples': 6893568, 'steps': 35903, 'loss/train': 1.1220324039459229} 08/30/2021 19:41:57 - INFO - __main__ - Step 35905: {'lr': 0.000438004265484286, 'samples': 6893760, 'steps': 35904, 'loss/train': 1.3246674537658691} 08/30/2021 19:41:59 - INFO - __main__ - Step 35906: {'lr': 0.0004380007675351431, 'samples': 6893952, 'steps': 35905, 'loss/train': 1.105709195137024} 08/30/2021 19:41:59 - INFO - __main__ - Step 35907: {'lr': 0.00043799726950128997, 'samples': 6894144, 'steps': 35906, 'loss/train': 1.3028582334518433} 08/30/2021 19:42:00 - INFO - __main__ - Step 35908: {'lr': 0.0004379937713827282, 'samples': 6894336, 'steps': 35907, 'loss/train': 1.5036885738372803} 08/30/2021 19:42:00 - INFO - __main__ - Step 35909: {'lr': 0.0004379902731794593, 'samples': 6894528, 'steps': 35908, 'loss/train': 1.6185053586959839} 08/30/2021 19:42:00 - INFO - __main__ - Step 35910: {'lr': 0.00043798677489148487, 'samples': 6894720, 'steps': 35909, 'loss/train': 1.006392002105713} 08/30/2021 19:42:01 - INFO - __main__ - Step 35911: {'lr': 0.0004379832765188065, 'samples': 6894912, 'steps': 35910, 'loss/train': 1.156903624534607} 08/30/2021 19:42:01 - INFO - __main__ - Step 35912: {'lr': 0.00043797977806142585, 'samples': 6895104, 'steps': 35911, 'loss/train': 0.23539602756500244} 08/30/2021 19:42:03 - INFO - __main__ - Step 35913: {'lr': 0.0004379762795193443, 'samples': 6895296, 'steps': 35912, 'loss/train': 0.12552106380462646} 08/30/2021 19:42:03 - INFO - __main__ - Step 35914: {'lr': 0.0004379727808925636, 'samples': 6895488, 'steps': 35913, 'loss/train': 1.5842339992523193} 08/30/2021 19:42:04 - INFO - __main__ - Step 35915: {'lr': 0.00043796928218108527, 'samples': 6895680, 'steps': 35914, 'loss/train': 1.5486630201339722} 08/30/2021 19:42:04 - INFO - __main__ - Step 35916: {'lr': 0.0004379657833849109, 'samples': 6895872, 'steps': 35915, 'loss/train': 2.00393009185791} 08/30/2021 19:42:04 - INFO - __main__ - Step 35917: {'lr': 0.000437962284504042, 'samples': 6896064, 'steps': 35916, 'loss/train': 1.2316259145736694} 08/30/2021 19:42:06 - INFO - __main__ - Step 35918: {'lr': 0.00043795878553848025, 'samples': 6896256, 'steps': 35917, 'loss/train': 1.6356743574142456} 08/30/2021 19:42:06 - INFO - __main__ - Step 35919: {'lr': 0.0004379552864882271, 'samples': 6896448, 'steps': 35918, 'loss/train': 0.13809886574745178} 08/30/2021 19:42:07 - INFO - __main__ - Step 35920: {'lr': 0.00043795178735328425, 'samples': 6896640, 'steps': 35919, 'loss/train': 1.2755662202835083} 08/30/2021 19:42:07 - INFO - __main__ - Step 35921: {'lr': 0.0004379482881336532, 'samples': 6896832, 'steps': 35920, 'loss/train': 1.628170371055603} 08/30/2021 19:42:07 - INFO - __main__ - Step 35922: {'lr': 0.0004379447888293355, 'samples': 6897024, 'steps': 35921, 'loss/train': 1.4386086463928223} 08/30/2021 19:42:08 - INFO - __main__ - Step 35923: {'lr': 0.0004379412894403328, 'samples': 6897216, 'steps': 35922, 'loss/train': 1.5190057754516602} 08/30/2021 19:42:09 - INFO - __main__ - Step 35924: {'lr': 0.0004379377899666468, 'samples': 6897408, 'steps': 35923, 'loss/train': 1.868404746055603} 08/30/2021 19:42:10 - INFO - __main__ - Step 35925: {'lr': 0.0004379342904082788, 'samples': 6897600, 'steps': 35924, 'loss/train': 1.0146533250808716} 08/30/2021 19:42:10 - INFO - __main__ - Step 35926: {'lr': 0.00043793079076523053, 'samples': 6897792, 'steps': 35925, 'loss/train': 0.5593517422676086} 08/30/2021 19:42:10 - INFO - __main__ - Step 35927: {'lr': 0.0004379272910375035, 'samples': 6897984, 'steps': 35926, 'loss/train': 1.5626782178878784} 08/30/2021 19:42:11 - INFO - __main__ - Step 35928: {'lr': 0.0004379237912250994, 'samples': 6898176, 'steps': 35927, 'loss/train': 1.6108183860778809} 08/30/2021 19:42:12 - INFO - __main__ - Step 35929: {'lr': 0.0004379202913280197, 'samples': 6898368, 'steps': 35928, 'loss/train': 0.7381371259689331} 08/30/2021 19:42:13 - INFO - __main__ - Step 35930: {'lr': 0.0004379167913462661, 'samples': 6898560, 'steps': 35929, 'loss/train': 1.7457282543182373} 08/30/2021 19:42:13 - INFO - __main__ - Step 35931: {'lr': 0.00043791329127984004, 'samples': 6898752, 'steps': 35930, 'loss/train': 1.0831356048583984} 08/30/2021 19:42:13 - INFO - __main__ - Step 35932: {'lr': 0.0004379097911287431, 'samples': 6898944, 'steps': 35931, 'loss/train': 1.2513684034347534} 08/30/2021 19:42:14 - INFO - __main__ - Step 35933: {'lr': 0.000437906290892977, 'samples': 6899136, 'steps': 35932, 'loss/train': 1.300889253616333} 08/30/2021 19:42:16 - INFO - __main__ - Step 35934: {'lr': 0.00043790279057254314, 'samples': 6899328, 'steps': 35933, 'loss/train': 1.373547077178955} 08/30/2021 19:42:16 - INFO - __main__ - Step 35935: {'lr': 0.00043789929016744324, 'samples': 6899520, 'steps': 35934, 'loss/train': 1.266237497329712} 08/30/2021 19:42:16 - INFO - __main__ - Step 35936: {'lr': 0.0004378957896776787, 'samples': 6899712, 'steps': 35935, 'loss/train': 1.0654737949371338} 08/30/2021 19:42:17 - INFO - __main__ - Step 35937: {'lr': 0.0004378922891032514, 'samples': 6899904, 'steps': 35936, 'loss/train': 1.1746692657470703} 08/30/2021 19:42:17 - INFO - __main__ - Step 35938: {'lr': 0.0004378887884441626, 'samples': 6900096, 'steps': 35937, 'loss/train': 0.03163360059261322} 08/30/2021 19:42:17 - INFO - __main__ - Step 35939: {'lr': 0.000437885287700414, 'samples': 6900288, 'steps': 35938, 'loss/train': 1.0469541549682617} 08/30/2021 19:42:19 - INFO - __main__ - Step 35940: {'lr': 0.0004378817868720073, 'samples': 6900480, 'steps': 35939, 'loss/train': 1.2296102046966553} 08/30/2021 19:42:19 - INFO - __main__ - Step 35941: {'lr': 0.0004378782859589439, 'samples': 6900672, 'steps': 35940, 'loss/train': 1.4204121828079224} 08/30/2021 19:42:20 - INFO - __main__ - Step 35942: {'lr': 0.00043787478496122546, 'samples': 6900864, 'steps': 35941, 'loss/train': 1.2266864776611328} 08/30/2021 19:42:20 - INFO - __main__ - Step 35943: {'lr': 0.0004378712838788536, 'samples': 6901056, 'steps': 35942, 'loss/train': 1.0710322856903076} 08/30/2021 19:42:21 - INFO - __main__ - Step 35944: {'lr': 0.0004378677827118297, 'samples': 6901248, 'steps': 35943, 'loss/train': 1.3463505506515503} 08/30/2021 19:42:22 - INFO - __main__ - Step 35945: {'lr': 0.0004378642814601556, 'samples': 6901440, 'steps': 35944, 'loss/train': 1.977847695350647} 08/30/2021 19:42:23 - INFO - __main__ - Step 35946: {'lr': 0.0004378607801238327, 'samples': 6901632, 'steps': 35945, 'loss/train': 1.4442052841186523} 08/30/2021 19:42:23 - INFO - __main__ - Step 35947: {'lr': 0.00043785727870286265, 'samples': 6901824, 'steps': 35946, 'loss/train': 1.5053248405456543} 08/30/2021 19:42:23 - INFO - __main__ - Step 35948: {'lr': 0.00043785377719724697, 'samples': 6902016, 'steps': 35947, 'loss/train': 1.0368385314941406} 08/30/2021 19:42:24 - INFO - __main__ - Step 35949: {'lr': 0.0004378502756069873, 'samples': 6902208, 'steps': 35948, 'loss/train': 0.6296055912971497} 08/30/2021 19:42:26 - INFO - __main__ - Step 35950: {'lr': 0.0004378467739320852, 'samples': 6902400, 'steps': 35949, 'loss/train': 1.8616852760314941} 08/30/2021 19:42:26 - INFO - __main__ - Step 35951: {'lr': 0.0004378432721725422, 'samples': 6902592, 'steps': 35950, 'loss/train': 1.6548593044281006} 08/30/2021 19:42:27 - INFO - __main__ - Step 35952: {'lr': 0.00043783977032836, 'samples': 6902784, 'steps': 35951, 'loss/train': 1.3482282161712646} 08/30/2021 19:42:27 - INFO - __main__ - Step 35953: {'lr': 0.00043783626839954005, 'samples': 6902976, 'steps': 35952, 'loss/train': 1.2887263298034668} 08/30/2021 19:42:27 - INFO - __main__ - Step 35954: {'lr': 0.0004378327663860839, 'samples': 6903168, 'steps': 35953, 'loss/train': 1.7742043733596802} 08/30/2021 19:42:28 - INFO - __main__ - Step 35955: {'lr': 0.00043782926428799333, 'samples': 6903360, 'steps': 35954, 'loss/train': 1.4570260047912598} 08/30/2021 19:42:30 - INFO - __main__ - Step 35956: {'lr': 0.0004378257621052698, 'samples': 6903552, 'steps': 35955, 'loss/train': 0.19698043167591095} 08/30/2021 19:42:30 - INFO - __main__ - Step 35957: {'lr': 0.0004378222598379148, 'samples': 6903744, 'steps': 35956, 'loss/train': 1.0483758449554443} 08/30/2021 19:42:30 - INFO - __main__ - Step 35958: {'lr': 0.00043781875748593, 'samples': 6903936, 'steps': 35957, 'loss/train': 1.1234116554260254} 08/30/2021 19:42:31 - INFO - __main__ - Step 35959: {'lr': 0.000437815255049317, 'samples': 6904128, 'steps': 35958, 'loss/train': 1.541306495666504} 08/30/2021 19:42:31 - INFO - __main__ - Step 35960: {'lr': 0.0004378117525280773, 'samples': 6904320, 'steps': 35959, 'loss/train': 1.461466670036316} 08/30/2021 19:42:33 - INFO - __main__ - Step 35961: {'lr': 0.00043780824992221257, 'samples': 6904512, 'steps': 35960, 'loss/train': 1.5916260480880737} 08/30/2021 19:42:33 - INFO - __main__ - Step 35962: {'lr': 0.00043780474723172433, 'samples': 6904704, 'steps': 35961, 'loss/train': 1.4838563203811646} 08/30/2021 19:42:34 - INFO - __main__ - Step 35963: {'lr': 0.00043780124445661416, 'samples': 6904896, 'steps': 35962, 'loss/train': 0.2184886336326599} 08/30/2021 19:42:34 - INFO - __main__ - Step 35964: {'lr': 0.00043779774159688364, 'samples': 6905088, 'steps': 35963, 'loss/train': 1.4340686798095703} 08/30/2021 19:42:34 - INFO - __main__ - Step 35965: {'lr': 0.00043779423865253434, 'samples': 6905280, 'steps': 35964, 'loss/train': 1.2144970893859863} 08/30/2021 19:42:36 - INFO - __main__ - Step 35966: {'lr': 0.00043779073562356783, 'samples': 6905472, 'steps': 35965, 'loss/train': 1.4804232120513916} 08/30/2021 19:42:36 - INFO - __main__ - Step 35967: {'lr': 0.0004377872325099858, 'samples': 6905664, 'steps': 35966, 'loss/train': 1.1439294815063477} 08/30/2021 19:42:37 - INFO - __main__ - Step 35968: {'lr': 0.00043778372931178974, 'samples': 6905856, 'steps': 35967, 'loss/train': 1.7621876001358032} 08/30/2021 19:42:37 - INFO - __main__ - Step 35969: {'lr': 0.00043778022602898115, 'samples': 6906048, 'steps': 35968, 'loss/train': 2.0064849853515625} 08/30/2021 19:42:37 - INFO - __main__ - Step 35970: {'lr': 0.0004377767226615617, 'samples': 6906240, 'steps': 35969, 'loss/train': 1.1076551675796509} 08/30/2021 19:42:39 - INFO - __main__ - Step 35971: {'lr': 0.000437773219209533, 'samples': 6906432, 'steps': 35970, 'loss/train': 1.1933568716049194} 08/30/2021 19:42:39 - INFO - __main__ - Step 35972: {'lr': 0.00043776971567289656, 'samples': 6906624, 'steps': 35971, 'loss/train': 1.253467082977295} 08/30/2021 19:42:40 - INFO - __main__ - Step 35973: {'lr': 0.00043776621205165404, 'samples': 6906816, 'steps': 35972, 'loss/train': 0.8991245627403259} 08/30/2021 19:42:40 - INFO - __main__ - Step 35974: {'lr': 0.0004377627083458069, 'samples': 6907008, 'steps': 35973, 'loss/train': 1.5318894386291504} 08/30/2021 19:42:40 - INFO - __main__ - Step 35975: {'lr': 0.0004377592045553568, 'samples': 6907200, 'steps': 35974, 'loss/train': 1.268610954284668} 08/30/2021 19:42:41 - INFO - __main__ - Step 35976: {'lr': 0.00043775570068030524, 'samples': 6907392, 'steps': 35975, 'loss/train': 0.7990579605102539} 08/30/2021 19:42:42 - INFO - __main__ - Step 35977: {'lr': 0.0004377521967206539, 'samples': 6907584, 'steps': 35976, 'loss/train': 0.8548378944396973} 08/30/2021 19:42:43 - INFO - __main__ - Step 35978: {'lr': 0.00043774869267640436, 'samples': 6907776, 'steps': 35977, 'loss/train': 1.7069313526153564} 08/30/2021 19:42:43 - INFO - __main__ - Step 35979: {'lr': 0.0004377451885475581, 'samples': 6907968, 'steps': 35978, 'loss/train': 1.6038774251937866} 08/30/2021 19:42:43 - INFO - __main__ - Step 35980: {'lr': 0.0004377416843341168, 'samples': 6908160, 'steps': 35979, 'loss/train': 1.096545696258545} 08/30/2021 19:42:44 - INFO - __main__ - Step 35981: {'lr': 0.00043773818003608203, 'samples': 6908352, 'steps': 35980, 'loss/train': 1.547872543334961} 08/30/2021 19:42:45 - INFO - __main__ - Step 35982: {'lr': 0.00043773467565345523, 'samples': 6908544, 'steps': 35981, 'loss/train': 1.7717556953430176} 08/30/2021 19:42:46 - INFO - __main__ - Step 35983: {'lr': 0.0004377311711862381, 'samples': 6908736, 'steps': 35982, 'loss/train': 1.2803595066070557} 08/30/2021 19:42:46 - INFO - __main__ - Step 35984: {'lr': 0.0004377276666344322, 'samples': 6908928, 'steps': 35983, 'loss/train': 1.8664737939834595} 08/30/2021 19:42:46 - INFO - __main__ - Step 35985: {'lr': 0.00043772416199803924, 'samples': 6909120, 'steps': 35984, 'loss/train': 1.4957305192947388} 08/30/2021 19:42:47 - INFO - __main__ - Step 35986: {'lr': 0.00043772065727706053, 'samples': 6909312, 'steps': 35985, 'loss/train': 1.1382882595062256} 08/30/2021 19:42:48 - INFO - __main__ - Step 35987: {'lr': 0.0004377171524714978, 'samples': 6909504, 'steps': 35986, 'loss/train': 1.461427092552185} 08/30/2021 19:42:49 - INFO - __main__ - Step 35988: {'lr': 0.0004377136475813527, 'samples': 6909696, 'steps': 35987, 'loss/train': 1.9665017127990723} 08/30/2021 19:42:49 - INFO - __main__ - Step 35989: {'lr': 0.0004377101426066266, 'samples': 6909888, 'steps': 35988, 'loss/train': 1.9896049499511719} 08/30/2021 19:42:49 - INFO - __main__ - Step 35990: {'lr': 0.0004377066375473213, 'samples': 6910080, 'steps': 35989, 'loss/train': 1.1919983625411987} 08/30/2021 19:42:50 - INFO - __main__ - Step 35991: {'lr': 0.00043770313240343826, 'samples': 6910272, 'steps': 35990, 'loss/train': 1.751158595085144} 08/30/2021 19:42:51 - INFO - __main__ - Step 35992: {'lr': 0.00043769962717497916, 'samples': 6910464, 'steps': 35991, 'loss/train': 1.5254515409469604} 08/30/2021 19:42:52 - INFO - __main__ - Step 35993: {'lr': 0.0004376961218619454, 'samples': 6910656, 'steps': 35992, 'loss/train': 1.237084150314331} 08/30/2021 19:42:52 - INFO - __main__ - Step 35994: {'lr': 0.00043769261646433867, 'samples': 6910848, 'steps': 35993, 'loss/train': 1.1449388265609741} 08/30/2021 19:42:52 - INFO - __main__ - Step 35995: {'lr': 0.0004376891109821606, 'samples': 6911040, 'steps': 35994, 'loss/train': 1.532547950744629} 08/30/2021 19:42:53 - INFO - __main__ - Step 35996: {'lr': 0.0004376856054154127, 'samples': 6911232, 'steps': 35995, 'loss/train': 1.8205986022949219} 08/30/2021 19:42:54 - INFO - __main__ - Step 35997: {'lr': 0.00043768209976409645, 'samples': 6911424, 'steps': 35996, 'loss/train': 1.4493441581726074} 08/30/2021 19:42:55 - INFO - __main__ - Step 35998: {'lr': 0.0004376785940282137, 'samples': 6911616, 'steps': 35997, 'loss/train': 1.7962307929992676} 08/30/2021 19:42:55 - INFO - __main__ - Step 35999: {'lr': 0.0004376750882077658, 'samples': 6911808, 'steps': 35998, 'loss/train': 0.8227716684341431} 08/30/2021 19:42:55 - INFO - __main__ - Step 36000: {'lr': 0.0004376715823027544, 'samples': 6912000, 'steps': 35999, 'loss/train': 0.28827592730522156} 08/30/2021 19:42:56 - INFO - __main__ - Step 36001: {'lr': 0.0004376680763131811, 'samples': 6912192, 'steps': 36000, 'loss/train': 1.0225043296813965} 08/30/2021 19:42:57 - INFO - __main__ - Step 36002: {'lr': 0.0004376645702390475, 'samples': 6912384, 'steps': 36001, 'loss/train': 1.203527569770813} 08/30/2021 19:42:58 - INFO - __main__ - Step 36003: {'lr': 0.00043766106408035506, 'samples': 6912576, 'steps': 36002, 'loss/train': 1.2971988916397095} 08/30/2021 19:42:58 - INFO - __main__ - Step 36004: {'lr': 0.0004376575578371055, 'samples': 6912768, 'steps': 36003, 'loss/train': 1.5095651149749756} 08/30/2021 19:42:58 - INFO - __main__ - Step 36005: {'lr': 0.0004376540515093003, 'samples': 6912960, 'steps': 36004, 'loss/train': 0.9047927260398865} 08/30/2021 19:42:59 - INFO - __main__ - Step 36006: {'lr': 0.0004376505450969411, 'samples': 6913152, 'steps': 36005, 'loss/train': 1.8407281637191772} 08/30/2021 19:42:59 - INFO - __main__ - Step 36007: {'lr': 0.0004376470386000294, 'samples': 6913344, 'steps': 36006, 'loss/train': 1.3397948741912842} 08/30/2021 19:43:01 - INFO - __main__ - Step 36008: {'lr': 0.0004376435320185669, 'samples': 6913536, 'steps': 36007, 'loss/train': 1.3284211158752441} 08/30/2021 19:43:02 - INFO - __main__ - Step 36009: {'lr': 0.0004376400253525551, 'samples': 6913728, 'steps': 36008, 'loss/train': 0.869174063205719} 08/30/2021 19:43:02 - INFO - __main__ - Step 36010: {'lr': 0.0004376365186019956, 'samples': 6913920, 'steps': 36009, 'loss/train': 1.620209813117981} 08/30/2021 19:43:02 - INFO - __main__ - Step 36011: {'lr': 0.00043763301176689, 'samples': 6914112, 'steps': 36010, 'loss/train': 1.8468531370162964} 08/30/2021 19:43:03 - INFO - __main__ - Step 36012: {'lr': 0.0004376295048472399, 'samples': 6914304, 'steps': 36011, 'loss/train': 0.8346722722053528} 08/30/2021 19:43:04 - INFO - __main__ - Step 36013: {'lr': 0.0004376259978430468, 'samples': 6914496, 'steps': 36012, 'loss/train': 1.434913158416748} 08/30/2021 19:43:05 - INFO - __main__ - Step 36014: {'lr': 0.0004376224907543123, 'samples': 6914688, 'steps': 36013, 'loss/train': 0.7564408183097839} 08/30/2021 19:43:05 - INFO - __main__ - Step 36015: {'lr': 0.00043761898358103804, 'samples': 6914880, 'steps': 36014, 'loss/train': 1.110268235206604} 08/30/2021 19:43:05 - INFO - __main__ - Step 36016: {'lr': 0.0004376154763232255, 'samples': 6915072, 'steps': 36015, 'loss/train': 1.2822383642196655} 08/30/2021 19:43:06 - INFO - __main__ - Step 36017: {'lr': 0.0004376119689808764, 'samples': 6915264, 'steps': 36016, 'loss/train': 1.6770011186599731} 08/30/2021 19:43:08 - INFO - __main__ - Step 36018: {'lr': 0.00043760846155399216, 'samples': 6915456, 'steps': 36017, 'loss/train': 0.08690931648015976} 08/30/2021 19:43:08 - INFO - __main__ - Step 36019: {'lr': 0.0004376049540425745, 'samples': 6915648, 'steps': 36018, 'loss/train': 1.2932840585708618} 08/30/2021 19:43:08 - INFO - __main__ - Step 36020: {'lr': 0.0004376014464466249, 'samples': 6915840, 'steps': 36019, 'loss/train': 1.8744899034500122} 08/30/2021 19:43:09 - INFO - __main__ - Step 36021: {'lr': 0.0004375979387661451, 'samples': 6916032, 'steps': 36020, 'loss/train': 1.6647194623947144} 08/30/2021 19:43:09 - INFO - __main__ - Step 36022: {'lr': 0.0004375944310011364, 'samples': 6916224, 'steps': 36021, 'loss/train': 1.9740253686904907} 08/30/2021 19:43:11 - INFO - __main__ - Step 36023: {'lr': 0.00043759092315160064, 'samples': 6916416, 'steps': 36022, 'loss/train': 0.09651821851730347} 08/30/2021 19:43:11 - INFO - __main__ - Step 36024: {'lr': 0.00043758741521753925, 'samples': 6916608, 'steps': 36023, 'loss/train': 1.815151572227478} 08/30/2021 19:43:12 - INFO - __main__ - Step 36025: {'lr': 0.0004375839071989539, 'samples': 6916800, 'steps': 36024, 'loss/train': 1.6136376857757568} 08/30/2021 19:43:12 - INFO - __main__ - Step 36026: {'lr': 0.00043758039909584613, 'samples': 6916992, 'steps': 36025, 'loss/train': 1.468501329421997} 08/30/2021 19:43:12 - INFO - __main__ - Step 36027: {'lr': 0.0004375768909082175, 'samples': 6917184, 'steps': 36026, 'loss/train': 0.10584470629692078} 08/30/2021 19:43:13 - INFO - __main__ - Step 36028: {'lr': 0.0004375733826360697, 'samples': 6917376, 'steps': 36027, 'loss/train': 0.765294075012207} 08/30/2021 19:43:14 - INFO - __main__ - Step 36029: {'lr': 0.0004375698742794042, 'samples': 6917568, 'steps': 36028, 'loss/train': 5.794175148010254} 08/30/2021 19:43:15 - INFO - __main__ - Step 36030: {'lr': 0.0004375663658382225, 'samples': 6917760, 'steps': 36029, 'loss/train': 0.9114642143249512} 08/30/2021 19:43:15 - INFO - __main__ - Step 36031: {'lr': 0.0004375628573125264, 'samples': 6917952, 'steps': 36030, 'loss/train': 1.5143628120422363} 08/30/2021 19:43:15 - INFO - __main__ - Step 36032: {'lr': 0.0004375593487023174, 'samples': 6918144, 'steps': 36031, 'loss/train': 0.9707401990890503} 08/30/2021 19:43:16 - INFO - __main__ - Step 36033: {'lr': 0.00043755584000759696, 'samples': 6918336, 'steps': 36032, 'loss/train': 1.919002890586853} 08/30/2021 19:43:17 - INFO - __main__ - Step 36034: {'lr': 0.0004375523312283668, 'samples': 6918528, 'steps': 36033, 'loss/train': 1.9662377834320068} 08/30/2021 19:43:18 - INFO - __main__ - Step 36035: {'lr': 0.00043754882236462844, 'samples': 6918720, 'steps': 36034, 'loss/train': 1.7322356700897217} 08/30/2021 19:43:18 - INFO - __main__ - Step 36036: {'lr': 0.00043754531341638346, 'samples': 6918912, 'steps': 36035, 'loss/train': 1.3574854135513306} 08/30/2021 19:43:18 - INFO - __main__ - Step 36037: {'lr': 0.00043754180438363344, 'samples': 6919104, 'steps': 36036, 'loss/train': 1.8688459396362305} 08/30/2021 19:43:19 - INFO - __main__ - Step 36038: {'lr': 0.00043753829526638, 'samples': 6919296, 'steps': 36037, 'loss/train': 1.3560893535614014} 08/30/2021 19:43:20 - INFO - __main__ - Step 36039: {'lr': 0.0004375347860646247, 'samples': 6919488, 'steps': 36038, 'loss/train': 1.8518990278244019} 08/30/2021 19:43:21 - INFO - __main__ - Step 36040: {'lr': 0.00043753127677836917, 'samples': 6919680, 'steps': 36039, 'loss/train': 0.848493754863739} 08/30/2021 19:43:21 - INFO - __main__ - Step 36041: {'lr': 0.0004375277674076149, 'samples': 6919872, 'steps': 36040, 'loss/train': 1.4543474912643433} 08/30/2021 19:43:21 - INFO - __main__ - Step 36042: {'lr': 0.0004375242579523635, 'samples': 6920064, 'steps': 36041, 'loss/train': 2.002323627471924} 08/30/2021 19:43:22 - INFO - __main__ - Step 36043: {'lr': 0.0004375207484126166, 'samples': 6920256, 'steps': 36042, 'loss/train': 1.7686681747436523} 08/30/2021 19:43:22 - INFO - __main__ - Step 36044: {'lr': 0.0004375172387883757, 'samples': 6920448, 'steps': 36043, 'loss/train': 2.4521396160125732} 08/30/2021 19:43:24 - INFO - __main__ - Step 36045: {'lr': 0.00043751372907964247, 'samples': 6920640, 'steps': 36044, 'loss/train': 1.3211314678192139} 08/30/2021 19:43:24 - INFO - __main__ - Step 36046: {'lr': 0.00043751021928641845, 'samples': 6920832, 'steps': 36045, 'loss/train': 1.4622420072555542} 08/30/2021 19:43:24 - INFO - __main__ - Step 36047: {'lr': 0.0004375067094087051, 'samples': 6921024, 'steps': 36046, 'loss/train': 1.1819556951522827} 08/30/2021 19:43:25 - INFO - __main__ - Step 36048: {'lr': 0.0004375031994465042, 'samples': 6921216, 'steps': 36047, 'loss/train': 2.2134838104248047} 08/30/2021 19:43:25 - INFO - __main__ - Step 36049: {'lr': 0.00043749968939981734, 'samples': 6921408, 'steps': 36048, 'loss/train': 1.0158450603485107} 08/30/2021 19:43:27 - INFO - __main__ - Step 36050: {'lr': 0.0004374961792686459, 'samples': 6921600, 'steps': 36049, 'loss/train': 2.0458874702453613} 08/30/2021 19:43:27 - INFO - __main__ - Step 36051: {'lr': 0.00043749266905299155, 'samples': 6921792, 'steps': 36050, 'loss/train': 1.354964256286621} 08/30/2021 19:43:27 - INFO - __main__ - Step 36052: {'lr': 0.000437489158752856, 'samples': 6921984, 'steps': 36051, 'loss/train': 1.5432651042938232} 08/30/2021 19:43:28 - INFO - __main__ - Step 36053: {'lr': 0.00043748564836824065, 'samples': 6922176, 'steps': 36052, 'loss/train': 1.6794992685317993} 08/30/2021 19:43:28 - INFO - __main__ - Step 36054: {'lr': 0.0004374821378991473, 'samples': 6922368, 'steps': 36053, 'loss/train': 1.8025633096694946} 08/30/2021 19:43:30 - INFO - __main__ - Step 36055: {'lr': 0.0004374786273455772, 'samples': 6922560, 'steps': 36054, 'loss/train': 1.141648530960083} 08/30/2021 19:43:30 - INFO - __main__ - Step 36056: {'lr': 0.0004374751167075322, 'samples': 6922752, 'steps': 36055, 'loss/train': 1.8451446294784546} 08/30/2021 19:43:30 - INFO - __main__ - Step 36057: {'lr': 0.0004374716059850138, 'samples': 6922944, 'steps': 36056, 'loss/train': 1.531600832939148} 08/30/2021 19:43:31 - INFO - __main__ - Step 36058: {'lr': 0.0004374680951780236, 'samples': 6923136, 'steps': 36057, 'loss/train': 0.5976413488388062} 08/30/2021 19:43:31 - INFO - __main__ - Step 36059: {'lr': 0.00043746458428656324, 'samples': 6923328, 'steps': 36058, 'loss/train': 1.4780911207199097} 08/30/2021 19:43:33 - INFO - __main__ - Step 36060: {'lr': 0.00043746107331063414, 'samples': 6923520, 'steps': 36059, 'loss/train': 1.6300278902053833} 08/30/2021 19:43:33 - INFO - __main__ - Step 36061: {'lr': 0.000437457562250238, 'samples': 6923712, 'steps': 36060, 'loss/train': 0.7864250540733337} 08/30/2021 19:43:33 - INFO - __main__ - Step 36062: {'lr': 0.0004374540511053763, 'samples': 6923904, 'steps': 36061, 'loss/train': 1.363936424255371} 08/30/2021 19:43:34 - INFO - __main__ - Step 36063: {'lr': 0.00043745053987605075, 'samples': 6924096, 'steps': 36062, 'loss/train': 1.2985875606536865} 08/30/2021 19:43:34 - INFO - __main__ - Step 36064: {'lr': 0.00043744702856226295, 'samples': 6924288, 'steps': 36063, 'loss/train': 1.1848994493484497} 08/30/2021 19:43:36 - INFO - __main__ - Step 36065: {'lr': 0.0004374435171640144, 'samples': 6924480, 'steps': 36064, 'loss/train': 1.1395477056503296} 08/30/2021 19:43:37 - INFO - __main__ - Step 36066: {'lr': 0.0004374400056813066, 'samples': 6924672, 'steps': 36065, 'loss/train': 0.05058704689145088} 08/30/2021 19:43:37 - INFO - __main__ - Step 36067: {'lr': 0.0004374364941141413, 'samples': 6924864, 'steps': 36066, 'loss/train': 1.5755720138549805} 08/30/2021 19:43:37 - INFO - __main__ - Step 36068: {'lr': 0.00043743298246251994, 'samples': 6925056, 'steps': 36067, 'loss/train': 1.4239070415496826} 08/30/2021 19:43:38 - INFO - __main__ - Step 36069: {'lr': 0.00043742947072644424, 'samples': 6925248, 'steps': 36068, 'loss/train': 1.3607182502746582} 08/30/2021 19:43:39 - INFO - __main__ - Step 36070: {'lr': 0.0004374259589059157, 'samples': 6925440, 'steps': 36069, 'loss/train': 1.3380931615829468} 08/30/2021 19:43:40 - INFO - __main__ - Step 36071: {'lr': 0.0004374224470009359, 'samples': 6925632, 'steps': 36070, 'loss/train': 1.2803268432617188} 08/30/2021 19:43:40 - INFO - __main__ - Step 36072: {'lr': 0.00043741893501150644, 'samples': 6925824, 'steps': 36071, 'loss/train': 1.140285611152649} 08/30/2021 19:43:40 - INFO - __main__ - Step 36073: {'lr': 0.0004374154229376289, 'samples': 6926016, 'steps': 36072, 'loss/train': 1.416749119758606} 08/30/2021 19:43:41 - INFO - __main__ - Step 36074: {'lr': 0.00043741191077930486, 'samples': 6926208, 'steps': 36073, 'loss/train': 1.8557988405227661} 08/30/2021 19:43:42 - INFO - __main__ - Step 36075: {'lr': 0.00043740839853653594, 'samples': 6926400, 'steps': 36074, 'loss/train': 1.285251498222351} 08/30/2021 19:43:43 - INFO - __main__ - Step 36076: {'lr': 0.0004374048862093236, 'samples': 6926592, 'steps': 36075, 'loss/train': 1.213763952255249} 08/30/2021 19:43:43 - INFO - __main__ - Step 36077: {'lr': 0.00043740137379766954, 'samples': 6926784, 'steps': 36076, 'loss/train': 1.7948158979415894} 08/30/2021 19:43:43 - INFO - __main__ - Step 36078: {'lr': 0.0004373978613015753, 'samples': 6926976, 'steps': 36077, 'loss/train': 1.2927815914154053} 08/30/2021 19:43:44 - INFO - __main__ - Step 36079: {'lr': 0.00043739434872104257, 'samples': 6927168, 'steps': 36078, 'loss/train': 1.382166862487793} 08/30/2021 19:43:45 - INFO - __main__ - Step 36080: {'lr': 0.00043739083605607275, 'samples': 6927360, 'steps': 36079, 'loss/train': 0.3568832278251648} 08/30/2021 19:43:46 - INFO - __main__ - Step 36081: {'lr': 0.0004373873233066676, 'samples': 6927552, 'steps': 36080, 'loss/train': 1.6571969985961914} 08/30/2021 19:43:46 - INFO - __main__ - Step 36082: {'lr': 0.00043738381047282856, 'samples': 6927744, 'steps': 36081, 'loss/train': 1.4800221920013428} 08/30/2021 19:43:46 - INFO - __main__ - Step 36083: {'lr': 0.00043738029755455724, 'samples': 6927936, 'steps': 36082, 'loss/train': 1.482835054397583} 08/30/2021 19:43:47 - INFO - __main__ - Step 36084: {'lr': 0.00043737678455185524, 'samples': 6928128, 'steps': 36083, 'loss/train': 1.1489288806915283} 08/30/2021 19:43:47 - INFO - __main__ - Step 36085: {'lr': 0.0004373732714647242, 'samples': 6928320, 'steps': 36084, 'loss/train': 1.46577787399292} 08/30/2021 19:43:49 - INFO - __main__ - Step 36086: {'lr': 0.0004373697582931657, 'samples': 6928512, 'steps': 36085, 'loss/train': 0.9283316135406494} 08/30/2021 19:43:49 - INFO - __main__ - Step 36087: {'lr': 0.0004373662450371812, 'samples': 6928704, 'steps': 36086, 'loss/train': 1.5501642227172852} 08/30/2021 19:43:49 - INFO - __main__ - Step 36088: {'lr': 0.0004373627316967723, 'samples': 6928896, 'steps': 36087, 'loss/train': 1.4926953315734863} 08/30/2021 19:43:50 - INFO - __main__ - Step 36089: {'lr': 0.0004373592182719408, 'samples': 6929088, 'steps': 36088, 'loss/train': 1.7692233324050903} 08/30/2021 19:43:50 - INFO - __main__ - Step 36090: {'lr': 0.00043735570476268804, 'samples': 6929280, 'steps': 36089, 'loss/train': 0.8793413043022156} 08/30/2021 19:43:52 - INFO - __main__ - Step 36091: {'lr': 0.0004373521911690157, 'samples': 6929472, 'steps': 36090, 'loss/train': 1.1689447164535522} 08/30/2021 19:43:52 - INFO - __main__ - Step 36092: {'lr': 0.00043734867749092534, 'samples': 6929664, 'steps': 36091, 'loss/train': 1.890589952468872} 08/30/2021 19:43:53 - INFO - __main__ - Step 36093: {'lr': 0.0004373451637284186, 'samples': 6929856, 'steps': 36092, 'loss/train': 0.511699914932251} 08/30/2021 19:43:53 - INFO - __main__ - Step 36094: {'lr': 0.0004373416498814969, 'samples': 6930048, 'steps': 36093, 'loss/train': 1.3292160034179688} 08/30/2021 19:43:53 - INFO - __main__ - Step 36095: {'lr': 0.0004373381359501621, 'samples': 6930240, 'steps': 36094, 'loss/train': 1.3810791969299316} 08/30/2021 19:43:54 - INFO - __main__ - Step 36096: {'lr': 0.00043733462193441553, 'samples': 6930432, 'steps': 36095, 'loss/train': 0.6969497799873352} 08/30/2021 19:43:55 - INFO - __main__ - Step 36097: {'lr': 0.00043733110783425894, 'samples': 6930624, 'steps': 36096, 'loss/train': 1.5299763679504395} 08/30/2021 19:43:56 - INFO - __main__ - Step 36098: {'lr': 0.00043732759364969374, 'samples': 6930816, 'steps': 36097, 'loss/train': 1.5626649856567383} 08/30/2021 19:43:56 - INFO - __main__ - Step 36099: {'lr': 0.0004373240793807217, 'samples': 6931008, 'steps': 36098, 'loss/train': 1.3506392240524292} 08/30/2021 19:43:57 - INFO - __main__ - Step 36100: {'lr': 0.00043732056502734435, 'samples': 6931200, 'steps': 36099, 'loss/train': 1.5071520805358887} 08/30/2021 19:43:57 - INFO - __main__ - Step 36101: {'lr': 0.0004373170505895632, 'samples': 6931392, 'steps': 36100, 'loss/train': 0.1549835354089737} 08/30/2021 19:43:58 - INFO - __main__ - Step 36102: {'lr': 0.0004373135360673799, 'samples': 6931584, 'steps': 36101, 'loss/train': 1.5522302389144897} 08/30/2021 19:43:59 - INFO - __main__ - Step 36103: {'lr': 0.000437310021460796, 'samples': 6931776, 'steps': 36102, 'loss/train': 1.450844407081604} 08/30/2021 19:43:59 - INFO - __main__ - Step 36104: {'lr': 0.000437306506769813, 'samples': 6931968, 'steps': 36103, 'loss/train': 1.9918410778045654} 08/30/2021 19:44:00 - INFO - __main__ - Step 36105: {'lr': 0.0004373029919944327, 'samples': 6932160, 'steps': 36104, 'loss/train': 1.6261976957321167} 08/30/2021 19:44:00 - INFO - __main__ - Step 36106: {'lr': 0.00043729947713465653, 'samples': 6932352, 'steps': 36105, 'loss/train': 1.0425323247909546} 08/30/2021 19:44:01 - INFO - __main__ - Step 36107: {'lr': 0.00043729596219048607, 'samples': 6932544, 'steps': 36106, 'loss/train': 1.4196878671646118} 08/30/2021 19:44:02 - INFO - __main__ - Step 36108: {'lr': 0.000437292447161923, 'samples': 6932736, 'steps': 36107, 'loss/train': 1.3793174028396606} 08/30/2021 19:44:02 - INFO - __main__ - Step 36109: {'lr': 0.0004372889320489688, 'samples': 6932928, 'steps': 36108, 'loss/train': 0.8662286996841431} 08/30/2021 19:44:02 - INFO - __main__ - Step 36110: {'lr': 0.00043728541685162503, 'samples': 6933120, 'steps': 36109, 'loss/train': 1.8410738706588745} 08/30/2021 19:44:03 - INFO - __main__ - Step 36111: {'lr': 0.0004372819015698934, 'samples': 6933312, 'steps': 36110, 'loss/train': 0.6522652506828308} 08/30/2021 19:44:04 - INFO - __main__ - Step 36112: {'lr': 0.0004372783862037755, 'samples': 6933504, 'steps': 36111, 'loss/train': 1.6090412139892578} 08/30/2021 19:44:05 - INFO - __main__ - Step 36113: {'lr': 0.00043727487075327285, 'samples': 6933696, 'steps': 36112, 'loss/train': 1.2346184253692627} 08/30/2021 19:44:05 - INFO - __main__ - Step 36114: {'lr': 0.00043727135521838697, 'samples': 6933888, 'steps': 36113, 'loss/train': 1.940293312072754} 08/30/2021 19:44:05 - INFO - __main__ - Step 36115: {'lr': 0.00043726783959911953, 'samples': 6934080, 'steps': 36114, 'loss/train': 1.8155865669250488} 08/30/2021 19:44:06 - INFO - __main__ - Step 36116: {'lr': 0.00043726432389547205, 'samples': 6934272, 'steps': 36115, 'loss/train': 1.8422759771347046} 08/30/2021 19:44:08 - INFO - __main__ - Step 36117: {'lr': 0.00043726080810744616, 'samples': 6934464, 'steps': 36116, 'loss/train': 2.2651312351226807} 08/30/2021 19:44:08 - INFO - __main__ - Step 36118: {'lr': 0.0004372572922350435, 'samples': 6934656, 'steps': 36117, 'loss/train': 1.2567503452301025} 08/30/2021 19:44:09 - INFO - __main__ - Step 36119: {'lr': 0.0004372537762782656, 'samples': 6934848, 'steps': 36118, 'loss/train': 2.4502525329589844} 08/30/2021 19:44:09 - INFO - __main__ - Step 36120: {'lr': 0.00043725026023711395, 'samples': 6935040, 'steps': 36119, 'loss/train': 1.0960851907730103} 08/30/2021 19:44:09 - INFO - __main__ - Step 36121: {'lr': 0.0004372467441115903, 'samples': 6935232, 'steps': 36120, 'loss/train': 0.6183828115463257} 08/30/2021 19:44:11 - INFO - __main__ - Step 36122: {'lr': 0.00043724322790169613, 'samples': 6935424, 'steps': 36121, 'loss/train': 1.1075011491775513} 08/30/2021 19:44:12 - INFO - __main__ - Step 36123: {'lr': 0.00043723971160743305, 'samples': 6935616, 'steps': 36122, 'loss/train': 1.1525518894195557} 08/30/2021 19:44:12 - INFO - __main__ - Step 36124: {'lr': 0.00043723619522880266, 'samples': 6935808, 'steps': 36123, 'loss/train': 2.762505054473877} 08/30/2021 19:44:12 - INFO - __main__ - Step 36125: {'lr': 0.0004372326787658065, 'samples': 6936000, 'steps': 36124, 'loss/train': 1.3858706951141357} 08/30/2021 19:44:13 - INFO - __main__ - Step 36126: {'lr': 0.00043722916221844617, 'samples': 6936192, 'steps': 36125, 'loss/train': 1.8959014415740967} 08/30/2021 19:44:14 - INFO - __main__ - Step 36127: {'lr': 0.0004372256455867233, 'samples': 6936384, 'steps': 36126, 'loss/train': 0.088154137134552} 08/30/2021 19:44:14 - INFO - __main__ - Step 36128: {'lr': 0.0004372221288706394, 'samples': 6936576, 'steps': 36127, 'loss/train': 1.7600674629211426} 08/30/2021 19:44:15 - INFO - __main__ - Step 36129: {'lr': 0.0004372186120701962, 'samples': 6936768, 'steps': 36128, 'loss/train': 1.3942238092422485} 08/30/2021 19:44:15 - INFO - __main__ - Step 36130: {'lr': 0.00043721509518539507, 'samples': 6936960, 'steps': 36129, 'loss/train': 1.1062726974487305} 08/30/2021 19:44:15 - INFO - __main__ - Step 36131: {'lr': 0.0004372115782162378, 'samples': 6937152, 'steps': 36130, 'loss/train': 1.438301682472229} 08/30/2021 19:44:17 - INFO - __main__ - Step 36132: {'lr': 0.00043720806116272584, 'samples': 6937344, 'steps': 36131, 'loss/train': 1.54770028591156} 08/30/2021 19:44:17 - INFO - __main__ - Step 36133: {'lr': 0.00043720454402486076, 'samples': 6937536, 'steps': 36132, 'loss/train': 1.4610021114349365} 08/30/2021 19:44:18 - INFO - __main__ - Step 36134: {'lr': 0.00043720102680264427, 'samples': 6937728, 'steps': 36133, 'loss/train': 1.7238088846206665} 08/30/2021 19:44:18 - INFO - __main__ - Step 36135: {'lr': 0.0004371975094960778, 'samples': 6937920, 'steps': 36134, 'loss/train': 1.848029375076294} 08/30/2021 19:44:18 - INFO - __main__ - Step 36136: {'lr': 0.0004371939921051632, 'samples': 6938112, 'steps': 36135, 'loss/train': 1.175031304359436} 08/30/2021 19:44:19 - INFO - __main__ - Step 36137: {'lr': 0.00043719047462990174, 'samples': 6938304, 'steps': 36136, 'loss/train': 1.9913254976272583} 08/30/2021 19:44:20 - INFO - __main__ - Step 36138: {'lr': 0.0004371869570702952, 'samples': 6938496, 'steps': 36137, 'loss/train': 1.6899923086166382} 08/30/2021 19:44:21 - INFO - __main__ - Step 36139: {'lr': 0.0004371834394263451, 'samples': 6938688, 'steps': 36138, 'loss/train': 1.2530657052993774} 08/30/2021 19:44:21 - INFO - __main__ - Step 36140: {'lr': 0.000437179921698053, 'samples': 6938880, 'steps': 36139, 'loss/train': 1.5722675323486328} 08/30/2021 19:44:21 - INFO - __main__ - Step 36141: {'lr': 0.00043717640388542045, 'samples': 6939072, 'steps': 36140, 'loss/train': 1.606685996055603} 08/30/2021 19:44:22 - INFO - __main__ - Step 36142: {'lr': 0.00043717288598844916, 'samples': 6939264, 'steps': 36141, 'loss/train': 1.9109846353530884} 08/30/2021 19:44:23 - INFO - __main__ - Step 36143: {'lr': 0.0004371693680071407, 'samples': 6939456, 'steps': 36142, 'loss/train': 1.5546871423721313} 08/30/2021 19:44:24 - INFO - __main__ - Step 36144: {'lr': 0.00043716584994149657, 'samples': 6939648, 'steps': 36143, 'loss/train': 1.5325613021850586} 08/30/2021 19:44:24 - INFO - __main__ - Step 36145: {'lr': 0.0004371623317915184, 'samples': 6939840, 'steps': 36144, 'loss/train': 1.2303208112716675} 08/30/2021 19:44:24 - INFO - __main__ - Step 36146: {'lr': 0.00043715881355720776, 'samples': 6940032, 'steps': 36145, 'loss/train': 1.4710524082183838} 08/30/2021 19:44:25 - INFO - __main__ - Step 36147: {'lr': 0.0004371552952385663, 'samples': 6940224, 'steps': 36146, 'loss/train': 1.0660884380340576} 08/30/2021 19:44:26 - INFO - __main__ - Step 36148: {'lr': 0.00043715177683559546, 'samples': 6940416, 'steps': 36147, 'loss/train': 1.469367265701294} 08/30/2021 19:44:27 - INFO - __main__ - Step 36149: {'lr': 0.000437148258348297, 'samples': 6940608, 'steps': 36148, 'loss/train': 1.448828101158142} 08/30/2021 19:44:27 - INFO - __main__ - Step 36150: {'lr': 0.0004371447397766724, 'samples': 6940800, 'steps': 36149, 'loss/train': 1.3521138429641724} 08/30/2021 19:44:27 - INFO - __main__ - Step 36151: {'lr': 0.0004371412211207233, 'samples': 6940992, 'steps': 36150, 'loss/train': 1.6602424383163452} 08/30/2021 19:44:28 - INFO - __main__ - Step 36152: {'lr': 0.0004371377023804512, 'samples': 6941184, 'steps': 36151, 'loss/train': 1.3956000804901123} 08/30/2021 19:44:30 - INFO - __main__ - Step 36153: {'lr': 0.0004371341835558578, 'samples': 6941376, 'steps': 36152, 'loss/train': 1.2133311033248901} 08/30/2021 19:44:30 - INFO - __main__ - Step 36154: {'lr': 0.0004371306646469445, 'samples': 6941568, 'steps': 36153, 'loss/train': 0.9220306873321533} 08/30/2021 19:44:30 - INFO - __main__ - Step 36155: {'lr': 0.00043712714565371315, 'samples': 6941760, 'steps': 36154, 'loss/train': 1.729306697845459} 08/30/2021 19:44:31 - INFO - __main__ - Step 36156: {'lr': 0.0004371236265761651, 'samples': 6941952, 'steps': 36155, 'loss/train': 1.8302483558654785} 08/30/2021 19:44:31 - INFO - __main__ - Step 36157: {'lr': 0.0004371201074143021, 'samples': 6942144, 'steps': 36156, 'loss/train': 1.705064296722412} 08/30/2021 19:44:31 - INFO - __main__ - Step 36158: {'lr': 0.0004371165881681256, 'samples': 6942336, 'steps': 36157, 'loss/train': 1.1303297281265259} 08/30/2021 19:44:33 - INFO - __main__ - Step 36159: {'lr': 0.0004371130688376373, 'samples': 6942528, 'steps': 36158, 'loss/train': 1.4892210960388184} 08/30/2021 19:44:34 - INFO - __main__ - Step 36160: {'lr': 0.00043710954942283875, 'samples': 6942720, 'steps': 36159, 'loss/train': 1.5749467611312866} 08/30/2021 19:44:34 - INFO - __main__ - Step 36161: {'lr': 0.0004371060299237315, 'samples': 6942912, 'steps': 36160, 'loss/train': 1.079881191253662} 08/30/2021 19:44:34 - INFO - __main__ - Step 36162: {'lr': 0.00043710251034031713, 'samples': 6943104, 'steps': 36161, 'loss/train': 1.4332362413406372} 08/30/2021 19:44:35 - INFO - __main__ - Step 36163: {'lr': 0.0004370989906725973, 'samples': 6943296, 'steps': 36162, 'loss/train': 1.3096790313720703} 08/30/2021 19:44:36 - INFO - __main__ - Step 36164: {'lr': 0.00043709547092057356, 'samples': 6943488, 'steps': 36163, 'loss/train': 0.06760528683662415} 08/30/2021 19:44:37 - INFO - __main__ - Step 36165: {'lr': 0.00043709195108424746, 'samples': 6943680, 'steps': 36164, 'loss/train': 1.3607068061828613} 08/30/2021 19:44:37 - INFO - __main__ - Step 36166: {'lr': 0.0004370884311636206, 'samples': 6943872, 'steps': 36165, 'loss/train': 1.660696268081665} 08/30/2021 19:44:37 - INFO - __main__ - Step 36167: {'lr': 0.0004370849111586946, 'samples': 6944064, 'steps': 36166, 'loss/train': 1.7609360218048096} 08/30/2021 19:44:38 - INFO - __main__ - Step 36168: {'lr': 0.000437081391069471, 'samples': 6944256, 'steps': 36167, 'loss/train': 1.4726663827896118} 08/30/2021 19:44:38 - INFO - __main__ - Step 36169: {'lr': 0.0004370778708959514, 'samples': 6944448, 'steps': 36168, 'loss/train': 1.277608036994934} 08/30/2021 19:44:40 - INFO - __main__ - Step 36170: {'lr': 0.00043707435063813747, 'samples': 6944640, 'steps': 36169, 'loss/train': 1.2327027320861816} 08/30/2021 19:44:40 - INFO - __main__ - Step 36171: {'lr': 0.0004370708302960307, 'samples': 6944832, 'steps': 36170, 'loss/train': 0.8638128042221069} 08/30/2021 19:44:40 - INFO - __main__ - Step 36172: {'lr': 0.00043706730986963274, 'samples': 6945024, 'steps': 36171, 'loss/train': 1.5289987325668335} 08/30/2021 19:44:41 - INFO - __main__ - Step 36173: {'lr': 0.0004370637893589451, 'samples': 6945216, 'steps': 36172, 'loss/train': 1.1286712884902954} 08/30/2021 19:44:41 - INFO - __main__ - Step 36174: {'lr': 0.0004370602687639693, 'samples': 6945408, 'steps': 36173, 'loss/train': 1.2298859357833862} 08/30/2021 19:44:43 - INFO - __main__ - Step 36175: {'lr': 0.00043705674808470715, 'samples': 6945600, 'steps': 36174, 'loss/train': 1.3916815519332886} 08/30/2021 19:44:44 - INFO - __main__ - Step 36176: {'lr': 0.00043705322732116007, 'samples': 6945792, 'steps': 36175, 'loss/train': 1.8155173063278198} 08/30/2021 19:44:44 - INFO - __main__ - Step 36177: {'lr': 0.00043704970647332977, 'samples': 6945984, 'steps': 36176, 'loss/train': 1.2930392026901245} 08/30/2021 19:44:44 - INFO - __main__ - Step 36178: {'lr': 0.00043704618554121766, 'samples': 6946176, 'steps': 36177, 'loss/train': 1.5829293727874756} 08/30/2021 19:44:45 - INFO - __main__ - Step 36179: {'lr': 0.0004370426645248254, 'samples': 6946368, 'steps': 36178, 'loss/train': 0.9655218124389648} 08/30/2021 19:44:46 - INFO - __main__ - Step 36180: {'lr': 0.00043703914342415473, 'samples': 6946560, 'steps': 36179, 'loss/train': 1.4457999467849731} 08/30/2021 19:44:47 - INFO - __main__ - Step 36181: {'lr': 0.000437035622239207, 'samples': 6946752, 'steps': 36180, 'loss/train': 1.3025232553482056} 08/30/2021 19:44:47 - INFO - __main__ - Step 36182: {'lr': 0.00043703210096998396, 'samples': 6946944, 'steps': 36181, 'loss/train': 1.5481994152069092} 08/30/2021 19:44:47 - INFO - __main__ - Step 36183: {'lr': 0.00043702857961648713, 'samples': 6947136, 'steps': 36182, 'loss/train': 0.7084340453147888} 08/30/2021 19:44:48 - INFO - __main__ - Step 36184: {'lr': 0.0004370250581787181, 'samples': 6947328, 'steps': 36183, 'loss/train': 1.3375695943832397} 08/30/2021 19:44:49 - INFO - __main__ - Step 36185: {'lr': 0.00043702153665667846, 'samples': 6947520, 'steps': 36184, 'loss/train': 1.5599709749221802} 08/30/2021 19:44:50 - INFO - __main__ - Step 36186: {'lr': 0.0004370180150503698, 'samples': 6947712, 'steps': 36185, 'loss/train': 1.7210819721221924} 08/30/2021 19:44:50 - INFO - __main__ - Step 36187: {'lr': 0.0004370144933597938, 'samples': 6947904, 'steps': 36186, 'loss/train': 0.1739286184310913} 08/30/2021 19:44:51 - INFO - __main__ - Step 36188: {'lr': 0.00043701097158495186, 'samples': 6948096, 'steps': 36187, 'loss/train': 1.976375699043274} 08/30/2021 19:44:51 - INFO - __main__ - Step 36189: {'lr': 0.0004370074497258456, 'samples': 6948288, 'steps': 36188, 'loss/train': 1.0812376737594604} 08/30/2021 19:44:52 - INFO - __main__ - Step 36190: {'lr': 0.00043700392778247676, 'samples': 6948480, 'steps': 36189, 'loss/train': 0.06739005446434021} 08/30/2021 19:44:53 - INFO - __main__ - Step 36191: {'lr': 0.0004370004057548468, 'samples': 6948672, 'steps': 36190, 'loss/train': 1.254050850868225} 08/30/2021 19:44:53 - INFO - __main__ - Step 36192: {'lr': 0.0004369968836429574, 'samples': 6948864, 'steps': 36191, 'loss/train': 1.595575213432312} 08/30/2021 19:44:53 - INFO - __main__ - Step 36193: {'lr': 0.0004369933614468101, 'samples': 6949056, 'steps': 36192, 'loss/train': 1.0041005611419678} 08/30/2021 19:44:54 - INFO - __main__ - Step 36194: {'lr': 0.0004369898391664064, 'samples': 6949248, 'steps': 36193, 'loss/train': 0.678227424621582} 08/30/2021 19:44:54 - INFO - __main__ - Step 36195: {'lr': 0.000436986316801748, 'samples': 6949440, 'steps': 36194, 'loss/train': 1.6307750940322876} 08/30/2021 19:44:56 - INFO - __main__ - Step 36196: {'lr': 0.00043698279435283637, 'samples': 6949632, 'steps': 36195, 'loss/train': 1.4718012809753418} 08/30/2021 19:44:56 - INFO - __main__ - Step 36197: {'lr': 0.0004369792718196733, 'samples': 6949824, 'steps': 36196, 'loss/train': 1.6100915670394897} 08/30/2021 19:44:56 - INFO - __main__ - Step 36198: {'lr': 0.0004369757492022602, 'samples': 6950016, 'steps': 36197, 'loss/train': 0.9444458484649658} 08/30/2021 19:44:57 - INFO - __main__ - Step 36199: {'lr': 0.00043697222650059876, 'samples': 6950208, 'steps': 36198, 'loss/train': 1.5574300289154053} 08/30/2021 19:44:57 - INFO - __main__ - Step 36200: {'lr': 0.00043696870371469045, 'samples': 6950400, 'steps': 36199, 'loss/train': 1.7513478994369507} 08/30/2021 19:44:59 - INFO - __main__ - Step 36201: {'lr': 0.000436965180844537, 'samples': 6950592, 'steps': 36200, 'loss/train': 1.6801937818527222} 08/30/2021 19:44:59 - INFO - __main__ - Step 36202: {'lr': 0.00043696165789013986, 'samples': 6950784, 'steps': 36201, 'loss/train': 1.6791130304336548} 08/30/2021 19:45:00 - INFO - __main__ - Step 36203: {'lr': 0.0004369581348515007, 'samples': 6950976, 'steps': 36202, 'loss/train': 1.7950574159622192} 08/30/2021 19:45:00 - INFO - __main__ - Step 36204: {'lr': 0.00043695461172862113, 'samples': 6951168, 'steps': 36203, 'loss/train': 1.4765222072601318} 08/30/2021 19:45:00 - INFO - __main__ - Step 36205: {'lr': 0.0004369510885215026, 'samples': 6951360, 'steps': 36204, 'loss/train': 1.7500945329666138} 08/30/2021 19:45:02 - INFO - __main__ - Step 36206: {'lr': 0.0004369475652301469, 'samples': 6951552, 'steps': 36205, 'loss/train': 1.255204677581787} 08/30/2021 19:45:02 - INFO - __main__ - Step 36207: {'lr': 0.0004369440418545555, 'samples': 6951744, 'steps': 36206, 'loss/train': 1.4784289598464966} 08/30/2021 19:45:03 - INFO - __main__ - Step 36208: {'lr': 0.00043694051839472995, 'samples': 6951936, 'steps': 36207, 'loss/train': 1.869343638420105} 08/30/2021 19:45:03 - INFO - __main__ - Step 36209: {'lr': 0.00043693699485067186, 'samples': 6952128, 'steps': 36208, 'loss/train': 1.2865989208221436} 08/30/2021 19:45:03 - INFO - __main__ - Step 36210: {'lr': 0.0004369334712223829, 'samples': 6952320, 'steps': 36209, 'loss/train': 1.4650505781173706} 08/30/2021 19:45:05 - INFO - __main__ - Step 36211: {'lr': 0.0004369299475098646, 'samples': 6952512, 'steps': 36210, 'loss/train': 1.2392257452011108} 08/30/2021 19:45:05 - INFO - __main__ - Step 36212: {'lr': 0.00043692642371311854, 'samples': 6952704, 'steps': 36211, 'loss/train': 1.435381531715393} 08/30/2021 19:45:06 - INFO - __main__ - Step 36213: {'lr': 0.00043692289983214626, 'samples': 6952896, 'steps': 36212, 'loss/train': 1.03143310546875} 08/30/2021 19:45:06 - INFO - __main__ - Step 36214: {'lr': 0.0004369193758669495, 'samples': 6953088, 'steps': 36213, 'loss/train': 1.5595673322677612} 08/30/2021 19:45:06 - INFO - __main__ - Step 36215: {'lr': 0.0004369158518175297, 'samples': 6953280, 'steps': 36214, 'loss/train': 1.5154434442520142} 08/30/2021 19:45:07 - INFO - __main__ - Step 36216: {'lr': 0.00043691232768388856, 'samples': 6953472, 'steps': 36215, 'loss/train': 1.42335045337677} 08/30/2021 19:45:09 - INFO - __main__ - Step 36217: {'lr': 0.00043690880346602755, 'samples': 6953664, 'steps': 36216, 'loss/train': 1.2866326570510864} 08/30/2021 19:45:09 - INFO - __main__ - Step 36218: {'lr': 0.0004369052791639483, 'samples': 6953856, 'steps': 36217, 'loss/train': 1.5749741792678833} 08/30/2021 19:45:09 - INFO - __main__ - Step 36219: {'lr': 0.0004369017547776525, 'samples': 6954048, 'steps': 36218, 'loss/train': 1.0419127941131592} 08/30/2021 19:45:10 - INFO - __main__ - Step 36220: {'lr': 0.0004368982303071416, 'samples': 6954240, 'steps': 36219, 'loss/train': 0.9410125613212585} 08/30/2021 19:45:10 - INFO - __main__ - Step 36221: {'lr': 0.0004368947057524173, 'samples': 6954432, 'steps': 36220, 'loss/train': 0.1284305900335312} 08/30/2021 19:45:12 - INFO - __main__ - Step 36222: {'lr': 0.00043689118111348105, 'samples': 6954624, 'steps': 36221, 'loss/train': 1.5536609888076782} 08/30/2021 19:45:12 - INFO - __main__ - Step 36223: {'lr': 0.00043688765639033456, 'samples': 6954816, 'steps': 36222, 'loss/train': 0.5226022005081177} 08/30/2021 19:45:12 - INFO - __main__ - Step 36224: {'lr': 0.00043688413158297934, 'samples': 6955008, 'steps': 36223, 'loss/train': 1.2744625806808472} 08/30/2021 19:45:13 - INFO - __main__ - Step 36225: {'lr': 0.00043688060669141705, 'samples': 6955200, 'steps': 36224, 'loss/train': 1.3792767524719238} 08/30/2021 19:45:13 - INFO - __main__ - Step 36226: {'lr': 0.00043687708171564923, 'samples': 6955392, 'steps': 36225, 'loss/train': 1.159806489944458} 08/30/2021 19:45:15 - INFO - __main__ - Step 36227: {'lr': 0.00043687355665567745, 'samples': 6955584, 'steps': 36226, 'loss/train': 1.1828851699829102} 08/30/2021 19:45:16 - INFO - __main__ - Step 36228: {'lr': 0.0004368700315115034, 'samples': 6955776, 'steps': 36227, 'loss/train': 1.8451720476150513} 08/30/2021 19:45:16 - INFO - __main__ - Step 36229: {'lr': 0.00043686650628312854, 'samples': 6955968, 'steps': 36228, 'loss/train': 1.1378953456878662} 08/30/2021 19:45:16 - INFO - __main__ - Step 36230: {'lr': 0.00043686298097055456, 'samples': 6956160, 'steps': 36229, 'loss/train': 1.9758963584899902} 08/30/2021 19:45:17 - INFO - __main__ - Step 36231: {'lr': 0.0004368594555737829, 'samples': 6956352, 'steps': 36230, 'loss/train': 1.3730993270874023} 08/30/2021 19:45:18 - INFO - __main__ - Step 36232: {'lr': 0.0004368559300928153, 'samples': 6956544, 'steps': 36231, 'loss/train': 1.512043833732605} 08/30/2021 19:45:19 - INFO - __main__ - Step 36233: {'lr': 0.0004368524045276534, 'samples': 6956736, 'steps': 36232, 'loss/train': 1.282394289970398} 08/30/2021 19:45:19 - INFO - __main__ - Step 36234: {'lr': 0.00043684887887829863, 'samples': 6956928, 'steps': 36233, 'loss/train': 2.2907588481903076} 08/30/2021 19:45:19 - INFO - __main__ - Step 36235: {'lr': 0.0004368453531447526, 'samples': 6957120, 'steps': 36234, 'loss/train': 1.3599456548690796} 08/30/2021 19:45:20 - INFO - __main__ - Step 36236: {'lr': 0.00043684182732701694, 'samples': 6957312, 'steps': 36235, 'loss/train': 1.5863093137741089} 08/30/2021 19:45:21 - INFO - __main__ - Step 36237: {'lr': 0.00043683830142509327, 'samples': 6957504, 'steps': 36236, 'loss/train': 1.5000536441802979} 08/30/2021 19:45:22 - INFO - __main__ - Step 36238: {'lr': 0.00043683477543898314, 'samples': 6957696, 'steps': 36237, 'loss/train': 1.005483627319336} 08/30/2021 19:45:22 - INFO - __main__ - Step 36239: {'lr': 0.0004368312493686881, 'samples': 6957888, 'steps': 36238, 'loss/train': 0.786897599697113} 08/30/2021 19:45:23 - INFO - __main__ - Step 36240: {'lr': 0.0004368277232142098, 'samples': 6958080, 'steps': 36239, 'loss/train': 1.2815017700195312} 08/30/2021 19:45:23 - INFO - __main__ - Step 36241: {'lr': 0.00043682419697554985, 'samples': 6958272, 'steps': 36240, 'loss/train': 0.2626532316207886} 08/30/2021 19:45:25 - INFO - __main__ - Step 36242: {'lr': 0.0004368206706527098, 'samples': 6958464, 'steps': 36241, 'loss/train': 1.5950918197631836} 08/30/2021 19:45:26 - INFO - __main__ - Step 36243: {'lr': 0.00043681714424569117, 'samples': 6958656, 'steps': 36242, 'loss/train': 0.9098647832870483} 08/30/2021 19:45:26 - INFO - __main__ - Step 36244: {'lr': 0.0004368136177544957, 'samples': 6958848, 'steps': 36243, 'loss/train': 1.3512158393859863} 08/30/2021 19:45:26 - INFO - __main__ - Step 36245: {'lr': 0.00043681009117912484, 'samples': 6959040, 'steps': 36244, 'loss/train': 1.772580862045288} 08/30/2021 19:45:27 - INFO - __main__ - Step 36246: {'lr': 0.0004368065645195803, 'samples': 6959232, 'steps': 36245, 'loss/train': 1.6935904026031494} 08/30/2021 19:45:27 - INFO - __main__ - Step 36247: {'lr': 0.0004368030377758636, 'samples': 6959424, 'steps': 36246, 'loss/train': 1.2961620092391968} 08/30/2021 19:45:27 - INFO - __main__ - Step 36248: {'lr': 0.0004367995109479763, 'samples': 6959616, 'steps': 36247, 'loss/train': 1.5124505758285522} 08/30/2021 19:45:29 - INFO - __main__ - Step 36249: {'lr': 0.00043679598403592, 'samples': 6959808, 'steps': 36248, 'loss/train': 0.9172031283378601} 08/30/2021 19:45:29 - INFO - __main__ - Step 36250: {'lr': 0.00043679245703969627, 'samples': 6960000, 'steps': 36249, 'loss/train': 1.30707848072052} 08/30/2021 19:45:30 - INFO - __main__ - Step 36251: {'lr': 0.00043678892995930685, 'samples': 6960192, 'steps': 36250, 'loss/train': 1.4898329973220825} 08/30/2021 19:45:30 - INFO - __main__ - Step 36252: {'lr': 0.00043678540279475314, 'samples': 6960384, 'steps': 36251, 'loss/train': 1.596374750137329} 08/30/2021 19:45:30 - INFO - __main__ - Step 36253: {'lr': 0.0004367818755460369, 'samples': 6960576, 'steps': 36252, 'loss/train': 0.13209521770477295} 08/30/2021 19:45:32 - INFO - __main__ - Step 36254: {'lr': 0.00043677834821315956, 'samples': 6960768, 'steps': 36253, 'loss/train': 1.007800579071045} 08/30/2021 19:45:32 - INFO - __main__ - Step 36255: {'lr': 0.00043677482079612276, 'samples': 6960960, 'steps': 36254, 'loss/train': 1.576393961906433} 08/30/2021 19:45:33 - INFO - __main__ - Step 36256: {'lr': 0.00043677129329492814, 'samples': 6961152, 'steps': 36255, 'loss/train': 1.7132619619369507} 08/30/2021 19:45:33 - INFO - __main__ - Step 36257: {'lr': 0.00043676776570957725, 'samples': 6961344, 'steps': 36256, 'loss/train': 1.5446170568466187} 08/30/2021 19:45:33 - INFO - __main__ - Step 36258: {'lr': 0.0004367642380400717, 'samples': 6961536, 'steps': 36257, 'loss/train': 1.608413815498352} 08/30/2021 19:45:34 - INFO - __main__ - Step 36259: {'lr': 0.0004367607102864131, 'samples': 6961728, 'steps': 36258, 'loss/train': 1.252132534980774} 08/30/2021 19:45:35 - INFO - __main__ - Step 36260: {'lr': 0.00043675718244860296, 'samples': 6961920, 'steps': 36259, 'loss/train': 2.2234764099121094} 08/30/2021 19:45:36 - INFO - __main__ - Step 36261: {'lr': 0.00043675365452664286, 'samples': 6962112, 'steps': 36260, 'loss/train': 1.8667486906051636} 08/30/2021 19:45:36 - INFO - __main__ - Step 36262: {'lr': 0.0004367501265205345, 'samples': 6962304, 'steps': 36261, 'loss/train': 1.3845876455307007} 08/30/2021 19:45:36 - INFO - __main__ - Step 36263: {'lr': 0.0004367465984302794, 'samples': 6962496, 'steps': 36262, 'loss/train': 1.7512222528457642} 08/30/2021 19:45:37 - INFO - __main__ - Step 36264: {'lr': 0.0004367430702558792, 'samples': 6962688, 'steps': 36263, 'loss/train': 1.561260461807251} 08/30/2021 19:45:39 - INFO - __main__ - Step 36265: {'lr': 0.0004367395419973355, 'samples': 6962880, 'steps': 36264, 'loss/train': 1.352837324142456} 08/30/2021 19:45:39 - INFO - __main__ - Step 36266: {'lr': 0.00043673601365464975, 'samples': 6963072, 'steps': 36265, 'loss/train': 1.7692322731018066} 08/30/2021 19:45:39 - INFO - __main__ - Step 36267: {'lr': 0.00043673248522782364, 'samples': 6963264, 'steps': 36266, 'loss/train': 1.645789623260498} 08/30/2021 19:45:40 - INFO - __main__ - Step 36268: {'lr': 0.0004367289567168588, 'samples': 6963456, 'steps': 36267, 'loss/train': 0.10028726607561111} 08/30/2021 19:45:40 - INFO - __main__ - Step 36269: {'lr': 0.00043672542812175675, 'samples': 6963648, 'steps': 36268, 'loss/train': 0.47563982009887695} 08/30/2021 19:45:40 - INFO - __main__ - Step 36270: {'lr': 0.00043672189944251905, 'samples': 6963840, 'steps': 36269, 'loss/train': 1.2824796438217163} 08/30/2021 19:45:42 - INFO - __main__ - Step 36271: {'lr': 0.0004367183706791474, 'samples': 6964032, 'steps': 36270, 'loss/train': 1.4002498388290405} 08/30/2021 19:45:43 - INFO - __main__ - Step 36272: {'lr': 0.0004367148418316434, 'samples': 6964224, 'steps': 36271, 'loss/train': 1.5807998180389404} 08/30/2021 19:45:43 - INFO - __main__ - Step 36273: {'lr': 0.0004367113129000085, 'samples': 6964416, 'steps': 36272, 'loss/train': 1.772133708000183} 08/30/2021 19:45:43 - INFO - __main__ - Step 36274: {'lr': 0.00043670778388424434, 'samples': 6964608, 'steps': 36273, 'loss/train': 1.4267396926879883} 08/30/2021 19:45:44 - INFO - __main__ - Step 36275: {'lr': 0.00043670425478435263, 'samples': 6964800, 'steps': 36274, 'loss/train': 1.4207713603973389} 08/30/2021 19:45:45 - INFO - __main__ - Step 36276: {'lr': 0.00043670072560033474, 'samples': 6964992, 'steps': 36275, 'loss/train': 1.940977931022644} 08/30/2021 19:45:46 - INFO - __main__ - Step 36277: {'lr': 0.00043669719633219247, 'samples': 6965184, 'steps': 36276, 'loss/train': 1.104358434677124} 08/30/2021 19:45:46 - INFO - __main__ - Step 36278: {'lr': 0.0004366936669799273, 'samples': 6965376, 'steps': 36277, 'loss/train': 1.3936634063720703} 08/30/2021 19:45:46 - INFO - __main__ - Step 36279: {'lr': 0.0004366901375435408, 'samples': 6965568, 'steps': 36278, 'loss/train': 0.5173631310462952} 08/30/2021 19:45:47 - INFO - __main__ - Step 36280: {'lr': 0.0004366866080230347, 'samples': 6965760, 'steps': 36279, 'loss/train': 1.362754464149475} 08/30/2021 19:45:49 - INFO - __main__ - Step 36281: {'lr': 0.0004366830784184104, 'samples': 6965952, 'steps': 36280, 'loss/train': 0.9476340413093567} 08/30/2021 19:45:49 - INFO - __main__ - Step 36282: {'lr': 0.00043667954872966965, 'samples': 6966144, 'steps': 36281, 'loss/train': 1.6118483543395996} 08/30/2021 19:45:49 - INFO - __main__ - Step 36283: {'lr': 0.000436676018956814, 'samples': 6966336, 'steps': 36282, 'loss/train': 1.2911791801452637} 08/30/2021 19:45:50 - INFO - __main__ - Step 36284: {'lr': 0.0004366724890998449, 'samples': 6966528, 'steps': 36283, 'loss/train': 1.72792649269104} 08/30/2021 19:45:50 - INFO - __main__ - Step 36285: {'lr': 0.00043666895915876416, 'samples': 6966720, 'steps': 36284, 'loss/train': 1.0139909982681274} 08/30/2021 19:45:51 - INFO - __main__ - Step 36286: {'lr': 0.0004366654291335732, 'samples': 6966912, 'steps': 36285, 'loss/train': 2.0946671962738037} 08/30/2021 19:45:52 - INFO - __main__ - Step 36287: {'lr': 0.00043666189902427367, 'samples': 6967104, 'steps': 36286, 'loss/train': 1.5928480625152588} 08/30/2021 19:45:52 - INFO - __main__ - Step 36288: {'lr': 0.00043665836883086725, 'samples': 6967296, 'steps': 36287, 'loss/train': 1.501845359802246} 08/30/2021 19:45:53 - INFO - __main__ - Step 36289: {'lr': 0.0004366548385533554, 'samples': 6967488, 'steps': 36288, 'loss/train': 1.6620104312896729} 08/30/2021 19:45:53 - INFO - __main__ - Step 36290: {'lr': 0.0004366513081917398, 'samples': 6967680, 'steps': 36289, 'loss/train': 1.5876080989837646} 08/30/2021 19:45:54 - INFO - __main__ - Step 36291: {'lr': 0.00043664777774602196, 'samples': 6967872, 'steps': 36290, 'loss/train': 1.1251871585845947} 08/30/2021 19:45:55 - INFO - __main__ - Step 36292: {'lr': 0.00043664424721620354, 'samples': 6968064, 'steps': 36291, 'loss/train': 1.3264949321746826} 08/30/2021 19:45:55 - INFO - __main__ - Step 36293: {'lr': 0.00043664071660228605, 'samples': 6968256, 'steps': 36292, 'loss/train': 1.2746326923370361} 08/30/2021 19:45:56 - INFO - __main__ - Step 36294: {'lr': 0.00043663718590427117, 'samples': 6968448, 'steps': 36293, 'loss/train': 1.3966554403305054} 08/30/2021 19:45:56 - INFO - __main__ - Step 36295: {'lr': 0.0004366336551221605, 'samples': 6968640, 'steps': 36294, 'loss/train': 1.408300757408142} 08/30/2021 19:45:56 - INFO - __main__ - Step 36296: {'lr': 0.0004366301242559555, 'samples': 6968832, 'steps': 36295, 'loss/train': 1.7586427927017212} 08/30/2021 19:45:59 - INFO - __main__ - Step 36297: {'lr': 0.00043662659330565793, 'samples': 6969024, 'steps': 36296, 'loss/train': 0.875842273235321} 08/30/2021 19:45:59 - INFO - __main__ - Step 36298: {'lr': 0.00043662306227126917, 'samples': 6969216, 'steps': 36297, 'loss/train': 0.8898364305496216} 08/30/2021 19:45:59 - INFO - __main__ - Step 36299: {'lr': 0.00043661953115279104, 'samples': 6969408, 'steps': 36298, 'loss/train': 1.5504984855651855} 08/30/2021 19:46:00 - INFO - __main__ - Step 36300: {'lr': 0.000436615999950225, 'samples': 6969600, 'steps': 36299, 'loss/train': 0.1926325410604477} 08/30/2021 19:46:00 - INFO - __main__ - Step 36301: {'lr': 0.0004366124686635727, 'samples': 6969792, 'steps': 36300, 'loss/train': 2.0592730045318604} 08/30/2021 19:46:02 - INFO - __main__ - Step 36302: {'lr': 0.00043660893729283564, 'samples': 6969984, 'steps': 36301, 'loss/train': 1.6141204833984375} 08/30/2021 19:46:02 - INFO - __main__ - Step 36303: {'lr': 0.0004366054058380155, 'samples': 6970176, 'steps': 36302, 'loss/train': 1.7512975931167603} 08/30/2021 19:46:02 - INFO - __main__ - Step 36304: {'lr': 0.0004366018742991139, 'samples': 6970368, 'steps': 36303, 'loss/train': 0.26098498702049255} 08/30/2021 19:46:03 - INFO - __main__ - Step 36305: {'lr': 0.00043659834267613227, 'samples': 6970560, 'steps': 36304, 'loss/train': 1.9825482368469238} 08/30/2021 19:46:03 - INFO - __main__ - Step 36306: {'lr': 0.0004365948109690724, 'samples': 6970752, 'steps': 36305, 'loss/train': 1.3607426881790161} 08/30/2021 19:46:05 - INFO - __main__ - Step 36307: {'lr': 0.0004365912791779357, 'samples': 6970944, 'steps': 36306, 'loss/train': 1.9683040380477905} 08/30/2021 19:46:05 - INFO - __main__ - Step 36308: {'lr': 0.00043658774730272393, 'samples': 6971136, 'steps': 36307, 'loss/train': 1.0265824794769287} 08/30/2021 19:46:05 - INFO - __main__ - Step 36309: {'lr': 0.00043658421534343856, 'samples': 6971328, 'steps': 36308, 'loss/train': 1.1142578125} 08/30/2021 19:46:06 - INFO - __main__ - Step 36310: {'lr': 0.0004365806833000813, 'samples': 6971520, 'steps': 36309, 'loss/train': 1.6549283266067505} 08/30/2021 19:46:06 - INFO - __main__ - Step 36311: {'lr': 0.0004365771511726535, 'samples': 6971712, 'steps': 36310, 'loss/train': 1.6925839185714722} 08/30/2021 19:46:08 - INFO - __main__ - Step 36312: {'lr': 0.00043657361896115706, 'samples': 6971904, 'steps': 36311, 'loss/train': 1.011309266090393} 08/30/2021 19:46:08 - INFO - __main__ - Step 36313: {'lr': 0.0004365700866655934, 'samples': 6972096, 'steps': 36312, 'loss/train': 1.3822884559631348} 08/30/2021 19:46:09 - INFO - __main__ - Step 36314: {'lr': 0.00043656655428596407, 'samples': 6972288, 'steps': 36313, 'loss/train': 1.634024977684021} 08/30/2021 19:46:09 - INFO - __main__ - Step 36315: {'lr': 0.0004365630218222708, 'samples': 6972480, 'steps': 36314, 'loss/train': 1.1251134872436523} 08/30/2021 19:46:09 - INFO - __main__ - Step 36316: {'lr': 0.00043655948927451505, 'samples': 6972672, 'steps': 36315, 'loss/train': 1.1436549425125122} 08/30/2021 19:46:10 - INFO - __main__ - Step 36317: {'lr': 0.0004365559566426985, 'samples': 6972864, 'steps': 36316, 'loss/train': 0.9091794490814209} 08/30/2021 19:46:11 - INFO - __main__ - Step 36318: {'lr': 0.0004365524239268227, 'samples': 6973056, 'steps': 36317, 'loss/train': 1.8467167615890503} 08/30/2021 19:46:12 - INFO - __main__ - Step 36319: {'lr': 0.00043654889112688933, 'samples': 6973248, 'steps': 36318, 'loss/train': 1.1432421207427979} 08/30/2021 19:46:12 - INFO - __main__ - Step 36320: {'lr': 0.00043654535824289985, 'samples': 6973440, 'steps': 36319, 'loss/train': 1.821355938911438} 08/30/2021 19:46:12 - INFO - __main__ - Step 36321: {'lr': 0.0004365418252748559, 'samples': 6973632, 'steps': 36320, 'loss/train': 0.08417873829603195} 08/30/2021 19:46:13 - INFO - __main__ - Step 36322: {'lr': 0.0004365382922227591, 'samples': 6973824, 'steps': 36321, 'loss/train': 1.5863474607467651} 08/30/2021 19:46:14 - INFO - __main__ - Step 36323: {'lr': 0.000436534759086611, 'samples': 6974016, 'steps': 36322, 'loss/train': 0.971802830696106} 08/30/2021 19:46:15 - INFO - __main__ - Step 36324: {'lr': 0.00043653122586641323, 'samples': 6974208, 'steps': 36323, 'loss/train': 1.5479087829589844} 08/30/2021 19:46:15 - INFO - __main__ - Step 36325: {'lr': 0.0004365276925621674, 'samples': 6974400, 'steps': 36324, 'loss/train': 1.3704218864440918} 08/30/2021 19:46:16 - INFO - __main__ - Step 36326: {'lr': 0.0004365241591738751, 'samples': 6974592, 'steps': 36325, 'loss/train': 1.4487746953964233} 08/30/2021 19:46:16 - INFO - __main__ - Step 36327: {'lr': 0.0004365206257015378, 'samples': 6974784, 'steps': 36326, 'loss/train': 0.9230908751487732} 08/30/2021 19:46:18 - INFO - __main__ - Step 36328: {'lr': 0.0004365170921451572, 'samples': 6974976, 'steps': 36327, 'loss/train': 2.0408403873443604} 08/30/2021 19:46:18 - INFO - __main__ - Step 36329: {'lr': 0.00043651355850473495, 'samples': 6975168, 'steps': 36328, 'loss/train': 0.9604093432426453} 08/30/2021 19:46:18 - INFO - __main__ - Step 36330: {'lr': 0.0004365100247802725, 'samples': 6975360, 'steps': 36329, 'loss/train': 5.837498188018799} 08/30/2021 19:46:19 - INFO - __main__ - Step 36331: {'lr': 0.0004365064909717715, 'samples': 6975552, 'steps': 36330, 'loss/train': 1.7468425035476685} 08/30/2021 19:46:19 - INFO - __main__ - Step 36332: {'lr': 0.0004365029570792336, 'samples': 6975744, 'steps': 36331, 'loss/train': 1.1854568719863892} 08/30/2021 19:46:19 - INFO - __main__ - Step 36333: {'lr': 0.00043649942310266035, 'samples': 6975936, 'steps': 36332, 'loss/train': 1.463685393333435} 08/30/2021 19:46:21 - INFO - __main__ - Step 36334: {'lr': 0.00043649588904205326, 'samples': 6976128, 'steps': 36333, 'loss/train': 1.4908409118652344} 08/30/2021 19:46:21 - INFO - __main__ - Step 36335: {'lr': 0.0004364923548974141, 'samples': 6976320, 'steps': 36334, 'loss/train': 1.406709909439087} 08/30/2021 19:46:22 - INFO - __main__ - Step 36336: {'lr': 0.0004364888206687443, 'samples': 6976512, 'steps': 36335, 'loss/train': 1.4437986612319946} 08/30/2021 19:46:22 - INFO - __main__ - Step 36337: {'lr': 0.00043648528635604556, 'samples': 6976704, 'steps': 36336, 'loss/train': 1.535369634628296} 08/30/2021 19:46:22 - INFO - __main__ - Step 36338: {'lr': 0.00043648175195931937, 'samples': 6976896, 'steps': 36337, 'loss/train': 1.943576693534851} 08/30/2021 19:46:24 - INFO - __main__ - Step 36339: {'lr': 0.0004364782174785674, 'samples': 6977088, 'steps': 36338, 'loss/train': 1.0343637466430664} 08/30/2021 19:46:25 - INFO - __main__ - Step 36340: {'lr': 0.0004364746829137912, 'samples': 6977280, 'steps': 36339, 'loss/train': 1.1846541166305542} 08/30/2021 19:46:25 - INFO - __main__ - Step 36341: {'lr': 0.0004364711482649925, 'samples': 6977472, 'steps': 36340, 'loss/train': 1.517400860786438} 08/30/2021 19:46:26 - INFO - __main__ - Step 36342: {'lr': 0.00043646761353217266, 'samples': 6977664, 'steps': 36341, 'loss/train': 1.5300853252410889} 08/30/2021 19:46:26 - INFO - __main__ - Step 36343: {'lr': 0.0004364640787153334, 'samples': 6977856, 'steps': 36342, 'loss/train': 0.7770493626594543} 08/30/2021 19:46:27 - INFO - __main__ - Step 36344: {'lr': 0.0004364605438144764, 'samples': 6978048, 'steps': 36343, 'loss/train': 0.9535834789276123} 08/30/2021 19:46:28 - INFO - __main__ - Step 36345: {'lr': 0.000436457008829603, 'samples': 6978240, 'steps': 36344, 'loss/train': 1.6743377447128296} 08/30/2021 19:46:28 - INFO - __main__ - Step 36346: {'lr': 0.00043645347376071507, 'samples': 6978432, 'steps': 36345, 'loss/train': 1.1523141860961914} 08/30/2021 19:46:29 - INFO - __main__ - Step 36347: {'lr': 0.0004364499386078141, 'samples': 6978624, 'steps': 36346, 'loss/train': 1.6288502216339111} 08/30/2021 19:46:29 - INFO - __main__ - Step 36348: {'lr': 0.00043644640337090157, 'samples': 6978816, 'steps': 36347, 'loss/train': 1.502032995223999} 08/30/2021 19:46:29 - INFO - __main__ - Step 36349: {'lr': 0.0004364428680499792, 'samples': 6979008, 'steps': 36348, 'loss/train': 1.5496554374694824} 08/30/2021 19:46:31 - INFO - __main__ - Step 36350: {'lr': 0.0004364393326450486, 'samples': 6979200, 'steps': 36349, 'loss/train': 1.6158000230789185} 08/30/2021 19:46:31 - INFO - __main__ - Step 36351: {'lr': 0.00043643579715611124, 'samples': 6979392, 'steps': 36350, 'loss/train': 2.336977005004883} 08/30/2021 19:46:32 - INFO - __main__ - Step 36352: {'lr': 0.00043643226158316886, 'samples': 6979584, 'steps': 36351, 'loss/train': 2.0129332542419434} 08/30/2021 19:46:32 - INFO - __main__ - Step 36353: {'lr': 0.00043642872592622293, 'samples': 6979776, 'steps': 36352, 'loss/train': 1.4041097164154053} 08/30/2021 19:46:32 - INFO - __main__ - Step 36354: {'lr': 0.0004364251901852751, 'samples': 6979968, 'steps': 36353, 'loss/train': 0.8781626224517822} 08/30/2021 19:46:34 - INFO - __main__ - Step 36355: {'lr': 0.000436421654360327, 'samples': 6980160, 'steps': 36354, 'loss/train': 1.2388808727264404} 08/30/2021 19:46:34 - INFO - __main__ - Step 36356: {'lr': 0.00043641811845138016, 'samples': 6980352, 'steps': 36355, 'loss/train': 2.17956280708313} 08/30/2021 19:46:35 - INFO - __main__ - Step 36357: {'lr': 0.0004364145824584361, 'samples': 6980544, 'steps': 36356, 'loss/train': 1.1740961074829102} 08/30/2021 19:46:35 - INFO - __main__ - Step 36358: {'lr': 0.00043641104638149656, 'samples': 6980736, 'steps': 36357, 'loss/train': 1.27120041847229} 08/30/2021 19:46:35 - INFO - __main__ - Step 36359: {'lr': 0.00043640751022056316, 'samples': 6980928, 'steps': 36358, 'loss/train': 1.6762738227844238} 08/30/2021 19:46:37 - INFO - __main__ - Step 36360: {'lr': 0.00043640397397563737, 'samples': 6981120, 'steps': 36359, 'loss/train': 1.1005442142486572} 08/30/2021 19:46:37 - INFO - __main__ - Step 36361: {'lr': 0.00043640043764672077, 'samples': 6981312, 'steps': 36360, 'loss/train': 1.5166518688201904} 08/30/2021 19:46:38 - INFO - __main__ - Step 36362: {'lr': 0.00043639690123381503, 'samples': 6981504, 'steps': 36361, 'loss/train': 1.233532190322876} 08/30/2021 19:46:38 - INFO - __main__ - Step 36363: {'lr': 0.00043639336473692174, 'samples': 6981696, 'steps': 36362, 'loss/train': 1.1842894554138184} 08/30/2021 19:46:38 - INFO - __main__ - Step 36364: {'lr': 0.00043638982815604247, 'samples': 6981888, 'steps': 36363, 'loss/train': 1.7364468574523926} 08/30/2021 19:46:39 - INFO - __main__ - Step 36365: {'lr': 0.00043638629149117883, 'samples': 6982080, 'steps': 36364, 'loss/train': 1.4133139848709106} 08/30/2021 19:46:40 - INFO - __main__ - Step 36366: {'lr': 0.0004363827547423324, 'samples': 6982272, 'steps': 36365, 'loss/train': 1.4663580656051636} 08/30/2021 19:46:41 - INFO - __main__ - Step 36367: {'lr': 0.00043637921790950476, 'samples': 6982464, 'steps': 36366, 'loss/train': 0.044430457055568695} 08/30/2021 19:46:41 - INFO - __main__ - Step 36368: {'lr': 0.00043637568099269753, 'samples': 6982656, 'steps': 36367, 'loss/train': 1.4652724266052246} 08/30/2021 19:46:41 - INFO - __main__ - Step 36369: {'lr': 0.00043637214399191234, 'samples': 6982848, 'steps': 36368, 'loss/train': 1.1841883659362793} 08/30/2021 19:46:42 - INFO - __main__ - Step 36370: {'lr': 0.00043636860690715064, 'samples': 6983040, 'steps': 36369, 'loss/train': 1.732420802116394} 08/30/2021 19:46:43 - INFO - __main__ - Step 36371: {'lr': 0.00043636506973841424, 'samples': 6983232, 'steps': 36370, 'loss/train': 1.3470722436904907} 08/30/2021 19:46:44 - INFO - __main__ - Step 36372: {'lr': 0.00043636153248570453, 'samples': 6983424, 'steps': 36371, 'loss/train': 0.8544849753379822} 08/30/2021 19:46:44 - INFO - __main__ - Step 36373: {'lr': 0.0004363579951490232, 'samples': 6983616, 'steps': 36372, 'loss/train': 1.2581340074539185} 08/30/2021 19:46:44 - INFO - __main__ - Step 36374: {'lr': 0.0004363544577283718, 'samples': 6983808, 'steps': 36373, 'loss/train': 0.6959117650985718} 08/30/2021 19:46:45 - INFO - __main__ - Step 36375: {'lr': 0.0004363509202237521, 'samples': 6984000, 'steps': 36374, 'loss/train': 1.0700585842132568} 08/30/2021 19:46:46 - INFO - __main__ - Step 36376: {'lr': 0.0004363473826351654, 'samples': 6984192, 'steps': 36375, 'loss/train': 1.657585859298706} 08/30/2021 19:46:47 - INFO - __main__ - Step 36377: {'lr': 0.0004363438449626135, 'samples': 6984384, 'steps': 36376, 'loss/train': 1.5339055061340332} 08/30/2021 19:46:47 - INFO - __main__ - Step 36378: {'lr': 0.000436340307206098, 'samples': 6984576, 'steps': 36377, 'loss/train': 1.1779080629348755} 08/30/2021 19:46:47 - INFO - __main__ - Step 36379: {'lr': 0.00043633676936562026, 'samples': 6984768, 'steps': 36378, 'loss/train': 0.8532932996749878} 08/30/2021 19:46:48 - INFO - __main__ - Step 36380: {'lr': 0.0004363332314411822, 'samples': 6984960, 'steps': 36379, 'loss/train': 1.6608859300613403} 08/30/2021 19:46:49 - INFO - __main__ - Step 36381: {'lr': 0.0004363296934327852, 'samples': 6985152, 'steps': 36380, 'loss/train': 2.0106258392333984} 08/30/2021 19:46:50 - INFO - __main__ - Step 36382: {'lr': 0.00043632615534043096, 'samples': 6985344, 'steps': 36381, 'loss/train': 1.5246495008468628} 08/30/2021 19:46:50 - INFO - __main__ - Step 36383: {'lr': 0.00043632261716412097, 'samples': 6985536, 'steps': 36382, 'loss/train': 1.2977567911148071} 08/30/2021 19:46:50 - INFO - __main__ - Step 36384: {'lr': 0.0004363190789038569, 'samples': 6985728, 'steps': 36383, 'loss/train': 0.9314844608306885} 08/30/2021 19:46:51 - INFO - __main__ - Step 36385: {'lr': 0.0004363155405596404, 'samples': 6985920, 'steps': 36384, 'loss/train': 1.174365758895874} 08/30/2021 19:46:52 - INFO - __main__ - Step 36386: {'lr': 0.00043631200213147296, 'samples': 6986112, 'steps': 36385, 'loss/train': 1.2470765113830566} 08/30/2021 19:46:52 - INFO - __main__ - Step 36387: {'lr': 0.0004363084636193561, 'samples': 6986304, 'steps': 36386, 'loss/train': 1.5699836015701294} 08/30/2021 19:46:53 - INFO - __main__ - Step 36388: {'lr': 0.0004363049250232917, 'samples': 6986496, 'steps': 36387, 'loss/train': 1.5065574645996094} 08/30/2021 19:46:53 - INFO - __main__ - Step 36389: {'lr': 0.000436301386343281, 'samples': 6986688, 'steps': 36388, 'loss/train': 0.9250494837760925} 08/30/2021 19:46:54 - INFO - __main__ - Step 36390: {'lr': 0.0004362978475793259, 'samples': 6986880, 'steps': 36389, 'loss/train': 1.5851961374282837} 08/30/2021 19:46:56 - INFO - __main__ - Step 36391: {'lr': 0.00043629430873142773, 'samples': 6987072, 'steps': 36390, 'loss/train': 0.9763813018798828} 08/30/2021 19:46:56 - INFO - __main__ - Step 36392: {'lr': 0.00043629076979958837, 'samples': 6987264, 'steps': 36391, 'loss/train': 1.4903507232666016} 08/30/2021 19:46:56 - INFO - __main__ - Step 36393: {'lr': 0.00043628723078380916, 'samples': 6987456, 'steps': 36392, 'loss/train': 1.2402701377868652} 08/30/2021 19:46:57 - INFO - __main__ - Step 36394: {'lr': 0.0004362836916840919, 'samples': 6987648, 'steps': 36393, 'loss/train': 1.290327787399292} 08/30/2021 19:46:57 - INFO - __main__ - Step 36395: {'lr': 0.00043628015250043794, 'samples': 6987840, 'steps': 36394, 'loss/train': 1.3989843130111694} 08/30/2021 19:46:59 - INFO - __main__ - Step 36396: {'lr': 0.00043627661323284914, 'samples': 6988032, 'steps': 36395, 'loss/train': 1.5493284463882446} 08/30/2021 19:46:59 - INFO - __main__ - Step 36397: {'lr': 0.00043627307388132693, 'samples': 6988224, 'steps': 36396, 'loss/train': 1.6801135540008545} 08/30/2021 19:46:59 - INFO - __main__ - Step 36398: {'lr': 0.0004362695344458729, 'samples': 6988416, 'steps': 36397, 'loss/train': 1.5184098482131958} 08/30/2021 19:47:00 - INFO - __main__ - Step 36399: {'lr': 0.00043626599492648877, 'samples': 6988608, 'steps': 36398, 'loss/train': 1.9017716646194458} 08/30/2021 19:47:00 - INFO - __main__ - Step 36400: {'lr': 0.000436262455323176, 'samples': 6988800, 'steps': 36399, 'loss/train': 1.036109209060669} 08/30/2021 19:47:02 - INFO - __main__ - Step 36401: {'lr': 0.0004362589156359363, 'samples': 6988992, 'steps': 36400, 'loss/train': 1.6708488464355469} 08/30/2021 19:47:02 - INFO - __main__ - Step 36402: {'lr': 0.00043625537586477114, 'samples': 6989184, 'steps': 36401, 'loss/train': 1.72758150100708} 08/30/2021 19:47:03 - INFO - __main__ - Step 36403: {'lr': 0.00043625183600968224, 'samples': 6989376, 'steps': 36402, 'loss/train': 1.4736424684524536} 08/30/2021 19:47:03 - INFO - __main__ - Step 36404: {'lr': 0.00043624829607067105, 'samples': 6989568, 'steps': 36403, 'loss/train': 1.1701653003692627} 08/30/2021 19:47:03 - INFO - __main__ - Step 36405: {'lr': 0.0004362447560477394, 'samples': 6989760, 'steps': 36404, 'loss/train': 0.028951827436685562} 08/30/2021 19:47:04 - INFO - __main__ - Step 36406: {'lr': 0.0004362412159408886, 'samples': 6989952, 'steps': 36405, 'loss/train': 1.3001972436904907} 08/30/2021 19:47:04 - INFO - __main__ - Step 36407: {'lr': 0.0004362376757501205, 'samples': 6990144, 'steps': 36406, 'loss/train': 1.716759204864502} 08/30/2021 19:47:06 - INFO - __main__ - Step 36408: {'lr': 0.00043623413547543645, 'samples': 6990336, 'steps': 36407, 'loss/train': 0.8372818827629089} 08/30/2021 19:47:06 - INFO - __main__ - Step 36409: {'lr': 0.00043623059511683826, 'samples': 6990528, 'steps': 36408, 'loss/train': 0.8395217061042786} 08/30/2021 19:47:06 - INFO - __main__ - Step 36410: {'lr': 0.0004362270546743274, 'samples': 6990720, 'steps': 36409, 'loss/train': 0.4687364399433136} 08/30/2021 19:47:07 - INFO - __main__ - Step 36411: {'lr': 0.0004362235141479055, 'samples': 6990912, 'steps': 36410, 'loss/train': 1.0184953212738037} 08/30/2021 19:47:07 - INFO - __main__ - Step 36412: {'lr': 0.0004362199735375742, 'samples': 6991104, 'steps': 36411, 'loss/train': 1.4308748245239258} 08/30/2021 19:47:09 - INFO - __main__ - Step 36413: {'lr': 0.000436216432843335, 'samples': 6991296, 'steps': 36412, 'loss/train': 1.4313554763793945} 08/30/2021 19:47:09 - INFO - __main__ - Step 36414: {'lr': 0.00043621289206518957, 'samples': 6991488, 'steps': 36413, 'loss/train': 1.0186474323272705} 08/30/2021 19:47:09 - INFO - __main__ - Step 36415: {'lr': 0.00043620935120313955, 'samples': 6991680, 'steps': 36414, 'loss/train': 0.6312722563743591} 08/30/2021 19:47:10 - INFO - __main__ - Step 36416: {'lr': 0.0004362058102571864, 'samples': 6991872, 'steps': 36415, 'loss/train': 0.806549608707428} 08/30/2021 19:47:10 - INFO - __main__ - Step 36417: {'lr': 0.00043620226922733174, 'samples': 6992064, 'steps': 36416, 'loss/train': 1.9578888416290283} 08/30/2021 19:47:12 - INFO - __main__ - Step 36418: {'lr': 0.0004361987281135773, 'samples': 6992256, 'steps': 36417, 'loss/train': 1.956422209739685} 08/30/2021 19:47:12 - INFO - __main__ - Step 36419: {'lr': 0.00043619518691592453, 'samples': 6992448, 'steps': 36418, 'loss/train': 0.8095663189888} 08/30/2021 19:47:12 - INFO - __main__ - Step 36420: {'lr': 0.00043619164563437506, 'samples': 6992640, 'steps': 36419, 'loss/train': 1.6983819007873535} 08/30/2021 19:47:13 - INFO - __main__ - Step 36421: {'lr': 0.0004361881042689306, 'samples': 6992832, 'steps': 36420, 'loss/train': 1.4028847217559814} 08/30/2021 19:47:13 - INFO - __main__ - Step 36422: {'lr': 0.00043618456281959263, 'samples': 6993024, 'steps': 36421, 'loss/train': 1.512710452079773} 08/30/2021 19:47:15 - INFO - __main__ - Step 36423: {'lr': 0.0004361810212863627, 'samples': 6993216, 'steps': 36422, 'loss/train': 1.3518368005752563} 08/30/2021 19:47:15 - INFO - __main__ - Step 36424: {'lr': 0.0004361774796692425, 'samples': 6993408, 'steps': 36423, 'loss/train': 0.9979020357131958} 08/30/2021 19:47:15 - INFO - __main__ - Step 36425: {'lr': 0.00043617393796823367, 'samples': 6993600, 'steps': 36424, 'loss/train': 1.237671136856079} 08/30/2021 19:47:16 - INFO - __main__ - Step 36426: {'lr': 0.00043617039618333765, 'samples': 6993792, 'steps': 36425, 'loss/train': 1.2507598400115967} 08/30/2021 19:47:16 - INFO - __main__ - Step 36427: {'lr': 0.00043616685431455615, 'samples': 6993984, 'steps': 36426, 'loss/train': 1.2287665605545044} 08/30/2021 19:47:18 - INFO - __main__ - Step 36428: {'lr': 0.0004361633123618908, 'samples': 6994176, 'steps': 36427, 'loss/train': 1.2938023805618286} 08/30/2021 19:47:19 - INFO - __main__ - Step 36429: {'lr': 0.00043615977032534305, 'samples': 6994368, 'steps': 36428, 'loss/train': 1.3939820528030396} 08/30/2021 19:47:19 - INFO - __main__ - Step 36430: {'lr': 0.00043615622820491464, 'samples': 6994560, 'steps': 36429, 'loss/train': 1.091234564781189} 08/30/2021 19:47:19 - INFO - __main__ - Step 36431: {'lr': 0.00043615268600060705, 'samples': 6994752, 'steps': 36430, 'loss/train': 0.9800477623939514} 08/30/2021 19:47:20 - INFO - __main__ - Step 36432: {'lr': 0.000436149143712422, 'samples': 6994944, 'steps': 36431, 'loss/train': 0.08381208777427673} 08/30/2021 19:47:21 - INFO - __main__ - Step 36433: {'lr': 0.0004361456013403609, 'samples': 6995136, 'steps': 36432, 'loss/train': 1.5640465021133423} 08/30/2021 19:47:21 - INFO - __main__ - Step 36434: {'lr': 0.00043614205888442553, 'samples': 6995328, 'steps': 36433, 'loss/train': 1.1764110326766968} 08/30/2021 19:47:22 - INFO - __main__ - Step 36435: {'lr': 0.00043613851634461743, 'samples': 6995520, 'steps': 36434, 'loss/train': 1.5034747123718262} 08/30/2021 19:47:22 - INFO - __main__ - Step 36436: {'lr': 0.00043613497372093827, 'samples': 6995712, 'steps': 36435, 'loss/train': 1.010730504989624} 08/30/2021 19:47:22 - INFO - __main__ - Step 36437: {'lr': 0.0004361314310133894, 'samples': 6995904, 'steps': 36436, 'loss/train': 1.4037946462631226} 08/30/2021 19:47:24 - INFO - __main__ - Step 36438: {'lr': 0.00043612788822197266, 'samples': 6996096, 'steps': 36437, 'loss/train': 1.5880666971206665} 08/30/2021 19:47:24 - INFO - __main__ - Step 36439: {'lr': 0.0004361243453466896, 'samples': 6996288, 'steps': 36438, 'loss/train': 0.5422747731208801} 08/30/2021 19:47:25 - INFO - __main__ - Step 36440: {'lr': 0.0004361208023875417, 'samples': 6996480, 'steps': 36439, 'loss/train': 2.4194462299346924} 08/30/2021 19:47:25 - INFO - __main__ - Step 36441: {'lr': 0.00043611725934453074, 'samples': 6996672, 'steps': 36440, 'loss/train': 1.7073898315429688} 08/30/2021 19:47:25 - INFO - __main__ - Step 36442: {'lr': 0.00043611371621765817, 'samples': 6996864, 'steps': 36441, 'loss/train': 1.4313596487045288} 08/30/2021 19:47:27 - INFO - __main__ - Step 36443: {'lr': 0.0004361101730069256, 'samples': 6997056, 'steps': 36442, 'loss/train': 1.48096764087677} 08/30/2021 19:47:27 - INFO - __main__ - Step 36444: {'lr': 0.00043610662971233465, 'samples': 6997248, 'steps': 36443, 'loss/train': 1.0268685817718506} 08/30/2021 19:47:28 - INFO - __main__ - Step 36445: {'lr': 0.00043610308633388695, 'samples': 6997440, 'steps': 36444, 'loss/train': 1.5223705768585205} 08/30/2021 19:47:28 - INFO - __main__ - Step 36446: {'lr': 0.0004360995428715841, 'samples': 6997632, 'steps': 36445, 'loss/train': 1.1339970827102661} 08/30/2021 19:47:28 - INFO - __main__ - Step 36447: {'lr': 0.00043609599932542764, 'samples': 6997824, 'steps': 36446, 'loss/train': 1.1776108741760254} 08/30/2021 19:47:29 - INFO - __main__ - Step 36448: {'lr': 0.00043609245569541924, 'samples': 6998016, 'steps': 36447, 'loss/train': 1.4329923391342163} 08/30/2021 19:47:31 - INFO - __main__ - Step 36449: {'lr': 0.00043608891198156037, 'samples': 6998208, 'steps': 36448, 'loss/train': 0.9501417875289917} 08/30/2021 19:47:31 - INFO - __main__ - Step 36450: {'lr': 0.0004360853681838528, 'samples': 6998400, 'steps': 36449, 'loss/train': 1.625877022743225} 08/30/2021 19:47:31 - INFO - __main__ - Step 36451: {'lr': 0.0004360818243022979, 'samples': 6998592, 'steps': 36450, 'loss/train': 0.9098576903343201} 08/30/2021 19:47:32 - INFO - __main__ - Step 36452: {'lr': 0.00043607828033689753, 'samples': 6998784, 'steps': 36451, 'loss/train': 1.3731720447540283} 08/30/2021 19:47:32 - INFO - __main__ - Step 36453: {'lr': 0.000436074736287653, 'samples': 6998976, 'steps': 36452, 'loss/train': 1.8267905712127686} 08/30/2021 19:47:34 - INFO - __main__ - Step 36454: {'lr': 0.00043607119215456625, 'samples': 6999168, 'steps': 36453, 'loss/train': 1.9684451818466187} 08/30/2021 19:47:34 - INFO - __main__ - Step 36455: {'lr': 0.00043606764793763865, 'samples': 6999360, 'steps': 36454, 'loss/train': 1.4963877201080322} 08/30/2021 19:47:34 - INFO - __main__ - Step 36456: {'lr': 0.00043606410363687177, 'samples': 6999552, 'steps': 36455, 'loss/train': 0.8276395201683044} 08/30/2021 19:47:35 - INFO - __main__ - Step 36457: {'lr': 0.00043606055925226727, 'samples': 6999744, 'steps': 36456, 'loss/train': 1.0844939947128296} 08/30/2021 19:47:35 - INFO - __main__ - Step 36458: {'lr': 0.0004360570147838269, 'samples': 6999936, 'steps': 36457, 'loss/train': 0.823511004447937} 08/30/2021 19:47:37 - INFO - __main__ - Step 36459: {'lr': 0.00043605347023155193, 'samples': 7000128, 'steps': 36458, 'loss/train': 1.3540081977844238} 08/30/2021 19:47:37 - INFO - __main__ - Step 36460: {'lr': 0.0004360499255954442, 'samples': 7000320, 'steps': 36459, 'loss/train': 1.195165753364563} 08/30/2021 19:47:37 - INFO - __main__ - Step 36461: {'lr': 0.0004360463808755053, 'samples': 7000512, 'steps': 36460, 'loss/train': 0.6927940845489502} 08/30/2021 19:47:38 - INFO - __main__ - Step 36462: {'lr': 0.00043604283607173673, 'samples': 7000704, 'steps': 36461, 'loss/train': 1.1124961376190186} 08/30/2021 19:47:38 - INFO - __main__ - Step 36463: {'lr': 0.0004360392911841401, 'samples': 7000896, 'steps': 36462, 'loss/train': 1.461443305015564} 08/30/2021 19:47:40 - INFO - __main__ - Step 36464: {'lr': 0.0004360357462127171, 'samples': 7001088, 'steps': 36463, 'loss/train': 1.238618016242981} 08/30/2021 19:47:40 - INFO - __main__ - Step 36465: {'lr': 0.0004360322011574692, 'samples': 7001280, 'steps': 36464, 'loss/train': 0.5723713636398315} 08/30/2021 19:47:41 - INFO - __main__ - Step 36466: {'lr': 0.00043602865601839817, 'samples': 7001472, 'steps': 36465, 'loss/train': 1.0349533557891846} 08/30/2021 19:47:41 - INFO - __main__ - Step 36467: {'lr': 0.00043602511079550535, 'samples': 7001664, 'steps': 36466, 'loss/train': 0.8309263586997986} 08/30/2021 19:47:41 - INFO - __main__ - Step 36468: {'lr': 0.0004360215654887926, 'samples': 7001856, 'steps': 36467, 'loss/train': 1.879464030265808} 08/30/2021 19:47:42 - INFO - __main__ - Step 36469: {'lr': 0.0004360180200982613, 'samples': 7002048, 'steps': 36468, 'loss/train': 1.3553422689437866} 08/30/2021 19:47:43 - INFO - __main__ - Step 36470: {'lr': 0.00043601447462391317, 'samples': 7002240, 'steps': 36469, 'loss/train': 0.9028359055519104} 08/30/2021 19:47:44 - INFO - __main__ - Step 36471: {'lr': 0.00043601092906574986, 'samples': 7002432, 'steps': 36470, 'loss/train': 1.421359658241272} 08/30/2021 19:47:44 - INFO - __main__ - Step 36472: {'lr': 0.0004360073834237729, 'samples': 7002624, 'steps': 36471, 'loss/train': 1.6730273962020874} 08/30/2021 19:47:44 - INFO - __main__ - Step 36473: {'lr': 0.0004360038376979838, 'samples': 7002816, 'steps': 36472, 'loss/train': 1.1096608638763428} 08/30/2021 19:47:45 - INFO - __main__ - Step 36474: {'lr': 0.0004360002918883843, 'samples': 7003008, 'steps': 36473, 'loss/train': 5.877317905426025} 08/30/2021 19:47:46 - INFO - __main__ - Step 36475: {'lr': 0.00043599674599497593, 'samples': 7003200, 'steps': 36474, 'loss/train': 1.6931506395339966} 08/30/2021 19:47:47 - INFO - __main__ - Step 36476: {'lr': 0.00043599320001776025, 'samples': 7003392, 'steps': 36475, 'loss/train': 1.4531265497207642} 08/30/2021 19:47:47 - INFO - __main__ - Step 36477: {'lr': 0.00043598965395673893, 'samples': 7003584, 'steps': 36476, 'loss/train': 1.1867077350616455} 08/30/2021 19:47:47 - INFO - __main__ - Step 36478: {'lr': 0.0004359861078119136, 'samples': 7003776, 'steps': 36477, 'loss/train': 1.9284695386886597} 08/30/2021 19:47:48 - INFO - __main__ - Step 36479: {'lr': 0.00043598256158328575, 'samples': 7003968, 'steps': 36478, 'loss/train': 1.6126198768615723} 08/30/2021 19:47:48 - INFO - __main__ - Step 36480: {'lr': 0.00043597901527085703, 'samples': 7004160, 'steps': 36479, 'loss/train': 1.5148154497146606} 08/30/2021 19:47:50 - INFO - __main__ - Step 36481: {'lr': 0.000435975468874629, 'samples': 7004352, 'steps': 36480, 'loss/train': 2.088822841644287} 08/30/2021 19:47:50 - INFO - __main__ - Step 36482: {'lr': 0.00043597192239460336, 'samples': 7004544, 'steps': 36481, 'loss/train': 1.85660982131958} 08/30/2021 19:47:50 - INFO - __main__ - Step 36483: {'lr': 0.00043596837583078165, 'samples': 7004736, 'steps': 36482, 'loss/train': 0.9900230765342712} 08/30/2021 19:47:51 - INFO - __main__ - Step 36484: {'lr': 0.0004359648291831654, 'samples': 7004928, 'steps': 36483, 'loss/train': 1.157524824142456} 08/30/2021 19:47:51 - INFO - __main__ - Step 36485: {'lr': 0.0004359612824517563, 'samples': 7005120, 'steps': 36484, 'loss/train': 1.1578923463821411} 08/30/2021 19:47:53 - INFO - __main__ - Step 36486: {'lr': 0.0004359577356365559, 'samples': 7005312, 'steps': 36485, 'loss/train': 1.3362678289413452} 08/30/2021 19:47:53 - INFO - __main__ - Step 36487: {'lr': 0.00043595418873756584, 'samples': 7005504, 'steps': 36486, 'loss/train': 0.8806517720222473} 08/30/2021 19:47:53 - INFO - __main__ - Step 36488: {'lr': 0.0004359506417547876, 'samples': 7005696, 'steps': 36487, 'loss/train': 0.6454231142997742} 08/30/2021 19:47:54 - INFO - __main__ - Step 36489: {'lr': 0.000435947094688223, 'samples': 7005888, 'steps': 36488, 'loss/train': 1.2656669616699219} 08/30/2021 19:47:54 - INFO - __main__ - Step 36490: {'lr': 0.0004359435475378735, 'samples': 7006080, 'steps': 36489, 'loss/train': 1.606446623802185} 08/30/2021 19:47:55 - INFO - __main__ - Step 36491: {'lr': 0.0004359400003037406, 'samples': 7006272, 'steps': 36490, 'loss/train': 2.6311333179473877} 08/30/2021 19:47:56 - INFO - __main__ - Step 36492: {'lr': 0.0004359364529858261, 'samples': 7006464, 'steps': 36491, 'loss/train': 1.030823826789856} 08/30/2021 19:47:56 - INFO - __main__ - Step 36493: {'lr': 0.00043593290558413143, 'samples': 7006656, 'steps': 36492, 'loss/train': 1.479521632194519} 08/30/2021 19:47:57 - INFO - __main__ - Step 36494: {'lr': 0.0004359293580986583, 'samples': 7006848, 'steps': 36493, 'loss/train': 1.374276876449585} 08/30/2021 19:47:57 - INFO - __main__ - Step 36495: {'lr': 0.0004359258105294083, 'samples': 7007040, 'steps': 36494, 'loss/train': 1.6317195892333984} 08/30/2021 19:47:58 - INFO - __main__ - Step 36496: {'lr': 0.0004359222628763829, 'samples': 7007232, 'steps': 36495, 'loss/train': 6.169818878173828} 08/30/2021 19:47:59 - INFO - __main__ - Step 36497: {'lr': 0.0004359187151395839, 'samples': 7007424, 'steps': 36496, 'loss/train': 1.41305410861969} 08/30/2021 19:47:59 - INFO - __main__ - Step 36498: {'lr': 0.0004359151673190127, 'samples': 7007616, 'steps': 36497, 'loss/train': 1.8294190168380737} 08/30/2021 19:48:00 - INFO - __main__ - Step 36499: {'lr': 0.0004359116194146711, 'samples': 7007808, 'steps': 36498, 'loss/train': 1.3524771928787231} 08/30/2021 19:48:00 - INFO - __main__ - Step 36500: {'lr': 0.0004359080714265605, 'samples': 7008000, 'steps': 36499, 'loss/train': 1.275800108909607} 08/30/2021 19:48:02 - INFO - __main__ - Step 36501: {'lr': 0.00043590452335468265, 'samples': 7008192, 'steps': 36500, 'loss/train': 1.5451632738113403} 08/30/2021 19:48:03 - INFO - __main__ - Step 36502: {'lr': 0.00043590097519903917, 'samples': 7008384, 'steps': 36501, 'loss/train': 1.144112467765808} 08/30/2021 19:48:03 - INFO - __main__ - Step 36503: {'lr': 0.0004358974269596314, 'samples': 7008576, 'steps': 36502, 'loss/train': 1.904725193977356} 08/30/2021 19:48:04 - INFO - __main__ - Step 36504: {'lr': 0.00043589387863646125, 'samples': 7008768, 'steps': 36503, 'loss/train': 0.38427162170410156} 08/30/2021 19:48:04 - INFO - __main__ - Step 36505: {'lr': 0.0004358903302295301, 'samples': 7008960, 'steps': 36504, 'loss/train': 1.152559757232666} 08/30/2021 19:48:05 - INFO - __main__ - Step 36506: {'lr': 0.0004358867817388397, 'samples': 7009152, 'steps': 36505, 'loss/train': 0.5000024437904358} 08/30/2021 19:48:06 - INFO - __main__ - Step 36507: {'lr': 0.0004358832331643916, 'samples': 7009344, 'steps': 36506, 'loss/train': 1.2807445526123047} 08/30/2021 19:48:06 - INFO - __main__ - Step 36508: {'lr': 0.0004358796845061873, 'samples': 7009536, 'steps': 36507, 'loss/train': 1.509907841682434} 08/30/2021 19:48:06 - INFO - __main__ - Step 36509: {'lr': 0.00043587613576422855, 'samples': 7009728, 'steps': 36508, 'loss/train': 1.8179283142089844} 08/30/2021 19:48:07 - INFO - __main__ - Step 36510: {'lr': 0.00043587258693851685, 'samples': 7009920, 'steps': 36509, 'loss/train': 1.31987726688385} 08/30/2021 19:48:08 - INFO - __main__ - Step 36511: {'lr': 0.0004358690380290539, 'samples': 7010112, 'steps': 36510, 'loss/train': 1.4994300603866577} 08/30/2021 19:48:09 - INFO - __main__ - Step 36512: {'lr': 0.00043586548903584113, 'samples': 7010304, 'steps': 36511, 'loss/train': 2.2657501697540283} 08/30/2021 19:48:09 - INFO - __main__ - Step 36513: {'lr': 0.0004358619399588802, 'samples': 7010496, 'steps': 36512, 'loss/train': 1.943145513534546} 08/30/2021 19:48:09 - INFO - __main__ - Step 36514: {'lr': 0.0004358583907981729, 'samples': 7010688, 'steps': 36513, 'loss/train': 0.41833555698394775} 08/30/2021 19:48:10 - INFO - __main__ - Step 36515: {'lr': 0.0004358548415537206, 'samples': 7010880, 'steps': 36514, 'loss/train': 1.337725043296814} 08/30/2021 19:48:10 - INFO - __main__ - Step 36516: {'lr': 0.000435851292225525, 'samples': 7011072, 'steps': 36515, 'loss/train': 1.452592372894287} 08/30/2021 19:48:12 - INFO - __main__ - Step 36517: {'lr': 0.0004358477428135876, 'samples': 7011264, 'steps': 36516, 'loss/train': 1.5251343250274658} 08/30/2021 19:48:12 - INFO - __main__ - Step 36518: {'lr': 0.00043584419331791014, 'samples': 7011456, 'steps': 36517, 'loss/train': 1.6350144147872925} 08/30/2021 19:48:12 - INFO - __main__ - Step 36519: {'lr': 0.0004358406437384942, 'samples': 7011648, 'steps': 36518, 'loss/train': 1.236351490020752} 08/30/2021 19:48:13 - INFO - __main__ - Step 36520: {'lr': 0.0004358370940753412, 'samples': 7011840, 'steps': 36519, 'loss/train': 1.3332247734069824} 08/30/2021 19:48:13 - INFO - __main__ - Step 36521: {'lr': 0.000435833544328453, 'samples': 7012032, 'steps': 36520, 'loss/train': 1.3820645809173584} 08/30/2021 19:48:15 - INFO - __main__ - Step 36522: {'lr': 0.00043582999449783103, 'samples': 7012224, 'steps': 36521, 'loss/train': 1.4637681245803833} 08/30/2021 19:48:15 - INFO - __main__ - Step 36523: {'lr': 0.0004358264445834769, 'samples': 7012416, 'steps': 36522, 'loss/train': 1.278749942779541} 08/30/2021 19:48:16 - INFO - __main__ - Step 36524: {'lr': 0.00043582289458539224, 'samples': 7012608, 'steps': 36523, 'loss/train': 0.8776615262031555} 08/30/2021 19:48:16 - INFO - __main__ - Step 36525: {'lr': 0.00043581934450357876, 'samples': 7012800, 'steps': 36524, 'loss/train': 1.9267964363098145} 08/30/2021 19:48:16 - INFO - __main__ - Step 36526: {'lr': 0.0004358157943380379, 'samples': 7012992, 'steps': 36525, 'loss/train': 2.7304790019989014} 08/30/2021 19:48:18 - INFO - __main__ - Step 36527: {'lr': 0.00043581224408877116, 'samples': 7013184, 'steps': 36526, 'loss/train': 1.2880278825759888} 08/30/2021 19:48:18 - INFO - __main__ - Step 36528: {'lr': 0.00043580869375578046, 'samples': 7013376, 'steps': 36527, 'loss/train': 5.815019607543945} 08/30/2021 19:48:19 - INFO - __main__ - Step 36529: {'lr': 0.00043580514333906717, 'samples': 7013568, 'steps': 36528, 'loss/train': 1.5183874368667603} 08/30/2021 19:48:19 - INFO - __main__ - Step 36530: {'lr': 0.000435801592838633, 'samples': 7013760, 'steps': 36529, 'loss/train': 1.5846532583236694} 08/30/2021 19:48:19 - INFO - __main__ - Step 36531: {'lr': 0.0004357980422544794, 'samples': 7013952, 'steps': 36530, 'loss/train': 1.8552756309509277} 08/30/2021 19:48:20 - INFO - __main__ - Step 36532: {'lr': 0.00043579449158660815, 'samples': 7014144, 'steps': 36531, 'loss/train': 1.71445631980896} 08/30/2021 19:48:21 - INFO - __main__ - Step 36533: {'lr': 0.0004357909408350208, 'samples': 7014336, 'steps': 36532, 'loss/train': 1.38188636302948} 08/30/2021 19:48:22 - INFO - __main__ - Step 36534: {'lr': 0.00043578738999971886, 'samples': 7014528, 'steps': 36533, 'loss/train': 2.012483835220337} 08/30/2021 19:48:22 - INFO - __main__ - Step 36535: {'lr': 0.000435783839080704, 'samples': 7014720, 'steps': 36534, 'loss/train': 0.05404497683048248} 08/30/2021 19:48:22 - INFO - __main__ - Step 36536: {'lr': 0.00043578028807797774, 'samples': 7014912, 'steps': 36535, 'loss/train': 1.4148170948028564} 08/30/2021 19:48:23 - INFO - __main__ - Step 36537: {'lr': 0.0004357767369915419, 'samples': 7015104, 'steps': 36536, 'loss/train': 2.089134693145752} 08/30/2021 19:48:24 - INFO - __main__ - Step 36538: {'lr': 0.0004357731858213978, 'samples': 7015296, 'steps': 36537, 'loss/train': 1.2578330039978027} 08/30/2021 19:48:25 - INFO - __main__ - Step 36539: {'lr': 0.0004357696345675472, 'samples': 7015488, 'steps': 36538, 'loss/train': 1.3099653720855713} 08/30/2021 19:48:25 - INFO - __main__ - Step 36540: {'lr': 0.00043576608322999167, 'samples': 7015680, 'steps': 36539, 'loss/train': 1.617466688156128} 08/30/2021 19:48:25 - INFO - __main__ - Step 36541: {'lr': 0.0004357625318087328, 'samples': 7015872, 'steps': 36540, 'loss/train': 1.8089059591293335} 08/30/2021 19:48:26 - INFO - __main__ - Step 36542: {'lr': 0.00043575898030377225, 'samples': 7016064, 'steps': 36541, 'loss/train': 2.036715269088745} 08/30/2021 19:48:27 - INFO - __main__ - Step 36543: {'lr': 0.00043575542871511155, 'samples': 7016256, 'steps': 36542, 'loss/train': 1.4833344221115112} 08/30/2021 19:48:28 - INFO - __main__ - Step 36544: {'lr': 0.00043575187704275234, 'samples': 7016448, 'steps': 36543, 'loss/train': 1.2527631521224976} 08/30/2021 19:48:28 - INFO - __main__ - Step 36545: {'lr': 0.0004357483252866961, 'samples': 7016640, 'steps': 36544, 'loss/train': 2.0547447204589844} 08/30/2021 19:48:28 - INFO - __main__ - Step 36546: {'lr': 0.00043574477344694463, 'samples': 7016832, 'steps': 36545, 'loss/train': 1.2601391077041626} 08/30/2021 19:48:29 - INFO - __main__ - Step 36547: {'lr': 0.0004357412215234994, 'samples': 7017024, 'steps': 36546, 'loss/train': 1.3062084913253784} 08/30/2021 19:48:31 - INFO - __main__ - Step 36548: {'lr': 0.00043573766951636206, 'samples': 7017216, 'steps': 36547, 'loss/train': 1.1554791927337646} 08/30/2021 19:48:31 - INFO - __main__ - Step 36549: {'lr': 0.00043573411742553415, 'samples': 7017408, 'steps': 36548, 'loss/train': 1.0076406002044678} 08/30/2021 19:48:32 - INFO - __main__ - Step 36550: {'lr': 0.0004357305652510174, 'samples': 7017600, 'steps': 36549, 'loss/train': 2.242140769958496} 08/30/2021 19:48:32 - INFO - __main__ - Step 36551: {'lr': 0.00043572701299281327, 'samples': 7017792, 'steps': 36550, 'loss/train': 0.660279393196106} 08/30/2021 19:48:32 - INFO - __main__ - Step 36552: {'lr': 0.0004357234606509234, 'samples': 7017984, 'steps': 36551, 'loss/train': 1.575362205505371} 08/30/2021 19:48:33 - INFO - __main__ - Step 36553: {'lr': 0.00043571990822534936, 'samples': 7018176, 'steps': 36552, 'loss/train': 3.932896137237549} 08/30/2021 19:48:35 - INFO - __main__ - Step 36554: {'lr': 0.00043571635571609287, 'samples': 7018368, 'steps': 36553, 'loss/train': 1.0440348386764526} 08/30/2021 19:48:35 - INFO - __main__ - Step 36555: {'lr': 0.00043571280312315543, 'samples': 7018560, 'steps': 36554, 'loss/train': 1.1563599109649658} 08/30/2021 19:48:35 - INFO - __main__ - Step 36556: {'lr': 0.0004357092504465386, 'samples': 7018752, 'steps': 36555, 'loss/train': 1.3621444702148438} 08/30/2021 19:48:36 - INFO - __main__ - Step 36557: {'lr': 0.00043570569768624416, 'samples': 7018944, 'steps': 36556, 'loss/train': 1.2782279253005981} 08/30/2021 19:48:36 - INFO - __main__ - Step 36558: {'lr': 0.00043570214484227353, 'samples': 7019136, 'steps': 36557, 'loss/train': 1.4263688325881958} 08/30/2021 19:48:38 - INFO - __main__ - Step 36559: {'lr': 0.00043569859191462847, 'samples': 7019328, 'steps': 36558, 'loss/train': 1.3615001440048218} 08/30/2021 19:48:38 - INFO - __main__ - Step 36560: {'lr': 0.0004356950389033104, 'samples': 7019520, 'steps': 36559, 'loss/train': 1.5760283470153809} 08/30/2021 19:48:38 - INFO - __main__ - Step 36561: {'lr': 0.0004356914858083211, 'samples': 7019712, 'steps': 36560, 'loss/train': 1.891967535018921} 08/30/2021 19:48:39 - INFO - __main__ - Step 36562: {'lr': 0.00043568793262966195, 'samples': 7019904, 'steps': 36561, 'loss/train': 1.246058464050293} 08/30/2021 19:48:39 - INFO - __main__ - Step 36563: {'lr': 0.00043568437936733473, 'samples': 7020096, 'steps': 36562, 'loss/train': 1.5230660438537598} 08/30/2021 19:48:41 - INFO - __main__ - Step 36564: {'lr': 0.0004356808260213411, 'samples': 7020288, 'steps': 36563, 'loss/train': 1.6539273262023926} 08/30/2021 19:48:41 - INFO - __main__ - Step 36565: {'lr': 0.00043567727259168244, 'samples': 7020480, 'steps': 36564, 'loss/train': 1.2522408962249756} 08/30/2021 19:48:41 - INFO - __main__ - Step 36566: {'lr': 0.0004356737190783605, 'samples': 7020672, 'steps': 36565, 'loss/train': 1.108936071395874} 08/30/2021 19:48:42 - INFO - __main__ - Step 36567: {'lr': 0.00043567016548137685, 'samples': 7020864, 'steps': 36566, 'loss/train': 1.2651119232177734} 08/30/2021 19:48:42 - INFO - __main__ - Step 36568: {'lr': 0.00043566661180073304, 'samples': 7021056, 'steps': 36567, 'loss/train': 1.0394198894500732} 08/30/2021 19:48:44 - INFO - __main__ - Step 36569: {'lr': 0.00043566305803643073, 'samples': 7021248, 'steps': 36568, 'loss/train': 1.6034506559371948} 08/30/2021 19:48:44 - INFO - __main__ - Step 36570: {'lr': 0.00043565950418847154, 'samples': 7021440, 'steps': 36569, 'loss/train': 2.1219236850738525} 08/30/2021 19:48:44 - INFO - __main__ - Step 36571: {'lr': 0.00043565595025685705, 'samples': 7021632, 'steps': 36570, 'loss/train': 1.7575101852416992} 08/30/2021 19:48:45 - INFO - __main__ - Step 36572: {'lr': 0.0004356523962415889, 'samples': 7021824, 'steps': 36571, 'loss/train': 2.0594255924224854} 08/30/2021 19:48:45 - INFO - __main__ - Step 36573: {'lr': 0.00043564884214266855, 'samples': 7022016, 'steps': 36572, 'loss/train': 1.5242760181427002} 08/30/2021 19:48:47 - INFO - __main__ - Step 36574: {'lr': 0.00043564528796009774, 'samples': 7022208, 'steps': 36573, 'loss/train': 1.4918831586837769} 08/30/2021 19:48:47 - INFO - __main__ - Step 36575: {'lr': 0.00043564173369387807, 'samples': 7022400, 'steps': 36574, 'loss/train': 1.3450161218643188} 08/30/2021 19:48:47 - INFO - __main__ - Step 36576: {'lr': 0.00043563817934401107, 'samples': 7022592, 'steps': 36575, 'loss/train': 1.106136441230774} 08/30/2021 19:48:48 - INFO - __main__ - Step 36577: {'lr': 0.0004356346249104983, 'samples': 7022784, 'steps': 36576, 'loss/train': 1.150787591934204} 08/30/2021 19:48:48 - INFO - __main__ - Step 36578: {'lr': 0.0004356310703933415, 'samples': 7022976, 'steps': 36577, 'loss/train': 1.2052197456359863} 08/30/2021 19:48:50 - INFO - __main__ - Step 36579: {'lr': 0.00043562751579254215, 'samples': 7023168, 'steps': 36578, 'loss/train': 2.0636699199676514} 08/30/2021 19:48:50 - INFO - __main__ - Step 36580: {'lr': 0.00043562396110810196, 'samples': 7023360, 'steps': 36579, 'loss/train': 1.325165033340454} 08/30/2021 19:48:50 - INFO - __main__ - Step 36581: {'lr': 0.00043562040634002245, 'samples': 7023552, 'steps': 36580, 'loss/train': 1.8251488208770752} 08/30/2021 19:48:51 - INFO - __main__ - Step 36582: {'lr': 0.0004356168514883053, 'samples': 7023744, 'steps': 36581, 'loss/train': 1.6045143604278564} 08/30/2021 19:48:51 - INFO - __main__ - Step 36583: {'lr': 0.000435613296552952, 'samples': 7023936, 'steps': 36582, 'loss/train': 1.722639560699463} 08/30/2021 19:48:53 - INFO - __main__ - Step 36584: {'lr': 0.0004356097415339643, 'samples': 7024128, 'steps': 36583, 'loss/train': 1.5015318393707275} 08/30/2021 19:48:53 - INFO - __main__ - Step 36585: {'lr': 0.0004356061864313436, 'samples': 7024320, 'steps': 36584, 'loss/train': 0.8369975090026855} 08/30/2021 19:48:54 - INFO - __main__ - Step 36586: {'lr': 0.0004356026312450917, 'samples': 7024512, 'steps': 36585, 'loss/train': 1.0878782272338867} 08/30/2021 19:48:54 - INFO - __main__ - Step 36587: {'lr': 0.00043559907597521007, 'samples': 7024704, 'steps': 36586, 'loss/train': 0.20002266764640808} 08/30/2021 19:48:54 - INFO - __main__ - Step 36588: {'lr': 0.00043559552062170037, 'samples': 7024896, 'steps': 36587, 'loss/train': 1.7895675897598267} 08/30/2021 19:48:56 - INFO - __main__ - Step 36589: {'lr': 0.00043559196518456425, 'samples': 7025088, 'steps': 36588, 'loss/train': 1.6089807748794556} 08/30/2021 19:48:56 - INFO - __main__ - Step 36590: {'lr': 0.0004355884096638032, 'samples': 7025280, 'steps': 36589, 'loss/train': 1.6458605527877808} 08/30/2021 19:48:57 - INFO - __main__ - Step 36591: {'lr': 0.0004355848540594188, 'samples': 7025472, 'steps': 36590, 'loss/train': 1.2729971408843994} 08/30/2021 19:48:57 - INFO - __main__ - Step 36592: {'lr': 0.00043558129837141285, 'samples': 7025664, 'steps': 36591, 'loss/train': 1.5198731422424316} 08/30/2021 19:48:57 - INFO - __main__ - Step 36593: {'lr': 0.0004355777425997868, 'samples': 7025856, 'steps': 36592, 'loss/train': 1.761038899421692} 08/30/2021 19:48:59 - INFO - __main__ - Step 36594: {'lr': 0.0004355741867445423, 'samples': 7026048, 'steps': 36593, 'loss/train': 1.2411330938339233} 08/30/2021 19:48:59 - INFO - __main__ - Step 36595: {'lr': 0.00043557063080568094, 'samples': 7026240, 'steps': 36594, 'loss/train': 1.5074400901794434} 08/30/2021 19:49:00 - INFO - __main__ - Step 36596: {'lr': 0.00043556707478320425, 'samples': 7026432, 'steps': 36595, 'loss/train': 1.2042975425720215} 08/30/2021 19:49:00 - INFO - __main__ - Step 36597: {'lr': 0.000435563518677114, 'samples': 7026624, 'steps': 36596, 'loss/train': 1.2453397512435913} 08/30/2021 19:49:01 - INFO - __main__ - Step 36598: {'lr': 0.00043555996248741157, 'samples': 7026816, 'steps': 36597, 'loss/train': 1.4067848920822144} 08/30/2021 19:49:01 - INFO - __main__ - Step 36599: {'lr': 0.00043555640621409874, 'samples': 7027008, 'steps': 36598, 'loss/train': 0.9534721374511719} 08/30/2021 19:49:03 - INFO - __main__ - Step 36600: {'lr': 0.000435552849857177, 'samples': 7027200, 'steps': 36599, 'loss/train': 1.4208219051361084} 08/30/2021 19:49:03 - INFO - __main__ - Step 36601: {'lr': 0.0004355492934166481, 'samples': 7027392, 'steps': 36600, 'loss/train': 0.06765236705541611} 08/30/2021 19:49:03 - INFO - __main__ - Step 36602: {'lr': 0.00043554573689251355, 'samples': 7027584, 'steps': 36601, 'loss/train': 1.4174158573150635} 08/30/2021 19:49:04 - INFO - __main__ - Step 36603: {'lr': 0.00043554218028477493, 'samples': 7027776, 'steps': 36602, 'loss/train': 1.5248489379882812} 08/30/2021 19:49:04 - INFO - __main__ - Step 36604: {'lr': 0.0004355386235934339, 'samples': 7027968, 'steps': 36603, 'loss/train': 1.6492342948913574} 08/30/2021 19:49:05 - INFO - __main__ - Step 36605: {'lr': 0.0004355350668184919, 'samples': 7028160, 'steps': 36604, 'loss/train': 1.1743378639221191} 08/30/2021 19:49:06 - INFO - __main__ - Step 36606: {'lr': 0.0004355315099599508, 'samples': 7028352, 'steps': 36605, 'loss/train': 0.7627246379852295} 08/30/2021 19:49:06 - INFO - __main__ - Step 36607: {'lr': 0.000435527953017812, 'samples': 7028544, 'steps': 36606, 'loss/train': 1.5173484086990356} 08/30/2021 19:49:07 - INFO - __main__ - Step 36608: {'lr': 0.00043552439599207714, 'samples': 7028736, 'steps': 36607, 'loss/train': 1.3291195631027222} 08/30/2021 19:49:07 - INFO - __main__ - Step 36609: {'lr': 0.00043552083888274794, 'samples': 7028928, 'steps': 36608, 'loss/train': 2.4523611068725586} 08/30/2021 19:49:09 - INFO - __main__ - Step 36610: {'lr': 0.00043551728168982583, 'samples': 7029120, 'steps': 36609, 'loss/train': 1.1981136798858643} 08/30/2021 19:49:09 - INFO - __main__ - Step 36611: {'lr': 0.0004355137244133126, 'samples': 7029312, 'steps': 36610, 'loss/train': 1.184779167175293} 08/30/2021 19:49:10 - INFO - __main__ - Step 36612: {'lr': 0.00043551016705320965, 'samples': 7029504, 'steps': 36611, 'loss/train': 1.491159200668335} 08/30/2021 19:49:10 - INFO - __main__ - Step 36613: {'lr': 0.00043550660960951874, 'samples': 7029696, 'steps': 36612, 'loss/train': 0.6981892585754395} 08/30/2021 19:49:10 - INFO - __main__ - Step 36614: {'lr': 0.0004355030520822414, 'samples': 7029888, 'steps': 36613, 'loss/train': 1.2497870922088623} 08/30/2021 19:49:12 - INFO - __main__ - Step 36615: {'lr': 0.00043549949447137915, 'samples': 7030080, 'steps': 36614, 'loss/train': 1.1743836402893066} 08/30/2021 19:49:12 - INFO - __main__ - Step 36616: {'lr': 0.00043549593677693385, 'samples': 7030272, 'steps': 36615, 'loss/train': 1.3580169677734375} 08/30/2021 19:49:13 - INFO - __main__ - Step 36617: {'lr': 0.0004354923789989068, 'samples': 7030464, 'steps': 36616, 'loss/train': 1.4517509937286377} 08/30/2021 19:49:13 - INFO - __main__ - Step 36618: {'lr': 0.0004354888211372998, 'samples': 7030656, 'steps': 36617, 'loss/train': 0.4366558790206909} 08/30/2021 19:49:13 - INFO - __main__ - Step 36619: {'lr': 0.0004354852631921145, 'samples': 7030848, 'steps': 36618, 'loss/train': 1.0512324571609497} 08/30/2021 19:49:15 - INFO - __main__ - Step 36620: {'lr': 0.0004354817051633523, 'samples': 7031040, 'steps': 36619, 'loss/train': 1.2595950365066528} 08/30/2021 19:49:15 - INFO - __main__ - Step 36621: {'lr': 0.00043547814705101486, 'samples': 7031232, 'steps': 36620, 'loss/train': 2.4898011684417725} 08/30/2021 19:49:16 - INFO - __main__ - Step 36622: {'lr': 0.00043547458885510393, 'samples': 7031424, 'steps': 36621, 'loss/train': 1.334200143814087} 08/30/2021 19:49:16 - INFO - __main__ - Step 36623: {'lr': 0.00043547103057562097, 'samples': 7031616, 'steps': 36622, 'loss/train': 1.209738850593567} 08/30/2021 19:49:16 - INFO - __main__ - Step 36624: {'lr': 0.00043546747221256764, 'samples': 7031808, 'steps': 36623, 'loss/train': 3.094558000564575} 08/30/2021 19:49:17 - INFO - __main__ - Step 36625: {'lr': 0.00043546391376594553, 'samples': 7032000, 'steps': 36624, 'loss/train': 1.9644629955291748} 08/30/2021 19:49:18 - INFO - __main__ - Step 36626: {'lr': 0.0004354603552357562, 'samples': 7032192, 'steps': 36625, 'loss/train': 1.131923794746399} 08/30/2021 19:49:19 - INFO - __main__ - Step 36627: {'lr': 0.0004354567966220013, 'samples': 7032384, 'steps': 36626, 'loss/train': 1.3133677244186401} 08/30/2021 19:49:19 - INFO - __main__ - Step 36628: {'lr': 0.0004354532379246825, 'samples': 7032576, 'steps': 36627, 'loss/train': 1.3306858539581299} 08/30/2021 19:49:19 - INFO - __main__ - Step 36629: {'lr': 0.0004354496791438013, 'samples': 7032768, 'steps': 36628, 'loss/train': 1.0869311094284058} 08/30/2021 19:49:20 - INFO - __main__ - Step 36630: {'lr': 0.0004354461202793593, 'samples': 7032960, 'steps': 36629, 'loss/train': 1.7309787273406982} 08/30/2021 19:49:21 - INFO - __main__ - Step 36631: {'lr': 0.00043544256133135815, 'samples': 7033152, 'steps': 36630, 'loss/train': 0.3938276767730713} 08/30/2021 19:49:22 - INFO - __main__ - Step 36632: {'lr': 0.0004354390022997995, 'samples': 7033344, 'steps': 36631, 'loss/train': 1.2225375175476074} 08/30/2021 19:49:22 - INFO - __main__ - Step 36633: {'lr': 0.0004354354431846848, 'samples': 7033536, 'steps': 36632, 'loss/train': 1.5289702415466309} 08/30/2021 19:49:22 - INFO - __main__ - Step 36634: {'lr': 0.00043543188398601586, 'samples': 7033728, 'steps': 36633, 'loss/train': 1.410776138305664} 08/30/2021 19:49:23 - INFO - __main__ - Step 36635: {'lr': 0.00043542832470379415, 'samples': 7033920, 'steps': 36634, 'loss/train': 0.9819300174713135} 08/30/2021 19:49:24 - INFO - __main__ - Step 36636: {'lr': 0.0004354247653380212, 'samples': 7034112, 'steps': 36635, 'loss/train': 0.7413052916526794} 08/30/2021 19:49:25 - INFO - __main__ - Step 36637: {'lr': 0.00043542120588869885, 'samples': 7034304, 'steps': 36636, 'loss/train': 1.367821216583252} 08/30/2021 19:49:25 - INFO - __main__ - Step 36638: {'lr': 0.0004354176463558284, 'samples': 7034496, 'steps': 36637, 'loss/train': 1.754111647605896} 08/30/2021 19:49:25 - INFO - __main__ - Step 36639: {'lr': 0.00043541408673941173, 'samples': 7034688, 'steps': 36638, 'loss/train': 1.5507147312164307} 08/30/2021 19:49:26 - INFO - __main__ - Step 36640: {'lr': 0.00043541052703945034, 'samples': 7034880, 'steps': 36639, 'loss/train': 1.081290602684021} 08/30/2021 19:49:28 - INFO - __main__ - Step 36641: {'lr': 0.0004354069672559458, 'samples': 7035072, 'steps': 36640, 'loss/train': 1.4214664697647095} 08/30/2021 19:49:28 - INFO - __main__ - Step 36642: {'lr': 0.0004354034073888997, 'samples': 7035264, 'steps': 36641, 'loss/train': 0.8091091513633728} 08/30/2021 19:49:29 - INFO - __main__ - Step 36643: {'lr': 0.00043539984743831375, 'samples': 7035456, 'steps': 36642, 'loss/train': 0.8957213759422302} 08/30/2021 19:49:29 - INFO - __main__ - Step 36644: {'lr': 0.0004353962874041895, 'samples': 7035648, 'steps': 36643, 'loss/train': 0.9911098480224609} 08/30/2021 19:49:29 - INFO - __main__ - Step 36645: {'lr': 0.0004353927272865285, 'samples': 7035840, 'steps': 36644, 'loss/train': 1.4371337890625} 08/30/2021 19:49:30 - INFO - __main__ - Step 36646: {'lr': 0.0004353891670853324, 'samples': 7036032, 'steps': 36645, 'loss/train': 2.2173895835876465} 08/30/2021 19:49:30 - INFO - __main__ - Step 36647: {'lr': 0.00043538560680060287, 'samples': 7036224, 'steps': 36646, 'loss/train': 1.6057382822036743} 08/30/2021 19:49:32 - INFO - __main__ - Step 36648: {'lr': 0.00043538204643234137, 'samples': 7036416, 'steps': 36647, 'loss/train': 1.1364264488220215} 08/30/2021 19:49:32 - INFO - __main__ - Step 36649: {'lr': 0.0004353784859805496, 'samples': 7036608, 'steps': 36648, 'loss/train': 1.198661208152771} 08/30/2021 19:49:33 - INFO - __main__ - Step 36650: {'lr': 0.00043537492544522917, 'samples': 7036800, 'steps': 36649, 'loss/train': 1.7976967096328735} 08/30/2021 19:49:33 - INFO - __main__ - Step 36651: {'lr': 0.0004353713648263816, 'samples': 7036992, 'steps': 36650, 'loss/train': 1.2448914051055908} 08/30/2021 19:49:33 - INFO - __main__ - Step 36652: {'lr': 0.00043536780412400857, 'samples': 7037184, 'steps': 36651, 'loss/train': 1.5411320924758911} 08/30/2021 19:49:35 - INFO - __main__ - Step 36653: {'lr': 0.0004353642433381117, 'samples': 7037376, 'steps': 36652, 'loss/train': 1.1788196563720703} 08/30/2021 19:49:35 - INFO - __main__ - Step 36654: {'lr': 0.00043536068246869254, 'samples': 7037568, 'steps': 36653, 'loss/train': 1.728651762008667} 08/30/2021 19:49:36 - INFO - __main__ - Step 36655: {'lr': 0.00043535712151575274, 'samples': 7037760, 'steps': 36654, 'loss/train': 1.6517583131790161} 08/30/2021 19:49:36 - INFO - __main__ - Step 36656: {'lr': 0.00043535356047929387, 'samples': 7037952, 'steps': 36655, 'loss/train': 1.6122596263885498} 08/30/2021 19:49:36 - INFO - __main__ - Step 36657: {'lr': 0.0004353499993593176, 'samples': 7038144, 'steps': 36656, 'loss/train': 1.6522592306137085} 08/30/2021 19:49:38 - INFO - __main__ - Step 36658: {'lr': 0.0004353464381558254, 'samples': 7038336, 'steps': 36657, 'loss/train': 1.2207783460617065} 08/30/2021 19:49:38 - INFO - __main__ - Step 36659: {'lr': 0.00043534287686881895, 'samples': 7038528, 'steps': 36658, 'loss/train': 1.5376250743865967} 08/30/2021 19:49:39 - INFO - __main__ - Step 36660: {'lr': 0.00043533931549829993, 'samples': 7038720, 'steps': 36659, 'loss/train': 0.8740956783294678} 08/30/2021 19:49:39 - INFO - __main__ - Step 36661: {'lr': 0.00043533575404426986, 'samples': 7038912, 'steps': 36660, 'loss/train': 1.4214528799057007} 08/30/2021 19:49:39 - INFO - __main__ - Step 36662: {'lr': 0.0004353321925067303, 'samples': 7039104, 'steps': 36661, 'loss/train': 1.2832437753677368} 08/30/2021 19:49:41 - INFO - __main__ - Step 36663: {'lr': 0.0004353286308856829, 'samples': 7039296, 'steps': 36662, 'loss/train': 0.044129423797130585} 08/30/2021 19:49:42 - INFO - __main__ - Step 36664: {'lr': 0.00043532506918112933, 'samples': 7039488, 'steps': 36663, 'loss/train': 1.424027442932129} 08/30/2021 19:49:42 - INFO - __main__ - Step 36665: {'lr': 0.0004353215073930712, 'samples': 7039680, 'steps': 36664, 'loss/train': 1.690145492553711} 08/30/2021 19:49:43 - INFO - __main__ - Step 36666: {'lr': 0.00043531794552150994, 'samples': 7039872, 'steps': 36665, 'loss/train': 0.25014355778694153} 08/30/2021 19:49:43 - INFO - __main__ - Step 36667: {'lr': 0.0004353143835664474, 'samples': 7040064, 'steps': 36666, 'loss/train': 0.4051026403903961} 08/30/2021 19:49:44 - INFO - __main__ - Step 36668: {'lr': 0.00043531082152788495, 'samples': 7040256, 'steps': 36667, 'loss/train': 0.6898967027664185} 08/30/2021 19:49:45 - INFO - __main__ - Step 36669: {'lr': 0.0004353072594058243, 'samples': 7040448, 'steps': 36668, 'loss/train': 1.3379818201065063} 08/30/2021 19:49:45 - INFO - __main__ - Step 36670: {'lr': 0.0004353036972002671, 'samples': 7040640, 'steps': 36669, 'loss/train': 1.7584658861160278} 08/30/2021 19:49:46 - INFO - __main__ - Step 36671: {'lr': 0.00043530013491121497, 'samples': 7040832, 'steps': 36670, 'loss/train': 1.6686280965805054} 08/30/2021 19:49:46 - INFO - __main__ - Step 36672: {'lr': 0.00043529657253866936, 'samples': 7041024, 'steps': 36671, 'loss/train': 1.2137001752853394} 08/30/2021 19:49:47 - INFO - __main__ - Step 36673: {'lr': 0.000435293010082632, 'samples': 7041216, 'steps': 36672, 'loss/train': 1.3776910305023193} 08/30/2021 19:49:48 - INFO - __main__ - Step 36674: {'lr': 0.0004352894475431045, 'samples': 7041408, 'steps': 36673, 'loss/train': 1.8339715003967285} 08/30/2021 19:49:48 - INFO - __main__ - Step 36675: {'lr': 0.0004352858849200885, 'samples': 7041600, 'steps': 36674, 'loss/train': 0.048947595059871674} 08/30/2021 19:49:49 - INFO - __main__ - Step 36676: {'lr': 0.0004352823222135854, 'samples': 7041792, 'steps': 36675, 'loss/train': 1.431644320487976} 08/30/2021 19:49:49 - INFO - __main__ - Step 36677: {'lr': 0.00043527875942359697, 'samples': 7041984, 'steps': 36676, 'loss/train': 1.2802859544754028} 08/30/2021 19:49:50 - INFO - __main__ - Step 36678: {'lr': 0.0004352751965501248, 'samples': 7042176, 'steps': 36677, 'loss/train': 1.8463026285171509} 08/30/2021 19:49:51 - INFO - __main__ - Step 36679: {'lr': 0.0004352716335931706, 'samples': 7042368, 'steps': 36678, 'loss/train': 1.1140857934951782} 08/30/2021 19:49:51 - INFO - __main__ - Step 36680: {'lr': 0.0004352680705527357, 'samples': 7042560, 'steps': 36679, 'loss/train': 1.790854811668396} 08/30/2021 19:49:52 - INFO - __main__ - Step 36681: {'lr': 0.00043526450742882193, 'samples': 7042752, 'steps': 36680, 'loss/train': 1.316838264465332} 08/30/2021 19:49:52 - INFO - __main__ - Step 36682: {'lr': 0.0004352609442214309, 'samples': 7042944, 'steps': 36681, 'loss/train': 1.2183455228805542} 08/30/2021 19:49:54 - INFO - __main__ - Step 36683: {'lr': 0.00043525738093056404, 'samples': 7043136, 'steps': 36682, 'loss/train': 1.3153342008590698} 08/30/2021 19:49:54 - INFO - __main__ - Step 36684: {'lr': 0.0004352538175562231, 'samples': 7043328, 'steps': 36683, 'loss/train': 1.073585867881775} 08/30/2021 19:49:55 - INFO - __main__ - Step 36685: {'lr': 0.00043525025409840967, 'samples': 7043520, 'steps': 36684, 'loss/train': 0.9450781941413879} 08/30/2021 19:49:55 - INFO - __main__ - Step 36686: {'lr': 0.00043524669055712534, 'samples': 7043712, 'steps': 36685, 'loss/train': 1.3040051460266113} 08/30/2021 19:49:55 - INFO - __main__ - Step 36687: {'lr': 0.00043524312693237166, 'samples': 7043904, 'steps': 36686, 'loss/train': 1.2252814769744873} 08/30/2021 19:49:56 - INFO - __main__ - Step 36688: {'lr': 0.0004352395632241504, 'samples': 7044096, 'steps': 36687, 'loss/train': 0.060605812817811966} 08/30/2021 19:49:58 - INFO - __main__ - Step 36689: {'lr': 0.00043523599943246297, 'samples': 7044288, 'steps': 36688, 'loss/train': 0.7352709770202637} 08/30/2021 19:49:58 - INFO - __main__ - Step 36690: {'lr': 0.00043523243555731094, 'samples': 7044480, 'steps': 36689, 'loss/train': 1.1972976922988892} 08/30/2021 19:49:58 - INFO - __main__ - Step 36691: {'lr': 0.00043522887159869617, 'samples': 7044672, 'steps': 36690, 'loss/train': 1.4369250535964966} 08/30/2021 19:49:59 - INFO - __main__ - Step 36692: {'lr': 0.00043522530755662017, 'samples': 7044864, 'steps': 36691, 'loss/train': 1.1358816623687744} 08/30/2021 19:49:59 - INFO - __main__ - Step 36693: {'lr': 0.00043522174343108445, 'samples': 7045056, 'steps': 36692, 'loss/train': 0.2358015775680542} 08/30/2021 19:49:59 - INFO - __main__ - Step 36694: {'lr': 0.00043521817922209064, 'samples': 7045248, 'steps': 36693, 'loss/train': 0.2850950062274933} 08/30/2021 19:50:01 - INFO - __main__ - Step 36695: {'lr': 0.00043521461492964037, 'samples': 7045440, 'steps': 36694, 'loss/train': 1.0765414237976074} 08/30/2021 19:50:02 - INFO - __main__ - Step 36696: {'lr': 0.00043521105055373526, 'samples': 7045632, 'steps': 36695, 'loss/train': 1.4708921909332275} 08/30/2021 19:50:02 - INFO - __main__ - Step 36697: {'lr': 0.000435207486094377, 'samples': 7045824, 'steps': 36696, 'loss/train': 1.1216543912887573} 08/30/2021 19:50:02 - INFO - __main__ - Step 36698: {'lr': 0.00043520392155156694, 'samples': 7046016, 'steps': 36697, 'loss/train': 1.6061737537384033} 08/30/2021 19:50:03 - INFO - __main__ - Step 36699: {'lr': 0.000435200356925307, 'samples': 7046208, 'steps': 36698, 'loss/train': 1.096311092376709} 08/30/2021 19:50:03 - INFO - __main__ - Step 36700: {'lr': 0.0004351967922155986, 'samples': 7046400, 'steps': 36699, 'loss/train': 1.0611648559570312} 08/30/2021 19:50:05 - INFO - __main__ - Step 36701: {'lr': 0.0004351932274224434, 'samples': 7046592, 'steps': 36700, 'loss/train': 1.1511927843093872} 08/30/2021 19:50:05 - INFO - __main__ - Step 36702: {'lr': 0.0004351896625458429, 'samples': 7046784, 'steps': 36701, 'loss/train': 1.3228759765625} 08/30/2021 19:50:05 - INFO - __main__ - Step 36703: {'lr': 0.0004351860975857989, 'samples': 7046976, 'steps': 36702, 'loss/train': 1.0734847784042358} 08/30/2021 19:50:06 - INFO - __main__ - Step 36704: {'lr': 0.00043518253254231276, 'samples': 7047168, 'steps': 36703, 'loss/train': 1.5056232213974} 08/30/2021 19:50:06 - INFO - __main__ - Step 36705: {'lr': 0.00043517896741538634, 'samples': 7047360, 'steps': 36704, 'loss/train': 1.000693678855896} 08/30/2021 19:50:08 - INFO - __main__ - Step 36706: {'lr': 0.0004351754022050212, 'samples': 7047552, 'steps': 36705, 'loss/train': 1.2989751100540161} 08/30/2021 19:50:08 - INFO - __main__ - Step 36707: {'lr': 0.00043517183691121875, 'samples': 7047744, 'steps': 36706, 'loss/train': 1.2257020473480225} 08/30/2021 19:50:09 - INFO - __main__ - Step 36708: {'lr': 0.00043516827153398073, 'samples': 7047936, 'steps': 36707, 'loss/train': 1.4511054754257202} 08/30/2021 19:50:09 - INFO - __main__ - Step 36709: {'lr': 0.0004351647060733088, 'samples': 7048128, 'steps': 36708, 'loss/train': 1.8234800100326538} 08/30/2021 19:50:09 - INFO - __main__ - Step 36710: {'lr': 0.00043516114052920453, 'samples': 7048320, 'steps': 36709, 'loss/train': 1.5382531881332397} 08/30/2021 19:50:11 - INFO - __main__ - Step 36711: {'lr': 0.00043515757490166944, 'samples': 7048512, 'steps': 36710, 'loss/train': 1.3825267553329468} 08/30/2021 19:50:11 - INFO - __main__ - Step 36712: {'lr': 0.00043515400919070526, 'samples': 7048704, 'steps': 36711, 'loss/train': 0.8438291549682617} 08/30/2021 19:50:12 - INFO - __main__ - Step 36713: {'lr': 0.0004351504433963135, 'samples': 7048896, 'steps': 36712, 'loss/train': 1.3279600143432617} 08/30/2021 19:50:12 - INFO - __main__ - Step 36714: {'lr': 0.0004351468775184959, 'samples': 7049088, 'steps': 36713, 'loss/train': 1.023358702659607} 08/30/2021 19:50:12 - INFO - __main__ - Step 36715: {'lr': 0.0004351433115572538, 'samples': 7049280, 'steps': 36714, 'loss/train': 1.5246587991714478} 08/30/2021 19:50:14 - INFO - __main__ - Step 36716: {'lr': 0.00043513974551258913, 'samples': 7049472, 'steps': 36715, 'loss/train': 1.4114965200424194} 08/30/2021 19:50:14 - INFO - __main__ - Step 36717: {'lr': 0.00043513617938450327, 'samples': 7049664, 'steps': 36716, 'loss/train': 1.702172040939331} 08/30/2021 19:50:15 - INFO - __main__ - Step 36718: {'lr': 0.00043513261317299797, 'samples': 7049856, 'steps': 36717, 'loss/train': 0.9815688729286194} 08/30/2021 19:50:15 - INFO - __main__ - Step 36719: {'lr': 0.00043512904687807475, 'samples': 7050048, 'steps': 36718, 'loss/train': 1.148401141166687} 08/30/2021 19:50:15 - INFO - __main__ - Step 36720: {'lr': 0.00043512548049973523, 'samples': 7050240, 'steps': 36719, 'loss/train': 0.8587327003479004} 08/30/2021 19:50:17 - INFO - __main__ - Step 36721: {'lr': 0.00043512191403798095, 'samples': 7050432, 'steps': 36720, 'loss/train': 1.6336232423782349} 08/30/2021 19:50:18 - INFO - __main__ - Step 36722: {'lr': 0.0004351183474928137, 'samples': 7050624, 'steps': 36721, 'loss/train': 1.1510086059570312} 08/30/2021 19:50:18 - INFO - __main__ - Step 36723: {'lr': 0.00043511478086423493, 'samples': 7050816, 'steps': 36722, 'loss/train': 1.3894286155700684} 08/30/2021 19:50:19 - INFO - __main__ - Step 36724: {'lr': 0.0004351112141522463, 'samples': 7051008, 'steps': 36723, 'loss/train': 1.3885177373886108} 08/30/2021 19:50:19 - INFO - __main__ - Step 36725: {'lr': 0.00043510764735684945, 'samples': 7051200, 'steps': 36724, 'loss/train': 1.2266805171966553} 08/30/2021 19:50:20 - INFO - __main__ - Step 36726: {'lr': 0.0004351040804780459, 'samples': 7051392, 'steps': 36725, 'loss/train': 1.6934620141983032} 08/30/2021 19:50:21 - INFO - __main__ - Step 36727: {'lr': 0.00043510051351583733, 'samples': 7051584, 'steps': 36726, 'loss/train': 1.350189447402954} 08/30/2021 19:50:21 - INFO - __main__ - Step 36728: {'lr': 0.0004350969464702254, 'samples': 7051776, 'steps': 36727, 'loss/train': 1.2746144533157349} 08/30/2021 19:50:22 - INFO - __main__ - Step 36729: {'lr': 0.0004350933793412115, 'samples': 7051968, 'steps': 36728, 'loss/train': 1.035346269607544} 08/30/2021 19:50:22 - INFO - __main__ - Step 36730: {'lr': 0.00043508981212879737, 'samples': 7052160, 'steps': 36729, 'loss/train': 1.4221863746643066} 08/30/2021 19:50:22 - INFO - __main__ - Step 36731: {'lr': 0.0004350862448329848, 'samples': 7052352, 'steps': 36730, 'loss/train': 1.3501044511795044} 08/30/2021 19:50:24 - INFO - __main__ - Step 36732: {'lr': 0.00043508267745377504, 'samples': 7052544, 'steps': 36731, 'loss/train': 1.5294417142868042} 08/30/2021 19:50:24 - INFO - __main__ - Step 36733: {'lr': 0.00043507910999117003, 'samples': 7052736, 'steps': 36732, 'loss/train': 1.114034652709961} 08/30/2021 19:50:25 - INFO - __main__ - Step 36734: {'lr': 0.00043507554244517113, 'samples': 7052928, 'steps': 36733, 'loss/train': 1.204210638999939} 08/30/2021 19:50:25 - INFO - __main__ - Step 36735: {'lr': 0.0004350719748157801, 'samples': 7053120, 'steps': 36734, 'loss/train': 1.4735853672027588} 08/30/2021 19:50:25 - INFO - __main__ - Step 36736: {'lr': 0.00043506840710299844, 'samples': 7053312, 'steps': 36735, 'loss/train': 0.8844746947288513} 08/30/2021 19:50:27 - INFO - __main__ - Step 36737: {'lr': 0.00043506483930682785, 'samples': 7053504, 'steps': 36736, 'loss/train': 1.420186161994934} 08/30/2021 19:50:27 - INFO - __main__ - Step 36738: {'lr': 0.0004350612714272699, 'samples': 7053696, 'steps': 36737, 'loss/train': 1.5141267776489258} 08/30/2021 19:50:28 - INFO - __main__ - Step 36739: {'lr': 0.0004350577034643262, 'samples': 7053888, 'steps': 36738, 'loss/train': 1.4006013870239258} 08/30/2021 19:50:28 - INFO - __main__ - Step 36740: {'lr': 0.0004350541354179983, 'samples': 7054080, 'steps': 36739, 'loss/train': 1.53284752368927} 08/30/2021 19:50:28 - INFO - __main__ - Step 36741: {'lr': 0.00043505056728828794, 'samples': 7054272, 'steps': 36740, 'loss/train': 0.5731781721115112} 08/30/2021 19:50:30 - INFO - __main__ - Step 36742: {'lr': 0.0004350469990751966, 'samples': 7054464, 'steps': 36741, 'loss/train': 1.130262017250061} 08/30/2021 19:50:30 - INFO - __main__ - Step 36743: {'lr': 0.000435043430778726, 'samples': 7054656, 'steps': 36742, 'loss/train': 2.417330265045166} 08/30/2021 19:50:31 - INFO - __main__ - Step 36744: {'lr': 0.00043503986239887765, 'samples': 7054848, 'steps': 36743, 'loss/train': 1.7894667387008667} 08/30/2021 19:50:31 - INFO - __main__ - Step 36745: {'lr': 0.0004350362939356532, 'samples': 7055040, 'steps': 36744, 'loss/train': 1.0532146692276} 08/30/2021 19:50:31 - INFO - __main__ - Step 36746: {'lr': 0.00043503272538905423, 'samples': 7055232, 'steps': 36745, 'loss/train': 1.0075383186340332} 08/30/2021 19:50:33 - INFO - __main__ - Step 36747: {'lr': 0.0004350291567590824, 'samples': 7055424, 'steps': 36746, 'loss/train': 1.5667258501052856} 08/30/2021 19:50:33 - INFO - __main__ - Step 36748: {'lr': 0.00043502558804573924, 'samples': 7055616, 'steps': 36747, 'loss/train': 1.3375009298324585} 08/30/2021 19:50:34 - INFO - __main__ - Step 36749: {'lr': 0.0004350220192490264, 'samples': 7055808, 'steps': 36748, 'loss/train': 1.066444993019104} 08/30/2021 19:50:34 - INFO - __main__ - Step 36750: {'lr': 0.00043501845036894555, 'samples': 7056000, 'steps': 36749, 'loss/train': 1.5496065616607666} 08/30/2021 19:50:34 - INFO - __main__ - Step 36751: {'lr': 0.00043501488140549824, 'samples': 7056192, 'steps': 36750, 'loss/train': 1.5164856910705566} 08/30/2021 19:50:36 - INFO - __main__ - Step 36752: {'lr': 0.000435011312358686, 'samples': 7056384, 'steps': 36751, 'loss/train': 1.5143030881881714} 08/30/2021 19:50:36 - INFO - __main__ - Step 36753: {'lr': 0.0004350077432285106, 'samples': 7056576, 'steps': 36752, 'loss/train': 1.4826269149780273} 08/30/2021 19:50:37 - INFO - __main__ - Step 36754: {'lr': 0.0004350041740149735, 'samples': 7056768, 'steps': 36753, 'loss/train': 1.3413727283477783} 08/30/2021 19:50:37 - INFO - __main__ - Step 36755: {'lr': 0.00043500060471807645, 'samples': 7056960, 'steps': 36754, 'loss/train': 1.3902397155761719} 08/30/2021 19:50:37 - INFO - __main__ - Step 36756: {'lr': 0.000434997035337821, 'samples': 7057152, 'steps': 36755, 'loss/train': 1.5261427164077759} 08/30/2021 19:50:38 - INFO - __main__ - Step 36757: {'lr': 0.0004349934658742086, 'samples': 7057344, 'steps': 36756, 'loss/train': 1.793416142463684} 08/30/2021 19:50:39 - INFO - __main__ - Step 36758: {'lr': 0.00043498989632724105, 'samples': 7057536, 'steps': 36757, 'loss/train': 0.07235637307167053} 08/30/2021 19:50:40 - INFO - __main__ - Step 36759: {'lr': 0.00043498632669692, 'samples': 7057728, 'steps': 36758, 'loss/train': 1.0857549905776978} 08/30/2021 19:50:40 - INFO - __main__ - Step 36760: {'lr': 0.0004349827569832469, 'samples': 7057920, 'steps': 36759, 'loss/train': 1.811194896697998} 08/30/2021 19:50:41 - INFO - __main__ - Step 36761: {'lr': 0.00043497918718622344, 'samples': 7058112, 'steps': 36760, 'loss/train': 1.170149326324463} 08/30/2021 19:50:41 - INFO - __main__ - Step 36762: {'lr': 0.0004349756173058512, 'samples': 7058304, 'steps': 36761, 'loss/train': 1.4687120914459229} 08/30/2021 19:50:43 - INFO - __main__ - Step 36763: {'lr': 0.0004349720473421318, 'samples': 7058496, 'steps': 36762, 'loss/train': 1.5276732444763184} 08/30/2021 19:50:43 - INFO - __main__ - Step 36764: {'lr': 0.00043496847729506685, 'samples': 7058688, 'steps': 36763, 'loss/train': 1.513434648513794} 08/30/2021 19:50:43 - INFO - __main__ - Step 36765: {'lr': 0.000434964907164658, 'samples': 7058880, 'steps': 36764, 'loss/train': 0.8090911507606506} 08/30/2021 19:50:44 - INFO - __main__ - Step 36766: {'lr': 0.0004349613369509067, 'samples': 7059072, 'steps': 36765, 'loss/train': 1.393768072128296} 08/30/2021 19:50:44 - INFO - __main__ - Step 36767: {'lr': 0.0004349577666538148, 'samples': 7059264, 'steps': 36766, 'loss/train': 1.1167211532592773} 08/30/2021 19:50:46 - INFO - __main__ - Step 36768: {'lr': 0.0004349541962733837, 'samples': 7059456, 'steps': 36767, 'loss/train': 1.119260549545288} 08/30/2021 19:50:46 - INFO - __main__ - Step 36769: {'lr': 0.0004349506258096152, 'samples': 7059648, 'steps': 36768, 'loss/train': 1.2865499258041382} 08/30/2021 19:50:46 - INFO - __main__ - Step 36770: {'lr': 0.00043494705526251064, 'samples': 7059840, 'steps': 36769, 'loss/train': 1.5907214879989624} 08/30/2021 19:50:47 - INFO - __main__ - Step 36771: {'lr': 0.00043494348463207197, 'samples': 7060032, 'steps': 36770, 'loss/train': 1.2490900754928589} 08/30/2021 19:50:47 - INFO - __main__ - Step 36772: {'lr': 0.0004349399139183005, 'samples': 7060224, 'steps': 36771, 'loss/train': 1.3989109992980957} 08/30/2021 19:50:50 - INFO - __main__ - Step 36773: {'lr': 0.000434936343121198, 'samples': 7060416, 'steps': 36772, 'loss/train': 0.5802854895591736} 08/30/2021 19:50:50 - INFO - __main__ - Step 36774: {'lr': 0.000434932772240766, 'samples': 7060608, 'steps': 36773, 'loss/train': 2.3337364196777344} 08/30/2021 19:50:50 - INFO - __main__ - Step 36775: {'lr': 0.0004349292012770062, 'samples': 7060800, 'steps': 36774, 'loss/train': 1.7584441900253296} 08/30/2021 19:50:51 - INFO - __main__ - Step 36776: {'lr': 0.00043492563022992013, 'samples': 7060992, 'steps': 36775, 'loss/train': 0.41401219367980957} 08/30/2021 19:50:51 - INFO - __main__ - Step 36777: {'lr': 0.00043492205909950943, 'samples': 7061184, 'steps': 36776, 'loss/train': 1.0634077787399292} 08/30/2021 19:50:52 - INFO - __main__ - Step 36778: {'lr': 0.0004349184878857757, 'samples': 7061376, 'steps': 36777, 'loss/train': 0.6090685725212097} 08/30/2021 19:50:53 - INFO - __main__ - Step 36779: {'lr': 0.0004349149165887205, 'samples': 7061568, 'steps': 36778, 'loss/train': 2.570732593536377} 08/30/2021 19:50:53 - INFO - __main__ - Step 36780: {'lr': 0.0004349113452083456, 'samples': 7061760, 'steps': 36779, 'loss/train': 1.5769164562225342} 08/30/2021 19:50:54 - INFO - __main__ - Step 36781: {'lr': 0.00043490777374465244, 'samples': 7061952, 'steps': 36780, 'loss/train': 1.5659064054489136} 08/30/2021 19:50:54 - INFO - __main__ - Step 36782: {'lr': 0.0004349042021976427, 'samples': 7062144, 'steps': 36781, 'loss/train': 1.8731383085250854} 08/30/2021 19:50:55 - INFO - __main__ - Step 36783: {'lr': 0.000434900630567318, 'samples': 7062336, 'steps': 36782, 'loss/train': 1.11239492893219} 08/30/2021 19:50:56 - INFO - __main__ - Step 36784: {'lr': 0.00043489705885367986, 'samples': 7062528, 'steps': 36783, 'loss/train': 1.7922813892364502} 08/30/2021 19:50:56 - INFO - __main__ - Step 36785: {'lr': 0.00043489348705673, 'samples': 7062720, 'steps': 36784, 'loss/train': 1.6734100580215454} 08/30/2021 19:50:57 - INFO - __main__ - Step 36786: {'lr': 0.00043488991517647, 'samples': 7062912, 'steps': 36785, 'loss/train': 1.780049443244934} 08/30/2021 19:50:57 - INFO - __main__ - Step 36787: {'lr': 0.00043488634321290146, 'samples': 7063104, 'steps': 36786, 'loss/train': 1.3812592029571533} 08/30/2021 19:50:57 - INFO - __main__ - Step 36788: {'lr': 0.000434882771166026, 'samples': 7063296, 'steps': 36787, 'loss/train': 1.7514374256134033} 08/30/2021 19:50:58 - INFO - __main__ - Step 36789: {'lr': 0.00043487919903584515, 'samples': 7063488, 'steps': 36788, 'loss/train': 1.6486750841140747} 08/30/2021 19:51:00 - INFO - __main__ - Step 36790: {'lr': 0.00043487562682236066, 'samples': 7063680, 'steps': 36789, 'loss/train': 1.6784473657608032} 08/30/2021 19:51:00 - INFO - __main__ - Step 36791: {'lr': 0.000434872054525574, 'samples': 7063872, 'steps': 36790, 'loss/train': 1.5071698427200317} 08/30/2021 19:51:01 - INFO - __main__ - Step 36792: {'lr': 0.00043486848214548693, 'samples': 7064064, 'steps': 36791, 'loss/train': 0.7901178002357483} 08/30/2021 19:51:01 - INFO - __main__ - Step 36793: {'lr': 0.0004348649096821009, 'samples': 7064256, 'steps': 36792, 'loss/train': 1.458463191986084} 08/30/2021 19:51:01 - INFO - __main__ - Step 36794: {'lr': 0.0004348613371354176, 'samples': 7064448, 'steps': 36793, 'loss/train': 2.257478952407837} 08/30/2021 19:51:04 - INFO - __main__ - Step 36795: {'lr': 0.0004348577645054387, 'samples': 7064640, 'steps': 36794, 'loss/train': 0.14407555758953094} 08/30/2021 19:51:04 - INFO - __main__ - Step 36796: {'lr': 0.0004348541917921657, 'samples': 7064832, 'steps': 36795, 'loss/train': 1.0325839519500732} 08/30/2021 19:51:04 - INFO - __main__ - Step 36797: {'lr': 0.0004348506189956002, 'samples': 7065024, 'steps': 36796, 'loss/train': 1.8709971904754639} 08/30/2021 19:51:05 - INFO - __main__ - Step 36798: {'lr': 0.0004348470461157439, 'samples': 7065216, 'steps': 36797, 'loss/train': 1.183646321296692} 08/30/2021 19:51:05 - INFO - __main__ - Step 36799: {'lr': 0.0004348434731525984, 'samples': 7065408, 'steps': 36798, 'loss/train': 1.7938910722732544} 08/30/2021 19:51:05 - INFO - __main__ - Step 36800: {'lr': 0.00043483990010616524, 'samples': 7065600, 'steps': 36799, 'loss/train': 1.2465991973876953} 08/30/2021 19:51:07 - INFO - __main__ - Step 36801: {'lr': 0.00043483632697644616, 'samples': 7065792, 'steps': 36800, 'loss/train': 0.11328092962503433} 08/30/2021 19:51:08 - INFO - __main__ - Step 36802: {'lr': 0.00043483275376344257, 'samples': 7065984, 'steps': 36801, 'loss/train': 1.626562237739563} 08/30/2021 19:51:08 - INFO - __main__ - Step 36803: {'lr': 0.00043482918046715627, 'samples': 7066176, 'steps': 36802, 'loss/train': 0.9440440535545349} 08/30/2021 19:51:08 - INFO - __main__ - Step 36804: {'lr': 0.00043482560708758876, 'samples': 7066368, 'steps': 36803, 'loss/train': 1.7031415700912476} 08/30/2021 19:51:09 - INFO - __main__ - Step 36805: {'lr': 0.0004348220336247417, 'samples': 7066560, 'steps': 36804, 'loss/train': 1.7413356304168701} 08/30/2021 19:51:09 - INFO - __main__ - Step 36806: {'lr': 0.0004348184600786167, 'samples': 7066752, 'steps': 36805, 'loss/train': 1.2216918468475342} 08/30/2021 19:51:10 - INFO - __main__ - Step 36807: {'lr': 0.0004348148864492153, 'samples': 7066944, 'steps': 36806, 'loss/train': 1.392309546470642} 08/30/2021 19:51:11 - INFO - __main__ - Step 36808: {'lr': 0.00043481131273653926, 'samples': 7067136, 'steps': 36807, 'loss/train': 0.5392890572547913} 08/30/2021 19:51:11 - INFO - __main__ - Step 36809: {'lr': 0.00043480773894059, 'samples': 7067328, 'steps': 36808, 'loss/train': 1.9753751754760742} 08/30/2021 19:51:12 - INFO - __main__ - Step 36810: {'lr': 0.0004348041650613692, 'samples': 7067520, 'steps': 36809, 'loss/train': 1.767722249031067} 08/30/2021 19:51:12 - INFO - __main__ - Step 36811: {'lr': 0.0004348005910988786, 'samples': 7067712, 'steps': 36810, 'loss/train': 1.9477856159210205} 08/30/2021 19:51:14 - INFO - __main__ - Step 36812: {'lr': 0.0004347970170531197, 'samples': 7067904, 'steps': 36811, 'loss/train': 3.1116228103637695} 08/30/2021 19:51:14 - INFO - __main__ - Step 36813: {'lr': 0.000434793442924094, 'samples': 7068096, 'steps': 36812, 'loss/train': 1.2393287420272827} 08/30/2021 19:51:14 - INFO - __main__ - Step 36814: {'lr': 0.0004347898687118033, 'samples': 7068288, 'steps': 36813, 'loss/train': 1.3419828414916992} 08/30/2021 19:51:15 - INFO - __main__ - Step 36815: {'lr': 0.0004347862944162492, 'samples': 7068480, 'steps': 36814, 'loss/train': 1.2952697277069092} 08/30/2021 19:51:15 - INFO - __main__ - Step 36816: {'lr': 0.00043478272003743315, 'samples': 7068672, 'steps': 36815, 'loss/train': 1.283370852470398} 08/30/2021 19:51:17 - INFO - __main__ - Step 36817: {'lr': 0.0004347791455753569, 'samples': 7068864, 'steps': 36816, 'loss/train': 2.282930374145508} 08/30/2021 19:51:17 - INFO - __main__ - Step 36818: {'lr': 0.00043477557103002197, 'samples': 7069056, 'steps': 36817, 'loss/train': 1.0517560243606567} 08/30/2021 19:51:17 - INFO - __main__ - Step 36819: {'lr': 0.00043477199640143004, 'samples': 7069248, 'steps': 36818, 'loss/train': 1.9354766607284546} 08/30/2021 19:51:18 - INFO - __main__ - Step 36820: {'lr': 0.00043476842168958276, 'samples': 7069440, 'steps': 36819, 'loss/train': 1.3237605094909668} 08/30/2021 19:51:18 - INFO - __main__ - Step 36821: {'lr': 0.0004347648468944816, 'samples': 7069632, 'steps': 36820, 'loss/train': 2.9693386554718018} 08/30/2021 19:51:20 - INFO - __main__ - Step 36822: {'lr': 0.0004347612720161283, 'samples': 7069824, 'steps': 36821, 'loss/train': 1.0591917037963867} 08/30/2021 19:51:20 - INFO - __main__ - Step 36823: {'lr': 0.00043475769705452437, 'samples': 7070016, 'steps': 36822, 'loss/train': 0.6354339122772217} 08/30/2021 19:51:20 - INFO - __main__ - Step 36824: {'lr': 0.00043475412200967155, 'samples': 7070208, 'steps': 36823, 'loss/train': 0.27789032459259033} 08/30/2021 19:51:21 - INFO - __main__ - Step 36825: {'lr': 0.00043475054688157136, 'samples': 7070400, 'steps': 36824, 'loss/train': 1.7641217708587646} 08/30/2021 19:51:21 - INFO - __main__ - Step 36826: {'lr': 0.00043474697167022536, 'samples': 7070592, 'steps': 36825, 'loss/train': 1.9912052154541016} 08/30/2021 19:51:22 - INFO - __main__ - Step 36827: {'lr': 0.0004347433963756353, 'samples': 7070784, 'steps': 36826, 'loss/train': 1.850598692893982} 08/30/2021 19:51:23 - INFO - __main__ - Step 36828: {'lr': 0.0004347398209978027, 'samples': 7070976, 'steps': 36827, 'loss/train': 1.684794306755066} 08/30/2021 19:51:23 - INFO - __main__ - Step 36829: {'lr': 0.0004347362455367292, 'samples': 7071168, 'steps': 36828, 'loss/train': 1.0775448083877563} 08/30/2021 19:51:24 - INFO - __main__ - Step 36830: {'lr': 0.0004347326699924163, 'samples': 7071360, 'steps': 36829, 'loss/train': 0.7445506453514099} 08/30/2021 19:51:24 - INFO - __main__ - Step 36831: {'lr': 0.0004347290943648658, 'samples': 7071552, 'steps': 36830, 'loss/train': 1.5281739234924316} 08/30/2021 19:51:24 - INFO - __main__ - Step 36832: {'lr': 0.00043472551865407917, 'samples': 7071744, 'steps': 36831, 'loss/train': 1.7025636434555054} 08/30/2021 19:51:27 - INFO - __main__ - Step 36833: {'lr': 0.0004347219428600581, 'samples': 7071936, 'steps': 36832, 'loss/train': 1.5944740772247314} 08/30/2021 19:51:27 - INFO - __main__ - Step 36834: {'lr': 0.0004347183669828042, 'samples': 7072128, 'steps': 36833, 'loss/train': 1.6958502531051636} 08/30/2021 19:51:27 - INFO - __main__ - Step 36835: {'lr': 0.00043471479102231904, 'samples': 7072320, 'steps': 36834, 'loss/train': 1.7756755352020264} 08/30/2021 19:51:28 - INFO - __main__ - Step 36836: {'lr': 0.0004347112149786042, 'samples': 7072512, 'steps': 36835, 'loss/train': 1.0302866697311401} 08/30/2021 19:51:28 - INFO - __main__ - Step 36837: {'lr': 0.0004347076388516614, 'samples': 7072704, 'steps': 36836, 'loss/train': 2.2028441429138184} 08/30/2021 19:51:29 - INFO - __main__ - Step 36838: {'lr': 0.00043470406264149215, 'samples': 7072896, 'steps': 36837, 'loss/train': 1.542486310005188} 08/30/2021 19:51:30 - INFO - __main__ - Step 36839: {'lr': 0.00043470048634809813, 'samples': 7073088, 'steps': 36838, 'loss/train': 1.6159751415252686} 08/30/2021 19:51:30 - INFO - __main__ - Step 36840: {'lr': 0.00043469690997148086, 'samples': 7073280, 'steps': 36839, 'loss/train': 1.5094271898269653} 08/30/2021 19:51:31 - INFO - __main__ - Step 36841: {'lr': 0.00043469333351164207, 'samples': 7073472, 'steps': 36840, 'loss/train': 1.7073278427124023} 08/30/2021 19:51:31 - INFO - __main__ - Step 36842: {'lr': 0.0004346897569685833, 'samples': 7073664, 'steps': 36841, 'loss/train': 1.5118752717971802} 08/30/2021 19:51:31 - INFO - __main__ - Step 36843: {'lr': 0.00043468618034230613, 'samples': 7073856, 'steps': 36842, 'loss/train': 1.497745394706726} 08/30/2021 19:51:33 - INFO - __main__ - Step 36844: {'lr': 0.00043468260363281234, 'samples': 7074048, 'steps': 36843, 'loss/train': 1.622791051864624} 08/30/2021 19:51:34 - INFO - __main__ - Step 36845: {'lr': 0.0004346790268401033, 'samples': 7074240, 'steps': 36844, 'loss/train': 0.13512659072875977} 08/30/2021 19:51:34 - INFO - __main__ - Step 36846: {'lr': 0.00043467544996418075, 'samples': 7074432, 'steps': 36845, 'loss/train': 1.831268310546875} 08/30/2021 19:51:34 - INFO - __main__ - Step 36847: {'lr': 0.0004346718730050463, 'samples': 7074624, 'steps': 36846, 'loss/train': 1.5660496950149536} 08/30/2021 19:51:35 - INFO - __main__ - Step 36848: {'lr': 0.0004346682959627016, 'samples': 7074816, 'steps': 36847, 'loss/train': 1.698951244354248} 08/30/2021 19:51:35 - INFO - __main__ - Step 36849: {'lr': 0.0004346647188371482, 'samples': 7075008, 'steps': 36848, 'loss/train': 1.3131630420684814} 08/30/2021 19:51:37 - INFO - __main__ - Step 36850: {'lr': 0.00043466114162838765, 'samples': 7075200, 'steps': 36849, 'loss/train': 1.89736807346344} 08/30/2021 19:51:37 - INFO - __main__ - Step 36851: {'lr': 0.00043465756433642175, 'samples': 7075392, 'steps': 36850, 'loss/train': 1.7006425857543945} 08/30/2021 19:51:37 - INFO - __main__ - Step 36852: {'lr': 0.0004346539869612519, 'samples': 7075584, 'steps': 36851, 'loss/train': 1.5596452951431274} 08/30/2021 19:51:38 - INFO - __main__ - Step 36853: {'lr': 0.0004346504095028799, 'samples': 7075776, 'steps': 36852, 'loss/train': 0.6171156764030457} 08/30/2021 19:51:38 - INFO - __main__ - Step 36854: {'lr': 0.00043464683196130726, 'samples': 7075968, 'steps': 36853, 'loss/train': 1.4701935052871704} 08/30/2021 19:51:38 - INFO - __main__ - Step 36855: {'lr': 0.00043464325433653563, 'samples': 7076160, 'steps': 36854, 'loss/train': 0.6239742636680603} 08/30/2021 19:51:40 - INFO - __main__ - Step 36856: {'lr': 0.0004346396766285665, 'samples': 7076352, 'steps': 36855, 'loss/train': 1.4213045835494995} 08/30/2021 19:51:40 - INFO - __main__ - Step 36857: {'lr': 0.0004346360988374016, 'samples': 7076544, 'steps': 36856, 'loss/train': 0.8447583913803101} 08/30/2021 19:51:41 - INFO - __main__ - Step 36858: {'lr': 0.0004346325209630426, 'samples': 7076736, 'steps': 36857, 'loss/train': 1.7020998001098633} 08/30/2021 19:51:41 - INFO - __main__ - Step 36859: {'lr': 0.00043462894300549097, 'samples': 7076928, 'steps': 36858, 'loss/train': 1.4927747249603271} 08/30/2021 19:51:42 - INFO - __main__ - Step 36860: {'lr': 0.0004346253649647485, 'samples': 7077120, 'steps': 36859, 'loss/train': 1.1809659004211426} 08/30/2021 19:51:43 - INFO - __main__ - Step 36861: {'lr': 0.00043462178684081657, 'samples': 7077312, 'steps': 36860, 'loss/train': 1.1880556344985962} 08/30/2021 19:51:43 - INFO - __main__ - Step 36862: {'lr': 0.00043461820863369697, 'samples': 7077504, 'steps': 36861, 'loss/train': 0.9868214726448059} 08/30/2021 19:51:44 - INFO - __main__ - Step 36863: {'lr': 0.0004346146303433912, 'samples': 7077696, 'steps': 36862, 'loss/train': 1.9891897439956665} 08/30/2021 19:51:44 - INFO - __main__ - Step 36864: {'lr': 0.00043461105196990093, 'samples': 7077888, 'steps': 36863, 'loss/train': 1.4800950288772583} 08/30/2021 19:51:44 - INFO - __main__ - Step 36865: {'lr': 0.0004346074735132278, 'samples': 7078080, 'steps': 36864, 'loss/train': 1.5107578039169312} 08/30/2021 19:51:46 - INFO - __main__ - Step 36866: {'lr': 0.0004346038949733734, 'samples': 7078272, 'steps': 36865, 'loss/train': 0.944397509098053} 08/30/2021 19:51:46 - INFO - __main__ - Step 36867: {'lr': 0.0004346003163503393, 'samples': 7078464, 'steps': 36866, 'loss/train': 1.6311485767364502} 08/30/2021 19:51:47 - INFO - __main__ - Step 36868: {'lr': 0.00043459673764412713, 'samples': 7078656, 'steps': 36867, 'loss/train': 1.911833643913269} 08/30/2021 19:51:47 - INFO - __main__ - Step 36869: {'lr': 0.0004345931588547386, 'samples': 7078848, 'steps': 36868, 'loss/train': 0.20603567361831665} 08/30/2021 19:51:47 - INFO - __main__ - Step 36870: {'lr': 0.00043458957998217517, 'samples': 7079040, 'steps': 36869, 'loss/train': 0.93301922082901} 08/30/2021 19:51:49 - INFO - __main__ - Step 36871: {'lr': 0.0004345860010264385, 'samples': 7079232, 'steps': 36870, 'loss/train': 1.9856507778167725} 08/30/2021 19:51:49 - INFO - __main__ - Step 36872: {'lr': 0.00043458242198753035, 'samples': 7079424, 'steps': 36871, 'loss/train': 0.7868944406509399} 08/30/2021 19:51:50 - INFO - __main__ - Step 36873: {'lr': 0.00043457884286545216, 'samples': 7079616, 'steps': 36872, 'loss/train': 1.3528791666030884} 08/30/2021 19:51:50 - INFO - __main__ - Step 36874: {'lr': 0.0004345752636602055, 'samples': 7079808, 'steps': 36873, 'loss/train': 1.4041922092437744} 08/30/2021 19:51:50 - INFO - __main__ - Step 36875: {'lr': 0.00043457168437179217, 'samples': 7080000, 'steps': 36874, 'loss/train': 1.0192317962646484} 08/30/2021 19:51:52 - INFO - __main__ - Step 36876: {'lr': 0.00043456810500021363, 'samples': 7080192, 'steps': 36875, 'loss/train': 1.3907181024551392} 08/30/2021 19:51:53 - INFO - __main__ - Step 36877: {'lr': 0.00043456452554547153, 'samples': 7080384, 'steps': 36876, 'loss/train': 1.4760247468948364} 08/30/2021 19:51:53 - INFO - __main__ - Step 36878: {'lr': 0.0004345609460075676, 'samples': 7080576, 'steps': 36877, 'loss/train': 1.4130911827087402} 08/30/2021 19:51:54 - INFO - __main__ - Step 36879: {'lr': 0.00043455736638650335, 'samples': 7080768, 'steps': 36878, 'loss/train': 0.7857569456100464} 08/30/2021 19:51:54 - INFO - __main__ - Step 36880: {'lr': 0.0004345537866822803, 'samples': 7080960, 'steps': 36879, 'loss/train': 1.0793346166610718} 08/30/2021 19:51:55 - INFO - __main__ - Step 36881: {'lr': 0.0004345502068949002, 'samples': 7081152, 'steps': 36880, 'loss/train': 1.303871512413025} 08/30/2021 19:51:56 - INFO - __main__ - Step 36882: {'lr': 0.0004345466270243646, 'samples': 7081344, 'steps': 36881, 'loss/train': 1.7368212938308716} 08/30/2021 19:51:56 - INFO - __main__ - Step 36883: {'lr': 0.0004345430470706753, 'samples': 7081536, 'steps': 36882, 'loss/train': 1.3319361209869385} 08/30/2021 19:51:57 - INFO - __main__ - Step 36884: {'lr': 0.00043453946703383354, 'samples': 7081728, 'steps': 36883, 'loss/train': 1.3173316717147827} 08/30/2021 19:51:57 - INFO - __main__ - Step 36885: {'lr': 0.00043453588691384125, 'samples': 7081920, 'steps': 36884, 'loss/train': 1.3831349611282349} 08/30/2021 19:51:57 - INFO - __main__ - Step 36886: {'lr': 0.0004345323067106999, 'samples': 7082112, 'steps': 36885, 'loss/train': 2.2285733222961426} 08/30/2021 19:51:59 - INFO - __main__ - Step 36887: {'lr': 0.00043452872642441124, 'samples': 7082304, 'steps': 36886, 'loss/train': 1.0684077739715576} 08/30/2021 19:52:00 - INFO - __main__ - Step 36888: {'lr': 0.0004345251460549766, 'samples': 7082496, 'steps': 36887, 'loss/train': 1.6257017850875854} 08/30/2021 19:52:00 - INFO - __main__ - Step 36889: {'lr': 0.0004345215656023979, 'samples': 7082688, 'steps': 36888, 'loss/train': 0.5881924629211426} 08/30/2021 19:52:00 - INFO - __main__ - Step 36890: {'lr': 0.0004345179850666766, 'samples': 7082880, 'steps': 36889, 'loss/train': 1.4926257133483887} 08/30/2021 19:52:01 - INFO - __main__ - Step 36891: {'lr': 0.0004345144044478144, 'samples': 7083072, 'steps': 36890, 'loss/train': 1.6564733982086182} 08/30/2021 19:52:02 - INFO - __main__ - Step 36892: {'lr': 0.0004345108237458128, 'samples': 7083264, 'steps': 36891, 'loss/train': 1.6903613805770874} 08/30/2021 19:52:03 - INFO - __main__ - Step 36893: {'lr': 0.00043450724296067344, 'samples': 7083456, 'steps': 36892, 'loss/train': 0.7877649664878845} 08/30/2021 19:52:03 - INFO - __main__ - Step 36894: {'lr': 0.00043450366209239803, 'samples': 7083648, 'steps': 36893, 'loss/train': 1.5424647331237793} 08/30/2021 19:52:03 - INFO - __main__ - Step 36895: {'lr': 0.0004345000811409881, 'samples': 7083840, 'steps': 36894, 'loss/train': 1.7291079759597778} 08/30/2021 19:52:04 - INFO - __main__ - Step 36896: {'lr': 0.0004344965001064453, 'samples': 7084032, 'steps': 36895, 'loss/train': 2.0265002250671387} 08/30/2021 19:52:05 - INFO - __main__ - Step 36897: {'lr': 0.0004344929189887712, 'samples': 7084224, 'steps': 36896, 'loss/train': 1.2669568061828613} 08/30/2021 19:52:06 - INFO - __main__ - Step 36898: {'lr': 0.0004344893377879674, 'samples': 7084416, 'steps': 36897, 'loss/train': 1.0824276208877563} 08/30/2021 19:52:06 - INFO - __main__ - Step 36899: {'lr': 0.00043448575650403555, 'samples': 7084608, 'steps': 36898, 'loss/train': 1.5803066492080688} 08/30/2021 19:52:06 - INFO - __main__ - Step 36900: {'lr': 0.00043448217513697727, 'samples': 7084800, 'steps': 36899, 'loss/train': 1.8659253120422363} 08/30/2021 19:52:07 - INFO - __main__ - Step 36901: {'lr': 0.0004344785936867942, 'samples': 7084992, 'steps': 36900, 'loss/train': 1.3426913022994995} 08/30/2021 19:52:09 - INFO - __main__ - Step 36902: {'lr': 0.00043447501215348794, 'samples': 7085184, 'steps': 36901, 'loss/train': 1.2634861469268799} 08/30/2021 19:52:10 - INFO - __main__ - Step 36903: {'lr': 0.00043447143053706007, 'samples': 7085376, 'steps': 36902, 'loss/train': 1.5066152811050415} 08/30/2021 19:52:10 - INFO - __main__ - Step 36904: {'lr': 0.00043446784883751223, 'samples': 7085568, 'steps': 36903, 'loss/train': 1.6530123949050903} 08/30/2021 19:52:10 - INFO - __main__ - Step 36905: {'lr': 0.000434464267054846, 'samples': 7085760, 'steps': 36904, 'loss/train': 0.7644088268280029} 08/30/2021 19:52:11 - INFO - __main__ - Step 36906: {'lr': 0.000434460685189063, 'samples': 7085952, 'steps': 36905, 'loss/train': 1.1632622480392456} 08/30/2021 19:52:11 - INFO - __main__ - Step 36907: {'lr': 0.0004344571032401649, 'samples': 7086144, 'steps': 36906, 'loss/train': 1.4312840700149536} 08/30/2021 19:52:12 - INFO - __main__ - Step 36908: {'lr': 0.0004344535212081533, 'samples': 7086336, 'steps': 36907, 'loss/train': 0.15583209693431854} 08/30/2021 19:52:13 - INFO - __main__ - Step 36909: {'lr': 0.0004344499390930298, 'samples': 7086528, 'steps': 36908, 'loss/train': 1.5124632120132446} 08/30/2021 19:52:13 - INFO - __main__ - Step 36910: {'lr': 0.0004344463568947959, 'samples': 7086720, 'steps': 36909, 'loss/train': 1.3383314609527588} 08/30/2021 19:52:14 - INFO - __main__ - Step 36911: {'lr': 0.0004344427746134534, 'samples': 7086912, 'steps': 36910, 'loss/train': 0.69477778673172} 08/30/2021 19:52:14 - INFO - __main__ - Step 36912: {'lr': 0.0004344391922490037, 'samples': 7087104, 'steps': 36911, 'loss/train': 1.7162814140319824} 08/30/2021 19:52:16 - INFO - __main__ - Step 36913: {'lr': 0.0004344356098014487, 'samples': 7087296, 'steps': 36912, 'loss/train': 1.2389296293258667} 08/30/2021 19:52:16 - INFO - __main__ - Step 36914: {'lr': 0.0004344320272707898, 'samples': 7087488, 'steps': 36913, 'loss/train': 1.6162362098693848} 08/30/2021 19:52:17 - INFO - __main__ - Step 36915: {'lr': 0.0004344284446570287, 'samples': 7087680, 'steps': 36914, 'loss/train': 0.20172248780727386} 08/30/2021 19:52:17 - INFO - __main__ - Step 36916: {'lr': 0.00043442486196016697, 'samples': 7087872, 'steps': 36915, 'loss/train': 1.0644278526306152} 08/30/2021 19:52:17 - INFO - __main__ - Step 36917: {'lr': 0.00043442127918020624, 'samples': 7088064, 'steps': 36916, 'loss/train': 1.3371798992156982} 08/30/2021 19:52:18 - INFO - __main__ - Step 36918: {'lr': 0.00043441769631714813, 'samples': 7088256, 'steps': 36917, 'loss/train': 1.6196606159210205} 08/30/2021 19:52:19 - INFO - __main__ - Step 36919: {'lr': 0.0004344141133709943, 'samples': 7088448, 'steps': 36918, 'loss/train': 1.281686544418335} 08/30/2021 19:52:20 - INFO - __main__ - Step 36920: {'lr': 0.00043441053034174625, 'samples': 7088640, 'steps': 36919, 'loss/train': 2.353680372238159} 08/30/2021 19:52:20 - INFO - __main__ - Step 36921: {'lr': 0.00043440694722940567, 'samples': 7088832, 'steps': 36920, 'loss/train': 1.623010277748108} 08/30/2021 19:52:20 - INFO - __main__ - Step 36922: {'lr': 0.00043440336403397417, 'samples': 7089024, 'steps': 36921, 'loss/train': 1.7530802488327026} 08/30/2021 19:52:21 - INFO - __main__ - Step 36923: {'lr': 0.00043439978075545337, 'samples': 7089216, 'steps': 36922, 'loss/train': 1.8340357542037964} 08/30/2021 19:52:22 - INFO - __main__ - Step 36924: {'lr': 0.0004343961973938449, 'samples': 7089408, 'steps': 36923, 'loss/train': 2.0118818283081055} 08/30/2021 19:52:22 - INFO - __main__ - Step 36925: {'lr': 0.00043439261394915033, 'samples': 7089600, 'steps': 36924, 'loss/train': 1.7424439191818237} 08/30/2021 19:52:23 - INFO - __main__ - Step 36926: {'lr': 0.0004343890304213713, 'samples': 7089792, 'steps': 36925, 'loss/train': 1.5566686391830444} 08/30/2021 19:52:23 - INFO - __main__ - Step 36927: {'lr': 0.0004343854468105094, 'samples': 7089984, 'steps': 36926, 'loss/train': 1.6069055795669556} 08/30/2021 19:52:23 - INFO - __main__ - Step 36928: {'lr': 0.00043438186311656624, 'samples': 7090176, 'steps': 36927, 'loss/train': 1.2824548482894897} 08/30/2021 19:52:25 - INFO - __main__ - Step 36929: {'lr': 0.0004343782793395435, 'samples': 7090368, 'steps': 36928, 'loss/train': 0.23958955705165863} 08/30/2021 19:52:25 - INFO - __main__ - Step 36930: {'lr': 0.00043437469547944277, 'samples': 7090560, 'steps': 36929, 'loss/train': 0.9688027501106262} 08/30/2021 19:52:26 - INFO - __main__ - Step 36931: {'lr': 0.0004343711115362656, 'samples': 7090752, 'steps': 36930, 'loss/train': 2.1543033123016357} 08/30/2021 19:52:26 - INFO - __main__ - Step 36932: {'lr': 0.00043436752751001365, 'samples': 7090944, 'steps': 36931, 'loss/train': 1.5060359239578247} 08/30/2021 19:52:26 - INFO - __main__ - Step 36933: {'lr': 0.0004343639434006885, 'samples': 7091136, 'steps': 36932, 'loss/train': 0.7337257862091064} 08/30/2021 19:52:28 - INFO - __main__ - Step 36934: {'lr': 0.00043436035920829186, 'samples': 7091328, 'steps': 36933, 'loss/train': 1.5979710817337036} 08/30/2021 19:52:29 - INFO - __main__ - Step 36935: {'lr': 0.0004343567749328253, 'samples': 7091520, 'steps': 36934, 'loss/train': 1.3218986988067627} 08/30/2021 19:52:29 - INFO - __main__ - Step 36936: {'lr': 0.00043435319057429046, 'samples': 7091712, 'steps': 36935, 'loss/train': 1.294980525970459} 08/30/2021 19:52:29 - INFO - __main__ - Step 36937: {'lr': 0.0004343496061326888, 'samples': 7091904, 'steps': 36936, 'loss/train': 1.5687510967254639} 08/30/2021 19:52:30 - INFO - __main__ - Step 36938: {'lr': 0.0004343460216080221, 'samples': 7092096, 'steps': 36937, 'loss/train': 1.8208032846450806} 08/30/2021 19:52:30 - INFO - __main__ - Step 36939: {'lr': 0.00043434243700029196, 'samples': 7092288, 'steps': 36938, 'loss/train': 2.672553062438965} 08/30/2021 19:52:32 - INFO - __main__ - Step 36940: {'lr': 0.0004343388523095, 'samples': 7092480, 'steps': 36939, 'loss/train': 1.633872628211975} 08/30/2021 19:52:32 - INFO - __main__ - Step 36941: {'lr': 0.00043433526753564766, 'samples': 7092672, 'steps': 36940, 'loss/train': 1.6166070699691772} 08/30/2021 19:52:33 - INFO - __main__ - Step 36942: {'lr': 0.00043433168267873677, 'samples': 7092864, 'steps': 36941, 'loss/train': 1.5333166122436523} 08/30/2021 19:52:33 - INFO - __main__ - Step 36943: {'lr': 0.0004343280977387689, 'samples': 7093056, 'steps': 36942, 'loss/train': 1.033284306526184} 08/30/2021 19:52:33 - INFO - __main__ - Step 36944: {'lr': 0.0004343245127157456, 'samples': 7093248, 'steps': 36943, 'loss/train': 2.024367332458496} 08/30/2021 19:52:35 - INFO - __main__ - Step 36945: {'lr': 0.0004343209276096686, 'samples': 7093440, 'steps': 36944, 'loss/train': 1.439671516418457} 08/30/2021 19:52:35 - INFO - __main__ - Step 36946: {'lr': 0.00043431734242053933, 'samples': 7093632, 'steps': 36945, 'loss/train': 1.2868527173995972} 08/30/2021 19:52:36 - INFO - __main__ - Step 36947: {'lr': 0.0004343137571483595, 'samples': 7093824, 'steps': 36946, 'loss/train': 1.385898232460022} 08/30/2021 19:52:36 - INFO - __main__ - Step 36948: {'lr': 0.00043431017179313075, 'samples': 7094016, 'steps': 36947, 'loss/train': 1.1743888854980469} 08/30/2021 19:52:36 - INFO - __main__ - Step 36949: {'lr': 0.0004343065863548548, 'samples': 7094208, 'steps': 36948, 'loss/train': 1.4184134006500244} 08/30/2021 19:52:38 - INFO - __main__ - Step 36950: {'lr': 0.000434303000833533, 'samples': 7094400, 'steps': 36949, 'loss/train': 1.347912073135376} 08/30/2021 19:52:38 - INFO - __main__ - Step 36951: {'lr': 0.00043429941522916715, 'samples': 7094592, 'steps': 36950, 'loss/train': 0.6524996757507324} 08/30/2021 19:52:39 - INFO - __main__ - Step 36952: {'lr': 0.0004342958295417588, 'samples': 7094784, 'steps': 36951, 'loss/train': 2.1537210941314697} 08/30/2021 19:52:39 - INFO - __main__ - Step 36953: {'lr': 0.00043429224377130964, 'samples': 7094976, 'steps': 36952, 'loss/train': 1.3659676313400269} 08/30/2021 19:52:39 - INFO - __main__ - Step 36954: {'lr': 0.00043428865791782126, 'samples': 7095168, 'steps': 36953, 'loss/train': 1.3667595386505127} 08/30/2021 19:52:41 - INFO - __main__ - Step 36955: {'lr': 0.0004342850719812952, 'samples': 7095360, 'steps': 36954, 'loss/train': 1.1743696928024292} 08/30/2021 19:52:41 - INFO - __main__ - Step 36956: {'lr': 0.00043428148596173316, 'samples': 7095552, 'steps': 36955, 'loss/train': 1.2689417600631714} 08/30/2021 19:52:42 - INFO - __main__ - Step 36957: {'lr': 0.00043427789985913675, 'samples': 7095744, 'steps': 36956, 'loss/train': 1.1221024990081787} 08/30/2021 19:52:42 - INFO - __main__ - Step 36958: {'lr': 0.00043427431367350753, 'samples': 7095936, 'steps': 36957, 'loss/train': 1.446897268295288} 08/30/2021 19:52:42 - INFO - __main__ - Step 36959: {'lr': 0.0004342707274048472, 'samples': 7096128, 'steps': 36958, 'loss/train': 1.893778920173645} 08/30/2021 19:52:44 - INFO - __main__ - Step 36960: {'lr': 0.0004342671410531572, 'samples': 7096320, 'steps': 36959, 'loss/train': 1.1127581596374512} 08/30/2021 19:52:44 - INFO - __main__ - Step 36961: {'lr': 0.00043426355461843934, 'samples': 7096512, 'steps': 36960, 'loss/train': 1.0507432222366333} 08/30/2021 19:52:45 - INFO - __main__ - Step 36962: {'lr': 0.00043425996810069525, 'samples': 7096704, 'steps': 36961, 'loss/train': 0.758385956287384} 08/30/2021 19:52:45 - INFO - __main__ - Step 36963: {'lr': 0.0004342563814999264, 'samples': 7096896, 'steps': 36962, 'loss/train': 1.7164360284805298} 08/30/2021 19:52:45 - INFO - __main__ - Step 36964: {'lr': 0.0004342527948161344, 'samples': 7097088, 'steps': 36963, 'loss/train': 1.39939284324646} 08/30/2021 19:52:46 - INFO - __main__ - Step 36965: {'lr': 0.000434249208049321, 'samples': 7097280, 'steps': 36964, 'loss/train': 1.573245882987976} 08/30/2021 19:52:47 - INFO - __main__ - Step 36966: {'lr': 0.0004342456211994877, 'samples': 7097472, 'steps': 36965, 'loss/train': 0.9394899010658264} 08/30/2021 19:52:48 - INFO - __main__ - Step 36967: {'lr': 0.00043424203426663623, 'samples': 7097664, 'steps': 36966, 'loss/train': 0.26969125866889954} 08/30/2021 19:52:48 - INFO - __main__ - Step 36968: {'lr': 0.0004342384472507681, 'samples': 7097856, 'steps': 36967, 'loss/train': 1.4364887475967407} 08/30/2021 19:52:48 - INFO - __main__ - Step 36969: {'lr': 0.00043423486015188497, 'samples': 7098048, 'steps': 36968, 'loss/train': 1.5569854974746704} 08/30/2021 19:52:49 - INFO - __main__ - Step 36970: {'lr': 0.00043423127296998845, 'samples': 7098240, 'steps': 36969, 'loss/train': 1.4173226356506348} 08/30/2021 19:52:50 - INFO - __main__ - Step 36971: {'lr': 0.0004342276857050802, 'samples': 7098432, 'steps': 36970, 'loss/train': 1.9105315208435059} 08/30/2021 19:52:51 - INFO - __main__ - Step 36972: {'lr': 0.00043422409835716175, 'samples': 7098624, 'steps': 36971, 'loss/train': 2.0277769565582275} 08/30/2021 19:52:51 - INFO - __main__ - Step 36973: {'lr': 0.00043422051092623483, 'samples': 7098816, 'steps': 36972, 'loss/train': 1.1386018991470337} 08/30/2021 19:52:51 - INFO - __main__ - Step 36974: {'lr': 0.0004342169234123009, 'samples': 7099008, 'steps': 36973, 'loss/train': 1.489443063735962} 08/30/2021 19:52:52 - INFO - __main__ - Step 36975: {'lr': 0.0004342133358153617, 'samples': 7099200, 'steps': 36974, 'loss/train': 1.8622065782546997} 08/30/2021 19:52:53 - INFO - __main__ - Step 36976: {'lr': 0.0004342097481354189, 'samples': 7099392, 'steps': 36975, 'loss/train': 1.5048037767410278} 08/30/2021 19:52:54 - INFO - __main__ - Step 36977: {'lr': 0.00043420616037247395, 'samples': 7099584, 'steps': 36976, 'loss/train': 1.5004308223724365} 08/30/2021 19:52:54 - INFO - __main__ - Step 36978: {'lr': 0.0004342025725265285, 'samples': 7099776, 'steps': 36977, 'loss/train': 1.0251719951629639} 08/30/2021 19:52:54 - INFO - __main__ - Step 36979: {'lr': 0.00043419898459758435, 'samples': 7099968, 'steps': 36978, 'loss/train': 1.5730838775634766} 08/30/2021 19:52:55 - INFO - __main__ - Step 36980: {'lr': 0.00043419539658564286, 'samples': 7100160, 'steps': 36979, 'loss/train': 1.404199481010437} 08/30/2021 19:52:56 - INFO - __main__ - Step 36981: {'lr': 0.0004341918084907058, 'samples': 7100352, 'steps': 36980, 'loss/train': 1.177692174911499} 08/30/2021 19:52:57 - INFO - __main__ - Step 36982: {'lr': 0.0004341882203127747, 'samples': 7100544, 'steps': 36981, 'loss/train': 1.64198899269104} 08/30/2021 19:52:57 - INFO - __main__ - Step 36983: {'lr': 0.00043418463205185134, 'samples': 7100736, 'steps': 36982, 'loss/train': 1.1643450260162354} 08/30/2021 19:52:57 - INFO - __main__ - Step 36984: {'lr': 0.0004341810437079372, 'samples': 7100928, 'steps': 36983, 'loss/train': 1.3584672212600708} 08/30/2021 19:52:58 - INFO - __main__ - Step 36985: {'lr': 0.0004341774552810339, 'samples': 7101120, 'steps': 36984, 'loss/train': 1.108555555343628} 08/30/2021 19:52:59 - INFO - __main__ - Step 36986: {'lr': 0.0004341738667711431, 'samples': 7101312, 'steps': 36985, 'loss/train': 1.617867350578308} 08/30/2021 19:53:00 - INFO - __main__ - Step 36987: {'lr': 0.0004341702781782664, 'samples': 7101504, 'steps': 36986, 'loss/train': 1.32652747631073} 08/30/2021 19:53:00 - INFO - __main__ - Step 36988: {'lr': 0.00043416668950240536, 'samples': 7101696, 'steps': 36987, 'loss/train': 1.2426902055740356} 08/30/2021 19:53:00 - INFO - __main__ - Step 36989: {'lr': 0.0004341631007435617, 'samples': 7101888, 'steps': 36988, 'loss/train': 0.7134483456611633} 08/30/2021 19:53:01 - INFO - __main__ - Step 36990: {'lr': 0.00043415951190173697, 'samples': 7102080, 'steps': 36989, 'loss/train': 1.0421174764633179} 08/30/2021 19:53:02 - INFO - __main__ - Step 36991: {'lr': 0.00043415592297693276, 'samples': 7102272, 'steps': 36990, 'loss/train': 1.1955801248550415} 08/30/2021 19:53:03 - INFO - __main__ - Step 36992: {'lr': 0.00043415233396915077, 'samples': 7102464, 'steps': 36991, 'loss/train': 1.566650629043579} 08/30/2021 19:53:03 - INFO - __main__ - Step 36993: {'lr': 0.0004341487448783926, 'samples': 7102656, 'steps': 36992, 'loss/train': 1.7085177898406982} 08/30/2021 19:53:03 - INFO - __main__ - Step 36994: {'lr': 0.00043414515570465987, 'samples': 7102848, 'steps': 36993, 'loss/train': 1.1849037408828735} 08/30/2021 19:53:04 - INFO - __main__ - Step 36995: {'lr': 0.0004341415664479541, 'samples': 7103040, 'steps': 36994, 'loss/train': 1.8075555562973022} 08/30/2021 19:53:04 - INFO - __main__ - Step 36996: {'lr': 0.00043413797710827707, 'samples': 7103232, 'steps': 36995, 'loss/train': 1.0284196138381958} 08/30/2021 19:53:06 - INFO - __main__ - Step 36997: {'lr': 0.00043413438768563026, 'samples': 7103424, 'steps': 36996, 'loss/train': 1.2237123250961304} 08/30/2021 19:53:07 - INFO - __main__ - Step 36998: {'lr': 0.0004341307981800153, 'samples': 7103616, 'steps': 36997, 'loss/train': 1.5749413967132568} 08/30/2021 19:53:07 - INFO - __main__ - Step 36999: {'lr': 0.0004341272085914339, 'samples': 7103808, 'steps': 36998, 'loss/train': 1.7321717739105225} 08/30/2021 19:53:07 - INFO - __main__ - Step 37000: {'lr': 0.00043412361891988763, 'samples': 7104000, 'steps': 36999, 'loss/train': 1.539825439453125} 08/30/2021 19:53:08 - INFO - __main__ - Step 37001: {'lr': 0.0004341200291653781, 'samples': 7104192, 'steps': 37000, 'loss/train': 0.8989658951759338} 08/30/2021 19:53:09 - INFO - __main__ - Step 37002: {'lr': 0.00043411643932790686, 'samples': 7104384, 'steps': 37001, 'loss/train': 1.5800189971923828} 08/30/2021 19:53:10 - INFO - __main__ - Step 37003: {'lr': 0.0004341128494074756, 'samples': 7104576, 'steps': 37002, 'loss/train': 1.349951148033142} 08/30/2021 19:53:10 - INFO - __main__ - Step 37004: {'lr': 0.00043410925940408595, 'samples': 7104768, 'steps': 37003, 'loss/train': 0.2885541021823883} 08/30/2021 19:53:10 - INFO - __main__ - Step 37005: {'lr': 0.00043410566931773953, 'samples': 7104960, 'steps': 37004, 'loss/train': 1.5363378524780273} 08/30/2021 19:53:11 - INFO - __main__ - Step 37006: {'lr': 0.000434102079148438, 'samples': 7105152, 'steps': 37005, 'loss/train': 1.4845151901245117} 08/30/2021 19:53:12 - INFO - __main__ - Step 37007: {'lr': 0.0004340984888961828, 'samples': 7105344, 'steps': 37006, 'loss/train': 1.6094889640808105} 08/30/2021 19:53:13 - INFO - __main__ - Step 37008: {'lr': 0.00043409489856097573, 'samples': 7105536, 'steps': 37007, 'loss/train': 1.469128966331482} 08/30/2021 19:53:13 - INFO - __main__ - Step 37009: {'lr': 0.0004340913081428183, 'samples': 7105728, 'steps': 37008, 'loss/train': 1.7176958322525024} 08/30/2021 19:53:14 - INFO - __main__ - Step 37010: {'lr': 0.00043408771764171216, 'samples': 7105920, 'steps': 37009, 'loss/train': 1.3295246362686157} 08/30/2021 19:53:14 - INFO - __main__ - Step 37011: {'lr': 0.000434084127057659, 'samples': 7106112, 'steps': 37010, 'loss/train': 0.6916934847831726} 08/30/2021 19:53:14 - INFO - __main__ - Step 37012: {'lr': 0.0004340805363906603, 'samples': 7106304, 'steps': 37011, 'loss/train': 1.2902816534042358} 08/30/2021 19:53:16 - INFO - __main__ - Step 37013: {'lr': 0.00043407694564071773, 'samples': 7106496, 'steps': 37012, 'loss/train': 0.057550281286239624} 08/30/2021 19:53:16 - INFO - __main__ - Step 37014: {'lr': 0.00043407335480783306, 'samples': 7106688, 'steps': 37013, 'loss/train': 0.858756422996521} 08/30/2021 19:53:17 - INFO - __main__ - Step 37015: {'lr': 0.0004340697638920077, 'samples': 7106880, 'steps': 37014, 'loss/train': 1.4779387712478638} 08/30/2021 19:53:17 - INFO - __main__ - Step 37016: {'lr': 0.0004340661728932433, 'samples': 7107072, 'steps': 37015, 'loss/train': 1.6564719676971436} 08/30/2021 19:53:17 - INFO - __main__ - Step 37017: {'lr': 0.0004340625818115416, 'samples': 7107264, 'steps': 37016, 'loss/train': 1.3332830667495728} 08/30/2021 19:53:18 - INFO - __main__ - Step 37018: {'lr': 0.00043405899064690405, 'samples': 7107456, 'steps': 37017, 'loss/train': 1.2354892492294312} 08/30/2021 19:53:19 - INFO - __main__ - Step 37019: {'lr': 0.0004340553993993325, 'samples': 7107648, 'steps': 37018, 'loss/train': 1.2463513612747192} 08/30/2021 19:53:20 - INFO - __main__ - Step 37020: {'lr': 0.0004340518080688283, 'samples': 7107840, 'steps': 37019, 'loss/train': 1.396854281425476} 08/30/2021 19:53:20 - INFO - __main__ - Step 37021: {'lr': 0.0004340482166553932, 'samples': 7108032, 'steps': 37020, 'loss/train': 1.6890665292739868} 08/30/2021 19:53:20 - INFO - __main__ - Step 37022: {'lr': 0.0004340446251590289, 'samples': 7108224, 'steps': 37021, 'loss/train': 1.6288957595825195} 08/30/2021 19:53:21 - INFO - __main__ - Step 37023: {'lr': 0.00043404103357973684, 'samples': 7108416, 'steps': 37022, 'loss/train': 1.4945032596588135} 08/30/2021 19:53:22 - INFO - __main__ - Step 37024: {'lr': 0.0004340374419175188, 'samples': 7108608, 'steps': 37023, 'loss/train': 1.2181408405303955} 08/30/2021 19:53:23 - INFO - __main__ - Step 37025: {'lr': 0.0004340338501723763, 'samples': 7108800, 'steps': 37024, 'loss/train': 1.5541753768920898} 08/30/2021 19:53:23 - INFO - __main__ - Step 37026: {'lr': 0.00043403025834431097, 'samples': 7108992, 'steps': 37025, 'loss/train': 1.6661155223846436} 08/30/2021 19:53:23 - INFO - __main__ - Step 37027: {'lr': 0.00043402666643332444, 'samples': 7109184, 'steps': 37026, 'loss/train': 1.4981967210769653} 08/30/2021 19:53:24 - INFO - __main__ - Step 37028: {'lr': 0.00043402307443941835, 'samples': 7109376, 'steps': 37027, 'loss/train': 1.227504014968872} 08/30/2021 19:53:25 - INFO - __main__ - Step 37029: {'lr': 0.00043401948236259437, 'samples': 7109568, 'steps': 37028, 'loss/train': 1.4776465892791748} 08/30/2021 19:53:26 - INFO - __main__ - Step 37030: {'lr': 0.000434015890202854, 'samples': 7109760, 'steps': 37029, 'loss/train': 1.3422006368637085} 08/30/2021 19:53:26 - INFO - __main__ - Step 37031: {'lr': 0.0004340122979601989, 'samples': 7109952, 'steps': 37030, 'loss/train': 1.5140113830566406} 08/30/2021 19:53:26 - INFO - __main__ - Step 37032: {'lr': 0.0004340087056346307, 'samples': 7110144, 'steps': 37031, 'loss/train': 1.6615102291107178} 08/30/2021 19:53:27 - INFO - __main__ - Step 37033: {'lr': 0.000434005113226151, 'samples': 7110336, 'steps': 37032, 'loss/train': 1.2792826890945435} 08/30/2021 19:53:28 - INFO - __main__ - Step 37034: {'lr': 0.0004340015207347614, 'samples': 7110528, 'steps': 37033, 'loss/train': 1.2476483583450317} 08/30/2021 19:53:29 - INFO - __main__ - Step 37035: {'lr': 0.0004339979281604636, 'samples': 7110720, 'steps': 37034, 'loss/train': 1.4508005380630493} 08/30/2021 19:53:29 - INFO - __main__ - Step 37036: {'lr': 0.00043399433550325917, 'samples': 7110912, 'steps': 37035, 'loss/train': 1.631337285041809} 08/30/2021 19:53:29 - INFO - __main__ - Step 37037: {'lr': 0.00043399074276314974, 'samples': 7111104, 'steps': 37036, 'loss/train': 1.7164074182510376} 08/30/2021 19:53:30 - INFO - __main__ - Step 37038: {'lr': 0.00043398714994013696, 'samples': 7111296, 'steps': 37037, 'loss/train': 1.6832025051116943} 08/30/2021 19:53:31 - INFO - __main__ - Step 37039: {'lr': 0.00043398355703422233, 'samples': 7111488, 'steps': 37038, 'loss/train': 0.34106573462486267} 08/30/2021 19:53:32 - INFO - __main__ - Step 37040: {'lr': 0.0004339799640454076, 'samples': 7111680, 'steps': 37039, 'loss/train': 1.8033214807510376} 08/30/2021 19:53:32 - INFO - __main__ - Step 37041: {'lr': 0.00043397637097369434, 'samples': 7111872, 'steps': 37040, 'loss/train': 1.70357346534729} 08/30/2021 19:53:32 - INFO - __main__ - Step 37042: {'lr': 0.0004339727778190842, 'samples': 7112064, 'steps': 37041, 'loss/train': 1.618456482887268} 08/30/2021 19:53:33 - INFO - __main__ - Step 37043: {'lr': 0.0004339691845815786, 'samples': 7112256, 'steps': 37042, 'loss/train': 1.5284024477005005} 08/30/2021 19:53:33 - INFO - __main__ - Step 37044: {'lr': 0.0004339655912611795, 'samples': 7112448, 'steps': 37043, 'loss/train': 1.093475341796875} 08/30/2021 19:53:34 - INFO - __main__ - Step 37045: {'lr': 0.00043396199785788824, 'samples': 7112640, 'steps': 37044, 'loss/train': 1.6510095596313477} 08/30/2021 19:53:35 - INFO - __main__ - Step 37046: {'lr': 0.00043395840437170666, 'samples': 7112832, 'steps': 37045, 'loss/train': 1.233132243156433} 08/30/2021 19:53:35 - INFO - __main__ - Step 37047: {'lr': 0.00043395481080263614, 'samples': 7113024, 'steps': 37046, 'loss/train': 1.533531665802002} 08/30/2021 19:53:36 - INFO - __main__ - Step 37048: {'lr': 0.0004339512171506785, 'samples': 7113216, 'steps': 37047, 'loss/train': 1.6453118324279785} 08/30/2021 19:53:36 - INFO - __main__ - Step 37049: {'lr': 0.0004339476234158352, 'samples': 7113408, 'steps': 37048, 'loss/train': 1.7882049083709717} 08/30/2021 19:53:38 - INFO - __main__ - Step 37050: {'lr': 0.00043394402959810795, 'samples': 7113600, 'steps': 37049, 'loss/train': 1.091997504234314} 08/30/2021 19:53:38 - INFO - __main__ - Step 37051: {'lr': 0.00043394043569749843, 'samples': 7113792, 'steps': 37050, 'loss/train': 1.4180865287780762} 08/30/2021 19:53:39 - INFO - __main__ - Step 37052: {'lr': 0.00043393684171400817, 'samples': 7113984, 'steps': 37051, 'loss/train': 1.5587260723114014} 08/30/2021 19:53:39 - INFO - __main__ - Step 37053: {'lr': 0.00043393324764763873, 'samples': 7114176, 'steps': 37052, 'loss/train': 0.796995222568512} 08/30/2021 19:53:40 - INFO - __main__ - Step 37054: {'lr': 0.0004339296534983919, 'samples': 7114368, 'steps': 37053, 'loss/train': 0.9326147437095642} 08/30/2021 19:53:41 - INFO - __main__ - Step 37055: {'lr': 0.00043392605926626914, 'samples': 7114560, 'steps': 37054, 'loss/train': 0.9415121078491211} 08/30/2021 19:53:41 - INFO - __main__ - Step 37056: {'lr': 0.0004339224649512722, 'samples': 7114752, 'steps': 37055, 'loss/train': 1.4428216218948364} 08/30/2021 19:53:42 - INFO - __main__ - Step 37057: {'lr': 0.00043391887055340263, 'samples': 7114944, 'steps': 37056, 'loss/train': 1.523805856704712} 08/30/2021 19:53:42 - INFO - __main__ - Step 37058: {'lr': 0.000433915276072662, 'samples': 7115136, 'steps': 37057, 'loss/train': 1.5136395692825317} 08/30/2021 19:53:43 - INFO - __main__ - Step 37059: {'lr': 0.00043391168150905203, 'samples': 7115328, 'steps': 37058, 'loss/train': 1.1078822612762451} 08/30/2021 19:53:44 - INFO - __main__ - Step 37060: {'lr': 0.0004339080868625743, 'samples': 7115520, 'steps': 37059, 'loss/train': 0.41612711548805237} 08/30/2021 19:53:45 - INFO - __main__ - Step 37061: {'lr': 0.00043390449213323037, 'samples': 7115712, 'steps': 37060, 'loss/train': 1.3532260656356812} 08/30/2021 19:53:45 - INFO - __main__ - Step 37062: {'lr': 0.000433900897321022, 'samples': 7115904, 'steps': 37061, 'loss/train': 1.4750059843063354} 08/30/2021 19:53:46 - INFO - __main__ - Step 37063: {'lr': 0.0004338973024259506, 'samples': 7116096, 'steps': 37062, 'loss/train': 1.4050695896148682} 08/30/2021 19:53:46 - INFO - __main__ - Step 37064: {'lr': 0.00043389370744801806, 'samples': 7116288, 'steps': 37063, 'loss/train': 1.2933963537216187} 08/30/2021 19:53:48 - INFO - __main__ - Step 37065: {'lr': 0.00043389011238722575, 'samples': 7116480, 'steps': 37064, 'loss/train': 1.612127423286438} 08/30/2021 19:53:48 - INFO - __main__ - Step 37066: {'lr': 0.0004338865172435754, 'samples': 7116672, 'steps': 37065, 'loss/train': 1.811689853668213} 08/30/2021 19:53:48 - INFO - __main__ - Step 37067: {'lr': 0.00043388292201706867, 'samples': 7116864, 'steps': 37066, 'loss/train': 1.3822399377822876} 08/30/2021 19:53:49 - INFO - __main__ - Step 37068: {'lr': 0.0004338793267077071, 'samples': 7117056, 'steps': 37067, 'loss/train': 0.1393483281135559} 08/30/2021 19:53:49 - INFO - __main__ - Step 37069: {'lr': 0.0004338757313154923, 'samples': 7117248, 'steps': 37068, 'loss/train': 1.6364192962646484} 08/30/2021 19:53:50 - INFO - __main__ - Step 37070: {'lr': 0.000433872135840426, 'samples': 7117440, 'steps': 37069, 'loss/train': 1.6288944482803345} 08/30/2021 19:53:51 - INFO - __main__ - Step 37071: {'lr': 0.00043386854028250977, 'samples': 7117632, 'steps': 37070, 'loss/train': 1.01338529586792} 08/30/2021 19:53:51 - INFO - __main__ - Step 37072: {'lr': 0.00043386494464174515, 'samples': 7117824, 'steps': 37071, 'loss/train': 1.7017862796783447} 08/30/2021 19:53:52 - INFO - __main__ - Step 37073: {'lr': 0.0004338613489181338, 'samples': 7118016, 'steps': 37072, 'loss/train': 1.5734326839447021} 08/30/2021 19:53:52 - INFO - __main__ - Step 37074: {'lr': 0.00043385775311167746, 'samples': 7118208, 'steps': 37073, 'loss/train': 1.0885738134384155} 08/30/2021 19:53:52 - INFO - __main__ - Step 37075: {'lr': 0.00043385415722237765, 'samples': 7118400, 'steps': 37074, 'loss/train': 1.5801478624343872} 08/30/2021 19:53:54 - INFO - __main__ - Step 37076: {'lr': 0.0004338505612502359, 'samples': 7118592, 'steps': 37075, 'loss/train': 0.5208668112754822} 08/30/2021 19:53:54 - INFO - __main__ - Step 37077: {'lr': 0.000433846965195254, 'samples': 7118784, 'steps': 37076, 'loss/train': 1.3963780403137207} 08/30/2021 19:53:55 - INFO - __main__ - Step 37078: {'lr': 0.00043384336905743343, 'samples': 7118976, 'steps': 37077, 'loss/train': 1.4589495658874512} 08/30/2021 19:53:55 - INFO - __main__ - Step 37079: {'lr': 0.0004338397728367759, 'samples': 7119168, 'steps': 37078, 'loss/train': 1.3546909093856812} 08/30/2021 19:53:55 - INFO - __main__ - Step 37080: {'lr': 0.000433836176533283, 'samples': 7119360, 'steps': 37079, 'loss/train': 0.8696184158325195} 08/30/2021 19:53:57 - INFO - __main__ - Step 37081: {'lr': 0.0004338325801469564, 'samples': 7119552, 'steps': 37080, 'loss/train': 0.8663526177406311} 08/30/2021 19:53:57 - INFO - __main__ - Step 37082: {'lr': 0.00043382898367779767, 'samples': 7119744, 'steps': 37081, 'loss/train': 1.0161995887756348} 08/30/2021 19:53:58 - INFO - __main__ - Step 37083: {'lr': 0.00043382538712580845, 'samples': 7119936, 'steps': 37082, 'loss/train': 1.668605923652649} 08/30/2021 19:53:58 - INFO - __main__ - Step 37084: {'lr': 0.00043382179049099024, 'samples': 7120128, 'steps': 37083, 'loss/train': 0.6745041608810425} 08/30/2021 19:53:58 - INFO - __main__ - Step 37085: {'lr': 0.00043381819377334485, 'samples': 7120320, 'steps': 37084, 'loss/train': 1.7028006315231323} 08/30/2021 19:54:00 - INFO - __main__ - Step 37086: {'lr': 0.00043381459697287383, 'samples': 7120512, 'steps': 37085, 'loss/train': 1.6769983768463135} 08/30/2021 19:54:00 - INFO - __main__ - Step 37087: {'lr': 0.0004338110000895787, 'samples': 7120704, 'steps': 37086, 'loss/train': 1.716045618057251} 08/30/2021 19:54:01 - INFO - __main__ - Step 37088: {'lr': 0.00043380740312346135, 'samples': 7120896, 'steps': 37087, 'loss/train': 1.728021264076233} 08/30/2021 19:54:01 - INFO - __main__ - Step 37089: {'lr': 0.00043380380607452307, 'samples': 7121088, 'steps': 37088, 'loss/train': 2.275291919708252} 08/30/2021 19:54:01 - INFO - __main__ - Step 37090: {'lr': 0.0004338002089427657, 'samples': 7121280, 'steps': 37089, 'loss/train': 1.7778035402297974} 08/30/2021 19:54:03 - INFO - __main__ - Step 37091: {'lr': 0.00043379661172819075, 'samples': 7121472, 'steps': 37090, 'loss/train': 1.234944224357605} 08/30/2021 19:54:04 - INFO - __main__ - Step 37092: {'lr': 0.0004337930144307999, 'samples': 7121664, 'steps': 37091, 'loss/train': 1.5676524639129639} 08/30/2021 19:54:04 - INFO - __main__ - Step 37093: {'lr': 0.0004337894170505947, 'samples': 7121856, 'steps': 37092, 'loss/train': 1.1639885902404785} 08/30/2021 19:54:04 - INFO - __main__ - Step 37094: {'lr': 0.0004337858195875769, 'samples': 7122048, 'steps': 37093, 'loss/train': 0.280882865190506} 08/30/2021 19:54:05 - INFO - __main__ - Step 37095: {'lr': 0.00043378222204174807, 'samples': 7122240, 'steps': 37094, 'loss/train': 1.2138230800628662} 08/30/2021 19:54:06 - INFO - __main__ - Step 37096: {'lr': 0.0004337786244131097, 'samples': 7122432, 'steps': 37095, 'loss/train': 1.653456449508667} 08/30/2021 19:54:07 - INFO - __main__ - Step 37097: {'lr': 0.00043377502670166357, 'samples': 7122624, 'steps': 37096, 'loss/train': 1.5132277011871338} 08/30/2021 19:54:07 - INFO - __main__ - Step 37098: {'lr': 0.0004337714289074113, 'samples': 7122816, 'steps': 37097, 'loss/train': 0.9573349952697754} 08/30/2021 19:54:07 - INFO - __main__ - Step 37099: {'lr': 0.0004337678310303544, 'samples': 7123008, 'steps': 37098, 'loss/train': 1.622782588005066} 08/30/2021 19:54:08 - INFO - __main__ - Step 37100: {'lr': 0.00043376423307049455, 'samples': 7123200, 'steps': 37099, 'loss/train': 0.9316123723983765} 08/30/2021 19:54:10 - INFO - __main__ - Step 37101: {'lr': 0.00043376063502783337, 'samples': 7123392, 'steps': 37100, 'loss/train': 1.652148962020874} 08/30/2021 19:54:10 - INFO - __main__ - Step 37102: {'lr': 0.00043375703690237254, 'samples': 7123584, 'steps': 37101, 'loss/train': 1.684349775314331} 08/30/2021 19:54:11 - INFO - __main__ - Step 37103: {'lr': 0.0004337534386941135, 'samples': 7123776, 'steps': 37102, 'loss/train': 1.8276478052139282} 08/30/2021 19:54:11 - INFO - __main__ - Step 37104: {'lr': 0.00043374984040305816, 'samples': 7123968, 'steps': 37103, 'loss/train': 1.924911618232727} 08/30/2021 19:54:11 - INFO - __main__ - Step 37105: {'lr': 0.00043374624202920786, 'samples': 7124160, 'steps': 37104, 'loss/train': 1.290555715560913} 08/30/2021 19:54:13 - INFO - __main__ - Step 37106: {'lr': 0.0004337426435725644, 'samples': 7124352, 'steps': 37105, 'loss/train': 2.033660411834717} 08/30/2021 19:54:14 - INFO - __main__ - Step 37107: {'lr': 0.00043373904503312934, 'samples': 7124544, 'steps': 37106, 'loss/train': 1.5066791772842407} 08/30/2021 19:54:14 - INFO - __main__ - Step 37108: {'lr': 0.0004337354464109042, 'samples': 7124736, 'steps': 37107, 'loss/train': 0.9907783269882202} 08/30/2021 19:54:14 - INFO - __main__ - Step 37109: {'lr': 0.0004337318477058908, 'samples': 7124928, 'steps': 37108, 'loss/train': 1.429274320602417} 08/30/2021 19:54:15 - INFO - __main__ - Step 37110: {'lr': 0.0004337282489180907, 'samples': 7125120, 'steps': 37109, 'loss/train': 1.2618458271026611} 08/30/2021 19:54:15 - INFO - __main__ - Step 37111: {'lr': 0.0004337246500475054, 'samples': 7125312, 'steps': 37110, 'loss/train': 1.6446267366409302} 08/30/2021 19:54:16 - INFO - __main__ - Step 37112: {'lr': 0.0004337210510941366, 'samples': 7125504, 'steps': 37111, 'loss/train': 0.05694969743490219} 08/30/2021 19:54:17 - INFO - __main__ - Step 37113: {'lr': 0.000433717452057986, 'samples': 7125696, 'steps': 37112, 'loss/train': 1.4984523057937622} 08/30/2021 19:54:17 - INFO - __main__ - Step 37114: {'lr': 0.00043371385293905517, 'samples': 7125888, 'steps': 37113, 'loss/train': 1.72265625} 08/30/2021 19:54:18 - INFO - __main__ - Step 37115: {'lr': 0.0004337102537373456, 'samples': 7126080, 'steps': 37114, 'loss/train': 1.5365489721298218} 08/30/2021 19:54:18 - INFO - __main__ - Step 37116: {'lr': 0.0004337066544528591, 'samples': 7126272, 'steps': 37115, 'loss/train': 1.3277665376663208} 08/30/2021 19:54:19 - INFO - __main__ - Step 37117: {'lr': 0.00043370305508559723, 'samples': 7126464, 'steps': 37116, 'loss/train': 1.1964889764785767} 08/30/2021 19:54:20 - INFO - __main__ - Step 37118: {'lr': 0.00043369945563556157, 'samples': 7126656, 'steps': 37117, 'loss/train': 1.2485020160675049} 08/30/2021 19:54:20 - INFO - __main__ - Step 37119: {'lr': 0.00043369585610275374, 'samples': 7126848, 'steps': 37118, 'loss/train': 1.522022008895874} 08/30/2021 19:54:21 - INFO - __main__ - Step 37120: {'lr': 0.0004336922564871755, 'samples': 7127040, 'steps': 37119, 'loss/train': 1.2104867696762085} 08/30/2021 19:54:21 - INFO - __main__ - Step 37121: {'lr': 0.00043368865678882824, 'samples': 7127232, 'steps': 37120, 'loss/train': 0.8421387076377869} 08/30/2021 19:54:23 - INFO - __main__ - Step 37122: {'lr': 0.00043368505700771377, 'samples': 7127424, 'steps': 37121, 'loss/train': 1.1219406127929688} 08/30/2021 19:54:23 - INFO - __main__ - Step 37123: {'lr': 0.00043368145714383364, 'samples': 7127616, 'steps': 37122, 'loss/train': 1.9347363710403442} 08/30/2021 19:54:24 - INFO - __main__ - Step 37124: {'lr': 0.00043367785719718947, 'samples': 7127808, 'steps': 37123, 'loss/train': 1.542358160018921} 08/30/2021 19:54:24 - INFO - __main__ - Step 37125: {'lr': 0.0004336742571677829, 'samples': 7128000, 'steps': 37124, 'loss/train': 0.1368544101715088} 08/30/2021 19:54:24 - INFO - __main__ - Step 37126: {'lr': 0.00043367065705561547, 'samples': 7128192, 'steps': 37125, 'loss/train': 1.227088451385498} 08/30/2021 19:54:25 - INFO - __main__ - Step 37127: {'lr': 0.00043366705686068895, 'samples': 7128384, 'steps': 37126, 'loss/train': 1.4763684272766113} 08/30/2021 19:54:26 - INFO - __main__ - Step 37128: {'lr': 0.0004336634565830049, 'samples': 7128576, 'steps': 37127, 'loss/train': 0.3037351667881012} 08/30/2021 19:54:27 - INFO - __main__ - Step 37129: {'lr': 0.0004336598562225649, 'samples': 7128768, 'steps': 37128, 'loss/train': 0.9881518483161926} 08/30/2021 19:54:27 - INFO - __main__ - Step 37130: {'lr': 0.00043365625577937065, 'samples': 7128960, 'steps': 37129, 'loss/train': 0.9750529527664185} 08/30/2021 19:54:27 - INFO - __main__ - Step 37131: {'lr': 0.00043365265525342365, 'samples': 7129152, 'steps': 37130, 'loss/train': 1.4949061870574951} 08/30/2021 19:54:28 - INFO - __main__ - Step 37132: {'lr': 0.00043364905464472563, 'samples': 7129344, 'steps': 37131, 'loss/train': 1.2265797853469849} 08/30/2021 19:54:29 - INFO - __main__ - Step 37133: {'lr': 0.0004336454539532782, 'samples': 7129536, 'steps': 37132, 'loss/train': 1.5571553707122803} 08/30/2021 19:54:30 - INFO - __main__ - Step 37134: {'lr': 0.00043364185317908296, 'samples': 7129728, 'steps': 37133, 'loss/train': 0.9152698516845703} 08/30/2021 19:54:30 - INFO - __main__ - Step 37135: {'lr': 0.0004336382523221415, 'samples': 7129920, 'steps': 37134, 'loss/train': 1.4276806116104126} 08/30/2021 19:54:30 - INFO - __main__ - Step 37136: {'lr': 0.0004336346513824555, 'samples': 7130112, 'steps': 37135, 'loss/train': 1.975346326828003} 08/30/2021 19:54:31 - INFO - __main__ - Step 37137: {'lr': 0.0004336310503600266, 'samples': 7130304, 'steps': 37136, 'loss/train': 2.117755889892578} 08/30/2021 19:54:32 - INFO - __main__ - Step 37138: {'lr': 0.0004336274492548563, 'samples': 7130496, 'steps': 37137, 'loss/train': 1.3216679096221924} 08/30/2021 19:54:33 - INFO - __main__ - Step 37139: {'lr': 0.0004336238480669463, 'samples': 7130688, 'steps': 37138, 'loss/train': 1.5789737701416016} 08/30/2021 19:54:33 - INFO - __main__ - Step 37140: {'lr': 0.0004336202467962983, 'samples': 7130880, 'steps': 37139, 'loss/train': 1.8885977268218994} 08/30/2021 19:54:34 - INFO - __main__ - Step 37141: {'lr': 0.0004336166454429139, 'samples': 7131072, 'steps': 37140, 'loss/train': 1.868220567703247} 08/30/2021 19:54:34 - INFO - __main__ - Step 37142: {'lr': 0.0004336130440067946, 'samples': 7131264, 'steps': 37141, 'loss/train': 1.0575519800186157} 08/30/2021 19:54:35 - INFO - __main__ - Step 37143: {'lr': 0.000433609442487942, 'samples': 7131456, 'steps': 37142, 'loss/train': 1.2918672561645508} 08/30/2021 19:54:36 - INFO - __main__ - Step 37144: {'lr': 0.00043360584088635804, 'samples': 7131648, 'steps': 37143, 'loss/train': 2.4049482345581055} 08/30/2021 19:54:36 - INFO - __main__ - Step 37145: {'lr': 0.0004336022392020439, 'samples': 7131840, 'steps': 37144, 'loss/train': 1.272507905960083} 08/30/2021 19:54:37 - INFO - __main__ - Step 37146: {'lr': 0.0004335986374350015, 'samples': 7132032, 'steps': 37145, 'loss/train': 0.7864501476287842} 08/30/2021 19:54:37 - INFO - __main__ - Step 37147: {'lr': 0.00043359503558523246, 'samples': 7132224, 'steps': 37146, 'loss/train': 1.36385977268219} 08/30/2021 19:54:38 - INFO - __main__ - Step 37148: {'lr': 0.0004335914336527382, 'samples': 7132416, 'steps': 37147, 'loss/train': 1.7500404119491577} 08/30/2021 19:54:39 - INFO - __main__ - Step 37149: {'lr': 0.0004335878316375206, 'samples': 7132608, 'steps': 37148, 'loss/train': 1.0112521648406982} 08/30/2021 19:54:39 - INFO - __main__ - Step 37150: {'lr': 0.0004335842295395811, 'samples': 7132800, 'steps': 37149, 'loss/train': 0.23985888063907623} 08/30/2021 19:54:40 - INFO - __main__ - Step 37151: {'lr': 0.0004335806273589214, 'samples': 7132992, 'steps': 37150, 'loss/train': 1.2631280422210693} 08/30/2021 19:54:40 - INFO - __main__ - Step 37152: {'lr': 0.0004335770250955431, 'samples': 7133184, 'steps': 37151, 'loss/train': 1.8199909925460815} 08/30/2021 19:54:42 - INFO - __main__ - Step 37153: {'lr': 0.0004335734227494478, 'samples': 7133376, 'steps': 37152, 'loss/train': 1.0068362951278687} 08/30/2021 19:54:42 - INFO - __main__ - Step 37154: {'lr': 0.0004335698203206372, 'samples': 7133568, 'steps': 37153, 'loss/train': 1.2943278551101685} 08/30/2021 19:54:42 - INFO - __main__ - Step 37155: {'lr': 0.00043356621780911273, 'samples': 7133760, 'steps': 37154, 'loss/train': 1.223723292350769} 08/30/2021 19:54:43 - INFO - __main__ - Step 37156: {'lr': 0.0004335626152148763, 'samples': 7133952, 'steps': 37155, 'loss/train': 0.8880375623703003} 08/30/2021 19:54:43 - INFO - __main__ - Step 37157: {'lr': 0.0004335590125379293, 'samples': 7134144, 'steps': 37156, 'loss/train': 1.708461046218872} 08/30/2021 19:54:44 - INFO - __main__ - Step 37158: {'lr': 0.00043355540977827356, 'samples': 7134336, 'steps': 37157, 'loss/train': 1.7664451599121094} 08/30/2021 19:54:46 - INFO - __main__ - Step 37159: {'lr': 0.0004335518069359105, 'samples': 7134528, 'steps': 37158, 'loss/train': 1.7524760961532593} 08/30/2021 19:54:46 - INFO - __main__ - Step 37160: {'lr': 0.0004335482040108418, 'samples': 7134720, 'steps': 37159, 'loss/train': 1.235119342803955} 08/30/2021 19:54:47 - INFO - __main__ - Step 37161: {'lr': 0.00043354460100306915, 'samples': 7134912, 'steps': 37160, 'loss/train': 1.0423471927642822} 08/30/2021 19:54:47 - INFO - __main__ - Step 37162: {'lr': 0.00043354099791259414, 'samples': 7135104, 'steps': 37161, 'loss/train': 1.8361793756484985} 08/30/2021 19:54:47 - INFO - __main__ - Step 37163: {'lr': 0.00043353739473941846, 'samples': 7135296, 'steps': 37162, 'loss/train': 2.021512985229492} 08/30/2021 19:54:49 - INFO - __main__ - Step 37164: {'lr': 0.0004335337914835435, 'samples': 7135488, 'steps': 37163, 'loss/train': 1.564961552619934} 08/30/2021 19:54:49 - INFO - __main__ - Step 37165: {'lr': 0.0004335301881449711, 'samples': 7135680, 'steps': 37164, 'loss/train': 0.5492373704910278} 08/30/2021 19:54:50 - INFO - __main__ - Step 37166: {'lr': 0.00043352658472370294, 'samples': 7135872, 'steps': 37165, 'loss/train': 1.3987257480621338} 08/30/2021 19:54:50 - INFO - __main__ - Step 37167: {'lr': 0.00043352298121974043, 'samples': 7136064, 'steps': 37166, 'loss/train': 1.5350240468978882} 08/30/2021 19:54:50 - INFO - __main__ - Step 37168: {'lr': 0.00043351937763308533, 'samples': 7136256, 'steps': 37167, 'loss/train': 1.6532922983169556} 08/30/2021 19:54:52 - INFO - __main__ - Step 37169: {'lr': 0.0004335157739637392, 'samples': 7136448, 'steps': 37168, 'loss/train': 1.6544990539550781} 08/30/2021 19:54:52 - INFO - __main__ - Step 37170: {'lr': 0.0004335121702117038, 'samples': 7136640, 'steps': 37169, 'loss/train': 1.416341781616211} 08/30/2021 19:54:53 - INFO - __main__ - Step 37171: {'lr': 0.0004335085663769805, 'samples': 7136832, 'steps': 37170, 'loss/train': 0.6026067733764648} 08/30/2021 19:54:53 - INFO - __main__ - Step 37172: {'lr': 0.00043350496245957116, 'samples': 7137024, 'steps': 37171, 'loss/train': 2.3104517459869385} 08/30/2021 19:54:54 - INFO - __main__ - Step 37173: {'lr': 0.00043350135845947725, 'samples': 7137216, 'steps': 37172, 'loss/train': 1.5542380809783936} 08/30/2021 19:54:55 - INFO - __main__ - Step 37174: {'lr': 0.00043349775437670046, 'samples': 7137408, 'steps': 37173, 'loss/train': 1.3513115644454956} 08/30/2021 19:54:56 - INFO - __main__ - Step 37175: {'lr': 0.0004334941502112425, 'samples': 7137600, 'steps': 37174, 'loss/train': 0.10398662090301514} 08/30/2021 19:54:56 - INFO - __main__ - Step 37176: {'lr': 0.0004334905459631049, 'samples': 7137792, 'steps': 37175, 'loss/train': 0.24205230176448822} 08/30/2021 19:54:57 - INFO - __main__ - Step 37177: {'lr': 0.0004334869416322892, 'samples': 7137984, 'steps': 37176, 'loss/train': 1.1347286701202393} 08/30/2021 19:54:57 - INFO - __main__ - Step 37178: {'lr': 0.0004334833372187972, 'samples': 7138176, 'steps': 37177, 'loss/train': 0.954086184501648} 08/30/2021 19:54:58 - INFO - __main__ - Step 37179: {'lr': 0.0004334797327226304, 'samples': 7138368, 'steps': 37178, 'loss/train': 1.5092992782592773} 08/30/2021 19:54:59 - INFO - __main__ - Step 37180: {'lr': 0.00043347612814379047, 'samples': 7138560, 'steps': 37179, 'loss/train': 1.203762173652649} 08/30/2021 19:54:59 - INFO - __main__ - Step 37181: {'lr': 0.000433472523482279, 'samples': 7138752, 'steps': 37180, 'loss/train': 1.647207498550415} 08/30/2021 19:55:00 - INFO - __main__ - Step 37182: {'lr': 0.0004334689187380977, 'samples': 7138944, 'steps': 37181, 'loss/train': 1.4049173593521118} 08/30/2021 19:55:00 - INFO - __main__ - Step 37183: {'lr': 0.0004334653139112481, 'samples': 7139136, 'steps': 37182, 'loss/train': 1.3880038261413574} 08/30/2021 19:55:00 - INFO - __main__ - Step 37184: {'lr': 0.0004334617090017319, 'samples': 7139328, 'steps': 37183, 'loss/train': 1.5641449689865112} 08/30/2021 19:55:02 - INFO - __main__ - Step 37185: {'lr': 0.0004334581040095506, 'samples': 7139520, 'steps': 37184, 'loss/train': 1.4881904125213623} 08/30/2021 19:55:02 - INFO - __main__ - Step 37186: {'lr': 0.00043345449893470594, 'samples': 7139712, 'steps': 37185, 'loss/train': 1.1744705438613892} 08/30/2021 19:55:03 - INFO - __main__ - Step 37187: {'lr': 0.00043345089377719954, 'samples': 7139904, 'steps': 37186, 'loss/train': 1.065626859664917} 08/30/2021 19:55:03 - INFO - __main__ - Step 37188: {'lr': 0.00043344728853703297, 'samples': 7140096, 'steps': 37187, 'loss/train': 1.326798677444458} 08/30/2021 19:55:03 - INFO - __main__ - Step 37189: {'lr': 0.0004334436832142079, 'samples': 7140288, 'steps': 37188, 'loss/train': 1.3048057556152344} 08/30/2021 19:55:06 - INFO - __main__ - Step 37190: {'lr': 0.000433440077808726, 'samples': 7140480, 'steps': 37189, 'loss/train': 1.572681188583374} 08/30/2021 19:55:06 - INFO - __main__ - Step 37191: {'lr': 0.00043343647232058877, 'samples': 7140672, 'steps': 37190, 'loss/train': 1.8363094329833984} 08/30/2021 19:55:07 - INFO - __main__ - Step 37192: {'lr': 0.0004334328667497979, 'samples': 7140864, 'steps': 37191, 'loss/train': 2.047091245651245} 08/30/2021 19:55:07 - INFO - __main__ - Step 37193: {'lr': 0.00043342926109635497, 'samples': 7141056, 'steps': 37192, 'loss/train': 0.43282344937324524} 08/30/2021 19:55:07 - INFO - __main__ - Step 37194: {'lr': 0.0004334256553602617, 'samples': 7141248, 'steps': 37193, 'loss/train': 2.75614857673645} 08/30/2021 19:55:08 - INFO - __main__ - Step 37195: {'lr': 0.00043342204954151963, 'samples': 7141440, 'steps': 37194, 'loss/train': 1.511721134185791} 08/30/2021 19:55:08 - INFO - __main__ - Step 37196: {'lr': 0.00043341844364013047, 'samples': 7141632, 'steps': 37195, 'loss/train': 1.2944092750549316} 08/30/2021 19:55:10 - INFO - __main__ - Step 37197: {'lr': 0.00043341483765609566, 'samples': 7141824, 'steps': 37196, 'loss/train': 1.5528048276901245} 08/30/2021 19:55:10 - INFO - __main__ - Step 37198: {'lr': 0.0004334112315894171, 'samples': 7142016, 'steps': 37197, 'loss/train': 0.17207683622837067} 08/30/2021 19:55:10 - INFO - __main__ - Step 37199: {'lr': 0.00043340762544009627, 'samples': 7142208, 'steps': 37198, 'loss/train': 1.4666324853897095} 08/30/2021 19:55:11 - INFO - __main__ - Step 37200: {'lr': 0.0004334040192081347, 'samples': 7142400, 'steps': 37199, 'loss/train': 1.9627348184585571} 08/30/2021 19:55:11 - INFO - __main__ - Step 37201: {'lr': 0.00043340041289353416, 'samples': 7142592, 'steps': 37200, 'loss/train': 1.0309817790985107} 08/30/2021 19:55:13 - INFO - __main__ - Step 37202: {'lr': 0.0004333968064962962, 'samples': 7142784, 'steps': 37201, 'loss/train': 1.6099499464035034} 08/30/2021 19:55:14 - INFO - __main__ - Step 37203: {'lr': 0.00043339320001642244, 'samples': 7142976, 'steps': 37202, 'loss/train': 1.5217416286468506} 08/30/2021 19:55:14 - INFO - __main__ - Step 37204: {'lr': 0.0004333895934539146, 'samples': 7143168, 'steps': 37203, 'loss/train': 2.3480777740478516} 08/30/2021 19:55:15 - INFO - __main__ - Step 37205: {'lr': 0.00043338598680877423, 'samples': 7143360, 'steps': 37204, 'loss/train': 1.8372015953063965} 08/30/2021 19:55:15 - INFO - __main__ - Step 37206: {'lr': 0.00043338238008100297, 'samples': 7143552, 'steps': 37205, 'loss/train': 1.8181730508804321} 08/30/2021 19:55:15 - INFO - __main__ - Step 37207: {'lr': 0.0004333787732706024, 'samples': 7143744, 'steps': 37206, 'loss/train': 1.7918623685836792} 08/30/2021 19:55:16 - INFO - __main__ - Step 37208: {'lr': 0.00043337516637757416, 'samples': 7143936, 'steps': 37207, 'loss/train': 1.2571052312850952} 08/30/2021 19:55:17 - INFO - __main__ - Step 37209: {'lr': 0.00043337155940191996, 'samples': 7144128, 'steps': 37208, 'loss/train': 1.115092158317566} 08/30/2021 19:55:18 - INFO - __main__ - Step 37210: {'lr': 0.0004333679523436413, 'samples': 7144320, 'steps': 37209, 'loss/train': 1.2502648830413818} 08/30/2021 19:55:18 - INFO - __main__ - Step 37211: {'lr': 0.0004333643452027399, 'samples': 7144512, 'steps': 37210, 'loss/train': 0.840894877910614} 08/30/2021 19:55:18 - INFO - __main__ - Step 37212: {'lr': 0.00043336073797921743, 'samples': 7144704, 'steps': 37211, 'loss/train': 0.8375406861305237} 08/30/2021 19:55:19 - INFO - __main__ - Step 37213: {'lr': 0.0004333571306730754, 'samples': 7144896, 'steps': 37212, 'loss/train': 1.2654939889907837} 08/30/2021 19:55:19 - INFO - __main__ - Step 37214: {'lr': 0.00043335352328431544, 'samples': 7145088, 'steps': 37213, 'loss/train': 0.24022336304187775} 08/30/2021 19:55:21 - INFO - __main__ - Step 37215: {'lr': 0.00043334991581293924, 'samples': 7145280, 'steps': 37214, 'loss/train': 1.8620597124099731} 08/30/2021 19:55:21 - INFO - __main__ - Step 37216: {'lr': 0.0004333463082589484, 'samples': 7145472, 'steps': 37215, 'loss/train': 1.8533010482788086} 08/30/2021 19:55:22 - INFO - __main__ - Step 37217: {'lr': 0.0004333427006223445, 'samples': 7145664, 'steps': 37216, 'loss/train': 1.8302745819091797} 08/30/2021 19:55:22 - INFO - __main__ - Step 37218: {'lr': 0.00043333909290312923, 'samples': 7145856, 'steps': 37217, 'loss/train': 1.461767554283142} 08/30/2021 19:55:22 - INFO - __main__ - Step 37219: {'lr': 0.00043333548510130426, 'samples': 7146048, 'steps': 37218, 'loss/train': 1.3717758655548096} 08/30/2021 19:55:24 - INFO - __main__ - Step 37220: {'lr': 0.00043333187721687104, 'samples': 7146240, 'steps': 37219, 'loss/train': 1.4820228815078735} 08/30/2021 19:55:24 - INFO - __main__ - Step 37221: {'lr': 0.0004333282692498314, 'samples': 7146432, 'steps': 37220, 'loss/train': 1.2022372484207153} 08/30/2021 19:55:25 - INFO - __main__ - Step 37222: {'lr': 0.00043332466120018685, 'samples': 7146624, 'steps': 37221, 'loss/train': 1.107514500617981} 08/30/2021 19:55:25 - INFO - __main__ - Step 37223: {'lr': 0.000433321053067939, 'samples': 7146816, 'steps': 37222, 'loss/train': 1.4988950490951538} 08/30/2021 19:55:25 - INFO - __main__ - Step 37224: {'lr': 0.00043331744485308954, 'samples': 7147008, 'steps': 37223, 'loss/train': 1.3260629177093506} 08/30/2021 19:55:27 - INFO - __main__ - Step 37225: {'lr': 0.00043331383655564003, 'samples': 7147200, 'steps': 37224, 'loss/train': 1.2078348398208618} 08/30/2021 19:55:27 - INFO - __main__ - Step 37226: {'lr': 0.0004333102281755922, 'samples': 7147392, 'steps': 37225, 'loss/train': 1.2126277685165405} 08/30/2021 19:55:28 - INFO - __main__ - Step 37227: {'lr': 0.0004333066197129475, 'samples': 7147584, 'steps': 37226, 'loss/train': 1.4857620000839233} 08/30/2021 19:55:28 - INFO - __main__ - Step 37228: {'lr': 0.00043330301116770777, 'samples': 7147776, 'steps': 37227, 'loss/train': 0.8882859945297241} 08/30/2021 19:55:29 - INFO - __main__ - Step 37229: {'lr': 0.0004332994025398745, 'samples': 7147968, 'steps': 37228, 'loss/train': 1.3623707294464111} 08/30/2021 19:55:30 - INFO - __main__ - Step 37230: {'lr': 0.0004332957938294493, 'samples': 7148160, 'steps': 37229, 'loss/train': 1.6523367166519165} 08/30/2021 19:55:31 - INFO - __main__ - Step 37231: {'lr': 0.0004332921850364339, 'samples': 7148352, 'steps': 37230, 'loss/train': 0.6934989094734192} 08/30/2021 19:55:31 - INFO - __main__ - Step 37232: {'lr': 0.00043328857616082986, 'samples': 7148544, 'steps': 37231, 'loss/train': 1.1358364820480347} 08/30/2021 19:55:31 - INFO - __main__ - Step 37233: {'lr': 0.0004332849672026388, 'samples': 7148736, 'steps': 37232, 'loss/train': 1.2381203174591064} 08/30/2021 19:55:32 - INFO - __main__ - Step 37234: {'lr': 0.0004332813581618624, 'samples': 7148928, 'steps': 37233, 'loss/train': 1.1748789548873901} 08/30/2021 19:55:32 - INFO - __main__ - Step 37235: {'lr': 0.00043327774903850226, 'samples': 7149120, 'steps': 37234, 'loss/train': 1.7189126014709473} 08/30/2021 19:55:33 - INFO - __main__ - Step 37236: {'lr': 0.0004332741398325599, 'samples': 7149312, 'steps': 37235, 'loss/train': 0.944999635219574} 08/30/2021 19:55:34 - INFO - __main__ - Step 37237: {'lr': 0.00043327053054403707, 'samples': 7149504, 'steps': 37236, 'loss/train': 0.4593856930732727} 08/30/2021 19:55:34 - INFO - __main__ - Step 37238: {'lr': 0.0004332669211729354, 'samples': 7149696, 'steps': 37237, 'loss/train': 1.4445148706436157} 08/30/2021 19:55:35 - INFO - __main__ - Step 37239: {'lr': 0.00043326331171925656, 'samples': 7149888, 'steps': 37238, 'loss/train': 1.6017992496490479} 08/30/2021 19:55:35 - INFO - __main__ - Step 37240: {'lr': 0.000433259702183002, 'samples': 7150080, 'steps': 37239, 'loss/train': 0.5682351589202881} 08/30/2021 19:55:36 - INFO - __main__ - Step 37241: {'lr': 0.0004332560925641734, 'samples': 7150272, 'steps': 37240, 'loss/train': 1.3645657300949097} 08/30/2021 19:55:37 - INFO - __main__ - Step 37242: {'lr': 0.0004332524828627725, 'samples': 7150464, 'steps': 37241, 'loss/train': 1.4339689016342163} 08/30/2021 19:55:37 - INFO - __main__ - Step 37243: {'lr': 0.0004332488730788009, 'samples': 7150656, 'steps': 37242, 'loss/train': 1.087787389755249} 08/30/2021 19:55:38 - INFO - __main__ - Step 37244: {'lr': 0.0004332452632122601, 'samples': 7150848, 'steps': 37243, 'loss/train': 1.5928938388824463} 08/30/2021 19:55:38 - INFO - __main__ - Step 37245: {'lr': 0.0004332416532631519, 'samples': 7151040, 'steps': 37244, 'loss/train': 0.34386229515075684} 08/30/2021 19:55:40 - INFO - __main__ - Step 37246: {'lr': 0.00043323804323147777, 'samples': 7151232, 'steps': 37245, 'loss/train': 1.358180284500122} 08/30/2021 19:55:40 - INFO - __main__ - Step 37247: {'lr': 0.0004332344331172394, 'samples': 7151424, 'steps': 37246, 'loss/train': 1.5665887594223022} 08/30/2021 19:55:41 - INFO - __main__ - Step 37248: {'lr': 0.0004332308229204385, 'samples': 7151616, 'steps': 37247, 'loss/train': 1.357224941253662} 08/30/2021 19:55:41 - INFO - __main__ - Step 37249: {'lr': 0.00043322721264107657, 'samples': 7151808, 'steps': 37248, 'loss/train': 1.1494323015213013} 08/30/2021 19:55:41 - INFO - __main__ - Step 37250: {'lr': 0.00043322360227915526, 'samples': 7152000, 'steps': 37249, 'loss/train': 0.16026242077350616} 08/30/2021 19:55:43 - INFO - __main__ - Step 37251: {'lr': 0.0004332199918346763, 'samples': 7152192, 'steps': 37250, 'loss/train': 0.15770988166332245} 08/30/2021 19:55:43 - INFO - __main__ - Step 37252: {'lr': 0.00043321638130764116, 'samples': 7152384, 'steps': 37251, 'loss/train': 1.315923810005188} 08/30/2021 19:55:44 - INFO - __main__ - Step 37253: {'lr': 0.00043321277069805153, 'samples': 7152576, 'steps': 37252, 'loss/train': 0.7792982459068298} 08/30/2021 19:55:44 - INFO - __main__ - Step 37254: {'lr': 0.0004332091600059091, 'samples': 7152768, 'steps': 37253, 'loss/train': 1.541377067565918} 08/30/2021 19:55:44 - INFO - __main__ - Step 37255: {'lr': 0.00043320554923121545, 'samples': 7152960, 'steps': 37254, 'loss/train': 1.4678643941879272} 08/30/2021 19:55:45 - INFO - __main__ - Step 37256: {'lr': 0.0004332019383739722, 'samples': 7153152, 'steps': 37255, 'loss/train': 1.4669246673583984} 08/30/2021 19:55:47 - INFO - __main__ - Step 37257: {'lr': 0.000433198327434181, 'samples': 7153344, 'steps': 37256, 'loss/train': 1.6319292783737183} 08/30/2021 19:55:47 - INFO - __main__ - Step 37258: {'lr': 0.0004331947164118434, 'samples': 7153536, 'steps': 37257, 'loss/train': 1.3833212852478027} 08/30/2021 19:55:47 - INFO - __main__ - Step 37259: {'lr': 0.00043319110530696116, 'samples': 7153728, 'steps': 37258, 'loss/train': 1.1719000339508057} 08/30/2021 19:55:48 - INFO - __main__ - Step 37260: {'lr': 0.00043318749411953584, 'samples': 7153920, 'steps': 37259, 'loss/train': 1.6889448165893555} 08/30/2021 19:55:48 - INFO - __main__ - Step 37261: {'lr': 0.000433183882849569, 'samples': 7154112, 'steps': 37260, 'loss/train': 1.5338735580444336} 08/30/2021 19:55:49 - INFO - __main__ - Step 37262: {'lr': 0.0004331802714970624, 'samples': 7154304, 'steps': 37261, 'loss/train': 1.3940200805664062} 08/30/2021 19:55:50 - INFO - __main__ - Step 37263: {'lr': 0.0004331766600620175, 'samples': 7154496, 'steps': 37262, 'loss/train': 1.5051100254058838} 08/30/2021 19:55:50 - INFO - __main__ - Step 37264: {'lr': 0.00043317304854443607, 'samples': 7154688, 'steps': 37263, 'loss/train': 1.626781940460205} 08/30/2021 19:55:51 - INFO - __main__ - Step 37265: {'lr': 0.0004331694369443197, 'samples': 7154880, 'steps': 37264, 'loss/train': 1.3269175291061401} 08/30/2021 19:55:51 - INFO - __main__ - Step 37266: {'lr': 0.00043316582526167004, 'samples': 7155072, 'steps': 37265, 'loss/train': 1.393304467201233} 08/30/2021 19:55:53 - INFO - __main__ - Step 37267: {'lr': 0.0004331622134964887, 'samples': 7155264, 'steps': 37266, 'loss/train': 1.2010682821273804} 08/30/2021 19:55:53 - INFO - __main__ - Step 37268: {'lr': 0.0004331586016487772, 'samples': 7155456, 'steps': 37267, 'loss/train': 0.3664584457874298} 08/30/2021 19:55:53 - INFO - __main__ - Step 37269: {'lr': 0.00043315498971853726, 'samples': 7155648, 'steps': 37268, 'loss/train': 0.09463349729776382} 08/30/2021 19:55:54 - INFO - __main__ - Step 37270: {'lr': 0.0004331513777057706, 'samples': 7155840, 'steps': 37269, 'loss/train': 1.4243720769882202} 08/30/2021 19:55:54 - INFO - __main__ - Step 37271: {'lr': 0.00043314776561047865, 'samples': 7156032, 'steps': 37270, 'loss/train': 1.5816227197647095} 08/30/2021 19:55:56 - INFO - __main__ - Step 37272: {'lr': 0.0004331441534326632, 'samples': 7156224, 'steps': 37271, 'loss/train': 1.6990299224853516} 08/30/2021 19:55:56 - INFO - __main__ - Step 37273: {'lr': 0.0004331405411723258, 'samples': 7156416, 'steps': 37272, 'loss/train': 1.6356576681137085} 08/30/2021 19:55:57 - INFO - __main__ - Step 37274: {'lr': 0.0004331369288294681, 'samples': 7156608, 'steps': 37273, 'loss/train': 1.199906587600708} 08/30/2021 19:55:57 - INFO - __main__ - Step 37275: {'lr': 0.0004331333164040918, 'samples': 7156800, 'steps': 37274, 'loss/train': 1.1874136924743652} 08/30/2021 19:55:58 - INFO - __main__ - Step 37276: {'lr': 0.0004331297038961984, 'samples': 7156992, 'steps': 37275, 'loss/train': 1.125455379486084} 08/30/2021 19:55:59 - INFO - __main__ - Step 37277: {'lr': 0.00043312609130578963, 'samples': 7157184, 'steps': 37276, 'loss/train': 1.2430005073547363} 08/30/2021 19:56:00 - INFO - __main__ - Step 37278: {'lr': 0.000433122478632867, 'samples': 7157376, 'steps': 37277, 'loss/train': 0.1170068085193634} 08/30/2021 19:56:00 - INFO - __main__ - Step 37279: {'lr': 0.0004331188658774322, 'samples': 7157568, 'steps': 37278, 'loss/train': 1.7714715003967285} 08/30/2021 19:56:00 - INFO - __main__ - Step 37280: {'lr': 0.00043311525303948685, 'samples': 7157760, 'steps': 37279, 'loss/train': 0.8312937617301941} 08/30/2021 19:56:01 - INFO - __main__ - Step 37281: {'lr': 0.0004331116401190327, 'samples': 7157952, 'steps': 37280, 'loss/train': 1.6909489631652832} 08/30/2021 19:56:02 - INFO - __main__ - Step 37282: {'lr': 0.0004331080271160712, 'samples': 7158144, 'steps': 37281, 'loss/train': 1.5297600030899048} 08/30/2021 19:56:03 - INFO - __main__ - Step 37283: {'lr': 0.00043310441403060404, 'samples': 7158336, 'steps': 37282, 'loss/train': 1.5976977348327637} 08/30/2021 19:56:03 - INFO - __main__ - Step 37284: {'lr': 0.00043310080086263284, 'samples': 7158528, 'steps': 37283, 'loss/train': 1.4269418716430664} 08/30/2021 19:56:03 - INFO - __main__ - Step 37285: {'lr': 0.0004330971876121593, 'samples': 7158720, 'steps': 37284, 'loss/train': 1.2697572708129883} 08/30/2021 19:56:04 - INFO - __main__ - Step 37286: {'lr': 0.0004330935742791849, 'samples': 7158912, 'steps': 37285, 'loss/train': 1.423542857170105} 08/30/2021 19:56:06 - INFO - __main__ - Step 37287: {'lr': 0.00043308996086371146, 'samples': 7159104, 'steps': 37286, 'loss/train': 2.171774387359619} 08/30/2021 19:56:06 - INFO - __main__ - Step 37288: {'lr': 0.0004330863473657405, 'samples': 7159296, 'steps': 37287, 'loss/train': 1.756593942642212} 08/30/2021 19:56:07 - INFO - __main__ - Step 37289: {'lr': 0.00043308273378527364, 'samples': 7159488, 'steps': 37288, 'loss/train': 1.410674810409546} 08/30/2021 19:56:07 - INFO - __main__ - Step 37290: {'lr': 0.00043307912012231255, 'samples': 7159680, 'steps': 37289, 'loss/train': 1.7248365879058838} 08/30/2021 19:56:07 - INFO - __main__ - Step 37291: {'lr': 0.0004330755063768588, 'samples': 7159872, 'steps': 37290, 'loss/train': 0.11255665123462677} 08/30/2021 19:56:08 - INFO - __main__ - Step 37292: {'lr': 0.000433071892548914, 'samples': 7160064, 'steps': 37291, 'loss/train': 0.06722675263881683} 08/30/2021 19:56:08 - INFO - __main__ - Step 37293: {'lr': 0.00043306827863847985, 'samples': 7160256, 'steps': 37292, 'loss/train': 1.6550936698913574} 08/30/2021 19:56:10 - INFO - __main__ - Step 37294: {'lr': 0.00043306466464555803, 'samples': 7160448, 'steps': 37293, 'loss/train': 0.29456886649131775} 08/30/2021 19:56:10 - INFO - __main__ - Step 37295: {'lr': 0.0004330610505701501, 'samples': 7160640, 'steps': 37294, 'loss/train': 1.5085599422454834} 08/30/2021 19:56:11 - INFO - __main__ - Step 37296: {'lr': 0.00043305743641225766, 'samples': 7160832, 'steps': 37295, 'loss/train': 1.5765646696090698} 08/30/2021 19:56:11 - INFO - __main__ - Step 37297: {'lr': 0.00043305382217188225, 'samples': 7161024, 'steps': 37296, 'loss/train': 1.4817980527877808} 08/30/2021 19:56:11 - INFO - __main__ - Step 37298: {'lr': 0.0004330502078490258, 'samples': 7161216, 'steps': 37297, 'loss/train': 1.6245449781417847} 08/30/2021 19:56:13 - INFO - __main__ - Step 37299: {'lr': 0.0004330465934436896, 'samples': 7161408, 'steps': 37298, 'loss/train': 1.7996934652328491} 08/30/2021 19:56:13 - INFO - __main__ - Step 37300: {'lr': 0.00043304297895587553, 'samples': 7161600, 'steps': 37299, 'loss/train': 1.0784474611282349} 08/30/2021 19:56:14 - INFO - __main__ - Step 37301: {'lr': 0.0004330393643855851, 'samples': 7161792, 'steps': 37300, 'loss/train': 1.261918067932129} 08/30/2021 19:56:14 - INFO - __main__ - Step 37302: {'lr': 0.0004330357497328199, 'samples': 7161984, 'steps': 37301, 'loss/train': 1.263678789138794} 08/30/2021 19:56:14 - INFO - __main__ - Step 37303: {'lr': 0.00043303213499758166, 'samples': 7162176, 'steps': 37302, 'loss/train': 1.6204594373703003} 08/30/2021 19:56:16 - INFO - __main__ - Step 37304: {'lr': 0.00043302852017987196, 'samples': 7162368, 'steps': 37303, 'loss/train': 1.5933401584625244} 08/30/2021 19:56:17 - INFO - __main__ - Step 37305: {'lr': 0.0004330249052796924, 'samples': 7162560, 'steps': 37304, 'loss/train': 0.846378743648529} 08/30/2021 19:56:17 - INFO - __main__ - Step 37306: {'lr': 0.0004330212902970447, 'samples': 7162752, 'steps': 37305, 'loss/train': 1.3449466228485107} 08/30/2021 19:56:17 - INFO - __main__ - Step 37307: {'lr': 0.0004330176752319304, 'samples': 7162944, 'steps': 37306, 'loss/train': 1.298366904258728} 08/30/2021 19:56:18 - INFO - __main__ - Step 37308: {'lr': 0.0004330140600843512, 'samples': 7163136, 'steps': 37307, 'loss/train': 0.14137066900730133} 08/30/2021 19:56:18 - INFO - __main__ - Step 37309: {'lr': 0.0004330104448543086, 'samples': 7163328, 'steps': 37308, 'loss/train': 1.425593376159668} 08/30/2021 19:56:20 - INFO - __main__ - Step 37310: {'lr': 0.0004330068295418044, 'samples': 7163520, 'steps': 37309, 'loss/train': 1.1895626783370972} 08/30/2021 19:56:20 - INFO - __main__ - Step 37311: {'lr': 0.0004330032141468401, 'samples': 7163712, 'steps': 37310, 'loss/train': 1.4988731145858765} 08/30/2021 19:56:20 - INFO - __main__ - Step 37312: {'lr': 0.0004329995986694174, 'samples': 7163904, 'steps': 37311, 'loss/train': 1.6009279489517212} 08/30/2021 19:56:21 - INFO - __main__ - Step 37313: {'lr': 0.00043299598310953793, 'samples': 7164096, 'steps': 37312, 'loss/train': 1.7883325815200806} 08/30/2021 19:56:21 - INFO - __main__ - Step 37314: {'lr': 0.0004329923674672032, 'samples': 7164288, 'steps': 37313, 'loss/train': 1.531451940536499} 08/30/2021 19:56:23 - INFO - __main__ - Step 37315: {'lr': 0.00043298875174241504, 'samples': 7164480, 'steps': 37314, 'loss/train': 1.3104544878005981} 08/30/2021 19:56:23 - INFO - __main__ - Step 37316: {'lr': 0.00043298513593517483, 'samples': 7164672, 'steps': 37315, 'loss/train': 1.6571338176727295} 08/30/2021 19:56:24 - INFO - __main__ - Step 37317: {'lr': 0.0004329815200454845, 'samples': 7164864, 'steps': 37316, 'loss/train': 0.07107654958963394} 08/30/2021 19:56:24 - INFO - __main__ - Step 37318: {'lr': 0.00043297790407334545, 'samples': 7165056, 'steps': 37317, 'loss/train': 1.0674660205841064} 08/30/2021 19:56:24 - INFO - __main__ - Step 37319: {'lr': 0.0004329742880187594, 'samples': 7165248, 'steps': 37318, 'loss/train': 1.6088038682937622} 08/30/2021 19:56:26 - INFO - __main__ - Step 37320: {'lr': 0.0004329706718817279, 'samples': 7165440, 'steps': 37319, 'loss/train': 1.5619314908981323} 08/30/2021 19:56:27 - INFO - __main__ - Step 37321: {'lr': 0.00043296705566225267, 'samples': 7165632, 'steps': 37320, 'loss/train': 1.4305415153503418} 08/30/2021 19:56:27 - INFO - __main__ - Step 37322: {'lr': 0.00043296343936033535, 'samples': 7165824, 'steps': 37321, 'loss/train': 1.6878626346588135} 08/30/2021 19:56:27 - INFO - __main__ - Step 37323: {'lr': 0.0004329598229759775, 'samples': 7166016, 'steps': 37322, 'loss/train': 1.2063426971435547} 08/30/2021 19:56:28 - INFO - __main__ - Step 37324: {'lr': 0.00043295620650918076, 'samples': 7166208, 'steps': 37323, 'loss/train': 0.07216602563858032} 08/30/2021 19:56:28 - INFO - __main__ - Step 37325: {'lr': 0.0004329525899599468, 'samples': 7166400, 'steps': 37324, 'loss/train': 0.3446216881275177} 08/30/2021 19:56:30 - INFO - __main__ - Step 37326: {'lr': 0.0004329489733282772, 'samples': 7166592, 'steps': 37325, 'loss/train': 0.14824801683425903} 08/30/2021 19:56:30 - INFO - __main__ - Step 37327: {'lr': 0.0004329453566141737, 'samples': 7166784, 'steps': 37326, 'loss/train': 1.5553874969482422} 08/30/2021 19:56:31 - INFO - __main__ - Step 37328: {'lr': 0.00043294173981763776, 'samples': 7166976, 'steps': 37327, 'loss/train': 1.5382400751113892} 08/30/2021 19:56:31 - INFO - __main__ - Step 37329: {'lr': 0.00043293812293867113, 'samples': 7167168, 'steps': 37328, 'loss/train': 1.0531420707702637} 08/30/2021 19:56:31 - INFO - __main__ - Step 37330: {'lr': 0.0004329345059772754, 'samples': 7167360, 'steps': 37329, 'loss/train': 1.4449208974838257} 08/30/2021 19:56:33 - INFO - __main__ - Step 37331: {'lr': 0.0004329308889334522, 'samples': 7167552, 'steps': 37330, 'loss/train': 1.391638159751892} 08/30/2021 19:56:33 - INFO - __main__ - Step 37332: {'lr': 0.00043292727180720315, 'samples': 7167744, 'steps': 37331, 'loss/train': 1.972778558731079} 08/30/2021 19:56:34 - INFO - __main__ - Step 37333: {'lr': 0.0004329236545985299, 'samples': 7167936, 'steps': 37332, 'loss/train': 1.0132642984390259} 08/30/2021 19:56:34 - INFO - __main__ - Step 37334: {'lr': 0.000432920037307434, 'samples': 7168128, 'steps': 37333, 'loss/train': 1.914176106452942} 08/30/2021 19:56:34 - INFO - __main__ - Step 37335: {'lr': 0.00043291641993391727, 'samples': 7168320, 'steps': 37334, 'loss/train': 1.3197611570358276} 08/30/2021 19:56:36 - INFO - __main__ - Step 37336: {'lr': 0.0004329128024779812, 'samples': 7168512, 'steps': 37335, 'loss/train': 0.8799515962600708} 08/30/2021 19:56:37 - INFO - __main__ - Step 37337: {'lr': 0.0004329091849396274, 'samples': 7168704, 'steps': 37336, 'loss/train': 1.0617070198059082} 08/30/2021 19:56:37 - INFO - __main__ - Step 37338: {'lr': 0.00043290556731885756, 'samples': 7168896, 'steps': 37337, 'loss/train': 1.0679913759231567} 08/30/2021 19:56:37 - INFO - __main__ - Step 37339: {'lr': 0.0004329019496156733, 'samples': 7169088, 'steps': 37338, 'loss/train': 0.05821027234196663} 08/30/2021 19:56:38 - INFO - __main__ - Step 37340: {'lr': 0.0004328983318300763, 'samples': 7169280, 'steps': 37339, 'loss/train': 0.5832203030586243} 08/30/2021 19:56:39 - INFO - __main__ - Step 37341: {'lr': 0.00043289471396206803, 'samples': 7169472, 'steps': 37340, 'loss/train': 2.432037830352783} 08/30/2021 19:56:40 - INFO - __main__ - Step 37342: {'lr': 0.0004328910960116503, 'samples': 7169664, 'steps': 37341, 'loss/train': 1.2108513116836548} 08/30/2021 19:56:40 - INFO - __main__ - Step 37343: {'lr': 0.00043288747797882467, 'samples': 7169856, 'steps': 37342, 'loss/train': 1.0174715518951416} 08/30/2021 19:56:40 - INFO - __main__ - Step 37344: {'lr': 0.00043288385986359266, 'samples': 7170048, 'steps': 37343, 'loss/train': 1.4958276748657227} 08/30/2021 19:56:41 - INFO - __main__ - Step 37345: {'lr': 0.00043288024166595614, 'samples': 7170240, 'steps': 37344, 'loss/train': 1.271643042564392} 08/30/2021 19:56:41 - INFO - __main__ - Step 37346: {'lr': 0.00043287662338591657, 'samples': 7170432, 'steps': 37345, 'loss/train': 1.5020782947540283} 08/30/2021 19:56:43 - INFO - __main__ - Step 37347: {'lr': 0.0004328730050234756, 'samples': 7170624, 'steps': 37346, 'loss/train': 1.7531085014343262} 08/30/2021 19:56:43 - INFO - __main__ - Step 37348: {'lr': 0.00043286938657863483, 'samples': 7170816, 'steps': 37347, 'loss/train': 1.0881903171539307} 08/30/2021 19:56:43 - INFO - __main__ - Step 37349: {'lr': 0.00043286576805139597, 'samples': 7171008, 'steps': 37348, 'loss/train': 1.3239662647247314} 08/30/2021 19:56:44 - INFO - __main__ - Step 37350: {'lr': 0.0004328621494417606, 'samples': 7171200, 'steps': 37349, 'loss/train': 1.359250783920288} 08/30/2021 19:56:44 - INFO - __main__ - Step 37351: {'lr': 0.0004328585307497304, 'samples': 7171392, 'steps': 37350, 'loss/train': 1.7430981397628784} 08/30/2021 19:56:44 - INFO - __main__ - Step 37352: {'lr': 0.00043285491197530694, 'samples': 7171584, 'steps': 37351, 'loss/train': 1.6985012292861938} 08/30/2021 19:56:46 - INFO - __main__ - Step 37353: {'lr': 0.00043285129311849193, 'samples': 7171776, 'steps': 37352, 'loss/train': 0.9445045590400696} 08/30/2021 19:56:46 - INFO - __main__ - Step 37354: {'lr': 0.0004328476741792869, 'samples': 7171968, 'steps': 37353, 'loss/train': 0.12586896121501923} 08/30/2021 19:56:47 - INFO - __main__ - Step 37355: {'lr': 0.00043284405515769356, 'samples': 7172160, 'steps': 37354, 'loss/train': 1.033687710762024} 08/30/2021 19:56:47 - INFO - __main__ - Step 37356: {'lr': 0.00043284043605371346, 'samples': 7172352, 'steps': 37355, 'loss/train': 1.3645912408828735} 08/30/2021 19:56:49 - INFO - __main__ - Step 37357: {'lr': 0.0004328368168673483, 'samples': 7172544, 'steps': 37356, 'loss/train': 1.8850632905960083} 08/30/2021 19:56:49 - INFO - __main__ - Step 37358: {'lr': 0.00043283319759859974, 'samples': 7172736, 'steps': 37357, 'loss/train': 1.6752790212631226} 08/30/2021 19:56:49 - INFO - __main__ - Step 37359: {'lr': 0.0004328295782474693, 'samples': 7172928, 'steps': 37358, 'loss/train': 1.166944980621338} 08/30/2021 19:56:50 - INFO - __main__ - Step 37360: {'lr': 0.0004328259588139587, 'samples': 7173120, 'steps': 37359, 'loss/train': 1.457136869430542} 08/30/2021 19:56:50 - INFO - __main__ - Step 37361: {'lr': 0.0004328223392980696, 'samples': 7173312, 'steps': 37360, 'loss/train': 2.1077630519866943} 08/30/2021 19:56:50 - INFO - __main__ - Step 37362: {'lr': 0.00043281871969980346, 'samples': 7173504, 'steps': 37361, 'loss/train': 1.880540370941162} 08/30/2021 19:56:52 - INFO - __main__ - Step 37363: {'lr': 0.00043281510001916214, 'samples': 7173696, 'steps': 37362, 'loss/train': 2.121408224105835} 08/30/2021 19:56:52 - INFO - __main__ - Step 37364: {'lr': 0.0004328114802561471, 'samples': 7173888, 'steps': 37363, 'loss/train': 1.6379472017288208} 08/30/2021 19:56:53 - INFO - __main__ - Step 37365: {'lr': 0.00043280786041076006, 'samples': 7174080, 'steps': 37364, 'loss/train': 1.5812128782272339} 08/30/2021 19:56:53 - INFO - __main__ - Step 37366: {'lr': 0.0004328042404830026, 'samples': 7174272, 'steps': 37365, 'loss/train': 1.535988450050354} 08/30/2021 19:56:53 - INFO - __main__ - Step 37367: {'lr': 0.0004328006204728763, 'samples': 7174464, 'steps': 37366, 'loss/train': 1.198941946029663} 08/30/2021 19:56:55 - INFO - __main__ - Step 37368: {'lr': 0.00043279700038038296, 'samples': 7174656, 'steps': 37367, 'loss/train': 1.422837257385254} 08/30/2021 19:56:55 - INFO - __main__ - Step 37369: {'lr': 0.0004327933802055241, 'samples': 7174848, 'steps': 37368, 'loss/train': 1.2558835744857788} 08/30/2021 19:56:56 - INFO - __main__ - Step 37370: {'lr': 0.0004327897599483013, 'samples': 7175040, 'steps': 37369, 'loss/train': 1.3162193298339844} 08/30/2021 19:56:56 - INFO - __main__ - Step 37371: {'lr': 0.00043278613960871624, 'samples': 7175232, 'steps': 37370, 'loss/train': 1.0559483766555786} 08/30/2021 19:56:56 - INFO - __main__ - Step 37372: {'lr': 0.00043278251918677066, 'samples': 7175424, 'steps': 37371, 'loss/train': 0.9671065807342529} 08/30/2021 19:56:58 - INFO - __main__ - Step 37373: {'lr': 0.00043277889868246605, 'samples': 7175616, 'steps': 37372, 'loss/train': 1.4900364875793457} 08/30/2021 19:56:59 - INFO - __main__ - Step 37374: {'lr': 0.0004327752780958041, 'samples': 7175808, 'steps': 37373, 'loss/train': 0.9577486515045166} 08/30/2021 19:56:59 - INFO - __main__ - Step 37375: {'lr': 0.0004327716574267864, 'samples': 7176000, 'steps': 37374, 'loss/train': 2.4016902446746826} 08/30/2021 19:56:59 - INFO - __main__ - Step 37376: {'lr': 0.00043276803667541465, 'samples': 7176192, 'steps': 37375, 'loss/train': 1.3319861888885498} 08/30/2021 19:57:00 - INFO - __main__ - Step 37377: {'lr': 0.0004327644158416905, 'samples': 7176384, 'steps': 37376, 'loss/train': 1.5461835861206055} 08/30/2021 19:57:02 - INFO - __main__ - Step 37378: {'lr': 0.0004327607949256154, 'samples': 7176576, 'steps': 37377, 'loss/train': 0.04532282054424286} 08/30/2021 19:57:02 - INFO - __main__ - Step 37379: {'lr': 0.00043275717392719115, 'samples': 7176768, 'steps': 37378, 'loss/train': 1.0498652458190918} 08/30/2021 19:57:02 - INFO - __main__ - Step 37380: {'lr': 0.0004327535528464194, 'samples': 7176960, 'steps': 37379, 'loss/train': 0.8886426091194153} 08/30/2021 19:57:03 - INFO - __main__ - Step 37381: {'lr': 0.0004327499316833016, 'samples': 7177152, 'steps': 37380, 'loss/train': 1.3985416889190674} 08/30/2021 19:57:03 - INFO - __main__ - Step 37382: {'lr': 0.0004327463104378395, 'samples': 7177344, 'steps': 37381, 'loss/train': 1.2480146884918213} 08/30/2021 19:57:05 - INFO - __main__ - Step 37383: {'lr': 0.0004327426891100349, 'samples': 7177536, 'steps': 37382, 'loss/train': 1.7824444770812988} 08/30/2021 19:57:06 - INFO - __main__ - Step 37384: {'lr': 0.0004327390676998891, 'samples': 7177728, 'steps': 37383, 'loss/train': 1.5549664497375488} 08/30/2021 19:57:06 - INFO - __main__ - Step 37385: {'lr': 0.000432735446207404, 'samples': 7177920, 'steps': 37384, 'loss/train': 1.207931637763977} 08/30/2021 19:57:06 - INFO - __main__ - Step 37386: {'lr': 0.0004327318246325811, 'samples': 7178112, 'steps': 37385, 'loss/train': 1.0678645372390747} 08/30/2021 19:57:07 - INFO - __main__ - Step 37387: {'lr': 0.000432728202975422, 'samples': 7178304, 'steps': 37386, 'loss/train': 0.37636715173721313} 08/30/2021 19:57:07 - INFO - __main__ - Step 37388: {'lr': 0.0004327245812359285, 'samples': 7178496, 'steps': 37387, 'loss/train': 0.088512122631073} 08/30/2021 19:57:09 - INFO - __main__ - Step 37389: {'lr': 0.000432720959414102, 'samples': 7178688, 'steps': 37388, 'loss/train': 1.6997284889221191} 08/30/2021 19:57:09 - INFO - __main__ - Step 37390: {'lr': 0.00043271733750994436, 'samples': 7178880, 'steps': 37389, 'loss/train': 1.2147971391677856} 08/30/2021 19:57:10 - INFO - __main__ - Step 37391: {'lr': 0.00043271371552345704, 'samples': 7179072, 'steps': 37390, 'loss/train': 1.3436174392700195} 08/30/2021 19:57:10 - INFO - __main__ - Step 37392: {'lr': 0.00043271009345464175, 'samples': 7179264, 'steps': 37391, 'loss/train': 0.6908589601516724} 08/30/2021 19:57:10 - INFO - __main__ - Step 37393: {'lr': 0.0004327064713035002, 'samples': 7179456, 'steps': 37392, 'loss/train': 1.4388829469680786} 08/30/2021 19:57:12 - INFO - __main__ - Step 37394: {'lr': 0.00043270284907003377, 'samples': 7179648, 'steps': 37393, 'loss/train': 1.4150233268737793} 08/30/2021 19:57:12 - INFO - __main__ - Step 37395: {'lr': 0.0004326992267542443, 'samples': 7179840, 'steps': 37394, 'loss/train': 1.4888242483139038} 08/30/2021 19:57:13 - INFO - __main__ - Step 37396: {'lr': 0.0004326956043561335, 'samples': 7180032, 'steps': 37395, 'loss/train': 1.0283443927764893} 08/30/2021 19:57:13 - INFO - __main__ - Step 37397: {'lr': 0.0004326919818757028, 'samples': 7180224, 'steps': 37396, 'loss/train': 3.0277960300445557} 08/30/2021 19:57:14 - INFO - __main__ - Step 37398: {'lr': 0.00043268835931295393, 'samples': 7180416, 'steps': 37397, 'loss/train': 0.054287899285554886} 08/30/2021 19:57:14 - INFO - __main__ - Step 37399: {'lr': 0.00043268473666788844, 'samples': 7180608, 'steps': 37398, 'loss/train': 1.6503711938858032} 08/30/2021 19:57:15 - INFO - __main__ - Step 37400: {'lr': 0.0004326811139405081, 'samples': 7180800, 'steps': 37399, 'loss/train': 1.7558388710021973} 08/30/2021 19:57:16 - INFO - __main__ - Step 37401: {'lr': 0.0004326774911308145, 'samples': 7180992, 'steps': 37400, 'loss/train': 1.7582695484161377} 08/30/2021 19:57:16 - INFO - __main__ - Step 37402: {'lr': 0.00043267386823880904, 'samples': 7181184, 'steps': 37401, 'loss/train': 1.6344903707504272} 08/30/2021 19:57:16 - INFO - __main__ - Step 37403: {'lr': 0.00043267024526449374, 'samples': 7181376, 'steps': 37402, 'loss/train': 1.507318377494812} 08/30/2021 19:57:17 - INFO - __main__ - Step 37404: {'lr': 0.00043266662220787003, 'samples': 7181568, 'steps': 37403, 'loss/train': 1.3364880084991455} 08/30/2021 19:57:18 - INFO - __main__ - Step 37405: {'lr': 0.0004326629990689395, 'samples': 7181760, 'steps': 37404, 'loss/train': 1.3650082349777222} 08/30/2021 19:57:19 - INFO - __main__ - Step 37406: {'lr': 0.0004326593758477039, 'samples': 7181952, 'steps': 37405, 'loss/train': 0.8217769265174866} 08/30/2021 19:57:19 - INFO - __main__ - Step 37407: {'lr': 0.0004326557525441648, 'samples': 7182144, 'steps': 37406, 'loss/train': 1.3236083984375} 08/30/2021 19:57:19 - INFO - __main__ - Step 37408: {'lr': 0.00043265212915832374, 'samples': 7182336, 'steps': 37407, 'loss/train': 1.3377635478973389} 08/30/2021 19:57:20 - INFO - __main__ - Step 37409: {'lr': 0.00043264850569018254, 'samples': 7182528, 'steps': 37408, 'loss/train': 1.2040746212005615} 08/30/2021 19:57:21 - INFO - __main__ - Step 37410: {'lr': 0.00043264488213974275, 'samples': 7182720, 'steps': 37409, 'loss/train': 1.322455883026123} 08/30/2021 19:57:22 - INFO - __main__ - Step 37411: {'lr': 0.000432641258507006, 'samples': 7182912, 'steps': 37410, 'loss/train': 1.3514970541000366} 08/30/2021 19:57:22 - INFO - __main__ - Step 37412: {'lr': 0.0004326376347919738, 'samples': 7183104, 'steps': 37411, 'loss/train': 0.9499925374984741} 08/30/2021 19:57:22 - INFO - __main__ - Step 37413: {'lr': 0.00043263401099464805, 'samples': 7183296, 'steps': 37412, 'loss/train': 1.6077375411987305} 08/30/2021 19:57:23 - INFO - __main__ - Step 37414: {'lr': 0.00043263038711503017, 'samples': 7183488, 'steps': 37413, 'loss/train': 1.4592623710632324} 08/30/2021 19:57:24 - INFO - __main__ - Step 37415: {'lr': 0.00043262676315312183, 'samples': 7183680, 'steps': 37414, 'loss/train': 1.508489966392517} 08/30/2021 19:57:25 - INFO - __main__ - Step 37416: {'lr': 0.0004326231391089247, 'samples': 7183872, 'steps': 37415, 'loss/train': 1.2562161684036255} 08/30/2021 19:57:25 - INFO - __main__ - Step 37417: {'lr': 0.00043261951498244045, 'samples': 7184064, 'steps': 37416, 'loss/train': 1.4437053203582764} 08/30/2021 19:57:25 - INFO - __main__ - Step 37418: {'lr': 0.0004326158907736706, 'samples': 7184256, 'steps': 37417, 'loss/train': 1.0420544147491455} 08/30/2021 19:57:26 - INFO - __main__ - Step 37419: {'lr': 0.00043261226648261687, 'samples': 7184448, 'steps': 37418, 'loss/train': 1.6170576810836792} 08/30/2021 19:57:27 - INFO - __main__ - Step 37420: {'lr': 0.0004326086421092809, 'samples': 7184640, 'steps': 37419, 'loss/train': 1.7398796081542969} 08/30/2021 19:57:28 - INFO - __main__ - Step 37421: {'lr': 0.00043260501765366425, 'samples': 7184832, 'steps': 37420, 'loss/train': 1.1298325061798096} 08/30/2021 19:57:28 - INFO - __main__ - Step 37422: {'lr': 0.00043260139311576863, 'samples': 7185024, 'steps': 37421, 'loss/train': 0.9653279185295105} 08/30/2021 19:57:28 - INFO - __main__ - Step 37423: {'lr': 0.0004325977684955956, 'samples': 7185216, 'steps': 37422, 'loss/train': 1.33500075340271} 08/30/2021 19:57:29 - INFO - __main__ - Step 37424: {'lr': 0.0004325941437931469, 'samples': 7185408, 'steps': 37423, 'loss/train': 1.562026023864746} 08/30/2021 19:57:30 - INFO - __main__ - Step 37425: {'lr': 0.0004325905190084241, 'samples': 7185600, 'steps': 37424, 'loss/train': 1.6564122438430786} 08/30/2021 19:57:31 - INFO - __main__ - Step 37426: {'lr': 0.00043258689414142875, 'samples': 7185792, 'steps': 37425, 'loss/train': 1.2570436000823975} 08/30/2021 19:57:31 - INFO - __main__ - Step 37427: {'lr': 0.0004325832691921626, 'samples': 7185984, 'steps': 37426, 'loss/train': 1.313199520111084} 08/30/2021 19:57:31 - INFO - __main__ - Step 37428: {'lr': 0.00043257964416062723, 'samples': 7186176, 'steps': 37427, 'loss/train': 1.1498758792877197} 08/30/2021 19:57:32 - INFO - __main__ - Step 37429: {'lr': 0.0004325760190468243, 'samples': 7186368, 'steps': 37428, 'loss/train': 1.528903603553772} 08/30/2021 19:57:33 - INFO - __main__ - Step 37430: {'lr': 0.0004325723938507555, 'samples': 7186560, 'steps': 37429, 'loss/train': 1.7303169965744019} 08/30/2021 19:57:34 - INFO - __main__ - Step 37431: {'lr': 0.0004325687685724223, 'samples': 7186752, 'steps': 37430, 'loss/train': 1.217275857925415} 08/30/2021 19:57:34 - INFO - __main__ - Step 37432: {'lr': 0.0004325651432118265, 'samples': 7186944, 'steps': 37431, 'loss/train': 1.6117987632751465} 08/30/2021 19:57:34 - INFO - __main__ - Step 37433: {'lr': 0.00043256151776896955, 'samples': 7187136, 'steps': 37432, 'loss/train': 0.9703555703163147} 08/30/2021 19:57:35 - INFO - __main__ - Step 37434: {'lr': 0.0004325578922438533, 'samples': 7187328, 'steps': 37433, 'loss/train': 1.4213981628417969} 08/30/2021 19:57:37 - INFO - __main__ - Step 37435: {'lr': 0.0004325542666364793, 'samples': 7187520, 'steps': 37434, 'loss/train': 1.5709381103515625} 08/30/2021 19:57:37 - INFO - __main__ - Step 37436: {'lr': 0.00043255064094684917, 'samples': 7187712, 'steps': 37435, 'loss/train': 1.619301199913025} 08/30/2021 19:57:38 - INFO - __main__ - Step 37437: {'lr': 0.0004325470151749644, 'samples': 7187904, 'steps': 37436, 'loss/train': 1.691413402557373} 08/30/2021 19:57:38 - INFO - __main__ - Step 37438: {'lr': 0.00043254338932082696, 'samples': 7188096, 'steps': 37437, 'loss/train': 1.849639892578125} 08/30/2021 19:57:38 - INFO - __main__ - Step 37439: {'lr': 0.00043253976338443814, 'samples': 7188288, 'steps': 37438, 'loss/train': 1.6818939447402954} 08/30/2021 19:57:40 - INFO - __main__ - Step 37440: {'lr': 0.00043253613736579975, 'samples': 7188480, 'steps': 37439, 'loss/train': 1.8714663982391357} 08/30/2021 19:57:40 - INFO - __main__ - Step 37441: {'lr': 0.0004325325112649134, 'samples': 7188672, 'steps': 37440, 'loss/train': 0.05223394185304642} 08/30/2021 19:57:41 - INFO - __main__ - Step 37442: {'lr': 0.00043252888508178066, 'samples': 7188864, 'steps': 37441, 'loss/train': 1.535318374633789} 08/30/2021 19:57:41 - INFO - __main__ - Step 37443: {'lr': 0.0004325252588164033, 'samples': 7189056, 'steps': 37442, 'loss/train': 1.324577808380127} 08/30/2021 19:57:41 - INFO - __main__ - Step 37444: {'lr': 0.00043252163246878286, 'samples': 7189248, 'steps': 37443, 'loss/train': 1.3996564149856567} 08/30/2021 19:57:43 - INFO - __main__ - Step 37445: {'lr': 0.000432518006038921, 'samples': 7189440, 'steps': 37444, 'loss/train': 1.14308762550354} 08/30/2021 19:57:43 - INFO - __main__ - Step 37446: {'lr': 0.00043251437952681926, 'samples': 7189632, 'steps': 37445, 'loss/train': 0.6676692366600037} 08/30/2021 19:57:44 - INFO - __main__ - Step 37447: {'lr': 0.0004325107529324795, 'samples': 7189824, 'steps': 37446, 'loss/train': 1.4937154054641724} 08/30/2021 19:57:44 - INFO - __main__ - Step 37448: {'lr': 0.0004325071262559031, 'samples': 7190016, 'steps': 37447, 'loss/train': 1.6540510654449463} 08/30/2021 19:57:44 - INFO - __main__ - Step 37449: {'lr': 0.00043250349949709184, 'samples': 7190208, 'steps': 37448, 'loss/train': 1.3088397979736328} 08/30/2021 19:57:45 - INFO - __main__ - Step 37450: {'lr': 0.0004324998726560473, 'samples': 7190400, 'steps': 37449, 'loss/train': 0.5380183458328247} 08/30/2021 19:57:46 - INFO - __main__ - Step 37451: {'lr': 0.0004324962457327712, 'samples': 7190592, 'steps': 37450, 'loss/train': 1.4496593475341797} 08/30/2021 19:57:47 - INFO - __main__ - Step 37452: {'lr': 0.00043249261872726504, 'samples': 7190784, 'steps': 37451, 'loss/train': 1.0326513051986694} 08/30/2021 19:57:47 - INFO - __main__ - Step 37453: {'lr': 0.0004324889916395305, 'samples': 7190976, 'steps': 37452, 'loss/train': 2.254138946533203} 08/30/2021 19:57:47 - INFO - __main__ - Step 37454: {'lr': 0.0004324853644695693, 'samples': 7191168, 'steps': 37453, 'loss/train': 1.4218182563781738} 08/30/2021 19:57:48 - INFO - __main__ - Step 37455: {'lr': 0.000432481737217383, 'samples': 7191360, 'steps': 37454, 'loss/train': 1.4825137853622437} 08/30/2021 19:57:49 - INFO - __main__ - Step 37456: {'lr': 0.0004324781098829732, 'samples': 7191552, 'steps': 37455, 'loss/train': 0.029197394847869873} 08/30/2021 19:57:50 - INFO - __main__ - Step 37457: {'lr': 0.0004324744824663417, 'samples': 7191744, 'steps': 37456, 'loss/train': 1.437658429145813} 08/30/2021 19:57:50 - INFO - __main__ - Step 37458: {'lr': 0.00043247085496748983, 'samples': 7191936, 'steps': 37457, 'loss/train': 0.9503560662269592} 08/30/2021 19:57:50 - INFO - __main__ - Step 37459: {'lr': 0.0004324672273864195, 'samples': 7192128, 'steps': 37458, 'loss/train': 1.532064437866211} 08/30/2021 19:57:51 - INFO - __main__ - Step 37460: {'lr': 0.00043246359972313233, 'samples': 7192320, 'steps': 37459, 'loss/train': 1.625966191291809} 08/30/2021 19:57:52 - INFO - __main__ - Step 37461: {'lr': 0.0004324599719776298, 'samples': 7192512, 'steps': 37460, 'loss/train': 1.7297823429107666} 08/30/2021 19:57:53 - INFO - __main__ - Step 37462: {'lr': 0.00043245634414991365, 'samples': 7192704, 'steps': 37461, 'loss/train': 1.6629902124404907} 08/30/2021 19:57:53 - INFO - __main__ - Step 37463: {'lr': 0.0004324527162399854, 'samples': 7192896, 'steps': 37462, 'loss/train': 1.5064109563827515} 08/30/2021 19:57:53 - INFO - __main__ - Step 37464: {'lr': 0.0004324490882478469, 'samples': 7193088, 'steps': 37463, 'loss/train': 1.5163710117340088} 08/30/2021 19:57:54 - INFO - __main__ - Step 37465: {'lr': 0.0004324454601734995, 'samples': 7193280, 'steps': 37464, 'loss/train': 0.9994857907295227} 08/30/2021 19:57:55 - INFO - __main__ - Step 37466: {'lr': 0.0004324418320169451, 'samples': 7193472, 'steps': 37465, 'loss/train': 1.6675835847854614} 08/30/2021 19:57:56 - INFO - __main__ - Step 37467: {'lr': 0.00043243820377818524, 'samples': 7193664, 'steps': 37466, 'loss/train': 1.3926085233688354} 08/30/2021 19:57:56 - INFO - __main__ - Step 37468: {'lr': 0.0004324345754572215, 'samples': 7193856, 'steps': 37467, 'loss/train': 1.9959787130355835} 08/30/2021 19:57:56 - INFO - __main__ - Step 37469: {'lr': 0.00043243094705405554, 'samples': 7194048, 'steps': 37468, 'loss/train': 0.8023901581764221} 08/30/2021 19:57:57 - INFO - __main__ - Step 37470: {'lr': 0.0004324273185686891, 'samples': 7194240, 'steps': 37469, 'loss/train': 1.7683916091918945} 08/30/2021 19:57:58 - INFO - __main__ - Step 37471: {'lr': 0.00043242369000112365, 'samples': 7194432, 'steps': 37470, 'loss/train': 1.9535781145095825} 08/30/2021 19:57:59 - INFO - __main__ - Step 37472: {'lr': 0.00043242006135136093, 'samples': 7194624, 'steps': 37471, 'loss/train': 1.5709192752838135} 08/30/2021 19:57:59 - INFO - __main__ - Step 37473: {'lr': 0.00043241643261940246, 'samples': 7194816, 'steps': 37472, 'loss/train': 1.2576907873153687} 08/30/2021 19:58:00 - INFO - __main__ - Step 37474: {'lr': 0.00043241280380525003, 'samples': 7195008, 'steps': 37473, 'loss/train': 1.5616741180419922} 08/30/2021 19:58:00 - INFO - __main__ - Step 37475: {'lr': 0.0004324091749089052, 'samples': 7195200, 'steps': 37474, 'loss/train': 1.4544329643249512} 08/30/2021 19:58:00 - INFO - __main__ - Step 37476: {'lr': 0.0004324055459303696, 'samples': 7195392, 'steps': 37475, 'loss/train': 2.2143774032592773} 08/30/2021 19:58:02 - INFO - __main__ - Step 37477: {'lr': 0.00043240191686964494, 'samples': 7195584, 'steps': 37476, 'loss/train': 1.9346952438354492} 08/30/2021 19:58:02 - INFO - __main__ - Step 37478: {'lr': 0.00043239828772673276, 'samples': 7195776, 'steps': 37477, 'loss/train': 1.6234220266342163} 08/30/2021 19:58:03 - INFO - __main__ - Step 37479: {'lr': 0.0004323946585016347, 'samples': 7195968, 'steps': 37478, 'loss/train': 1.0614049434661865} 08/30/2021 19:58:03 - INFO - __main__ - Step 37480: {'lr': 0.00043239102919435235, 'samples': 7196160, 'steps': 37479, 'loss/train': 1.4087451696395874} 08/30/2021 19:58:03 - INFO - __main__ - Step 37481: {'lr': 0.0004323873998048875, 'samples': 7196352, 'steps': 37480, 'loss/train': 1.5892679691314697} 08/30/2021 19:58:05 - INFO - __main__ - Step 37482: {'lr': 0.00043238377033324175, 'samples': 7196544, 'steps': 37481, 'loss/train': 2.275916337966919} 08/30/2021 19:58:06 - INFO - __main__ - Step 37483: {'lr': 0.00043238014077941656, 'samples': 7196736, 'steps': 37482, 'loss/train': 1.1161500215530396} 08/30/2021 19:58:06 - INFO - __main__ - Step 37484: {'lr': 0.00043237651114341383, 'samples': 7196928, 'steps': 37483, 'loss/train': 1.7871931791305542} 08/30/2021 19:58:07 - INFO - __main__ - Step 37485: {'lr': 0.00043237288142523503, 'samples': 7197120, 'steps': 37484, 'loss/train': 1.4332817792892456} 08/30/2021 19:58:07 - INFO - __main__ - Step 37486: {'lr': 0.00043236925162488173, 'samples': 7197312, 'steps': 37485, 'loss/train': 1.6623674631118774} 08/30/2021 19:58:07 - INFO - __main__ - Step 37487: {'lr': 0.0004323656217423557, 'samples': 7197504, 'steps': 37486, 'loss/train': 1.1692649126052856} 08/30/2021 19:58:09 - INFO - __main__ - Step 37488: {'lr': 0.00043236199177765856, 'samples': 7197696, 'steps': 37487, 'loss/train': 1.9744224548339844} 08/30/2021 19:58:10 - INFO - __main__ - Step 37489: {'lr': 0.0004323583617307919, 'samples': 7197888, 'steps': 37488, 'loss/train': 1.7935391664505005} 08/30/2021 19:58:10 - INFO - __main__ - Step 37490: {'lr': 0.00043235473160175745, 'samples': 7198080, 'steps': 37489, 'loss/train': 1.656412124633789} 08/30/2021 19:58:10 - INFO - __main__ - Step 37491: {'lr': 0.0004323511013905567, 'samples': 7198272, 'steps': 37490, 'loss/train': 1.7821305990219116} 08/30/2021 19:58:11 - INFO - __main__ - Step 37492: {'lr': 0.0004323474710971913, 'samples': 7198464, 'steps': 37491, 'loss/train': 0.2615404725074768} 08/30/2021 19:58:12 - INFO - __main__ - Step 37493: {'lr': 0.0004323438407216631, 'samples': 7198656, 'steps': 37492, 'loss/train': 1.3712270259857178} 08/30/2021 19:58:13 - INFO - __main__ - Step 37494: {'lr': 0.0004323402102639734, 'samples': 7198848, 'steps': 37493, 'loss/train': 1.5318272113800049} 08/30/2021 19:58:13 - INFO - __main__ - Step 37495: {'lr': 0.00043233657972412414, 'samples': 7199040, 'steps': 37494, 'loss/train': 1.8162832260131836} 08/30/2021 19:58:13 - INFO - __main__ - Step 37496: {'lr': 0.00043233294910211684, 'samples': 7199232, 'steps': 37495, 'loss/train': 0.6068657636642456} 08/30/2021 19:58:14 - INFO - __main__ - Step 37497: {'lr': 0.0004323293183979531, 'samples': 7199424, 'steps': 37496, 'loss/train': 1.4310290813446045} 08/30/2021 19:58:15 - INFO - __main__ - Step 37498: {'lr': 0.0004323256876116345, 'samples': 7199616, 'steps': 37497, 'loss/train': 1.5072999000549316} 08/30/2021 19:58:16 - INFO - __main__ - Step 37499: {'lr': 0.0004323220567431628, 'samples': 7199808, 'steps': 37498, 'loss/train': 1.1527888774871826} 08/30/2021 19:58:16 - INFO - __main__ - Step 37500: {'lr': 0.0004323184257925397, 'samples': 7200000, 'steps': 37499, 'loss/train': 1.0558773279190063} 08/30/2021 19:58:16 - INFO - __main__ - Step 37501: {'lr': 0.0004323147947597667, 'samples': 7200192, 'steps': 37500, 'loss/train': 1.4937289953231812} 08/30/2021 19:58:17 - INFO - __main__ - Step 37502: {'lr': 0.00043231116364484534, 'samples': 7200384, 'steps': 37501, 'loss/train': 1.1834146976470947} 08/30/2021 19:58:18 - INFO - __main__ - Step 37503: {'lr': 0.00043230753244777743, 'samples': 7200576, 'steps': 37502, 'loss/train': 1.7812247276306152} 08/30/2021 19:58:19 - INFO - __main__ - Step 37504: {'lr': 0.00043230390116856467, 'samples': 7200768, 'steps': 37503, 'loss/train': 0.9910949468612671} 08/30/2021 19:58:19 - INFO - __main__ - Step 37505: {'lr': 0.00043230026980720847, 'samples': 7200960, 'steps': 37504, 'loss/train': 0.27721384167671204} 08/30/2021 19:58:19 - INFO - __main__ - Step 37506: {'lr': 0.00043229663836371056, 'samples': 7201152, 'steps': 37505, 'loss/train': 1.6516259908676147} 08/30/2021 19:58:20 - INFO - __main__ - Step 37507: {'lr': 0.0004322930068380727, 'samples': 7201344, 'steps': 37506, 'loss/train': 1.2754383087158203} 08/30/2021 19:58:20 - INFO - __main__ - Step 37508: {'lr': 0.00043228937523029636, 'samples': 7201536, 'steps': 37507, 'loss/train': 1.1058402061462402} 08/30/2021 19:58:21 - INFO - __main__ - Step 37509: {'lr': 0.00043228574354038326, 'samples': 7201728, 'steps': 37508, 'loss/train': 1.912397027015686} 08/30/2021 19:58:22 - INFO - __main__ - Step 37510: {'lr': 0.00043228211176833496, 'samples': 7201920, 'steps': 37509, 'loss/train': 1.2819210290908813} 08/30/2021 19:58:22 - INFO - __main__ - Step 37511: {'lr': 0.00043227847991415326, 'samples': 7202112, 'steps': 37510, 'loss/train': 1.7909189462661743} 08/30/2021 19:58:23 - INFO - __main__ - Step 37512: {'lr': 0.00043227484797783965, 'samples': 7202304, 'steps': 37511, 'loss/train': 1.4759891033172607} 08/30/2021 19:58:23 - INFO - __main__ - Step 37513: {'lr': 0.0004322712159593958, 'samples': 7202496, 'steps': 37512, 'loss/train': 1.4428958892822266} 08/30/2021 19:58:25 - INFO - __main__ - Step 37514: {'lr': 0.0004322675838588234, 'samples': 7202688, 'steps': 37513, 'loss/train': 1.2655271291732788} 08/30/2021 19:58:25 - INFO - __main__ - Step 37515: {'lr': 0.0004322639516761239, 'samples': 7202880, 'steps': 37514, 'loss/train': 1.7687451839447021} 08/30/2021 19:58:25 - INFO - __main__ - Step 37516: {'lr': 0.0004322603194112992, 'samples': 7203072, 'steps': 37515, 'loss/train': 1.3810795545578003} 08/30/2021 19:58:26 - INFO - __main__ - Step 37517: {'lr': 0.00043225668706435073, 'samples': 7203264, 'steps': 37516, 'loss/train': 1.9673357009887695} 08/30/2021 19:58:26 - INFO - __main__ - Step 37518: {'lr': 0.0004322530546352803, 'samples': 7203456, 'steps': 37517, 'loss/train': 1.2577698230743408} 08/30/2021 19:58:28 - INFO - __main__ - Step 37519: {'lr': 0.0004322494221240894, 'samples': 7203648, 'steps': 37518, 'loss/train': 1.4642664194107056} 08/30/2021 19:58:28 - INFO - __main__ - Step 37520: {'lr': 0.0004322457895307797, 'samples': 7203840, 'steps': 37519, 'loss/train': 0.9526332020759583} 08/30/2021 19:58:29 - INFO - __main__ - Step 37521: {'lr': 0.00043224215685535287, 'samples': 7204032, 'steps': 37520, 'loss/train': 1.2903285026550293} 08/30/2021 19:58:29 - INFO - __main__ - Step 37522: {'lr': 0.0004322385240978106, 'samples': 7204224, 'steps': 37521, 'loss/train': 1.4051399230957031} 08/30/2021 19:58:29 - INFO - __main__ - Step 37523: {'lr': 0.0004322348912581544, 'samples': 7204416, 'steps': 37522, 'loss/train': 1.049926996231079} 08/30/2021 19:58:31 - INFO - __main__ - Step 37524: {'lr': 0.000432231258336386, 'samples': 7204608, 'steps': 37523, 'loss/train': 1.4273812770843506} 08/30/2021 19:58:31 - INFO - __main__ - Step 37525: {'lr': 0.000432227625332507, 'samples': 7204800, 'steps': 37524, 'loss/train': 0.8716246485710144} 08/30/2021 19:58:32 - INFO - __main__ - Step 37526: {'lr': 0.000432223992246519, 'samples': 7204992, 'steps': 37525, 'loss/train': 1.1482375860214233} 08/30/2021 19:58:32 - INFO - __main__ - Step 37527: {'lr': 0.0004322203590784237, 'samples': 7205184, 'steps': 37526, 'loss/train': 1.5492173433303833} 08/30/2021 19:58:32 - INFO - __main__ - Step 37528: {'lr': 0.0004322167258282228, 'samples': 7205376, 'steps': 37527, 'loss/train': 1.2992923259735107} 08/30/2021 19:58:33 - INFO - __main__ - Step 37529: {'lr': 0.0004322130924959178, 'samples': 7205568, 'steps': 37528, 'loss/train': 1.7902179956436157} 08/30/2021 19:58:34 - INFO - __main__ - Step 37530: {'lr': 0.0004322094590815104, 'samples': 7205760, 'steps': 37529, 'loss/train': 1.3195284605026245} 08/30/2021 19:58:34 - INFO - __main__ - Step 37531: {'lr': 0.00043220582558500223, 'samples': 7205952, 'steps': 37530, 'loss/train': 1.6612164974212646} 08/30/2021 19:58:35 - INFO - __main__ - Step 37532: {'lr': 0.00043220219200639485, 'samples': 7206144, 'steps': 37531, 'loss/train': 1.0602866411209106} 08/30/2021 19:58:35 - INFO - __main__ - Step 37533: {'lr': 0.00043219855834569006, 'samples': 7206336, 'steps': 37532, 'loss/train': 1.4278581142425537} 08/30/2021 19:58:36 - INFO - __main__ - Step 37534: {'lr': 0.00043219492460288937, 'samples': 7206528, 'steps': 37533, 'loss/train': 0.9774312973022461} 08/30/2021 19:58:37 - INFO - __main__ - Step 37535: {'lr': 0.00043219129077799447, 'samples': 7206720, 'steps': 37534, 'loss/train': 1.0480772256851196} 08/30/2021 19:58:37 - INFO - __main__ - Step 37536: {'lr': 0.000432187656871007, 'samples': 7206912, 'steps': 37535, 'loss/train': 1.4655450582504272} 08/30/2021 19:58:38 - INFO - __main__ - Step 37537: {'lr': 0.0004321840228819286, 'samples': 7207104, 'steps': 37536, 'loss/train': 1.4091171026229858} 08/30/2021 19:58:38 - INFO - __main__ - Step 37538: {'lr': 0.0004321803888107608, 'samples': 7207296, 'steps': 37537, 'loss/train': 1.4877434968948364} 08/30/2021 19:58:39 - INFO - __main__ - Step 37539: {'lr': 0.0004321767546575054, 'samples': 7207488, 'steps': 37538, 'loss/train': 1.3915910720825195} 08/30/2021 19:58:40 - INFO - __main__ - Step 37540: {'lr': 0.000432173120422164, 'samples': 7207680, 'steps': 37539, 'loss/train': 1.5611861944198608} 08/30/2021 19:58:40 - INFO - __main__ - Step 37541: {'lr': 0.00043216948610473816, 'samples': 7207872, 'steps': 37540, 'loss/train': 2.035835027694702} 08/30/2021 19:58:41 - INFO - __main__ - Step 37542: {'lr': 0.0004321658517052296, 'samples': 7208064, 'steps': 37541, 'loss/train': 1.3971617221832275} 08/30/2021 19:58:41 - INFO - __main__ - Step 37543: {'lr': 0.00043216221722363983, 'samples': 7208256, 'steps': 37542, 'loss/train': 1.233750343322754} 08/30/2021 19:58:42 - INFO - __main__ - Step 37544: {'lr': 0.00043215858265997065, 'samples': 7208448, 'steps': 37543, 'loss/train': 1.4952385425567627} 08/30/2021 19:58:44 - INFO - __main__ - Step 37545: {'lr': 0.0004321549480142236, 'samples': 7208640, 'steps': 37544, 'loss/train': 0.9079849720001221} 08/30/2021 19:58:44 - INFO - __main__ - Step 37546: {'lr': 0.0004321513132864003, 'samples': 7208832, 'steps': 37545, 'loss/train': 1.5006433725357056} 08/30/2021 19:58:45 - INFO - __main__ - Step 37547: {'lr': 0.0004321476784765025, 'samples': 7209024, 'steps': 37546, 'loss/train': 2.069721221923828} 08/30/2021 19:58:45 - INFO - __main__ - Step 37548: {'lr': 0.00043214404358453174, 'samples': 7209216, 'steps': 37547, 'loss/train': 1.0978617668151855} 08/30/2021 19:58:45 - INFO - __main__ - Step 37549: {'lr': 0.0004321404086104897, 'samples': 7209408, 'steps': 37548, 'loss/train': 1.4166901111602783} 08/30/2021 19:58:46 - INFO - __main__ - Step 37550: {'lr': 0.00043213677355437795, 'samples': 7209600, 'steps': 37549, 'loss/train': 2.1366448402404785} 08/30/2021 19:58:47 - INFO - __main__ - Step 37551: {'lr': 0.0004321331384161983, 'samples': 7209792, 'steps': 37550, 'loss/train': 1.1152297258377075} 08/30/2021 19:58:47 - INFO - __main__ - Step 37552: {'lr': 0.00043212950319595215, 'samples': 7209984, 'steps': 37551, 'loss/train': 1.4170417785644531} 08/30/2021 19:58:48 - INFO - __main__ - Step 37553: {'lr': 0.0004321258678936413, 'samples': 7210176, 'steps': 37552, 'loss/train': 1.6036512851715088} 08/30/2021 19:58:48 - INFO - __main__ - Step 37554: {'lr': 0.00043212223250926727, 'samples': 7210368, 'steps': 37553, 'loss/train': 0.7793318629264832} 08/30/2021 19:58:49 - INFO - __main__ - Step 37555: {'lr': 0.00043211859704283184, 'samples': 7210560, 'steps': 37554, 'loss/train': 0.17542804777622223} 08/30/2021 19:58:50 - INFO - __main__ - Step 37556: {'lr': 0.0004321149614943366, 'samples': 7210752, 'steps': 37555, 'loss/train': 0.9032306671142578} 08/30/2021 19:58:50 - INFO - __main__ - Step 37557: {'lr': 0.0004321113258637832, 'samples': 7210944, 'steps': 37556, 'loss/train': 1.3906383514404297} 08/30/2021 19:58:51 - INFO - __main__ - Step 37558: {'lr': 0.0004321076901511731, 'samples': 7211136, 'steps': 37557, 'loss/train': 1.1014204025268555} 08/30/2021 19:58:51 - INFO - __main__ - Step 37559: {'lr': 0.0004321040543565082, 'samples': 7211328, 'steps': 37558, 'loss/train': 1.4682289361953735} 08/30/2021 19:58:51 - INFO - __main__ - Step 37560: {'lr': 0.00043210041847979003, 'samples': 7211520, 'steps': 37559, 'loss/train': 1.8109159469604492} 08/30/2021 19:58:53 - INFO - __main__ - Step 37561: {'lr': 0.0004320967825210202, 'samples': 7211712, 'steps': 37560, 'loss/train': 1.3364187479019165} 08/30/2021 19:58:53 - INFO - __main__ - Step 37562: {'lr': 0.00043209314648020035, 'samples': 7211904, 'steps': 37561, 'loss/train': 1.6465651988983154} 08/30/2021 19:58:54 - INFO - __main__ - Step 37563: {'lr': 0.0004320895103573321, 'samples': 7212096, 'steps': 37562, 'loss/train': 2.1376163959503174} 08/30/2021 19:58:54 - INFO - __main__ - Step 37564: {'lr': 0.00043208587415241725, 'samples': 7212288, 'steps': 37563, 'loss/train': 1.2642743587493896} 08/30/2021 19:58:54 - INFO - __main__ - Step 37565: {'lr': 0.00043208223786545723, 'samples': 7212480, 'steps': 37564, 'loss/train': 1.5711627006530762} 08/30/2021 19:58:55 - INFO - __main__ - Step 37566: {'lr': 0.0004320786014964538, 'samples': 7212672, 'steps': 37565, 'loss/train': 1.5496430397033691} 08/30/2021 19:58:56 - INFO - __main__ - Step 37567: {'lr': 0.0004320749650454085, 'samples': 7212864, 'steps': 37566, 'loss/train': 1.6033724546432495} 08/30/2021 19:58:57 - INFO - __main__ - Step 37568: {'lr': 0.0004320713285123231, 'samples': 7213056, 'steps': 37567, 'loss/train': 1.73569917678833} 08/30/2021 19:58:57 - INFO - __main__ - Step 37569: {'lr': 0.0004320676918971991, 'samples': 7213248, 'steps': 37568, 'loss/train': 1.4966765642166138} 08/30/2021 19:58:57 - INFO - __main__ - Step 37570: {'lr': 0.00043206405520003824, 'samples': 7213440, 'steps': 37569, 'loss/train': 1.7415043115615845} 08/30/2021 19:58:58 - INFO - __main__ - Step 37571: {'lr': 0.00043206041842084214, 'samples': 7213632, 'steps': 37570, 'loss/train': 1.3438230752944946} 08/30/2021 19:58:59 - INFO - __main__ - Step 37572: {'lr': 0.00043205678155961244, 'samples': 7213824, 'steps': 37571, 'loss/train': 1.7384071350097656} 08/30/2021 19:59:00 - INFO - __main__ - Step 37573: {'lr': 0.0004320531446163507, 'samples': 7214016, 'steps': 37572, 'loss/train': 1.6909834146499634} 08/30/2021 19:59:00 - INFO - __main__ - Step 37574: {'lr': 0.00043204950759105865, 'samples': 7214208, 'steps': 37573, 'loss/train': 1.6572736501693726} 08/30/2021 19:59:00 - INFO - __main__ - Step 37575: {'lr': 0.0004320458704837379, 'samples': 7214400, 'steps': 37574, 'loss/train': 1.727827548980713} 08/30/2021 19:59:01 - INFO - __main__ - Step 37576: {'lr': 0.00043204223329439015, 'samples': 7214592, 'steps': 37575, 'loss/train': 1.2690116167068481} 08/30/2021 19:59:02 - INFO - __main__ - Step 37577: {'lr': 0.00043203859602301695, 'samples': 7214784, 'steps': 37576, 'loss/train': 1.1359823942184448} 08/30/2021 19:59:03 - INFO - __main__ - Step 37578: {'lr': 0.00043203495866961996, 'samples': 7214976, 'steps': 37577, 'loss/train': 1.6740102767944336} 08/30/2021 19:59:03 - INFO - __main__ - Step 37579: {'lr': 0.00043203132123420074, 'samples': 7215168, 'steps': 37578, 'loss/train': 1.6285802125930786} 08/30/2021 19:59:03 - INFO - __main__ - Step 37580: {'lr': 0.00043202768371676113, 'samples': 7215360, 'steps': 37579, 'loss/train': 1.6305042505264282} 08/30/2021 19:59:04 - INFO - __main__ - Step 37581: {'lr': 0.0004320240461173026, 'samples': 7215552, 'steps': 37580, 'loss/train': 1.7473945617675781} 08/30/2021 19:59:05 - INFO - __main__ - Step 37582: {'lr': 0.00043202040843582685, 'samples': 7215744, 'steps': 37581, 'loss/train': 1.7889299392700195} 08/30/2021 19:59:06 - INFO - __main__ - Step 37583: {'lr': 0.00043201677067233554, 'samples': 7215936, 'steps': 37582, 'loss/train': 1.1004011631011963} 08/30/2021 19:59:06 - INFO - __main__ - Step 37584: {'lr': 0.00043201313282683024, 'samples': 7216128, 'steps': 37583, 'loss/train': 1.7682527303695679} 08/30/2021 19:59:06 - INFO - __main__ - Step 37585: {'lr': 0.0004320094948993127, 'samples': 7216320, 'steps': 37584, 'loss/train': 1.712681770324707} 08/30/2021 19:59:07 - INFO - __main__ - Step 37586: {'lr': 0.00043200585688978445, 'samples': 7216512, 'steps': 37585, 'loss/train': 1.4677200317382812} 08/30/2021 19:59:08 - INFO - __main__ - Step 37587: {'lr': 0.00043200221879824706, 'samples': 7216704, 'steps': 37586, 'loss/train': 1.5668485164642334} 08/30/2021 19:59:09 - INFO - __main__ - Step 37588: {'lr': 0.0004319985806247024, 'samples': 7216896, 'steps': 37587, 'loss/train': 1.33074152469635} 08/30/2021 19:59:09 - INFO - __main__ - Step 37589: {'lr': 0.00043199494236915206, 'samples': 7217088, 'steps': 37588, 'loss/train': 1.2112542390823364} 08/30/2021 19:59:09 - INFO - __main__ - Step 37590: {'lr': 0.0004319913040315975, 'samples': 7217280, 'steps': 37589, 'loss/train': 1.16719388961792} 08/30/2021 19:59:10 - INFO - __main__ - Step 37591: {'lr': 0.00043198766561204047, 'samples': 7217472, 'steps': 37590, 'loss/train': 1.869739294052124} 08/30/2021 19:59:10 - INFO - __main__ - Step 37592: {'lr': 0.0004319840271104826, 'samples': 7217664, 'steps': 37591, 'loss/train': 0.04509987309575081} 08/30/2021 19:59:12 - INFO - __main__ - Step 37593: {'lr': 0.0004319803885269256, 'samples': 7217856, 'steps': 37592, 'loss/train': 1.1683651208877563} 08/30/2021 19:59:12 - INFO - __main__ - Step 37594: {'lr': 0.0004319767498613709, 'samples': 7218048, 'steps': 37593, 'loss/train': 1.0008716583251953} 08/30/2021 19:59:13 - INFO - __main__ - Step 37595: {'lr': 0.00043197311111382045, 'samples': 7218240, 'steps': 37594, 'loss/train': 1.6956290006637573} 08/30/2021 19:59:13 - INFO - __main__ - Step 37596: {'lr': 0.00043196947228427564, 'samples': 7218432, 'steps': 37595, 'loss/train': 1.082789421081543} 08/30/2021 19:59:14 - INFO - __main__ - Step 37597: {'lr': 0.0004319658333727382, 'samples': 7218624, 'steps': 37596, 'loss/train': 1.2129055261611938} 08/30/2021 19:59:15 - INFO - __main__ - Step 37598: {'lr': 0.0004319621943792098, 'samples': 7218816, 'steps': 37597, 'loss/train': 0.16011081635951996} 08/30/2021 19:59:15 - INFO - __main__ - Step 37599: {'lr': 0.000431958555303692, 'samples': 7219008, 'steps': 37598, 'loss/train': 2.258772134780884} 08/30/2021 19:59:16 - INFO - __main__ - Step 37600: {'lr': 0.00043195491614618655, 'samples': 7219200, 'steps': 37599, 'loss/train': 1.2972426414489746} 08/30/2021 19:59:16 - INFO - __main__ - Step 37601: {'lr': 0.00043195127690669486, 'samples': 7219392, 'steps': 37600, 'loss/train': 0.4891473948955536} 08/30/2021 19:59:16 - INFO - __main__ - Step 37602: {'lr': 0.00043194763758521896, 'samples': 7219584, 'steps': 37601, 'loss/train': 1.3949825763702393} 08/30/2021 19:59:18 - INFO - __main__ - Step 37603: {'lr': 0.00043194399818176013, 'samples': 7219776, 'steps': 37602, 'loss/train': 1.4770081043243408} 08/30/2021 19:59:19 - INFO - __main__ - Step 37604: {'lr': 0.00043194035869632017, 'samples': 7219968, 'steps': 37603, 'loss/train': 0.296678364276886} 08/30/2021 19:59:19 - INFO - __main__ - Step 37605: {'lr': 0.00043193671912890064, 'samples': 7220160, 'steps': 37604, 'loss/train': 1.6438281536102295} 08/30/2021 19:59:19 - INFO - __main__ - Step 37606: {'lr': 0.0004319330794795033, 'samples': 7220352, 'steps': 37605, 'loss/train': 0.17355850338935852} 08/30/2021 19:59:20 - INFO - __main__ - Step 37607: {'lr': 0.0004319294397481297, 'samples': 7220544, 'steps': 37606, 'loss/train': 0.6790974736213684} 08/30/2021 19:59:21 - INFO - __main__ - Step 37608: {'lr': 0.0004319257999347815, 'samples': 7220736, 'steps': 37607, 'loss/train': 0.651013970375061} 08/30/2021 19:59:22 - INFO - __main__ - Step 37609: {'lr': 0.0004319221600394603, 'samples': 7220928, 'steps': 37608, 'loss/train': 1.365445613861084} 08/30/2021 19:59:22 - INFO - __main__ - Step 37610: {'lr': 0.0004319185200621678, 'samples': 7221120, 'steps': 37609, 'loss/train': 0.05014752224087715} 08/30/2021 19:59:23 - INFO - __main__ - Step 37611: {'lr': 0.0004319148800029057, 'samples': 7221312, 'steps': 37610, 'loss/train': 1.3334579467773438} 08/30/2021 19:59:23 - INFO - __main__ - Step 37612: {'lr': 0.0004319112398616755, 'samples': 7221504, 'steps': 37611, 'loss/train': 1.457069754600525} 08/30/2021 19:59:24 - INFO - __main__ - Step 37613: {'lr': 0.00043190759963847894, 'samples': 7221696, 'steps': 37612, 'loss/train': 1.3781859874725342} 08/30/2021 19:59:25 - INFO - __main__ - Step 37614: {'lr': 0.00043190395933331757, 'samples': 7221888, 'steps': 37613, 'loss/train': 1.5307385921478271} 08/30/2021 19:59:25 - INFO - __main__ - Step 37615: {'lr': 0.00043190031894619306, 'samples': 7222080, 'steps': 37614, 'loss/train': 1.5736502408981323} 08/30/2021 19:59:26 - INFO - __main__ - Step 37616: {'lr': 0.0004318966784771071, 'samples': 7222272, 'steps': 37615, 'loss/train': 1.6792057752609253} 08/30/2021 19:59:26 - INFO - __main__ - Step 37617: {'lr': 0.00043189303792606136, 'samples': 7222464, 'steps': 37616, 'loss/train': 1.4793416261672974} 08/30/2021 19:59:26 - INFO - __main__ - Step 37618: {'lr': 0.0004318893972930574, 'samples': 7222656, 'steps': 37617, 'loss/train': 1.5910242795944214} 08/30/2021 19:59:28 - INFO - __main__ - Step 37619: {'lr': 0.00043188575657809685, 'samples': 7222848, 'steps': 37618, 'loss/train': 1.156327486038208} 08/30/2021 19:59:29 - INFO - __main__ - Step 37620: {'lr': 0.00043188211578118143, 'samples': 7223040, 'steps': 37619, 'loss/train': 1.646649956703186} 08/30/2021 19:59:29 - INFO - __main__ - Step 37621: {'lr': 0.0004318784749023127, 'samples': 7223232, 'steps': 37620, 'loss/train': 1.2390806674957275} 08/30/2021 19:59:29 - INFO - __main__ - Step 37622: {'lr': 0.0004318748339414923, 'samples': 7223424, 'steps': 37621, 'loss/train': 2.3212947845458984} 08/30/2021 19:59:30 - INFO - __main__ - Step 37623: {'lr': 0.000431871192898722, 'samples': 7223616, 'steps': 37622, 'loss/train': 1.117757797241211} 08/30/2021 19:59:31 - INFO - __main__ - Step 37624: {'lr': 0.0004318675517740033, 'samples': 7223808, 'steps': 37623, 'loss/train': 1.309813380241394} 08/30/2021 19:59:32 - INFO - __main__ - Step 37625: {'lr': 0.0004318639105673379, 'samples': 7224000, 'steps': 37624, 'loss/train': 1.8009846210479736} 08/30/2021 19:59:32 - INFO - __main__ - Step 37626: {'lr': 0.00043186026927872736, 'samples': 7224192, 'steps': 37625, 'loss/train': 0.9139742255210876} 08/30/2021 19:59:32 - INFO - __main__ - Step 37627: {'lr': 0.0004318566279081735, 'samples': 7224384, 'steps': 37626, 'loss/train': 1.024888277053833} 08/30/2021 19:59:33 - INFO - __main__ - Step 37628: {'lr': 0.0004318529864556777, 'samples': 7224576, 'steps': 37627, 'loss/train': 0.9063631892204285} 08/30/2021 19:59:34 - INFO - __main__ - Step 37629: {'lr': 0.0004318493449212419, 'samples': 7224768, 'steps': 37628, 'loss/train': 1.1232155561447144} 08/30/2021 19:59:35 - INFO - __main__ - Step 37630: {'lr': 0.00043184570330486756, 'samples': 7224960, 'steps': 37629, 'loss/train': 1.5673871040344238} 08/30/2021 19:59:35 - INFO - __main__ - Step 37631: {'lr': 0.0004318420616065563, 'samples': 7225152, 'steps': 37630, 'loss/train': 1.8563885688781738} 08/30/2021 19:59:35 - INFO - __main__ - Step 37632: {'lr': 0.0004318384198263099, 'samples': 7225344, 'steps': 37631, 'loss/train': 1.389448642730713} 08/30/2021 19:59:36 - INFO - __main__ - Step 37633: {'lr': 0.0004318347779641298, 'samples': 7225536, 'steps': 37632, 'loss/train': 0.9539344906806946} 08/30/2021 19:59:36 - INFO - __main__ - Step 37634: {'lr': 0.00043183113602001777, 'samples': 7225728, 'steps': 37633, 'loss/train': 0.7564384937286377} 08/30/2021 19:59:38 - INFO - __main__ - Step 37635: {'lr': 0.0004318274939939755, 'samples': 7225920, 'steps': 37634, 'loss/train': 1.7145167589187622} 08/30/2021 19:59:38 - INFO - __main__ - Step 37636: {'lr': 0.00043182385188600457, 'samples': 7226112, 'steps': 37635, 'loss/train': 0.7960317730903625} 08/30/2021 19:59:38 - INFO - __main__ - Step 37637: {'lr': 0.0004318202096961066, 'samples': 7226304, 'steps': 37636, 'loss/train': 1.4038528203964233} 08/30/2021 19:59:39 - INFO - __main__ - Step 37638: {'lr': 0.0004318165674242832, 'samples': 7226496, 'steps': 37637, 'loss/train': 1.1525098085403442} 08/30/2021 19:59:39 - INFO - __main__ - Step 37639: {'lr': 0.0004318129250705361, 'samples': 7226688, 'steps': 37638, 'loss/train': 1.8547435998916626} 08/30/2021 19:59:41 - INFO - __main__ - Step 37640: {'lr': 0.0004318092826348669, 'samples': 7226880, 'steps': 37639, 'loss/train': 1.3831381797790527} 08/30/2021 19:59:41 - INFO - __main__ - Step 37641: {'lr': 0.0004318056401172772, 'samples': 7227072, 'steps': 37640, 'loss/train': 1.096973180770874} 08/30/2021 19:59:42 - INFO - __main__ - Step 37642: {'lr': 0.0004318019975177688, 'samples': 7227264, 'steps': 37641, 'loss/train': 1.2614604234695435} 08/30/2021 19:59:42 - INFO - __main__ - Step 37643: {'lr': 0.0004317983548363431, 'samples': 7227456, 'steps': 37642, 'loss/train': 1.274519920349121} 08/30/2021 19:59:42 - INFO - __main__ - Step 37644: {'lr': 0.0004317947120730019, 'samples': 7227648, 'steps': 37643, 'loss/train': 1.0516068935394287} 08/30/2021 19:59:44 - INFO - __main__ - Step 37645: {'lr': 0.0004317910692277469, 'samples': 7227840, 'steps': 37644, 'loss/train': 1.3844913244247437} 08/30/2021 19:59:44 - INFO - __main__ - Step 37646: {'lr': 0.0004317874263005795, 'samples': 7228032, 'steps': 37645, 'loss/train': 0.9391219615936279} 08/30/2021 19:59:45 - INFO - __main__ - Step 37647: {'lr': 0.0004317837832915016, 'samples': 7228224, 'steps': 37646, 'loss/train': 1.628291368484497} 08/30/2021 19:59:45 - INFO - __main__ - Step 37648: {'lr': 0.0004317801402005147, 'samples': 7228416, 'steps': 37647, 'loss/train': 1.0557103157043457} 08/30/2021 19:59:45 - INFO - __main__ - Step 37649: {'lr': 0.00043177649702762043, 'samples': 7228608, 'steps': 37648, 'loss/train': 1.723480224609375} 08/30/2021 19:59:46 - INFO - __main__ - Step 37650: {'lr': 0.0004317728537728206, 'samples': 7228800, 'steps': 37649, 'loss/train': 1.3076304197311401} 08/30/2021 19:59:48 - INFO - __main__ - Step 37651: {'lr': 0.0004317692104361166, 'samples': 7228992, 'steps': 37650, 'loss/train': 1.1958271265029907} 08/30/2021 19:59:48 - INFO - __main__ - Step 37652: {'lr': 0.0004317655670175102, 'samples': 7229184, 'steps': 37651, 'loss/train': 1.4377630949020386} 08/30/2021 19:59:49 - INFO - __main__ - Step 37653: {'lr': 0.0004317619235170032, 'samples': 7229376, 'steps': 37652, 'loss/train': 0.5691970586776733} 08/30/2021 19:59:49 - INFO - __main__ - Step 37654: {'lr': 0.00043175827993459696, 'samples': 7229568, 'steps': 37653, 'loss/train': 0.05685167387127876} 08/30/2021 19:59:49 - INFO - __main__ - Step 37655: {'lr': 0.0004317546362702932, 'samples': 7229760, 'steps': 37654, 'loss/train': 1.6861059665679932} 08/30/2021 19:59:51 - INFO - __main__ - Step 37656: {'lr': 0.0004317509925240937, 'samples': 7229952, 'steps': 37655, 'loss/train': 1.8072127103805542} 08/30/2021 19:59:52 - INFO - __main__ - Step 37657: {'lr': 0.00043174734869599993, 'samples': 7230144, 'steps': 37656, 'loss/train': 1.6896204948425293} 08/30/2021 19:59:52 - INFO - __main__ - Step 37658: {'lr': 0.0004317437047860137, 'samples': 7230336, 'steps': 37657, 'loss/train': 1.2762514352798462} 08/30/2021 19:59:53 - INFO - __main__ - Step 37659: {'lr': 0.0004317400607941364, 'samples': 7230528, 'steps': 37658, 'loss/train': 3.2795166969299316} 08/30/2021 19:59:53 - INFO - __main__ - Step 37660: {'lr': 0.00043173641672037, 'samples': 7230720, 'steps': 37659, 'loss/train': 1.296006202697754} 08/30/2021 19:59:53 - INFO - __main__ - Step 37661: {'lr': 0.00043173277256471586, 'samples': 7230912, 'steps': 37660, 'loss/train': 1.295522689819336} 08/30/2021 19:59:55 - INFO - __main__ - Step 37662: {'lr': 0.0004317291283271758, 'samples': 7231104, 'steps': 37661, 'loss/train': 0.0589936301112175} 08/30/2021 19:59:55 - INFO - __main__ - Step 37663: {'lr': 0.0004317254840077514, 'samples': 7231296, 'steps': 37662, 'loss/train': 1.808688759803772} 08/30/2021 19:59:55 - INFO - __main__ - Step 37664: {'lr': 0.0004317218396064443, 'samples': 7231488, 'steps': 37663, 'loss/train': 1.4146373271942139} 08/30/2021 19:59:56 - INFO - __main__ - Step 37665: {'lr': 0.00043171819512325614, 'samples': 7231680, 'steps': 37664, 'loss/train': 1.7586722373962402} 08/30/2021 19:59:56 - INFO - __main__ - Step 37666: {'lr': 0.00043171455055818854, 'samples': 7231872, 'steps': 37665, 'loss/train': 3.4197332859039307} 08/30/2021 19:59:58 - INFO - __main__ - Step 37667: {'lr': 0.0004317109059112432, 'samples': 7232064, 'steps': 37666, 'loss/train': 0.9519919753074646} 08/30/2021 19:59:58 - INFO - __main__ - Step 37668: {'lr': 0.00043170726118242164, 'samples': 7232256, 'steps': 37667, 'loss/train': 1.6871439218521118} 08/30/2021 19:59:58 - INFO - __main__ - Step 37669: {'lr': 0.0004317036163717257, 'samples': 7232448, 'steps': 37668, 'loss/train': 1.7556183338165283} 08/30/2021 19:59:59 - INFO - __main__ - Step 37670: {'lr': 0.0004316999714791569, 'samples': 7232640, 'steps': 37669, 'loss/train': 1.513393759727478} 08/30/2021 19:59:59 - INFO - __main__ - Step 37671: {'lr': 0.0004316963265047169, 'samples': 7232832, 'steps': 37670, 'loss/train': 3.277825117111206} 08/30/2021 20:00:01 - INFO - __main__ - Step 37672: {'lr': 0.00043169268144840726, 'samples': 7233024, 'steps': 37671, 'loss/train': 0.6956737637519836} 08/30/2021 20:00:01 - INFO - __main__ - Step 37673: {'lr': 0.0004316890363102298, 'samples': 7233216, 'steps': 37672, 'loss/train': 1.0515555143356323} 08/30/2021 20:00:01 - INFO - __main__ - Step 37674: {'lr': 0.000431685391090186, 'samples': 7233408, 'steps': 37673, 'loss/train': 0.7952166199684143} 08/30/2021 20:00:02 - INFO - __main__ - Step 37675: {'lr': 0.00043168174578827755, 'samples': 7233600, 'steps': 37674, 'loss/train': 1.5562384128570557} 08/30/2021 20:00:02 - INFO - __main__ - Step 37676: {'lr': 0.00043167810040450617, 'samples': 7233792, 'steps': 37675, 'loss/train': 1.666055679321289} 08/30/2021 20:00:02 - INFO - __main__ - Step 37677: {'lr': 0.00043167445493887347, 'samples': 7233984, 'steps': 37676, 'loss/train': 2.1080710887908936} 08/30/2021 20:00:04 - INFO - __main__ - Step 37678: {'lr': 0.000431670809391381, 'samples': 7234176, 'steps': 37677, 'loss/train': 1.3906583786010742} 08/30/2021 20:00:04 - INFO - __main__ - Step 37679: {'lr': 0.00043166716376203047, 'samples': 7234368, 'steps': 37678, 'loss/train': 1.8267698287963867} 08/30/2021 20:00:05 - INFO - __main__ - Step 37680: {'lr': 0.0004316635180508235, 'samples': 7234560, 'steps': 37679, 'loss/train': 1.3839911222457886} 08/30/2021 20:00:05 - INFO - __main__ - Step 37681: {'lr': 0.0004316598722577618, 'samples': 7234752, 'steps': 37680, 'loss/train': 1.4439574480056763} 08/30/2021 20:00:05 - INFO - __main__ - Step 37682: {'lr': 0.000431656226382847, 'samples': 7234944, 'steps': 37681, 'loss/train': 2.007516622543335} 08/30/2021 20:00:07 - INFO - __main__ - Step 37683: {'lr': 0.00043165258042608055, 'samples': 7235136, 'steps': 37682, 'loss/train': 1.4240386486053467} 08/30/2021 20:00:08 - INFO - __main__ - Step 37684: {'lr': 0.0004316489343874644, 'samples': 7235328, 'steps': 37683, 'loss/train': 3.268465518951416} 08/30/2021 20:00:08 - INFO - __main__ - Step 37685: {'lr': 0.000431645288267, 'samples': 7235520, 'steps': 37684, 'loss/train': 2.1904873847961426} 08/30/2021 20:00:08 - INFO - __main__ - Step 37686: {'lr': 0.00043164164206468904, 'samples': 7235712, 'steps': 37685, 'loss/train': 1.0899049043655396} 08/30/2021 20:00:09 - INFO - __main__ - Step 37687: {'lr': 0.00043163799578053313, 'samples': 7235904, 'steps': 37686, 'loss/train': 1.3167779445648193} 08/30/2021 20:00:10 - INFO - __main__ - Step 37688: {'lr': 0.00043163434941453395, 'samples': 7236096, 'steps': 37687, 'loss/train': 1.7515298128128052} 08/30/2021 20:00:11 - INFO - __main__ - Step 37689: {'lr': 0.00043163070296669317, 'samples': 7236288, 'steps': 37688, 'loss/train': 1.6320736408233643} 08/30/2021 20:00:11 - INFO - __main__ - Step 37690: {'lr': 0.00043162705643701236, 'samples': 7236480, 'steps': 37689, 'loss/train': 1.1585415601730347} 08/30/2021 20:00:11 - INFO - __main__ - Step 37691: {'lr': 0.00043162340982549327, 'samples': 7236672, 'steps': 37690, 'loss/train': 1.2465486526489258} 08/30/2021 20:00:12 - INFO - __main__ - Step 37692: {'lr': 0.00043161976313213735, 'samples': 7236864, 'steps': 37691, 'loss/train': 0.7220036387443542} 08/30/2021 20:00:13 - INFO - __main__ - Step 37693: {'lr': 0.0004316161163569465, 'samples': 7237056, 'steps': 37692, 'loss/train': 1.8642101287841797} 08/30/2021 20:00:14 - INFO - __main__ - Step 37694: {'lr': 0.0004316124694999222, 'samples': 7237248, 'steps': 37693, 'loss/train': 1.3861749172210693} 08/30/2021 20:00:14 - INFO - __main__ - Step 37695: {'lr': 0.000431608822561066, 'samples': 7237440, 'steps': 37694, 'loss/train': 1.209458589553833} 08/30/2021 20:00:14 - INFO - __main__ - Step 37696: {'lr': 0.0004316051755403798, 'samples': 7237632, 'steps': 37695, 'loss/train': 1.4119212627410889} 08/30/2021 20:00:15 - INFO - __main__ - Step 37697: {'lr': 0.000431601528437865, 'samples': 7237824, 'steps': 37696, 'loss/train': 0.8251736760139465} 08/30/2021 20:00:16 - INFO - __main__ - Step 37698: {'lr': 0.00043159788125352353, 'samples': 7238016, 'steps': 37697, 'loss/train': 0.3981972932815552} 08/30/2021 20:00:17 - INFO - __main__ - Step 37699: {'lr': 0.0004315942339873567, 'samples': 7238208, 'steps': 37698, 'loss/train': 1.198006510734558} 08/30/2021 20:00:17 - INFO - __main__ - Step 37700: {'lr': 0.00043159058663936635, 'samples': 7238400, 'steps': 37699, 'loss/train': 1.1396652460098267} 08/30/2021 20:00:17 - INFO - __main__ - Step 37701: {'lr': 0.0004315869392095542, 'samples': 7238592, 'steps': 37700, 'loss/train': 1.6370837688446045} 08/30/2021 20:00:18 - INFO - __main__ - Step 37702: {'lr': 0.0004315832916979216, 'samples': 7238784, 'steps': 37701, 'loss/train': 1.0754244327545166} 08/30/2021 20:00:19 - INFO - __main__ - Step 37703: {'lr': 0.00043157964410447047, 'samples': 7238976, 'steps': 37702, 'loss/train': 1.0226269960403442} 08/30/2021 20:00:20 - INFO - __main__ - Step 37704: {'lr': 0.0004315759964292023, 'samples': 7239168, 'steps': 37703, 'loss/train': 1.6114041805267334} 08/30/2021 20:00:20 - INFO - __main__ - Step 37705: {'lr': 0.0004315723486721188, 'samples': 7239360, 'steps': 37704, 'loss/train': 1.4619520902633667} 08/30/2021 20:00:20 - INFO - __main__ - Step 37706: {'lr': 0.00043156870083322166, 'samples': 7239552, 'steps': 37705, 'loss/train': 1.3416861295700073} 08/30/2021 20:00:21 - INFO - __main__ - Step 37707: {'lr': 0.00043156505291251234, 'samples': 7239744, 'steps': 37706, 'loss/train': 1.5742803812026978} 08/30/2021 20:00:23 - INFO - __main__ - Step 37708: {'lr': 0.00043156140490999275, 'samples': 7239936, 'steps': 37707, 'loss/train': 1.2783983945846558} 08/30/2021 20:00:23 - INFO - __main__ - Step 37709: {'lr': 0.0004315577568256643, 'samples': 7240128, 'steps': 37708, 'loss/train': 1.647295594215393} 08/30/2021 20:00:23 - INFO - __main__ - Step 37710: {'lr': 0.0004315541086595288, 'samples': 7240320, 'steps': 37709, 'loss/train': 0.6494789123535156} 08/30/2021 20:00:24 - INFO - __main__ - Step 37711: {'lr': 0.00043155046041158776, 'samples': 7240512, 'steps': 37710, 'loss/train': 1.8711117506027222} 08/30/2021 20:00:24 - INFO - __main__ - Step 37712: {'lr': 0.0004315468120818429, 'samples': 7240704, 'steps': 37711, 'loss/train': 1.697899341583252} 08/30/2021 20:00:24 - INFO - __main__ - Step 37713: {'lr': 0.0004315431636702959, 'samples': 7240896, 'steps': 37712, 'loss/train': 1.2972338199615479} 08/30/2021 20:00:26 - INFO - __main__ - Step 37714: {'lr': 0.00043153951517694824, 'samples': 7241088, 'steps': 37713, 'loss/train': 1.4324350357055664} 08/30/2021 20:00:26 - INFO - __main__ - Step 37715: {'lr': 0.0004315358666018018, 'samples': 7241280, 'steps': 37714, 'loss/train': 1.8348197937011719} 08/30/2021 20:00:27 - INFO - __main__ - Step 37716: {'lr': 0.00043153221794485795, 'samples': 7241472, 'steps': 37715, 'loss/train': 2.153360605239868} 08/30/2021 20:00:27 - INFO - __main__ - Step 37717: {'lr': 0.0004315285692061186, 'samples': 7241664, 'steps': 37716, 'loss/train': 1.7202860116958618} 08/30/2021 20:00:28 - INFO - __main__ - Step 37718: {'lr': 0.00043152492038558526, 'samples': 7241856, 'steps': 37717, 'loss/train': 1.7653424739837646} 08/30/2021 20:00:29 - INFO - __main__ - Step 37719: {'lr': 0.00043152127148325957, 'samples': 7242048, 'steps': 37718, 'loss/train': 0.4958634078502655} 08/30/2021 20:00:30 - INFO - __main__ - Step 37720: {'lr': 0.00043151762249914324, 'samples': 7242240, 'steps': 37719, 'loss/train': 1.39985191822052} 08/30/2021 20:00:30 - INFO - __main__ - Step 37721: {'lr': 0.00043151397343323784, 'samples': 7242432, 'steps': 37720, 'loss/train': 2.093074083328247} 08/30/2021 20:00:30 - INFO - __main__ - Step 37722: {'lr': 0.00043151032428554505, 'samples': 7242624, 'steps': 37721, 'loss/train': 1.455536127090454} 08/30/2021 20:00:31 - INFO - __main__ - Step 37723: {'lr': 0.0004315066750560665, 'samples': 7242816, 'steps': 37722, 'loss/train': 1.557468295097351} 08/30/2021 20:00:32 - INFO - __main__ - Step 37724: {'lr': 0.0004315030257448038, 'samples': 7243008, 'steps': 37723, 'loss/train': 1.5150514841079712} 08/30/2021 20:00:33 - INFO - __main__ - Step 37725: {'lr': 0.00043149937635175874, 'samples': 7243200, 'steps': 37724, 'loss/train': 1.359570026397705} 08/30/2021 20:00:33 - INFO - __main__ - Step 37726: {'lr': 0.0004314957268769328, 'samples': 7243392, 'steps': 37725, 'loss/train': 1.3170517683029175} 08/30/2021 20:00:33 - INFO - __main__ - Step 37727: {'lr': 0.00043149207732032767, 'samples': 7243584, 'steps': 37726, 'loss/train': 1.7453690767288208} 08/30/2021 20:00:34 - INFO - __main__ - Step 37728: {'lr': 0.00043148842768194503, 'samples': 7243776, 'steps': 37727, 'loss/train': 1.6623790264129639} 08/30/2021 20:00:35 - INFO - __main__ - Step 37729: {'lr': 0.0004314847779617865, 'samples': 7243968, 'steps': 37728, 'loss/train': 0.448483943939209} 08/30/2021 20:00:36 - INFO - __main__ - Step 37730: {'lr': 0.00043148112815985377, 'samples': 7244160, 'steps': 37729, 'loss/train': 1.305484652519226} 08/30/2021 20:00:36 - INFO - __main__ - Step 37731: {'lr': 0.0004314774782761484, 'samples': 7244352, 'steps': 37730, 'loss/train': 0.3110705316066742} 08/30/2021 20:00:36 - INFO - __main__ - Step 37732: {'lr': 0.00043147382831067204, 'samples': 7244544, 'steps': 37731, 'loss/train': 1.6531836986541748} 08/30/2021 20:00:37 - INFO - __main__ - Step 37733: {'lr': 0.0004314701782634264, 'samples': 7244736, 'steps': 37732, 'loss/train': 1.6658873558044434} 08/30/2021 20:00:38 - INFO - __main__ - Step 37734: {'lr': 0.0004314665281344132, 'samples': 7244928, 'steps': 37733, 'loss/train': 1.7653268575668335} 08/30/2021 20:00:39 - INFO - __main__ - Step 37735: {'lr': 0.0004314628779236339, 'samples': 7245120, 'steps': 37734, 'loss/train': 1.4686462879180908} 08/30/2021 20:00:39 - INFO - __main__ - Step 37736: {'lr': 0.00043145922763109017, 'samples': 7245312, 'steps': 37735, 'loss/train': 1.2351796627044678} 08/30/2021 20:00:40 - INFO - __main__ - Step 37737: {'lr': 0.0004314555772567838, 'samples': 7245504, 'steps': 37736, 'loss/train': 0.5019418001174927} 08/30/2021 20:00:40 - INFO - __main__ - Step 37738: {'lr': 0.0004314519268007163, 'samples': 7245696, 'steps': 37737, 'loss/train': 1.318006157875061} 08/30/2021 20:00:41 - INFO - __main__ - Step 37739: {'lr': 0.00043144827626288943, 'samples': 7245888, 'steps': 37738, 'loss/train': 1.523842453956604} 08/30/2021 20:00:42 - INFO - __main__ - Step 37740: {'lr': 0.00043144462564330464, 'samples': 7246080, 'steps': 37739, 'loss/train': 1.5707664489746094} 08/30/2021 20:00:42 - INFO - __main__ - Step 37741: {'lr': 0.0004314409749419638, 'samples': 7246272, 'steps': 37740, 'loss/train': 1.3167386054992676} 08/30/2021 20:00:43 - INFO - __main__ - Step 37742: {'lr': 0.00043143732415886843, 'samples': 7246464, 'steps': 37741, 'loss/train': 1.1945606470108032} 08/30/2021 20:00:43 - INFO - __main__ - Step 37743: {'lr': 0.0004314336732940202, 'samples': 7246656, 'steps': 37742, 'loss/train': 1.58213210105896} 08/30/2021 20:00:43 - INFO - __main__ - Step 37744: {'lr': 0.0004314300223474208, 'samples': 7246848, 'steps': 37743, 'loss/train': 1.0002487897872925} 08/30/2021 20:00:45 - INFO - __main__ - Step 37745: {'lr': 0.0004314263713190718, 'samples': 7247040, 'steps': 37744, 'loss/train': 1.4598662853240967} 08/30/2021 20:00:45 - INFO - __main__ - Step 37746: {'lr': 0.00043142272020897486, 'samples': 7247232, 'steps': 37745, 'loss/train': 1.5184264183044434} 08/30/2021 20:00:46 - INFO - __main__ - Step 37747: {'lr': 0.0004314190690171317, 'samples': 7247424, 'steps': 37746, 'loss/train': 1.203436255455017} 08/30/2021 20:00:46 - INFO - __main__ - Step 37748: {'lr': 0.0004314154177435438, 'samples': 7247616, 'steps': 37747, 'loss/train': 1.6650391817092896} 08/30/2021 20:00:46 - INFO - __main__ - Step 37749: {'lr': 0.000431411766388213, 'samples': 7247808, 'steps': 37748, 'loss/train': 1.3178043365478516} 08/30/2021 20:00:48 - INFO - __main__ - Step 37750: {'lr': 0.0004314081149511409, 'samples': 7248000, 'steps': 37749, 'loss/train': 1.464530348777771} 08/30/2021 20:00:48 - INFO - __main__ - Step 37751: {'lr': 0.00043140446343232895, 'samples': 7248192, 'steps': 37750, 'loss/train': 1.2500584125518799} 08/30/2021 20:00:49 - INFO - __main__ - Step 37752: {'lr': 0.000431400811831779, 'samples': 7248384, 'steps': 37751, 'loss/train': 1.2512109279632568} 08/30/2021 20:00:49 - INFO - __main__ - Step 37753: {'lr': 0.0004313971601494927, 'samples': 7248576, 'steps': 37752, 'loss/train': 1.548935055732727} 08/30/2021 20:00:49 - INFO - __main__ - Step 37754: {'lr': 0.0004313935083854716, 'samples': 7248768, 'steps': 37753, 'loss/train': 1.5450690984725952} 08/30/2021 20:00:51 - INFO - __main__ - Step 37755: {'lr': 0.0004313898565397174, 'samples': 7248960, 'steps': 37754, 'loss/train': 0.1970173716545105} 08/30/2021 20:00:52 - INFO - __main__ - Step 37756: {'lr': 0.00043138620461223175, 'samples': 7249152, 'steps': 37755, 'loss/train': 1.8051140308380127} 08/30/2021 20:00:52 - INFO - __main__ - Step 37757: {'lr': 0.00043138255260301625, 'samples': 7249344, 'steps': 37756, 'loss/train': 1.5002102851867676} 08/30/2021 20:00:52 - INFO - __main__ - Step 37758: {'lr': 0.0004313789005120725, 'samples': 7249536, 'steps': 37757, 'loss/train': 1.4088208675384521} 08/30/2021 20:00:53 - INFO - __main__ - Step 37759: {'lr': 0.00043137524833940233, 'samples': 7249728, 'steps': 37758, 'loss/train': 1.7270442247390747} 08/30/2021 20:00:55 - INFO - __main__ - Step 37760: {'lr': 0.0004313715960850072, 'samples': 7249920, 'steps': 37759, 'loss/train': 2.1317856311798096} 08/30/2021 20:00:55 - INFO - __main__ - Step 37761: {'lr': 0.00043136794374888887, 'samples': 7250112, 'steps': 37760, 'loss/train': 1.4589859247207642} 08/30/2021 20:00:56 - INFO - __main__ - Step 37762: {'lr': 0.0004313642913310489, 'samples': 7250304, 'steps': 37761, 'loss/train': 1.3985317945480347} 08/30/2021 20:00:56 - INFO - __main__ - Step 37763: {'lr': 0.00043136063883148905, 'samples': 7250496, 'steps': 37762, 'loss/train': 1.383558988571167} 08/30/2021 20:00:56 - INFO - __main__ - Step 37764: {'lr': 0.00043135698625021093, 'samples': 7250688, 'steps': 37763, 'loss/train': 1.6549559831619263} 08/30/2021 20:00:58 - INFO - __main__ - Step 37765: {'lr': 0.000431353333587216, 'samples': 7250880, 'steps': 37764, 'loss/train': 1.2775039672851562} 08/30/2021 20:00:58 - INFO - __main__ - Step 37766: {'lr': 0.00043134968084250616, 'samples': 7251072, 'steps': 37765, 'loss/train': 1.4158092737197876} 08/30/2021 20:00:59 - INFO - __main__ - Step 37767: {'lr': 0.00043134602801608293, 'samples': 7251264, 'steps': 37766, 'loss/train': 1.577428936958313} 08/30/2021 20:00:59 - INFO - __main__ - Step 37768: {'lr': 0.00043134237510794794, 'samples': 7251456, 'steps': 37767, 'loss/train': 2.0538487434387207} 08/30/2021 20:00:59 - INFO - __main__ - Step 37769: {'lr': 0.0004313387221181029, 'samples': 7251648, 'steps': 37768, 'loss/train': 1.7513422966003418} 08/30/2021 20:01:01 - INFO - __main__ - Step 37770: {'lr': 0.0004313350690465495, 'samples': 7251840, 'steps': 37769, 'loss/train': 1.4537458419799805} 08/30/2021 20:01:01 - INFO - __main__ - Step 37771: {'lr': 0.00043133141589328923, 'samples': 7252032, 'steps': 37770, 'loss/train': 0.7458590865135193} 08/30/2021 20:01:02 - INFO - __main__ - Step 37772: {'lr': 0.0004313277626583239, 'samples': 7252224, 'steps': 37771, 'loss/train': 1.2735846042633057} 08/30/2021 20:01:02 - INFO - __main__ - Step 37773: {'lr': 0.000431324109341655, 'samples': 7252416, 'steps': 37772, 'loss/train': 0.7350367307662964} 08/30/2021 20:01:02 - INFO - __main__ - Step 37774: {'lr': 0.0004313204559432842, 'samples': 7252608, 'steps': 37773, 'loss/train': 1.2383387088775635} 08/30/2021 20:01:04 - INFO - __main__ - Step 37775: {'lr': 0.0004313168024632133, 'samples': 7252800, 'steps': 37774, 'loss/train': 0.5584983825683594} 08/30/2021 20:01:04 - INFO - __main__ - Step 37776: {'lr': 0.00043131314890144386, 'samples': 7252992, 'steps': 37775, 'loss/train': 1.2908673286437988} 08/30/2021 20:01:05 - INFO - __main__ - Step 37777: {'lr': 0.0004313094952579775, 'samples': 7253184, 'steps': 37776, 'loss/train': 1.3741708993911743} 08/30/2021 20:01:05 - INFO - __main__ - Step 37778: {'lr': 0.0004313058415328158, 'samples': 7253376, 'steps': 37777, 'loss/train': 0.317062109708786} 08/30/2021 20:01:05 - INFO - __main__ - Step 37779: {'lr': 0.00043130218772596053, 'samples': 7253568, 'steps': 37778, 'loss/train': 1.5649075508117676} 08/30/2021 20:01:07 - INFO - __main__ - Step 37780: {'lr': 0.00043129853383741334, 'samples': 7253760, 'steps': 37779, 'loss/train': 0.6254189610481262} 08/30/2021 20:01:08 - INFO - __main__ - Step 37781: {'lr': 0.00043129487986717574, 'samples': 7253952, 'steps': 37780, 'loss/train': 2.1937649250030518} 08/30/2021 20:01:08 - INFO - __main__ - Step 37782: {'lr': 0.00043129122581524957, 'samples': 7254144, 'steps': 37781, 'loss/train': 1.481724739074707} 08/30/2021 20:01:09 - INFO - __main__ - Step 37783: {'lr': 0.0004312875716816363, 'samples': 7254336, 'steps': 37782, 'loss/train': 1.017342448234558} 08/30/2021 20:01:09 - INFO - __main__ - Step 37784: {'lr': 0.0004312839174663377, 'samples': 7254528, 'steps': 37783, 'loss/train': 1.4106327295303345} 08/30/2021 20:01:09 - INFO - __main__ - Step 37785: {'lr': 0.0004312802631693553, 'samples': 7254720, 'steps': 37784, 'loss/train': 0.6265113353729248} 08/30/2021 20:01:10 - INFO - __main__ - Step 37786: {'lr': 0.00043127660879069084, 'samples': 7254912, 'steps': 37785, 'loss/train': 0.5277948975563049} 08/30/2021 20:01:11 - INFO - __main__ - Step 37787: {'lr': 0.00043127295433034594, 'samples': 7255104, 'steps': 37786, 'loss/train': 1.2199138402938843} 08/30/2021 20:01:12 - INFO - __main__ - Step 37788: {'lr': 0.00043126929978832217, 'samples': 7255296, 'steps': 37787, 'loss/train': 0.05714753642678261} 08/30/2021 20:01:12 - INFO - __main__ - Step 37789: {'lr': 0.00043126564516462134, 'samples': 7255488, 'steps': 37788, 'loss/train': 0.993311882019043} 08/30/2021 20:01:12 - INFO - __main__ - Step 37790: {'lr': 0.000431261990459245, 'samples': 7255680, 'steps': 37789, 'loss/train': 4.479589939117432} 08/30/2021 20:01:13 - INFO - __main__ - Step 37791: {'lr': 0.0004312583356721948, 'samples': 7255872, 'steps': 37790, 'loss/train': 1.38930082321167} 08/30/2021 20:01:14 - INFO - __main__ - Step 37792: {'lr': 0.0004312546808034724, 'samples': 7256064, 'steps': 37791, 'loss/train': 1.716701865196228} 08/30/2021 20:01:15 - INFO - __main__ - Step 37793: {'lr': 0.0004312510258530794, 'samples': 7256256, 'steps': 37792, 'loss/train': 1.6482864618301392} 08/30/2021 20:01:15 - INFO - __main__ - Step 37794: {'lr': 0.0004312473708210175, 'samples': 7256448, 'steps': 37793, 'loss/train': 0.8659932017326355} 08/30/2021 20:01:15 - INFO - __main__ - Step 37795: {'lr': 0.0004312437157072884, 'samples': 7256640, 'steps': 37794, 'loss/train': 1.498479962348938} 08/30/2021 20:01:16 - INFO - __main__ - Step 37796: {'lr': 0.00043124006051189356, 'samples': 7256832, 'steps': 37795, 'loss/train': 1.50589919090271} 08/30/2021 20:01:17 - INFO - __main__ - Step 37797: {'lr': 0.0004312364052348348, 'samples': 7257024, 'steps': 37796, 'loss/train': 1.1998440027236938} 08/30/2021 20:01:18 - INFO - __main__ - Step 37798: {'lr': 0.0004312327498761137, 'samples': 7257216, 'steps': 37797, 'loss/train': 1.165573239326477} 08/30/2021 20:01:18 - INFO - __main__ - Step 37799: {'lr': 0.000431229094435732, 'samples': 7257408, 'steps': 37798, 'loss/train': 1.298769235610962} 08/30/2021 20:01:18 - INFO - __main__ - Step 37800: {'lr': 0.0004312254389136911, 'samples': 7257600, 'steps': 37799, 'loss/train': 1.6393367052078247} 08/30/2021 20:01:19 - INFO - __main__ - Step 37801: {'lr': 0.00043122178330999296, 'samples': 7257792, 'steps': 37800, 'loss/train': 1.7565828561782837} 08/30/2021 20:01:20 - INFO - __main__ - Step 37802: {'lr': 0.0004312181276246391, 'samples': 7257984, 'steps': 37801, 'loss/train': 1.5882149934768677} 08/30/2021 20:01:21 - INFO - __main__ - Step 37803: {'lr': 0.00043121447185763106, 'samples': 7258176, 'steps': 37802, 'loss/train': 1.6342334747314453} 08/30/2021 20:01:21 - INFO - __main__ - Step 37804: {'lr': 0.0004312108160089706, 'samples': 7258368, 'steps': 37803, 'loss/train': 1.569624900817871} 08/30/2021 20:01:21 - INFO - __main__ - Step 37805: {'lr': 0.00043120716007865933, 'samples': 7258560, 'steps': 37804, 'loss/train': 0.5727700591087341} 08/30/2021 20:01:22 - INFO - __main__ - Step 37806: {'lr': 0.0004312035040666989, 'samples': 7258752, 'steps': 37805, 'loss/train': 1.0620774030685425} 08/30/2021 20:01:23 - INFO - __main__ - Step 37807: {'lr': 0.000431199847973091, 'samples': 7258944, 'steps': 37806, 'loss/train': 1.3332579135894775} 08/30/2021 20:01:24 - INFO - __main__ - Step 37808: {'lr': 0.0004311961917978372, 'samples': 7259136, 'steps': 37807, 'loss/train': 1.697693943977356} 08/30/2021 20:01:24 - INFO - __main__ - Step 37809: {'lr': 0.0004311925355409393, 'samples': 7259328, 'steps': 37808, 'loss/train': 1.5940006971359253} 08/30/2021 20:01:24 - INFO - __main__ - Step 37810: {'lr': 0.00043118887920239876, 'samples': 7259520, 'steps': 37809, 'loss/train': 1.4617135524749756} 08/30/2021 20:01:25 - INFO - __main__ - Step 37811: {'lr': 0.00043118522278221726, 'samples': 7259712, 'steps': 37810, 'loss/train': 1.3778870105743408} 08/30/2021 20:01:27 - INFO - __main__ - Step 37812: {'lr': 0.0004311815662803966, 'samples': 7259904, 'steps': 37811, 'loss/train': 2.3793747425079346} 08/30/2021 20:01:27 - INFO - __main__ - Step 37813: {'lr': 0.00043117790969693826, 'samples': 7260096, 'steps': 37812, 'loss/train': 1.7134493589401245} 08/30/2021 20:01:27 - INFO - __main__ - Step 37814: {'lr': 0.00043117425303184395, 'samples': 7260288, 'steps': 37813, 'loss/train': 1.6078107357025146} 08/30/2021 20:01:28 - INFO - __main__ - Step 37815: {'lr': 0.0004311705962851153, 'samples': 7260480, 'steps': 37814, 'loss/train': 1.257380485534668} 08/30/2021 20:01:28 - INFO - __main__ - Step 37816: {'lr': 0.000431166939456754, 'samples': 7260672, 'steps': 37815, 'loss/train': 1.3523883819580078} 08/30/2021 20:01:30 - INFO - __main__ - Step 37817: {'lr': 0.0004311632825467617, 'samples': 7260864, 'steps': 37816, 'loss/train': 0.7073904275894165} 08/30/2021 20:01:30 - INFO - __main__ - Step 37818: {'lr': 0.00043115962555514, 'samples': 7261056, 'steps': 37817, 'loss/train': 1.1123647689819336} 08/30/2021 20:01:31 - INFO - __main__ - Step 37819: {'lr': 0.0004311559684818905, 'samples': 7261248, 'steps': 37818, 'loss/train': 1.449662685394287} 08/30/2021 20:01:31 - INFO - __main__ - Step 37820: {'lr': 0.000431152311327015, 'samples': 7261440, 'steps': 37819, 'loss/train': 0.5699060559272766} 08/30/2021 20:01:31 - INFO - __main__ - Step 37821: {'lr': 0.00043114865409051505, 'samples': 7261632, 'steps': 37820, 'loss/train': 1.3527705669403076} 08/30/2021 20:01:33 - INFO - __main__ - Step 37822: {'lr': 0.0004311449967723923, 'samples': 7261824, 'steps': 37821, 'loss/train': 1.5606176853179932} 08/30/2021 20:01:33 - INFO - __main__ - Step 37823: {'lr': 0.00043114133937264843, 'samples': 7262016, 'steps': 37822, 'loss/train': 1.5322378873825073} 08/30/2021 20:01:34 - INFO - __main__ - Step 37824: {'lr': 0.000431137681891285, 'samples': 7262208, 'steps': 37823, 'loss/train': 0.664175808429718} 08/30/2021 20:01:34 - INFO - __main__ - Step 37825: {'lr': 0.0004311340243283038, 'samples': 7262400, 'steps': 37824, 'loss/train': 0.0782211422920227} 08/30/2021 20:01:34 - INFO - __main__ - Step 37826: {'lr': 0.0004311303666837064, 'samples': 7262592, 'steps': 37825, 'loss/train': 1.404437780380249} 08/30/2021 20:01:35 - INFO - __main__ - Step 37827: {'lr': 0.0004311267089574944, 'samples': 7262784, 'steps': 37826, 'loss/train': 0.18977566063404083} 08/30/2021 20:01:36 - INFO - __main__ - Step 37828: {'lr': 0.00043112305114966957, 'samples': 7262976, 'steps': 37827, 'loss/train': 2.391573190689087} 08/30/2021 20:01:37 - INFO - __main__ - Step 37829: {'lr': 0.0004311193932602334, 'samples': 7263168, 'steps': 37828, 'loss/train': 1.4405546188354492} 08/30/2021 20:01:37 - INFO - __main__ - Step 37830: {'lr': 0.0004311157352891877, 'samples': 7263360, 'steps': 37829, 'loss/train': 1.7260751724243164} 08/30/2021 20:01:37 - INFO - __main__ - Step 37831: {'lr': 0.000431112077236534, 'samples': 7263552, 'steps': 37830, 'loss/train': 1.29401433467865} 08/30/2021 20:01:38 - INFO - __main__ - Step 37832: {'lr': 0.0004311084191022741, 'samples': 7263744, 'steps': 37831, 'loss/train': 1.2429078817367554} 08/30/2021 20:01:39 - INFO - __main__ - Step 37833: {'lr': 0.00043110476088640935, 'samples': 7263936, 'steps': 37832, 'loss/train': 1.2765179872512817} 08/30/2021 20:01:39 - INFO - __main__ - Step 37834: {'lr': 0.00043110110258894177, 'samples': 7264128, 'steps': 37833, 'loss/train': 2.3622725009918213} 08/30/2021 20:01:40 - INFO - __main__ - Step 37835: {'lr': 0.00043109744420987274, 'samples': 7264320, 'steps': 37834, 'loss/train': 1.2294102907180786} 08/30/2021 20:01:40 - INFO - __main__ - Step 37836: {'lr': 0.000431093785749204, 'samples': 7264512, 'steps': 37835, 'loss/train': 1.6432852745056152} 08/30/2021 20:01:40 - INFO - __main__ - Step 37837: {'lr': 0.00043109012720693717, 'samples': 7264704, 'steps': 37836, 'loss/train': 1.603135108947754} 08/30/2021 20:01:42 - INFO - __main__ - Step 37838: {'lr': 0.000431086468583074, 'samples': 7264896, 'steps': 37837, 'loss/train': 1.3908874988555908} 08/30/2021 20:01:43 - INFO - __main__ - Step 37839: {'lr': 0.00043108280987761593, 'samples': 7265088, 'steps': 37838, 'loss/train': 0.3412628173828125} 08/30/2021 20:01:43 - INFO - __main__ - Step 37840: {'lr': 0.0004310791510905649, 'samples': 7265280, 'steps': 37839, 'loss/train': 1.7199853658676147} 08/30/2021 20:01:43 - INFO - __main__ - Step 37841: {'lr': 0.00043107549222192235, 'samples': 7265472, 'steps': 37840, 'loss/train': 1.634230136871338} 08/30/2021 20:01:44 - INFO - __main__ - Step 37842: {'lr': 0.0004310718332716899, 'samples': 7265664, 'steps': 37841, 'loss/train': 1.3085078001022339} 08/30/2021 20:01:45 - INFO - __main__ - Step 37843: {'lr': 0.00043106817423986933, 'samples': 7265856, 'steps': 37842, 'loss/train': 1.3753633499145508} 08/30/2021 20:01:46 - INFO - __main__ - Step 37844: {'lr': 0.00043106451512646226, 'samples': 7266048, 'steps': 37843, 'loss/train': 1.5045685768127441} 08/30/2021 20:01:46 - INFO - __main__ - Step 37845: {'lr': 0.00043106085593147027, 'samples': 7266240, 'steps': 37844, 'loss/train': 1.0204722881317139} 08/30/2021 20:01:46 - INFO - __main__ - Step 37846: {'lr': 0.00043105719665489505, 'samples': 7266432, 'steps': 37845, 'loss/train': 1.5937714576721191} 08/30/2021 20:01:47 - INFO - __main__ - Step 37847: {'lr': 0.0004310535372967383, 'samples': 7266624, 'steps': 37846, 'loss/train': 1.3426986932754517} 08/30/2021 20:01:48 - INFO - __main__ - Step 37848: {'lr': 0.0004310498778570016, 'samples': 7266816, 'steps': 37847, 'loss/train': 1.5222175121307373} 08/30/2021 20:01:49 - INFO - __main__ - Step 37849: {'lr': 0.0004310462183356866, 'samples': 7267008, 'steps': 37848, 'loss/train': 1.5410236120224} 08/30/2021 20:01:49 - INFO - __main__ - Step 37850: {'lr': 0.00043104255873279497, 'samples': 7267200, 'steps': 37849, 'loss/train': 0.9960685968399048} 08/30/2021 20:01:49 - INFO - __main__ - Step 37851: {'lr': 0.00043103889904832837, 'samples': 7267392, 'steps': 37850, 'loss/train': 1.3453502655029297} 08/30/2021 20:01:50 - INFO - __main__ - Step 37852: {'lr': 0.0004310352392822884, 'samples': 7267584, 'steps': 37851, 'loss/train': 1.0611807107925415} 08/30/2021 20:01:51 - INFO - __main__ - Step 37853: {'lr': 0.00043103157943467674, 'samples': 7267776, 'steps': 37852, 'loss/train': 1.4241032600402832} 08/30/2021 20:01:52 - INFO - __main__ - Step 37854: {'lr': 0.00043102791950549513, 'samples': 7267968, 'steps': 37853, 'loss/train': 1.404571533203125} 08/30/2021 20:01:52 - INFO - __main__ - Step 37855: {'lr': 0.00043102425949474504, 'samples': 7268160, 'steps': 37854, 'loss/train': 1.0707902908325195} 08/30/2021 20:01:53 - INFO - __main__ - Step 37856: {'lr': 0.00043102059940242825, 'samples': 7268352, 'steps': 37855, 'loss/train': 1.2622687816619873} 08/30/2021 20:01:53 - INFO - __main__ - Step 37857: {'lr': 0.0004310169392285464, 'samples': 7268544, 'steps': 37856, 'loss/train': 1.3767515420913696} 08/30/2021 20:01:53 - INFO - __main__ - Step 37858: {'lr': 0.0004310132789731011, 'samples': 7268736, 'steps': 37857, 'loss/train': 1.4821090698242188} 08/30/2021 20:01:56 - INFO - __main__ - Step 37859: {'lr': 0.000431009618636094, 'samples': 7268928, 'steps': 37858, 'loss/train': 0.06676900386810303} 08/30/2021 20:01:57 - INFO - __main__ - Step 37860: {'lr': 0.00043100595821752674, 'samples': 7269120, 'steps': 37859, 'loss/train': 1.4708852767944336} 08/30/2021 20:01:57 - INFO - __main__ - Step 37861: {'lr': 0.00043100229771740096, 'samples': 7269312, 'steps': 37860, 'loss/train': 1.5063320398330688} 08/30/2021 20:01:57 - INFO - __main__ - Step 37862: {'lr': 0.0004309986371357184, 'samples': 7269504, 'steps': 37861, 'loss/train': 1.0035943984985352} 08/30/2021 20:01:58 - INFO - __main__ - Step 37863: {'lr': 0.00043099497647248065, 'samples': 7269696, 'steps': 37862, 'loss/train': 1.7991957664489746} 08/30/2021 20:01:58 - INFO - __main__ - Step 37864: {'lr': 0.00043099131572768936, 'samples': 7269888, 'steps': 37863, 'loss/train': 1.7775837182998657} 08/30/2021 20:01:58 - INFO - __main__ - Step 37865: {'lr': 0.00043098765490134607, 'samples': 7270080, 'steps': 37864, 'loss/train': 1.0462443828582764} 08/30/2021 20:01:59 - INFO - __main__ - Step 37866: {'lr': 0.00043098399399345267, 'samples': 7270272, 'steps': 37865, 'loss/train': 2.1398673057556152} 08/30/2021 20:02:00 - INFO - __main__ - Step 37867: {'lr': 0.0004309803330040106, 'samples': 7270464, 'steps': 37866, 'loss/train': 5.814516067504883} 08/30/2021 20:02:01 - INFO - __main__ - Step 37868: {'lr': 0.0004309766719330216, 'samples': 7270656, 'steps': 37867, 'loss/train': 0.6848388910293579} 08/30/2021 20:02:01 - INFO - __main__ - Step 37869: {'lr': 0.00043097301078048736, 'samples': 7270848, 'steps': 37868, 'loss/train': 1.5420037508010864} 08/30/2021 20:02:02 - INFO - __main__ - Step 37870: {'lr': 0.00043096934954640935, 'samples': 7271040, 'steps': 37869, 'loss/train': 1.61904776096344} 08/30/2021 20:02:02 - INFO - __main__ - Step 37871: {'lr': 0.0004309656882307894, 'samples': 7271232, 'steps': 37870, 'loss/train': 0.18017643690109253} 08/30/2021 20:02:02 - INFO - __main__ - Step 37872: {'lr': 0.0004309620268336292, 'samples': 7271424, 'steps': 37871, 'loss/train': 0.8786585330963135} 08/30/2021 20:02:04 - INFO - __main__ - Step 37873: {'lr': 0.0004309583653549302, 'samples': 7271616, 'steps': 37872, 'loss/train': 1.290591835975647} 08/30/2021 20:02:05 - INFO - __main__ - Step 37874: {'lr': 0.0004309547037946941, 'samples': 7271808, 'steps': 37873, 'loss/train': 1.7790499925613403} 08/30/2021 20:02:05 - INFO - __main__ - Step 37875: {'lr': 0.0004309510421529227, 'samples': 7272000, 'steps': 37874, 'loss/train': 1.4028468132019043} 08/30/2021 20:02:05 - INFO - __main__ - Step 37876: {'lr': 0.00043094738042961754, 'samples': 7272192, 'steps': 37875, 'loss/train': 1.6830459833145142} 08/30/2021 20:02:06 - INFO - __main__ - Step 37877: {'lr': 0.0004309437186247803, 'samples': 7272384, 'steps': 37876, 'loss/train': 1.4887789487838745} 08/30/2021 20:02:07 - INFO - __main__ - Step 37878: {'lr': 0.00043094005673841257, 'samples': 7272576, 'steps': 37877, 'loss/train': 0.8011658191680908} 08/30/2021 20:02:08 - INFO - __main__ - Step 37879: {'lr': 0.00043093639477051606, 'samples': 7272768, 'steps': 37878, 'loss/train': 1.5701242685317993} 08/30/2021 20:02:08 - INFO - __main__ - Step 37880: {'lr': 0.0004309327327210923, 'samples': 7272960, 'steps': 37879, 'loss/train': 1.2994638681411743} 08/30/2021 20:02:08 - INFO - __main__ - Step 37881: {'lr': 0.00043092907059014325, 'samples': 7273152, 'steps': 37880, 'loss/train': 1.2492634057998657} 08/30/2021 20:02:09 - INFO - __main__ - Step 37882: {'lr': 0.00043092540837767025, 'samples': 7273344, 'steps': 37881, 'loss/train': 1.1876689195632935} 08/30/2021 20:02:10 - INFO - __main__ - Step 37883: {'lr': 0.000430921746083675, 'samples': 7273536, 'steps': 37882, 'loss/train': 1.6326980590820312} 08/30/2021 20:02:11 - INFO - __main__ - Step 37884: {'lr': 0.00043091808370815935, 'samples': 7273728, 'steps': 37883, 'loss/train': 1.6195087432861328} 08/30/2021 20:02:11 - INFO - __main__ - Step 37885: {'lr': 0.0004309144212511246, 'samples': 7273920, 'steps': 37884, 'loss/train': 1.1608182191848755} 08/30/2021 20:02:11 - INFO - __main__ - Step 37886: {'lr': 0.00043091075871257275, 'samples': 7274112, 'steps': 37885, 'loss/train': 1.5530043840408325} 08/30/2021 20:02:12 - INFO - __main__ - Step 37887: {'lr': 0.0004309070960925052, 'samples': 7274304, 'steps': 37886, 'loss/train': 1.4360982179641724} 08/30/2021 20:02:13 - INFO - __main__ - Step 37888: {'lr': 0.0004309034333909238, 'samples': 7274496, 'steps': 37887, 'loss/train': 2.7442939281463623} 08/30/2021 20:02:14 - INFO - __main__ - Step 37889: {'lr': 0.0004308997706078301, 'samples': 7274688, 'steps': 37888, 'loss/train': 0.9758208394050598} 08/30/2021 20:02:14 - INFO - __main__ - Step 37890: {'lr': 0.00043089610774322575, 'samples': 7274880, 'steps': 37889, 'loss/train': 0.5293806195259094} 08/30/2021 20:02:15 - INFO - __main__ - Step 37891: {'lr': 0.00043089244479711233, 'samples': 7275072, 'steps': 37890, 'loss/train': 1.2836235761642456} 08/30/2021 20:02:15 - INFO - __main__ - Step 37892: {'lr': 0.00043088878176949163, 'samples': 7275264, 'steps': 37891, 'loss/train': 1.7117257118225098} 08/30/2021 20:02:16 - INFO - __main__ - Step 37893: {'lr': 0.0004308851186603652, 'samples': 7275456, 'steps': 37892, 'loss/train': 1.4861423969268799} 08/30/2021 20:02:17 - INFO - __main__ - Step 37894: {'lr': 0.0004308814554697348, 'samples': 7275648, 'steps': 37893, 'loss/train': 1.29928719997406} 08/30/2021 20:02:17 - INFO - __main__ - Step 37895: {'lr': 0.0004308777921976019, 'samples': 7275840, 'steps': 37894, 'loss/train': 0.8017020225524902} 08/30/2021 20:02:18 - INFO - __main__ - Step 37896: {'lr': 0.00043087412884396835, 'samples': 7276032, 'steps': 37895, 'loss/train': 1.224180817604065} 08/30/2021 20:02:18 - INFO - __main__ - Step 37897: {'lr': 0.0004308704654088357, 'samples': 7276224, 'steps': 37896, 'loss/train': 1.6390975713729858} 08/30/2021 20:02:18 - INFO - __main__ - Step 37898: {'lr': 0.00043086680189220554, 'samples': 7276416, 'steps': 37897, 'loss/train': 1.4691028594970703} 08/30/2021 20:02:20 - INFO - __main__ - Step 37899: {'lr': 0.00043086313829407966, 'samples': 7276608, 'steps': 37898, 'loss/train': 1.4377100467681885} 08/30/2021 20:02:20 - INFO - __main__ - Step 37900: {'lr': 0.0004308594746144596, 'samples': 7276800, 'steps': 37899, 'loss/train': 1.1837940216064453} 08/30/2021 20:02:21 - INFO - __main__ - Step 37901: {'lr': 0.0004308558108533471, 'samples': 7276992, 'steps': 37900, 'loss/train': 1.5996122360229492} 08/30/2021 20:02:21 - INFO - __main__ - Step 37902: {'lr': 0.0004308521470107437, 'samples': 7277184, 'steps': 37901, 'loss/train': 1.0837979316711426} 08/30/2021 20:02:21 - INFO - __main__ - Step 37903: {'lr': 0.00043084848308665115, 'samples': 7277376, 'steps': 37902, 'loss/train': 1.2540404796600342} 08/30/2021 20:02:23 - INFO - __main__ - Step 37904: {'lr': 0.00043084481908107103, 'samples': 7277568, 'steps': 37903, 'loss/train': 1.5019642114639282} 08/30/2021 20:02:24 - INFO - __main__ - Step 37905: {'lr': 0.00043084115499400505, 'samples': 7277760, 'steps': 37904, 'loss/train': 1.501989722251892} 08/30/2021 20:02:24 - INFO - __main__ - Step 37906: {'lr': 0.0004308374908254549, 'samples': 7277952, 'steps': 37905, 'loss/train': 1.6943483352661133} 08/30/2021 20:02:24 - INFO - __main__ - Step 37907: {'lr': 0.000430833826575422, 'samples': 7278144, 'steps': 37906, 'loss/train': 1.894102931022644} 08/30/2021 20:02:25 - INFO - __main__ - Step 37908: {'lr': 0.0004308301622439083, 'samples': 7278336, 'steps': 37907, 'loss/train': 0.05945177748799324} 08/30/2021 20:02:25 - INFO - __main__ - Step 37909: {'lr': 0.0004308264978309153, 'samples': 7278528, 'steps': 37908, 'loss/train': 0.5095059275627136} 08/30/2021 20:02:27 - INFO - __main__ - Step 37910: {'lr': 0.0004308228333364447, 'samples': 7278720, 'steps': 37909, 'loss/train': 1.611308217048645} 08/30/2021 20:02:27 - INFO - __main__ - Step 37911: {'lr': 0.000430819168760498, 'samples': 7278912, 'steps': 37910, 'loss/train': 0.7591837048530579} 08/30/2021 20:02:27 - INFO - __main__ - Step 37912: {'lr': 0.0004308155041030771, 'samples': 7279104, 'steps': 37911, 'loss/train': 1.6226508617401123} 08/30/2021 20:02:28 - INFO - __main__ - Step 37913: {'lr': 0.00043081183936418343, 'samples': 7279296, 'steps': 37912, 'loss/train': 0.12308230251073837} 08/30/2021 20:02:28 - INFO - __main__ - Step 37914: {'lr': 0.0004308081745438188, 'samples': 7279488, 'steps': 37913, 'loss/train': 1.0532708168029785} 08/30/2021 20:02:30 - INFO - __main__ - Step 37915: {'lr': 0.00043080450964198483, 'samples': 7279680, 'steps': 37914, 'loss/train': 1.7810993194580078} 08/30/2021 20:02:31 - INFO - __main__ - Step 37916: {'lr': 0.00043080084465868307, 'samples': 7279872, 'steps': 37915, 'loss/train': 1.8623061180114746} 08/30/2021 20:02:31 - INFO - __main__ - Step 37917: {'lr': 0.0004307971795939152, 'samples': 7280064, 'steps': 37916, 'loss/train': 1.3737930059432983} 08/30/2021 20:02:31 - INFO - __main__ - Step 37918: {'lr': 0.000430793514447683, 'samples': 7280256, 'steps': 37917, 'loss/train': 1.1269421577453613} 08/30/2021 20:02:32 - INFO - __main__ - Step 37919: {'lr': 0.000430789849219988, 'samples': 7280448, 'steps': 37918, 'loss/train': 0.9433661103248596} 08/30/2021 20:02:32 - INFO - __main__ - Step 37920: {'lr': 0.0004307861839108319, 'samples': 7280640, 'steps': 37919, 'loss/train': 1.3293336629867554} 08/30/2021 20:02:34 - INFO - __main__ - Step 37921: {'lr': 0.00043078251852021634, 'samples': 7280832, 'steps': 37920, 'loss/train': 1.1722218990325928} 08/30/2021 20:02:34 - INFO - __main__ - Step 37922: {'lr': 0.0004307788530481429, 'samples': 7281024, 'steps': 37921, 'loss/train': 1.3880480527877808} 08/30/2021 20:02:34 - INFO - __main__ - Step 37923: {'lr': 0.00043077518749461336, 'samples': 7281216, 'steps': 37922, 'loss/train': 0.8215358853340149} 08/30/2021 20:02:35 - INFO - __main__ - Step 37924: {'lr': 0.00043077152185962933, 'samples': 7281408, 'steps': 37923, 'loss/train': 2.0082170963287354} 08/30/2021 20:02:35 - INFO - __main__ - Step 37925: {'lr': 0.00043076785614319234, 'samples': 7281600, 'steps': 37924, 'loss/train': 1.9002224206924438} 08/30/2021 20:02:37 - INFO - __main__ - Step 37926: {'lr': 0.0004307641903453042, 'samples': 7281792, 'steps': 37925, 'loss/train': 1.3372080326080322} 08/30/2021 20:02:38 - INFO - __main__ - Step 37927: {'lr': 0.00043076052446596656, 'samples': 7281984, 'steps': 37926, 'loss/train': 0.9769525527954102} 08/30/2021 20:02:38 - INFO - __main__ - Step 37928: {'lr': 0.000430756858505181, 'samples': 7282176, 'steps': 37927, 'loss/train': 2.007188320159912} 08/30/2021 20:02:39 - INFO - __main__ - Step 37929: {'lr': 0.00043075319246294914, 'samples': 7282368, 'steps': 37928, 'loss/train': 2.086503267288208} 08/30/2021 20:02:39 - INFO - __main__ - Step 37930: {'lr': 0.0004307495263392727, 'samples': 7282560, 'steps': 37929, 'loss/train': 1.3345279693603516} 08/30/2021 20:02:40 - INFO - __main__ - Step 37931: {'lr': 0.00043074586013415337, 'samples': 7282752, 'steps': 37930, 'loss/train': 0.8397785425186157} 08/30/2021 20:02:41 - INFO - __main__ - Step 37932: {'lr': 0.0004307421938475926, 'samples': 7282944, 'steps': 37931, 'loss/train': 1.3382477760314941} 08/30/2021 20:02:41 - INFO - __main__ - Step 37933: {'lr': 0.0004307385274795923, 'samples': 7283136, 'steps': 37932, 'loss/train': 1.1909817457199097} 08/30/2021 20:02:42 - INFO - __main__ - Step 37934: {'lr': 0.000430734861030154, 'samples': 7283328, 'steps': 37933, 'loss/train': 1.8692418336868286} 08/30/2021 20:02:42 - INFO - __main__ - Step 37935: {'lr': 0.0004307311944992793, 'samples': 7283520, 'steps': 37934, 'loss/train': 1.2709850072860718} 08/30/2021 20:02:44 - INFO - __main__ - Step 37936: {'lr': 0.00043072752788697003, 'samples': 7283712, 'steps': 37935, 'loss/train': 0.8929647207260132} 08/30/2021 20:02:44 - INFO - __main__ - Step 37937: {'lr': 0.0004307238611932276, 'samples': 7283904, 'steps': 37936, 'loss/train': 1.7575852870941162} 08/30/2021 20:02:44 - INFO - __main__ - Step 37938: {'lr': 0.00043072019441805386, 'samples': 7284096, 'steps': 37937, 'loss/train': 1.7067137956619263} 08/30/2021 20:02:45 - INFO - __main__ - Step 37939: {'lr': 0.00043071652756145035, 'samples': 7284288, 'steps': 37938, 'loss/train': 1.6471831798553467} 08/30/2021 20:02:45 - INFO - __main__ - Step 37940: {'lr': 0.0004307128606234188, 'samples': 7284480, 'steps': 37939, 'loss/train': 1.3572616577148438} 08/30/2021 20:02:45 - INFO - __main__ - Step 37941: {'lr': 0.00043070919360396076, 'samples': 7284672, 'steps': 37940, 'loss/train': 1.5423264503479004} 08/30/2021 20:02:47 - INFO - __main__ - Step 37942: {'lr': 0.00043070552650307804, 'samples': 7284864, 'steps': 37941, 'loss/train': 1.6752439737319946} 08/30/2021 20:02:47 - INFO - __main__ - Step 37943: {'lr': 0.0004307018593207721, 'samples': 7285056, 'steps': 37942, 'loss/train': 1.6285309791564941} 08/30/2021 20:02:48 - INFO - __main__ - Step 37944: {'lr': 0.0004306981920570447, 'samples': 7285248, 'steps': 37943, 'loss/train': 1.3542191982269287} 08/30/2021 20:02:48 - INFO - __main__ - Step 37945: {'lr': 0.00043069452471189765, 'samples': 7285440, 'steps': 37944, 'loss/train': 2.0343024730682373} 08/30/2021 20:02:49 - INFO - __main__ - Step 37946: {'lr': 0.00043069085728533225, 'samples': 7285632, 'steps': 37945, 'loss/train': 0.996588408946991} 08/30/2021 20:02:50 - INFO - __main__ - Step 37947: {'lr': 0.0004306871897773504, 'samples': 7285824, 'steps': 37946, 'loss/train': 1.0571370124816895} 08/30/2021 20:02:51 - INFO - __main__ - Step 37948: {'lr': 0.0004306835221879537, 'samples': 7286016, 'steps': 37947, 'loss/train': 2.371856689453125} 08/30/2021 20:02:51 - INFO - __main__ - Step 37949: {'lr': 0.00043067985451714373, 'samples': 7286208, 'steps': 37948, 'loss/train': 1.525660514831543} 08/30/2021 20:02:51 - INFO - __main__ - Step 37950: {'lr': 0.0004306761867649223, 'samples': 7286400, 'steps': 37949, 'loss/train': 1.173021674156189} 08/30/2021 20:02:52 - INFO - __main__ - Step 37951: {'lr': 0.0004306725189312909, 'samples': 7286592, 'steps': 37950, 'loss/train': 1.0360796451568604} 08/30/2021 20:02:53 - INFO - __main__ - Step 37952: {'lr': 0.00043066885101625133, 'samples': 7286784, 'steps': 37951, 'loss/train': 1.4797992706298828} 08/30/2021 20:02:54 - INFO - __main__ - Step 37953: {'lr': 0.00043066518301980504, 'samples': 7286976, 'steps': 37952, 'loss/train': 1.709488868713379} 08/30/2021 20:02:54 - INFO - __main__ - Step 37954: {'lr': 0.00043066151494195387, 'samples': 7287168, 'steps': 37953, 'loss/train': 1.8373823165893555} 08/30/2021 20:02:55 - INFO - __main__ - Step 37955: {'lr': 0.00043065784678269944, 'samples': 7287360, 'steps': 37954, 'loss/train': 1.8149770498275757} 08/30/2021 20:02:55 - INFO - __main__ - Step 37956: {'lr': 0.00043065417854204333, 'samples': 7287552, 'steps': 37955, 'loss/train': 1.3321179151535034} 08/30/2021 20:02:56 - INFO - __main__ - Step 37957: {'lr': 0.0004306505102199872, 'samples': 7287744, 'steps': 37956, 'loss/train': 1.5129896402359009} 08/30/2021 20:02:57 - INFO - __main__ - Step 37958: {'lr': 0.0004306468418165328, 'samples': 7287936, 'steps': 37957, 'loss/train': 1.294215440750122} 08/30/2021 20:02:57 - INFO - __main__ - Step 37959: {'lr': 0.0004306431733316817, 'samples': 7288128, 'steps': 37958, 'loss/train': 1.1099672317504883} 08/30/2021 20:02:58 - INFO - __main__ - Step 37960: {'lr': 0.00043063950476543563, 'samples': 7288320, 'steps': 37959, 'loss/train': 1.4662171602249146} 08/30/2021 20:02:58 - INFO - __main__ - Step 37961: {'lr': 0.0004306358361177961, 'samples': 7288512, 'steps': 37960, 'loss/train': 1.893613338470459} 08/30/2021 20:02:59 - INFO - __main__ - Step 37962: {'lr': 0.00043063216738876487, 'samples': 7288704, 'steps': 37961, 'loss/train': 0.6625356674194336} 08/30/2021 20:03:00 - INFO - __main__ - Step 37963: {'lr': 0.0004306284985783436, 'samples': 7288896, 'steps': 37962, 'loss/train': 1.7436747550964355} 08/30/2021 20:03:00 - INFO - __main__ - Step 37964: {'lr': 0.00043062482968653394, 'samples': 7289088, 'steps': 37963, 'loss/train': 1.6192299127578735} 08/30/2021 20:03:01 - INFO - __main__ - Step 37965: {'lr': 0.00043062116071333745, 'samples': 7289280, 'steps': 37964, 'loss/train': 1.397481918334961} 08/30/2021 20:03:01 - INFO - __main__ - Step 37966: {'lr': 0.0004306174916587559, 'samples': 7289472, 'steps': 37965, 'loss/train': 2.117974042892456} 08/30/2021 20:03:02 - INFO - __main__ - Step 37967: {'lr': 0.0004306138225227909, 'samples': 7289664, 'steps': 37966, 'loss/train': 1.8756572008132935} 08/30/2021 20:03:03 - INFO - __main__ - Step 37968: {'lr': 0.0004306101533054441, 'samples': 7289856, 'steps': 37967, 'loss/train': 0.8081443905830383} 08/30/2021 20:03:03 - INFO - __main__ - Step 37969: {'lr': 0.0004306064840067171, 'samples': 7290048, 'steps': 37968, 'loss/train': 1.2252280712127686} 08/30/2021 20:03:04 - INFO - __main__ - Step 37970: {'lr': 0.00043060281462661165, 'samples': 7290240, 'steps': 37969, 'loss/train': 1.2962955236434937} 08/30/2021 20:03:04 - INFO - __main__ - Step 37971: {'lr': 0.0004305991451651293, 'samples': 7290432, 'steps': 37970, 'loss/train': 1.7549068927764893} 08/30/2021 20:03:04 - INFO - __main__ - Step 37972: {'lr': 0.00043059547562227185, 'samples': 7290624, 'steps': 37971, 'loss/train': 1.2480435371398926} 08/30/2021 20:03:06 - INFO - __main__ - Step 37973: {'lr': 0.0004305918059980408, 'samples': 7290816, 'steps': 37972, 'loss/train': 0.8773108124732971} 08/30/2021 20:03:07 - INFO - __main__ - Step 37974: {'lr': 0.00043058813629243787, 'samples': 7291008, 'steps': 37973, 'loss/train': 1.6526979207992554} 08/30/2021 20:03:07 - INFO - __main__ - Step 37975: {'lr': 0.0004305844665054648, 'samples': 7291200, 'steps': 37974, 'loss/train': 0.11428213864564896} 08/30/2021 20:03:07 - INFO - __main__ - Step 37976: {'lr': 0.00043058079663712304, 'samples': 7291392, 'steps': 37975, 'loss/train': 0.05056499317288399} 08/30/2021 20:03:08 - INFO - __main__ - Step 37977: {'lr': 0.00043057712668741443, 'samples': 7291584, 'steps': 37976, 'loss/train': 0.5404082536697388} 08/30/2021 20:03:08 - INFO - __main__ - Step 37978: {'lr': 0.0004305734566563405, 'samples': 7291776, 'steps': 37977, 'loss/train': 1.5344116687774658} 08/30/2021 20:03:10 - INFO - __main__ - Step 37979: {'lr': 0.000430569786543903, 'samples': 7291968, 'steps': 37978, 'loss/train': 0.616824209690094} 08/30/2021 20:03:11 - INFO - __main__ - Step 37980: {'lr': 0.00043056611635010355, 'samples': 7292160, 'steps': 37979, 'loss/train': 1.741088628768921} 08/30/2021 20:03:11 - INFO - __main__ - Step 37981: {'lr': 0.00043056244607494375, 'samples': 7292352, 'steps': 37980, 'loss/train': 1.4914863109588623} 08/30/2021 20:03:11 - INFO - __main__ - Step 37982: {'lr': 0.0004305587757184254, 'samples': 7292544, 'steps': 37981, 'loss/train': 0.07795705646276474} 08/30/2021 20:03:12 - INFO - __main__ - Step 37983: {'lr': 0.0004305551052805499, 'samples': 7292736, 'steps': 37982, 'loss/train': 0.9139474034309387} 08/30/2021 20:03:13 - INFO - __main__ - Step 37984: {'lr': 0.0004305514347613191, 'samples': 7292928, 'steps': 37983, 'loss/train': 1.4218533039093018} 08/30/2021 20:03:14 - INFO - __main__ - Step 37985: {'lr': 0.0004305477641607347, 'samples': 7293120, 'steps': 37984, 'loss/train': 1.732502818107605} 08/30/2021 20:03:14 - INFO - __main__ - Step 37986: {'lr': 0.0004305440934787982, 'samples': 7293312, 'steps': 37985, 'loss/train': 1.4697660207748413} 08/30/2021 20:03:14 - INFO - __main__ - Step 37987: {'lr': 0.0004305404227155113, 'samples': 7293504, 'steps': 37986, 'loss/train': 0.8130356669425964} 08/30/2021 20:03:15 - INFO - __main__ - Step 37988: {'lr': 0.0004305367518708757, 'samples': 7293696, 'steps': 37987, 'loss/train': 1.533135175704956} 08/30/2021 20:03:17 - INFO - __main__ - Step 37989: {'lr': 0.000430533080944893, 'samples': 7293888, 'steps': 37988, 'loss/train': 1.0704238414764404} 08/30/2021 20:03:17 - INFO - __main__ - Step 37990: {'lr': 0.00043052940993756493, 'samples': 7294080, 'steps': 37989, 'loss/train': 1.513957142829895} 08/30/2021 20:03:17 - INFO - __main__ - Step 37991: {'lr': 0.00043052573884889305, 'samples': 7294272, 'steps': 37990, 'loss/train': 0.9590299725532532} 08/30/2021 20:03:18 - INFO - __main__ - Step 37992: {'lr': 0.00043052206767887907, 'samples': 7294464, 'steps': 37991, 'loss/train': 1.0240545272827148} 08/30/2021 20:03:18 - INFO - __main__ - Step 37993: {'lr': 0.00043051839642752466, 'samples': 7294656, 'steps': 37992, 'loss/train': 0.6313053965568542} 08/30/2021 20:03:18 - INFO - __main__ - Step 37994: {'lr': 0.00043051472509483135, 'samples': 7294848, 'steps': 37993, 'loss/train': 2.0285911560058594} 08/30/2021 20:03:19 - INFO - __main__ - Step 37995: {'lr': 0.00043051105368080103, 'samples': 7295040, 'steps': 37994, 'loss/train': 3.0165655612945557} 08/30/2021 20:03:20 - INFO - __main__ - Step 37996: {'lr': 0.00043050738218543505, 'samples': 7295232, 'steps': 37995, 'loss/train': 0.8663383722305298} 08/30/2021 20:03:21 - INFO - __main__ - Step 37997: {'lr': 0.00043050371060873537, 'samples': 7295424, 'steps': 37996, 'loss/train': 1.5373209714889526} 08/30/2021 20:03:21 - INFO - __main__ - Step 37998: {'lr': 0.00043050003895070345, 'samples': 7295616, 'steps': 37997, 'loss/train': 1.8453495502471924} 08/30/2021 20:03:22 - INFO - __main__ - Step 37999: {'lr': 0.000430496367211341, 'samples': 7295808, 'steps': 37998, 'loss/train': 1.5784364938735962} 08/30/2021 20:03:22 - INFO - __main__ - Step 38000: {'lr': 0.00043049269539064967, 'samples': 7296000, 'steps': 37999, 'loss/train': 1.7386360168457031} 08/30/2021 20:03:24 - INFO - __main__ - Step 38001: {'lr': 0.0004304890234886311, 'samples': 7296192, 'steps': 38000, 'loss/train': 1.4180324077606201} 08/30/2021 20:03:24 - INFO - __main__ - Step 38002: {'lr': 0.000430485351505287, 'samples': 7296384, 'steps': 38001, 'loss/train': 1.0759921073913574} 08/30/2021 20:03:25 - INFO - __main__ - Step 38003: {'lr': 0.000430481679440619, 'samples': 7296576, 'steps': 38002, 'loss/train': 1.434752106666565} 08/30/2021 20:03:25 - INFO - __main__ - Step 38004: {'lr': 0.0004304780072946287, 'samples': 7296768, 'steps': 38003, 'loss/train': 0.1043323203921318} 08/30/2021 20:03:25 - INFO - __main__ - Step 38005: {'lr': 0.00043047433506731783, 'samples': 7296960, 'steps': 38004, 'loss/train': 1.4746665954589844} 08/30/2021 20:03:27 - INFO - __main__ - Step 38006: {'lr': 0.00043047066275868795, 'samples': 7297152, 'steps': 38005, 'loss/train': 1.7519036531448364} 08/30/2021 20:03:27 - INFO - __main__ - Step 38007: {'lr': 0.0004304669903687408, 'samples': 7297344, 'steps': 38006, 'loss/train': 0.8012483716011047} 08/30/2021 20:03:28 - INFO - __main__ - Step 38008: {'lr': 0.000430463317897478, 'samples': 7297536, 'steps': 38007, 'loss/train': 1.7156062126159668} 08/30/2021 20:03:28 - INFO - __main__ - Step 38009: {'lr': 0.0004304596453449012, 'samples': 7297728, 'steps': 38008, 'loss/train': 2.0242068767547607} 08/30/2021 20:03:28 - INFO - __main__ - Step 38010: {'lr': 0.0004304559727110121, 'samples': 7297920, 'steps': 38009, 'loss/train': 2.1348319053649902} 08/30/2021 20:03:29 - INFO - __main__ - Step 38011: {'lr': 0.0004304522999958124, 'samples': 7298112, 'steps': 38010, 'loss/train': 1.8222863674163818} 08/30/2021 20:03:30 - INFO - __main__ - Step 38012: {'lr': 0.00043044862719930356, 'samples': 7298304, 'steps': 38011, 'loss/train': 1.3840633630752563} 08/30/2021 20:03:31 - INFO - __main__ - Step 38013: {'lr': 0.0004304449543214874, 'samples': 7298496, 'steps': 38012, 'loss/train': 1.9130126237869263} 08/30/2021 20:03:31 - INFO - __main__ - Step 38014: {'lr': 0.0004304412813623655, 'samples': 7298688, 'steps': 38013, 'loss/train': 1.882386326789856} 08/30/2021 20:03:32 - INFO - __main__ - Step 38015: {'lr': 0.0004304376083219396, 'samples': 7298880, 'steps': 38014, 'loss/train': 0.8804007768630981} 08/30/2021 20:03:32 - INFO - __main__ - Step 38016: {'lr': 0.00043043393520021125, 'samples': 7299072, 'steps': 38015, 'loss/train': 0.13883128762245178} 08/30/2021 20:03:33 - INFO - __main__ - Step 38017: {'lr': 0.0004304302619971822, 'samples': 7299264, 'steps': 38016, 'loss/train': 1.70297110080719} 08/30/2021 20:03:34 - INFO - __main__ - Step 38018: {'lr': 0.000430426588712854, 'samples': 7299456, 'steps': 38017, 'loss/train': 1.4282335042953491} 08/30/2021 20:03:34 - INFO - __main__ - Step 38019: {'lr': 0.0004304229153472283, 'samples': 7299648, 'steps': 38018, 'loss/train': 1.3424490690231323} 08/30/2021 20:03:35 - INFO - __main__ - Step 38020: {'lr': 0.0004304192419003069, 'samples': 7299840, 'steps': 38019, 'loss/train': 1.3992161750793457} 08/30/2021 20:03:35 - INFO - __main__ - Step 38021: {'lr': 0.0004304155683720914, 'samples': 7300032, 'steps': 38020, 'loss/train': 1.5418304204940796} 08/30/2021 20:03:37 - INFO - __main__ - Step 38022: {'lr': 0.0004304118947625835, 'samples': 7300224, 'steps': 38021, 'loss/train': 0.09601171314716339} 08/30/2021 20:03:37 - INFO - __main__ - Step 38023: {'lr': 0.00043040822107178465, 'samples': 7300416, 'steps': 38022, 'loss/train': 1.2730473279953003} 08/30/2021 20:03:37 - INFO - __main__ - Step 38024: {'lr': 0.0004304045472996966, 'samples': 7300608, 'steps': 38023, 'loss/train': 1.0747939348220825} 08/30/2021 20:03:38 - INFO - __main__ - Step 38025: {'lr': 0.0004304008734463212, 'samples': 7300800, 'steps': 38024, 'loss/train': 1.6828967332839966} 08/30/2021 20:03:38 - INFO - __main__ - Step 38026: {'lr': 0.00043039719951165986, 'samples': 7300992, 'steps': 38025, 'loss/train': 2.090561866760254} 08/30/2021 20:03:39 - INFO - __main__ - Step 38027: {'lr': 0.0004303935254957143, 'samples': 7301184, 'steps': 38026, 'loss/train': 1.8977477550506592} 08/30/2021 20:03:40 - INFO - __main__ - Step 38028: {'lr': 0.0004303898513984863, 'samples': 7301376, 'steps': 38027, 'loss/train': 1.4088269472122192} 08/30/2021 20:03:40 - INFO - __main__ - Step 38029: {'lr': 0.0004303861772199773, 'samples': 7301568, 'steps': 38028, 'loss/train': 1.0330966711044312} 08/30/2021 20:03:41 - INFO - __main__ - Step 38030: {'lr': 0.00043038250296018916, 'samples': 7301760, 'steps': 38029, 'loss/train': 1.5588605403900146} 08/30/2021 20:03:41 - INFO - __main__ - Step 38031: {'lr': 0.00043037882861912344, 'samples': 7301952, 'steps': 38030, 'loss/train': 0.5695727467536926} 08/30/2021 20:03:43 - INFO - __main__ - Step 38032: {'lr': 0.00043037515419678174, 'samples': 7302144, 'steps': 38031, 'loss/train': 1.294374704360962} 08/30/2021 20:03:44 - INFO - __main__ - Step 38033: {'lr': 0.0004303714796931658, 'samples': 7302336, 'steps': 38032, 'loss/train': 0.7637272477149963} 08/30/2021 20:03:44 - INFO - __main__ - Step 38034: {'lr': 0.0004303678051082773, 'samples': 7302528, 'steps': 38033, 'loss/train': 1.7364870309829712} 08/30/2021 20:03:44 - INFO - __main__ - Step 38035: {'lr': 0.00043036413044211786, 'samples': 7302720, 'steps': 38034, 'loss/train': 1.1784203052520752} 08/30/2021 20:03:45 - INFO - __main__ - Step 38036: {'lr': 0.0004303604556946891, 'samples': 7302912, 'steps': 38035, 'loss/train': 1.5858491659164429} 08/30/2021 20:03:46 - INFO - __main__ - Step 38037: {'lr': 0.00043035678086599265, 'samples': 7303104, 'steps': 38036, 'loss/train': 0.9570990800857544} 08/30/2021 20:03:46 - INFO - __main__ - Step 38038: {'lr': 0.00043035310595603026, 'samples': 7303296, 'steps': 38037, 'loss/train': 0.3596562147140503} 08/30/2021 20:03:47 - INFO - __main__ - Step 38039: {'lr': 0.00043034943096480357, 'samples': 7303488, 'steps': 38038, 'loss/train': 1.8890827894210815} 08/30/2021 20:03:47 - INFO - __main__ - Step 38040: {'lr': 0.0004303457558923142, 'samples': 7303680, 'steps': 38039, 'loss/train': 1.600340485572815} 08/30/2021 20:03:47 - INFO - __main__ - Step 38041: {'lr': 0.00043034208073856374, 'samples': 7303872, 'steps': 38040, 'loss/train': 0.49670132994651794} 08/30/2021 20:03:48 - INFO - __main__ - Step 38042: {'lr': 0.000430338405503554, 'samples': 7304064, 'steps': 38041, 'loss/train': 1.7882537841796875} 08/30/2021 20:03:49 - INFO - __main__ - Step 38043: {'lr': 0.00043033473018728655, 'samples': 7304256, 'steps': 38042, 'loss/train': 1.536326289176941} 08/30/2021 20:03:50 - INFO - __main__ - Step 38044: {'lr': 0.00043033105478976306, 'samples': 7304448, 'steps': 38043, 'loss/train': 1.5883727073669434} 08/30/2021 20:03:50 - INFO - __main__ - Step 38045: {'lr': 0.00043032737931098517, 'samples': 7304640, 'steps': 38044, 'loss/train': 1.8947027921676636} 08/30/2021 20:03:51 - INFO - __main__ - Step 38046: {'lr': 0.0004303237037509545, 'samples': 7304832, 'steps': 38045, 'loss/train': 0.8449161052703857} 08/30/2021 20:03:51 - INFO - __main__ - Step 38047: {'lr': 0.0004303200281096727, 'samples': 7305024, 'steps': 38046, 'loss/train': 1.590850591659546} 08/30/2021 20:03:52 - INFO - __main__ - Step 38048: {'lr': 0.00043031635238714163, 'samples': 7305216, 'steps': 38047, 'loss/train': 1.472548007965088} 08/30/2021 20:03:53 - INFO - __main__ - Step 38049: {'lr': 0.00043031267658336276, 'samples': 7305408, 'steps': 38048, 'loss/train': 1.02083158493042} 08/30/2021 20:03:53 - INFO - __main__ - Step 38050: {'lr': 0.00043030900069833774, 'samples': 7305600, 'steps': 38049, 'loss/train': 1.3275349140167236} 08/30/2021 20:03:54 - INFO - __main__ - Step 38051: {'lr': 0.0004303053247320683, 'samples': 7305792, 'steps': 38050, 'loss/train': 1.6457797288894653} 08/30/2021 20:03:54 - INFO - __main__ - Step 38052: {'lr': 0.000430301648684556, 'samples': 7305984, 'steps': 38051, 'loss/train': 1.064283013343811} 08/30/2021 20:03:55 - INFO - __main__ - Step 38053: {'lr': 0.0004302979725558026, 'samples': 7306176, 'steps': 38052, 'loss/train': 1.4403722286224365} 08/30/2021 20:03:56 - INFO - __main__ - Step 38054: {'lr': 0.0004302942963458097, 'samples': 7306368, 'steps': 38053, 'loss/train': 1.52396559715271} 08/30/2021 20:03:56 - INFO - __main__ - Step 38055: {'lr': 0.00043029062005457897, 'samples': 7306560, 'steps': 38054, 'loss/train': 1.647038221359253} 08/30/2021 20:03:57 - INFO - __main__ - Step 38056: {'lr': 0.00043028694368211216, 'samples': 7306752, 'steps': 38055, 'loss/train': 1.6798739433288574} 08/30/2021 20:03:57 - INFO - __main__ - Step 38057: {'lr': 0.00043028326722841073, 'samples': 7306944, 'steps': 38056, 'loss/train': 1.427933692932129} 08/30/2021 20:03:59 - INFO - __main__ - Step 38058: {'lr': 0.00043027959069347644, 'samples': 7307136, 'steps': 38057, 'loss/train': 1.5558427572250366} 08/30/2021 20:03:59 - INFO - __main__ - Step 38059: {'lr': 0.00043027591407731106, 'samples': 7307328, 'steps': 38058, 'loss/train': 0.9162428379058838} 08/30/2021 20:03:59 - INFO - __main__ - Step 38060: {'lr': 0.000430272237379916, 'samples': 7307520, 'steps': 38059, 'loss/train': 1.9274269342422485} 08/30/2021 20:04:00 - INFO - __main__ - Step 38061: {'lr': 0.00043026856060129307, 'samples': 7307712, 'steps': 38060, 'loss/train': 1.641619086265564} 08/30/2021 20:04:00 - INFO - __main__ - Step 38062: {'lr': 0.00043026488374144404, 'samples': 7307904, 'steps': 38061, 'loss/train': 1.0995973348617554} 08/30/2021 20:04:01 - INFO - __main__ - Step 38063: {'lr': 0.00043026120680037026, 'samples': 7308096, 'steps': 38062, 'loss/train': 1.8768608570098877} 08/30/2021 20:04:02 - INFO - __main__ - Step 38064: {'lr': 0.00043025752977807365, 'samples': 7308288, 'steps': 38063, 'loss/train': 1.5482667684555054} 08/30/2021 20:04:02 - INFO - __main__ - Step 38065: {'lr': 0.00043025385267455576, 'samples': 7308480, 'steps': 38064, 'loss/train': 1.600582242012024} 08/30/2021 20:04:03 - INFO - __main__ - Step 38066: {'lr': 0.0004302501754898183, 'samples': 7308672, 'steps': 38065, 'loss/train': 1.2704813480377197} 08/30/2021 20:04:03 - INFO - __main__ - Step 38067: {'lr': 0.00043024649822386284, 'samples': 7308864, 'steps': 38066, 'loss/train': 1.2843825817108154} 08/30/2021 20:04:04 - INFO - __main__ - Step 38068: {'lr': 0.00043024282087669106, 'samples': 7309056, 'steps': 38067, 'loss/train': 1.643200159072876} 08/30/2021 20:04:05 - INFO - __main__ - Step 38069: {'lr': 0.0004302391434483048, 'samples': 7309248, 'steps': 38068, 'loss/train': 1.4084856510162354} 08/30/2021 20:04:05 - INFO - __main__ - Step 38070: {'lr': 0.00043023546593870543, 'samples': 7309440, 'steps': 38069, 'loss/train': 1.260197639465332} 08/30/2021 20:04:05 - INFO - __main__ - Step 38071: {'lr': 0.00043023178834789477, 'samples': 7309632, 'steps': 38070, 'loss/train': 1.0648444890975952} 08/30/2021 20:04:06 - INFO - __main__ - Step 38072: {'lr': 0.0004302281106758745, 'samples': 7309824, 'steps': 38071, 'loss/train': 1.3773057460784912} 08/30/2021 20:04:07 - INFO - __main__ - Step 38073: {'lr': 0.00043022443292264613, 'samples': 7310016, 'steps': 38072, 'loss/train': 2.071263313293457} 08/30/2021 20:04:08 - INFO - __main__ - Step 38074: {'lr': 0.00043022075508821145, 'samples': 7310208, 'steps': 38073, 'loss/train': 1.4826546907424927} 08/30/2021 20:04:08 - INFO - __main__ - Step 38075: {'lr': 0.0004302170771725721, 'samples': 7310400, 'steps': 38074, 'loss/train': 1.163777470588684} 08/30/2021 20:04:09 - INFO - __main__ - Step 38076: {'lr': 0.0004302133991757297, 'samples': 7310592, 'steps': 38075, 'loss/train': 1.8173130750656128} 08/30/2021 20:04:09 - INFO - __main__ - Step 38077: {'lr': 0.000430209721097686, 'samples': 7310784, 'steps': 38076, 'loss/train': 1.3335477113723755} 08/30/2021 20:04:11 - INFO - __main__ - Step 38078: {'lr': 0.00043020604293844244, 'samples': 7310976, 'steps': 38077, 'loss/train': 1.1913659572601318} 08/30/2021 20:04:11 - INFO - __main__ - Step 38079: {'lr': 0.0004302023646980009, 'samples': 7311168, 'steps': 38078, 'loss/train': 1.4555636644363403} 08/30/2021 20:04:11 - INFO - __main__ - Step 38080: {'lr': 0.00043019868637636294, 'samples': 7311360, 'steps': 38079, 'loss/train': 1.7773770093917847} 08/30/2021 20:04:12 - INFO - __main__ - Step 38081: {'lr': 0.0004301950079735302, 'samples': 7311552, 'steps': 38080, 'loss/train': 1.149129033088684} 08/30/2021 20:04:12 - INFO - __main__ - Step 38082: {'lr': 0.00043019132948950443, 'samples': 7311744, 'steps': 38081, 'loss/train': 3.0543625354766846} 08/30/2021 20:04:12 - INFO - __main__ - Step 38083: {'lr': 0.0004301876509242872, 'samples': 7311936, 'steps': 38082, 'loss/train': 1.4620031118392944} 08/30/2021 20:04:13 - INFO - __main__ - Step 38084: {'lr': 0.0004301839722778802, 'samples': 7312128, 'steps': 38083, 'loss/train': 1.4417636394500732} 08/30/2021 20:04:14 - INFO - __main__ - Step 38085: {'lr': 0.0004301802935502851, 'samples': 7312320, 'steps': 38084, 'loss/train': 1.1092498302459717} 08/30/2021 20:04:15 - INFO - __main__ - Step 38086: {'lr': 0.00043017661474150347, 'samples': 7312512, 'steps': 38085, 'loss/train': 1.0917634963989258} 08/30/2021 20:04:15 - INFO - __main__ - Step 38087: {'lr': 0.0004301729358515371, 'samples': 7312704, 'steps': 38086, 'loss/train': 1.238690972328186} 08/30/2021 20:04:15 - INFO - __main__ - Step 38088: {'lr': 0.00043016925688038756, 'samples': 7312896, 'steps': 38087, 'loss/train': 1.6434701681137085} 08/30/2021 20:04:16 - INFO - __main__ - Step 38089: {'lr': 0.00043016557782805655, 'samples': 7313088, 'steps': 38088, 'loss/train': 1.3235447406768799} 08/30/2021 20:04:18 - INFO - __main__ - Step 38090: {'lr': 0.0004301618986945457, 'samples': 7313280, 'steps': 38089, 'loss/train': 0.9472088813781738} 08/30/2021 20:04:18 - INFO - __main__ - Step 38091: {'lr': 0.0004301582194798567, 'samples': 7313472, 'steps': 38090, 'loss/train': 1.320418357849121} 08/30/2021 20:04:19 - INFO - __main__ - Step 38092: {'lr': 0.00043015454018399115, 'samples': 7313664, 'steps': 38091, 'loss/train': 1.4500608444213867} 08/30/2021 20:04:19 - INFO - __main__ - Step 38093: {'lr': 0.00043015086080695075, 'samples': 7313856, 'steps': 38092, 'loss/train': 2.2782180309295654} 08/30/2021 20:04:19 - INFO - __main__ - Step 38094: {'lr': 0.0004301471813487372, 'samples': 7314048, 'steps': 38093, 'loss/train': 1.544771671295166} 08/30/2021 20:04:21 - INFO - __main__ - Step 38095: {'lr': 0.00043014350180935207, 'samples': 7314240, 'steps': 38094, 'loss/train': 1.32065749168396} 08/30/2021 20:04:21 - INFO - __main__ - Step 38096: {'lr': 0.0004301398221887971, 'samples': 7314432, 'steps': 38095, 'loss/train': 1.8495428562164307} 08/30/2021 20:04:22 - INFO - __main__ - Step 38097: {'lr': 0.0004301361424870739, 'samples': 7314624, 'steps': 38096, 'loss/train': 0.18316933512687683} 08/30/2021 20:04:22 - INFO - __main__ - Step 38098: {'lr': 0.00043013246270418406, 'samples': 7314816, 'steps': 38097, 'loss/train': 2.0615177154541016} 08/30/2021 20:04:22 - INFO - __main__ - Step 38099: {'lr': 0.00043012878284012936, 'samples': 7315008, 'steps': 38098, 'loss/train': 1.0804531574249268} 08/30/2021 20:04:23 - INFO - __main__ - Step 38100: {'lr': 0.0004301251028949114, 'samples': 7315200, 'steps': 38099, 'loss/train': 1.241612195968628} 08/30/2021 20:04:24 - INFO - __main__ - Step 38101: {'lr': 0.00043012142286853185, 'samples': 7315392, 'steps': 38100, 'loss/train': 1.2666245698928833} 08/30/2021 20:04:25 - INFO - __main__ - Step 38102: {'lr': 0.00043011774276099235, 'samples': 7315584, 'steps': 38101, 'loss/train': 1.3013263940811157} 08/30/2021 20:04:25 - INFO - __main__ - Step 38103: {'lr': 0.0004301140625722946, 'samples': 7315776, 'steps': 38102, 'loss/train': 1.5301237106323242} 08/30/2021 20:04:26 - INFO - __main__ - Step 38104: {'lr': 0.0004301103823024403, 'samples': 7315968, 'steps': 38103, 'loss/train': 1.8450559377670288} 08/30/2021 20:04:26 - INFO - __main__ - Step 38105: {'lr': 0.0004301067019514309, 'samples': 7316160, 'steps': 38104, 'loss/train': 1.2126245498657227} 08/30/2021 20:04:27 - INFO - __main__ - Step 38106: {'lr': 0.0004301030215192683, 'samples': 7316352, 'steps': 38105, 'loss/train': 1.06794011592865} 08/30/2021 20:04:28 - INFO - __main__ - Step 38107: {'lr': 0.00043009934100595403, 'samples': 7316544, 'steps': 38106, 'loss/train': 1.2656378746032715} 08/30/2021 20:04:28 - INFO - __main__ - Step 38108: {'lr': 0.00043009566041148973, 'samples': 7316736, 'steps': 38107, 'loss/train': 1.358382225036621} 08/30/2021 20:04:28 - INFO - __main__ - Step 38109: {'lr': 0.0004300919797358772, 'samples': 7316928, 'steps': 38108, 'loss/train': 1.4306318759918213} 08/30/2021 20:04:29 - INFO - __main__ - Step 38110: {'lr': 0.00043008829897911796, 'samples': 7317120, 'steps': 38109, 'loss/train': 1.4010542631149292} 08/30/2021 20:04:30 - INFO - __main__ - Step 38111: {'lr': 0.0004300846181412137, 'samples': 7317312, 'steps': 38110, 'loss/train': 1.4865506887435913} 08/30/2021 20:04:31 - INFO - __main__ - Step 38112: {'lr': 0.00043008093722216603, 'samples': 7317504, 'steps': 38111, 'loss/train': 1.0639395713806152} 08/30/2021 20:04:31 - INFO - __main__ - Step 38113: {'lr': 0.00043007725622197675, 'samples': 7317696, 'steps': 38112, 'loss/train': 1.9150346517562866} 08/30/2021 20:04:32 - INFO - __main__ - Step 38114: {'lr': 0.0004300735751406474, 'samples': 7317888, 'steps': 38113, 'loss/train': 2.0976529121398926} 08/30/2021 20:04:32 - INFO - __main__ - Step 38115: {'lr': 0.00043006989397817967, 'samples': 7318080, 'steps': 38114, 'loss/train': 1.4350019693374634} 08/30/2021 20:04:32 - INFO - __main__ - Step 38116: {'lr': 0.00043006621273457523, 'samples': 7318272, 'steps': 38115, 'loss/train': 1.3051835298538208} 08/30/2021 20:04:34 - INFO - __main__ - Step 38117: {'lr': 0.0004300625314098358, 'samples': 7318464, 'steps': 38116, 'loss/train': 0.10825788229703903} 08/30/2021 20:04:34 - INFO - __main__ - Step 38118: {'lr': 0.0004300588500039629, 'samples': 7318656, 'steps': 38117, 'loss/train': 5.947971343994141} 08/30/2021 20:04:35 - INFO - __main__ - Step 38119: {'lr': 0.0004300551685169583, 'samples': 7318848, 'steps': 38118, 'loss/train': 1.714760184288025} 08/30/2021 20:04:35 - INFO - __main__ - Step 38120: {'lr': 0.0004300514869488236, 'samples': 7319040, 'steps': 38119, 'loss/train': 1.7870771884918213} 08/30/2021 20:04:35 - INFO - __main__ - Step 38121: {'lr': 0.00043004780529956046, 'samples': 7319232, 'steps': 38120, 'loss/train': 1.267866849899292} 08/30/2021 20:04:37 - INFO - __main__ - Step 38122: {'lr': 0.00043004412356917055, 'samples': 7319424, 'steps': 38121, 'loss/train': 1.9728401899337769} 08/30/2021 20:04:37 - INFO - __main__ - Step 38123: {'lr': 0.0004300404417576556, 'samples': 7319616, 'steps': 38122, 'loss/train': 1.5835316181182861} 08/30/2021 20:04:38 - INFO - __main__ - Step 38124: {'lr': 0.00043003675986501717, 'samples': 7319808, 'steps': 38123, 'loss/train': 1.705342173576355} 08/30/2021 20:04:38 - INFO - __main__ - Step 38125: {'lr': 0.00043003307789125694, 'samples': 7320000, 'steps': 38124, 'loss/train': 1.744152545928955} 08/30/2021 20:04:39 - INFO - __main__ - Step 38126: {'lr': 0.0004300293958363766, 'samples': 7320192, 'steps': 38125, 'loss/train': 1.6485809087753296} 08/30/2021 20:04:40 - INFO - __main__ - Step 38127: {'lr': 0.00043002571370037777, 'samples': 7320384, 'steps': 38126, 'loss/train': 2.0750226974487305} 08/30/2021 20:04:41 - INFO - __main__ - Step 38128: {'lr': 0.00043002203148326213, 'samples': 7320576, 'steps': 38127, 'loss/train': 1.4557346105575562} 08/30/2021 20:04:41 - INFO - __main__ - Step 38129: {'lr': 0.0004300183491850314, 'samples': 7320768, 'steps': 38128, 'loss/train': 1.4113519191741943} 08/30/2021 20:04:41 - INFO - __main__ - Step 38130: {'lr': 0.0004300146668056871, 'samples': 7320960, 'steps': 38129, 'loss/train': 1.333693027496338} 08/30/2021 20:04:42 - INFO - __main__ - Step 38131: {'lr': 0.00043001098434523107, 'samples': 7321152, 'steps': 38130, 'loss/train': 1.1593481302261353} 08/30/2021 20:04:42 - INFO - __main__ - Step 38132: {'lr': 0.0004300073018036648, 'samples': 7321344, 'steps': 38131, 'loss/train': 0.5571146011352539} 08/30/2021 20:04:44 - INFO - __main__ - Step 38133: {'lr': 0.00043000361918099, 'samples': 7321536, 'steps': 38132, 'loss/train': 1.232261300086975} 08/30/2021 20:04:44 - INFO - __main__ - Step 38134: {'lr': 0.00042999993647720836, 'samples': 7321728, 'steps': 38133, 'loss/train': 0.06851159036159515} 08/30/2021 20:04:45 - INFO - __main__ - Step 38135: {'lr': 0.0004299962536923215, 'samples': 7321920, 'steps': 38134, 'loss/train': 1.6765235662460327} 08/30/2021 20:04:45 - INFO - __main__ - Step 38136: {'lr': 0.0004299925708263312, 'samples': 7322112, 'steps': 38135, 'loss/train': 1.6706408262252808} 08/30/2021 20:04:45 - INFO - __main__ - Step 38137: {'lr': 0.00042998888787923895, 'samples': 7322304, 'steps': 38136, 'loss/train': 1.7377032041549683} 08/30/2021 20:04:47 - INFO - __main__ - Step 38138: {'lr': 0.0004299852048510465, 'samples': 7322496, 'steps': 38137, 'loss/train': 1.678581953048706} 08/30/2021 20:04:47 - INFO - __main__ - Step 38139: {'lr': 0.00042998152174175555, 'samples': 7322688, 'steps': 38138, 'loss/train': 1.3767420053482056} 08/30/2021 20:04:48 - INFO - __main__ - Step 38140: {'lr': 0.0004299778385513676, 'samples': 7322880, 'steps': 38139, 'loss/train': 1.274703860282898} 08/30/2021 20:04:48 - INFO - __main__ - Step 38141: {'lr': 0.0004299741552798845, 'samples': 7323072, 'steps': 38140, 'loss/train': 1.2292976379394531} 08/30/2021 20:04:48 - INFO - __main__ - Step 38142: {'lr': 0.0004299704719273078, 'samples': 7323264, 'steps': 38141, 'loss/train': 1.185442566871643} 08/30/2021 20:04:49 - INFO - __main__ - Step 38143: {'lr': 0.00042996678849363914, 'samples': 7323456, 'steps': 38142, 'loss/train': 1.057015299797058} 08/30/2021 20:04:51 - INFO - __main__ - Step 38144: {'lr': 0.00042996310497888025, 'samples': 7323648, 'steps': 38143, 'loss/train': 1.5116634368896484} 08/30/2021 20:04:51 - INFO - __main__ - Step 38145: {'lr': 0.00042995942138303274, 'samples': 7323840, 'steps': 38144, 'loss/train': 1.4529461860656738} 08/30/2021 20:04:52 - INFO - __main__ - Step 38146: {'lr': 0.0004299557377060983, 'samples': 7324032, 'steps': 38145, 'loss/train': 1.35940682888031} 08/30/2021 20:04:52 - INFO - __main__ - Step 38147: {'lr': 0.00042995205394807864, 'samples': 7324224, 'steps': 38146, 'loss/train': 1.5660464763641357} 08/30/2021 20:04:52 - INFO - __main__ - Step 38148: {'lr': 0.00042994837010897524, 'samples': 7324416, 'steps': 38147, 'loss/train': 1.2501001358032227} 08/30/2021 20:04:55 - INFO - __main__ - Step 38149: {'lr': 0.00042994468618879, 'samples': 7324608, 'steps': 38148, 'loss/train': 1.6698060035705566} 08/30/2021 20:04:55 - INFO - __main__ - Step 38150: {'lr': 0.0004299410021875244, 'samples': 7324800, 'steps': 38149, 'loss/train': 0.5998290181159973} 08/30/2021 20:04:55 - INFO - __main__ - Step 38151: {'lr': 0.00042993731810518025, 'samples': 7324992, 'steps': 38150, 'loss/train': 0.5505896806716919} 08/30/2021 20:04:56 - INFO - __main__ - Step 38152: {'lr': 0.00042993363394175897, 'samples': 7325184, 'steps': 38151, 'loss/train': 1.2739479541778564} 08/30/2021 20:04:56 - INFO - __main__ - Step 38153: {'lr': 0.0004299299496972625, 'samples': 7325376, 'steps': 38152, 'loss/train': 0.7034235596656799} 08/30/2021 20:04:57 - INFO - __main__ - Step 38154: {'lr': 0.0004299262653716923, 'samples': 7325568, 'steps': 38153, 'loss/train': 1.1546645164489746} 08/30/2021 20:04:58 - INFO - __main__ - Step 38155: {'lr': 0.0004299225809650501, 'samples': 7325760, 'steps': 38154, 'loss/train': 1.1841838359832764} 08/30/2021 20:04:58 - INFO - __main__ - Step 38156: {'lr': 0.0004299188964773376, 'samples': 7325952, 'steps': 38155, 'loss/train': 1.0835820436477661} 08/30/2021 20:04:59 - INFO - __main__ - Step 38157: {'lr': 0.0004299152119085564, 'samples': 7326144, 'steps': 38156, 'loss/train': 1.6562628746032715} 08/30/2021 20:04:59 - INFO - __main__ - Step 38158: {'lr': 0.0004299115272587082, 'samples': 7326336, 'steps': 38157, 'loss/train': 0.6394487023353577} 08/30/2021 20:05:00 - INFO - __main__ - Step 38159: {'lr': 0.0004299078425277947, 'samples': 7326528, 'steps': 38158, 'loss/train': 1.6423875093460083} 08/30/2021 20:05:01 - INFO - __main__ - Step 38160: {'lr': 0.00042990415771581734, 'samples': 7326720, 'steps': 38159, 'loss/train': 1.2092241048812866} 08/30/2021 20:05:02 - INFO - __main__ - Step 38161: {'lr': 0.0004299004728227781, 'samples': 7326912, 'steps': 38160, 'loss/train': 1.6938648223876953} 08/30/2021 20:05:02 - INFO - __main__ - Step 38162: {'lr': 0.0004298967878486784, 'samples': 7327104, 'steps': 38161, 'loss/train': 2.016425371170044} 08/30/2021 20:05:02 - INFO - __main__ - Step 38163: {'lr': 0.00042989310279352, 'samples': 7327296, 'steps': 38162, 'loss/train': 1.2421073913574219} 08/30/2021 20:05:03 - INFO - __main__ - Step 38164: {'lr': 0.0004298894176573046, 'samples': 7327488, 'steps': 38163, 'loss/train': 0.059755463153123856} 08/30/2021 20:05:03 - INFO - __main__ - Step 38165: {'lr': 0.0004298857324400337, 'samples': 7327680, 'steps': 38164, 'loss/train': 1.375670075416565} 08/30/2021 20:05:05 - INFO - __main__ - Step 38166: {'lr': 0.0004298820471417091, 'samples': 7327872, 'steps': 38165, 'loss/train': 1.4727246761322021} 08/30/2021 20:05:05 - INFO - __main__ - Step 38167: {'lr': 0.00042987836176233246, 'samples': 7328064, 'steps': 38166, 'loss/train': 0.7216182947158813} 08/30/2021 20:05:05 - INFO - __main__ - Step 38168: {'lr': 0.0004298746763019054, 'samples': 7328256, 'steps': 38167, 'loss/train': 1.4980967044830322} 08/30/2021 20:05:06 - INFO - __main__ - Step 38169: {'lr': 0.0004298709907604296, 'samples': 7328448, 'steps': 38168, 'loss/train': 0.632712721824646} 08/30/2021 20:05:06 - INFO - __main__ - Step 38170: {'lr': 0.0004298673051379066, 'samples': 7328640, 'steps': 38169, 'loss/train': 0.4579286277294159} 08/30/2021 20:05:08 - INFO - __main__ - Step 38171: {'lr': 0.0004298636194343383, 'samples': 7328832, 'steps': 38170, 'loss/train': 1.649490475654602} 08/30/2021 20:05:08 - INFO - __main__ - Step 38172: {'lr': 0.0004298599336497262, 'samples': 7329024, 'steps': 38171, 'loss/train': 1.2945585250854492} 08/30/2021 20:05:08 - INFO - __main__ - Step 38173: {'lr': 0.00042985624778407196, 'samples': 7329216, 'steps': 38172, 'loss/train': 2.015388011932373} 08/30/2021 20:05:09 - INFO - __main__ - Step 38174: {'lr': 0.00042985256183737723, 'samples': 7329408, 'steps': 38173, 'loss/train': 1.3931941986083984} 08/30/2021 20:05:09 - INFO - __main__ - Step 38175: {'lr': 0.00042984887580964376, 'samples': 7329600, 'steps': 38174, 'loss/train': 1.5762046575546265} 08/30/2021 20:05:11 - INFO - __main__ - Step 38176: {'lr': 0.00042984518970087316, 'samples': 7329792, 'steps': 38175, 'loss/train': 1.447563886642456} 08/30/2021 20:05:11 - INFO - __main__ - Step 38177: {'lr': 0.0004298415035110671, 'samples': 7329984, 'steps': 38176, 'loss/train': 0.9451384544372559} 08/30/2021 20:05:11 - INFO - __main__ - Step 38178: {'lr': 0.00042983781724022723, 'samples': 7330176, 'steps': 38177, 'loss/train': 1.563511848449707} 08/30/2021 20:05:12 - INFO - __main__ - Step 38179: {'lr': 0.0004298341308883552, 'samples': 7330368, 'steps': 38178, 'loss/train': 1.2556973695755005} 08/30/2021 20:05:12 - INFO - __main__ - Step 38180: {'lr': 0.0004298304444554527, 'samples': 7330560, 'steps': 38179, 'loss/train': 1.8115509748458862} 08/30/2021 20:05:14 - INFO - __main__ - Step 38181: {'lr': 0.00042982675794152135, 'samples': 7330752, 'steps': 38180, 'loss/train': 1.5163209438323975} 08/30/2021 20:05:14 - INFO - __main__ - Step 38182: {'lr': 0.0004298230713465629, 'samples': 7330944, 'steps': 38181, 'loss/train': 3.8600540161132812} 08/30/2021 20:05:15 - INFO - __main__ - Step 38183: {'lr': 0.00042981938467057893, 'samples': 7331136, 'steps': 38182, 'loss/train': 0.09460396319627762} 08/30/2021 20:05:15 - INFO - __main__ - Step 38184: {'lr': 0.0004298156979135711, 'samples': 7331328, 'steps': 38183, 'loss/train': 1.7542532682418823} 08/30/2021 20:05:15 - INFO - __main__ - Step 38185: {'lr': 0.000429812011075541, 'samples': 7331520, 'steps': 38184, 'loss/train': 1.335465431213379} 08/30/2021 20:05:16 - INFO - __main__ - Step 38186: {'lr': 0.0004298083241564905, 'samples': 7331712, 'steps': 38185, 'loss/train': 0.14262399077415466} 08/30/2021 20:05:18 - INFO - __main__ - Step 38187: {'lr': 0.00042980463715642115, 'samples': 7331904, 'steps': 38186, 'loss/train': 1.7476221323013306} 08/30/2021 20:05:18 - INFO - __main__ - Step 38188: {'lr': 0.0004298009500753346, 'samples': 7332096, 'steps': 38187, 'loss/train': 1.2012053728103638} 08/30/2021 20:05:19 - INFO - __main__ - Step 38189: {'lr': 0.00042979726291323246, 'samples': 7332288, 'steps': 38188, 'loss/train': 0.08518649637699127} 08/30/2021 20:05:19 - INFO - __main__ - Step 38190: {'lr': 0.00042979357567011643, 'samples': 7332480, 'steps': 38189, 'loss/train': 1.461737036705017} 08/30/2021 20:05:19 - INFO - __main__ - Step 38191: {'lr': 0.0004297898883459883, 'samples': 7332672, 'steps': 38190, 'loss/train': 1.0762619972229004} 08/30/2021 20:05:20 - INFO - __main__ - Step 38192: {'lr': 0.00042978620094084955, 'samples': 7332864, 'steps': 38191, 'loss/train': 1.7315171957015991} 08/30/2021 20:05:21 - INFO - __main__ - Step 38193: {'lr': 0.00042978251345470185, 'samples': 7333056, 'steps': 38192, 'loss/train': 0.8061356544494629} 08/30/2021 20:05:22 - INFO - __main__ - Step 38194: {'lr': 0.000429778825887547, 'samples': 7333248, 'steps': 38193, 'loss/train': 1.8283162117004395} 08/30/2021 20:05:22 - INFO - __main__ - Step 38195: {'lr': 0.00042977513823938665, 'samples': 7333440, 'steps': 38194, 'loss/train': 0.6713355779647827} 08/30/2021 20:05:22 - INFO - __main__ - Step 38196: {'lr': 0.00042977145051022224, 'samples': 7333632, 'steps': 38195, 'loss/train': 2.2314579486846924} 08/30/2021 20:05:23 - INFO - __main__ - Step 38197: {'lr': 0.0004297677627000557, 'samples': 7333824, 'steps': 38196, 'loss/train': 1.8773198127746582} 08/30/2021 20:05:24 - INFO - __main__ - Step 38198: {'lr': 0.0004297640748088886, 'samples': 7334016, 'steps': 38197, 'loss/train': 1.4580886363983154} 08/30/2021 20:05:25 - INFO - __main__ - Step 38199: {'lr': 0.0004297603868367225, 'samples': 7334208, 'steps': 38198, 'loss/train': 1.021130084991455} 08/30/2021 20:05:25 - INFO - __main__ - Step 38200: {'lr': 0.00042975669878355917, 'samples': 7334400, 'steps': 38199, 'loss/train': 0.9159539937973022} 08/30/2021 20:05:25 - INFO - __main__ - Step 38201: {'lr': 0.00042975301064940026, 'samples': 7334592, 'steps': 38200, 'loss/train': 1.5189489126205444} 08/30/2021 20:05:26 - INFO - __main__ - Step 38202: {'lr': 0.00042974932243424743, 'samples': 7334784, 'steps': 38201, 'loss/train': 1.0034737586975098} 08/30/2021 20:05:28 - INFO - __main__ - Step 38203: {'lr': 0.0004297456341381023, 'samples': 7334976, 'steps': 38202, 'loss/train': 1.9908865690231323} 08/30/2021 20:05:28 - INFO - __main__ - Step 38204: {'lr': 0.0004297419457609666, 'samples': 7335168, 'steps': 38203, 'loss/train': 1.3665775060653687} 08/30/2021 20:05:28 - INFO - __main__ - Step 38205: {'lr': 0.0004297382573028419, 'samples': 7335360, 'steps': 38204, 'loss/train': 1.351920485496521} 08/30/2021 20:05:29 - INFO - __main__ - Step 38206: {'lr': 0.0004297345687637299, 'samples': 7335552, 'steps': 38205, 'loss/train': 1.8134219646453857} 08/30/2021 20:05:29 - INFO - __main__ - Step 38207: {'lr': 0.00042973088014363237, 'samples': 7335744, 'steps': 38206, 'loss/train': 1.4496570825576782} 08/30/2021 20:05:30 - INFO - __main__ - Step 38208: {'lr': 0.0004297271914425508, 'samples': 7335936, 'steps': 38207, 'loss/train': 1.2204450368881226} 08/30/2021 20:05:31 - INFO - __main__ - Step 38209: {'lr': 0.00042972350266048693, 'samples': 7336128, 'steps': 38208, 'loss/train': 1.5176422595977783} 08/30/2021 20:05:31 - INFO - __main__ - Step 38210: {'lr': 0.0004297198137974425, 'samples': 7336320, 'steps': 38209, 'loss/train': 1.4744043350219727} 08/30/2021 20:05:32 - INFO - __main__ - Step 38211: {'lr': 0.00042971612485341896, 'samples': 7336512, 'steps': 38210, 'loss/train': 1.7286087274551392} 08/30/2021 20:05:32 - INFO - __main__ - Step 38212: {'lr': 0.00042971243582841823, 'samples': 7336704, 'steps': 38211, 'loss/train': 1.5018001794815063} 08/30/2021 20:05:33 - INFO - __main__ - Step 38213: {'lr': 0.0004297087467224418, 'samples': 7336896, 'steps': 38212, 'loss/train': 1.4578546285629272} 08/30/2021 20:05:34 - INFO - __main__ - Step 38214: {'lr': 0.0004297050575354914, 'samples': 7337088, 'steps': 38213, 'loss/train': 1.1368920803070068} 08/30/2021 20:05:35 - INFO - __main__ - Step 38215: {'lr': 0.0004297013682675687, 'samples': 7337280, 'steps': 38214, 'loss/train': 0.7339975237846375} 08/30/2021 20:05:35 - INFO - __main__ - Step 38216: {'lr': 0.0004296976789186753, 'samples': 7337472, 'steps': 38215, 'loss/train': 1.039969801902771} 08/30/2021 20:05:35 - INFO - __main__ - Step 38217: {'lr': 0.00042969398948881286, 'samples': 7337664, 'steps': 38216, 'loss/train': 1.5827642679214478} 08/30/2021 20:05:36 - INFO - __main__ - Step 38218: {'lr': 0.00042969029997798314, 'samples': 7337856, 'steps': 38217, 'loss/train': 0.9548296332359314} 08/30/2021 20:05:37 - INFO - __main__ - Step 38219: {'lr': 0.00042968661038618775, 'samples': 7338048, 'steps': 38218, 'loss/train': 0.9502847194671631} 08/30/2021 20:05:38 - INFO - __main__ - Step 38220: {'lr': 0.0004296829207134283, 'samples': 7338240, 'steps': 38219, 'loss/train': 1.522841453552246} 08/30/2021 20:05:38 - INFO - __main__ - Step 38221: {'lr': 0.0004296792309597065, 'samples': 7338432, 'steps': 38220, 'loss/train': 2.252483367919922} 08/30/2021 20:05:38 - INFO - __main__ - Step 38222: {'lr': 0.00042967554112502404, 'samples': 7338624, 'steps': 38221, 'loss/train': 1.893862247467041} 08/30/2021 20:05:39 - INFO - __main__ - Step 38223: {'lr': 0.00042967185120938256, 'samples': 7338816, 'steps': 38222, 'loss/train': 1.1537975072860718} 08/30/2021 20:05:40 - INFO - __main__ - Step 38224: {'lr': 0.00042966816121278365, 'samples': 7339008, 'steps': 38223, 'loss/train': 1.4714430570602417} 08/30/2021 20:05:41 - INFO - __main__ - Step 38225: {'lr': 0.0004296644711352291, 'samples': 7339200, 'steps': 38224, 'loss/train': 0.22892123460769653} 08/30/2021 20:05:41 - INFO - __main__ - Step 38226: {'lr': 0.0004296607809767205, 'samples': 7339392, 'steps': 38225, 'loss/train': 1.49606192111969} 08/30/2021 20:05:41 - INFO - __main__ - Step 38227: {'lr': 0.00042965709073725957, 'samples': 7339584, 'steps': 38226, 'loss/train': 1.4638125896453857} 08/30/2021 20:05:42 - INFO - __main__ - Step 38228: {'lr': 0.00042965340041684785, 'samples': 7339776, 'steps': 38227, 'loss/train': 1.256641149520874} 08/30/2021 20:05:42 - INFO - __main__ - Step 38229: {'lr': 0.00042964971001548715, 'samples': 7339968, 'steps': 38228, 'loss/train': 1.588843584060669} 08/30/2021 20:05:43 - INFO - __main__ - Step 38230: {'lr': 0.00042964601953317895, 'samples': 7340160, 'steps': 38229, 'loss/train': 1.417837381362915} 08/30/2021 20:05:44 - INFO - __main__ - Step 38231: {'lr': 0.0004296423289699252, 'samples': 7340352, 'steps': 38230, 'loss/train': 1.3788716793060303} 08/30/2021 20:05:44 - INFO - __main__ - Step 38232: {'lr': 0.00042963863832572727, 'samples': 7340544, 'steps': 38231, 'loss/train': 1.118288516998291} 08/30/2021 20:05:45 - INFO - __main__ - Step 38233: {'lr': 0.0004296349476005869, 'samples': 7340736, 'steps': 38232, 'loss/train': 1.4372879266738892} 08/30/2021 20:05:45 - INFO - __main__ - Step 38234: {'lr': 0.0004296312567945059, 'samples': 7340928, 'steps': 38233, 'loss/train': 1.1061968803405762} 08/30/2021 20:05:47 - INFO - __main__ - Step 38235: {'lr': 0.0004296275659074858, 'samples': 7341120, 'steps': 38234, 'loss/train': 1.413161039352417} 08/30/2021 20:05:47 - INFO - __main__ - Step 38236: {'lr': 0.00042962387493952823, 'samples': 7341312, 'steps': 38235, 'loss/train': 1.414198398590088} 08/30/2021 20:05:48 - INFO - __main__ - Step 38237: {'lr': 0.00042962018389063495, 'samples': 7341504, 'steps': 38236, 'loss/train': 0.4985870122909546} 08/30/2021 20:05:48 - INFO - __main__ - Step 38238: {'lr': 0.0004296164927608076, 'samples': 7341696, 'steps': 38237, 'loss/train': 1.5697894096374512} 08/30/2021 20:05:48 - INFO - __main__ - Step 38239: {'lr': 0.00042961280155004786, 'samples': 7341888, 'steps': 38238, 'loss/train': 1.022641897201538} 08/30/2021 20:05:50 - INFO - __main__ - Step 38240: {'lr': 0.0004296091102583573, 'samples': 7342080, 'steps': 38239, 'loss/train': 0.495064914226532} 08/30/2021 20:05:50 - INFO - __main__ - Step 38241: {'lr': 0.0004296054188857377, 'samples': 7342272, 'steps': 38240, 'loss/train': 0.7581716179847717} 08/30/2021 20:05:50 - INFO - __main__ - Step 38242: {'lr': 0.0004296017274321906, 'samples': 7342464, 'steps': 38241, 'loss/train': 1.1975090503692627} 08/30/2021 20:05:51 - INFO - __main__ - Step 38243: {'lr': 0.0004295980358977178, 'samples': 7342656, 'steps': 38242, 'loss/train': 1.9184114933013916} 08/30/2021 20:05:51 - INFO - __main__ - Step 38244: {'lr': 0.0004295943442823209, 'samples': 7342848, 'steps': 38243, 'loss/train': 1.3504652976989746} 08/30/2021 20:05:53 - INFO - __main__ - Step 38245: {'lr': 0.0004295906525860015, 'samples': 7343040, 'steps': 38244, 'loss/train': 1.0900636911392212} 08/30/2021 20:05:53 - INFO - __main__ - Step 38246: {'lr': 0.00042958696080876136, 'samples': 7343232, 'steps': 38245, 'loss/train': 1.3474056720733643} 08/30/2021 20:05:53 - INFO - __main__ - Step 38247: {'lr': 0.00042958326895060206, 'samples': 7343424, 'steps': 38246, 'loss/train': 1.1300328969955444} 08/30/2021 20:05:54 - INFO - __main__ - Step 38248: {'lr': 0.0004295795770115254, 'samples': 7343616, 'steps': 38247, 'loss/train': 0.5504335165023804} 08/30/2021 20:05:54 - INFO - __main__ - Step 38249: {'lr': 0.0004295758849915329, 'samples': 7343808, 'steps': 38248, 'loss/train': 1.278775691986084} 08/30/2021 20:05:56 - INFO - __main__ - Step 38250: {'lr': 0.00042957219289062635, 'samples': 7344000, 'steps': 38249, 'loss/train': 1.3333531618118286} 08/30/2021 20:05:56 - INFO - __main__ - Step 38251: {'lr': 0.0004295685007088072, 'samples': 7344192, 'steps': 38250, 'loss/train': 1.7198967933654785} 08/30/2021 20:05:57 - INFO - __main__ - Step 38252: {'lr': 0.00042956480844607734, 'samples': 7344384, 'steps': 38251, 'loss/train': 1.3209530115127563} 08/30/2021 20:05:57 - INFO - __main__ - Step 38253: {'lr': 0.00042956111610243833, 'samples': 7344576, 'steps': 38252, 'loss/train': 1.4080396890640259} 08/30/2021 20:05:57 - INFO - __main__ - Step 38254: {'lr': 0.0004295574236778919, 'samples': 7344768, 'steps': 38253, 'loss/train': 1.213220477104187} 08/30/2021 20:05:59 - INFO - __main__ - Step 38255: {'lr': 0.00042955373117243954, 'samples': 7344960, 'steps': 38254, 'loss/train': 1.8991073369979858} 08/30/2021 20:06:00 - INFO - __main__ - Step 38256: {'lr': 0.0004295500385860832, 'samples': 7345152, 'steps': 38255, 'loss/train': 1.8520393371582031} 08/30/2021 20:06:00 - INFO - __main__ - Step 38257: {'lr': 0.0004295463459188243, 'samples': 7345344, 'steps': 38256, 'loss/train': 1.1536933183670044} 08/30/2021 20:06:01 - INFO - __main__ - Step 38258: {'lr': 0.00042954265317066457, 'samples': 7345536, 'steps': 38257, 'loss/train': 1.7650787830352783} 08/30/2021 20:06:01 - INFO - __main__ - Step 38259: {'lr': 0.0004295389603416057, 'samples': 7345728, 'steps': 38258, 'loss/train': 1.3722585439682007} 08/30/2021 20:06:02 - INFO - __main__ - Step 38260: {'lr': 0.0004295352674316494, 'samples': 7345920, 'steps': 38259, 'loss/train': 0.08418068289756775} 08/30/2021 20:06:03 - INFO - __main__ - Step 38261: {'lr': 0.0004295315744407972, 'samples': 7346112, 'steps': 38260, 'loss/train': 1.8569375276565552} 08/30/2021 20:06:03 - INFO - __main__ - Step 38262: {'lr': 0.0004295278813690509, 'samples': 7346304, 'steps': 38261, 'loss/train': 1.8080946207046509} 08/30/2021 20:06:04 - INFO - __main__ - Step 38263: {'lr': 0.0004295241882164121, 'samples': 7346496, 'steps': 38262, 'loss/train': 0.0890379324555397} 08/30/2021 20:06:04 - INFO - __main__ - Step 38264: {'lr': 0.0004295204949828825, 'samples': 7346688, 'steps': 38263, 'loss/train': 1.5070195198059082} 08/30/2021 20:06:04 - INFO - __main__ - Step 38265: {'lr': 0.0004295168016684636, 'samples': 7346880, 'steps': 38264, 'loss/train': 1.324474573135376} 08/30/2021 20:06:06 - INFO - __main__ - Step 38266: {'lr': 0.0004295131082731574, 'samples': 7347072, 'steps': 38265, 'loss/train': 1.471064805984497} 08/30/2021 20:06:07 - INFO - __main__ - Step 38267: {'lr': 0.0004295094147969652, 'samples': 7347264, 'steps': 38266, 'loss/train': 1.5266824960708618} 08/30/2021 20:06:07 - INFO - __main__ - Step 38268: {'lr': 0.0004295057212398889, 'samples': 7347456, 'steps': 38267, 'loss/train': 1.4947975873947144} 08/30/2021 20:06:07 - INFO - __main__ - Step 38269: {'lr': 0.00042950202760193003, 'samples': 7347648, 'steps': 38268, 'loss/train': 0.7710279822349548} 08/30/2021 20:06:08 - INFO - __main__ - Step 38270: {'lr': 0.0004294983338830904, 'samples': 7347840, 'steps': 38269, 'loss/train': 0.06871286779642105} 08/30/2021 20:06:09 - INFO - __main__ - Step 38271: {'lr': 0.0004294946400833716, 'samples': 7348032, 'steps': 38270, 'loss/train': 1.5208311080932617} 08/30/2021 20:06:10 - INFO - __main__ - Step 38272: {'lr': 0.0004294909462027752, 'samples': 7348224, 'steps': 38271, 'loss/train': 0.9921095371246338} 08/30/2021 20:06:10 - INFO - __main__ - Step 38273: {'lr': 0.000429487252241303, 'samples': 7348416, 'steps': 38272, 'loss/train': 1.6964455842971802} 08/30/2021 20:06:10 - INFO - __main__ - Step 38274: {'lr': 0.00042948355819895655, 'samples': 7348608, 'steps': 38273, 'loss/train': 0.6870641708374023} 08/30/2021 20:06:11 - INFO - __main__ - Step 38275: {'lr': 0.0004294798640757377, 'samples': 7348800, 'steps': 38274, 'loss/train': 1.894271731376648} 08/30/2021 20:06:12 - INFO - __main__ - Step 38276: {'lr': 0.00042947616987164787, 'samples': 7348992, 'steps': 38275, 'loss/train': 1.4293462038040161} 08/30/2021 20:06:13 - INFO - __main__ - Step 38277: {'lr': 0.00042947247558668887, 'samples': 7349184, 'steps': 38276, 'loss/train': 1.2104756832122803} 08/30/2021 20:06:13 - INFO - __main__ - Step 38278: {'lr': 0.00042946878122086243, 'samples': 7349376, 'steps': 38277, 'loss/train': 2.1625611782073975} 08/30/2021 20:06:13 - INFO - __main__ - Step 38279: {'lr': 0.00042946508677417007, 'samples': 7349568, 'steps': 38278, 'loss/train': 0.9601813554763794} 08/30/2021 20:06:14 - INFO - __main__ - Step 38280: {'lr': 0.0004294613922466135, 'samples': 7349760, 'steps': 38279, 'loss/train': 1.3848577737808228} 08/30/2021 20:06:15 - INFO - __main__ - Step 38281: {'lr': 0.0004294576976381944, 'samples': 7349952, 'steps': 38280, 'loss/train': 1.0251612663269043} 08/30/2021 20:06:15 - INFO - __main__ - Step 38282: {'lr': 0.00042945400294891445, 'samples': 7350144, 'steps': 38281, 'loss/train': 0.4659092426300049} 08/30/2021 20:06:16 - INFO - __main__ - Step 38283: {'lr': 0.0004294503081787753, 'samples': 7350336, 'steps': 38282, 'loss/train': 1.0270302295684814} 08/30/2021 20:06:16 - INFO - __main__ - Step 38284: {'lr': 0.0004294466133277786, 'samples': 7350528, 'steps': 38283, 'loss/train': 1.0008982419967651} 08/30/2021 20:06:17 - INFO - __main__ - Step 38285: {'lr': 0.00042944291839592597, 'samples': 7350720, 'steps': 38284, 'loss/train': 1.7949819564819336} 08/30/2021 20:06:19 - INFO - __main__ - Step 38286: {'lr': 0.0004294392233832192, 'samples': 7350912, 'steps': 38285, 'loss/train': 1.3292067050933838} 08/30/2021 20:06:19 - INFO - __main__ - Step 38287: {'lr': 0.0004294355282896599, 'samples': 7351104, 'steps': 38286, 'loss/train': 1.497835397720337} 08/30/2021 20:06:19 - INFO - __main__ - Step 38288: {'lr': 0.00042943183311524967, 'samples': 7351296, 'steps': 38287, 'loss/train': 1.17180597782135} 08/30/2021 20:06:20 - INFO - __main__ - Step 38289: {'lr': 0.0004294281378599902, 'samples': 7351488, 'steps': 38288, 'loss/train': 0.8179500102996826} 08/30/2021 20:06:20 - INFO - __main__ - Step 38290: {'lr': 0.00042942444252388323, 'samples': 7351680, 'steps': 38289, 'loss/train': 1.8279922008514404} 08/30/2021 20:06:21 - INFO - __main__ - Step 38291: {'lr': 0.0004294207471069304, 'samples': 7351872, 'steps': 38290, 'loss/train': 0.3865101933479309} 08/30/2021 20:06:22 - INFO - __main__ - Step 38292: {'lr': 0.0004294170516091332, 'samples': 7352064, 'steps': 38291, 'loss/train': 0.199554905295372} 08/30/2021 20:06:23 - INFO - __main__ - Step 38293: {'lr': 0.0004294133560304936, 'samples': 7352256, 'steps': 38292, 'loss/train': 0.6022427082061768} 08/30/2021 20:06:23 - INFO - __main__ - Step 38294: {'lr': 0.00042940966037101314, 'samples': 7352448, 'steps': 38293, 'loss/train': 0.4879750609397888} 08/30/2021 20:06:23 - INFO - __main__ - Step 38295: {'lr': 0.00042940596463069336, 'samples': 7352640, 'steps': 38294, 'loss/train': 1.4816641807556152} 08/30/2021 20:06:24 - INFO - __main__ - Step 38296: {'lr': 0.00042940226880953605, 'samples': 7352832, 'steps': 38295, 'loss/train': 0.8066173195838928} 08/30/2021 20:06:25 - INFO - __main__ - Step 38297: {'lr': 0.0004293985729075428, 'samples': 7353024, 'steps': 38296, 'loss/train': 1.0941252708435059} 08/30/2021 20:06:26 - INFO - __main__ - Step 38298: {'lr': 0.00042939487692471534, 'samples': 7353216, 'steps': 38297, 'loss/train': 1.3860887289047241} 08/30/2021 20:06:26 - INFO - __main__ - Step 38299: {'lr': 0.0004293911808610554, 'samples': 7353408, 'steps': 38298, 'loss/train': 1.9408745765686035} 08/30/2021 20:06:27 - INFO - __main__ - Step 38300: {'lr': 0.0004293874847165645, 'samples': 7353600, 'steps': 38299, 'loss/train': 2.1356542110443115} 08/30/2021 20:06:27 - INFO - __main__ - Step 38301: {'lr': 0.0004293837884912444, 'samples': 7353792, 'steps': 38300, 'loss/train': 1.271031379699707} 08/30/2021 20:06:27 - INFO - __main__ - Step 38302: {'lr': 0.00042938009218509667, 'samples': 7353984, 'steps': 38301, 'loss/train': 0.039873361587524414} 08/30/2021 20:06:29 - INFO - __main__ - Step 38303: {'lr': 0.00042937639579812304, 'samples': 7354176, 'steps': 38302, 'loss/train': 1.24366295337677} 08/30/2021 20:06:29 - INFO - __main__ - Step 38304: {'lr': 0.0004293726993303252, 'samples': 7354368, 'steps': 38303, 'loss/train': 1.8782334327697754} 08/30/2021 20:06:30 - INFO - __main__ - Step 38305: {'lr': 0.0004293690027817048, 'samples': 7354560, 'steps': 38304, 'loss/train': 1.8164504766464233} 08/30/2021 20:06:30 - INFO - __main__ - Step 38306: {'lr': 0.00042936530615226355, 'samples': 7354752, 'steps': 38305, 'loss/train': 1.1669104099273682} 08/30/2021 20:06:30 - INFO - __main__ - Step 38307: {'lr': 0.00042936160944200295, 'samples': 7354944, 'steps': 38306, 'loss/train': 0.7284160256385803} 08/30/2021 20:06:32 - INFO - __main__ - Step 38308: {'lr': 0.00042935791265092483, 'samples': 7355136, 'steps': 38307, 'loss/train': 1.7641724348068237} 08/30/2021 20:06:33 - INFO - __main__ - Step 38309: {'lr': 0.0004293542157790308, 'samples': 7355328, 'steps': 38308, 'loss/train': 1.6868990659713745} 08/30/2021 20:06:33 - INFO - __main__ - Step 38310: {'lr': 0.00042935051882632245, 'samples': 7355520, 'steps': 38309, 'loss/train': 1.474240779876709} 08/30/2021 20:06:34 - INFO - __main__ - Step 38311: {'lr': 0.0004293468217928017, 'samples': 7355712, 'steps': 38310, 'loss/train': 1.1536802053451538} 08/30/2021 20:06:34 - INFO - __main__ - Step 38312: {'lr': 0.0004293431246784699, 'samples': 7355904, 'steps': 38311, 'loss/train': 1.35757315158844} 08/30/2021 20:06:34 - INFO - __main__ - Step 38313: {'lr': 0.0004293394274833289, 'samples': 7356096, 'steps': 38312, 'loss/train': 2.712996006011963} 08/30/2021 20:06:36 - INFO - __main__ - Step 38314: {'lr': 0.0004293357302073804, 'samples': 7356288, 'steps': 38313, 'loss/train': 1.4420884847640991} 08/30/2021 20:06:37 - INFO - __main__ - Step 38315: {'lr': 0.00042933203285062585, 'samples': 7356480, 'steps': 38314, 'loss/train': 0.03965742886066437} 08/30/2021 20:06:37 - INFO - __main__ - Step 38316: {'lr': 0.00042932833541306704, 'samples': 7356672, 'steps': 38315, 'loss/train': 0.05863025411963463} 08/30/2021 20:06:37 - INFO - __main__ - Step 38317: {'lr': 0.0004293246378947058, 'samples': 7356864, 'steps': 38316, 'loss/train': 1.2256696224212646} 08/30/2021 20:06:38 - INFO - __main__ - Step 38318: {'lr': 0.00042932094029554354, 'samples': 7357056, 'steps': 38317, 'loss/train': 1.7070883512496948} 08/30/2021 20:06:38 - INFO - __main__ - Step 38319: {'lr': 0.00042931724261558205, 'samples': 7357248, 'steps': 38318, 'loss/train': 1.1679096221923828} 08/30/2021 20:06:40 - INFO - __main__ - Step 38320: {'lr': 0.000429313544854823, 'samples': 7357440, 'steps': 38319, 'loss/train': 2.084946393966675} 08/30/2021 20:06:40 - INFO - __main__ - Step 38321: {'lr': 0.00042930984701326796, 'samples': 7357632, 'steps': 38320, 'loss/train': 0.9213653802871704} 08/30/2021 20:06:41 - INFO - __main__ - Step 38322: {'lr': 0.0004293061490909187, 'samples': 7357824, 'steps': 38321, 'loss/train': 2.204930305480957} 08/30/2021 20:06:41 - INFO - __main__ - Step 38323: {'lr': 0.0004293024510877769, 'samples': 7358016, 'steps': 38322, 'loss/train': 1.5008680820465088} 08/30/2021 20:06:41 - INFO - __main__ - Step 38324: {'lr': 0.00042929875300384417, 'samples': 7358208, 'steps': 38323, 'loss/train': 1.2555770874023438} 08/30/2021 20:06:43 - INFO - __main__ - Step 38325: {'lr': 0.0004292950548391222, 'samples': 7358400, 'steps': 38324, 'loss/train': 1.0517908334732056} 08/30/2021 20:06:43 - INFO - __main__ - Step 38326: {'lr': 0.00042929135659361265, 'samples': 7358592, 'steps': 38325, 'loss/train': 1.4341306686401367} 08/30/2021 20:06:44 - INFO - __main__ - Step 38327: {'lr': 0.0004292876582673171, 'samples': 7358784, 'steps': 38326, 'loss/train': 1.5242656469345093} 08/30/2021 20:06:44 - INFO - __main__ - Step 38328: {'lr': 0.0004292839598602374, 'samples': 7358976, 'steps': 38327, 'loss/train': 1.540467381477356} 08/30/2021 20:06:44 - INFO - __main__ - Step 38329: {'lr': 0.000429280261372375, 'samples': 7359168, 'steps': 38328, 'loss/train': 1.4473063945770264} 08/30/2021 20:06:46 - INFO - __main__ - Step 38330: {'lr': 0.00042927656280373176, 'samples': 7359360, 'steps': 38329, 'loss/train': 1.760880470275879} 08/30/2021 20:06:47 - INFO - __main__ - Step 38331: {'lr': 0.00042927286415430933, 'samples': 7359552, 'steps': 38330, 'loss/train': 1.310583233833313} 08/30/2021 20:06:47 - INFO - __main__ - Step 38332: {'lr': 0.0004292691654241092, 'samples': 7359744, 'steps': 38331, 'loss/train': 1.4204710721969604} 08/30/2021 20:06:47 - INFO - __main__ - Step 38333: {'lr': 0.00042926546661313313, 'samples': 7359936, 'steps': 38332, 'loss/train': 1.2705073356628418} 08/30/2021 20:06:48 - INFO - __main__ - Step 38334: {'lr': 0.00042926176772138295, 'samples': 7360128, 'steps': 38333, 'loss/train': 1.5802440643310547} 08/30/2021 20:06:49 - INFO - __main__ - Step 38335: {'lr': 0.0004292580687488601, 'samples': 7360320, 'steps': 38334, 'loss/train': 0.784907341003418} 08/30/2021 20:06:50 - INFO - __main__ - Step 38336: {'lr': 0.0004292543696955663, 'samples': 7360512, 'steps': 38335, 'loss/train': 1.3498750925064087} 08/30/2021 20:06:50 - INFO - __main__ - Step 38337: {'lr': 0.00042925067056150324, 'samples': 7360704, 'steps': 38336, 'loss/train': 1.0025606155395508} 08/30/2021 20:06:50 - INFO - __main__ - Step 38338: {'lr': 0.0004292469713466727, 'samples': 7360896, 'steps': 38337, 'loss/train': 1.865934133529663} 08/30/2021 20:06:51 - INFO - __main__ - Step 38339: {'lr': 0.00042924327205107616, 'samples': 7361088, 'steps': 38338, 'loss/train': 1.722361445426941} 08/30/2021 20:06:52 - INFO - __main__ - Step 38340: {'lr': 0.00042923957267471536, 'samples': 7361280, 'steps': 38339, 'loss/train': 1.7274144887924194} 08/30/2021 20:06:53 - INFO - __main__ - Step 38341: {'lr': 0.000429235873217592, 'samples': 7361472, 'steps': 38340, 'loss/train': 1.5452969074249268} 08/30/2021 20:06:53 - INFO - __main__ - Step 38342: {'lr': 0.0004292321736797077, 'samples': 7361664, 'steps': 38341, 'loss/train': 0.16172029078006744} 08/30/2021 20:06:53 - INFO - __main__ - Step 38343: {'lr': 0.0004292284740610642, 'samples': 7361856, 'steps': 38342, 'loss/train': 1.1055632829666138} 08/30/2021 20:06:54 - INFO - __main__ - Step 38344: {'lr': 0.0004292247743616631, 'samples': 7362048, 'steps': 38343, 'loss/train': 1.6674665212631226} 08/30/2021 20:06:54 - INFO - __main__ - Step 38345: {'lr': 0.00042922107458150604, 'samples': 7362240, 'steps': 38344, 'loss/train': 1.0714342594146729} 08/30/2021 20:06:55 - INFO - __main__ - Step 38346: {'lr': 0.00042921737472059474, 'samples': 7362432, 'steps': 38345, 'loss/train': 0.8256217837333679} 08/30/2021 20:06:56 - INFO - __main__ - Step 38347: {'lr': 0.0004292136747789309, 'samples': 7362624, 'steps': 38346, 'loss/train': 1.4083000421524048} 08/30/2021 20:06:56 - INFO - __main__ - Step 38348: {'lr': 0.00042920997475651607, 'samples': 7362816, 'steps': 38347, 'loss/train': 1.5473214387893677} 08/30/2021 20:06:57 - INFO - __main__ - Step 38349: {'lr': 0.00042920627465335205, 'samples': 7363008, 'steps': 38348, 'loss/train': 1.6063055992126465} 08/30/2021 20:06:57 - INFO - __main__ - Step 38350: {'lr': 0.00042920257446944044, 'samples': 7363200, 'steps': 38349, 'loss/train': 1.1227517127990723} 08/30/2021 20:06:59 - INFO - __main__ - Step 38351: {'lr': 0.0004291988742047829, 'samples': 7363392, 'steps': 38350, 'loss/train': 1.6076951026916504} 08/30/2021 20:06:59 - INFO - __main__ - Step 38352: {'lr': 0.0004291951738593811, 'samples': 7363584, 'steps': 38351, 'loss/train': 1.4710899591445923} 08/30/2021 20:06:59 - INFO - __main__ - Step 38353: {'lr': 0.0004291914734332367, 'samples': 7363776, 'steps': 38352, 'loss/train': 1.488527536392212} 08/30/2021 20:07:00 - INFO - __main__ - Step 38354: {'lr': 0.0004291877729263515, 'samples': 7363968, 'steps': 38353, 'loss/train': 0.05705566331744194} 08/30/2021 20:07:00 - INFO - __main__ - Step 38355: {'lr': 0.0004291840723387269, 'samples': 7364160, 'steps': 38354, 'loss/train': 1.9111604690551758} 08/30/2021 20:07:02 - INFO - __main__ - Step 38356: {'lr': 0.0004291803716703648, 'samples': 7364352, 'steps': 38355, 'loss/train': 1.3006529808044434} 08/30/2021 20:07:02 - INFO - __main__ - Step 38357: {'lr': 0.0004291766709212668, 'samples': 7364544, 'steps': 38356, 'loss/train': 1.4822531938552856} 08/30/2021 20:07:02 - INFO - __main__ - Step 38358: {'lr': 0.00042917297009143455, 'samples': 7364736, 'steps': 38357, 'loss/train': 1.4925570487976074} 08/30/2021 20:07:03 - INFO - __main__ - Step 38359: {'lr': 0.00042916926918086973, 'samples': 7364928, 'steps': 38358, 'loss/train': 1.2138392925262451} 08/30/2021 20:07:03 - INFO - __main__ - Step 38360: {'lr': 0.000429165568189574, 'samples': 7365120, 'steps': 38359, 'loss/train': 1.5441910028457642} 08/30/2021 20:07:05 - INFO - __main__ - Step 38361: {'lr': 0.000429161867117549, 'samples': 7365312, 'steps': 38360, 'loss/train': 1.702162265777588} 08/30/2021 20:07:06 - INFO - __main__ - Step 38362: {'lr': 0.0004291581659647965, 'samples': 7365504, 'steps': 38361, 'loss/train': 1.0644760131835938} 08/30/2021 20:07:06 - INFO - __main__ - Step 38363: {'lr': 0.00042915446473131805, 'samples': 7365696, 'steps': 38362, 'loss/train': 1.857157826423645} 08/30/2021 20:07:06 - INFO - __main__ - Step 38364: {'lr': 0.0004291507634171153, 'samples': 7365888, 'steps': 38363, 'loss/train': 1.570695161819458} 08/30/2021 20:07:07 - INFO - __main__ - Step 38365: {'lr': 0.0004291470620221901, 'samples': 7366080, 'steps': 38364, 'loss/train': 1.4484847784042358} 08/30/2021 20:07:08 - INFO - __main__ - Step 38366: {'lr': 0.0004291433605465439, 'samples': 7366272, 'steps': 38365, 'loss/train': 1.6458383798599243} 08/30/2021 20:07:09 - INFO - __main__ - Step 38367: {'lr': 0.00042913965899017855, 'samples': 7366464, 'steps': 38366, 'loss/train': 1.7018097639083862} 08/30/2021 20:07:09 - INFO - __main__ - Step 38368: {'lr': 0.0004291359573530956, 'samples': 7366656, 'steps': 38367, 'loss/train': 0.5052033066749573} 08/30/2021 20:07:09 - INFO - __main__ - Step 38369: {'lr': 0.0004291322556352967, 'samples': 7366848, 'steps': 38368, 'loss/train': 1.6005996465682983} 08/30/2021 20:07:10 - INFO - __main__ - Step 38370: {'lr': 0.00042912855383678365, 'samples': 7367040, 'steps': 38369, 'loss/train': 1.4237728118896484} 08/30/2021 20:07:10 - INFO - __main__ - Step 38371: {'lr': 0.000429124851957558, 'samples': 7367232, 'steps': 38370, 'loss/train': 1.1759494543075562} 08/30/2021 20:07:12 - INFO - __main__ - Step 38372: {'lr': 0.0004291211499976214, 'samples': 7367424, 'steps': 38371, 'loss/train': 0.0802549198269844} 08/30/2021 20:07:12 - INFO - __main__ - Step 38373: {'lr': 0.0004291174479569757, 'samples': 7367616, 'steps': 38372, 'loss/train': 0.9666499495506287} 08/30/2021 20:07:12 - INFO - __main__ - Step 38374: {'lr': 0.00042911374583562233, 'samples': 7367808, 'steps': 38373, 'loss/train': 1.8338737487792969} 08/30/2021 20:07:13 - INFO - __main__ - Step 38375: {'lr': 0.0004291100436335631, 'samples': 7368000, 'steps': 38374, 'loss/train': 1.7034742832183838} 08/30/2021 20:07:13 - INFO - __main__ - Step 38376: {'lr': 0.00042910634135079963, 'samples': 7368192, 'steps': 38375, 'loss/train': 1.0884268283843994} 08/30/2021 20:07:15 - INFO - __main__ - Step 38377: {'lr': 0.00042910263898733364, 'samples': 7368384, 'steps': 38376, 'loss/train': 1.3782685995101929} 08/30/2021 20:07:15 - INFO - __main__ - Step 38378: {'lr': 0.0004290989365431668, 'samples': 7368576, 'steps': 38377, 'loss/train': 1.3031351566314697} 08/30/2021 20:07:16 - INFO - __main__ - Step 38379: {'lr': 0.0004290952340183007, 'samples': 7368768, 'steps': 38378, 'loss/train': 1.3178495168685913} 08/30/2021 20:07:16 - INFO - __main__ - Step 38380: {'lr': 0.00042909153141273705, 'samples': 7368960, 'steps': 38379, 'loss/train': 1.0316145420074463} 08/30/2021 20:07:16 - INFO - __main__ - Step 38381: {'lr': 0.0004290878287264775, 'samples': 7369152, 'steps': 38380, 'loss/train': 1.0927937030792236} 08/30/2021 20:07:17 - INFO - __main__ - Step 38382: {'lr': 0.0004290841259595237, 'samples': 7369344, 'steps': 38381, 'loss/train': 0.21168382465839386} 08/30/2021 20:07:18 - INFO - __main__ - Step 38383: {'lr': 0.00042908042311187744, 'samples': 7369536, 'steps': 38382, 'loss/train': 0.2850779891014099} 08/30/2021 20:07:19 - INFO - __main__ - Step 38384: {'lr': 0.00042907672018354027, 'samples': 7369728, 'steps': 38383, 'loss/train': 1.570150375366211} 08/30/2021 20:07:19 - INFO - __main__ - Step 38385: {'lr': 0.00042907301717451396, 'samples': 7369920, 'steps': 38384, 'loss/train': 1.4802727699279785} 08/30/2021 20:07:19 - INFO - __main__ - Step 38386: {'lr': 0.0004290693140848, 'samples': 7370112, 'steps': 38385, 'loss/train': 1.4690767526626587} 08/30/2021 20:07:20 - INFO - __main__ - Step 38387: {'lr': 0.0004290656109144003, 'samples': 7370304, 'steps': 38386, 'loss/train': 1.6843456029891968} 08/30/2021 20:07:21 - INFO - __main__ - Step 38388: {'lr': 0.0004290619076633163, 'samples': 7370496, 'steps': 38387, 'loss/train': 1.4054378271102905} 08/30/2021 20:07:22 - INFO - __main__ - Step 38389: {'lr': 0.0004290582043315498, 'samples': 7370688, 'steps': 38388, 'loss/train': 2.0691275596618652} 08/30/2021 20:07:22 - INFO - __main__ - Step 38390: {'lr': 0.0004290545009191024, 'samples': 7370880, 'steps': 38389, 'loss/train': 1.850519061088562} 08/30/2021 20:07:23 - INFO - __main__ - Step 38391: {'lr': 0.0004290507974259759, 'samples': 7371072, 'steps': 38390, 'loss/train': 1.5354053974151611} 08/30/2021 20:07:23 - INFO - __main__ - Step 38392: {'lr': 0.0004290470938521718, 'samples': 7371264, 'steps': 38391, 'loss/train': 1.6896512508392334} 08/30/2021 20:07:24 - INFO - __main__ - Step 38393: {'lr': 0.0004290433901976918, 'samples': 7371456, 'steps': 38392, 'loss/train': 1.3803422451019287} 08/30/2021 20:07:25 - INFO - __main__ - Step 38394: {'lr': 0.0004290396864625377, 'samples': 7371648, 'steps': 38393, 'loss/train': 1.3532553911209106} 08/30/2021 20:07:25 - INFO - __main__ - Step 38395: {'lr': 0.000429035982646711, 'samples': 7371840, 'steps': 38394, 'loss/train': 1.0663450956344604} 08/30/2021 20:07:25 - INFO - __main__ - Step 38396: {'lr': 0.0004290322787502135, 'samples': 7372032, 'steps': 38395, 'loss/train': 1.366197109222412} 08/30/2021 20:07:26 - INFO - __main__ - Step 38397: {'lr': 0.0004290285747730468, 'samples': 7372224, 'steps': 38396, 'loss/train': 1.0420398712158203} 08/30/2021 20:07:27 - INFO - __main__ - Step 38398: {'lr': 0.00042902487071521257, 'samples': 7372416, 'steps': 38397, 'loss/train': 1.5380035638809204} 08/30/2021 20:07:28 - INFO - __main__ - Step 38399: {'lr': 0.0004290211665767125, 'samples': 7372608, 'steps': 38398, 'loss/train': 1.3863297700881958} 08/30/2021 20:07:28 - INFO - __main__ - Step 38400: {'lr': 0.00042901746235754837, 'samples': 7372800, 'steps': 38399, 'loss/train': 5.894840717315674} 08/30/2021 20:07:29 - INFO - __main__ - Step 38401: {'lr': 0.0004290137580577216, 'samples': 7372992, 'steps': 38400, 'loss/train': 1.3483859300613403} 08/30/2021 20:07:29 - INFO - __main__ - Step 38402: {'lr': 0.000429010053677234, 'samples': 7373184, 'steps': 38401, 'loss/train': 1.3598942756652832} 08/30/2021 20:07:29 - INFO - __main__ - Step 38403: {'lr': 0.00042900634921608726, 'samples': 7373376, 'steps': 38402, 'loss/train': 1.2021913528442383} 08/30/2021 20:07:31 - INFO - __main__ - Step 38404: {'lr': 0.0004290026446742831, 'samples': 7373568, 'steps': 38403, 'loss/train': 1.045536756515503} 08/30/2021 20:07:32 - INFO - __main__ - Step 38405: {'lr': 0.00042899894005182294, 'samples': 7373760, 'steps': 38404, 'loss/train': 1.710484266281128} 08/30/2021 20:07:32 - INFO - __main__ - Step 38406: {'lr': 0.0004289952353487088, 'samples': 7373952, 'steps': 38405, 'loss/train': 1.2518749237060547} 08/30/2021 20:07:32 - INFO - __main__ - Step 38407: {'lr': 0.000428991530564942, 'samples': 7374144, 'steps': 38406, 'loss/train': 1.3863412141799927} 08/30/2021 20:07:33 - INFO - __main__ - Step 38408: {'lr': 0.00042898782570052453, 'samples': 7374336, 'steps': 38407, 'loss/train': 1.3660690784454346} 08/30/2021 20:07:33 - INFO - __main__ - Step 38409: {'lr': 0.0004289841207554578, 'samples': 7374528, 'steps': 38408, 'loss/train': 1.8012281656265259} 08/30/2021 20:07:34 - INFO - __main__ - Step 38410: {'lr': 0.00042898041572974363, 'samples': 7374720, 'steps': 38409, 'loss/train': 0.05124419555068016} 08/30/2021 20:07:35 - INFO - __main__ - Step 38411: {'lr': 0.0004289767106233836, 'samples': 7374912, 'steps': 38410, 'loss/train': 1.5511677265167236} 08/30/2021 20:07:35 - INFO - __main__ - Step 38412: {'lr': 0.0004289730054363795, 'samples': 7375104, 'steps': 38411, 'loss/train': 1.6404657363891602} 08/30/2021 20:07:36 - INFO - __main__ - Step 38413: {'lr': 0.00042896930016873293, 'samples': 7375296, 'steps': 38412, 'loss/train': 0.4600420296192169} 08/30/2021 20:07:36 - INFO - __main__ - Step 38414: {'lr': 0.0004289655948204455, 'samples': 7375488, 'steps': 38413, 'loss/train': 1.2763087749481201} 08/30/2021 20:07:38 - INFO - __main__ - Step 38415: {'lr': 0.00042896188939151893, 'samples': 7375680, 'steps': 38414, 'loss/train': 0.8128842115402222} 08/30/2021 20:07:38 - INFO - __main__ - Step 38416: {'lr': 0.00042895818388195497, 'samples': 7375872, 'steps': 38415, 'loss/train': 1.8555107116699219} 08/30/2021 20:07:38 - INFO - __main__ - Step 38417: {'lr': 0.00042895447829175516, 'samples': 7376064, 'steps': 38416, 'loss/train': 0.6345165967941284} 08/30/2021 20:07:39 - INFO - __main__ - Step 38418: {'lr': 0.00042895077262092117, 'samples': 7376256, 'steps': 38417, 'loss/train': 1.8651283979415894} 08/30/2021 20:07:39 - INFO - __main__ - Step 38419: {'lr': 0.00042894706686945485, 'samples': 7376448, 'steps': 38418, 'loss/train': 0.7478687763214111} 08/30/2021 20:07:39 - INFO - __main__ - Step 38420: {'lr': 0.00042894336103735766, 'samples': 7376640, 'steps': 38419, 'loss/train': 2.884406805038452} 08/30/2021 20:07:41 - INFO - __main__ - Step 38421: {'lr': 0.0004289396551246313, 'samples': 7376832, 'steps': 38420, 'loss/train': 1.53440260887146} 08/30/2021 20:07:42 - INFO - __main__ - Step 38422: {'lr': 0.0004289359491312776, 'samples': 7377024, 'steps': 38421, 'loss/train': 1.1233142614364624} 08/30/2021 20:07:42 - INFO - __main__ - Step 38423: {'lr': 0.00042893224305729806, 'samples': 7377216, 'steps': 38422, 'loss/train': 1.0973279476165771} 08/30/2021 20:07:43 - INFO - __main__ - Step 38424: {'lr': 0.0004289285369026944, 'samples': 7377408, 'steps': 38423, 'loss/train': 1.3954734802246094} 08/30/2021 20:07:43 - INFO - __main__ - Step 38425: {'lr': 0.00042892483066746836, 'samples': 7377600, 'steps': 38424, 'loss/train': 2.1326191425323486} 08/30/2021 20:07:44 - INFO - __main__ - Step 38426: {'lr': 0.0004289211243516216, 'samples': 7377792, 'steps': 38425, 'loss/train': 1.6857160329818726} 08/30/2021 20:07:45 - INFO - __main__ - Step 38427: {'lr': 0.0004289174179551556, 'samples': 7377984, 'steps': 38426, 'loss/train': 1.6702098846435547} 08/30/2021 20:07:45 - INFO - __main__ - Step 38428: {'lr': 0.0004289137114780722, 'samples': 7378176, 'steps': 38427, 'loss/train': 1.3359206914901733} 08/30/2021 20:07:46 - INFO - __main__ - Step 38429: {'lr': 0.00042891000492037315, 'samples': 7378368, 'steps': 38428, 'loss/train': 1.6277127265930176} 08/30/2021 20:07:46 - INFO - __main__ - Step 38430: {'lr': 0.00042890629828205997, 'samples': 7378560, 'steps': 38429, 'loss/train': 0.9746399521827698} 08/30/2021 20:07:47 - INFO - __main__ - Step 38431: {'lr': 0.0004289025915631343, 'samples': 7378752, 'steps': 38430, 'loss/train': 1.7930362224578857} 08/30/2021 20:07:48 - INFO - __main__ - Step 38432: {'lr': 0.00042889888476359793, 'samples': 7378944, 'steps': 38431, 'loss/train': 1.0633318424224854} 08/30/2021 20:07:48 - INFO - __main__ - Step 38433: {'lr': 0.0004288951778834525, 'samples': 7379136, 'steps': 38432, 'loss/train': 1.75481116771698} 08/30/2021 20:07:49 - INFO - __main__ - Step 38434: {'lr': 0.00042889147092269964, 'samples': 7379328, 'steps': 38433, 'loss/train': 1.6086457967758179} 08/30/2021 20:07:49 - INFO - __main__ - Step 38435: {'lr': 0.0004288877638813411, 'samples': 7379520, 'steps': 38434, 'loss/train': 1.5156124830245972} 08/30/2021 20:07:51 - INFO - __main__ - Step 38436: {'lr': 0.00042888405675937843, 'samples': 7379712, 'steps': 38435, 'loss/train': 1.480774998664856} 08/30/2021 20:07:51 - INFO - __main__ - Step 38437: {'lr': 0.00042888034955681337, 'samples': 7379904, 'steps': 38436, 'loss/train': 1.2685781717300415} 08/30/2021 20:07:52 - INFO - __main__ - Step 38438: {'lr': 0.0004288766422736476, 'samples': 7380096, 'steps': 38437, 'loss/train': 1.4384146928787231} 08/30/2021 20:07:52 - INFO - __main__ - Step 38439: {'lr': 0.00042887293490988276, 'samples': 7380288, 'steps': 38438, 'loss/train': 1.7205339670181274} 08/30/2021 20:07:52 - INFO - __main__ - Step 38440: {'lr': 0.00042886922746552056, 'samples': 7380480, 'steps': 38439, 'loss/train': 0.03151669725775719} 08/30/2021 20:07:53 - INFO - __main__ - Step 38441: {'lr': 0.0004288655199405626, 'samples': 7380672, 'steps': 38440, 'loss/train': 1.7208235263824463} 08/30/2021 20:07:54 - INFO - __main__ - Step 38442: {'lr': 0.00042886181233501067, 'samples': 7380864, 'steps': 38441, 'loss/train': 1.6233160495758057} 08/30/2021 20:07:55 - INFO - __main__ - Step 38443: {'lr': 0.00042885810464886635, 'samples': 7381056, 'steps': 38442, 'loss/train': 1.3776395320892334} 08/30/2021 20:07:55 - INFO - __main__ - Step 38444: {'lr': 0.0004288543968821312, 'samples': 7381248, 'steps': 38443, 'loss/train': 1.6801183223724365} 08/30/2021 20:07:55 - INFO - __main__ - Step 38445: {'lr': 0.00042885068903480717, 'samples': 7381440, 'steps': 38444, 'loss/train': 1.5177701711654663} 08/30/2021 20:07:56 - INFO - __main__ - Step 38446: {'lr': 0.00042884698110689574, 'samples': 7381632, 'steps': 38445, 'loss/train': 1.238015055656433} 08/30/2021 20:07:58 - INFO - __main__ - Step 38447: {'lr': 0.00042884327309839865, 'samples': 7381824, 'steps': 38446, 'loss/train': 0.98250412940979} 08/30/2021 20:07:58 - INFO - __main__ - Step 38448: {'lr': 0.0004288395650093174, 'samples': 7382016, 'steps': 38447, 'loss/train': 1.351719856262207} 08/30/2021 20:07:59 - INFO - __main__ - Step 38449: {'lr': 0.000428835856839654, 'samples': 7382208, 'steps': 38448, 'loss/train': 1.6364364624023438} 08/30/2021 20:07:59 - INFO - __main__ - Step 38450: {'lr': 0.0004288321485894098, 'samples': 7382400, 'steps': 38449, 'loss/train': 1.087575912475586} 08/30/2021 20:07:59 - INFO - __main__ - Step 38451: {'lr': 0.0004288284402585866, 'samples': 7382592, 'steps': 38450, 'loss/train': 1.4363609552383423} 08/30/2021 20:08:00 - INFO - __main__ - Step 38452: {'lr': 0.0004288247318471861, 'samples': 7382784, 'steps': 38451, 'loss/train': 1.2984539270401} 08/30/2021 20:08:01 - INFO - __main__ - Step 38453: {'lr': 0.0004288210233552099, 'samples': 7382976, 'steps': 38452, 'loss/train': 0.6166121959686279} 08/30/2021 20:08:02 - INFO - __main__ - Step 38454: {'lr': 0.00042881731478265975, 'samples': 7383168, 'steps': 38453, 'loss/train': 1.294426679611206} 08/30/2021 20:08:02 - INFO - __main__ - Step 38455: {'lr': 0.00042881360612953724, 'samples': 7383360, 'steps': 38454, 'loss/train': 1.5295624732971191} 08/30/2021 20:08:03 - INFO - __main__ - Step 38456: {'lr': 0.0004288098973958441, 'samples': 7383552, 'steps': 38455, 'loss/train': 0.06265326589345932} 08/30/2021 20:08:03 - INFO - __main__ - Step 38457: {'lr': 0.000428806188581582, 'samples': 7383744, 'steps': 38456, 'loss/train': 0.11087145656347275} 08/30/2021 20:08:04 - INFO - __main__ - Step 38458: {'lr': 0.00042880247968675255, 'samples': 7383936, 'steps': 38457, 'loss/train': 1.7792470455169678} 08/30/2021 20:08:05 - INFO - __main__ - Step 38459: {'lr': 0.00042879877071135746, 'samples': 7384128, 'steps': 38458, 'loss/train': 1.6664425134658813} 08/30/2021 20:08:05 - INFO - __main__ - Step 38460: {'lr': 0.0004287950616553984, 'samples': 7384320, 'steps': 38459, 'loss/train': 1.4453438520431519} 08/30/2021 20:08:05 - INFO - __main__ - Step 38461: {'lr': 0.0004287913525188771, 'samples': 7384512, 'steps': 38460, 'loss/train': 1.2469711303710938} 08/30/2021 20:08:06 - INFO - __main__ - Step 38462: {'lr': 0.0004287876433017951, 'samples': 7384704, 'steps': 38461, 'loss/train': 1.9227299690246582} 08/30/2021 20:08:07 - INFO - __main__ - Step 38463: {'lr': 0.0004287839340041542, 'samples': 7384896, 'steps': 38462, 'loss/train': 1.9891043901443481} 08/30/2021 20:08:08 - INFO - __main__ - Step 38464: {'lr': 0.000428780224625956, 'samples': 7385088, 'steps': 38463, 'loss/train': 1.535179853439331} 08/30/2021 20:08:08 - INFO - __main__ - Step 38465: {'lr': 0.00042877651516720215, 'samples': 7385280, 'steps': 38464, 'loss/train': 1.1087923049926758} 08/30/2021 20:08:08 - INFO - __main__ - Step 38466: {'lr': 0.0004287728056278944, 'samples': 7385472, 'steps': 38465, 'loss/train': 0.8257372379302979} 08/30/2021 20:08:09 - INFO - __main__ - Step 38467: {'lr': 0.00042876909600803444, 'samples': 7385664, 'steps': 38466, 'loss/train': 1.8143433332443237} 08/30/2021 20:08:10 - INFO - __main__ - Step 38468: {'lr': 0.00042876538630762386, 'samples': 7385856, 'steps': 38467, 'loss/train': 1.3907827138900757} 08/30/2021 20:08:11 - INFO - __main__ - Step 38469: {'lr': 0.00042876167652666433, 'samples': 7386048, 'steps': 38468, 'loss/train': 1.5649192333221436} 08/30/2021 20:08:11 - INFO - __main__ - Step 38470: {'lr': 0.0004287579666651575, 'samples': 7386240, 'steps': 38469, 'loss/train': 1.6606879234313965} 08/30/2021 20:08:12 - INFO - __main__ - Step 38471: {'lr': 0.00042875425672310506, 'samples': 7386432, 'steps': 38470, 'loss/train': 1.539514183998108} 08/30/2021 20:08:12 - INFO - __main__ - Step 38472: {'lr': 0.00042875054670050885, 'samples': 7386624, 'steps': 38471, 'loss/train': 1.4509732723236084} 08/30/2021 20:08:14 - INFO - __main__ - Step 38473: {'lr': 0.00042874683659737035, 'samples': 7386816, 'steps': 38472, 'loss/train': 1.0951043367385864} 08/30/2021 20:08:15 - INFO - __main__ - Step 38474: {'lr': 0.0004287431264136913, 'samples': 7387008, 'steps': 38473, 'loss/train': 1.0203770399093628} 08/30/2021 20:08:15 - INFO - __main__ - Step 38475: {'lr': 0.0004287394161494733, 'samples': 7387200, 'steps': 38474, 'loss/train': 1.8917231559753418} 08/30/2021 20:08:16 - INFO - __main__ - Step 38476: {'lr': 0.0004287357058047181, 'samples': 7387392, 'steps': 38475, 'loss/train': 2.1725013256073} 08/30/2021 20:08:16 - INFO - __main__ - Step 38477: {'lr': 0.00042873199537942733, 'samples': 7387584, 'steps': 38476, 'loss/train': 1.5604864358901978} 08/30/2021 20:08:16 - INFO - __main__ - Step 38478: {'lr': 0.0004287282848736027, 'samples': 7387776, 'steps': 38477, 'loss/train': 0.026956936344504356} 08/30/2021 20:08:18 - INFO - __main__ - Step 38479: {'lr': 0.00042872457428724586, 'samples': 7387968, 'steps': 38478, 'loss/train': 1.6910027265548706} 08/30/2021 20:08:18 - INFO - __main__ - Step 38480: {'lr': 0.00042872086362035844, 'samples': 7388160, 'steps': 38479, 'loss/train': 1.4944396018981934} 08/30/2021 20:08:18 - INFO - __main__ - Step 38481: {'lr': 0.00042871715287294223, 'samples': 7388352, 'steps': 38480, 'loss/train': 1.3934500217437744} 08/30/2021 20:08:19 - INFO - __main__ - Step 38482: {'lr': 0.00042871344204499886, 'samples': 7388544, 'steps': 38481, 'loss/train': 0.8657522201538086} 08/30/2021 20:08:19 - INFO - __main__ - Step 38483: {'lr': 0.0004287097311365299, 'samples': 7388736, 'steps': 38482, 'loss/train': 1.3216339349746704} 08/30/2021 20:08:21 - INFO - __main__ - Step 38484: {'lr': 0.00042870602014753707, 'samples': 7388928, 'steps': 38483, 'loss/train': 1.3031517267227173} 08/30/2021 20:08:21 - INFO - __main__ - Step 38485: {'lr': 0.0004287023090780221, 'samples': 7389120, 'steps': 38484, 'loss/train': 1.4127449989318848} 08/30/2021 20:08:21 - INFO - __main__ - Step 38486: {'lr': 0.0004286985979279866, 'samples': 7389312, 'steps': 38485, 'loss/train': 1.0331435203552246} 08/30/2021 20:08:22 - INFO - __main__ - Step 38487: {'lr': 0.0004286948866974323, 'samples': 7389504, 'steps': 38486, 'loss/train': 2.846611976623535} 08/30/2021 20:08:22 - INFO - __main__ - Step 38488: {'lr': 0.0004286911753863608, 'samples': 7389696, 'steps': 38487, 'loss/train': 1.4545589685440063} 08/30/2021 20:08:24 - INFO - __main__ - Step 38489: {'lr': 0.0004286874639947739, 'samples': 7389888, 'steps': 38488, 'loss/train': 0.8318132758140564} 08/30/2021 20:08:24 - INFO - __main__ - Step 38490: {'lr': 0.0004286837525226731, 'samples': 7390080, 'steps': 38489, 'loss/train': 1.4098542928695679} 08/30/2021 20:08:24 - INFO - __main__ - Step 38491: {'lr': 0.0004286800409700602, 'samples': 7390272, 'steps': 38490, 'loss/train': 1.7316874265670776} 08/30/2021 20:08:25 - INFO - __main__ - Step 38492: {'lr': 0.0004286763293369369, 'samples': 7390464, 'steps': 38491, 'loss/train': 1.665035367012024} 08/30/2021 20:08:25 - INFO - __main__ - Step 38493: {'lr': 0.00042867261762330466, 'samples': 7390656, 'steps': 38492, 'loss/train': 1.579277515411377} 08/30/2021 20:08:25 - INFO - __main__ - Step 38494: {'lr': 0.0004286689058291654, 'samples': 7390848, 'steps': 38493, 'loss/train': 1.2257510423660278} 08/30/2021 20:08:27 - INFO - __main__ - Step 38495: {'lr': 0.00042866519395452063, 'samples': 7391040, 'steps': 38494, 'loss/train': 1.256990671157837} 08/30/2021 20:08:27 - INFO - __main__ - Step 38496: {'lr': 0.00042866148199937216, 'samples': 7391232, 'steps': 38495, 'loss/train': 1.0256305932998657} 08/30/2021 20:08:28 - INFO - __main__ - Step 38497: {'lr': 0.00042865776996372146, 'samples': 7391424, 'steps': 38496, 'loss/train': 0.6763159036636353} 08/30/2021 20:08:28 - INFO - __main__ - Step 38498: {'lr': 0.00042865405784757037, 'samples': 7391616, 'steps': 38497, 'loss/train': 1.5458842515945435} 08/30/2021 20:08:29 - INFO - __main__ - Step 38499: {'lr': 0.0004286503456509206, 'samples': 7391808, 'steps': 38498, 'loss/train': 1.0726215839385986} 08/30/2021 20:08:30 - INFO - __main__ - Step 38500: {'lr': 0.0004286466333737737, 'samples': 7392000, 'steps': 38499, 'loss/train': 1.5382964611053467} 08/30/2021 20:08:30 - INFO - __main__ - Step 38501: {'lr': 0.00042864292101613133, 'samples': 7392192, 'steps': 38500, 'loss/train': 1.2885104417800903} 08/30/2021 20:08:31 - INFO - __main__ - Step 38502: {'lr': 0.0004286392085779953, 'samples': 7392384, 'steps': 38501, 'loss/train': 1.8463127613067627} 08/30/2021 20:08:31 - INFO - __main__ - Step 38503: {'lr': 0.00042863549605936716, 'samples': 7392576, 'steps': 38502, 'loss/train': 0.9789907932281494} 08/30/2021 20:08:31 - INFO - __main__ - Step 38504: {'lr': 0.00042863178346024856, 'samples': 7392768, 'steps': 38503, 'loss/train': 1.4179446697235107} 08/30/2021 20:08:33 - INFO - __main__ - Step 38505: {'lr': 0.00042862807078064124, 'samples': 7392960, 'steps': 38504, 'loss/train': 0.829459547996521} 08/30/2021 20:08:34 - INFO - __main__ - Step 38506: {'lr': 0.00042862435802054703, 'samples': 7393152, 'steps': 38505, 'loss/train': 0.11938699334859848} 08/30/2021 20:08:34 - INFO - __main__ - Step 38507: {'lr': 0.00042862064517996723, 'samples': 7393344, 'steps': 38506, 'loss/train': 1.2859399318695068} 08/30/2021 20:08:34 - INFO - __main__ - Step 38508: {'lr': 0.00042861693225890385, 'samples': 7393536, 'steps': 38507, 'loss/train': 1.0238215923309326} 08/30/2021 20:08:35 - INFO - __main__ - Step 38509: {'lr': 0.0004286132192573584, 'samples': 7393728, 'steps': 38508, 'loss/train': 2.307140827178955} 08/30/2021 20:08:36 - INFO - __main__ - Step 38510: {'lr': 0.0004286095061753326, 'samples': 7393920, 'steps': 38509, 'loss/train': 1.4286121129989624} 08/30/2021 20:08:37 - INFO - __main__ - Step 38511: {'lr': 0.0004286057930128281, 'samples': 7394112, 'steps': 38510, 'loss/train': 1.5474827289581299} 08/30/2021 20:08:37 - INFO - __main__ - Step 38512: {'lr': 0.00042860207976984664, 'samples': 7394304, 'steps': 38511, 'loss/train': 0.9539635181427002} 08/30/2021 20:08:38 - INFO - __main__ - Step 38513: {'lr': 0.00042859836644638976, 'samples': 7394496, 'steps': 38512, 'loss/train': 0.13185752928256989} 08/30/2021 20:08:38 - INFO - __main__ - Step 38514: {'lr': 0.00042859465304245927, 'samples': 7394688, 'steps': 38513, 'loss/train': 1.589725375175476} 08/30/2021 20:08:39 - INFO - __main__ - Step 38515: {'lr': 0.00042859093955805675, 'samples': 7394880, 'steps': 38514, 'loss/train': 1.4439661502838135} 08/30/2021 20:08:40 - INFO - __main__ - Step 38516: {'lr': 0.0004285872259931839, 'samples': 7395072, 'steps': 38515, 'loss/train': 0.9839127063751221} 08/30/2021 20:08:40 - INFO - __main__ - Step 38517: {'lr': 0.00042858351234784244, 'samples': 7395264, 'steps': 38516, 'loss/train': 1.1193145513534546} 08/30/2021 20:08:41 - INFO - __main__ - Step 38518: {'lr': 0.000428579798622034, 'samples': 7395456, 'steps': 38517, 'loss/train': 1.6708089113235474} 08/30/2021 20:08:41 - INFO - __main__ - Step 38519: {'lr': 0.0004285760848157603, 'samples': 7395648, 'steps': 38518, 'loss/train': 1.71746027469635} 08/30/2021 20:08:42 - INFO - __main__ - Step 38520: {'lr': 0.00042857237092902285, 'samples': 7395840, 'steps': 38519, 'loss/train': 1.389754056930542} 08/30/2021 20:08:43 - INFO - __main__ - Step 38521: {'lr': 0.0004285686569618235, 'samples': 7396032, 'steps': 38520, 'loss/train': 1.28855299949646} 08/30/2021 20:08:43 - INFO - __main__ - Step 38522: {'lr': 0.0004285649429141639, 'samples': 7396224, 'steps': 38521, 'loss/train': 1.0698468685150146} 08/30/2021 20:08:43 - INFO - __main__ - Step 38523: {'lr': 0.00042856122878604566, 'samples': 7396416, 'steps': 38522, 'loss/train': 1.6809558868408203} 08/30/2021 20:08:44 - INFO - __main__ - Step 38524: {'lr': 0.0004285575145774705, 'samples': 7396608, 'steps': 38523, 'loss/train': 1.2037886381149292} 08/30/2021 20:08:46 - INFO - __main__ - Step 38525: {'lr': 0.00042855380028844004, 'samples': 7396800, 'steps': 38524, 'loss/train': 1.1967549324035645} 08/30/2021 20:08:46 - INFO - __main__ - Step 38526: {'lr': 0.00042855008591895607, 'samples': 7396992, 'steps': 38525, 'loss/train': 1.2843049764633179} 08/30/2021 20:08:47 - INFO - __main__ - Step 38527: {'lr': 0.00042854637146902007, 'samples': 7397184, 'steps': 38526, 'loss/train': 1.729673981666565} 08/30/2021 20:08:47 - INFO - __main__ - Step 38528: {'lr': 0.00042854265693863394, 'samples': 7397376, 'steps': 38527, 'loss/train': 1.2778013944625854} 08/30/2021 20:08:47 - INFO - __main__ - Step 38529: {'lr': 0.00042853894232779924, 'samples': 7397568, 'steps': 38528, 'loss/train': 1.6214121580123901} 08/30/2021 20:08:48 - INFO - __main__ - Step 38530: {'lr': 0.00042853522763651767, 'samples': 7397760, 'steps': 38529, 'loss/train': 1.3370741605758667} 08/30/2021 20:08:49 - INFO - __main__ - Step 38531: {'lr': 0.00042853151286479074, 'samples': 7397952, 'steps': 38530, 'loss/train': 1.225573182106018} 08/30/2021 20:08:50 - INFO - __main__ - Step 38532: {'lr': 0.0004285277980126204, 'samples': 7398144, 'steps': 38531, 'loss/train': 1.3735125064849854} 08/30/2021 20:08:50 - INFO - __main__ - Step 38533: {'lr': 0.0004285240830800081, 'samples': 7398336, 'steps': 38532, 'loss/train': 1.0428873300552368} 08/30/2021 20:08:51 - INFO - __main__ - Step 38534: {'lr': 0.00042852036806695565, 'samples': 7398528, 'steps': 38533, 'loss/train': 1.1194499731063843} 08/30/2021 20:08:51 - INFO - __main__ - Step 38535: {'lr': 0.0004285166529734647, 'samples': 7398720, 'steps': 38534, 'loss/train': 0.12767842411994934} 08/30/2021 20:08:53 - INFO - __main__ - Step 38536: {'lr': 0.0004285129377995369, 'samples': 7398912, 'steps': 38535, 'loss/train': 0.9758719801902771} 08/30/2021 20:08:53 - INFO - __main__ - Step 38537: {'lr': 0.0004285092225451739, 'samples': 7399104, 'steps': 38536, 'loss/train': 0.6560772061347961} 08/30/2021 20:08:53 - INFO - __main__ - Step 38538: {'lr': 0.0004285055072103774, 'samples': 7399296, 'steps': 38537, 'loss/train': 0.06396327912807465} 08/30/2021 20:08:54 - INFO - __main__ - Step 38539: {'lr': 0.00042850179179514906, 'samples': 7399488, 'steps': 38538, 'loss/train': 0.8640857338905334} 08/30/2021 20:08:54 - INFO - __main__ - Step 38540: {'lr': 0.00042849807629949057, 'samples': 7399680, 'steps': 38539, 'loss/train': 1.4904595613479614} 08/30/2021 20:08:56 - INFO - __main__ - Step 38541: {'lr': 0.0004284943607234036, 'samples': 7399872, 'steps': 38540, 'loss/train': 0.756790041923523} 08/30/2021 20:08:56 - INFO - __main__ - Step 38542: {'lr': 0.00042849064506688984, 'samples': 7400064, 'steps': 38541, 'loss/train': 1.6215373277664185} 08/30/2021 20:08:56 - INFO - __main__ - Step 38543: {'lr': 0.00042848692932995094, 'samples': 7400256, 'steps': 38542, 'loss/train': 1.2473387718200684} 08/30/2021 20:08:57 - INFO - __main__ - Step 38544: {'lr': 0.0004284832135125886, 'samples': 7400448, 'steps': 38543, 'loss/train': 1.1544280052185059} 08/30/2021 20:08:57 - INFO - __main__ - Step 38545: {'lr': 0.0004284794976148044, 'samples': 7400640, 'steps': 38544, 'loss/train': 0.5333156585693359} 08/30/2021 20:08:59 - INFO - __main__ - Step 38546: {'lr': 0.00042847578163660016, 'samples': 7400832, 'steps': 38545, 'loss/train': 1.554076075553894} 08/30/2021 20:08:59 - INFO - __main__ - Step 38547: {'lr': 0.0004284720655779775, 'samples': 7401024, 'steps': 38546, 'loss/train': 1.4622931480407715} 08/30/2021 20:09:00 - INFO - __main__ - Step 38548: {'lr': 0.00042846834943893806, 'samples': 7401216, 'steps': 38547, 'loss/train': 1.4342594146728516} 08/30/2021 20:09:00 - INFO - __main__ - Step 38549: {'lr': 0.0004284646332194836, 'samples': 7401408, 'steps': 38548, 'loss/train': 0.026467587798833847} 08/30/2021 20:09:00 - INFO - __main__ - Step 38550: {'lr': 0.0004284609169196156, 'samples': 7401600, 'steps': 38549, 'loss/train': 4.960337162017822} 08/30/2021 20:09:01 - INFO - __main__ - Step 38551: {'lr': 0.000428457200539336, 'samples': 7401792, 'steps': 38550, 'loss/train': 1.6371339559555054} 08/30/2021 20:09:01 - INFO - __main__ - Step 38552: {'lr': 0.0004284534840786463, 'samples': 7401984, 'steps': 38551, 'loss/train': 2.3429114818573} 08/30/2021 20:09:03 - INFO - __main__ - Step 38553: {'lr': 0.0004284497675375482, 'samples': 7402176, 'steps': 38552, 'loss/train': 1.4956729412078857} 08/30/2021 20:09:03 - INFO - __main__ - Step 38554: {'lr': 0.0004284460509160433, 'samples': 7402368, 'steps': 38553, 'loss/train': 1.6276262998580933} 08/30/2021 20:09:03 - INFO - __main__ - Step 38555: {'lr': 0.0004284423342141335, 'samples': 7402560, 'steps': 38554, 'loss/train': 1.6214299201965332} 08/30/2021 20:09:04 - INFO - __main__ - Step 38556: {'lr': 0.0004284386174318202, 'samples': 7402752, 'steps': 38555, 'loss/train': 1.9098286628723145} 08/30/2021 20:09:04 - INFO - __main__ - Step 38557: {'lr': 0.00042843490056910534, 'samples': 7402944, 'steps': 38556, 'loss/train': 1.6006876230239868} 08/30/2021 20:09:06 - INFO - __main__ - Step 38558: {'lr': 0.00042843118362599045, 'samples': 7403136, 'steps': 38557, 'loss/train': 1.0018879175186157} 08/30/2021 20:09:06 - INFO - __main__ - Step 38559: {'lr': 0.0004284274666024772, 'samples': 7403328, 'steps': 38558, 'loss/train': 0.9748728275299072} 08/30/2021 20:09:06 - INFO - __main__ - Step 38560: {'lr': 0.0004284237494985672, 'samples': 7403520, 'steps': 38559, 'loss/train': 1.503739356994629} 08/30/2021 20:09:07 - INFO - __main__ - Step 38561: {'lr': 0.0004284200323142623, 'samples': 7403712, 'steps': 38560, 'loss/train': 1.3755677938461304} 08/30/2021 20:09:07 - INFO - __main__ - Step 38562: {'lr': 0.0004284163150495641, 'samples': 7403904, 'steps': 38561, 'loss/train': 1.1172332763671875} 08/30/2021 20:09:08 - INFO - __main__ - Step 38563: {'lr': 0.00042841259770447427, 'samples': 7404096, 'steps': 38562, 'loss/train': 1.1763057708740234} 08/30/2021 20:09:09 - INFO - __main__ - Step 38564: {'lr': 0.00042840888027899436, 'samples': 7404288, 'steps': 38563, 'loss/train': 0.8469580411911011} 08/30/2021 20:09:09 - INFO - __main__ - Step 38565: {'lr': 0.0004284051627731263, 'samples': 7404480, 'steps': 38564, 'loss/train': 1.3201395273208618} 08/30/2021 20:09:10 - INFO - __main__ - Step 38566: {'lr': 0.0004284014451868716, 'samples': 7404672, 'steps': 38565, 'loss/train': 0.761022686958313} 08/30/2021 20:09:10 - INFO - __main__ - Step 38567: {'lr': 0.0004283977275202319, 'samples': 7404864, 'steps': 38566, 'loss/train': 1.4326833486557007} 08/30/2021 20:09:12 - INFO - __main__ - Step 38568: {'lr': 0.00042839400977320895, 'samples': 7405056, 'steps': 38567, 'loss/train': 0.9958623647689819} 08/30/2021 20:09:13 - INFO - __main__ - Step 38569: {'lr': 0.00042839029194580446, 'samples': 7405248, 'steps': 38568, 'loss/train': 1.4541212320327759} 08/30/2021 20:09:13 - INFO - __main__ - Step 38570: {'lr': 0.0004283865740380201, 'samples': 7405440, 'steps': 38569, 'loss/train': 1.0612595081329346} 08/30/2021 20:09:13 - INFO - __main__ - Step 38571: {'lr': 0.0004283828560498574, 'samples': 7405632, 'steps': 38570, 'loss/train': 4.319080829620361} 08/30/2021 20:09:14 - INFO - __main__ - Step 38572: {'lr': 0.0004283791379813181, 'samples': 7405824, 'steps': 38571, 'loss/train': 4.791377544403076} 08/30/2021 20:09:14 - INFO - __main__ - Step 38573: {'lr': 0.000428375419832404, 'samples': 7406016, 'steps': 38572, 'loss/train': 2.282837152481079} 08/30/2021 20:09:16 - INFO - __main__ - Step 38574: {'lr': 0.0004283717016031167, 'samples': 7406208, 'steps': 38573, 'loss/train': 2.021578788757324} 08/30/2021 20:09:16 - INFO - __main__ - Step 38575: {'lr': 0.0004283679832934578, 'samples': 7406400, 'steps': 38574, 'loss/train': 1.5614449977874756} 08/30/2021 20:09:16 - INFO - __main__ - Step 38576: {'lr': 0.0004283642649034291, 'samples': 7406592, 'steps': 38575, 'loss/train': 1.622318148612976} 08/30/2021 20:09:17 - INFO - __main__ - Step 38577: {'lr': 0.00042836054643303226, 'samples': 7406784, 'steps': 38576, 'loss/train': 0.8903332948684692} 08/30/2021 20:09:17 - INFO - __main__ - Step 38578: {'lr': 0.0004283568278822688, 'samples': 7406976, 'steps': 38577, 'loss/train': 1.5244050025939941} 08/30/2021 20:09:19 - INFO - __main__ - Step 38579: {'lr': 0.0004283531092511405, 'samples': 7407168, 'steps': 38578, 'loss/train': 2.0325591564178467} 08/30/2021 20:09:19 - INFO - __main__ - Step 38580: {'lr': 0.0004283493905396491, 'samples': 7407360, 'steps': 38579, 'loss/train': 1.0972278118133545} 08/30/2021 20:09:20 - INFO - __main__ - Step 38581: {'lr': 0.00042834567174779623, 'samples': 7407552, 'steps': 38580, 'loss/train': 1.1752090454101562} 08/30/2021 20:09:20 - INFO - __main__ - Step 38582: {'lr': 0.00042834195287558356, 'samples': 7407744, 'steps': 38581, 'loss/train': 1.4278823137283325} 08/30/2021 20:09:20 - INFO - __main__ - Step 38583: {'lr': 0.00042833823392301264, 'samples': 7407936, 'steps': 38582, 'loss/train': 1.79173743724823} 08/30/2021 20:09:23 - INFO - __main__ - Step 38584: {'lr': 0.00042833451489008537, 'samples': 7408128, 'steps': 38583, 'loss/train': 0.21683377027511597} 08/30/2021 20:09:23 - INFO - __main__ - Step 38585: {'lr': 0.00042833079577680327, 'samples': 7408320, 'steps': 38584, 'loss/train': 1.5409005880355835} 08/30/2021 20:09:24 - INFO - __main__ - Step 38586: {'lr': 0.0004283270765831682, 'samples': 7408512, 'steps': 38585, 'loss/train': 1.4707132577896118} 08/30/2021 20:09:24 - INFO - __main__ - Step 38587: {'lr': 0.00042832335730918147, 'samples': 7408704, 'steps': 38586, 'loss/train': 0.1335688829421997} 08/30/2021 20:09:24 - INFO - __main__ - Step 38588: {'lr': 0.0004283196379548451, 'samples': 7408896, 'steps': 38587, 'loss/train': 0.10015653073787689} 08/30/2021 20:09:25 - INFO - __main__ - Step 38589: {'lr': 0.0004283159185201607, 'samples': 7409088, 'steps': 38588, 'loss/train': 1.6177349090576172} 08/30/2021 20:09:26 - INFO - __main__ - Step 38590: {'lr': 0.00042831219900512984, 'samples': 7409280, 'steps': 38589, 'loss/train': 0.554823637008667} 08/30/2021 20:09:27 - INFO - __main__ - Step 38591: {'lr': 0.0004283084794097543, 'samples': 7409472, 'steps': 38590, 'loss/train': 2.556117296218872} 08/30/2021 20:09:27 - INFO - __main__ - Step 38592: {'lr': 0.00042830475973403573, 'samples': 7409664, 'steps': 38591, 'loss/train': 1.9750686883926392} 08/30/2021 20:09:28 - INFO - __main__ - Step 38593: {'lr': 0.0004283010399779757, 'samples': 7409856, 'steps': 38592, 'loss/train': 2.290078639984131} 08/30/2021 20:09:28 - INFO - __main__ - Step 38594: {'lr': 0.000428297320141576, 'samples': 7410048, 'steps': 38593, 'loss/train': 1.5426976680755615} 08/30/2021 20:09:29 - INFO - __main__ - Step 38595: {'lr': 0.0004282936002248383, 'samples': 7410240, 'steps': 38594, 'loss/train': 1.6319833993911743} 08/30/2021 20:09:30 - INFO - __main__ - Step 38596: {'lr': 0.00042828988022776426, 'samples': 7410432, 'steps': 38595, 'loss/train': 1.6357815265655518} 08/30/2021 20:09:30 - INFO - __main__ - Step 38597: {'lr': 0.00042828616015035554, 'samples': 7410624, 'steps': 38596, 'loss/train': 1.467668890953064} 08/30/2021 20:09:31 - INFO - __main__ - Step 38598: {'lr': 0.00042828243999261384, 'samples': 7410816, 'steps': 38597, 'loss/train': 1.3639193773269653} 08/30/2021 20:09:31 - INFO - __main__ - Step 38599: {'lr': 0.0004282787197545408, 'samples': 7411008, 'steps': 38598, 'loss/train': 1.701872706413269} 08/30/2021 20:09:33 - INFO - __main__ - Step 38600: {'lr': 0.00042827499943613815, 'samples': 7411200, 'steps': 38599, 'loss/train': 1.4856274127960205} 08/30/2021 20:09:33 - INFO - __main__ - Step 38601: {'lr': 0.00042827127903740747, 'samples': 7411392, 'steps': 38600, 'loss/train': 2.1299808025360107} 08/30/2021 20:09:34 - INFO - __main__ - Step 38602: {'lr': 0.00042826755855835053, 'samples': 7411584, 'steps': 38601, 'loss/train': 1.2858208417892456} 08/30/2021 20:09:34 - INFO - __main__ - Step 38603: {'lr': 0.00042826383799896906, 'samples': 7411776, 'steps': 38602, 'loss/train': 1.8762195110321045} 08/30/2021 20:09:35 - INFO - __main__ - Step 38604: {'lr': 0.0004282601173592646, 'samples': 7411968, 'steps': 38603, 'loss/train': 1.772971510887146} 08/30/2021 20:09:35 - INFO - __main__ - Step 38605: {'lr': 0.0004282563966392389, 'samples': 7412160, 'steps': 38604, 'loss/train': 0.21396401524543762} 08/30/2021 20:09:37 - INFO - __main__ - Step 38606: {'lr': 0.00042825267583889354, 'samples': 7412352, 'steps': 38605, 'loss/train': 0.1161898598074913} 08/30/2021 20:09:38 - INFO - __main__ - Step 38607: {'lr': 0.00042824895495823033, 'samples': 7412544, 'steps': 38606, 'loss/train': 1.6667474508285522} 08/30/2021 20:09:38 - INFO - __main__ - Step 38608: {'lr': 0.0004282452339972509, 'samples': 7412736, 'steps': 38607, 'loss/train': 2.1116271018981934} 08/30/2021 20:09:38 - INFO - __main__ - Step 38609: {'lr': 0.00042824151295595695, 'samples': 7412928, 'steps': 38608, 'loss/train': 1.9374371767044067} 08/30/2021 20:09:39 - INFO - __main__ - Step 38610: {'lr': 0.0004282377918343501, 'samples': 7413120, 'steps': 38609, 'loss/train': 0.6436307430267334} 08/30/2021 20:09:39 - INFO - __main__ - Step 38611: {'lr': 0.00042823407063243197, 'samples': 7413312, 'steps': 38610, 'loss/train': 0.5573675036430359} 08/30/2021 20:09:41 - INFO - __main__ - Step 38612: {'lr': 0.0004282303493502044, 'samples': 7413504, 'steps': 38611, 'loss/train': 1.6397336721420288} 08/30/2021 20:09:41 - INFO - __main__ - Step 38613: {'lr': 0.000428226627987669, 'samples': 7413696, 'steps': 38612, 'loss/train': 1.955654501914978} 08/30/2021 20:09:41 - INFO - __main__ - Step 38614: {'lr': 0.0004282229065448273, 'samples': 7413888, 'steps': 38613, 'loss/train': 1.315771460533142} 08/30/2021 20:09:42 - INFO - __main__ - Step 38615: {'lr': 0.0004282191850216812, 'samples': 7414080, 'steps': 38614, 'loss/train': 1.478628396987915} 08/30/2021 20:09:42 - INFO - __main__ - Step 38616: {'lr': 0.00042821546341823236, 'samples': 7414272, 'steps': 38615, 'loss/train': 1.2186205387115479} 08/30/2021 20:09:44 - INFO - __main__ - Step 38617: {'lr': 0.0004282117417344823, 'samples': 7414464, 'steps': 38616, 'loss/train': 2.0446653366088867} 08/30/2021 20:09:44 - INFO - __main__ - Step 38618: {'lr': 0.00042820801997043277, 'samples': 7414656, 'steps': 38617, 'loss/train': 1.4565842151641846} 08/30/2021 20:09:45 - INFO - __main__ - Step 38619: {'lr': 0.0004282042981260855, 'samples': 7414848, 'steps': 38618, 'loss/train': 1.7942994832992554} 08/30/2021 20:09:45 - INFO - __main__ - Step 38620: {'lr': 0.00042820057620144214, 'samples': 7415040, 'steps': 38619, 'loss/train': 1.426952838897705} 08/30/2021 20:09:45 - INFO - __main__ - Step 38621: {'lr': 0.00042819685419650427, 'samples': 7415232, 'steps': 38620, 'loss/train': 2.0606207847595215} 08/30/2021 20:09:47 - INFO - __main__ - Step 38622: {'lr': 0.0004281931321112737, 'samples': 7415424, 'steps': 38621, 'loss/train': 1.652417778968811} 08/30/2021 20:09:47 - INFO - __main__ - Step 38623: {'lr': 0.0004281894099457521, 'samples': 7415616, 'steps': 38622, 'loss/train': 0.8534078598022461} 08/30/2021 20:09:48 - INFO - __main__ - Step 38624: {'lr': 0.00042818568769994103, 'samples': 7415808, 'steps': 38623, 'loss/train': 1.6389437913894653} 08/30/2021 20:09:48 - INFO - __main__ - Step 38625: {'lr': 0.00042818196537384225, 'samples': 7416000, 'steps': 38624, 'loss/train': 1.456589698791504} 08/30/2021 20:09:48 - INFO - __main__ - Step 38626: {'lr': 0.0004281782429674574, 'samples': 7416192, 'steps': 38625, 'loss/train': 1.4333062171936035} 08/30/2021 20:09:50 - INFO - __main__ - Step 38627: {'lr': 0.0004281745204807882, 'samples': 7416384, 'steps': 38626, 'loss/train': 0.43587514758110046} 08/30/2021 20:09:50 - INFO - __main__ - Step 38628: {'lr': 0.00042817079791383636, 'samples': 7416576, 'steps': 38627, 'loss/train': 2.1891889572143555} 08/30/2021 20:09:51 - INFO - __main__ - Step 38629: {'lr': 0.00042816707526660346, 'samples': 7416768, 'steps': 38628, 'loss/train': 1.2977513074874878} 08/30/2021 20:09:51 - INFO - __main__ - Step 38630: {'lr': 0.00042816335253909125, 'samples': 7416960, 'steps': 38629, 'loss/train': 1.475739598274231} 08/30/2021 20:09:51 - INFO - __main__ - Step 38631: {'lr': 0.00042815962973130134, 'samples': 7417152, 'steps': 38630, 'loss/train': 1.857330083847046} 08/30/2021 20:09:53 - INFO - __main__ - Step 38632: {'lr': 0.00042815590684323554, 'samples': 7417344, 'steps': 38631, 'loss/train': 1.4106769561767578} 08/30/2021 20:09:53 - INFO - __main__ - Step 38633: {'lr': 0.00042815218387489535, 'samples': 7417536, 'steps': 38632, 'loss/train': 1.4453449249267578} 08/30/2021 20:09:54 - INFO - __main__ - Step 38634: {'lr': 0.00042814846082628256, 'samples': 7417728, 'steps': 38633, 'loss/train': 1.7522774934768677} 08/30/2021 20:09:54 - INFO - __main__ - Step 38635: {'lr': 0.0004281447376973988, 'samples': 7417920, 'steps': 38634, 'loss/train': 1.7621123790740967} 08/30/2021 20:09:54 - INFO - __main__ - Step 38636: {'lr': 0.00042814101448824583, 'samples': 7418112, 'steps': 38635, 'loss/train': 1.2906841039657593} 08/30/2021 20:09:56 - INFO - __main__ - Step 38637: {'lr': 0.0004281372911988253, 'samples': 7418304, 'steps': 38636, 'loss/train': 0.8466001152992249} 08/30/2021 20:09:57 - INFO - __main__ - Step 38638: {'lr': 0.0004281335678291387, 'samples': 7418496, 'steps': 38637, 'loss/train': 1.6220788955688477} 08/30/2021 20:09:57 - INFO - __main__ - Step 38639: {'lr': 0.000428129844379188, 'samples': 7418688, 'steps': 38638, 'loss/train': 1.6182951927185059} 08/30/2021 20:09:58 - INFO - __main__ - Step 38640: {'lr': 0.0004281261208489747, 'samples': 7418880, 'steps': 38639, 'loss/train': 1.4365603923797607} 08/30/2021 20:09:58 - INFO - __main__ - Step 38641: {'lr': 0.0004281223972385004, 'samples': 7419072, 'steps': 38640, 'loss/train': 1.4633879661560059} 08/30/2021 20:09:58 - INFO - __main__ - Step 38642: {'lr': 0.00042811867354776705, 'samples': 7419264, 'steps': 38641, 'loss/train': 1.6247738599777222} 08/30/2021 20:10:00 - INFO - __main__ - Step 38643: {'lr': 0.0004281149497767761, 'samples': 7419456, 'steps': 38642, 'loss/train': 0.5863242745399475} 08/30/2021 20:10:01 - INFO - __main__ - Step 38644: {'lr': 0.00042811122592552943, 'samples': 7419648, 'steps': 38643, 'loss/train': 1.9961851835250854} 08/30/2021 20:10:01 - INFO - __main__ - Step 38645: {'lr': 0.0004281075019940285, 'samples': 7419840, 'steps': 38644, 'loss/train': 1.3115507364273071} 08/30/2021 20:10:01 - INFO - __main__ - Step 38646: {'lr': 0.00042810377798227506, 'samples': 7420032, 'steps': 38645, 'loss/train': 1.6012402772903442} 08/30/2021 20:10:02 - INFO - __main__ - Step 38647: {'lr': 0.00042810005389027077, 'samples': 7420224, 'steps': 38646, 'loss/train': 1.3315033912658691} 08/30/2021 20:10:03 - INFO - __main__ - Step 38648: {'lr': 0.0004280963297180174, 'samples': 7420416, 'steps': 38647, 'loss/train': 1.3940638303756714} 08/30/2021 20:10:04 - INFO - __main__ - Step 38649: {'lr': 0.0004280926054655165, 'samples': 7420608, 'steps': 38648, 'loss/train': 1.7996569871902466} 08/30/2021 20:10:04 - INFO - __main__ - Step 38650: {'lr': 0.00042808888113277, 'samples': 7420800, 'steps': 38649, 'loss/train': 1.0887048244476318} 08/30/2021 20:10:04 - INFO - __main__ - Step 38651: {'lr': 0.0004280851567197792, 'samples': 7420992, 'steps': 38650, 'loss/train': 1.5012034177780151} 08/30/2021 20:10:05 - INFO - __main__ - Step 38652: {'lr': 0.0004280814322265461, 'samples': 7421184, 'steps': 38651, 'loss/train': 1.7306108474731445} 08/30/2021 20:10:06 - INFO - __main__ - Step 38653: {'lr': 0.00042807770765307217, 'samples': 7421376, 'steps': 38652, 'loss/train': 1.6279971599578857} 08/30/2021 20:10:07 - INFO - __main__ - Step 38654: {'lr': 0.00042807398299935927, 'samples': 7421568, 'steps': 38653, 'loss/train': 1.1435880661010742} 08/30/2021 20:10:07 - INFO - __main__ - Step 38655: {'lr': 0.0004280702582654089, 'samples': 7421760, 'steps': 38654, 'loss/train': 1.231977939605713} 08/30/2021 20:10:08 - INFO - __main__ - Step 38656: {'lr': 0.00042806653345122287, 'samples': 7421952, 'steps': 38655, 'loss/train': 1.288036823272705} 08/30/2021 20:10:08 - INFO - __main__ - Step 38657: {'lr': 0.0004280628085568028, 'samples': 7422144, 'steps': 38656, 'loss/train': 0.7506770491600037} 08/30/2021 20:10:09 - INFO - __main__ - Step 38658: {'lr': 0.0004280590835821503, 'samples': 7422336, 'steps': 38657, 'loss/train': 0.6064561605453491} 08/30/2021 20:10:10 - INFO - __main__ - Step 38659: {'lr': 0.0004280553585272672, 'samples': 7422528, 'steps': 38658, 'loss/train': 1.281550407409668} 08/30/2021 20:10:10 - INFO - __main__ - Step 38660: {'lr': 0.0004280516333921551, 'samples': 7422720, 'steps': 38659, 'loss/train': 1.726662039756775} 08/30/2021 20:10:11 - INFO - __main__ - Step 38661: {'lr': 0.00042804790817681574, 'samples': 7422912, 'steps': 38660, 'loss/train': 1.4874367713928223} 08/30/2021 20:10:11 - INFO - __main__ - Step 38662: {'lr': 0.0004280441828812506, 'samples': 7423104, 'steps': 38661, 'loss/train': 1.0482029914855957} 08/30/2021 20:10:11 - INFO - __main__ - Step 38663: {'lr': 0.0004280404575054616, 'samples': 7423296, 'steps': 38662, 'loss/train': 1.4116946458816528} 08/30/2021 20:10:13 - INFO - __main__ - Step 38664: {'lr': 0.00042803673204945027, 'samples': 7423488, 'steps': 38663, 'loss/train': 2.0071163177490234} 08/30/2021 20:10:13 - INFO - __main__ - Step 38665: {'lr': 0.0004280330065132184, 'samples': 7423680, 'steps': 38664, 'loss/train': 1.448816180229187} 08/30/2021 20:10:14 - INFO - __main__ - Step 38666: {'lr': 0.0004280292808967675, 'samples': 7423872, 'steps': 38665, 'loss/train': 0.9995388388633728} 08/30/2021 20:10:14 - INFO - __main__ - Step 38667: {'lr': 0.00042802555520009945, 'samples': 7424064, 'steps': 38666, 'loss/train': 1.0025697946548462} 08/30/2021 20:10:14 - INFO - __main__ - Step 38668: {'lr': 0.00042802182942321576, 'samples': 7424256, 'steps': 38667, 'loss/train': 1.261796236038208} 08/30/2021 20:10:16 - INFO - __main__ - Step 38669: {'lr': 0.0004280181035661182, 'samples': 7424448, 'steps': 38668, 'loss/train': 2.285823106765747} 08/30/2021 20:10:16 - INFO - __main__ - Step 38670: {'lr': 0.0004280143776288085, 'samples': 7424640, 'steps': 38669, 'loss/train': 1.179396152496338} 08/30/2021 20:10:17 - INFO - __main__ - Step 38671: {'lr': 0.00042801065161128814, 'samples': 7424832, 'steps': 38670, 'loss/train': 1.3689016103744507} 08/30/2021 20:10:17 - INFO - __main__ - Step 38672: {'lr': 0.000428006925513559, 'samples': 7425024, 'steps': 38671, 'loss/train': 1.0872362852096558} 08/30/2021 20:10:17 - INFO - __main__ - Step 38673: {'lr': 0.0004280031993356227, 'samples': 7425216, 'steps': 38672, 'loss/train': 1.3017916679382324} 08/30/2021 20:10:19 - INFO - __main__ - Step 38674: {'lr': 0.00042799947307748087, 'samples': 7425408, 'steps': 38673, 'loss/train': 1.8740603923797607} 08/30/2021 20:10:20 - INFO - __main__ - Step 38675: {'lr': 0.0004279957467391353, 'samples': 7425600, 'steps': 38674, 'loss/train': 1.3275476694107056} 08/30/2021 20:10:20 - INFO - __main__ - Step 38676: {'lr': 0.0004279920203205875, 'samples': 7425792, 'steps': 38675, 'loss/train': 0.6729128956794739} 08/30/2021 20:10:20 - INFO - __main__ - Step 38677: {'lr': 0.0004279882938218393, 'samples': 7425984, 'steps': 38676, 'loss/train': 1.571664571762085} 08/30/2021 20:10:21 - INFO - __main__ - Step 38678: {'lr': 0.00042798456724289227, 'samples': 7426176, 'steps': 38677, 'loss/train': 1.4537087678909302} 08/30/2021 20:10:22 - INFO - __main__ - Step 38679: {'lr': 0.0004279808405837482, 'samples': 7426368, 'steps': 38678, 'loss/train': 0.09544751048088074} 08/30/2021 20:10:23 - INFO - __main__ - Step 38680: {'lr': 0.00042797711384440863, 'samples': 7426560, 'steps': 38679, 'loss/train': 1.1798216104507446} 08/30/2021 20:10:23 - INFO - __main__ - Step 38681: {'lr': 0.0004279733870248754, 'samples': 7426752, 'steps': 38680, 'loss/train': 1.4335826635360718} 08/30/2021 20:10:23 - INFO - __main__ - Step 38682: {'lr': 0.00042796966012515007, 'samples': 7426944, 'steps': 38681, 'loss/train': 1.7576112747192383} 08/30/2021 20:10:24 - INFO - __main__ - Step 38683: {'lr': 0.00042796593314523435, 'samples': 7427136, 'steps': 38682, 'loss/train': 1.6155834197998047} 08/30/2021 20:10:25 - INFO - __main__ - Step 38684: {'lr': 0.0004279622060851299, 'samples': 7427328, 'steps': 38683, 'loss/train': 1.3129968643188477} 08/30/2021 20:10:26 - INFO - __main__ - Step 38685: {'lr': 0.0004279584789448385, 'samples': 7427520, 'steps': 38684, 'loss/train': 1.273803949356079} 08/30/2021 20:10:26 - INFO - __main__ - Step 38686: {'lr': 0.0004279547517243617, 'samples': 7427712, 'steps': 38685, 'loss/train': 1.3160357475280762} 08/30/2021 20:10:27 - INFO - __main__ - Step 38687: {'lr': 0.00042795102442370127, 'samples': 7427904, 'steps': 38686, 'loss/train': 1.5185521841049194} 08/30/2021 20:10:27 - INFO - __main__ - Step 38688: {'lr': 0.0004279472970428588, 'samples': 7428096, 'steps': 38687, 'loss/train': 1.4837063550949097} 08/30/2021 20:10:27 - INFO - __main__ - Step 38689: {'lr': 0.0004279435695818361, 'samples': 7428288, 'steps': 38688, 'loss/train': 0.05492337793111801} 08/30/2021 20:10:30 - INFO - __main__ - Step 38690: {'lr': 0.00042793984204063477, 'samples': 7428480, 'steps': 38689, 'loss/train': 1.6588153839111328} 08/30/2021 20:10:30 - INFO - __main__ - Step 38691: {'lr': 0.0004279361144192565, 'samples': 7428672, 'steps': 38690, 'loss/train': 0.08101096004247665} 08/30/2021 20:10:31 - INFO - __main__ - Step 38692: {'lr': 0.00042793238671770285, 'samples': 7428864, 'steps': 38691, 'loss/train': 1.7580540180206299} 08/30/2021 20:10:31 - INFO - __main__ - Step 38693: {'lr': 0.0004279286589359757, 'samples': 7429056, 'steps': 38692, 'loss/train': 0.9432997107505798} 08/30/2021 20:10:31 - INFO - __main__ - Step 38694: {'lr': 0.00042792493107407666, 'samples': 7429248, 'steps': 38693, 'loss/train': 0.04007983207702637} 08/30/2021 20:10:32 - INFO - __main__ - Step 38695: {'lr': 0.0004279212031320073, 'samples': 7429440, 'steps': 38694, 'loss/train': 1.4492865800857544} 08/30/2021 20:10:33 - INFO - __main__ - Step 38696: {'lr': 0.00042791747510976955, 'samples': 7429632, 'steps': 38695, 'loss/train': 1.645767331123352} 08/30/2021 20:10:34 - INFO - __main__ - Step 38697: {'lr': 0.0004279137470073648, 'samples': 7429824, 'steps': 38696, 'loss/train': 1.941857099533081} 08/30/2021 20:10:34 - INFO - __main__ - Step 38698: {'lr': 0.00042791001882479485, 'samples': 7430016, 'steps': 38697, 'loss/train': 1.4204496145248413} 08/30/2021 20:10:34 - INFO - __main__ - Step 38699: {'lr': 0.0004279062905620614, 'samples': 7430208, 'steps': 38698, 'loss/train': 1.3363687992095947} 08/30/2021 20:10:35 - INFO - __main__ - Step 38700: {'lr': 0.0004279025622191662, 'samples': 7430400, 'steps': 38699, 'loss/train': 1.0146483182907104} 08/30/2021 20:10:36 - INFO - __main__ - Step 38701: {'lr': 0.00042789883379611084, 'samples': 7430592, 'steps': 38700, 'loss/train': 1.5381847620010376} 08/30/2021 20:10:37 - INFO - __main__ - Step 38702: {'lr': 0.000427895105292897, 'samples': 7430784, 'steps': 38701, 'loss/train': 1.6289020776748657} 08/30/2021 20:10:37 - INFO - __main__ - Step 38703: {'lr': 0.00042789137670952627, 'samples': 7430976, 'steps': 38702, 'loss/train': 1.2194492816925049} 08/30/2021 20:10:37 - INFO - __main__ - Step 38704: {'lr': 0.00042788764804600055, 'samples': 7431168, 'steps': 38703, 'loss/train': 1.3122613430023193} 08/30/2021 20:10:38 - INFO - __main__ - Step 38705: {'lr': 0.0004278839193023214, 'samples': 7431360, 'steps': 38704, 'loss/train': 0.5256453156471252} 08/30/2021 20:10:38 - INFO - __main__ - Step 38706: {'lr': 0.0004278801904784904, 'samples': 7431552, 'steps': 38705, 'loss/train': 1.7385294437408447} 08/30/2021 20:10:40 - INFO - __main__ - Step 38707: {'lr': 0.00042787646157450946, 'samples': 7431744, 'steps': 38706, 'loss/train': 0.43294215202331543} 08/30/2021 20:10:40 - INFO - __main__ - Step 38708: {'lr': 0.00042787273259038, 'samples': 7431936, 'steps': 38707, 'loss/train': 1.0498179197311401} 08/30/2021 20:10:40 - INFO - __main__ - Step 38709: {'lr': 0.00042786900352610393, 'samples': 7432128, 'steps': 38708, 'loss/train': 0.6126086711883545} 08/30/2021 20:10:41 - INFO - __main__ - Step 38710: {'lr': 0.0004278652743816828, 'samples': 7432320, 'steps': 38709, 'loss/train': 1.7270009517669678} 08/30/2021 20:10:41 - INFO - __main__ - Step 38711: {'lr': 0.00042786154515711826, 'samples': 7432512, 'steps': 38710, 'loss/train': 1.660953402519226} 08/30/2021 20:10:43 - INFO - __main__ - Step 38712: {'lr': 0.0004278578158524121, 'samples': 7432704, 'steps': 38711, 'loss/train': 0.07817649096250534} 08/30/2021 20:10:43 - INFO - __main__ - Step 38713: {'lr': 0.00042785408646756594, 'samples': 7432896, 'steps': 38712, 'loss/train': 0.9201869964599609} 08/30/2021 20:10:43 - INFO - __main__ - Step 38714: {'lr': 0.0004278503570025816, 'samples': 7433088, 'steps': 38713, 'loss/train': 1.5371040105819702} 08/30/2021 20:10:44 - INFO - __main__ - Step 38715: {'lr': 0.0004278466274574605, 'samples': 7433280, 'steps': 38714, 'loss/train': 1.8116850852966309} 08/30/2021 20:10:44 - INFO - __main__ - Step 38716: {'lr': 0.0004278428978322044, 'samples': 7433472, 'steps': 38715, 'loss/train': 1.53053879737854} 08/30/2021 20:10:46 - INFO - __main__ - Step 38717: {'lr': 0.00042783916812681516, 'samples': 7433664, 'steps': 38716, 'loss/train': 1.78085458278656} 08/30/2021 20:10:46 - INFO - __main__ - Step 38718: {'lr': 0.0004278354383412943, 'samples': 7433856, 'steps': 38717, 'loss/train': 1.4068180322647095} 08/30/2021 20:10:46 - INFO - __main__ - Step 38719: {'lr': 0.0004278317084756435, 'samples': 7434048, 'steps': 38718, 'loss/train': 1.5187715291976929} 08/30/2021 20:10:47 - INFO - __main__ - Step 38720: {'lr': 0.00042782797852986454, 'samples': 7434240, 'steps': 38719, 'loss/train': 1.3090986013412476} 08/30/2021 20:10:47 - INFO - __main__ - Step 38721: {'lr': 0.00042782424850395894, 'samples': 7434432, 'steps': 38720, 'loss/train': 1.1511976718902588} 08/30/2021 20:10:49 - INFO - __main__ - Step 38722: {'lr': 0.00042782051839792857, 'samples': 7434624, 'steps': 38721, 'loss/train': 1.9558556079864502} 08/30/2021 20:10:49 - INFO - __main__ - Step 38723: {'lr': 0.000427816788211775, 'samples': 7434816, 'steps': 38722, 'loss/train': 0.044451870024204254} 08/30/2021 20:10:50 - INFO - __main__ - Step 38724: {'lr': 0.00042781305794549994, 'samples': 7435008, 'steps': 38723, 'loss/train': 1.308264136314392} 08/30/2021 20:10:50 - INFO - __main__ - Step 38725: {'lr': 0.00042780932759910504, 'samples': 7435200, 'steps': 38724, 'loss/train': 1.4418635368347168} 08/30/2021 20:10:50 - INFO - __main__ - Step 38726: {'lr': 0.00042780559717259194, 'samples': 7435392, 'steps': 38725, 'loss/train': 1.03141450881958} 08/30/2021 20:10:52 - INFO - __main__ - Step 38727: {'lr': 0.0004278018666659624, 'samples': 7435584, 'steps': 38726, 'loss/train': 1.353161096572876} 08/30/2021 20:10:52 - INFO - __main__ - Step 38728: {'lr': 0.0004277981360792182, 'samples': 7435776, 'steps': 38727, 'loss/train': 1.473778247833252} 08/30/2021 20:10:53 - INFO - __main__ - Step 38729: {'lr': 0.0004277944054123608, 'samples': 7435968, 'steps': 38728, 'loss/train': 0.8205475211143494} 08/30/2021 20:10:53 - INFO - __main__ - Step 38730: {'lr': 0.000427790674665392, 'samples': 7436160, 'steps': 38729, 'loss/train': 1.5710917711257935} 08/30/2021 20:10:53 - INFO - __main__ - Step 38731: {'lr': 0.00042778694383831354, 'samples': 7436352, 'steps': 38730, 'loss/train': 1.616429090499878} 08/30/2021 20:10:55 - INFO - __main__ - Step 38732: {'lr': 0.0004277832129311269, 'samples': 7436544, 'steps': 38731, 'loss/train': 1.319718837738037} 08/30/2021 20:10:55 - INFO - __main__ - Step 38733: {'lr': 0.000427779481943834, 'samples': 7436736, 'steps': 38732, 'loss/train': 1.6281687021255493} 08/30/2021 20:10:56 - INFO - __main__ - Step 38734: {'lr': 0.0004277757508764363, 'samples': 7436928, 'steps': 38733, 'loss/train': 1.7237601280212402} 08/30/2021 20:10:56 - INFO - __main__ - Step 38735: {'lr': 0.00042777201972893564, 'samples': 7437120, 'steps': 38734, 'loss/train': 1.6055048704147339} 08/30/2021 20:10:56 - INFO - __main__ - Step 38736: {'lr': 0.00042776828850133364, 'samples': 7437312, 'steps': 38735, 'loss/train': 1.5065596103668213} 08/30/2021 20:10:57 - INFO - __main__ - Step 38737: {'lr': 0.0004277645571936321, 'samples': 7437504, 'steps': 38736, 'loss/train': 1.191209316253662} 08/30/2021 20:10:58 - INFO - __main__ - Step 38738: {'lr': 0.0004277608258058324, 'samples': 7437696, 'steps': 38737, 'loss/train': 1.4561070203781128} 08/30/2021 20:10:59 - INFO - __main__ - Step 38739: {'lr': 0.00042775709433793657, 'samples': 7437888, 'steps': 38738, 'loss/train': 1.4625935554504395} 08/30/2021 20:10:59 - INFO - __main__ - Step 38740: {'lr': 0.0004277533627899461, 'samples': 7438080, 'steps': 38739, 'loss/train': 1.3131028413772583} 08/30/2021 20:10:59 - INFO - __main__ - Step 38741: {'lr': 0.00042774963116186274, 'samples': 7438272, 'steps': 38740, 'loss/train': 1.5198599100112915} 08/30/2021 20:11:00 - INFO - __main__ - Step 38742: {'lr': 0.000427745899453688, 'samples': 7438464, 'steps': 38741, 'loss/train': 0.0744587630033493} 08/30/2021 20:11:01 - INFO - __main__ - Step 38743: {'lr': 0.00042774216766542386, 'samples': 7438656, 'steps': 38742, 'loss/train': 1.6099133491516113} 08/30/2021 20:11:02 - INFO - __main__ - Step 38744: {'lr': 0.0004277384357970717, 'samples': 7438848, 'steps': 38743, 'loss/train': 1.8320605754852295} 08/30/2021 20:11:02 - INFO - __main__ - Step 38745: {'lr': 0.00042773470384863344, 'samples': 7439040, 'steps': 38744, 'loss/train': 0.9649897813796997} 08/30/2021 20:11:03 - INFO - __main__ - Step 38746: {'lr': 0.0004277309718201107, 'samples': 7439232, 'steps': 38745, 'loss/train': 2.1139719486236572} 08/30/2021 20:11:03 - INFO - __main__ - Step 38747: {'lr': 0.000427727239711505, 'samples': 7439424, 'steps': 38746, 'loss/train': 1.3948806524276733} 08/30/2021 20:11:05 - INFO - __main__ - Step 38748: {'lr': 0.00042772350752281823, 'samples': 7439616, 'steps': 38747, 'loss/train': 1.5157158374786377} 08/30/2021 20:11:06 - INFO - __main__ - Step 38749: {'lr': 0.000427719775254052, 'samples': 7439808, 'steps': 38748, 'loss/train': 1.089264988899231} 08/30/2021 20:11:06 - INFO - __main__ - Step 38750: {'lr': 0.00042771604290520795, 'samples': 7440000, 'steps': 38749, 'loss/train': 1.44356369972229} 08/30/2021 20:11:06 - INFO - __main__ - Step 38751: {'lr': 0.00042771231047628776, 'samples': 7440192, 'steps': 38750, 'loss/train': 1.9884164333343506} 08/30/2021 20:11:08 - INFO - __main__ - Step 38752: {'lr': 0.0004277085779672932, 'samples': 7440384, 'steps': 38751, 'loss/train': 0.7363114953041077} 08/30/2021 20:11:08 - INFO - __main__ - Step 38753: {'lr': 0.0004277048453782259, 'samples': 7440576, 'steps': 38752, 'loss/train': 1.1619985103607178} 08/30/2021 20:11:09 - INFO - __main__ - Step 38754: {'lr': 0.0004277011127090875, 'samples': 7440768, 'steps': 38753, 'loss/train': 1.361302375793457} 08/30/2021 20:11:09 - INFO - __main__ - Step 38755: {'lr': 0.0004276973799598798, 'samples': 7440960, 'steps': 38754, 'loss/train': 1.1801483631134033} 08/30/2021 20:11:09 - INFO - __main__ - Step 38756: {'lr': 0.0004276936471306043, 'samples': 7441152, 'steps': 38755, 'loss/train': 1.3994168043136597} 08/30/2021 20:11:11 - INFO - __main__ - Step 38757: {'lr': 0.00042768991422126285, 'samples': 7441344, 'steps': 38756, 'loss/train': 1.5156992673873901} 08/30/2021 20:11:12 - INFO - __main__ - Step 38758: {'lr': 0.00042768618123185703, 'samples': 7441536, 'steps': 38757, 'loss/train': 0.6526063680648804} 08/30/2021 20:11:12 - INFO - __main__ - Step 38759: {'lr': 0.00042768244816238863, 'samples': 7441728, 'steps': 38758, 'loss/train': 1.3877465724945068} 08/30/2021 20:11:12 - INFO - __main__ - Step 38760: {'lr': 0.00042767871501285916, 'samples': 7441920, 'steps': 38759, 'loss/train': 1.3566300868988037} 08/30/2021 20:11:13 - INFO - __main__ - Step 38761: {'lr': 0.00042767498178327047, 'samples': 7442112, 'steps': 38760, 'loss/train': 1.9401377439498901} 08/30/2021 20:11:13 - INFO - __main__ - Step 38762: {'lr': 0.00042767124847362413, 'samples': 7442304, 'steps': 38761, 'loss/train': 1.9453312158584595} 08/30/2021 20:11:15 - INFO - __main__ - Step 38763: {'lr': 0.00042766751508392187, 'samples': 7442496, 'steps': 38762, 'loss/train': 1.4461653232574463} 08/30/2021 20:11:15 - INFO - __main__ - Step 38764: {'lr': 0.00042766378161416543, 'samples': 7442688, 'steps': 38763, 'loss/train': 1.3366578817367554} 08/30/2021 20:11:15 - INFO - __main__ - Step 38765: {'lr': 0.00042766004806435643, 'samples': 7442880, 'steps': 38764, 'loss/train': 1.4643217325210571} 08/30/2021 20:11:16 - INFO - __main__ - Step 38766: {'lr': 0.0004276563144344965, 'samples': 7443072, 'steps': 38765, 'loss/train': 0.7589820623397827} 08/30/2021 20:11:16 - INFO - __main__ - Step 38767: {'lr': 0.00042765258072458733, 'samples': 7443264, 'steps': 38766, 'loss/train': 1.4181276559829712} 08/30/2021 20:11:18 - INFO - __main__ - Step 38768: {'lr': 0.00042764884693463075, 'samples': 7443456, 'steps': 38767, 'loss/train': 1.443307638168335} 08/30/2021 20:11:18 - INFO - __main__ - Step 38769: {'lr': 0.0004276451130646283, 'samples': 7443648, 'steps': 38768, 'loss/train': 1.3338168859481812} 08/30/2021 20:11:18 - INFO - __main__ - Step 38770: {'lr': 0.0004276413791145817, 'samples': 7443840, 'steps': 38769, 'loss/train': 1.2715299129486084} 08/30/2021 20:11:19 - INFO - __main__ - Step 38771: {'lr': 0.00042763764508449263, 'samples': 7444032, 'steps': 38770, 'loss/train': 1.8022055625915527} 08/30/2021 20:11:19 - INFO - __main__ - Step 38772: {'lr': 0.0004276339109743628, 'samples': 7444224, 'steps': 38771, 'loss/train': 1.31218421459198} 08/30/2021 20:11:20 - INFO - __main__ - Step 38773: {'lr': 0.0004276301767841939, 'samples': 7444416, 'steps': 38772, 'loss/train': 2.7003791332244873} 08/30/2021 20:11:21 - INFO - __main__ - Step 38774: {'lr': 0.00042762644251398755, 'samples': 7444608, 'steps': 38773, 'loss/train': 1.368554949760437} 08/30/2021 20:11:21 - INFO - __main__ - Step 38775: {'lr': 0.0004276227081637454, 'samples': 7444800, 'steps': 38774, 'loss/train': 1.202033519744873} 08/30/2021 20:11:22 - INFO - __main__ - Step 38776: {'lr': 0.00042761897373346923, 'samples': 7444992, 'steps': 38775, 'loss/train': 1.1454054117202759} 08/30/2021 20:11:22 - INFO - __main__ - Step 38777: {'lr': 0.0004276152392231608, 'samples': 7445184, 'steps': 38776, 'loss/train': 1.5549793243408203} 08/30/2021 20:11:22 - INFO - __main__ - Step 38778: {'lr': 0.00042761150463282164, 'samples': 7445376, 'steps': 38777, 'loss/train': 1.290086269378662} 08/30/2021 20:11:24 - INFO - __main__ - Step 38779: {'lr': 0.0004276077699624534, 'samples': 7445568, 'steps': 38778, 'loss/train': 1.5495622158050537} 08/30/2021 20:11:25 - INFO - __main__ - Step 38780: {'lr': 0.0004276040352120578, 'samples': 7445760, 'steps': 38779, 'loss/train': 1.4970108270645142} 08/30/2021 20:11:25 - INFO - __main__ - Step 38781: {'lr': 0.0004276003003816367, 'samples': 7445952, 'steps': 38780, 'loss/train': 1.9532743692398071} 08/30/2021 20:11:25 - INFO - __main__ - Step 38782: {'lr': 0.0004275965654711916, 'samples': 7446144, 'steps': 38781, 'loss/train': 1.3598995208740234} 08/30/2021 20:11:26 - INFO - __main__ - Step 38783: {'lr': 0.0004275928304807242, 'samples': 7446336, 'steps': 38782, 'loss/train': 1.4608898162841797} 08/30/2021 20:11:27 - INFO - __main__ - Step 38784: {'lr': 0.0004275890954102362, 'samples': 7446528, 'steps': 38783, 'loss/train': 1.734776258468628} 08/30/2021 20:11:28 - INFO - __main__ - Step 38785: {'lr': 0.0004275853602597294, 'samples': 7446720, 'steps': 38784, 'loss/train': 1.3762632608413696} 08/30/2021 20:11:28 - INFO - __main__ - Step 38786: {'lr': 0.00042758162502920527, 'samples': 7446912, 'steps': 38785, 'loss/train': 0.9701852798461914} 08/30/2021 20:11:28 - INFO - __main__ - Step 38787: {'lr': 0.0004275778897186656, 'samples': 7447104, 'steps': 38786, 'loss/train': 1.4358216524124146} 08/30/2021 20:11:29 - INFO - __main__ - Step 38788: {'lr': 0.0004275741543281121, 'samples': 7447296, 'steps': 38787, 'loss/train': 1.4445950984954834} 08/30/2021 20:11:30 - INFO - __main__ - Step 38789: {'lr': 0.0004275704188575464, 'samples': 7447488, 'steps': 38788, 'loss/train': 0.5505427718162537} 08/30/2021 20:11:31 - INFO - __main__ - Step 38790: {'lr': 0.00042756668330697024, 'samples': 7447680, 'steps': 38789, 'loss/train': 0.9554463624954224} 08/30/2021 20:11:31 - INFO - __main__ - Step 38791: {'lr': 0.00042756294767638527, 'samples': 7447872, 'steps': 38790, 'loss/train': 1.079748511314392} 08/30/2021 20:11:31 - INFO - __main__ - Step 38792: {'lr': 0.00042755921196579316, 'samples': 7448064, 'steps': 38791, 'loss/train': 1.6538499593734741} 08/30/2021 20:11:32 - INFO - __main__ - Step 38793: {'lr': 0.0004275554761751956, 'samples': 7448256, 'steps': 38792, 'loss/train': 0.8024705648422241} 08/30/2021 20:11:34 - INFO - __main__ - Step 38794: {'lr': 0.0004275517403045943, 'samples': 7448448, 'steps': 38793, 'loss/train': 1.7083035707473755} 08/30/2021 20:11:34 - INFO - __main__ - Step 38795: {'lr': 0.000427548004353991, 'samples': 7448640, 'steps': 38794, 'loss/train': 1.5873737335205078} 08/30/2021 20:11:34 - INFO - __main__ - Step 38796: {'lr': 0.00042754426832338724, 'samples': 7448832, 'steps': 38795, 'loss/train': 0.06725167483091354} 08/30/2021 20:11:35 - INFO - __main__ - Step 38797: {'lr': 0.00042754053221278476, 'samples': 7449024, 'steps': 38796, 'loss/train': 0.6868668794631958} 08/30/2021 20:11:35 - INFO - __main__ - Step 38798: {'lr': 0.0004275367960221853, 'samples': 7449216, 'steps': 38797, 'loss/train': 0.6166905164718628} 08/30/2021 20:11:37 - INFO - __main__ - Step 38799: {'lr': 0.0004275330597515904, 'samples': 7449408, 'steps': 38798, 'loss/train': 1.342469573020935} 08/30/2021 20:11:38 - INFO - __main__ - Step 38800: {'lr': 0.00042752932340100195, 'samples': 7449600, 'steps': 38799, 'loss/train': 1.7195112705230713} 08/30/2021 20:11:38 - INFO - __main__ - Step 38801: {'lr': 0.00042752558697042143, 'samples': 7449792, 'steps': 38800, 'loss/train': 1.3047715425491333} 08/30/2021 20:11:38 - INFO - __main__ - Step 38802: {'lr': 0.0004275218504598507, 'samples': 7449984, 'steps': 38801, 'loss/train': 1.9004665613174438} 08/30/2021 20:11:39 - INFO - __main__ - Step 38803: {'lr': 0.0004275181138692914, 'samples': 7450176, 'steps': 38802, 'loss/train': 1.2620739936828613} 08/30/2021 20:11:40 - INFO - __main__ - Step 38804: {'lr': 0.0004275143771987451, 'samples': 7450368, 'steps': 38803, 'loss/train': 1.871267318725586} 08/30/2021 20:11:41 - INFO - __main__ - Step 38805: {'lr': 0.00042751064044821354, 'samples': 7450560, 'steps': 38804, 'loss/train': 1.3852405548095703} 08/30/2021 20:11:41 - INFO - __main__ - Step 38806: {'lr': 0.0004275069036176985, 'samples': 7450752, 'steps': 38805, 'loss/train': 1.641545295715332} 08/30/2021 20:11:41 - INFO - __main__ - Step 38807: {'lr': 0.0004275031667072015, 'samples': 7450944, 'steps': 38806, 'loss/train': 1.673424482345581} 08/30/2021 20:11:42 - INFO - __main__ - Step 38808: {'lr': 0.0004274994297167244, 'samples': 7451136, 'steps': 38807, 'loss/train': 1.533370018005371} 08/30/2021 20:11:42 - INFO - __main__ - Step 38809: {'lr': 0.00042749569264626875, 'samples': 7451328, 'steps': 38808, 'loss/train': 0.7603945732116699} 08/30/2021 20:11:44 - INFO - __main__ - Step 38810: {'lr': 0.0004274919554958363, 'samples': 7451520, 'steps': 38809, 'loss/train': 1.2478253841400146} 08/30/2021 20:11:44 - INFO - __main__ - Step 38811: {'lr': 0.00042748821826542875, 'samples': 7451712, 'steps': 38810, 'loss/train': 0.049417704343795776} 08/30/2021 20:11:45 - INFO - __main__ - Step 38812: {'lr': 0.00042748448095504765, 'samples': 7451904, 'steps': 38811, 'loss/train': 2.2108635902404785} 08/30/2021 20:11:45 - INFO - __main__ - Step 38813: {'lr': 0.0004274807435646948, 'samples': 7452096, 'steps': 38812, 'loss/train': 3.019526720046997} 08/30/2021 20:11:45 - INFO - __main__ - Step 38814: {'lr': 0.0004274770060943719, 'samples': 7452288, 'steps': 38813, 'loss/train': 0.995280921459198} 08/30/2021 20:11:47 - INFO - __main__ - Step 38815: {'lr': 0.00042747326854408063, 'samples': 7452480, 'steps': 38814, 'loss/train': 1.0013155937194824} 08/30/2021 20:11:47 - INFO - __main__ - Step 38816: {'lr': 0.00042746953091382254, 'samples': 7452672, 'steps': 38815, 'loss/train': 1.4817057847976685} 08/30/2021 20:11:47 - INFO - __main__ - Step 38817: {'lr': 0.00042746579320359956, 'samples': 7452864, 'steps': 38816, 'loss/train': 1.8496936559677124} 08/30/2021 20:11:48 - INFO - __main__ - Step 38818: {'lr': 0.00042746205541341315, 'samples': 7453056, 'steps': 38817, 'loss/train': 1.0554754734039307} 08/30/2021 20:11:48 - INFO - __main__ - Step 38819: {'lr': 0.0004274583175432651, 'samples': 7453248, 'steps': 38818, 'loss/train': 1.0900686979293823} 08/30/2021 20:11:50 - INFO - __main__ - Step 38820: {'lr': 0.000427454579593157, 'samples': 7453440, 'steps': 38819, 'loss/train': 0.7323368191719055} 08/30/2021 20:11:50 - INFO - __main__ - Step 38821: {'lr': 0.00042745084156309065, 'samples': 7453632, 'steps': 38820, 'loss/train': 1.5207645893096924} 08/30/2021 20:11:51 - INFO - __main__ - Step 38822: {'lr': 0.00042744710345306774, 'samples': 7453824, 'steps': 38821, 'loss/train': 1.7052807807922363} 08/30/2021 20:11:51 - INFO - __main__ - Step 38823: {'lr': 0.00042744336526308986, 'samples': 7454016, 'steps': 38822, 'loss/train': 1.7357161045074463} 08/30/2021 20:11:51 - INFO - __main__ - Step 38824: {'lr': 0.0004274396269931587, 'samples': 7454208, 'steps': 38823, 'loss/train': 5.671684741973877} 08/30/2021 20:11:52 - INFO - __main__ - Step 38825: {'lr': 0.0004274358886432761, 'samples': 7454400, 'steps': 38824, 'loss/train': 1.1085503101348877} 08/30/2021 20:11:53 - INFO - __main__ - Step 38826: {'lr': 0.0004274321502134435, 'samples': 7454592, 'steps': 38825, 'loss/train': 0.936346173286438} 08/30/2021 20:11:54 - INFO - __main__ - Step 38827: {'lr': 0.00042742841170366274, 'samples': 7454784, 'steps': 38826, 'loss/train': 1.3706201314926147} 08/30/2021 20:11:54 - INFO - __main__ - Step 38828: {'lr': 0.0004274246731139355, 'samples': 7454976, 'steps': 38827, 'loss/train': 1.6990272998809814} 08/30/2021 20:11:54 - INFO - __main__ - Step 38829: {'lr': 0.0004274209344442634, 'samples': 7455168, 'steps': 38828, 'loss/train': 1.3024113178253174} 08/30/2021 20:11:55 - INFO - __main__ - Step 38830: {'lr': 0.00042741719569464834, 'samples': 7455360, 'steps': 38829, 'loss/train': 1.5719633102416992} 08/30/2021 20:11:56 - INFO - __main__ - Step 38831: {'lr': 0.0004274134568650916, 'samples': 7455552, 'steps': 38830, 'loss/train': 1.2164031267166138} 08/30/2021 20:11:57 - INFO - __main__ - Step 38832: {'lr': 0.00042740971795559527, 'samples': 7455744, 'steps': 38831, 'loss/train': 1.5107475519180298} 08/30/2021 20:11:57 - INFO - __main__ - Step 38833: {'lr': 0.00042740597896616075, 'samples': 7455936, 'steps': 38832, 'loss/train': 1.4301981925964355} 08/30/2021 20:11:57 - INFO - __main__ - Step 38834: {'lr': 0.00042740223989678984, 'samples': 7456128, 'steps': 38833, 'loss/train': 1.6313468217849731} 08/30/2021 20:11:58 - INFO - __main__ - Step 38835: {'lr': 0.0004273985007474842, 'samples': 7456320, 'steps': 38834, 'loss/train': 1.4326335191726685} 08/30/2021 20:11:59 - INFO - __main__ - Step 38836: {'lr': 0.00042739476151824565, 'samples': 7456512, 'steps': 38835, 'loss/train': 1.4646745920181274} 08/30/2021 20:12:00 - INFO - __main__ - Step 38837: {'lr': 0.00042739102220907567, 'samples': 7456704, 'steps': 38836, 'loss/train': 1.492846131324768} 08/30/2021 20:12:00 - INFO - __main__ - Step 38838: {'lr': 0.000427387282819976, 'samples': 7456896, 'steps': 38837, 'loss/train': 0.743320643901825} 08/30/2021 20:12:00 - INFO - __main__ - Step 38839: {'lr': 0.0004273835433509484, 'samples': 7457088, 'steps': 38838, 'loss/train': 0.8244975805282593} 08/30/2021 20:12:01 - INFO - __main__ - Step 38840: {'lr': 0.0004273798038019945, 'samples': 7457280, 'steps': 38839, 'loss/train': 1.8393313884735107} 08/30/2021 20:12:02 - INFO - __main__ - Step 38841: {'lr': 0.000427376064173116, 'samples': 7457472, 'steps': 38840, 'loss/train': 1.638372778892517} 08/30/2021 20:12:03 - INFO - __main__ - Step 38842: {'lr': 0.0004273723244643146, 'samples': 7457664, 'steps': 38841, 'loss/train': 1.1974339485168457} 08/30/2021 20:12:03 - INFO - __main__ - Step 38843: {'lr': 0.000427368584675592, 'samples': 7457856, 'steps': 38842, 'loss/train': 1.6608766317367554} 08/30/2021 20:12:03 - INFO - __main__ - Step 38844: {'lr': 0.0004273648448069498, 'samples': 7458048, 'steps': 38843, 'loss/train': 1.576238751411438} 08/30/2021 20:12:04 - INFO - __main__ - Step 38845: {'lr': 0.00042736110485838973, 'samples': 7458240, 'steps': 38844, 'loss/train': 1.5806571245193481} 08/30/2021 20:12:06 - INFO - __main__ - Step 38846: {'lr': 0.0004273573648299135, 'samples': 7458432, 'steps': 38845, 'loss/train': 1.2291008234024048} 08/30/2021 20:12:06 - INFO - __main__ - Step 38847: {'lr': 0.0004273536247215227, 'samples': 7458624, 'steps': 38846, 'loss/train': 1.3920701742172241} 08/30/2021 20:12:06 - INFO - __main__ - Step 38848: {'lr': 0.00042734988453321923, 'samples': 7458816, 'steps': 38847, 'loss/train': 1.7615653276443481} 08/30/2021 20:12:07 - INFO - __main__ - Step 38849: {'lr': 0.0004273461442650046, 'samples': 7459008, 'steps': 38848, 'loss/train': 1.2972995042800903} 08/30/2021 20:12:07 - INFO - __main__ - Step 38850: {'lr': 0.0004273424039168805, 'samples': 7459200, 'steps': 38849, 'loss/train': 0.03974912688136101} 08/30/2021 20:12:07 - INFO - __main__ - Step 38851: {'lr': 0.00042733866348884864, 'samples': 7459392, 'steps': 38850, 'loss/train': 2.0268895626068115} 08/30/2021 20:12:08 - INFO - __main__ - Step 38852: {'lr': 0.0004273349229809108, 'samples': 7459584, 'steps': 38851, 'loss/train': 1.621764063835144} 08/30/2021 20:12:09 - INFO - __main__ - Step 38853: {'lr': 0.00042733118239306845, 'samples': 7459776, 'steps': 38852, 'loss/train': 0.741858184337616} 08/30/2021 20:12:10 - INFO - __main__ - Step 38854: {'lr': 0.0004273274417253235, 'samples': 7459968, 'steps': 38853, 'loss/train': 1.4695534706115723} 08/30/2021 20:12:10 - INFO - __main__ - Step 38855: {'lr': 0.00042732370097767756, 'samples': 7460160, 'steps': 38854, 'loss/train': 1.8754863739013672} 08/30/2021 20:12:10 - INFO - __main__ - Step 38856: {'lr': 0.0004273199601501322, 'samples': 7460352, 'steps': 38855, 'loss/train': 0.3878907263278961} 08/30/2021 20:12:11 - INFO - __main__ - Step 38857: {'lr': 0.0004273162192426893, 'samples': 7460544, 'steps': 38856, 'loss/train': 1.5242090225219727} 08/30/2021 20:12:13 - INFO - __main__ - Step 38858: {'lr': 0.00042731247825535037, 'samples': 7460736, 'steps': 38857, 'loss/train': 1.4300408363342285} 08/30/2021 20:12:13 - INFO - __main__ - Step 38859: {'lr': 0.00042730873718811724, 'samples': 7460928, 'steps': 38858, 'loss/train': 5.811954021453857} 08/30/2021 20:12:14 - INFO - __main__ - Step 38860: {'lr': 0.0004273049960409915, 'samples': 7461120, 'steps': 38859, 'loss/train': 1.892176866531372} 08/30/2021 20:12:14 - INFO - __main__ - Step 38861: {'lr': 0.00042730125481397487, 'samples': 7461312, 'steps': 38860, 'loss/train': 1.5292850732803345} 08/30/2021 20:12:14 - INFO - __main__ - Step 38862: {'lr': 0.00042729751350706905, 'samples': 7461504, 'steps': 38861, 'loss/train': 0.8005544543266296} 08/30/2021 20:12:16 - INFO - __main__ - Step 38863: {'lr': 0.00042729377212027557, 'samples': 7461696, 'steps': 38862, 'loss/train': 1.3388922214508057} 08/30/2021 20:12:16 - INFO - __main__ - Step 38864: {'lr': 0.0004272900306535964, 'samples': 7461888, 'steps': 38863, 'loss/train': 1.8581312894821167} 08/30/2021 20:12:17 - INFO - __main__ - Step 38865: {'lr': 0.00042728628910703305, 'samples': 7462080, 'steps': 38864, 'loss/train': 1.4440981149673462} 08/30/2021 20:12:17 - INFO - __main__ - Step 38866: {'lr': 0.0004272825474805872, 'samples': 7462272, 'steps': 38865, 'loss/train': 1.6697527170181274} 08/30/2021 20:12:17 - INFO - __main__ - Step 38867: {'lr': 0.0004272788057742606, 'samples': 7462464, 'steps': 38866, 'loss/train': 0.9913666844367981} 08/30/2021 20:12:19 - INFO - __main__ - Step 38868: {'lr': 0.0004272750639880549, 'samples': 7462656, 'steps': 38867, 'loss/train': 1.2427674531936646} 08/30/2021 20:12:19 - INFO - __main__ - Step 38869: {'lr': 0.0004272713221219718, 'samples': 7462848, 'steps': 38868, 'loss/train': 1.768541932106018} 08/30/2021 20:12:20 - INFO - __main__ - Step 38870: {'lr': 0.00042726758017601297, 'samples': 7463040, 'steps': 38869, 'loss/train': 1.740482211112976} 08/30/2021 20:12:20 - INFO - __main__ - Step 38871: {'lr': 0.00042726383815018006, 'samples': 7463232, 'steps': 38870, 'loss/train': 1.0954400300979614} 08/30/2021 20:12:20 - INFO - __main__ - Step 38872: {'lr': 0.00042726009604447484, 'samples': 7463424, 'steps': 38871, 'loss/train': 1.7786637544631958} 08/30/2021 20:12:22 - INFO - __main__ - Step 38873: {'lr': 0.00042725635385889893, 'samples': 7463616, 'steps': 38872, 'loss/train': 1.2100390195846558} 08/30/2021 20:12:22 - INFO - __main__ - Step 38874: {'lr': 0.0004272526115934541, 'samples': 7463808, 'steps': 38873, 'loss/train': 2.9023475646972656} 08/30/2021 20:12:23 - INFO - __main__ - Step 38875: {'lr': 0.0004272488692481419, 'samples': 7464000, 'steps': 38874, 'loss/train': 1.4789249897003174} 08/30/2021 20:12:23 - INFO - __main__ - Step 38876: {'lr': 0.00042724512682296416, 'samples': 7464192, 'steps': 38875, 'loss/train': 1.707767128944397} 08/30/2021 20:12:23 - INFO - __main__ - Step 38877: {'lr': 0.00042724138431792245, 'samples': 7464384, 'steps': 38876, 'loss/train': 1.9130243062973022} 08/30/2021 20:12:25 - INFO - __main__ - Step 38878: {'lr': 0.0004272376417330186, 'samples': 7464576, 'steps': 38877, 'loss/train': 1.606658697128296} 08/30/2021 20:12:25 - INFO - __main__ - Step 38879: {'lr': 0.00042723389906825415, 'samples': 7464768, 'steps': 38878, 'loss/train': 1.967221975326538} 08/30/2021 20:12:26 - INFO - __main__ - Step 38880: {'lr': 0.0004272301563236308, 'samples': 7464960, 'steps': 38879, 'loss/train': 1.6439955234527588} 08/30/2021 20:12:26 - INFO - __main__ - Step 38881: {'lr': 0.0004272264134991503, 'samples': 7465152, 'steps': 38880, 'loss/train': 1.4029533863067627} 08/30/2021 20:12:26 - INFO - __main__ - Step 38882: {'lr': 0.0004272226705948143, 'samples': 7465344, 'steps': 38881, 'loss/train': 1.0242358446121216} 08/30/2021 20:12:27 - INFO - __main__ - Step 38883: {'lr': 0.00042721892761062453, 'samples': 7465536, 'steps': 38882, 'loss/train': 1.760402798652649} 08/30/2021 20:12:28 - INFO - __main__ - Step 38884: {'lr': 0.00042721518454658265, 'samples': 7465728, 'steps': 38883, 'loss/train': 1.1447868347167969} 08/30/2021 20:12:29 - INFO - __main__ - Step 38885: {'lr': 0.0004272114414026903, 'samples': 7465920, 'steps': 38884, 'loss/train': 1.2751240730285645} 08/30/2021 20:12:29 - INFO - __main__ - Step 38886: {'lr': 0.00042720769817894926, 'samples': 7466112, 'steps': 38885, 'loss/train': 1.0240662097930908} 08/30/2021 20:12:29 - INFO - __main__ - Step 38887: {'lr': 0.00042720395487536115, 'samples': 7466304, 'steps': 38886, 'loss/train': 1.2464112043380737} 08/30/2021 20:12:30 - INFO - __main__ - Step 38888: {'lr': 0.0004272002114919277, 'samples': 7466496, 'steps': 38887, 'loss/train': 2.1759443283081055} 08/30/2021 20:12:31 - INFO - __main__ - Step 38889: {'lr': 0.0004271964680286505, 'samples': 7466688, 'steps': 38888, 'loss/train': 1.3713324069976807} 08/30/2021 20:12:32 - INFO - __main__ - Step 38890: {'lr': 0.00042719272448553137, 'samples': 7466880, 'steps': 38889, 'loss/train': 1.3767149448394775} 08/30/2021 20:12:32 - INFO - __main__ - Step 38891: {'lr': 0.00042718898086257183, 'samples': 7467072, 'steps': 38890, 'loss/train': 1.054800271987915} 08/30/2021 20:12:33 - INFO - __main__ - Step 38892: {'lr': 0.0004271852371597738, 'samples': 7467264, 'steps': 38891, 'loss/train': 1.1322903633117676} 08/30/2021 20:12:33 - INFO - __main__ - Step 38893: {'lr': 0.00042718149337713873, 'samples': 7467456, 'steps': 38892, 'loss/train': 1.3412657976150513} 08/30/2021 20:12:35 - INFO - __main__ - Step 38894: {'lr': 0.0004271777495146685, 'samples': 7467648, 'steps': 38893, 'loss/train': 1.7502262592315674} 08/30/2021 20:12:35 - INFO - __main__ - Step 38895: {'lr': 0.00042717400557236467, 'samples': 7467840, 'steps': 38894, 'loss/train': 1.6785212755203247} 08/30/2021 20:12:35 - INFO - __main__ - Step 38896: {'lr': 0.000427170261550229, 'samples': 7468032, 'steps': 38895, 'loss/train': 0.10268183797597885} 08/30/2021 20:12:36 - INFO - __main__ - Step 38897: {'lr': 0.0004271665174482631, 'samples': 7468224, 'steps': 38896, 'loss/train': 1.6445964574813843} 08/30/2021 20:12:36 - INFO - __main__ - Step 38898: {'lr': 0.0004271627732664687, 'samples': 7468416, 'steps': 38897, 'loss/train': 1.277680516242981} 08/30/2021 20:12:36 - INFO - __main__ - Step 38899: {'lr': 0.0004271590290048475, 'samples': 7468608, 'steps': 38898, 'loss/train': 1.1523408889770508} 08/30/2021 20:12:38 - INFO - __main__ - Step 38900: {'lr': 0.00042715528466340117, 'samples': 7468800, 'steps': 38899, 'loss/train': 1.2972526550292969} 08/30/2021 20:12:39 - INFO - __main__ - Step 38901: {'lr': 0.00042715154024213143, 'samples': 7468992, 'steps': 38900, 'loss/train': 1.7928061485290527} 08/30/2021 20:12:39 - INFO - __main__ - Step 38902: {'lr': 0.0004271477957410399, 'samples': 7469184, 'steps': 38901, 'loss/train': 1.1343905925750732} 08/30/2021 20:12:39 - INFO - __main__ - Step 38903: {'lr': 0.00042714405116012834, 'samples': 7469376, 'steps': 38902, 'loss/train': 1.207249402999878} 08/30/2021 20:12:40 - INFO - __main__ - Step 38904: {'lr': 0.0004271403064993984, 'samples': 7469568, 'steps': 38903, 'loss/train': 1.5169848203659058} 08/30/2021 20:12:41 - INFO - __main__ - Step 38905: {'lr': 0.00042713656175885173, 'samples': 7469760, 'steps': 38904, 'loss/train': 1.6788558959960938} 08/30/2021 20:12:41 - INFO - __main__ - Step 38906: {'lr': 0.00042713281693849015, 'samples': 7469952, 'steps': 38905, 'loss/train': 1.1194159984588623} 08/30/2021 20:12:42 - INFO - __main__ - Step 38907: {'lr': 0.0004271290720383152, 'samples': 7470144, 'steps': 38906, 'loss/train': 1.097764253616333} 08/30/2021 20:12:42 - INFO - __main__ - Step 38908: {'lr': 0.00042712532705832865, 'samples': 7470336, 'steps': 38907, 'loss/train': 2.204711675643921} 08/30/2021 20:12:43 - INFO - __main__ - Step 38909: {'lr': 0.0004271215819985321, 'samples': 7470528, 'steps': 38908, 'loss/train': 2.249115467071533} 08/30/2021 20:12:45 - INFO - __main__ - Step 38910: {'lr': 0.0004271178368589273, 'samples': 7470720, 'steps': 38909, 'loss/train': 1.112189769744873} 08/30/2021 20:12:45 - INFO - __main__ - Step 38911: {'lr': 0.000427114091639516, 'samples': 7470912, 'steps': 38910, 'loss/train': 1.3625484704971313} 08/30/2021 20:12:45 - INFO - __main__ - Step 38912: {'lr': 0.0004271103463402998, 'samples': 7471104, 'steps': 38911, 'loss/train': 1.3684254884719849} 08/30/2021 20:12:46 - INFO - __main__ - Step 38913: {'lr': 0.0004271066009612804, 'samples': 7471296, 'steps': 38912, 'loss/train': 1.8041632175445557} 08/30/2021 20:12:46 - INFO - __main__ - Step 38914: {'lr': 0.0004271028555024594, 'samples': 7471488, 'steps': 38913, 'loss/train': 1.4527479410171509} 08/30/2021 20:12:48 - INFO - __main__ - Step 38915: {'lr': 0.0004270991099638387, 'samples': 7471680, 'steps': 38914, 'loss/train': 1.4462686777114868} 08/30/2021 20:12:48 - INFO - __main__ - Step 38916: {'lr': 0.0004270953643454199, 'samples': 7471872, 'steps': 38915, 'loss/train': 1.3754023313522339} 08/30/2021 20:12:48 - INFO - __main__ - Step 38917: {'lr': 0.0004270916186472046, 'samples': 7472064, 'steps': 38916, 'loss/train': 1.425809621810913} 08/30/2021 20:12:49 - INFO - __main__ - Step 38918: {'lr': 0.0004270878728691946, 'samples': 7472256, 'steps': 38917, 'loss/train': 2.0539333820343018} 08/30/2021 20:12:49 - INFO - __main__ - Step 38919: {'lr': 0.00042708412701139147, 'samples': 7472448, 'steps': 38918, 'loss/train': 1.4504209756851196} 08/30/2021 20:12:50 - INFO - __main__ - Step 38920: {'lr': 0.000427080381073797, 'samples': 7472640, 'steps': 38919, 'loss/train': 2.1193222999572754} 08/30/2021 20:12:51 - INFO - __main__ - Step 38921: {'lr': 0.00042707663505641287, 'samples': 7472832, 'steps': 38920, 'loss/train': 1.7147212028503418} 08/30/2021 20:12:51 - INFO - __main__ - Step 38922: {'lr': 0.00042707288895924066, 'samples': 7473024, 'steps': 38921, 'loss/train': 1.0057674646377563} 08/30/2021 20:12:52 - INFO - __main__ - Step 38923: {'lr': 0.0004270691427822823, 'samples': 7473216, 'steps': 38922, 'loss/train': 1.7988524436950684} 08/30/2021 20:12:52 - INFO - __main__ - Step 38924: {'lr': 0.0004270653965255391, 'samples': 7473408, 'steps': 38923, 'loss/train': 1.2420998811721802} 08/30/2021 20:12:53 - INFO - __main__ - Step 38925: {'lr': 0.0004270616501890131, 'samples': 7473600, 'steps': 38924, 'loss/train': 1.2856082916259766} 08/30/2021 20:12:54 - INFO - __main__ - Step 38926: {'lr': 0.0004270579037727058, 'samples': 7473792, 'steps': 38925, 'loss/train': 1.660669207572937} 08/30/2021 20:12:54 - INFO - __main__ - Step 38927: {'lr': 0.000427054157276619, 'samples': 7473984, 'steps': 38926, 'loss/train': 1.3976815938949585} 08/30/2021 20:12:55 - INFO - __main__ - Step 38928: {'lr': 0.00042705041070075433, 'samples': 7474176, 'steps': 38927, 'loss/train': 0.8167530298233032} 08/30/2021 20:12:55 - INFO - __main__ - Step 38929: {'lr': 0.00042704666404511343, 'samples': 7474368, 'steps': 38928, 'loss/train': 1.8932794332504272} 08/30/2021 20:12:55 - INFO - __main__ - Step 38930: {'lr': 0.000427042917309698, 'samples': 7474560, 'steps': 38929, 'loss/train': 1.473808765411377} 08/30/2021 20:12:58 - INFO - __main__ - Step 38931: {'lr': 0.00042703917049450983, 'samples': 7474752, 'steps': 38930, 'loss/train': 1.594633936882019} 08/30/2021 20:12:58 - INFO - __main__ - Step 38932: {'lr': 0.0004270354235995505, 'samples': 7474944, 'steps': 38931, 'loss/train': 0.06461476534605026} 08/30/2021 20:12:59 - INFO - __main__ - Step 38933: {'lr': 0.0004270316766248218, 'samples': 7475136, 'steps': 38932, 'loss/train': 1.381054162979126} 08/30/2021 20:12:59 - INFO - __main__ - Step 38934: {'lr': 0.0004270279295703253, 'samples': 7475328, 'steps': 38933, 'loss/train': 2.11806058883667} 08/30/2021 20:12:59 - INFO - __main__ - Step 38935: {'lr': 0.00042702418243606275, 'samples': 7475520, 'steps': 38934, 'loss/train': 1.3243941068649292} 08/30/2021 20:13:00 - INFO - __main__ - Step 38936: {'lr': 0.00042702043522203594, 'samples': 7475712, 'steps': 38935, 'loss/train': 0.5328168272972107} 08/30/2021 20:13:00 - INFO - __main__ - Step 38937: {'lr': 0.00042701668792824633, 'samples': 7475904, 'steps': 38936, 'loss/train': 0.41878703236579895} 08/30/2021 20:13:01 - INFO - __main__ - Step 38938: {'lr': 0.00042701294055469576, 'samples': 7476096, 'steps': 38937, 'loss/train': 0.9047747254371643} 08/30/2021 20:13:02 - INFO - __main__ - Step 38939: {'lr': 0.0004270091931013859, 'samples': 7476288, 'steps': 38938, 'loss/train': 1.2436997890472412} 08/30/2021 20:13:02 - INFO - __main__ - Step 38940: {'lr': 0.00042700544556831846, 'samples': 7476480, 'steps': 38939, 'loss/train': 1.4766095876693726} 08/30/2021 20:13:03 - INFO - __main__ - Step 38941: {'lr': 0.00042700169795549504, 'samples': 7476672, 'steps': 38940, 'loss/train': 1.43293035030365} 08/30/2021 20:13:03 - INFO - __main__ - Step 38942: {'lr': 0.00042699795026291743, 'samples': 7476864, 'steps': 38941, 'loss/train': 2.0445070266723633} 08/30/2021 20:13:04 - INFO - __main__ - Step 38943: {'lr': 0.0004269942024905872, 'samples': 7477056, 'steps': 38942, 'loss/train': 0.8253125548362732} 08/30/2021 20:13:05 - INFO - __main__ - Step 38944: {'lr': 0.00042699045463850623, 'samples': 7477248, 'steps': 38943, 'loss/train': 1.3244879245758057} 08/30/2021 20:13:05 - INFO - __main__ - Step 38945: {'lr': 0.000426986706706676, 'samples': 7477440, 'steps': 38944, 'loss/train': 0.7600665092468262} 08/30/2021 20:13:06 - INFO - __main__ - Step 38946: {'lr': 0.00042698295869509836, 'samples': 7477632, 'steps': 38945, 'loss/train': 1.1268936395645142} 08/30/2021 20:13:06 - INFO - __main__ - Step 38947: {'lr': 0.0004269792106037749, 'samples': 7477824, 'steps': 38946, 'loss/train': 0.8434619307518005} 08/30/2021 20:13:07 - INFO - __main__ - Step 38948: {'lr': 0.0004269754624327073, 'samples': 7478016, 'steps': 38947, 'loss/train': 1.2072659730911255} 08/30/2021 20:13:08 - INFO - __main__ - Step 38949: {'lr': 0.0004269717141818973, 'samples': 7478208, 'steps': 38948, 'loss/train': 2.111098527908325} 08/30/2021 20:13:08 - INFO - __main__ - Step 38950: {'lr': 0.0004269679658513466, 'samples': 7478400, 'steps': 38949, 'loss/train': 1.4043744802474976} 08/30/2021 20:13:08 - INFO - __main__ - Step 38951: {'lr': 0.00042696421744105686, 'samples': 7478592, 'steps': 38950, 'loss/train': 1.335856556892395} 08/30/2021 20:13:09 - INFO - __main__ - Step 38952: {'lr': 0.0004269604689510298, 'samples': 7478784, 'steps': 38951, 'loss/train': 1.4491199254989624} 08/30/2021 20:13:10 - INFO - __main__ - Step 38953: {'lr': 0.0004269567203812671, 'samples': 7478976, 'steps': 38952, 'loss/train': 1.7880336046218872} 08/30/2021 20:13:11 - INFO - __main__ - Step 38954: {'lr': 0.00042695297173177033, 'samples': 7479168, 'steps': 38953, 'loss/train': 2.1866867542266846} 08/30/2021 20:13:11 - INFO - __main__ - Step 38955: {'lr': 0.0004269492230025413, 'samples': 7479360, 'steps': 38954, 'loss/train': 1.1974194049835205} 08/30/2021 20:13:11 - INFO - __main__ - Step 38956: {'lr': 0.0004269454741935818, 'samples': 7479552, 'steps': 38955, 'loss/train': 1.2394767999649048} 08/30/2021 20:13:12 - INFO - __main__ - Step 38957: {'lr': 0.00042694172530489326, 'samples': 7479744, 'steps': 38956, 'loss/train': 1.0012314319610596} 08/30/2021 20:13:13 - INFO - __main__ - Step 38958: {'lr': 0.00042693797633647755, 'samples': 7479936, 'steps': 38957, 'loss/train': 1.2408217191696167} 08/30/2021 20:13:14 - INFO - __main__ - Step 38959: {'lr': 0.00042693422728833644, 'samples': 7480128, 'steps': 38958, 'loss/train': 1.2148038148880005} 08/30/2021 20:13:14 - INFO - __main__ - Step 38960: {'lr': 0.00042693047816047135, 'samples': 7480320, 'steps': 38959, 'loss/train': 0.929209291934967} 08/30/2021 20:13:14 - INFO - __main__ - Step 38961: {'lr': 0.0004269267289528842, 'samples': 7480512, 'steps': 38960, 'loss/train': 1.593306064605713} 08/30/2021 20:13:15 - INFO - __main__ - Step 38962: {'lr': 0.00042692297966557657, 'samples': 7480704, 'steps': 38961, 'loss/train': 1.6138441562652588} 08/30/2021 20:13:18 - INFO - __main__ - Step 38963: {'lr': 0.0004269192302985502, 'samples': 7480896, 'steps': 38962, 'loss/train': 1.0217334032058716} 08/30/2021 20:13:18 - INFO - __main__ - Step 38964: {'lr': 0.00042691548085180666, 'samples': 7481088, 'steps': 38963, 'loss/train': 1.1979821920394897} 08/30/2021 20:13:18 - INFO - __main__ - Step 38965: {'lr': 0.00042691173132534775, 'samples': 7481280, 'steps': 38964, 'loss/train': 1.181747317314148} 08/30/2021 20:13:19 - INFO - __main__ - Step 38966: {'lr': 0.0004269079817191752, 'samples': 7481472, 'steps': 38965, 'loss/train': 0.7483606934547424} 08/30/2021 20:13:19 - INFO - __main__ - Step 38967: {'lr': 0.00042690423203329067, 'samples': 7481664, 'steps': 38966, 'loss/train': 1.322017788887024} 08/30/2021 20:13:19 - INFO - __main__ - Step 38968: {'lr': 0.0004269004822676958, 'samples': 7481856, 'steps': 38967, 'loss/train': 1.121822476387024} 08/30/2021 20:13:21 - INFO - __main__ - Step 38969: {'lr': 0.0004268967324223922, 'samples': 7482048, 'steps': 38968, 'loss/train': 1.158146858215332} 08/30/2021 20:13:21 - INFO - __main__ - Step 38970: {'lr': 0.00042689298249738185, 'samples': 7482240, 'steps': 38969, 'loss/train': 1.3048549890518188} 08/30/2021 20:13:22 - INFO - __main__ - Step 38971: {'lr': 0.00042688923249266614, 'samples': 7482432, 'steps': 38970, 'loss/train': 1.3903834819793701} 08/30/2021 20:13:22 - INFO - __main__ - Step 38972: {'lr': 0.00042688548240824687, 'samples': 7482624, 'steps': 38971, 'loss/train': 1.5594826936721802} 08/30/2021 20:13:22 - INFO - __main__ - Step 38973: {'lr': 0.00042688173224412573, 'samples': 7482816, 'steps': 38972, 'loss/train': 1.3469113111495972} 08/30/2021 20:13:24 - INFO - __main__ - Step 38974: {'lr': 0.00042687798200030446, 'samples': 7483008, 'steps': 38973, 'loss/train': 0.8241060376167297} 08/30/2021 20:13:24 - INFO - __main__ - Step 38975: {'lr': 0.00042687423167678463, 'samples': 7483200, 'steps': 38974, 'loss/train': 1.3494739532470703} 08/30/2021 20:13:25 - INFO - __main__ - Step 38976: {'lr': 0.0004268704812735681, 'samples': 7483392, 'steps': 38975, 'loss/train': 1.4919968843460083} 08/30/2021 20:13:25 - INFO - __main__ - Step 38977: {'lr': 0.00042686673079065637, 'samples': 7483584, 'steps': 38976, 'loss/train': 1.9727466106414795} 08/30/2021 20:13:25 - INFO - __main__ - Step 38978: {'lr': 0.00042686298022805126, 'samples': 7483776, 'steps': 38977, 'loss/train': 1.2541768550872803} 08/30/2021 20:13:26 - INFO - __main__ - Step 38979: {'lr': 0.0004268592295857544, 'samples': 7483968, 'steps': 38978, 'loss/train': 1.2378605604171753} 08/30/2021 20:13:27 - INFO - __main__ - Step 38980: {'lr': 0.0004268554788637675, 'samples': 7484160, 'steps': 38979, 'loss/train': 1.3495855331420898} 08/30/2021 20:13:28 - INFO - __main__ - Step 38981: {'lr': 0.0004268517280620923, 'samples': 7484352, 'steps': 38980, 'loss/train': 1.540118932723999} 08/30/2021 20:13:28 - INFO - __main__ - Step 38982: {'lr': 0.0004268479771807303, 'samples': 7484544, 'steps': 38981, 'loss/train': 0.09688853472471237} 08/30/2021 20:13:28 - INFO - __main__ - Step 38983: {'lr': 0.00042684422621968346, 'samples': 7484736, 'steps': 38982, 'loss/train': 1.5230143070220947} 08/30/2021 20:13:29 - INFO - __main__ - Step 38984: {'lr': 0.0004268404751789533, 'samples': 7484928, 'steps': 38983, 'loss/train': 1.1378527879714966} 08/30/2021 20:13:30 - INFO - __main__ - Step 38985: {'lr': 0.0004268367240585416, 'samples': 7485120, 'steps': 38984, 'loss/train': 1.434148907661438} 08/30/2021 20:13:31 - INFO - __main__ - Step 38986: {'lr': 0.0004268329728584499, 'samples': 7485312, 'steps': 38985, 'loss/train': 0.058183636516332626} 08/30/2021 20:13:31 - INFO - __main__ - Step 38987: {'lr': 0.0004268292215786801, 'samples': 7485504, 'steps': 38986, 'loss/train': 1.881852626800537} 08/30/2021 20:13:32 - INFO - __main__ - Step 38988: {'lr': 0.0004268254702192337, 'samples': 7485696, 'steps': 38987, 'loss/train': 1.5401113033294678} 08/30/2021 20:13:32 - INFO - __main__ - Step 38989: {'lr': 0.00042682171878011255, 'samples': 7485888, 'steps': 38988, 'loss/train': 0.6354928016662598} 08/30/2021 20:13:34 - INFO - __main__ - Step 38990: {'lr': 0.00042681796726131815, 'samples': 7486080, 'steps': 38989, 'loss/train': 1.691983938217163} 08/30/2021 20:13:34 - INFO - __main__ - Step 38991: {'lr': 0.0004268142156628524, 'samples': 7486272, 'steps': 38990, 'loss/train': 1.2542545795440674} 08/30/2021 20:13:34 - INFO - __main__ - Step 38992: {'lr': 0.00042681046398471693, 'samples': 7486464, 'steps': 38991, 'loss/train': 1.1526399850845337} 08/30/2021 20:13:35 - INFO - __main__ - Step 38993: {'lr': 0.00042680671222691325, 'samples': 7486656, 'steps': 38992, 'loss/train': 2.0675790309906006} 08/30/2021 20:13:35 - INFO - __main__ - Step 38994: {'lr': 0.0004268029603894433, 'samples': 7486848, 'steps': 38993, 'loss/train': 1.9092001914978027} 08/30/2021 20:13:37 - INFO - __main__ - Step 38995: {'lr': 0.00042679920847230865, 'samples': 7487040, 'steps': 38994, 'loss/train': 1.5690864324569702} 08/30/2021 20:13:37 - INFO - __main__ - Step 38996: {'lr': 0.000426795456475511, 'samples': 7487232, 'steps': 38995, 'loss/train': 1.309863805770874} 08/30/2021 20:13:37 - INFO - __main__ - Step 38997: {'lr': 0.00042679170439905204, 'samples': 7487424, 'steps': 38996, 'loss/train': 1.4097307920455933} 08/30/2021 20:13:38 - INFO - __main__ - Step 38998: {'lr': 0.0004267879522429334, 'samples': 7487616, 'steps': 38997, 'loss/train': 0.8415262699127197} 08/30/2021 20:13:38 - INFO - __main__ - Step 38999: {'lr': 0.00042678420000715687, 'samples': 7487808, 'steps': 38998, 'loss/train': 1.4544283151626587} 08/30/2021 20:13:40 - INFO - __main__ - Step 39000: {'lr': 0.0004267804476917242, 'samples': 7488000, 'steps': 38999, 'loss/train': 1.2814282178878784} 08/30/2021 20:13:40 - INFO - __main__ - Step 39001: {'lr': 0.00042677669529663686, 'samples': 7488192, 'steps': 39000, 'loss/train': 1.3801774978637695} 08/30/2021 20:13:40 - INFO - __main__ - Step 39002: {'lr': 0.0004267729428218968, 'samples': 7488384, 'steps': 39001, 'loss/train': 1.5354958772659302} 08/30/2021 20:13:41 - INFO - __main__ - Step 39003: {'lr': 0.0004267691902675055, 'samples': 7488576, 'steps': 39002, 'loss/train': 1.7666679620742798} 08/30/2021 20:13:41 - INFO - __main__ - Step 39004: {'lr': 0.0004267654376334647, 'samples': 7488768, 'steps': 39003, 'loss/train': 1.3279566764831543} 08/30/2021 20:13:41 - INFO - __main__ - Step 39005: {'lr': 0.00042676168491977617, 'samples': 7488960, 'steps': 39004, 'loss/train': 1.5926154851913452} 08/30/2021 20:13:43 - INFO - __main__ - Step 39006: {'lr': 0.00042675793212644156, 'samples': 7489152, 'steps': 39005, 'loss/train': 1.590686321258545} 08/30/2021 20:13:43 - INFO - __main__ - Step 39007: {'lr': 0.00042675417925346255, 'samples': 7489344, 'steps': 39006, 'loss/train': 2.3390822410583496} 08/30/2021 20:13:44 - INFO - __main__ - Step 39008: {'lr': 0.0004267504263008408, 'samples': 7489536, 'steps': 39007, 'loss/train': 1.6897366046905518} 08/30/2021 20:13:44 - INFO - __main__ - Step 39009: {'lr': 0.0004267466732685781, 'samples': 7489728, 'steps': 39008, 'loss/train': 1.3430382013320923} 08/30/2021 20:13:44 - INFO - __main__ - Step 39010: {'lr': 0.000426742920156676, 'samples': 7489920, 'steps': 39009, 'loss/train': 1.7711538076400757} 08/30/2021 20:13:46 - INFO - __main__ - Step 39011: {'lr': 0.00042673916696513625, 'samples': 7490112, 'steps': 39010, 'loss/train': 1.4898557662963867} 08/30/2021 20:13:46 - INFO - __main__ - Step 39012: {'lr': 0.0004267354136939607, 'samples': 7490304, 'steps': 39011, 'loss/train': 1.4680469036102295} 08/30/2021 20:13:47 - INFO - __main__ - Step 39013: {'lr': 0.0004267316603431508, 'samples': 7490496, 'steps': 39012, 'loss/train': 1.5781192779541016} 08/30/2021 20:13:47 - INFO - __main__ - Step 39014: {'lr': 0.00042672790691270835, 'samples': 7490688, 'steps': 39013, 'loss/train': 1.2442946434020996} 08/30/2021 20:13:48 - INFO - __main__ - Step 39015: {'lr': 0.00042672415340263507, 'samples': 7490880, 'steps': 39014, 'loss/train': 1.6976791620254517} 08/30/2021 20:13:49 - INFO - __main__ - Step 39016: {'lr': 0.00042672039981293255, 'samples': 7491072, 'steps': 39015, 'loss/train': 1.614533543586731} 08/30/2021 20:13:50 - INFO - __main__ - Step 39017: {'lr': 0.0004267166461436025, 'samples': 7491264, 'steps': 39016, 'loss/train': 1.3815348148345947} 08/30/2021 20:13:50 - INFO - __main__ - Step 39018: {'lr': 0.0004267128923946468, 'samples': 7491456, 'steps': 39017, 'loss/train': 1.6059067249298096} 08/30/2021 20:13:51 - INFO - __main__ - Step 39019: {'lr': 0.00042670913856606693, 'samples': 7491648, 'steps': 39018, 'loss/train': 1.1394164562225342} 08/30/2021 20:13:51 - INFO - __main__ - Step 39020: {'lr': 0.0004267053846578646, 'samples': 7491840, 'steps': 39019, 'loss/train': 1.4777863025665283} 08/30/2021 20:13:52 - INFO - __main__ - Step 39021: {'lr': 0.00042670163067004156, 'samples': 7492032, 'steps': 39020, 'loss/train': 1.1149781942367554} 08/30/2021 20:13:53 - INFO - __main__ - Step 39022: {'lr': 0.00042669787660259956, 'samples': 7492224, 'steps': 39021, 'loss/train': 0.8894286155700684} 08/30/2021 20:13:53 - INFO - __main__ - Step 39023: {'lr': 0.0004266941224555402, 'samples': 7492416, 'steps': 39022, 'loss/train': 2.54011869430542} 08/30/2021 20:13:54 - INFO - __main__ - Step 39024: {'lr': 0.0004266903682288652, 'samples': 7492608, 'steps': 39023, 'loss/train': 1.3905818462371826} 08/30/2021 20:13:54 - INFO - __main__ - Step 39025: {'lr': 0.00042668661392257626, 'samples': 7492800, 'steps': 39024, 'loss/train': 1.6680063009262085} 08/30/2021 20:13:56 - INFO - __main__ - Step 39026: {'lr': 0.00042668285953667497, 'samples': 7492992, 'steps': 39025, 'loss/train': 1.1222834587097168} 08/30/2021 20:13:56 - INFO - __main__ - Step 39027: {'lr': 0.0004266791050711632, 'samples': 7493184, 'steps': 39026, 'loss/train': 1.3310561180114746} 08/30/2021 20:13:56 - INFO - __main__ - Step 39028: {'lr': 0.0004266753505260425, 'samples': 7493376, 'steps': 39027, 'loss/train': 1.7979142665863037} 08/30/2021 20:13:57 - INFO - __main__ - Step 39029: {'lr': 0.00042667159590131467, 'samples': 7493568, 'steps': 39028, 'loss/train': 1.5943289995193481} 08/30/2021 20:13:57 - INFO - __main__ - Step 39030: {'lr': 0.0004266678411969813, 'samples': 7493760, 'steps': 39029, 'loss/train': 1.3485994338989258} 08/30/2021 20:13:59 - INFO - __main__ - Step 39031: {'lr': 0.0004266640864130441, 'samples': 7493952, 'steps': 39030, 'loss/train': 1.3079279661178589} 08/30/2021 20:13:59 - INFO - __main__ - Step 39032: {'lr': 0.00042666033154950485, 'samples': 7494144, 'steps': 39031, 'loss/train': 1.6716195344924927} 08/30/2021 20:13:59 - INFO - __main__ - Step 39033: {'lr': 0.00042665657660636517, 'samples': 7494336, 'steps': 39032, 'loss/train': 1.573898196220398} 08/30/2021 20:14:00 - INFO - __main__ - Step 39034: {'lr': 0.0004266528215836267, 'samples': 7494528, 'steps': 39033, 'loss/train': 1.597040057182312} 08/30/2021 20:14:00 - INFO - __main__ - Step 39035: {'lr': 0.0004266490664812913, 'samples': 7494720, 'steps': 39034, 'loss/train': 1.586173176765442} 08/30/2021 20:14:01 - INFO - __main__ - Step 39036: {'lr': 0.00042664531129936044, 'samples': 7494912, 'steps': 39035, 'loss/train': 1.112544298171997} 08/30/2021 20:14:02 - INFO - __main__ - Step 39037: {'lr': 0.00042664155603783606, 'samples': 7495104, 'steps': 39036, 'loss/train': 1.3590707778930664} 08/30/2021 20:14:03 - INFO - __main__ - Step 39038: {'lr': 0.00042663780069671965, 'samples': 7495296, 'steps': 39037, 'loss/train': 2.1780588626861572} 08/30/2021 20:14:03 - INFO - __main__ - Step 39039: {'lr': 0.00042663404527601293, 'samples': 7495488, 'steps': 39038, 'loss/train': 0.46188870072364807} 08/30/2021 20:14:03 - INFO - __main__ - Step 39040: {'lr': 0.00042663028977571774, 'samples': 7495680, 'steps': 39039, 'loss/train': 1.2312473058700562} 08/30/2021 20:14:04 - INFO - __main__ - Step 39041: {'lr': 0.0004266265341958355, 'samples': 7495872, 'steps': 39040, 'loss/train': 1.8984804153442383} 08/30/2021 20:14:05 - INFO - __main__ - Step 39042: {'lr': 0.0004266227785363682, 'samples': 7496064, 'steps': 39041, 'loss/train': 1.8092193603515625} 08/30/2021 20:14:05 - INFO - __main__ - Step 39043: {'lr': 0.0004266190227973174, 'samples': 7496256, 'steps': 39042, 'loss/train': 1.4890114068984985} 08/30/2021 20:14:06 - INFO - __main__ - Step 39044: {'lr': 0.00042661526697868475, 'samples': 7496448, 'steps': 39043, 'loss/train': 0.5905696153640747} 08/30/2021 20:14:06 - INFO - __main__ - Step 39045: {'lr': 0.000426611511080472, 'samples': 7496640, 'steps': 39044, 'loss/train': 1.751371145248413} 08/30/2021 20:14:06 - INFO - __main__ - Step 39046: {'lr': 0.0004266077551026809, 'samples': 7496832, 'steps': 39045, 'loss/train': 1.410527229309082} 08/30/2021 20:14:08 - INFO - __main__ - Step 39047: {'lr': 0.000426603999045313, 'samples': 7497024, 'steps': 39046, 'loss/train': 1.6472623348236084} 08/30/2021 20:14:09 - INFO - __main__ - Step 39048: {'lr': 0.00042660024290837003, 'samples': 7497216, 'steps': 39047, 'loss/train': 0.04206864535808563} 08/30/2021 20:14:09 - INFO - __main__ - Step 39049: {'lr': 0.00042659648669185376, 'samples': 7497408, 'steps': 39048, 'loss/train': 1.561629056930542} 08/30/2021 20:14:09 - INFO - __main__ - Step 39050: {'lr': 0.0004265927303957658, 'samples': 7497600, 'steps': 39049, 'loss/train': 1.5536412000656128} 08/30/2021 20:14:10 - INFO - __main__ - Step 39051: {'lr': 0.0004265889740201079, 'samples': 7497792, 'steps': 39050, 'loss/train': 1.8471053838729858} 08/30/2021 20:14:10 - INFO - __main__ - Step 39052: {'lr': 0.0004265852175648818, 'samples': 7497984, 'steps': 39051, 'loss/train': 1.4708019495010376} 08/30/2021 20:14:12 - INFO - __main__ - Step 39053: {'lr': 0.00042658146103008904, 'samples': 7498176, 'steps': 39052, 'loss/train': 1.2126667499542236} 08/30/2021 20:14:13 - INFO - __main__ - Step 39054: {'lr': 0.0004265777044157314, 'samples': 7498368, 'steps': 39053, 'loss/train': 1.099593162536621} 08/30/2021 20:14:13 - INFO - __main__ - Step 39055: {'lr': 0.0004265739477218106, 'samples': 7498560, 'steps': 39054, 'loss/train': 1.913072943687439} 08/30/2021 20:14:13 - INFO - __main__ - Step 39056: {'lr': 0.0004265701909483283, 'samples': 7498752, 'steps': 39055, 'loss/train': 1.4912137985229492} 08/30/2021 20:14:14 - INFO - __main__ - Step 39057: {'lr': 0.0004265664340952862, 'samples': 7498944, 'steps': 39056, 'loss/train': 1.2456638813018799} 08/30/2021 20:14:15 - INFO - __main__ - Step 39058: {'lr': 0.00042656267716268596, 'samples': 7499136, 'steps': 39057, 'loss/train': 0.7144192457199097} 08/30/2021 20:14:16 - INFO - __main__ - Step 39059: {'lr': 0.00042655892015052945, 'samples': 7499328, 'steps': 39058, 'loss/train': 1.4376308917999268} 08/30/2021 20:14:16 - INFO - __main__ - Step 39060: {'lr': 0.00042655516305881803, 'samples': 7499520, 'steps': 39059, 'loss/train': 1.449514389038086} 08/30/2021 20:14:16 - INFO - __main__ - Step 39061: {'lr': 0.00042655140588755366, 'samples': 7499712, 'steps': 39060, 'loss/train': 1.37236750125885} 08/30/2021 20:14:17 - INFO - __main__ - Step 39062: {'lr': 0.0004265476486367379, 'samples': 7499904, 'steps': 39061, 'loss/train': 1.8755433559417725} 08/30/2021 20:14:17 - INFO - __main__ - Step 39063: {'lr': 0.00042654389130637255, 'samples': 7500096, 'steps': 39062, 'loss/train': 1.4207885265350342} 08/30/2021 20:14:19 - INFO - __main__ - Step 39064: {'lr': 0.0004265401338964592, 'samples': 7500288, 'steps': 39063, 'loss/train': 1.5218433141708374} 08/30/2021 20:14:19 - INFO - __main__ - Step 39065: {'lr': 0.0004265363764069997, 'samples': 7500480, 'steps': 39064, 'loss/train': 1.3951611518859863} 08/30/2021 20:14:20 - INFO - __main__ - Step 39066: {'lr': 0.0004265326188379955, 'samples': 7500672, 'steps': 39065, 'loss/train': 1.4596272706985474} 08/30/2021 20:14:20 - INFO - __main__ - Step 39067: {'lr': 0.00042652886118944844, 'samples': 7500864, 'steps': 39066, 'loss/train': 1.3833550214767456} 08/30/2021 20:14:20 - INFO - __main__ - Step 39068: {'lr': 0.0004265251034613603, 'samples': 7501056, 'steps': 39067, 'loss/train': 1.3588005304336548} 08/30/2021 20:14:22 - INFO - __main__ - Step 39069: {'lr': 0.0004265213456537326, 'samples': 7501248, 'steps': 39068, 'loss/train': 1.6298719644546509} 08/30/2021 20:14:23 - INFO - __main__ - Step 39070: {'lr': 0.0004265175877665671, 'samples': 7501440, 'steps': 39069, 'loss/train': 1.5082911252975464} 08/30/2021 20:14:23 - INFO - __main__ - Step 39071: {'lr': 0.0004265138297998655, 'samples': 7501632, 'steps': 39070, 'loss/train': 1.578966498374939} 08/30/2021 20:14:23 - INFO - __main__ - Step 39072: {'lr': 0.0004265100717536295, 'samples': 7501824, 'steps': 39071, 'loss/train': 0.1390034556388855} 08/30/2021 20:14:24 - INFO - __main__ - Step 39073: {'lr': 0.0004265063136278608, 'samples': 7502016, 'steps': 39072, 'loss/train': 0.05011961981654167} 08/30/2021 20:14:26 - INFO - __main__ - Step 39074: {'lr': 0.00042650255542256107, 'samples': 7502208, 'steps': 39073, 'loss/train': 1.4226551055908203} 08/30/2021 20:14:26 - INFO - __main__ - Step 39075: {'lr': 0.000426498797137732, 'samples': 7502400, 'steps': 39074, 'loss/train': 1.2472825050354004} 08/30/2021 20:14:27 - INFO - __main__ - Step 39076: {'lr': 0.00042649503877337523, 'samples': 7502592, 'steps': 39075, 'loss/train': 2.1044628620147705} 08/30/2021 20:14:27 - INFO - __main__ - Step 39077: {'lr': 0.0004264912803294926, 'samples': 7502784, 'steps': 39076, 'loss/train': 1.8073034286499023} 08/30/2021 20:14:27 - INFO - __main__ - Step 39078: {'lr': 0.0004264875218060857, 'samples': 7502976, 'steps': 39077, 'loss/train': 1.684946894645691} 08/30/2021 20:14:29 - INFO - __main__ - Step 39079: {'lr': 0.00042648376320315634, 'samples': 7503168, 'steps': 39078, 'loss/train': 1.5687719583511353} 08/30/2021 20:14:29 - INFO - __main__ - Step 39080: {'lr': 0.000426480004520706, 'samples': 7503360, 'steps': 39079, 'loss/train': 0.0665900930762291} 08/30/2021 20:14:29 - INFO - __main__ - Step 39081: {'lr': 0.00042647624575873656, 'samples': 7503552, 'steps': 39080, 'loss/train': 1.672710657119751} 08/30/2021 20:14:30 - INFO - __main__ - Step 39082: {'lr': 0.0004264724869172496, 'samples': 7503744, 'steps': 39081, 'loss/train': 1.476485013961792} 08/30/2021 20:14:30 - INFO - __main__ - Step 39083: {'lr': 0.00042646872799624694, 'samples': 7503936, 'steps': 39082, 'loss/train': 1.4662269353866577} 08/30/2021 20:14:32 - INFO - __main__ - Step 39084: {'lr': 0.00042646496899573005, 'samples': 7504128, 'steps': 39083, 'loss/train': 1.0886486768722534} 08/30/2021 20:14:32 - INFO - __main__ - Step 39085: {'lr': 0.0004264612099157009, 'samples': 7504320, 'steps': 39084, 'loss/train': 1.6391215324401855} 08/30/2021 20:14:32 - INFO - __main__ - Step 39086: {'lr': 0.00042645745075616106, 'samples': 7504512, 'steps': 39085, 'loss/train': 1.3249776363372803} 08/30/2021 20:14:33 - INFO - __main__ - Step 39087: {'lr': 0.0004264536915171121, 'samples': 7504704, 'steps': 39086, 'loss/train': 0.7305589318275452} 08/30/2021 20:14:33 - INFO - __main__ - Step 39088: {'lr': 0.0004264499321985559, 'samples': 7504896, 'steps': 39087, 'loss/train': 1.3197695016860962} 08/30/2021 20:14:35 - INFO - __main__ - Step 39089: {'lr': 0.0004264461728004941, 'samples': 7505088, 'steps': 39088, 'loss/train': 0.15367215871810913} 08/30/2021 20:14:35 - INFO - __main__ - Step 39090: {'lr': 0.0004264424133229283, 'samples': 7505280, 'steps': 39089, 'loss/train': 1.4112424850463867} 08/30/2021 20:14:35 - INFO - __main__ - Step 39091: {'lr': 0.0004264386537658603, 'samples': 7505472, 'steps': 39090, 'loss/train': 1.0174434185028076} 08/30/2021 20:14:36 - INFO - __main__ - Step 39092: {'lr': 0.0004264348941292919, 'samples': 7505664, 'steps': 39091, 'loss/train': 0.962507426738739} 08/30/2021 20:14:36 - INFO - __main__ - Step 39093: {'lr': 0.0004264311344132245, 'samples': 7505856, 'steps': 39092, 'loss/train': 1.2160069942474365} 08/30/2021 20:14:37 - INFO - __main__ - Step 39094: {'lr': 0.00042642737461766003, 'samples': 7506048, 'steps': 39093, 'loss/train': 1.3217370510101318} 08/30/2021 20:14:38 - INFO - __main__ - Step 39095: {'lr': 0.0004264236147426, 'samples': 7506240, 'steps': 39094, 'loss/train': 1.3808517456054688} 08/30/2021 20:14:39 - INFO - __main__ - Step 39096: {'lr': 0.0004264198547880464, 'samples': 7506432, 'steps': 39095, 'loss/train': 1.059320092201233} 08/30/2021 20:14:39 - INFO - __main__ - Step 39097: {'lr': 0.00042641609475400054, 'samples': 7506624, 'steps': 39096, 'loss/train': 1.7606483697891235} 08/30/2021 20:14:39 - INFO - __main__ - Step 39098: {'lr': 0.0004264123346404644, 'samples': 7506816, 'steps': 39097, 'loss/train': 1.3320167064666748} 08/30/2021 20:14:40 - INFO - __main__ - Step 39099: {'lr': 0.0004264085744474396, 'samples': 7507008, 'steps': 39098, 'loss/train': 1.9074100255966187} 08/30/2021 20:14:41 - INFO - __main__ - Step 39100: {'lr': 0.0004264048141749278, 'samples': 7507200, 'steps': 39099, 'loss/train': 1.4979037046432495} 08/30/2021 20:14:42 - INFO - __main__ - Step 39101: {'lr': 0.00042640105382293073, 'samples': 7507392, 'steps': 39100, 'loss/train': 0.907530665397644} 08/30/2021 20:14:42 - INFO - __main__ - Step 39102: {'lr': 0.00042639729339145004, 'samples': 7507584, 'steps': 39101, 'loss/train': 0.15617690980434418} 08/30/2021 20:14:43 - INFO - __main__ - Step 39103: {'lr': 0.0004263935328804874, 'samples': 7507776, 'steps': 39102, 'loss/train': 0.2130056768655777} 08/30/2021 20:14:43 - INFO - __main__ - Step 39104: {'lr': 0.0004263897722900447, 'samples': 7507968, 'steps': 39103, 'loss/train': 1.9279919862747192} 08/30/2021 20:14:43 - INFO - __main__ - Step 39105: {'lr': 0.0004263860116201234, 'samples': 7508160, 'steps': 39104, 'loss/train': 1.8019262552261353} 08/30/2021 20:14:45 - INFO - __main__ - Step 39106: {'lr': 0.00042638225087072523, 'samples': 7508352, 'steps': 39105, 'loss/train': 1.7949875593185425} 08/30/2021 20:14:45 - INFO - __main__ - Step 39107: {'lr': 0.00042637849004185203, 'samples': 7508544, 'steps': 39106, 'loss/train': 1.3953295946121216} 08/30/2021 20:14:46 - INFO - __main__ - Step 39108: {'lr': 0.0004263747291335054, 'samples': 7508736, 'steps': 39107, 'loss/train': 1.1228476762771606} 08/30/2021 20:14:46 - INFO - __main__ - Step 39109: {'lr': 0.00042637096814568696, 'samples': 7508928, 'steps': 39108, 'loss/train': 1.1814470291137695} 08/30/2021 20:14:46 - INFO - __main__ - Step 39110: {'lr': 0.0004263672070783986, 'samples': 7509120, 'steps': 39109, 'loss/train': 1.302478551864624} 08/30/2021 20:14:48 - INFO - __main__ - Step 39111: {'lr': 0.0004263634459316418, 'samples': 7509312, 'steps': 39110, 'loss/train': 1.102424144744873} 08/30/2021 20:14:48 - INFO - __main__ - Step 39112: {'lr': 0.0004263596847054184, 'samples': 7509504, 'steps': 39111, 'loss/train': 1.7552907466888428} 08/30/2021 20:14:49 - INFO - __main__ - Step 39113: {'lr': 0.00042635592339973006, 'samples': 7509696, 'steps': 39112, 'loss/train': 1.0346333980560303} 08/30/2021 20:14:49 - INFO - __main__ - Step 39114: {'lr': 0.00042635216201457836, 'samples': 7509888, 'steps': 39113, 'loss/train': 1.3420451879501343} 08/30/2021 20:14:49 - INFO - __main__ - Step 39115: {'lr': 0.00042634840054996527, 'samples': 7510080, 'steps': 39114, 'loss/train': 2.001659631729126} 08/30/2021 20:14:50 - INFO - __main__ - Step 39116: {'lr': 0.00042634463900589214, 'samples': 7510272, 'steps': 39115, 'loss/train': 1.4357761144638062} 08/30/2021 20:14:51 - INFO - __main__ - Step 39117: {'lr': 0.0004263408773823609, 'samples': 7510464, 'steps': 39116, 'loss/train': 0.5859894752502441} 08/30/2021 20:14:51 - INFO - __main__ - Step 39118: {'lr': 0.00042633711567937325, 'samples': 7510656, 'steps': 39117, 'loss/train': 1.568800449371338} 08/30/2021 20:14:52 - INFO - __main__ - Step 39119: {'lr': 0.00042633335389693073, 'samples': 7510848, 'steps': 39118, 'loss/train': 1.540902018547058} 08/30/2021 20:14:52 - INFO - __main__ - Step 39120: {'lr': 0.0004263295920350352, 'samples': 7511040, 'steps': 39119, 'loss/train': 1.9303350448608398} 08/30/2021 20:14:52 - INFO - __main__ - Step 39121: {'lr': 0.0004263258300936882, 'samples': 7511232, 'steps': 39120, 'loss/train': 1.1475542783737183} 08/30/2021 20:14:54 - INFO - __main__ - Step 39122: {'lr': 0.00042632206807289154, 'samples': 7511424, 'steps': 39121, 'loss/train': 1.180432677268982} 08/30/2021 20:14:55 - INFO - __main__ - Step 39123: {'lr': 0.00042631830597264687, 'samples': 7511616, 'steps': 39122, 'loss/train': 1.460362195968628} 08/30/2021 20:14:55 - INFO - __main__ - Step 39124: {'lr': 0.0004263145437929559, 'samples': 7511808, 'steps': 39123, 'loss/train': 0.7202699184417725} 08/30/2021 20:14:55 - INFO - __main__ - Step 39125: {'lr': 0.0004263107815338203, 'samples': 7512000, 'steps': 39124, 'loss/train': 1.0189943313598633} 08/30/2021 20:14:56 - INFO - __main__ - Step 39126: {'lr': 0.00042630701919524176, 'samples': 7512192, 'steps': 39125, 'loss/train': 2.0857889652252197} 08/30/2021 20:14:58 - INFO - __main__ - Step 39127: {'lr': 0.00042630325677722204, 'samples': 7512384, 'steps': 39126, 'loss/train': 0.7416525483131409} 08/30/2021 20:14:58 - INFO - __main__ - Step 39128: {'lr': 0.0004262994942797628, 'samples': 7512576, 'steps': 39127, 'loss/train': 1.3737872838974} 08/30/2021 20:14:59 - INFO - __main__ - Step 39129: {'lr': 0.0004262957317028657, 'samples': 7512768, 'steps': 39128, 'loss/train': 1.5676079988479614} 08/30/2021 20:14:59 - INFO - __main__ - Step 39130: {'lr': 0.00042629196904653245, 'samples': 7512960, 'steps': 39129, 'loss/train': 0.9293034076690674} 08/30/2021 20:14:59 - INFO - __main__ - Step 39131: {'lr': 0.00042628820631076484, 'samples': 7513152, 'steps': 39130, 'loss/train': 0.6962493062019348} 08/30/2021 20:15:00 - INFO - __main__ - Step 39132: {'lr': 0.0004262844434955644, 'samples': 7513344, 'steps': 39131, 'loss/train': 1.7585588693618774} 08/30/2021 20:15:02 - INFO - __main__ - Step 39133: {'lr': 0.00042628068060093294, 'samples': 7513536, 'steps': 39132, 'loss/train': 1.7021483182907104} 08/30/2021 20:15:02 - INFO - __main__ - Step 39134: {'lr': 0.0004262769176268722, 'samples': 7513728, 'steps': 39133, 'loss/train': 1.4474977254867554} 08/30/2021 20:15:02 - INFO - __main__ - Step 39135: {'lr': 0.0004262731545733837, 'samples': 7513920, 'steps': 39134, 'loss/train': 1.8324302434921265} 08/30/2021 20:15:03 - INFO - __main__ - Step 39136: {'lr': 0.0004262693914404692, 'samples': 7514112, 'steps': 39135, 'loss/train': 1.6235870122909546} 08/30/2021 20:15:03 - INFO - __main__ - Step 39137: {'lr': 0.0004262656282281305, 'samples': 7514304, 'steps': 39136, 'loss/train': 1.699751615524292} 08/30/2021 20:15:05 - INFO - __main__ - Step 39138: {'lr': 0.0004262618649363692, 'samples': 7514496, 'steps': 39137, 'loss/train': 3.4799325466156006} 08/30/2021 20:15:05 - INFO - __main__ - Step 39139: {'lr': 0.0004262581015651871, 'samples': 7514688, 'steps': 39138, 'loss/train': 1.3937004804611206} 08/30/2021 20:15:06 - INFO - __main__ - Step 39140: {'lr': 0.0004262543381145857, 'samples': 7514880, 'steps': 39139, 'loss/train': 1.8962650299072266} 08/30/2021 20:15:06 - INFO - __main__ - Step 39141: {'lr': 0.0004262505745845669, 'samples': 7515072, 'steps': 39140, 'loss/train': 0.09406972676515579} 08/30/2021 20:15:06 - INFO - __main__ - Step 39142: {'lr': 0.0004262468109751323, 'samples': 7515264, 'steps': 39141, 'loss/train': 2.190310001373291} 08/30/2021 20:15:08 - INFO - __main__ - Step 39143: {'lr': 0.0004262430472862836, 'samples': 7515456, 'steps': 39142, 'loss/train': 1.079997181892395} 08/30/2021 20:15:08 - INFO - __main__ - Step 39144: {'lr': 0.00042623928351802245, 'samples': 7515648, 'steps': 39143, 'loss/train': 1.3742101192474365} 08/30/2021 20:15:09 - INFO - __main__ - Step 39145: {'lr': 0.00042623551967035066, 'samples': 7515840, 'steps': 39144, 'loss/train': 1.6789116859436035} 08/30/2021 20:15:09 - INFO - __main__ - Step 39146: {'lr': 0.0004262317557432699, 'samples': 7516032, 'steps': 39145, 'loss/train': 2.3123044967651367} 08/30/2021 20:15:09 - INFO - __main__ - Step 39147: {'lr': 0.0004262279917367817, 'samples': 7516224, 'steps': 39146, 'loss/train': 1.5434142351150513} 08/30/2021 20:15:10 - INFO - __main__ - Step 39148: {'lr': 0.00042622422765088805, 'samples': 7516416, 'steps': 39147, 'loss/train': 1.468110203742981} 08/30/2021 20:15:11 - INFO - __main__ - Step 39149: {'lr': 0.00042622046348559034, 'samples': 7516608, 'steps': 39148, 'loss/train': 1.066454291343689} 08/30/2021 20:15:12 - INFO - __main__ - Step 39150: {'lr': 0.00042621669924089044, 'samples': 7516800, 'steps': 39149, 'loss/train': 1.9181402921676636} 08/30/2021 20:15:12 - INFO - __main__ - Step 39151: {'lr': 0.00042621293491679007, 'samples': 7516992, 'steps': 39150, 'loss/train': 1.5696115493774414} 08/30/2021 20:15:12 - INFO - __main__ - Step 39152: {'lr': 0.00042620917051329086, 'samples': 7517184, 'steps': 39151, 'loss/train': 1.254530668258667} 08/30/2021 20:15:13 - INFO - __main__ - Step 39153: {'lr': 0.0004262054060303945, 'samples': 7517376, 'steps': 39152, 'loss/train': 1.6173115968704224} 08/30/2021 20:15:14 - INFO - __main__ - Step 39154: {'lr': 0.00042620164146810267, 'samples': 7517568, 'steps': 39153, 'loss/train': 1.3876872062683105} 08/30/2021 20:15:15 - INFO - __main__ - Step 39155: {'lr': 0.0004261978768264172, 'samples': 7517760, 'steps': 39154, 'loss/train': 1.2458218336105347} 08/30/2021 20:15:15 - INFO - __main__ - Step 39156: {'lr': 0.00042619411210533957, 'samples': 7517952, 'steps': 39155, 'loss/train': 1.3571326732635498} 08/30/2021 20:15:15 - INFO - __main__ - Step 39157: {'lr': 0.00042619034730487167, 'samples': 7518144, 'steps': 39156, 'loss/train': 0.08076008409261703} 08/30/2021 20:15:16 - INFO - __main__ - Step 39158: {'lr': 0.00042618658242501507, 'samples': 7518336, 'steps': 39157, 'loss/train': 1.8906840085983276} 08/30/2021 20:15:17 - INFO - __main__ - Step 39159: {'lr': 0.0004261828174657716, 'samples': 7518528, 'steps': 39158, 'loss/train': 0.06880287081003189} 08/30/2021 20:15:18 - INFO - __main__ - Step 39160: {'lr': 0.0004261790524271427, 'samples': 7518720, 'steps': 39159, 'loss/train': 1.4318112134933472} 08/30/2021 20:15:18 - INFO - __main__ - Step 39161: {'lr': 0.00042617528730913036, 'samples': 7518912, 'steps': 39160, 'loss/train': 1.2938989400863647} 08/30/2021 20:15:19 - INFO - __main__ - Step 39162: {'lr': 0.00042617152211173615, 'samples': 7519104, 'steps': 39161, 'loss/train': 1.4352787733078003} 08/30/2021 20:15:19 - INFO - __main__ - Step 39163: {'lr': 0.0004261677568349618, 'samples': 7519296, 'steps': 39162, 'loss/train': 1.2439548969268799} 08/30/2021 20:15:20 - INFO - __main__ - Step 39164: {'lr': 0.0004261639914788089, 'samples': 7519488, 'steps': 39163, 'loss/train': 1.2463551759719849} 08/30/2021 20:15:21 - INFO - __main__ - Step 39165: {'lr': 0.0004261602260432792, 'samples': 7519680, 'steps': 39164, 'loss/train': 1.2323464155197144} 08/30/2021 20:15:21 - INFO - __main__ - Step 39166: {'lr': 0.0004261564605283745, 'samples': 7519872, 'steps': 39165, 'loss/train': 1.5970195531845093} 08/30/2021 20:15:22 - INFO - __main__ - Step 39167: {'lr': 0.0004261526949340965, 'samples': 7520064, 'steps': 39166, 'loss/train': 1.86358642578125} 08/30/2021 20:15:22 - INFO - __main__ - Step 39168: {'lr': 0.0004261489292604467, 'samples': 7520256, 'steps': 39167, 'loss/train': 1.248688817024231} 08/30/2021 20:15:23 - INFO - __main__ - Step 39169: {'lr': 0.0004261451635074269, 'samples': 7520448, 'steps': 39168, 'loss/train': 1.2779831886291504} 08/30/2021 20:15:24 - INFO - __main__ - Step 39170: {'lr': 0.0004261413976750388, 'samples': 7520640, 'steps': 39169, 'loss/train': 1.563864827156067} 08/30/2021 20:15:24 - INFO - __main__ - Step 39171: {'lr': 0.00042613763176328415, 'samples': 7520832, 'steps': 39170, 'loss/train': 1.3924736976623535} 08/30/2021 20:15:24 - INFO - __main__ - Step 39172: {'lr': 0.00042613386577216455, 'samples': 7521024, 'steps': 39171, 'loss/train': 1.9655263423919678} 08/30/2021 20:15:25 - INFO - __main__ - Step 39173: {'lr': 0.0004261300997016818, 'samples': 7521216, 'steps': 39172, 'loss/train': 0.9479031562805176} 08/30/2021 20:15:26 - INFO - __main__ - Step 39174: {'lr': 0.0004261263335518375, 'samples': 7521408, 'steps': 39173, 'loss/train': 1.9122108221054077} 08/30/2021 20:15:27 - INFO - __main__ - Step 39175: {'lr': 0.00042612256732263345, 'samples': 7521600, 'steps': 39174, 'loss/train': 1.4972925186157227} 08/30/2021 20:15:27 - INFO - __main__ - Step 39176: {'lr': 0.0004261188010140712, 'samples': 7521792, 'steps': 39175, 'loss/train': 1.7078129053115845} 08/30/2021 20:15:27 - INFO - __main__ - Step 39177: {'lr': 0.00042611503462615266, 'samples': 7521984, 'steps': 39176, 'loss/train': 1.2863445281982422} 08/30/2021 20:15:28 - INFO - __main__ - Step 39178: {'lr': 0.0004261112681588793, 'samples': 7522176, 'steps': 39177, 'loss/train': 1.2235257625579834} 08/30/2021 20:15:30 - INFO - __main__ - Step 39179: {'lr': 0.000426107501612253, 'samples': 7522368, 'steps': 39178, 'loss/train': 2.2244679927825928} 08/30/2021 20:15:31 - INFO - __main__ - Step 39180: {'lr': 0.0004261037349862753, 'samples': 7522560, 'steps': 39179, 'loss/train': 1.0812623500823975} 08/30/2021 20:15:31 - INFO - __main__ - Step 39181: {'lr': 0.000426099968280948, 'samples': 7522752, 'steps': 39180, 'loss/train': 0.9474536180496216} 08/30/2021 20:15:31 - INFO - __main__ - Step 39182: {'lr': 0.00042609620149627284, 'samples': 7522944, 'steps': 39181, 'loss/train': 1.2128833532333374} 08/30/2021 20:15:32 - INFO - __main__ - Step 39183: {'lr': 0.00042609243463225134, 'samples': 7523136, 'steps': 39182, 'loss/train': 1.0542069673538208} 08/30/2021 20:15:32 - INFO - __main__ - Step 39184: {'lr': 0.00042608866768888533, 'samples': 7523328, 'steps': 39183, 'loss/train': 1.7255816459655762} 08/30/2021 20:15:34 - INFO - __main__ - Step 39185: {'lr': 0.0004260849006661765, 'samples': 7523520, 'steps': 39184, 'loss/train': 0.14229607582092285} 08/30/2021 20:15:34 - INFO - __main__ - Step 39186: {'lr': 0.0004260811335641266, 'samples': 7523712, 'steps': 39185, 'loss/train': 1.5025449991226196} 08/30/2021 20:15:34 - INFO - __main__ - Step 39187: {'lr': 0.0004260773663827372, 'samples': 7523904, 'steps': 39186, 'loss/train': 1.7135591506958008} 08/30/2021 20:15:35 - INFO - __main__ - Step 39188: {'lr': 0.00042607359912201004, 'samples': 7524096, 'steps': 39187, 'loss/train': 5.811387062072754} 08/30/2021 20:15:35 - INFO - __main__ - Step 39189: {'lr': 0.0004260698317819468, 'samples': 7524288, 'steps': 39188, 'loss/train': 1.4644395112991333} 08/30/2021 20:15:35 - INFO - __main__ - Step 39190: {'lr': 0.00042606606436254926, 'samples': 7524480, 'steps': 39189, 'loss/train': 1.6314276456832886} 08/30/2021 20:15:37 - INFO - __main__ - Step 39191: {'lr': 0.000426062296863819, 'samples': 7524672, 'steps': 39190, 'loss/train': 1.338916301727295} 08/30/2021 20:15:38 - INFO - __main__ - Step 39192: {'lr': 0.00042605852928575796, 'samples': 7524864, 'steps': 39191, 'loss/train': 1.9953043460845947} 08/30/2021 20:15:38 - INFO - __main__ - Step 39193: {'lr': 0.00042605476162836756, 'samples': 7525056, 'steps': 39192, 'loss/train': 1.5283734798431396} 08/30/2021 20:15:38 - INFO - __main__ - Step 39194: {'lr': 0.00042605099389164957, 'samples': 7525248, 'steps': 39193, 'loss/train': 1.6781046390533447} 08/30/2021 20:15:39 - INFO - __main__ - Step 39195: {'lr': 0.00042604722607560575, 'samples': 7525440, 'steps': 39194, 'loss/train': 1.2429226636886597} 08/30/2021 20:15:40 - INFO - __main__ - Step 39196: {'lr': 0.0004260434581802377, 'samples': 7525632, 'steps': 39195, 'loss/train': 1.4645442962646484} 08/30/2021 20:15:41 - INFO - __main__ - Step 39197: {'lr': 0.0004260396902055473, 'samples': 7525824, 'steps': 39196, 'loss/train': 0.0686180517077446} 08/30/2021 20:15:41 - INFO - __main__ - Step 39198: {'lr': 0.0004260359221515361, 'samples': 7526016, 'steps': 39197, 'loss/train': 1.7838993072509766} 08/30/2021 20:15:41 - INFO - __main__ - Step 39199: {'lr': 0.0004260321540182057, 'samples': 7526208, 'steps': 39198, 'loss/train': 1.4074504375457764} 08/30/2021 20:15:42 - INFO - __main__ - Step 39200: {'lr': 0.00042602838580555814, 'samples': 7526400, 'steps': 39199, 'loss/train': 1.5589021444320679} 08/30/2021 20:15:43 - INFO - __main__ - Step 39201: {'lr': 0.0004260246175135948, 'samples': 7526592, 'steps': 39200, 'loss/train': 1.4375873804092407} 08/30/2021 20:15:44 - INFO - __main__ - Step 39202: {'lr': 0.00042602084914231743, 'samples': 7526784, 'steps': 39201, 'loss/train': 1.554763913154602} 08/30/2021 20:15:44 - INFO - __main__ - Step 39203: {'lr': 0.0004260170806917278, 'samples': 7526976, 'steps': 39202, 'loss/train': 1.6370964050292969} 08/30/2021 20:15:45 - INFO - __main__ - Step 39204: {'lr': 0.0004260133121618276, 'samples': 7527168, 'steps': 39203, 'loss/train': 1.733738899230957} 08/30/2021 20:15:45 - INFO - __main__ - Step 39205: {'lr': 0.0004260095435526186, 'samples': 7527360, 'steps': 39204, 'loss/train': 1.4207985401153564} 08/30/2021 20:15:46 - INFO - __main__ - Step 39206: {'lr': 0.0004260057748641024, 'samples': 7527552, 'steps': 39205, 'loss/train': 0.0773579478263855} 08/30/2021 20:15:47 - INFO - __main__ - Step 39207: {'lr': 0.00042600200609628063, 'samples': 7527744, 'steps': 39206, 'loss/train': 1.6099849939346313} 08/30/2021 20:15:47 - INFO - __main__ - Step 39208: {'lr': 0.0004259982372491551, 'samples': 7527936, 'steps': 39207, 'loss/train': 1.5052069425582886} 08/30/2021 20:15:48 - INFO - __main__ - Step 39209: {'lr': 0.00042599446832272746, 'samples': 7528128, 'steps': 39208, 'loss/train': 1.2605875730514526} 08/30/2021 20:15:48 - INFO - __main__ - Step 39210: {'lr': 0.0004259906993169995, 'samples': 7528320, 'steps': 39209, 'loss/train': 1.5393530130386353} 08/30/2021 20:15:49 - INFO - __main__ - Step 39211: {'lr': 0.00042598693023197283, 'samples': 7528512, 'steps': 39210, 'loss/train': 1.4948527812957764} 08/30/2021 20:15:50 - INFO - __main__ - Step 39212: {'lr': 0.00042598316106764913, 'samples': 7528704, 'steps': 39211, 'loss/train': 0.7949560880661011} 08/30/2021 20:15:50 - INFO - __main__ - Step 39213: {'lr': 0.0004259793918240302, 'samples': 7528896, 'steps': 39212, 'loss/train': 2.4645466804504395} 08/30/2021 20:15:50 - INFO - __main__ - Step 39214: {'lr': 0.00042597562250111753, 'samples': 7529088, 'steps': 39213, 'loss/train': 1.5193893909454346} 08/30/2021 20:15:51 - INFO - __main__ - Step 39215: {'lr': 0.00042597185309891305, 'samples': 7529280, 'steps': 39214, 'loss/train': 1.2662200927734375} 08/30/2021 20:15:51 - INFO - __main__ - Step 39216: {'lr': 0.0004259680836174184, 'samples': 7529472, 'steps': 39215, 'loss/train': 1.31745445728302} 08/30/2021 20:15:53 - INFO - __main__ - Step 39217: {'lr': 0.0004259643140566352, 'samples': 7529664, 'steps': 39216, 'loss/train': 1.2903964519500732} 08/30/2021 20:15:53 - INFO - __main__ - Step 39218: {'lr': 0.0004259605444165652, 'samples': 7529856, 'steps': 39217, 'loss/train': 1.7505873441696167} 08/30/2021 20:15:54 - INFO - __main__ - Step 39219: {'lr': 0.0004259567746972101, 'samples': 7530048, 'steps': 39218, 'loss/train': 1.378353476524353} 08/30/2021 20:15:54 - INFO - __main__ - Step 39220: {'lr': 0.00042595300489857164, 'samples': 7530240, 'steps': 39219, 'loss/train': 1.2656008005142212} 08/30/2021 20:15:54 - INFO - __main__ - Step 39221: {'lr': 0.0004259492350206514, 'samples': 7530432, 'steps': 39220, 'loss/train': 1.7456952333450317} 08/30/2021 20:15:56 - INFO - __main__ - Step 39222: {'lr': 0.00042594546506345124, 'samples': 7530624, 'steps': 39221, 'loss/train': 1.2530466318130493} 08/30/2021 20:15:56 - INFO - __main__ - Step 39223: {'lr': 0.00042594169502697265, 'samples': 7530816, 'steps': 39222, 'loss/train': 1.15249502658844} 08/30/2021 20:15:57 - INFO - __main__ - Step 39224: {'lr': 0.00042593792491121753, 'samples': 7531008, 'steps': 39223, 'loss/train': 0.8006893396377563} 08/30/2021 20:15:57 - INFO - __main__ - Step 39225: {'lr': 0.00042593415471618744, 'samples': 7531200, 'steps': 39224, 'loss/train': 1.5839146375656128} 08/30/2021 20:15:57 - INFO - __main__ - Step 39226: {'lr': 0.0004259303844418841, 'samples': 7531392, 'steps': 39225, 'loss/train': 1.3223596811294556} 08/30/2021 20:15:59 - INFO - __main__ - Step 39227: {'lr': 0.00042592661408830937, 'samples': 7531584, 'steps': 39226, 'loss/train': 1.6665972471237183} 08/30/2021 20:16:00 - INFO - __main__ - Step 39228: {'lr': 0.00042592284365546474, 'samples': 7531776, 'steps': 39227, 'loss/train': 1.773131251335144} 08/30/2021 20:16:00 - INFO - __main__ - Step 39229: {'lr': 0.00042591907314335197, 'samples': 7531968, 'steps': 39228, 'loss/train': 1.867200255393982} 08/30/2021 20:16:00 - INFO - __main__ - Step 39230: {'lr': 0.00042591530255197286, 'samples': 7532160, 'steps': 39229, 'loss/train': 1.3140276670455933} 08/30/2021 20:16:01 - INFO - __main__ - Step 39231: {'lr': 0.00042591153188132903, 'samples': 7532352, 'steps': 39230, 'loss/train': 1.2540984153747559} 08/30/2021 20:16:01 - INFO - __main__ - Step 39232: {'lr': 0.00042590776113142216, 'samples': 7532544, 'steps': 39231, 'loss/train': 1.1593823432922363} 08/30/2021 20:16:02 - INFO - __main__ - Step 39233: {'lr': 0.00042590399030225393, 'samples': 7532736, 'steps': 39232, 'loss/train': 0.9333450198173523} 08/30/2021 20:16:03 - INFO - __main__ - Step 39234: {'lr': 0.0004259002193938261, 'samples': 7532928, 'steps': 39233, 'loss/train': 1.2447391748428345} 08/30/2021 20:16:03 - INFO - __main__ - Step 39235: {'lr': 0.0004258964484061403, 'samples': 7533120, 'steps': 39234, 'loss/train': 1.5167738199234009} 08/30/2021 20:16:04 - INFO - __main__ - Step 39236: {'lr': 0.00042589267733919833, 'samples': 7533312, 'steps': 39235, 'loss/train': 1.5196619033813477} 08/30/2021 20:16:04 - INFO - __main__ - Step 39237: {'lr': 0.0004258889061930018, 'samples': 7533504, 'steps': 39236, 'loss/train': 1.4889049530029297} 08/30/2021 20:16:06 - INFO - __main__ - Step 39238: {'lr': 0.0004258851349675524, 'samples': 7533696, 'steps': 39237, 'loss/train': 1.5146186351776123} 08/30/2021 20:16:07 - INFO - __main__ - Step 39239: {'lr': 0.00042588136366285197, 'samples': 7533888, 'steps': 39238, 'loss/train': 1.1814444065093994} 08/30/2021 20:16:07 - INFO - __main__ - Step 39240: {'lr': 0.0004258775922789021, 'samples': 7534080, 'steps': 39239, 'loss/train': 1.5750893354415894} 08/30/2021 20:16:07 - INFO - __main__ - Step 39241: {'lr': 0.0004258738208157045, 'samples': 7534272, 'steps': 39240, 'loss/train': 1.8444780111312866} 08/30/2021 20:16:08 - INFO - __main__ - Step 39242: {'lr': 0.0004258700492732608, 'samples': 7534464, 'steps': 39241, 'loss/train': 1.6651300191879272} 08/30/2021 20:16:08 - INFO - __main__ - Step 39243: {'lr': 0.0004258662776515728, 'samples': 7534656, 'steps': 39242, 'loss/train': 1.331242322921753} 08/30/2021 20:16:10 - INFO - __main__ - Step 39244: {'lr': 0.00042586250595064216, 'samples': 7534848, 'steps': 39243, 'loss/train': 0.8905333280563354} 08/30/2021 20:16:11 - INFO - __main__ - Step 39245: {'lr': 0.0004258587341704706, 'samples': 7535040, 'steps': 39244, 'loss/train': 2.15775465965271} 08/30/2021 20:16:11 - INFO - __main__ - Step 39246: {'lr': 0.00042585496231105986, 'samples': 7535232, 'steps': 39245, 'loss/train': 1.777660846710205} 08/30/2021 20:16:11 - INFO - __main__ - Step 39247: {'lr': 0.00042585119037241156, 'samples': 7535424, 'steps': 39246, 'loss/train': 2.3965721130371094} 08/30/2021 20:16:12 - INFO - __main__ - Step 39248: {'lr': 0.00042584741835452743, 'samples': 7535616, 'steps': 39247, 'loss/train': 1.7814289331436157} 08/30/2021 20:16:13 - INFO - __main__ - Step 39249: {'lr': 0.0004258436462574091, 'samples': 7535808, 'steps': 39248, 'loss/train': 0.7484597563743591} 08/30/2021 20:16:14 - INFO - __main__ - Step 39250: {'lr': 0.0004258398740810584, 'samples': 7536000, 'steps': 39249, 'loss/train': 1.218285322189331} 08/30/2021 20:16:14 - INFO - __main__ - Step 39251: {'lr': 0.00042583610182547694, 'samples': 7536192, 'steps': 39250, 'loss/train': 1.0163325071334839} 08/30/2021 20:16:14 - INFO - __main__ - Step 39252: {'lr': 0.0004258323294906665, 'samples': 7536384, 'steps': 39251, 'loss/train': 1.140373706817627} 08/30/2021 20:16:15 - INFO - __main__ - Step 39253: {'lr': 0.00042582855707662864, 'samples': 7536576, 'steps': 39252, 'loss/train': 1.8493263721466064} 08/30/2021 20:16:16 - INFO - __main__ - Step 39254: {'lr': 0.00042582478458336523, 'samples': 7536768, 'steps': 39253, 'loss/train': 0.8339062333106995} 08/30/2021 20:16:17 - INFO - __main__ - Step 39255: {'lr': 0.00042582101201087786, 'samples': 7536960, 'steps': 39254, 'loss/train': 1.7238658666610718} 08/30/2021 20:16:17 - INFO - __main__ - Step 39256: {'lr': 0.00042581723935916817, 'samples': 7537152, 'steps': 39255, 'loss/train': 1.4438048601150513} 08/30/2021 20:16:17 - INFO - __main__ - Step 39257: {'lr': 0.00042581346662823804, 'samples': 7537344, 'steps': 39256, 'loss/train': 1.309090495109558} 08/30/2021 20:16:18 - INFO - __main__ - Step 39258: {'lr': 0.00042580969381808906, 'samples': 7537536, 'steps': 39257, 'loss/train': 2.51485013961792} 08/30/2021 20:16:19 - INFO - __main__ - Step 39259: {'lr': 0.00042580592092872295, 'samples': 7537728, 'steps': 39258, 'loss/train': 0.9091335535049438} 08/30/2021 20:16:20 - INFO - __main__ - Step 39260: {'lr': 0.0004258021479601414, 'samples': 7537920, 'steps': 39259, 'loss/train': 2.7244107723236084} 08/30/2021 20:16:20 - INFO - __main__ - Step 39261: {'lr': 0.0004257983749123461, 'samples': 7538112, 'steps': 39260, 'loss/train': 1.6110857725143433} 08/30/2021 20:16:20 - INFO - __main__ - Step 39262: {'lr': 0.00042579460178533875, 'samples': 7538304, 'steps': 39261, 'loss/train': 1.5759211778640747} 08/30/2021 20:16:21 - INFO - __main__ - Step 39263: {'lr': 0.0004257908285791211, 'samples': 7538496, 'steps': 39262, 'loss/train': 1.3688291311264038} 08/30/2021 20:16:21 - INFO - __main__ - Step 39264: {'lr': 0.00042578705529369476, 'samples': 7538688, 'steps': 39263, 'loss/train': 2.0688281059265137} 08/30/2021 20:16:23 - INFO - __main__ - Step 39265: {'lr': 0.00042578328192906153, 'samples': 7538880, 'steps': 39264, 'loss/train': 1.6296072006225586} 08/30/2021 20:16:23 - INFO - __main__ - Step 39266: {'lr': 0.00042577950848522305, 'samples': 7539072, 'steps': 39265, 'loss/train': 1.6873074769973755} 08/30/2021 20:16:23 - INFO - __main__ - Step 39267: {'lr': 0.0004257757349621811, 'samples': 7539264, 'steps': 39266, 'loss/train': 1.5894533395767212} 08/30/2021 20:16:24 - INFO - __main__ - Step 39268: {'lr': 0.0004257719613599372, 'samples': 7539456, 'steps': 39267, 'loss/train': 1.077060341835022} 08/30/2021 20:16:24 - INFO - __main__ - Step 39269: {'lr': 0.0004257681876784932, 'samples': 7539648, 'steps': 39268, 'loss/train': 1.9370777606964111} 08/30/2021 20:16:25 - INFO - __main__ - Step 39270: {'lr': 0.0004257644139178508, 'samples': 7539840, 'steps': 39269, 'loss/train': 1.8108786344528198} 08/30/2021 20:16:26 - INFO - __main__ - Step 39271: {'lr': 0.0004257606400780117, 'samples': 7540032, 'steps': 39270, 'loss/train': 1.5082741975784302} 08/30/2021 20:16:26 - INFO - __main__ - Step 39272: {'lr': 0.0004257568661589775, 'samples': 7540224, 'steps': 39271, 'loss/train': 1.2383904457092285} 08/30/2021 20:16:27 - INFO - __main__ - Step 39273: {'lr': 0.00042575309216074997, 'samples': 7540416, 'steps': 39272, 'loss/train': 1.8964496850967407} 08/30/2021 20:16:27 - INFO - __main__ - Step 39274: {'lr': 0.00042574931808333095, 'samples': 7540608, 'steps': 39273, 'loss/train': 1.383758306503296} 08/30/2021 20:16:28 - INFO - __main__ - Step 39275: {'lr': 0.0004257455439267218, 'samples': 7540800, 'steps': 39274, 'loss/train': 1.560986042022705} 08/30/2021 20:16:29 - INFO - __main__ - Step 39276: {'lr': 0.00042574176969092454, 'samples': 7540992, 'steps': 39275, 'loss/train': 1.3361958265304565} 08/30/2021 20:16:29 - INFO - __main__ - Step 39277: {'lr': 0.0004257379953759407, 'samples': 7541184, 'steps': 39276, 'loss/train': 1.5455554723739624} 08/30/2021 20:16:30 - INFO - __main__ - Step 39278: {'lr': 0.00042573422098177204, 'samples': 7541376, 'steps': 39277, 'loss/train': 1.0981570482254028} 08/30/2021 20:16:30 - INFO - __main__ - Step 39279: {'lr': 0.0004257304465084203, 'samples': 7541568, 'steps': 39278, 'loss/train': 1.1934826374053955} 08/30/2021 20:16:32 - INFO - __main__ - Step 39280: {'lr': 0.0004257266719558871, 'samples': 7541760, 'steps': 39279, 'loss/train': 1.4602062702178955} 08/30/2021 20:16:32 - INFO - __main__ - Step 39281: {'lr': 0.0004257228973241741, 'samples': 7541952, 'steps': 39280, 'loss/train': 1.2158236503601074} 08/30/2021 20:16:32 - INFO - __main__ - Step 39282: {'lr': 0.00042571912261328315, 'samples': 7542144, 'steps': 39281, 'loss/train': 1.546975016593933} 08/30/2021 20:16:33 - INFO - __main__ - Step 39283: {'lr': 0.00042571534782321593, 'samples': 7542336, 'steps': 39282, 'loss/train': 1.710975170135498} 08/30/2021 20:16:33 - INFO - __main__ - Step 39284: {'lr': 0.000425711572953974, 'samples': 7542528, 'steps': 39283, 'loss/train': 0.4806158244609833} 08/30/2021 20:16:35 - INFO - __main__ - Step 39285: {'lr': 0.00042570779800555914, 'samples': 7542720, 'steps': 39284, 'loss/train': 1.3156388998031616} 08/30/2021 20:16:35 - INFO - __main__ - Step 39286: {'lr': 0.00042570402297797304, 'samples': 7542912, 'steps': 39285, 'loss/train': 1.1073112487792969} 08/30/2021 20:16:35 - INFO - __main__ - Step 39287: {'lr': 0.0004257002478712175, 'samples': 7543104, 'steps': 39286, 'loss/train': 0.7631056904792786} 08/30/2021 20:16:36 - INFO - __main__ - Step 39288: {'lr': 0.0004256964726852941, 'samples': 7543296, 'steps': 39287, 'loss/train': 1.4516005516052246} 08/30/2021 20:16:36 - INFO - __main__ - Step 39289: {'lr': 0.0004256926974202046, 'samples': 7543488, 'steps': 39288, 'loss/train': 1.4791836738586426} 08/30/2021 20:16:38 - INFO - __main__ - Step 39290: {'lr': 0.00042568892207595066, 'samples': 7543680, 'steps': 39289, 'loss/train': 1.9839260578155518} 08/30/2021 20:16:38 - INFO - __main__ - Step 39291: {'lr': 0.000425685146652534, 'samples': 7543872, 'steps': 39290, 'loss/train': 0.5053918957710266} 08/30/2021 20:16:39 - INFO - __main__ - Step 39292: {'lr': 0.00042568137114995633, 'samples': 7544064, 'steps': 39291, 'loss/train': 1.3245831727981567} 08/30/2021 20:16:39 - INFO - __main__ - Step 39293: {'lr': 0.00042567759556821937, 'samples': 7544256, 'steps': 39292, 'loss/train': 0.08145341277122498} 08/30/2021 20:16:39 - INFO - __main__ - Step 39294: {'lr': 0.00042567381990732476, 'samples': 7544448, 'steps': 39293, 'loss/train': 0.670648992061615} 08/30/2021 20:16:41 - INFO - __main__ - Step 39295: {'lr': 0.0004256700441672743, 'samples': 7544640, 'steps': 39294, 'loss/train': 1.8403757810592651} 08/30/2021 20:16:42 - INFO - __main__ - Step 39296: {'lr': 0.0004256662683480695, 'samples': 7544832, 'steps': 39295, 'loss/train': 1.3670477867126465} 08/30/2021 20:16:42 - INFO - __main__ - Step 39297: {'lr': 0.00042566249244971235, 'samples': 7545024, 'steps': 39296, 'loss/train': 1.0663715600967407} 08/30/2021 20:16:43 - INFO - __main__ - Step 39298: {'lr': 0.0004256587164722043, 'samples': 7545216, 'steps': 39297, 'loss/train': 1.6513261795043945} 08/30/2021 20:16:43 - INFO - __main__ - Step 39299: {'lr': 0.0004256549404155471, 'samples': 7545408, 'steps': 39298, 'loss/train': 2.644193410873413} 08/30/2021 20:16:44 - INFO - __main__ - Step 39300: {'lr': 0.0004256511642797426, 'samples': 7545600, 'steps': 39299, 'loss/train': 1.4818652868270874} 08/30/2021 20:16:45 - INFO - __main__ - Step 39301: {'lr': 0.0004256473880647923, 'samples': 7545792, 'steps': 39300, 'loss/train': 1.6008274555206299} 08/30/2021 20:16:45 - INFO - __main__ - Step 39302: {'lr': 0.0004256436117706981, 'samples': 7545984, 'steps': 39301, 'loss/train': 1.086125135421753} 08/30/2021 20:16:46 - INFO - __main__ - Step 39303: {'lr': 0.0004256398353974615, 'samples': 7546176, 'steps': 39302, 'loss/train': 1.7928388118743896} 08/30/2021 20:16:46 - INFO - __main__ - Step 39304: {'lr': 0.00042563605894508434, 'samples': 7546368, 'steps': 39303, 'loss/train': 1.5981634855270386} 08/30/2021 20:16:46 - INFO - __main__ - Step 39305: {'lr': 0.00042563228241356834, 'samples': 7546560, 'steps': 39304, 'loss/train': 1.6829520463943481} 08/30/2021 20:16:48 - INFO - __main__ - Step 39306: {'lr': 0.000425628505802915, 'samples': 7546752, 'steps': 39305, 'loss/train': 1.738876461982727} 08/30/2021 20:16:48 - INFO - __main__ - Step 39307: {'lr': 0.0004256247291131263, 'samples': 7546944, 'steps': 39306, 'loss/train': 1.655989408493042} 08/30/2021 20:16:49 - INFO - __main__ - Step 39308: {'lr': 0.00042562095234420375, 'samples': 7547136, 'steps': 39307, 'loss/train': 1.2943518161773682} 08/30/2021 20:16:49 - INFO - __main__ - Step 39309: {'lr': 0.00042561717549614907, 'samples': 7547328, 'steps': 39308, 'loss/train': 0.30530333518981934} 08/30/2021 20:16:49 - INFO - __main__ - Step 39310: {'lr': 0.0004256133985689641, 'samples': 7547520, 'steps': 39309, 'loss/train': 1.379294753074646} 08/30/2021 20:16:51 - INFO - __main__ - Step 39311: {'lr': 0.0004256096215626504, 'samples': 7547712, 'steps': 39310, 'loss/train': 1.431809425354004} 08/30/2021 20:16:51 - INFO - __main__ - Step 39312: {'lr': 0.0004256058444772097, 'samples': 7547904, 'steps': 39311, 'loss/train': 1.136567234992981} 08/30/2021 20:16:52 - INFO - __main__ - Step 39313: {'lr': 0.0004256020673126437, 'samples': 7548096, 'steps': 39312, 'loss/train': 0.739686131477356} 08/30/2021 20:16:52 - INFO - __main__ - Step 39314: {'lr': 0.0004255982900689541, 'samples': 7548288, 'steps': 39313, 'loss/train': 1.1690136194229126} 08/30/2021 20:16:52 - INFO - __main__ - Step 39315: {'lr': 0.0004255945127461427, 'samples': 7548480, 'steps': 39314, 'loss/train': 0.05878067389130592} 08/30/2021 20:16:54 - INFO - __main__ - Step 39316: {'lr': 0.00042559073534421114, 'samples': 7548672, 'steps': 39315, 'loss/train': 1.8100237846374512} 08/30/2021 20:16:54 - INFO - __main__ - Step 39317: {'lr': 0.00042558695786316106, 'samples': 7548864, 'steps': 39316, 'loss/train': 1.430045485496521} 08/30/2021 20:16:55 - INFO - __main__ - Step 39318: {'lr': 0.00042558318030299415, 'samples': 7549056, 'steps': 39317, 'loss/train': 1.5092629194259644} 08/30/2021 20:16:55 - INFO - __main__ - Step 39319: {'lr': 0.0004255794026637122, 'samples': 7549248, 'steps': 39318, 'loss/train': 0.06414658576250076} 08/30/2021 20:16:55 - INFO - __main__ - Step 39320: {'lr': 0.0004255756249453169, 'samples': 7549440, 'steps': 39319, 'loss/train': 1.1893595457077026} 08/30/2021 20:16:57 - INFO - __main__ - Step 39321: {'lr': 0.00042557184714780993, 'samples': 7549632, 'steps': 39320, 'loss/train': 1.2197809219360352} 08/30/2021 20:16:57 - INFO - __main__ - Step 39322: {'lr': 0.000425568069271193, 'samples': 7549824, 'steps': 39321, 'loss/train': 0.46699976921081543} 08/30/2021 20:16:58 - INFO - __main__ - Step 39323: {'lr': 0.00042556429131546775, 'samples': 7550016, 'steps': 39322, 'loss/train': 2.1314680576324463} 08/30/2021 20:16:58 - INFO - __main__ - Step 39324: {'lr': 0.000425560513280636, 'samples': 7550208, 'steps': 39323, 'loss/train': 1.6722991466522217} 08/30/2021 20:16:58 - INFO - __main__ - Step 39325: {'lr': 0.00042555673516669933, 'samples': 7550400, 'steps': 39324, 'loss/train': 1.047684907913208} 08/30/2021 20:17:00 - INFO - __main__ - Step 39326: {'lr': 0.0004255529569736596, 'samples': 7550592, 'steps': 39325, 'loss/train': 2.393691301345825} 08/30/2021 20:17:00 - INFO - __main__ - Step 39327: {'lr': 0.0004255491787015183, 'samples': 7550784, 'steps': 39326, 'loss/train': 1.661149024963379} 08/30/2021 20:17:01 - INFO - __main__ - Step 39328: {'lr': 0.0004255454003502774, 'samples': 7550976, 'steps': 39327, 'loss/train': 1.659741759300232} 08/30/2021 20:17:01 - INFO - __main__ - Step 39329: {'lr': 0.0004255416219199384, 'samples': 7551168, 'steps': 39328, 'loss/train': 1.645760416984558} 08/30/2021 20:17:01 - INFO - __main__ - Step 39330: {'lr': 0.0004255378434105029, 'samples': 7551360, 'steps': 39329, 'loss/train': 1.4031420946121216} 08/30/2021 20:17:03 - INFO - __main__ - Step 39331: {'lr': 0.00042553406482197297, 'samples': 7551552, 'steps': 39330, 'loss/train': 1.3567979335784912} 08/30/2021 20:17:03 - INFO - __main__ - Step 39332: {'lr': 0.00042553028615434997, 'samples': 7551744, 'steps': 39331, 'loss/train': 1.6148399114608765} 08/30/2021 20:17:04 - INFO - __main__ - Step 39333: {'lr': 0.0004255265074076358, 'samples': 7551936, 'steps': 39332, 'loss/train': 0.9594143629074097} 08/30/2021 20:17:04 - INFO - __main__ - Step 39334: {'lr': 0.00042552272858183203, 'samples': 7552128, 'steps': 39333, 'loss/train': 0.033706679940223694} 08/30/2021 20:17:04 - INFO - __main__ - Step 39335: {'lr': 0.0004255189496769405, 'samples': 7552320, 'steps': 39334, 'loss/train': 1.1487500667572021} 08/30/2021 20:17:06 - INFO - __main__ - Step 39336: {'lr': 0.00042551517069296276, 'samples': 7552512, 'steps': 39335, 'loss/train': 1.7795332670211792} 08/30/2021 20:17:07 - INFO - __main__ - Step 39337: {'lr': 0.00042551139162990065, 'samples': 7552704, 'steps': 39336, 'loss/train': 1.3000907897949219} 08/30/2021 20:17:07 - INFO - __main__ - Step 39338: {'lr': 0.0004255076124877558, 'samples': 7552896, 'steps': 39337, 'loss/train': 0.12005091458559036} 08/30/2021 20:17:07 - INFO - __main__ - Step 39339: {'lr': 0.0004255038332665299, 'samples': 7553088, 'steps': 39338, 'loss/train': 1.580047607421875} 08/30/2021 20:17:08 - INFO - __main__ - Step 39340: {'lr': 0.0004255000539662247, 'samples': 7553280, 'steps': 39339, 'loss/train': 1.6727694272994995} 08/30/2021 20:17:08 - INFO - __main__ - Step 39341: {'lr': 0.0004254962745868419, 'samples': 7553472, 'steps': 39340, 'loss/train': 1.2373043298721313} 08/30/2021 20:17:09 - INFO - __main__ - Step 39342: {'lr': 0.00042549249512838325, 'samples': 7553664, 'steps': 39341, 'loss/train': 1.2816848754882812} 08/30/2021 20:17:10 - INFO - __main__ - Step 39343: {'lr': 0.00042548871559085026, 'samples': 7553856, 'steps': 39342, 'loss/train': 0.9505172371864319} 08/30/2021 20:17:10 - INFO - __main__ - Step 39344: {'lr': 0.0004254849359742449, 'samples': 7554048, 'steps': 39343, 'loss/train': 0.4994402527809143} 08/30/2021 20:17:11 - INFO - __main__ - Step 39345: {'lr': 0.0004254811562785686, 'samples': 7554240, 'steps': 39344, 'loss/train': 1.2361412048339844} 08/30/2021 20:17:11 - INFO - __main__ - Step 39346: {'lr': 0.00042547737650382324, 'samples': 7554432, 'steps': 39345, 'loss/train': 1.553163766860962} 08/30/2021 20:17:13 - INFO - __main__ - Step 39347: {'lr': 0.0004254735966500105, 'samples': 7554624, 'steps': 39346, 'loss/train': 0.9998989701271057} 08/30/2021 20:17:14 - INFO - __main__ - Step 39348: {'lr': 0.00042546981671713206, 'samples': 7554816, 'steps': 39347, 'loss/train': 1.6435304880142212} 08/30/2021 20:17:14 - INFO - __main__ - Step 39349: {'lr': 0.0004254660367051896, 'samples': 7555008, 'steps': 39348, 'loss/train': 1.8735414743423462} 08/30/2021 20:17:14 - INFO - __main__ - Step 39350: {'lr': 0.0004254622566141849, 'samples': 7555200, 'steps': 39349, 'loss/train': 1.5143274068832397} 08/30/2021 20:17:15 - INFO - __main__ - Step 39351: {'lr': 0.0004254584764441196, 'samples': 7555392, 'steps': 39350, 'loss/train': 1.3694311380386353} 08/30/2021 20:17:16 - INFO - __main__ - Step 39352: {'lr': 0.00042545469619499545, 'samples': 7555584, 'steps': 39351, 'loss/train': 0.5295366048812866} 08/30/2021 20:17:16 - INFO - __main__ - Step 39353: {'lr': 0.00042545091586681404, 'samples': 7555776, 'steps': 39352, 'loss/train': 1.4884425401687622} 08/30/2021 20:17:17 - INFO - __main__ - Step 39354: {'lr': 0.0004254471354595772, 'samples': 7555968, 'steps': 39353, 'loss/train': 1.6351653337478638} 08/30/2021 20:17:17 - INFO - __main__ - Step 39355: {'lr': 0.0004254433549732866, 'samples': 7556160, 'steps': 39354, 'loss/train': 1.3009556531906128} 08/30/2021 20:17:18 - INFO - __main__ - Step 39356: {'lr': 0.0004254395744079439, 'samples': 7556352, 'steps': 39355, 'loss/train': 0.8656249642372131} 08/30/2021 20:17:19 - INFO - __main__ - Step 39357: {'lr': 0.0004254357937635509, 'samples': 7556544, 'steps': 39356, 'loss/train': 1.461314082145691} 08/30/2021 20:17:20 - INFO - __main__ - Step 39358: {'lr': 0.00042543201304010914, 'samples': 7556736, 'steps': 39357, 'loss/train': 1.8331661224365234} 08/30/2021 20:17:20 - INFO - __main__ - Step 39359: {'lr': 0.0004254282322376205, 'samples': 7556928, 'steps': 39358, 'loss/train': 1.5330111980438232} 08/30/2021 20:17:20 - INFO - __main__ - Step 39360: {'lr': 0.0004254244513560866, 'samples': 7557120, 'steps': 39359, 'loss/train': 1.3315730094909668} 08/30/2021 20:17:21 - INFO - __main__ - Step 39361: {'lr': 0.00042542067039550916, 'samples': 7557312, 'steps': 39360, 'loss/train': 1.5101749897003174} 08/30/2021 20:17:22 - INFO - __main__ - Step 39362: {'lr': 0.00042541688935588984, 'samples': 7557504, 'steps': 39361, 'loss/train': 1.3210201263427734} 08/30/2021 20:17:23 - INFO - __main__ - Step 39363: {'lr': 0.00042541310823723035, 'samples': 7557696, 'steps': 39362, 'loss/train': 1.3677185773849487} 08/30/2021 20:17:23 - INFO - __main__ - Step 39364: {'lr': 0.00042540932703953246, 'samples': 7557888, 'steps': 39363, 'loss/train': 1.2405917644500732} 08/30/2021 20:17:23 - INFO - __main__ - Step 39365: {'lr': 0.00042540554576279776, 'samples': 7558080, 'steps': 39364, 'loss/train': 0.6681594848632812} 08/30/2021 20:17:24 - INFO - __main__ - Step 39366: {'lr': 0.0004254017644070282, 'samples': 7558272, 'steps': 39365, 'loss/train': 0.9929782152175903} 08/30/2021 20:17:24 - INFO - __main__ - Step 39367: {'lr': 0.0004253979829722251, 'samples': 7558464, 'steps': 39366, 'loss/train': 0.08690003305673599} 08/30/2021 20:17:26 - INFO - __main__ - Step 39368: {'lr': 0.00042539420145839055, 'samples': 7558656, 'steps': 39367, 'loss/train': 1.2248239517211914} 08/30/2021 20:17:26 - INFO - __main__ - Step 39369: {'lr': 0.00042539041986552596, 'samples': 7558848, 'steps': 39368, 'loss/train': 1.0808542966842651} 08/30/2021 20:17:26 - INFO - __main__ - Step 39370: {'lr': 0.00042538663819363323, 'samples': 7559040, 'steps': 39369, 'loss/train': 3.869018793106079} 08/30/2021 20:17:27 - INFO - __main__ - Step 39371: {'lr': 0.000425382856442714, 'samples': 7559232, 'steps': 39370, 'loss/train': 0.8527717590332031} 08/30/2021 20:17:27 - INFO - __main__ - Step 39372: {'lr': 0.0004253790746127699, 'samples': 7559424, 'steps': 39371, 'loss/train': 1.0129683017730713} 08/30/2021 20:17:29 - INFO - __main__ - Step 39373: {'lr': 0.0004253752927038027, 'samples': 7559616, 'steps': 39372, 'loss/train': 0.922639012336731} 08/30/2021 20:17:29 - INFO - __main__ - Step 39374: {'lr': 0.0004253715107158141, 'samples': 7559808, 'steps': 39373, 'loss/train': 1.7660993337631226} 08/30/2021 20:17:29 - INFO - __main__ - Step 39375: {'lr': 0.0004253677286488058, 'samples': 7560000, 'steps': 39374, 'loss/train': 1.4221876859664917} 08/30/2021 20:17:30 - INFO - __main__ - Step 39376: {'lr': 0.00042536394650277953, 'samples': 7560192, 'steps': 39375, 'loss/train': 1.4791922569274902} 08/30/2021 20:17:30 - INFO - __main__ - Step 39377: {'lr': 0.000425360164277737, 'samples': 7560384, 'steps': 39376, 'loss/train': 1.7833961248397827} 08/30/2021 20:17:32 - INFO - __main__ - Step 39378: {'lr': 0.00042535638197367984, 'samples': 7560576, 'steps': 39377, 'loss/train': 1.848827600479126} 08/30/2021 20:17:32 - INFO - __main__ - Step 39379: {'lr': 0.0004253525995906098, 'samples': 7560768, 'steps': 39378, 'loss/train': 1.3308979272842407} 08/30/2021 20:17:32 - INFO - __main__ - Step 39380: {'lr': 0.00042534881712852856, 'samples': 7560960, 'steps': 39379, 'loss/train': 0.5071209073066711} 08/30/2021 20:17:33 - INFO - __main__ - Step 39381: {'lr': 0.0004253450345874379, 'samples': 7561152, 'steps': 39380, 'loss/train': 0.22713203728199005} 08/30/2021 20:17:33 - INFO - __main__ - Step 39382: {'lr': 0.00042534125196733955, 'samples': 7561344, 'steps': 39381, 'loss/train': 1.9108912944793701} 08/30/2021 20:17:35 - INFO - __main__ - Step 39383: {'lr': 0.000425337469268235, 'samples': 7561536, 'steps': 39382, 'loss/train': 1.2672617435455322} 08/30/2021 20:17:35 - INFO - __main__ - Step 39384: {'lr': 0.00042533368649012615, 'samples': 7561728, 'steps': 39383, 'loss/train': 1.6363317966461182} 08/30/2021 20:17:35 - INFO - __main__ - Step 39385: {'lr': 0.0004253299036330146, 'samples': 7561920, 'steps': 39384, 'loss/train': 0.5283082127571106} 08/30/2021 20:17:36 - INFO - __main__ - Step 39386: {'lr': 0.00042532612069690214, 'samples': 7562112, 'steps': 39385, 'loss/train': 1.4869177341461182} 08/30/2021 20:17:36 - INFO - __main__ - Step 39387: {'lr': 0.0004253223376817904, 'samples': 7562304, 'steps': 39386, 'loss/train': 1.831048607826233} 08/30/2021 20:17:38 - INFO - __main__ - Step 39388: {'lr': 0.0004253185545876812, 'samples': 7562496, 'steps': 39387, 'loss/train': 1.0880411863327026} 08/30/2021 20:17:38 - INFO - __main__ - Step 39389: {'lr': 0.0004253147714145761, 'samples': 7562688, 'steps': 39388, 'loss/train': 1.1887985467910767} 08/30/2021 20:17:39 - INFO - __main__ - Step 39390: {'lr': 0.00042531098816247695, 'samples': 7562880, 'steps': 39389, 'loss/train': 1.5237889289855957} 08/30/2021 20:17:39 - INFO - __main__ - Step 39391: {'lr': 0.00042530720483138524, 'samples': 7563072, 'steps': 39390, 'loss/train': 1.3814122676849365} 08/30/2021 20:17:39 - INFO - __main__ - Step 39392: {'lr': 0.00042530342142130283, 'samples': 7563264, 'steps': 39391, 'loss/train': 1.1057311296463013} 08/30/2021 20:17:40 - INFO - __main__ - Step 39393: {'lr': 0.0004252996379322315, 'samples': 7563456, 'steps': 39392, 'loss/train': 1.0700563192367554} 08/30/2021 20:17:41 - INFO - __main__ - Step 39394: {'lr': 0.0004252958543641728, 'samples': 7563648, 'steps': 39393, 'loss/train': 1.4636409282684326} 08/30/2021 20:17:42 - INFO - __main__ - Step 39395: {'lr': 0.0004252920707171285, 'samples': 7563840, 'steps': 39394, 'loss/train': 1.658215880393982} 08/30/2021 20:17:42 - INFO - __main__ - Step 39396: {'lr': 0.00042528828699110033, 'samples': 7564032, 'steps': 39395, 'loss/train': 1.7424261569976807} 08/30/2021 20:17:42 - INFO - __main__ - Step 39397: {'lr': 0.0004252845031860899, 'samples': 7564224, 'steps': 39396, 'loss/train': 1.0661591291427612} 08/30/2021 20:17:43 - INFO - __main__ - Step 39398: {'lr': 0.000425280719302099, 'samples': 7564416, 'steps': 39397, 'loss/train': 1.4587175846099854} 08/30/2021 20:17:44 - INFO - __main__ - Step 39399: {'lr': 0.0004252769353391294, 'samples': 7564608, 'steps': 39398, 'loss/train': 0.7495118975639343} 08/30/2021 20:17:45 - INFO - __main__ - Step 39400: {'lr': 0.00042527315129718257, 'samples': 7564800, 'steps': 39399, 'loss/train': 0.42761915922164917} 08/30/2021 20:17:45 - INFO - __main__ - Step 39401: {'lr': 0.00042526936717626046, 'samples': 7564992, 'steps': 39400, 'loss/train': 1.2316175699234009} 08/30/2021 20:17:45 - INFO - __main__ - Step 39402: {'lr': 0.00042526558297636464, 'samples': 7565184, 'steps': 39401, 'loss/train': 1.448720097541809} 08/30/2021 20:17:46 - INFO - __main__ - Step 39403: {'lr': 0.0004252617986974969, 'samples': 7565376, 'steps': 39402, 'loss/train': 1.3910382986068726} 08/30/2021 20:17:48 - INFO - __main__ - Step 39404: {'lr': 0.00042525801433965883, 'samples': 7565568, 'steps': 39403, 'loss/train': 1.7211908102035522} 08/30/2021 20:17:48 - INFO - __main__ - Step 39405: {'lr': 0.00042525422990285225, 'samples': 7565760, 'steps': 39404, 'loss/train': 1.9738531112670898} 08/30/2021 20:17:48 - INFO - __main__ - Step 39406: {'lr': 0.0004252504453870788, 'samples': 7565952, 'steps': 39405, 'loss/train': 1.6185775995254517} 08/30/2021 20:17:49 - INFO - __main__ - Step 39407: {'lr': 0.0004252466607923402, 'samples': 7566144, 'steps': 39406, 'loss/train': 1.0970726013183594} 08/30/2021 20:17:49 - INFO - __main__ - Step 39408: {'lr': 0.0004252428761186382, 'samples': 7566336, 'steps': 39407, 'loss/train': 1.7352116107940674} 08/30/2021 20:17:50 - INFO - __main__ - Step 39409: {'lr': 0.0004252390913659744, 'samples': 7566528, 'steps': 39408, 'loss/train': 1.5175449848175049} 08/30/2021 20:17:51 - INFO - __main__ - Step 39410: {'lr': 0.0004252353065343506, 'samples': 7566720, 'steps': 39409, 'loss/train': 1.4668569564819336} 08/30/2021 20:17:51 - INFO - __main__ - Step 39411: {'lr': 0.0004252315216237684, 'samples': 7566912, 'steps': 39410, 'loss/train': 1.9068946838378906} 08/30/2021 20:17:52 - INFO - __main__ - Step 39412: {'lr': 0.00042522773663422977, 'samples': 7567104, 'steps': 39411, 'loss/train': 1.8970649242401123} 08/30/2021 20:17:52 - INFO - __main__ - Step 39413: {'lr': 0.000425223951565736, 'samples': 7567296, 'steps': 39412, 'loss/train': 0.7986385822296143} 08/30/2021 20:17:53 - INFO - __main__ - Step 39414: {'lr': 0.0004252201664182892, 'samples': 7567488, 'steps': 39413, 'loss/train': 1.1627320051193237} 08/30/2021 20:17:54 - INFO - __main__ - Step 39415: {'lr': 0.0004252163811918909, 'samples': 7567680, 'steps': 39414, 'loss/train': 1.0643250942230225} 08/30/2021 20:17:54 - INFO - __main__ - Step 39416: {'lr': 0.00042521259588654264, 'samples': 7567872, 'steps': 39415, 'loss/train': 0.5217099785804749} 08/30/2021 20:17:55 - INFO - __main__ - Step 39417: {'lr': 0.00042520881050224637, 'samples': 7568064, 'steps': 39416, 'loss/train': 1.5016180276870728} 08/30/2021 20:17:55 - INFO - __main__ - Step 39418: {'lr': 0.0004252050250390037, 'samples': 7568256, 'steps': 39417, 'loss/train': 1.5426591634750366} 08/30/2021 20:17:55 - INFO - __main__ - Step 39419: {'lr': 0.0004252012394968164, 'samples': 7568448, 'steps': 39418, 'loss/train': 0.9755098223686218} 08/30/2021 20:17:57 - INFO - __main__ - Step 39420: {'lr': 0.0004251974538756861, 'samples': 7568640, 'steps': 39419, 'loss/train': 1.761231780052185} 08/30/2021 20:17:57 - INFO - __main__ - Step 39421: {'lr': 0.00042519366817561453, 'samples': 7568832, 'steps': 39420, 'loss/train': 1.431688666343689} 08/30/2021 20:17:58 - INFO - __main__ - Step 39422: {'lr': 0.0004251898823966034, 'samples': 7569024, 'steps': 39421, 'loss/train': 1.2372949123382568} 08/30/2021 20:17:58 - INFO - __main__ - Step 39423: {'lr': 0.00042518609653865444, 'samples': 7569216, 'steps': 39422, 'loss/train': 2.4636294841766357} 08/30/2021 20:18:00 - INFO - __main__ - Step 39424: {'lr': 0.00042518231060176926, 'samples': 7569408, 'steps': 39423, 'loss/train': 1.4081465005874634} 08/30/2021 20:18:00 - INFO - __main__ - Step 39425: {'lr': 0.00042517852458594967, 'samples': 7569600, 'steps': 39424, 'loss/train': 1.8521902561187744} 08/30/2021 20:18:01 - INFO - __main__ - Step 39426: {'lr': 0.00042517473849119734, 'samples': 7569792, 'steps': 39425, 'loss/train': 1.607431411743164} 08/30/2021 20:18:01 - INFO - __main__ - Step 39427: {'lr': 0.000425170952317514, 'samples': 7569984, 'steps': 39426, 'loss/train': 1.3722666501998901} 08/30/2021 20:18:02 - INFO - __main__ - Step 39428: {'lr': 0.0004251671660649013, 'samples': 7570176, 'steps': 39427, 'loss/train': 0.19016487896442413} 08/30/2021 20:18:02 - INFO - __main__ - Step 39429: {'lr': 0.000425163379733361, 'samples': 7570368, 'steps': 39428, 'loss/train': 1.5978096723556519} 08/30/2021 20:18:03 - INFO - __main__ - Step 39430: {'lr': 0.00042515959332289476, 'samples': 7570560, 'steps': 39429, 'loss/train': 0.8655191659927368} 08/30/2021 20:18:04 - INFO - __main__ - Step 39431: {'lr': 0.0004251558068335043, 'samples': 7570752, 'steps': 39430, 'loss/train': 1.6447068452835083} 08/30/2021 20:18:04 - INFO - __main__ - Step 39432: {'lr': 0.00042515202026519136, 'samples': 7570944, 'steps': 39431, 'loss/train': 1.4137521982192993} 08/30/2021 20:18:04 - INFO - __main__ - Step 39433: {'lr': 0.00042514823361795764, 'samples': 7571136, 'steps': 39432, 'loss/train': 1.389886736869812} 08/30/2021 20:18:05 - INFO - __main__ - Step 39434: {'lr': 0.0004251444468918048, 'samples': 7571328, 'steps': 39433, 'loss/train': 1.359593152999878} 08/30/2021 20:18:06 - INFO - __main__ - Step 39435: {'lr': 0.0004251406600867346, 'samples': 7571520, 'steps': 39434, 'loss/train': 1.7458051443099976} 08/30/2021 20:18:07 - INFO - __main__ - Step 39436: {'lr': 0.00042513687320274866, 'samples': 7571712, 'steps': 39435, 'loss/train': 0.9783296585083008} 08/30/2021 20:18:07 - INFO - __main__ - Step 39437: {'lr': 0.0004251330862398488, 'samples': 7571904, 'steps': 39436, 'loss/train': 1.424580454826355} 08/30/2021 20:18:07 - INFO - __main__ - Step 39438: {'lr': 0.0004251292991980367, 'samples': 7572096, 'steps': 39437, 'loss/train': 1.449739933013916} 08/30/2021 20:18:08 - INFO - __main__ - Step 39439: {'lr': 0.000425125512077314, 'samples': 7572288, 'steps': 39438, 'loss/train': 1.382744550704956} 08/30/2021 20:18:10 - INFO - __main__ - Step 39440: {'lr': 0.00042512172487768244, 'samples': 7572480, 'steps': 39439, 'loss/train': 1.4800609350204468} 08/30/2021 20:18:10 - INFO - __main__ - Step 39441: {'lr': 0.00042511793759914375, 'samples': 7572672, 'steps': 39440, 'loss/train': 1.0243180990219116} 08/30/2021 20:18:10 - INFO - __main__ - Step 39442: {'lr': 0.0004251141502416996, 'samples': 7572864, 'steps': 39441, 'loss/train': 1.5579551458358765} 08/30/2021 20:18:11 - INFO - __main__ - Step 39443: {'lr': 0.0004251103628053517, 'samples': 7573056, 'steps': 39442, 'loss/train': 1.1759260892868042} 08/30/2021 20:18:11 - INFO - __main__ - Step 39444: {'lr': 0.0004251065752901018, 'samples': 7573248, 'steps': 39443, 'loss/train': 0.05363607034087181} 08/30/2021 20:18:11 - INFO - __main__ - Step 39445: {'lr': 0.0004251027876959516, 'samples': 7573440, 'steps': 39444, 'loss/train': 1.4465770721435547} 08/30/2021 20:18:13 - INFO - __main__ - Step 39446: {'lr': 0.0004250990000229028, 'samples': 7573632, 'steps': 39445, 'loss/train': 1.134953260421753} 08/30/2021 20:18:14 - INFO - __main__ - Step 39447: {'lr': 0.00042509521227095706, 'samples': 7573824, 'steps': 39446, 'loss/train': 1.4134520292282104} 08/30/2021 20:18:14 - INFO - __main__ - Step 39448: {'lr': 0.0004250914244401161, 'samples': 7574016, 'steps': 39447, 'loss/train': 1.6693947315216064} 08/30/2021 20:18:14 - INFO - __main__ - Step 39449: {'lr': 0.00042508763653038167, 'samples': 7574208, 'steps': 39448, 'loss/train': 1.1682648658752441} 08/30/2021 20:18:15 - INFO - __main__ - Step 39450: {'lr': 0.0004250838485417554, 'samples': 7574400, 'steps': 39449, 'loss/train': 1.0540648698806763} 08/30/2021 20:18:17 - INFO - __main__ - Step 39451: {'lr': 0.00042508006047423916, 'samples': 7574592, 'steps': 39450, 'loss/train': 1.8485313653945923} 08/30/2021 20:18:17 - INFO - __main__ - Step 39452: {'lr': 0.0004250762723278344, 'samples': 7574784, 'steps': 39451, 'loss/train': 0.808741569519043} 08/30/2021 20:18:18 - INFO - __main__ - Step 39453: {'lr': 0.00042507248410254307, 'samples': 7574976, 'steps': 39452, 'loss/train': 1.4375113248825073} 08/30/2021 20:18:18 - INFO - __main__ - Step 39454: {'lr': 0.0004250686957983668, 'samples': 7575168, 'steps': 39453, 'loss/train': 1.6407214403152466} 08/30/2021 20:18:18 - INFO - __main__ - Step 39455: {'lr': 0.00042506490741530724, 'samples': 7575360, 'steps': 39454, 'loss/train': 1.4404360055923462} 08/30/2021 20:18:20 - INFO - __main__ - Step 39456: {'lr': 0.00042506111895336616, 'samples': 7575552, 'steps': 39455, 'loss/train': 1.480907917022705} 08/30/2021 20:18:21 - INFO - __main__ - Step 39457: {'lr': 0.00042505733041254526, 'samples': 7575744, 'steps': 39456, 'loss/train': 0.9219895601272583} 08/30/2021 20:18:21 - INFO - __main__ - Step 39458: {'lr': 0.00042505354179284615, 'samples': 7575936, 'steps': 39457, 'loss/train': 1.2193272113800049} 08/30/2021 20:18:21 - INFO - __main__ - Step 39459: {'lr': 0.00042504975309427064, 'samples': 7576128, 'steps': 39458, 'loss/train': 0.9388018250465393} 08/30/2021 20:18:22 - INFO - __main__ - Step 39460: {'lr': 0.0004250459643168204, 'samples': 7576320, 'steps': 39459, 'loss/train': 1.744175672531128} 08/30/2021 20:18:22 - INFO - __main__ - Step 39461: {'lr': 0.0004250421754604972, 'samples': 7576512, 'steps': 39460, 'loss/train': 1.3544243574142456} 08/30/2021 20:18:24 - INFO - __main__ - Step 39462: {'lr': 0.0004250383865253027, 'samples': 7576704, 'steps': 39461, 'loss/train': 0.6414830088615417} 08/30/2021 20:18:24 - INFO - __main__ - Step 39463: {'lr': 0.00042503459751123854, 'samples': 7576896, 'steps': 39462, 'loss/train': 1.3449714183807373} 08/30/2021 20:18:24 - INFO - __main__ - Step 39464: {'lr': 0.00042503080841830654, 'samples': 7577088, 'steps': 39463, 'loss/train': 1.4991395473480225} 08/30/2021 20:18:25 - INFO - __main__ - Step 39465: {'lr': 0.0004250270192465083, 'samples': 7577280, 'steps': 39464, 'loss/train': 0.6795907616615295} 08/30/2021 20:18:25 - INFO - __main__ - Step 39466: {'lr': 0.0004250232299958456, 'samples': 7577472, 'steps': 39465, 'loss/train': 1.0619497299194336} 08/30/2021 20:18:28 - INFO - __main__ - Step 39467: {'lr': 0.0004250194406663203, 'samples': 7577664, 'steps': 39466, 'loss/train': 0.04803982749581337} 08/30/2021 20:18:28 - INFO - __main__ - Step 39468: {'lr': 0.00042501565125793375, 'samples': 7577856, 'steps': 39467, 'loss/train': 0.48896893858909607} 08/30/2021 20:18:28 - INFO - __main__ - Step 39469: {'lr': 0.0004250118617706879, 'samples': 7578048, 'steps': 39468, 'loss/train': 0.471354603767395} 08/30/2021 20:18:29 - INFO - __main__ - Step 39470: {'lr': 0.0004250080722045844, 'samples': 7578240, 'steps': 39469, 'loss/train': 0.4417729675769806} 08/30/2021 20:18:29 - INFO - __main__ - Step 39471: {'lr': 0.000425004282559625, 'samples': 7578432, 'steps': 39470, 'loss/train': 1.9594004154205322} 08/30/2021 20:18:29 - INFO - __main__ - Step 39472: {'lr': 0.0004250004928358113, 'samples': 7578624, 'steps': 39471, 'loss/train': 1.3119771480560303} 08/30/2021 20:18:31 - INFO - __main__ - Step 39473: {'lr': 0.0004249967030331451, 'samples': 7578816, 'steps': 39472, 'loss/train': 1.843422532081604} 08/30/2021 20:18:31 - INFO - __main__ - Step 39474: {'lr': 0.0004249929131516281, 'samples': 7579008, 'steps': 39473, 'loss/train': 1.687857985496521} 08/30/2021 20:18:32 - INFO - __main__ - Step 39475: {'lr': 0.00042498912319126206, 'samples': 7579200, 'steps': 39474, 'loss/train': 1.562577486038208} 08/30/2021 20:18:32 - INFO - __main__ - Step 39476: {'lr': 0.00042498533315204855, 'samples': 7579392, 'steps': 39475, 'loss/train': 0.8977767825126648} 08/30/2021 20:18:32 - INFO - __main__ - Step 39477: {'lr': 0.0004249815430339894, 'samples': 7579584, 'steps': 39476, 'loss/train': 1.6779088973999023} 08/30/2021 20:18:34 - INFO - __main__ - Step 39478: {'lr': 0.0004249777528370862, 'samples': 7579776, 'steps': 39477, 'loss/train': 1.6529103517532349} 08/30/2021 20:18:34 - INFO - __main__ - Step 39479: {'lr': 0.00042497396256134073, 'samples': 7579968, 'steps': 39478, 'loss/train': 1.3054628372192383} 08/30/2021 20:18:35 - INFO - __main__ - Step 39480: {'lr': 0.0004249701722067547, 'samples': 7580160, 'steps': 39479, 'loss/train': 0.9560337662696838} 08/30/2021 20:18:35 - INFO - __main__ - Step 39481: {'lr': 0.0004249663817733298, 'samples': 7580352, 'steps': 39480, 'loss/train': 1.0896540880203247} 08/30/2021 20:18:36 - INFO - __main__ - Step 39482: {'lr': 0.00042496259126106786, 'samples': 7580544, 'steps': 39481, 'loss/train': 1.1687583923339844} 08/30/2021 20:18:36 - INFO - __main__ - Step 39483: {'lr': 0.0004249588006699704, 'samples': 7580736, 'steps': 39482, 'loss/train': 0.2920774817466736} 08/30/2021 20:18:37 - INFO - __main__ - Step 39484: {'lr': 0.0004249550100000392, 'samples': 7580928, 'steps': 39483, 'loss/train': 1.023453712463379} 08/30/2021 20:18:38 - INFO - __main__ - Step 39485: {'lr': 0.0004249512192512759, 'samples': 7581120, 'steps': 39484, 'loss/train': 1.498961329460144} 08/30/2021 20:18:38 - INFO - __main__ - Step 39486: {'lr': 0.0004249474284236824, 'samples': 7581312, 'steps': 39485, 'loss/train': 1.3543148040771484} 08/30/2021 20:18:39 - INFO - __main__ - Step 39487: {'lr': 0.0004249436375172602, 'samples': 7581504, 'steps': 39486, 'loss/train': 5.647855281829834} 08/30/2021 20:18:39 - INFO - __main__ - Step 39488: {'lr': 0.0004249398465320111, 'samples': 7581696, 'steps': 39487, 'loss/train': 1.8692651987075806} 08/30/2021 20:18:41 - INFO - __main__ - Step 39489: {'lr': 0.0004249360554679369, 'samples': 7581888, 'steps': 39488, 'loss/train': 1.686635136604309} 08/30/2021 20:18:41 - INFO - __main__ - Step 39490: {'lr': 0.00042493226432503917, 'samples': 7582080, 'steps': 39489, 'loss/train': 1.572129726409912} 08/30/2021 20:18:42 - INFO - __main__ - Step 39491: {'lr': 0.00042492847310331963, 'samples': 7582272, 'steps': 39490, 'loss/train': 1.2694830894470215} 08/30/2021 20:18:42 - INFO - __main__ - Step 39492: {'lr': 0.00042492468180278, 'samples': 7582464, 'steps': 39491, 'loss/train': 1.402726650238037} 08/30/2021 20:18:42 - INFO - __main__ - Step 39493: {'lr': 0.000424920890423422, 'samples': 7582656, 'steps': 39492, 'loss/train': 1.7928509712219238} 08/30/2021 20:18:43 - INFO - __main__ - Step 39494: {'lr': 0.0004249170989652474, 'samples': 7582848, 'steps': 39493, 'loss/train': 1.0122957229614258} 08/30/2021 20:18:44 - INFO - __main__ - Step 39495: {'lr': 0.00042491330742825783, 'samples': 7583040, 'steps': 39494, 'loss/train': 0.059469517320394516} 08/30/2021 20:18:45 - INFO - __main__ - Step 39496: {'lr': 0.0004249095158124551, 'samples': 7583232, 'steps': 39495, 'loss/train': 1.5529097318649292} 08/30/2021 20:18:45 - INFO - __main__ - Step 39497: {'lr': 0.0004249057241178407, 'samples': 7583424, 'steps': 39496, 'loss/train': 1.6514521837234497} 08/30/2021 20:18:45 - INFO - __main__ - Step 39498: {'lr': 0.00042490193234441656, 'samples': 7583616, 'steps': 39497, 'loss/train': 1.4907827377319336} 08/30/2021 20:18:46 - INFO - __main__ - Step 39499: {'lr': 0.00042489814049218434, 'samples': 7583808, 'steps': 39498, 'loss/train': 1.4580267667770386} 08/30/2021 20:18:46 - INFO - __main__ - Step 39500: {'lr': 0.00042489434856114565, 'samples': 7584000, 'steps': 39499, 'loss/train': 1.9874862432479858} 08/30/2021 20:18:47 - INFO - __main__ - Step 39501: {'lr': 0.00042489055655130226, 'samples': 7584192, 'steps': 39500, 'loss/train': 1.38264000415802} 08/30/2021 20:18:48 - INFO - __main__ - Step 39502: {'lr': 0.00042488676446265596, 'samples': 7584384, 'steps': 39501, 'loss/train': 1.1394124031066895} 08/30/2021 20:18:48 - INFO - __main__ - Step 39503: {'lr': 0.00042488297229520834, 'samples': 7584576, 'steps': 39502, 'loss/train': 1.03812575340271} 08/30/2021 20:18:49 - INFO - __main__ - Step 39504: {'lr': 0.00042487918004896117, 'samples': 7584768, 'steps': 39503, 'loss/train': 0.8285332322120667} 08/30/2021 20:18:49 - INFO - __main__ - Step 39505: {'lr': 0.0004248753877239161, 'samples': 7584960, 'steps': 39504, 'loss/train': 1.6451088190078735} 08/30/2021 20:18:50 - INFO - __main__ - Step 39506: {'lr': 0.0004248715953200749, 'samples': 7585152, 'steps': 39505, 'loss/train': 1.5462449789047241} 08/30/2021 20:18:51 - INFO - __main__ - Step 39507: {'lr': 0.00042486780283743927, 'samples': 7585344, 'steps': 39506, 'loss/train': 1.0202428102493286} 08/30/2021 20:18:51 - INFO - __main__ - Step 39508: {'lr': 0.00042486401027601084, 'samples': 7585536, 'steps': 39507, 'loss/train': 0.9145278930664062} 08/30/2021 20:18:52 - INFO - __main__ - Step 39509: {'lr': 0.0004248602176357915, 'samples': 7585728, 'steps': 39508, 'loss/train': 1.6860967874526978} 08/30/2021 20:18:52 - INFO - __main__ - Step 39510: {'lr': 0.0004248564249167828, 'samples': 7585920, 'steps': 39509, 'loss/train': 1.3073070049285889} 08/30/2021 20:18:54 - INFO - __main__ - Step 39511: {'lr': 0.00042485263211898647, 'samples': 7586112, 'steps': 39510, 'loss/train': 0.9959359765052795} 08/30/2021 20:18:54 - INFO - __main__ - Step 39512: {'lr': 0.00042484883924240427, 'samples': 7586304, 'steps': 39511, 'loss/train': 0.91527259349823} 08/30/2021 20:18:55 - INFO - __main__ - Step 39513: {'lr': 0.0004248450462870378, 'samples': 7586496, 'steps': 39512, 'loss/train': 1.3920543193817139} 08/30/2021 20:18:55 - INFO - __main__ - Step 39514: {'lr': 0.0004248412532528889, 'samples': 7586688, 'steps': 39513, 'loss/train': 1.7589521408081055} 08/30/2021 20:18:55 - INFO - __main__ - Step 39515: {'lr': 0.00042483746013995924, 'samples': 7586880, 'steps': 39514, 'loss/train': 1.122774600982666} 08/30/2021 20:18:57 - INFO - __main__ - Step 39516: {'lr': 0.00042483366694825054, 'samples': 7587072, 'steps': 39515, 'loss/train': 1.2255520820617676} 08/30/2021 20:18:57 - INFO - __main__ - Step 39517: {'lr': 0.0004248298736777645, 'samples': 7587264, 'steps': 39516, 'loss/train': 1.5675015449523926} 08/30/2021 20:18:58 - INFO - __main__ - Step 39518: {'lr': 0.00042482608032850275, 'samples': 7587456, 'steps': 39517, 'loss/train': 1.147222876548767} 08/30/2021 20:18:58 - INFO - __main__ - Step 39519: {'lr': 0.0004248222869004671, 'samples': 7587648, 'steps': 39518, 'loss/train': 1.7895618677139282} 08/30/2021 20:18:58 - INFO - __main__ - Step 39520: {'lr': 0.0004248184933936592, 'samples': 7587840, 'steps': 39519, 'loss/train': 1.3324826955795288} 08/30/2021 20:19:00 - INFO - __main__ - Step 39521: {'lr': 0.0004248146998080808, 'samples': 7588032, 'steps': 39520, 'loss/train': 1.1157089471817017} 08/30/2021 20:19:00 - INFO - __main__ - Step 39522: {'lr': 0.00042481090614373364, 'samples': 7588224, 'steps': 39521, 'loss/train': 1.195725917816162} 08/30/2021 20:19:01 - INFO - __main__ - Step 39523: {'lr': 0.00042480711240061933, 'samples': 7588416, 'steps': 39522, 'loss/train': 1.6636579036712646} 08/30/2021 20:19:01 - INFO - __main__ - Step 39524: {'lr': 0.0004248033185787397, 'samples': 7588608, 'steps': 39523, 'loss/train': 2.113940954208374} 08/30/2021 20:19:01 - INFO - __main__ - Step 39525: {'lr': 0.00042479952467809623, 'samples': 7588800, 'steps': 39524, 'loss/train': 0.8742247223854065} 08/30/2021 20:19:02 - INFO - __main__ - Step 39526: {'lr': 0.00042479573069869095, 'samples': 7588992, 'steps': 39525, 'loss/train': 1.3103822469711304} 08/30/2021 20:19:03 - INFO - __main__ - Step 39527: {'lr': 0.0004247919366405253, 'samples': 7589184, 'steps': 39526, 'loss/train': 0.8090722560882568} 08/30/2021 20:19:04 - INFO - __main__ - Step 39528: {'lr': 0.0004247881425036012, 'samples': 7589376, 'steps': 39527, 'loss/train': 1.4750295877456665} 08/30/2021 20:19:04 - INFO - __main__ - Step 39529: {'lr': 0.00042478434828792025, 'samples': 7589568, 'steps': 39528, 'loss/train': 1.0613157749176025} 08/30/2021 20:19:04 - INFO - __main__ - Step 39530: {'lr': 0.00042478055399348415, 'samples': 7589760, 'steps': 39529, 'loss/train': 1.7844194173812866} 08/30/2021 20:19:05 - INFO - __main__ - Step 39531: {'lr': 0.0004247767596202946, 'samples': 7589952, 'steps': 39530, 'loss/train': 1.3964990377426147} 08/30/2021 20:19:06 - INFO - __main__ - Step 39532: {'lr': 0.00042477296516835335, 'samples': 7590144, 'steps': 39531, 'loss/train': 1.268181324005127} 08/30/2021 20:19:07 - INFO - __main__ - Step 39533: {'lr': 0.00042476917063766207, 'samples': 7590336, 'steps': 39532, 'loss/train': 2.2163519859313965} 08/30/2021 20:19:07 - INFO - __main__ - Step 39534: {'lr': 0.0004247653760282225, 'samples': 7590528, 'steps': 39533, 'loss/train': 1.7320178747177124} 08/30/2021 20:19:08 - INFO - __main__ - Step 39535: {'lr': 0.0004247615813400364, 'samples': 7590720, 'steps': 39534, 'loss/train': 1.2027949094772339} 08/30/2021 20:19:08 - INFO - __main__ - Step 39536: {'lr': 0.0004247577865731055, 'samples': 7590912, 'steps': 39535, 'loss/train': 0.5038268566131592} 08/30/2021 20:19:09 - INFO - __main__ - Step 39537: {'lr': 0.00042475399172743134, 'samples': 7591104, 'steps': 39536, 'loss/train': 1.6581089496612549} 08/30/2021 20:19:10 - INFO - __main__ - Step 39538: {'lr': 0.0004247501968030157, 'samples': 7591296, 'steps': 39537, 'loss/train': 1.2676939964294434} 08/30/2021 20:19:10 - INFO - __main__ - Step 39539: {'lr': 0.00042474640179986035, 'samples': 7591488, 'steps': 39538, 'loss/train': 0.9572631120681763} 08/30/2021 20:19:10 - INFO - __main__ - Step 39540: {'lr': 0.00042474260671796697, 'samples': 7591680, 'steps': 39539, 'loss/train': 1.9065203666687012} 08/30/2021 20:19:11 - INFO - __main__ - Step 39541: {'lr': 0.0004247388115573373, 'samples': 7591872, 'steps': 39540, 'loss/train': 1.538730263710022} 08/30/2021 20:19:12 - INFO - __main__ - Step 39542: {'lr': 0.00042473501631797294, 'samples': 7592064, 'steps': 39541, 'loss/train': 0.1999540627002716} 08/30/2021 20:19:13 - INFO - __main__ - Step 39543: {'lr': 0.0004247312209998758, 'samples': 7592256, 'steps': 39542, 'loss/train': 1.7726805210113525} 08/30/2021 20:19:13 - INFO - __main__ - Step 39544: {'lr': 0.00042472742560304734, 'samples': 7592448, 'steps': 39543, 'loss/train': 1.321663737297058} 08/30/2021 20:19:13 - INFO - __main__ - Step 39545: {'lr': 0.00042472363012748947, 'samples': 7592640, 'steps': 39544, 'loss/train': 1.5099347829818726} 08/30/2021 20:19:14 - INFO - __main__ - Step 39546: {'lr': 0.00042471983457320384, 'samples': 7592832, 'steps': 39545, 'loss/train': 1.6786268949508667} 08/30/2021 20:19:16 - INFO - __main__ - Step 39547: {'lr': 0.00042471603894019206, 'samples': 7593024, 'steps': 39546, 'loss/train': 1.2953327894210815} 08/30/2021 20:19:16 - INFO - __main__ - Step 39548: {'lr': 0.00042471224322845603, 'samples': 7593216, 'steps': 39547, 'loss/train': 0.9177379608154297} 08/30/2021 20:19:16 - INFO - __main__ - Step 39549: {'lr': 0.00042470844743799734, 'samples': 7593408, 'steps': 39548, 'loss/train': 0.6467287540435791} 08/30/2021 20:19:17 - INFO - __main__ - Step 39550: {'lr': 0.00042470465156881765, 'samples': 7593600, 'steps': 39549, 'loss/train': 1.0442194938659668} 08/30/2021 20:19:17 - INFO - __main__ - Step 39551: {'lr': 0.00042470085562091887, 'samples': 7593792, 'steps': 39550, 'loss/train': 1.3773002624511719} 08/30/2021 20:19:19 - INFO - __main__ - Step 39552: {'lr': 0.0004246970595943025, 'samples': 7593984, 'steps': 39551, 'loss/train': 0.7412907481193542} 08/30/2021 20:19:19 - INFO - __main__ - Step 39553: {'lr': 0.0004246932634889703, 'samples': 7594176, 'steps': 39552, 'loss/train': 1.5008081197738647} 08/30/2021 20:19:20 - INFO - __main__ - Step 39554: {'lr': 0.00042468946730492404, 'samples': 7594368, 'steps': 39553, 'loss/train': 1.4761254787445068} 08/30/2021 20:19:20 - INFO - __main__ - Step 39555: {'lr': 0.00042468567104216536, 'samples': 7594560, 'steps': 39554, 'loss/train': 1.5336171388626099} 08/30/2021 20:19:20 - INFO - __main__ - Step 39556: {'lr': 0.0004246818747006961, 'samples': 7594752, 'steps': 39555, 'loss/train': 1.179232120513916} 08/30/2021 20:19:22 - INFO - __main__ - Step 39557: {'lr': 0.00042467807828051787, 'samples': 7594944, 'steps': 39556, 'loss/train': 1.318572759628296} 08/30/2021 20:19:22 - INFO - __main__ - Step 39558: {'lr': 0.0004246742817816323, 'samples': 7595136, 'steps': 39557, 'loss/train': 1.4071831703186035} 08/30/2021 20:19:23 - INFO - __main__ - Step 39559: {'lr': 0.00042467048520404126, 'samples': 7595328, 'steps': 39558, 'loss/train': 1.3430149555206299} 08/30/2021 20:19:23 - INFO - __main__ - Step 39560: {'lr': 0.00042466668854774636, 'samples': 7595520, 'steps': 39559, 'loss/train': 1.8356088399887085} 08/30/2021 20:19:23 - INFO - __main__ - Step 39561: {'lr': 0.00042466289181274943, 'samples': 7595712, 'steps': 39560, 'loss/train': 0.9999196529388428} 08/30/2021 20:19:26 - INFO - __main__ - Step 39562: {'lr': 0.00042465909499905206, 'samples': 7595904, 'steps': 39561, 'loss/train': 1.8007441759109497} 08/30/2021 20:19:26 - INFO - __main__ - Step 39563: {'lr': 0.0004246552981066559, 'samples': 7596096, 'steps': 39562, 'loss/train': 1.6961530447006226} 08/30/2021 20:19:26 - INFO - __main__ - Step 39564: {'lr': 0.0004246515011355629, 'samples': 7596288, 'steps': 39563, 'loss/train': 1.6991370916366577} 08/30/2021 20:19:27 - INFO - __main__ - Step 39565: {'lr': 0.0004246477040857746, 'samples': 7596480, 'steps': 39564, 'loss/train': 1.9942409992218018} 08/30/2021 20:19:27 - INFO - __main__ - Step 39566: {'lr': 0.0004246439069572926, 'samples': 7596672, 'steps': 39565, 'loss/train': 1.7631640434265137} 08/30/2021 20:19:27 - INFO - __main__ - Step 39567: {'lr': 0.00042464010975011893, 'samples': 7596864, 'steps': 39566, 'loss/train': 1.181044578552246} 08/30/2021 20:19:29 - INFO - __main__ - Step 39568: {'lr': 0.00042463631246425504, 'samples': 7597056, 'steps': 39567, 'loss/train': 0.8439130187034607} 08/30/2021 20:19:29 - INFO - __main__ - Step 39569: {'lr': 0.0004246325150997027, 'samples': 7597248, 'steps': 39568, 'loss/train': 1.4189765453338623} 08/30/2021 20:19:30 - INFO - __main__ - Step 39570: {'lr': 0.0004246287176564637, 'samples': 7597440, 'steps': 39569, 'loss/train': 1.715533971786499} 08/30/2021 20:19:30 - INFO - __main__ - Step 39571: {'lr': 0.0004246249201345397, 'samples': 7597632, 'steps': 39570, 'loss/train': 1.205657720565796} 08/30/2021 20:19:30 - INFO - __main__ - Step 39572: {'lr': 0.0004246211225339323, 'samples': 7597824, 'steps': 39571, 'loss/train': 1.4443302154541016} 08/30/2021 20:19:32 - INFO - __main__ - Step 39573: {'lr': 0.0004246173248546434, 'samples': 7598016, 'steps': 39572, 'loss/train': 1.4024207592010498} 08/30/2021 20:19:32 - INFO - __main__ - Step 39574: {'lr': 0.0004246135270966747, 'samples': 7598208, 'steps': 39573, 'loss/train': 1.9255534410476685} 08/30/2021 20:19:33 - INFO - __main__ - Step 39575: {'lr': 0.00042460972926002774, 'samples': 7598400, 'steps': 39574, 'loss/train': 1.9846572875976562} 08/30/2021 20:19:33 - INFO - __main__ - Step 39576: {'lr': 0.00042460593134470426, 'samples': 7598592, 'steps': 39575, 'loss/train': 0.5578235983848572} 08/30/2021 20:19:34 - INFO - __main__ - Step 39577: {'lr': 0.0004246021333507062, 'samples': 7598784, 'steps': 39576, 'loss/train': 1.2485721111297607} 08/30/2021 20:19:35 - INFO - __main__ - Step 39578: {'lr': 0.00042459833527803503, 'samples': 7598976, 'steps': 39577, 'loss/train': 1.5933971405029297} 08/30/2021 20:19:36 - INFO - __main__ - Step 39579: {'lr': 0.00042459453712669255, 'samples': 7599168, 'steps': 39578, 'loss/train': 1.4226523637771606} 08/30/2021 20:19:36 - INFO - __main__ - Step 39580: {'lr': 0.0004245907388966804, 'samples': 7599360, 'steps': 39579, 'loss/train': 1.3121119737625122} 08/30/2021 20:19:36 - INFO - __main__ - Step 39581: {'lr': 0.0004245869405880005, 'samples': 7599552, 'steps': 39580, 'loss/train': 1.4871419668197632} 08/30/2021 20:19:37 - INFO - __main__ - Step 39582: {'lr': 0.0004245831422006543, 'samples': 7599744, 'steps': 39581, 'loss/train': 1.8283289670944214} 08/30/2021 20:19:39 - INFO - __main__ - Step 39583: {'lr': 0.0004245793437346437, 'samples': 7599936, 'steps': 39582, 'loss/train': 1.5888737440109253} 08/30/2021 20:19:39 - INFO - __main__ - Step 39584: {'lr': 0.0004245755451899703, 'samples': 7600128, 'steps': 39583, 'loss/train': 1.085365653038025} 08/30/2021 20:19:39 - INFO - __main__ - Step 39585: {'lr': 0.0004245717465666359, 'samples': 7600320, 'steps': 39584, 'loss/train': 0.13444222509860992} 08/30/2021 20:19:40 - INFO - __main__ - Step 39586: {'lr': 0.0004245679478646421, 'samples': 7600512, 'steps': 39585, 'loss/train': 1.1106112003326416} 08/30/2021 20:19:40 - INFO - __main__ - Step 39587: {'lr': 0.00042456414908399075, 'samples': 7600704, 'steps': 39586, 'loss/train': 1.6339653730392456} 08/30/2021 20:19:42 - INFO - __main__ - Step 39588: {'lr': 0.00042456035022468344, 'samples': 7600896, 'steps': 39587, 'loss/train': 2.0127503871917725} 08/30/2021 20:19:42 - INFO - __main__ - Step 39589: {'lr': 0.0004245565512867219, 'samples': 7601088, 'steps': 39588, 'loss/train': 1.4844590425491333} 08/30/2021 20:19:43 - INFO - __main__ - Step 39590: {'lr': 0.000424552752270108, 'samples': 7601280, 'steps': 39589, 'loss/train': 0.3811574876308441} 08/30/2021 20:19:43 - INFO - __main__ - Step 39591: {'lr': 0.0004245489531748432, 'samples': 7601472, 'steps': 39590, 'loss/train': 1.7608567476272583} 08/30/2021 20:19:43 - INFO - __main__ - Step 39592: {'lr': 0.00042454515400092944, 'samples': 7601664, 'steps': 39591, 'loss/train': 5.242020606994629} 08/30/2021 20:19:44 - INFO - __main__ - Step 39593: {'lr': 0.00042454135474836817, 'samples': 7601856, 'steps': 39592, 'loss/train': 1.218087077140808} 08/30/2021 20:19:45 - INFO - __main__ - Step 39594: {'lr': 0.0004245375554171613, 'samples': 7602048, 'steps': 39593, 'loss/train': 0.9052404165267944} 08/30/2021 20:19:46 - INFO - __main__ - Step 39595: {'lr': 0.00042453375600731057, 'samples': 7602240, 'steps': 39594, 'loss/train': 1.5481382608413696} 08/30/2021 20:19:46 - INFO - __main__ - Step 39596: {'lr': 0.00042452995651881764, 'samples': 7602432, 'steps': 39595, 'loss/train': 1.738535761833191} 08/30/2021 20:19:46 - INFO - __main__ - Step 39597: {'lr': 0.0004245261569516842, 'samples': 7602624, 'steps': 39596, 'loss/train': 0.7275892496109009} 08/30/2021 20:19:47 - INFO - __main__ - Step 39598: {'lr': 0.00042452235730591195, 'samples': 7602816, 'steps': 39597, 'loss/train': 1.4351816177368164} 08/30/2021 20:19:48 - INFO - __main__ - Step 39599: {'lr': 0.00042451855758150254, 'samples': 7603008, 'steps': 39598, 'loss/train': 0.7411654591560364} 08/30/2021 20:19:49 - INFO - __main__ - Step 39600: {'lr': 0.00042451475777845784, 'samples': 7603200, 'steps': 39599, 'loss/train': 1.7640950679779053} 08/30/2021 20:19:49 - INFO - __main__ - Step 39601: {'lr': 0.00042451095789677943, 'samples': 7603392, 'steps': 39600, 'loss/train': 1.423945665359497} 08/30/2021 20:19:49 - INFO - __main__ - Step 39602: {'lr': 0.0004245071579364691, 'samples': 7603584, 'steps': 39601, 'loss/train': 1.0180280208587646} 08/30/2021 20:19:50 - INFO - __main__ - Step 39603: {'lr': 0.0004245033578975286, 'samples': 7603776, 'steps': 39602, 'loss/train': 1.0098040103912354} 08/30/2021 20:19:51 - INFO - __main__ - Step 39604: {'lr': 0.00042449955777995954, 'samples': 7603968, 'steps': 39603, 'loss/train': 1.530120849609375} 08/30/2021 20:19:52 - INFO - __main__ - Step 39605: {'lr': 0.0004244957575837636, 'samples': 7604160, 'steps': 39604, 'loss/train': 1.3768794536590576} 08/30/2021 20:19:52 - INFO - __main__ - Step 39606: {'lr': 0.00042449195730894266, 'samples': 7604352, 'steps': 39605, 'loss/train': 1.3495783805847168} 08/30/2021 20:19:53 - INFO - __main__ - Step 39607: {'lr': 0.00042448815695549823, 'samples': 7604544, 'steps': 39606, 'loss/train': 1.0748873949050903} 08/30/2021 20:19:53 - INFO - __main__ - Step 39608: {'lr': 0.00042448435652343223, 'samples': 7604736, 'steps': 39607, 'loss/train': 0.28193408250808716} 08/30/2021 20:19:53 - INFO - __main__ - Step 39609: {'lr': 0.0004244805560127463, 'samples': 7604928, 'steps': 39608, 'loss/train': 1.3490265607833862} 08/30/2021 20:19:55 - INFO - __main__ - Step 39610: {'lr': 0.00042447675542344203, 'samples': 7605120, 'steps': 39609, 'loss/train': 1.0516595840454102} 08/30/2021 20:19:55 - INFO - __main__ - Step 39611: {'lr': 0.0004244729547555213, 'samples': 7605312, 'steps': 39610, 'loss/train': 1.6864597797393799} 08/30/2021 20:19:56 - INFO - __main__ - Step 39612: {'lr': 0.00042446915400898565, 'samples': 7605504, 'steps': 39611, 'loss/train': 1.721461296081543} 08/30/2021 20:19:56 - INFO - __main__ - Step 39613: {'lr': 0.00042446535318383695, 'samples': 7605696, 'steps': 39612, 'loss/train': 1.4178909063339233} 08/30/2021 20:19:56 - INFO - __main__ - Step 39614: {'lr': 0.00042446155228007687, 'samples': 7605888, 'steps': 39613, 'loss/train': 1.7122137546539307} 08/30/2021 20:19:58 - INFO - __main__ - Step 39615: {'lr': 0.0004244577512977071, 'samples': 7606080, 'steps': 39614, 'loss/train': 2.324068307876587} 08/30/2021 20:19:59 - INFO - __main__ - Step 39616: {'lr': 0.00042445395023672935, 'samples': 7606272, 'steps': 39615, 'loss/train': 1.7929363250732422} 08/30/2021 20:19:59 - INFO - __main__ - Step 39617: {'lr': 0.0004244501490971454, 'samples': 7606464, 'steps': 39616, 'loss/train': 1.9229449033737183} 08/30/2021 20:19:59 - INFO - __main__ - Step 39618: {'lr': 0.0004244463478789568, 'samples': 7606656, 'steps': 39617, 'loss/train': 0.8985770344734192} 08/30/2021 20:20:00 - INFO - __main__ - Step 39619: {'lr': 0.0004244425465821654, 'samples': 7606848, 'steps': 39618, 'loss/train': 1.1737024784088135} 08/30/2021 20:20:00 - INFO - __main__ - Step 39620: {'lr': 0.0004244387452067729, 'samples': 7607040, 'steps': 39619, 'loss/train': 0.37495139241218567} 08/30/2021 20:20:02 - INFO - __main__ - Step 39621: {'lr': 0.000424434943752781, 'samples': 7607232, 'steps': 39620, 'loss/train': 1.5510468482971191} 08/30/2021 20:20:02 - INFO - __main__ - Step 39622: {'lr': 0.0004244311422201914, 'samples': 7607424, 'steps': 39621, 'loss/train': 1.1349774599075317} 08/30/2021 20:20:03 - INFO - __main__ - Step 39623: {'lr': 0.0004244273406090058, 'samples': 7607616, 'steps': 39622, 'loss/train': 1.3849761486053467} 08/30/2021 20:20:03 - INFO - __main__ - Step 39624: {'lr': 0.000424423538919226, 'samples': 7607808, 'steps': 39623, 'loss/train': 1.084895133972168} 08/30/2021 20:20:03 - INFO - __main__ - Step 39625: {'lr': 0.0004244197371508536, 'samples': 7608000, 'steps': 39624, 'loss/train': 2.32084059715271} 08/30/2021 20:20:05 - INFO - __main__ - Step 39626: {'lr': 0.00042441593530389025, 'samples': 7608192, 'steps': 39625, 'loss/train': 1.5204460620880127} 08/30/2021 20:20:05 - INFO - __main__ - Step 39627: {'lr': 0.0004244121333783379, 'samples': 7608384, 'steps': 39626, 'loss/train': 1.4676190614700317} 08/30/2021 20:20:06 - INFO - __main__ - Step 39628: {'lr': 0.0004244083313741981, 'samples': 7608576, 'steps': 39627, 'loss/train': 1.4633153676986694} 08/30/2021 20:20:06 - INFO - __main__ - Step 39629: {'lr': 0.0004244045292914726, 'samples': 7608768, 'steps': 39628, 'loss/train': 1.313714861869812} 08/30/2021 20:20:06 - INFO - __main__ - Step 39630: {'lr': 0.00042440072713016317, 'samples': 7608960, 'steps': 39629, 'loss/train': 1.387855052947998} 08/30/2021 20:20:08 - INFO - __main__ - Step 39631: {'lr': 0.00042439692489027136, 'samples': 7609152, 'steps': 39630, 'loss/train': 1.3798304796218872} 08/30/2021 20:20:08 - INFO - __main__ - Step 39632: {'lr': 0.000424393122571799, 'samples': 7609344, 'steps': 39631, 'loss/train': 1.1280311346054077} 08/30/2021 20:20:09 - INFO - __main__ - Step 39633: {'lr': 0.00042438932017474783, 'samples': 7609536, 'steps': 39632, 'loss/train': 1.1781045198440552} 08/30/2021 20:20:09 - INFO - __main__ - Step 39634: {'lr': 0.0004243855176991195, 'samples': 7609728, 'steps': 39633, 'loss/train': 1.705105185508728} 08/30/2021 20:20:09 - INFO - __main__ - Step 39635: {'lr': 0.0004243817151449158, 'samples': 7609920, 'steps': 39634, 'loss/train': 1.374541163444519} 08/30/2021 20:20:11 - INFO - __main__ - Step 39636: {'lr': 0.0004243779125121383, 'samples': 7610112, 'steps': 39635, 'loss/train': 1.4222357273101807} 08/30/2021 20:20:11 - INFO - __main__ - Step 39637: {'lr': 0.00042437410980078894, 'samples': 7610304, 'steps': 39636, 'loss/train': 1.373152732849121} 08/30/2021 20:20:12 - INFO - __main__ - Step 39638: {'lr': 0.0004243703070108692, 'samples': 7610496, 'steps': 39637, 'loss/train': 1.3218297958374023} 08/30/2021 20:20:12 - INFO - __main__ - Step 39639: {'lr': 0.00042436650414238086, 'samples': 7610688, 'steps': 39638, 'loss/train': 0.9254968762397766} 08/30/2021 20:20:12 - INFO - __main__ - Step 39640: {'lr': 0.0004243627011953257, 'samples': 7610880, 'steps': 39639, 'loss/train': 1.0002259016036987} 08/30/2021 20:20:14 - INFO - __main__ - Step 39641: {'lr': 0.0004243588981697054, 'samples': 7611072, 'steps': 39640, 'loss/train': 1.3645919561386108} 08/30/2021 20:20:14 - INFO - __main__ - Step 39642: {'lr': 0.0004243550950655217, 'samples': 7611264, 'steps': 39641, 'loss/train': 2.0988473892211914} 08/30/2021 20:20:15 - INFO - __main__ - Step 39643: {'lr': 0.00042435129188277625, 'samples': 7611456, 'steps': 39642, 'loss/train': 1.6015135049819946} 08/30/2021 20:20:15 - INFO - __main__ - Step 39644: {'lr': 0.0004243474886214708, 'samples': 7611648, 'steps': 39643, 'loss/train': 1.3720701932907104} 08/30/2021 20:20:15 - INFO - __main__ - Step 39645: {'lr': 0.0004243436852816071, 'samples': 7611840, 'steps': 39644, 'loss/train': 1.2842869758605957} 08/30/2021 20:20:17 - INFO - __main__ - Step 39646: {'lr': 0.0004243398818631868, 'samples': 7612032, 'steps': 39645, 'loss/train': 1.5468418598175049} 08/30/2021 20:20:17 - INFO - __main__ - Step 39647: {'lr': 0.0004243360783662116, 'samples': 7612224, 'steps': 39646, 'loss/train': 0.5295102000236511} 08/30/2021 20:20:18 - INFO - __main__ - Step 39648: {'lr': 0.0004243322747906833, 'samples': 7612416, 'steps': 39647, 'loss/train': 0.30289480090141296} 08/30/2021 20:20:18 - INFO - __main__ - Step 39649: {'lr': 0.00042432847113660355, 'samples': 7612608, 'steps': 39648, 'loss/train': 0.9014484286308289} 08/30/2021 20:20:18 - INFO - __main__ - Step 39650: {'lr': 0.0004243246674039741, 'samples': 7612800, 'steps': 39649, 'loss/train': 1.8353095054626465} 08/30/2021 20:20:20 - INFO - __main__ - Step 39651: {'lr': 0.00042432086359279667, 'samples': 7612992, 'steps': 39650, 'loss/train': 1.4529352188110352} 08/30/2021 20:20:20 - INFO - __main__ - Step 39652: {'lr': 0.0004243170597030729, 'samples': 7613184, 'steps': 39651, 'loss/train': 1.6424646377563477} 08/30/2021 20:20:21 - INFO - __main__ - Step 39653: {'lr': 0.0004243132557348045, 'samples': 7613376, 'steps': 39652, 'loss/train': 1.0673192739486694} 08/30/2021 20:20:21 - INFO - __main__ - Step 39654: {'lr': 0.00042430945168799326, 'samples': 7613568, 'steps': 39653, 'loss/train': 1.2372204065322876} 08/30/2021 20:20:21 - INFO - __main__ - Step 39655: {'lr': 0.000424305647562641, 'samples': 7613760, 'steps': 39654, 'loss/train': 0.9994213581085205} 08/30/2021 20:20:23 - INFO - __main__ - Step 39656: {'lr': 0.00042430184335874924, 'samples': 7613952, 'steps': 39655, 'loss/train': 1.098544955253601} 08/30/2021 20:20:23 - INFO - __main__ - Step 39657: {'lr': 0.0004242980390763197, 'samples': 7614144, 'steps': 39656, 'loss/train': 1.1567517518997192} 08/30/2021 20:20:24 - INFO - __main__ - Step 39658: {'lr': 0.0004242942347153542, 'samples': 7614336, 'steps': 39657, 'loss/train': 1.428024411201477} 08/30/2021 20:20:24 - INFO - __main__ - Step 39659: {'lr': 0.00042429043027585435, 'samples': 7614528, 'steps': 39658, 'loss/train': 1.4090584516525269} 08/30/2021 20:20:24 - INFO - __main__ - Step 39660: {'lr': 0.000424286625757822, 'samples': 7614720, 'steps': 39659, 'loss/train': 1.344565510749817} 08/30/2021 20:20:25 - INFO - __main__ - Step 39661: {'lr': 0.00042428282116125873, 'samples': 7614912, 'steps': 39660, 'loss/train': 1.4870916604995728} 08/30/2021 20:20:26 - INFO - __main__ - Step 39662: {'lr': 0.0004242790164861663, 'samples': 7615104, 'steps': 39661, 'loss/train': 1.3315699100494385} 08/30/2021 20:20:27 - INFO - __main__ - Step 39663: {'lr': 0.0004242752117325465, 'samples': 7615296, 'steps': 39662, 'loss/train': 1.230576515197754} 08/30/2021 20:20:27 - INFO - __main__ - Step 39664: {'lr': 0.000424271406900401, 'samples': 7615488, 'steps': 39663, 'loss/train': 0.9211643934249878} 08/30/2021 20:20:27 - INFO - __main__ - Step 39665: {'lr': 0.0004242676019897314, 'samples': 7615680, 'steps': 39664, 'loss/train': 1.0158231258392334} 08/30/2021 20:20:28 - INFO - __main__ - Step 39666: {'lr': 0.00042426379700053954, 'samples': 7615872, 'steps': 39665, 'loss/train': 1.5026607513427734} 08/30/2021 20:20:29 - INFO - __main__ - Step 39667: {'lr': 0.00042425999193282713, 'samples': 7616064, 'steps': 39666, 'loss/train': 1.8173192739486694} 08/30/2021 20:20:30 - INFO - __main__ - Step 39668: {'lr': 0.0004242561867865958, 'samples': 7616256, 'steps': 39667, 'loss/train': 1.5084888935089111} 08/30/2021 20:20:30 - INFO - __main__ - Step 39669: {'lr': 0.0004242523815618473, 'samples': 7616448, 'steps': 39668, 'loss/train': 1.3154528141021729} 08/30/2021 20:20:31 - INFO - __main__ - Step 39670: {'lr': 0.0004242485762585835, 'samples': 7616640, 'steps': 39669, 'loss/train': 1.3291431665420532} 08/30/2021 20:20:31 - INFO - __main__ - Step 39671: {'lr': 0.0004242447708768059, 'samples': 7616832, 'steps': 39670, 'loss/train': 1.6188416481018066} 08/30/2021 20:20:33 - INFO - __main__ - Step 39672: {'lr': 0.0004242409654165163, 'samples': 7617024, 'steps': 39671, 'loss/train': 1.55584716796875} 08/30/2021 20:20:33 - INFO - __main__ - Step 39673: {'lr': 0.00042423715987771637, 'samples': 7617216, 'steps': 39672, 'loss/train': 1.708908200263977} 08/30/2021 20:20:34 - INFO - __main__ - Step 39674: {'lr': 0.0004242333542604079, 'samples': 7617408, 'steps': 39673, 'loss/train': 1.2755793333053589} 08/30/2021 20:20:34 - INFO - __main__ - Step 39675: {'lr': 0.0004242295485645926, 'samples': 7617600, 'steps': 39674, 'loss/train': 1.422940969467163} 08/30/2021 20:20:34 - INFO - __main__ - Step 39676: {'lr': 0.0004242257427902721, 'samples': 7617792, 'steps': 39675, 'loss/train': 1.6290698051452637} 08/30/2021 20:20:36 - INFO - __main__ - Step 39677: {'lr': 0.00042422193693744827, 'samples': 7617984, 'steps': 39676, 'loss/train': 1.594285249710083} 08/30/2021 20:20:36 - INFO - __main__ - Step 39678: {'lr': 0.0004242181310061226, 'samples': 7618176, 'steps': 39677, 'loss/train': 2.1580467224121094} 08/30/2021 20:20:37 - INFO - __main__ - Step 39679: {'lr': 0.000424214324996297, 'samples': 7618368, 'steps': 39678, 'loss/train': 1.8396358489990234} 08/30/2021 20:20:37 - INFO - __main__ - Step 39680: {'lr': 0.000424210518907973, 'samples': 7618560, 'steps': 39679, 'loss/train': 1.3235629796981812} 08/30/2021 20:20:37 - INFO - __main__ - Step 39681: {'lr': 0.0004242067127411525, 'samples': 7618752, 'steps': 39680, 'loss/train': 1.2612700462341309} 08/30/2021 20:20:39 - INFO - __main__ - Step 39682: {'lr': 0.0004242029064958372, 'samples': 7618944, 'steps': 39681, 'loss/train': 1.8453831672668457} 08/30/2021 20:20:40 - INFO - __main__ - Step 39683: {'lr': 0.0004241991001720287, 'samples': 7619136, 'steps': 39682, 'loss/train': 1.2175443172454834} 08/30/2021 20:20:40 - INFO - __main__ - Step 39684: {'lr': 0.00042419529376972885, 'samples': 7619328, 'steps': 39683, 'loss/train': 1.4574471712112427} 08/30/2021 20:20:40 - INFO - __main__ - Step 39685: {'lr': 0.0004241914872889392, 'samples': 7619520, 'steps': 39684, 'loss/train': 1.4367091655731201} 08/30/2021 20:20:41 - INFO - __main__ - Step 39686: {'lr': 0.00042418768072966163, 'samples': 7619712, 'steps': 39685, 'loss/train': 1.7369105815887451} 08/30/2021 20:20:41 - INFO - __main__ - Step 39687: {'lr': 0.0004241838740918977, 'samples': 7619904, 'steps': 39686, 'loss/train': 2.5677261352539062} 08/30/2021 20:20:43 - INFO - __main__ - Step 39688: {'lr': 0.00042418006737564924, 'samples': 7620096, 'steps': 39687, 'loss/train': 1.3622618913650513} 08/30/2021 20:20:43 - INFO - __main__ - Step 39689: {'lr': 0.0004241762605809179, 'samples': 7620288, 'steps': 39688, 'loss/train': 1.7934119701385498} 08/30/2021 20:20:44 - INFO - __main__ - Step 39690: {'lr': 0.00042417245370770547, 'samples': 7620480, 'steps': 39689, 'loss/train': 1.4852654933929443} 08/30/2021 20:20:44 - INFO - __main__ - Step 39691: {'lr': 0.00042416864675601365, 'samples': 7620672, 'steps': 39690, 'loss/train': 2.3179264068603516} 08/30/2021 20:20:44 - INFO - __main__ - Step 39692: {'lr': 0.0004241648397258441, 'samples': 7620864, 'steps': 39691, 'loss/train': 1.2021403312683105} 08/30/2021 20:20:46 - INFO - __main__ - Step 39693: {'lr': 0.0004241610326171985, 'samples': 7621056, 'steps': 39692, 'loss/train': 1.3357957601547241} 08/30/2021 20:20:46 - INFO - __main__ - Step 39694: {'lr': 0.0004241572254300786, 'samples': 7621248, 'steps': 39693, 'loss/train': 1.3742859363555908} 08/30/2021 20:20:47 - INFO - __main__ - Step 39695: {'lr': 0.00042415341816448625, 'samples': 7621440, 'steps': 39694, 'loss/train': 0.7203447222709656} 08/30/2021 20:20:47 - INFO - __main__ - Step 39696: {'lr': 0.000424149610820423, 'samples': 7621632, 'steps': 39695, 'loss/train': 1.7883760929107666} 08/30/2021 20:20:47 - INFO - __main__ - Step 39697: {'lr': 0.00042414580339789065, 'samples': 7621824, 'steps': 39696, 'loss/train': 1.5429047346115112} 08/30/2021 20:20:49 - INFO - __main__ - Step 39698: {'lr': 0.00042414199589689084, 'samples': 7622016, 'steps': 39697, 'loss/train': 1.3451834917068481} 08/30/2021 20:20:49 - INFO - __main__ - Step 39699: {'lr': 0.0004241381883174254, 'samples': 7622208, 'steps': 39698, 'loss/train': 1.063746452331543} 08/30/2021 20:20:49 - INFO - __main__ - Step 39700: {'lr': 0.00042413438065949595, 'samples': 7622400, 'steps': 39699, 'loss/train': 1.5426853895187378} 08/30/2021 20:20:50 - INFO - __main__ - Step 39701: {'lr': 0.0004241305729231042, 'samples': 7622592, 'steps': 39700, 'loss/train': 1.979162573814392} 08/30/2021 20:20:50 - INFO - __main__ - Step 39702: {'lr': 0.00042412676510825197, 'samples': 7622784, 'steps': 39701, 'loss/train': 1.1119879484176636} 08/30/2021 20:20:52 - INFO - __main__ - Step 39703: {'lr': 0.00042412295721494086, 'samples': 7622976, 'steps': 39702, 'loss/train': 0.3166111707687378} 08/30/2021 20:20:52 - INFO - __main__ - Step 39704: {'lr': 0.00042411914924317265, 'samples': 7623168, 'steps': 39703, 'loss/train': 1.8205727338790894} 08/30/2021 20:20:53 - INFO - __main__ - Step 39705: {'lr': 0.00042411534119294903, 'samples': 7623360, 'steps': 39704, 'loss/train': 0.08558724820613861} 08/30/2021 20:20:53 - INFO - __main__ - Step 39706: {'lr': 0.0004241115330642717, 'samples': 7623552, 'steps': 39705, 'loss/train': 1.253430724143982} 08/30/2021 20:20:53 - INFO - __main__ - Step 39707: {'lr': 0.0004241077248571424, 'samples': 7623744, 'steps': 39706, 'loss/train': 1.7641167640686035} 08/30/2021 20:20:54 - INFO - __main__ - Step 39708: {'lr': 0.0004241039165715629, 'samples': 7623936, 'steps': 39707, 'loss/train': 1.6174490451812744} 08/30/2021 20:20:55 - INFO - __main__ - Step 39709: {'lr': 0.00042410010820753485, 'samples': 7624128, 'steps': 39708, 'loss/train': 1.50947904586792} 08/30/2021 20:20:56 - INFO - __main__ - Step 39710: {'lr': 0.00042409629976505994, 'samples': 7624320, 'steps': 39709, 'loss/train': 2.0942623615264893} 08/30/2021 20:20:56 - INFO - __main__ - Step 39711: {'lr': 0.00042409249124414, 'samples': 7624512, 'steps': 39710, 'loss/train': 1.424556851387024} 08/30/2021 20:20:57 - INFO - __main__ - Step 39712: {'lr': 0.00042408868264477657, 'samples': 7624704, 'steps': 39711, 'loss/train': 1.8498318195343018} 08/30/2021 20:20:57 - INFO - __main__ - Step 39713: {'lr': 0.00042408487396697147, 'samples': 7624896, 'steps': 39712, 'loss/train': 1.6383851766586304} 08/30/2021 20:20:58 - INFO - __main__ - Step 39714: {'lr': 0.0004240810652107265, 'samples': 7625088, 'steps': 39713, 'loss/train': 1.579742431640625} 08/30/2021 20:20:59 - INFO - __main__ - Step 39715: {'lr': 0.0004240772563760432, 'samples': 7625280, 'steps': 39714, 'loss/train': 1.310516119003296} 08/30/2021 20:20:59 - INFO - __main__ - Step 39716: {'lr': 0.00042407344746292345, 'samples': 7625472, 'steps': 39715, 'loss/train': 2.0912563800811768} 08/30/2021 20:21:00 - INFO - __main__ - Step 39717: {'lr': 0.00042406963847136883, 'samples': 7625664, 'steps': 39716, 'loss/train': 1.6308954954147339} 08/30/2021 20:21:00 - INFO - __main__ - Step 39718: {'lr': 0.0004240658294013812, 'samples': 7625856, 'steps': 39717, 'loss/train': 1.8312853574752808} 08/30/2021 20:21:01 - INFO - __main__ - Step 39719: {'lr': 0.00042406202025296213, 'samples': 7626048, 'steps': 39718, 'loss/train': 1.6745630502700806} 08/30/2021 20:21:02 - INFO - __main__ - Step 39720: {'lr': 0.00042405821102611336, 'samples': 7626240, 'steps': 39719, 'loss/train': 1.1348166465759277} 08/30/2021 20:21:02 - INFO - __main__ - Step 39721: {'lr': 0.0004240544017208367, 'samples': 7626432, 'steps': 39720, 'loss/train': 1.1951721906661987} 08/30/2021 20:21:03 - INFO - __main__ - Step 39722: {'lr': 0.0004240505923371338, 'samples': 7626624, 'steps': 39721, 'loss/train': 1.2257647514343262} 08/30/2021 20:21:03 - INFO - __main__ - Step 39723: {'lr': 0.0004240467828750064, 'samples': 7626816, 'steps': 39722, 'loss/train': 1.4201858043670654} 08/30/2021 20:21:05 - INFO - __main__ - Step 39724: {'lr': 0.0004240429733344562, 'samples': 7627008, 'steps': 39723, 'loss/train': 1.5598580837249756} 08/30/2021 20:21:06 - INFO - __main__ - Step 39725: {'lr': 0.0004240391637154849, 'samples': 7627200, 'steps': 39724, 'loss/train': 0.9043325781822205} 08/30/2021 20:21:06 - INFO - __main__ - Step 39726: {'lr': 0.0004240353540180942, 'samples': 7627392, 'steps': 39725, 'loss/train': 1.3059759140014648} 08/30/2021 20:21:06 - INFO - __main__ - Step 39727: {'lr': 0.00042403154424228596, 'samples': 7627584, 'steps': 39726, 'loss/train': 2.4985077381134033} 08/30/2021 20:21:07 - INFO - __main__ - Step 39728: {'lr': 0.00042402773438806175, 'samples': 7627776, 'steps': 39727, 'loss/train': 2.4102859497070312} 08/30/2021 20:21:07 - INFO - __main__ - Step 39729: {'lr': 0.00042402392445542333, 'samples': 7627968, 'steps': 39728, 'loss/train': 1.0131531953811646} 08/30/2021 20:21:07 - INFO - __main__ - Step 39730: {'lr': 0.0004240201144443724, 'samples': 7628160, 'steps': 39729, 'loss/train': 0.4219430685043335} 08/30/2021 20:21:09 - INFO - __main__ - Step 39731: {'lr': 0.00042401630435491073, 'samples': 7628352, 'steps': 39730, 'loss/train': 1.3452719449996948} 08/30/2021 20:21:10 - INFO - __main__ - Step 39732: {'lr': 0.00042401249418703996, 'samples': 7628544, 'steps': 39731, 'loss/train': 1.2301236391067505} 08/30/2021 20:21:10 - INFO - __main__ - Step 39733: {'lr': 0.00042400868394076185, 'samples': 7628736, 'steps': 39732, 'loss/train': 1.7061527967453003} 08/30/2021 20:21:10 - INFO - __main__ - Step 39734: {'lr': 0.0004240048736160781, 'samples': 7628928, 'steps': 39733, 'loss/train': 1.0829201936721802} 08/30/2021 20:21:11 - INFO - __main__ - Step 39735: {'lr': 0.0004240010632129905, 'samples': 7629120, 'steps': 39734, 'loss/train': 1.6662555932998657} 08/30/2021 20:21:12 - INFO - __main__ - Step 39736: {'lr': 0.00042399725273150056, 'samples': 7629312, 'steps': 39735, 'loss/train': 1.4515132904052734} 08/30/2021 20:21:13 - INFO - __main__ - Step 39737: {'lr': 0.0004239934421716103, 'samples': 7629504, 'steps': 39736, 'loss/train': 0.6121734976768494} 08/30/2021 20:21:13 - INFO - __main__ - Step 39738: {'lr': 0.00042398963153332124, 'samples': 7629696, 'steps': 39737, 'loss/train': 0.9485858678817749} 08/30/2021 20:21:13 - INFO - __main__ - Step 39739: {'lr': 0.00042398582081663513, 'samples': 7629888, 'steps': 39738, 'loss/train': 1.646243691444397} 08/30/2021 20:21:14 - INFO - __main__ - Step 39740: {'lr': 0.0004239820100215537, 'samples': 7630080, 'steps': 39739, 'loss/train': 1.9203139543533325} 08/30/2021 20:21:14 - INFO - __main__ - Step 39741: {'lr': 0.00042397819914807855, 'samples': 7630272, 'steps': 39740, 'loss/train': 0.053706929087638855} 08/30/2021 20:21:15 - INFO - __main__ - Step 39742: {'lr': 0.00042397438819621164, 'samples': 7630464, 'steps': 39741, 'loss/train': 1.4636296033859253} 08/30/2021 20:21:16 - INFO - __main__ - Step 39743: {'lr': 0.0004239705771659545, 'samples': 7630656, 'steps': 39742, 'loss/train': 1.2163830995559692} 08/30/2021 20:21:16 - INFO - __main__ - Step 39744: {'lr': 0.000423966766057309, 'samples': 7630848, 'steps': 39743, 'loss/train': 1.6223723888397217} 08/30/2021 20:21:16 - INFO - __main__ - Step 39745: {'lr': 0.00042396295487027666, 'samples': 7631040, 'steps': 39744, 'loss/train': 1.0613372325897217} 08/30/2021 20:21:17 - INFO - __main__ - Step 39746: {'lr': 0.0004239591436048593, 'samples': 7631232, 'steps': 39745, 'loss/train': 1.5498744249343872} 08/30/2021 20:21:19 - INFO - __main__ - Step 39747: {'lr': 0.0004239553322610586, 'samples': 7631424, 'steps': 39746, 'loss/train': 1.68617582321167} 08/30/2021 20:21:19 - INFO - __main__ - Step 39748: {'lr': 0.0004239515208388764, 'samples': 7631616, 'steps': 39747, 'loss/train': 1.2268978357315063} 08/30/2021 20:21:20 - INFO - __main__ - Step 39749: {'lr': 0.00042394770933831425, 'samples': 7631808, 'steps': 39748, 'loss/train': 1.8943700790405273} 08/30/2021 20:21:20 - INFO - __main__ - Step 39750: {'lr': 0.00042394389775937403, 'samples': 7632000, 'steps': 39749, 'loss/train': 1.6310123205184937} 08/30/2021 20:21:20 - INFO - __main__ - Step 39751: {'lr': 0.0004239400861020574, 'samples': 7632192, 'steps': 39750, 'loss/train': 2.052149534225464} 08/30/2021 20:21:21 - INFO - __main__ - Step 39752: {'lr': 0.00042393627436636597, 'samples': 7632384, 'steps': 39751, 'loss/train': 1.577345609664917} 08/30/2021 20:21:23 - INFO - __main__ - Step 39753: {'lr': 0.0004239324625523015, 'samples': 7632576, 'steps': 39752, 'loss/train': 1.107822299003601} 08/30/2021 20:21:24 - INFO - __main__ - Step 39754: {'lr': 0.00042392865065986573, 'samples': 7632768, 'steps': 39753, 'loss/train': 1.2555097341537476} 08/30/2021 20:21:24 - INFO - __main__ - Step 39755: {'lr': 0.00042392483868906053, 'samples': 7632960, 'steps': 39754, 'loss/train': 1.6713358163833618} 08/30/2021 20:21:24 - INFO - __main__ - Step 39756: {'lr': 0.0004239210266398874, 'samples': 7633152, 'steps': 39755, 'loss/train': 0.10498946160078049} 08/30/2021 20:21:25 - INFO - __main__ - Step 39757: {'lr': 0.0004239172145123481, 'samples': 7633344, 'steps': 39756, 'loss/train': 1.5836464166641235} 08/30/2021 20:21:25 - INFO - __main__ - Step 39758: {'lr': 0.0004239134023064445, 'samples': 7633536, 'steps': 39757, 'loss/train': 1.675431728363037} 08/30/2021 20:21:25 - INFO - __main__ - Step 39759: {'lr': 0.0004239095900221781, 'samples': 7633728, 'steps': 39758, 'loss/train': 0.0664868876338005} 08/30/2021 20:21:27 - INFO - __main__ - Step 39760: {'lr': 0.00042390577765955077, 'samples': 7633920, 'steps': 39759, 'loss/train': 1.6064023971557617} 08/30/2021 20:21:27 - INFO - __main__ - Step 39761: {'lr': 0.00042390196521856417, 'samples': 7634112, 'steps': 39760, 'loss/train': 1.6149566173553467} 08/30/2021 20:21:28 - INFO - __main__ - Step 39762: {'lr': 0.00042389815269922005, 'samples': 7634304, 'steps': 39761, 'loss/train': 1.4950525760650635} 08/30/2021 20:21:28 - INFO - __main__ - Step 39763: {'lr': 0.0004238943401015201, 'samples': 7634496, 'steps': 39762, 'loss/train': 1.5462342500686646} 08/30/2021 20:21:28 - INFO - __main__ - Step 39764: {'lr': 0.0004238905274254661, 'samples': 7634688, 'steps': 39763, 'loss/train': 1.8067632913589478} 08/30/2021 20:21:30 - INFO - __main__ - Step 39765: {'lr': 0.0004238867146710596, 'samples': 7634880, 'steps': 39764, 'loss/train': 2.1296796798706055} 08/30/2021 20:21:30 - INFO - __main__ - Step 39766: {'lr': 0.0004238829018383025, 'samples': 7635072, 'steps': 39765, 'loss/train': 1.5659006834030151} 08/30/2021 20:21:31 - INFO - __main__ - Step 39767: {'lr': 0.0004238790889271964, 'samples': 7635264, 'steps': 39766, 'loss/train': 1.9521446228027344} 08/30/2021 20:21:31 - INFO - __main__ - Step 39768: {'lr': 0.0004238752759377431, 'samples': 7635456, 'steps': 39767, 'loss/train': 1.5365787744522095} 08/30/2021 20:21:31 - INFO - __main__ - Step 39769: {'lr': 0.0004238714628699443, 'samples': 7635648, 'steps': 39768, 'loss/train': 1.3166062831878662} 08/30/2021 20:21:33 - INFO - __main__ - Step 39770: {'lr': 0.00042386764972380164, 'samples': 7635840, 'steps': 39769, 'loss/train': 1.8102490901947021} 08/30/2021 20:21:33 - INFO - __main__ - Step 39771: {'lr': 0.00042386383649931693, 'samples': 7636032, 'steps': 39770, 'loss/train': 1.4819411039352417} 08/30/2021 20:21:33 - INFO - __main__ - Step 39772: {'lr': 0.00042386002319649184, 'samples': 7636224, 'steps': 39771, 'loss/train': 1.9187854528427124} 08/30/2021 20:21:34 - INFO - __main__ - Step 39773: {'lr': 0.0004238562098153281, 'samples': 7636416, 'steps': 39772, 'loss/train': 1.5359846353530884} 08/30/2021 20:21:34 - INFO - __main__ - Step 39774: {'lr': 0.0004238523963558275, 'samples': 7636608, 'steps': 39773, 'loss/train': 1.1927670240402222} 08/30/2021 20:21:35 - INFO - __main__ - Step 39775: {'lr': 0.0004238485828179917, 'samples': 7636800, 'steps': 39774, 'loss/train': 1.3483922481536865} 08/30/2021 20:21:36 - INFO - __main__ - Step 39776: {'lr': 0.00042384476920182234, 'samples': 7636992, 'steps': 39775, 'loss/train': 1.1310625076293945} 08/30/2021 20:21:37 - INFO - __main__ - Step 39777: {'lr': 0.0004238409555073212, 'samples': 7637184, 'steps': 39776, 'loss/train': 1.4612566232681274} 08/30/2021 20:21:37 - INFO - __main__ - Step 39778: {'lr': 0.00042383714173449007, 'samples': 7637376, 'steps': 39777, 'loss/train': 1.555152416229248} 08/30/2021 20:21:37 - INFO - __main__ - Step 39779: {'lr': 0.00042383332788333055, 'samples': 7637568, 'steps': 39778, 'loss/train': 1.5594398975372314} 08/30/2021 20:21:38 - INFO - __main__ - Step 39780: {'lr': 0.0004238295139538445, 'samples': 7637760, 'steps': 39779, 'loss/train': 1.8967844247817993} 08/30/2021 20:21:39 - INFO - __main__ - Step 39781: {'lr': 0.0004238256999460335, 'samples': 7637952, 'steps': 39780, 'loss/train': 1.8482410907745361} 08/30/2021 20:21:40 - INFO - __main__ - Step 39782: {'lr': 0.00042382188585989933, 'samples': 7638144, 'steps': 39781, 'loss/train': 1.0997345447540283} 08/30/2021 20:21:40 - INFO - __main__ - Step 39783: {'lr': 0.0004238180716954436, 'samples': 7638336, 'steps': 39782, 'loss/train': 1.8072947263717651} 08/30/2021 20:21:40 - INFO - __main__ - Step 39784: {'lr': 0.0004238142574526683, 'samples': 7638528, 'steps': 39783, 'loss/train': 1.4344013929367065} 08/30/2021 20:21:41 - INFO - __main__ - Step 39785: {'lr': 0.0004238104431315749, 'samples': 7638720, 'steps': 39784, 'loss/train': 1.0944627523422241} 08/30/2021 20:21:42 - INFO - __main__ - Step 39786: {'lr': 0.00042380662873216517, 'samples': 7638912, 'steps': 39785, 'loss/train': 1.6362626552581787} 08/30/2021 20:21:43 - INFO - __main__ - Step 39787: {'lr': 0.00042380281425444087, 'samples': 7639104, 'steps': 39786, 'loss/train': 1.4634677171707153} 08/30/2021 20:21:43 - INFO - __main__ - Step 39788: {'lr': 0.0004237989996984037, 'samples': 7639296, 'steps': 39787, 'loss/train': 1.2802988290786743} 08/30/2021 20:21:43 - INFO - __main__ - Step 39789: {'lr': 0.0004237951850640555, 'samples': 7639488, 'steps': 39788, 'loss/train': 1.3769564628601074} 08/30/2021 20:21:44 - INFO - __main__ - Step 39790: {'lr': 0.0004237913703513977, 'samples': 7639680, 'steps': 39789, 'loss/train': 1.6763055324554443} 08/30/2021 20:21:45 - INFO - __main__ - Step 39791: {'lr': 0.00042378755556043225, 'samples': 7639872, 'steps': 39790, 'loss/train': 1.154290795326233} 08/30/2021 20:21:46 - INFO - __main__ - Step 39792: {'lr': 0.0004237837406911608, 'samples': 7640064, 'steps': 39791, 'loss/train': 1.4609167575836182} 08/30/2021 20:21:46 - INFO - __main__ - Step 39793: {'lr': 0.00042377992574358514, 'samples': 7640256, 'steps': 39792, 'loss/train': 1.802790880203247} 08/30/2021 20:21:47 - INFO - __main__ - Step 39794: {'lr': 0.0004237761107177068, 'samples': 7640448, 'steps': 39793, 'loss/train': 1.6666299104690552} 08/30/2021 20:21:47 - INFO - __main__ - Step 39795: {'lr': 0.00042377229561352774, 'samples': 7640640, 'steps': 39794, 'loss/train': 1.34855055809021} 08/30/2021 20:21:47 - INFO - __main__ - Step 39796: {'lr': 0.00042376848043104953, 'samples': 7640832, 'steps': 39795, 'loss/train': 1.399302363395691} 08/30/2021 20:21:49 - INFO - __main__ - Step 39797: {'lr': 0.00042376466517027387, 'samples': 7641024, 'steps': 39796, 'loss/train': 0.7730812430381775} 08/30/2021 20:21:49 - INFO - __main__ - Step 39798: {'lr': 0.00042376084983120266, 'samples': 7641216, 'steps': 39797, 'loss/train': 1.2225711345672607} 08/30/2021 20:21:50 - INFO - __main__ - Step 39799: {'lr': 0.0004237570344138374, 'samples': 7641408, 'steps': 39798, 'loss/train': 1.5387535095214844} 08/30/2021 20:21:50 - INFO - __main__ - Step 39800: {'lr': 0.00042375321891818, 'samples': 7641600, 'steps': 39799, 'loss/train': 1.4773350954055786} 08/30/2021 20:21:50 - INFO - __main__ - Step 39801: {'lr': 0.00042374940334423194, 'samples': 7641792, 'steps': 39800, 'loss/train': 0.9736891984939575} 08/30/2021 20:21:52 - INFO - __main__ - Step 39802: {'lr': 0.00042374558769199517, 'samples': 7641984, 'steps': 39801, 'loss/train': 0.5339415669441223} 08/30/2021 20:21:53 - INFO - __main__ - Step 39803: {'lr': 0.0004237417719614713, 'samples': 7642176, 'steps': 39802, 'loss/train': 1.0176312923431396} 08/30/2021 20:21:53 - INFO - __main__ - Step 39804: {'lr': 0.000423737956152662, 'samples': 7642368, 'steps': 39803, 'loss/train': 1.7241501808166504} 08/30/2021 20:21:53 - INFO - __main__ - Step 39805: {'lr': 0.0004237341402655692, 'samples': 7642560, 'steps': 39804, 'loss/train': 1.385020136833191} 08/30/2021 20:21:54 - INFO - __main__ - Step 39806: {'lr': 0.00042373032430019443, 'samples': 7642752, 'steps': 39805, 'loss/train': 1.0439468622207642} 08/30/2021 20:21:54 - INFO - __main__ - Step 39807: {'lr': 0.00042372650825653937, 'samples': 7642944, 'steps': 39806, 'loss/train': 1.5732402801513672} 08/30/2021 20:21:56 - INFO - __main__ - Step 39808: {'lr': 0.0004237226921346059, 'samples': 7643136, 'steps': 39807, 'loss/train': 2.7936289310455322} 08/30/2021 20:21:57 - INFO - __main__ - Step 39809: {'lr': 0.0004237188759343956, 'samples': 7643328, 'steps': 39808, 'loss/train': 1.8445457220077515} 08/30/2021 20:21:57 - INFO - __main__ - Step 39810: {'lr': 0.0004237150596559103, 'samples': 7643520, 'steps': 39809, 'loss/train': 0.8576852083206177} 08/30/2021 20:21:57 - INFO - __main__ - Step 39811: {'lr': 0.00042371124329915167, 'samples': 7643712, 'steps': 39810, 'loss/train': 1.330367088317871} 08/30/2021 20:21:58 - INFO - __main__ - Step 39812: {'lr': 0.0004237074268641215, 'samples': 7643904, 'steps': 39811, 'loss/train': 1.4323655366897583} 08/30/2021 20:21:59 - INFO - __main__ - Step 39813: {'lr': 0.00042370361035082136, 'samples': 7644096, 'steps': 39812, 'loss/train': 1.3146483898162842} 08/30/2021 20:22:00 - INFO - __main__ - Step 39814: {'lr': 0.000423699793759253, 'samples': 7644288, 'steps': 39813, 'loss/train': 1.748504877090454} 08/30/2021 20:22:00 - INFO - __main__ - Step 39815: {'lr': 0.0004236959770894183, 'samples': 7644480, 'steps': 39814, 'loss/train': 1.4523926973342896} 08/30/2021 20:22:00 - INFO - __main__ - Step 39816: {'lr': 0.00042369216034131887, 'samples': 7644672, 'steps': 39815, 'loss/train': 1.234877347946167} 08/30/2021 20:22:01 - INFO - __main__ - Step 39817: {'lr': 0.0004236883435149564, 'samples': 7644864, 'steps': 39816, 'loss/train': 1.5407646894454956} 08/30/2021 20:22:01 - INFO - __main__ - Step 39818: {'lr': 0.0004236845266103327, 'samples': 7645056, 'steps': 39817, 'loss/train': 1.4343197345733643} 08/30/2021 20:22:02 - INFO - __main__ - Step 39819: {'lr': 0.00042368070962744937, 'samples': 7645248, 'steps': 39818, 'loss/train': 0.7413326501846313} 08/30/2021 20:22:03 - INFO - __main__ - Step 39820: {'lr': 0.0004236768925663082, 'samples': 7645440, 'steps': 39819, 'loss/train': 1.5835468769073486} 08/30/2021 20:22:03 - INFO - __main__ - Step 39821: {'lr': 0.0004236730754269109, 'samples': 7645632, 'steps': 39820, 'loss/train': 1.2382744550704956} 08/30/2021 20:22:04 - INFO - __main__ - Step 39822: {'lr': 0.00042366925820925915, 'samples': 7645824, 'steps': 39821, 'loss/train': 1.099984049797058} 08/30/2021 20:22:04 - INFO - __main__ - Step 39823: {'lr': 0.0004236654409133548, 'samples': 7646016, 'steps': 39822, 'loss/train': 0.7239627838134766} 08/30/2021 20:22:06 - INFO - __main__ - Step 39824: {'lr': 0.0004236616235391995, 'samples': 7646208, 'steps': 39823, 'loss/train': 1.9253596067428589} 08/30/2021 20:22:06 - INFO - __main__ - Step 39825: {'lr': 0.0004236578060867949, 'samples': 7646400, 'steps': 39824, 'loss/train': 1.6039097309112549} 08/30/2021 20:22:07 - INFO - __main__ - Step 39826: {'lr': 0.0004236539885561427, 'samples': 7646592, 'steps': 39825, 'loss/train': 0.11956195533275604} 08/30/2021 20:22:07 - INFO - __main__ - Step 39827: {'lr': 0.0004236501709472448, 'samples': 7646784, 'steps': 39826, 'loss/train': 1.5506343841552734} 08/30/2021 20:22:07 - INFO - __main__ - Step 39828: {'lr': 0.00042364635326010277, 'samples': 7646976, 'steps': 39827, 'loss/train': 1.3428919315338135} 08/30/2021 20:22:08 - INFO - __main__ - Step 39829: {'lr': 0.0004236425354947183, 'samples': 7647168, 'steps': 39828, 'loss/train': 1.362579345703125} 08/30/2021 20:22:09 - INFO - __main__ - Step 39830: {'lr': 0.0004236387176510933, 'samples': 7647360, 'steps': 39829, 'loss/train': 2.4064180850982666} 08/30/2021 20:22:10 - INFO - __main__ - Step 39831: {'lr': 0.00042363489972922937, 'samples': 7647552, 'steps': 39830, 'loss/train': 1.4314252138137817} 08/30/2021 20:22:10 - INFO - __main__ - Step 39832: {'lr': 0.00042363108172912824, 'samples': 7647744, 'steps': 39831, 'loss/train': 1.1759506464004517} 08/30/2021 20:22:10 - INFO - __main__ - Step 39833: {'lr': 0.0004236272636507915, 'samples': 7647936, 'steps': 39832, 'loss/train': 1.8201500177383423} 08/30/2021 20:22:11 - INFO - __main__ - Step 39834: {'lr': 0.0004236234454942211, 'samples': 7648128, 'steps': 39833, 'loss/train': 1.2150834798812866} 08/30/2021 20:22:12 - INFO - __main__ - Step 39835: {'lr': 0.0004236196272594186, 'samples': 7648320, 'steps': 39834, 'loss/train': 3.5438666343688965} 08/30/2021 20:22:13 - INFO - __main__ - Step 39836: {'lr': 0.00042361580894638586, 'samples': 7648512, 'steps': 39835, 'loss/train': 1.3479591608047485} 08/30/2021 20:22:13 - INFO - __main__ - Step 39837: {'lr': 0.0004236119905551244, 'samples': 7648704, 'steps': 39836, 'loss/train': 1.3892861604690552} 08/30/2021 20:22:13 - INFO - __main__ - Step 39838: {'lr': 0.0004236081720856362, 'samples': 7648896, 'steps': 39837, 'loss/train': 1.6087465286254883} 08/30/2021 20:22:14 - INFO - __main__ - Step 39839: {'lr': 0.0004236043535379227, 'samples': 7649088, 'steps': 39838, 'loss/train': 1.2033506631851196} 08/30/2021 20:22:15 - INFO - __main__ - Step 39840: {'lr': 0.0004236005349119858, 'samples': 7649280, 'steps': 39839, 'loss/train': 1.4677839279174805} 08/30/2021 20:22:16 - INFO - __main__ - Step 39841: {'lr': 0.0004235967162078272, 'samples': 7649472, 'steps': 39840, 'loss/train': 1.2253412008285522} 08/30/2021 20:22:16 - INFO - __main__ - Step 39842: {'lr': 0.0004235928974254486, 'samples': 7649664, 'steps': 39841, 'loss/train': 1.2615032196044922} 08/30/2021 20:22:16 - INFO - __main__ - Step 39843: {'lr': 0.00042358907856485166, 'samples': 7649856, 'steps': 39842, 'loss/train': 1.5576845407485962} 08/30/2021 20:22:17 - INFO - __main__ - Step 39844: {'lr': 0.0004235852596260382, 'samples': 7650048, 'steps': 39843, 'loss/train': 1.876056432723999} 08/30/2021 20:22:17 - INFO - __main__ - Step 39845: {'lr': 0.0004235814406090099, 'samples': 7650240, 'steps': 39844, 'loss/train': 1.249107003211975} 08/30/2021 20:22:19 - INFO - __main__ - Step 39846: {'lr': 0.0004235776215137686, 'samples': 7650432, 'steps': 39845, 'loss/train': 1.5645771026611328} 08/30/2021 20:22:19 - INFO - __main__ - Step 39847: {'lr': 0.0004235738023403157, 'samples': 7650624, 'steps': 39846, 'loss/train': 1.2951265573501587} 08/30/2021 20:22:20 - INFO - __main__ - Step 39848: {'lr': 0.00042356998308865323, 'samples': 7650816, 'steps': 39847, 'loss/train': 1.1508517265319824} 08/30/2021 20:22:20 - INFO - __main__ - Step 39849: {'lr': 0.00042356616375878274, 'samples': 7651008, 'steps': 39848, 'loss/train': 1.85157310962677} 08/30/2021 20:22:20 - INFO - __main__ - Step 39850: {'lr': 0.00042356234435070604, 'samples': 7651200, 'steps': 39849, 'loss/train': 3.2641148567199707} 08/30/2021 20:22:22 - INFO - __main__ - Step 39851: {'lr': 0.0004235585248644249, 'samples': 7651392, 'steps': 39850, 'loss/train': 1.4653106927871704} 08/30/2021 20:22:22 - INFO - __main__ - Step 39852: {'lr': 0.0004235547052999409, 'samples': 7651584, 'steps': 39851, 'loss/train': 0.9225090146064758} 08/30/2021 20:22:23 - INFO - __main__ - Step 39853: {'lr': 0.00042355088565725584, 'samples': 7651776, 'steps': 39852, 'loss/train': 1.5941897630691528} 08/30/2021 20:22:23 - INFO - __main__ - Step 39854: {'lr': 0.0004235470659363714, 'samples': 7651968, 'steps': 39853, 'loss/train': 1.9329582452774048} 08/30/2021 20:22:23 - INFO - __main__ - Step 39855: {'lr': 0.0004235432461372894, 'samples': 7652160, 'steps': 39854, 'loss/train': 1.5335501432418823} 08/30/2021 20:22:26 - INFO - __main__ - Step 39856: {'lr': 0.0004235394262600114, 'samples': 7652352, 'steps': 39855, 'loss/train': 2.1897225379943848} 08/30/2021 20:22:26 - INFO - __main__ - Step 39857: {'lr': 0.0004235356063045393, 'samples': 7652544, 'steps': 39856, 'loss/train': 1.5117830038070679} 08/30/2021 20:22:27 - INFO - __main__ - Step 39858: {'lr': 0.0004235317862708747, 'samples': 7652736, 'steps': 39857, 'loss/train': 1.3249950408935547} 08/30/2021 20:22:27 - INFO - __main__ - Step 39859: {'lr': 0.00042352796615901937, 'samples': 7652928, 'steps': 39858, 'loss/train': 2.392627239227295} 08/30/2021 20:22:27 - INFO - __main__ - Step 39860: {'lr': 0.000423524145968975, 'samples': 7653120, 'steps': 39859, 'loss/train': 2.405303716659546} 08/30/2021 20:22:28 - INFO - __main__ - Step 39861: {'lr': 0.00042352032570074327, 'samples': 7653312, 'steps': 39860, 'loss/train': 3.2477967739105225} 08/30/2021 20:22:28 - INFO - __main__ - Step 39862: {'lr': 0.00042351650535432607, 'samples': 7653504, 'steps': 39861, 'loss/train': 0.34251442551612854} 08/30/2021 20:22:28 - INFO - __main__ - Step 39863: {'lr': 0.00042351268492972494, 'samples': 7653696, 'steps': 39862, 'loss/train': 0.23484422266483307} 08/30/2021 20:22:29 - INFO - __main__ - Step 39864: {'lr': 0.0004235088644269417, 'samples': 7653888, 'steps': 39863, 'loss/train': 1.8007278442382812} 08/30/2021 20:22:30 - INFO - __main__ - Step 39865: {'lr': 0.00042350504384597803, 'samples': 7654080, 'steps': 39864, 'loss/train': 6.510688304901123} 08/30/2021 20:22:30 - INFO - __main__ - Step 39866: {'lr': 0.0004235012231868357, 'samples': 7654272, 'steps': 39865, 'loss/train': 1.8088299036026} 08/30/2021 20:22:31 - INFO - __main__ - Step 39867: {'lr': 0.0004234974024495163, 'samples': 7654464, 'steps': 39866, 'loss/train': 2.0929627418518066} 08/30/2021 20:22:31 - INFO - __main__ - Step 39868: {'lr': 0.00042349358163402175, 'samples': 7654656, 'steps': 39867, 'loss/train': 1.964975118637085} 08/30/2021 20:22:32 - INFO - __main__ - Step 39869: {'lr': 0.0004234897607403536, 'samples': 7654848, 'steps': 39868, 'loss/train': 1.8140032291412354} 08/30/2021 20:22:33 - INFO - __main__ - Step 39870: {'lr': 0.0004234859397685137, 'samples': 7655040, 'steps': 39869, 'loss/train': 0.901826024055481} 08/30/2021 20:22:34 - INFO - __main__ - Step 39871: {'lr': 0.0004234821187185036, 'samples': 7655232, 'steps': 39870, 'loss/train': 1.8299572467803955} 08/30/2021 20:22:34 - INFO - __main__ - Step 39872: {'lr': 0.0004234782975903253, 'samples': 7655424, 'steps': 39871, 'loss/train': 1.7122297286987305} 08/30/2021 20:22:35 - INFO - __main__ - Step 39873: {'lr': 0.00042347447638398024, 'samples': 7655616, 'steps': 39872, 'loss/train': 1.5269038677215576} 08/30/2021 20:22:35 - INFO - __main__ - Step 39874: {'lr': 0.00042347065509947023, 'samples': 7655808, 'steps': 39873, 'loss/train': 1.7298256158828735} 08/30/2021 20:22:36 - INFO - __main__ - Step 39875: {'lr': 0.0004234668337367971, 'samples': 7656000, 'steps': 39874, 'loss/train': 2.083935260772705} 08/30/2021 20:22:37 - INFO - __main__ - Step 39876: {'lr': 0.0004234630122959625, 'samples': 7656192, 'steps': 39875, 'loss/train': 1.4115592241287231} 08/30/2021 20:22:37 - INFO - __main__ - Step 39877: {'lr': 0.0004234591907769681, 'samples': 7656384, 'steps': 39876, 'loss/train': 2.0594301223754883} 08/30/2021 20:22:38 - INFO - __main__ - Step 39878: {'lr': 0.0004234553691798156, 'samples': 7656576, 'steps': 39877, 'loss/train': 2.1799516677856445} 08/30/2021 20:22:38 - INFO - __main__ - Step 39879: {'lr': 0.000423451547504507, 'samples': 7656768, 'steps': 39878, 'loss/train': 1.482926845550537} 08/30/2021 20:22:39 - INFO - __main__ - Step 39880: {'lr': 0.0004234477257510436, 'samples': 7656960, 'steps': 39879, 'loss/train': 1.8995473384857178} 08/30/2021 20:22:40 - INFO - __main__ - Step 39881: {'lr': 0.00042344390391942745, 'samples': 7657152, 'steps': 39880, 'loss/train': 0.5500131249427795} 08/30/2021 20:22:40 - INFO - __main__ - Step 39882: {'lr': 0.0004234400820096601, 'samples': 7657344, 'steps': 39881, 'loss/train': 1.4850785732269287} 08/30/2021 20:22:41 - INFO - __main__ - Step 39883: {'lr': 0.0004234362600217433, 'samples': 7657536, 'steps': 39882, 'loss/train': 1.2737517356872559} 08/30/2021 20:22:41 - INFO - __main__ - Step 39884: {'lr': 0.0004234324379556789, 'samples': 7657728, 'steps': 39883, 'loss/train': 2.354860305786133} 08/30/2021 20:22:42 - INFO - __main__ - Step 39885: {'lr': 0.0004234286158114684, 'samples': 7657920, 'steps': 39884, 'loss/train': 1.7381205558776855} 08/30/2021 20:22:43 - INFO - __main__ - Step 39886: {'lr': 0.0004234247935891137, 'samples': 7658112, 'steps': 39885, 'loss/train': 1.4401222467422485} 08/30/2021 20:22:43 - INFO - __main__ - Step 39887: {'lr': 0.00042342097128861647, 'samples': 7658304, 'steps': 39886, 'loss/train': 1.9009616374969482} 08/30/2021 20:22:44 - INFO - __main__ - Step 39888: {'lr': 0.0004234171489099784, 'samples': 7658496, 'steps': 39887, 'loss/train': 1.29734206199646} 08/30/2021 20:22:44 - INFO - __main__ - Step 39889: {'lr': 0.00042341332645320126, 'samples': 7658688, 'steps': 39888, 'loss/train': 2.1100194454193115} 08/30/2021 20:22:46 - INFO - __main__ - Step 39890: {'lr': 0.0004234095039182867, 'samples': 7658880, 'steps': 39889, 'loss/train': 2.002281427383423} 08/30/2021 20:22:46 - INFO - __main__ - Step 39891: {'lr': 0.00042340568130523653, 'samples': 7659072, 'steps': 39890, 'loss/train': 1.6675454378128052} 08/30/2021 20:22:46 - INFO - __main__ - Step 39892: {'lr': 0.0004234018586140525, 'samples': 7659264, 'steps': 39891, 'loss/train': 1.6324392557144165} 08/30/2021 20:22:47 - INFO - __main__ - Step 39893: {'lr': 0.00042339803584473626, 'samples': 7659456, 'steps': 39892, 'loss/train': 1.6695985794067383} 08/30/2021 20:22:47 - INFO - __main__ - Step 39894: {'lr': 0.0004233942129972894, 'samples': 7659648, 'steps': 39893, 'loss/train': 0.17922604084014893} 08/30/2021 20:22:49 - INFO - __main__ - Step 39895: {'lr': 0.00042339039007171386, 'samples': 7659840, 'steps': 39894, 'loss/train': 1.1587668657302856} 08/30/2021 20:22:49 - INFO - __main__ - Step 39896: {'lr': 0.00042338656706801135, 'samples': 7660032, 'steps': 39895, 'loss/train': 1.8000980615615845} 08/30/2021 20:22:49 - INFO - __main__ - Step 39897: {'lr': 0.00042338274398618346, 'samples': 7660224, 'steps': 39896, 'loss/train': 1.6434587240219116} 08/30/2021 20:22:50 - INFO - __main__ - Step 39898: {'lr': 0.000423378920826232, 'samples': 7660416, 'steps': 39897, 'loss/train': 1.6689329147338867} 08/30/2021 20:22:50 - INFO - __main__ - Step 39899: {'lr': 0.0004233750975881587, 'samples': 7660608, 'steps': 39898, 'loss/train': 1.5078701972961426} 08/30/2021 20:22:50 - INFO - __main__ - Step 39900: {'lr': 0.0004233712742719652, 'samples': 7660800, 'steps': 39899, 'loss/train': 1.9081040620803833} 08/30/2021 20:22:52 - INFO - __main__ - Step 39901: {'lr': 0.0004233674508776533, 'samples': 7660992, 'steps': 39900, 'loss/train': 2.3875625133514404} 08/30/2021 20:22:52 - INFO - __main__ - Step 39902: {'lr': 0.00042336362740522473, 'samples': 7661184, 'steps': 39901, 'loss/train': 1.2209930419921875} 08/30/2021 20:22:53 - INFO - __main__ - Step 39903: {'lr': 0.0004233598038546812, 'samples': 7661376, 'steps': 39902, 'loss/train': 1.5918796062469482} 08/30/2021 20:22:53 - INFO - __main__ - Step 39904: {'lr': 0.0004233559802260244, 'samples': 7661568, 'steps': 39903, 'loss/train': 1.8165403604507446} 08/30/2021 20:22:53 - INFO - __main__ - Step 39905: {'lr': 0.000423352156519256, 'samples': 7661760, 'steps': 39904, 'loss/train': 1.0334722995758057} 08/30/2021 20:22:55 - INFO - __main__ - Step 39906: {'lr': 0.0004233483327343779, 'samples': 7661952, 'steps': 39905, 'loss/train': 1.5503871440887451} 08/30/2021 20:22:55 - INFO - __main__ - Step 39907: {'lr': 0.0004233445088713916, 'samples': 7662144, 'steps': 39906, 'loss/train': 1.7237764596939087} 08/30/2021 20:22:56 - INFO - __main__ - Step 39908: {'lr': 0.000423340684930299, 'samples': 7662336, 'steps': 39907, 'loss/train': 1.325069785118103} 08/30/2021 20:22:56 - INFO - __main__ - Step 39909: {'lr': 0.0004233368609111018, 'samples': 7662528, 'steps': 39908, 'loss/train': 1.6507238149642944} 08/30/2021 20:22:56 - INFO - __main__ - Step 39910: {'lr': 0.00042333303681380165, 'samples': 7662720, 'steps': 39909, 'loss/train': 1.624729871749878} 08/30/2021 20:22:58 - INFO - __main__ - Step 39911: {'lr': 0.0004233292126384003, 'samples': 7662912, 'steps': 39910, 'loss/train': 1.3100122213363647} 08/30/2021 20:22:58 - INFO - __main__ - Step 39912: {'lr': 0.00042332538838489955, 'samples': 7663104, 'steps': 39911, 'loss/train': 0.9684287905693054} 08/30/2021 20:22:58 - INFO - __main__ - Step 39913: {'lr': 0.0004233215640533009, 'samples': 7663296, 'steps': 39912, 'loss/train': 2.1299078464508057} 08/30/2021 20:22:59 - INFO - __main__ - Step 39914: {'lr': 0.0004233177396436064, 'samples': 7663488, 'steps': 39913, 'loss/train': 1.3713035583496094} 08/30/2021 20:22:59 - INFO - __main__ - Step 39915: {'lr': 0.00042331391515581753, 'samples': 7663680, 'steps': 39914, 'loss/train': 1.481816053390503} 08/30/2021 20:23:01 - INFO - __main__ - Step 39916: {'lr': 0.00042331009058993604, 'samples': 7663872, 'steps': 39915, 'loss/train': 0.8788862228393555} 08/30/2021 20:23:01 - INFO - __main__ - Step 39917: {'lr': 0.00042330626594596374, 'samples': 7664064, 'steps': 39916, 'loss/train': 1.7196238040924072} 08/30/2021 20:23:01 - INFO - __main__ - Step 39918: {'lr': 0.00042330244122390227, 'samples': 7664256, 'steps': 39917, 'loss/train': 1.3474643230438232} 08/30/2021 20:23:02 - INFO - __main__ - Step 39919: {'lr': 0.00042329861642375347, 'samples': 7664448, 'steps': 39918, 'loss/train': 1.5671926736831665} 08/30/2021 20:23:02 - INFO - __main__ - Step 39920: {'lr': 0.00042329479154551897, 'samples': 7664640, 'steps': 39919, 'loss/train': 1.7457983493804932} 08/30/2021 20:23:05 - INFO - __main__ - Step 39921: {'lr': 0.0004232909665892005, 'samples': 7664832, 'steps': 39920, 'loss/train': 1.34580659866333} 08/30/2021 20:23:05 - INFO - __main__ - Step 39922: {'lr': 0.00042328714155479973, 'samples': 7665024, 'steps': 39921, 'loss/train': 1.4555563926696777} 08/30/2021 20:23:05 - INFO - __main__ - Step 39923: {'lr': 0.0004232833164423185, 'samples': 7665216, 'steps': 39922, 'loss/train': 1.605604887008667} 08/30/2021 20:23:06 - INFO - __main__ - Step 39924: {'lr': 0.00042327949125175844, 'samples': 7665408, 'steps': 39923, 'loss/train': 1.1793478727340698} 08/30/2021 20:23:06 - INFO - __main__ - Step 39925: {'lr': 0.0004232756659831214, 'samples': 7665600, 'steps': 39924, 'loss/train': 1.2907603979110718} 08/30/2021 20:23:06 - INFO - __main__ - Step 39926: {'lr': 0.000423271840636409, 'samples': 7665792, 'steps': 39925, 'loss/train': 1.2843084335327148} 08/30/2021 20:23:08 - INFO - __main__ - Step 39927: {'lr': 0.00042326801521162295, 'samples': 7665984, 'steps': 39926, 'loss/train': 1.4443492889404297} 08/30/2021 20:23:08 - INFO - __main__ - Step 39928: {'lr': 0.000423264189708765, 'samples': 7666176, 'steps': 39927, 'loss/train': 1.5435090065002441} 08/30/2021 20:23:09 - INFO - __main__ - Step 39929: {'lr': 0.0004232603641278369, 'samples': 7666368, 'steps': 39928, 'loss/train': 1.5917209386825562} 08/30/2021 20:23:09 - INFO - __main__ - Step 39930: {'lr': 0.00042325653846884037, 'samples': 7666560, 'steps': 39929, 'loss/train': 1.4119353294372559} 08/30/2021 20:23:09 - INFO - __main__ - Step 39931: {'lr': 0.00042325271273177707, 'samples': 7666752, 'steps': 39930, 'loss/train': 0.9169667959213257} 08/30/2021 20:23:11 - INFO - __main__ - Step 39932: {'lr': 0.0004232488869166488, 'samples': 7666944, 'steps': 39931, 'loss/train': 1.5057662725448608} 08/30/2021 20:23:11 - INFO - __main__ - Step 39933: {'lr': 0.0004232450610234573, 'samples': 7667136, 'steps': 39932, 'loss/train': 1.2545952796936035} 08/30/2021 20:23:12 - INFO - __main__ - Step 39934: {'lr': 0.00042324123505220414, 'samples': 7667328, 'steps': 39933, 'loss/train': 1.3745766878128052} 08/30/2021 20:23:12 - INFO - __main__ - Step 39935: {'lr': 0.0004232374090028912, 'samples': 7667520, 'steps': 39934, 'loss/train': 1.1821707487106323} 08/30/2021 20:23:12 - INFO - __main__ - Step 39936: {'lr': 0.00042323358287552017, 'samples': 7667712, 'steps': 39935, 'loss/train': 2.2497944831848145} 08/30/2021 20:23:14 - INFO - __main__ - Step 39937: {'lr': 0.0004232297566700928, 'samples': 7667904, 'steps': 39936, 'loss/train': 1.1231679916381836} 08/30/2021 20:23:15 - INFO - __main__ - Step 39938: {'lr': 0.00042322593038661074, 'samples': 7668096, 'steps': 39937, 'loss/train': 1.443115472793579} 08/30/2021 20:23:15 - INFO - __main__ - Step 39939: {'lr': 0.0004232221040250758, 'samples': 7668288, 'steps': 39938, 'loss/train': 1.262053370475769} 08/30/2021 20:23:15 - INFO - __main__ - Step 39940: {'lr': 0.00042321827758548953, 'samples': 7668480, 'steps': 39939, 'loss/train': 1.3323216438293457} 08/30/2021 20:23:16 - INFO - __main__ - Step 39941: {'lr': 0.00042321445106785385, 'samples': 7668672, 'steps': 39940, 'loss/train': 1.4669933319091797} 08/30/2021 20:23:17 - INFO - __main__ - Step 39942: {'lr': 0.0004232106244721704, 'samples': 7668864, 'steps': 39941, 'loss/train': 1.7182587385177612} 08/30/2021 20:23:17 - INFO - __main__ - Step 39943: {'lr': 0.0004232067977984409, 'samples': 7669056, 'steps': 39942, 'loss/train': 1.418216586112976} 08/30/2021 20:23:18 - INFO - __main__ - Step 39944: {'lr': 0.0004232029710466671, 'samples': 7669248, 'steps': 39943, 'loss/train': 1.1714415550231934} 08/30/2021 20:23:18 - INFO - __main__ - Step 39945: {'lr': 0.00042319914421685067, 'samples': 7669440, 'steps': 39944, 'loss/train': 2.1570920944213867} 08/30/2021 20:23:19 - INFO - __main__ - Step 39946: {'lr': 0.0004231953173089935, 'samples': 7669632, 'steps': 39945, 'loss/train': 1.5293985605239868} 08/30/2021 20:23:20 - INFO - __main__ - Step 39947: {'lr': 0.00042319149032309713, 'samples': 7669824, 'steps': 39946, 'loss/train': 1.2032697200775146} 08/30/2021 20:23:20 - INFO - __main__ - Step 39948: {'lr': 0.00042318766325916336, 'samples': 7670016, 'steps': 39947, 'loss/train': 1.647952914237976} 08/30/2021 20:23:21 - INFO - __main__ - Step 39949: {'lr': 0.00042318383611719386, 'samples': 7670208, 'steps': 39948, 'loss/train': 1.2331401109695435} 08/30/2021 20:23:21 - INFO - __main__ - Step 39950: {'lr': 0.00042318000889719044, 'samples': 7670400, 'steps': 39949, 'loss/train': 0.0455939918756485} 08/30/2021 20:23:22 - INFO - __main__ - Step 39951: {'lr': 0.0004231761815991547, 'samples': 7670592, 'steps': 39950, 'loss/train': 1.5954842567443848} 08/30/2021 20:23:22 - INFO - __main__ - Step 39952: {'lr': 0.0004231723542230885, 'samples': 7670784, 'steps': 39951, 'loss/train': 1.6678485870361328} 08/30/2021 20:23:23 - INFO - __main__ - Step 39953: {'lr': 0.0004231685267689935, 'samples': 7670976, 'steps': 39952, 'loss/train': 1.9941524267196655} 08/30/2021 20:23:24 - INFO - __main__ - Step 39954: {'lr': 0.0004231646992368715, 'samples': 7671168, 'steps': 39953, 'loss/train': 1.7930129766464233} 08/30/2021 20:23:24 - INFO - __main__ - Step 39955: {'lr': 0.00042316087162672415, 'samples': 7671360, 'steps': 39954, 'loss/train': 1.3292405605316162} 08/30/2021 20:23:24 - INFO - __main__ - Step 39956: {'lr': 0.0004231570439385531, 'samples': 7671552, 'steps': 39955, 'loss/train': 1.0995622873306274} 08/30/2021 20:23:25 - INFO - __main__ - Step 39957: {'lr': 0.0004231532161723602, 'samples': 7671744, 'steps': 39956, 'loss/train': 1.0264662504196167} 08/30/2021 20:23:26 - INFO - __main__ - Step 39958: {'lr': 0.0004231493883281471, 'samples': 7671936, 'steps': 39957, 'loss/train': 2.15161395072937} 08/30/2021 20:23:27 - INFO - __main__ - Step 39959: {'lr': 0.00042314556040591567, 'samples': 7672128, 'steps': 39958, 'loss/train': 2.17378568649292} 08/30/2021 20:23:27 - INFO - __main__ - Step 39960: {'lr': 0.0004231417324056674, 'samples': 7672320, 'steps': 39959, 'loss/train': 1.5137709379196167} 08/30/2021 20:23:27 - INFO - __main__ - Step 39961: {'lr': 0.00042313790432740416, 'samples': 7672512, 'steps': 39960, 'loss/train': 1.715969204902649} 08/30/2021 20:23:28 - INFO - __main__ - Step 39962: {'lr': 0.00042313407617112765, 'samples': 7672704, 'steps': 39961, 'loss/train': 1.2451519966125488} 08/30/2021 20:23:29 - INFO - __main__ - Step 39963: {'lr': 0.00042313024793683965, 'samples': 7672896, 'steps': 39962, 'loss/train': 1.930191159248352} 08/30/2021 20:23:30 - INFO - __main__ - Step 39964: {'lr': 0.0004231264196245418, 'samples': 7673088, 'steps': 39963, 'loss/train': 1.4040091037750244} 08/30/2021 20:23:30 - INFO - __main__ - Step 39965: {'lr': 0.00042312259123423584, 'samples': 7673280, 'steps': 39964, 'loss/train': 1.5934674739837646} 08/30/2021 20:23:30 - INFO - __main__ - Step 39966: {'lr': 0.00042311876276592355, 'samples': 7673472, 'steps': 39965, 'loss/train': 1.616688847541809} 08/30/2021 20:23:31 - INFO - __main__ - Step 39967: {'lr': 0.00042311493421960656, 'samples': 7673664, 'steps': 39966, 'loss/train': 0.9064227938652039} 08/30/2021 20:23:32 - INFO - __main__ - Step 39968: {'lr': 0.0004231111055952867, 'samples': 7673856, 'steps': 39967, 'loss/train': 1.3322641849517822} 08/30/2021 20:23:33 - INFO - __main__ - Step 39969: {'lr': 0.00042310727689296563, 'samples': 7674048, 'steps': 39968, 'loss/train': 1.5939640998840332} 08/30/2021 20:23:33 - INFO - __main__ - Step 39970: {'lr': 0.0004231034481126451, 'samples': 7674240, 'steps': 39969, 'loss/train': 1.2966455221176147} 08/30/2021 20:23:33 - INFO - __main__ - Step 39971: {'lr': 0.0004230996192543268, 'samples': 7674432, 'steps': 39970, 'loss/train': 0.8900102376937866} 08/30/2021 20:23:34 - INFO - __main__ - Step 39972: {'lr': 0.0004230957903180125, 'samples': 7674624, 'steps': 39971, 'loss/train': 1.0530837774276733} 08/30/2021 20:23:36 - INFO - __main__ - Step 39973: {'lr': 0.00042309196130370396, 'samples': 7674816, 'steps': 39972, 'loss/train': 2.0230767726898193} 08/30/2021 20:23:37 - INFO - __main__ - Step 39974: {'lr': 0.00042308813221140275, 'samples': 7675008, 'steps': 39973, 'loss/train': 1.1553943157196045} 08/30/2021 20:23:37 - INFO - __main__ - Step 39975: {'lr': 0.00042308430304111076, 'samples': 7675200, 'steps': 39974, 'loss/train': 0.8316280245780945} 08/30/2021 20:23:37 - INFO - __main__ - Step 39976: {'lr': 0.00042308047379282967, 'samples': 7675392, 'steps': 39975, 'loss/train': 1.8400486707687378} 08/30/2021 20:23:38 - INFO - __main__ - Step 39977: {'lr': 0.00042307664446656116, 'samples': 7675584, 'steps': 39976, 'loss/train': 1.4745255708694458} 08/30/2021 20:23:38 - INFO - __main__ - Step 39978: {'lr': 0.000423072815062307, 'samples': 7675776, 'steps': 39977, 'loss/train': 1.0939977169036865} 08/30/2021 20:23:39 - INFO - __main__ - Step 39979: {'lr': 0.0004230689855800689, 'samples': 7675968, 'steps': 39978, 'loss/train': 1.5234830379486084} 08/30/2021 20:23:40 - INFO - __main__ - Step 39980: {'lr': 0.0004230651560198486, 'samples': 7676160, 'steps': 39979, 'loss/train': 1.273972988128662} 08/30/2021 20:23:40 - INFO - __main__ - Step 39981: {'lr': 0.0004230613263816478, 'samples': 7676352, 'steps': 39980, 'loss/train': 1.3743761777877808} 08/30/2021 20:23:40 - INFO - __main__ - Step 39982: {'lr': 0.0004230574966654682, 'samples': 7676544, 'steps': 39981, 'loss/train': 1.2279105186462402} 08/30/2021 20:23:41 - INFO - __main__ - Step 39983: {'lr': 0.0004230536668713116, 'samples': 7676736, 'steps': 39982, 'loss/train': 1.8766906261444092} 08/30/2021 20:23:42 - INFO - __main__ - Step 39984: {'lr': 0.00042304983699917965, 'samples': 7676928, 'steps': 39983, 'loss/train': 1.9027396440505981} 08/30/2021 20:23:43 - INFO - __main__ - Step 39985: {'lr': 0.00042304600704907416, 'samples': 7677120, 'steps': 39984, 'loss/train': 1.3698922395706177} 08/30/2021 20:23:43 - INFO - __main__ - Step 39986: {'lr': 0.0004230421770209968, 'samples': 7677312, 'steps': 39985, 'loss/train': 0.8721058964729309} 08/30/2021 20:23:43 - INFO - __main__ - Step 39987: {'lr': 0.0004230383469149493, 'samples': 7677504, 'steps': 39986, 'loss/train': 1.796926498413086} 08/30/2021 20:23:44 - INFO - __main__ - Step 39988: {'lr': 0.0004230345167309334, 'samples': 7677696, 'steps': 39987, 'loss/train': 2.138378381729126} 08/30/2021 20:23:45 - INFO - __main__ - Step 39989: {'lr': 0.00042303068646895077, 'samples': 7677888, 'steps': 39988, 'loss/train': 1.626409649848938} 08/30/2021 20:23:46 - INFO - __main__ - Step 39990: {'lr': 0.0004230268561290032, 'samples': 7678080, 'steps': 39989, 'loss/train': 1.6420769691467285} 08/30/2021 20:23:46 - INFO - __main__ - Step 39991: {'lr': 0.0004230230257110924, 'samples': 7678272, 'steps': 39990, 'loss/train': 1.2929669618606567} 08/30/2021 20:23:46 - INFO - __main__ - Step 39992: {'lr': 0.00042301919521522014, 'samples': 7678464, 'steps': 39991, 'loss/train': 1.5793284177780151} 08/30/2021 20:23:47 - INFO - __main__ - Step 39993: {'lr': 0.0004230153646413881, 'samples': 7678656, 'steps': 39992, 'loss/train': 1.4071989059448242} 08/30/2021 20:23:48 - INFO - __main__ - Step 39994: {'lr': 0.000423011533989598, 'samples': 7678848, 'steps': 39993, 'loss/train': 1.5328775644302368} 08/30/2021 20:23:49 - INFO - __main__ - Step 39995: {'lr': 0.0004230077032598515, 'samples': 7679040, 'steps': 39994, 'loss/train': 1.4727871417999268} 08/30/2021 20:23:49 - INFO - __main__ - Step 39996: {'lr': 0.00042300387245215043, 'samples': 7679232, 'steps': 39995, 'loss/train': 1.583439826965332} 08/30/2021 20:23:49 - INFO - __main__ - Step 39997: {'lr': 0.00042300004156649654, 'samples': 7679424, 'steps': 39996, 'loss/train': 1.5471478700637817} 08/30/2021 20:23:50 - INFO - __main__ - Step 39998: {'lr': 0.0004229962106028914, 'samples': 7679616, 'steps': 39997, 'loss/train': 1.212770700454712} 08/30/2021 20:23:52 - INFO - __main__ - Step 39999: {'lr': 0.0004229923795613369, 'samples': 7679808, 'steps': 39998, 'loss/train': 1.3915947675704956} 08/30/2021 20:23:52 - INFO - __main__ - Step 40000: {'lr': 0.00042298854844183476, 'samples': 7680000, 'steps': 39999, 'loss/train': 1.4365646839141846} 08/30/2021 20:23:52 - INFO - __main__ - Step 40001: {'lr': 0.0004229847172443866, 'samples': 7680192, 'steps': 40000, 'loss/train': 1.7908278703689575} 08/30/2021 20:23:53 - INFO - __main__ - Step 40002: {'lr': 0.0004229808859689941, 'samples': 7680384, 'steps': 40001, 'loss/train': 1.0729361772537231} 08/30/2021 20:23:53 - INFO - __main__ - Step 40003: {'lr': 0.0004229770546156592, 'samples': 7680576, 'steps': 40002, 'loss/train': 0.7916885614395142} 08/30/2021 20:23:53 - INFO - __main__ - Step 40004: {'lr': 0.00042297322318438345, 'samples': 7680768, 'steps': 40003, 'loss/train': 1.9215587377548218} 08/30/2021 20:23:55 - INFO - __main__ - Step 40005: {'lr': 0.0004229693916751687, 'samples': 7680960, 'steps': 40004, 'loss/train': 1.7415010929107666} 08/30/2021 20:23:56 - INFO - __main__ - Step 40006: {'lr': 0.00042296556008801663, 'samples': 7681152, 'steps': 40005, 'loss/train': 1.1243678331375122} 08/30/2021 20:23:56 - INFO - __main__ - Step 40007: {'lr': 0.0004229617284229289, 'samples': 7681344, 'steps': 40006, 'loss/train': 1.5198845863342285} 08/30/2021 20:23:56 - INFO - __main__ - Step 40008: {'lr': 0.00042295789667990726, 'samples': 7681536, 'steps': 40007, 'loss/train': 0.33052346110343933} 08/30/2021 20:23:57 - INFO - __main__ - Step 40009: {'lr': 0.00042295406485895346, 'samples': 7681728, 'steps': 40008, 'loss/train': 1.6835016012191772} 08/30/2021 20:23:58 - INFO - __main__ - Step 40010: {'lr': 0.0004229502329600692, 'samples': 7681920, 'steps': 40009, 'loss/train': 1.5930639505386353} 08/30/2021 20:23:59 - INFO - __main__ - Step 40011: {'lr': 0.0004229464009832563, 'samples': 7682112, 'steps': 40010, 'loss/train': 0.7433944344520569} 08/30/2021 20:23:59 - INFO - __main__ - Step 40012: {'lr': 0.0004229425689285163, 'samples': 7682304, 'steps': 40011, 'loss/train': 1.4278309345245361} 08/30/2021 20:23:59 - INFO - __main__ - Step 40013: {'lr': 0.00042293873679585125, 'samples': 7682496, 'steps': 40012, 'loss/train': 1.2927014827728271} 08/30/2021 20:24:00 - INFO - __main__ - Step 40014: {'lr': 0.00042293490458526257, 'samples': 7682688, 'steps': 40013, 'loss/train': 1.5832417011260986} 08/30/2021 20:24:02 - INFO - __main__ - Step 40015: {'lr': 0.0004229310722967521, 'samples': 7682880, 'steps': 40014, 'loss/train': 1.4748404026031494} 08/30/2021 20:24:02 - INFO - __main__ - Step 40016: {'lr': 0.00042292723993032157, 'samples': 7683072, 'steps': 40015, 'loss/train': 1.4790807962417603} 08/30/2021 20:24:03 - INFO - __main__ - Step 40017: {'lr': 0.0004229234074859726, 'samples': 7683264, 'steps': 40016, 'loss/train': 1.6112967729568481} 08/30/2021 20:24:03 - INFO - __main__ - Step 40018: {'lr': 0.00042291957496370713, 'samples': 7683456, 'steps': 40017, 'loss/train': 0.19286830723285675} 08/30/2021 20:24:03 - INFO - __main__ - Step 40019: {'lr': 0.0004229157423635267, 'samples': 7683648, 'steps': 40018, 'loss/train': 1.9733043909072876} 08/30/2021 20:24:05 - INFO - __main__ - Step 40020: {'lr': 0.00042291190968543315, 'samples': 7683840, 'steps': 40019, 'loss/train': 1.6683762073516846} 08/30/2021 20:24:06 - INFO - __main__ - Step 40021: {'lr': 0.0004229080769294281, 'samples': 7684032, 'steps': 40020, 'loss/train': 1.3969764709472656} 08/30/2021 20:24:06 - INFO - __main__ - Step 40022: {'lr': 0.00042290424409551343, 'samples': 7684224, 'steps': 40021, 'loss/train': 0.3898797333240509} 08/30/2021 20:24:06 - INFO - __main__ - Step 40023: {'lr': 0.0004229004111836907, 'samples': 7684416, 'steps': 40022, 'loss/train': 0.12853480875492096} 08/30/2021 20:24:07 - INFO - __main__ - Step 40024: {'lr': 0.0004228965781939617, 'samples': 7684608, 'steps': 40023, 'loss/train': 1.3174782991409302} 08/30/2021 20:24:07 - INFO - __main__ - Step 40025: {'lr': 0.00042289274512632817, 'samples': 7684800, 'steps': 40024, 'loss/train': 1.428648829460144} 08/30/2021 20:24:09 - INFO - __main__ - Step 40026: {'lr': 0.00042288891198079194, 'samples': 7684992, 'steps': 40025, 'loss/train': 1.0943942070007324} 08/30/2021 20:24:10 - INFO - __main__ - Step 40027: {'lr': 0.00042288507875735455, 'samples': 7685184, 'steps': 40026, 'loss/train': 0.9271484613418579} 08/30/2021 20:24:10 - INFO - __main__ - Step 40028: {'lr': 0.0004228812454560178, 'samples': 7685376, 'steps': 40027, 'loss/train': 1.2065141201019287} 08/30/2021 20:24:10 - INFO - __main__ - Step 40029: {'lr': 0.0004228774120767835, 'samples': 7685568, 'steps': 40028, 'loss/train': 1.2031065225601196} 08/30/2021 20:24:11 - INFO - __main__ - Step 40030: {'lr': 0.00042287357861965326, 'samples': 7685760, 'steps': 40029, 'loss/train': 0.0939389318227768} 08/30/2021 20:24:12 - INFO - __main__ - Step 40031: {'lr': 0.00042286974508462885, 'samples': 7685952, 'steps': 40030, 'loss/train': 0.4339176416397095} 08/30/2021 20:24:13 - INFO - __main__ - Step 40032: {'lr': 0.000422865911471712, 'samples': 7686144, 'steps': 40031, 'loss/train': 1.5876401662826538} 08/30/2021 20:24:13 - INFO - __main__ - Step 40033: {'lr': 0.00042286207778090447, 'samples': 7686336, 'steps': 40032, 'loss/train': 1.6221156120300293} 08/30/2021 20:24:13 - INFO - __main__ - Step 40034: {'lr': 0.00042285824401220787, 'samples': 7686528, 'steps': 40033, 'loss/train': 1.4964542388916016} 08/30/2021 20:24:14 - INFO - __main__ - Step 40035: {'lr': 0.0004228544101656241, 'samples': 7686720, 'steps': 40034, 'loss/train': 1.556596279144287} 08/30/2021 20:24:15 - INFO - __main__ - Step 40036: {'lr': 0.00042285057624115473, 'samples': 7686912, 'steps': 40035, 'loss/train': 1.0824153423309326} 08/30/2021 20:24:16 - INFO - __main__ - Step 40037: {'lr': 0.0004228467422388016, 'samples': 7687104, 'steps': 40036, 'loss/train': 1.5320526361465454} 08/30/2021 20:24:16 - INFO - __main__ - Step 40038: {'lr': 0.0004228429081585664, 'samples': 7687296, 'steps': 40037, 'loss/train': 1.1062607765197754} 08/30/2021 20:24:16 - INFO - __main__ - Step 40039: {'lr': 0.00042283907400045084, 'samples': 7687488, 'steps': 40038, 'loss/train': 0.6215230226516724} 08/30/2021 20:24:17 - INFO - __main__ - Step 40040: {'lr': 0.0004228352397644567, 'samples': 7687680, 'steps': 40039, 'loss/train': 1.4788440465927124} 08/30/2021 20:24:17 - INFO - __main__ - Step 40041: {'lr': 0.0004228314054505856, 'samples': 7687872, 'steps': 40040, 'loss/train': 1.5475090742111206} 08/30/2021 20:24:19 - INFO - __main__ - Step 40042: {'lr': 0.0004228275710588394, 'samples': 7688064, 'steps': 40041, 'loss/train': 1.282443881034851} 08/30/2021 20:24:19 - INFO - __main__ - Step 40043: {'lr': 0.0004228237365892197, 'samples': 7688256, 'steps': 40042, 'loss/train': 1.4643335342407227} 08/30/2021 20:24:19 - INFO - __main__ - Step 40044: {'lr': 0.00042281990204172837, 'samples': 7688448, 'steps': 40043, 'loss/train': 0.9389199018478394} 08/30/2021 20:24:20 - INFO - __main__ - Step 40045: {'lr': 0.000422816067416367, 'samples': 7688640, 'steps': 40044, 'loss/train': 1.473731279373169} 08/30/2021 20:24:20 - INFO - __main__ - Step 40046: {'lr': 0.00042281223271313734, 'samples': 7688832, 'steps': 40045, 'loss/train': 0.9742891192436218} 08/30/2021 20:24:22 - INFO - __main__ - Step 40047: {'lr': 0.0004228083979320412, 'samples': 7689024, 'steps': 40046, 'loss/train': 1.7017384767532349} 08/30/2021 20:24:22 - INFO - __main__ - Step 40048: {'lr': 0.00042280456307308034, 'samples': 7689216, 'steps': 40047, 'loss/train': 1.0361615419387817} 08/30/2021 20:24:22 - INFO - __main__ - Step 40049: {'lr': 0.0004228007281362563, 'samples': 7689408, 'steps': 40048, 'loss/train': 1.1506147384643555} 08/30/2021 20:24:23 - INFO - __main__ - Step 40050: {'lr': 0.0004227968931215709, 'samples': 7689600, 'steps': 40049, 'loss/train': 1.2911769151687622} 08/30/2021 20:24:23 - INFO - __main__ - Step 40051: {'lr': 0.000422793058029026, 'samples': 7689792, 'steps': 40050, 'loss/train': 1.5743813514709473} 08/30/2021 20:24:25 - INFO - __main__ - Step 40052: {'lr': 0.0004227892228586231, 'samples': 7689984, 'steps': 40051, 'loss/train': 1.305594563484192} 08/30/2021 20:24:25 - INFO - __main__ - Step 40053: {'lr': 0.0004227853876103641, 'samples': 7690176, 'steps': 40052, 'loss/train': 1.4357455968856812} 08/30/2021 20:24:26 - INFO - __main__ - Step 40054: {'lr': 0.0004227815522842507, 'samples': 7690368, 'steps': 40053, 'loss/train': 1.4548953771591187} 08/30/2021 20:24:26 - INFO - __main__ - Step 40055: {'lr': 0.00042277771688028457, 'samples': 7690560, 'steps': 40054, 'loss/train': 1.394719123840332} 08/30/2021 20:24:26 - INFO - __main__ - Step 40056: {'lr': 0.0004227738813984675, 'samples': 7690752, 'steps': 40055, 'loss/train': 1.5078915357589722} 08/30/2021 20:24:28 - INFO - __main__ - Step 40057: {'lr': 0.00042277004583880106, 'samples': 7690944, 'steps': 40056, 'loss/train': 1.3259233236312866} 08/30/2021 20:24:28 - INFO - __main__ - Step 40058: {'lr': 0.00042276621020128724, 'samples': 7691136, 'steps': 40057, 'loss/train': 1.6630440950393677} 08/30/2021 20:24:29 - INFO - __main__ - Step 40059: {'lr': 0.0004227623744859276, 'samples': 7691328, 'steps': 40058, 'loss/train': 1.198193073272705} 08/30/2021 20:24:29 - INFO - __main__ - Step 40060: {'lr': 0.0004227585386927239, 'samples': 7691520, 'steps': 40059, 'loss/train': 1.3635294437408447} 08/30/2021 20:24:29 - INFO - __main__ - Step 40061: {'lr': 0.0004227547028216778, 'samples': 7691712, 'steps': 40060, 'loss/train': 1.105837106704712} 08/30/2021 20:24:30 - INFO - __main__ - Step 40062: {'lr': 0.00042275086687279116, 'samples': 7691904, 'steps': 40061, 'loss/train': 1.3114802837371826} 08/30/2021 20:24:31 - INFO - __main__ - Step 40063: {'lr': 0.0004227470308460657, 'samples': 7692096, 'steps': 40062, 'loss/train': 1.6279492378234863} 08/30/2021 20:24:32 - INFO - __main__ - Step 40064: {'lr': 0.000422743194741503, 'samples': 7692288, 'steps': 40063, 'loss/train': 1.8441680669784546} 08/30/2021 20:24:32 - INFO - __main__ - Step 40065: {'lr': 0.00042273935855910487, 'samples': 7692480, 'steps': 40064, 'loss/train': 1.5744364261627197} 08/30/2021 20:24:32 - INFO - __main__ - Step 40066: {'lr': 0.00042273552229887313, 'samples': 7692672, 'steps': 40065, 'loss/train': 1.5886642932891846} 08/30/2021 20:24:33 - INFO - __main__ - Step 40067: {'lr': 0.00042273168596080934, 'samples': 7692864, 'steps': 40066, 'loss/train': 1.115769386291504} 08/30/2021 20:24:34 - INFO - __main__ - Step 40068: {'lr': 0.0004227278495449154, 'samples': 7693056, 'steps': 40067, 'loss/train': 0.4387758672237396} 08/30/2021 20:24:34 - INFO - __main__ - Step 40069: {'lr': 0.0004227240130511929, 'samples': 7693248, 'steps': 40068, 'loss/train': 1.2347543239593506} 08/30/2021 20:24:35 - INFO - __main__ - Step 40070: {'lr': 0.0004227201764796437, 'samples': 7693440, 'steps': 40069, 'loss/train': 1.8556299209594727} 08/30/2021 20:24:35 - INFO - __main__ - Step 40071: {'lr': 0.00042271633983026935, 'samples': 7693632, 'steps': 40070, 'loss/train': 1.4767194986343384} 08/30/2021 20:24:36 - INFO - __main__ - Step 40072: {'lr': 0.00042271250310307174, 'samples': 7693824, 'steps': 40071, 'loss/train': 1.3978941440582275} 08/30/2021 20:24:37 - INFO - __main__ - Step 40073: {'lr': 0.0004227086662980525, 'samples': 7694016, 'steps': 40072, 'loss/train': 1.6440999507904053} 08/30/2021 20:24:38 - INFO - __main__ - Step 40074: {'lr': 0.00042270482941521347, 'samples': 7694208, 'steps': 40073, 'loss/train': 1.8462797403335571} 08/30/2021 20:24:38 - INFO - __main__ - Step 40075: {'lr': 0.0004227009924545563, 'samples': 7694400, 'steps': 40074, 'loss/train': 1.6532827615737915} 08/30/2021 20:24:38 - INFO - __main__ - Step 40076: {'lr': 0.00042269715541608265, 'samples': 7694592, 'steps': 40075, 'loss/train': 1.437268614768982} 08/30/2021 20:24:39 - INFO - __main__ - Step 40077: {'lr': 0.0004226933182997944, 'samples': 7694784, 'steps': 40076, 'loss/train': 1.716097354888916} 08/30/2021 20:24:40 - INFO - __main__ - Step 40078: {'lr': 0.00042268948110569317, 'samples': 7694976, 'steps': 40077, 'loss/train': 1.6675812005996704} 08/30/2021 20:24:41 - INFO - __main__ - Step 40079: {'lr': 0.00042268564383378073, 'samples': 7695168, 'steps': 40078, 'loss/train': 1.4932663440704346} 08/30/2021 20:24:41 - INFO - __main__ - Step 40080: {'lr': 0.00042268180648405884, 'samples': 7695360, 'steps': 40079, 'loss/train': 1.8863270282745361} 08/30/2021 20:24:41 - INFO - __main__ - Step 40081: {'lr': 0.00042267796905652924, 'samples': 7695552, 'steps': 40080, 'loss/train': 1.533851146697998} 08/30/2021 20:24:42 - INFO - __main__ - Step 40082: {'lr': 0.0004226741315511935, 'samples': 7695744, 'steps': 40081, 'loss/train': 0.9106437563896179} 08/30/2021 20:24:44 - INFO - __main__ - Step 40083: {'lr': 0.00042267029396805345, 'samples': 7695936, 'steps': 40082, 'loss/train': 0.22785265743732452} 08/30/2021 20:24:44 - INFO - __main__ - Step 40084: {'lr': 0.0004226664563071109, 'samples': 7696128, 'steps': 40083, 'loss/train': 1.4615514278411865} 08/30/2021 20:24:45 - INFO - __main__ - Step 40085: {'lr': 0.0004226626185683675, 'samples': 7696320, 'steps': 40084, 'loss/train': 1.8035987615585327} 08/30/2021 20:24:45 - INFO - __main__ - Step 40086: {'lr': 0.00042265878075182497, 'samples': 7696512, 'steps': 40085, 'loss/train': 1.7350702285766602} 08/30/2021 20:24:45 - INFO - __main__ - Step 40087: {'lr': 0.0004226549428574851, 'samples': 7696704, 'steps': 40086, 'loss/train': 1.4968773126602173} 08/30/2021 20:24:46 - INFO - __main__ - Step 40088: {'lr': 0.0004226511048853495, 'samples': 7696896, 'steps': 40087, 'loss/train': 1.630066156387329} 08/30/2021 20:24:47 - INFO - __main__ - Step 40089: {'lr': 0.00042264726683542, 'samples': 7697088, 'steps': 40088, 'loss/train': 1.514136791229248} 08/30/2021 20:24:48 - INFO - __main__ - Step 40090: {'lr': 0.00042264342870769835, 'samples': 7697280, 'steps': 40089, 'loss/train': 1.4384431838989258} 08/30/2021 20:24:48 - INFO - __main__ - Step 40091: {'lr': 0.0004226395905021862, 'samples': 7697472, 'steps': 40090, 'loss/train': 3.484011650085449} 08/30/2021 20:24:49 - INFO - __main__ - Step 40092: {'lr': 0.0004226357522188853, 'samples': 7697664, 'steps': 40091, 'loss/train': 1.4920129776000977} 08/30/2021 20:24:49 - INFO - __main__ - Step 40093: {'lr': 0.0004226319138577974, 'samples': 7697856, 'steps': 40092, 'loss/train': 1.2493542432785034} 08/30/2021 20:24:50 - INFO - __main__ - Step 40094: {'lr': 0.0004226280754189243, 'samples': 7698048, 'steps': 40093, 'loss/train': 1.2865017652511597} 08/30/2021 20:24:51 - INFO - __main__ - Step 40095: {'lr': 0.0004226242369022676, 'samples': 7698240, 'steps': 40094, 'loss/train': 1.741750955581665} 08/30/2021 20:24:51 - INFO - __main__ - Step 40096: {'lr': 0.00042262039830782906, 'samples': 7698432, 'steps': 40095, 'loss/train': 0.4658586084842682} 08/30/2021 20:24:51 - INFO - __main__ - Step 40097: {'lr': 0.00042261655963561043, 'samples': 7698624, 'steps': 40096, 'loss/train': 1.557449460029602} 08/30/2021 20:24:52 - INFO - __main__ - Step 40098: {'lr': 0.0004226127208856134, 'samples': 7698816, 'steps': 40097, 'loss/train': 1.4780389070510864} 08/30/2021 20:24:53 - INFO - __main__ - Step 40099: {'lr': 0.0004226088820578399, 'samples': 7699008, 'steps': 40098, 'loss/train': 0.8832118511199951} 08/30/2021 20:24:54 - INFO - __main__ - Step 40100: {'lr': 0.00042260504315229136, 'samples': 7699200, 'steps': 40099, 'loss/train': 1.1463679075241089} 08/30/2021 20:24:54 - INFO - __main__ - Step 40101: {'lr': 0.00042260120416896975, 'samples': 7699392, 'steps': 40100, 'loss/train': 1.1320773363113403} 08/30/2021 20:24:54 - INFO - __main__ - Step 40102: {'lr': 0.0004225973651078766, 'samples': 7699584, 'steps': 40101, 'loss/train': 1.163228988647461} 08/30/2021 20:24:55 - INFO - __main__ - Step 40103: {'lr': 0.0004225935259690138, 'samples': 7699776, 'steps': 40102, 'loss/train': 1.7681277990341187} 08/30/2021 20:24:57 - INFO - __main__ - Step 40104: {'lr': 0.00042258968675238295, 'samples': 7699968, 'steps': 40103, 'loss/train': 1.5688971281051636} 08/30/2021 20:24:57 - INFO - __main__ - Step 40105: {'lr': 0.00042258584745798595, 'samples': 7700160, 'steps': 40104, 'loss/train': 1.2291992902755737} 08/30/2021 20:24:57 - INFO - __main__ - Step 40106: {'lr': 0.00042258200808582434, 'samples': 7700352, 'steps': 40105, 'loss/train': 1.602418303489685} 08/30/2021 20:24:58 - INFO - __main__ - Step 40107: {'lr': 0.00042257816863590006, 'samples': 7700544, 'steps': 40106, 'loss/train': 1.0369330644607544} 08/30/2021 20:24:58 - INFO - __main__ - Step 40108: {'lr': 0.0004225743291082146, 'samples': 7700736, 'steps': 40107, 'loss/train': 1.5382561683654785} 08/30/2021 20:24:59 - INFO - __main__ - Step 40109: {'lr': 0.0004225704895027699, 'samples': 7700928, 'steps': 40108, 'loss/train': 0.04080049693584442} 08/30/2021 20:25:00 - INFO - __main__ - Step 40110: {'lr': 0.0004225666498195675, 'samples': 7701120, 'steps': 40109, 'loss/train': 0.5043378472328186} 08/30/2021 20:25:01 - INFO - __main__ - Step 40111: {'lr': 0.0004225628100586093, 'samples': 7701312, 'steps': 40110, 'loss/train': 1.935161828994751} 08/30/2021 20:25:01 - INFO - __main__ - Step 40112: {'lr': 0.00042255897021989695, 'samples': 7701504, 'steps': 40111, 'loss/train': 1.0228524208068848} 08/30/2021 20:25:01 - INFO - __main__ - Step 40113: {'lr': 0.0004225551303034322, 'samples': 7701696, 'steps': 40112, 'loss/train': 1.6141903400421143} 08/30/2021 20:25:02 - INFO - __main__ - Step 40114: {'lr': 0.00042255129030921673, 'samples': 7701888, 'steps': 40113, 'loss/train': 1.0793025493621826} 08/30/2021 20:25:03 - INFO - __main__ - Step 40115: {'lr': 0.0004225474502372524, 'samples': 7702080, 'steps': 40114, 'loss/train': 1.5178107023239136} 08/30/2021 20:25:04 - INFO - __main__ - Step 40116: {'lr': 0.00042254361008754076, 'samples': 7702272, 'steps': 40115, 'loss/train': 1.3765003681182861} 08/30/2021 20:25:04 - INFO - __main__ - Step 40117: {'lr': 0.0004225397698600837, 'samples': 7702464, 'steps': 40116, 'loss/train': 2.1357617378234863} 08/30/2021 20:25:05 - INFO - __main__ - Step 40118: {'lr': 0.0004225359295548828, 'samples': 7702656, 'steps': 40117, 'loss/train': 0.9446281790733337} 08/30/2021 20:25:05 - INFO - __main__ - Step 40119: {'lr': 0.0004225320891719399, 'samples': 7702848, 'steps': 40118, 'loss/train': 1.4856083393096924} 08/30/2021 20:25:07 - INFO - __main__ - Step 40120: {'lr': 0.0004225282487112567, 'samples': 7703040, 'steps': 40119, 'loss/train': 1.324765682220459} 08/30/2021 20:25:07 - INFO - __main__ - Step 40121: {'lr': 0.000422524408172835, 'samples': 7703232, 'steps': 40120, 'loss/train': 2.013789415359497} 08/30/2021 20:25:08 - INFO - __main__ - Step 40122: {'lr': 0.0004225205675566765, 'samples': 7703424, 'steps': 40121, 'loss/train': 1.408373475074768} 08/30/2021 20:25:08 - INFO - __main__ - Step 40123: {'lr': 0.00042251672686278275, 'samples': 7703616, 'steps': 40122, 'loss/train': 1.0368902683258057} 08/30/2021 20:25:08 - INFO - __main__ - Step 40124: {'lr': 0.0004225128860911557, 'samples': 7703808, 'steps': 40123, 'loss/train': 1.0282988548278809} 08/30/2021 20:25:09 - INFO - __main__ - Step 40125: {'lr': 0.00042250904524179697, 'samples': 7704000, 'steps': 40124, 'loss/train': 1.749969244003296} 08/30/2021 20:25:10 - INFO - __main__ - Step 40126: {'lr': 0.00042250520431470827, 'samples': 7704192, 'steps': 40125, 'loss/train': 0.07141036540269852} 08/30/2021 20:25:11 - INFO - __main__ - Step 40127: {'lr': 0.00042250136330989154, 'samples': 7704384, 'steps': 40126, 'loss/train': 1.5025092363357544} 08/30/2021 20:25:11 - INFO - __main__ - Step 40128: {'lr': 0.00042249752222734826, 'samples': 7704576, 'steps': 40127, 'loss/train': 1.748719573020935} 08/30/2021 20:25:12 - INFO - __main__ - Step 40129: {'lr': 0.0004224936810670803, 'samples': 7704768, 'steps': 40128, 'loss/train': 1.230688214302063} 08/30/2021 20:25:12 - INFO - __main__ - Step 40130: {'lr': 0.0004224898398290893, 'samples': 7704960, 'steps': 40129, 'loss/train': 1.589765191078186} 08/30/2021 20:25:13 - INFO - __main__ - Step 40131: {'lr': 0.0004224859985133771, 'samples': 7705152, 'steps': 40130, 'loss/train': 0.2544907331466675} 08/30/2021 20:25:14 - INFO - __main__ - Step 40132: {'lr': 0.0004224821571199453, 'samples': 7705344, 'steps': 40131, 'loss/train': 1.3932286500930786} 08/30/2021 20:25:14 - INFO - __main__ - Step 40133: {'lr': 0.0004224783156487958, 'samples': 7705536, 'steps': 40132, 'loss/train': 1.7468143701553345} 08/30/2021 20:25:15 - INFO - __main__ - Step 40134: {'lr': 0.0004224744740999302, 'samples': 7705728, 'steps': 40133, 'loss/train': 1.5016592741012573} 08/30/2021 20:25:15 - INFO - __main__ - Step 40135: {'lr': 0.0004224706324733502, 'samples': 7705920, 'steps': 40134, 'loss/train': 1.1475318670272827} 08/30/2021 20:25:17 - INFO - __main__ - Step 40136: {'lr': 0.00042246679076905763, 'samples': 7706112, 'steps': 40135, 'loss/train': 1.443509578704834} 08/30/2021 20:25:17 - INFO - __main__ - Step 40137: {'lr': 0.00042246294898705416, 'samples': 7706304, 'steps': 40136, 'loss/train': 1.1780893802642822} 08/30/2021 20:25:18 - INFO - __main__ - Step 40138: {'lr': 0.0004224591071273416, 'samples': 7706496, 'steps': 40137, 'loss/train': 1.2799158096313477} 08/30/2021 20:25:18 - INFO - __main__ - Step 40139: {'lr': 0.00042245526518992164, 'samples': 7706688, 'steps': 40138, 'loss/train': 1.420188069343567} 08/30/2021 20:25:18 - INFO - __main__ - Step 40140: {'lr': 0.0004224514231747959, 'samples': 7706880, 'steps': 40139, 'loss/train': 1.156541109085083} 08/30/2021 20:25:19 - INFO - __main__ - Step 40141: {'lr': 0.00042244758108196635, 'samples': 7707072, 'steps': 40140, 'loss/train': 1.3181376457214355} 08/30/2021 20:25:20 - INFO - __main__ - Step 40142: {'lr': 0.00042244373891143453, 'samples': 7707264, 'steps': 40141, 'loss/train': 1.780436635017395} 08/30/2021 20:25:21 - INFO - __main__ - Step 40143: {'lr': 0.00042243989666320217, 'samples': 7707456, 'steps': 40142, 'loss/train': 0.983108401298523} 08/30/2021 20:25:21 - INFO - __main__ - Step 40144: {'lr': 0.00042243605433727106, 'samples': 7707648, 'steps': 40143, 'loss/train': 2.8953497409820557} 08/30/2021 20:25:21 - INFO - __main__ - Step 40145: {'lr': 0.0004224322119336429, 'samples': 7707840, 'steps': 40144, 'loss/train': 1.4392122030258179} 08/30/2021 20:25:22 - INFO - __main__ - Step 40146: {'lr': 0.0004224283694523195, 'samples': 7708032, 'steps': 40145, 'loss/train': 1.4808763265609741} 08/30/2021 20:25:23 - INFO - __main__ - Step 40147: {'lr': 0.0004224245268933025, 'samples': 7708224, 'steps': 40146, 'loss/train': 1.6406389474868774} 08/30/2021 20:25:24 - INFO - __main__ - Step 40148: {'lr': 0.0004224206842565937, 'samples': 7708416, 'steps': 40147, 'loss/train': 1.9504764080047607} 08/30/2021 20:25:24 - INFO - __main__ - Step 40149: {'lr': 0.0004224168415421948, 'samples': 7708608, 'steps': 40148, 'loss/train': 1.5916428565979004} 08/30/2021 20:25:24 - INFO - __main__ - Step 40150: {'lr': 0.0004224129987501075, 'samples': 7708800, 'steps': 40149, 'loss/train': 1.1741554737091064} 08/30/2021 20:25:25 - INFO - __main__ - Step 40151: {'lr': 0.0004224091558803337, 'samples': 7708992, 'steps': 40150, 'loss/train': 1.4782854318618774} 08/30/2021 20:25:26 - INFO - __main__ - Step 40152: {'lr': 0.0004224053129328748, 'samples': 7709184, 'steps': 40151, 'loss/train': 1.6107507944107056} 08/30/2021 20:25:27 - INFO - __main__ - Step 40153: {'lr': 0.0004224014699077329, 'samples': 7709376, 'steps': 40152, 'loss/train': 1.3659883737564087} 08/30/2021 20:25:27 - INFO - __main__ - Step 40154: {'lr': 0.00042239762680490944, 'samples': 7709568, 'steps': 40153, 'loss/train': 1.8823963403701782} 08/30/2021 20:25:27 - INFO - __main__ - Step 40155: {'lr': 0.00042239378362440627, 'samples': 7709760, 'steps': 40154, 'loss/train': 1.9861246347427368} 08/30/2021 20:25:28 - INFO - __main__ - Step 40156: {'lr': 0.0004223899403662251, 'samples': 7709952, 'steps': 40155, 'loss/train': 1.3641180992126465} 08/30/2021 20:25:29 - INFO - __main__ - Step 40157: {'lr': 0.0004223860970303678, 'samples': 7710144, 'steps': 40156, 'loss/train': 0.8633911609649658} 08/30/2021 20:25:29 - INFO - __main__ - Step 40158: {'lr': 0.00042238225361683593, 'samples': 7710336, 'steps': 40157, 'loss/train': 1.4306128025054932} 08/30/2021 20:25:30 - INFO - __main__ - Step 40159: {'lr': 0.00042237841012563126, 'samples': 7710528, 'steps': 40158, 'loss/train': 1.4161688089370728} 08/30/2021 20:25:30 - INFO - __main__ - Step 40160: {'lr': 0.00042237456655675555, 'samples': 7710720, 'steps': 40159, 'loss/train': 0.8530848622322083} 08/30/2021 20:25:31 - INFO - __main__ - Step 40161: {'lr': 0.0004223707229102105, 'samples': 7710912, 'steps': 40160, 'loss/train': 1.4616531133651733} 08/30/2021 20:25:32 - INFO - __main__ - Step 40162: {'lr': 0.0004223668791859979, 'samples': 7711104, 'steps': 40161, 'loss/train': 1.4830741882324219} 08/30/2021 20:25:32 - INFO - __main__ - Step 40163: {'lr': 0.00042236303538411934, 'samples': 7711296, 'steps': 40162, 'loss/train': 1.6665172576904297} 08/30/2021 20:25:33 - INFO - __main__ - Step 40164: {'lr': 0.0004223591915045768, 'samples': 7711488, 'steps': 40163, 'loss/train': 1.1709684133529663} 08/30/2021 20:25:33 - INFO - __main__ - Step 40165: {'lr': 0.0004223553475473718, 'samples': 7711680, 'steps': 40164, 'loss/train': 1.786667823791504} 08/30/2021 20:25:33 - INFO - __main__ - Step 40166: {'lr': 0.00042235150351250617, 'samples': 7711872, 'steps': 40165, 'loss/train': 0.9781188368797302} 08/30/2021 20:25:34 - INFO - __main__ - Step 40167: {'lr': 0.00042234765939998156, 'samples': 7712064, 'steps': 40166, 'loss/train': 1.8463987112045288} 08/30/2021 20:25:36 - INFO - __main__ - Step 40168: {'lr': 0.00042234381520979983, 'samples': 7712256, 'steps': 40167, 'loss/train': 1.7644538879394531} 08/30/2021 20:25:36 - INFO - __main__ - Step 40169: {'lr': 0.0004223399709419625, 'samples': 7712448, 'steps': 40168, 'loss/train': 1.6409869194030762} 08/30/2021 20:25:36 - INFO - __main__ - Step 40170: {'lr': 0.0004223361265964716, 'samples': 7712640, 'steps': 40169, 'loss/train': 1.7242861986160278} 08/30/2021 20:25:37 - INFO - __main__ - Step 40171: {'lr': 0.0004223322821733286, 'samples': 7712832, 'steps': 40170, 'loss/train': 1.6220542192459106} 08/30/2021 20:25:37 - INFO - __main__ - Step 40172: {'lr': 0.0004223284376725354, 'samples': 7713024, 'steps': 40171, 'loss/train': 1.19353187084198} 08/30/2021 20:25:39 - INFO - __main__ - Step 40173: {'lr': 0.00042232459309409355, 'samples': 7713216, 'steps': 40172, 'loss/train': 0.06970373541116714} 08/30/2021 20:25:39 - INFO - __main__ - Step 40174: {'lr': 0.00042232074843800494, 'samples': 7713408, 'steps': 40173, 'loss/train': 1.3166005611419678} 08/30/2021 20:25:40 - INFO - __main__ - Step 40175: {'lr': 0.00042231690370427135, 'samples': 7713600, 'steps': 40174, 'loss/train': 1.6356009244918823} 08/30/2021 20:25:40 - INFO - __main__ - Step 40176: {'lr': 0.00042231305889289437, 'samples': 7713792, 'steps': 40175, 'loss/train': 1.422113060951233} 08/30/2021 20:25:41 - INFO - __main__ - Step 40177: {'lr': 0.00042230921400387576, 'samples': 7713984, 'steps': 40176, 'loss/train': 1.337374210357666} 08/30/2021 20:25:41 - INFO - __main__ - Step 40178: {'lr': 0.0004223053690372173, 'samples': 7714176, 'steps': 40177, 'loss/train': 1.1246124505996704} 08/30/2021 20:25:42 - INFO - __main__ - Step 40179: {'lr': 0.00042230152399292065, 'samples': 7714368, 'steps': 40178, 'loss/train': 1.218896508216858} 08/30/2021 20:25:43 - INFO - __main__ - Step 40180: {'lr': 0.00042229767887098766, 'samples': 7714560, 'steps': 40179, 'loss/train': 0.061578940600156784} 08/30/2021 20:25:43 - INFO - __main__ - Step 40181: {'lr': 0.00042229383367142, 'samples': 7714752, 'steps': 40180, 'loss/train': 1.214537501335144} 08/30/2021 20:25:44 - INFO - __main__ - Step 40182: {'lr': 0.0004222899883942194, 'samples': 7714944, 'steps': 40181, 'loss/train': 1.0074496269226074} 08/30/2021 20:25:44 - INFO - __main__ - Step 40183: {'lr': 0.0004222861430393875, 'samples': 7715136, 'steps': 40182, 'loss/train': 2.0966055393218994} 08/30/2021 20:25:45 - INFO - __main__ - Step 40184: {'lr': 0.0004222822976069262, 'samples': 7715328, 'steps': 40183, 'loss/train': 1.9399789571762085} 08/30/2021 20:25:46 - INFO - __main__ - Step 40185: {'lr': 0.0004222784520968371, 'samples': 7715520, 'steps': 40184, 'loss/train': 1.4649888277053833} 08/30/2021 20:25:46 - INFO - __main__ - Step 40186: {'lr': 0.0004222746065091221, 'samples': 7715712, 'steps': 40185, 'loss/train': 1.5618942975997925} 08/30/2021 20:25:47 - INFO - __main__ - Step 40187: {'lr': 0.0004222707608437827, 'samples': 7715904, 'steps': 40186, 'loss/train': 0.6976447105407715} 08/30/2021 20:25:47 - INFO - __main__ - Step 40188: {'lr': 0.00042226691510082083, 'samples': 7716096, 'steps': 40187, 'loss/train': 1.6354740858078003} 08/30/2021 20:25:49 - INFO - __main__ - Step 40189: {'lr': 0.0004222630692802381, 'samples': 7716288, 'steps': 40188, 'loss/train': 1.2968591451644897} 08/30/2021 20:25:50 - INFO - __main__ - Step 40190: {'lr': 0.00042225922338203625, 'samples': 7716480, 'steps': 40189, 'loss/train': 1.4233076572418213} 08/30/2021 20:25:50 - INFO - __main__ - Step 40191: {'lr': 0.00042225537740621713, 'samples': 7716672, 'steps': 40190, 'loss/train': 0.5747855305671692} 08/30/2021 20:25:50 - INFO - __main__ - Step 40192: {'lr': 0.00042225153135278236, 'samples': 7716864, 'steps': 40191, 'loss/train': 1.2353590726852417} 08/30/2021 20:25:51 - INFO - __main__ - Step 40193: {'lr': 0.00042224768522173374, 'samples': 7717056, 'steps': 40192, 'loss/train': 1.044938564300537} 08/30/2021 20:25:51 - INFO - __main__ - Step 40194: {'lr': 0.00042224383901307293, 'samples': 7717248, 'steps': 40193, 'loss/train': 1.9550994634628296} 08/30/2021 20:25:53 - INFO - __main__ - Step 40195: {'lr': 0.0004222399927268018, 'samples': 7717440, 'steps': 40194, 'loss/train': 2.1724047660827637} 08/30/2021 20:25:53 - INFO - __main__ - Step 40196: {'lr': 0.0004222361463629218, 'samples': 7717632, 'steps': 40195, 'loss/train': 0.1256076693534851} 08/30/2021 20:25:54 - INFO - __main__ - Step 40197: {'lr': 0.00042223229992143505, 'samples': 7717824, 'steps': 40196, 'loss/train': 1.5086017847061157} 08/30/2021 20:25:54 - INFO - __main__ - Step 40198: {'lr': 0.00042222845340234293, 'samples': 7718016, 'steps': 40197, 'loss/train': 1.4065885543823242} 08/30/2021 20:25:54 - INFO - __main__ - Step 40199: {'lr': 0.00042222460680564747, 'samples': 7718208, 'steps': 40198, 'loss/train': 1.6255756616592407} 08/30/2021 20:25:55 - INFO - __main__ - Step 40200: {'lr': 0.0004222207601313501, 'samples': 7718400, 'steps': 40199, 'loss/train': 1.2395771741867065} 08/30/2021 20:25:56 - INFO - __main__ - Step 40201: {'lr': 0.00042221691337945285, 'samples': 7718592, 'steps': 40200, 'loss/train': 1.7549831867218018} 08/30/2021 20:25:57 - INFO - __main__ - Step 40202: {'lr': 0.0004222130665499573, 'samples': 7718784, 'steps': 40201, 'loss/train': 1.170562744140625} 08/30/2021 20:25:57 - INFO - __main__ - Step 40203: {'lr': 0.0004222092196428651, 'samples': 7718976, 'steps': 40202, 'loss/train': 1.9099899530410767} 08/30/2021 20:25:57 - INFO - __main__ - Step 40204: {'lr': 0.0004222053726581782, 'samples': 7719168, 'steps': 40203, 'loss/train': 1.7395405769348145} 08/30/2021 20:25:58 - INFO - __main__ - Step 40205: {'lr': 0.0004222015255958981, 'samples': 7719360, 'steps': 40204, 'loss/train': 1.62998628616333} 08/30/2021 20:25:59 - INFO - __main__ - Step 40206: {'lr': 0.0004221976784560267, 'samples': 7719552, 'steps': 40205, 'loss/train': 2.335939645767212} 08/30/2021 20:26:00 - INFO - __main__ - Step 40207: {'lr': 0.0004221938312385657, 'samples': 7719744, 'steps': 40206, 'loss/train': 1.6312938928604126} 08/30/2021 20:26:00 - INFO - __main__ - Step 40208: {'lr': 0.00042218998394351684, 'samples': 7719936, 'steps': 40207, 'loss/train': 0.9350178837776184} 08/30/2021 20:26:01 - INFO - __main__ - Step 40209: {'lr': 0.0004221861365708818, 'samples': 7720128, 'steps': 40208, 'loss/train': 1.3486769199371338} 08/30/2021 20:26:01 - INFO - __main__ - Step 40210: {'lr': 0.0004221822891206623, 'samples': 7720320, 'steps': 40209, 'loss/train': 1.4945238828659058} 08/30/2021 20:26:02 - INFO - __main__ - Step 40211: {'lr': 0.00042217844159286015, 'samples': 7720512, 'steps': 40210, 'loss/train': 1.356119155883789} 08/30/2021 20:26:03 - INFO - __main__ - Step 40212: {'lr': 0.00042217459398747703, 'samples': 7720704, 'steps': 40211, 'loss/train': 1.0561883449554443} 08/30/2021 20:26:03 - INFO - __main__ - Step 40213: {'lr': 0.0004221707463045148, 'samples': 7720896, 'steps': 40212, 'loss/train': 1.2845380306243896} 08/30/2021 20:26:04 - INFO - __main__ - Step 40214: {'lr': 0.0004221668985439749, 'samples': 7721088, 'steps': 40213, 'loss/train': 1.4505268335342407} 08/30/2021 20:26:04 - INFO - __main__ - Step 40215: {'lr': 0.00042216305070585946, 'samples': 7721280, 'steps': 40214, 'loss/train': 1.356143832206726} 08/30/2021 20:26:06 - INFO - __main__ - Step 40216: {'lr': 0.00042215920279016993, 'samples': 7721472, 'steps': 40215, 'loss/train': 1.7022701501846313} 08/30/2021 20:26:06 - INFO - __main__ - Step 40217: {'lr': 0.00042215535479690807, 'samples': 7721664, 'steps': 40216, 'loss/train': 1.1661900281906128} 08/30/2021 20:26:06 - INFO - __main__ - Step 40218: {'lr': 0.0004221515067260757, 'samples': 7721856, 'steps': 40217, 'loss/train': 1.6053369045257568} 08/30/2021 20:26:07 - INFO - __main__ - Step 40219: {'lr': 0.0004221476585776745, 'samples': 7722048, 'steps': 40218, 'loss/train': 0.9795981645584106} 08/30/2021 20:26:07 - INFO - __main__ - Step 40220: {'lr': 0.00042214381035170624, 'samples': 7722240, 'steps': 40219, 'loss/train': 1.2027286291122437} 08/30/2021 20:26:07 - INFO - __main__ - Step 40221: {'lr': 0.0004221399620481726, 'samples': 7722432, 'steps': 40220, 'loss/train': 1.3306986093521118} 08/30/2021 20:26:09 - INFO - __main__ - Step 40222: {'lr': 0.00042213611366707547, 'samples': 7722624, 'steps': 40221, 'loss/train': 1.4610397815704346} 08/30/2021 20:26:09 - INFO - __main__ - Step 40223: {'lr': 0.0004221322652084163, 'samples': 7722816, 'steps': 40222, 'loss/train': 1.5459133386611938} 08/30/2021 20:26:10 - INFO - __main__ - Step 40224: {'lr': 0.0004221284166721971, 'samples': 7723008, 'steps': 40223, 'loss/train': 1.3988077640533447} 08/30/2021 20:26:10 - INFO - __main__ - Step 40225: {'lr': 0.00042212456805841944, 'samples': 7723200, 'steps': 40224, 'loss/train': 1.1661248207092285} 08/30/2021 20:26:10 - INFO - __main__ - Step 40226: {'lr': 0.00042212071936708506, 'samples': 7723392, 'steps': 40225, 'loss/train': 1.7283368110656738} 08/30/2021 20:26:12 - INFO - __main__ - Step 40227: {'lr': 0.0004221168705981958, 'samples': 7723584, 'steps': 40226, 'loss/train': 1.7759498357772827} 08/30/2021 20:26:12 - INFO - __main__ - Step 40228: {'lr': 0.00042211302175175334, 'samples': 7723776, 'steps': 40227, 'loss/train': 1.4242711067199707} 08/30/2021 20:26:13 - INFO - __main__ - Step 40229: {'lr': 0.0004221091728277595, 'samples': 7723968, 'steps': 40228, 'loss/train': 1.1733466386795044} 08/30/2021 20:26:13 - INFO - __main__ - Step 40230: {'lr': 0.0004221053238262158, 'samples': 7724160, 'steps': 40229, 'loss/train': 1.3824355602264404} 08/30/2021 20:26:13 - INFO - __main__ - Step 40231: {'lr': 0.0004221014747471241, 'samples': 7724352, 'steps': 40230, 'loss/train': 1.3102034330368042} 08/30/2021 20:26:15 - INFO - __main__ - Step 40232: {'lr': 0.0004220976255904861, 'samples': 7724544, 'steps': 40231, 'loss/train': 2.7779786586761475} 08/30/2021 20:26:15 - INFO - __main__ - Step 40233: {'lr': 0.00042209377635630364, 'samples': 7724736, 'steps': 40232, 'loss/train': 1.4527312517166138} 08/30/2021 20:26:16 - INFO - __main__ - Step 40234: {'lr': 0.00042208992704457837, 'samples': 7724928, 'steps': 40233, 'loss/train': 1.3883405923843384} 08/30/2021 20:26:16 - INFO - __main__ - Step 40235: {'lr': 0.00042208607765531204, 'samples': 7725120, 'steps': 40234, 'loss/train': 0.9999542832374573} 08/30/2021 20:26:16 - INFO - __main__ - Step 40236: {'lr': 0.00042208222818850634, 'samples': 7725312, 'steps': 40235, 'loss/train': 1.4538649320602417} 08/30/2021 20:26:18 - INFO - __main__ - Step 40237: {'lr': 0.0004220783786441631, 'samples': 7725504, 'steps': 40236, 'loss/train': 2.277010917663574} 08/30/2021 20:26:19 - INFO - __main__ - Step 40238: {'lr': 0.0004220745290222839, 'samples': 7725696, 'steps': 40237, 'loss/train': 1.5419234037399292} 08/30/2021 20:26:19 - INFO - __main__ - Step 40239: {'lr': 0.00042207067932287066, 'samples': 7725888, 'steps': 40238, 'loss/train': 0.10715563595294952} 08/30/2021 20:26:19 - INFO - __main__ - Step 40240: {'lr': 0.00042206682954592503, 'samples': 7726080, 'steps': 40239, 'loss/train': 1.7700825929641724} 08/30/2021 20:26:20 - INFO - __main__ - Step 40241: {'lr': 0.0004220629796914487, 'samples': 7726272, 'steps': 40240, 'loss/train': 1.2869728803634644} 08/30/2021 20:26:21 - INFO - __main__ - Step 40242: {'lr': 0.00042205912975944344, 'samples': 7726464, 'steps': 40241, 'loss/train': 1.4915441274642944} 08/30/2021 20:26:22 - INFO - __main__ - Step 40243: {'lr': 0.00042205527974991096, 'samples': 7726656, 'steps': 40242, 'loss/train': 1.5039814710617065} 08/30/2021 20:26:22 - INFO - __main__ - Step 40244: {'lr': 0.00042205142966285315, 'samples': 7726848, 'steps': 40243, 'loss/train': 1.6874818801879883} 08/30/2021 20:26:22 - INFO - __main__ - Step 40245: {'lr': 0.0004220475794982716, 'samples': 7727040, 'steps': 40244, 'loss/train': 1.5026730298995972} 08/30/2021 20:26:23 - INFO - __main__ - Step 40246: {'lr': 0.00042204372925616797, 'samples': 7727232, 'steps': 40245, 'loss/train': 1.845436453819275} 08/30/2021 20:26:25 - INFO - __main__ - Step 40247: {'lr': 0.0004220398789365441, 'samples': 7727424, 'steps': 40246, 'loss/train': 1.6923195123672485} 08/30/2021 20:26:25 - INFO - __main__ - Step 40248: {'lr': 0.0004220360285394017, 'samples': 7727616, 'steps': 40247, 'loss/train': 1.8158271312713623} 08/30/2021 20:26:25 - INFO - __main__ - Step 40249: {'lr': 0.0004220321780647426, 'samples': 7727808, 'steps': 40248, 'loss/train': 1.2127046585083008} 08/30/2021 20:26:26 - INFO - __main__ - Step 40250: {'lr': 0.00042202832751256846, 'samples': 7728000, 'steps': 40249, 'loss/train': 1.5437755584716797} 08/30/2021 20:26:26 - INFO - __main__ - Step 40251: {'lr': 0.0004220244768828809, 'samples': 7728192, 'steps': 40250, 'loss/train': 1.290106177330017} 08/30/2021 20:26:27 - INFO - __main__ - Step 40252: {'lr': 0.0004220206261756819, 'samples': 7728384, 'steps': 40251, 'loss/train': 1.5362416505813599} 08/30/2021 20:26:28 - INFO - __main__ - Step 40253: {'lr': 0.00042201677539097294, 'samples': 7728576, 'steps': 40252, 'loss/train': 1.6931043863296509} 08/30/2021 20:26:28 - INFO - __main__ - Step 40254: {'lr': 0.00042201292452875595, 'samples': 7728768, 'steps': 40253, 'loss/train': 1.2157080173492432} 08/30/2021 20:26:29 - INFO - __main__ - Step 40255: {'lr': 0.00042200907358903264, 'samples': 7728960, 'steps': 40254, 'loss/train': 1.0430796146392822} 08/30/2021 20:26:29 - INFO - __main__ - Step 40256: {'lr': 0.0004220052225718046, 'samples': 7729152, 'steps': 40255, 'loss/train': 0.3433298170566559} 08/30/2021 20:26:31 - INFO - __main__ - Step 40257: {'lr': 0.0004220013714770737, 'samples': 7729344, 'steps': 40256, 'loss/train': 1.6203621625900269} 08/30/2021 20:26:31 - INFO - __main__ - Step 40258: {'lr': 0.0004219975203048416, 'samples': 7729536, 'steps': 40257, 'loss/train': 1.6242464780807495} 08/30/2021 20:26:31 - INFO - __main__ - Step 40259: {'lr': 0.0004219936690551101, 'samples': 7729728, 'steps': 40258, 'loss/train': 1.542497992515564} 08/30/2021 20:26:32 - INFO - __main__ - Step 40260: {'lr': 0.0004219898177278809, 'samples': 7729920, 'steps': 40259, 'loss/train': 1.1110448837280273} 08/30/2021 20:26:32 - INFO - __main__ - Step 40261: {'lr': 0.00042198596632315576, 'samples': 7730112, 'steps': 40260, 'loss/train': 1.1610714197158813} 08/30/2021 20:26:32 - INFO - __main__ - Step 40262: {'lr': 0.0004219821148409364, 'samples': 7730304, 'steps': 40261, 'loss/train': 0.886784553527832} 08/30/2021 20:26:34 - INFO - __main__ - Step 40263: {'lr': 0.00042197826328122456, 'samples': 7730496, 'steps': 40262, 'loss/train': 1.809583067893982} 08/30/2021 20:26:34 - INFO - __main__ - Step 40264: {'lr': 0.00042197441164402197, 'samples': 7730688, 'steps': 40263, 'loss/train': 0.9538978338241577} 08/30/2021 20:26:35 - INFO - __main__ - Step 40265: {'lr': 0.0004219705599293303, 'samples': 7730880, 'steps': 40264, 'loss/train': 1.320407509803772} 08/30/2021 20:26:35 - INFO - __main__ - Step 40266: {'lr': 0.00042196670813715137, 'samples': 7731072, 'steps': 40265, 'loss/train': 1.3191862106323242} 08/30/2021 20:26:35 - INFO - __main__ - Step 40267: {'lr': 0.0004219628562674869, 'samples': 7731264, 'steps': 40266, 'loss/train': 1.5166136026382446} 08/30/2021 20:26:37 - INFO - __main__ - Step 40268: {'lr': 0.00042195900432033865, 'samples': 7731456, 'steps': 40267, 'loss/train': 1.1742010116577148} 08/30/2021 20:26:38 - INFO - __main__ - Step 40269: {'lr': 0.00042195515229570833, 'samples': 7731648, 'steps': 40268, 'loss/train': 2.4226460456848145} 08/30/2021 20:26:38 - INFO - __main__ - Step 40270: {'lr': 0.0004219513001935976, 'samples': 7731840, 'steps': 40269, 'loss/train': 0.08580461144447327} 08/30/2021 20:26:38 - INFO - __main__ - Step 40271: {'lr': 0.00042194744801400837, 'samples': 7732032, 'steps': 40270, 'loss/train': 1.444115400314331} 08/30/2021 20:26:39 - INFO - __main__ - Step 40272: {'lr': 0.0004219435957569422, 'samples': 7732224, 'steps': 40271, 'loss/train': 1.6173263788223267} 08/30/2021 20:26:40 - INFO - __main__ - Step 40273: {'lr': 0.0004219397434224009, 'samples': 7732416, 'steps': 40272, 'loss/train': 1.2772033214569092} 08/30/2021 20:26:41 - INFO - __main__ - Step 40274: {'lr': 0.0004219358910103862, 'samples': 7732608, 'steps': 40273, 'loss/train': 1.7011590003967285} 08/30/2021 20:26:41 - INFO - __main__ - Step 40275: {'lr': 0.00042193203852089993, 'samples': 7732800, 'steps': 40274, 'loss/train': 1.663090705871582} 08/30/2021 20:26:41 - INFO - __main__ - Step 40276: {'lr': 0.00042192818595394367, 'samples': 7732992, 'steps': 40275, 'loss/train': 1.5258194208145142} 08/30/2021 20:26:42 - INFO - __main__ - Step 40277: {'lr': 0.00042192433330951926, 'samples': 7733184, 'steps': 40276, 'loss/train': 1.3969306945800781} 08/30/2021 20:26:42 - INFO - __main__ - Step 40278: {'lr': 0.00042192048058762834, 'samples': 7733376, 'steps': 40277, 'loss/train': 1.6105679273605347} 08/30/2021 20:26:44 - INFO - __main__ - Step 40279: {'lr': 0.00042191662778827275, 'samples': 7733568, 'steps': 40278, 'loss/train': 1.8405061960220337} 08/30/2021 20:26:44 - INFO - __main__ - Step 40280: {'lr': 0.0004219127749114541, 'samples': 7733760, 'steps': 40279, 'loss/train': 1.2166024446487427} 08/30/2021 20:26:45 - INFO - __main__ - Step 40281: {'lr': 0.00042190892195717426, 'samples': 7733952, 'steps': 40280, 'loss/train': 0.11395849287509918} 08/30/2021 20:26:45 - INFO - __main__ - Step 40282: {'lr': 0.000421905068925435, 'samples': 7734144, 'steps': 40281, 'loss/train': 0.8582900166511536} 08/30/2021 20:26:45 - INFO - __main__ - Step 40283: {'lr': 0.00042190121581623784, 'samples': 7734336, 'steps': 40282, 'loss/train': 0.1202424168586731} 08/30/2021 20:26:47 - INFO - __main__ - Step 40284: {'lr': 0.0004218973626295847, 'samples': 7734528, 'steps': 40283, 'loss/train': 0.883367657661438} 08/30/2021 20:26:47 - INFO - __main__ - Step 40285: {'lr': 0.0004218935093654772, 'samples': 7734720, 'steps': 40284, 'loss/train': 1.707689881324768} 08/30/2021 20:26:48 - INFO - __main__ - Step 40286: {'lr': 0.00042188965602391726, 'samples': 7734912, 'steps': 40285, 'loss/train': 1.4564054012298584} 08/30/2021 20:26:48 - INFO - __main__ - Step 40287: {'lr': 0.0004218858026049064, 'samples': 7735104, 'steps': 40286, 'loss/train': 1.4280130863189697} 08/30/2021 20:26:48 - INFO - __main__ - Step 40288: {'lr': 0.00042188194910844644, 'samples': 7735296, 'steps': 40287, 'loss/train': 0.8406389355659485} 08/30/2021 20:26:50 - INFO - __main__ - Step 40289: {'lr': 0.0004218780955345392, 'samples': 7735488, 'steps': 40288, 'loss/train': 1.1888542175292969} 08/30/2021 20:26:50 - INFO - __main__ - Step 40290: {'lr': 0.0004218742418831863, 'samples': 7735680, 'steps': 40289, 'loss/train': 1.2641905546188354} 08/30/2021 20:26:50 - INFO - __main__ - Step 40291: {'lr': 0.0004218703881543895, 'samples': 7735872, 'steps': 40290, 'loss/train': 1.9486578702926636} 08/30/2021 20:26:51 - INFO - __main__ - Step 40292: {'lr': 0.0004218665343481506, 'samples': 7736064, 'steps': 40291, 'loss/train': 1.593509554862976} 08/30/2021 20:26:51 - INFO - __main__ - Step 40293: {'lr': 0.00042186268046447124, 'samples': 7736256, 'steps': 40292, 'loss/train': 1.459471344947815} 08/30/2021 20:26:53 - INFO - __main__ - Step 40294: {'lr': 0.0004218588265033533, 'samples': 7736448, 'steps': 40293, 'loss/train': 1.3312150239944458} 08/30/2021 20:26:53 - INFO - __main__ - Step 40295: {'lr': 0.0004218549724647983, 'samples': 7736640, 'steps': 40294, 'loss/train': 1.2679634094238281} 08/30/2021 20:26:54 - INFO - __main__ - Step 40296: {'lr': 0.0004218511183488082, 'samples': 7736832, 'steps': 40295, 'loss/train': 1.7948038578033447} 08/30/2021 20:26:54 - INFO - __main__ - Step 40297: {'lr': 0.00042184726415538457, 'samples': 7737024, 'steps': 40296, 'loss/train': 0.22260817885398865} 08/30/2021 20:26:54 - INFO - __main__ - Step 40298: {'lr': 0.00042184340988452924, 'samples': 7737216, 'steps': 40297, 'loss/train': 0.058078914880752563} 08/30/2021 20:26:55 - INFO - __main__ - Step 40299: {'lr': 0.00042183955553624393, 'samples': 7737408, 'steps': 40298, 'loss/train': 3.3233203887939453} 08/30/2021 20:26:57 - INFO - __main__ - Step 40300: {'lr': 0.0004218357011105304, 'samples': 7737600, 'steps': 40299, 'loss/train': 1.1314195394515991} 08/30/2021 20:26:58 - INFO - __main__ - Step 40301: {'lr': 0.00042183184660739027, 'samples': 7737792, 'steps': 40300, 'loss/train': 1.8569934368133545} 08/30/2021 20:26:58 - INFO - __main__ - Step 40302: {'lr': 0.00042182799202682543, 'samples': 7737984, 'steps': 40301, 'loss/train': 1.2081995010375977} 08/30/2021 20:26:58 - INFO - __main__ - Step 40303: {'lr': 0.0004218241373688375, 'samples': 7738176, 'steps': 40302, 'loss/train': 1.2449356317520142} 08/30/2021 20:26:59 - INFO - __main__ - Step 40304: {'lr': 0.0004218202826334283, 'samples': 7738368, 'steps': 40303, 'loss/train': 1.396825909614563} 08/30/2021 20:27:00 - INFO - __main__ - Step 40305: {'lr': 0.0004218164278205995, 'samples': 7738560, 'steps': 40304, 'loss/train': 0.2743162512779236} 08/30/2021 20:27:01 - INFO - __main__ - Step 40306: {'lr': 0.00042181257293035293, 'samples': 7738752, 'steps': 40305, 'loss/train': 1.203744888305664} 08/30/2021 20:27:01 - INFO - __main__ - Step 40307: {'lr': 0.00042180871796269025, 'samples': 7738944, 'steps': 40306, 'loss/train': 1.3717964887619019} 08/30/2021 20:27:01 - INFO - __main__ - Step 40308: {'lr': 0.00042180486291761314, 'samples': 7739136, 'steps': 40307, 'loss/train': 1.3883644342422485} 08/30/2021 20:27:02 - INFO - __main__ - Step 40309: {'lr': 0.0004218010077951235, 'samples': 7739328, 'steps': 40308, 'loss/train': 1.1176751852035522} 08/30/2021 20:27:03 - INFO - __main__ - Step 40310: {'lr': 0.00042179715259522293, 'samples': 7739520, 'steps': 40309, 'loss/train': 1.3393816947937012} 08/30/2021 20:27:04 - INFO - __main__ - Step 40311: {'lr': 0.00042179329731791324, 'samples': 7739712, 'steps': 40310, 'loss/train': 1.5139739513397217} 08/30/2021 20:27:04 - INFO - __main__ - Step 40312: {'lr': 0.0004217894419631961, 'samples': 7739904, 'steps': 40311, 'loss/train': 1.3634111881256104} 08/30/2021 20:27:04 - INFO - __main__ - Step 40313: {'lr': 0.00042178558653107337, 'samples': 7740096, 'steps': 40312, 'loss/train': 1.403426170349121} 08/30/2021 20:27:05 - INFO - __main__ - Step 40314: {'lr': 0.0004217817310215466, 'samples': 7740288, 'steps': 40313, 'loss/train': 1.4507509469985962} 08/30/2021 20:27:05 - INFO - __main__ - Step 40315: {'lr': 0.00042177787543461767, 'samples': 7740480, 'steps': 40314, 'loss/train': 1.1985925436019897} 08/30/2021 20:27:07 - INFO - __main__ - Step 40316: {'lr': 0.0004217740197702883, 'samples': 7740672, 'steps': 40315, 'loss/train': 1.3934478759765625} 08/30/2021 20:27:07 - INFO - __main__ - Step 40317: {'lr': 0.00042177016402856023, 'samples': 7740864, 'steps': 40316, 'loss/train': 1.6885063648223877} 08/30/2021 20:27:07 - INFO - __main__ - Step 40318: {'lr': 0.00042176630820943515, 'samples': 7741056, 'steps': 40317, 'loss/train': 1.5838969945907593} 08/30/2021 20:27:08 - INFO - __main__ - Step 40319: {'lr': 0.0004217624523129148, 'samples': 7741248, 'steps': 40318, 'loss/train': 1.466996431350708} 08/30/2021 20:27:08 - INFO - __main__ - Step 40320: {'lr': 0.0004217585963390009, 'samples': 7741440, 'steps': 40319, 'loss/train': 1.7655426263809204} 08/30/2021 20:27:10 - INFO - __main__ - Step 40321: {'lr': 0.00042175474028769534, 'samples': 7741632, 'steps': 40320, 'loss/train': 1.281391978263855} 08/30/2021 20:27:10 - INFO - __main__ - Step 40322: {'lr': 0.00042175088415899963, 'samples': 7741824, 'steps': 40321, 'loss/train': 0.9976521730422974} 08/30/2021 20:27:11 - INFO - __main__ - Step 40323: {'lr': 0.00042174702795291574, 'samples': 7742016, 'steps': 40322, 'loss/train': 1.610156536102295} 08/30/2021 20:27:11 - INFO - __main__ - Step 40324: {'lr': 0.0004217431716694452, 'samples': 7742208, 'steps': 40323, 'loss/train': 1.3683069944381714} 08/30/2021 20:27:11 - INFO - __main__ - Step 40325: {'lr': 0.00042173931530858986, 'samples': 7742400, 'steps': 40324, 'loss/train': 1.3470276594161987} 08/30/2021 20:27:12 - INFO - __main__ - Step 40326: {'lr': 0.00042173545887035145, 'samples': 7742592, 'steps': 40325, 'loss/train': 2.7673308849334717} 08/30/2021 20:27:13 - INFO - __main__ - Step 40327: {'lr': 0.0004217316023547317, 'samples': 7742784, 'steps': 40326, 'loss/train': 1.4720513820648193} 08/30/2021 20:27:14 - INFO - __main__ - Step 40328: {'lr': 0.00042172774576173226, 'samples': 7742976, 'steps': 40327, 'loss/train': 1.5200849771499634} 08/30/2021 20:27:14 - INFO - __main__ - Step 40329: {'lr': 0.00042172388909135505, 'samples': 7743168, 'steps': 40328, 'loss/train': 1.0162831544876099} 08/30/2021 20:27:14 - INFO - __main__ - Step 40330: {'lr': 0.0004217200323436017, 'samples': 7743360, 'steps': 40329, 'loss/train': 1.2907416820526123} 08/30/2021 20:27:15 - INFO - __main__ - Step 40331: {'lr': 0.00042171617551847387, 'samples': 7743552, 'steps': 40330, 'loss/train': 1.3495899438858032} 08/30/2021 20:27:16 - INFO - __main__ - Step 40332: {'lr': 0.0004217123186159735, 'samples': 7743744, 'steps': 40331, 'loss/train': 1.6993693113327026} 08/30/2021 20:27:17 - INFO - __main__ - Step 40333: {'lr': 0.0004217084616361021, 'samples': 7743936, 'steps': 40332, 'loss/train': 1.6641629934310913} 08/30/2021 20:27:17 - INFO - __main__ - Step 40334: {'lr': 0.0004217046045788615, 'samples': 7744128, 'steps': 40333, 'loss/train': 0.5669681429862976} 08/30/2021 20:27:17 - INFO - __main__ - Step 40335: {'lr': 0.0004217007474442535, 'samples': 7744320, 'steps': 40334, 'loss/train': 1.3328664302825928} 08/30/2021 20:27:18 - INFO - __main__ - Step 40336: {'lr': 0.00042169689023227987, 'samples': 7744512, 'steps': 40335, 'loss/train': 1.328505516052246} 08/30/2021 20:27:19 - INFO - __main__ - Step 40337: {'lr': 0.00042169303294294216, 'samples': 7744704, 'steps': 40336, 'loss/train': 1.4756109714508057} 08/30/2021 20:27:20 - INFO - __main__ - Step 40338: {'lr': 0.0004216891755762423, 'samples': 7744896, 'steps': 40337, 'loss/train': 1.2971888780593872} 08/30/2021 20:27:20 - INFO - __main__ - Step 40339: {'lr': 0.00042168531813218193, 'samples': 7745088, 'steps': 40338, 'loss/train': 1.5193443298339844} 08/30/2021 20:27:20 - INFO - __main__ - Step 40340: {'lr': 0.0004216814606107627, 'samples': 7745280, 'steps': 40339, 'loss/train': 1.5263233184814453} 08/30/2021 20:27:21 - INFO - __main__ - Step 40341: {'lr': 0.00042167760301198656, 'samples': 7745472, 'steps': 40340, 'loss/train': 1.0317834615707397} 08/30/2021 20:27:22 - INFO - __main__ - Step 40342: {'lr': 0.0004216737453358551, 'samples': 7745664, 'steps': 40341, 'loss/train': 1.6369235515594482} 08/30/2021 20:27:22 - INFO - __main__ - Step 40343: {'lr': 0.00042166988758237013, 'samples': 7745856, 'steps': 40342, 'loss/train': 1.9898678064346313} 08/30/2021 20:27:23 - INFO - __main__ - Step 40344: {'lr': 0.00042166602975153333, 'samples': 7746048, 'steps': 40343, 'loss/train': 0.6933454275131226} 08/30/2021 20:27:23 - INFO - __main__ - Step 40345: {'lr': 0.0004216621718433465, 'samples': 7746240, 'steps': 40344, 'loss/train': 1.4344582557678223} 08/30/2021 20:27:23 - INFO - __main__ - Step 40346: {'lr': 0.0004216583138578113, 'samples': 7746432, 'steps': 40345, 'loss/train': 1.5408536195755005} 08/30/2021 20:27:24 - INFO - __main__ - Step 40347: {'lr': 0.00042165445579492956, 'samples': 7746624, 'steps': 40346, 'loss/train': 1.0205566883087158} 08/30/2021 20:27:25 - INFO - __main__ - Step 40348: {'lr': 0.00042165059765470294, 'samples': 7746816, 'steps': 40347, 'loss/train': 0.20116294920444489} 08/30/2021 20:27:26 - INFO - __main__ - Step 40349: {'lr': 0.0004216467394371333, 'samples': 7747008, 'steps': 40348, 'loss/train': 1.8667646646499634} 08/30/2021 20:27:26 - INFO - __main__ - Step 40350: {'lr': 0.00042164288114222213, 'samples': 7747200, 'steps': 40349, 'loss/train': 0.07593879848718643} 08/30/2021 20:27:27 - INFO - __main__ - Step 40351: {'lr': 0.0004216390227699714, 'samples': 7747392, 'steps': 40350, 'loss/train': 1.6598784923553467} 08/30/2021 20:27:27 - INFO - __main__ - Step 40352: {'lr': 0.0004216351643203828, 'samples': 7747584, 'steps': 40351, 'loss/train': 1.124419093132019} 08/30/2021 20:27:28 - INFO - __main__ - Step 40353: {'lr': 0.000421631305793458, 'samples': 7747776, 'steps': 40352, 'loss/train': 1.5605723857879639} 08/30/2021 20:27:29 - INFO - __main__ - Step 40354: {'lr': 0.00042162744718919875, 'samples': 7747968, 'steps': 40353, 'loss/train': 1.3406190872192383} 08/30/2021 20:27:29 - INFO - __main__ - Step 40355: {'lr': 0.0004216235885076069, 'samples': 7748160, 'steps': 40354, 'loss/train': 0.9849457740783691} 08/30/2021 20:27:29 - INFO - __main__ - Step 40356: {'lr': 0.00042161972974868415, 'samples': 7748352, 'steps': 40355, 'loss/train': 1.4419806003570557} 08/30/2021 20:27:30 - INFO - __main__ - Step 40357: {'lr': 0.00042161587091243215, 'samples': 7748544, 'steps': 40356, 'loss/train': 1.6206034421920776} 08/30/2021 20:27:32 - INFO - __main__ - Step 40358: {'lr': 0.00042161201199885257, 'samples': 7748736, 'steps': 40357, 'loss/train': 1.4444661140441895} 08/30/2021 20:27:32 - INFO - __main__ - Step 40359: {'lr': 0.0004216081530079474, 'samples': 7748928, 'steps': 40358, 'loss/train': 0.3225405812263489} 08/30/2021 20:27:33 - INFO - __main__ - Step 40360: {'lr': 0.0004216042939397182, 'samples': 7749120, 'steps': 40359, 'loss/train': 1.5831632614135742} 08/30/2021 20:27:33 - INFO - __main__ - Step 40361: {'lr': 0.00042160043479416676, 'samples': 7749312, 'steps': 40360, 'loss/train': 1.3057969808578491} 08/30/2021 20:27:33 - INFO - __main__ - Step 40362: {'lr': 0.00042159657557129483, 'samples': 7749504, 'steps': 40361, 'loss/train': 1.74065101146698} 08/30/2021 20:27:35 - INFO - __main__ - Step 40363: {'lr': 0.0004215927162711041, 'samples': 7749696, 'steps': 40362, 'loss/train': 2.012923002243042} 08/30/2021 20:27:36 - INFO - __main__ - Step 40364: {'lr': 0.00042158885689359637, 'samples': 7749888, 'steps': 40363, 'loss/train': 1.2692090272903442} 08/30/2021 20:27:36 - INFO - __main__ - Step 40365: {'lr': 0.0004215849974387733, 'samples': 7750080, 'steps': 40364, 'loss/train': 0.5138596296310425} 08/30/2021 20:27:36 - INFO - __main__ - Step 40366: {'lr': 0.0004215811379066367, 'samples': 7750272, 'steps': 40365, 'loss/train': 1.9462394714355469} 08/30/2021 20:27:37 - INFO - __main__ - Step 40367: {'lr': 0.00042157727829718827, 'samples': 7750464, 'steps': 40366, 'loss/train': 1.1545941829681396} 08/30/2021 20:27:38 - INFO - __main__ - Step 40368: {'lr': 0.00042157341861042986, 'samples': 7750656, 'steps': 40367, 'loss/train': 1.166222095489502} 08/30/2021 20:27:39 - INFO - __main__ - Step 40369: {'lr': 0.00042156955884636307, 'samples': 7750848, 'steps': 40368, 'loss/train': 1.1601929664611816} 08/30/2021 20:27:39 - INFO - __main__ - Step 40370: {'lr': 0.0004215656990049896, 'samples': 7751040, 'steps': 40369, 'loss/train': 0.9019650816917419} 08/30/2021 20:27:39 - INFO - __main__ - Step 40371: {'lr': 0.0004215618390863114, 'samples': 7751232, 'steps': 40370, 'loss/train': 0.5609971880912781} 08/30/2021 20:27:40 - INFO - __main__ - Step 40372: {'lr': 0.00042155797909033, 'samples': 7751424, 'steps': 40371, 'loss/train': 1.0752054452896118} 08/30/2021 20:27:42 - INFO - __main__ - Step 40373: {'lr': 0.00042155411901704723, 'samples': 7751616, 'steps': 40372, 'loss/train': 1.7423181533813477} 08/30/2021 20:27:42 - INFO - __main__ - Step 40374: {'lr': 0.0004215502588664648, 'samples': 7751808, 'steps': 40373, 'loss/train': 1.6888480186462402} 08/30/2021 20:27:42 - INFO - __main__ - Step 40375: {'lr': 0.0004215463986385845, 'samples': 7752000, 'steps': 40374, 'loss/train': 0.9067996144294739} 08/30/2021 20:27:43 - INFO - __main__ - Step 40376: {'lr': 0.0004215425383334081, 'samples': 7752192, 'steps': 40375, 'loss/train': 0.1130153089761734} 08/30/2021 20:27:43 - INFO - __main__ - Step 40377: {'lr': 0.00042153867795093714, 'samples': 7752384, 'steps': 40376, 'loss/train': 1.697483777999878} 08/30/2021 20:27:45 - INFO - __main__ - Step 40378: {'lr': 0.0004215348174911736, 'samples': 7752576, 'steps': 40377, 'loss/train': 1.3804517984390259} 08/30/2021 20:27:45 - INFO - __main__ - Step 40379: {'lr': 0.0004215309569541191, 'samples': 7752768, 'steps': 40378, 'loss/train': 1.7700001001358032} 08/30/2021 20:27:45 - INFO - __main__ - Step 40380: {'lr': 0.00042152709633977545, 'samples': 7752960, 'steps': 40379, 'loss/train': 0.9675085544586182} 08/30/2021 20:27:46 - INFO - __main__ - Step 40381: {'lr': 0.0004215232356481442, 'samples': 7753152, 'steps': 40380, 'loss/train': 1.470218539237976} 08/30/2021 20:27:46 - INFO - __main__ - Step 40382: {'lr': 0.0004215193748792273, 'samples': 7753344, 'steps': 40381, 'loss/train': 0.9617518782615662} 08/30/2021 20:27:46 - INFO - __main__ - Step 40383: {'lr': 0.00042151551403302645, 'samples': 7753536, 'steps': 40382, 'loss/train': 2.5395267009735107} 08/30/2021 20:27:48 - INFO - __main__ - Step 40384: {'lr': 0.00042151165310954335, 'samples': 7753728, 'steps': 40383, 'loss/train': 1.0392248630523682} 08/30/2021 20:27:48 - INFO - __main__ - Step 40385: {'lr': 0.0004215077921087798, 'samples': 7753920, 'steps': 40384, 'loss/train': 1.2678207159042358} 08/30/2021 20:27:49 - INFO - __main__ - Step 40386: {'lr': 0.00042150393103073736, 'samples': 7754112, 'steps': 40385, 'loss/train': 1.7337491512298584} 08/30/2021 20:27:49 - INFO - __main__ - Step 40387: {'lr': 0.00042150006987541795, 'samples': 7754304, 'steps': 40386, 'loss/train': 1.4797840118408203} 08/30/2021 20:27:49 - INFO - __main__ - Step 40388: {'lr': 0.0004214962086428232, 'samples': 7754496, 'steps': 40387, 'loss/train': 1.6027675867080688} 08/30/2021 20:27:51 - INFO - __main__ - Step 40389: {'lr': 0.00042149234733295497, 'samples': 7754688, 'steps': 40388, 'loss/train': 1.48690664768219} 08/30/2021 20:27:52 - INFO - __main__ - Step 40390: {'lr': 0.00042148848594581503, 'samples': 7754880, 'steps': 40389, 'loss/train': 0.8856250643730164} 08/30/2021 20:27:52 - INFO - __main__ - Step 40391: {'lr': 0.00042148462448140487, 'samples': 7755072, 'steps': 40390, 'loss/train': 1.2726149559020996} 08/30/2021 20:27:52 - INFO - __main__ - Step 40392: {'lr': 0.0004214807629397264, 'samples': 7755264, 'steps': 40391, 'loss/train': 1.0841002464294434} 08/30/2021 20:27:53 - INFO - __main__ - Step 40393: {'lr': 0.00042147690132078136, 'samples': 7755456, 'steps': 40392, 'loss/train': 0.5488522052764893} 08/30/2021 20:27:54 - INFO - __main__ - Step 40394: {'lr': 0.0004214730396245715, 'samples': 7755648, 'steps': 40393, 'loss/train': 1.7260538339614868} 08/30/2021 20:27:55 - INFO - __main__ - Step 40395: {'lr': 0.0004214691778510985, 'samples': 7755840, 'steps': 40394, 'loss/train': 1.1251493692398071} 08/30/2021 20:27:55 - INFO - __main__ - Step 40396: {'lr': 0.0004214653160003642, 'samples': 7756032, 'steps': 40395, 'loss/train': 1.223690152168274} 08/30/2021 20:27:55 - INFO - __main__ - Step 40397: {'lr': 0.00042146145407237023, 'samples': 7756224, 'steps': 40396, 'loss/train': 1.7771278619766235} 08/30/2021 20:27:56 - INFO - __main__ - Step 40398: {'lr': 0.00042145759206711834, 'samples': 7756416, 'steps': 40397, 'loss/train': 1.2685621976852417} 08/30/2021 20:27:57 - INFO - __main__ - Step 40399: {'lr': 0.0004214537299846104, 'samples': 7756608, 'steps': 40398, 'loss/train': 1.491264820098877} 08/30/2021 20:27:58 - INFO - __main__ - Step 40400: {'lr': 0.00042144986782484796, 'samples': 7756800, 'steps': 40399, 'loss/train': 0.7894092798233032} 08/30/2021 20:27:58 - INFO - __main__ - Step 40401: {'lr': 0.00042144600558783284, 'samples': 7756992, 'steps': 40400, 'loss/train': 1.8036856651306152} 08/30/2021 20:27:58 - INFO - __main__ - Step 40402: {'lr': 0.0004214421432735669, 'samples': 7757184, 'steps': 40401, 'loss/train': 1.860939621925354} 08/30/2021 20:27:59 - INFO - __main__ - Step 40403: {'lr': 0.0004214382808820517, 'samples': 7757376, 'steps': 40402, 'loss/train': 1.1518206596374512} 08/30/2021 20:28:00 - INFO - __main__ - Step 40404: {'lr': 0.0004214344184132891, 'samples': 7757568, 'steps': 40403, 'loss/train': 1.4019520282745361} 08/30/2021 20:28:01 - INFO - __main__ - Step 40405: {'lr': 0.0004214305558672808, 'samples': 7757760, 'steps': 40404, 'loss/train': 1.6815168857574463} 08/30/2021 20:28:01 - INFO - __main__ - Step 40406: {'lr': 0.0004214266932440285, 'samples': 7757952, 'steps': 40405, 'loss/train': 1.1195424795150757} 08/30/2021 20:28:01 - INFO - __main__ - Step 40407: {'lr': 0.000421422830543534, 'samples': 7758144, 'steps': 40406, 'loss/train': 1.978991985321045} 08/30/2021 20:28:02 - INFO - __main__ - Step 40408: {'lr': 0.00042141896776579904, 'samples': 7758336, 'steps': 40407, 'loss/train': 1.7775918245315552} 08/30/2021 20:28:02 - INFO - __main__ - Step 40409: {'lr': 0.0004214151049108252, 'samples': 7758528, 'steps': 40408, 'loss/train': 1.9017950296401978} 08/30/2021 20:28:04 - INFO - __main__ - Step 40410: {'lr': 0.00042141124197861456, 'samples': 7758720, 'steps': 40409, 'loss/train': 1.5890322923660278} 08/30/2021 20:28:05 - INFO - __main__ - Step 40411: {'lr': 0.0004214073789691686, 'samples': 7758912, 'steps': 40410, 'loss/train': 1.2397980690002441} 08/30/2021 20:28:05 - INFO - __main__ - Step 40412: {'lr': 0.00042140351588248906, 'samples': 7759104, 'steps': 40411, 'loss/train': 1.108689546585083} 08/30/2021 20:28:05 - INFO - __main__ - Step 40413: {'lr': 0.00042139965271857774, 'samples': 7759296, 'steps': 40412, 'loss/train': 1.601515293121338} 08/30/2021 20:28:06 - INFO - __main__ - Step 40414: {'lr': 0.0004213957894774364, 'samples': 7759488, 'steps': 40413, 'loss/train': 1.6199307441711426} 08/30/2021 20:28:07 - INFO - __main__ - Step 40415: {'lr': 0.0004213919261590667, 'samples': 7759680, 'steps': 40414, 'loss/train': 1.2000441551208496} 08/30/2021 20:28:08 - INFO - __main__ - Step 40416: {'lr': 0.0004213880627634705, 'samples': 7759872, 'steps': 40415, 'loss/train': 1.3455394506454468} 08/30/2021 20:28:08 - INFO - __main__ - Step 40417: {'lr': 0.0004213841992906496, 'samples': 7760064, 'steps': 40416, 'loss/train': 1.445949673652649} 08/30/2021 20:28:08 - INFO - __main__ - Step 40418: {'lr': 0.0004213803357406055, 'samples': 7760256, 'steps': 40417, 'loss/train': 3.0253524780273438} 08/30/2021 20:28:09 - INFO - __main__ - Step 40419: {'lr': 0.00042137647211334007, 'samples': 7760448, 'steps': 40418, 'loss/train': 1.703039288520813} 08/30/2021 20:28:10 - INFO - __main__ - Step 40420: {'lr': 0.000421372608408855, 'samples': 7760640, 'steps': 40419, 'loss/train': 1.0548624992370605} 08/30/2021 20:28:11 - INFO - __main__ - Step 40421: {'lr': 0.0004213687446271522, 'samples': 7760832, 'steps': 40420, 'loss/train': 0.630613386631012} 08/30/2021 20:28:11 - INFO - __main__ - Step 40422: {'lr': 0.0004213648807682332, 'samples': 7761024, 'steps': 40421, 'loss/train': 1.1315127611160278} 08/30/2021 20:28:12 - INFO - __main__ - Step 40423: {'lr': 0.00042136101683209993, 'samples': 7761216, 'steps': 40422, 'loss/train': 0.7948915958404541} 08/30/2021 20:28:12 - INFO - __main__ - Step 40424: {'lr': 0.00042135715281875393, 'samples': 7761408, 'steps': 40423, 'loss/train': 1.3141162395477295} 08/30/2021 20:28:13 - INFO - __main__ - Step 40425: {'lr': 0.000421353288728197, 'samples': 7761600, 'steps': 40424, 'loss/train': 1.365285873413086} 08/30/2021 20:28:14 - INFO - __main__ - Step 40426: {'lr': 0.00042134942456043104, 'samples': 7761792, 'steps': 40425, 'loss/train': 1.4979889392852783} 08/30/2021 20:28:14 - INFO - __main__ - Step 40427: {'lr': 0.00042134556031545755, 'samples': 7761984, 'steps': 40426, 'loss/train': 1.6646672487258911} 08/30/2021 20:28:15 - INFO - __main__ - Step 40428: {'lr': 0.0004213416959932785, 'samples': 7762176, 'steps': 40427, 'loss/train': 1.4719834327697754} 08/30/2021 20:28:15 - INFO - __main__ - Step 40429: {'lr': 0.0004213378315938955, 'samples': 7762368, 'steps': 40428, 'loss/train': 1.4625318050384521} 08/30/2021 20:28:16 - INFO - __main__ - Step 40430: {'lr': 0.0004213339671173103, 'samples': 7762560, 'steps': 40429, 'loss/train': 1.7609469890594482} 08/30/2021 20:28:17 - INFO - __main__ - Step 40431: {'lr': 0.00042133010256352466, 'samples': 7762752, 'steps': 40430, 'loss/train': 1.342767357826233} 08/30/2021 20:28:17 - INFO - __main__ - Step 40432: {'lr': 0.00042132623793254034, 'samples': 7762944, 'steps': 40431, 'loss/train': 1.5123486518859863} 08/30/2021 20:28:17 - INFO - __main__ - Step 40433: {'lr': 0.0004213223732243591, 'samples': 7763136, 'steps': 40432, 'loss/train': 1.015679955482483} 08/30/2021 20:28:18 - INFO - __main__ - Step 40434: {'lr': 0.00042131850843898255, 'samples': 7763328, 'steps': 40433, 'loss/train': 1.6167149543762207} 08/30/2021 20:28:19 - INFO - __main__ - Step 40435: {'lr': 0.0004213146435764126, 'samples': 7763520, 'steps': 40434, 'loss/train': 1.1222697496414185} 08/30/2021 20:28:20 - INFO - __main__ - Step 40436: {'lr': 0.00042131077863665086, 'samples': 7763712, 'steps': 40435, 'loss/train': 1.3205466270446777} 08/30/2021 20:28:20 - INFO - __main__ - Step 40437: {'lr': 0.00042130691361969914, 'samples': 7763904, 'steps': 40436, 'loss/train': 1.8007813692092896} 08/30/2021 20:28:20 - INFO - __main__ - Step 40438: {'lr': 0.00042130304852555916, 'samples': 7764096, 'steps': 40437, 'loss/train': 1.0469818115234375} 08/30/2021 20:28:21 - INFO - __main__ - Step 40439: {'lr': 0.00042129918335423265, 'samples': 7764288, 'steps': 40438, 'loss/train': 1.7245885133743286} 08/30/2021 20:28:21 - INFO - __main__ - Step 40440: {'lr': 0.0004212953181057214, 'samples': 7764480, 'steps': 40439, 'loss/train': 0.9249213933944702} 08/30/2021 20:28:23 - INFO - __main__ - Step 40441: {'lr': 0.0004212914527800272, 'samples': 7764672, 'steps': 40440, 'loss/train': 1.673649787902832} 08/30/2021 20:28:23 - INFO - __main__ - Step 40442: {'lr': 0.0004212875873771516, 'samples': 7764864, 'steps': 40441, 'loss/train': 1.8173637390136719} 08/30/2021 20:28:23 - INFO - __main__ - Step 40443: {'lr': 0.0004212837218970965, 'samples': 7765056, 'steps': 40442, 'loss/train': 1.2666174173355103} 08/30/2021 20:28:24 - INFO - __main__ - Step 40444: {'lr': 0.00042127985633986365, 'samples': 7765248, 'steps': 40443, 'loss/train': 1.8080965280532837} 08/30/2021 20:28:24 - INFO - __main__ - Step 40445: {'lr': 0.0004212759907054546, 'samples': 7765440, 'steps': 40444, 'loss/train': 0.9029436111450195} 08/30/2021 20:28:26 - INFO - __main__ - Step 40446: {'lr': 0.00042127212499387136, 'samples': 7765632, 'steps': 40445, 'loss/train': 1.9689255952835083} 08/30/2021 20:28:26 - INFO - __main__ - Step 40447: {'lr': 0.0004212682592051155, 'samples': 7765824, 'steps': 40446, 'loss/train': 0.8188783526420593} 08/30/2021 20:28:26 - INFO - __main__ - Step 40448: {'lr': 0.0004212643933391888, 'samples': 7766016, 'steps': 40447, 'loss/train': 1.0567514896392822} 08/30/2021 20:28:27 - INFO - __main__ - Step 40449: {'lr': 0.000421260527396093, 'samples': 7766208, 'steps': 40448, 'loss/train': 1.8368842601776123} 08/30/2021 20:28:27 - INFO - __main__ - Step 40450: {'lr': 0.0004212566613758299, 'samples': 7766400, 'steps': 40449, 'loss/train': 1.2382378578186035} 08/30/2021 20:28:28 - INFO - __main__ - Step 40451: {'lr': 0.00042125279527840124, 'samples': 7766592, 'steps': 40450, 'loss/train': 1.1999740600585938} 08/30/2021 20:28:29 - INFO - __main__ - Step 40452: {'lr': 0.0004212489291038085, 'samples': 7766784, 'steps': 40451, 'loss/train': 1.3785598278045654} 08/30/2021 20:28:29 - INFO - __main__ - Step 40453: {'lr': 0.0004212450628520538, 'samples': 7766976, 'steps': 40452, 'loss/train': 1.0922719240188599} 08/30/2021 20:28:30 - INFO - __main__ - Step 40454: {'lr': 0.0004212411965231387, 'samples': 7767168, 'steps': 40453, 'loss/train': 0.7920715808868408} 08/30/2021 20:28:30 - INFO - __main__ - Step 40455: {'lr': 0.0004212373301170649, 'samples': 7767360, 'steps': 40454, 'loss/train': 1.383434772491455} 08/30/2021 20:28:32 - INFO - __main__ - Step 40456: {'lr': 0.00042123346363383426, 'samples': 7767552, 'steps': 40455, 'loss/train': 1.9311542510986328} 08/30/2021 20:28:32 - INFO - __main__ - Step 40457: {'lr': 0.0004212295970734484, 'samples': 7767744, 'steps': 40456, 'loss/train': 1.3312681913375854} 08/30/2021 20:28:33 - INFO - __main__ - Step 40458: {'lr': 0.00042122573043590925, 'samples': 7767936, 'steps': 40457, 'loss/train': 1.8653721809387207} 08/30/2021 20:28:33 - INFO - __main__ - Step 40459: {'lr': 0.0004212218637212183, 'samples': 7768128, 'steps': 40458, 'loss/train': 1.610128402709961} 08/30/2021 20:28:33 - INFO - __main__ - Step 40460: {'lr': 0.00042121799692937747, 'samples': 7768320, 'steps': 40459, 'loss/train': 1.544898271560669} 08/30/2021 20:28:34 - INFO - __main__ - Step 40461: {'lr': 0.00042121413006038845, 'samples': 7768512, 'steps': 40460, 'loss/train': 0.045086152851581573} 08/30/2021 20:28:34 - INFO - __main__ - Step 40462: {'lr': 0.000421210263114253, 'samples': 7768704, 'steps': 40461, 'loss/train': 0.26992398500442505} 08/30/2021 20:28:36 - INFO - __main__ - Step 40463: {'lr': 0.00042120639609097277, 'samples': 7768896, 'steps': 40462, 'loss/train': 1.440134048461914} 08/30/2021 20:28:36 - INFO - __main__ - Step 40464: {'lr': 0.0004212025289905497, 'samples': 7769088, 'steps': 40463, 'loss/train': 1.5344254970550537} 08/30/2021 20:28:36 - INFO - __main__ - Step 40465: {'lr': 0.0004211986618129854, 'samples': 7769280, 'steps': 40464, 'loss/train': 1.4416701793670654} 08/30/2021 20:28:37 - INFO - __main__ - Step 40466: {'lr': 0.00042119479455828153, 'samples': 7769472, 'steps': 40465, 'loss/train': 1.1182299852371216} 08/30/2021 20:28:37 - INFO - __main__ - Step 40467: {'lr': 0.00042119092722644, 'samples': 7769664, 'steps': 40466, 'loss/train': 1.1801046133041382} 08/30/2021 20:28:39 - INFO - __main__ - Step 40468: {'lr': 0.0004211870598174624, 'samples': 7769856, 'steps': 40467, 'loss/train': 1.793915867805481} 08/30/2021 20:28:40 - INFO - __main__ - Step 40469: {'lr': 0.0004211831923313506, 'samples': 7770048, 'steps': 40468, 'loss/train': 0.9394699931144714} 08/30/2021 20:28:40 - INFO - __main__ - Step 40470: {'lr': 0.0004211793247681064, 'samples': 7770240, 'steps': 40469, 'loss/train': 1.645469307899475} 08/30/2021 20:28:40 - INFO - __main__ - Step 40471: {'lr': 0.0004211754571277313, 'samples': 7770432, 'steps': 40470, 'loss/train': 1.4317232370376587} 08/30/2021 20:28:41 - INFO - __main__ - Step 40472: {'lr': 0.0004211715894102272, 'samples': 7770624, 'steps': 40471, 'loss/train': 2.090947389602661} 08/30/2021 20:28:42 - INFO - __main__ - Step 40473: {'lr': 0.00042116772161559585, 'samples': 7770816, 'steps': 40472, 'loss/train': 1.602316975593567} 08/30/2021 20:28:43 - INFO - __main__ - Step 40474: {'lr': 0.0004211638537438389, 'samples': 7771008, 'steps': 40473, 'loss/train': 1.196723461151123} 08/30/2021 20:28:43 - INFO - __main__ - Step 40475: {'lr': 0.0004211599857949583, 'samples': 7771200, 'steps': 40474, 'loss/train': 1.0629518032073975} 08/30/2021 20:28:44 - INFO - __main__ - Step 40476: {'lr': 0.00042115611776895556, 'samples': 7771392, 'steps': 40475, 'loss/train': 1.3481874465942383} 08/30/2021 20:28:44 - INFO - __main__ - Step 40477: {'lr': 0.00042115224966583255, 'samples': 7771584, 'steps': 40476, 'loss/train': 1.5721675157546997} 08/30/2021 20:28:44 - INFO - __main__ - Step 40478: {'lr': 0.00042114838148559093, 'samples': 7771776, 'steps': 40477, 'loss/train': 1.6162680387496948} 08/30/2021 20:28:46 - INFO - __main__ - Step 40479: {'lr': 0.0004211445132282325, 'samples': 7771968, 'steps': 40478, 'loss/train': 2.3836116790771484} 08/30/2021 20:28:46 - INFO - __main__ - Step 40480: {'lr': 0.000421140644893759, 'samples': 7772160, 'steps': 40479, 'loss/train': 0.700352132320404} 08/30/2021 20:28:47 - INFO - __main__ - Step 40481: {'lr': 0.0004211367764821722, 'samples': 7772352, 'steps': 40480, 'loss/train': 1.353203296661377} 08/30/2021 20:28:47 - INFO - __main__ - Step 40482: {'lr': 0.00042113290799347376, 'samples': 7772544, 'steps': 40481, 'loss/train': 1.2763320207595825} 08/30/2021 20:28:47 - INFO - __main__ - Step 40483: {'lr': 0.00042112903942766546, 'samples': 7772736, 'steps': 40482, 'loss/train': 1.6155753135681152} 08/30/2021 20:28:49 - INFO - __main__ - Step 40484: {'lr': 0.00042112517078474914, 'samples': 7772928, 'steps': 40483, 'loss/train': 1.287023901939392} 08/30/2021 20:28:49 - INFO - __main__ - Step 40485: {'lr': 0.0004211213020647264, 'samples': 7773120, 'steps': 40484, 'loss/train': 0.597719132900238} 08/30/2021 20:28:50 - INFO - __main__ - Step 40486: {'lr': 0.00042111743326759903, 'samples': 7773312, 'steps': 40485, 'loss/train': 1.7989550828933716} 08/30/2021 20:28:50 - INFO - __main__ - Step 40487: {'lr': 0.00042111356439336877, 'samples': 7773504, 'steps': 40486, 'loss/train': 1.4463798999786377} 08/30/2021 20:28:50 - INFO - __main__ - Step 40488: {'lr': 0.0004211096954420375, 'samples': 7773696, 'steps': 40487, 'loss/train': 1.395016074180603} 08/30/2021 20:28:52 - INFO - __main__ - Step 40489: {'lr': 0.0004211058264136067, 'samples': 7773888, 'steps': 40488, 'loss/train': 1.35060715675354} 08/30/2021 20:28:52 - INFO - __main__ - Step 40490: {'lr': 0.0004211019573080783, 'samples': 7774080, 'steps': 40489, 'loss/train': 1.1428407430648804} 08/30/2021 20:28:53 - INFO - __main__ - Step 40491: {'lr': 0.00042109808812545405, 'samples': 7774272, 'steps': 40490, 'loss/train': 1.4952999353408813} 08/30/2021 20:28:53 - INFO - __main__ - Step 40492: {'lr': 0.0004210942188657356, 'samples': 7774464, 'steps': 40491, 'loss/train': 0.39101436734199524} 08/30/2021 20:28:53 - INFO - __main__ - Step 40493: {'lr': 0.00042109034952892473, 'samples': 7774656, 'steps': 40492, 'loss/train': 0.9900166988372803} 08/30/2021 20:28:55 - INFO - __main__ - Step 40494: {'lr': 0.00042108648011502314, 'samples': 7774848, 'steps': 40493, 'loss/train': 1.4828351736068726} 08/30/2021 20:28:55 - INFO - __main__ - Step 40495: {'lr': 0.00042108261062403276, 'samples': 7775040, 'steps': 40494, 'loss/train': 1.9816858768463135} 08/30/2021 20:28:55 - INFO - __main__ - Step 40496: {'lr': 0.00042107874105595507, 'samples': 7775232, 'steps': 40495, 'loss/train': 1.195799469947815} 08/30/2021 20:28:56 - INFO - __main__ - Step 40497: {'lr': 0.00042107487141079206, 'samples': 7775424, 'steps': 40496, 'loss/train': 0.9438231587409973} 08/30/2021 20:28:56 - INFO - __main__ - Step 40498: {'lr': 0.00042107100168854516, 'samples': 7775616, 'steps': 40497, 'loss/train': 1.4688013792037964} 08/30/2021 20:28:57 - INFO - __main__ - Step 40499: {'lr': 0.00042106713188921647, 'samples': 7775808, 'steps': 40498, 'loss/train': 1.4553735256195068} 08/30/2021 20:28:59 - INFO - __main__ - Step 40500: {'lr': 0.00042106326201280756, 'samples': 7776000, 'steps': 40499, 'loss/train': 0.4389041066169739} 08/30/2021 20:28:59 - INFO - __main__ - Step 40501: {'lr': 0.0004210593920593201, 'samples': 7776192, 'steps': 40500, 'loss/train': 1.2959622144699097} 08/30/2021 20:29:00 - INFO - __main__ - Step 40502: {'lr': 0.000421055522028756, 'samples': 7776384, 'steps': 40501, 'loss/train': 1.405869960784912} 08/30/2021 20:29:00 - INFO - __main__ - Step 40503: {'lr': 0.00042105165192111684, 'samples': 7776576, 'steps': 40502, 'loss/train': 1.3999860286712646} 08/30/2021 20:29:01 - INFO - __main__ - Step 40504: {'lr': 0.00042104778173640453, 'samples': 7776768, 'steps': 40503, 'loss/train': 1.0617791414260864} 08/30/2021 20:29:01 - INFO - __main__ - Step 40505: {'lr': 0.0004210439114746206, 'samples': 7776960, 'steps': 40504, 'loss/train': 0.5073390007019043} 08/30/2021 20:29:01 - INFO - __main__ - Step 40506: {'lr': 0.00042104004113576707, 'samples': 7777152, 'steps': 40505, 'loss/train': 0.43421733379364014} 08/30/2021 20:29:03 - INFO - __main__ - Step 40507: {'lr': 0.00042103617071984544, 'samples': 7777344, 'steps': 40506, 'loss/train': 0.43527668714523315} 08/30/2021 20:29:03 - INFO - __main__ - Step 40508: {'lr': 0.00042103230022685765, 'samples': 7777536, 'steps': 40507, 'loss/train': 1.2526508569717407} 08/30/2021 20:29:04 - INFO - __main__ - Step 40509: {'lr': 0.0004210284296568052, 'samples': 7777728, 'steps': 40508, 'loss/train': 1.5543291568756104} 08/30/2021 20:29:04 - INFO - __main__ - Step 40510: {'lr': 0.0004210245590096901, 'samples': 7777920, 'steps': 40509, 'loss/train': 1.6170828342437744} 08/30/2021 20:29:04 - INFO - __main__ - Step 40511: {'lr': 0.000421020688285514, 'samples': 7778112, 'steps': 40510, 'loss/train': 1.6495461463928223} 08/30/2021 20:29:06 - INFO - __main__ - Step 40512: {'lr': 0.0004210168174842785, 'samples': 7778304, 'steps': 40511, 'loss/train': 1.6361174583435059} 08/30/2021 20:29:06 - INFO - __main__ - Step 40513: {'lr': 0.00042101294660598556, 'samples': 7778496, 'steps': 40512, 'loss/train': 1.4974020719528198} 08/30/2021 20:29:07 - INFO - __main__ - Step 40514: {'lr': 0.0004210090756506367, 'samples': 7778688, 'steps': 40513, 'loss/train': 1.6260173320770264} 08/30/2021 20:29:07 - INFO - __main__ - Step 40515: {'lr': 0.0004210052046182339, 'samples': 7778880, 'steps': 40514, 'loss/train': 1.3380181789398193} 08/30/2021 20:29:07 - INFO - __main__ - Step 40516: {'lr': 0.0004210013335087787, 'samples': 7779072, 'steps': 40515, 'loss/train': 1.1280826330184937} 08/30/2021 20:29:09 - INFO - __main__ - Step 40517: {'lr': 0.000420997462322273, 'samples': 7779264, 'steps': 40516, 'loss/train': 1.1551539897918701} 08/30/2021 20:29:10 - INFO - __main__ - Step 40518: {'lr': 0.00042099359105871856, 'samples': 7779456, 'steps': 40517, 'loss/train': 2.428903341293335} 08/30/2021 20:29:10 - INFO - __main__ - Step 40519: {'lr': 0.00042098971971811695, 'samples': 7779648, 'steps': 40518, 'loss/train': 0.9138599634170532} 08/30/2021 20:29:10 - INFO - __main__ - Step 40520: {'lr': 0.00042098584830047004, 'samples': 7779840, 'steps': 40519, 'loss/train': 1.2494220733642578} 08/30/2021 20:29:11 - INFO - __main__ - Step 40521: {'lr': 0.00042098197680577956, 'samples': 7780032, 'steps': 40520, 'loss/train': 1.0672250986099243} 08/30/2021 20:29:13 - INFO - __main__ - Step 40522: {'lr': 0.00042097810523404714, 'samples': 7780224, 'steps': 40521, 'loss/train': 1.3310288190841675} 08/30/2021 20:29:13 - INFO - __main__ - Step 40523: {'lr': 0.0004209742335852747, 'samples': 7780416, 'steps': 40522, 'loss/train': 1.6031845808029175} 08/30/2021 20:29:14 - INFO - __main__ - Step 40524: {'lr': 0.0004209703618594639, 'samples': 7780608, 'steps': 40523, 'loss/train': 1.6723653078079224} 08/30/2021 20:29:14 - INFO - __main__ - Step 40525: {'lr': 0.00042096649005661654, 'samples': 7780800, 'steps': 40524, 'loss/train': 1.7833189964294434} 08/30/2021 20:29:14 - INFO - __main__ - Step 40526: {'lr': 0.00042096261817673423, 'samples': 7780992, 'steps': 40525, 'loss/train': 1.3080673217773438} 08/30/2021 20:29:16 - INFO - __main__ - Step 40527: {'lr': 0.0004209587462198189, 'samples': 7781184, 'steps': 40526, 'loss/train': 1.0665901899337769} 08/30/2021 20:29:16 - INFO - __main__ - Step 40528: {'lr': 0.0004209548741858721, 'samples': 7781376, 'steps': 40527, 'loss/train': 1.4239306449890137} 08/30/2021 20:29:17 - INFO - __main__ - Step 40529: {'lr': 0.00042095100207489573, 'samples': 7781568, 'steps': 40528, 'loss/train': 1.3944056034088135} 08/30/2021 20:29:17 - INFO - __main__ - Step 40530: {'lr': 0.0004209471298868914, 'samples': 7781760, 'steps': 40529, 'loss/train': 1.9133447408676147} 08/30/2021 20:29:17 - INFO - __main__ - Step 40531: {'lr': 0.00042094325762186103, 'samples': 7781952, 'steps': 40530, 'loss/train': 2.0818612575531006} 08/30/2021 20:29:18 - INFO - __main__ - Step 40532: {'lr': 0.0004209393852798062, 'samples': 7782144, 'steps': 40531, 'loss/train': 1.2844743728637695} 08/30/2021 20:29:19 - INFO - __main__ - Step 40533: {'lr': 0.00042093551286072887, 'samples': 7782336, 'steps': 40532, 'loss/train': 1.804255723953247} 08/30/2021 20:29:20 - INFO - __main__ - Step 40534: {'lr': 0.00042093164036463045, 'samples': 7782528, 'steps': 40533, 'loss/train': 1.6033272743225098} 08/30/2021 20:29:20 - INFO - __main__ - Step 40535: {'lr': 0.0004209277677915129, 'samples': 7782720, 'steps': 40534, 'loss/train': 0.6958231329917908} 08/30/2021 20:29:21 - INFO - __main__ - Step 40536: {'lr': 0.000420923895141378, 'samples': 7782912, 'steps': 40535, 'loss/train': 1.510439157485962} 08/30/2021 20:29:21 - INFO - __main__ - Step 40537: {'lr': 0.0004209200224142274, 'samples': 7783104, 'steps': 40536, 'loss/train': 1.6485573053359985} 08/30/2021 20:29:22 - INFO - __main__ - Step 40538: {'lr': 0.0004209161496100629, 'samples': 7783296, 'steps': 40537, 'loss/train': 1.9332777261734009} 08/30/2021 20:29:23 - INFO - __main__ - Step 40539: {'lr': 0.00042091227672888624, 'samples': 7783488, 'steps': 40538, 'loss/train': 1.284566879272461} 08/30/2021 20:29:23 - INFO - __main__ - Step 40540: {'lr': 0.00042090840377069906, 'samples': 7783680, 'steps': 40539, 'loss/train': 1.3033260107040405} 08/30/2021 20:29:24 - INFO - __main__ - Step 40541: {'lr': 0.00042090453073550323, 'samples': 7783872, 'steps': 40540, 'loss/train': 1.5416302680969238} 08/30/2021 20:29:24 - INFO - __main__ - Step 40542: {'lr': 0.0004209006576233004, 'samples': 7784064, 'steps': 40541, 'loss/train': 1.5478184223175049} 08/30/2021 20:29:26 - INFO - __main__ - Step 40543: {'lr': 0.0004208967844340925, 'samples': 7784256, 'steps': 40542, 'loss/train': 1.293800950050354} 08/30/2021 20:29:26 - INFO - __main__ - Step 40544: {'lr': 0.0004208929111678811, 'samples': 7784448, 'steps': 40543, 'loss/train': 1.3689665794372559} 08/30/2021 20:29:26 - INFO - __main__ - Step 40545: {'lr': 0.0004208890378246679, 'samples': 7784640, 'steps': 40544, 'loss/train': 0.8256595134735107} 08/30/2021 20:29:27 - INFO - __main__ - Step 40546: {'lr': 0.00042088516440445486, 'samples': 7784832, 'steps': 40545, 'loss/train': 1.716766357421875} 08/30/2021 20:29:27 - INFO - __main__ - Step 40547: {'lr': 0.0004208812909072435, 'samples': 7785024, 'steps': 40546, 'loss/train': 1.1976085901260376} 08/30/2021 20:29:28 - INFO - __main__ - Step 40548: {'lr': 0.00042087741733303575, 'samples': 7785216, 'steps': 40547, 'loss/train': 1.2565360069274902} 08/30/2021 20:29:29 - INFO - __main__ - Step 40549: {'lr': 0.00042087354368183316, 'samples': 7785408, 'steps': 40548, 'loss/train': 1.0759553909301758} 08/30/2021 20:29:29 - INFO - __main__ - Step 40550: {'lr': 0.00042086966995363774, 'samples': 7785600, 'steps': 40549, 'loss/train': 1.431450366973877} 08/30/2021 20:29:30 - INFO - __main__ - Step 40551: {'lr': 0.000420865796148451, 'samples': 7785792, 'steps': 40550, 'loss/train': 1.3393325805664062} 08/30/2021 20:29:30 - INFO - __main__ - Step 40552: {'lr': 0.00042086192226627476, 'samples': 7785984, 'steps': 40551, 'loss/train': 1.5410536527633667} 08/30/2021 20:29:31 - INFO - __main__ - Step 40553: {'lr': 0.00042085804830711084, 'samples': 7786176, 'steps': 40552, 'loss/train': 1.4146901369094849} 08/30/2021 20:29:32 - INFO - __main__ - Step 40554: {'lr': 0.00042085417427096085, 'samples': 7786368, 'steps': 40553, 'loss/train': 0.5668691396713257} 08/30/2021 20:29:32 - INFO - __main__ - Step 40555: {'lr': 0.0004208503001578266, 'samples': 7786560, 'steps': 40554, 'loss/train': 1.485809087753296} 08/30/2021 20:29:33 - INFO - __main__ - Step 40556: {'lr': 0.00042084642596770984, 'samples': 7786752, 'steps': 40555, 'loss/train': 0.9962664246559143} 08/30/2021 20:29:33 - INFO - __main__ - Step 40557: {'lr': 0.0004208425517006124, 'samples': 7786944, 'steps': 40556, 'loss/train': 1.43374502658844} 08/30/2021 20:29:35 - INFO - __main__ - Step 40558: {'lr': 0.0004208386773565359, 'samples': 7787136, 'steps': 40557, 'loss/train': 1.6456314325332642} 08/30/2021 20:29:35 - INFO - __main__ - Step 40559: {'lr': 0.0004208348029354821, 'samples': 7787328, 'steps': 40558, 'loss/train': 1.6254279613494873} 08/30/2021 20:29:35 - INFO - __main__ - Step 40560: {'lr': 0.00042083092843745275, 'samples': 7787520, 'steps': 40559, 'loss/train': 1.1712114810943604} 08/30/2021 20:29:36 - INFO - __main__ - Step 40561: {'lr': 0.0004208270538624497, 'samples': 7787712, 'steps': 40560, 'loss/train': 1.325748085975647} 08/30/2021 20:29:36 - INFO - __main__ - Step 40562: {'lr': 0.00042082317921047455, 'samples': 7787904, 'steps': 40561, 'loss/train': 0.9385061264038086} 08/30/2021 20:29:37 - INFO - __main__ - Step 40563: {'lr': 0.0004208193044815291, 'samples': 7788096, 'steps': 40562, 'loss/train': 1.8918570280075073} 08/30/2021 20:29:38 - INFO - __main__ - Step 40564: {'lr': 0.0004208154296756152, 'samples': 7788288, 'steps': 40563, 'loss/train': 1.2039144039154053} 08/30/2021 20:29:38 - INFO - __main__ - Step 40565: {'lr': 0.0004208115547927345, 'samples': 7788480, 'steps': 40564, 'loss/train': 1.1967377662658691} 08/30/2021 20:29:39 - INFO - __main__ - Step 40566: {'lr': 0.0004208076798328886, 'samples': 7788672, 'steps': 40565, 'loss/train': 1.9980802536010742} 08/30/2021 20:29:39 - INFO - __main__ - Step 40567: {'lr': 0.00042080380479607947, 'samples': 7788864, 'steps': 40566, 'loss/train': 1.5531868934631348} 08/30/2021 20:29:40 - INFO - __main__ - Step 40568: {'lr': 0.00042079992968230886, 'samples': 7789056, 'steps': 40567, 'loss/train': 1.3410086631774902} 08/30/2021 20:29:41 - INFO - __main__ - Step 40569: {'lr': 0.0004207960544915784, 'samples': 7789248, 'steps': 40568, 'loss/train': 1.0361840724945068} 08/30/2021 20:29:41 - INFO - __main__ - Step 40570: {'lr': 0.0004207921792238898, 'samples': 7789440, 'steps': 40569, 'loss/train': 1.177603840827942} 08/30/2021 20:29:42 - INFO - __main__ - Step 40571: {'lr': 0.0004207883038792449, 'samples': 7789632, 'steps': 40570, 'loss/train': 1.1117411851882935} 08/30/2021 20:29:42 - INFO - __main__ - Step 40572: {'lr': 0.0004207844284576455, 'samples': 7789824, 'steps': 40571, 'loss/train': 1.6639740467071533} 08/30/2021 20:29:44 - INFO - __main__ - Step 40573: {'lr': 0.0004207805529590932, 'samples': 7790016, 'steps': 40572, 'loss/train': 1.3262563943862915} 08/30/2021 20:29:44 - INFO - __main__ - Step 40574: {'lr': 0.0004207766773835899, 'samples': 7790208, 'steps': 40573, 'loss/train': 0.8548374176025391} 08/30/2021 20:29:45 - INFO - __main__ - Step 40575: {'lr': 0.0004207728017311372, 'samples': 7790400, 'steps': 40574, 'loss/train': 1.327256679534912} 08/30/2021 20:29:45 - INFO - __main__ - Step 40576: {'lr': 0.0004207689260017369, 'samples': 7790592, 'steps': 40575, 'loss/train': 1.304694652557373} 08/30/2021 20:29:46 - INFO - __main__ - Step 40577: {'lr': 0.0004207650501953908, 'samples': 7790784, 'steps': 40576, 'loss/train': 1.0193008184432983} 08/30/2021 20:29:47 - INFO - __main__ - Step 40578: {'lr': 0.0004207611743121006, 'samples': 7790976, 'steps': 40577, 'loss/train': 1.682633876800537} 08/30/2021 20:29:48 - INFO - __main__ - Step 40579: {'lr': 0.00042075729835186807, 'samples': 7791168, 'steps': 40578, 'loss/train': 1.562943458557129} 08/30/2021 20:29:48 - INFO - __main__ - Step 40580: {'lr': 0.0004207534223146948, 'samples': 7791360, 'steps': 40579, 'loss/train': 1.6095415353775024} 08/30/2021 20:29:48 - INFO - __main__ - Step 40581: {'lr': 0.0004207495462005828, 'samples': 7791552, 'steps': 40580, 'loss/train': 1.4702998399734497} 08/30/2021 20:29:49 - INFO - __main__ - Step 40582: {'lr': 0.0004207456700095337, 'samples': 7791744, 'steps': 40581, 'loss/train': 0.8661431074142456} 08/30/2021 20:29:50 - INFO - __main__ - Step 40583: {'lr': 0.0004207417937415492, 'samples': 7791936, 'steps': 40582, 'loss/train': 1.81490957736969} 08/30/2021 20:29:51 - INFO - __main__ - Step 40584: {'lr': 0.000420737917396631, 'samples': 7792128, 'steps': 40583, 'loss/train': 1.5431385040283203} 08/30/2021 20:29:51 - INFO - __main__ - Step 40585: {'lr': 0.00042073404097478105, 'samples': 7792320, 'steps': 40584, 'loss/train': 1.380693793296814} 08/30/2021 20:29:51 - INFO - __main__ - Step 40586: {'lr': 0.000420730164476001, 'samples': 7792512, 'steps': 40585, 'loss/train': 1.7884832620620728} 08/30/2021 20:29:52 - INFO - __main__ - Step 40587: {'lr': 0.00042072628790029243, 'samples': 7792704, 'steps': 40586, 'loss/train': 1.7218916416168213} 08/30/2021 20:29:52 - INFO - __main__ - Step 40588: {'lr': 0.0004207224112476573, 'samples': 7792896, 'steps': 40587, 'loss/train': 1.5347225666046143} 08/30/2021 20:29:53 - INFO - __main__ - Step 40589: {'lr': 0.0004207185345180973, 'samples': 7793088, 'steps': 40588, 'loss/train': 1.5618696212768555} 08/30/2021 20:29:54 - INFO - __main__ - Step 40590: {'lr': 0.00042071465771161416, 'samples': 7793280, 'steps': 40589, 'loss/train': 2.105295419692993} 08/30/2021 20:29:54 - INFO - __main__ - Step 40591: {'lr': 0.0004207107808282097, 'samples': 7793472, 'steps': 40590, 'loss/train': 1.6732038259506226} 08/30/2021 20:29:54 - INFO - __main__ - Step 40592: {'lr': 0.00042070690386788545, 'samples': 7793664, 'steps': 40591, 'loss/train': 1.551571011543274} 08/30/2021 20:29:55 - INFO - __main__ - Step 40593: {'lr': 0.0004207030268306434, 'samples': 7793856, 'steps': 40592, 'loss/train': 1.283904790878296} 08/30/2021 20:29:56 - INFO - __main__ - Step 40594: {'lr': 0.00042069914971648516, 'samples': 7794048, 'steps': 40593, 'loss/train': 1.5216953754425049} 08/30/2021 20:29:57 - INFO - __main__ - Step 40595: {'lr': 0.0004206952725254125, 'samples': 7794240, 'steps': 40594, 'loss/train': 1.1923627853393555} 08/30/2021 20:29:57 - INFO - __main__ - Step 40596: {'lr': 0.00042069139525742727, 'samples': 7794432, 'steps': 40595, 'loss/train': 0.9968594908714294} 08/30/2021 20:29:57 - INFO - __main__ - Step 40597: {'lr': 0.000420687517912531, 'samples': 7794624, 'steps': 40596, 'loss/train': 1.4605414867401123} 08/30/2021 20:29:58 - INFO - __main__ - Step 40598: {'lr': 0.0004206836404907257, 'samples': 7794816, 'steps': 40597, 'loss/train': 0.6130566000938416} 08/30/2021 20:29:59 - INFO - __main__ - Step 40599: {'lr': 0.0004206797629920129, 'samples': 7795008, 'steps': 40598, 'loss/train': 1.4869836568832397} 08/30/2021 20:30:00 - INFO - __main__ - Step 40600: {'lr': 0.0004206758854163945, 'samples': 7795200, 'steps': 40599, 'loss/train': 1.494636058807373} 08/30/2021 20:30:00 - INFO - __main__ - Step 40601: {'lr': 0.00042067200776387215, 'samples': 7795392, 'steps': 40600, 'loss/train': 1.434457540512085} 08/30/2021 20:30:00 - INFO - __main__ - Step 40602: {'lr': 0.0004206681300344476, 'samples': 7795584, 'steps': 40601, 'loss/train': 1.4297521114349365} 08/30/2021 20:30:01 - INFO - __main__ - Step 40603: {'lr': 0.0004206642522281227, 'samples': 7795776, 'steps': 40602, 'loss/train': 1.6480880975723267} 08/30/2021 20:30:02 - INFO - __main__ - Step 40604: {'lr': 0.000420660374344899, 'samples': 7795968, 'steps': 40603, 'loss/train': 0.9270496964454651} 08/30/2021 20:30:03 - INFO - __main__ - Step 40605: {'lr': 0.00042065649638477843, 'samples': 7796160, 'steps': 40604, 'loss/train': 1.1310598850250244} 08/30/2021 20:30:03 - INFO - __main__ - Step 40606: {'lr': 0.0004206526183477627, 'samples': 7796352, 'steps': 40605, 'loss/train': 1.1386243104934692} 08/30/2021 20:30:03 - INFO - __main__ - Step 40607: {'lr': 0.0004206487402338535, 'samples': 7796544, 'steps': 40606, 'loss/train': 0.95960533618927} 08/30/2021 20:30:04 - INFO - __main__ - Step 40608: {'lr': 0.00042064486204305263, 'samples': 7796736, 'steps': 40607, 'loss/train': 1.4682912826538086} 08/30/2021 20:30:05 - INFO - __main__ - Step 40609: {'lr': 0.0004206409837753618, 'samples': 7796928, 'steps': 40608, 'loss/train': 1.5144367218017578} 08/30/2021 20:30:06 - INFO - __main__ - Step 40610: {'lr': 0.00042063710543078283, 'samples': 7797120, 'steps': 40609, 'loss/train': 1.1375278234481812} 08/30/2021 20:30:06 - INFO - __main__ - Step 40611: {'lr': 0.00042063322700931733, 'samples': 7797312, 'steps': 40610, 'loss/train': 1.7519469261169434} 08/30/2021 20:30:07 - INFO - __main__ - Step 40612: {'lr': 0.0004206293485109672, 'samples': 7797504, 'steps': 40611, 'loss/train': 1.4417210817337036} 08/30/2021 20:30:07 - INFO - __main__ - Step 40613: {'lr': 0.0004206254699357341, 'samples': 7797696, 'steps': 40612, 'loss/train': 1.1510708332061768} 08/30/2021 20:30:07 - INFO - __main__ - Step 40614: {'lr': 0.00042062159128361976, 'samples': 7797888, 'steps': 40613, 'loss/train': 0.03064132109284401} 08/30/2021 20:30:09 - INFO - __main__ - Step 40615: {'lr': 0.000420617712554626, 'samples': 7798080, 'steps': 40614, 'loss/train': 1.5406118631362915} 08/30/2021 20:30:09 - INFO - __main__ - Step 40616: {'lr': 0.0004206138337487545, 'samples': 7798272, 'steps': 40615, 'loss/train': 1.668717622756958} 08/30/2021 20:30:10 - INFO - __main__ - Step 40617: {'lr': 0.0004206099548660071, 'samples': 7798464, 'steps': 40616, 'loss/train': 1.5844056606292725} 08/30/2021 20:30:10 - INFO - __main__ - Step 40618: {'lr': 0.00042060607590638547, 'samples': 7798656, 'steps': 40617, 'loss/train': 1.5757007598876953} 08/30/2021 20:30:10 - INFO - __main__ - Step 40619: {'lr': 0.00042060219686989133, 'samples': 7798848, 'steps': 40618, 'loss/train': 1.5157809257507324} 08/30/2021 20:30:12 - INFO - __main__ - Step 40620: {'lr': 0.00042059831775652644, 'samples': 7799040, 'steps': 40619, 'loss/train': 1.8588722944259644} 08/30/2021 20:30:12 - INFO - __main__ - Step 40621: {'lr': 0.00042059443856629265, 'samples': 7799232, 'steps': 40620, 'loss/train': 0.05576677620410919} 08/30/2021 20:30:13 - INFO - __main__ - Step 40622: {'lr': 0.00042059055929919163, 'samples': 7799424, 'steps': 40621, 'loss/train': 2.0204005241394043} 08/30/2021 20:30:13 - INFO - __main__ - Step 40623: {'lr': 0.00042058667995522513, 'samples': 7799616, 'steps': 40622, 'loss/train': 0.38546594977378845} 08/30/2021 20:30:13 - INFO - __main__ - Step 40624: {'lr': 0.0004205828005343949, 'samples': 7799808, 'steps': 40623, 'loss/train': 1.2320804595947266} 08/30/2021 20:30:14 - INFO - __main__ - Step 40625: {'lr': 0.00042057892103670275, 'samples': 7800000, 'steps': 40624, 'loss/train': 1.3380446434020996} 08/30/2021 20:30:16 - INFO - __main__ - Step 40626: {'lr': 0.0004205750414621503, 'samples': 7800192, 'steps': 40625, 'loss/train': 1.481024146080017} 08/30/2021 20:30:16 - INFO - __main__ - Step 40627: {'lr': 0.0004205711618107394, 'samples': 7800384, 'steps': 40626, 'loss/train': 1.230425238609314} 08/30/2021 20:30:17 - INFO - __main__ - Step 40628: {'lr': 0.00042056728208247175, 'samples': 7800576, 'steps': 40627, 'loss/train': 0.9796714782714844} 08/30/2021 20:30:17 - INFO - __main__ - Step 40629: {'lr': 0.0004205634022773491, 'samples': 7800768, 'steps': 40628, 'loss/train': 1.3274792432785034} 08/30/2021 20:30:17 - INFO - __main__ - Step 40630: {'lr': 0.0004205595223953732, 'samples': 7800960, 'steps': 40629, 'loss/train': 1.756373405456543} 08/30/2021 20:30:19 - INFO - __main__ - Step 40631: {'lr': 0.0004205556424365459, 'samples': 7801152, 'steps': 40630, 'loss/train': 0.5165131092071533} 08/30/2021 20:30:19 - INFO - __main__ - Step 40632: {'lr': 0.0004205517624008688, 'samples': 7801344, 'steps': 40631, 'loss/train': 1.3324552774429321} 08/30/2021 20:30:20 - INFO - __main__ - Step 40633: {'lr': 0.00042054788228834374, 'samples': 7801536, 'steps': 40632, 'loss/train': 1.2723091840744019} 08/30/2021 20:30:20 - INFO - __main__ - Step 40634: {'lr': 0.0004205440020989724, 'samples': 7801728, 'steps': 40633, 'loss/train': 1.8608767986297607} 08/30/2021 20:30:20 - INFO - __main__ - Step 40635: {'lr': 0.0004205401218327565, 'samples': 7801920, 'steps': 40634, 'loss/train': 0.1952928751707077} 08/30/2021 20:30:22 - INFO - __main__ - Step 40636: {'lr': 0.0004205362414896979, 'samples': 7802112, 'steps': 40635, 'loss/train': 1.4910147190093994} 08/30/2021 20:30:22 - INFO - __main__ - Step 40637: {'lr': 0.0004205323610697984, 'samples': 7802304, 'steps': 40636, 'loss/train': 1.6579813957214355} 08/30/2021 20:30:23 - INFO - __main__ - Step 40638: {'lr': 0.0004205284805730596, 'samples': 7802496, 'steps': 40637, 'loss/train': 1.6472336053848267} 08/30/2021 20:30:23 - INFO - __main__ - Step 40639: {'lr': 0.00042052459999948323, 'samples': 7802688, 'steps': 40638, 'loss/train': 1.7449266910552979} 08/30/2021 20:30:23 - INFO - __main__ - Step 40640: {'lr': 0.00042052071934907116, 'samples': 7802880, 'steps': 40639, 'loss/train': 1.3850665092468262} 08/30/2021 20:30:25 - INFO - __main__ - Step 40641: {'lr': 0.00042051683862182504, 'samples': 7803072, 'steps': 40640, 'loss/train': 1.5129368305206299} 08/30/2021 20:30:25 - INFO - __main__ - Step 40642: {'lr': 0.0004205129578177467, 'samples': 7803264, 'steps': 40641, 'loss/train': 1.6151237487792969} 08/30/2021 20:30:26 - INFO - __main__ - Step 40643: {'lr': 0.0004205090769368379, 'samples': 7803456, 'steps': 40642, 'loss/train': 1.2536816596984863} 08/30/2021 20:30:26 - INFO - __main__ - Step 40644: {'lr': 0.00042050519597910024, 'samples': 7803648, 'steps': 40643, 'loss/train': 1.6010931730270386} 08/30/2021 20:30:26 - INFO - __main__ - Step 40645: {'lr': 0.00042050131494453567, 'samples': 7803840, 'steps': 40644, 'loss/train': 1.305932641029358} 08/30/2021 20:30:28 - INFO - __main__ - Step 40646: {'lr': 0.00042049743383314577, 'samples': 7804032, 'steps': 40645, 'loss/train': 1.2957103252410889} 08/30/2021 20:30:28 - INFO - __main__ - Step 40647: {'lr': 0.0004204935526449324, 'samples': 7804224, 'steps': 40646, 'loss/train': 1.4285246133804321} 08/30/2021 20:30:28 - INFO - __main__ - Step 40648: {'lr': 0.0004204896713798972, 'samples': 7804416, 'steps': 40647, 'loss/train': 1.6725188493728638} 08/30/2021 20:30:29 - INFO - __main__ - Step 40649: {'lr': 0.00042048579003804205, 'samples': 7804608, 'steps': 40648, 'loss/train': 1.425777792930603} 08/30/2021 20:30:29 - INFO - __main__ - Step 40650: {'lr': 0.00042048190861936866, 'samples': 7804800, 'steps': 40649, 'loss/train': 1.3483316898345947} 08/30/2021 20:30:29 - INFO - __main__ - Step 40651: {'lr': 0.0004204780271238786, 'samples': 7804992, 'steps': 40650, 'loss/train': 1.0939075946807861} 08/30/2021 20:30:31 - INFO - __main__ - Step 40652: {'lr': 0.00042047414555157394, 'samples': 7805184, 'steps': 40651, 'loss/train': 1.7882989645004272} 08/30/2021 20:30:31 - INFO - __main__ - Step 40653: {'lr': 0.0004204702639024562, 'samples': 7805376, 'steps': 40652, 'loss/train': 1.6279653310775757} 08/30/2021 20:30:32 - INFO - __main__ - Step 40654: {'lr': 0.00042046638217652717, 'samples': 7805568, 'steps': 40653, 'loss/train': 1.6124012470245361} 08/30/2021 20:30:32 - INFO - __main__ - Step 40655: {'lr': 0.00042046250037378865, 'samples': 7805760, 'steps': 40654, 'loss/train': 2.157416820526123} 08/30/2021 20:30:33 - INFO - __main__ - Step 40656: {'lr': 0.0004204586184942423, 'samples': 7805952, 'steps': 40655, 'loss/train': 1.045082926750183} 08/30/2021 20:30:34 - INFO - __main__ - Step 40657: {'lr': 0.00042045473653789004, 'samples': 7806144, 'steps': 40656, 'loss/train': 0.9390610456466675} 08/30/2021 20:30:34 - INFO - __main__ - Step 40658: {'lr': 0.00042045085450473336, 'samples': 7806336, 'steps': 40657, 'loss/train': 0.6429643630981445} 08/30/2021 20:30:35 - INFO - __main__ - Step 40659: {'lr': 0.00042044697239477423, 'samples': 7806528, 'steps': 40658, 'loss/train': 0.7809738516807556} 08/30/2021 20:30:35 - INFO - __main__ - Step 40660: {'lr': 0.00042044309020801434, 'samples': 7806720, 'steps': 40659, 'loss/train': 1.6725441217422485} 08/30/2021 20:30:35 - INFO - __main__ - Step 40661: {'lr': 0.00042043920794445543, 'samples': 7806912, 'steps': 40660, 'loss/train': 1.09107506275177} 08/30/2021 20:30:37 - INFO - __main__ - Step 40662: {'lr': 0.0004204353256040992, 'samples': 7807104, 'steps': 40661, 'loss/train': 0.2506924569606781} 08/30/2021 20:30:38 - INFO - __main__ - Step 40663: {'lr': 0.0004204314431869475, 'samples': 7807296, 'steps': 40662, 'loss/train': 1.3914165496826172} 08/30/2021 20:30:38 - INFO - __main__ - Step 40664: {'lr': 0.0004204275606930019, 'samples': 7807488, 'steps': 40663, 'loss/train': 0.08640512824058533} 08/30/2021 20:30:38 - INFO - __main__ - Step 40665: {'lr': 0.00042042367812226446, 'samples': 7807680, 'steps': 40664, 'loss/train': 1.6619248390197754} 08/30/2021 20:30:39 - INFO - __main__ - Step 40666: {'lr': 0.00042041979547473665, 'samples': 7807872, 'steps': 40665, 'loss/train': 1.1679056882858276} 08/30/2021 20:30:40 - INFO - __main__ - Step 40667: {'lr': 0.0004204159127504202, 'samples': 7808064, 'steps': 40666, 'loss/train': 1.5541876554489136} 08/30/2021 20:30:41 - INFO - __main__ - Step 40668: {'lr': 0.0004204120299493171, 'samples': 7808256, 'steps': 40667, 'loss/train': 1.4965434074401855} 08/30/2021 20:30:41 - INFO - __main__ - Step 40669: {'lr': 0.0004204081470714289, 'samples': 7808448, 'steps': 40668, 'loss/train': 2.0811808109283447} 08/30/2021 20:30:41 - INFO - __main__ - Step 40670: {'lr': 0.00042040426411675747, 'samples': 7808640, 'steps': 40669, 'loss/train': 1.2840136289596558} 08/30/2021 20:30:42 - INFO - __main__ - Step 40671: {'lr': 0.0004204003810853045, 'samples': 7808832, 'steps': 40670, 'loss/train': 1.9235584735870361} 08/30/2021 20:30:43 - INFO - __main__ - Step 40672: {'lr': 0.00042039649797707176, 'samples': 7809024, 'steps': 40671, 'loss/train': 1.5719984769821167} 08/30/2021 20:30:44 - INFO - __main__ - Step 40673: {'lr': 0.0004203926147920609, 'samples': 7809216, 'steps': 40672, 'loss/train': 1.508525013923645} 08/30/2021 20:30:44 - INFO - __main__ - Step 40674: {'lr': 0.0004203887315302739, 'samples': 7809408, 'steps': 40673, 'loss/train': 1.892645239830017} 08/30/2021 20:30:44 - INFO - __main__ - Step 40675: {'lr': 0.0004203848481917122, 'samples': 7809600, 'steps': 40674, 'loss/train': 1.736484408378601} 08/30/2021 20:30:45 - INFO - __main__ - Step 40676: {'lr': 0.00042038096477637786, 'samples': 7809792, 'steps': 40675, 'loss/train': 0.9497137069702148} 08/30/2021 20:30:46 - INFO - __main__ - Step 40677: {'lr': 0.00042037708128427243, 'samples': 7809984, 'steps': 40676, 'loss/train': 1.9614101648330688} 08/30/2021 20:30:47 - INFO - __main__ - Step 40678: {'lr': 0.00042037319771539775, 'samples': 7810176, 'steps': 40677, 'loss/train': 1.2367404699325562} 08/30/2021 20:30:47 - INFO - __main__ - Step 40679: {'lr': 0.00042036931406975547, 'samples': 7810368, 'steps': 40678, 'loss/train': 1.1385862827301025} 08/30/2021 20:30:48 - INFO - __main__ - Step 40680: {'lr': 0.0004203654303473474, 'samples': 7810560, 'steps': 40679, 'loss/train': 1.5016164779663086} 08/30/2021 20:30:48 - INFO - __main__ - Step 40681: {'lr': 0.0004203615465481754, 'samples': 7810752, 'steps': 40680, 'loss/train': 2.079608678817749} 08/30/2021 20:30:48 - INFO - __main__ - Step 40682: {'lr': 0.0004203576626722411, 'samples': 7810944, 'steps': 40681, 'loss/train': 1.6436620950698853} 08/30/2021 20:30:50 - INFO - __main__ - Step 40683: {'lr': 0.00042035377871954614, 'samples': 7811136, 'steps': 40682, 'loss/train': 1.5468770265579224} 08/30/2021 20:30:51 - INFO - __main__ - Step 40684: {'lr': 0.00042034989469009245, 'samples': 7811328, 'steps': 40683, 'loss/train': 1.3297398090362549} 08/30/2021 20:30:51 - INFO - __main__ - Step 40685: {'lr': 0.0004203460105838818, 'samples': 7811520, 'steps': 40684, 'loss/train': 1.8256430625915527} 08/30/2021 20:30:52 - INFO - __main__ - Step 40686: {'lr': 0.00042034212640091587, 'samples': 7811712, 'steps': 40685, 'loss/train': 1.199657917022705} 08/30/2021 20:30:52 - INFO - __main__ - Step 40687: {'lr': 0.00042033824214119633, 'samples': 7811904, 'steps': 40686, 'loss/train': 2.0564515590667725} 08/30/2021 20:30:53 - INFO - __main__ - Step 40688: {'lr': 0.00042033435780472494, 'samples': 7812096, 'steps': 40687, 'loss/train': 1.097558856010437} 08/30/2021 20:30:54 - INFO - __main__ - Step 40689: {'lr': 0.00042033047339150363, 'samples': 7812288, 'steps': 40688, 'loss/train': 1.2923438549041748} 08/30/2021 20:30:54 - INFO - __main__ - Step 40690: {'lr': 0.00042032658890153404, 'samples': 7812480, 'steps': 40689, 'loss/train': 1.314319372177124} 08/30/2021 20:30:55 - INFO - __main__ - Step 40691: {'lr': 0.0004203227043348179, 'samples': 7812672, 'steps': 40690, 'loss/train': 1.4398634433746338} 08/30/2021 20:30:55 - INFO - __main__ - Step 40692: {'lr': 0.000420318819691357, 'samples': 7812864, 'steps': 40691, 'loss/train': 1.1700912714004517} 08/30/2021 20:30:57 - INFO - __main__ - Step 40693: {'lr': 0.00042031493497115304, 'samples': 7813056, 'steps': 40692, 'loss/train': 1.6856290102005005} 08/30/2021 20:30:57 - INFO - __main__ - Step 40694: {'lr': 0.0004203110501742078, 'samples': 7813248, 'steps': 40693, 'loss/train': 1.530055046081543} 08/30/2021 20:30:57 - INFO - __main__ - Step 40695: {'lr': 0.00042030716530052297, 'samples': 7813440, 'steps': 40694, 'loss/train': 1.0971704721450806} 08/30/2021 20:30:58 - INFO - __main__ - Step 40696: {'lr': 0.00042030328035010047, 'samples': 7813632, 'steps': 40695, 'loss/train': 1.4052329063415527} 08/30/2021 20:30:58 - INFO - __main__ - Step 40697: {'lr': 0.0004202993953229418, 'samples': 7813824, 'steps': 40696, 'loss/train': 1.1811143159866333} 08/30/2021 20:30:58 - INFO - __main__ - Step 40698: {'lr': 0.000420295510219049, 'samples': 7814016, 'steps': 40697, 'loss/train': 1.4804872274398804} 08/30/2021 20:31:00 - INFO - __main__ - Step 40699: {'lr': 0.00042029162503842357, 'samples': 7814208, 'steps': 40698, 'loss/train': 1.4191936254501343} 08/30/2021 20:31:01 - INFO - __main__ - Step 40700: {'lr': 0.0004202877397810674, 'samples': 7814400, 'steps': 40699, 'loss/train': 1.951290249824524} 08/30/2021 20:31:01 - INFO - __main__ - Step 40701: {'lr': 0.0004202838544469822, 'samples': 7814592, 'steps': 40700, 'loss/train': 1.3045618534088135} 08/30/2021 20:31:01 - INFO - __main__ - Step 40702: {'lr': 0.00042027996903616974, 'samples': 7814784, 'steps': 40701, 'loss/train': 1.5571815967559814} 08/30/2021 20:31:02 - INFO - __main__ - Step 40703: {'lr': 0.0004202760835486317, 'samples': 7814976, 'steps': 40702, 'loss/train': 1.5170612335205078} 08/30/2021 20:31:03 - INFO - __main__ - Step 40704: {'lr': 0.00042027219798436996, 'samples': 7815168, 'steps': 40703, 'loss/train': 0.7151506543159485} 08/30/2021 20:31:04 - INFO - __main__ - Step 40705: {'lr': 0.00042026831234338614, 'samples': 7815360, 'steps': 40704, 'loss/train': 0.5749585628509521} 08/30/2021 20:31:04 - INFO - __main__ - Step 40706: {'lr': 0.0004202644266256821, 'samples': 7815552, 'steps': 40705, 'loss/train': 1.3966641426086426} 08/30/2021 20:31:04 - INFO - __main__ - Step 40707: {'lr': 0.00042026054083125943, 'samples': 7815744, 'steps': 40706, 'loss/train': 1.345969796180725} 08/30/2021 20:31:05 - INFO - __main__ - Step 40708: {'lr': 0.0004202566549601201, 'samples': 7815936, 'steps': 40707, 'loss/train': 1.4172412157058716} 08/30/2021 20:31:06 - INFO - __main__ - Step 40709: {'lr': 0.00042025276901226573, 'samples': 7816128, 'steps': 40708, 'loss/train': 1.7815989255905151} 08/30/2021 20:31:07 - INFO - __main__ - Step 40710: {'lr': 0.00042024888298769806, 'samples': 7816320, 'steps': 40709, 'loss/train': 1.5435044765472412} 08/30/2021 20:31:07 - INFO - __main__ - Step 40711: {'lr': 0.0004202449968864188, 'samples': 7816512, 'steps': 40710, 'loss/train': 1.2542626857757568} 08/30/2021 20:31:07 - INFO - __main__ - Step 40712: {'lr': 0.00042024111070842985, 'samples': 7816704, 'steps': 40711, 'loss/train': 1.5079811811447144} 08/30/2021 20:31:08 - INFO - __main__ - Step 40713: {'lr': 0.0004202372244537329, 'samples': 7816896, 'steps': 40712, 'loss/train': 1.2696741819381714} 08/30/2021 20:31:09 - INFO - __main__ - Step 40714: {'lr': 0.00042023333812232967, 'samples': 7817088, 'steps': 40713, 'loss/train': 1.3684004545211792} 08/30/2021 20:31:10 - INFO - __main__ - Step 40715: {'lr': 0.0004202294517142219, 'samples': 7817280, 'steps': 40714, 'loss/train': 1.5804187059402466} 08/30/2021 20:31:10 - INFO - __main__ - Step 40716: {'lr': 0.0004202255652294114, 'samples': 7817472, 'steps': 40715, 'loss/train': 1.6122698783874512} 08/30/2021 20:31:10 - INFO - __main__ - Step 40717: {'lr': 0.00042022167866789985, 'samples': 7817664, 'steps': 40716, 'loss/train': 1.394217610359192} 08/30/2021 20:31:11 - INFO - __main__ - Step 40718: {'lr': 0.00042021779202968903, 'samples': 7817856, 'steps': 40717, 'loss/train': 1.4484519958496094} 08/30/2021 20:31:12 - INFO - __main__ - Step 40719: {'lr': 0.0004202139053147808, 'samples': 7818048, 'steps': 40718, 'loss/train': 1.6146900653839111} 08/30/2021 20:31:13 - INFO - __main__ - Step 40720: {'lr': 0.0004202100185231767, 'samples': 7818240, 'steps': 40719, 'loss/train': 1.3560950756072998} 08/30/2021 20:31:13 - INFO - __main__ - Step 40721: {'lr': 0.00042020613165487863, 'samples': 7818432, 'steps': 40720, 'loss/train': 1.5143665075302124} 08/30/2021 20:31:13 - INFO - __main__ - Step 40722: {'lr': 0.0004202022447098883, 'samples': 7818624, 'steps': 40721, 'loss/train': 1.448867917060852} 08/30/2021 20:31:14 - INFO - __main__ - Step 40723: {'lr': 0.00042019835768820744, 'samples': 7818816, 'steps': 40722, 'loss/train': 0.8615542650222778} 08/30/2021 20:31:14 - INFO - __main__ - Step 40724: {'lr': 0.00042019447058983786, 'samples': 7819008, 'steps': 40723, 'loss/train': 1.5015555620193481} 08/30/2021 20:31:15 - INFO - __main__ - Step 40725: {'lr': 0.0004201905834147813, 'samples': 7819200, 'steps': 40724, 'loss/train': 1.515428066253662} 08/30/2021 20:31:16 - INFO - __main__ - Step 40726: {'lr': 0.0004201866961630395, 'samples': 7819392, 'steps': 40725, 'loss/train': 1.4868468046188354} 08/30/2021 20:31:16 - INFO - __main__ - Step 40727: {'lr': 0.00042018280883461415, 'samples': 7819584, 'steps': 40726, 'loss/train': 1.3024789094924927} 08/30/2021 20:31:17 - INFO - __main__ - Step 40728: {'lr': 0.000420178921429507, 'samples': 7819776, 'steps': 40727, 'loss/train': 2.0891103744506836} 08/30/2021 20:31:17 - INFO - __main__ - Step 40729: {'lr': 0.00042017503394771997, 'samples': 7819968, 'steps': 40728, 'loss/train': 1.2729058265686035} 08/30/2021 20:31:19 - INFO - __main__ - Step 40730: {'lr': 0.00042017114638925456, 'samples': 7820160, 'steps': 40729, 'loss/train': 1.5011334419250488} 08/30/2021 20:31:19 - INFO - __main__ - Step 40731: {'lr': 0.00042016725875411274, 'samples': 7820352, 'steps': 40730, 'loss/train': 1.2995166778564453} 08/30/2021 20:31:19 - INFO - __main__ - Step 40732: {'lr': 0.0004201633710422962, 'samples': 7820544, 'steps': 40731, 'loss/train': 2.2093710899353027} 08/30/2021 20:31:20 - INFO - __main__ - Step 40733: {'lr': 0.0004201594832538067, 'samples': 7820736, 'steps': 40732, 'loss/train': 0.3605997860431671} 08/30/2021 20:31:20 - INFO - __main__ - Step 40734: {'lr': 0.0004201555953886459, 'samples': 7820928, 'steps': 40733, 'loss/train': 1.5841865539550781} 08/30/2021 20:31:22 - INFO - __main__ - Step 40735: {'lr': 0.00042015170744681566, 'samples': 7821120, 'steps': 40734, 'loss/train': 1.6072136163711548} 08/30/2021 20:31:23 - INFO - __main__ - Step 40736: {'lr': 0.00042014781942831757, 'samples': 7821312, 'steps': 40735, 'loss/train': 1.4822163581848145} 08/30/2021 20:31:23 - INFO - __main__ - Step 40737: {'lr': 0.00042014393133315366, 'samples': 7821504, 'steps': 40736, 'loss/train': 1.812747597694397} 08/30/2021 20:31:23 - INFO - __main__ - Step 40738: {'lr': 0.00042014004316132537, 'samples': 7821696, 'steps': 40737, 'loss/train': 1.6188654899597168} 08/30/2021 20:31:24 - INFO - __main__ - Step 40739: {'lr': 0.0004201361549128347, 'samples': 7821888, 'steps': 40738, 'loss/train': 0.8519554138183594} 08/30/2021 20:31:25 - INFO - __main__ - Step 40740: {'lr': 0.00042013226658768333, 'samples': 7822080, 'steps': 40739, 'loss/train': 0.8235333561897278} 08/30/2021 20:31:26 - INFO - __main__ - Step 40741: {'lr': 0.0004201283781858729, 'samples': 7822272, 'steps': 40740, 'loss/train': 1.0463306903839111} 08/30/2021 20:31:26 - INFO - __main__ - Step 40742: {'lr': 0.00042012448970740523, 'samples': 7822464, 'steps': 40741, 'loss/train': 1.7897881269454956} 08/30/2021 20:31:26 - INFO - __main__ - Step 40743: {'lr': 0.00042012060115228215, 'samples': 7822656, 'steps': 40742, 'loss/train': 1.5615816116333008} 08/30/2021 20:31:27 - INFO - __main__ - Step 40744: {'lr': 0.0004201167125205054, 'samples': 7822848, 'steps': 40743, 'loss/train': 1.391696810722351} 08/30/2021 20:31:28 - INFO - __main__ - Step 40745: {'lr': 0.0004201128238120766, 'samples': 7823040, 'steps': 40744, 'loss/train': 1.45644211769104} 08/30/2021 20:31:29 - INFO - __main__ - Step 40746: {'lr': 0.00042010893502699765, 'samples': 7823232, 'steps': 40745, 'loss/train': 1.5940656661987305} 08/30/2021 20:31:29 - INFO - __main__ - Step 40747: {'lr': 0.0004201050461652702, 'samples': 7823424, 'steps': 40746, 'loss/train': 1.6794425249099731} 08/30/2021 20:31:30 - INFO - __main__ - Step 40748: {'lr': 0.00042010115722689603, 'samples': 7823616, 'steps': 40747, 'loss/train': 1.3612704277038574} 08/30/2021 20:31:30 - INFO - __main__ - Step 40749: {'lr': 0.0004200972682118769, 'samples': 7823808, 'steps': 40748, 'loss/train': 3.4012866020202637} 08/30/2021 20:31:30 - INFO - __main__ - Step 40750: {'lr': 0.0004200933791202146, 'samples': 7824000, 'steps': 40749, 'loss/train': 1.6295348405838013} 08/30/2021 20:31:32 - INFO - __main__ - Step 40751: {'lr': 0.0004200894899519108, 'samples': 7824192, 'steps': 40750, 'loss/train': 0.8933557271957397} 08/30/2021 20:31:32 - INFO - __main__ - Step 40752: {'lr': 0.00042008560070696735, 'samples': 7824384, 'steps': 40751, 'loss/train': 0.6759853959083557} 08/30/2021 20:31:33 - INFO - __main__ - Step 40753: {'lr': 0.000420081711385386, 'samples': 7824576, 'steps': 40752, 'loss/train': 1.4800009727478027} 08/30/2021 20:31:33 - INFO - __main__ - Step 40754: {'lr': 0.00042007782198716836, 'samples': 7824768, 'steps': 40753, 'loss/train': 0.784487247467041} 08/30/2021 20:31:33 - INFO - __main__ - Step 40755: {'lr': 0.0004200739325123163, 'samples': 7824960, 'steps': 40754, 'loss/train': 1.2747842073440552} 08/30/2021 20:31:35 - INFO - __main__ - Step 40756: {'lr': 0.0004200700429608315, 'samples': 7825152, 'steps': 40755, 'loss/train': 1.3847298622131348} 08/30/2021 20:31:35 - INFO - __main__ - Step 40757: {'lr': 0.00042006615333271585, 'samples': 7825344, 'steps': 40756, 'loss/train': 2.2461814880371094} 08/30/2021 20:31:36 - INFO - __main__ - Step 40758: {'lr': 0.000420062263627971, 'samples': 7825536, 'steps': 40757, 'loss/train': 1.123727560043335} 08/30/2021 20:31:36 - INFO - __main__ - Step 40759: {'lr': 0.0004200583738465987, 'samples': 7825728, 'steps': 40758, 'loss/train': 1.3890599012374878} 08/30/2021 20:31:36 - INFO - __main__ - Step 40760: {'lr': 0.00042005448398860077, 'samples': 7825920, 'steps': 40759, 'loss/train': 1.6194686889648438} 08/30/2021 20:31:38 - INFO - __main__ - Step 40761: {'lr': 0.00042005059405397885, 'samples': 7826112, 'steps': 40760, 'loss/train': 1.5006707906723022} 08/30/2021 20:31:38 - INFO - __main__ - Step 40762: {'lr': 0.00042004670404273474, 'samples': 7826304, 'steps': 40761, 'loss/train': 1.7742111682891846} 08/30/2021 20:31:39 - INFO - __main__ - Step 40763: {'lr': 0.0004200428139548703, 'samples': 7826496, 'steps': 40762, 'loss/train': 1.2751787900924683} 08/30/2021 20:31:39 - INFO - __main__ - Step 40764: {'lr': 0.0004200389237903871, 'samples': 7826688, 'steps': 40763, 'loss/train': 1.3245795965194702} 08/30/2021 20:31:39 - INFO - __main__ - Step 40765: {'lr': 0.000420035033549287, 'samples': 7826880, 'steps': 40764, 'loss/train': 1.836117148399353} 08/30/2021 20:31:41 - INFO - __main__ - Step 40766: {'lr': 0.0004200311432315718, 'samples': 7827072, 'steps': 40765, 'loss/train': 1.620129942893982} 08/30/2021 20:31:41 - INFO - __main__ - Step 40767: {'lr': 0.0004200272528372432, 'samples': 7827264, 'steps': 40766, 'loss/train': 1.4418184757232666} 08/30/2021 20:31:42 - INFO - __main__ - Step 40768: {'lr': 0.0004200233623663028, 'samples': 7827456, 'steps': 40767, 'loss/train': 0.97811359167099} 08/30/2021 20:31:42 - INFO - __main__ - Step 40769: {'lr': 0.0004200194718187527, 'samples': 7827648, 'steps': 40768, 'loss/train': 1.4465548992156982} 08/30/2021 20:31:42 - INFO - __main__ - Step 40770: {'lr': 0.0004200155811945943, 'samples': 7827840, 'steps': 40769, 'loss/train': 1.631633996963501} 08/30/2021 20:31:43 - INFO - __main__ - Step 40771: {'lr': 0.0004200116904938295, 'samples': 7828032, 'steps': 40770, 'loss/train': 1.412317156791687} 08/30/2021 20:31:44 - INFO - __main__ - Step 40772: {'lr': 0.00042000779971646007, 'samples': 7828224, 'steps': 40771, 'loss/train': 0.9450168013572693} 08/30/2021 20:31:45 - INFO - __main__ - Step 40773: {'lr': 0.00042000390886248783, 'samples': 7828416, 'steps': 40772, 'loss/train': 1.4411104917526245} 08/30/2021 20:31:45 - INFO - __main__ - Step 40774: {'lr': 0.0004200000179319144, 'samples': 7828608, 'steps': 40773, 'loss/train': 1.274450659751892} 08/30/2021 20:31:46 - INFO - __main__ - Step 40775: {'lr': 0.0004199961269247416, 'samples': 7828800, 'steps': 40774, 'loss/train': 1.3851836919784546} 08/30/2021 20:31:46 - INFO - __main__ - Step 40776: {'lr': 0.0004199922358409711, 'samples': 7828992, 'steps': 40775, 'loss/train': 1.1934096813201904} 08/30/2021 20:31:47 - INFO - __main__ - Step 40777: {'lr': 0.0004199883446806048, 'samples': 7829184, 'steps': 40776, 'loss/train': 1.3191113471984863} 08/30/2021 20:31:48 - INFO - __main__ - Step 40778: {'lr': 0.0004199844534436443, 'samples': 7829376, 'steps': 40777, 'loss/train': 1.5529453754425049} 08/30/2021 20:31:48 - INFO - __main__ - Step 40779: {'lr': 0.0004199805621300915, 'samples': 7829568, 'steps': 40778, 'loss/train': 1.5645092725753784} 08/30/2021 20:31:49 - INFO - __main__ - Step 40780: {'lr': 0.0004199766707399481, 'samples': 7829760, 'steps': 40779, 'loss/train': 1.0841411352157593} 08/30/2021 20:31:49 - INFO - __main__ - Step 40781: {'lr': 0.0004199727792732158, 'samples': 7829952, 'steps': 40780, 'loss/train': 0.8259776830673218} 08/30/2021 20:31:50 - INFO - __main__ - Step 40782: {'lr': 0.0004199688877298964, 'samples': 7830144, 'steps': 40781, 'loss/train': 0.651124894618988} 08/30/2021 20:31:51 - INFO - __main__ - Step 40783: {'lr': 0.00041996499610999163, 'samples': 7830336, 'steps': 40782, 'loss/train': 1.0718125104904175} 08/30/2021 20:31:51 - INFO - __main__ - Step 40784: {'lr': 0.00041996110441350323, 'samples': 7830528, 'steps': 40783, 'loss/train': 1.4192897081375122} 08/30/2021 20:31:51 - INFO - __main__ - Step 40785: {'lr': 0.000419957212640433, 'samples': 7830720, 'steps': 40784, 'loss/train': 0.5693715214729309} 08/30/2021 20:31:52 - INFO - __main__ - Step 40786: {'lr': 0.0004199533207907827, 'samples': 7830912, 'steps': 40785, 'loss/train': 1.3015637397766113} 08/30/2021 20:31:53 - INFO - __main__ - Step 40787: {'lr': 0.00041994942886455403, 'samples': 7831104, 'steps': 40786, 'loss/train': 1.9497350454330444} 08/30/2021 20:31:54 - INFO - __main__ - Step 40788: {'lr': 0.00041994553686174876, 'samples': 7831296, 'steps': 40787, 'loss/train': 1.1419200897216797} 08/30/2021 20:31:54 - INFO - __main__ - Step 40789: {'lr': 0.0004199416447823686, 'samples': 7831488, 'steps': 40788, 'loss/train': 1.3467382192611694} 08/30/2021 20:31:54 - INFO - __main__ - Step 40790: {'lr': 0.0004199377526264154, 'samples': 7831680, 'steps': 40789, 'loss/train': 1.7472642660140991} 08/30/2021 20:31:55 - INFO - __main__ - Step 40791: {'lr': 0.00041993386039389095, 'samples': 7831872, 'steps': 40790, 'loss/train': 1.4851189851760864} 08/30/2021 20:31:57 - INFO - __main__ - Step 40792: {'lr': 0.0004199299680847969, 'samples': 7832064, 'steps': 40791, 'loss/train': 1.480136513710022} 08/30/2021 20:31:57 - INFO - __main__ - Step 40793: {'lr': 0.000419926075699135, 'samples': 7832256, 'steps': 40792, 'loss/train': 1.2308827638626099} 08/30/2021 20:31:58 - INFO - __main__ - Step 40794: {'lr': 0.000419922183236907, 'samples': 7832448, 'steps': 40793, 'loss/train': 2.031688690185547} 08/30/2021 20:31:58 - INFO - __main__ - Step 40795: {'lr': 0.0004199182906981147, 'samples': 7832640, 'steps': 40794, 'loss/train': 1.254698395729065} 08/30/2021 20:31:58 - INFO - __main__ - Step 40796: {'lr': 0.00041991439808275986, 'samples': 7832832, 'steps': 40795, 'loss/train': 1.4454256296157837} 08/30/2021 20:32:00 - INFO - __main__ - Step 40797: {'lr': 0.0004199105053908442, 'samples': 7833024, 'steps': 40796, 'loss/train': 1.0112686157226562} 08/30/2021 20:32:00 - INFO - __main__ - Step 40798: {'lr': 0.0004199066126223695, 'samples': 7833216, 'steps': 40797, 'loss/train': 1.6412845849990845} 08/30/2021 20:32:01 - INFO - __main__ - Step 40799: {'lr': 0.0004199027197773375, 'samples': 7833408, 'steps': 40798, 'loss/train': 1.3444037437438965} 08/30/2021 20:32:01 - INFO - __main__ - Step 40800: {'lr': 0.00041989882685575, 'samples': 7833600, 'steps': 40799, 'loss/train': 1.5402215719223022} 08/30/2021 20:32:01 - INFO - __main__ - Step 40801: {'lr': 0.0004198949338576086, 'samples': 7833792, 'steps': 40800, 'loss/train': 0.43507120013237} 08/30/2021 20:32:03 - INFO - __main__ - Step 40802: {'lr': 0.0004198910407829152, 'samples': 7833984, 'steps': 40801, 'loss/train': 1.6014635562896729} 08/30/2021 20:32:03 - INFO - __main__ - Step 40803: {'lr': 0.00041988714763167156, 'samples': 7834176, 'steps': 40802, 'loss/train': 1.6347209215164185} 08/30/2021 20:32:04 - INFO - __main__ - Step 40804: {'lr': 0.00041988325440387944, 'samples': 7834368, 'steps': 40803, 'loss/train': 1.5274289846420288} 08/30/2021 20:32:04 - INFO - __main__ - Step 40805: {'lr': 0.00041987936109954047, 'samples': 7834560, 'steps': 40804, 'loss/train': 0.7356760501861572} 08/30/2021 20:32:04 - INFO - __main__ - Step 40806: {'lr': 0.0004198754677186565, 'samples': 7834752, 'steps': 40805, 'loss/train': 1.103785753250122} 08/30/2021 20:32:05 - INFO - __main__ - Step 40807: {'lr': 0.0004198715742612292, 'samples': 7834944, 'steps': 40806, 'loss/train': 0.7137376666069031} 08/30/2021 20:32:07 - INFO - __main__ - Step 40808: {'lr': 0.0004198676807272605, 'samples': 7835136, 'steps': 40807, 'loss/train': 1.6436622142791748} 08/30/2021 20:32:07 - INFO - __main__ - Step 40809: {'lr': 0.000419863787116752, 'samples': 7835328, 'steps': 40808, 'loss/train': 2.2599761486053467} 08/30/2021 20:32:08 - INFO - __main__ - Step 40810: {'lr': 0.0004198598934297055, 'samples': 7835520, 'steps': 40809, 'loss/train': 1.6801259517669678} 08/30/2021 20:32:08 - INFO - __main__ - Step 40811: {'lr': 0.00041985599966612273, 'samples': 7835712, 'steps': 40810, 'loss/train': 1.842291235923767} 08/30/2021 20:32:08 - INFO - __main__ - Step 40812: {'lr': 0.0004198521058260055, 'samples': 7835904, 'steps': 40811, 'loss/train': 1.2753660678863525} 08/30/2021 20:32:10 - INFO - __main__ - Step 40813: {'lr': 0.0004198482119093555, 'samples': 7836096, 'steps': 40812, 'loss/train': 0.14927802979946136} 08/30/2021 20:32:11 - INFO - __main__ - Step 40814: {'lr': 0.00041984431791617456, 'samples': 7836288, 'steps': 40813, 'loss/train': 1.5204445123672485} 08/30/2021 20:32:11 - INFO - __main__ - Step 40815: {'lr': 0.0004198404238464644, 'samples': 7836480, 'steps': 40814, 'loss/train': 1.2533056735992432} 08/30/2021 20:32:11 - INFO - __main__ - Step 40816: {'lr': 0.0004198365297002267, 'samples': 7836672, 'steps': 40815, 'loss/train': 1.3474946022033691} 08/30/2021 20:32:12 - INFO - __main__ - Step 40817: {'lr': 0.0004198326354774633, 'samples': 7836864, 'steps': 40816, 'loss/train': 0.9882884621620178} 08/30/2021 20:32:13 - INFO - __main__ - Step 40818: {'lr': 0.00041982874117817593, 'samples': 7837056, 'steps': 40817, 'loss/train': 1.624408483505249} 08/30/2021 20:32:14 - INFO - __main__ - Step 40819: {'lr': 0.00041982484680236636, 'samples': 7837248, 'steps': 40818, 'loss/train': 1.7785921096801758} 08/30/2021 20:32:14 - INFO - __main__ - Step 40820: {'lr': 0.00041982095235003634, 'samples': 7837440, 'steps': 40819, 'loss/train': 0.9864234328269958} 08/30/2021 20:32:14 - INFO - __main__ - Step 40821: {'lr': 0.0004198170578211877, 'samples': 7837632, 'steps': 40820, 'loss/train': 0.7419716119766235} 08/30/2021 20:32:15 - INFO - __main__ - Step 40822: {'lr': 0.000419813163215822, 'samples': 7837824, 'steps': 40821, 'loss/train': 1.6487023830413818} 08/30/2021 20:32:15 - INFO - __main__ - Step 40823: {'lr': 0.0004198092685339411, 'samples': 7838016, 'steps': 40822, 'loss/train': 1.6824064254760742} 08/30/2021 20:32:17 - INFO - __main__ - Step 40824: {'lr': 0.00041980537377554685, 'samples': 7838208, 'steps': 40823, 'loss/train': 1.3728519678115845} 08/30/2021 20:32:17 - INFO - __main__ - Step 40825: {'lr': 0.00041980147894064086, 'samples': 7838400, 'steps': 40824, 'loss/train': 0.7681717872619629} 08/30/2021 20:32:17 - INFO - __main__ - Step 40826: {'lr': 0.00041979758402922496, 'samples': 7838592, 'steps': 40825, 'loss/train': 0.15895843505859375} 08/30/2021 20:32:18 - INFO - __main__ - Step 40827: {'lr': 0.00041979368904130086, 'samples': 7838784, 'steps': 40826, 'loss/train': 1.4759423732757568} 08/30/2021 20:32:18 - INFO - __main__ - Step 40828: {'lr': 0.00041978979397687047, 'samples': 7838976, 'steps': 40827, 'loss/train': 1.4417155981063843} 08/30/2021 20:32:20 - INFO - __main__ - Step 40829: {'lr': 0.00041978589883593525, 'samples': 7839168, 'steps': 40828, 'loss/train': 0.963193416595459} 08/30/2021 20:32:20 - INFO - __main__ - Step 40830: {'lr': 0.0004197820036184972, 'samples': 7839360, 'steps': 40829, 'loss/train': 1.3285272121429443} 08/30/2021 20:32:21 - INFO - __main__ - Step 40831: {'lr': 0.000419778108324558, 'samples': 7839552, 'steps': 40830, 'loss/train': 2.3227992057800293} 08/30/2021 20:32:21 - INFO - __main__ - Step 40832: {'lr': 0.00041977421295411944, 'samples': 7839744, 'steps': 40831, 'loss/train': 2.025751829147339} 08/30/2021 20:32:21 - INFO - __main__ - Step 40833: {'lr': 0.00041977031750718317, 'samples': 7839936, 'steps': 40832, 'loss/train': 1.7972112894058228} 08/30/2021 20:32:22 - INFO - __main__ - Step 40834: {'lr': 0.000419766421983751, 'samples': 7840128, 'steps': 40833, 'loss/train': 1.7379446029663086} 08/30/2021 20:32:23 - INFO - __main__ - Step 40835: {'lr': 0.00041976252638382483, 'samples': 7840320, 'steps': 40834, 'loss/train': 1.588943600654602} 08/30/2021 20:32:24 - INFO - __main__ - Step 40836: {'lr': 0.00041975863070740617, 'samples': 7840512, 'steps': 40835, 'loss/train': 1.5860025882720947} 08/30/2021 20:32:24 - INFO - __main__ - Step 40837: {'lr': 0.0004197547349544969, 'samples': 7840704, 'steps': 40836, 'loss/train': 1.605682134628296} 08/30/2021 20:32:25 - INFO - __main__ - Step 40838: {'lr': 0.0004197508391250988, 'samples': 7840896, 'steps': 40837, 'loss/train': 1.5250840187072754} 08/30/2021 20:32:25 - INFO - __main__ - Step 40839: {'lr': 0.0004197469432192136, 'samples': 7841088, 'steps': 40838, 'loss/train': 1.4490379095077515} 08/30/2021 20:32:26 - INFO - __main__ - Step 40840: {'lr': 0.000419743047236843, 'samples': 7841280, 'steps': 40839, 'loss/train': 1.5496867895126343} 08/30/2021 20:32:27 - INFO - __main__ - Step 40841: {'lr': 0.00041973915117798883, 'samples': 7841472, 'steps': 40840, 'loss/train': 1.083207607269287} 08/30/2021 20:32:27 - INFO - __main__ - Step 40842: {'lr': 0.0004197352550426528, 'samples': 7841664, 'steps': 40841, 'loss/train': 1.5124861001968384} 08/30/2021 20:32:28 - INFO - __main__ - Step 40843: {'lr': 0.0004197313588308367, 'samples': 7841856, 'steps': 40842, 'loss/train': 1.3684998750686646} 08/30/2021 20:32:28 - INFO - __main__ - Step 40844: {'lr': 0.0004197274625425423, 'samples': 7842048, 'steps': 40843, 'loss/train': 1.7779576778411865} 08/30/2021 20:32:30 - INFO - __main__ - Step 40845: {'lr': 0.0004197235661777713, 'samples': 7842240, 'steps': 40844, 'loss/train': 1.5463695526123047} 08/30/2021 20:32:30 - INFO - __main__ - Step 40846: {'lr': 0.00041971966973652545, 'samples': 7842432, 'steps': 40845, 'loss/train': 0.9762404561042786} 08/30/2021 20:32:31 - INFO - __main__ - Step 40847: {'lr': 0.00041971577321880656, 'samples': 7842624, 'steps': 40846, 'loss/train': 1.8867933750152588} 08/30/2021 20:32:31 - INFO - __main__ - Step 40848: {'lr': 0.00041971187662461634, 'samples': 7842816, 'steps': 40847, 'loss/train': 1.183830976486206} 08/30/2021 20:32:31 - INFO - __main__ - Step 40849: {'lr': 0.0004197079799539566, 'samples': 7843008, 'steps': 40848, 'loss/train': 1.3238204717636108} 08/30/2021 20:32:33 - INFO - __main__ - Step 40850: {'lr': 0.0004197040832068291, 'samples': 7843200, 'steps': 40849, 'loss/train': 1.2573596239089966} 08/30/2021 20:32:33 - INFO - __main__ - Step 40851: {'lr': 0.00041970018638323546, 'samples': 7843392, 'steps': 40850, 'loss/train': 1.4237372875213623} 08/30/2021 20:32:34 - INFO - __main__ - Step 40852: {'lr': 0.00041969628948317756, 'samples': 7843584, 'steps': 40851, 'loss/train': 0.417272686958313} 08/30/2021 20:32:34 - INFO - __main__ - Step 40853: {'lr': 0.00041969239250665716, 'samples': 7843776, 'steps': 40852, 'loss/train': 1.62783944606781} 08/30/2021 20:32:34 - INFO - __main__ - Step 40854: {'lr': 0.000419688495453676, 'samples': 7843968, 'steps': 40853, 'loss/train': 1.5535670518875122} 08/30/2021 20:32:35 - INFO - __main__ - Step 40855: {'lr': 0.0004196845983242358, 'samples': 7844160, 'steps': 40854, 'loss/train': 0.938503623008728} 08/30/2021 20:32:36 - INFO - __main__ - Step 40856: {'lr': 0.0004196807011183383, 'samples': 7844352, 'steps': 40855, 'loss/train': 1.6601595878601074} 08/30/2021 20:32:37 - INFO - __main__ - Step 40857: {'lr': 0.00041967680383598536, 'samples': 7844544, 'steps': 40856, 'loss/train': 1.7420214414596558} 08/30/2021 20:32:37 - INFO - __main__ - Step 40858: {'lr': 0.00041967290647717864, 'samples': 7844736, 'steps': 40857, 'loss/train': 1.5125513076782227} 08/30/2021 20:32:37 - INFO - __main__ - Step 40859: {'lr': 0.00041966900904191995, 'samples': 7844928, 'steps': 40858, 'loss/train': 1.4889695644378662} 08/30/2021 20:32:38 - INFO - __main__ - Step 40860: {'lr': 0.000419665111530211, 'samples': 7845120, 'steps': 40859, 'loss/train': 2.4015071392059326} 08/30/2021 20:32:39 - INFO - __main__ - Step 40861: {'lr': 0.00041966121394205357, 'samples': 7845312, 'steps': 40860, 'loss/train': 1.2893686294555664} 08/30/2021 20:32:40 - INFO - __main__ - Step 40862: {'lr': 0.0004196573162774494, 'samples': 7845504, 'steps': 40861, 'loss/train': 1.5658608675003052} 08/30/2021 20:32:40 - INFO - __main__ - Step 40863: {'lr': 0.0004196534185364003, 'samples': 7845696, 'steps': 40862, 'loss/train': 1.632365107536316} 08/30/2021 20:32:40 - INFO - __main__ - Step 40864: {'lr': 0.00041964952071890795, 'samples': 7845888, 'steps': 40863, 'loss/train': 1.7567949295043945} 08/30/2021 20:32:41 - INFO - __main__ - Step 40865: {'lr': 0.00041964562282497417, 'samples': 7846080, 'steps': 40864, 'loss/train': 3.308375358581543} 08/30/2021 20:32:42 - INFO - __main__ - Step 40866: {'lr': 0.0004196417248546006, 'samples': 7846272, 'steps': 40865, 'loss/train': 1.10386323928833} 08/30/2021 20:32:43 - INFO - __main__ - Step 40867: {'lr': 0.0004196378268077893, 'samples': 7846464, 'steps': 40866, 'loss/train': 1.3081706762313843} 08/30/2021 20:32:43 - INFO - __main__ - Step 40868: {'lr': 0.00041963392868454163, 'samples': 7846656, 'steps': 40867, 'loss/train': 1.3719993829727173} 08/30/2021 20:32:44 - INFO - __main__ - Step 40869: {'lr': 0.0004196300304848596, 'samples': 7846848, 'steps': 40868, 'loss/train': 1.3687745332717896} 08/30/2021 20:32:44 - INFO - __main__ - Step 40870: {'lr': 0.00041962613220874486, 'samples': 7847040, 'steps': 40869, 'loss/train': 2.1709072589874268} 08/30/2021 20:32:45 - INFO - __main__ - Step 40871: {'lr': 0.0004196222338561992, 'samples': 7847232, 'steps': 40870, 'loss/train': 0.800399899482727} 08/30/2021 20:32:46 - INFO - __main__ - Step 40872: {'lr': 0.0004196183354272244, 'samples': 7847424, 'steps': 40871, 'loss/train': 1.1716111898422241} 08/30/2021 20:32:46 - INFO - __main__ - Step 40873: {'lr': 0.00041961443692182214, 'samples': 7847616, 'steps': 40872, 'loss/train': 1.7098530530929565} 08/30/2021 20:32:47 - INFO - __main__ - Step 40874: {'lr': 0.00041961053833999433, 'samples': 7847808, 'steps': 40873, 'loss/train': 1.7292158603668213} 08/30/2021 20:32:47 - INFO - __main__ - Step 40875: {'lr': 0.00041960663968174263, 'samples': 7848000, 'steps': 40874, 'loss/train': 1.6533483266830444} 08/30/2021 20:32:47 - INFO - __main__ - Step 40876: {'lr': 0.0004196027409470687, 'samples': 7848192, 'steps': 40875, 'loss/train': 1.117339849472046} 08/30/2021 20:32:49 - INFO - __main__ - Step 40877: {'lr': 0.00041959884213597443, 'samples': 7848384, 'steps': 40876, 'loss/train': 1.6889264583587646} 08/30/2021 20:32:49 - INFO - __main__ - Step 40878: {'lr': 0.0004195949432484615, 'samples': 7848576, 'steps': 40877, 'loss/train': 2.027769088745117} 08/30/2021 20:32:50 - INFO - __main__ - Step 40879: {'lr': 0.00041959104428453175, 'samples': 7848768, 'steps': 40878, 'loss/train': 1.3049023151397705} 08/30/2021 20:32:50 - INFO - __main__ - Step 40880: {'lr': 0.000419587145244187, 'samples': 7848960, 'steps': 40879, 'loss/train': 1.8736363649368286} 08/30/2021 20:32:50 - INFO - __main__ - Step 40881: {'lr': 0.0004195832461274288, 'samples': 7849152, 'steps': 40880, 'loss/train': 1.5118097066879272} 08/30/2021 20:32:52 - INFO - __main__ - Step 40882: {'lr': 0.00041957934693425894, 'samples': 7849344, 'steps': 40881, 'loss/train': 1.5298237800598145} 08/30/2021 20:32:52 - INFO - __main__ - Step 40883: {'lr': 0.0004195754476646793, 'samples': 7849536, 'steps': 40882, 'loss/train': 1.593651533126831} 08/30/2021 20:32:53 - INFO - __main__ - Step 40884: {'lr': 0.0004195715483186916, 'samples': 7849728, 'steps': 40883, 'loss/train': 1.6793041229248047} 08/30/2021 20:32:53 - INFO - __main__ - Step 40885: {'lr': 0.00041956764889629756, 'samples': 7849920, 'steps': 40884, 'loss/train': 2.224100351333618} 08/30/2021 20:32:53 - INFO - __main__ - Step 40886: {'lr': 0.000419563749397499, 'samples': 7850112, 'steps': 40885, 'loss/train': 1.3643192052841187} 08/30/2021 20:32:54 - INFO - __main__ - Step 40887: {'lr': 0.00041955984982229756, 'samples': 7850304, 'steps': 40886, 'loss/train': 1.7641876935958862} 08/30/2021 20:32:55 - INFO - __main__ - Step 40888: {'lr': 0.0004195559501706951, 'samples': 7850496, 'steps': 40887, 'loss/train': 0.14660528302192688} 08/30/2021 20:32:56 - INFO - __main__ - Step 40889: {'lr': 0.0004195520504426933, 'samples': 7850688, 'steps': 40888, 'loss/train': 1.8347421884536743} 08/30/2021 20:32:56 - INFO - __main__ - Step 40890: {'lr': 0.000419548150638294, 'samples': 7850880, 'steps': 40889, 'loss/train': 1.368322491645813} 08/30/2021 20:32:56 - INFO - __main__ - Step 40891: {'lr': 0.0004195442507574989, 'samples': 7851072, 'steps': 40890, 'loss/train': 1.2386257648468018} 08/30/2021 20:32:57 - INFO - __main__ - Step 40892: {'lr': 0.00041954035080030985, 'samples': 7851264, 'steps': 40891, 'loss/train': 0.9416026473045349} 08/30/2021 20:32:58 - INFO - __main__ - Step 40893: {'lr': 0.0004195364507667284, 'samples': 7851456, 'steps': 40892, 'loss/train': 1.2902321815490723} 08/30/2021 20:32:59 - INFO - __main__ - Step 40894: {'lr': 0.0004195325506567566, 'samples': 7851648, 'steps': 40893, 'loss/train': 0.7052925825119019} 08/30/2021 20:32:59 - INFO - __main__ - Step 40895: {'lr': 0.00041952865047039604, 'samples': 7851840, 'steps': 40894, 'loss/train': 0.9954533576965332} 08/30/2021 20:32:59 - INFO - __main__ - Step 40896: {'lr': 0.00041952475020764834, 'samples': 7852032, 'steps': 40895, 'loss/train': 1.9334520101547241} 08/30/2021 20:33:00 - INFO - __main__ - Step 40897: {'lr': 0.00041952084986851546, 'samples': 7852224, 'steps': 40896, 'loss/train': 1.5377235412597656} 08/30/2021 20:33:02 - INFO - __main__ - Step 40898: {'lr': 0.0004195169494529991, 'samples': 7852416, 'steps': 40897, 'loss/train': 1.4728283882141113} 08/30/2021 20:33:02 - INFO - __main__ - Step 40899: {'lr': 0.0004195130489611011, 'samples': 7852608, 'steps': 40898, 'loss/train': 1.4611942768096924} 08/30/2021 20:33:03 - INFO - __main__ - Step 40900: {'lr': 0.0004195091483928231, 'samples': 7852800, 'steps': 40899, 'loss/train': 1.3139704465866089} 08/30/2021 20:33:03 - INFO - __main__ - Step 40901: {'lr': 0.0004195052477481669, 'samples': 7852992, 'steps': 40900, 'loss/train': 1.336854100227356} 08/30/2021 20:33:03 - INFO - __main__ - Step 40902: {'lr': 0.00041950134702713415, 'samples': 7853184, 'steps': 40901, 'loss/train': 0.6940378546714783} 08/30/2021 20:33:05 - INFO - __main__ - Step 40903: {'lr': 0.0004194974462297268, 'samples': 7853376, 'steps': 40902, 'loss/train': 0.768294632434845} 08/30/2021 20:33:06 - INFO - __main__ - Step 40904: {'lr': 0.00041949354535594655, 'samples': 7853568, 'steps': 40903, 'loss/train': 1.3073195219039917} 08/30/2021 20:33:06 - INFO - __main__ - Step 40905: {'lr': 0.000419489644405795, 'samples': 7853760, 'steps': 40904, 'loss/train': 1.103238821029663} 08/30/2021 20:33:06 - INFO - __main__ - Step 40906: {'lr': 0.00041948574337927414, 'samples': 7853952, 'steps': 40905, 'loss/train': 1.9622260332107544} 08/30/2021 20:33:07 - INFO - __main__ - Step 40907: {'lr': 0.0004194818422763856, 'samples': 7854144, 'steps': 40906, 'loss/train': 0.5710344314575195} 08/30/2021 20:33:07 - INFO - __main__ - Step 40908: {'lr': 0.00041947794109713113, 'samples': 7854336, 'steps': 40907, 'loss/train': 0.06249542161822319} 08/30/2021 20:33:09 - INFO - __main__ - Step 40909: {'lr': 0.0004194740398415125, 'samples': 7854528, 'steps': 40908, 'loss/train': 1.1699984073638916} 08/30/2021 20:33:09 - INFO - __main__ - Step 40910: {'lr': 0.00041947013850953156, 'samples': 7854720, 'steps': 40909, 'loss/train': 1.4442816972732544} 08/30/2021 20:33:09 - INFO - __main__ - Step 40911: {'lr': 0.00041946623710118993, 'samples': 7854912, 'steps': 40910, 'loss/train': 1.077022671699524} 08/30/2021 20:33:10 - INFO - __main__ - Step 40912: {'lr': 0.0004194623356164894, 'samples': 7855104, 'steps': 40911, 'loss/train': 1.2743233442306519} 08/30/2021 20:33:10 - INFO - __main__ - Step 40913: {'lr': 0.0004194584340554318, 'samples': 7855296, 'steps': 40912, 'loss/train': 1.6945490837097168} 08/30/2021 20:33:12 - INFO - __main__ - Step 40914: {'lr': 0.0004194545324180188, 'samples': 7855488, 'steps': 40913, 'loss/train': 1.3466601371765137} 08/30/2021 20:33:12 - INFO - __main__ - Step 40915: {'lr': 0.00041945063070425226, 'samples': 7855680, 'steps': 40914, 'loss/train': 1.2468785047531128} 08/30/2021 20:33:13 - INFO - __main__ - Step 40916: {'lr': 0.0004194467289141339, 'samples': 7855872, 'steps': 40915, 'loss/train': 1.5406134128570557} 08/30/2021 20:33:13 - INFO - __main__ - Step 40917: {'lr': 0.00041944282704766534, 'samples': 7856064, 'steps': 40916, 'loss/train': 0.8024212718009949} 08/30/2021 20:33:13 - INFO - __main__ - Step 40918: {'lr': 0.0004194389251048486, 'samples': 7856256, 'steps': 40917, 'loss/train': 1.2845203876495361} 08/30/2021 20:33:15 - INFO - __main__ - Step 40919: {'lr': 0.00041943502308568523, 'samples': 7856448, 'steps': 40918, 'loss/train': 0.3970642685890198} 08/30/2021 20:33:15 - INFO - __main__ - Step 40920: {'lr': 0.000419431120990177, 'samples': 7856640, 'steps': 40919, 'loss/train': 1.4084731340408325} 08/30/2021 20:33:16 - INFO - __main__ - Step 40921: {'lr': 0.0004194272188183258, 'samples': 7856832, 'steps': 40920, 'loss/train': 1.4735500812530518} 08/30/2021 20:33:16 - INFO - __main__ - Step 40922: {'lr': 0.0004194233165701333, 'samples': 7857024, 'steps': 40921, 'loss/train': 1.3554116487503052} 08/30/2021 20:33:16 - INFO - __main__ - Step 40923: {'lr': 0.0004194194142456013, 'samples': 7857216, 'steps': 40922, 'loss/train': 1.3129101991653442} 08/30/2021 20:33:18 - INFO - __main__ - Step 40924: {'lr': 0.00041941551184473144, 'samples': 7857408, 'steps': 40923, 'loss/train': 1.389233946800232} 08/30/2021 20:33:18 - INFO - __main__ - Step 40925: {'lr': 0.0004194116093675256, 'samples': 7857600, 'steps': 40924, 'loss/train': 1.1665074825286865} 08/30/2021 20:33:19 - INFO - __main__ - Step 40926: {'lr': 0.0004194077068139855, 'samples': 7857792, 'steps': 40925, 'loss/train': 1.9135937690734863} 08/30/2021 20:33:19 - INFO - __main__ - Step 40927: {'lr': 0.00041940380418411296, 'samples': 7857984, 'steps': 40926, 'loss/train': 1.7282769680023193} 08/30/2021 20:33:19 - INFO - __main__ - Step 40928: {'lr': 0.00041939990147790956, 'samples': 7858176, 'steps': 40927, 'loss/train': 0.7967919707298279} 08/30/2021 20:33:20 - INFO - __main__ - Step 40929: {'lr': 0.00041939599869537724, 'samples': 7858368, 'steps': 40928, 'loss/train': 1.0501060485839844} 08/30/2021 20:33:21 - INFO - __main__ - Step 40930: {'lr': 0.00041939209583651774, 'samples': 7858560, 'steps': 40929, 'loss/train': 1.4101780652999878} 08/30/2021 20:33:22 - INFO - __main__ - Step 40931: {'lr': 0.0004193881929013327, 'samples': 7858752, 'steps': 40930, 'loss/train': 1.2091023921966553} 08/30/2021 20:33:22 - INFO - __main__ - Step 40932: {'lr': 0.00041938428988982403, 'samples': 7858944, 'steps': 40931, 'loss/train': 1.4088445901870728} 08/30/2021 20:33:22 - INFO - __main__ - Step 40933: {'lr': 0.00041938038680199333, 'samples': 7859136, 'steps': 40932, 'loss/train': 1.4141396284103394} 08/30/2021 20:33:23 - INFO - __main__ - Step 40934: {'lr': 0.0004193764836378425, 'samples': 7859328, 'steps': 40933, 'loss/train': 1.4904959201812744} 08/30/2021 20:33:24 - INFO - __main__ - Step 40935: {'lr': 0.0004193725803973732, 'samples': 7859520, 'steps': 40934, 'loss/train': 1.1050435304641724} 08/30/2021 20:33:25 - INFO - __main__ - Step 40936: {'lr': 0.0004193686770805873, 'samples': 7859712, 'steps': 40935, 'loss/train': 1.6410069465637207} 08/30/2021 20:33:25 - INFO - __main__ - Step 40937: {'lr': 0.00041936477368748645, 'samples': 7859904, 'steps': 40936, 'loss/train': 1.3336771726608276} 08/30/2021 20:33:26 - INFO - __main__ - Step 40938: {'lr': 0.00041936087021807243, 'samples': 7860096, 'steps': 40937, 'loss/train': 0.07436837255954742} 08/30/2021 20:33:26 - INFO - __main__ - Step 40939: {'lr': 0.000419356966672347, 'samples': 7860288, 'steps': 40938, 'loss/train': 0.44961774349212646} 08/30/2021 20:33:27 - INFO - __main__ - Step 40940: {'lr': 0.00041935306305031195, 'samples': 7860480, 'steps': 40939, 'loss/train': 1.4658244848251343} 08/30/2021 20:33:28 - INFO - __main__ - Step 40941: {'lr': 0.000419349159351969, 'samples': 7860672, 'steps': 40940, 'loss/train': 1.6728591918945312} 08/30/2021 20:33:28 - INFO - __main__ - Step 40942: {'lr': 0.00041934525557732005, 'samples': 7860864, 'steps': 40941, 'loss/train': 1.8563625812530518} 08/30/2021 20:33:29 - INFO - __main__ - Step 40943: {'lr': 0.00041934135172636667, 'samples': 7861056, 'steps': 40942, 'loss/train': 0.6185595989227295} 08/30/2021 20:33:29 - INFO - __main__ - Step 40944: {'lr': 0.00041933744779911066, 'samples': 7861248, 'steps': 40943, 'loss/train': 1.0351604223251343} 08/30/2021 20:33:30 - INFO - __main__ - Step 40945: {'lr': 0.00041933354379555376, 'samples': 7861440, 'steps': 40944, 'loss/train': 0.8298118114471436} 08/30/2021 20:33:31 - INFO - __main__ - Step 40946: {'lr': 0.00041932963971569786, 'samples': 7861632, 'steps': 40945, 'loss/train': 1.2659929990768433} 08/30/2021 20:33:31 - INFO - __main__ - Step 40947: {'lr': 0.0004193257355595446, 'samples': 7861824, 'steps': 40946, 'loss/train': 1.6088361740112305} 08/30/2021 20:33:32 - INFO - __main__ - Step 40948: {'lr': 0.00041932183132709587, 'samples': 7862016, 'steps': 40947, 'loss/train': 1.2395412921905518} 08/30/2021 20:33:32 - INFO - __main__ - Step 40949: {'lr': 0.00041931792701835325, 'samples': 7862208, 'steps': 40948, 'loss/train': 0.9507985711097717} 08/30/2021 20:33:34 - INFO - __main__ - Step 40950: {'lr': 0.00041931402263331856, 'samples': 7862400, 'steps': 40949, 'loss/train': 1.495686650276184} 08/30/2021 20:33:34 - INFO - __main__ - Step 40951: {'lr': 0.0004193101181719936, 'samples': 7862592, 'steps': 40950, 'loss/train': 1.3619741201400757} 08/30/2021 20:33:35 - INFO - __main__ - Step 40952: {'lr': 0.00041930621363438014, 'samples': 7862784, 'steps': 40951, 'loss/train': 1.8789520263671875} 08/30/2021 20:33:35 - INFO - __main__ - Step 40953: {'lr': 0.0004193023090204799, 'samples': 7862976, 'steps': 40952, 'loss/train': 2.3328163623809814} 08/30/2021 20:33:36 - INFO - __main__ - Step 40954: {'lr': 0.0004192984043302947, 'samples': 7863168, 'steps': 40953, 'loss/train': 1.0303049087524414} 08/30/2021 20:33:36 - INFO - __main__ - Step 40955: {'lr': 0.00041929449956382625, 'samples': 7863360, 'steps': 40954, 'loss/train': 1.4737156629562378} 08/30/2021 20:33:38 - INFO - __main__ - Step 40956: {'lr': 0.0004192905947210762, 'samples': 7863552, 'steps': 40955, 'loss/train': 1.62615966796875} 08/30/2021 20:33:39 - INFO - __main__ - Step 40957: {'lr': 0.00041928668980204653, 'samples': 7863744, 'steps': 40956, 'loss/train': 1.65840744972229} 08/30/2021 20:33:39 - INFO - __main__ - Step 40958: {'lr': 0.00041928278480673884, 'samples': 7863936, 'steps': 40957, 'loss/train': 1.5239286422729492} 08/30/2021 20:33:39 - INFO - __main__ - Step 40959: {'lr': 0.00041927887973515493, 'samples': 7864128, 'steps': 40958, 'loss/train': 1.4872782230377197} 08/30/2021 20:33:40 - INFO - __main__ - Step 40960: {'lr': 0.0004192749745872966, 'samples': 7864320, 'steps': 40959, 'loss/train': 4.225166320800781} 08/30/2021 20:33:40 - INFO - __main__ - Step 40961: {'lr': 0.00041927106936316563, 'samples': 7864512, 'steps': 40960, 'loss/train': 1.5450806617736816} 08/30/2021 20:33:41 - INFO - __main__ - Step 40962: {'lr': 0.00041926716406276367, 'samples': 7864704, 'steps': 40961, 'loss/train': 2.4315237998962402} 08/30/2021 20:33:42 - INFO - __main__ - Step 40963: {'lr': 0.00041926325868609247, 'samples': 7864896, 'steps': 40962, 'loss/train': 1.53387451171875} 08/30/2021 20:33:42 - INFO - __main__ - Step 40964: {'lr': 0.0004192593532331539, 'samples': 7865088, 'steps': 40963, 'loss/train': 1.7144404649734497} 08/30/2021 20:33:43 - INFO - __main__ - Step 40965: {'lr': 0.00041925544770394976, 'samples': 7865280, 'steps': 40964, 'loss/train': 1.5886229276657104} 08/30/2021 20:33:43 - INFO - __main__ - Step 40966: {'lr': 0.0004192515420984816, 'samples': 7865472, 'steps': 40965, 'loss/train': 2.5931015014648438} 08/30/2021 20:33:43 - INFO - __main__ - Step 40967: {'lr': 0.0004192476364167514, 'samples': 7865664, 'steps': 40966, 'loss/train': 1.7479819059371948} 08/30/2021 20:33:45 - INFO - __main__ - Step 40968: {'lr': 0.0004192437306587608, 'samples': 7865856, 'steps': 40967, 'loss/train': 1.5609920024871826} 08/30/2021 20:33:45 - INFO - __main__ - Step 40969: {'lr': 0.0004192398248245116, 'samples': 7866048, 'steps': 40968, 'loss/train': 1.842596411705017} 08/30/2021 20:33:46 - INFO - __main__ - Step 40970: {'lr': 0.00041923591891400555, 'samples': 7866240, 'steps': 40969, 'loss/train': 1.1909911632537842} 08/30/2021 20:33:46 - INFO - __main__ - Step 40971: {'lr': 0.00041923201292724436, 'samples': 7866432, 'steps': 40970, 'loss/train': 1.5168083906173706} 08/30/2021 20:33:46 - INFO - __main__ - Step 40972: {'lr': 0.00041922810686422987, 'samples': 7866624, 'steps': 40971, 'loss/train': 1.8781682252883911} 08/30/2021 20:33:48 - INFO - __main__ - Step 40973: {'lr': 0.00041922420072496383, 'samples': 7866816, 'steps': 40972, 'loss/train': 1.786932110786438} 08/30/2021 20:33:48 - INFO - __main__ - Step 40974: {'lr': 0.00041922029450944785, 'samples': 7867008, 'steps': 40973, 'loss/train': 1.4572707414627075} 08/30/2021 20:33:49 - INFO - __main__ - Step 40975: {'lr': 0.000419216388217684, 'samples': 7867200, 'steps': 40974, 'loss/train': 1.5855839252471924} 08/30/2021 20:33:49 - INFO - __main__ - Step 40976: {'lr': 0.00041921248184967374, 'samples': 7867392, 'steps': 40975, 'loss/train': 1.5981673002243042} 08/30/2021 20:33:49 - INFO - __main__ - Step 40977: {'lr': 0.000419208575405419, 'samples': 7867584, 'steps': 40976, 'loss/train': 2.135380506515503} 08/30/2021 20:33:51 - INFO - __main__ - Step 40978: {'lr': 0.00041920466888492147, 'samples': 7867776, 'steps': 40977, 'loss/train': 1.3703010082244873} 08/30/2021 20:33:52 - INFO - __main__ - Step 40979: {'lr': 0.00041920076228818293, 'samples': 7867968, 'steps': 40978, 'loss/train': 1.575701355934143} 08/30/2021 20:33:52 - INFO - __main__ - Step 40980: {'lr': 0.0004191968556152051, 'samples': 7868160, 'steps': 40979, 'loss/train': 2.3708324432373047} 08/30/2021 20:33:52 - INFO - __main__ - Step 40981: {'lr': 0.0004191929488659898, 'samples': 7868352, 'steps': 40980, 'loss/train': 1.5656780004501343} 08/30/2021 20:33:53 - INFO - __main__ - Step 40982: {'lr': 0.00041918904204053874, 'samples': 7868544, 'steps': 40981, 'loss/train': 1.12666654586792} 08/30/2021 20:33:53 - INFO - __main__ - Step 40983: {'lr': 0.0004191851351388538, 'samples': 7868736, 'steps': 40982, 'loss/train': 1.218644142150879} 08/30/2021 20:33:54 - INFO - __main__ - Step 40984: {'lr': 0.0004191812281609366, 'samples': 7868928, 'steps': 40983, 'loss/train': 1.4286248683929443} 08/30/2021 20:33:55 - INFO - __main__ - Step 40985: {'lr': 0.00041917732110678896, 'samples': 7869120, 'steps': 40984, 'loss/train': 1.8776036500930786} 08/30/2021 20:33:55 - INFO - __main__ - Step 40986: {'lr': 0.0004191734139764126, 'samples': 7869312, 'steps': 40985, 'loss/train': 1.6581599712371826} 08/30/2021 20:33:56 - INFO - __main__ - Step 40987: {'lr': 0.00041916950676980933, 'samples': 7869504, 'steps': 40986, 'loss/train': 2.2027676105499268} 08/30/2021 20:33:56 - INFO - __main__ - Step 40988: {'lr': 0.0004191655994869809, 'samples': 7869696, 'steps': 40987, 'loss/train': 1.9761977195739746} 08/30/2021 20:33:57 - INFO - __main__ - Step 40989: {'lr': 0.000419161692127929, 'samples': 7869888, 'steps': 40988, 'loss/train': 1.248308539390564} 08/30/2021 20:33:58 - INFO - __main__ - Step 40990: {'lr': 0.00041915778469265555, 'samples': 7870080, 'steps': 40989, 'loss/train': 1.5555769205093384} 08/30/2021 20:33:58 - INFO - __main__ - Step 40991: {'lr': 0.0004191538771811621, 'samples': 7870272, 'steps': 40990, 'loss/train': 1.1149226427078247} 08/30/2021 20:33:59 - INFO - __main__ - Step 40992: {'lr': 0.00041914996959345057, 'samples': 7870464, 'steps': 40991, 'loss/train': 1.4795925617218018} 08/30/2021 20:33:59 - INFO - __main__ - Step 40993: {'lr': 0.0004191460619295227, 'samples': 7870656, 'steps': 40992, 'loss/train': 1.583585500717163} 08/30/2021 20:34:01 - INFO - __main__ - Step 40994: {'lr': 0.0004191421541893802, 'samples': 7870848, 'steps': 40993, 'loss/train': 1.6287332773208618} 08/30/2021 20:34:01 - INFO - __main__ - Step 40995: {'lr': 0.0004191382463730249, 'samples': 7871040, 'steps': 40994, 'loss/train': 1.6534956693649292} 08/30/2021 20:34:01 - INFO - __main__ - Step 40996: {'lr': 0.00041913433848045844, 'samples': 7871232, 'steps': 40995, 'loss/train': 1.4942495822906494} 08/30/2021 20:34:02 - INFO - __main__ - Step 40997: {'lr': 0.00041913043051168276, 'samples': 7871424, 'steps': 40996, 'loss/train': 0.5345218777656555} 08/30/2021 20:34:02 - INFO - __main__ - Step 40998: {'lr': 0.00041912652246669943, 'samples': 7871616, 'steps': 40997, 'loss/train': 0.9556570649147034} 08/30/2021 20:34:04 - INFO - __main__ - Step 40999: {'lr': 0.0004191226143455103, 'samples': 7871808, 'steps': 40998, 'loss/train': 2.0120275020599365} 08/30/2021 20:34:04 - INFO - __main__ - Step 41000: {'lr': 0.00041911870614811715, 'samples': 7872000, 'steps': 40999, 'loss/train': 1.7070958614349365} 08/30/2021 20:34:05 - INFO - __main__ - Step 41001: {'lr': 0.00041911479787452177, 'samples': 7872192, 'steps': 41000, 'loss/train': 1.471051573753357} 08/30/2021 20:34:05 - INFO - __main__ - Step 41002: {'lr': 0.0004191108895247258, 'samples': 7872384, 'steps': 41001, 'loss/train': 1.1451913118362427} 08/30/2021 20:34:05 - INFO - __main__ - Step 41003: {'lr': 0.00041910698109873116, 'samples': 7872576, 'steps': 41002, 'loss/train': 1.0168237686157227} 08/30/2021 20:34:07 - INFO - __main__ - Step 41004: {'lr': 0.0004191030725965394, 'samples': 7872768, 'steps': 41003, 'loss/train': 0.10557163506746292} 08/30/2021 20:34:07 - INFO - __main__ - Step 41005: {'lr': 0.00041909916401815245, 'samples': 7872960, 'steps': 41004, 'loss/train': 1.5996288061141968} 08/30/2021 20:34:08 - INFO - __main__ - Step 41006: {'lr': 0.00041909525536357206, 'samples': 7873152, 'steps': 41005, 'loss/train': 1.5740998983383179} 08/30/2021 20:34:08 - INFO - __main__ - Step 41007: {'lr': 0.0004190913466327999, 'samples': 7873344, 'steps': 41006, 'loss/train': 0.0771162211894989} 08/30/2021 20:34:08 - INFO - __main__ - Step 41008: {'lr': 0.00041908743782583793, 'samples': 7873536, 'steps': 41007, 'loss/train': 1.7025703191757202} 08/30/2021 20:34:11 - INFO - __main__ - Step 41009: {'lr': 0.00041908352894268766, 'samples': 7873728, 'steps': 41008, 'loss/train': 1.8158495426177979} 08/30/2021 20:34:11 - INFO - __main__ - Step 41010: {'lr': 0.00041907961998335094, 'samples': 7873920, 'steps': 41009, 'loss/train': 1.762906789779663} 08/30/2021 20:34:12 - INFO - __main__ - Step 41011: {'lr': 0.0004190757109478296, 'samples': 7874112, 'steps': 41010, 'loss/train': 1.8688335418701172} 08/30/2021 20:34:12 - INFO - __main__ - Step 41012: {'lr': 0.00041907180183612525, 'samples': 7874304, 'steps': 41011, 'loss/train': 1.7534507513046265} 08/30/2021 20:34:12 - INFO - __main__ - Step 41013: {'lr': 0.00041906789264823985, 'samples': 7874496, 'steps': 41012, 'loss/train': 0.09809020161628723} 08/30/2021 20:34:14 - INFO - __main__ - Step 41014: {'lr': 0.00041906398338417504, 'samples': 7874688, 'steps': 41013, 'loss/train': 1.5099958181381226} 08/30/2021 20:34:14 - INFO - __main__ - Step 41015: {'lr': 0.00041906007404393273, 'samples': 7874880, 'steps': 41014, 'loss/train': 1.496046781539917} 08/30/2021 20:34:15 - INFO - __main__ - Step 41016: {'lr': 0.0004190561646275144, 'samples': 7875072, 'steps': 41015, 'loss/train': 1.1792261600494385} 08/30/2021 20:34:15 - INFO - __main__ - Step 41017: {'lr': 0.0004190522551349221, 'samples': 7875264, 'steps': 41016, 'loss/train': 1.4963449239730835} 08/30/2021 20:34:15 - INFO - __main__ - Step 41018: {'lr': 0.00041904834556615733, 'samples': 7875456, 'steps': 41017, 'loss/train': 1.59846031665802} 08/30/2021 20:34:17 - INFO - __main__ - Step 41019: {'lr': 0.000419044435921222, 'samples': 7875648, 'steps': 41018, 'loss/train': 1.589135766029358} 08/30/2021 20:34:17 - INFO - __main__ - Step 41020: {'lr': 0.0004190405262001179, 'samples': 7875840, 'steps': 41019, 'loss/train': 1.3507919311523438} 08/30/2021 20:34:18 - INFO - __main__ - Step 41021: {'lr': 0.00041903661640284675, 'samples': 7876032, 'steps': 41020, 'loss/train': 1.435124158859253} 08/30/2021 20:34:18 - INFO - __main__ - Step 41022: {'lr': 0.0004190327065294104, 'samples': 7876224, 'steps': 41021, 'loss/train': 1.5862599611282349} 08/30/2021 20:34:18 - INFO - __main__ - Step 41023: {'lr': 0.00041902879657981036, 'samples': 7876416, 'steps': 41022, 'loss/train': 1.248430848121643} 08/30/2021 20:34:20 - INFO - __main__ - Step 41024: {'lr': 0.00041902488655404864, 'samples': 7876608, 'steps': 41023, 'loss/train': 1.1055865287780762} 08/30/2021 20:34:20 - INFO - __main__ - Step 41025: {'lr': 0.0004190209764521269, 'samples': 7876800, 'steps': 41024, 'loss/train': 1.3772032260894775} 08/30/2021 20:34:20 - INFO - __main__ - Step 41026: {'lr': 0.0004190170662740469, 'samples': 7876992, 'steps': 41025, 'loss/train': 1.45427405834198} 08/30/2021 20:34:21 - INFO - __main__ - Step 41027: {'lr': 0.0004190131560198104, 'samples': 7877184, 'steps': 41026, 'loss/train': 1.41404390335083} 08/30/2021 20:34:21 - INFO - __main__ - Step 41028: {'lr': 0.00041900924568941925, 'samples': 7877376, 'steps': 41027, 'loss/train': 1.3327659368515015} 08/30/2021 20:34:21 - INFO - __main__ - Step 41029: {'lr': 0.0004190053352828751, 'samples': 7877568, 'steps': 41028, 'loss/train': 1.8245478868484497} 08/30/2021 20:34:23 - INFO - __main__ - Step 41030: {'lr': 0.00041900142480017974, 'samples': 7877760, 'steps': 41029, 'loss/train': 0.3308565616607666} 08/30/2021 20:34:23 - INFO - __main__ - Step 41031: {'lr': 0.0004189975142413349, 'samples': 7877952, 'steps': 41030, 'loss/train': 1.8376173973083496} 08/30/2021 20:34:24 - INFO - __main__ - Step 41032: {'lr': 0.00041899360360634247, 'samples': 7878144, 'steps': 41031, 'loss/train': 1.2415484189987183} 08/30/2021 20:34:24 - INFO - __main__ - Step 41033: {'lr': 0.0004189896928952041, 'samples': 7878336, 'steps': 41032, 'loss/train': 1.8353732824325562} 08/30/2021 20:34:24 - INFO - __main__ - Step 41034: {'lr': 0.0004189857821079216, 'samples': 7878528, 'steps': 41033, 'loss/train': 1.7956066131591797} 08/30/2021 20:34:26 - INFO - __main__ - Step 41035: {'lr': 0.0004189818712444967, 'samples': 7878720, 'steps': 41034, 'loss/train': 1.1152185201644897} 08/30/2021 20:34:26 - INFO - __main__ - Step 41036: {'lr': 0.0004189779603049312, 'samples': 7878912, 'steps': 41035, 'loss/train': 0.5350671410560608} 08/30/2021 20:34:27 - INFO - __main__ - Step 41037: {'lr': 0.0004189740492892268, 'samples': 7879104, 'steps': 41036, 'loss/train': 1.9817450046539307} 08/30/2021 20:34:27 - INFO - __main__ - Step 41038: {'lr': 0.0004189701381973853, 'samples': 7879296, 'steps': 41037, 'loss/train': 1.8521685600280762} 08/30/2021 20:34:27 - INFO - __main__ - Step 41039: {'lr': 0.00041896622702940846, 'samples': 7879488, 'steps': 41038, 'loss/train': 0.6891412734985352} 08/30/2021 20:34:29 - INFO - __main__ - Step 41040: {'lr': 0.0004189623157852981, 'samples': 7879680, 'steps': 41039, 'loss/train': 1.5992757081985474} 08/30/2021 20:34:30 - INFO - __main__ - Step 41041: {'lr': 0.0004189584044650559, 'samples': 7879872, 'steps': 41040, 'loss/train': 0.8640210032463074} 08/30/2021 20:34:30 - INFO - __main__ - Step 41042: {'lr': 0.0004189544930686837, 'samples': 7880064, 'steps': 41041, 'loss/train': 2.5475447177886963} 08/30/2021 20:34:30 - INFO - __main__ - Step 41043: {'lr': 0.0004189505815961831, 'samples': 7880256, 'steps': 41042, 'loss/train': 1.4506341218948364} 08/30/2021 20:34:31 - INFO - __main__ - Step 41044: {'lr': 0.000418946670047556, 'samples': 7880448, 'steps': 41043, 'loss/train': 1.0487667322158813} 08/30/2021 20:34:32 - INFO - __main__ - Step 41045: {'lr': 0.0004189427584228042, 'samples': 7880640, 'steps': 41044, 'loss/train': 1.7175081968307495} 08/30/2021 20:34:33 - INFO - __main__ - Step 41046: {'lr': 0.0004189388467219294, 'samples': 7880832, 'steps': 41045, 'loss/train': 1.326883316040039} 08/30/2021 20:34:33 - INFO - __main__ - Step 41047: {'lr': 0.0004189349349449333, 'samples': 7881024, 'steps': 41046, 'loss/train': 2.106649875640869} 08/30/2021 20:34:33 - INFO - __main__ - Step 41048: {'lr': 0.00041893102309181773, 'samples': 7881216, 'steps': 41047, 'loss/train': 1.4961119890213013} 08/30/2021 20:34:34 - INFO - __main__ - Step 41049: {'lr': 0.00041892711116258454, 'samples': 7881408, 'steps': 41048, 'loss/train': 1.5439482927322388} 08/30/2021 20:34:35 - INFO - __main__ - Step 41050: {'lr': 0.00041892319915723533, 'samples': 7881600, 'steps': 41049, 'loss/train': 3.664855718612671} 08/30/2021 20:34:36 - INFO - __main__ - Step 41051: {'lr': 0.0004189192870757719, 'samples': 7881792, 'steps': 41050, 'loss/train': 0.9282266497612} 08/30/2021 20:34:36 - INFO - __main__ - Step 41052: {'lr': 0.0004189153749181961, 'samples': 7881984, 'steps': 41051, 'loss/train': 1.2515292167663574} 08/30/2021 20:34:36 - INFO - __main__ - Step 41053: {'lr': 0.00041891146268450963, 'samples': 7882176, 'steps': 41052, 'loss/train': 0.8474591970443726} 08/30/2021 20:34:37 - INFO - __main__ - Step 41054: {'lr': 0.0004189075503747142, 'samples': 7882368, 'steps': 41053, 'loss/train': 1.5076950788497925} 08/30/2021 20:34:37 - INFO - __main__ - Step 41055: {'lr': 0.0004189036379888117, 'samples': 7882560, 'steps': 41054, 'loss/train': 1.2326934337615967} 08/30/2021 20:34:38 - INFO - __main__ - Step 41056: {'lr': 0.00041889972552680387, 'samples': 7882752, 'steps': 41055, 'loss/train': 1.9456889629364014} 08/30/2021 20:34:39 - INFO - __main__ - Step 41057: {'lr': 0.0004188958129886924, 'samples': 7882944, 'steps': 41056, 'loss/train': 2.0564045906066895} 08/30/2021 20:34:39 - INFO - __main__ - Step 41058: {'lr': 0.000418891900374479, 'samples': 7883136, 'steps': 41057, 'loss/train': 1.8548705577850342} 08/30/2021 20:34:40 - INFO - __main__ - Step 41059: {'lr': 0.0004188879876841656, 'samples': 7883328, 'steps': 41058, 'loss/train': 1.7685585021972656} 08/30/2021 20:34:40 - INFO - __main__ - Step 41060: {'lr': 0.0004188840749177538, 'samples': 7883520, 'steps': 41059, 'loss/train': 0.6381027698516846} 08/30/2021 20:34:42 - INFO - __main__ - Step 41061: {'lr': 0.0004188801620752455, 'samples': 7883712, 'steps': 41060, 'loss/train': 1.7532620429992676} 08/30/2021 20:34:42 - INFO - __main__ - Step 41062: {'lr': 0.00041887624915664247, 'samples': 7883904, 'steps': 41061, 'loss/train': 1.5054994821548462} 08/30/2021 20:34:43 - INFO - __main__ - Step 41063: {'lr': 0.0004188723361619463, 'samples': 7884096, 'steps': 41062, 'loss/train': 1.0998432636260986} 08/30/2021 20:34:43 - INFO - __main__ - Step 41064: {'lr': 0.0004188684230911589, 'samples': 7884288, 'steps': 41063, 'loss/train': 1.6960923671722412} 08/30/2021 20:34:43 - INFO - __main__ - Step 41065: {'lr': 0.00041886450994428197, 'samples': 7884480, 'steps': 41064, 'loss/train': 1.6947439908981323} 08/30/2021 20:34:45 - INFO - __main__ - Step 41066: {'lr': 0.0004188605967213174, 'samples': 7884672, 'steps': 41065, 'loss/train': 1.2996693849563599} 08/30/2021 20:34:45 - INFO - __main__ - Step 41067: {'lr': 0.0004188566834222667, 'samples': 7884864, 'steps': 41066, 'loss/train': 1.9593781232833862} 08/30/2021 20:34:46 - INFO - __main__ - Step 41068: {'lr': 0.00041885277004713185, 'samples': 7885056, 'steps': 41067, 'loss/train': 1.4899647235870361} 08/30/2021 20:34:46 - INFO - __main__ - Step 41069: {'lr': 0.0004188488565959146, 'samples': 7885248, 'steps': 41068, 'loss/train': 1.6581939458847046} 08/30/2021 20:34:46 - INFO - __main__ - Step 41070: {'lr': 0.0004188449430686166, 'samples': 7885440, 'steps': 41069, 'loss/train': 1.0358103513717651} 08/30/2021 20:34:48 - INFO - __main__ - Step 41071: {'lr': 0.00041884102946523964, 'samples': 7885632, 'steps': 41070, 'loss/train': 1.515663981437683} 08/30/2021 20:34:48 - INFO - __main__ - Step 41072: {'lr': 0.0004188371157857856, 'samples': 7885824, 'steps': 41071, 'loss/train': 1.427071213722229} 08/30/2021 20:34:49 - INFO - __main__ - Step 41073: {'lr': 0.0004188332020302561, 'samples': 7886016, 'steps': 41072, 'loss/train': 2.385524034500122} 08/30/2021 20:34:49 - INFO - __main__ - Step 41074: {'lr': 0.000418829288198653, 'samples': 7886208, 'steps': 41073, 'loss/train': 1.531606912612915} 08/30/2021 20:34:49 - INFO - __main__ - Step 41075: {'lr': 0.00041882537429097804, 'samples': 7886400, 'steps': 41074, 'loss/train': 1.4643745422363281} 08/30/2021 20:34:51 - INFO - __main__ - Step 41076: {'lr': 0.00041882146030723297, 'samples': 7886592, 'steps': 41075, 'loss/train': 1.5161347389221191} 08/30/2021 20:34:51 - INFO - __main__ - Step 41077: {'lr': 0.0004188175462474195, 'samples': 7886784, 'steps': 41076, 'loss/train': 1.3104255199432373} 08/30/2021 20:34:52 - INFO - __main__ - Step 41078: {'lr': 0.0004188136321115395, 'samples': 7886976, 'steps': 41077, 'loss/train': 1.5040000677108765} 08/30/2021 20:34:52 - INFO - __main__ - Step 41079: {'lr': 0.00041880971789959466, 'samples': 7887168, 'steps': 41078, 'loss/train': 1.5095070600509644} 08/30/2021 20:34:52 - INFO - __main__ - Step 41080: {'lr': 0.0004188058036115868, 'samples': 7887360, 'steps': 41079, 'loss/train': 1.3772051334381104} 08/30/2021 20:34:54 - INFO - __main__ - Step 41081: {'lr': 0.0004188018892475176, 'samples': 7887552, 'steps': 41080, 'loss/train': 1.5810112953186035} 08/30/2021 20:34:55 - INFO - __main__ - Step 41082: {'lr': 0.0004187979748073889, 'samples': 7887744, 'steps': 41081, 'loss/train': 1.3758090734481812} 08/30/2021 20:34:55 - INFO - __main__ - Step 41083: {'lr': 0.0004187940602912024, 'samples': 7887936, 'steps': 41082, 'loss/train': 0.6491727232933044} 08/30/2021 20:34:55 - INFO - __main__ - Step 41084: {'lr': 0.00041879014569895994, 'samples': 7888128, 'steps': 41083, 'loss/train': 1.2365748882293701} 08/30/2021 20:34:56 - INFO - __main__ - Step 41085: {'lr': 0.0004187862310306633, 'samples': 7888320, 'steps': 41084, 'loss/train': 1.220784306526184} 08/30/2021 20:34:56 - INFO - __main__ - Step 41086: {'lr': 0.00041878231628631406, 'samples': 7888512, 'steps': 41085, 'loss/train': 0.9743812084197998} 08/30/2021 20:34:58 - INFO - __main__ - Step 41087: {'lr': 0.0004187784014659142, 'samples': 7888704, 'steps': 41086, 'loss/train': 0.9892066717147827} 08/30/2021 20:34:58 - INFO - __main__ - Step 41088: {'lr': 0.0004187744865694654, 'samples': 7888896, 'steps': 41087, 'loss/train': 1.1738516092300415} 08/30/2021 20:34:59 - INFO - __main__ - Step 41089: {'lr': 0.0004187705715969694, 'samples': 7889088, 'steps': 41088, 'loss/train': 1.317478895187378} 08/30/2021 20:34:59 - INFO - __main__ - Step 41090: {'lr': 0.0004187666565484279, 'samples': 7889280, 'steps': 41089, 'loss/train': 1.4726805686950684} 08/30/2021 20:34:59 - INFO - __main__ - Step 41091: {'lr': 0.0004187627414238428, 'samples': 7889472, 'steps': 41090, 'loss/train': 1.7937759160995483} 08/30/2021 20:35:01 - INFO - __main__ - Step 41092: {'lr': 0.0004187588262232159, 'samples': 7889664, 'steps': 41091, 'loss/train': 1.5622119903564453} 08/30/2021 20:35:01 - INFO - __main__ - Step 41093: {'lr': 0.00041875491094654885, 'samples': 7889856, 'steps': 41092, 'loss/train': 2.9122872352600098} 08/30/2021 20:35:02 - INFO - __main__ - Step 41094: {'lr': 0.0004187509955938434, 'samples': 7890048, 'steps': 41093, 'loss/train': 1.279302954673767} 08/30/2021 20:35:02 - INFO - __main__ - Step 41095: {'lr': 0.0004187470801651013, 'samples': 7890240, 'steps': 41094, 'loss/train': 1.1253182888031006} 08/30/2021 20:35:02 - INFO - __main__ - Step 41096: {'lr': 0.0004187431646603245, 'samples': 7890432, 'steps': 41095, 'loss/train': 1.3879632949829102} 08/30/2021 20:35:04 - INFO - __main__ - Step 41097: {'lr': 0.0004187392490795146, 'samples': 7890624, 'steps': 41096, 'loss/train': 1.0568162202835083} 08/30/2021 20:35:04 - INFO - __main__ - Step 41098: {'lr': 0.00041873533342267336, 'samples': 7890816, 'steps': 41097, 'loss/train': 0.3235325813293457} 08/30/2021 20:35:05 - INFO - __main__ - Step 41099: {'lr': 0.0004187314176898026, 'samples': 7891008, 'steps': 41098, 'loss/train': 2.0620148181915283} 08/30/2021 20:35:05 - INFO - __main__ - Step 41100: {'lr': 0.000418727501880904, 'samples': 7891200, 'steps': 41099, 'loss/train': 1.509527325630188} 08/30/2021 20:35:05 - INFO - __main__ - Step 41101: {'lr': 0.00041872358599597947, 'samples': 7891392, 'steps': 41100, 'loss/train': 1.011954426765442} 08/30/2021 20:35:07 - INFO - __main__ - Step 41102: {'lr': 0.00041871967003503073, 'samples': 7891584, 'steps': 41101, 'loss/train': 1.260717749595642} 08/30/2021 20:35:07 - INFO - __main__ - Step 41103: {'lr': 0.00041871575399805947, 'samples': 7891776, 'steps': 41102, 'loss/train': 0.8088870644569397} 08/30/2021 20:35:08 - INFO - __main__ - Step 41104: {'lr': 0.0004187118378850674, 'samples': 7891968, 'steps': 41103, 'loss/train': 1.5420666933059692} 08/30/2021 20:35:08 - INFO - __main__ - Step 41105: {'lr': 0.00041870792169605654, 'samples': 7892160, 'steps': 41104, 'loss/train': 2.1212775707244873} 08/30/2021 20:35:08 - INFO - __main__ - Step 41106: {'lr': 0.0004187040054310284, 'samples': 7892352, 'steps': 41105, 'loss/train': 1.63030207157135} 08/30/2021 20:35:10 - INFO - __main__ - Step 41107: {'lr': 0.0004187000890899848, 'samples': 7892544, 'steps': 41106, 'loss/train': 1.4593793153762817} 08/30/2021 20:35:11 - INFO - __main__ - Step 41108: {'lr': 0.0004186961726729276, 'samples': 7892736, 'steps': 41107, 'loss/train': 1.0815961360931396} 08/30/2021 20:35:11 - INFO - __main__ - Step 41109: {'lr': 0.0004186922561798585, 'samples': 7892928, 'steps': 41108, 'loss/train': 1.1557074785232544} 08/30/2021 20:35:12 - INFO - __main__ - Step 41110: {'lr': 0.00041868833961077935, 'samples': 7893120, 'steps': 41109, 'loss/train': 1.4992958307266235} 08/30/2021 20:35:12 - INFO - __main__ - Step 41111: {'lr': 0.0004186844229656917, 'samples': 7893312, 'steps': 41110, 'loss/train': 1.2947490215301514} 08/30/2021 20:35:12 - INFO - __main__ - Step 41112: {'lr': 0.0004186805062445975, 'samples': 7893504, 'steps': 41111, 'loss/train': 1.4569388628005981} 08/30/2021 20:35:13 - INFO - __main__ - Step 41113: {'lr': 0.00041867658944749856, 'samples': 7893696, 'steps': 41112, 'loss/train': 0.7800092697143555} 08/30/2021 20:35:14 - INFO - __main__ - Step 41114: {'lr': 0.00041867267257439644, 'samples': 7893888, 'steps': 41113, 'loss/train': 0.17996972799301147} 08/30/2021 20:35:15 - INFO - __main__ - Step 41115: {'lr': 0.00041866875562529305, 'samples': 7894080, 'steps': 41114, 'loss/train': 1.33939528465271} 08/30/2021 20:35:15 - INFO - __main__ - Step 41116: {'lr': 0.0004186648386001901, 'samples': 7894272, 'steps': 41115, 'loss/train': 0.7180574536323547} 08/30/2021 20:35:15 - INFO - __main__ - Step 41117: {'lr': 0.0004186609214990894, 'samples': 7894464, 'steps': 41116, 'loss/train': 2.001742362976074} 08/30/2021 20:35:16 - INFO - __main__ - Step 41118: {'lr': 0.0004186570043219927, 'samples': 7894656, 'steps': 41117, 'loss/train': 2.100369453430176} 08/30/2021 20:35:18 - INFO - __main__ - Step 41119: {'lr': 0.0004186530870689017, 'samples': 7894848, 'steps': 41118, 'loss/train': 1.9339611530303955} 08/30/2021 20:35:18 - INFO - __main__ - Step 41120: {'lr': 0.00041864916973981833, 'samples': 7895040, 'steps': 41119, 'loss/train': 1.5928391218185425} 08/30/2021 20:35:19 - INFO - __main__ - Step 41121: {'lr': 0.0004186452523347442, 'samples': 7895232, 'steps': 41120, 'loss/train': 1.2443376779556274} 08/30/2021 20:35:19 - INFO - __main__ - Step 41122: {'lr': 0.00041864133485368106, 'samples': 7895424, 'steps': 41121, 'loss/train': 1.0927437543869019} 08/30/2021 20:35:19 - INFO - __main__ - Step 41123: {'lr': 0.0004186374172966308, 'samples': 7895616, 'steps': 41122, 'loss/train': 1.3871151208877563} 08/30/2021 20:35:21 - INFO - __main__ - Step 41124: {'lr': 0.0004186334996635951, 'samples': 7895808, 'steps': 41123, 'loss/train': 1.2048654556274414} 08/30/2021 20:35:21 - INFO - __main__ - Step 41125: {'lr': 0.00041862958195457574, 'samples': 7896000, 'steps': 41124, 'loss/train': 1.8102298974990845} 08/30/2021 20:35:22 - INFO - __main__ - Step 41126: {'lr': 0.0004186256641695745, 'samples': 7896192, 'steps': 41125, 'loss/train': 1.4453532695770264} 08/30/2021 20:35:22 - INFO - __main__ - Step 41127: {'lr': 0.00041862174630859315, 'samples': 7896384, 'steps': 41126, 'loss/train': 1.3289623260498047} 08/30/2021 20:35:22 - INFO - __main__ - Step 41128: {'lr': 0.0004186178283716334, 'samples': 7896576, 'steps': 41127, 'loss/train': 1.6302162408828735} 08/30/2021 20:35:24 - INFO - __main__ - Step 41129: {'lr': 0.0004186139103586971, 'samples': 7896768, 'steps': 41128, 'loss/train': 0.8472530245780945} 08/30/2021 20:35:24 - INFO - __main__ - Step 41130: {'lr': 0.00041860999226978605, 'samples': 7896960, 'steps': 41129, 'loss/train': 1.3820165395736694} 08/30/2021 20:35:25 - INFO - __main__ - Step 41131: {'lr': 0.0004186060741049018, 'samples': 7897152, 'steps': 41130, 'loss/train': 1.2151693105697632} 08/30/2021 20:35:25 - INFO - __main__ - Step 41132: {'lr': 0.00041860215586404624, 'samples': 7897344, 'steps': 41131, 'loss/train': 1.4448633193969727} 08/30/2021 20:35:25 - INFO - __main__ - Step 41133: {'lr': 0.00041859823754722127, 'samples': 7897536, 'steps': 41132, 'loss/train': 1.6656172275543213} 08/30/2021 20:35:27 - INFO - __main__ - Step 41134: {'lr': 0.00041859431915442847, 'samples': 7897728, 'steps': 41133, 'loss/train': 1.26059889793396} 08/30/2021 20:35:28 - INFO - __main__ - Step 41135: {'lr': 0.0004185904006856697, 'samples': 7897920, 'steps': 41134, 'loss/train': 2.2405757904052734} 08/30/2021 20:35:28 - INFO - __main__ - Step 41136: {'lr': 0.0004185864821409467, 'samples': 7898112, 'steps': 41135, 'loss/train': 1.5884689092636108} 08/30/2021 20:35:28 - INFO - __main__ - Step 41137: {'lr': 0.00041858256352026124, 'samples': 7898304, 'steps': 41136, 'loss/train': 1.6267186403274536} 08/30/2021 20:35:29 - INFO - __main__ - Step 41138: {'lr': 0.0004185786448236151, 'samples': 7898496, 'steps': 41137, 'loss/train': 0.18343879282474518} 08/30/2021 20:35:30 - INFO - __main__ - Step 41139: {'lr': 0.0004185747260510099, 'samples': 7898688, 'steps': 41138, 'loss/train': 1.2509409189224243} 08/30/2021 20:35:30 - INFO - __main__ - Step 41140: {'lr': 0.0004185708072024476, 'samples': 7898880, 'steps': 41139, 'loss/train': 1.298266053199768} 08/30/2021 20:35:31 - INFO - __main__ - Step 41141: {'lr': 0.0004185668882779299, 'samples': 7899072, 'steps': 41140, 'loss/train': 1.5813754796981812} 08/30/2021 20:35:31 - INFO - __main__ - Step 41142: {'lr': 0.00041856296927745857, 'samples': 7899264, 'steps': 41141, 'loss/train': 1.2210720777511597} 08/30/2021 20:35:32 - INFO - __main__ - Step 41143: {'lr': 0.00041855905020103543, 'samples': 7899456, 'steps': 41142, 'loss/train': 1.44577956199646} 08/30/2021 20:35:33 - INFO - __main__ - Step 41144: {'lr': 0.00041855513104866203, 'samples': 7899648, 'steps': 41143, 'loss/train': 1.6004148721694946} 08/30/2021 20:35:33 - INFO - __main__ - Step 41145: {'lr': 0.00041855121182034037, 'samples': 7899840, 'steps': 41144, 'loss/train': 1.6002393960952759} 08/30/2021 20:35:34 - INFO - __main__ - Step 41146: {'lr': 0.00041854729251607214, 'samples': 7900032, 'steps': 41145, 'loss/train': 1.4809231758117676} 08/30/2021 20:35:34 - INFO - __main__ - Step 41147: {'lr': 0.00041854337313585913, 'samples': 7900224, 'steps': 41146, 'loss/train': 1.6612613201141357} 08/30/2021 20:35:35 - INFO - __main__ - Step 41148: {'lr': 0.000418539453679703, 'samples': 7900416, 'steps': 41147, 'loss/train': 1.6361193656921387} 08/30/2021 20:35:35 - INFO - __main__ - Step 41149: {'lr': 0.0004185355341476057, 'samples': 7900608, 'steps': 41148, 'loss/train': 0.9765746593475342} 08/30/2021 20:35:36 - INFO - __main__ - Step 41150: {'lr': 0.00041853161453956885, 'samples': 7900800, 'steps': 41149, 'loss/train': 1.0844651460647583} 08/30/2021 20:35:37 - INFO - __main__ - Step 41151: {'lr': 0.0004185276948555942, 'samples': 7900992, 'steps': 41150, 'loss/train': 0.9594156742095947} 08/30/2021 20:35:37 - INFO - __main__ - Step 41152: {'lr': 0.0004185237750956836, 'samples': 7901184, 'steps': 41151, 'loss/train': 1.0592890977859497} 08/30/2021 20:35:37 - INFO - __main__ - Step 41153: {'lr': 0.0004185198552598388, 'samples': 7901376, 'steps': 41152, 'loss/train': 1.8063973188400269} 08/30/2021 20:35:38 - INFO - __main__ - Step 41154: {'lr': 0.00041851593534806154, 'samples': 7901568, 'steps': 41153, 'loss/train': 1.9475303888320923} 08/30/2021 20:35:39 - INFO - __main__ - Step 41155: {'lr': 0.0004185120153603536, 'samples': 7901760, 'steps': 41154, 'loss/train': 1.7926287651062012} 08/30/2021 20:35:40 - INFO - __main__ - Step 41156: {'lr': 0.0004185080952967168, 'samples': 7901952, 'steps': 41155, 'loss/train': 1.501604676246643} 08/30/2021 20:35:40 - INFO - __main__ - Step 41157: {'lr': 0.00041850417515715277, 'samples': 7902144, 'steps': 41156, 'loss/train': 1.3695975542068481} 08/30/2021 20:35:40 - INFO - __main__ - Step 41158: {'lr': 0.00041850025494166346, 'samples': 7902336, 'steps': 41157, 'loss/train': 1.0999211072921753} 08/30/2021 20:35:41 - INFO - __main__ - Step 41159: {'lr': 0.0004184963346502504, 'samples': 7902528, 'steps': 41158, 'loss/train': 1.0254195928573608} 08/30/2021 20:35:42 - INFO - __main__ - Step 41160: {'lr': 0.00041849241428291555, 'samples': 7902720, 'steps': 41159, 'loss/train': 1.5622034072875977} 08/30/2021 20:35:43 - INFO - __main__ - Step 41161: {'lr': 0.00041848849383966063, 'samples': 7902912, 'steps': 41160, 'loss/train': 1.7479673624038696} 08/30/2021 20:35:43 - INFO - __main__ - Step 41162: {'lr': 0.0004184845733204874, 'samples': 7903104, 'steps': 41161, 'loss/train': 1.334159016609192} 08/30/2021 20:35:43 - INFO - __main__ - Step 41163: {'lr': 0.00041848065272539765, 'samples': 7903296, 'steps': 41162, 'loss/train': 1.4729894399642944} 08/30/2021 20:35:44 - INFO - __main__ - Step 41164: {'lr': 0.00041847673205439305, 'samples': 7903488, 'steps': 41163, 'loss/train': 1.6320799589157104} 08/30/2021 20:35:46 - INFO - __main__ - Step 41165: {'lr': 0.0004184728113074755, 'samples': 7903680, 'steps': 41164, 'loss/train': 1.4478167295455933} 08/30/2021 20:35:46 - INFO - __main__ - Step 41166: {'lr': 0.00041846889048464665, 'samples': 7903872, 'steps': 41165, 'loss/train': 1.0429561138153076} 08/30/2021 20:35:46 - INFO - __main__ - Step 41167: {'lr': 0.0004184649695859083, 'samples': 7904064, 'steps': 41166, 'loss/train': 1.8019750118255615} 08/30/2021 20:35:47 - INFO - __main__ - Step 41168: {'lr': 0.00041846104861126233, 'samples': 7904256, 'steps': 41167, 'loss/train': 1.6707919836044312} 08/30/2021 20:35:47 - INFO - __main__ - Step 41169: {'lr': 0.0004184571275607103, 'samples': 7904448, 'steps': 41168, 'loss/train': 1.258258581161499} 08/30/2021 20:35:49 - INFO - __main__ - Step 41170: {'lr': 0.0004184532064342542, 'samples': 7904640, 'steps': 41169, 'loss/train': 1.4854133129119873} 08/30/2021 20:35:49 - INFO - __main__ - Step 41171: {'lr': 0.0004184492852318956, 'samples': 7904832, 'steps': 41170, 'loss/train': 1.4144489765167236} 08/30/2021 20:35:49 - INFO - __main__ - Step 41172: {'lr': 0.00041844536395363636, 'samples': 7905024, 'steps': 41171, 'loss/train': 1.8512024879455566} 08/30/2021 20:35:50 - INFO - __main__ - Step 41173: {'lr': 0.00041844144259947825, 'samples': 7905216, 'steps': 41172, 'loss/train': 1.0345797538757324} 08/30/2021 20:35:50 - INFO - __main__ - Step 41174: {'lr': 0.000418437521169423, 'samples': 7905408, 'steps': 41173, 'loss/train': 1.175742268562317} 08/30/2021 20:35:52 - INFO - __main__ - Step 41175: {'lr': 0.0004184335996634725, 'samples': 7905600, 'steps': 41174, 'loss/train': 1.855373501777649} 08/30/2021 20:35:52 - INFO - __main__ - Step 41176: {'lr': 0.00041842967808162834, 'samples': 7905792, 'steps': 41175, 'loss/train': 1.1694527864456177} 08/30/2021 20:35:52 - INFO - __main__ - Step 41177: {'lr': 0.0004184257564238924, 'samples': 7905984, 'steps': 41176, 'loss/train': 1.225437045097351} 08/30/2021 20:35:53 - INFO - __main__ - Step 41178: {'lr': 0.0004184218346902663, 'samples': 7906176, 'steps': 41177, 'loss/train': 1.5754886865615845} 08/30/2021 20:35:53 - INFO - __main__ - Step 41179: {'lr': 0.00041841791288075203, 'samples': 7906368, 'steps': 41178, 'loss/train': 1.413666009902954} 08/30/2021 20:35:53 - INFO - __main__ - Step 41180: {'lr': 0.0004184139909953513, 'samples': 7906560, 'steps': 41179, 'loss/train': 1.5631316900253296} 08/30/2021 20:35:55 - INFO - __main__ - Step 41181: {'lr': 0.0004184100690340657, 'samples': 7906752, 'steps': 41180, 'loss/train': 1.9184987545013428} 08/30/2021 20:35:56 - INFO - __main__ - Step 41182: {'lr': 0.00041840614699689715, 'samples': 7906944, 'steps': 41181, 'loss/train': 1.3525869846343994} 08/30/2021 20:35:56 - INFO - __main__ - Step 41183: {'lr': 0.00041840222488384745, 'samples': 7907136, 'steps': 41182, 'loss/train': 1.8391982316970825} 08/30/2021 20:35:57 - INFO - __main__ - Step 41184: {'lr': 0.00041839830269491823, 'samples': 7907328, 'steps': 41183, 'loss/train': 1.794416069984436} 08/30/2021 20:35:57 - INFO - __main__ - Step 41185: {'lr': 0.0004183943804301114, 'samples': 7907520, 'steps': 41184, 'loss/train': 0.9707196950912476} 08/30/2021 20:35:58 - INFO - __main__ - Step 41186: {'lr': 0.0004183904580894287, 'samples': 7907712, 'steps': 41185, 'loss/train': 1.2880208492279053} 08/30/2021 20:35:59 - INFO - __main__ - Step 41187: {'lr': 0.0004183865356728717, 'samples': 7907904, 'steps': 41186, 'loss/train': 1.4405531883239746} 08/30/2021 20:35:59 - INFO - __main__ - Step 41188: {'lr': 0.0004183826131804424, 'samples': 7908096, 'steps': 41187, 'loss/train': 1.4917259216308594} 08/30/2021 20:36:00 - INFO - __main__ - Step 41189: {'lr': 0.0004183786906121425, 'samples': 7908288, 'steps': 41188, 'loss/train': 1.5126454830169678} 08/30/2021 20:36:00 - INFO - __main__ - Step 41190: {'lr': 0.0004183747679679738, 'samples': 7908480, 'steps': 41189, 'loss/train': 1.4933738708496094} 08/30/2021 20:36:01 - INFO - __main__ - Step 41191: {'lr': 0.000418370845247938, 'samples': 7908672, 'steps': 41190, 'loss/train': 1.5166252851486206} 08/30/2021 20:36:02 - INFO - __main__ - Step 41192: {'lr': 0.0004183669224520369, 'samples': 7908864, 'steps': 41191, 'loss/train': 1.0033994913101196} 08/30/2021 20:36:02 - INFO - __main__ - Step 41193: {'lr': 0.00041836299958027226, 'samples': 7909056, 'steps': 41192, 'loss/train': 1.684597373008728} 08/30/2021 20:36:03 - INFO - __main__ - Step 41194: {'lr': 0.00041835907663264585, 'samples': 7909248, 'steps': 41193, 'loss/train': 1.4224045276641846} 08/30/2021 20:36:03 - INFO - __main__ - Step 41195: {'lr': 0.0004183551536091594, 'samples': 7909440, 'steps': 41194, 'loss/train': 1.156130313873291} 08/30/2021 20:36:05 - INFO - __main__ - Step 41196: {'lr': 0.00041835123050981476, 'samples': 7909632, 'steps': 41195, 'loss/train': 1.3038029670715332} 08/30/2021 20:36:05 - INFO - __main__ - Step 41197: {'lr': 0.00041834730733461366, 'samples': 7909824, 'steps': 41196, 'loss/train': 1.849747896194458} 08/30/2021 20:36:05 - INFO - __main__ - Step 41198: {'lr': 0.0004183433840835578, 'samples': 7910016, 'steps': 41197, 'loss/train': 1.677782416343689} 08/30/2021 20:36:06 - INFO - __main__ - Step 41199: {'lr': 0.0004183394607566491, 'samples': 7910208, 'steps': 41198, 'loss/train': 1.5658795833587646} 08/30/2021 20:36:06 - INFO - __main__ - Step 41200: {'lr': 0.0004183355373538892, 'samples': 7910400, 'steps': 41199, 'loss/train': 1.3178255558013916} 08/30/2021 20:36:07 - INFO - __main__ - Step 41201: {'lr': 0.00041833161387527985, 'samples': 7910592, 'steps': 41200, 'loss/train': 2.0289249420166016} 08/30/2021 20:36:08 - INFO - __main__ - Step 41202: {'lr': 0.0004183276903208228, 'samples': 7910784, 'steps': 41201, 'loss/train': 1.6866228580474854} 08/30/2021 20:36:08 - INFO - __main__ - Step 41203: {'lr': 0.0004183237666905201, 'samples': 7910976, 'steps': 41202, 'loss/train': 2.2124955654144287} 08/30/2021 20:36:09 - INFO - __main__ - Step 41204: {'lr': 0.0004183198429843732, 'samples': 7911168, 'steps': 41203, 'loss/train': 1.5908187627792358} 08/30/2021 20:36:09 - INFO - __main__ - Step 41205: {'lr': 0.00041831591920238396, 'samples': 7911360, 'steps': 41204, 'loss/train': 1.152055025100708} 08/30/2021 20:36:09 - INFO - __main__ - Step 41206: {'lr': 0.0004183119953445542, 'samples': 7911552, 'steps': 41205, 'loss/train': 1.8606780767440796} 08/30/2021 20:36:11 - INFO - __main__ - Step 41207: {'lr': 0.00041830807141088566, 'samples': 7911744, 'steps': 41206, 'loss/train': 1.3945108652114868} 08/30/2021 20:36:11 - INFO - __main__ - Step 41208: {'lr': 0.0004183041474013801, 'samples': 7911936, 'steps': 41207, 'loss/train': 1.9925767183303833} 08/30/2021 20:36:12 - INFO - __main__ - Step 41209: {'lr': 0.00041830022331603925, 'samples': 7912128, 'steps': 41208, 'loss/train': 1.4634283781051636} 08/30/2021 20:36:12 - INFO - __main__ - Step 41210: {'lr': 0.000418296299154865, 'samples': 7912320, 'steps': 41209, 'loss/train': 0.9838194847106934} 08/30/2021 20:36:13 - INFO - __main__ - Step 41211: {'lr': 0.000418292374917859, 'samples': 7912512, 'steps': 41210, 'loss/train': 0.11574981361627579} 08/30/2021 20:36:14 - INFO - __main__ - Step 41212: {'lr': 0.00041828845060502297, 'samples': 7912704, 'steps': 41211, 'loss/train': 1.3025445938110352} 08/30/2021 20:36:14 - INFO - __main__ - Step 41213: {'lr': 0.00041828452621635884, 'samples': 7912896, 'steps': 41212, 'loss/train': 1.4020315408706665} 08/30/2021 20:36:15 - INFO - __main__ - Step 41214: {'lr': 0.0004182806017518682, 'samples': 7913088, 'steps': 41213, 'loss/train': 1.5939383506774902} 08/30/2021 20:36:15 - INFO - __main__ - Step 41215: {'lr': 0.00041827667721155303, 'samples': 7913280, 'steps': 41214, 'loss/train': 1.310970425605774} 08/30/2021 20:36:16 - INFO - __main__ - Step 41216: {'lr': 0.000418272752595415, 'samples': 7913472, 'steps': 41215, 'loss/train': 1.8270729780197144} 08/30/2021 20:36:17 - INFO - __main__ - Step 41217: {'lr': 0.00041826882790345577, 'samples': 7913664, 'steps': 41216, 'loss/train': 1.6407090425491333} 08/30/2021 20:36:18 - INFO - __main__ - Step 41218: {'lr': 0.00041826490313567725, 'samples': 7913856, 'steps': 41217, 'loss/train': 1.4719997644424438} 08/30/2021 20:36:18 - INFO - __main__ - Step 41219: {'lr': 0.0004182609782920812, 'samples': 7914048, 'steps': 41218, 'loss/train': 1.364977240562439} 08/30/2021 20:36:18 - INFO - __main__ - Step 41220: {'lr': 0.0004182570533726693, 'samples': 7914240, 'steps': 41219, 'loss/train': 1.3081600666046143} 08/30/2021 20:36:19 - INFO - __main__ - Step 41221: {'lr': 0.00041825312837744333, 'samples': 7914432, 'steps': 41220, 'loss/train': 1.5823677778244019} 08/30/2021 20:36:19 - INFO - __main__ - Step 41222: {'lr': 0.00041824920330640517, 'samples': 7914624, 'steps': 41221, 'loss/train': 1.9655245542526245} 08/30/2021 20:36:21 - INFO - __main__ - Step 41223: {'lr': 0.0004182452781595565, 'samples': 7914816, 'steps': 41222, 'loss/train': 1.5999000072479248} 08/30/2021 20:36:21 - INFO - __main__ - Step 41224: {'lr': 0.0004182413529368991, 'samples': 7915008, 'steps': 41223, 'loss/train': 1.6796811819076538} 08/30/2021 20:36:21 - INFO - __main__ - Step 41225: {'lr': 0.0004182374276384347, 'samples': 7915200, 'steps': 41224, 'loss/train': 1.036651372909546} 08/30/2021 20:36:22 - INFO - __main__ - Step 41226: {'lr': 0.0004182335022641651, 'samples': 7915392, 'steps': 41225, 'loss/train': 0.069374680519104} 08/30/2021 20:36:22 - INFO - __main__ - Step 41227: {'lr': 0.00041822957681409215, 'samples': 7915584, 'steps': 41226, 'loss/train': 1.2115402221679688} 08/30/2021 20:36:24 - INFO - __main__ - Step 41228: {'lr': 0.00041822565128821757, 'samples': 7915776, 'steps': 41227, 'loss/train': 2.117685079574585} 08/30/2021 20:36:24 - INFO - __main__ - Step 41229: {'lr': 0.00041822172568654306, 'samples': 7915968, 'steps': 41228, 'loss/train': 1.4366461038589478} 08/30/2021 20:36:24 - INFO - __main__ - Step 41230: {'lr': 0.0004182178000090704, 'samples': 7916160, 'steps': 41229, 'loss/train': 1.3132134675979614} 08/30/2021 20:36:25 - INFO - __main__ - Step 41231: {'lr': 0.0004182138742558015, 'samples': 7916352, 'steps': 41230, 'loss/train': 1.5946420431137085} 08/30/2021 20:36:25 - INFO - __main__ - Step 41232: {'lr': 0.00041820994842673787, 'samples': 7916544, 'steps': 41231, 'loss/train': 1.184988021850586} 08/30/2021 20:36:27 - INFO - __main__ - Step 41233: {'lr': 0.00041820602252188156, 'samples': 7916736, 'steps': 41232, 'loss/train': 1.5236599445343018} 08/30/2021 20:36:27 - INFO - __main__ - Step 41234: {'lr': 0.00041820209654123416, 'samples': 7916928, 'steps': 41233, 'loss/train': 0.06497249752283096} 08/30/2021 20:36:28 - INFO - __main__ - Step 41235: {'lr': 0.00041819817048479745, 'samples': 7917120, 'steps': 41234, 'loss/train': 2.5339417457580566} 08/30/2021 20:36:28 - INFO - __main__ - Step 41236: {'lr': 0.0004181942443525734, 'samples': 7917312, 'steps': 41235, 'loss/train': 1.3345385789871216} 08/30/2021 20:36:28 - INFO - __main__ - Step 41237: {'lr': 0.00041819031814456346, 'samples': 7917504, 'steps': 41236, 'loss/train': 1.2078496217727661} 08/30/2021 20:36:29 - INFO - __main__ - Step 41238: {'lr': 0.0004181863918607696, 'samples': 7917696, 'steps': 41237, 'loss/train': 2.0453271865844727} 08/30/2021 20:36:31 - INFO - __main__ - Step 41239: {'lr': 0.00041818246550119354, 'samples': 7917888, 'steps': 41238, 'loss/train': 0.9403941035270691} 08/30/2021 20:36:31 - INFO - __main__ - Step 41240: {'lr': 0.00041817853906583706, 'samples': 7918080, 'steps': 41239, 'loss/train': 1.2611885070800781} 08/30/2021 20:36:31 - INFO - __main__ - Step 41241: {'lr': 0.000418174612554702, 'samples': 7918272, 'steps': 41240, 'loss/train': 1.3527159690856934} 08/30/2021 20:36:32 - INFO - __main__ - Step 41242: {'lr': 0.00041817068596778994, 'samples': 7918464, 'steps': 41241, 'loss/train': 1.6246562004089355} 08/30/2021 20:36:32 - INFO - __main__ - Step 41243: {'lr': 0.0004181667593051028, 'samples': 7918656, 'steps': 41242, 'loss/train': 1.3783191442489624} 08/30/2021 20:36:34 - INFO - __main__ - Step 41244: {'lr': 0.0004181628325666424, 'samples': 7918848, 'steps': 41243, 'loss/train': 1.810223937034607} 08/30/2021 20:36:34 - INFO - __main__ - Step 41245: {'lr': 0.0004181589057524103, 'samples': 7919040, 'steps': 41244, 'loss/train': 1.1112293004989624} 08/30/2021 20:36:35 - INFO - __main__ - Step 41246: {'lr': 0.0004181549788624085, 'samples': 7919232, 'steps': 41245, 'loss/train': 1.631000280380249} 08/30/2021 20:36:35 - INFO - __main__ - Step 41247: {'lr': 0.0004181510518966386, 'samples': 7919424, 'steps': 41246, 'loss/train': 1.891631007194519} 08/30/2021 20:36:35 - INFO - __main__ - Step 41248: {'lr': 0.00041814712485510245, 'samples': 7919616, 'steps': 41247, 'loss/train': 1.438342809677124} 08/30/2021 20:36:36 - INFO - __main__ - Step 41249: {'lr': 0.0004181431977378017, 'samples': 7919808, 'steps': 41248, 'loss/train': 1.6112282276153564} 08/30/2021 20:36:37 - INFO - __main__ - Step 41250: {'lr': 0.00041813927054473835, 'samples': 7920000, 'steps': 41249, 'loss/train': 1.4170291423797607} 08/30/2021 20:36:38 - INFO - __main__ - Step 41251: {'lr': 0.000418135343275914, 'samples': 7920192, 'steps': 41250, 'loss/train': 1.076360821723938} 08/30/2021 20:36:38 - INFO - __main__ - Step 41252: {'lr': 0.0004181314159313305, 'samples': 7920384, 'steps': 41251, 'loss/train': 1.6936711072921753} 08/30/2021 20:36:38 - INFO - __main__ - Step 41253: {'lr': 0.0004181274885109895, 'samples': 7920576, 'steps': 41252, 'loss/train': 1.1377519369125366} 08/30/2021 20:36:39 - INFO - __main__ - Step 41254: {'lr': 0.0004181235610148929, 'samples': 7920768, 'steps': 41253, 'loss/train': 1.7415578365325928} 08/30/2021 20:36:40 - INFO - __main__ - Step 41255: {'lr': 0.0004181196334430424, 'samples': 7920960, 'steps': 41254, 'loss/train': 1.8357971906661987} 08/30/2021 20:36:41 - INFO - __main__ - Step 41256: {'lr': 0.00041811570579543977, 'samples': 7921152, 'steps': 41255, 'loss/train': 1.1603772640228271} 08/30/2021 20:36:41 - INFO - __main__ - Step 41257: {'lr': 0.0004181117780720868, 'samples': 7921344, 'steps': 41256, 'loss/train': 1.2881780862808228} 08/30/2021 20:36:41 - INFO - __main__ - Step 41258: {'lr': 0.00041810785027298524, 'samples': 7921536, 'steps': 41257, 'loss/train': 1.499526023864746} 08/30/2021 20:36:42 - INFO - __main__ - Step 41259: {'lr': 0.00041810392239813695, 'samples': 7921728, 'steps': 41258, 'loss/train': 1.756121277809143} 08/30/2021 20:36:43 - INFO - __main__ - Step 41260: {'lr': 0.00041809999444754353, 'samples': 7921920, 'steps': 41259, 'loss/train': 1.7205058336257935} 08/30/2021 20:36:44 - INFO - __main__ - Step 41261: {'lr': 0.0004180960664212069, 'samples': 7922112, 'steps': 41260, 'loss/train': 1.3784785270690918} 08/30/2021 20:36:44 - INFO - __main__ - Step 41262: {'lr': 0.00041809213831912884, 'samples': 7922304, 'steps': 41261, 'loss/train': 1.8103562593460083} 08/30/2021 20:36:44 - INFO - __main__ - Step 41263: {'lr': 0.0004180882101413109, 'samples': 7922496, 'steps': 41262, 'loss/train': 1.4028496742248535} 08/30/2021 20:36:45 - INFO - __main__ - Step 41264: {'lr': 0.00041808428188775515, 'samples': 7922688, 'steps': 41263, 'loss/train': 1.2405023574829102} 08/30/2021 20:36:45 - INFO - __main__ - Step 41265: {'lr': 0.0004180803535584632, 'samples': 7922880, 'steps': 41264, 'loss/train': 1.0862245559692383} 08/30/2021 20:36:47 - INFO - __main__ - Step 41266: {'lr': 0.0004180764251534368, 'samples': 7923072, 'steps': 41265, 'loss/train': 0.8103510141372681} 08/30/2021 20:36:47 - INFO - __main__ - Step 41267: {'lr': 0.0004180724966726778, 'samples': 7923264, 'steps': 41266, 'loss/train': 0.6353318095207214} 08/30/2021 20:36:47 - INFO - __main__ - Step 41268: {'lr': 0.00041806856811618784, 'samples': 7923456, 'steps': 41267, 'loss/train': 1.0904096364974976} 08/30/2021 20:36:48 - INFO - __main__ - Step 41269: {'lr': 0.00041806463948396876, 'samples': 7923648, 'steps': 41268, 'loss/train': 0.03769872710108757} 08/30/2021 20:36:48 - INFO - __main__ - Step 41270: {'lr': 0.0004180607107760225, 'samples': 7923840, 'steps': 41269, 'loss/train': 1.3871409893035889} 08/30/2021 20:36:50 - INFO - __main__ - Step 41271: {'lr': 0.0004180567819923505, 'samples': 7924032, 'steps': 41270, 'loss/train': 1.689682126045227} 08/30/2021 20:36:51 - INFO - __main__ - Step 41272: {'lr': 0.0004180528531329548, 'samples': 7924224, 'steps': 41271, 'loss/train': 1.1208053827285767} 08/30/2021 20:36:51 - INFO - __main__ - Step 41273: {'lr': 0.00041804892419783715, 'samples': 7924416, 'steps': 41272, 'loss/train': 1.3321681022644043} 08/30/2021 20:36:51 - INFO - __main__ - Step 41274: {'lr': 0.0004180449951869991, 'samples': 7924608, 'steps': 41273, 'loss/train': 2.166050672531128} 08/30/2021 20:36:52 - INFO - __main__ - Step 41275: {'lr': 0.00041804106610044263, 'samples': 7924800, 'steps': 41274, 'loss/train': 1.4557514190673828} 08/30/2021 20:36:52 - INFO - __main__ - Step 41276: {'lr': 0.00041803713693816947, 'samples': 7924992, 'steps': 41275, 'loss/train': 1.561365008354187} 08/30/2021 20:36:53 - INFO - __main__ - Step 41277: {'lr': 0.0004180332077001814, 'samples': 7925184, 'steps': 41276, 'loss/train': 1.3182331323623657} 08/30/2021 20:36:54 - INFO - __main__ - Step 41278: {'lr': 0.0004180292783864801, 'samples': 7925376, 'steps': 41277, 'loss/train': 0.9406395554542542} 08/30/2021 20:36:54 - INFO - __main__ - Step 41279: {'lr': 0.00041802534899706734, 'samples': 7925568, 'steps': 41278, 'loss/train': 1.492274522781372} 08/30/2021 20:36:55 - INFO - __main__ - Step 41280: {'lr': 0.0004180214195319451, 'samples': 7925760, 'steps': 41279, 'loss/train': 0.9967102408409119} 08/30/2021 20:36:55 - INFO - __main__ - Step 41281: {'lr': 0.00041801748999111487, 'samples': 7925952, 'steps': 41280, 'loss/train': 3.0506930351257324} 08/30/2021 20:36:57 - INFO - __main__ - Step 41282: {'lr': 0.0004180135603745786, 'samples': 7926144, 'steps': 41281, 'loss/train': 2.5706984996795654} 08/30/2021 20:36:57 - INFO - __main__ - Step 41283: {'lr': 0.000418009630682338, 'samples': 7926336, 'steps': 41282, 'loss/train': 1.1314271688461304} 08/30/2021 20:36:57 - INFO - __main__ - Step 41284: {'lr': 0.00041800570091439493, 'samples': 7926528, 'steps': 41283, 'loss/train': 0.8926066160202026} 08/30/2021 20:36:58 - INFO - __main__ - Step 41285: {'lr': 0.000418001771070751, 'samples': 7926720, 'steps': 41284, 'loss/train': 1.5769743919372559} 08/30/2021 20:36:58 - INFO - __main__ - Step 41286: {'lr': 0.0004179978411514081, 'samples': 7926912, 'steps': 41285, 'loss/train': 0.6704384088516235} 08/30/2021 20:37:00 - INFO - __main__ - Step 41287: {'lr': 0.000417993911156368, 'samples': 7927104, 'steps': 41286, 'loss/train': 1.2842239141464233} 08/30/2021 20:37:00 - INFO - __main__ - Step 41288: {'lr': 0.00041798998108563234, 'samples': 7927296, 'steps': 41287, 'loss/train': 1.8976343870162964} 08/30/2021 20:37:01 - INFO - __main__ - Step 41289: {'lr': 0.00041798605093920307, 'samples': 7927488, 'steps': 41288, 'loss/train': 1.4811615943908691} 08/30/2021 20:37:01 - INFO - __main__ - Step 41290: {'lr': 0.00041798212071708185, 'samples': 7927680, 'steps': 41289, 'loss/train': 1.5192782878875732} 08/30/2021 20:37:02 - INFO - __main__ - Step 41291: {'lr': 0.0004179781904192704, 'samples': 7927872, 'steps': 41290, 'loss/train': 1.0847587585449219} 08/30/2021 20:37:02 - INFO - __main__ - Step 41292: {'lr': 0.00041797426004577066, 'samples': 7928064, 'steps': 41291, 'loss/train': 1.0678871870040894} 08/30/2021 20:37:05 - INFO - __main__ - Step 41293: {'lr': 0.00041797032959658433, 'samples': 7928256, 'steps': 41292, 'loss/train': 0.04964858293533325} 08/30/2021 20:37:05 - INFO - __main__ - Step 41294: {'lr': 0.0004179663990717131, 'samples': 7928448, 'steps': 41293, 'loss/train': 0.8260741233825684} 08/30/2021 20:37:05 - INFO - __main__ - Step 41295: {'lr': 0.0004179624684711588, 'samples': 7928640, 'steps': 41294, 'loss/train': 1.6288862228393555} 08/30/2021 20:37:06 - INFO - __main__ - Step 41296: {'lr': 0.0004179585377949232, 'samples': 7928832, 'steps': 41295, 'loss/train': 1.1667031049728394} 08/30/2021 20:37:06 - INFO - __main__ - Step 41297: {'lr': 0.0004179546070430082, 'samples': 7929024, 'steps': 41296, 'loss/train': 1.6510547399520874} 08/30/2021 20:37:07 - INFO - __main__ - Step 41298: {'lr': 0.0004179506762154153, 'samples': 7929216, 'steps': 41297, 'loss/train': 1.3736963272094727} 08/30/2021 20:37:07 - INFO - __main__ - Step 41299: {'lr': 0.0004179467453121465, 'samples': 7929408, 'steps': 41298, 'loss/train': 0.03156067430973053} 08/30/2021 20:37:08 - INFO - __main__ - Step 41300: {'lr': 0.0004179428143332035, 'samples': 7929600, 'steps': 41299, 'loss/train': 0.03029993362724781} 08/30/2021 20:37:09 - INFO - __main__ - Step 41301: {'lr': 0.000417938883278588, 'samples': 7929792, 'steps': 41300, 'loss/train': 1.6002839803695679} 08/30/2021 20:37:09 - INFO - __main__ - Step 41302: {'lr': 0.0004179349521483018, 'samples': 7929984, 'steps': 41301, 'loss/train': 0.8408775329589844} 08/30/2021 20:37:10 - INFO - __main__ - Step 41303: {'lr': 0.00041793102094234673, 'samples': 7930176, 'steps': 41302, 'loss/train': 0.9855254888534546} 08/30/2021 20:37:10 - INFO - __main__ - Step 41304: {'lr': 0.00041792708966072455, 'samples': 7930368, 'steps': 41303, 'loss/train': 0.8408874273300171} 08/30/2021 20:37:11 - INFO - __main__ - Step 41305: {'lr': 0.0004179231583034371, 'samples': 7930560, 'steps': 41304, 'loss/train': 1.7330666780471802} 08/30/2021 20:37:12 - INFO - __main__ - Step 41306: {'lr': 0.0004179192268704859, 'samples': 7930752, 'steps': 41305, 'loss/train': 1.4362725019454956} 08/30/2021 20:37:12 - INFO - __main__ - Step 41307: {'lr': 0.000417915295361873, 'samples': 7930944, 'steps': 41306, 'loss/train': 1.5189247131347656} 08/30/2021 20:37:13 - INFO - __main__ - Step 41308: {'lr': 0.0004179113637776, 'samples': 7931136, 'steps': 41307, 'loss/train': 1.153175711631775} 08/30/2021 20:37:13 - INFO - __main__ - Step 41309: {'lr': 0.0004179074321176688, 'samples': 7931328, 'steps': 41308, 'loss/train': 5.87996768951416} 08/30/2021 20:37:14 - INFO - __main__ - Step 41310: {'lr': 0.000417903500382081, 'samples': 7931520, 'steps': 41309, 'loss/train': 1.574993371963501} 08/30/2021 20:37:15 - INFO - __main__ - Step 41311: {'lr': 0.00041789956857083853, 'samples': 7931712, 'steps': 41310, 'loss/train': 1.482379674911499} 08/30/2021 20:37:15 - INFO - __main__ - Step 41312: {'lr': 0.00041789563668394314, 'samples': 7931904, 'steps': 41311, 'loss/train': 1.3061654567718506} 08/30/2021 20:37:15 - INFO - __main__ - Step 41313: {'lr': 0.0004178917047213965, 'samples': 7932096, 'steps': 41312, 'loss/train': 1.6246038675308228} 08/30/2021 20:37:16 - INFO - __main__ - Step 41314: {'lr': 0.00041788777268320055, 'samples': 7932288, 'steps': 41313, 'loss/train': 1.4020289182662964} 08/30/2021 20:37:18 - INFO - __main__ - Step 41315: {'lr': 0.00041788384056935693, 'samples': 7932480, 'steps': 41314, 'loss/train': 1.9095011949539185} 08/30/2021 20:37:18 - INFO - __main__ - Step 41316: {'lr': 0.0004178799083798673, 'samples': 7932672, 'steps': 41315, 'loss/train': 0.05646982043981552} 08/30/2021 20:37:19 - INFO - __main__ - Step 41317: {'lr': 0.00041787597611473375, 'samples': 7932864, 'steps': 41316, 'loss/train': 0.280333012342453} 08/30/2021 20:37:19 - INFO - __main__ - Step 41318: {'lr': 0.00041787204377395783, 'samples': 7933056, 'steps': 41317, 'loss/train': 1.6196471452713013} 08/30/2021 20:37:19 - INFO - __main__ - Step 41319: {'lr': 0.0004178681113575413, 'samples': 7933248, 'steps': 41318, 'loss/train': 2.8572938442230225} 08/30/2021 20:37:20 - INFO - __main__ - Step 41320: {'lr': 0.00041786417886548606, 'samples': 7933440, 'steps': 41319, 'loss/train': 1.4754540920257568} 08/30/2021 20:37:21 - INFO - __main__ - Step 41321: {'lr': 0.0004178602462977937, 'samples': 7933632, 'steps': 41320, 'loss/train': 1.090175986289978} 08/30/2021 20:37:22 - INFO - __main__ - Step 41322: {'lr': 0.0004178563136544662, 'samples': 7933824, 'steps': 41321, 'loss/train': 0.8622119426727295} 08/30/2021 20:37:22 - INFO - __main__ - Step 41323: {'lr': 0.0004178523809355053, 'samples': 7934016, 'steps': 41322, 'loss/train': 1.6504896879196167} 08/30/2021 20:37:22 - INFO - __main__ - Step 41324: {'lr': 0.00041784844814091263, 'samples': 7934208, 'steps': 41323, 'loss/train': 1.3027901649475098} 08/30/2021 20:37:23 - INFO - __main__ - Step 41325: {'lr': 0.00041784451527069, 'samples': 7934400, 'steps': 41324, 'loss/train': 1.4094593524932861} 08/30/2021 20:37:24 - INFO - __main__ - Step 41326: {'lr': 0.0004178405823248392, 'samples': 7934592, 'steps': 41325, 'loss/train': 1.3172539472579956} 08/30/2021 20:37:25 - INFO - __main__ - Step 41327: {'lr': 0.0004178366493033621, 'samples': 7934784, 'steps': 41326, 'loss/train': 1.769757628440857} 08/30/2021 20:37:25 - INFO - __main__ - Step 41328: {'lr': 0.0004178327162062604, 'samples': 7934976, 'steps': 41327, 'loss/train': 1.6797744035720825} 08/30/2021 20:37:25 - INFO - __main__ - Step 41329: {'lr': 0.00041782878303353577, 'samples': 7935168, 'steps': 41328, 'loss/train': 1.444676399230957} 08/30/2021 20:37:26 - INFO - __main__ - Step 41330: {'lr': 0.0004178248497851902, 'samples': 7935360, 'steps': 41329, 'loss/train': 1.2998301982879639} 08/30/2021 20:37:27 - INFO - __main__ - Step 41331: {'lr': 0.00041782091646122533, 'samples': 7935552, 'steps': 41330, 'loss/train': 1.433681845664978} 08/30/2021 20:37:28 - INFO - __main__ - Step 41332: {'lr': 0.00041781698306164283, 'samples': 7935744, 'steps': 41331, 'loss/train': 1.5670560598373413} 08/30/2021 20:37:28 - INFO - __main__ - Step 41333: {'lr': 0.0004178130495864447, 'samples': 7935936, 'steps': 41332, 'loss/train': 0.9618202447891235} 08/30/2021 20:37:28 - INFO - __main__ - Step 41334: {'lr': 0.00041780911603563254, 'samples': 7936128, 'steps': 41333, 'loss/train': 2.1129024028778076} 08/30/2021 20:37:29 - INFO - __main__ - Step 41335: {'lr': 0.00041780518240920817, 'samples': 7936320, 'steps': 41334, 'loss/train': 1.4177297353744507} 08/30/2021 20:37:30 - INFO - __main__ - Step 41336: {'lr': 0.0004178012487071734, 'samples': 7936512, 'steps': 41335, 'loss/train': 1.4227393865585327} 08/30/2021 20:37:31 - INFO - __main__ - Step 41337: {'lr': 0.00041779731492953, 'samples': 7936704, 'steps': 41336, 'loss/train': 1.8759641647338867} 08/30/2021 20:37:31 - INFO - __main__ - Step 41338: {'lr': 0.0004177933810762797, 'samples': 7936896, 'steps': 41337, 'loss/train': 0.45274025201797485} 08/30/2021 20:37:31 - INFO - __main__ - Step 41339: {'lr': 0.00041778944714742435, 'samples': 7937088, 'steps': 41338, 'loss/train': 1.0199908018112183} 08/30/2021 20:37:32 - INFO - __main__ - Step 41340: {'lr': 0.00041778551314296556, 'samples': 7937280, 'steps': 41339, 'loss/train': 0.9563559293746948} 08/30/2021 20:37:33 - INFO - __main__ - Step 41341: {'lr': 0.00041778157906290525, 'samples': 7937472, 'steps': 41340, 'loss/train': 1.699133276939392} 08/30/2021 20:37:34 - INFO - __main__ - Step 41342: {'lr': 0.00041777764490724515, 'samples': 7937664, 'steps': 41341, 'loss/train': 1.13656747341156} 08/30/2021 20:37:34 - INFO - __main__ - Step 41343: {'lr': 0.00041777371067598705, 'samples': 7937856, 'steps': 41342, 'loss/train': 0.8937574028968811} 08/30/2021 20:37:34 - INFO - __main__ - Step 41344: {'lr': 0.00041776977636913274, 'samples': 7938048, 'steps': 41343, 'loss/train': 1.0681222677230835} 08/30/2021 20:37:35 - INFO - __main__ - Step 41345: {'lr': 0.0004177658419866839, 'samples': 7938240, 'steps': 41344, 'loss/train': 0.837557315826416} 08/30/2021 20:37:35 - INFO - __main__ - Step 41346: {'lr': 0.0004177619075286424, 'samples': 7938432, 'steps': 41345, 'loss/train': 1.1064404249191284} 08/30/2021 20:37:37 - INFO - __main__ - Step 41347: {'lr': 0.00041775797299500997, 'samples': 7938624, 'steps': 41346, 'loss/train': 1.5079741477966309} 08/30/2021 20:37:38 - INFO - __main__ - Step 41348: {'lr': 0.0004177540383857883, 'samples': 7938816, 'steps': 41347, 'loss/train': 2.0026466846466064} 08/30/2021 20:37:38 - INFO - __main__ - Step 41349: {'lr': 0.0004177501037009793, 'samples': 7939008, 'steps': 41348, 'loss/train': 1.864587426185608} 08/30/2021 20:37:38 - INFO - __main__ - Step 41350: {'lr': 0.0004177461689405847, 'samples': 7939200, 'steps': 41349, 'loss/train': 1.3859156370162964} 08/30/2021 20:37:39 - INFO - __main__ - Step 41351: {'lr': 0.00041774223410460633, 'samples': 7939392, 'steps': 41350, 'loss/train': 1.5511083602905273} 08/30/2021 20:37:40 - INFO - __main__ - Step 41352: {'lr': 0.00041773829919304584, 'samples': 7939584, 'steps': 41351, 'loss/train': 1.1542161703109741} 08/30/2021 20:37:41 - INFO - __main__ - Step 41353: {'lr': 0.000417734364205905, 'samples': 7939776, 'steps': 41352, 'loss/train': 1.1124930381774902} 08/30/2021 20:37:41 - INFO - __main__ - Step 41354: {'lr': 0.0004177304291431857, 'samples': 7939968, 'steps': 41353, 'loss/train': 2.221064329147339} 08/30/2021 20:37:41 - INFO - __main__ - Step 41355: {'lr': 0.00041772649400488967, 'samples': 7940160, 'steps': 41354, 'loss/train': 1.5445185899734497} 08/30/2021 20:37:42 - INFO - __main__ - Step 41356: {'lr': 0.0004177225587910186, 'samples': 7940352, 'steps': 41355, 'loss/train': 1.1371402740478516} 08/30/2021 20:37:43 - INFO - __main__ - Step 41357: {'lr': 0.0004177186235015744, 'samples': 7940544, 'steps': 41356, 'loss/train': 1.7798751592636108} 08/30/2021 20:37:44 - INFO - __main__ - Step 41358: {'lr': 0.0004177146881365588, 'samples': 7940736, 'steps': 41357, 'loss/train': 1.2525073289871216} 08/30/2021 20:37:44 - INFO - __main__ - Step 41359: {'lr': 0.00041771075269597354, 'samples': 7940928, 'steps': 41358, 'loss/train': 1.3471342325210571} 08/30/2021 20:37:44 - INFO - __main__ - Step 41360: {'lr': 0.0004177068171798204, 'samples': 7941120, 'steps': 41359, 'loss/train': 1.2018510103225708} 08/30/2021 20:37:45 - INFO - __main__ - Step 41361: {'lr': 0.0004177028815881011, 'samples': 7941312, 'steps': 41360, 'loss/train': 1.8874595165252686} 08/30/2021 20:37:46 - INFO - __main__ - Step 41362: {'lr': 0.00041769894592081746, 'samples': 7941504, 'steps': 41361, 'loss/train': 1.9354338645935059} 08/30/2021 20:37:47 - INFO - __main__ - Step 41363: {'lr': 0.0004176950101779713, 'samples': 7941696, 'steps': 41362, 'loss/train': 0.7589229345321655} 08/30/2021 20:37:47 - INFO - __main__ - Step 41364: {'lr': 0.00041769107435956444, 'samples': 7941888, 'steps': 41363, 'loss/train': 1.5308563709259033} 08/30/2021 20:37:48 - INFO - __main__ - Step 41365: {'lr': 0.00041768713846559844, 'samples': 7942080, 'steps': 41364, 'loss/train': 1.4399404525756836} 08/30/2021 20:37:48 - INFO - __main__ - Step 41366: {'lr': 0.00041768320249607527, 'samples': 7942272, 'steps': 41365, 'loss/train': 1.1068576574325562} 08/30/2021 20:37:49 - INFO - __main__ - Step 41367: {'lr': 0.00041767926645099664, 'samples': 7942464, 'steps': 41366, 'loss/train': 1.0698051452636719} 08/30/2021 20:37:50 - INFO - __main__ - Step 41368: {'lr': 0.00041767533033036425, 'samples': 7942656, 'steps': 41367, 'loss/train': 2.2422380447387695} 08/30/2021 20:37:50 - INFO - __main__ - Step 41369: {'lr': 0.00041767139413418, 'samples': 7942848, 'steps': 41368, 'loss/train': 1.1421459913253784} 08/30/2021 20:37:51 - INFO - __main__ - Step 41370: {'lr': 0.00041766745786244564, 'samples': 7943040, 'steps': 41369, 'loss/train': 1.7020671367645264} 08/30/2021 20:37:51 - INFO - __main__ - Step 41371: {'lr': 0.00041766352151516284, 'samples': 7943232, 'steps': 41370, 'loss/train': 2.0855867862701416} 08/30/2021 20:37:52 - INFO - __main__ - Step 41372: {'lr': 0.0004176595850923335, 'samples': 7943424, 'steps': 41371, 'loss/train': 0.4040973484516144} 08/30/2021 20:37:53 - INFO - __main__ - Step 41373: {'lr': 0.0004176556485939593, 'samples': 7943616, 'steps': 41372, 'loss/train': 0.9285533428192139} 08/30/2021 20:37:53 - INFO - __main__ - Step 41374: {'lr': 0.00041765171202004205, 'samples': 7943808, 'steps': 41373, 'loss/train': 1.5626639127731323} 08/30/2021 20:37:54 - INFO - __main__ - Step 41375: {'lr': 0.00041764777537058354, 'samples': 7944000, 'steps': 41374, 'loss/train': 1.3051823377609253} 08/30/2021 20:37:54 - INFO - __main__ - Step 41376: {'lr': 0.0004176438386455855, 'samples': 7944192, 'steps': 41375, 'loss/train': 1.5558784008026123} 08/30/2021 20:37:55 - INFO - __main__ - Step 41377: {'lr': 0.00041763990184504984, 'samples': 7944384, 'steps': 41376, 'loss/train': 1.1090941429138184} 08/30/2021 20:37:56 - INFO - __main__ - Step 41378: {'lr': 0.00041763596496897817, 'samples': 7944576, 'steps': 41377, 'loss/train': 1.9707355499267578} 08/30/2021 20:37:56 - INFO - __main__ - Step 41379: {'lr': 0.00041763202801737225, 'samples': 7944768, 'steps': 41378, 'loss/train': 1.4138187170028687} 08/30/2021 20:37:56 - INFO - __main__ - Step 41380: {'lr': 0.00041762809099023403, 'samples': 7944960, 'steps': 41379, 'loss/train': 1.791852355003357} 08/30/2021 20:37:57 - INFO - __main__ - Step 41381: {'lr': 0.00041762415388756514, 'samples': 7945152, 'steps': 41380, 'loss/train': 1.7626186609268188} 08/30/2021 20:37:58 - INFO - __main__ - Step 41382: {'lr': 0.00041762021670936736, 'samples': 7945344, 'steps': 41381, 'loss/train': 1.1181529760360718} 08/30/2021 20:37:59 - INFO - __main__ - Step 41383: {'lr': 0.0004176162794556425, 'samples': 7945536, 'steps': 41382, 'loss/train': 1.6964209079742432} 08/30/2021 20:37:59 - INFO - __main__ - Step 41384: {'lr': 0.0004176123421263923, 'samples': 7945728, 'steps': 41383, 'loss/train': 1.393151044845581} 08/30/2021 20:38:00 - INFO - __main__ - Step 41385: {'lr': 0.00041760840472161866, 'samples': 7945920, 'steps': 41384, 'loss/train': 1.5543761253356934} 08/30/2021 20:38:00 - INFO - __main__ - Step 41386: {'lr': 0.0004176044672413232, 'samples': 7946112, 'steps': 41385, 'loss/train': 2.9954159259796143} 08/30/2021 20:38:00 - INFO - __main__ - Step 41387: {'lr': 0.00041760052968550776, 'samples': 7946304, 'steps': 41386, 'loss/train': 1.5306628942489624} 08/30/2021 20:38:02 - INFO - __main__ - Step 41388: {'lr': 0.0004175965920541741, 'samples': 7946496, 'steps': 41387, 'loss/train': 1.3748397827148438} 08/30/2021 20:38:02 - INFO - __main__ - Step 41389: {'lr': 0.00041759265434732404, 'samples': 7946688, 'steps': 41388, 'loss/train': 1.5823618173599243} 08/30/2021 20:38:03 - INFO - __main__ - Step 41390: {'lr': 0.00041758871656495927, 'samples': 7946880, 'steps': 41389, 'loss/train': 1.0068360567092896} 08/30/2021 20:38:03 - INFO - __main__ - Step 41391: {'lr': 0.00041758477870708165, 'samples': 7947072, 'steps': 41390, 'loss/train': 0.8377043008804321} 08/30/2021 20:38:03 - INFO - __main__ - Step 41392: {'lr': 0.0004175808407736929, 'samples': 7947264, 'steps': 41391, 'loss/train': 1.8361799716949463} 08/30/2021 20:38:05 - INFO - __main__ - Step 41393: {'lr': 0.00041757690276479474, 'samples': 7947456, 'steps': 41392, 'loss/train': 1.3056310415267944} 08/30/2021 20:38:05 - INFO - __main__ - Step 41394: {'lr': 0.0004175729646803891, 'samples': 7947648, 'steps': 41393, 'loss/train': 1.055996060371399} 08/30/2021 20:38:05 - INFO - __main__ - Step 41395: {'lr': 0.00041756902652047767, 'samples': 7947840, 'steps': 41394, 'loss/train': 1.4928996562957764} 08/30/2021 20:38:06 - INFO - __main__ - Step 41396: {'lr': 0.0004175650882850622, 'samples': 7948032, 'steps': 41395, 'loss/train': 1.640062689781189} 08/30/2021 20:38:06 - INFO - __main__ - Step 41397: {'lr': 0.0004175611499741445, 'samples': 7948224, 'steps': 41396, 'loss/train': 1.1785069704055786} 08/30/2021 20:38:08 - INFO - __main__ - Step 41398: {'lr': 0.00041755721158772633, 'samples': 7948416, 'steps': 41397, 'loss/train': 1.6382743120193481} 08/30/2021 20:38:08 - INFO - __main__ - Step 41399: {'lr': 0.00041755327312580944, 'samples': 7948608, 'steps': 41398, 'loss/train': 1.462915301322937} 08/30/2021 20:38:08 - INFO - __main__ - Step 41400: {'lr': 0.0004175493345883956, 'samples': 7948800, 'steps': 41399, 'loss/train': 1.6920114755630493} 08/30/2021 20:38:09 - INFO - __main__ - Step 41401: {'lr': 0.0004175453959754867, 'samples': 7948992, 'steps': 41400, 'loss/train': 1.072318196296692} 08/30/2021 20:38:09 - INFO - __main__ - Step 41402: {'lr': 0.00041754145728708434, 'samples': 7949184, 'steps': 41401, 'loss/train': 1.888789415359497} 08/30/2021 20:38:11 - INFO - __main__ - Step 41403: {'lr': 0.0004175375185231904, 'samples': 7949376, 'steps': 41402, 'loss/train': 1.2134674787521362} 08/30/2021 20:38:12 - INFO - __main__ - Step 41404: {'lr': 0.00041753357968380675, 'samples': 7949568, 'steps': 41403, 'loss/train': 1.6988017559051514} 08/30/2021 20:38:12 - INFO - __main__ - Step 41405: {'lr': 0.00041752964076893496, 'samples': 7949760, 'steps': 41404, 'loss/train': 2.844590902328491} 08/30/2021 20:38:13 - INFO - __main__ - Step 41406: {'lr': 0.00041752570177857695, 'samples': 7949952, 'steps': 41405, 'loss/train': 1.5071130990982056} 08/30/2021 20:38:13 - INFO - __main__ - Step 41407: {'lr': 0.0004175217627127344, 'samples': 7950144, 'steps': 41406, 'loss/train': 1.532647967338562} 08/30/2021 20:38:15 - INFO - __main__ - Step 41408: {'lr': 0.0004175178235714091, 'samples': 7950336, 'steps': 41407, 'loss/train': 1.46100914478302} 08/30/2021 20:38:15 - INFO - __main__ - Step 41409: {'lr': 0.0004175138843546029, 'samples': 7950528, 'steps': 41408, 'loss/train': 0.05259615182876587} 08/30/2021 20:38:16 - INFO - __main__ - Step 41410: {'lr': 0.00041750994506231756, 'samples': 7950720, 'steps': 41409, 'loss/train': 1.2466177940368652} 08/30/2021 20:38:16 - INFO - __main__ - Step 41411: {'lr': 0.00041750600569455474, 'samples': 7950912, 'steps': 41410, 'loss/train': 1.555919885635376} 08/30/2021 20:38:16 - INFO - __main__ - Step 41412: {'lr': 0.0004175020662513164, 'samples': 7951104, 'steps': 41411, 'loss/train': 2.918903350830078} 08/30/2021 20:38:17 - INFO - __main__ - Step 41413: {'lr': 0.0004174981267326041, 'samples': 7951296, 'steps': 41412, 'loss/train': 1.8798463344573975} 08/30/2021 20:38:18 - INFO - __main__ - Step 41414: {'lr': 0.0004174941871384198, 'samples': 7951488, 'steps': 41413, 'loss/train': 1.8909170627593994} 08/30/2021 20:38:18 - INFO - __main__ - Step 41415: {'lr': 0.00041749024746876517, 'samples': 7951680, 'steps': 41414, 'loss/train': 1.196697473526001} 08/30/2021 20:38:19 - INFO - __main__ - Step 41416: {'lr': 0.00041748630772364204, 'samples': 7951872, 'steps': 41415, 'loss/train': 1.4976251125335693} 08/30/2021 20:38:19 - INFO - __main__ - Step 41417: {'lr': 0.00041748236790305215, 'samples': 7952064, 'steps': 41416, 'loss/train': 0.9984554648399353} 08/30/2021 20:38:20 - INFO - __main__ - Step 41418: {'lr': 0.0004174784280069973, 'samples': 7952256, 'steps': 41417, 'loss/train': 1.6519157886505127} 08/30/2021 20:38:21 - INFO - __main__ - Step 41419: {'lr': 0.00041747448803547925, 'samples': 7952448, 'steps': 41418, 'loss/train': 1.4101771116256714} 08/30/2021 20:38:22 - INFO - __main__ - Step 41420: {'lr': 0.0004174705479884998, 'samples': 7952640, 'steps': 41419, 'loss/train': 1.2860792875289917} 08/30/2021 20:38:22 - INFO - __main__ - Step 41421: {'lr': 0.0004174666078660607, 'samples': 7952832, 'steps': 41420, 'loss/train': 1.4192967414855957} 08/30/2021 20:38:23 - INFO - __main__ - Step 41422: {'lr': 0.00041746266766816377, 'samples': 7953024, 'steps': 41421, 'loss/train': 1.8272082805633545} 08/30/2021 20:38:23 - INFO - __main__ - Step 41423: {'lr': 0.0004174587273948106, 'samples': 7953216, 'steps': 41422, 'loss/train': 0.573168158531189} 08/30/2021 20:38:24 - INFO - __main__ - Step 41424: {'lr': 0.0004174547870460033, 'samples': 7953408, 'steps': 41423, 'loss/train': 1.5065640211105347} 08/30/2021 20:38:25 - INFO - __main__ - Step 41425: {'lr': 0.0004174508466217434, 'samples': 7953600, 'steps': 41424, 'loss/train': 1.6666555404663086} 08/30/2021 20:38:25 - INFO - __main__ - Step 41426: {'lr': 0.00041744690612203263, 'samples': 7953792, 'steps': 41425, 'loss/train': 1.2866551876068115} 08/30/2021 20:38:26 - INFO - __main__ - Step 41427: {'lr': 0.00041744296554687294, 'samples': 7953984, 'steps': 41426, 'loss/train': 1.8438634872436523} 08/30/2021 20:38:26 - INFO - __main__ - Step 41428: {'lr': 0.00041743902489626606, 'samples': 7954176, 'steps': 41427, 'loss/train': 1.6337019205093384} 08/30/2021 20:38:27 - INFO - __main__ - Step 41429: {'lr': 0.0004174350841702137, 'samples': 7954368, 'steps': 41428, 'loss/train': 2.0448713302612305} 08/30/2021 20:38:28 - INFO - __main__ - Step 41430: {'lr': 0.0004174311433687177, 'samples': 7954560, 'steps': 41429, 'loss/train': 1.7109603881835938} 08/30/2021 20:38:28 - INFO - __main__ - Step 41431: {'lr': 0.00041742720249177975, 'samples': 7954752, 'steps': 41430, 'loss/train': 2.66896653175354} 08/30/2021 20:38:29 - INFO - __main__ - Step 41432: {'lr': 0.0004174232615394018, 'samples': 7954944, 'steps': 41431, 'loss/train': 1.5298560857772827} 08/30/2021 20:38:29 - INFO - __main__ - Step 41433: {'lr': 0.00041741932051158535, 'samples': 7955136, 'steps': 41432, 'loss/train': 0.978148877620697} 08/30/2021 20:38:29 - INFO - __main__ - Step 41434: {'lr': 0.00041741537940833247, 'samples': 7955328, 'steps': 41433, 'loss/train': 1.3200790882110596} 08/30/2021 20:38:31 - INFO - __main__ - Step 41435: {'lr': 0.00041741143822964476, 'samples': 7955520, 'steps': 41434, 'loss/train': 1.3774951696395874} 08/30/2021 20:38:31 - INFO - __main__ - Step 41436: {'lr': 0.00041740749697552406, 'samples': 7955712, 'steps': 41435, 'loss/train': 0.8942598104476929} 08/30/2021 20:38:32 - INFO - __main__ - Step 41437: {'lr': 0.0004174035556459721, 'samples': 7955904, 'steps': 41436, 'loss/train': 0.5630281567573547} 08/30/2021 20:38:32 - INFO - __main__ - Step 41438: {'lr': 0.0004173996142409907, 'samples': 7956096, 'steps': 41437, 'loss/train': 1.3800159692764282} 08/30/2021 20:38:34 - INFO - __main__ - Step 41439: {'lr': 0.0004173956727605816, 'samples': 7956288, 'steps': 41438, 'loss/train': 0.20855551958084106} 08/30/2021 20:38:34 - INFO - __main__ - Step 41440: {'lr': 0.00041739173120474663, 'samples': 7956480, 'steps': 41439, 'loss/train': 0.7213126420974731} 08/30/2021 20:38:35 - INFO - __main__ - Step 41441: {'lr': 0.00041738778957348745, 'samples': 7956672, 'steps': 41440, 'loss/train': 1.5504837036132812} 08/30/2021 20:38:35 - INFO - __main__ - Step 41442: {'lr': 0.00041738384786680596, 'samples': 7956864, 'steps': 41441, 'loss/train': 1.3565422296524048} 08/30/2021 20:38:35 - INFO - __main__ - Step 41443: {'lr': 0.0004173799060847039, 'samples': 7957056, 'steps': 41442, 'loss/train': 1.049843192100525} 08/30/2021 20:38:36 - INFO - __main__ - Step 41444: {'lr': 0.00041737596422718306, 'samples': 7957248, 'steps': 41443, 'loss/train': 2.10805606842041} 08/30/2021 20:38:37 - INFO - __main__ - Step 41445: {'lr': 0.0004173720222942452, 'samples': 7957440, 'steps': 41444, 'loss/train': 1.4697864055633545} 08/30/2021 20:38:38 - INFO - __main__ - Step 41446: {'lr': 0.000417368080285892, 'samples': 7957632, 'steps': 41445, 'loss/train': 1.1761834621429443} 08/30/2021 20:38:38 - INFO - __main__ - Step 41447: {'lr': 0.0004173641382021254, 'samples': 7957824, 'steps': 41446, 'loss/train': 1.6018630266189575} 08/30/2021 20:38:38 - INFO - __main__ - Step 41448: {'lr': 0.00041736019604294704, 'samples': 7958016, 'steps': 41447, 'loss/train': 1.4833124876022339} 08/30/2021 20:38:39 - INFO - __main__ - Step 41449: {'lr': 0.00041735625380835884, 'samples': 7958208, 'steps': 41448, 'loss/train': 1.0895339250564575} 08/30/2021 20:38:40 - INFO - __main__ - Step 41450: {'lr': 0.0004173523114983624, 'samples': 7958400, 'steps': 41449, 'loss/train': 1.660897135734558} 08/30/2021 20:38:41 - INFO - __main__ - Step 41451: {'lr': 0.0004173483691129597, 'samples': 7958592, 'steps': 41450, 'loss/train': 1.5639561414718628} 08/30/2021 20:38:41 - INFO - __main__ - Step 41452: {'lr': 0.00041734442665215235, 'samples': 7958784, 'steps': 41451, 'loss/train': 1.9907350540161133} 08/30/2021 20:38:41 - INFO - __main__ - Step 41453: {'lr': 0.00041734048411594214, 'samples': 7958976, 'steps': 41452, 'loss/train': 0.7563914656639099} 08/30/2021 20:38:42 - INFO - __main__ - Step 41454: {'lr': 0.000417336541504331, 'samples': 7959168, 'steps': 41453, 'loss/train': 1.73635995388031} 08/30/2021 20:38:43 - INFO - __main__ - Step 41455: {'lr': 0.0004173325988173205, 'samples': 7959360, 'steps': 41454, 'loss/train': 1.8685799837112427} 08/30/2021 20:38:44 - INFO - __main__ - Step 41456: {'lr': 0.00041732865605491256, 'samples': 7959552, 'steps': 41455, 'loss/train': 1.984452486038208} 08/30/2021 20:38:44 - INFO - __main__ - Step 41457: {'lr': 0.00041732471321710886, 'samples': 7959744, 'steps': 41456, 'loss/train': 1.0195425748825073} 08/30/2021 20:38:44 - INFO - __main__ - Step 41458: {'lr': 0.00041732077030391126, 'samples': 7959936, 'steps': 41457, 'loss/train': 1.4068340063095093} 08/30/2021 20:38:45 - INFO - __main__ - Step 41459: {'lr': 0.00041731682731532154, 'samples': 7960128, 'steps': 41458, 'loss/train': 1.5764505863189697} 08/30/2021 20:38:47 - INFO - __main__ - Step 41460: {'lr': 0.0004173128842513414, 'samples': 7960320, 'steps': 41459, 'loss/train': 1.0523980855941772} 08/30/2021 20:38:47 - INFO - __main__ - Step 41461: {'lr': 0.00041730894111197266, 'samples': 7960512, 'steps': 41460, 'loss/train': 0.8384407758712769} 08/30/2021 20:38:48 - INFO - __main__ - Step 41462: {'lr': 0.0004173049978972171, 'samples': 7960704, 'steps': 41461, 'loss/train': 1.2816945314407349} 08/30/2021 20:38:48 - INFO - __main__ - Step 41463: {'lr': 0.0004173010546070765, 'samples': 7960896, 'steps': 41462, 'loss/train': 1.4940721988677979} 08/30/2021 20:38:48 - INFO - __main__ - Step 41464: {'lr': 0.00041729711124155255, 'samples': 7961088, 'steps': 41463, 'loss/train': 1.7958987951278687} 08/30/2021 20:38:50 - INFO - __main__ - Step 41465: {'lr': 0.0004172931678006472, 'samples': 7961280, 'steps': 41464, 'loss/train': 0.41954341530799866} 08/30/2021 20:38:51 - INFO - __main__ - Step 41466: {'lr': 0.00041728922428436213, 'samples': 7961472, 'steps': 41465, 'loss/train': 1.403683066368103} 08/30/2021 20:38:51 - INFO - __main__ - Step 41467: {'lr': 0.000417285280692699, 'samples': 7961664, 'steps': 41466, 'loss/train': 1.4509979486465454} 08/30/2021 20:38:51 - INFO - __main__ - Step 41468: {'lr': 0.00041728133702565985, 'samples': 7961856, 'steps': 41467, 'loss/train': 0.25000718235969543} 08/30/2021 20:38:52 - INFO - __main__ - Step 41469: {'lr': 0.0004172773932832462, 'samples': 7962048, 'steps': 41468, 'loss/train': 0.24955615401268005} 08/30/2021 20:38:53 - INFO - __main__ - Step 41470: {'lr': 0.00041727344946546, 'samples': 7962240, 'steps': 41469, 'loss/train': 2.0024654865264893} 08/30/2021 20:38:54 - INFO - __main__ - Step 41471: {'lr': 0.00041726950557230294, 'samples': 7962432, 'steps': 41470, 'loss/train': 1.3711596727371216} 08/30/2021 20:38:54 - INFO - __main__ - Step 41472: {'lr': 0.0004172655616037768, 'samples': 7962624, 'steps': 41471, 'loss/train': 1.7318528890609741} 08/30/2021 20:38:54 - INFO - __main__ - Step 41473: {'lr': 0.0004172616175598835, 'samples': 7962816, 'steps': 41472, 'loss/train': 1.5632617473602295} 08/30/2021 20:38:55 - INFO - __main__ - Step 41474: {'lr': 0.00041725767344062453, 'samples': 7963008, 'steps': 41473, 'loss/train': 1.4895762205123901} 08/30/2021 20:38:55 - INFO - __main__ - Step 41475: {'lr': 0.00041725372924600193, 'samples': 7963200, 'steps': 41474, 'loss/train': 1.7173179388046265} 08/30/2021 20:38:57 - INFO - __main__ - Step 41476: {'lr': 0.00041724978497601736, 'samples': 7963392, 'steps': 41475, 'loss/train': 0.9980760812759399} 08/30/2021 20:38:57 - INFO - __main__ - Step 41477: {'lr': 0.0004172458406306726, 'samples': 7963584, 'steps': 41476, 'loss/train': 0.7931108474731445} 08/30/2021 20:38:58 - INFO - __main__ - Step 41478: {'lr': 0.00041724189620996946, 'samples': 7963776, 'steps': 41477, 'loss/train': 0.9811127781867981} 08/30/2021 20:38:58 - INFO - __main__ - Step 41479: {'lr': 0.0004172379517139097, 'samples': 7963968, 'steps': 41478, 'loss/train': 1.246964454650879} 08/30/2021 20:38:58 - INFO - __main__ - Step 41480: {'lr': 0.0004172340071424951, 'samples': 7964160, 'steps': 41479, 'loss/train': 0.7575798034667969} 08/30/2021 20:39:00 - INFO - __main__ - Step 41481: {'lr': 0.00041723006249572744, 'samples': 7964352, 'steps': 41480, 'loss/train': 1.4947830438613892} 08/30/2021 20:39:00 - INFO - __main__ - Step 41482: {'lr': 0.00041722611777360844, 'samples': 7964544, 'steps': 41481, 'loss/train': 1.1833040714263916} 08/30/2021 20:39:01 - INFO - __main__ - Step 41483: {'lr': 0.00041722217297614, 'samples': 7964736, 'steps': 41482, 'loss/train': 1.942763090133667} 08/30/2021 20:39:01 - INFO - __main__ - Step 41484: {'lr': 0.00041721822810332384, 'samples': 7964928, 'steps': 41483, 'loss/train': 1.4728940725326538} 08/30/2021 20:39:01 - INFO - __main__ - Step 41485: {'lr': 0.00041721428315516176, 'samples': 7965120, 'steps': 41484, 'loss/train': 1.0895189046859741} 08/30/2021 20:39:03 - INFO - __main__ - Step 41486: {'lr': 0.00041721033813165543, 'samples': 7965312, 'steps': 41485, 'loss/train': 1.047298550605774} 08/30/2021 20:39:03 - INFO - __main__ - Step 41487: {'lr': 0.0004172063930328067, 'samples': 7965504, 'steps': 41486, 'loss/train': 1.745688557624817} 08/30/2021 20:39:04 - INFO - __main__ - Step 41488: {'lr': 0.00041720244785861736, 'samples': 7965696, 'steps': 41487, 'loss/train': 1.6669461727142334} 08/30/2021 20:39:04 - INFO - __main__ - Step 41489: {'lr': 0.0004171985026090892, 'samples': 7965888, 'steps': 41488, 'loss/train': 1.7797329425811768} 08/30/2021 20:39:04 - INFO - __main__ - Step 41490: {'lr': 0.00041719455728422394, 'samples': 7966080, 'steps': 41489, 'loss/train': 1.5193333625793457} 08/30/2021 20:39:06 - INFO - __main__ - Step 41491: {'lr': 0.0004171906118840234, 'samples': 7966272, 'steps': 41490, 'loss/train': 1.7020156383514404} 08/30/2021 20:39:06 - INFO - __main__ - Step 41492: {'lr': 0.00041718666640848937, 'samples': 7966464, 'steps': 41491, 'loss/train': 1.3126717805862427} 08/30/2021 20:39:07 - INFO - __main__ - Step 41493: {'lr': 0.0004171827208576236, 'samples': 7966656, 'steps': 41492, 'loss/train': 1.7679609060287476} 08/30/2021 20:39:07 - INFO - __main__ - Step 41494: {'lr': 0.00041717877523142786, 'samples': 7966848, 'steps': 41493, 'loss/train': 1.6426056623458862} 08/30/2021 20:39:07 - INFO - __main__ - Step 41495: {'lr': 0.00041717482952990394, 'samples': 7967040, 'steps': 41494, 'loss/train': 1.0831743478775024} 08/30/2021 20:39:09 - INFO - __main__ - Step 41496: {'lr': 0.00041717088375305367, 'samples': 7967232, 'steps': 41495, 'loss/train': 1.4067193269729614} 08/30/2021 20:39:09 - INFO - __main__ - Step 41497: {'lr': 0.0004171669379008787, 'samples': 7967424, 'steps': 41496, 'loss/train': 1.2224026918411255} 08/30/2021 20:39:10 - INFO - __main__ - Step 41498: {'lr': 0.00041716299197338093, 'samples': 7967616, 'steps': 41497, 'loss/train': 1.1732620000839233} 08/30/2021 20:39:10 - INFO - __main__ - Step 41499: {'lr': 0.0004171590459705622, 'samples': 7967808, 'steps': 41498, 'loss/train': 1.3189703226089478} 08/30/2021 20:39:10 - INFO - __main__ - Step 41500: {'lr': 0.0004171550998924241, 'samples': 7968000, 'steps': 41499, 'loss/train': 1.5910859107971191} 08/30/2021 20:39:12 - INFO - __main__ - Step 41501: {'lr': 0.0004171511537389684, 'samples': 7968192, 'steps': 41500, 'loss/train': 1.173943042755127} 08/30/2021 20:39:12 - INFO - __main__ - Step 41502: {'lr': 0.0004171472075101971, 'samples': 7968384, 'steps': 41501, 'loss/train': 1.6349396705627441} 08/30/2021 20:39:13 - INFO - __main__ - Step 41503: {'lr': 0.0004171432612061117, 'samples': 7968576, 'steps': 41502, 'loss/train': 1.531803846359253} 08/30/2021 20:39:13 - INFO - __main__ - Step 41504: {'lr': 0.00041713931482671425, 'samples': 7968768, 'steps': 41503, 'loss/train': 1.3499886989593506} 08/30/2021 20:39:13 - INFO - __main__ - Step 41505: {'lr': 0.0004171353683720064, 'samples': 7968960, 'steps': 41504, 'loss/train': 1.4708598852157593} 08/30/2021 20:39:15 - INFO - __main__ - Step 41506: {'lr': 0.00041713142184198994, 'samples': 7969152, 'steps': 41505, 'loss/train': 1.8893855810165405} 08/30/2021 20:39:15 - INFO - __main__ - Step 41507: {'lr': 0.0004171274752366665, 'samples': 7969344, 'steps': 41506, 'loss/train': 1.178467869758606} 08/30/2021 20:39:15 - INFO - __main__ - Step 41508: {'lr': 0.00041712352855603817, 'samples': 7969536, 'steps': 41507, 'loss/train': 1.5718910694122314} 08/30/2021 20:39:16 - INFO - __main__ - Step 41509: {'lr': 0.00041711958180010644, 'samples': 7969728, 'steps': 41508, 'loss/train': 0.7867884039878845} 08/30/2021 20:39:16 - INFO - __main__ - Step 41510: {'lr': 0.0004171156349688733, 'samples': 7969920, 'steps': 41509, 'loss/train': 1.8031187057495117} 08/30/2021 20:39:17 - INFO - __main__ - Step 41511: {'lr': 0.0004171116880623404, 'samples': 7970112, 'steps': 41510, 'loss/train': 1.1286834478378296} 08/30/2021 20:39:19 - INFO - __main__ - Step 41512: {'lr': 0.0004171077410805095, 'samples': 7970304, 'steps': 41511, 'loss/train': 1.209172010421753} 08/30/2021 20:39:19 - INFO - __main__ - Step 41513: {'lr': 0.0004171037940233825, 'samples': 7970496, 'steps': 41512, 'loss/train': 1.487059473991394} 08/30/2021 20:39:19 - INFO - __main__ - Step 41514: {'lr': 0.0004170998468909611, 'samples': 7970688, 'steps': 41513, 'loss/train': 0.9373190999031067} 08/30/2021 20:39:20 - INFO - __main__ - Step 41515: {'lr': 0.00041709589968324704, 'samples': 7970880, 'steps': 41514, 'loss/train': 1.4967365264892578} 08/30/2021 20:39:20 - INFO - __main__ - Step 41516: {'lr': 0.00041709195240024224, 'samples': 7971072, 'steps': 41515, 'loss/train': 1.346509337425232} 08/30/2021 20:39:21 - INFO - __main__ - Step 41517: {'lr': 0.0004170880050419483, 'samples': 7971264, 'steps': 41516, 'loss/train': 1.2530436515808105} 08/30/2021 20:39:22 - INFO - __main__ - Step 41518: {'lr': 0.0004170840576083671, 'samples': 7971456, 'steps': 41517, 'loss/train': 1.0286527872085571} 08/30/2021 20:39:22 - INFO - __main__ - Step 41519: {'lr': 0.00041708011009950044, 'samples': 7971648, 'steps': 41518, 'loss/train': 1.2466856241226196} 08/30/2021 20:39:23 - INFO - __main__ - Step 41520: {'lr': 0.00041707616251535, 'samples': 7971840, 'steps': 41519, 'loss/train': 1.613173007965088} 08/30/2021 20:39:23 - INFO - __main__ - Step 41521: {'lr': 0.0004170722148559176, 'samples': 7972032, 'steps': 41520, 'loss/train': 1.8256449699401855} 08/30/2021 20:39:24 - INFO - __main__ - Step 41522: {'lr': 0.0004170682671212051, 'samples': 7972224, 'steps': 41521, 'loss/train': 1.3022528886795044} 08/30/2021 20:39:25 - INFO - __main__ - Step 41523: {'lr': 0.00041706431931121416, 'samples': 7972416, 'steps': 41522, 'loss/train': 1.4363267421722412} 08/30/2021 20:39:25 - INFO - __main__ - Step 41524: {'lr': 0.00041706037142594666, 'samples': 7972608, 'steps': 41523, 'loss/train': 1.076782464981079} 08/30/2021 20:39:26 - INFO - __main__ - Step 41525: {'lr': 0.00041705642346540436, 'samples': 7972800, 'steps': 41524, 'loss/train': 1.3851639032363892} 08/30/2021 20:39:26 - INFO - __main__ - Step 41526: {'lr': 0.00041705247542958904, 'samples': 7972992, 'steps': 41525, 'loss/train': 1.574877381324768} 08/30/2021 20:39:27 - INFO - __main__ - Step 41527: {'lr': 0.00041704852731850234, 'samples': 7973184, 'steps': 41526, 'loss/train': 1.2817974090576172} 08/30/2021 20:39:28 - INFO - __main__ - Step 41528: {'lr': 0.0004170445791321462, 'samples': 7973376, 'steps': 41527, 'loss/train': 1.2958797216415405} 08/30/2021 20:39:28 - INFO - __main__ - Step 41529: {'lr': 0.00041704063087052236, 'samples': 7973568, 'steps': 41528, 'loss/train': 0.4314829111099243} 08/30/2021 20:39:29 - INFO - __main__ - Step 41530: {'lr': 0.0004170366825336326, 'samples': 7973760, 'steps': 41529, 'loss/train': 1.3234946727752686} 08/30/2021 20:39:29 - INFO - __main__ - Step 41531: {'lr': 0.0004170327341214787, 'samples': 7973952, 'steps': 41530, 'loss/train': 1.867661952972412} 08/30/2021 20:39:31 - INFO - __main__ - Step 41532: {'lr': 0.00041702878563406237, 'samples': 7974144, 'steps': 41531, 'loss/train': 1.7998889684677124} 08/30/2021 20:39:31 - INFO - __main__ - Step 41533: {'lr': 0.0004170248370713855, 'samples': 7974336, 'steps': 41532, 'loss/train': 1.7397903203964233} 08/30/2021 20:39:31 - INFO - __main__ - Step 41534: {'lr': 0.0004170208884334498, 'samples': 7974528, 'steps': 41533, 'loss/train': 0.8247806429862976} 08/30/2021 20:39:32 - INFO - __main__ - Step 41535: {'lr': 0.000417016939720257, 'samples': 7974720, 'steps': 41534, 'loss/train': 0.8748294711112976} 08/30/2021 20:39:32 - INFO - __main__ - Step 41536: {'lr': 0.000417012990931809, 'samples': 7974912, 'steps': 41535, 'loss/train': 0.7379003763198853} 08/30/2021 20:39:34 - INFO - __main__ - Step 41537: {'lr': 0.00041700904206810755, 'samples': 7975104, 'steps': 41536, 'loss/train': 0.9927288293838501} 08/30/2021 20:39:34 - INFO - __main__ - Step 41538: {'lr': 0.00041700509312915437, 'samples': 7975296, 'steps': 41537, 'loss/train': 1.592069149017334} 08/30/2021 20:39:35 - INFO - __main__ - Step 41539: {'lr': 0.0004170011441149513, 'samples': 7975488, 'steps': 41538, 'loss/train': 2.8865084648132324} 08/30/2021 20:39:35 - INFO - __main__ - Step 41540: {'lr': 0.0004169971950255001, 'samples': 7975680, 'steps': 41539, 'loss/train': 0.8969731330871582} 08/30/2021 20:39:35 - INFO - __main__ - Step 41541: {'lr': 0.0004169932458608025, 'samples': 7975872, 'steps': 41540, 'loss/train': 1.250950813293457} 08/30/2021 20:39:36 - INFO - __main__ - Step 41542: {'lr': 0.00041698929662086035, 'samples': 7976064, 'steps': 41541, 'loss/train': 0.42570292949676514} 08/30/2021 20:39:37 - INFO - __main__ - Step 41543: {'lr': 0.0004169853473056754, 'samples': 7976256, 'steps': 41542, 'loss/train': 1.0075010061264038} 08/30/2021 20:39:38 - INFO - __main__ - Step 41544: {'lr': 0.0004169813979152494, 'samples': 7976448, 'steps': 41543, 'loss/train': 1.811414122581482} 08/30/2021 20:39:38 - INFO - __main__ - Step 41545: {'lr': 0.0004169774484495841, 'samples': 7976640, 'steps': 41544, 'loss/train': 1.2107313871383667} 08/30/2021 20:39:38 - INFO - __main__ - Step 41546: {'lr': 0.00041697349890868146, 'samples': 7976832, 'steps': 41545, 'loss/train': 1.656603217124939} 08/30/2021 20:39:39 - INFO - __main__ - Step 41547: {'lr': 0.0004169695492925431, 'samples': 7977024, 'steps': 41546, 'loss/train': 1.1806819438934326} 08/30/2021 20:39:40 - INFO - __main__ - Step 41548: {'lr': 0.0004169655996011708, 'samples': 7977216, 'steps': 41547, 'loss/train': 1.7755823135375977} 08/30/2021 20:39:41 - INFO - __main__ - Step 41549: {'lr': 0.0004169616498345664, 'samples': 7977408, 'steps': 41548, 'loss/train': 1.4425559043884277} 08/30/2021 20:39:41 - INFO - __main__ - Step 41550: {'lr': 0.0004169576999927317, 'samples': 7977600, 'steps': 41549, 'loss/train': 1.7261983156204224} 08/30/2021 20:39:41 - INFO - __main__ - Step 41551: {'lr': 0.00041695375007566837, 'samples': 7977792, 'steps': 41550, 'loss/train': 1.1468747854232788} 08/30/2021 20:39:42 - INFO - __main__ - Step 41552: {'lr': 0.00041694980008337825, 'samples': 7977984, 'steps': 41551, 'loss/train': 1.8117878437042236} 08/30/2021 20:39:43 - INFO - __main__ - Step 41553: {'lr': 0.0004169458500158632, 'samples': 7978176, 'steps': 41552, 'loss/train': 1.265033483505249} 08/30/2021 20:39:43 - INFO - __main__ - Step 41554: {'lr': 0.0004169418998731249, 'samples': 7978368, 'steps': 41553, 'loss/train': 1.387193202972412} 08/30/2021 20:39:44 - INFO - __main__ - Step 41555: {'lr': 0.00041693794965516514, 'samples': 7978560, 'steps': 41554, 'loss/train': 1.7047737836837769} 08/30/2021 20:39:44 - INFO - __main__ - Step 41556: {'lr': 0.0004169339993619857, 'samples': 7978752, 'steps': 41555, 'loss/train': 2.482072353363037} 08/30/2021 20:39:44 - INFO - __main__ - Step 41557: {'lr': 0.0004169300489935884, 'samples': 7978944, 'steps': 41556, 'loss/train': 1.5112351179122925} 08/30/2021 20:39:46 - INFO - __main__ - Step 41558: {'lr': 0.000416926098549975, 'samples': 7979136, 'steps': 41557, 'loss/train': 1.1393442153930664} 08/30/2021 20:39:47 - INFO - __main__ - Step 41559: {'lr': 0.00041692214803114725, 'samples': 7979328, 'steps': 41558, 'loss/train': 1.5220495462417603} 08/30/2021 20:39:47 - INFO - __main__ - Step 41560: {'lr': 0.00041691819743710704, 'samples': 7979520, 'steps': 41559, 'loss/train': 0.31711891293525696} 08/30/2021 20:39:48 - INFO - __main__ - Step 41561: {'lr': 0.00041691424676785593, 'samples': 7979712, 'steps': 41560, 'loss/train': 1.0074025392532349} 08/30/2021 20:39:48 - INFO - __main__ - Step 41562: {'lr': 0.00041691029602339595, 'samples': 7979904, 'steps': 41561, 'loss/train': 1.6283786296844482} 08/30/2021 20:39:48 - INFO - __main__ - Step 41563: {'lr': 0.00041690634520372865, 'samples': 7980096, 'steps': 41562, 'loss/train': 0.6212571263313293} 08/30/2021 20:39:50 - INFO - __main__ - Step 41564: {'lr': 0.000416902394308856, 'samples': 7980288, 'steps': 41563, 'loss/train': 1.5276856422424316} 08/30/2021 20:39:51 - INFO - __main__ - Step 41565: {'lr': 0.00041689844333877966, 'samples': 7980480, 'steps': 41564, 'loss/train': 1.7597904205322266} 08/30/2021 20:39:51 - INFO - __main__ - Step 41566: {'lr': 0.00041689449229350155, 'samples': 7980672, 'steps': 41565, 'loss/train': 1.3865047693252563} 08/30/2021 20:39:51 - INFO - __main__ - Step 41567: {'lr': 0.00041689054117302333, 'samples': 7980864, 'steps': 41566, 'loss/train': 1.9710938930511475} 08/30/2021 20:39:52 - INFO - __main__ - Step 41568: {'lr': 0.00041688658997734675, 'samples': 7981056, 'steps': 41567, 'loss/train': 0.9598851203918457} 08/30/2021 20:39:53 - INFO - __main__ - Step 41569: {'lr': 0.0004168826387064737, 'samples': 7981248, 'steps': 41568, 'loss/train': 1.4870154857635498} 08/30/2021 20:39:54 - INFO - __main__ - Step 41570: {'lr': 0.00041687868736040593, 'samples': 7981440, 'steps': 41569, 'loss/train': 1.1243648529052734} 08/30/2021 20:39:54 - INFO - __main__ - Step 41571: {'lr': 0.0004168747359391451, 'samples': 7981632, 'steps': 41570, 'loss/train': 1.6850124597549438} 08/30/2021 20:39:54 - INFO - __main__ - Step 41572: {'lr': 0.00041687078444269316, 'samples': 7981824, 'steps': 41571, 'loss/train': 1.2938319444656372} 08/30/2021 20:39:55 - INFO - __main__ - Step 41573: {'lr': 0.0004168668328710518, 'samples': 7982016, 'steps': 41572, 'loss/train': 1.5878853797912598} 08/30/2021 20:39:56 - INFO - __main__ - Step 41574: {'lr': 0.0004168628812242228, 'samples': 7982208, 'steps': 41573, 'loss/train': 1.6730941534042358} 08/30/2021 20:39:57 - INFO - __main__ - Step 41575: {'lr': 0.00041685892950220804, 'samples': 7982400, 'steps': 41574, 'loss/train': 1.5698238611221313} 08/30/2021 20:39:57 - INFO - __main__ - Step 41576: {'lr': 0.0004168549777050091, 'samples': 7982592, 'steps': 41575, 'loss/train': 1.30485200881958} 08/30/2021 20:39:57 - INFO - __main__ - Step 41577: {'lr': 0.000416851025832628, 'samples': 7982784, 'steps': 41576, 'loss/train': 1.11117422580719} 08/30/2021 20:39:58 - INFO - __main__ - Step 41578: {'lr': 0.0004168470738850664, 'samples': 7982976, 'steps': 41577, 'loss/train': 1.492432951927185} 08/30/2021 20:39:59 - INFO - __main__ - Step 41579: {'lr': 0.00041684312186232597, 'samples': 7983168, 'steps': 41578, 'loss/train': 1.218453049659729} 08/30/2021 20:40:00 - INFO - __main__ - Step 41580: {'lr': 0.0004168391697644087, 'samples': 7983360, 'steps': 41579, 'loss/train': 1.2426108121871948} 08/30/2021 20:40:00 - INFO - __main__ - Step 41581: {'lr': 0.0004168352175913163, 'samples': 7983552, 'steps': 41580, 'loss/train': 1.7683639526367188} 08/30/2021 20:40:00 - INFO - __main__ - Step 41582: {'lr': 0.00041683126534305037, 'samples': 7983744, 'steps': 41581, 'loss/train': 0.6085885763168335} 08/30/2021 20:40:01 - INFO - __main__ - Step 41583: {'lr': 0.000416827313019613, 'samples': 7983936, 'steps': 41582, 'loss/train': 1.1550097465515137} 08/30/2021 20:40:02 - INFO - __main__ - Step 41584: {'lr': 0.0004168233606210058, 'samples': 7984128, 'steps': 41583, 'loss/train': 0.8691121339797974} 08/30/2021 20:40:03 - INFO - __main__ - Step 41585: {'lr': 0.0004168194081472305, 'samples': 7984320, 'steps': 41584, 'loss/train': 1.0411816835403442} 08/30/2021 20:40:03 - INFO - __main__ - Step 41586: {'lr': 0.000416815455598289, 'samples': 7984512, 'steps': 41585, 'loss/train': 0.1261669099330902} 08/30/2021 20:40:03 - INFO - __main__ - Step 41587: {'lr': 0.000416811502974183, 'samples': 7984704, 'steps': 41586, 'loss/train': 1.4329789876937866} 08/30/2021 20:40:04 - INFO - __main__ - Step 41588: {'lr': 0.00041680755027491433, 'samples': 7984896, 'steps': 41587, 'loss/train': 1.6943320035934448} 08/30/2021 20:40:05 - INFO - __main__ - Step 41589: {'lr': 0.0004168035975004847, 'samples': 7985088, 'steps': 41588, 'loss/train': 1.0669463872909546} 08/30/2021 20:40:06 - INFO - __main__ - Step 41590: {'lr': 0.00041679964465089596, 'samples': 7985280, 'steps': 41589, 'loss/train': 1.1656787395477295} 08/30/2021 20:40:06 - INFO - __main__ - Step 41591: {'lr': 0.00041679569172614996, 'samples': 7985472, 'steps': 41590, 'loss/train': 2.1059494018554688} 08/30/2021 20:40:06 - INFO - __main__ - Step 41592: {'lr': 0.0004167917387262483, 'samples': 7985664, 'steps': 41591, 'loss/train': 1.3925353288650513} 08/30/2021 20:40:07 - INFO - __main__ - Step 41593: {'lr': 0.0004167877856511929, 'samples': 7985856, 'steps': 41592, 'loss/train': 1.4096202850341797} 08/30/2021 20:40:07 - INFO - __main__ - Step 41594: {'lr': 0.0004167838325009855, 'samples': 7986048, 'steps': 41593, 'loss/train': 1.6820869445800781} 08/30/2021 20:40:09 - INFO - __main__ - Step 41595: {'lr': 0.0004167798792756279, 'samples': 7986240, 'steps': 41594, 'loss/train': 1.8147940635681152} 08/30/2021 20:40:09 - INFO - __main__ - Step 41596: {'lr': 0.0004167759259751218, 'samples': 7986432, 'steps': 41595, 'loss/train': 1.5824813842773438} 08/30/2021 20:40:09 - INFO - __main__ - Step 41597: {'lr': 0.0004167719725994691, 'samples': 7986624, 'steps': 41596, 'loss/train': 1.7292206287384033} 08/30/2021 20:40:10 - INFO - __main__ - Step 41598: {'lr': 0.00041676801914867145, 'samples': 7986816, 'steps': 41597, 'loss/train': 0.9773558378219604} 08/30/2021 20:40:10 - INFO - __main__ - Step 41599: {'lr': 0.00041676406562273074, 'samples': 7987008, 'steps': 41598, 'loss/train': 1.4441684484481812} 08/30/2021 20:40:12 - INFO - __main__ - Step 41600: {'lr': 0.00041676011202164875, 'samples': 7987200, 'steps': 41599, 'loss/train': 1.2454993724822998} 08/30/2021 20:40:13 - INFO - __main__ - Step 41601: {'lr': 0.00041675615834542716, 'samples': 7987392, 'steps': 41600, 'loss/train': 1.5815929174423218} 08/30/2021 20:40:13 - INFO - __main__ - Step 41602: {'lr': 0.0004167522045940678, 'samples': 7987584, 'steps': 41601, 'loss/train': 0.09359685331583023} 08/30/2021 20:40:13 - INFO - __main__ - Step 41603: {'lr': 0.0004167482507675726, 'samples': 7987776, 'steps': 41602, 'loss/train': 1.3966649770736694} 08/30/2021 20:40:14 - INFO - __main__ - Step 41604: {'lr': 0.0004167442968659431, 'samples': 7987968, 'steps': 41603, 'loss/train': 1.4776785373687744} 08/30/2021 20:40:16 - INFO - __main__ - Step 41605: {'lr': 0.0004167403428891812, 'samples': 7988160, 'steps': 41604, 'loss/train': 1.1176069974899292} 08/30/2021 20:40:16 - INFO - __main__ - Step 41606: {'lr': 0.00041673638883728877, 'samples': 7988352, 'steps': 41605, 'loss/train': 1.7049412727355957} 08/30/2021 20:40:16 - INFO - __main__ - Step 41607: {'lr': 0.00041673243471026746, 'samples': 7988544, 'steps': 41606, 'loss/train': 1.7950657606124878} 08/30/2021 20:40:17 - INFO - __main__ - Step 41608: {'lr': 0.000416728480508119, 'samples': 7988736, 'steps': 41607, 'loss/train': 0.930979311466217} 08/30/2021 20:40:17 - INFO - __main__ - Step 41609: {'lr': 0.00041672452623084535, 'samples': 7988928, 'steps': 41608, 'loss/train': 0.1624361276626587} 08/30/2021 20:40:19 - INFO - __main__ - Step 41610: {'lr': 0.0004167205718784481, 'samples': 7989120, 'steps': 41609, 'loss/train': 0.1405334174633026} 08/30/2021 20:40:19 - INFO - __main__ - Step 41611: {'lr': 0.0004167166174509293, 'samples': 7989312, 'steps': 41610, 'loss/train': 1.0899964570999146} 08/30/2021 20:40:19 - INFO - __main__ - Step 41612: {'lr': 0.00041671266294829036, 'samples': 7989504, 'steps': 41611, 'loss/train': 1.2400552034378052} 08/30/2021 20:40:20 - INFO - __main__ - Step 41613: {'lr': 0.0004167087083705334, 'samples': 7989696, 'steps': 41612, 'loss/train': 1.4398250579833984} 08/30/2021 20:40:20 - INFO - __main__ - Step 41614: {'lr': 0.00041670475371766, 'samples': 7989888, 'steps': 41613, 'loss/train': 2.004798412322998} 08/30/2021 20:40:22 - INFO - __main__ - Step 41615: {'lr': 0.0004167007989896721, 'samples': 7990080, 'steps': 41614, 'loss/train': 1.3180453777313232} 08/30/2021 20:40:22 - INFO - __main__ - Step 41616: {'lr': 0.0004166968441865714, 'samples': 7990272, 'steps': 41615, 'loss/train': 1.1415334939956665} 08/30/2021 20:40:22 - INFO - __main__ - Step 41617: {'lr': 0.00041669288930835957, 'samples': 7990464, 'steps': 41616, 'loss/train': 1.180234432220459} 08/30/2021 20:40:23 - INFO - __main__ - Step 41618: {'lr': 0.0004166889343550385, 'samples': 7990656, 'steps': 41617, 'loss/train': 1.3564943075180054} 08/30/2021 20:40:23 - INFO - __main__ - Step 41619: {'lr': 0.00041668497932661005, 'samples': 7990848, 'steps': 41618, 'loss/train': 2.0460641384124756} 08/30/2021 20:40:26 - INFO - __main__ - Step 41620: {'lr': 0.00041668102422307593, 'samples': 7991040, 'steps': 41619, 'loss/train': 2.012375593185425} 08/30/2021 20:40:26 - INFO - __main__ - Step 41621: {'lr': 0.0004166770690444378, 'samples': 7991232, 'steps': 41620, 'loss/train': 0.1633165031671524} 08/30/2021 20:40:27 - INFO - __main__ - Step 41622: {'lr': 0.0004166731137906976, 'samples': 7991424, 'steps': 41621, 'loss/train': 0.1540095955133438} 08/30/2021 20:40:27 - INFO - __main__ - Step 41623: {'lr': 0.0004166691584618572, 'samples': 7991616, 'steps': 41622, 'loss/train': 1.4212417602539062} 08/30/2021 20:40:27 - INFO - __main__ - Step 41624: {'lr': 0.00041666520305791806, 'samples': 7991808, 'steps': 41623, 'loss/train': 1.1137620210647583} 08/30/2021 20:40:29 - INFO - __main__ - Step 41625: {'lr': 0.00041666124757888223, 'samples': 7992000, 'steps': 41624, 'loss/train': 1.381408929824829} 08/30/2021 20:40:29 - INFO - __main__ - Step 41626: {'lr': 0.0004166572920247514, 'samples': 7992192, 'steps': 41625, 'loss/train': 2.322394847869873} 08/30/2021 20:40:29 - INFO - __main__ - Step 41627: {'lr': 0.0004166533363955274, 'samples': 7992384, 'steps': 41626, 'loss/train': 1.4913469552993774} 08/30/2021 20:40:30 - INFO - __main__ - Step 41628: {'lr': 0.00041664938069121195, 'samples': 7992576, 'steps': 41627, 'loss/train': 1.10299551486969} 08/30/2021 20:40:30 - INFO - __main__ - Step 41629: {'lr': 0.00041664542491180685, 'samples': 7992768, 'steps': 41628, 'loss/train': 1.6439335346221924} 08/30/2021 20:40:32 - INFO - __main__ - Step 41630: {'lr': 0.0004166414690573139, 'samples': 7992960, 'steps': 41629, 'loss/train': 1.7799092531204224} 08/30/2021 20:40:32 - INFO - __main__ - Step 41631: {'lr': 0.0004166375131277349, 'samples': 7993152, 'steps': 41630, 'loss/train': 1.5723235607147217} 08/30/2021 20:40:33 - INFO - __main__ - Step 41632: {'lr': 0.0004166335571230716, 'samples': 7993344, 'steps': 41631, 'loss/train': 1.0552995204925537} 08/30/2021 20:40:33 - INFO - __main__ - Step 41633: {'lr': 0.0004166296010433258, 'samples': 7993536, 'steps': 41632, 'loss/train': 0.09982667863368988} 08/30/2021 20:40:33 - INFO - __main__ - Step 41634: {'lr': 0.00041662564488849927, 'samples': 7993728, 'steps': 41633, 'loss/train': 1.9106051921844482} 08/30/2021 20:40:35 - INFO - __main__ - Step 41635: {'lr': 0.00041662168865859374, 'samples': 7993920, 'steps': 41634, 'loss/train': 0.09316297620534897} 08/30/2021 20:40:35 - INFO - __main__ - Step 41636: {'lr': 0.0004166177323536111, 'samples': 7994112, 'steps': 41635, 'loss/train': 1.5177817344665527} 08/30/2021 20:40:36 - INFO - __main__ - Step 41637: {'lr': 0.000416613775973553, 'samples': 7994304, 'steps': 41636, 'loss/train': 1.1875720024108887} 08/30/2021 20:40:36 - INFO - __main__ - Step 41638: {'lr': 0.0004166098195184214, 'samples': 7994496, 'steps': 41637, 'loss/train': 0.15914101898670197} 08/30/2021 20:40:36 - INFO - __main__ - Step 41639: {'lr': 0.000416605862988218, 'samples': 7994688, 'steps': 41638, 'loss/train': 1.3329083919525146} 08/30/2021 20:40:37 - INFO - __main__ - Step 41640: {'lr': 0.00041660190638294456, 'samples': 7994880, 'steps': 41639, 'loss/train': 1.1964194774627686} 08/30/2021 20:40:38 - INFO - __main__ - Step 41641: {'lr': 0.0004165979497026028, 'samples': 7995072, 'steps': 41640, 'loss/train': 1.3991683721542358} 08/30/2021 20:40:39 - INFO - __main__ - Step 41642: {'lr': 0.00041659399294719456, 'samples': 7995264, 'steps': 41641, 'loss/train': 0.5802916884422302} 08/30/2021 20:40:39 - INFO - __main__ - Step 41643: {'lr': 0.00041659003611672175, 'samples': 7995456, 'steps': 41642, 'loss/train': 1.4516220092773438} 08/30/2021 20:40:39 - INFO - __main__ - Step 41644: {'lr': 0.000416586079211186, 'samples': 7995648, 'steps': 41643, 'loss/train': 0.95184326171875} 08/30/2021 20:40:40 - INFO - __main__ - Step 41645: {'lr': 0.0004165821222305891, 'samples': 7995840, 'steps': 41644, 'loss/train': 2.0189318656921387} 08/30/2021 20:40:42 - INFO - __main__ - Step 41646: {'lr': 0.00041657816517493284, 'samples': 7996032, 'steps': 41645, 'loss/train': 1.3277875185012817} 08/30/2021 20:40:42 - INFO - __main__ - Step 41647: {'lr': 0.00041657420804421907, 'samples': 7996224, 'steps': 41646, 'loss/train': 0.09014960378408432} 08/30/2021 20:40:42 - INFO - __main__ - Step 41648: {'lr': 0.00041657025083844957, 'samples': 7996416, 'steps': 41647, 'loss/train': 1.9317916631698608} 08/30/2021 20:40:43 - INFO - __main__ - Step 41649: {'lr': 0.00041656629355762607, 'samples': 7996608, 'steps': 41648, 'loss/train': 3.170945882797241} 08/30/2021 20:40:43 - INFO - __main__ - Step 41650: {'lr': 0.00041656233620175035, 'samples': 7996800, 'steps': 41649, 'loss/train': 1.0516948699951172} 08/30/2021 20:40:45 - INFO - __main__ - Step 41651: {'lr': 0.0004165583787708242, 'samples': 7996992, 'steps': 41650, 'loss/train': 1.4989819526672363} 08/30/2021 20:40:45 - INFO - __main__ - Step 41652: {'lr': 0.0004165544212648494, 'samples': 7997184, 'steps': 41651, 'loss/train': 1.1397823095321655} 08/30/2021 20:40:45 - INFO - __main__ - Step 41653: {'lr': 0.0004165504636838278, 'samples': 7997376, 'steps': 41652, 'loss/train': 1.192221760749817} 08/30/2021 20:40:46 - INFO - __main__ - Step 41654: {'lr': 0.0004165465060277611, 'samples': 7997568, 'steps': 41653, 'loss/train': 1.7243061065673828} 08/30/2021 20:40:46 - INFO - __main__ - Step 41655: {'lr': 0.0004165425482966512, 'samples': 7997760, 'steps': 41654, 'loss/train': 1.3988286256790161} 08/30/2021 20:40:48 - INFO - __main__ - Step 41656: {'lr': 0.00041653859049049964, 'samples': 7997952, 'steps': 41655, 'loss/train': 1.3119416236877441} 08/30/2021 20:40:48 - INFO - __main__ - Step 41657: {'lr': 0.00041653463260930845, 'samples': 7998144, 'steps': 41656, 'loss/train': 0.28657767176628113} 08/30/2021 20:40:48 - INFO - __main__ - Step 41658: {'lr': 0.00041653067465307925, 'samples': 7998336, 'steps': 41657, 'loss/train': 1.3334693908691406} 08/30/2021 20:40:49 - INFO - __main__ - Step 41659: {'lr': 0.00041652671662181394, 'samples': 7998528, 'steps': 41658, 'loss/train': 2.8703110218048096} 08/30/2021 20:40:49 - INFO - __main__ - Step 41660: {'lr': 0.00041652275851551435, 'samples': 7998720, 'steps': 41659, 'loss/train': 1.5845590829849243} 08/30/2021 20:40:51 - INFO - __main__ - Step 41661: {'lr': 0.0004165188003341821, 'samples': 7998912, 'steps': 41660, 'loss/train': 1.2762160301208496} 08/30/2021 20:40:51 - INFO - __main__ - Step 41662: {'lr': 0.0004165148420778191, 'samples': 7999104, 'steps': 41661, 'loss/train': 1.0728442668914795} 08/30/2021 20:40:52 - INFO - __main__ - Step 41663: {'lr': 0.000416510883746427, 'samples': 7999296, 'steps': 41662, 'loss/train': 1.3767396211624146} 08/30/2021 20:40:52 - INFO - __main__ - Step 41664: {'lr': 0.00041650692534000766, 'samples': 7999488, 'steps': 41663, 'loss/train': 1.7291936874389648} 08/30/2021 20:40:53 - INFO - __main__ - Step 41665: {'lr': 0.0004165029668585629, 'samples': 7999680, 'steps': 41664, 'loss/train': 1.774588942527771} 08/30/2021 20:40:53 - INFO - __main__ - Step 41666: {'lr': 0.00041649900830209455, 'samples': 7999872, 'steps': 41665, 'loss/train': 1.6639882326126099} 08/30/2021 20:40:54 - INFO - __main__ - Step 41667: {'lr': 0.00041649504967060423, 'samples': 8000064, 'steps': 41666, 'loss/train': 0.029390107840299606} 08/30/2021 20:40:55 - INFO - __main__ - Step 41668: {'lr': 0.0004164910909640938, 'samples': 8000256, 'steps': 41667, 'loss/train': 1.9860399961471558} 08/30/2021 20:40:55 - INFO - __main__ - Step 41669: {'lr': 0.0004164871321825651, 'samples': 8000448, 'steps': 41668, 'loss/train': 1.43567955493927} 08/30/2021 20:40:56 - INFO - __main__ - Step 41670: {'lr': 0.0004164831733260198, 'samples': 8000640, 'steps': 41669, 'loss/train': 1.5842734575271606} 08/30/2021 20:40:56 - INFO - __main__ - Step 41671: {'lr': 0.0004164792143944598, 'samples': 8000832, 'steps': 41670, 'loss/train': 1.0877556800842285} 08/30/2021 20:40:58 - INFO - __main__ - Step 41672: {'lr': 0.0004164752553878868, 'samples': 8001024, 'steps': 41671, 'loss/train': 1.483295202255249} 08/30/2021 20:40:59 - INFO - __main__ - Step 41673: {'lr': 0.00041647129630630265, 'samples': 8001216, 'steps': 41672, 'loss/train': 1.4576988220214844} 08/30/2021 20:40:59 - INFO - __main__ - Step 41674: {'lr': 0.0004164673371497092, 'samples': 8001408, 'steps': 41673, 'loss/train': 1.1592954397201538} 08/30/2021 20:40:59 - INFO - __main__ - Step 41675: {'lr': 0.000416463377918108, 'samples': 8001600, 'steps': 41674, 'loss/train': 1.2738759517669678} 08/30/2021 20:41:00 - INFO - __main__ - Step 41676: {'lr': 0.00041645941861150103, 'samples': 8001792, 'steps': 41675, 'loss/train': 1.7697786092758179} 08/30/2021 20:41:01 - INFO - __main__ - Step 41677: {'lr': 0.00041645545922989, 'samples': 8001984, 'steps': 41676, 'loss/train': 1.461212158203125} 08/30/2021 20:41:02 - INFO - __main__ - Step 41678: {'lr': 0.00041645149977327667, 'samples': 8002176, 'steps': 41677, 'loss/train': 1.5270456075668335} 08/30/2021 20:41:02 - INFO - __main__ - Step 41679: {'lr': 0.0004164475402416629, 'samples': 8002368, 'steps': 41678, 'loss/train': 1.594008207321167} 08/30/2021 20:41:02 - INFO - __main__ - Step 41680: {'lr': 0.0004164435806350505, 'samples': 8002560, 'steps': 41679, 'loss/train': 1.2985014915466309} 08/30/2021 20:41:03 - INFO - __main__ - Step 41681: {'lr': 0.00041643962095344107, 'samples': 8002752, 'steps': 41680, 'loss/train': 1.9186331033706665} 08/30/2021 20:41:03 - INFO - __main__ - Step 41682: {'lr': 0.0004164356611968366, 'samples': 8002944, 'steps': 41681, 'loss/train': 2.1798055171966553} 08/30/2021 20:41:04 - INFO - __main__ - Step 41683: {'lr': 0.0004164317013652387, 'samples': 8003136, 'steps': 41682, 'loss/train': 1.7911888360977173} 08/30/2021 20:41:05 - INFO - __main__ - Step 41684: {'lr': 0.00041642774145864934, 'samples': 8003328, 'steps': 41683, 'loss/train': 1.2257550954818726} 08/30/2021 20:41:05 - INFO - __main__ - Step 41685: {'lr': 0.00041642378147707014, 'samples': 8003520, 'steps': 41684, 'loss/train': 1.4834332466125488} 08/30/2021 20:41:06 - INFO - __main__ - Step 41686: {'lr': 0.00041641982142050297, 'samples': 8003712, 'steps': 41685, 'loss/train': 2.2028777599334717} 08/30/2021 20:41:06 - INFO - __main__ - Step 41687: {'lr': 0.00041641586128894967, 'samples': 8003904, 'steps': 41686, 'loss/train': 1.3898755311965942} 08/30/2021 20:41:07 - INFO - __main__ - Step 41688: {'lr': 0.0004164119010824119, 'samples': 8004096, 'steps': 41687, 'loss/train': 1.174214243888855} 08/30/2021 20:41:08 - INFO - __main__ - Step 41689: {'lr': 0.00041640794080089144, 'samples': 8004288, 'steps': 41688, 'loss/train': 0.9038873314857483} 08/30/2021 20:41:08 - INFO - __main__ - Step 41690: {'lr': 0.0004164039804443902, 'samples': 8004480, 'steps': 41689, 'loss/train': 1.2460660934448242} 08/30/2021 20:41:09 - INFO - __main__ - Step 41691: {'lr': 0.0004164000200129099, 'samples': 8004672, 'steps': 41690, 'loss/train': 1.462849736213684} 08/30/2021 20:41:09 - INFO - __main__ - Step 41692: {'lr': 0.0004163960595064522, 'samples': 8004864, 'steps': 41691, 'loss/train': 0.45430922508239746} 08/30/2021 20:41:11 - INFO - __main__ - Step 41693: {'lr': 0.00041639209892501913, 'samples': 8005056, 'steps': 41692, 'loss/train': 1.3535102605819702} 08/30/2021 20:41:11 - INFO - __main__ - Step 41694: {'lr': 0.00041638813826861234, 'samples': 8005248, 'steps': 41693, 'loss/train': 0.0332728773355484} 08/30/2021 20:41:12 - INFO - __main__ - Step 41695: {'lr': 0.00041638417753723356, 'samples': 8005440, 'steps': 41694, 'loss/train': 0.026177937164902687} 08/30/2021 20:41:12 - INFO - __main__ - Step 41696: {'lr': 0.00041638021673088464, 'samples': 8005632, 'steps': 41695, 'loss/train': 0.538514256477356} 08/30/2021 20:41:12 - INFO - __main__ - Step 41697: {'lr': 0.0004163762558495674, 'samples': 8005824, 'steps': 41696, 'loss/train': 1.7629307508468628} 08/30/2021 20:41:13 - INFO - __main__ - Step 41698: {'lr': 0.0004163722948932836, 'samples': 8006016, 'steps': 41697, 'loss/train': 1.450182557106018} 08/30/2021 20:41:14 - INFO - __main__ - Step 41699: {'lr': 0.000416368333862035, 'samples': 8006208, 'steps': 41698, 'loss/train': 1.321563482284546} 08/30/2021 20:41:15 - INFO - __main__ - Step 41700: {'lr': 0.00041636437275582335, 'samples': 8006400, 'steps': 41699, 'loss/train': 0.8955653309822083} 08/30/2021 20:41:15 - INFO - __main__ - Step 41701: {'lr': 0.00041636041157465056, 'samples': 8006592, 'steps': 41700, 'loss/train': 1.5074267387390137} 08/30/2021 20:41:16 - INFO - __main__ - Step 41702: {'lr': 0.00041635645031851826, 'samples': 8006784, 'steps': 41701, 'loss/train': 0.4653592109680176} 08/30/2021 20:41:16 - INFO - __main__ - Step 41703: {'lr': 0.00041635248898742834, 'samples': 8006976, 'steps': 41702, 'loss/train': 1.423519253730774} 08/30/2021 20:41:17 - INFO - __main__ - Step 41704: {'lr': 0.00041634852758138253, 'samples': 8007168, 'steps': 41703, 'loss/train': 1.2567559480667114} 08/30/2021 20:41:18 - INFO - __main__ - Step 41705: {'lr': 0.0004163445661003827, 'samples': 8007360, 'steps': 41704, 'loss/train': 0.8124480247497559} 08/30/2021 20:41:18 - INFO - __main__ - Step 41706: {'lr': 0.0004163406045444306, 'samples': 8007552, 'steps': 41705, 'loss/train': 1.2445435523986816} 08/30/2021 20:41:18 - INFO - __main__ - Step 41707: {'lr': 0.0004163366429135279, 'samples': 8007744, 'steps': 41706, 'loss/train': 1.383264183998108} 08/30/2021 20:41:19 - INFO - __main__ - Step 41708: {'lr': 0.00041633268120767653, 'samples': 8007936, 'steps': 41707, 'loss/train': 1.9784590005874634} 08/30/2021 20:41:20 - INFO - __main__ - Step 41709: {'lr': 0.00041632871942687814, 'samples': 8008128, 'steps': 41708, 'loss/train': 1.3793046474456787} 08/30/2021 20:41:21 - INFO - __main__ - Step 41710: {'lr': 0.00041632475757113466, 'samples': 8008320, 'steps': 41709, 'loss/train': 1.2249361276626587} 08/30/2021 20:41:21 - INFO - __main__ - Step 41711: {'lr': 0.00041632079564044776, 'samples': 8008512, 'steps': 41710, 'loss/train': 1.6648656129837036} 08/30/2021 20:41:21 - INFO - __main__ - Step 41712: {'lr': 0.0004163168336348194, 'samples': 8008704, 'steps': 41711, 'loss/train': 1.4305875301361084} 08/30/2021 20:41:22 - INFO - __main__ - Step 41713: {'lr': 0.00041631287155425114, 'samples': 8008896, 'steps': 41712, 'loss/train': 1.3651845455169678} 08/30/2021 20:41:23 - INFO - __main__ - Step 41714: {'lr': 0.0004163089093987449, 'samples': 8009088, 'steps': 41713, 'loss/train': 0.8557790517807007} 08/30/2021 20:41:24 - INFO - __main__ - Step 41715: {'lr': 0.00041630494716830244, 'samples': 8009280, 'steps': 41714, 'loss/train': 1.4982314109802246} 08/30/2021 20:41:24 - INFO - __main__ - Step 41716: {'lr': 0.00041630098486292546, 'samples': 8009472, 'steps': 41715, 'loss/train': 1.1822165250778198} 08/30/2021 20:41:24 - INFO - __main__ - Step 41717: {'lr': 0.0004162970224826159, 'samples': 8009664, 'steps': 41716, 'loss/train': 0.06584852933883667} 08/30/2021 20:41:25 - INFO - __main__ - Step 41718: {'lr': 0.0004162930600273754, 'samples': 8009856, 'steps': 41717, 'loss/train': 1.3209549188613892} 08/30/2021 20:41:25 - INFO - __main__ - Step 41719: {'lr': 0.0004162890974972059, 'samples': 8010048, 'steps': 41718, 'loss/train': 1.4217456579208374} 08/30/2021 20:41:27 - INFO - __main__ - Step 41720: {'lr': 0.00041628513489210906, 'samples': 8010240, 'steps': 41719, 'loss/train': 1.3186596632003784} 08/30/2021 20:41:27 - INFO - __main__ - Step 41721: {'lr': 0.0004162811722120867, 'samples': 8010432, 'steps': 41720, 'loss/train': 0.04912729561328888} 08/30/2021 20:41:28 - INFO - __main__ - Step 41722: {'lr': 0.00041627720945714065, 'samples': 8010624, 'steps': 41721, 'loss/train': 1.4928698539733887} 08/30/2021 20:41:28 - INFO - __main__ - Step 41723: {'lr': 0.00041627324662727263, 'samples': 8010816, 'steps': 41722, 'loss/train': 1.291818618774414} 08/30/2021 20:41:28 - INFO - __main__ - Step 41724: {'lr': 0.0004162692837224844, 'samples': 8011008, 'steps': 41723, 'loss/train': 0.8185926675796509} 08/30/2021 20:41:30 - INFO - __main__ - Step 41725: {'lr': 0.00041626532074277785, 'samples': 8011200, 'steps': 41724, 'loss/train': 2.1224584579467773} 08/30/2021 20:41:31 - INFO - __main__ - Step 41726: {'lr': 0.00041626135768815467, 'samples': 8011392, 'steps': 41725, 'loss/train': 1.2835928201675415} 08/30/2021 20:41:31 - INFO - __main__ - Step 41727: {'lr': 0.0004162573945586168, 'samples': 8011584, 'steps': 41726, 'loss/train': 1.151503324508667} 08/30/2021 20:41:32 - INFO - __main__ - Step 41728: {'lr': 0.0004162534313541658, 'samples': 8011776, 'steps': 41727, 'loss/train': 1.7242884635925293} 08/30/2021 20:41:32 - INFO - __main__ - Step 41729: {'lr': 0.00041624946807480357, 'samples': 8011968, 'steps': 41728, 'loss/train': 1.2168521881103516} 08/30/2021 20:41:34 - INFO - __main__ - Step 41730: {'lr': 0.0004162455047205319, 'samples': 8012160, 'steps': 41729, 'loss/train': 1.6182444095611572} 08/30/2021 20:41:34 - INFO - __main__ - Step 41731: {'lr': 0.0004162415412913526, 'samples': 8012352, 'steps': 41730, 'loss/train': 1.455169439315796} 08/30/2021 20:41:34 - INFO - __main__ - Step 41732: {'lr': 0.00041623757778726743, 'samples': 8012544, 'steps': 41731, 'loss/train': 1.88149893283844} 08/30/2021 20:41:35 - INFO - __main__ - Step 41733: {'lr': 0.00041623361420827816, 'samples': 8012736, 'steps': 41732, 'loss/train': 1.9368934631347656} 08/30/2021 20:41:35 - INFO - __main__ - Step 41734: {'lr': 0.0004162296505543867, 'samples': 8012928, 'steps': 41733, 'loss/train': 1.6959967613220215} 08/30/2021 20:41:37 - INFO - __main__ - Step 41735: {'lr': 0.00041622568682559455, 'samples': 8013120, 'steps': 41734, 'loss/train': 1.5027997493743896} 08/30/2021 20:41:37 - INFO - __main__ - Step 41736: {'lr': 0.0004162217230219038, 'samples': 8013312, 'steps': 41735, 'loss/train': 1.6844298839569092} 08/30/2021 20:41:38 - INFO - __main__ - Step 41737: {'lr': 0.00041621775914331595, 'samples': 8013504, 'steps': 41736, 'loss/train': 1.9245612621307373} 08/30/2021 20:41:38 - INFO - __main__ - Step 41738: {'lr': 0.00041621379518983306, 'samples': 8013696, 'steps': 41737, 'loss/train': 1.6410257816314697} 08/30/2021 20:41:38 - INFO - __main__ - Step 41739: {'lr': 0.00041620983116145673, 'samples': 8013888, 'steps': 41738, 'loss/train': 1.424729585647583} 08/30/2021 20:41:39 - INFO - __main__ - Step 41740: {'lr': 0.00041620586705818887, 'samples': 8014080, 'steps': 41739, 'loss/train': 0.9353100657463074} 08/30/2021 20:41:40 - INFO - __main__ - Step 41741: {'lr': 0.00041620190288003126, 'samples': 8014272, 'steps': 41740, 'loss/train': 1.457993507385254} 08/30/2021 20:41:41 - INFO - __main__ - Step 41742: {'lr': 0.00041619793862698553, 'samples': 8014464, 'steps': 41741, 'loss/train': 1.6768105030059814} 08/30/2021 20:41:41 - INFO - __main__ - Step 41743: {'lr': 0.00041619397429905363, 'samples': 8014656, 'steps': 41742, 'loss/train': 1.489015817642212} 08/30/2021 20:41:42 - INFO - __main__ - Step 41744: {'lr': 0.0004161900098962373, 'samples': 8014848, 'steps': 41743, 'loss/train': 1.8153353929519653} 08/30/2021 20:41:42 - INFO - __main__ - Step 41745: {'lr': 0.00041618604541853826, 'samples': 8015040, 'steps': 41744, 'loss/train': 0.9990391135215759} 08/30/2021 20:41:44 - INFO - __main__ - Step 41746: {'lr': 0.00041618208086595843, 'samples': 8015232, 'steps': 41745, 'loss/train': 0.48116764426231384} 08/30/2021 20:41:44 - INFO - __main__ - Step 41747: {'lr': 0.0004161781162384994, 'samples': 8015424, 'steps': 41746, 'loss/train': 1.7746678590774536} 08/30/2021 20:41:44 - INFO - __main__ - Step 41748: {'lr': 0.00041617415153616323, 'samples': 8015616, 'steps': 41747, 'loss/train': 0.4191964268684387} 08/30/2021 20:41:45 - INFO - __main__ - Step 41749: {'lr': 0.00041617018675895145, 'samples': 8015808, 'steps': 41748, 'loss/train': 0.8925157785415649} 08/30/2021 20:41:45 - INFO - __main__ - Step 41750: {'lr': 0.00041616622190686597, 'samples': 8016000, 'steps': 41749, 'loss/train': 1.9171894788742065} 08/30/2021 20:41:47 - INFO - __main__ - Step 41751: {'lr': 0.0004161622569799086, 'samples': 8016192, 'steps': 41750, 'loss/train': 0.05079185962677002} 08/30/2021 20:41:47 - INFO - __main__ - Step 41752: {'lr': 0.00041615829197808095, 'samples': 8016384, 'steps': 41751, 'loss/train': 1.4282255172729492} 08/30/2021 20:41:48 - INFO - __main__ - Step 41753: {'lr': 0.0004161543269013851, 'samples': 8016576, 'steps': 41752, 'loss/train': 0.18148311972618103} 08/30/2021 20:41:48 - INFO - __main__ - Step 41754: {'lr': 0.0004161503617498226, 'samples': 8016768, 'steps': 41753, 'loss/train': 1.6366389989852905} 08/30/2021 20:41:49 - INFO - __main__ - Step 41755: {'lr': 0.00041614639652339533, 'samples': 8016960, 'steps': 41754, 'loss/train': 1.260956048965454} 08/30/2021 20:41:49 - INFO - __main__ - Step 41756: {'lr': 0.00041614243122210505, 'samples': 8017152, 'steps': 41755, 'loss/train': 0.8986827731132507} 08/30/2021 20:41:50 - INFO - __main__ - Step 41757: {'lr': 0.0004161384658459535, 'samples': 8017344, 'steps': 41756, 'loss/train': 1.7238725423812866} 08/30/2021 20:41:51 - INFO - __main__ - Step 41758: {'lr': 0.0004161345003949426, 'samples': 8017536, 'steps': 41757, 'loss/train': 1.31426203250885} 08/30/2021 20:41:51 - INFO - __main__ - Step 41759: {'lr': 0.00041613053486907396, 'samples': 8017728, 'steps': 41758, 'loss/train': 1.3150458335876465} 08/30/2021 20:41:52 - INFO - __main__ - Step 41760: {'lr': 0.0004161265692683496, 'samples': 8017920, 'steps': 41759, 'loss/train': 1.899686574935913} 08/30/2021 20:41:52 - INFO - __main__ - Step 41761: {'lr': 0.0004161226035927711, 'samples': 8018112, 'steps': 41760, 'loss/train': 2.4361443519592285} 08/30/2021 20:41:53 - INFO - __main__ - Step 41762: {'lr': 0.0004161186378423403, 'samples': 8018304, 'steps': 41761, 'loss/train': 0.9371394515037537} 08/30/2021 20:41:54 - INFO - __main__ - Step 41763: {'lr': 0.000416114672017059, 'samples': 8018496, 'steps': 41762, 'loss/train': 1.2019520998001099} 08/30/2021 20:41:54 - INFO - __main__ - Step 41764: {'lr': 0.000416110706116929, 'samples': 8018688, 'steps': 41763, 'loss/train': 1.0509260892868042} 08/30/2021 20:41:55 - INFO - __main__ - Step 41765: {'lr': 0.0004161067401419521, 'samples': 8018880, 'steps': 41764, 'loss/train': 1.5440552234649658} 08/30/2021 20:41:55 - INFO - __main__ - Step 41766: {'lr': 0.00041610277409213003, 'samples': 8019072, 'steps': 41765, 'loss/train': 1.3422781229019165} 08/30/2021 20:41:57 - INFO - __main__ - Step 41767: {'lr': 0.00041609880796746463, 'samples': 8019264, 'steps': 41766, 'loss/train': 1.0526846647262573} 08/30/2021 20:41:57 - INFO - __main__ - Step 41768: {'lr': 0.00041609484176795774, 'samples': 8019456, 'steps': 41767, 'loss/train': 1.498138666152954} 08/30/2021 20:41:57 - INFO - __main__ - Step 41769: {'lr': 0.000416090875493611, 'samples': 8019648, 'steps': 41768, 'loss/train': 0.9550386071205139} 08/30/2021 20:41:58 - INFO - __main__ - Step 41770: {'lr': 0.0004160869091444263, 'samples': 8019840, 'steps': 41769, 'loss/train': 1.6613816022872925} 08/30/2021 20:41:58 - INFO - __main__ - Step 41771: {'lr': 0.0004160829427204054, 'samples': 8020032, 'steps': 41770, 'loss/train': 0.5467845797538757} 08/30/2021 20:42:00 - INFO - __main__ - Step 41772: {'lr': 0.00041607897622155006, 'samples': 8020224, 'steps': 41771, 'loss/train': 1.3568012714385986} 08/30/2021 20:42:00 - INFO - __main__ - Step 41773: {'lr': 0.00041607500964786217, 'samples': 8020416, 'steps': 41772, 'loss/train': 1.6734267473220825} 08/30/2021 20:42:00 - INFO - __main__ - Step 41774: {'lr': 0.0004160710429993434, 'samples': 8020608, 'steps': 41773, 'loss/train': 1.9361891746520996} 08/30/2021 20:42:01 - INFO - __main__ - Step 41775: {'lr': 0.00041606707627599556, 'samples': 8020800, 'steps': 41774, 'loss/train': 1.5149098634719849} 08/30/2021 20:42:01 - INFO - __main__ - Step 41776: {'lr': 0.00041606310947782046, 'samples': 8020992, 'steps': 41775, 'loss/train': 1.3088252544403076} 08/30/2021 20:42:03 - INFO - __main__ - Step 41777: {'lr': 0.0004160591426048199, 'samples': 8021184, 'steps': 41776, 'loss/train': 1.2729098796844482} 08/30/2021 20:42:03 - INFO - __main__ - Step 41778: {'lr': 0.00041605517565699565, 'samples': 8021376, 'steps': 41777, 'loss/train': 1.208472728729248} 08/30/2021 20:42:03 - INFO - __main__ - Step 41779: {'lr': 0.00041605120863434945, 'samples': 8021568, 'steps': 41778, 'loss/train': 1.831836223602295} 08/30/2021 20:42:04 - INFO - __main__ - Step 41780: {'lr': 0.0004160472415368832, 'samples': 8021760, 'steps': 41779, 'loss/train': 1.271667718887329} 08/30/2021 20:42:04 - INFO - __main__ - Step 41781: {'lr': 0.00041604327436459864, 'samples': 8021952, 'steps': 41780, 'loss/train': 1.7045323848724365} 08/30/2021 20:42:04 - INFO - __main__ - Step 41782: {'lr': 0.0004160393071174975, 'samples': 8022144, 'steps': 41781, 'loss/train': 0.5790306329727173} 08/30/2021 20:42:07 - INFO - __main__ - Step 41783: {'lr': 0.00041603533979558163, 'samples': 8022336, 'steps': 41782, 'loss/train': 0.6085450649261475} 08/30/2021 20:42:07 - INFO - __main__ - Step 41784: {'lr': 0.0004160313723988528, 'samples': 8022528, 'steps': 41783, 'loss/train': 0.17379771173000336} 08/30/2021 20:42:07 - INFO - __main__ - Step 41785: {'lr': 0.00041602740492731284, 'samples': 8022720, 'steps': 41784, 'loss/train': 1.8490116596221924} 08/30/2021 20:42:08 - INFO - __main__ - Step 41786: {'lr': 0.0004160234373809634, 'samples': 8022912, 'steps': 41785, 'loss/train': 1.3827310800552368} 08/30/2021 20:42:08 - INFO - __main__ - Step 41787: {'lr': 0.0004160194697598064, 'samples': 8023104, 'steps': 41786, 'loss/train': 1.4580172300338745} 08/30/2021 20:42:10 - INFO - __main__ - Step 41788: {'lr': 0.0004160155020638436, 'samples': 8023296, 'steps': 41787, 'loss/train': 1.7783116102218628} 08/30/2021 20:42:10 - INFO - __main__ - Step 41789: {'lr': 0.0004160115342930768, 'samples': 8023488, 'steps': 41788, 'loss/train': 2.2475783824920654} 08/30/2021 20:42:10 - INFO - __main__ - Step 41790: {'lr': 0.0004160075664475077, 'samples': 8023680, 'steps': 41789, 'loss/train': 1.2616629600524902} 08/30/2021 20:42:11 - INFO - __main__ - Step 41791: {'lr': 0.0004160035985271382, 'samples': 8023872, 'steps': 41790, 'loss/train': 0.49890244007110596} 08/30/2021 20:42:11 - INFO - __main__ - Step 41792: {'lr': 0.00041599963053196997, 'samples': 8024064, 'steps': 41791, 'loss/train': 2.033851385116577} 08/30/2021 20:42:13 - INFO - __main__ - Step 41793: {'lr': 0.0004159956624620049, 'samples': 8024256, 'steps': 41792, 'loss/train': 1.469059944152832} 08/30/2021 20:42:13 - INFO - __main__ - Step 41794: {'lr': 0.0004159916943172448, 'samples': 8024448, 'steps': 41793, 'loss/train': 1.3045949935913086} 08/30/2021 20:42:14 - INFO - __main__ - Step 41795: {'lr': 0.0004159877260976914, 'samples': 8024640, 'steps': 41794, 'loss/train': 1.591121792793274} 08/30/2021 20:42:14 - INFO - __main__ - Step 41796: {'lr': 0.00041598375780334653, 'samples': 8024832, 'steps': 41795, 'loss/train': 0.847492516040802} 08/30/2021 20:42:14 - INFO - __main__ - Step 41797: {'lr': 0.0004159797894342118, 'samples': 8025024, 'steps': 41796, 'loss/train': 1.1704052686691284} 08/30/2021 20:42:16 - INFO - __main__ - Step 41798: {'lr': 0.0004159758209902892, 'samples': 8025216, 'steps': 41797, 'loss/train': 1.4010660648345947} 08/30/2021 20:42:16 - INFO - __main__ - Step 41799: {'lr': 0.00041597185247158053, 'samples': 8025408, 'steps': 41798, 'loss/train': 0.780902624130249} 08/30/2021 20:42:17 - INFO - __main__ - Step 41800: {'lr': 0.0004159678838780874, 'samples': 8025600, 'steps': 41799, 'loss/train': 1.338391900062561} 08/30/2021 20:42:17 - INFO - __main__ - Step 41801: {'lr': 0.0004159639152098118, 'samples': 8025792, 'steps': 41800, 'loss/train': 1.3567825555801392} 08/30/2021 20:42:17 - INFO - __main__ - Step 41802: {'lr': 0.00041595994646675537, 'samples': 8025984, 'steps': 41801, 'loss/train': 1.3682771921157837} 08/30/2021 20:42:18 - INFO - __main__ - Step 41803: {'lr': 0.0004159559776489199, 'samples': 8026176, 'steps': 41802, 'loss/train': 1.5757153034210205} 08/30/2021 20:42:19 - INFO - __main__ - Step 41804: {'lr': 0.00041595200875630734, 'samples': 8026368, 'steps': 41803, 'loss/train': 0.9679489135742188} 08/30/2021 20:42:19 - INFO - __main__ - Step 41805: {'lr': 0.00041594803978891925, 'samples': 8026560, 'steps': 41804, 'loss/train': 1.078711986541748} 08/30/2021 20:42:20 - INFO - __main__ - Step 41806: {'lr': 0.00041594407074675753, 'samples': 8026752, 'steps': 41805, 'loss/train': 1.5219484567642212} 08/30/2021 20:42:20 - INFO - __main__ - Step 41807: {'lr': 0.0004159401016298241, 'samples': 8026944, 'steps': 41806, 'loss/train': 2.496682643890381} 08/30/2021 20:42:21 - INFO - __main__ - Step 41808: {'lr': 0.0004159361324381206, 'samples': 8027136, 'steps': 41807, 'loss/train': 1.4242775440216064} 08/30/2021 20:42:22 - INFO - __main__ - Step 41809: {'lr': 0.0004159321631716487, 'samples': 8027328, 'steps': 41808, 'loss/train': 1.583635926246643} 08/30/2021 20:42:23 - INFO - __main__ - Step 41810: {'lr': 0.00041592819383041047, 'samples': 8027520, 'steps': 41809, 'loss/train': 1.483121633529663} 08/30/2021 20:42:23 - INFO - __main__ - Step 41811: {'lr': 0.0004159242244144075, 'samples': 8027712, 'steps': 41810, 'loss/train': 1.496715784072876} 08/30/2021 20:42:24 - INFO - __main__ - Step 41812: {'lr': 0.0004159202549236416, 'samples': 8027904, 'steps': 41811, 'loss/train': 1.4398528337478638} 08/30/2021 20:42:24 - INFO - __main__ - Step 41813: {'lr': 0.00041591628535811464, 'samples': 8028096, 'steps': 41812, 'loss/train': 0.08508310467004776} 08/30/2021 20:42:24 - INFO - __main__ - Step 41814: {'lr': 0.00041591231571782834, 'samples': 8028288, 'steps': 41813, 'loss/train': 0.26660722494125366} 08/30/2021 20:42:26 - INFO - __main__ - Step 41815: {'lr': 0.0004159083460027845, 'samples': 8028480, 'steps': 41814, 'loss/train': 1.042811632156372} 08/30/2021 20:42:26 - INFO - __main__ - Step 41816: {'lr': 0.000415904376212985, 'samples': 8028672, 'steps': 41815, 'loss/train': 1.7438234090805054} 08/30/2021 20:42:27 - INFO - __main__ - Step 41817: {'lr': 0.00041590040634843144, 'samples': 8028864, 'steps': 41816, 'loss/train': 1.9059609174728394} 08/30/2021 20:42:27 - INFO - __main__ - Step 41818: {'lr': 0.00041589643640912576, 'samples': 8029056, 'steps': 41817, 'loss/train': 1.4541925191879272} 08/30/2021 20:42:27 - INFO - __main__ - Step 41819: {'lr': 0.0004158924663950697, 'samples': 8029248, 'steps': 41818, 'loss/train': 1.4391422271728516} 08/30/2021 20:42:29 - INFO - __main__ - Step 41820: {'lr': 0.00041588849630626513, 'samples': 8029440, 'steps': 41819, 'loss/train': 1.200029969215393} 08/30/2021 20:42:29 - INFO - __main__ - Step 41821: {'lr': 0.00041588452614271364, 'samples': 8029632, 'steps': 41820, 'loss/train': 1.5291684865951538} 08/30/2021 20:42:30 - INFO - __main__ - Step 41822: {'lr': 0.00041588055590441726, 'samples': 8029824, 'steps': 41821, 'loss/train': 1.3797036409378052} 08/30/2021 20:42:30 - INFO - __main__ - Step 41823: {'lr': 0.0004158765855913776, 'samples': 8030016, 'steps': 41822, 'loss/train': 1.2176798582077026} 08/30/2021 20:42:31 - INFO - __main__ - Step 41824: {'lr': 0.0004158726152035965, 'samples': 8030208, 'steps': 41823, 'loss/train': 1.4863344430923462} 08/30/2021 20:42:33 - INFO - __main__ - Step 41825: {'lr': 0.00041586864474107575, 'samples': 8030400, 'steps': 41824, 'loss/train': 1.5318057537078857} 08/30/2021 20:42:34 - INFO - __main__ - Step 41826: {'lr': 0.0004158646742038172, 'samples': 8030592, 'steps': 41825, 'loss/train': 1.7026723623275757} 08/30/2021 20:42:34 - INFO - __main__ - Step 41827: {'lr': 0.00041586070359182255, 'samples': 8030784, 'steps': 41826, 'loss/train': 1.4229241609573364} 08/30/2021 20:42:35 - INFO - __main__ - Step 41828: {'lr': 0.00041585673290509364, 'samples': 8030976, 'steps': 41827, 'loss/train': 1.519781231880188} 08/30/2021 20:42:35 - INFO - __main__ - Step 41829: {'lr': 0.0004158527621436322, 'samples': 8031168, 'steps': 41828, 'loss/train': 1.8084534406661987} 08/30/2021 20:42:35 - INFO - __main__ - Step 41830: {'lr': 0.0004158487913074401, 'samples': 8031360, 'steps': 41829, 'loss/train': 1.7924851179122925} 08/30/2021 20:42:36 - INFO - __main__ - Step 41831: {'lr': 0.0004158448203965192, 'samples': 8031552, 'steps': 41830, 'loss/train': 1.825628399848938} 08/30/2021 20:42:36 - INFO - __main__ - Step 41832: {'lr': 0.000415840849410871, 'samples': 8031744, 'steps': 41831, 'loss/train': 0.1913384348154068} 08/30/2021 20:42:37 - INFO - __main__ - Step 41833: {'lr': 0.0004158368783504975, 'samples': 8031936, 'steps': 41832, 'loss/train': 1.4772800207138062} 08/30/2021 20:42:38 - INFO - __main__ - Step 41834: {'lr': 0.00041583290721540055, 'samples': 8032128, 'steps': 41833, 'loss/train': 1.0174660682678223} 08/30/2021 20:42:38 - INFO - __main__ - Step 41835: {'lr': 0.0004158289360055819, 'samples': 8032320, 'steps': 41834, 'loss/train': 1.4912314414978027} 08/30/2021 20:42:38 - INFO - __main__ - Step 41836: {'lr': 0.00041582496472104314, 'samples': 8032512, 'steps': 41835, 'loss/train': 1.8404120206832886} 08/30/2021 20:42:39 - INFO - __main__ - Step 41837: {'lr': 0.0004158209933617863, 'samples': 8032704, 'steps': 41836, 'loss/train': 1.5737131834030151} 08/30/2021 20:42:40 - INFO - __main__ - Step 41838: {'lr': 0.00041581702192781305, 'samples': 8032896, 'steps': 41837, 'loss/train': 1.67239511013031} 08/30/2021 20:42:41 - INFO - __main__ - Step 41839: {'lr': 0.0004158130504191252, 'samples': 8033088, 'steps': 41838, 'loss/train': 1.185289740562439} 08/30/2021 20:42:41 - INFO - __main__ - Step 41840: {'lr': 0.0004158090788357246, 'samples': 8033280, 'steps': 41839, 'loss/train': 1.847983717918396} 08/30/2021 20:42:42 - INFO - __main__ - Step 41841: {'lr': 0.0004158051071776129, 'samples': 8033472, 'steps': 41840, 'loss/train': 1.5942496061325073} 08/30/2021 20:42:42 - INFO - __main__ - Step 41842: {'lr': 0.00041580113544479203, 'samples': 8033664, 'steps': 41841, 'loss/train': 1.6874637603759766} 08/30/2021 20:42:44 - INFO - __main__ - Step 41843: {'lr': 0.00041579716363726376, 'samples': 8033856, 'steps': 41842, 'loss/train': 1.8654677867889404} 08/30/2021 20:42:44 - INFO - __main__ - Step 41844: {'lr': 0.00041579319175502985, 'samples': 8034048, 'steps': 41843, 'loss/train': 1.5211448669433594} 08/30/2021 20:42:45 - INFO - __main__ - Step 41845: {'lr': 0.000415789219798092, 'samples': 8034240, 'steps': 41844, 'loss/train': 1.0404632091522217} 08/30/2021 20:42:45 - INFO - __main__ - Step 41846: {'lr': 0.00041578524776645216, 'samples': 8034432, 'steps': 41845, 'loss/train': 1.1511561870574951} 08/30/2021 20:42:46 - INFO - __main__ - Step 41847: {'lr': 0.00041578127566011203, 'samples': 8034624, 'steps': 41846, 'loss/train': 1.2978366613388062} 08/30/2021 20:42:47 - INFO - __main__ - Step 41848: {'lr': 0.0004157773034790734, 'samples': 8034816, 'steps': 41847, 'loss/train': 0.9080016016960144} 08/30/2021 20:42:48 - INFO - __main__ - Step 41849: {'lr': 0.00041577333122333807, 'samples': 8035008, 'steps': 41848, 'loss/train': 1.3785098791122437} 08/30/2021 20:42:48 - INFO - __main__ - Step 41850: {'lr': 0.00041576935889290777, 'samples': 8035200, 'steps': 41849, 'loss/train': 1.5190757513046265} 08/30/2021 20:42:48 - INFO - __main__ - Step 41851: {'lr': 0.0004157653864877845, 'samples': 8035392, 'steps': 41850, 'loss/train': 0.7366766929626465} 08/30/2021 20:42:49 - INFO - __main__ - Step 41852: {'lr': 0.00041576141400796984, 'samples': 8035584, 'steps': 41851, 'loss/train': 0.07756426185369492} 08/30/2021 20:42:49 - INFO - __main__ - Step 41853: {'lr': 0.00041575744145346563, 'samples': 8035776, 'steps': 41852, 'loss/train': 0.9598649144172668} 08/30/2021 20:42:51 - INFO - __main__ - Step 41854: {'lr': 0.00041575346882427366, 'samples': 8035968, 'steps': 41853, 'loss/train': 1.652033805847168} 08/30/2021 20:42:51 - INFO - __main__ - Step 41855: {'lr': 0.00041574949612039583, 'samples': 8036160, 'steps': 41854, 'loss/train': 1.572953224182129} 08/30/2021 20:42:51 - INFO - __main__ - Step 41856: {'lr': 0.0004157455233418337, 'samples': 8036352, 'steps': 41855, 'loss/train': 1.3858767747879028} 08/30/2021 20:42:52 - INFO - __main__ - Step 41857: {'lr': 0.0004157415504885893, 'samples': 8036544, 'steps': 41856, 'loss/train': 1.0582249164581299} 08/30/2021 20:42:52 - INFO - __main__ - Step 41858: {'lr': 0.00041573757756066423, 'samples': 8036736, 'steps': 41857, 'loss/train': 0.40921273827552795} 08/30/2021 20:42:54 - INFO - __main__ - Step 41859: {'lr': 0.0004157336045580604, 'samples': 8036928, 'steps': 41858, 'loss/train': 1.0436087846755981} 08/30/2021 20:42:54 - INFO - __main__ - Step 41860: {'lr': 0.0004157296314807796, 'samples': 8037120, 'steps': 41859, 'loss/train': 1.573651671409607} 08/30/2021 20:42:54 - INFO - __main__ - Step 41861: {'lr': 0.0004157256583288235, 'samples': 8037312, 'steps': 41860, 'loss/train': 1.570266842842102} 08/30/2021 20:42:55 - INFO - __main__ - Step 41862: {'lr': 0.0004157216851021941, 'samples': 8037504, 'steps': 41861, 'loss/train': 1.5497149229049683} 08/30/2021 20:42:55 - INFO - __main__ - Step 41863: {'lr': 0.00041571771180089304, 'samples': 8037696, 'steps': 41862, 'loss/train': 1.0708867311477661} 08/30/2021 20:42:57 - INFO - __main__ - Step 41864: {'lr': 0.0004157137384249221, 'samples': 8037888, 'steps': 41863, 'loss/train': 1.174491286277771} 08/30/2021 20:42:57 - INFO - __main__ - Step 41865: {'lr': 0.00041570976497428303, 'samples': 8038080, 'steps': 41864, 'loss/train': 1.3570365905761719} 08/30/2021 20:42:58 - INFO - __main__ - Step 41866: {'lr': 0.0004157057914489778, 'samples': 8038272, 'steps': 41865, 'loss/train': 1.6820279359817505} 08/30/2021 20:42:58 - INFO - __main__ - Step 41867: {'lr': 0.00041570181784900806, 'samples': 8038464, 'steps': 41866, 'loss/train': 1.382882833480835} 08/30/2021 20:42:58 - INFO - __main__ - Step 41868: {'lr': 0.0004156978441743756, 'samples': 8038656, 'steps': 41867, 'loss/train': 2.1571285724639893} 08/30/2021 20:42:59 - INFO - __main__ - Step 41869: {'lr': 0.00041569387042508235, 'samples': 8038848, 'steps': 41868, 'loss/train': 1.3227064609527588} 08/30/2021 20:43:00 - INFO - __main__ - Step 41870: {'lr': 0.0004156898966011299, 'samples': 8039040, 'steps': 41869, 'loss/train': 1.7419781684875488} 08/30/2021 20:43:01 - INFO - __main__ - Step 41871: {'lr': 0.0004156859227025202, 'samples': 8039232, 'steps': 41870, 'loss/train': 1.4750696420669556} 08/30/2021 20:43:01 - INFO - __main__ - Step 41872: {'lr': 0.0004156819487292549, 'samples': 8039424, 'steps': 41871, 'loss/train': 1.37647545337677} 08/30/2021 20:43:02 - INFO - __main__ - Step 41873: {'lr': 0.00041567797468133595, 'samples': 8039616, 'steps': 41872, 'loss/train': 1.659361481666565} 08/30/2021 20:43:02 - INFO - __main__ - Step 41874: {'lr': 0.00041567400055876505, 'samples': 8039808, 'steps': 41873, 'loss/train': 1.371205449104309} 08/30/2021 20:43:04 - INFO - __main__ - Step 41875: {'lr': 0.00041567002636154406, 'samples': 8040000, 'steps': 41874, 'loss/train': 0.840124249458313} 08/30/2021 20:43:04 - INFO - __main__ - Step 41876: {'lr': 0.0004156660520896746, 'samples': 8040192, 'steps': 41875, 'loss/train': 1.6229898929595947} 08/30/2021 20:43:05 - INFO - __main__ - Step 41877: {'lr': 0.00041566207774315866, 'samples': 8040384, 'steps': 41876, 'loss/train': 1.4709619283676147} 08/30/2021 20:43:05 - INFO - __main__ - Step 41878: {'lr': 0.0004156581033219979, 'samples': 8040576, 'steps': 41877, 'loss/train': 0.6833112835884094} 08/30/2021 20:43:06 - INFO - __main__ - Step 41879: {'lr': 0.0004156541288261941, 'samples': 8040768, 'steps': 41878, 'loss/train': 1.489064335823059} 08/30/2021 20:43:06 - INFO - __main__ - Step 41880: {'lr': 0.00041565015425574917, 'samples': 8040960, 'steps': 41879, 'loss/train': 0.029329517856240273} 08/30/2021 20:43:07 - INFO - __main__ - Step 41881: {'lr': 0.00041564617961066487, 'samples': 8041152, 'steps': 41880, 'loss/train': 1.3005467653274536} 08/30/2021 20:43:08 - INFO - __main__ - Step 41882: {'lr': 0.00041564220489094295, 'samples': 8041344, 'steps': 41881, 'loss/train': 1.610386610031128} 08/30/2021 20:43:08 - INFO - __main__ - Step 41883: {'lr': 0.00041563823009658514, 'samples': 8041536, 'steps': 41882, 'loss/train': 0.897910475730896} 08/30/2021 20:43:09 - INFO - __main__ - Step 41884: {'lr': 0.00041563425522759336, 'samples': 8041728, 'steps': 41883, 'loss/train': 1.4776582717895508} 08/30/2021 20:43:09 - INFO - __main__ - Step 41885: {'lr': 0.0004156302802839693, 'samples': 8041920, 'steps': 41884, 'loss/train': 1.9614852666854858} 08/30/2021 20:43:10 - INFO - __main__ - Step 41886: {'lr': 0.0004156263052657148, 'samples': 8042112, 'steps': 41885, 'loss/train': 1.7023252248764038} 08/30/2021 20:43:11 - INFO - __main__ - Step 41887: {'lr': 0.0004156223301728316, 'samples': 8042304, 'steps': 41886, 'loss/train': 1.903437852859497} 08/30/2021 20:43:11 - INFO - __main__ - Step 41888: {'lr': 0.0004156183550053216, 'samples': 8042496, 'steps': 41887, 'loss/train': 1.803829312324524} 08/30/2021 20:43:11 - INFO - __main__ - Step 41889: {'lr': 0.0004156143797631866, 'samples': 8042688, 'steps': 41888, 'loss/train': 1.4281631708145142} 08/30/2021 20:43:12 - INFO - __main__ - Step 41890: {'lr': 0.0004156104044464282, 'samples': 8042880, 'steps': 41889, 'loss/train': 0.9988219141960144} 08/30/2021 20:43:14 - INFO - __main__ - Step 41891: {'lr': 0.00041560642905504833, 'samples': 8043072, 'steps': 41890, 'loss/train': 0.5660489797592163} 08/30/2021 20:43:14 - INFO - __main__ - Step 41892: {'lr': 0.0004156024535890487, 'samples': 8043264, 'steps': 41891, 'loss/train': 1.4819796085357666} 08/30/2021 20:43:15 - INFO - __main__ - Step 41893: {'lr': 0.00041559847804843123, 'samples': 8043456, 'steps': 41892, 'loss/train': 1.305707335472107} 08/30/2021 20:43:15 - INFO - __main__ - Step 41894: {'lr': 0.0004155945024331976, 'samples': 8043648, 'steps': 41893, 'loss/train': 1.7447402477264404} 08/30/2021 20:43:15 - INFO - __main__ - Step 41895: {'lr': 0.00041559052674334975, 'samples': 8043840, 'steps': 41894, 'loss/train': 1.294675350189209} 08/30/2021 20:43:16 - INFO - __main__ - Step 41896: {'lr': 0.0004155865509788893, 'samples': 8044032, 'steps': 41895, 'loss/train': 1.0206354856491089} 08/30/2021 20:43:18 - INFO - __main__ - Step 41897: {'lr': 0.00041558257513981805, 'samples': 8044224, 'steps': 41896, 'loss/train': 0.14419202506542206} 08/30/2021 20:43:18 - INFO - __main__ - Step 41898: {'lr': 0.00041557859922613795, 'samples': 8044416, 'steps': 41897, 'loss/train': 1.6448591947555542} 08/30/2021 20:43:19 - INFO - __main__ - Step 41899: {'lr': 0.00041557462323785053, 'samples': 8044608, 'steps': 41898, 'loss/train': 1.1527259349822998} 08/30/2021 20:43:19 - INFO - __main__ - Step 41900: {'lr': 0.00041557064717495786, 'samples': 8044800, 'steps': 41899, 'loss/train': 1.0871294736862183} 08/30/2021 20:43:19 - INFO - __main__ - Step 41901: {'lr': 0.00041556667103746157, 'samples': 8044992, 'steps': 41900, 'loss/train': 0.06764210015535355} 08/30/2021 20:43:21 - INFO - __main__ - Step 41902: {'lr': 0.00041556269482536355, 'samples': 8045184, 'steps': 41901, 'loss/train': 2.183725118637085} 08/30/2021 20:43:22 - INFO - __main__ - Step 41903: {'lr': 0.00041555871853866553, 'samples': 8045376, 'steps': 41902, 'loss/train': 1.1897425651550293} 08/30/2021 20:43:22 - INFO - __main__ - Step 41904: {'lr': 0.00041555474217736926, 'samples': 8045568, 'steps': 41903, 'loss/train': 0.4623366892337799} 08/30/2021 20:43:22 - INFO - __main__ - Step 41905: {'lr': 0.0004155507657414766, 'samples': 8045760, 'steps': 41904, 'loss/train': 1.517594337463379} 08/30/2021 20:43:23 - INFO - __main__ - Step 41906: {'lr': 0.0004155467892309893, 'samples': 8045952, 'steps': 41905, 'loss/train': 1.351616621017456} 08/30/2021 20:43:24 - INFO - __main__ - Step 41907: {'lr': 0.0004155428126459092, 'samples': 8046144, 'steps': 41906, 'loss/train': 1.2100814580917358} 08/30/2021 20:43:24 - INFO - __main__ - Step 41908: {'lr': 0.00041553883598623804, 'samples': 8046336, 'steps': 41907, 'loss/train': 1.0407642126083374} 08/30/2021 20:43:25 - INFO - __main__ - Step 41909: {'lr': 0.00041553485925197763, 'samples': 8046528, 'steps': 41908, 'loss/train': 1.5186941623687744} 08/30/2021 20:43:25 - INFO - __main__ - Step 41910: {'lr': 0.00041553088244312975, 'samples': 8046720, 'steps': 41909, 'loss/train': 1.2687880992889404} 08/30/2021 20:43:25 - INFO - __main__ - Step 41911: {'lr': 0.0004155269055596963, 'samples': 8046912, 'steps': 41910, 'loss/train': 1.5419580936431885} 08/30/2021 20:43:27 - INFO - __main__ - Step 41912: {'lr': 0.0004155229286016789, 'samples': 8047104, 'steps': 41911, 'loss/train': 0.28386372327804565} 08/30/2021 20:43:27 - INFO - __main__ - Step 41913: {'lr': 0.0004155189515690794, 'samples': 8047296, 'steps': 41912, 'loss/train': 1.9679127931594849} 08/30/2021 20:43:28 - INFO - __main__ - Step 41914: {'lr': 0.0004155149744618997, 'samples': 8047488, 'steps': 41913, 'loss/train': 0.8942242860794067} 08/30/2021 20:43:28 - INFO - __main__ - Step 41915: {'lr': 0.0004155109972801414, 'samples': 8047680, 'steps': 41914, 'loss/train': 1.5286887884140015} 08/30/2021 20:43:28 - INFO - __main__ - Step 41916: {'lr': 0.0004155070200238065, 'samples': 8047872, 'steps': 41915, 'loss/train': 1.4754290580749512} 08/30/2021 20:43:29 - INFO - __main__ - Step 41917: {'lr': 0.00041550304269289664, 'samples': 8048064, 'steps': 41916, 'loss/train': 1.644362449645996} 08/30/2021 20:43:30 - INFO - __main__ - Step 41918: {'lr': 0.00041549906528741366, 'samples': 8048256, 'steps': 41917, 'loss/train': 5.717835903167725} 08/30/2021 20:43:31 - INFO - __main__ - Step 41919: {'lr': 0.0004154950878073594, 'samples': 8048448, 'steps': 41918, 'loss/train': 1.3945873975753784} 08/30/2021 20:43:31 - INFO - __main__ - Step 41920: {'lr': 0.0004154911102527356, 'samples': 8048640, 'steps': 41919, 'loss/train': 1.3416826725006104} 08/30/2021 20:43:31 - INFO - __main__ - Step 41921: {'lr': 0.00041548713262354396, 'samples': 8048832, 'steps': 41920, 'loss/train': 1.6950429677963257} 08/30/2021 20:43:32 - INFO - __main__ - Step 41922: {'lr': 0.0004154831549197865, 'samples': 8049024, 'steps': 41921, 'loss/train': 1.313057541847229} 08/30/2021 20:43:33 - INFO - __main__ - Step 41923: {'lr': 0.0004154791771414648, 'samples': 8049216, 'steps': 41922, 'loss/train': 1.4533997774124146} 08/30/2021 20:43:34 - INFO - __main__ - Step 41924: {'lr': 0.0004154751992885808, 'samples': 8049408, 'steps': 41923, 'loss/train': 1.559550404548645} 08/30/2021 20:43:34 - INFO - __main__ - Step 41925: {'lr': 0.0004154712213611362, 'samples': 8049600, 'steps': 41924, 'loss/train': 1.6962049007415771} 08/30/2021 20:43:35 - INFO - __main__ - Step 41926: {'lr': 0.0004154672433591328, 'samples': 8049792, 'steps': 41925, 'loss/train': 1.6122878789901733} 08/30/2021 20:43:35 - INFO - __main__ - Step 41927: {'lr': 0.0004154632652825724, 'samples': 8049984, 'steps': 41926, 'loss/train': 2.295560836791992} 08/30/2021 20:43:36 - INFO - __main__ - Step 41928: {'lr': 0.00041545928713145687, 'samples': 8050176, 'steps': 41927, 'loss/train': 1.4711755514144897} 08/30/2021 20:43:37 - INFO - __main__ - Step 41929: {'lr': 0.00041545530890578784, 'samples': 8050368, 'steps': 41928, 'loss/train': 1.9420548677444458} 08/30/2021 20:43:37 - INFO - __main__ - Step 41930: {'lr': 0.00041545133060556734, 'samples': 8050560, 'steps': 41929, 'loss/train': 0.9520986676216125} 08/30/2021 20:43:38 - INFO - __main__ - Step 41931: {'lr': 0.00041544735223079693, 'samples': 8050752, 'steps': 41930, 'loss/train': 1.1703599691390991} 08/30/2021 20:43:38 - INFO - __main__ - Step 41932: {'lr': 0.0004154433737814786, 'samples': 8050944, 'steps': 41931, 'loss/train': 1.2997748851776123} 08/30/2021 20:43:39 - INFO - __main__ - Step 41933: {'lr': 0.0004154393952576139, 'samples': 8051136, 'steps': 41932, 'loss/train': 1.6423181295394897} 08/30/2021 20:43:40 - INFO - __main__ - Step 41934: {'lr': 0.00041543541665920483, 'samples': 8051328, 'steps': 41933, 'loss/train': 1.6377413272857666} 08/30/2021 20:43:40 - INFO - __main__ - Step 41935: {'lr': 0.000415431437986253, 'samples': 8051520, 'steps': 41934, 'loss/train': 1.0988579988479614} 08/30/2021 20:43:41 - INFO - __main__ - Step 41936: {'lr': 0.00041542745923876047, 'samples': 8051712, 'steps': 41935, 'loss/train': 0.6673511266708374} 08/30/2021 20:43:41 - INFO - __main__ - Step 41937: {'lr': 0.00041542348041672886, 'samples': 8051904, 'steps': 41936, 'loss/train': 1.1943817138671875} 08/30/2021 20:43:42 - INFO - __main__ - Step 41938: {'lr': 0.00041541950152015997, 'samples': 8052096, 'steps': 41937, 'loss/train': 1.6588021516799927} 08/30/2021 20:43:43 - INFO - __main__ - Step 41939: {'lr': 0.0004154155225490555, 'samples': 8052288, 'steps': 41938, 'loss/train': 0.11105537414550781} 08/30/2021 20:43:43 - INFO - __main__ - Step 41940: {'lr': 0.0004154115435034175, 'samples': 8052480, 'steps': 41939, 'loss/train': 1.7889378070831299} 08/30/2021 20:43:44 - INFO - __main__ - Step 41941: {'lr': 0.00041540756438324746, 'samples': 8052672, 'steps': 41940, 'loss/train': 1.812666893005371} 08/30/2021 20:43:44 - INFO - __main__ - Step 41942: {'lr': 0.0004154035851885474, 'samples': 8052864, 'steps': 41941, 'loss/train': 1.3219572305679321} 08/30/2021 20:43:45 - INFO - __main__ - Step 41943: {'lr': 0.0004153996059193191, 'samples': 8053056, 'steps': 41942, 'loss/train': 1.5544521808624268} 08/30/2021 20:43:46 - INFO - __main__ - Step 41944: {'lr': 0.0004153956265755642, 'samples': 8053248, 'steps': 41943, 'loss/train': 1.6918978691101074} 08/30/2021 20:43:46 - INFO - __main__ - Step 41945: {'lr': 0.0004153916471572846, 'samples': 8053440, 'steps': 41944, 'loss/train': 1.6003272533416748} 08/30/2021 20:43:47 - INFO - __main__ - Step 41946: {'lr': 0.0004153876676644821, 'samples': 8053632, 'steps': 41945, 'loss/train': 1.4478598833084106} 08/30/2021 20:43:47 - INFO - __main__ - Step 41947: {'lr': 0.0004153836880971585, 'samples': 8053824, 'steps': 41946, 'loss/train': 1.5218452215194702} 08/30/2021 20:43:47 - INFO - __main__ - Step 41948: {'lr': 0.00041537970845531547, 'samples': 8054016, 'steps': 41947, 'loss/train': 1.337354302406311} 08/30/2021 20:43:49 - INFO - __main__ - Step 41949: {'lr': 0.00041537572873895503, 'samples': 8054208, 'steps': 41948, 'loss/train': 1.4841079711914062} 08/30/2021 20:43:50 - INFO - __main__ - Step 41950: {'lr': 0.00041537174894807873, 'samples': 8054400, 'steps': 41949, 'loss/train': 1.608992338180542} 08/30/2021 20:43:50 - INFO - __main__ - Step 41951: {'lr': 0.00041536776908268847, 'samples': 8054592, 'steps': 41950, 'loss/train': 1.4331024885177612} 08/30/2021 20:43:51 - INFO - __main__ - Step 41952: {'lr': 0.00041536378914278603, 'samples': 8054784, 'steps': 41951, 'loss/train': 0.1175106018781662} 08/30/2021 20:43:51 - INFO - __main__ - Step 41953: {'lr': 0.00041535980912837326, 'samples': 8054976, 'steps': 41952, 'loss/train': 1.721665859222412} 08/30/2021 20:43:53 - INFO - __main__ - Step 41954: {'lr': 0.00041535582903945195, 'samples': 8055168, 'steps': 41953, 'loss/train': 0.03491394221782684} 08/30/2021 20:43:53 - INFO - __main__ - Step 41955: {'lr': 0.00041535184887602384, 'samples': 8055360, 'steps': 41954, 'loss/train': 0.6006178855895996} 08/30/2021 20:43:53 - INFO - __main__ - Step 41956: {'lr': 0.0004153478686380907, 'samples': 8055552, 'steps': 41955, 'loss/train': 2.0354340076446533} 08/30/2021 20:43:54 - INFO - __main__ - Step 41957: {'lr': 0.0004153438883256544, 'samples': 8055744, 'steps': 41956, 'loss/train': 1.9349210262298584} 08/30/2021 20:43:54 - INFO - __main__ - Step 41958: {'lr': 0.0004153399079387167, 'samples': 8055936, 'steps': 41957, 'loss/train': 1.0108331441879272} 08/30/2021 20:43:55 - INFO - __main__ - Step 41959: {'lr': 0.00041533592747727935, 'samples': 8056128, 'steps': 41958, 'loss/train': 1.2150534391403198} 08/30/2021 20:43:56 - INFO - __main__ - Step 41960: {'lr': 0.00041533194694134414, 'samples': 8056320, 'steps': 41959, 'loss/train': 1.5075238943099976} 08/30/2021 20:43:56 - INFO - __main__ - Step 41961: {'lr': 0.00041532796633091297, 'samples': 8056512, 'steps': 41960, 'loss/train': 1.1125930547714233} 08/30/2021 20:43:57 - INFO - __main__ - Step 41962: {'lr': 0.00041532398564598757, 'samples': 8056704, 'steps': 41961, 'loss/train': 1.5493428707122803} 08/30/2021 20:43:57 - INFO - __main__ - Step 41963: {'lr': 0.0004153200048865697, 'samples': 8056896, 'steps': 41962, 'loss/train': 1.2770804166793823} 08/30/2021 20:43:58 - INFO - __main__ - Step 41964: {'lr': 0.0004153160240526612, 'samples': 8057088, 'steps': 41963, 'loss/train': 1.2553688287734985} 08/30/2021 20:43:59 - INFO - __main__ - Step 41965: {'lr': 0.0004153120431442639, 'samples': 8057280, 'steps': 41964, 'loss/train': 1.5876924991607666} 08/30/2021 20:43:59 - INFO - __main__ - Step 41966: {'lr': 0.00041530806216137953, 'samples': 8057472, 'steps': 41965, 'loss/train': 1.6402713060379028} 08/30/2021 20:44:00 - INFO - __main__ - Step 41967: {'lr': 0.00041530408110400987, 'samples': 8057664, 'steps': 41966, 'loss/train': 1.7930269241333008} 08/30/2021 20:44:00 - INFO - __main__ - Step 41968: {'lr': 0.00041530009997215665, 'samples': 8057856, 'steps': 41967, 'loss/train': 1.823445200920105} 08/30/2021 20:44:02 - INFO - __main__ - Step 41969: {'lr': 0.00041529611876582194, 'samples': 8058048, 'steps': 41968, 'loss/train': 1.8255748748779297} 08/30/2021 20:44:02 - INFO - __main__ - Step 41970: {'lr': 0.00041529213748500726, 'samples': 8058240, 'steps': 41969, 'loss/train': 0.5113900303840637} 08/30/2021 20:44:02 - INFO - __main__ - Step 41971: {'lr': 0.0004152881561297145, 'samples': 8058432, 'steps': 41970, 'loss/train': 1.0384371280670166} 08/30/2021 20:44:03 - INFO - __main__ - Step 41972: {'lr': 0.0004152841746999454, 'samples': 8058624, 'steps': 41971, 'loss/train': 0.9688120484352112} 08/30/2021 20:44:03 - INFO - __main__ - Step 41973: {'lr': 0.00041528019319570186, 'samples': 8058816, 'steps': 41972, 'loss/train': 0.4540366530418396} 08/30/2021 20:44:03 - INFO - __main__ - Step 41974: {'lr': 0.0004152762116169856, 'samples': 8059008, 'steps': 41973, 'loss/train': 0.8219721913337708} 08/30/2021 20:44:05 - INFO - __main__ - Step 41975: {'lr': 0.00041527222996379844, 'samples': 8059200, 'steps': 41974, 'loss/train': 1.9123342037200928} 08/30/2021 20:44:05 - INFO - __main__ - Step 41976: {'lr': 0.0004152682482361422, 'samples': 8059392, 'steps': 41975, 'loss/train': 1.3277689218521118} 08/30/2021 20:44:06 - INFO - __main__ - Step 41977: {'lr': 0.0004152642664340185, 'samples': 8059584, 'steps': 41976, 'loss/train': 1.7774512767791748} 08/30/2021 20:44:06 - INFO - __main__ - Step 41978: {'lr': 0.00041526028455742936, 'samples': 8059776, 'steps': 41977, 'loss/train': 1.6565258502960205} 08/30/2021 20:44:06 - INFO - __main__ - Step 41979: {'lr': 0.0004152563026063765, 'samples': 8059968, 'steps': 41978, 'loss/train': 1.4913169145584106} 08/30/2021 20:44:08 - INFO - __main__ - Step 41980: {'lr': 0.00041525232058086173, 'samples': 8060160, 'steps': 41979, 'loss/train': 1.4618779420852661} 08/30/2021 20:44:08 - INFO - __main__ - Step 41981: {'lr': 0.0004152483384808867, 'samples': 8060352, 'steps': 41980, 'loss/train': 1.6179994344711304} 08/30/2021 20:44:08 - INFO - __main__ - Step 41982: {'lr': 0.0004152443563064534, 'samples': 8060544, 'steps': 41981, 'loss/train': 1.0159025192260742} 08/30/2021 20:44:09 - INFO - __main__ - Step 41983: {'lr': 0.00041524037405756356, 'samples': 8060736, 'steps': 41982, 'loss/train': 1.7705333232879639} 08/30/2021 20:44:09 - INFO - __main__ - Step 41984: {'lr': 0.0004152363917342189, 'samples': 8060928, 'steps': 41983, 'loss/train': 1.202101469039917} 08/30/2021 20:44:11 - INFO - __main__ - Step 41985: {'lr': 0.00041523240933642134, 'samples': 8061120, 'steps': 41984, 'loss/train': 1.7345613241195679} 08/30/2021 20:44:11 - INFO - __main__ - Step 41986: {'lr': 0.00041522842686417255, 'samples': 8061312, 'steps': 41985, 'loss/train': 1.6383717060089111} 08/30/2021 20:44:11 - INFO - __main__ - Step 41987: {'lr': 0.0004152244443174744, 'samples': 8061504, 'steps': 41986, 'loss/train': 0.06885938346385956} 08/30/2021 20:44:12 - INFO - __main__ - Step 41988: {'lr': 0.00041522046169632863, 'samples': 8061696, 'steps': 41987, 'loss/train': 1.3218573331832886} 08/30/2021 20:44:12 - INFO - __main__ - Step 41989: {'lr': 0.0004152164790007371, 'samples': 8061888, 'steps': 41988, 'loss/train': 1.261513352394104} 08/30/2021 20:44:14 - INFO - __main__ - Step 41990: {'lr': 0.00041521249623070164, 'samples': 8062080, 'steps': 41989, 'loss/train': 1.639464020729065} 08/30/2021 20:44:14 - INFO - __main__ - Step 41991: {'lr': 0.0004152085133862239, 'samples': 8062272, 'steps': 41990, 'loss/train': 1.3137935400009155} 08/30/2021 20:44:14 - INFO - __main__ - Step 41992: {'lr': 0.0004152045304673058, 'samples': 8062464, 'steps': 41991, 'loss/train': 1.3072303533554077} 08/30/2021 20:44:15 - INFO - __main__ - Step 41993: {'lr': 0.000415200547473949, 'samples': 8062656, 'steps': 41992, 'loss/train': 1.5884655714035034} 08/30/2021 20:44:15 - INFO - __main__ - Step 41994: {'lr': 0.00041519656440615544, 'samples': 8062848, 'steps': 41993, 'loss/train': 1.2554905414581299} 08/30/2021 20:44:17 - INFO - __main__ - Step 41995: {'lr': 0.00041519258126392685, 'samples': 8063040, 'steps': 41994, 'loss/train': 1.6075098514556885} 08/30/2021 20:44:17 - INFO - __main__ - Step 41996: {'lr': 0.00041518859804726507, 'samples': 8063232, 'steps': 41995, 'loss/train': 1.328611135482788} 08/30/2021 20:44:17 - INFO - __main__ - Step 41997: {'lr': 0.00041518461475617183, 'samples': 8063424, 'steps': 41996, 'loss/train': 1.576134204864502} 08/30/2021 20:44:18 - INFO - __main__ - Step 41998: {'lr': 0.00041518063139064893, 'samples': 8063616, 'steps': 41997, 'loss/train': 1.6799370050430298} 08/30/2021 20:44:18 - INFO - __main__ - Step 41999: {'lr': 0.0004151766479506982, 'samples': 8063808, 'steps': 41998, 'loss/train': 2.7042174339294434} 08/30/2021 20:44:20 - INFO - __main__ - Step 42000: {'lr': 0.0004151726644363214, 'samples': 8064000, 'steps': 41999, 'loss/train': 1.5599470138549805} 08/30/2021 20:44:21 - INFO - __main__ - Step 42001: {'lr': 0.00041516868084752034, 'samples': 8064192, 'steps': 42000, 'loss/train': 1.5925219058990479} 08/30/2021 20:44:21 - INFO - __main__ - Step 42002: {'lr': 0.0004151646971842968, 'samples': 8064384, 'steps': 42001, 'loss/train': 1.3629719018936157} 08/30/2021 20:44:21 - INFO - __main__ - Step 42003: {'lr': 0.00041516071344665275, 'samples': 8064576, 'steps': 42002, 'loss/train': 1.7206238508224487} 08/30/2021 20:44:22 - INFO - __main__ - Step 42004: {'lr': 0.00041515672963458975, 'samples': 8064768, 'steps': 42003, 'loss/train': 1.1813071966171265} 08/30/2021 20:44:22 - INFO - __main__ - Step 42005: {'lr': 0.00041515274574810965, 'samples': 8064960, 'steps': 42004, 'loss/train': 1.6746045351028442} 08/30/2021 20:44:24 - INFO - __main__ - Step 42006: {'lr': 0.00041514876178721426, 'samples': 8065152, 'steps': 42005, 'loss/train': 2.2018063068389893} 08/30/2021 20:44:25 - INFO - __main__ - Step 42007: {'lr': 0.0004151447777519054, 'samples': 8065344, 'steps': 42006, 'loss/train': 1.6507172584533691} 08/30/2021 20:44:25 - INFO - __main__ - Step 42008: {'lr': 0.00041514079364218483, 'samples': 8065536, 'steps': 42007, 'loss/train': 1.3309930562973022} 08/30/2021 20:44:25 - INFO - __main__ - Step 42009: {'lr': 0.0004151368094580544, 'samples': 8065728, 'steps': 42008, 'loss/train': 1.4450976848602295} 08/30/2021 20:44:26 - INFO - __main__ - Step 42010: {'lr': 0.0004151328251995159, 'samples': 8065920, 'steps': 42009, 'loss/train': 1.633277177810669} 08/30/2021 20:44:26 - INFO - __main__ - Step 42011: {'lr': 0.000415128840866571, 'samples': 8066112, 'steps': 42010, 'loss/train': 1.006747841835022} 08/30/2021 20:44:27 - INFO - __main__ - Step 42012: {'lr': 0.00041512485645922164, 'samples': 8066304, 'steps': 42011, 'loss/train': 0.03204198554158211} 08/30/2021 20:44:28 - INFO - __main__ - Step 42013: {'lr': 0.0004151208719774696, 'samples': 8066496, 'steps': 42012, 'loss/train': 0.5145212411880493} 08/30/2021 20:44:28 - INFO - __main__ - Step 42014: {'lr': 0.0004151168874213166, 'samples': 8066688, 'steps': 42013, 'loss/train': 0.7954835891723633} 08/30/2021 20:44:29 - INFO - __main__ - Step 42015: {'lr': 0.00041511290279076454, 'samples': 8066880, 'steps': 42014, 'loss/train': 1.919533371925354} 08/30/2021 20:44:29 - INFO - __main__ - Step 42016: {'lr': 0.0004151089180858151, 'samples': 8067072, 'steps': 42015, 'loss/train': 1.7257556915283203} 08/30/2021 20:44:31 - INFO - __main__ - Step 42017: {'lr': 0.00041510493330647015, 'samples': 8067264, 'steps': 42016, 'loss/train': 0.636605441570282} 08/30/2021 20:44:31 - INFO - __main__ - Step 42018: {'lr': 0.00041510094845273145, 'samples': 8067456, 'steps': 42017, 'loss/train': 0.7040926814079285} 08/30/2021 20:44:32 - INFO - __main__ - Step 42019: {'lr': 0.0004150969635246008, 'samples': 8067648, 'steps': 42018, 'loss/train': 1.7151103019714355} 08/30/2021 20:44:32 - INFO - __main__ - Step 42020: {'lr': 0.00041509297852208003, 'samples': 8067840, 'steps': 42019, 'loss/train': 1.4303449392318726} 08/30/2021 20:44:32 - INFO - __main__ - Step 42021: {'lr': 0.00041508899344517094, 'samples': 8068032, 'steps': 42020, 'loss/train': 1.4094502925872803} 08/30/2021 20:44:34 - INFO - __main__ - Step 42022: {'lr': 0.0004150850082938752, 'samples': 8068224, 'steps': 42021, 'loss/train': 1.4454941749572754} 08/30/2021 20:44:34 - INFO - __main__ - Step 42023: {'lr': 0.00041508102306819485, 'samples': 8068416, 'steps': 42022, 'loss/train': 1.2959115505218506} 08/30/2021 20:44:35 - INFO - __main__ - Step 42024: {'lr': 0.0004150770377681314, 'samples': 8068608, 'steps': 42023, 'loss/train': 1.805885672569275} 08/30/2021 20:44:35 - INFO - __main__ - Step 42025: {'lr': 0.00041507305239368684, 'samples': 8068800, 'steps': 42024, 'loss/train': 1.2741270065307617} 08/30/2021 20:44:35 - INFO - __main__ - Step 42026: {'lr': 0.0004150690669448629, 'samples': 8068992, 'steps': 42025, 'loss/train': 0.33695948123931885} 08/30/2021 20:44:37 - INFO - __main__ - Step 42027: {'lr': 0.0004150650814216614, 'samples': 8069184, 'steps': 42026, 'loss/train': 1.5946998596191406} 08/30/2021 20:44:37 - INFO - __main__ - Step 42028: {'lr': 0.0004150610958240841, 'samples': 8069376, 'steps': 42027, 'loss/train': 2.5631399154663086} 08/30/2021 20:44:38 - INFO - __main__ - Step 42029: {'lr': 0.00041505711015213284, 'samples': 8069568, 'steps': 42028, 'loss/train': 1.6531378030776978} 08/30/2021 20:44:38 - INFO - __main__ - Step 42030: {'lr': 0.0004150531244058094, 'samples': 8069760, 'steps': 42029, 'loss/train': 1.429823637008667} 08/30/2021 20:44:38 - INFO - __main__ - Step 42031: {'lr': 0.00041504913858511557, 'samples': 8069952, 'steps': 42030, 'loss/train': 0.6526381373405457} 08/30/2021 20:44:40 - INFO - __main__ - Step 42032: {'lr': 0.0004150451526900531, 'samples': 8070144, 'steps': 42031, 'loss/train': 1.5835820436477661} 08/30/2021 20:44:40 - INFO - __main__ - Step 42033: {'lr': 0.00041504116672062385, 'samples': 8070336, 'steps': 42032, 'loss/train': 1.0987393856048584} 08/30/2021 20:44:41 - INFO - __main__ - Step 42034: {'lr': 0.0004150371806768296, 'samples': 8070528, 'steps': 42033, 'loss/train': 1.2248111963272095} 08/30/2021 20:44:41 - INFO - __main__ - Step 42035: {'lr': 0.00041503319455867216, 'samples': 8070720, 'steps': 42034, 'loss/train': 1.1465586423873901} 08/30/2021 20:44:41 - INFO - __main__ - Step 42036: {'lr': 0.0004150292083661533, 'samples': 8070912, 'steps': 42035, 'loss/train': 1.0095746517181396} 08/30/2021 20:44:42 - INFO - __main__ - Step 42037: {'lr': 0.00041502522209927486, 'samples': 8071104, 'steps': 42036, 'loss/train': 1.3447126150131226} 08/30/2021 20:44:43 - INFO - __main__ - Step 42038: {'lr': 0.00041502123575803854, 'samples': 8071296, 'steps': 42037, 'loss/train': 2.114588499069214} 08/30/2021 20:44:44 - INFO - __main__ - Step 42039: {'lr': 0.0004150172493424462, 'samples': 8071488, 'steps': 42038, 'loss/train': 1.4473960399627686} 08/30/2021 20:44:44 - INFO - __main__ - Step 42040: {'lr': 0.00041501326285249963, 'samples': 8071680, 'steps': 42039, 'loss/train': 1.7579057216644287} 08/30/2021 20:44:44 - INFO - __main__ - Step 42041: {'lr': 0.0004150092762882007, 'samples': 8071872, 'steps': 42040, 'loss/train': 1.3453913927078247} 08/30/2021 20:44:45 - INFO - __main__ - Step 42042: {'lr': 0.00041500528964955106, 'samples': 8072064, 'steps': 42041, 'loss/train': 1.215481162071228} 08/30/2021 20:44:46 - INFO - __main__ - Step 42043: {'lr': 0.0004150013029365527, 'samples': 8072256, 'steps': 42042, 'loss/train': 1.2389215230941772} 08/30/2021 20:44:47 - INFO - __main__ - Step 42044: {'lr': 0.0004149973161492072, 'samples': 8072448, 'steps': 42043, 'loss/train': 1.378302812576294} 08/30/2021 20:44:47 - INFO - __main__ - Step 42045: {'lr': 0.0004149933292875164, 'samples': 8072640, 'steps': 42044, 'loss/train': 1.7734328508377075} 08/30/2021 20:44:47 - INFO - __main__ - Step 42046: {'lr': 0.0004149893423514822, 'samples': 8072832, 'steps': 42045, 'loss/train': 1.802382230758667} 08/30/2021 20:44:48 - INFO - __main__ - Step 42047: {'lr': 0.0004149853553411064, 'samples': 8073024, 'steps': 42046, 'loss/train': 1.4193822145462036} 08/30/2021 20:44:49 - INFO - __main__ - Step 42048: {'lr': 0.00041498136825639074, 'samples': 8073216, 'steps': 42047, 'loss/train': 1.117325782775879} 08/30/2021 20:44:50 - INFO - __main__ - Step 42049: {'lr': 0.000414977381097337, 'samples': 8073408, 'steps': 42048, 'loss/train': 1.589279055595398} 08/30/2021 20:44:50 - INFO - __main__ - Step 42050: {'lr': 0.000414973393863947, 'samples': 8073600, 'steps': 42049, 'loss/train': 1.5615315437316895} 08/30/2021 20:44:50 - INFO - __main__ - Step 42051: {'lr': 0.0004149694065562225, 'samples': 8073792, 'steps': 42050, 'loss/train': 0.7782192826271057} 08/30/2021 20:44:51 - INFO - __main__ - Step 42052: {'lr': 0.0004149654191741654, 'samples': 8073984, 'steps': 42051, 'loss/train': 1.3162301778793335} 08/30/2021 20:44:52 - INFO - __main__ - Step 42053: {'lr': 0.0004149614317177774, 'samples': 8074176, 'steps': 42052, 'loss/train': 1.6516133546829224} 08/30/2021 20:44:53 - INFO - __main__ - Step 42054: {'lr': 0.00041495744418706027, 'samples': 8074368, 'steps': 42053, 'loss/train': 1.6669666767120361} 08/30/2021 20:44:53 - INFO - __main__ - Step 42055: {'lr': 0.00041495345658201587, 'samples': 8074560, 'steps': 42054, 'loss/train': 1.176653265953064} 08/30/2021 20:44:53 - INFO - __main__ - Step 42056: {'lr': 0.00041494946890264606, 'samples': 8074752, 'steps': 42055, 'loss/train': 0.6083608865737915} 08/30/2021 20:44:54 - INFO - __main__ - Step 42057: {'lr': 0.00041494548114895255, 'samples': 8074944, 'steps': 42056, 'loss/train': 1.3563673496246338} 08/30/2021 20:44:56 - INFO - __main__ - Step 42058: {'lr': 0.0004149414933209371, 'samples': 8075136, 'steps': 42057, 'loss/train': 1.8304144144058228} 08/30/2021 20:44:56 - INFO - __main__ - Step 42059: {'lr': 0.00041493750541860165, 'samples': 8075328, 'steps': 42058, 'loss/train': 1.4650368690490723} 08/30/2021 20:44:56 - INFO - __main__ - Step 42060: {'lr': 0.0004149335174419478, 'samples': 8075520, 'steps': 42059, 'loss/train': 1.3190314769744873} 08/30/2021 20:44:57 - INFO - __main__ - Step 42061: {'lr': 0.0004149295293909775, 'samples': 8075712, 'steps': 42060, 'loss/train': 1.6788418292999268} 08/30/2021 20:44:57 - INFO - __main__ - Step 42062: {'lr': 0.0004149255412656925, 'samples': 8075904, 'steps': 42061, 'loss/train': 1.3540338277816772} 08/30/2021 20:44:59 - INFO - __main__ - Step 42063: {'lr': 0.00041492155306609456, 'samples': 8076096, 'steps': 42062, 'loss/train': 0.8162250518798828} 08/30/2021 20:45:00 - INFO - __main__ - Step 42064: {'lr': 0.00041491756479218557, 'samples': 8076288, 'steps': 42063, 'loss/train': 1.209893822669983} 08/30/2021 20:45:00 - INFO - __main__ - Step 42065: {'lr': 0.0004149135764439672, 'samples': 8076480, 'steps': 42064, 'loss/train': 1.308935284614563} 08/30/2021 20:45:00 - INFO - __main__ - Step 42066: {'lr': 0.0004149095880214414, 'samples': 8076672, 'steps': 42065, 'loss/train': 1.46317458152771} 08/30/2021 20:45:01 - INFO - __main__ - Step 42067: {'lr': 0.00041490559952460983, 'samples': 8076864, 'steps': 42066, 'loss/train': 1.1638134717941284} 08/30/2021 20:45:01 - INFO - __main__ - Step 42068: {'lr': 0.00041490161095347435, 'samples': 8077056, 'steps': 42067, 'loss/train': 0.02409498579800129} 08/30/2021 20:45:02 - INFO - __main__ - Step 42069: {'lr': 0.00041489762230803676, 'samples': 8077248, 'steps': 42068, 'loss/train': 1.397840976715088} 08/30/2021 20:45:03 - INFO - __main__ - Step 42070: {'lr': 0.00041489363358829885, 'samples': 8077440, 'steps': 42069, 'loss/train': 1.2321537733078003} 08/30/2021 20:45:03 - INFO - __main__ - Step 42071: {'lr': 0.0004148896447942624, 'samples': 8077632, 'steps': 42070, 'loss/train': 1.6488279104232788} 08/30/2021 20:45:04 - INFO - __main__ - Step 42072: {'lr': 0.00041488565592592917, 'samples': 8077824, 'steps': 42071, 'loss/train': 1.214510202407837} 08/30/2021 20:45:04 - INFO - __main__ - Step 42073: {'lr': 0.0004148816669833011, 'samples': 8078016, 'steps': 42072, 'loss/train': 1.2845994234085083} 08/30/2021 20:45:05 - INFO - __main__ - Step 42074: {'lr': 0.0004148776779663799, 'samples': 8078208, 'steps': 42073, 'loss/train': 1.5515477657318115} 08/30/2021 20:45:06 - INFO - __main__ - Step 42075: {'lr': 0.00041487368887516726, 'samples': 8078400, 'steps': 42074, 'loss/train': 1.2906405925750732} 08/30/2021 20:45:06 - INFO - __main__ - Step 42076: {'lr': 0.00041486969970966516, 'samples': 8078592, 'steps': 42075, 'loss/train': 0.5965171456336975} 08/30/2021 20:45:07 - INFO - __main__ - Step 42077: {'lr': 0.0004148657104698753, 'samples': 8078784, 'steps': 42076, 'loss/train': 1.554368495941162} 08/30/2021 20:45:07 - INFO - __main__ - Step 42078: {'lr': 0.00041486172115579945, 'samples': 8078976, 'steps': 42077, 'loss/train': 1.259277105331421} 08/30/2021 20:45:09 - INFO - __main__ - Step 42079: {'lr': 0.00041485773176743953, 'samples': 8079168, 'steps': 42078, 'loss/train': 1.202600359916687} 08/30/2021 20:45:09 - INFO - __main__ - Step 42080: {'lr': 0.00041485374230479724, 'samples': 8079360, 'steps': 42079, 'loss/train': 1.328616738319397} 08/30/2021 20:45:09 - INFO - __main__ - Step 42081: {'lr': 0.00041484975276787436, 'samples': 8079552, 'steps': 42080, 'loss/train': 0.7397907972335815} 08/30/2021 20:45:10 - INFO - __main__ - Step 42082: {'lr': 0.00041484576315667273, 'samples': 8079744, 'steps': 42081, 'loss/train': 0.28067469596862793} 08/30/2021 20:45:10 - INFO - __main__ - Step 42083: {'lr': 0.0004148417734711941, 'samples': 8079936, 'steps': 42082, 'loss/train': 1.526578664779663} 08/30/2021 20:45:12 - INFO - __main__ - Step 42084: {'lr': 0.00041483778371144046, 'samples': 8080128, 'steps': 42083, 'loss/train': 1.2580015659332275} 08/30/2021 20:45:12 - INFO - __main__ - Step 42085: {'lr': 0.0004148337938774134, 'samples': 8080320, 'steps': 42084, 'loss/train': 1.0709748268127441} 08/30/2021 20:45:13 - INFO - __main__ - Step 42086: {'lr': 0.00041482980396911467, 'samples': 8080512, 'steps': 42085, 'loss/train': 1.2933945655822754} 08/30/2021 20:45:13 - INFO - __main__ - Step 42087: {'lr': 0.0004148258139865463, 'samples': 8080704, 'steps': 42086, 'loss/train': 0.09568388015031815} 08/30/2021 20:45:13 - INFO - __main__ - Step 42088: {'lr': 0.00041482182392970984, 'samples': 8080896, 'steps': 42087, 'loss/train': 1.2936928272247314} 08/30/2021 20:45:15 - INFO - __main__ - Step 42089: {'lr': 0.00041481783379860725, 'samples': 8081088, 'steps': 42088, 'loss/train': 1.108892798423767} 08/30/2021 20:45:15 - INFO - __main__ - Step 42090: {'lr': 0.0004148138435932404, 'samples': 8081280, 'steps': 42089, 'loss/train': 0.617364227771759} 08/30/2021 20:45:16 - INFO - __main__ - Step 42091: {'lr': 0.0004148098533136109, 'samples': 8081472, 'steps': 42090, 'loss/train': 0.0499710887670517} 08/30/2021 20:45:16 - INFO - __main__ - Step 42092: {'lr': 0.0004148058629597206, 'samples': 8081664, 'steps': 42091, 'loss/train': 1.4710822105407715} 08/30/2021 20:45:16 - INFO - __main__ - Step 42093: {'lr': 0.0004148018725315713, 'samples': 8081856, 'steps': 42092, 'loss/train': 1.3668607473373413} 08/30/2021 20:45:18 - INFO - __main__ - Step 42094: {'lr': 0.00041479788202916483, 'samples': 8082048, 'steps': 42093, 'loss/train': 1.7293243408203125} 08/30/2021 20:45:18 - INFO - __main__ - Step 42095: {'lr': 0.000414793891452503, 'samples': 8082240, 'steps': 42094, 'loss/train': 1.3674372434616089} 08/30/2021 20:45:19 - INFO - __main__ - Step 42096: {'lr': 0.0004147899008015876, 'samples': 8082432, 'steps': 42095, 'loss/train': 1.4402815103530884} 08/30/2021 20:45:19 - INFO - __main__ - Step 42097: {'lr': 0.0004147859100764204, 'samples': 8082624, 'steps': 42096, 'loss/train': 1.3156471252441406} 08/30/2021 20:45:19 - INFO - __main__ - Step 42098: {'lr': 0.0004147819192770033, 'samples': 8082816, 'steps': 42097, 'loss/train': 1.2385623455047607} 08/30/2021 20:45:20 - INFO - __main__ - Step 42099: {'lr': 0.00041477792840333784, 'samples': 8083008, 'steps': 42098, 'loss/train': 1.3595072031021118} 08/30/2021 20:45:21 - INFO - __main__ - Step 42100: {'lr': 0.00041477393745542607, 'samples': 8083200, 'steps': 42099, 'loss/train': 1.516279697418213} 08/30/2021 20:45:21 - INFO - __main__ - Step 42101: {'lr': 0.0004147699464332697, 'samples': 8083392, 'steps': 42100, 'loss/train': 0.9354690909385681} 08/30/2021 20:45:22 - INFO - __main__ - Step 42102: {'lr': 0.0004147659553368706, 'samples': 8083584, 'steps': 42101, 'loss/train': 1.1088016033172607} 08/30/2021 20:45:22 - INFO - __main__ - Step 42103: {'lr': 0.00041476196416623034, 'samples': 8083776, 'steps': 42102, 'loss/train': 1.4322679042816162} 08/30/2021 20:45:23 - INFO - __main__ - Step 42104: {'lr': 0.0004147579729213511, 'samples': 8083968, 'steps': 42103, 'loss/train': 1.6741018295288086} 08/30/2021 20:45:24 - INFO - __main__ - Step 42105: {'lr': 0.0004147539816022343, 'samples': 8084160, 'steps': 42104, 'loss/train': 1.603182315826416} 08/30/2021 20:45:24 - INFO - __main__ - Step 42106: {'lr': 0.0004147499902088819, 'samples': 8084352, 'steps': 42105, 'loss/train': 0.5111899971961975} 08/30/2021 20:45:25 - INFO - __main__ - Step 42107: {'lr': 0.0004147459987412958, 'samples': 8084544, 'steps': 42106, 'loss/train': 1.6472759246826172} 08/30/2021 20:45:25 - INFO - __main__ - Step 42108: {'lr': 0.0004147420071994776, 'samples': 8084736, 'steps': 42107, 'loss/train': 1.324957251548767} 08/30/2021 20:45:25 - INFO - __main__ - Step 42109: {'lr': 0.0004147380155834293, 'samples': 8084928, 'steps': 42108, 'loss/train': 1.5634123086929321} 08/30/2021 20:45:28 - INFO - __main__ - Step 42110: {'lr': 0.0004147340238931525, 'samples': 8085120, 'steps': 42109, 'loss/train': 1.2766777276992798} 08/30/2021 20:45:28 - INFO - __main__ - Step 42111: {'lr': 0.0004147300321286491, 'samples': 8085312, 'steps': 42110, 'loss/train': 1.0279078483581543} 08/30/2021 20:45:29 - INFO - __main__ - Step 42112: {'lr': 0.0004147260402899209, 'samples': 8085504, 'steps': 42111, 'loss/train': 1.8470271825790405} 08/30/2021 20:45:29 - INFO - __main__ - Step 42113: {'lr': 0.0004147220483769697, 'samples': 8085696, 'steps': 42112, 'loss/train': 1.6055042743682861} 08/30/2021 20:45:29 - INFO - __main__ - Step 42114: {'lr': 0.0004147180563897972, 'samples': 8085888, 'steps': 42113, 'loss/train': 0.9499245882034302} 08/30/2021 20:45:31 - INFO - __main__ - Step 42115: {'lr': 0.0004147140643284054, 'samples': 8086080, 'steps': 42114, 'loss/train': 1.522879719734192} 08/30/2021 20:45:31 - INFO - __main__ - Step 42116: {'lr': 0.00041471007219279595, 'samples': 8086272, 'steps': 42115, 'loss/train': 1.5455400943756104} 08/30/2021 20:45:32 - INFO - __main__ - Step 42117: {'lr': 0.0004147060799829707, 'samples': 8086464, 'steps': 42116, 'loss/train': 1.317301869392395} 08/30/2021 20:45:32 - INFO - __main__ - Step 42118: {'lr': 0.00041470208769893137, 'samples': 8086656, 'steps': 42117, 'loss/train': 0.8650458455085754} 08/30/2021 20:45:32 - INFO - __main__ - Step 42119: {'lr': 0.0004146980953406799, 'samples': 8086848, 'steps': 42118, 'loss/train': 1.4716070890426636} 08/30/2021 20:45:34 - INFO - __main__ - Step 42120: {'lr': 0.000414694102908218, 'samples': 8087040, 'steps': 42119, 'loss/train': 1.7921462059020996} 08/30/2021 20:45:34 - INFO - __main__ - Step 42121: {'lr': 0.0004146901104015474, 'samples': 8087232, 'steps': 42120, 'loss/train': 1.6152158975601196} 08/30/2021 20:45:34 - INFO - __main__ - Step 42122: {'lr': 0.00041468611782067, 'samples': 8087424, 'steps': 42121, 'loss/train': 1.0863064527511597} 08/30/2021 20:45:35 - INFO - __main__ - Step 42123: {'lr': 0.0004146821251655877, 'samples': 8087616, 'steps': 42122, 'loss/train': 1.3849724531173706} 08/30/2021 20:45:35 - INFO - __main__ - Step 42124: {'lr': 0.000414678132436302, 'samples': 8087808, 'steps': 42123, 'loss/train': 1.5474445819854736} 08/30/2021 20:45:37 - INFO - __main__ - Step 42125: {'lr': 0.000414674139632815, 'samples': 8088000, 'steps': 42124, 'loss/train': 1.581607699394226} 08/30/2021 20:45:37 - INFO - __main__ - Step 42126: {'lr': 0.0004146701467551283, 'samples': 8088192, 'steps': 42125, 'loss/train': 1.3367286920547485} 08/30/2021 20:45:38 - INFO - __main__ - Step 42127: {'lr': 0.0004146661538032438, 'samples': 8088384, 'steps': 42126, 'loss/train': 1.5993620157241821} 08/30/2021 20:45:38 - INFO - __main__ - Step 42128: {'lr': 0.0004146621607771633, 'samples': 8088576, 'steps': 42127, 'loss/train': 1.5183007717132568} 08/30/2021 20:45:38 - INFO - __main__ - Step 42129: {'lr': 0.00041465816767688853, 'samples': 8088768, 'steps': 42128, 'loss/train': 0.9067882299423218} 08/30/2021 20:45:39 - INFO - __main__ - Step 42130: {'lr': 0.0004146541745024214, 'samples': 8088960, 'steps': 42129, 'loss/train': 1.7860867977142334} 08/30/2021 20:45:40 - INFO - __main__ - Step 42131: {'lr': 0.00041465018125376354, 'samples': 8089152, 'steps': 42130, 'loss/train': 1.2774993181228638} 08/30/2021 20:45:40 - INFO - __main__ - Step 42132: {'lr': 0.0004146461879309169, 'samples': 8089344, 'steps': 42131, 'loss/train': 1.5761557817459106} 08/30/2021 20:45:41 - INFO - __main__ - Step 42133: {'lr': 0.0004146421945338832, 'samples': 8089536, 'steps': 42132, 'loss/train': 0.6396993398666382} 08/30/2021 20:45:41 - INFO - __main__ - Step 42134: {'lr': 0.0004146382010626643, 'samples': 8089728, 'steps': 42133, 'loss/train': 1.1455062627792358} 08/30/2021 20:45:42 - INFO - __main__ - Step 42135: {'lr': 0.000414634207517262, 'samples': 8089920, 'steps': 42134, 'loss/train': 1.4439822435379028} 08/30/2021 20:45:43 - INFO - __main__ - Step 42136: {'lr': 0.000414630213897678, 'samples': 8090112, 'steps': 42135, 'loss/train': 1.022885799407959} 08/30/2021 20:45:44 - INFO - __main__ - Step 42137: {'lr': 0.00041462622020391416, 'samples': 8090304, 'steps': 42136, 'loss/train': 1.18490469455719} 08/30/2021 20:45:44 - INFO - __main__ - Step 42138: {'lr': 0.00041462222643597236, 'samples': 8090496, 'steps': 42137, 'loss/train': 1.3145403861999512} 08/30/2021 20:45:44 - INFO - __main__ - Step 42139: {'lr': 0.00041461823259385423, 'samples': 8090688, 'steps': 42138, 'loss/train': 1.1623032093048096} 08/30/2021 20:45:45 - INFO - __main__ - Step 42140: {'lr': 0.00041461423867756176, 'samples': 8090880, 'steps': 42139, 'loss/train': 0.8623557090759277} 08/30/2021 20:45:46 - INFO - __main__ - Step 42141: {'lr': 0.00041461024468709664, 'samples': 8091072, 'steps': 42140, 'loss/train': 1.5169148445129395} 08/30/2021 20:45:47 - INFO - __main__ - Step 42142: {'lr': 0.0004146062506224606, 'samples': 8091264, 'steps': 42141, 'loss/train': 1.6592957973480225} 08/30/2021 20:45:47 - INFO - __main__ - Step 42143: {'lr': 0.0004146022564836556, 'samples': 8091456, 'steps': 42142, 'loss/train': 1.1839269399642944} 08/30/2021 20:45:47 - INFO - __main__ - Step 42144: {'lr': 0.0004145982622706833, 'samples': 8091648, 'steps': 42143, 'loss/train': 1.323874831199646} 08/30/2021 20:45:48 - INFO - __main__ - Step 42145: {'lr': 0.00041459426798354563, 'samples': 8091840, 'steps': 42144, 'loss/train': 1.4421354532241821} 08/30/2021 20:45:49 - INFO - __main__ - Step 42146: {'lr': 0.00041459027362224433, 'samples': 8092032, 'steps': 42145, 'loss/train': 1.411238670349121} 08/30/2021 20:45:50 - INFO - __main__ - Step 42147: {'lr': 0.00041458627918678116, 'samples': 8092224, 'steps': 42146, 'loss/train': 0.050818443298339844} 08/30/2021 20:45:50 - INFO - __main__ - Step 42148: {'lr': 0.00041458228467715786, 'samples': 8092416, 'steps': 42147, 'loss/train': 0.9675813913345337} 08/30/2021 20:45:50 - INFO - __main__ - Step 42149: {'lr': 0.00041457829009337643, 'samples': 8092608, 'steps': 42148, 'loss/train': 1.189178466796875} 08/30/2021 20:45:51 - INFO - __main__ - Step 42150: {'lr': 0.00041457429543543856, 'samples': 8092800, 'steps': 42149, 'loss/train': 1.7160683870315552} 08/30/2021 20:45:52 - INFO - __main__ - Step 42151: {'lr': 0.0004145703007033461, 'samples': 8092992, 'steps': 42150, 'loss/train': 1.4187594652175903} 08/30/2021 20:45:53 - INFO - __main__ - Step 42152: {'lr': 0.00041456630589710073, 'samples': 8093184, 'steps': 42151, 'loss/train': 1.5434417724609375} 08/30/2021 20:45:53 - INFO - __main__ - Step 42153: {'lr': 0.0004145623110167043, 'samples': 8093376, 'steps': 42152, 'loss/train': 0.7602411508560181} 08/30/2021 20:45:53 - INFO - __main__ - Step 42154: {'lr': 0.00041455831606215863, 'samples': 8093568, 'steps': 42153, 'loss/train': 1.4812666177749634} 08/30/2021 20:45:54 - INFO - __main__ - Step 42155: {'lr': 0.0004145543210334656, 'samples': 8093760, 'steps': 42154, 'loss/train': 1.4547737836837769} 08/30/2021 20:45:54 - INFO - __main__ - Step 42156: {'lr': 0.00041455032593062685, 'samples': 8093952, 'steps': 42155, 'loss/train': 2.3969500064849854} 08/30/2021 20:45:56 - INFO - __main__ - Step 42157: {'lr': 0.00041454633075364427, 'samples': 8094144, 'steps': 42156, 'loss/train': 0.7574585676193237} 08/30/2021 20:45:56 - INFO - __main__ - Step 42158: {'lr': 0.00041454233550251976, 'samples': 8094336, 'steps': 42157, 'loss/train': 1.8785595893859863} 08/30/2021 20:45:56 - INFO - __main__ - Step 42159: {'lr': 0.0004145383401772549, 'samples': 8094528, 'steps': 42158, 'loss/train': 1.3645179271697998} 08/30/2021 20:45:57 - INFO - __main__ - Step 42160: {'lr': 0.00041453434477785165, 'samples': 8094720, 'steps': 42159, 'loss/train': 1.180868148803711} 08/30/2021 20:45:57 - INFO - __main__ - Step 42161: {'lr': 0.0004145303493043118, 'samples': 8094912, 'steps': 42160, 'loss/train': 0.8418003916740417} 08/30/2021 20:45:59 - INFO - __main__ - Step 42162: {'lr': 0.000414526353756637, 'samples': 8095104, 'steps': 42161, 'loss/train': 2.004115581512451} 08/30/2021 20:45:59 - INFO - __main__ - Step 42163: {'lr': 0.0004145223581348292, 'samples': 8095296, 'steps': 42162, 'loss/train': 1.0504868030548096} 08/30/2021 20:45:59 - INFO - __main__ - Step 42164: {'lr': 0.00041451836243889027, 'samples': 8095488, 'steps': 42163, 'loss/train': 1.025084137916565} 08/30/2021 20:46:00 - INFO - __main__ - Step 42165: {'lr': 0.0004145143666688218, 'samples': 8095680, 'steps': 42164, 'loss/train': 0.9310389161109924} 08/30/2021 20:46:00 - INFO - __main__ - Step 42166: {'lr': 0.0004145103708246257, 'samples': 8095872, 'steps': 42165, 'loss/train': 1.0532963275909424} 08/30/2021 20:46:02 - INFO - __main__ - Step 42167: {'lr': 0.0004145063749063038, 'samples': 8096064, 'steps': 42166, 'loss/train': 1.9102671146392822} 08/30/2021 20:46:02 - INFO - __main__ - Step 42168: {'lr': 0.00041450237891385783, 'samples': 8096256, 'steps': 42167, 'loss/train': 1.6247804164886475} 08/30/2021 20:46:03 - INFO - __main__ - Step 42169: {'lr': 0.00041449838284728964, 'samples': 8096448, 'steps': 42168, 'loss/train': 1.7039918899536133} 08/30/2021 20:46:03 - INFO - __main__ - Step 42170: {'lr': 0.000414494386706601, 'samples': 8096640, 'steps': 42169, 'loss/train': 1.6172739267349243} 08/30/2021 20:46:03 - INFO - __main__ - Step 42171: {'lr': 0.00041449039049179385, 'samples': 8096832, 'steps': 42170, 'loss/train': 1.4287976026535034} 08/30/2021 20:46:05 - INFO - __main__ - Step 42172: {'lr': 0.0004144863942028697, 'samples': 8097024, 'steps': 42171, 'loss/train': 1.3822600841522217} 08/30/2021 20:46:06 - INFO - __main__ - Step 42173: {'lr': 0.0004144823978398306, 'samples': 8097216, 'steps': 42172, 'loss/train': 1.5369291305541992} 08/30/2021 20:46:06 - INFO - __main__ - Step 42174: {'lr': 0.0004144784014026782, 'samples': 8097408, 'steps': 42173, 'loss/train': 1.4141660928726196} 08/30/2021 20:46:06 - INFO - __main__ - Step 42175: {'lr': 0.0004144744048914145, 'samples': 8097600, 'steps': 42174, 'loss/train': 1.4566032886505127} 08/30/2021 20:46:07 - INFO - __main__ - Step 42176: {'lr': 0.0004144704083060411, 'samples': 8097792, 'steps': 42175, 'loss/train': 1.6292386054992676} 08/30/2021 20:46:08 - INFO - __main__ - Step 42177: {'lr': 0.00041446641164655983, 'samples': 8097984, 'steps': 42176, 'loss/train': 1.6132475137710571} 08/30/2021 20:46:08 - INFO - __main__ - Step 42178: {'lr': 0.0004144624149129727, 'samples': 8098176, 'steps': 42177, 'loss/train': 1.4272546768188477} 08/30/2021 20:46:09 - INFO - __main__ - Step 42179: {'lr': 0.00041445841810528117, 'samples': 8098368, 'steps': 42178, 'loss/train': 1.5255573987960815} 08/30/2021 20:46:09 - INFO - __main__ - Step 42180: {'lr': 0.00041445442122348727, 'samples': 8098560, 'steps': 42179, 'loss/train': 1.7269580364227295} 08/30/2021 20:46:10 - INFO - __main__ - Step 42181: {'lr': 0.0004144504242675927, 'samples': 8098752, 'steps': 42180, 'loss/train': 1.402187705039978} 08/30/2021 20:46:11 - INFO - __main__ - Step 42182: {'lr': 0.0004144464272375994, 'samples': 8098944, 'steps': 42181, 'loss/train': 1.038556694984436} 08/30/2021 20:46:12 - INFO - __main__ - Step 42183: {'lr': 0.000414442430133509, 'samples': 8099136, 'steps': 42182, 'loss/train': 1.7038600444793701} 08/30/2021 20:46:12 - INFO - __main__ - Step 42184: {'lr': 0.00041443843295532333, 'samples': 8099328, 'steps': 42183, 'loss/train': 1.1766091585159302} 08/30/2021 20:46:12 - INFO - __main__ - Step 42185: {'lr': 0.0004144344357030444, 'samples': 8099520, 'steps': 42184, 'loss/train': 0.7377972602844238} 08/30/2021 20:46:13 - INFO - __main__ - Step 42186: {'lr': 0.0004144304383766737, 'samples': 8099712, 'steps': 42185, 'loss/train': 1.0757642984390259} 08/30/2021 20:46:13 - INFO - __main__ - Step 42187: {'lr': 0.0004144264409762133, 'samples': 8099904, 'steps': 42186, 'loss/train': 1.3502475023269653} 08/30/2021 20:46:14 - INFO - __main__ - Step 42188: {'lr': 0.0004144224435016648, 'samples': 8100096, 'steps': 42187, 'loss/train': 2.035529613494873} 08/30/2021 20:46:15 - INFO - __main__ - Step 42189: {'lr': 0.00041441844595303015, 'samples': 8100288, 'steps': 42188, 'loss/train': 1.5047987699508667} 08/30/2021 20:46:15 - INFO - __main__ - Step 42190: {'lr': 0.0004144144483303111, 'samples': 8100480, 'steps': 42189, 'loss/train': 1.7014646530151367} 08/30/2021 20:46:16 - INFO - __main__ - Step 42191: {'lr': 0.00041441045063350933, 'samples': 8100672, 'steps': 42190, 'loss/train': 1.41290283203125} 08/30/2021 20:46:16 - INFO - __main__ - Step 42192: {'lr': 0.00041440645286262677, 'samples': 8100864, 'steps': 42191, 'loss/train': 1.4311779737472534} 08/30/2021 20:46:17 - INFO - __main__ - Step 42193: {'lr': 0.0004144024550176653, 'samples': 8101056, 'steps': 42192, 'loss/train': 0.7025465965270996} 08/30/2021 20:46:18 - INFO - __main__ - Step 42194: {'lr': 0.0004143984570986265, 'samples': 8101248, 'steps': 42193, 'loss/train': 1.4432069063186646} 08/30/2021 20:46:18 - INFO - __main__ - Step 42195: {'lr': 0.00041439445910551235, 'samples': 8101440, 'steps': 42194, 'loss/train': 1.0412001609802246} 08/30/2021 20:46:19 - INFO - __main__ - Step 42196: {'lr': 0.00041439046103832454, 'samples': 8101632, 'steps': 42195, 'loss/train': 1.7480463981628418} 08/30/2021 20:46:19 - INFO - __main__ - Step 42197: {'lr': 0.000414386462897065, 'samples': 8101824, 'steps': 42196, 'loss/train': 1.311126947402954} 08/30/2021 20:46:20 - INFO - __main__ - Step 42198: {'lr': 0.00041438246468173545, 'samples': 8102016, 'steps': 42197, 'loss/train': 1.207491159439087} 08/30/2021 20:46:21 - INFO - __main__ - Step 42199: {'lr': 0.0004143784663923377, 'samples': 8102208, 'steps': 42198, 'loss/train': 1.446942925453186} 08/30/2021 20:46:21 - INFO - __main__ - Step 42200: {'lr': 0.00041437446802887354, 'samples': 8102400, 'steps': 42199, 'loss/train': 1.9346952438354492} 08/30/2021 20:46:21 - INFO - __main__ - Step 42201: {'lr': 0.0004143704695913447, 'samples': 8102592, 'steps': 42200, 'loss/train': 0.8921756744384766} 08/30/2021 20:46:22 - INFO - __main__ - Step 42202: {'lr': 0.0004143664710797531, 'samples': 8102784, 'steps': 42201, 'loss/train': 1.4309717416763306} 08/30/2021 20:46:23 - INFO - __main__ - Step 42203: {'lr': 0.0004143624724941006, 'samples': 8102976, 'steps': 42202, 'loss/train': 1.6684378385543823} 08/30/2021 20:46:24 - INFO - __main__ - Step 42204: {'lr': 0.00041435847383438886, 'samples': 8103168, 'steps': 42203, 'loss/train': 0.9194706678390503} 08/30/2021 20:46:24 - INFO - __main__ - Step 42205: {'lr': 0.0004143544751006197, 'samples': 8103360, 'steps': 42204, 'loss/train': 1.3952915668487549} 08/30/2021 20:46:25 - INFO - __main__ - Step 42206: {'lr': 0.000414350476292795, 'samples': 8103552, 'steps': 42205, 'loss/train': 0.5288825631141663} 08/30/2021 20:46:25 - INFO - __main__ - Step 42207: {'lr': 0.0004143464774109164, 'samples': 8103744, 'steps': 42206, 'loss/train': 1.461159110069275} 08/30/2021 20:46:26 - INFO - __main__ - Step 42208: {'lr': 0.0004143424784549859, 'samples': 8103936, 'steps': 42207, 'loss/train': 1.186647891998291} 08/30/2021 20:46:27 - INFO - __main__ - Step 42209: {'lr': 0.00041433847942500516, 'samples': 8104128, 'steps': 42208, 'loss/train': 1.447962999343872} 08/30/2021 20:46:27 - INFO - __main__ - Step 42210: {'lr': 0.0004143344803209761, 'samples': 8104320, 'steps': 42209, 'loss/train': 1.9218649864196777} 08/30/2021 20:46:27 - INFO - __main__ - Step 42211: {'lr': 0.0004143304811429005, 'samples': 8104512, 'steps': 42210, 'loss/train': 1.1474194526672363} 08/30/2021 20:46:28 - INFO - __main__ - Step 42212: {'lr': 0.00041432648189078006, 'samples': 8104704, 'steps': 42211, 'loss/train': 1.5400233268737793} 08/30/2021 20:46:28 - INFO - __main__ - Step 42213: {'lr': 0.0004143224825646166, 'samples': 8104896, 'steps': 42212, 'loss/train': 1.8447178602218628} 08/30/2021 20:46:30 - INFO - __main__ - Step 42214: {'lr': 0.000414318483164412, 'samples': 8105088, 'steps': 42213, 'loss/train': 1.5515023469924927} 08/30/2021 20:46:30 - INFO - __main__ - Step 42215: {'lr': 0.000414314483690168, 'samples': 8105280, 'steps': 42214, 'loss/train': 1.1254675388336182} 08/30/2021 20:46:30 - INFO - __main__ - Step 42216: {'lr': 0.00041431048414188645, 'samples': 8105472, 'steps': 42215, 'loss/train': 1.2145752906799316} 08/30/2021 20:46:31 - INFO - __main__ - Step 42217: {'lr': 0.00041430648451956913, 'samples': 8105664, 'steps': 42216, 'loss/train': 0.9684998393058777} 08/30/2021 20:46:31 - INFO - __main__ - Step 42218: {'lr': 0.00041430248482321794, 'samples': 8105856, 'steps': 42217, 'loss/train': 1.4339289665222168} 08/30/2021 20:46:33 - INFO - __main__ - Step 42219: {'lr': 0.00041429848505283444, 'samples': 8106048, 'steps': 42218, 'loss/train': 1.1669222116470337} 08/30/2021 20:46:34 - INFO - __main__ - Step 42220: {'lr': 0.00041429448520842064, 'samples': 8106240, 'steps': 42219, 'loss/train': 1.4249677658081055} 08/30/2021 20:46:34 - INFO - __main__ - Step 42221: {'lr': 0.0004142904852899783, 'samples': 8106432, 'steps': 42220, 'loss/train': 1.1597368717193604} 08/30/2021 20:46:34 - INFO - __main__ - Step 42222: {'lr': 0.0004142864852975092, 'samples': 8106624, 'steps': 42221, 'loss/train': 2.188777446746826} 08/30/2021 20:46:35 - INFO - __main__ - Step 42223: {'lr': 0.00041428248523101507, 'samples': 8106816, 'steps': 42222, 'loss/train': 0.25819453597068787} 08/30/2021 20:46:36 - INFO - __main__ - Step 42224: {'lr': 0.0004142784850904978, 'samples': 8107008, 'steps': 42223, 'loss/train': 1.8180350065231323} 08/30/2021 20:46:37 - INFO - __main__ - Step 42225: {'lr': 0.00041427448487595933, 'samples': 8107200, 'steps': 42224, 'loss/train': 1.1398649215698242} 08/30/2021 20:46:37 - INFO - __main__ - Step 42226: {'lr': 0.0004142704845874012, 'samples': 8107392, 'steps': 42225, 'loss/train': 1.6380653381347656} 08/30/2021 20:46:37 - INFO - __main__ - Step 42227: {'lr': 0.00041426648422482527, 'samples': 8107584, 'steps': 42226, 'loss/train': 1.6042135953903198} 08/30/2021 20:46:38 - INFO - __main__ - Step 42228: {'lr': 0.0004142624837882335, 'samples': 8107776, 'steps': 42227, 'loss/train': 1.3946853876113892} 08/30/2021 20:46:39 - INFO - __main__ - Step 42229: {'lr': 0.0004142584832776275, 'samples': 8107968, 'steps': 42228, 'loss/train': 1.629384160041809} 08/30/2021 20:46:40 - INFO - __main__ - Step 42230: {'lr': 0.00041425448269300923, 'samples': 8108160, 'steps': 42229, 'loss/train': 0.3680429458618164} 08/30/2021 20:46:40 - INFO - __main__ - Step 42231: {'lr': 0.00041425048203438036, 'samples': 8108352, 'steps': 42230, 'loss/train': 1.462911605834961} 08/30/2021 20:46:41 - INFO - __main__ - Step 42232: {'lr': 0.0004142464813017429, 'samples': 8108544, 'steps': 42231, 'loss/train': 0.07783259451389313} 08/30/2021 20:46:41 - INFO - __main__ - Step 42233: {'lr': 0.0004142424804950984, 'samples': 8108736, 'steps': 42232, 'loss/train': 0.4490537941455841} 08/30/2021 20:46:42 - INFO - __main__ - Step 42234: {'lr': 0.00041423847961444873, 'samples': 8108928, 'steps': 42233, 'loss/train': 1.3863348960876465} 08/30/2021 20:46:43 - INFO - __main__ - Step 42235: {'lr': 0.0004142344786597958, 'samples': 8109120, 'steps': 42234, 'loss/train': 1.1885013580322266} 08/30/2021 20:46:43 - INFO - __main__ - Step 42236: {'lr': 0.0004142304776311413, 'samples': 8109312, 'steps': 42235, 'loss/train': 1.1874572038650513} 08/30/2021 20:46:44 - INFO - __main__ - Step 42237: {'lr': 0.0004142264765284871, 'samples': 8109504, 'steps': 42236, 'loss/train': 1.1852940320968628} 08/30/2021 20:46:44 - INFO - __main__ - Step 42238: {'lr': 0.0004142224753518351, 'samples': 8109696, 'steps': 42237, 'loss/train': 0.8874362707138062} 08/30/2021 20:46:45 - INFO - __main__ - Step 42239: {'lr': 0.00041421847410118685, 'samples': 8109888, 'steps': 42238, 'loss/train': 1.4015588760375977} 08/30/2021 20:46:46 - INFO - __main__ - Step 42240: {'lr': 0.00041421447277654436, 'samples': 8110080, 'steps': 42239, 'loss/train': 1.5901575088500977} 08/30/2021 20:46:46 - INFO - __main__ - Step 42241: {'lr': 0.0004142104713779093, 'samples': 8110272, 'steps': 42240, 'loss/train': 1.4169880151748657} 08/30/2021 20:46:47 - INFO - __main__ - Step 42242: {'lr': 0.00041420646990528355, 'samples': 8110464, 'steps': 42241, 'loss/train': 1.8420770168304443} 08/30/2021 20:46:47 - INFO - __main__ - Step 42243: {'lr': 0.0004142024683586689, 'samples': 8110656, 'steps': 42242, 'loss/train': 1.6727858781814575} 08/30/2021 20:46:49 - INFO - __main__ - Step 42244: {'lr': 0.00041419846673806715, 'samples': 8110848, 'steps': 42243, 'loss/train': 1.2827200889587402} 08/30/2021 20:46:49 - INFO - __main__ - Step 42245: {'lr': 0.0004141944650434801, 'samples': 8111040, 'steps': 42244, 'loss/train': 1.2395683526992798} 08/30/2021 20:46:49 - INFO - __main__ - Step 42246: {'lr': 0.00041419046327490964, 'samples': 8111232, 'steps': 42245, 'loss/train': 1.6822307109832764} 08/30/2021 20:46:50 - INFO - __main__ - Step 42247: {'lr': 0.00041418646143235737, 'samples': 8111424, 'steps': 42246, 'loss/train': 1.0382400751113892} 08/30/2021 20:46:50 - INFO - __main__ - Step 42248: {'lr': 0.0004141824595158253, 'samples': 8111616, 'steps': 42247, 'loss/train': 1.8770506381988525} 08/30/2021 20:46:50 - INFO - __main__ - Step 42249: {'lr': 0.0004141784575253151, 'samples': 8111808, 'steps': 42248, 'loss/train': 1.2458492517471313} 08/30/2021 20:46:52 - INFO - __main__ - Step 42250: {'lr': 0.0004141744554608287, 'samples': 8112000, 'steps': 42249, 'loss/train': 1.2245113849639893} 08/30/2021 20:46:52 - INFO - __main__ - Step 42251: {'lr': 0.00041417045332236776, 'samples': 8112192, 'steps': 42250, 'loss/train': 1.21090567111969} 08/30/2021 20:46:53 - INFO - __main__ - Step 42252: {'lr': 0.0004141664511099341, 'samples': 8112384, 'steps': 42251, 'loss/train': 1.0141521692276} 08/30/2021 20:46:53 - INFO - __main__ - Step 42253: {'lr': 0.00041416244882352965, 'samples': 8112576, 'steps': 42252, 'loss/train': 1.0303927659988403} 08/30/2021 20:46:53 - INFO - __main__ - Step 42254: {'lr': 0.00041415844646315613, 'samples': 8112768, 'steps': 42253, 'loss/train': 1.3580528497695923} 08/30/2021 20:46:55 - INFO - __main__ - Step 42255: {'lr': 0.0004141544440288153, 'samples': 8112960, 'steps': 42254, 'loss/train': 1.4445478916168213} 08/30/2021 20:46:55 - INFO - __main__ - Step 42256: {'lr': 0.0004141504415205091, 'samples': 8113152, 'steps': 42255, 'loss/train': 0.8169226050376892} 08/30/2021 20:46:56 - INFO - __main__ - Step 42257: {'lr': 0.0004141464389382391, 'samples': 8113344, 'steps': 42256, 'loss/train': 1.4042410850524902} 08/30/2021 20:46:56 - INFO - __main__ - Step 42258: {'lr': 0.0004141424362820073, 'samples': 8113536, 'steps': 42257, 'loss/train': 1.4125057458877563} 08/30/2021 20:46:56 - INFO - __main__ - Step 42259: {'lr': 0.0004141384335518155, 'samples': 8113728, 'steps': 42258, 'loss/train': 1.494933843612671} 08/30/2021 20:46:58 - INFO - __main__ - Step 42260: {'lr': 0.00041413443074766543, 'samples': 8113920, 'steps': 42259, 'loss/train': 1.651997685432434} 08/30/2021 20:46:59 - INFO - __main__ - Step 42261: {'lr': 0.000414130427869559, 'samples': 8114112, 'steps': 42260, 'loss/train': 1.7769715785980225} 08/30/2021 20:46:59 - INFO - __main__ - Step 42262: {'lr': 0.0004141264249174978, 'samples': 8114304, 'steps': 42261, 'loss/train': 1.8201574087142944} 08/30/2021 20:46:59 - INFO - __main__ - Step 42263: {'lr': 0.00041412242189148383, 'samples': 8114496, 'steps': 42262, 'loss/train': 0.06089145690202713} 08/30/2021 20:47:00 - INFO - __main__ - Step 42264: {'lr': 0.00041411841879151877, 'samples': 8114688, 'steps': 42263, 'loss/train': 1.713726282119751} 08/30/2021 20:47:01 - INFO - __main__ - Step 42265: {'lr': 0.00041411441561760455, 'samples': 8114880, 'steps': 42264, 'loss/train': 0.847568929195404} 08/30/2021 20:47:02 - INFO - __main__ - Step 42266: {'lr': 0.0004141104123697429, 'samples': 8115072, 'steps': 42265, 'loss/train': 1.4999792575836182} 08/30/2021 20:47:02 - INFO - __main__ - Step 42267: {'lr': 0.00041410640904793563, 'samples': 8115264, 'steps': 42266, 'loss/train': 1.7000240087509155} 08/30/2021 20:47:02 - INFO - __main__ - Step 42268: {'lr': 0.0004141024056521845, 'samples': 8115456, 'steps': 42267, 'loss/train': 1.2713193893432617} 08/30/2021 20:47:03 - INFO - __main__ - Step 42269: {'lr': 0.0004140984021824914, 'samples': 8115648, 'steps': 42268, 'loss/train': 1.7952033281326294} 08/30/2021 20:47:04 - INFO - __main__ - Step 42270: {'lr': 0.0004140943986388581, 'samples': 8115840, 'steps': 42269, 'loss/train': 0.06707034260034561} 08/30/2021 20:47:05 - INFO - __main__ - Step 42271: {'lr': 0.00041409039502128634, 'samples': 8116032, 'steps': 42270, 'loss/train': 1.0375711917877197} 08/30/2021 20:47:05 - INFO - __main__ - Step 42272: {'lr': 0.000414086391329778, 'samples': 8116224, 'steps': 42271, 'loss/train': 1.1584436893463135} 08/30/2021 20:47:05 - INFO - __main__ - Step 42273: {'lr': 0.0004140823875643349, 'samples': 8116416, 'steps': 42272, 'loss/train': 0.8180829882621765} 08/30/2021 20:47:06 - INFO - __main__ - Step 42274: {'lr': 0.00041407838372495883, 'samples': 8116608, 'steps': 42273, 'loss/train': 1.377746343612671} 08/30/2021 20:47:06 - INFO - __main__ - Step 42275: {'lr': 0.00041407437981165154, 'samples': 8116800, 'steps': 42274, 'loss/train': 1.178992509841919} 08/30/2021 20:47:08 - INFO - __main__ - Step 42276: {'lr': 0.0004140703758244148, 'samples': 8116992, 'steps': 42275, 'loss/train': 1.6284089088439941} 08/30/2021 20:47:09 - INFO - __main__ - Step 42277: {'lr': 0.00041406637176325054, 'samples': 8117184, 'steps': 42276, 'loss/train': 1.1715081930160522} 08/30/2021 20:47:09 - INFO - __main__ - Step 42278: {'lr': 0.00041406236762816053, 'samples': 8117376, 'steps': 42277, 'loss/train': 1.3192260265350342} 08/30/2021 20:47:10 - INFO - __main__ - Step 42279: {'lr': 0.0004140583634191465, 'samples': 8117568, 'steps': 42278, 'loss/train': 1.326980471611023} 08/30/2021 20:47:10 - INFO - __main__ - Step 42280: {'lr': 0.00041405435913621037, 'samples': 8117760, 'steps': 42279, 'loss/train': 1.7745006084442139} 08/30/2021 20:47:11 - INFO - __main__ - Step 42281: {'lr': 0.0004140503547793538, 'samples': 8117952, 'steps': 42280, 'loss/train': 0.8168326616287231} 08/30/2021 20:47:12 - INFO - __main__ - Step 42282: {'lr': 0.00041404635034857876, 'samples': 8118144, 'steps': 42281, 'loss/train': 1.3293964862823486} 08/30/2021 20:47:12 - INFO - __main__ - Step 42283: {'lr': 0.00041404234584388683, 'samples': 8118336, 'steps': 42282, 'loss/train': 1.3677918910980225} 08/30/2021 20:47:13 - INFO - __main__ - Step 42284: {'lr': 0.00041403834126528007, 'samples': 8118528, 'steps': 42283, 'loss/train': 1.8644312620162964} 08/30/2021 20:47:13 - INFO - __main__ - Step 42285: {'lr': 0.00041403433661276015, 'samples': 8118720, 'steps': 42284, 'loss/train': 0.9539211988449097} 08/30/2021 20:47:14 - INFO - __main__ - Step 42286: {'lr': 0.0004140303318863288, 'samples': 8118912, 'steps': 42285, 'loss/train': 1.2375967502593994} 08/30/2021 20:47:15 - INFO - __main__ - Step 42287: {'lr': 0.00041402632708598797, 'samples': 8119104, 'steps': 42286, 'loss/train': 1.9723584651947021} 08/30/2021 20:47:15 - INFO - __main__ - Step 42288: {'lr': 0.0004140223222117394, 'samples': 8119296, 'steps': 42287, 'loss/train': 1.137107253074646} 08/30/2021 20:47:16 - INFO - __main__ - Step 42289: {'lr': 0.00041401831726358497, 'samples': 8119488, 'steps': 42288, 'loss/train': 0.07174333184957504} 08/30/2021 20:47:16 - INFO - __main__ - Step 42290: {'lr': 0.0004140143122415263, 'samples': 8119680, 'steps': 42289, 'loss/train': 1.2087912559509277} 08/30/2021 20:47:18 - INFO - __main__ - Step 42291: {'lr': 0.0004140103071455654, 'samples': 8119872, 'steps': 42290, 'loss/train': 1.216581106185913} 08/30/2021 20:47:18 - INFO - __main__ - Step 42292: {'lr': 0.000414006301975704, 'samples': 8120064, 'steps': 42291, 'loss/train': 1.4962636232376099} 08/30/2021 20:47:18 - INFO - __main__ - Step 42293: {'lr': 0.0004140022967319439, 'samples': 8120256, 'steps': 42292, 'loss/train': 1.4432076215744019} 08/30/2021 20:47:19 - INFO - __main__ - Step 42294: {'lr': 0.0004139982914142868, 'samples': 8120448, 'steps': 42293, 'loss/train': 1.4617767333984375} 08/30/2021 20:47:19 - INFO - __main__ - Step 42295: {'lr': 0.0004139942860227346, 'samples': 8120640, 'steps': 42294, 'loss/train': 0.6603941321372986} 08/30/2021 20:47:21 - INFO - __main__ - Step 42296: {'lr': 0.00041399028055728914, 'samples': 8120832, 'steps': 42295, 'loss/train': 1.6991488933563232} 08/30/2021 20:47:21 - INFO - __main__ - Step 42297: {'lr': 0.0004139862750179523, 'samples': 8121024, 'steps': 42296, 'loss/train': 1.3488762378692627} 08/30/2021 20:47:21 - INFO - __main__ - Step 42298: {'lr': 0.0004139822694047256, 'samples': 8121216, 'steps': 42297, 'loss/train': 1.7634027004241943} 08/30/2021 20:47:22 - INFO - __main__ - Step 42299: {'lr': 0.0004139782637176112, 'samples': 8121408, 'steps': 42298, 'loss/train': 1.4938671588897705} 08/30/2021 20:47:22 - INFO - __main__ - Step 42300: {'lr': 0.0004139742579566106, 'samples': 8121600, 'steps': 42299, 'loss/train': 1.2177492380142212} 08/30/2021 20:47:22 - INFO - __main__ - Step 42301: {'lr': 0.00041397025212172573, 'samples': 8121792, 'steps': 42300, 'loss/train': 1.2403696775436401} 08/30/2021 20:47:24 - INFO - __main__ - Step 42302: {'lr': 0.00041396624621295843, 'samples': 8121984, 'steps': 42301, 'loss/train': 0.5987139940261841} 08/30/2021 20:47:24 - INFO - __main__ - Step 42303: {'lr': 0.00041396224023031045, 'samples': 8122176, 'steps': 42302, 'loss/train': 1.612777829170227} 08/30/2021 20:47:25 - INFO - __main__ - Step 42304: {'lr': 0.0004139582341737836, 'samples': 8122368, 'steps': 42303, 'loss/train': 0.9146180152893066} 08/30/2021 20:47:25 - INFO - __main__ - Step 42305: {'lr': 0.0004139542280433797, 'samples': 8122560, 'steps': 42304, 'loss/train': 0.8867013454437256} 08/30/2021 20:47:25 - INFO - __main__ - Step 42306: {'lr': 0.00041395022183910064, 'samples': 8122752, 'steps': 42305, 'loss/train': 1.7288566827774048} 08/30/2021 20:47:27 - INFO - __main__ - Step 42307: {'lr': 0.00041394621556094805, 'samples': 8122944, 'steps': 42306, 'loss/train': 1.3016126155853271} 08/30/2021 20:47:27 - INFO - __main__ - Step 42308: {'lr': 0.0004139422092089239, 'samples': 8123136, 'steps': 42307, 'loss/train': 1.4550639390945435} 08/30/2021 20:47:28 - INFO - __main__ - Step 42309: {'lr': 0.0004139382027830298, 'samples': 8123328, 'steps': 42308, 'loss/train': 1.4436196088790894} 08/30/2021 20:47:28 - INFO - __main__ - Step 42310: {'lr': 0.00041393419628326777, 'samples': 8123520, 'steps': 42309, 'loss/train': 1.1155717372894287} 08/30/2021 20:47:28 - INFO - __main__ - Step 42311: {'lr': 0.00041393018970963945, 'samples': 8123712, 'steps': 42310, 'loss/train': 0.27183741331100464} 08/30/2021 20:47:30 - INFO - __main__ - Step 42312: {'lr': 0.00041392618306214683, 'samples': 8123904, 'steps': 42311, 'loss/train': 0.4071536958217621} 08/30/2021 20:47:30 - INFO - __main__ - Step 42313: {'lr': 0.0004139221763407915, 'samples': 8124096, 'steps': 42312, 'loss/train': 1.318495512008667} 08/30/2021 20:47:31 - INFO - __main__ - Step 42314: {'lr': 0.00041391816954557543, 'samples': 8124288, 'steps': 42313, 'loss/train': 1.7925927639007568} 08/30/2021 20:47:31 - INFO - __main__ - Step 42315: {'lr': 0.00041391416267650034, 'samples': 8124480, 'steps': 42314, 'loss/train': 1.2577730417251587} 08/30/2021 20:47:31 - INFO - __main__ - Step 42316: {'lr': 0.00041391015573356805, 'samples': 8124672, 'steps': 42315, 'loss/train': 1.387742280960083} 08/30/2021 20:47:33 - INFO - __main__ - Step 42317: {'lr': 0.0004139061487167804, 'samples': 8124864, 'steps': 42316, 'loss/train': 1.376395583152771} 08/30/2021 20:47:33 - INFO - __main__ - Step 42318: {'lr': 0.00041390214162613916, 'samples': 8125056, 'steps': 42317, 'loss/train': 0.8154731392860413} 08/30/2021 20:47:34 - INFO - __main__ - Step 42319: {'lr': 0.00041389813446164614, 'samples': 8125248, 'steps': 42318, 'loss/train': 0.37088194489479065} 08/30/2021 20:47:34 - INFO - __main__ - Step 42320: {'lr': 0.0004138941272233031, 'samples': 8125440, 'steps': 42319, 'loss/train': 1.0520355701446533} 08/30/2021 20:47:34 - INFO - __main__ - Step 42321: {'lr': 0.0004138901199111119, 'samples': 8125632, 'steps': 42320, 'loss/train': 1.4669736623764038} 08/30/2021 20:47:36 - INFO - __main__ - Step 42322: {'lr': 0.00041388611252507446, 'samples': 8125824, 'steps': 42321, 'loss/train': 1.990148663520813} 08/30/2021 20:47:37 - INFO - __main__ - Step 42323: {'lr': 0.0004138821050651923, 'samples': 8126016, 'steps': 42322, 'loss/train': 1.2143610715866089} 08/30/2021 20:47:37 - INFO - __main__ - Step 42324: {'lr': 0.00041387809753146756, 'samples': 8126208, 'steps': 42323, 'loss/train': 1.393174648284912} 08/30/2021 20:47:38 - INFO - __main__ - Step 42325: {'lr': 0.00041387408992390177, 'samples': 8126400, 'steps': 42324, 'loss/train': 1.2353628873825073} 08/30/2021 20:47:38 - INFO - __main__ - Step 42326: {'lr': 0.0004138700822424968, 'samples': 8126592, 'steps': 42325, 'loss/train': 1.2122210264205933} 08/30/2021 20:47:38 - INFO - __main__ - Step 42327: {'lr': 0.0004138660744872547, 'samples': 8126784, 'steps': 42326, 'loss/train': 1.7359952926635742} 08/30/2021 20:47:40 - INFO - __main__ - Step 42328: {'lr': 0.00041386206665817684, 'samples': 8126976, 'steps': 42327, 'loss/train': 0.7341434955596924} 08/30/2021 20:47:41 - INFO - __main__ - Step 42329: {'lr': 0.0004138580587552654, 'samples': 8127168, 'steps': 42328, 'loss/train': 1.654409646987915} 08/30/2021 20:47:41 - INFO - __main__ - Step 42330: {'lr': 0.000413854050778522, 'samples': 8127360, 'steps': 42329, 'loss/train': 1.464223861694336} 08/30/2021 20:47:42 - INFO - __main__ - Step 42331: {'lr': 0.00041385004272794846, 'samples': 8127552, 'steps': 42330, 'loss/train': 0.576591968536377} 08/30/2021 20:47:42 - INFO - __main__ - Step 42332: {'lr': 0.0004138460346035467, 'samples': 8127744, 'steps': 42331, 'loss/train': 1.5685197114944458} 08/30/2021 20:47:43 - INFO - __main__ - Step 42333: {'lr': 0.0004138420264053184, 'samples': 8127936, 'steps': 42332, 'loss/train': 1.5571768283843994} 08/30/2021 20:47:44 - INFO - __main__ - Step 42334: {'lr': 0.00041383801813326543, 'samples': 8128128, 'steps': 42333, 'loss/train': 1.3254379034042358} 08/30/2021 20:47:44 - INFO - __main__ - Step 42335: {'lr': 0.00041383400978738956, 'samples': 8128320, 'steps': 42334, 'loss/train': 1.1243456602096558} 08/30/2021 20:47:45 - INFO - __main__ - Step 42336: {'lr': 0.0004138300013676926, 'samples': 8128512, 'steps': 42335, 'loss/train': 1.4749187231063843} 08/30/2021 20:47:45 - INFO - __main__ - Step 42337: {'lr': 0.0004138259928741764, 'samples': 8128704, 'steps': 42336, 'loss/train': 1.1158260107040405} 08/30/2021 20:47:45 - INFO - __main__ - Step 42338: {'lr': 0.0004138219843068427, 'samples': 8128896, 'steps': 42337, 'loss/train': 1.6016513109207153} 08/30/2021 20:47:47 - INFO - __main__ - Step 42339: {'lr': 0.00041381797566569345, 'samples': 8129088, 'steps': 42338, 'loss/train': 1.2200013399124146} 08/30/2021 20:47:47 - INFO - __main__ - Step 42340: {'lr': 0.0004138139669507303, 'samples': 8129280, 'steps': 42339, 'loss/train': 1.9808986186981201} 08/30/2021 20:47:48 - INFO - __main__ - Step 42341: {'lr': 0.000413809958161955, 'samples': 8129472, 'steps': 42340, 'loss/train': 0.7874013781547546} 08/30/2021 20:47:48 - INFO - __main__ - Step 42342: {'lr': 0.0004138059492993695, 'samples': 8129664, 'steps': 42341, 'loss/train': 1.4540199041366577} 08/30/2021 20:47:49 - INFO - __main__ - Step 42343: {'lr': 0.0004138019403629756, 'samples': 8129856, 'steps': 42342, 'loss/train': 0.6971977949142456} 08/30/2021 20:47:50 - INFO - __main__ - Step 42344: {'lr': 0.0004137979313527751, 'samples': 8130048, 'steps': 42343, 'loss/train': 0.027746109291911125} 08/30/2021 20:47:50 - INFO - __main__ - Step 42345: {'lr': 0.00041379392226876974, 'samples': 8130240, 'steps': 42344, 'loss/train': 1.6688930988311768} 08/30/2021 20:47:51 - INFO - __main__ - Step 42346: {'lr': 0.0004137899131109614, 'samples': 8130432, 'steps': 42345, 'loss/train': 0.9629099369049072} 08/30/2021 20:47:51 - INFO - __main__ - Step 42347: {'lr': 0.0004137859038793518, 'samples': 8130624, 'steps': 42346, 'loss/train': 0.9345664381980896} 08/30/2021 20:47:51 - INFO - __main__ - Step 42348: {'lr': 0.0004137818945739428, 'samples': 8130816, 'steps': 42347, 'loss/train': 1.118801474571228} 08/30/2021 20:47:52 - INFO - __main__ - Step 42349: {'lr': 0.00041377788519473624, 'samples': 8131008, 'steps': 42348, 'loss/train': 1.4099096059799194} 08/30/2021 20:47:53 - INFO - __main__ - Step 42350: {'lr': 0.0004137738757417339, 'samples': 8131200, 'steps': 42349, 'loss/train': 1.2825098037719727} 08/30/2021 20:47:54 - INFO - __main__ - Step 42351: {'lr': 0.0004137698662149375, 'samples': 8131392, 'steps': 42350, 'loss/train': 1.5043368339538574} 08/30/2021 20:47:54 - INFO - __main__ - Step 42352: {'lr': 0.00041376585661434903, 'samples': 8131584, 'steps': 42351, 'loss/train': 1.049721121788025} 08/30/2021 20:47:54 - INFO - __main__ - Step 42353: {'lr': 0.0004137618469399702, 'samples': 8131776, 'steps': 42352, 'loss/train': 1.226038932800293} 08/30/2021 20:47:55 - INFO - __main__ - Step 42354: {'lr': 0.0004137578371918027, 'samples': 8131968, 'steps': 42353, 'loss/train': 1.4198780059814453} 08/30/2021 20:47:56 - INFO - __main__ - Step 42355: {'lr': 0.00041375382736984857, 'samples': 8132160, 'steps': 42354, 'loss/train': 0.3786611258983612} 08/30/2021 20:47:57 - INFO - __main__ - Step 42356: {'lr': 0.0004137498174741094, 'samples': 8132352, 'steps': 42355, 'loss/train': 1.0501378774642944} 08/30/2021 20:47:57 - INFO - __main__ - Step 42357: {'lr': 0.0004137458075045871, 'samples': 8132544, 'steps': 42356, 'loss/train': 1.5100451707839966} 08/30/2021 20:47:58 - INFO - __main__ - Step 42358: {'lr': 0.0004137417974612835, 'samples': 8132736, 'steps': 42357, 'loss/train': 0.7366935610771179} 08/30/2021 20:47:58 - INFO - __main__ - Step 42359: {'lr': 0.0004137377873442004, 'samples': 8132928, 'steps': 42358, 'loss/train': 1.0398112535476685} 08/30/2021 20:47:59 - INFO - __main__ - Step 42360: {'lr': 0.00041373377715333946, 'samples': 8133120, 'steps': 42359, 'loss/train': 0.3249274492263794} 08/30/2021 20:48:00 - INFO - __main__ - Step 42361: {'lr': 0.00041372976688870266, 'samples': 8133312, 'steps': 42360, 'loss/train': 1.0224472284317017} 08/30/2021 20:48:00 - INFO - __main__ - Step 42362: {'lr': 0.0004137257565502918, 'samples': 8133504, 'steps': 42361, 'loss/train': 1.5017039775848389} 08/30/2021 20:48:00 - INFO - __main__ - Step 42363: {'lr': 0.00041372174613810863, 'samples': 8133696, 'steps': 42362, 'loss/train': 0.9485722184181213} 08/30/2021 20:48:01 - INFO - __main__ - Step 42364: {'lr': 0.00041371773565215494, 'samples': 8133888, 'steps': 42363, 'loss/train': 1.691267728805542} 08/30/2021 20:48:02 - INFO - __main__ - Step 42365: {'lr': 0.00041371372509243256, 'samples': 8134080, 'steps': 42364, 'loss/train': 1.8485782146453857} 08/30/2021 20:48:03 - INFO - __main__ - Step 42366: {'lr': 0.00041370971445894335, 'samples': 8134272, 'steps': 42365, 'loss/train': 1.4423432350158691} 08/30/2021 20:48:03 - INFO - __main__ - Step 42367: {'lr': 0.00041370570375168903, 'samples': 8134464, 'steps': 42366, 'loss/train': 1.0338165760040283} 08/30/2021 20:48:04 - INFO - __main__ - Step 42368: {'lr': 0.00041370169297067145, 'samples': 8134656, 'steps': 42367, 'loss/train': 1.3190189599990845} 08/30/2021 20:48:04 - INFO - __main__ - Step 42369: {'lr': 0.00041369768211589245, 'samples': 8134848, 'steps': 42368, 'loss/train': 1.589645504951477} 08/30/2021 20:48:06 - INFO - __main__ - Step 42370: {'lr': 0.0004136936711873537, 'samples': 8135040, 'steps': 42369, 'loss/train': 1.5672895908355713} 08/30/2021 20:48:06 - INFO - __main__ - Step 42371: {'lr': 0.0004136896601850572, 'samples': 8135232, 'steps': 42370, 'loss/train': 1.205672264099121} 08/30/2021 20:48:07 - INFO - __main__ - Step 42372: {'lr': 0.0004136856491090046, 'samples': 8135424, 'steps': 42371, 'loss/train': 0.03171316534280777} 08/30/2021 20:48:07 - INFO - __main__ - Step 42373: {'lr': 0.0004136816379591979, 'samples': 8135616, 'steps': 42372, 'loss/train': 1.3279576301574707} 08/30/2021 20:48:07 - INFO - __main__ - Step 42374: {'lr': 0.0004136776267356387, 'samples': 8135808, 'steps': 42373, 'loss/train': 1.119813084602356} 08/30/2021 20:48:08 - INFO - __main__ - Step 42375: {'lr': 0.0004136736154383288, 'samples': 8136000, 'steps': 42374, 'loss/train': 0.40838176012039185} 08/30/2021 20:48:08 - INFO - __main__ - Step 42376: {'lr': 0.00041366960406727024, 'samples': 8136192, 'steps': 42375, 'loss/train': 1.4585062265396118} 08/30/2021 20:48:09 - INFO - __main__ - Step 42377: {'lr': 0.00041366559262246463, 'samples': 8136384, 'steps': 42376, 'loss/train': 1.2161041498184204} 08/30/2021 20:48:10 - INFO - __main__ - Step 42378: {'lr': 0.00041366158110391375, 'samples': 8136576, 'steps': 42377, 'loss/train': 1.6128627061843872} 08/30/2021 20:48:10 - INFO - __main__ - Step 42379: {'lr': 0.0004136575695116196, 'samples': 8136768, 'steps': 42378, 'loss/train': 0.9576939940452576} 08/30/2021 20:48:11 - INFO - __main__ - Step 42380: {'lr': 0.0004136535578455838, 'samples': 8136960, 'steps': 42379, 'loss/train': 1.3552660942077637} 08/30/2021 20:48:11 - INFO - __main__ - Step 42381: {'lr': 0.0004136495461058083, 'samples': 8137152, 'steps': 42380, 'loss/train': 1.3495925664901733} 08/30/2021 20:48:13 - INFO - __main__ - Step 42382: {'lr': 0.0004136455342922948, 'samples': 8137344, 'steps': 42381, 'loss/train': 1.1265242099761963} 08/30/2021 20:48:14 - INFO - __main__ - Step 42383: {'lr': 0.0004136415224050451, 'samples': 8137536, 'steps': 42382, 'loss/train': 1.225480318069458} 08/30/2021 20:48:14 - INFO - __main__ - Step 42384: {'lr': 0.0004136375104440611, 'samples': 8137728, 'steps': 42383, 'loss/train': 1.4332607984542847} 08/30/2021 20:48:14 - INFO - __main__ - Step 42385: {'lr': 0.0004136334984093446, 'samples': 8137920, 'steps': 42384, 'loss/train': 1.367175579071045} 08/30/2021 20:48:15 - INFO - __main__ - Step 42386: {'lr': 0.0004136294863008974, 'samples': 8138112, 'steps': 42385, 'loss/train': 1.166471242904663} 08/30/2021 20:48:16 - INFO - __main__ - Step 42387: {'lr': 0.00041362547411872116, 'samples': 8138304, 'steps': 42386, 'loss/train': 1.5373362302780151} 08/30/2021 20:48:17 - INFO - __main__ - Step 42388: {'lr': 0.00041362146186281777, 'samples': 8138496, 'steps': 42387, 'loss/train': 1.256736397743225} 08/30/2021 20:48:17 - INFO - __main__ - Step 42389: {'lr': 0.00041361744953318923, 'samples': 8138688, 'steps': 42388, 'loss/train': 1.2164804935455322} 08/30/2021 20:48:17 - INFO - __main__ - Step 42390: {'lr': 0.0004136134371298371, 'samples': 8138880, 'steps': 42389, 'loss/train': 1.3490917682647705} 08/30/2021 20:48:18 - INFO - __main__ - Step 42391: {'lr': 0.0004136094246527633, 'samples': 8139072, 'steps': 42390, 'loss/train': 1.1110398769378662} 08/30/2021 20:48:19 - INFO - __main__ - Step 42392: {'lr': 0.0004136054121019697, 'samples': 8139264, 'steps': 42391, 'loss/train': 1.7152825593948364} 08/30/2021 20:48:20 - INFO - __main__ - Step 42393: {'lr': 0.0004136013994774579, 'samples': 8139456, 'steps': 42392, 'loss/train': 1.9314446449279785} 08/30/2021 20:48:20 - INFO - __main__ - Step 42394: {'lr': 0.00041359738677922993, 'samples': 8139648, 'steps': 42393, 'loss/train': 0.9482883810997009} 08/30/2021 20:48:20 - INFO - __main__ - Step 42395: {'lr': 0.00041359337400728746, 'samples': 8139840, 'steps': 42394, 'loss/train': 1.4887709617614746} 08/30/2021 20:48:21 - INFO - __main__ - Step 42396: {'lr': 0.00041358936116163224, 'samples': 8140032, 'steps': 42395, 'loss/train': 1.4302090406417847} 08/30/2021 20:48:21 - INFO - __main__ - Step 42397: {'lr': 0.00041358534824226635, 'samples': 8140224, 'steps': 42396, 'loss/train': 0.04405956715345383} 08/30/2021 20:48:22 - INFO - __main__ - Step 42398: {'lr': 0.0004135813352491913, 'samples': 8140416, 'steps': 42397, 'loss/train': 1.9415369033813477} 08/30/2021 20:48:23 - INFO - __main__ - Step 42399: {'lr': 0.00041357732218240905, 'samples': 8140608, 'steps': 42398, 'loss/train': 1.2596665620803833} 08/30/2021 20:48:23 - INFO - __main__ - Step 42400: {'lr': 0.0004135733090419215, 'samples': 8140800, 'steps': 42399, 'loss/train': 1.1599003076553345} 08/30/2021 20:48:24 - INFO - __main__ - Step 42401: {'lr': 0.00041356929582773023, 'samples': 8140992, 'steps': 42400, 'loss/train': 2.08315110206604} 08/30/2021 20:48:24 - INFO - __main__ - Step 42402: {'lr': 0.00041356528253983714, 'samples': 8141184, 'steps': 42401, 'loss/train': 1.1858502626419067} 08/30/2021 20:48:26 - INFO - __main__ - Step 42403: {'lr': 0.0004135612691782441, 'samples': 8141376, 'steps': 42402, 'loss/train': 1.6564069986343384} 08/30/2021 20:48:26 - INFO - __main__ - Step 42404: {'lr': 0.0004135572557429529, 'samples': 8141568, 'steps': 42403, 'loss/train': 1.3619468212127686} 08/30/2021 20:48:26 - INFO - __main__ - Step 42405: {'lr': 0.0004135532422339653, 'samples': 8141760, 'steps': 42404, 'loss/train': 1.3367135524749756} 08/30/2021 20:48:27 - INFO - __main__ - Step 42406: {'lr': 0.00041354922865128316, 'samples': 8141952, 'steps': 42405, 'loss/train': 1.5595271587371826} 08/30/2021 20:48:27 - INFO - __main__ - Step 42407: {'lr': 0.00041354521499490813, 'samples': 8142144, 'steps': 42406, 'loss/train': 1.2361431121826172} 08/30/2021 20:48:28 - INFO - __main__ - Step 42408: {'lr': 0.00041354120126484227, 'samples': 8142336, 'steps': 42407, 'loss/train': 1.781445026397705} 08/30/2021 20:48:29 - INFO - __main__ - Step 42409: {'lr': 0.00041353718746108724, 'samples': 8142528, 'steps': 42408, 'loss/train': 1.3715013265609741} 08/30/2021 20:48:29 - INFO - __main__ - Step 42410: {'lr': 0.00041353317358364496, 'samples': 8142720, 'steps': 42409, 'loss/train': 1.4446797370910645} 08/30/2021 20:48:30 - INFO - __main__ - Step 42411: {'lr': 0.00041352915963251705, 'samples': 8142912, 'steps': 42410, 'loss/train': 1.5277940034866333} 08/30/2021 20:48:30 - INFO - __main__ - Step 42412: {'lr': 0.00041352514560770545, 'samples': 8143104, 'steps': 42411, 'loss/train': 0.3148159086704254} 08/30/2021 20:48:31 - INFO - __main__ - Step 42413: {'lr': 0.000413521131509212, 'samples': 8143296, 'steps': 42412, 'loss/train': 1.5040147304534912} 08/30/2021 20:48:32 - INFO - __main__ - Step 42414: {'lr': 0.0004135171173370383, 'samples': 8143488, 'steps': 42413, 'loss/train': 1.3710672855377197} 08/30/2021 20:48:32 - INFO - __main__ - Step 42415: {'lr': 0.00041351310309118653, 'samples': 8143680, 'steps': 42414, 'loss/train': 1.2292615175247192} 08/30/2021 20:48:33 - INFO - __main__ - Step 42416: {'lr': 0.00041350908877165805, 'samples': 8143872, 'steps': 42415, 'loss/train': 1.3799588680267334} 08/30/2021 20:48:33 - INFO - __main__ - Step 42417: {'lr': 0.00041350507437845505, 'samples': 8144064, 'steps': 42416, 'loss/train': 0.8461814522743225} 08/30/2021 20:48:34 - INFO - __main__ - Step 42418: {'lr': 0.00041350105991157915, 'samples': 8144256, 'steps': 42417, 'loss/train': 1.0097887516021729} 08/30/2021 20:48:35 - INFO - __main__ - Step 42419: {'lr': 0.00041349704537103216, 'samples': 8144448, 'steps': 42418, 'loss/train': 1.3813625574111938} 08/30/2021 20:48:35 - INFO - __main__ - Step 42420: {'lr': 0.000413493030756816, 'samples': 8144640, 'steps': 42419, 'loss/train': 1.6276328563690186} 08/30/2021 20:48:35 - INFO - __main__ - Step 42421: {'lr': 0.0004134890160689323, 'samples': 8144832, 'steps': 42420, 'loss/train': 1.6141060590744019} 08/30/2021 20:48:36 - INFO - __main__ - Step 42422: {'lr': 0.000413485001307383, 'samples': 8145024, 'steps': 42421, 'loss/train': 1.1245355606079102} 08/30/2021 20:48:37 - INFO - __main__ - Step 42423: {'lr': 0.00041348098647216993, 'samples': 8145216, 'steps': 42422, 'loss/train': 1.54545259475708} 08/30/2021 20:48:38 - INFO - __main__ - Step 42424: {'lr': 0.00041347697156329485, 'samples': 8145408, 'steps': 42423, 'loss/train': 1.2535576820373535} 08/30/2021 20:48:38 - INFO - __main__ - Step 42425: {'lr': 0.00041347295658075955, 'samples': 8145600, 'steps': 42424, 'loss/train': 1.6858940124511719} 08/30/2021 20:48:38 - INFO - __main__ - Step 42426: {'lr': 0.00041346894152456584, 'samples': 8145792, 'steps': 42425, 'loss/train': 1.5264227390289307} 08/30/2021 20:48:39 - INFO - __main__ - Step 42427: {'lr': 0.00041346492639471555, 'samples': 8145984, 'steps': 42426, 'loss/train': 1.5428723096847534} 08/30/2021 20:48:40 - INFO - __main__ - Step 42428: {'lr': 0.0004134609111912105, 'samples': 8146176, 'steps': 42427, 'loss/train': 1.4447158575057983} 08/30/2021 20:48:41 - INFO - __main__ - Step 42429: {'lr': 0.00041345689591405256, 'samples': 8146368, 'steps': 42428, 'loss/train': 0.8225834965705872} 08/30/2021 20:48:41 - INFO - __main__ - Step 42430: {'lr': 0.0004134528805632434, 'samples': 8146560, 'steps': 42429, 'loss/train': 1.8460559844970703} 08/30/2021 20:48:41 - INFO - __main__ - Step 42431: {'lr': 0.00041344886513878485, 'samples': 8146752, 'steps': 42430, 'loss/train': 1.1114012002944946} 08/30/2021 20:48:42 - INFO - __main__ - Step 42432: {'lr': 0.00041344484964067873, 'samples': 8146944, 'steps': 42431, 'loss/train': 1.7520263195037842} 08/30/2021 20:48:44 - INFO - __main__ - Step 42433: {'lr': 0.00041344083406892704, 'samples': 8147136, 'steps': 42432, 'loss/train': 1.3878406286239624} 08/30/2021 20:48:44 - INFO - __main__ - Step 42434: {'lr': 0.0004134368184235313, 'samples': 8147328, 'steps': 42433, 'loss/train': 1.199316382408142} 08/30/2021 20:48:45 - INFO - __main__ - Step 42435: {'lr': 0.0004134328027044935, 'samples': 8147520, 'steps': 42434, 'loss/train': 1.25644052028656} 08/30/2021 20:48:45 - INFO - __main__ - Step 42436: {'lr': 0.0004134287869118154, 'samples': 8147712, 'steps': 42435, 'loss/train': 3.500422239303589} 08/30/2021 20:48:45 - INFO - __main__ - Step 42437: {'lr': 0.0004134247710454988, 'samples': 8147904, 'steps': 42436, 'loss/train': 0.9930896162986755} 08/30/2021 20:48:47 - INFO - __main__ - Step 42438: {'lr': 0.00041342075510554554, 'samples': 8148096, 'steps': 42437, 'loss/train': 1.6353338956832886} 08/30/2021 20:48:47 - INFO - __main__ - Step 42439: {'lr': 0.0004134167390919574, 'samples': 8148288, 'steps': 42438, 'loss/train': 1.2115516662597656} 08/30/2021 20:48:48 - INFO - __main__ - Step 42440: {'lr': 0.0004134127230047362, 'samples': 8148480, 'steps': 42439, 'loss/train': 1.7827893495559692} 08/30/2021 20:48:48 - INFO - __main__ - Step 42441: {'lr': 0.00041340870684388375, 'samples': 8148672, 'steps': 42440, 'loss/train': 1.2603460550308228} 08/30/2021 20:48:48 - INFO - __main__ - Step 42442: {'lr': 0.00041340469060940183, 'samples': 8148864, 'steps': 42441, 'loss/train': 1.1322824954986572} 08/30/2021 20:48:50 - INFO - __main__ - Step 42443: {'lr': 0.0004134006743012923, 'samples': 8149056, 'steps': 42442, 'loss/train': 1.6862225532531738} 08/30/2021 20:48:50 - INFO - __main__ - Step 42444: {'lr': 0.00041339665791955695, 'samples': 8149248, 'steps': 42443, 'loss/train': 1.663807988166809} 08/30/2021 20:48:51 - INFO - __main__ - Step 42445: {'lr': 0.00041339264146419757, 'samples': 8149440, 'steps': 42444, 'loss/train': 1.8957269191741943} 08/30/2021 20:48:51 - INFO - __main__ - Step 42446: {'lr': 0.000413388624935216, 'samples': 8149632, 'steps': 42445, 'loss/train': 1.2831565141677856} 08/30/2021 20:48:51 - INFO - __main__ - Step 42447: {'lr': 0.00041338460833261403, 'samples': 8149824, 'steps': 42446, 'loss/train': 1.7989166975021362} 08/30/2021 20:48:52 - INFO - __main__ - Step 42448: {'lr': 0.0004133805916563935, 'samples': 8150016, 'steps': 42447, 'loss/train': 1.447562336921692} 08/30/2021 20:48:53 - INFO - __main__ - Step 42449: {'lr': 0.00041337657490655625, 'samples': 8150208, 'steps': 42448, 'loss/train': 1.2173305749893188} 08/30/2021 20:48:54 - INFO - __main__ - Step 42450: {'lr': 0.00041337255808310394, 'samples': 8150400, 'steps': 42449, 'loss/train': 1.344080924987793} 08/30/2021 20:48:54 - INFO - __main__ - Step 42451: {'lr': 0.0004133685411860385, 'samples': 8150592, 'steps': 42450, 'loss/train': 1.2352086305618286} 08/30/2021 20:48:54 - INFO - __main__ - Step 42452: {'lr': 0.0004133645242153617, 'samples': 8150784, 'steps': 42451, 'loss/train': 1.5105088949203491} 08/30/2021 20:48:55 - INFO - __main__ - Step 42453: {'lr': 0.0004133605071710754, 'samples': 8150976, 'steps': 42452, 'loss/train': 1.3102952241897583} 08/30/2021 20:48:56 - INFO - __main__ - Step 42454: {'lr': 0.00041335649005318133, 'samples': 8151168, 'steps': 42453, 'loss/train': 1.5437383651733398} 08/30/2021 20:48:56 - INFO - __main__ - Step 42455: {'lr': 0.0004133524728616814, 'samples': 8151360, 'steps': 42454, 'loss/train': 1.6159123182296753} 08/30/2021 20:48:57 - INFO - __main__ - Step 42456: {'lr': 0.00041334845559657735, 'samples': 8151552, 'steps': 42455, 'loss/train': 1.3256717920303345} 08/30/2021 20:48:57 - INFO - __main__ - Step 42457: {'lr': 0.00041334443825787097, 'samples': 8151744, 'steps': 42456, 'loss/train': 1.9957058429718018} 08/30/2021 20:48:57 - INFO - __main__ - Step 42458: {'lr': 0.0004133404208455642, 'samples': 8151936, 'steps': 42457, 'loss/train': 1.4002066850662231} 08/30/2021 20:48:59 - INFO - __main__ - Step 42459: {'lr': 0.00041333640335965865, 'samples': 8152128, 'steps': 42458, 'loss/train': 1.3307198286056519} 08/30/2021 20:49:00 - INFO - __main__ - Step 42460: {'lr': 0.0004133323858001563, 'samples': 8152320, 'steps': 42459, 'loss/train': 1.5307797193527222} 08/30/2021 20:49:00 - INFO - __main__ - Step 42461: {'lr': 0.0004133283681670589, 'samples': 8152512, 'steps': 42460, 'loss/train': 1.557697057723999} 08/30/2021 20:49:00 - INFO - __main__ - Step 42462: {'lr': 0.0004133243504603682, 'samples': 8152704, 'steps': 42461, 'loss/train': 1.1681164503097534} 08/30/2021 20:49:01 - INFO - __main__ - Step 42463: {'lr': 0.0004133203326800861, 'samples': 8152896, 'steps': 42462, 'loss/train': 1.160837173461914} 08/30/2021 20:49:02 - INFO - __main__ - Step 42464: {'lr': 0.0004133163148262144, 'samples': 8153088, 'steps': 42463, 'loss/train': 1.4581665992736816} 08/30/2021 20:49:03 - INFO - __main__ - Step 42465: {'lr': 0.00041331229689875487, 'samples': 8153280, 'steps': 42464, 'loss/train': 1.4419481754302979} 08/30/2021 20:49:03 - INFO - __main__ - Step 42466: {'lr': 0.0004133082788977093, 'samples': 8153472, 'steps': 42465, 'loss/train': 1.2427361011505127} 08/30/2021 20:49:04 - INFO - __main__ - Step 42467: {'lr': 0.00041330426082307963, 'samples': 8153664, 'steps': 42466, 'loss/train': 1.6228910684585571} 08/30/2021 20:49:04 - INFO - __main__ - Step 42468: {'lr': 0.0004133002426748675, 'samples': 8153856, 'steps': 42467, 'loss/train': 1.0492117404937744} 08/30/2021 20:49:05 - INFO - __main__ - Step 42469: {'lr': 0.0004132962244530749, 'samples': 8154048, 'steps': 42468, 'loss/train': 1.7547143697738647} 08/30/2021 20:49:06 - INFO - __main__ - Step 42470: {'lr': 0.0004132922061577035, 'samples': 8154240, 'steps': 42469, 'loss/train': 2.085209846496582} 08/30/2021 20:49:06 - INFO - __main__ - Step 42471: {'lr': 0.0004132881877887551, 'samples': 8154432, 'steps': 42470, 'loss/train': 1.7114394903182983} 08/30/2021 20:49:06 - INFO - __main__ - Step 42472: {'lr': 0.0004132841693462315, 'samples': 8154624, 'steps': 42471, 'loss/train': 1.3582477569580078} 08/30/2021 20:49:07 - INFO - __main__ - Step 42473: {'lr': 0.0004132801508301347, 'samples': 8154816, 'steps': 42472, 'loss/train': 1.6064342260360718} 08/30/2021 20:49:08 - INFO - __main__ - Step 42474: {'lr': 0.0004132761322404663, 'samples': 8155008, 'steps': 42473, 'loss/train': 1.0829704999923706} 08/30/2021 20:49:09 - INFO - __main__ - Step 42475: {'lr': 0.00041327211357722825, 'samples': 8155200, 'steps': 42474, 'loss/train': 1.2835875749588013} 08/30/2021 20:49:09 - INFO - __main__ - Step 42476: {'lr': 0.00041326809484042235, 'samples': 8155392, 'steps': 42475, 'loss/train': 0.7128322124481201} 08/30/2021 20:49:10 - INFO - __main__ - Step 42477: {'lr': 0.0004132640760300503, 'samples': 8155584, 'steps': 42476, 'loss/train': 1.240614652633667} 08/30/2021 20:49:10 - INFO - __main__ - Step 42478: {'lr': 0.000413260057146114, 'samples': 8155776, 'steps': 42477, 'loss/train': 1.553532600402832} 08/30/2021 20:49:11 - INFO - __main__ - Step 42479: {'lr': 0.00041325603818861517, 'samples': 8155968, 'steps': 42478, 'loss/train': 1.4823521375656128} 08/30/2021 20:49:12 - INFO - __main__ - Step 42480: {'lr': 0.0004132520191575558, 'samples': 8156160, 'steps': 42479, 'loss/train': 0.9626538753509521} 08/30/2021 20:49:12 - INFO - __main__ - Step 42481: {'lr': 0.0004132480000529375, 'samples': 8156352, 'steps': 42480, 'loss/train': 1.4451993703842163} 08/30/2021 20:49:12 - INFO - __main__ - Step 42482: {'lr': 0.0004132439808747622, 'samples': 8156544, 'steps': 42481, 'loss/train': 1.4184468984603882} 08/30/2021 20:49:13 - INFO - __main__ - Step 42483: {'lr': 0.00041323996162303167, 'samples': 8156736, 'steps': 42482, 'loss/train': 1.3234270811080933} 08/30/2021 20:49:14 - INFO - __main__ - Step 42484: {'lr': 0.0004132359422977477, 'samples': 8156928, 'steps': 42483, 'loss/train': 1.406661868095398} 08/30/2021 20:49:15 - INFO - __main__ - Step 42485: {'lr': 0.0004132319228989122, 'samples': 8157120, 'steps': 42484, 'loss/train': 1.8578543663024902} 08/30/2021 20:49:15 - INFO - __main__ - Step 42486: {'lr': 0.00041322790342652695, 'samples': 8157312, 'steps': 42485, 'loss/train': 1.0198510885238647} 08/30/2021 20:49:16 - INFO - __main__ - Step 42487: {'lr': 0.00041322388388059366, 'samples': 8157504, 'steps': 42486, 'loss/train': 1.4509892463684082} 08/30/2021 20:49:16 - INFO - __main__ - Step 42488: {'lr': 0.0004132198642611142, 'samples': 8157696, 'steps': 42487, 'loss/train': 1.0758757591247559} 08/30/2021 20:49:16 - INFO - __main__ - Step 42489: {'lr': 0.0004132158445680904, 'samples': 8157888, 'steps': 42488, 'loss/train': 0.9270089268684387} 08/30/2021 20:49:18 - INFO - __main__ - Step 42490: {'lr': 0.0004132118248015241, 'samples': 8158080, 'steps': 42489, 'loss/train': 1.3946577310562134} 08/30/2021 20:49:19 - INFO - __main__ - Step 42491: {'lr': 0.000413207804961417, 'samples': 8158272, 'steps': 42490, 'loss/train': 1.0323116779327393} 08/30/2021 20:49:19 - INFO - __main__ - Step 42492: {'lr': 0.000413203785047771, 'samples': 8158464, 'steps': 42491, 'loss/train': 0.9179449677467346} 08/30/2021 20:49:20 - INFO - __main__ - Step 42493: {'lr': 0.00041319976506058785, 'samples': 8158656, 'steps': 42492, 'loss/train': 1.4155821800231934} 08/30/2021 20:49:20 - INFO - __main__ - Step 42494: {'lr': 0.00041319574499986957, 'samples': 8158848, 'steps': 42493, 'loss/train': 1.4145019054412842} 08/30/2021 20:49:21 - INFO - __main__ - Step 42495: {'lr': 0.0004131917248656177, 'samples': 8159040, 'steps': 42494, 'loss/train': 1.4065266847610474} 08/30/2021 20:49:22 - INFO - __main__ - Step 42496: {'lr': 0.0004131877046578341, 'samples': 8159232, 'steps': 42495, 'loss/train': 1.091234564781189} 08/30/2021 20:49:22 - INFO - __main__ - Step 42497: {'lr': 0.0004131836843765207, 'samples': 8159424, 'steps': 42496, 'loss/train': 1.2532246112823486} 08/30/2021 20:49:23 - INFO - __main__ - Step 42498: {'lr': 0.00041317966402167923, 'samples': 8159616, 'steps': 42497, 'loss/train': 1.2371271848678589} 08/30/2021 20:49:23 - INFO - __main__ - Step 42499: {'lr': 0.0004131756435933115, 'samples': 8159808, 'steps': 42498, 'loss/train': 1.3292351961135864} 08/30/2021 20:49:24 - INFO - __main__ - Step 42500: {'lr': 0.00041317162309141944, 'samples': 8160000, 'steps': 42499, 'loss/train': 1.3966660499572754} 08/30/2021 20:49:25 - INFO - __main__ - Step 42501: {'lr': 0.00041316760251600474, 'samples': 8160192, 'steps': 42500, 'loss/train': 1.6189367771148682} 08/30/2021 20:49:25 - INFO - __main__ - Step 42502: {'lr': 0.00041316358186706915, 'samples': 8160384, 'steps': 42501, 'loss/train': 1.6204622983932495} 08/30/2021 20:49:26 - INFO - __main__ - Step 42503: {'lr': 0.0004131595611446146, 'samples': 8160576, 'steps': 42502, 'loss/train': 1.3200327157974243} 08/30/2021 20:49:26 - INFO - __main__ - Step 42504: {'lr': 0.0004131555403486429, 'samples': 8160768, 'steps': 42503, 'loss/train': 0.7993461489677429} 08/30/2021 20:49:28 - INFO - __main__ - Step 42505: {'lr': 0.00041315151947915577, 'samples': 8160960, 'steps': 42504, 'loss/train': 1.470508098602295} 08/30/2021 20:49:28 - INFO - __main__ - Step 42506: {'lr': 0.0004131474985361551, 'samples': 8161152, 'steps': 42505, 'loss/train': 1.4613349437713623} 08/30/2021 20:49:28 - INFO - __main__ - Step 42507: {'lr': 0.0004131434775196428, 'samples': 8161344, 'steps': 42506, 'loss/train': 1.308729887008667} 08/30/2021 20:49:29 - INFO - __main__ - Step 42508: {'lr': 0.0004131394564296205, 'samples': 8161536, 'steps': 42507, 'loss/train': 0.7662352323532104} 08/30/2021 20:49:29 - INFO - __main__ - Step 42509: {'lr': 0.00041313543526609, 'samples': 8161728, 'steps': 42508, 'loss/train': 1.3929641246795654} 08/30/2021 20:49:31 - INFO - __main__ - Step 42510: {'lr': 0.00041313141402905324, 'samples': 8161920, 'steps': 42509, 'loss/train': 1.1557228565216064} 08/30/2021 20:49:32 - INFO - __main__ - Step 42511: {'lr': 0.00041312739271851196, 'samples': 8162112, 'steps': 42510, 'loss/train': 0.04168722778558731} 08/30/2021 20:49:32 - INFO - __main__ - Step 42512: {'lr': 0.0004131233713344681, 'samples': 8162304, 'steps': 42511, 'loss/train': 1.5663254261016846} 08/30/2021 20:49:32 - INFO - __main__ - Step 42513: {'lr': 0.0004131193498769232, 'samples': 8162496, 'steps': 42512, 'loss/train': 1.2366207838058472} 08/30/2021 20:49:33 - INFO - __main__ - Step 42514: {'lr': 0.0004131153283458794, 'samples': 8162688, 'steps': 42513, 'loss/train': 1.5431313514709473} 08/30/2021 20:49:33 - INFO - __main__ - Step 42515: {'lr': 0.00041311130674133824, 'samples': 8162880, 'steps': 42514, 'loss/train': 1.900691270828247} 08/30/2021 20:49:35 - INFO - __main__ - Step 42516: {'lr': 0.0004131072850633017, 'samples': 8163072, 'steps': 42515, 'loss/train': 3.089237928390503} 08/30/2021 20:49:35 - INFO - __main__ - Step 42517: {'lr': 0.0004131032633117715, 'samples': 8163264, 'steps': 42516, 'loss/train': 1.9592214822769165} 08/30/2021 20:49:35 - INFO - __main__ - Step 42518: {'lr': 0.0004130992414867495, 'samples': 8163456, 'steps': 42517, 'loss/train': 1.484342336654663} 08/30/2021 20:49:36 - INFO - __main__ - Step 42519: {'lr': 0.0004130952195882375, 'samples': 8163648, 'steps': 42518, 'loss/train': 0.9774752855300903} 08/30/2021 20:49:36 - INFO - __main__ - Step 42520: {'lr': 0.0004130911976162373, 'samples': 8163840, 'steps': 42519, 'loss/train': 2.4007885456085205} 08/30/2021 20:49:36 - INFO - __main__ - Step 42521: {'lr': 0.0004130871755707508, 'samples': 8164032, 'steps': 42520, 'loss/train': 2.6587793827056885} 08/30/2021 20:49:38 - INFO - __main__ - Step 42522: {'lr': 0.0004130831534517796, 'samples': 8164224, 'steps': 42521, 'loss/train': 1.5851733684539795} 08/30/2021 20:49:38 - INFO - __main__ - Step 42523: {'lr': 0.00041307913125932574, 'samples': 8164416, 'steps': 42522, 'loss/train': 1.733384609222412} 08/30/2021 20:49:39 - INFO - __main__ - Step 42524: {'lr': 0.00041307510899339097, 'samples': 8164608, 'steps': 42523, 'loss/train': 1.9815850257873535} 08/30/2021 20:49:39 - INFO - __main__ - Step 42525: {'lr': 0.00041307108665397695, 'samples': 8164800, 'steps': 42524, 'loss/train': 1.700609803199768} 08/30/2021 20:49:39 - INFO - __main__ - Step 42526: {'lr': 0.00041306706424108563, 'samples': 8164992, 'steps': 42525, 'loss/train': 1.851414680480957} 08/30/2021 20:49:41 - INFO - __main__ - Step 42527: {'lr': 0.0004130630417547189, 'samples': 8165184, 'steps': 42526, 'loss/train': 0.22715997695922852} 08/30/2021 20:49:41 - INFO - __main__ - Step 42528: {'lr': 0.00041305901919487845, 'samples': 8165376, 'steps': 42527, 'loss/train': 1.1178879737854004} 08/30/2021 20:49:42 - INFO - __main__ - Step 42529: {'lr': 0.0004130549965615661, 'samples': 8165568, 'steps': 42528, 'loss/train': 1.2869858741760254} 08/30/2021 20:49:42 - INFO - __main__ - Step 42530: {'lr': 0.00041305097385478375, 'samples': 8165760, 'steps': 42529, 'loss/train': 1.551637053489685} 08/30/2021 20:49:42 - INFO - __main__ - Step 42531: {'lr': 0.00041304695107453307, 'samples': 8165952, 'steps': 42530, 'loss/train': 1.540576457977295} 08/30/2021 20:49:44 - INFO - __main__ - Step 42532: {'lr': 0.000413042928220816, 'samples': 8166144, 'steps': 42531, 'loss/train': 1.5075185298919678} 08/30/2021 20:49:44 - INFO - __main__ - Step 42533: {'lr': 0.0004130389052936342, 'samples': 8166336, 'steps': 42532, 'loss/train': 1.7715404033660889} 08/30/2021 20:49:45 - INFO - __main__ - Step 42534: {'lr': 0.0004130348822929897, 'samples': 8166528, 'steps': 42533, 'loss/train': 1.2812774181365967} 08/30/2021 20:49:45 - INFO - __main__ - Step 42535: {'lr': 0.0004130308592188842, 'samples': 8166720, 'steps': 42534, 'loss/train': 1.3679696321487427} 08/30/2021 20:49:45 - INFO - __main__ - Step 42536: {'lr': 0.0004130268360713194, 'samples': 8166912, 'steps': 42535, 'loss/train': 1.3101842403411865} 08/30/2021 20:49:47 - INFO - __main__ - Step 42537: {'lr': 0.0004130228128502973, 'samples': 8167104, 'steps': 42536, 'loss/train': 0.7195220589637756} 08/30/2021 20:49:48 - INFO - __main__ - Step 42538: {'lr': 0.0004130187895558196, 'samples': 8167296, 'steps': 42537, 'loss/train': 1.4899779558181763} 08/30/2021 20:49:48 - INFO - __main__ - Step 42539: {'lr': 0.00041301476618788827, 'samples': 8167488, 'steps': 42538, 'loss/train': 1.2303898334503174} 08/30/2021 20:49:48 - INFO - __main__ - Step 42540: {'lr': 0.0004130107427465049, 'samples': 8167680, 'steps': 42539, 'loss/train': 2.069544792175293} 08/30/2021 20:49:49 - INFO - __main__ - Step 42541: {'lr': 0.00041300671923167145, 'samples': 8167872, 'steps': 42540, 'loss/train': 1.3896760940551758} 08/30/2021 20:49:49 - INFO - __main__ - Step 42542: {'lr': 0.00041300269564338956, 'samples': 8168064, 'steps': 42541, 'loss/train': 1.662202000617981} 08/30/2021 20:49:51 - INFO - __main__ - Step 42543: {'lr': 0.0004129986719816613, 'samples': 8168256, 'steps': 42542, 'loss/train': 1.1935375928878784} 08/30/2021 20:49:52 - INFO - __main__ - Step 42544: {'lr': 0.0004129946482464883, 'samples': 8168448, 'steps': 42543, 'loss/train': 1.8810354471206665} 08/30/2021 20:49:52 - INFO - __main__ - Step 42545: {'lr': 0.0004129906244378724, 'samples': 8168640, 'steps': 42544, 'loss/train': 1.8081306219100952} 08/30/2021 20:49:52 - INFO - __main__ - Step 42546: {'lr': 0.0004129866005558155, 'samples': 8168832, 'steps': 42545, 'loss/train': 1.1107478141784668} 08/30/2021 20:49:53 - INFO - __main__ - Step 42547: {'lr': 0.00041298257660031935, 'samples': 8169024, 'steps': 42546, 'loss/train': 1.7478294372558594} 08/30/2021 20:49:54 - INFO - __main__ - Step 42548: {'lr': 0.00041297855257138577, 'samples': 8169216, 'steps': 42547, 'loss/train': 1.5327491760253906} 08/30/2021 20:49:55 - INFO - __main__ - Step 42549: {'lr': 0.0004129745284690165, 'samples': 8169408, 'steps': 42548, 'loss/train': 1.8275268077850342} 08/30/2021 20:49:55 - INFO - __main__ - Step 42550: {'lr': 0.0004129705042932135, 'samples': 8169600, 'steps': 42549, 'loss/train': 1.6237115859985352} 08/30/2021 20:49:56 - INFO - __main__ - Step 42551: {'lr': 0.0004129664800439785, 'samples': 8169792, 'steps': 42550, 'loss/train': 1.6580188274383545} 08/30/2021 20:49:56 - INFO - __main__ - Step 42552: {'lr': 0.0004129624557213133, 'samples': 8169984, 'steps': 42551, 'loss/train': 0.9206991791725159} 08/30/2021 20:49:57 - INFO - __main__ - Step 42553: {'lr': 0.00041295843132521973, 'samples': 8170176, 'steps': 42552, 'loss/train': 1.4790221452713013} 08/30/2021 20:49:58 - INFO - __main__ - Step 42554: {'lr': 0.0004129544068556996, 'samples': 8170368, 'steps': 42553, 'loss/train': 1.334619402885437} 08/30/2021 20:49:58 - INFO - __main__ - Step 42555: {'lr': 0.00041295038231275473, 'samples': 8170560, 'steps': 42554, 'loss/train': 1.3303892612457275} 08/30/2021 20:49:59 - INFO - __main__ - Step 42556: {'lr': 0.0004129463576963869, 'samples': 8170752, 'steps': 42555, 'loss/train': 1.7905478477478027} 08/30/2021 20:49:59 - INFO - __main__ - Step 42557: {'lr': 0.000412942333006598, 'samples': 8170944, 'steps': 42556, 'loss/train': 1.8300361633300781} 08/30/2021 20:50:00 - INFO - __main__ - Step 42558: {'lr': 0.0004129383082433898, 'samples': 8171136, 'steps': 42557, 'loss/train': 1.423487663269043} 08/30/2021 20:50:01 - INFO - __main__ - Step 42559: {'lr': 0.0004129342834067641, 'samples': 8171328, 'steps': 42558, 'loss/train': 0.595382809638977} 08/30/2021 20:50:01 - INFO - __main__ - Step 42560: {'lr': 0.0004129302584967227, 'samples': 8171520, 'steps': 42559, 'loss/train': 0.5447129011154175} 08/30/2021 20:50:02 - INFO - __main__ - Step 42561: {'lr': 0.0004129262335132675, 'samples': 8171712, 'steps': 42560, 'loss/train': 1.147903561592102} 08/30/2021 20:50:02 - INFO - __main__ - Step 42562: {'lr': 0.00041292220845640023, 'samples': 8171904, 'steps': 42561, 'loss/train': 1.5784170627593994} 08/30/2021 20:50:03 - INFO - __main__ - Step 42563: {'lr': 0.00041291818332612275, 'samples': 8172096, 'steps': 42562, 'loss/train': 1.3214142322540283} 08/30/2021 20:50:04 - INFO - __main__ - Step 42564: {'lr': 0.00041291415812243676, 'samples': 8172288, 'steps': 42563, 'loss/train': 1.2969063520431519} 08/30/2021 20:50:04 - INFO - __main__ - Step 42565: {'lr': 0.0004129101328453442, 'samples': 8172480, 'steps': 42564, 'loss/train': 1.8963228464126587} 08/30/2021 20:50:05 - INFO - __main__ - Step 42566: {'lr': 0.0004129061074948469, 'samples': 8172672, 'steps': 42565, 'loss/train': 0.8637040853500366} 08/30/2021 20:50:05 - INFO - __main__ - Step 42567: {'lr': 0.0004129020820709466, 'samples': 8172864, 'steps': 42566, 'loss/train': 1.4360512495040894} 08/30/2021 20:50:05 - INFO - __main__ - Step 42568: {'lr': 0.00041289805657364516, 'samples': 8173056, 'steps': 42567, 'loss/train': 1.4814757108688354} 08/30/2021 20:50:07 - INFO - __main__ - Step 42569: {'lr': 0.0004128940310029443, 'samples': 8173248, 'steps': 42568, 'loss/train': 1.460622787475586} 08/30/2021 20:50:07 - INFO - __main__ - Step 42570: {'lr': 0.0004128900053588459, 'samples': 8173440, 'steps': 42569, 'loss/train': 1.2954845428466797} 08/30/2021 20:50:08 - INFO - __main__ - Step 42571: {'lr': 0.00041288597964135186, 'samples': 8173632, 'steps': 42570, 'loss/train': 1.1991653442382812} 08/30/2021 20:50:08 - INFO - __main__ - Step 42572: {'lr': 0.0004128819538504639, 'samples': 8173824, 'steps': 42571, 'loss/train': 1.2448238134384155} 08/30/2021 20:50:08 - INFO - __main__ - Step 42573: {'lr': 0.00041287792798618374, 'samples': 8174016, 'steps': 42572, 'loss/train': 1.7913423776626587} 08/30/2021 20:50:10 - INFO - __main__ - Step 42574: {'lr': 0.00041287390204851343, 'samples': 8174208, 'steps': 42573, 'loss/train': 1.2062824964523315} 08/30/2021 20:50:10 - INFO - __main__ - Step 42575: {'lr': 0.0004128698760374546, 'samples': 8174400, 'steps': 42574, 'loss/train': 1.3583638668060303} 08/30/2021 20:50:11 - INFO - __main__ - Step 42576: {'lr': 0.0004128658499530091, 'samples': 8174592, 'steps': 42575, 'loss/train': 1.3554943799972534} 08/30/2021 20:50:11 - INFO - __main__ - Step 42577: {'lr': 0.00041286182379517876, 'samples': 8174784, 'steps': 42576, 'loss/train': 1.3241122961044312} 08/30/2021 20:50:11 - INFO - __main__ - Step 42578: {'lr': 0.00041285779756396543, 'samples': 8174976, 'steps': 42577, 'loss/train': 1.5234028100967407} 08/30/2021 20:50:13 - INFO - __main__ - Step 42579: {'lr': 0.00041285377125937085, 'samples': 8175168, 'steps': 42578, 'loss/train': 1.1367021799087524} 08/30/2021 20:50:13 - INFO - __main__ - Step 42580: {'lr': 0.0004128497448813969, 'samples': 8175360, 'steps': 42579, 'loss/train': 1.0235539674758911} 08/30/2021 20:50:13 - INFO - __main__ - Step 42581: {'lr': 0.0004128457184300454, 'samples': 8175552, 'steps': 42580, 'loss/train': 1.264026403427124} 08/30/2021 20:50:14 - INFO - __main__ - Step 42582: {'lr': 0.0004128416919053181, 'samples': 8175744, 'steps': 42581, 'loss/train': 1.6446257829666138} 08/30/2021 20:50:14 - INFO - __main__ - Step 42583: {'lr': 0.0004128376653072168, 'samples': 8175936, 'steps': 42582, 'loss/train': 2.0228919982910156} 08/30/2021 20:50:16 - INFO - __main__ - Step 42584: {'lr': 0.0004128336386357434, 'samples': 8176128, 'steps': 42583, 'loss/train': 0.9513541460037231} 08/30/2021 20:50:16 - INFO - __main__ - Step 42585: {'lr': 0.0004128296118908997, 'samples': 8176320, 'steps': 42584, 'loss/train': 0.9187955856323242} 08/30/2021 20:50:16 - INFO - __main__ - Step 42586: {'lr': 0.0004128255850726874, 'samples': 8176512, 'steps': 42585, 'loss/train': 1.342198133468628} 08/30/2021 20:50:17 - INFO - __main__ - Step 42587: {'lr': 0.0004128215581811085, 'samples': 8176704, 'steps': 42586, 'loss/train': 1.0489925146102905} 08/30/2021 20:50:17 - INFO - __main__ - Step 42588: {'lr': 0.0004128175312161647, 'samples': 8176896, 'steps': 42587, 'loss/train': 1.5324856042861938} 08/30/2021 20:50:19 - INFO - __main__ - Step 42589: {'lr': 0.00041281350417785777, 'samples': 8177088, 'steps': 42588, 'loss/train': 1.1539678573608398} 08/30/2021 20:50:19 - INFO - __main__ - Step 42590: {'lr': 0.00041280947706618965, 'samples': 8177280, 'steps': 42589, 'loss/train': 1.7433608770370483} 08/30/2021 20:50:19 - INFO - __main__ - Step 42591: {'lr': 0.0004128054498811621, 'samples': 8177472, 'steps': 42590, 'loss/train': 1.2905824184417725} 08/30/2021 20:50:20 - INFO - __main__ - Step 42592: {'lr': 0.0004128014226227769, 'samples': 8177664, 'steps': 42591, 'loss/train': 0.9582744836807251} 08/30/2021 20:50:20 - INFO - __main__ - Step 42593: {'lr': 0.00041279739529103586, 'samples': 8177856, 'steps': 42592, 'loss/train': 0.974994957447052} 08/30/2021 20:50:22 - INFO - __main__ - Step 42594: {'lr': 0.0004127933678859409, 'samples': 8178048, 'steps': 42593, 'loss/train': 1.4279515743255615} 08/30/2021 20:50:22 - INFO - __main__ - Step 42595: {'lr': 0.00041278934040749375, 'samples': 8178240, 'steps': 42594, 'loss/train': 1.3299150466918945} 08/30/2021 20:50:22 - INFO - __main__ - Step 42596: {'lr': 0.0004127853128556962, 'samples': 8178432, 'steps': 42595, 'loss/train': 0.41914287209510803} 08/30/2021 20:50:23 - INFO - __main__ - Step 42597: {'lr': 0.00041278128523055015, 'samples': 8178624, 'steps': 42596, 'loss/train': 1.0886958837509155} 08/30/2021 20:50:23 - INFO - __main__ - Step 42598: {'lr': 0.0004127772575320573, 'samples': 8178816, 'steps': 42597, 'loss/train': 1.7218480110168457} 08/30/2021 20:50:25 - INFO - __main__ - Step 42599: {'lr': 0.0004127732297602196, 'samples': 8179008, 'steps': 42598, 'loss/train': 1.7389047145843506} 08/30/2021 20:50:25 - INFO - __main__ - Step 42600: {'lr': 0.0004127692019150387, 'samples': 8179200, 'steps': 42599, 'loss/train': 1.8176203966140747} 08/30/2021 20:50:26 - INFO - __main__ - Step 42601: {'lr': 0.00041276517399651657, 'samples': 8179392, 'steps': 42600, 'loss/train': 1.3899518251419067} 08/30/2021 20:50:26 - INFO - __main__ - Step 42602: {'lr': 0.00041276114600465497, 'samples': 8179584, 'steps': 42601, 'loss/train': 1.1477563381195068} 08/30/2021 20:50:26 - INFO - __main__ - Step 42603: {'lr': 0.0004127571179394557, 'samples': 8179776, 'steps': 42602, 'loss/train': 1.45731782913208} 08/30/2021 20:50:27 - INFO - __main__ - Step 42604: {'lr': 0.0004127530898009205, 'samples': 8179968, 'steps': 42603, 'loss/train': 1.2893725633621216} 08/30/2021 20:50:28 - INFO - __main__ - Step 42605: {'lr': 0.00041274906158905137, 'samples': 8180160, 'steps': 42604, 'loss/train': 0.9913890361785889} 08/30/2021 20:50:29 - INFO - __main__ - Step 42606: {'lr': 0.00041274503330384997, 'samples': 8180352, 'steps': 42605, 'loss/train': 0.5048430562019348} 08/30/2021 20:50:29 - INFO - __main__ - Step 42607: {'lr': 0.0004127410049453182, 'samples': 8180544, 'steps': 42606, 'loss/train': 1.211820363998413} 08/30/2021 20:50:30 - INFO - __main__ - Step 42608: {'lr': 0.00041273697651345785, 'samples': 8180736, 'steps': 42607, 'loss/train': 1.0460318326950073} 08/30/2021 20:50:30 - INFO - __main__ - Step 42609: {'lr': 0.00041273294800827075, 'samples': 8180928, 'steps': 42608, 'loss/train': 1.3623193502426147} 08/30/2021 20:50:31 - INFO - __main__ - Step 42610: {'lr': 0.00041272891942975863, 'samples': 8181120, 'steps': 42609, 'loss/train': 1.2552400827407837} 08/30/2021 20:50:32 - INFO - __main__ - Step 42611: {'lr': 0.00041272489077792343, 'samples': 8181312, 'steps': 42610, 'loss/train': 1.045832633972168} 08/30/2021 20:50:32 - INFO - __main__ - Step 42612: {'lr': 0.0004127208620527669, 'samples': 8181504, 'steps': 42611, 'loss/train': 0.9717525839805603} 08/30/2021 20:50:33 - INFO - __main__ - Step 42613: {'lr': 0.00041271683325429075, 'samples': 8181696, 'steps': 42612, 'loss/train': 0.8153554797172546} 08/30/2021 20:50:33 - INFO - __main__ - Step 42614: {'lr': 0.00041271280438249705, 'samples': 8181888, 'steps': 42613, 'loss/train': 1.4658877849578857} 08/30/2021 20:50:35 - INFO - __main__ - Step 42615: {'lr': 0.00041270877543738744, 'samples': 8182080, 'steps': 42614, 'loss/train': 1.6607701778411865} 08/30/2021 20:50:35 - INFO - __main__ - Step 42616: {'lr': 0.0004127047464189637, 'samples': 8182272, 'steps': 42615, 'loss/train': 1.2117866277694702} 08/30/2021 20:50:35 - INFO - __main__ - Step 42617: {'lr': 0.0004127007173272278, 'samples': 8182464, 'steps': 42616, 'loss/train': 1.2703490257263184} 08/30/2021 20:50:36 - INFO - __main__ - Step 42618: {'lr': 0.0004126966881621814, 'samples': 8182656, 'steps': 42617, 'loss/train': 1.5068018436431885} 08/30/2021 20:50:36 - INFO - __main__ - Step 42619: {'lr': 0.0004126926589238264, 'samples': 8182848, 'steps': 42618, 'loss/train': 1.1753032207489014} 08/30/2021 20:50:38 - INFO - __main__ - Step 42620: {'lr': 0.00041268862961216457, 'samples': 8183040, 'steps': 42619, 'loss/train': 1.5578181743621826} 08/30/2021 20:50:38 - INFO - __main__ - Step 42621: {'lr': 0.00041268460022719783, 'samples': 8183232, 'steps': 42620, 'loss/train': 1.3847417831420898} 08/30/2021 20:50:38 - INFO - __main__ - Step 42622: {'lr': 0.0004126805707689279, 'samples': 8183424, 'steps': 42621, 'loss/train': 1.6318258047103882} 08/30/2021 20:50:39 - INFO - __main__ - Step 42623: {'lr': 0.0004126765412373566, 'samples': 8183616, 'steps': 42622, 'loss/train': 1.423075795173645} 08/30/2021 20:50:39 - INFO - __main__ - Step 42624: {'lr': 0.0004126725116324858, 'samples': 8183808, 'steps': 42623, 'loss/train': 2.2788617610931396} 08/30/2021 20:50:40 - INFO - __main__ - Step 42625: {'lr': 0.00041266848195431715, 'samples': 8184000, 'steps': 42624, 'loss/train': 2.6883630752563477} 08/30/2021 20:50:41 - INFO - __main__ - Step 42626: {'lr': 0.00041266445220285267, 'samples': 8184192, 'steps': 42625, 'loss/train': 1.554368019104004} 08/30/2021 20:50:41 - INFO - __main__ - Step 42627: {'lr': 0.0004126604223780941, 'samples': 8184384, 'steps': 42626, 'loss/train': 1.5231170654296875} 08/30/2021 20:50:42 - INFO - __main__ - Step 42628: {'lr': 0.00041265639248004327, 'samples': 8184576, 'steps': 42627, 'loss/train': 1.1753484010696411} 08/30/2021 20:50:42 - INFO - __main__ - Step 42629: {'lr': 0.000412652362508702, 'samples': 8184768, 'steps': 42628, 'loss/train': 1.1532585620880127} 08/30/2021 20:50:42 - INFO - __main__ - Step 42630: {'lr': 0.000412648332464072, 'samples': 8184960, 'steps': 42629, 'loss/train': 1.1923291683197021} 08/30/2021 20:50:44 - INFO - __main__ - Step 42631: {'lr': 0.00041264430234615526, 'samples': 8185152, 'steps': 42630, 'loss/train': 1.5295366048812866} 08/30/2021 20:50:44 - INFO - __main__ - Step 42632: {'lr': 0.0004126402721549535, 'samples': 8185344, 'steps': 42631, 'loss/train': 1.3435066938400269} 08/30/2021 20:50:45 - INFO - __main__ - Step 42633: {'lr': 0.00041263624189046846, 'samples': 8185536, 'steps': 42632, 'loss/train': 1.9694530963897705} 08/30/2021 20:50:45 - INFO - __main__ - Step 42634: {'lr': 0.0004126322115527021, 'samples': 8185728, 'steps': 42633, 'loss/train': 1.7155439853668213} 08/30/2021 20:50:45 - INFO - __main__ - Step 42635: {'lr': 0.00041262818114165615, 'samples': 8185920, 'steps': 42634, 'loss/train': 0.8143765330314636} 08/30/2021 20:50:47 - INFO - __main__ - Step 42636: {'lr': 0.0004126241506573325, 'samples': 8186112, 'steps': 42635, 'loss/train': 1.4423202276229858} 08/30/2021 20:50:47 - INFO - __main__ - Step 42637: {'lr': 0.00041262012009973283, 'samples': 8186304, 'steps': 42636, 'loss/train': 1.0636776685714722} 08/30/2021 20:50:48 - INFO - __main__ - Step 42638: {'lr': 0.0004126160894688591, 'samples': 8186496, 'steps': 42637, 'loss/train': 1.1029741764068604} 08/30/2021 20:50:48 - INFO - __main__ - Step 42639: {'lr': 0.00041261205876471307, 'samples': 8186688, 'steps': 42638, 'loss/train': 1.4843602180480957} 08/30/2021 20:50:48 - INFO - __main__ - Step 42640: {'lr': 0.0004126080279872966, 'samples': 8186880, 'steps': 42639, 'loss/train': 1.6286613941192627} 08/30/2021 20:50:50 - INFO - __main__ - Step 42641: {'lr': 0.0004126039971366114, 'samples': 8187072, 'steps': 42640, 'loss/train': 1.3744587898254395} 08/30/2021 20:50:51 - INFO - __main__ - Step 42642: {'lr': 0.0004125999662126594, 'samples': 8187264, 'steps': 42641, 'loss/train': 1.0720371007919312} 08/30/2021 20:50:51 - INFO - __main__ - Step 42643: {'lr': 0.00041259593521544223, 'samples': 8187456, 'steps': 42642, 'loss/train': 1.090353012084961} 08/30/2021 20:50:52 - INFO - __main__ - Step 42644: {'lr': 0.00041259190414496194, 'samples': 8187648, 'steps': 42643, 'loss/train': 1.4614031314849854} 08/30/2021 20:50:52 - INFO - __main__ - Step 42645: {'lr': 0.00041258787300122026, 'samples': 8187840, 'steps': 42644, 'loss/train': 1.0903599262237549} 08/30/2021 20:50:52 - INFO - __main__ - Step 42646: {'lr': 0.000412583841784219, 'samples': 8188032, 'steps': 42645, 'loss/train': 0.9116281867027283} 08/30/2021 20:50:54 - INFO - __main__ - Step 42647: {'lr': 0.00041257981049395997, 'samples': 8188224, 'steps': 42646, 'loss/train': 0.9863569736480713} 08/30/2021 20:50:54 - INFO - __main__ - Step 42648: {'lr': 0.000412575779130445, 'samples': 8188416, 'steps': 42647, 'loss/train': 0.9859895706176758} 08/30/2021 20:50:55 - INFO - __main__ - Step 42649: {'lr': 0.0004125717476936758, 'samples': 8188608, 'steps': 42648, 'loss/train': 1.2508624792099} 08/30/2021 20:50:55 - INFO - __main__ - Step 42650: {'lr': 0.0004125677161836543, 'samples': 8188800, 'steps': 42649, 'loss/train': 1.386723518371582} 08/30/2021 20:50:55 - INFO - __main__ - Step 42651: {'lr': 0.00041256368460038237, 'samples': 8188992, 'steps': 42650, 'loss/train': 1.272167444229126} 08/30/2021 20:50:57 - INFO - __main__ - Step 42652: {'lr': 0.00041255965294386174, 'samples': 8189184, 'steps': 42651, 'loss/train': 1.139366626739502} 08/30/2021 20:50:57 - INFO - __main__ - Step 42653: {'lr': 0.00041255562121409416, 'samples': 8189376, 'steps': 42652, 'loss/train': 1.252394676208496} 08/30/2021 20:50:58 - INFO - __main__ - Step 42654: {'lr': 0.0004125515894110816, 'samples': 8189568, 'steps': 42653, 'loss/train': 1.7041313648223877} 08/30/2021 20:50:58 - INFO - __main__ - Step 42655: {'lr': 0.00041254755753482574, 'samples': 8189760, 'steps': 42654, 'loss/train': 0.987637996673584} 08/30/2021 20:50:58 - INFO - __main__ - Step 42656: {'lr': 0.00041254352558532854, 'samples': 8189952, 'steps': 42655, 'loss/train': 1.3389077186584473} 08/30/2021 20:51:00 - INFO - __main__ - Step 42657: {'lr': 0.0004125394935625917, 'samples': 8190144, 'steps': 42656, 'loss/train': 1.2290616035461426} 08/30/2021 20:51:00 - INFO - __main__ - Step 42658: {'lr': 0.00041253546146661704, 'samples': 8190336, 'steps': 42657, 'loss/train': 1.597948670387268} 08/30/2021 20:51:01 - INFO - __main__ - Step 42659: {'lr': 0.00041253142929740643, 'samples': 8190528, 'steps': 42658, 'loss/train': 0.8809319138526917} 08/30/2021 20:51:01 - INFO - __main__ - Step 42660: {'lr': 0.00041252739705496165, 'samples': 8190720, 'steps': 42659, 'loss/train': 1.0182900428771973} 08/30/2021 20:51:01 - INFO - __main__ - Step 42661: {'lr': 0.00041252336473928455, 'samples': 8190912, 'steps': 42660, 'loss/train': 1.8301284313201904} 08/30/2021 20:51:03 - INFO - __main__ - Step 42662: {'lr': 0.00041251933235037695, 'samples': 8191104, 'steps': 42661, 'loss/train': 1.517749309539795} 08/30/2021 20:51:03 - INFO - __main__ - Step 42663: {'lr': 0.00041251529988824067, 'samples': 8191296, 'steps': 42662, 'loss/train': 0.9042937159538269} 08/30/2021 20:51:04 - INFO - __main__ - Step 42664: {'lr': 0.0004125112673528775, 'samples': 8191488, 'steps': 42663, 'loss/train': 1.3166545629501343} 08/30/2021 20:51:04 - INFO - __main__ - Step 42665: {'lr': 0.0004125072347442892, 'samples': 8191680, 'steps': 42664, 'loss/train': 1.620734453201294} 08/30/2021 20:51:04 - INFO - __main__ - Step 42666: {'lr': 0.0004125032020624776, 'samples': 8191872, 'steps': 42665, 'loss/train': 1.7824167013168335} 08/30/2021 20:51:06 - INFO - __main__ - Step 42667: {'lr': 0.0004124991693074447, 'samples': 8192064, 'steps': 42666, 'loss/train': 1.478500247001648} 08/30/2021 20:51:06 - INFO - __main__ - Step 42668: {'lr': 0.00041249513647919207, 'samples': 8192256, 'steps': 42667, 'loss/train': 1.3233987092971802} 08/30/2021 20:51:07 - INFO - __main__ - Step 42669: {'lr': 0.00041249110357772167, 'samples': 8192448, 'steps': 42668, 'loss/train': 1.3106153011322021} 08/30/2021 20:51:07 - INFO - __main__ - Step 42670: {'lr': 0.00041248707060303536, 'samples': 8192640, 'steps': 42669, 'loss/train': 1.2161531448364258} 08/30/2021 20:51:07 - INFO - __main__ - Step 42671: {'lr': 0.00041248303755513484, 'samples': 8192832, 'steps': 42670, 'loss/train': 1.5994771718978882} 08/30/2021 20:51:10 - INFO - __main__ - Step 42672: {'lr': 0.00041247900443402194, 'samples': 8193024, 'steps': 42671, 'loss/train': 1.877849817276001} 08/30/2021 20:51:10 - INFO - __main__ - Step 42673: {'lr': 0.00041247497123969844, 'samples': 8193216, 'steps': 42672, 'loss/train': 1.4366408586502075} 08/30/2021 20:51:10 - INFO - __main__ - Step 42674: {'lr': 0.00041247093797216637, 'samples': 8193408, 'steps': 42673, 'loss/train': 2.9169890880584717} 08/30/2021 20:51:11 - INFO - __main__ - Step 42675: {'lr': 0.00041246690463142733, 'samples': 8193600, 'steps': 42674, 'loss/train': 0.12583310902118683} 08/30/2021 20:51:11 - INFO - __main__ - Step 42676: {'lr': 0.0004124628712174833, 'samples': 8193792, 'steps': 42675, 'loss/train': 0.24078887701034546} 08/30/2021 20:51:12 - INFO - __main__ - Step 42677: {'lr': 0.0004124588377303359, 'samples': 8193984, 'steps': 42676, 'loss/train': 1.1301815509796143} 08/30/2021 20:51:13 - INFO - __main__ - Step 42678: {'lr': 0.00041245480416998704, 'samples': 8194176, 'steps': 42677, 'loss/train': 1.311215877532959} 08/30/2021 20:51:13 - INFO - __main__ - Step 42679: {'lr': 0.00041245077053643866, 'samples': 8194368, 'steps': 42678, 'loss/train': 1.1596556901931763} 08/30/2021 20:51:14 - INFO - __main__ - Step 42680: {'lr': 0.0004124467368296924, 'samples': 8194560, 'steps': 42679, 'loss/train': 0.9840144515037537} 08/30/2021 20:51:14 - INFO - __main__ - Step 42681: {'lr': 0.00041244270304975004, 'samples': 8194752, 'steps': 42680, 'loss/train': 1.235546588897705} 08/30/2021 20:51:14 - INFO - __main__ - Step 42682: {'lr': 0.0004124386691966137, 'samples': 8194944, 'steps': 42681, 'loss/train': 1.643437385559082} 08/30/2021 20:51:16 - INFO - __main__ - Step 42683: {'lr': 0.00041243463527028493, 'samples': 8195136, 'steps': 42682, 'loss/train': 1.6930502653121948} 08/30/2021 20:51:16 - INFO - __main__ - Step 42684: {'lr': 0.0004124306012707656, 'samples': 8195328, 'steps': 42683, 'loss/train': 1.128927230834961} 08/30/2021 20:51:17 - INFO - __main__ - Step 42685: {'lr': 0.00041242656719805754, 'samples': 8195520, 'steps': 42684, 'loss/train': 1.5005710124969482} 08/30/2021 20:51:17 - INFO - __main__ - Step 42686: {'lr': 0.0004124225330521626, 'samples': 8195712, 'steps': 42685, 'loss/train': 1.2922616004943848} 08/30/2021 20:51:17 - INFO - __main__ - Step 42687: {'lr': 0.0004124184988330826, 'samples': 8195904, 'steps': 42686, 'loss/train': 1.1025948524475098} 08/30/2021 20:51:19 - INFO - __main__ - Step 42688: {'lr': 0.0004124144645408192, 'samples': 8196096, 'steps': 42687, 'loss/train': 2.2752678394317627} 08/30/2021 20:51:19 - INFO - __main__ - Step 42689: {'lr': 0.0004124104301753745, 'samples': 8196288, 'steps': 42688, 'loss/train': 1.0980074405670166} 08/30/2021 20:51:20 - INFO - __main__ - Step 42690: {'lr': 0.0004124063957367501, 'samples': 8196480, 'steps': 42689, 'loss/train': 0.9873174428939819} 08/30/2021 20:51:20 - INFO - __main__ - Step 42691: {'lr': 0.0004124023612249479, 'samples': 8196672, 'steps': 42690, 'loss/train': 0.8801842927932739} 08/30/2021 20:51:20 - INFO - __main__ - Step 42692: {'lr': 0.0004123983266399697, 'samples': 8196864, 'steps': 42691, 'loss/train': 1.5642693042755127} 08/30/2021 20:51:22 - INFO - __main__ - Step 42693: {'lr': 0.0004123942919818173, 'samples': 8197056, 'steps': 42692, 'loss/train': 1.1973350048065186} 08/30/2021 20:51:22 - INFO - __main__ - Step 42694: {'lr': 0.00041239025725049256, 'samples': 8197248, 'steps': 42693, 'loss/train': 1.8853051662445068} 08/30/2021 20:51:23 - INFO - __main__ - Step 42695: {'lr': 0.0004123862224459973, 'samples': 8197440, 'steps': 42694, 'loss/train': 1.9385746717453003} 08/30/2021 20:51:23 - INFO - __main__ - Step 42696: {'lr': 0.0004123821875683333, 'samples': 8197632, 'steps': 42695, 'loss/train': 1.6885868310928345} 08/30/2021 20:51:23 - INFO - __main__ - Step 42697: {'lr': 0.0004123781526175023, 'samples': 8197824, 'steps': 42696, 'loss/train': 1.3855059146881104} 08/30/2021 20:51:26 - INFO - __main__ - Step 42698: {'lr': 0.0004123741175935063, 'samples': 8198016, 'steps': 42697, 'loss/train': 1.3950804471969604} 08/30/2021 20:51:26 - INFO - __main__ - Step 42699: {'lr': 0.000412370082496347, 'samples': 8198208, 'steps': 42698, 'loss/train': 1.429821491241455} 08/30/2021 20:51:27 - INFO - __main__ - Step 42700: {'lr': 0.0004123660473260263, 'samples': 8198400, 'steps': 42699, 'loss/train': 1.7408299446105957} 08/30/2021 20:51:27 - INFO - __main__ - Step 42701: {'lr': 0.0004123620120825459, 'samples': 8198592, 'steps': 42700, 'loss/train': 1.7905468940734863} 08/30/2021 20:51:27 - INFO - __main__ - Step 42702: {'lr': 0.00041235797676590776, 'samples': 8198784, 'steps': 42701, 'loss/train': 1.6065155267715454} 08/30/2021 20:51:28 - INFO - __main__ - Step 42703: {'lr': 0.0004123539413761136, 'samples': 8198976, 'steps': 42702, 'loss/train': 1.134494423866272} 08/30/2021 20:51:29 - INFO - __main__ - Step 42704: {'lr': 0.0004123499059131652, 'samples': 8199168, 'steps': 42703, 'loss/train': 0.7257978320121765} 08/30/2021 20:51:30 - INFO - __main__ - Step 42705: {'lr': 0.00041234587037706447, 'samples': 8199360, 'steps': 42704, 'loss/train': 0.3595121502876282} 08/30/2021 20:51:30 - INFO - __main__ - Step 42706: {'lr': 0.0004123418347678132, 'samples': 8199552, 'steps': 42705, 'loss/train': 0.3763863742351532} 08/30/2021 20:51:31 - INFO - __main__ - Step 42707: {'lr': 0.00041233779908541316, 'samples': 8199744, 'steps': 42706, 'loss/train': 1.2722951173782349} 08/30/2021 20:51:31 - INFO - __main__ - Step 42708: {'lr': 0.0004123337633298662, 'samples': 8199936, 'steps': 42707, 'loss/train': 1.1446754932403564} 08/30/2021 20:51:33 - INFO - __main__ - Step 42709: {'lr': 0.0004123297275011743, 'samples': 8200128, 'steps': 42708, 'loss/train': 1.24917733669281} 08/30/2021 20:51:33 - INFO - __main__ - Step 42710: {'lr': 0.00041232569159933895, 'samples': 8200320, 'steps': 42709, 'loss/train': 0.7024908065795898} 08/30/2021 20:51:34 - INFO - __main__ - Step 42711: {'lr': 0.00041232165562436225, 'samples': 8200512, 'steps': 42710, 'loss/train': 0.7034547924995422} 08/30/2021 20:51:34 - INFO - __main__ - Step 42712: {'lr': 0.00041231761957624593, 'samples': 8200704, 'steps': 42711, 'loss/train': 1.034439206123352} 08/30/2021 20:51:34 - INFO - __main__ - Step 42713: {'lr': 0.0004123135834549917, 'samples': 8200896, 'steps': 42712, 'loss/train': 0.9282547831535339} 08/30/2021 20:51:35 - INFO - __main__ - Step 42714: {'lr': 0.00041230954726060155, 'samples': 8201088, 'steps': 42713, 'loss/train': 1.7811814546585083} 08/30/2021 20:51:36 - INFO - __main__ - Step 42715: {'lr': 0.00041230551099307724, 'samples': 8201280, 'steps': 42714, 'loss/train': 0.07779279351234436} 08/30/2021 20:51:37 - INFO - __main__ - Step 42716: {'lr': 0.0004123014746524205, 'samples': 8201472, 'steps': 42715, 'loss/train': 0.580621063709259} 08/30/2021 20:51:37 - INFO - __main__ - Step 42717: {'lr': 0.0004122974382386333, 'samples': 8201664, 'steps': 42716, 'loss/train': 0.7306473255157471} 08/30/2021 20:51:38 - INFO - __main__ - Step 42718: {'lr': 0.00041229340175171733, 'samples': 8201856, 'steps': 42717, 'loss/train': 1.378116488456726} 08/30/2021 20:51:38 - INFO - __main__ - Step 42719: {'lr': 0.00041228936519167446, 'samples': 8202048, 'steps': 42718, 'loss/train': 1.2331045866012573} 08/30/2021 20:51:39 - INFO - __main__ - Step 42720: {'lr': 0.00041228532855850655, 'samples': 8202240, 'steps': 42719, 'loss/train': 1.4135370254516602} 08/30/2021 20:51:40 - INFO - __main__ - Step 42721: {'lr': 0.0004122812918522153, 'samples': 8202432, 'steps': 42720, 'loss/train': 1.4351112842559814} 08/30/2021 20:51:40 - INFO - __main__ - Step 42722: {'lr': 0.0004122772550728027, 'samples': 8202624, 'steps': 42721, 'loss/train': 0.8106284737586975} 08/30/2021 20:51:40 - INFO - __main__ - Step 42723: {'lr': 0.0004122732182202703, 'samples': 8202816, 'steps': 42722, 'loss/train': 1.8287279605865479} 08/30/2021 20:51:41 - INFO - __main__ - Step 42724: {'lr': 0.0004122691812946202, 'samples': 8203008, 'steps': 42723, 'loss/train': 0.2856653332710266} 08/30/2021 20:51:42 - INFO - __main__ - Step 42725: {'lr': 0.00041226514429585417, 'samples': 8203200, 'steps': 42724, 'loss/train': 1.4880412817001343} 08/30/2021 20:51:43 - INFO - __main__ - Step 42726: {'lr': 0.0004122611072239739, 'samples': 8203392, 'steps': 42725, 'loss/train': 0.20633737742900848} 08/30/2021 20:51:43 - INFO - __main__ - Step 42727: {'lr': 0.00041225707007898127, 'samples': 8203584, 'steps': 42726, 'loss/train': 0.8177879452705383} 08/30/2021 20:51:43 - INFO - __main__ - Step 42728: {'lr': 0.0004122530328608781, 'samples': 8203776, 'steps': 42727, 'loss/train': 1.210819959640503} 08/30/2021 20:51:44 - INFO - __main__ - Step 42729: {'lr': 0.00041224899556966635, 'samples': 8203968, 'steps': 42728, 'loss/train': 1.593616008758545} 08/30/2021 20:51:45 - INFO - __main__ - Step 42730: {'lr': 0.00041224495820534757, 'samples': 8204160, 'steps': 42729, 'loss/train': 1.6073495149612427} 08/30/2021 20:51:46 - INFO - __main__ - Step 42731: {'lr': 0.00041224092076792374, 'samples': 8204352, 'steps': 42730, 'loss/train': 1.475361943244934} 08/30/2021 20:51:46 - INFO - __main__ - Step 42732: {'lr': 0.0004122368832573967, 'samples': 8204544, 'steps': 42731, 'loss/train': 1.1168408393859863} 08/30/2021 20:51:46 - INFO - __main__ - Step 42733: {'lr': 0.00041223284567376816, 'samples': 8204736, 'steps': 42732, 'loss/train': 1.1464427709579468} 08/30/2021 20:51:47 - INFO - __main__ - Step 42734: {'lr': 0.00041222880801704005, 'samples': 8204928, 'steps': 42733, 'loss/train': 1.3804570436477661} 08/30/2021 20:51:48 - INFO - __main__ - Step 42735: {'lr': 0.0004122247702872141, 'samples': 8205120, 'steps': 42734, 'loss/train': 1.5680476427078247} 08/30/2021 20:51:49 - INFO - __main__ - Step 42736: {'lr': 0.0004122207324842923, 'samples': 8205312, 'steps': 42735, 'loss/train': 1.2770121097564697} 08/30/2021 20:51:49 - INFO - __main__ - Step 42737: {'lr': 0.00041221669460827614, 'samples': 8205504, 'steps': 42736, 'loss/train': 1.2181936502456665} 08/30/2021 20:51:50 - INFO - __main__ - Step 42738: {'lr': 0.00041221265665916776, 'samples': 8205696, 'steps': 42737, 'loss/train': 1.5945320129394531} 08/30/2021 20:51:50 - INFO - __main__ - Step 42739: {'lr': 0.00041220861863696886, 'samples': 8205888, 'steps': 42738, 'loss/train': 2.015470266342163} 08/30/2021 20:51:51 - INFO - __main__ - Step 42740: {'lr': 0.0004122045805416812, 'samples': 8206080, 'steps': 42739, 'loss/train': 0.0998903140425682} 08/30/2021 20:51:52 - INFO - __main__ - Step 42741: {'lr': 0.00041220054237330674, 'samples': 8206272, 'steps': 42740, 'loss/train': 1.2674150466918945} 08/30/2021 20:51:52 - INFO - __main__ - Step 42742: {'lr': 0.00041219650413184714, 'samples': 8206464, 'steps': 42741, 'loss/train': 1.152045726776123} 08/30/2021 20:51:52 - INFO - __main__ - Step 42743: {'lr': 0.00041219246581730435, 'samples': 8206656, 'steps': 42742, 'loss/train': 1.2147914171218872} 08/30/2021 20:51:53 - INFO - __main__ - Step 42744: {'lr': 0.0004121884274296801, 'samples': 8206848, 'steps': 42743, 'loss/train': 1.6697134971618652} 08/30/2021 20:51:53 - INFO - __main__ - Step 42745: {'lr': 0.00041218438896897623, 'samples': 8207040, 'steps': 42744, 'loss/train': 1.5761781930923462} 08/30/2021 20:51:55 - INFO - __main__ - Step 42746: {'lr': 0.00041218035043519464, 'samples': 8207232, 'steps': 42745, 'loss/train': 0.6791060566902161} 08/30/2021 20:51:55 - INFO - __main__ - Step 42747: {'lr': 0.00041217631182833707, 'samples': 8207424, 'steps': 42746, 'loss/train': 1.3686248064041138} 08/30/2021 20:51:55 - INFO - __main__ - Step 42748: {'lr': 0.00041217227314840535, 'samples': 8207616, 'steps': 42747, 'loss/train': 1.5877742767333984} 08/30/2021 20:51:56 - INFO - __main__ - Step 42749: {'lr': 0.00041216823439540134, 'samples': 8207808, 'steps': 42748, 'loss/train': 1.3075661659240723} 08/30/2021 20:51:56 - INFO - __main__ - Step 42750: {'lr': 0.0004121641955693268, 'samples': 8208000, 'steps': 42749, 'loss/train': 1.519882082939148} 08/30/2021 20:51:58 - INFO - __main__ - Step 42751: {'lr': 0.00041216015667018357, 'samples': 8208192, 'steps': 42750, 'loss/train': 1.529238224029541} 08/30/2021 20:51:59 - INFO - __main__ - Step 42752: {'lr': 0.00041215611769797344, 'samples': 8208384, 'steps': 42751, 'loss/train': 1.2978233098983765} 08/30/2021 20:51:59 - INFO - __main__ - Step 42753: {'lr': 0.00041215207865269833, 'samples': 8208576, 'steps': 42752, 'loss/train': 1.2263840436935425} 08/30/2021 20:51:59 - INFO - __main__ - Step 42754: {'lr': 0.00041214803953435993, 'samples': 8208768, 'steps': 42753, 'loss/train': 1.5428600311279297} 08/30/2021 20:52:00 - INFO - __main__ - Step 42755: {'lr': 0.0004121440003429602, 'samples': 8208960, 'steps': 42754, 'loss/train': 1.6345829963684082} 08/30/2021 20:52:01 - INFO - __main__ - Step 42756: {'lr': 0.0004121399610785008, 'samples': 8209152, 'steps': 42755, 'loss/train': 0.3770456910133362} 08/30/2021 20:52:02 - INFO - __main__ - Step 42757: {'lr': 0.00041213592174098367, 'samples': 8209344, 'steps': 42756, 'loss/train': 1.4098496437072754} 08/30/2021 20:52:02 - INFO - __main__ - Step 42758: {'lr': 0.00041213188233041065, 'samples': 8209536, 'steps': 42757, 'loss/train': 1.814401388168335} 08/30/2021 20:52:02 - INFO - __main__ - Step 42759: {'lr': 0.00041212784284678345, 'samples': 8209728, 'steps': 42758, 'loss/train': 1.141072154045105} 08/30/2021 20:52:03 - INFO - __main__ - Step 42760: {'lr': 0.0004121238032901039, 'samples': 8209920, 'steps': 42759, 'loss/train': 1.5040597915649414} 08/30/2021 20:52:04 - INFO - __main__ - Step 42761: {'lr': 0.00041211976366037394, 'samples': 8210112, 'steps': 42760, 'loss/train': 1.5597246885299683} 08/30/2021 20:52:05 - INFO - __main__ - Step 42762: {'lr': 0.0004121157239575953, 'samples': 8210304, 'steps': 42761, 'loss/train': 1.2797777652740479} 08/30/2021 20:52:05 - INFO - __main__ - Step 42763: {'lr': 0.0004121116841817699, 'samples': 8210496, 'steps': 42762, 'loss/train': 2.1422858238220215} 08/30/2021 20:52:06 - INFO - __main__ - Step 42764: {'lr': 0.00041210764433289936, 'samples': 8210688, 'steps': 42763, 'loss/train': 1.0626745223999023} 08/30/2021 20:52:06 - INFO - __main__ - Step 42765: {'lr': 0.0004121036044109856, 'samples': 8210880, 'steps': 42764, 'loss/train': 0.0444820336997509} 08/30/2021 20:52:06 - INFO - __main__ - Step 42766: {'lr': 0.00041209956441603054, 'samples': 8211072, 'steps': 42765, 'loss/train': 0.05257513001561165} 08/30/2021 20:52:08 - INFO - __main__ - Step 42767: {'lr': 0.0004120955243480359, 'samples': 8211264, 'steps': 42766, 'loss/train': 1.326391577720642} 08/30/2021 20:52:08 - INFO - __main__ - Step 42768: {'lr': 0.0004120914842070035, 'samples': 8211456, 'steps': 42767, 'loss/train': 1.9479166269302368} 08/30/2021 20:52:09 - INFO - __main__ - Step 42769: {'lr': 0.0004120874439929352, 'samples': 8211648, 'steps': 42768, 'loss/train': 1.226039171218872} 08/30/2021 20:52:09 - INFO - __main__ - Step 42770: {'lr': 0.00041208340370583275, 'samples': 8211840, 'steps': 42769, 'loss/train': 1.243990182876587} 08/30/2021 20:52:10 - INFO - __main__ - Step 42771: {'lr': 0.0004120793633456981, 'samples': 8212032, 'steps': 42770, 'loss/train': 1.5370738506317139} 08/30/2021 20:52:11 - INFO - __main__ - Step 42772: {'lr': 0.0004120753229125329, 'samples': 8212224, 'steps': 42771, 'loss/train': 0.3223148584365845} 08/30/2021 20:52:11 - INFO - __main__ - Step 42773: {'lr': 0.00041207128240633906, 'samples': 8212416, 'steps': 42772, 'loss/train': 0.8358148336410522} 08/30/2021 20:52:12 - INFO - __main__ - Step 42774: {'lr': 0.0004120672418271184, 'samples': 8212608, 'steps': 42773, 'loss/train': 1.6780993938446045} 08/30/2021 20:52:12 - INFO - __main__ - Step 42775: {'lr': 0.0004120632011748728, 'samples': 8212800, 'steps': 42774, 'loss/train': 1.3218542337417603} 08/30/2021 20:52:12 - INFO - __main__ - Step 42776: {'lr': 0.00041205916044960406, 'samples': 8212992, 'steps': 42775, 'loss/train': 1.6444679498672485} 08/30/2021 20:52:14 - INFO - __main__ - Step 42777: {'lr': 0.0004120551196513139, 'samples': 8213184, 'steps': 42776, 'loss/train': 1.0199215412139893} 08/30/2021 20:52:15 - INFO - __main__ - Step 42778: {'lr': 0.0004120510787800042, 'samples': 8213376, 'steps': 42777, 'loss/train': 1.2396245002746582} 08/30/2021 20:52:15 - INFO - __main__ - Step 42779: {'lr': 0.0004120470378356768, 'samples': 8213568, 'steps': 42778, 'loss/train': 1.6554065942764282} 08/30/2021 20:52:16 - INFO - __main__ - Step 42780: {'lr': 0.00041204299681833344, 'samples': 8213760, 'steps': 42779, 'loss/train': 1.4116393327713013} 08/30/2021 20:52:16 - INFO - __main__ - Step 42781: {'lr': 0.00041203895572797613, 'samples': 8213952, 'steps': 42780, 'loss/train': 0.26155638694763184} 08/30/2021 20:52:16 - INFO - __main__ - Step 42782: {'lr': 0.00041203491456460653, 'samples': 8214144, 'steps': 42781, 'loss/train': 1.3729006052017212} 08/30/2021 20:52:18 - INFO - __main__ - Step 42783: {'lr': 0.00041203087332822644, 'samples': 8214336, 'steps': 42782, 'loss/train': 1.929867148399353} 08/30/2021 20:52:18 - INFO - __main__ - Step 42784: {'lr': 0.0004120268320188378, 'samples': 8214528, 'steps': 42783, 'loss/train': 1.0946468114852905} 08/30/2021 20:52:18 - INFO - __main__ - Step 42785: {'lr': 0.00041202279063644234, 'samples': 8214720, 'steps': 42784, 'loss/train': 1.5491408109664917} 08/30/2021 20:52:19 - INFO - __main__ - Step 42786: {'lr': 0.00041201874918104185, 'samples': 8214912, 'steps': 42785, 'loss/train': 1.2300634384155273} 08/30/2021 20:52:19 - INFO - __main__ - Step 42787: {'lr': 0.0004120147076526383, 'samples': 8215104, 'steps': 42786, 'loss/train': 1.3511295318603516} 08/30/2021 20:52:21 - INFO - __main__ - Step 42788: {'lr': 0.0004120106660512334, 'samples': 8215296, 'steps': 42787, 'loss/train': 1.5419447422027588} 08/30/2021 20:52:21 - INFO - __main__ - Step 42789: {'lr': 0.000412006624376829, 'samples': 8215488, 'steps': 42788, 'loss/train': 1.2196044921875} 08/30/2021 20:52:21 - INFO - __main__ - Step 42790: {'lr': 0.0004120025826294269, 'samples': 8215680, 'steps': 42789, 'loss/train': 1.9221341609954834} 08/30/2021 20:52:22 - INFO - __main__ - Step 42791: {'lr': 0.00041199854080902897, 'samples': 8215872, 'steps': 42790, 'loss/train': 1.1416150331497192} 08/30/2021 20:52:22 - INFO - __main__ - Step 42792: {'lr': 0.00041199449891563694, 'samples': 8216064, 'steps': 42791, 'loss/train': 1.2159194946289062} 08/30/2021 20:52:24 - INFO - __main__ - Step 42793: {'lr': 0.00041199045694925273, 'samples': 8216256, 'steps': 42792, 'loss/train': 1.6979012489318848} 08/30/2021 20:52:24 - INFO - __main__ - Step 42794: {'lr': 0.0004119864149098781, 'samples': 8216448, 'steps': 42793, 'loss/train': 1.5664771795272827} 08/30/2021 20:52:24 - INFO - __main__ - Step 42795: {'lr': 0.0004119823727975149, 'samples': 8216640, 'steps': 42794, 'loss/train': 1.4682016372680664} 08/30/2021 20:52:25 - INFO - __main__ - Step 42796: {'lr': 0.00041197833061216494, 'samples': 8216832, 'steps': 42795, 'loss/train': 1.8733136653900146} 08/30/2021 20:52:25 - INFO - __main__ - Step 42797: {'lr': 0.00041197428835383, 'samples': 8217024, 'steps': 42796, 'loss/train': 1.9760923385620117} 08/30/2021 20:52:27 - INFO - __main__ - Step 42798: {'lr': 0.00041197024602251204, 'samples': 8217216, 'steps': 42797, 'loss/train': 0.9231312870979309} 08/30/2021 20:52:27 - INFO - __main__ - Step 42799: {'lr': 0.0004119662036182127, 'samples': 8217408, 'steps': 42798, 'loss/train': 1.344942569732666} 08/30/2021 20:52:28 - INFO - __main__ - Step 42800: {'lr': 0.00041196216114093397, 'samples': 8217600, 'steps': 42799, 'loss/train': 0.9927522540092468} 08/30/2021 20:52:28 - INFO - __main__ - Step 42801: {'lr': 0.00041195811859067756, 'samples': 8217792, 'steps': 42800, 'loss/train': 1.3030191659927368} 08/30/2021 20:52:28 - INFO - __main__ - Step 42802: {'lr': 0.0004119540759674453, 'samples': 8217984, 'steps': 42801, 'loss/train': 1.5118681192398071} 08/30/2021 20:52:30 - INFO - __main__ - Step 42803: {'lr': 0.000411950033271239, 'samples': 8218176, 'steps': 42802, 'loss/train': 0.9536420106887817} 08/30/2021 20:52:31 - INFO - __main__ - Step 42804: {'lr': 0.0004119459905020606, 'samples': 8218368, 'steps': 42803, 'loss/train': 1.7397682666778564} 08/30/2021 20:52:31 - INFO - __main__ - Step 42805: {'lr': 0.0004119419476599118, 'samples': 8218560, 'steps': 42804, 'loss/train': 1.6398180723190308} 08/30/2021 20:52:31 - INFO - __main__ - Step 42806: {'lr': 0.0004119379047447944, 'samples': 8218752, 'steps': 42805, 'loss/train': 0.8062236309051514} 08/30/2021 20:52:32 - INFO - __main__ - Step 42807: {'lr': 0.00041193386175671033, 'samples': 8218944, 'steps': 42806, 'loss/train': 0.8588298559188843} 08/30/2021 20:52:32 - INFO - __main__ - Step 42808: {'lr': 0.0004119298186956613, 'samples': 8219136, 'steps': 42807, 'loss/train': 2.1786930561065674} 08/30/2021 20:52:34 - INFO - __main__ - Step 42809: {'lr': 0.00041192577556164924, 'samples': 8219328, 'steps': 42808, 'loss/train': 0.7691994309425354} 08/30/2021 20:52:35 - INFO - __main__ - Step 42810: {'lr': 0.000411921732354676, 'samples': 8219520, 'steps': 42809, 'loss/train': 0.030235696583986282} 08/30/2021 20:52:35 - INFO - __main__ - Step 42811: {'lr': 0.00041191768907474326, 'samples': 8219712, 'steps': 42810, 'loss/train': 0.026263045147061348} 08/30/2021 20:52:35 - INFO - __main__ - Step 42812: {'lr': 0.00041191364572185286, 'samples': 8219904, 'steps': 42811, 'loss/train': 1.3629406690597534} 08/30/2021 20:52:36 - INFO - __main__ - Step 42813: {'lr': 0.0004119096022960067, 'samples': 8220096, 'steps': 42812, 'loss/train': 0.1095290333032608} 08/30/2021 20:52:36 - INFO - __main__ - Step 42814: {'lr': 0.0004119055587972066, 'samples': 8220288, 'steps': 42813, 'loss/train': 1.9197845458984375} 08/30/2021 20:52:37 - INFO - __main__ - Step 42815: {'lr': 0.0004119015152254543, 'samples': 8220480, 'steps': 42814, 'loss/train': 1.541056513786316} 08/30/2021 20:52:38 - INFO - __main__ - Step 42816: {'lr': 0.00041189747158075176, 'samples': 8220672, 'steps': 42815, 'loss/train': 1.2116667032241821} 08/30/2021 20:52:38 - INFO - __main__ - Step 42817: {'lr': 0.00041189342786310067, 'samples': 8220864, 'steps': 42816, 'loss/train': 0.5459004044532776} 08/30/2021 20:52:39 - INFO - __main__ - Step 42818: {'lr': 0.0004118893840725029, 'samples': 8221056, 'steps': 42817, 'loss/train': 1.2930238246917725} 08/30/2021 20:52:39 - INFO - __main__ - Step 42819: {'lr': 0.0004118853402089603, 'samples': 8221248, 'steps': 42818, 'loss/train': 1.6231409311294556} 08/30/2021 20:52:41 - INFO - __main__ - Step 42820: {'lr': 0.0004118812962724746, 'samples': 8221440, 'steps': 42819, 'loss/train': 1.44464111328125} 08/30/2021 20:52:42 - INFO - __main__ - Step 42821: {'lr': 0.00041187725226304775, 'samples': 8221632, 'steps': 42820, 'loss/train': 1.3955358266830444} 08/30/2021 20:52:42 - INFO - __main__ - Step 42822: {'lr': 0.0004118732081806814, 'samples': 8221824, 'steps': 42821, 'loss/train': 0.9620579481124878} 08/30/2021 20:52:43 - INFO - __main__ - Step 42823: {'lr': 0.0004118691640253777, 'samples': 8222016, 'steps': 42822, 'loss/train': 1.7535643577575684} 08/30/2021 20:52:43 - INFO - __main__ - Step 42824: {'lr': 0.00041186511979713806, 'samples': 8222208, 'steps': 42823, 'loss/train': 1.4558895826339722} 08/30/2021 20:52:43 - INFO - __main__ - Step 42825: {'lr': 0.00041186107549596453, 'samples': 8222400, 'steps': 42824, 'loss/train': 0.46301376819610596} 08/30/2021 20:52:45 - INFO - __main__ - Step 42826: {'lr': 0.0004118570311218589, 'samples': 8222592, 'steps': 42825, 'loss/train': 0.4012913405895233} 08/30/2021 20:52:46 - INFO - __main__ - Step 42827: {'lr': 0.00041185298667482294, 'samples': 8222784, 'steps': 42826, 'loss/train': 1.157563328742981} 08/30/2021 20:52:46 - INFO - __main__ - Step 42828: {'lr': 0.0004118489421548586, 'samples': 8222976, 'steps': 42827, 'loss/train': 1.3738535642623901} 08/30/2021 20:52:46 - INFO - __main__ - Step 42829: {'lr': 0.00041184489756196764, 'samples': 8223168, 'steps': 42828, 'loss/train': 1.152182698249817} 08/30/2021 20:52:47 - INFO - __main__ - Step 42830: {'lr': 0.0004118408528961519, 'samples': 8223360, 'steps': 42829, 'loss/train': 1.5130033493041992} 08/30/2021 20:52:47 - INFO - __main__ - Step 42831: {'lr': 0.00041183680815741307, 'samples': 8223552, 'steps': 42830, 'loss/train': 1.4232146739959717} 08/30/2021 20:52:49 - INFO - __main__ - Step 42832: {'lr': 0.0004118327633457531, 'samples': 8223744, 'steps': 42831, 'loss/train': 0.8346356749534607} 08/30/2021 20:52:49 - INFO - __main__ - Step 42833: {'lr': 0.00041182871846117373, 'samples': 8223936, 'steps': 42832, 'loss/train': 1.4951962232589722} 08/30/2021 20:52:49 - INFO - __main__ - Step 42834: {'lr': 0.0004118246735036769, 'samples': 8224128, 'steps': 42833, 'loss/train': 1.8352375030517578} 08/30/2021 20:52:50 - INFO - __main__ - Step 42835: {'lr': 0.0004118206284732644, 'samples': 8224320, 'steps': 42834, 'loss/train': 1.4015146493911743} 08/30/2021 20:52:50 - INFO - __main__ - Step 42836: {'lr': 0.000411816583369938, 'samples': 8224512, 'steps': 42835, 'loss/train': 1.4538276195526123} 08/30/2021 20:52:52 - INFO - __main__ - Step 42837: {'lr': 0.0004118125381936996, 'samples': 8224704, 'steps': 42836, 'loss/train': 1.6377867460250854} 08/30/2021 20:52:52 - INFO - __main__ - Step 42838: {'lr': 0.0004118084929445508, 'samples': 8224896, 'steps': 42837, 'loss/train': 1.1447142362594604} 08/30/2021 20:52:53 - INFO - __main__ - Step 42839: {'lr': 0.0004118044476224937, 'samples': 8225088, 'steps': 42838, 'loss/train': 1.6882789134979248} 08/30/2021 20:52:53 - INFO - __main__ - Step 42840: {'lr': 0.00041180040222753, 'samples': 8225280, 'steps': 42839, 'loss/train': 1.0161800384521484} 08/30/2021 20:52:53 - INFO - __main__ - Step 42841: {'lr': 0.00041179635675966155, 'samples': 8225472, 'steps': 42840, 'loss/train': 1.38160240650177} 08/30/2021 20:52:55 - INFO - __main__ - Step 42842: {'lr': 0.00041179231121889014, 'samples': 8225664, 'steps': 42841, 'loss/train': 1.4770721197128296} 08/30/2021 20:52:55 - INFO - __main__ - Step 42843: {'lr': 0.0004117882656052176, 'samples': 8225856, 'steps': 42842, 'loss/train': 1.7939602136611938} 08/30/2021 20:52:56 - INFO - __main__ - Step 42844: {'lr': 0.0004117842199186458, 'samples': 8226048, 'steps': 42843, 'loss/train': 1.4858546257019043} 08/30/2021 20:52:56 - INFO - __main__ - Step 42845: {'lr': 0.00041178017415917655, 'samples': 8226240, 'steps': 42844, 'loss/train': 1.8660188913345337} 08/30/2021 20:52:56 - INFO - __main__ - Step 42846: {'lr': 0.00041177612832681156, 'samples': 8226432, 'steps': 42845, 'loss/train': 1.0155410766601562} 08/30/2021 20:52:58 - INFO - __main__ - Step 42847: {'lr': 0.00041177208242155285, 'samples': 8226624, 'steps': 42846, 'loss/train': 1.1603670120239258} 08/30/2021 20:52:59 - INFO - __main__ - Step 42848: {'lr': 0.000411768036443402, 'samples': 8226816, 'steps': 42847, 'loss/train': 1.6450775861740112} 08/30/2021 20:52:59 - INFO - __main__ - Step 42849: {'lr': 0.0004117639903923611, 'samples': 8227008, 'steps': 42848, 'loss/train': 0.08885498344898224} 08/30/2021 20:52:59 - INFO - __main__ - Step 42850: {'lr': 0.00041175994426843177, 'samples': 8227200, 'steps': 42849, 'loss/train': 1.087542176246643} 08/30/2021 20:53:00 - INFO - __main__ - Step 42851: {'lr': 0.00041175589807161597, 'samples': 8227392, 'steps': 42850, 'loss/train': 0.3503994047641754} 08/30/2021 20:53:01 - INFO - __main__ - Step 42852: {'lr': 0.0004117518518019154, 'samples': 8227584, 'steps': 42851, 'loss/train': 1.0052155256271362} 08/30/2021 20:53:01 - INFO - __main__ - Step 42853: {'lr': 0.00041174780545933195, 'samples': 8227776, 'steps': 42852, 'loss/train': 1.4477592706680298} 08/30/2021 20:53:02 - INFO - __main__ - Step 42854: {'lr': 0.0004117437590438674, 'samples': 8227968, 'steps': 42853, 'loss/train': 1.4567382335662842} 08/30/2021 20:53:02 - INFO - __main__ - Step 42855: {'lr': 0.0004117397125555237, 'samples': 8228160, 'steps': 42854, 'loss/train': 0.15344618260860443} 08/30/2021 20:53:03 - INFO - __main__ - Step 42856: {'lr': 0.00041173566599430245, 'samples': 8228352, 'steps': 42855, 'loss/train': 1.1155697107315063} 08/30/2021 20:53:04 - INFO - __main__ - Step 42857: {'lr': 0.00041173161936020573, 'samples': 8228544, 'steps': 42856, 'loss/train': 1.1189734935760498} 08/30/2021 20:53:04 - INFO - __main__ - Step 42858: {'lr': 0.0004117275726532352, 'samples': 8228736, 'steps': 42857, 'loss/train': 1.1313668489456177} 08/30/2021 20:53:05 - INFO - __main__ - Step 42859: {'lr': 0.0004117235258733927, 'samples': 8228928, 'steps': 42858, 'loss/train': 1.4892619848251343} 08/30/2021 20:53:05 - INFO - __main__ - Step 42860: {'lr': 0.00041171947902068006, 'samples': 8229120, 'steps': 42859, 'loss/train': 1.7968533039093018} 08/30/2021 20:53:05 - INFO - __main__ - Step 42861: {'lr': 0.00041171543209509923, 'samples': 8229312, 'steps': 42860, 'loss/train': 1.0041232109069824} 08/30/2021 20:53:06 - INFO - __main__ - Step 42862: {'lr': 0.0004117113850966517, 'samples': 8229504, 'steps': 42861, 'loss/train': 0.9973611235618591} 08/30/2021 20:53:08 - INFO - __main__ - Step 42863: {'lr': 0.00041170733802533974, 'samples': 8229696, 'steps': 42862, 'loss/train': 0.8780614137649536} 08/30/2021 20:53:08 - INFO - __main__ - Step 42864: {'lr': 0.0004117032908811649, 'samples': 8229888, 'steps': 42863, 'loss/train': 1.8098726272583008} 08/30/2021 20:53:09 - INFO - __main__ - Step 42865: {'lr': 0.000411699243664129, 'samples': 8230080, 'steps': 42864, 'loss/train': 1.443603754043579} 08/30/2021 20:53:09 - INFO - __main__ - Step 42866: {'lr': 0.00041169519637423394, 'samples': 8230272, 'steps': 42865, 'loss/train': 1.1232253313064575} 08/30/2021 20:53:09 - INFO - __main__ - Step 42867: {'lr': 0.0004116911490114815, 'samples': 8230464, 'steps': 42866, 'loss/train': 1.7242082357406616} 08/30/2021 20:53:11 - INFO - __main__ - Step 42868: {'lr': 0.0004116871015758735, 'samples': 8230656, 'steps': 42867, 'loss/train': 1.5670757293701172} 08/30/2021 20:53:11 - INFO - __main__ - Step 42869: {'lr': 0.0004116830540674118, 'samples': 8230848, 'steps': 42868, 'loss/train': 1.870622158050537} 08/30/2021 20:53:12 - INFO - __main__ - Step 42870: {'lr': 0.00041167900648609825, 'samples': 8231040, 'steps': 42869, 'loss/train': 1.8268203735351562} 08/30/2021 20:53:12 - INFO - __main__ - Step 42871: {'lr': 0.00041167495883193464, 'samples': 8231232, 'steps': 42870, 'loss/train': 1.4920810461044312} 08/30/2021 20:53:12 - INFO - __main__ - Step 42872: {'lr': 0.00041167091110492273, 'samples': 8231424, 'steps': 42871, 'loss/train': 1.83479642868042} 08/30/2021 20:53:14 - INFO - __main__ - Step 42873: {'lr': 0.0004116668633050644, 'samples': 8231616, 'steps': 42872, 'loss/train': 1.071567416191101} 08/30/2021 20:53:15 - INFO - __main__ - Step 42874: {'lr': 0.0004116628154323616, 'samples': 8231808, 'steps': 42873, 'loss/train': 0.1352720558643341} 08/30/2021 20:53:15 - INFO - __main__ - Step 42875: {'lr': 0.0004116587674868159, 'samples': 8232000, 'steps': 42874, 'loss/train': 1.1919699907302856} 08/30/2021 20:53:16 - INFO - __main__ - Step 42876: {'lr': 0.00041165471946842924, 'samples': 8232192, 'steps': 42875, 'loss/train': 1.3944077491760254} 08/30/2021 20:53:16 - INFO - __main__ - Step 42877: {'lr': 0.00041165067137720356, 'samples': 8232384, 'steps': 42876, 'loss/train': 1.2207744121551514} 08/30/2021 20:53:18 - INFO - __main__ - Step 42878: {'lr': 0.00041164662321314054, 'samples': 8232576, 'steps': 42877, 'loss/train': 1.6044350862503052} 08/30/2021 20:53:18 - INFO - __main__ - Step 42879: {'lr': 0.000411642574976242, 'samples': 8232768, 'steps': 42878, 'loss/train': 0.9108901619911194} 08/30/2021 20:53:18 - INFO - __main__ - Step 42880: {'lr': 0.0004116385266665099, 'samples': 8232960, 'steps': 42879, 'loss/train': 1.097786784172058} 08/30/2021 20:53:19 - INFO - __main__ - Step 42881: {'lr': 0.0004116344782839459, 'samples': 8233152, 'steps': 42880, 'loss/train': 1.279736042022705} 08/30/2021 20:53:19 - INFO - __main__ - Step 42882: {'lr': 0.00041163042982855194, 'samples': 8233344, 'steps': 42881, 'loss/train': 0.9716207981109619} 08/30/2021 20:53:21 - INFO - __main__ - Step 42883: {'lr': 0.00041162638130032975, 'samples': 8233536, 'steps': 42882, 'loss/train': 0.08397163450717926} 08/30/2021 20:53:21 - INFO - __main__ - Step 42884: {'lr': 0.00041162233269928126, 'samples': 8233728, 'steps': 42883, 'loss/train': 1.1683320999145508} 08/30/2021 20:53:21 - INFO - __main__ - Step 42885: {'lr': 0.0004116182840254082, 'samples': 8233920, 'steps': 42884, 'loss/train': 1.6379175186157227} 08/30/2021 20:53:22 - INFO - __main__ - Step 42886: {'lr': 0.0004116142352787125, 'samples': 8234112, 'steps': 42885, 'loss/train': 1.2654114961624146} 08/30/2021 20:53:22 - INFO - __main__ - Step 42887: {'lr': 0.00041161018645919593, 'samples': 8234304, 'steps': 42886, 'loss/train': 1.6422559022903442} 08/30/2021 20:53:24 - INFO - __main__ - Step 42888: {'lr': 0.00041160613756686015, 'samples': 8234496, 'steps': 42887, 'loss/train': 1.6191211938858032} 08/30/2021 20:53:24 - INFO - __main__ - Step 42889: {'lr': 0.00041160208860170725, 'samples': 8234688, 'steps': 42888, 'loss/train': 1.5554444789886475} 08/30/2021 20:53:25 - INFO - __main__ - Step 42890: {'lr': 0.000411598039563739, 'samples': 8234880, 'steps': 42889, 'loss/train': 1.5288052558898926} 08/30/2021 20:53:25 - INFO - __main__ - Step 42891: {'lr': 0.0004115939904529571, 'samples': 8235072, 'steps': 42890, 'loss/train': 1.9154614210128784} 08/30/2021 20:53:25 - INFO - __main__ - Step 42892: {'lr': 0.00041158994126936347, 'samples': 8235264, 'steps': 42891, 'loss/train': 5.809218883514404} 08/30/2021 20:53:26 - INFO - __main__ - Step 42893: {'lr': 0.0004115858920129598, 'samples': 8235456, 'steps': 42892, 'loss/train': 0.41727232933044434} 08/30/2021 20:53:27 - INFO - __main__ - Step 42894: {'lr': 0.0004115818426837481, 'samples': 8235648, 'steps': 42893, 'loss/train': 1.4420056343078613} 08/30/2021 20:53:27 - INFO - __main__ - Step 42895: {'lr': 0.0004115777932817301, 'samples': 8235840, 'steps': 42894, 'loss/train': 1.2058171033859253} 08/30/2021 20:53:28 - INFO - __main__ - Step 42896: {'lr': 0.00041157374380690765, 'samples': 8236032, 'steps': 42895, 'loss/train': 1.7355314493179321} 08/30/2021 20:53:28 - INFO - __main__ - Step 42897: {'lr': 0.0004115696942592826, 'samples': 8236224, 'steps': 42896, 'loss/train': 1.4481213092803955} 08/30/2021 20:53:29 - INFO - __main__ - Step 42898: {'lr': 0.0004115656446388567, 'samples': 8236416, 'steps': 42897, 'loss/train': 1.7035605907440186} 08/30/2021 20:53:30 - INFO - __main__ - Step 42899: {'lr': 0.00041156159494563183, 'samples': 8236608, 'steps': 42898, 'loss/train': 1.4951162338256836} 08/30/2021 20:53:31 - INFO - __main__ - Step 42900: {'lr': 0.00041155754517960974, 'samples': 8236800, 'steps': 42899, 'loss/train': 1.2954660654067993} 08/30/2021 20:53:31 - INFO - __main__ - Step 42901: {'lr': 0.00041155349534079236, 'samples': 8236992, 'steps': 42900, 'loss/train': 1.0552476644515991} 08/30/2021 20:53:31 - INFO - __main__ - Step 42902: {'lr': 0.0004115494454291815, 'samples': 8237184, 'steps': 42901, 'loss/train': 0.16165167093276978} 08/30/2021 20:53:32 - INFO - __main__ - Step 42903: {'lr': 0.0004115453954447789, 'samples': 8237376, 'steps': 42902, 'loss/train': 1.3315397500991821} 08/30/2021 20:53:33 - INFO - __main__ - Step 42904: {'lr': 0.0004115413453875865, 'samples': 8237568, 'steps': 42903, 'loss/train': 1.1729339361190796} 08/30/2021 20:53:34 - INFO - __main__ - Step 42905: {'lr': 0.000411537295257606, 'samples': 8237760, 'steps': 42904, 'loss/train': 1.0337938070297241} 08/30/2021 20:53:34 - INFO - __main__ - Step 42906: {'lr': 0.00041153324505483933, 'samples': 8237952, 'steps': 42905, 'loss/train': 0.1835448443889618} 08/30/2021 20:53:35 - INFO - __main__ - Step 42907: {'lr': 0.0004115291947792882, 'samples': 8238144, 'steps': 42906, 'loss/train': 1.2645149230957031} 08/30/2021 20:53:35 - INFO - __main__ - Step 42908: {'lr': 0.00041152514443095454, 'samples': 8238336, 'steps': 42907, 'loss/train': 1.3040850162506104} 08/30/2021 20:53:36 - INFO - __main__ - Step 42909: {'lr': 0.00041152109400984015, 'samples': 8238528, 'steps': 42908, 'loss/train': 1.9677035808563232} 08/30/2021 20:53:37 - INFO - __main__ - Step 42910: {'lr': 0.0004115170435159469, 'samples': 8238720, 'steps': 42909, 'loss/train': 1.6824175119400024} 08/30/2021 20:53:37 - INFO - __main__ - Step 42911: {'lr': 0.00041151299294927657, 'samples': 8238912, 'steps': 42910, 'loss/train': 1.0541698932647705} 08/30/2021 20:53:38 - INFO - __main__ - Step 42912: {'lr': 0.0004115089423098309, 'samples': 8239104, 'steps': 42911, 'loss/train': 1.4474738836288452} 08/30/2021 20:53:38 - INFO - __main__ - Step 42913: {'lr': 0.00041150489159761186, 'samples': 8239296, 'steps': 42912, 'loss/train': 1.3622851371765137} 08/30/2021 20:53:40 - INFO - __main__ - Step 42914: {'lr': 0.00041150084081262105, 'samples': 8239488, 'steps': 42913, 'loss/train': 1.0948444604873657} 08/30/2021 20:53:40 - INFO - __main__ - Step 42915: {'lr': 0.0004114967899548606, 'samples': 8239680, 'steps': 42914, 'loss/train': 0.9798698425292969} 08/30/2021 20:53:40 - INFO - __main__ - Step 42916: {'lr': 0.0004114927390243322, 'samples': 8239872, 'steps': 42915, 'loss/train': 0.13289666175842285} 08/30/2021 20:53:41 - INFO - __main__ - Step 42917: {'lr': 0.00041148868802103766, 'samples': 8240064, 'steps': 42916, 'loss/train': 1.7086477279663086} 08/30/2021 20:53:41 - INFO - __main__ - Step 42918: {'lr': 0.00041148463694497874, 'samples': 8240256, 'steps': 42917, 'loss/train': 0.8621677160263062} 08/30/2021 20:53:43 - INFO - __main__ - Step 42919: {'lr': 0.00041148058579615733, 'samples': 8240448, 'steps': 42918, 'loss/train': 0.07445593178272247} 08/30/2021 20:53:44 - INFO - __main__ - Step 42920: {'lr': 0.00041147653457457534, 'samples': 8240640, 'steps': 42919, 'loss/train': 1.5192316770553589} 08/30/2021 20:53:44 - INFO - __main__ - Step 42921: {'lr': 0.0004114724832802345, 'samples': 8240832, 'steps': 42920, 'loss/train': 1.2820676565170288} 08/30/2021 20:53:44 - INFO - __main__ - Step 42922: {'lr': 0.0004114684319131366, 'samples': 8241024, 'steps': 42921, 'loss/train': 1.4727269411087036} 08/30/2021 20:53:45 - INFO - __main__ - Step 42923: {'lr': 0.00041146438047328347, 'samples': 8241216, 'steps': 42922, 'loss/train': 2.0088417530059814} 08/30/2021 20:53:46 - INFO - __main__ - Step 42924: {'lr': 0.0004114603289606771, 'samples': 8241408, 'steps': 42923, 'loss/train': 1.1138535737991333} 08/30/2021 20:53:47 - INFO - __main__ - Step 42925: {'lr': 0.00041145627737531915, 'samples': 8241600, 'steps': 42924, 'loss/train': 0.8508906960487366} 08/30/2021 20:53:47 - INFO - __main__ - Step 42926: {'lr': 0.0004114522257172115, 'samples': 8241792, 'steps': 42925, 'loss/train': 1.475974202156067} 08/30/2021 20:53:47 - INFO - __main__ - Step 42927: {'lr': 0.000411448173986356, 'samples': 8241984, 'steps': 42926, 'loss/train': 1.4380686283111572} 08/30/2021 20:53:48 - INFO - __main__ - Step 42928: {'lr': 0.0004114441221827544, 'samples': 8242176, 'steps': 42927, 'loss/train': 1.2631417512893677} 08/30/2021 20:53:48 - INFO - __main__ - Step 42929: {'lr': 0.0004114400703064085, 'samples': 8242368, 'steps': 42928, 'loss/train': 1.3651388883590698} 08/30/2021 20:53:49 - INFO - __main__ - Step 42930: {'lr': 0.0004114360183573203, 'samples': 8242560, 'steps': 42929, 'loss/train': 1.5953912734985352} 08/30/2021 20:53:50 - INFO - __main__ - Step 42931: {'lr': 0.0004114319663354915, 'samples': 8242752, 'steps': 42930, 'loss/train': 0.5755936503410339} 08/30/2021 20:53:50 - INFO - __main__ - Step 42932: {'lr': 0.000411427914240924, 'samples': 8242944, 'steps': 42931, 'loss/train': 1.3591316938400269} 08/30/2021 20:53:51 - INFO - __main__ - Step 42933: {'lr': 0.0004114238620736195, 'samples': 8243136, 'steps': 42932, 'loss/train': 1.2380326986312866} 08/30/2021 20:53:51 - INFO - __main__ - Step 42934: {'lr': 0.00041141980983357986, 'samples': 8243328, 'steps': 42933, 'loss/train': 1.1282389163970947} 08/30/2021 20:53:53 - INFO - __main__ - Step 42935: {'lr': 0.000411415757520807, 'samples': 8243520, 'steps': 42934, 'loss/train': 1.7134774923324585} 08/30/2021 20:53:53 - INFO - __main__ - Step 42936: {'lr': 0.00041141170513530267, 'samples': 8243712, 'steps': 42935, 'loss/train': 1.3076099157333374} 08/30/2021 20:53:53 - INFO - __main__ - Step 42937: {'lr': 0.0004114076526770688, 'samples': 8243904, 'steps': 42936, 'loss/train': 1.791196346282959} 08/30/2021 20:53:54 - INFO - __main__ - Step 42938: {'lr': 0.000411403600146107, 'samples': 8244096, 'steps': 42937, 'loss/train': 1.2904411554336548} 08/30/2021 20:53:54 - INFO - __main__ - Step 42939: {'lr': 0.0004113995475424193, 'samples': 8244288, 'steps': 42938, 'loss/train': 1.544174075126648} 08/30/2021 20:53:55 - INFO - __main__ - Step 42940: {'lr': 0.0004113954948660075, 'samples': 8244480, 'steps': 42939, 'loss/train': 1.528918981552124} 08/30/2021 20:53:56 - INFO - __main__ - Step 42941: {'lr': 0.00041139144211687327, 'samples': 8244672, 'steps': 42940, 'loss/train': 1.118261456489563} 08/30/2021 20:53:56 - INFO - __main__ - Step 42942: {'lr': 0.0004113873892950186, 'samples': 8244864, 'steps': 42941, 'loss/train': 1.538267970085144} 08/30/2021 20:53:57 - INFO - __main__ - Step 42943: {'lr': 0.00041138333640044523, 'samples': 8245056, 'steps': 42942, 'loss/train': 1.3038625717163086} 08/30/2021 20:53:57 - INFO - __main__ - Step 42944: {'lr': 0.0004113792834331551, 'samples': 8245248, 'steps': 42943, 'loss/train': 0.9847640991210938} 08/30/2021 20:53:58 - INFO - __main__ - Step 42945: {'lr': 0.00041137523039314994, 'samples': 8245440, 'steps': 42944, 'loss/train': 1.8071902990341187} 08/30/2021 20:53:59 - INFO - __main__ - Step 42946: {'lr': 0.0004113711772804315, 'samples': 8245632, 'steps': 42945, 'loss/train': 1.2316664457321167} 08/30/2021 20:53:59 - INFO - __main__ - Step 42947: {'lr': 0.0004113671240950018, 'samples': 8245824, 'steps': 42946, 'loss/train': 0.8486292958259583} 08/30/2021 20:54:00 - INFO - __main__ - Step 42948: {'lr': 0.0004113630708368625, 'samples': 8246016, 'steps': 42947, 'loss/train': 1.2827318906784058} 08/30/2021 20:54:00 - INFO - __main__ - Step 42949: {'lr': 0.0004113590175060155, 'samples': 8246208, 'steps': 42948, 'loss/train': 1.527235746383667} 08/30/2021 20:54:02 - INFO - __main__ - Step 42950: {'lr': 0.00041135496410246264, 'samples': 8246400, 'steps': 42949, 'loss/train': 1.4695416688919067} 08/30/2021 20:54:02 - INFO - __main__ - Step 42951: {'lr': 0.0004113509106262058, 'samples': 8246592, 'steps': 42950, 'loss/train': 1.556428074836731} 08/30/2021 20:54:02 - INFO - __main__ - Step 42952: {'lr': 0.00041134685707724656, 'samples': 8246784, 'steps': 42951, 'loss/train': 1.46836256980896} 08/30/2021 20:54:03 - INFO - __main__ - Step 42953: {'lr': 0.000411342803455587, 'samples': 8246976, 'steps': 42952, 'loss/train': 0.7759209871292114} 08/30/2021 20:54:03 - INFO - __main__ - Step 42954: {'lr': 0.0004113387497612289, 'samples': 8247168, 'steps': 42953, 'loss/train': 1.290662407875061} 08/30/2021 20:54:05 - INFO - __main__ - Step 42955: {'lr': 0.00041133469599417393, 'samples': 8247360, 'steps': 42954, 'loss/train': 1.3949353694915771} 08/30/2021 20:54:05 - INFO - __main__ - Step 42956: {'lr': 0.00041133064215442415, 'samples': 8247552, 'steps': 42955, 'loss/train': 1.7359212636947632} 08/30/2021 20:54:06 - INFO - __main__ - Step 42957: {'lr': 0.0004113265882419812, 'samples': 8247744, 'steps': 42956, 'loss/train': 0.11023519188165665} 08/30/2021 20:54:06 - INFO - __main__ - Step 42958: {'lr': 0.0004113225342568471, 'samples': 8247936, 'steps': 42957, 'loss/train': 1.3494611978530884} 08/30/2021 20:54:06 - INFO - __main__ - Step 42959: {'lr': 0.00041131848019902343, 'samples': 8248128, 'steps': 42958, 'loss/train': 0.9846700429916382} 08/30/2021 20:54:08 - INFO - __main__ - Step 42960: {'lr': 0.0004113144260685122, 'samples': 8248320, 'steps': 42959, 'loss/train': 0.4094661474227905} 08/30/2021 20:54:08 - INFO - __main__ - Step 42961: {'lr': 0.00041131037186531514, 'samples': 8248512, 'steps': 42960, 'loss/train': 1.7571051120758057} 08/30/2021 20:54:09 - INFO - __main__ - Step 42962: {'lr': 0.00041130631758943414, 'samples': 8248704, 'steps': 42961, 'loss/train': 1.472283959388733} 08/30/2021 20:54:09 - INFO - __main__ - Step 42963: {'lr': 0.00041130226324087094, 'samples': 8248896, 'steps': 42962, 'loss/train': 0.9628196954727173} 08/30/2021 20:54:09 - INFO - __main__ - Step 42964: {'lr': 0.00041129820881962754, 'samples': 8249088, 'steps': 42963, 'loss/train': 1.908008337020874} 08/30/2021 20:54:10 - INFO - __main__ - Step 42965: {'lr': 0.0004112941543257056, 'samples': 8249280, 'steps': 42964, 'loss/train': 1.7026253938674927} 08/30/2021 20:54:12 - INFO - __main__ - Step 42966: {'lr': 0.00041129009975910704, 'samples': 8249472, 'steps': 42965, 'loss/train': 1.1823099851608276} 08/30/2021 20:54:12 - INFO - __main__ - Step 42967: {'lr': 0.00041128604511983356, 'samples': 8249664, 'steps': 42966, 'loss/train': 0.098127081990242} 08/30/2021 20:54:13 - INFO - __main__ - Step 42968: {'lr': 0.00041128199040788715, 'samples': 8249856, 'steps': 42967, 'loss/train': 1.0449495315551758} 08/30/2021 20:54:13 - INFO - __main__ - Step 42969: {'lr': 0.00041127793562326955, 'samples': 8250048, 'steps': 42968, 'loss/train': 1.4471373558044434} 08/30/2021 20:54:13 - INFO - __main__ - Step 42970: {'lr': 0.0004112738807659826, 'samples': 8250240, 'steps': 42969, 'loss/train': 1.9988512992858887} 08/30/2021 20:54:15 - INFO - __main__ - Step 42971: {'lr': 0.00041126982583602817, 'samples': 8250432, 'steps': 42970, 'loss/train': 1.7404166460037231} 08/30/2021 20:54:16 - INFO - __main__ - Step 42972: {'lr': 0.00041126577083340797, 'samples': 8250624, 'steps': 42971, 'loss/train': 1.699367642402649} 08/30/2021 20:54:16 - INFO - __main__ - Step 42973: {'lr': 0.000411261715758124, 'samples': 8250816, 'steps': 42972, 'loss/train': 1.3783475160598755} 08/30/2021 20:54:17 - INFO - __main__ - Step 42974: {'lr': 0.0004112576606101779, 'samples': 8251008, 'steps': 42973, 'loss/train': 0.2923354208469391} 08/30/2021 20:54:17 - INFO - __main__ - Step 42975: {'lr': 0.0004112536053895716, 'samples': 8251200, 'steps': 42974, 'loss/train': 1.114609956741333} 08/30/2021 20:54:19 - INFO - __main__ - Step 42976: {'lr': 0.0004112495500963069, 'samples': 8251392, 'steps': 42975, 'loss/train': 1.5944143533706665} 08/30/2021 20:54:19 - INFO - __main__ - Step 42977: {'lr': 0.00041124549473038564, 'samples': 8251584, 'steps': 42976, 'loss/train': 1.1461849212646484} 08/30/2021 20:54:20 - INFO - __main__ - Step 42978: {'lr': 0.0004112414392918097, 'samples': 8251776, 'steps': 42977, 'loss/train': 1.4242169857025146} 08/30/2021 20:54:20 - INFO - __main__ - Step 42979: {'lr': 0.00041123738378058083, 'samples': 8251968, 'steps': 42978, 'loss/train': 1.6473948955535889} 08/30/2021 20:54:20 - INFO - __main__ - Step 42980: {'lr': 0.0004112333281967009, 'samples': 8252160, 'steps': 42979, 'loss/train': 1.504165530204773} 08/30/2021 20:54:22 - INFO - __main__ - Step 42981: {'lr': 0.00041122927254017173, 'samples': 8252352, 'steps': 42980, 'loss/train': 0.08477223664522171} 08/30/2021 20:54:23 - INFO - __main__ - Step 42982: {'lr': 0.0004112252168109951, 'samples': 8252544, 'steps': 42981, 'loss/train': 1.4745913743972778} 08/30/2021 20:54:23 - INFO - __main__ - Step 42983: {'lr': 0.0004112211610091728, 'samples': 8252736, 'steps': 42982, 'loss/train': 0.8877905607223511} 08/30/2021 20:54:23 - INFO - __main__ - Step 42984: {'lr': 0.0004112171051347069, 'samples': 8252928, 'steps': 42983, 'loss/train': 1.5028365850448608} 08/30/2021 20:54:24 - INFO - __main__ - Step 42985: {'lr': 0.00041121304918759893, 'samples': 8253120, 'steps': 42984, 'loss/train': 1.6529144048690796} 08/30/2021 20:54:24 - INFO - __main__ - Step 42986: {'lr': 0.00041120899316785095, 'samples': 8253312, 'steps': 42985, 'loss/train': 1.1791515350341797} 08/30/2021 20:54:25 - INFO - __main__ - Step 42987: {'lr': 0.00041120493707546456, 'samples': 8253504, 'steps': 42986, 'loss/train': 1.733790636062622} 08/30/2021 20:54:26 - INFO - __main__ - Step 42988: {'lr': 0.00041120088091044183, 'samples': 8253696, 'steps': 42987, 'loss/train': 1.5295441150665283} 08/30/2021 20:54:26 - INFO - __main__ - Step 42989: {'lr': 0.0004111968246727844, 'samples': 8253888, 'steps': 42988, 'loss/train': 1.394679069519043} 08/30/2021 20:54:27 - INFO - __main__ - Step 42990: {'lr': 0.0004111927683624942, 'samples': 8254080, 'steps': 42989, 'loss/train': 1.6150819063186646} 08/30/2021 20:54:27 - INFO - __main__ - Step 42991: {'lr': 0.00041118871197957306, 'samples': 8254272, 'steps': 42990, 'loss/train': 1.1454073190689087} 08/30/2021 20:54:28 - INFO - __main__ - Step 42992: {'lr': 0.00041118465552402274, 'samples': 8254464, 'steps': 42991, 'loss/train': 1.2107809782028198} 08/30/2021 20:54:29 - INFO - __main__ - Step 42993: {'lr': 0.00041118059899584503, 'samples': 8254656, 'steps': 42992, 'loss/train': 1.2875572443008423} 08/30/2021 20:54:29 - INFO - __main__ - Step 42994: {'lr': 0.00041117654239504193, 'samples': 8254848, 'steps': 42993, 'loss/train': 0.7668571472167969} 08/30/2021 20:54:30 - INFO - __main__ - Step 42995: {'lr': 0.0004111724857216151, 'samples': 8255040, 'steps': 42994, 'loss/train': 1.070777177810669} 08/30/2021 20:54:30 - INFO - __main__ - Step 42996: {'lr': 0.0004111684289755665, 'samples': 8255232, 'steps': 42995, 'loss/train': 1.1700886487960815} 08/30/2021 20:54:32 - INFO - __main__ - Step 42997: {'lr': 0.00041116437215689785, 'samples': 8255424, 'steps': 42996, 'loss/train': 1.3913509845733643} 08/30/2021 20:54:32 - INFO - __main__ - Step 42998: {'lr': 0.000411160315265611, 'samples': 8255616, 'steps': 42997, 'loss/train': 1.449651837348938} 08/30/2021 20:54:32 - INFO - __main__ - Step 42999: {'lr': 0.0004111562583017079, 'samples': 8255808, 'steps': 42998, 'loss/train': 1.2014268636703491} 08/30/2021 20:54:33 - INFO - __main__ - Step 43000: {'lr': 0.00041115220126519014, 'samples': 8256000, 'steps': 42999, 'loss/train': 1.4964714050292969} 08/30/2021 20:54:33 - INFO - __main__ - Step 43001: {'lr': 0.00041114814415605977, 'samples': 8256192, 'steps': 43000, 'loss/train': 0.9783806204795837} 08/30/2021 20:54:34 - INFO - __main__ - Step 43002: {'lr': 0.0004111440869743185, 'samples': 8256384, 'steps': 43001, 'loss/train': 1.5132663249969482} 08/30/2021 20:54:35 - INFO - __main__ - Step 43003: {'lr': 0.00041114002971996824, 'samples': 8256576, 'steps': 43002, 'loss/train': 1.4489054679870605} 08/30/2021 20:54:35 - INFO - __main__ - Step 43004: {'lr': 0.0004111359723930107, 'samples': 8256768, 'steps': 43003, 'loss/train': 1.620793104171753} 08/30/2021 20:54:36 - INFO - __main__ - Step 43005: {'lr': 0.00041113191499344784, 'samples': 8256960, 'steps': 43004, 'loss/train': 1.5167750120162964} 08/30/2021 20:54:36 - INFO - __main__ - Step 43006: {'lr': 0.0004111278575212814, 'samples': 8257152, 'steps': 43005, 'loss/train': 0.6572314500808716} 08/30/2021 20:54:37 - INFO - __main__ - Step 43007: {'lr': 0.0004111237999765132, 'samples': 8257344, 'steps': 43006, 'loss/train': 1.3900483846664429} 08/30/2021 20:54:38 - INFO - __main__ - Step 43008: {'lr': 0.0004111197423591452, 'samples': 8257536, 'steps': 43007, 'loss/train': 1.0233813524246216} 08/30/2021 20:54:38 - INFO - __main__ - Step 43009: {'lr': 0.000411115684669179, 'samples': 8257728, 'steps': 43008, 'loss/train': 1.621573567390442} 08/30/2021 20:54:39 - INFO - __main__ - Step 43010: {'lr': 0.00041111162690661665, 'samples': 8257920, 'steps': 43009, 'loss/train': 1.2237497568130493} 08/30/2021 20:54:39 - INFO - __main__ - Step 43011: {'lr': 0.00041110756907145984, 'samples': 8258112, 'steps': 43010, 'loss/train': 1.7718816995620728} 08/30/2021 20:54:40 - INFO - __main__ - Step 43012: {'lr': 0.0004111035111637105, 'samples': 8258304, 'steps': 43011, 'loss/train': 1.0399419069290161} 08/30/2021 20:54:41 - INFO - __main__ - Step 43013: {'lr': 0.00041109945318337034, 'samples': 8258496, 'steps': 43012, 'loss/train': 1.405644178390503} 08/30/2021 20:54:41 - INFO - __main__ - Step 43014: {'lr': 0.00041109539513044127, 'samples': 8258688, 'steps': 43013, 'loss/train': 1.6959083080291748} 08/30/2021 20:54:42 - INFO - __main__ - Step 43015: {'lr': 0.0004110913370049251, 'samples': 8258880, 'steps': 43014, 'loss/train': 1.3006491661071777} 08/30/2021 20:54:42 - INFO - __main__ - Step 43016: {'lr': 0.00041108727880682363, 'samples': 8259072, 'steps': 43015, 'loss/train': 1.342881679534912} 08/30/2021 20:54:43 - INFO - __main__ - Step 43017: {'lr': 0.0004110832205361388, 'samples': 8259264, 'steps': 43016, 'loss/train': 0.15349045395851135} 08/30/2021 20:54:44 - INFO - __main__ - Step 43018: {'lr': 0.0004110791621928723, 'samples': 8259456, 'steps': 43017, 'loss/train': 1.2687389850616455} 08/30/2021 20:54:44 - INFO - __main__ - Step 43019: {'lr': 0.00041107510377702604, 'samples': 8259648, 'steps': 43018, 'loss/train': 1.9783213138580322} 08/30/2021 20:54:45 - INFO - __main__ - Step 43020: {'lr': 0.00041107104528860186, 'samples': 8259840, 'steps': 43019, 'loss/train': 1.0433523654937744} 08/30/2021 20:54:45 - INFO - __main__ - Step 43021: {'lr': 0.00041106698672760145, 'samples': 8260032, 'steps': 43020, 'loss/train': 1.1559176445007324} 08/30/2021 20:54:45 - INFO - __main__ - Step 43022: {'lr': 0.0004110629280940268, 'samples': 8260224, 'steps': 43021, 'loss/train': 1.5960071086883545} 08/30/2021 20:54:47 - INFO - __main__ - Step 43023: {'lr': 0.0004110588693878796, 'samples': 8260416, 'steps': 43022, 'loss/train': 0.8455272316932678} 08/30/2021 20:54:48 - INFO - __main__ - Step 43024: {'lr': 0.0004110548106091619, 'samples': 8260608, 'steps': 43023, 'loss/train': 1.1341500282287598} 08/30/2021 20:54:48 - INFO - __main__ - Step 43025: {'lr': 0.00041105075175787534, 'samples': 8260800, 'steps': 43024, 'loss/train': 1.5918952226638794} 08/30/2021 20:54:49 - INFO - __main__ - Step 43026: {'lr': 0.00041104669283402174, 'samples': 8260992, 'steps': 43025, 'loss/train': 1.2125768661499023} 08/30/2021 20:54:49 - INFO - __main__ - Step 43027: {'lr': 0.00041104263383760304, 'samples': 8261184, 'steps': 43026, 'loss/train': 0.5623721480369568} 08/30/2021 20:54:50 - INFO - __main__ - Step 43028: {'lr': 0.000411038574768621, 'samples': 8261376, 'steps': 43027, 'loss/train': 1.2327876091003418} 08/30/2021 20:54:51 - INFO - __main__ - Step 43029: {'lr': 0.00041103451562707745, 'samples': 8261568, 'steps': 43028, 'loss/train': 1.1186000108718872} 08/30/2021 20:54:51 - INFO - __main__ - Step 43030: {'lr': 0.0004110304564129742, 'samples': 8261760, 'steps': 43029, 'loss/train': 1.7397935390472412} 08/30/2021 20:54:51 - INFO - __main__ - Step 43031: {'lr': 0.00041102639712631316, 'samples': 8261952, 'steps': 43030, 'loss/train': 1.7311002016067505} 08/30/2021 20:54:52 - INFO - __main__ - Step 43032: {'lr': 0.0004110223377670962, 'samples': 8262144, 'steps': 43031, 'loss/train': 1.5193501710891724} 08/30/2021 20:54:54 - INFO - __main__ - Step 43033: {'lr': 0.0004110182783353249, 'samples': 8262336, 'steps': 43032, 'loss/train': 1.6572611331939697} 08/30/2021 20:54:54 - INFO - __main__ - Step 43034: {'lr': 0.0004110142188310013, 'samples': 8262528, 'steps': 43033, 'loss/train': 1.1107121706008911} 08/30/2021 20:54:55 - INFO - __main__ - Step 43035: {'lr': 0.0004110101592541272, 'samples': 8262720, 'steps': 43034, 'loss/train': 1.4978253841400146} 08/30/2021 20:54:55 - INFO - __main__ - Step 43036: {'lr': 0.0004110060996047044, 'samples': 8262912, 'steps': 43035, 'loss/train': 1.8207767009735107} 08/30/2021 20:54:55 - INFO - __main__ - Step 43037: {'lr': 0.00041100203988273475, 'samples': 8263104, 'steps': 43036, 'loss/train': 1.5406898260116577} 08/30/2021 20:54:56 - INFO - __main__ - Step 43038: {'lr': 0.0004109979800882201, 'samples': 8263296, 'steps': 43037, 'loss/train': 0.8528545498847961} 08/30/2021 20:54:57 - INFO - __main__ - Step 43039: {'lr': 0.00041099392022116214, 'samples': 8263488, 'steps': 43038, 'loss/train': 1.31240975856781} 08/30/2021 20:54:58 - INFO - __main__ - Step 43040: {'lr': 0.0004109898602815629, 'samples': 8263680, 'steps': 43039, 'loss/train': 1.2402949333190918} 08/30/2021 20:54:58 - INFO - __main__ - Step 43041: {'lr': 0.000410985800269424, 'samples': 8263872, 'steps': 43040, 'loss/train': 1.3851898908615112} 08/30/2021 20:54:58 - INFO - __main__ - Step 43042: {'lr': 0.00041098174018474747, 'samples': 8264064, 'steps': 43041, 'loss/train': 1.4205424785614014} 08/30/2021 20:54:59 - INFO - __main__ - Step 43043: {'lr': 0.000410977680027535, 'samples': 8264256, 'steps': 43042, 'loss/train': 1.4728164672851562} 08/30/2021 20:55:00 - INFO - __main__ - Step 43044: {'lr': 0.00041097361979778853, 'samples': 8264448, 'steps': 43043, 'loss/train': 1.7134778499603271} 08/30/2021 20:55:01 - INFO - __main__ - Step 43045: {'lr': 0.00041096955949550983, 'samples': 8264640, 'steps': 43044, 'loss/train': 2.695533037185669} 08/30/2021 20:55:01 - INFO - __main__ - Step 43046: {'lr': 0.00041096549912070067, 'samples': 8264832, 'steps': 43045, 'loss/train': 1.2888792753219604} 08/30/2021 20:55:02 - INFO - __main__ - Step 43047: {'lr': 0.000410961438673363, 'samples': 8265024, 'steps': 43046, 'loss/train': 1.505315899848938} 08/30/2021 20:55:02 - INFO - __main__ - Step 43048: {'lr': 0.0004109573781534985, 'samples': 8265216, 'steps': 43047, 'loss/train': 2.0587618350982666} 08/30/2021 20:55:04 - INFO - __main__ - Step 43049: {'lr': 0.0004109533175611092, 'samples': 8265408, 'steps': 43048, 'loss/train': 1.5550066232681274} 08/30/2021 20:55:04 - INFO - __main__ - Step 43050: {'lr': 0.0004109492568961968, 'samples': 8265600, 'steps': 43049, 'loss/train': 1.3739714622497559} 08/30/2021 20:55:04 - INFO - __main__ - Step 43051: {'lr': 0.00041094519615876313, 'samples': 8265792, 'steps': 43050, 'loss/train': 1.5388081073760986} 08/30/2021 20:55:05 - INFO - __main__ - Step 43052: {'lr': 0.0004109411353488101, 'samples': 8265984, 'steps': 43051, 'loss/train': 1.6552338600158691} 08/30/2021 20:55:05 - INFO - __main__ - Step 43053: {'lr': 0.00041093707446633934, 'samples': 8266176, 'steps': 43052, 'loss/train': 1.3406568765640259} 08/30/2021 20:55:07 - INFO - __main__ - Step 43054: {'lr': 0.00041093301351135294, 'samples': 8266368, 'steps': 43053, 'loss/train': 0.39391854405403137} 08/30/2021 20:55:07 - INFO - __main__ - Step 43055: {'lr': 0.00041092895248385255, 'samples': 8266560, 'steps': 43054, 'loss/train': 1.4422074556350708} 08/30/2021 20:55:08 - INFO - __main__ - Step 43056: {'lr': 0.00041092489138384, 'samples': 8266752, 'steps': 43055, 'loss/train': 0.11934449523687363} 08/30/2021 20:55:08 - INFO - __main__ - Step 43057: {'lr': 0.0004109208302113173, 'samples': 8266944, 'steps': 43056, 'loss/train': 1.5346908569335938} 08/30/2021 20:55:08 - INFO - __main__ - Step 43058: {'lr': 0.00041091676896628604, 'samples': 8267136, 'steps': 43057, 'loss/train': 0.6464435458183289} 08/30/2021 20:55:10 - INFO - __main__ - Step 43059: {'lr': 0.00041091270764874823, 'samples': 8267328, 'steps': 43058, 'loss/train': 1.2979649305343628} 08/30/2021 20:55:11 - INFO - __main__ - Step 43060: {'lr': 0.0004109086462587056, 'samples': 8267520, 'steps': 43059, 'loss/train': 1.1548914909362793} 08/30/2021 20:55:11 - INFO - __main__ - Step 43061: {'lr': 0.0004109045847961601, 'samples': 8267712, 'steps': 43060, 'loss/train': 0.536292552947998} 08/30/2021 20:55:11 - INFO - __main__ - Step 43062: {'lr': 0.0004109005232611134, 'samples': 8267904, 'steps': 43061, 'loss/train': 0.4752870202064514} 08/30/2021 20:55:12 - INFO - __main__ - Step 43063: {'lr': 0.00041089646165356743, 'samples': 8268096, 'steps': 43062, 'loss/train': 0.8744156956672668} 08/30/2021 20:55:12 - INFO - __main__ - Step 43064: {'lr': 0.000410892399973524, 'samples': 8268288, 'steps': 43063, 'loss/train': 1.301539659500122} 08/30/2021 20:55:14 - INFO - __main__ - Step 43065: {'lr': 0.00041088833822098495, 'samples': 8268480, 'steps': 43064, 'loss/train': 1.0908784866333008} 08/30/2021 20:55:14 - INFO - __main__ - Step 43066: {'lr': 0.00041088427639595206, 'samples': 8268672, 'steps': 43065, 'loss/train': 1.5283879041671753} 08/30/2021 20:55:14 - INFO - __main__ - Step 43067: {'lr': 0.0004108802144984273, 'samples': 8268864, 'steps': 43066, 'loss/train': 1.5658838748931885} 08/30/2021 20:55:15 - INFO - __main__ - Step 43068: {'lr': 0.0004108761525284123, 'samples': 8269056, 'steps': 43067, 'loss/train': 1.3104747533798218} 08/30/2021 20:55:15 - INFO - __main__ - Step 43069: {'lr': 0.000410872090485909, 'samples': 8269248, 'steps': 43068, 'loss/train': 1.3385337591171265} 08/30/2021 20:55:17 - INFO - __main__ - Step 43070: {'lr': 0.00041086802837091916, 'samples': 8269440, 'steps': 43069, 'loss/train': 1.539482831954956} 08/30/2021 20:55:17 - INFO - __main__ - Step 43071: {'lr': 0.00041086396618344475, 'samples': 8269632, 'steps': 43070, 'loss/train': 1.0114749670028687} 08/30/2021 20:55:18 - INFO - __main__ - Step 43072: {'lr': 0.0004108599039234875, 'samples': 8269824, 'steps': 43071, 'loss/train': 1.4196584224700928} 08/30/2021 20:55:18 - INFO - __main__ - Step 43073: {'lr': 0.00041085584159104925, 'samples': 8270016, 'steps': 43072, 'loss/train': 0.05706416070461273} 08/30/2021 20:55:18 - INFO - __main__ - Step 43074: {'lr': 0.00041085177918613185, 'samples': 8270208, 'steps': 43073, 'loss/train': 2.471883773803711} 08/30/2021 20:55:20 - INFO - __main__ - Step 43075: {'lr': 0.0004108477167087371, 'samples': 8270400, 'steps': 43074, 'loss/train': 0.9876798391342163} 08/30/2021 20:55:21 - INFO - __main__ - Step 43076: {'lr': 0.0004108436541588669, 'samples': 8270592, 'steps': 43075, 'loss/train': 1.0809775590896606} 08/30/2021 20:55:21 - INFO - __main__ - Step 43077: {'lr': 0.000410839591536523, 'samples': 8270784, 'steps': 43076, 'loss/train': 1.496696949005127} 08/30/2021 20:55:21 - INFO - __main__ - Step 43078: {'lr': 0.00041083552884170726, 'samples': 8270976, 'steps': 43077, 'loss/train': 1.478933572769165} 08/30/2021 20:55:22 - INFO - __main__ - Step 43079: {'lr': 0.0004108314660744216, 'samples': 8271168, 'steps': 43078, 'loss/train': 1.5491466522216797} 08/30/2021 20:55:22 - INFO - __main__ - Step 43080: {'lr': 0.0004108274032346676, 'samples': 8271360, 'steps': 43079, 'loss/train': 1.7027873992919922} 08/30/2021 20:55:25 - INFO - __main__ - Step 43081: {'lr': 0.0004108233403224474, 'samples': 8271552, 'steps': 43080, 'loss/train': 1.9535102844238281} 08/30/2021 20:55:26 - INFO - __main__ - Step 43082: {'lr': 0.0004108192773377626, 'samples': 8271744, 'steps': 43081, 'loss/train': 0.9428542852401733} 08/30/2021 20:55:26 - INFO - __main__ - Step 43083: {'lr': 0.0004108152142806151, 'samples': 8271936, 'steps': 43082, 'loss/train': 1.867835521697998} 08/30/2021 20:55:27 - INFO - __main__ - Step 43084: {'lr': 0.00041081115115100677, 'samples': 8272128, 'steps': 43083, 'loss/train': 2.852897882461548} 08/30/2021 20:55:27 - INFO - __main__ - Step 43085: {'lr': 0.0004108070879489395, 'samples': 8272320, 'steps': 43084, 'loss/train': 3.130497694015503} 08/30/2021 20:55:27 - INFO - __main__ - Step 43086: {'lr': 0.0004108030246744149, 'samples': 8272512, 'steps': 43085, 'loss/train': 2.817951202392578} 08/30/2021 20:55:28 - INFO - __main__ - Step 43087: {'lr': 0.00041079896132743506, 'samples': 8272704, 'steps': 43086, 'loss/train': 3.796910524368286} 08/30/2021 20:55:28 - INFO - __main__ - Step 43088: {'lr': 0.0004107948979080016, 'samples': 8272896, 'steps': 43087, 'loss/train': 2.6971192359924316} 08/30/2021 20:55:29 - INFO - __main__ - Step 43089: {'lr': 0.00041079083441611646, 'samples': 8273088, 'steps': 43088, 'loss/train': 1.759987711906433} 08/30/2021 20:55:30 - INFO - __main__ - Step 43090: {'lr': 0.0004107867708517815, 'samples': 8273280, 'steps': 43089, 'loss/train': 2.4432783126831055} 08/30/2021 20:55:30 - INFO - __main__ - Step 43091: {'lr': 0.0004107827072149984, 'samples': 8273472, 'steps': 43090, 'loss/train': 2.1201558113098145} 08/30/2021 20:55:31 - INFO - __main__ - Step 43092: {'lr': 0.0004107786435057692, 'samples': 8273664, 'steps': 43091, 'loss/train': 1.9819567203521729} 08/30/2021 20:55:31 - INFO - __main__ - Step 43093: {'lr': 0.0004107745797240956, 'samples': 8273856, 'steps': 43092, 'loss/train': 1.7590715885162354} 08/30/2021 20:55:32 - INFO - __main__ - Step 43094: {'lr': 0.0004107705158699794, 'samples': 8274048, 'steps': 43093, 'loss/train': 2.135681629180908} 08/30/2021 20:55:33 - INFO - __main__ - Step 43095: {'lr': 0.00041076645194342254, 'samples': 8274240, 'steps': 43094, 'loss/train': 1.6176354885101318} 08/30/2021 20:55:33 - INFO - __main__ - Step 43096: {'lr': 0.00041076238794442675, 'samples': 8274432, 'steps': 43095, 'loss/train': 2.0285708904266357} 08/30/2021 20:55:34 - INFO - __main__ - Step 43097: {'lr': 0.00041075832387299396, 'samples': 8274624, 'steps': 43096, 'loss/train': 2.0638937950134277} 08/30/2021 20:55:34 - INFO - __main__ - Step 43098: {'lr': 0.00041075425972912595, 'samples': 8274816, 'steps': 43097, 'loss/train': 1.5374903678894043} 08/30/2021 20:55:35 - INFO - __main__ - Step 43099: {'lr': 0.00041075019551282455, 'samples': 8275008, 'steps': 43098, 'loss/train': 1.8236980438232422} 08/30/2021 20:55:36 - INFO - __main__ - Step 43100: {'lr': 0.00041074613122409157, 'samples': 8275200, 'steps': 43099, 'loss/train': 2.400517225265503} 08/30/2021 20:55:36 - INFO - __main__ - Step 43101: {'lr': 0.0004107420668629289, 'samples': 8275392, 'steps': 43100, 'loss/train': 1.7645496129989624} 08/30/2021 20:55:36 - INFO - __main__ - Step 43102: {'lr': 0.00041073800242933826, 'samples': 8275584, 'steps': 43101, 'loss/train': 2.390949010848999} 08/30/2021 20:55:37 - INFO - __main__ - Step 43103: {'lr': 0.00041073393792332157, 'samples': 8275776, 'steps': 43102, 'loss/train': 1.0891464948654175} 08/30/2021 20:55:38 - INFO - __main__ - Step 43104: {'lr': 0.0004107298733448807, 'samples': 8275968, 'steps': 43103, 'loss/train': 2.014225959777832} 08/30/2021 20:55:39 - INFO - __main__ - Step 43105: {'lr': 0.0004107258086940174, 'samples': 8276160, 'steps': 43104, 'loss/train': 1.7214444875717163} 08/30/2021 20:55:39 - INFO - __main__ - Step 43106: {'lr': 0.0004107217439707336, 'samples': 8276352, 'steps': 43105, 'loss/train': 1.5326868295669556} 08/30/2021 20:55:39 - INFO - __main__ - Step 43107: {'lr': 0.000410717679175031, 'samples': 8276544, 'steps': 43106, 'loss/train': 1.7199546098709106} 08/30/2021 20:55:40 - INFO - __main__ - Step 43108: {'lr': 0.00041071361430691143, 'samples': 8276736, 'steps': 43107, 'loss/train': 1.5477620363235474} 08/30/2021 20:55:41 - INFO - __main__ - Step 43109: {'lr': 0.00041070954936637687, 'samples': 8276928, 'steps': 43108, 'loss/train': 1.5906322002410889} 08/30/2021 20:55:42 - INFO - __main__ - Step 43110: {'lr': 0.00041070548435342903, 'samples': 8277120, 'steps': 43109, 'loss/train': 1.9322139024734497} 08/30/2021 20:55:42 - INFO - __main__ - Step 43111: {'lr': 0.00041070141926806983, 'samples': 8277312, 'steps': 43110, 'loss/train': 0.8504245281219482} 08/30/2021 20:55:43 - INFO - __main__ - Step 43112: {'lr': 0.00041069735411030105, 'samples': 8277504, 'steps': 43111, 'loss/train': 1.200981616973877} 08/30/2021 20:55:43 - INFO - __main__ - Step 43113: {'lr': 0.00041069328888012447, 'samples': 8277696, 'steps': 43112, 'loss/train': 1.0931965112686157} 08/30/2021 20:55:44 - INFO - __main__ - Step 43114: {'lr': 0.000410689223577542, 'samples': 8277888, 'steps': 43113, 'loss/train': 1.9876457452774048} 08/30/2021 20:55:45 - INFO - __main__ - Step 43115: {'lr': 0.00041068515820255543, 'samples': 8278080, 'steps': 43114, 'loss/train': 1.8466354608535767} 08/30/2021 20:55:45 - INFO - __main__ - Step 43116: {'lr': 0.00041068109275516665, 'samples': 8278272, 'steps': 43115, 'loss/train': 1.5738556385040283} 08/30/2021 20:55:46 - INFO - __main__ - Step 43117: {'lr': 0.0004106770272353774, 'samples': 8278464, 'steps': 43116, 'loss/train': 1.864491581916809} 08/30/2021 20:55:46 - INFO - __main__ - Step 43118: {'lr': 0.00041067296164318956, 'samples': 8278656, 'steps': 43117, 'loss/train': 1.5471930503845215} 08/30/2021 20:55:47 - INFO - __main__ - Step 43119: {'lr': 0.000410668895978605, 'samples': 8278848, 'steps': 43118, 'loss/train': 1.773576021194458} 08/30/2021 20:55:48 - INFO - __main__ - Step 43120: {'lr': 0.0004106648302416255, 'samples': 8279040, 'steps': 43119, 'loss/train': 1.5012117624282837} 08/30/2021 20:55:48 - INFO - __main__ - Step 43121: {'lr': 0.0004106607644322529, 'samples': 8279232, 'steps': 43120, 'loss/train': 1.490515947341919} 08/30/2021 20:55:49 - INFO - __main__ - Step 43122: {'lr': 0.00041065669855048896, 'samples': 8279424, 'steps': 43121, 'loss/train': 1.4472399950027466} 08/30/2021 20:55:49 - INFO - __main__ - Step 43123: {'lr': 0.0004106526325963357, 'samples': 8279616, 'steps': 43122, 'loss/train': 1.9854379892349243} 08/30/2021 20:55:50 - INFO - __main__ - Step 43124: {'lr': 0.0004106485665697948, 'samples': 8279808, 'steps': 43123, 'loss/train': 2.118741989135742} 08/30/2021 20:55:51 - INFO - __main__ - Step 43125: {'lr': 0.00041064450047086814, 'samples': 8280000, 'steps': 43124, 'loss/train': 1.5702439546585083} 08/30/2021 20:55:51 - INFO - __main__ - Step 43126: {'lr': 0.00041064043429955756, 'samples': 8280192, 'steps': 43125, 'loss/train': 1.6925501823425293} 08/30/2021 20:55:52 - INFO - __main__ - Step 43127: {'lr': 0.0004106363680558649, 'samples': 8280384, 'steps': 43126, 'loss/train': 0.9814291000366211} 08/30/2021 20:55:52 - INFO - __main__ - Step 43128: {'lr': 0.0004106323017397919, 'samples': 8280576, 'steps': 43127, 'loss/train': 1.7775154113769531} 08/30/2021 20:55:53 - INFO - __main__ - Step 43129: {'lr': 0.00041062823535134053, 'samples': 8280768, 'steps': 43128, 'loss/train': 1.8378931283950806} 08/30/2021 20:55:54 - INFO - __main__ - Step 43130: {'lr': 0.0004106241688905126, 'samples': 8280960, 'steps': 43129, 'loss/train': 1.81867516040802} 08/30/2021 20:55:54 - INFO - __main__ - Step 43131: {'lr': 0.00041062010235730974, 'samples': 8281152, 'steps': 43130, 'loss/train': 1.5315477848052979} 08/30/2021 20:55:55 - INFO - __main__ - Step 43132: {'lr': 0.0004106160357517341, 'samples': 8281344, 'steps': 43131, 'loss/train': 1.633876919746399} 08/30/2021 20:55:55 - INFO - __main__ - Step 43133: {'lr': 0.00041061196907378727, 'samples': 8281536, 'steps': 43132, 'loss/train': 1.5402170419692993} 08/30/2021 20:55:57 - INFO - __main__ - Step 43134: {'lr': 0.00041060790232347116, 'samples': 8281728, 'steps': 43133, 'loss/train': 1.6886050701141357} 08/30/2021 20:55:57 - INFO - __main__ - Step 43135: {'lr': 0.00041060383550078764, 'samples': 8281920, 'steps': 43134, 'loss/train': 1.912307620048523} 08/30/2021 20:55:58 - INFO - __main__ - Step 43136: {'lr': 0.00041059976860573845, 'samples': 8282112, 'steps': 43135, 'loss/train': 2.060131072998047} 08/30/2021 20:55:58 - INFO - __main__ - Step 43137: {'lr': 0.00041059570163832555, 'samples': 8282304, 'steps': 43136, 'loss/train': 1.4196592569351196} 08/30/2021 20:55:58 - INFO - __main__ - Step 43138: {'lr': 0.00041059163459855066, 'samples': 8282496, 'steps': 43137, 'loss/train': 1.8933769464492798} 08/30/2021 20:56:00 - INFO - __main__ - Step 43139: {'lr': 0.00041058756748641573, 'samples': 8282688, 'steps': 43138, 'loss/train': 1.4502156972885132} 08/30/2021 20:56:00 - INFO - __main__ - Step 43140: {'lr': 0.0004105835003019225, 'samples': 8282880, 'steps': 43139, 'loss/train': 1.7310553789138794} 08/30/2021 20:56:01 - INFO - __main__ - Step 43141: {'lr': 0.00041057943304507273, 'samples': 8283072, 'steps': 43140, 'loss/train': 2.4128997325897217} 08/30/2021 20:56:01 - INFO - __main__ - Step 43142: {'lr': 0.0004105753657158684, 'samples': 8283264, 'steps': 43141, 'loss/train': 1.6390939950942993} 08/30/2021 20:56:02 - INFO - __main__ - Step 43143: {'lr': 0.00041057129831431133, 'samples': 8283456, 'steps': 43142, 'loss/train': 1.4584561586380005} 08/30/2021 20:56:02 - INFO - __main__ - Step 43144: {'lr': 0.00041056723084040324, 'samples': 8283648, 'steps': 43143, 'loss/train': 2.5227386951446533} 08/30/2021 20:56:04 - INFO - __main__ - Step 43145: {'lr': 0.00041056316329414613, 'samples': 8283840, 'steps': 43144, 'loss/train': 1.335874319076538} 08/30/2021 20:56:04 - INFO - __main__ - Step 43146: {'lr': 0.00041055909567554166, 'samples': 8284032, 'steps': 43145, 'loss/train': 1.2328912019729614} 08/30/2021 20:56:04 - INFO - __main__ - Step 43147: {'lr': 0.00041055502798459175, 'samples': 8284224, 'steps': 43146, 'loss/train': 0.1554865539073944} 08/30/2021 20:56:05 - INFO - __main__ - Step 43148: {'lr': 0.00041055096022129823, 'samples': 8284416, 'steps': 43147, 'loss/train': 1.098775863647461} 08/30/2021 20:56:05 - INFO - __main__ - Step 43149: {'lr': 0.0004105468923856629, 'samples': 8284608, 'steps': 43148, 'loss/train': 1.5607126951217651} 08/30/2021 20:56:07 - INFO - __main__ - Step 43150: {'lr': 0.00041054282447768763, 'samples': 8284800, 'steps': 43149, 'loss/train': 0.9097418785095215} 08/30/2021 20:56:07 - INFO - __main__ - Step 43151: {'lr': 0.00041053875649737424, 'samples': 8284992, 'steps': 43150, 'loss/train': 1.4875164031982422} 08/30/2021 20:56:08 - INFO - __main__ - Step 43152: {'lr': 0.0004105346884447246, 'samples': 8285184, 'steps': 43151, 'loss/train': 1.6775925159454346} 08/30/2021 20:56:08 - INFO - __main__ - Step 43153: {'lr': 0.00041053062031974055, 'samples': 8285376, 'steps': 43152, 'loss/train': 2.6256110668182373} 08/30/2021 20:56:08 - INFO - __main__ - Step 43154: {'lr': 0.00041052655212242377, 'samples': 8285568, 'steps': 43153, 'loss/train': 1.8446276187896729} 08/30/2021 20:56:10 - INFO - __main__ - Step 43155: {'lr': 0.00041052248385277623, 'samples': 8285760, 'steps': 43154, 'loss/train': 1.4902443885803223} 08/30/2021 20:56:10 - INFO - __main__ - Step 43156: {'lr': 0.0004105184155107998, 'samples': 8285952, 'steps': 43155, 'loss/train': 1.7433875799179077} 08/30/2021 20:56:11 - INFO - __main__ - Step 43157: {'lr': 0.00041051434709649614, 'samples': 8286144, 'steps': 43156, 'loss/train': 1.2297192811965942} 08/30/2021 20:56:11 - INFO - __main__ - Step 43158: {'lr': 0.0004105102786098672, 'samples': 8286336, 'steps': 43157, 'loss/train': 1.7540655136108398} 08/30/2021 20:56:11 - INFO - __main__ - Step 43159: {'lr': 0.0004105062100509149, 'samples': 8286528, 'steps': 43158, 'loss/train': 2.0551722049713135} 08/30/2021 20:56:13 - INFO - __main__ - Step 43160: {'lr': 0.000410502141419641, 'samples': 8286720, 'steps': 43159, 'loss/train': 0.9355669021606445} 08/30/2021 20:56:14 - INFO - __main__ - Step 43161: {'lr': 0.00041049807271604724, 'samples': 8286912, 'steps': 43160, 'loss/train': 0.8614419102668762} 08/30/2021 20:56:14 - INFO - __main__ - Step 43162: {'lr': 0.00041049400394013545, 'samples': 8287104, 'steps': 43161, 'loss/train': 1.5363117456436157} 08/30/2021 20:56:14 - INFO - __main__ - Step 43163: {'lr': 0.0004104899350919077, 'samples': 8287296, 'steps': 43162, 'loss/train': 1.1739214658737183} 08/30/2021 20:56:15 - INFO - __main__ - Step 43164: {'lr': 0.0004104858661713655, 'samples': 8287488, 'steps': 43163, 'loss/train': 1.264413833618164} 08/30/2021 20:56:15 - INFO - __main__ - Step 43165: {'lr': 0.00041048179717851095, 'samples': 8287680, 'steps': 43164, 'loss/train': 1.8646942377090454} 08/30/2021 20:56:17 - INFO - __main__ - Step 43166: {'lr': 0.00041047772811334584, 'samples': 8287872, 'steps': 43165, 'loss/train': 1.9736560583114624} 08/30/2021 20:56:17 - INFO - __main__ - Step 43167: {'lr': 0.0004104736589758719, 'samples': 8288064, 'steps': 43166, 'loss/train': 2.0940358638763428} 08/30/2021 20:56:17 - INFO - __main__ - Step 43168: {'lr': 0.0004104695897660909, 'samples': 8288256, 'steps': 43167, 'loss/train': 1.7892898321151733} 08/30/2021 20:56:18 - INFO - __main__ - Step 43169: {'lr': 0.0004104655204840048, 'samples': 8288448, 'steps': 43168, 'loss/train': 1.464721441268921} 08/30/2021 20:56:18 - INFO - __main__ - Step 43170: {'lr': 0.0004104614511296155, 'samples': 8288640, 'steps': 43169, 'loss/train': 1.292941927909851} 08/30/2021 20:56:20 - INFO - __main__ - Step 43171: {'lr': 0.00041045738170292467, 'samples': 8288832, 'steps': 43170, 'loss/train': 1.2955961227416992} 08/30/2021 20:56:20 - INFO - __main__ - Step 43172: {'lr': 0.0004104533122039342, 'samples': 8289024, 'steps': 43171, 'loss/train': 1.3241108655929565} 08/30/2021 20:56:20 - INFO - __main__ - Step 43173: {'lr': 0.00041044924263264603, 'samples': 8289216, 'steps': 43172, 'loss/train': 1.7729849815368652} 08/30/2021 20:56:21 - INFO - __main__ - Step 43174: {'lr': 0.00041044517298906194, 'samples': 8289408, 'steps': 43173, 'loss/train': 1.3600283861160278} 08/30/2021 20:56:21 - INFO - __main__ - Step 43175: {'lr': 0.0004104411032731836, 'samples': 8289600, 'steps': 43174, 'loss/train': 1.2630465030670166} 08/30/2021 20:56:23 - INFO - __main__ - Step 43176: {'lr': 0.00041043703348501304, 'samples': 8289792, 'steps': 43175, 'loss/train': 1.2705659866333008} 08/30/2021 20:56:23 - INFO - __main__ - Step 43177: {'lr': 0.0004104329636245521, 'samples': 8289984, 'steps': 43176, 'loss/train': 1.558911681175232} 08/30/2021 20:56:23 - INFO - __main__ - Step 43178: {'lr': 0.0004104288936918024, 'samples': 8290176, 'steps': 43177, 'loss/train': 1.6005598306655884} 08/30/2021 20:56:24 - INFO - __main__ - Step 43179: {'lr': 0.00041042482368676604, 'samples': 8290368, 'steps': 43178, 'loss/train': 1.395361065864563} 08/30/2021 20:56:24 - INFO - __main__ - Step 43180: {'lr': 0.00041042075360944464, 'samples': 8290560, 'steps': 43179, 'loss/train': 1.6645832061767578} 08/30/2021 20:56:26 - INFO - __main__ - Step 43181: {'lr': 0.0004104166834598402, 'samples': 8290752, 'steps': 43180, 'loss/train': 1.572617769241333} 08/30/2021 20:56:26 - INFO - __main__ - Step 43182: {'lr': 0.00041041261323795437, 'samples': 8290944, 'steps': 43181, 'loss/train': 1.6113719940185547} 08/30/2021 20:56:26 - INFO - __main__ - Step 43183: {'lr': 0.0004104085429437892, 'samples': 8291136, 'steps': 43182, 'loss/train': 1.317272424697876} 08/30/2021 20:56:27 - INFO - __main__ - Step 43184: {'lr': 0.00041040447257734635, 'samples': 8291328, 'steps': 43183, 'loss/train': 1.3970937728881836} 08/30/2021 20:56:27 - INFO - __main__ - Step 43185: {'lr': 0.00041040040213862774, 'samples': 8291520, 'steps': 43184, 'loss/train': 1.9437177181243896} 08/30/2021 20:56:27 - INFO - __main__ - Step 43186: {'lr': 0.00041039633162763523, 'samples': 8291712, 'steps': 43185, 'loss/train': 1.3823318481445312} 08/30/2021 20:56:29 - INFO - __main__ - Step 43187: {'lr': 0.00041039226104437056, 'samples': 8291904, 'steps': 43186, 'loss/train': 1.1192784309387207} 08/30/2021 20:56:30 - INFO - __main__ - Step 43188: {'lr': 0.0004103881903888356, 'samples': 8292096, 'steps': 43187, 'loss/train': 1.5928676128387451} 08/30/2021 20:56:30 - INFO - __main__ - Step 43189: {'lr': 0.0004103841196610322, 'samples': 8292288, 'steps': 43188, 'loss/train': 2.524419069290161} 08/30/2021 20:56:31 - INFO - __main__ - Step 43190: {'lr': 0.0004103800488609622, 'samples': 8292480, 'steps': 43189, 'loss/train': 1.5301052331924438} 08/30/2021 20:56:32 - INFO - __main__ - Step 43191: {'lr': 0.0004103759779886274, 'samples': 8292672, 'steps': 43190, 'loss/train': 0.9256829023361206} 08/30/2021 20:56:33 - INFO - __main__ - Step 43192: {'lr': 0.0004103719070440297, 'samples': 8292864, 'steps': 43191, 'loss/train': 0.2546115517616272} 08/30/2021 20:56:33 - INFO - __main__ - Step 43193: {'lr': 0.00041036783602717086, 'samples': 8293056, 'steps': 43192, 'loss/train': 1.9964308738708496} 08/30/2021 20:56:33 - INFO - __main__ - Step 43194: {'lr': 0.00041036376493805286, 'samples': 8293248, 'steps': 43193, 'loss/train': 1.8302520513534546} 08/30/2021 20:56:34 - INFO - __main__ - Step 43195: {'lr': 0.0004103596937766773, 'samples': 8293440, 'steps': 43194, 'loss/train': 1.5031763315200806} 08/30/2021 20:56:34 - INFO - __main__ - Step 43196: {'lr': 0.00041035562254304614, 'samples': 8293632, 'steps': 43195, 'loss/train': 1.8386255502700806} 08/30/2021 20:56:36 - INFO - __main__ - Step 43197: {'lr': 0.00041035155123716127, 'samples': 8293824, 'steps': 43196, 'loss/train': 1.88656485080719} 08/30/2021 20:56:36 - INFO - __main__ - Step 43198: {'lr': 0.00041034747985902446, 'samples': 8294016, 'steps': 43197, 'loss/train': 1.1430670022964478} 08/30/2021 20:56:37 - INFO - __main__ - Step 43199: {'lr': 0.0004103434084086375, 'samples': 8294208, 'steps': 43198, 'loss/train': 0.44922199845314026} 08/30/2021 20:56:37 - INFO - __main__ - Step 43200: {'lr': 0.0004103393368860023, 'samples': 8294400, 'steps': 43199, 'loss/train': 1.2825961112976074} 08/30/2021 20:56:37 - INFO - __main__ - Step 43201: {'lr': 0.0004103352652911206, 'samples': 8294592, 'steps': 43200, 'loss/train': 0.7601348161697388} 08/30/2021 20:56:39 - INFO - __main__ - Step 43202: {'lr': 0.0004103311936239944, 'samples': 8294784, 'steps': 43201, 'loss/train': 1.7089953422546387} 08/30/2021 20:56:39 - INFO - __main__ - Step 43203: {'lr': 0.0004103271218846254, 'samples': 8294976, 'steps': 43202, 'loss/train': 2.0975441932678223} 08/30/2021 20:56:40 - INFO - __main__ - Step 43204: {'lr': 0.00041032305007301554, 'samples': 8295168, 'steps': 43203, 'loss/train': 1.337768793106079} 08/30/2021 20:56:40 - INFO - __main__ - Step 43205: {'lr': 0.00041031897818916645, 'samples': 8295360, 'steps': 43204, 'loss/train': 1.448705792427063} 08/30/2021 20:56:40 - INFO - __main__ - Step 43206: {'lr': 0.0004103149062330802, 'samples': 8295552, 'steps': 43205, 'loss/train': 0.9176228046417236} 08/30/2021 20:56:42 - INFO - __main__ - Step 43207: {'lr': 0.00041031083420475854, 'samples': 8295744, 'steps': 43206, 'loss/train': 1.174670934677124} 08/30/2021 20:56:42 - INFO - __main__ - Step 43208: {'lr': 0.00041030676210420324, 'samples': 8295936, 'steps': 43207, 'loss/train': 0.7236738801002502} 08/30/2021 20:56:43 - INFO - __main__ - Step 43209: {'lr': 0.0004103026899314162, 'samples': 8296128, 'steps': 43208, 'loss/train': 1.2783769369125366} 08/30/2021 20:56:43 - INFO - __main__ - Step 43210: {'lr': 0.00041029861768639934, 'samples': 8296320, 'steps': 43209, 'loss/train': 1.0573124885559082} 08/30/2021 20:56:43 - INFO - __main__ - Step 43211: {'lr': 0.0004102945453691542, 'samples': 8296512, 'steps': 43210, 'loss/train': 1.7038862705230713} 08/30/2021 20:56:45 - INFO - __main__ - Step 43212: {'lr': 0.00041029047297968293, 'samples': 8296704, 'steps': 43211, 'loss/train': 1.4660732746124268} 08/30/2021 20:56:45 - INFO - __main__ - Step 43213: {'lr': 0.00041028640051798726, 'samples': 8296896, 'steps': 43212, 'loss/train': 1.6577725410461426} 08/30/2021 20:56:46 - INFO - __main__ - Step 43214: {'lr': 0.000410282327984069, 'samples': 8297088, 'steps': 43213, 'loss/train': 1.0727344751358032} 08/30/2021 20:56:46 - INFO - __main__ - Step 43215: {'lr': 0.00041027825537792993, 'samples': 8297280, 'steps': 43214, 'loss/train': 1.4634149074554443} 08/30/2021 20:56:46 - INFO - __main__ - Step 43216: {'lr': 0.0004102741826995721, 'samples': 8297472, 'steps': 43215, 'loss/train': 1.6086004972457886} 08/30/2021 20:56:48 - INFO - __main__ - Step 43217: {'lr': 0.000410270109948997, 'samples': 8297664, 'steps': 43216, 'loss/train': 1.3327802419662476} 08/30/2021 20:56:48 - INFO - __main__ - Step 43218: {'lr': 0.0004102660371262068, 'samples': 8297856, 'steps': 43217, 'loss/train': 1.402684211730957} 08/30/2021 20:56:49 - INFO - __main__ - Step 43219: {'lr': 0.0004102619642312031, 'samples': 8298048, 'steps': 43218, 'loss/train': 0.6042243242263794} 08/30/2021 20:56:49 - INFO - __main__ - Step 43220: {'lr': 0.00041025789126398793, 'samples': 8298240, 'steps': 43219, 'loss/train': 1.2345627546310425} 08/30/2021 20:56:49 - INFO - __main__ - Step 43221: {'lr': 0.000410253818224563, 'samples': 8298432, 'steps': 43220, 'loss/train': 1.1704076528549194} 08/30/2021 20:56:51 - INFO - __main__ - Step 43222: {'lr': 0.0004102497451129302, 'samples': 8298624, 'steps': 43221, 'loss/train': 1.4527727365493774} 08/30/2021 20:56:52 - INFO - __main__ - Step 43223: {'lr': 0.00041024567192909125, 'samples': 8298816, 'steps': 43222, 'loss/train': 1.1646500825881958} 08/30/2021 20:56:52 - INFO - __main__ - Step 43224: {'lr': 0.0004102415986730481, 'samples': 8299008, 'steps': 43223, 'loss/train': 1.9749263525009155} 08/30/2021 20:56:52 - INFO - __main__ - Step 43225: {'lr': 0.0004102375253448026, 'samples': 8299200, 'steps': 43224, 'loss/train': 2.0163774490356445} 08/30/2021 20:56:53 - INFO - __main__ - Step 43226: {'lr': 0.0004102334519443565, 'samples': 8299392, 'steps': 43225, 'loss/train': 2.1163246631622314} 08/30/2021 20:56:55 - INFO - __main__ - Step 43227: {'lr': 0.0004102293784717117, 'samples': 8299584, 'steps': 43226, 'loss/train': 2.4043784141540527} 08/30/2021 20:56:55 - INFO - __main__ - Step 43228: {'lr': 0.00041022530492687006, 'samples': 8299776, 'steps': 43227, 'loss/train': 1.658603310585022} 08/30/2021 20:56:56 - INFO - __main__ - Step 43229: {'lr': 0.0004102212313098333, 'samples': 8299968, 'steps': 43228, 'loss/train': 1.077207326889038} 08/30/2021 20:56:56 - INFO - __main__ - Step 43230: {'lr': 0.00041021715762060336, 'samples': 8300160, 'steps': 43229, 'loss/train': 1.538438320159912} 08/30/2021 20:56:56 - INFO - __main__ - Step 43231: {'lr': 0.000410213083859182, 'samples': 8300352, 'steps': 43230, 'loss/train': 1.754391074180603} 08/30/2021 20:56:57 - INFO - __main__ - Step 43232: {'lr': 0.0004102090100255711, 'samples': 8300544, 'steps': 43231, 'loss/train': 0.8378159999847412} 08/30/2021 20:56:57 - INFO - __main__ - Step 43233: {'lr': 0.00041020493611977263, 'samples': 8300736, 'steps': 43232, 'loss/train': 0.06667105853557587} 08/30/2021 20:56:59 - INFO - __main__ - Step 43234: {'lr': 0.0004102008621417881, 'samples': 8300928, 'steps': 43233, 'loss/train': 0.054393839091062546} 08/30/2021 20:57:00 - INFO - __main__ - Step 43235: {'lr': 0.0004101967880916196, 'samples': 8301120, 'steps': 43234, 'loss/train': 1.5266391038894653} 08/30/2021 20:57:00 - INFO - __main__ - Step 43236: {'lr': 0.00041019271396926894, 'samples': 8301312, 'steps': 43235, 'loss/train': 0.8984933495521545} 08/30/2021 20:57:00 - INFO - __main__ - Step 43237: {'lr': 0.0004101886397747379, 'samples': 8301504, 'steps': 43236, 'loss/train': 1.8313606977462769} 08/30/2021 20:57:01 - INFO - __main__ - Step 43238: {'lr': 0.0004101845655080283, 'samples': 8301696, 'steps': 43237, 'loss/train': 1.2376304864883423} 08/30/2021 20:57:02 - INFO - __main__ - Step 43239: {'lr': 0.00041018049116914204, 'samples': 8301888, 'steps': 43238, 'loss/train': 1.576903223991394} 08/30/2021 20:57:03 - INFO - __main__ - Step 43240: {'lr': 0.00041017641675808095, 'samples': 8302080, 'steps': 43239, 'loss/train': 1.4447237253189087} 08/30/2021 20:57:03 - INFO - __main__ - Step 43241: {'lr': 0.00041017234227484675, 'samples': 8302272, 'steps': 43240, 'loss/train': 1.3892391920089722} 08/30/2021 20:57:03 - INFO - __main__ - Step 43242: {'lr': 0.0004101682677194414, 'samples': 8302464, 'steps': 43241, 'loss/train': 1.3279780149459839} 08/30/2021 20:57:04 - INFO - __main__ - Step 43243: {'lr': 0.0004101641930918667, 'samples': 8302656, 'steps': 43242, 'loss/train': 1.5703035593032837} 08/30/2021 20:57:04 - INFO - __main__ - Step 43244: {'lr': 0.00041016011839212446, 'samples': 8302848, 'steps': 43243, 'loss/train': 0.08699626475572586} 08/30/2021 20:57:06 - INFO - __main__ - Step 43245: {'lr': 0.0004101560436202166, 'samples': 8303040, 'steps': 43244, 'loss/train': 1.2573353052139282} 08/30/2021 20:57:07 - INFO - __main__ - Step 43246: {'lr': 0.0004101519687761449, 'samples': 8303232, 'steps': 43245, 'loss/train': 1.365147352218628} 08/30/2021 20:57:07 - INFO - __main__ - Step 43247: {'lr': 0.00041014789385991114, 'samples': 8303424, 'steps': 43246, 'loss/train': 0.09524846076965332} 08/30/2021 20:57:07 - INFO - __main__ - Step 43248: {'lr': 0.00041014381887151727, 'samples': 8303616, 'steps': 43247, 'loss/train': 1.0626354217529297} 08/30/2021 20:57:08 - INFO - __main__ - Step 43249: {'lr': 0.00041013974381096503, 'samples': 8303808, 'steps': 43248, 'loss/train': 0.7480886578559875} 08/30/2021 20:57:09 - INFO - __main__ - Step 43250: {'lr': 0.00041013566867825627, 'samples': 8304000, 'steps': 43249, 'loss/train': 1.284941554069519} 08/30/2021 20:57:09 - INFO - __main__ - Step 43251: {'lr': 0.00041013159347339293, 'samples': 8304192, 'steps': 43250, 'loss/train': 2.1499013900756836} 08/30/2021 20:57:10 - INFO - __main__ - Step 43252: {'lr': 0.0004101275181963767, 'samples': 8304384, 'steps': 43251, 'loss/train': 1.934585690498352} 08/30/2021 20:57:10 - INFO - __main__ - Step 43253: {'lr': 0.0004101234428472095, 'samples': 8304576, 'steps': 43252, 'loss/train': 1.6276915073394775} 08/30/2021 20:57:10 - INFO - __main__ - Step 43254: {'lr': 0.0004101193674258931, 'samples': 8304768, 'steps': 43253, 'loss/train': 1.7796305418014526} 08/30/2021 20:57:12 - INFO - __main__ - Step 43255: {'lr': 0.00041011529193242947, 'samples': 8304960, 'steps': 43254, 'loss/train': 0.6792890429496765} 08/30/2021 20:57:12 - INFO - __main__ - Step 43256: {'lr': 0.00041011121636682024, 'samples': 8305152, 'steps': 43255, 'loss/train': 1.7855327129364014} 08/30/2021 20:57:13 - INFO - __main__ - Step 43257: {'lr': 0.0004101071407290675, 'samples': 8305344, 'steps': 43256, 'loss/train': 1.4853849411010742} 08/30/2021 20:57:13 - INFO - __main__ - Step 43258: {'lr': 0.00041010306501917287, 'samples': 8305536, 'steps': 43257, 'loss/train': 1.3908770084381104} 08/30/2021 20:57:14 - INFO - __main__ - Step 43259: {'lr': 0.0004100989892371383, 'samples': 8305728, 'steps': 43258, 'loss/train': 1.152788758277893} 08/30/2021 20:57:15 - INFO - __main__ - Step 43260: {'lr': 0.00041009491338296557, 'samples': 8305920, 'steps': 43259, 'loss/train': 1.1953675746917725} 08/30/2021 20:57:16 - INFO - __main__ - Step 43261: {'lr': 0.00041009083745665654, 'samples': 8306112, 'steps': 43260, 'loss/train': 1.8269766569137573} 08/30/2021 20:57:16 - INFO - __main__ - Step 43262: {'lr': 0.0004100867614582131, 'samples': 8306304, 'steps': 43261, 'loss/train': 1.5924428701400757} 08/30/2021 20:57:16 - INFO - __main__ - Step 43263: {'lr': 0.00041008268538763703, 'samples': 8306496, 'steps': 43262, 'loss/train': 1.9329931735992432} 08/30/2021 20:57:17 - INFO - __main__ - Step 43264: {'lr': 0.00041007860924493014, 'samples': 8306688, 'steps': 43263, 'loss/train': 1.3639891147613525} 08/30/2021 20:57:18 - INFO - __main__ - Step 43265: {'lr': 0.0004100745330300943, 'samples': 8306880, 'steps': 43264, 'loss/train': 1.416107416152954} 08/30/2021 20:57:19 - INFO - __main__ - Step 43266: {'lr': 0.0004100704567431314, 'samples': 8307072, 'steps': 43265, 'loss/train': 1.5389951467514038} 08/30/2021 20:57:19 - INFO - __main__ - Step 43267: {'lr': 0.0004100663803840431, 'samples': 8307264, 'steps': 43266, 'loss/train': 1.7031641006469727} 08/30/2021 20:57:19 - INFO - __main__ - Step 43268: {'lr': 0.0004100623039528315, 'samples': 8307456, 'steps': 43267, 'loss/train': 2.2104427814483643} 08/30/2021 20:57:20 - INFO - __main__ - Step 43269: {'lr': 0.0004100582274494982, 'samples': 8307648, 'steps': 43268, 'loss/train': 1.275783896446228} 08/30/2021 20:57:21 - INFO - __main__ - Step 43270: {'lr': 0.00041005415087404516, 'samples': 8307840, 'steps': 43269, 'loss/train': 1.8312181234359741} 08/30/2021 20:57:22 - INFO - __main__ - Step 43271: {'lr': 0.0004100500742264742, 'samples': 8308032, 'steps': 43270, 'loss/train': 1.5607789754867554} 08/30/2021 20:57:22 - INFO - __main__ - Step 43272: {'lr': 0.0004100459975067871, 'samples': 8308224, 'steps': 43271, 'loss/train': 1.6923092603683472} 08/30/2021 20:57:22 - INFO - __main__ - Step 43273: {'lr': 0.0004100419207149858, 'samples': 8308416, 'steps': 43272, 'loss/train': 1.5120006799697876} 08/30/2021 20:57:23 - INFO - __main__ - Step 43274: {'lr': 0.0004100378438510721, 'samples': 8308608, 'steps': 43273, 'loss/train': 1.1149519681930542} 08/30/2021 20:57:24 - INFO - __main__ - Step 43275: {'lr': 0.00041003376691504777, 'samples': 8308800, 'steps': 43274, 'loss/train': 1.576702356338501} 08/30/2021 20:57:25 - INFO - __main__ - Step 43276: {'lr': 0.0004100296899069147, 'samples': 8308992, 'steps': 43275, 'loss/train': 0.930472195148468} 08/30/2021 20:57:25 - INFO - __main__ - Step 43277: {'lr': 0.0004100256128266747, 'samples': 8309184, 'steps': 43276, 'loss/train': 1.6813923120498657} 08/30/2021 20:57:25 - INFO - __main__ - Step 43278: {'lr': 0.00041002153567432965, 'samples': 8309376, 'steps': 43277, 'loss/train': 0.9155459403991699} 08/30/2021 20:57:26 - INFO - __main__ - Step 43279: {'lr': 0.00041001745844988134, 'samples': 8309568, 'steps': 43278, 'loss/train': 1.7488728761672974} 08/30/2021 20:57:26 - INFO - __main__ - Step 43280: {'lr': 0.00041001338115333175, 'samples': 8309760, 'steps': 43279, 'loss/train': 0.9087408781051636} 08/30/2021 20:57:28 - INFO - __main__ - Step 43281: {'lr': 0.0004100093037846825, 'samples': 8309952, 'steps': 43280, 'loss/train': 1.424195647239685} 08/30/2021 20:57:28 - INFO - __main__ - Step 43282: {'lr': 0.0004100052263439355, 'samples': 8310144, 'steps': 43281, 'loss/train': 1.234944462776184} 08/30/2021 20:57:28 - INFO - __main__ - Step 43283: {'lr': 0.00041000114883109264, 'samples': 8310336, 'steps': 43282, 'loss/train': 1.565063238143921} 08/30/2021 20:57:29 - INFO - __main__ - Step 43284: {'lr': 0.00040999707124615573, 'samples': 8310528, 'steps': 43283, 'loss/train': 1.1456494331359863} 08/30/2021 20:57:29 - INFO - __main__ - Step 43285: {'lr': 0.00040999299358912664, 'samples': 8310720, 'steps': 43284, 'loss/train': 1.3309671878814697} 08/30/2021 20:57:31 - INFO - __main__ - Step 43286: {'lr': 0.00040998891586000716, 'samples': 8310912, 'steps': 43285, 'loss/train': 0.8662579655647278} 08/30/2021 20:57:31 - INFO - __main__ - Step 43287: {'lr': 0.0004099848380587992, 'samples': 8311104, 'steps': 43286, 'loss/train': 1.4355156421661377} 08/30/2021 20:57:31 - INFO - __main__ - Step 43288: {'lr': 0.00040998076018550444, 'samples': 8311296, 'steps': 43287, 'loss/train': 1.2939621210098267} 08/30/2021 20:57:32 - INFO - __main__ - Step 43289: {'lr': 0.00040997668224012485, 'samples': 8311488, 'steps': 43288, 'loss/train': 1.2802733182907104} 08/30/2021 20:57:32 - INFO - __main__ - Step 43290: {'lr': 0.00040997260422266223, 'samples': 8311680, 'steps': 43289, 'loss/train': 1.5579886436462402} 08/30/2021 20:57:33 - INFO - __main__ - Step 43291: {'lr': 0.00040996852613311844, 'samples': 8311872, 'steps': 43290, 'loss/train': 1.4921661615371704} 08/30/2021 20:57:34 - INFO - __main__ - Step 43292: {'lr': 0.00040996444797149526, 'samples': 8312064, 'steps': 43291, 'loss/train': 1.5541744232177734} 08/30/2021 20:57:34 - INFO - __main__ - Step 43293: {'lr': 0.0004099603697377946, 'samples': 8312256, 'steps': 43292, 'loss/train': 1.6156797409057617} 08/30/2021 20:57:35 - INFO - __main__ - Step 43294: {'lr': 0.0004099562914320183, 'samples': 8312448, 'steps': 43293, 'loss/train': 1.19282865524292} 08/30/2021 20:57:35 - INFO - __main__ - Step 43295: {'lr': 0.0004099522130541681, 'samples': 8312640, 'steps': 43294, 'loss/train': 1.2898142337799072} 08/30/2021 20:57:37 - INFO - __main__ - Step 43296: {'lr': 0.000409948134604246, 'samples': 8312832, 'steps': 43295, 'loss/train': 2.0650501251220703} 08/30/2021 20:57:37 - INFO - __main__ - Step 43297: {'lr': 0.0004099440560822536, 'samples': 8313024, 'steps': 43296, 'loss/train': 1.9747849702835083} 08/30/2021 20:57:38 - INFO - __main__ - Step 43298: {'lr': 0.000409939977488193, 'samples': 8313216, 'steps': 43297, 'loss/train': 1.3749817609786987} 08/30/2021 20:57:38 - INFO - __main__ - Step 43299: {'lr': 0.0004099358988220658, 'samples': 8313408, 'steps': 43298, 'loss/train': 1.4827638864517212} 08/30/2021 20:57:39 - INFO - __main__ - Step 43300: {'lr': 0.00040993182008387406, 'samples': 8313600, 'steps': 43299, 'loss/train': 1.8128889799118042} 08/30/2021 20:57:40 - INFO - __main__ - Step 43301: {'lr': 0.0004099277412736195, 'samples': 8313792, 'steps': 43300, 'loss/train': 1.1603326797485352} 08/30/2021 20:57:41 - INFO - __main__ - Step 43302: {'lr': 0.0004099236623913039, 'samples': 8313984, 'steps': 43301, 'loss/train': 1.1888824701309204} 08/30/2021 20:57:41 - INFO - __main__ - Step 43303: {'lr': 0.0004099195834369292, 'samples': 8314176, 'steps': 43302, 'loss/train': 0.5895113348960876} 08/30/2021 20:57:42 - INFO - __main__ - Step 43304: {'lr': 0.0004099155044104972, 'samples': 8314368, 'steps': 43303, 'loss/train': 1.690457820892334} 08/30/2021 20:57:42 - INFO - __main__ - Step 43305: {'lr': 0.00040991142531200973, 'samples': 8314560, 'steps': 43304, 'loss/train': 1.3655470609664917} 08/30/2021 20:57:42 - INFO - __main__ - Step 43306: {'lr': 0.0004099073461414686, 'samples': 8314752, 'steps': 43305, 'loss/train': 0.5894904732704163} 08/30/2021 20:57:44 - INFO - __main__ - Step 43307: {'lr': 0.0004099032668988758, 'samples': 8314944, 'steps': 43306, 'loss/train': 1.3736538887023926} 08/30/2021 20:57:45 - INFO - __main__ - Step 43308: {'lr': 0.00040989918758423306, 'samples': 8315136, 'steps': 43307, 'loss/train': 1.5043609142303467} 08/30/2021 20:57:45 - INFO - __main__ - Step 43309: {'lr': 0.0004098951081975421, 'samples': 8315328, 'steps': 43308, 'loss/train': 1.9528248310089111} 08/30/2021 20:57:45 - INFO - __main__ - Step 43310: {'lr': 0.0004098910287388049, 'samples': 8315520, 'steps': 43309, 'loss/train': 1.2753669023513794} 08/30/2021 20:57:46 - INFO - __main__ - Step 43311: {'lr': 0.00040988694920802326, 'samples': 8315712, 'steps': 43310, 'loss/train': 5.918020725250244} 08/30/2021 20:57:46 - INFO - __main__ - Step 43312: {'lr': 0.0004098828696051991, 'samples': 8315904, 'steps': 43311, 'loss/train': 5.878353118896484} 08/30/2021 20:57:47 - INFO - __main__ - Step 43313: {'lr': 0.00040987878993033417, 'samples': 8316096, 'steps': 43312, 'loss/train': 1.402848720550537} 08/30/2021 20:57:48 - INFO - __main__ - Step 43314: {'lr': 0.0004098747101834303, 'samples': 8316288, 'steps': 43313, 'loss/train': 0.8779363036155701} 08/30/2021 20:57:48 - INFO - __main__ - Step 43315: {'lr': 0.00040987063036448934, 'samples': 8316480, 'steps': 43314, 'loss/train': 1.0568691492080688} 08/30/2021 20:57:49 - INFO - __main__ - Step 43316: {'lr': 0.0004098665504735132, 'samples': 8316672, 'steps': 43315, 'loss/train': 1.6869804859161377} 08/30/2021 20:57:49 - INFO - __main__ - Step 43317: {'lr': 0.0004098624705105036, 'samples': 8316864, 'steps': 43316, 'loss/train': 0.6246923208236694} 08/30/2021 20:57:49 - INFO - __main__ - Step 43318: {'lr': 0.00040985839047546243, 'samples': 8317056, 'steps': 43317, 'loss/train': 1.9683358669281006} 08/30/2021 20:57:52 - INFO - __main__ - Step 43319: {'lr': 0.00040985431036839155, 'samples': 8317248, 'steps': 43318, 'loss/train': 1.346144437789917} 08/30/2021 20:57:52 - INFO - __main__ - Step 43320: {'lr': 0.00040985023018929277, 'samples': 8317440, 'steps': 43319, 'loss/train': 0.14741285145282745} 08/30/2021 20:57:52 - INFO - __main__ - Step 43321: {'lr': 0.000409846149938168, 'samples': 8317632, 'steps': 43320, 'loss/train': 1.372376799583435} 08/30/2021 20:57:53 - INFO - __main__ - Step 43322: {'lr': 0.000409842069615019, 'samples': 8317824, 'steps': 43321, 'loss/train': 1.4731149673461914} 08/30/2021 20:57:53 - INFO - __main__ - Step 43323: {'lr': 0.0004098379892198476, 'samples': 8318016, 'steps': 43322, 'loss/train': 0.18085931241512299} 08/30/2021 20:57:54 - INFO - __main__ - Step 43324: {'lr': 0.0004098339087526557, 'samples': 8318208, 'steps': 43323, 'loss/train': 0.05744965746998787} 08/30/2021 20:57:54 - INFO - __main__ - Step 43325: {'lr': 0.00040982982821344505, 'samples': 8318400, 'steps': 43324, 'loss/train': 0.554118275642395} 08/30/2021 20:57:56 - INFO - __main__ - Step 43326: {'lr': 0.0004098257476022176, 'samples': 8318592, 'steps': 43325, 'loss/train': 0.48451897501945496} 08/30/2021 20:57:56 - INFO - __main__ - Step 43327: {'lr': 0.00040982166691897517, 'samples': 8318784, 'steps': 43326, 'loss/train': 1.301076054573059} 08/30/2021 20:57:56 - INFO - __main__ - Step 43328: {'lr': 0.00040981758616371943, 'samples': 8318976, 'steps': 43327, 'loss/train': 1.4311808347702026} 08/30/2021 20:57:57 - INFO - __main__ - Step 43329: {'lr': 0.00040981350533645245, 'samples': 8319168, 'steps': 43328, 'loss/train': 1.9092429876327515} 08/30/2021 20:57:57 - INFO - __main__ - Step 43330: {'lr': 0.00040980942443717596, 'samples': 8319360, 'steps': 43329, 'loss/train': 1.692765712738037} 08/30/2021 20:57:58 - INFO - __main__ - Step 43331: {'lr': 0.0004098053434658918, 'samples': 8319552, 'steps': 43330, 'loss/train': 1.0924246311187744} 08/30/2021 20:57:59 - INFO - __main__ - Step 43332: {'lr': 0.0004098012624226018, 'samples': 8319744, 'steps': 43331, 'loss/train': 1.207492470741272} 08/30/2021 20:57:59 - INFO - __main__ - Step 43333: {'lr': 0.00040979718130730786, 'samples': 8319936, 'steps': 43332, 'loss/train': 1.9438953399658203} 08/30/2021 20:58:00 - INFO - __main__ - Step 43334: {'lr': 0.0004097931001200118, 'samples': 8320128, 'steps': 43333, 'loss/train': 1.279848337173462} 08/30/2021 20:58:00 - INFO - __main__ - Step 43335: {'lr': 0.00040978901886071543, 'samples': 8320320, 'steps': 43334, 'loss/train': 0.936413049697876} 08/30/2021 20:58:00 - INFO - __main__ - Step 43336: {'lr': 0.0004097849375294205, 'samples': 8320512, 'steps': 43335, 'loss/train': 1.6210170984268188} 08/30/2021 20:58:02 - INFO - __main__ - Step 43337: {'lr': 0.000409780856126129, 'samples': 8320704, 'steps': 43336, 'loss/train': 1.6832184791564941} 08/30/2021 20:58:03 - INFO - __main__ - Step 43338: {'lr': 0.00040977677465084275, 'samples': 8320896, 'steps': 43337, 'loss/train': 1.524421215057373} 08/30/2021 20:58:03 - INFO - __main__ - Step 43339: {'lr': 0.00040977269310356345, 'samples': 8321088, 'steps': 43338, 'loss/train': 1.1104391813278198} 08/30/2021 20:58:03 - INFO - __main__ - Step 43340: {'lr': 0.00040976861148429313, 'samples': 8321280, 'steps': 43339, 'loss/train': 2.2770543098449707} 08/30/2021 20:58:04 - INFO - __main__ - Step 43341: {'lr': 0.0004097645297930335, 'samples': 8321472, 'steps': 43340, 'loss/train': 0.0981130376458168} 08/30/2021 20:58:05 - INFO - __main__ - Step 43342: {'lr': 0.00040976044802978645, 'samples': 8321664, 'steps': 43341, 'loss/train': 1.6146026849746704} 08/30/2021 20:58:06 - INFO - __main__ - Step 43343: {'lr': 0.0004097563661945538, 'samples': 8321856, 'steps': 43342, 'loss/train': 1.3437130451202393} 08/30/2021 20:58:06 - INFO - __main__ - Step 43344: {'lr': 0.0004097522842873374, 'samples': 8322048, 'steps': 43343, 'loss/train': 1.407339334487915} 08/30/2021 20:58:06 - INFO - __main__ - Step 43345: {'lr': 0.0004097482023081391, 'samples': 8322240, 'steps': 43344, 'loss/train': 1.2994706630706787} 08/30/2021 20:58:07 - INFO - __main__ - Step 43346: {'lr': 0.00040974412025696067, 'samples': 8322432, 'steps': 43345, 'loss/train': 1.680964708328247} 08/30/2021 20:58:08 - INFO - __main__ - Step 43347: {'lr': 0.0004097400381338041, 'samples': 8322624, 'steps': 43346, 'loss/train': 1.319219708442688} 08/30/2021 20:58:09 - INFO - __main__ - Step 43348: {'lr': 0.0004097359559386711, 'samples': 8322816, 'steps': 43347, 'loss/train': 1.5931075811386108} 08/30/2021 20:58:09 - INFO - __main__ - Step 43349: {'lr': 0.0004097318736715635, 'samples': 8323008, 'steps': 43348, 'loss/train': 1.4774757623672485} 08/30/2021 20:58:09 - INFO - __main__ - Step 43350: {'lr': 0.0004097277913324832, 'samples': 8323200, 'steps': 43349, 'loss/train': 1.358873963356018} 08/30/2021 20:58:10 - INFO - __main__ - Step 43351: {'lr': 0.000409723708921432, 'samples': 8323392, 'steps': 43350, 'loss/train': 1.7013866901397705} 08/30/2021 20:58:10 - INFO - __main__ - Step 43352: {'lr': 0.0004097196264384118, 'samples': 8323584, 'steps': 43351, 'loss/train': 1.1859010457992554} 08/30/2021 20:58:12 - INFO - __main__ - Step 43353: {'lr': 0.00040971554388342436, 'samples': 8323776, 'steps': 43352, 'loss/train': 1.1149338483810425} 08/30/2021 20:58:13 - INFO - __main__ - Step 43354: {'lr': 0.00040971146125647165, 'samples': 8323968, 'steps': 43353, 'loss/train': 1.788057804107666} 08/30/2021 20:58:13 - INFO - __main__ - Step 43355: {'lr': 0.00040970737855755535, 'samples': 8324160, 'steps': 43354, 'loss/train': 1.388297200202942} 08/30/2021 20:58:14 - INFO - __main__ - Step 43356: {'lr': 0.00040970329578667735, 'samples': 8324352, 'steps': 43355, 'loss/train': 0.2147456854581833} 08/30/2021 20:58:14 - INFO - __main__ - Step 43357: {'lr': 0.00040969921294383956, 'samples': 8324544, 'steps': 43356, 'loss/train': 1.1008005142211914} 08/30/2021 20:58:16 - INFO - __main__ - Step 43358: {'lr': 0.00040969513002904375, 'samples': 8324736, 'steps': 43357, 'loss/train': 1.5434210300445557} 08/30/2021 20:58:16 - INFO - __main__ - Step 43359: {'lr': 0.0004096910470422918, 'samples': 8324928, 'steps': 43358, 'loss/train': 1.9454022645950317} 08/30/2021 20:58:16 - INFO - __main__ - Step 43360: {'lr': 0.0004096869639835855, 'samples': 8325120, 'steps': 43359, 'loss/train': 1.454698085784912} 08/30/2021 20:58:17 - INFO - __main__ - Step 43361: {'lr': 0.0004096828808529267, 'samples': 8325312, 'steps': 43360, 'loss/train': 0.07345447689294815} 08/30/2021 20:58:17 - INFO - __main__ - Step 43362: {'lr': 0.0004096787976503173, 'samples': 8325504, 'steps': 43361, 'loss/train': 0.7993736863136292} 08/30/2021 20:58:18 - INFO - __main__ - Step 43363: {'lr': 0.0004096747143757591, 'samples': 8325696, 'steps': 43362, 'loss/train': 1.400583028793335} 08/30/2021 20:58:19 - INFO - __main__ - Step 43364: {'lr': 0.0004096706310292539, 'samples': 8325888, 'steps': 43363, 'loss/train': 1.705430030822754} 08/30/2021 20:58:19 - INFO - __main__ - Step 43365: {'lr': 0.0004096665476108036, 'samples': 8326080, 'steps': 43364, 'loss/train': 1.1131094694137573} 08/30/2021 20:58:20 - INFO - __main__ - Step 43366: {'lr': 0.00040966246412040995, 'samples': 8326272, 'steps': 43365, 'loss/train': 1.2293146848678589} 08/30/2021 20:58:20 - INFO - __main__ - Step 43367: {'lr': 0.00040965838055807493, 'samples': 8326464, 'steps': 43366, 'loss/train': 1.9997642040252686} 08/30/2021 20:58:20 - INFO - __main__ - Step 43368: {'lr': 0.00040965429692380034, 'samples': 8326656, 'steps': 43367, 'loss/train': 1.0075520277023315} 08/30/2021 20:58:22 - INFO - __main__ - Step 43369: {'lr': 0.00040965021321758796, 'samples': 8326848, 'steps': 43368, 'loss/train': 1.459784984588623} 08/30/2021 20:58:22 - INFO - __main__ - Step 43370: {'lr': 0.00040964612943943964, 'samples': 8327040, 'steps': 43369, 'loss/train': 1.4586421251296997} 08/30/2021 20:58:23 - INFO - __main__ - Step 43371: {'lr': 0.00040964204558935726, 'samples': 8327232, 'steps': 43370, 'loss/train': 1.2619712352752686} 08/30/2021 20:58:23 - INFO - __main__ - Step 43372: {'lr': 0.00040963796166734257, 'samples': 8327424, 'steps': 43371, 'loss/train': 0.8410171866416931} 08/30/2021 20:58:23 - INFO - __main__ - Step 43373: {'lr': 0.00040963387767339757, 'samples': 8327616, 'steps': 43372, 'loss/train': 1.6045360565185547} 08/30/2021 20:58:25 - INFO - __main__ - Step 43374: {'lr': 0.00040962979360752394, 'samples': 8327808, 'steps': 43373, 'loss/train': 1.0213145017623901} 08/30/2021 20:58:25 - INFO - __main__ - Step 43375: {'lr': 0.0004096257094697236, 'samples': 8328000, 'steps': 43374, 'loss/train': 0.8814600706100464} 08/30/2021 20:58:26 - INFO - __main__ - Step 43376: {'lr': 0.00040962162525999833, 'samples': 8328192, 'steps': 43375, 'loss/train': 1.1390459537506104} 08/30/2021 20:58:26 - INFO - __main__ - Step 43377: {'lr': 0.00040961754097835015, 'samples': 8328384, 'steps': 43376, 'loss/train': 0.8413316011428833} 08/30/2021 20:58:26 - INFO - __main__ - Step 43378: {'lr': 0.00040961345662478065, 'samples': 8328576, 'steps': 43377, 'loss/train': 1.6547396183013916} 08/30/2021 20:58:28 - INFO - __main__ - Step 43379: {'lr': 0.00040960937219929186, 'samples': 8328768, 'steps': 43378, 'loss/train': 1.0291426181793213} 08/30/2021 20:58:29 - INFO - __main__ - Step 43380: {'lr': 0.00040960528770188554, 'samples': 8328960, 'steps': 43379, 'loss/train': 1.0927127599716187} 08/30/2021 20:58:29 - INFO - __main__ - Step 43381: {'lr': 0.00040960120313256356, 'samples': 8329152, 'steps': 43380, 'loss/train': 1.1517938375473022} 08/30/2021 20:58:30 - INFO - __main__ - Step 43382: {'lr': 0.0004095971184913277, 'samples': 8329344, 'steps': 43381, 'loss/train': 1.6215919256210327} 08/30/2021 20:58:30 - INFO - __main__ - Step 43383: {'lr': 0.0004095930337781798, 'samples': 8329536, 'steps': 43382, 'loss/train': 1.6278475522994995} 08/30/2021 20:58:30 - INFO - __main__ - Step 43384: {'lr': 0.00040958894899312183, 'samples': 8329728, 'steps': 43383, 'loss/train': 1.1109435558319092} 08/30/2021 20:58:32 - INFO - __main__ - Step 43385: {'lr': 0.0004095848641361555, 'samples': 8329920, 'steps': 43384, 'loss/train': 1.0669652223587036} 08/30/2021 20:58:32 - INFO - __main__ - Step 43386: {'lr': 0.0004095807792072827, 'samples': 8330112, 'steps': 43385, 'loss/train': 1.3824292421340942} 08/30/2021 20:58:32 - INFO - __main__ - Step 43387: {'lr': 0.00040957669420650525, 'samples': 8330304, 'steps': 43386, 'loss/train': 1.7778005599975586} 08/30/2021 20:58:33 - INFO - __main__ - Step 43388: {'lr': 0.000409572609133825, 'samples': 8330496, 'steps': 43387, 'loss/train': 1.4954004287719727} 08/30/2021 20:58:33 - INFO - __main__ - Step 43389: {'lr': 0.00040956852398924383, 'samples': 8330688, 'steps': 43388, 'loss/train': 1.5687731504440308} 08/30/2021 20:58:35 - INFO - __main__ - Step 43390: {'lr': 0.0004095644387727635, 'samples': 8330880, 'steps': 43389, 'loss/train': 2.525780439376831} 08/30/2021 20:58:35 - INFO - __main__ - Step 43391: {'lr': 0.0004095603534843859, 'samples': 8331072, 'steps': 43390, 'loss/train': 1.3043450117111206} 08/30/2021 20:58:35 - INFO - __main__ - Step 43392: {'lr': 0.00040955626812411297, 'samples': 8331264, 'steps': 43391, 'loss/train': 1.4299070835113525} 08/30/2021 20:58:36 - INFO - __main__ - Step 43393: {'lr': 0.0004095521826919463, 'samples': 8331456, 'steps': 43392, 'loss/train': 1.1157358884811401} 08/30/2021 20:58:36 - INFO - __main__ - Step 43394: {'lr': 0.0004095480971878879, 'samples': 8331648, 'steps': 43393, 'loss/train': 1.221972942352295} 08/30/2021 20:58:38 - INFO - __main__ - Step 43395: {'lr': 0.0004095440116119397, 'samples': 8331840, 'steps': 43394, 'loss/train': 1.6612670421600342} 08/30/2021 20:58:38 - INFO - __main__ - Step 43396: {'lr': 0.00040953992596410335, 'samples': 8332032, 'steps': 43395, 'loss/train': 1.297799825668335} 08/30/2021 20:58:38 - INFO - __main__ - Step 43397: {'lr': 0.0004095358402443808, 'samples': 8332224, 'steps': 43396, 'loss/train': 1.5782296657562256} 08/30/2021 20:58:39 - INFO - __main__ - Step 43398: {'lr': 0.0004095317544527738, 'samples': 8332416, 'steps': 43397, 'loss/train': 1.165611743927002} 08/30/2021 20:58:39 - INFO - __main__ - Step 43399: {'lr': 0.00040952766858928433, 'samples': 8332608, 'steps': 43398, 'loss/train': 0.9418405294418335} 08/30/2021 20:58:41 - INFO - __main__ - Step 43400: {'lr': 0.0004095235826539141, 'samples': 8332800, 'steps': 43399, 'loss/train': 1.2756699323654175} 08/30/2021 20:58:41 - INFO - __main__ - Step 43401: {'lr': 0.00040951949664666504, 'samples': 8332992, 'steps': 43400, 'loss/train': 0.5364533066749573} 08/30/2021 20:58:41 - INFO - __main__ - Step 43402: {'lr': 0.00040951541056753895, 'samples': 8333184, 'steps': 43401, 'loss/train': 2.167762279510498} 08/30/2021 20:58:42 - INFO - __main__ - Step 43403: {'lr': 0.00040951132441653773, 'samples': 8333376, 'steps': 43402, 'loss/train': 1.5748502016067505} 08/30/2021 20:58:42 - INFO - __main__ - Step 43404: {'lr': 0.00040950723819366307, 'samples': 8333568, 'steps': 43403, 'loss/train': 0.9157592058181763} 08/30/2021 20:58:44 - INFO - __main__ - Step 43405: {'lr': 0.000409503151898917, 'samples': 8333760, 'steps': 43404, 'loss/train': 0.4294249415397644} 08/30/2021 20:58:44 - INFO - __main__ - Step 43406: {'lr': 0.0004094990655323012, 'samples': 8333952, 'steps': 43405, 'loss/train': 1.1591331958770752} 08/30/2021 20:58:44 - INFO - __main__ - Step 43407: {'lr': 0.00040949497909381757, 'samples': 8334144, 'steps': 43406, 'loss/train': 0.509672224521637} 08/30/2021 20:58:45 - INFO - __main__ - Step 43408: {'lr': 0.000409490892583468, 'samples': 8334336, 'steps': 43407, 'loss/train': 1.084208607673645} 08/30/2021 20:58:45 - INFO - __main__ - Step 43409: {'lr': 0.0004094868060012543, 'samples': 8334528, 'steps': 43408, 'loss/train': 0.672725260257721} 08/30/2021 20:58:47 - INFO - __main__ - Step 43410: {'lr': 0.0004094827193471783, 'samples': 8334720, 'steps': 43409, 'loss/train': 1.4566689729690552} 08/30/2021 20:58:48 - INFO - __main__ - Step 43411: {'lr': 0.00040947863262124186, 'samples': 8334912, 'steps': 43410, 'loss/train': 1.4267734289169312} 08/30/2021 20:58:48 - INFO - __main__ - Step 43412: {'lr': 0.0004094745458234468, 'samples': 8335104, 'steps': 43411, 'loss/train': 1.5116239786148071} 08/30/2021 20:58:49 - INFO - __main__ - Step 43413: {'lr': 0.00040947045895379494, 'samples': 8335296, 'steps': 43412, 'loss/train': 1.513641595840454} 08/30/2021 20:58:49 - INFO - __main__ - Step 43414: {'lr': 0.00040946637201228815, 'samples': 8335488, 'steps': 43413, 'loss/train': 0.3500490188598633} 08/30/2021 20:58:49 - INFO - __main__ - Step 43415: {'lr': 0.00040946228499892835, 'samples': 8335680, 'steps': 43414, 'loss/train': 1.5490992069244385} 08/30/2021 20:58:51 - INFO - __main__ - Step 43416: {'lr': 0.0004094581979137172, 'samples': 8335872, 'steps': 43415, 'loss/train': 1.1055530309677124} 08/30/2021 20:58:51 - INFO - __main__ - Step 43417: {'lr': 0.00040945411075665674, 'samples': 8336064, 'steps': 43416, 'loss/train': 1.5763269662857056} 08/30/2021 20:58:52 - INFO - __main__ - Step 43418: {'lr': 0.0004094500235277486, 'samples': 8336256, 'steps': 43417, 'loss/train': 1.535204291343689} 08/30/2021 20:58:52 - INFO - __main__ - Step 43419: {'lr': 0.0004094459362269949, 'samples': 8336448, 'steps': 43418, 'loss/train': 1.4099704027175903} 08/30/2021 20:58:52 - INFO - __main__ - Step 43420: {'lr': 0.0004094418488543972, 'samples': 8336640, 'steps': 43419, 'loss/train': 1.3240219354629517} 08/30/2021 20:58:54 - INFO - __main__ - Step 43421: {'lr': 0.00040943776140995756, 'samples': 8336832, 'steps': 43420, 'loss/train': 1.636500597000122} 08/30/2021 20:58:54 - INFO - __main__ - Step 43422: {'lr': 0.0004094336738936777, 'samples': 8337024, 'steps': 43421, 'loss/train': 1.5919028520584106} 08/30/2021 20:58:55 - INFO - __main__ - Step 43423: {'lr': 0.0004094295863055594, 'samples': 8337216, 'steps': 43422, 'loss/train': 1.3845083713531494} 08/30/2021 20:58:55 - INFO - __main__ - Step 43424: {'lr': 0.0004094254986456046, 'samples': 8337408, 'steps': 43423, 'loss/train': 1.5208150148391724} 08/30/2021 20:58:55 - INFO - __main__ - Step 43425: {'lr': 0.0004094214109138152, 'samples': 8337600, 'steps': 43424, 'loss/train': 1.5718562602996826} 08/30/2021 20:58:57 - INFO - __main__ - Step 43426: {'lr': 0.000409417323110193, 'samples': 8337792, 'steps': 43425, 'loss/train': 1.39116370677948} 08/30/2021 20:58:57 - INFO - __main__ - Step 43427: {'lr': 0.00040941323523473975, 'samples': 8337984, 'steps': 43426, 'loss/train': 0.9971347451210022} 08/30/2021 20:58:58 - INFO - __main__ - Step 43428: {'lr': 0.00040940914728745736, 'samples': 8338176, 'steps': 43427, 'loss/train': 1.3643150329589844} 08/30/2021 20:58:58 - INFO - __main__ - Step 43429: {'lr': 0.0004094050592683477, 'samples': 8338368, 'steps': 43428, 'loss/train': 2.310330390930176} 08/30/2021 20:58:58 - INFO - __main__ - Step 43430: {'lr': 0.00040940097117741255, 'samples': 8338560, 'steps': 43429, 'loss/train': 1.6164817810058594} 08/30/2021 20:58:59 - INFO - __main__ - Step 43431: {'lr': 0.00040939688301465377, 'samples': 8338752, 'steps': 43430, 'loss/train': 1.855127215385437} 08/30/2021 20:59:00 - INFO - __main__ - Step 43432: {'lr': 0.0004093927947800732, 'samples': 8338944, 'steps': 43431, 'loss/train': 2.8005080223083496} 08/30/2021 20:59:01 - INFO - __main__ - Step 43433: {'lr': 0.00040938870647367275, 'samples': 8339136, 'steps': 43432, 'loss/train': 0.2542159855365753} 08/30/2021 20:59:01 - INFO - __main__ - Step 43434: {'lr': 0.0004093846180954542, 'samples': 8339328, 'steps': 43433, 'loss/train': 1.6060121059417725} 08/30/2021 20:59:02 - INFO - __main__ - Step 43435: {'lr': 0.00040938052964541936, 'samples': 8339520, 'steps': 43434, 'loss/train': 1.561721682548523} 08/30/2021 20:59:02 - INFO - __main__ - Step 43436: {'lr': 0.0004093764411235702, 'samples': 8339712, 'steps': 43435, 'loss/train': 1.6833140850067139} 08/30/2021 20:59:04 - INFO - __main__ - Step 43437: {'lr': 0.00040937235252990834, 'samples': 8339904, 'steps': 43436, 'loss/train': 1.2376240491867065} 08/30/2021 20:59:04 - INFO - __main__ - Step 43438: {'lr': 0.00040936826386443585, 'samples': 8340096, 'steps': 43437, 'loss/train': 1.8350682258605957} 08/30/2021 20:59:04 - INFO - __main__ - Step 43439: {'lr': 0.00040936417512715454, 'samples': 8340288, 'steps': 43438, 'loss/train': 1.7881381511688232} 08/30/2021 20:59:05 - INFO - __main__ - Step 43440: {'lr': 0.00040936008631806603, 'samples': 8340480, 'steps': 43439, 'loss/train': 1.2008146047592163} 08/30/2021 20:59:05 - INFO - __main__ - Step 43441: {'lr': 0.00040935599743717243, 'samples': 8340672, 'steps': 43440, 'loss/train': 1.6067630052566528} 08/30/2021 20:59:07 - INFO - __main__ - Step 43442: {'lr': 0.00040935190848447544, 'samples': 8340864, 'steps': 43441, 'loss/train': 1.3503886461257935} 08/30/2021 20:59:07 - INFO - __main__ - Step 43443: {'lr': 0.000409347819459977, 'samples': 8341056, 'steps': 43442, 'loss/train': 1.217471718788147} 08/30/2021 20:59:08 - INFO - __main__ - Step 43444: {'lr': 0.0004093437303636788, 'samples': 8341248, 'steps': 43443, 'loss/train': 2.0348846912384033} 08/30/2021 20:59:08 - INFO - __main__ - Step 43445: {'lr': 0.0004093396411955829, 'samples': 8341440, 'steps': 43444, 'loss/train': 0.8413245677947998} 08/30/2021 20:59:08 - INFO - __main__ - Step 43446: {'lr': 0.0004093355519556908, 'samples': 8341632, 'steps': 43445, 'loss/train': 1.2147419452667236} 08/30/2021 20:59:10 - INFO - __main__ - Step 43447: {'lr': 0.0004093314626440048, 'samples': 8341824, 'steps': 43446, 'loss/train': 1.4269837141036987} 08/30/2021 20:59:10 - INFO - __main__ - Step 43448: {'lr': 0.0004093273732605264, 'samples': 8342016, 'steps': 43447, 'loss/train': 1.7882280349731445} 08/30/2021 20:59:11 - INFO - __main__ - Step 43449: {'lr': 0.0004093232838052575, 'samples': 8342208, 'steps': 43448, 'loss/train': 1.3685007095336914} 08/30/2021 20:59:11 - INFO - __main__ - Step 43450: {'lr': 0.0004093191942782001, 'samples': 8342400, 'steps': 43449, 'loss/train': 1.5755748748779297} 08/30/2021 20:59:11 - INFO - __main__ - Step 43451: {'lr': 0.0004093151046793558, 'samples': 8342592, 'steps': 43450, 'loss/train': 1.5783625841140747} 08/30/2021 20:59:13 - INFO - __main__ - Step 43452: {'lr': 0.00040931101500872656, 'samples': 8342784, 'steps': 43451, 'loss/train': 1.5340065956115723} 08/30/2021 20:59:13 - INFO - __main__ - Step 43453: {'lr': 0.00040930692526631443, 'samples': 8342976, 'steps': 43452, 'loss/train': 1.3310062885284424} 08/30/2021 20:59:14 - INFO - __main__ - Step 43454: {'lr': 0.0004093028354521209, 'samples': 8343168, 'steps': 43453, 'loss/train': 1.7738624811172485} 08/30/2021 20:59:14 - INFO - __main__ - Step 43455: {'lr': 0.000409298745566148, 'samples': 8343360, 'steps': 43454, 'loss/train': 1.6138641834259033} 08/30/2021 20:59:14 - INFO - __main__ - Step 43456: {'lr': 0.00040929465560839753, 'samples': 8343552, 'steps': 43455, 'loss/train': 1.0026392936706543} 08/30/2021 20:59:15 - INFO - __main__ - Step 43457: {'lr': 0.00040929056557887137, 'samples': 8343744, 'steps': 43456, 'loss/train': 1.594305396080017} 08/30/2021 20:59:17 - INFO - __main__ - Step 43458: {'lr': 0.0004092864754775713, 'samples': 8343936, 'steps': 43457, 'loss/train': 1.7979779243469238} 08/30/2021 20:59:17 - INFO - __main__ - Step 43459: {'lr': 0.00040928238530449926, 'samples': 8344128, 'steps': 43458, 'loss/train': 1.6893632411956787} 08/30/2021 20:59:17 - INFO - __main__ - Step 43460: {'lr': 0.00040927829505965694, 'samples': 8344320, 'steps': 43459, 'loss/train': 1.198866844177246} 08/30/2021 20:59:18 - INFO - __main__ - Step 43461: {'lr': 0.00040927420474304646, 'samples': 8344512, 'steps': 43460, 'loss/train': 1.4430618286132812} 08/30/2021 20:59:18 - INFO - __main__ - Step 43462: {'lr': 0.00040927011435466933, 'samples': 8344704, 'steps': 43461, 'loss/train': 2.045926332473755} 08/30/2021 20:59:20 - INFO - __main__ - Step 43463: {'lr': 0.0004092660238945276, 'samples': 8344896, 'steps': 43462, 'loss/train': 0.4425169825553894} 08/30/2021 20:59:21 - INFO - __main__ - Step 43464: {'lr': 0.00040926193336262304, 'samples': 8345088, 'steps': 43463, 'loss/train': 1.5673891305923462} 08/30/2021 20:59:21 - INFO - __main__ - Step 43465: {'lr': 0.0004092578427589575, 'samples': 8345280, 'steps': 43464, 'loss/train': 1.622633695602417} 08/30/2021 20:59:21 - INFO - __main__ - Step 43466: {'lr': 0.0004092537520835328, 'samples': 8345472, 'steps': 43465, 'loss/train': 0.8515864610671997} 08/30/2021 20:59:22 - INFO - __main__ - Step 43467: {'lr': 0.0004092496613363509, 'samples': 8345664, 'steps': 43466, 'loss/train': 1.6168700456619263} 08/30/2021 20:59:22 - INFO - __main__ - Step 43468: {'lr': 0.0004092455705174135, 'samples': 8345856, 'steps': 43467, 'loss/train': 1.315977692604065} 08/30/2021 20:59:23 - INFO - __main__ - Step 43469: {'lr': 0.00040924147962672253, 'samples': 8346048, 'steps': 43468, 'loss/train': 1.5509092807769775} 08/30/2021 20:59:24 - INFO - __main__ - Step 43470: {'lr': 0.00040923738866427986, 'samples': 8346240, 'steps': 43469, 'loss/train': 1.4158509969711304} 08/30/2021 20:59:24 - INFO - __main__ - Step 43471: {'lr': 0.00040923329763008714, 'samples': 8346432, 'steps': 43470, 'loss/train': 1.3277255296707153} 08/30/2021 20:59:24 - INFO - __main__ - Step 43472: {'lr': 0.0004092292065241464, 'samples': 8346624, 'steps': 43471, 'loss/train': 1.3438161611557007} 08/30/2021 20:59:25 - INFO - __main__ - Step 43473: {'lr': 0.00040922511534645953, 'samples': 8346816, 'steps': 43472, 'loss/train': 1.7162595987319946} 08/30/2021 20:59:27 - INFO - __main__ - Step 43474: {'lr': 0.0004092210240970282, 'samples': 8347008, 'steps': 43473, 'loss/train': 0.415038138628006} 08/30/2021 20:59:27 - INFO - __main__ - Step 43475: {'lr': 0.0004092169327758544, 'samples': 8347200, 'steps': 43474, 'loss/train': 2.0186753273010254} 08/30/2021 20:59:27 - INFO - __main__ - Step 43476: {'lr': 0.0004092128413829398, 'samples': 8347392, 'steps': 43475, 'loss/train': 1.492740273475647} 08/30/2021 20:59:28 - INFO - __main__ - Step 43477: {'lr': 0.0004092087499182864, 'samples': 8347584, 'steps': 43476, 'loss/train': 1.8593817949295044} 08/30/2021 20:59:28 - INFO - __main__ - Step 43478: {'lr': 0.000409204658381896, 'samples': 8347776, 'steps': 43477, 'loss/train': 1.3084630966186523} 08/30/2021 20:59:29 - INFO - __main__ - Step 43479: {'lr': 0.00040920056677377047, 'samples': 8347968, 'steps': 43478, 'loss/train': 1.449884295463562} 08/30/2021 20:59:30 - INFO - __main__ - Step 43480: {'lr': 0.00040919647509391155, 'samples': 8348160, 'steps': 43479, 'loss/train': 1.1660586595535278} 08/30/2021 20:59:30 - INFO - __main__ - Step 43481: {'lr': 0.0004091923833423212, 'samples': 8348352, 'steps': 43480, 'loss/train': 1.6018120050430298} 08/30/2021 20:59:31 - INFO - __main__ - Step 43482: {'lr': 0.00040918829151900127, 'samples': 8348544, 'steps': 43481, 'loss/train': 1.1463183164596558} 08/30/2021 20:59:31 - INFO - __main__ - Step 43483: {'lr': 0.0004091841996239535, 'samples': 8348736, 'steps': 43482, 'loss/train': 1.4388169050216675} 08/30/2021 20:59:33 - INFO - __main__ - Step 43484: {'lr': 0.00040918010765717976, 'samples': 8348928, 'steps': 43483, 'loss/train': 2.377580165863037} 08/30/2021 20:59:33 - INFO - __main__ - Step 43485: {'lr': 0.00040917601561868194, 'samples': 8349120, 'steps': 43484, 'loss/train': 1.4399527311325073} 08/30/2021 20:59:33 - INFO - __main__ - Step 43486: {'lr': 0.00040917192350846187, 'samples': 8349312, 'steps': 43485, 'loss/train': 1.2692066431045532} 08/30/2021 20:59:34 - INFO - __main__ - Step 43487: {'lr': 0.00040916783132652134, 'samples': 8349504, 'steps': 43486, 'loss/train': 1.2149641513824463} 08/30/2021 20:59:34 - INFO - __main__ - Step 43488: {'lr': 0.0004091637390728623, 'samples': 8349696, 'steps': 43487, 'loss/train': 1.3833638429641724} 08/30/2021 20:59:36 - INFO - __main__ - Step 43489: {'lr': 0.00040915964674748665, 'samples': 8349888, 'steps': 43488, 'loss/train': 1.2569570541381836} 08/30/2021 20:59:36 - INFO - __main__ - Step 43490: {'lr': 0.0004091555543503959, 'samples': 8350080, 'steps': 43489, 'loss/train': 1.5424100160598755} 08/30/2021 20:59:36 - INFO - __main__ - Step 43491: {'lr': 0.00040915146188159223, 'samples': 8350272, 'steps': 43490, 'loss/train': 1.5001763105392456} 08/30/2021 20:59:37 - INFO - __main__ - Step 43492: {'lr': 0.0004091473693410773, 'samples': 8350464, 'steps': 43491, 'loss/train': 1.5339666604995728} 08/30/2021 20:59:37 - INFO - __main__ - Step 43493: {'lr': 0.0004091432767288531, 'samples': 8350656, 'steps': 43492, 'loss/train': 1.5622690916061401} 08/30/2021 20:59:38 - INFO - __main__ - Step 43494: {'lr': 0.0004091391840449213, 'samples': 8350848, 'steps': 43493, 'loss/train': 0.9105747938156128} 08/30/2021 20:59:39 - INFO - __main__ - Step 43495: {'lr': 0.00040913509128928394, 'samples': 8351040, 'steps': 43494, 'loss/train': 0.9648832082748413} 08/30/2021 20:59:39 - INFO - __main__ - Step 43496: {'lr': 0.00040913099846194274, 'samples': 8351232, 'steps': 43495, 'loss/train': 0.9120098352432251} 08/30/2021 20:59:40 - INFO - __main__ - Step 43497: {'lr': 0.00040912690556289957, 'samples': 8351424, 'steps': 43496, 'loss/train': 0.5447750091552734} 08/30/2021 20:59:40 - INFO - __main__ - Step 43498: {'lr': 0.0004091228125921562, 'samples': 8351616, 'steps': 43497, 'loss/train': 1.810316801071167} 08/30/2021 20:59:40 - INFO - __main__ - Step 43499: {'lr': 0.0004091187195497146, 'samples': 8351808, 'steps': 43498, 'loss/train': 1.1804993152618408} 08/30/2021 20:59:42 - INFO - __main__ - Step 43500: {'lr': 0.00040911462643557656, 'samples': 8352000, 'steps': 43499, 'loss/train': 1.554088830947876} 08/30/2021 20:59:42 - INFO - __main__ - Step 43501: {'lr': 0.0004091105332497439, 'samples': 8352192, 'steps': 43500, 'loss/train': 1.2700055837631226} 08/30/2021 20:59:43 - INFO - __main__ - Step 43502: {'lr': 0.0004091064399922185, 'samples': 8352384, 'steps': 43501, 'loss/train': 1.230256199836731} 08/30/2021 20:59:43 - INFO - __main__ - Step 43503: {'lr': 0.0004091023466630023, 'samples': 8352576, 'steps': 43502, 'loss/train': 1.2320678234100342} 08/30/2021 20:59:43 - INFO - __main__ - Step 43504: {'lr': 0.00040909825326209694, 'samples': 8352768, 'steps': 43503, 'loss/train': 1.304828405380249} 08/30/2021 20:59:45 - INFO - __main__ - Step 43505: {'lr': 0.0004090941597895043, 'samples': 8352960, 'steps': 43504, 'loss/train': 1.513417363166809} 08/30/2021 20:59:45 - INFO - __main__ - Step 43506: {'lr': 0.0004090900662452264, 'samples': 8353152, 'steps': 43505, 'loss/train': 0.8245118856430054} 08/30/2021 20:59:46 - INFO - __main__ - Step 43507: {'lr': 0.00040908597262926484, 'samples': 8353344, 'steps': 43506, 'loss/train': 0.46327120065689087} 08/30/2021 20:59:46 - INFO - __main__ - Step 43508: {'lr': 0.0004090818789416217, 'samples': 8353536, 'steps': 43507, 'loss/train': 1.8288776874542236} 08/30/2021 20:59:46 - INFO - __main__ - Step 43509: {'lr': 0.0004090777851822988, 'samples': 8353728, 'steps': 43508, 'loss/train': 1.6535285711288452} 08/30/2021 20:59:48 - INFO - __main__ - Step 43510: {'lr': 0.0004090736913512977, 'samples': 8353920, 'steps': 43509, 'loss/train': 1.4248156547546387} 08/30/2021 20:59:48 - INFO - __main__ - Step 43511: {'lr': 0.0004090695974486206, 'samples': 8354112, 'steps': 43510, 'loss/train': 1.4615013599395752} 08/30/2021 20:59:49 - INFO - __main__ - Step 43512: {'lr': 0.00040906550347426907, 'samples': 8354304, 'steps': 43511, 'loss/train': 2.2905707359313965} 08/30/2021 20:59:49 - INFO - __main__ - Step 43513: {'lr': 0.0004090614094282452, 'samples': 8354496, 'steps': 43512, 'loss/train': 1.2138750553131104} 08/30/2021 20:59:49 - INFO - __main__ - Step 43514: {'lr': 0.00040905731531055067, 'samples': 8354688, 'steps': 43513, 'loss/train': 1.4084804058074951} 08/30/2021 20:59:51 - INFO - __main__ - Step 43515: {'lr': 0.0004090532211211874, 'samples': 8354880, 'steps': 43514, 'loss/train': 1.2168047428131104} 08/30/2021 20:59:51 - INFO - __main__ - Step 43516: {'lr': 0.0004090491268601572, 'samples': 8355072, 'steps': 43515, 'loss/train': 1.6737269163131714} 08/30/2021 20:59:52 - INFO - __main__ - Step 43517: {'lr': 0.0004090450325274618, 'samples': 8355264, 'steps': 43516, 'loss/train': 0.9451260566711426} 08/30/2021 20:59:52 - INFO - __main__ - Step 43518: {'lr': 0.0004090409381231033, 'samples': 8355456, 'steps': 43517, 'loss/train': 1.3149120807647705} 08/30/2021 20:59:52 - INFO - __main__ - Step 43519: {'lr': 0.0004090368436470833, 'samples': 8355648, 'steps': 43518, 'loss/train': 1.4054244756698608} 08/30/2021 20:59:54 - INFO - __main__ - Step 43520: {'lr': 0.0004090327490994038, 'samples': 8355840, 'steps': 43519, 'loss/train': 1.840895414352417} 08/30/2021 20:59:55 - INFO - __main__ - Step 43521: {'lr': 0.00040902865448006663, 'samples': 8356032, 'steps': 43520, 'loss/train': 0.7905577421188354} 08/30/2021 20:59:56 - INFO - __main__ - Step 43522: {'lr': 0.0004090245597890736, 'samples': 8356224, 'steps': 43521, 'loss/train': 1.9034472703933716} 08/30/2021 20:59:56 - INFO - __main__ - Step 43523: {'lr': 0.00040902046502642656, 'samples': 8356416, 'steps': 43522, 'loss/train': 1.4901223182678223} 08/30/2021 20:59:56 - INFO - __main__ - Step 43524: {'lr': 0.0004090163701921273, 'samples': 8356608, 'steps': 43523, 'loss/train': 2.0895180702209473} 08/30/2021 20:59:58 - INFO - __main__ - Step 43525: {'lr': 0.0004090122752861777, 'samples': 8356800, 'steps': 43524, 'loss/train': 1.4673142433166504} 08/30/2021 20:59:58 - INFO - __main__ - Step 43526: {'lr': 0.0004090081803085797, 'samples': 8356992, 'steps': 43525, 'loss/train': 1.6373339891433716} 08/30/2021 20:59:59 - INFO - __main__ - Step 43527: {'lr': 0.00040900408525933505, 'samples': 8357184, 'steps': 43526, 'loss/train': 0.7308704853057861} 08/30/2021 20:59:59 - INFO - __main__ - Step 43528: {'lr': 0.0004089999901384456, 'samples': 8357376, 'steps': 43527, 'loss/train': 1.4978106021881104} 08/30/2021 20:59:59 - INFO - __main__ - Step 43529: {'lr': 0.00040899589494591316, 'samples': 8357568, 'steps': 43528, 'loss/train': 1.6159049272537231} 08/30/2021 21:00:00 - INFO - __main__ - Step 43530: {'lr': 0.0004089917996817397, 'samples': 8357760, 'steps': 43529, 'loss/train': 1.2600092887878418} 08/30/2021 21:00:01 - INFO - __main__ - Step 43531: {'lr': 0.00040898770434592694, 'samples': 8357952, 'steps': 43530, 'loss/train': 1.5700477361679077} 08/30/2021 21:00:02 - INFO - __main__ - Step 43532: {'lr': 0.0004089836089384768, 'samples': 8358144, 'steps': 43531, 'loss/train': 1.2421658039093018} 08/30/2021 21:00:02 - INFO - __main__ - Step 43533: {'lr': 0.0004089795134593911, 'samples': 8358336, 'steps': 43532, 'loss/train': 1.5936055183410645} 08/30/2021 21:00:02 - INFO - __main__ - Step 43534: {'lr': 0.00040897541790867165, 'samples': 8358528, 'steps': 43533, 'loss/train': 0.3454930782318115} 08/30/2021 21:00:03 - INFO - __main__ - Step 43535: {'lr': 0.00040897132228632035, 'samples': 8358720, 'steps': 43534, 'loss/train': 1.991028904914856} 08/30/2021 21:00:03 - INFO - __main__ - Step 43536: {'lr': 0.000408967226592339, 'samples': 8358912, 'steps': 43535, 'loss/train': 1.256789207458496} 08/30/2021 21:00:05 - INFO - __main__ - Step 43537: {'lr': 0.00040896313082672953, 'samples': 8359104, 'steps': 43536, 'loss/train': 1.0655033588409424} 08/30/2021 21:00:05 - INFO - __main__ - Step 43538: {'lr': 0.0004089590349894937, 'samples': 8359296, 'steps': 43537, 'loss/train': 1.5189064741134644} 08/30/2021 21:00:05 - INFO - __main__ - Step 43539: {'lr': 0.0004089549390806334, 'samples': 8359488, 'steps': 43538, 'loss/train': 1.5763905048370361} 08/30/2021 21:00:06 - INFO - __main__ - Step 43540: {'lr': 0.0004089508431001504, 'samples': 8359680, 'steps': 43539, 'loss/train': 0.6611826419830322} 08/30/2021 21:00:06 - INFO - __main__ - Step 43541: {'lr': 0.00040894674704804667, 'samples': 8359872, 'steps': 43540, 'loss/train': 1.797633171081543} 08/30/2021 21:00:07 - INFO - __main__ - Step 43542: {'lr': 0.00040894265092432397, 'samples': 8360064, 'steps': 43541, 'loss/train': 1.352376937866211} 08/30/2021 21:00:08 - INFO - __main__ - Step 43543: {'lr': 0.0004089385547289841, 'samples': 8360256, 'steps': 43542, 'loss/train': 1.684341311454773} 08/30/2021 21:00:08 - INFO - __main__ - Step 43544: {'lr': 0.00040893445846202904, 'samples': 8360448, 'steps': 43543, 'loss/train': 1.78757905960083} 08/30/2021 21:00:09 - INFO - __main__ - Step 43545: {'lr': 0.00040893036212346056, 'samples': 8360640, 'steps': 43544, 'loss/train': 1.09691321849823} 08/30/2021 21:00:09 - INFO - __main__ - Step 43546: {'lr': 0.00040892626571328053, 'samples': 8360832, 'steps': 43545, 'loss/train': 1.354297399520874} 08/30/2021 21:00:11 - INFO - __main__ - Step 43547: {'lr': 0.00040892216923149073, 'samples': 8361024, 'steps': 43546, 'loss/train': 1.2973880767822266} 08/30/2021 21:00:11 - INFO - __main__ - Step 43548: {'lr': 0.000408918072678093, 'samples': 8361216, 'steps': 43547, 'loss/train': 1.8560454845428467} 08/30/2021 21:00:12 - INFO - __main__ - Step 43549: {'lr': 0.0004089139760530893, 'samples': 8361408, 'steps': 43548, 'loss/train': 1.3205373287200928} 08/30/2021 21:00:12 - INFO - __main__ - Step 43550: {'lr': 0.0004089098793564815, 'samples': 8361600, 'steps': 43549, 'loss/train': 1.5110255479812622} 08/30/2021 21:00:12 - INFO - __main__ - Step 43551: {'lr': 0.00040890578258827125, 'samples': 8361792, 'steps': 43550, 'loss/train': 0.12010274082422256} 08/30/2021 21:00:14 - INFO - __main__ - Step 43552: {'lr': 0.00040890168574846055, 'samples': 8361984, 'steps': 43551, 'loss/train': 2.036977767944336} 08/30/2021 21:00:14 - INFO - __main__ - Step 43553: {'lr': 0.0004088975888370512, 'samples': 8362176, 'steps': 43552, 'loss/train': 1.012085199356079} 08/30/2021 21:00:15 - INFO - __main__ - Step 43554: {'lr': 0.00040889349185404503, 'samples': 8362368, 'steps': 43553, 'loss/train': 1.2202578783035278} 08/30/2021 21:00:15 - INFO - __main__ - Step 43555: {'lr': 0.00040888939479944385, 'samples': 8362560, 'steps': 43554, 'loss/train': 1.8396084308624268} 08/30/2021 21:00:15 - INFO - __main__ - Step 43556: {'lr': 0.00040888529767324966, 'samples': 8362752, 'steps': 43555, 'loss/train': 1.653887152671814} 08/30/2021 21:00:17 - INFO - __main__ - Step 43557: {'lr': 0.0004088812004754642, 'samples': 8362944, 'steps': 43556, 'loss/train': 1.1581887006759644} 08/30/2021 21:00:18 - INFO - __main__ - Step 43558: {'lr': 0.00040887710320608927, 'samples': 8363136, 'steps': 43557, 'loss/train': 1.6807453632354736} 08/30/2021 21:00:18 - INFO - __main__ - Step 43559: {'lr': 0.00040887300586512677, 'samples': 8363328, 'steps': 43558, 'loss/train': 0.6707919836044312} 08/30/2021 21:00:18 - INFO - __main__ - Step 43560: {'lr': 0.0004088689084525786, 'samples': 8363520, 'steps': 43559, 'loss/train': 1.6107722520828247} 08/30/2021 21:00:19 - INFO - __main__ - Step 43561: {'lr': 0.0004088648109684465, 'samples': 8363712, 'steps': 43560, 'loss/train': 1.2834357023239136} 08/30/2021 21:00:20 - INFO - __main__ - Step 43562: {'lr': 0.00040886071341273236, 'samples': 8363904, 'steps': 43561, 'loss/train': 1.5500766038894653} 08/30/2021 21:00:21 - INFO - __main__ - Step 43563: {'lr': 0.0004088566157854381, 'samples': 8364096, 'steps': 43562, 'loss/train': 1.4507262706756592} 08/30/2021 21:00:21 - INFO - __main__ - Step 43564: {'lr': 0.0004088525180865654, 'samples': 8364288, 'steps': 43563, 'loss/train': 1.3127750158309937} 08/30/2021 21:00:21 - INFO - __main__ - Step 43565: {'lr': 0.0004088484203161163, 'samples': 8364480, 'steps': 43564, 'loss/train': 1.2134068012237549} 08/30/2021 21:00:22 - INFO - __main__ - Step 43566: {'lr': 0.0004088443224740925, 'samples': 8364672, 'steps': 43565, 'loss/train': 1.307991623878479} 08/30/2021 21:00:23 - INFO - __main__ - Step 43567: {'lr': 0.00040884022456049595, 'samples': 8364864, 'steps': 43566, 'loss/train': 1.4102755784988403} 08/30/2021 21:00:24 - INFO - __main__ - Step 43568: {'lr': 0.00040883612657532844, 'samples': 8365056, 'steps': 43567, 'loss/train': 1.437592625617981} 08/30/2021 21:00:24 - INFO - __main__ - Step 43569: {'lr': 0.0004088320285185918, 'samples': 8365248, 'steps': 43568, 'loss/train': 2.1850321292877197} 08/30/2021 21:00:24 - INFO - __main__ - Step 43570: {'lr': 0.0004088279303902879, 'samples': 8365440, 'steps': 43569, 'loss/train': 1.4614529609680176} 08/30/2021 21:00:25 - INFO - __main__ - Step 43571: {'lr': 0.0004088238321904185, 'samples': 8365632, 'steps': 43570, 'loss/train': 1.2102651596069336} 08/30/2021 21:00:27 - INFO - __main__ - Step 43572: {'lr': 0.00040881973391898563, 'samples': 8365824, 'steps': 43571, 'loss/train': 1.9799891710281372} 08/30/2021 21:00:27 - INFO - __main__ - Step 43573: {'lr': 0.00040881563557599107, 'samples': 8366016, 'steps': 43572, 'loss/train': 1.2908083200454712} 08/30/2021 21:00:28 - INFO - __main__ - Step 43574: {'lr': 0.00040881153716143656, 'samples': 8366208, 'steps': 43573, 'loss/train': 1.3629207611083984} 08/30/2021 21:00:28 - INFO - __main__ - Step 43575: {'lr': 0.000408807438675324, 'samples': 8366400, 'steps': 43574, 'loss/train': 1.2900439500808716} 08/30/2021 21:00:28 - INFO - __main__ - Step 43576: {'lr': 0.0004088033401176554, 'samples': 8366592, 'steps': 43575, 'loss/train': 1.2305748462677002} 08/30/2021 21:00:30 - INFO - __main__ - Step 43577: {'lr': 0.00040879924148843233, 'samples': 8366784, 'steps': 43576, 'loss/train': 1.3015834093093872} 08/30/2021 21:00:30 - INFO - __main__ - Step 43578: {'lr': 0.00040879514278765685, 'samples': 8366976, 'steps': 43577, 'loss/train': 1.572119116783142} 08/30/2021 21:00:31 - INFO - __main__ - Step 43579: {'lr': 0.00040879104401533064, 'samples': 8367168, 'steps': 43578, 'loss/train': 1.538743495941162} 08/30/2021 21:00:31 - INFO - __main__ - Step 43580: {'lr': 0.0004087869451714557, 'samples': 8367360, 'steps': 43579, 'loss/train': 0.8841307163238525} 08/30/2021 21:00:31 - INFO - __main__ - Step 43581: {'lr': 0.0004087828462560338, 'samples': 8367552, 'steps': 43580, 'loss/train': 1.8244174718856812} 08/30/2021 21:00:32 - INFO - __main__ - Step 43582: {'lr': 0.0004087787472690668, 'samples': 8367744, 'steps': 43581, 'loss/train': 0.39079025387763977} 08/30/2021 21:00:33 - INFO - __main__ - Step 43583: {'lr': 0.00040877464821055656, 'samples': 8367936, 'steps': 43582, 'loss/train': 1.4974087476730347} 08/30/2021 21:00:33 - INFO - __main__ - Step 43584: {'lr': 0.00040877054908050495, 'samples': 8368128, 'steps': 43583, 'loss/train': 1.0725429058074951} 08/30/2021 21:00:34 - INFO - __main__ - Step 43585: {'lr': 0.0004087664498789137, 'samples': 8368320, 'steps': 43584, 'loss/train': 1.1277167797088623} 08/30/2021 21:00:34 - INFO - __main__ - Step 43586: {'lr': 0.00040876235060578476, 'samples': 8368512, 'steps': 43585, 'loss/train': 0.8686061501502991} 08/30/2021 21:00:34 - INFO - __main__ - Step 43587: {'lr': 0.00040875825126112, 'samples': 8368704, 'steps': 43586, 'loss/train': 1.2955750226974487} 08/30/2021 21:00:36 - INFO - __main__ - Step 43588: {'lr': 0.00040875415184492113, 'samples': 8368896, 'steps': 43587, 'loss/train': 1.6488643884658813} 08/30/2021 21:00:36 - INFO - __main__ - Step 43589: {'lr': 0.0004087500523571902, 'samples': 8369088, 'steps': 43588, 'loss/train': 1.1287872791290283} 08/30/2021 21:00:37 - INFO - __main__ - Step 43590: {'lr': 0.00040874595279792884, 'samples': 8369280, 'steps': 43589, 'loss/train': 0.82212895154953} 08/30/2021 21:00:37 - INFO - __main__ - Step 43591: {'lr': 0.00040874185316713905, 'samples': 8369472, 'steps': 43590, 'loss/train': 1.332965612411499} 08/30/2021 21:00:37 - INFO - __main__ - Step 43592: {'lr': 0.00040873775346482265, 'samples': 8369664, 'steps': 43591, 'loss/train': 1.5776841640472412} 08/30/2021 21:00:39 - INFO - __main__ - Step 43593: {'lr': 0.0004087336536909815, 'samples': 8369856, 'steps': 43592, 'loss/train': 1.265476107597351} 08/30/2021 21:00:39 - INFO - __main__ - Step 43594: {'lr': 0.00040872955384561735, 'samples': 8370048, 'steps': 43593, 'loss/train': 1.8268992900848389} 08/30/2021 21:00:40 - INFO - __main__ - Step 43595: {'lr': 0.00040872545392873214, 'samples': 8370240, 'steps': 43594, 'loss/train': 1.119771122932434} 08/30/2021 21:00:40 - INFO - __main__ - Step 43596: {'lr': 0.00040872135394032764, 'samples': 8370432, 'steps': 43595, 'loss/train': 1.3884943723678589} 08/30/2021 21:00:40 - INFO - __main__ - Step 43597: {'lr': 0.0004087172538804058, 'samples': 8370624, 'steps': 43596, 'loss/train': 1.2326133251190186} 08/30/2021 21:00:42 - INFO - __main__ - Step 43598: {'lr': 0.0004087131537489685, 'samples': 8370816, 'steps': 43597, 'loss/train': 0.9040321111679077} 08/30/2021 21:00:42 - INFO - __main__ - Step 43599: {'lr': 0.00040870905354601733, 'samples': 8371008, 'steps': 43598, 'loss/train': 1.3405879735946655} 08/30/2021 21:00:43 - INFO - __main__ - Step 43600: {'lr': 0.0004087049532715544, 'samples': 8371200, 'steps': 43599, 'loss/train': 1.5261836051940918} 08/30/2021 21:00:43 - INFO - __main__ - Step 43601: {'lr': 0.00040870085292558147, 'samples': 8371392, 'steps': 43600, 'loss/train': 1.6984177827835083} 08/30/2021 21:00:43 - INFO - __main__ - Step 43602: {'lr': 0.0004086967525081003, 'samples': 8371584, 'steps': 43601, 'loss/train': 0.9577161073684692} 08/30/2021 21:00:45 - INFO - __main__ - Step 43603: {'lr': 0.00040869265201911285, 'samples': 8371776, 'steps': 43602, 'loss/train': 1.515116810798645} 08/30/2021 21:00:46 - INFO - __main__ - Step 43604: {'lr': 0.00040868855145862105, 'samples': 8371968, 'steps': 43603, 'loss/train': 1.2844641208648682} 08/30/2021 21:00:46 - INFO - __main__ - Step 43605: {'lr': 0.00040868445082662655, 'samples': 8372160, 'steps': 43604, 'loss/train': 1.6302162408828735} 08/30/2021 21:00:46 - INFO - __main__ - Step 43606: {'lr': 0.0004086803501231313, 'samples': 8372352, 'steps': 43605, 'loss/train': 1.1906564235687256} 08/30/2021 21:00:47 - INFO - __main__ - Step 43607: {'lr': 0.00040867624934813715, 'samples': 8372544, 'steps': 43606, 'loss/train': 1.7421822547912598} 08/30/2021 21:00:48 - INFO - __main__ - Step 43608: {'lr': 0.00040867214850164594, 'samples': 8372736, 'steps': 43607, 'loss/train': 0.7915459871292114} 08/30/2021 21:00:48 - INFO - __main__ - Step 43609: {'lr': 0.0004086680475836594, 'samples': 8372928, 'steps': 43608, 'loss/train': 1.2626932859420776} 08/30/2021 21:00:49 - INFO - __main__ - Step 43610: {'lr': 0.0004086639465941796, 'samples': 8373120, 'steps': 43609, 'loss/train': 1.2351818084716797} 08/30/2021 21:00:49 - INFO - __main__ - Step 43611: {'lr': 0.00040865984553320825, 'samples': 8373312, 'steps': 43610, 'loss/train': 2.0004420280456543} 08/30/2021 21:00:49 - INFO - __main__ - Step 43612: {'lr': 0.0004086557444007472, 'samples': 8373504, 'steps': 43611, 'loss/train': 1.4509479999542236} 08/30/2021 21:00:51 - INFO - __main__ - Step 43613: {'lr': 0.0004086516431967984, 'samples': 8373696, 'steps': 43612, 'loss/train': 1.6439779996871948} 08/30/2021 21:00:51 - INFO - __main__ - Step 43614: {'lr': 0.0004086475419213635, 'samples': 8373888, 'steps': 43613, 'loss/train': 1.9279168844223022} 08/30/2021 21:00:52 - INFO - __main__ - Step 43615: {'lr': 0.0004086434405744445, 'samples': 8374080, 'steps': 43614, 'loss/train': 1.1898761987686157} 08/30/2021 21:00:52 - INFO - __main__ - Step 43616: {'lr': 0.00040863933915604323, 'samples': 8374272, 'steps': 43615, 'loss/train': 1.2589688301086426} 08/30/2021 21:00:52 - INFO - __main__ - Step 43617: {'lr': 0.00040863523766616157, 'samples': 8374464, 'steps': 43616, 'loss/train': 1.367022156715393} 08/30/2021 21:00:54 - INFO - __main__ - Step 43618: {'lr': 0.0004086311361048012, 'samples': 8374656, 'steps': 43617, 'loss/train': 1.3885738849639893} 08/30/2021 21:00:54 - INFO - __main__ - Step 43619: {'lr': 0.0004086270344719642, 'samples': 8374848, 'steps': 43618, 'loss/train': 1.4041556119918823} 08/30/2021 21:00:55 - INFO - __main__ - Step 43620: {'lr': 0.00040862293276765227, 'samples': 8375040, 'steps': 43619, 'loss/train': 1.7073453664779663} 08/30/2021 21:00:55 - INFO - __main__ - Step 43621: {'lr': 0.00040861883099186725, 'samples': 8375232, 'steps': 43620, 'loss/train': 1.5339233875274658} 08/30/2021 21:00:55 - INFO - __main__ - Step 43622: {'lr': 0.0004086147291446111, 'samples': 8375424, 'steps': 43621, 'loss/train': 1.1537561416625977} 08/30/2021 21:00:56 - INFO - __main__ - Step 43623: {'lr': 0.0004086106272258856, 'samples': 8375616, 'steps': 43622, 'loss/train': 3.4219653606414795} 08/30/2021 21:00:58 - INFO - __main__ - Step 43624: {'lr': 0.0004086065252356925, 'samples': 8375808, 'steps': 43623, 'loss/train': 1.460680365562439} 08/30/2021 21:00:58 - INFO - __main__ - Step 43625: {'lr': 0.00040860242317403383, 'samples': 8376000, 'steps': 43624, 'loss/train': 1.245326280593872} 08/30/2021 21:00:59 - INFO - __main__ - Step 43626: {'lr': 0.0004085983210409114, 'samples': 8376192, 'steps': 43625, 'loss/train': 1.675591230392456} 08/30/2021 21:00:59 - INFO - __main__ - Step 43627: {'lr': 0.00040859421883632696, 'samples': 8376384, 'steps': 43626, 'loss/train': 1.3258898258209229} 08/30/2021 21:00:59 - INFO - __main__ - Step 43628: {'lr': 0.0004085901165602824, 'samples': 8376576, 'steps': 43627, 'loss/train': 1.4475562572479248} 08/30/2021 21:01:01 - INFO - __main__ - Step 43629: {'lr': 0.00040858601421277956, 'samples': 8376768, 'steps': 43628, 'loss/train': 4.370294094085693} 08/30/2021 21:01:02 - INFO - __main__ - Step 43630: {'lr': 0.00040858191179382044, 'samples': 8376960, 'steps': 43629, 'loss/train': 0.07411886751651764} 08/30/2021 21:01:02 - INFO - __main__ - Step 43631: {'lr': 0.0004085778093034066, 'samples': 8377152, 'steps': 43630, 'loss/train': 1.795538067817688} 08/30/2021 21:01:02 - INFO - __main__ - Step 43632: {'lr': 0.0004085737067415401, 'samples': 8377344, 'steps': 43631, 'loss/train': 1.4656035900115967} 08/30/2021 21:01:03 - INFO - __main__ - Step 43633: {'lr': 0.00040856960410822277, 'samples': 8377536, 'steps': 43632, 'loss/train': 0.781088650226593} 08/30/2021 21:01:04 - INFO - __main__ - Step 43634: {'lr': 0.0004085655014034564, 'samples': 8377728, 'steps': 43633, 'loss/train': 1.227291464805603} 08/30/2021 21:01:05 - INFO - __main__ - Step 43635: {'lr': 0.0004085613986272428, 'samples': 8377920, 'steps': 43634, 'loss/train': 1.5319759845733643} 08/30/2021 21:01:05 - INFO - __main__ - Step 43636: {'lr': 0.0004085572957795839, 'samples': 8378112, 'steps': 43635, 'loss/train': 1.3055925369262695} 08/30/2021 21:01:05 - INFO - __main__ - Step 43637: {'lr': 0.00040855319286048163, 'samples': 8378304, 'steps': 43636, 'loss/train': 1.7575457096099854} 08/30/2021 21:01:06 - INFO - __main__ - Step 43638: {'lr': 0.0004085490898699377, 'samples': 8378496, 'steps': 43637, 'loss/train': 1.7916195392608643} 08/30/2021 21:01:06 - INFO - __main__ - Step 43639: {'lr': 0.0004085449868079539, 'samples': 8378688, 'steps': 43638, 'loss/train': 1.268640398979187} 08/30/2021 21:01:07 - INFO - __main__ - Step 43640: {'lr': 0.00040854088367453225, 'samples': 8378880, 'steps': 43639, 'loss/train': 1.395135521888733} 08/30/2021 21:01:08 - INFO - __main__ - Step 43641: {'lr': 0.00040853678046967454, 'samples': 8379072, 'steps': 43640, 'loss/train': 1.7019858360290527} 08/30/2021 21:01:08 - INFO - __main__ - Step 43642: {'lr': 0.00040853267719338256, 'samples': 8379264, 'steps': 43641, 'loss/train': 1.9262727499008179} 08/30/2021 21:01:09 - INFO - __main__ - Step 43643: {'lr': 0.00040852857384565824, 'samples': 8379456, 'steps': 43642, 'loss/train': 1.7774850130081177} 08/30/2021 21:01:09 - INFO - __main__ - Step 43644: {'lr': 0.00040852447042650337, 'samples': 8379648, 'steps': 43643, 'loss/train': 1.3540111780166626} 08/30/2021 21:01:10 - INFO - __main__ - Step 43645: {'lr': 0.0004085203669359198, 'samples': 8379840, 'steps': 43644, 'loss/train': 1.5102699995040894} 08/30/2021 21:01:11 - INFO - __main__ - Step 43646: {'lr': 0.0004085162633739095, 'samples': 8380032, 'steps': 43645, 'loss/train': 1.3230069875717163} 08/30/2021 21:01:11 - INFO - __main__ - Step 43647: {'lr': 0.0004085121597404741, 'samples': 8380224, 'steps': 43646, 'loss/train': 1.4717904329299927} 08/30/2021 21:01:12 - INFO - __main__ - Step 43648: {'lr': 0.0004085080560356156, 'samples': 8380416, 'steps': 43647, 'loss/train': 1.499605417251587} 08/30/2021 21:01:12 - INFO - __main__ - Step 43649: {'lr': 0.0004085039522593358, 'samples': 8380608, 'steps': 43648, 'loss/train': 1.5564775466918945} 08/30/2021 21:01:13 - INFO - __main__ - Step 43650: {'lr': 0.0004084998484116366, 'samples': 8380800, 'steps': 43649, 'loss/train': 1.0594967603683472} 08/30/2021 21:01:14 - INFO - __main__ - Step 43651: {'lr': 0.0004084957444925198, 'samples': 8380992, 'steps': 43650, 'loss/train': 1.7161197662353516} 08/30/2021 21:01:14 - INFO - __main__ - Step 43652: {'lr': 0.0004084916405019873, 'samples': 8381184, 'steps': 43651, 'loss/train': 1.237003207206726} 08/30/2021 21:01:15 - INFO - __main__ - Step 43653: {'lr': 0.0004084875364400409, 'samples': 8381376, 'steps': 43652, 'loss/train': 1.4637783765792847} 08/30/2021 21:01:15 - INFO - __main__ - Step 43654: {'lr': 0.0004084834323066824, 'samples': 8381568, 'steps': 43653, 'loss/train': 1.5486664772033691} 08/30/2021 21:01:17 - INFO - __main__ - Step 43655: {'lr': 0.00040847932810191375, 'samples': 8381760, 'steps': 43654, 'loss/train': 0.529299795627594} 08/30/2021 21:01:17 - INFO - __main__ - Step 43656: {'lr': 0.00040847522382573675, 'samples': 8381952, 'steps': 43655, 'loss/train': 1.722328543663025} 08/30/2021 21:01:17 - INFO - __main__ - Step 43657: {'lr': 0.0004084711194781533, 'samples': 8382144, 'steps': 43656, 'loss/train': 1.4397668838500977} 08/30/2021 21:01:18 - INFO - __main__ - Step 43658: {'lr': 0.00040846701505916516, 'samples': 8382336, 'steps': 43657, 'loss/train': 1.9381386041641235} 08/30/2021 21:01:18 - INFO - __main__ - Step 43659: {'lr': 0.00040846291056877425, 'samples': 8382528, 'steps': 43658, 'loss/train': 2.053208112716675} 08/30/2021 21:01:19 - INFO - __main__ - Step 43660: {'lr': 0.0004084588060069824, 'samples': 8382720, 'steps': 43659, 'loss/train': 1.2218683958053589} 08/30/2021 21:01:20 - INFO - __main__ - Step 43661: {'lr': 0.0004084547013737915, 'samples': 8382912, 'steps': 43660, 'loss/train': 1.1074050664901733} 08/30/2021 21:01:20 - INFO - __main__ - Step 43662: {'lr': 0.00040845059666920323, 'samples': 8383104, 'steps': 43661, 'loss/train': 0.9613440632820129} 08/30/2021 21:01:21 - INFO - __main__ - Step 43663: {'lr': 0.0004084464918932197, 'samples': 8383296, 'steps': 43662, 'loss/train': 1.67049241065979} 08/30/2021 21:01:21 - INFO - __main__ - Step 43664: {'lr': 0.0004084423870458426, 'samples': 8383488, 'steps': 43663, 'loss/train': 1.410565972328186} 08/30/2021 21:01:23 - INFO - __main__ - Step 43665: {'lr': 0.00040843828212707366, 'samples': 8383680, 'steps': 43664, 'loss/train': 1.6554551124572754} 08/30/2021 21:01:23 - INFO - __main__ - Step 43666: {'lr': 0.00040843417713691505, 'samples': 8383872, 'steps': 43665, 'loss/train': 1.251230239868164} 08/30/2021 21:01:23 - INFO - __main__ - Step 43667: {'lr': 0.0004084300720753684, 'samples': 8384064, 'steps': 43666, 'loss/train': 1.2498807907104492} 08/30/2021 21:01:24 - INFO - __main__ - Step 43668: {'lr': 0.0004084259669424356, 'samples': 8384256, 'steps': 43667, 'loss/train': 1.5934815406799316} 08/30/2021 21:01:24 - INFO - __main__ - Step 43669: {'lr': 0.0004084218617381185, 'samples': 8384448, 'steps': 43668, 'loss/train': 1.8616904020309448} 08/30/2021 21:01:26 - INFO - __main__ - Step 43670: {'lr': 0.00040841775646241897, 'samples': 8384640, 'steps': 43669, 'loss/train': 0.9714229702949524} 08/30/2021 21:01:26 - INFO - __main__ - Step 43671: {'lr': 0.0004084136511153388, 'samples': 8384832, 'steps': 43670, 'loss/train': 1.8559218645095825} 08/30/2021 21:01:26 - INFO - __main__ - Step 43672: {'lr': 0.0004084095456968799, 'samples': 8385024, 'steps': 43671, 'loss/train': 1.5746978521347046} 08/30/2021 21:01:27 - INFO - __main__ - Step 43673: {'lr': 0.0004084054402070441, 'samples': 8385216, 'steps': 43672, 'loss/train': 2.47072434425354} 08/30/2021 21:01:27 - INFO - __main__ - Step 43674: {'lr': 0.0004084013346458333, 'samples': 8385408, 'steps': 43673, 'loss/train': 1.443535327911377} 08/30/2021 21:01:28 - INFO - __main__ - Step 43675: {'lr': 0.00040839722901324924, 'samples': 8385600, 'steps': 43674, 'loss/train': 1.4247541427612305} 08/30/2021 21:01:29 - INFO - __main__ - Step 43676: {'lr': 0.00040839312330929377, 'samples': 8385792, 'steps': 43675, 'loss/train': 1.2561787366867065} 08/30/2021 21:01:29 - INFO - __main__ - Step 43677: {'lr': 0.00040838901753396896, 'samples': 8385984, 'steps': 43676, 'loss/train': 0.9809263944625854} 08/30/2021 21:01:30 - INFO - __main__ - Step 43678: {'lr': 0.0004083849116872764, 'samples': 8386176, 'steps': 43677, 'loss/train': 1.2022013664245605} 08/30/2021 21:01:30 - INFO - __main__ - Step 43679: {'lr': 0.0004083808057692181, 'samples': 8386368, 'steps': 43678, 'loss/train': 0.6751843690872192} 08/30/2021 21:01:30 - INFO - __main__ - Step 43680: {'lr': 0.00040837669977979586, 'samples': 8386560, 'steps': 43679, 'loss/train': 1.5646017789840698} 08/30/2021 21:01:33 - INFO - __main__ - Step 43681: {'lr': 0.00040837259371901145, 'samples': 8386752, 'steps': 43680, 'loss/train': 2.472356081008911} 08/30/2021 21:01:33 - INFO - __main__ - Step 43682: {'lr': 0.00040836848758686687, 'samples': 8386944, 'steps': 43681, 'loss/train': 1.1849440336227417} 08/30/2021 21:01:33 - INFO - __main__ - Step 43683: {'lr': 0.00040836438138336384, 'samples': 8387136, 'steps': 43682, 'loss/train': 1.327950119972229} 08/30/2021 21:01:34 - INFO - __main__ - Step 43684: {'lr': 0.00040836027510850426, 'samples': 8387328, 'steps': 43683, 'loss/train': 1.4204602241516113} 08/30/2021 21:01:34 - INFO - __main__ - Step 43685: {'lr': 0.00040835616876229, 'samples': 8387520, 'steps': 43684, 'loss/train': 1.4153857231140137} 08/30/2021 21:01:36 - INFO - __main__ - Step 43686: {'lr': 0.00040835206234472287, 'samples': 8387712, 'steps': 43685, 'loss/train': 1.4426779747009277} 08/30/2021 21:01:36 - INFO - __main__ - Step 43687: {'lr': 0.0004083479558558048, 'samples': 8387904, 'steps': 43686, 'loss/train': 1.643937587738037} 08/30/2021 21:01:36 - INFO - __main__ - Step 43688: {'lr': 0.0004083438492955376, 'samples': 8388096, 'steps': 43687, 'loss/train': 1.5799084901809692} 08/30/2021 21:01:37 - INFO - __main__ - Step 43689: {'lr': 0.00040833974266392306, 'samples': 8388288, 'steps': 43688, 'loss/train': 1.8566995859146118} 08/30/2021 21:01:37 - INFO - __main__ - Step 43690: {'lr': 0.00040833563596096305, 'samples': 8388480, 'steps': 43689, 'loss/train': 1.5041723251342773} 08/30/2021 21:01:39 - INFO - __main__ - Step 43691: {'lr': 0.0004083315291866595, 'samples': 8388672, 'steps': 43690, 'loss/train': 0.6873224377632141} 08/30/2021 21:01:39 - INFO - __main__ - Step 43692: {'lr': 0.00040832742234101415, 'samples': 8388864, 'steps': 43691, 'loss/train': 1.5964791774749756} 08/30/2021 21:01:40 - INFO - __main__ - Step 43693: {'lr': 0.00040832331542402895, 'samples': 8389056, 'steps': 43692, 'loss/train': 1.6457117795944214} 08/30/2021 21:01:40 - INFO - __main__ - Step 43694: {'lr': 0.0004083192084357057, 'samples': 8389248, 'steps': 43693, 'loss/train': 1.4226797819137573} 08/30/2021 21:01:40 - INFO - __main__ - Step 43695: {'lr': 0.0004083151013760462, 'samples': 8389440, 'steps': 43694, 'loss/train': 1.2428357601165771} 08/30/2021 21:01:42 - INFO - __main__ - Step 43696: {'lr': 0.0004083109942450524, 'samples': 8389632, 'steps': 43695, 'loss/train': 0.08396401256322861} 08/30/2021 21:01:42 - INFO - __main__ - Step 43697: {'lr': 0.00040830688704272615, 'samples': 8389824, 'steps': 43696, 'loss/train': 1.7063456773757935} 08/30/2021 21:01:43 - INFO - __main__ - Step 43698: {'lr': 0.0004083027797690693, 'samples': 8390016, 'steps': 43697, 'loss/train': 1.39260995388031} 08/30/2021 21:01:43 - INFO - __main__ - Step 43699: {'lr': 0.0004082986724240835, 'samples': 8390208, 'steps': 43698, 'loss/train': 1.6733640432357788} 08/30/2021 21:01:43 - INFO - __main__ - Step 43700: {'lr': 0.00040829456500777084, 'samples': 8390400, 'steps': 43699, 'loss/train': 1.4554531574249268} 08/30/2021 21:01:44 - INFO - __main__ - Step 43701: {'lr': 0.00040829045752013317, 'samples': 8390592, 'steps': 43700, 'loss/train': 1.7216246128082275} 08/30/2021 21:01:45 - INFO - __main__ - Step 43702: {'lr': 0.00040828634996117213, 'samples': 8390784, 'steps': 43701, 'loss/train': 0.9410873055458069} 08/30/2021 21:01:46 - INFO - __main__ - Step 43703: {'lr': 0.0004082822423308897, 'samples': 8390976, 'steps': 43702, 'loss/train': 1.5017255544662476} 08/30/2021 21:01:46 - INFO - __main__ - Step 43704: {'lr': 0.00040827813462928784, 'samples': 8391168, 'steps': 43703, 'loss/train': 1.172599196434021} 08/30/2021 21:01:46 - INFO - __main__ - Step 43705: {'lr': 0.0004082740268563683, 'samples': 8391360, 'steps': 43704, 'loss/train': 1.2726798057556152} 08/30/2021 21:01:47 - INFO - __main__ - Step 43706: {'lr': 0.0004082699190121329, 'samples': 8391552, 'steps': 43705, 'loss/train': 1.0417487621307373} 08/30/2021 21:01:48 - INFO - __main__ - Step 43707: {'lr': 0.00040826581109658345, 'samples': 8391744, 'steps': 43706, 'loss/train': 1.6766895055770874} 08/30/2021 21:01:49 - INFO - __main__ - Step 43708: {'lr': 0.00040826170310972196, 'samples': 8391936, 'steps': 43707, 'loss/train': 1.2837923765182495} 08/30/2021 21:01:49 - INFO - __main__ - Step 43709: {'lr': 0.0004082575950515501, 'samples': 8392128, 'steps': 43708, 'loss/train': 1.6939594745635986} 08/30/2021 21:01:49 - INFO - __main__ - Step 43710: {'lr': 0.00040825348692206985, 'samples': 8392320, 'steps': 43709, 'loss/train': 0.06294246762990952} 08/30/2021 21:01:50 - INFO - __main__ - Step 43711: {'lr': 0.0004082493787212831, 'samples': 8392512, 'steps': 43710, 'loss/train': 1.4290003776550293} 08/30/2021 21:01:51 - INFO - __main__ - Step 43712: {'lr': 0.00040824527044919153, 'samples': 8392704, 'steps': 43711, 'loss/train': 1.5055707693099976} 08/30/2021 21:01:52 - INFO - __main__ - Step 43713: {'lr': 0.0004082411621057971, 'samples': 8392896, 'steps': 43712, 'loss/train': 0.5905166864395142} 08/30/2021 21:01:52 - INFO - __main__ - Step 43714: {'lr': 0.00040823705369110163, 'samples': 8393088, 'steps': 43713, 'loss/train': 1.1393905878067017} 08/30/2021 21:01:52 - INFO - __main__ - Step 43715: {'lr': 0.000408232945205107, 'samples': 8393280, 'steps': 43714, 'loss/train': 0.6976398825645447} 08/30/2021 21:01:53 - INFO - __main__ - Step 43716: {'lr': 0.00040822883664781506, 'samples': 8393472, 'steps': 43715, 'loss/train': 1.6211543083190918} 08/30/2021 21:01:54 - INFO - __main__ - Step 43717: {'lr': 0.0004082247280192276, 'samples': 8393664, 'steps': 43716, 'loss/train': 1.4505462646484375} 08/30/2021 21:01:55 - INFO - __main__ - Step 43718: {'lr': 0.00040822061931934656, 'samples': 8393856, 'steps': 43717, 'loss/train': 1.775937795639038} 08/30/2021 21:01:55 - INFO - __main__ - Step 43719: {'lr': 0.00040821651054817376, 'samples': 8394048, 'steps': 43718, 'loss/train': 0.8606746196746826} 08/30/2021 21:01:55 - INFO - __main__ - Step 43720: {'lr': 0.000408212401705711, 'samples': 8394240, 'steps': 43719, 'loss/train': 0.05085897445678711} 08/30/2021 21:01:56 - INFO - __main__ - Step 43721: {'lr': 0.0004082082927919602, 'samples': 8394432, 'steps': 43720, 'loss/train': 0.7344890236854553} 08/30/2021 21:01:57 - INFO - __main__ - Step 43722: {'lr': 0.0004082041838069232, 'samples': 8394624, 'steps': 43721, 'loss/train': 0.7271328568458557} 08/30/2021 21:01:58 - INFO - __main__ - Step 43723: {'lr': 0.0004082000747506018, 'samples': 8394816, 'steps': 43722, 'loss/train': 1.4934117794036865} 08/30/2021 21:01:58 - INFO - __main__ - Step 43724: {'lr': 0.00040819596562299793, 'samples': 8395008, 'steps': 43723, 'loss/train': 1.8259570598602295} 08/30/2021 21:01:59 - INFO - __main__ - Step 43725: {'lr': 0.0004081918564241134, 'samples': 8395200, 'steps': 43724, 'loss/train': 1.497853398323059} 08/30/2021 21:01:59 - INFO - __main__ - Step 43726: {'lr': 0.00040818774715395, 'samples': 8395392, 'steps': 43725, 'loss/train': 1.4134975671768188} 08/30/2021 21:02:01 - INFO - __main__ - Step 43727: {'lr': 0.0004081836378125097, 'samples': 8395584, 'steps': 43726, 'loss/train': 0.7622026801109314} 08/30/2021 21:02:01 - INFO - __main__ - Step 43728: {'lr': 0.00040817952839979424, 'samples': 8395776, 'steps': 43727, 'loss/train': 1.0191752910614014} 08/30/2021 21:02:02 - INFO - __main__ - Step 43729: {'lr': 0.00040817541891580557, 'samples': 8395968, 'steps': 43728, 'loss/train': 1.3521406650543213} 08/30/2021 21:02:02 - INFO - __main__ - Step 43730: {'lr': 0.00040817130936054546, 'samples': 8396160, 'steps': 43729, 'loss/train': 1.674381971359253} 08/30/2021 21:02:02 - INFO - __main__ - Step 43731: {'lr': 0.00040816719973401586, 'samples': 8396352, 'steps': 43730, 'loss/train': 1.7359634637832642} 08/30/2021 21:02:03 - INFO - __main__ - Step 43732: {'lr': 0.0004081630900362185, 'samples': 8396544, 'steps': 43731, 'loss/train': 1.6136072874069214} 08/30/2021 21:02:03 - INFO - __main__ - Step 43733: {'lr': 0.0004081589802671553, 'samples': 8396736, 'steps': 43732, 'loss/train': 1.2608113288879395} 08/30/2021 21:02:05 - INFO - __main__ - Step 43734: {'lr': 0.00040815487042682814, 'samples': 8396928, 'steps': 43733, 'loss/train': 1.5819666385650635} 08/30/2021 21:02:06 - INFO - __main__ - Step 43735: {'lr': 0.0004081507605152388, 'samples': 8397120, 'steps': 43734, 'loss/train': 0.5912426710128784} 08/30/2021 21:02:06 - INFO - __main__ - Step 43736: {'lr': 0.0004081466505323892, 'samples': 8397312, 'steps': 43735, 'loss/train': 1.3046391010284424} 08/30/2021 21:02:06 - INFO - __main__ - Step 43737: {'lr': 0.0004081425404782811, 'samples': 8397504, 'steps': 43736, 'loss/train': 1.4426459074020386} 08/30/2021 21:02:07 - INFO - __main__ - Step 43738: {'lr': 0.00040813843035291655, 'samples': 8397696, 'steps': 43737, 'loss/train': 1.0813347101211548} 08/30/2021 21:02:08 - INFO - __main__ - Step 43739: {'lr': 0.00040813432015629714, 'samples': 8397888, 'steps': 43738, 'loss/train': 2.5605125427246094} 08/30/2021 21:02:09 - INFO - __main__ - Step 43740: {'lr': 0.0004081302098884249, 'samples': 8398080, 'steps': 43739, 'loss/train': 0.8698285818099976} 08/30/2021 21:02:09 - INFO - __main__ - Step 43741: {'lr': 0.0004081260995493015, 'samples': 8398272, 'steps': 43740, 'loss/train': 1.6621204614639282} 08/30/2021 21:02:09 - INFO - __main__ - Step 43742: {'lr': 0.0004081219891389291, 'samples': 8398464, 'steps': 43741, 'loss/train': 1.5140966176986694} 08/30/2021 21:02:10 - INFO - __main__ - Step 43743: {'lr': 0.0004081178786573092, 'samples': 8398656, 'steps': 43742, 'loss/train': 1.632564663887024} 08/30/2021 21:02:11 - INFO - __main__ - Step 43744: {'lr': 0.000408113768104444, 'samples': 8398848, 'steps': 43743, 'loss/train': 1.4046502113342285} 08/30/2021 21:02:12 - INFO - __main__ - Step 43745: {'lr': 0.0004081096574803351, 'samples': 8399040, 'steps': 43744, 'loss/train': 1.2226265668869019} 08/30/2021 21:02:12 - INFO - __main__ - Step 43746: {'lr': 0.00040810554678498434, 'samples': 8399232, 'steps': 43745, 'loss/train': 1.4193094968795776} 08/30/2021 21:02:12 - INFO - __main__ - Step 43747: {'lr': 0.00040810143601839377, 'samples': 8399424, 'steps': 43746, 'loss/train': 1.0071032047271729} 08/30/2021 21:02:13 - INFO - __main__ - Step 43748: {'lr': 0.0004080973251805651, 'samples': 8399616, 'steps': 43747, 'loss/train': 1.4941350221633911} 08/30/2021 21:02:13 - INFO - __main__ - Step 43749: {'lr': 0.0004080932142715002, 'samples': 8399808, 'steps': 43748, 'loss/train': 1.2283105850219727} 08/30/2021 21:02:15 - INFO - __main__ - Step 43750: {'lr': 0.000408089103291201, 'samples': 8400000, 'steps': 43749, 'loss/train': 0.14603550732135773} 08/30/2021 21:02:15 - INFO - __main__ - Step 43751: {'lr': 0.0004080849922396692, 'samples': 8400192, 'steps': 43750, 'loss/train': 1.366817593574524} 08/30/2021 21:02:16 - INFO - __main__ - Step 43752: {'lr': 0.00040808088111690677, 'samples': 8400384, 'steps': 43751, 'loss/train': 0.3306434750556946} 08/30/2021 21:02:16 - INFO - __main__ - Step 43753: {'lr': 0.00040807676992291557, 'samples': 8400576, 'steps': 43752, 'loss/train': 1.340009331703186} 08/30/2021 21:02:16 - INFO - __main__ - Step 43754: {'lr': 0.0004080726586576974, 'samples': 8400768, 'steps': 43753, 'loss/train': 1.3768584728240967} 08/30/2021 21:02:18 - INFO - __main__ - Step 43755: {'lr': 0.0004080685473212541, 'samples': 8400960, 'steps': 43754, 'loss/train': 1.0741140842437744} 08/30/2021 21:02:18 - INFO - __main__ - Step 43756: {'lr': 0.0004080644359135876, 'samples': 8401152, 'steps': 43755, 'loss/train': 0.8876070976257324} 08/30/2021 21:02:19 - INFO - __main__ - Step 43757: {'lr': 0.00040806032443469967, 'samples': 8401344, 'steps': 43756, 'loss/train': 2.336810827255249} 08/30/2021 21:02:19 - INFO - __main__ - Step 43758: {'lr': 0.0004080562128845923, 'samples': 8401536, 'steps': 43757, 'loss/train': 0.38245025277137756} 08/30/2021 21:02:19 - INFO - __main__ - Step 43759: {'lr': 0.0004080521012632671, 'samples': 8401728, 'steps': 43758, 'loss/train': 1.6534713506698608} 08/30/2021 21:02:21 - INFO - __main__ - Step 43760: {'lr': 0.00040804798957072607, 'samples': 8401920, 'steps': 43759, 'loss/train': 1.2356674671173096} 08/30/2021 21:02:21 - INFO - __main__ - Step 43761: {'lr': 0.0004080438778069711, 'samples': 8402112, 'steps': 43760, 'loss/train': 1.4373027086257935} 08/30/2021 21:02:22 - INFO - __main__ - Step 43762: {'lr': 0.000408039765972004, 'samples': 8402304, 'steps': 43761, 'loss/train': 1.1325913667678833} 08/30/2021 21:02:22 - INFO - __main__ - Step 43763: {'lr': 0.0004080356540658266, 'samples': 8402496, 'steps': 43762, 'loss/train': 1.7916455268859863} 08/30/2021 21:02:22 - INFO - __main__ - Step 43764: {'lr': 0.00040803154208844086, 'samples': 8402688, 'steps': 43763, 'loss/train': 0.8445713520050049} 08/30/2021 21:02:24 - INFO - __main__ - Step 43765: {'lr': 0.00040802743003984845, 'samples': 8402880, 'steps': 43764, 'loss/train': 1.5798017978668213} 08/30/2021 21:02:24 - INFO - __main__ - Step 43766: {'lr': 0.0004080233179200513, 'samples': 8403072, 'steps': 43765, 'loss/train': 1.2093489170074463} 08/30/2021 21:02:25 - INFO - __main__ - Step 43767: {'lr': 0.00040801920572905133, 'samples': 8403264, 'steps': 43766, 'loss/train': 1.7842795848846436} 08/30/2021 21:02:25 - INFO - __main__ - Step 43768: {'lr': 0.0004080150934668503, 'samples': 8403456, 'steps': 43767, 'loss/train': 0.964861273765564} 08/30/2021 21:02:25 - INFO - __main__ - Step 43769: {'lr': 0.00040801098113345014, 'samples': 8403648, 'steps': 43768, 'loss/train': 1.5773066282272339} 08/30/2021 21:02:26 - INFO - __main__ - Step 43770: {'lr': 0.00040800686872885267, 'samples': 8403840, 'steps': 43769, 'loss/train': 1.9818191528320312} 08/30/2021 21:02:27 - INFO - __main__ - Step 43771: {'lr': 0.0004080027562530598, 'samples': 8404032, 'steps': 43770, 'loss/train': 1.4162108898162842} 08/30/2021 21:02:28 - INFO - __main__ - Step 43772: {'lr': 0.0004079986437060733, 'samples': 8404224, 'steps': 43771, 'loss/train': 1.3940703868865967} 08/30/2021 21:02:28 - INFO - __main__ - Step 43773: {'lr': 0.00040799453108789497, 'samples': 8404416, 'steps': 43772, 'loss/train': 1.5082343816757202} 08/30/2021 21:02:28 - INFO - __main__ - Step 43774: {'lr': 0.0004079904183985268, 'samples': 8404608, 'steps': 43773, 'loss/train': 1.5286884307861328} 08/30/2021 21:02:29 - INFO - __main__ - Step 43775: {'lr': 0.00040798630563797055, 'samples': 8404800, 'steps': 43774, 'loss/train': 1.7596948146820068} 08/30/2021 21:02:30 - INFO - __main__ - Step 43776: {'lr': 0.00040798219280622816, 'samples': 8404992, 'steps': 43775, 'loss/train': 1.007391095161438} 08/30/2021 21:02:31 - INFO - __main__ - Step 43777: {'lr': 0.0004079780799033014, 'samples': 8405184, 'steps': 43776, 'loss/train': 1.338560938835144} 08/30/2021 21:02:31 - INFO - __main__ - Step 43778: {'lr': 0.0004079739669291922, 'samples': 8405376, 'steps': 43777, 'loss/train': 1.2960642576217651} 08/30/2021 21:02:32 - INFO - __main__ - Step 43779: {'lr': 0.0004079698538839023, 'samples': 8405568, 'steps': 43778, 'loss/train': 0.4765457212924957} 08/30/2021 21:02:32 - INFO - __main__ - Step 43780: {'lr': 0.00040796574076743366, 'samples': 8405760, 'steps': 43779, 'loss/train': 1.7926512956619263} 08/30/2021 21:02:33 - INFO - __main__ - Step 43781: {'lr': 0.00040796162757978803, 'samples': 8405952, 'steps': 43780, 'loss/train': 1.431853175163269} 08/30/2021 21:02:34 - INFO - __main__ - Step 43782: {'lr': 0.00040795751432096746, 'samples': 8406144, 'steps': 43781, 'loss/train': 1.6874363422393799} 08/30/2021 21:02:34 - INFO - __main__ - Step 43783: {'lr': 0.00040795340099097357, 'samples': 8406336, 'steps': 43782, 'loss/train': 1.5607199668884277} 08/30/2021 21:02:35 - INFO - __main__ - Step 43784: {'lr': 0.00040794928758980837, 'samples': 8406528, 'steps': 43783, 'loss/train': 1.580759048461914} 08/30/2021 21:02:35 - INFO - __main__ - Step 43785: {'lr': 0.0004079451741174737, 'samples': 8406720, 'steps': 43784, 'loss/train': 1.0252681970596313} 08/30/2021 21:02:37 - INFO - __main__ - Step 43786: {'lr': 0.00040794106057397123, 'samples': 8406912, 'steps': 43785, 'loss/train': 1.7935954332351685} 08/30/2021 21:02:37 - INFO - __main__ - Step 43787: {'lr': 0.00040793694695930304, 'samples': 8407104, 'steps': 43786, 'loss/train': 1.7533847093582153} 08/30/2021 21:02:38 - INFO - __main__ - Step 43788: {'lr': 0.00040793283327347085, 'samples': 8407296, 'steps': 43787, 'loss/train': 1.3374837636947632} 08/30/2021 21:02:38 - INFO - __main__ - Step 43789: {'lr': 0.00040792871951647657, 'samples': 8407488, 'steps': 43788, 'loss/train': 1.531365990638733} 08/30/2021 21:02:38 - INFO - __main__ - Step 43790: {'lr': 0.00040792460568832214, 'samples': 8407680, 'steps': 43789, 'loss/train': 1.2555129528045654} 08/30/2021 21:02:40 - INFO - __main__ - Step 43791: {'lr': 0.00040792049178900924, 'samples': 8407872, 'steps': 43790, 'loss/train': 0.8884113430976868} 08/30/2021 21:02:40 - INFO - __main__ - Step 43792: {'lr': 0.00040791637781853983, 'samples': 8408064, 'steps': 43791, 'loss/train': 0.9146926999092102} 08/30/2021 21:02:41 - INFO - __main__ - Step 43793: {'lr': 0.0004079122637769157, 'samples': 8408256, 'steps': 43792, 'loss/train': 1.1160128116607666} 08/30/2021 21:02:41 - INFO - __main__ - Step 43794: {'lr': 0.0004079081496641388, 'samples': 8408448, 'steps': 43793, 'loss/train': 1.344011664390564} 08/30/2021 21:02:41 - INFO - __main__ - Step 43795: {'lr': 0.0004079040354802109, 'samples': 8408640, 'steps': 43794, 'loss/train': 1.2532360553741455} 08/30/2021 21:02:43 - INFO - __main__ - Step 43796: {'lr': 0.00040789992122513386, 'samples': 8408832, 'steps': 43795, 'loss/train': 1.2086224555969238} 08/30/2021 21:02:44 - INFO - __main__ - Step 43797: {'lr': 0.00040789580689890953, 'samples': 8409024, 'steps': 43796, 'loss/train': 1.8269503116607666} 08/30/2021 21:02:44 - INFO - __main__ - Step 43798: {'lr': 0.00040789169250153985, 'samples': 8409216, 'steps': 43797, 'loss/train': 1.4898165464401245} 08/30/2021 21:02:44 - INFO - __main__ - Step 43799: {'lr': 0.00040788757803302656, 'samples': 8409408, 'steps': 43798, 'loss/train': 1.146410584449768} 08/30/2021 21:02:45 - INFO - __main__ - Step 43800: {'lr': 0.00040788346349337156, 'samples': 8409600, 'steps': 43799, 'loss/train': 1.0319801568984985} 08/30/2021 21:02:46 - INFO - __main__ - Step 43801: {'lr': 0.00040787934888257673, 'samples': 8409792, 'steps': 43800, 'loss/train': 0.7334209680557251} 08/30/2021 21:02:47 - INFO - __main__ - Step 43802: {'lr': 0.00040787523420064394, 'samples': 8409984, 'steps': 43801, 'loss/train': 1.9177191257476807} 08/30/2021 21:02:47 - INFO - __main__ - Step 43803: {'lr': 0.00040787111944757496, 'samples': 8410176, 'steps': 43802, 'loss/train': 1.2845685482025146} 08/30/2021 21:02:47 - INFO - __main__ - Step 43804: {'lr': 0.0004078670046233717, 'samples': 8410368, 'steps': 43803, 'loss/train': 1.444190502166748} 08/30/2021 21:02:48 - INFO - __main__ - Step 43805: {'lr': 0.000407862889728036, 'samples': 8410560, 'steps': 43804, 'loss/train': 1.090221881866455} 08/30/2021 21:02:49 - INFO - __main__ - Step 43806: {'lr': 0.0004078587747615697, 'samples': 8410752, 'steps': 43805, 'loss/train': 1.213196873664856} 08/30/2021 21:02:50 - INFO - __main__ - Step 43807: {'lr': 0.00040785465972397475, 'samples': 8410944, 'steps': 43806, 'loss/train': 1.4244780540466309} 08/30/2021 21:02:50 - INFO - __main__ - Step 43808: {'lr': 0.0004078505446152528, 'samples': 8411136, 'steps': 43807, 'loss/train': 1.005820631980896} 08/30/2021 21:02:51 - INFO - __main__ - Step 43809: {'lr': 0.0004078464294354059, 'samples': 8411328, 'steps': 43808, 'loss/train': 0.8411766886711121} 08/30/2021 21:02:51 - INFO - __main__ - Step 43810: {'lr': 0.00040784231418443585, 'samples': 8411520, 'steps': 43809, 'loss/train': 1.2766271829605103} 08/30/2021 21:02:51 - INFO - __main__ - Step 43811: {'lr': 0.00040783819886234445, 'samples': 8411712, 'steps': 43810, 'loss/train': 0.6391169428825378} 08/30/2021 21:02:53 - INFO - __main__ - Step 43812: {'lr': 0.00040783408346913366, 'samples': 8411904, 'steps': 43811, 'loss/train': 0.5448909401893616} 08/30/2021 21:02:53 - INFO - __main__ - Step 43813: {'lr': 0.00040782996800480523, 'samples': 8412096, 'steps': 43812, 'loss/train': 0.4895644783973694} 08/30/2021 21:02:53 - INFO - __main__ - Step 43814: {'lr': 0.000407825852469361, 'samples': 8412288, 'steps': 43813, 'loss/train': 1.6099004745483398} 08/30/2021 21:02:54 - INFO - __main__ - Step 43815: {'lr': 0.00040782173686280287, 'samples': 8412480, 'steps': 43814, 'loss/train': 1.7540996074676514} 08/30/2021 21:02:54 - INFO - __main__ - Step 43816: {'lr': 0.0004078176211851328, 'samples': 8412672, 'steps': 43815, 'loss/train': 1.876587152481079} 08/30/2021 21:02:56 - INFO - __main__ - Step 43817: {'lr': 0.0004078135054363524, 'samples': 8412864, 'steps': 43816, 'loss/train': 1.8550409078598022} 08/30/2021 21:02:56 - INFO - __main__ - Step 43818: {'lr': 0.00040780938961646385, 'samples': 8413056, 'steps': 43817, 'loss/train': 1.0840035676956177} 08/30/2021 21:02:56 - INFO - __main__ - Step 43819: {'lr': 0.00040780527372546874, 'samples': 8413248, 'steps': 43818, 'loss/train': 1.4322997331619263} 08/30/2021 21:02:57 - INFO - __main__ - Step 43820: {'lr': 0.000407801157763369, 'samples': 8413440, 'steps': 43819, 'loss/train': 1.511563777923584} 08/30/2021 21:02:57 - INFO - __main__ - Step 43821: {'lr': 0.0004077970417301665, 'samples': 8413632, 'steps': 43820, 'loss/train': 1.0809530019760132} 08/30/2021 21:02:59 - INFO - __main__ - Step 43822: {'lr': 0.00040779292562586304, 'samples': 8413824, 'steps': 43821, 'loss/train': 1.597350001335144} 08/30/2021 21:02:59 - INFO - __main__ - Step 43823: {'lr': 0.0004077888094504606, 'samples': 8414016, 'steps': 43822, 'loss/train': 0.8721112608909607} 08/30/2021 21:02:59 - INFO - __main__ - Step 43824: {'lr': 0.0004077846932039609, 'samples': 8414208, 'steps': 43823, 'loss/train': 0.8232129812240601} 08/30/2021 21:03:00 - INFO - __main__ - Step 43825: {'lr': 0.00040778057688636594, 'samples': 8414400, 'steps': 43824, 'loss/train': 1.5072728395462036} 08/30/2021 21:03:00 - INFO - __main__ - Step 43826: {'lr': 0.00040777646049767736, 'samples': 8414592, 'steps': 43825, 'loss/train': 1.5393011569976807} 08/30/2021 21:03:02 - INFO - __main__ - Step 43827: {'lr': 0.0004077723440378972, 'samples': 8414784, 'steps': 43826, 'loss/train': 1.9465694427490234} 08/30/2021 21:03:02 - INFO - __main__ - Step 43828: {'lr': 0.0004077682275070273, 'samples': 8414976, 'steps': 43827, 'loss/train': 1.6047816276550293} 08/30/2021 21:03:02 - INFO - __main__ - Step 43829: {'lr': 0.00040776411090506944, 'samples': 8415168, 'steps': 43828, 'loss/train': 2.350435256958008} 08/30/2021 21:03:03 - INFO - __main__ - Step 43830: {'lr': 0.0004077599942320255, 'samples': 8415360, 'steps': 43829, 'loss/train': 0.9171452522277832} 08/30/2021 21:03:03 - INFO - __main__ - Step 43831: {'lr': 0.00040775587748789733, 'samples': 8415552, 'steps': 43830, 'loss/train': 1.3286149501800537} 08/30/2021 21:03:05 - INFO - __main__ - Step 43832: {'lr': 0.0004077517606726868, 'samples': 8415744, 'steps': 43831, 'loss/train': 0.9289796352386475} 08/30/2021 21:03:05 - INFO - __main__ - Step 43833: {'lr': 0.0004077476437863958, 'samples': 8415936, 'steps': 43832, 'loss/train': 0.6664148569107056} 08/30/2021 21:03:06 - INFO - __main__ - Step 43834: {'lr': 0.0004077435268290261, 'samples': 8416128, 'steps': 43833, 'loss/train': 1.2577805519104004} 08/30/2021 21:03:06 - INFO - __main__ - Step 43835: {'lr': 0.0004077394098005796, 'samples': 8416320, 'steps': 43834, 'loss/train': 1.7036726474761963} 08/30/2021 21:03:06 - INFO - __main__ - Step 43836: {'lr': 0.00040773529270105816, 'samples': 8416512, 'steps': 43835, 'loss/train': 1.7892454862594604} 08/30/2021 21:03:07 - INFO - __main__ - Step 43837: {'lr': 0.0004077311755304637, 'samples': 8416704, 'steps': 43836, 'loss/train': 1.1891313791275024} 08/30/2021 21:03:08 - INFO - __main__ - Step 43838: {'lr': 0.000407727058288798, 'samples': 8416896, 'steps': 43837, 'loss/train': 1.8460379838943481} 08/30/2021 21:03:08 - INFO - __main__ - Step 43839: {'lr': 0.00040772294097606276, 'samples': 8417088, 'steps': 43838, 'loss/train': 0.9670521020889282} 08/30/2021 21:03:09 - INFO - __main__ - Step 43840: {'lr': 0.0004077188235922601, 'samples': 8417280, 'steps': 43839, 'loss/train': 0.8974589705467224} 08/30/2021 21:03:09 - INFO - __main__ - Step 43841: {'lr': 0.0004077147061373918, 'samples': 8417472, 'steps': 43840, 'loss/train': 1.8419151306152344} 08/30/2021 21:03:10 - INFO - __main__ - Step 43842: {'lr': 0.00040771058861145963, 'samples': 8417664, 'steps': 43841, 'loss/train': 1.1319509744644165} 08/30/2021 21:03:11 - INFO - __main__ - Step 43843: {'lr': 0.0004077064710144656, 'samples': 8417856, 'steps': 43842, 'loss/train': 1.4944205284118652} 08/30/2021 21:03:12 - INFO - __main__ - Step 43844: {'lr': 0.0004077023533464114, 'samples': 8418048, 'steps': 43843, 'loss/train': 1.3543598651885986} 08/30/2021 21:03:12 - INFO - __main__ - Step 43845: {'lr': 0.000407698235607299, 'samples': 8418240, 'steps': 43844, 'loss/train': 1.1973967552185059} 08/30/2021 21:03:13 - INFO - __main__ - Step 43846: {'lr': 0.0004076941177971301, 'samples': 8418432, 'steps': 43845, 'loss/train': 1.476593255996704} 08/30/2021 21:03:13 - INFO - __main__ - Step 43847: {'lr': 0.0004076899999159067, 'samples': 8418624, 'steps': 43846, 'loss/train': 1.3293201923370361} 08/30/2021 21:03:14 - INFO - __main__ - Step 43848: {'lr': 0.0004076858819636307, 'samples': 8418816, 'steps': 43847, 'loss/train': 1.1217072010040283} 08/30/2021 21:03:15 - INFO - __main__ - Step 43849: {'lr': 0.0004076817639403038, 'samples': 8419008, 'steps': 43848, 'loss/train': 1.5927393436431885} 08/30/2021 21:03:15 - INFO - __main__ - Step 43850: {'lr': 0.0004076776458459279, 'samples': 8419200, 'steps': 43849, 'loss/train': 1.2272676229476929} 08/30/2021 21:03:15 - INFO - __main__ - Step 43851: {'lr': 0.00040767352768050503, 'samples': 8419392, 'steps': 43850, 'loss/train': 1.0939770936965942} 08/30/2021 21:03:16 - INFO - __main__ - Step 43852: {'lr': 0.0004076694094440368, 'samples': 8419584, 'steps': 43851, 'loss/train': 1.546807050704956} 08/30/2021 21:03:17 - INFO - __main__ - Step 43853: {'lr': 0.0004076652911365252, 'samples': 8419776, 'steps': 43852, 'loss/train': 1.1474628448486328} 08/30/2021 21:03:18 - INFO - __main__ - Step 43854: {'lr': 0.00040766117275797196, 'samples': 8419968, 'steps': 43853, 'loss/train': 1.6309174299240112} 08/30/2021 21:03:18 - INFO - __main__ - Step 43855: {'lr': 0.0004076570543083792, 'samples': 8420160, 'steps': 43854, 'loss/train': 1.2588063478469849} 08/30/2021 21:03:18 - INFO - __main__ - Step 43856: {'lr': 0.0004076529357877485, 'samples': 8420352, 'steps': 43855, 'loss/train': 1.4545656442642212} 08/30/2021 21:03:19 - INFO - __main__ - Step 43857: {'lr': 0.00040764881719608184, 'samples': 8420544, 'steps': 43856, 'loss/train': 2.186136245727539} 08/30/2021 21:03:20 - INFO - __main__ - Step 43858: {'lr': 0.000407644698533381, 'samples': 8420736, 'steps': 43857, 'loss/train': 1.274720311164856} 08/30/2021 21:03:21 - INFO - __main__ - Step 43859: {'lr': 0.00040764057979964793, 'samples': 8420928, 'steps': 43858, 'loss/train': 1.7305853366851807} 08/30/2021 21:03:21 - INFO - __main__ - Step 43860: {'lr': 0.0004076364609948844, 'samples': 8421120, 'steps': 43859, 'loss/train': 1.5938680171966553} 08/30/2021 21:03:21 - INFO - __main__ - Step 43861: {'lr': 0.0004076323421190924, 'samples': 8421312, 'steps': 43860, 'loss/train': 1.387589931488037} 08/30/2021 21:03:22 - INFO - __main__ - Step 43862: {'lr': 0.0004076282231722737, 'samples': 8421504, 'steps': 43861, 'loss/train': 1.0618559122085571} 08/30/2021 21:03:24 - INFO - __main__ - Step 43863: {'lr': 0.0004076241041544301, 'samples': 8421696, 'steps': 43862, 'loss/train': 1.2857544422149658} 08/30/2021 21:03:24 - INFO - __main__ - Step 43864: {'lr': 0.00040761998506556353, 'samples': 8421888, 'steps': 43863, 'loss/train': 1.4223642349243164} 08/30/2021 21:03:24 - INFO - __main__ - Step 43865: {'lr': 0.0004076158659056758, 'samples': 8422080, 'steps': 43864, 'loss/train': 1.2648245096206665} 08/30/2021 21:03:25 - INFO - __main__ - Step 43866: {'lr': 0.00040761174667476883, 'samples': 8422272, 'steps': 43865, 'loss/train': 0.03963041305541992} 08/30/2021 21:03:25 - INFO - __main__ - Step 43867: {'lr': 0.0004076076273728444, 'samples': 8422464, 'steps': 43866, 'loss/train': 1.169355869293213} 08/30/2021 21:03:26 - INFO - __main__ - Step 43868: {'lr': 0.0004076035079999045, 'samples': 8422656, 'steps': 43867, 'loss/train': 0.9768556952476501} 08/30/2021 21:03:27 - INFO - __main__ - Step 43869: {'lr': 0.0004075993885559508, 'samples': 8422848, 'steps': 43868, 'loss/train': 0.4165455102920532} 08/30/2021 21:03:27 - INFO - __main__ - Step 43870: {'lr': 0.0004075952690409852, 'samples': 8423040, 'steps': 43869, 'loss/train': 1.5621095895767212} 08/30/2021 21:03:28 - INFO - __main__ - Step 43871: {'lr': 0.00040759114945500974, 'samples': 8423232, 'steps': 43870, 'loss/train': 1.6777276992797852} 08/30/2021 21:03:28 - INFO - __main__ - Step 43872: {'lr': 0.0004075870297980261, 'samples': 8423424, 'steps': 43871, 'loss/train': 0.8194810152053833} 08/30/2021 21:03:29 - INFO - __main__ - Step 43873: {'lr': 0.0004075829100700361, 'samples': 8423616, 'steps': 43872, 'loss/train': 0.7439547777175903} 08/30/2021 21:03:30 - INFO - __main__ - Step 43874: {'lr': 0.0004075787902710417, 'samples': 8423808, 'steps': 43873, 'loss/train': 1.4584407806396484} 08/30/2021 21:03:31 - INFO - __main__ - Step 43875: {'lr': 0.0004075746704010448, 'samples': 8424000, 'steps': 43874, 'loss/train': 1.446795105934143} 08/30/2021 21:03:31 - INFO - __main__ - Step 43876: {'lr': 0.0004075705504600471, 'samples': 8424192, 'steps': 43875, 'loss/train': 1.3926080465316772} 08/30/2021 21:03:31 - INFO - __main__ - Step 43877: {'lr': 0.00040756643044805057, 'samples': 8424384, 'steps': 43876, 'loss/train': 1.0353636741638184} 08/30/2021 21:03:32 - INFO - __main__ - Step 43878: {'lr': 0.0004075623103650571, 'samples': 8424576, 'steps': 43877, 'loss/train': 1.4024126529693604} 08/30/2021 21:03:32 - INFO - __main__ - Step 43879: {'lr': 0.00040755819021106844, 'samples': 8424768, 'steps': 43878, 'loss/train': 1.1849769353866577} 08/30/2021 21:03:33 - INFO - __main__ - Step 43880: {'lr': 0.00040755406998608645, 'samples': 8424960, 'steps': 43879, 'loss/train': 1.5743694305419922} 08/30/2021 21:03:34 - INFO - __main__ - Step 43881: {'lr': 0.00040754994969011306, 'samples': 8425152, 'steps': 43880, 'loss/train': 1.6137919425964355} 08/30/2021 21:03:34 - INFO - __main__ - Step 43882: {'lr': 0.00040754582932315007, 'samples': 8425344, 'steps': 43881, 'loss/train': 1.4733422994613647} 08/30/2021 21:03:35 - INFO - __main__ - Step 43883: {'lr': 0.0004075417088851994, 'samples': 8425536, 'steps': 43882, 'loss/train': 1.5610766410827637} 08/30/2021 21:03:35 - INFO - __main__ - Step 43884: {'lr': 0.0004075375883762629, 'samples': 8425728, 'steps': 43883, 'loss/train': 1.7823412418365479} 08/30/2021 21:03:37 - INFO - __main__ - Step 43885: {'lr': 0.0004075334677963423, 'samples': 8425920, 'steps': 43884, 'loss/train': 1.299405574798584} 08/30/2021 21:03:37 - INFO - __main__ - Step 43886: {'lr': 0.0004075293471454396, 'samples': 8426112, 'steps': 43885, 'loss/train': 1.5364983081817627} 08/30/2021 21:03:38 - INFO - __main__ - Step 43887: {'lr': 0.0004075252264235566, 'samples': 8426304, 'steps': 43886, 'loss/train': 1.0168243646621704} 08/30/2021 21:03:38 - INFO - __main__ - Step 43888: {'lr': 0.0004075211056306951, 'samples': 8426496, 'steps': 43887, 'loss/train': 1.063670039176941} 08/30/2021 21:03:38 - INFO - __main__ - Step 43889: {'lr': 0.00040751698476685716, 'samples': 8426688, 'steps': 43888, 'loss/train': 0.824373185634613} 08/30/2021 21:03:40 - INFO - __main__ - Step 43890: {'lr': 0.00040751286383204437, 'samples': 8426880, 'steps': 43889, 'loss/train': 1.1412771940231323} 08/30/2021 21:03:40 - INFO - __main__ - Step 43891: {'lr': 0.0004075087428262588, 'samples': 8427072, 'steps': 43890, 'loss/train': 0.9771620035171509} 08/30/2021 21:03:41 - INFO - __main__ - Step 43892: {'lr': 0.0004075046217495022, 'samples': 8427264, 'steps': 43891, 'loss/train': 0.9868575930595398} 08/30/2021 21:03:41 - INFO - __main__ - Step 43893: {'lr': 0.00040750050060177643, 'samples': 8427456, 'steps': 43892, 'loss/train': 0.15345190465450287} 08/30/2021 21:03:42 - INFO - __main__ - Step 43894: {'lr': 0.00040749637938308336, 'samples': 8427648, 'steps': 43893, 'loss/train': 1.109050989151001} 08/30/2021 21:03:42 - INFO - __main__ - Step 43895: {'lr': 0.00040749225809342485, 'samples': 8427840, 'steps': 43894, 'loss/train': 1.54781174659729} 08/30/2021 21:03:44 - INFO - __main__ - Step 43896: {'lr': 0.00040748813673280277, 'samples': 8428032, 'steps': 43895, 'loss/train': 1.2555979490280151} 08/30/2021 21:03:44 - INFO - __main__ - Step 43897: {'lr': 0.0004074840153012189, 'samples': 8428224, 'steps': 43896, 'loss/train': 1.1280982494354248} 08/30/2021 21:03:45 - INFO - __main__ - Step 43898: {'lr': 0.0004074798937986753, 'samples': 8428416, 'steps': 43897, 'loss/train': 1.4909759759902954} 08/30/2021 21:03:45 - INFO - __main__ - Step 43899: {'lr': 0.00040747577222517364, 'samples': 8428608, 'steps': 43898, 'loss/train': 1.1590861082077026} 08/30/2021 21:03:46 - INFO - __main__ - Step 43900: {'lr': 0.0004074716505807158, 'samples': 8428800, 'steps': 43899, 'loss/train': 1.1700905561447144} 08/30/2021 21:03:47 - INFO - __main__ - Step 43901: {'lr': 0.0004074675288653037, 'samples': 8428992, 'steps': 43900, 'loss/train': 1.1349079608917236} 08/30/2021 21:03:48 - INFO - __main__ - Step 43902: {'lr': 0.0004074634070789391, 'samples': 8429184, 'steps': 43901, 'loss/train': 1.6077814102172852} 08/30/2021 21:03:48 - INFO - __main__ - Step 43903: {'lr': 0.0004074592852216239, 'samples': 8429376, 'steps': 43902, 'loss/train': 1.3170939683914185} 08/30/2021 21:03:48 - INFO - __main__ - Step 43904: {'lr': 0.0004074551632933601, 'samples': 8429568, 'steps': 43903, 'loss/train': 0.9808275103569031} 08/30/2021 21:03:49 - INFO - __main__ - Step 43905: {'lr': 0.00040745104129414933, 'samples': 8429760, 'steps': 43904, 'loss/train': 0.9745615124702454} 08/30/2021 21:03:50 - INFO - __main__ - Step 43906: {'lr': 0.0004074469192239936, 'samples': 8429952, 'steps': 43905, 'loss/train': 2.1799445152282715} 08/30/2021 21:03:51 - INFO - __main__ - Step 43907: {'lr': 0.0004074427970828947, 'samples': 8430144, 'steps': 43906, 'loss/train': 1.1147089004516602} 08/30/2021 21:03:51 - INFO - __main__ - Step 43908: {'lr': 0.00040743867487085444, 'samples': 8430336, 'steps': 43907, 'loss/train': 1.3706434965133667} 08/30/2021 21:03:52 - INFO - __main__ - Step 43909: {'lr': 0.0004074345525878748, 'samples': 8430528, 'steps': 43908, 'loss/train': 2.2214980125427246} 08/30/2021 21:03:52 - INFO - __main__ - Step 43910: {'lr': 0.0004074304302339576, 'samples': 8430720, 'steps': 43909, 'loss/train': 0.03032659739255905} 08/30/2021 21:03:52 - INFO - __main__ - Step 43911: {'lr': 0.0004074263078091046, 'samples': 8430912, 'steps': 43910, 'loss/train': 0.25154292583465576} 08/30/2021 21:03:54 - INFO - __main__ - Step 43912: {'lr': 0.00040742218531331786, 'samples': 8431104, 'steps': 43911, 'loss/train': 1.2891852855682373} 08/30/2021 21:03:54 - INFO - __main__ - Step 43913: {'lr': 0.0004074180627465991, 'samples': 8431296, 'steps': 43912, 'loss/train': 1.1473833322525024} 08/30/2021 21:03:55 - INFO - __main__ - Step 43914: {'lr': 0.00040741394010895013, 'samples': 8431488, 'steps': 43913, 'loss/train': 0.8665730357170105} 08/30/2021 21:03:55 - INFO - __main__ - Step 43915: {'lr': 0.0004074098174003729, 'samples': 8431680, 'steps': 43914, 'loss/train': 0.4884485900402069} 08/30/2021 21:03:56 - INFO - __main__ - Step 43916: {'lr': 0.0004074056946208692, 'samples': 8431872, 'steps': 43915, 'loss/train': 1.7602063417434692} 08/30/2021 21:03:57 - INFO - __main__ - Step 43917: {'lr': 0.0004074015717704409, 'samples': 8432064, 'steps': 43916, 'loss/train': 1.4096194505691528} 08/30/2021 21:03:57 - INFO - __main__ - Step 43918: {'lr': 0.00040739744884908994, 'samples': 8432256, 'steps': 43917, 'loss/train': 1.1563514471054077} 08/30/2021 21:03:58 - INFO - __main__ - Step 43919: {'lr': 0.00040739332585681807, 'samples': 8432448, 'steps': 43918, 'loss/train': 1.4544111490249634} 08/30/2021 21:03:58 - INFO - __main__ - Step 43920: {'lr': 0.00040738920279362724, 'samples': 8432640, 'steps': 43919, 'loss/train': 1.5442497730255127} 08/30/2021 21:03:58 - INFO - __main__ - Step 43921: {'lr': 0.00040738507965951923, 'samples': 8432832, 'steps': 43920, 'loss/train': 1.340509295463562} 08/30/2021 21:03:59 - INFO - __main__ - Step 43922: {'lr': 0.0004073809564544959, 'samples': 8433024, 'steps': 43921, 'loss/train': 1.0293766260147095} 08/30/2021 21:04:00 - INFO - __main__ - Step 43923: {'lr': 0.0004073768331785592, 'samples': 8433216, 'steps': 43922, 'loss/train': 1.2574676275253296} 08/30/2021 21:04:01 - INFO - __main__ - Step 43924: {'lr': 0.0004073727098317109, 'samples': 8433408, 'steps': 43923, 'loss/train': 0.984167218208313} 08/30/2021 21:04:01 - INFO - __main__ - Step 43925: {'lr': 0.0004073685864139529, 'samples': 8433600, 'steps': 43924, 'loss/train': 1.1035782098770142} 08/30/2021 21:04:02 - INFO - __main__ - Step 43926: {'lr': 0.00040736446292528704, 'samples': 8433792, 'steps': 43925, 'loss/train': 0.4938061237335205} 08/30/2021 21:04:02 - INFO - __main__ - Step 43927: {'lr': 0.0004073603393657152, 'samples': 8433984, 'steps': 43926, 'loss/train': 1.6660019159317017} 08/30/2021 21:04:03 - INFO - __main__ - Step 43928: {'lr': 0.0004073562157352392, 'samples': 8434176, 'steps': 43927, 'loss/train': 1.6551334857940674} 08/30/2021 21:04:04 - INFO - __main__ - Step 43929: {'lr': 0.00040735209203386093, 'samples': 8434368, 'steps': 43928, 'loss/train': 0.8628782629966736} 08/30/2021 21:04:04 - INFO - __main__ - Step 43930: {'lr': 0.00040734796826158226, 'samples': 8434560, 'steps': 43929, 'loss/train': 1.896470546722412} 08/30/2021 21:04:05 - INFO - __main__ - Step 43931: {'lr': 0.000407343844418405, 'samples': 8434752, 'steps': 43930, 'loss/train': 1.371834397315979} 08/30/2021 21:04:05 - INFO - __main__ - Step 43932: {'lr': 0.000407339720504331, 'samples': 8434944, 'steps': 43931, 'loss/train': 1.731903076171875} 08/30/2021 21:04:06 - INFO - __main__ - Step 43933: {'lr': 0.00040733559651936216, 'samples': 8435136, 'steps': 43932, 'loss/train': 1.1435072422027588} 08/30/2021 21:04:07 - INFO - __main__ - Step 43934: {'lr': 0.0004073314724635003, 'samples': 8435328, 'steps': 43933, 'loss/train': 1.2890568971633911} 08/30/2021 21:04:07 - INFO - __main__ - Step 43935: {'lr': 0.0004073273483367474, 'samples': 8435520, 'steps': 43934, 'loss/train': 1.3700639009475708} 08/30/2021 21:04:08 - INFO - __main__ - Step 43936: {'lr': 0.0004073232241391052, 'samples': 8435712, 'steps': 43935, 'loss/train': 0.9591358304023743} 08/30/2021 21:04:08 - INFO - __main__ - Step 43937: {'lr': 0.00040731909987057547, 'samples': 8435904, 'steps': 43936, 'loss/train': 1.744177222251892} 08/30/2021 21:04:09 - INFO - __main__ - Step 43938: {'lr': 0.0004073149755311603, 'samples': 8436096, 'steps': 43937, 'loss/train': 0.9035826921463013} 08/30/2021 21:04:10 - INFO - __main__ - Step 43939: {'lr': 0.0004073108511208614, 'samples': 8436288, 'steps': 43938, 'loss/train': 0.13453228771686554} 08/30/2021 21:04:10 - INFO - __main__ - Step 43940: {'lr': 0.0004073067266396807, 'samples': 8436480, 'steps': 43939, 'loss/train': 1.2400567531585693} 08/30/2021 21:04:11 - INFO - __main__ - Step 43941: {'lr': 0.00040730260208761995, 'samples': 8436672, 'steps': 43940, 'loss/train': 1.8284215927124023} 08/30/2021 21:04:11 - INFO - __main__ - Step 43942: {'lr': 0.0004072984774646811, 'samples': 8436864, 'steps': 43941, 'loss/train': 1.6001628637313843} 08/30/2021 21:04:11 - INFO - __main__ - Step 43943: {'lr': 0.0004072943527708659, 'samples': 8437056, 'steps': 43942, 'loss/train': 1.002147912979126} 08/30/2021 21:04:13 - INFO - __main__ - Step 43944: {'lr': 0.00040729022800617637, 'samples': 8437248, 'steps': 43943, 'loss/train': 1.5290356874465942} 08/30/2021 21:04:14 - INFO - __main__ - Step 43945: {'lr': 0.00040728610317061433, 'samples': 8437440, 'steps': 43944, 'loss/train': 1.4458039999008179} 08/30/2021 21:04:14 - INFO - __main__ - Step 43946: {'lr': 0.0004072819782641816, 'samples': 8437632, 'steps': 43945, 'loss/train': 0.09694980084896088} 08/30/2021 21:04:14 - INFO - __main__ - Step 43947: {'lr': 0.00040727785328687995, 'samples': 8437824, 'steps': 43946, 'loss/train': 1.6269800662994385} 08/30/2021 21:04:15 - INFO - __main__ - Step 43948: {'lr': 0.00040727372823871135, 'samples': 8438016, 'steps': 43947, 'loss/train': 1.74516761302948} 08/30/2021 21:04:17 - INFO - __main__ - Step 43949: {'lr': 0.00040726960311967766, 'samples': 8438208, 'steps': 43948, 'loss/train': 1.564193844795227} 08/30/2021 21:04:17 - INFO - __main__ - Step 43950: {'lr': 0.0004072654779297807, 'samples': 8438400, 'steps': 43949, 'loss/train': 1.4121545553207397} 08/30/2021 21:04:18 - INFO - __main__ - Step 43951: {'lr': 0.0004072613526690223, 'samples': 8438592, 'steps': 43950, 'loss/train': 1.3532283306121826} 08/30/2021 21:04:18 - INFO - __main__ - Step 43952: {'lr': 0.00040725722733740444, 'samples': 8438784, 'steps': 43951, 'loss/train': 0.6691199541091919} 08/30/2021 21:04:18 - INFO - __main__ - Step 43953: {'lr': 0.0004072531019349289, 'samples': 8438976, 'steps': 43952, 'loss/train': 0.08725161850452423} 08/30/2021 21:04:20 - INFO - __main__ - Step 43954: {'lr': 0.00040724897646159753, 'samples': 8439168, 'steps': 43953, 'loss/train': 1.4267401695251465} 08/30/2021 21:04:21 - INFO - __main__ - Step 43955: {'lr': 0.0004072448509174121, 'samples': 8439360, 'steps': 43954, 'loss/train': 1.5169744491577148} 08/30/2021 21:04:21 - INFO - __main__ - Step 43956: {'lr': 0.00040724072530237465, 'samples': 8439552, 'steps': 43955, 'loss/train': 1.4594926834106445} 08/30/2021 21:04:21 - INFO - __main__ - Step 43957: {'lr': 0.00040723659961648694, 'samples': 8439744, 'steps': 43956, 'loss/train': 2.367868185043335} 08/30/2021 21:04:22 - INFO - __main__ - Step 43958: {'lr': 0.0004072324738597509, 'samples': 8439936, 'steps': 43957, 'loss/train': 1.8564107418060303} 08/30/2021 21:04:22 - INFO - __main__ - Step 43959: {'lr': 0.00040722834803216834, 'samples': 8440128, 'steps': 43958, 'loss/train': 1.297493577003479} 08/30/2021 21:04:24 - INFO - __main__ - Step 43960: {'lr': 0.000407224222133741, 'samples': 8440320, 'steps': 43959, 'loss/train': 1.605318546295166} 08/30/2021 21:04:24 - INFO - __main__ - Step 43961: {'lr': 0.00040722009616447094, 'samples': 8440512, 'steps': 43960, 'loss/train': 0.9258254766464233} 08/30/2021 21:04:24 - INFO - __main__ - Step 43962: {'lr': 0.0004072159701243599, 'samples': 8440704, 'steps': 43961, 'loss/train': 1.8031784296035767} 08/30/2021 21:04:25 - INFO - __main__ - Step 43963: {'lr': 0.00040721184401340977, 'samples': 8440896, 'steps': 43962, 'loss/train': 1.1122639179229736} 08/30/2021 21:04:25 - INFO - __main__ - Step 43964: {'lr': 0.00040720771783162236, 'samples': 8441088, 'steps': 43963, 'loss/train': 2.069490671157837} 08/30/2021 21:04:27 - INFO - __main__ - Step 43965: {'lr': 0.0004072035915789997, 'samples': 8441280, 'steps': 43964, 'loss/train': 1.6985869407653809} 08/30/2021 21:04:27 - INFO - __main__ - Step 43966: {'lr': 0.0004071994652555434, 'samples': 8441472, 'steps': 43965, 'loss/train': 1.697348952293396} 08/30/2021 21:04:27 - INFO - __main__ - Step 43967: {'lr': 0.0004071953388612555, 'samples': 8441664, 'steps': 43966, 'loss/train': 1.953321933746338} 08/30/2021 21:04:28 - INFO - __main__ - Step 43968: {'lr': 0.0004071912123961379, 'samples': 8441856, 'steps': 43967, 'loss/train': 1.9049609899520874} 08/30/2021 21:04:28 - INFO - __main__ - Step 43969: {'lr': 0.00040718708586019226, 'samples': 8442048, 'steps': 43968, 'loss/train': 2.4460678100585938} 08/30/2021 21:04:30 - INFO - __main__ - Step 43970: {'lr': 0.00040718295925342053, 'samples': 8442240, 'steps': 43969, 'loss/train': 1.5364702939987183} 08/30/2021 21:04:30 - INFO - __main__ - Step 43971: {'lr': 0.0004071788325758246, 'samples': 8442432, 'steps': 43970, 'loss/train': 1.694097876548767} 08/30/2021 21:04:31 - INFO - __main__ - Step 43972: {'lr': 0.00040717470582740634, 'samples': 8442624, 'steps': 43971, 'loss/train': 1.186929702758789} 08/30/2021 21:04:31 - INFO - __main__ - Step 43973: {'lr': 0.0004071705790081676, 'samples': 8442816, 'steps': 43972, 'loss/train': 1.6415050029754639} 08/30/2021 21:04:31 - INFO - __main__ - Step 43974: {'lr': 0.0004071664521181102, 'samples': 8443008, 'steps': 43973, 'loss/train': 1.6543328762054443} 08/30/2021 21:04:32 - INFO - __main__ - Step 43975: {'lr': 0.00040716232515723596, 'samples': 8443200, 'steps': 43974, 'loss/train': 0.9742529988288879} 08/30/2021 21:04:33 - INFO - __main__ - Step 43976: {'lr': 0.00040715819812554686, 'samples': 8443392, 'steps': 43975, 'loss/train': 1.328025460243225} 08/30/2021 21:04:34 - INFO - __main__ - Step 43977: {'lr': 0.0004071540710230447, 'samples': 8443584, 'steps': 43976, 'loss/train': 1.250742793083191} 08/30/2021 21:04:34 - INFO - __main__ - Step 43978: {'lr': 0.0004071499438497314, 'samples': 8443776, 'steps': 43977, 'loss/train': 1.7461166381835938} 08/30/2021 21:04:34 - INFO - __main__ - Step 43979: {'lr': 0.0004071458166056087, 'samples': 8443968, 'steps': 43978, 'loss/train': 1.1584110260009766} 08/30/2021 21:04:35 - INFO - __main__ - Step 43980: {'lr': 0.00040714168929067854, 'samples': 8444160, 'steps': 43979, 'loss/train': 1.5158499479293823} 08/30/2021 21:04:36 - INFO - __main__ - Step 43981: {'lr': 0.0004071375619049427, 'samples': 8444352, 'steps': 43980, 'loss/train': 0.52995365858078} 08/30/2021 21:04:36 - INFO - __main__ - Step 43982: {'lr': 0.0004071334344484031, 'samples': 8444544, 'steps': 43981, 'loss/train': 1.6067311763763428} 08/30/2021 21:04:37 - INFO - __main__ - Step 43983: {'lr': 0.00040712930692106164, 'samples': 8444736, 'steps': 43982, 'loss/train': 1.567029595375061} 08/30/2021 21:04:37 - INFO - __main__ - Step 43984: {'lr': 0.00040712517932292016, 'samples': 8444928, 'steps': 43983, 'loss/train': 1.1418006420135498} 08/30/2021 21:04:37 - INFO - __main__ - Step 43985: {'lr': 0.00040712105165398044, 'samples': 8445120, 'steps': 43984, 'loss/train': 1.5418975353240967} 08/30/2021 21:04:40 - INFO - __main__ - Step 43986: {'lr': 0.0004071169239142445, 'samples': 8445312, 'steps': 43985, 'loss/train': 0.8572920560836792} 08/30/2021 21:04:40 - INFO - __main__ - Step 43987: {'lr': 0.000407112796103714, 'samples': 8445504, 'steps': 43986, 'loss/train': 1.5083720684051514} 08/30/2021 21:04:41 - INFO - __main__ - Step 43988: {'lr': 0.0004071086682223909, 'samples': 8445696, 'steps': 43987, 'loss/train': 1.4546016454696655} 08/30/2021 21:04:41 - INFO - __main__ - Step 43989: {'lr': 0.0004071045402702771, 'samples': 8445888, 'steps': 43988, 'loss/train': 1.4353991746902466} 08/30/2021 21:04:41 - INFO - __main__ - Step 43990: {'lr': 0.0004071004122473744, 'samples': 8446080, 'steps': 43989, 'loss/train': 4.287884712219238} 08/30/2021 21:04:42 - INFO - __main__ - Step 43991: {'lr': 0.0004070962841536847, 'samples': 8446272, 'steps': 43990, 'loss/train': 3.6109960079193115} 08/30/2021 21:04:42 - INFO - __main__ - Step 43992: {'lr': 0.0004070921559892098, 'samples': 8446464, 'steps': 43991, 'loss/train': 1.8031673431396484} 08/30/2021 21:04:44 - INFO - __main__ - Step 43993: {'lr': 0.00040708802775395165, 'samples': 8446656, 'steps': 43992, 'loss/train': 1.3961414098739624} 08/30/2021 21:04:44 - INFO - __main__ - Step 43994: {'lr': 0.000407083899447912, 'samples': 8446848, 'steps': 43993, 'loss/train': 1.6908056735992432} 08/30/2021 21:04:45 - INFO - __main__ - Step 43995: {'lr': 0.00040707977107109285, 'samples': 8447040, 'steps': 43994, 'loss/train': 1.4549931287765503} 08/30/2021 21:04:45 - INFO - __main__ - Step 43996: {'lr': 0.00040707564262349594, 'samples': 8447232, 'steps': 43995, 'loss/train': 1.7547231912612915} 08/30/2021 21:04:46 - INFO - __main__ - Step 43997: {'lr': 0.0004070715141051231, 'samples': 8447424, 'steps': 43996, 'loss/train': 1.4241794347763062} 08/30/2021 21:04:46 - INFO - __main__ - Step 43998: {'lr': 0.00040706738551597634, 'samples': 8447616, 'steps': 43997, 'loss/train': 1.6100412607192993} 08/30/2021 21:04:48 - INFO - __main__ - Step 43999: {'lr': 0.0004070632568560574, 'samples': 8447808, 'steps': 43998, 'loss/train': 1.0230473279953003} 08/30/2021 21:04:48 - INFO - __main__ - Step 44000: {'lr': 0.0004070591281253682, 'samples': 8448000, 'steps': 43999, 'loss/train': 1.6883628368377686} 08/30/2021 21:04:49 - INFO - __main__ - Step 44001: {'lr': 0.0004070549993239106, 'samples': 8448192, 'steps': 44000, 'loss/train': 1.7681210041046143} 08/30/2021 21:04:49 - INFO - __main__ - Step 44002: {'lr': 0.0004070508704516864, 'samples': 8448384, 'steps': 44001, 'loss/train': 1.634460687637329} 08/30/2021 21:04:49 - INFO - __main__ - Step 44003: {'lr': 0.00040704674150869753, 'samples': 8448576, 'steps': 44002, 'loss/train': 0.09653045237064362} 08/30/2021 21:04:51 - INFO - __main__ - Step 44004: {'lr': 0.0004070426124949458, 'samples': 8448768, 'steps': 44003, 'loss/train': 1.0189266204833984} 08/30/2021 21:04:52 - INFO - __main__ - Step 44005: {'lr': 0.00040703848341043313, 'samples': 8448960, 'steps': 44004, 'loss/train': 1.2246114015579224} 08/30/2021 21:04:52 - INFO - __main__ - Step 44006: {'lr': 0.00040703435425516136, 'samples': 8449152, 'steps': 44005, 'loss/train': 1.3576551675796509} 08/30/2021 21:04:53 - INFO - __main__ - Step 44007: {'lr': 0.0004070302250291322, 'samples': 8449344, 'steps': 44006, 'loss/train': 1.2517186403274536} 08/30/2021 21:04:53 - INFO - __main__ - Step 44008: {'lr': 0.0004070260957323478, 'samples': 8449536, 'steps': 44007, 'loss/train': 0.9721700549125671} 08/30/2021 21:04:54 - INFO - __main__ - Step 44009: {'lr': 0.0004070219663648098, 'samples': 8449728, 'steps': 44008, 'loss/train': 0.29462742805480957} 08/30/2021 21:04:55 - INFO - __main__ - Step 44010: {'lr': 0.0004070178369265201, 'samples': 8449920, 'steps': 44009, 'loss/train': 1.1606645584106445} 08/30/2021 21:04:55 - INFO - __main__ - Step 44011: {'lr': 0.00040701370741748057, 'samples': 8450112, 'steps': 44010, 'loss/train': 1.4054937362670898} 08/30/2021 21:04:56 - INFO - __main__ - Step 44012: {'lr': 0.0004070095778376932, 'samples': 8450304, 'steps': 44011, 'loss/train': 1.9526406526565552} 08/30/2021 21:04:56 - INFO - __main__ - Step 44013: {'lr': 0.0004070054481871597, 'samples': 8450496, 'steps': 44012, 'loss/train': 1.422410011291504} 08/30/2021 21:04:56 - INFO - __main__ - Step 44014: {'lr': 0.00040700131846588185, 'samples': 8450688, 'steps': 44013, 'loss/train': 0.7295418977737427} 08/30/2021 21:04:58 - INFO - __main__ - Step 44015: {'lr': 0.0004069971886738617, 'samples': 8450880, 'steps': 44014, 'loss/train': 0.7755770683288574} 08/30/2021 21:04:58 - INFO - __main__ - Step 44016: {'lr': 0.00040699305881110103, 'samples': 8451072, 'steps': 44015, 'loss/train': 0.23817451298236847} 08/30/2021 21:04:59 - INFO - __main__ - Step 44017: {'lr': 0.00040698892887760174, 'samples': 8451264, 'steps': 44016, 'loss/train': 1.6032133102416992} 08/30/2021 21:04:59 - INFO - __main__ - Step 44018: {'lr': 0.00040698479887336567, 'samples': 8451456, 'steps': 44017, 'loss/train': 0.8851715922355652} 08/30/2021 21:04:59 - INFO - __main__ - Step 44019: {'lr': 0.00040698066879839463, 'samples': 8451648, 'steps': 44018, 'loss/train': 1.801906943321228} 08/30/2021 21:05:01 - INFO - __main__ - Step 44020: {'lr': 0.00040697653865269057, 'samples': 8451840, 'steps': 44019, 'loss/train': 1.512095332145691} 08/30/2021 21:05:01 - INFO - __main__ - Step 44021: {'lr': 0.00040697240843625527, 'samples': 8452032, 'steps': 44020, 'loss/train': 1.5614702701568604} 08/30/2021 21:05:02 - INFO - __main__ - Step 44022: {'lr': 0.00040696827814909063, 'samples': 8452224, 'steps': 44021, 'loss/train': 1.474902629852295} 08/30/2021 21:05:02 - INFO - __main__ - Step 44023: {'lr': 0.0004069641477911985, 'samples': 8452416, 'steps': 44022, 'loss/train': 1.4494317770004272} 08/30/2021 21:05:02 - INFO - __main__ - Step 44024: {'lr': 0.00040696001736258077, 'samples': 8452608, 'steps': 44023, 'loss/train': 1.4783082008361816} 08/30/2021 21:05:03 - INFO - __main__ - Step 44025: {'lr': 0.0004069558868632393, 'samples': 8452800, 'steps': 44024, 'loss/train': 1.7977288961410522} 08/30/2021 21:05:04 - INFO - __main__ - Step 44026: {'lr': 0.0004069517562931759, 'samples': 8452992, 'steps': 44025, 'loss/train': 0.8883320093154907} 08/30/2021 21:05:05 - INFO - __main__ - Step 44027: {'lr': 0.0004069476256523924, 'samples': 8453184, 'steps': 44026, 'loss/train': 1.756035327911377} 08/30/2021 21:05:05 - INFO - __main__ - Step 44028: {'lr': 0.0004069434949408908, 'samples': 8453376, 'steps': 44027, 'loss/train': 1.7327704429626465} 08/30/2021 21:05:05 - INFO - __main__ - Step 44029: {'lr': 0.0004069393641586728, 'samples': 8453568, 'steps': 44028, 'loss/train': 1.2854416370391846} 08/30/2021 21:05:06 - INFO - __main__ - Step 44030: {'lr': 0.00040693523330574043, 'samples': 8453760, 'steps': 44029, 'loss/train': 1.326966404914856} 08/30/2021 21:05:07 - INFO - __main__ - Step 44031: {'lr': 0.0004069311023820954, 'samples': 8453952, 'steps': 44030, 'loss/train': 0.4490516483783722} 08/30/2021 21:05:08 - INFO - __main__ - Step 44032: {'lr': 0.0004069269713877397, 'samples': 8454144, 'steps': 44031, 'loss/train': 1.516026258468628} 08/30/2021 21:05:08 - INFO - __main__ - Step 44033: {'lr': 0.00040692284032267515, 'samples': 8454336, 'steps': 44032, 'loss/train': 1.405348539352417} 08/30/2021 21:05:08 - INFO - __main__ - Step 44034: {'lr': 0.0004069187091869035, 'samples': 8454528, 'steps': 44033, 'loss/train': 1.6795917749404907} 08/30/2021 21:05:09 - INFO - __main__ - Step 44035: {'lr': 0.00040691457798042673, 'samples': 8454720, 'steps': 44034, 'loss/train': 1.501344084739685} 08/30/2021 21:05:10 - INFO - __main__ - Step 44036: {'lr': 0.00040691044670324673, 'samples': 8454912, 'steps': 44035, 'loss/train': 1.3635294437408447} 08/30/2021 21:05:11 - INFO - __main__ - Step 44037: {'lr': 0.00040690631535536526, 'samples': 8455104, 'steps': 44036, 'loss/train': 1.8514584302902222} 08/30/2021 21:05:11 - INFO - __main__ - Step 44038: {'lr': 0.00040690218393678426, 'samples': 8455296, 'steps': 44037, 'loss/train': 1.7052663564682007} 08/30/2021 21:05:11 - INFO - __main__ - Step 44039: {'lr': 0.0004068980524475054, 'samples': 8455488, 'steps': 44038, 'loss/train': 0.9369568824768066} 08/30/2021 21:05:12 - INFO - __main__ - Step 44040: {'lr': 0.00040689392088753097, 'samples': 8455680, 'steps': 44039, 'loss/train': 1.6158311367034912} 08/30/2021 21:05:13 - INFO - __main__ - Step 44041: {'lr': 0.00040688978925686235, 'samples': 8455872, 'steps': 44040, 'loss/train': 1.236326813697815} 08/30/2021 21:05:14 - INFO - __main__ - Step 44042: {'lr': 0.00040688565755550164, 'samples': 8456064, 'steps': 44041, 'loss/train': 1.429333209991455} 08/30/2021 21:05:14 - INFO - __main__ - Step 44043: {'lr': 0.00040688152578345074, 'samples': 8456256, 'steps': 44042, 'loss/train': 1.495693325996399} 08/30/2021 21:05:14 - INFO - __main__ - Step 44044: {'lr': 0.0004068773939407114, 'samples': 8456448, 'steps': 44043, 'loss/train': 2.3508682250976562} 08/30/2021 21:05:15 - INFO - __main__ - Step 44045: {'lr': 0.0004068732620272856, 'samples': 8456640, 'steps': 44044, 'loss/train': 1.1969764232635498} 08/30/2021 21:05:16 - INFO - __main__ - Step 44046: {'lr': 0.000406869130043175, 'samples': 8456832, 'steps': 44045, 'loss/train': 1.5663310289382935} 08/30/2021 21:05:17 - INFO - __main__ - Step 44047: {'lr': 0.0004068649979883817, 'samples': 8457024, 'steps': 44046, 'loss/train': 1.184269905090332} 08/30/2021 21:05:17 - INFO - __main__ - Step 44048: {'lr': 0.0004068608658629074, 'samples': 8457216, 'steps': 44047, 'loss/train': 1.5107033252716064} 08/30/2021 21:05:17 - INFO - __main__ - Step 44049: {'lr': 0.000406856733666754, 'samples': 8457408, 'steps': 44048, 'loss/train': 1.5339034795761108} 08/30/2021 21:05:18 - INFO - __main__ - Step 44050: {'lr': 0.00040685260139992343, 'samples': 8457600, 'steps': 44049, 'loss/train': 3.922504425048828} 08/30/2021 21:05:18 - INFO - __main__ - Step 44051: {'lr': 0.00040684846906241745, 'samples': 8457792, 'steps': 44050, 'loss/train': 1.319611668586731} 08/30/2021 21:05:20 - INFO - __main__ - Step 44052: {'lr': 0.000406844336654238, 'samples': 8457984, 'steps': 44051, 'loss/train': 1.6890438795089722} 08/30/2021 21:05:20 - INFO - __main__ - Step 44053: {'lr': 0.00040684020417538694, 'samples': 8458176, 'steps': 44052, 'loss/train': 1.6068098545074463} 08/30/2021 21:05:20 - INFO - __main__ - Step 44054: {'lr': 0.00040683607162586604, 'samples': 8458368, 'steps': 44053, 'loss/train': 1.1027469635009766} 08/30/2021 21:05:21 - INFO - __main__ - Step 44055: {'lr': 0.00040683193900567727, 'samples': 8458560, 'steps': 44054, 'loss/train': 1.6322596073150635} 08/30/2021 21:05:21 - INFO - __main__ - Step 44056: {'lr': 0.00040682780631482243, 'samples': 8458752, 'steps': 44055, 'loss/train': 1.3942008018493652} 08/30/2021 21:05:23 - INFO - __main__ - Step 44057: {'lr': 0.0004068236735533034, 'samples': 8458944, 'steps': 44056, 'loss/train': 1.5049303770065308} 08/30/2021 21:05:23 - INFO - __main__ - Step 44058: {'lr': 0.00040681954072112206, 'samples': 8459136, 'steps': 44057, 'loss/train': 1.6280584335327148} 08/30/2021 21:05:24 - INFO - __main__ - Step 44059: {'lr': 0.0004068154078182802, 'samples': 8459328, 'steps': 44058, 'loss/train': 1.3362181186676025} 08/30/2021 21:05:24 - INFO - __main__ - Step 44060: {'lr': 0.00040681127484477983, 'samples': 8459520, 'steps': 44059, 'loss/train': 1.1541709899902344} 08/30/2021 21:05:24 - INFO - __main__ - Step 44061: {'lr': 0.0004068071418006226, 'samples': 8459712, 'steps': 44060, 'loss/train': 0.5931140780448914} 08/30/2021 21:05:25 - INFO - __main__ - Step 44062: {'lr': 0.0004068030086858106, 'samples': 8459904, 'steps': 44061, 'loss/train': 0.5837137699127197} 08/30/2021 21:05:27 - INFO - __main__ - Step 44063: {'lr': 0.00040679887550034555, 'samples': 8460096, 'steps': 44062, 'loss/train': 1.3376882076263428} 08/30/2021 21:05:27 - INFO - __main__ - Step 44064: {'lr': 0.0004067947422442293, 'samples': 8460288, 'steps': 44063, 'loss/train': 0.8842340707778931} 08/30/2021 21:05:28 - INFO - __main__ - Step 44065: {'lr': 0.00040679060891746384, 'samples': 8460480, 'steps': 44064, 'loss/train': 1.1304583549499512} 08/30/2021 21:05:28 - INFO - __main__ - Step 44066: {'lr': 0.00040678647552005087, 'samples': 8460672, 'steps': 44065, 'loss/train': 1.2364016771316528} 08/30/2021 21:05:28 - INFO - __main__ - Step 44067: {'lr': 0.00040678234205199237, 'samples': 8460864, 'steps': 44066, 'loss/train': 1.329094409942627} 08/30/2021 21:05:30 - INFO - __main__ - Step 44068: {'lr': 0.0004067782085132902, 'samples': 8461056, 'steps': 44067, 'loss/train': 1.4064669609069824} 08/30/2021 21:05:30 - INFO - __main__ - Step 44069: {'lr': 0.00040677407490394616, 'samples': 8461248, 'steps': 44068, 'loss/train': 1.4992949962615967} 08/30/2021 21:05:31 - INFO - __main__ - Step 44070: {'lr': 0.0004067699412239622, 'samples': 8461440, 'steps': 44069, 'loss/train': 1.8124302625656128} 08/30/2021 21:05:31 - INFO - __main__ - Step 44071: {'lr': 0.00040676580747334, 'samples': 8461632, 'steps': 44070, 'loss/train': 1.4818695783615112} 08/30/2021 21:05:31 - INFO - __main__ - Step 44072: {'lr': 0.0004067616736520816, 'samples': 8461824, 'steps': 44071, 'loss/train': 1.3591928482055664} 08/30/2021 21:05:33 - INFO - __main__ - Step 44073: {'lr': 0.0004067575397601888, 'samples': 8462016, 'steps': 44072, 'loss/train': 1.4126721620559692} 08/30/2021 21:05:33 - INFO - __main__ - Step 44074: {'lr': 0.0004067534057976635, 'samples': 8462208, 'steps': 44073, 'loss/train': 1.7215222120285034} 08/30/2021 21:05:34 - INFO - __main__ - Step 44075: {'lr': 0.0004067492717645075, 'samples': 8462400, 'steps': 44074, 'loss/train': 1.1917779445648193} 08/30/2021 21:05:34 - INFO - __main__ - Step 44076: {'lr': 0.00040674513766072274, 'samples': 8462592, 'steps': 44075, 'loss/train': 1.491504192352295} 08/30/2021 21:05:34 - INFO - __main__ - Step 44077: {'lr': 0.000406741003486311, 'samples': 8462784, 'steps': 44076, 'loss/train': 1.7367831468582153} 08/30/2021 21:05:36 - INFO - __main__ - Step 44078: {'lr': 0.00040673686924127416, 'samples': 8462976, 'steps': 44077, 'loss/train': 1.3610408306121826} 08/30/2021 21:05:36 - INFO - __main__ - Step 44079: {'lr': 0.0004067327349256142, 'samples': 8463168, 'steps': 44078, 'loss/train': 1.1683216094970703} 08/30/2021 21:05:37 - INFO - __main__ - Step 44080: {'lr': 0.00040672860053933286, 'samples': 8463360, 'steps': 44079, 'loss/train': 1.4513936042785645} 08/30/2021 21:05:37 - INFO - __main__ - Step 44081: {'lr': 0.00040672446608243194, 'samples': 8463552, 'steps': 44080, 'loss/train': 1.4032937288284302} 08/30/2021 21:05:37 - INFO - __main__ - Step 44082: {'lr': 0.0004067203315549135, 'samples': 8463744, 'steps': 44081, 'loss/train': 1.293398141860962} 08/30/2021 21:05:39 - INFO - __main__ - Step 44083: {'lr': 0.00040671619695677923, 'samples': 8463936, 'steps': 44082, 'loss/train': 0.9986708760261536} 08/30/2021 21:05:39 - INFO - __main__ - Step 44084: {'lr': 0.00040671206228803117, 'samples': 8464128, 'steps': 44083, 'loss/train': 1.7144861221313477} 08/30/2021 21:05:40 - INFO - __main__ - Step 44085: {'lr': 0.0004067079275486709, 'samples': 8464320, 'steps': 44084, 'loss/train': 1.4291151762008667} 08/30/2021 21:05:40 - INFO - __main__ - Step 44086: {'lr': 0.00040670379273870054, 'samples': 8464512, 'steps': 44085, 'loss/train': 1.1487314701080322} 08/30/2021 21:05:40 - INFO - __main__ - Step 44087: {'lr': 0.00040669965785812193, 'samples': 8464704, 'steps': 44086, 'loss/train': 1.2978435754776} 08/30/2021 21:05:42 - INFO - __main__ - Step 44088: {'lr': 0.00040669552290693677, 'samples': 8464896, 'steps': 44087, 'loss/train': 1.4583364725112915} 08/30/2021 21:05:42 - INFO - __main__ - Step 44089: {'lr': 0.0004066913878851471, 'samples': 8465088, 'steps': 44088, 'loss/train': 1.3761975765228271} 08/30/2021 21:05:43 - INFO - __main__ - Step 44090: {'lr': 0.00040668725279275464, 'samples': 8465280, 'steps': 44089, 'loss/train': 1.0192394256591797} 08/30/2021 21:05:43 - INFO - __main__ - Step 44091: {'lr': 0.0004066831176297614, 'samples': 8465472, 'steps': 44090, 'loss/train': 2.068331241607666} 08/30/2021 21:05:43 - INFO - __main__ - Step 44092: {'lr': 0.0004066789823961691, 'samples': 8465664, 'steps': 44091, 'loss/train': 1.458799958229065} 08/30/2021 21:05:44 - INFO - __main__ - Step 44093: {'lr': 0.00040667484709197967, 'samples': 8465856, 'steps': 44092, 'loss/train': 1.0155807733535767} 08/30/2021 21:05:45 - INFO - __main__ - Step 44094: {'lr': 0.00040667071171719503, 'samples': 8466048, 'steps': 44093, 'loss/train': 1.2309426069259644} 08/30/2021 21:05:46 - INFO - __main__ - Step 44095: {'lr': 0.00040666657627181697, 'samples': 8466240, 'steps': 44094, 'loss/train': 1.088587760925293} 08/30/2021 21:05:46 - INFO - __main__ - Step 44096: {'lr': 0.00040666244075584736, 'samples': 8466432, 'steps': 44095, 'loss/train': 1.5288745164871216} 08/30/2021 21:05:46 - INFO - __main__ - Step 44097: {'lr': 0.000406658305169288, 'samples': 8466624, 'steps': 44096, 'loss/train': 1.044421911239624} 08/30/2021 21:05:47 - INFO - __main__ - Step 44098: {'lr': 0.000406654169512141, 'samples': 8466816, 'steps': 44097, 'loss/train': 1.3983596563339233} 08/30/2021 21:05:48 - INFO - __main__ - Step 44099: {'lr': 0.0004066500337844078, 'samples': 8467008, 'steps': 44098, 'loss/train': 1.4583714008331299} 08/30/2021 21:05:49 - INFO - __main__ - Step 44100: {'lr': 0.0004066458979860907, 'samples': 8467200, 'steps': 44099, 'loss/train': 1.4323664903640747} 08/30/2021 21:05:49 - INFO - __main__ - Step 44101: {'lr': 0.00040664176211719136, 'samples': 8467392, 'steps': 44100, 'loss/train': 0.8173502683639526} 08/30/2021 21:05:50 - INFO - __main__ - Step 44102: {'lr': 0.00040663762617771163, 'samples': 8467584, 'steps': 44101, 'loss/train': 0.12298928946256638} 08/30/2021 21:05:50 - INFO - __main__ - Step 44103: {'lr': 0.00040663349016765337, 'samples': 8467776, 'steps': 44102, 'loss/train': 1.1373111009597778} 08/30/2021 21:05:52 - INFO - __main__ - Step 44104: {'lr': 0.00040662935408701853, 'samples': 8467968, 'steps': 44103, 'loss/train': 1.406807780265808} 08/30/2021 21:05:52 - INFO - __main__ - Step 44105: {'lr': 0.00040662521793580886, 'samples': 8468160, 'steps': 44104, 'loss/train': 1.4186218976974487} 08/30/2021 21:05:53 - INFO - __main__ - Step 44106: {'lr': 0.0004066210817140263, 'samples': 8468352, 'steps': 44105, 'loss/train': 1.270269513130188} 08/30/2021 21:05:53 - INFO - __main__ - Step 44107: {'lr': 0.0004066169454216727, 'samples': 8468544, 'steps': 44106, 'loss/train': 0.07096153497695923} 08/30/2021 21:05:53 - INFO - __main__ - Step 44108: {'lr': 0.00040661280905875, 'samples': 8468736, 'steps': 44107, 'loss/train': 1.267858624458313} 08/30/2021 21:05:54 - INFO - __main__ - Step 44109: {'lr': 0.0004066086726252599, 'samples': 8468928, 'steps': 44108, 'loss/train': 1.168114423751831} 08/30/2021 21:05:55 - INFO - __main__ - Step 44110: {'lr': 0.0004066045361212043, 'samples': 8469120, 'steps': 44109, 'loss/train': 1.3575265407562256} 08/30/2021 21:05:56 - INFO - __main__ - Step 44111: {'lr': 0.00040660039954658523, 'samples': 8469312, 'steps': 44110, 'loss/train': 1.1176503896713257} 08/30/2021 21:05:56 - INFO - __main__ - Step 44112: {'lr': 0.0004065962629014044, 'samples': 8469504, 'steps': 44111, 'loss/train': 1.4290441274642944} 08/30/2021 21:05:56 - INFO - __main__ - Step 44113: {'lr': 0.00040659212618566364, 'samples': 8469696, 'steps': 44112, 'loss/train': 0.9308264851570129} 08/30/2021 21:05:57 - INFO - __main__ - Step 44114: {'lr': 0.000406587989399365, 'samples': 8469888, 'steps': 44113, 'loss/train': 1.6912705898284912} 08/30/2021 21:05:57 - INFO - __main__ - Step 44115: {'lr': 0.0004065838525425102, 'samples': 8470080, 'steps': 44114, 'loss/train': 1.562868595123291} 08/30/2021 21:05:59 - INFO - __main__ - Step 44116: {'lr': 0.00040657971561510104, 'samples': 8470272, 'steps': 44115, 'loss/train': 1.3296985626220703} 08/30/2021 21:05:59 - INFO - __main__ - Step 44117: {'lr': 0.00040657557861713956, 'samples': 8470464, 'steps': 44116, 'loss/train': 0.8412728905677795} 08/30/2021 21:06:00 - INFO - __main__ - Step 44118: {'lr': 0.00040657144154862746, 'samples': 8470656, 'steps': 44117, 'loss/train': 1.5692476034164429} 08/30/2021 21:06:00 - INFO - __main__ - Step 44119: {'lr': 0.00040656730440956677, 'samples': 8470848, 'steps': 44118, 'loss/train': 1.500753402709961} 08/30/2021 21:06:00 - INFO - __main__ - Step 44120: {'lr': 0.0004065631671999592, 'samples': 8471040, 'steps': 44119, 'loss/train': 1.0208393335342407} 08/30/2021 21:06:02 - INFO - __main__ - Step 44121: {'lr': 0.0004065590299198068, 'samples': 8471232, 'steps': 44120, 'loss/train': 0.2500440776348114} 08/30/2021 21:06:02 - INFO - __main__ - Step 44122: {'lr': 0.00040655489256911123, 'samples': 8471424, 'steps': 44121, 'loss/train': 1.3094968795776367} 08/30/2021 21:06:03 - INFO - __main__ - Step 44123: {'lr': 0.00040655075514787445, 'samples': 8471616, 'steps': 44122, 'loss/train': 1.3478151559829712} 08/30/2021 21:06:03 - INFO - __main__ - Step 44124: {'lr': 0.0004065466176560983, 'samples': 8471808, 'steps': 44123, 'loss/train': 1.3414958715438843} 08/30/2021 21:06:03 - INFO - __main__ - Step 44125: {'lr': 0.0004065424800937847, 'samples': 8472000, 'steps': 44124, 'loss/train': 1.5347563028335571} 08/30/2021 21:06:05 - INFO - __main__ - Step 44126: {'lr': 0.0004065383424609354, 'samples': 8472192, 'steps': 44125, 'loss/train': 0.9165471196174622} 08/30/2021 21:06:05 - INFO - __main__ - Step 44127: {'lr': 0.00040653420475755245, 'samples': 8472384, 'steps': 44126, 'loss/train': 1.5624030828475952} 08/30/2021 21:06:06 - INFO - __main__ - Step 44128: {'lr': 0.0004065300669836375, 'samples': 8472576, 'steps': 44127, 'loss/train': 1.4960596561431885} 08/30/2021 21:06:06 - INFO - __main__ - Step 44129: {'lr': 0.0004065259291391926, 'samples': 8472768, 'steps': 44128, 'loss/train': 1.1617436408996582} 08/30/2021 21:06:06 - INFO - __main__ - Step 44130: {'lr': 0.0004065217912242195, 'samples': 8472960, 'steps': 44129, 'loss/train': 1.5795999765396118} 08/30/2021 21:06:08 - INFO - __main__ - Step 44131: {'lr': 0.00040651765323872, 'samples': 8473152, 'steps': 44130, 'loss/train': 1.4055019617080688} 08/30/2021 21:06:08 - INFO - __main__ - Step 44132: {'lr': 0.0004065135151826962, 'samples': 8473344, 'steps': 44131, 'loss/train': 1.4845198392868042} 08/30/2021 21:06:09 - INFO - __main__ - Step 44133: {'lr': 0.00040650937705614975, 'samples': 8473536, 'steps': 44132, 'loss/train': 1.2122938632965088} 08/30/2021 21:06:09 - INFO - __main__ - Step 44134: {'lr': 0.0004065052388590826, 'samples': 8473728, 'steps': 44133, 'loss/train': 1.4062912464141846} 08/30/2021 21:06:09 - INFO - __main__ - Step 44135: {'lr': 0.00040650110059149664, 'samples': 8473920, 'steps': 44134, 'loss/train': 1.6718124151229858} 08/30/2021 21:06:11 - INFO - __main__ - Step 44136: {'lr': 0.0004064969622533937, 'samples': 8474112, 'steps': 44135, 'loss/train': 1.1252530813217163} 08/30/2021 21:06:11 - INFO - __main__ - Step 44137: {'lr': 0.0004064928238447756, 'samples': 8474304, 'steps': 44136, 'loss/train': 0.7014845013618469} 08/30/2021 21:06:12 - INFO - __main__ - Step 44138: {'lr': 0.00040648868536564427, 'samples': 8474496, 'steps': 44137, 'loss/train': 1.4529163837432861} 08/30/2021 21:06:12 - INFO - __main__ - Step 44139: {'lr': 0.00040648454681600153, 'samples': 8474688, 'steps': 44138, 'loss/train': 1.6480276584625244} 08/30/2021 21:06:12 - INFO - __main__ - Step 44140: {'lr': 0.0004064804081958493, 'samples': 8474880, 'steps': 44139, 'loss/train': 1.2589802742004395} 08/30/2021 21:06:14 - INFO - __main__ - Step 44141: {'lr': 0.00040647626950518945, 'samples': 8475072, 'steps': 44140, 'loss/train': 1.8385587930679321} 08/30/2021 21:06:14 - INFO - __main__ - Step 44142: {'lr': 0.00040647213074402374, 'samples': 8475264, 'steps': 44141, 'loss/train': 1.5320193767547607} 08/30/2021 21:06:15 - INFO - __main__ - Step 44143: {'lr': 0.0004064679919123541, 'samples': 8475456, 'steps': 44142, 'loss/train': 1.4705506563186646} 08/30/2021 21:06:15 - INFO - __main__ - Step 44144: {'lr': 0.00040646385301018243, 'samples': 8475648, 'steps': 44143, 'loss/train': 1.7159574031829834} 08/30/2021 21:06:15 - INFO - __main__ - Step 44145: {'lr': 0.0004064597140375105, 'samples': 8475840, 'steps': 44144, 'loss/train': 1.5686514377593994} 08/30/2021 21:06:17 - INFO - __main__ - Step 44146: {'lr': 0.00040645557499434035, 'samples': 8476032, 'steps': 44145, 'loss/train': 1.5966949462890625} 08/30/2021 21:06:17 - INFO - __main__ - Step 44147: {'lr': 0.0004064514358806737, 'samples': 8476224, 'steps': 44146, 'loss/train': 1.3904095888137817} 08/30/2021 21:06:18 - INFO - __main__ - Step 44148: {'lr': 0.00040644729669651235, 'samples': 8476416, 'steps': 44147, 'loss/train': 1.3803188800811768} 08/30/2021 21:06:18 - INFO - __main__ - Step 44149: {'lr': 0.0004064431574418583, 'samples': 8476608, 'steps': 44148, 'loss/train': 1.4059433937072754} 08/30/2021 21:06:18 - INFO - __main__ - Step 44150: {'lr': 0.00040643901811671345, 'samples': 8476800, 'steps': 44149, 'loss/train': 1.6222126483917236} 08/30/2021 21:06:20 - INFO - __main__ - Step 44151: {'lr': 0.0004064348787210795, 'samples': 8476992, 'steps': 44150, 'loss/train': 1.2151063680648804} 08/30/2021 21:06:20 - INFO - __main__ - Step 44152: {'lr': 0.0004064307392549585, 'samples': 8477184, 'steps': 44151, 'loss/train': 1.2867988348007202} 08/30/2021 21:06:20 - INFO - __main__ - Step 44153: {'lr': 0.00040642659971835217, 'samples': 8477376, 'steps': 44152, 'loss/train': 0.3661315441131592} 08/30/2021 21:06:21 - INFO - __main__ - Step 44154: {'lr': 0.0004064224601112625, 'samples': 8477568, 'steps': 44153, 'loss/train': 1.40620756149292} 08/30/2021 21:06:21 - INFO - __main__ - Step 44155: {'lr': 0.0004064183204336912, 'samples': 8477760, 'steps': 44154, 'loss/train': 1.3225756883621216} 08/30/2021 21:06:23 - INFO - __main__ - Step 44156: {'lr': 0.00040641418068564024, 'samples': 8477952, 'steps': 44155, 'loss/train': 0.6734851598739624} 08/30/2021 21:06:23 - INFO - __main__ - Step 44157: {'lr': 0.0004064100408671114, 'samples': 8478144, 'steps': 44156, 'loss/train': 1.5098363161087036} 08/30/2021 21:06:23 - INFO - __main__ - Step 44158: {'lr': 0.0004064059009781067, 'samples': 8478336, 'steps': 44157, 'loss/train': 1.511729121208191} 08/30/2021 21:06:24 - INFO - __main__ - Step 44159: {'lr': 0.0004064017610186279, 'samples': 8478528, 'steps': 44158, 'loss/train': 1.451151967048645} 08/30/2021 21:06:24 - INFO - __main__ - Step 44160: {'lr': 0.00040639762098867684, 'samples': 8478720, 'steps': 44159, 'loss/train': 0.9728785753250122} 08/30/2021 21:06:26 - INFO - __main__ - Step 44161: {'lr': 0.0004063934808882555, 'samples': 8478912, 'steps': 44160, 'loss/train': 1.5216493606567383} 08/30/2021 21:06:26 - INFO - __main__ - Step 44162: {'lr': 0.0004063893407173656, 'samples': 8479104, 'steps': 44161, 'loss/train': 1.3516279458999634} 08/30/2021 21:06:27 - INFO - __main__ - Step 44163: {'lr': 0.00040638520047600916, 'samples': 8479296, 'steps': 44162, 'loss/train': 1.7257524728775024} 08/30/2021 21:06:27 - INFO - __main__ - Step 44164: {'lr': 0.00040638106016418785, 'samples': 8479488, 'steps': 44163, 'loss/train': 1.6789913177490234} 08/30/2021 21:06:27 - INFO - __main__ - Step 44165: {'lr': 0.0004063769197819037, 'samples': 8479680, 'steps': 44164, 'loss/train': 1.4162310361862183} 08/30/2021 21:06:28 - INFO - __main__ - Step 44166: {'lr': 0.0004063727793291585, 'samples': 8479872, 'steps': 44165, 'loss/train': 1.1711804866790771} 08/30/2021 21:06:29 - INFO - __main__ - Step 44167: {'lr': 0.00040636863880595415, 'samples': 8480064, 'steps': 44166, 'loss/train': 1.2680935859680176} 08/30/2021 21:06:30 - INFO - __main__ - Step 44168: {'lr': 0.0004063644982122926, 'samples': 8480256, 'steps': 44167, 'loss/train': 1.6841156482696533} 08/30/2021 21:06:30 - INFO - __main__ - Step 44169: {'lr': 0.00040636035754817545, 'samples': 8480448, 'steps': 44168, 'loss/train': 1.058955430984497} 08/30/2021 21:06:30 - INFO - __main__ - Step 44170: {'lr': 0.00040635621681360485, 'samples': 8480640, 'steps': 44169, 'loss/train': 1.4076007604599} 08/30/2021 21:06:31 - INFO - __main__ - Step 44171: {'lr': 0.00040635207600858247, 'samples': 8480832, 'steps': 44170, 'loss/train': 0.6762776374816895} 08/30/2021 21:06:33 - INFO - __main__ - Step 44172: {'lr': 0.00040634793513311037, 'samples': 8481024, 'steps': 44171, 'loss/train': 0.8838333487510681} 08/30/2021 21:06:33 - INFO - __main__ - Step 44173: {'lr': 0.0004063437941871903, 'samples': 8481216, 'steps': 44172, 'loss/train': 1.3215932846069336} 08/30/2021 21:06:33 - INFO - __main__ - Step 44174: {'lr': 0.000406339653170824, 'samples': 8481408, 'steps': 44173, 'loss/train': 1.5783798694610596} 08/30/2021 21:06:34 - INFO - __main__ - Step 44175: {'lr': 0.00040633551208401356, 'samples': 8481600, 'steps': 44174, 'loss/train': 1.1169246435165405} 08/30/2021 21:06:34 - INFO - __main__ - Step 44176: {'lr': 0.0004063313709267607, 'samples': 8481792, 'steps': 44175, 'loss/train': 1.2964143753051758} 08/30/2021 21:06:36 - INFO - __main__ - Step 44177: {'lr': 0.0004063272296990674, 'samples': 8481984, 'steps': 44176, 'loss/train': 1.526625394821167} 08/30/2021 21:06:36 - INFO - __main__ - Step 44178: {'lr': 0.00040632308840093533, 'samples': 8482176, 'steps': 44177, 'loss/train': 0.9614483714103699} 08/30/2021 21:06:36 - INFO - __main__ - Step 44179: {'lr': 0.0004063189470323666, 'samples': 8482368, 'steps': 44178, 'loss/train': 0.8579971790313721} 08/30/2021 21:06:37 - INFO - __main__ - Step 44180: {'lr': 0.000406314805593363, 'samples': 8482560, 'steps': 44179, 'loss/train': 1.4750815629959106} 08/30/2021 21:06:37 - INFO - __main__ - Step 44181: {'lr': 0.00040631066408392636, 'samples': 8482752, 'steps': 44180, 'loss/train': 0.8314672112464905} 08/30/2021 21:06:39 - INFO - __main__ - Step 44182: {'lr': 0.0004063065225040584, 'samples': 8482944, 'steps': 44181, 'loss/train': 1.0320812463760376} 08/30/2021 21:06:39 - INFO - __main__ - Step 44183: {'lr': 0.0004063023808537613, 'samples': 8483136, 'steps': 44182, 'loss/train': 1.485159993171692} 08/30/2021 21:06:40 - INFO - __main__ - Step 44184: {'lr': 0.00040629823913303665, 'samples': 8483328, 'steps': 44183, 'loss/train': 1.607389211654663} 08/30/2021 21:06:40 - INFO - __main__ - Step 44185: {'lr': 0.0004062940973418865, 'samples': 8483520, 'steps': 44184, 'loss/train': 2.7643890380859375} 08/30/2021 21:06:40 - INFO - __main__ - Step 44186: {'lr': 0.00040628995548031254, 'samples': 8483712, 'steps': 44185, 'loss/train': 1.3176820278167725} 08/30/2021 21:06:41 - INFO - __main__ - Step 44187: {'lr': 0.00040628581354831687, 'samples': 8483904, 'steps': 44186, 'loss/train': 1.4538748264312744} 08/30/2021 21:06:42 - INFO - __main__ - Step 44188: {'lr': 0.0004062816715459011, 'samples': 8484096, 'steps': 44187, 'loss/train': 1.4020036458969116} 08/30/2021 21:06:43 - INFO - __main__ - Step 44189: {'lr': 0.0004062775294730673, 'samples': 8484288, 'steps': 44188, 'loss/train': 1.2786281108856201} 08/30/2021 21:06:43 - INFO - __main__ - Step 44190: {'lr': 0.0004062733873298172, 'samples': 8484480, 'steps': 44189, 'loss/train': 1.6497596502304077} 08/30/2021 21:06:43 - INFO - __main__ - Step 44191: {'lr': 0.0004062692451161528, 'samples': 8484672, 'steps': 44190, 'loss/train': 1.0401939153671265} 08/30/2021 21:06:44 - INFO - __main__ - Step 44192: {'lr': 0.00040626510283207586, 'samples': 8484864, 'steps': 44191, 'loss/train': 1.780696988105774} 08/30/2021 21:06:45 - INFO - __main__ - Step 44193: {'lr': 0.00040626096047758823, 'samples': 8485056, 'steps': 44192, 'loss/train': 1.407740592956543} 08/30/2021 21:06:46 - INFO - __main__ - Step 44194: {'lr': 0.0004062568180526919, 'samples': 8485248, 'steps': 44193, 'loss/train': 0.06727295368909836} 08/30/2021 21:06:46 - INFO - __main__ - Step 44195: {'lr': 0.0004062526755573886, 'samples': 8485440, 'steps': 44194, 'loss/train': 1.4399356842041016} 08/30/2021 21:06:47 - INFO - __main__ - Step 44196: {'lr': 0.00040624853299168025, 'samples': 8485632, 'steps': 44195, 'loss/train': 1.7573808431625366} 08/30/2021 21:06:47 - INFO - __main__ - Step 44197: {'lr': 0.0004062443903555687, 'samples': 8485824, 'steps': 44196, 'loss/train': 1.3407443761825562} 08/30/2021 21:06:49 - INFO - __main__ - Step 44198: {'lr': 0.0004062402476490559, 'samples': 8486016, 'steps': 44197, 'loss/train': 1.9403477907180786} 08/30/2021 21:06:49 - INFO - __main__ - Step 44199: {'lr': 0.00040623610487214366, 'samples': 8486208, 'steps': 44198, 'loss/train': 0.8868473172187805} 08/30/2021 21:06:49 - INFO - __main__ - Step 44200: {'lr': 0.0004062319620248338, 'samples': 8486400, 'steps': 44199, 'loss/train': 1.279229760169983} 08/30/2021 21:06:50 - INFO - __main__ - Step 44201: {'lr': 0.00040622781910712826, 'samples': 8486592, 'steps': 44200, 'loss/train': 1.4272246360778809} 08/30/2021 21:06:50 - INFO - __main__ - Step 44202: {'lr': 0.00040622367611902886, 'samples': 8486784, 'steps': 44201, 'loss/train': 1.5270839929580688} 08/30/2021 21:06:51 - INFO - __main__ - Step 44203: {'lr': 0.0004062195330605375, 'samples': 8486976, 'steps': 44202, 'loss/train': 1.258521318435669} 08/30/2021 21:06:52 - INFO - __main__ - Step 44204: {'lr': 0.000406215389931656, 'samples': 8487168, 'steps': 44203, 'loss/train': 1.3526769876480103} 08/30/2021 21:06:52 - INFO - __main__ - Step 44205: {'lr': 0.0004062112467323863, 'samples': 8487360, 'steps': 44204, 'loss/train': 1.6489837169647217} 08/30/2021 21:06:53 - INFO - __main__ - Step 44206: {'lr': 0.00040620710346273015, 'samples': 8487552, 'steps': 44205, 'loss/train': 1.5647201538085938} 08/30/2021 21:06:53 - INFO - __main__ - Step 44207: {'lr': 0.00040620296012268956, 'samples': 8487744, 'steps': 44206, 'loss/train': 1.396378993988037} 08/30/2021 21:06:54 - INFO - __main__ - Step 44208: {'lr': 0.0004061988167122663, 'samples': 8487936, 'steps': 44207, 'loss/train': 1.0479145050048828} 08/30/2021 21:06:55 - INFO - __main__ - Step 44209: {'lr': 0.00040619467323146224, 'samples': 8488128, 'steps': 44208, 'loss/train': 1.0903661251068115} 08/30/2021 21:06:55 - INFO - __main__ - Step 44210: {'lr': 0.0004061905296802793, 'samples': 8488320, 'steps': 44209, 'loss/train': 1.6131728887557983} 08/30/2021 21:06:55 - INFO - __main__ - Step 44211: {'lr': 0.00040618638605871934, 'samples': 8488512, 'steps': 44210, 'loss/train': 1.4721304178237915} 08/30/2021 21:06:56 - INFO - __main__ - Step 44212: {'lr': 0.00040618224236678413, 'samples': 8488704, 'steps': 44211, 'loss/train': 1.6304879188537598} 08/30/2021 21:06:57 - INFO - __main__ - Step 44213: {'lr': 0.00040617809860447564, 'samples': 8488896, 'steps': 44212, 'loss/train': 0.9545351266860962} 08/30/2021 21:06:58 - INFO - __main__ - Step 44214: {'lr': 0.00040617395477179577, 'samples': 8489088, 'steps': 44213, 'loss/train': 1.9828261137008667} 08/30/2021 21:06:58 - INFO - __main__ - Step 44215: {'lr': 0.0004061698108687463, 'samples': 8489280, 'steps': 44214, 'loss/train': 1.167463779449463} 08/30/2021 21:06:59 - INFO - __main__ - Step 44216: {'lr': 0.00040616566689532905, 'samples': 8489472, 'steps': 44215, 'loss/train': 1.4615789651870728} 08/30/2021 21:06:59 - INFO - __main__ - Step 44217: {'lr': 0.00040616152285154607, 'samples': 8489664, 'steps': 44216, 'loss/train': 0.8346847295761108} 08/30/2021 21:07:00 - INFO - __main__ - Step 44218: {'lr': 0.000406157378737399, 'samples': 8489856, 'steps': 44217, 'loss/train': 0.7510921359062195} 08/30/2021 21:07:01 - INFO - __main__ - Step 44219: {'lr': 0.0004061532345528899, 'samples': 8490048, 'steps': 44218, 'loss/train': 1.3765695095062256} 08/30/2021 21:07:01 - INFO - __main__ - Step 44220: {'lr': 0.00040614909029802054, 'samples': 8490240, 'steps': 44219, 'loss/train': 0.6475852727890015} 08/30/2021 21:07:02 - INFO - __main__ - Step 44221: {'lr': 0.0004061449459727928, 'samples': 8490432, 'steps': 44220, 'loss/train': 1.4275166988372803} 08/30/2021 21:07:02 - INFO - __main__ - Step 44222: {'lr': 0.0004061408015772086, 'samples': 8490624, 'steps': 44221, 'loss/train': 1.222055196762085} 08/30/2021 21:07:02 - INFO - __main__ - Step 44223: {'lr': 0.0004061366571112698, 'samples': 8490816, 'steps': 44222, 'loss/train': 1.6360888481140137} 08/30/2021 21:07:04 - INFO - __main__ - Step 44224: {'lr': 0.0004061325125749781, 'samples': 8491008, 'steps': 44223, 'loss/train': 1.2136449813842773} 08/30/2021 21:07:05 - INFO - __main__ - Step 44225: {'lr': 0.00040612836796833556, 'samples': 8491200, 'steps': 44224, 'loss/train': 1.289175033569336} 08/30/2021 21:07:05 - INFO - __main__ - Step 44226: {'lr': 0.000406124223291344, 'samples': 8491392, 'steps': 44225, 'loss/train': 1.1006243228912354} 08/30/2021 21:07:06 - INFO - __main__ - Step 44227: {'lr': 0.0004061200785440052, 'samples': 8491584, 'steps': 44226, 'loss/train': 1.8398195505142212} 08/30/2021 21:07:06 - INFO - __main__ - Step 44228: {'lr': 0.0004061159337263213, 'samples': 8491776, 'steps': 44227, 'loss/train': 1.19362211227417} 08/30/2021 21:07:07 - INFO - __main__ - Step 44229: {'lr': 0.0004061117888382938, 'samples': 8491968, 'steps': 44228, 'loss/train': 1.4343485832214355} 08/30/2021 21:07:08 - INFO - __main__ - Step 44230: {'lr': 0.00040610764387992475, 'samples': 8492160, 'steps': 44229, 'loss/train': 1.6166287660598755} 08/30/2021 21:07:08 - INFO - __main__ - Step 44231: {'lr': 0.0004061034988512161, 'samples': 8492352, 'steps': 44230, 'loss/train': 1.3016630411148071} 08/30/2021 21:07:09 - INFO - __main__ - Step 44232: {'lr': 0.0004060993537521695, 'samples': 8492544, 'steps': 44231, 'loss/train': 1.1095161437988281} 08/30/2021 21:07:09 - INFO - __main__ - Step 44233: {'lr': 0.00040609520858278704, 'samples': 8492736, 'steps': 44232, 'loss/train': 1.3086873292922974} 08/30/2021 21:07:10 - INFO - __main__ - Step 44234: {'lr': 0.0004060910633430704, 'samples': 8492928, 'steps': 44233, 'loss/train': 1.9117945432662964} 08/30/2021 21:07:11 - INFO - __main__ - Step 44235: {'lr': 0.0004060869180330216, 'samples': 8493120, 'steps': 44234, 'loss/train': 1.2222625017166138} 08/30/2021 21:07:11 - INFO - __main__ - Step 44236: {'lr': 0.00040608277265264243, 'samples': 8493312, 'steps': 44235, 'loss/train': 1.3907073736190796} 08/30/2021 21:07:12 - INFO - __main__ - Step 44237: {'lr': 0.0004060786272019348, 'samples': 8493504, 'steps': 44236, 'loss/train': 1.9474618434906006} 08/30/2021 21:07:12 - INFO - __main__ - Step 44238: {'lr': 0.00040607448168090044, 'samples': 8493696, 'steps': 44237, 'loss/train': 1.4182382822036743} 08/30/2021 21:07:14 - INFO - __main__ - Step 44239: {'lr': 0.00040607033608954136, 'samples': 8493888, 'steps': 44238, 'loss/train': 0.38596755266189575} 08/30/2021 21:07:14 - INFO - __main__ - Step 44240: {'lr': 0.0004060661904278595, 'samples': 8494080, 'steps': 44239, 'loss/train': 1.5403029918670654} 08/30/2021 21:07:14 - INFO - __main__ - Step 44241: {'lr': 0.0004060620446958565, 'samples': 8494272, 'steps': 44240, 'loss/train': 1.410273790359497} 08/30/2021 21:07:15 - INFO - __main__ - Step 44242: {'lr': 0.00040605789889353445, 'samples': 8494464, 'steps': 44241, 'loss/train': 1.7102348804473877} 08/30/2021 21:07:15 - INFO - __main__ - Step 44243: {'lr': 0.00040605375302089507, 'samples': 8494656, 'steps': 44242, 'loss/train': 1.4443905353546143} 08/30/2021 21:07:16 - INFO - __main__ - Step 44244: {'lr': 0.00040604960707794023, 'samples': 8494848, 'steps': 44243, 'loss/train': 1.3313616514205933} 08/30/2021 21:07:17 - INFO - __main__ - Step 44245: {'lr': 0.00040604546106467196, 'samples': 8495040, 'steps': 44244, 'loss/train': 1.096571445465088} 08/30/2021 21:07:17 - INFO - __main__ - Step 44246: {'lr': 0.00040604131498109193, 'samples': 8495232, 'steps': 44245, 'loss/train': 1.005394458770752} 08/30/2021 21:07:18 - INFO - __main__ - Step 44247: {'lr': 0.0004060371688272021, 'samples': 8495424, 'steps': 44246, 'loss/train': 1.7249945402145386} 08/30/2021 21:07:18 - INFO - __main__ - Step 44248: {'lr': 0.00040603302260300435, 'samples': 8495616, 'steps': 44247, 'loss/train': 1.425903081893921} 08/30/2021 21:07:18 - INFO - __main__ - Step 44249: {'lr': 0.00040602887630850055, 'samples': 8495808, 'steps': 44248, 'loss/train': 1.4206792116165161} 08/30/2021 21:07:20 - INFO - __main__ - Step 44250: {'lr': 0.0004060247299436925, 'samples': 8496000, 'steps': 44249, 'loss/train': 1.3775831460952759} 08/30/2021 21:07:20 - INFO - __main__ - Step 44251: {'lr': 0.0004060205835085821, 'samples': 8496192, 'steps': 44250, 'loss/train': 1.731313705444336} 08/30/2021 21:07:21 - INFO - __main__ - Step 44252: {'lr': 0.00040601643700317126, 'samples': 8496384, 'steps': 44251, 'loss/train': 1.2964200973510742} 08/30/2021 21:07:21 - INFO - __main__ - Step 44253: {'lr': 0.0004060122904274618, 'samples': 8496576, 'steps': 44252, 'loss/train': 1.4697345495224} 08/30/2021 21:07:21 - INFO - __main__ - Step 44254: {'lr': 0.0004060081437814557, 'samples': 8496768, 'steps': 44253, 'loss/train': 1.290294885635376} 08/30/2021 21:07:23 - INFO - __main__ - Step 44255: {'lr': 0.00040600399706515466, 'samples': 8496960, 'steps': 44254, 'loss/train': 1.2453558444976807} 08/30/2021 21:07:23 - INFO - __main__ - Step 44256: {'lr': 0.0004059998502785606, 'samples': 8497152, 'steps': 44255, 'loss/train': 0.8972698450088501} 08/30/2021 21:07:24 - INFO - __main__ - Step 44257: {'lr': 0.0004059957034216755, 'samples': 8497344, 'steps': 44256, 'loss/train': 1.6260112524032593} 08/30/2021 21:07:24 - INFO - __main__ - Step 44258: {'lr': 0.00040599155649450106, 'samples': 8497536, 'steps': 44257, 'loss/train': 1.6431219577789307} 08/30/2021 21:07:24 - INFO - __main__ - Step 44259: {'lr': 0.00040598740949703927, 'samples': 8497728, 'steps': 44258, 'loss/train': 1.289858341217041} 08/30/2021 21:07:26 - INFO - __main__ - Step 44260: {'lr': 0.00040598326242929195, 'samples': 8497920, 'steps': 44259, 'loss/train': 1.2255562543869019} 08/30/2021 21:07:26 - INFO - __main__ - Step 44261: {'lr': 0.00040597911529126096, 'samples': 8498112, 'steps': 44260, 'loss/train': 1.1856263875961304} 08/30/2021 21:07:27 - INFO - __main__ - Step 44262: {'lr': 0.00040597496808294825, 'samples': 8498304, 'steps': 44261, 'loss/train': 1.9981262683868408} 08/30/2021 21:07:27 - INFO - __main__ - Step 44263: {'lr': 0.0004059708208043556, 'samples': 8498496, 'steps': 44262, 'loss/train': 1.3707419633865356} 08/30/2021 21:07:27 - INFO - __main__ - Step 44264: {'lr': 0.00040596667345548486, 'samples': 8498688, 'steps': 44263, 'loss/train': 0.8817673921585083} 08/30/2021 21:07:29 - INFO - __main__ - Step 44265: {'lr': 0.00040596252603633797, 'samples': 8498880, 'steps': 44264, 'loss/train': 0.9865076541900635} 08/30/2021 21:07:30 - INFO - __main__ - Step 44266: {'lr': 0.0004059583785469168, 'samples': 8499072, 'steps': 44265, 'loss/train': 1.5346657037734985} 08/30/2021 21:07:30 - INFO - __main__ - Step 44267: {'lr': 0.00040595423098722315, 'samples': 8499264, 'steps': 44266, 'loss/train': 0.6381934881210327} 08/30/2021 21:07:30 - INFO - __main__ - Step 44268: {'lr': 0.000405950083357259, 'samples': 8499456, 'steps': 44267, 'loss/train': 0.1051681861281395} 08/30/2021 21:07:31 - INFO - __main__ - Step 44269: {'lr': 0.0004059459356570261, 'samples': 8499648, 'steps': 44268, 'loss/train': 1.7870903015136719} 08/30/2021 21:07:32 - INFO - __main__ - Step 44270: {'lr': 0.00040594178788652636, 'samples': 8499840, 'steps': 44269, 'loss/train': 1.3645126819610596} 08/30/2021 21:07:33 - INFO - __main__ - Step 44271: {'lr': 0.00040593764004576166, 'samples': 8500032, 'steps': 44270, 'loss/train': 0.8432281613349915} 08/30/2021 21:07:33 - INFO - __main__ - Step 44272: {'lr': 0.0004059334921347339, 'samples': 8500224, 'steps': 44271, 'loss/train': 1.7896136045455933} 08/30/2021 21:07:33 - INFO - __main__ - Step 44273: {'lr': 0.00040592934415344486, 'samples': 8500416, 'steps': 44272, 'loss/train': 1.0209556818008423} 08/30/2021 21:07:34 - INFO - __main__ - Step 44274: {'lr': 0.0004059251961018965, 'samples': 8500608, 'steps': 44273, 'loss/train': 1.3701362609863281} 08/30/2021 21:07:35 - INFO - __main__ - Step 44275: {'lr': 0.00040592104798009066, 'samples': 8500800, 'steps': 44274, 'loss/train': 0.9669306874275208} 08/30/2021 21:07:36 - INFO - __main__ - Step 44276: {'lr': 0.00040591689978802917, 'samples': 8500992, 'steps': 44275, 'loss/train': 1.9835619926452637} 08/30/2021 21:07:36 - INFO - __main__ - Step 44277: {'lr': 0.0004059127515257139, 'samples': 8501184, 'steps': 44276, 'loss/train': 1.2374932765960693} 08/30/2021 21:07:36 - INFO - __main__ - Step 44278: {'lr': 0.0004059086031931468, 'samples': 8501376, 'steps': 44277, 'loss/train': 1.4289745092391968} 08/30/2021 21:07:37 - INFO - __main__ - Step 44279: {'lr': 0.00040590445479032965, 'samples': 8501568, 'steps': 44278, 'loss/train': 0.5289366841316223} 08/30/2021 21:07:39 - INFO - __main__ - Step 44280: {'lr': 0.0004059003063172644, 'samples': 8501760, 'steps': 44279, 'loss/train': 2.079277753829956} 08/30/2021 21:07:39 - INFO - __main__ - Step 44281: {'lr': 0.0004058961577739529, 'samples': 8501952, 'steps': 44280, 'loss/train': 1.273216724395752} 08/30/2021 21:07:40 - INFO - __main__ - Step 44282: {'lr': 0.00040589200916039703, 'samples': 8502144, 'steps': 44281, 'loss/train': 1.8912079334259033} 08/30/2021 21:07:40 - INFO - __main__ - Step 44283: {'lr': 0.0004058878604765985, 'samples': 8502336, 'steps': 44282, 'loss/train': 1.608237862586975} 08/30/2021 21:07:40 - INFO - __main__ - Step 44284: {'lr': 0.00040588371172255936, 'samples': 8502528, 'steps': 44283, 'loss/train': 1.7200936079025269} 08/30/2021 21:07:42 - INFO - __main__ - Step 44285: {'lr': 0.0004058795628982814, 'samples': 8502720, 'steps': 44284, 'loss/train': 1.2227617502212524} 08/30/2021 21:07:42 - INFO - __main__ - Step 44286: {'lr': 0.0004058754140037666, 'samples': 8502912, 'steps': 44285, 'loss/train': 1.2834556102752686} 08/30/2021 21:07:43 - INFO - __main__ - Step 44287: {'lr': 0.00040587126503901664, 'samples': 8503104, 'steps': 44286, 'loss/train': 1.5086218118667603} 08/30/2021 21:07:43 - INFO - __main__ - Step 44288: {'lr': 0.0004058671160040336, 'samples': 8503296, 'steps': 44287, 'loss/train': 1.3518232107162476} 08/30/2021 21:07:43 - INFO - __main__ - Step 44289: {'lr': 0.0004058629668988192, 'samples': 8503488, 'steps': 44288, 'loss/train': 1.1476361751556396} 08/30/2021 21:07:45 - INFO - __main__ - Step 44290: {'lr': 0.0004058588177233753, 'samples': 8503680, 'steps': 44289, 'loss/train': 1.532558560371399} 08/30/2021 21:07:45 - INFO - __main__ - Step 44291: {'lr': 0.0004058546684777039, 'samples': 8503872, 'steps': 44290, 'loss/train': 0.211063951253891} 08/30/2021 21:07:46 - INFO - __main__ - Step 44292: {'lr': 0.0004058505191618067, 'samples': 8504064, 'steps': 44291, 'loss/train': 1.150338053703308} 08/30/2021 21:07:46 - INFO - __main__ - Step 44293: {'lr': 0.00040584636977568573, 'samples': 8504256, 'steps': 44292, 'loss/train': 0.8358545303344727} 08/30/2021 21:07:46 - INFO - __main__ - Step 44294: {'lr': 0.0004058422203193428, 'samples': 8504448, 'steps': 44293, 'loss/train': 0.9335961937904358} 08/30/2021 21:07:48 - INFO - __main__ - Step 44295: {'lr': 0.0004058380707927798, 'samples': 8504640, 'steps': 44294, 'loss/train': 1.069401741027832} 08/30/2021 21:07:48 - INFO - __main__ - Step 44296: {'lr': 0.00040583392119599847, 'samples': 8504832, 'steps': 44295, 'loss/train': 1.6561537981033325} 08/30/2021 21:07:49 - INFO - __main__ - Step 44297: {'lr': 0.0004058297715290008, 'samples': 8505024, 'steps': 44296, 'loss/train': 1.3577299118041992} 08/30/2021 21:07:49 - INFO - __main__ - Step 44298: {'lr': 0.00040582562179178864, 'samples': 8505216, 'steps': 44297, 'loss/train': 1.6764581203460693} 08/30/2021 21:07:49 - INFO - __main__ - Step 44299: {'lr': 0.0004058214719843639, 'samples': 8505408, 'steps': 44298, 'loss/train': 1.693547010421753} 08/30/2021 21:07:51 - INFO - __main__ - Step 44300: {'lr': 0.0004058173221067284, 'samples': 8505600, 'steps': 44299, 'loss/train': 1.5342638492584229} 08/30/2021 21:07:52 - INFO - __main__ - Step 44301: {'lr': 0.00040581317215888403, 'samples': 8505792, 'steps': 44300, 'loss/train': 1.0842876434326172} 08/30/2021 21:07:52 - INFO - __main__ - Step 44302: {'lr': 0.0004058090221408326, 'samples': 8505984, 'steps': 44301, 'loss/train': 0.6397159695625305} 08/30/2021 21:07:52 - INFO - __main__ - Step 44303: {'lr': 0.0004058048720525761, 'samples': 8506176, 'steps': 44302, 'loss/train': 0.8952687382698059} 08/30/2021 21:07:53 - INFO - __main__ - Step 44304: {'lr': 0.00040580072189411626, 'samples': 8506368, 'steps': 44303, 'loss/train': 1.2569971084594727} 08/30/2021 21:07:53 - INFO - __main__ - Step 44305: {'lr': 0.00040579657166545503, 'samples': 8506560, 'steps': 44304, 'loss/train': 1.7909328937530518} 08/30/2021 21:07:55 - INFO - __main__ - Step 44306: {'lr': 0.0004057924213665943, 'samples': 8506752, 'steps': 44305, 'loss/train': 0.21140064299106598} 08/30/2021 21:07:55 - INFO - __main__ - Step 44307: {'lr': 0.0004057882709975359, 'samples': 8506944, 'steps': 44306, 'loss/train': 1.1904557943344116} 08/30/2021 21:07:55 - INFO - __main__ - Step 44308: {'lr': 0.0004057841205582817, 'samples': 8507136, 'steps': 44307, 'loss/train': 1.4542088508605957} 08/30/2021 21:07:56 - INFO - __main__ - Step 44309: {'lr': 0.0004057799700488336, 'samples': 8507328, 'steps': 44308, 'loss/train': 1.513412594795227} 08/30/2021 21:07:56 - INFO - __main__ - Step 44310: {'lr': 0.0004057758194691934, 'samples': 8507520, 'steps': 44309, 'loss/train': 1.5556021928787231} 08/30/2021 21:07:57 - INFO - __main__ - Step 44311: {'lr': 0.00040577166881936304, 'samples': 8507712, 'steps': 44310, 'loss/train': 1.3197760581970215} 08/30/2021 21:07:58 - INFO - __main__ - Step 44312: {'lr': 0.0004057675180993444, 'samples': 8507904, 'steps': 44311, 'loss/train': 0.688572347164154} 08/30/2021 21:07:58 - INFO - __main__ - Step 44313: {'lr': 0.00040576336730913933, 'samples': 8508096, 'steps': 44312, 'loss/train': 0.686278760433197} 08/30/2021 21:07:59 - INFO - __main__ - Step 44314: {'lr': 0.00040575921644874966, 'samples': 8508288, 'steps': 44313, 'loss/train': 1.106673240661621} 08/30/2021 21:07:59 - INFO - __main__ - Step 44315: {'lr': 0.00040575506551817725, 'samples': 8508480, 'steps': 44314, 'loss/train': 1.3167310953140259} 08/30/2021 21:08:00 - INFO - __main__ - Step 44316: {'lr': 0.00040575091451742405, 'samples': 8508672, 'steps': 44315, 'loss/train': 1.2857811450958252} 08/30/2021 21:08:01 - INFO - __main__ - Step 44317: {'lr': 0.0004057467634464919, 'samples': 8508864, 'steps': 44316, 'loss/train': 1.5763572454452515} 08/30/2021 21:08:01 - INFO - __main__ - Step 44318: {'lr': 0.00040574261230538267, 'samples': 8509056, 'steps': 44317, 'loss/train': 1.7079591751098633} 08/30/2021 21:08:02 - INFO - __main__ - Step 44319: {'lr': 0.0004057384610940982, 'samples': 8509248, 'steps': 44318, 'loss/train': 1.7545469999313354} 08/30/2021 21:08:02 - INFO - __main__ - Step 44320: {'lr': 0.0004057343098126404, 'samples': 8509440, 'steps': 44319, 'loss/train': 1.6263655424118042} 08/30/2021 21:08:04 - INFO - __main__ - Step 44321: {'lr': 0.0004057301584610111, 'samples': 8509632, 'steps': 44320, 'loss/train': 2.9451348781585693} 08/30/2021 21:08:04 - INFO - __main__ - Step 44322: {'lr': 0.00040572600703921223, 'samples': 8509824, 'steps': 44321, 'loss/train': 1.6663204431533813} 08/30/2021 21:08:04 - INFO - __main__ - Step 44323: {'lr': 0.0004057218555472456, 'samples': 8510016, 'steps': 44322, 'loss/train': 1.0474318265914917} 08/30/2021 21:08:05 - INFO - __main__ - Step 44324: {'lr': 0.0004057177039851131, 'samples': 8510208, 'steps': 44323, 'loss/train': 0.9182167053222656} 08/30/2021 21:08:05 - INFO - __main__ - Step 44325: {'lr': 0.00040571355235281657, 'samples': 8510400, 'steps': 44324, 'loss/train': 1.3504478931427002} 08/30/2021 21:08:06 - INFO - __main__ - Step 44326: {'lr': 0.00040570940065035797, 'samples': 8510592, 'steps': 44325, 'loss/train': 0.0857388824224472} 08/30/2021 21:08:07 - INFO - __main__ - Step 44327: {'lr': 0.0004057052488777392, 'samples': 8510784, 'steps': 44326, 'loss/train': 1.8662266731262207} 08/30/2021 21:08:08 - INFO - __main__ - Step 44328: {'lr': 0.0004057010970349619, 'samples': 8510976, 'steps': 44327, 'loss/train': 1.5167348384857178} 08/30/2021 21:08:08 - INFO - __main__ - Step 44329: {'lr': 0.00040569694512202815, 'samples': 8511168, 'steps': 44328, 'loss/train': 0.7417482137680054} 08/30/2021 21:08:08 - INFO - __main__ - Step 44330: {'lr': 0.00040569279313893976, 'samples': 8511360, 'steps': 44329, 'loss/train': 1.1411490440368652} 08/30/2021 21:08:09 - INFO - __main__ - Step 44331: {'lr': 0.0004056886410856986, 'samples': 8511552, 'steps': 44330, 'loss/train': 1.4563403129577637} 08/30/2021 21:08:11 - INFO - __main__ - Step 44332: {'lr': 0.0004056844889623065, 'samples': 8511744, 'steps': 44331, 'loss/train': 0.6688815355300903} 08/30/2021 21:08:11 - INFO - __main__ - Step 44333: {'lr': 0.0004056803367687654, 'samples': 8511936, 'steps': 44332, 'loss/train': 2.130687952041626} 08/30/2021 21:08:11 - INFO - __main__ - Step 44334: {'lr': 0.0004056761845050772, 'samples': 8512128, 'steps': 44333, 'loss/train': 0.916379988193512} 08/30/2021 21:08:12 - INFO - __main__ - Step 44335: {'lr': 0.0004056720321712436, 'samples': 8512320, 'steps': 44334, 'loss/train': 2.310025930404663} 08/30/2021 21:08:12 - INFO - __main__ - Step 44336: {'lr': 0.00040566787976726665, 'samples': 8512512, 'steps': 44335, 'loss/train': 1.4363394975662231} 08/30/2021 21:08:14 - INFO - __main__ - Step 44337: {'lr': 0.00040566372729314813, 'samples': 8512704, 'steps': 44336, 'loss/train': 1.2332144975662231} 08/30/2021 21:08:14 - INFO - __main__ - Step 44338: {'lr': 0.00040565957474889, 'samples': 8512896, 'steps': 44337, 'loss/train': 1.513017177581787} 08/30/2021 21:08:14 - INFO - __main__ - Step 44339: {'lr': 0.000405655422134494, 'samples': 8513088, 'steps': 44338, 'loss/train': 1.5066421031951904} 08/30/2021 21:08:15 - INFO - __main__ - Step 44340: {'lr': 0.0004056512694499621, 'samples': 8513280, 'steps': 44339, 'loss/train': 1.3086494207382202} 08/30/2021 21:08:15 - INFO - __main__ - Step 44341: {'lr': 0.0004056471166952961, 'samples': 8513472, 'steps': 44340, 'loss/train': 1.198072910308838} 08/30/2021 21:08:17 - INFO - __main__ - Step 44342: {'lr': 0.0004056429638704979, 'samples': 8513664, 'steps': 44341, 'loss/train': 1.437775731086731} 08/30/2021 21:08:17 - INFO - __main__ - Step 44343: {'lr': 0.0004056388109755695, 'samples': 8513856, 'steps': 44342, 'loss/train': 0.780569851398468} 08/30/2021 21:08:18 - INFO - __main__ - Step 44344: {'lr': 0.0004056346580105126, 'samples': 8514048, 'steps': 44343, 'loss/train': 1.385893702507019} 08/30/2021 21:08:18 - INFO - __main__ - Step 44345: {'lr': 0.00040563050497532905, 'samples': 8514240, 'steps': 44344, 'loss/train': 1.0065590143203735} 08/30/2021 21:08:18 - INFO - __main__ - Step 44346: {'lr': 0.00040562635187002083, 'samples': 8514432, 'steps': 44345, 'loss/train': 1.6725244522094727} 08/30/2021 21:08:20 - INFO - __main__ - Step 44347: {'lr': 0.0004056221986945898, 'samples': 8514624, 'steps': 44346, 'loss/train': 1.7639890909194946} 08/30/2021 21:08:20 - INFO - __main__ - Step 44348: {'lr': 0.0004056180454490378, 'samples': 8514816, 'steps': 44347, 'loss/train': 1.2765198945999146} 08/30/2021 21:08:20 - INFO - __main__ - Step 44349: {'lr': 0.00040561389213336673, 'samples': 8515008, 'steps': 44348, 'loss/train': 1.6406426429748535} 08/30/2021 21:08:21 - INFO - __main__ - Step 44350: {'lr': 0.00040560973874757844, 'samples': 8515200, 'steps': 44349, 'loss/train': 1.497821569442749} 08/30/2021 21:08:21 - INFO - __main__ - Step 44351: {'lr': 0.0004056055852916748, 'samples': 8515392, 'steps': 44350, 'loss/train': 1.352238655090332} 08/30/2021 21:08:22 - INFO - __main__ - Step 44352: {'lr': 0.0004056014317656577, 'samples': 8515584, 'steps': 44351, 'loss/train': 0.9462263584136963} 08/30/2021 21:08:23 - INFO - __main__ - Step 44353: {'lr': 0.00040559727816952897, 'samples': 8515776, 'steps': 44352, 'loss/train': 0.90390944480896} 08/30/2021 21:08:23 - INFO - __main__ - Step 44354: {'lr': 0.0004055931245032904, 'samples': 8515968, 'steps': 44353, 'loss/train': 1.8002678155899048} 08/30/2021 21:08:24 - INFO - __main__ - Step 44355: {'lr': 0.0004055889707669441, 'samples': 8516160, 'steps': 44354, 'loss/train': 1.4575846195220947} 08/30/2021 21:08:24 - INFO - __main__ - Step 44356: {'lr': 0.0004055848169604919, 'samples': 8516352, 'steps': 44355, 'loss/train': 1.347817063331604} 08/30/2021 21:08:24 - INFO - __main__ - Step 44357: {'lr': 0.00040558066308393536, 'samples': 8516544, 'steps': 44356, 'loss/train': 1.2407376766204834} 08/30/2021 21:08:26 - INFO - __main__ - Step 44358: {'lr': 0.0004055765091372767, 'samples': 8516736, 'steps': 44357, 'loss/train': 1.603507161140442} 08/30/2021 21:08:26 - INFO - __main__ - Step 44359: {'lr': 0.0004055723551205177, 'samples': 8516928, 'steps': 44358, 'loss/train': 1.2168844938278198} 08/30/2021 21:08:27 - INFO - __main__ - Step 44360: {'lr': 0.0004055682010336601, 'samples': 8517120, 'steps': 44359, 'loss/train': 1.5627723932266235} 08/30/2021 21:08:27 - INFO - __main__ - Step 44361: {'lr': 0.0004055640468767059, 'samples': 8517312, 'steps': 44360, 'loss/train': 1.615235447883606} 08/30/2021 21:08:28 - INFO - __main__ - Step 44362: {'lr': 0.000405559892649657, 'samples': 8517504, 'steps': 44361, 'loss/train': 1.522583246231079} 08/30/2021 21:08:29 - INFO - __main__ - Step 44363: {'lr': 0.00040555573835251513, 'samples': 8517696, 'steps': 44362, 'loss/train': 1.4683529138565063} 08/30/2021 21:08:30 - INFO - __main__ - Step 44364: {'lr': 0.00040555158398528237, 'samples': 8517888, 'steps': 44363, 'loss/train': 1.1983929872512817} 08/30/2021 21:08:30 - INFO - __main__ - Step 44365: {'lr': 0.0004055474295479603, 'samples': 8518080, 'steps': 44364, 'loss/train': 1.5823521614074707} 08/30/2021 21:08:30 - INFO - __main__ - Step 44366: {'lr': 0.00040554327504055106, 'samples': 8518272, 'steps': 44365, 'loss/train': 1.7043169736862183} 08/30/2021 21:08:31 - INFO - __main__ - Step 44367: {'lr': 0.0004055391204630564, 'samples': 8518464, 'steps': 44366, 'loss/train': 1.4671788215637207} 08/30/2021 21:08:32 - INFO - __main__ - Step 44368: {'lr': 0.0004055349658154782, 'samples': 8518656, 'steps': 44367, 'loss/train': 0.8614078164100647} 08/30/2021 21:08:33 - INFO - __main__ - Step 44369: {'lr': 0.00040553081109781844, 'samples': 8518848, 'steps': 44368, 'loss/train': 1.3381456136703491} 08/30/2021 21:08:33 - INFO - __main__ - Step 44370: {'lr': 0.0004055266563100788, 'samples': 8519040, 'steps': 44369, 'loss/train': 1.3427907228469849} 08/30/2021 21:08:33 - INFO - __main__ - Step 44371: {'lr': 0.00040552250145226124, 'samples': 8519232, 'steps': 44370, 'loss/train': 1.5324828624725342} 08/30/2021 21:08:34 - INFO - __main__ - Step 44372: {'lr': 0.0004055183465243676, 'samples': 8519424, 'steps': 44371, 'loss/train': 1.672202706336975} 08/30/2021 21:08:35 - INFO - __main__ - Step 44373: {'lr': 0.0004055141915263999, 'samples': 8519616, 'steps': 44372, 'loss/train': 1.2652825117111206} 08/30/2021 21:08:36 - INFO - __main__ - Step 44374: {'lr': 0.0004055100364583598, 'samples': 8519808, 'steps': 44373, 'loss/train': 1.2054704427719116} 08/30/2021 21:08:36 - INFO - __main__ - Step 44375: {'lr': 0.0004055058813202493, 'samples': 8520000, 'steps': 44374, 'loss/train': 1.5328508615493774} 08/30/2021 21:08:36 - INFO - __main__ - Step 44376: {'lr': 0.0004055017261120704, 'samples': 8520192, 'steps': 44375, 'loss/train': 1.181402325630188} 08/30/2021 21:08:37 - INFO - __main__ - Step 44377: {'lr': 0.00040549757083382465, 'samples': 8520384, 'steps': 44376, 'loss/train': 0.12349032610654831} 08/30/2021 21:08:38 - INFO - __main__ - Step 44378: {'lr': 0.00040549341548551415, 'samples': 8520576, 'steps': 44377, 'loss/train': 1.0654141902923584} 08/30/2021 21:08:39 - INFO - __main__ - Step 44379: {'lr': 0.0004054892600671407, 'samples': 8520768, 'steps': 44378, 'loss/train': 1.143369197845459} 08/30/2021 21:08:39 - INFO - __main__ - Step 44380: {'lr': 0.00040548510457870623, 'samples': 8520960, 'steps': 44379, 'loss/train': 0.18210400640964508} 08/30/2021 21:08:40 - INFO - __main__ - Step 44381: {'lr': 0.00040548094902021257, 'samples': 8521152, 'steps': 44380, 'loss/train': 0.9839759469032288} 08/30/2021 21:08:40 - INFO - __main__ - Step 44382: {'lr': 0.00040547679339166155, 'samples': 8521344, 'steps': 44381, 'loss/train': 1.4647890329360962} 08/30/2021 21:08:42 - INFO - __main__ - Step 44383: {'lr': 0.0004054726376930551, 'samples': 8521536, 'steps': 44382, 'loss/train': 1.3601447343826294} 08/30/2021 21:08:42 - INFO - __main__ - Step 44384: {'lr': 0.0004054684819243951, 'samples': 8521728, 'steps': 44383, 'loss/train': 1.464267611503601} 08/30/2021 21:08:42 - INFO - __main__ - Step 44385: {'lr': 0.0004054643260856834, 'samples': 8521920, 'steps': 44384, 'loss/train': 1.268541693687439} 08/30/2021 21:08:43 - INFO - __main__ - Step 44386: {'lr': 0.00040546017017692183, 'samples': 8522112, 'steps': 44385, 'loss/train': 0.5542771220207214} 08/30/2021 21:08:43 - INFO - __main__ - Step 44387: {'lr': 0.00040545601419811236, 'samples': 8522304, 'steps': 44386, 'loss/train': 0.6981580853462219} 08/30/2021 21:08:43 - INFO - __main__ - Step 44388: {'lr': 0.00040545185814925676, 'samples': 8522496, 'steps': 44387, 'loss/train': 0.9781181812286377} 08/30/2021 21:08:46 - INFO - __main__ - Step 44389: {'lr': 0.00040544770203035705, 'samples': 8522688, 'steps': 44388, 'loss/train': 1.3792634010314941} 08/30/2021 21:08:46 - INFO - __main__ - Step 44390: {'lr': 0.0004054435458414149, 'samples': 8522880, 'steps': 44389, 'loss/train': 1.5857902765274048} 08/30/2021 21:08:46 - INFO - __main__ - Step 44391: {'lr': 0.0004054393895824323, 'samples': 8523072, 'steps': 44390, 'loss/train': 1.8444561958312988} 08/30/2021 21:08:47 - INFO - __main__ - Step 44392: {'lr': 0.00040543523325341116, 'samples': 8523264, 'steps': 44391, 'loss/train': 1.0472975969314575} 08/30/2021 21:08:47 - INFO - __main__ - Step 44393: {'lr': 0.0004054310768543532, 'samples': 8523456, 'steps': 44392, 'loss/train': 0.889835000038147} 08/30/2021 21:08:49 - INFO - __main__ - Step 44394: {'lr': 0.00040542692038526054, 'samples': 8523648, 'steps': 44393, 'loss/train': 1.0555006265640259} 08/30/2021 21:08:49 - INFO - __main__ - Step 44395: {'lr': 0.0004054227638461348, 'samples': 8523840, 'steps': 44394, 'loss/train': 1.0273945331573486} 08/30/2021 21:08:49 - INFO - __main__ - Step 44396: {'lr': 0.000405418607236978, 'samples': 8524032, 'steps': 44395, 'loss/train': 1.463208794593811} 08/30/2021 21:08:50 - INFO - __main__ - Step 44397: {'lr': 0.00040541445055779197, 'samples': 8524224, 'steps': 44396, 'loss/train': 1.6251517534255981} 08/30/2021 21:08:50 - INFO - __main__ - Step 44398: {'lr': 0.0004054102938085786, 'samples': 8524416, 'steps': 44397, 'loss/train': 1.1361525058746338} 08/30/2021 21:08:52 - INFO - __main__ - Step 44399: {'lr': 0.0004054061369893397, 'samples': 8524608, 'steps': 44398, 'loss/train': 1.5430678129196167} 08/30/2021 21:08:52 - INFO - __main__ - Step 44400: {'lr': 0.0004054019801000772, 'samples': 8524800, 'steps': 44399, 'loss/train': 1.450382947921753} 08/30/2021 21:08:52 - INFO - __main__ - Step 44401: {'lr': 0.00040539782314079304, 'samples': 8524992, 'steps': 44400, 'loss/train': 1.108041763305664} 08/30/2021 21:08:53 - INFO - __main__ - Step 44402: {'lr': 0.000405393666111489, 'samples': 8525184, 'steps': 44401, 'loss/train': 1.10700523853302} 08/30/2021 21:08:53 - INFO - __main__ - Step 44403: {'lr': 0.0004053895090121669, 'samples': 8525376, 'steps': 44402, 'loss/train': 1.555692434310913} 08/30/2021 21:08:55 - INFO - __main__ - Step 44404: {'lr': 0.00040538535184282877, 'samples': 8525568, 'steps': 44403, 'loss/train': 1.4380104541778564} 08/30/2021 21:08:55 - INFO - __main__ - Step 44405: {'lr': 0.00040538119460347636, 'samples': 8525760, 'steps': 44404, 'loss/train': 0.3123876452445984} 08/30/2021 21:08:56 - INFO - __main__ - Step 44406: {'lr': 0.0004053770372941116, 'samples': 8525952, 'steps': 44405, 'loss/train': 1.4943342208862305} 08/30/2021 21:08:56 - INFO - __main__ - Step 44407: {'lr': 0.00040537287991473627, 'samples': 8526144, 'steps': 44406, 'loss/train': 1.6229242086410522} 08/30/2021 21:08:56 - INFO - __main__ - Step 44408: {'lr': 0.0004053687224653524, 'samples': 8526336, 'steps': 44407, 'loss/train': 1.8058867454528809} 08/30/2021 21:08:57 - INFO - __main__ - Step 44409: {'lr': 0.0004053645649459617, 'samples': 8526528, 'steps': 44408, 'loss/train': 1.1329448223114014} 08/30/2021 21:08:58 - INFO - __main__ - Step 44410: {'lr': 0.0004053604073565662, 'samples': 8526720, 'steps': 44409, 'loss/train': 1.3405773639678955} 08/30/2021 21:08:59 - INFO - __main__ - Step 44411: {'lr': 0.0004053562496971677, 'samples': 8526912, 'steps': 44410, 'loss/train': 1.1856756210327148} 08/30/2021 21:08:59 - INFO - __main__ - Step 44412: {'lr': 0.00040535209196776803, 'samples': 8527104, 'steps': 44411, 'loss/train': 0.09055878221988678} 08/30/2021 21:08:59 - INFO - __main__ - Step 44413: {'lr': 0.00040534793416836915, 'samples': 8527296, 'steps': 44412, 'loss/train': 0.9902360439300537} 08/30/2021 21:09:00 - INFO - __main__ - Step 44414: {'lr': 0.00040534377629897276, 'samples': 8527488, 'steps': 44413, 'loss/train': 0.7650054097175598} 08/30/2021 21:09:01 - INFO - __main__ - Step 44415: {'lr': 0.000405339618359581, 'samples': 8527680, 'steps': 44414, 'loss/train': 0.4365941882133484} 08/30/2021 21:09:02 - INFO - __main__ - Step 44416: {'lr': 0.0004053354603501956, 'samples': 8527872, 'steps': 44415, 'loss/train': 1.9157416820526123} 08/30/2021 21:09:02 - INFO - __main__ - Step 44417: {'lr': 0.0004053313022708184, 'samples': 8528064, 'steps': 44416, 'loss/train': 1.7101826667785645} 08/30/2021 21:09:02 - INFO - __main__ - Step 44418: {'lr': 0.00040532714412145135, 'samples': 8528256, 'steps': 44417, 'loss/train': 1.0287338495254517} 08/30/2021 21:09:03 - INFO - __main__ - Step 44419: {'lr': 0.0004053229859020962, 'samples': 8528448, 'steps': 44418, 'loss/train': 1.6128599643707275} 08/30/2021 21:09:05 - INFO - __main__ - Step 44420: {'lr': 0.00040531882761275496, 'samples': 8528640, 'steps': 44419, 'loss/train': 1.497105360031128} 08/30/2021 21:09:05 - INFO - __main__ - Step 44421: {'lr': 0.00040531466925342947, 'samples': 8528832, 'steps': 44420, 'loss/train': 0.8967697024345398} 08/30/2021 21:09:05 - INFO - __main__ - Step 44422: {'lr': 0.0004053105108241216, 'samples': 8529024, 'steps': 44421, 'loss/train': 1.6246263980865479} 08/30/2021 21:09:06 - INFO - __main__ - Step 44423: {'lr': 0.0004053063523248331, 'samples': 8529216, 'steps': 44422, 'loss/train': 1.360418438911438} 08/30/2021 21:09:06 - INFO - __main__ - Step 44424: {'lr': 0.0004053021937555661, 'samples': 8529408, 'steps': 44423, 'loss/train': 1.585578203201294} 08/30/2021 21:09:07 - INFO - __main__ - Step 44425: {'lr': 0.00040529803511632224, 'samples': 8529600, 'steps': 44424, 'loss/train': 1.7599161863327026} 08/30/2021 21:09:08 - INFO - __main__ - Step 44426: {'lr': 0.0004052938764071035, 'samples': 8529792, 'steps': 44425, 'loss/train': 1.6455732583999634} 08/30/2021 21:09:08 - INFO - __main__ - Step 44427: {'lr': 0.00040528971762791177, 'samples': 8529984, 'steps': 44426, 'loss/train': 1.3100522756576538} 08/30/2021 21:09:08 - INFO - __main__ - Step 44428: {'lr': 0.0004052855587787488, 'samples': 8530176, 'steps': 44427, 'loss/train': 1.5594284534454346} 08/30/2021 21:09:09 - INFO - __main__ - Step 44429: {'lr': 0.0004052813998596167, 'samples': 8530368, 'steps': 44428, 'loss/train': 1.7124489545822144} 08/30/2021 21:09:10 - INFO - __main__ - Step 44430: {'lr': 0.0004052772408705171, 'samples': 8530560, 'steps': 44429, 'loss/train': 1.6920275688171387} 08/30/2021 21:09:11 - INFO - __main__ - Step 44431: {'lr': 0.000405273081811452, 'samples': 8530752, 'steps': 44430, 'loss/train': 1.4410616159439087} 08/30/2021 21:09:11 - INFO - __main__ - Step 44432: {'lr': 0.0004052689226824232, 'samples': 8530944, 'steps': 44431, 'loss/train': 1.5302947759628296} 08/30/2021 21:09:12 - INFO - __main__ - Step 44433: {'lr': 0.0004052647634834327, 'samples': 8531136, 'steps': 44432, 'loss/train': 1.1068027019500732} 08/30/2021 21:09:12 - INFO - __main__ - Step 44434: {'lr': 0.00040526060421448216, 'samples': 8531328, 'steps': 44433, 'loss/train': 1.0758174657821655} 08/30/2021 21:09:14 - INFO - __main__ - Step 44435: {'lr': 0.00040525644487557366, 'samples': 8531520, 'steps': 44434, 'loss/train': 2.474747896194458} 08/30/2021 21:09:14 - INFO - __main__ - Step 44436: {'lr': 0.000405252285466709, 'samples': 8531712, 'steps': 44435, 'loss/train': 1.5391771793365479} 08/30/2021 21:09:15 - INFO - __main__ - Step 44437: {'lr': 0.0004052481259878901, 'samples': 8531904, 'steps': 44436, 'loss/train': 1.489598274230957} 08/30/2021 21:09:15 - INFO - __main__ - Step 44438: {'lr': 0.00040524396643911874, 'samples': 8532096, 'steps': 44437, 'loss/train': 1.71968674659729} 08/30/2021 21:09:15 - INFO - __main__ - Step 44439: {'lr': 0.00040523980682039684, 'samples': 8532288, 'steps': 44438, 'loss/train': 0.9684491157531738} 08/30/2021 21:09:16 - INFO - __main__ - Step 44440: {'lr': 0.00040523564713172634, 'samples': 8532480, 'steps': 44439, 'loss/train': 0.7825356721878052} 08/30/2021 21:09:18 - INFO - __main__ - Step 44441: {'lr': 0.000405231487373109, 'samples': 8532672, 'steps': 44440, 'loss/train': 1.4384033679962158} 08/30/2021 21:09:18 - INFO - __main__ - Step 44442: {'lr': 0.00040522732754454674, 'samples': 8532864, 'steps': 44441, 'loss/train': 1.5658432245254517} 08/30/2021 21:09:19 - INFO - __main__ - Step 44443: {'lr': 0.0004052231676460415, 'samples': 8533056, 'steps': 44442, 'loss/train': 0.04636095464229584} 08/30/2021 21:09:19 - INFO - __main__ - Step 44444: {'lr': 0.000405219007677595, 'samples': 8533248, 'steps': 44443, 'loss/train': 1.0714856386184692} 08/30/2021 21:09:19 - INFO - __main__ - Step 44445: {'lr': 0.0004052148476392093, 'samples': 8533440, 'steps': 44444, 'loss/train': 1.0937790870666504} 08/30/2021 21:09:21 - INFO - __main__ - Step 44446: {'lr': 0.00040521068753088615, 'samples': 8533632, 'steps': 44445, 'loss/train': 1.9813108444213867} 08/30/2021 21:09:21 - INFO - __main__ - Step 44447: {'lr': 0.0004052065273526274, 'samples': 8533824, 'steps': 44446, 'loss/train': 1.0501751899719238} 08/30/2021 21:09:22 - INFO - __main__ - Step 44448: {'lr': 0.0004052023671044351, 'samples': 8534016, 'steps': 44447, 'loss/train': 1.4251588582992554} 08/30/2021 21:09:22 - INFO - __main__ - Step 44449: {'lr': 0.0004051982067863109, 'samples': 8534208, 'steps': 44448, 'loss/train': 1.5152170658111572} 08/30/2021 21:09:22 - INFO - __main__ - Step 44450: {'lr': 0.0004051940463982569, 'samples': 8534400, 'steps': 44449, 'loss/train': 2.029966115951538} 08/30/2021 21:09:24 - INFO - __main__ - Step 44451: {'lr': 0.0004051898859402748, 'samples': 8534592, 'steps': 44450, 'loss/train': 0.6633539199829102} 08/30/2021 21:09:24 - INFO - __main__ - Step 44452: {'lr': 0.00040518572541236653, 'samples': 8534784, 'steps': 44451, 'loss/train': 1.9171779155731201} 08/30/2021 21:09:25 - INFO - __main__ - Step 44453: {'lr': 0.00040518156481453397, 'samples': 8534976, 'steps': 44452, 'loss/train': 1.0319797992706299} 08/30/2021 21:09:25 - INFO - __main__ - Step 44454: {'lr': 0.0004051774041467789, 'samples': 8535168, 'steps': 44453, 'loss/train': 0.956123948097229} 08/30/2021 21:09:25 - INFO - __main__ - Step 44455: {'lr': 0.00040517324340910347, 'samples': 8535360, 'steps': 44454, 'loss/train': 1.4808039665222168} 08/30/2021 21:09:27 - INFO - __main__ - Step 44456: {'lr': 0.0004051690826015092, 'samples': 8535552, 'steps': 44455, 'loss/train': 1.4301506280899048} 08/30/2021 21:09:27 - INFO - __main__ - Step 44457: {'lr': 0.0004051649217239982, 'samples': 8535744, 'steps': 44456, 'loss/train': 1.0478050708770752} 08/30/2021 21:09:27 - INFO - __main__ - Step 44458: {'lr': 0.00040516076077657233, 'samples': 8535936, 'steps': 44457, 'loss/train': 1.3084079027175903} 08/30/2021 21:09:28 - INFO - __main__ - Step 44459: {'lr': 0.0004051565997592334, 'samples': 8536128, 'steps': 44458, 'loss/train': 1.7300537824630737} 08/30/2021 21:09:28 - INFO - __main__ - Step 44460: {'lr': 0.0004051524386719832, 'samples': 8536320, 'steps': 44459, 'loss/train': 1.4327802658081055} 08/30/2021 21:09:30 - INFO - __main__ - Step 44461: {'lr': 0.0004051482775148238, 'samples': 8536512, 'steps': 44460, 'loss/train': 1.2706925868988037} 08/30/2021 21:09:30 - INFO - __main__ - Step 44462: {'lr': 0.00040514411628775695, 'samples': 8536704, 'steps': 44461, 'loss/train': 1.3717412948608398} 08/30/2021 21:09:30 - INFO - __main__ - Step 44463: {'lr': 0.0004051399549907846, 'samples': 8536896, 'steps': 44462, 'loss/train': 0.8411885499954224} 08/30/2021 21:09:31 - INFO - __main__ - Step 44464: {'lr': 0.0004051357936239085, 'samples': 8537088, 'steps': 44463, 'loss/train': 1.7029852867126465} 08/30/2021 21:09:31 - INFO - __main__ - Step 44465: {'lr': 0.0004051316321871307, 'samples': 8537280, 'steps': 44464, 'loss/train': 1.7586841583251953} 08/30/2021 21:09:33 - INFO - __main__ - Step 44466: {'lr': 0.0004051274706804529, 'samples': 8537472, 'steps': 44465, 'loss/train': 1.1580958366394043} 08/30/2021 21:09:33 - INFO - __main__ - Step 44467: {'lr': 0.00040512330910387706, 'samples': 8537664, 'steps': 44466, 'loss/train': 1.5329684019088745} 08/30/2021 21:09:33 - INFO - __main__ - Step 44468: {'lr': 0.0004051191474574051, 'samples': 8537856, 'steps': 44467, 'loss/train': 0.5874102115631104} 08/30/2021 21:09:34 - INFO - __main__ - Step 44469: {'lr': 0.0004051149857410388, 'samples': 8538048, 'steps': 44468, 'loss/train': 1.3083397150039673} 08/30/2021 21:09:34 - INFO - __main__ - Step 44470: {'lr': 0.00040511082395478014, 'samples': 8538240, 'steps': 44469, 'loss/train': 0.9663345813751221} 08/30/2021 21:09:36 - INFO - __main__ - Step 44471: {'lr': 0.0004051066620986309, 'samples': 8538432, 'steps': 44470, 'loss/train': 1.491760492324829} 08/30/2021 21:09:36 - INFO - __main__ - Step 44472: {'lr': 0.00040510250017259297, 'samples': 8538624, 'steps': 44471, 'loss/train': 1.2722337245941162} 08/30/2021 21:09:36 - INFO - __main__ - Step 44473: {'lr': 0.0004050983381766683, 'samples': 8538816, 'steps': 44472, 'loss/train': 1.2302114963531494} 08/30/2021 21:09:37 - INFO - __main__ - Step 44474: {'lr': 0.00040509417611085864, 'samples': 8539008, 'steps': 44473, 'loss/train': 1.02627694606781} 08/30/2021 21:09:37 - INFO - __main__ - Step 44475: {'lr': 0.000405090013975166, 'samples': 8539200, 'steps': 44474, 'loss/train': 1.4069682359695435} 08/30/2021 21:09:39 - INFO - __main__ - Step 44476: {'lr': 0.0004050858517695921, 'samples': 8539392, 'steps': 44475, 'loss/train': 0.056732427328825} 08/30/2021 21:09:39 - INFO - __main__ - Step 44477: {'lr': 0.00040508168949413904, 'samples': 8539584, 'steps': 44476, 'loss/train': 0.49713489413261414} 08/30/2021 21:09:40 - INFO - __main__ - Step 44478: {'lr': 0.00040507752714880854, 'samples': 8539776, 'steps': 44477, 'loss/train': 1.7905160188674927} 08/30/2021 21:09:40 - INFO - __main__ - Step 44479: {'lr': 0.0004050733647336024, 'samples': 8539968, 'steps': 44478, 'loss/train': 0.039963483810424805} 08/30/2021 21:09:40 - INFO - __main__ - Step 44480: {'lr': 0.00040506920224852265, 'samples': 8540160, 'steps': 44479, 'loss/train': 1.5167438983917236} 08/30/2021 21:09:42 - INFO - __main__ - Step 44481: {'lr': 0.0004050650396935711, 'samples': 8540352, 'steps': 44480, 'loss/train': 0.9848048686981201} 08/30/2021 21:09:42 - INFO - __main__ - Step 44482: {'lr': 0.00040506087706874966, 'samples': 8540544, 'steps': 44481, 'loss/train': 1.1850807666778564} 08/30/2021 21:09:43 - INFO - __main__ - Step 44483: {'lr': 0.00040505671437406017, 'samples': 8540736, 'steps': 44482, 'loss/train': 1.566209316253662} 08/30/2021 21:09:43 - INFO - __main__ - Step 44484: {'lr': 0.00040505255160950453, 'samples': 8540928, 'steps': 44483, 'loss/train': 1.4203972816467285} 08/30/2021 21:09:43 - INFO - __main__ - Step 44485: {'lr': 0.00040504838877508464, 'samples': 8541120, 'steps': 44484, 'loss/train': 1.0548129081726074} 08/30/2021 21:09:44 - INFO - __main__ - Step 44486: {'lr': 0.0004050442258708022, 'samples': 8541312, 'steps': 44485, 'loss/train': 1.396460771560669} 08/30/2021 21:09:45 - INFO - __main__ - Step 44487: {'lr': 0.0004050400628966594, 'samples': 8541504, 'steps': 44486, 'loss/train': 1.2104344367980957} 08/30/2021 21:09:46 - INFO - __main__ - Step 44488: {'lr': 0.0004050358998526578, 'samples': 8541696, 'steps': 44487, 'loss/train': 1.3652832508087158} 08/30/2021 21:09:46 - INFO - __main__ - Step 44489: {'lr': 0.00040503173673879945, 'samples': 8541888, 'steps': 44488, 'loss/train': 0.5879058837890625} 08/30/2021 21:09:46 - INFO - __main__ - Step 44490: {'lr': 0.00040502757355508626, 'samples': 8542080, 'steps': 44489, 'loss/train': 1.201690435409546} 08/30/2021 21:09:47 - INFO - __main__ - Step 44491: {'lr': 0.00040502341030152, 'samples': 8542272, 'steps': 44490, 'loss/train': 1.2262431383132935} 08/30/2021 21:09:49 - INFO - __main__ - Step 44492: {'lr': 0.0004050192469781025, 'samples': 8542464, 'steps': 44491, 'loss/train': 1.5194636583328247} 08/30/2021 21:09:49 - INFO - __main__ - Step 44493: {'lr': 0.00040501508358483583, 'samples': 8542656, 'steps': 44492, 'loss/train': 1.5061290264129639} 08/30/2021 21:09:50 - INFO - __main__ - Step 44494: {'lr': 0.00040501092012172173, 'samples': 8542848, 'steps': 44493, 'loss/train': 1.147111177444458} 08/30/2021 21:09:50 - INFO - __main__ - Step 44495: {'lr': 0.0004050067565887621, 'samples': 8543040, 'steps': 44494, 'loss/train': 1.7778196334838867} 08/30/2021 21:09:50 - INFO - __main__ - Step 44496: {'lr': 0.00040500259298595874, 'samples': 8543232, 'steps': 44495, 'loss/train': 0.8166763186454773} 08/30/2021 21:09:52 - INFO - __main__ - Step 44497: {'lr': 0.00040499842931331374, 'samples': 8543424, 'steps': 44496, 'loss/train': 2.023059844970703} 08/30/2021 21:09:52 - INFO - __main__ - Step 44498: {'lr': 0.0004049942655708287, 'samples': 8543616, 'steps': 44497, 'loss/train': 1.2264952659606934} 08/30/2021 21:09:53 - INFO - __main__ - Step 44499: {'lr': 0.0004049901017585058, 'samples': 8543808, 'steps': 44498, 'loss/train': 1.063349723815918} 08/30/2021 21:09:53 - INFO - __main__ - Step 44500: {'lr': 0.00040498593787634664, 'samples': 8544000, 'steps': 44499, 'loss/train': 1.9578582048416138} 08/30/2021 21:09:53 - INFO - __main__ - Step 44501: {'lr': 0.0004049817739243532, 'samples': 8544192, 'steps': 44500, 'loss/train': 1.4517039060592651} 08/30/2021 21:09:55 - INFO - __main__ - Step 44502: {'lr': 0.0004049776099025274, 'samples': 8544384, 'steps': 44501, 'loss/train': 1.0581343173980713} 08/30/2021 21:09:55 - INFO - __main__ - Step 44503: {'lr': 0.000404973445810871, 'samples': 8544576, 'steps': 44502, 'loss/train': 1.193643569946289} 08/30/2021 21:09:56 - INFO - __main__ - Step 44504: {'lr': 0.00040496928164938614, 'samples': 8544768, 'steps': 44503, 'loss/train': 1.5667099952697754} 08/30/2021 21:09:56 - INFO - __main__ - Step 44505: {'lr': 0.0004049651174180744, 'samples': 8544960, 'steps': 44504, 'loss/train': 1.494455337524414} 08/30/2021 21:09:56 - INFO - __main__ - Step 44506: {'lr': 0.00040496095311693775, 'samples': 8545152, 'steps': 44505, 'loss/train': 1.3121304512023926} 08/30/2021 21:09:57 - INFO - __main__ - Step 44507: {'lr': 0.0004049567887459781, 'samples': 8545344, 'steps': 44506, 'loss/train': 1.0474810600280762} 08/30/2021 21:09:58 - INFO - __main__ - Step 44508: {'lr': 0.0004049526243051973, 'samples': 8545536, 'steps': 44507, 'loss/train': 0.04861311987042427} 08/30/2021 21:09:59 - INFO - __main__ - Step 44509: {'lr': 0.0004049484597945973, 'samples': 8545728, 'steps': 44508, 'loss/train': 2.0066797733306885} 08/30/2021 21:09:59 - INFO - __main__ - Step 44510: {'lr': 0.00040494429521417983, 'samples': 8545920, 'steps': 44509, 'loss/train': 0.8908435106277466} 08/30/2021 21:10:00 - INFO - __main__ - Step 44511: {'lr': 0.0004049401305639469, 'samples': 8546112, 'steps': 44510, 'loss/train': 1.5709240436553955} 08/30/2021 21:10:00 - INFO - __main__ - Step 44512: {'lr': 0.00040493596584390034, 'samples': 8546304, 'steps': 44511, 'loss/train': 1.5960265398025513} 08/30/2021 21:10:02 - INFO - __main__ - Step 44513: {'lr': 0.00040493180105404203, 'samples': 8546496, 'steps': 44512, 'loss/train': 1.4478884935379028} 08/30/2021 21:10:02 - INFO - __main__ - Step 44514: {'lr': 0.0004049276361943738, 'samples': 8546688, 'steps': 44513, 'loss/train': 0.0514056570827961} 08/30/2021 21:10:02 - INFO - __main__ - Step 44515: {'lr': 0.0004049234712648976, 'samples': 8546880, 'steps': 44514, 'loss/train': 1.0247831344604492} 08/30/2021 21:10:03 - INFO - __main__ - Step 44516: {'lr': 0.00040491930626561525, 'samples': 8547072, 'steps': 44515, 'loss/train': 1.5291014909744263} 08/30/2021 21:10:03 - INFO - __main__ - Step 44517: {'lr': 0.00040491514119652875, 'samples': 8547264, 'steps': 44516, 'loss/train': 1.1822515726089478} 08/30/2021 21:10:03 - INFO - __main__ - Step 44518: {'lr': 0.00040491097605763974, 'samples': 8547456, 'steps': 44517, 'loss/train': 1.1921422481536865} 08/30/2021 21:10:05 - INFO - __main__ - Step 44519: {'lr': 0.00040490681084895034, 'samples': 8547648, 'steps': 44518, 'loss/train': 1.7431014776229858} 08/30/2021 21:10:05 - INFO - __main__ - Step 44520: {'lr': 0.00040490264557046217, 'samples': 8547840, 'steps': 44519, 'loss/train': 0.5104594826698303} 08/30/2021 21:10:06 - INFO - __main__ - Step 44521: {'lr': 0.0004048984802221774, 'samples': 8548032, 'steps': 44520, 'loss/train': 1.6499903202056885} 08/30/2021 21:10:06 - INFO - __main__ - Step 44522: {'lr': 0.0004048943148040977, 'samples': 8548224, 'steps': 44521, 'loss/train': 1.3680845499038696} 08/30/2021 21:10:06 - INFO - __main__ - Step 44523: {'lr': 0.0004048901493162251, 'samples': 8548416, 'steps': 44522, 'loss/train': 1.0962400436401367} 08/30/2021 21:10:08 - INFO - __main__ - Step 44524: {'lr': 0.00040488598375856133, 'samples': 8548608, 'steps': 44523, 'loss/train': 0.7335981130599976} 08/30/2021 21:10:08 - INFO - __main__ - Step 44525: {'lr': 0.0004048818181311083, 'samples': 8548800, 'steps': 44524, 'loss/train': 1.4960570335388184} 08/30/2021 21:10:09 - INFO - __main__ - Step 44526: {'lr': 0.000404877652433868, 'samples': 8548992, 'steps': 44525, 'loss/train': 0.5900524258613586} 08/30/2021 21:10:09 - INFO - __main__ - Step 44527: {'lr': 0.0004048734866668421, 'samples': 8549184, 'steps': 44526, 'loss/train': 1.2702893018722534} 08/30/2021 21:10:10 - INFO - __main__ - Step 44528: {'lr': 0.0004048693208300327, 'samples': 8549376, 'steps': 44527, 'loss/train': 1.304343581199646} 08/30/2021 21:10:11 - INFO - __main__ - Step 44529: {'lr': 0.00040486515492344145, 'samples': 8549568, 'steps': 44528, 'loss/train': 1.3608784675598145} 08/30/2021 21:10:11 - INFO - __main__ - Step 44530: {'lr': 0.00040486098894707044, 'samples': 8549760, 'steps': 44529, 'loss/train': 0.8541049361228943} 08/30/2021 21:10:12 - INFO - __main__ - Step 44531: {'lr': 0.00040485682290092144, 'samples': 8549952, 'steps': 44530, 'loss/train': 1.5711885690689087} 08/30/2021 21:10:12 - INFO - __main__ - Step 44532: {'lr': 0.0004048526567849964, 'samples': 8550144, 'steps': 44531, 'loss/train': 1.330690622329712} 08/30/2021 21:10:13 - INFO - __main__ - Step 44533: {'lr': 0.00040484849059929705, 'samples': 8550336, 'steps': 44532, 'loss/train': 1.4260104894638062} 08/30/2021 21:10:14 - INFO - __main__ - Step 44534: {'lr': 0.00040484432434382547, 'samples': 8550528, 'steps': 44533, 'loss/train': 1.393811583518982} 08/30/2021 21:10:14 - INFO - __main__ - Step 44535: {'lr': 0.0004048401580185833, 'samples': 8550720, 'steps': 44534, 'loss/train': 1.7350919246673584} 08/30/2021 21:10:15 - INFO - __main__ - Step 44536: {'lr': 0.00040483599162357257, 'samples': 8550912, 'steps': 44535, 'loss/train': 1.83530855178833} 08/30/2021 21:10:15 - INFO - __main__ - Step 44537: {'lr': 0.0004048318251587952, 'samples': 8551104, 'steps': 44536, 'loss/train': 1.079136610031128} 08/30/2021 21:10:16 - INFO - __main__ - Step 44538: {'lr': 0.000404827658624253, 'samples': 8551296, 'steps': 44537, 'loss/train': 1.5141124725341797} 08/30/2021 21:10:17 - INFO - __main__ - Step 44539: {'lr': 0.00040482349201994785, 'samples': 8551488, 'steps': 44538, 'loss/train': 1.415168046951294} 08/30/2021 21:10:17 - INFO - __main__ - Step 44540: {'lr': 0.00040481932534588153, 'samples': 8551680, 'steps': 44539, 'loss/train': 0.9200124740600586} 08/30/2021 21:10:18 - INFO - __main__ - Step 44541: {'lr': 0.00040481515860205607, 'samples': 8551872, 'steps': 44540, 'loss/train': 1.6551047563552856} 08/30/2021 21:10:18 - INFO - __main__ - Step 44542: {'lr': 0.00040481099178847326, 'samples': 8552064, 'steps': 44541, 'loss/train': 1.1200001239776611} 08/30/2021 21:10:18 - INFO - __main__ - Step 44543: {'lr': 0.000404806824905135, 'samples': 8552256, 'steps': 44542, 'loss/train': 1.4508363008499146} 08/30/2021 21:10:19 - INFO - __main__ - Step 44544: {'lr': 0.0004048026579520433, 'samples': 8552448, 'steps': 44543, 'loss/train': 1.4934316873550415} 08/30/2021 21:10:21 - INFO - __main__ - Step 44545: {'lr': 0.00040479849092919974, 'samples': 8552640, 'steps': 44544, 'loss/train': 1.4598311185836792} 08/30/2021 21:10:21 - INFO - __main__ - Step 44546: {'lr': 0.00040479432383660644, 'samples': 8552832, 'steps': 44545, 'loss/train': 1.3036412000656128} 08/30/2021 21:10:22 - INFO - __main__ - Step 44547: {'lr': 0.00040479015667426523, 'samples': 8553024, 'steps': 44546, 'loss/train': 0.9568488597869873} 08/30/2021 21:10:22 - INFO - __main__ - Step 44548: {'lr': 0.00040478598944217794, 'samples': 8553216, 'steps': 44547, 'loss/train': 1.3391884565353394} 08/30/2021 21:10:22 - INFO - __main__ - Step 44549: {'lr': 0.0004047818221403464, 'samples': 8553408, 'steps': 44548, 'loss/train': 1.869517207145691} 08/30/2021 21:10:24 - INFO - __main__ - Step 44550: {'lr': 0.0004047776547687727, 'samples': 8553600, 'steps': 44549, 'loss/train': 2.083289384841919} 08/30/2021 21:10:25 - INFO - __main__ - Step 44551: {'lr': 0.00040477348732745853, 'samples': 8553792, 'steps': 44550, 'loss/train': 1.6396681070327759} 08/30/2021 21:10:25 - INFO - __main__ - Step 44552: {'lr': 0.0004047693198164058, 'samples': 8553984, 'steps': 44551, 'loss/train': 0.03724002093076706} 08/30/2021 21:10:25 - INFO - __main__ - Step 44553: {'lr': 0.0004047651522356164, 'samples': 8554176, 'steps': 44552, 'loss/train': 1.58552086353302} 08/30/2021 21:10:26 - INFO - __main__ - Step 44554: {'lr': 0.0004047609845850922, 'samples': 8554368, 'steps': 44553, 'loss/train': 3.346970319747925} 08/30/2021 21:10:27 - INFO - __main__ - Step 44555: {'lr': 0.0004047568168648351, 'samples': 8554560, 'steps': 44554, 'loss/train': 1.0322961807250977} 08/30/2021 21:10:28 - INFO - __main__ - Step 44556: {'lr': 0.00040475264907484696, 'samples': 8554752, 'steps': 44555, 'loss/train': 1.4441256523132324} 08/30/2021 21:10:28 - INFO - __main__ - Step 44557: {'lr': 0.0004047484812151296, 'samples': 8554944, 'steps': 44556, 'loss/train': 0.47064775228500366} 08/30/2021 21:10:28 - INFO - __main__ - Step 44558: {'lr': 0.00040474431328568506, 'samples': 8555136, 'steps': 44557, 'loss/train': 1.3238126039505005} 08/30/2021 21:10:29 - INFO - __main__ - Step 44559: {'lr': 0.00040474014528651514, 'samples': 8555328, 'steps': 44558, 'loss/train': 1.3393900394439697} 08/30/2021 21:10:31 - INFO - __main__ - Step 44560: {'lr': 0.00040473597721762164, 'samples': 8555520, 'steps': 44559, 'loss/train': 1.0714969635009766} 08/30/2021 21:10:31 - INFO - __main__ - Step 44561: {'lr': 0.00040473180907900645, 'samples': 8555712, 'steps': 44560, 'loss/train': 1.986654281616211} 08/30/2021 21:10:31 - INFO - __main__ - Step 44562: {'lr': 0.0004047276408706716, 'samples': 8555904, 'steps': 44561, 'loss/train': 1.0027275085449219} 08/30/2021 21:10:32 - INFO - __main__ - Step 44563: {'lr': 0.00040472347259261875, 'samples': 8556096, 'steps': 44562, 'loss/train': 1.2030565738677979} 08/30/2021 21:10:32 - INFO - __main__ - Step 44564: {'lr': 0.00040471930424485, 'samples': 8556288, 'steps': 44563, 'loss/train': 0.9676149487495422} 08/30/2021 21:10:34 - INFO - __main__ - Step 44565: {'lr': 0.0004047151358273671, 'samples': 8556480, 'steps': 44564, 'loss/train': 0.5190265774726868} 08/30/2021 21:10:34 - INFO - __main__ - Step 44566: {'lr': 0.00040471096734017185, 'samples': 8556672, 'steps': 44565, 'loss/train': 1.3869503736495972} 08/30/2021 21:10:34 - INFO - __main__ - Step 44567: {'lr': 0.0004047067987832663, 'samples': 8556864, 'steps': 44566, 'loss/train': 1.4650006294250488} 08/30/2021 21:10:35 - INFO - __main__ - Step 44568: {'lr': 0.00040470263015665234, 'samples': 8557056, 'steps': 44567, 'loss/train': 1.9376749992370605} 08/30/2021 21:10:35 - INFO - __main__ - Step 44569: {'lr': 0.00040469846146033164, 'samples': 8557248, 'steps': 44568, 'loss/train': 1.3339883089065552} 08/30/2021 21:10:36 - INFO - __main__ - Step 44570: {'lr': 0.00040469429269430617, 'samples': 8557440, 'steps': 44569, 'loss/train': 1.1745285987854004} 08/30/2021 21:10:37 - INFO - __main__ - Step 44571: {'lr': 0.00040469012385857794, 'samples': 8557632, 'steps': 44570, 'loss/train': 1.4878660440444946} 08/30/2021 21:10:37 - INFO - __main__ - Step 44572: {'lr': 0.0004046859549531487, 'samples': 8557824, 'steps': 44571, 'loss/train': 1.124781847000122} 08/30/2021 21:10:38 - INFO - __main__ - Step 44573: {'lr': 0.0004046817859780203, 'samples': 8558016, 'steps': 44572, 'loss/train': 1.2476392984390259} 08/30/2021 21:10:38 - INFO - __main__ - Step 44574: {'lr': 0.00040467761693319473, 'samples': 8558208, 'steps': 44573, 'loss/train': 1.9991528987884521} 08/30/2021 21:10:39 - INFO - __main__ - Step 44575: {'lr': 0.0004046734478186738, 'samples': 8558400, 'steps': 44574, 'loss/train': 1.5686951875686646} 08/30/2021 21:10:40 - INFO - __main__ - Step 44576: {'lr': 0.0004046692786344594, 'samples': 8558592, 'steps': 44575, 'loss/train': 0.7465823292732239} 08/30/2021 21:10:40 - INFO - __main__ - Step 44577: {'lr': 0.0004046651093805534, 'samples': 8558784, 'steps': 44576, 'loss/train': 1.6808507442474365} 08/30/2021 21:10:41 - INFO - __main__ - Step 44578: {'lr': 0.0004046609400569577, 'samples': 8558976, 'steps': 44577, 'loss/train': 1.4354959726333618} 08/30/2021 21:10:41 - INFO - __main__ - Step 44579: {'lr': 0.00040465677066367424, 'samples': 8559168, 'steps': 44578, 'loss/train': 2.2899327278137207} 08/30/2021 21:10:41 - INFO - __main__ - Step 44580: {'lr': 0.0004046526012007047, 'samples': 8559360, 'steps': 44579, 'loss/train': 1.1801016330718994} 08/30/2021 21:10:43 - INFO - __main__ - Step 44581: {'lr': 0.0004046484316680511, 'samples': 8559552, 'steps': 44580, 'loss/train': 1.6281802654266357} 08/30/2021 21:10:43 - INFO - __main__ - Step 44582: {'lr': 0.0004046442620657154, 'samples': 8559744, 'steps': 44581, 'loss/train': 1.3720782995224} 08/30/2021 21:10:44 - INFO - __main__ - Step 44583: {'lr': 0.00040464009239369925, 'samples': 8559936, 'steps': 44582, 'loss/train': 1.4667978286743164} 08/30/2021 21:10:44 - INFO - __main__ - Step 44584: {'lr': 0.0004046359226520048, 'samples': 8560128, 'steps': 44583, 'loss/train': 1.2026638984680176} 08/30/2021 21:10:44 - INFO - __main__ - Step 44585: {'lr': 0.0004046317528406337, 'samples': 8560320, 'steps': 44584, 'loss/train': 2.0747039318084717} 08/30/2021 21:10:46 - INFO - __main__ - Step 44586: {'lr': 0.0004046275829595879, 'samples': 8560512, 'steps': 44585, 'loss/train': 1.427085280418396} 08/30/2021 21:10:46 - INFO - __main__ - Step 44587: {'lr': 0.0004046234130088694, 'samples': 8560704, 'steps': 44586, 'loss/train': 1.8774505853652954} 08/30/2021 21:10:47 - INFO - __main__ - Step 44588: {'lr': 0.00040461924298847987, 'samples': 8560896, 'steps': 44587, 'loss/train': 1.5450016260147095} 08/30/2021 21:10:47 - INFO - __main__ - Step 44589: {'lr': 0.0004046150728984214, 'samples': 8561088, 'steps': 44588, 'loss/train': 1.47158682346344} 08/30/2021 21:10:47 - INFO - __main__ - Step 44590: {'lr': 0.00040461090273869566, 'samples': 8561280, 'steps': 44589, 'loss/train': 1.338092565536499} 08/30/2021 21:10:49 - INFO - __main__ - Step 44591: {'lr': 0.0004046067325093047, 'samples': 8561472, 'steps': 44590, 'loss/train': 1.5805087089538574} 08/30/2021 21:10:49 - INFO - __main__ - Step 44592: {'lr': 0.00040460256221025025, 'samples': 8561664, 'steps': 44591, 'loss/train': 1.2867668867111206} 08/30/2021 21:10:50 - INFO - __main__ - Step 44593: {'lr': 0.00040459839184153436, 'samples': 8561856, 'steps': 44592, 'loss/train': 0.5937618017196655} 08/30/2021 21:10:50 - INFO - __main__ - Step 44594: {'lr': 0.00040459422140315876, 'samples': 8562048, 'steps': 44593, 'loss/train': 1.3605940341949463} 08/30/2021 21:10:50 - INFO - __main__ - Step 44595: {'lr': 0.00040459005089512544, 'samples': 8562240, 'steps': 44594, 'loss/train': 1.4812759160995483} 08/30/2021 21:10:52 - INFO - __main__ - Step 44596: {'lr': 0.0004045858803174362, 'samples': 8562432, 'steps': 44595, 'loss/train': 0.9486871361732483} 08/30/2021 21:10:52 - INFO - __main__ - Step 44597: {'lr': 0.0004045817096700929, 'samples': 8562624, 'steps': 44596, 'loss/train': 1.0470929145812988} 08/30/2021 21:10:53 - INFO - __main__ - Step 44598: {'lr': 0.0004045775389530976, 'samples': 8562816, 'steps': 44597, 'loss/train': 1.4578419923782349} 08/30/2021 21:10:53 - INFO - __main__ - Step 44599: {'lr': 0.00040457336816645195, 'samples': 8563008, 'steps': 44598, 'loss/train': 1.2007524967193604} 08/30/2021 21:10:53 - INFO - __main__ - Step 44600: {'lr': 0.000404569197310158, 'samples': 8563200, 'steps': 44599, 'loss/train': 0.5367192625999451} 08/30/2021 21:10:54 - INFO - __main__ - Step 44601: {'lr': 0.0004045650263842174, 'samples': 8563392, 'steps': 44600, 'loss/train': 1.443903923034668} 08/30/2021 21:10:56 - INFO - __main__ - Step 44602: {'lr': 0.0004045608553886323, 'samples': 8563584, 'steps': 44601, 'loss/train': 1.5638363361358643} 08/30/2021 21:10:56 - INFO - __main__ - Step 44603: {'lr': 0.0004045566843234044, 'samples': 8563776, 'steps': 44602, 'loss/train': 1.3564800024032593} 08/30/2021 21:10:57 - INFO - __main__ - Step 44604: {'lr': 0.0004045525131885357, 'samples': 8563968, 'steps': 44603, 'loss/train': 1.8736985921859741} 08/30/2021 21:10:57 - INFO - __main__ - Step 44605: {'lr': 0.0004045483419840281, 'samples': 8564160, 'steps': 44604, 'loss/train': 1.6619324684143066} 08/30/2021 21:10:57 - INFO - __main__ - Step 44606: {'lr': 0.00040454417070988325, 'samples': 8564352, 'steps': 44605, 'loss/train': 1.4417486190795898} 08/30/2021 21:10:59 - INFO - __main__ - Step 44607: {'lr': 0.0004045399993661033, 'samples': 8564544, 'steps': 44606, 'loss/train': 1.2746599912643433} 08/30/2021 21:11:00 - INFO - __main__ - Step 44608: {'lr': 0.00040453582795268994, 'samples': 8564736, 'steps': 44607, 'loss/train': 1.128827452659607} 08/30/2021 21:11:00 - INFO - __main__ - Step 44609: {'lr': 0.00040453165646964505, 'samples': 8564928, 'steps': 44608, 'loss/train': 1.4094294309616089} 08/30/2021 21:11:00 - INFO - __main__ - Step 44610: {'lr': 0.00040452748491697074, 'samples': 8565120, 'steps': 44609, 'loss/train': 1.2495408058166504} 08/30/2021 21:11:01 - INFO - __main__ - Step 44611: {'lr': 0.00040452331329466864, 'samples': 8565312, 'steps': 44610, 'loss/train': 1.2370538711547852} 08/30/2021 21:11:02 - INFO - __main__ - Step 44612: {'lr': 0.0004045191416027407, 'samples': 8565504, 'steps': 44611, 'loss/train': 1.7766664028167725} 08/30/2021 21:11:03 - INFO - __main__ - Step 44613: {'lr': 0.0004045149698411889, 'samples': 8565696, 'steps': 44612, 'loss/train': 1.398087501525879} 08/30/2021 21:11:03 - INFO - __main__ - Step 44614: {'lr': 0.000404510798010015, 'samples': 8565888, 'steps': 44613, 'loss/train': 1.3768959045410156} 08/30/2021 21:11:03 - INFO - __main__ - Step 44615: {'lr': 0.0004045066261092209, 'samples': 8566080, 'steps': 44614, 'loss/train': 1.4024088382720947} 08/30/2021 21:11:04 - INFO - __main__ - Step 44616: {'lr': 0.0004045024541388085, 'samples': 8566272, 'steps': 44615, 'loss/train': 1.6499426364898682} 08/30/2021 21:11:06 - INFO - __main__ - Step 44617: {'lr': 0.0004044982820987797, 'samples': 8566464, 'steps': 44616, 'loss/train': 1.173856258392334} 08/30/2021 21:11:06 - INFO - __main__ - Step 44618: {'lr': 0.0004044941099891364, 'samples': 8566656, 'steps': 44617, 'loss/train': 1.4359219074249268} 08/30/2021 21:11:06 - INFO - __main__ - Step 44619: {'lr': 0.0004044899378098803, 'samples': 8566848, 'steps': 44618, 'loss/train': 0.23497290909290314} 08/30/2021 21:11:07 - INFO - __main__ - Step 44620: {'lr': 0.00040448576556101356, 'samples': 8567040, 'steps': 44619, 'loss/train': 0.146611288189888} 08/30/2021 21:11:07 - INFO - __main__ - Step 44621: {'lr': 0.0004044815932425379, 'samples': 8567232, 'steps': 44620, 'loss/train': 1.557465672492981} 08/30/2021 21:11:08 - INFO - __main__ - Step 44622: {'lr': 0.0004044774208544551, 'samples': 8567424, 'steps': 44621, 'loss/train': 1.8804394006729126} 08/30/2021 21:11:09 - INFO - __main__ - Step 44623: {'lr': 0.00040447324839676727, 'samples': 8567616, 'steps': 44622, 'loss/train': 0.31287211179733276} 08/30/2021 21:11:09 - INFO - __main__ - Step 44624: {'lr': 0.00040446907586947614, 'samples': 8567808, 'steps': 44623, 'loss/train': 1.286818265914917} 08/30/2021 21:11:10 - INFO - __main__ - Step 44625: {'lr': 0.0004044649032725836, 'samples': 8568000, 'steps': 44624, 'loss/train': 1.5650722980499268} 08/30/2021 21:11:10 - INFO - __main__ - Step 44626: {'lr': 0.00040446073060609156, 'samples': 8568192, 'steps': 44625, 'loss/train': 1.2029505968093872} 08/30/2021 21:11:10 - INFO - __main__ - Step 44627: {'lr': 0.00040445655787000196, 'samples': 8568384, 'steps': 44626, 'loss/train': 1.951327919960022} 08/30/2021 21:11:12 - INFO - __main__ - Step 44628: {'lr': 0.0004044523850643166, 'samples': 8568576, 'steps': 44627, 'loss/train': 1.024367332458496} 08/30/2021 21:11:13 - INFO - __main__ - Step 44629: {'lr': 0.0004044482121890374, 'samples': 8568768, 'steps': 44628, 'loss/train': 1.6101847887039185} 08/30/2021 21:11:13 - INFO - __main__ - Step 44630: {'lr': 0.00040444403924416614, 'samples': 8568960, 'steps': 44629, 'loss/train': 0.09740839898586273} 08/30/2021 21:11:13 - INFO - __main__ - Step 44631: {'lr': 0.00040443986622970486, 'samples': 8569152, 'steps': 44630, 'loss/train': 1.6449363231658936} 08/30/2021 21:11:14 - INFO - __main__ - Step 44632: {'lr': 0.0004044356931456553, 'samples': 8569344, 'steps': 44631, 'loss/train': 1.6267058849334717} 08/30/2021 21:11:15 - INFO - __main__ - Step 44633: {'lr': 0.00040443151999201946, 'samples': 8569536, 'steps': 44632, 'loss/train': 1.104532241821289} 08/30/2021 21:11:16 - INFO - __main__ - Step 44634: {'lr': 0.00040442734676879907, 'samples': 8569728, 'steps': 44633, 'loss/train': 1.3367877006530762} 08/30/2021 21:11:16 - INFO - __main__ - Step 44635: {'lr': 0.0004044231734759961, 'samples': 8569920, 'steps': 44634, 'loss/train': 1.462814211845398} 08/30/2021 21:11:16 - INFO - __main__ - Step 44636: {'lr': 0.00040441900011361256, 'samples': 8570112, 'steps': 44635, 'loss/train': 1.0984530448913574} 08/30/2021 21:11:17 - INFO - __main__ - Step 44637: {'lr': 0.0004044148266816501, 'samples': 8570304, 'steps': 44636, 'loss/train': 1.2905670404434204} 08/30/2021 21:11:18 - INFO - __main__ - Step 44638: {'lr': 0.0004044106531801107, 'samples': 8570496, 'steps': 44637, 'loss/train': 0.05202246829867363} 08/30/2021 21:11:19 - INFO - __main__ - Step 44639: {'lr': 0.0004044064796089963, 'samples': 8570688, 'steps': 44638, 'loss/train': 1.5542014837265015} 08/30/2021 21:11:19 - INFO - __main__ - Step 44640: {'lr': 0.0004044023059683087, 'samples': 8570880, 'steps': 44639, 'loss/train': 2.373070001602173} 08/30/2021 21:11:20 - INFO - __main__ - Step 44641: {'lr': 0.00040439813225804977, 'samples': 8571072, 'steps': 44640, 'loss/train': 1.9628074169158936} 08/30/2021 21:11:20 - INFO - __main__ - Step 44642: {'lr': 0.00040439395847822145, 'samples': 8571264, 'steps': 44641, 'loss/train': 1.1866061687469482} 08/30/2021 21:11:20 - INFO - __main__ - Step 44643: {'lr': 0.00040438978462882557, 'samples': 8571456, 'steps': 44642, 'loss/train': 1.1060564517974854} 08/30/2021 21:11:22 - INFO - __main__ - Step 44644: {'lr': 0.0004043856107098641, 'samples': 8571648, 'steps': 44643, 'loss/train': 1.6540125608444214} 08/30/2021 21:11:22 - INFO - __main__ - Step 44645: {'lr': 0.0004043814367213388, 'samples': 8571840, 'steps': 44644, 'loss/train': 1.6237667798995972} 08/30/2021 21:11:23 - INFO - __main__ - Step 44646: {'lr': 0.00040437726266325164, 'samples': 8572032, 'steps': 44645, 'loss/train': 1.1387388706207275} 08/30/2021 21:11:23 - INFO - __main__ - Step 44647: {'lr': 0.00040437308853560444, 'samples': 8572224, 'steps': 44646, 'loss/train': 1.3084309101104736} 08/30/2021 21:11:23 - INFO - __main__ - Step 44648: {'lr': 0.0004043689143383991, 'samples': 8572416, 'steps': 44647, 'loss/train': 1.6508070230484009} 08/30/2021 21:11:25 - INFO - __main__ - Step 44649: {'lr': 0.00040436474007163754, 'samples': 8572608, 'steps': 44648, 'loss/train': 1.7929701805114746} 08/30/2021 21:11:25 - INFO - __main__ - Step 44650: {'lr': 0.0004043605657353216, 'samples': 8572800, 'steps': 44649, 'loss/train': 1.3815667629241943} 08/30/2021 21:11:25 - INFO - __main__ - Step 44651: {'lr': 0.00040435639132945314, 'samples': 8572992, 'steps': 44650, 'loss/train': 1.6113414764404297} 08/30/2021 21:11:26 - INFO - __main__ - Step 44652: {'lr': 0.0004043522168540341, 'samples': 8573184, 'steps': 44651, 'loss/train': 1.4216866493225098} 08/30/2021 21:11:26 - INFO - __main__ - Step 44653: {'lr': 0.0004043480423090664, 'samples': 8573376, 'steps': 44652, 'loss/train': 1.890062689781189} 08/30/2021 21:11:29 - INFO - __main__ - Step 44654: {'lr': 0.0004043438676945518, 'samples': 8573568, 'steps': 44653, 'loss/train': 1.3811109066009521} 08/30/2021 21:11:29 - INFO - __main__ - Step 44655: {'lr': 0.0004043396930104922, 'samples': 8573760, 'steps': 44654, 'loss/train': 0.7382684946060181} 08/30/2021 21:11:30 - INFO - __main__ - Step 44656: {'lr': 0.0004043355182568895, 'samples': 8573952, 'steps': 44655, 'loss/train': 1.6606881618499756} 08/30/2021 21:11:30 - INFO - __main__ - Step 44657: {'lr': 0.00040433134343374565, 'samples': 8574144, 'steps': 44656, 'loss/train': 1.5059059858322144} 08/30/2021 21:11:30 - INFO - __main__ - Step 44658: {'lr': 0.0004043271685410625, 'samples': 8574336, 'steps': 44657, 'loss/train': 1.1747535467147827} 08/30/2021 21:11:31 - INFO - __main__ - Step 44659: {'lr': 0.00040432299357884185, 'samples': 8574528, 'steps': 44658, 'loss/train': 0.9353310465812683} 08/30/2021 21:11:33 - INFO - __main__ - Step 44660: {'lr': 0.0004043188185470856, 'samples': 8574720, 'steps': 44659, 'loss/train': 0.7692214250564575} 08/30/2021 21:11:33 - INFO - __main__ - Step 44661: {'lr': 0.00040431464344579585, 'samples': 8574912, 'steps': 44660, 'loss/train': 1.4351422786712646} 08/30/2021 21:11:33 - INFO - __main__ - Step 44662: {'lr': 0.00040431046827497415, 'samples': 8575104, 'steps': 44661, 'loss/train': 0.36177942156791687} 08/30/2021 21:11:34 - INFO - __main__ - Step 44663: {'lr': 0.00040430629303462256, 'samples': 8575296, 'steps': 44662, 'loss/train': 1.2546839714050293} 08/30/2021 21:11:34 - INFO - __main__ - Step 44664: {'lr': 0.000404302117724743, 'samples': 8575488, 'steps': 44663, 'loss/train': 0.21498185396194458} 08/30/2021 21:11:36 - INFO - __main__ - Step 44665: {'lr': 0.00040429794234533726, 'samples': 8575680, 'steps': 44664, 'loss/train': 0.13312803208827972} 08/30/2021 21:11:36 - INFO - __main__ - Step 44666: {'lr': 0.0004042937668964072, 'samples': 8575872, 'steps': 44665, 'loss/train': 1.3231137990951538} 08/30/2021 21:11:36 - INFO - __main__ - Step 44667: {'lr': 0.00040428959137795475, 'samples': 8576064, 'steps': 44666, 'loss/train': 1.6441969871520996} 08/30/2021 21:11:37 - INFO - __main__ - Step 44668: {'lr': 0.0004042854157899818, 'samples': 8576256, 'steps': 44667, 'loss/train': 1.4304097890853882} 08/30/2021 21:11:37 - INFO - __main__ - Step 44669: {'lr': 0.0004042812401324902, 'samples': 8576448, 'steps': 44668, 'loss/train': 1.2681901454925537} 08/30/2021 21:11:39 - INFO - __main__ - Step 44670: {'lr': 0.0004042770644054819, 'samples': 8576640, 'steps': 44669, 'loss/train': 1.4806114435195923} 08/30/2021 21:11:39 - INFO - __main__ - Step 44671: {'lr': 0.0004042728886089587, 'samples': 8576832, 'steps': 44670, 'loss/train': 1.3516522645950317} 08/30/2021 21:11:39 - INFO - __main__ - Step 44672: {'lr': 0.00040426871274292257, 'samples': 8577024, 'steps': 44671, 'loss/train': 1.53693425655365} 08/30/2021 21:11:40 - INFO - __main__ - Step 44673: {'lr': 0.00040426453680737534, 'samples': 8577216, 'steps': 44672, 'loss/train': 1.702268123626709} 08/30/2021 21:11:40 - INFO - __main__ - Step 44674: {'lr': 0.0004042603608023189, 'samples': 8577408, 'steps': 44673, 'loss/train': 0.33006757497787476} 08/30/2021 21:11:42 - INFO - __main__ - Step 44675: {'lr': 0.00040425618472775504, 'samples': 8577600, 'steps': 44674, 'loss/train': 0.7661734223365784} 08/30/2021 21:11:42 - INFO - __main__ - Step 44676: {'lr': 0.0004042520085836857, 'samples': 8577792, 'steps': 44675, 'loss/train': 0.9462581276893616} 08/30/2021 21:11:43 - INFO - __main__ - Step 44677: {'lr': 0.0004042478323701129, 'samples': 8577984, 'steps': 44676, 'loss/train': 1.4574273824691772} 08/30/2021 21:11:43 - INFO - __main__ - Step 44678: {'lr': 0.00040424365608703836, 'samples': 8578176, 'steps': 44677, 'loss/train': 0.20433904230594635} 08/30/2021 21:11:43 - INFO - __main__ - Step 44679: {'lr': 0.00040423947973446404, 'samples': 8578368, 'steps': 44678, 'loss/train': 1.3947556018829346} 08/30/2021 21:11:45 - INFO - __main__ - Step 44680: {'lr': 0.00040423530331239177, 'samples': 8578560, 'steps': 44679, 'loss/train': 1.6145468950271606} 08/30/2021 21:11:45 - INFO - __main__ - Step 44681: {'lr': 0.0004042311268208234, 'samples': 8578752, 'steps': 44680, 'loss/train': 1.1512095928192139} 08/30/2021 21:11:46 - INFO - __main__ - Step 44682: {'lr': 0.00040422695025976084, 'samples': 8578944, 'steps': 44681, 'loss/train': 1.4892487525939941} 08/30/2021 21:11:46 - INFO - __main__ - Step 44683: {'lr': 0.00040422277362920614, 'samples': 8579136, 'steps': 44682, 'loss/train': 0.6761452555656433} 08/30/2021 21:11:46 - INFO - __main__ - Step 44684: {'lr': 0.0004042185969291609, 'samples': 8579328, 'steps': 44683, 'loss/train': 1.565118432044983} 08/30/2021 21:11:47 - INFO - __main__ - Step 44685: {'lr': 0.00040421442015962727, 'samples': 8579520, 'steps': 44684, 'loss/train': 1.8606051206588745} 08/30/2021 21:11:48 - INFO - __main__ - Step 44686: {'lr': 0.0004042102433206069, 'samples': 8579712, 'steps': 44685, 'loss/train': 1.0377438068389893} 08/30/2021 21:11:48 - INFO - __main__ - Step 44687: {'lr': 0.0004042060664121018, 'samples': 8579904, 'steps': 44686, 'loss/train': 2.0329248905181885} 08/30/2021 21:11:49 - INFO - __main__ - Step 44688: {'lr': 0.00040420188943411385, 'samples': 8580096, 'steps': 44687, 'loss/train': 1.2740154266357422} 08/30/2021 21:11:49 - INFO - __main__ - Step 44689: {'lr': 0.0004041977123866448, 'samples': 8580288, 'steps': 44688, 'loss/train': 1.4535404443740845} 08/30/2021 21:11:50 - INFO - __main__ - Step 44690: {'lr': 0.0004041935352696968, 'samples': 8580480, 'steps': 44689, 'loss/train': 1.383649230003357} 08/30/2021 21:11:51 - INFO - __main__ - Step 44691: {'lr': 0.00040418935808327153, 'samples': 8580672, 'steps': 44690, 'loss/train': 1.1525440216064453} 08/30/2021 21:11:52 - INFO - __main__ - Step 44692: {'lr': 0.00040418518082737087, 'samples': 8580864, 'steps': 44691, 'loss/train': 1.4060755968093872} 08/30/2021 21:11:52 - INFO - __main__ - Step 44693: {'lr': 0.0004041810035019967, 'samples': 8581056, 'steps': 44692, 'loss/train': 1.3666003942489624} 08/30/2021 21:11:53 - INFO - __main__ - Step 44694: {'lr': 0.00040417682610715107, 'samples': 8581248, 'steps': 44693, 'loss/train': 1.4005112648010254} 08/30/2021 21:11:53 - INFO - __main__ - Step 44695: {'lr': 0.00040417264864283563, 'samples': 8581440, 'steps': 44694, 'loss/train': 1.1218857765197754} 08/30/2021 21:11:53 - INFO - __main__ - Step 44696: {'lr': 0.00040416847110905243, 'samples': 8581632, 'steps': 44695, 'loss/train': 2.3378443717956543} 08/30/2021 21:11:55 - INFO - __main__ - Step 44697: {'lr': 0.0004041642935058033, 'samples': 8581824, 'steps': 44696, 'loss/train': 4.12662935256958} 08/30/2021 21:11:55 - INFO - __main__ - Step 44698: {'lr': 0.0004041601158330901, 'samples': 8582016, 'steps': 44697, 'loss/train': 1.7522892951965332} 08/30/2021 21:11:56 - INFO - __main__ - Step 44699: {'lr': 0.0004041559380909148, 'samples': 8582208, 'steps': 44698, 'loss/train': 2.321178913116455} 08/30/2021 21:11:56 - INFO - __main__ - Step 44700: {'lr': 0.00040415176027927915, 'samples': 8582400, 'steps': 44699, 'loss/train': 1.611406922340393} 08/30/2021 21:11:56 - INFO - __main__ - Step 44701: {'lr': 0.00040414758239818506, 'samples': 8582592, 'steps': 44700, 'loss/train': 1.4158567190170288} 08/30/2021 21:11:58 - INFO - __main__ - Step 44702: {'lr': 0.00040414340444763455, 'samples': 8582784, 'steps': 44701, 'loss/train': 1.0129512548446655} 08/30/2021 21:11:58 - INFO - __main__ - Step 44703: {'lr': 0.0004041392264276292, 'samples': 8582976, 'steps': 44702, 'loss/train': 0.12805743515491486} 08/30/2021 21:11:59 - INFO - __main__ - Step 44704: {'lr': 0.00040413504833817127, 'samples': 8583168, 'steps': 44703, 'loss/train': 1.6544349193572998} 08/30/2021 21:11:59 - INFO - __main__ - Step 44705: {'lr': 0.0004041308701792625, 'samples': 8583360, 'steps': 44704, 'loss/train': 1.9136465787887573} 08/30/2021 21:11:59 - INFO - __main__ - Step 44706: {'lr': 0.00040412669195090466, 'samples': 8583552, 'steps': 44705, 'loss/train': 1.2178682088851929} 08/30/2021 21:12:01 - INFO - __main__ - Step 44707: {'lr': 0.0004041225136530997, 'samples': 8583744, 'steps': 44706, 'loss/train': 0.1818217635154724} 08/30/2021 21:12:02 - INFO - __main__ - Step 44708: {'lr': 0.0004041183352858495, 'samples': 8583936, 'steps': 44707, 'loss/train': 1.3122010231018066} 08/30/2021 21:12:02 - INFO - __main__ - Step 44709: {'lr': 0.00040411415684915596, 'samples': 8584128, 'steps': 44708, 'loss/train': 0.7890591621398926} 08/30/2021 21:12:03 - INFO - __main__ - Step 44710: {'lr': 0.000404109978343021, 'samples': 8584320, 'steps': 44709, 'loss/train': 1.327783226966858} 08/30/2021 21:12:03 - INFO - __main__ - Step 44711: {'lr': 0.0004041057997674464, 'samples': 8584512, 'steps': 44710, 'loss/train': 2.0814294815063477} 08/30/2021 21:12:04 - INFO - __main__ - Step 44712: {'lr': 0.0004041016211224342, 'samples': 8584704, 'steps': 44711, 'loss/train': 2.0686967372894287} 08/30/2021 21:12:05 - INFO - __main__ - Step 44713: {'lr': 0.0004040974424079862, 'samples': 8584896, 'steps': 44712, 'loss/train': 1.5370765924453735} 08/30/2021 21:12:05 - INFO - __main__ - Step 44714: {'lr': 0.00040409326362410416, 'samples': 8585088, 'steps': 44713, 'loss/train': 0.9850499033927917} 08/30/2021 21:12:06 - INFO - __main__ - Step 44715: {'lr': 0.0004040890847707901, 'samples': 8585280, 'steps': 44714, 'loss/train': 1.515038251876831} 08/30/2021 21:12:06 - INFO - __main__ - Step 44716: {'lr': 0.0004040849058480459, 'samples': 8585472, 'steps': 44715, 'loss/train': 1.6759437322616577} 08/30/2021 21:12:08 - INFO - __main__ - Step 44717: {'lr': 0.0004040807268558734, 'samples': 8585664, 'steps': 44716, 'loss/train': 0.9891268610954285} 08/30/2021 21:12:08 - INFO - __main__ - Step 44718: {'lr': 0.0004040765477942745, 'samples': 8585856, 'steps': 44717, 'loss/train': 1.1774619817733765} 08/30/2021 21:12:08 - INFO - __main__ - Step 44719: {'lr': 0.0004040723686632512, 'samples': 8586048, 'steps': 44718, 'loss/train': 0.14400401711463928} 08/30/2021 21:12:09 - INFO - __main__ - Step 44720: {'lr': 0.00040406818946280514, 'samples': 8586240, 'steps': 44719, 'loss/train': 1.463714599609375} 08/30/2021 21:12:09 - INFO - __main__ - Step 44721: {'lr': 0.0004040640101929384, 'samples': 8586432, 'steps': 44720, 'loss/train': 1.3119109869003296} 08/30/2021 21:12:10 - INFO - __main__ - Step 44722: {'lr': 0.0004040598308536527, 'samples': 8586624, 'steps': 44721, 'loss/train': 2.74611496925354} 08/30/2021 21:12:11 - INFO - __main__ - Step 44723: {'lr': 0.0004040556514449501, 'samples': 8586816, 'steps': 44722, 'loss/train': 0.10382609814405441} 08/30/2021 21:12:11 - INFO - __main__ - Step 44724: {'lr': 0.0004040514719668324, 'samples': 8587008, 'steps': 44723, 'loss/train': 1.820826768875122} 08/30/2021 21:12:12 - INFO - __main__ - Step 44725: {'lr': 0.00040404729241930144, 'samples': 8587200, 'steps': 44724, 'loss/train': 1.4273552894592285} 08/30/2021 21:12:12 - INFO - __main__ - Step 44726: {'lr': 0.0004040431128023592, 'samples': 8587392, 'steps': 44725, 'loss/train': 1.0794281959533691} 08/30/2021 21:12:12 - INFO - __main__ - Step 44727: {'lr': 0.0004040389331160075, 'samples': 8587584, 'steps': 44726, 'loss/train': 0.5066059231758118} 08/30/2021 21:12:14 - INFO - __main__ - Step 44728: {'lr': 0.00040403475336024816, 'samples': 8587776, 'steps': 44727, 'loss/train': 1.3578089475631714} 08/30/2021 21:12:14 - INFO - __main__ - Step 44729: {'lr': 0.0004040305735350832, 'samples': 8587968, 'steps': 44728, 'loss/train': 1.3866970539093018} 08/30/2021 21:12:15 - INFO - __main__ - Step 44730: {'lr': 0.00040402639364051443, 'samples': 8588160, 'steps': 44729, 'loss/train': 1.7742223739624023} 08/30/2021 21:12:15 - INFO - __main__ - Step 44731: {'lr': 0.0004040222136765437, 'samples': 8588352, 'steps': 44730, 'loss/train': 1.0697300434112549} 08/30/2021 21:12:15 - INFO - __main__ - Step 44732: {'lr': 0.000404018033643173, 'samples': 8588544, 'steps': 44731, 'loss/train': 1.42644464969635} 08/30/2021 21:12:17 - INFO - __main__ - Step 44733: {'lr': 0.00040401385354040415, 'samples': 8588736, 'steps': 44732, 'loss/train': 1.4834192991256714} 08/30/2021 21:12:18 - INFO - __main__ - Step 44734: {'lr': 0.00040400967336823903, 'samples': 8588928, 'steps': 44733, 'loss/train': 0.5549272298812866} 08/30/2021 21:12:18 - INFO - __main__ - Step 44735: {'lr': 0.0004040054931266795, 'samples': 8589120, 'steps': 44734, 'loss/train': 1.0352789163589478} 08/30/2021 21:12:19 - INFO - __main__ - Step 44736: {'lr': 0.0004040013128157275, 'samples': 8589312, 'steps': 44735, 'loss/train': 1.5035122632980347} 08/30/2021 21:12:19 - INFO - __main__ - Step 44737: {'lr': 0.00040399713243538483, 'samples': 8589504, 'steps': 44736, 'loss/train': 1.7758814096450806} 08/30/2021 21:12:19 - INFO - __main__ - Step 44738: {'lr': 0.00040399295198565344, 'samples': 8589696, 'steps': 44737, 'loss/train': 1.4000332355499268} 08/30/2021 21:12:21 - INFO - __main__ - Step 44739: {'lr': 0.0004039887714665352, 'samples': 8589888, 'steps': 44738, 'loss/train': 1.2474510669708252} 08/30/2021 21:12:21 - INFO - __main__ - Step 44740: {'lr': 0.0004039845908780321, 'samples': 8590080, 'steps': 44739, 'loss/train': 0.25095704197883606} 08/30/2021 21:12:22 - INFO - __main__ - Step 44741: {'lr': 0.00040398041022014585, 'samples': 8590272, 'steps': 44740, 'loss/train': 0.3515515625476837} 08/30/2021 21:12:22 - INFO - __main__ - Step 44742: {'lr': 0.0004039762294928784, 'samples': 8590464, 'steps': 44741, 'loss/train': 1.3373171091079712} 08/30/2021 21:12:23 - INFO - __main__ - Step 44743: {'lr': 0.0004039720486962316, 'samples': 8590656, 'steps': 44742, 'loss/train': 1.7016260623931885} 08/30/2021 21:12:23 - INFO - __main__ - Step 44744: {'lr': 0.00040396786783020747, 'samples': 8590848, 'steps': 44743, 'loss/train': 1.3754642009735107} 08/30/2021 21:12:24 - INFO - __main__ - Step 44745: {'lr': 0.00040396368689480766, 'samples': 8591040, 'steps': 44744, 'loss/train': 1.0809239149093628} 08/30/2021 21:12:25 - INFO - __main__ - Step 44746: {'lr': 0.00040395950589003425, 'samples': 8591232, 'steps': 44745, 'loss/train': 1.9665225744247437} 08/30/2021 21:12:25 - INFO - __main__ - Step 44747: {'lr': 0.00040395532481588914, 'samples': 8591424, 'steps': 44746, 'loss/train': 1.4787989854812622} 08/30/2021 21:12:25 - INFO - __main__ - Step 44748: {'lr': 0.00040395114367237407, 'samples': 8591616, 'steps': 44747, 'loss/train': 1.827306866645813} 08/30/2021 21:12:26 - INFO - __main__ - Step 44749: {'lr': 0.00040394696245949093, 'samples': 8591808, 'steps': 44748, 'loss/train': 1.3914703130722046} 08/30/2021 21:12:27 - INFO - __main__ - Step 44750: {'lr': 0.0004039427811772417, 'samples': 8592000, 'steps': 44749, 'loss/train': 1.7765800952911377} 08/30/2021 21:12:28 - INFO - __main__ - Step 44751: {'lr': 0.0004039385998256283, 'samples': 8592192, 'steps': 44750, 'loss/train': 1.7809475660324097} 08/30/2021 21:12:28 - INFO - __main__ - Step 44752: {'lr': 0.0004039344184046525, 'samples': 8592384, 'steps': 44751, 'loss/train': 1.1189547777175903} 08/30/2021 21:12:28 - INFO - __main__ - Step 44753: {'lr': 0.00040393023691431617, 'samples': 8592576, 'steps': 44752, 'loss/train': 1.2198259830474854} 08/30/2021 21:12:29 - INFO - __main__ - Step 44754: {'lr': 0.00040392605535462137, 'samples': 8592768, 'steps': 44753, 'loss/train': 1.5017012357711792} 08/30/2021 21:12:29 - INFO - __main__ - Step 44755: {'lr': 0.00040392187372556977, 'samples': 8592960, 'steps': 44754, 'loss/train': 1.3450887203216553} 08/30/2021 21:12:31 - INFO - __main__ - Step 44756: {'lr': 0.00040391769202716333, 'samples': 8593152, 'steps': 44755, 'loss/train': 1.689627766609192} 08/30/2021 21:12:31 - INFO - __main__ - Step 44757: {'lr': 0.00040391351025940406, 'samples': 8593344, 'steps': 44756, 'loss/train': 2.285498857498169} 08/30/2021 21:12:31 - INFO - __main__ - Step 44758: {'lr': 0.00040390932842229363, 'samples': 8593536, 'steps': 44757, 'loss/train': 1.3162336349487305} 08/30/2021 21:12:32 - INFO - __main__ - Step 44759: {'lr': 0.0004039051465158341, 'samples': 8593728, 'steps': 44758, 'loss/train': 1.2031238079071045} 08/30/2021 21:12:32 - INFO - __main__ - Step 44760: {'lr': 0.0004039009645400272, 'samples': 8593920, 'steps': 44759, 'loss/train': 2.238046407699585} 08/30/2021 21:12:34 - INFO - __main__ - Step 44761: {'lr': 0.00040389678249487504, 'samples': 8594112, 'steps': 44760, 'loss/train': 1.9598907232284546} 08/30/2021 21:12:34 - INFO - __main__ - Step 44762: {'lr': 0.00040389260038037924, 'samples': 8594304, 'steps': 44761, 'loss/train': 1.3632460832595825} 08/30/2021 21:12:34 - INFO - __main__ - Step 44763: {'lr': 0.0004038884181965419, 'samples': 8594496, 'steps': 44762, 'loss/train': 1.8618515729904175} 08/30/2021 21:12:35 - INFO - __main__ - Step 44764: {'lr': 0.0004038842359433647, 'samples': 8594688, 'steps': 44763, 'loss/train': 1.0962245464324951} 08/30/2021 21:12:35 - INFO - __main__ - Step 44765: {'lr': 0.0004038800536208497, 'samples': 8594880, 'steps': 44764, 'loss/train': 1.3337403535842896} 08/30/2021 21:12:37 - INFO - __main__ - Step 44766: {'lr': 0.00040387587122899877, 'samples': 8595072, 'steps': 44765, 'loss/train': 1.6342111825942993} 08/30/2021 21:12:38 - INFO - __main__ - Step 44767: {'lr': 0.0004038716887678137, 'samples': 8595264, 'steps': 44766, 'loss/train': 1.220460295677185} 08/30/2021 21:12:38 - INFO - __main__ - Step 44768: {'lr': 0.0004038675062372964, 'samples': 8595456, 'steps': 44767, 'loss/train': 0.762306809425354} 08/30/2021 21:12:38 - INFO - __main__ - Step 44769: {'lr': 0.00040386332363744884, 'samples': 8595648, 'steps': 44768, 'loss/train': 1.6427874565124512} 08/30/2021 21:12:39 - INFO - __main__ - Step 44770: {'lr': 0.0004038591409682728, 'samples': 8595840, 'steps': 44769, 'loss/train': 1.0624582767486572} 08/30/2021 21:12:40 - INFO - __main__ - Step 44771: {'lr': 0.00040385495822977015, 'samples': 8596032, 'steps': 44770, 'loss/train': 1.3694335222244263} 08/30/2021 21:12:41 - INFO - __main__ - Step 44772: {'lr': 0.00040385077542194294, 'samples': 8596224, 'steps': 44771, 'loss/train': 0.9849164485931396} 08/30/2021 21:12:41 - INFO - __main__ - Step 44773: {'lr': 0.0004038465925447929, 'samples': 8596416, 'steps': 44772, 'loss/train': 1.452582836151123} 08/30/2021 21:12:42 - INFO - __main__ - Step 44774: {'lr': 0.00040384240959832196, 'samples': 8596608, 'steps': 44773, 'loss/train': 1.5353108644485474} 08/30/2021 21:12:42 - INFO - __main__ - Step 44775: {'lr': 0.000403838226582532, 'samples': 8596800, 'steps': 44774, 'loss/train': 1.2722387313842773} 08/30/2021 21:12:43 - INFO - __main__ - Step 44776: {'lr': 0.00040383404349742484, 'samples': 8596992, 'steps': 44775, 'loss/train': 0.08614099025726318} 08/30/2021 21:12:44 - INFO - __main__ - Step 44777: {'lr': 0.0004038298603430025, 'samples': 8597184, 'steps': 44776, 'loss/train': 1.6187736988067627} 08/30/2021 21:12:44 - INFO - __main__ - Step 44778: {'lr': 0.0004038256771192668, 'samples': 8597376, 'steps': 44777, 'loss/train': 1.1794672012329102} 08/30/2021 21:12:44 - INFO - __main__ - Step 44779: {'lr': 0.00040382149382621967, 'samples': 8597568, 'steps': 44778, 'loss/train': 1.0087658166885376} 08/30/2021 21:12:45 - INFO - __main__ - Step 44780: {'lr': 0.00040381731046386295, 'samples': 8597760, 'steps': 44779, 'loss/train': 1.5379784107208252} 08/30/2021 21:12:46 - INFO - __main__ - Step 44781: {'lr': 0.0004038131270321984, 'samples': 8597952, 'steps': 44780, 'loss/train': 1.3625178337097168} 08/30/2021 21:12:47 - INFO - __main__ - Step 44782: {'lr': 0.0004038089435312281, 'samples': 8598144, 'steps': 44781, 'loss/train': 1.5956666469573975} 08/30/2021 21:12:47 - INFO - __main__ - Step 44783: {'lr': 0.0004038047599609539, 'samples': 8598336, 'steps': 44782, 'loss/train': 0.7987320423126221} 08/30/2021 21:12:48 - INFO - __main__ - Step 44784: {'lr': 0.00040380057632137756, 'samples': 8598528, 'steps': 44783, 'loss/train': 1.4341366291046143} 08/30/2021 21:12:48 - INFO - __main__ - Step 44785: {'lr': 0.0004037963926125011, 'samples': 8598720, 'steps': 44784, 'loss/train': 0.057333629578351974} 08/30/2021 21:12:49 - INFO - __main__ - Step 44786: {'lr': 0.00040379220883432644, 'samples': 8598912, 'steps': 44785, 'loss/train': 1.1526473760604858} 08/30/2021 21:12:50 - INFO - __main__ - Step 44787: {'lr': 0.0004037880249868553, 'samples': 8599104, 'steps': 44786, 'loss/train': 1.2982807159423828} 08/30/2021 21:12:50 - INFO - __main__ - Step 44788: {'lr': 0.00040378384107008967, 'samples': 8599296, 'steps': 44787, 'loss/train': 1.4623582363128662} 08/30/2021 21:12:51 - INFO - __main__ - Step 44789: {'lr': 0.00040377965708403133, 'samples': 8599488, 'steps': 44788, 'loss/train': 1.7044297456741333} 08/30/2021 21:12:51 - INFO - __main__ - Step 44790: {'lr': 0.00040377547302868235, 'samples': 8599680, 'steps': 44789, 'loss/train': 1.9895410537719727} 08/30/2021 21:12:51 - INFO - __main__ - Step 44791: {'lr': 0.00040377128890404444, 'samples': 8599872, 'steps': 44790, 'loss/train': 1.7813513278961182} 08/30/2021 21:12:53 - INFO - __main__ - Step 44792: {'lr': 0.00040376710471011967, 'samples': 8600064, 'steps': 44791, 'loss/train': 1.7507117986679077} 08/30/2021 21:12:53 - INFO - __main__ - Step 44793: {'lr': 0.0004037629204469098, 'samples': 8600256, 'steps': 44792, 'loss/train': 1.2732532024383545} 08/30/2021 21:12:54 - INFO - __main__ - Step 44794: {'lr': 0.0004037587361144166, 'samples': 8600448, 'steps': 44793, 'loss/train': 1.7000207901000977} 08/30/2021 21:12:54 - INFO - __main__ - Step 44795: {'lr': 0.0004037545517126422, 'samples': 8600640, 'steps': 44794, 'loss/train': 0.5240303874015808} 08/30/2021 21:12:54 - INFO - __main__ - Step 44796: {'lr': 0.0004037503672415883, 'samples': 8600832, 'steps': 44795, 'loss/train': 1.7082513570785522} 08/30/2021 21:12:56 - INFO - __main__ - Step 44797: {'lr': 0.000403746182701257, 'samples': 8601024, 'steps': 44796, 'loss/train': 1.4022642374038696} 08/30/2021 21:12:56 - INFO - __main__ - Step 44798: {'lr': 0.0004037419980916499, 'samples': 8601216, 'steps': 44797, 'loss/train': 1.2172809839248657} 08/30/2021 21:12:57 - INFO - __main__ - Step 44799: {'lr': 0.00040373781341276904, 'samples': 8601408, 'steps': 44798, 'loss/train': 1.5933799743652344} 08/30/2021 21:12:57 - INFO - __main__ - Step 44800: {'lr': 0.00040373362866461633, 'samples': 8601600, 'steps': 44799, 'loss/train': 1.5234166383743286} 08/30/2021 21:12:57 - INFO - __main__ - Step 44801: {'lr': 0.0004037294438471936, 'samples': 8601792, 'steps': 44800, 'loss/train': 1.8410542011260986} 08/30/2021 21:12:59 - INFO - __main__ - Step 44802: {'lr': 0.00040372525896050285, 'samples': 8601984, 'steps': 44801, 'loss/train': 1.719411849975586} 08/30/2021 21:12:59 - INFO - __main__ - Step 44803: {'lr': 0.0004037210740045457, 'samples': 8602176, 'steps': 44802, 'loss/train': 0.5989000797271729} 08/30/2021 21:13:00 - INFO - __main__ - Step 44804: {'lr': 0.0004037168889793243, 'samples': 8602368, 'steps': 44803, 'loss/train': 1.1456217765808105} 08/30/2021 21:13:00 - INFO - __main__ - Step 44805: {'lr': 0.0004037127038848404, 'samples': 8602560, 'steps': 44804, 'loss/train': 1.4343721866607666} 08/30/2021 21:13:00 - INFO - __main__ - Step 44806: {'lr': 0.00040370851872109604, 'samples': 8602752, 'steps': 44805, 'loss/train': 0.966774046421051} 08/30/2021 21:13:02 - INFO - __main__ - Step 44807: {'lr': 0.0004037043334880929, 'samples': 8602944, 'steps': 44806, 'loss/train': 1.4352450370788574} 08/30/2021 21:13:02 - INFO - __main__ - Step 44808: {'lr': 0.000403700148185833, 'samples': 8603136, 'steps': 44807, 'loss/train': 1.2813022136688232} 08/30/2021 21:13:03 - INFO - __main__ - Step 44809: {'lr': 0.00040369596281431816, 'samples': 8603328, 'steps': 44808, 'loss/train': 0.12124764919281006} 08/30/2021 21:13:03 - INFO - __main__ - Step 44810: {'lr': 0.0004036917773735502, 'samples': 8603520, 'steps': 44809, 'loss/train': 1.1848020553588867} 08/30/2021 21:13:04 - INFO - __main__ - Step 44811: {'lr': 0.00040368759186353123, 'samples': 8603712, 'steps': 44810, 'loss/train': 0.3524267375469208} 08/30/2021 21:13:05 - INFO - __main__ - Step 44812: {'lr': 0.0004036834062842629, 'samples': 8603904, 'steps': 44811, 'loss/train': 1.1271228790283203} 08/30/2021 21:13:05 - INFO - __main__ - Step 44813: {'lr': 0.00040367922063574735, 'samples': 8604096, 'steps': 44812, 'loss/train': 1.3416420221328735} 08/30/2021 21:13:06 - INFO - __main__ - Step 44814: {'lr': 0.0004036750349179862, 'samples': 8604288, 'steps': 44813, 'loss/train': 1.1397815942764282} 08/30/2021 21:13:06 - INFO - __main__ - Step 44815: {'lr': 0.00040367084913098153, 'samples': 8604480, 'steps': 44814, 'loss/train': 0.9503486752510071} 08/30/2021 21:13:06 - INFO - __main__ - Step 44816: {'lr': 0.000403666663274735, 'samples': 8604672, 'steps': 44815, 'loss/train': 1.4151442050933838} 08/30/2021 21:13:08 - INFO - __main__ - Step 44817: {'lr': 0.0004036624773492488, 'samples': 8604864, 'steps': 44816, 'loss/train': 1.4580477476119995} 08/30/2021 21:13:09 - INFO - __main__ - Step 44818: {'lr': 0.0004036582913545246, 'samples': 8605056, 'steps': 44817, 'loss/train': 1.3998230695724487} 08/30/2021 21:13:09 - INFO - __main__ - Step 44819: {'lr': 0.0004036541052905643, 'samples': 8605248, 'steps': 44818, 'loss/train': 1.0086911916732788} 08/30/2021 21:13:10 - INFO - __main__ - Step 44820: {'lr': 0.0004036499191573699, 'samples': 8605440, 'steps': 44819, 'loss/train': 1.54413640499115} 08/30/2021 21:13:10 - INFO - __main__ - Step 44821: {'lr': 0.00040364573295494316, 'samples': 8605632, 'steps': 44820, 'loss/train': 1.0503805875778198} 08/30/2021 21:13:10 - INFO - __main__ - Step 44822: {'lr': 0.00040364154668328604, 'samples': 8605824, 'steps': 44821, 'loss/train': 1.2390207052230835} 08/30/2021 21:13:13 - INFO - __main__ - Step 44823: {'lr': 0.0004036373603424004, 'samples': 8606016, 'steps': 44822, 'loss/train': 1.408416748046875} 08/30/2021 21:13:14 - INFO - __main__ - Step 44824: {'lr': 0.00040363317393228814, 'samples': 8606208, 'steps': 44823, 'loss/train': 1.9918785095214844} 08/30/2021 21:13:14 - INFO - __main__ - Step 44825: {'lr': 0.00040362898745295117, 'samples': 8606400, 'steps': 44824, 'loss/train': 1.9970000982284546} 08/30/2021 21:13:14 - INFO - __main__ - Step 44826: {'lr': 0.00040362480090439136, 'samples': 8606592, 'steps': 44825, 'loss/train': 1.832792043685913} 08/30/2021 21:13:15 - INFO - __main__ - Step 44827: {'lr': 0.00040362061428661055, 'samples': 8606784, 'steps': 44826, 'loss/train': 1.7892916202545166} 08/30/2021 21:13:15 - INFO - __main__ - Step 44828: {'lr': 0.0004036164275996107, 'samples': 8606976, 'steps': 44827, 'loss/train': 1.4752496480941772} 08/30/2021 21:13:15 - INFO - __main__ - Step 44829: {'lr': 0.00040361224084339365, 'samples': 8607168, 'steps': 44828, 'loss/train': 1.9663931131362915} 08/30/2021 21:13:17 - INFO - __main__ - Step 44830: {'lr': 0.00040360805401796124, 'samples': 8607360, 'steps': 44829, 'loss/train': 1.1984492540359497} 08/30/2021 21:13:17 - INFO - __main__ - Step 44831: {'lr': 0.0004036038671233154, 'samples': 8607552, 'steps': 44830, 'loss/train': 1.2167338132858276} 08/30/2021 21:13:18 - INFO - __main__ - Step 44832: {'lr': 0.00040359968015945814, 'samples': 8607744, 'steps': 44831, 'loss/train': 2.0896899700164795} 08/30/2021 21:13:18 - INFO - __main__ - Step 44833: {'lr': 0.0004035954931263912, 'samples': 8607936, 'steps': 44832, 'loss/train': 1.2225323915481567} 08/30/2021 21:13:19 - INFO - __main__ - Step 44834: {'lr': 0.00040359130602411644, 'samples': 8608128, 'steps': 44833, 'loss/train': 1.1123920679092407} 08/30/2021 21:13:20 - INFO - __main__ - Step 44835: {'lr': 0.0004035871188526358, 'samples': 8608320, 'steps': 44834, 'loss/train': 1.6819673776626587} 08/30/2021 21:13:20 - INFO - __main__ - Step 44836: {'lr': 0.00040358293161195125, 'samples': 8608512, 'steps': 44835, 'loss/train': 1.055145025253296} 08/30/2021 21:13:21 - INFO - __main__ - Step 44837: {'lr': 0.0004035787443020645, 'samples': 8608704, 'steps': 44836, 'loss/train': 1.4019320011138916} 08/30/2021 21:13:21 - INFO - __main__ - Step 44838: {'lr': 0.00040357455692297765, 'samples': 8608896, 'steps': 44837, 'loss/train': 0.7773519158363342} 08/30/2021 21:13:22 - INFO - __main__ - Step 44839: {'lr': 0.0004035703694746924, 'samples': 8609088, 'steps': 44838, 'loss/train': 1.1051130294799805} 08/30/2021 21:13:22 - INFO - __main__ - Step 44840: {'lr': 0.0004035661819572108, 'samples': 8609280, 'steps': 44839, 'loss/train': 1.2858930826187134} 08/30/2021 21:13:23 - INFO - __main__ - Step 44841: {'lr': 0.0004035619943705345, 'samples': 8609472, 'steps': 44840, 'loss/train': 1.8081300258636475} 08/30/2021 21:13:24 - INFO - __main__ - Step 44842: {'lr': 0.0004035578067146657, 'samples': 8609664, 'steps': 44841, 'loss/train': 1.3008902072906494} 08/30/2021 21:13:24 - INFO - __main__ - Step 44843: {'lr': 0.000403553618989606, 'samples': 8609856, 'steps': 44842, 'loss/train': 1.1326730251312256} 08/30/2021 21:13:25 - INFO - __main__ - Step 44844: {'lr': 0.0004035494311953575, 'samples': 8610048, 'steps': 44843, 'loss/train': 1.447136640548706} 08/30/2021 21:13:25 - INFO - __main__ - Step 44845: {'lr': 0.0004035452433319219, 'samples': 8610240, 'steps': 44844, 'loss/train': 0.6824878454208374} 08/30/2021 21:13:26 - INFO - __main__ - Step 44846: {'lr': 0.0004035410553993012, 'samples': 8610432, 'steps': 44845, 'loss/train': 1.9774402379989624} 08/30/2021 21:13:27 - INFO - __main__ - Step 44847: {'lr': 0.00040353686739749733, 'samples': 8610624, 'steps': 44846, 'loss/train': 1.1656694412231445} 08/30/2021 21:13:27 - INFO - __main__ - Step 44848: {'lr': 0.0004035326793265121, 'samples': 8610816, 'steps': 44847, 'loss/train': 1.234243392944336} 08/30/2021 21:13:28 - INFO - __main__ - Step 44849: {'lr': 0.0004035284911863474, 'samples': 8611008, 'steps': 44848, 'loss/train': 1.1792242527008057} 08/30/2021 21:13:28 - INFO - __main__ - Step 44850: {'lr': 0.00040352430297700513, 'samples': 8611200, 'steps': 44849, 'loss/train': 0.7943199872970581} 08/30/2021 21:13:29 - INFO - __main__ - Step 44851: {'lr': 0.00040352011469848713, 'samples': 8611392, 'steps': 44850, 'loss/train': 1.5195316076278687} 08/30/2021 21:13:30 - INFO - __main__ - Step 44852: {'lr': 0.00040351592635079535, 'samples': 8611584, 'steps': 44851, 'loss/train': 1.5766055583953857} 08/30/2021 21:13:30 - INFO - __main__ - Step 44853: {'lr': 0.0004035117379339318, 'samples': 8611776, 'steps': 44852, 'loss/train': 1.315437912940979} 08/30/2021 21:13:31 - INFO - __main__ - Step 44854: {'lr': 0.00040350754944789815, 'samples': 8611968, 'steps': 44853, 'loss/train': 1.4011709690093994} 08/30/2021 21:13:31 - INFO - __main__ - Step 44855: {'lr': 0.0004035033608926963, 'samples': 8612160, 'steps': 44854, 'loss/train': 1.288525938987732} 08/30/2021 21:13:32 - INFO - __main__ - Step 44856: {'lr': 0.0004034991722683282, 'samples': 8612352, 'steps': 44855, 'loss/train': 1.4414703845977783} 08/30/2021 21:13:33 - INFO - __main__ - Step 44857: {'lr': 0.0004034949835747958, 'samples': 8612544, 'steps': 44856, 'loss/train': 1.63954758644104} 08/30/2021 21:13:33 - INFO - __main__ - Step 44858: {'lr': 0.00040349079481210096, 'samples': 8612736, 'steps': 44857, 'loss/train': 1.5960896015167236} 08/30/2021 21:13:34 - INFO - __main__ - Step 44859: {'lr': 0.00040348660598024547, 'samples': 8612928, 'steps': 44858, 'loss/train': 2.125499963760376} 08/30/2021 21:13:34 - INFO - __main__ - Step 44860: {'lr': 0.0004034824170792313, 'samples': 8613120, 'steps': 44859, 'loss/train': 1.7612104415893555} 08/30/2021 21:13:34 - INFO - __main__ - Step 44861: {'lr': 0.0004034782281090603, 'samples': 8613312, 'steps': 44860, 'loss/train': 1.3749823570251465} 08/30/2021 21:13:36 - INFO - __main__ - Step 44862: {'lr': 0.00040347403906973445, 'samples': 8613504, 'steps': 44861, 'loss/train': 1.1683363914489746} 08/30/2021 21:13:37 - INFO - __main__ - Step 44863: {'lr': 0.0004034698499612555, 'samples': 8613696, 'steps': 44862, 'loss/train': 0.06823708862066269} 08/30/2021 21:13:37 - INFO - __main__ - Step 44864: {'lr': 0.00040346566078362545, 'samples': 8613888, 'steps': 44863, 'loss/train': 0.049810729920864105} 08/30/2021 21:13:37 - INFO - __main__ - Step 44865: {'lr': 0.0004034614715368461, 'samples': 8614080, 'steps': 44864, 'loss/train': 1.4070563316345215} 08/30/2021 21:13:38 - INFO - __main__ - Step 44866: {'lr': 0.0004034572822209194, 'samples': 8614272, 'steps': 44865, 'loss/train': 1.8077664375305176} 08/30/2021 21:13:38 - INFO - __main__ - Step 44867: {'lr': 0.00040345309283584726, 'samples': 8614464, 'steps': 44866, 'loss/train': 1.9318798780441284} 08/30/2021 21:13:39 - INFO - __main__ - Step 44868: {'lr': 0.0004034489033816314, 'samples': 8614656, 'steps': 44867, 'loss/train': 0.6336967945098877} 08/30/2021 21:13:40 - INFO - __main__ - Step 44869: {'lr': 0.00040344471385827396, 'samples': 8614848, 'steps': 44868, 'loss/train': 1.1346098184585571} 08/30/2021 21:13:40 - INFO - __main__ - Step 44870: {'lr': 0.00040344052426577665, 'samples': 8615040, 'steps': 44869, 'loss/train': 0.7720788717269897} 08/30/2021 21:13:41 - INFO - __main__ - Step 44871: {'lr': 0.0004034363346041414, 'samples': 8615232, 'steps': 44870, 'loss/train': 1.6827176809310913} 08/30/2021 21:13:41 - INFO - __main__ - Step 44872: {'lr': 0.0004034321448733701, 'samples': 8615424, 'steps': 44871, 'loss/train': 1.4226248264312744} 08/30/2021 21:13:43 - INFO - __main__ - Step 44873: {'lr': 0.00040342795507346464, 'samples': 8615616, 'steps': 44872, 'loss/train': 1.684158205986023} 08/30/2021 21:13:43 - INFO - __main__ - Step 44874: {'lr': 0.000403423765204427, 'samples': 8615808, 'steps': 44873, 'loss/train': 1.4739277362823486} 08/30/2021 21:13:44 - INFO - __main__ - Step 44875: {'lr': 0.0004034195752662589, 'samples': 8616000, 'steps': 44874, 'loss/train': 0.8114175796508789} 08/30/2021 21:13:44 - INFO - __main__ - Step 44876: {'lr': 0.00040341538525896233, 'samples': 8616192, 'steps': 44875, 'loss/train': 1.1240508556365967} 08/30/2021 21:13:44 - INFO - __main__ - Step 44877: {'lr': 0.0004034111951825391, 'samples': 8616384, 'steps': 44876, 'loss/train': 0.12597016990184784} 08/30/2021 21:13:46 - INFO - __main__ - Step 44878: {'lr': 0.00040340700503699116, 'samples': 8616576, 'steps': 44877, 'loss/train': 1.5539361238479614} 08/30/2021 21:13:47 - INFO - __main__ - Step 44879: {'lr': 0.0004034028148223204, 'samples': 8616768, 'steps': 44878, 'loss/train': 1.5281035900115967} 08/30/2021 21:13:47 - INFO - __main__ - Step 44880: {'lr': 0.0004033986245385288, 'samples': 8616960, 'steps': 44879, 'loss/train': 0.9278026223182678} 08/30/2021 21:13:47 - INFO - __main__ - Step 44881: {'lr': 0.0004033944341856181, 'samples': 8617152, 'steps': 44880, 'loss/train': 1.3097578287124634} 08/30/2021 21:13:48 - INFO - __main__ - Step 44882: {'lr': 0.00040339024376359015, 'samples': 8617344, 'steps': 44881, 'loss/train': 1.283706784248352} 08/30/2021 21:13:49 - INFO - __main__ - Step 44883: {'lr': 0.000403386053272447, 'samples': 8617536, 'steps': 44882, 'loss/train': 1.464145302772522} 08/30/2021 21:13:50 - INFO - __main__ - Step 44884: {'lr': 0.0004033818627121904, 'samples': 8617728, 'steps': 44883, 'loss/train': 0.14013558626174927} 08/30/2021 21:13:50 - INFO - __main__ - Step 44885: {'lr': 0.00040337767208282235, 'samples': 8617920, 'steps': 44884, 'loss/train': 1.519673466682434} 08/30/2021 21:13:51 - INFO - __main__ - Step 44886: {'lr': 0.00040337348138434466, 'samples': 8618112, 'steps': 44885, 'loss/train': 2.190647840499878} 08/30/2021 21:13:51 - INFO - __main__ - Step 44887: {'lr': 0.00040336929061675933, 'samples': 8618304, 'steps': 44886, 'loss/train': 2.1774699687957764} 08/30/2021 21:13:51 - INFO - __main__ - Step 44888: {'lr': 0.0004033650997800681, 'samples': 8618496, 'steps': 44887, 'loss/train': 1.4825836420059204} 08/30/2021 21:13:53 - INFO - __main__ - Step 44889: {'lr': 0.00040336090887427284, 'samples': 8618688, 'steps': 44888, 'loss/train': 1.1236737966537476} 08/30/2021 21:13:53 - INFO - __main__ - Step 44890: {'lr': 0.00040335671789937564, 'samples': 8618880, 'steps': 44889, 'loss/train': 1.5144944190979004} 08/30/2021 21:13:54 - INFO - __main__ - Step 44891: {'lr': 0.00040335252685537817, 'samples': 8619072, 'steps': 44890, 'loss/train': 1.1874704360961914} 08/30/2021 21:13:54 - INFO - __main__ - Step 44892: {'lr': 0.0004033483357422825, 'samples': 8619264, 'steps': 44891, 'loss/train': 1.4392975568771362} 08/30/2021 21:13:54 - INFO - __main__ - Step 44893: {'lr': 0.0004033441445600904, 'samples': 8619456, 'steps': 44892, 'loss/train': 1.5645421743392944} 08/30/2021 21:13:56 - INFO - __main__ - Step 44894: {'lr': 0.0004033399533088038, 'samples': 8619648, 'steps': 44893, 'loss/train': 1.152329683303833} 08/30/2021 21:13:57 - INFO - __main__ - Step 44895: {'lr': 0.00040333576198842456, 'samples': 8619840, 'steps': 44894, 'loss/train': 1.283441424369812} 08/30/2021 21:13:57 - INFO - __main__ - Step 44896: {'lr': 0.00040333157059895463, 'samples': 8620032, 'steps': 44895, 'loss/train': 1.3250155448913574} 08/30/2021 21:13:58 - INFO - __main__ - Step 44897: {'lr': 0.0004033273791403959, 'samples': 8620224, 'steps': 44896, 'loss/train': 1.0440212488174438} 08/30/2021 21:13:58 - INFO - __main__ - Step 44898: {'lr': 0.0004033231876127501, 'samples': 8620416, 'steps': 44897, 'loss/train': 0.9838039875030518} 08/30/2021 21:14:00 - INFO - __main__ - Step 44899: {'lr': 0.00040331899601601934, 'samples': 8620608, 'steps': 44898, 'loss/train': 1.089269757270813} 08/30/2021 21:14:00 - INFO - __main__ - Step 44900: {'lr': 0.0004033148043502054, 'samples': 8620800, 'steps': 44899, 'loss/train': 1.3817768096923828} 08/30/2021 21:14:01 - INFO - __main__ - Step 44901: {'lr': 0.00040331061261531014, 'samples': 8620992, 'steps': 44900, 'loss/train': 1.220621109008789} 08/30/2021 21:14:01 - INFO - __main__ - Step 44902: {'lr': 0.0004033064208113355, 'samples': 8621184, 'steps': 44901, 'loss/train': 1.7035713195800781} 08/30/2021 21:14:01 - INFO - __main__ - Step 44903: {'lr': 0.00040330222893828334, 'samples': 8621376, 'steps': 44902, 'loss/train': 0.05508426949381828} 08/30/2021 21:14:02 - INFO - __main__ - Step 44904: {'lr': 0.0004032980369961555, 'samples': 8621568, 'steps': 44903, 'loss/train': 0.047360729426145554} 08/30/2021 21:14:03 - INFO - __main__ - Step 44905: {'lr': 0.000403293844984954, 'samples': 8621760, 'steps': 44904, 'loss/train': 0.61209636926651} 08/30/2021 21:14:04 - INFO - __main__ - Step 44906: {'lr': 0.00040328965290468066, 'samples': 8621952, 'steps': 44905, 'loss/train': 1.838263988494873} 08/30/2021 21:14:04 - INFO - __main__ - Step 44907: {'lr': 0.00040328546075533745, 'samples': 8622144, 'steps': 44906, 'loss/train': 1.6684576272964478} 08/30/2021 21:14:04 - INFO - __main__ - Step 44908: {'lr': 0.00040328126853692606, 'samples': 8622336, 'steps': 44907, 'loss/train': 1.5004563331604004} 08/30/2021 21:14:05 - INFO - __main__ - Step 44909: {'lr': 0.00040327707624944855, 'samples': 8622528, 'steps': 44908, 'loss/train': 2.075423240661621} 08/30/2021 21:14:06 - INFO - __main__ - Step 44910: {'lr': 0.0004032728838929067, 'samples': 8622720, 'steps': 44909, 'loss/train': 1.376769781112671} 08/30/2021 21:14:07 - INFO - __main__ - Step 44911: {'lr': 0.0004032686914673025, 'samples': 8622912, 'steps': 44910, 'loss/train': 1.015067458152771} 08/30/2021 21:14:07 - INFO - __main__ - Step 44912: {'lr': 0.00040326449897263775, 'samples': 8623104, 'steps': 44911, 'loss/train': 1.6484332084655762} 08/30/2021 21:14:07 - INFO - __main__ - Step 44913: {'lr': 0.0004032603064089144, 'samples': 8623296, 'steps': 44912, 'loss/train': 2.6110422611236572} 08/30/2021 21:14:08 - INFO - __main__ - Step 44914: {'lr': 0.00040325611377613435, 'samples': 8623488, 'steps': 44913, 'loss/train': 1.0199846029281616} 08/30/2021 21:14:09 - INFO - __main__ - Step 44915: {'lr': 0.00040325192107429944, 'samples': 8623680, 'steps': 44914, 'loss/train': 1.5279827117919922} 08/30/2021 21:14:10 - INFO - __main__ - Step 44916: {'lr': 0.00040324772830341163, 'samples': 8623872, 'steps': 44915, 'loss/train': 1.4078264236450195} 08/30/2021 21:14:10 - INFO - __main__ - Step 44917: {'lr': 0.0004032435354634726, 'samples': 8624064, 'steps': 44916, 'loss/train': 1.3844274282455444} 08/30/2021 21:14:11 - INFO - __main__ - Step 44918: {'lr': 0.00040323934255448457, 'samples': 8624256, 'steps': 44917, 'loss/train': 1.578859567642212} 08/30/2021 21:14:11 - INFO - __main__ - Step 44919: {'lr': 0.00040323514957644915, 'samples': 8624448, 'steps': 44918, 'loss/train': 1.1246085166931152} 08/30/2021 21:14:11 - INFO - __main__ - Step 44920: {'lr': 0.00040323095652936843, 'samples': 8624640, 'steps': 44919, 'loss/train': 2.017256498336792} 08/30/2021 21:14:13 - INFO - __main__ - Step 44921: {'lr': 0.00040322676341324415, 'samples': 8624832, 'steps': 44920, 'loss/train': 1.0597833395004272} 08/30/2021 21:14:14 - INFO - __main__ - Step 44922: {'lr': 0.0004032225702280783, 'samples': 8625024, 'steps': 44921, 'loss/train': 1.168633222579956} 08/30/2021 21:14:14 - INFO - __main__ - Step 44923: {'lr': 0.00040321837697387264, 'samples': 8625216, 'steps': 44922, 'loss/train': 1.4514899253845215} 08/30/2021 21:14:14 - INFO - __main__ - Step 44924: {'lr': 0.00040321418365062915, 'samples': 8625408, 'steps': 44923, 'loss/train': 1.0002316236495972} 08/30/2021 21:14:15 - INFO - __main__ - Step 44925: {'lr': 0.00040320999025834973, 'samples': 8625600, 'steps': 44924, 'loss/train': 1.454721450805664} 08/30/2021 21:14:16 - INFO - __main__ - Step 44926: {'lr': 0.0004032057967970363, 'samples': 8625792, 'steps': 44925, 'loss/train': 0.06795018911361694} 08/30/2021 21:14:17 - INFO - __main__ - Step 44927: {'lr': 0.0004032016032666907, 'samples': 8625984, 'steps': 44926, 'loss/train': 1.5177743434906006} 08/30/2021 21:14:17 - INFO - __main__ - Step 44928: {'lr': 0.00040319740966731477, 'samples': 8626176, 'steps': 44927, 'loss/train': 1.4378429651260376} 08/30/2021 21:14:17 - INFO - __main__ - Step 44929: {'lr': 0.0004031932159989105, 'samples': 8626368, 'steps': 44928, 'loss/train': 1.5881174802780151} 08/30/2021 21:14:18 - INFO - __main__ - Step 44930: {'lr': 0.0004031890222614797, 'samples': 8626560, 'steps': 44929, 'loss/train': 1.4071862697601318} 08/30/2021 21:14:18 - INFO - __main__ - Step 44931: {'lr': 0.0004031848284550243, 'samples': 8626752, 'steps': 44930, 'loss/train': 1.6574229001998901} 08/30/2021 21:14:20 - INFO - __main__ - Step 44932: {'lr': 0.0004031806345795462, 'samples': 8626944, 'steps': 44931, 'loss/train': 1.4888023138046265} 08/30/2021 21:14:21 - INFO - __main__ - Step 44933: {'lr': 0.0004031764406350472, 'samples': 8627136, 'steps': 44932, 'loss/train': 1.3646762371063232} 08/30/2021 21:14:21 - INFO - __main__ - Step 44934: {'lr': 0.0004031722466215293, 'samples': 8627328, 'steps': 44933, 'loss/train': 0.13535496592521667} 08/30/2021 21:14:22 - INFO - __main__ - Step 44935: {'lr': 0.00040316805253899434, 'samples': 8627520, 'steps': 44934, 'loss/train': 1.5405174493789673} 08/30/2021 21:14:22 - INFO - __main__ - Step 44936: {'lr': 0.0004031638583874443, 'samples': 8627712, 'steps': 44935, 'loss/train': 1.0725810527801514} 08/30/2021 21:14:24 - INFO - __main__ - Step 44937: {'lr': 0.0004031596641668809, 'samples': 8627904, 'steps': 44936, 'loss/train': 1.475506067276001} 08/30/2021 21:14:24 - INFO - __main__ - Step 44938: {'lr': 0.0004031554698773061, 'samples': 8628096, 'steps': 44937, 'loss/train': 0.7295766472816467} 08/30/2021 21:14:25 - INFO - __main__ - Step 44939: {'lr': 0.0004031512755187219, 'samples': 8628288, 'steps': 44938, 'loss/train': 1.4751077890396118} 08/30/2021 21:14:25 - INFO - __main__ - Step 44940: {'lr': 0.00040314708109113003, 'samples': 8628480, 'steps': 44939, 'loss/train': 1.4967466592788696} 08/30/2021 21:14:26 - INFO - __main__ - Step 44941: {'lr': 0.0004031428865945325, 'samples': 8628672, 'steps': 44940, 'loss/train': 1.3530702590942383} 08/30/2021 21:14:26 - INFO - __main__ - Step 44942: {'lr': 0.0004031386920289311, 'samples': 8628864, 'steps': 44941, 'loss/train': 1.267376184463501} 08/30/2021 21:14:28 - INFO - __main__ - Step 44943: {'lr': 0.0004031344973943278, 'samples': 8629056, 'steps': 44942, 'loss/train': 0.04985160380601883} 08/30/2021 21:14:28 - INFO - __main__ - Step 44944: {'lr': 0.00040313030269072445, 'samples': 8629248, 'steps': 44943, 'loss/train': 3.206683397293091} 08/30/2021 21:14:29 - INFO - __main__ - Step 44945: {'lr': 0.00040312610791812286, 'samples': 8629440, 'steps': 44944, 'loss/train': 3.8430142402648926} 08/30/2021 21:14:29 - INFO - __main__ - Step 44946: {'lr': 0.00040312191307652513, 'samples': 8629632, 'steps': 44945, 'loss/train': 1.984574794769287} 08/30/2021 21:14:29 - INFO - __main__ - Step 44947: {'lr': 0.000403117718165933, 'samples': 8629824, 'steps': 44946, 'loss/train': 1.3935471773147583} 08/30/2021 21:14:30 - INFO - __main__ - Step 44948: {'lr': 0.00040311352318634844, 'samples': 8630016, 'steps': 44947, 'loss/train': 1.3401875495910645} 08/30/2021 21:14:30 - INFO - __main__ - Step 44949: {'lr': 0.00040310932813777316, 'samples': 8630208, 'steps': 44948, 'loss/train': 3.4064152240753174} 08/30/2021 21:14:31 - INFO - __main__ - Step 44950: {'lr': 0.0004031051330202092, 'samples': 8630400, 'steps': 44949, 'loss/train': 2.279451608657837} 08/30/2021 21:14:32 - INFO - __main__ - Step 44951: {'lr': 0.00040310093783365854, 'samples': 8630592, 'steps': 44950, 'loss/train': 1.5151925086975098} 08/30/2021 21:14:32 - INFO - __main__ - Step 44952: {'lr': 0.0004030967425781229, 'samples': 8630784, 'steps': 44951, 'loss/train': 1.4714986085891724} 08/30/2021 21:14:32 - INFO - __main__ - Step 44953: {'lr': 0.0004030925472536042, 'samples': 8630976, 'steps': 44952, 'loss/train': 1.6764044761657715} 08/30/2021 21:14:33 - INFO - __main__ - Step 44954: {'lr': 0.0004030883518601044, 'samples': 8631168, 'steps': 44953, 'loss/train': 1.183774471282959} 08/30/2021 21:14:34 - INFO - __main__ - Step 44955: {'lr': 0.0004030841563976254, 'samples': 8631360, 'steps': 44954, 'loss/train': 1.4662946462631226} 08/30/2021 21:14:35 - INFO - __main__ - Step 44956: {'lr': 0.00040307996086616895, 'samples': 8631552, 'steps': 44955, 'loss/train': 1.4177237749099731} 08/30/2021 21:14:35 - INFO - __main__ - Step 44957: {'lr': 0.00040307576526573704, 'samples': 8631744, 'steps': 44956, 'loss/train': 1.635191559791565} 08/30/2021 21:14:35 - INFO - __main__ - Step 44958: {'lr': 0.00040307156959633154, 'samples': 8631936, 'steps': 44957, 'loss/train': 1.4528034925460815} 08/30/2021 21:14:36 - INFO - __main__ - Step 44959: {'lr': 0.00040306737385795437, 'samples': 8632128, 'steps': 44958, 'loss/train': 1.2309240102767944} 08/30/2021 21:14:37 - INFO - __main__ - Step 44960: {'lr': 0.00040306317805060746, 'samples': 8632320, 'steps': 44959, 'loss/train': 1.8696389198303223} 08/30/2021 21:14:38 - INFO - __main__ - Step 44961: {'lr': 0.0004030589821742926, 'samples': 8632512, 'steps': 44960, 'loss/train': 1.4075578451156616} 08/30/2021 21:14:38 - INFO - __main__ - Step 44962: {'lr': 0.00040305478622901177, 'samples': 8632704, 'steps': 44961, 'loss/train': 2.2401885986328125} 08/30/2021 21:14:38 - INFO - __main__ - Step 44963: {'lr': 0.0004030505902147668, 'samples': 8632896, 'steps': 44962, 'loss/train': 1.155764102935791} 08/30/2021 21:14:39 - INFO - __main__ - Step 44964: {'lr': 0.00040304639413155953, 'samples': 8633088, 'steps': 44963, 'loss/train': 1.3837316036224365} 08/30/2021 21:14:40 - INFO - __main__ - Step 44965: {'lr': 0.0004030421979793919, 'samples': 8633280, 'steps': 44964, 'loss/train': 1.4347622394561768} 08/30/2021 21:14:41 - INFO - __main__ - Step 44966: {'lr': 0.0004030380017582659, 'samples': 8633472, 'steps': 44965, 'loss/train': 0.919955849647522} 08/30/2021 21:14:41 - INFO - __main__ - Step 44967: {'lr': 0.0004030338054681833, 'samples': 8633664, 'steps': 44966, 'loss/train': 1.210355520248413} 08/30/2021 21:14:41 - INFO - __main__ - Step 44968: {'lr': 0.0004030296091091461, 'samples': 8633856, 'steps': 44967, 'loss/train': 0.8844677209854126} 08/30/2021 21:14:42 - INFO - __main__ - Step 44969: {'lr': 0.000403025412681156, 'samples': 8634048, 'steps': 44968, 'loss/train': 1.4895728826522827} 08/30/2021 21:14:43 - INFO - __main__ - Step 44970: {'lr': 0.00040302121618421505, 'samples': 8634240, 'steps': 44969, 'loss/train': 1.4343740940093994} 08/30/2021 21:14:44 - INFO - __main__ - Step 44971: {'lr': 0.0004030170196183252, 'samples': 8634432, 'steps': 44970, 'loss/train': 1.7820158004760742} 08/30/2021 21:14:44 - INFO - __main__ - Step 44972: {'lr': 0.00040301282298348806, 'samples': 8634624, 'steps': 44971, 'loss/train': 1.2913589477539062} 08/30/2021 21:14:45 - INFO - __main__ - Step 44973: {'lr': 0.0004030086262797058, 'samples': 8634816, 'steps': 44972, 'loss/train': 1.0297352075576782} 08/30/2021 21:14:45 - INFO - __main__ - Step 44974: {'lr': 0.0004030044295069803, 'samples': 8635008, 'steps': 44973, 'loss/train': 1.4256709814071655} 08/30/2021 21:14:46 - INFO - __main__ - Step 44975: {'lr': 0.00040300023266531327, 'samples': 8635200, 'steps': 44974, 'loss/train': 1.3890684843063354} 08/30/2021 21:14:47 - INFO - __main__ - Step 44976: {'lr': 0.0004029960357547067, 'samples': 8635392, 'steps': 44975, 'loss/train': 1.1985225677490234} 08/30/2021 21:14:47 - INFO - __main__ - Step 44977: {'lr': 0.0004029918387751625, 'samples': 8635584, 'steps': 44976, 'loss/train': 1.3467111587524414} 08/30/2021 21:14:48 - INFO - __main__ - Step 44978: {'lr': 0.00040298764172668253, 'samples': 8635776, 'steps': 44977, 'loss/train': 1.2234351634979248} 08/30/2021 21:14:48 - INFO - __main__ - Step 44979: {'lr': 0.00040298344460926866, 'samples': 8635968, 'steps': 44978, 'loss/train': 1.788515329360962} 08/30/2021 21:14:48 - INFO - __main__ - Step 44980: {'lr': 0.0004029792474229228, 'samples': 8636160, 'steps': 44979, 'loss/train': 1.798466682434082} 08/30/2021 21:14:50 - INFO - __main__ - Step 44981: {'lr': 0.00040297505016764697, 'samples': 8636352, 'steps': 44980, 'loss/train': 1.6477324962615967} 08/30/2021 21:14:50 - INFO - __main__ - Step 44982: {'lr': 0.00040297085284344284, 'samples': 8636544, 'steps': 44981, 'loss/train': 1.4184931516647339} 08/30/2021 21:14:50 - INFO - __main__ - Step 44983: {'lr': 0.0004029666554503124, 'samples': 8636736, 'steps': 44982, 'loss/train': 1.7507404088974} 08/30/2021 21:14:51 - INFO - __main__ - Step 44984: {'lr': 0.0004029624579882576, 'samples': 8636928, 'steps': 44983, 'loss/train': 0.8345987200737} 08/30/2021 21:14:51 - INFO - __main__ - Step 44985: {'lr': 0.00040295826045728023, 'samples': 8637120, 'steps': 44984, 'loss/train': 1.2658404111862183} 08/30/2021 21:14:53 - INFO - __main__ - Step 44986: {'lr': 0.00040295406285738224, 'samples': 8637312, 'steps': 44985, 'loss/train': 1.327380657196045} 08/30/2021 21:14:53 - INFO - __main__ - Step 44987: {'lr': 0.00040294986518856553, 'samples': 8637504, 'steps': 44986, 'loss/train': 0.9981260299682617} 08/30/2021 21:14:53 - INFO - __main__ - Step 44988: {'lr': 0.00040294566745083195, 'samples': 8637696, 'steps': 44987, 'loss/train': 1.7384164333343506} 08/30/2021 21:14:54 - INFO - __main__ - Step 44989: {'lr': 0.00040294146964418344, 'samples': 8637888, 'steps': 44988, 'loss/train': 1.4508442878723145} 08/30/2021 21:14:54 - INFO - __main__ - Step 44990: {'lr': 0.00040293727176862184, 'samples': 8638080, 'steps': 44989, 'loss/train': 0.9214214086532593} 08/30/2021 21:14:56 - INFO - __main__ - Step 44991: {'lr': 0.000402933073824149, 'samples': 8638272, 'steps': 44990, 'loss/train': 1.816994309425354} 08/30/2021 21:14:57 - INFO - __main__ - Step 44992: {'lr': 0.000402928875810767, 'samples': 8638464, 'steps': 44991, 'loss/train': 0.9074856638908386} 08/30/2021 21:14:57 - INFO - __main__ - Step 44993: {'lr': 0.00040292467772847754, 'samples': 8638656, 'steps': 44992, 'loss/train': 0.8389215469360352} 08/30/2021 21:14:58 - INFO - __main__ - Step 44994: {'lr': 0.00040292047957728264, 'samples': 8638848, 'steps': 44993, 'loss/train': 1.8396106958389282} 08/30/2021 21:14:58 - INFO - __main__ - Step 44995: {'lr': 0.00040291628135718404, 'samples': 8639040, 'steps': 44994, 'loss/train': 1.2606348991394043} 08/30/2021 21:14:59 - INFO - __main__ - Step 44996: {'lr': 0.0004029120830681838, 'samples': 8639232, 'steps': 44995, 'loss/train': 1.3793385028839111} 08/30/2021 21:15:00 - INFO - __main__ - Step 44997: {'lr': 0.0004029078847102837, 'samples': 8639424, 'steps': 44996, 'loss/train': 1.0976223945617676} 08/30/2021 21:15:00 - INFO - __main__ - Step 44998: {'lr': 0.00040290368628348564, 'samples': 8639616, 'steps': 44997, 'loss/train': 0.9544579386711121} 08/30/2021 21:15:01 - INFO - __main__ - Step 44999: {'lr': 0.00040289948778779157, 'samples': 8639808, 'steps': 44998, 'loss/train': 1.2889509201049805} 08/30/2021 21:15:01 - INFO - __main__ - Step 45000: {'lr': 0.00040289528922320334, 'samples': 8640000, 'steps': 44999, 'loss/train': 1.3871757984161377} 08/30/2021 21:15:01 - INFO - __main__ - Evaluating model checkpoint 08/30/2021 21:23:39 - INFO - __main__ - Step 45000: {'loss/eval': 1.285548210144043, 'perplexity': 3.616650104522705} 08/30/2021 21:23:39 - INFO - __main__ - Saving model checkpoint 08/30/2021 21:24:31 - INFO - __main__ - Step 45001: {'lr': 0.00040289109058972285, 'samples': 8640192, 'steps': 45000, 'loss/train': 1.4529192447662354} 08/30/2021 21:24:33 - INFO - __main__ - Step 45002: {'lr': 0.000402886891887352, 'samples': 8640384, 'steps': 45001, 'loss/train': 1.7427260875701904} 08/30/2021 21:24:33 - INFO - __main__ - Step 45003: {'lr': 0.0004028826931160927, 'samples': 8640576, 'steps': 45002, 'loss/train': 0.9633615612983704} 08/30/2021 21:24:34 - INFO - __main__ - Step 45004: {'lr': 0.0004028784942759468, 'samples': 8640768, 'steps': 45003, 'loss/train': 1.0695204734802246} 08/30/2021 21:24:34 - INFO - __main__ - Step 45005: {'lr': 0.0004028742953669162, 'samples': 8640960, 'steps': 45004, 'loss/train': 1.0802251100540161} 08/30/2021 21:24:34 - INFO - __main__ - Step 45006: {'lr': 0.0004028700963890028, 'samples': 8641152, 'steps': 45005, 'loss/train': 1.7785050868988037} 08/30/2021 21:24:36 - INFO - __main__ - Step 45007: {'lr': 0.0004028658973422085, 'samples': 8641344, 'steps': 45006, 'loss/train': 1.711496114730835} 08/30/2021 21:24:36 - INFO - __main__ - Step 45008: {'lr': 0.0004028616982265352, 'samples': 8641536, 'steps': 45007, 'loss/train': 1.7617367506027222} 08/30/2021 21:24:37 - INFO - __main__ - Step 45009: {'lr': 0.0004028574990419848, 'samples': 8641728, 'steps': 45008, 'loss/train': 1.7040481567382812} 08/30/2021 21:24:37 - INFO - __main__ - Step 45010: {'lr': 0.0004028532997885591, 'samples': 8641920, 'steps': 45009, 'loss/train': 1.4897103309631348} 08/30/2021 21:24:37 - INFO - __main__ - Step 45011: {'lr': 0.0004028491004662601, 'samples': 8642112, 'steps': 45010, 'loss/train': 1.4451160430908203} 08/30/2021 21:24:38 - INFO - __main__ - Step 45012: {'lr': 0.0004028449010750896, 'samples': 8642304, 'steps': 45011, 'loss/train': 1.6340372562408447} 08/30/2021 21:24:39 - INFO - __main__ - Step 45013: {'lr': 0.0004028407016150496, 'samples': 8642496, 'steps': 45012, 'loss/train': 2.0591118335723877} 08/30/2021 21:24:40 - INFO - __main__ - Step 45014: {'lr': 0.000402836502086142, 'samples': 8642688, 'steps': 45013, 'loss/train': 2.6037046909332275} 08/30/2021 21:24:40 - INFO - __main__ - Step 45015: {'lr': 0.00040283230248836855, 'samples': 8642880, 'steps': 45014, 'loss/train': 1.441423773765564} 08/30/2021 21:24:40 - INFO - __main__ - Step 45016: {'lr': 0.0004028281028217312, 'samples': 8643072, 'steps': 45015, 'loss/train': 1.0699127912521362} 08/30/2021 21:24:41 - INFO - __main__ - Step 45017: {'lr': 0.00040282390308623195, 'samples': 8643264, 'steps': 45016, 'loss/train': 1.4675841331481934} 08/30/2021 21:24:42 - INFO - __main__ - Step 45018: {'lr': 0.0004028197032818726, 'samples': 8643456, 'steps': 45017, 'loss/train': 1.482582926750183} 08/30/2021 21:24:43 - INFO - __main__ - Step 45019: {'lr': 0.00040281550340865493, 'samples': 8643648, 'steps': 45018, 'loss/train': 0.7939011454582214} 08/30/2021 21:24:43 - INFO - __main__ - Step 45020: {'lr': 0.000402811303466581, 'samples': 8643840, 'steps': 45019, 'loss/train': 1.3104171752929688} 08/30/2021 21:24:43 - INFO - __main__ - Step 45021: {'lr': 0.00040280710345565277, 'samples': 8644032, 'steps': 45020, 'loss/train': 1.2066048383712769} 08/30/2021 21:24:44 - INFO - __main__ - Step 45022: {'lr': 0.0004028029033758719, 'samples': 8644224, 'steps': 45021, 'loss/train': 0.5076983571052551} 08/30/2021 21:24:45 - INFO - __main__ - Step 45023: {'lr': 0.00040279870322724044, 'samples': 8644416, 'steps': 45022, 'loss/train': 1.5589089393615723} 08/30/2021 21:24:46 - INFO - __main__ - Step 45024: {'lr': 0.00040279450300976025, 'samples': 8644608, 'steps': 45023, 'loss/train': 1.701154112815857} 08/30/2021 21:24:46 - INFO - __main__ - Step 45025: {'lr': 0.0004027903027234332, 'samples': 8644800, 'steps': 45024, 'loss/train': 1.7186825275421143} 08/30/2021 21:24:46 - INFO - __main__ - Step 45026: {'lr': 0.0004027861023682612, 'samples': 8644992, 'steps': 45025, 'loss/train': 1.7952632904052734} 08/30/2021 21:24:47 - INFO - __main__ - Step 45027: {'lr': 0.00040278190194424613, 'samples': 8645184, 'steps': 45026, 'loss/train': 1.8114113807678223} 08/30/2021 21:24:48 - INFO - __main__ - Step 45028: {'lr': 0.0004027777014513899, 'samples': 8645376, 'steps': 45027, 'loss/train': 1.1434229612350464} 08/30/2021 21:24:49 - INFO - __main__ - Step 45029: {'lr': 0.0004027735008896944, 'samples': 8645568, 'steps': 45028, 'loss/train': 1.470395565032959} 08/30/2021 21:24:49 - INFO - __main__ - Step 45030: {'lr': 0.0004027693002591615, 'samples': 8645760, 'steps': 45029, 'loss/train': 1.7409037351608276} 08/30/2021 21:24:49 - INFO - __main__ - Step 45031: {'lr': 0.0004027650995597931, 'samples': 8645952, 'steps': 45030, 'loss/train': 1.4654394388198853} 08/30/2021 21:24:50 - INFO - __main__ - Step 45032: {'lr': 0.0004027608987915912, 'samples': 8646144, 'steps': 45031, 'loss/train': 1.1138930320739746} 08/30/2021 21:24:51 - INFO - __main__ - Step 45033: {'lr': 0.0004027566979545574, 'samples': 8646336, 'steps': 45032, 'loss/train': 1.749453067779541} 08/30/2021 21:24:52 - INFO - __main__ - Step 45034: {'lr': 0.000402752497048694, 'samples': 8646528, 'steps': 45033, 'loss/train': 1.281395673751831} 08/30/2021 21:24:52 - INFO - __main__ - Step 45035: {'lr': 0.0004027482960740026, 'samples': 8646720, 'steps': 45034, 'loss/train': 1.667781114578247} 08/30/2021 21:24:52 - INFO - __main__ - Step 45036: {'lr': 0.00040274409503048513, 'samples': 8646912, 'steps': 45035, 'loss/train': 1.2671470642089844} 08/30/2021 21:24:53 - INFO - __main__ - Step 45037: {'lr': 0.0004027398939181436, 'samples': 8647104, 'steps': 45036, 'loss/train': 2.7126309871673584} 08/30/2021 21:24:53 - INFO - __main__ - Step 45038: {'lr': 0.00040273569273697974, 'samples': 8647296, 'steps': 45037, 'loss/train': 1.6907230615615845} 08/30/2021 21:24:55 - INFO - __main__ - Step 45039: {'lr': 0.0004027314914869956, 'samples': 8647488, 'steps': 45038, 'loss/train': 1.9945603609085083} 08/30/2021 21:24:56 - INFO - __main__ - Step 45040: {'lr': 0.000402727290168193, 'samples': 8647680, 'steps': 45039, 'loss/train': 1.7411452531814575} 08/30/2021 21:24:56 - INFO - __main__ - Step 45041: {'lr': 0.00040272308878057383, 'samples': 8647872, 'steps': 45040, 'loss/train': 1.96919584274292} 08/30/2021 21:24:56 - INFO - __main__ - Step 45042: {'lr': 0.0004027188873241401, 'samples': 8648064, 'steps': 45041, 'loss/train': 1.712279200553894} 08/30/2021 21:24:57 - INFO - __main__ - Step 45043: {'lr': 0.00040271468579889346, 'samples': 8648256, 'steps': 45042, 'loss/train': 1.2977653741836548} 08/30/2021 21:24:57 - INFO - __main__ - Step 45044: {'lr': 0.0004027104842048359, 'samples': 8648448, 'steps': 45043, 'loss/train': 0.8696951866149902} 08/30/2021 21:24:59 - INFO - __main__ - Step 45045: {'lr': 0.0004027062825419695, 'samples': 8648640, 'steps': 45044, 'loss/train': 1.4597512483596802} 08/30/2021 21:25:00 - INFO - __main__ - Step 45046: {'lr': 0.0004027020808102959, 'samples': 8648832, 'steps': 45045, 'loss/train': 1.647222638130188} 08/30/2021 21:25:00 - INFO - __main__ - Step 45047: {'lr': 0.0004026978790098171, 'samples': 8649024, 'steps': 45046, 'loss/train': 2.0563488006591797} 08/30/2021 21:25:00 - INFO - __main__ - Step 45048: {'lr': 0.0004026936771405351, 'samples': 8649216, 'steps': 45047, 'loss/train': 1.577674388885498} 08/30/2021 21:25:01 - INFO - __main__ - Step 45049: {'lr': 0.0004026894752024516, 'samples': 8649408, 'steps': 45048, 'loss/train': 1.3633127212524414} 08/30/2021 21:25:02 - INFO - __main__ - Step 45050: {'lr': 0.00040268527319556856, 'samples': 8649600, 'steps': 45049, 'loss/train': 1.5550334453582764} 08/30/2021 21:25:03 - INFO - __main__ - Step 45051: {'lr': 0.0004026810711198879, 'samples': 8649792, 'steps': 45050, 'loss/train': 1.421905279159546} 08/30/2021 21:25:03 - INFO - __main__ - Step 45052: {'lr': 0.00040267686897541157, 'samples': 8649984, 'steps': 45051, 'loss/train': 1.6891404390335083} 08/30/2021 21:25:03 - INFO - __main__ - Step 45053: {'lr': 0.0004026726667621413, 'samples': 8650176, 'steps': 45052, 'loss/train': 1.5040290355682373} 08/30/2021 21:25:04 - INFO - __main__ - Step 45054: {'lr': 0.00040266846448007914, 'samples': 8650368, 'steps': 45053, 'loss/train': 1.712159514427185} 08/30/2021 21:25:05 - INFO - __main__ - Step 45055: {'lr': 0.00040266426212922697, 'samples': 8650560, 'steps': 45054, 'loss/train': 0.8725683689117432} 08/30/2021 21:25:06 - INFO - __main__ - Step 45056: {'lr': 0.00040266005970958656, 'samples': 8650752, 'steps': 45055, 'loss/train': 1.3331995010375977} 08/30/2021 21:25:06 - INFO - __main__ - Step 45057: {'lr': 0.0004026558572211599, 'samples': 8650944, 'steps': 45056, 'loss/train': 1.406862735748291} 08/30/2021 21:25:07 - INFO - __main__ - Step 45058: {'lr': 0.00040265165466394894, 'samples': 8651136, 'steps': 45057, 'loss/train': 1.4554100036621094} 08/30/2021 21:25:07 - INFO - __main__ - Step 45059: {'lr': 0.00040264745203795536, 'samples': 8651328, 'steps': 45058, 'loss/train': 1.6819303035736084} 08/30/2021 21:25:10 - INFO - __main__ - Step 45060: {'lr': 0.0004026432493431813, 'samples': 8651520, 'steps': 45059, 'loss/train': 0.13371874392032623} 08/30/2021 21:25:10 - INFO - __main__ - Step 45061: {'lr': 0.0004026390465796286, 'samples': 8651712, 'steps': 45060, 'loss/train': 1.288615107536316} 08/30/2021 21:25:11 - INFO - __main__ - Step 45062: {'lr': 0.000402634843747299, 'samples': 8651904, 'steps': 45061, 'loss/train': 2.206705331802368} 08/30/2021 21:25:11 - INFO - __main__ - Step 45063: {'lr': 0.0004026306408461945, 'samples': 8652096, 'steps': 45062, 'loss/train': 3.178462505340576} 08/30/2021 21:25:11 - INFO - __main__ - Step 45064: {'lr': 0.000402626437876317, 'samples': 8652288, 'steps': 45063, 'loss/train': 1.5514113903045654} 08/30/2021 21:25:12 - INFO - __main__ - Step 45065: {'lr': 0.00040262223483766835, 'samples': 8652480, 'steps': 45064, 'loss/train': 1.488478183746338} 08/30/2021 21:25:13 - INFO - __main__ - Step 45066: {'lr': 0.0004026180317302506, 'samples': 8652672, 'steps': 45065, 'loss/train': 2.1092100143432617} 08/30/2021 21:25:14 - INFO - __main__ - Step 45067: {'lr': 0.0004026138285540654, 'samples': 8652864, 'steps': 45066, 'loss/train': 2.2072505950927734} 08/30/2021 21:25:14 - INFO - __main__ - Step 45068: {'lr': 0.0004026096253091148, 'samples': 8653056, 'steps': 45067, 'loss/train': 1.8169845342636108} 08/30/2021 21:25:14 - INFO - __main__ - Step 45069: {'lr': 0.00040260542199540064, 'samples': 8653248, 'steps': 45068, 'loss/train': 1.8276143074035645} 08/30/2021 21:25:15 - INFO - __main__ - Step 45070: {'lr': 0.00040260121861292484, 'samples': 8653440, 'steps': 45069, 'loss/train': 2.101228952407837} 08/30/2021 21:25:15 - INFO - __main__ - Step 45071: {'lr': 0.0004025970151616893, 'samples': 8653632, 'steps': 45070, 'loss/train': 4.186982154846191} 08/30/2021 21:25:16 - INFO - __main__ - Step 45072: {'lr': 0.0004025928116416959, 'samples': 8653824, 'steps': 45071, 'loss/train': 1.756313443183899} 08/30/2021 21:25:17 - INFO - __main__ - Step 45073: {'lr': 0.0004025886080529465, 'samples': 8654016, 'steps': 45072, 'loss/train': 1.7998212575912476} 08/30/2021 21:25:17 - INFO - __main__ - Step 45074: {'lr': 0.00040258440439544307, 'samples': 8654208, 'steps': 45073, 'loss/train': 1.5091502666473389} 08/30/2021 21:25:18 - INFO - __main__ - Step 45075: {'lr': 0.0004025802006691874, 'samples': 8654400, 'steps': 45074, 'loss/train': 1.4549766778945923} 08/30/2021 21:25:18 - INFO - __main__ - Step 45076: {'lr': 0.0004025759968741816, 'samples': 8654592, 'steps': 45075, 'loss/train': 1.9283344745635986} 08/30/2021 21:25:19 - INFO - __main__ - Step 45077: {'lr': 0.00040257179301042724, 'samples': 8654784, 'steps': 45076, 'loss/train': 1.647515058517456} 08/30/2021 21:25:20 - INFO - __main__ - Step 45078: {'lr': 0.00040256758907792646, 'samples': 8654976, 'steps': 45077, 'loss/train': 2.8315911293029785} 08/30/2021 21:25:20 - INFO - __main__ - Step 45079: {'lr': 0.0004025633850766811, 'samples': 8655168, 'steps': 45078, 'loss/train': 1.2989681959152222} 08/30/2021 21:25:21 - INFO - __main__ - Step 45080: {'lr': 0.00040255918100669296, 'samples': 8655360, 'steps': 45079, 'loss/train': 1.736068606376648} 08/30/2021 21:25:21 - INFO - __main__ - Step 45081: {'lr': 0.000402554976867964, 'samples': 8655552, 'steps': 45080, 'loss/train': 1.838010311126709} 08/30/2021 21:25:23 - INFO - __main__ - Step 45082: {'lr': 0.00040255077266049624, 'samples': 8655744, 'steps': 45081, 'loss/train': 1.5102806091308594} 08/30/2021 21:25:23 - INFO - __main__ - Step 45083: {'lr': 0.0004025465683842914, 'samples': 8655936, 'steps': 45082, 'loss/train': 1.8476357460021973} 08/30/2021 21:25:23 - INFO - __main__ - Step 45084: {'lr': 0.0004025423640393514, 'samples': 8656128, 'steps': 45083, 'loss/train': 1.7623934745788574} 08/30/2021 21:25:24 - INFO - __main__ - Step 45085: {'lr': 0.0004025381596256782, 'samples': 8656320, 'steps': 45084, 'loss/train': 1.4438000917434692} 08/30/2021 21:25:24 - INFO - __main__ - Step 45086: {'lr': 0.0004025339551432736, 'samples': 8656512, 'steps': 45085, 'loss/train': 1.7174092531204224} 08/30/2021 21:25:26 - INFO - __main__ - Step 45087: {'lr': 0.0004025297505921396, 'samples': 8656704, 'steps': 45086, 'loss/train': 1.3684344291687012} 08/30/2021 21:25:26 - INFO - __main__ - Step 45088: {'lr': 0.00040252554597227795, 'samples': 8656896, 'steps': 45087, 'loss/train': 2.029940366744995} 08/30/2021 21:25:26 - INFO - __main__ - Step 45089: {'lr': 0.00040252134128369085, 'samples': 8657088, 'steps': 45088, 'loss/train': 1.645632266998291} 08/30/2021 21:25:27 - INFO - __main__ - Step 45090: {'lr': 0.00040251713652637985, 'samples': 8657280, 'steps': 45089, 'loss/train': 2.0566251277923584} 08/30/2021 21:25:27 - INFO - __main__ - Step 45091: {'lr': 0.00040251293170034697, 'samples': 8657472, 'steps': 45090, 'loss/train': 1.2192778587341309} 08/30/2021 21:25:29 - INFO - __main__ - Step 45092: {'lr': 0.00040250872680559416, 'samples': 8657664, 'steps': 45091, 'loss/train': 1.8568124771118164} 08/30/2021 21:25:29 - INFO - __main__ - Step 45093: {'lr': 0.00040250452184212326, 'samples': 8657856, 'steps': 45092, 'loss/train': 1.3581924438476562} 08/30/2021 21:25:29 - INFO - __main__ - Step 45094: {'lr': 0.00040250031680993617, 'samples': 8658048, 'steps': 45093, 'loss/train': 1.4816144704818726} 08/30/2021 21:25:30 - INFO - __main__ - Step 45095: {'lr': 0.0004024961117090348, 'samples': 8658240, 'steps': 45094, 'loss/train': 2.1238787174224854} 08/30/2021 21:25:30 - INFO - __main__ - Step 45096: {'lr': 0.00040249190653942105, 'samples': 8658432, 'steps': 45095, 'loss/train': 1.2603925466537476} 08/30/2021 21:25:30 - INFO - __main__ - Step 45097: {'lr': 0.00040248770130109677, 'samples': 8658624, 'steps': 45096, 'loss/train': 1.5867254734039307} 08/30/2021 21:25:32 - INFO - __main__ - Step 45098: {'lr': 0.0004024834959940639, 'samples': 8658816, 'steps': 45097, 'loss/train': 1.7172764539718628} 08/30/2021 21:25:33 - INFO - __main__ - Step 45099: {'lr': 0.0004024792906183243, 'samples': 8659008, 'steps': 45098, 'loss/train': 1.516958236694336} 08/30/2021 21:25:33 - INFO - __main__ - Step 45100: {'lr': 0.0004024750851738799, 'samples': 8659200, 'steps': 45099, 'loss/train': 1.6982613801956177} 08/30/2021 21:25:33 - INFO - __main__ - Step 45101: {'lr': 0.00040247087966073253, 'samples': 8659392, 'steps': 45100, 'loss/train': 1.380101203918457} 08/30/2021 21:25:34 - INFO - __main__ - Step 45102: {'lr': 0.00040246667407888427, 'samples': 8659584, 'steps': 45101, 'loss/train': 1.3081490993499756} 08/30/2021 21:25:35 - INFO - __main__ - Step 45103: {'lr': 0.0004024624684283368, 'samples': 8659776, 'steps': 45102, 'loss/train': 1.572332739830017} 08/30/2021 21:25:36 - INFO - __main__ - Step 45104: {'lr': 0.000402458262709092, 'samples': 8659968, 'steps': 45103, 'loss/train': 1.3511675596237183} 08/30/2021 21:25:36 - INFO - __main__ - Step 45105: {'lr': 0.00040245405692115193, 'samples': 8660160, 'steps': 45104, 'loss/train': 1.4388599395751953} 08/30/2021 21:25:36 - INFO - __main__ - Step 45106: {'lr': 0.0004024498510645185, 'samples': 8660352, 'steps': 45105, 'loss/train': 1.2101796865463257} 08/30/2021 21:25:37 - INFO - __main__ - Step 45107: {'lr': 0.0004024456451391934, 'samples': 8660544, 'steps': 45106, 'loss/train': 1.2687268257141113} 08/30/2021 21:25:38 - INFO - __main__ - Step 45108: {'lr': 0.0004024414391451787, 'samples': 8660736, 'steps': 45107, 'loss/train': 1.5186289548873901} 08/30/2021 21:25:39 - INFO - __main__ - Step 45109: {'lr': 0.00040243723308247624, 'samples': 8660928, 'steps': 45108, 'loss/train': 1.085286259651184} 08/30/2021 21:25:39 - INFO - __main__ - Step 45110: {'lr': 0.0004024330269510879, 'samples': 8661120, 'steps': 45109, 'loss/train': 1.389014720916748} 08/30/2021 21:25:39 - INFO - __main__ - Step 45111: {'lr': 0.00040242882075101563, 'samples': 8661312, 'steps': 45110, 'loss/train': 1.1004711389541626} 08/30/2021 21:25:40 - INFO - __main__ - Step 45112: {'lr': 0.0004024246144822612, 'samples': 8661504, 'steps': 45111, 'loss/train': 0.9022179245948792} 08/30/2021 21:25:41 - INFO - __main__ - Step 45113: {'lr': 0.00040242040814482665, 'samples': 8661696, 'steps': 45112, 'loss/train': 1.7989670038223267} 08/30/2021 21:25:42 - INFO - __main__ - Step 45114: {'lr': 0.00040241620173871385, 'samples': 8661888, 'steps': 45113, 'loss/train': 1.1808686256408691} 08/30/2021 21:25:42 - INFO - __main__ - Step 45115: {'lr': 0.0004024119952639246, 'samples': 8662080, 'steps': 45114, 'loss/train': 1.1829791069030762} 08/30/2021 21:25:42 - INFO - __main__ - Step 45116: {'lr': 0.00040240778872046093, 'samples': 8662272, 'steps': 45115, 'loss/train': 2.0790300369262695} 08/30/2021 21:25:43 - INFO - __main__ - Step 45117: {'lr': 0.00040240358210832456, 'samples': 8662464, 'steps': 45116, 'loss/train': 1.0125223398208618} 08/30/2021 21:25:44 - INFO - __main__ - Step 45118: {'lr': 0.00040239937542751753, 'samples': 8662656, 'steps': 45117, 'loss/train': 1.2831854820251465} 08/30/2021 21:25:45 - INFO - __main__ - Step 45119: {'lr': 0.0004023951686780417, 'samples': 8662848, 'steps': 45118, 'loss/train': 1.3456792831420898} 08/30/2021 21:25:45 - INFO - __main__ - Step 45120: {'lr': 0.000402390961859899, 'samples': 8663040, 'steps': 45119, 'loss/train': 1.8141673803329468} 08/30/2021 21:25:45 - INFO - __main__ - Step 45121: {'lr': 0.00040238675497309117, 'samples': 8663232, 'steps': 45120, 'loss/train': 1.1669790744781494} 08/30/2021 21:25:46 - INFO - __main__ - Step 45122: {'lr': 0.0004023825480176204, 'samples': 8663424, 'steps': 45121, 'loss/train': 1.5144553184509277} 08/30/2021 21:25:47 - INFO - __main__ - Step 45123: {'lr': 0.0004023783409934882, 'samples': 8663616, 'steps': 45122, 'loss/train': 0.5693473815917969} 08/30/2021 21:25:48 - INFO - __main__ - Step 45124: {'lr': 0.00040237413390069684, 'samples': 8663808, 'steps': 45123, 'loss/train': 1.1970113515853882} 08/30/2021 21:25:48 - INFO - __main__ - Step 45125: {'lr': 0.000402369926739248, 'samples': 8664000, 'steps': 45124, 'loss/train': 1.4020979404449463} 08/30/2021 21:25:49 - INFO - __main__ - Step 45126: {'lr': 0.0004023657195091436, 'samples': 8664192, 'steps': 45125, 'loss/train': 1.6678982973098755} 08/30/2021 21:25:49 - INFO - __main__ - Step 45127: {'lr': 0.00040236151221038555, 'samples': 8664384, 'steps': 45126, 'loss/train': 0.18871457874774933} 08/30/2021 21:25:50 - INFO - __main__ - Step 45128: {'lr': 0.00040235730484297573, 'samples': 8664576, 'steps': 45127, 'loss/train': 1.0326552391052246} 08/30/2021 21:25:51 - INFO - __main__ - Step 45129: {'lr': 0.00040235309740691607, 'samples': 8664768, 'steps': 45128, 'loss/train': 1.3598569631576538} 08/30/2021 21:25:51 - INFO - __main__ - Step 45130: {'lr': 0.0004023488899022085, 'samples': 8664960, 'steps': 45129, 'loss/train': 1.6308218240737915} 08/30/2021 21:25:51 - INFO - __main__ - Step 45131: {'lr': 0.00040234468232885483, 'samples': 8665152, 'steps': 45130, 'loss/train': 1.5824154615402222} 08/30/2021 21:25:52 - INFO - __main__ - Step 45132: {'lr': 0.00040234047468685704, 'samples': 8665344, 'steps': 45131, 'loss/train': 1.6160740852355957} 08/30/2021 21:25:53 - INFO - __main__ - Step 45133: {'lr': 0.00040233626697621695, 'samples': 8665536, 'steps': 45132, 'loss/train': 1.3872069120407104} 08/30/2021 21:25:54 - INFO - __main__ - Step 45134: {'lr': 0.0004023320591969365, 'samples': 8665728, 'steps': 45133, 'loss/train': 1.5919708013534546} 08/30/2021 21:25:54 - INFO - __main__ - Step 45135: {'lr': 0.00040232785134901755, 'samples': 8665920, 'steps': 45134, 'loss/train': 0.6691237688064575} 08/30/2021 21:25:54 - INFO - __main__ - Step 45136: {'lr': 0.0004023236434324621, 'samples': 8666112, 'steps': 45135, 'loss/train': 1.3559731245040894} 08/30/2021 21:25:55 - INFO - __main__ - Step 45137: {'lr': 0.0004023194354472719, 'samples': 8666304, 'steps': 45136, 'loss/train': 1.3152339458465576} 08/30/2021 21:25:56 - INFO - __main__ - Step 45138: {'lr': 0.0004023152273934489, 'samples': 8666496, 'steps': 45137, 'loss/train': 1.6463127136230469} 08/30/2021 21:25:57 - INFO - __main__ - Step 45139: {'lr': 0.000402311019270995, 'samples': 8666688, 'steps': 45138, 'loss/train': 0.6973602175712585} 08/30/2021 21:25:57 - INFO - __main__ - Step 45140: {'lr': 0.00040230681107991217, 'samples': 8666880, 'steps': 45139, 'loss/train': 1.6793612241744995} 08/30/2021 21:25:58 - INFO - __main__ - Step 45141: {'lr': 0.0004023026028202021, 'samples': 8667072, 'steps': 45140, 'loss/train': 1.6262484788894653} 08/30/2021 21:25:58 - INFO - __main__ - Step 45142: {'lr': 0.000402298394491867, 'samples': 8667264, 'steps': 45141, 'loss/train': 1.3933535814285278} 08/30/2021 21:25:58 - INFO - __main__ - Step 45143: {'lr': 0.0004022941860949085, 'samples': 8667456, 'steps': 45142, 'loss/train': 1.4439202547073364} 08/30/2021 21:26:00 - INFO - __main__ - Step 45144: {'lr': 0.0004022899776293287, 'samples': 8667648, 'steps': 45143, 'loss/train': 0.09861698001623154} 08/30/2021 21:26:01 - INFO - __main__ - Step 45145: {'lr': 0.00040228576909512927, 'samples': 8667840, 'steps': 45144, 'loss/train': 1.7973074913024902} 08/30/2021 21:26:01 - INFO - __main__ - Step 45146: {'lr': 0.0004022815604923122, 'samples': 8668032, 'steps': 45145, 'loss/train': 3.4507994651794434} 08/30/2021 21:26:01 - INFO - __main__ - Step 45147: {'lr': 0.00040227735182087954, 'samples': 8668224, 'steps': 45146, 'loss/train': 0.0915398970246315} 08/30/2021 21:26:02 - INFO - __main__ - Step 45148: {'lr': 0.00040227314308083296, 'samples': 8668416, 'steps': 45147, 'loss/train': 1.4490028619766235} 08/30/2021 21:26:02 - INFO - __main__ - Step 45149: {'lr': 0.0004022689342721745, 'samples': 8668608, 'steps': 45148, 'loss/train': 1.3307652473449707} 08/30/2021 21:26:04 - INFO - __main__ - Step 45150: {'lr': 0.000402264725394906, 'samples': 8668800, 'steps': 45149, 'loss/train': 1.6872589588165283} 08/30/2021 21:26:04 - INFO - __main__ - Step 45151: {'lr': 0.00040226051644902925, 'samples': 8668992, 'steps': 45150, 'loss/train': 1.2641016244888306} 08/30/2021 21:26:04 - INFO - __main__ - Step 45152: {'lr': 0.0004022563074345464, 'samples': 8669184, 'steps': 45151, 'loss/train': 1.261623501777649} 08/30/2021 21:26:05 - INFO - __main__ - Step 45153: {'lr': 0.00040225209835145916, 'samples': 8669376, 'steps': 45152, 'loss/train': 1.574806809425354} 08/30/2021 21:26:05 - INFO - __main__ - Step 45154: {'lr': 0.0004022478891997695, 'samples': 8669568, 'steps': 45153, 'loss/train': 1.6885905265808105} 08/30/2021 21:26:07 - INFO - __main__ - Step 45155: {'lr': 0.0004022436799794792, 'samples': 8669760, 'steps': 45154, 'loss/train': 0.9964928030967712} 08/30/2021 21:26:08 - INFO - __main__ - Step 45156: {'lr': 0.0004022394706905904, 'samples': 8669952, 'steps': 45155, 'loss/train': 1.844875693321228} 08/30/2021 21:26:08 - INFO - __main__ - Step 45157: {'lr': 0.0004022352613331047, 'samples': 8670144, 'steps': 45156, 'loss/train': 1.6679919958114624} 08/30/2021 21:26:08 - INFO - __main__ - Step 45158: {'lr': 0.0004022310519070242, 'samples': 8670336, 'steps': 45157, 'loss/train': 1.661723256111145} 08/30/2021 21:26:09 - INFO - __main__ - Step 45159: {'lr': 0.00040222684241235075, 'samples': 8670528, 'steps': 45158, 'loss/train': 1.6632270812988281} 08/30/2021 21:26:10 - INFO - __main__ - Step 45160: {'lr': 0.00040222263284908616, 'samples': 8670720, 'steps': 45159, 'loss/train': 1.235009789466858} 08/30/2021 21:26:11 - INFO - __main__ - Step 45161: {'lr': 0.00040221842321723245, 'samples': 8670912, 'steps': 45160, 'loss/train': 0.6463727355003357} 08/30/2021 21:26:11 - INFO - __main__ - Step 45162: {'lr': 0.0004022142135167915, 'samples': 8671104, 'steps': 45161, 'loss/train': 1.435362458229065} 08/30/2021 21:26:12 - INFO - __main__ - Step 45163: {'lr': 0.0004022100037477652, 'samples': 8671296, 'steps': 45162, 'loss/train': 1.6625282764434814} 08/30/2021 21:26:12 - INFO - __main__ - Step 45164: {'lr': 0.0004022057939101553, 'samples': 8671488, 'steps': 45163, 'loss/train': 1.5202744007110596} 08/30/2021 21:26:12 - INFO - __main__ - Step 45165: {'lr': 0.0004022015840039639, 'samples': 8671680, 'steps': 45164, 'loss/train': 1.7744377851486206} 08/30/2021 21:26:14 - INFO - __main__ - Step 45166: {'lr': 0.00040219737402919284, 'samples': 8671872, 'steps': 45165, 'loss/train': 1.7089102268218994} 08/30/2021 21:26:14 - INFO - __main__ - Step 45167: {'lr': 0.0004021931639858439, 'samples': 8672064, 'steps': 45166, 'loss/train': 1.8279352188110352} 08/30/2021 21:26:15 - INFO - __main__ - Step 45168: {'lr': 0.00040218895387391913, 'samples': 8672256, 'steps': 45167, 'loss/train': 1.2124706506729126} 08/30/2021 21:26:15 - INFO - __main__ - Step 45169: {'lr': 0.0004021847436934204, 'samples': 8672448, 'steps': 45168, 'loss/train': 1.634500503540039} 08/30/2021 21:26:15 - INFO - __main__ - Step 45170: {'lr': 0.0004021805334443496, 'samples': 8672640, 'steps': 45169, 'loss/train': 2.0135257244110107} 08/30/2021 21:26:17 - INFO - __main__ - Step 45171: {'lr': 0.00040217632312670846, 'samples': 8672832, 'steps': 45170, 'loss/train': 1.0767260789871216} 08/30/2021 21:26:17 - INFO - __main__ - Step 45172: {'lr': 0.0004021721127404991, 'samples': 8673024, 'steps': 45171, 'loss/train': 1.7100480794906616} 08/30/2021 21:26:18 - INFO - __main__ - Step 45173: {'lr': 0.0004021679022857233, 'samples': 8673216, 'steps': 45172, 'loss/train': 0.8735764622688293} 08/30/2021 21:26:18 - INFO - __main__ - Step 45174: {'lr': 0.000402163691762383, 'samples': 8673408, 'steps': 45173, 'loss/train': 0.9695132374763489} 08/30/2021 21:26:18 - INFO - __main__ - Step 45175: {'lr': 0.00040215948117048006, 'samples': 8673600, 'steps': 45174, 'loss/train': 1.5175728797912598} 08/30/2021 21:26:20 - INFO - __main__ - Step 45176: {'lr': 0.00040215527051001653, 'samples': 8673792, 'steps': 45175, 'loss/train': 2.1440935134887695} 08/30/2021 21:26:20 - INFO - __main__ - Step 45177: {'lr': 0.00040215105978099407, 'samples': 8673984, 'steps': 45176, 'loss/train': 0.6213804483413696} 08/30/2021 21:26:21 - INFO - __main__ - Step 45178: {'lr': 0.00040214684898341475, 'samples': 8674176, 'steps': 45177, 'loss/train': 1.0209404230117798} 08/30/2021 21:26:21 - INFO - __main__ - Step 45179: {'lr': 0.00040214263811728034, 'samples': 8674368, 'steps': 45178, 'loss/train': 1.6317853927612305} 08/30/2021 21:26:21 - INFO - __main__ - Step 45180: {'lr': 0.00040213842718259287, 'samples': 8674560, 'steps': 45179, 'loss/train': 1.3017443418502808} 08/30/2021 21:26:23 - INFO - __main__ - Step 45181: {'lr': 0.00040213421617935416, 'samples': 8674752, 'steps': 45180, 'loss/train': 1.840362787246704} 08/30/2021 21:26:23 - INFO - __main__ - Step 45182: {'lr': 0.000402130005107566, 'samples': 8674944, 'steps': 45181, 'loss/train': 0.6452128291130066} 08/30/2021 21:26:24 - INFO - __main__ - Step 45183: {'lr': 0.0004021257939672306, 'samples': 8675136, 'steps': 45182, 'loss/train': 1.3573397397994995} 08/30/2021 21:26:24 - INFO - __main__ - Step 45184: {'lr': 0.0004021215827583496, 'samples': 8675328, 'steps': 45183, 'loss/train': 1.5065065622329712} 08/30/2021 21:26:24 - INFO - __main__ - Step 45185: {'lr': 0.0004021173714809249, 'samples': 8675520, 'steps': 45184, 'loss/train': 2.3413240909576416} 08/30/2021 21:26:26 - INFO - __main__ - Step 45186: {'lr': 0.0004021131601349585, 'samples': 8675712, 'steps': 45185, 'loss/train': 0.1006455197930336} 08/30/2021 21:26:27 - INFO - __main__ - Step 45187: {'lr': 0.0004021089487204522, 'samples': 8675904, 'steps': 45186, 'loss/train': 1.4627920389175415} 08/30/2021 21:26:27 - INFO - __main__ - Step 45188: {'lr': 0.00040210473723740803, 'samples': 8676096, 'steps': 45187, 'loss/train': 0.1854332983493805} 08/30/2021 21:26:28 - INFO - __main__ - Step 45189: {'lr': 0.0004021005256858279, 'samples': 8676288, 'steps': 45188, 'loss/train': 2.417635679244995} 08/30/2021 21:26:28 - INFO - __main__ - Step 45190: {'lr': 0.00040209631406571344, 'samples': 8676480, 'steps': 45189, 'loss/train': 1.8251458406448364} 08/30/2021 21:26:29 - INFO - __main__ - Step 45191: {'lr': 0.00040209210237706684, 'samples': 8676672, 'steps': 45190, 'loss/train': 1.7103395462036133} 08/30/2021 21:26:30 - INFO - __main__ - Step 45192: {'lr': 0.0004020878906198898, 'samples': 8676864, 'steps': 45191, 'loss/train': 1.358802080154419} 08/30/2021 21:26:30 - INFO - __main__ - Step 45193: {'lr': 0.0004020836787941844, 'samples': 8677056, 'steps': 45192, 'loss/train': 1.6523271799087524} 08/30/2021 21:26:31 - INFO - __main__ - Step 45194: {'lr': 0.0004020794668999524, 'samples': 8677248, 'steps': 45193, 'loss/train': 1.580916404724121} 08/30/2021 21:26:31 - INFO - __main__ - Step 45195: {'lr': 0.0004020752549371957, 'samples': 8677440, 'steps': 45194, 'loss/train': 2.040734052658081} 08/30/2021 21:26:33 - INFO - __main__ - Step 45196: {'lr': 0.00040207104290591633, 'samples': 8677632, 'steps': 45195, 'loss/train': 1.3342704772949219} 08/30/2021 21:26:33 - INFO - __main__ - Step 45197: {'lr': 0.000402066830806116, 'samples': 8677824, 'steps': 45196, 'loss/train': 1.5754648447036743} 08/30/2021 21:26:33 - INFO - __main__ - Step 45198: {'lr': 0.0004020626186377967, 'samples': 8678016, 'steps': 45197, 'loss/train': 1.622589349746704} 08/30/2021 21:26:34 - INFO - __main__ - Step 45199: {'lr': 0.00040205840640096036, 'samples': 8678208, 'steps': 45198, 'loss/train': 1.131399393081665} 08/30/2021 21:26:34 - INFO - __main__ - Step 45200: {'lr': 0.0004020541940956089, 'samples': 8678400, 'steps': 45199, 'loss/train': 1.2490323781967163} 08/30/2021 21:26:36 - INFO - __main__ - Step 45201: {'lr': 0.0004020499817217441, 'samples': 8678592, 'steps': 45200, 'loss/train': 2.06465220451355} 08/30/2021 21:26:36 - INFO - __main__ - Step 45202: {'lr': 0.000402045769279368, 'samples': 8678784, 'steps': 45201, 'loss/train': 1.343319296836853} 08/30/2021 21:26:37 - INFO - __main__ - Step 45203: {'lr': 0.0004020415567684823, 'samples': 8678976, 'steps': 45202, 'loss/train': 1.325750470161438} 08/30/2021 21:26:37 - INFO - __main__ - Step 45204: {'lr': 0.0004020373441890891, 'samples': 8679168, 'steps': 45203, 'loss/train': 1.1039748191833496} 08/30/2021 21:26:37 - INFO - __main__ - Step 45205: {'lr': 0.00040203313154119026, 'samples': 8679360, 'steps': 45204, 'loss/train': 0.6253945827484131} 08/30/2021 21:26:38 - INFO - __main__ - Step 45206: {'lr': 0.00040202891882478754, 'samples': 8679552, 'steps': 45205, 'loss/train': 1.3993908166885376} 08/30/2021 21:26:40 - INFO - __main__ - Step 45207: {'lr': 0.000402024706039883, 'samples': 8679744, 'steps': 45206, 'loss/train': 0.05071474611759186} 08/30/2021 21:26:40 - INFO - __main__ - Step 45208: {'lr': 0.0004020204931864785, 'samples': 8679936, 'steps': 45207, 'loss/train': 0.66348797082901} 08/30/2021 21:26:41 - INFO - __main__ - Step 45209: {'lr': 0.0004020162802645758, 'samples': 8680128, 'steps': 45208, 'loss/train': 1.10163152217865} 08/30/2021 21:26:41 - INFO - __main__ - Step 45210: {'lr': 0.000402012067274177, 'samples': 8680320, 'steps': 45209, 'loss/train': 1.6773884296417236} 08/30/2021 21:26:41 - INFO - __main__ - Step 45211: {'lr': 0.0004020078542152839, 'samples': 8680512, 'steps': 45210, 'loss/train': 1.4000777006149292} 08/30/2021 21:26:43 - INFO - __main__ - Step 45212: {'lr': 0.0004020036410878984, 'samples': 8680704, 'steps': 45211, 'loss/train': 1.1540910005569458} 08/30/2021 21:26:43 - INFO - __main__ - Step 45213: {'lr': 0.0004019994278920224, 'samples': 8680896, 'steps': 45212, 'loss/train': 1.5811522006988525} 08/30/2021 21:26:44 - INFO - __main__ - Step 45214: {'lr': 0.00040199521462765776, 'samples': 8681088, 'steps': 45213, 'loss/train': 1.3787648677825928} 08/30/2021 21:26:44 - INFO - __main__ - Step 45215: {'lr': 0.0004019910012948065, 'samples': 8681280, 'steps': 45214, 'loss/train': 0.09304669499397278} 08/30/2021 21:26:44 - INFO - __main__ - Step 45216: {'lr': 0.0004019867878934704, 'samples': 8681472, 'steps': 45215, 'loss/train': 1.4651738405227661} 08/30/2021 21:26:46 - INFO - __main__ - Step 45217: {'lr': 0.0004019825744236514, 'samples': 8681664, 'steps': 45216, 'loss/train': 0.48439496755599976} 08/30/2021 21:26:46 - INFO - __main__ - Step 45218: {'lr': 0.0004019783608853513, 'samples': 8681856, 'steps': 45217, 'loss/train': 1.2058886289596558} 08/30/2021 21:26:47 - INFO - __main__ - Step 45219: {'lr': 0.0004019741472785723, 'samples': 8682048, 'steps': 45218, 'loss/train': 1.054483413696289} 08/30/2021 21:26:47 - INFO - __main__ - Step 45220: {'lr': 0.0004019699336033159, 'samples': 8682240, 'steps': 45219, 'loss/train': 2.2588601112365723} 08/30/2021 21:26:47 - INFO - __main__ - Step 45221: {'lr': 0.0004019657198595843, 'samples': 8682432, 'steps': 45220, 'loss/train': 1.4068375825881958} 08/30/2021 21:26:49 - INFO - __main__ - Step 45222: {'lr': 0.00040196150604737924, 'samples': 8682624, 'steps': 45221, 'loss/train': 1.260451316833496} 08/30/2021 21:26:49 - INFO - __main__ - Step 45223: {'lr': 0.0004019572921667027, 'samples': 8682816, 'steps': 45222, 'loss/train': 1.1345397233963013} 08/30/2021 21:26:50 - INFO - __main__ - Step 45224: {'lr': 0.0004019530782175566, 'samples': 8683008, 'steps': 45223, 'loss/train': 0.8595730066299438} 08/30/2021 21:26:50 - INFO - __main__ - Step 45225: {'lr': 0.00040194886419994274, 'samples': 8683200, 'steps': 45224, 'loss/train': 1.3685495853424072} 08/30/2021 21:26:50 - INFO - __main__ - Step 45226: {'lr': 0.0004019446501138631, 'samples': 8683392, 'steps': 45225, 'loss/train': 1.742268443107605} 08/30/2021 21:26:52 - INFO - __main__ - Step 45227: {'lr': 0.0004019404359593195, 'samples': 8683584, 'steps': 45226, 'loss/train': 1.4271306991577148} 08/30/2021 21:26:52 - INFO - __main__ - Step 45228: {'lr': 0.0004019362217363138, 'samples': 8683776, 'steps': 45227, 'loss/train': 1.571885347366333} 08/30/2021 21:26:53 - INFO - __main__ - Step 45229: {'lr': 0.00040193200744484815, 'samples': 8683968, 'steps': 45228, 'loss/train': 0.9927380084991455} 08/30/2021 21:26:53 - INFO - __main__ - Step 45230: {'lr': 0.00040192779308492423, 'samples': 8684160, 'steps': 45229, 'loss/train': 1.130592942237854} 08/30/2021 21:26:53 - INFO - __main__ - Step 45231: {'lr': 0.00040192357865654395, 'samples': 8684352, 'steps': 45230, 'loss/train': 0.5775272846221924} 08/30/2021 21:26:55 - INFO - __main__ - Step 45232: {'lr': 0.00040191936415970926, 'samples': 8684544, 'steps': 45231, 'loss/train': 1.9309287071228027} 08/30/2021 21:26:56 - INFO - __main__ - Step 45233: {'lr': 0.00040191514959442206, 'samples': 8684736, 'steps': 45232, 'loss/train': 0.07123694568872452} 08/30/2021 21:26:56 - INFO - __main__ - Step 45234: {'lr': 0.0004019109349606842, 'samples': 8684928, 'steps': 45233, 'loss/train': 1.4687259197235107} 08/30/2021 21:26:56 - INFO - __main__ - Step 45235: {'lr': 0.0004019067202584977, 'samples': 8685120, 'steps': 45234, 'loss/train': 0.5876619815826416} 08/30/2021 21:26:57 - INFO - __main__ - Step 45236: {'lr': 0.0004019025054878643, 'samples': 8685312, 'steps': 45235, 'loss/train': 0.8078687787055969} 08/30/2021 21:26:58 - INFO - __main__ - Step 45237: {'lr': 0.00040189829064878605, 'samples': 8685504, 'steps': 45236, 'loss/train': 1.732340693473816} 08/30/2021 21:26:59 - INFO - __main__ - Step 45238: {'lr': 0.0004018940757412647, 'samples': 8685696, 'steps': 45237, 'loss/train': 1.624877691268921} 08/30/2021 21:26:59 - INFO - __main__ - Step 45239: {'lr': 0.0004018898607653022, 'samples': 8685888, 'steps': 45238, 'loss/train': 1.5087510347366333} 08/30/2021 21:26:59 - INFO - __main__ - Step 45240: {'lr': 0.00040188564572090057, 'samples': 8686080, 'steps': 45239, 'loss/train': 1.4165570735931396} 08/30/2021 21:27:00 - INFO - __main__ - Step 45241: {'lr': 0.00040188143060806156, 'samples': 8686272, 'steps': 45240, 'loss/train': 1.0970169305801392} 08/30/2021 21:27:00 - INFO - __main__ - Step 45242: {'lr': 0.0004018772154267871, 'samples': 8686464, 'steps': 45241, 'loss/train': 1.244028925895691} 08/30/2021 21:27:02 - INFO - __main__ - Step 45243: {'lr': 0.0004018730001770792, 'samples': 8686656, 'steps': 45242, 'loss/train': 0.06590409576892853} 08/30/2021 21:27:02 - INFO - __main__ - Step 45244: {'lr': 0.00040186878485893955, 'samples': 8686848, 'steps': 45243, 'loss/train': 1.2824143171310425} 08/30/2021 21:27:02 - INFO - __main__ - Step 45245: {'lr': 0.0004018645694723703, 'samples': 8687040, 'steps': 45244, 'loss/train': 1.242163896560669} 08/30/2021 21:27:03 - INFO - __main__ - Step 45246: {'lr': 0.00040186035401737307, 'samples': 8687232, 'steps': 45245, 'loss/train': 1.4473241567611694} 08/30/2021 21:27:03 - INFO - __main__ - Step 45247: {'lr': 0.00040185613849395, 'samples': 8687424, 'steps': 45246, 'loss/train': 2.455127716064453} 08/30/2021 21:27:05 - INFO - __main__ - Step 45248: {'lr': 0.0004018519229021029, 'samples': 8687616, 'steps': 45247, 'loss/train': 1.652255892753601} 08/30/2021 21:27:05 - INFO - __main__ - Step 45249: {'lr': 0.0004018477072418336, 'samples': 8687808, 'steps': 45248, 'loss/train': 1.7025799751281738} 08/30/2021 21:27:05 - INFO - __main__ - Step 45250: {'lr': 0.00040184349151314413, 'samples': 8688000, 'steps': 45249, 'loss/train': 1.5914254188537598} 08/30/2021 21:27:06 - INFO - __main__ - Step 45251: {'lr': 0.0004018392757160363, 'samples': 8688192, 'steps': 45250, 'loss/train': 1.1948776245117188} 08/30/2021 21:27:06 - INFO - __main__ - Step 45252: {'lr': 0.00040183505985051204, 'samples': 8688384, 'steps': 45251, 'loss/train': 1.5230097770690918} 08/30/2021 21:27:08 - INFO - __main__ - Step 45253: {'lr': 0.0004018308439165733, 'samples': 8688576, 'steps': 45252, 'loss/train': 1.324571132659912} 08/30/2021 21:27:08 - INFO - __main__ - Step 45254: {'lr': 0.00040182662791422185, 'samples': 8688768, 'steps': 45253, 'loss/train': 0.5762340426445007} 08/30/2021 21:27:09 - INFO - __main__ - Step 45255: {'lr': 0.0004018224118434597, 'samples': 8688960, 'steps': 45254, 'loss/train': 1.4324442148208618} 08/30/2021 21:27:09 - INFO - __main__ - Step 45256: {'lr': 0.0004018181957042887, 'samples': 8689152, 'steps': 45255, 'loss/train': 1.5107744932174683} 08/30/2021 21:27:09 - INFO - __main__ - Step 45257: {'lr': 0.00040181397949671073, 'samples': 8689344, 'steps': 45256, 'loss/train': 0.6136773824691772} 08/30/2021 21:27:11 - INFO - __main__ - Step 45258: {'lr': 0.00040180976322072776, 'samples': 8689536, 'steps': 45257, 'loss/train': 1.2147080898284912} 08/30/2021 21:27:11 - INFO - __main__ - Step 45259: {'lr': 0.0004018055468763416, 'samples': 8689728, 'steps': 45258, 'loss/train': 1.5769293308258057} 08/30/2021 21:27:12 - INFO - __main__ - Step 45260: {'lr': 0.0004018013304635543, 'samples': 8689920, 'steps': 45259, 'loss/train': 1.0438284873962402} 08/30/2021 21:27:12 - INFO - __main__ - Step 45261: {'lr': 0.0004017971139823676, 'samples': 8690112, 'steps': 45260, 'loss/train': 1.6896641254425049} 08/30/2021 21:27:12 - INFO - __main__ - Step 45262: {'lr': 0.0004017928974327835, 'samples': 8690304, 'steps': 45261, 'loss/train': 1.7051851749420166} 08/30/2021 21:27:14 - INFO - __main__ - Step 45263: {'lr': 0.00040178868081480393, 'samples': 8690496, 'steps': 45262, 'loss/train': 1.5047693252563477} 08/30/2021 21:27:15 - INFO - __main__ - Step 45264: {'lr': 0.00040178446412843054, 'samples': 8690688, 'steps': 45263, 'loss/train': 1.429306983947754} 08/30/2021 21:27:15 - INFO - __main__ - Step 45265: {'lr': 0.0004017802473736655, 'samples': 8690880, 'steps': 45264, 'loss/train': 1.924657940864563} 08/30/2021 21:27:15 - INFO - __main__ - Step 45266: {'lr': 0.00040177603055051065, 'samples': 8691072, 'steps': 45265, 'loss/train': 1.6970393657684326} 08/30/2021 21:27:16 - INFO - __main__ - Step 45267: {'lr': 0.0004017718136589679, 'samples': 8691264, 'steps': 45266, 'loss/train': 1.4279415607452393} 08/30/2021 21:27:17 - INFO - __main__ - Step 45268: {'lr': 0.000401767596699039, 'samples': 8691456, 'steps': 45267, 'loss/train': 1.8002479076385498} 08/30/2021 21:27:18 - INFO - __main__ - Step 45269: {'lr': 0.00040176337967072603, 'samples': 8691648, 'steps': 45268, 'loss/train': 1.7292377948760986} 08/30/2021 21:27:18 - INFO - __main__ - Step 45270: {'lr': 0.0004017591625740308, 'samples': 8691840, 'steps': 45269, 'loss/train': 1.7646021842956543} 08/30/2021 21:27:19 - INFO - __main__ - Step 45271: {'lr': 0.0004017549454089553, 'samples': 8692032, 'steps': 45270, 'loss/train': 1.4502753019332886} 08/30/2021 21:27:19 - INFO - __main__ - Step 45272: {'lr': 0.00040175072817550127, 'samples': 8692224, 'steps': 45271, 'loss/train': 1.2278869152069092} 08/30/2021 21:27:19 - INFO - __main__ - Step 45273: {'lr': 0.00040174651087367076, 'samples': 8692416, 'steps': 45272, 'loss/train': 1.3958121538162231} 08/30/2021 21:27:21 - INFO - __main__ - Step 45274: {'lr': 0.0004017422935034656, 'samples': 8692608, 'steps': 45273, 'loss/train': 0.32039281725883484} 08/30/2021 21:27:21 - INFO - __main__ - Step 45275: {'lr': 0.00040173807606488763, 'samples': 8692800, 'steps': 45274, 'loss/train': 1.6026588678359985} 08/30/2021 21:27:22 - INFO - __main__ - Step 45276: {'lr': 0.0004017338585579389, 'samples': 8692992, 'steps': 45275, 'loss/train': 1.8548914194107056} 08/30/2021 21:27:22 - INFO - __main__ - Step 45277: {'lr': 0.0004017296409826213, 'samples': 8693184, 'steps': 45276, 'loss/train': 1.3057940006256104} 08/30/2021 21:27:22 - INFO - __main__ - Step 45278: {'lr': 0.00040172542333893657, 'samples': 8693376, 'steps': 45277, 'loss/train': 1.186486005783081} 08/30/2021 21:27:24 - INFO - __main__ - Step 45279: {'lr': 0.00040172120562688673, 'samples': 8693568, 'steps': 45278, 'loss/train': 1.3602626323699951} 08/30/2021 21:27:24 - INFO - __main__ - Step 45280: {'lr': 0.00040171698784647366, 'samples': 8693760, 'steps': 45279, 'loss/train': 1.3070400953292847} 08/30/2021 21:27:25 - INFO - __main__ - Step 45281: {'lr': 0.00040171276999769926, 'samples': 8693952, 'steps': 45280, 'loss/train': 1.3612293004989624} 08/30/2021 21:27:25 - INFO - __main__ - Step 45282: {'lr': 0.00040170855208056537, 'samples': 8694144, 'steps': 45281, 'loss/train': 0.5573500394821167} 08/30/2021 21:27:25 - INFO - __main__ - Step 45283: {'lr': 0.000401704334095074, 'samples': 8694336, 'steps': 45282, 'loss/train': 2.2114064693450928} 08/30/2021 21:27:27 - INFO - __main__ - Step 45284: {'lr': 0.00040170011604122704, 'samples': 8694528, 'steps': 45283, 'loss/train': 1.6097602844238281} 08/30/2021 21:27:27 - INFO - __main__ - Step 45285: {'lr': 0.0004016958979190263, 'samples': 8694720, 'steps': 45284, 'loss/train': 1.6535147428512573} 08/30/2021 21:27:28 - INFO - __main__ - Step 45286: {'lr': 0.0004016916797284738, 'samples': 8694912, 'steps': 45285, 'loss/train': 1.5273797512054443} 08/30/2021 21:27:28 - INFO - __main__ - Step 45287: {'lr': 0.00040168746146957123, 'samples': 8695104, 'steps': 45286, 'loss/train': 1.1005959510803223} 08/30/2021 21:27:28 - INFO - __main__ - Step 45288: {'lr': 0.0004016832431423207, 'samples': 8695296, 'steps': 45287, 'loss/train': 1.3159942626953125} 08/30/2021 21:27:30 - INFO - __main__ - Step 45289: {'lr': 0.00040167902474672404, 'samples': 8695488, 'steps': 45288, 'loss/train': 1.511220932006836} 08/30/2021 21:27:30 - INFO - __main__ - Step 45290: {'lr': 0.0004016748062827832, 'samples': 8695680, 'steps': 45289, 'loss/train': 1.4889229536056519} 08/30/2021 21:27:31 - INFO - __main__ - Step 45291: {'lr': 0.00040167058775049993, 'samples': 8695872, 'steps': 45290, 'loss/train': 0.9322032928466797} 08/30/2021 21:27:31 - INFO - __main__ - Step 45292: {'lr': 0.0004016663691498763, 'samples': 8696064, 'steps': 45291, 'loss/train': 2.1582694053649902} 08/30/2021 21:27:31 - INFO - __main__ - Step 45293: {'lr': 0.00040166215048091414, 'samples': 8696256, 'steps': 45292, 'loss/train': 1.3934918642044067} 08/30/2021 21:27:33 - INFO - __main__ - Step 45294: {'lr': 0.0004016579317436153, 'samples': 8696448, 'steps': 45293, 'loss/train': 1.3077359199523926} 08/30/2021 21:27:33 - INFO - __main__ - Step 45295: {'lr': 0.0004016537129379818, 'samples': 8696640, 'steps': 45294, 'loss/train': 0.5296040773391724} 08/30/2021 21:27:34 - INFO - __main__ - Step 45296: {'lr': 0.0004016494940640155, 'samples': 8696832, 'steps': 45295, 'loss/train': 1.626242756843567} 08/30/2021 21:27:34 - INFO - __main__ - Step 45297: {'lr': 0.0004016452751217183, 'samples': 8697024, 'steps': 45296, 'loss/train': 1.5968647003173828} 08/30/2021 21:27:34 - INFO - __main__ - Step 45298: {'lr': 0.00040164105611109195, 'samples': 8697216, 'steps': 45297, 'loss/train': 1.4990514516830444} 08/30/2021 21:27:36 - INFO - __main__ - Step 45299: {'lr': 0.0004016368370321386, 'samples': 8697408, 'steps': 45298, 'loss/train': 1.072702407836914} 08/30/2021 21:27:37 - INFO - __main__ - Step 45300: {'lr': 0.00040163261788485994, 'samples': 8697600, 'steps': 45299, 'loss/train': 0.779970645904541} 08/30/2021 21:27:37 - INFO - __main__ - Step 45301: {'lr': 0.00040162839866925804, 'samples': 8697792, 'steps': 45300, 'loss/train': 2.057222843170166} 08/30/2021 21:27:37 - INFO - __main__ - Step 45302: {'lr': 0.0004016241793853347, 'samples': 8697984, 'steps': 45301, 'loss/train': 1.5212918519973755} 08/30/2021 21:27:38 - INFO - __main__ - Step 45303: {'lr': 0.00040161996003309174, 'samples': 8698176, 'steps': 45302, 'loss/train': 0.07882996648550034} 08/30/2021 21:27:39 - INFO - __main__ - Step 45304: {'lr': 0.00040161574061253134, 'samples': 8698368, 'steps': 45303, 'loss/train': 1.3946245908737183} 08/30/2021 21:27:39 - INFO - __main__ - Step 45305: {'lr': 0.0004016115211236552, 'samples': 8698560, 'steps': 45304, 'loss/train': 1.4245455265045166} 08/30/2021 21:27:40 - INFO - __main__ - Step 45306: {'lr': 0.0004016073015664651, 'samples': 8698752, 'steps': 45305, 'loss/train': 1.5707294940948486} 08/30/2021 21:27:40 - INFO - __main__ - Step 45307: {'lr': 0.0004016030819409632, 'samples': 8698944, 'steps': 45306, 'loss/train': 1.669108510017395} 08/30/2021 21:27:41 - INFO - __main__ - Step 45308: {'lr': 0.00040159886224715126, 'samples': 8699136, 'steps': 45307, 'loss/train': 1.294464349746704} 08/30/2021 21:27:41 - INFO - __main__ - Step 45309: {'lr': 0.0004015946424850312, 'samples': 8699328, 'steps': 45308, 'loss/train': 1.6534972190856934} 08/30/2021 21:27:42 - INFO - __main__ - Step 45310: {'lr': 0.000401590422654605, 'samples': 8699520, 'steps': 45309, 'loss/train': 1.4779269695281982} 08/30/2021 21:27:43 - INFO - __main__ - Step 45311: {'lr': 0.00040158620275587443, 'samples': 8699712, 'steps': 45310, 'loss/train': 0.8517269492149353} 08/30/2021 21:27:43 - INFO - __main__ - Step 45312: {'lr': 0.0004015819827888415, 'samples': 8699904, 'steps': 45311, 'loss/train': 0.2647896707057953} 08/30/2021 21:27:44 - INFO - __main__ - Step 45313: {'lr': 0.00040157776275350805, 'samples': 8700096, 'steps': 45312, 'loss/train': 1.3386090993881226} 08/30/2021 21:27:44 - INFO - __main__ - Step 45314: {'lr': 0.000401573542649876, 'samples': 8700288, 'steps': 45313, 'loss/train': 1.1151525974273682} 08/30/2021 21:27:46 - INFO - __main__ - Step 45315: {'lr': 0.0004015693224779472, 'samples': 8700480, 'steps': 45314, 'loss/train': 1.425656795501709} 08/30/2021 21:27:47 - INFO - __main__ - Step 45316: {'lr': 0.0004015651022377237, 'samples': 8700672, 'steps': 45315, 'loss/train': 1.3129818439483643} 08/30/2021 21:27:47 - INFO - __main__ - Step 45317: {'lr': 0.00040156088192920726, 'samples': 8700864, 'steps': 45316, 'loss/train': 1.5592702627182007} 08/30/2021 21:27:47 - INFO - __main__ - Step 45318: {'lr': 0.0004015566615523998, 'samples': 8701056, 'steps': 45317, 'loss/train': 0.5816635489463806} 08/30/2021 21:27:48 - INFO - __main__ - Step 45319: {'lr': 0.00040155244110730325, 'samples': 8701248, 'steps': 45318, 'loss/train': 1.3422900438308716} 08/30/2021 21:27:49 - INFO - __main__ - Step 45320: {'lr': 0.00040154822059391954, 'samples': 8701440, 'steps': 45319, 'loss/train': 0.23084278404712677} 08/30/2021 21:27:50 - INFO - __main__ - Step 45321: {'lr': 0.00040154400001225055, 'samples': 8701632, 'steps': 45320, 'loss/train': 1.3002429008483887} 08/30/2021 21:27:50 - INFO - __main__ - Step 45322: {'lr': 0.00040153977936229813, 'samples': 8701824, 'steps': 45321, 'loss/train': 1.5011858940124512} 08/30/2021 21:27:50 - INFO - __main__ - Step 45323: {'lr': 0.00040153555864406423, 'samples': 8702016, 'steps': 45322, 'loss/train': 1.5152275562286377} 08/30/2021 21:27:51 - INFO - __main__ - Step 45324: {'lr': 0.0004015313378575508, 'samples': 8702208, 'steps': 45323, 'loss/train': 0.7593422532081604} 08/30/2021 21:27:52 - INFO - __main__ - Step 45325: {'lr': 0.00040152711700275963, 'samples': 8702400, 'steps': 45324, 'loss/train': 1.472410798072815} 08/30/2021 21:27:52 - INFO - __main__ - Step 45326: {'lr': 0.0004015228960796927, 'samples': 8702592, 'steps': 45325, 'loss/train': 1.106531023979187} 08/30/2021 21:27:53 - INFO - __main__ - Step 45327: {'lr': 0.0004015186750883518, 'samples': 8702784, 'steps': 45326, 'loss/train': 1.4397965669631958} 08/30/2021 21:27:53 - INFO - __main__ - Step 45328: {'lr': 0.0004015144540287391, 'samples': 8702976, 'steps': 45327, 'loss/train': 1.7939039468765259} 08/30/2021 21:27:54 - INFO - __main__ - Step 45329: {'lr': 0.0004015102329008562, 'samples': 8703168, 'steps': 45328, 'loss/train': 1.007328987121582} 08/30/2021 21:27:55 - INFO - __main__ - Step 45330: {'lr': 0.0004015060117047051, 'samples': 8703360, 'steps': 45329, 'loss/train': 1.4897968769073486} 08/30/2021 21:27:56 - INFO - __main__ - Step 45331: {'lr': 0.0004015017904402879, 'samples': 8703552, 'steps': 45330, 'loss/train': 1.1192376613616943} 08/30/2021 21:27:56 - INFO - __main__ - Step 45332: {'lr': 0.00040149756910760616, 'samples': 8703744, 'steps': 45331, 'loss/train': 1.6463425159454346} 08/30/2021 21:27:56 - INFO - __main__ - Step 45333: {'lr': 0.000401493347706662, 'samples': 8703936, 'steps': 45332, 'loss/train': 1.337498426437378} 08/30/2021 21:27:57 - INFO - __main__ - Step 45334: {'lr': 0.00040148912623745733, 'samples': 8704128, 'steps': 45333, 'loss/train': 1.8205915689468384} 08/30/2021 21:27:57 - INFO - __main__ - Step 45335: {'lr': 0.0004014849046999939, 'samples': 8704320, 'steps': 45334, 'loss/train': 1.6223994493484497} 08/30/2021 21:27:58 - INFO - __main__ - Step 45336: {'lr': 0.00040148068309427376, 'samples': 8704512, 'steps': 45335, 'loss/train': 0.8280646204948425} 08/30/2021 21:27:59 - INFO - __main__ - Step 45337: {'lr': 0.00040147646142029884, 'samples': 8704704, 'steps': 45336, 'loss/train': 1.5944470167160034} 08/30/2021 21:27:59 - INFO - __main__ - Step 45338: {'lr': 0.0004014722396780709, 'samples': 8704896, 'steps': 45337, 'loss/train': 0.5360270738601685} 08/30/2021 21:28:00 - INFO - __main__ - Step 45339: {'lr': 0.00040146801786759183, 'samples': 8705088, 'steps': 45338, 'loss/train': 1.356668472290039} 08/30/2021 21:28:00 - INFO - __main__ - Step 45340: {'lr': 0.00040146379598886376, 'samples': 8705280, 'steps': 45339, 'loss/train': 1.6232160329818726} 08/30/2021 21:28:02 - INFO - __main__ - Step 45341: {'lr': 0.00040145957404188825, 'samples': 8705472, 'steps': 45340, 'loss/train': 0.8288556933403015} 08/30/2021 21:28:02 - INFO - __main__ - Step 45342: {'lr': 0.00040145535202666747, 'samples': 8705664, 'steps': 45341, 'loss/train': 1.5144007205963135} 08/30/2021 21:28:02 - INFO - __main__ - Step 45343: {'lr': 0.0004014511299432033, 'samples': 8705856, 'steps': 45342, 'loss/train': 1.071869969367981} 08/30/2021 21:28:03 - INFO - __main__ - Step 45344: {'lr': 0.0004014469077914976, 'samples': 8706048, 'steps': 45343, 'loss/train': 0.9121518731117249} 08/30/2021 21:28:03 - INFO - __main__ - Step 45345: {'lr': 0.0004014426855715523, 'samples': 8706240, 'steps': 45344, 'loss/train': 1.3119964599609375} 08/30/2021 21:28:04 - INFO - __main__ - Step 45346: {'lr': 0.00040143846328336913, 'samples': 8706432, 'steps': 45345, 'loss/train': 1.8048839569091797} 08/30/2021 21:28:05 - INFO - __main__ - Step 45347: {'lr': 0.00040143424092695015, 'samples': 8706624, 'steps': 45346, 'loss/train': 1.022029161453247} 08/30/2021 21:28:05 - INFO - __main__ - Step 45348: {'lr': 0.00040143001850229733, 'samples': 8706816, 'steps': 45347, 'loss/train': 1.3824069499969482} 08/30/2021 21:28:06 - INFO - __main__ - Step 45349: {'lr': 0.00040142579600941237, 'samples': 8707008, 'steps': 45348, 'loss/train': 2.026054859161377} 08/30/2021 21:28:06 - INFO - __main__ - Step 45350: {'lr': 0.0004014215734482973, 'samples': 8707200, 'steps': 45349, 'loss/train': 1.4047070741653442} 08/30/2021 21:28:08 - INFO - __main__ - Step 45351: {'lr': 0.00040141735081895407, 'samples': 8707392, 'steps': 45350, 'loss/train': 1.727834939956665} 08/30/2021 21:28:08 - INFO - __main__ - Step 45352: {'lr': 0.00040141312812138453, 'samples': 8707584, 'steps': 45351, 'loss/train': 1.3803212642669678} 08/30/2021 21:28:08 - INFO - __main__ - Step 45353: {'lr': 0.0004014089053555905, 'samples': 8707776, 'steps': 45352, 'loss/train': 2.1634228229522705} 08/30/2021 21:28:09 - INFO - __main__ - Step 45354: {'lr': 0.000401404682521574, 'samples': 8707968, 'steps': 45353, 'loss/train': 0.2770467698574066} 08/30/2021 21:28:09 - INFO - __main__ - Step 45355: {'lr': 0.0004014004596193368, 'samples': 8708160, 'steps': 45354, 'loss/train': 1.6003938913345337} 08/30/2021 21:28:11 - INFO - __main__ - Step 45356: {'lr': 0.000401396236648881, 'samples': 8708352, 'steps': 45355, 'loss/train': 1.273625373840332} 08/30/2021 21:28:11 - INFO - __main__ - Step 45357: {'lr': 0.00040139201361020827, 'samples': 8708544, 'steps': 45356, 'loss/train': 5.488168716430664} 08/30/2021 21:28:11 - INFO - __main__ - Step 45358: {'lr': 0.0004013877905033208, 'samples': 8708736, 'steps': 45357, 'loss/train': 1.6528087854385376} 08/30/2021 21:28:12 - INFO - __main__ - Step 45359: {'lr': 0.0004013835673282202, 'samples': 8708928, 'steps': 45358, 'loss/train': 1.9127607345581055} 08/30/2021 21:28:12 - INFO - __main__ - Step 45360: {'lr': 0.00040137934408490856, 'samples': 8709120, 'steps': 45359, 'loss/train': 1.0785194635391235} 08/30/2021 21:28:14 - INFO - __main__ - Step 45361: {'lr': 0.0004013751207733877, 'samples': 8709312, 'steps': 45360, 'loss/train': 0.5043270587921143} 08/30/2021 21:28:14 - INFO - __main__ - Step 45362: {'lr': 0.0004013708973936595, 'samples': 8709504, 'steps': 45361, 'loss/train': 1.7443922758102417} 08/30/2021 21:28:15 - INFO - __main__ - Step 45363: {'lr': 0.000401366673945726, 'samples': 8709696, 'steps': 45362, 'loss/train': 0.9119384288787842} 08/30/2021 21:28:15 - INFO - __main__ - Step 45364: {'lr': 0.00040136245042958897, 'samples': 8709888, 'steps': 45363, 'loss/train': 1.0617207288742065} 08/30/2021 21:28:15 - INFO - __main__ - Step 45365: {'lr': 0.00040135822684525036, 'samples': 8710080, 'steps': 45364, 'loss/train': 1.573112964630127} 08/30/2021 21:28:16 - INFO - __main__ - Step 45366: {'lr': 0.0004013540031927121, 'samples': 8710272, 'steps': 45365, 'loss/train': 1.224539875984192} 08/30/2021 21:28:18 - INFO - __main__ - Step 45367: {'lr': 0.000401349779471976, 'samples': 8710464, 'steps': 45366, 'loss/train': 1.812270998954773} 08/30/2021 21:28:18 - INFO - __main__ - Step 45368: {'lr': 0.000401345555683044, 'samples': 8710656, 'steps': 45367, 'loss/train': 1.7808396816253662} 08/30/2021 21:28:19 - INFO - __main__ - Step 45369: {'lr': 0.00040134133182591813, 'samples': 8710848, 'steps': 45368, 'loss/train': 1.260252833366394} 08/30/2021 21:28:19 - INFO - __main__ - Step 45370: {'lr': 0.0004013371079006001, 'samples': 8711040, 'steps': 45369, 'loss/train': 1.496720314025879} 08/30/2021 21:28:19 - INFO - __main__ - Step 45371: {'lr': 0.000401332883907092, 'samples': 8711232, 'steps': 45370, 'loss/train': 1.5574270486831665} 08/30/2021 21:28:21 - INFO - __main__ - Step 45372: {'lr': 0.00040132865984539556, 'samples': 8711424, 'steps': 45371, 'loss/train': 0.4318111836910248} 08/30/2021 21:28:21 - INFO - __main__ - Step 45373: {'lr': 0.0004013244357155128, 'samples': 8711616, 'steps': 45372, 'loss/train': 2.623877763748169} 08/30/2021 21:28:22 - INFO - __main__ - Step 45374: {'lr': 0.0004013202115174456, 'samples': 8711808, 'steps': 45373, 'loss/train': 0.1138872429728508} 08/30/2021 21:28:22 - INFO - __main__ - Step 45375: {'lr': 0.0004013159872511958, 'samples': 8712000, 'steps': 45374, 'loss/train': 1.6977163553237915} 08/30/2021 21:28:22 - INFO - __main__ - Step 45376: {'lr': 0.0004013117629167653, 'samples': 8712192, 'steps': 45375, 'loss/train': 1.474536657333374} 08/30/2021 21:28:24 - INFO - __main__ - Step 45377: {'lr': 0.0004013075385141561, 'samples': 8712384, 'steps': 45376, 'loss/train': 0.8163807392120361} 08/30/2021 21:28:24 - INFO - __main__ - Step 45378: {'lr': 0.0004013033140433702, 'samples': 8712576, 'steps': 45377, 'loss/train': 1.6421191692352295} 08/30/2021 21:28:25 - INFO - __main__ - Step 45379: {'lr': 0.0004012990895044092, 'samples': 8712768, 'steps': 45378, 'loss/train': 1.4193545579910278} 08/30/2021 21:28:25 - INFO - __main__ - Step 45380: {'lr': 0.0004012948648972752, 'samples': 8712960, 'steps': 45379, 'loss/train': 1.4047447443008423} 08/30/2021 21:28:25 - INFO - __main__ - Step 45381: {'lr': 0.00040129064022197006, 'samples': 8713152, 'steps': 45380, 'loss/train': 1.6190682649612427} 08/30/2021 21:28:27 - INFO - __main__ - Step 45382: {'lr': 0.0004012864154784957, 'samples': 8713344, 'steps': 45381, 'loss/train': 1.1732662916183472} 08/30/2021 21:28:28 - INFO - __main__ - Step 45383: {'lr': 0.00040128219066685403, 'samples': 8713536, 'steps': 45382, 'loss/train': 1.0996413230895996} 08/30/2021 21:28:28 - INFO - __main__ - Step 45384: {'lr': 0.00040127796578704703, 'samples': 8713728, 'steps': 45383, 'loss/train': 1.3954378366470337} 08/30/2021 21:28:29 - INFO - __main__ - Step 45385: {'lr': 0.00040127374083907634, 'samples': 8713920, 'steps': 45384, 'loss/train': 1.5807826519012451} 08/30/2021 21:28:29 - INFO - __main__ - Step 45386: {'lr': 0.00040126951582294414, 'samples': 8714112, 'steps': 45385, 'loss/train': 1.41490638256073} 08/30/2021 21:28:30 - INFO - __main__ - Step 45387: {'lr': 0.00040126529073865216, 'samples': 8714304, 'steps': 45386, 'loss/train': 0.07542635500431061} 08/30/2021 21:28:31 - INFO - __main__ - Step 45388: {'lr': 0.00040126106558620246, 'samples': 8714496, 'steps': 45387, 'loss/train': 1.5419925451278687} 08/30/2021 21:28:31 - INFO - __main__ - Step 45389: {'lr': 0.0004012568403655967, 'samples': 8714688, 'steps': 45388, 'loss/train': 1.31706702709198} 08/30/2021 21:28:32 - INFO - __main__ - Step 45390: {'lr': 0.00040125261507683706, 'samples': 8714880, 'steps': 45389, 'loss/train': 0.8293589353561401} 08/30/2021 21:28:32 - INFO - __main__ - Step 45391: {'lr': 0.0004012483897199254, 'samples': 8715072, 'steps': 45390, 'loss/train': 1.2823151350021362} 08/30/2021 21:28:32 - INFO - __main__ - Step 45392: {'lr': 0.0004012441642948635, 'samples': 8715264, 'steps': 45391, 'loss/train': 1.317599892616272} 08/30/2021 21:28:34 - INFO - __main__ - Step 45393: {'lr': 0.0004012399388016533, 'samples': 8715456, 'steps': 45392, 'loss/train': 1.1026018857955933} 08/30/2021 21:28:35 - INFO - __main__ - Step 45394: {'lr': 0.00040123571324029663, 'samples': 8715648, 'steps': 45393, 'loss/train': 1.3523563146591187} 08/30/2021 21:28:35 - INFO - __main__ - Step 45395: {'lr': 0.0004012314876107956, 'samples': 8715840, 'steps': 45394, 'loss/train': 1.7424101829528809} 08/30/2021 21:28:35 - INFO - __main__ - Step 45396: {'lr': 0.00040122726191315196, 'samples': 8716032, 'steps': 45395, 'loss/train': 1.8487505912780762} 08/30/2021 21:28:36 - INFO - __main__ - Step 45397: {'lr': 0.00040122303614736763, 'samples': 8716224, 'steps': 45396, 'loss/train': 0.09886649996042252} 08/30/2021 21:28:37 - INFO - __main__ - Step 45398: {'lr': 0.00040121881031344455, 'samples': 8716416, 'steps': 45397, 'loss/train': 1.9953153133392334} 08/30/2021 21:28:38 - INFO - __main__ - Step 45399: {'lr': 0.00040121458441138457, 'samples': 8716608, 'steps': 45398, 'loss/train': 1.039934754371643} 08/30/2021 21:28:38 - INFO - __main__ - Step 45400: {'lr': 0.0004012103584411897, 'samples': 8716800, 'steps': 45399, 'loss/train': 1.3867274522781372} 08/30/2021 21:28:38 - INFO - __main__ - Step 45401: {'lr': 0.0004012061324028617, 'samples': 8716992, 'steps': 45400, 'loss/train': 1.5387483835220337} 08/30/2021 21:28:39 - INFO - __main__ - Step 45402: {'lr': 0.0004012019062964026, 'samples': 8717184, 'steps': 45401, 'loss/train': 1.2923636436462402} 08/30/2021 21:28:40 - INFO - __main__ - Step 45403: {'lr': 0.00040119768012181423, 'samples': 8717376, 'steps': 45402, 'loss/train': 1.4038010835647583} 08/30/2021 21:28:40 - INFO - __main__ - Step 45404: {'lr': 0.0004011934538790986, 'samples': 8717568, 'steps': 45403, 'loss/train': 1.52717924118042} 08/30/2021 21:28:41 - INFO - __main__ - Step 45405: {'lr': 0.00040118922756825735, 'samples': 8717760, 'steps': 45404, 'loss/train': 1.5960084199905396} 08/30/2021 21:28:41 - INFO - __main__ - Step 45406: {'lr': 0.00040118500118929267, 'samples': 8717952, 'steps': 45405, 'loss/train': 1.4100596904754639} 08/30/2021 21:28:41 - INFO - __main__ - Step 45407: {'lr': 0.00040118077474220643, 'samples': 8718144, 'steps': 45406, 'loss/train': 0.9633892774581909} 08/30/2021 21:28:43 - INFO - __main__ - Step 45408: {'lr': 0.00040117654822700047, 'samples': 8718336, 'steps': 45407, 'loss/train': 0.9670495986938477} 08/30/2021 21:28:44 - INFO - __main__ - Step 45409: {'lr': 0.0004011723216436766, 'samples': 8718528, 'steps': 45408, 'loss/train': 1.2607340812683105} 08/30/2021 21:28:44 - INFO - __main__ - Step 45410: {'lr': 0.0004011680949922368, 'samples': 8718720, 'steps': 45409, 'loss/train': 2.0846927165985107} 08/30/2021 21:28:45 - INFO - __main__ - Step 45411: {'lr': 0.00040116386827268304, 'samples': 8718912, 'steps': 45410, 'loss/train': 1.393372654914856} 08/30/2021 21:28:45 - INFO - __main__ - Step 45412: {'lr': 0.0004011596414850172, 'samples': 8719104, 'steps': 45411, 'loss/train': 1.2103919982910156} 08/30/2021 21:28:45 - INFO - __main__ - Step 45413: {'lr': 0.0004011554146292411, 'samples': 8719296, 'steps': 45412, 'loss/train': 1.2174266576766968} 08/30/2021 21:28:47 - INFO - __main__ - Step 45414: {'lr': 0.0004011511877053567, 'samples': 8719488, 'steps': 45413, 'loss/train': 0.08311525732278824} 08/30/2021 21:28:47 - INFO - __main__ - Step 45415: {'lr': 0.0004011469607133659, 'samples': 8719680, 'steps': 45414, 'loss/train': 1.235756278038025} 08/30/2021 21:28:48 - INFO - __main__ - Step 45416: {'lr': 0.0004011427336532707, 'samples': 8719872, 'steps': 45415, 'loss/train': 0.9479379057884216} 08/30/2021 21:28:48 - INFO - __main__ - Step 45417: {'lr': 0.00040113850652507286, 'samples': 8720064, 'steps': 45416, 'loss/train': 1.297389030456543} 08/30/2021 21:28:48 - INFO - __main__ - Step 45418: {'lr': 0.00040113427932877434, 'samples': 8720256, 'steps': 45417, 'loss/train': 2.1371407508850098} 08/30/2021 21:28:50 - INFO - __main__ - Step 45419: {'lr': 0.00040113005206437704, 'samples': 8720448, 'steps': 45418, 'loss/train': 1.5319702625274658} 08/30/2021 21:28:51 - INFO - __main__ - Step 45420: {'lr': 0.00040112582473188284, 'samples': 8720640, 'steps': 45419, 'loss/train': 1.5424004793167114} 08/30/2021 21:28:51 - INFO - __main__ - Step 45421: {'lr': 0.00040112159733129375, 'samples': 8720832, 'steps': 45420, 'loss/train': 1.8127344846725464} 08/30/2021 21:28:51 - INFO - __main__ - Step 45422: {'lr': 0.00040111736986261155, 'samples': 8721024, 'steps': 45421, 'loss/train': 1.8065634965896606} 08/30/2021 21:28:52 - INFO - __main__ - Step 45423: {'lr': 0.00040111314232583816, 'samples': 8721216, 'steps': 45422, 'loss/train': 1.6546831130981445} 08/30/2021 21:28:53 - INFO - __main__ - Step 45424: {'lr': 0.0004011089147209756, 'samples': 8721408, 'steps': 45423, 'loss/train': 1.1582897901535034} 08/30/2021 21:28:54 - INFO - __main__ - Step 45425: {'lr': 0.00040110468704802573, 'samples': 8721600, 'steps': 45424, 'loss/train': 1.1235169172286987} 08/30/2021 21:28:54 - INFO - __main__ - Step 45426: {'lr': 0.00040110045930699033, 'samples': 8721792, 'steps': 45425, 'loss/train': 1.5955837965011597} 08/30/2021 21:28:55 - INFO - __main__ - Step 45427: {'lr': 0.00040109623149787137, 'samples': 8721984, 'steps': 45426, 'loss/train': 0.06536370515823364} 08/30/2021 21:28:55 - INFO - __main__ - Step 45428: {'lr': 0.0004010920036206709, 'samples': 8722176, 'steps': 45427, 'loss/train': 1.6359869241714478} 08/30/2021 21:28:55 - INFO - __main__ - Step 45429: {'lr': 0.00040108777567539057, 'samples': 8722368, 'steps': 45428, 'loss/train': 2.8949060440063477} 08/30/2021 21:28:57 - INFO - __main__ - Step 45430: {'lr': 0.00040108354766203247, 'samples': 8722560, 'steps': 45429, 'loss/train': 1.245950698852539} 08/30/2021 21:28:57 - INFO - __main__ - Step 45431: {'lr': 0.0004010793195805985, 'samples': 8722752, 'steps': 45430, 'loss/train': 0.9855471849441528} 08/30/2021 21:28:58 - INFO - __main__ - Step 45432: {'lr': 0.0004010750914310905, 'samples': 8722944, 'steps': 45431, 'loss/train': 1.2119560241699219} 08/30/2021 21:28:58 - INFO - __main__ - Step 45433: {'lr': 0.0004010708632135104, 'samples': 8723136, 'steps': 45432, 'loss/train': 1.519665002822876} 08/30/2021 21:28:58 - INFO - __main__ - Step 45434: {'lr': 0.00040106663492786007, 'samples': 8723328, 'steps': 45433, 'loss/train': 1.0891577005386353} 08/30/2021 21:29:00 - INFO - __main__ - Step 45435: {'lr': 0.00040106240657414137, 'samples': 8723520, 'steps': 45434, 'loss/train': 1.9796557426452637} 08/30/2021 21:29:00 - INFO - __main__ - Step 45436: {'lr': 0.0004010581781523564, 'samples': 8723712, 'steps': 45435, 'loss/train': 1.5103728771209717} 08/30/2021 21:29:01 - INFO - __main__ - Step 45437: {'lr': 0.0004010539496625069, 'samples': 8723904, 'steps': 45436, 'loss/train': 1.4284931421279907} 08/30/2021 21:29:01 - INFO - __main__ - Step 45438: {'lr': 0.00040104972110459493, 'samples': 8724096, 'steps': 45437, 'loss/train': 1.1571506261825562} 08/30/2021 21:29:01 - INFO - __main__ - Step 45439: {'lr': 0.00040104549247862217, 'samples': 8724288, 'steps': 45438, 'loss/train': 0.8309714794158936} 08/30/2021 21:29:03 - INFO - __main__ - Step 45440: {'lr': 0.0004010412637845906, 'samples': 8724480, 'steps': 45439, 'loss/train': 1.3919790983200073} 08/30/2021 21:29:03 - INFO - __main__ - Step 45441: {'lr': 0.00040103703502250223, 'samples': 8724672, 'steps': 45440, 'loss/train': 1.5892564058303833} 08/30/2021 21:29:04 - INFO - __main__ - Step 45442: {'lr': 0.0004010328061923589, 'samples': 8724864, 'steps': 45441, 'loss/train': 1.2075039148330688} 08/30/2021 21:29:04 - INFO - __main__ - Step 45443: {'lr': 0.00040102857729416256, 'samples': 8725056, 'steps': 45442, 'loss/train': 0.7748900055885315} 08/30/2021 21:29:04 - INFO - __main__ - Step 45444: {'lr': 0.000401024348327915, 'samples': 8725248, 'steps': 45443, 'loss/train': 0.8441669940948486} 08/30/2021 21:29:06 - INFO - __main__ - Step 45445: {'lr': 0.00040102011929361826, 'samples': 8725440, 'steps': 45444, 'loss/train': 1.2751429080963135} 08/30/2021 21:29:06 - INFO - __main__ - Step 45446: {'lr': 0.00040101589019127416, 'samples': 8725632, 'steps': 45445, 'loss/train': 1.0400675535202026} 08/30/2021 21:29:07 - INFO - __main__ - Step 45447: {'lr': 0.0004010116610208846, 'samples': 8725824, 'steps': 45446, 'loss/train': 1.0018789768218994} 08/30/2021 21:29:07 - INFO - __main__ - Step 45448: {'lr': 0.0004010074317824516, 'samples': 8726016, 'steps': 45447, 'loss/train': 1.3485724925994873} 08/30/2021 21:29:07 - INFO - __main__ - Step 45449: {'lr': 0.0004010032024759769, 'samples': 8726208, 'steps': 45448, 'loss/train': 1.177703619003296} 08/30/2021 21:29:08 - INFO - __main__ - Step 45450: {'lr': 0.0004009989731014625, 'samples': 8726400, 'steps': 45449, 'loss/train': 1.7052592039108276} 08/30/2021 21:29:09 - INFO - __main__ - Step 45451: {'lr': 0.00040099474365891033, 'samples': 8726592, 'steps': 45450, 'loss/train': 1.4146960973739624} 08/30/2021 21:29:10 - INFO - __main__ - Step 45452: {'lr': 0.0004009905141483222, 'samples': 8726784, 'steps': 45451, 'loss/train': 0.34710901975631714} 08/30/2021 21:29:10 - INFO - __main__ - Step 45453: {'lr': 0.0004009862845697001, 'samples': 8726976, 'steps': 45452, 'loss/train': 1.0887223482131958} 08/30/2021 21:29:10 - INFO - __main__ - Step 45454: {'lr': 0.00040098205492304596, 'samples': 8727168, 'steps': 45453, 'loss/train': 1.1947344541549683} 08/30/2021 21:29:11 - INFO - __main__ - Step 45455: {'lr': 0.00040097782520836156, 'samples': 8727360, 'steps': 45454, 'loss/train': 1.1545122861862183} 08/30/2021 21:29:12 - INFO - __main__ - Step 45456: {'lr': 0.00040097359542564894, 'samples': 8727552, 'steps': 45455, 'loss/train': 2.0078704357147217} 08/30/2021 21:29:13 - INFO - __main__ - Step 45457: {'lr': 0.0004009693655749099, 'samples': 8727744, 'steps': 45456, 'loss/train': 0.11971364915370941} 08/30/2021 21:29:13 - INFO - __main__ - Step 45458: {'lr': 0.00040096513565614645, 'samples': 8727936, 'steps': 45457, 'loss/train': 1.2176803350448608} 08/30/2021 21:29:13 - INFO - __main__ - Step 45459: {'lr': 0.00040096090566936037, 'samples': 8728128, 'steps': 45458, 'loss/train': 0.8424366116523743} 08/30/2021 21:29:14 - INFO - __main__ - Step 45460: {'lr': 0.00040095667561455367, 'samples': 8728320, 'steps': 45459, 'loss/train': 2.1787607669830322} 08/30/2021 21:29:15 - INFO - __main__ - Step 45461: {'lr': 0.00040095244549172824, 'samples': 8728512, 'steps': 45460, 'loss/train': 1.6568368673324585} 08/30/2021 21:29:16 - INFO - __main__ - Step 45462: {'lr': 0.00040094821530088594, 'samples': 8728704, 'steps': 45461, 'loss/train': 1.0476864576339722} 08/30/2021 21:29:16 - INFO - __main__ - Step 45463: {'lr': 0.0004009439850420287, 'samples': 8728896, 'steps': 45462, 'loss/train': 1.9075450897216797} 08/30/2021 21:29:16 - INFO - __main__ - Step 45464: {'lr': 0.00040093975471515843, 'samples': 8729088, 'steps': 45463, 'loss/train': 1.4943007230758667} 08/30/2021 21:29:17 - INFO - __main__ - Step 45465: {'lr': 0.00040093552432027713, 'samples': 8729280, 'steps': 45464, 'loss/train': 1.2659046649932861} 08/30/2021 21:29:18 - INFO - __main__ - Step 45466: {'lr': 0.0004009312938573865, 'samples': 8729472, 'steps': 45465, 'loss/train': 1.3164613246917725} 08/30/2021 21:29:19 - INFO - __main__ - Step 45467: {'lr': 0.00040092706332648856, 'samples': 8729664, 'steps': 45466, 'loss/train': 1.007828950881958} 08/30/2021 21:29:19 - INFO - __main__ - Step 45468: {'lr': 0.00040092283272758525, 'samples': 8729856, 'steps': 45467, 'loss/train': 1.7720130681991577} 08/30/2021 21:29:20 - INFO - __main__ - Step 45469: {'lr': 0.00040091860206067844, 'samples': 8730048, 'steps': 45468, 'loss/train': 1.6414732933044434} 08/30/2021 21:29:20 - INFO - __main__ - Step 45470: {'lr': 0.00040091437132577004, 'samples': 8730240, 'steps': 45469, 'loss/train': 2.295259475708008} 08/30/2021 21:29:22 - INFO - __main__ - Step 45471: {'lr': 0.0004009101405228619, 'samples': 8730432, 'steps': 45470, 'loss/train': 1.6183714866638184} 08/30/2021 21:29:22 - INFO - __main__ - Step 45472: {'lr': 0.00040090590965195604, 'samples': 8730624, 'steps': 45471, 'loss/train': 1.215678095817566} 08/30/2021 21:29:22 - INFO - __main__ - Step 45473: {'lr': 0.0004009016787130543, 'samples': 8730816, 'steps': 45472, 'loss/train': 1.4575421810150146} 08/30/2021 21:29:23 - INFO - __main__ - Step 45474: {'lr': 0.0004008974477061586, 'samples': 8731008, 'steps': 45473, 'loss/train': 1.6828049421310425} 08/30/2021 21:29:23 - INFO - __main__ - Step 45475: {'lr': 0.0004008932166312708, 'samples': 8731200, 'steps': 45474, 'loss/train': 0.7714130878448486} 08/30/2021 21:29:25 - INFO - __main__ - Step 45476: {'lr': 0.0004008889854883929, 'samples': 8731392, 'steps': 45475, 'loss/train': 1.5005035400390625} 08/30/2021 21:29:26 - INFO - __main__ - Step 45477: {'lr': 0.0004008847542775267, 'samples': 8731584, 'steps': 45476, 'loss/train': 1.3288564682006836} 08/30/2021 21:29:26 - INFO - __main__ - Step 45478: {'lr': 0.00040088052299867415, 'samples': 8731776, 'steps': 45477, 'loss/train': 0.6208505034446716} 08/30/2021 21:29:26 - INFO - __main__ - Step 45479: {'lr': 0.0004008762916518372, 'samples': 8731968, 'steps': 45478, 'loss/train': 1.729872226715088} 08/30/2021 21:29:27 - INFO - __main__ - Step 45480: {'lr': 0.0004008720602370177, 'samples': 8732160, 'steps': 45479, 'loss/train': 0.5428986549377441} 08/30/2021 21:29:27 - INFO - __main__ - Step 45481: {'lr': 0.00040086782875421755, 'samples': 8732352, 'steps': 45480, 'loss/train': 1.205990195274353} 08/30/2021 21:29:29 - INFO - __main__ - Step 45482: {'lr': 0.0004008635972034388, 'samples': 8732544, 'steps': 45481, 'loss/train': 0.07471577823162079} 08/30/2021 21:29:29 - INFO - __main__ - Step 45483: {'lr': 0.0004008593655846831, 'samples': 8732736, 'steps': 45482, 'loss/train': 0.6490263938903809} 08/30/2021 21:29:30 - INFO - __main__ - Step 45484: {'lr': 0.0004008551338979526, 'samples': 8732928, 'steps': 45483, 'loss/train': 1.3342127799987793} 08/30/2021 21:29:30 - INFO - __main__ - Step 45485: {'lr': 0.00040085090214324906, 'samples': 8733120, 'steps': 45484, 'loss/train': 1.4586942195892334} 08/30/2021 21:29:30 - INFO - __main__ - Step 45486: {'lr': 0.00040084667032057444, 'samples': 8733312, 'steps': 45485, 'loss/train': 1.4325790405273438} 08/30/2021 21:29:32 - INFO - __main__ - Step 45487: {'lr': 0.00040084243842993065, 'samples': 8733504, 'steps': 45486, 'loss/train': 1.696501612663269} 08/30/2021 21:29:32 - INFO - __main__ - Step 45488: {'lr': 0.0004008382064713195, 'samples': 8733696, 'steps': 45487, 'loss/train': 1.1347908973693848} 08/30/2021 21:29:33 - INFO - __main__ - Step 45489: {'lr': 0.0004008339744447431, 'samples': 8733888, 'steps': 45488, 'loss/train': 0.8334765434265137} 08/30/2021 21:29:33 - INFO - __main__ - Step 45490: {'lr': 0.0004008297423502032, 'samples': 8734080, 'steps': 45489, 'loss/train': 1.8002088069915771} 08/30/2021 21:29:33 - INFO - __main__ - Step 45491: {'lr': 0.0004008255101877017, 'samples': 8734272, 'steps': 45490, 'loss/train': 1.6147581338882446} 08/30/2021 21:29:35 - INFO - __main__ - Step 45492: {'lr': 0.00040082127795724066, 'samples': 8734464, 'steps': 45491, 'loss/train': 1.075305461883545} 08/30/2021 21:29:35 - INFO - __main__ - Step 45493: {'lr': 0.00040081704565882176, 'samples': 8734656, 'steps': 45492, 'loss/train': 1.6420460939407349} 08/30/2021 21:29:36 - INFO - __main__ - Step 45494: {'lr': 0.00040081281329244707, 'samples': 8734848, 'steps': 45493, 'loss/train': 1.2672457695007324} 08/30/2021 21:29:36 - INFO - __main__ - Step 45495: {'lr': 0.00040080858085811844, 'samples': 8735040, 'steps': 45494, 'loss/train': 1.67847740650177} 08/30/2021 21:29:36 - INFO - __main__ - Step 45496: {'lr': 0.00040080434835583777, 'samples': 8735232, 'steps': 45495, 'loss/train': 1.8523110151290894} 08/30/2021 21:29:38 - INFO - __main__ - Step 45497: {'lr': 0.00040080011578560705, 'samples': 8735424, 'steps': 45496, 'loss/train': 1.3734145164489746} 08/30/2021 21:29:38 - INFO - __main__ - Step 45498: {'lr': 0.0004007958831474281, 'samples': 8735616, 'steps': 45497, 'loss/train': 1.0486962795257568} 08/30/2021 21:29:39 - INFO - __main__ - Step 45499: {'lr': 0.0004007916504413029, 'samples': 8735808, 'steps': 45498, 'loss/train': 1.5811030864715576} 08/30/2021 21:29:39 - INFO - __main__ - Step 45500: {'lr': 0.00040078741766723326, 'samples': 8736000, 'steps': 45499, 'loss/train': 0.6940418481826782} 08/30/2021 21:29:40 - INFO - __main__ - Step 45501: {'lr': 0.00040078318482522114, 'samples': 8736192, 'steps': 45500, 'loss/train': 1.7465928792953491} 08/30/2021 21:29:40 - INFO - __main__ - Step 45502: {'lr': 0.0004007789519152684, 'samples': 8736384, 'steps': 45501, 'loss/train': 1.59458589553833} 08/30/2021 21:29:41 - INFO - __main__ - Step 45503: {'lr': 0.00040077471893737703, 'samples': 8736576, 'steps': 45502, 'loss/train': 1.2154748439788818} 08/30/2021 21:29:42 - INFO - __main__ - Step 45504: {'lr': 0.0004007704858915489, 'samples': 8736768, 'steps': 45503, 'loss/train': 1.0664267539978027} 08/30/2021 21:29:42 - INFO - __main__ - Step 45505: {'lr': 0.00040076625277778594, 'samples': 8736960, 'steps': 45504, 'loss/train': 1.6744377613067627} 08/30/2021 21:29:43 - INFO - __main__ - Step 45506: {'lr': 0.00040076201959609003, 'samples': 8737152, 'steps': 45505, 'loss/train': 1.6000587940216064} 08/30/2021 21:29:43 - INFO - __main__ - Step 45507: {'lr': 0.00040075778634646305, 'samples': 8737344, 'steps': 45506, 'loss/train': 1.4726711511611938} 08/30/2021 21:29:44 - INFO - __main__ - Step 45508: {'lr': 0.0004007535530289069, 'samples': 8737536, 'steps': 45507, 'loss/train': 1.6910285949707031} 08/30/2021 21:29:45 - INFO - __main__ - Step 45509: {'lr': 0.0004007493196434236, 'samples': 8737728, 'steps': 45508, 'loss/train': 1.3586182594299316} 08/30/2021 21:29:45 - INFO - __main__ - Step 45510: {'lr': 0.0004007450861900149, 'samples': 8737920, 'steps': 45509, 'loss/train': 1.1043330430984497} 08/30/2021 21:29:46 - INFO - __main__ - Step 45511: {'lr': 0.00040074085266868285, 'samples': 8738112, 'steps': 45510, 'loss/train': 1.0693639516830444} 08/30/2021 21:29:46 - INFO - __main__ - Step 45512: {'lr': 0.0004007366190794294, 'samples': 8738304, 'steps': 45511, 'loss/train': 1.3530992269515991} 08/30/2021 21:29:47 - INFO - __main__ - Step 45513: {'lr': 0.00040073238542225623, 'samples': 8738496, 'steps': 45512, 'loss/train': 1.760133981704712} 08/30/2021 21:29:48 - INFO - __main__ - Step 45514: {'lr': 0.00040072815169716534, 'samples': 8738688, 'steps': 45513, 'loss/train': 1.5427560806274414} 08/30/2021 21:29:48 - INFO - __main__ - Step 45515: {'lr': 0.00040072391790415873, 'samples': 8738880, 'steps': 45514, 'loss/train': 1.7055184841156006} 08/30/2021 21:29:49 - INFO - __main__ - Step 45516: {'lr': 0.00040071968404323824, 'samples': 8739072, 'steps': 45515, 'loss/train': 1.5958950519561768} 08/30/2021 21:29:49 - INFO - __main__ - Step 45517: {'lr': 0.0004007154501144058, 'samples': 8739264, 'steps': 45516, 'loss/train': 1.3519912958145142} 08/30/2021 21:29:49 - INFO - __main__ - Step 45518: {'lr': 0.00040071121611766325, 'samples': 8739456, 'steps': 45517, 'loss/train': 1.5267068147659302} 08/30/2021 21:29:51 - INFO - __main__ - Step 45519: {'lr': 0.00040070698205301266, 'samples': 8739648, 'steps': 45518, 'loss/train': 1.2159485816955566} 08/30/2021 21:29:52 - INFO - __main__ - Step 45520: {'lr': 0.0004007027479204557, 'samples': 8739840, 'steps': 45519, 'loss/train': 1.5194048881530762} 08/30/2021 21:29:52 - INFO - __main__ - Step 45521: {'lr': 0.0004006985137199945, 'samples': 8740032, 'steps': 45520, 'loss/train': 1.0500580072402954} 08/30/2021 21:29:52 - INFO - __main__ - Step 45522: {'lr': 0.00040069427945163083, 'samples': 8740224, 'steps': 45521, 'loss/train': 1.6080890893936157} 08/30/2021 21:29:53 - INFO - __main__ - Step 45523: {'lr': 0.00040069004511536667, 'samples': 8740416, 'steps': 45522, 'loss/train': 0.7664833664894104} 08/30/2021 21:29:54 - INFO - __main__ - Step 45524: {'lr': 0.00040068581071120386, 'samples': 8740608, 'steps': 45523, 'loss/train': 1.7894295454025269} 08/30/2021 21:29:55 - INFO - __main__ - Step 45525: {'lr': 0.00040068157623914435, 'samples': 8740800, 'steps': 45524, 'loss/train': 1.0367735624313354} 08/30/2021 21:29:55 - INFO - __main__ - Step 45526: {'lr': 0.0004006773416991901, 'samples': 8740992, 'steps': 45525, 'loss/train': 0.7200155854225159} 08/30/2021 21:29:55 - INFO - __main__ - Step 45527: {'lr': 0.00040067310709134295, 'samples': 8741184, 'steps': 45526, 'loss/train': 1.2963911294937134} 08/30/2021 21:29:56 - INFO - __main__ - Step 45528: {'lr': 0.0004006688724156048, 'samples': 8741376, 'steps': 45527, 'loss/train': 1.4715675115585327} 08/30/2021 21:29:56 - INFO - __main__ - Step 45529: {'lr': 0.00040066463767197757, 'samples': 8741568, 'steps': 45528, 'loss/train': 5.922485828399658} 08/30/2021 21:29:57 - INFO - __main__ - Step 45530: {'lr': 0.00040066040286046325, 'samples': 8741760, 'steps': 45529, 'loss/train': 1.1490989923477173} 08/30/2021 21:29:58 - INFO - __main__ - Step 45531: {'lr': 0.0004006561679810636, 'samples': 8741952, 'steps': 45530, 'loss/train': 1.5902715921401978} 08/30/2021 21:29:58 - INFO - __main__ - Step 45532: {'lr': 0.0004006519330337807, 'samples': 8742144, 'steps': 45531, 'loss/train': 1.101464867591858} 08/30/2021 21:29:59 - INFO - __main__ - Step 45533: {'lr': 0.0004006476980186163, 'samples': 8742336, 'steps': 45532, 'loss/train': 1.519769310951233} 08/30/2021 21:29:59 - INFO - __main__ - Step 45534: {'lr': 0.0004006434629355723, 'samples': 8742528, 'steps': 45533, 'loss/train': 1.768357753753662} 08/30/2021 21:30:01 - INFO - __main__ - Step 45535: {'lr': 0.0004006392277846508, 'samples': 8742720, 'steps': 45534, 'loss/train': 1.5503679513931274} 08/30/2021 21:30:01 - INFO - __main__ - Step 45536: {'lr': 0.00040063499256585354, 'samples': 8742912, 'steps': 45535, 'loss/train': 1.3042975664138794} 08/30/2021 21:30:02 - INFO - __main__ - Step 45537: {'lr': 0.00040063075727918247, 'samples': 8743104, 'steps': 45536, 'loss/train': 1.399466872215271} 08/30/2021 21:30:02 - INFO - __main__ - Step 45538: {'lr': 0.0004006265219246395, 'samples': 8743296, 'steps': 45537, 'loss/train': 1.2500193119049072} 08/30/2021 21:30:02 - INFO - __main__ - Step 45539: {'lr': 0.00040062228650222657, 'samples': 8743488, 'steps': 45538, 'loss/train': 1.764947533607483} 08/30/2021 21:30:04 - INFO - __main__ - Step 45540: {'lr': 0.00040061805101194553, 'samples': 8743680, 'steps': 45539, 'loss/train': 1.8575208187103271} 08/30/2021 21:30:04 - INFO - __main__ - Step 45541: {'lr': 0.00040061381545379837, 'samples': 8743872, 'steps': 45540, 'loss/train': 1.5655728578567505} 08/30/2021 21:30:04 - INFO - __main__ - Step 45542: {'lr': 0.00040060957982778687, 'samples': 8744064, 'steps': 45541, 'loss/train': 1.728339672088623} 08/30/2021 21:30:05 - INFO - __main__ - Step 45543: {'lr': 0.0004006053441339131, 'samples': 8744256, 'steps': 45542, 'loss/train': 1.527356505393982} 08/30/2021 21:30:05 - INFO - __main__ - Step 45544: {'lr': 0.00040060110837217885, 'samples': 8744448, 'steps': 45543, 'loss/train': 1.4790219068527222} 08/30/2021 21:30:07 - INFO - __main__ - Step 45545: {'lr': 0.000400596872542586, 'samples': 8744640, 'steps': 45544, 'loss/train': 0.9987359642982483} 08/30/2021 21:30:07 - INFO - __main__ - Step 45546: {'lr': 0.0004005926366451367, 'samples': 8744832, 'steps': 45545, 'loss/train': 1.2463665008544922} 08/30/2021 21:30:07 - INFO - __main__ - Step 45547: {'lr': 0.0004005884006798325, 'samples': 8745024, 'steps': 45546, 'loss/train': 0.9123632907867432} 08/30/2021 21:30:08 - INFO - __main__ - Step 45548: {'lr': 0.0004005841646466756, 'samples': 8745216, 'steps': 45547, 'loss/train': 1.4175655841827393} 08/30/2021 21:30:08 - INFO - __main__ - Step 45549: {'lr': 0.00040057992854566774, 'samples': 8745408, 'steps': 45548, 'loss/train': 1.6521754264831543} 08/30/2021 21:30:10 - INFO - __main__ - Step 45550: {'lr': 0.0004005756923768109, 'samples': 8745600, 'steps': 45549, 'loss/train': 1.5313432216644287} 08/30/2021 21:30:10 - INFO - __main__ - Step 45551: {'lr': 0.0004005714561401069, 'samples': 8745792, 'steps': 45550, 'loss/train': 0.9201018810272217} 08/30/2021 21:30:10 - INFO - __main__ - Step 45552: {'lr': 0.0004005672198355579, 'samples': 8745984, 'steps': 45551, 'loss/train': 1.7975521087646484} 08/30/2021 21:30:11 - INFO - __main__ - Step 45553: {'lr': 0.00040056298346316554, 'samples': 8746176, 'steps': 45552, 'loss/train': 1.6051639318466187} 08/30/2021 21:30:11 - INFO - __main__ - Step 45554: {'lr': 0.0004005587470229318, 'samples': 8746368, 'steps': 45553, 'loss/train': 1.3946226835250854} 08/30/2021 21:30:13 - INFO - __main__ - Step 45555: {'lr': 0.00040055451051485865, 'samples': 8746560, 'steps': 45554, 'loss/train': 0.8503422737121582} 08/30/2021 21:30:13 - INFO - __main__ - Step 45556: {'lr': 0.0004005502739389479, 'samples': 8746752, 'steps': 45555, 'loss/train': 1.3847535848617554} 08/30/2021 21:30:14 - INFO - __main__ - Step 45557: {'lr': 0.00040054603729520154, 'samples': 8746944, 'steps': 45556, 'loss/train': 1.164264440536499} 08/30/2021 21:30:14 - INFO - __main__ - Step 45558: {'lr': 0.00040054180058362156, 'samples': 8747136, 'steps': 45557, 'loss/train': 1.205686330795288} 08/30/2021 21:30:14 - INFO - __main__ - Step 45559: {'lr': 0.0004005375638042097, 'samples': 8747328, 'steps': 45558, 'loss/train': 1.2713847160339355} 08/30/2021 21:30:15 - INFO - __main__ - Step 45560: {'lr': 0.0004005333269569679, 'samples': 8747520, 'steps': 45559, 'loss/train': 0.03529397398233414} 08/30/2021 21:30:16 - INFO - __main__ - Step 45561: {'lr': 0.0004005290900418982, 'samples': 8747712, 'steps': 45560, 'loss/train': 1.3542087078094482} 08/30/2021 21:30:17 - INFO - __main__ - Step 45562: {'lr': 0.0004005248530590023, 'samples': 8747904, 'steps': 45561, 'loss/train': 0.6402948498725891} 08/30/2021 21:30:17 - INFO - __main__ - Step 45563: {'lr': 0.0004005206160082823, 'samples': 8748096, 'steps': 45562, 'loss/train': 1.2478729486465454} 08/30/2021 21:30:17 - INFO - __main__ - Step 45564: {'lr': 0.00040051637888973996, 'samples': 8748288, 'steps': 45563, 'loss/train': 1.1593557596206665} 08/30/2021 21:30:18 - INFO - __main__ - Step 45565: {'lr': 0.0004005121417033773, 'samples': 8748480, 'steps': 45564, 'loss/train': 2.1077229976654053} 08/30/2021 21:30:19 - INFO - __main__ - Step 45566: {'lr': 0.0004005079044491963, 'samples': 8748672, 'steps': 45565, 'loss/train': 1.3774333000183105} 08/30/2021 21:30:20 - INFO - __main__ - Step 45567: {'lr': 0.0004005036671271986, 'samples': 8748864, 'steps': 45566, 'loss/train': 1.4116657972335815} 08/30/2021 21:30:20 - INFO - __main__ - Step 45568: {'lr': 0.00040049942973738626, 'samples': 8749056, 'steps': 45567, 'loss/train': 1.5779608488082886} 08/30/2021 21:30:21 - INFO - __main__ - Step 45569: {'lr': 0.00040049519227976135, 'samples': 8749248, 'steps': 45568, 'loss/train': 1.1621469259262085} 08/30/2021 21:30:21 - INFO - __main__ - Step 45570: {'lr': 0.0004004909547543255, 'samples': 8749440, 'steps': 45569, 'loss/train': 0.09808221459388733} 08/30/2021 21:30:23 - INFO - __main__ - Step 45571: {'lr': 0.0004004867171610808, 'samples': 8749632, 'steps': 45570, 'loss/train': 1.1585769653320312} 08/30/2021 21:30:24 - INFO - __main__ - Step 45572: {'lr': 0.00040048247950002917, 'samples': 8749824, 'steps': 45571, 'loss/train': 1.1929718255996704} 08/30/2021 21:30:24 - INFO - __main__ - Step 45573: {'lr': 0.0004004782417711724, 'samples': 8750016, 'steps': 45572, 'loss/train': 1.6099721193313599} 08/30/2021 21:30:24 - INFO - __main__ - Step 45574: {'lr': 0.0004004740039745124, 'samples': 8750208, 'steps': 45573, 'loss/train': 1.5693515539169312} 08/30/2021 21:30:25 - INFO - __main__ - Step 45575: {'lr': 0.0004004697661100512, 'samples': 8750400, 'steps': 45574, 'loss/train': 1.6056859493255615} 08/30/2021 21:30:25 - INFO - __main__ - Step 45576: {'lr': 0.0004004655281777906, 'samples': 8750592, 'steps': 45575, 'loss/train': 1.7467777729034424} 08/30/2021 21:30:27 - INFO - __main__ - Step 45577: {'lr': 0.0004004612901777326, 'samples': 8750784, 'steps': 45576, 'loss/train': 1.7978405952453613} 08/30/2021 21:30:27 - INFO - __main__ - Step 45578: {'lr': 0.000400457052109879, 'samples': 8750976, 'steps': 45577, 'loss/train': 1.581963300704956} 08/30/2021 21:30:28 - INFO - __main__ - Step 45579: {'lr': 0.0004004528139742319, 'samples': 8751168, 'steps': 45578, 'loss/train': 1.3904138803482056} 08/30/2021 21:30:28 - INFO - __main__ - Step 45580: {'lr': 0.00040044857577079294, 'samples': 8751360, 'steps': 45579, 'loss/train': 1.352089285850525} 08/30/2021 21:30:28 - INFO - __main__ - Step 45581: {'lr': 0.00040044433749956434, 'samples': 8751552, 'steps': 45580, 'loss/train': 1.4210666418075562} 08/30/2021 21:30:29 - INFO - __main__ - Step 45582: {'lr': 0.0004004400991605477, 'samples': 8751744, 'steps': 45581, 'loss/train': 1.3799400329589844} 08/30/2021 21:30:30 - INFO - __main__ - Step 45583: {'lr': 0.0004004358607537451, 'samples': 8751936, 'steps': 45582, 'loss/train': 1.426185965538025} 08/30/2021 21:30:31 - INFO - __main__ - Step 45584: {'lr': 0.0004004316222791584, 'samples': 8752128, 'steps': 45583, 'loss/train': 0.9114278554916382} 08/30/2021 21:30:31 - INFO - __main__ - Step 45585: {'lr': 0.00040042738373678954, 'samples': 8752320, 'steps': 45584, 'loss/train': 1.2945493459701538} 08/30/2021 21:30:31 - INFO - __main__ - Step 45586: {'lr': 0.0004004231451266406, 'samples': 8752512, 'steps': 45585, 'loss/train': 1.7090985774993896} 08/30/2021 21:30:32 - INFO - __main__ - Step 45587: {'lr': 0.0004004189064487131, 'samples': 8752704, 'steps': 45586, 'loss/train': 1.0333878993988037} 08/30/2021 21:30:33 - INFO - __main__ - Step 45588: {'lr': 0.00040041466770300923, 'samples': 8752896, 'steps': 45587, 'loss/train': 1.3956458568572998} 08/30/2021 21:30:34 - INFO - __main__ - Step 45589: {'lr': 0.00040041042888953085, 'samples': 8753088, 'steps': 45588, 'loss/train': 1.5097129344940186} 08/30/2021 21:30:34 - INFO - __main__ - Step 45590: {'lr': 0.0004004061900082798, 'samples': 8753280, 'steps': 45589, 'loss/train': 1.5660483837127686} 08/30/2021 21:30:35 - INFO - __main__ - Step 45591: {'lr': 0.00040040195105925803, 'samples': 8753472, 'steps': 45590, 'loss/train': 1.2408846616744995} 08/30/2021 21:30:35 - INFO - __main__ - Step 45592: {'lr': 0.00040039771204246756, 'samples': 8753664, 'steps': 45591, 'loss/train': 1.593881607055664} 08/30/2021 21:30:36 - INFO - __main__ - Step 45593: {'lr': 0.0004003934729579101, 'samples': 8753856, 'steps': 45592, 'loss/train': 0.12923464179039001} 08/30/2021 21:30:37 - INFO - __main__ - Step 45594: {'lr': 0.0004003892338055877, 'samples': 8754048, 'steps': 45593, 'loss/train': 0.11357492953538895} 08/30/2021 21:30:37 - INFO - __main__ - Step 45595: {'lr': 0.0004003849945855023, 'samples': 8754240, 'steps': 45594, 'loss/train': 1.4381378889083862} 08/30/2021 21:30:38 - INFO - __main__ - Step 45596: {'lr': 0.0004003807552976556, 'samples': 8754432, 'steps': 45595, 'loss/train': 1.894063949584961} 08/30/2021 21:30:38 - INFO - __main__ - Step 45597: {'lr': 0.00040037651594204975, 'samples': 8754624, 'steps': 45596, 'loss/train': 1.1790415048599243} 08/30/2021 21:30:40 - INFO - __main__ - Step 45598: {'lr': 0.00040037227651868655, 'samples': 8754816, 'steps': 45597, 'loss/train': 1.7249220609664917} 08/30/2021 21:30:40 - INFO - __main__ - Step 45599: {'lr': 0.000400368037027568, 'samples': 8755008, 'steps': 45598, 'loss/train': 1.5415078401565552} 08/30/2021 21:30:40 - INFO - __main__ - Step 45600: {'lr': 0.0004003637974686958, 'samples': 8755200, 'steps': 45599, 'loss/train': 1.1206258535385132} 08/30/2021 21:30:41 - INFO - __main__ - Step 45601: {'lr': 0.000400359557842072, 'samples': 8755392, 'steps': 45600, 'loss/train': 1.5202081203460693} 08/30/2021 21:30:41 - INFO - __main__ - Step 45602: {'lr': 0.00040035531814769853, 'samples': 8755584, 'steps': 45601, 'loss/train': 1.4554232358932495} 08/30/2021 21:30:43 - INFO - __main__ - Step 45603: {'lr': 0.0004003510783855774, 'samples': 8755776, 'steps': 45602, 'loss/train': 1.5050292015075684} 08/30/2021 21:30:43 - INFO - __main__ - Step 45604: {'lr': 0.00040034683855571027, 'samples': 8755968, 'steps': 45603, 'loss/train': 1.5374759435653687} 08/30/2021 21:30:44 - INFO - __main__ - Step 45605: {'lr': 0.00040034259865809915, 'samples': 8756160, 'steps': 45604, 'loss/train': 1.7383564710617065} 08/30/2021 21:30:44 - INFO - __main__ - Step 45606: {'lr': 0.00040033835869274605, 'samples': 8756352, 'steps': 45605, 'loss/train': 1.903132438659668} 08/30/2021 21:30:44 - INFO - __main__ - Step 45607: {'lr': 0.00040033411865965276, 'samples': 8756544, 'steps': 45606, 'loss/train': 1.8588534593582153} 08/30/2021 21:30:46 - INFO - __main__ - Step 45608: {'lr': 0.0004003298785588212, 'samples': 8756736, 'steps': 45607, 'loss/train': 0.06825053691864014} 08/30/2021 21:30:47 - INFO - __main__ - Step 45609: {'lr': 0.00040032563839025335, 'samples': 8756928, 'steps': 45608, 'loss/train': 1.7190632820129395} 08/30/2021 21:30:47 - INFO - __main__ - Step 45610: {'lr': 0.00040032139815395114, 'samples': 8757120, 'steps': 45609, 'loss/train': 1.9274654388427734} 08/30/2021 21:30:47 - INFO - __main__ - Step 45611: {'lr': 0.00040031715784991643, 'samples': 8757312, 'steps': 45610, 'loss/train': 0.8872581720352173} 08/30/2021 21:30:48 - INFO - __main__ - Step 45612: {'lr': 0.000400312917478151, 'samples': 8757504, 'steps': 45611, 'loss/train': 1.425658106803894} 08/30/2021 21:30:48 - INFO - __main__ - Step 45613: {'lr': 0.000400308677038657, 'samples': 8757696, 'steps': 45612, 'loss/train': 0.7507902383804321} 08/30/2021 21:30:49 - INFO - __main__ - Step 45614: {'lr': 0.0004003044365314362, 'samples': 8757888, 'steps': 45613, 'loss/train': 1.42909836769104} 08/30/2021 21:30:50 - INFO - __main__ - Step 45615: {'lr': 0.0004003001959564906, 'samples': 8758080, 'steps': 45614, 'loss/train': 1.3172701597213745} 08/30/2021 21:30:50 - INFO - __main__ - Step 45616: {'lr': 0.000400295955313822, 'samples': 8758272, 'steps': 45615, 'loss/train': 1.369828224182129} 08/30/2021 21:30:51 - INFO - __main__ - Step 45617: {'lr': 0.0004002917146034323, 'samples': 8758464, 'steps': 45616, 'loss/train': 1.1888891458511353} 08/30/2021 21:30:51 - INFO - __main__ - Step 45618: {'lr': 0.0004002874738253235, 'samples': 8758656, 'steps': 45617, 'loss/train': 1.2672510147094727} 08/30/2021 21:30:53 - INFO - __main__ - Step 45619: {'lr': 0.00040028323297949754, 'samples': 8758848, 'steps': 45618, 'loss/train': 1.2632243633270264} 08/30/2021 21:30:53 - INFO - __main__ - Step 45620: {'lr': 0.0004002789920659563, 'samples': 8759040, 'steps': 45619, 'loss/train': 1.6408114433288574} 08/30/2021 21:30:54 - INFO - __main__ - Step 45621: {'lr': 0.0004002747510847016, 'samples': 8759232, 'steps': 45620, 'loss/train': 1.0925028324127197} 08/30/2021 21:30:54 - INFO - __main__ - Step 45622: {'lr': 0.0004002705100357354, 'samples': 8759424, 'steps': 45621, 'loss/train': 1.4130882024765015} 08/30/2021 21:30:54 - INFO - __main__ - Step 45623: {'lr': 0.00040026626891905963, 'samples': 8759616, 'steps': 45622, 'loss/train': 0.97480708360672} 08/30/2021 21:30:55 - INFO - __main__ - Step 45624: {'lr': 0.00040026202773467623, 'samples': 8759808, 'steps': 45623, 'loss/train': 1.5982215404510498} 08/30/2021 21:30:57 - INFO - __main__ - Step 45625: {'lr': 0.00040025778648258706, 'samples': 8760000, 'steps': 45624, 'loss/train': 0.045749176293611526} 08/30/2021 21:30:57 - INFO - __main__ - Step 45626: {'lr': 0.00040025354516279413, 'samples': 8760192, 'steps': 45625, 'loss/train': 1.8206430673599243} 08/30/2021 21:30:57 - INFO - __main__ - Step 45627: {'lr': 0.0004002493037752992, 'samples': 8760384, 'steps': 45626, 'loss/train': 1.7614457607269287} 08/30/2021 21:30:58 - INFO - __main__ - Step 45628: {'lr': 0.0004002450623201043, 'samples': 8760576, 'steps': 45627, 'loss/train': 1.2492746114730835} 08/30/2021 21:30:58 - INFO - __main__ - Step 45629: {'lr': 0.0004002408207972111, 'samples': 8760768, 'steps': 45628, 'loss/train': 1.8820266723632812} 08/30/2021 21:31:00 - INFO - __main__ - Step 45630: {'lr': 0.00040023657920662195, 'samples': 8760960, 'steps': 45629, 'loss/train': 1.9036760330200195} 08/30/2021 21:31:00 - INFO - __main__ - Step 45631: {'lr': 0.0004002323375483384, 'samples': 8761152, 'steps': 45630, 'loss/train': 1.6004084348678589} 08/30/2021 21:31:01 - INFO - __main__ - Step 45632: {'lr': 0.00040022809582236245, 'samples': 8761344, 'steps': 45631, 'loss/train': 0.8890056014060974} 08/30/2021 21:31:01 - INFO - __main__ - Step 45633: {'lr': 0.0004002238540286961, 'samples': 8761536, 'steps': 45632, 'loss/train': 1.4282796382904053} 08/30/2021 21:31:01 - INFO - __main__ - Step 45634: {'lr': 0.00040021961216734123, 'samples': 8761728, 'steps': 45633, 'loss/train': 1.3680033683776855} 08/30/2021 21:31:02 - INFO - __main__ - Step 45635: {'lr': 0.0004002153702382997, 'samples': 8761920, 'steps': 45634, 'loss/train': 1.284507155418396} 08/30/2021 21:31:03 - INFO - __main__ - Step 45636: {'lr': 0.0004002111282415734, 'samples': 8762112, 'steps': 45635, 'loss/train': 0.9587433338165283} 08/30/2021 21:31:04 - INFO - __main__ - Step 45637: {'lr': 0.00040020688617716427, 'samples': 8762304, 'steps': 45636, 'loss/train': 1.4804365634918213} 08/30/2021 21:31:04 - INFO - __main__ - Step 45638: {'lr': 0.0004002026440450742, 'samples': 8762496, 'steps': 45637, 'loss/train': 0.9273775815963745} 08/30/2021 21:31:04 - INFO - __main__ - Step 45639: {'lr': 0.0004001984018453052, 'samples': 8762688, 'steps': 45638, 'loss/train': 1.2588932514190674} 08/30/2021 21:31:05 - INFO - __main__ - Step 45640: {'lr': 0.0004001941595778592, 'samples': 8762880, 'steps': 45639, 'loss/train': 0.9720456004142761} 08/30/2021 21:31:06 - INFO - __main__ - Step 45641: {'lr': 0.0004001899172427379, 'samples': 8763072, 'steps': 45640, 'loss/train': 1.5970231294631958} 08/30/2021 21:31:07 - INFO - __main__ - Step 45642: {'lr': 0.00040018567483994337, 'samples': 8763264, 'steps': 45641, 'loss/train': 1.4056333303451538} 08/30/2021 21:31:07 - INFO - __main__ - Step 45643: {'lr': 0.00040018143236947756, 'samples': 8763456, 'steps': 45642, 'loss/train': 1.3044254779815674} 08/30/2021 21:31:07 - INFO - __main__ - Step 45644: {'lr': 0.0004001771898313422, 'samples': 8763648, 'steps': 45643, 'loss/train': 1.5113991498947144} 08/30/2021 21:31:08 - INFO - __main__ - Step 45645: {'lr': 0.00040017294722553945, 'samples': 8763840, 'steps': 45644, 'loss/train': 0.6521874666213989} 08/30/2021 21:31:08 - INFO - __main__ - Step 45646: {'lr': 0.000400168704552071, 'samples': 8764032, 'steps': 45645, 'loss/train': 0.3046039938926697} 08/30/2021 21:31:10 - INFO - __main__ - Step 45647: {'lr': 0.0004001644618109389, 'samples': 8764224, 'steps': 45646, 'loss/train': 0.9743245244026184} 08/30/2021 21:31:10 - INFO - __main__ - Step 45648: {'lr': 0.00040016021900214497, 'samples': 8764416, 'steps': 45647, 'loss/train': 1.7741951942443848} 08/30/2021 21:31:10 - INFO - __main__ - Step 45649: {'lr': 0.00040015597612569115, 'samples': 8764608, 'steps': 45648, 'loss/train': 1.0282500982284546} 08/30/2021 21:31:11 - INFO - __main__ - Step 45650: {'lr': 0.00040015173318157937, 'samples': 8764800, 'steps': 45649, 'loss/train': 1.1559091806411743} 08/30/2021 21:31:11 - INFO - __main__ - Step 45651: {'lr': 0.00040014749016981154, 'samples': 8764992, 'steps': 45650, 'loss/train': 1.6319549083709717} 08/30/2021 21:31:13 - INFO - __main__ - Step 45652: {'lr': 0.00040014324709038965, 'samples': 8765184, 'steps': 45651, 'loss/train': 1.382581353187561} 08/30/2021 21:31:13 - INFO - __main__ - Step 45653: {'lr': 0.00040013900394331544, 'samples': 8765376, 'steps': 45652, 'loss/train': 1.2670832872390747} 08/30/2021 21:31:14 - INFO - __main__ - Step 45654: {'lr': 0.0004001347607285909, 'samples': 8765568, 'steps': 45653, 'loss/train': 1.1949220895767212} 08/30/2021 21:31:14 - INFO - __main__ - Step 45655: {'lr': 0.000400130517446218, 'samples': 8765760, 'steps': 45654, 'loss/train': 0.4517842233181} 08/30/2021 21:31:14 - INFO - __main__ - Step 45656: {'lr': 0.00040012627409619853, 'samples': 8765952, 'steps': 45655, 'loss/train': 1.4933371543884277} 08/30/2021 21:31:16 - INFO - __main__ - Step 45657: {'lr': 0.00040012203067853457, 'samples': 8766144, 'steps': 45656, 'loss/train': 1.934327483177185} 08/30/2021 21:31:16 - INFO - __main__ - Step 45658: {'lr': 0.0004001177871932279, 'samples': 8766336, 'steps': 45657, 'loss/train': 1.5139893293380737} 08/30/2021 21:31:16 - INFO - __main__ - Step 45659: {'lr': 0.00040011354364028053, 'samples': 8766528, 'steps': 45658, 'loss/train': 1.7372409105300903} 08/30/2021 21:31:17 - INFO - __main__ - Step 45660: {'lr': 0.00040010930001969426, 'samples': 8766720, 'steps': 45659, 'loss/train': 1.2435288429260254} 08/30/2021 21:31:17 - INFO - __main__ - Step 45661: {'lr': 0.00040010505633147106, 'samples': 8766912, 'steps': 45660, 'loss/train': 1.042527198791504} 08/30/2021 21:31:19 - INFO - __main__ - Step 45662: {'lr': 0.00040010081257561283, 'samples': 8767104, 'steps': 45661, 'loss/train': 1.4332000017166138} 08/30/2021 21:31:20 - INFO - __main__ - Step 45663: {'lr': 0.0004000965687521215, 'samples': 8767296, 'steps': 45662, 'loss/train': 1.4125158786773682} 08/30/2021 21:31:20 - INFO - __main__ - Step 45664: {'lr': 0.0004000923248609989, 'samples': 8767488, 'steps': 45663, 'loss/train': 0.5679012537002563} 08/30/2021 21:31:20 - INFO - __main__ - Step 45665: {'lr': 0.00040008808090224714, 'samples': 8767680, 'steps': 45664, 'loss/train': 1.638641119003296} 08/30/2021 21:31:21 - INFO - __main__ - Step 45666: {'lr': 0.0004000838368758679, 'samples': 8767872, 'steps': 45665, 'loss/train': 0.9655702114105225} 08/30/2021 21:31:21 - INFO - __main__ - Step 45667: {'lr': 0.00040007959278186327, 'samples': 8768064, 'steps': 45666, 'loss/train': 0.028480539098381996} 08/30/2021 21:31:23 - INFO - __main__ - Step 45668: {'lr': 0.0004000753486202351, 'samples': 8768256, 'steps': 45667, 'loss/train': 1.4113613367080688} 08/30/2021 21:31:23 - INFO - __main__ - Step 45669: {'lr': 0.0004000711043909853, 'samples': 8768448, 'steps': 45668, 'loss/train': 1.301478624343872} 08/30/2021 21:31:23 - INFO - __main__ - Step 45670: {'lr': 0.0004000668600941157, 'samples': 8768640, 'steps': 45669, 'loss/train': 1.0411229133605957} 08/30/2021 21:31:24 - INFO - __main__ - Step 45671: {'lr': 0.00040006261572962833, 'samples': 8768832, 'steps': 45670, 'loss/train': 1.7721610069274902} 08/30/2021 21:31:24 - INFO - __main__ - Step 45672: {'lr': 0.00040005837129752496, 'samples': 8769024, 'steps': 45671, 'loss/train': 1.4920334815979004} 08/30/2021 21:31:24 - INFO - __main__ - Step 45673: {'lr': 0.00040005412679780777, 'samples': 8769216, 'steps': 45672, 'loss/train': 1.280248761177063} 08/30/2021 21:31:26 - INFO - __main__ - Step 45674: {'lr': 0.00040004988223047843, 'samples': 8769408, 'steps': 45673, 'loss/train': 1.319585919380188} 08/30/2021 21:31:26 - INFO - __main__ - Step 45675: {'lr': 0.0004000456375955389, 'samples': 8769600, 'steps': 45674, 'loss/train': 0.6134784817695618} 08/30/2021 21:31:27 - INFO - __main__ - Step 45676: {'lr': 0.00040004139289299127, 'samples': 8769792, 'steps': 45675, 'loss/train': 1.514657974243164} 08/30/2021 21:31:27 - INFO - __main__ - Step 45677: {'lr': 0.0004000371481228371, 'samples': 8769984, 'steps': 45676, 'loss/train': 1.6194335222244263} 08/30/2021 21:31:28 - INFO - __main__ - Step 45678: {'lr': 0.00040003290328507855, 'samples': 8770176, 'steps': 45677, 'loss/train': 1.5988292694091797} 08/30/2021 21:31:28 - INFO - __main__ - Step 45679: {'lr': 0.0004000286583797176, 'samples': 8770368, 'steps': 45678, 'loss/train': 1.1662352085113525} 08/30/2021 21:31:29 - INFO - __main__ - Step 45680: {'lr': 0.000400024413406756, 'samples': 8770560, 'steps': 45679, 'loss/train': 5.883415222167969} 08/30/2021 21:31:30 - INFO - __main__ - Step 45681: {'lr': 0.0004000201683661957, 'samples': 8770752, 'steps': 45680, 'loss/train': 0.9710056781768799} 08/30/2021 21:31:30 - INFO - __main__ - Step 45682: {'lr': 0.0004000159232580386, 'samples': 8770944, 'steps': 45681, 'loss/train': 1.4683516025543213} 08/30/2021 21:31:31 - INFO - __main__ - Step 45683: {'lr': 0.0004000116780822867, 'samples': 8771136, 'steps': 45682, 'loss/train': 1.7683079242706299} 08/30/2021 21:31:31 - INFO - __main__ - Step 45684: {'lr': 0.0004000074328389418, 'samples': 8771328, 'steps': 45683, 'loss/train': 1.3312487602233887} 08/30/2021 21:31:33 - INFO - __main__ - Step 45685: {'lr': 0.0004000031875280059, 'samples': 8771520, 'steps': 45684, 'loss/train': 1.3476998805999756} 08/30/2021 21:31:34 - INFO - __main__ - Step 45686: {'lr': 0.00039999894214948087, 'samples': 8771712, 'steps': 45685, 'loss/train': 1.0608386993408203} 08/30/2021 21:31:34 - INFO - __main__ - Step 45687: {'lr': 0.00039999469670336864, 'samples': 8771904, 'steps': 45686, 'loss/train': 1.2171738147735596} 08/30/2021 21:31:34 - INFO - __main__ - Step 45688: {'lr': 0.0003999904511896711, 'samples': 8772096, 'steps': 45687, 'loss/train': 1.53910231590271} 08/30/2021 21:31:35 - INFO - __main__ - Step 45689: {'lr': 0.00039998620560839014, 'samples': 8772288, 'steps': 45688, 'loss/train': 1.030777096748352} 08/30/2021 21:31:36 - INFO - __main__ - Step 45690: {'lr': 0.0003999819599595278, 'samples': 8772480, 'steps': 45689, 'loss/train': 0.5401210784912109} 08/30/2021 21:31:37 - INFO - __main__ - Step 45691: {'lr': 0.00039997771424308583, 'samples': 8772672, 'steps': 45690, 'loss/train': 0.47847780585289} 08/30/2021 21:31:37 - INFO - __main__ - Step 45692: {'lr': 0.0003999734684590662, 'samples': 8772864, 'steps': 45691, 'loss/train': 1.5724024772644043} 08/30/2021 21:31:37 - INFO - __main__ - Step 45693: {'lr': 0.0003999692226074709, 'samples': 8773056, 'steps': 45692, 'loss/train': 1.4545607566833496} 08/30/2021 21:31:38 - INFO - __main__ - Step 45694: {'lr': 0.0003999649766883018, 'samples': 8773248, 'steps': 45693, 'loss/train': 1.3308472633361816} 08/30/2021 21:31:39 - INFO - __main__ - Step 45695: {'lr': 0.0003999607307015607, 'samples': 8773440, 'steps': 45694, 'loss/train': 1.6001659631729126} 08/30/2021 21:31:40 - INFO - __main__ - Step 45696: {'lr': 0.00039995648464724966, 'samples': 8773632, 'steps': 45695, 'loss/train': 1.3919919729232788} 08/30/2021 21:31:40 - INFO - __main__ - Step 45697: {'lr': 0.00039995223852537054, 'samples': 8773824, 'steps': 45696, 'loss/train': 1.4473979473114014} 08/30/2021 21:31:40 - INFO - __main__ - Step 45698: {'lr': 0.0003999479923359253, 'samples': 8774016, 'steps': 45697, 'loss/train': 1.136098027229309} 08/30/2021 21:31:41 - INFO - __main__ - Step 45699: {'lr': 0.0003999437460789157, 'samples': 8774208, 'steps': 45698, 'loss/train': 1.8405425548553467} 08/30/2021 21:31:43 - INFO - __main__ - Step 45700: {'lr': 0.0003999394997543439, 'samples': 8774400, 'steps': 45699, 'loss/train': 1.5210239887237549} 08/30/2021 21:31:43 - INFO - __main__ - Step 45701: {'lr': 0.0003999352533622116, 'samples': 8774592, 'steps': 45700, 'loss/train': 0.22797487676143646} 08/30/2021 21:31:43 - INFO - __main__ - Step 45702: {'lr': 0.00039993100690252084, 'samples': 8774784, 'steps': 45701, 'loss/train': 1.781153917312622} 08/30/2021 21:31:44 - INFO - __main__ - Step 45703: {'lr': 0.00039992676037527337, 'samples': 8774976, 'steps': 45702, 'loss/train': 1.6705224514007568} 08/30/2021 21:31:44 - INFO - __main__ - Step 45704: {'lr': 0.0003999225137804713, 'samples': 8775168, 'steps': 45703, 'loss/train': 1.9252976179122925} 08/30/2021 21:31:45 - INFO - __main__ - Step 45705: {'lr': 0.0003999182671181164, 'samples': 8775360, 'steps': 45704, 'loss/train': 1.451731562614441} 08/30/2021 21:31:46 - INFO - __main__ - Step 45706: {'lr': 0.00039991402038821067, 'samples': 8775552, 'steps': 45705, 'loss/train': 0.5823312401771545} 08/30/2021 21:31:46 - INFO - __main__ - Step 45707: {'lr': 0.00039990977359075607, 'samples': 8775744, 'steps': 45706, 'loss/train': 1.7803608179092407} 08/30/2021 21:31:47 - INFO - __main__ - Step 45708: {'lr': 0.00039990552672575436, 'samples': 8775936, 'steps': 45707, 'loss/train': 1.5841566324234009} 08/30/2021 21:31:47 - INFO - __main__ - Step 45709: {'lr': 0.00039990127979320757, 'samples': 8776128, 'steps': 45708, 'loss/train': 1.2163341045379639} 08/30/2021 21:31:49 - INFO - __main__ - Step 45710: {'lr': 0.00039989703279311753, 'samples': 8776320, 'steps': 45709, 'loss/train': 1.7694246768951416} 08/30/2021 21:31:49 - INFO - __main__ - Step 45711: {'lr': 0.00039989278572548625, 'samples': 8776512, 'steps': 45710, 'loss/train': 1.7745155096054077} 08/30/2021 21:31:49 - INFO - __main__ - Step 45712: {'lr': 0.00039988853859031557, 'samples': 8776704, 'steps': 45711, 'loss/train': 1.1858346462249756} 08/30/2021 21:31:50 - INFO - __main__ - Step 45713: {'lr': 0.0003998842913876074, 'samples': 8776896, 'steps': 45712, 'loss/train': 1.0947071313858032} 08/30/2021 21:31:50 - INFO - __main__ - Step 45714: {'lr': 0.0003998800441173637, 'samples': 8777088, 'steps': 45713, 'loss/train': 1.3598521947860718} 08/30/2021 21:31:50 - INFO - __main__ - Step 45715: {'lr': 0.00039987579677958643, 'samples': 8777280, 'steps': 45714, 'loss/train': 1.56691575050354} 08/30/2021 21:31:52 - INFO - __main__ - Step 45716: {'lr': 0.0003998715493742774, 'samples': 8777472, 'steps': 45715, 'loss/train': 1.5442273616790771} 08/30/2021 21:31:52 - INFO - __main__ - Step 45717: {'lr': 0.0003998673019014385, 'samples': 8777664, 'steps': 45716, 'loss/train': 2.142970085144043} 08/30/2021 21:31:53 - INFO - __main__ - Step 45718: {'lr': 0.0003998630543610717, 'samples': 8777856, 'steps': 45717, 'loss/train': 1.1037765741348267} 08/30/2021 21:31:53 - INFO - __main__ - Step 45719: {'lr': 0.00039985880675317897, 'samples': 8778048, 'steps': 45718, 'loss/train': 1.637785792350769} 08/30/2021 21:31:54 - INFO - __main__ - Step 45720: {'lr': 0.0003998545590777622, 'samples': 8778240, 'steps': 45719, 'loss/train': 1.7826141119003296} 08/30/2021 21:31:55 - INFO - __main__ - Step 45721: {'lr': 0.0003998503113348233, 'samples': 8778432, 'steps': 45720, 'loss/train': 1.620204210281372} 08/30/2021 21:31:55 - INFO - __main__ - Step 45722: {'lr': 0.0003998460635243641, 'samples': 8778624, 'steps': 45721, 'loss/train': 1.5672633647918701} 08/30/2021 21:31:56 - INFO - __main__ - Step 45723: {'lr': 0.00039984181564638654, 'samples': 8778816, 'steps': 45722, 'loss/train': 1.310011625289917} 08/30/2021 21:31:56 - INFO - __main__ - Step 45724: {'lr': 0.00039983756770089264, 'samples': 8779008, 'steps': 45723, 'loss/train': 1.7102843523025513} 08/30/2021 21:31:56 - INFO - __main__ - Step 45725: {'lr': 0.0003998333196878843, 'samples': 8779200, 'steps': 45724, 'loss/train': 1.3844170570373535} 08/30/2021 21:31:58 - INFO - __main__ - Step 45726: {'lr': 0.00039982907160736325, 'samples': 8779392, 'steps': 45725, 'loss/train': 1.552479863166809} 08/30/2021 21:31:59 - INFO - __main__ - Step 45727: {'lr': 0.00039982482345933155, 'samples': 8779584, 'steps': 45726, 'loss/train': 1.3059972524642944} 08/30/2021 21:31:59 - INFO - __main__ - Step 45728: {'lr': 0.00039982057524379124, 'samples': 8779776, 'steps': 45727, 'loss/train': 1.1507110595703125} 08/30/2021 21:31:59 - INFO - __main__ - Step 45729: {'lr': 0.00039981632696074396, 'samples': 8779968, 'steps': 45728, 'loss/train': 1.6962097883224487} 08/30/2021 21:32:00 - INFO - __main__ - Step 45730: {'lr': 0.00039981207861019175, 'samples': 8780160, 'steps': 45729, 'loss/train': 1.4264379739761353} 08/30/2021 21:32:01 - INFO - __main__ - Step 45731: {'lr': 0.0003998078301921365, 'samples': 8780352, 'steps': 45730, 'loss/train': 1.6870983839035034} 08/30/2021 21:32:02 - INFO - __main__ - Step 45732: {'lr': 0.00039980358170658026, 'samples': 8780544, 'steps': 45731, 'loss/train': 0.5918977856636047} 08/30/2021 21:32:02 - INFO - __main__ - Step 45733: {'lr': 0.0003997993331535248, 'samples': 8780736, 'steps': 45732, 'loss/train': 1.3852952718734741} 08/30/2021 21:32:03 - INFO - __main__ - Step 45734: {'lr': 0.0003997950845329721, 'samples': 8780928, 'steps': 45733, 'loss/train': 0.7267405390739441} 08/30/2021 21:32:03 - INFO - __main__ - Step 45735: {'lr': 0.000399790835844924, 'samples': 8781120, 'steps': 45734, 'loss/train': 1.3988796472549438} 08/30/2021 21:32:03 - INFO - __main__ - Step 45736: {'lr': 0.00039978658708938244, 'samples': 8781312, 'steps': 45735, 'loss/train': 0.04054870456457138} 08/30/2021 21:32:05 - INFO - __main__ - Step 45737: {'lr': 0.00039978233826634934, 'samples': 8781504, 'steps': 45736, 'loss/train': 0.04201611131429672} 08/30/2021 21:32:06 - INFO - __main__ - Step 45738: {'lr': 0.0003997780893758267, 'samples': 8781696, 'steps': 45737, 'loss/train': 1.4057588577270508} 08/30/2021 21:32:06 - INFO - __main__ - Step 45739: {'lr': 0.0003997738404178164, 'samples': 8781888, 'steps': 45738, 'loss/train': 1.3034766912460327} 08/30/2021 21:32:07 - INFO - __main__ - Step 45740: {'lr': 0.00039976959139232017, 'samples': 8782080, 'steps': 45739, 'loss/train': 1.550410270690918} 08/30/2021 21:32:07 - INFO - __main__ - Step 45741: {'lr': 0.0003997653422993402, 'samples': 8782272, 'steps': 45740, 'loss/train': 1.3442806005477905} 08/30/2021 21:32:09 - INFO - __main__ - Step 45742: {'lr': 0.0003997610931388782, 'samples': 8782464, 'steps': 45741, 'loss/train': 2.68050217628479} 08/30/2021 21:32:09 - INFO - __main__ - Step 45743: {'lr': 0.0003997568439109363, 'samples': 8782656, 'steps': 45742, 'loss/train': 1.544089913368225} 08/30/2021 21:32:09 - INFO - __main__ - Step 45744: {'lr': 0.00039975259461551613, 'samples': 8782848, 'steps': 45743, 'loss/train': 1.8000953197479248} 08/30/2021 21:32:10 - INFO - __main__ - Step 45745: {'lr': 0.0003997483452526198, 'samples': 8783040, 'steps': 45744, 'loss/train': 1.804950475692749} 08/30/2021 21:32:10 - INFO - __main__ - Step 45746: {'lr': 0.0003997440958222491, 'samples': 8783232, 'steps': 45745, 'loss/train': 1.5842504501342773} 08/30/2021 21:32:12 - INFO - __main__ - Step 45747: {'lr': 0.0003997398463244062, 'samples': 8783424, 'steps': 45746, 'loss/train': 2.106240749359131} 08/30/2021 21:32:12 - INFO - __main__ - Step 45748: {'lr': 0.00039973559675909274, 'samples': 8783616, 'steps': 45747, 'loss/train': 1.1705864667892456} 08/30/2021 21:32:12 - INFO - __main__ - Step 45749: {'lr': 0.00039973134712631067, 'samples': 8783808, 'steps': 45748, 'loss/train': 1.3314101696014404} 08/30/2021 21:32:13 - INFO - __main__ - Step 45750: {'lr': 0.00039972709742606207, 'samples': 8784000, 'steps': 45749, 'loss/train': 1.6287176609039307} 08/30/2021 21:32:13 - INFO - __main__ - Step 45751: {'lr': 0.00039972284765834866, 'samples': 8784192, 'steps': 45750, 'loss/train': 2.1587624549865723} 08/30/2021 21:32:15 - INFO - __main__ - Step 45752: {'lr': 0.00039971859782317245, 'samples': 8784384, 'steps': 45751, 'loss/train': 1.4193994998931885} 08/30/2021 21:32:15 - INFO - __main__ - Step 45753: {'lr': 0.0003997143479205354, 'samples': 8784576, 'steps': 45752, 'loss/train': 1.2462074756622314} 08/30/2021 21:32:16 - INFO - __main__ - Step 45754: {'lr': 0.0003997100979504394, 'samples': 8784768, 'steps': 45753, 'loss/train': 0.04681426286697388} 08/30/2021 21:32:16 - INFO - __main__ - Step 45755: {'lr': 0.00039970584791288626, 'samples': 8784960, 'steps': 45754, 'loss/train': 1.263257622718811} 08/30/2021 21:32:16 - INFO - __main__ - Step 45756: {'lr': 0.000399701597807878, 'samples': 8785152, 'steps': 45755, 'loss/train': 1.7074925899505615} 08/30/2021 21:32:18 - INFO - __main__ - Step 45757: {'lr': 0.00039969734763541657, 'samples': 8785344, 'steps': 45756, 'loss/train': 1.359625220298767} 08/30/2021 21:32:18 - INFO - __main__ - Step 45758: {'lr': 0.00039969309739550373, 'samples': 8785536, 'steps': 45757, 'loss/train': 1.2389707565307617} 08/30/2021 21:32:19 - INFO - __main__ - Step 45759: {'lr': 0.0003996888470881416, 'samples': 8785728, 'steps': 45758, 'loss/train': 1.407562255859375} 08/30/2021 21:32:19 - INFO - __main__ - Step 45760: {'lr': 0.0003996845967133319, 'samples': 8785920, 'steps': 45759, 'loss/train': 1.3659547567367554} 08/30/2021 21:32:19 - INFO - __main__ - Step 45761: {'lr': 0.0003996803462710766, 'samples': 8786112, 'steps': 45760, 'loss/train': 1.514388918876648} 08/30/2021 21:32:21 - INFO - __main__ - Step 45762: {'lr': 0.00039967609576137774, 'samples': 8786304, 'steps': 45761, 'loss/train': 1.777955174446106} 08/30/2021 21:32:22 - INFO - __main__ - Step 45763: {'lr': 0.0003996718451842371, 'samples': 8786496, 'steps': 45762, 'loss/train': 1.290058970451355} 08/30/2021 21:32:22 - INFO - __main__ - Step 45764: {'lr': 0.00039966759453965664, 'samples': 8786688, 'steps': 45763, 'loss/train': 1.766306757926941} 08/30/2021 21:32:22 - INFO - __main__ - Step 45765: {'lr': 0.00039966334382763826, 'samples': 8786880, 'steps': 45764, 'loss/train': 1.765210747718811} 08/30/2021 21:32:23 - INFO - __main__ - Step 45766: {'lr': 0.00039965909304818387, 'samples': 8787072, 'steps': 45765, 'loss/train': 1.630203366279602} 08/30/2021 21:32:25 - INFO - __main__ - Step 45767: {'lr': 0.00039965484220129546, 'samples': 8787264, 'steps': 45766, 'loss/train': 1.7340587377548218} 08/30/2021 21:32:25 - INFO - __main__ - Step 45768: {'lr': 0.0003996505912869749, 'samples': 8787456, 'steps': 45767, 'loss/train': 1.8549233675003052} 08/30/2021 21:32:25 - INFO - __main__ - Step 45769: {'lr': 0.000399646340305224, 'samples': 8787648, 'steps': 45768, 'loss/train': 0.6560509204864502} 08/30/2021 21:32:26 - INFO - __main__ - Step 45770: {'lr': 0.00039964208925604485, 'samples': 8787840, 'steps': 45769, 'loss/train': 0.8023548126220703} 08/30/2021 21:32:26 - INFO - __main__ - Step 45771: {'lr': 0.0003996378381394392, 'samples': 8788032, 'steps': 45770, 'loss/train': 1.5847631692886353} 08/30/2021 21:32:27 - INFO - __main__ - Step 45772: {'lr': 0.00039963358695540907, 'samples': 8788224, 'steps': 45771, 'loss/train': 1.3048385381698608} 08/30/2021 21:32:28 - INFO - __main__ - Step 45773: {'lr': 0.0003996293357039564, 'samples': 8788416, 'steps': 45772, 'loss/train': 1.6023977994918823} 08/30/2021 21:32:29 - INFO - __main__ - Step 45774: {'lr': 0.0003996250843850831, 'samples': 8788608, 'steps': 45773, 'loss/train': 1.0310152769088745} 08/30/2021 21:32:29 - INFO - __main__ - Step 45775: {'lr': 0.000399620832998791, 'samples': 8788800, 'steps': 45774, 'loss/train': 1.878286361694336} 08/30/2021 21:32:30 - INFO - __main__ - Step 45776: {'lr': 0.000399616581545082, 'samples': 8788992, 'steps': 45775, 'loss/train': 1.5252773761749268} 08/30/2021 21:32:30 - INFO - __main__ - Step 45777: {'lr': 0.0003996123300239581, 'samples': 8789184, 'steps': 45776, 'loss/train': 1.6312905550003052} 08/30/2021 21:32:30 - INFO - __main__ - Step 45778: {'lr': 0.0003996080784354212, 'samples': 8789376, 'steps': 45777, 'loss/train': 1.090775728225708} 08/30/2021 21:32:32 - INFO - __main__ - Step 45779: {'lr': 0.0003996038267794733, 'samples': 8789568, 'steps': 45778, 'loss/train': 0.096169114112854} 08/30/2021 21:32:32 - INFO - __main__ - Step 45780: {'lr': 0.0003995995750561161, 'samples': 8789760, 'steps': 45779, 'loss/train': 1.1614532470703125} 08/30/2021 21:32:33 - INFO - __main__ - Step 45781: {'lr': 0.00039959532326535175, 'samples': 8789952, 'steps': 45780, 'loss/train': 1.170967936515808} 08/30/2021 21:32:33 - INFO - __main__ - Step 45782: {'lr': 0.000399591071407182, 'samples': 8790144, 'steps': 45781, 'loss/train': 1.3381215333938599} 08/30/2021 21:32:33 - INFO - __main__ - Step 45783: {'lr': 0.0003995868194816088, 'samples': 8790336, 'steps': 45782, 'loss/train': 1.15363609790802} 08/30/2021 21:32:35 - INFO - __main__ - Step 45784: {'lr': 0.0003995825674886341, 'samples': 8790528, 'steps': 45783, 'loss/train': 1.415030598640442} 08/30/2021 21:32:35 - INFO - __main__ - Step 45785: {'lr': 0.00039957831542825983, 'samples': 8790720, 'steps': 45784, 'loss/train': 1.0968674421310425} 08/30/2021 21:32:36 - INFO - __main__ - Step 45786: {'lr': 0.0003995740633004878, 'samples': 8790912, 'steps': 45785, 'loss/train': 1.6236929893493652} 08/30/2021 21:32:36 - INFO - __main__ - Step 45787: {'lr': 0.00039956981110532007, 'samples': 8791104, 'steps': 45786, 'loss/train': 1.8155336380004883} 08/30/2021 21:32:36 - INFO - __main__ - Step 45788: {'lr': 0.0003995655588427586, 'samples': 8791296, 'steps': 45787, 'loss/train': 1.5406101942062378} 08/30/2021 21:32:38 - INFO - __main__ - Step 45789: {'lr': 0.00039956130651280504, 'samples': 8791488, 'steps': 45788, 'loss/train': 1.2359778881072998} 08/30/2021 21:32:38 - INFO - __main__ - Step 45790: {'lr': 0.0003995570541154615, 'samples': 8791680, 'steps': 45789, 'loss/train': 1.6529431343078613} 08/30/2021 21:32:39 - INFO - __main__ - Step 45791: {'lr': 0.0003995528016507298, 'samples': 8791872, 'steps': 45790, 'loss/train': 0.9503229260444641} 08/30/2021 21:32:39 - INFO - __main__ - Step 45792: {'lr': 0.000399548549118612, 'samples': 8792064, 'steps': 45791, 'loss/train': 0.8938019275665283} 08/30/2021 21:32:39 - INFO - __main__ - Step 45793: {'lr': 0.00039954429651910993, 'samples': 8792256, 'steps': 45792, 'loss/train': 1.4242010116577148} 08/30/2021 21:32:42 - INFO - __main__ - Step 45794: {'lr': 0.00039954004385222555, 'samples': 8792448, 'steps': 45793, 'loss/train': 1.5062648057937622} 08/30/2021 21:32:42 - INFO - __main__ - Step 45795: {'lr': 0.00039953579111796065, 'samples': 8792640, 'steps': 45794, 'loss/train': 1.07527494430542} 08/30/2021 21:32:42 - INFO - __main__ - Step 45796: {'lr': 0.00039953153831631726, 'samples': 8792832, 'steps': 45795, 'loss/train': 2.9385814666748047} 08/30/2021 21:32:43 - INFO - __main__ - Step 45797: {'lr': 0.0003995272854472972, 'samples': 8793024, 'steps': 45796, 'loss/train': 1.1036850214004517} 08/30/2021 21:32:43 - INFO - __main__ - Step 45798: {'lr': 0.00039952303251090254, 'samples': 8793216, 'steps': 45797, 'loss/train': 1.6317808628082275} 08/30/2021 21:32:44 - INFO - __main__ - Step 45799: {'lr': 0.00039951877950713513, 'samples': 8793408, 'steps': 45798, 'loss/train': 1.0030560493469238} 08/30/2021 21:32:45 - INFO - __main__ - Step 45800: {'lr': 0.0003995145264359968, 'samples': 8793600, 'steps': 45799, 'loss/train': 1.8060802221298218} 08/30/2021 21:32:45 - INFO - __main__ - Step 45801: {'lr': 0.00039951027329748957, 'samples': 8793792, 'steps': 45800, 'loss/train': 1.2176737785339355} 08/30/2021 21:32:46 - INFO - __main__ - Step 45802: {'lr': 0.0003995060200916153, 'samples': 8793984, 'steps': 45801, 'loss/train': 1.5483342409133911} 08/30/2021 21:32:46 - INFO - __main__ - Step 45803: {'lr': 0.0003995017668183759, 'samples': 8794176, 'steps': 45802, 'loss/train': 1.2297035455703735} 08/30/2021 21:32:47 - INFO - __main__ - Step 45804: {'lr': 0.0003994975134777733, 'samples': 8794368, 'steps': 45803, 'loss/train': 1.6194614171981812} 08/30/2021 21:32:48 - INFO - __main__ - Step 45805: {'lr': 0.00039949326006980944, 'samples': 8794560, 'steps': 45804, 'loss/train': 0.9340513348579407} 08/30/2021 21:32:49 - INFO - __main__ - Step 45806: {'lr': 0.0003994890065944863, 'samples': 8794752, 'steps': 45805, 'loss/train': 0.7877193689346313} 08/30/2021 21:32:49 - INFO - __main__ - Step 45807: {'lr': 0.00039948475305180567, 'samples': 8794944, 'steps': 45806, 'loss/train': 1.4938911199569702} 08/30/2021 21:32:50 - INFO - __main__ - Step 45808: {'lr': 0.0003994804994417695, 'samples': 8795136, 'steps': 45807, 'loss/train': 0.08275206387042999} 08/30/2021 21:32:50 - INFO - __main__ - Step 45809: {'lr': 0.0003994762457643797, 'samples': 8795328, 'steps': 45808, 'loss/train': 1.5253511667251587} 08/30/2021 21:32:52 - INFO - __main__ - Step 45810: {'lr': 0.0003994719920196383, 'samples': 8795520, 'steps': 45809, 'loss/train': 0.14636556804180145} 08/30/2021 21:32:52 - INFO - __main__ - Step 45811: {'lr': 0.00039946773820754704, 'samples': 8795712, 'steps': 45810, 'loss/train': 1.3765766620635986} 08/30/2021 21:32:52 - INFO - __main__ - Step 45812: {'lr': 0.00039946348432810797, 'samples': 8795904, 'steps': 45811, 'loss/train': 1.2858155965805054} 08/30/2021 21:32:53 - INFO - __main__ - Step 45813: {'lr': 0.0003994592303813229, 'samples': 8796096, 'steps': 45812, 'loss/train': 1.4192514419555664} 08/30/2021 21:32:53 - INFO - __main__ - Step 45814: {'lr': 0.00039945497636719384, 'samples': 8796288, 'steps': 45813, 'loss/train': 1.5997782945632935} 08/30/2021 21:32:53 - INFO - __main__ - Step 45815: {'lr': 0.00039945072228572275, 'samples': 8796480, 'steps': 45814, 'loss/train': 0.4692443311214447} 08/30/2021 21:32:55 - INFO - __main__ - Step 45816: {'lr': 0.0003994464681369114, 'samples': 8796672, 'steps': 45815, 'loss/train': 1.213433027267456} 08/30/2021 21:32:55 - INFO - __main__ - Step 45817: {'lr': 0.0003994422139207618, 'samples': 8796864, 'steps': 45816, 'loss/train': 1.4724456071853638} 08/30/2021 21:32:56 - INFO - __main__ - Step 45818: {'lr': 0.00039943795963727583, 'samples': 8797056, 'steps': 45817, 'loss/train': 0.6934868097305298} 08/30/2021 21:32:56 - INFO - __main__ - Step 45819: {'lr': 0.0003994337052864554, 'samples': 8797248, 'steps': 45818, 'loss/train': 0.8116896152496338} 08/30/2021 21:32:56 - INFO - __main__ - Step 45820: {'lr': 0.00039942945086830246, 'samples': 8797440, 'steps': 45819, 'loss/train': 1.499266505241394} 08/30/2021 21:32:58 - INFO - __main__ - Step 45821: {'lr': 0.00039942519638281893, 'samples': 8797632, 'steps': 45820, 'loss/train': 1.9684098958969116} 08/30/2021 21:32:58 - INFO - __main__ - Step 45822: {'lr': 0.0003994209418300068, 'samples': 8797824, 'steps': 45821, 'loss/train': 1.5065957307815552} 08/30/2021 21:32:59 - INFO - __main__ - Step 45823: {'lr': 0.0003994166872098677, 'samples': 8798016, 'steps': 45822, 'loss/train': 1.4278074502944946} 08/30/2021 21:32:59 - INFO - __main__ - Step 45824: {'lr': 0.0003994124325224039, 'samples': 8798208, 'steps': 45823, 'loss/train': 1.2310861349105835} 08/30/2021 21:32:59 - INFO - __main__ - Step 45825: {'lr': 0.00039940817776761706, 'samples': 8798400, 'steps': 45824, 'loss/train': 1.5549328327178955} 08/30/2021 21:33:01 - INFO - __main__ - Step 45826: {'lr': 0.0003994039229455093, 'samples': 8798592, 'steps': 45825, 'loss/train': 1.5929532051086426} 08/30/2021 21:33:02 - INFO - __main__ - Step 45827: {'lr': 0.00039939966805608234, 'samples': 8798784, 'steps': 45826, 'loss/train': 1.0453182458877563} 08/30/2021 21:33:02 - INFO - __main__ - Step 45828: {'lr': 0.0003993954130993383, 'samples': 8798976, 'steps': 45827, 'loss/train': 1.3045328855514526} 08/30/2021 21:33:02 - INFO - __main__ - Step 45829: {'lr': 0.0003993911580752789, 'samples': 8799168, 'steps': 45828, 'loss/train': 2.1668474674224854} 08/30/2021 21:33:03 - INFO - __main__ - Step 45830: {'lr': 0.00039938690298390624, 'samples': 8799360, 'steps': 45829, 'loss/train': 1.710523247718811} 08/30/2021 21:33:04 - INFO - __main__ - Step 45831: {'lr': 0.00039938264782522206, 'samples': 8799552, 'steps': 45830, 'loss/train': 1.1563140153884888} 08/30/2021 21:33:05 - INFO - __main__ - Step 45832: {'lr': 0.0003993783925992284, 'samples': 8799744, 'steps': 45831, 'loss/train': 1.2424277067184448} 08/30/2021 21:33:05 - INFO - __main__ - Step 45833: {'lr': 0.00039937413730592713, 'samples': 8799936, 'steps': 45832, 'loss/train': 2.8488364219665527} 08/30/2021 21:33:05 - INFO - __main__ - Step 45834: {'lr': 0.0003993698819453202, 'samples': 8800128, 'steps': 45833, 'loss/train': 1.3206452131271362} 08/30/2021 21:33:06 - INFO - __main__ - Step 45835: {'lr': 0.00039936562651740956, 'samples': 8800320, 'steps': 45834, 'loss/train': 1.7306476831436157} 08/30/2021 21:33:07 - INFO - __main__ - Step 45836: {'lr': 0.00039936137102219695, 'samples': 8800512, 'steps': 45835, 'loss/train': 1.238366961479187} 08/30/2021 21:33:07 - INFO - __main__ - Step 45837: {'lr': 0.0003993571154596845, 'samples': 8800704, 'steps': 45836, 'loss/train': 1.3619805574417114} 08/30/2021 21:33:08 - INFO - __main__ - Step 45838: {'lr': 0.00039935285982987403, 'samples': 8800896, 'steps': 45837, 'loss/train': 1.4047608375549316} 08/30/2021 21:33:08 - INFO - __main__ - Step 45839: {'lr': 0.0003993486041327674, 'samples': 8801088, 'steps': 45838, 'loss/train': 1.5239295959472656} 08/30/2021 21:33:08 - INFO - __main__ - Step 45840: {'lr': 0.00039934434836836664, 'samples': 8801280, 'steps': 45839, 'loss/train': 1.3367984294891357} 08/30/2021 21:33:10 - INFO - __main__ - Step 45841: {'lr': 0.00039934009253667356, 'samples': 8801472, 'steps': 45840, 'loss/train': 1.990939974784851} 08/30/2021 21:33:11 - INFO - __main__ - Step 45842: {'lr': 0.0003993358366376903, 'samples': 8801664, 'steps': 45841, 'loss/train': 1.1347744464874268} 08/30/2021 21:33:11 - INFO - __main__ - Step 45843: {'lr': 0.0003993315806714185, 'samples': 8801856, 'steps': 45842, 'loss/train': 0.45819583535194397} 08/30/2021 21:33:11 - INFO - __main__ - Step 45844: {'lr': 0.0003993273246378602, 'samples': 8802048, 'steps': 45843, 'loss/train': 1.4478795528411865} 08/30/2021 21:33:12 - INFO - __main__ - Step 45845: {'lr': 0.00039932306853701735, 'samples': 8802240, 'steps': 45844, 'loss/train': 1.007699728012085} 08/30/2021 21:33:14 - INFO - __main__ - Step 45846: {'lr': 0.0003993188123688918, 'samples': 8802432, 'steps': 45845, 'loss/train': 1.6348592042922974} 08/30/2021 21:33:14 - INFO - __main__ - Step 45847: {'lr': 0.00039931455613348546, 'samples': 8802624, 'steps': 45846, 'loss/train': 1.3800431489944458} 08/30/2021 21:33:14 - INFO - __main__ - Step 45848: {'lr': 0.0003993102998308004, 'samples': 8802816, 'steps': 45847, 'loss/train': 1.3395081758499146} 08/30/2021 21:33:15 - INFO - __main__ - Step 45849: {'lr': 0.0003993060434608383, 'samples': 8803008, 'steps': 45848, 'loss/train': 1.1784669160842896} 08/30/2021 21:33:15 - INFO - __main__ - Step 45850: {'lr': 0.0003993017870236012, 'samples': 8803200, 'steps': 45849, 'loss/train': 1.4567183256149292} 08/30/2021 21:33:17 - INFO - __main__ - Step 45851: {'lr': 0.0003992975305190911, 'samples': 8803392, 'steps': 45850, 'loss/train': 1.535145878791809} 08/30/2021 21:33:17 - INFO - __main__ - Step 45852: {'lr': 0.0003992932739473098, 'samples': 8803584, 'steps': 45851, 'loss/train': 1.2231274843215942} 08/30/2021 21:33:18 - INFO - __main__ - Step 45853: {'lr': 0.0003992890173082593, 'samples': 8803776, 'steps': 45852, 'loss/train': 1.3898508548736572} 08/30/2021 21:33:18 - INFO - __main__ - Step 45854: {'lr': 0.00039928476060194137, 'samples': 8803968, 'steps': 45853, 'loss/train': 1.2472736835479736} 08/30/2021 21:33:18 - INFO - __main__ - Step 45855: {'lr': 0.0003992805038283581, 'samples': 8804160, 'steps': 45854, 'loss/train': 1.6525698900222778} 08/30/2021 21:33:19 - INFO - __main__ - Step 45856: {'lr': 0.0003992762469875113, 'samples': 8804352, 'steps': 45855, 'loss/train': 1.320794701576233} 08/30/2021 21:33:21 - INFO - __main__ - Step 45857: {'lr': 0.00039927199007940294, 'samples': 8804544, 'steps': 45856, 'loss/train': 1.7343603372573853} 08/30/2021 21:33:21 - INFO - __main__ - Step 45858: {'lr': 0.00039926773310403497, 'samples': 8804736, 'steps': 45857, 'loss/train': 1.3271514177322388} 08/30/2021 21:33:21 - INFO - __main__ - Step 45859: {'lr': 0.0003992634760614092, 'samples': 8804928, 'steps': 45858, 'loss/train': 1.2711429595947266} 08/30/2021 21:33:22 - INFO - __main__ - Step 45860: {'lr': 0.00039925921895152765, 'samples': 8805120, 'steps': 45859, 'loss/train': 1.6370981931686401} 08/30/2021 21:33:22 - INFO - __main__ - Step 45861: {'lr': 0.00039925496177439226, 'samples': 8805312, 'steps': 45860, 'loss/train': 1.435247778892517} 08/30/2021 21:33:23 - INFO - __main__ - Step 45862: {'lr': 0.0003992507045300048, 'samples': 8805504, 'steps': 45861, 'loss/train': 1.2945324182510376} 08/30/2021 21:33:24 - INFO - __main__ - Step 45863: {'lr': 0.00039924644721836734, 'samples': 8805696, 'steps': 45862, 'loss/train': 0.9160441756248474} 08/30/2021 21:33:24 - INFO - __main__ - Step 45864: {'lr': 0.0003992421898394817, 'samples': 8805888, 'steps': 45863, 'loss/train': 2.2872025966644287} 08/30/2021 21:33:25 - INFO - __main__ - Step 45865: {'lr': 0.00039923793239334974, 'samples': 8806080, 'steps': 45864, 'loss/train': 1.0798128843307495} 08/30/2021 21:33:25 - INFO - __main__ - Step 45866: {'lr': 0.0003992336748799736, 'samples': 8806272, 'steps': 45865, 'loss/train': 1.1462929248809814} 08/30/2021 21:33:26 - INFO - __main__ - Step 45867: {'lr': 0.00039922941729935503, 'samples': 8806464, 'steps': 45866, 'loss/train': 0.9772617220878601} 08/30/2021 21:33:27 - INFO - __main__ - Step 45868: {'lr': 0.000399225159651496, 'samples': 8806656, 'steps': 45867, 'loss/train': 1.1342010498046875} 08/30/2021 21:33:27 - INFO - __main__ - Step 45869: {'lr': 0.0003992209019363984, 'samples': 8806848, 'steps': 45868, 'loss/train': 1.7325915098190308} 08/30/2021 21:33:28 - INFO - __main__ - Step 45870: {'lr': 0.0003992166441540641, 'samples': 8807040, 'steps': 45869, 'loss/train': 1.0027644634246826} 08/30/2021 21:33:28 - INFO - __main__ - Step 45871: {'lr': 0.00039921238630449515, 'samples': 8807232, 'steps': 45870, 'loss/train': 1.4486463069915771} 08/30/2021 21:33:28 - INFO - __main__ - Step 45872: {'lr': 0.0003992081283876934, 'samples': 8807424, 'steps': 45871, 'loss/train': 1.6098607778549194} 08/30/2021 21:33:30 - INFO - __main__ - Step 45873: {'lr': 0.00039920387040366076, 'samples': 8807616, 'steps': 45872, 'loss/train': 0.7041446566581726} 08/30/2021 21:33:31 - INFO - __main__ - Step 45874: {'lr': 0.00039919961235239913, 'samples': 8807808, 'steps': 45873, 'loss/train': 1.3921667337417603} 08/30/2021 21:33:31 - INFO - __main__ - Step 45875: {'lr': 0.0003991953542339105, 'samples': 8808000, 'steps': 45874, 'loss/train': 0.9629362225532532} 08/30/2021 21:33:31 - INFO - __main__ - Step 45876: {'lr': 0.00039919109604819676, 'samples': 8808192, 'steps': 45875, 'loss/train': 1.245280385017395} 08/30/2021 21:33:32 - INFO - __main__ - Step 45877: {'lr': 0.00039918683779525976, 'samples': 8808384, 'steps': 45876, 'loss/train': 1.3967478275299072} 08/30/2021 21:33:33 - INFO - __main__ - Step 45878: {'lr': 0.0003991825794751015, 'samples': 8808576, 'steps': 45877, 'loss/train': 1.1662044525146484} 08/30/2021 21:33:34 - INFO - __main__ - Step 45879: {'lr': 0.0003991783210877239, 'samples': 8808768, 'steps': 45878, 'loss/train': 1.7753769159317017} 08/30/2021 21:33:34 - INFO - __main__ - Step 45880: {'lr': 0.00039917406263312885, 'samples': 8808960, 'steps': 45879, 'loss/train': 1.012062668800354} 08/30/2021 21:33:34 - INFO - __main__ - Step 45881: {'lr': 0.0003991698041113182, 'samples': 8809152, 'steps': 45880, 'loss/train': 1.456717848777771} 08/30/2021 21:33:35 - INFO - __main__ - Step 45882: {'lr': 0.000399165545522294, 'samples': 8809344, 'steps': 45881, 'loss/train': 1.4315998554229736} 08/30/2021 21:33:36 - INFO - __main__ - Step 45883: {'lr': 0.0003991612868660581, 'samples': 8809536, 'steps': 45882, 'loss/train': 1.0726063251495361} 08/30/2021 21:33:37 - INFO - __main__ - Step 45884: {'lr': 0.0003991570281426124, 'samples': 8809728, 'steps': 45883, 'loss/train': 1.6751062870025635} 08/30/2021 21:33:37 - INFO - __main__ - Step 45885: {'lr': 0.0003991527693519589, 'samples': 8809920, 'steps': 45884, 'loss/train': 1.5585232973098755} 08/30/2021 21:33:37 - INFO - __main__ - Step 45886: {'lr': 0.0003991485104940994, 'samples': 8810112, 'steps': 45885, 'loss/train': 1.547220230102539} 08/30/2021 21:33:38 - INFO - __main__ - Step 45887: {'lr': 0.0003991442515690359, 'samples': 8810304, 'steps': 45886, 'loss/train': 1.4062625169754028} 08/30/2021 21:33:40 - INFO - __main__ - Step 45888: {'lr': 0.00039913999257677025, 'samples': 8810496, 'steps': 45887, 'loss/train': 1.7330727577209473} 08/30/2021 21:33:40 - INFO - __main__ - Step 45889: {'lr': 0.0003991357335173045, 'samples': 8810688, 'steps': 45888, 'loss/train': 1.272483468055725} 08/30/2021 21:33:40 - INFO - __main__ - Step 45890: {'lr': 0.0003991314743906405, 'samples': 8810880, 'steps': 45889, 'loss/train': 1.3651748895645142} 08/30/2021 21:33:41 - INFO - __main__ - Step 45891: {'lr': 0.0003991272151967801, 'samples': 8811072, 'steps': 45890, 'loss/train': 0.0798591822385788} 08/30/2021 21:33:41 - INFO - __main__ - Step 45892: {'lr': 0.0003991229559357253, 'samples': 8811264, 'steps': 45891, 'loss/train': 0.03657440096139908} 08/30/2021 21:33:43 - INFO - __main__ - Step 45893: {'lr': 0.00039911869660747804, 'samples': 8811456, 'steps': 45892, 'loss/train': 1.5833854675292969} 08/30/2021 21:33:43 - INFO - __main__ - Step 45894: {'lr': 0.0003991144372120401, 'samples': 8811648, 'steps': 45893, 'loss/train': 1.4732928276062012} 08/30/2021 21:33:43 - INFO - __main__ - Step 45895: {'lr': 0.0003991101777494136, 'samples': 8811840, 'steps': 45894, 'loss/train': 1.619711995124817} 08/30/2021 21:33:44 - INFO - __main__ - Step 45896: {'lr': 0.0003991059182196003, 'samples': 8812032, 'steps': 45895, 'loss/train': 2.6794183254241943} 08/30/2021 21:33:44 - INFO - __main__ - Step 45897: {'lr': 0.00039910165862260216, 'samples': 8812224, 'steps': 45896, 'loss/train': 0.8295580744743347} 08/30/2021 21:33:47 - INFO - __main__ - Step 45898: {'lr': 0.0003990973989584211, 'samples': 8812416, 'steps': 45897, 'loss/train': 1.5137559175491333} 08/30/2021 21:33:47 - INFO - __main__ - Step 45899: {'lr': 0.00039909313922705913, 'samples': 8812608, 'steps': 45898, 'loss/train': 0.6221747398376465} 08/30/2021 21:33:47 - INFO - __main__ - Step 45900: {'lr': 0.000399088879428518, 'samples': 8812800, 'steps': 45899, 'loss/train': 1.3043019771575928} 08/30/2021 21:33:48 - INFO - __main__ - Step 45901: {'lr': 0.0003990846195627998, 'samples': 8812992, 'steps': 45900, 'loss/train': 1.4080753326416016} 08/30/2021 21:33:48 - INFO - __main__ - Step 45902: {'lr': 0.0003990803596299064, 'samples': 8813184, 'steps': 45901, 'loss/train': 1.4008264541625977} 08/30/2021 21:33:48 - INFO - __main__ - Step 45903: {'lr': 0.0003990760996298396, 'samples': 8813376, 'steps': 45902, 'loss/train': 1.3440762758255005} 08/30/2021 21:33:50 - INFO - __main__ - Step 45904: {'lr': 0.0003990718395626014, 'samples': 8813568, 'steps': 45903, 'loss/train': 0.16512420773506165} 08/30/2021 21:33:50 - INFO - __main__ - Step 45905: {'lr': 0.0003990675794281938, 'samples': 8813760, 'steps': 45904, 'loss/train': 1.7513208389282227} 08/30/2021 21:33:51 - INFO - __main__ - Step 45906: {'lr': 0.00039906331922661857, 'samples': 8813952, 'steps': 45905, 'loss/train': 1.7248902320861816} 08/30/2021 21:33:51 - INFO - __main__ - Step 45907: {'lr': 0.00039905905895787775, 'samples': 8814144, 'steps': 45906, 'loss/train': 1.5553399324417114} 08/30/2021 21:33:52 - INFO - __main__ - Step 45908: {'lr': 0.00039905479862197327, 'samples': 8814336, 'steps': 45907, 'loss/train': 0.7354121208190918} 08/30/2021 21:33:53 - INFO - __main__ - Step 45909: {'lr': 0.00039905053821890697, 'samples': 8814528, 'steps': 45908, 'loss/train': 1.3031671047210693} 08/30/2021 21:33:53 - INFO - __main__ - Step 45910: {'lr': 0.0003990462777486808, 'samples': 8814720, 'steps': 45909, 'loss/train': 1.3022174835205078} 08/30/2021 21:33:54 - INFO - __main__ - Step 45911: {'lr': 0.00039904201721129663, 'samples': 8814912, 'steps': 45910, 'loss/train': 1.3297829627990723} 08/30/2021 21:33:54 - INFO - __main__ - Step 45912: {'lr': 0.00039903775660675645, 'samples': 8815104, 'steps': 45911, 'loss/train': 2.0103020668029785} 08/30/2021 21:33:55 - INFO - __main__ - Step 45913: {'lr': 0.00039903349593506214, 'samples': 8815296, 'steps': 45912, 'loss/train': 1.5464253425598145} 08/30/2021 21:33:56 - INFO - __main__ - Step 45914: {'lr': 0.0003990292351962157, 'samples': 8815488, 'steps': 45913, 'loss/train': 0.8021082878112793} 08/30/2021 21:33:56 - INFO - __main__ - Step 45915: {'lr': 0.00039902497439021895, 'samples': 8815680, 'steps': 45914, 'loss/train': 1.675797462463379} 08/30/2021 21:33:57 - INFO - __main__ - Step 45916: {'lr': 0.0003990207135170738, 'samples': 8815872, 'steps': 45915, 'loss/train': 0.9508106112480164} 08/30/2021 21:33:57 - INFO - __main__ - Step 45917: {'lr': 0.00039901645257678234, 'samples': 8816064, 'steps': 45916, 'loss/train': 0.556931734085083} 08/30/2021 21:33:57 - INFO - __main__ - Step 45918: {'lr': 0.0003990121915693462, 'samples': 8816256, 'steps': 45917, 'loss/train': 1.3384051322937012} 08/30/2021 21:33:58 - INFO - __main__ - Step 45919: {'lr': 0.0003990079304947676, 'samples': 8816448, 'steps': 45918, 'loss/train': 0.9686638712882996} 08/30/2021 21:33:59 - INFO - __main__ - Step 45920: {'lr': 0.00039900366935304824, 'samples': 8816640, 'steps': 45919, 'loss/train': 1.8176053762435913} 08/30/2021 21:34:00 - INFO - __main__ - Step 45921: {'lr': 0.0003989994081441902, 'samples': 8816832, 'steps': 45920, 'loss/train': 1.976651906967163} 08/30/2021 21:34:00 - INFO - __main__ - Step 45922: {'lr': 0.00039899514686819526, 'samples': 8817024, 'steps': 45921, 'loss/train': 0.12316101789474487} 08/30/2021 21:34:01 - INFO - __main__ - Step 45923: {'lr': 0.00039899088552506544, 'samples': 8817216, 'steps': 45922, 'loss/train': 0.9177865982055664} 08/30/2021 21:34:01 - INFO - __main__ - Step 45924: {'lr': 0.00039898662411480264, 'samples': 8817408, 'steps': 45923, 'loss/train': 1.1662096977233887} 08/30/2021 21:34:02 - INFO - __main__ - Step 45925: {'lr': 0.00039898236263740875, 'samples': 8817600, 'steps': 45924, 'loss/train': 1.1464731693267822} 08/30/2021 21:34:03 - INFO - __main__ - Step 45926: {'lr': 0.00039897810109288566, 'samples': 8817792, 'steps': 45925, 'loss/train': 1.1101843118667603} 08/30/2021 21:34:03 - INFO - __main__ - Step 45927: {'lr': 0.0003989738394812354, 'samples': 8817984, 'steps': 45926, 'loss/train': 1.1896226406097412} 08/30/2021 21:34:04 - INFO - __main__ - Step 45928: {'lr': 0.0003989695778024598, 'samples': 8818176, 'steps': 45927, 'loss/train': 1.5410248041152954} 08/30/2021 21:34:04 - INFO - __main__ - Step 45929: {'lr': 0.00039896531605656085, 'samples': 8818368, 'steps': 45928, 'loss/train': 1.9736499786376953} 08/30/2021 21:34:06 - INFO - __main__ - Step 45930: {'lr': 0.00039896105424354035, 'samples': 8818560, 'steps': 45929, 'loss/train': 1.1277334690093994} 08/30/2021 21:34:06 - INFO - __main__ - Step 45931: {'lr': 0.0003989567923634003, 'samples': 8818752, 'steps': 45930, 'loss/train': 1.309943675994873} 08/30/2021 21:34:06 - INFO - __main__ - Step 45932: {'lr': 0.00039895253041614265, 'samples': 8818944, 'steps': 45931, 'loss/train': 1.166379451751709} 08/30/2021 21:34:07 - INFO - __main__ - Step 45933: {'lr': 0.00039894826840176933, 'samples': 8819136, 'steps': 45932, 'loss/train': 1.2008832693099976} 08/30/2021 21:34:07 - INFO - __main__ - Step 45934: {'lr': 0.00039894400632028217, 'samples': 8819328, 'steps': 45933, 'loss/train': 1.6712656021118164} 08/30/2021 21:34:08 - INFO - __main__ - Step 45935: {'lr': 0.00039893974417168316, 'samples': 8819520, 'steps': 45934, 'loss/train': 1.550011396408081} 08/30/2021 21:34:09 - INFO - __main__ - Step 45936: {'lr': 0.00039893548195597415, 'samples': 8819712, 'steps': 45935, 'loss/train': 1.5504117012023926} 08/30/2021 21:34:09 - INFO - __main__ - Step 45937: {'lr': 0.0003989312196731572, 'samples': 8819904, 'steps': 45936, 'loss/train': 0.873008131980896} 08/30/2021 21:34:10 - INFO - __main__ - Step 45938: {'lr': 0.0003989269573232341, 'samples': 8820096, 'steps': 45937, 'loss/train': 1.8701066970825195} 08/30/2021 21:34:10 - INFO - __main__ - Step 45939: {'lr': 0.0003989226949062068, 'samples': 8820288, 'steps': 45938, 'loss/train': 1.6357719898223877} 08/30/2021 21:34:10 - INFO - __main__ - Step 45940: {'lr': 0.00039891843242207726, 'samples': 8820480, 'steps': 45939, 'loss/train': 1.146041750907898} 08/30/2021 21:34:12 - INFO - __main__ - Step 45941: {'lr': 0.00039891416987084726, 'samples': 8820672, 'steps': 45940, 'loss/train': 0.5608364939689636} 08/30/2021 21:34:12 - INFO - __main__ - Step 45942: {'lr': 0.00039890990725251896, 'samples': 8820864, 'steps': 45941, 'loss/train': 1.4235665798187256} 08/30/2021 21:34:13 - INFO - __main__ - Step 45943: {'lr': 0.0003989056445670941, 'samples': 8821056, 'steps': 45942, 'loss/train': 1.67377769947052} 08/30/2021 21:34:13 - INFO - __main__ - Step 45944: {'lr': 0.0003989013818145747, 'samples': 8821248, 'steps': 45943, 'loss/train': 1.1196436882019043} 08/30/2021 21:34:14 - INFO - __main__ - Step 45945: {'lr': 0.0003988971189949626, 'samples': 8821440, 'steps': 45944, 'loss/train': 0.8334695100784302} 08/30/2021 21:34:14 - INFO - __main__ - Step 45946: {'lr': 0.0003988928561082598, 'samples': 8821632, 'steps': 45945, 'loss/train': 1.5286099910736084} 08/30/2021 21:34:16 - INFO - __main__ - Step 45947: {'lr': 0.0003988885931544681, 'samples': 8821824, 'steps': 45946, 'loss/train': 1.1778885126113892} 08/30/2021 21:34:16 - INFO - __main__ - Step 45948: {'lr': 0.0003988843301335895, 'samples': 8822016, 'steps': 45947, 'loss/train': 1.183476209640503} 08/30/2021 21:34:17 - INFO - __main__ - Step 45949: {'lr': 0.00039888006704562594, 'samples': 8822208, 'steps': 45948, 'loss/train': 1.108405590057373} 08/30/2021 21:34:17 - INFO - __main__ - Step 45950: {'lr': 0.0003988758038905794, 'samples': 8822400, 'steps': 45949, 'loss/train': 1.4362045526504517} 08/30/2021 21:34:17 - INFO - __main__ - Step 45951: {'lr': 0.00039887154066845166, 'samples': 8822592, 'steps': 45950, 'loss/train': 0.6259725689888} 08/30/2021 21:34:18 - INFO - __main__ - Step 45952: {'lr': 0.00039886727737924464, 'samples': 8822784, 'steps': 45951, 'loss/train': 0.9381634593009949} 08/30/2021 21:34:19 - INFO - __main__ - Step 45953: {'lr': 0.00039886301402296037, 'samples': 8822976, 'steps': 45952, 'loss/train': 1.2229812145233154} 08/30/2021 21:34:20 - INFO - __main__ - Step 45954: {'lr': 0.00039885875059960074, 'samples': 8823168, 'steps': 45953, 'loss/train': 1.5409786701202393} 08/30/2021 21:34:20 - INFO - __main__ - Step 45955: {'lr': 0.0003988544871091676, 'samples': 8823360, 'steps': 45954, 'loss/train': 1.3310774564743042} 08/30/2021 21:34:20 - INFO - __main__ - Step 45956: {'lr': 0.000398850223551663, 'samples': 8823552, 'steps': 45955, 'loss/train': 1.934818983078003} 08/30/2021 21:34:21 - INFO - __main__ - Step 45957: {'lr': 0.00039884595992708877, 'samples': 8823744, 'steps': 45956, 'loss/train': 1.6563388109207153} 08/30/2021 21:34:23 - INFO - __main__ - Step 45958: {'lr': 0.00039884169623544683, 'samples': 8823936, 'steps': 45957, 'loss/train': 0.6444125771522522} 08/30/2021 21:34:23 - INFO - __main__ - Step 45959: {'lr': 0.0003988374324767391, 'samples': 8824128, 'steps': 45958, 'loss/train': 1.2904642820358276} 08/30/2021 21:34:24 - INFO - __main__ - Step 45960: {'lr': 0.0003988331686509675, 'samples': 8824320, 'steps': 45959, 'loss/train': 0.8290671706199646} 08/30/2021 21:34:24 - INFO - __main__ - Step 45961: {'lr': 0.000398828904758134, 'samples': 8824512, 'steps': 45960, 'loss/train': 0.5800647735595703} 08/30/2021 21:34:24 - INFO - __main__ - Step 45962: {'lr': 0.0003988246407982405, 'samples': 8824704, 'steps': 45961, 'loss/train': 1.6646595001220703} 08/30/2021 21:34:26 - INFO - __main__ - Step 45963: {'lr': 0.00039882037677128895, 'samples': 8824896, 'steps': 45962, 'loss/train': 0.8743748664855957} 08/30/2021 21:34:26 - INFO - __main__ - Step 45964: {'lr': 0.0003988161126772812, 'samples': 8825088, 'steps': 45963, 'loss/train': 1.4011805057525635} 08/30/2021 21:34:27 - INFO - __main__ - Step 45965: {'lr': 0.0003988118485162192, 'samples': 8825280, 'steps': 45964, 'loss/train': 1.5982658863067627} 08/30/2021 21:34:27 - INFO - __main__ - Step 45966: {'lr': 0.00039880758428810487, 'samples': 8825472, 'steps': 45965, 'loss/train': 1.5529544353485107} 08/30/2021 21:34:27 - INFO - __main__ - Step 45967: {'lr': 0.00039880331999294017, 'samples': 8825664, 'steps': 45966, 'loss/train': 1.2997111082077026} 08/30/2021 21:34:29 - INFO - __main__ - Step 45968: {'lr': 0.00039879905563072694, 'samples': 8825856, 'steps': 45967, 'loss/train': 0.6538985371589661} 08/30/2021 21:34:29 - INFO - __main__ - Step 45969: {'lr': 0.00039879479120146725, 'samples': 8826048, 'steps': 45968, 'loss/train': 0.47482556104660034} 08/30/2021 21:34:30 - INFO - __main__ - Step 45970: {'lr': 0.0003987905267051628, 'samples': 8826240, 'steps': 45969, 'loss/train': 1.6342581510543823} 08/30/2021 21:34:30 - INFO - __main__ - Step 45971: {'lr': 0.0003987862621418157, 'samples': 8826432, 'steps': 45970, 'loss/train': 1.4716788530349731} 08/30/2021 21:34:30 - INFO - __main__ - Step 45972: {'lr': 0.0003987819975114278, 'samples': 8826624, 'steps': 45971, 'loss/train': 1.6564103364944458} 08/30/2021 21:34:32 - INFO - __main__ - Step 45973: {'lr': 0.000398777732814001, 'samples': 8826816, 'steps': 45972, 'loss/train': 1.319682240486145} 08/30/2021 21:34:32 - INFO - __main__ - Step 45974: {'lr': 0.0003987734680495373, 'samples': 8827008, 'steps': 45973, 'loss/train': 1.4295915365219116} 08/30/2021 21:34:33 - INFO - __main__ - Step 45975: {'lr': 0.0003987692032180385, 'samples': 8827200, 'steps': 45974, 'loss/train': 1.4333821535110474} 08/30/2021 21:34:33 - INFO - __main__ - Step 45976: {'lr': 0.00039876493831950664, 'samples': 8827392, 'steps': 45975, 'loss/train': 2.162172555923462} 08/30/2021 21:34:33 - INFO - __main__ - Step 45977: {'lr': 0.00039876067335394363, 'samples': 8827584, 'steps': 45976, 'loss/train': 1.4194296598434448} 08/30/2021 21:34:35 - INFO - __main__ - Step 45978: {'lr': 0.0003987564083213513, 'samples': 8827776, 'steps': 45977, 'loss/train': 1.04628324508667} 08/30/2021 21:34:35 - INFO - __main__ - Step 45979: {'lr': 0.00039875214322173167, 'samples': 8827968, 'steps': 45978, 'loss/train': 1.8911947011947632} 08/30/2021 21:34:36 - INFO - __main__ - Step 45980: {'lr': 0.00039874787805508656, 'samples': 8828160, 'steps': 45979, 'loss/train': 1.6589652299880981} 08/30/2021 21:34:36 - INFO - __main__ - Step 45981: {'lr': 0.000398743612821418, 'samples': 8828352, 'steps': 45980, 'loss/train': 1.4017174243927002} 08/30/2021 21:34:36 - INFO - __main__ - Step 45982: {'lr': 0.0003987393475207278, 'samples': 8828544, 'steps': 45981, 'loss/train': 2.876781940460205} 08/30/2021 21:34:37 - INFO - __main__ - Step 45983: {'lr': 0.000398735082153018, 'samples': 8828736, 'steps': 45982, 'loss/train': 1.3135699033737183} 08/30/2021 21:34:38 - INFO - __main__ - Step 45984: {'lr': 0.00039873081671829046, 'samples': 8828928, 'steps': 45983, 'loss/train': 1.3262829780578613} 08/30/2021 21:34:39 - INFO - __main__ - Step 45985: {'lr': 0.0003987265512165471, 'samples': 8829120, 'steps': 45984, 'loss/train': 1.9111242294311523} 08/30/2021 21:34:39 - INFO - __main__ - Step 45986: {'lr': 0.0003987222856477899, 'samples': 8829312, 'steps': 45985, 'loss/train': 1.7914196252822876} 08/30/2021 21:34:39 - INFO - __main__ - Step 45987: {'lr': 0.0003987180200120207, 'samples': 8829504, 'steps': 45986, 'loss/train': 0.8986952304840088} 08/30/2021 21:34:40 - INFO - __main__ - Step 45988: {'lr': 0.0003987137543092414, 'samples': 8829696, 'steps': 45987, 'loss/train': 0.6883071064949036} 08/30/2021 21:34:41 - INFO - __main__ - Step 45989: {'lr': 0.0003987094885394541, 'samples': 8829888, 'steps': 45988, 'loss/train': 1.5992047786712646} 08/30/2021 21:34:41 - INFO - __main__ - Step 45990: {'lr': 0.0003987052227026605, 'samples': 8830080, 'steps': 45989, 'loss/train': 1.3425664901733398} 08/30/2021 21:34:42 - INFO - __main__ - Step 45991: {'lr': 0.0003987009567988626, 'samples': 8830272, 'steps': 45990, 'loss/train': 0.8926039934158325} 08/30/2021 21:34:42 - INFO - __main__ - Step 45992: {'lr': 0.00039869669082806243, 'samples': 8830464, 'steps': 45991, 'loss/train': 1.725190281867981} 08/30/2021 21:34:43 - INFO - __main__ - Step 45993: {'lr': 0.0003986924247902618, 'samples': 8830656, 'steps': 45992, 'loss/train': 0.8363355994224548} 08/30/2021 21:34:44 - INFO - __main__ - Step 45994: {'lr': 0.00039868815868546257, 'samples': 8830848, 'steps': 45993, 'loss/train': 1.0703015327453613} 08/30/2021 21:34:44 - INFO - __main__ - Step 45995: {'lr': 0.00039868389251366686, 'samples': 8831040, 'steps': 45994, 'loss/train': 1.4130018949508667} 08/30/2021 21:34:45 - INFO - __main__ - Step 45996: {'lr': 0.00039867962627487645, 'samples': 8831232, 'steps': 45995, 'loss/train': 1.5226773023605347} 08/30/2021 21:34:45 - INFO - __main__ - Step 45997: {'lr': 0.0003986753599690933, 'samples': 8831424, 'steps': 45996, 'loss/train': 1.3419251441955566} 08/30/2021 21:34:45 - INFO - __main__ - Step 45998: {'lr': 0.00039867109359631935, 'samples': 8831616, 'steps': 45997, 'loss/train': 1.1787835359573364} 08/30/2021 21:34:47 - INFO - __main__ - Step 45999: {'lr': 0.00039866682715655646, 'samples': 8831808, 'steps': 45998, 'loss/train': 1.144551157951355} 08/30/2021 21:34:47 - INFO - __main__ - Step 46000: {'lr': 0.00039866256064980657, 'samples': 8832000, 'steps': 45999, 'loss/train': 1.1735973358154297} 08/30/2021 21:34:48 - INFO - __main__ - Step 46001: {'lr': 0.0003986582940760717, 'samples': 8832192, 'steps': 46000, 'loss/train': 1.7374322414398193} 08/30/2021 21:34:48 - INFO - __main__ - Step 46002: {'lr': 0.0003986540274353536, 'samples': 8832384, 'steps': 46001, 'loss/train': 1.0739721059799194} 08/30/2021 21:34:48 - INFO - __main__ - Step 46003: {'lr': 0.00039864976072765437, 'samples': 8832576, 'steps': 46002, 'loss/train': 1.173020362854004} 08/30/2021 21:34:50 - INFO - __main__ - Step 46004: {'lr': 0.0003986454939529758, 'samples': 8832768, 'steps': 46003, 'loss/train': 1.0811725854873657} 08/30/2021 21:34:50 - INFO - __main__ - Step 46005: {'lr': 0.0003986412271113199, 'samples': 8832960, 'steps': 46004, 'loss/train': 0.9034219980239868} 08/30/2021 21:34:51 - INFO - __main__ - Step 46006: {'lr': 0.0003986369602026886, 'samples': 8833152, 'steps': 46005, 'loss/train': 1.269287347793579} 08/30/2021 21:34:51 - INFO - __main__ - Step 46007: {'lr': 0.0003986326932270836, 'samples': 8833344, 'steps': 46006, 'loss/train': 1.2735518217086792} 08/30/2021 21:34:51 - INFO - __main__ - Step 46008: {'lr': 0.00039862842618450717, 'samples': 8833536, 'steps': 46007, 'loss/train': 1.4346592426300049} 08/30/2021 21:34:54 - INFO - __main__ - Step 46009: {'lr': 0.00039862415907496103, 'samples': 8833728, 'steps': 46008, 'loss/train': 1.2043991088867188} 08/30/2021 21:34:54 - INFO - __main__ - Step 46010: {'lr': 0.00039861989189844715, 'samples': 8833920, 'steps': 46009, 'loss/train': 1.2698410749435425} 08/30/2021 21:34:55 - INFO - __main__ - Step 46011: {'lr': 0.00039861562465496735, 'samples': 8834112, 'steps': 46010, 'loss/train': 0.44780731201171875} 08/30/2021 21:34:55 - INFO - __main__ - Step 46012: {'lr': 0.00039861135734452376, 'samples': 8834304, 'steps': 46011, 'loss/train': 0.15395143628120422} 08/30/2021 21:34:55 - INFO - __main__ - Step 46013: {'lr': 0.00039860708996711816, 'samples': 8834496, 'steps': 46012, 'loss/train': 1.599525809288025} 08/30/2021 21:34:57 - INFO - __main__ - Step 46014: {'lr': 0.00039860282252275245, 'samples': 8834688, 'steps': 46013, 'loss/train': 2.1880736351013184} 08/30/2021 21:34:57 - INFO - __main__ - Step 46015: {'lr': 0.0003985985550114286, 'samples': 8834880, 'steps': 46014, 'loss/train': 1.771926999092102} 08/30/2021 21:34:57 - INFO - __main__ - Step 46016: {'lr': 0.00039859428743314857, 'samples': 8835072, 'steps': 46015, 'loss/train': 1.3153576850891113} 08/30/2021 21:34:58 - INFO - __main__ - Step 46017: {'lr': 0.0003985900197879142, 'samples': 8835264, 'steps': 46016, 'loss/train': 0.9063101410865784} 08/30/2021 21:34:58 - INFO - __main__ - Step 46018: {'lr': 0.00039858575207572756, 'samples': 8835456, 'steps': 46017, 'loss/train': 0.9806237816810608} 08/30/2021 21:35:00 - INFO - __main__ - Step 46019: {'lr': 0.00039858148429659036, 'samples': 8835648, 'steps': 46018, 'loss/train': 1.1178653240203857} 08/30/2021 21:35:00 - INFO - __main__ - Step 46020: {'lr': 0.0003985772164505047, 'samples': 8835840, 'steps': 46019, 'loss/train': 1.2177878618240356} 08/30/2021 21:35:00 - INFO - __main__ - Step 46021: {'lr': 0.0003985729485374724, 'samples': 8836032, 'steps': 46020, 'loss/train': 1.352109432220459} 08/30/2021 21:35:01 - INFO - __main__ - Step 46022: {'lr': 0.0003985686805574954, 'samples': 8836224, 'steps': 46021, 'loss/train': 1.0561004877090454} 08/30/2021 21:35:01 - INFO - __main__ - Step 46023: {'lr': 0.00039856441251057573, 'samples': 8836416, 'steps': 46022, 'loss/train': 1.6003743410110474} 08/30/2021 21:35:02 - INFO - __main__ - Step 46024: {'lr': 0.0003985601443967152, 'samples': 8836608, 'steps': 46023, 'loss/train': 1.4200018644332886} 08/30/2021 21:35:03 - INFO - __main__ - Step 46025: {'lr': 0.0003985558762159157, 'samples': 8836800, 'steps': 46024, 'loss/train': 1.4329794645309448} 08/30/2021 21:35:03 - INFO - __main__ - Step 46026: {'lr': 0.0003985516079681793, 'samples': 8836992, 'steps': 46025, 'loss/train': 1.9898192882537842} 08/30/2021 21:35:04 - INFO - __main__ - Step 46027: {'lr': 0.0003985473396535078, 'samples': 8837184, 'steps': 46026, 'loss/train': 2.1930010318756104} 08/30/2021 21:35:04 - INFO - __main__ - Step 46028: {'lr': 0.00039854307127190316, 'samples': 8837376, 'steps': 46027, 'loss/train': 1.0728346109390259} 08/30/2021 21:35:04 - INFO - __main__ - Step 46029: {'lr': 0.0003985388028233673, 'samples': 8837568, 'steps': 46028, 'loss/train': 1.0078150033950806} 08/30/2021 21:35:06 - INFO - __main__ - Step 46030: {'lr': 0.0003985345343079022, 'samples': 8837760, 'steps': 46029, 'loss/train': 1.5804888010025024} 08/30/2021 21:35:06 - INFO - __main__ - Step 46031: {'lr': 0.00039853026572550965, 'samples': 8837952, 'steps': 46030, 'loss/train': 1.2204777002334595} 08/30/2021 21:35:07 - INFO - __main__ - Step 46032: {'lr': 0.0003985259970761917, 'samples': 8838144, 'steps': 46031, 'loss/train': 1.3898285627365112} 08/30/2021 21:35:07 - INFO - __main__ - Step 46033: {'lr': 0.0003985217283599502, 'samples': 8838336, 'steps': 46032, 'loss/train': 1.1773681640625} 08/30/2021 21:35:08 - INFO - __main__ - Step 46034: {'lr': 0.0003985174595767871, 'samples': 8838528, 'steps': 46033, 'loss/train': 1.0620403289794922} 08/30/2021 21:35:09 - INFO - __main__ - Step 46035: {'lr': 0.0003985131907267043, 'samples': 8838720, 'steps': 46034, 'loss/train': 1.7556136846542358} 08/30/2021 21:35:10 - INFO - __main__ - Step 46036: {'lr': 0.00039850892180970387, 'samples': 8838912, 'steps': 46035, 'loss/train': 1.4639158248901367} 08/30/2021 21:35:10 - INFO - __main__ - Step 46037: {'lr': 0.0003985046528257875, 'samples': 8839104, 'steps': 46036, 'loss/train': 1.5760293006896973} 08/30/2021 21:35:10 - INFO - __main__ - Step 46038: {'lr': 0.00039850038377495727, 'samples': 8839296, 'steps': 46037, 'loss/train': 1.2258882522583008} 08/30/2021 21:35:11 - INFO - __main__ - Step 46039: {'lr': 0.000398496114657215, 'samples': 8839488, 'steps': 46038, 'loss/train': 0.9945687651634216} 08/30/2021 21:35:11 - INFO - __main__ - Step 46040: {'lr': 0.0003984918454725628, 'samples': 8839680, 'steps': 46039, 'loss/train': 1.3057918548583984} 08/30/2021 21:35:12 - INFO - __main__ - Step 46041: {'lr': 0.0003984875762210023, 'samples': 8839872, 'steps': 46040, 'loss/train': 1.7759654521942139} 08/30/2021 21:35:13 - INFO - __main__ - Step 46042: {'lr': 0.0003984833069025357, 'samples': 8840064, 'steps': 46041, 'loss/train': 1.5332950353622437} 08/30/2021 21:35:13 - INFO - __main__ - Step 46043: {'lr': 0.00039847903751716486, 'samples': 8840256, 'steps': 46042, 'loss/train': 1.4358203411102295} 08/30/2021 21:35:14 - INFO - __main__ - Step 46044: {'lr': 0.00039847476806489153, 'samples': 8840448, 'steps': 46043, 'loss/train': 1.3734197616577148} 08/30/2021 21:35:14 - INFO - __main__ - Step 46045: {'lr': 0.00039847049854571784, 'samples': 8840640, 'steps': 46044, 'loss/train': 1.4672223329544067} 08/30/2021 21:35:16 - INFO - __main__ - Step 46046: {'lr': 0.00039846622895964556, 'samples': 8840832, 'steps': 46045, 'loss/train': 1.105386734008789} 08/30/2021 21:35:16 - INFO - __main__ - Step 46047: {'lr': 0.0003984619593066767, 'samples': 8841024, 'steps': 46046, 'loss/train': 1.7899452447891235} 08/30/2021 21:35:17 - INFO - __main__ - Step 46048: {'lr': 0.0003984576895868132, 'samples': 8841216, 'steps': 46047, 'loss/train': 1.5395907163619995} 08/30/2021 21:35:17 - INFO - __main__ - Step 46049: {'lr': 0.000398453419800057, 'samples': 8841408, 'steps': 46048, 'loss/train': 0.8314034938812256} 08/30/2021 21:35:18 - INFO - __main__ - Step 46050: {'lr': 0.00039844914994640994, 'samples': 8841600, 'steps': 46049, 'loss/train': 0.3109332025051117} 08/30/2021 21:35:18 - INFO - __main__ - Step 46051: {'lr': 0.00039844488002587397, 'samples': 8841792, 'steps': 46050, 'loss/train': 1.7853615283966064} 08/30/2021 21:35:19 - INFO - __main__ - Step 46052: {'lr': 0.00039844061003845114, 'samples': 8841984, 'steps': 46051, 'loss/train': 0.5214645862579346} 08/30/2021 21:35:20 - INFO - __main__ - Step 46053: {'lr': 0.00039843633998414306, 'samples': 8842176, 'steps': 46052, 'loss/train': 1.3784608840942383} 08/30/2021 21:35:20 - INFO - __main__ - Step 46054: {'lr': 0.000398432069862952, 'samples': 8842368, 'steps': 46053, 'loss/train': 1.4672095775604248} 08/30/2021 21:35:21 - INFO - __main__ - Step 46055: {'lr': 0.00039842779967487967, 'samples': 8842560, 'steps': 46054, 'loss/train': 1.5179264545440674} 08/30/2021 21:35:21 - INFO - __main__ - Step 46056: {'lr': 0.0003984235294199281, 'samples': 8842752, 'steps': 46055, 'loss/train': 1.3943374156951904} 08/30/2021 21:35:23 - INFO - __main__ - Step 46057: {'lr': 0.0003984192590980992, 'samples': 8842944, 'steps': 46056, 'loss/train': 1.4477373361587524} 08/30/2021 21:35:24 - INFO - __main__ - Step 46058: {'lr': 0.00039841498870939483, 'samples': 8843136, 'steps': 46057, 'loss/train': 2.065382719039917} 08/30/2021 21:35:24 - INFO - __main__ - Step 46059: {'lr': 0.000398410718253817, 'samples': 8843328, 'steps': 46058, 'loss/train': 1.6766257286071777} 08/30/2021 21:35:24 - INFO - __main__ - Step 46060: {'lr': 0.00039840644773136757, 'samples': 8843520, 'steps': 46059, 'loss/train': 1.5089621543884277} 08/30/2021 21:35:25 - INFO - __main__ - Step 46061: {'lr': 0.0003984021771420484, 'samples': 8843712, 'steps': 46060, 'loss/train': 1.3594402074813843} 08/30/2021 21:35:25 - INFO - __main__ - Step 46062: {'lr': 0.0003983979064858616, 'samples': 8843904, 'steps': 46061, 'loss/train': 1.247732400894165} 08/30/2021 21:35:25 - INFO - __main__ - Step 46063: {'lr': 0.000398393635762809, 'samples': 8844096, 'steps': 46062, 'loss/train': 0.05368264392018318} 08/30/2021 21:35:27 - INFO - __main__ - Step 46064: {'lr': 0.0003983893649728925, 'samples': 8844288, 'steps': 46063, 'loss/train': 0.7466768026351929} 08/30/2021 21:35:28 - INFO - __main__ - Step 46065: {'lr': 0.000398385094116114, 'samples': 8844480, 'steps': 46064, 'loss/train': 1.3943030834197998} 08/30/2021 21:35:28 - INFO - __main__ - Step 46066: {'lr': 0.0003983808231924755, 'samples': 8844672, 'steps': 46065, 'loss/train': 1.189836859703064} 08/30/2021 21:35:29 - INFO - __main__ - Step 46067: {'lr': 0.0003983765522019789, 'samples': 8844864, 'steps': 46066, 'loss/train': 0.10465364158153534} 08/30/2021 21:35:29 - INFO - __main__ - Step 46068: {'lr': 0.0003983722811446261, 'samples': 8845056, 'steps': 46067, 'loss/train': 1.2041999101638794} 08/30/2021 21:35:30 - INFO - __main__ - Step 46069: {'lr': 0.00039836801002041903, 'samples': 8845248, 'steps': 46068, 'loss/train': 1.5342386960983276} 08/30/2021 21:35:31 - INFO - __main__ - Step 46070: {'lr': 0.00039836373882935967, 'samples': 8845440, 'steps': 46069, 'loss/train': 0.9626764059066772} 08/30/2021 21:35:31 - INFO - __main__ - Step 46071: {'lr': 0.0003983594675714498, 'samples': 8845632, 'steps': 46070, 'loss/train': 1.5838414430618286} 08/30/2021 21:35:32 - INFO - __main__ - Step 46072: {'lr': 0.0003983551962466915, 'samples': 8845824, 'steps': 46071, 'loss/train': 0.5252110362052917} 08/30/2021 21:35:32 - INFO - __main__ - Step 46073: {'lr': 0.0003983509248550867, 'samples': 8846016, 'steps': 46072, 'loss/train': 1.6192330121994019} 08/30/2021 21:35:33 - INFO - __main__ - Step 46074: {'lr': 0.00039834665339663725, 'samples': 8846208, 'steps': 46073, 'loss/train': 1.453455924987793} 08/30/2021 21:35:34 - INFO - __main__ - Step 46075: {'lr': 0.00039834238187134497, 'samples': 8846400, 'steps': 46074, 'loss/train': 1.0606783628463745} 08/30/2021 21:35:34 - INFO - __main__ - Step 46076: {'lr': 0.00039833811027921196, 'samples': 8846592, 'steps': 46075, 'loss/train': 1.0795825719833374} 08/30/2021 21:35:35 - INFO - __main__ - Step 46077: {'lr': 0.00039833383862024016, 'samples': 8846784, 'steps': 46076, 'loss/train': 1.3732281923294067} 08/30/2021 21:35:35 - INFO - __main__ - Step 46078: {'lr': 0.00039832956689443135, 'samples': 8846976, 'steps': 46077, 'loss/train': 1.1644858121871948} 08/30/2021 21:35:36 - INFO - __main__ - Step 46079: {'lr': 0.00039832529510178756, 'samples': 8847168, 'steps': 46078, 'loss/train': 1.5265620946884155} 08/30/2021 21:35:37 - INFO - __main__ - Step 46080: {'lr': 0.0003983210232423107, 'samples': 8847360, 'steps': 46079, 'loss/train': 1.5379303693771362} 08/30/2021 21:35:37 - INFO - __main__ - Step 46081: {'lr': 0.00039831675131600253, 'samples': 8847552, 'steps': 46080, 'loss/train': 1.4588737487792969} 08/30/2021 21:35:38 - INFO - __main__ - Step 46082: {'lr': 0.0003983124793228653, 'samples': 8847744, 'steps': 46081, 'loss/train': 1.8334448337554932} 08/30/2021 21:35:38 - INFO - __main__ - Step 46083: {'lr': 0.00039830820726290063, 'samples': 8847936, 'steps': 46082, 'loss/train': 1.2814098596572876} 08/30/2021 21:35:40 - INFO - __main__ - Step 46084: {'lr': 0.0003983039351361106, 'samples': 8848128, 'steps': 46083, 'loss/train': 1.3197534084320068} 08/30/2021 21:35:40 - INFO - __main__ - Step 46085: {'lr': 0.0003982996629424972, 'samples': 8848320, 'steps': 46084, 'loss/train': 2.0131566524505615} 08/30/2021 21:35:40 - INFO - __main__ - Step 46086: {'lr': 0.0003982953906820622, 'samples': 8848512, 'steps': 46085, 'loss/train': 1.2611488103866577} 08/30/2021 21:35:41 - INFO - __main__ - Step 46087: {'lr': 0.0003982911183548075, 'samples': 8848704, 'steps': 46086, 'loss/train': 1.3952438831329346} 08/30/2021 21:35:41 - INFO - __main__ - Step 46088: {'lr': 0.0003982868459607352, 'samples': 8848896, 'steps': 46087, 'loss/train': 1.7468812465667725} 08/30/2021 21:35:43 - INFO - __main__ - Step 46089: {'lr': 0.0003982825734998471, 'samples': 8849088, 'steps': 46088, 'loss/train': 1.384050965309143} 08/30/2021 21:35:43 - INFO - __main__ - Step 46090: {'lr': 0.0003982783009721452, 'samples': 8849280, 'steps': 46089, 'loss/train': 1.6091235876083374} 08/30/2021 21:35:44 - INFO - __main__ - Step 46091: {'lr': 0.00039827402837763136, 'samples': 8849472, 'steps': 46090, 'loss/train': 1.1778900623321533} 08/30/2021 21:35:44 - INFO - __main__ - Step 46092: {'lr': 0.00039826975571630754, 'samples': 8849664, 'steps': 46091, 'loss/train': 0.9310660362243652} 08/30/2021 21:35:44 - INFO - __main__ - Step 46093: {'lr': 0.0003982654829881757, 'samples': 8849856, 'steps': 46092, 'loss/train': 1.8160934448242188} 08/30/2021 21:35:45 - INFO - __main__ - Step 46094: {'lr': 0.0003982612101932376, 'samples': 8850048, 'steps': 46093, 'loss/train': 1.1759487390518188} 08/30/2021 21:35:45 - INFO - __main__ - Step 46095: {'lr': 0.0003982569373314954, 'samples': 8850240, 'steps': 46094, 'loss/train': 0.03603367879986763} 08/30/2021 21:35:47 - INFO - __main__ - Step 46096: {'lr': 0.0003982526644029508, 'samples': 8850432, 'steps': 46095, 'loss/train': 1.5609126091003418} 08/30/2021 21:35:47 - INFO - __main__ - Step 46097: {'lr': 0.000398248391407606, 'samples': 8850624, 'steps': 46096, 'loss/train': 1.5165722370147705} 08/30/2021 21:35:47 - INFO - __main__ - Step 46098: {'lr': 0.0003982441183454627, 'samples': 8850816, 'steps': 46097, 'loss/train': 1.7708914279937744} 08/30/2021 21:35:48 - INFO - __main__ - Step 46099: {'lr': 0.0003982398452165228, 'samples': 8851008, 'steps': 46098, 'loss/train': 1.1890300512313843} 08/30/2021 21:35:48 - INFO - __main__ - Step 46100: {'lr': 0.0003982355720207884, 'samples': 8851200, 'steps': 46099, 'loss/train': 1.7634931802749634} 08/30/2021 21:35:50 - INFO - __main__ - Step 46101: {'lr': 0.00039823129875826127, 'samples': 8851392, 'steps': 46100, 'loss/train': 1.0142585039138794} 08/30/2021 21:35:50 - INFO - __main__ - Step 46102: {'lr': 0.0003982270254289435, 'samples': 8851584, 'steps': 46101, 'loss/train': 2.123687267303467} 08/30/2021 21:35:51 - INFO - __main__ - Step 46103: {'lr': 0.0003982227520328368, 'samples': 8851776, 'steps': 46102, 'loss/train': 1.2674418687820435} 08/30/2021 21:35:51 - INFO - __main__ - Step 46104: {'lr': 0.0003982184785699433, 'samples': 8851968, 'steps': 46103, 'loss/train': 1.8261513710021973} 08/30/2021 21:35:51 - INFO - __main__ - Step 46105: {'lr': 0.00039821420504026486, 'samples': 8852160, 'steps': 46104, 'loss/train': 1.1738165616989136} 08/30/2021 21:35:53 - INFO - __main__ - Step 46106: {'lr': 0.00039820993144380333, 'samples': 8852352, 'steps': 46105, 'loss/train': 1.0078974962234497} 08/30/2021 21:35:53 - INFO - __main__ - Step 46107: {'lr': 0.0003982056577805607, 'samples': 8852544, 'steps': 46106, 'loss/train': 0.9887067675590515} 08/30/2021 21:35:54 - INFO - __main__ - Step 46108: {'lr': 0.00039820138405053887, 'samples': 8852736, 'steps': 46107, 'loss/train': 1.2157014608383179} 08/30/2021 21:35:54 - INFO - __main__ - Step 46109: {'lr': 0.0003981971102537398, 'samples': 8852928, 'steps': 46108, 'loss/train': 1.0998417139053345} 08/30/2021 21:35:54 - INFO - __main__ - Step 46110: {'lr': 0.00039819283639016547, 'samples': 8853120, 'steps': 46109, 'loss/train': 1.6847704648971558} 08/30/2021 21:35:56 - INFO - __main__ - Step 46111: {'lr': 0.00039818856245981766, 'samples': 8853312, 'steps': 46110, 'loss/train': 1.3850125074386597} 08/30/2021 21:35:56 - INFO - __main__ - Step 46112: {'lr': 0.0003981842884626984, 'samples': 8853504, 'steps': 46111, 'loss/train': 0.20583832263946533} 08/30/2021 21:35:57 - INFO - __main__ - Step 46113: {'lr': 0.0003981800143988095, 'samples': 8853696, 'steps': 46112, 'loss/train': 1.6219192743301392} 08/30/2021 21:35:57 - INFO - __main__ - Step 46114: {'lr': 0.00039817574026815305, 'samples': 8853888, 'steps': 46113, 'loss/train': 1.994206190109253} 08/30/2021 21:35:57 - INFO - __main__ - Step 46115: {'lr': 0.0003981714660707309, 'samples': 8854080, 'steps': 46114, 'loss/train': 1.6100820302963257} 08/30/2021 21:35:59 - INFO - __main__ - Step 46116: {'lr': 0.00039816719180654493, 'samples': 8854272, 'steps': 46115, 'loss/train': 1.5760902166366577} 08/30/2021 21:36:00 - INFO - __main__ - Step 46117: {'lr': 0.0003981629174755972, 'samples': 8854464, 'steps': 46116, 'loss/train': 1.4815994501113892} 08/30/2021 21:36:00 - INFO - __main__ - Step 46118: {'lr': 0.0003981586430778895, 'samples': 8854656, 'steps': 46117, 'loss/train': 1.3517539501190186} 08/30/2021 21:36:00 - INFO - __main__ - Step 46119: {'lr': 0.0003981543686134238, 'samples': 8854848, 'steps': 46118, 'loss/train': 1.9788190126419067} 08/30/2021 21:36:01 - INFO - __main__ - Step 46120: {'lr': 0.000398150094082202, 'samples': 8855040, 'steps': 46119, 'loss/train': 0.6015864610671997} 08/30/2021 21:36:01 - INFO - __main__ - Step 46121: {'lr': 0.000398145819484226, 'samples': 8855232, 'steps': 46120, 'loss/train': 1.427643895149231} 08/30/2021 21:36:03 - INFO - __main__ - Step 46122: {'lr': 0.00039814154481949786, 'samples': 8855424, 'steps': 46121, 'loss/train': 0.10691922158002853} 08/30/2021 21:36:04 - INFO - __main__ - Step 46123: {'lr': 0.00039813727008801945, 'samples': 8855616, 'steps': 46122, 'loss/train': 0.900311291217804} 08/30/2021 21:36:04 - INFO - __main__ - Step 46124: {'lr': 0.00039813299528979263, 'samples': 8855808, 'steps': 46123, 'loss/train': 1.440889596939087} 08/30/2021 21:36:04 - INFO - __main__ - Step 46125: {'lr': 0.0003981287204248194, 'samples': 8856000, 'steps': 46124, 'loss/train': 1.5318527221679688} 08/30/2021 21:36:05 - INFO - __main__ - Step 46126: {'lr': 0.0003981244454931017, 'samples': 8856192, 'steps': 46125, 'loss/train': 1.2276725769042969} 08/30/2021 21:36:06 - INFO - __main__ - Step 46127: {'lr': 0.00039812017049464126, 'samples': 8856384, 'steps': 46126, 'loss/train': 1.801188349723816} 08/30/2021 21:36:07 - INFO - __main__ - Step 46128: {'lr': 0.0003981158954294403, 'samples': 8856576, 'steps': 46127, 'loss/train': 1.2678282260894775} 08/30/2021 21:36:07 - INFO - __main__ - Step 46129: {'lr': 0.00039811162029750047, 'samples': 8856768, 'steps': 46128, 'loss/train': 1.3311612606048584} 08/30/2021 21:36:07 - INFO - __main__ - Step 46130: {'lr': 0.00039810734509882395, 'samples': 8856960, 'steps': 46129, 'loss/train': 1.0655478239059448} 08/30/2021 21:36:08 - INFO - __main__ - Step 46131: {'lr': 0.0003981030698334125, 'samples': 8857152, 'steps': 46130, 'loss/train': 1.7195959091186523} 08/30/2021 21:36:09 - INFO - __main__ - Step 46132: {'lr': 0.00039809879450126805, 'samples': 8857344, 'steps': 46131, 'loss/train': 1.5221997499465942} 08/30/2021 21:36:10 - INFO - __main__ - Step 46133: {'lr': 0.00039809451910239257, 'samples': 8857536, 'steps': 46132, 'loss/train': 1.752462387084961} 08/30/2021 21:36:10 - INFO - __main__ - Step 46134: {'lr': 0.000398090243636788, 'samples': 8857728, 'steps': 46133, 'loss/train': 1.5113725662231445} 08/30/2021 21:36:10 - INFO - __main__ - Step 46135: {'lr': 0.00039808596810445636, 'samples': 8857920, 'steps': 46134, 'loss/train': 1.106951117515564} 08/30/2021 21:36:11 - INFO - __main__ - Step 46136: {'lr': 0.0003980816925053994, 'samples': 8858112, 'steps': 46135, 'loss/train': 1.3570268154144287} 08/30/2021 21:36:13 - INFO - __main__ - Step 46137: {'lr': 0.0003980774168396191, 'samples': 8858304, 'steps': 46136, 'loss/train': 0.6676763892173767} 08/30/2021 21:36:13 - INFO - __main__ - Step 46138: {'lr': 0.00039807314110711735, 'samples': 8858496, 'steps': 46137, 'loss/train': 1.039880633354187} 08/30/2021 21:36:14 - INFO - __main__ - Step 46139: {'lr': 0.0003980688653078962, 'samples': 8858688, 'steps': 46138, 'loss/train': 0.527498185634613} 08/30/2021 21:36:14 - INFO - __main__ - Step 46140: {'lr': 0.00039806458944195743, 'samples': 8858880, 'steps': 46139, 'loss/train': 1.460119605064392} 08/30/2021 21:36:14 - INFO - __main__ - Step 46141: {'lr': 0.00039806031350930315, 'samples': 8859072, 'steps': 46140, 'loss/train': 1.4636150598526} 08/30/2021 21:36:15 - INFO - __main__ - Step 46142: {'lr': 0.00039805603750993514, 'samples': 8859264, 'steps': 46141, 'loss/train': 0.8240839242935181} 08/30/2021 21:36:17 - INFO - __main__ - Step 46143: {'lr': 0.0003980517614438553, 'samples': 8859456, 'steps': 46142, 'loss/train': 0.1934243142604828} 08/30/2021 21:36:17 - INFO - __main__ - Step 46144: {'lr': 0.00039804748531106565, 'samples': 8859648, 'steps': 46143, 'loss/train': 0.29726606607437134} 08/30/2021 21:36:17 - INFO - __main__ - Step 46145: {'lr': 0.0003980432091115681, 'samples': 8859840, 'steps': 46144, 'loss/train': 1.9492334127426147} 08/30/2021 21:36:18 - INFO - __main__ - Step 46146: {'lr': 0.0003980389328453646, 'samples': 8860032, 'steps': 46145, 'loss/train': 1.390972375869751} 08/30/2021 21:36:18 - INFO - __main__ - Step 46147: {'lr': 0.00039803465651245694, 'samples': 8860224, 'steps': 46146, 'loss/train': 1.752730131149292} 08/30/2021 21:36:20 - INFO - __main__ - Step 46148: {'lr': 0.00039803038011284724, 'samples': 8860416, 'steps': 46147, 'loss/train': 1.2309606075286865} 08/30/2021 21:36:20 - INFO - __main__ - Step 46149: {'lr': 0.00039802610364653737, 'samples': 8860608, 'steps': 46148, 'loss/train': 1.667372703552246} 08/30/2021 21:36:20 - INFO - __main__ - Step 46150: {'lr': 0.00039802182711352906, 'samples': 8860800, 'steps': 46149, 'loss/train': 1.5557856559753418} 08/30/2021 21:36:21 - INFO - __main__ - Step 46151: {'lr': 0.0003980175505138246, 'samples': 8860992, 'steps': 46150, 'loss/train': 1.385726809501648} 08/30/2021 21:36:21 - INFO - __main__ - Step 46152: {'lr': 0.0003980132738474256, 'samples': 8861184, 'steps': 46151, 'loss/train': 1.421400547027588} 08/30/2021 21:36:23 - INFO - __main__ - Step 46153: {'lr': 0.0003980089971143341, 'samples': 8861376, 'steps': 46152, 'loss/train': 1.3695296049118042} 08/30/2021 21:36:24 - INFO - __main__ - Step 46154: {'lr': 0.000398004720314552, 'samples': 8861568, 'steps': 46153, 'loss/train': 1.2512880563735962} 08/30/2021 21:36:24 - INFO - __main__ - Step 46155: {'lr': 0.00039800044344808134, 'samples': 8861760, 'steps': 46154, 'loss/train': 1.1035337448120117} 08/30/2021 21:36:24 - INFO - __main__ - Step 46156: {'lr': 0.00039799616651492394, 'samples': 8861952, 'steps': 46155, 'loss/train': 1.1669267416000366} 08/30/2021 21:36:25 - INFO - __main__ - Step 46157: {'lr': 0.00039799188951508176, 'samples': 8862144, 'steps': 46156, 'loss/train': 1.2630959749221802} 08/30/2021 21:36:25 - INFO - __main__ - Step 46158: {'lr': 0.0003979876124485567, 'samples': 8862336, 'steps': 46157, 'loss/train': 0.9439281821250916} 08/30/2021 21:36:25 - INFO - __main__ - Step 46159: {'lr': 0.0003979833353153507, 'samples': 8862528, 'steps': 46158, 'loss/train': 1.7229725122451782} 08/30/2021 21:36:27 - INFO - __main__ - Step 46160: {'lr': 0.00039797905811546564, 'samples': 8862720, 'steps': 46159, 'loss/train': 1.7560029029846191} 08/30/2021 21:36:27 - INFO - __main__ - Step 46161: {'lr': 0.0003979747808489036, 'samples': 8862912, 'steps': 46160, 'loss/train': 1.4252433776855469} 08/30/2021 21:36:28 - INFO - __main__ - Step 46162: {'lr': 0.0003979705035156663, 'samples': 8863104, 'steps': 46161, 'loss/train': 1.0816069841384888} 08/30/2021 21:36:28 - INFO - __main__ - Step 46163: {'lr': 0.0003979662261157558, 'samples': 8863296, 'steps': 46162, 'loss/train': 1.4421778917312622} 08/30/2021 21:36:28 - INFO - __main__ - Step 46164: {'lr': 0.00039796194864917414, 'samples': 8863488, 'steps': 46163, 'loss/train': 1.2068511247634888} 08/30/2021 21:36:30 - INFO - __main__ - Step 46165: {'lr': 0.00039795767111592303, 'samples': 8863680, 'steps': 46164, 'loss/train': 1.4976835250854492} 08/30/2021 21:36:30 - INFO - __main__ - Step 46166: {'lr': 0.00039795339351600444, 'samples': 8863872, 'steps': 46165, 'loss/train': 1.525852918624878} 08/30/2021 21:36:31 - INFO - __main__ - Step 46167: {'lr': 0.0003979491158494203, 'samples': 8864064, 'steps': 46166, 'loss/train': 0.6323105096817017} 08/30/2021 21:36:31 - INFO - __main__ - Step 46168: {'lr': 0.00039794483811617267, 'samples': 8864256, 'steps': 46167, 'loss/train': 1.0992785692214966} 08/30/2021 21:36:31 - INFO - __main__ - Step 46169: {'lr': 0.0003979405603162633, 'samples': 8864448, 'steps': 46168, 'loss/train': 0.6095963716506958} 08/30/2021 21:36:33 - INFO - __main__ - Step 46170: {'lr': 0.0003979362824496942, 'samples': 8864640, 'steps': 46169, 'loss/train': 1.1593022346496582} 08/30/2021 21:36:34 - INFO - __main__ - Step 46171: {'lr': 0.00039793200451646737, 'samples': 8864832, 'steps': 46170, 'loss/train': 2.0511343479156494} 08/30/2021 21:36:34 - INFO - __main__ - Step 46172: {'lr': 0.0003979277265165846, 'samples': 8865024, 'steps': 46171, 'loss/train': 0.8530001640319824} 08/30/2021 21:36:34 - INFO - __main__ - Step 46173: {'lr': 0.00039792344845004793, 'samples': 8865216, 'steps': 46172, 'loss/train': 0.21832449734210968} 08/30/2021 21:36:35 - INFO - __main__ - Step 46174: {'lr': 0.00039791917031685914, 'samples': 8865408, 'steps': 46173, 'loss/train': 1.4622730016708374} 08/30/2021 21:36:35 - INFO - __main__ - Step 46175: {'lr': 0.0003979148921170203, 'samples': 8865600, 'steps': 46174, 'loss/train': 1.5187691450119019} 08/30/2021 21:36:37 - INFO - __main__ - Step 46176: {'lr': 0.0003979106138505333, 'samples': 8865792, 'steps': 46175, 'loss/train': 0.1938311755657196} 08/30/2021 21:36:38 - INFO - __main__ - Step 46177: {'lr': 0.00039790633551740006, 'samples': 8865984, 'steps': 46176, 'loss/train': 1.7372809648513794} 08/30/2021 21:36:38 - INFO - __main__ - Step 46178: {'lr': 0.0003979020571176226, 'samples': 8866176, 'steps': 46177, 'loss/train': 1.3579798936843872} 08/30/2021 21:36:38 - INFO - __main__ - Step 46179: {'lr': 0.00039789777865120257, 'samples': 8866368, 'steps': 46178, 'loss/train': 1.2651915550231934} 08/30/2021 21:36:39 - INFO - __main__ - Step 46180: {'lr': 0.0003978935001181422, 'samples': 8866560, 'steps': 46179, 'loss/train': 0.8050438761711121} 08/30/2021 21:36:40 - INFO - __main__ - Step 46181: {'lr': 0.0003978892215184433, 'samples': 8866752, 'steps': 46180, 'loss/train': 1.3935328722000122} 08/30/2021 21:36:41 - INFO - __main__ - Step 46182: {'lr': 0.00039788494285210774, 'samples': 8866944, 'steps': 46181, 'loss/train': 1.5677921772003174} 08/30/2021 21:36:41 - INFO - __main__ - Step 46183: {'lr': 0.0003978806641191376, 'samples': 8867136, 'steps': 46182, 'loss/train': 1.093623399734497} 08/30/2021 21:36:41 - INFO - __main__ - Step 46184: {'lr': 0.0003978763853195346, 'samples': 8867328, 'steps': 46183, 'loss/train': 1.6276055574417114} 08/30/2021 21:36:42 - INFO - __main__ - Step 46185: {'lr': 0.0003978721064533009, 'samples': 8867520, 'steps': 46184, 'loss/train': 0.7652538418769836} 08/30/2021 21:36:43 - INFO - __main__ - Step 46186: {'lr': 0.0003978678275204383, 'samples': 8867712, 'steps': 46185, 'loss/train': 1.3193808794021606} 08/30/2021 21:36:44 - INFO - __main__ - Step 46187: {'lr': 0.00039786354852094864, 'samples': 8867904, 'steps': 46186, 'loss/train': 1.2814688682556152} 08/30/2021 21:36:44 - INFO - __main__ - Step 46188: {'lr': 0.00039785926945483396, 'samples': 8868096, 'steps': 46187, 'loss/train': 1.363050103187561} 08/30/2021 21:36:44 - INFO - __main__ - Step 46189: {'lr': 0.00039785499032209625, 'samples': 8868288, 'steps': 46188, 'loss/train': 1.6129274368286133} 08/30/2021 21:36:45 - INFO - __main__ - Step 46190: {'lr': 0.0003978507111227373, 'samples': 8868480, 'steps': 46189, 'loss/train': 1.592990756034851} 08/30/2021 21:36:46 - INFO - __main__ - Step 46191: {'lr': 0.00039784643185675916, 'samples': 8868672, 'steps': 46190, 'loss/train': 1.0570385456085205} 08/30/2021 21:36:47 - INFO - __main__ - Step 46192: {'lr': 0.0003978421525241637, 'samples': 8868864, 'steps': 46191, 'loss/train': 1.2486673593521118} 08/30/2021 21:36:47 - INFO - __main__ - Step 46193: {'lr': 0.00039783787312495277, 'samples': 8869056, 'steps': 46192, 'loss/train': 1.3574209213256836} 08/30/2021 21:36:47 - INFO - __main__ - Step 46194: {'lr': 0.0003978335936591284, 'samples': 8869248, 'steps': 46193, 'loss/train': 1.377662181854248} 08/30/2021 21:36:48 - INFO - __main__ - Step 46195: {'lr': 0.00039782931412669253, 'samples': 8869440, 'steps': 46194, 'loss/train': 1.480639934539795} 08/30/2021 21:36:49 - INFO - __main__ - Step 46196: {'lr': 0.000397825034527647, 'samples': 8869632, 'steps': 46195, 'loss/train': 1.0930739641189575} 08/30/2021 21:36:50 - INFO - __main__ - Step 46197: {'lr': 0.0003978207548619939, 'samples': 8869824, 'steps': 46196, 'loss/train': 1.1441224813461304} 08/30/2021 21:36:50 - INFO - __main__ - Step 46198: {'lr': 0.000397816475129735, 'samples': 8870016, 'steps': 46197, 'loss/train': 1.2958287000656128} 08/30/2021 21:36:50 - INFO - __main__ - Step 46199: {'lr': 0.0003978121953308722, 'samples': 8870208, 'steps': 46198, 'loss/train': 0.08704115450382233} 08/30/2021 21:36:51 - INFO - __main__ - Step 46200: {'lr': 0.0003978079154654075, 'samples': 8870400, 'steps': 46199, 'loss/train': 1.887276530265808} 08/30/2021 21:36:52 - INFO - __main__ - Step 46201: {'lr': 0.000397803635533343, 'samples': 8870592, 'steps': 46200, 'loss/train': 1.4722938537597656} 08/30/2021 21:36:53 - INFO - __main__ - Step 46202: {'lr': 0.00039779935553468026, 'samples': 8870784, 'steps': 46201, 'loss/train': 0.962514340877533} 08/30/2021 21:36:53 - INFO - __main__ - Step 46203: {'lr': 0.0003977950754694215, 'samples': 8870976, 'steps': 46202, 'loss/train': 1.211369276046753} 08/30/2021 21:36:53 - INFO - __main__ - Step 46204: {'lr': 0.00039779079533756856, 'samples': 8871168, 'steps': 46203, 'loss/train': 0.9213801026344299} 08/30/2021 21:36:54 - INFO - __main__ - Step 46205: {'lr': 0.00039778651513912343, 'samples': 8871360, 'steps': 46204, 'loss/train': 1.4540120363235474} 08/30/2021 21:36:55 - INFO - __main__ - Step 46206: {'lr': 0.00039778223487408796, 'samples': 8871552, 'steps': 46205, 'loss/train': 1.5263670682907104} 08/30/2021 21:36:56 - INFO - __main__ - Step 46207: {'lr': 0.000397777954542464, 'samples': 8871744, 'steps': 46206, 'loss/train': 1.5929806232452393} 08/30/2021 21:36:56 - INFO - __main__ - Step 46208: {'lr': 0.0003977736741442537, 'samples': 8871936, 'steps': 46207, 'loss/train': 0.9667959809303284} 08/30/2021 21:36:57 - INFO - __main__ - Step 46209: {'lr': 0.00039776939367945874, 'samples': 8872128, 'steps': 46208, 'loss/train': 0.7413719296455383} 08/30/2021 21:36:57 - INFO - __main__ - Step 46210: {'lr': 0.00039776511314808125, 'samples': 8872320, 'steps': 46209, 'loss/train': 1.5515624284744263} 08/30/2021 21:36:59 - INFO - __main__ - Step 46211: {'lr': 0.00039776083255012307, 'samples': 8872512, 'steps': 46210, 'loss/train': 1.241766095161438} 08/30/2021 21:36:59 - INFO - __main__ - Step 46212: {'lr': 0.0003977565518855861, 'samples': 8872704, 'steps': 46211, 'loss/train': 1.7987287044525146} 08/30/2021 21:36:59 - INFO - __main__ - Step 46213: {'lr': 0.0003977522711544723, 'samples': 8872896, 'steps': 46212, 'loss/train': 1.8362617492675781} 08/30/2021 21:37:00 - INFO - __main__ - Step 46214: {'lr': 0.00039774799035678367, 'samples': 8873088, 'steps': 46213, 'loss/train': 1.6681052446365356} 08/30/2021 21:37:00 - INFO - __main__ - Step 46215: {'lr': 0.000397743709492522, 'samples': 8873280, 'steps': 46214, 'loss/train': 1.1651482582092285} 08/30/2021 21:37:00 - INFO - __main__ - Step 46216: {'lr': 0.0003977394285616893, 'samples': 8873472, 'steps': 46215, 'loss/train': 1.7766283750534058} 08/30/2021 21:37:02 - INFO - __main__ - Step 46217: {'lr': 0.0003977351475642876, 'samples': 8873664, 'steps': 46216, 'loss/train': 1.6095948219299316} 08/30/2021 21:37:02 - INFO - __main__ - Step 46218: {'lr': 0.00039773086650031866, 'samples': 8873856, 'steps': 46217, 'loss/train': 1.8161734342575073} 08/30/2021 21:37:03 - INFO - __main__ - Step 46219: {'lr': 0.00039772658536978443, 'samples': 8874048, 'steps': 46218, 'loss/train': 2.2312960624694824} 08/30/2021 21:37:03 - INFO - __main__ - Step 46220: {'lr': 0.00039772230417268697, 'samples': 8874240, 'steps': 46219, 'loss/train': 1.3596910238265991} 08/30/2021 21:37:03 - INFO - __main__ - Step 46221: {'lr': 0.00039771802290902806, 'samples': 8874432, 'steps': 46220, 'loss/train': 1.7038460969924927} 08/30/2021 21:37:05 - INFO - __main__ - Step 46222: {'lr': 0.0003977137415788097, 'samples': 8874624, 'steps': 46221, 'loss/train': 1.1598373651504517} 08/30/2021 21:37:06 - INFO - __main__ - Step 46223: {'lr': 0.00039770946018203375, 'samples': 8874816, 'steps': 46222, 'loss/train': 1.12007737159729} 08/30/2021 21:37:06 - INFO - __main__ - Step 46224: {'lr': 0.00039770517871870226, 'samples': 8875008, 'steps': 46223, 'loss/train': 1.3621773719787598} 08/30/2021 21:37:06 - INFO - __main__ - Step 46225: {'lr': 0.00039770089718881707, 'samples': 8875200, 'steps': 46224, 'loss/train': 1.7137166261672974} 08/30/2021 21:37:07 - INFO - __main__ - Step 46226: {'lr': 0.00039769661559238014, 'samples': 8875392, 'steps': 46225, 'loss/train': 2.332510232925415} 08/30/2021 21:37:09 - INFO - __main__ - Step 46227: {'lr': 0.0003976923339293934, 'samples': 8875584, 'steps': 46226, 'loss/train': 1.9135557413101196} 08/30/2021 21:37:09 - INFO - __main__ - Step 46228: {'lr': 0.0003976880521998588, 'samples': 8875776, 'steps': 46227, 'loss/train': 1.3628970384597778} 08/30/2021 21:37:10 - INFO - __main__ - Step 46229: {'lr': 0.00039768377040377823, 'samples': 8875968, 'steps': 46228, 'loss/train': 1.220140814781189} 08/30/2021 21:37:10 - INFO - __main__ - Step 46230: {'lr': 0.00039767948854115356, 'samples': 8876160, 'steps': 46229, 'loss/train': 1.4693472385406494} 08/30/2021 21:37:10 - INFO - __main__ - Step 46231: {'lr': 0.0003976752066119869, 'samples': 8876352, 'steps': 46230, 'loss/train': 0.8738886713981628} 08/30/2021 21:37:12 - INFO - __main__ - Step 46232: {'lr': 0.00039767092461628, 'samples': 8876544, 'steps': 46231, 'loss/train': 1.5112401247024536} 08/30/2021 21:37:12 - INFO - __main__ - Step 46233: {'lr': 0.0003976666425540349, 'samples': 8876736, 'steps': 46232, 'loss/train': 1.237876296043396} 08/30/2021 21:37:13 - INFO - __main__ - Step 46234: {'lr': 0.00039766236042525346, 'samples': 8876928, 'steps': 46233, 'loss/train': 1.1422197818756104} 08/30/2021 21:37:13 - INFO - __main__ - Step 46235: {'lr': 0.0003976580782299376, 'samples': 8877120, 'steps': 46234, 'loss/train': 0.8942980170249939} 08/30/2021 21:37:13 - INFO - __main__ - Step 46236: {'lr': 0.0003976537959680894, 'samples': 8877312, 'steps': 46235, 'loss/train': 0.6486141085624695} 08/30/2021 21:37:14 - INFO - __main__ - Step 46237: {'lr': 0.0003976495136397106, 'samples': 8877504, 'steps': 46236, 'loss/train': 1.5675405263900757} 08/30/2021 21:37:15 - INFO - __main__ - Step 46238: {'lr': 0.0003976452312448032, 'samples': 8877696, 'steps': 46237, 'loss/train': 0.45567041635513306} 08/30/2021 21:37:16 - INFO - __main__ - Step 46239: {'lr': 0.0003976409487833692, 'samples': 8877888, 'steps': 46238, 'loss/train': 0.8916254043579102} 08/30/2021 21:37:16 - INFO - __main__ - Step 46240: {'lr': 0.0003976366662554104, 'samples': 8878080, 'steps': 46239, 'loss/train': 1.6405450105667114} 08/30/2021 21:37:16 - INFO - __main__ - Step 46241: {'lr': 0.0003976323836609288, 'samples': 8878272, 'steps': 46240, 'loss/train': 1.2557779550552368} 08/30/2021 21:37:17 - INFO - __main__ - Step 46242: {'lr': 0.00039762810099992644, 'samples': 8878464, 'steps': 46241, 'loss/train': 1.4504786729812622} 08/30/2021 21:37:18 - INFO - __main__ - Step 46243: {'lr': 0.00039762381827240496, 'samples': 8878656, 'steps': 46242, 'loss/train': 0.8763937950134277} 08/30/2021 21:37:19 - INFO - __main__ - Step 46244: {'lr': 0.00039761953547836655, 'samples': 8878848, 'steps': 46243, 'loss/train': 1.3108327388763428} 08/30/2021 21:37:19 - INFO - __main__ - Step 46245: {'lr': 0.00039761525261781304, 'samples': 8879040, 'steps': 46244, 'loss/train': 1.341046929359436} 08/30/2021 21:37:19 - INFO - __main__ - Step 46246: {'lr': 0.00039761096969074644, 'samples': 8879232, 'steps': 46245, 'loss/train': 2.0777194499969482} 08/30/2021 21:37:20 - INFO - __main__ - Step 46247: {'lr': 0.0003976066866971686, 'samples': 8879424, 'steps': 46246, 'loss/train': 2.3430278301239014} 08/30/2021 21:37:22 - INFO - __main__ - Step 46248: {'lr': 0.0003976024036370814, 'samples': 8879616, 'steps': 46247, 'loss/train': 1.6097919940948486} 08/30/2021 21:37:22 - INFO - __main__ - Step 46249: {'lr': 0.0003975981205104868, 'samples': 8879808, 'steps': 46248, 'loss/train': 1.5714012384414673} 08/30/2021 21:37:23 - INFO - __main__ - Step 46250: {'lr': 0.0003975938373173868, 'samples': 8880000, 'steps': 46249, 'loss/train': 1.0613620281219482} 08/30/2021 21:37:23 - INFO - __main__ - Step 46251: {'lr': 0.00039758955405778344, 'samples': 8880192, 'steps': 46250, 'loss/train': 1.2717669010162354} 08/30/2021 21:37:23 - INFO - __main__ - Step 46252: {'lr': 0.0003975852707316784, 'samples': 8880384, 'steps': 46251, 'loss/train': 0.6949333548545837} 08/30/2021 21:37:25 - INFO - __main__ - Step 46253: {'lr': 0.00039758098733907364, 'samples': 8880576, 'steps': 46252, 'loss/train': 1.4614229202270508} 08/30/2021 21:37:26 - INFO - __main__ - Step 46254: {'lr': 0.00039757670387997125, 'samples': 8880768, 'steps': 46253, 'loss/train': 1.3671222925186157} 08/30/2021 21:37:26 - INFO - __main__ - Step 46255: {'lr': 0.000397572420354373, 'samples': 8880960, 'steps': 46254, 'loss/train': 1.1175525188446045} 08/30/2021 21:37:26 - INFO - __main__ - Step 46256: {'lr': 0.00039756813676228097, 'samples': 8881152, 'steps': 46255, 'loss/train': 0.03302577883005142} 08/30/2021 21:37:27 - INFO - __main__ - Step 46257: {'lr': 0.00039756385310369703, 'samples': 8881344, 'steps': 46256, 'loss/train': 1.6000744104385376} 08/30/2021 21:37:27 - INFO - __main__ - Step 46258: {'lr': 0.00039755956937862305, 'samples': 8881536, 'steps': 46257, 'loss/train': 1.1022528409957886} 08/30/2021 21:37:28 - INFO - __main__ - Step 46259: {'lr': 0.000397555285587061, 'samples': 8881728, 'steps': 46258, 'loss/train': 1.7841720581054688} 08/30/2021 21:37:29 - INFO - __main__ - Step 46260: {'lr': 0.0003975510017290128, 'samples': 8881920, 'steps': 46259, 'loss/train': 1.7257399559020996} 08/30/2021 21:37:29 - INFO - __main__ - Step 46261: {'lr': 0.00039754671780448044, 'samples': 8882112, 'steps': 46260, 'loss/train': 1.54389488697052} 08/30/2021 21:37:30 - INFO - __main__ - Step 46262: {'lr': 0.00039754243381346575, 'samples': 8882304, 'steps': 46261, 'loss/train': 1.3437176942825317} 08/30/2021 21:37:30 - INFO - __main__ - Step 46263: {'lr': 0.0003975381497559708, 'samples': 8882496, 'steps': 46262, 'loss/train': 1.2379319667816162} 08/30/2021 21:37:32 - INFO - __main__ - Step 46264: {'lr': 0.00039753386563199733, 'samples': 8882688, 'steps': 46263, 'loss/train': 1.2745450735092163} 08/30/2021 21:37:32 - INFO - __main__ - Step 46265: {'lr': 0.0003975295814415475, 'samples': 8882880, 'steps': 46264, 'loss/train': 1.6064344644546509} 08/30/2021 21:37:32 - INFO - __main__ - Step 46266: {'lr': 0.000397525297184623, 'samples': 8883072, 'steps': 46265, 'loss/train': 1.5587611198425293} 08/30/2021 21:37:33 - INFO - __main__ - Step 46267: {'lr': 0.000397521012861226, 'samples': 8883264, 'steps': 46266, 'loss/train': 1.1561015844345093} 08/30/2021 21:37:33 - INFO - __main__ - Step 46268: {'lr': 0.0003975167284713582, 'samples': 8883456, 'steps': 46267, 'loss/train': 0.9928433299064636} 08/30/2021 21:37:33 - INFO - __main__ - Step 46269: {'lr': 0.0003975124440150217, 'samples': 8883648, 'steps': 46268, 'loss/train': 1.107236385345459} 08/30/2021 21:37:35 - INFO - __main__ - Step 46270: {'lr': 0.0003975081594922183, 'samples': 8883840, 'steps': 46269, 'loss/train': 1.228446364402771} 08/30/2021 21:37:35 - INFO - __main__ - Step 46271: {'lr': 0.00039750387490295006, 'samples': 8884032, 'steps': 46270, 'loss/train': 1.3913148641586304} 08/30/2021 21:37:36 - INFO - __main__ - Step 46272: {'lr': 0.00039749959024721883, 'samples': 8884224, 'steps': 46271, 'loss/train': 1.6982171535491943} 08/30/2021 21:37:36 - INFO - __main__ - Step 46273: {'lr': 0.00039749530552502654, 'samples': 8884416, 'steps': 46272, 'loss/train': 1.3710078001022339} 08/30/2021 21:37:36 - INFO - __main__ - Step 46274: {'lr': 0.0003974910207363752, 'samples': 8884608, 'steps': 46273, 'loss/train': 1.2208378314971924} 08/30/2021 21:37:38 - INFO - __main__ - Step 46275: {'lr': 0.00039748673588126674, 'samples': 8884800, 'steps': 46274, 'loss/train': 1.2052921056747437} 08/30/2021 21:37:39 - INFO - __main__ - Step 46276: {'lr': 0.00039748245095970285, 'samples': 8884992, 'steps': 46275, 'loss/train': 1.2287741899490356} 08/30/2021 21:37:39 - INFO - __main__ - Step 46277: {'lr': 0.0003974781659716857, 'samples': 8885184, 'steps': 46276, 'loss/train': 1.2335220575332642} 08/30/2021 21:37:39 - INFO - __main__ - Step 46278: {'lr': 0.00039747388091721723, 'samples': 8885376, 'steps': 46277, 'loss/train': 1.5257847309112549} 08/30/2021 21:37:40 - INFO - __main__ - Step 46279: {'lr': 0.00039746959579629924, 'samples': 8885568, 'steps': 46278, 'loss/train': 1.1049121618270874} 08/30/2021 21:37:40 - INFO - __main__ - Step 46280: {'lr': 0.00039746531060893387, 'samples': 8885760, 'steps': 46279, 'loss/train': 1.31150484085083} 08/30/2021 21:37:41 - INFO - __main__ - Step 46281: {'lr': 0.00039746102535512273, 'samples': 8885952, 'steps': 46280, 'loss/train': 0.13650427758693695} 08/30/2021 21:37:42 - INFO - __main__ - Step 46282: {'lr': 0.000397456740034868, 'samples': 8886144, 'steps': 46281, 'loss/train': 0.8148044943809509} 08/30/2021 21:37:42 - INFO - __main__ - Step 46283: {'lr': 0.00039745245464817156, 'samples': 8886336, 'steps': 46282, 'loss/train': 1.9434828758239746} 08/30/2021 21:37:43 - INFO - __main__ - Step 46284: {'lr': 0.0003974481691950352, 'samples': 8886528, 'steps': 46283, 'loss/train': 1.0992425680160522} 08/30/2021 21:37:43 - INFO - __main__ - Step 46285: {'lr': 0.00039744388367546113, 'samples': 8886720, 'steps': 46284, 'loss/train': 1.3984664678573608} 08/30/2021 21:37:45 - INFO - __main__ - Step 46286: {'lr': 0.0003974395980894511, 'samples': 8886912, 'steps': 46285, 'loss/train': 1.708347201347351} 08/30/2021 21:37:46 - INFO - __main__ - Step 46287: {'lr': 0.000397435312437007, 'samples': 8887104, 'steps': 46286, 'loss/train': 1.7272266149520874} 08/30/2021 21:37:46 - INFO - __main__ - Step 46288: {'lr': 0.0003974310267181308, 'samples': 8887296, 'steps': 46287, 'loss/train': 1.528700351715088} 08/30/2021 21:37:47 - INFO - __main__ - Step 46289: {'lr': 0.00039742674093282447, 'samples': 8887488, 'steps': 46288, 'loss/train': 1.1809642314910889} 08/30/2021 21:37:47 - INFO - __main__ - Step 46290: {'lr': 0.00039742245508109, 'samples': 8887680, 'steps': 46289, 'loss/train': 1.0454107522964478} 08/30/2021 21:37:47 - INFO - __main__ - Step 46291: {'lr': 0.0003974181691629292, 'samples': 8887872, 'steps': 46290, 'loss/train': 0.8907452821731567} 08/30/2021 21:37:49 - INFO - __main__ - Step 46292: {'lr': 0.00039741388317834404, 'samples': 8888064, 'steps': 46291, 'loss/train': 1.265981674194336} 08/30/2021 21:37:49 - INFO - __main__ - Step 46293: {'lr': 0.0003974095971273365, 'samples': 8888256, 'steps': 46292, 'loss/train': 1.664109230041504} 08/30/2021 21:37:50 - INFO - __main__ - Step 46294: {'lr': 0.0003974053110099084, 'samples': 8888448, 'steps': 46293, 'loss/train': 0.955172061920166} 08/30/2021 21:37:50 - INFO - __main__ - Step 46295: {'lr': 0.00039740102482606175, 'samples': 8888640, 'steps': 46294, 'loss/train': 0.922761857509613} 08/30/2021 21:37:50 - INFO - __main__ - Step 46296: {'lr': 0.0003973967385757985, 'samples': 8888832, 'steps': 46295, 'loss/train': 1.448323369026184} 08/30/2021 21:37:52 - INFO - __main__ - Step 46297: {'lr': 0.00039739245225912055, 'samples': 8889024, 'steps': 46296, 'loss/train': 0.8080700039863586} 08/30/2021 21:37:52 - INFO - __main__ - Step 46298: {'lr': 0.0003973881658760298, 'samples': 8889216, 'steps': 46297, 'loss/train': 5.871662139892578} 08/30/2021 21:37:53 - INFO - __main__ - Step 46299: {'lr': 0.0003973838794265283, 'samples': 8889408, 'steps': 46298, 'loss/train': 1.580929160118103} 08/30/2021 21:37:53 - INFO - __main__ - Step 46300: {'lr': 0.00039737959291061785, 'samples': 8889600, 'steps': 46299, 'loss/train': 1.277411699295044} 08/30/2021 21:37:53 - INFO - __main__ - Step 46301: {'lr': 0.00039737530632830045, 'samples': 8889792, 'steps': 46300, 'loss/train': 0.9611787796020508} 08/30/2021 21:37:55 - INFO - __main__ - Step 46302: {'lr': 0.000397371019679578, 'samples': 8889984, 'steps': 46301, 'loss/train': 1.0047014951705933} 08/30/2021 21:37:55 - INFO - __main__ - Step 46303: {'lr': 0.00039736673296445233, 'samples': 8890176, 'steps': 46302, 'loss/train': 0.8591474890708923} 08/30/2021 21:37:56 - INFO - __main__ - Step 46304: {'lr': 0.00039736244618292563, 'samples': 8890368, 'steps': 46303, 'loss/train': 1.2880016565322876} 08/30/2021 21:37:56 - INFO - __main__ - Step 46305: {'lr': 0.0003973581593349997, 'samples': 8890560, 'steps': 46304, 'loss/train': 1.2761203050613403} 08/30/2021 21:37:56 - INFO - __main__ - Step 46306: {'lr': 0.00039735387242067637, 'samples': 8890752, 'steps': 46305, 'loss/train': 1.420340895652771} 08/30/2021 21:37:58 - INFO - __main__ - Step 46307: {'lr': 0.0003973495854399577, 'samples': 8890944, 'steps': 46306, 'loss/train': 1.4159529209136963} 08/30/2021 21:37:58 - INFO - __main__ - Step 46308: {'lr': 0.0003973452983928456, 'samples': 8891136, 'steps': 46307, 'loss/train': 1.291045069694519} 08/30/2021 21:37:59 - INFO - __main__ - Step 46309: {'lr': 0.00039734101127934194, 'samples': 8891328, 'steps': 46308, 'loss/train': 1.4797084331512451} 08/30/2021 21:37:59 - INFO - __main__ - Step 46310: {'lr': 0.0003973367240994487, 'samples': 8891520, 'steps': 46309, 'loss/train': 1.1744816303253174} 08/30/2021 21:38:00 - INFO - __main__ - Step 46311: {'lr': 0.00039733243685316776, 'samples': 8891712, 'steps': 46310, 'loss/train': 1.0302352905273438} 08/30/2021 21:38:00 - INFO - __main__ - Step 46312: {'lr': 0.00039732814954050125, 'samples': 8891904, 'steps': 46311, 'loss/train': 1.0603570938110352} 08/30/2021 21:38:01 - INFO - __main__ - Step 46313: {'lr': 0.0003973238621614508, 'samples': 8892096, 'steps': 46312, 'loss/train': 1.2772960662841797} 08/30/2021 21:38:02 - INFO - __main__ - Step 46314: {'lr': 0.0003973195747160185, 'samples': 8892288, 'steps': 46313, 'loss/train': 1.4406161308288574} 08/30/2021 21:38:02 - INFO - __main__ - Step 46315: {'lr': 0.00039731528720420635, 'samples': 8892480, 'steps': 46314, 'loss/train': 1.1468085050582886} 08/30/2021 21:38:03 - INFO - __main__ - Step 46316: {'lr': 0.00039731099962601613, 'samples': 8892672, 'steps': 46315, 'loss/train': 1.6534302234649658} 08/30/2021 21:38:03 - INFO - __main__ - Step 46317: {'lr': 0.0003973067119814499, 'samples': 8892864, 'steps': 46316, 'loss/train': 1.471175193786621} 08/30/2021 21:38:05 - INFO - __main__ - Step 46318: {'lr': 0.00039730242427050955, 'samples': 8893056, 'steps': 46317, 'loss/train': 1.638662338256836} 08/30/2021 21:38:05 - INFO - __main__ - Step 46319: {'lr': 0.00039729813649319704, 'samples': 8893248, 'steps': 46318, 'loss/train': 1.3218716382980347} 08/30/2021 21:38:05 - INFO - __main__ - Step 46320: {'lr': 0.0003972938486495141, 'samples': 8893440, 'steps': 46319, 'loss/train': 1.574557900428772} 08/30/2021 21:38:06 - INFO - __main__ - Step 46321: {'lr': 0.000397289560739463, 'samples': 8893632, 'steps': 46320, 'loss/train': 1.5087918043136597} 08/30/2021 21:38:06 - INFO - __main__ - Step 46322: {'lr': 0.0003972852727630454, 'samples': 8893824, 'steps': 46321, 'loss/train': 0.4920039474964142} 08/30/2021 21:38:08 - INFO - __main__ - Step 46323: {'lr': 0.0003972809847202633, 'samples': 8894016, 'steps': 46322, 'loss/train': 1.6612825393676758} 08/30/2021 21:38:08 - INFO - __main__ - Step 46324: {'lr': 0.0003972766966111187, 'samples': 8894208, 'steps': 46323, 'loss/train': 1.1593036651611328} 08/30/2021 21:38:09 - INFO - __main__ - Step 46325: {'lr': 0.0003972724084356135, 'samples': 8894400, 'steps': 46324, 'loss/train': 0.040521807968616486} 08/30/2021 21:38:09 - INFO - __main__ - Step 46326: {'lr': 0.0003972681201937497, 'samples': 8894592, 'steps': 46325, 'loss/train': 1.5153847932815552} 08/30/2021 21:38:09 - INFO - __main__ - Step 46327: {'lr': 0.00039726383188552907, 'samples': 8894784, 'steps': 46326, 'loss/train': 1.453345775604248} 08/30/2021 21:38:11 - INFO - __main__ - Step 46328: {'lr': 0.0003972595435109536, 'samples': 8894976, 'steps': 46327, 'loss/train': 1.4819231033325195} 08/30/2021 21:38:11 - INFO - __main__ - Step 46329: {'lr': 0.0003972552550700253, 'samples': 8895168, 'steps': 46328, 'loss/train': 1.424748182296753} 08/30/2021 21:38:12 - INFO - __main__ - Step 46330: {'lr': 0.00039725096656274605, 'samples': 8895360, 'steps': 46329, 'loss/train': 1.365673542022705} 08/30/2021 21:38:12 - INFO - __main__ - Step 46331: {'lr': 0.0003972466779891178, 'samples': 8895552, 'steps': 46330, 'loss/train': 1.0477070808410645} 08/30/2021 21:38:12 - INFO - __main__ - Step 46332: {'lr': 0.00039724238934914246, 'samples': 8895744, 'steps': 46331, 'loss/train': 0.24520935118198395} 08/30/2021 21:38:14 - INFO - __main__ - Step 46333: {'lr': 0.00039723810064282194, 'samples': 8895936, 'steps': 46332, 'loss/train': 1.0881191492080688} 08/30/2021 21:38:14 - INFO - __main__ - Step 46334: {'lr': 0.00039723381187015827, 'samples': 8896128, 'steps': 46333, 'loss/train': 0.9277474284172058} 08/30/2021 21:38:14 - INFO - __main__ - Step 46335: {'lr': 0.00039722952303115325, 'samples': 8896320, 'steps': 46334, 'loss/train': 0.9513620734214783} 08/30/2021 21:38:15 - INFO - __main__ - Step 46336: {'lr': 0.00039722523412580893, 'samples': 8896512, 'steps': 46335, 'loss/train': 1.427181363105774} 08/30/2021 21:38:15 - INFO - __main__ - Step 46337: {'lr': 0.00039722094515412716, 'samples': 8896704, 'steps': 46336, 'loss/train': 1.63276207447052} 08/30/2021 21:38:17 - INFO - __main__ - Step 46338: {'lr': 0.0003972166561161099, 'samples': 8896896, 'steps': 46337, 'loss/train': 1.3761049509048462} 08/30/2021 21:38:18 - INFO - __main__ - Step 46339: {'lr': 0.0003972123670117591, 'samples': 8897088, 'steps': 46338, 'loss/train': 0.9049459099769592} 08/30/2021 21:38:18 - INFO - __main__ - Step 46340: {'lr': 0.0003972080778410767, 'samples': 8897280, 'steps': 46339, 'loss/train': 1.4141075611114502} 08/30/2021 21:38:18 - INFO - __main__ - Step 46341: {'lr': 0.0003972037886040646, 'samples': 8897472, 'steps': 46340, 'loss/train': 1.6987277269363403} 08/30/2021 21:38:19 - INFO - __main__ - Step 46342: {'lr': 0.0003971994993007247, 'samples': 8897664, 'steps': 46341, 'loss/train': 1.3541159629821777} 08/30/2021 21:38:20 - INFO - __main__ - Step 46343: {'lr': 0.000397195209931059, 'samples': 8897856, 'steps': 46342, 'loss/train': 1.1848081350326538} 08/30/2021 21:38:21 - INFO - __main__ - Step 46344: {'lr': 0.00039719092049506945, 'samples': 8898048, 'steps': 46343, 'loss/train': 1.038587212562561} 08/30/2021 21:38:21 - INFO - __main__ - Step 46345: {'lr': 0.0003971866309927579, 'samples': 8898240, 'steps': 46344, 'loss/train': 1.5718634128570557} 08/30/2021 21:38:21 - INFO - __main__ - Step 46346: {'lr': 0.0003971823414241263, 'samples': 8898432, 'steps': 46345, 'loss/train': 1.2847014665603638} 08/30/2021 21:38:22 - INFO - __main__ - Step 46347: {'lr': 0.00039717805178917666, 'samples': 8898624, 'steps': 46346, 'loss/train': 1.255956768989563} 08/30/2021 21:38:23 - INFO - __main__ - Step 46348: {'lr': 0.0003971737620879109, 'samples': 8898816, 'steps': 46347, 'loss/train': 2.589430809020996} 08/30/2021 21:38:24 - INFO - __main__ - Step 46349: {'lr': 0.00039716947232033086, 'samples': 8899008, 'steps': 46348, 'loss/train': 1.7308956384658813} 08/30/2021 21:38:24 - INFO - __main__ - Step 46350: {'lr': 0.0003971651824864385, 'samples': 8899200, 'steps': 46349, 'loss/train': 2.113405466079712} 08/30/2021 21:38:24 - INFO - __main__ - Step 46351: {'lr': 0.0003971608925862358, 'samples': 8899392, 'steps': 46350, 'loss/train': 1.2174782752990723} 08/30/2021 21:38:25 - INFO - __main__ - Step 46352: {'lr': 0.0003971566026197247, 'samples': 8899584, 'steps': 46351, 'loss/train': 1.4920482635498047} 08/30/2021 21:38:25 - INFO - __main__ - Step 46353: {'lr': 0.0003971523125869071, 'samples': 8899776, 'steps': 46352, 'loss/train': 1.7018327713012695} 08/30/2021 21:38:26 - INFO - __main__ - Step 46354: {'lr': 0.0003971480224877849, 'samples': 8899968, 'steps': 46353, 'loss/train': 1.3080763816833496} 08/30/2021 21:38:27 - INFO - __main__ - Step 46355: {'lr': 0.0003971437323223601, 'samples': 8900160, 'steps': 46354, 'loss/train': 1.4450814723968506} 08/30/2021 21:38:27 - INFO - __main__ - Step 46356: {'lr': 0.0003971394420906346, 'samples': 8900352, 'steps': 46355, 'loss/train': 0.7579420208930969} 08/30/2021 21:38:28 - INFO - __main__ - Step 46357: {'lr': 0.0003971351517926103, 'samples': 8900544, 'steps': 46356, 'loss/train': 1.5609254837036133} 08/30/2021 21:38:28 - INFO - __main__ - Step 46358: {'lr': 0.00039713086142828926, 'samples': 8900736, 'steps': 46357, 'loss/train': 1.2565550804138184} 08/30/2021 21:38:30 - INFO - __main__ - Step 46359: {'lr': 0.0003971265709976732, 'samples': 8900928, 'steps': 46358, 'loss/train': 1.2098388671875} 08/30/2021 21:38:30 - INFO - __main__ - Step 46360: {'lr': 0.0003971222805007643, 'samples': 8901120, 'steps': 46359, 'loss/train': 0.48269620537757874} 08/30/2021 21:38:30 - INFO - __main__ - Step 46361: {'lr': 0.0003971179899375643, 'samples': 8901312, 'steps': 46360, 'loss/train': 1.6152585744857788} 08/30/2021 21:38:31 - INFO - __main__ - Step 46362: {'lr': 0.0003971136993080753, 'samples': 8901504, 'steps': 46361, 'loss/train': 1.2865593433380127} 08/30/2021 21:38:31 - INFO - __main__ - Step 46363: {'lr': 0.000397109408612299, 'samples': 8901696, 'steps': 46362, 'loss/train': 1.8012503385543823} 08/30/2021 21:38:33 - INFO - __main__ - Step 46364: {'lr': 0.0003971051178502375, 'samples': 8901888, 'steps': 46363, 'loss/train': 1.3171979188919067} 08/30/2021 21:38:33 - INFO - __main__ - Step 46365: {'lr': 0.00039710082702189276, 'samples': 8902080, 'steps': 46364, 'loss/train': 1.145189642906189} 08/30/2021 21:38:34 - INFO - __main__ - Step 46366: {'lr': 0.0003970965361272667, 'samples': 8902272, 'steps': 46365, 'loss/train': 1.235060453414917} 08/30/2021 21:38:34 - INFO - __main__ - Step 46367: {'lr': 0.0003970922451663611, 'samples': 8902464, 'steps': 46366, 'loss/train': 1.468003511428833} 08/30/2021 21:38:34 - INFO - __main__ - Step 46368: {'lr': 0.0003970879541391781, 'samples': 8902656, 'steps': 46367, 'loss/train': 0.9957088232040405} 08/30/2021 21:38:35 - INFO - __main__ - Step 46369: {'lr': 0.0003970836630457194, 'samples': 8902848, 'steps': 46368, 'loss/train': 1.3989332914352417} 08/30/2021 21:38:36 - INFO - __main__ - Step 46370: {'lr': 0.00039707937188598717, 'samples': 8903040, 'steps': 46369, 'loss/train': 1.7219014167785645} 08/30/2021 21:38:37 - INFO - __main__ - Step 46371: {'lr': 0.00039707508065998324, 'samples': 8903232, 'steps': 46370, 'loss/train': 0.7707935571670532} 08/30/2021 21:38:37 - INFO - __main__ - Step 46372: {'lr': 0.0003970707893677095, 'samples': 8903424, 'steps': 46371, 'loss/train': 1.5996007919311523} 08/30/2021 21:38:37 - INFO - __main__ - Step 46373: {'lr': 0.00039706649800916804, 'samples': 8903616, 'steps': 46372, 'loss/train': 1.0786998271942139} 08/30/2021 21:38:38 - INFO - __main__ - Step 46374: {'lr': 0.0003970622065843607, 'samples': 8903808, 'steps': 46373, 'loss/train': 1.22597336769104} 08/30/2021 21:38:40 - INFO - __main__ - Step 46375: {'lr': 0.00039705791509328926, 'samples': 8904000, 'steps': 46374, 'loss/train': 1.8490779399871826} 08/30/2021 21:38:40 - INFO - __main__ - Step 46376: {'lr': 0.0003970536235359558, 'samples': 8904192, 'steps': 46375, 'loss/train': 0.08509698510169983} 08/30/2021 21:38:41 - INFO - __main__ - Step 46377: {'lr': 0.00039704933191236225, 'samples': 8904384, 'steps': 46376, 'loss/train': 1.120384693145752} 08/30/2021 21:38:41 - INFO - __main__ - Step 46378: {'lr': 0.00039704504022251066, 'samples': 8904576, 'steps': 46377, 'loss/train': 1.7474642992019653} 08/30/2021 21:38:41 - INFO - __main__ - Step 46379: {'lr': 0.00039704074846640277, 'samples': 8904768, 'steps': 46378, 'loss/train': 0.44692519307136536} 08/30/2021 21:38:43 - INFO - __main__ - Step 46380: {'lr': 0.0003970364566440406, 'samples': 8904960, 'steps': 46379, 'loss/train': 1.6594629287719727} 08/30/2021 21:38:43 - INFO - __main__ - Step 46381: {'lr': 0.000397032164755426, 'samples': 8905152, 'steps': 46380, 'loss/train': 1.3192886114120483} 08/30/2021 21:38:44 - INFO - __main__ - Step 46382: {'lr': 0.0003970278728005611, 'samples': 8905344, 'steps': 46381, 'loss/train': 1.883972406387329} 08/30/2021 21:38:44 - INFO - __main__ - Step 46383: {'lr': 0.0003970235807794476, 'samples': 8905536, 'steps': 46382, 'loss/train': 1.01622474193573} 08/30/2021 21:38:44 - INFO - __main__ - Step 46384: {'lr': 0.00039701928869208757, 'samples': 8905728, 'steps': 46383, 'loss/train': 1.8688762187957764} 08/30/2021 21:38:46 - INFO - __main__ - Step 46385: {'lr': 0.0003970149965384829, 'samples': 8905920, 'steps': 46384, 'loss/train': 1.564450740814209} 08/30/2021 21:38:46 - INFO - __main__ - Step 46386: {'lr': 0.00039701070431863564, 'samples': 8906112, 'steps': 46385, 'loss/train': 0.7310260534286499} 08/30/2021 21:38:47 - INFO - __main__ - Step 46387: {'lr': 0.00039700641203254755, 'samples': 8906304, 'steps': 46386, 'loss/train': 1.1244299411773682} 08/30/2021 21:38:47 - INFO - __main__ - Step 46388: {'lr': 0.0003970021196802206, 'samples': 8906496, 'steps': 46387, 'loss/train': 0.5553213357925415} 08/30/2021 21:38:47 - INFO - __main__ - Step 46389: {'lr': 0.0003969978272616569, 'samples': 8906688, 'steps': 46388, 'loss/train': 1.1225703954696655} 08/30/2021 21:38:49 - INFO - __main__ - Step 46390: {'lr': 0.0003969935347768581, 'samples': 8906880, 'steps': 46389, 'loss/train': 1.4424350261688232} 08/30/2021 21:38:50 - INFO - __main__ - Step 46391: {'lr': 0.00039698924222582636, 'samples': 8907072, 'steps': 46390, 'loss/train': 1.399309515953064} 08/30/2021 21:38:50 - INFO - __main__ - Step 46392: {'lr': 0.00039698494960856346, 'samples': 8907264, 'steps': 46391, 'loss/train': 1.6217565536499023} 08/30/2021 21:38:50 - INFO - __main__ - Step 46393: {'lr': 0.0003969806569250716, 'samples': 8907456, 'steps': 46392, 'loss/train': 1.702538251876831} 08/30/2021 21:38:51 - INFO - __main__ - Step 46394: {'lr': 0.0003969763641753523, 'samples': 8907648, 'steps': 46393, 'loss/train': 1.9131591320037842} 08/30/2021 21:38:51 - INFO - __main__ - Step 46395: {'lr': 0.00039697207135940785, 'samples': 8907840, 'steps': 46394, 'loss/train': 1.413002848625183} 08/30/2021 21:38:53 - INFO - __main__ - Step 46396: {'lr': 0.00039696777847724, 'samples': 8908032, 'steps': 46395, 'loss/train': 1.2963913679122925} 08/30/2021 21:38:54 - INFO - __main__ - Step 46397: {'lr': 0.00039696348552885075, 'samples': 8908224, 'steps': 46396, 'loss/train': 1.4687113761901855} 08/30/2021 21:38:54 - INFO - __main__ - Step 46398: {'lr': 0.000396959192514242, 'samples': 8908416, 'steps': 46397, 'loss/train': 0.5586197972297668} 08/30/2021 21:38:54 - INFO - __main__ - Step 46399: {'lr': 0.0003969548994334158, 'samples': 8908608, 'steps': 46398, 'loss/train': 1.152075171470642} 08/30/2021 21:38:55 - INFO - __main__ - Step 46400: {'lr': 0.0003969506062863739, 'samples': 8908800, 'steps': 46399, 'loss/train': 1.3723593950271606} 08/30/2021 21:38:56 - INFO - __main__ - Step 46401: {'lr': 0.0003969463130731183, 'samples': 8908992, 'steps': 46400, 'loss/train': 1.1905274391174316} 08/30/2021 21:38:57 - INFO - __main__ - Step 46402: {'lr': 0.00039694201979365094, 'samples': 8909184, 'steps': 46401, 'loss/train': 1.1204434633255005} 08/30/2021 21:38:57 - INFO - __main__ - Step 46403: {'lr': 0.00039693772644797386, 'samples': 8909376, 'steps': 46402, 'loss/train': 1.4405134916305542} 08/30/2021 21:38:57 - INFO - __main__ - Step 46404: {'lr': 0.0003969334330360889, 'samples': 8909568, 'steps': 46403, 'loss/train': 0.5971283316612244} 08/30/2021 21:38:58 - INFO - __main__ - Step 46405: {'lr': 0.000396929139557998, 'samples': 8909760, 'steps': 46404, 'loss/train': 1.2352240085601807} 08/30/2021 21:38:59 - INFO - __main__ - Step 46406: {'lr': 0.00039692484601370305, 'samples': 8909952, 'steps': 46405, 'loss/train': 0.257072776556015} 08/30/2021 21:39:00 - INFO - __main__ - Step 46407: {'lr': 0.0003969205524032061, 'samples': 8910144, 'steps': 46406, 'loss/train': 1.5808016061782837} 08/30/2021 21:39:00 - INFO - __main__ - Step 46408: {'lr': 0.00039691625872650895, 'samples': 8910336, 'steps': 46407, 'loss/train': 0.11251096427440643} 08/30/2021 21:39:01 - INFO - __main__ - Step 46409: {'lr': 0.00039691196498361364, 'samples': 8910528, 'steps': 46408, 'loss/train': 1.4163175821304321} 08/30/2021 21:39:01 - INFO - __main__ - Step 46410: {'lr': 0.0003969076711745221, 'samples': 8910720, 'steps': 46409, 'loss/train': 1.0320390462875366} 08/30/2021 21:39:02 - INFO - __main__ - Step 46411: {'lr': 0.00039690337729923617, 'samples': 8910912, 'steps': 46410, 'loss/train': 1.420272707939148} 08/30/2021 21:39:03 - INFO - __main__ - Step 46412: {'lr': 0.0003968990833577578, 'samples': 8911104, 'steps': 46411, 'loss/train': 1.061478853225708} 08/30/2021 21:39:03 - INFO - __main__ - Step 46413: {'lr': 0.00039689478935008905, 'samples': 8911296, 'steps': 46412, 'loss/train': 1.1672465801239014} 08/30/2021 21:39:04 - INFO - __main__ - Step 46414: {'lr': 0.00039689049527623176, 'samples': 8911488, 'steps': 46413, 'loss/train': 1.199647068977356} 08/30/2021 21:39:04 - INFO - __main__ - Step 46415: {'lr': 0.0003968862011361879, 'samples': 8911680, 'steps': 46414, 'loss/train': 4.687029838562012} 08/30/2021 21:39:04 - INFO - __main__ - Step 46416: {'lr': 0.0003968819069299593, 'samples': 8911872, 'steps': 46415, 'loss/train': 1.5679432153701782} 08/30/2021 21:39:06 - INFO - __main__ - Step 46417: {'lr': 0.0003968776126575481, 'samples': 8912064, 'steps': 46416, 'loss/train': 1.315466284751892} 08/30/2021 21:39:06 - INFO - __main__ - Step 46418: {'lr': 0.000396873318318956, 'samples': 8912256, 'steps': 46417, 'loss/train': 1.759112000465393} 08/30/2021 21:39:07 - INFO - __main__ - Step 46419: {'lr': 0.00039686902391418514, 'samples': 8912448, 'steps': 46418, 'loss/train': 1.6858388185501099} 08/30/2021 21:39:07 - INFO - __main__ - Step 46420: {'lr': 0.00039686472944323734, 'samples': 8912640, 'steps': 46419, 'loss/train': 1.2738598585128784} 08/30/2021 21:39:07 - INFO - __main__ - Step 46421: {'lr': 0.0003968604349061145, 'samples': 8912832, 'steps': 46420, 'loss/train': 1.1749749183654785} 08/30/2021 21:39:09 - INFO - __main__ - Step 46422: {'lr': 0.0003968561403028187, 'samples': 8913024, 'steps': 46421, 'loss/train': 0.9057864546775818} 08/30/2021 21:39:09 - INFO - __main__ - Step 46423: {'lr': 0.00039685184563335174, 'samples': 8913216, 'steps': 46422, 'loss/train': 0.8991967439651489} 08/30/2021 21:39:10 - INFO - __main__ - Step 46424: {'lr': 0.00039684755089771555, 'samples': 8913408, 'steps': 46423, 'loss/train': 1.1481351852416992} 08/30/2021 21:39:10 - INFO - __main__ - Step 46425: {'lr': 0.0003968432560959122, 'samples': 8913600, 'steps': 46424, 'loss/train': 1.4056631326675415} 08/30/2021 21:39:10 - INFO - __main__ - Step 46426: {'lr': 0.00039683896122794354, 'samples': 8913792, 'steps': 46425, 'loss/train': 0.5119500160217285} 08/30/2021 21:39:12 - INFO - __main__ - Step 46427: {'lr': 0.0003968346662938115, 'samples': 8913984, 'steps': 46426, 'loss/train': 1.2142152786254883} 08/30/2021 21:39:12 - INFO - __main__ - Step 46428: {'lr': 0.00039683037129351805, 'samples': 8914176, 'steps': 46427, 'loss/train': 1.055873155593872} 08/30/2021 21:39:13 - INFO - __main__ - Step 46429: {'lr': 0.000396826076227065, 'samples': 8914368, 'steps': 46428, 'loss/train': 2.5989089012145996} 08/30/2021 21:39:13 - INFO - __main__ - Step 46430: {'lr': 0.00039682178109445447, 'samples': 8914560, 'steps': 46429, 'loss/train': 1.3609981536865234} 08/30/2021 21:39:14 - INFO - __main__ - Step 46431: {'lr': 0.0003968174858956883, 'samples': 8914752, 'steps': 46430, 'loss/train': 1.3880488872528076} 08/30/2021 21:39:14 - INFO - __main__ - Step 46432: {'lr': 0.0003968131906307684, 'samples': 8914944, 'steps': 46431, 'loss/train': 2.0379881858825684} 08/30/2021 21:39:15 - INFO - __main__ - Step 46433: {'lr': 0.00039680889529969686, 'samples': 8915136, 'steps': 46432, 'loss/train': 1.4394398927688599} 08/30/2021 21:39:16 - INFO - __main__ - Step 46434: {'lr': 0.0003968045999024754, 'samples': 8915328, 'steps': 46433, 'loss/train': 1.478371500968933} 08/30/2021 21:39:16 - INFO - __main__ - Step 46435: {'lr': 0.0003968003044391061, 'samples': 8915520, 'steps': 46434, 'loss/train': 1.430979609489441} 08/30/2021 21:39:17 - INFO - __main__ - Step 46436: {'lr': 0.00039679600890959077, 'samples': 8915712, 'steps': 46435, 'loss/train': 1.47868013381958} 08/30/2021 21:39:17 - INFO - __main__ - Step 46437: {'lr': 0.0003967917133139315, 'samples': 8915904, 'steps': 46436, 'loss/train': 0.9623647928237915} 08/30/2021 21:39:18 - INFO - __main__ - Step 46438: {'lr': 0.00039678741765213006, 'samples': 8916096, 'steps': 46437, 'loss/train': 1.2012237310409546} 08/30/2021 21:39:19 - INFO - __main__ - Step 46439: {'lr': 0.0003967831219241885, 'samples': 8916288, 'steps': 46438, 'loss/train': 1.716123342514038} 08/30/2021 21:39:19 - INFO - __main__ - Step 46440: {'lr': 0.00039677882613010885, 'samples': 8916480, 'steps': 46439, 'loss/train': 1.2938593626022339} 08/30/2021 21:39:20 - INFO - __main__ - Step 46441: {'lr': 0.0003967745302698928, 'samples': 8916672, 'steps': 46440, 'loss/train': 1.6129469871520996} 08/30/2021 21:39:20 - INFO - __main__ - Step 46442: {'lr': 0.0003967702343435424, 'samples': 8916864, 'steps': 46441, 'loss/train': 1.0996365547180176} 08/30/2021 21:39:21 - INFO - __main__ - Step 46443: {'lr': 0.00039676593835105966, 'samples': 8917056, 'steps': 46442, 'loss/train': 1.3036185503005981} 08/30/2021 21:39:22 - INFO - __main__ - Step 46444: {'lr': 0.0003967616422924465, 'samples': 8917248, 'steps': 46443, 'loss/train': 0.3570886254310608} 08/30/2021 21:39:22 - INFO - __main__ - Step 46445: {'lr': 0.0003967573461677047, 'samples': 8917440, 'steps': 46444, 'loss/train': 1.205920934677124} 08/30/2021 21:39:23 - INFO - __main__ - Step 46446: {'lr': 0.0003967530499768364, 'samples': 8917632, 'steps': 46445, 'loss/train': 1.3876349925994873} 08/30/2021 21:39:23 - INFO - __main__ - Step 46447: {'lr': 0.00039674875371984336, 'samples': 8917824, 'steps': 46446, 'loss/train': 1.094080924987793} 08/30/2021 21:39:25 - INFO - __main__ - Step 46448: {'lr': 0.0003967444573967277, 'samples': 8918016, 'steps': 46447, 'loss/train': 1.777151107788086} 08/30/2021 21:39:26 - INFO - __main__ - Step 46449: {'lr': 0.0003967401610074911, 'samples': 8918208, 'steps': 46448, 'loss/train': 1.5550758838653564} 08/30/2021 21:39:26 - INFO - __main__ - Step 46450: {'lr': 0.0003967358645521357, 'samples': 8918400, 'steps': 46449, 'loss/train': 1.61412513256073} 08/30/2021 21:39:26 - INFO - __main__ - Step 46451: {'lr': 0.00039673156803066346, 'samples': 8918592, 'steps': 46450, 'loss/train': 1.265376329421997} 08/30/2021 21:39:27 - INFO - __main__ - Step 46452: {'lr': 0.00039672727144307617, 'samples': 8918784, 'steps': 46451, 'loss/train': 1.3651338815689087} 08/30/2021 21:39:29 - INFO - __main__ - Step 46453: {'lr': 0.0003967229747893759, 'samples': 8918976, 'steps': 46452, 'loss/train': 1.778683066368103} 08/30/2021 21:39:29 - INFO - __main__ - Step 46454: {'lr': 0.0003967186780695645, 'samples': 8919168, 'steps': 46453, 'loss/train': 0.8877943754196167} 08/30/2021 21:39:29 - INFO - __main__ - Step 46455: {'lr': 0.0003967143812836439, 'samples': 8919360, 'steps': 46454, 'loss/train': 1.4448751211166382} 08/30/2021 21:39:30 - INFO - __main__ - Step 46456: {'lr': 0.00039671008443161604, 'samples': 8919552, 'steps': 46455, 'loss/train': 1.5197033882141113} 08/30/2021 21:39:30 - INFO - __main__ - Step 46457: {'lr': 0.00039670578751348283, 'samples': 8919744, 'steps': 46456, 'loss/train': 1.4699782133102417} 08/30/2021 21:39:31 - INFO - __main__ - Step 46458: {'lr': 0.0003967014905292464, 'samples': 8919936, 'steps': 46457, 'loss/train': 1.248752474784851} 08/30/2021 21:39:32 - INFO - __main__ - Step 46459: {'lr': 0.0003966971934789084, 'samples': 8920128, 'steps': 46458, 'loss/train': 1.0813713073730469} 08/30/2021 21:39:33 - INFO - __main__ - Step 46460: {'lr': 0.0003966928963624711, 'samples': 8920320, 'steps': 46459, 'loss/train': 0.6591024994850159} 08/30/2021 21:39:33 - INFO - __main__ - Step 46461: {'lr': 0.0003966885991799361, 'samples': 8920512, 'steps': 46460, 'loss/train': 0.09682805836200714} 08/30/2021 21:39:34 - INFO - __main__ - Step 46462: {'lr': 0.0003966843019313055, 'samples': 8920704, 'steps': 46461, 'loss/train': 1.508422613143921} 08/30/2021 21:39:34 - INFO - __main__ - Step 46463: {'lr': 0.00039668000461658126, 'samples': 8920896, 'steps': 46462, 'loss/train': 1.7693690061569214} 08/30/2021 21:39:34 - INFO - __main__ - Step 46464: {'lr': 0.00039667570723576516, 'samples': 8921088, 'steps': 46463, 'loss/train': 1.7197455167770386} 08/30/2021 21:39:36 - INFO - __main__ - Step 46465: {'lr': 0.0003966714097888594, 'samples': 8921280, 'steps': 46464, 'loss/train': 1.1874061822891235} 08/30/2021 21:39:37 - INFO - __main__ - Step 46466: {'lr': 0.0003966671122758657, 'samples': 8921472, 'steps': 46465, 'loss/train': 1.247516393661499} 08/30/2021 21:39:37 - INFO - __main__ - Step 46467: {'lr': 0.00039666281469678604, 'samples': 8921664, 'steps': 46466, 'loss/train': 0.1041969582438469} 08/30/2021 21:39:37 - INFO - __main__ - Step 46468: {'lr': 0.0003966585170516224, 'samples': 8921856, 'steps': 46467, 'loss/train': 1.6621135473251343} 08/30/2021 21:39:38 - INFO - __main__ - Step 46469: {'lr': 0.0003966542193403767, 'samples': 8922048, 'steps': 46468, 'loss/train': 1.3643832206726074} 08/30/2021 21:39:39 - INFO - __main__ - Step 46470: {'lr': 0.00039664992156305086, 'samples': 8922240, 'steps': 46469, 'loss/train': 1.1635733842849731} 08/30/2021 21:39:40 - INFO - __main__ - Step 46471: {'lr': 0.00039664562371964683, 'samples': 8922432, 'steps': 46470, 'loss/train': 1.905537486076355} 08/30/2021 21:39:40 - INFO - __main__ - Step 46472: {'lr': 0.00039664132581016654, 'samples': 8922624, 'steps': 46471, 'loss/train': 1.318577766418457} 08/30/2021 21:39:40 - INFO - __main__ - Step 46473: {'lr': 0.000396637027834612, 'samples': 8922816, 'steps': 46472, 'loss/train': 1.265029788017273} 08/30/2021 21:39:41 - INFO - __main__ - Step 46474: {'lr': 0.000396632729792985, 'samples': 8923008, 'steps': 46473, 'loss/train': 1.259962558746338} 08/30/2021 21:39:42 - INFO - __main__ - Step 46475: {'lr': 0.00039662843168528756, 'samples': 8923200, 'steps': 46474, 'loss/train': 0.720410168170929} 08/30/2021 21:39:43 - INFO - __main__ - Step 46476: {'lr': 0.0003966241335115216, 'samples': 8923392, 'steps': 46475, 'loss/train': 0.5920434594154358} 08/30/2021 21:39:43 - INFO - __main__ - Step 46477: {'lr': 0.0003966198352716891, 'samples': 8923584, 'steps': 46476, 'loss/train': 1.7952494621276855} 08/30/2021 21:39:43 - INFO - __main__ - Step 46478: {'lr': 0.000396615536965792, 'samples': 8923776, 'steps': 46477, 'loss/train': 1.2083547115325928} 08/30/2021 21:39:44 - INFO - __main__ - Step 46479: {'lr': 0.00039661123859383214, 'samples': 8923968, 'steps': 46478, 'loss/train': 1.3400609493255615} 08/30/2021 21:39:45 - INFO - __main__ - Step 46480: {'lr': 0.0003966069401558116, 'samples': 8924160, 'steps': 46479, 'loss/train': 1.2760469913482666} 08/30/2021 21:39:46 - INFO - __main__ - Step 46481: {'lr': 0.0003966026416517321, 'samples': 8924352, 'steps': 46480, 'loss/train': 1.30097496509552} 08/30/2021 21:39:46 - INFO - __main__ - Step 46482: {'lr': 0.0003965983430815958, 'samples': 8924544, 'steps': 46481, 'loss/train': 0.6618870496749878} 08/30/2021 21:39:46 - INFO - __main__ - Step 46483: {'lr': 0.00039659404444540456, 'samples': 8924736, 'steps': 46482, 'loss/train': 0.9682953953742981} 08/30/2021 21:39:47 - INFO - __main__ - Step 46484: {'lr': 0.0003965897457431602, 'samples': 8924928, 'steps': 46483, 'loss/train': 1.440982460975647} 08/30/2021 21:39:48 - INFO - __main__ - Step 46485: {'lr': 0.00039658544697486486, 'samples': 8925120, 'steps': 46484, 'loss/train': 0.9061474800109863} 08/30/2021 21:39:49 - INFO - __main__ - Step 46486: {'lr': 0.0003965811481405204, 'samples': 8925312, 'steps': 46485, 'loss/train': 1.4429975748062134} 08/30/2021 21:39:49 - INFO - __main__ - Step 46487: {'lr': 0.00039657684924012873, 'samples': 8925504, 'steps': 46486, 'loss/train': 1.25197434425354} 08/30/2021 21:39:49 - INFO - __main__ - Step 46488: {'lr': 0.0003965725502736917, 'samples': 8925696, 'steps': 46487, 'loss/train': 2.442518472671509} 08/30/2021 21:39:50 - INFO - __main__ - Step 46489: {'lr': 0.0003965682512412114, 'samples': 8925888, 'steps': 46488, 'loss/train': 1.2521421909332275} 08/30/2021 21:39:52 - INFO - __main__ - Step 46490: {'lr': 0.0003965639521426897, 'samples': 8926080, 'steps': 46489, 'loss/train': 1.011144995689392} 08/30/2021 21:39:52 - INFO - __main__ - Step 46491: {'lr': 0.0003965596529781286, 'samples': 8926272, 'steps': 46490, 'loss/train': 1.5611035823822021} 08/30/2021 21:39:52 - INFO - __main__ - Step 46492: {'lr': 0.0003965553537475299, 'samples': 8926464, 'steps': 46491, 'loss/train': 0.7885032892227173} 08/30/2021 21:39:53 - INFO - __main__ - Step 46493: {'lr': 0.0003965510544508957, 'samples': 8926656, 'steps': 46492, 'loss/train': 2.105489492416382} 08/30/2021 21:39:53 - INFO - __main__ - Step 46494: {'lr': 0.0003965467550882278, 'samples': 8926848, 'steps': 46493, 'loss/train': 0.4497945308685303} 08/30/2021 21:39:53 - INFO - __main__ - Step 46495: {'lr': 0.0003965424556595282, 'samples': 8927040, 'steps': 46494, 'loss/train': 0.15612703561782837} 08/30/2021 21:39:55 - INFO - __main__ - Step 46496: {'lr': 0.0003965381561647988, 'samples': 8927232, 'steps': 46495, 'loss/train': 0.16381971538066864} 08/30/2021 21:39:56 - INFO - __main__ - Step 46497: {'lr': 0.0003965338566040416, 'samples': 8927424, 'steps': 46496, 'loss/train': 2.6674323081970215} 08/30/2021 21:39:56 - INFO - __main__ - Step 46498: {'lr': 0.0003965295569772585, 'samples': 8927616, 'steps': 46497, 'loss/train': 1.3930017948150635} 08/30/2021 21:39:56 - INFO - __main__ - Step 46499: {'lr': 0.00039652525728445145, 'samples': 8927808, 'steps': 46498, 'loss/train': 1.14142906665802} 08/30/2021 21:39:57 - INFO - __main__ - Step 46500: {'lr': 0.00039652095752562246, 'samples': 8928000, 'steps': 46499, 'loss/train': 1.0763142108917236} 08/30/2021 21:39:57 - INFO - __main__ - Step 46501: {'lr': 0.00039651665770077326, 'samples': 8928192, 'steps': 46500, 'loss/train': 1.2496905326843262} 08/30/2021 21:39:59 - INFO - __main__ - Step 46502: {'lr': 0.00039651235780990596, 'samples': 8928384, 'steps': 46501, 'loss/train': 1.7091392278671265} 08/30/2021 21:40:00 - INFO - __main__ - Step 46503: {'lr': 0.00039650805785302245, 'samples': 8928576, 'steps': 46502, 'loss/train': 1.410305142402649} 08/30/2021 21:40:00 - INFO - __main__ - Step 46504: {'lr': 0.0003965037578301247, 'samples': 8928768, 'steps': 46503, 'loss/train': 2.1920878887176514} 08/30/2021 21:40:01 - INFO - __main__ - Step 46505: {'lr': 0.00039649945774121453, 'samples': 8928960, 'steps': 46504, 'loss/train': 0.07647178322076797} 08/30/2021 21:40:01 - INFO - __main__ - Step 46506: {'lr': 0.0003964951575862941, 'samples': 8929152, 'steps': 46505, 'loss/train': 2.2515416145324707} 08/30/2021 21:40:03 - INFO - __main__ - Step 46507: {'lr': 0.00039649085736536517, 'samples': 8929344, 'steps': 46506, 'loss/train': 1.6036421060562134} 08/30/2021 21:40:03 - INFO - __main__ - Step 46508: {'lr': 0.0003964865570784296, 'samples': 8929536, 'steps': 46507, 'loss/train': 1.660893201828003} 08/30/2021 21:40:03 - INFO - __main__ - Step 46509: {'lr': 0.00039648225672548953, 'samples': 8929728, 'steps': 46508, 'loss/train': 1.238147497177124} 08/30/2021 21:40:04 - INFO - __main__ - Step 46510: {'lr': 0.00039647795630654687, 'samples': 8929920, 'steps': 46509, 'loss/train': 0.27527180314064026} 08/30/2021 21:40:04 - INFO - __main__ - Step 46511: {'lr': 0.00039647365582160345, 'samples': 8930112, 'steps': 46510, 'loss/train': 1.1017048358917236} 08/30/2021 21:40:06 - INFO - __main__ - Step 46512: {'lr': 0.00039646935527066124, 'samples': 8930304, 'steps': 46511, 'loss/train': 1.0389946699142456} 08/30/2021 21:40:06 - INFO - __main__ - Step 46513: {'lr': 0.00039646505465372223, 'samples': 8930496, 'steps': 46512, 'loss/train': 1.0745177268981934} 08/30/2021 21:40:06 - INFO - __main__ - Step 46514: {'lr': 0.0003964607539707884, 'samples': 8930688, 'steps': 46513, 'loss/train': 1.3683040142059326} 08/30/2021 21:40:07 - INFO - __main__ - Step 46515: {'lr': 0.0003964564532218615, 'samples': 8930880, 'steps': 46514, 'loss/train': 1.363304853439331} 08/30/2021 21:40:07 - INFO - __main__ - Step 46516: {'lr': 0.0003964521524069436, 'samples': 8931072, 'steps': 46515, 'loss/train': 1.4092862606048584} 08/30/2021 21:40:09 - INFO - __main__ - Step 46517: {'lr': 0.00039644785152603666, 'samples': 8931264, 'steps': 46516, 'loss/train': 2.0359411239624023} 08/30/2021 21:40:09 - INFO - __main__ - Step 46518: {'lr': 0.0003964435505791425, 'samples': 8931456, 'steps': 46517, 'loss/train': 1.0100133419036865} 08/30/2021 21:40:09 - INFO - __main__ - Step 46519: {'lr': 0.0003964392495662632, 'samples': 8931648, 'steps': 46518, 'loss/train': 2.2036702632904053} 08/30/2021 21:40:10 - INFO - __main__ - Step 46520: {'lr': 0.0003964349484874007, 'samples': 8931840, 'steps': 46519, 'loss/train': 1.5280835628509521} 08/30/2021 21:40:10 - INFO - __main__ - Step 46521: {'lr': 0.00039643064734255675, 'samples': 8932032, 'steps': 46520, 'loss/train': 1.4089839458465576} 08/30/2021 21:40:12 - INFO - __main__ - Step 46522: {'lr': 0.0003964263461317334, 'samples': 8932224, 'steps': 46521, 'loss/train': 1.513013243675232} 08/30/2021 21:40:12 - INFO - __main__ - Step 46523: {'lr': 0.0003964220448549327, 'samples': 8932416, 'steps': 46522, 'loss/train': 1.6826832294464111} 08/30/2021 21:40:12 - INFO - __main__ - Step 46524: {'lr': 0.0003964177435121565, 'samples': 8932608, 'steps': 46523, 'loss/train': 1.1576457023620605} 08/30/2021 21:40:13 - INFO - __main__ - Step 46525: {'lr': 0.00039641344210340665, 'samples': 8932800, 'steps': 46524, 'loss/train': 1.2321707010269165} 08/30/2021 21:40:13 - INFO - __main__ - Step 46526: {'lr': 0.00039640914062868515, 'samples': 8932992, 'steps': 46525, 'loss/train': 1.8718773126602173} 08/30/2021 21:40:15 - INFO - __main__ - Step 46527: {'lr': 0.000396404839087994, 'samples': 8933184, 'steps': 46526, 'loss/train': 1.7893112897872925} 08/30/2021 21:40:16 - INFO - __main__ - Step 46528: {'lr': 0.0003964005374813351, 'samples': 8933376, 'steps': 46527, 'loss/train': 1.5159106254577637} 08/30/2021 21:40:16 - INFO - __main__ - Step 46529: {'lr': 0.0003963962358087103, 'samples': 8933568, 'steps': 46528, 'loss/train': 1.5724738836288452} 08/30/2021 21:40:16 - INFO - __main__ - Step 46530: {'lr': 0.00039639193407012166, 'samples': 8933760, 'steps': 46529, 'loss/train': 1.3901058435440063} 08/30/2021 21:40:17 - INFO - __main__ - Step 46531: {'lr': 0.00039638763226557106, 'samples': 8933952, 'steps': 46530, 'loss/train': 0.6951644420623779} 08/30/2021 21:40:17 - INFO - __main__ - Step 46532: {'lr': 0.0003963833303950605, 'samples': 8934144, 'steps': 46531, 'loss/train': 1.2721052169799805} 08/30/2021 21:40:18 - INFO - __main__ - Step 46533: {'lr': 0.00039637902845859185, 'samples': 8934336, 'steps': 46532, 'loss/train': 0.113104909658432} 08/30/2021 21:40:19 - INFO - __main__ - Step 46534: {'lr': 0.00039637472645616704, 'samples': 8934528, 'steps': 46533, 'loss/train': 1.9434700012207031} 08/30/2021 21:40:19 - INFO - __main__ - Step 46535: {'lr': 0.00039637042438778804, 'samples': 8934720, 'steps': 46534, 'loss/train': 1.445247769355774} 08/30/2021 21:40:20 - INFO - __main__ - Step 46536: {'lr': 0.0003963661222534568, 'samples': 8934912, 'steps': 46535, 'loss/train': 1.4683629274368286} 08/30/2021 21:40:20 - INFO - __main__ - Step 46537: {'lr': 0.00039636182005317524, 'samples': 8935104, 'steps': 46536, 'loss/train': 0.9552136063575745} 08/30/2021 21:40:22 - INFO - __main__ - Step 46538: {'lr': 0.0003963575177869453, 'samples': 8935296, 'steps': 46537, 'loss/train': 1.3797650337219238} 08/30/2021 21:40:22 - INFO - __main__ - Step 46539: {'lr': 0.00039635321545476894, 'samples': 8935488, 'steps': 46538, 'loss/train': 1.5685139894485474} 08/30/2021 21:40:23 - INFO - __main__ - Step 46540: {'lr': 0.00039634891305664806, 'samples': 8935680, 'steps': 46539, 'loss/train': 0.4467147886753082} 08/30/2021 21:40:23 - INFO - __main__ - Step 46541: {'lr': 0.00039634461059258466, 'samples': 8935872, 'steps': 46540, 'loss/train': 1.5122681856155396} 08/30/2021 21:40:23 - INFO - __main__ - Step 46542: {'lr': 0.0003963403080625806, 'samples': 8936064, 'steps': 46541, 'loss/train': 1.4097596406936646} 08/30/2021 21:40:24 - INFO - __main__ - Step 46543: {'lr': 0.00039633600546663784, 'samples': 8936256, 'steps': 46542, 'loss/train': 0.620442807674408} 08/30/2021 21:40:25 - INFO - __main__ - Step 46544: {'lr': 0.00039633170280475833, 'samples': 8936448, 'steps': 46543, 'loss/train': 0.02913687936961651} 08/30/2021 21:40:26 - INFO - __main__ - Step 46545: {'lr': 0.000396327400076944, 'samples': 8936640, 'steps': 46544, 'loss/train': 1.2260843515396118} 08/30/2021 21:40:26 - INFO - __main__ - Step 46546: {'lr': 0.0003963230972831968, 'samples': 8936832, 'steps': 46545, 'loss/train': 1.0982706546783447} 08/30/2021 21:40:26 - INFO - __main__ - Step 46547: {'lr': 0.0003963187944235188, 'samples': 8937024, 'steps': 46546, 'loss/train': 1.8399192094802856} 08/30/2021 21:40:27 - INFO - __main__ - Step 46548: {'lr': 0.00039631449149791164, 'samples': 8937216, 'steps': 46547, 'loss/train': 1.7213678359985352} 08/30/2021 21:40:27 - INFO - __main__ - Step 46549: {'lr': 0.0003963101885063776, 'samples': 8937408, 'steps': 46548, 'loss/train': 0.965840220451355} 08/30/2021 21:40:29 - INFO - __main__ - Step 46550: {'lr': 0.00039630588544891835, 'samples': 8937600, 'steps': 46549, 'loss/train': 1.4790263175964355} 08/30/2021 21:40:29 - INFO - __main__ - Step 46551: {'lr': 0.0003963015823255359, 'samples': 8937792, 'steps': 46550, 'loss/train': 1.2357102632522583} 08/30/2021 21:40:30 - INFO - __main__ - Step 46552: {'lr': 0.00039629727913623213, 'samples': 8937984, 'steps': 46551, 'loss/train': 0.5301083922386169} 08/30/2021 21:40:30 - INFO - __main__ - Step 46553: {'lr': 0.0003962929758810092, 'samples': 8938176, 'steps': 46552, 'loss/train': 1.064673900604248} 08/30/2021 21:40:30 - INFO - __main__ - Step 46554: {'lr': 0.00039628867255986887, 'samples': 8938368, 'steps': 46553, 'loss/train': 1.47206449508667} 08/30/2021 21:40:32 - INFO - __main__ - Step 46555: {'lr': 0.0003962843691728132, 'samples': 8938560, 'steps': 46554, 'loss/train': 1.1223132610321045} 08/30/2021 21:40:32 - INFO - __main__ - Step 46556: {'lr': 0.000396280065719844, 'samples': 8938752, 'steps': 46555, 'loss/train': 1.6951189041137695} 08/30/2021 21:40:33 - INFO - __main__ - Step 46557: {'lr': 0.0003962757622009632, 'samples': 8938944, 'steps': 46556, 'loss/train': 1.1746906042099} 08/30/2021 21:40:33 - INFO - __main__ - Step 46558: {'lr': 0.0003962714586161729, 'samples': 8939136, 'steps': 46557, 'loss/train': 1.461194634437561} 08/30/2021 21:40:33 - INFO - __main__ - Step 46559: {'lr': 0.0003962671549654748, 'samples': 8939328, 'steps': 46558, 'loss/train': 1.3189209699630737} 08/30/2021 21:40:35 - INFO - __main__ - Step 46560: {'lr': 0.00039626285124887107, 'samples': 8939520, 'steps': 46559, 'loss/train': 1.350839376449585} 08/30/2021 21:40:36 - INFO - __main__ - Step 46561: {'lr': 0.00039625854746636356, 'samples': 8939712, 'steps': 46560, 'loss/train': 1.627736210823059} 08/30/2021 21:40:36 - INFO - __main__ - Step 46562: {'lr': 0.0003962542436179542, 'samples': 8939904, 'steps': 46561, 'loss/train': 1.5022746324539185} 08/30/2021 21:40:37 - INFO - __main__ - Step 46563: {'lr': 0.0003962499397036449, 'samples': 8940096, 'steps': 46562, 'loss/train': 1.1978126764297485} 08/30/2021 21:40:37 - INFO - __main__ - Step 46564: {'lr': 0.0003962456357234377, 'samples': 8940288, 'steps': 46563, 'loss/train': 1.5251049995422363} 08/30/2021 21:40:38 - INFO - __main__ - Step 46565: {'lr': 0.0003962413316773344, 'samples': 8940480, 'steps': 46564, 'loss/train': 0.9784834980964661} 08/30/2021 21:40:39 - INFO - __main__ - Step 46566: {'lr': 0.000396237027565337, 'samples': 8940672, 'steps': 46565, 'loss/train': 1.513731837272644} 08/30/2021 21:40:39 - INFO - __main__ - Step 46567: {'lr': 0.00039623272338744754, 'samples': 8940864, 'steps': 46566, 'loss/train': 1.0512104034423828} 08/30/2021 21:40:40 - INFO - __main__ - Step 46568: {'lr': 0.00039622841914366784, 'samples': 8941056, 'steps': 46567, 'loss/train': 1.1498605012893677} 08/30/2021 21:40:40 - INFO - __main__ - Step 46569: {'lr': 0.0003962241148339999, 'samples': 8941248, 'steps': 46568, 'loss/train': 1.5554029941558838} 08/30/2021 21:40:41 - INFO - __main__ - Step 46570: {'lr': 0.0003962198104584456, 'samples': 8941440, 'steps': 46569, 'loss/train': 1.2344026565551758} 08/30/2021 21:40:42 - INFO - __main__ - Step 46571: {'lr': 0.00039621550601700683, 'samples': 8941632, 'steps': 46570, 'loss/train': 1.5185738801956177} 08/30/2021 21:40:42 - INFO - __main__ - Step 46572: {'lr': 0.0003962112015096857, 'samples': 8941824, 'steps': 46571, 'loss/train': 0.6050847768783569} 08/30/2021 21:40:43 - INFO - __main__ - Step 46573: {'lr': 0.00039620689693648404, 'samples': 8942016, 'steps': 46572, 'loss/train': 1.4969356060028076} 08/30/2021 21:40:43 - INFO - __main__ - Step 46574: {'lr': 0.0003962025922974038, 'samples': 8942208, 'steps': 46573, 'loss/train': 1.7167227268218994} 08/30/2021 21:40:45 - INFO - __main__ - Step 46575: {'lr': 0.00039619828759244693, 'samples': 8942400, 'steps': 46574, 'loss/train': 1.585473895072937} 08/30/2021 21:40:45 - INFO - __main__ - Step 46576: {'lr': 0.00039619398282161536, 'samples': 8942592, 'steps': 46575, 'loss/train': 0.7961347103118896} 08/30/2021 21:40:45 - INFO - __main__ - Step 46577: {'lr': 0.000396189677984911, 'samples': 8942784, 'steps': 46576, 'loss/train': 1.3021938800811768} 08/30/2021 21:40:46 - INFO - __main__ - Step 46578: {'lr': 0.00039618537308233593, 'samples': 8942976, 'steps': 46577, 'loss/train': 1.3764525651931763} 08/30/2021 21:40:46 - INFO - __main__ - Step 46579: {'lr': 0.00039618106811389187, 'samples': 8943168, 'steps': 46578, 'loss/train': 1.0017321109771729} 08/30/2021 21:40:46 - INFO - __main__ - Step 46580: {'lr': 0.00039617676307958095, 'samples': 8943360, 'steps': 46579, 'loss/train': 1.287327527999878} 08/30/2021 21:40:48 - INFO - __main__ - Step 46581: {'lr': 0.000396172457979405, 'samples': 8943552, 'steps': 46580, 'loss/train': 0.498635470867157} 08/30/2021 21:40:48 - INFO - __main__ - Step 46582: {'lr': 0.0003961681528133661, 'samples': 8943744, 'steps': 46581, 'loss/train': 1.1807124614715576} 08/30/2021 21:40:49 - INFO - __main__ - Step 46583: {'lr': 0.00039616384758146594, 'samples': 8943936, 'steps': 46582, 'loss/train': 1.3059812784194946} 08/30/2021 21:40:49 - INFO - __main__ - Step 46584: {'lr': 0.0003961595422837067, 'samples': 8944128, 'steps': 46583, 'loss/train': 1.5214323997497559} 08/30/2021 21:40:50 - INFO - __main__ - Step 46585: {'lr': 0.0003961552369200902, 'samples': 8944320, 'steps': 46584, 'loss/train': 2.019771099090576} 08/30/2021 21:40:51 - INFO - __main__ - Step 46586: {'lr': 0.0003961509314906184, 'samples': 8944512, 'steps': 46585, 'loss/train': 1.2820249795913696} 08/30/2021 21:40:51 - INFO - __main__ - Step 46587: {'lr': 0.00039614662599529325, 'samples': 8944704, 'steps': 46586, 'loss/train': 1.367170810699463} 08/30/2021 21:40:52 - INFO - __main__ - Step 46588: {'lr': 0.0003961423204341167, 'samples': 8944896, 'steps': 46587, 'loss/train': 1.2543559074401855} 08/30/2021 21:40:52 - INFO - __main__ - Step 46589: {'lr': 0.00039613801480709065, 'samples': 8945088, 'steps': 46588, 'loss/train': 1.3060096502304077} 08/30/2021 21:40:52 - INFO - __main__ - Step 46590: {'lr': 0.00039613370911421706, 'samples': 8945280, 'steps': 46589, 'loss/train': 0.9692651629447937} 08/30/2021 21:40:54 - INFO - __main__ - Step 46591: {'lr': 0.00039612940335549793, 'samples': 8945472, 'steps': 46590, 'loss/train': 1.582956075668335} 08/30/2021 21:40:54 - INFO - __main__ - Step 46592: {'lr': 0.0003961250975309351, 'samples': 8945664, 'steps': 46591, 'loss/train': 1.4397635459899902} 08/30/2021 21:40:55 - INFO - __main__ - Step 46593: {'lr': 0.0003961207916405305, 'samples': 8945856, 'steps': 46592, 'loss/train': 1.5003052949905396} 08/30/2021 21:40:55 - INFO - __main__ - Step 46594: {'lr': 0.00039611648568428626, 'samples': 8946048, 'steps': 46593, 'loss/train': 1.9489387273788452} 08/30/2021 21:40:55 - INFO - __main__ - Step 46595: {'lr': 0.0003961121796622041, 'samples': 8946240, 'steps': 46594, 'loss/train': 0.9217385053634644} 08/30/2021 21:40:57 - INFO - __main__ - Step 46596: {'lr': 0.000396107873574286, 'samples': 8946432, 'steps': 46595, 'loss/train': 1.646704912185669} 08/30/2021 21:40:58 - INFO - __main__ - Step 46597: {'lr': 0.00039610356742053403, 'samples': 8946624, 'steps': 46596, 'loss/train': 1.2484387159347534} 08/30/2021 21:40:58 - INFO - __main__ - Step 46598: {'lr': 0.0003960992612009501, 'samples': 8946816, 'steps': 46597, 'loss/train': 1.335153341293335} 08/30/2021 21:40:58 - INFO - __main__ - Step 46599: {'lr': 0.0003960949549155359, 'samples': 8947008, 'steps': 46598, 'loss/train': 1.810439109802246} 08/30/2021 21:40:59 - INFO - __main__ - Step 46600: {'lr': 0.0003960906485642938, 'samples': 8947200, 'steps': 46599, 'loss/train': 1.3295032978057861} 08/30/2021 21:41:00 - INFO - __main__ - Step 46601: {'lr': 0.0003960863421472254, 'samples': 8947392, 'steps': 46600, 'loss/train': 1.6985481977462769} 08/30/2021 21:41:01 - INFO - __main__ - Step 46602: {'lr': 0.00039608203566433273, 'samples': 8947584, 'steps': 46601, 'loss/train': 0.1064622700214386} 08/30/2021 21:41:01 - INFO - __main__ - Step 46603: {'lr': 0.00039607772911561776, 'samples': 8947776, 'steps': 46602, 'loss/train': 1.2042964696884155} 08/30/2021 21:41:01 - INFO - __main__ - Step 46604: {'lr': 0.00039607342250108234, 'samples': 8947968, 'steps': 46603, 'loss/train': 4.798513412475586} 08/30/2021 21:41:02 - INFO - __main__ - Step 46605: {'lr': 0.0003960691158207287, 'samples': 8948160, 'steps': 46604, 'loss/train': 1.0515400171279907} 08/30/2021 21:41:03 - INFO - __main__ - Step 46606: {'lr': 0.0003960648090745584, 'samples': 8948352, 'steps': 46605, 'loss/train': 1.8739527463912964} 08/30/2021 21:41:04 - INFO - __main__ - Step 46607: {'lr': 0.00039606050226257354, 'samples': 8948544, 'steps': 46606, 'loss/train': 1.622254729270935} 08/30/2021 21:41:04 - INFO - __main__ - Step 46608: {'lr': 0.00039605619538477617, 'samples': 8948736, 'steps': 46607, 'loss/train': 1.3610005378723145} 08/30/2021 21:41:04 - INFO - __main__ - Step 46609: {'lr': 0.00039605188844116815, 'samples': 8948928, 'steps': 46608, 'loss/train': 1.7554134130477905} 08/30/2021 21:41:05 - INFO - __main__ - Step 46610: {'lr': 0.0003960475814317512, 'samples': 8949120, 'steps': 46609, 'loss/train': 1.739786148071289} 08/30/2021 21:41:07 - INFO - __main__ - Step 46611: {'lr': 0.0003960432743565277, 'samples': 8949312, 'steps': 46610, 'loss/train': 1.4992097616195679} 08/30/2021 21:41:07 - INFO - __main__ - Step 46612: {'lr': 0.00039603896721549924, 'samples': 8949504, 'steps': 46611, 'loss/train': 1.392314076423645} 08/30/2021 21:41:08 - INFO - __main__ - Step 46613: {'lr': 0.0003960346600086679, 'samples': 8949696, 'steps': 46612, 'loss/train': 0.6547484993934631} 08/30/2021 21:41:08 - INFO - __main__ - Step 46614: {'lr': 0.0003960303527360356, 'samples': 8949888, 'steps': 46613, 'loss/train': 0.21509812772274017} 08/30/2021 21:41:09 - INFO - __main__ - Step 46615: {'lr': 0.00039602604539760425, 'samples': 8950080, 'steps': 46614, 'loss/train': 1.5131797790527344} 08/30/2021 21:41:09 - INFO - __main__ - Step 46616: {'lr': 0.0003960217379933758, 'samples': 8950272, 'steps': 46615, 'loss/train': 0.821017324924469} 08/30/2021 21:41:10 - INFO - __main__ - Step 46617: {'lr': 0.00039601743052335224, 'samples': 8950464, 'steps': 46616, 'loss/train': 1.099391222000122} 08/30/2021 21:41:11 - INFO - __main__ - Step 46618: {'lr': 0.00039601312298753554, 'samples': 8950656, 'steps': 46617, 'loss/train': 1.1759282350540161} 08/30/2021 21:41:11 - INFO - __main__ - Step 46619: {'lr': 0.0003960088153859275, 'samples': 8950848, 'steps': 46618, 'loss/train': 1.1875337362289429} 08/30/2021 21:41:12 - INFO - __main__ - Step 46620: {'lr': 0.0003960045077185301, 'samples': 8951040, 'steps': 46619, 'loss/train': 1.3251686096191406} 08/30/2021 21:41:12 - INFO - __main__ - Step 46621: {'lr': 0.0003960001999853454, 'samples': 8951232, 'steps': 46620, 'loss/train': 1.4342947006225586} 08/30/2021 21:41:13 - INFO - __main__ - Step 46622: {'lr': 0.00039599589218637535, 'samples': 8951424, 'steps': 46621, 'loss/train': 2.8867359161376953} 08/30/2021 21:41:14 - INFO - __main__ - Step 46623: {'lr': 0.00039599158432162163, 'samples': 8951616, 'steps': 46622, 'loss/train': 1.3775701522827148} 08/30/2021 21:41:14 - INFO - __main__ - Step 46624: {'lr': 0.00039598727639108644, 'samples': 8951808, 'steps': 46623, 'loss/train': 1.4124351739883423} 08/30/2021 21:41:15 - INFO - __main__ - Step 46625: {'lr': 0.00039598296839477167, 'samples': 8952000, 'steps': 46624, 'loss/train': 1.266311526298523} 08/30/2021 21:41:15 - INFO - __main__ - Step 46626: {'lr': 0.00039597866033267917, 'samples': 8952192, 'steps': 46625, 'loss/train': 1.1594483852386475} 08/30/2021 21:41:16 - INFO - __main__ - Step 46627: {'lr': 0.00039597435220481094, 'samples': 8952384, 'steps': 46626, 'loss/train': 0.37517017126083374} 08/30/2021 21:41:17 - INFO - __main__ - Step 46628: {'lr': 0.0003959700440111689, 'samples': 8952576, 'steps': 46627, 'loss/train': 0.752773106098175} 08/30/2021 21:41:17 - INFO - __main__ - Step 46629: {'lr': 0.00039596573575175506, 'samples': 8952768, 'steps': 46628, 'loss/train': 1.2355459928512573} 08/30/2021 21:41:18 - INFO - __main__ - Step 46630: {'lr': 0.00039596142742657125, 'samples': 8952960, 'steps': 46629, 'loss/train': 0.8349224925041199} 08/30/2021 21:41:18 - INFO - __main__ - Step 46631: {'lr': 0.00039595711903561947, 'samples': 8953152, 'steps': 46630, 'loss/train': 1.322335958480835} 08/30/2021 21:41:18 - INFO - __main__ - Step 46632: {'lr': 0.0003959528105789018, 'samples': 8953344, 'steps': 46631, 'loss/train': 1.4486145973205566} 08/30/2021 21:41:20 - INFO - __main__ - Step 46633: {'lr': 0.00039594850205641985, 'samples': 8953536, 'steps': 46632, 'loss/train': 2.146667242050171} 08/30/2021 21:41:20 - INFO - __main__ - Step 46634: {'lr': 0.0003959441934681759, 'samples': 8953728, 'steps': 46633, 'loss/train': 0.9349782466888428} 08/30/2021 21:41:20 - INFO - __main__ - Step 46635: {'lr': 0.00039593988481417174, 'samples': 8953920, 'steps': 46634, 'loss/train': 1.77628493309021} 08/30/2021 21:41:21 - INFO - __main__ - Step 46636: {'lr': 0.0003959355760944093, 'samples': 8954112, 'steps': 46635, 'loss/train': 1.5776880979537964} 08/30/2021 21:41:21 - INFO - __main__ - Step 46637: {'lr': 0.0003959312673088905, 'samples': 8954304, 'steps': 46636, 'loss/train': 1.3206682205200195} 08/30/2021 21:41:23 - INFO - __main__ - Step 46638: {'lr': 0.0003959269584576173, 'samples': 8954496, 'steps': 46637, 'loss/train': 1.2387782335281372} 08/30/2021 21:41:23 - INFO - __main__ - Step 46639: {'lr': 0.00039592264954059177, 'samples': 8954688, 'steps': 46638, 'loss/train': 1.8264864683151245} 08/30/2021 21:41:24 - INFO - __main__ - Step 46640: {'lr': 0.00039591834055781566, 'samples': 8954880, 'steps': 46639, 'loss/train': 0.7616661787033081} 08/30/2021 21:41:24 - INFO - __main__ - Step 46641: {'lr': 0.0003959140315092911, 'samples': 8955072, 'steps': 46640, 'loss/train': 1.5174589157104492} 08/30/2021 21:41:25 - INFO - __main__ - Step 46642: {'lr': 0.00039590972239501984, 'samples': 8955264, 'steps': 46641, 'loss/train': 1.505954384803772} 08/30/2021 21:41:26 - INFO - __main__ - Step 46643: {'lr': 0.0003959054132150039, 'samples': 8955456, 'steps': 46642, 'loss/train': 1.04756498336792} 08/30/2021 21:41:26 - INFO - __main__ - Step 46644: {'lr': 0.00039590110396924526, 'samples': 8955648, 'steps': 46643, 'loss/train': 1.6038703918457031} 08/30/2021 21:41:27 - INFO - __main__ - Step 46645: {'lr': 0.0003958967946577459, 'samples': 8955840, 'steps': 46644, 'loss/train': 1.108014702796936} 08/30/2021 21:41:27 - INFO - __main__ - Step 46646: {'lr': 0.0003958924852805076, 'samples': 8956032, 'steps': 46645, 'loss/train': 1.7820674180984497} 08/30/2021 21:41:28 - INFO - __main__ - Step 46647: {'lr': 0.00039588817583753236, 'samples': 8956224, 'steps': 46646, 'loss/train': 1.1025137901306152} 08/30/2021 21:41:28 - INFO - __main__ - Step 46648: {'lr': 0.0003958838663288223, 'samples': 8956416, 'steps': 46647, 'loss/train': 1.5573009252548218} 08/30/2021 21:41:29 - INFO - __main__ - Step 46649: {'lr': 0.00039587955675437917, 'samples': 8956608, 'steps': 46648, 'loss/train': 1.522752285003662} 08/30/2021 21:41:30 - INFO - __main__ - Step 46650: {'lr': 0.00039587524711420487, 'samples': 8956800, 'steps': 46649, 'loss/train': 1.0329043865203857} 08/30/2021 21:41:30 - INFO - __main__ - Step 46651: {'lr': 0.00039587093740830147, 'samples': 8956992, 'steps': 46650, 'loss/train': 1.0183699131011963} 08/30/2021 21:41:30 - INFO - __main__ - Step 46652: {'lr': 0.0003958666276366709, 'samples': 8957184, 'steps': 46651, 'loss/train': 1.0930331945419312} 08/30/2021 21:41:31 - INFO - __main__ - Step 46653: {'lr': 0.00039586231779931516, 'samples': 8957376, 'steps': 46652, 'loss/train': 1.5064520835876465} 08/30/2021 21:41:32 - INFO - __main__ - Step 46654: {'lr': 0.000395858007896236, 'samples': 8957568, 'steps': 46653, 'loss/train': 1.2531154155731201} 08/30/2021 21:41:33 - INFO - __main__ - Step 46655: {'lr': 0.0003958536979274355, 'samples': 8957760, 'steps': 46654, 'loss/train': 1.304987907409668} 08/30/2021 21:41:33 - INFO - __main__ - Step 46656: {'lr': 0.00039584938789291563, 'samples': 8957952, 'steps': 46655, 'loss/train': 1.5240198373794556} 08/30/2021 21:41:33 - INFO - __main__ - Step 46657: {'lr': 0.0003958450777926782, 'samples': 8958144, 'steps': 46656, 'loss/train': 1.392342209815979} 08/30/2021 21:41:34 - INFO - __main__ - Step 46658: {'lr': 0.00039584076762672526, 'samples': 8958336, 'steps': 46657, 'loss/train': 1.3740333318710327} 08/30/2021 21:41:35 - INFO - __main__ - Step 46659: {'lr': 0.0003958364573950587, 'samples': 8958528, 'steps': 46658, 'loss/train': 1.1832071542739868} 08/30/2021 21:41:36 - INFO - __main__ - Step 46660: {'lr': 0.00039583214709768054, 'samples': 8958720, 'steps': 46659, 'loss/train': 0.8641722202301025} 08/30/2021 21:41:36 - INFO - __main__ - Step 46661: {'lr': 0.0003958278367345926, 'samples': 8958912, 'steps': 46660, 'loss/train': 1.4959338903427124} 08/30/2021 21:41:37 - INFO - __main__ - Step 46662: {'lr': 0.00039582352630579697, 'samples': 8959104, 'steps': 46661, 'loss/train': 0.5050196647644043} 08/30/2021 21:41:37 - INFO - __main__ - Step 46663: {'lr': 0.00039581921581129543, 'samples': 8959296, 'steps': 46662, 'loss/train': 1.296554446220398} 08/30/2021 21:41:39 - INFO - __main__ - Step 46664: {'lr': 0.00039581490525109005, 'samples': 8959488, 'steps': 46663, 'loss/train': 1.3569530248641968} 08/30/2021 21:41:39 - INFO - __main__ - Step 46665: {'lr': 0.00039581059462518266, 'samples': 8959680, 'steps': 46664, 'loss/train': 1.441269874572754} 08/30/2021 21:41:40 - INFO - __main__ - Step 46666: {'lr': 0.00039580628393357534, 'samples': 8959872, 'steps': 46665, 'loss/train': 2.0926387310028076} 08/30/2021 21:41:40 - INFO - __main__ - Step 46667: {'lr': 0.0003958019731762699, 'samples': 8960064, 'steps': 46666, 'loss/train': 1.323270559310913} 08/30/2021 21:41:41 - INFO - __main__ - Step 46668: {'lr': 0.0003957976623532684, 'samples': 8960256, 'steps': 46667, 'loss/train': 1.51996910572052} 08/30/2021 21:41:42 - INFO - __main__ - Step 46669: {'lr': 0.0003957933514645727, 'samples': 8960448, 'steps': 46668, 'loss/train': 0.8904617428779602} 08/30/2021 21:41:43 - INFO - __main__ - Step 46670: {'lr': 0.00039578904051018474, 'samples': 8960640, 'steps': 46669, 'loss/train': 1.41978120803833} 08/30/2021 21:41:43 - INFO - __main__ - Step 46671: {'lr': 0.00039578472949010644, 'samples': 8960832, 'steps': 46670, 'loss/train': 1.8270494937896729} 08/30/2021 21:41:44 - INFO - __main__ - Step 46672: {'lr': 0.00039578041840433986, 'samples': 8961024, 'steps': 46671, 'loss/train': 1.687943696975708} 08/30/2021 21:41:44 - INFO - __main__ - Step 46673: {'lr': 0.00039577610725288694, 'samples': 8961216, 'steps': 46672, 'loss/train': 1.4522080421447754} 08/30/2021 21:41:44 - INFO - __main__ - Step 46674: {'lr': 0.0003957717960357494, 'samples': 8961408, 'steps': 46673, 'loss/train': 0.05596524477005005} 08/30/2021 21:41:46 - INFO - __main__ - Step 46675: {'lr': 0.0003957674847529295, 'samples': 8961600, 'steps': 46674, 'loss/train': 1.565984845161438} 08/30/2021 21:41:46 - INFO - __main__ - Step 46676: {'lr': 0.00039576317340442893, 'samples': 8961792, 'steps': 46675, 'loss/train': 0.8277280926704407} 08/30/2021 21:41:47 - INFO - __main__ - Step 46677: {'lr': 0.00039575886199024976, 'samples': 8961984, 'steps': 46676, 'loss/train': 1.6112449169158936} 08/30/2021 21:41:47 - INFO - __main__ - Step 46678: {'lr': 0.0003957545505103939, 'samples': 8962176, 'steps': 46677, 'loss/train': 1.4441978931427002} 08/30/2021 21:41:47 - INFO - __main__ - Step 46679: {'lr': 0.0003957502389648632, 'samples': 8962368, 'steps': 46678, 'loss/train': 0.9319394826889038} 08/30/2021 21:41:49 - INFO - __main__ - Step 46680: {'lr': 0.00039574592735365976, 'samples': 8962560, 'steps': 46679, 'loss/train': 1.4110281467437744} 08/30/2021 21:41:49 - INFO - __main__ - Step 46681: {'lr': 0.00039574161567678545, 'samples': 8962752, 'steps': 46680, 'loss/train': 1.7208095788955688} 08/30/2021 21:41:50 - INFO - __main__ - Step 46682: {'lr': 0.00039573730393424226, 'samples': 8962944, 'steps': 46681, 'loss/train': 1.565172791481018} 08/30/2021 21:41:50 - INFO - __main__ - Step 46683: {'lr': 0.000395732992126032, 'samples': 8963136, 'steps': 46682, 'loss/train': 0.8123407959938049} 08/30/2021 21:41:50 - INFO - __main__ - Step 46684: {'lr': 0.00039572868025215677, 'samples': 8963328, 'steps': 46683, 'loss/train': 1.3226916790008545} 08/30/2021 21:41:52 - INFO - __main__ - Step 46685: {'lr': 0.0003957243683126184, 'samples': 8963520, 'steps': 46684, 'loss/train': 1.796629786491394} 08/30/2021 21:41:52 - INFO - __main__ - Step 46686: {'lr': 0.00039572005630741886, 'samples': 8963712, 'steps': 46685, 'loss/train': 1.2148160934448242} 08/30/2021 21:41:52 - INFO - __main__ - Step 46687: {'lr': 0.00039571574423656017, 'samples': 8963904, 'steps': 46686, 'loss/train': 1.4637819528579712} 08/30/2021 21:41:53 - INFO - __main__ - Step 46688: {'lr': 0.0003957114321000442, 'samples': 8964096, 'steps': 46687, 'loss/train': 1.4490044116973877} 08/30/2021 21:41:53 - INFO - __main__ - Step 46689: {'lr': 0.0003957071198978729, 'samples': 8964288, 'steps': 46688, 'loss/train': 1.9750012159347534} 08/30/2021 21:41:55 - INFO - __main__ - Step 46690: {'lr': 0.00039570280763004823, 'samples': 8964480, 'steps': 46689, 'loss/train': 0.6598650813102722} 08/30/2021 21:41:55 - INFO - __main__ - Step 46691: {'lr': 0.0003956984952965721, 'samples': 8964672, 'steps': 46690, 'loss/train': 0.6906108856201172} 08/30/2021 21:41:56 - INFO - __main__ - Step 46692: {'lr': 0.0003956941828974465, 'samples': 8964864, 'steps': 46691, 'loss/train': 1.3910542726516724} 08/30/2021 21:41:56 - INFO - __main__ - Step 46693: {'lr': 0.0003956898704326733, 'samples': 8965056, 'steps': 46692, 'loss/train': 1.6841434240341187} 08/30/2021 21:41:56 - INFO - __main__ - Step 46694: {'lr': 0.00039568555790225456, 'samples': 8965248, 'steps': 46693, 'loss/train': 0.796154260635376} 08/30/2021 21:41:58 - INFO - __main__ - Step 46695: {'lr': 0.00039568124530619213, 'samples': 8965440, 'steps': 46694, 'loss/train': 1.714715838432312} 08/30/2021 21:41:58 - INFO - __main__ - Step 46696: {'lr': 0.00039567693264448803, 'samples': 8965632, 'steps': 46695, 'loss/train': 1.0624397993087769} 08/30/2021 21:41:59 - INFO - __main__ - Step 46697: {'lr': 0.00039567261991714406, 'samples': 8965824, 'steps': 46696, 'loss/train': 1.678095817565918} 08/30/2021 21:41:59 - INFO - __main__ - Step 46698: {'lr': 0.00039566830712416226, 'samples': 8966016, 'steps': 46697, 'loss/train': 1.608786940574646} 08/30/2021 21:41:59 - INFO - __main__ - Step 46699: {'lr': 0.0003956639942655446, 'samples': 8966208, 'steps': 46698, 'loss/train': 1.038271188735962} 08/30/2021 21:42:01 - INFO - __main__ - Step 46700: {'lr': 0.000395659681341293, 'samples': 8966400, 'steps': 46699, 'loss/train': 1.3168480396270752} 08/30/2021 21:42:01 - INFO - __main__ - Step 46701: {'lr': 0.00039565536835140934, 'samples': 8966592, 'steps': 46700, 'loss/train': 1.6376005411148071} 08/30/2021 21:42:01 - INFO - __main__ - Step 46702: {'lr': 0.00039565105529589575, 'samples': 8966784, 'steps': 46701, 'loss/train': 0.26876187324523926} 08/30/2021 21:42:02 - INFO - __main__ - Step 46703: {'lr': 0.00039564674217475393, 'samples': 8966976, 'steps': 46702, 'loss/train': 2.0138771533966064} 08/30/2021 21:42:02 - INFO - __main__ - Step 46704: {'lr': 0.00039564242898798595, 'samples': 8967168, 'steps': 46703, 'loss/train': 1.4675276279449463} 08/30/2021 21:42:03 - INFO - __main__ - Step 46705: {'lr': 0.00039563811573559377, 'samples': 8967360, 'steps': 46704, 'loss/train': 1.349774718284607} 08/30/2021 21:42:04 - INFO - __main__ - Step 46706: {'lr': 0.00039563380241757927, 'samples': 8967552, 'steps': 46705, 'loss/train': 2.0031542778015137} 08/30/2021 21:42:05 - INFO - __main__ - Step 46707: {'lr': 0.00039562948903394446, 'samples': 8967744, 'steps': 46706, 'loss/train': 1.5094764232635498} 08/30/2021 21:42:05 - INFO - __main__ - Step 46708: {'lr': 0.00039562517558469124, 'samples': 8967936, 'steps': 46707, 'loss/train': 1.3479992151260376} 08/30/2021 21:42:05 - INFO - __main__ - Step 46709: {'lr': 0.00039562086206982157, 'samples': 8968128, 'steps': 46708, 'loss/train': 1.9954441785812378} 08/30/2021 21:42:06 - INFO - __main__ - Step 46710: {'lr': 0.0003956165484893374, 'samples': 8968320, 'steps': 46709, 'loss/train': 1.4335076808929443} 08/30/2021 21:42:07 - INFO - __main__ - Step 46711: {'lr': 0.0003956122348432406, 'samples': 8968512, 'steps': 46710, 'loss/train': 1.5069633722305298} 08/30/2021 21:42:08 - INFO - __main__ - Step 46712: {'lr': 0.0003956079211315332, 'samples': 8968704, 'steps': 46711, 'loss/train': 1.1742591857910156} 08/30/2021 21:42:08 - INFO - __main__ - Step 46713: {'lr': 0.00039560360735421706, 'samples': 8968896, 'steps': 46712, 'loss/train': 1.3166167736053467} 08/30/2021 21:42:08 - INFO - __main__ - Step 46714: {'lr': 0.0003955992935112943, 'samples': 8969088, 'steps': 46713, 'loss/train': 2.564699649810791} 08/30/2021 21:42:09 - INFO - __main__ - Step 46715: {'lr': 0.00039559497960276667, 'samples': 8969280, 'steps': 46714, 'loss/train': 0.9008917212486267} 08/30/2021 21:42:10 - INFO - __main__ - Step 46716: {'lr': 0.0003955906656286362, 'samples': 8969472, 'steps': 46715, 'loss/train': 1.0075536966323853} 08/30/2021 21:42:11 - INFO - __main__ - Step 46717: {'lr': 0.00039558635158890487, 'samples': 8969664, 'steps': 46716, 'loss/train': 1.7885315418243408} 08/30/2021 21:42:11 - INFO - __main__ - Step 46718: {'lr': 0.0003955820374835745, 'samples': 8969856, 'steps': 46717, 'loss/train': 1.791002869606018} 08/30/2021 21:42:11 - INFO - __main__ - Step 46719: {'lr': 0.0003955777233126472, 'samples': 8970048, 'steps': 46718, 'loss/train': 1.9397109746932983} 08/30/2021 21:42:12 - INFO - __main__ - Step 46720: {'lr': 0.00039557340907612473, 'samples': 8970240, 'steps': 46719, 'loss/train': 1.7698420286178589} 08/30/2021 21:42:14 - INFO - __main__ - Step 46721: {'lr': 0.00039556909477400914, 'samples': 8970432, 'steps': 46720, 'loss/train': 1.16049063205719} 08/30/2021 21:42:14 - INFO - __main__ - Step 46722: {'lr': 0.00039556478040630246, 'samples': 8970624, 'steps': 46721, 'loss/train': 0.9853895902633667} 08/30/2021 21:42:14 - INFO - __main__ - Step 46723: {'lr': 0.0003955604659730064, 'samples': 8970816, 'steps': 46722, 'loss/train': 1.8158965110778809} 08/30/2021 21:42:15 - INFO - __main__ - Step 46724: {'lr': 0.00039555615147412315, 'samples': 8971008, 'steps': 46723, 'loss/train': 1.3533720970153809} 08/30/2021 21:42:15 - INFO - __main__ - Step 46725: {'lr': 0.00039555183690965454, 'samples': 8971200, 'steps': 46724, 'loss/train': 0.7115915417671204} 08/30/2021 21:42:16 - INFO - __main__ - Step 46726: {'lr': 0.00039554752227960243, 'samples': 8971392, 'steps': 46725, 'loss/train': 1.4556275606155396} 08/30/2021 21:42:17 - INFO - __main__ - Step 46727: {'lr': 0.0003955432075839689, 'samples': 8971584, 'steps': 46726, 'loss/train': 1.592814326286316} 08/30/2021 21:42:18 - INFO - __main__ - Step 46728: {'lr': 0.00039553889282275585, 'samples': 8971776, 'steps': 46727, 'loss/train': 1.2864998579025269} 08/30/2021 21:42:18 - INFO - __main__ - Step 46729: {'lr': 0.0003955345779959653, 'samples': 8971968, 'steps': 46728, 'loss/train': 1.4471197128295898} 08/30/2021 21:42:18 - INFO - __main__ - Step 46730: {'lr': 0.00039553026310359897, 'samples': 8972160, 'steps': 46729, 'loss/train': 1.2276301383972168} 08/30/2021 21:42:19 - INFO - __main__ - Step 46731: {'lr': 0.000395525948145659, 'samples': 8972352, 'steps': 46730, 'loss/train': 1.077656865119934} 08/30/2021 21:42:21 - INFO - __main__ - Step 46732: {'lr': 0.0003955216331221473, 'samples': 8972544, 'steps': 46731, 'loss/train': 1.38236665725708} 08/30/2021 21:42:21 - INFO - __main__ - Step 46733: {'lr': 0.00039551731803306577, 'samples': 8972736, 'steps': 46732, 'loss/train': 1.2690858840942383} 08/30/2021 21:42:21 - INFO - __main__ - Step 46734: {'lr': 0.0003955130028784165, 'samples': 8972928, 'steps': 46733, 'loss/train': 1.246100902557373} 08/30/2021 21:42:22 - INFO - __main__ - Step 46735: {'lr': 0.0003955086876582012, 'samples': 8973120, 'steps': 46734, 'loss/train': 1.5914968252182007} 08/30/2021 21:42:22 - INFO - __main__ - Step 46736: {'lr': 0.000395504372372422, 'samples': 8973312, 'steps': 46735, 'loss/train': 1.3203520774841309} 08/30/2021 21:42:23 - INFO - __main__ - Step 46737: {'lr': 0.0003955000570210807, 'samples': 8973504, 'steps': 46736, 'loss/train': 1.2192316055297852} 08/30/2021 21:42:24 - INFO - __main__ - Step 46738: {'lr': 0.0003954957416041793, 'samples': 8973696, 'steps': 46737, 'loss/train': 1.6705372333526611} 08/30/2021 21:42:24 - INFO - __main__ - Step 46739: {'lr': 0.0003954914261217198, 'samples': 8973888, 'steps': 46738, 'loss/train': 1.587420105934143} 08/30/2021 21:42:25 - INFO - __main__ - Step 46740: {'lr': 0.0003954871105737042, 'samples': 8974080, 'steps': 46739, 'loss/train': 1.7164605855941772} 08/30/2021 21:42:25 - INFO - __main__ - Step 46741: {'lr': 0.00039548279496013424, 'samples': 8974272, 'steps': 46740, 'loss/train': 1.354990005493164} 08/30/2021 21:42:26 - INFO - __main__ - Step 46742: {'lr': 0.000395478479281012, 'samples': 8974464, 'steps': 46741, 'loss/train': 0.49001172184944153} 08/30/2021 21:42:27 - INFO - __main__ - Step 46743: {'lr': 0.00039547416353633946, 'samples': 8974656, 'steps': 46742, 'loss/train': 1.719616174697876} 08/30/2021 21:42:27 - INFO - __main__ - Step 46744: {'lr': 0.00039546984772611843, 'samples': 8974848, 'steps': 46743, 'loss/train': 1.4128555059432983} 08/30/2021 21:42:28 - INFO - __main__ - Step 46745: {'lr': 0.00039546553185035093, 'samples': 8975040, 'steps': 46744, 'loss/train': 1.2041451930999756} 08/30/2021 21:42:28 - INFO - __main__ - Step 46746: {'lr': 0.00039546121590903897, 'samples': 8975232, 'steps': 46745, 'loss/train': 0.9949818849563599} 08/30/2021 21:42:29 - INFO - __main__ - Step 46747: {'lr': 0.0003954568999021844, 'samples': 8975424, 'steps': 46746, 'loss/train': 0.9891777634620667} 08/30/2021 21:42:30 - INFO - __main__ - Step 46748: {'lr': 0.0003954525838297892, 'samples': 8975616, 'steps': 46747, 'loss/train': 0.6386354565620422} 08/30/2021 21:42:30 - INFO - __main__ - Step 46749: {'lr': 0.0003954482676918553, 'samples': 8975808, 'steps': 46748, 'loss/train': 1.3243474960327148} 08/30/2021 21:42:31 - INFO - __main__ - Step 46750: {'lr': 0.00039544395148838465, 'samples': 8976000, 'steps': 46749, 'loss/train': 1.4077264070510864} 08/30/2021 21:42:31 - INFO - __main__ - Step 46751: {'lr': 0.0003954396352193792, 'samples': 8976192, 'steps': 46750, 'loss/train': 1.731931209564209} 08/30/2021 21:42:32 - INFO - __main__ - Step 46752: {'lr': 0.000395435318884841, 'samples': 8976384, 'steps': 46751, 'loss/train': 0.9415560364723206} 08/30/2021 21:42:33 - INFO - __main__ - Step 46753: {'lr': 0.0003954310024847717, 'samples': 8976576, 'steps': 46752, 'loss/train': 0.8254061341285706} 08/30/2021 21:42:33 - INFO - __main__ - Step 46754: {'lr': 0.00039542668601917353, 'samples': 8976768, 'steps': 46753, 'loss/train': 1.4402449131011963} 08/30/2021 21:42:34 - INFO - __main__ - Step 46755: {'lr': 0.0003954223694880483, 'samples': 8976960, 'steps': 46754, 'loss/train': 1.4386957883834839} 08/30/2021 21:42:34 - INFO - __main__ - Step 46756: {'lr': 0.0003954180528913981, 'samples': 8977152, 'steps': 46755, 'loss/train': 1.414384365081787} 08/30/2021 21:42:34 - INFO - __main__ - Step 46757: {'lr': 0.0003954137362292247, 'samples': 8977344, 'steps': 46756, 'loss/train': 1.3734735250473022} 08/30/2021 21:42:36 - INFO - __main__ - Step 46758: {'lr': 0.0003954094195015301, 'samples': 8977536, 'steps': 46757, 'loss/train': 1.3338264226913452} 08/30/2021 21:42:36 - INFO - __main__ - Step 46759: {'lr': 0.0003954051027083163, 'samples': 8977728, 'steps': 46758, 'loss/train': 1.257049322128296} 08/30/2021 21:42:37 - INFO - __main__ - Step 46760: {'lr': 0.0003954007858495852, 'samples': 8977920, 'steps': 46759, 'loss/train': 1.6133140325546265} 08/30/2021 21:42:37 - INFO - __main__ - Step 46761: {'lr': 0.00039539646892533867, 'samples': 8978112, 'steps': 46760, 'loss/train': 0.7925180792808533} 08/30/2021 21:42:37 - INFO - __main__ - Step 46762: {'lr': 0.00039539215193557886, 'samples': 8978304, 'steps': 46761, 'loss/train': 1.6431457996368408} 08/30/2021 21:42:39 - INFO - __main__ - Step 46763: {'lr': 0.0003953878348803075, 'samples': 8978496, 'steps': 46762, 'loss/train': 1.5009441375732422} 08/30/2021 21:42:40 - INFO - __main__ - Step 46764: {'lr': 0.0003953835177595266, 'samples': 8978688, 'steps': 46763, 'loss/train': 1.6703245639801025} 08/30/2021 21:42:40 - INFO - __main__ - Step 46765: {'lr': 0.0003953792005732382, 'samples': 8978880, 'steps': 46764, 'loss/train': 1.4324314594268799} 08/30/2021 21:42:40 - INFO - __main__ - Step 46766: {'lr': 0.0003953748833214442, 'samples': 8979072, 'steps': 46765, 'loss/train': 2.132652759552002} 08/30/2021 21:42:41 - INFO - __main__ - Step 46767: {'lr': 0.00039537056600414647, 'samples': 8979264, 'steps': 46766, 'loss/train': 1.484071969985962} 08/30/2021 21:42:43 - INFO - __main__ - Step 46768: {'lr': 0.00039536624862134695, 'samples': 8979456, 'steps': 46767, 'loss/train': 0.051184408366680145} 08/30/2021 21:42:43 - INFO - __main__ - Step 46769: {'lr': 0.00039536193117304774, 'samples': 8979648, 'steps': 46768, 'loss/train': 0.13648787140846252} 08/30/2021 21:42:43 - INFO - __main__ - Step 46770: {'lr': 0.0003953576136592507, 'samples': 8979840, 'steps': 46769, 'loss/train': 1.4143809080123901} 08/30/2021 21:42:44 - INFO - __main__ - Step 46771: {'lr': 0.0003953532960799577, 'samples': 8980032, 'steps': 46770, 'loss/train': 0.10448271036148071} 08/30/2021 21:42:44 - INFO - __main__ - Step 46772: {'lr': 0.0003953489784351707, 'samples': 8980224, 'steps': 46771, 'loss/train': 1.5549207925796509} 08/30/2021 21:42:46 - INFO - __main__ - Step 46773: {'lr': 0.0003953446607248918, 'samples': 8980416, 'steps': 46772, 'loss/train': 0.9098787903785706} 08/30/2021 21:42:47 - INFO - __main__ - Step 46774: {'lr': 0.00039534034294912276, 'samples': 8980608, 'steps': 46773, 'loss/train': 1.4835467338562012} 08/30/2021 21:42:47 - INFO - __main__ - Step 46775: {'lr': 0.0003953360251078656, 'samples': 8980800, 'steps': 46774, 'loss/train': 1.5607223510742188} 08/30/2021 21:42:47 - INFO - __main__ - Step 46776: {'lr': 0.0003953317072011224, 'samples': 8980992, 'steps': 46775, 'loss/train': 1.2999229431152344} 08/30/2021 21:42:48 - INFO - __main__ - Step 46777: {'lr': 0.0003953273892288949, 'samples': 8981184, 'steps': 46776, 'loss/train': 0.8891803026199341} 08/30/2021 21:42:48 - INFO - __main__ - Step 46778: {'lr': 0.00039532307119118505, 'samples': 8981376, 'steps': 46777, 'loss/train': 1.2651509046554565} 08/30/2021 21:42:50 - INFO - __main__ - Step 46779: {'lr': 0.00039531875308799493, 'samples': 8981568, 'steps': 46778, 'loss/train': 1.9276164770126343} 08/30/2021 21:42:50 - INFO - __main__ - Step 46780: {'lr': 0.0003953144349193264, 'samples': 8981760, 'steps': 46779, 'loss/train': 1.5773847103118896} 08/30/2021 21:42:50 - INFO - __main__ - Step 46781: {'lr': 0.0003953101166851814, 'samples': 8981952, 'steps': 46780, 'loss/train': 1.127846360206604} 08/30/2021 21:42:51 - INFO - __main__ - Step 46782: {'lr': 0.0003953057983855619, 'samples': 8982144, 'steps': 46781, 'loss/train': 0.2567024230957031} 08/30/2021 21:42:51 - INFO - __main__ - Step 46783: {'lr': 0.00039530148002046996, 'samples': 8982336, 'steps': 46782, 'loss/train': 0.8835437297821045} 08/30/2021 21:42:53 - INFO - __main__ - Step 46784: {'lr': 0.0003952971615899074, 'samples': 8982528, 'steps': 46783, 'loss/train': 1.8005626201629639} 08/30/2021 21:42:53 - INFO - __main__ - Step 46785: {'lr': 0.00039529284309387607, 'samples': 8982720, 'steps': 46784, 'loss/train': 0.7701586484909058} 08/30/2021 21:42:53 - INFO - __main__ - Step 46786: {'lr': 0.0003952885245323781, 'samples': 8982912, 'steps': 46785, 'loss/train': 1.129795789718628} 08/30/2021 21:42:54 - INFO - __main__ - Step 46787: {'lr': 0.00039528420590541536, 'samples': 8983104, 'steps': 46786, 'loss/train': 1.7253730297088623} 08/30/2021 21:42:54 - INFO - __main__ - Step 46788: {'lr': 0.0003952798872129897, 'samples': 8983296, 'steps': 46787, 'loss/train': 1.5704959630966187} 08/30/2021 21:42:56 - INFO - __main__ - Step 46789: {'lr': 0.00039527556845510336, 'samples': 8983488, 'steps': 46788, 'loss/train': 0.7137991786003113} 08/30/2021 21:42:56 - INFO - __main__ - Step 46790: {'lr': 0.00039527124963175796, 'samples': 8983680, 'steps': 46789, 'loss/train': 1.4640997648239136} 08/30/2021 21:42:56 - INFO - __main__ - Step 46791: {'lr': 0.0003952669307429556, 'samples': 8983872, 'steps': 46790, 'loss/train': 1.5724915266036987} 08/30/2021 21:42:57 - INFO - __main__ - Step 46792: {'lr': 0.00039526261178869816, 'samples': 8984064, 'steps': 46791, 'loss/train': 1.6930660009384155} 08/30/2021 21:42:57 - INFO - __main__ - Step 46793: {'lr': 0.0003952582927689877, 'samples': 8984256, 'steps': 46792, 'loss/train': 1.3517203330993652} 08/30/2021 21:42:59 - INFO - __main__ - Step 46794: {'lr': 0.00039525397368382604, 'samples': 8984448, 'steps': 46793, 'loss/train': 1.7242711782455444} 08/30/2021 21:42:59 - INFO - __main__ - Step 46795: {'lr': 0.0003952496545332152, 'samples': 8984640, 'steps': 46794, 'loss/train': 1.0633474588394165} 08/30/2021 21:42:59 - INFO - __main__ - Step 46796: {'lr': 0.00039524533531715714, 'samples': 8984832, 'steps': 46795, 'loss/train': 0.38748928904533386} 08/30/2021 21:43:00 - INFO - __main__ - Step 46797: {'lr': 0.00039524101603565377, 'samples': 8985024, 'steps': 46796, 'loss/train': 1.515345811843872} 08/30/2021 21:43:00 - INFO - __main__ - Step 46798: {'lr': 0.000395236696688707, 'samples': 8985216, 'steps': 46797, 'loss/train': 1.1993645429611206} 08/30/2021 21:43:02 - INFO - __main__ - Step 46799: {'lr': 0.0003952323772763188, 'samples': 8985408, 'steps': 46798, 'loss/train': 1.1981366872787476} 08/30/2021 21:43:02 - INFO - __main__ - Step 46800: {'lr': 0.00039522805779849116, 'samples': 8985600, 'steps': 46799, 'loss/train': 1.5931971073150635} 08/30/2021 21:43:02 - INFO - __main__ - Step 46801: {'lr': 0.000395223738255226, 'samples': 8985792, 'steps': 46800, 'loss/train': 1.298779010772705} 08/30/2021 21:43:03 - INFO - __main__ - Step 46802: {'lr': 0.00039521941864652525, 'samples': 8985984, 'steps': 46801, 'loss/train': 1.1574164628982544} 08/30/2021 21:43:03 - INFO - __main__ - Step 46803: {'lr': 0.0003952150989723909, 'samples': 8986176, 'steps': 46802, 'loss/train': 0.6707392334938049} 08/30/2021 21:43:04 - INFO - __main__ - Step 46804: {'lr': 0.00039521077923282486, 'samples': 8986368, 'steps': 46803, 'loss/train': 1.3017579317092896} 08/30/2021 21:43:05 - INFO - __main__ - Step 46805: {'lr': 0.00039520645942782906, 'samples': 8986560, 'steps': 46804, 'loss/train': 1.4511346817016602} 08/30/2021 21:43:05 - INFO - __main__ - Step 46806: {'lr': 0.00039520213955740555, 'samples': 8986752, 'steps': 46805, 'loss/train': 1.5111244916915894} 08/30/2021 21:43:06 - INFO - __main__ - Step 46807: {'lr': 0.0003951978196215561, 'samples': 8986944, 'steps': 46806, 'loss/train': 0.9505908489227295} 08/30/2021 21:43:06 - INFO - __main__ - Step 46808: {'lr': 0.00039519349962028276, 'samples': 8987136, 'steps': 46807, 'loss/train': 1.3132978677749634} 08/30/2021 21:43:06 - INFO - __main__ - Step 46809: {'lr': 0.0003951891795535875, 'samples': 8987328, 'steps': 46808, 'loss/train': 0.7465982437133789} 08/30/2021 21:43:08 - INFO - __main__ - Step 46810: {'lr': 0.00039518485942147233, 'samples': 8987520, 'steps': 46809, 'loss/train': 1.4024896621704102} 08/30/2021 21:43:09 - INFO - __main__ - Step 46811: {'lr': 0.0003951805392239389, 'samples': 8987712, 'steps': 46810, 'loss/train': 1.0648093223571777} 08/30/2021 21:43:09 - INFO - __main__ - Step 46812: {'lr': 0.00039517621896098954, 'samples': 8987904, 'steps': 46811, 'loss/train': 0.9817931056022644} 08/30/2021 21:43:09 - INFO - __main__ - Step 46813: {'lr': 0.00039517189863262593, 'samples': 8988096, 'steps': 46812, 'loss/train': 1.2508925199508667} 08/30/2021 21:43:10 - INFO - __main__ - Step 46814: {'lr': 0.00039516757823885006, 'samples': 8988288, 'steps': 46813, 'loss/train': 1.2731566429138184} 08/30/2021 21:43:11 - INFO - __main__ - Step 46815: {'lr': 0.000395163257779664, 'samples': 8988480, 'steps': 46814, 'loss/train': 0.9015750288963318} 08/30/2021 21:43:12 - INFO - __main__ - Step 46816: {'lr': 0.00039515893725506956, 'samples': 8988672, 'steps': 46815, 'loss/train': 1.5776115655899048} 08/30/2021 21:43:12 - INFO - __main__ - Step 46817: {'lr': 0.0003951546166650688, 'samples': 8988864, 'steps': 46816, 'loss/train': 1.4892765283584595} 08/30/2021 21:43:12 - INFO - __main__ - Step 46818: {'lr': 0.0003951502960096636, 'samples': 8989056, 'steps': 46817, 'loss/train': 1.0947678089141846} 08/30/2021 21:43:13 - INFO - __main__ - Step 46819: {'lr': 0.00039514597528885587, 'samples': 8989248, 'steps': 46818, 'loss/train': 1.752001166343689} 08/30/2021 21:43:13 - INFO - __main__ - Step 46820: {'lr': 0.0003951416545026476, 'samples': 8989440, 'steps': 46819, 'loss/train': 1.6288435459136963} 08/30/2021 21:43:15 - INFO - __main__ - Step 46821: {'lr': 0.0003951373336510408, 'samples': 8989632, 'steps': 46820, 'loss/train': 0.8195870518684387} 08/30/2021 21:43:15 - INFO - __main__ - Step 46822: {'lr': 0.00039513301273403733, 'samples': 8989824, 'steps': 46821, 'loss/train': 1.6529247760772705} 08/30/2021 21:43:15 - INFO - __main__ - Step 46823: {'lr': 0.0003951286917516392, 'samples': 8990016, 'steps': 46822, 'loss/train': 0.9636734127998352} 08/30/2021 21:43:16 - INFO - __main__ - Step 46824: {'lr': 0.00039512437070384827, 'samples': 8990208, 'steps': 46823, 'loss/train': 1.0846912860870361} 08/30/2021 21:43:16 - INFO - __main__ - Step 46825: {'lr': 0.00039512004959066653, 'samples': 8990400, 'steps': 46824, 'loss/train': 2.174528121948242} 08/30/2021 21:43:18 - INFO - __main__ - Step 46826: {'lr': 0.00039511572841209597, 'samples': 8990592, 'steps': 46825, 'loss/train': 1.1301943063735962} 08/30/2021 21:43:18 - INFO - __main__ - Step 46827: {'lr': 0.00039511140716813847, 'samples': 8990784, 'steps': 46826, 'loss/train': 1.4306621551513672} 08/30/2021 21:43:19 - INFO - __main__ - Step 46828: {'lr': 0.00039510708585879605, 'samples': 8990976, 'steps': 46827, 'loss/train': 1.274446725845337} 08/30/2021 21:43:19 - INFO - __main__ - Step 46829: {'lr': 0.00039510276448407054, 'samples': 8991168, 'steps': 46828, 'loss/train': 1.6111103296279907} 08/30/2021 21:43:19 - INFO - __main__ - Step 46830: {'lr': 0.00039509844304396407, 'samples': 8991360, 'steps': 46829, 'loss/train': 0.9941524863243103} 08/30/2021 21:43:21 - INFO - __main__ - Step 46831: {'lr': 0.00039509412153847847, 'samples': 8991552, 'steps': 46830, 'loss/train': 1.8219833374023438} 08/30/2021 21:43:22 - INFO - __main__ - Step 46832: {'lr': 0.00039508979996761564, 'samples': 8991744, 'steps': 46831, 'loss/train': 0.06311263889074326} 08/30/2021 21:43:22 - INFO - __main__ - Step 46833: {'lr': 0.00039508547833137753, 'samples': 8991936, 'steps': 46832, 'loss/train': 1.9140911102294922} 08/30/2021 21:43:22 - INFO - __main__ - Step 46834: {'lr': 0.0003950811566297662, 'samples': 8992128, 'steps': 46833, 'loss/train': 0.9637599587440491} 08/30/2021 21:43:23 - INFO - __main__ - Step 46835: {'lr': 0.00039507683486278357, 'samples': 8992320, 'steps': 46834, 'loss/train': 0.997583270072937} 08/30/2021 21:43:25 - INFO - __main__ - Step 46836: {'lr': 0.00039507251303043156, 'samples': 8992512, 'steps': 46835, 'loss/train': 1.4343088865280151} 08/30/2021 21:43:25 - INFO - __main__ - Step 46837: {'lr': 0.0003950681911327121, 'samples': 8992704, 'steps': 46836, 'loss/train': 0.8677394390106201} 08/30/2021 21:43:26 - INFO - __main__ - Step 46838: {'lr': 0.00039506386916962714, 'samples': 8992896, 'steps': 46837, 'loss/train': 1.7345106601715088} 08/30/2021 21:43:26 - INFO - __main__ - Step 46839: {'lr': 0.0003950595471411786, 'samples': 8993088, 'steps': 46838, 'loss/train': 0.7948237061500549} 08/30/2021 21:43:26 - INFO - __main__ - Step 46840: {'lr': 0.00039505522504736855, 'samples': 8993280, 'steps': 46839, 'loss/train': 1.6832594871520996} 08/30/2021 21:43:27 - INFO - __main__ - Step 46841: {'lr': 0.00039505090288819876, 'samples': 8993472, 'steps': 46840, 'loss/train': 1.6884573698043823} 08/30/2021 21:43:27 - INFO - __main__ - Step 46842: {'lr': 0.00039504658066367136, 'samples': 8993664, 'steps': 46841, 'loss/train': 1.4265028238296509} 08/30/2021 21:43:29 - INFO - __main__ - Step 46843: {'lr': 0.0003950422583737882, 'samples': 8993856, 'steps': 46842, 'loss/train': 1.5434978008270264} 08/30/2021 21:43:29 - INFO - __main__ - Step 46844: {'lr': 0.0003950379360185512, 'samples': 8994048, 'steps': 46843, 'loss/train': 0.9535610675811768} 08/30/2021 21:43:29 - INFO - __main__ - Step 46845: {'lr': 0.00039503361359796235, 'samples': 8994240, 'steps': 46844, 'loss/train': 0.6791813969612122} 08/30/2021 21:43:30 - INFO - __main__ - Step 46846: {'lr': 0.00039502929111202357, 'samples': 8994432, 'steps': 46845, 'loss/train': 1.835464358329773} 08/30/2021 21:43:30 - INFO - __main__ - Step 46847: {'lr': 0.0003950249685607369, 'samples': 8994624, 'steps': 46846, 'loss/train': 1.4448151588439941} 08/30/2021 21:43:32 - INFO - __main__ - Step 46848: {'lr': 0.00039502064594410414, 'samples': 8994816, 'steps': 46847, 'loss/train': 1.239708423614502} 08/30/2021 21:43:32 - INFO - __main__ - Step 46849: {'lr': 0.00039501632326212734, 'samples': 8995008, 'steps': 46848, 'loss/train': 1.8383761644363403} 08/30/2021 21:43:33 - INFO - __main__ - Step 46850: {'lr': 0.00039501200051480844, 'samples': 8995200, 'steps': 46849, 'loss/train': 1.7683511972427368} 08/30/2021 21:43:33 - INFO - __main__ - Step 46851: {'lr': 0.0003950076777021494, 'samples': 8995392, 'steps': 46850, 'loss/train': 1.6279022693634033} 08/30/2021 21:43:33 - INFO - __main__ - Step 46852: {'lr': 0.00039500335482415205, 'samples': 8995584, 'steps': 46851, 'loss/train': 1.3126909732818604} 08/30/2021 21:43:35 - INFO - __main__ - Step 46853: {'lr': 0.00039499903188081856, 'samples': 8995776, 'steps': 46852, 'loss/train': 1.5261602401733398} 08/30/2021 21:43:35 - INFO - __main__ - Step 46854: {'lr': 0.0003949947088721506, 'samples': 8995968, 'steps': 46853, 'loss/train': 1.5286965370178223} 08/30/2021 21:43:36 - INFO - __main__ - Step 46855: {'lr': 0.0003949903857981503, 'samples': 8996160, 'steps': 46854, 'loss/train': 1.4346762895584106} 08/30/2021 21:43:36 - INFO - __main__ - Step 46856: {'lr': 0.0003949860626588196, 'samples': 8996352, 'steps': 46855, 'loss/train': 1.3137578964233398} 08/30/2021 21:43:36 - INFO - __main__ - Step 46857: {'lr': 0.0003949817394541604, 'samples': 8996544, 'steps': 46856, 'loss/train': 1.7748647928237915} 08/30/2021 21:43:37 - INFO - __main__ - Step 46858: {'lr': 0.0003949774161841747, 'samples': 8996736, 'steps': 46857, 'loss/train': 1.0847824811935425} 08/30/2021 21:43:38 - INFO - __main__ - Step 46859: {'lr': 0.0003949730928488644, 'samples': 8996928, 'steps': 46858, 'loss/train': 1.1866612434387207} 08/30/2021 21:43:39 - INFO - __main__ - Step 46860: {'lr': 0.0003949687694482314, 'samples': 8997120, 'steps': 46859, 'loss/train': 0.5565835237503052} 08/30/2021 21:43:39 - INFO - __main__ - Step 46861: {'lr': 0.0003949644459822778, 'samples': 8997312, 'steps': 46860, 'loss/train': 1.680198073387146} 08/30/2021 21:43:40 - INFO - __main__ - Step 46862: {'lr': 0.00039496012245100536, 'samples': 8997504, 'steps': 46861, 'loss/train': 1.6474800109863281} 08/30/2021 21:43:40 - INFO - __main__ - Step 46863: {'lr': 0.0003949557988544162, 'samples': 8997696, 'steps': 46862, 'loss/train': 1.7829217910766602} 08/30/2021 21:43:40 - INFO - __main__ - Step 46864: {'lr': 0.0003949514751925122, 'samples': 8997888, 'steps': 46863, 'loss/train': 0.6775663495063782} 08/30/2021 21:43:42 - INFO - __main__ - Step 46865: {'lr': 0.00039494715146529526, 'samples': 8998080, 'steps': 46864, 'loss/train': 0.6734489798545837} 08/30/2021 21:43:42 - INFO - __main__ - Step 46866: {'lr': 0.00039494282767276736, 'samples': 8998272, 'steps': 46865, 'loss/train': 1.3911417722702026} 08/30/2021 21:43:42 - INFO - __main__ - Step 46867: {'lr': 0.0003949385038149305, 'samples': 8998464, 'steps': 46866, 'loss/train': 1.6095683574676514} 08/30/2021 21:43:43 - INFO - __main__ - Step 46868: {'lr': 0.0003949341798917866, 'samples': 8998656, 'steps': 46867, 'loss/train': 1.4861193895339966} 08/30/2021 21:43:43 - INFO - __main__ - Step 46869: {'lr': 0.00039492985590333754, 'samples': 8998848, 'steps': 46868, 'loss/train': 1.6450875997543335} 08/30/2021 21:43:45 - INFO - __main__ - Step 46870: {'lr': 0.00039492553184958533, 'samples': 8999040, 'steps': 46869, 'loss/train': 1.5479779243469238} 08/30/2021 21:43:45 - INFO - __main__ - Step 46871: {'lr': 0.00039492120773053195, 'samples': 8999232, 'steps': 46870, 'loss/train': 0.8354942202568054} 08/30/2021 21:43:46 - INFO - __main__ - Step 46872: {'lr': 0.0003949168835461793, 'samples': 8999424, 'steps': 46871, 'loss/train': 1.2415190935134888} 08/30/2021 21:43:46 - INFO - __main__ - Step 46873: {'lr': 0.0003949125592965293, 'samples': 8999616, 'steps': 46872, 'loss/train': 1.026503086090088} 08/30/2021 21:43:46 - INFO - __main__ - Step 46874: {'lr': 0.000394908234981584, 'samples': 8999808, 'steps': 46873, 'loss/train': 1.2157422304153442} 08/30/2021 21:43:48 - INFO - __main__ - Step 46875: {'lr': 0.00039490391060134525, 'samples': 9000000, 'steps': 46874, 'loss/train': 0.33740949630737305} 08/30/2021 21:43:48 - INFO - __main__ - Step 46876: {'lr': 0.000394899586155815, 'samples': 9000192, 'steps': 46875, 'loss/train': 1.6828782558441162} 08/30/2021 21:43:49 - INFO - __main__ - Step 46877: {'lr': 0.00039489526164499536, 'samples': 9000384, 'steps': 46876, 'loss/train': 1.5990478992462158} 08/30/2021 21:43:49 - INFO - __main__ - Step 46878: {'lr': 0.000394890937068888, 'samples': 9000576, 'steps': 46877, 'loss/train': 1.383968472480774} 08/30/2021 21:43:49 - INFO - __main__ - Step 46879: {'lr': 0.00039488661242749506, 'samples': 9000768, 'steps': 46878, 'loss/train': 0.0676184818148613} 08/30/2021 21:43:51 - INFO - __main__ - Step 46880: {'lr': 0.00039488228772081846, 'samples': 9000960, 'steps': 46879, 'loss/train': 1.2641034126281738} 08/30/2021 21:43:51 - INFO - __main__ - Step 46881: {'lr': 0.00039487796294886016, 'samples': 9001152, 'steps': 46880, 'loss/train': 1.5757015943527222} 08/30/2021 21:43:52 - INFO - __main__ - Step 46882: {'lr': 0.0003948736381116221, 'samples': 9001344, 'steps': 46881, 'loss/train': 0.9407084584236145} 08/30/2021 21:43:52 - INFO - __main__ - Step 46883: {'lr': 0.0003948693132091061, 'samples': 9001536, 'steps': 46882, 'loss/train': 1.3212473392486572} 08/30/2021 21:43:52 - INFO - __main__ - Step 46884: {'lr': 0.00039486498824131434, 'samples': 9001728, 'steps': 46883, 'loss/train': 0.8301441669464111} 08/30/2021 21:43:53 - INFO - __main__ - Step 46885: {'lr': 0.00039486066320824865, 'samples': 9001920, 'steps': 46884, 'loss/train': 1.3472568988800049} 08/30/2021 21:43:55 - INFO - __main__ - Step 46886: {'lr': 0.00039485633810991096, 'samples': 9002112, 'steps': 46885, 'loss/train': 1.4078797101974487} 08/30/2021 21:43:55 - INFO - __main__ - Step 46887: {'lr': 0.0003948520129463032, 'samples': 9002304, 'steps': 46886, 'loss/train': 1.7623382806777954} 08/30/2021 21:43:55 - INFO - __main__ - Step 46888: {'lr': 0.0003948476877174274, 'samples': 9002496, 'steps': 46887, 'loss/train': 1.0218671560287476} 08/30/2021 21:43:56 - INFO - __main__ - Step 46889: {'lr': 0.0003948433624232854, 'samples': 9002688, 'steps': 46888, 'loss/train': 0.778704047203064} 08/30/2021 21:43:56 - INFO - __main__ - Step 46890: {'lr': 0.0003948390370638794, 'samples': 9002880, 'steps': 46889, 'loss/train': 0.9362194538116455} 08/30/2021 21:43:58 - INFO - __main__ - Step 46891: {'lr': 0.000394834711639211, 'samples': 9003072, 'steps': 46890, 'loss/train': 1.4387551546096802} 08/30/2021 21:43:59 - INFO - __main__ - Step 46892: {'lr': 0.00039483038614928235, 'samples': 9003264, 'steps': 46891, 'loss/train': 2.5729401111602783} 08/30/2021 21:43:59 - INFO - __main__ - Step 46893: {'lr': 0.0003948260605940953, 'samples': 9003456, 'steps': 46892, 'loss/train': 2.4900550842285156} 08/30/2021 21:44:00 - INFO - __main__ - Step 46894: {'lr': 0.00039482173497365193, 'samples': 9003648, 'steps': 46893, 'loss/train': 0.16495098173618317} 08/30/2021 21:44:00 - INFO - __main__ - Step 46895: {'lr': 0.0003948174092879541, 'samples': 9003840, 'steps': 46894, 'loss/train': 1.792518973350525} 08/30/2021 21:44:00 - INFO - __main__ - Step 46896: {'lr': 0.0003948130835370038, 'samples': 9004032, 'steps': 46895, 'loss/train': 1.7676103115081787} 08/30/2021 21:44:02 - INFO - __main__ - Step 46897: {'lr': 0.000394808757720803, 'samples': 9004224, 'steps': 46896, 'loss/train': 1.2244478464126587} 08/30/2021 21:44:02 - INFO - __main__ - Step 46898: {'lr': 0.00039480443183935357, 'samples': 9004416, 'steps': 46897, 'loss/train': 1.4690419435501099} 08/30/2021 21:44:02 - INFO - __main__ - Step 46899: {'lr': 0.0003948001058926575, 'samples': 9004608, 'steps': 46898, 'loss/train': 1.1695542335510254} 08/30/2021 21:44:03 - INFO - __main__ - Step 46900: {'lr': 0.0003947957798807167, 'samples': 9004800, 'steps': 46899, 'loss/train': 1.4416167736053467} 08/30/2021 21:44:03 - INFO - __main__ - Step 46901: {'lr': 0.00039479145380353313, 'samples': 9004992, 'steps': 46900, 'loss/train': 1.119141936302185} 08/30/2021 21:44:05 - INFO - __main__ - Step 46902: {'lr': 0.0003947871276611088, 'samples': 9005184, 'steps': 46901, 'loss/train': 1.3132799863815308} 08/30/2021 21:44:05 - INFO - __main__ - Step 46903: {'lr': 0.0003947828014534457, 'samples': 9005376, 'steps': 46902, 'loss/train': 0.9954779744148254} 08/30/2021 21:44:06 - INFO - __main__ - Step 46904: {'lr': 0.00039477847518054566, 'samples': 9005568, 'steps': 46903, 'loss/train': 1.407454252243042} 08/30/2021 21:44:06 - INFO - __main__ - Step 46905: {'lr': 0.00039477414884241064, 'samples': 9005760, 'steps': 46904, 'loss/train': 1.0129156112670898} 08/30/2021 21:44:06 - INFO - __main__ - Step 46906: {'lr': 0.0003947698224390426, 'samples': 9005952, 'steps': 46905, 'loss/train': 1.088590383529663} 08/30/2021 21:44:08 - INFO - __main__ - Step 46907: {'lr': 0.0003947654959704435, 'samples': 9006144, 'steps': 46906, 'loss/train': 1.8336222171783447} 08/30/2021 21:44:08 - INFO - __main__ - Step 46908: {'lr': 0.00039476116943661544, 'samples': 9006336, 'steps': 46907, 'loss/train': 1.141404390335083} 08/30/2021 21:44:09 - INFO - __main__ - Step 46909: {'lr': 0.00039475684283756007, 'samples': 9006528, 'steps': 46908, 'loss/train': 0.9881564378738403} 08/30/2021 21:44:09 - INFO - __main__ - Step 46910: {'lr': 0.0003947525161732797, 'samples': 9006720, 'steps': 46909, 'loss/train': 1.0977205038070679} 08/30/2021 21:44:09 - INFO - __main__ - Step 46911: {'lr': 0.0003947481894437759, 'samples': 9006912, 'steps': 46910, 'loss/train': 1.8670387268066406} 08/30/2021 21:44:11 - INFO - __main__ - Step 46912: {'lr': 0.0003947438626490508, 'samples': 9007104, 'steps': 46911, 'loss/train': 1.5186539888381958} 08/30/2021 21:44:11 - INFO - __main__ - Step 46913: {'lr': 0.0003947395357891064, 'samples': 9007296, 'steps': 46912, 'loss/train': 1.1929248571395874} 08/30/2021 21:44:12 - INFO - __main__ - Step 46914: {'lr': 0.00039473520886394465, 'samples': 9007488, 'steps': 46913, 'loss/train': 1.3482972383499146} 08/30/2021 21:44:12 - INFO - __main__ - Step 46915: {'lr': 0.00039473088187356737, 'samples': 9007680, 'steps': 46914, 'loss/train': 3.0119411945343018} 08/30/2021 21:44:12 - INFO - __main__ - Step 46916: {'lr': 0.0003947265548179766, 'samples': 9007872, 'steps': 46915, 'loss/train': 1.7715628147125244} 08/30/2021 21:44:13 - INFO - __main__ - Step 46917: {'lr': 0.00039472222769717434, 'samples': 9008064, 'steps': 46916, 'loss/train': 1.0797874927520752} 08/30/2021 21:44:14 - INFO - __main__ - Step 46918: {'lr': 0.00039471790051116243, 'samples': 9008256, 'steps': 46917, 'loss/train': 1.1832444667816162} 08/30/2021 21:44:15 - INFO - __main__ - Step 46919: {'lr': 0.0003947135732599428, 'samples': 9008448, 'steps': 46918, 'loss/train': 1.14852774143219} 08/30/2021 21:44:15 - INFO - __main__ - Step 46920: {'lr': 0.0003947092459435176, 'samples': 9008640, 'steps': 46919, 'loss/train': 1.499640703201294} 08/30/2021 21:44:16 - INFO - __main__ - Step 46921: {'lr': 0.0003947049185618886, 'samples': 9008832, 'steps': 46920, 'loss/train': 1.3729298114776611} 08/30/2021 21:44:16 - INFO - __main__ - Step 46922: {'lr': 0.0003947005911150577, 'samples': 9009024, 'steps': 46921, 'loss/train': 0.9926202297210693} 08/30/2021 21:44:16 - INFO - __main__ - Step 46923: {'lr': 0.0003946962636030271, 'samples': 9009216, 'steps': 46922, 'loss/train': 1.3934400081634521} 08/30/2021 21:44:18 - INFO - __main__ - Step 46924: {'lr': 0.00039469193602579856, 'samples': 9009408, 'steps': 46923, 'loss/train': 1.8092750310897827} 08/30/2021 21:44:18 - INFO - __main__ - Step 46925: {'lr': 0.000394687608383374, 'samples': 9009600, 'steps': 46924, 'loss/train': 0.7849079966545105} 08/30/2021 21:44:19 - INFO - __main__ - Step 46926: {'lr': 0.0003946832806757554, 'samples': 9009792, 'steps': 46925, 'loss/train': 2.220301866531372} 08/30/2021 21:44:19 - INFO - __main__ - Step 46927: {'lr': 0.00039467895290294484, 'samples': 9009984, 'steps': 46926, 'loss/train': 1.5471405982971191} 08/30/2021 21:44:19 - INFO - __main__ - Step 46928: {'lr': 0.00039467462506494416, 'samples': 9010176, 'steps': 46927, 'loss/train': 1.6559935808181763} 08/30/2021 21:44:21 - INFO - __main__ - Step 46929: {'lr': 0.0003946702971617553, 'samples': 9010368, 'steps': 46928, 'loss/train': 1.1120922565460205} 08/30/2021 21:44:21 - INFO - __main__ - Step 46930: {'lr': 0.00039466596919338027, 'samples': 9010560, 'steps': 46929, 'loss/train': 1.6416133642196655} 08/30/2021 21:44:22 - INFO - __main__ - Step 46931: {'lr': 0.000394661641159821, 'samples': 9010752, 'steps': 46930, 'loss/train': 1.5514638423919678} 08/30/2021 21:44:22 - INFO - __main__ - Step 46932: {'lr': 0.00039465731306107937, 'samples': 9010944, 'steps': 46931, 'loss/train': 1.6745285987854004} 08/30/2021 21:44:22 - INFO - __main__ - Step 46933: {'lr': 0.0003946529848971574, 'samples': 9011136, 'steps': 46932, 'loss/train': 1.6818374395370483} 08/30/2021 21:44:24 - INFO - __main__ - Step 46934: {'lr': 0.00039464865666805706, 'samples': 9011328, 'steps': 46933, 'loss/train': 1.267052412033081} 08/30/2021 21:44:25 - INFO - __main__ - Step 46935: {'lr': 0.00039464432837378025, 'samples': 9011520, 'steps': 46934, 'loss/train': 1.4714409112930298} 08/30/2021 21:44:25 - INFO - __main__ - Step 46936: {'lr': 0.0003946400000143289, 'samples': 9011712, 'steps': 46935, 'loss/train': 1.5869170427322388} 08/30/2021 21:44:25 - INFO - __main__ - Step 46937: {'lr': 0.000394635671589705, 'samples': 9011904, 'steps': 46936, 'loss/train': 1.4760212898254395} 08/30/2021 21:44:26 - INFO - __main__ - Step 46938: {'lr': 0.0003946313430999106, 'samples': 9012096, 'steps': 46937, 'loss/train': 1.5378096103668213} 08/30/2021 21:44:28 - INFO - __main__ - Step 46939: {'lr': 0.0003946270145449475, 'samples': 9012288, 'steps': 46938, 'loss/train': 1.1220684051513672} 08/30/2021 21:44:28 - INFO - __main__ - Step 46940: {'lr': 0.00039462268592481767, 'samples': 9012480, 'steps': 46939, 'loss/train': 1.6197477579116821} 08/30/2021 21:44:28 - INFO - __main__ - Step 46941: {'lr': 0.00039461835723952313, 'samples': 9012672, 'steps': 46940, 'loss/train': 1.4468624591827393} 08/30/2021 21:44:29 - INFO - __main__ - Step 46942: {'lr': 0.0003946140284890657, 'samples': 9012864, 'steps': 46941, 'loss/train': 2.260392189025879} 08/30/2021 21:44:29 - INFO - __main__ - Step 46943: {'lr': 0.0003946096996734475, 'samples': 9013056, 'steps': 46942, 'loss/train': 1.5174592733383179} 08/30/2021 21:44:31 - INFO - __main__ - Step 46944: {'lr': 0.00039460537079267035, 'samples': 9013248, 'steps': 46943, 'loss/train': 1.016710638999939} 08/30/2021 21:44:32 - INFO - __main__ - Step 46945: {'lr': 0.00039460104184673627, 'samples': 9013440, 'steps': 46944, 'loss/train': 0.7979376912117004} 08/30/2021 21:44:32 - INFO - __main__ - Step 46946: {'lr': 0.00039459671283564727, 'samples': 9013632, 'steps': 46945, 'loss/train': 1.6598806381225586} 08/30/2021 21:44:32 - INFO - __main__ - Step 46947: {'lr': 0.0003945923837594051, 'samples': 9013824, 'steps': 46946, 'loss/train': 0.9393380284309387} 08/30/2021 21:44:33 - INFO - __main__ - Step 46948: {'lr': 0.0003945880546180119, 'samples': 9014016, 'steps': 46947, 'loss/train': 1.2374600172042847} 08/30/2021 21:44:33 - INFO - __main__ - Step 46949: {'lr': 0.00039458372541146955, 'samples': 9014208, 'steps': 46948, 'loss/train': 1.5660732984542847} 08/30/2021 21:44:35 - INFO - __main__ - Step 46950: {'lr': 0.00039457939613978, 'samples': 9014400, 'steps': 46949, 'loss/train': 1.7887295484542847} 08/30/2021 21:44:35 - INFO - __main__ - Step 46951: {'lr': 0.0003945750668029452, 'samples': 9014592, 'steps': 46950, 'loss/train': 1.6144603490829468} 08/30/2021 21:44:35 - INFO - __main__ - Step 46952: {'lr': 0.0003945707374009671, 'samples': 9014784, 'steps': 46951, 'loss/train': 1.471245527267456} 08/30/2021 21:44:36 - INFO - __main__ - Step 46953: {'lr': 0.0003945664079338477, 'samples': 9014976, 'steps': 46952, 'loss/train': 2.249976873397827} 08/30/2021 21:44:36 - INFO - __main__ - Step 46954: {'lr': 0.0003945620784015888, 'samples': 9015168, 'steps': 46953, 'loss/train': 1.4158796072006226} 08/30/2021 21:44:38 - INFO - __main__ - Step 46955: {'lr': 0.00039455774880419256, 'samples': 9015360, 'steps': 46954, 'loss/train': 1.712270736694336} 08/30/2021 21:44:38 - INFO - __main__ - Step 46956: {'lr': 0.00039455341914166074, 'samples': 9015552, 'steps': 46955, 'loss/train': 1.4940677881240845} 08/30/2021 21:44:38 - INFO - __main__ - Step 46957: {'lr': 0.0003945490894139955, 'samples': 9015744, 'steps': 46956, 'loss/train': 1.315157413482666} 08/30/2021 21:44:39 - INFO - __main__ - Step 46958: {'lr': 0.0003945447596211986, 'samples': 9015936, 'steps': 46957, 'loss/train': 1.2470693588256836} 08/30/2021 21:44:39 - INFO - __main__ - Step 46959: {'lr': 0.0003945404297632721, 'samples': 9016128, 'steps': 46958, 'loss/train': 1.544315218925476} 08/30/2021 21:44:41 - INFO - __main__ - Step 46960: {'lr': 0.00039453609984021787, 'samples': 9016320, 'steps': 46959, 'loss/train': 1.6414031982421875} 08/30/2021 21:44:41 - INFO - __main__ - Step 46961: {'lr': 0.00039453176985203785, 'samples': 9016512, 'steps': 46960, 'loss/train': 1.4637598991394043} 08/30/2021 21:44:41 - INFO - __main__ - Step 46962: {'lr': 0.0003945274397987342, 'samples': 9016704, 'steps': 46961, 'loss/train': 1.4995415210723877} 08/30/2021 21:44:42 - INFO - __main__ - Step 46963: {'lr': 0.0003945231096803086, 'samples': 9016896, 'steps': 46962, 'loss/train': 0.4901764988899231} 08/30/2021 21:44:42 - INFO - __main__ - Step 46964: {'lr': 0.0003945187794967632, 'samples': 9017088, 'steps': 46963, 'loss/train': 1.1779558658599854} 08/30/2021 21:44:43 - INFO - __main__ - Step 46965: {'lr': 0.00039451444924809976, 'samples': 9017280, 'steps': 46964, 'loss/train': 1.3195405006408691} 08/30/2021 21:44:44 - INFO - __main__ - Step 46966: {'lr': 0.0003945101189343204, 'samples': 9017472, 'steps': 46965, 'loss/train': 0.8720847964286804} 08/30/2021 21:44:44 - INFO - __main__ - Step 46967: {'lr': 0.000394505788555427, 'samples': 9017664, 'steps': 46966, 'loss/train': 1.677130103111267} 08/30/2021 21:44:45 - INFO - __main__ - Step 46968: {'lr': 0.0003945014581114215, 'samples': 9017856, 'steps': 46967, 'loss/train': 1.6841708421707153} 08/30/2021 21:44:45 - INFO - __main__ - Step 46969: {'lr': 0.00039449712760230584, 'samples': 9018048, 'steps': 46968, 'loss/train': 1.2529847621917725} 08/30/2021 21:44:47 - INFO - __main__ - Step 46970: {'lr': 0.0003944927970280821, 'samples': 9018240, 'steps': 46969, 'loss/train': 1.7225449085235596} 08/30/2021 21:44:47 - INFO - __main__ - Step 46971: {'lr': 0.00039448846638875213, 'samples': 9018432, 'steps': 46970, 'loss/train': 1.5357646942138672} 08/30/2021 21:44:47 - INFO - __main__ - Step 46972: {'lr': 0.00039448413568431785, 'samples': 9018624, 'steps': 46971, 'loss/train': 1.1177994012832642} 08/30/2021 21:44:48 - INFO - __main__ - Step 46973: {'lr': 0.0003944798049147812, 'samples': 9018816, 'steps': 46972, 'loss/train': 1.3170790672302246} 08/30/2021 21:44:48 - INFO - __main__ - Step 46974: {'lr': 0.00039447547408014426, 'samples': 9019008, 'steps': 46973, 'loss/train': 1.2802783250808716} 08/30/2021 21:44:48 - INFO - __main__ - Step 46975: {'lr': 0.00039447114318040885, 'samples': 9019200, 'steps': 46974, 'loss/train': 1.9557400941848755} 08/30/2021 21:44:50 - INFO - __main__ - Step 46976: {'lr': 0.000394466812215577, 'samples': 9019392, 'steps': 46975, 'loss/train': 2.048022985458374} 08/30/2021 21:44:50 - INFO - __main__ - Step 46977: {'lr': 0.0003944624811856506, 'samples': 9019584, 'steps': 46976, 'loss/train': 1.5928115844726562} 08/30/2021 21:44:51 - INFO - __main__ - Step 46978: {'lr': 0.0003944581500906317, 'samples': 9019776, 'steps': 46977, 'loss/train': 1.9153282642364502} 08/30/2021 21:44:51 - INFO - __main__ - Step 46979: {'lr': 0.00039445381893052215, 'samples': 9019968, 'steps': 46978, 'loss/train': 3.6052839756011963} 08/30/2021 21:44:51 - INFO - __main__ - Step 46980: {'lr': 0.0003944494877053239, 'samples': 9020160, 'steps': 46979, 'loss/train': 1.5440027713775635} 08/30/2021 21:44:53 - INFO - __main__ - Step 46981: {'lr': 0.00039444515641503896, 'samples': 9020352, 'steps': 46980, 'loss/train': 1.8482164144515991} 08/30/2021 21:44:53 - INFO - __main__ - Step 46982: {'lr': 0.00039444082505966926, 'samples': 9020544, 'steps': 46981, 'loss/train': 1.3363295793533325} 08/30/2021 21:44:54 - INFO - __main__ - Step 46983: {'lr': 0.0003944364936392168, 'samples': 9020736, 'steps': 46982, 'loss/train': 1.784623384475708} 08/30/2021 21:44:54 - INFO - __main__ - Step 46984: {'lr': 0.0003944321621536835, 'samples': 9020928, 'steps': 46983, 'loss/train': 1.76750910282135} 08/30/2021 21:44:54 - INFO - __main__ - Step 46985: {'lr': 0.00039442783060307117, 'samples': 9021120, 'steps': 46984, 'loss/train': 1.5290135145187378} 08/30/2021 21:44:55 - INFO - __main__ - Step 46986: {'lr': 0.00039442349898738204, 'samples': 9021312, 'steps': 46985, 'loss/train': 1.8976329565048218} 08/30/2021 21:44:56 - INFO - __main__ - Step 46987: {'lr': 0.0003944191673066178, 'samples': 9021504, 'steps': 46986, 'loss/train': 1.7026069164276123} 08/30/2021 21:44:57 - INFO - __main__ - Step 46988: {'lr': 0.00039441483556078055, 'samples': 9021696, 'steps': 46987, 'loss/train': 1.8321424722671509} 08/30/2021 21:44:57 - INFO - __main__ - Step 46989: {'lr': 0.0003944105037498722, 'samples': 9021888, 'steps': 46988, 'loss/train': 0.8016990423202515} 08/30/2021 21:44:57 - INFO - __main__ - Step 46990: {'lr': 0.0003944061718738947, 'samples': 9022080, 'steps': 46989, 'loss/train': 1.5196932554244995} 08/30/2021 21:44:58 - INFO - __main__ - Step 46991: {'lr': 0.00039440183993285006, 'samples': 9022272, 'steps': 46990, 'loss/train': 1.5645670890808105} 08/30/2021 21:44:59 - INFO - __main__ - Step 46992: {'lr': 0.0003943975079267401, 'samples': 9022464, 'steps': 46991, 'loss/train': 1.1234192848205566} 08/30/2021 21:45:00 - INFO - __main__ - Step 46993: {'lr': 0.0003943931758555669, 'samples': 9022656, 'steps': 46992, 'loss/train': 0.9302326440811157} 08/30/2021 21:45:00 - INFO - __main__ - Step 46994: {'lr': 0.0003943888437193324, 'samples': 9022848, 'steps': 46993, 'loss/train': 1.0642530918121338} 08/30/2021 21:45:01 - INFO - __main__ - Step 46995: {'lr': 0.00039438451151803844, 'samples': 9023040, 'steps': 46994, 'loss/train': 1.7438215017318726} 08/30/2021 21:45:01 - INFO - __main__ - Step 46996: {'lr': 0.000394380179251687, 'samples': 9023232, 'steps': 46995, 'loss/train': 2.1431987285614014} 08/30/2021 21:45:03 - INFO - __main__ - Step 46997: {'lr': 0.0003943758469202802, 'samples': 9023424, 'steps': 46996, 'loss/train': 1.2174314260482788} 08/30/2021 21:45:03 - INFO - __main__ - Step 46998: {'lr': 0.0003943715145238198, 'samples': 9023616, 'steps': 46997, 'loss/train': 1.0514683723449707} 08/30/2021 21:45:04 - INFO - __main__ - Step 46999: {'lr': 0.00039436718206230795, 'samples': 9023808, 'steps': 46998, 'loss/train': 1.1923924684524536} 08/30/2021 21:45:04 - INFO - __main__ - Step 47000: {'lr': 0.0003943628495357463, 'samples': 9024000, 'steps': 46999, 'loss/train': 0.7480464577674866} 08/30/2021 21:45:04 - INFO - __main__ - Step 47001: {'lr': 0.00039435851694413705, 'samples': 9024192, 'steps': 47000, 'loss/train': 1.3538702726364136} 08/30/2021 21:45:06 - INFO - __main__ - Step 47002: {'lr': 0.00039435418428748206, 'samples': 9024384, 'steps': 47001, 'loss/train': 1.1366056203842163} 08/30/2021 21:45:06 - INFO - __main__ - Step 47003: {'lr': 0.00039434985156578333, 'samples': 9024576, 'steps': 47002, 'loss/train': 1.3417569398880005} 08/30/2021 21:45:07 - INFO - __main__ - Step 47004: {'lr': 0.0003943455187790428, 'samples': 9024768, 'steps': 47003, 'loss/train': 1.371974229812622} 08/30/2021 21:45:07 - INFO - __main__ - Step 47005: {'lr': 0.0003943411859272624, 'samples': 9024960, 'steps': 47004, 'loss/train': 1.052565574645996} 08/30/2021 21:45:07 - INFO - __main__ - Step 47006: {'lr': 0.0003943368530104441, 'samples': 9025152, 'steps': 47005, 'loss/train': 1.609918475151062} 08/30/2021 21:45:09 - INFO - __main__ - Step 47007: {'lr': 0.00039433252002858975, 'samples': 9025344, 'steps': 47006, 'loss/train': 1.7140456438064575} 08/30/2021 21:45:09 - INFO - __main__ - Step 47008: {'lr': 0.0003943281869817015, 'samples': 9025536, 'steps': 47007, 'loss/train': 1.5079469680786133} 08/30/2021 21:45:10 - INFO - __main__ - Step 47009: {'lr': 0.0003943238538697811, 'samples': 9025728, 'steps': 47008, 'loss/train': 1.6488761901855469} 08/30/2021 21:45:10 - INFO - __main__ - Step 47010: {'lr': 0.00039431952069283067, 'samples': 9025920, 'steps': 47009, 'loss/train': 1.4270639419555664} 08/30/2021 21:45:10 - INFO - __main__ - Step 47011: {'lr': 0.00039431518745085205, 'samples': 9026112, 'steps': 47010, 'loss/train': 1.5178182125091553} 08/30/2021 21:45:11 - INFO - __main__ - Step 47012: {'lr': 0.00039431085414384727, 'samples': 9026304, 'steps': 47011, 'loss/train': 0.6716890335083008} 08/30/2021 21:45:13 - INFO - __main__ - Step 47013: {'lr': 0.0003943065207718182, 'samples': 9026496, 'steps': 47012, 'loss/train': 1.6696041822433472} 08/30/2021 21:45:13 - INFO - __main__ - Step 47014: {'lr': 0.0003943021873347669, 'samples': 9026688, 'steps': 47013, 'loss/train': 1.5473829507827759} 08/30/2021 21:45:13 - INFO - __main__ - Step 47015: {'lr': 0.00039429785383269524, 'samples': 9026880, 'steps': 47014, 'loss/train': 2.9138872623443604} 08/30/2021 21:45:14 - INFO - __main__ - Step 47016: {'lr': 0.00039429352026560516, 'samples': 9027072, 'steps': 47015, 'loss/train': 1.1713416576385498} 08/30/2021 21:45:14 - INFO - __main__ - Step 47017: {'lr': 0.0003942891866334987, 'samples': 9027264, 'steps': 47016, 'loss/train': 1.0460469722747803} 08/30/2021 21:45:16 - INFO - __main__ - Step 47018: {'lr': 0.00039428485293637773, 'samples': 9027456, 'steps': 47017, 'loss/train': 1.8020797967910767} 08/30/2021 21:45:16 - INFO - __main__ - Step 47019: {'lr': 0.00039428051917424423, 'samples': 9027648, 'steps': 47018, 'loss/train': 1.086907982826233} 08/30/2021 21:45:17 - INFO - __main__ - Step 47020: {'lr': 0.0003942761853471002, 'samples': 9027840, 'steps': 47019, 'loss/train': 1.6968697309494019} 08/30/2021 21:45:17 - INFO - __main__ - Step 47021: {'lr': 0.0003942718514549475, 'samples': 9028032, 'steps': 47020, 'loss/train': 1.5713204145431519} 08/30/2021 21:45:17 - INFO - __main__ - Step 47022: {'lr': 0.0003942675174977881, 'samples': 9028224, 'steps': 47021, 'loss/train': 1.4160035848617554} 08/30/2021 21:45:19 - INFO - __main__ - Step 47023: {'lr': 0.000394263183475624, 'samples': 9028416, 'steps': 47022, 'loss/train': 0.7884634733200073} 08/30/2021 21:45:20 - INFO - __main__ - Step 47024: {'lr': 0.0003942588493884571, 'samples': 9028608, 'steps': 47023, 'loss/train': 1.5771461725234985} 08/30/2021 21:45:20 - INFO - __main__ - Step 47025: {'lr': 0.00039425451523628953, 'samples': 9028800, 'steps': 47024, 'loss/train': 1.2272441387176514} 08/30/2021 21:45:20 - INFO - __main__ - Step 47026: {'lr': 0.00039425018101912305, 'samples': 9028992, 'steps': 47025, 'loss/train': 1.5435431003570557} 08/30/2021 21:45:21 - INFO - __main__ - Step 47027: {'lr': 0.00039424584673695956, 'samples': 9029184, 'steps': 47026, 'loss/train': 1.3484901189804077} 08/30/2021 21:45:21 - INFO - __main__ - Step 47028: {'lr': 0.0003942415123898012, 'samples': 9029376, 'steps': 47027, 'loss/train': 0.33479100465774536} 08/30/2021 21:45:23 - INFO - __main__ - Step 47029: {'lr': 0.0003942371779776498, 'samples': 9029568, 'steps': 47028, 'loss/train': 1.252678632736206} 08/30/2021 21:45:23 - INFO - __main__ - Step 47030: {'lr': 0.00039423284350050735, 'samples': 9029760, 'steps': 47029, 'loss/train': 1.354400873184204} 08/30/2021 21:45:24 - INFO - __main__ - Step 47031: {'lr': 0.0003942285089583759, 'samples': 9029952, 'steps': 47030, 'loss/train': 1.5203813314437866} 08/30/2021 21:45:24 - INFO - __main__ - Step 47032: {'lr': 0.0003942241743512572, 'samples': 9030144, 'steps': 47031, 'loss/train': 1.0415359735488892} 08/30/2021 21:45:24 - INFO - __main__ - Step 47033: {'lr': 0.00039421983967915337, 'samples': 9030336, 'steps': 47032, 'loss/train': 1.2102928161621094} 08/30/2021 21:45:26 - INFO - __main__ - Step 47034: {'lr': 0.00039421550494206625, 'samples': 9030528, 'steps': 47033, 'loss/train': 0.6218977570533752} 08/30/2021 21:45:26 - INFO - __main__ - Step 47035: {'lr': 0.0003942111701399979, 'samples': 9030720, 'steps': 47034, 'loss/train': 1.8368933200836182} 08/30/2021 21:45:27 - INFO - __main__ - Step 47036: {'lr': 0.0003942068352729502, 'samples': 9030912, 'steps': 47035, 'loss/train': 1.4152131080627441} 08/30/2021 21:45:27 - INFO - __main__ - Step 47037: {'lr': 0.0003942025003409252, 'samples': 9031104, 'steps': 47036, 'loss/train': 1.9444457292556763} 08/30/2021 21:45:28 - INFO - __main__ - Step 47038: {'lr': 0.0003941981653439247, 'samples': 9031296, 'steps': 47037, 'loss/train': 1.0517847537994385} 08/30/2021 21:45:29 - INFO - __main__ - Step 47039: {'lr': 0.00039419383028195076, 'samples': 9031488, 'steps': 47038, 'loss/train': 1.2911107540130615} 08/30/2021 21:45:30 - INFO - __main__ - Step 47040: {'lr': 0.00039418949515500524, 'samples': 9031680, 'steps': 47039, 'loss/train': 1.6040315628051758} 08/30/2021 21:45:30 - INFO - __main__ - Step 47041: {'lr': 0.0003941851599630902, 'samples': 9031872, 'steps': 47040, 'loss/train': 1.6276823282241821} 08/30/2021 21:45:30 - INFO - __main__ - Step 47042: {'lr': 0.00039418082470620756, 'samples': 9032064, 'steps': 47041, 'loss/train': 0.8975918889045715} 08/30/2021 21:45:31 - INFO - __main__ - Step 47043: {'lr': 0.0003941764893843593, 'samples': 9032256, 'steps': 47042, 'loss/train': 1.4319145679473877} 08/30/2021 21:45:32 - INFO - __main__ - Step 47044: {'lr': 0.0003941721539975473, 'samples': 9032448, 'steps': 47043, 'loss/train': 1.940021276473999} 08/30/2021 21:45:33 - INFO - __main__ - Step 47045: {'lr': 0.0003941678185457736, 'samples': 9032640, 'steps': 47044, 'loss/train': 1.6918425559997559} 08/30/2021 21:45:33 - INFO - __main__ - Step 47046: {'lr': 0.00039416348302904005, 'samples': 9032832, 'steps': 47045, 'loss/train': 1.6045674085617065} 08/30/2021 21:45:34 - INFO - __main__ - Step 47047: {'lr': 0.0003941591474473487, 'samples': 9033024, 'steps': 47046, 'loss/train': 1.2545980215072632} 08/30/2021 21:45:34 - INFO - __main__ - Step 47048: {'lr': 0.0003941548118007014, 'samples': 9033216, 'steps': 47047, 'loss/train': 0.8215344548225403} 08/30/2021 21:45:36 - INFO - __main__ - Step 47049: {'lr': 0.00039415047608910023, 'samples': 9033408, 'steps': 47048, 'loss/train': 0.1027296856045723} 08/30/2021 21:45:36 - INFO - __main__ - Step 47050: {'lr': 0.000394146140312547, 'samples': 9033600, 'steps': 47049, 'loss/train': 0.8259753584861755} 08/30/2021 21:45:37 - INFO - __main__ - Step 47051: {'lr': 0.0003941418044710438, 'samples': 9033792, 'steps': 47050, 'loss/train': 1.8476759195327759} 08/30/2021 21:45:37 - INFO - __main__ - Step 47052: {'lr': 0.00039413746856459253, 'samples': 9033984, 'steps': 47051, 'loss/train': 1.7540653944015503} 08/30/2021 21:45:37 - INFO - __main__ - Step 47053: {'lr': 0.0003941331325931952, 'samples': 9034176, 'steps': 47052, 'loss/train': 1.3884731531143188} 08/30/2021 21:45:38 - INFO - __main__ - Step 47054: {'lr': 0.0003941287965568536, 'samples': 9034368, 'steps': 47053, 'loss/train': 0.5963377952575684} 08/30/2021 21:45:39 - INFO - __main__ - Step 47055: {'lr': 0.0003941244604555698, 'samples': 9034560, 'steps': 47054, 'loss/train': 1.5608035326004028} 08/30/2021 21:45:39 - INFO - __main__ - Step 47056: {'lr': 0.0003941201242893457, 'samples': 9034752, 'steps': 47055, 'loss/train': 0.8580886721611023} 08/30/2021 21:45:40 - INFO - __main__ - Step 47057: {'lr': 0.00039411578805818344, 'samples': 9034944, 'steps': 47056, 'loss/train': 1.5278757810592651} 08/30/2021 21:45:40 - INFO - __main__ - Step 47058: {'lr': 0.00039411145176208477, 'samples': 9035136, 'steps': 47057, 'loss/train': 1.5152755975723267} 08/30/2021 21:45:41 - INFO - __main__ - Step 47059: {'lr': 0.0003941071154010517, 'samples': 9035328, 'steps': 47058, 'loss/train': 1.2857751846313477} 08/30/2021 21:45:42 - INFO - __main__ - Step 47060: {'lr': 0.00039410277897508617, 'samples': 9035520, 'steps': 47059, 'loss/train': 1.3531262874603271} 08/30/2021 21:45:43 - INFO - __main__ - Step 47061: {'lr': 0.00039409844248419014, 'samples': 9035712, 'steps': 47060, 'loss/train': 1.585766315460205} 08/30/2021 21:45:43 - INFO - __main__ - Step 47062: {'lr': 0.0003940941059283656, 'samples': 9035904, 'steps': 47061, 'loss/train': 1.4567688703536987} 08/30/2021 21:45:43 - INFO - __main__ - Step 47063: {'lr': 0.00039408976930761444, 'samples': 9036096, 'steps': 47062, 'loss/train': 1.182168960571289} 08/30/2021 21:45:44 - INFO - __main__ - Step 47064: {'lr': 0.00039408543262193867, 'samples': 9036288, 'steps': 47063, 'loss/train': 1.4591920375823975} 08/30/2021 21:45:45 - INFO - __main__ - Step 47065: {'lr': 0.00039408109587134034, 'samples': 9036480, 'steps': 47064, 'loss/train': 1.959205985069275} 08/30/2021 21:45:46 - INFO - __main__ - Step 47066: {'lr': 0.00039407675905582117, 'samples': 9036672, 'steps': 47065, 'loss/train': 1.7146639823913574} 08/30/2021 21:45:46 - INFO - __main__ - Step 47067: {'lr': 0.00039407242217538317, 'samples': 9036864, 'steps': 47066, 'loss/train': 1.0863569974899292} 08/30/2021 21:45:46 - INFO - __main__ - Step 47068: {'lr': 0.0003940680852300285, 'samples': 9037056, 'steps': 47067, 'loss/train': 1.4741212129592896} 08/30/2021 21:45:47 - INFO - __main__ - Step 47069: {'lr': 0.00039406374821975893, 'samples': 9037248, 'steps': 47068, 'loss/train': 1.7408515214920044} 08/30/2021 21:45:48 - INFO - __main__ - Step 47070: {'lr': 0.00039405941114457644, 'samples': 9037440, 'steps': 47069, 'loss/train': 1.5101934671401978} 08/30/2021 21:45:49 - INFO - __main__ - Step 47071: {'lr': 0.000394055074004483, 'samples': 9037632, 'steps': 47070, 'loss/train': 1.4572372436523438} 08/30/2021 21:45:49 - INFO - __main__ - Step 47072: {'lr': 0.0003940507367994806, 'samples': 9037824, 'steps': 47071, 'loss/train': 1.3657548427581787} 08/30/2021 21:45:50 - INFO - __main__ - Step 47073: {'lr': 0.00039404639952957116, 'samples': 9038016, 'steps': 47072, 'loss/train': 0.06788039952516556} 08/30/2021 21:45:50 - INFO - __main__ - Step 47074: {'lr': 0.00039404206219475655, 'samples': 9038208, 'steps': 47073, 'loss/train': 0.8680133819580078} 08/30/2021 21:45:50 - INFO - __main__ - Step 47075: {'lr': 0.00039403772479503895, 'samples': 9038400, 'steps': 47074, 'loss/train': 1.4910752773284912} 08/30/2021 21:45:52 - INFO - __main__ - Step 47076: {'lr': 0.0003940333873304201, 'samples': 9038592, 'steps': 47075, 'loss/train': 4.312713623046875} 08/30/2021 21:45:52 - INFO - __main__ - Step 47077: {'lr': 0.000394029049800902, 'samples': 9038784, 'steps': 47076, 'loss/train': 1.2238141298294067} 08/30/2021 21:45:53 - INFO - __main__ - Step 47078: {'lr': 0.00039402471220648675, 'samples': 9038976, 'steps': 47077, 'loss/train': 1.933716893196106} 08/30/2021 21:45:53 - INFO - __main__ - Step 47079: {'lr': 0.000394020374547176, 'samples': 9039168, 'steps': 47078, 'loss/train': 1.262068748474121} 08/30/2021 21:45:53 - INFO - __main__ - Step 47080: {'lr': 0.00039401603682297204, 'samples': 9039360, 'steps': 47079, 'loss/train': 1.51416015625} 08/30/2021 21:45:55 - INFO - __main__ - Step 47081: {'lr': 0.0003940116990338766, 'samples': 9039552, 'steps': 47080, 'loss/train': 2.1935997009277344} 08/30/2021 21:45:56 - INFO - __main__ - Step 47082: {'lr': 0.00039400736117989175, 'samples': 9039744, 'steps': 47081, 'loss/train': 1.6061735153198242} 08/30/2021 21:45:56 - INFO - __main__ - Step 47083: {'lr': 0.0003940030232610194, 'samples': 9039936, 'steps': 47082, 'loss/train': 1.4907827377319336} 08/30/2021 21:45:57 - INFO - __main__ - Step 47084: {'lr': 0.0003939986852772615, 'samples': 9040128, 'steps': 47083, 'loss/train': 1.3143213987350464} 08/30/2021 21:45:57 - INFO - __main__ - Step 47085: {'lr': 0.00039399434722862004, 'samples': 9040320, 'steps': 47084, 'loss/train': 1.3996050357818604} 08/30/2021 21:45:59 - INFO - __main__ - Step 47086: {'lr': 0.00039399000911509685, 'samples': 9040512, 'steps': 47085, 'loss/train': 1.675197958946228} 08/30/2021 21:45:59 - INFO - __main__ - Step 47087: {'lr': 0.00039398567093669413, 'samples': 9040704, 'steps': 47086, 'loss/train': 1.6289172172546387} 08/30/2021 21:46:00 - INFO - __main__ - Step 47088: {'lr': 0.00039398133269341357, 'samples': 9040896, 'steps': 47087, 'loss/train': 0.8133636116981506} 08/30/2021 21:46:00 - INFO - __main__ - Step 47089: {'lr': 0.0003939769943852573, 'samples': 9041088, 'steps': 47088, 'loss/train': 0.26620832085609436} 08/30/2021 21:46:00 - INFO - __main__ - Step 47090: {'lr': 0.0003939726560122272, 'samples': 9041280, 'steps': 47089, 'loss/train': 1.7133350372314453} 08/30/2021 21:46:01 - INFO - __main__ - Step 47091: {'lr': 0.00039396831757432526, 'samples': 9041472, 'steps': 47090, 'loss/train': 2.0110116004943848} 08/30/2021 21:46:02 - INFO - __main__ - Step 47092: {'lr': 0.0003939639790715535, 'samples': 9041664, 'steps': 47091, 'loss/train': 1.6223446130752563} 08/30/2021 21:46:03 - INFO - __main__ - Step 47093: {'lr': 0.0003939596405039136, 'samples': 9041856, 'steps': 47092, 'loss/train': 1.348044514656067} 08/30/2021 21:46:03 - INFO - __main__ - Step 47094: {'lr': 0.00039395530187140784, 'samples': 9042048, 'steps': 47093, 'loss/train': 1.1098629236221313} 08/30/2021 21:46:03 - INFO - __main__ - Step 47095: {'lr': 0.000393950963174038, 'samples': 9042240, 'steps': 47094, 'loss/train': 0.1541656106710434} 08/30/2021 21:46:05 - INFO - __main__ - Step 47096: {'lr': 0.00039394662441180606, 'samples': 9042432, 'steps': 47095, 'loss/train': 1.5069993734359741} 08/30/2021 21:46:05 - INFO - __main__ - Step 47097: {'lr': 0.000393942285584714, 'samples': 9042624, 'steps': 47096, 'loss/train': 1.5107636451721191} 08/30/2021 21:46:06 - INFO - __main__ - Step 47098: {'lr': 0.00039393794669276386, 'samples': 9042816, 'steps': 47097, 'loss/train': 1.9983701705932617} 08/30/2021 21:46:06 - INFO - __main__ - Step 47099: {'lr': 0.00039393360773595744, 'samples': 9043008, 'steps': 47098, 'loss/train': 0.9121749401092529} 08/30/2021 21:46:06 - INFO - __main__ - Step 47100: {'lr': 0.0003939292687142967, 'samples': 9043200, 'steps': 47099, 'loss/train': 1.341982126235962} 08/30/2021 21:46:08 - INFO - __main__ - Step 47101: {'lr': 0.0003939249296277837, 'samples': 9043392, 'steps': 47100, 'loss/train': 1.7498527765274048} 08/30/2021 21:46:08 - INFO - __main__ - Step 47102: {'lr': 0.0003939205904764204, 'samples': 9043584, 'steps': 47101, 'loss/train': 0.6947213411331177} 08/30/2021 21:46:09 - INFO - __main__ - Step 47103: {'lr': 0.00039391625126020856, 'samples': 9043776, 'steps': 47102, 'loss/train': 1.2254722118377686} 08/30/2021 21:46:09 - INFO - __main__ - Step 47104: {'lr': 0.0003939119119791504, 'samples': 9043968, 'steps': 47103, 'loss/train': 1.9305309057235718} 08/30/2021 21:46:09 - INFO - __main__ - Step 47105: {'lr': 0.0003939075726332477, 'samples': 9044160, 'steps': 47104, 'loss/train': 1.6418644189834595} 08/30/2021 21:46:10 - INFO - __main__ - Step 47106: {'lr': 0.00039390323322250253, 'samples': 9044352, 'steps': 47105, 'loss/train': 0.999724805355072} 08/30/2021 21:46:11 - INFO - __main__ - Step 47107: {'lr': 0.0003938988937469168, 'samples': 9044544, 'steps': 47106, 'loss/train': 1.5427132844924927} 08/30/2021 21:46:12 - INFO - __main__ - Step 47108: {'lr': 0.0003938945542064923, 'samples': 9044736, 'steps': 47107, 'loss/train': 1.400425672531128} 08/30/2021 21:46:12 - INFO - __main__ - Step 47109: {'lr': 0.00039389021460123125, 'samples': 9044928, 'steps': 47108, 'loss/train': 1.135919213294983} 08/30/2021 21:46:12 - INFO - __main__ - Step 47110: {'lr': 0.0003938858749311355, 'samples': 9045120, 'steps': 47109, 'loss/train': 1.2661519050598145} 08/30/2021 21:46:13 - INFO - __main__ - Step 47111: {'lr': 0.00039388153519620696, 'samples': 9045312, 'steps': 47110, 'loss/train': 0.6855300664901733} 08/30/2021 21:46:14 - INFO - __main__ - Step 47112: {'lr': 0.0003938771953964476, 'samples': 9045504, 'steps': 47111, 'loss/train': 1.3073887825012207} 08/30/2021 21:46:15 - INFO - __main__ - Step 47113: {'lr': 0.0003938728555318594, 'samples': 9045696, 'steps': 47112, 'loss/train': 1.8746938705444336} 08/30/2021 21:46:15 - INFO - __main__ - Step 47114: {'lr': 0.00039386851560244433, 'samples': 9045888, 'steps': 47113, 'loss/train': 1.8838722705841064} 08/30/2021 21:46:15 - INFO - __main__ - Step 47115: {'lr': 0.0003938641756082043, 'samples': 9046080, 'steps': 47114, 'loss/train': 1.3469740152359009} 08/30/2021 21:46:16 - INFO - __main__ - Step 47116: {'lr': 0.00039385983554914136, 'samples': 9046272, 'steps': 47115, 'loss/train': 1.5194928646087646} 08/30/2021 21:46:17 - INFO - __main__ - Step 47117: {'lr': 0.0003938554954252573, 'samples': 9046464, 'steps': 47116, 'loss/train': 1.3795456886291504} 08/30/2021 21:46:18 - INFO - __main__ - Step 47118: {'lr': 0.00039385115523655426, 'samples': 9046656, 'steps': 47117, 'loss/train': 2.304798126220703} 08/30/2021 21:46:18 - INFO - __main__ - Step 47119: {'lr': 0.00039384681498303407, 'samples': 9046848, 'steps': 47118, 'loss/train': 5.85479211807251} 08/30/2021 21:46:19 - INFO - __main__ - Step 47120: {'lr': 0.0003938424746646988, 'samples': 9047040, 'steps': 47119, 'loss/train': 0.5144325494766235} 08/30/2021 21:46:19 - INFO - __main__ - Step 47121: {'lr': 0.00039383813428155027, 'samples': 9047232, 'steps': 47120, 'loss/train': 1.1317442655563354} 08/30/2021 21:46:19 - INFO - __main__ - Step 47122: {'lr': 0.0003938337938335904, 'samples': 9047424, 'steps': 47121, 'loss/train': 2.2960336208343506} 08/30/2021 21:46:21 - INFO - __main__ - Step 47123: {'lr': 0.00039382945332082136, 'samples': 9047616, 'steps': 47122, 'loss/train': 1.7264989614486694} 08/30/2021 21:46:21 - INFO - __main__ - Step 47124: {'lr': 0.00039382511274324496, 'samples': 9047808, 'steps': 47123, 'loss/train': 1.1836076974868774} 08/30/2021 21:46:22 - INFO - __main__ - Step 47125: {'lr': 0.0003938207721008632, 'samples': 9048000, 'steps': 47124, 'loss/train': 0.16168496012687683} 08/30/2021 21:46:22 - INFO - __main__ - Step 47126: {'lr': 0.00039381643139367806, 'samples': 9048192, 'steps': 47125, 'loss/train': 2.9365546703338623} 08/30/2021 21:46:22 - INFO - __main__ - Step 47127: {'lr': 0.00039381209062169136, 'samples': 9048384, 'steps': 47126, 'loss/train': 1.4645624160766602} 08/30/2021 21:46:23 - INFO - __main__ - Step 47128: {'lr': 0.0003938077497849052, 'samples': 9048576, 'steps': 47127, 'loss/train': 1.6827888488769531} 08/30/2021 21:46:25 - INFO - __main__ - Step 47129: {'lr': 0.00039380340888332143, 'samples': 9048768, 'steps': 47128, 'loss/train': 2.3274762630462646} 08/30/2021 21:46:25 - INFO - __main__ - Step 47130: {'lr': 0.0003937990679169421, 'samples': 9048960, 'steps': 47129, 'loss/train': 1.2184545993804932} 08/30/2021 21:46:26 - INFO - __main__ - Step 47131: {'lr': 0.0003937947268857692, 'samples': 9049152, 'steps': 47130, 'loss/train': 0.9901658296585083} 08/30/2021 21:46:26 - INFO - __main__ - Step 47132: {'lr': 0.00039379038578980454, 'samples': 9049344, 'steps': 47131, 'loss/train': 0.043276507407426834} 08/30/2021 21:46:26 - INFO - __main__ - Step 47133: {'lr': 0.0003937860446290502, 'samples': 9049536, 'steps': 47132, 'loss/train': 1.4290553331375122} 08/30/2021 21:46:27 - INFO - __main__ - Step 47134: {'lr': 0.0003937817034035081, 'samples': 9049728, 'steps': 47133, 'loss/train': 1.8684417009353638} 08/30/2021 21:46:27 - INFO - __main__ - Step 47135: {'lr': 0.00039377736211318004, 'samples': 9049920, 'steps': 47134, 'loss/train': 0.2874923348426819} 08/30/2021 21:46:29 - INFO - __main__ - Step 47136: {'lr': 0.0003937730207580682, 'samples': 9050112, 'steps': 47135, 'loss/train': 0.13769075274467468} 08/30/2021 21:46:30 - INFO - __main__ - Step 47137: {'lr': 0.0003937686793381745, 'samples': 9050304, 'steps': 47136, 'loss/train': 1.4981313943862915} 08/30/2021 21:46:30 - INFO - __main__ - Step 47138: {'lr': 0.0003937643378535009, 'samples': 9050496, 'steps': 47137, 'loss/train': 1.5889283418655396} 08/30/2021 21:46:30 - INFO - __main__ - Step 47139: {'lr': 0.0003937599963040491, 'samples': 9050688, 'steps': 47138, 'loss/train': 1.4682588577270508} 08/30/2021 21:46:31 - INFO - __main__ - Step 47140: {'lr': 0.0003937556546898214, 'samples': 9050880, 'steps': 47139, 'loss/train': 0.18973694741725922} 08/30/2021 21:46:31 - INFO - __main__ - Step 47141: {'lr': 0.0003937513130108197, 'samples': 9051072, 'steps': 47140, 'loss/train': 0.3625023365020752} 08/30/2021 21:46:33 - INFO - __main__ - Step 47142: {'lr': 0.00039374697126704573, 'samples': 9051264, 'steps': 47141, 'loss/train': 1.8720823526382446} 08/30/2021 21:46:33 - INFO - __main__ - Step 47143: {'lr': 0.0003937426294585017, 'samples': 9051456, 'steps': 47142, 'loss/train': 1.1312073469161987} 08/30/2021 21:46:34 - INFO - __main__ - Step 47144: {'lr': 0.00039373828758518936, 'samples': 9051648, 'steps': 47143, 'loss/train': 1.7806357145309448} 08/30/2021 21:46:34 - INFO - __main__ - Step 47145: {'lr': 0.00039373394564711086, 'samples': 9051840, 'steps': 47144, 'loss/train': 1.7965664863586426} 08/30/2021 21:46:34 - INFO - __main__ - Step 47146: {'lr': 0.00039372960364426803, 'samples': 9052032, 'steps': 47145, 'loss/train': 1.4933303594589233} 08/30/2021 21:46:36 - INFO - __main__ - Step 47147: {'lr': 0.0003937252615766628, 'samples': 9052224, 'steps': 47146, 'loss/train': 0.8132494688034058} 08/30/2021 21:46:36 - INFO - __main__ - Step 47148: {'lr': 0.0003937209194442973, 'samples': 9052416, 'steps': 47147, 'loss/train': 1.3352147340774536} 08/30/2021 21:46:37 - INFO - __main__ - Step 47149: {'lr': 0.00039371657724717325, 'samples': 9052608, 'steps': 47148, 'loss/train': 1.5505788326263428} 08/30/2021 21:46:37 - INFO - __main__ - Step 47150: {'lr': 0.0003937122349852928, 'samples': 9052800, 'steps': 47149, 'loss/train': 1.6834405660629272} 08/30/2021 21:46:38 - INFO - __main__ - Step 47151: {'lr': 0.0003937078926586578, 'samples': 9052992, 'steps': 47150, 'loss/train': 1.6427558660507202} 08/30/2021 21:46:39 - INFO - __main__ - Step 47152: {'lr': 0.0003937035502672703, 'samples': 9053184, 'steps': 47151, 'loss/train': 0.958710253238678} 08/30/2021 21:46:39 - INFO - __main__ - Step 47153: {'lr': 0.0003936992078111321, 'samples': 9053376, 'steps': 47152, 'loss/train': 1.375846266746521} 08/30/2021 21:46:40 - INFO - __main__ - Step 47154: {'lr': 0.0003936948652902453, 'samples': 9053568, 'steps': 47153, 'loss/train': 1.597145676612854} 08/30/2021 21:46:40 - INFO - __main__ - Step 47155: {'lr': 0.0003936905227046119, 'samples': 9053760, 'steps': 47154, 'loss/train': 1.5597662925720215} 08/30/2021 21:46:40 - INFO - __main__ - Step 47156: {'lr': 0.00039368618005423365, 'samples': 9053952, 'steps': 47155, 'loss/train': 1.5827739238739014} 08/30/2021 21:46:42 - INFO - __main__ - Step 47157: {'lr': 0.00039368183733911265, 'samples': 9054144, 'steps': 47156, 'loss/train': 1.0623199939727783} 08/30/2021 21:46:43 - INFO - __main__ - Step 47158: {'lr': 0.00039367749455925086, 'samples': 9054336, 'steps': 47157, 'loss/train': 1.1863417625427246} 08/30/2021 21:46:43 - INFO - __main__ - Step 47159: {'lr': 0.0003936731517146502, 'samples': 9054528, 'steps': 47158, 'loss/train': 0.9572000503540039} 08/30/2021 21:46:44 - INFO - __main__ - Step 47160: {'lr': 0.0003936688088053126, 'samples': 9054720, 'steps': 47159, 'loss/train': 0.9539853930473328} 08/30/2021 21:46:44 - INFO - __main__ - Step 47161: {'lr': 0.0003936644658312401, 'samples': 9054912, 'steps': 47160, 'loss/train': 1.5425822734832764} 08/30/2021 21:46:44 - INFO - __main__ - Step 47162: {'lr': 0.0003936601227924346, 'samples': 9055104, 'steps': 47161, 'loss/train': 0.059844743460416794} 08/30/2021 21:46:46 - INFO - __main__ - Step 47163: {'lr': 0.00039365577968889805, 'samples': 9055296, 'steps': 47162, 'loss/train': 1.5637813806533813} 08/30/2021 21:46:46 - INFO - __main__ - Step 47164: {'lr': 0.0003936514365206324, 'samples': 9055488, 'steps': 47163, 'loss/train': 1.7346241474151611} 08/30/2021 21:46:46 - INFO - __main__ - Step 47165: {'lr': 0.00039364709328763966, 'samples': 9055680, 'steps': 47164, 'loss/train': 1.0631160736083984} 08/30/2021 21:46:47 - INFO - __main__ - Step 47166: {'lr': 0.00039364274998992177, 'samples': 9055872, 'steps': 47165, 'loss/train': 1.503037452697754} 08/30/2021 21:46:47 - INFO - __main__ - Step 47167: {'lr': 0.00039363840662748063, 'samples': 9056064, 'steps': 47166, 'loss/train': 1.1738473176956177} 08/30/2021 21:46:49 - INFO - __main__ - Step 47168: {'lr': 0.0003936340632003183, 'samples': 9056256, 'steps': 47167, 'loss/train': 1.3312121629714966} 08/30/2021 21:46:49 - INFO - __main__ - Step 47169: {'lr': 0.0003936297197084366, 'samples': 9056448, 'steps': 47168, 'loss/train': 2.259002685546875} 08/30/2021 21:46:50 - INFO - __main__ - Step 47170: {'lr': 0.00039362537615183764, 'samples': 9056640, 'steps': 47169, 'loss/train': 1.2216168642044067} 08/30/2021 21:46:50 - INFO - __main__ - Step 47171: {'lr': 0.0003936210325305233, 'samples': 9056832, 'steps': 47170, 'loss/train': 0.9417734742164612} 08/30/2021 21:46:50 - INFO - __main__ - Step 47172: {'lr': 0.0003936166888444954, 'samples': 9057024, 'steps': 47171, 'loss/train': 1.0368679761886597} 08/30/2021 21:46:52 - INFO - __main__ - Step 47173: {'lr': 0.0003936123450937562, 'samples': 9057216, 'steps': 47172, 'loss/train': 1.2912726402282715} 08/30/2021 21:46:52 - INFO - __main__ - Step 47174: {'lr': 0.0003936080012783075, 'samples': 9057408, 'steps': 47173, 'loss/train': 1.5052670240402222} 08/30/2021 21:46:53 - INFO - __main__ - Step 47175: {'lr': 0.0003936036573981512, 'samples': 9057600, 'steps': 47174, 'loss/train': 1.4165047407150269} 08/30/2021 21:46:53 - INFO - __main__ - Step 47176: {'lr': 0.00039359931345328927, 'samples': 9057792, 'steps': 47175, 'loss/train': 0.636588990688324} 08/30/2021 21:46:53 - INFO - __main__ - Step 47177: {'lr': 0.0003935949694437237, 'samples': 9057984, 'steps': 47176, 'loss/train': 1.0945026874542236} 08/30/2021 21:46:55 - INFO - __main__ - Step 47178: {'lr': 0.00039359062536945645, 'samples': 9058176, 'steps': 47177, 'loss/train': 1.099445104598999} 08/30/2021 21:46:55 - INFO - __main__ - Step 47179: {'lr': 0.00039358628123048955, 'samples': 9058368, 'steps': 47178, 'loss/train': 1.7694694995880127} 08/30/2021 21:46:56 - INFO - __main__ - Step 47180: {'lr': 0.0003935819370268249, 'samples': 9058560, 'steps': 47179, 'loss/train': 1.023068904876709} 08/30/2021 21:46:56 - INFO - __main__ - Step 47181: {'lr': 0.00039357759275846437, 'samples': 9058752, 'steps': 47180, 'loss/train': 1.374024510383606} 08/30/2021 21:46:56 - INFO - __main__ - Step 47182: {'lr': 0.00039357324842541, 'samples': 9058944, 'steps': 47181, 'loss/train': 1.5039547681808472} 08/30/2021 21:46:58 - INFO - __main__ - Step 47183: {'lr': 0.0003935689040276638, 'samples': 9059136, 'steps': 47182, 'loss/train': 1.2474969625473022} 08/30/2021 21:46:58 - INFO - __main__ - Step 47184: {'lr': 0.0003935645595652276, 'samples': 9059328, 'steps': 47183, 'loss/train': 1.548696756362915} 08/30/2021 21:46:59 - INFO - __main__ - Step 47185: {'lr': 0.0003935602150381034, 'samples': 9059520, 'steps': 47184, 'loss/train': 0.9608526825904846} 08/30/2021 21:46:59 - INFO - __main__ - Step 47186: {'lr': 0.00039355587044629325, 'samples': 9059712, 'steps': 47185, 'loss/train': 1.438480019569397} 08/30/2021 21:46:59 - INFO - __main__ - Step 47187: {'lr': 0.00039355152578979903, 'samples': 9059904, 'steps': 47186, 'loss/train': 1.0906423330307007} 08/30/2021 21:47:00 - INFO - __main__ - Step 47188: {'lr': 0.0003935471810686228, 'samples': 9060096, 'steps': 47187, 'loss/train': 1.8375911712646484} 08/30/2021 21:47:01 - INFO - __main__ - Step 47189: {'lr': 0.0003935428362827662, 'samples': 9060288, 'steps': 47188, 'loss/train': 1.8356000185012817} 08/30/2021 21:47:02 - INFO - __main__ - Step 47190: {'lr': 0.0003935384914322316, 'samples': 9060480, 'steps': 47189, 'loss/train': 1.4232927560806274} 08/30/2021 21:47:02 - INFO - __main__ - Step 47191: {'lr': 0.0003935341465170207, 'samples': 9060672, 'steps': 47190, 'loss/train': 1.9569494724273682} 08/30/2021 21:47:02 - INFO - __main__ - Step 47192: {'lr': 0.0003935298015371355, 'samples': 9060864, 'steps': 47191, 'loss/train': 1.5322213172912598} 08/30/2021 21:47:03 - INFO - __main__ - Step 47193: {'lr': 0.0003935254564925781, 'samples': 9061056, 'steps': 47192, 'loss/train': 0.9357300996780396} 08/30/2021 21:47:05 - INFO - __main__ - Step 47194: {'lr': 0.0003935211113833502, 'samples': 9061248, 'steps': 47193, 'loss/train': 1.6644103527069092} 08/30/2021 21:47:05 - INFO - __main__ - Step 47195: {'lr': 0.00039351676620945396, 'samples': 9061440, 'steps': 47194, 'loss/train': 1.3437191247940063} 08/30/2021 21:47:06 - INFO - __main__ - Step 47196: {'lr': 0.00039351242097089133, 'samples': 9061632, 'steps': 47195, 'loss/train': 1.4233492612838745} 08/30/2021 21:47:06 - INFO - __main__ - Step 47197: {'lr': 0.0003935080756676641, 'samples': 9061824, 'steps': 47196, 'loss/train': 1.3775190114974976} 08/30/2021 21:47:06 - INFO - __main__ - Step 47198: {'lr': 0.0003935037302997745, 'samples': 9062016, 'steps': 47197, 'loss/train': 1.7171847820281982} 08/30/2021 21:47:08 - INFO - __main__ - Step 47199: {'lr': 0.00039349938486722425, 'samples': 9062208, 'steps': 47198, 'loss/train': 1.541567087173462} 08/30/2021 21:47:08 - INFO - __main__ - Step 47200: {'lr': 0.0003934950393700154, 'samples': 9062400, 'steps': 47199, 'loss/train': 1.4359557628631592} 08/30/2021 21:47:09 - INFO - __main__ - Step 47201: {'lr': 0.0003934906938081499, 'samples': 9062592, 'steps': 47200, 'loss/train': 1.3227238655090332} 08/30/2021 21:47:09 - INFO - __main__ - Step 47202: {'lr': 0.0003934863481816297, 'samples': 9062784, 'steps': 47201, 'loss/train': 2.2633533477783203} 08/30/2021 21:47:09 - INFO - __main__ - Step 47203: {'lr': 0.00039348200249045675, 'samples': 9062976, 'steps': 47202, 'loss/train': 2.111750841140747} 08/30/2021 21:47:11 - INFO - __main__ - Step 47204: {'lr': 0.000393477656734633, 'samples': 9063168, 'steps': 47203, 'loss/train': 1.31951904296875} 08/30/2021 21:47:11 - INFO - __main__ - Step 47205: {'lr': 0.0003934733109141605, 'samples': 9063360, 'steps': 47204, 'loss/train': 1.2697341442108154} 08/30/2021 21:47:12 - INFO - __main__ - Step 47206: {'lr': 0.00039346896502904117, 'samples': 9063552, 'steps': 47205, 'loss/train': 1.754895567893982} 08/30/2021 21:47:12 - INFO - __main__ - Step 47207: {'lr': 0.0003934646190792769, 'samples': 9063744, 'steps': 47206, 'loss/train': 1.533581018447876} 08/30/2021 21:47:12 - INFO - __main__ - Step 47208: {'lr': 0.00039346027306486964, 'samples': 9063936, 'steps': 47207, 'loss/train': 1.1768206357955933} 08/30/2021 21:47:14 - INFO - __main__ - Step 47209: {'lr': 0.00039345592698582146, 'samples': 9064128, 'steps': 47208, 'loss/train': 1.5395684242248535} 08/30/2021 21:47:14 - INFO - __main__ - Step 47210: {'lr': 0.00039345158084213417, 'samples': 9064320, 'steps': 47209, 'loss/train': 1.130729079246521} 08/30/2021 21:47:14 - INFO - __main__ - Step 47211: {'lr': 0.0003934472346338099, 'samples': 9064512, 'steps': 47210, 'loss/train': 1.8665534257888794} 08/30/2021 21:47:15 - INFO - __main__ - Step 47212: {'lr': 0.00039344288836085046, 'samples': 9064704, 'steps': 47211, 'loss/train': 0.8307130932807922} 08/30/2021 21:47:15 - INFO - __main__ - Step 47213: {'lr': 0.0003934385420232579, 'samples': 9064896, 'steps': 47212, 'loss/train': 1.6355105638504028} 08/30/2021 21:47:17 - INFO - __main__ - Step 47214: {'lr': 0.0003934341956210341, 'samples': 9065088, 'steps': 47213, 'loss/train': 1.9811102151870728} 08/30/2021 21:47:17 - INFO - __main__ - Step 47215: {'lr': 0.0003934298491541811, 'samples': 9065280, 'steps': 47214, 'loss/train': 0.6664502620697021} 08/30/2021 21:47:17 - INFO - __main__ - Step 47216: {'lr': 0.0003934255026227008, 'samples': 9065472, 'steps': 47215, 'loss/train': 1.1501413583755493} 08/30/2021 21:47:18 - INFO - __main__ - Step 47217: {'lr': 0.0003934211560265952, 'samples': 9065664, 'steps': 47216, 'loss/train': 1.3039368391036987} 08/30/2021 21:47:18 - INFO - __main__ - Step 47218: {'lr': 0.0003934168093658663, 'samples': 9065856, 'steps': 47217, 'loss/train': 1.2305551767349243} 08/30/2021 21:47:19 - INFO - __main__ - Step 47219: {'lr': 0.0003934124626405159, 'samples': 9066048, 'steps': 47218, 'loss/train': 1.9310535192489624} 08/30/2021 21:47:20 - INFO - __main__ - Step 47220: {'lr': 0.00039340811585054615, 'samples': 9066240, 'steps': 47219, 'loss/train': 1.0418373346328735} 08/30/2021 21:47:21 - INFO - __main__ - Step 47221: {'lr': 0.0003934037689959589, 'samples': 9066432, 'steps': 47220, 'loss/train': 0.6557124853134155} 08/30/2021 21:47:21 - INFO - __main__ - Step 47222: {'lr': 0.00039339942207675604, 'samples': 9066624, 'steps': 47221, 'loss/train': 0.11926555633544922} 08/30/2021 21:47:21 - INFO - __main__ - Step 47223: {'lr': 0.0003933950750929397, 'samples': 9066816, 'steps': 47222, 'loss/train': 1.38284432888031} 08/30/2021 21:47:22 - INFO - __main__ - Step 47224: {'lr': 0.0003933907280445117, 'samples': 9067008, 'steps': 47223, 'loss/train': 1.1271244287490845} 08/30/2021 21:47:23 - INFO - __main__ - Step 47225: {'lr': 0.00039338638093147404, 'samples': 9067200, 'steps': 47224, 'loss/train': 1.3011709451675415} 08/30/2021 21:47:24 - INFO - __main__ - Step 47226: {'lr': 0.00039338203375382873, 'samples': 9067392, 'steps': 47225, 'loss/train': 1.519370675086975} 08/30/2021 21:47:24 - INFO - __main__ - Step 47227: {'lr': 0.00039337768651157766, 'samples': 9067584, 'steps': 47226, 'loss/train': 1.7933515310287476} 08/30/2021 21:47:24 - INFO - __main__ - Step 47228: {'lr': 0.0003933733392047228, 'samples': 9067776, 'steps': 47227, 'loss/train': 0.613797664642334} 08/30/2021 21:47:25 - INFO - __main__ - Step 47229: {'lr': 0.0003933689918332662, 'samples': 9067968, 'steps': 47228, 'loss/train': 1.5601712465286255} 08/30/2021 21:47:26 - INFO - __main__ - Step 47230: {'lr': 0.0003933646443972097, 'samples': 9068160, 'steps': 47229, 'loss/train': 1.699337124824524} 08/30/2021 21:47:27 - INFO - __main__ - Step 47231: {'lr': 0.0003933602968965553, 'samples': 9068352, 'steps': 47230, 'loss/train': 1.508933424949646} 08/30/2021 21:47:27 - INFO - __main__ - Step 47232: {'lr': 0.00039335594933130494, 'samples': 9068544, 'steps': 47231, 'loss/train': 1.45913565158844} 08/30/2021 21:47:28 - INFO - __main__ - Step 47233: {'lr': 0.0003933516017014607, 'samples': 9068736, 'steps': 47232, 'loss/train': 1.5323749780654907} 08/30/2021 21:47:28 - INFO - __main__ - Step 47234: {'lr': 0.0003933472540070243, 'samples': 9068928, 'steps': 47233, 'loss/train': 1.5066059827804565} 08/30/2021 21:47:29 - INFO - __main__ - Step 47235: {'lr': 0.00039334290624799795, 'samples': 9069120, 'steps': 47234, 'loss/train': 0.7128892540931702} 08/30/2021 21:47:30 - INFO - __main__ - Step 47236: {'lr': 0.0003933385584243834, 'samples': 9069312, 'steps': 47235, 'loss/train': 1.6853135824203491} 08/30/2021 21:47:30 - INFO - __main__ - Step 47237: {'lr': 0.0003933342105361828, 'samples': 9069504, 'steps': 47236, 'loss/train': 1.0111676454544067} 08/30/2021 21:47:31 - INFO - __main__ - Step 47238: {'lr': 0.000393329862583398, 'samples': 9069696, 'steps': 47237, 'loss/train': 1.313427209854126} 08/30/2021 21:47:31 - INFO - __main__ - Step 47239: {'lr': 0.00039332551456603093, 'samples': 9069888, 'steps': 47238, 'loss/train': 1.5572577714920044} 08/30/2021 21:47:31 - INFO - __main__ - Step 47240: {'lr': 0.00039332116648408365, 'samples': 9070080, 'steps': 47239, 'loss/train': 1.349772572517395} 08/30/2021 21:47:33 - INFO - __main__ - Step 47241: {'lr': 0.00039331681833755804, 'samples': 9070272, 'steps': 47240, 'loss/train': 1.349863886833191} 08/30/2021 21:47:33 - INFO - __main__ - Step 47242: {'lr': 0.00039331247012645604, 'samples': 9070464, 'steps': 47241, 'loss/train': 1.808831810951233} 08/30/2021 21:47:34 - INFO - __main__ - Step 47243: {'lr': 0.00039330812185077967, 'samples': 9070656, 'steps': 47242, 'loss/train': 1.6437147855758667} 08/30/2021 21:47:34 - INFO - __main__ - Step 47244: {'lr': 0.0003933037735105309, 'samples': 9070848, 'steps': 47243, 'loss/train': 1.2804737091064453} 08/30/2021 21:47:34 - INFO - __main__ - Step 47245: {'lr': 0.00039329942510571165, 'samples': 9071040, 'steps': 47244, 'loss/train': 1.3627424240112305} 08/30/2021 21:47:36 - INFO - __main__ - Step 47246: {'lr': 0.0003932950766363239, 'samples': 9071232, 'steps': 47245, 'loss/train': 1.1552386283874512} 08/30/2021 21:47:37 - INFO - __main__ - Step 47247: {'lr': 0.00039329072810236965, 'samples': 9071424, 'steps': 47246, 'loss/train': 1.071413278579712} 08/30/2021 21:47:37 - INFO - __main__ - Step 47248: {'lr': 0.0003932863795038507, 'samples': 9071616, 'steps': 47247, 'loss/train': 0.11882774531841278} 08/30/2021 21:47:37 - INFO - __main__ - Step 47249: {'lr': 0.0003932820308407692, 'samples': 9071808, 'steps': 47248, 'loss/train': 1.7145575284957886} 08/30/2021 21:47:38 - INFO - __main__ - Step 47250: {'lr': 0.000393277682113127, 'samples': 9072000, 'steps': 47249, 'loss/train': 1.3279597759246826} 08/30/2021 21:47:38 - INFO - __main__ - Step 47251: {'lr': 0.00039327333332092606, 'samples': 9072192, 'steps': 47250, 'loss/train': 1.0670586824417114} 08/30/2021 21:47:41 - INFO - __main__ - Step 47252: {'lr': 0.0003932689844641684, 'samples': 9072384, 'steps': 47251, 'loss/train': 1.458558440208435} 08/30/2021 21:47:41 - INFO - __main__ - Step 47253: {'lr': 0.00039326463554285597, 'samples': 9072576, 'steps': 47252, 'loss/train': 1.4830328226089478} 08/30/2021 21:47:41 - INFO - __main__ - Step 47254: {'lr': 0.00039326028655699063, 'samples': 9072768, 'steps': 47253, 'loss/train': 1.6451884508132935} 08/30/2021 21:47:42 - INFO - __main__ - Step 47255: {'lr': 0.0003932559375065745, 'samples': 9072960, 'steps': 47254, 'loss/train': 1.4628525972366333} 08/30/2021 21:47:42 - INFO - __main__ - Step 47256: {'lr': 0.00039325158839160937, 'samples': 9073152, 'steps': 47255, 'loss/train': 0.9414811730384827} 08/30/2021 21:47:42 - INFO - __main__ - Step 47257: {'lr': 0.0003932472392120974, 'samples': 9073344, 'steps': 47256, 'loss/train': 1.7280681133270264} 08/30/2021 21:47:44 - INFO - __main__ - Step 47258: {'lr': 0.00039324288996804026, 'samples': 9073536, 'steps': 47257, 'loss/train': 1.7407526969909668} 08/30/2021 21:47:44 - INFO - __main__ - Step 47259: {'lr': 0.0003932385406594402, 'samples': 9073728, 'steps': 47258, 'loss/train': 0.9837968349456787} 08/30/2021 21:47:45 - INFO - __main__ - Step 47260: {'lr': 0.0003932341912862991, 'samples': 9073920, 'steps': 47259, 'loss/train': 0.5422816872596741} 08/30/2021 21:47:45 - INFO - __main__ - Step 47261: {'lr': 0.0003932298418486188, 'samples': 9074112, 'steps': 47260, 'loss/train': 1.6922330856323242} 08/30/2021 21:47:45 - INFO - __main__ - Step 47262: {'lr': 0.00039322549234640136, 'samples': 9074304, 'steps': 47261, 'loss/train': 1.4442442655563354} 08/30/2021 21:47:46 - INFO - __main__ - Step 47263: {'lr': 0.00039322114277964875, 'samples': 9074496, 'steps': 47262, 'loss/train': 1.4364198446273804} 08/30/2021 21:47:48 - INFO - __main__ - Step 47264: {'lr': 0.0003932167931483629, 'samples': 9074688, 'steps': 47263, 'loss/train': 1.5787311792373657} 08/30/2021 21:47:49 - INFO - __main__ - Step 47265: {'lr': 0.00039321244345254583, 'samples': 9074880, 'steps': 47264, 'loss/train': 1.5624264478683472} 08/30/2021 21:47:49 - INFO - __main__ - Step 47266: {'lr': 0.0003932080936921993, 'samples': 9075072, 'steps': 47265, 'loss/train': 4.3112897872924805} 08/30/2021 21:47:49 - INFO - __main__ - Step 47267: {'lr': 0.00039320374386732555, 'samples': 9075264, 'steps': 47266, 'loss/train': 4.432944297790527} 08/30/2021 21:47:50 - INFO - __main__ - Step 47268: {'lr': 0.00039319939397792635, 'samples': 9075456, 'steps': 47267, 'loss/train': 1.9740513563156128} 08/30/2021 21:47:50 - INFO - __main__ - Step 47269: {'lr': 0.00039319504402400367, 'samples': 9075648, 'steps': 47268, 'loss/train': 1.079913854598999} 08/30/2021 21:47:52 - INFO - __main__ - Step 47270: {'lr': 0.0003931906940055596, 'samples': 9075840, 'steps': 47269, 'loss/train': 1.2581286430358887} 08/30/2021 21:47:52 - INFO - __main__ - Step 47271: {'lr': 0.00039318634392259593, 'samples': 9076032, 'steps': 47270, 'loss/train': 1.5154542922973633} 08/30/2021 21:47:52 - INFO - __main__ - Step 47272: {'lr': 0.00039318199377511476, 'samples': 9076224, 'steps': 47271, 'loss/train': 0.8166834712028503} 08/30/2021 21:47:53 - INFO - __main__ - Step 47273: {'lr': 0.00039317764356311803, 'samples': 9076416, 'steps': 47272, 'loss/train': 3.0102884769439697} 08/30/2021 21:47:53 - INFO - __main__ - Step 47274: {'lr': 0.00039317329328660754, 'samples': 9076608, 'steps': 47273, 'loss/train': 1.2756074666976929} 08/30/2021 21:47:54 - INFO - __main__ - Step 47275: {'lr': 0.0003931689429455855, 'samples': 9076800, 'steps': 47274, 'loss/train': 1.1009291410446167} 08/30/2021 21:47:55 - INFO - __main__ - Step 47276: {'lr': 0.00039316459254005364, 'samples': 9076992, 'steps': 47275, 'loss/train': 1.7836995124816895} 08/30/2021 21:47:55 - INFO - __main__ - Step 47277: {'lr': 0.00039316024207001403, 'samples': 9077184, 'steps': 47276, 'loss/train': 1.9067935943603516} 08/30/2021 21:47:56 - INFO - __main__ - Step 47278: {'lr': 0.0003931558915354687, 'samples': 9077376, 'steps': 47277, 'loss/train': 1.2166469097137451} 08/30/2021 21:47:56 - INFO - __main__ - Step 47279: {'lr': 0.00039315154093641947, 'samples': 9077568, 'steps': 47278, 'loss/train': 1.7116620540618896} 08/30/2021 21:47:57 - INFO - __main__ - Step 47280: {'lr': 0.00039314719027286837, 'samples': 9077760, 'steps': 47279, 'loss/train': 1.3903424739837646} 08/30/2021 21:47:58 - INFO - __main__ - Step 47281: {'lr': 0.00039314283954481737, 'samples': 9077952, 'steps': 47280, 'loss/train': 0.059253908693790436} 08/30/2021 21:47:58 - INFO - __main__ - Step 47282: {'lr': 0.00039313848875226844, 'samples': 9078144, 'steps': 47281, 'loss/train': 1.5881465673446655} 08/30/2021 21:47:59 - INFO - __main__ - Step 47283: {'lr': 0.0003931341378952235, 'samples': 9078336, 'steps': 47282, 'loss/train': 1.2724661827087402} 08/30/2021 21:47:59 - INFO - __main__ - Step 47284: {'lr': 0.0003931297869736845, 'samples': 9078528, 'steps': 47283, 'loss/train': 1.3937915563583374} 08/30/2021 21:48:00 - INFO - __main__ - Step 47285: {'lr': 0.0003931254359876535, 'samples': 9078720, 'steps': 47284, 'loss/train': 0.7238603234291077} 08/30/2021 21:48:01 - INFO - __main__ - Step 47286: {'lr': 0.00039312108493713227, 'samples': 9078912, 'steps': 47285, 'loss/train': 1.7359777688980103} 08/30/2021 21:48:01 - INFO - __main__ - Step 47287: {'lr': 0.00039311673382212296, 'samples': 9079104, 'steps': 47286, 'loss/train': 1.3183573484420776} 08/30/2021 21:48:02 - INFO - __main__ - Step 47288: {'lr': 0.0003931123826426275, 'samples': 9079296, 'steps': 47287, 'loss/train': 0.08673273026943207} 08/30/2021 21:48:02 - INFO - __main__ - Step 47289: {'lr': 0.00039310803139864777, 'samples': 9079488, 'steps': 47288, 'loss/train': 1.4308583736419678} 08/30/2021 21:48:03 - INFO - __main__ - Step 47290: {'lr': 0.0003931036800901857, 'samples': 9079680, 'steps': 47289, 'loss/train': 1.5248067378997803} 08/30/2021 21:48:04 - INFO - __main__ - Step 47291: {'lr': 0.0003930993287172434, 'samples': 9079872, 'steps': 47290, 'loss/train': 1.4464563131332397} 08/30/2021 21:48:04 - INFO - __main__ - Step 47292: {'lr': 0.0003930949772798227, 'samples': 9080064, 'steps': 47291, 'loss/train': 1.6020326614379883} 08/30/2021 21:48:05 - INFO - __main__ - Step 47293: {'lr': 0.00039309062577792565, 'samples': 9080256, 'steps': 47292, 'loss/train': 1.4132577180862427} 08/30/2021 21:48:05 - INFO - __main__ - Step 47294: {'lr': 0.0003930862742115542, 'samples': 9080448, 'steps': 47293, 'loss/train': 1.614087700843811} 08/30/2021 21:48:07 - INFO - __main__ - Step 47295: {'lr': 0.0003930819225807102, 'samples': 9080640, 'steps': 47294, 'loss/train': 1.2367781400680542} 08/30/2021 21:48:07 - INFO - __main__ - Step 47296: {'lr': 0.00039307757088539574, 'samples': 9080832, 'steps': 47295, 'loss/train': 2.146489381790161} 08/30/2021 21:48:07 - INFO - __main__ - Step 47297: {'lr': 0.0003930732191256128, 'samples': 9081024, 'steps': 47296, 'loss/train': 1.5928442478179932} 08/30/2021 21:48:08 - INFO - __main__ - Step 47298: {'lr': 0.00039306886730136316, 'samples': 9081216, 'steps': 47297, 'loss/train': 2.2303366661071777} 08/30/2021 21:48:08 - INFO - __main__ - Step 47299: {'lr': 0.00039306451541264896, 'samples': 9081408, 'steps': 47298, 'loss/train': 0.9554955959320068} 08/30/2021 21:48:08 - INFO - __main__ - Step 47300: {'lr': 0.0003930601634594721, 'samples': 9081600, 'steps': 47299, 'loss/train': 1.4821048974990845} 08/30/2021 21:48:10 - INFO - __main__ - Step 47301: {'lr': 0.0003930558114418345, 'samples': 9081792, 'steps': 47300, 'loss/train': 1.671755075454712} 08/30/2021 21:48:10 - INFO - __main__ - Step 47302: {'lr': 0.0003930514593597382, 'samples': 9081984, 'steps': 47301, 'loss/train': 1.0608506202697754} 08/30/2021 21:48:11 - INFO - __main__ - Step 47303: {'lr': 0.00039304710721318505, 'samples': 9082176, 'steps': 47302, 'loss/train': 1.6971443891525269} 08/30/2021 21:48:11 - INFO - __main__ - Step 47304: {'lr': 0.0003930427550021771, 'samples': 9082368, 'steps': 47303, 'loss/train': 0.21481195092201233} 08/30/2021 21:48:11 - INFO - __main__ - Step 47305: {'lr': 0.00039303840272671636, 'samples': 9082560, 'steps': 47304, 'loss/train': 1.41652250289917} 08/30/2021 21:48:13 - INFO - __main__ - Step 47306: {'lr': 0.00039303405038680465, 'samples': 9082752, 'steps': 47305, 'loss/train': 1.2006443738937378} 08/30/2021 21:48:14 - INFO - __main__ - Step 47307: {'lr': 0.00039302969798244407, 'samples': 9082944, 'steps': 47306, 'loss/train': 1.6500297784805298} 08/30/2021 21:48:14 - INFO - __main__ - Step 47308: {'lr': 0.0003930253455136365, 'samples': 9083136, 'steps': 47307, 'loss/train': 0.12864425778388977} 08/30/2021 21:48:15 - INFO - __main__ - Step 47309: {'lr': 0.0003930209929803839, 'samples': 9083328, 'steps': 47308, 'loss/train': 1.8450382947921753} 08/30/2021 21:48:15 - INFO - __main__ - Step 47310: {'lr': 0.0003930166403826883, 'samples': 9083520, 'steps': 47309, 'loss/train': 1.412922739982605} 08/30/2021 21:48:17 - INFO - __main__ - Step 47311: {'lr': 0.00039301228772055147, 'samples': 9083712, 'steps': 47310, 'loss/train': 1.0711334943771362} 08/30/2021 21:48:17 - INFO - __main__ - Step 47312: {'lr': 0.0003930079349939756, 'samples': 9083904, 'steps': 47311, 'loss/train': 0.9847979545593262} 08/30/2021 21:48:17 - INFO - __main__ - Step 47313: {'lr': 0.00039300358220296255, 'samples': 9084096, 'steps': 47312, 'loss/train': 1.3400652408599854} 08/30/2021 21:48:18 - INFO - __main__ - Step 47314: {'lr': 0.0003929992293475143, 'samples': 9084288, 'steps': 47313, 'loss/train': 1.718641996383667} 08/30/2021 21:48:18 - INFO - __main__ - Step 47315: {'lr': 0.00039299487642763286, 'samples': 9084480, 'steps': 47314, 'loss/train': 1.306476354598999} 08/30/2021 21:48:20 - INFO - __main__ - Step 47316: {'lr': 0.00039299052344332, 'samples': 9084672, 'steps': 47315, 'loss/train': 1.2910528182983398} 08/30/2021 21:48:20 - INFO - __main__ - Step 47317: {'lr': 0.00039298617039457796, 'samples': 9084864, 'steps': 47316, 'loss/train': 0.380572110414505} 08/30/2021 21:48:21 - INFO - __main__ - Step 47318: {'lr': 0.0003929818172814085, 'samples': 9085056, 'steps': 47317, 'loss/train': 1.2524960041046143} 08/30/2021 21:48:21 - INFO - __main__ - Step 47319: {'lr': 0.00039297746410381357, 'samples': 9085248, 'steps': 47318, 'loss/train': 1.192836046218872} 08/30/2021 21:48:21 - INFO - __main__ - Step 47320: {'lr': 0.00039297311086179535, 'samples': 9085440, 'steps': 47319, 'loss/train': 1.6921825408935547} 08/30/2021 21:48:22 - INFO - __main__ - Step 47321: {'lr': 0.00039296875755535557, 'samples': 9085632, 'steps': 47320, 'loss/train': 1.0637820959091187} 08/30/2021 21:48:23 - INFO - __main__ - Step 47322: {'lr': 0.0003929644041844962, 'samples': 9085824, 'steps': 47321, 'loss/train': 1.711601734161377} 08/30/2021 21:48:24 - INFO - __main__ - Step 47323: {'lr': 0.00039296005074921937, 'samples': 9086016, 'steps': 47322, 'loss/train': 0.10674764215946198} 08/30/2021 21:48:24 - INFO - __main__ - Step 47324: {'lr': 0.0003929556972495269, 'samples': 9086208, 'steps': 47323, 'loss/train': 1.6770915985107422} 08/30/2021 21:48:25 - INFO - __main__ - Step 47325: {'lr': 0.00039295134368542083, 'samples': 9086400, 'steps': 47324, 'loss/train': 0.9848683476448059} 08/30/2021 21:48:25 - INFO - __main__ - Step 47326: {'lr': 0.000392946990056903, 'samples': 9086592, 'steps': 47325, 'loss/train': 1.8454848527908325} 08/30/2021 21:48:27 - INFO - __main__ - Step 47327: {'lr': 0.00039294263636397564, 'samples': 9086784, 'steps': 47326, 'loss/train': 1.303276538848877} 08/30/2021 21:48:27 - INFO - __main__ - Step 47328: {'lr': 0.00039293828260664047, 'samples': 9086976, 'steps': 47327, 'loss/train': 0.07456887513399124} 08/30/2021 21:48:27 - INFO - __main__ - Step 47329: {'lr': 0.0003929339287848994, 'samples': 9087168, 'steps': 47328, 'loss/train': 0.6583238840103149} 08/30/2021 21:48:28 - INFO - __main__ - Step 47330: {'lr': 0.00039292957489875456, 'samples': 9087360, 'steps': 47329, 'loss/train': 1.1777760982513428} 08/30/2021 21:48:28 - INFO - __main__ - Step 47331: {'lr': 0.00039292522094820794, 'samples': 9087552, 'steps': 47330, 'loss/train': 1.2854838371276855} 08/30/2021 21:48:30 - INFO - __main__ - Step 47332: {'lr': 0.00039292086693326134, 'samples': 9087744, 'steps': 47331, 'loss/train': 1.453113079071045} 08/30/2021 21:48:30 - INFO - __main__ - Step 47333: {'lr': 0.0003929165128539168, 'samples': 9087936, 'steps': 47332, 'loss/train': 1.2781678438186646} 08/30/2021 21:48:30 - INFO - __main__ - Step 47334: {'lr': 0.0003929121587101764, 'samples': 9088128, 'steps': 47333, 'loss/train': 2.0703165531158447} 08/30/2021 21:48:31 - INFO - __main__ - Step 47335: {'lr': 0.00039290780450204187, 'samples': 9088320, 'steps': 47334, 'loss/train': 1.426224708557129} 08/30/2021 21:48:31 - INFO - __main__ - Step 47336: {'lr': 0.00039290345022951535, 'samples': 9088512, 'steps': 47335, 'loss/train': 1.387518048286438} 08/30/2021 21:48:33 - INFO - __main__ - Step 47337: {'lr': 0.0003928990958925987, 'samples': 9088704, 'steps': 47336, 'loss/train': 1.381941318511963} 08/30/2021 21:48:33 - INFO - __main__ - Step 47338: {'lr': 0.0003928947414912939, 'samples': 9088896, 'steps': 47337, 'loss/train': 1.4821908473968506} 08/30/2021 21:48:33 - INFO - __main__ - Step 47339: {'lr': 0.00039289038702560304, 'samples': 9089088, 'steps': 47338, 'loss/train': 1.3943333625793457} 08/30/2021 21:48:34 - INFO - __main__ - Step 47340: {'lr': 0.0003928860324955279, 'samples': 9089280, 'steps': 47339, 'loss/train': 1.7870291471481323} 08/30/2021 21:48:34 - INFO - __main__ - Step 47341: {'lr': 0.00039288167790107055, 'samples': 9089472, 'steps': 47340, 'loss/train': 0.9736477136611938} 08/30/2021 21:48:36 - INFO - __main__ - Step 47342: {'lr': 0.00039287732324223287, 'samples': 9089664, 'steps': 47341, 'loss/train': 1.3744133710861206} 08/30/2021 21:48:36 - INFO - __main__ - Step 47343: {'lr': 0.0003928729685190169, 'samples': 9089856, 'steps': 47342, 'loss/train': 1.6169779300689697} 08/30/2021 21:48:37 - INFO - __main__ - Step 47344: {'lr': 0.00039286861373142456, 'samples': 9090048, 'steps': 47343, 'loss/train': 1.1734250783920288} 08/30/2021 21:48:37 - INFO - __main__ - Step 47345: {'lr': 0.0003928642588794579, 'samples': 9090240, 'steps': 47344, 'loss/train': 1.5925641059875488} 08/30/2021 21:48:37 - INFO - __main__ - Step 47346: {'lr': 0.0003928599039631187, 'samples': 9090432, 'steps': 47345, 'loss/train': 1.6263929605484009} 08/30/2021 21:48:38 - INFO - __main__ - Step 47347: {'lr': 0.00039285554898240907, 'samples': 9090624, 'steps': 47346, 'loss/train': 1.6302977800369263} 08/30/2021 21:48:40 - INFO - __main__ - Step 47348: {'lr': 0.0003928511939373309, 'samples': 9090816, 'steps': 47347, 'loss/train': 1.4947547912597656} 08/30/2021 21:48:40 - INFO - __main__ - Step 47349: {'lr': 0.0003928468388278863, 'samples': 9091008, 'steps': 47348, 'loss/train': 1.2743167877197266} 08/30/2021 21:48:41 - INFO - __main__ - Step 47350: {'lr': 0.00039284248365407704, 'samples': 9091200, 'steps': 47349, 'loss/train': 1.8058005571365356} 08/30/2021 21:48:41 - INFO - __main__ - Step 47351: {'lr': 0.00039283812841590514, 'samples': 9091392, 'steps': 47350, 'loss/train': 2.523587226867676} 08/30/2021 21:48:42 - INFO - __main__ - Step 47352: {'lr': 0.0003928337731133727, 'samples': 9091584, 'steps': 47351, 'loss/train': 1.3642462491989136} 08/30/2021 21:48:43 - INFO - __main__ - Step 47353: {'lr': 0.0003928294177464814, 'samples': 9091776, 'steps': 47352, 'loss/train': 1.4685677289962769} 08/30/2021 21:48:44 - INFO - __main__ - Step 47354: {'lr': 0.0003928250623152335, 'samples': 9091968, 'steps': 47353, 'loss/train': 1.6228684186935425} 08/30/2021 21:48:44 - INFO - __main__ - Step 47355: {'lr': 0.00039282070681963076, 'samples': 9092160, 'steps': 47354, 'loss/train': 0.20396752655506134} 08/30/2021 21:48:45 - INFO - __main__ - Step 47356: {'lr': 0.00039281635125967525, 'samples': 9092352, 'steps': 47355, 'loss/train': 0.0710807666182518} 08/30/2021 21:48:45 - INFO - __main__ - Step 47357: {'lr': 0.00039281199563536887, 'samples': 9092544, 'steps': 47356, 'loss/train': 1.3086320161819458} 08/30/2021 21:48:45 - INFO - __main__ - Step 47358: {'lr': 0.00039280763994671363, 'samples': 9092736, 'steps': 47357, 'loss/train': 0.5093753337860107} 08/30/2021 21:48:47 - INFO - __main__ - Step 47359: {'lr': 0.0003928032841937115, 'samples': 9092928, 'steps': 47358, 'loss/train': 0.6711312532424927} 08/30/2021 21:48:47 - INFO - __main__ - Step 47360: {'lr': 0.0003927989283763643, 'samples': 9093120, 'steps': 47359, 'loss/train': 1.0352784395217896} 08/30/2021 21:48:48 - INFO - __main__ - Step 47361: {'lr': 0.0003927945724946742, 'samples': 9093312, 'steps': 47360, 'loss/train': 0.9162634015083313} 08/30/2021 21:48:48 - INFO - __main__ - Step 47362: {'lr': 0.00039279021654864307, 'samples': 9093504, 'steps': 47361, 'loss/train': 1.5815321207046509} 08/30/2021 21:48:48 - INFO - __main__ - Step 47363: {'lr': 0.0003927858605382728, 'samples': 9093696, 'steps': 47362, 'loss/train': 1.7978036403656006} 08/30/2021 21:48:49 - INFO - __main__ - Step 47364: {'lr': 0.0003927815044635655, 'samples': 9093888, 'steps': 47363, 'loss/train': 1.3591214418411255} 08/30/2021 21:48:50 - INFO - __main__ - Step 47365: {'lr': 0.00039277714832452304, 'samples': 9094080, 'steps': 47364, 'loss/train': 1.1065795421600342} 08/30/2021 21:48:51 - INFO - __main__ - Step 47366: {'lr': 0.0003927727921211474, 'samples': 9094272, 'steps': 47365, 'loss/train': 1.1524626016616821} 08/30/2021 21:48:51 - INFO - __main__ - Step 47367: {'lr': 0.00039276843585344046, 'samples': 9094464, 'steps': 47366, 'loss/train': 1.0965452194213867} 08/30/2021 21:48:52 - INFO - __main__ - Step 47368: {'lr': 0.0003927640795214044, 'samples': 9094656, 'steps': 47367, 'loss/train': 1.4337648153305054} 08/30/2021 21:48:52 - INFO - __main__ - Step 47369: {'lr': 0.00039275972312504103, 'samples': 9094848, 'steps': 47368, 'loss/train': 1.6651297807693481} 08/30/2021 21:48:53 - INFO - __main__ - Step 47370: {'lr': 0.0003927553666643523, 'samples': 9095040, 'steps': 47369, 'loss/train': 0.8628102540969849} 08/30/2021 21:48:54 - INFO - __main__ - Step 47371: {'lr': 0.0003927510101393401, 'samples': 9095232, 'steps': 47370, 'loss/train': 1.278727412223816} 08/30/2021 21:48:54 - INFO - __main__ - Step 47372: {'lr': 0.0003927466535500066, 'samples': 9095424, 'steps': 47371, 'loss/train': 1.3257778882980347} 08/30/2021 21:48:55 - INFO - __main__ - Step 47373: {'lr': 0.00039274229689635365, 'samples': 9095616, 'steps': 47372, 'loss/train': 0.7446551322937012} 08/30/2021 21:48:55 - INFO - __main__ - Step 47374: {'lr': 0.00039273794017838327, 'samples': 9095808, 'steps': 47373, 'loss/train': 1.4918280839920044} 08/30/2021 21:48:56 - INFO - __main__ - Step 47375: {'lr': 0.0003927335833960973, 'samples': 9096000, 'steps': 47374, 'loss/train': 1.3082075119018555} 08/30/2021 21:48:57 - INFO - __main__ - Step 47376: {'lr': 0.00039272922654949783, 'samples': 9096192, 'steps': 47375, 'loss/train': 1.3660470247268677} 08/30/2021 21:48:57 - INFO - __main__ - Step 47377: {'lr': 0.0003927248696385868, 'samples': 9096384, 'steps': 47376, 'loss/train': 1.9401534795761108} 08/30/2021 21:48:57 - INFO - __main__ - Step 47378: {'lr': 0.00039272051266336607, 'samples': 9096576, 'steps': 47377, 'loss/train': 1.5061721801757812} 08/30/2021 21:48:58 - INFO - __main__ - Step 47379: {'lr': 0.00039271615562383775, 'samples': 9096768, 'steps': 47378, 'loss/train': 1.7097561359405518} 08/30/2021 21:48:59 - INFO - __main__ - Step 47380: {'lr': 0.00039271179852000366, 'samples': 9096960, 'steps': 47379, 'loss/train': 0.7220338582992554} 08/30/2021 21:49:00 - INFO - __main__ - Step 47381: {'lr': 0.0003927074413518659, 'samples': 9097152, 'steps': 47380, 'loss/train': 0.9531300663948059} 08/30/2021 21:49:00 - INFO - __main__ - Step 47382: {'lr': 0.0003927030841194263, 'samples': 9097344, 'steps': 47381, 'loss/train': 1.2772434949874878} 08/30/2021 21:49:00 - INFO - __main__ - Step 47383: {'lr': 0.00039269872682268697, 'samples': 9097536, 'steps': 47382, 'loss/train': 1.0565341711044312} 08/30/2021 21:49:01 - INFO - __main__ - Step 47384: {'lr': 0.00039269436946164977, 'samples': 9097728, 'steps': 47383, 'loss/train': 1.0536904335021973} 08/30/2021 21:49:02 - INFO - __main__ - Step 47385: {'lr': 0.00039269001203631667, 'samples': 9097920, 'steps': 47384, 'loss/train': 1.4151859283447266} 08/30/2021 21:49:03 - INFO - __main__ - Step 47386: {'lr': 0.0003926856545466896, 'samples': 9098112, 'steps': 47385, 'loss/train': 0.9711772203445435} 08/30/2021 21:49:03 - INFO - __main__ - Step 47387: {'lr': 0.0003926812969927707, 'samples': 9098304, 'steps': 47386, 'loss/train': 1.7893248796463013} 08/30/2021 21:49:04 - INFO - __main__ - Step 47388: {'lr': 0.0003926769393745617, 'samples': 9098496, 'steps': 47387, 'loss/train': 1.298899531364441} 08/30/2021 21:49:04 - INFO - __main__ - Step 47389: {'lr': 0.0003926725816920648, 'samples': 9098688, 'steps': 47388, 'loss/train': 1.5883861780166626} 08/30/2021 21:49:06 - INFO - __main__ - Step 47390: {'lr': 0.0003926682239452817, 'samples': 9098880, 'steps': 47389, 'loss/train': 0.9644375443458557} 08/30/2021 21:49:06 - INFO - __main__ - Step 47391: {'lr': 0.00039266386613421455, 'samples': 9099072, 'steps': 47390, 'loss/train': 1.1020708084106445} 08/30/2021 21:49:07 - INFO - __main__ - Step 47392: {'lr': 0.00039265950825886523, 'samples': 9099264, 'steps': 47391, 'loss/train': 0.19431518018245697} 08/30/2021 21:49:07 - INFO - __main__ - Step 47393: {'lr': 0.00039265515031923585, 'samples': 9099456, 'steps': 47392, 'loss/train': 0.9279852509498596} 08/30/2021 21:49:07 - INFO - __main__ - Step 47394: {'lr': 0.0003926507923153282, 'samples': 9099648, 'steps': 47393, 'loss/train': 0.6067180633544922} 08/30/2021 21:49:08 - INFO - __main__ - Step 47395: {'lr': 0.0003926464342471443, 'samples': 9099840, 'steps': 47394, 'loss/train': 1.6401456594467163} 08/30/2021 21:49:09 - INFO - __main__ - Step 47396: {'lr': 0.00039264207611468607, 'samples': 9100032, 'steps': 47395, 'loss/train': 1.9120762348175049} 08/30/2021 21:49:10 - INFO - __main__ - Step 47397: {'lr': 0.00039263771791795554, 'samples': 9100224, 'steps': 47396, 'loss/train': 1.4913197755813599} 08/30/2021 21:49:10 - INFO - __main__ - Step 47398: {'lr': 0.0003926333596569547, 'samples': 9100416, 'steps': 47397, 'loss/train': 1.4576208591461182} 08/30/2021 21:49:10 - INFO - __main__ - Step 47399: {'lr': 0.00039262900133168544, 'samples': 9100608, 'steps': 47398, 'loss/train': 1.4530779123306274} 08/30/2021 21:49:11 - INFO - __main__ - Step 47400: {'lr': 0.0003926246429421497, 'samples': 9100800, 'steps': 47399, 'loss/train': 1.494839072227478} 08/30/2021 21:49:13 - INFO - __main__ - Step 47401: {'lr': 0.00039262028448834964, 'samples': 9100992, 'steps': 47400, 'loss/train': 1.1281623840332031} 08/30/2021 21:49:14 - INFO - __main__ - Step 47402: {'lr': 0.00039261592597028696, 'samples': 9101184, 'steps': 47401, 'loss/train': 1.382845163345337} 08/30/2021 21:49:14 - INFO - __main__ - Step 47403: {'lr': 0.0003926115673879638, 'samples': 9101376, 'steps': 47402, 'loss/train': 1.2787145376205444} 08/30/2021 21:49:14 - INFO - __main__ - Step 47404: {'lr': 0.000392607208741382, 'samples': 9101568, 'steps': 47403, 'loss/train': 1.7682346105575562} 08/30/2021 21:49:15 - INFO - __main__ - Step 47405: {'lr': 0.00039260285003054365, 'samples': 9101760, 'steps': 47404, 'loss/train': 1.6048250198364258} 08/30/2021 21:49:15 - INFO - __main__ - Step 47406: {'lr': 0.0003925984912554507, 'samples': 9101952, 'steps': 47405, 'loss/train': 1.9606859683990479} 08/30/2021 21:49:17 - INFO - __main__ - Step 47407: {'lr': 0.00039259413241610495, 'samples': 9102144, 'steps': 47406, 'loss/train': 1.7560627460479736} 08/30/2021 21:49:18 - INFO - __main__ - Step 47408: {'lr': 0.0003925897735125086, 'samples': 9102336, 'steps': 47407, 'loss/train': 1.170751690864563} 08/30/2021 21:49:18 - INFO - __main__ - Step 47409: {'lr': 0.00039258541454466344, 'samples': 9102528, 'steps': 47408, 'loss/train': 1.424579381942749} 08/30/2021 21:49:18 - INFO - __main__ - Step 47410: {'lr': 0.0003925810555125715, 'samples': 9102720, 'steps': 47409, 'loss/train': 0.12577219307422638} 08/30/2021 21:49:19 - INFO - __main__ - Step 47411: {'lr': 0.00039257669641623474, 'samples': 9102912, 'steps': 47410, 'loss/train': 0.04750821366906166} 08/30/2021 21:49:19 - INFO - __main__ - Step 47412: {'lr': 0.0003925723372556551, 'samples': 9103104, 'steps': 47411, 'loss/train': 0.2771010398864746} 08/30/2021 21:49:19 - INFO - __main__ - Step 47413: {'lr': 0.00039256797803083457, 'samples': 9103296, 'steps': 47412, 'loss/train': 1.927358865737915} 08/30/2021 21:49:22 - INFO - __main__ - Step 47414: {'lr': 0.00039256361874177517, 'samples': 9103488, 'steps': 47413, 'loss/train': 0.9046767354011536} 08/30/2021 21:49:22 - INFO - __main__ - Step 47415: {'lr': 0.0003925592593884787, 'samples': 9103680, 'steps': 47414, 'loss/train': 1.6944732666015625} 08/30/2021 21:49:22 - INFO - __main__ - Step 47416: {'lr': 0.0003925548999709473, 'samples': 9103872, 'steps': 47415, 'loss/train': 1.658400058746338} 08/30/2021 21:49:23 - INFO - __main__ - Step 47417: {'lr': 0.00039255054048918284, 'samples': 9104064, 'steps': 47416, 'loss/train': 1.794282078742981} 08/30/2021 21:49:23 - INFO - __main__ - Step 47418: {'lr': 0.00039254618094318726, 'samples': 9104256, 'steps': 47417, 'loss/train': 1.8073607683181763} 08/30/2021 21:49:23 - INFO - __main__ - Step 47419: {'lr': 0.0003925418213329627, 'samples': 9104448, 'steps': 47418, 'loss/train': 1.5887683629989624} 08/30/2021 21:49:24 - INFO - __main__ - Step 47420: {'lr': 0.0003925374616585109, 'samples': 9104640, 'steps': 47419, 'loss/train': 1.5960773229599} 08/30/2021 21:49:26 - INFO - __main__ - Step 47421: {'lr': 0.00039253310191983393, 'samples': 9104832, 'steps': 47420, 'loss/train': 1.1781538724899292} 08/30/2021 21:49:26 - INFO - __main__ - Step 47422: {'lr': 0.0003925287421169337, 'samples': 9105024, 'steps': 47421, 'loss/train': 0.784122109413147} 08/30/2021 21:49:27 - INFO - __main__ - Step 47423: {'lr': 0.00039252438224981237, 'samples': 9105216, 'steps': 47422, 'loss/train': 1.922245740890503} 08/30/2021 21:49:27 - INFO - __main__ - Step 47424: {'lr': 0.0003925200223184716, 'samples': 9105408, 'steps': 47423, 'loss/train': 0.8925718665122986} 08/30/2021 21:49:27 - INFO - __main__ - Step 47425: {'lr': 0.0003925156623229136, 'samples': 9105600, 'steps': 47424, 'loss/train': 1.8791476488113403} 08/30/2021 21:49:29 - INFO - __main__ - Step 47426: {'lr': 0.00039251130226314015, 'samples': 9105792, 'steps': 47425, 'loss/train': 1.4244506359100342} 08/30/2021 21:49:29 - INFO - __main__ - Step 47427: {'lr': 0.00039250694213915335, 'samples': 9105984, 'steps': 47426, 'loss/train': 1.4092888832092285} 08/30/2021 21:49:30 - INFO - __main__ - Step 47428: {'lr': 0.0003925025819509551, 'samples': 9106176, 'steps': 47427, 'loss/train': 1.921508550643921} 08/30/2021 21:49:30 - INFO - __main__ - Step 47429: {'lr': 0.00039249822169854745, 'samples': 9106368, 'steps': 47428, 'loss/train': 1.3877923488616943} 08/30/2021 21:49:31 - INFO - __main__ - Step 47430: {'lr': 0.0003924938613819322, 'samples': 9106560, 'steps': 47429, 'loss/train': 1.2928165197372437} 08/30/2021 21:49:32 - INFO - __main__ - Step 47431: {'lr': 0.0003924895010011115, 'samples': 9106752, 'steps': 47430, 'loss/train': 0.1274806261062622} 08/30/2021 21:49:33 - INFO - __main__ - Step 47432: {'lr': 0.0003924851405560872, 'samples': 9106944, 'steps': 47431, 'loss/train': 1.6685556173324585} 08/30/2021 21:49:33 - INFO - __main__ - Step 47433: {'lr': 0.00039248078004686126, 'samples': 9107136, 'steps': 47432, 'loss/train': 0.8660440444946289} 08/30/2021 21:49:34 - INFO - __main__ - Step 47434: {'lr': 0.00039247641947343575, 'samples': 9107328, 'steps': 47433, 'loss/train': 1.1961708068847656} 08/30/2021 21:49:34 - INFO - __main__ - Step 47435: {'lr': 0.0003924720588358126, 'samples': 9107520, 'steps': 47434, 'loss/train': 1.08945631980896} 08/30/2021 21:49:34 - INFO - __main__ - Step 47436: {'lr': 0.0003924676981339936, 'samples': 9107712, 'steps': 47435, 'loss/train': 1.3576847314834595} 08/30/2021 21:49:35 - INFO - __main__ - Step 47437: {'lr': 0.00039246333736798095, 'samples': 9107904, 'steps': 47436, 'loss/train': 2.1324586868286133} 08/30/2021 21:49:36 - INFO - __main__ - Step 47438: {'lr': 0.0003924589765377765, 'samples': 9108096, 'steps': 47437, 'loss/train': 1.4530651569366455} 08/30/2021 21:49:37 - INFO - __main__ - Step 47439: {'lr': 0.00039245461564338223, 'samples': 9108288, 'steps': 47438, 'loss/train': 2.4995298385620117} 08/30/2021 21:49:37 - INFO - __main__ - Step 47440: {'lr': 0.00039245025468480013, 'samples': 9108480, 'steps': 47439, 'loss/train': 1.6787322759628296} 08/30/2021 21:49:38 - INFO - __main__ - Step 47441: {'lr': 0.00039244589366203207, 'samples': 9108672, 'steps': 47440, 'loss/train': 0.7857919931411743} 08/30/2021 21:49:38 - INFO - __main__ - Step 47442: {'lr': 0.0003924415325750802, 'samples': 9108864, 'steps': 47441, 'loss/train': 0.9463993310928345} 08/30/2021 21:49:39 - INFO - __main__ - Step 47443: {'lr': 0.0003924371714239463, 'samples': 9109056, 'steps': 47442, 'loss/train': 1.5027315616607666} 08/30/2021 21:49:40 - INFO - __main__ - Step 47444: {'lr': 0.0003924328102086324, 'samples': 9109248, 'steps': 47443, 'loss/train': 1.0893957614898682} 08/30/2021 21:49:40 - INFO - __main__ - Step 47445: {'lr': 0.0003924284489291405, 'samples': 9109440, 'steps': 47444, 'loss/train': 1.009865403175354} 08/30/2021 21:49:41 - INFO - __main__ - Step 47446: {'lr': 0.00039242408758547256, 'samples': 9109632, 'steps': 47445, 'loss/train': 2.0451200008392334} 08/30/2021 21:49:41 - INFO - __main__ - Step 47447: {'lr': 0.0003924197261776304, 'samples': 9109824, 'steps': 47446, 'loss/train': 1.5461087226867676} 08/30/2021 21:49:43 - INFO - __main__ - Step 47448: {'lr': 0.0003924153647056163, 'samples': 9110016, 'steps': 47447, 'loss/train': 1.535399317741394} 08/30/2021 21:49:43 - INFO - __main__ - Step 47449: {'lr': 0.0003924110031694319, 'samples': 9110208, 'steps': 47448, 'loss/train': 1.4370900392532349} 08/30/2021 21:49:43 - INFO - __main__ - Step 47450: {'lr': 0.00039240664156907937, 'samples': 9110400, 'steps': 47449, 'loss/train': 1.9424941539764404} 08/30/2021 21:49:44 - INFO - __main__ - Step 47451: {'lr': 0.00039240227990456055, 'samples': 9110592, 'steps': 47450, 'loss/train': 1.3079520463943481} 08/30/2021 21:49:44 - INFO - __main__ - Step 47452: {'lr': 0.00039239791817587746, 'samples': 9110784, 'steps': 47451, 'loss/train': 1.511841058731079} 08/30/2021 21:49:44 - INFO - __main__ - Step 47453: {'lr': 0.0003923935563830321, 'samples': 9110976, 'steps': 47452, 'loss/train': 1.8246479034423828} 08/30/2021 21:49:46 - INFO - __main__ - Step 47454: {'lr': 0.0003923891945260264, 'samples': 9111168, 'steps': 47453, 'loss/train': 0.06469002366065979} 08/30/2021 21:49:47 - INFO - __main__ - Step 47455: {'lr': 0.00039238483260486235, 'samples': 9111360, 'steps': 47454, 'loss/train': 0.39675575494766235} 08/30/2021 21:49:47 - INFO - __main__ - Step 47456: {'lr': 0.0003923804706195418, 'samples': 9111552, 'steps': 47455, 'loss/train': 1.219374179840088} 08/30/2021 21:49:47 - INFO - __main__ - Step 47457: {'lr': 0.0003923761085700669, 'samples': 9111744, 'steps': 47456, 'loss/train': 0.9257020354270935} 08/30/2021 21:49:48 - INFO - __main__ - Step 47458: {'lr': 0.0003923717464564395, 'samples': 9111936, 'steps': 47457, 'loss/train': 1.6188582181930542} 08/30/2021 21:49:49 - INFO - __main__ - Step 47459: {'lr': 0.00039236738427866154, 'samples': 9112128, 'steps': 47458, 'loss/train': 1.765936017036438} 08/30/2021 21:49:49 - INFO - __main__ - Step 47460: {'lr': 0.000392363022036735, 'samples': 9112320, 'steps': 47459, 'loss/train': 1.5301679372787476} 08/30/2021 21:49:50 - INFO - __main__ - Step 47461: {'lr': 0.00039235865973066196, 'samples': 9112512, 'steps': 47460, 'loss/train': 1.359564185142517} 08/30/2021 21:49:50 - INFO - __main__ - Step 47462: {'lr': 0.00039235429736044435, 'samples': 9112704, 'steps': 47461, 'loss/train': 1.1371489763259888} 08/30/2021 21:49:51 - INFO - __main__ - Step 47463: {'lr': 0.00039234993492608404, 'samples': 9112896, 'steps': 47462, 'loss/train': 1.474984049797058} 08/30/2021 21:49:52 - INFO - __main__ - Step 47464: {'lr': 0.0003923455724275831, 'samples': 9113088, 'steps': 47463, 'loss/train': 0.7468206882476807} 08/30/2021 21:49:52 - INFO - __main__ - Step 47465: {'lr': 0.0003923412098649433, 'samples': 9113280, 'steps': 47464, 'loss/train': 1.3695276975631714} 08/30/2021 21:49:53 - INFO - __main__ - Step 47466: {'lr': 0.0003923368472381668, 'samples': 9113472, 'steps': 47465, 'loss/train': 1.4852293729782104} 08/30/2021 21:49:53 - INFO - __main__ - Step 47467: {'lr': 0.0003923324845472556, 'samples': 9113664, 'steps': 47466, 'loss/train': 1.7139065265655518} 08/30/2021 21:49:53 - INFO - __main__ - Step 47468: {'lr': 0.0003923281217922115, 'samples': 9113856, 'steps': 47467, 'loss/train': 2.0019984245300293} 08/30/2021 21:49:55 - INFO - __main__ - Step 47469: {'lr': 0.0003923237589730366, 'samples': 9114048, 'steps': 47468, 'loss/train': 0.5439435839653015} 08/30/2021 21:49:55 - INFO - __main__ - Step 47470: {'lr': 0.00039231939608973276, 'samples': 9114240, 'steps': 47469, 'loss/train': 0.8051151633262634} 08/30/2021 21:49:56 - INFO - __main__ - Step 47471: {'lr': 0.000392315033142302, 'samples': 9114432, 'steps': 47470, 'loss/train': 1.8148776292800903} 08/30/2021 21:49:56 - INFO - __main__ - Step 47472: {'lr': 0.0003923106701307463, 'samples': 9114624, 'steps': 47471, 'loss/train': 1.5005706548690796} 08/30/2021 21:49:56 - INFO - __main__ - Step 47473: {'lr': 0.0003923063070550676, 'samples': 9114816, 'steps': 47472, 'loss/train': 1.4210914373397827} 08/30/2021 21:49:58 - INFO - __main__ - Step 47474: {'lr': 0.00039230194391526784, 'samples': 9115008, 'steps': 47473, 'loss/train': 1.538997769355774} 08/30/2021 21:49:59 - INFO - __main__ - Step 47475: {'lr': 0.00039229758071134907, 'samples': 9115200, 'steps': 47474, 'loss/train': 1.7825133800506592} 08/30/2021 21:49:59 - INFO - __main__ - Step 47476: {'lr': 0.0003922932174433132, 'samples': 9115392, 'steps': 47475, 'loss/train': 0.8834695219993591} 08/30/2021 21:50:00 - INFO - __main__ - Step 47477: {'lr': 0.0003922888541111622, 'samples': 9115584, 'steps': 47476, 'loss/train': 1.6944807767868042} 08/30/2021 21:50:00 - INFO - __main__ - Step 47478: {'lr': 0.00039228449071489804, 'samples': 9115776, 'steps': 47477, 'loss/train': 1.2691766023635864} 08/30/2021 21:50:00 - INFO - __main__ - Step 47479: {'lr': 0.0003922801272545227, 'samples': 9115968, 'steps': 47478, 'loss/train': 1.378496766090393} 08/30/2021 21:50:02 - INFO - __main__ - Step 47480: {'lr': 0.000392275763730038, 'samples': 9116160, 'steps': 47479, 'loss/train': 1.267137050628662} 08/30/2021 21:50:02 - INFO - __main__ - Step 47481: {'lr': 0.00039227140014144615, 'samples': 9116352, 'steps': 47480, 'loss/train': 1.0980186462402344} 08/30/2021 21:50:03 - INFO - __main__ - Step 47482: {'lr': 0.00039226703648874905, 'samples': 9116544, 'steps': 47481, 'loss/train': 1.189841389656067} 08/30/2021 21:50:03 - INFO - __main__ - Step 47483: {'lr': 0.00039226267277194855, 'samples': 9116736, 'steps': 47482, 'loss/train': 1.4233750104904175} 08/30/2021 21:50:03 - INFO - __main__ - Step 47484: {'lr': 0.0003922583089910467, 'samples': 9116928, 'steps': 47483, 'loss/train': 1.0525566339492798} 08/30/2021 21:50:05 - INFO - __main__ - Step 47485: {'lr': 0.0003922539451460454, 'samples': 9117120, 'steps': 47484, 'loss/train': 1.0316088199615479} 08/30/2021 21:50:05 - INFO - __main__ - Step 47486: {'lr': 0.00039224958123694676, 'samples': 9117312, 'steps': 47485, 'loss/train': 1.5966614484786987} 08/30/2021 21:50:05 - INFO - __main__ - Step 47487: {'lr': 0.0003922452172637526, 'samples': 9117504, 'steps': 47486, 'loss/train': 1.7844959497451782} 08/30/2021 21:50:06 - INFO - __main__ - Step 47488: {'lr': 0.000392240853226465, 'samples': 9117696, 'steps': 47487, 'loss/train': 1.2453421354293823} 08/30/2021 21:50:06 - INFO - __main__ - Step 47489: {'lr': 0.0003922364891250858, 'samples': 9117888, 'steps': 47488, 'loss/train': 1.7250230312347412} 08/30/2021 21:50:08 - INFO - __main__ - Step 47490: {'lr': 0.00039223212495961704, 'samples': 9118080, 'steps': 47489, 'loss/train': 1.206486463546753} 08/30/2021 21:50:08 - INFO - __main__ - Step 47491: {'lr': 0.0003922277607300607, 'samples': 9118272, 'steps': 47490, 'loss/train': 0.9815263152122498} 08/30/2021 21:50:09 - INFO - __main__ - Step 47492: {'lr': 0.0003922233964364187, 'samples': 9118464, 'steps': 47491, 'loss/train': 1.0688601732254028} 08/30/2021 21:50:09 - INFO - __main__ - Step 47493: {'lr': 0.000392219032078693, 'samples': 9118656, 'steps': 47492, 'loss/train': 1.7482033967971802} 08/30/2021 21:50:09 - INFO - __main__ - Step 47494: {'lr': 0.0003922146676568856, 'samples': 9118848, 'steps': 47493, 'loss/train': 1.4080946445465088} 08/30/2021 21:50:11 - INFO - __main__ - Step 47495: {'lr': 0.0003922103031709986, 'samples': 9119040, 'steps': 47494, 'loss/train': 1.4170136451721191} 08/30/2021 21:50:11 - INFO - __main__ - Step 47496: {'lr': 0.0003922059386210337, 'samples': 9119232, 'steps': 47495, 'loss/train': 0.5779529809951782} 08/30/2021 21:50:11 - INFO - __main__ - Step 47497: {'lr': 0.0003922015740069931, 'samples': 9119424, 'steps': 47496, 'loss/train': 1.0202704668045044} 08/30/2021 21:50:12 - INFO - __main__ - Step 47498: {'lr': 0.0003921972093288786, 'samples': 9119616, 'steps': 47497, 'loss/train': 0.9841870069503784} 08/30/2021 21:50:12 - INFO - __main__ - Step 47499: {'lr': 0.00039219284458669217, 'samples': 9119808, 'steps': 47498, 'loss/train': 1.5301270484924316} 08/30/2021 21:50:14 - INFO - __main__ - Step 47500: {'lr': 0.00039218847978043594, 'samples': 9120000, 'steps': 47499, 'loss/train': 1.0793498754501343} 08/30/2021 21:50:14 - INFO - __main__ - Step 47501: {'lr': 0.00039218411491011176, 'samples': 9120192, 'steps': 47500, 'loss/train': 0.859450101852417} 08/30/2021 21:50:14 - INFO - __main__ - Step 47502: {'lr': 0.0003921797499757216, 'samples': 9120384, 'steps': 47501, 'loss/train': 1.2548826932907104} 08/30/2021 21:50:15 - INFO - __main__ - Step 47503: {'lr': 0.0003921753849772674, 'samples': 9120576, 'steps': 47502, 'loss/train': 0.47821664810180664} 08/30/2021 21:50:15 - INFO - __main__ - Step 47504: {'lr': 0.0003921710199147512, 'samples': 9120768, 'steps': 47503, 'loss/train': 1.3237571716308594} 08/30/2021 21:50:17 - INFO - __main__ - Step 47505: {'lr': 0.0003921666547881749, 'samples': 9120960, 'steps': 47504, 'loss/train': 0.6785144209861755} 08/30/2021 21:50:17 - INFO - __main__ - Step 47506: {'lr': 0.00039216228959754055, 'samples': 9121152, 'steps': 47505, 'loss/train': 2.1855690479278564} 08/30/2021 21:50:17 - INFO - __main__ - Step 47507: {'lr': 0.00039215792434285, 'samples': 9121344, 'steps': 47506, 'loss/train': 1.2324528694152832} 08/30/2021 21:50:18 - INFO - __main__ - Step 47508: {'lr': 0.00039215355902410534, 'samples': 9121536, 'steps': 47507, 'loss/train': 1.0141741037368774} 08/30/2021 21:50:18 - INFO - __main__ - Step 47509: {'lr': 0.0003921491936413085, 'samples': 9121728, 'steps': 47508, 'loss/train': 1.500723958015442} 08/30/2021 21:50:18 - INFO - __main__ - Step 47510: {'lr': 0.0003921448281944614, 'samples': 9121920, 'steps': 47509, 'loss/train': 1.2323713302612305} 08/30/2021 21:50:20 - INFO - __main__ - Step 47511: {'lr': 0.000392140462683566, 'samples': 9122112, 'steps': 47510, 'loss/train': 1.747552514076233} 08/30/2021 21:50:20 - INFO - __main__ - Step 47512: {'lr': 0.0003921360971086243, 'samples': 9122304, 'steps': 47511, 'loss/train': 1.82868492603302} 08/30/2021 21:50:21 - INFO - __main__ - Step 47513: {'lr': 0.0003921317314696383, 'samples': 9122496, 'steps': 47512, 'loss/train': 1.50871741771698} 08/30/2021 21:50:21 - INFO - __main__ - Step 47514: {'lr': 0.0003921273657666099, 'samples': 9122688, 'steps': 47513, 'loss/train': 1.6595972776412964} 08/30/2021 21:50:21 - INFO - __main__ - Step 47515: {'lr': 0.0003921229999995412, 'samples': 9122880, 'steps': 47514, 'loss/train': 0.7272273898124695} 08/30/2021 21:50:23 - INFO - __main__ - Step 47516: {'lr': 0.000392118634168434, 'samples': 9123072, 'steps': 47515, 'loss/train': 2.1457037925720215} 08/30/2021 21:50:23 - INFO - __main__ - Step 47517: {'lr': 0.00039211426827329035, 'samples': 9123264, 'steps': 47516, 'loss/train': 1.6039600372314453} 08/30/2021 21:50:24 - INFO - __main__ - Step 47518: {'lr': 0.0003921099023141121, 'samples': 9123456, 'steps': 47517, 'loss/train': 1.5681538581848145} 08/30/2021 21:50:24 - INFO - __main__ - Step 47519: {'lr': 0.0003921055362909015, 'samples': 9123648, 'steps': 47518, 'loss/train': 0.8581191897392273} 08/30/2021 21:50:24 - INFO - __main__ - Step 47520: {'lr': 0.0003921011702036602, 'samples': 9123840, 'steps': 47519, 'loss/train': 1.4746692180633545} 08/30/2021 21:50:26 - INFO - __main__ - Step 47521: {'lr': 0.00039209680405239035, 'samples': 9124032, 'steps': 47520, 'loss/train': 1.566706895828247} 08/30/2021 21:50:26 - INFO - __main__ - Step 47522: {'lr': 0.0003920924378370939, 'samples': 9124224, 'steps': 47521, 'loss/train': 1.1851613521575928} 08/30/2021 21:50:27 - INFO - __main__ - Step 47523: {'lr': 0.0003920880715577728, 'samples': 9124416, 'steps': 47522, 'loss/train': 1.1102629899978638} 08/30/2021 21:50:27 - INFO - __main__ - Step 47524: {'lr': 0.00039208370521442895, 'samples': 9124608, 'steps': 47523, 'loss/train': 1.5686856508255005} 08/30/2021 21:50:27 - INFO - __main__ - Step 47525: {'lr': 0.0003920793388070644, 'samples': 9124800, 'steps': 47524, 'loss/train': 0.8846790790557861} 08/30/2021 21:50:29 - INFO - __main__ - Step 47526: {'lr': 0.0003920749723356811, 'samples': 9124992, 'steps': 47525, 'loss/train': 1.4392623901367188} 08/30/2021 21:50:29 - INFO - __main__ - Step 47527: {'lr': 0.000392070605800281, 'samples': 9125184, 'steps': 47526, 'loss/train': 1.339270830154419} 08/30/2021 21:50:30 - INFO - __main__ - Step 47528: {'lr': 0.00039206623920086603, 'samples': 9125376, 'steps': 47527, 'loss/train': 1.602022647857666} 08/30/2021 21:50:30 - INFO - __main__ - Step 47529: {'lr': 0.0003920618725374383, 'samples': 9125568, 'steps': 47528, 'loss/train': 1.8743805885314941} 08/30/2021 21:50:30 - INFO - __main__ - Step 47530: {'lr': 0.00039205750580999964, 'samples': 9125760, 'steps': 47529, 'loss/train': 1.496177077293396} 08/30/2021 21:50:32 - INFO - __main__ - Step 47531: {'lr': 0.0003920531390185521, 'samples': 9125952, 'steps': 47530, 'loss/train': 1.705356240272522} 08/30/2021 21:50:33 - INFO - __main__ - Step 47532: {'lr': 0.00039204877216309755, 'samples': 9126144, 'steps': 47531, 'loss/train': 0.45835936069488525} 08/30/2021 21:50:33 - INFO - __main__ - Step 47533: {'lr': 0.00039204440524363805, 'samples': 9126336, 'steps': 47532, 'loss/train': 1.1870044469833374} 08/30/2021 21:50:34 - INFO - __main__ - Step 47534: {'lr': 0.0003920400382601755, 'samples': 9126528, 'steps': 47533, 'loss/train': 1.445563554763794} 08/30/2021 21:50:34 - INFO - __main__ - Step 47535: {'lr': 0.00039203567121271187, 'samples': 9126720, 'steps': 47534, 'loss/train': 0.9779070615768433} 08/30/2021 21:50:35 - INFO - __main__ - Step 47536: {'lr': 0.00039203130410124927, 'samples': 9126912, 'steps': 47535, 'loss/train': 1.7712767124176025} 08/30/2021 21:50:36 - INFO - __main__ - Step 47537: {'lr': 0.0003920269369257895, 'samples': 9127104, 'steps': 47536, 'loss/train': 0.8141536116600037} 08/30/2021 21:50:36 - INFO - __main__ - Step 47538: {'lr': 0.0003920225696863345, 'samples': 9127296, 'steps': 47537, 'loss/train': 1.448149561882019} 08/30/2021 21:50:37 - INFO - __main__ - Step 47539: {'lr': 0.00039201820238288644, 'samples': 9127488, 'steps': 47538, 'loss/train': 1.2583411931991577} 08/30/2021 21:50:37 - INFO - __main__ - Step 47540: {'lr': 0.00039201383501544706, 'samples': 9127680, 'steps': 47539, 'loss/train': 1.6331803798675537} 08/30/2021 21:50:39 - INFO - __main__ - Step 47541: {'lr': 0.00039200946758401856, 'samples': 9127872, 'steps': 47540, 'loss/train': 1.4651482105255127} 08/30/2021 21:50:39 - INFO - __main__ - Step 47542: {'lr': 0.00039200510008860273, 'samples': 9128064, 'steps': 47541, 'loss/train': 1.3782695531845093} 08/30/2021 21:50:39 - INFO - __main__ - Step 47543: {'lr': 0.0003920007325292016, 'samples': 9128256, 'steps': 47542, 'loss/train': 2.249802589416504} 08/30/2021 21:50:40 - INFO - __main__ - Step 47544: {'lr': 0.00039199636490581713, 'samples': 9128448, 'steps': 47543, 'loss/train': 1.2696423530578613} 08/30/2021 21:50:40 - INFO - __main__ - Step 47545: {'lr': 0.00039199199721845127, 'samples': 9128640, 'steps': 47544, 'loss/train': 0.7399950623512268} 08/30/2021 21:50:42 - INFO - __main__ - Step 47546: {'lr': 0.000391987629467106, 'samples': 9128832, 'steps': 47545, 'loss/train': 0.9999672770500183} 08/30/2021 21:50:42 - INFO - __main__ - Step 47547: {'lr': 0.00039198326165178335, 'samples': 9129024, 'steps': 47546, 'loss/train': 1.477217674255371} 08/30/2021 21:50:42 - INFO - __main__ - Step 47548: {'lr': 0.0003919788937724852, 'samples': 9129216, 'steps': 47547, 'loss/train': 1.8754897117614746} 08/30/2021 21:50:43 - INFO - __main__ - Step 47549: {'lr': 0.0003919745258292135, 'samples': 9129408, 'steps': 47548, 'loss/train': 4.169376850128174} 08/30/2021 21:50:43 - INFO - __main__ - Step 47550: {'lr': 0.00039197015782197034, 'samples': 9129600, 'steps': 47549, 'loss/train': 1.6852302551269531} 08/30/2021 21:50:43 - INFO - __main__ - Step 47551: {'lr': 0.0003919657897507576, 'samples': 9129792, 'steps': 47550, 'loss/train': 1.4910401105880737} 08/30/2021 21:50:45 - INFO - __main__ - Step 47552: {'lr': 0.0003919614216155772, 'samples': 9129984, 'steps': 47551, 'loss/train': 1.3738433122634888} 08/30/2021 21:50:45 - INFO - __main__ - Step 47553: {'lr': 0.0003919570534164313, 'samples': 9130176, 'steps': 47552, 'loss/train': 1.4206960201263428} 08/30/2021 21:50:46 - INFO - __main__ - Step 47554: {'lr': 0.0003919526851533216, 'samples': 9130368, 'steps': 47553, 'loss/train': 1.335051417350769} 08/30/2021 21:50:46 - INFO - __main__ - Step 47555: {'lr': 0.00039194831682625033, 'samples': 9130560, 'steps': 47554, 'loss/train': 1.690909504890442} 08/30/2021 21:50:46 - INFO - __main__ - Step 47556: {'lr': 0.0003919439484352193, 'samples': 9130752, 'steps': 47555, 'loss/train': 0.09721633791923523} 08/30/2021 21:50:48 - INFO - __main__ - Step 47557: {'lr': 0.00039193957998023057, 'samples': 9130944, 'steps': 47556, 'loss/train': 0.9456935524940491} 08/30/2021 21:50:48 - INFO - __main__ - Step 47558: {'lr': 0.000391935211461286, 'samples': 9131136, 'steps': 47557, 'loss/train': 0.6503803133964539} 08/30/2021 21:50:49 - INFO - __main__ - Step 47559: {'lr': 0.00039193084287838755, 'samples': 9131328, 'steps': 47558, 'loss/train': 0.7927486896514893} 08/30/2021 21:50:49 - INFO - __main__ - Step 47560: {'lr': 0.0003919264742315373, 'samples': 9131520, 'steps': 47559, 'loss/train': 1.5858039855957031} 08/30/2021 21:50:49 - INFO - __main__ - Step 47561: {'lr': 0.00039192210552073723, 'samples': 9131712, 'steps': 47560, 'loss/train': 1.0409817695617676} 08/30/2021 21:50:51 - INFO - __main__ - Step 47562: {'lr': 0.0003919177367459892, 'samples': 9131904, 'steps': 47561, 'loss/train': 1.0228266716003418} 08/30/2021 21:50:51 - INFO - __main__ - Step 47563: {'lr': 0.00039191336790729526, 'samples': 9132096, 'steps': 47562, 'loss/train': 1.468979001045227} 08/30/2021 21:50:52 - INFO - __main__ - Step 47564: {'lr': 0.00039190899900465727, 'samples': 9132288, 'steps': 47563, 'loss/train': 1.1165070533752441} 08/30/2021 21:50:52 - INFO - __main__ - Step 47565: {'lr': 0.0003919046300380773, 'samples': 9132480, 'steps': 47564, 'loss/train': 1.1435688734054565} 08/30/2021 21:50:52 - INFO - __main__ - Step 47566: {'lr': 0.00039190026100755735, 'samples': 9132672, 'steps': 47565, 'loss/train': 1.1976114511489868} 08/30/2021 21:50:54 - INFO - __main__ - Step 47567: {'lr': 0.00039189589191309927, 'samples': 9132864, 'steps': 47566, 'loss/train': 1.7406421899795532} 08/30/2021 21:50:54 - INFO - __main__ - Step 47568: {'lr': 0.00039189152275470514, 'samples': 9133056, 'steps': 47567, 'loss/train': 1.0698328018188477} 08/30/2021 21:50:55 - INFO - __main__ - Step 47569: {'lr': 0.0003918871535323769, 'samples': 9133248, 'steps': 47568, 'loss/train': 1.104062795639038} 08/30/2021 21:50:55 - INFO - __main__ - Step 47570: {'lr': 0.0003918827842461165, 'samples': 9133440, 'steps': 47569, 'loss/train': 1.4716874361038208} 08/30/2021 21:50:55 - INFO - __main__ - Step 47571: {'lr': 0.0003918784148959258, 'samples': 9133632, 'steps': 47570, 'loss/train': 1.5160268545150757} 08/30/2021 21:50:57 - INFO - __main__ - Step 47572: {'lr': 0.0003918740454818069, 'samples': 9133824, 'steps': 47571, 'loss/train': 1.2590101957321167} 08/30/2021 21:50:57 - INFO - __main__ - Step 47573: {'lr': 0.0003918696760037618, 'samples': 9134016, 'steps': 47572, 'loss/train': 1.2887803316116333} 08/30/2021 21:50:58 - INFO - __main__ - Step 47574: {'lr': 0.0003918653064617924, 'samples': 9134208, 'steps': 47573, 'loss/train': 1.6382392644882202} 08/30/2021 21:50:58 - INFO - __main__ - Step 47575: {'lr': 0.00039186093685590064, 'samples': 9134400, 'steps': 47574, 'loss/train': 0.8733863830566406} 08/30/2021 21:50:58 - INFO - __main__ - Step 47576: {'lr': 0.0003918565671860886, 'samples': 9134592, 'steps': 47575, 'loss/train': 1.272176742553711} 08/30/2021 21:51:00 - INFO - __main__ - Step 47577: {'lr': 0.00039185219745235816, 'samples': 9134784, 'steps': 47576, 'loss/train': 0.7759772539138794} 08/30/2021 21:51:00 - INFO - __main__ - Step 47578: {'lr': 0.0003918478276547113, 'samples': 9134976, 'steps': 47577, 'loss/train': 1.5864347219467163} 08/30/2021 21:51:01 - INFO - __main__ - Step 47579: {'lr': 0.00039184345779315, 'samples': 9135168, 'steps': 47578, 'loss/train': 0.9600334763526917} 08/30/2021 21:51:01 - INFO - __main__ - Step 47580: {'lr': 0.0003918390878676762, 'samples': 9135360, 'steps': 47579, 'loss/train': 1.842550277709961} 08/30/2021 21:51:01 - INFO - __main__ - Step 47581: {'lr': 0.00039183471787829194, 'samples': 9135552, 'steps': 47580, 'loss/train': 1.8136920928955078} 08/30/2021 21:51:02 - INFO - __main__ - Step 47582: {'lr': 0.0003918303478249991, 'samples': 9135744, 'steps': 47581, 'loss/train': 1.4065524339675903} 08/30/2021 21:51:04 - INFO - __main__ - Step 47583: {'lr': 0.0003918259777077997, 'samples': 9135936, 'steps': 47582, 'loss/train': 1.5654438734054565} 08/30/2021 21:51:04 - INFO - __main__ - Step 47584: {'lr': 0.00039182160752669577, 'samples': 9136128, 'steps': 47583, 'loss/train': 1.805586576461792} 08/30/2021 21:51:05 - INFO - __main__ - Step 47585: {'lr': 0.0003918172372816892, 'samples': 9136320, 'steps': 47584, 'loss/train': 1.0967366695404053} 08/30/2021 21:51:05 - INFO - __main__ - Step 47586: {'lr': 0.0003918128669727818, 'samples': 9136512, 'steps': 47585, 'loss/train': 1.576042890548706} 08/30/2021 21:51:05 - INFO - __main__ - Step 47587: {'lr': 0.00039180849659997593, 'samples': 9136704, 'steps': 47586, 'loss/train': 1.7267149686813354} 08/30/2021 21:51:07 - INFO - __main__ - Step 47588: {'lr': 0.00039180412616327323, 'samples': 9136896, 'steps': 47587, 'loss/train': 1.9029110670089722} 08/30/2021 21:51:07 - INFO - __main__ - Step 47589: {'lr': 0.00039179975566267585, 'samples': 9137088, 'steps': 47588, 'loss/train': 0.7890552878379822} 08/30/2021 21:51:08 - INFO - __main__ - Step 47590: {'lr': 0.00039179538509818556, 'samples': 9137280, 'steps': 47589, 'loss/train': 1.4764454364776611} 08/30/2021 21:51:08 - INFO - __main__ - Step 47591: {'lr': 0.0003917910144698046, 'samples': 9137472, 'steps': 47590, 'loss/train': 1.6669155359268188} 08/30/2021 21:51:08 - INFO - __main__ - Step 47592: {'lr': 0.0003917866437775347, 'samples': 9137664, 'steps': 47591, 'loss/train': 0.9721720218658447} 08/30/2021 21:51:10 - INFO - __main__ - Step 47593: {'lr': 0.000391782273021378, 'samples': 9137856, 'steps': 47592, 'loss/train': 0.14700405299663544} 08/30/2021 21:51:10 - INFO - __main__ - Step 47594: {'lr': 0.00039177790220133637, 'samples': 9138048, 'steps': 47593, 'loss/train': 2.0277597904205322} 08/30/2021 21:51:11 - INFO - __main__ - Step 47595: {'lr': 0.0003917735313174117, 'samples': 9138240, 'steps': 47594, 'loss/train': 1.2065784931182861} 08/30/2021 21:51:11 - INFO - __main__ - Step 47596: {'lr': 0.0003917691603696062, 'samples': 9138432, 'steps': 47595, 'loss/train': 1.2386913299560547} 08/30/2021 21:51:11 - INFO - __main__ - Step 47597: {'lr': 0.0003917647893579217, 'samples': 9138624, 'steps': 47596, 'loss/train': 1.1212928295135498} 08/30/2021 21:51:13 - INFO - __main__ - Step 47598: {'lr': 0.0003917604182823601, 'samples': 9138816, 'steps': 47597, 'loss/train': 2.062592029571533} 08/30/2021 21:51:13 - INFO - __main__ - Step 47599: {'lr': 0.00039175604714292346, 'samples': 9139008, 'steps': 47598, 'loss/train': 0.6993901133537292} 08/30/2021 21:51:14 - INFO - __main__ - Step 47600: {'lr': 0.00039175167593961377, 'samples': 9139200, 'steps': 47599, 'loss/train': 1.723766565322876} 08/30/2021 21:51:14 - INFO - __main__ - Step 47601: {'lr': 0.0003917473046724329, 'samples': 9139392, 'steps': 47600, 'loss/train': 1.776467204093933} 08/30/2021 21:51:14 - INFO - __main__ - Step 47602: {'lr': 0.000391742933341383, 'samples': 9139584, 'steps': 47601, 'loss/train': 1.4710078239440918} 08/30/2021 21:51:16 - INFO - __main__ - Step 47603: {'lr': 0.00039173856194646585, 'samples': 9139776, 'steps': 47602, 'loss/train': 0.7388753890991211} 08/30/2021 21:51:16 - INFO - __main__ - Step 47604: {'lr': 0.00039173419048768343, 'samples': 9139968, 'steps': 47603, 'loss/train': 1.710203766822815} 08/30/2021 21:51:17 - INFO - __main__ - Step 47605: {'lr': 0.0003917298189650378, 'samples': 9140160, 'steps': 47604, 'loss/train': 1.5066584348678589} 08/30/2021 21:51:17 - INFO - __main__ - Step 47606: {'lr': 0.00039172544737853097, 'samples': 9140352, 'steps': 47605, 'loss/train': 1.441505789756775} 08/30/2021 21:51:17 - INFO - __main__ - Step 47607: {'lr': 0.00039172107572816477, 'samples': 9140544, 'steps': 47606, 'loss/train': 1.1783387660980225} 08/30/2021 21:51:19 - INFO - __main__ - Step 47608: {'lr': 0.00039171670401394134, 'samples': 9140736, 'steps': 47607, 'loss/train': 1.3212872743606567} 08/30/2021 21:51:20 - INFO - __main__ - Step 47609: {'lr': 0.00039171233223586247, 'samples': 9140928, 'steps': 47608, 'loss/train': 0.5811963677406311} 08/30/2021 21:51:20 - INFO - __main__ - Step 47610: {'lr': 0.0003917079603939302, 'samples': 9141120, 'steps': 47609, 'loss/train': 1.2613604068756104} 08/30/2021 21:51:20 - INFO - __main__ - Step 47611: {'lr': 0.0003917035884881465, 'samples': 9141312, 'steps': 47610, 'loss/train': 0.19551026821136475} 08/30/2021 21:51:21 - INFO - __main__ - Step 47612: {'lr': 0.00039169921651851337, 'samples': 9141504, 'steps': 47611, 'loss/train': 0.7926893830299377} 08/30/2021 21:51:21 - INFO - __main__ - Step 47613: {'lr': 0.0003916948444850328, 'samples': 9141696, 'steps': 47612, 'loss/train': 1.088605523109436} 08/30/2021 21:51:23 - INFO - __main__ - Step 47614: {'lr': 0.0003916904723877067, 'samples': 9141888, 'steps': 47613, 'loss/train': 1.3022652864456177} 08/30/2021 21:51:23 - INFO - __main__ - Step 47615: {'lr': 0.000391686100226537, 'samples': 9142080, 'steps': 47614, 'loss/train': 1.158038854598999} 08/30/2021 21:51:23 - INFO - __main__ - Step 47616: {'lr': 0.00039168172800152577, 'samples': 9142272, 'steps': 47615, 'loss/train': 1.601486325263977} 08/30/2021 21:51:24 - INFO - __main__ - Step 47617: {'lr': 0.0003916773557126749, 'samples': 9142464, 'steps': 47616, 'loss/train': 1.1697089672088623} 08/30/2021 21:51:24 - INFO - __main__ - Step 47618: {'lr': 0.00039167298335998646, 'samples': 9142656, 'steps': 47617, 'loss/train': 1.6931227445602417} 08/30/2021 21:51:26 - INFO - __main__ - Step 47619: {'lr': 0.0003916686109434624, 'samples': 9142848, 'steps': 47618, 'loss/train': 1.5393420457839966} 08/30/2021 21:51:26 - INFO - __main__ - Step 47620: {'lr': 0.00039166423846310463, 'samples': 9143040, 'steps': 47619, 'loss/train': 1.480875849723816} 08/30/2021 21:51:26 - INFO - __main__ - Step 47621: {'lr': 0.00039165986591891506, 'samples': 9143232, 'steps': 47620, 'loss/train': 0.6889795064926147} 08/30/2021 21:51:27 - INFO - __main__ - Step 47622: {'lr': 0.0003916554933108958, 'samples': 9143424, 'steps': 47621, 'loss/train': 1.7952052354812622} 08/30/2021 21:51:27 - INFO - __main__ - Step 47623: {'lr': 0.00039165112063904874, 'samples': 9143616, 'steps': 47622, 'loss/train': 1.2486134767532349} 08/30/2021 21:51:29 - INFO - __main__ - Step 47624: {'lr': 0.0003916467479033759, 'samples': 9143808, 'steps': 47623, 'loss/train': 1.7592450380325317} 08/30/2021 21:51:29 - INFO - __main__ - Step 47625: {'lr': 0.00039164237510387915, 'samples': 9144000, 'steps': 47624, 'loss/train': 1.065859317779541} 08/30/2021 21:51:29 - INFO - __main__ - Step 47626: {'lr': 0.0003916380022405606, 'samples': 9144192, 'steps': 47625, 'loss/train': 1.2433457374572754} 08/30/2021 21:51:30 - INFO - __main__ - Step 47627: {'lr': 0.0003916336293134222, 'samples': 9144384, 'steps': 47626, 'loss/train': 1.419934868812561} 08/30/2021 21:51:30 - INFO - __main__ - Step 47628: {'lr': 0.0003916292563224657, 'samples': 9144576, 'steps': 47627, 'loss/train': 1.0608665943145752} 08/30/2021 21:51:32 - INFO - __main__ - Step 47629: {'lr': 0.00039162488326769334, 'samples': 9144768, 'steps': 47628, 'loss/train': 1.278180480003357} 08/30/2021 21:51:32 - INFO - __main__ - Step 47630: {'lr': 0.00039162051014910706, 'samples': 9144960, 'steps': 47629, 'loss/train': 1.1645411252975464} 08/30/2021 21:51:32 - INFO - __main__ - Step 47631: {'lr': 0.0003916161369667087, 'samples': 9145152, 'steps': 47630, 'loss/train': 1.5614615678787231} 08/30/2021 21:51:33 - INFO - __main__ - Step 47632: {'lr': 0.0003916117637205003, 'samples': 9145344, 'steps': 47631, 'loss/train': 1.0071594715118408} 08/30/2021 21:51:33 - INFO - __main__ - Step 47633: {'lr': 0.00039160739041048376, 'samples': 9145536, 'steps': 47632, 'loss/train': 1.1946840286254883} 08/30/2021 21:51:35 - INFO - __main__ - Step 47634: {'lr': 0.0003916030170366612, 'samples': 9145728, 'steps': 47633, 'loss/train': 0.9085675477981567} 08/30/2021 21:51:36 - INFO - __main__ - Step 47635: {'lr': 0.0003915986435990345, 'samples': 9145920, 'steps': 47634, 'loss/train': 1.7320348024368286} 08/30/2021 21:51:36 - INFO - __main__ - Step 47636: {'lr': 0.0003915942700976056, 'samples': 9146112, 'steps': 47635, 'loss/train': 1.090275764465332} 08/30/2021 21:51:36 - INFO - __main__ - Step 47637: {'lr': 0.0003915898965323765, 'samples': 9146304, 'steps': 47636, 'loss/train': 0.6358849406242371} 08/30/2021 21:51:37 - INFO - __main__ - Step 47638: {'lr': 0.00039158552290334927, 'samples': 9146496, 'steps': 47637, 'loss/train': 1.4608738422393799} 08/30/2021 21:51:38 - INFO - __main__ - Step 47639: {'lr': 0.00039158114921052567, 'samples': 9146688, 'steps': 47638, 'loss/train': 1.7298426628112793} 08/30/2021 21:51:39 - INFO - __main__ - Step 47640: {'lr': 0.0003915767754539078, 'samples': 9146880, 'steps': 47639, 'loss/train': 1.4851280450820923} 08/30/2021 21:51:39 - INFO - __main__ - Step 47641: {'lr': 0.0003915724016334977, 'samples': 9147072, 'steps': 47640, 'loss/train': 1.4141086339950562} 08/30/2021 21:51:39 - INFO - __main__ - Step 47642: {'lr': 0.00039156802774929723, 'samples': 9147264, 'steps': 47641, 'loss/train': 1.5010415315628052} 08/30/2021 21:51:40 - INFO - __main__ - Step 47643: {'lr': 0.00039156365380130844, 'samples': 9147456, 'steps': 47642, 'loss/train': 1.7737804651260376} 08/30/2021 21:51:42 - INFO - __main__ - Step 47644: {'lr': 0.00039155927978953316, 'samples': 9147648, 'steps': 47643, 'loss/train': 1.9736300706863403} 08/30/2021 21:51:42 - INFO - __main__ - Step 47645: {'lr': 0.00039155490571397345, 'samples': 9147840, 'steps': 47644, 'loss/train': 1.2133373022079468} 08/30/2021 21:51:43 - INFO - __main__ - Step 47646: {'lr': 0.0003915505315746313, 'samples': 9148032, 'steps': 47645, 'loss/train': 2.050436496734619} 08/30/2021 21:51:43 - INFO - __main__ - Step 47647: {'lr': 0.00039154615737150867, 'samples': 9148224, 'steps': 47646, 'loss/train': 0.4955146610736847} 08/30/2021 21:51:43 - INFO - __main__ - Step 47648: {'lr': 0.00039154178310460755, 'samples': 9148416, 'steps': 47647, 'loss/train': 2.5190417766571045} 08/30/2021 21:51:44 - INFO - __main__ - Step 47649: {'lr': 0.00039153740877392987, 'samples': 9148608, 'steps': 47648, 'loss/train': 1.6596466302871704} 08/30/2021 21:51:45 - INFO - __main__ - Step 47650: {'lr': 0.0003915330343794777, 'samples': 9148800, 'steps': 47649, 'loss/train': 1.7659639120101929} 08/30/2021 21:51:46 - INFO - __main__ - Step 47651: {'lr': 0.0003915286599212529, 'samples': 9148992, 'steps': 47650, 'loss/train': 1.4008673429489136} 08/30/2021 21:51:46 - INFO - __main__ - Step 47652: {'lr': 0.0003915242853992573, 'samples': 9149184, 'steps': 47651, 'loss/train': 1.771010398864746} 08/30/2021 21:51:46 - INFO - __main__ - Step 47653: {'lr': 0.0003915199108134932, 'samples': 9149376, 'steps': 47652, 'loss/train': 0.19851015508174896} 08/30/2021 21:51:47 - INFO - __main__ - Step 47654: {'lr': 0.00039151553616396234, 'samples': 9149568, 'steps': 47653, 'loss/train': 1.6640305519104004} 08/30/2021 21:51:49 - INFO - __main__ - Step 47655: {'lr': 0.0003915111614506668, 'samples': 9149760, 'steps': 47654, 'loss/train': 1.647017478942871} 08/30/2021 21:51:49 - INFO - __main__ - Step 47656: {'lr': 0.0003915067866736085, 'samples': 9149952, 'steps': 47655, 'loss/train': 0.43213528394699097} 08/30/2021 21:51:50 - INFO - __main__ - Step 47657: {'lr': 0.0003915024118327895, 'samples': 9150144, 'steps': 47656, 'loss/train': 1.7160296440124512} 08/30/2021 21:51:50 - INFO - __main__ - Step 47658: {'lr': 0.0003914980369282116, 'samples': 9150336, 'steps': 47657, 'loss/train': 1.2589799165725708} 08/30/2021 21:51:50 - INFO - __main__ - Step 47659: {'lr': 0.0003914936619598769, 'samples': 9150528, 'steps': 47658, 'loss/train': 1.67231285572052} 08/30/2021 21:51:51 - INFO - __main__ - Step 47660: {'lr': 0.0003914892869277873, 'samples': 9150720, 'steps': 47659, 'loss/train': 0.037424180656671524} 08/30/2021 21:51:52 - INFO - __main__ - Step 47661: {'lr': 0.0003914849118319449, 'samples': 9150912, 'steps': 47660, 'loss/train': 0.0350780114531517} 08/30/2021 21:51:52 - INFO - __main__ - Step 47662: {'lr': 0.0003914805366723515, 'samples': 9151104, 'steps': 47661, 'loss/train': 1.2098432779312134} 08/30/2021 21:51:53 - INFO - __main__ - Step 47663: {'lr': 0.0003914761614490092, 'samples': 9151296, 'steps': 47662, 'loss/train': 1.0824904441833496} 08/30/2021 21:51:53 - INFO - __main__ - Step 47664: {'lr': 0.0003914717861619199, 'samples': 9151488, 'steps': 47663, 'loss/train': 1.6083405017852783} 08/30/2021 21:51:53 - INFO - __main__ - Step 47665: {'lr': 0.00039146741081108567, 'samples': 9151680, 'steps': 47664, 'loss/train': 1.360947608947754} 08/30/2021 21:51:55 - INFO - __main__ - Step 47666: {'lr': 0.0003914630353965083, 'samples': 9151872, 'steps': 47665, 'loss/train': 1.2947280406951904} 08/30/2021 21:51:56 - INFO - __main__ - Step 47667: {'lr': 0.00039145865991818994, 'samples': 9152064, 'steps': 47666, 'loss/train': 0.07312767207622528} 08/30/2021 21:51:56 - INFO - __main__ - Step 47668: {'lr': 0.00039145428437613246, 'samples': 9152256, 'steps': 47667, 'loss/train': 1.3473976850509644} 08/30/2021 21:51:56 - INFO - __main__ - Step 47669: {'lr': 0.0003914499087703379, 'samples': 9152448, 'steps': 47668, 'loss/train': 1.1242252588272095} 08/30/2021 21:51:57 - INFO - __main__ - Step 47670: {'lr': 0.00039144553310080816, 'samples': 9152640, 'steps': 47669, 'loss/train': 1.4932323694229126} 08/30/2021 21:51:58 - INFO - __main__ - Step 47671: {'lr': 0.0003914411573675453, 'samples': 9152832, 'steps': 47670, 'loss/train': 1.550141453742981} 08/30/2021 21:51:59 - INFO - __main__ - Step 47672: {'lr': 0.0003914367815705511, 'samples': 9153024, 'steps': 47671, 'loss/train': 1.6797983646392822} 08/30/2021 21:51:59 - INFO - __main__ - Step 47673: {'lr': 0.00039143240570982776, 'samples': 9153216, 'steps': 47672, 'loss/train': 0.8465274572372437} 08/30/2021 21:51:59 - INFO - __main__ - Step 47674: {'lr': 0.00039142802978537716, 'samples': 9153408, 'steps': 47673, 'loss/train': 1.4265611171722412} 08/30/2021 21:52:00 - INFO - __main__ - Step 47675: {'lr': 0.00039142365379720123, 'samples': 9153600, 'steps': 47674, 'loss/train': 0.9644783139228821} 08/30/2021 21:52:02 - INFO - __main__ - Step 47676: {'lr': 0.0003914192777453021, 'samples': 9153792, 'steps': 47675, 'loss/train': 1.1561638116836548} 08/30/2021 21:52:02 - INFO - __main__ - Step 47677: {'lr': 0.00039141490162968154, 'samples': 9153984, 'steps': 47676, 'loss/train': 1.2505598068237305} 08/30/2021 21:52:02 - INFO - __main__ - Step 47678: {'lr': 0.0003914105254503416, 'samples': 9154176, 'steps': 47677, 'loss/train': 0.14060133695602417} 08/30/2021 21:52:03 - INFO - __main__ - Step 47679: {'lr': 0.00039140614920728424, 'samples': 9154368, 'steps': 47678, 'loss/train': 1.32106614112854} 08/30/2021 21:52:03 - INFO - __main__ - Step 47680: {'lr': 0.0003914017729005115, 'samples': 9154560, 'steps': 47679, 'loss/train': 1.5116673707962036} 08/30/2021 21:52:05 - INFO - __main__ - Step 47681: {'lr': 0.00039139739653002527, 'samples': 9154752, 'steps': 47680, 'loss/train': 1.3136156797409058} 08/30/2021 21:52:05 - INFO - __main__ - Step 47682: {'lr': 0.00039139302009582753, 'samples': 9154944, 'steps': 47681, 'loss/train': 1.2316099405288696} 08/30/2021 21:52:06 - INFO - __main__ - Step 47683: {'lr': 0.00039138864359792035, 'samples': 9155136, 'steps': 47682, 'loss/train': 1.121056079864502} 08/30/2021 21:52:06 - INFO - __main__ - Step 47684: {'lr': 0.0003913842670363056, 'samples': 9155328, 'steps': 47683, 'loss/train': 0.18311218917369843} 08/30/2021 21:52:06 - INFO - __main__ - Step 47685: {'lr': 0.0003913798904109853, 'samples': 9155520, 'steps': 47684, 'loss/train': 0.2778708338737488} 08/30/2021 21:52:07 - INFO - __main__ - Step 47686: {'lr': 0.0003913755137219614, 'samples': 9155712, 'steps': 47685, 'loss/train': 1.6655666828155518} 08/30/2021 21:52:08 - INFO - __main__ - Step 47687: {'lr': 0.00039137113696923587, 'samples': 9155904, 'steps': 47686, 'loss/train': 0.5548986792564392} 08/30/2021 21:52:09 - INFO - __main__ - Step 47688: {'lr': 0.00039136676015281063, 'samples': 9156096, 'steps': 47687, 'loss/train': 1.1955080032348633} 08/30/2021 21:52:09 - INFO - __main__ - Step 47689: {'lr': 0.00039136238327268776, 'samples': 9156288, 'steps': 47688, 'loss/train': 1.114600419998169} 08/30/2021 21:52:09 - INFO - __main__ - Step 47690: {'lr': 0.0003913580063288692, 'samples': 9156480, 'steps': 47689, 'loss/train': 1.1117278337478638} 08/30/2021 21:52:10 - INFO - __main__ - Step 47691: {'lr': 0.0003913536293213569, 'samples': 9156672, 'steps': 47690, 'loss/train': 1.5939730405807495} 08/30/2021 21:52:10 - INFO - __main__ - Step 47692: {'lr': 0.00039134925225015277, 'samples': 9156864, 'steps': 47691, 'loss/train': 1.0508226156234741} 08/30/2021 21:52:12 - INFO - __main__ - Step 47693: {'lr': 0.0003913448751152589, 'samples': 9157056, 'steps': 47692, 'loss/train': 2.471090078353882} 08/30/2021 21:52:12 - INFO - __main__ - Step 47694: {'lr': 0.0003913404979166772, 'samples': 9157248, 'steps': 47693, 'loss/train': 1.124953269958496} 08/30/2021 21:52:13 - INFO - __main__ - Step 47695: {'lr': 0.00039133612065440964, 'samples': 9157440, 'steps': 47694, 'loss/train': 1.1248496770858765} 08/30/2021 21:52:13 - INFO - __main__ - Step 47696: {'lr': 0.0003913317433284582, 'samples': 9157632, 'steps': 47695, 'loss/train': 1.6754659414291382} 08/30/2021 21:52:13 - INFO - __main__ - Step 47697: {'lr': 0.0003913273659388249, 'samples': 9157824, 'steps': 47696, 'loss/train': 1.3552273511886597} 08/30/2021 21:52:15 - INFO - __main__ - Step 47698: {'lr': 0.0003913229884855117, 'samples': 9158016, 'steps': 47697, 'loss/train': 2.4169790744781494} 08/30/2021 21:52:16 - INFO - __main__ - Step 47699: {'lr': 0.00039131861096852044, 'samples': 9158208, 'steps': 47698, 'loss/train': 1.438448429107666} 08/30/2021 21:52:16 - INFO - __main__ - Step 47700: {'lr': 0.0003913142333878533, 'samples': 9158400, 'steps': 47699, 'loss/train': 1.4683477878570557} 08/30/2021 21:52:16 - INFO - __main__ - Step 47701: {'lr': 0.0003913098557435121, 'samples': 9158592, 'steps': 47700, 'loss/train': 1.1579670906066895} 08/30/2021 21:52:17 - INFO - __main__ - Step 47702: {'lr': 0.00039130547803549877, 'samples': 9158784, 'steps': 47701, 'loss/train': 0.5222880244255066} 08/30/2021 21:52:18 - INFO - __main__ - Step 47703: {'lr': 0.00039130110026381547, 'samples': 9158976, 'steps': 47702, 'loss/train': 1.1332464218139648} 08/30/2021 21:52:18 - INFO - __main__ - Step 47704: {'lr': 0.00039129672242846407, 'samples': 9159168, 'steps': 47703, 'loss/train': 1.3162339925765991} 08/30/2021 21:52:19 - INFO - __main__ - Step 47705: {'lr': 0.0003912923445294465, 'samples': 9159360, 'steps': 47704, 'loss/train': 1.6958369016647339} 08/30/2021 21:52:19 - INFO - __main__ - Step 47706: {'lr': 0.00039128796656676487, 'samples': 9159552, 'steps': 47705, 'loss/train': 1.4678961038589478} 08/30/2021 21:52:20 - INFO - __main__ - Step 47707: {'lr': 0.000391283588540421, 'samples': 9159744, 'steps': 47706, 'loss/train': 1.2647621631622314} 08/30/2021 21:52:20 - INFO - __main__ - Step 47708: {'lr': 0.00039127921045041693, 'samples': 9159936, 'steps': 47707, 'loss/train': 1.7813242673873901} 08/30/2021 21:52:22 - INFO - __main__ - Step 47709: {'lr': 0.00039127483229675457, 'samples': 9160128, 'steps': 47708, 'loss/train': 1.9884852170944214} 08/30/2021 21:52:22 - INFO - __main__ - Step 47710: {'lr': 0.0003912704540794361, 'samples': 9160320, 'steps': 47709, 'loss/train': 1.2117905616760254} 08/30/2021 21:52:22 - INFO - __main__ - Step 47711: {'lr': 0.0003912660757984632, 'samples': 9160512, 'steps': 47710, 'loss/train': 2.0725977420806885} 08/30/2021 21:52:23 - INFO - __main__ - Step 47712: {'lr': 0.00039126169745383807, 'samples': 9160704, 'steps': 47711, 'loss/train': 1.0492584705352783} 08/30/2021 21:52:23 - INFO - __main__ - Step 47713: {'lr': 0.00039125731904556254, 'samples': 9160896, 'steps': 47712, 'loss/train': 1.644363284111023} 08/30/2021 21:52:25 - INFO - __main__ - Step 47714: {'lr': 0.0003912529405736387, 'samples': 9161088, 'steps': 47713, 'loss/train': 1.2478951215744019} 08/30/2021 21:52:25 - INFO - __main__ - Step 47715: {'lr': 0.00039124856203806834, 'samples': 9161280, 'steps': 47714, 'loss/train': 1.6116446256637573} 08/30/2021 21:52:26 - INFO - __main__ - Step 47716: {'lr': 0.0003912441834388537, 'samples': 9161472, 'steps': 47715, 'loss/train': 0.12646691501140594} 08/30/2021 21:52:26 - INFO - __main__ - Step 47717: {'lr': 0.00039123980477599664, 'samples': 9161664, 'steps': 47716, 'loss/train': 1.5476903915405273} 08/30/2021 21:52:26 - INFO - __main__ - Step 47718: {'lr': 0.00039123542604949904, 'samples': 9161856, 'steps': 47717, 'loss/train': 0.11959554255008698} 08/30/2021 21:52:28 - INFO - __main__ - Step 47719: {'lr': 0.0003912310472593629, 'samples': 9162048, 'steps': 47718, 'loss/train': 1.5829530954360962} 08/30/2021 21:52:29 - INFO - __main__ - Step 47720: {'lr': 0.0003912266684055902, 'samples': 9162240, 'steps': 47719, 'loss/train': 1.357043743133545} 08/30/2021 21:52:29 - INFO - __main__ - Step 47721: {'lr': 0.000391222289488183, 'samples': 9162432, 'steps': 47720, 'loss/train': 1.4404535293579102} 08/30/2021 21:52:29 - INFO - __main__ - Step 47722: {'lr': 0.00039121791050714317, 'samples': 9162624, 'steps': 47721, 'loss/train': 1.5500365495681763} 08/30/2021 21:52:30 - INFO - __main__ - Step 47723: {'lr': 0.0003912135314624728, 'samples': 9162816, 'steps': 47722, 'loss/train': 1.1916786432266235} 08/30/2021 21:52:30 - INFO - __main__ - Step 47724: {'lr': 0.00039120915235417377, 'samples': 9163008, 'steps': 47723, 'loss/train': 1.1242374181747437} 08/30/2021 21:52:32 - INFO - __main__ - Step 47725: {'lr': 0.0003912047731822481, 'samples': 9163200, 'steps': 47724, 'loss/train': 2.36653470993042} 08/30/2021 21:52:32 - INFO - __main__ - Step 47726: {'lr': 0.0003912003939466977, 'samples': 9163392, 'steps': 47725, 'loss/train': 1.5357462167739868} 08/30/2021 21:52:32 - INFO - __main__ - Step 47727: {'lr': 0.0003911960146475245, 'samples': 9163584, 'steps': 47726, 'loss/train': 1.4503769874572754} 08/30/2021 21:52:33 - INFO - __main__ - Step 47728: {'lr': 0.0003911916352847307, 'samples': 9163776, 'steps': 47727, 'loss/train': 1.131748080253601} 08/30/2021 21:52:33 - INFO - __main__ - Step 47729: {'lr': 0.0003911872558583181, 'samples': 9163968, 'steps': 47728, 'loss/train': 2.0050408840179443} 08/30/2021 21:52:35 - INFO - __main__ - Step 47730: {'lr': 0.00039118287636828866, 'samples': 9164160, 'steps': 47729, 'loss/train': 1.6159602403640747} 08/30/2021 21:52:35 - INFO - __main__ - Step 47731: {'lr': 0.0003911784968146444, 'samples': 9164352, 'steps': 47730, 'loss/train': 1.4069621562957764} 08/30/2021 21:52:35 - INFO - __main__ - Step 47732: {'lr': 0.00039117411719738726, 'samples': 9164544, 'steps': 47731, 'loss/train': 1.5779651403427124} 08/30/2021 21:52:36 - INFO - __main__ - Step 47733: {'lr': 0.0003911697375165193, 'samples': 9164736, 'steps': 47732, 'loss/train': 0.6587130427360535} 08/30/2021 21:52:36 - INFO - __main__ - Step 47734: {'lr': 0.00039116535777204237, 'samples': 9164928, 'steps': 47733, 'loss/train': 0.37427887320518494} 08/30/2021 21:52:36 - INFO - __main__ - Step 47735: {'lr': 0.00039116097796395856, 'samples': 9165120, 'steps': 47734, 'loss/train': 0.9871906638145447} 08/30/2021 21:52:38 - INFO - __main__ - Step 47736: {'lr': 0.00039115659809226975, 'samples': 9165312, 'steps': 47735, 'loss/train': 1.377522349357605} 08/30/2021 21:52:39 - INFO - __main__ - Step 47737: {'lr': 0.00039115221815697797, 'samples': 9165504, 'steps': 47736, 'loss/train': 0.12300369888544083} 08/30/2021 21:52:39 - INFO - __main__ - Step 47738: {'lr': 0.00039114783815808526, 'samples': 9165696, 'steps': 47737, 'loss/train': 1.6736088991165161} 08/30/2021 21:52:39 - INFO - __main__ - Step 47739: {'lr': 0.0003911434580955934, 'samples': 9165888, 'steps': 47738, 'loss/train': 0.9321932792663574} 08/30/2021 21:52:40 - INFO - __main__ - Step 47740: {'lr': 0.00039113907796950453, 'samples': 9166080, 'steps': 47739, 'loss/train': 1.7272741794586182} 08/30/2021 21:52:41 - INFO - __main__ - Step 47741: {'lr': 0.0003911346977798206, 'samples': 9166272, 'steps': 47740, 'loss/train': 0.4666619300842285} 08/30/2021 21:52:42 - INFO - __main__ - Step 47742: {'lr': 0.0003911303175265435, 'samples': 9166464, 'steps': 47741, 'loss/train': 1.4512208700180054} 08/30/2021 21:52:42 - INFO - __main__ - Step 47743: {'lr': 0.00039112593720967524, 'samples': 9166656, 'steps': 47742, 'loss/train': 1.0627355575561523} 08/30/2021 21:52:42 - INFO - __main__ - Step 47744: {'lr': 0.00039112155682921785, 'samples': 9166848, 'steps': 47743, 'loss/train': 1.1207740306854248} 08/30/2021 21:52:43 - INFO - __main__ - Step 47745: {'lr': 0.00039111717638517325, 'samples': 9167040, 'steps': 47744, 'loss/train': 0.9456784129142761} 08/30/2021 21:52:45 - INFO - __main__ - Step 47746: {'lr': 0.00039111279587754344, 'samples': 9167232, 'steps': 47745, 'loss/train': 1.540494441986084} 08/30/2021 21:52:45 - INFO - __main__ - Step 47747: {'lr': 0.0003911084153063303, 'samples': 9167424, 'steps': 47746, 'loss/train': 1.6111749410629272} 08/30/2021 21:52:46 - INFO - __main__ - Step 47748: {'lr': 0.000391104034671536, 'samples': 9167616, 'steps': 47747, 'loss/train': 1.0142439603805542} 08/30/2021 21:52:46 - INFO - __main__ - Step 47749: {'lr': 0.00039109965397316236, 'samples': 9167808, 'steps': 47748, 'loss/train': 1.4544976949691772} 08/30/2021 21:52:46 - INFO - __main__ - Step 47750: {'lr': 0.0003910952732112114, 'samples': 9168000, 'steps': 47749, 'loss/train': 1.2413040399551392} 08/30/2021 21:52:48 - INFO - __main__ - Step 47751: {'lr': 0.00039109089238568507, 'samples': 9168192, 'steps': 47750, 'loss/train': 1.8442610502243042} 08/30/2021 21:52:49 - INFO - __main__ - Step 47752: {'lr': 0.00039108651149658534, 'samples': 9168384, 'steps': 47751, 'loss/train': 1.941083312034607} 08/30/2021 21:52:49 - INFO - __main__ - Step 47753: {'lr': 0.0003910821305439143, 'samples': 9168576, 'steps': 47752, 'loss/train': 0.8489578366279602} 08/30/2021 21:52:49 - INFO - __main__ - Step 47754: {'lr': 0.00039107774952767374, 'samples': 9168768, 'steps': 47753, 'loss/train': 0.9137014746665955} 08/30/2021 21:52:50 - INFO - __main__ - Step 47755: {'lr': 0.0003910733684478657, 'samples': 9168960, 'steps': 47754, 'loss/train': 1.9159895181655884} 08/30/2021 21:52:51 - INFO - __main__ - Step 47756: {'lr': 0.00039106898730449223, 'samples': 9169152, 'steps': 47755, 'loss/train': 1.085327386856079} 08/30/2021 21:52:52 - INFO - __main__ - Step 47757: {'lr': 0.0003910646060975553, 'samples': 9169344, 'steps': 47756, 'loss/train': 1.554229974746704} 08/30/2021 21:52:52 - INFO - __main__ - Step 47758: {'lr': 0.00039106022482705675, 'samples': 9169536, 'steps': 47757, 'loss/train': 1.5550178289413452} 08/30/2021 21:52:52 - INFO - __main__ - Step 47759: {'lr': 0.0003910558434929987, 'samples': 9169728, 'steps': 47758, 'loss/train': 1.4158895015716553} 08/30/2021 21:52:53 - INFO - __main__ - Step 47760: {'lr': 0.000391051462095383, 'samples': 9169920, 'steps': 47759, 'loss/train': 1.0833162069320679} 08/30/2021 21:52:53 - INFO - __main__ - Step 47761: {'lr': 0.0003910470806342117, 'samples': 9170112, 'steps': 47760, 'loss/train': 1.4738497734069824} 08/30/2021 21:52:55 - INFO - __main__ - Step 47762: {'lr': 0.00039104269910948675, 'samples': 9170304, 'steps': 47761, 'loss/train': 1.1122866868972778} 08/30/2021 21:52:55 - INFO - __main__ - Step 47763: {'lr': 0.00039103831752121024, 'samples': 9170496, 'steps': 47762, 'loss/train': 1.7349724769592285} 08/30/2021 21:52:55 - INFO - __main__ - Step 47764: {'lr': 0.00039103393586938394, 'samples': 9170688, 'steps': 47763, 'loss/train': 1.354042410850525} 08/30/2021 21:52:56 - INFO - __main__ - Step 47765: {'lr': 0.00039102955415401, 'samples': 9170880, 'steps': 47764, 'loss/train': 2.238220691680908} 08/30/2021 21:52:56 - INFO - __main__ - Step 47766: {'lr': 0.00039102517237509025, 'samples': 9171072, 'steps': 47765, 'loss/train': 1.214213252067566} 08/30/2021 21:52:58 - INFO - __main__ - Step 47767: {'lr': 0.0003910207905326267, 'samples': 9171264, 'steps': 47766, 'loss/train': 0.09470254927873611} 08/30/2021 21:52:58 - INFO - __main__ - Step 47768: {'lr': 0.00039101640862662147, 'samples': 9171456, 'steps': 47767, 'loss/train': 0.06765691190958023} 08/30/2021 21:52:58 - INFO - __main__ - Step 47769: {'lr': 0.0003910120266570764, 'samples': 9171648, 'steps': 47768, 'loss/train': 1.2740015983581543} 08/30/2021 21:52:59 - INFO - __main__ - Step 47770: {'lr': 0.0003910076446239934, 'samples': 9171840, 'steps': 47769, 'loss/train': 1.1646220684051514} 08/30/2021 21:52:59 - INFO - __main__ - Step 47771: {'lr': 0.00039100326252737463, 'samples': 9172032, 'steps': 47770, 'loss/train': 0.7772130370140076} 08/30/2021 21:53:01 - INFO - __main__ - Step 47772: {'lr': 0.00039099888036722187, 'samples': 9172224, 'steps': 47771, 'loss/train': 1.241371989250183} 08/30/2021 21:53:01 - INFO - __main__ - Step 47773: {'lr': 0.00039099449814353725, 'samples': 9172416, 'steps': 47772, 'loss/train': 1.0401647090911865} 08/30/2021 21:53:02 - INFO - __main__ - Step 47774: {'lr': 0.00039099011585632266, 'samples': 9172608, 'steps': 47773, 'loss/train': 2.0747087001800537} 08/30/2021 21:53:02 - INFO - __main__ - Step 47775: {'lr': 0.0003909857335055801, 'samples': 9172800, 'steps': 47774, 'loss/train': 1.495471477508545} 08/30/2021 21:53:02 - INFO - __main__ - Step 47776: {'lr': 0.00039098135109131156, 'samples': 9172992, 'steps': 47775, 'loss/train': 1.5542500019073486} 08/30/2021 21:53:04 - INFO - __main__ - Step 47777: {'lr': 0.00039097696861351895, 'samples': 9173184, 'steps': 47776, 'loss/train': 1.196526288986206} 08/30/2021 21:53:04 - INFO - __main__ - Step 47778: {'lr': 0.00039097258607220445, 'samples': 9173376, 'steps': 47777, 'loss/train': 1.1890817880630493} 08/30/2021 21:53:05 - INFO - __main__ - Step 47779: {'lr': 0.00039096820346736974, 'samples': 9173568, 'steps': 47778, 'loss/train': 1.9189021587371826} 08/30/2021 21:53:05 - INFO - __main__ - Step 47780: {'lr': 0.00039096382079901695, 'samples': 9173760, 'steps': 47779, 'loss/train': 0.8137530088424683} 08/30/2021 21:53:05 - INFO - __main__ - Step 47781: {'lr': 0.000390959438067148, 'samples': 9173952, 'steps': 47780, 'loss/train': 1.1605702638626099} 08/30/2021 21:53:07 - INFO - __main__ - Step 47782: {'lr': 0.000390955055271765, 'samples': 9174144, 'steps': 47781, 'loss/train': 1.4485225677490234} 08/30/2021 21:53:07 - INFO - __main__ - Step 47783: {'lr': 0.00039095067241286973, 'samples': 9174336, 'steps': 47782, 'loss/train': 2.0699949264526367} 08/30/2021 21:53:08 - INFO - __main__ - Step 47784: {'lr': 0.00039094628949046435, 'samples': 9174528, 'steps': 47783, 'loss/train': 2.5348355770111084} 08/30/2021 21:53:08 - INFO - __main__ - Step 47785: {'lr': 0.0003909419065045507, 'samples': 9174720, 'steps': 47784, 'loss/train': 1.4091465473175049} 08/30/2021 21:53:08 - INFO - __main__ - Step 47786: {'lr': 0.0003909375234551308, 'samples': 9174912, 'steps': 47785, 'loss/train': 0.7870063781738281} 08/30/2021 21:53:09 - INFO - __main__ - Step 47787: {'lr': 0.0003909331403422066, 'samples': 9175104, 'steps': 47786, 'loss/train': 1.681264877319336} 08/30/2021 21:53:11 - INFO - __main__ - Step 47788: {'lr': 0.00039092875716578013, 'samples': 9175296, 'steps': 47787, 'loss/train': 1.670573115348816} 08/30/2021 21:53:11 - INFO - __main__ - Step 47789: {'lr': 0.00039092437392585335, 'samples': 9175488, 'steps': 47788, 'loss/train': 1.2213523387908936} 08/30/2021 21:53:11 - INFO - __main__ - Step 47790: {'lr': 0.0003909199906224282, 'samples': 9175680, 'steps': 47789, 'loss/train': 1.4888702630996704} 08/30/2021 21:53:12 - INFO - __main__ - Step 47791: {'lr': 0.00039091560725550676, 'samples': 9175872, 'steps': 47790, 'loss/train': 1.2352653741836548} 08/30/2021 21:53:12 - INFO - __main__ - Step 47792: {'lr': 0.0003909112238250908, 'samples': 9176064, 'steps': 47791, 'loss/train': 0.04455862566828728} 08/30/2021 21:53:14 - INFO - __main__ - Step 47793: {'lr': 0.0003909068403311825, 'samples': 9176256, 'steps': 47792, 'loss/train': 1.3104918003082275} 08/30/2021 21:53:14 - INFO - __main__ - Step 47794: {'lr': 0.0003909024567737837, 'samples': 9176448, 'steps': 47793, 'loss/train': 1.0472642183303833} 08/30/2021 21:53:14 - INFO - __main__ - Step 47795: {'lr': 0.0003908980731528965, 'samples': 9176640, 'steps': 47794, 'loss/train': 1.5005263090133667} 08/30/2021 21:53:15 - INFO - __main__ - Step 47796: {'lr': 0.0003908936894685227, 'samples': 9176832, 'steps': 47795, 'loss/train': 1.6320569515228271} 08/30/2021 21:53:15 - INFO - __main__ - Step 47797: {'lr': 0.0003908893057206644, 'samples': 9177024, 'steps': 47796, 'loss/train': 0.8997487425804138} 08/30/2021 21:53:17 - INFO - __main__ - Step 47798: {'lr': 0.00039088492190932365, 'samples': 9177216, 'steps': 47797, 'loss/train': 1.0634236335754395} 08/30/2021 21:53:17 - INFO - __main__ - Step 47799: {'lr': 0.00039088053803450223, 'samples': 9177408, 'steps': 47798, 'loss/train': 1.648417592048645} 08/30/2021 21:53:17 - INFO - __main__ - Step 47800: {'lr': 0.00039087615409620223, 'samples': 9177600, 'steps': 47799, 'loss/train': 0.7527249455451965} 08/30/2021 21:53:18 - INFO - __main__ - Step 47801: {'lr': 0.00039087177009442567, 'samples': 9177792, 'steps': 47800, 'loss/train': 0.8085160255432129} 08/30/2021 21:53:18 - INFO - __main__ - Step 47802: {'lr': 0.0003908673860291744, 'samples': 9177984, 'steps': 47801, 'loss/train': 1.4453188180923462} 08/30/2021 21:53:20 - INFO - __main__ - Step 47803: {'lr': 0.0003908630019004504, 'samples': 9178176, 'steps': 47802, 'loss/train': 1.3109943866729736} 08/30/2021 21:53:21 - INFO - __main__ - Step 47804: {'lr': 0.00039085861770825586, 'samples': 9178368, 'steps': 47803, 'loss/train': 1.4579682350158691} 08/30/2021 21:53:21 - INFO - __main__ - Step 47805: {'lr': 0.00039085423345259254, 'samples': 9178560, 'steps': 47804, 'loss/train': 0.5984822511672974} 08/30/2021 21:53:21 - INFO - __main__ - Step 47806: {'lr': 0.00039084984913346246, 'samples': 9178752, 'steps': 47805, 'loss/train': 1.1868911981582642} 08/30/2021 21:53:22 - INFO - __main__ - Step 47807: {'lr': 0.0003908454647508676, 'samples': 9178944, 'steps': 47806, 'loss/train': 1.2919950485229492} 08/30/2021 21:53:23 - INFO - __main__ - Step 47808: {'lr': 0.0003908410803048099, 'samples': 9179136, 'steps': 47807, 'loss/train': 1.1233738660812378} 08/30/2021 21:53:24 - INFO - __main__ - Step 47809: {'lr': 0.0003908366957952915, 'samples': 9179328, 'steps': 47808, 'loss/train': 2.2985167503356934} 08/30/2021 21:53:24 - INFO - __main__ - Step 47810: {'lr': 0.0003908323112223142, 'samples': 9179520, 'steps': 47809, 'loss/train': 1.0263887643814087} 08/30/2021 21:53:25 - INFO - __main__ - Step 47811: {'lr': 0.0003908279265858801, 'samples': 9179712, 'steps': 47810, 'loss/train': 0.3828620910644531} 08/30/2021 21:53:25 - INFO - __main__ - Step 47812: {'lr': 0.00039082354188599094, 'samples': 9179904, 'steps': 47811, 'loss/train': 1.3684004545211792} 08/30/2021 21:53:26 - INFO - __main__ - Step 47813: {'lr': 0.00039081915712264897, 'samples': 9180096, 'steps': 47812, 'loss/train': 1.2352933883666992} 08/30/2021 21:53:27 - INFO - __main__ - Step 47814: {'lr': 0.000390814772295856, 'samples': 9180288, 'steps': 47813, 'loss/train': 1.4901241064071655} 08/30/2021 21:53:27 - INFO - __main__ - Step 47815: {'lr': 0.0003908103874056142, 'samples': 9180480, 'steps': 47814, 'loss/train': 0.19271336495876312} 08/30/2021 21:53:28 - INFO - __main__ - Step 47816: {'lr': 0.0003908060024519253, 'samples': 9180672, 'steps': 47815, 'loss/train': 1.2182456254959106} 08/30/2021 21:53:28 - INFO - __main__ - Step 47817: {'lr': 0.0003908016174347915, 'samples': 9180864, 'steps': 47816, 'loss/train': 1.3654496669769287} 08/30/2021 21:53:28 - INFO - __main__ - Step 47818: {'lr': 0.00039079723235421456, 'samples': 9181056, 'steps': 47817, 'loss/train': 2.243772506713867} 08/30/2021 21:53:30 - INFO - __main__ - Step 47819: {'lr': 0.0003907928472101966, 'samples': 9181248, 'steps': 47818, 'loss/train': 1.1528795957565308} 08/30/2021 21:53:31 - INFO - __main__ - Step 47820: {'lr': 0.00039078846200273955, 'samples': 9181440, 'steps': 47819, 'loss/train': 1.8712186813354492} 08/30/2021 21:53:31 - INFO - __main__ - Step 47821: {'lr': 0.00039078407673184536, 'samples': 9181632, 'steps': 47820, 'loss/train': 1.1071661710739136} 08/30/2021 21:53:31 - INFO - __main__ - Step 47822: {'lr': 0.000390779691397516, 'samples': 9181824, 'steps': 47821, 'loss/train': 0.027321387082338333} 08/30/2021 21:53:32 - INFO - __main__ - Step 47823: {'lr': 0.0003907753059997536, 'samples': 9182016, 'steps': 47822, 'loss/train': 1.240317702293396} 08/30/2021 21:53:32 - INFO - __main__ - Step 47824: {'lr': 0.00039077092053855996, 'samples': 9182208, 'steps': 47823, 'loss/train': 1.1229140758514404} 08/30/2021 21:53:34 - INFO - __main__ - Step 47825: {'lr': 0.0003907665350139371, 'samples': 9182400, 'steps': 47824, 'loss/train': 1.1748948097229004} 08/30/2021 21:53:34 - INFO - __main__ - Step 47826: {'lr': 0.00039076214942588704, 'samples': 9182592, 'steps': 47825, 'loss/train': 1.1977704763412476} 08/30/2021 21:53:34 - INFO - __main__ - Step 47827: {'lr': 0.00039075776377441176, 'samples': 9182784, 'steps': 47826, 'loss/train': 1.5836211442947388} 08/30/2021 21:53:35 - INFO - __main__ - Step 47828: {'lr': 0.00039075337805951314, 'samples': 9182976, 'steps': 47827, 'loss/train': 1.2987773418426514} 08/30/2021 21:53:35 - INFO - __main__ - Step 47829: {'lr': 0.0003907489922811932, 'samples': 9183168, 'steps': 47828, 'loss/train': 1.127219319343567} 08/30/2021 21:53:35 - INFO - __main__ - Step 47830: {'lr': 0.000390744606439454, 'samples': 9183360, 'steps': 47829, 'loss/train': 1.4508413076400757} 08/30/2021 21:53:37 - INFO - __main__ - Step 47831: {'lr': 0.00039074022053429746, 'samples': 9183552, 'steps': 47830, 'loss/train': 1.0003811120986938} 08/30/2021 21:53:37 - INFO - __main__ - Step 47832: {'lr': 0.00039073583456572547, 'samples': 9183744, 'steps': 47831, 'loss/train': 1.0092073678970337} 08/30/2021 21:53:38 - INFO - __main__ - Step 47833: {'lr': 0.0003907314485337402, 'samples': 9183936, 'steps': 47832, 'loss/train': 0.6801624894142151} 08/30/2021 21:53:38 - INFO - __main__ - Step 47834: {'lr': 0.00039072706243834345, 'samples': 9184128, 'steps': 47833, 'loss/train': 1.3620165586471558} 08/30/2021 21:53:39 - INFO - __main__ - Step 47835: {'lr': 0.0003907226762795372, 'samples': 9184320, 'steps': 47834, 'loss/train': 1.6177831888198853} 08/30/2021 21:53:40 - INFO - __main__ - Step 47836: {'lr': 0.0003907182900573235, 'samples': 9184512, 'steps': 47835, 'loss/train': 1.9017062187194824} 08/30/2021 21:53:40 - INFO - __main__ - Step 47837: {'lr': 0.00039071390377170434, 'samples': 9184704, 'steps': 47836, 'loss/train': 2.029161214828491} 08/30/2021 21:53:41 - INFO - __main__ - Step 47838: {'lr': 0.00039070951742268173, 'samples': 9184896, 'steps': 47837, 'loss/train': 1.786980390548706} 08/30/2021 21:53:41 - INFO - __main__ - Step 47839: {'lr': 0.00039070513101025753, 'samples': 9185088, 'steps': 47838, 'loss/train': 1.1534768342971802} 08/30/2021 21:53:41 - INFO - __main__ - Step 47840: {'lr': 0.00039070074453443374, 'samples': 9185280, 'steps': 47839, 'loss/train': 2.1194944381713867} 08/30/2021 21:53:43 - INFO - __main__ - Step 47841: {'lr': 0.0003906963579952124, 'samples': 9185472, 'steps': 47840, 'loss/train': 1.5754231214523315} 08/30/2021 21:53:44 - INFO - __main__ - Step 47842: {'lr': 0.0003906919713925954, 'samples': 9185664, 'steps': 47841, 'loss/train': 0.2891518175601959} 08/30/2021 21:53:44 - INFO - __main__ - Step 47843: {'lr': 0.00039068758472658483, 'samples': 9185856, 'steps': 47842, 'loss/train': 1.1745272874832153} 08/30/2021 21:53:44 - INFO - __main__ - Step 47844: {'lr': 0.0003906831979971826, 'samples': 9186048, 'steps': 47843, 'loss/train': 1.2733420133590698} 08/30/2021 21:53:45 - INFO - __main__ - Step 47845: {'lr': 0.0003906788112043907, 'samples': 9186240, 'steps': 47844, 'loss/train': 1.5973608493804932} 08/30/2021 21:53:46 - INFO - __main__ - Step 47846: {'lr': 0.00039067442434821106, 'samples': 9186432, 'steps': 47845, 'loss/train': 1.3231230974197388} 08/30/2021 21:53:47 - INFO - __main__ - Step 47847: {'lr': 0.0003906700374286457, 'samples': 9186624, 'steps': 47846, 'loss/train': 1.4371161460876465} 08/30/2021 21:53:47 - INFO - __main__ - Step 47848: {'lr': 0.0003906656504456966, 'samples': 9186816, 'steps': 47847, 'loss/train': 1.802668809890747} 08/30/2021 21:53:47 - INFO - __main__ - Step 47849: {'lr': 0.0003906612633993657, 'samples': 9187008, 'steps': 47848, 'loss/train': 1.4726520776748657} 08/30/2021 21:53:48 - INFO - __main__ - Step 47850: {'lr': 0.00039065687628965506, 'samples': 9187200, 'steps': 47849, 'loss/train': 1.7587085962295532} 08/30/2021 21:53:49 - INFO - __main__ - Step 47851: {'lr': 0.0003906524891165666, 'samples': 9187392, 'steps': 47850, 'loss/train': 1.3055469989776611} 08/30/2021 21:53:50 - INFO - __main__ - Step 47852: {'lr': 0.00039064810188010223, 'samples': 9187584, 'steps': 47851, 'loss/train': 1.5824121236801147} 08/30/2021 21:53:50 - INFO - __main__ - Step 47853: {'lr': 0.000390643714580264, 'samples': 9187776, 'steps': 47852, 'loss/train': 1.0733797550201416} 08/30/2021 21:53:50 - INFO - __main__ - Step 47854: {'lr': 0.000390639327217054, 'samples': 9187968, 'steps': 47853, 'loss/train': 1.1565110683441162} 08/30/2021 21:53:51 - INFO - __main__ - Step 47855: {'lr': 0.000390634939790474, 'samples': 9188160, 'steps': 47854, 'loss/train': 1.4136343002319336} 08/30/2021 21:53:51 - INFO - __main__ - Step 47856: {'lr': 0.00039063055230052605, 'samples': 9188352, 'steps': 47855, 'loss/train': 1.7883784770965576} 08/30/2021 21:53:54 - INFO - __main__ - Step 47857: {'lr': 0.00039062616474721217, 'samples': 9188544, 'steps': 47856, 'loss/train': 1.0259677171707153} 08/30/2021 21:53:54 - INFO - __main__ - Step 47858: {'lr': 0.00039062177713053436, 'samples': 9188736, 'steps': 47857, 'loss/train': 0.8832210898399353} 08/30/2021 21:53:54 - INFO - __main__ - Step 47859: {'lr': 0.00039061738945049454, 'samples': 9188928, 'steps': 47858, 'loss/train': 1.596526026725769} 08/30/2021 21:53:55 - INFO - __main__ - Step 47860: {'lr': 0.0003906130017070946, 'samples': 9189120, 'steps': 47859, 'loss/train': 1.2877858877182007} 08/30/2021 21:53:55 - INFO - __main__ - Step 47861: {'lr': 0.0003906086139003366, 'samples': 9189312, 'steps': 47860, 'loss/train': 1.2230300903320312} 08/30/2021 21:53:55 - INFO - __main__ - Step 47862: {'lr': 0.00039060422603022266, 'samples': 9189504, 'steps': 47861, 'loss/train': 1.6417721509933472} 08/30/2021 21:53:57 - INFO - __main__ - Step 47863: {'lr': 0.0003905998380967546, 'samples': 9189696, 'steps': 47862, 'loss/train': 1.4069128036499023} 08/30/2021 21:53:57 - INFO - __main__ - Step 47864: {'lr': 0.00039059545009993436, 'samples': 9189888, 'steps': 47863, 'loss/train': 1.6009562015533447} 08/30/2021 21:53:58 - INFO - __main__ - Step 47865: {'lr': 0.00039059106203976403, 'samples': 9190080, 'steps': 47864, 'loss/train': 1.6115458011627197} 08/30/2021 21:53:58 - INFO - __main__ - Step 47866: {'lr': 0.00039058667391624546, 'samples': 9190272, 'steps': 47865, 'loss/train': 1.3307462930679321} 08/30/2021 21:53:58 - INFO - __main__ - Step 47867: {'lr': 0.00039058228572938074, 'samples': 9190464, 'steps': 47866, 'loss/train': 1.7715603113174438} 08/30/2021 21:54:00 - INFO - __main__ - Step 47868: {'lr': 0.00039057789747917184, 'samples': 9190656, 'steps': 47867, 'loss/train': 1.685539722442627} 08/30/2021 21:54:00 - INFO - __main__ - Step 47869: {'lr': 0.00039057350916562065, 'samples': 9190848, 'steps': 47868, 'loss/train': 1.5434104204177856} 08/30/2021 21:54:01 - INFO - __main__ - Step 47870: {'lr': 0.0003905691207887293, 'samples': 9191040, 'steps': 47869, 'loss/train': 1.1712714433670044} 08/30/2021 21:54:01 - INFO - __main__ - Step 47871: {'lr': 0.00039056473234849964, 'samples': 9191232, 'steps': 47870, 'loss/train': 0.8834353089332581} 08/30/2021 21:54:02 - INFO - __main__ - Step 47872: {'lr': 0.0003905603438449337, 'samples': 9191424, 'steps': 47871, 'loss/train': 1.0077705383300781} 08/30/2021 21:54:04 - INFO - __main__ - Step 47873: {'lr': 0.00039055595527803333, 'samples': 9191616, 'steps': 47872, 'loss/train': 0.5067219138145447} 08/30/2021 21:54:04 - INFO - __main__ - Step 47874: {'lr': 0.00039055156664780067, 'samples': 9191808, 'steps': 47873, 'loss/train': 1.157138466835022} 08/30/2021 21:54:05 - INFO - __main__ - Step 47875: {'lr': 0.00039054717795423765, 'samples': 9192000, 'steps': 47874, 'loss/train': 1.508017897605896} 08/30/2021 21:54:05 - INFO - __main__ - Step 47876: {'lr': 0.0003905427891973463, 'samples': 9192192, 'steps': 47875, 'loss/train': 0.22306524217128754} 08/30/2021 21:54:05 - INFO - __main__ - Step 47877: {'lr': 0.0003905384003771285, 'samples': 9192384, 'steps': 47876, 'loss/train': 1.6413267850875854} 08/30/2021 21:54:06 - INFO - __main__ - Step 47878: {'lr': 0.00039053401149358625, 'samples': 9192576, 'steps': 47877, 'loss/train': 1.6126058101654053} 08/30/2021 21:54:06 - INFO - __main__ - Step 47879: {'lr': 0.0003905296225467215, 'samples': 9192768, 'steps': 47878, 'loss/train': 1.5501893758773804} 08/30/2021 21:54:06 - INFO - __main__ - Step 47880: {'lr': 0.0003905252335365364, 'samples': 9192960, 'steps': 47879, 'loss/train': 1.0960619449615479} 08/30/2021 21:54:08 - INFO - __main__ - Step 47881: {'lr': 0.00039052084446303264, 'samples': 9193152, 'steps': 47880, 'loss/train': 1.2098392248153687} 08/30/2021 21:54:09 - INFO - __main__ - Step 47882: {'lr': 0.0003905164553262125, 'samples': 9193344, 'steps': 47881, 'loss/train': 1.3932965993881226} 08/30/2021 21:54:09 - INFO - __main__ - Step 47883: {'lr': 0.0003905120661260777, 'samples': 9193536, 'steps': 47882, 'loss/train': 3.418060064315796} 08/30/2021 21:54:09 - INFO - __main__ - Step 47884: {'lr': 0.00039050767686263035, 'samples': 9193728, 'steps': 47883, 'loss/train': 1.6404333114624023} 08/30/2021 21:54:10 - INFO - __main__ - Step 47885: {'lr': 0.0003905032875358725, 'samples': 9193920, 'steps': 47884, 'loss/train': 2.0146450996398926} 08/30/2021 21:54:11 - INFO - __main__ - Step 47886: {'lr': 0.00039049889814580597, 'samples': 9194112, 'steps': 47885, 'loss/train': 1.7083091735839844} 08/30/2021 21:54:12 - INFO - __main__ - Step 47887: {'lr': 0.00039049450869243276, 'samples': 9194304, 'steps': 47886, 'loss/train': 1.903693437576294} 08/30/2021 21:54:12 - INFO - __main__ - Step 47888: {'lr': 0.00039049011917575494, 'samples': 9194496, 'steps': 47887, 'loss/train': 1.0813472270965576} 08/30/2021 21:54:12 - INFO - __main__ - Step 47889: {'lr': 0.00039048572959577446, 'samples': 9194688, 'steps': 47888, 'loss/train': 0.12155977636575699} 08/30/2021 21:54:13 - INFO - __main__ - Step 47890: {'lr': 0.0003904813399524932, 'samples': 9194880, 'steps': 47889, 'loss/train': 1.5737905502319336} 08/30/2021 21:54:15 - INFO - __main__ - Step 47891: {'lr': 0.0003904769502459133, 'samples': 9195072, 'steps': 47890, 'loss/train': 1.5343148708343506} 08/30/2021 21:54:15 - INFO - __main__ - Step 47892: {'lr': 0.0003904725604760366, 'samples': 9195264, 'steps': 47891, 'loss/train': 1.2744956016540527} 08/30/2021 21:54:15 - INFO - __main__ - Step 47893: {'lr': 0.0003904681706428652, 'samples': 9195456, 'steps': 47892, 'loss/train': 1.2772544622421265} 08/30/2021 21:54:16 - INFO - __main__ - Step 47894: {'lr': 0.000390463780746401, 'samples': 9195648, 'steps': 47893, 'loss/train': 1.5194251537322998} 08/30/2021 21:54:16 - INFO - __main__ - Step 47895: {'lr': 0.00039045939078664595, 'samples': 9195840, 'steps': 47894, 'loss/train': 0.1151193231344223} 08/30/2021 21:54:17 - INFO - __main__ - Step 47896: {'lr': 0.0003904550007636021, 'samples': 9196032, 'steps': 47895, 'loss/train': 1.2806284427642822} 08/30/2021 21:54:18 - INFO - __main__ - Step 47897: {'lr': 0.00039045061067727126, 'samples': 9196224, 'steps': 47896, 'loss/train': 1.4310710430145264} 08/30/2021 21:54:19 - INFO - __main__ - Step 47898: {'lr': 0.0003904462205276557, 'samples': 9196416, 'steps': 47897, 'loss/train': 1.7274322509765625} 08/30/2021 21:54:19 - INFO - __main__ - Step 47899: {'lr': 0.0003904418303147572, 'samples': 9196608, 'steps': 47898, 'loss/train': 1.5581552982330322} 08/30/2021 21:54:19 - INFO - __main__ - Step 47900: {'lr': 0.0003904374400385777, 'samples': 9196800, 'steps': 47899, 'loss/train': 0.18381276726722717} 08/30/2021 21:54:20 - INFO - __main__ - Step 47901: {'lr': 0.0003904330496991194, 'samples': 9196992, 'steps': 47900, 'loss/train': 1.5149794816970825} 08/30/2021 21:54:21 - INFO - __main__ - Step 47902: {'lr': 0.00039042865929638404, 'samples': 9197184, 'steps': 47901, 'loss/train': 0.7306432127952576} 08/30/2021 21:54:22 - INFO - __main__ - Step 47903: {'lr': 0.00039042426883037376, 'samples': 9197376, 'steps': 47902, 'loss/train': 1.137852668762207} 08/30/2021 21:54:22 - INFO - __main__ - Step 47904: {'lr': 0.00039041987830109036, 'samples': 9197568, 'steps': 47903, 'loss/train': 0.8726712465286255} 08/30/2021 21:54:22 - INFO - __main__ - Step 47905: {'lr': 0.000390415487708536, 'samples': 9197760, 'steps': 47904, 'loss/train': 1.6011446714401245} 08/30/2021 21:54:23 - INFO - __main__ - Step 47906: {'lr': 0.0003904110970527126, 'samples': 9197952, 'steps': 47905, 'loss/train': 1.809960961341858} 08/30/2021 21:54:24 - INFO - __main__ - Step 47907: {'lr': 0.00039040670633362206, 'samples': 9198144, 'steps': 47906, 'loss/train': 1.7568812370300293} 08/30/2021 21:54:25 - INFO - __main__ - Step 47908: {'lr': 0.00039040231555126647, 'samples': 9198336, 'steps': 47907, 'loss/train': 1.692173719406128} 08/30/2021 21:54:25 - INFO - __main__ - Step 47909: {'lr': 0.0003903979247056478, 'samples': 9198528, 'steps': 47908, 'loss/train': 1.6197781562805176} 08/30/2021 21:54:25 - INFO - __main__ - Step 47910: {'lr': 0.00039039353379676796, 'samples': 9198720, 'steps': 47909, 'loss/train': 1.9702115058898926} 08/30/2021 21:54:26 - INFO - __main__ - Step 47911: {'lr': 0.0003903891428246289, 'samples': 9198912, 'steps': 47910, 'loss/train': 1.5342292785644531} 08/30/2021 21:54:29 - INFO - __main__ - Step 47912: {'lr': 0.0003903847517892328, 'samples': 9199104, 'steps': 47911, 'loss/train': 1.557690978050232} 08/30/2021 21:54:29 - INFO - __main__ - Step 47913: {'lr': 0.00039038036069058137, 'samples': 9199296, 'steps': 47912, 'loss/train': 0.6306040287017822} 08/30/2021 21:54:30 - INFO - __main__ - Step 47914: {'lr': 0.0003903759695286768, 'samples': 9199488, 'steps': 47913, 'loss/train': 0.5553920865058899} 08/30/2021 21:54:30 - INFO - __main__ - Step 47915: {'lr': 0.0003903715783035209, 'samples': 9199680, 'steps': 47914, 'loss/train': 0.7273662686347961} 08/30/2021 21:54:30 - INFO - __main__ - Step 47916: {'lr': 0.00039036718701511577, 'samples': 9199872, 'steps': 47915, 'loss/train': 0.8915906548500061} 08/30/2021 21:54:31 - INFO - __main__ - Step 47917: {'lr': 0.00039036279566346334, 'samples': 9200064, 'steps': 47916, 'loss/train': 1.5083653926849365} 08/30/2021 21:54:32 - INFO - __main__ - Step 47918: {'lr': 0.0003903584042485656, 'samples': 9200256, 'steps': 47917, 'loss/train': 1.7090014219284058} 08/30/2021 21:54:33 - INFO - __main__ - Step 47919: {'lr': 0.0003903540127704246, 'samples': 9200448, 'steps': 47918, 'loss/train': 1.157689094543457} 08/30/2021 21:54:33 - INFO - __main__ - Step 47920: {'lr': 0.0003903496212290422, 'samples': 9200640, 'steps': 47919, 'loss/train': 1.1067941188812256} 08/30/2021 21:54:33 - INFO - __main__ - Step 47921: {'lr': 0.00039034522962442045, 'samples': 9200832, 'steps': 47920, 'loss/train': 1.3353887796401978} 08/30/2021 21:54:34 - INFO - __main__ - Step 47922: {'lr': 0.0003903408379565612, 'samples': 9201024, 'steps': 47921, 'loss/train': 1.388068437576294} 08/30/2021 21:54:34 - INFO - __main__ - Step 47923: {'lr': 0.0003903364462254666, 'samples': 9201216, 'steps': 47922, 'loss/train': 1.748176097869873} 08/30/2021 21:54:35 - INFO - __main__ - Step 47924: {'lr': 0.0003903320544311386, 'samples': 9201408, 'steps': 47923, 'loss/train': 0.8511806726455688} 08/30/2021 21:54:36 - INFO - __main__ - Step 47925: {'lr': 0.0003903276625735791, 'samples': 9201600, 'steps': 47924, 'loss/train': 1.4516433477401733} 08/30/2021 21:54:36 - INFO - __main__ - Step 47926: {'lr': 0.00039032327065279015, 'samples': 9201792, 'steps': 47925, 'loss/train': 1.4957444667816162} 08/30/2021 21:54:37 - INFO - __main__ - Step 47927: {'lr': 0.0003903188786687737, 'samples': 9201984, 'steps': 47926, 'loss/train': 1.5750483274459839} 08/30/2021 21:54:37 - INFO - __main__ - Step 47928: {'lr': 0.0003903144866215317, 'samples': 9202176, 'steps': 47927, 'loss/train': 1.068113923072815} 08/30/2021 21:54:38 - INFO - __main__ - Step 47929: {'lr': 0.0003903100945110661, 'samples': 9202368, 'steps': 47928, 'loss/train': 1.5552136898040771} 08/30/2021 21:54:39 - INFO - __main__ - Step 47930: {'lr': 0.00039030570233737903, 'samples': 9202560, 'steps': 47929, 'loss/train': 0.5898703336715698} 08/30/2021 21:54:39 - INFO - __main__ - Step 47931: {'lr': 0.0003903013101004724, 'samples': 9202752, 'steps': 47930, 'loss/train': 1.919891595840454} 08/30/2021 21:54:40 - INFO - __main__ - Step 47932: {'lr': 0.00039029691780034814, 'samples': 9202944, 'steps': 47931, 'loss/train': 1.6875079870224} 08/30/2021 21:54:40 - INFO - __main__ - Step 47933: {'lr': 0.00039029252543700823, 'samples': 9203136, 'steps': 47932, 'loss/train': 0.33154863119125366} 08/30/2021 21:54:41 - INFO - __main__ - Step 47934: {'lr': 0.0003902881330104546, 'samples': 9203328, 'steps': 47933, 'loss/train': 0.7379415035247803} 08/30/2021 21:54:42 - INFO - __main__ - Step 47935: {'lr': 0.00039028374052068937, 'samples': 9203520, 'steps': 47934, 'loss/train': 1.36952543258667} 08/30/2021 21:54:42 - INFO - __main__ - Step 47936: {'lr': 0.0003902793479677145, 'samples': 9203712, 'steps': 47935, 'loss/train': 0.9311469197273254} 08/30/2021 21:54:43 - INFO - __main__ - Step 47937: {'lr': 0.00039027495535153185, 'samples': 9203904, 'steps': 47936, 'loss/train': 1.6109387874603271} 08/30/2021 21:54:43 - INFO - __main__ - Step 47938: {'lr': 0.0003902705626721435, 'samples': 9204096, 'steps': 47937, 'loss/train': 1.5544806718826294} 08/30/2021 21:54:45 - INFO - __main__ - Step 47939: {'lr': 0.00039026616992955145, 'samples': 9204288, 'steps': 47938, 'loss/train': 0.9728268980979919} 08/30/2021 21:54:45 - INFO - __main__ - Step 47940: {'lr': 0.0003902617771237575, 'samples': 9204480, 'steps': 47939, 'loss/train': 0.7438373565673828} 08/30/2021 21:54:45 - INFO - __main__ - Step 47941: {'lr': 0.0003902573842547639, 'samples': 9204672, 'steps': 47940, 'loss/train': 1.1454633474349976} 08/30/2021 21:54:46 - INFO - __main__ - Step 47942: {'lr': 0.00039025299132257243, 'samples': 9204864, 'steps': 47941, 'loss/train': 1.1059343814849854} 08/30/2021 21:54:46 - INFO - __main__ - Step 47943: {'lr': 0.00039024859832718505, 'samples': 9205056, 'steps': 47942, 'loss/train': 1.249679684638977} 08/30/2021 21:54:48 - INFO - __main__ - Step 47944: {'lr': 0.0003902442052686039, 'samples': 9205248, 'steps': 47943, 'loss/train': 0.05899669975042343} 08/30/2021 21:54:48 - INFO - __main__ - Step 47945: {'lr': 0.00039023981214683087, 'samples': 9205440, 'steps': 47944, 'loss/train': 1.2613134384155273} 08/30/2021 21:54:48 - INFO - __main__ - Step 47946: {'lr': 0.0003902354189618679, 'samples': 9205632, 'steps': 47945, 'loss/train': 0.7736929655075073} 08/30/2021 21:54:49 - INFO - __main__ - Step 47947: {'lr': 0.00039023102571371707, 'samples': 9205824, 'steps': 47946, 'loss/train': 1.809786319732666} 08/30/2021 21:54:49 - INFO - __main__ - Step 47948: {'lr': 0.0003902266324023803, 'samples': 9206016, 'steps': 47947, 'loss/train': 1.0456798076629639} 08/30/2021 21:54:49 - INFO - __main__ - Step 47949: {'lr': 0.00039022223902785954, 'samples': 9206208, 'steps': 47948, 'loss/train': 1.6305575370788574} 08/30/2021 21:54:51 - INFO - __main__ - Step 47950: {'lr': 0.0003902178455901568, 'samples': 9206400, 'steps': 47949, 'loss/train': 0.6561105847358704} 08/30/2021 21:54:51 - INFO - __main__ - Step 47951: {'lr': 0.00039021345208927404, 'samples': 9206592, 'steps': 47950, 'loss/train': 1.4292510747909546} 08/30/2021 21:54:52 - INFO - __main__ - Step 47952: {'lr': 0.0003902090585252133, 'samples': 9206784, 'steps': 47951, 'loss/train': 1.6782574653625488} 08/30/2021 21:54:52 - INFO - __main__ - Step 47953: {'lr': 0.0003902046648979766, 'samples': 9206976, 'steps': 47952, 'loss/train': 2.1473450660705566} 08/30/2021 21:54:52 - INFO - __main__ - Step 47954: {'lr': 0.00039020027120756573, 'samples': 9207168, 'steps': 47953, 'loss/train': 1.3811249732971191} 08/30/2021 21:54:54 - INFO - __main__ - Step 47955: {'lr': 0.00039019587745398276, 'samples': 9207360, 'steps': 47954, 'loss/train': 1.7682926654815674} 08/30/2021 21:54:54 - INFO - __main__ - Step 47956: {'lr': 0.0003901914836372298, 'samples': 9207552, 'steps': 47955, 'loss/train': 1.0705757141113281} 08/30/2021 21:54:55 - INFO - __main__ - Step 47957: {'lr': 0.00039018708975730864, 'samples': 9207744, 'steps': 47956, 'loss/train': 1.2473047971725464} 08/30/2021 21:54:55 - INFO - __main__ - Step 47958: {'lr': 0.0003901826958142214, 'samples': 9207936, 'steps': 47957, 'loss/train': 1.014862060546875} 08/30/2021 21:54:55 - INFO - __main__ - Step 47959: {'lr': 0.0003901783018079699, 'samples': 9208128, 'steps': 47958, 'loss/train': 1.1212726831436157} 08/30/2021 21:54:57 - INFO - __main__ - Step 47960: {'lr': 0.0003901739077385563, 'samples': 9208320, 'steps': 47959, 'loss/train': 1.769634485244751} 08/30/2021 21:54:57 - INFO - __main__ - Step 47961: {'lr': 0.0003901695136059825, 'samples': 9208512, 'steps': 47960, 'loss/train': 1.6125181913375854} 08/30/2021 21:54:58 - INFO - __main__ - Step 47962: {'lr': 0.00039016511941025045, 'samples': 9208704, 'steps': 47961, 'loss/train': 1.411395788192749} 08/30/2021 21:54:58 - INFO - __main__ - Step 47963: {'lr': 0.0003901607251513622, 'samples': 9208896, 'steps': 47962, 'loss/train': 1.1251847743988037} 08/30/2021 21:54:58 - INFO - __main__ - Step 47964: {'lr': 0.0003901563308293197, 'samples': 9209088, 'steps': 47963, 'loss/train': 0.9561633467674255} 08/30/2021 21:55:00 - INFO - __main__ - Step 47965: {'lr': 0.0003901519364441248, 'samples': 9209280, 'steps': 47964, 'loss/train': 1.2790157794952393} 08/30/2021 21:55:01 - INFO - __main__ - Step 47966: {'lr': 0.0003901475419957797, 'samples': 9209472, 'steps': 47965, 'loss/train': 1.5799431800842285} 08/30/2021 21:55:01 - INFO - __main__ - Step 47967: {'lr': 0.0003901431474842863, 'samples': 9209664, 'steps': 47966, 'loss/train': 2.313375234603882} 08/30/2021 21:55:01 - INFO - __main__ - Step 47968: {'lr': 0.0003901387529096465, 'samples': 9209856, 'steps': 47967, 'loss/train': 1.353843331336975} 08/30/2021 21:55:02 - INFO - __main__ - Step 47969: {'lr': 0.0003901343582718624, 'samples': 9210048, 'steps': 47968, 'loss/train': 1.1205179691314697} 08/30/2021 21:55:04 - INFO - __main__ - Step 47970: {'lr': 0.0003901299635709359, 'samples': 9210240, 'steps': 47969, 'loss/train': 1.6425973176956177} 08/30/2021 21:55:04 - INFO - __main__ - Step 47971: {'lr': 0.00039012556880686897, 'samples': 9210432, 'steps': 47970, 'loss/train': 2.0301880836486816} 08/30/2021 21:55:05 - INFO - __main__ - Step 47972: {'lr': 0.00039012117397966363, 'samples': 9210624, 'steps': 47971, 'loss/train': 1.0088059902191162} 08/30/2021 21:55:05 - INFO - __main__ - Step 47973: {'lr': 0.00039011677908932184, 'samples': 9210816, 'steps': 47972, 'loss/train': 0.5545100569725037} 08/30/2021 21:55:05 - INFO - __main__ - Step 47974: {'lr': 0.00039011238413584566, 'samples': 9211008, 'steps': 47973, 'loss/train': 1.1089811325073242} 08/30/2021 21:55:07 - INFO - __main__ - Step 47975: {'lr': 0.0003901079891192369, 'samples': 9211200, 'steps': 47974, 'loss/train': 1.461216926574707} 08/30/2021 21:55:07 - INFO - __main__ - Step 47976: {'lr': 0.00039010359403949776, 'samples': 9211392, 'steps': 47975, 'loss/train': 0.5487602353096008} 08/30/2021 21:55:08 - INFO - __main__ - Step 47977: {'lr': 0.00039009919889663005, 'samples': 9211584, 'steps': 47976, 'loss/train': 0.881941556930542} 08/30/2021 21:55:08 - INFO - __main__ - Step 47978: {'lr': 0.00039009480369063575, 'samples': 9211776, 'steps': 47977, 'loss/train': 1.8178044557571411} 08/30/2021 21:55:08 - INFO - __main__ - Step 47979: {'lr': 0.000390090408421517, 'samples': 9211968, 'steps': 47978, 'loss/train': 0.7355507016181946} 08/30/2021 21:55:10 - INFO - __main__ - Step 47980: {'lr': 0.0003900860130892756, 'samples': 9212160, 'steps': 47979, 'loss/train': 1.2027751207351685} 08/30/2021 21:55:10 - INFO - __main__ - Step 47981: {'lr': 0.0003900816176939136, 'samples': 9212352, 'steps': 47980, 'loss/train': 0.8195446729660034} 08/30/2021 21:55:11 - INFO - __main__ - Step 47982: {'lr': 0.000390077222235433, 'samples': 9212544, 'steps': 47981, 'loss/train': 1.8953591585159302} 08/30/2021 21:55:11 - INFO - __main__ - Step 47983: {'lr': 0.0003900728267138357, 'samples': 9212736, 'steps': 47982, 'loss/train': 1.4434648752212524} 08/30/2021 21:55:12 - INFO - __main__ - Step 47984: {'lr': 0.0003900684311291238, 'samples': 9212928, 'steps': 47983, 'loss/train': 1.8007526397705078} 08/30/2021 21:55:13 - INFO - __main__ - Step 47985: {'lr': 0.0003900640354812992, 'samples': 9213120, 'steps': 47984, 'loss/train': 1.681673526763916} 08/30/2021 21:55:13 - INFO - __main__ - Step 47986: {'lr': 0.000390059639770364, 'samples': 9213312, 'steps': 47985, 'loss/train': 1.1255621910095215} 08/30/2021 21:55:14 - INFO - __main__ - Step 47987: {'lr': 0.0003900552439963201, 'samples': 9213504, 'steps': 47986, 'loss/train': 1.6035668849945068} 08/30/2021 21:55:14 - INFO - __main__ - Step 47988: {'lr': 0.0003900508481591694, 'samples': 9213696, 'steps': 47987, 'loss/train': 1.3248248100280762} 08/30/2021 21:55:14 - INFO - __main__ - Step 47989: {'lr': 0.00039004645225891387, 'samples': 9213888, 'steps': 47988, 'loss/train': 1.7217713594436646} 08/30/2021 21:55:16 - INFO - __main__ - Step 47990: {'lr': 0.0003900420562955557, 'samples': 9214080, 'steps': 47989, 'loss/train': 1.5362060070037842} 08/30/2021 21:55:16 - INFO - __main__ - Step 47991: {'lr': 0.0003900376602690966, 'samples': 9214272, 'steps': 47990, 'loss/train': 0.669004499912262} 08/30/2021 21:55:17 - INFO - __main__ - Step 47992: {'lr': 0.0003900332641795388, 'samples': 9214464, 'steps': 47991, 'loss/train': 1.6353973150253296} 08/30/2021 21:55:17 - INFO - __main__ - Step 47993: {'lr': 0.0003900288680268842, 'samples': 9214656, 'steps': 47992, 'loss/train': 1.7858846187591553} 08/30/2021 21:55:17 - INFO - __main__ - Step 47994: {'lr': 0.00039002447181113464, 'samples': 9214848, 'steps': 47993, 'loss/train': 1.558007001876831} 08/30/2021 21:55:18 - INFO - __main__ - Step 47995: {'lr': 0.0003900200755322923, 'samples': 9215040, 'steps': 47994, 'loss/train': 1.27335786819458} 08/30/2021 21:55:19 - INFO - __main__ - Step 47996: {'lr': 0.0003900156791903591, 'samples': 9215232, 'steps': 47995, 'loss/train': 0.9494937062263489} 08/30/2021 21:55:20 - INFO - __main__ - Step 47997: {'lr': 0.0003900112827853369, 'samples': 9215424, 'steps': 47996, 'loss/train': 1.9481124877929688} 08/30/2021 21:55:20 - INFO - __main__ - Step 47998: {'lr': 0.0003900068863172278, 'samples': 9215616, 'steps': 47997, 'loss/train': 1.7428592443466187} 08/30/2021 21:55:20 - INFO - __main__ - Step 47999: {'lr': 0.0003900024897860338, 'samples': 9215808, 'steps': 47998, 'loss/train': 0.9841916561126709} 08/30/2021 21:55:21 - INFO - __main__ - Step 48000: {'lr': 0.00038999809319175684, 'samples': 9216000, 'steps': 47999, 'loss/train': 1.3682252168655396} 08/30/2021 21:55:22 - INFO - __main__ - Step 48001: {'lr': 0.0003899936965343989, 'samples': 9216192, 'steps': 48000, 'loss/train': 0.7294800281524658} 08/30/2021 21:55:23 - INFO - __main__ - Step 48002: {'lr': 0.00038998929981396194, 'samples': 9216384, 'steps': 48001, 'loss/train': 0.6029478907585144} 08/30/2021 21:55:23 - INFO - __main__ - Step 48003: {'lr': 0.0003899849030304479, 'samples': 9216576, 'steps': 48002, 'loss/train': 1.418975830078125} 08/30/2021 21:55:23 - INFO - __main__ - Step 48004: {'lr': 0.0003899805061838589, 'samples': 9216768, 'steps': 48003, 'loss/train': 1.1456586122512817} 08/30/2021 21:55:24 - INFO - __main__ - Step 48005: {'lr': 0.0003899761092741968, 'samples': 9216960, 'steps': 48004, 'loss/train': 3.1620686054229736} 08/30/2021 21:55:25 - INFO - __main__ - Step 48006: {'lr': 0.00038997171230146366, 'samples': 9217152, 'steps': 48005, 'loss/train': 1.820265293121338} 08/30/2021 21:55:26 - INFO - __main__ - Step 48007: {'lr': 0.0003899673152656614, 'samples': 9217344, 'steps': 48006, 'loss/train': 0.8522946834564209} 08/30/2021 21:55:26 - INFO - __main__ - Step 48008: {'lr': 0.0003899629181667921, 'samples': 9217536, 'steps': 48007, 'loss/train': 1.411366581916809} 08/30/2021 21:55:26 - INFO - __main__ - Step 48009: {'lr': 0.0003899585210048576, 'samples': 9217728, 'steps': 48008, 'loss/train': 1.2145556211471558} 08/30/2021 21:55:27 - INFO - __main__ - Step 48010: {'lr': 0.0003899541237798599, 'samples': 9217920, 'steps': 48009, 'loss/train': 1.6335562467575073} 08/30/2021 21:55:28 - INFO - __main__ - Step 48011: {'lr': 0.0003899497264918012, 'samples': 9218112, 'steps': 48010, 'loss/train': 1.4699443578720093} 08/30/2021 21:55:28 - INFO - __main__ - Step 48012: {'lr': 0.00038994532914068313, 'samples': 9218304, 'steps': 48011, 'loss/train': 1.651854157447815} 08/30/2021 21:55:29 - INFO - __main__ - Step 48013: {'lr': 0.00038994093172650804, 'samples': 9218496, 'steps': 48012, 'loss/train': 0.6458513736724854} 08/30/2021 21:55:29 - INFO - __main__ - Step 48014: {'lr': 0.00038993653424927754, 'samples': 9218688, 'steps': 48013, 'loss/train': 1.3805373907089233} 08/30/2021 21:55:29 - INFO - __main__ - Step 48015: {'lr': 0.00038993213670899385, 'samples': 9218880, 'steps': 48014, 'loss/train': 1.4443672895431519} 08/30/2021 21:55:31 - INFO - __main__ - Step 48016: {'lr': 0.000389927739105659, 'samples': 9219072, 'steps': 48015, 'loss/train': 1.6568262577056885} 08/30/2021 21:55:31 - INFO - __main__ - Step 48017: {'lr': 0.0003899233414392748, 'samples': 9219264, 'steps': 48016, 'loss/train': 1.719864845275879} 08/30/2021 21:55:32 - INFO - __main__ - Step 48018: {'lr': 0.0003899189437098433, 'samples': 9219456, 'steps': 48017, 'loss/train': 1.2093226909637451} 08/30/2021 21:55:32 - INFO - __main__ - Step 48019: {'lr': 0.00038991454591736643, 'samples': 9219648, 'steps': 48018, 'loss/train': 0.6396217346191406} 08/30/2021 21:55:32 - INFO - __main__ - Step 48020: {'lr': 0.00038991014806184635, 'samples': 9219840, 'steps': 48019, 'loss/train': 1.373793363571167} 08/30/2021 21:55:34 - INFO - __main__ - Step 48021: {'lr': 0.0003899057501432848, 'samples': 9220032, 'steps': 48020, 'loss/train': 1.309171438217163} 08/30/2021 21:55:35 - INFO - __main__ - Step 48022: {'lr': 0.0003899013521616839, 'samples': 9220224, 'steps': 48021, 'loss/train': 1.4871996641159058} 08/30/2021 21:55:35 - INFO - __main__ - Step 48023: {'lr': 0.0003898969541170456, 'samples': 9220416, 'steps': 48022, 'loss/train': 1.4128605127334595} 08/30/2021 21:55:36 - INFO - __main__ - Step 48024: {'lr': 0.0003898925560093719, 'samples': 9220608, 'steps': 48023, 'loss/train': 0.7613070607185364} 08/30/2021 21:55:36 - INFO - __main__ - Step 48025: {'lr': 0.00038988815783866485, 'samples': 9220800, 'steps': 48024, 'loss/train': 1.3089985847473145} 08/30/2021 21:55:37 - INFO - __main__ - Step 48026: {'lr': 0.00038988375960492626, 'samples': 9220992, 'steps': 48025, 'loss/train': 1.4384922981262207} 08/30/2021 21:55:38 - INFO - __main__ - Step 48027: {'lr': 0.0003898793613081583, 'samples': 9221184, 'steps': 48026, 'loss/train': 0.5155933499336243} 08/30/2021 21:55:38 - INFO - __main__ - Step 48028: {'lr': 0.0003898749629483628, 'samples': 9221376, 'steps': 48027, 'loss/train': 0.04614232853055} 08/30/2021 21:55:39 - INFO - __main__ - Step 48029: {'lr': 0.00038987056452554177, 'samples': 9221568, 'steps': 48028, 'loss/train': 1.3231110572814941} 08/30/2021 21:55:39 - INFO - __main__ - Step 48030: {'lr': 0.0003898661660396973, 'samples': 9221760, 'steps': 48029, 'loss/train': 1.7507843971252441} 08/30/2021 21:55:40 - INFO - __main__ - Step 48031: {'lr': 0.00038986176749083117, 'samples': 9221952, 'steps': 48030, 'loss/train': 1.6523869037628174} 08/30/2021 21:55:41 - INFO - __main__ - Step 48032: {'lr': 0.0003898573688789456, 'samples': 9222144, 'steps': 48031, 'loss/train': 0.8921321630477905} 08/30/2021 21:55:41 - INFO - __main__ - Step 48033: {'lr': 0.0003898529702040424, 'samples': 9222336, 'steps': 48032, 'loss/train': 1.3697538375854492} 08/30/2021 21:55:42 - INFO - __main__ - Step 48034: {'lr': 0.00038984857146612365, 'samples': 9222528, 'steps': 48033, 'loss/train': 1.581619381904602} 08/30/2021 21:55:42 - INFO - __main__ - Step 48035: {'lr': 0.00038984417266519126, 'samples': 9222720, 'steps': 48034, 'loss/train': 1.5477761030197144} 08/30/2021 21:55:44 - INFO - __main__ - Step 48036: {'lr': 0.00038983977380124726, 'samples': 9222912, 'steps': 48035, 'loss/train': 0.9938199520111084} 08/30/2021 21:55:44 - INFO - __main__ - Step 48037: {'lr': 0.0003898353748742936, 'samples': 9223104, 'steps': 48036, 'loss/train': 0.9710741639137268} 08/30/2021 21:55:44 - INFO - __main__ - Step 48038: {'lr': 0.00038983097588433225, 'samples': 9223296, 'steps': 48037, 'loss/train': 2.5571200847625732} 08/30/2021 21:55:45 - INFO - __main__ - Step 48039: {'lr': 0.00038982657683136524, 'samples': 9223488, 'steps': 48038, 'loss/train': 1.3827848434448242} 08/30/2021 21:55:45 - INFO - __main__ - Step 48040: {'lr': 0.00038982217771539466, 'samples': 9223680, 'steps': 48039, 'loss/train': 1.2979451417922974} 08/30/2021 21:55:46 - INFO - __main__ - Step 48041: {'lr': 0.0003898177785364222, 'samples': 9223872, 'steps': 48040, 'loss/train': 0.8472513556480408} 08/30/2021 21:55:47 - INFO - __main__ - Step 48042: {'lr': 0.00038981337929445004, 'samples': 9224064, 'steps': 48041, 'loss/train': 0.0789189413189888} 08/30/2021 21:55:48 - INFO - __main__ - Step 48043: {'lr': 0.0003898089799894802, 'samples': 9224256, 'steps': 48042, 'loss/train': 1.749300479888916} 08/30/2021 21:55:48 - INFO - __main__ - Step 48044: {'lr': 0.0003898045806215145, 'samples': 9224448, 'steps': 48043, 'loss/train': 0.13373838365077972} 08/30/2021 21:55:48 - INFO - __main__ - Step 48045: {'lr': 0.00038980018119055506, 'samples': 9224640, 'steps': 48044, 'loss/train': 2.0769262313842773} 08/30/2021 21:55:49 - INFO - __main__ - Step 48046: {'lr': 0.00038979578169660384, 'samples': 9224832, 'steps': 48045, 'loss/train': 1.142823576927185} 08/30/2021 21:55:50 - INFO - __main__ - Step 48047: {'lr': 0.0003897913821396628, 'samples': 9225024, 'steps': 48046, 'loss/train': 1.7016246318817139} 08/30/2021 21:55:51 - INFO - __main__ - Step 48048: {'lr': 0.0003897869825197339, 'samples': 9225216, 'steps': 48047, 'loss/train': 1.712834119796753} 08/30/2021 21:55:51 - INFO - __main__ - Step 48049: {'lr': 0.0003897825828368191, 'samples': 9225408, 'steps': 48048, 'loss/train': 1.0804564952850342} 08/30/2021 21:55:52 - INFO - __main__ - Step 48050: {'lr': 0.0003897781830909204, 'samples': 9225600, 'steps': 48049, 'loss/train': 1.0883190631866455} 08/30/2021 21:55:52 - INFO - __main__ - Step 48051: {'lr': 0.00038977378328203987, 'samples': 9225792, 'steps': 48050, 'loss/train': 1.942132830619812} 08/30/2021 21:55:53 - INFO - __main__ - Step 48052: {'lr': 0.0003897693834101794, 'samples': 9225984, 'steps': 48051, 'loss/train': 1.2460460662841797} 08/30/2021 21:55:54 - INFO - __main__ - Step 48053: {'lr': 0.00038976498347534106, 'samples': 9226176, 'steps': 48052, 'loss/train': 1.46304190158844} 08/30/2021 21:55:54 - INFO - __main__ - Step 48054: {'lr': 0.0003897605834775267, 'samples': 9226368, 'steps': 48053, 'loss/train': 1.3460031747817993} 08/30/2021 21:55:54 - INFO - __main__ - Step 48055: {'lr': 0.00038975618341673845, 'samples': 9226560, 'steps': 48054, 'loss/train': 1.151011347770691} 08/30/2021 21:55:55 - INFO - __main__ - Step 48056: {'lr': 0.0003897517832929782, 'samples': 9226752, 'steps': 48055, 'loss/train': 1.1946170330047607} 08/30/2021 21:55:56 - INFO - __main__ - Step 48057: {'lr': 0.00038974738310624797, 'samples': 9226944, 'steps': 48056, 'loss/train': 1.568045973777771} 08/30/2021 21:55:57 - INFO - __main__ - Step 48058: {'lr': 0.00038974298285654967, 'samples': 9227136, 'steps': 48057, 'loss/train': 1.9462419748306274} 08/30/2021 21:55:57 - INFO - __main__ - Step 48059: {'lr': 0.0003897385825438854, 'samples': 9227328, 'steps': 48058, 'loss/train': 0.6368768811225891} 08/30/2021 21:55:57 - INFO - __main__ - Step 48060: {'lr': 0.0003897341821682571, 'samples': 9227520, 'steps': 48059, 'loss/train': 1.0692126750946045} 08/30/2021 21:55:58 - INFO - __main__ - Step 48061: {'lr': 0.0003897297817296667, 'samples': 9227712, 'steps': 48060, 'loss/train': 1.8624049425125122} 08/30/2021 21:56:00 - INFO - __main__ - Step 48062: {'lr': 0.00038972538122811613, 'samples': 9227904, 'steps': 48061, 'loss/train': 1.4940840005874634} 08/30/2021 21:56:00 - INFO - __main__ - Step 48063: {'lr': 0.00038972098066360753, 'samples': 9228096, 'steps': 48062, 'loss/train': 1.4992592334747314} 08/30/2021 21:56:00 - INFO - __main__ - Step 48064: {'lr': 0.0003897165800361427, 'samples': 9228288, 'steps': 48063, 'loss/train': 0.04728345572948456} 08/30/2021 21:56:01 - INFO - __main__ - Step 48065: {'lr': 0.0003897121793457239, 'samples': 9228480, 'steps': 48064, 'loss/train': 1.349684476852417} 08/30/2021 21:56:01 - INFO - __main__ - Step 48066: {'lr': 0.0003897077785923529, 'samples': 9228672, 'steps': 48065, 'loss/train': 0.16502012312412262} 08/30/2021 21:56:02 - INFO - __main__ - Step 48067: {'lr': 0.0003897033777760318, 'samples': 9228864, 'steps': 48066, 'loss/train': 1.3611706495285034} 08/30/2021 21:56:03 - INFO - __main__ - Step 48068: {'lr': 0.0003896989768967624, 'samples': 9229056, 'steps': 48067, 'loss/train': 0.6744688153266907} 08/30/2021 21:56:04 - INFO - __main__ - Step 48069: {'lr': 0.0003896945759545468, 'samples': 9229248, 'steps': 48068, 'loss/train': 5.85368537902832} 08/30/2021 21:56:04 - INFO - __main__ - Step 48070: {'lr': 0.000389690174949387, 'samples': 9229440, 'steps': 48069, 'loss/train': 5.836464881896973} 08/30/2021 21:56:05 - INFO - __main__ - Step 48071: {'lr': 0.00038968577388128503, 'samples': 9229632, 'steps': 48070, 'loss/train': 1.3360096216201782} 08/30/2021 21:56:05 - INFO - __main__ - Step 48072: {'lr': 0.00038968137275024274, 'samples': 9229824, 'steps': 48071, 'loss/train': 1.7021456956863403} 08/30/2021 21:56:05 - INFO - __main__ - Step 48073: {'lr': 0.0003896769715562622, 'samples': 9230016, 'steps': 48072, 'loss/train': 0.9753689169883728} 08/30/2021 21:56:08 - INFO - __main__ - Step 48074: {'lr': 0.0003896725702993453, 'samples': 9230208, 'steps': 48073, 'loss/train': 1.4867280721664429} 08/30/2021 21:56:08 - INFO - __main__ - Step 48075: {'lr': 0.0003896681689794942, 'samples': 9230400, 'steps': 48074, 'loss/train': 0.6709274649620056} 08/30/2021 21:56:09 - INFO - __main__ - Step 48076: {'lr': 0.00038966376759671075, 'samples': 9230592, 'steps': 48075, 'loss/train': 1.626508116722107} 08/30/2021 21:56:09 - INFO - __main__ - Step 48077: {'lr': 0.00038965936615099694, 'samples': 9230784, 'steps': 48076, 'loss/train': 0.4990983307361603} 08/30/2021 21:56:09 - INFO - __main__ - Step 48078: {'lr': 0.0003896549646423548, 'samples': 9230976, 'steps': 48077, 'loss/train': 0.9760861396789551} 08/30/2021 21:56:10 - INFO - __main__ - Step 48079: {'lr': 0.0003896505630707863, 'samples': 9231168, 'steps': 48078, 'loss/train': 1.4228544235229492} 08/30/2021 21:56:10 - INFO - __main__ - Step 48080: {'lr': 0.00038964616143629337, 'samples': 9231360, 'steps': 48079, 'loss/train': 0.6009047627449036} 08/30/2021 21:56:11 - INFO - __main__ - Step 48081: {'lr': 0.00038964175973887807, 'samples': 9231552, 'steps': 48080, 'loss/train': 0.40620696544647217} 08/30/2021 21:56:13 - INFO - __main__ - Step 48082: {'lr': 0.0003896373579785423, 'samples': 9231744, 'steps': 48081, 'loss/train': 0.3924275040626526} 08/30/2021 21:56:13 - INFO - __main__ - Step 48083: {'lr': 0.00038963295615528803, 'samples': 9231936, 'steps': 48082, 'loss/train': 1.9669965505599976} 08/30/2021 21:56:13 - INFO - __main__ - Step 48084: {'lr': 0.00038962855426911746, 'samples': 9232128, 'steps': 48083, 'loss/train': 1.495212435722351} 08/30/2021 21:56:14 - INFO - __main__ - Step 48085: {'lr': 0.00038962415232003233, 'samples': 9232320, 'steps': 48084, 'loss/train': 1.4255551099777222} 08/30/2021 21:56:14 - INFO - __main__ - Step 48086: {'lr': 0.00038961975030803474, 'samples': 9232512, 'steps': 48085, 'loss/train': 0.03670331463217735} 08/30/2021 21:56:16 - INFO - __main__ - Step 48087: {'lr': 0.00038961534823312664, 'samples': 9232704, 'steps': 48086, 'loss/train': 1.2051409482955933} 08/30/2021 21:56:16 - INFO - __main__ - Step 48088: {'lr': 0.00038961094609531, 'samples': 9232896, 'steps': 48087, 'loss/train': 0.8676460385322571} 08/30/2021 21:56:16 - INFO - __main__ - Step 48089: {'lr': 0.00038960654389458684, 'samples': 9233088, 'steps': 48088, 'loss/train': 1.1531951427459717} 08/30/2021 21:56:17 - INFO - __main__ - Step 48090: {'lr': 0.0003896021416309591, 'samples': 9233280, 'steps': 48089, 'loss/train': 1.3840491771697998} 08/30/2021 21:56:17 - INFO - __main__ - Step 48091: {'lr': 0.0003895977393044288, 'samples': 9233472, 'steps': 48090, 'loss/train': 2.1008269786834717} 08/30/2021 21:56:19 - INFO - __main__ - Step 48092: {'lr': 0.00038959333691499794, 'samples': 9233664, 'steps': 48091, 'loss/train': 1.0274615287780762} 08/30/2021 21:56:19 - INFO - __main__ - Step 48093: {'lr': 0.00038958893446266844, 'samples': 9233856, 'steps': 48092, 'loss/train': 1.6036871671676636} 08/30/2021 21:56:19 - INFO - __main__ - Step 48094: {'lr': 0.00038958453194744237, 'samples': 9234048, 'steps': 48093, 'loss/train': 1.0566166639328003} 08/30/2021 21:56:20 - INFO - __main__ - Step 48095: {'lr': 0.0003895801293693216, 'samples': 9234240, 'steps': 48094, 'loss/train': 1.053208589553833} 08/30/2021 21:56:20 - INFO - __main__ - Step 48096: {'lr': 0.0003895757267283082, 'samples': 9234432, 'steps': 48095, 'loss/train': 2.430922508239746} 08/30/2021 21:56:22 - INFO - __main__ - Step 48097: {'lr': 0.0003895713240244042, 'samples': 9234624, 'steps': 48096, 'loss/train': 1.8209210634231567} 08/30/2021 21:56:22 - INFO - __main__ - Step 48098: {'lr': 0.0003895669212576114, 'samples': 9234816, 'steps': 48097, 'loss/train': 1.0672640800476074} 08/30/2021 21:56:23 - INFO - __main__ - Step 48099: {'lr': 0.000389562518427932, 'samples': 9235008, 'steps': 48098, 'loss/train': 0.047764554619789124} 08/30/2021 21:56:23 - INFO - __main__ - Step 48100: {'lr': 0.00038955811553536787, 'samples': 9235200, 'steps': 48099, 'loss/train': 1.649141788482666} 08/30/2021 21:56:23 - INFO - __main__ - Step 48101: {'lr': 0.00038955371257992096, 'samples': 9235392, 'steps': 48100, 'loss/train': 0.9659141898155212} 08/30/2021 21:56:24 - INFO - __main__ - Step 48102: {'lr': 0.0003895493095615933, 'samples': 9235584, 'steps': 48101, 'loss/train': 1.4187041521072388} 08/30/2021 21:56:25 - INFO - __main__ - Step 48103: {'lr': 0.00038954490648038687, 'samples': 9235776, 'steps': 48102, 'loss/train': 1.3778592348098755} 08/30/2021 21:56:26 - INFO - __main__ - Step 48104: {'lr': 0.0003895405033363037, 'samples': 9235968, 'steps': 48103, 'loss/train': 1.2677559852600098} 08/30/2021 21:56:26 - INFO - __main__ - Step 48105: {'lr': 0.0003895361001293457, 'samples': 9236160, 'steps': 48104, 'loss/train': 1.3955543041229248} 08/30/2021 21:56:27 - INFO - __main__ - Step 48106: {'lr': 0.0003895316968595149, 'samples': 9236352, 'steps': 48105, 'loss/train': 1.6083626747131348} 08/30/2021 21:56:27 - INFO - __main__ - Step 48107: {'lr': 0.0003895272935268133, 'samples': 9236544, 'steps': 48106, 'loss/train': 1.3801171779632568} 08/30/2021 21:56:28 - INFO - __main__ - Step 48108: {'lr': 0.0003895228901312428, 'samples': 9236736, 'steps': 48107, 'loss/train': 0.6153112649917603} 08/30/2021 21:56:29 - INFO - __main__ - Step 48109: {'lr': 0.0003895184866728054, 'samples': 9236928, 'steps': 48108, 'loss/train': 1.0506694316864014} 08/30/2021 21:56:29 - INFO - __main__ - Step 48110: {'lr': 0.0003895140831515033, 'samples': 9237120, 'steps': 48109, 'loss/train': 1.713735580444336} 08/30/2021 21:56:30 - INFO - __main__ - Step 48111: {'lr': 0.0003895096795673381, 'samples': 9237312, 'steps': 48110, 'loss/train': 1.699536919593811} 08/30/2021 21:56:30 - INFO - __main__ - Step 48112: {'lr': 0.0003895052759203121, 'samples': 9237504, 'steps': 48111, 'loss/train': 1.416006088256836} 08/30/2021 21:56:32 - INFO - __main__ - Step 48113: {'lr': 0.0003895008722104272, 'samples': 9237696, 'steps': 48112, 'loss/train': 0.8337977528572083} 08/30/2021 21:56:32 - INFO - __main__ - Step 48114: {'lr': 0.00038949646843768526, 'samples': 9237888, 'steps': 48113, 'loss/train': 1.8441437482833862} 08/30/2021 21:56:33 - INFO - __main__ - Step 48115: {'lr': 0.00038949206460208845, 'samples': 9238080, 'steps': 48114, 'loss/train': 1.6917622089385986} 08/30/2021 21:56:33 - INFO - __main__ - Step 48116: {'lr': 0.0003894876607036386, 'samples': 9238272, 'steps': 48115, 'loss/train': 1.933457374572754} 08/30/2021 21:56:33 - INFO - __main__ - Step 48117: {'lr': 0.0003894832567423379, 'samples': 9238464, 'steps': 48116, 'loss/train': 1.2408145666122437} 08/30/2021 21:56:34 - INFO - __main__ - Step 48118: {'lr': 0.00038947885271818807, 'samples': 9238656, 'steps': 48117, 'loss/train': 1.8722898960113525} 08/30/2021 21:56:35 - INFO - __main__ - Step 48119: {'lr': 0.0003894744486311912, 'samples': 9238848, 'steps': 48118, 'loss/train': 0.07304657250642776} 08/30/2021 21:56:36 - INFO - __main__ - Step 48120: {'lr': 0.00038947004448134937, 'samples': 9239040, 'steps': 48119, 'loss/train': 1.9490514993667603} 08/30/2021 21:56:36 - INFO - __main__ - Step 48121: {'lr': 0.0003894656402686645, 'samples': 9239232, 'steps': 48120, 'loss/train': 1.4795867204666138} 08/30/2021 21:56:36 - INFO - __main__ - Step 48122: {'lr': 0.00038946123599313846, 'samples': 9239424, 'steps': 48121, 'loss/train': 1.2509700059890747} 08/30/2021 21:56:37 - INFO - __main__ - Step 48123: {'lr': 0.0003894568316547734, 'samples': 9239616, 'steps': 48122, 'loss/train': 1.1257843971252441} 08/30/2021 21:56:38 - INFO - __main__ - Step 48124: {'lr': 0.00038945242725357127, 'samples': 9239808, 'steps': 48123, 'loss/train': 0.9880104064941406} 08/30/2021 21:56:39 - INFO - __main__ - Step 48125: {'lr': 0.000389448022789534, 'samples': 9240000, 'steps': 48124, 'loss/train': 0.9245656132698059} 08/30/2021 21:56:39 - INFO - __main__ - Step 48126: {'lr': 0.0003894436182626636, 'samples': 9240192, 'steps': 48125, 'loss/train': 0.11599001288414001} 08/30/2021 21:56:39 - INFO - __main__ - Step 48127: {'lr': 0.00038943921367296213, 'samples': 9240384, 'steps': 48126, 'loss/train': 1.3803465366363525} 08/30/2021 21:56:40 - INFO - __main__ - Step 48128: {'lr': 0.00038943480902043146, 'samples': 9240576, 'steps': 48127, 'loss/train': 1.1955361366271973} 08/30/2021 21:56:41 - INFO - __main__ - Step 48129: {'lr': 0.0003894304043050736, 'samples': 9240768, 'steps': 48128, 'loss/train': 1.4488136768341064} 08/30/2021 21:56:42 - INFO - __main__ - Step 48130: {'lr': 0.0003894259995268905, 'samples': 9240960, 'steps': 48129, 'loss/train': 0.925774335861206} 08/30/2021 21:56:42 - INFO - __main__ - Step 48131: {'lr': 0.00038942159468588423, 'samples': 9241152, 'steps': 48130, 'loss/train': 0.7424302697181702} 08/30/2021 21:56:42 - INFO - __main__ - Step 48132: {'lr': 0.00038941718978205674, 'samples': 9241344, 'steps': 48131, 'loss/train': 1.6279820203781128} 08/30/2021 21:56:43 - INFO - __main__ - Step 48133: {'lr': 0.0003894127848154101, 'samples': 9241536, 'steps': 48132, 'loss/train': 1.5197559595108032} 08/30/2021 21:56:45 - INFO - __main__ - Step 48134: {'lr': 0.0003894083797859461, 'samples': 9241728, 'steps': 48133, 'loss/train': 0.6270791888237} 08/30/2021 21:56:45 - INFO - __main__ - Step 48135: {'lr': 0.00038940397469366695, 'samples': 9241920, 'steps': 48134, 'loss/train': 1.4272571802139282} 08/30/2021 21:56:46 - INFO - __main__ - Step 48136: {'lr': 0.0003893995695385744, 'samples': 9242112, 'steps': 48135, 'loss/train': 1.1951262950897217} 08/30/2021 21:56:46 - INFO - __main__ - Step 48137: {'lr': 0.0003893951643206706, 'samples': 9242304, 'steps': 48136, 'loss/train': 1.4697294235229492} 08/30/2021 21:56:46 - INFO - __main__ - Step 48138: {'lr': 0.00038939075903995744, 'samples': 9242496, 'steps': 48137, 'loss/train': 1.3757773637771606} 08/30/2021 21:56:48 - INFO - __main__ - Step 48139: {'lr': 0.000389386353696437, 'samples': 9242688, 'steps': 48138, 'loss/train': 1.4908357858657837} 08/30/2021 21:56:48 - INFO - __main__ - Step 48140: {'lr': 0.0003893819482901113, 'samples': 9242880, 'steps': 48139, 'loss/train': 0.48751139640808105} 08/30/2021 21:56:49 - INFO - __main__ - Step 48141: {'lr': 0.0003893775428209822, 'samples': 9243072, 'steps': 48140, 'loss/train': 1.1304608583450317} 08/30/2021 21:56:49 - INFO - __main__ - Step 48142: {'lr': 0.00038937313728905164, 'samples': 9243264, 'steps': 48141, 'loss/train': 1.231481909751892} 08/30/2021 21:56:49 - INFO - __main__ - Step 48143: {'lr': 0.0003893687316943218, 'samples': 9243456, 'steps': 48142, 'loss/train': 1.433244228363037} 08/30/2021 21:56:50 - INFO - __main__ - Step 48144: {'lr': 0.0003893643260367945, 'samples': 9243648, 'steps': 48143, 'loss/train': 1.7612348794937134} 08/30/2021 21:56:51 - INFO - __main__ - Step 48145: {'lr': 0.00038935992031647183, 'samples': 9243840, 'steps': 48144, 'loss/train': 1.9286956787109375} 08/30/2021 21:56:52 - INFO - __main__ - Step 48146: {'lr': 0.00038935551453335573, 'samples': 9244032, 'steps': 48145, 'loss/train': 1.3823174238204956} 08/30/2021 21:56:52 - INFO - __main__ - Step 48147: {'lr': 0.00038935110868744817, 'samples': 9244224, 'steps': 48146, 'loss/train': 1.4182697534561157} 08/30/2021 21:56:52 - INFO - __main__ - Step 48148: {'lr': 0.0003893467027787511, 'samples': 9244416, 'steps': 48147, 'loss/train': 1.5436605215072632} 08/30/2021 21:56:53 - INFO - __main__ - Step 48149: {'lr': 0.00038934229680726663, 'samples': 9244608, 'steps': 48148, 'loss/train': 1.4788745641708374} 08/30/2021 21:56:54 - INFO - __main__ - Step 48150: {'lr': 0.0003893378907729966, 'samples': 9244800, 'steps': 48149, 'loss/train': 1.4899238348007202} 08/30/2021 21:56:55 - INFO - __main__ - Step 48151: {'lr': 0.0003893334846759431, 'samples': 9244992, 'steps': 48150, 'loss/train': 1.5928133726119995} 08/30/2021 21:56:55 - INFO - __main__ - Step 48152: {'lr': 0.0003893290785161081, 'samples': 9245184, 'steps': 48151, 'loss/train': 1.5416806936264038} 08/30/2021 21:56:55 - INFO - __main__ - Step 48153: {'lr': 0.00038932467229349353, 'samples': 9245376, 'steps': 48152, 'loss/train': 1.5753623247146606} 08/30/2021 21:56:56 - INFO - __main__ - Step 48154: {'lr': 0.0003893202660081014, 'samples': 9245568, 'steps': 48153, 'loss/train': 1.5248019695281982} 08/30/2021 21:56:57 - INFO - __main__ - Step 48155: {'lr': 0.00038931585965993384, 'samples': 9245760, 'steps': 48154, 'loss/train': 0.8895750641822815} 08/30/2021 21:56:58 - INFO - __main__ - Step 48156: {'lr': 0.0003893114532489926, 'samples': 9245952, 'steps': 48155, 'loss/train': 1.3698105812072754} 08/30/2021 21:56:58 - INFO - __main__ - Step 48157: {'lr': 0.00038930704677527975, 'samples': 9246144, 'steps': 48156, 'loss/train': 0.3844267725944519} 08/30/2021 21:56:58 - INFO - __main__ - Step 48158: {'lr': 0.00038930264023879737, 'samples': 9246336, 'steps': 48157, 'loss/train': 1.3581583499908447} 08/30/2021 21:56:59 - INFO - __main__ - Step 48159: {'lr': 0.0003892982336395473, 'samples': 9246528, 'steps': 48158, 'loss/train': 1.4068442583084106} 08/30/2021 21:57:00 - INFO - __main__ - Step 48160: {'lr': 0.00038929382697753157, 'samples': 9246720, 'steps': 48159, 'loss/train': 1.2846893072128296} 08/30/2021 21:57:01 - INFO - __main__ - Step 48161: {'lr': 0.00038928942025275227, 'samples': 9246912, 'steps': 48160, 'loss/train': 1.0771214962005615} 08/30/2021 21:57:01 - INFO - __main__ - Step 48162: {'lr': 0.00038928501346521127, 'samples': 9247104, 'steps': 48161, 'loss/train': 1.3963046073913574} 08/30/2021 21:57:01 - INFO - __main__ - Step 48163: {'lr': 0.0003892806066149106, 'samples': 9247296, 'steps': 48162, 'loss/train': 0.7078620791435242} 08/30/2021 21:57:02 - INFO - __main__ - Step 48164: {'lr': 0.00038927619970185225, 'samples': 9247488, 'steps': 48163, 'loss/train': 1.7483363151550293} 08/30/2021 21:57:03 - INFO - __main__ - Step 48165: {'lr': 0.0003892717927260382, 'samples': 9247680, 'steps': 48164, 'loss/train': 1.5239465236663818} 08/30/2021 21:57:04 - INFO - __main__ - Step 48166: {'lr': 0.00038926738568747035, 'samples': 9247872, 'steps': 48165, 'loss/train': 0.5878647565841675} 08/30/2021 21:57:04 - INFO - __main__ - Step 48167: {'lr': 0.0003892629785861509, 'samples': 9248064, 'steps': 48166, 'loss/train': 1.365415096282959} 08/30/2021 21:57:04 - INFO - __main__ - Step 48168: {'lr': 0.00038925857142208155, 'samples': 9248256, 'steps': 48167, 'loss/train': 0.9016124606132507} 08/30/2021 21:57:05 - INFO - __main__ - Step 48169: {'lr': 0.0003892541641952645, 'samples': 9248448, 'steps': 48168, 'loss/train': 1.375416874885559} 08/30/2021 21:57:06 - INFO - __main__ - Step 48170: {'lr': 0.00038924975690570173, 'samples': 9248640, 'steps': 48169, 'loss/train': 0.7157394289970398} 08/30/2021 21:57:07 - INFO - __main__ - Step 48171: {'lr': 0.0003892453495533951, 'samples': 9248832, 'steps': 48170, 'loss/train': 1.1825578212738037} 08/30/2021 21:57:07 - INFO - __main__ - Step 48172: {'lr': 0.0003892409421383467, 'samples': 9249024, 'steps': 48171, 'loss/train': 0.9246358871459961} 08/30/2021 21:57:07 - INFO - __main__ - Step 48173: {'lr': 0.0003892365346605584, 'samples': 9249216, 'steps': 48172, 'loss/train': 1.4163233041763306} 08/30/2021 21:57:08 - INFO - __main__ - Step 48174: {'lr': 0.0003892321271200324, 'samples': 9249408, 'steps': 48173, 'loss/train': 1.3543813228607178} 08/30/2021 21:57:09 - INFO - __main__ - Step 48175: {'lr': 0.0003892277195167705, 'samples': 9249600, 'steps': 48174, 'loss/train': 1.419616937637329} 08/30/2021 21:57:10 - INFO - __main__ - Step 48176: {'lr': 0.00038922331185077465, 'samples': 9249792, 'steps': 48175, 'loss/train': 1.7056647539138794} 08/30/2021 21:57:10 - INFO - __main__ - Step 48177: {'lr': 0.000389218904122047, 'samples': 9249984, 'steps': 48176, 'loss/train': 3.6409785747528076} 08/30/2021 21:57:11 - INFO - __main__ - Step 48178: {'lr': 0.00038921449633058945, 'samples': 9250176, 'steps': 48177, 'loss/train': 0.8499018549919128} 08/30/2021 21:57:11 - INFO - __main__ - Step 48179: {'lr': 0.00038921008847640407, 'samples': 9250368, 'steps': 48178, 'loss/train': 1.1665587425231934} 08/30/2021 21:57:13 - INFO - __main__ - Step 48180: {'lr': 0.0003892056805594926, 'samples': 9250560, 'steps': 48179, 'loss/train': 1.4057285785675049} 08/30/2021 21:57:13 - INFO - __main__ - Step 48181: {'lr': 0.0003892012725798574, 'samples': 9250752, 'steps': 48180, 'loss/train': 1.4164289236068726} 08/30/2021 21:57:13 - INFO - __main__ - Step 48182: {'lr': 0.00038919686453750015, 'samples': 9250944, 'steps': 48181, 'loss/train': 1.7442010641098022} 08/30/2021 21:57:14 - INFO - __main__ - Step 48183: {'lr': 0.0003891924564324229, 'samples': 9251136, 'steps': 48182, 'loss/train': 1.5402005910873413} 08/30/2021 21:57:14 - INFO - __main__ - Step 48184: {'lr': 0.0003891880482646277, 'samples': 9251328, 'steps': 48183, 'loss/train': 1.1800891160964966} 08/30/2021 21:57:16 - INFO - __main__ - Step 48185: {'lr': 0.00038918364003411656, 'samples': 9251520, 'steps': 48184, 'loss/train': 1.1317538022994995} 08/30/2021 21:57:16 - INFO - __main__ - Step 48186: {'lr': 0.0003891792317408914, 'samples': 9251712, 'steps': 48185, 'loss/train': 1.2964351177215576} 08/30/2021 21:57:16 - INFO - __main__ - Step 48187: {'lr': 0.00038917482338495424, 'samples': 9251904, 'steps': 48186, 'loss/train': 1.8063730001449585} 08/30/2021 21:57:17 - INFO - __main__ - Step 48188: {'lr': 0.000389170414966307, 'samples': 9252096, 'steps': 48187, 'loss/train': 1.4626551866531372} 08/30/2021 21:57:17 - INFO - __main__ - Step 48189: {'lr': 0.0003891660064849518, 'samples': 9252288, 'steps': 48188, 'loss/train': 1.568405032157898} 08/30/2021 21:57:19 - INFO - __main__ - Step 48190: {'lr': 0.00038916159794089044, 'samples': 9252480, 'steps': 48189, 'loss/train': 1.222964882850647} 08/30/2021 21:57:20 - INFO - __main__ - Step 48191: {'lr': 0.00038915718933412515, 'samples': 9252672, 'steps': 48190, 'loss/train': 1.3123953342437744} 08/30/2021 21:57:20 - INFO - __main__ - Step 48192: {'lr': 0.0003891527806646576, 'samples': 9252864, 'steps': 48191, 'loss/train': 1.147048830986023} 08/30/2021 21:57:20 - INFO - __main__ - Step 48193: {'lr': 0.0003891483719324901, 'samples': 9253056, 'steps': 48192, 'loss/train': 1.331035852432251} 08/30/2021 21:57:21 - INFO - __main__ - Step 48194: {'lr': 0.00038914396313762445, 'samples': 9253248, 'steps': 48193, 'loss/train': 1.5172207355499268} 08/30/2021 21:57:21 - INFO - __main__ - Step 48195: {'lr': 0.00038913955428006265, 'samples': 9253440, 'steps': 48194, 'loss/train': 1.5401694774627686} 08/30/2021 21:57:23 - INFO - __main__ - Step 48196: {'lr': 0.00038913514535980675, 'samples': 9253632, 'steps': 48195, 'loss/train': 0.1042097806930542} 08/30/2021 21:57:23 - INFO - __main__ - Step 48197: {'lr': 0.0003891307363768587, 'samples': 9253824, 'steps': 48196, 'loss/train': 1.6444669961929321} 08/30/2021 21:57:23 - INFO - __main__ - Step 48198: {'lr': 0.00038912632733122045, 'samples': 9254016, 'steps': 48197, 'loss/train': 1.709092617034912} 08/30/2021 21:57:24 - INFO - __main__ - Step 48199: {'lr': 0.000389121918222894, 'samples': 9254208, 'steps': 48198, 'loss/train': 1.2692484855651855} 08/30/2021 21:57:24 - INFO - __main__ - Step 48200: {'lr': 0.0003891175090518814, 'samples': 9254400, 'steps': 48199, 'loss/train': 1.3176255226135254} 08/30/2021 21:57:26 - INFO - __main__ - Step 48201: {'lr': 0.00038911309981818466, 'samples': 9254592, 'steps': 48200, 'loss/train': 1.8013050556182861} 08/30/2021 21:57:26 - INFO - __main__ - Step 48202: {'lr': 0.00038910869052180563, 'samples': 9254784, 'steps': 48201, 'loss/train': 1.311497449874878} 08/30/2021 21:57:26 - INFO - __main__ - Step 48203: {'lr': 0.00038910428116274644, 'samples': 9254976, 'steps': 48202, 'loss/train': 1.6864207983016968} 08/30/2021 21:57:27 - INFO - __main__ - Step 48204: {'lr': 0.0003890998717410089, 'samples': 9255168, 'steps': 48203, 'loss/train': 1.054111123085022} 08/30/2021 21:57:27 - INFO - __main__ - Step 48205: {'lr': 0.0003890954622565952, 'samples': 9255360, 'steps': 48204, 'loss/train': 1.192077398300171} 08/30/2021 21:57:29 - INFO - __main__ - Step 48206: {'lr': 0.00038909105270950716, 'samples': 9255552, 'steps': 48205, 'loss/train': 0.4235106110572815} 08/30/2021 21:57:29 - INFO - __main__ - Step 48207: {'lr': 0.0003890866430997468, 'samples': 9255744, 'steps': 48206, 'loss/train': 1.1917065382003784} 08/30/2021 21:57:30 - INFO - __main__ - Step 48208: {'lr': 0.0003890822334273163, 'samples': 9255936, 'steps': 48207, 'loss/train': 1.5207353830337524} 08/30/2021 21:57:30 - INFO - __main__ - Step 48209: {'lr': 0.0003890778236922174, 'samples': 9256128, 'steps': 48208, 'loss/train': 1.5800981521606445} 08/30/2021 21:57:30 - INFO - __main__ - Step 48210: {'lr': 0.00038907341389445217, 'samples': 9256320, 'steps': 48209, 'loss/train': 1.5544887781143188} 08/30/2021 21:57:32 - INFO - __main__ - Step 48211: {'lr': 0.0003890690040340226, 'samples': 9256512, 'steps': 48210, 'loss/train': 1.1500834226608276} 08/30/2021 21:57:32 - INFO - __main__ - Step 48212: {'lr': 0.00038906459411093075, 'samples': 9256704, 'steps': 48211, 'loss/train': 1.1569143533706665} 08/30/2021 21:57:33 - INFO - __main__ - Step 48213: {'lr': 0.0003890601841251785, 'samples': 9256896, 'steps': 48212, 'loss/train': 1.6261870861053467} 08/30/2021 21:57:33 - INFO - __main__ - Step 48214: {'lr': 0.0003890557740767678, 'samples': 9257088, 'steps': 48213, 'loss/train': 0.5921133160591125} 08/30/2021 21:57:33 - INFO - __main__ - Step 48215: {'lr': 0.00038905136396570085, 'samples': 9257280, 'steps': 48214, 'loss/train': 1.7807836532592773} 08/30/2021 21:57:35 - INFO - __main__ - Step 48216: {'lr': 0.0003890469537919794, 'samples': 9257472, 'steps': 48215, 'loss/train': 1.232125997543335} 08/30/2021 21:57:36 - INFO - __main__ - Step 48217: {'lr': 0.0003890425435556055, 'samples': 9257664, 'steps': 48216, 'loss/train': 1.121621012687683} 08/30/2021 21:57:36 - INFO - __main__ - Step 48218: {'lr': 0.0003890381332565813, 'samples': 9257856, 'steps': 48217, 'loss/train': 1.8275268077850342} 08/30/2021 21:57:36 - INFO - __main__ - Step 48219: {'lr': 0.00038903372289490865, 'samples': 9258048, 'steps': 48218, 'loss/train': 1.3870809078216553} 08/30/2021 21:57:37 - INFO - __main__ - Step 48220: {'lr': 0.0003890293124705895, 'samples': 9258240, 'steps': 48219, 'loss/train': 1.0716545581817627} 08/30/2021 21:57:37 - INFO - __main__ - Step 48221: {'lr': 0.0003890249019836259, 'samples': 9258432, 'steps': 48220, 'loss/train': 2.0319488048553467} 08/30/2021 21:57:39 - INFO - __main__ - Step 48222: {'lr': 0.0003890204914340198, 'samples': 9258624, 'steps': 48221, 'loss/train': 1.296714425086975} 08/30/2021 21:57:39 - INFO - __main__ - Step 48223: {'lr': 0.00038901608082177327, 'samples': 9258816, 'steps': 48222, 'loss/train': 0.04402359947562218} 08/30/2021 21:57:39 - INFO - __main__ - Step 48224: {'lr': 0.0003890116701468882, 'samples': 9259008, 'steps': 48223, 'loss/train': 1.3679606914520264} 08/30/2021 21:57:40 - INFO - __main__ - Step 48225: {'lr': 0.0003890072594093666, 'samples': 9259200, 'steps': 48224, 'loss/train': 0.8457120060920715} 08/30/2021 21:57:40 - INFO - __main__ - Step 48226: {'lr': 0.00038900284860921046, 'samples': 9259392, 'steps': 48225, 'loss/train': 1.311064600944519} 08/30/2021 21:57:42 - INFO - __main__ - Step 48227: {'lr': 0.00038899843774642184, 'samples': 9259584, 'steps': 48226, 'loss/train': 3.014810085296631} 08/30/2021 21:57:42 - INFO - __main__ - Step 48228: {'lr': 0.00038899402682100265, 'samples': 9259776, 'steps': 48227, 'loss/train': 1.0211178064346313} 08/30/2021 21:57:42 - INFO - __main__ - Step 48229: {'lr': 0.0003889896158329549, 'samples': 9259968, 'steps': 48228, 'loss/train': 1.471662163734436} 08/30/2021 21:57:43 - INFO - __main__ - Step 48230: {'lr': 0.00038898520478228055, 'samples': 9260160, 'steps': 48229, 'loss/train': 0.9295299053192139} 08/30/2021 21:57:43 - INFO - __main__ - Step 48231: {'lr': 0.00038898079366898164, 'samples': 9260352, 'steps': 48230, 'loss/train': 2.265153408050537} 08/30/2021 21:57:45 - INFO - __main__ - Step 48232: {'lr': 0.0003889763824930601, 'samples': 9260544, 'steps': 48231, 'loss/train': 1.3204606771469116} 08/30/2021 21:57:45 - INFO - __main__ - Step 48233: {'lr': 0.00038897197125451795, 'samples': 9260736, 'steps': 48232, 'loss/train': 1.5183383226394653} 08/30/2021 21:57:46 - INFO - __main__ - Step 48234: {'lr': 0.0003889675599533572, 'samples': 9260928, 'steps': 48233, 'loss/train': 1.4311165809631348} 08/30/2021 21:57:46 - INFO - __main__ - Step 48235: {'lr': 0.0003889631485895798, 'samples': 9261120, 'steps': 48234, 'loss/train': 1.4235327243804932} 08/30/2021 21:57:46 - INFO - __main__ - Step 48236: {'lr': 0.00038895873716318776, 'samples': 9261312, 'steps': 48235, 'loss/train': 1.9887962341308594} 08/30/2021 21:57:48 - INFO - __main__ - Step 48237: {'lr': 0.000388954325674183, 'samples': 9261504, 'steps': 48236, 'loss/train': 0.8699989914894104} 08/30/2021 21:57:48 - INFO - __main__ - Step 48238: {'lr': 0.00038894991412256766, 'samples': 9261696, 'steps': 48237, 'loss/train': 1.5515996217727661} 08/30/2021 21:57:48 - INFO - __main__ - Step 48239: {'lr': 0.00038894550250834355, 'samples': 9261888, 'steps': 48238, 'loss/train': 1.2451509237289429} 08/30/2021 21:57:49 - INFO - __main__ - Step 48240: {'lr': 0.00038894109083151274, 'samples': 9262080, 'steps': 48239, 'loss/train': 1.6446844339370728} 08/30/2021 21:57:49 - INFO - __main__ - Step 48241: {'lr': 0.0003889366790920773, 'samples': 9262272, 'steps': 48240, 'loss/train': 1.305234432220459} 08/30/2021 21:57:51 - INFO - __main__ - Step 48242: {'lr': 0.00038893226729003904, 'samples': 9262464, 'steps': 48241, 'loss/train': 2.496769905090332} 08/30/2021 21:57:52 - INFO - __main__ - Step 48243: {'lr': 0.0003889278554254001, 'samples': 9262656, 'steps': 48242, 'loss/train': 0.2142036408185959} 08/30/2021 21:57:52 - INFO - __main__ - Step 48244: {'lr': 0.00038892344349816246, 'samples': 9262848, 'steps': 48243, 'loss/train': 1.3455396890640259} 08/30/2021 21:57:52 - INFO - __main__ - Step 48245: {'lr': 0.00038891903150832795, 'samples': 9263040, 'steps': 48244, 'loss/train': 1.6460636854171753} 08/30/2021 21:57:53 - INFO - __main__ - Step 48246: {'lr': 0.00038891461945589866, 'samples': 9263232, 'steps': 48245, 'loss/train': 1.3758220672607422} 08/30/2021 21:57:53 - INFO - __main__ - Step 48247: {'lr': 0.0003889102073408767, 'samples': 9263424, 'steps': 48246, 'loss/train': 1.6581454277038574} 08/30/2021 21:57:55 - INFO - __main__ - Step 48248: {'lr': 0.0003889057951632639, 'samples': 9263616, 'steps': 48247, 'loss/train': 0.8149415850639343} 08/30/2021 21:57:55 - INFO - __main__ - Step 48249: {'lr': 0.0003889013829230623, 'samples': 9263808, 'steps': 48248, 'loss/train': 1.3481032848358154} 08/30/2021 21:57:56 - INFO - __main__ - Step 48250: {'lr': 0.00038889697062027384, 'samples': 9264000, 'steps': 48249, 'loss/train': 1.7648568153381348} 08/30/2021 21:57:56 - INFO - __main__ - Step 48251: {'lr': 0.00038889255825490053, 'samples': 9264192, 'steps': 48250, 'loss/train': 1.4959568977355957} 08/30/2021 21:57:56 - INFO - __main__ - Step 48252: {'lr': 0.0003888881458269444, 'samples': 9264384, 'steps': 48251, 'loss/train': 1.0035902261734009} 08/30/2021 21:57:58 - INFO - __main__ - Step 48253: {'lr': 0.00038888373333640746, 'samples': 9264576, 'steps': 48252, 'loss/train': 1.2284576892852783} 08/30/2021 21:57:58 - INFO - __main__ - Step 48254: {'lr': 0.00038887932078329165, 'samples': 9264768, 'steps': 48253, 'loss/train': 1.819913625717163} 08/30/2021 21:57:59 - INFO - __main__ - Step 48255: {'lr': 0.00038887490816759895, 'samples': 9264960, 'steps': 48254, 'loss/train': 1.5095142126083374} 08/30/2021 21:57:59 - INFO - __main__ - Step 48256: {'lr': 0.00038887049548933135, 'samples': 9265152, 'steps': 48255, 'loss/train': 1.1086269617080688} 08/30/2021 21:57:59 - INFO - __main__ - Step 48257: {'lr': 0.0003888660827484908, 'samples': 9265344, 'steps': 48256, 'loss/train': 1.3071212768554688} 08/30/2021 21:58:01 - INFO - __main__ - Step 48258: {'lr': 0.00038886166994507945, 'samples': 9265536, 'steps': 48257, 'loss/train': 1.7825593948364258} 08/30/2021 21:58:01 - INFO - __main__ - Step 48259: {'lr': 0.00038885725707909905, 'samples': 9265728, 'steps': 48258, 'loss/train': 1.3432456254959106} 08/30/2021 21:58:02 - INFO - __main__ - Step 48260: {'lr': 0.0003888528441505518, 'samples': 9265920, 'steps': 48259, 'loss/train': 1.4666707515716553} 08/30/2021 21:58:02 - INFO - __main__ - Step 48261: {'lr': 0.00038884843115943955, 'samples': 9266112, 'steps': 48260, 'loss/train': 1.1235095262527466} 08/30/2021 21:58:02 - INFO - __main__ - Step 48262: {'lr': 0.00038884401810576434, 'samples': 9266304, 'steps': 48261, 'loss/train': 1.0756359100341797} 08/30/2021 21:58:04 - INFO - __main__ - Step 48263: {'lr': 0.0003888396049895282, 'samples': 9266496, 'steps': 48262, 'loss/train': 1.815375566482544} 08/30/2021 21:58:04 - INFO - __main__ - Step 48264: {'lr': 0.000388835191810733, 'samples': 9266688, 'steps': 48263, 'loss/train': 1.6188507080078125} 08/30/2021 21:58:05 - INFO - __main__ - Step 48265: {'lr': 0.0003888307785693809, 'samples': 9266880, 'steps': 48264, 'loss/train': 1.4475008249282837} 08/30/2021 21:58:05 - INFO - __main__ - Step 48266: {'lr': 0.0003888263652654738, 'samples': 9267072, 'steps': 48265, 'loss/train': 1.5052590370178223} 08/30/2021 21:58:05 - INFO - __main__ - Step 48267: {'lr': 0.0003888219518990136, 'samples': 9267264, 'steps': 48266, 'loss/train': 1.113168716430664} 08/30/2021 21:58:07 - INFO - __main__ - Step 48268: {'lr': 0.0003888175384700024, 'samples': 9267456, 'steps': 48267, 'loss/train': 1.3512853384017944} 08/30/2021 21:58:07 - INFO - __main__ - Step 48269: {'lr': 0.0003888131249784421, 'samples': 9267648, 'steps': 48268, 'loss/train': 1.8217908143997192} 08/30/2021 21:58:08 - INFO - __main__ - Step 48270: {'lr': 0.00038880871142433484, 'samples': 9267840, 'steps': 48269, 'loss/train': 1.1951217651367188} 08/30/2021 21:58:08 - INFO - __main__ - Step 48271: {'lr': 0.0003888042978076825, 'samples': 9268032, 'steps': 48270, 'loss/train': 0.6636618971824646} 08/30/2021 21:58:08 - INFO - __main__ - Step 48272: {'lr': 0.00038879988412848706, 'samples': 9268224, 'steps': 48271, 'loss/train': 1.0012128353118896} 08/30/2021 21:58:10 - INFO - __main__ - Step 48273: {'lr': 0.00038879547038675054, 'samples': 9268416, 'steps': 48272, 'loss/train': 2.0873050689697266} 08/30/2021 21:58:10 - INFO - __main__ - Step 48274: {'lr': 0.0003887910565824749, 'samples': 9268608, 'steps': 48273, 'loss/train': 0.6913456916809082} 08/30/2021 21:58:11 - INFO - __main__ - Step 48275: {'lr': 0.0003887866427156622, 'samples': 9268800, 'steps': 48274, 'loss/train': 1.6065735816955566} 08/30/2021 21:58:11 - INFO - __main__ - Step 48276: {'lr': 0.00038878222878631444, 'samples': 9268992, 'steps': 48275, 'loss/train': 1.3543517589569092} 08/30/2021 21:58:11 - INFO - __main__ - Step 48277: {'lr': 0.0003887778147944334, 'samples': 9269184, 'steps': 48276, 'loss/train': 1.6978094577789307} 08/30/2021 21:58:13 - INFO - __main__ - Step 48278: {'lr': 0.0003887734007400213, 'samples': 9269376, 'steps': 48277, 'loss/train': 0.6138620972633362} 08/30/2021 21:58:13 - INFO - __main__ - Step 48279: {'lr': 0.00038876898662308, 'samples': 9269568, 'steps': 48278, 'loss/train': 1.3005942106246948} 08/30/2021 21:58:14 - INFO - __main__ - Step 48280: {'lr': 0.00038876457244361166, 'samples': 9269760, 'steps': 48279, 'loss/train': 1.3384491205215454} 08/30/2021 21:58:14 - INFO - __main__ - Step 48281: {'lr': 0.000388760158201618, 'samples': 9269952, 'steps': 48280, 'loss/train': 1.2069329023361206} 08/30/2021 21:58:14 - INFO - __main__ - Step 48282: {'lr': 0.0003887557438971012, 'samples': 9270144, 'steps': 48281, 'loss/train': 1.4133845567703247} 08/30/2021 21:58:15 - INFO - __main__ - Step 48283: {'lr': 0.0003887513295300632, 'samples': 9270336, 'steps': 48282, 'loss/train': 1.0987493991851807} 08/30/2021 21:58:16 - INFO - __main__ - Step 48284: {'lr': 0.00038874691510050604, 'samples': 9270528, 'steps': 48283, 'loss/train': 1.3501638174057007} 08/30/2021 21:58:17 - INFO - __main__ - Step 48285: {'lr': 0.00038874250060843163, 'samples': 9270720, 'steps': 48284, 'loss/train': 1.2690856456756592} 08/30/2021 21:58:17 - INFO - __main__ - Step 48286: {'lr': 0.00038873808605384197, 'samples': 9270912, 'steps': 48285, 'loss/train': 1.2772575616836548} 08/30/2021 21:58:17 - INFO - __main__ - Step 48287: {'lr': 0.0003887336714367391, 'samples': 9271104, 'steps': 48286, 'loss/train': 1.1695002317428589} 08/30/2021 21:58:18 - INFO - __main__ - Step 48288: {'lr': 0.00038872925675712493, 'samples': 9271296, 'steps': 48287, 'loss/train': 1.7818000316619873} 08/30/2021 21:58:19 - INFO - __main__ - Step 48289: {'lr': 0.0003887248420150016, 'samples': 9271488, 'steps': 48288, 'loss/train': 1.5280708074569702} 08/30/2021 21:58:20 - INFO - __main__ - Step 48290: {'lr': 0.00038872042721037087, 'samples': 9271680, 'steps': 48289, 'loss/train': 1.4469332695007324} 08/30/2021 21:58:20 - INFO - __main__ - Step 48291: {'lr': 0.00038871601234323494, 'samples': 9271872, 'steps': 48290, 'loss/train': 1.1884874105453491} 08/30/2021 21:58:20 - INFO - __main__ - Step 48292: {'lr': 0.00038871159741359567, 'samples': 9272064, 'steps': 48291, 'loss/train': 1.6146996021270752} 08/30/2021 21:58:21 - INFO - __main__ - Step 48293: {'lr': 0.0003887071824214551, 'samples': 9272256, 'steps': 48292, 'loss/train': 1.3789864778518677} 08/30/2021 21:58:23 - INFO - __main__ - Step 48294: {'lr': 0.0003887027673668152, 'samples': 9272448, 'steps': 48293, 'loss/train': 1.115086317062378} 08/30/2021 21:58:23 - INFO - __main__ - Step 48295: {'lr': 0.0003886983522496781, 'samples': 9272640, 'steps': 48294, 'loss/train': 1.1463960409164429} 08/30/2021 21:58:24 - INFO - __main__ - Step 48296: {'lr': 0.00038869393707004554, 'samples': 9272832, 'steps': 48295, 'loss/train': 1.7747620344161987} 08/30/2021 21:58:24 - INFO - __main__ - Step 48297: {'lr': 0.00038868952182791964, 'samples': 9273024, 'steps': 48296, 'loss/train': 1.1227610111236572} 08/30/2021 21:58:24 - INFO - __main__ - Step 48298: {'lr': 0.0003886851065233024, 'samples': 9273216, 'steps': 48297, 'loss/train': 1.5021138191223145} 08/30/2021 21:58:26 - INFO - __main__ - Step 48299: {'lr': 0.0003886806911561958, 'samples': 9273408, 'steps': 48298, 'loss/train': 1.6091890335083008} 08/30/2021 21:58:26 - INFO - __main__ - Step 48300: {'lr': 0.0003886762757266018, 'samples': 9273600, 'steps': 48299, 'loss/train': 1.3598541021347046} 08/30/2021 21:58:27 - INFO - __main__ - Step 48301: {'lr': 0.0003886718602345224, 'samples': 9273792, 'steps': 48300, 'loss/train': 1.5867159366607666} 08/30/2021 21:58:27 - INFO - __main__ - Step 48302: {'lr': 0.0003886674446799596, 'samples': 9273984, 'steps': 48301, 'loss/train': 1.312446117401123} 08/30/2021 21:58:27 - INFO - __main__ - Step 48303: {'lr': 0.00038866302906291546, 'samples': 9274176, 'steps': 48302, 'loss/train': 0.038343943655490875} 08/30/2021 21:58:29 - INFO - __main__ - Step 48304: {'lr': 0.0003886586133833918, 'samples': 9274368, 'steps': 48303, 'loss/train': 1.187606692314148} 08/30/2021 21:58:29 - INFO - __main__ - Step 48305: {'lr': 0.00038865419764139077, 'samples': 9274560, 'steps': 48304, 'loss/train': 0.21710127592086792} 08/30/2021 21:58:30 - INFO - __main__ - Step 48306: {'lr': 0.00038864978183691425, 'samples': 9274752, 'steps': 48305, 'loss/train': 1.1679391860961914} 08/30/2021 21:58:30 - INFO - __main__ - Step 48307: {'lr': 0.00038864536596996437, 'samples': 9274944, 'steps': 48306, 'loss/train': 1.4437044858932495} 08/30/2021 21:58:31 - INFO - __main__ - Step 48308: {'lr': 0.0003886409500405429, 'samples': 9275136, 'steps': 48307, 'loss/train': 0.963511049747467} 08/30/2021 21:58:32 - INFO - __main__ - Step 48309: {'lr': 0.00038863653404865207, 'samples': 9275328, 'steps': 48308, 'loss/train': 1.4042670726776123} 08/30/2021 21:58:32 - INFO - __main__ - Step 48310: {'lr': 0.0003886321179942937, 'samples': 9275520, 'steps': 48309, 'loss/train': 1.1079864501953125} 08/30/2021 21:58:33 - INFO - __main__ - Step 48311: {'lr': 0.0003886277018774699, 'samples': 9275712, 'steps': 48310, 'loss/train': 1.093345284461975} 08/30/2021 21:58:33 - INFO - __main__ - Step 48312: {'lr': 0.0003886232856981825, 'samples': 9275904, 'steps': 48311, 'loss/train': 1.77463698387146} 08/30/2021 21:58:34 - INFO - __main__ - Step 48313: {'lr': 0.00038861886945643363, 'samples': 9276096, 'steps': 48312, 'loss/train': 1.984765887260437} 08/30/2021 21:58:35 - INFO - __main__ - Step 48314: {'lr': 0.00038861445315222523, 'samples': 9276288, 'steps': 48313, 'loss/train': 0.5787181258201599} 08/30/2021 21:58:36 - INFO - __main__ - Step 48315: {'lr': 0.00038861003678555936, 'samples': 9276480, 'steps': 48314, 'loss/train': 0.8000352382659912} 08/30/2021 21:58:36 - INFO - __main__ - Step 48316: {'lr': 0.00038860562035643786, 'samples': 9276672, 'steps': 48315, 'loss/train': 1.992283582687378} 08/30/2021 21:58:37 - INFO - __main__ - Step 48317: {'lr': 0.00038860120386486285, 'samples': 9276864, 'steps': 48316, 'loss/train': 1.4223742485046387} 08/30/2021 21:58:37 - INFO - __main__ - Step 48318: {'lr': 0.00038859678731083627, 'samples': 9277056, 'steps': 48317, 'loss/train': 1.3210381269454956} 08/30/2021 21:58:37 - INFO - __main__ - Step 48319: {'lr': 0.0003885923706943601, 'samples': 9277248, 'steps': 48318, 'loss/train': 0.06078751012682915} 08/30/2021 21:58:39 - INFO - __main__ - Step 48320: {'lr': 0.00038858795401543634, 'samples': 9277440, 'steps': 48319, 'loss/train': 1.268423080444336} 08/30/2021 21:58:39 - INFO - __main__ - Step 48321: {'lr': 0.000388583537274067, 'samples': 9277632, 'steps': 48320, 'loss/train': 1.5062557458877563} 08/30/2021 21:58:39 - INFO - __main__ - Step 48322: {'lr': 0.0003885791204702541, 'samples': 9277824, 'steps': 48321, 'loss/train': 1.3718653917312622} 08/30/2021 21:58:40 - INFO - __main__ - Step 48323: {'lr': 0.0003885747036039995, 'samples': 9278016, 'steps': 48322, 'loss/train': 1.2255308628082275} 08/30/2021 21:58:40 - INFO - __main__ - Step 48324: {'lr': 0.0003885702866753054, 'samples': 9278208, 'steps': 48323, 'loss/train': 1.0981525182724} 08/30/2021 21:58:42 - INFO - __main__ - Step 48325: {'lr': 0.00038856586968417353, 'samples': 9278400, 'steps': 48324, 'loss/train': 1.5038059949874878} 08/30/2021 21:58:42 - INFO - __main__ - Step 48326: {'lr': 0.00038856145263060606, 'samples': 9278592, 'steps': 48325, 'loss/train': 1.1133569478988647} 08/30/2021 21:58:43 - INFO - __main__ - Step 48327: {'lr': 0.00038855703551460497, 'samples': 9278784, 'steps': 48326, 'loss/train': 1.0519733428955078} 08/30/2021 21:58:43 - INFO - __main__ - Step 48328: {'lr': 0.00038855261833617216, 'samples': 9278976, 'steps': 48327, 'loss/train': 0.07743918895721436} 08/30/2021 21:58:43 - INFO - __main__ - Step 48329: {'lr': 0.00038854820109530974, 'samples': 9279168, 'steps': 48328, 'loss/train': 0.9702709317207336} 08/30/2021 21:58:45 - INFO - __main__ - Step 48330: {'lr': 0.00038854378379201966, 'samples': 9279360, 'steps': 48329, 'loss/train': 1.2366012334823608} 08/30/2021 21:58:45 - INFO - __main__ - Step 48331: {'lr': 0.0003885393664263038, 'samples': 9279552, 'steps': 48330, 'loss/train': 1.2706016302108765} 08/30/2021 21:58:46 - INFO - __main__ - Step 48332: {'lr': 0.00038853494899816434, 'samples': 9279744, 'steps': 48331, 'loss/train': 1.6393556594848633} 08/30/2021 21:58:46 - INFO - __main__ - Step 48333: {'lr': 0.0003885305315076031, 'samples': 9279936, 'steps': 48332, 'loss/train': 1.8684183359146118} 08/30/2021 21:58:46 - INFO - __main__ - Step 48334: {'lr': 0.0003885261139546221, 'samples': 9280128, 'steps': 48333, 'loss/train': 1.480150818824768} 08/30/2021 21:58:48 - INFO - __main__ - Step 48335: {'lr': 0.00038852169633922344, 'samples': 9280320, 'steps': 48334, 'loss/train': 1.5422346591949463} 08/30/2021 21:58:48 - INFO - __main__ - Step 48336: {'lr': 0.00038851727866140906, 'samples': 9280512, 'steps': 48335, 'loss/train': 1.3034451007843018} 08/30/2021 21:58:49 - INFO - __main__ - Step 48337: {'lr': 0.00038851286092118095, 'samples': 9280704, 'steps': 48336, 'loss/train': 0.8110340237617493} 08/30/2021 21:58:49 - INFO - __main__ - Step 48338: {'lr': 0.0003885084431185411, 'samples': 9280896, 'steps': 48337, 'loss/train': 1.1553807258605957} 08/30/2021 21:58:49 - INFO - __main__ - Step 48339: {'lr': 0.0003885040252534913, 'samples': 9281088, 'steps': 48338, 'loss/train': 0.9764419794082642} 08/30/2021 21:58:50 - INFO - __main__ - Step 48340: {'lr': 0.00038849960732603386, 'samples': 9281280, 'steps': 48339, 'loss/train': 0.7394328117370605} 08/30/2021 21:58:51 - INFO - __main__ - Step 48341: {'lr': 0.00038849518933617064, 'samples': 9281472, 'steps': 48340, 'loss/train': 1.1356828212738037} 08/30/2021 21:58:52 - INFO - __main__ - Step 48342: {'lr': 0.0003884907712839036, 'samples': 9281664, 'steps': 48341, 'loss/train': 1.5415717363357544} 08/30/2021 21:58:52 - INFO - __main__ - Step 48343: {'lr': 0.00038848635316923475, 'samples': 9281856, 'steps': 48342, 'loss/train': 1.4904346466064453} 08/30/2021 21:58:52 - INFO - __main__ - Step 48344: {'lr': 0.0003884819349921661, 'samples': 9282048, 'steps': 48343, 'loss/train': 1.1626802682876587} 08/30/2021 21:58:53 - INFO - __main__ - Step 48345: {'lr': 0.0003884775167526996, 'samples': 9282240, 'steps': 48344, 'loss/train': 2.119408130645752} 08/30/2021 21:58:54 - INFO - __main__ - Step 48346: {'lr': 0.0003884730984508373, 'samples': 9282432, 'steps': 48345, 'loss/train': 1.39040207862854} 08/30/2021 21:58:55 - INFO - __main__ - Step 48347: {'lr': 0.0003884686800865812, 'samples': 9282624, 'steps': 48346, 'loss/train': 1.1078393459320068} 08/30/2021 21:58:55 - INFO - __main__ - Step 48348: {'lr': 0.0003884642616599331, 'samples': 9282816, 'steps': 48347, 'loss/train': 0.9484126567840576} 08/30/2021 21:58:55 - INFO - __main__ - Step 48349: {'lr': 0.00038845984317089526, 'samples': 9283008, 'steps': 48348, 'loss/train': 1.0910555124282837} 08/30/2021 21:58:56 - INFO - __main__ - Step 48350: {'lr': 0.00038845542461946953, 'samples': 9283200, 'steps': 48349, 'loss/train': 1.940859317779541} 08/30/2021 21:58:58 - INFO - __main__ - Step 48351: {'lr': 0.00038845100600565794, 'samples': 9283392, 'steps': 48350, 'loss/train': 1.7277929782867432} 08/30/2021 21:58:58 - INFO - __main__ - Step 48352: {'lr': 0.00038844658732946244, 'samples': 9283584, 'steps': 48351, 'loss/train': 1.2096253633499146} 08/30/2021 21:58:59 - INFO - __main__ - Step 48353: {'lr': 0.000388442168590885, 'samples': 9283776, 'steps': 48352, 'loss/train': 1.2793059349060059} 08/30/2021 21:58:59 - INFO - __main__ - Step 48354: {'lr': 0.00038843774978992773, 'samples': 9283968, 'steps': 48353, 'loss/train': 1.665263056755066} 08/30/2021 21:58:59 - INFO - __main__ - Step 48355: {'lr': 0.0003884333309265925, 'samples': 9284160, 'steps': 48354, 'loss/train': 1.4314162731170654} 08/30/2021 21:59:00 - INFO - __main__ - Step 48356: {'lr': 0.00038842891200088135, 'samples': 9284352, 'steps': 48355, 'loss/train': 1.1668885946273804} 08/30/2021 21:59:02 - INFO - __main__ - Step 48357: {'lr': 0.0003884244930127963, 'samples': 9284544, 'steps': 48356, 'loss/train': 1.2831779718399048} 08/30/2021 21:59:02 - INFO - __main__ - Step 48358: {'lr': 0.0003884200739623393, 'samples': 9284736, 'steps': 48357, 'loss/train': 1.6840825080871582} 08/30/2021 21:59:02 - INFO - __main__ - Step 48359: {'lr': 0.00038841565484951237, 'samples': 9284928, 'steps': 48358, 'loss/train': 1.087289571762085} 08/30/2021 21:59:03 - INFO - __main__ - Step 48360: {'lr': 0.0003884112356743175, 'samples': 9285120, 'steps': 48359, 'loss/train': 1.6617010831832886} 08/30/2021 21:59:03 - INFO - __main__ - Step 48361: {'lr': 0.0003884068164367566, 'samples': 9285312, 'steps': 48360, 'loss/train': 1.6421316862106323} 08/30/2021 21:59:05 - INFO - __main__ - Step 48362: {'lr': 0.00038840239713683165, 'samples': 9285504, 'steps': 48361, 'loss/train': 1.23919677734375} 08/30/2021 21:59:05 - INFO - __main__ - Step 48363: {'lr': 0.0003883979777745449, 'samples': 9285696, 'steps': 48362, 'loss/train': 0.9007788896560669} 08/30/2021 21:59:05 - INFO - __main__ - Step 48364: {'lr': 0.00038839355834989806, 'samples': 9285888, 'steps': 48363, 'loss/train': 1.819191813468933} 08/30/2021 21:59:06 - INFO - __main__ - Step 48365: {'lr': 0.0003883891388628932, 'samples': 9286080, 'steps': 48364, 'loss/train': 1.2570253610610962} 08/30/2021 21:59:06 - INFO - __main__ - Step 48366: {'lr': 0.0003883847193135323, 'samples': 9286272, 'steps': 48365, 'loss/train': 0.1363932490348816} 08/30/2021 21:59:08 - INFO - __main__ - Step 48367: {'lr': 0.0003883802997018174, 'samples': 9286464, 'steps': 48366, 'loss/train': 1.0962309837341309} 08/30/2021 21:59:08 - INFO - __main__ - Step 48368: {'lr': 0.00038837588002775054, 'samples': 9286656, 'steps': 48367, 'loss/train': 1.1666758060455322} 08/30/2021 21:59:08 - INFO - __main__ - Step 48369: {'lr': 0.0003883714602913336, 'samples': 9286848, 'steps': 48368, 'loss/train': 1.0255509614944458} 08/30/2021 21:59:09 - INFO - __main__ - Step 48370: {'lr': 0.00038836704049256864, 'samples': 9287040, 'steps': 48369, 'loss/train': 1.2940367460250854} 08/30/2021 21:59:09 - INFO - __main__ - Step 48371: {'lr': 0.0003883626206314577, 'samples': 9287232, 'steps': 48370, 'loss/train': 1.3935354948043823} 08/30/2021 21:59:09 - INFO - __main__ - Step 48372: {'lr': 0.0003883582007080025, 'samples': 9287424, 'steps': 48371, 'loss/train': 1.1138713359832764} 08/30/2021 21:59:11 - INFO - __main__ - Step 48373: {'lr': 0.0003883537807222054, 'samples': 9287616, 'steps': 48372, 'loss/train': 1.8047584295272827} 08/30/2021 21:59:11 - INFO - __main__ - Step 48374: {'lr': 0.0003883493606740681, 'samples': 9287808, 'steps': 48373, 'loss/train': 1.9533841609954834} 08/30/2021 21:59:12 - INFO - __main__ - Step 48375: {'lr': 0.0003883449405635928, 'samples': 9288000, 'steps': 48374, 'loss/train': 1.3703405857086182} 08/30/2021 21:59:12 - INFO - __main__ - Step 48376: {'lr': 0.0003883405203907814, 'samples': 9288192, 'steps': 48375, 'loss/train': 1.1228867769241333} 08/30/2021 21:59:12 - INFO - __main__ - Step 48377: {'lr': 0.0003883361001556359, 'samples': 9288384, 'steps': 48376, 'loss/train': 1.0904194116592407} 08/30/2021 21:59:14 - INFO - __main__ - Step 48378: {'lr': 0.0003883316798581582, 'samples': 9288576, 'steps': 48377, 'loss/train': 0.3879660367965698} 08/30/2021 21:59:14 - INFO - __main__ - Step 48379: {'lr': 0.0003883272594983505, 'samples': 9288768, 'steps': 48378, 'loss/train': 1.7464022636413574} 08/30/2021 21:59:15 - INFO - __main__ - Step 48380: {'lr': 0.00038832283907621457, 'samples': 9288960, 'steps': 48379, 'loss/train': 1.7930223941802979} 08/30/2021 21:59:15 - INFO - __main__ - Step 48381: {'lr': 0.00038831841859175253, 'samples': 9289152, 'steps': 48380, 'loss/train': 1.3664124011993408} 08/30/2021 21:59:16 - INFO - __main__ - Step 48382: {'lr': 0.0003883139980449664, 'samples': 9289344, 'steps': 48381, 'loss/train': 1.7374769449234009} 08/30/2021 21:59:17 - INFO - __main__ - Step 48383: {'lr': 0.00038830957743585807, 'samples': 9289536, 'steps': 48382, 'loss/train': 0.6134921312332153} 08/30/2021 21:59:17 - INFO - __main__ - Step 48384: {'lr': 0.0003883051567644296, 'samples': 9289728, 'steps': 48383, 'loss/train': 1.443073034286499} 08/30/2021 21:59:18 - INFO - __main__ - Step 48385: {'lr': 0.00038830073603068297, 'samples': 9289920, 'steps': 48384, 'loss/train': 0.6213002800941467} 08/30/2021 21:59:18 - INFO - __main__ - Step 48386: {'lr': 0.00038829631523462003, 'samples': 9290112, 'steps': 48385, 'loss/train': 1.1812790632247925} 08/30/2021 21:59:18 - INFO - __main__ - Step 48387: {'lr': 0.000388291894376243, 'samples': 9290304, 'steps': 48386, 'loss/train': 1.1856460571289062} 08/30/2021 21:59:20 - INFO - __main__ - Step 48388: {'lr': 0.0003882874734555538, 'samples': 9290496, 'steps': 48387, 'loss/train': 1.2674168348312378} 08/30/2021 21:59:20 - INFO - __main__ - Step 48389: {'lr': 0.00038828305247255447, 'samples': 9290688, 'steps': 48388, 'loss/train': 1.4452506303787231} 08/30/2021 21:59:21 - INFO - __main__ - Step 48390: {'lr': 0.00038827863142724685, 'samples': 9290880, 'steps': 48389, 'loss/train': 1.6292476654052734} 08/30/2021 21:59:21 - INFO - __main__ - Step 48391: {'lr': 0.00038827421031963294, 'samples': 9291072, 'steps': 48390, 'loss/train': 0.7993712425231934} 08/30/2021 21:59:21 - INFO - __main__ - Step 48392: {'lr': 0.0003882697891497149, 'samples': 9291264, 'steps': 48391, 'loss/train': 1.254414677619934} 08/30/2021 21:59:23 - INFO - __main__ - Step 48393: {'lr': 0.00038826536791749454, 'samples': 9291456, 'steps': 48392, 'loss/train': 1.0764840841293335} 08/30/2021 21:59:23 - INFO - __main__ - Step 48394: {'lr': 0.00038826094662297404, 'samples': 9291648, 'steps': 48393, 'loss/train': 1.522329568862915} 08/30/2021 21:59:24 - INFO - __main__ - Step 48395: {'lr': 0.0003882565252661553, 'samples': 9291840, 'steps': 48394, 'loss/train': 1.815787672996521} 08/30/2021 21:59:24 - INFO - __main__ - Step 48396: {'lr': 0.00038825210384704024, 'samples': 9292032, 'steps': 48395, 'loss/train': 1.24665367603302} 08/30/2021 21:59:25 - INFO - __main__ - Step 48397: {'lr': 0.0003882476823656309, 'samples': 9292224, 'steps': 48396, 'loss/train': 1.9732352495193481} 08/30/2021 21:59:25 - INFO - __main__ - Step 48398: {'lr': 0.00038824326082192935, 'samples': 9292416, 'steps': 48397, 'loss/train': 1.3705459833145142} 08/30/2021 21:59:26 - INFO - __main__ - Step 48399: {'lr': 0.0003882388392159375, 'samples': 9292608, 'steps': 48398, 'loss/train': 1.7985793352127075} 08/30/2021 21:59:27 - INFO - __main__ - Step 48400: {'lr': 0.0003882344175476573, 'samples': 9292800, 'steps': 48399, 'loss/train': 1.1154745817184448} 08/30/2021 21:59:27 - INFO - __main__ - Step 48401: {'lr': 0.00038822999581709087, 'samples': 9292992, 'steps': 48400, 'loss/train': 1.4069701433181763} 08/30/2021 21:59:28 - INFO - __main__ - Step 48402: {'lr': 0.0003882255740242401, 'samples': 9293184, 'steps': 48401, 'loss/train': 1.6385899782180786} 08/30/2021 21:59:28 - INFO - __main__ - Step 48403: {'lr': 0.0003882211521691071, 'samples': 9293376, 'steps': 48402, 'loss/train': 1.8790549039840698} 08/30/2021 21:59:30 - INFO - __main__ - Step 48404: {'lr': 0.0003882167302516937, 'samples': 9293568, 'steps': 48403, 'loss/train': 1.8087621927261353} 08/30/2021 21:59:30 - INFO - __main__ - Step 48405: {'lr': 0.000388212308272002, 'samples': 9293760, 'steps': 48404, 'loss/train': 0.7198596596717834} 08/30/2021 21:59:31 - INFO - __main__ - Step 48406: {'lr': 0.00038820788623003397, 'samples': 9293952, 'steps': 48405, 'loss/train': 0.9973756074905396} 08/30/2021 21:59:31 - INFO - __main__ - Step 48407: {'lr': 0.00038820346412579156, 'samples': 9294144, 'steps': 48406, 'loss/train': 1.493796467781067} 08/30/2021 21:59:31 - INFO - __main__ - Step 48408: {'lr': 0.0003881990419592768, 'samples': 9294336, 'steps': 48407, 'loss/train': 1.2681516408920288} 08/30/2021 21:59:33 - INFO - __main__ - Step 48409: {'lr': 0.00038819461973049177, 'samples': 9294528, 'steps': 48408, 'loss/train': 1.3363465070724487} 08/30/2021 21:59:33 - INFO - __main__ - Step 48410: {'lr': 0.00038819019743943834, 'samples': 9294720, 'steps': 48409, 'loss/train': 2.367302894592285} 08/30/2021 21:59:34 - INFO - __main__ - Step 48411: {'lr': 0.00038818577508611854, 'samples': 9294912, 'steps': 48410, 'loss/train': 1.161450982093811} 08/30/2021 21:59:34 - INFO - __main__ - Step 48412: {'lr': 0.00038818135267053435, 'samples': 9295104, 'steps': 48411, 'loss/train': 1.2520462274551392} 08/30/2021 21:59:34 - INFO - __main__ - Step 48413: {'lr': 0.00038817693019268775, 'samples': 9295296, 'steps': 48412, 'loss/train': 1.4962916374206543} 08/30/2021 21:59:36 - INFO - __main__ - Step 48414: {'lr': 0.0003881725076525808, 'samples': 9295488, 'steps': 48413, 'loss/train': 1.604047179222107} 08/30/2021 21:59:36 - INFO - __main__ - Step 48415: {'lr': 0.0003881680850502154, 'samples': 9295680, 'steps': 48414, 'loss/train': 1.1570351123809814} 08/30/2021 21:59:37 - INFO - __main__ - Step 48416: {'lr': 0.00038816366238559366, 'samples': 9295872, 'steps': 48415, 'loss/train': 1.3183537721633911} 08/30/2021 21:59:37 - INFO - __main__ - Step 48417: {'lr': 0.00038815923965871747, 'samples': 9296064, 'steps': 48416, 'loss/train': 1.0234194993972778} 08/30/2021 21:59:37 - INFO - __main__ - Step 48418: {'lr': 0.00038815481686958883, 'samples': 9296256, 'steps': 48417, 'loss/train': 1.5382137298583984} 08/30/2021 21:59:39 - INFO - __main__ - Step 48419: {'lr': 0.0003881503940182098, 'samples': 9296448, 'steps': 48418, 'loss/train': 0.362134724855423} 08/30/2021 21:59:39 - INFO - __main__ - Step 48420: {'lr': 0.0003881459711045823, 'samples': 9296640, 'steps': 48419, 'loss/train': 1.6999907493591309} 08/30/2021 21:59:40 - INFO - __main__ - Step 48421: {'lr': 0.0003881415481287084, 'samples': 9296832, 'steps': 48420, 'loss/train': 0.5085893273353577} 08/30/2021 21:59:40 - INFO - __main__ - Step 48422: {'lr': 0.00038813712509058995, 'samples': 9297024, 'steps': 48421, 'loss/train': 1.0744240283966064} 08/30/2021 21:59:40 - INFO - __main__ - Step 48423: {'lr': 0.0003881327019902292, 'samples': 9297216, 'steps': 48422, 'loss/train': 1.4352797269821167} 08/30/2021 21:59:42 - INFO - __main__ - Step 48424: {'lr': 0.00038812827882762793, 'samples': 9297408, 'steps': 48423, 'loss/train': 1.353934645652771} 08/30/2021 21:59:42 - INFO - __main__ - Step 48425: {'lr': 0.00038812385560278815, 'samples': 9297600, 'steps': 48424, 'loss/train': 1.5925509929656982} 08/30/2021 21:59:43 - INFO - __main__ - Step 48426: {'lr': 0.0003881194323157119, 'samples': 9297792, 'steps': 48425, 'loss/train': 1.344125747680664} 08/30/2021 21:59:43 - INFO - __main__ - Step 48427: {'lr': 0.00038811500896640116, 'samples': 9297984, 'steps': 48426, 'loss/train': 1.7305984497070312} 08/30/2021 21:59:43 - INFO - __main__ - Step 48428: {'lr': 0.0003881105855548579, 'samples': 9298176, 'steps': 48427, 'loss/train': 1.3240357637405396} 08/30/2021 21:59:45 - INFO - __main__ - Step 48429: {'lr': 0.00038810616208108416, 'samples': 9298368, 'steps': 48428, 'loss/train': 0.5368484258651733} 08/30/2021 21:59:45 - INFO - __main__ - Step 48430: {'lr': 0.00038810173854508204, 'samples': 9298560, 'steps': 48429, 'loss/train': 1.1445903778076172} 08/30/2021 21:59:46 - INFO - __main__ - Step 48431: {'lr': 0.0003880973149468533, 'samples': 9298752, 'steps': 48430, 'loss/train': 1.6752376556396484} 08/30/2021 21:59:46 - INFO - __main__ - Step 48432: {'lr': 0.00038809289128640003, 'samples': 9298944, 'steps': 48431, 'loss/train': 1.3629772663116455} 08/30/2021 21:59:46 - INFO - __main__ - Step 48433: {'lr': 0.00038808846756372426, 'samples': 9299136, 'steps': 48432, 'loss/train': 0.5924604535102844} 08/30/2021 21:59:48 - INFO - __main__ - Step 48434: {'lr': 0.0003880840437788279, 'samples': 9299328, 'steps': 48433, 'loss/train': 0.0446803979575634} 08/30/2021 21:59:48 - INFO - __main__ - Step 48435: {'lr': 0.00038807961993171306, 'samples': 9299520, 'steps': 48434, 'loss/train': 1.0644896030426025} 08/30/2021 21:59:49 - INFO - __main__ - Step 48436: {'lr': 0.00038807519602238174, 'samples': 9299712, 'steps': 48435, 'loss/train': 1.1155132055282593} 08/30/2021 21:59:49 - INFO - __main__ - Step 48437: {'lr': 0.00038807077205083577, 'samples': 9299904, 'steps': 48436, 'loss/train': 1.0517810583114624} 08/30/2021 21:59:49 - INFO - __main__ - Step 48438: {'lr': 0.0003880663480170772, 'samples': 9300096, 'steps': 48437, 'loss/train': 0.8353077173233032} 08/30/2021 21:59:51 - INFO - __main__ - Step 48439: {'lr': 0.00038806192392110817, 'samples': 9300288, 'steps': 48438, 'loss/train': 1.4676532745361328} 08/30/2021 21:59:51 - INFO - __main__ - Step 48440: {'lr': 0.0003880574997629305, 'samples': 9300480, 'steps': 48439, 'loss/train': 2.0629382133483887} 08/30/2021 21:59:52 - INFO - __main__ - Step 48441: {'lr': 0.0003880530755425462, 'samples': 9300672, 'steps': 48440, 'loss/train': 1.1311228275299072} 08/30/2021 21:59:52 - INFO - __main__ - Step 48442: {'lr': 0.0003880486512599574, 'samples': 9300864, 'steps': 48441, 'loss/train': 1.1981433629989624} 08/30/2021 21:59:52 - INFO - __main__ - Step 48443: {'lr': 0.00038804422691516606, 'samples': 9301056, 'steps': 48442, 'loss/train': 0.9683637619018555} 08/30/2021 21:59:54 - INFO - __main__ - Step 48444: {'lr': 0.0003880398025081741, 'samples': 9301248, 'steps': 48443, 'loss/train': 1.5106436014175415} 08/30/2021 21:59:54 - INFO - __main__ - Step 48445: {'lr': 0.0003880353780389834, 'samples': 9301440, 'steps': 48444, 'loss/train': 1.2463641166687012} 08/30/2021 21:59:55 - INFO - __main__ - Step 48446: {'lr': 0.0003880309535075962, 'samples': 9301632, 'steps': 48445, 'loss/train': 1.7059900760650635} 08/30/2021 21:59:55 - INFO - __main__ - Step 48447: {'lr': 0.00038802652891401434, 'samples': 9301824, 'steps': 48446, 'loss/train': 0.9859436750411987} 08/30/2021 21:59:55 - INFO - __main__ - Step 48448: {'lr': 0.0003880221042582399, 'samples': 9302016, 'steps': 48447, 'loss/train': 1.3285859823226929} 08/30/2021 21:59:56 - INFO - __main__ - Step 48449: {'lr': 0.0003880176795402748, 'samples': 9302208, 'steps': 48448, 'loss/train': 0.9440991878509521} 08/30/2021 21:59:57 - INFO - __main__ - Step 48450: {'lr': 0.00038801325476012113, 'samples': 9302400, 'steps': 48449, 'loss/train': 1.6010005474090576} 08/30/2021 21:59:58 - INFO - __main__ - Step 48451: {'lr': 0.00038800882991778073, 'samples': 9302592, 'steps': 48450, 'loss/train': 1.1128400564193726} 08/30/2021 21:59:58 - INFO - __main__ - Step 48452: {'lr': 0.00038800440501325574, 'samples': 9302784, 'steps': 48451, 'loss/train': 1.4798130989074707} 08/30/2021 21:59:58 - INFO - __main__ - Step 48453: {'lr': 0.000387999980046548, 'samples': 9302976, 'steps': 48452, 'loss/train': 1.504532814025879} 08/30/2021 21:59:59 - INFO - __main__ - Step 48454: {'lr': 0.0003879955550176597, 'samples': 9303168, 'steps': 48453, 'loss/train': 1.6498000621795654} 08/30/2021 22:00:00 - INFO - __main__ - Step 48455: {'lr': 0.00038799112992659267, 'samples': 9303360, 'steps': 48454, 'loss/train': 1.0734919309616089} 08/30/2021 22:00:01 - INFO - __main__ - Step 48456: {'lr': 0.00038798670477334894, 'samples': 9303552, 'steps': 48455, 'loss/train': 1.2962626218795776} 08/30/2021 22:00:01 - INFO - __main__ - Step 48457: {'lr': 0.00038798227955793066, 'samples': 9303744, 'steps': 48456, 'loss/train': 1.6801810264587402} 08/30/2021 22:00:01 - INFO - __main__ - Step 48458: {'lr': 0.0003879778542803396, 'samples': 9303936, 'steps': 48457, 'loss/train': 1.099550724029541} 08/30/2021 22:00:02 - INFO - __main__ - Step 48459: {'lr': 0.00038797342894057783, 'samples': 9304128, 'steps': 48458, 'loss/train': 1.2253131866455078} 08/30/2021 22:00:03 - INFO - __main__ - Step 48460: {'lr': 0.0003879690035386474, 'samples': 9304320, 'steps': 48459, 'loss/train': 2.109959363937378} 08/30/2021 22:00:04 - INFO - __main__ - Step 48461: {'lr': 0.0003879645780745503, 'samples': 9304512, 'steps': 48460, 'loss/train': 0.7420564293861389} 08/30/2021 22:00:04 - INFO - __main__ - Step 48462: {'lr': 0.0003879601525482884, 'samples': 9304704, 'steps': 48461, 'loss/train': 1.545756220817566} 08/30/2021 22:00:05 - INFO - __main__ - Step 48463: {'lr': 0.00038795572695986394, 'samples': 9304896, 'steps': 48462, 'loss/train': 0.545409619808197} 08/30/2021 22:00:05 - INFO - __main__ - Step 48464: {'lr': 0.00038795130130927857, 'samples': 9305088, 'steps': 48463, 'loss/train': 2.039393663406372} 08/30/2021 22:00:07 - INFO - __main__ - Step 48465: {'lr': 0.0003879468755965346, 'samples': 9305280, 'steps': 48464, 'loss/train': 0.049927160143852234} 08/30/2021 22:00:07 - INFO - __main__ - Step 48466: {'lr': 0.00038794244982163383, 'samples': 9305472, 'steps': 48465, 'loss/train': 1.8855663537979126} 08/30/2021 22:00:07 - INFO - __main__ - Step 48467: {'lr': 0.0003879380239845783, 'samples': 9305664, 'steps': 48466, 'loss/train': 1.4282443523406982} 08/30/2021 22:00:08 - INFO - __main__ - Step 48468: {'lr': 0.0003879335980853701, 'samples': 9305856, 'steps': 48467, 'loss/train': 1.460593581199646} 08/30/2021 22:00:08 - INFO - __main__ - Step 48469: {'lr': 0.00038792917212401114, 'samples': 9306048, 'steps': 48468, 'loss/train': 1.587393879890442} 08/30/2021 22:00:09 - INFO - __main__ - Step 48470: {'lr': 0.0003879247461005034, 'samples': 9306240, 'steps': 48469, 'loss/train': 1.1955863237380981} 08/30/2021 22:00:10 - INFO - __main__ - Step 48471: {'lr': 0.0003879203200148489, 'samples': 9306432, 'steps': 48470, 'loss/train': 0.9549295902252197} 08/30/2021 22:00:10 - INFO - __main__ - Step 48472: {'lr': 0.0003879158938670496, 'samples': 9306624, 'steps': 48471, 'loss/train': 1.173951506614685} 08/30/2021 22:00:11 - INFO - __main__ - Step 48473: {'lr': 0.0003879114676571076, 'samples': 9306816, 'steps': 48472, 'loss/train': 1.5563071966171265} 08/30/2021 22:00:11 - INFO - __main__ - Step 48474: {'lr': 0.00038790704138502475, 'samples': 9307008, 'steps': 48473, 'loss/train': 1.4330594539642334} 08/30/2021 22:00:12 - INFO - __main__ - Step 48475: {'lr': 0.0003879026150508032, 'samples': 9307200, 'steps': 48474, 'loss/train': 0.9032770395278931} 08/30/2021 22:00:13 - INFO - __main__ - Step 48476: {'lr': 0.00038789818865444473, 'samples': 9307392, 'steps': 48475, 'loss/train': 1.3034579753875732} 08/30/2021 22:00:13 - INFO - __main__ - Step 48477: {'lr': 0.0003878937621959516, 'samples': 9307584, 'steps': 48476, 'loss/train': 1.8261030912399292} 08/30/2021 22:00:14 - INFO - __main__ - Step 48478: {'lr': 0.0003878893356753256, 'samples': 9307776, 'steps': 48477, 'loss/train': 0.9689961075782776} 08/30/2021 22:00:14 - INFO - __main__ - Step 48479: {'lr': 0.0003878849090925688, 'samples': 9307968, 'steps': 48478, 'loss/train': 1.4118194580078125} 08/30/2021 22:00:15 - INFO - __main__ - Step 48480: {'lr': 0.00038788048244768316, 'samples': 9308160, 'steps': 48479, 'loss/train': 1.6663236618041992} 08/30/2021 22:00:16 - INFO - __main__ - Step 48481: {'lr': 0.00038787605574067076, 'samples': 9308352, 'steps': 48480, 'loss/train': 1.6399551630020142} 08/30/2021 22:00:16 - INFO - __main__ - Step 48482: {'lr': 0.0003878716289715335, 'samples': 9308544, 'steps': 48481, 'loss/train': 0.5260775089263916} 08/30/2021 22:00:17 - INFO - __main__ - Step 48483: {'lr': 0.0003878672021402734, 'samples': 9308736, 'steps': 48482, 'loss/train': 4.811079978942871} 08/30/2021 22:00:17 - INFO - __main__ - Step 48484: {'lr': 0.00038786277524689245, 'samples': 9308928, 'steps': 48483, 'loss/train': 1.3441731929779053} 08/30/2021 22:00:18 - INFO - __main__ - Step 48485: {'lr': 0.0003878583482913927, 'samples': 9309120, 'steps': 48484, 'loss/train': 1.588223934173584} 08/30/2021 22:00:19 - INFO - __main__ - Step 48486: {'lr': 0.00038785392127377603, 'samples': 9309312, 'steps': 48485, 'loss/train': 1.7102043628692627} 08/30/2021 22:00:19 - INFO - __main__ - Step 48487: {'lr': 0.0003878494941940447, 'samples': 9309504, 'steps': 48486, 'loss/train': 1.1020991802215576} 08/30/2021 22:00:19 - INFO - __main__ - Step 48488: {'lr': 0.0003878450670522004, 'samples': 9309696, 'steps': 48487, 'loss/train': 1.5877913236618042} 08/30/2021 22:00:20 - INFO - __main__ - Step 48489: {'lr': 0.00038784063984824516, 'samples': 9309888, 'steps': 48488, 'loss/train': 1.4161159992218018} 08/30/2021 22:00:22 - INFO - __main__ - Step 48490: {'lr': 0.00038783621258218115, 'samples': 9310080, 'steps': 48489, 'loss/train': 0.1848432719707489} 08/30/2021 22:00:22 - INFO - __main__ - Step 48491: {'lr': 0.00038783178525401025, 'samples': 9310272, 'steps': 48490, 'loss/train': 0.2881789803504944} 08/30/2021 22:00:23 - INFO - __main__ - Step 48492: {'lr': 0.00038782735786373445, 'samples': 9310464, 'steps': 48491, 'loss/train': 1.5090851783752441} 08/30/2021 22:00:23 - INFO - __main__ - Step 48493: {'lr': 0.00038782293041135583, 'samples': 9310656, 'steps': 48492, 'loss/train': 1.3842346668243408} 08/30/2021 22:00:23 - INFO - __main__ - Step 48494: {'lr': 0.0003878185028968763, 'samples': 9310848, 'steps': 48493, 'loss/train': 1.8749058246612549} 08/30/2021 22:00:24 - INFO - __main__ - Step 48495: {'lr': 0.00038781407532029785, 'samples': 9311040, 'steps': 48494, 'loss/train': 1.3964929580688477} 08/30/2021 22:00:25 - INFO - __main__ - Step 48496: {'lr': 0.0003878096476816225, 'samples': 9311232, 'steps': 48495, 'loss/train': 1.5425902605056763} 08/30/2021 22:00:26 - INFO - __main__ - Step 48497: {'lr': 0.0003878052199808523, 'samples': 9311424, 'steps': 48496, 'loss/train': 2.0943737030029297} 08/30/2021 22:00:26 - INFO - __main__ - Step 48498: {'lr': 0.0003878007922179891, 'samples': 9311616, 'steps': 48497, 'loss/train': 0.5705732107162476} 08/30/2021 22:00:26 - INFO - __main__ - Step 48499: {'lr': 0.0003877963643930351, 'samples': 9311808, 'steps': 48498, 'loss/train': 1.2632553577423096} 08/30/2021 22:00:27 - INFO - __main__ - Step 48500: {'lr': 0.00038779193650599213, 'samples': 9312000, 'steps': 48499, 'loss/train': 0.9077624678611755} 08/30/2021 22:00:28 - INFO - __main__ - Step 48501: {'lr': 0.0003877875085568622, 'samples': 9312192, 'steps': 48500, 'loss/train': 1.6068578958511353} 08/30/2021 22:00:29 - INFO - __main__ - Step 48502: {'lr': 0.0003877830805456474, 'samples': 9312384, 'steps': 48501, 'loss/train': 1.3240727186203003} 08/30/2021 22:00:29 - INFO - __main__ - Step 48503: {'lr': 0.00038777865247234967, 'samples': 9312576, 'steps': 48502, 'loss/train': 1.2507191896438599} 08/30/2021 22:00:29 - INFO - __main__ - Step 48504: {'lr': 0.00038777422433697106, 'samples': 9312768, 'steps': 48503, 'loss/train': 1.4361670017242432} 08/30/2021 22:00:30 - INFO - __main__ - Step 48505: {'lr': 0.00038776979613951347, 'samples': 9312960, 'steps': 48504, 'loss/train': 1.8598394393920898} 08/30/2021 22:00:32 - INFO - __main__ - Step 48506: {'lr': 0.00038776536787997885, 'samples': 9313152, 'steps': 48505, 'loss/train': 0.8972229957580566} 08/30/2021 22:00:32 - INFO - __main__ - Step 48507: {'lr': 0.0003877609395583693, 'samples': 9313344, 'steps': 48506, 'loss/train': 1.6361212730407715} 08/30/2021 22:00:32 - INFO - __main__ - Step 48508: {'lr': 0.0003877565111746869, 'samples': 9313536, 'steps': 48507, 'loss/train': 1.3830232620239258} 08/30/2021 22:00:33 - INFO - __main__ - Step 48509: {'lr': 0.00038775208272893346, 'samples': 9313728, 'steps': 48508, 'loss/train': 1.616654396057129} 08/30/2021 22:00:33 - INFO - __main__ - Step 48510: {'lr': 0.0003877476542211111, 'samples': 9313920, 'steps': 48509, 'loss/train': 0.15169793367385864} 08/30/2021 22:00:35 - INFO - __main__ - Step 48511: {'lr': 0.0003877432256512218, 'samples': 9314112, 'steps': 48510, 'loss/train': 0.7469132542610168} 08/30/2021 22:00:35 - INFO - __main__ - Step 48512: {'lr': 0.00038773879701926747, 'samples': 9314304, 'steps': 48511, 'loss/train': 1.6190145015716553} 08/30/2021 22:00:35 - INFO - __main__ - Step 48513: {'lr': 0.0003877343683252501, 'samples': 9314496, 'steps': 48512, 'loss/train': 1.1561778783798218} 08/30/2021 22:00:36 - INFO - __main__ - Step 48514: {'lr': 0.00038772993956917183, 'samples': 9314688, 'steps': 48513, 'loss/train': 0.7685527801513672} 08/30/2021 22:00:36 - INFO - __main__ - Step 48515: {'lr': 0.00038772551075103457, 'samples': 9314880, 'steps': 48514, 'loss/train': 1.1655855178833008} 08/30/2021 22:00:36 - INFO - __main__ - Step 48516: {'lr': 0.00038772108187084034, 'samples': 9315072, 'steps': 48515, 'loss/train': 1.05631685256958} 08/30/2021 22:00:39 - INFO - __main__ - Step 48517: {'lr': 0.00038771665292859116, 'samples': 9315264, 'steps': 48516, 'loss/train': 1.5202178955078125} 08/30/2021 22:00:39 - INFO - __main__ - Step 48518: {'lr': 0.00038771222392428885, 'samples': 9315456, 'steps': 48517, 'loss/train': 0.0706179291009903} 08/30/2021 22:00:40 - INFO - __main__ - Step 48519: {'lr': 0.0003877077948579356, 'samples': 9315648, 'steps': 48518, 'loss/train': 0.4329894781112671} 08/30/2021 22:00:40 - INFO - __main__ - Step 48520: {'lr': 0.00038770336572953334, 'samples': 9315840, 'steps': 48519, 'loss/train': 1.4072073698043823} 08/30/2021 22:00:40 - INFO - __main__ - Step 48521: {'lr': 0.00038769893653908404, 'samples': 9316032, 'steps': 48520, 'loss/train': 1.2309231758117676} 08/30/2021 22:00:41 - INFO - __main__ - Step 48522: {'lr': 0.0003876945072865898, 'samples': 9316224, 'steps': 48521, 'loss/train': 1.207040786743164} 08/30/2021 22:00:41 - INFO - __main__ - Step 48523: {'lr': 0.0003876900779720525, 'samples': 9316416, 'steps': 48522, 'loss/train': 2.160245180130005} 08/30/2021 22:00:42 - INFO - __main__ - Step 48524: {'lr': 0.0003876856485954742, 'samples': 9316608, 'steps': 48523, 'loss/train': 2.266228199005127} 08/30/2021 22:00:43 - INFO - __main__ - Step 48525: {'lr': 0.00038768121915685685, 'samples': 9316800, 'steps': 48524, 'loss/train': 1.5202691555023193} 08/30/2021 22:00:43 - INFO - __main__ - Step 48526: {'lr': 0.00038767678965620245, 'samples': 9316992, 'steps': 48525, 'loss/train': 1.0634765625} 08/30/2021 22:00:44 - INFO - __main__ - Step 48527: {'lr': 0.00038767236009351304, 'samples': 9317184, 'steps': 48526, 'loss/train': 2.2997090816497803} 08/30/2021 22:00:44 - INFO - __main__ - Step 48528: {'lr': 0.00038766793046879057, 'samples': 9317376, 'steps': 48527, 'loss/train': 1.6402528285980225} 08/30/2021 22:00:46 - INFO - __main__ - Step 48529: {'lr': 0.000387663500782037, 'samples': 9317568, 'steps': 48528, 'loss/train': 1.3543519973754883} 08/30/2021 22:00:46 - INFO - __main__ - Step 48530: {'lr': 0.00038765907103325447, 'samples': 9317760, 'steps': 48529, 'loss/train': 1.1279032230377197} 08/30/2021 22:00:46 - INFO - __main__ - Step 48531: {'lr': 0.00038765464122244485, 'samples': 9317952, 'steps': 48530, 'loss/train': 1.2232149839401245} 08/30/2021 22:00:47 - INFO - __main__ - Step 48532: {'lr': 0.0003876502113496102, 'samples': 9318144, 'steps': 48531, 'loss/train': 1.2406408786773682} 08/30/2021 22:00:47 - INFO - __main__ - Step 48533: {'lr': 0.00038764578141475245, 'samples': 9318336, 'steps': 48532, 'loss/train': 1.344740390777588} 08/30/2021 22:00:49 - INFO - __main__ - Step 48534: {'lr': 0.0003876413514178736, 'samples': 9318528, 'steps': 48533, 'loss/train': 1.5499004125595093} 08/30/2021 22:00:49 - INFO - __main__ - Step 48535: {'lr': 0.0003876369213589758, 'samples': 9318720, 'steps': 48534, 'loss/train': 0.9566710591316223} 08/30/2021 22:00:49 - INFO - __main__ - Step 48536: {'lr': 0.0003876324912380608, 'samples': 9318912, 'steps': 48535, 'loss/train': 0.08877792209386826} 08/30/2021 22:00:50 - INFO - __main__ - Step 48537: {'lr': 0.00038762806105513084, 'samples': 9319104, 'steps': 48536, 'loss/train': 1.6251089572906494} 08/30/2021 22:00:50 - INFO - __main__ - Step 48538: {'lr': 0.0003876236308101877, 'samples': 9319296, 'steps': 48537, 'loss/train': 1.4864169359207153} 08/30/2021 22:00:53 - INFO - __main__ - Step 48539: {'lr': 0.0003876192005032335, 'samples': 9319488, 'steps': 48538, 'loss/train': 3.7254464626312256} 08/30/2021 22:00:53 - INFO - __main__ - Step 48540: {'lr': 0.00038761477013427026, 'samples': 9319680, 'steps': 48539, 'loss/train': 1.8291910886764526} 08/30/2021 22:00:54 - INFO - __main__ - Step 48541: {'lr': 0.00038761033970329987, 'samples': 9319872, 'steps': 48540, 'loss/train': 1.4286510944366455} 08/30/2021 22:00:54 - INFO - __main__ - Step 48542: {'lr': 0.00038760590921032445, 'samples': 9320064, 'steps': 48541, 'loss/train': 1.8013432025909424} 08/30/2021 22:00:54 - INFO - __main__ - Step 48543: {'lr': 0.0003876014786553459, 'samples': 9320256, 'steps': 48542, 'loss/train': 1.7205475568771362} 08/30/2021 22:00:55 - INFO - __main__ - Step 48544: {'lr': 0.00038759704803836625, 'samples': 9320448, 'steps': 48543, 'loss/train': 1.7732487916946411} 08/30/2021 22:00:55 - INFO - __main__ - Step 48545: {'lr': 0.00038759261735938743, 'samples': 9320640, 'steps': 48544, 'loss/train': 1.4101994037628174} 08/30/2021 22:00:55 - INFO - __main__ - Step 48546: {'lr': 0.00038758818661841155, 'samples': 9320832, 'steps': 48545, 'loss/train': 1.1383955478668213} 08/30/2021 22:00:56 - INFO - __main__ - Step 48547: {'lr': 0.0003875837558154406, 'samples': 9321024, 'steps': 48546, 'loss/train': 1.2493377923965454} 08/30/2021 22:00:58 - INFO - __main__ - Step 48548: {'lr': 0.0003875793249504765, 'samples': 9321216, 'steps': 48547, 'loss/train': 2.0622549057006836} 08/30/2021 22:00:58 - INFO - __main__ - Step 48549: {'lr': 0.00038757489402352124, 'samples': 9321408, 'steps': 48548, 'loss/train': 1.9969414472579956} 08/30/2021 22:00:59 - INFO - __main__ - Step 48550: {'lr': 0.0003875704630345769, 'samples': 9321600, 'steps': 48549, 'loss/train': 1.2790120840072632} 08/30/2021 22:00:59 - INFO - __main__ - Step 48551: {'lr': 0.00038756603198364544, 'samples': 9321792, 'steps': 48550, 'loss/train': 1.49632728099823} 08/30/2021 22:00:59 - INFO - __main__ - Step 48552: {'lr': 0.0003875616008707288, 'samples': 9321984, 'steps': 48551, 'loss/train': 1.6404567956924438} 08/30/2021 22:01:01 - INFO - __main__ - Step 48553: {'lr': 0.00038755716969582913, 'samples': 9322176, 'steps': 48552, 'loss/train': 0.1912604123353958} 08/30/2021 22:01:02 - INFO - __main__ - Step 48554: {'lr': 0.0003875527384589482, 'samples': 9322368, 'steps': 48553, 'loss/train': 0.8276629447937012} 08/30/2021 22:01:02 - INFO - __main__ - Step 48555: {'lr': 0.00038754830716008815, 'samples': 9322560, 'steps': 48554, 'loss/train': 0.9975128769874573} 08/30/2021 22:01:02 - INFO - __main__ - Step 48556: {'lr': 0.000387543875799251, 'samples': 9322752, 'steps': 48555, 'loss/train': 1.35439932346344} 08/30/2021 22:01:03 - INFO - __main__ - Step 48557: {'lr': 0.0003875394443764387, 'samples': 9322944, 'steps': 48556, 'loss/train': 1.3460139036178589} 08/30/2021 22:01:04 - INFO - __main__ - Step 48558: {'lr': 0.00038753501289165324, 'samples': 9323136, 'steps': 48557, 'loss/train': 1.215519666671753} 08/30/2021 22:01:05 - INFO - __main__ - Step 48559: {'lr': 0.0003875305813448966, 'samples': 9323328, 'steps': 48558, 'loss/train': 0.38438525795936584} 08/30/2021 22:01:05 - INFO - __main__ - Step 48560: {'lr': 0.00038752614973617085, 'samples': 9323520, 'steps': 48559, 'loss/train': 1.8800326585769653} 08/30/2021 22:01:05 - INFO - __main__ - Step 48561: {'lr': 0.0003875217180654779, 'samples': 9323712, 'steps': 48560, 'loss/train': 1.5727200508117676} 08/30/2021 22:01:06 - INFO - __main__ - Step 48562: {'lr': 0.00038751728633281974, 'samples': 9323904, 'steps': 48561, 'loss/train': 1.336424469947815} 08/30/2021 22:01:07 - INFO - __main__ - Step 48563: {'lr': 0.00038751285453819846, 'samples': 9324096, 'steps': 48562, 'loss/train': 1.8624446392059326} 08/30/2021 22:01:07 - INFO - __main__ - Step 48564: {'lr': 0.000387508422681616, 'samples': 9324288, 'steps': 48563, 'loss/train': 1.509786605834961} 08/30/2021 22:01:08 - INFO - __main__ - Step 48565: {'lr': 0.0003875039907630744, 'samples': 9324480, 'steps': 48564, 'loss/train': 1.1738789081573486} 08/30/2021 22:01:08 - INFO - __main__ - Step 48566: {'lr': 0.0003874995587825756, 'samples': 9324672, 'steps': 48565, 'loss/train': 1.6788603067398071} 08/30/2021 22:01:08 - INFO - __main__ - Step 48567: {'lr': 0.00038749512674012167, 'samples': 9324864, 'steps': 48566, 'loss/train': 2.1085872650146484} 08/30/2021 22:01:10 - INFO - __main__ - Step 48568: {'lr': 0.0003874906946357145, 'samples': 9325056, 'steps': 48567, 'loss/train': 1.2281612157821655} 08/30/2021 22:01:10 - INFO - __main__ - Step 48569: {'lr': 0.00038748626246935613, 'samples': 9325248, 'steps': 48568, 'loss/train': 1.6194109916687012} 08/30/2021 22:01:11 - INFO - __main__ - Step 48570: {'lr': 0.0003874818302410486, 'samples': 9325440, 'steps': 48569, 'loss/train': 1.574687123298645} 08/30/2021 22:01:11 - INFO - __main__ - Step 48571: {'lr': 0.00038747739795079396, 'samples': 9325632, 'steps': 48570, 'loss/train': 1.2672604322433472} 08/30/2021 22:01:11 - INFO - __main__ - Step 48572: {'lr': 0.000387472965598594, 'samples': 9325824, 'steps': 48571, 'loss/train': 1.5044519901275635} 08/30/2021 22:01:12 - INFO - __main__ - Step 48573: {'lr': 0.0003874685331844509, 'samples': 9326016, 'steps': 48572, 'loss/train': 1.6884443759918213} 08/30/2021 22:01:13 - INFO - __main__ - Step 48574: {'lr': 0.0003874641007083666, 'samples': 9326208, 'steps': 48573, 'loss/train': 1.3984692096710205} 08/30/2021 22:01:14 - INFO - __main__ - Step 48575: {'lr': 0.00038745966817034305, 'samples': 9326400, 'steps': 48574, 'loss/train': 0.9498159885406494} 08/30/2021 22:01:14 - INFO - __main__ - Step 48576: {'lr': 0.0003874552355703823, 'samples': 9326592, 'steps': 48575, 'loss/train': 1.2195899486541748} 08/30/2021 22:01:14 - INFO - __main__ - Step 48577: {'lr': 0.00038745080290848635, 'samples': 9326784, 'steps': 48576, 'loss/train': 1.8267135620117188} 08/30/2021 22:01:15 - INFO - __main__ - Step 48578: {'lr': 0.0003874463701846573, 'samples': 9326976, 'steps': 48577, 'loss/train': 1.5567800998687744} 08/30/2021 22:01:17 - INFO - __main__ - Step 48579: {'lr': 0.0003874419373988969, 'samples': 9327168, 'steps': 48578, 'loss/train': 1.8793991804122925} 08/30/2021 22:01:17 - INFO - __main__ - Step 48580: {'lr': 0.0003874375045512073, 'samples': 9327360, 'steps': 48579, 'loss/train': 0.9314099550247192} 08/30/2021 22:01:18 - INFO - __main__ - Step 48581: {'lr': 0.0003874330716415905, 'samples': 9327552, 'steps': 48580, 'loss/train': 1.1739728450775146} 08/30/2021 22:01:18 - INFO - __main__ - Step 48582: {'lr': 0.00038742863867004853, 'samples': 9327744, 'steps': 48581, 'loss/train': 1.144687533378601} 08/30/2021 22:01:18 - INFO - __main__ - Step 48583: {'lr': 0.0003874242056365833, 'samples': 9327936, 'steps': 48582, 'loss/train': 2.282952070236206} 08/30/2021 22:01:19 - INFO - __main__ - Step 48584: {'lr': 0.0003874197725411969, 'samples': 9328128, 'steps': 48583, 'loss/train': 0.7288729548454285} 08/30/2021 22:01:20 - INFO - __main__ - Step 48585: {'lr': 0.00038741533938389117, 'samples': 9328320, 'steps': 48584, 'loss/train': 0.5451220870018005} 08/30/2021 22:01:21 - INFO - __main__ - Step 48586: {'lr': 0.00038741090616466824, 'samples': 9328512, 'steps': 48585, 'loss/train': 1.2091689109802246} 08/30/2021 22:01:21 - INFO - __main__ - Step 48587: {'lr': 0.0003874064728835301, 'samples': 9328704, 'steps': 48586, 'loss/train': 1.4198529720306396} 08/30/2021 22:01:21 - INFO - __main__ - Step 48588: {'lr': 0.0003874020395404787, 'samples': 9328896, 'steps': 48587, 'loss/train': 1.4191687107086182} 08/30/2021 22:01:22 - INFO - __main__ - Step 48589: {'lr': 0.00038739760613551606, 'samples': 9329088, 'steps': 48588, 'loss/train': 1.0444717407226562} 08/30/2021 22:01:23 - INFO - __main__ - Step 48590: {'lr': 0.0003873931726686442, 'samples': 9329280, 'steps': 48589, 'loss/train': 1.896647334098816} 08/30/2021 22:01:24 - INFO - __main__ - Step 48591: {'lr': 0.0003873887391398651, 'samples': 9329472, 'steps': 48590, 'loss/train': 1.8076246976852417} 08/30/2021 22:01:24 - INFO - __main__ - Step 48592: {'lr': 0.0003873843055491807, 'samples': 9329664, 'steps': 48591, 'loss/train': 1.717578411102295} 08/30/2021 22:01:24 - INFO - __main__ - Step 48593: {'lr': 0.00038737987189659315, 'samples': 9329856, 'steps': 48592, 'loss/train': 1.5724797248840332} 08/30/2021 22:01:25 - INFO - __main__ - Step 48594: {'lr': 0.00038737543818210423, 'samples': 9330048, 'steps': 48593, 'loss/train': 0.06825880706310272} 08/30/2021 22:01:26 - INFO - __main__ - Step 48595: {'lr': 0.00038737100440571615, 'samples': 9330240, 'steps': 48594, 'loss/train': 1.4919979572296143} 08/30/2021 22:01:27 - INFO - __main__ - Step 48596: {'lr': 0.00038736657056743075, 'samples': 9330432, 'steps': 48595, 'loss/train': 0.07968267053365707} 08/30/2021 22:01:27 - INFO - __main__ - Step 48597: {'lr': 0.0003873621366672502, 'samples': 9330624, 'steps': 48596, 'loss/train': 0.06861887127161026} 08/30/2021 22:01:28 - INFO - __main__ - Step 48598: {'lr': 0.0003873577027051763, 'samples': 9330816, 'steps': 48597, 'loss/train': 1.5271934270858765} 08/30/2021 22:01:28 - INFO - __main__ - Step 48599: {'lr': 0.0003873532686812111, 'samples': 9331008, 'steps': 48598, 'loss/train': 0.9882999658584595} 08/30/2021 22:01:30 - INFO - __main__ - Step 48600: {'lr': 0.0003873488345953567, 'samples': 9331200, 'steps': 48599, 'loss/train': 1.1225131750106812} 08/30/2021 22:01:31 - INFO - __main__ - Step 48601: {'lr': 0.00038734440044761503, 'samples': 9331392, 'steps': 48600, 'loss/train': 1.5609920024871826} 08/30/2021 22:01:31 - INFO - __main__ - Step 48602: {'lr': 0.0003873399662379881, 'samples': 9331584, 'steps': 48601, 'loss/train': 0.691584587097168} 08/30/2021 22:01:31 - INFO - __main__ - Step 48603: {'lr': 0.00038733553196647786, 'samples': 9331776, 'steps': 48602, 'loss/train': 1.5188713073730469} 08/30/2021 22:01:32 - INFO - __main__ - Step 48604: {'lr': 0.00038733109763308644, 'samples': 9331968, 'steps': 48603, 'loss/train': 0.040184203535318375} 08/30/2021 22:01:32 - INFO - __main__ - Step 48605: {'lr': 0.0003873266632378157, 'samples': 9332160, 'steps': 48604, 'loss/train': 0.03341313824057579} 08/30/2021 22:01:34 - INFO - __main__ - Step 48606: {'lr': 0.00038732222878066764, 'samples': 9332352, 'steps': 48605, 'loss/train': 0.9039045572280884} 08/30/2021 22:01:35 - INFO - __main__ - Step 48607: {'lr': 0.0003873177942616444, 'samples': 9332544, 'steps': 48606, 'loss/train': 1.539287805557251} 08/30/2021 22:01:35 - INFO - __main__ - Step 48608: {'lr': 0.0003873133596807478, 'samples': 9332736, 'steps': 48607, 'loss/train': 1.449718952178955} 08/30/2021 22:01:35 - INFO - __main__ - Step 48609: {'lr': 0.00038730892503797986, 'samples': 9332928, 'steps': 48608, 'loss/train': 1.5010136365890503} 08/30/2021 22:01:36 - INFO - __main__ - Step 48610: {'lr': 0.00038730449033334277, 'samples': 9333120, 'steps': 48609, 'loss/train': 2.045989513397217} 08/30/2021 22:01:36 - INFO - __main__ - Step 48611: {'lr': 0.00038730005556683833, 'samples': 9333312, 'steps': 48610, 'loss/train': 1.9787211418151855} 08/30/2021 22:01:38 - INFO - __main__ - Step 48612: {'lr': 0.00038729562073846856, 'samples': 9333504, 'steps': 48611, 'loss/train': 1.6157768964767456} 08/30/2021 22:01:39 - INFO - __main__ - Step 48613: {'lr': 0.00038729118584823557, 'samples': 9333696, 'steps': 48612, 'loss/train': 0.7498517036437988} 08/30/2021 22:01:39 - INFO - __main__ - Step 48614: {'lr': 0.0003872867508961413, 'samples': 9333888, 'steps': 48613, 'loss/train': 1.5510752201080322} 08/30/2021 22:01:39 - INFO - __main__ - Step 48615: {'lr': 0.00038728231588218767, 'samples': 9334080, 'steps': 48614, 'loss/train': 1.334282636642456} 08/30/2021 22:01:40 - INFO - __main__ - Step 48616: {'lr': 0.00038727788080637684, 'samples': 9334272, 'steps': 48615, 'loss/train': 5.3211541175842285} 08/30/2021 22:01:40 - INFO - __main__ - Step 48617: {'lr': 0.00038727344566871064, 'samples': 9334464, 'steps': 48616, 'loss/train': 2.221296787261963} 08/30/2021 22:01:42 - INFO - __main__ - Step 48618: {'lr': 0.00038726901046919114, 'samples': 9334656, 'steps': 48617, 'loss/train': 1.4681886434555054} 08/30/2021 22:01:42 - INFO - __main__ - Step 48619: {'lr': 0.00038726457520782046, 'samples': 9334848, 'steps': 48618, 'loss/train': 1.652093768119812} 08/30/2021 22:01:42 - INFO - __main__ - Step 48620: {'lr': 0.00038726013988460027, 'samples': 9335040, 'steps': 48619, 'loss/train': 1.3608489036560059} 08/30/2021 22:01:43 - INFO - __main__ - Step 48621: {'lr': 0.00038725570449953296, 'samples': 9335232, 'steps': 48620, 'loss/train': 0.09964090585708618} 08/30/2021 22:01:43 - INFO - __main__ - Step 48622: {'lr': 0.0003872512690526203, 'samples': 9335424, 'steps': 48621, 'loss/train': 1.790815830230713} 08/30/2021 22:01:45 - INFO - __main__ - Step 48623: {'lr': 0.0003872468335438643, 'samples': 9335616, 'steps': 48622, 'loss/train': 0.8979711532592773} 08/30/2021 22:01:45 - INFO - __main__ - Step 48624: {'lr': 0.000387242397973267, 'samples': 9335808, 'steps': 48623, 'loss/train': 2.186614751815796} 08/30/2021 22:01:46 - INFO - __main__ - Step 48625: {'lr': 0.0003872379623408304, 'samples': 9336000, 'steps': 48624, 'loss/train': 2.225583076477051} 08/30/2021 22:01:46 - INFO - __main__ - Step 48626: {'lr': 0.0003872335266465565, 'samples': 9336192, 'steps': 48625, 'loss/train': 1.8306851387023926} 08/30/2021 22:01:46 - INFO - __main__ - Step 48627: {'lr': 0.00038722909089044735, 'samples': 9336384, 'steps': 48626, 'loss/train': 1.453413486480713} 08/30/2021 22:01:48 - INFO - __main__ - Step 48628: {'lr': 0.0003872246550725048, 'samples': 9336576, 'steps': 48627, 'loss/train': 1.4319450855255127} 08/30/2021 22:01:48 - INFO - __main__ - Step 48629: {'lr': 0.000387220219192731, 'samples': 9336768, 'steps': 48628, 'loss/train': 1.2898825407028198} 08/30/2021 22:01:49 - INFO - __main__ - Step 48630: {'lr': 0.00038721578325112785, 'samples': 9336960, 'steps': 48629, 'loss/train': 1.2649275064468384} 08/30/2021 22:01:49 - INFO - __main__ - Step 48631: {'lr': 0.00038721134724769733, 'samples': 9337152, 'steps': 48630, 'loss/train': 1.6351832151412964} 08/30/2021 22:01:49 - INFO - __main__ - Step 48632: {'lr': 0.00038720691118244164, 'samples': 9337344, 'steps': 48631, 'loss/train': 1.378145694732666} 08/30/2021 22:01:50 - INFO - __main__ - Step 48633: {'lr': 0.00038720247505536257, 'samples': 9337536, 'steps': 48632, 'loss/train': 1.890519142150879} 08/30/2021 22:01:51 - INFO - __main__ - Step 48634: {'lr': 0.0003871980388664621, 'samples': 9337728, 'steps': 48633, 'loss/train': 1.4490344524383545} 08/30/2021 22:01:52 - INFO - __main__ - Step 48635: {'lr': 0.00038719360261574233, 'samples': 9337920, 'steps': 48634, 'loss/train': 2.115863561630249} 08/30/2021 22:01:52 - INFO - __main__ - Step 48636: {'lr': 0.00038718916630320533, 'samples': 9338112, 'steps': 48635, 'loss/train': 1.0540931224822998} 08/30/2021 22:01:52 - INFO - __main__ - Step 48637: {'lr': 0.0003871847299288529, 'samples': 9338304, 'steps': 48636, 'loss/train': 1.5217387676239014} 08/30/2021 22:01:53 - INFO - __main__ - Step 48638: {'lr': 0.00038718029349268723, 'samples': 9338496, 'steps': 48637, 'loss/train': 0.6063851118087769} 08/30/2021 22:01:54 - INFO - __main__ - Step 48639: {'lr': 0.00038717585699471024, 'samples': 9338688, 'steps': 48638, 'loss/train': 1.37833571434021} 08/30/2021 22:01:54 - INFO - __main__ - Step 48640: {'lr': 0.0003871714204349239, 'samples': 9338880, 'steps': 48639, 'loss/train': 1.0108524560928345} 08/30/2021 22:01:55 - INFO - __main__ - Step 48641: {'lr': 0.00038716698381333027, 'samples': 9339072, 'steps': 48640, 'loss/train': 2.2253668308258057} 08/30/2021 22:01:55 - INFO - __main__ - Step 48642: {'lr': 0.0003871625471299313, 'samples': 9339264, 'steps': 48641, 'loss/train': 1.5927236080169678} 08/30/2021 22:01:56 - INFO - __main__ - Step 48643: {'lr': 0.00038715811038472894, 'samples': 9339456, 'steps': 48642, 'loss/train': 1.748753547668457} 08/30/2021 22:01:56 - INFO - __main__ - Step 48644: {'lr': 0.0003871536735777252, 'samples': 9339648, 'steps': 48643, 'loss/train': 1.4262044429779053} 08/30/2021 22:01:58 - INFO - __main__ - Step 48645: {'lr': 0.0003871492367089223, 'samples': 9339840, 'steps': 48644, 'loss/train': 1.225915551185608} 08/30/2021 22:01:58 - INFO - __main__ - Step 48646: {'lr': 0.000387144799778322, 'samples': 9340032, 'steps': 48645, 'loss/train': 1.203242540359497} 08/30/2021 22:01:58 - INFO - __main__ - Step 48647: {'lr': 0.00038714036278592636, 'samples': 9340224, 'steps': 48646, 'loss/train': 1.8290691375732422} 08/30/2021 22:01:59 - INFO - __main__ - Step 48648: {'lr': 0.0003871359257317374, 'samples': 9340416, 'steps': 48647, 'loss/train': 0.9520112872123718} 08/30/2021 22:01:59 - INFO - __main__ - Step 48649: {'lr': 0.0003871314886157571, 'samples': 9340608, 'steps': 48648, 'loss/train': 1.862069845199585} 08/30/2021 22:02:00 - INFO - __main__ - Step 48650: {'lr': 0.0003871270514379874, 'samples': 9340800, 'steps': 48649, 'loss/train': 1.5161504745483398} 08/30/2021 22:02:01 - INFO - __main__ - Step 48651: {'lr': 0.00038712261419843056, 'samples': 9340992, 'steps': 48650, 'loss/train': 0.9336527585983276} 08/30/2021 22:02:01 - INFO - __main__ - Step 48652: {'lr': 0.00038711817689708817, 'samples': 9341184, 'steps': 48651, 'loss/train': 0.7322373390197754} 08/30/2021 22:02:02 - INFO - __main__ - Step 48653: {'lr': 0.00038711373953396257, 'samples': 9341376, 'steps': 48652, 'loss/train': 1.7435458898544312} 08/30/2021 22:02:02 - INFO - __main__ - Step 48654: {'lr': 0.0003871093021090556, 'samples': 9341568, 'steps': 48653, 'loss/train': 2.6974470615386963} 08/30/2021 22:02:03 - INFO - __main__ - Step 48655: {'lr': 0.0003871048646223693, 'samples': 9341760, 'steps': 48654, 'loss/train': 1.5399779081344604} 08/30/2021 22:02:04 - INFO - __main__ - Step 48656: {'lr': 0.00038710042707390557, 'samples': 9341952, 'steps': 48655, 'loss/train': 1.410839319229126} 08/30/2021 22:02:04 - INFO - __main__ - Step 48657: {'lr': 0.00038709598946366666, 'samples': 9342144, 'steps': 48656, 'loss/train': 3.0726022720336914} 08/30/2021 22:02:05 - INFO - __main__ - Step 48658: {'lr': 0.00038709155179165436, 'samples': 9342336, 'steps': 48657, 'loss/train': 0.8205497860908508} 08/30/2021 22:02:05 - INFO - __main__ - Step 48659: {'lr': 0.00038708711405787067, 'samples': 9342528, 'steps': 48658, 'loss/train': 1.7225418090820312} 08/30/2021 22:02:07 - INFO - __main__ - Step 48660: {'lr': 0.0003870826762623177, 'samples': 9342720, 'steps': 48659, 'loss/train': 1.789350152015686} 08/30/2021 22:02:08 - INFO - __main__ - Step 48661: {'lr': 0.00038707823840499736, 'samples': 9342912, 'steps': 48660, 'loss/train': 1.518591284751892} 08/30/2021 22:02:08 - INFO - __main__ - Step 48662: {'lr': 0.0003870738004859117, 'samples': 9343104, 'steps': 48661, 'loss/train': 1.6038150787353516} 08/30/2021 22:02:09 - INFO - __main__ - Step 48663: {'lr': 0.0003870693625050626, 'samples': 9343296, 'steps': 48662, 'loss/train': 1.012636423110962} 08/30/2021 22:02:09 - INFO - __main__ - Step 48664: {'lr': 0.00038706492446245234, 'samples': 9343488, 'steps': 48663, 'loss/train': 0.10666092485189438} 08/30/2021 22:02:11 - INFO - __main__ - Step 48665: {'lr': 0.00038706048635808266, 'samples': 9343680, 'steps': 48664, 'loss/train': 1.1385022401809692} 08/30/2021 22:02:11 - INFO - __main__ - Step 48666: {'lr': 0.0003870560481919556, 'samples': 9343872, 'steps': 48665, 'loss/train': 1.7361559867858887} 08/30/2021 22:02:11 - INFO - __main__ - Step 48667: {'lr': 0.00038705160996407325, 'samples': 9344064, 'steps': 48666, 'loss/train': 1.2121331691741943} 08/30/2021 22:02:12 - INFO - __main__ - Step 48668: {'lr': 0.00038704717167443753, 'samples': 9344256, 'steps': 48667, 'loss/train': 0.8323307633399963} 08/30/2021 22:02:12 - INFO - __main__ - Step 48669: {'lr': 0.0003870427333230505, 'samples': 9344448, 'steps': 48668, 'loss/train': 1.4936115741729736} 08/30/2021 22:02:14 - INFO - __main__ - Step 48670: {'lr': 0.00038703829490991407, 'samples': 9344640, 'steps': 48669, 'loss/train': 1.1054717302322388} 08/30/2021 22:02:15 - INFO - __main__ - Step 48671: {'lr': 0.0003870338564350303, 'samples': 9344832, 'steps': 48670, 'loss/train': 1.3486878871917725} 08/30/2021 22:02:15 - INFO - __main__ - Step 48672: {'lr': 0.0003870294178984013, 'samples': 9345024, 'steps': 48671, 'loss/train': 1.659084677696228} 08/30/2021 22:02:15 - INFO - __main__ - Step 48673: {'lr': 0.0003870249793000289, 'samples': 9345216, 'steps': 48672, 'loss/train': 0.09946160018444061} 08/30/2021 22:02:16 - INFO - __main__ - Step 48674: {'lr': 0.0003870205406399151, 'samples': 9345408, 'steps': 48673, 'loss/train': 1.4737313985824585} 08/30/2021 22:02:16 - INFO - __main__ - Step 48675: {'lr': 0.000387016101918062, 'samples': 9345600, 'steps': 48674, 'loss/train': 1.0012191534042358} 08/30/2021 22:02:17 - INFO - __main__ - Step 48676: {'lr': 0.0003870116631344716, 'samples': 9345792, 'steps': 48675, 'loss/train': 0.1555851697921753} 08/30/2021 22:02:18 - INFO - __main__ - Step 48677: {'lr': 0.0003870072242891458, 'samples': 9345984, 'steps': 48676, 'loss/train': 1.399659276008606} 08/30/2021 22:02:18 - INFO - __main__ - Step 48678: {'lr': 0.0003870027853820867, 'samples': 9346176, 'steps': 48677, 'loss/train': 2.079132556915283} 08/30/2021 22:02:19 - INFO - __main__ - Step 48679: {'lr': 0.0003869983464132962, 'samples': 9346368, 'steps': 48678, 'loss/train': 2.057727813720703} 08/30/2021 22:02:19 - INFO - __main__ - Step 48680: {'lr': 0.0003869939073827764, 'samples': 9346560, 'steps': 48679, 'loss/train': 1.645869493484497} 08/30/2021 22:02:21 - INFO - __main__ - Step 48681: {'lr': 0.00038698946829052926, 'samples': 9346752, 'steps': 48680, 'loss/train': 1.690539002418518} 08/30/2021 22:02:21 - INFO - __main__ - Step 48682: {'lr': 0.00038698502913655673, 'samples': 9346944, 'steps': 48681, 'loss/train': 1.7273426055908203} 08/30/2021 22:02:21 - INFO - __main__ - Step 48683: {'lr': 0.00038698058992086095, 'samples': 9347136, 'steps': 48682, 'loss/train': 1.6277151107788086} 08/30/2021 22:02:22 - INFO - __main__ - Step 48684: {'lr': 0.0003869761506434438, 'samples': 9347328, 'steps': 48683, 'loss/train': 1.2992688417434692} 08/30/2021 22:02:22 - INFO - __main__ - Step 48685: {'lr': 0.0003869717113043073, 'samples': 9347520, 'steps': 48684, 'loss/train': 1.895695447921753} 08/30/2021 22:02:22 - INFO - __main__ - Step 48686: {'lr': 0.00038696727190345347, 'samples': 9347712, 'steps': 48685, 'loss/train': 1.1242011785507202} 08/30/2021 22:02:24 - INFO - __main__ - Step 48687: {'lr': 0.00038696283244088426, 'samples': 9347904, 'steps': 48686, 'loss/train': 1.6465619802474976} 08/30/2021 22:02:24 - INFO - __main__ - Step 48688: {'lr': 0.0003869583929166017, 'samples': 9348096, 'steps': 48687, 'loss/train': 1.2890759706497192} 08/30/2021 22:02:25 - INFO - __main__ - Step 48689: {'lr': 0.0003869539533306079, 'samples': 9348288, 'steps': 48688, 'loss/train': 1.1586542129516602} 08/30/2021 22:02:25 - INFO - __main__ - Step 48690: {'lr': 0.00038694951368290463, 'samples': 9348480, 'steps': 48689, 'loss/train': 1.6542549133300781} 08/30/2021 22:02:25 - INFO - __main__ - Step 48691: {'lr': 0.0003869450739734941, 'samples': 9348672, 'steps': 48690, 'loss/train': 1.0293065309524536} 08/30/2021 22:02:27 - INFO - __main__ - Step 48692: {'lr': 0.00038694063420237823, 'samples': 9348864, 'steps': 48691, 'loss/train': 1.182291030883789} 08/30/2021 22:02:27 - INFO - __main__ - Step 48693: {'lr': 0.00038693619436955907, 'samples': 9349056, 'steps': 48692, 'loss/train': 1.0384904146194458} 08/30/2021 22:02:28 - INFO - __main__ - Step 48694: {'lr': 0.0003869317544750385, 'samples': 9349248, 'steps': 48693, 'loss/train': 1.405635118484497} 08/30/2021 22:02:28 - INFO - __main__ - Step 48695: {'lr': 0.0003869273145188186, 'samples': 9349440, 'steps': 48694, 'loss/train': 1.4013278484344482} 08/30/2021 22:02:28 - INFO - __main__ - Step 48696: {'lr': 0.00038692287450090143, 'samples': 9349632, 'steps': 48695, 'loss/train': 1.0663057565689087} 08/30/2021 22:02:30 - INFO - __main__ - Step 48697: {'lr': 0.0003869184344212888, 'samples': 9349824, 'steps': 48696, 'loss/train': 1.4166395664215088} 08/30/2021 22:02:31 - INFO - __main__ - Step 48698: {'lr': 0.00038691399427998296, 'samples': 9350016, 'steps': 48697, 'loss/train': 1.0973402261734009} 08/30/2021 22:02:31 - INFO - __main__ - Step 48699: {'lr': 0.0003869095540769858, 'samples': 9350208, 'steps': 48698, 'loss/train': 0.11965186893939972} 08/30/2021 22:02:31 - INFO - __main__ - Step 48700: {'lr': 0.0003869051138122992, 'samples': 9350400, 'steps': 48699, 'loss/train': 1.6753551959991455} 08/30/2021 22:02:32 - INFO - __main__ - Step 48701: {'lr': 0.0003869006734859253, 'samples': 9350592, 'steps': 48700, 'loss/train': 1.0675082206726074} 08/30/2021 22:02:33 - INFO - __main__ - Step 48702: {'lr': 0.00038689623309786617, 'samples': 9350784, 'steps': 48701, 'loss/train': 1.283065676689148} 08/30/2021 22:02:34 - INFO - __main__ - Step 48703: {'lr': 0.00038689179264812356, 'samples': 9350976, 'steps': 48702, 'loss/train': 1.254591703414917} 08/30/2021 22:02:34 - INFO - __main__ - Step 48704: {'lr': 0.00038688735213669967, 'samples': 9351168, 'steps': 48703, 'loss/train': 1.1807243824005127} 08/30/2021 22:02:34 - INFO - __main__ - Step 48705: {'lr': 0.00038688291156359654, 'samples': 9351360, 'steps': 48704, 'loss/train': 1.4753825664520264} 08/30/2021 22:02:35 - INFO - __main__ - Step 48706: {'lr': 0.000386878470928816, 'samples': 9351552, 'steps': 48705, 'loss/train': 1.469362497329712} 08/30/2021 22:02:35 - INFO - __main__ - Step 48707: {'lr': 0.0003868740302323601, 'samples': 9351744, 'steps': 48706, 'loss/train': 1.3168137073516846} 08/30/2021 22:02:36 - INFO - __main__ - Step 48708: {'lr': 0.00038686958947423096, 'samples': 9351936, 'steps': 48707, 'loss/train': 1.1679786443710327} 08/30/2021 22:02:37 - INFO - __main__ - Step 48709: {'lr': 0.00038686514865443047, 'samples': 9352128, 'steps': 48708, 'loss/train': 1.2505630254745483} 08/30/2021 22:02:37 - INFO - __main__ - Step 48710: {'lr': 0.00038686070777296057, 'samples': 9352320, 'steps': 48709, 'loss/train': 1.2325536012649536} 08/30/2021 22:02:38 - INFO - __main__ - Step 48711: {'lr': 0.00038685626682982347, 'samples': 9352512, 'steps': 48710, 'loss/train': 1.2659049034118652} 08/30/2021 22:02:38 - INFO - __main__ - Step 48712: {'lr': 0.000386851825825021, 'samples': 9352704, 'steps': 48711, 'loss/train': 1.2162539958953857} 08/30/2021 22:02:40 - INFO - __main__ - Step 48713: {'lr': 0.0003868473847585552, 'samples': 9352896, 'steps': 48712, 'loss/train': 1.3787950277328491} 08/30/2021 22:02:40 - INFO - __main__ - Step 48714: {'lr': 0.00038684294363042806, 'samples': 9353088, 'steps': 48713, 'loss/train': 1.356581687927246} 08/30/2021 22:02:41 - INFO - __main__ - Step 48715: {'lr': 0.00038683850244064164, 'samples': 9353280, 'steps': 48714, 'loss/train': 1.8732585906982422} 08/30/2021 22:02:41 - INFO - __main__ - Step 48716: {'lr': 0.0003868340611891978, 'samples': 9353472, 'steps': 48715, 'loss/train': 1.5974364280700684} 08/30/2021 22:02:41 - INFO - __main__ - Step 48717: {'lr': 0.0003868296198760988, 'samples': 9353664, 'steps': 48716, 'loss/train': 1.2716572284698486} 08/30/2021 22:02:43 - INFO - __main__ - Step 48718: {'lr': 0.00038682517850134634, 'samples': 9353856, 'steps': 48717, 'loss/train': 0.8481349945068359} 08/30/2021 22:02:44 - INFO - __main__ - Step 48719: {'lr': 0.0003868207370649427, 'samples': 9354048, 'steps': 48718, 'loss/train': 1.2210620641708374} 08/30/2021 22:02:44 - INFO - __main__ - Step 48720: {'lr': 0.0003868162955668897, 'samples': 9354240, 'steps': 48719, 'loss/train': 1.0997753143310547} 08/30/2021 22:02:44 - INFO - __main__ - Step 48721: {'lr': 0.0003868118540071894, 'samples': 9354432, 'steps': 48720, 'loss/train': 1.3661706447601318} 08/30/2021 22:02:45 - INFO - __main__ - Step 48722: {'lr': 0.0003868074123858437, 'samples': 9354624, 'steps': 48721, 'loss/train': 0.8031905293464661} 08/30/2021 22:02:46 - INFO - __main__ - Step 48723: {'lr': 0.0003868029707028548, 'samples': 9354816, 'steps': 48722, 'loss/train': 1.1705511808395386} 08/30/2021 22:02:47 - INFO - __main__ - Step 48724: {'lr': 0.00038679852895822454, 'samples': 9355008, 'steps': 48723, 'loss/train': 1.1623700857162476} 08/30/2021 22:02:47 - INFO - __main__ - Step 48725: {'lr': 0.000386794087151955, 'samples': 9355200, 'steps': 48724, 'loss/train': 1.208777904510498} 08/30/2021 22:02:47 - INFO - __main__ - Step 48726: {'lr': 0.00038678964528404816, 'samples': 9355392, 'steps': 48725, 'loss/train': 1.2652634382247925} 08/30/2021 22:02:48 - INFO - __main__ - Step 48727: {'lr': 0.000386785203354506, 'samples': 9355584, 'steps': 48726, 'loss/train': 1.4759992361068726} 08/30/2021 22:02:49 - INFO - __main__ - Step 48728: {'lr': 0.0003867807613633305, 'samples': 9355776, 'steps': 48727, 'loss/train': 0.10973817110061646} 08/30/2021 22:02:50 - INFO - __main__ - Step 48729: {'lr': 0.0003867763193105237, 'samples': 9355968, 'steps': 48728, 'loss/train': 0.14093215763568878} 08/30/2021 22:02:50 - INFO - __main__ - Step 48730: {'lr': 0.00038677187719608763, 'samples': 9356160, 'steps': 48729, 'loss/train': 0.9056994915008545} 08/30/2021 22:02:50 - INFO - __main__ - Step 48731: {'lr': 0.00038676743502002434, 'samples': 9356352, 'steps': 48730, 'loss/train': 1.218212604522705} 08/30/2021 22:02:51 - INFO - __main__ - Step 48732: {'lr': 0.0003867629927823357, 'samples': 9356544, 'steps': 48731, 'loss/train': 1.4684395790100098} 08/30/2021 22:02:52 - INFO - __main__ - Step 48733: {'lr': 0.0003867585504830237, 'samples': 9356736, 'steps': 48732, 'loss/train': 1.312386155128479} 08/30/2021 22:02:53 - INFO - __main__ - Step 48734: {'lr': 0.00038675410812209044, 'samples': 9356928, 'steps': 48733, 'loss/train': 2.101454973220825} 08/30/2021 22:02:53 - INFO - __main__ - Step 48735: {'lr': 0.0003867496656995379, 'samples': 9357120, 'steps': 48734, 'loss/train': 1.7242871522903442} 08/30/2021 22:02:54 - INFO - __main__ - Step 48736: {'lr': 0.0003867452232153681, 'samples': 9357312, 'steps': 48735, 'loss/train': 1.1259361505508423} 08/30/2021 22:02:54 - INFO - __main__ - Step 48737: {'lr': 0.00038674078066958296, 'samples': 9357504, 'steps': 48736, 'loss/train': 1.1440268754959106} 08/30/2021 22:02:54 - INFO - __main__ - Step 48738: {'lr': 0.0003867363380621846, 'samples': 9357696, 'steps': 48737, 'loss/train': 1.0000988245010376} 08/30/2021 22:02:56 - INFO - __main__ - Step 48739: {'lr': 0.0003867318953931749, 'samples': 9357888, 'steps': 48738, 'loss/train': 0.8937061429023743} 08/30/2021 22:02:57 - INFO - __main__ - Step 48740: {'lr': 0.00038672745266255594, 'samples': 9358080, 'steps': 48739, 'loss/train': 0.8546640276908875} 08/30/2021 22:02:57 - INFO - __main__ - Step 48741: {'lr': 0.0003867230098703297, 'samples': 9358272, 'steps': 48740, 'loss/train': 1.2698071002960205} 08/30/2021 22:02:57 - INFO - __main__ - Step 48742: {'lr': 0.00038671856701649813, 'samples': 9358464, 'steps': 48741, 'loss/train': 4.387177467346191} 08/30/2021 22:02:58 - INFO - __main__ - Step 48743: {'lr': 0.0003867141241010633, 'samples': 9358656, 'steps': 48742, 'loss/train': 1.956860065460205} 08/30/2021 22:02:58 - INFO - __main__ - Step 48744: {'lr': 0.00038670968112402724, 'samples': 9358848, 'steps': 48743, 'loss/train': 1.6871875524520874} 08/30/2021 22:02:59 - INFO - __main__ - Step 48745: {'lr': 0.00038670523808539194, 'samples': 9359040, 'steps': 48744, 'loss/train': 1.1926343441009521} 08/30/2021 22:03:00 - INFO - __main__ - Step 48746: {'lr': 0.0003867007949851593, 'samples': 9359232, 'steps': 48745, 'loss/train': 1.7859184741973877} 08/30/2021 22:03:00 - INFO - __main__ - Step 48747: {'lr': 0.0003866963518233314, 'samples': 9359424, 'steps': 48746, 'loss/train': 1.6357057094573975} 08/30/2021 22:03:01 - INFO - __main__ - Step 48748: {'lr': 0.00038669190859991025, 'samples': 9359616, 'steps': 48747, 'loss/train': 1.3583440780639648} 08/30/2021 22:03:01 - INFO - __main__ - Step 48749: {'lr': 0.00038668746531489787, 'samples': 9359808, 'steps': 48748, 'loss/train': 1.5124634504318237} 08/30/2021 22:03:02 - INFO - __main__ - Step 48750: {'lr': 0.0003866830219682962, 'samples': 9360000, 'steps': 48749, 'loss/train': 1.5280160903930664} 08/30/2021 22:03:03 - INFO - __main__ - Step 48751: {'lr': 0.00038667857856010727, 'samples': 9360192, 'steps': 48750, 'loss/train': 1.3867889642715454} 08/30/2021 22:03:03 - INFO - __main__ - Step 48752: {'lr': 0.00038667413509033306, 'samples': 9360384, 'steps': 48751, 'loss/train': 1.306039571762085} 08/30/2021 22:03:04 - INFO - __main__ - Step 48753: {'lr': 0.0003866696915589756, 'samples': 9360576, 'steps': 48752, 'loss/train': 2.0511984825134277} 08/30/2021 22:03:04 - INFO - __main__ - Step 48754: {'lr': 0.0003866652479660369, 'samples': 9360768, 'steps': 48753, 'loss/train': 1.418534517288208} 08/30/2021 22:03:06 - INFO - __main__ - Step 48755: {'lr': 0.00038666080431151896, 'samples': 9360960, 'steps': 48754, 'loss/train': 0.6822006106376648} 08/30/2021 22:03:06 - INFO - __main__ - Step 48756: {'lr': 0.00038665636059542367, 'samples': 9361152, 'steps': 48755, 'loss/train': 1.70613694190979} 08/30/2021 22:03:07 - INFO - __main__ - Step 48757: {'lr': 0.00038665191681775323, 'samples': 9361344, 'steps': 48756, 'loss/train': 1.1581143140792847} 08/30/2021 22:03:07 - INFO - __main__ - Step 48758: {'lr': 0.00038664747297850955, 'samples': 9361536, 'steps': 48757, 'loss/train': 1.32694673538208} 08/30/2021 22:03:07 - INFO - __main__ - Step 48759: {'lr': 0.00038664302907769456, 'samples': 9361728, 'steps': 48758, 'loss/train': 1.8530160188674927} 08/30/2021 22:03:08 - INFO - __main__ - Step 48760: {'lr': 0.00038663858511531034, 'samples': 9361920, 'steps': 48759, 'loss/train': 1.2440946102142334} 08/30/2021 22:03:09 - INFO - __main__ - Step 48761: {'lr': 0.000386634141091359, 'samples': 9362112, 'steps': 48760, 'loss/train': 1.301032304763794} 08/30/2021 22:03:10 - INFO - __main__ - Step 48762: {'lr': 0.0003866296970058423, 'samples': 9362304, 'steps': 48761, 'loss/train': 1.8586019277572632} 08/30/2021 22:03:10 - INFO - __main__ - Step 48763: {'lr': 0.0003866252528587624, 'samples': 9362496, 'steps': 48762, 'loss/train': 1.463564157485962} 08/30/2021 22:03:10 - INFO - __main__ - Step 48764: {'lr': 0.00038662080865012127, 'samples': 9362688, 'steps': 48763, 'loss/train': 1.4040064811706543} 08/30/2021 22:03:11 - INFO - __main__ - Step 48765: {'lr': 0.00038661636437992093, 'samples': 9362880, 'steps': 48764, 'loss/train': 1.363713026046753} 08/30/2021 22:03:12 - INFO - __main__ - Step 48766: {'lr': 0.0003866119200481634, 'samples': 9363072, 'steps': 48765, 'loss/train': 1.459545373916626} 08/30/2021 22:03:13 - INFO - __main__ - Step 48767: {'lr': 0.00038660747565485054, 'samples': 9363264, 'steps': 48766, 'loss/train': 1.904281735420227} 08/30/2021 22:03:13 - INFO - __main__ - Step 48768: {'lr': 0.0003866030311999845, 'samples': 9363456, 'steps': 48767, 'loss/train': 0.7655251026153564} 08/30/2021 22:03:13 - INFO - __main__ - Step 48769: {'lr': 0.0003865985866835673, 'samples': 9363648, 'steps': 48768, 'loss/train': 1.2952150106430054} 08/30/2021 22:03:14 - INFO - __main__ - Step 48770: {'lr': 0.00038659414210560087, 'samples': 9363840, 'steps': 48769, 'loss/train': 1.252069354057312} 08/30/2021 22:03:16 - INFO - __main__ - Step 48771: {'lr': 0.00038658969746608717, 'samples': 9364032, 'steps': 48770, 'loss/train': 1.5985147953033447} 08/30/2021 22:03:16 - INFO - __main__ - Step 48772: {'lr': 0.0003865852527650283, 'samples': 9364224, 'steps': 48771, 'loss/train': 1.8734334707260132} 08/30/2021 22:03:17 - INFO - __main__ - Step 48773: {'lr': 0.0003865808080024262, 'samples': 9364416, 'steps': 48772, 'loss/train': 1.3664510250091553} 08/30/2021 22:03:17 - INFO - __main__ - Step 48774: {'lr': 0.00038657636317828293, 'samples': 9364608, 'steps': 48773, 'loss/train': 1.2749916315078735} 08/30/2021 22:03:17 - INFO - __main__ - Step 48775: {'lr': 0.00038657191829260043, 'samples': 9364800, 'steps': 48774, 'loss/train': 1.3623124361038208} 08/30/2021 22:03:19 - INFO - __main__ - Step 48776: {'lr': 0.00038656747334538073, 'samples': 9364992, 'steps': 48775, 'loss/train': 1.9370123147964478} 08/30/2021 22:03:19 - INFO - __main__ - Step 48777: {'lr': 0.00038656302833662583, 'samples': 9365184, 'steps': 48776, 'loss/train': 1.8823027610778809} 08/30/2021 22:03:20 - INFO - __main__ - Step 48778: {'lr': 0.00038655858326633774, 'samples': 9365376, 'steps': 48777, 'loss/train': 1.4413312673568726} 08/30/2021 22:03:20 - INFO - __main__ - Step 48779: {'lr': 0.0003865541381345185, 'samples': 9365568, 'steps': 48778, 'loss/train': 1.325539231300354} 08/30/2021 22:03:20 - INFO - __main__ - Step 48780: {'lr': 0.00038654969294117, 'samples': 9365760, 'steps': 48779, 'loss/train': 1.5048428773880005} 08/30/2021 22:03:21 - INFO - __main__ - Step 48781: {'lr': 0.0003865452476862944, 'samples': 9365952, 'steps': 48780, 'loss/train': 1.2868441343307495} 08/30/2021 22:03:22 - INFO - __main__ - Step 48782: {'lr': 0.0003865408023698935, 'samples': 9366144, 'steps': 48781, 'loss/train': 1.2281959056854248} 08/30/2021 22:03:23 - INFO - __main__ - Step 48783: {'lr': 0.00038653635699196956, 'samples': 9366336, 'steps': 48782, 'loss/train': 1.5570204257965088} 08/30/2021 22:03:23 - INFO - __main__ - Step 48784: {'lr': 0.0003865319115525244, 'samples': 9366528, 'steps': 48783, 'loss/train': 1.641545295715332} 08/30/2021 22:03:23 - INFO - __main__ - Step 48785: {'lr': 0.00038652746605156, 'samples': 9366720, 'steps': 48784, 'loss/train': 1.150676965713501} 08/30/2021 22:03:24 - INFO - __main__ - Step 48786: {'lr': 0.0003865230204890785, 'samples': 9366912, 'steps': 48785, 'loss/train': 1.3756340742111206} 08/30/2021 22:03:25 - INFO - __main__ - Step 48787: {'lr': 0.0003865185748650818, 'samples': 9367104, 'steps': 48786, 'loss/train': 1.1080893278121948} 08/30/2021 22:03:26 - INFO - __main__ - Step 48788: {'lr': 0.00038651412917957195, 'samples': 9367296, 'steps': 48787, 'loss/train': 0.9076159000396729} 08/30/2021 22:03:26 - INFO - __main__ - Step 48789: {'lr': 0.000386509683432551, 'samples': 9367488, 'steps': 48788, 'loss/train': 1.5767009258270264} 08/30/2021 22:03:26 - INFO - __main__ - Step 48790: {'lr': 0.0003865052376240208, 'samples': 9367680, 'steps': 48789, 'loss/train': 1.0853540897369385} 08/30/2021 22:03:27 - INFO - __main__ - Step 48791: {'lr': 0.00038650079175398346, 'samples': 9367872, 'steps': 48790, 'loss/train': 1.300365924835205} 08/30/2021 22:03:28 - INFO - __main__ - Step 48792: {'lr': 0.00038649634582244095, 'samples': 9368064, 'steps': 48791, 'loss/train': 0.9238002896308899} 08/30/2021 22:03:29 - INFO - __main__ - Step 48793: {'lr': 0.0003864918998293954, 'samples': 9368256, 'steps': 48792, 'loss/train': 1.3387572765350342} 08/30/2021 22:03:29 - INFO - __main__ - Step 48794: {'lr': 0.0003864874537748486, 'samples': 9368448, 'steps': 48793, 'loss/train': 1.006764531135559} 08/30/2021 22:03:29 - INFO - __main__ - Step 48795: {'lr': 0.00038648300765880276, 'samples': 9368640, 'steps': 48794, 'loss/train': 0.6098302006721497} 08/30/2021 22:03:30 - INFO - __main__ - Step 48796: {'lr': 0.0003864785614812597, 'samples': 9368832, 'steps': 48795, 'loss/train': 0.7445828318595886} 08/30/2021 22:03:31 - INFO - __main__ - Step 48797: {'lr': 0.00038647411524222146, 'samples': 9369024, 'steps': 48796, 'loss/train': 1.2196470499038696} 08/30/2021 22:03:31 - INFO - __main__ - Step 48798: {'lr': 0.00038646966894169014, 'samples': 9369216, 'steps': 48797, 'loss/train': 0.8344257473945618} 08/30/2021 22:03:32 - INFO - __main__ - Step 48799: {'lr': 0.00038646522257966776, 'samples': 9369408, 'steps': 48798, 'loss/train': 1.6496281623840332} 08/30/2021 22:03:32 - INFO - __main__ - Step 48800: {'lr': 0.0003864607761561562, 'samples': 9369600, 'steps': 48799, 'loss/train': 1.2403191328048706} 08/30/2021 22:03:33 - INFO - __main__ - Step 48801: {'lr': 0.00038645632967115753, 'samples': 9369792, 'steps': 48800, 'loss/train': 1.62411630153656} 08/30/2021 22:03:33 - INFO - __main__ - Step 48802: {'lr': 0.0003864518831246737, 'samples': 9369984, 'steps': 48801, 'loss/train': 1.5026872158050537} 08/30/2021 22:03:34 - INFO - __main__ - Step 48803: {'lr': 0.00038644743651670684, 'samples': 9370176, 'steps': 48802, 'loss/train': 1.3241527080535889} 08/30/2021 22:03:35 - INFO - __main__ - Step 48804: {'lr': 0.00038644298984725876, 'samples': 9370368, 'steps': 48803, 'loss/train': 1.9161458015441895} 08/30/2021 22:03:35 - INFO - __main__ - Step 48805: {'lr': 0.00038643854311633166, 'samples': 9370560, 'steps': 48804, 'loss/train': 1.5951666831970215} 08/30/2021 22:03:35 - INFO - __main__ - Step 48806: {'lr': 0.0003864340963239275, 'samples': 9370752, 'steps': 48805, 'loss/train': 1.6425849199295044} 08/30/2021 22:03:36 - INFO - __main__ - Step 48807: {'lr': 0.00038642964947004815, 'samples': 9370944, 'steps': 48806, 'loss/train': 1.3888704776763916} 08/30/2021 22:03:37 - INFO - __main__ - Step 48808: {'lr': 0.0003864252025546957, 'samples': 9371136, 'steps': 48807, 'loss/train': 1.5884183645248413} 08/30/2021 22:03:38 - INFO - __main__ - Step 48809: {'lr': 0.00038642075557787225, 'samples': 9371328, 'steps': 48808, 'loss/train': 1.2967875003814697} 08/30/2021 22:03:38 - INFO - __main__ - Step 48810: {'lr': 0.0003864163085395797, 'samples': 9371520, 'steps': 48809, 'loss/train': 2.3215925693511963} 08/30/2021 22:03:39 - INFO - __main__ - Step 48811: {'lr': 0.00038641186143982, 'samples': 9371712, 'steps': 48810, 'loss/train': 1.638586163520813} 08/30/2021 22:03:39 - INFO - __main__ - Step 48812: {'lr': 0.0003864074142785952, 'samples': 9371904, 'steps': 48811, 'loss/train': 0.7048910856246948} 08/30/2021 22:03:40 - INFO - __main__ - Step 48813: {'lr': 0.0003864029670559074, 'samples': 9372096, 'steps': 48812, 'loss/train': 0.5984480381011963} 08/30/2021 22:03:41 - INFO - __main__ - Step 48814: {'lr': 0.0003863985197717585, 'samples': 9372288, 'steps': 48813, 'loss/train': 1.8973820209503174} 08/30/2021 22:03:41 - INFO - __main__ - Step 48815: {'lr': 0.0003863940724261505, 'samples': 9372480, 'steps': 48814, 'loss/train': 1.1817797422409058} 08/30/2021 22:03:41 - INFO - __main__ - Step 48816: {'lr': 0.0003863896250190855, 'samples': 9372672, 'steps': 48815, 'loss/train': 1.7076836824417114} 08/30/2021 22:03:42 - INFO - __main__ - Step 48817: {'lr': 0.00038638517755056534, 'samples': 9372864, 'steps': 48816, 'loss/train': 1.409352421760559} 08/30/2021 22:03:44 - INFO - __main__ - Step 48818: {'lr': 0.00038638073002059223, 'samples': 9373056, 'steps': 48817, 'loss/train': 1.6329432725906372} 08/30/2021 22:03:44 - INFO - __main__ - Step 48819: {'lr': 0.000386376282429168, 'samples': 9373248, 'steps': 48818, 'loss/train': 0.04905432090163231} 08/30/2021 22:03:44 - INFO - __main__ - Step 48820: {'lr': 0.0003863718347762948, 'samples': 9373440, 'steps': 48819, 'loss/train': 0.043754201382398605} 08/30/2021 22:03:45 - INFO - __main__ - Step 48821: {'lr': 0.0003863673870619744, 'samples': 9373632, 'steps': 48820, 'loss/train': 1.8629157543182373} 08/30/2021 22:03:45 - INFO - __main__ - Step 48822: {'lr': 0.00038636293928620915, 'samples': 9373824, 'steps': 48821, 'loss/train': 1.4572480916976929} 08/30/2021 22:03:45 - INFO - __main__ - Step 48823: {'lr': 0.0003863584914490007, 'samples': 9374016, 'steps': 48822, 'loss/train': 0.354684978723526} 08/30/2021 22:03:47 - INFO - __main__ - Step 48824: {'lr': 0.0003863540435503513, 'samples': 9374208, 'steps': 48823, 'loss/train': 0.7377296686172485} 08/30/2021 22:03:48 - INFO - __main__ - Step 48825: {'lr': 0.0003863495955902629, 'samples': 9374400, 'steps': 48824, 'loss/train': 1.657758116722107} 08/30/2021 22:03:48 - INFO - __main__ - Step 48826: {'lr': 0.00038634514756873746, 'samples': 9374592, 'steps': 48825, 'loss/train': 1.356229305267334} 08/30/2021 22:03:49 - INFO - __main__ - Step 48827: {'lr': 0.000386340699485777, 'samples': 9374784, 'steps': 48826, 'loss/train': 1.508836269378662} 08/30/2021 22:03:49 - INFO - __main__ - Step 48828: {'lr': 0.0003863362513413835, 'samples': 9374976, 'steps': 48827, 'loss/train': 1.3471057415008545} 08/30/2021 22:03:50 - INFO - __main__ - Step 48829: {'lr': 0.00038633180313555894, 'samples': 9375168, 'steps': 48828, 'loss/train': 1.279208779335022} 08/30/2021 22:03:51 - INFO - __main__ - Step 48830: {'lr': 0.0003863273548683054, 'samples': 9375360, 'steps': 48829, 'loss/train': 1.1051563024520874} 08/30/2021 22:03:51 - INFO - __main__ - Step 48831: {'lr': 0.0003863229065396249, 'samples': 9375552, 'steps': 48830, 'loss/train': 1.3010259866714478} 08/30/2021 22:03:52 - INFO - __main__ - Step 48832: {'lr': 0.0003863184581495194, 'samples': 9375744, 'steps': 48831, 'loss/train': 1.3051475286483765} 08/30/2021 22:03:52 - INFO - __main__ - Step 48833: {'lr': 0.0003863140096979909, 'samples': 9375936, 'steps': 48832, 'loss/train': 1.056808590888977} 08/30/2021 22:03:53 - INFO - __main__ - Step 48834: {'lr': 0.00038630956118504146, 'samples': 9376128, 'steps': 48833, 'loss/train': 0.875105082988739} 08/30/2021 22:03:54 - INFO - __main__ - Step 48835: {'lr': 0.00038630511261067294, 'samples': 9376320, 'steps': 48834, 'loss/train': 1.1130019426345825} 08/30/2021 22:03:54 - INFO - __main__ - Step 48836: {'lr': 0.0003863006639748875, 'samples': 9376512, 'steps': 48835, 'loss/train': 1.3328715562820435} 08/30/2021 22:03:55 - INFO - __main__ - Step 48837: {'lr': 0.000386296215277687, 'samples': 9376704, 'steps': 48836, 'loss/train': 1.9974236488342285} 08/30/2021 22:03:55 - INFO - __main__ - Step 48838: {'lr': 0.0003862917665190736, 'samples': 9376896, 'steps': 48837, 'loss/train': 1.3784449100494385} 08/30/2021 22:03:57 - INFO - __main__ - Step 48839: {'lr': 0.0003862873176990492, 'samples': 9377088, 'steps': 48838, 'loss/train': 1.9237213134765625} 08/30/2021 22:03:57 - INFO - __main__ - Step 48840: {'lr': 0.00038628286881761594, 'samples': 9377280, 'steps': 48839, 'loss/train': 1.4314467906951904} 08/30/2021 22:03:57 - INFO - __main__ - Step 48841: {'lr': 0.0003862784198747756, 'samples': 9377472, 'steps': 48840, 'loss/train': 0.1966492086648941} 08/30/2021 22:03:58 - INFO - __main__ - Step 48842: {'lr': 0.0003862739708705304, 'samples': 9377664, 'steps': 48841, 'loss/train': 1.95949125289917} 08/30/2021 22:03:58 - INFO - __main__ - Step 48843: {'lr': 0.0003862695218048822, 'samples': 9377856, 'steps': 48842, 'loss/train': 1.1845020055770874} 08/30/2021 22:04:00 - INFO - __main__ - Step 48844: {'lr': 0.000386265072677833, 'samples': 9378048, 'steps': 48843, 'loss/train': 1.2413744926452637} 08/30/2021 22:04:00 - INFO - __main__ - Step 48845: {'lr': 0.00038626062348938494, 'samples': 9378240, 'steps': 48844, 'loss/train': 0.3717733919620514} 08/30/2021 22:04:01 - INFO - __main__ - Step 48846: {'lr': 0.00038625617423954, 'samples': 9378432, 'steps': 48845, 'loss/train': 0.07578319311141968} 08/30/2021 22:04:01 - INFO - __main__ - Step 48847: {'lr': 0.00038625172492829995, 'samples': 9378624, 'steps': 48846, 'loss/train': 1.8362623453140259} 08/30/2021 22:04:01 - INFO - __main__ - Step 48848: {'lr': 0.00038624727555566714, 'samples': 9378816, 'steps': 48847, 'loss/train': 1.4770867824554443} 08/30/2021 22:04:02 - INFO - __main__ - Step 48849: {'lr': 0.0003862428261216433, 'samples': 9379008, 'steps': 48848, 'loss/train': 1.720317006111145} 08/30/2021 22:04:03 - INFO - __main__ - Step 48850: {'lr': 0.00038623837662623065, 'samples': 9379200, 'steps': 48849, 'loss/train': 1.3068805932998657} 08/30/2021 22:04:04 - INFO - __main__ - Step 48851: {'lr': 0.000386233927069431, 'samples': 9379392, 'steps': 48850, 'loss/train': 0.20891162753105164} 08/30/2021 22:04:04 - INFO - __main__ - Step 48852: {'lr': 0.0003862294774512465, 'samples': 9379584, 'steps': 48851, 'loss/train': 1.6089826822280884} 08/30/2021 22:04:04 - INFO - __main__ - Step 48853: {'lr': 0.00038622502777167913, 'samples': 9379776, 'steps': 48852, 'loss/train': 0.48764216899871826} 08/30/2021 22:04:05 - INFO - __main__ - Step 48854: {'lr': 0.00038622057803073075, 'samples': 9379968, 'steps': 48853, 'loss/train': 1.1983458995819092} 08/30/2021 22:04:06 - INFO - __main__ - Step 48855: {'lr': 0.0003862161282284036, 'samples': 9380160, 'steps': 48854, 'loss/train': 1.7085390090942383} 08/30/2021 22:04:07 - INFO - __main__ - Step 48856: {'lr': 0.00038621167836469945, 'samples': 9380352, 'steps': 48855, 'loss/train': 1.2399362325668335} 08/30/2021 22:04:07 - INFO - __main__ - Step 48857: {'lr': 0.0003862072284396205, 'samples': 9380544, 'steps': 48856, 'loss/train': 0.9718574285507202} 08/30/2021 22:04:07 - INFO - __main__ - Step 48858: {'lr': 0.00038620277845316867, 'samples': 9380736, 'steps': 48857, 'loss/train': 1.0807909965515137} 08/30/2021 22:04:08 - INFO - __main__ - Step 48859: {'lr': 0.00038619832840534586, 'samples': 9380928, 'steps': 48858, 'loss/train': 0.9542996287345886} 08/30/2021 22:04:09 - INFO - __main__ - Step 48860: {'lr': 0.0003861938782961544, 'samples': 9381120, 'steps': 48859, 'loss/train': 1.150165319442749} 08/30/2021 22:04:10 - INFO - __main__ - Step 48861: {'lr': 0.0003861894281255959, 'samples': 9381312, 'steps': 48860, 'loss/train': 1.0504695177078247} 08/30/2021 22:04:10 - INFO - __main__ - Step 48862: {'lr': 0.0003861849778936726, 'samples': 9381504, 'steps': 48861, 'loss/train': 3.8373653888702393} 08/30/2021 22:04:10 - INFO - __main__ - Step 48863: {'lr': 0.00038618052760038647, 'samples': 9381696, 'steps': 48862, 'loss/train': 1.8387144804000854} 08/30/2021 22:04:11 - INFO - __main__ - Step 48864: {'lr': 0.00038617607724573944, 'samples': 9381888, 'steps': 48863, 'loss/train': 0.1540784239768982} 08/30/2021 22:04:12 - INFO - __main__ - Step 48865: {'lr': 0.0003861716268297336, 'samples': 9382080, 'steps': 48864, 'loss/train': 0.9872737526893616} 08/30/2021 22:04:13 - INFO - __main__ - Step 48866: {'lr': 0.000386167176352371, 'samples': 9382272, 'steps': 48865, 'loss/train': 0.6970322132110596} 08/30/2021 22:04:13 - INFO - __main__ - Step 48867: {'lr': 0.00038616272581365354, 'samples': 9382464, 'steps': 48866, 'loss/train': 1.0987118482589722} 08/30/2021 22:04:13 - INFO - __main__ - Step 48868: {'lr': 0.00038615827521358315, 'samples': 9382656, 'steps': 48867, 'loss/train': 1.129199504852295} 08/30/2021 22:04:14 - INFO - __main__ - Step 48869: {'lr': 0.00038615382455216204, 'samples': 9382848, 'steps': 48868, 'loss/train': 1.5722532272338867} 08/30/2021 22:04:16 - INFO - __main__ - Step 48870: {'lr': 0.0003861493738293921, 'samples': 9383040, 'steps': 48869, 'loss/train': 1.3339334726333618} 08/30/2021 22:04:16 - INFO - __main__ - Step 48871: {'lr': 0.0003861449230452753, 'samples': 9383232, 'steps': 48870, 'loss/train': 1.812423586845398} 08/30/2021 22:04:16 - INFO - __main__ - Step 48872: {'lr': 0.00038614047219981374, 'samples': 9383424, 'steps': 48871, 'loss/train': 1.188661813735962} 08/30/2021 22:04:17 - INFO - __main__ - Step 48873: {'lr': 0.0003861360212930094, 'samples': 9383616, 'steps': 48872, 'loss/train': 1.4395866394042969} 08/30/2021 22:04:17 - INFO - __main__ - Step 48874: {'lr': 0.0003861315703248643, 'samples': 9383808, 'steps': 48873, 'loss/train': 1.8299689292907715} 08/30/2021 22:04:19 - INFO - __main__ - Step 48875: {'lr': 0.0003861271192953804, 'samples': 9384000, 'steps': 48874, 'loss/train': 1.4445850849151611} 08/30/2021 22:04:19 - INFO - __main__ - Step 48876: {'lr': 0.00038612266820455964, 'samples': 9384192, 'steps': 48875, 'loss/train': 1.373655915260315} 08/30/2021 22:04:19 - INFO - __main__ - Step 48877: {'lr': 0.0003861182170524041, 'samples': 9384384, 'steps': 48876, 'loss/train': 0.6758992075920105} 08/30/2021 22:04:20 - INFO - __main__ - Step 48878: {'lr': 0.0003861137658389159, 'samples': 9384576, 'steps': 48877, 'loss/train': 1.1939611434936523} 08/30/2021 22:04:20 - INFO - __main__ - Step 48879: {'lr': 0.0003861093145640969, 'samples': 9384768, 'steps': 48878, 'loss/train': 1.2324585914611816} 08/30/2021 22:04:22 - INFO - __main__ - Step 48880: {'lr': 0.00038610486322794915, 'samples': 9384960, 'steps': 48879, 'loss/train': 0.9681851267814636} 08/30/2021 22:04:23 - INFO - __main__ - Step 48881: {'lr': 0.0003861004118304746, 'samples': 9385152, 'steps': 48880, 'loss/train': 1.161491870880127} 08/30/2021 22:04:23 - INFO - __main__ - Step 48882: {'lr': 0.0003860959603716754, 'samples': 9385344, 'steps': 48881, 'loss/train': 1.2258241176605225} 08/30/2021 22:04:23 - INFO - __main__ - Step 48883: {'lr': 0.00038609150885155337, 'samples': 9385536, 'steps': 48882, 'loss/train': 0.5083160996437073} 08/30/2021 22:04:24 - INFO - __main__ - Step 48884: {'lr': 0.0003860870572701106, 'samples': 9385728, 'steps': 48883, 'loss/train': 1.3246307373046875} 08/30/2021 22:04:24 - INFO - __main__ - Step 48885: {'lr': 0.0003860826056273492, 'samples': 9385920, 'steps': 48884, 'loss/train': 1.828690767288208} 08/30/2021 22:04:26 - INFO - __main__ - Step 48886: {'lr': 0.0003860781539232709, 'samples': 9386112, 'steps': 48885, 'loss/train': 1.5244758129119873} 08/30/2021 22:04:26 - INFO - __main__ - Step 48887: {'lr': 0.0003860737021578781, 'samples': 9386304, 'steps': 48886, 'loss/train': 1.7214467525482178} 08/30/2021 22:04:26 - INFO - __main__ - Step 48888: {'lr': 0.00038606925033117246, 'samples': 9386496, 'steps': 48887, 'loss/train': 1.25721275806427} 08/30/2021 22:04:27 - INFO - __main__ - Step 48889: {'lr': 0.00038606479844315614, 'samples': 9386688, 'steps': 48888, 'loss/train': 1.7863469123840332} 08/30/2021 22:04:27 - INFO - __main__ - Step 48890: {'lr': 0.00038606034649383116, 'samples': 9386880, 'steps': 48889, 'loss/train': 1.0416723489761353} 08/30/2021 22:04:28 - INFO - __main__ - Step 48891: {'lr': 0.0003860558944831994, 'samples': 9387072, 'steps': 48890, 'loss/train': 1.6393935680389404} 08/30/2021 22:04:29 - INFO - __main__ - Step 48892: {'lr': 0.000386051442411263, 'samples': 9387264, 'steps': 48891, 'loss/train': 1.5236557722091675} 08/30/2021 22:04:29 - INFO - __main__ - Step 48893: {'lr': 0.00038604699027802394, 'samples': 9387456, 'steps': 48892, 'loss/train': 1.3921586275100708} 08/30/2021 22:04:30 - INFO - __main__ - Step 48894: {'lr': 0.0003860425380834842, 'samples': 9387648, 'steps': 48893, 'loss/train': 0.5640357136726379} 08/30/2021 22:04:30 - INFO - __main__ - Step 48895: {'lr': 0.0003860380858276458, 'samples': 9387840, 'steps': 48894, 'loss/train': 1.8777879476547241} 08/30/2021 22:04:31 - INFO - __main__ - Step 48896: {'lr': 0.0003860336335105107, 'samples': 9388032, 'steps': 48895, 'loss/train': 1.0305182933807373} 08/30/2021 22:04:32 - INFO - __main__ - Step 48897: {'lr': 0.000386029181132081, 'samples': 9388224, 'steps': 48896, 'loss/train': 1.4447362422943115} 08/30/2021 22:04:32 - INFO - __main__ - Step 48898: {'lr': 0.0003860247286923586, 'samples': 9388416, 'steps': 48897, 'loss/train': 1.4515936374664307} 08/30/2021 22:04:33 - INFO - __main__ - Step 48899: {'lr': 0.0003860202761913455, 'samples': 9388608, 'steps': 48898, 'loss/train': 1.4361896514892578} 08/30/2021 22:04:33 - INFO - __main__ - Step 48900: {'lr': 0.00038601582362904384, 'samples': 9388800, 'steps': 48899, 'loss/train': 1.861391305923462} 08/30/2021 22:04:34 - INFO - __main__ - Step 48901: {'lr': 0.0003860113710054556, 'samples': 9388992, 'steps': 48900, 'loss/train': 1.129175066947937} 08/30/2021 22:04:35 - INFO - __main__ - Step 48902: {'lr': 0.00038600691832058265, 'samples': 9389184, 'steps': 48901, 'loss/train': 1.0938245058059692} 08/30/2021 22:04:35 - INFO - __main__ - Step 48903: {'lr': 0.0003860024655744271, 'samples': 9389376, 'steps': 48902, 'loss/train': 1.6246204376220703} 08/30/2021 22:04:36 - INFO - __main__ - Step 48904: {'lr': 0.000385998012766991, 'samples': 9389568, 'steps': 48903, 'loss/train': 1.0381877422332764} 08/30/2021 22:04:36 - INFO - __main__ - Step 48905: {'lr': 0.0003859935598982762, 'samples': 9389760, 'steps': 48904, 'loss/train': 1.2635709047317505} 08/30/2021 22:04:37 - INFO - __main__ - Step 48906: {'lr': 0.0003859891069682848, 'samples': 9389952, 'steps': 48905, 'loss/train': 0.6974548697471619} 08/30/2021 22:04:38 - INFO - __main__ - Step 48907: {'lr': 0.0003859846539770189, 'samples': 9390144, 'steps': 48906, 'loss/train': 1.1524872779846191} 08/30/2021 22:04:38 - INFO - __main__ - Step 48908: {'lr': 0.0003859802009244804, 'samples': 9390336, 'steps': 48907, 'loss/train': 0.04876082018017769} 08/30/2021 22:04:39 - INFO - __main__ - Step 48909: {'lr': 0.00038597574781067123, 'samples': 9390528, 'steps': 48908, 'loss/train': 1.3122353553771973} 08/30/2021 22:04:39 - INFO - __main__ - Step 48910: {'lr': 0.0003859712946355936, 'samples': 9390720, 'steps': 48909, 'loss/train': 0.6884896159172058} 08/30/2021 22:04:40 - INFO - __main__ - Step 48911: {'lr': 0.0003859668413992493, 'samples': 9390912, 'steps': 48910, 'loss/train': 1.178629755973816} 08/30/2021 22:04:41 - INFO - __main__ - Step 48912: {'lr': 0.0003859623881016404, 'samples': 9391104, 'steps': 48911, 'loss/train': 1.3759442567825317} 08/30/2021 22:04:41 - INFO - __main__ - Step 48913: {'lr': 0.000385957934742769, 'samples': 9391296, 'steps': 48912, 'loss/train': 0.03345291689038277} 08/30/2021 22:04:42 - INFO - __main__ - Step 48914: {'lr': 0.0003859534813226372, 'samples': 9391488, 'steps': 48913, 'loss/train': 1.1845836639404297} 08/30/2021 22:04:42 - INFO - __main__ - Step 48915: {'lr': 0.00038594902784124663, 'samples': 9391680, 'steps': 48914, 'loss/train': 1.2679426670074463} 08/30/2021 22:04:44 - INFO - __main__ - Step 48916: {'lr': 0.00038594457429859966, 'samples': 9391872, 'steps': 48915, 'loss/train': 0.6124281883239746} 08/30/2021 22:04:44 - INFO - __main__ - Step 48917: {'lr': 0.00038594012069469814, 'samples': 9392064, 'steps': 48916, 'loss/train': 1.376297950744629} 08/30/2021 22:04:44 - INFO - __main__ - Step 48918: {'lr': 0.0003859356670295441, 'samples': 9392256, 'steps': 48917, 'loss/train': 1.6040748357772827} 08/30/2021 22:04:45 - INFO - __main__ - Step 48919: {'lr': 0.00038593121330313953, 'samples': 9392448, 'steps': 48918, 'loss/train': 1.0200928449630737} 08/30/2021 22:04:45 - INFO - __main__ - Step 48920: {'lr': 0.0003859267595154865, 'samples': 9392640, 'steps': 48919, 'loss/train': 1.6063692569732666} 08/30/2021 22:04:46 - INFO - __main__ - Step 48921: {'lr': 0.0003859223056665869, 'samples': 9392832, 'steps': 48920, 'loss/train': 0.5206479430198669} 08/30/2021 22:04:47 - INFO - __main__ - Step 48922: {'lr': 0.00038591785175644283, 'samples': 9393024, 'steps': 48921, 'loss/train': 0.9892064929008484} 08/30/2021 22:04:47 - INFO - __main__ - Step 48923: {'lr': 0.0003859133977850563, 'samples': 9393216, 'steps': 48922, 'loss/train': 1.2768689393997192} 08/30/2021 22:04:48 - INFO - __main__ - Step 48924: {'lr': 0.00038590894375242925, 'samples': 9393408, 'steps': 48923, 'loss/train': 1.22904372215271} 08/30/2021 22:04:48 - INFO - __main__ - Step 48925: {'lr': 0.0003859044896585637, 'samples': 9393600, 'steps': 48924, 'loss/train': 1.7870597839355469} 08/30/2021 22:04:48 - INFO - __main__ - Step 48926: {'lr': 0.00038590003550346177, 'samples': 9393792, 'steps': 48925, 'loss/train': 1.990837812423706} 08/30/2021 22:04:50 - INFO - __main__ - Step 48927: {'lr': 0.0003858955812871254, 'samples': 9393984, 'steps': 48926, 'loss/train': 0.5840023756027222} 08/30/2021 22:04:50 - INFO - __main__ - Step 48928: {'lr': 0.0003858911270095565, 'samples': 9394176, 'steps': 48927, 'loss/train': 1.9934320449829102} 08/30/2021 22:04:51 - INFO - __main__ - Step 48929: {'lr': 0.00038588667267075715, 'samples': 9394368, 'steps': 48928, 'loss/train': 0.8887355327606201} 08/30/2021 22:04:51 - INFO - __main__ - Step 48930: {'lr': 0.0003858822182707294, 'samples': 9394560, 'steps': 48929, 'loss/train': 1.5476365089416504} 08/30/2021 22:04:51 - INFO - __main__ - Step 48931: {'lr': 0.00038587776380947516, 'samples': 9394752, 'steps': 48930, 'loss/train': 0.06992319226264954} 08/30/2021 22:04:54 - INFO - __main__ - Step 48932: {'lr': 0.0003858733092869966, 'samples': 9394944, 'steps': 48931, 'loss/train': 1.5100784301757812} 08/30/2021 22:04:54 - INFO - __main__ - Step 48933: {'lr': 0.00038586885470329554, 'samples': 9395136, 'steps': 48932, 'loss/train': 1.2027466297149658} 08/30/2021 22:04:54 - INFO - __main__ - Step 48934: {'lr': 0.0003858644000583741, 'samples': 9395328, 'steps': 48933, 'loss/train': 1.4855645895004272} 08/30/2021 22:04:55 - INFO - __main__ - Step 48935: {'lr': 0.0003858599453522342, 'samples': 9395520, 'steps': 48934, 'loss/train': 1.2240182161331177} 08/30/2021 22:04:55 - INFO - __main__ - Step 48936: {'lr': 0.000385855490584878, 'samples': 9395712, 'steps': 48935, 'loss/train': 0.6295226216316223} 08/30/2021 22:04:57 - INFO - __main__ - Step 48937: {'lr': 0.0003858510357563074, 'samples': 9395904, 'steps': 48936, 'loss/train': 1.3402289152145386} 08/30/2021 22:04:57 - INFO - __main__ - Step 48938: {'lr': 0.00038584658086652433, 'samples': 9396096, 'steps': 48937, 'loss/train': 1.4372090101242065} 08/30/2021 22:04:57 - INFO - __main__ - Step 48939: {'lr': 0.00038584212591553105, 'samples': 9396288, 'steps': 48938, 'loss/train': 1.3219102621078491} 08/30/2021 22:04:58 - INFO - __main__ - Step 48940: {'lr': 0.00038583767090332924, 'samples': 9396480, 'steps': 48939, 'loss/train': 1.308092474937439} 08/30/2021 22:04:58 - INFO - __main__ - Step 48941: {'lr': 0.00038583321582992113, 'samples': 9396672, 'steps': 48940, 'loss/train': 1.9299805164337158} 08/30/2021 22:05:00 - INFO - __main__ - Step 48942: {'lr': 0.0003858287606953087, 'samples': 9396864, 'steps': 48941, 'loss/train': 1.8272383213043213} 08/30/2021 22:05:00 - INFO - __main__ - Step 48943: {'lr': 0.00038582430549949386, 'samples': 9397056, 'steps': 48942, 'loss/train': 0.9642685055732727} 08/30/2021 22:05:01 - INFO - __main__ - Step 48944: {'lr': 0.00038581985024247877, 'samples': 9397248, 'steps': 48943, 'loss/train': 1.1718032360076904} 08/30/2021 22:05:01 - INFO - __main__ - Step 48945: {'lr': 0.0003858153949242653, 'samples': 9397440, 'steps': 48944, 'loss/train': 0.06403294205665588} 08/30/2021 22:05:01 - INFO - __main__ - Step 48946: {'lr': 0.00038581093954485554, 'samples': 9397632, 'steps': 48945, 'loss/train': 1.5827386379241943} 08/30/2021 22:05:02 - INFO - __main__ - Step 48947: {'lr': 0.00038580648410425146, 'samples': 9397824, 'steps': 48946, 'loss/train': 1.8211649656295776} 08/30/2021 22:05:03 - INFO - __main__ - Step 48948: {'lr': 0.00038580202860245507, 'samples': 9398016, 'steps': 48947, 'loss/train': 1.4734798669815063} 08/30/2021 22:05:03 - INFO - __main__ - Step 48949: {'lr': 0.00038579757303946826, 'samples': 9398208, 'steps': 48948, 'loss/train': 1.2593379020690918} 08/30/2021 22:05:04 - INFO - __main__ - Step 48950: {'lr': 0.0003857931174152933, 'samples': 9398400, 'steps': 48949, 'loss/train': 1.5898241996765137} 08/30/2021 22:05:04 - INFO - __main__ - Step 48951: {'lr': 0.000385788661729932, 'samples': 9398592, 'steps': 48950, 'loss/train': 1.2492865324020386} 08/30/2021 22:05:06 - INFO - __main__ - Step 48952: {'lr': 0.0003857842059833865, 'samples': 9398784, 'steps': 48951, 'loss/train': 1.3450074195861816} 08/30/2021 22:05:06 - INFO - __main__ - Step 48953: {'lr': 0.0003857797501756587, 'samples': 9398976, 'steps': 48952, 'loss/train': 1.014382243156433} 08/30/2021 22:05:06 - INFO - __main__ - Step 48954: {'lr': 0.0003857752943067506, 'samples': 9399168, 'steps': 48953, 'loss/train': 1.793885350227356} 08/30/2021 22:05:07 - INFO - __main__ - Step 48955: {'lr': 0.0003857708383766643, 'samples': 9399360, 'steps': 48954, 'loss/train': 1.1865606307983398} 08/30/2021 22:05:07 - INFO - __main__ - Step 48956: {'lr': 0.00038576638238540167, 'samples': 9399552, 'steps': 48955, 'loss/train': 0.9951339960098267} 08/30/2021 22:05:08 - INFO - __main__ - Step 48957: {'lr': 0.00038576192633296485, 'samples': 9399744, 'steps': 48956, 'loss/train': 1.3709392547607422} 08/30/2021 22:05:09 - INFO - __main__ - Step 48958: {'lr': 0.00038575747021935583, 'samples': 9399936, 'steps': 48957, 'loss/train': 1.641698956489563} 08/30/2021 22:05:09 - INFO - __main__ - Step 48959: {'lr': 0.0003857530140445765, 'samples': 9400128, 'steps': 48958, 'loss/train': 1.6269811391830444} 08/30/2021 22:05:10 - INFO - __main__ - Step 48960: {'lr': 0.00038574855780862903, 'samples': 9400320, 'steps': 48959, 'loss/train': 1.3960156440734863} 08/30/2021 22:05:10 - INFO - __main__ - Step 48961: {'lr': 0.0003857441015115154, 'samples': 9400512, 'steps': 48960, 'loss/train': 1.5628035068511963} 08/30/2021 22:05:10 - INFO - __main__ - Step 48962: {'lr': 0.00038573964515323754, 'samples': 9400704, 'steps': 48961, 'loss/train': 1.8988583087921143} 08/30/2021 22:05:12 - INFO - __main__ - Step 48963: {'lr': 0.0003857351887337974, 'samples': 9400896, 'steps': 48962, 'loss/train': 1.569704532623291} 08/30/2021 22:05:13 - INFO - __main__ - Step 48964: {'lr': 0.00038573073225319724, 'samples': 9401088, 'steps': 48963, 'loss/train': 1.144771695137024} 08/30/2021 22:05:13 - INFO - __main__ - Step 48965: {'lr': 0.00038572627571143873, 'samples': 9401280, 'steps': 48964, 'loss/train': 1.7368896007537842} 08/30/2021 22:05:13 - INFO - __main__ - Step 48966: {'lr': 0.0003857218191085242, 'samples': 9401472, 'steps': 48965, 'loss/train': 1.4399389028549194} 08/30/2021 22:05:14 - INFO - __main__ - Step 48967: {'lr': 0.0003857173624444554, 'samples': 9401664, 'steps': 48966, 'loss/train': 0.6976837515830994} 08/30/2021 22:05:15 - INFO - __main__ - Step 48968: {'lr': 0.00038571290571923455, 'samples': 9401856, 'steps': 48967, 'loss/train': 0.8567972183227539} 08/30/2021 22:05:16 - INFO - __main__ - Step 48969: {'lr': 0.0003857084489328635, 'samples': 9402048, 'steps': 48968, 'loss/train': 1.2729710340499878} 08/30/2021 22:05:16 - INFO - __main__ - Step 48970: {'lr': 0.00038570399208534437, 'samples': 9402240, 'steps': 48969, 'loss/train': 1.094132900238037} 08/30/2021 22:05:17 - INFO - __main__ - Step 48971: {'lr': 0.000385699535176679, 'samples': 9402432, 'steps': 48970, 'loss/train': 1.727378487586975} 08/30/2021 22:05:17 - INFO - __main__ - Step 48972: {'lr': 0.00038569507820686956, 'samples': 9402624, 'steps': 48971, 'loss/train': 0.02724265865981579} 08/30/2021 22:05:17 - INFO - __main__ - Step 48973: {'lr': 0.000385690621175918, 'samples': 9402816, 'steps': 48972, 'loss/train': 1.346278429031372} 08/30/2021 22:05:19 - INFO - __main__ - Step 48974: {'lr': 0.0003856861640838265, 'samples': 9403008, 'steps': 48973, 'loss/train': 0.9433966279029846} 08/30/2021 22:05:20 - INFO - __main__ - Step 48975: {'lr': 0.00038568170693059677, 'samples': 9403200, 'steps': 48974, 'loss/train': 1.6088309288024902} 08/30/2021 22:05:20 - INFO - __main__ - Step 48976: {'lr': 0.000385677249716231, 'samples': 9403392, 'steps': 48975, 'loss/train': 1.4307420253753662} 08/30/2021 22:05:20 - INFO - __main__ - Step 48977: {'lr': 0.0003856727924407311, 'samples': 9403584, 'steps': 48976, 'loss/train': 1.0638583898544312} 08/30/2021 22:05:21 - INFO - __main__ - Step 48978: {'lr': 0.0003856683351040992, 'samples': 9403776, 'steps': 48977, 'loss/train': 0.4514577090740204} 08/30/2021 22:05:21 - INFO - __main__ - Step 48979: {'lr': 0.00038566387770633715, 'samples': 9403968, 'steps': 48978, 'loss/train': 0.28638121485710144} 08/30/2021 22:05:23 - INFO - __main__ - Step 48980: {'lr': 0.00038565942024744703, 'samples': 9404160, 'steps': 48979, 'loss/train': 1.5438251495361328} 08/30/2021 22:05:23 - INFO - __main__ - Step 48981: {'lr': 0.000385654962727431, 'samples': 9404352, 'steps': 48980, 'loss/train': 1.0712181329727173} 08/30/2021 22:05:23 - INFO - __main__ - Step 48982: {'lr': 0.00038565050514629087, 'samples': 9404544, 'steps': 48981, 'loss/train': 1.0263208150863647} 08/30/2021 22:05:24 - INFO - __main__ - Step 48983: {'lr': 0.0003856460475040288, 'samples': 9404736, 'steps': 48982, 'loss/train': 1.5323868989944458} 08/30/2021 22:05:24 - INFO - __main__ - Step 48984: {'lr': 0.00038564158980064657, 'samples': 9404928, 'steps': 48983, 'loss/train': 1.7161959409713745} 08/30/2021 22:05:26 - INFO - __main__ - Step 48985: {'lr': 0.0003856371320361464, 'samples': 9405120, 'steps': 48984, 'loss/train': 1.8002005815505981} 08/30/2021 22:05:27 - INFO - __main__ - Step 48986: {'lr': 0.00038563267421053024, 'samples': 9405312, 'steps': 48985, 'loss/train': 1.0854445695877075} 08/30/2021 22:05:27 - INFO - __main__ - Step 48987: {'lr': 0.0003856282163238001, 'samples': 9405504, 'steps': 48986, 'loss/train': 1.325804591178894} 08/30/2021 22:05:27 - INFO - __main__ - Step 48988: {'lr': 0.000385623758375958, 'samples': 9405696, 'steps': 48987, 'loss/train': 1.0465092658996582} 08/30/2021 22:05:28 - INFO - __main__ - Step 48989: {'lr': 0.0003856193003670058, 'samples': 9405888, 'steps': 48988, 'loss/train': 0.7524456977844238} 08/30/2021 22:05:29 - INFO - __main__ - Step 48990: {'lr': 0.0003856148422969458, 'samples': 9406080, 'steps': 48989, 'loss/train': 1.0065088272094727} 08/30/2021 22:05:30 - INFO - __main__ - Step 48991: {'lr': 0.0003856103841657797, 'samples': 9406272, 'steps': 48990, 'loss/train': 1.1180819272994995} 08/30/2021 22:05:30 - INFO - __main__ - Step 48992: {'lr': 0.00038560592597350975, 'samples': 9406464, 'steps': 48991, 'loss/train': 0.7776837348937988} 08/30/2021 22:05:30 - INFO - __main__ - Step 48993: {'lr': 0.0003856014677201378, 'samples': 9406656, 'steps': 48992, 'loss/train': 1.5926661491394043} 08/30/2021 22:05:31 - INFO - __main__ - Step 48994: {'lr': 0.000385597009405666, 'samples': 9406848, 'steps': 48993, 'loss/train': 1.502701997756958} 08/30/2021 22:05:32 - INFO - __main__ - Step 48995: {'lr': 0.0003855925510300962, 'samples': 9407040, 'steps': 48994, 'loss/train': 0.35187649726867676} 08/30/2021 22:05:33 - INFO - __main__ - Step 48996: {'lr': 0.0003855880925934305, 'samples': 9407232, 'steps': 48995, 'loss/train': 1.3718417882919312} 08/30/2021 22:05:33 - INFO - __main__ - Step 48997: {'lr': 0.000385583634095671, 'samples': 9407424, 'steps': 48996, 'loss/train': 1.366726279258728} 08/30/2021 22:05:34 - INFO - __main__ - Step 48998: {'lr': 0.00038557917553681944, 'samples': 9407616, 'steps': 48997, 'loss/train': 1.1551061868667603} 08/30/2021 22:05:34 - INFO - __main__ - Step 48999: {'lr': 0.00038557471691687804, 'samples': 9407808, 'steps': 48998, 'loss/train': 0.06604742258787155} 08/30/2021 22:05:34 - INFO - __main__ - Step 49000: {'lr': 0.0003855702582358489, 'samples': 9408000, 'steps': 48999, 'loss/train': 0.05074768513441086} 08/30/2021 22:05:36 - INFO - __main__ - Step 49001: {'lr': 0.00038556579949373384, 'samples': 9408192, 'steps': 49000, 'loss/train': 1.6001778841018677} 08/30/2021 22:05:36 - INFO - __main__ - Step 49002: {'lr': 0.00038556134069053484, 'samples': 9408384, 'steps': 49001, 'loss/train': 0.16883888840675354} 08/30/2021 22:05:37 - INFO - __main__ - Step 49003: {'lr': 0.00038555688182625406, 'samples': 9408576, 'steps': 49002, 'loss/train': 1.1565419435501099} 08/30/2021 22:05:37 - INFO - __main__ - Step 49004: {'lr': 0.0003855524229008934, 'samples': 9408768, 'steps': 49003, 'loss/train': 0.05974424630403519} 08/30/2021 22:05:37 - INFO - __main__ - Step 49005: {'lr': 0.0003855479639144549, 'samples': 9408960, 'steps': 49004, 'loss/train': 0.8605421781539917} 08/30/2021 22:05:39 - INFO - __main__ - Step 49006: {'lr': 0.0003855435048669406, 'samples': 9409152, 'steps': 49005, 'loss/train': 1.5286893844604492} 08/30/2021 22:05:40 - INFO - __main__ - Step 49007: {'lr': 0.0003855390457583525, 'samples': 9409344, 'steps': 49006, 'loss/train': 1.5339139699935913} 08/30/2021 22:05:40 - INFO - __main__ - Step 49008: {'lr': 0.0003855345865886926, 'samples': 9409536, 'steps': 49007, 'loss/train': 1.1174426078796387} 08/30/2021 22:05:40 - INFO - __main__ - Step 49009: {'lr': 0.0003855301273579629, 'samples': 9409728, 'steps': 49008, 'loss/train': 1.479286789894104} 08/30/2021 22:05:41 - INFO - __main__ - Step 49010: {'lr': 0.0003855256680661654, 'samples': 9409920, 'steps': 49009, 'loss/train': 1.000381350517273} 08/30/2021 22:05:42 - INFO - __main__ - Step 49011: {'lr': 0.00038552120871330217, 'samples': 9410112, 'steps': 49010, 'loss/train': 0.09208838641643524} 08/30/2021 22:05:43 - INFO - __main__ - Step 49012: {'lr': 0.0003855167492993751, 'samples': 9410304, 'steps': 49011, 'loss/train': 2.397510528564453} 08/30/2021 22:05:43 - INFO - __main__ - Step 49013: {'lr': 0.00038551228982438635, 'samples': 9410496, 'steps': 49012, 'loss/train': 1.698974847793579} 08/30/2021 22:05:43 - INFO - __main__ - Step 49014: {'lr': 0.00038550783028833786, 'samples': 9410688, 'steps': 49013, 'loss/train': 1.7288204431533813} 08/30/2021 22:05:44 - INFO - __main__ - Step 49015: {'lr': 0.00038550337069123155, 'samples': 9410880, 'steps': 49014, 'loss/train': 1.5784059762954712} 08/30/2021 22:05:45 - INFO - __main__ - Step 49016: {'lr': 0.00038549891103306953, 'samples': 9411072, 'steps': 49015, 'loss/train': 0.041614703834056854} 08/30/2021 22:05:46 - INFO - __main__ - Step 49017: {'lr': 0.00038549445131385386, 'samples': 9411264, 'steps': 49016, 'loss/train': 1.5330461263656616} 08/30/2021 22:05:46 - INFO - __main__ - Step 49018: {'lr': 0.00038548999153358645, 'samples': 9411456, 'steps': 49017, 'loss/train': 1.3942714929580688} 08/30/2021 22:05:46 - INFO - __main__ - Step 49019: {'lr': 0.0003854855316922693, 'samples': 9411648, 'steps': 49018, 'loss/train': 0.940632700920105} 08/30/2021 22:05:47 - INFO - __main__ - Step 49020: {'lr': 0.0003854810717899045, 'samples': 9411840, 'steps': 49019, 'loss/train': 1.4342384338378906} 08/30/2021 22:05:47 - INFO - __main__ - Step 49021: {'lr': 0.0003854766118264941, 'samples': 9412032, 'steps': 49020, 'loss/train': 1.3366179466247559} 08/30/2021 22:05:49 - INFO - __main__ - Step 49022: {'lr': 0.0003854721518020399, 'samples': 9412224, 'steps': 49021, 'loss/train': 1.6159183979034424} 08/30/2021 22:05:49 - INFO - __main__ - Step 49023: {'lr': 0.00038546769171654403, 'samples': 9412416, 'steps': 49022, 'loss/train': 1.5129677057266235} 08/30/2021 22:05:49 - INFO - __main__ - Step 49024: {'lr': 0.00038546323157000856, 'samples': 9412608, 'steps': 49023, 'loss/train': 0.7947247624397278} 08/30/2021 22:05:50 - INFO - __main__ - Step 49025: {'lr': 0.00038545877136243544, 'samples': 9412800, 'steps': 49024, 'loss/train': 2.404702663421631} 08/30/2021 22:05:50 - INFO - __main__ - Step 49026: {'lr': 0.00038545431109382667, 'samples': 9412992, 'steps': 49025, 'loss/train': 1.0186800956726074} 08/30/2021 22:05:52 - INFO - __main__ - Step 49027: {'lr': 0.0003854498507641843, 'samples': 9413184, 'steps': 49026, 'loss/train': 1.428654670715332} 08/30/2021 22:05:52 - INFO - __main__ - Step 49028: {'lr': 0.00038544539037351037, 'samples': 9413376, 'steps': 49027, 'loss/train': 1.2143417596817017} 08/30/2021 22:05:52 - INFO - __main__ - Step 49029: {'lr': 0.0003854409299218068, 'samples': 9413568, 'steps': 49028, 'loss/train': 1.7249650955200195} 08/30/2021 22:05:53 - INFO - __main__ - Step 49030: {'lr': 0.00038543646940907564, 'samples': 9413760, 'steps': 49029, 'loss/train': 5.788559913635254} 08/30/2021 22:05:53 - INFO - __main__ - Step 49031: {'lr': 0.0003854320088353188, 'samples': 9413952, 'steps': 49030, 'loss/train': 2.2537002563476562} 08/30/2021 22:05:55 - INFO - __main__ - Step 49032: {'lr': 0.0003854275482005385, 'samples': 9414144, 'steps': 49031, 'loss/train': 1.6331944465637207} 08/30/2021 22:05:55 - INFO - __main__ - Step 49033: {'lr': 0.0003854230875047366, 'samples': 9414336, 'steps': 49032, 'loss/train': 1.2995882034301758} 08/30/2021 22:05:56 - INFO - __main__ - Step 49034: {'lr': 0.0003854186267479151, 'samples': 9414528, 'steps': 49033, 'loss/train': 1.2372866868972778} 08/30/2021 22:05:56 - INFO - __main__ - Step 49035: {'lr': 0.00038541416593007615, 'samples': 9414720, 'steps': 49034, 'loss/train': 0.025636833161115646} 08/30/2021 22:05:56 - INFO - __main__ - Step 49036: {'lr': 0.00038540970505122164, 'samples': 9414912, 'steps': 49035, 'loss/train': 1.113980770111084} 08/30/2021 22:05:57 - INFO - __main__ - Step 49037: {'lr': 0.0003854052441113536, 'samples': 9415104, 'steps': 49036, 'loss/train': 0.12852731347084045} 08/30/2021 22:05:59 - INFO - __main__ - Step 49038: {'lr': 0.00038540078311047397, 'samples': 9415296, 'steps': 49037, 'loss/train': 1.3197351694107056} 08/30/2021 22:06:00 - INFO - __main__ - Step 49039: {'lr': 0.0003853963220485849, 'samples': 9415488, 'steps': 49038, 'loss/train': 1.1949341297149658} 08/30/2021 22:06:00 - INFO - __main__ - Step 49040: {'lr': 0.00038539186092568833, 'samples': 9415680, 'steps': 49039, 'loss/train': 2.6087334156036377} 08/30/2021 22:06:00 - INFO - __main__ - Step 49041: {'lr': 0.00038538739974178633, 'samples': 9415872, 'steps': 49040, 'loss/train': 1.5769902467727661} 08/30/2021 22:06:01 - INFO - __main__ - Step 49042: {'lr': 0.00038538293849688077, 'samples': 9416064, 'steps': 49041, 'loss/train': 1.2928646802902222} 08/30/2021 22:06:01 - INFO - __main__ - Step 49043: {'lr': 0.0003853784771909739, 'samples': 9416256, 'steps': 49042, 'loss/train': 0.06994496285915375} 08/30/2021 22:06:02 - INFO - __main__ - Step 49044: {'lr': 0.0003853740158240674, 'samples': 9416448, 'steps': 49043, 'loss/train': 1.356127142906189} 08/30/2021 22:06:03 - INFO - __main__ - Step 49045: {'lr': 0.0003853695543961635, 'samples': 9416640, 'steps': 49044, 'loss/train': 1.8946690559387207} 08/30/2021 22:06:03 - INFO - __main__ - Step 49046: {'lr': 0.00038536509290726417, 'samples': 9416832, 'steps': 49045, 'loss/train': 1.2499479055404663} 08/30/2021 22:06:04 - INFO - __main__ - Step 49047: {'lr': 0.00038536063135737145, 'samples': 9417024, 'steps': 49046, 'loss/train': 0.9454519748687744} 08/30/2021 22:06:04 - INFO - __main__ - Step 49048: {'lr': 0.0003853561697464874, 'samples': 9417216, 'steps': 49047, 'loss/train': 1.106493353843689} 08/30/2021 22:06:06 - INFO - __main__ - Step 49049: {'lr': 0.0003853517080746138, 'samples': 9417408, 'steps': 49048, 'loss/train': 1.9031293392181396} 08/30/2021 22:06:06 - INFO - __main__ - Step 49050: {'lr': 0.00038534724634175285, 'samples': 9417600, 'steps': 49049, 'loss/train': 1.9974815845489502} 08/30/2021 22:06:06 - INFO - __main__ - Step 49051: {'lr': 0.0003853427845479065, 'samples': 9417792, 'steps': 49050, 'loss/train': 1.4240002632141113} 08/30/2021 22:06:07 - INFO - __main__ - Step 49052: {'lr': 0.0003853383226930768, 'samples': 9417984, 'steps': 49051, 'loss/train': 1.643623948097229} 08/30/2021 22:06:07 - INFO - __main__ - Step 49053: {'lr': 0.00038533386077726573, 'samples': 9418176, 'steps': 49052, 'loss/train': 1.0840246677398682} 08/30/2021 22:06:09 - INFO - __main__ - Step 49054: {'lr': 0.00038532939880047535, 'samples': 9418368, 'steps': 49053, 'loss/train': 1.6964430809020996} 08/30/2021 22:06:09 - INFO - __main__ - Step 49055: {'lr': 0.00038532493676270765, 'samples': 9418560, 'steps': 49054, 'loss/train': 1.2003834247589111} 08/30/2021 22:06:10 - INFO - __main__ - Step 49056: {'lr': 0.0003853204746639646, 'samples': 9418752, 'steps': 49055, 'loss/train': 1.6735671758651733} 08/30/2021 22:06:10 - INFO - __main__ - Step 49057: {'lr': 0.0003853160125042482, 'samples': 9418944, 'steps': 49056, 'loss/train': 0.05597090348601341} 08/30/2021 22:06:10 - INFO - __main__ - Step 49058: {'lr': 0.00038531155028356047, 'samples': 9419136, 'steps': 49057, 'loss/train': 0.05793747678399086} 08/30/2021 22:06:12 - INFO - __main__ - Step 49059: {'lr': 0.0003853070880019035, 'samples': 9419328, 'steps': 49058, 'loss/train': 1.2153240442276} 08/30/2021 22:06:13 - INFO - __main__ - Step 49060: {'lr': 0.0003853026256592792, 'samples': 9419520, 'steps': 49059, 'loss/train': 1.1163966655731201} 08/30/2021 22:06:13 - INFO - __main__ - Step 49061: {'lr': 0.0003852981632556897, 'samples': 9419712, 'steps': 49060, 'loss/train': 1.5554616451263428} 08/30/2021 22:06:13 - INFO - __main__ - Step 49062: {'lr': 0.0003852937007911369, 'samples': 9419904, 'steps': 49061, 'loss/train': 1.268764853477478} 08/30/2021 22:06:14 - INFO - __main__ - Step 49063: {'lr': 0.00038528923826562287, 'samples': 9420096, 'steps': 49062, 'loss/train': 0.5437546968460083} 08/30/2021 22:06:15 - INFO - __main__ - Step 49064: {'lr': 0.00038528477567914955, 'samples': 9420288, 'steps': 49063, 'loss/train': 0.05685457959771156} 08/30/2021 22:06:16 - INFO - __main__ - Step 49065: {'lr': 0.000385280313031719, 'samples': 9420480, 'steps': 49064, 'loss/train': 1.2891452312469482} 08/30/2021 22:06:16 - INFO - __main__ - Step 49066: {'lr': 0.00038527585032333326, 'samples': 9420672, 'steps': 49065, 'loss/train': 1.0293633937835693} 08/30/2021 22:06:16 - INFO - __main__ - Step 49067: {'lr': 0.00038527138755399423, 'samples': 9420864, 'steps': 49066, 'loss/train': 1.389180064201355} 08/30/2021 22:06:17 - INFO - __main__ - Step 49068: {'lr': 0.00038526692472370407, 'samples': 9421056, 'steps': 49067, 'loss/train': 1.0328811407089233} 08/30/2021 22:06:19 - INFO - __main__ - Step 49069: {'lr': 0.0003852624618324647, 'samples': 9421248, 'steps': 49068, 'loss/train': 1.6344799995422363} 08/30/2021 22:06:19 - INFO - __main__ - Step 49070: {'lr': 0.0003852579988802782, 'samples': 9421440, 'steps': 49069, 'loss/train': 1.729058027267456} 08/30/2021 22:06:20 - INFO - __main__ - Step 49071: {'lr': 0.00038525353586714645, 'samples': 9421632, 'steps': 49070, 'loss/train': 0.9593988060951233} 08/30/2021 22:06:20 - INFO - __main__ - Step 49072: {'lr': 0.0003852490727930716, 'samples': 9421824, 'steps': 49071, 'loss/train': 1.533362865447998} 08/30/2021 22:06:20 - INFO - __main__ - Step 49073: {'lr': 0.00038524460965805557, 'samples': 9422016, 'steps': 49072, 'loss/train': 1.2628542184829712} 08/30/2021 22:06:21 - INFO - __main__ - Step 49074: {'lr': 0.00038524014646210044, 'samples': 9422208, 'steps': 49073, 'loss/train': 1.5083762407302856} 08/30/2021 22:06:22 - INFO - __main__ - Step 49075: {'lr': 0.00038523568320520817, 'samples': 9422400, 'steps': 49074, 'loss/train': 0.08774276822805405} 08/30/2021 22:06:23 - INFO - __main__ - Step 49076: {'lr': 0.0003852312198873808, 'samples': 9422592, 'steps': 49075, 'loss/train': 1.3700473308563232} 08/30/2021 22:06:23 - INFO - __main__ - Step 49077: {'lr': 0.0003852267565086203, 'samples': 9422784, 'steps': 49076, 'loss/train': 1.1281664371490479} 08/30/2021 22:06:23 - INFO - __main__ - Step 49078: {'lr': 0.0003852222930689288, 'samples': 9422976, 'steps': 49077, 'loss/train': 1.6004756689071655} 08/30/2021 22:06:24 - INFO - __main__ - Step 49079: {'lr': 0.00038521782956830807, 'samples': 9423168, 'steps': 49078, 'loss/train': 1.5095425844192505} 08/30/2021 22:06:25 - INFO - __main__ - Step 49080: {'lr': 0.00038521336600676035, 'samples': 9423360, 'steps': 49079, 'loss/train': 1.3744326829910278} 08/30/2021 22:06:26 - INFO - __main__ - Step 49081: {'lr': 0.00038520890238428763, 'samples': 9423552, 'steps': 49080, 'loss/train': 1.2326339483261108} 08/30/2021 22:06:26 - INFO - __main__ - Step 49082: {'lr': 0.00038520443870089185, 'samples': 9423744, 'steps': 49081, 'loss/train': 1.3077542781829834} 08/30/2021 22:06:26 - INFO - __main__ - Step 49083: {'lr': 0.00038519997495657497, 'samples': 9423936, 'steps': 49082, 'loss/train': 0.3408316373825073} 08/30/2021 22:06:27 - INFO - __main__ - Step 49084: {'lr': 0.0003851955111513391, 'samples': 9424128, 'steps': 49083, 'loss/train': 1.054155707359314} 08/30/2021 22:06:28 - INFO - __main__ - Step 49085: {'lr': 0.0003851910472851862, 'samples': 9424320, 'steps': 49084, 'loss/train': 2.1540746688842773} 08/30/2021 22:06:29 - INFO - __main__ - Step 49086: {'lr': 0.0003851865833581183, 'samples': 9424512, 'steps': 49085, 'loss/train': 1.5708335638046265} 08/30/2021 22:06:29 - INFO - __main__ - Step 49087: {'lr': 0.0003851821193701375, 'samples': 9424704, 'steps': 49086, 'loss/train': 0.4879619777202606} 08/30/2021 22:06:30 - INFO - __main__ - Step 49088: {'lr': 0.0003851776553212456, 'samples': 9424896, 'steps': 49087, 'loss/train': 1.294213056564331} 08/30/2021 22:06:30 - INFO - __main__ - Step 49089: {'lr': 0.0003851731912114448, 'samples': 9425088, 'steps': 49088, 'loss/train': 1.686768651008606} 08/30/2021 22:06:30 - INFO - __main__ - Step 49090: {'lr': 0.00038516872704073704, 'samples': 9425280, 'steps': 49089, 'loss/train': 0.8860755562782288} 08/30/2021 22:06:32 - INFO - __main__ - Step 49091: {'lr': 0.0003851642628091243, 'samples': 9425472, 'steps': 49090, 'loss/train': 1.1916581392288208} 08/30/2021 22:06:32 - INFO - __main__ - Step 49092: {'lr': 0.0003851597985166087, 'samples': 9425664, 'steps': 49091, 'loss/train': 2.623727560043335} 08/30/2021 22:06:33 - INFO - __main__ - Step 49093: {'lr': 0.0003851553341631921, 'samples': 9425856, 'steps': 49092, 'loss/train': 1.8974367380142212} 08/30/2021 22:06:33 - INFO - __main__ - Step 49094: {'lr': 0.0003851508697488766, 'samples': 9426048, 'steps': 49093, 'loss/train': 1.468618631362915} 08/30/2021 22:06:33 - INFO - __main__ - Step 49095: {'lr': 0.0003851464052736643, 'samples': 9426240, 'steps': 49094, 'loss/train': 1.7923316955566406} 08/30/2021 22:06:35 - INFO - __main__ - Step 49096: {'lr': 0.00038514194073755706, 'samples': 9426432, 'steps': 49095, 'loss/train': 1.4214571714401245} 08/30/2021 22:06:36 - INFO - __main__ - Step 49097: {'lr': 0.00038513747614055696, 'samples': 9426624, 'steps': 49096, 'loss/train': 1.5716248750686646} 08/30/2021 22:06:36 - INFO - __main__ - Step 49098: {'lr': 0.0003851330114826659, 'samples': 9426816, 'steps': 49097, 'loss/train': 0.25750911235809326} 08/30/2021 22:06:37 - INFO - __main__ - Step 49099: {'lr': 0.0003851285467638861, 'samples': 9427008, 'steps': 49098, 'loss/train': 0.38401684165000916} 08/30/2021 22:06:37 - INFO - __main__ - Step 49100: {'lr': 0.00038512408198421936, 'samples': 9427200, 'steps': 49099, 'loss/train': 1.4481605291366577} 08/30/2021 22:06:39 - INFO - __main__ - Step 49101: {'lr': 0.0003851196171436679, 'samples': 9427392, 'steps': 49100, 'loss/train': 1.4853707551956177} 08/30/2021 22:06:39 - INFO - __main__ - Step 49102: {'lr': 0.0003851151522422336, 'samples': 9427584, 'steps': 49101, 'loss/train': 0.8223899006843567} 08/30/2021 22:06:40 - INFO - __main__ - Step 49103: {'lr': 0.0003851106872799185, 'samples': 9427776, 'steps': 49102, 'loss/train': 1.9657347202301025} 08/30/2021 22:06:40 - INFO - __main__ - Step 49104: {'lr': 0.00038510622225672455, 'samples': 9427968, 'steps': 49103, 'loss/train': 1.4518288373947144} 08/30/2021 22:06:40 - INFO - __main__ - Step 49105: {'lr': 0.0003851017571726539, 'samples': 9428160, 'steps': 49104, 'loss/train': 1.3620963096618652} 08/30/2021 22:06:41 - INFO - __main__ - Step 49106: {'lr': 0.00038509729202770843, 'samples': 9428352, 'steps': 49105, 'loss/train': 0.09259865432977676} 08/30/2021 22:06:42 - INFO - __main__ - Step 49107: {'lr': 0.00038509282682189016, 'samples': 9428544, 'steps': 49106, 'loss/train': 1.55458664894104} 08/30/2021 22:06:43 - INFO - __main__ - Step 49108: {'lr': 0.0003850883615552012, 'samples': 9428736, 'steps': 49107, 'loss/train': 1.168648362159729} 08/30/2021 22:06:43 - INFO - __main__ - Step 49109: {'lr': 0.0003850838962276436, 'samples': 9428928, 'steps': 49108, 'loss/train': 0.04796629026532173} 08/30/2021 22:06:44 - INFO - __main__ - Step 49110: {'lr': 0.0003850794308392192, 'samples': 9429120, 'steps': 49109, 'loss/train': 1.4770183563232422} 08/30/2021 22:06:44 - INFO - __main__ - Step 49111: {'lr': 0.00038507496538993006, 'samples': 9429312, 'steps': 49110, 'loss/train': 1.256965160369873} 08/30/2021 22:06:46 - INFO - __main__ - Step 49112: {'lr': 0.00038507049987977825, 'samples': 9429504, 'steps': 49111, 'loss/train': 0.637797474861145} 08/30/2021 22:06:46 - INFO - __main__ - Step 49113: {'lr': 0.0003850660343087657, 'samples': 9429696, 'steps': 49112, 'loss/train': 0.7961546182632446} 08/30/2021 22:06:47 - INFO - __main__ - Step 49114: {'lr': 0.0003850615686768946, 'samples': 9429888, 'steps': 49113, 'loss/train': 1.6420841217041016} 08/30/2021 22:06:47 - INFO - __main__ - Step 49115: {'lr': 0.00038505710298416683, 'samples': 9430080, 'steps': 49114, 'loss/train': 1.5022225379943848} 08/30/2021 22:06:48 - INFO - __main__ - Step 49116: {'lr': 0.00038505263723058437, 'samples': 9430272, 'steps': 49115, 'loss/train': 0.7905400991439819} 08/30/2021 22:06:48 - INFO - __main__ - Step 49117: {'lr': 0.0003850481714161492, 'samples': 9430464, 'steps': 49116, 'loss/train': 0.06218510866165161} 08/30/2021 22:06:49 - INFO - __main__ - Step 49118: {'lr': 0.00038504370554086353, 'samples': 9430656, 'steps': 49117, 'loss/train': 0.02573992684483528} 08/30/2021 22:06:50 - INFO - __main__ - Step 49119: {'lr': 0.0003850392396047292, 'samples': 9430848, 'steps': 49118, 'loss/train': 1.3654017448425293} 08/30/2021 22:06:50 - INFO - __main__ - Step 49120: {'lr': 0.0003850347736077483, 'samples': 9431040, 'steps': 49119, 'loss/train': 1.1493711471557617} 08/30/2021 22:06:50 - INFO - __main__ - Step 49121: {'lr': 0.0003850303075499227, 'samples': 9431232, 'steps': 49120, 'loss/train': 0.9882366061210632} 08/30/2021 22:06:51 - INFO - __main__ - Step 49122: {'lr': 0.0003850258414312547, 'samples': 9431424, 'steps': 49121, 'loss/train': 1.4244186878204346} 08/30/2021 22:06:52 - INFO - __main__ - Step 49123: {'lr': 0.000385021375251746, 'samples': 9431616, 'steps': 49122, 'loss/train': 1.4393975734710693} 08/30/2021 22:06:53 - INFO - __main__ - Step 49124: {'lr': 0.00038501690901139883, 'samples': 9431808, 'steps': 49123, 'loss/train': 1.1934809684753418} 08/30/2021 22:06:53 - INFO - __main__ - Step 49125: {'lr': 0.0003850124427102151, 'samples': 9432000, 'steps': 49124, 'loss/train': 1.727146029472351} 08/30/2021 22:06:53 - INFO - __main__ - Step 49126: {'lr': 0.0003850079763481968, 'samples': 9432192, 'steps': 49125, 'loss/train': 1.2128039598464966} 08/30/2021 22:06:54 - INFO - __main__ - Step 49127: {'lr': 0.0003850035099253461, 'samples': 9432384, 'steps': 49126, 'loss/train': 0.6615647077560425} 08/30/2021 22:06:55 - INFO - __main__ - Step 49128: {'lr': 0.00038499904344166483, 'samples': 9432576, 'steps': 49127, 'loss/train': 1.3362478017807007} 08/30/2021 22:06:56 - INFO - __main__ - Step 49129: {'lr': 0.0003849945768971551, 'samples': 9432768, 'steps': 49128, 'loss/train': 1.3057968616485596} 08/30/2021 22:06:56 - INFO - __main__ - Step 49130: {'lr': 0.0003849901102918189, 'samples': 9432960, 'steps': 49129, 'loss/train': 0.24954719841480255} 08/30/2021 22:06:56 - INFO - __main__ - Step 49131: {'lr': 0.00038498564362565826, 'samples': 9433152, 'steps': 49130, 'loss/train': 1.4137929677963257} 08/30/2021 22:06:57 - INFO - __main__ - Step 49132: {'lr': 0.0003849811768986751, 'samples': 9433344, 'steps': 49131, 'loss/train': 1.699936032295227} 08/30/2021 22:06:58 - INFO - __main__ - Step 49133: {'lr': 0.0003849767101108715, 'samples': 9433536, 'steps': 49132, 'loss/train': 1.5967504978179932} 08/30/2021 22:06:59 - INFO - __main__ - Step 49134: {'lr': 0.0003849722432622495, 'samples': 9433728, 'steps': 49133, 'loss/train': 1.2202248573303223} 08/30/2021 22:06:59 - INFO - __main__ - Step 49135: {'lr': 0.0003849677763528111, 'samples': 9433920, 'steps': 49134, 'loss/train': 0.2459113597869873} 08/30/2021 22:06:59 - INFO - __main__ - Step 49136: {'lr': 0.0003849633093825583, 'samples': 9434112, 'steps': 49135, 'loss/train': 0.7782366275787354} 08/30/2021 22:07:00 - INFO - __main__ - Step 49137: {'lr': 0.00038495884235149316, 'samples': 9434304, 'steps': 49136, 'loss/train': 1.1433498859405518} 08/30/2021 22:07:01 - INFO - __main__ - Step 49138: {'lr': 0.0003849543752596176, 'samples': 9434496, 'steps': 49137, 'loss/train': 1.048794150352478} 08/30/2021 22:07:02 - INFO - __main__ - Step 49139: {'lr': 0.00038494990810693366, 'samples': 9434688, 'steps': 49138, 'loss/train': 0.6492387652397156} 08/30/2021 22:07:02 - INFO - __main__ - Step 49140: {'lr': 0.0003849454408934434, 'samples': 9434880, 'steps': 49139, 'loss/train': 0.8339297771453857} 08/30/2021 22:07:03 - INFO - __main__ - Step 49141: {'lr': 0.0003849409736191488, 'samples': 9435072, 'steps': 49140, 'loss/train': 0.9653542041778564} 08/30/2021 22:07:03 - INFO - __main__ - Step 49142: {'lr': 0.00038493650628405196, 'samples': 9435264, 'steps': 49141, 'loss/train': 1.070016622543335} 08/30/2021 22:07:03 - INFO - __main__ - Step 49143: {'lr': 0.0003849320388881547, 'samples': 9435456, 'steps': 49142, 'loss/train': 1.752500295639038} 08/30/2021 22:07:05 - INFO - __main__ - Step 49144: {'lr': 0.0003849275714314592, 'samples': 9435648, 'steps': 49143, 'loss/train': 1.339125394821167} 08/30/2021 22:07:05 - INFO - __main__ - Step 49145: {'lr': 0.0003849231039139674, 'samples': 9435840, 'steps': 49144, 'loss/train': 1.0353636741638184} 08/30/2021 22:07:06 - INFO - __main__ - Step 49146: {'lr': 0.00038491863633568135, 'samples': 9436032, 'steps': 49145, 'loss/train': 1.3980462551116943} 08/30/2021 22:07:06 - INFO - __main__ - Step 49147: {'lr': 0.000384914168696603, 'samples': 9436224, 'steps': 49146, 'loss/train': 1.4324872493743896} 08/30/2021 22:07:06 - INFO - __main__ - Step 49148: {'lr': 0.0003849097009967344, 'samples': 9436416, 'steps': 49147, 'loss/train': 1.2474780082702637} 08/30/2021 22:07:08 - INFO - __main__ - Step 49149: {'lr': 0.0003849052332360777, 'samples': 9436608, 'steps': 49148, 'loss/train': 1.3348233699798584} 08/30/2021 22:07:09 - INFO - __main__ - Step 49150: {'lr': 0.0003849007654146347, 'samples': 9436800, 'steps': 49149, 'loss/train': 1.6907507181167603} 08/30/2021 22:07:09 - INFO - __main__ - Step 49151: {'lr': 0.0003848962975324074, 'samples': 9436992, 'steps': 49150, 'loss/train': 1.3018909692764282} 08/30/2021 22:07:09 - INFO - __main__ - Step 49152: {'lr': 0.00038489182958939804, 'samples': 9437184, 'steps': 49151, 'loss/train': 1.5151299238204956} 08/30/2021 22:07:10 - INFO - __main__ - Step 49153: {'lr': 0.00038488736158560845, 'samples': 9437376, 'steps': 49152, 'loss/train': 1.7668776512145996} 08/30/2021 22:07:10 - INFO - __main__ - Step 49154: {'lr': 0.00038488289352104065, 'samples': 9437568, 'steps': 49153, 'loss/train': 0.10143160820007324} 08/30/2021 22:07:12 - INFO - __main__ - Step 49155: {'lr': 0.0003848784253956968, 'samples': 9437760, 'steps': 49154, 'loss/train': 1.9443635940551758} 08/30/2021 22:07:13 - INFO - __main__ - Step 49156: {'lr': 0.00038487395720957884, 'samples': 9437952, 'steps': 49155, 'loss/train': 1.2713654041290283} 08/30/2021 22:07:13 - INFO - __main__ - Step 49157: {'lr': 0.0003848694889626886, 'samples': 9438144, 'steps': 49156, 'loss/train': 1.399463176727295} 08/30/2021 22:07:13 - INFO - __main__ - Step 49158: {'lr': 0.0003848650206550284, 'samples': 9438336, 'steps': 49157, 'loss/train': 1.6623822450637817} 08/30/2021 22:07:14 - INFO - __main__ - Step 49159: {'lr': 0.0003848605522866, 'samples': 9438528, 'steps': 49158, 'loss/train': 0.09078831970691681} 08/30/2021 22:07:15 - INFO - __main__ - Step 49160: {'lr': 0.00038485608385740555, 'samples': 9438720, 'steps': 49159, 'loss/train': 1.3066836595535278} 08/30/2021 22:07:16 - INFO - __main__ - Step 49161: {'lr': 0.00038485161536744707, 'samples': 9438912, 'steps': 49160, 'loss/train': 0.9863752126693726} 08/30/2021 22:07:16 - INFO - __main__ - Step 49162: {'lr': 0.0003848471468167265, 'samples': 9439104, 'steps': 49161, 'loss/train': 1.2677817344665527} 08/30/2021 22:07:16 - INFO - __main__ - Step 49163: {'lr': 0.00038484267820524586, 'samples': 9439296, 'steps': 49162, 'loss/train': 0.6565447449684143} 08/30/2021 22:07:17 - INFO - __main__ - Step 49164: {'lr': 0.00038483820953300724, 'samples': 9439488, 'steps': 49163, 'loss/train': 1.3577884435653687} 08/30/2021 22:07:18 - INFO - __main__ - Step 49165: {'lr': 0.00038483374080001254, 'samples': 9439680, 'steps': 49164, 'loss/train': 1.3161287307739258} 08/30/2021 22:07:19 - INFO - __main__ - Step 49166: {'lr': 0.00038482927200626386, 'samples': 9439872, 'steps': 49165, 'loss/train': 1.6842350959777832} 08/30/2021 22:07:19 - INFO - __main__ - Step 49167: {'lr': 0.0003848248031517633, 'samples': 9440064, 'steps': 49166, 'loss/train': 1.3498424291610718} 08/30/2021 22:07:19 - INFO - __main__ - Step 49168: {'lr': 0.00038482033423651256, 'samples': 9440256, 'steps': 49167, 'loss/train': 0.8299590349197388} 08/30/2021 22:07:20 - INFO - __main__ - Step 49169: {'lr': 0.00038481586526051406, 'samples': 9440448, 'steps': 49168, 'loss/train': 1.4562487602233887} 08/30/2021 22:07:21 - INFO - __main__ - Step 49170: {'lr': 0.0003848113962237695, 'samples': 9440640, 'steps': 49169, 'loss/train': 1.0819567441940308} 08/30/2021 22:07:22 - INFO - __main__ - Step 49171: {'lr': 0.00038480692712628104, 'samples': 9440832, 'steps': 49170, 'loss/train': 1.4156032800674438} 08/30/2021 22:07:22 - INFO - __main__ - Step 49172: {'lr': 0.0003848024579680506, 'samples': 9441024, 'steps': 49171, 'loss/train': 1.3263633251190186} 08/30/2021 22:07:22 - INFO - __main__ - Step 49173: {'lr': 0.00038479798874908026, 'samples': 9441216, 'steps': 49172, 'loss/train': 1.9806033372879028} 08/30/2021 22:07:23 - INFO - __main__ - Step 49174: {'lr': 0.00038479351946937206, 'samples': 9441408, 'steps': 49173, 'loss/train': 1.4277247190475464} 08/30/2021 22:07:24 - INFO - __main__ - Step 49175: {'lr': 0.000384789050128928, 'samples': 9441600, 'steps': 49174, 'loss/train': 2.0319559574127197} 08/30/2021 22:07:25 - INFO - __main__ - Step 49176: {'lr': 0.0003847845807277501, 'samples': 9441792, 'steps': 49175, 'loss/train': 1.4201515913009644} 08/30/2021 22:07:25 - INFO - __main__ - Step 49177: {'lr': 0.0003847801112658403, 'samples': 9441984, 'steps': 49176, 'loss/train': 1.3669161796569824} 08/30/2021 22:07:25 - INFO - __main__ - Step 49178: {'lr': 0.0003847756417432007, 'samples': 9442176, 'steps': 49177, 'loss/train': 1.3410295248031616} 08/30/2021 22:07:26 - INFO - __main__ - Step 49179: {'lr': 0.00038477117215983316, 'samples': 9442368, 'steps': 49178, 'loss/train': 1.8866170644760132} 08/30/2021 22:07:27 - INFO - __main__ - Step 49180: {'lr': 0.0003847667025157399, 'samples': 9442560, 'steps': 49179, 'loss/train': 1.0135726928710938} 08/30/2021 22:07:28 - INFO - __main__ - Step 49181: {'lr': 0.0003847622328109228, 'samples': 9442752, 'steps': 49180, 'loss/train': 0.07564075291156769} 08/30/2021 22:07:28 - INFO - __main__ - Step 49182: {'lr': 0.000384757763045384, 'samples': 9442944, 'steps': 49181, 'loss/train': 0.30715441703796387} 08/30/2021 22:07:28 - INFO - __main__ - Step 49183: {'lr': 0.0003847532932191254, 'samples': 9443136, 'steps': 49182, 'loss/train': 2.2355058193206787} 08/30/2021 22:07:29 - INFO - __main__ - Step 49184: {'lr': 0.000384748823332149, 'samples': 9443328, 'steps': 49183, 'loss/train': 1.1814032793045044} 08/30/2021 22:07:29 - INFO - __main__ - Step 49185: {'lr': 0.0003847443533844569, 'samples': 9443520, 'steps': 49184, 'loss/train': 0.8963515162467957} 08/30/2021 22:07:31 - INFO - __main__ - Step 49186: {'lr': 0.000384739883376051, 'samples': 9443712, 'steps': 49185, 'loss/train': 1.2738615274429321} 08/30/2021 22:07:31 - INFO - __main__ - Step 49187: {'lr': 0.0003847354133069335, 'samples': 9443904, 'steps': 49186, 'loss/train': 1.3274590969085693} 08/30/2021 22:07:31 - INFO - __main__ - Step 49188: {'lr': 0.0003847309431771062, 'samples': 9444096, 'steps': 49187, 'loss/train': 1.1198103427886963} 08/30/2021 22:07:32 - INFO - __main__ - Step 49189: {'lr': 0.00038472647298657135, 'samples': 9444288, 'steps': 49188, 'loss/train': 1.8722938299179077} 08/30/2021 22:07:32 - INFO - __main__ - Step 49190: {'lr': 0.0003847220027353308, 'samples': 9444480, 'steps': 49189, 'loss/train': 1.2559112310409546} 08/30/2021 22:07:34 - INFO - __main__ - Step 49191: {'lr': 0.0003847175324233865, 'samples': 9444672, 'steps': 49190, 'loss/train': 0.05498026683926582} 08/30/2021 22:07:34 - INFO - __main__ - Step 49192: {'lr': 0.00038471306205074054, 'samples': 9444864, 'steps': 49191, 'loss/train': 0.23929549753665924} 08/30/2021 22:07:34 - INFO - __main__ - Step 49193: {'lr': 0.00038470859161739504, 'samples': 9445056, 'steps': 49192, 'loss/train': 1.2826683521270752} 08/30/2021 22:07:35 - INFO - __main__ - Step 49194: {'lr': 0.00038470412112335184, 'samples': 9445248, 'steps': 49193, 'loss/train': 1.2122269868850708} 08/30/2021 22:07:35 - INFO - __main__ - Step 49195: {'lr': 0.0003846996505686131, 'samples': 9445440, 'steps': 49194, 'loss/train': 1.8681303262710571} 08/30/2021 22:07:37 - INFO - __main__ - Step 49196: {'lr': 0.00038469517995318083, 'samples': 9445632, 'steps': 49195, 'loss/train': 1.8390130996704102} 08/30/2021 22:07:37 - INFO - __main__ - Step 49197: {'lr': 0.000384690709277057, 'samples': 9445824, 'steps': 49196, 'loss/train': 1.7137749195098877} 08/30/2021 22:07:38 - INFO - __main__ - Step 49198: {'lr': 0.0003846862385402435, 'samples': 9446016, 'steps': 49197, 'loss/train': 1.2819528579711914} 08/30/2021 22:07:38 - INFO - __main__ - Step 49199: {'lr': 0.00038468176774274253, 'samples': 9446208, 'steps': 49198, 'loss/train': 1.664359211921692} 08/30/2021 22:07:38 - INFO - __main__ - Step 49200: {'lr': 0.000384677296884556, 'samples': 9446400, 'steps': 49199, 'loss/train': 0.8389221429824829} 08/30/2021 22:07:39 - INFO - __main__ - Step 49201: {'lr': 0.000384672825965686, 'samples': 9446592, 'steps': 49200, 'loss/train': 1.6279150247573853} 08/30/2021 22:07:40 - INFO - __main__ - Step 49202: {'lr': 0.0003846683549861344, 'samples': 9446784, 'steps': 49201, 'loss/train': 0.46289634704589844} 08/30/2021 22:07:41 - INFO - __main__ - Step 49203: {'lr': 0.00038466388394590344, 'samples': 9446976, 'steps': 49202, 'loss/train': 1.8024694919586182} 08/30/2021 22:07:41 - INFO - __main__ - Step 49204: {'lr': 0.00038465941284499493, 'samples': 9447168, 'steps': 49203, 'loss/train': 1.3128901720046997} 08/30/2021 22:07:41 - INFO - __main__ - Step 49205: {'lr': 0.00038465494168341105, 'samples': 9447360, 'steps': 49204, 'loss/train': 1.273717999458313} 08/30/2021 22:07:42 - INFO - __main__ - Step 49206: {'lr': 0.00038465047046115365, 'samples': 9447552, 'steps': 49205, 'loss/train': 1.4139982461929321} 08/30/2021 22:07:44 - INFO - __main__ - Step 49207: {'lr': 0.00038464599917822483, 'samples': 9447744, 'steps': 49206, 'loss/train': 1.3037517070770264} 08/30/2021 22:07:44 - INFO - __main__ - Step 49208: {'lr': 0.00038464152783462667, 'samples': 9447936, 'steps': 49207, 'loss/train': 1.5533766746520996} 08/30/2021 22:07:44 - INFO - __main__ - Step 49209: {'lr': 0.0003846370564303611, 'samples': 9448128, 'steps': 49208, 'loss/train': 1.4777576923370361} 08/30/2021 22:07:45 - INFO - __main__ - Step 49210: {'lr': 0.00038463258496543014, 'samples': 9448320, 'steps': 49209, 'loss/train': 1.3325976133346558} 08/30/2021 22:07:45 - INFO - __main__ - Step 49211: {'lr': 0.0003846281134398358, 'samples': 9448512, 'steps': 49210, 'loss/train': 3.1529150009155273} 08/30/2021 22:07:47 - INFO - __main__ - Step 49212: {'lr': 0.0003846236418535801, 'samples': 9448704, 'steps': 49211, 'loss/train': 1.3873063325881958} 08/30/2021 22:07:47 - INFO - __main__ - Step 49213: {'lr': 0.00038461917020666506, 'samples': 9448896, 'steps': 49212, 'loss/train': 1.4782735109329224} 08/30/2021 22:07:47 - INFO - __main__ - Step 49214: {'lr': 0.0003846146984990927, 'samples': 9449088, 'steps': 49213, 'loss/train': 0.1309545338153839} 08/30/2021 22:07:48 - INFO - __main__ - Step 49215: {'lr': 0.00038461022673086506, 'samples': 9449280, 'steps': 49214, 'loss/train': 1.222947597503662} 08/30/2021 22:07:48 - INFO - __main__ - Step 49216: {'lr': 0.0003846057549019841, 'samples': 9449472, 'steps': 49215, 'loss/train': 1.864250659942627} 08/30/2021 22:07:50 - INFO - __main__ - Step 49217: {'lr': 0.0003846012830124519, 'samples': 9449664, 'steps': 49216, 'loss/train': 1.0156919956207275} 08/30/2021 22:07:50 - INFO - __main__ - Step 49218: {'lr': 0.0003845968110622704, 'samples': 9449856, 'steps': 49217, 'loss/train': 0.9880573153495789} 08/30/2021 22:07:50 - INFO - __main__ - Step 49219: {'lr': 0.0003845923390514417, 'samples': 9450048, 'steps': 49218, 'loss/train': 1.7902029752731323} 08/30/2021 22:07:51 - INFO - __main__ - Step 49220: {'lr': 0.0003845878669799677, 'samples': 9450240, 'steps': 49219, 'loss/train': 1.3832365274429321} 08/30/2021 22:07:51 - INFO - __main__ - Step 49221: {'lr': 0.00038458339484785057, 'samples': 9450432, 'steps': 49220, 'loss/train': 0.6814090609550476} 08/30/2021 22:07:53 - INFO - __main__ - Step 49222: {'lr': 0.00038457892265509214, 'samples': 9450624, 'steps': 49221, 'loss/train': 1.1078617572784424} 08/30/2021 22:07:53 - INFO - __main__ - Step 49223: {'lr': 0.00038457445040169467, 'samples': 9450816, 'steps': 49222, 'loss/train': 1.317821741104126} 08/30/2021 22:07:54 - INFO - __main__ - Step 49224: {'lr': 0.00038456997808765993, 'samples': 9451008, 'steps': 49223, 'loss/train': 1.1129207611083984} 08/30/2021 22:07:54 - INFO - __main__ - Step 49225: {'lr': 0.00038456550571299, 'samples': 9451200, 'steps': 49224, 'loss/train': 1.248144507408142} 08/30/2021 22:07:54 - INFO - __main__ - Step 49226: {'lr': 0.000384561033277687, 'samples': 9451392, 'steps': 49225, 'loss/train': 0.04282043129205704} 08/30/2021 22:07:56 - INFO - __main__ - Step 49227: {'lr': 0.00038455656078175283, 'samples': 9451584, 'steps': 49226, 'loss/train': 0.7476810812950134} 08/30/2021 22:07:56 - INFO - __main__ - Step 49228: {'lr': 0.0003845520882251895, 'samples': 9451776, 'steps': 49227, 'loss/train': 1.4731860160827637} 08/30/2021 22:07:56 - INFO - __main__ - Step 49229: {'lr': 0.00038454761560799915, 'samples': 9451968, 'steps': 49228, 'loss/train': 1.58684241771698} 08/30/2021 22:07:57 - INFO - __main__ - Step 49230: {'lr': 0.0003845431429301838, 'samples': 9452160, 'steps': 49229, 'loss/train': 0.8257639408111572} 08/30/2021 22:07:57 - INFO - __main__ - Step 49231: {'lr': 0.0003845386701917453, 'samples': 9452352, 'steps': 49230, 'loss/train': 1.198689341545105} 08/30/2021 22:07:59 - INFO - __main__ - Step 49232: {'lr': 0.0003845341973926857, 'samples': 9452544, 'steps': 49231, 'loss/train': 1.4551129341125488} 08/30/2021 22:07:59 - INFO - __main__ - Step 49233: {'lr': 0.0003845297245330071, 'samples': 9452736, 'steps': 49232, 'loss/train': 1.2291473150253296} 08/30/2021 22:08:00 - INFO - __main__ - Step 49234: {'lr': 0.0003845252516127115, 'samples': 9452928, 'steps': 49233, 'loss/train': 1.5148202180862427} 08/30/2021 22:08:00 - INFO - __main__ - Step 49235: {'lr': 0.0003845207786318009, 'samples': 9453120, 'steps': 49234, 'loss/train': 1.0508157014846802} 08/30/2021 22:08:00 - INFO - __main__ - Step 49236: {'lr': 0.0003845163055902773, 'samples': 9453312, 'steps': 49235, 'loss/train': 1.4602532386779785} 08/30/2021 22:08:01 - INFO - __main__ - Step 49237: {'lr': 0.0003845118324881428, 'samples': 9453504, 'steps': 49236, 'loss/train': 1.648748517036438} 08/30/2021 22:08:02 - INFO - __main__ - Step 49238: {'lr': 0.00038450735932539927, 'samples': 9453696, 'steps': 49237, 'loss/train': 0.32679829001426697} 08/30/2021 22:08:03 - INFO - __main__ - Step 49239: {'lr': 0.0003845028861020488, 'samples': 9453888, 'steps': 49238, 'loss/train': 1.423423409461975} 08/30/2021 22:08:03 - INFO - __main__ - Step 49240: {'lr': 0.0003844984128180934, 'samples': 9454080, 'steps': 49239, 'loss/train': 1.4369245767593384} 08/30/2021 22:08:04 - INFO - __main__ - Step 49241: {'lr': 0.00038449393947353507, 'samples': 9454272, 'steps': 49240, 'loss/train': 1.8922852277755737} 08/30/2021 22:08:04 - INFO - __main__ - Step 49242: {'lr': 0.00038448946606837585, 'samples': 9454464, 'steps': 49241, 'loss/train': 4.198641300201416} 08/30/2021 22:08:05 - INFO - __main__ - Step 49243: {'lr': 0.00038448499260261787, 'samples': 9454656, 'steps': 49242, 'loss/train': 1.6535613536834717} 08/30/2021 22:08:06 - INFO - __main__ - Step 49244: {'lr': 0.0003844805190762629, 'samples': 9454848, 'steps': 49243, 'loss/train': 1.4675184488296509} 08/30/2021 22:08:06 - INFO - __main__ - Step 49245: {'lr': 0.00038447604548931313, 'samples': 9455040, 'steps': 49244, 'loss/train': 1.0234043598175049} 08/30/2021 22:08:07 - INFO - __main__ - Step 49246: {'lr': 0.0003844715718417705, 'samples': 9455232, 'steps': 49245, 'loss/train': 1.3436241149902344} 08/30/2021 22:08:07 - INFO - __main__ - Step 49247: {'lr': 0.0003844670981336371, 'samples': 9455424, 'steps': 49246, 'loss/train': 0.6790292263031006} 08/30/2021 22:08:08 - INFO - __main__ - Step 49248: {'lr': 0.000384462624364915, 'samples': 9455616, 'steps': 49247, 'loss/train': 1.5197412967681885} 08/30/2021 22:08:09 - INFO - __main__ - Step 49249: {'lr': 0.00038445815053560596, 'samples': 9455808, 'steps': 49248, 'loss/train': 1.5542930364608765} 08/30/2021 22:08:09 - INFO - __main__ - Step 49250: {'lr': 0.00038445367664571216, 'samples': 9456000, 'steps': 49249, 'loss/train': 1.1682729721069336} 08/30/2021 22:08:10 - INFO - __main__ - Step 49251: {'lr': 0.00038444920269523563, 'samples': 9456192, 'steps': 49250, 'loss/train': 1.1977733373641968} 08/30/2021 22:08:10 - INFO - __main__ - Step 49252: {'lr': 0.0003844447286841783, 'samples': 9456384, 'steps': 49251, 'loss/train': 1.5462701320648193} 08/30/2021 22:08:11 - INFO - __main__ - Step 49253: {'lr': 0.0003844402546125424, 'samples': 9456576, 'steps': 49252, 'loss/train': 0.2373725175857544} 08/30/2021 22:08:12 - INFO - __main__ - Step 49254: {'lr': 0.00038443578048032975, 'samples': 9456768, 'steps': 49253, 'loss/train': 1.6040765047073364} 08/30/2021 22:08:12 - INFO - __main__ - Step 49255: {'lr': 0.0003844313062875423, 'samples': 9456960, 'steps': 49254, 'loss/train': 1.4305919408798218} 08/30/2021 22:08:13 - INFO - __main__ - Step 49256: {'lr': 0.00038442683203418227, 'samples': 9457152, 'steps': 49255, 'loss/train': 1.3896656036376953} 08/30/2021 22:08:13 - INFO - __main__ - Step 49257: {'lr': 0.0003844223577202516, 'samples': 9457344, 'steps': 49256, 'loss/train': 1.2048274278640747} 08/30/2021 22:08:15 - INFO - __main__ - Step 49258: {'lr': 0.00038441788334575225, 'samples': 9457536, 'steps': 49257, 'loss/train': 1.546325922012329} 08/30/2021 22:08:16 - INFO - __main__ - Step 49259: {'lr': 0.0003844134089106863, 'samples': 9457728, 'steps': 49258, 'loss/train': 1.31949782371521} 08/30/2021 22:08:16 - INFO - __main__ - Step 49260: {'lr': 0.00038440893441505573, 'samples': 9457920, 'steps': 49259, 'loss/train': 1.5841712951660156} 08/30/2021 22:08:16 - INFO - __main__ - Step 49261: {'lr': 0.0003844044598588625, 'samples': 9458112, 'steps': 49260, 'loss/train': 1.8185442686080933} 08/30/2021 22:08:17 - INFO - __main__ - Step 49262: {'lr': 0.0003843999852421088, 'samples': 9458304, 'steps': 49261, 'loss/train': 0.04322107881307602} 08/30/2021 22:08:17 - INFO - __main__ - Step 49263: {'lr': 0.0003843955105647965, 'samples': 9458496, 'steps': 49262, 'loss/train': 1.0817681550979614} 08/30/2021 22:08:18 - INFO - __main__ - Step 49264: {'lr': 0.0003843910358269277, 'samples': 9458688, 'steps': 49263, 'loss/train': 0.05380666255950928} 08/30/2021 22:08:19 - INFO - __main__ - Step 49265: {'lr': 0.0003843865610285043, 'samples': 9458880, 'steps': 49264, 'loss/train': 1.3266944885253906} 08/30/2021 22:08:19 - INFO - __main__ - Step 49266: {'lr': 0.0003843820861695284, 'samples': 9459072, 'steps': 49265, 'loss/train': 1.446295142173767} 08/30/2021 22:08:20 - INFO - __main__ - Step 49267: {'lr': 0.00038437761125000204, 'samples': 9459264, 'steps': 49266, 'loss/train': 1.4948248863220215} 08/30/2021 22:08:20 - INFO - __main__ - Step 49268: {'lr': 0.00038437313626992723, 'samples': 9459456, 'steps': 49267, 'loss/train': 1.1032837629318237} 08/30/2021 22:08:22 - INFO - __main__ - Step 49269: {'lr': 0.0003843686612293059, 'samples': 9459648, 'steps': 49268, 'loss/train': 0.5796222686767578} 08/30/2021 22:08:22 - INFO - __main__ - Step 49270: {'lr': 0.0003843641861281402, 'samples': 9459840, 'steps': 49269, 'loss/train': 1.481544852256775} 08/30/2021 22:08:22 - INFO - __main__ - Step 49271: {'lr': 0.00038435971096643196, 'samples': 9460032, 'steps': 49270, 'loss/train': 0.8321482539176941} 08/30/2021 22:08:23 - INFO - __main__ - Step 49272: {'lr': 0.00038435523574418336, 'samples': 9460224, 'steps': 49271, 'loss/train': 1.2183438539505005} 08/30/2021 22:08:23 - INFO - __main__ - Step 49273: {'lr': 0.0003843507604613964, 'samples': 9460416, 'steps': 49272, 'loss/train': 1.5134491920471191} 08/30/2021 22:08:24 - INFO - __main__ - Step 49274: {'lr': 0.00038434628511807296, 'samples': 9460608, 'steps': 49273, 'loss/train': 0.6419780254364014} 08/30/2021 22:08:25 - INFO - __main__ - Step 49275: {'lr': 0.00038434180971421523, 'samples': 9460800, 'steps': 49274, 'loss/train': 1.5866234302520752} 08/30/2021 22:08:25 - INFO - __main__ - Step 49276: {'lr': 0.0003843373342498251, 'samples': 9460992, 'steps': 49275, 'loss/train': 0.7980654835700989} 08/30/2021 22:08:26 - INFO - __main__ - Step 49277: {'lr': 0.00038433285872490475, 'samples': 9461184, 'steps': 49276, 'loss/train': 1.5908366441726685} 08/30/2021 22:08:26 - INFO - __main__ - Step 49278: {'lr': 0.000384328383139456, 'samples': 9461376, 'steps': 49277, 'loss/train': 1.6412440538406372} 08/30/2021 22:08:26 - INFO - __main__ - Step 49279: {'lr': 0.000384323907493481, 'samples': 9461568, 'steps': 49278, 'loss/train': 1.5419632196426392} 08/30/2021 22:08:28 - INFO - __main__ - Step 49280: {'lr': 0.0003843194317869817, 'samples': 9461760, 'steps': 49279, 'loss/train': 1.3067244291305542} 08/30/2021 22:08:28 - INFO - __main__ - Step 49281: {'lr': 0.0003843149560199601, 'samples': 9461952, 'steps': 49280, 'loss/train': 1.2367156744003296} 08/30/2021 22:08:29 - INFO - __main__ - Step 49282: {'lr': 0.0003843104801924183, 'samples': 9462144, 'steps': 49281, 'loss/train': 1.2822291851043701} 08/30/2021 22:08:29 - INFO - __main__ - Step 49283: {'lr': 0.00038430600430435825, 'samples': 9462336, 'steps': 49282, 'loss/train': 1.815993070602417} 08/30/2021 22:08:29 - INFO - __main__ - Step 49284: {'lr': 0.000384301528355782, 'samples': 9462528, 'steps': 49283, 'loss/train': 1.6723556518554688} 08/30/2021 22:08:31 - INFO - __main__ - Step 49285: {'lr': 0.00038429705234669157, 'samples': 9462720, 'steps': 49284, 'loss/train': 1.1135339736938477} 08/30/2021 22:08:32 - INFO - __main__ - Step 49286: {'lr': 0.00038429257627708893, 'samples': 9462912, 'steps': 49285, 'loss/train': 1.359188199043274} 08/30/2021 22:08:32 - INFO - __main__ - Step 49287: {'lr': 0.00038428810014697615, 'samples': 9463104, 'steps': 49286, 'loss/train': 1.1317414045333862} 08/30/2021 22:08:32 - INFO - __main__ - Step 49288: {'lr': 0.00038428362395635514, 'samples': 9463296, 'steps': 49287, 'loss/train': 1.7288060188293457} 08/30/2021 22:08:33 - INFO - __main__ - Step 49289: {'lr': 0.0003842791477052281, 'samples': 9463488, 'steps': 49288, 'loss/train': 0.21582379937171936} 08/30/2021 22:08:33 - INFO - __main__ - Step 49290: {'lr': 0.00038427467139359696, 'samples': 9463680, 'steps': 49289, 'loss/train': 0.48793405294418335} 08/30/2021 22:08:35 - INFO - __main__ - Step 49291: {'lr': 0.00038427019502146364, 'samples': 9463872, 'steps': 49290, 'loss/train': 1.7250391244888306} 08/30/2021 22:08:35 - INFO - __main__ - Step 49292: {'lr': 0.0003842657185888303, 'samples': 9464064, 'steps': 49291, 'loss/train': 1.3810476064682007} 08/30/2021 22:08:35 - INFO - __main__ - Step 49293: {'lr': 0.00038426124209569885, 'samples': 9464256, 'steps': 49292, 'loss/train': 1.6160986423492432} 08/30/2021 22:08:36 - INFO - __main__ - Step 49294: {'lr': 0.00038425676554207133, 'samples': 9464448, 'steps': 49293, 'loss/train': 0.27751803398132324} 08/30/2021 22:08:36 - INFO - __main__ - Step 49295: {'lr': 0.0003842522889279499, 'samples': 9464640, 'steps': 49294, 'loss/train': 1.7591522932052612} 08/30/2021 22:08:38 - INFO - __main__ - Step 49296: {'lr': 0.00038424781225333636, 'samples': 9464832, 'steps': 49295, 'loss/train': 0.8963214755058289} 08/30/2021 22:08:38 - INFO - __main__ - Step 49297: {'lr': 0.0003842433355182329, 'samples': 9465024, 'steps': 49296, 'loss/train': 3.1488471031188965} 08/30/2021 22:08:39 - INFO - __main__ - Step 49298: {'lr': 0.0003842388587226414, 'samples': 9465216, 'steps': 49297, 'loss/train': 1.3312585353851318} 08/30/2021 22:08:39 - INFO - __main__ - Step 49299: {'lr': 0.000384234381866564, 'samples': 9465408, 'steps': 49298, 'loss/train': 1.4373165369033813} 08/30/2021 22:08:39 - INFO - __main__ - Step 49300: {'lr': 0.00038422990495000267, 'samples': 9465600, 'steps': 49299, 'loss/train': 0.09126025438308716} 08/30/2021 22:08:40 - INFO - __main__ - Step 49301: {'lr': 0.00038422542797295935, 'samples': 9465792, 'steps': 49300, 'loss/train': 0.33187004923820496} 08/30/2021 22:08:40 - INFO - __main__ - Step 49302: {'lr': 0.0003842209509354362, 'samples': 9465984, 'steps': 49301, 'loss/train': 0.9662020206451416} 08/30/2021 22:08:42 - INFO - __main__ - Step 49303: {'lr': 0.00038421647383743505, 'samples': 9466176, 'steps': 49302, 'loss/train': 1.3036764860153198} 08/30/2021 22:08:42 - INFO - __main__ - Step 49304: {'lr': 0.00038421199667895814, 'samples': 9466368, 'steps': 49303, 'loss/train': 1.3093466758728027} 08/30/2021 22:08:43 - INFO - __main__ - Step 49305: {'lr': 0.0003842075194600073, 'samples': 9466560, 'steps': 49304, 'loss/train': 1.181131362915039} 08/30/2021 22:08:43 - INFO - __main__ - Step 49306: {'lr': 0.00038420304218058466, 'samples': 9466752, 'steps': 49305, 'loss/train': 1.411622166633606} 08/30/2021 22:08:43 - INFO - __main__ - Step 49307: {'lr': 0.00038419856484069216, 'samples': 9466944, 'steps': 49306, 'loss/train': 1.4452733993530273} 08/30/2021 22:08:45 - INFO - __main__ - Step 49308: {'lr': 0.0003841940874403319, 'samples': 9467136, 'steps': 49307, 'loss/train': 0.11862015724182129} 08/30/2021 22:08:45 - INFO - __main__ - Step 49309: {'lr': 0.0003841896099795058, 'samples': 9467328, 'steps': 49308, 'loss/train': 0.39663875102996826} 08/30/2021 22:08:46 - INFO - __main__ - Step 49310: {'lr': 0.00038418513245821605, 'samples': 9467520, 'steps': 49309, 'loss/train': 0.5722724795341492} 08/30/2021 22:08:46 - INFO - __main__ - Step 49311: {'lr': 0.0003841806548764645, 'samples': 9467712, 'steps': 49310, 'loss/train': 1.5263508558273315} 08/30/2021 22:08:46 - INFO - __main__ - Step 49312: {'lr': 0.0003841761772342531, 'samples': 9467904, 'steps': 49311, 'loss/train': 0.9048899412155151} 08/30/2021 22:08:48 - INFO - __main__ - Step 49313: {'lr': 0.0003841716995315841, 'samples': 9468096, 'steps': 49312, 'loss/train': 1.241011619567871} 08/30/2021 22:08:48 - INFO - __main__ - Step 49314: {'lr': 0.00038416722176845943, 'samples': 9468288, 'steps': 49313, 'loss/train': 1.4199984073638916} 08/30/2021 22:08:49 - INFO - __main__ - Step 49315: {'lr': 0.000384162743944881, 'samples': 9468480, 'steps': 49314, 'loss/train': 1.339867353439331} 08/30/2021 22:08:49 - INFO - __main__ - Step 49316: {'lr': 0.0003841582660608509, 'samples': 9468672, 'steps': 49315, 'loss/train': 1.6245360374450684} 08/30/2021 22:08:49 - INFO - __main__ - Step 49317: {'lr': 0.00038415378811637124, 'samples': 9468864, 'steps': 49316, 'loss/train': 1.7857468128204346} 08/30/2021 22:08:52 - INFO - __main__ - Step 49318: {'lr': 0.00038414931011144393, 'samples': 9469056, 'steps': 49317, 'loss/train': 1.3455666303634644} 08/30/2021 22:08:52 - INFO - __main__ - Step 49319: {'lr': 0.000384144832046071, 'samples': 9469248, 'steps': 49318, 'loss/train': 1.9347959756851196} 08/30/2021 22:08:52 - INFO - __main__ - Step 49320: {'lr': 0.0003841403539202545, 'samples': 9469440, 'steps': 49319, 'loss/train': 1.1906849145889282} 08/30/2021 22:08:53 - INFO - __main__ - Step 49321: {'lr': 0.00038413587573399635, 'samples': 9469632, 'steps': 49320, 'loss/train': 1.1730536222457886} 08/30/2021 22:08:53 - INFO - __main__ - Step 49322: {'lr': 0.0003841313974872986, 'samples': 9469824, 'steps': 49321, 'loss/train': 1.3707752227783203} 08/30/2021 22:08:54 - INFO - __main__ - Step 49323: {'lr': 0.00038412691918016345, 'samples': 9470016, 'steps': 49322, 'loss/train': 1.0285190343856812} 08/30/2021 22:08:55 - INFO - __main__ - Step 49324: {'lr': 0.00038412244081259273, 'samples': 9470208, 'steps': 49323, 'loss/train': 1.0527369976043701} 08/30/2021 22:08:55 - INFO - __main__ - Step 49325: {'lr': 0.00038411796238458853, 'samples': 9470400, 'steps': 49324, 'loss/train': 1.8493014574050903} 08/30/2021 22:08:56 - INFO - __main__ - Step 49326: {'lr': 0.00038411348389615286, 'samples': 9470592, 'steps': 49325, 'loss/train': 1.1464709043502808} 08/30/2021 22:08:56 - INFO - __main__ - Step 49327: {'lr': 0.00038410900534728765, 'samples': 9470784, 'steps': 49326, 'loss/train': 1.5225107669830322} 08/30/2021 22:08:58 - INFO - __main__ - Step 49328: {'lr': 0.000384104526737995, 'samples': 9470976, 'steps': 49327, 'loss/train': 1.741552472114563} 08/30/2021 22:08:58 - INFO - __main__ - Step 49329: {'lr': 0.0003841000480682769, 'samples': 9471168, 'steps': 49328, 'loss/train': 1.9028974771499634} 08/30/2021 22:08:58 - INFO - __main__ - Step 49330: {'lr': 0.0003840955693381355, 'samples': 9471360, 'steps': 49329, 'loss/train': 1.6996532678604126} 08/30/2021 22:08:59 - INFO - __main__ - Step 49331: {'lr': 0.0003840910905475726, 'samples': 9471552, 'steps': 49330, 'loss/train': 1.088881015777588} 08/30/2021 22:08:59 - INFO - __main__ - Step 49332: {'lr': 0.0003840866116965904, 'samples': 9471744, 'steps': 49331, 'loss/train': 1.2434372901916504} 08/30/2021 22:08:59 - INFO - __main__ - Step 49333: {'lr': 0.00038408213278519083, 'samples': 9471936, 'steps': 49332, 'loss/train': 1.1687560081481934} 08/30/2021 22:09:01 - INFO - __main__ - Step 49334: {'lr': 0.0003840776538133759, 'samples': 9472128, 'steps': 49333, 'loss/train': 0.5918006300926208} 08/30/2021 22:09:02 - INFO - __main__ - Step 49335: {'lr': 0.00038407317478114764, 'samples': 9472320, 'steps': 49334, 'loss/train': 1.5982314348220825} 08/30/2021 22:09:02 - INFO - __main__ - Step 49336: {'lr': 0.00038406869568850805, 'samples': 9472512, 'steps': 49335, 'loss/train': 1.2378559112548828} 08/30/2021 22:09:02 - INFO - __main__ - Step 49337: {'lr': 0.00038406421653545926, 'samples': 9472704, 'steps': 49336, 'loss/train': 0.5362732410430908} 08/30/2021 22:09:03 - INFO - __main__ - Step 49338: {'lr': 0.00038405973732200317, 'samples': 9472896, 'steps': 49337, 'loss/train': 1.3490744829177856} 08/30/2021 22:09:04 - INFO - __main__ - Step 49339: {'lr': 0.0003840552580481418, 'samples': 9473088, 'steps': 49338, 'loss/train': 1.5935252904891968} 08/30/2021 22:09:04 - INFO - __main__ - Step 49340: {'lr': 0.00038405077871387716, 'samples': 9473280, 'steps': 49339, 'loss/train': 1.2003512382507324} 08/30/2021 22:09:05 - INFO - __main__ - Step 49341: {'lr': 0.00038404629931921137, 'samples': 9473472, 'steps': 49340, 'loss/train': 1.1513137817382812} 08/30/2021 22:09:05 - INFO - __main__ - Step 49342: {'lr': 0.0003840418198641463, 'samples': 9473664, 'steps': 49341, 'loss/train': 1.4045181274414062} 08/30/2021 22:09:05 - INFO - __main__ - Step 49343: {'lr': 0.0003840373403486842, 'samples': 9473856, 'steps': 49342, 'loss/train': 0.7895429134368896} 08/30/2021 22:09:07 - INFO - __main__ - Step 49344: {'lr': 0.0003840328607728269, 'samples': 9474048, 'steps': 49343, 'loss/train': 1.3992438316345215} 08/30/2021 22:09:07 - INFO - __main__ - Step 49345: {'lr': 0.0003840283811365764, 'samples': 9474240, 'steps': 49344, 'loss/train': 2.078401803970337} 08/30/2021 22:09:08 - INFO - __main__ - Step 49346: {'lr': 0.00038402390143993484, 'samples': 9474432, 'steps': 49345, 'loss/train': 1.3841291666030884} 08/30/2021 22:09:08 - INFO - __main__ - Step 49347: {'lr': 0.0003840194216829042, 'samples': 9474624, 'steps': 49346, 'loss/train': 0.9066892266273499} 08/30/2021 22:09:09 - INFO - __main__ - Step 49348: {'lr': 0.00038401494186548633, 'samples': 9474816, 'steps': 49347, 'loss/train': 1.1779420375823975} 08/30/2021 22:09:10 - INFO - __main__ - Step 49349: {'lr': 0.0003840104619876835, 'samples': 9475008, 'steps': 49348, 'loss/train': 1.8947360515594482} 08/30/2021 22:09:11 - INFO - __main__ - Step 49350: {'lr': 0.0003840059820494976, 'samples': 9475200, 'steps': 49349, 'loss/train': 1.7193268537521362} 08/30/2021 22:09:11 - INFO - __main__ - Step 49351: {'lr': 0.00038400150205093075, 'samples': 9475392, 'steps': 49350, 'loss/train': 1.2958611249923706} 08/30/2021 22:09:11 - INFO - __main__ - Step 49352: {'lr': 0.00038399702199198486, 'samples': 9475584, 'steps': 49351, 'loss/train': 1.5861743688583374} 08/30/2021 22:09:12 - INFO - __main__ - Step 49353: {'lr': 0.00038399254187266186, 'samples': 9475776, 'steps': 49352, 'loss/train': 0.9506011009216309} 08/30/2021 22:09:13 - INFO - __main__ - Step 49354: {'lr': 0.000383988061692964, 'samples': 9475968, 'steps': 49353, 'loss/train': 1.5978995561599731} 08/30/2021 22:09:14 - INFO - __main__ - Step 49355: {'lr': 0.0003839835814528931, 'samples': 9476160, 'steps': 49354, 'loss/train': 1.2448289394378662} 08/30/2021 22:09:14 - INFO - __main__ - Step 49356: {'lr': 0.0003839791011524514, 'samples': 9476352, 'steps': 49355, 'loss/train': 1.210731029510498} 08/30/2021 22:09:14 - INFO - __main__ - Step 49357: {'lr': 0.0003839746207916407, 'samples': 9476544, 'steps': 49356, 'loss/train': 1.3754315376281738} 08/30/2021 22:09:15 - INFO - __main__ - Step 49358: {'lr': 0.0003839701403704631, 'samples': 9476736, 'steps': 49357, 'loss/train': 1.206537127494812} 08/30/2021 22:09:16 - INFO - __main__ - Step 49359: {'lr': 0.00038396565988892063, 'samples': 9476928, 'steps': 49358, 'loss/train': 1.6833325624465942} 08/30/2021 22:09:17 - INFO - __main__ - Step 49360: {'lr': 0.00038396117934701537, 'samples': 9477120, 'steps': 49359, 'loss/train': 1.2171975374221802} 08/30/2021 22:09:17 - INFO - __main__ - Step 49361: {'lr': 0.00038395669874474915, 'samples': 9477312, 'steps': 49360, 'loss/train': 0.09465812891721725} 08/30/2021 22:09:17 - INFO - __main__ - Step 49362: {'lr': 0.00038395221808212415, 'samples': 9477504, 'steps': 49361, 'loss/train': 1.7135801315307617} 08/30/2021 22:09:18 - INFO - __main__ - Step 49363: {'lr': 0.0003839477373591423, 'samples': 9477696, 'steps': 49362, 'loss/train': 1.6088014841079712} 08/30/2021 22:09:19 - INFO - __main__ - Step 49364: {'lr': 0.0003839432565758059, 'samples': 9477888, 'steps': 49363, 'loss/train': 1.7376768589019775} 08/30/2021 22:09:20 - INFO - __main__ - Step 49365: {'lr': 0.0003839387757321165, 'samples': 9478080, 'steps': 49364, 'loss/train': 0.3677865266799927} 08/30/2021 22:09:20 - INFO - __main__ - Step 49366: {'lr': 0.0003839342948280764, 'samples': 9478272, 'steps': 49365, 'loss/train': 1.654752254486084} 08/30/2021 22:09:21 - INFO - __main__ - Step 49367: {'lr': 0.00038392981386368763, 'samples': 9478464, 'steps': 49366, 'loss/train': 1.5803627967834473} 08/30/2021 22:09:21 - INFO - __main__ - Step 49368: {'lr': 0.0003839253328389521, 'samples': 9478656, 'steps': 49367, 'loss/train': 1.4564448595046997} 08/30/2021 22:09:21 - INFO - __main__ - Step 49369: {'lr': 0.00038392085175387186, 'samples': 9478848, 'steps': 49368, 'loss/train': 1.250160813331604} 08/30/2021 22:09:24 - INFO - __main__ - Step 49370: {'lr': 0.000383916370608449, 'samples': 9479040, 'steps': 49369, 'loss/train': 1.2121021747589111} 08/30/2021 22:09:24 - INFO - __main__ - Step 49371: {'lr': 0.0003839118894026855, 'samples': 9479232, 'steps': 49370, 'loss/train': 1.5944617986679077} 08/30/2021 22:09:24 - INFO - __main__ - Step 49372: {'lr': 0.0003839074081365833, 'samples': 9479424, 'steps': 49371, 'loss/train': 1.2362544536590576} 08/30/2021 22:09:25 - INFO - __main__ - Step 49373: {'lr': 0.0003839029268101446, 'samples': 9479616, 'steps': 49372, 'loss/train': 0.6072336435317993} 08/30/2021 22:09:25 - INFO - __main__ - Step 49374: {'lr': 0.00038389844542337123, 'samples': 9479808, 'steps': 49373, 'loss/train': 1.4622094631195068} 08/30/2021 22:09:27 - INFO - __main__ - Step 49375: {'lr': 0.0003838939639762653, 'samples': 9480000, 'steps': 49374, 'loss/train': 0.26569798588752747} 08/30/2021 22:09:27 - INFO - __main__ - Step 49376: {'lr': 0.00038388948246882883, 'samples': 9480192, 'steps': 49375, 'loss/train': 1.557763695716858} 08/30/2021 22:09:27 - INFO - __main__ - Step 49377: {'lr': 0.0003838850009010638, 'samples': 9480384, 'steps': 49376, 'loss/train': 1.0884987115859985} 08/30/2021 22:09:28 - INFO - __main__ - Step 49378: {'lr': 0.0003838805192729723, 'samples': 9480576, 'steps': 49377, 'loss/train': 0.9593924880027771} 08/30/2021 22:09:28 - INFO - __main__ - Step 49379: {'lr': 0.00038387603758455624, 'samples': 9480768, 'steps': 49378, 'loss/train': 1.7927411794662476} 08/30/2021 22:09:29 - INFO - __main__ - Step 49380: {'lr': 0.00038387155583581773, 'samples': 9480960, 'steps': 49379, 'loss/train': 1.7089567184448242} 08/30/2021 22:09:30 - INFO - __main__ - Step 49381: {'lr': 0.00038386707402675877, 'samples': 9481152, 'steps': 49380, 'loss/train': 0.8583994507789612} 08/30/2021 22:09:30 - INFO - __main__ - Step 49382: {'lr': 0.00038386259215738135, 'samples': 9481344, 'steps': 49381, 'loss/train': 1.130814552307129} 08/30/2021 22:09:31 - INFO - __main__ - Step 49383: {'lr': 0.0003838581102276876, 'samples': 9481536, 'steps': 49382, 'loss/train': 1.6091268062591553} 08/30/2021 22:09:31 - INFO - __main__ - Step 49384: {'lr': 0.00038385362823767935, 'samples': 9481728, 'steps': 49383, 'loss/train': 1.6003414392471313} 08/30/2021 22:09:33 - INFO - __main__ - Step 49385: {'lr': 0.00038384914618735873, 'samples': 9481920, 'steps': 49384, 'loss/train': 1.8464782238006592} 08/30/2021 22:09:33 - INFO - __main__ - Step 49386: {'lr': 0.0003838446640767278, 'samples': 9482112, 'steps': 49385, 'loss/train': 1.2683963775634766} 08/30/2021 22:09:34 - INFO - __main__ - Step 49387: {'lr': 0.00038384018190578843, 'samples': 9482304, 'steps': 49386, 'loss/train': 1.3003493547439575} 08/30/2021 22:09:34 - INFO - __main__ - Step 49388: {'lr': 0.0003838356996745429, 'samples': 9482496, 'steps': 49387, 'loss/train': 1.158971905708313} 08/30/2021 22:09:35 - INFO - __main__ - Step 49389: {'lr': 0.00038383121738299296, 'samples': 9482688, 'steps': 49388, 'loss/train': 1.5438778400421143} 08/30/2021 22:09:35 - INFO - __main__ - Step 49390: {'lr': 0.00038382673503114075, 'samples': 9482880, 'steps': 49389, 'loss/train': 1.5751315355300903} 08/30/2021 22:09:36 - INFO - __main__ - Step 49391: {'lr': 0.0003838222526189883, 'samples': 9483072, 'steps': 49390, 'loss/train': 0.08660253137350082} 08/30/2021 22:09:37 - INFO - __main__ - Step 49392: {'lr': 0.0003838177701465376, 'samples': 9483264, 'steps': 49391, 'loss/train': 1.6198095083236694} 08/30/2021 22:09:37 - INFO - __main__ - Step 49393: {'lr': 0.00038381328761379063, 'samples': 9483456, 'steps': 49392, 'loss/train': 1.456913948059082} 08/30/2021 22:09:37 - INFO - __main__ - Step 49394: {'lr': 0.0003838088050207496, 'samples': 9483648, 'steps': 49393, 'loss/train': 1.3473281860351562} 08/30/2021 22:09:38 - INFO - __main__ - Step 49395: {'lr': 0.00038380432236741625, 'samples': 9483840, 'steps': 49394, 'loss/train': 0.7261760234832764} 08/30/2021 22:09:39 - INFO - __main__ - Step 49396: {'lr': 0.0003837998396537927, 'samples': 9484032, 'steps': 49395, 'loss/train': 1.481816053390503} 08/30/2021 22:09:40 - INFO - __main__ - Step 49397: {'lr': 0.0003837953568798811, 'samples': 9484224, 'steps': 49396, 'loss/train': 1.5362592935562134} 08/30/2021 22:09:40 - INFO - __main__ - Step 49398: {'lr': 0.00038379087404568333, 'samples': 9484416, 'steps': 49397, 'loss/train': 1.5976382493972778} 08/30/2021 22:09:41 - INFO - __main__ - Step 49399: {'lr': 0.00038378639115120154, 'samples': 9484608, 'steps': 49398, 'loss/train': 0.9332494735717773} 08/30/2021 22:09:41 - INFO - __main__ - Step 49400: {'lr': 0.0003837819081964377, 'samples': 9484800, 'steps': 49399, 'loss/train': 1.2511084079742432} 08/30/2021 22:09:42 - INFO - __main__ - Step 49401: {'lr': 0.0003837774251813936, 'samples': 9484992, 'steps': 49400, 'loss/train': 0.3496077060699463} 08/30/2021 22:09:43 - INFO - __main__ - Step 49402: {'lr': 0.0003837729421060716, 'samples': 9485184, 'steps': 49401, 'loss/train': 1.514067530632019} 08/30/2021 22:09:43 - INFO - __main__ - Step 49403: {'lr': 0.00038376845897047354, 'samples': 9485376, 'steps': 49402, 'loss/train': 1.1421542167663574} 08/30/2021 22:09:43 - INFO - __main__ - Step 49404: {'lr': 0.00038376397577460144, 'samples': 9485568, 'steps': 49403, 'loss/train': 1.1896404027938843} 08/30/2021 22:09:44 - INFO - __main__ - Step 49405: {'lr': 0.00038375949251845745, 'samples': 9485760, 'steps': 49404, 'loss/train': 0.8072686195373535} 08/30/2021 22:09:45 - INFO - __main__ - Step 49406: {'lr': 0.0003837550092020434, 'samples': 9485952, 'steps': 49405, 'loss/train': 1.6520885229110718} 08/30/2021 22:09:46 - INFO - __main__ - Step 49407: {'lr': 0.0003837505258253615, 'samples': 9486144, 'steps': 49406, 'loss/train': 1.38993501663208} 08/30/2021 22:09:46 - INFO - __main__ - Step 49408: {'lr': 0.0003837460423884136, 'samples': 9486336, 'steps': 49407, 'loss/train': 1.1067701578140259} 08/30/2021 22:09:46 - INFO - __main__ - Step 49409: {'lr': 0.00038374155889120176, 'samples': 9486528, 'steps': 49408, 'loss/train': 0.7197641730308533} 08/30/2021 22:09:47 - INFO - __main__ - Step 49410: {'lr': 0.0003837370753337281, 'samples': 9486720, 'steps': 49409, 'loss/train': 1.0605894327163696} 08/30/2021 22:09:47 - INFO - __main__ - Step 49411: {'lr': 0.00038373259171599463, 'samples': 9486912, 'steps': 49410, 'loss/train': 1.4700936079025269} 08/30/2021 22:09:49 - INFO - __main__ - Step 49412: {'lr': 0.0003837281080380033, 'samples': 9487104, 'steps': 49411, 'loss/train': 1.697468638420105} 08/30/2021 22:09:49 - INFO - __main__ - Step 49413: {'lr': 0.00038372362429975603, 'samples': 9487296, 'steps': 49412, 'loss/train': 1.6221933364868164} 08/30/2021 22:09:50 - INFO - __main__ - Step 49414: {'lr': 0.0003837191405012551, 'samples': 9487488, 'steps': 49413, 'loss/train': 1.7777656316757202} 08/30/2021 22:09:50 - INFO - __main__ - Step 49415: {'lr': 0.00038371465664250226, 'samples': 9487680, 'steps': 49414, 'loss/train': 0.2903272807598114} 08/30/2021 22:09:50 - INFO - __main__ - Step 49416: {'lr': 0.0003837101727234997, 'samples': 9487872, 'steps': 49415, 'loss/train': 5.898153781890869} 08/30/2021 22:09:52 - INFO - __main__ - Step 49417: {'lr': 0.0003837056887442495, 'samples': 9488064, 'steps': 49416, 'loss/train': 0.8973371386528015} 08/30/2021 22:09:52 - INFO - __main__ - Step 49418: {'lr': 0.00038370120470475355, 'samples': 9488256, 'steps': 49417, 'loss/train': 1.488458275794983} 08/30/2021 22:09:53 - INFO - __main__ - Step 49419: {'lr': 0.0003836967206050138, 'samples': 9488448, 'steps': 49418, 'loss/train': 1.4495447874069214} 08/30/2021 22:09:53 - INFO - __main__ - Step 49420: {'lr': 0.0003836922364450325, 'samples': 9488640, 'steps': 49419, 'loss/train': 1.8584849834442139} 08/30/2021 22:09:53 - INFO - __main__ - Step 49421: {'lr': 0.0003836877522248114, 'samples': 9488832, 'steps': 49420, 'loss/train': 1.1529241800308228} 08/30/2021 22:09:54 - INFO - __main__ - Step 49422: {'lr': 0.0003836832679443527, 'samples': 9489024, 'steps': 49421, 'loss/train': 1.2306180000305176} 08/30/2021 22:09:56 - INFO - __main__ - Step 49423: {'lr': 0.00038367878360365845, 'samples': 9489216, 'steps': 49422, 'loss/train': 1.336978554725647} 08/30/2021 22:09:56 - INFO - __main__ - Step 49424: {'lr': 0.00038367429920273054, 'samples': 9489408, 'steps': 49423, 'loss/train': 0.7112210392951965} 08/30/2021 22:09:56 - INFO - __main__ - Step 49425: {'lr': 0.00038366981474157114, 'samples': 9489600, 'steps': 49424, 'loss/train': 1.4397872686386108} 08/30/2021 22:09:57 - INFO - __main__ - Step 49426: {'lr': 0.00038366533022018214, 'samples': 9489792, 'steps': 49425, 'loss/train': 1.533323884010315} 08/30/2021 22:09:57 - INFO - __main__ - Step 49427: {'lr': 0.0003836608456385655, 'samples': 9489984, 'steps': 49426, 'loss/train': 1.4056570529937744} 08/30/2021 22:09:59 - INFO - __main__ - Step 49428: {'lr': 0.00038365636099672347, 'samples': 9490176, 'steps': 49427, 'loss/train': 1.6726080179214478} 08/30/2021 22:09:59 - INFO - __main__ - Step 49429: {'lr': 0.0003836518762946579, 'samples': 9490368, 'steps': 49428, 'loss/train': 1.3833744525909424} 08/30/2021 22:09:59 - INFO - __main__ - Step 49430: {'lr': 0.0003836473915323709, 'samples': 9490560, 'steps': 49429, 'loss/train': 1.5137934684753418} 08/30/2021 22:10:00 - INFO - __main__ - Step 49431: {'lr': 0.0003836429067098645, 'samples': 9490752, 'steps': 49430, 'loss/train': 0.8328871130943298} 08/30/2021 22:10:00 - INFO - __main__ - Step 49432: {'lr': 0.0003836384218271405, 'samples': 9490944, 'steps': 49431, 'loss/train': 1.5596773624420166} 08/30/2021 22:10:02 - INFO - __main__ - Step 49433: {'lr': 0.00038363393688420116, 'samples': 9491136, 'steps': 49432, 'loss/train': 1.1320542097091675} 08/30/2021 22:10:02 - INFO - __main__ - Step 49434: {'lr': 0.0003836294518810485, 'samples': 9491328, 'steps': 49433, 'loss/train': 1.5863744020462036} 08/30/2021 22:10:02 - INFO - __main__ - Step 49435: {'lr': 0.00038362496681768434, 'samples': 9491520, 'steps': 49434, 'loss/train': 1.1333986520767212} 08/30/2021 22:10:03 - INFO - __main__ - Step 49436: {'lr': 0.0003836204816941109, 'samples': 9491712, 'steps': 49435, 'loss/train': 1.4573496580123901} 08/30/2021 22:10:03 - INFO - __main__ - Step 49437: {'lr': 0.0003836159965103301, 'samples': 9491904, 'steps': 49436, 'loss/train': 1.6631131172180176} 08/30/2021 22:10:05 - INFO - __main__ - Step 49438: {'lr': 0.0003836115112663441, 'samples': 9492096, 'steps': 49437, 'loss/train': 1.154723882675171} 08/30/2021 22:10:05 - INFO - __main__ - Step 49439: {'lr': 0.0003836070259621548, 'samples': 9492288, 'steps': 49438, 'loss/train': 1.4596904516220093} 08/30/2021 22:10:06 - INFO - __main__ - Step 49440: {'lr': 0.0003836025405977641, 'samples': 9492480, 'steps': 49439, 'loss/train': 1.4924565553665161} 08/30/2021 22:10:06 - INFO - __main__ - Step 49441: {'lr': 0.00038359805517317427, 'samples': 9492672, 'steps': 49440, 'loss/train': 1.5082950592041016} 08/30/2021 22:10:06 - INFO - __main__ - Step 49442: {'lr': 0.00038359356968838723, 'samples': 9492864, 'steps': 49441, 'loss/train': 1.4074862003326416} 08/30/2021 22:10:07 - INFO - __main__ - Step 49443: {'lr': 0.00038358908414340485, 'samples': 9493056, 'steps': 49442, 'loss/train': 1.6441724300384521} 08/30/2021 22:10:08 - INFO - __main__ - Step 49444: {'lr': 0.0003835845985382294, 'samples': 9493248, 'steps': 49443, 'loss/train': 1.5533626079559326} 08/30/2021 22:10:09 - INFO - __main__ - Step 49445: {'lr': 0.00038358011287286287, 'samples': 9493440, 'steps': 49444, 'loss/train': 1.7546589374542236} 08/30/2021 22:10:09 - INFO - __main__ - Step 49446: {'lr': 0.0003835756271473071, 'samples': 9493632, 'steps': 49445, 'loss/train': 1.1725339889526367} 08/30/2021 22:10:09 - INFO - __main__ - Step 49447: {'lr': 0.0003835711413615642, 'samples': 9493824, 'steps': 49446, 'loss/train': 0.717629075050354} 08/30/2021 22:10:10 - INFO - __main__ - Step 49448: {'lr': 0.0003835666555156362, 'samples': 9494016, 'steps': 49447, 'loss/train': 2.4399120807647705} 08/30/2021 22:10:11 - INFO - __main__ - Step 49449: {'lr': 0.00038356216960952515, 'samples': 9494208, 'steps': 49448, 'loss/train': 1.2204011678695679} 08/30/2021 22:10:12 - INFO - __main__ - Step 49450: {'lr': 0.0003835576836432331, 'samples': 9494400, 'steps': 49449, 'loss/train': 1.36895751953125} 08/30/2021 22:10:12 - INFO - __main__ - Step 49451: {'lr': 0.000383553197616762, 'samples': 9494592, 'steps': 49450, 'loss/train': 1.116050124168396} 08/30/2021 22:10:13 - INFO - __main__ - Step 49452: {'lr': 0.00038354871153011385, 'samples': 9494784, 'steps': 49451, 'loss/train': 1.5069406032562256} 08/30/2021 22:10:13 - INFO - __main__ - Step 49453: {'lr': 0.0003835442253832907, 'samples': 9494976, 'steps': 49452, 'loss/train': 0.8713278770446777} 08/30/2021 22:10:14 - INFO - __main__ - Step 49454: {'lr': 0.00038353973917629457, 'samples': 9495168, 'steps': 49453, 'loss/train': 0.7570756077766418} 08/30/2021 22:10:15 - INFO - __main__ - Step 49455: {'lr': 0.0003835352529091275, 'samples': 9495360, 'steps': 49454, 'loss/train': 1.2459245920181274} 08/30/2021 22:10:15 - INFO - __main__ - Step 49456: {'lr': 0.0003835307665817915, 'samples': 9495552, 'steps': 49455, 'loss/train': 0.1712222546339035} 08/30/2021 22:10:15 - INFO - __main__ - Step 49457: {'lr': 0.0003835262801942887, 'samples': 9495744, 'steps': 49456, 'loss/train': 1.789059042930603} 08/30/2021 22:10:16 - INFO - __main__ - Step 49458: {'lr': 0.000383521793746621, 'samples': 9495936, 'steps': 49457, 'loss/train': 1.8182224035263062} 08/30/2021 22:10:17 - INFO - __main__ - Step 49459: {'lr': 0.00038351730723879034, 'samples': 9496128, 'steps': 49458, 'loss/train': 1.7775760889053345} 08/30/2021 22:10:18 - INFO - __main__ - Step 49460: {'lr': 0.0003835128206707989, 'samples': 9496320, 'steps': 49459, 'loss/train': 1.4985154867172241} 08/30/2021 22:10:18 - INFO - __main__ - Step 49461: {'lr': 0.00038350833404264865, 'samples': 9496512, 'steps': 49460, 'loss/train': 1.3443094491958618} 08/30/2021 22:10:19 - INFO - __main__ - Step 49462: {'lr': 0.0003835038473543416, 'samples': 9496704, 'steps': 49461, 'loss/train': 0.8598469495773315} 08/30/2021 22:10:19 - INFO - __main__ - Step 49463: {'lr': 0.0003834993606058798, 'samples': 9496896, 'steps': 49462, 'loss/train': 0.36771276593208313} 08/30/2021 22:10:21 - INFO - __main__ - Step 49464: {'lr': 0.00038349487379726513, 'samples': 9497088, 'steps': 49463, 'loss/train': 1.5126025676727295} 08/30/2021 22:10:21 - INFO - __main__ - Step 49465: {'lr': 0.0003834903869284999, 'samples': 9497280, 'steps': 49464, 'loss/train': 1.4187909364700317} 08/30/2021 22:10:22 - INFO - __main__ - Step 49466: {'lr': 0.00038348589999958585, 'samples': 9497472, 'steps': 49465, 'loss/train': 1.547430157661438} 08/30/2021 22:10:22 - INFO - __main__ - Step 49467: {'lr': 0.00038348141301052505, 'samples': 9497664, 'steps': 49466, 'loss/train': 1.3662631511688232} 08/30/2021 22:10:22 - INFO - __main__ - Step 49468: {'lr': 0.00038347692596131977, 'samples': 9497856, 'steps': 49467, 'loss/train': 0.1770838499069214} 08/30/2021 22:10:23 - INFO - __main__ - Step 49469: {'lr': 0.0003834724388519717, 'samples': 9498048, 'steps': 49468, 'loss/train': 0.22132369875907898} 08/30/2021 22:10:24 - INFO - __main__ - Step 49470: {'lr': 0.00038346795168248306, 'samples': 9498240, 'steps': 49469, 'loss/train': 1.1906710863113403} 08/30/2021 22:10:25 - INFO - __main__ - Step 49471: {'lr': 0.00038346346445285585, 'samples': 9498432, 'steps': 49470, 'loss/train': 1.5501283407211304} 08/30/2021 22:10:25 - INFO - __main__ - Step 49472: {'lr': 0.0003834589771630921, 'samples': 9498624, 'steps': 49471, 'loss/train': 1.5011506080627441} 08/30/2021 22:10:25 - INFO - __main__ - Step 49473: {'lr': 0.0003834544898131936, 'samples': 9498816, 'steps': 49472, 'loss/train': 1.8528144359588623} 08/30/2021 22:10:26 - INFO - __main__ - Step 49474: {'lr': 0.00038345000240316276, 'samples': 9499008, 'steps': 49473, 'loss/train': 1.3612840175628662} 08/30/2021 22:10:27 - INFO - __main__ - Step 49475: {'lr': 0.00038344551493300135, 'samples': 9499200, 'steps': 49474, 'loss/train': 1.6891896724700928} 08/30/2021 22:10:27 - INFO - __main__ - Step 49476: {'lr': 0.00038344102740271144, 'samples': 9499392, 'steps': 49475, 'loss/train': 0.7574342489242554} 08/30/2021 22:10:28 - INFO - __main__ - Step 49477: {'lr': 0.00038343653981229504, 'samples': 9499584, 'steps': 49476, 'loss/train': 1.5855237245559692} 08/30/2021 22:10:28 - INFO - __main__ - Step 49478: {'lr': 0.00038343205216175426, 'samples': 9499776, 'steps': 49477, 'loss/train': 0.7812578082084656} 08/30/2021 22:10:28 - INFO - __main__ - Step 49479: {'lr': 0.000383427564451091, 'samples': 9499968, 'steps': 49478, 'loss/train': 1.486604928970337} 08/30/2021 22:10:30 - INFO - __main__ - Step 49480: {'lr': 0.00038342307668030737, 'samples': 9500160, 'steps': 49479, 'loss/train': 1.6912150382995605} 08/30/2021 22:10:31 - INFO - __main__ - Step 49481: {'lr': 0.0003834185888494053, 'samples': 9500352, 'steps': 49480, 'loss/train': 0.8896346092224121} 08/30/2021 22:10:31 - INFO - __main__ - Step 49482: {'lr': 0.00038341410095838694, 'samples': 9500544, 'steps': 49481, 'loss/train': 1.469557285308838} 08/30/2021 22:10:32 - INFO - __main__ - Step 49483: {'lr': 0.0003834096130072542, 'samples': 9500736, 'steps': 49482, 'loss/train': 0.09400922805070877} 08/30/2021 22:10:32 - INFO - __main__ - Step 49484: {'lr': 0.00038340512499600917, 'samples': 9500928, 'steps': 49483, 'loss/train': 0.7293932437896729} 08/30/2021 22:10:34 - INFO - __main__ - Step 49485: {'lr': 0.00038340063692465386, 'samples': 9501120, 'steps': 49484, 'loss/train': 0.972122311592102} 08/30/2021 22:10:34 - INFO - __main__ - Step 49486: {'lr': 0.00038339614879319027, 'samples': 9501312, 'steps': 49485, 'loss/train': 1.702094554901123} 08/30/2021 22:10:34 - INFO - __main__ - Step 49487: {'lr': 0.00038339166060162046, 'samples': 9501504, 'steps': 49486, 'loss/train': 0.8908302187919617} 08/30/2021 22:10:35 - INFO - __main__ - Step 49488: {'lr': 0.00038338717234994633, 'samples': 9501696, 'steps': 49487, 'loss/train': 1.3802777528762817} 08/30/2021 22:10:35 - INFO - __main__ - Step 49489: {'lr': 0.0003833826840381701, 'samples': 9501888, 'steps': 49488, 'loss/train': 0.2174101173877716} 08/30/2021 22:10:36 - INFO - __main__ - Step 49490: {'lr': 0.00038337819566629363, 'samples': 9502080, 'steps': 49489, 'loss/train': 0.3199485242366791} 08/30/2021 22:10:37 - INFO - __main__ - Step 49491: {'lr': 0.000383373707234319, 'samples': 9502272, 'steps': 49490, 'loss/train': 1.3139634132385254} 08/30/2021 22:10:37 - INFO - __main__ - Step 49492: {'lr': 0.0003833692187422483, 'samples': 9502464, 'steps': 49491, 'loss/train': 1.0583555698394775} 08/30/2021 22:10:38 - INFO - __main__ - Step 49493: {'lr': 0.0003833647301900835, 'samples': 9502656, 'steps': 49492, 'loss/train': 1.6221011877059937} 08/30/2021 22:10:38 - INFO - __main__ - Step 49494: {'lr': 0.00038336024157782655, 'samples': 9502848, 'steps': 49493, 'loss/train': 1.476187825202942} 08/30/2021 22:10:39 - INFO - __main__ - Step 49495: {'lr': 0.00038335575290547954, 'samples': 9503040, 'steps': 49494, 'loss/train': 1.7007817029953003} 08/30/2021 22:10:40 - INFO - __main__ - Step 49496: {'lr': 0.0003833512641730445, 'samples': 9503232, 'steps': 49495, 'loss/train': 1.1251637935638428} 08/30/2021 22:10:40 - INFO - __main__ - Step 49497: {'lr': 0.0003833467753805234, 'samples': 9503424, 'steps': 49496, 'loss/train': 1.5556890964508057} 08/30/2021 22:10:41 - INFO - __main__ - Step 49498: {'lr': 0.00038334228652791837, 'samples': 9503616, 'steps': 49497, 'loss/train': 1.5392955541610718} 08/30/2021 22:10:41 - INFO - __main__ - Step 49499: {'lr': 0.00038333779761523133, 'samples': 9503808, 'steps': 49498, 'loss/train': 1.281488299369812} 08/30/2021 22:10:42 - INFO - __main__ - Step 49500: {'lr': 0.0003833333086424643, 'samples': 9504000, 'steps': 49499, 'loss/train': 1.2796951532363892} 08/30/2021 22:10:43 - INFO - __main__ - Step 49501: {'lr': 0.00038332881960961943, 'samples': 9504192, 'steps': 49500, 'loss/train': 1.130244255065918} 08/30/2021 22:10:43 - INFO - __main__ - Step 49502: {'lr': 0.0003833243305166986, 'samples': 9504384, 'steps': 49501, 'loss/train': 1.5526087284088135} 08/30/2021 22:10:43 - INFO - __main__ - Step 49503: {'lr': 0.00038331984136370377, 'samples': 9504576, 'steps': 49502, 'loss/train': 1.8512752056121826} 08/30/2021 22:10:44 - INFO - __main__ - Step 49504: {'lr': 0.0003833153521506372, 'samples': 9504768, 'steps': 49503, 'loss/train': 1.1084262132644653} 08/30/2021 22:10:45 - INFO - __main__ - Step 49505: {'lr': 0.00038331086287750083, 'samples': 9504960, 'steps': 49504, 'loss/train': 0.960732102394104} 08/30/2021 22:10:46 - INFO - __main__ - Step 49506: {'lr': 0.0003833063735442966, 'samples': 9505152, 'steps': 49505, 'loss/train': 1.3818302154541016} 08/30/2021 22:10:46 - INFO - __main__ - Step 49507: {'lr': 0.0003833018841510265, 'samples': 9505344, 'steps': 49506, 'loss/train': 1.2723408937454224} 08/30/2021 22:10:46 - INFO - __main__ - Step 49508: {'lr': 0.00038329739469769277, 'samples': 9505536, 'steps': 49507, 'loss/train': 0.9524272084236145} 08/30/2021 22:10:47 - INFO - __main__ - Step 49509: {'lr': 0.0003832929051842972, 'samples': 9505728, 'steps': 49508, 'loss/train': 1.4414458274841309} 08/30/2021 22:10:48 - INFO - __main__ - Step 49510: {'lr': 0.0003832884156108418, 'samples': 9505920, 'steps': 49509, 'loss/train': 1.0479592084884644} 08/30/2021 22:10:49 - INFO - __main__ - Step 49511: {'lr': 0.0003832839259773289, 'samples': 9506112, 'steps': 49510, 'loss/train': 1.2010400295257568} 08/30/2021 22:10:49 - INFO - __main__ - Step 49512: {'lr': 0.00038327943628376025, 'samples': 9506304, 'steps': 49511, 'loss/train': 0.9394859671592712} 08/30/2021 22:10:49 - INFO - __main__ - Step 49513: {'lr': 0.00038327494653013787, 'samples': 9506496, 'steps': 49512, 'loss/train': 1.3414398431777954} 08/30/2021 22:10:50 - INFO - __main__ - Step 49514: {'lr': 0.00038327045671646386, 'samples': 9506688, 'steps': 49513, 'loss/train': 1.532314419746399} 08/30/2021 22:10:50 - INFO - __main__ - Step 49515: {'lr': 0.00038326596684274035, 'samples': 9506880, 'steps': 49514, 'loss/train': 1.3462707996368408} 08/30/2021 22:10:52 - INFO - __main__ - Step 49516: {'lr': 0.00038326147690896916, 'samples': 9507072, 'steps': 49515, 'loss/train': 1.6698299646377563} 08/30/2021 22:10:52 - INFO - __main__ - Step 49517: {'lr': 0.00038325698691515247, 'samples': 9507264, 'steps': 49516, 'loss/train': 1.0764703750610352} 08/30/2021 22:10:53 - INFO - __main__ - Step 49518: {'lr': 0.00038325249686129223, 'samples': 9507456, 'steps': 49517, 'loss/train': 1.1404021978378296} 08/30/2021 22:10:53 - INFO - __main__ - Step 49519: {'lr': 0.0003832480067473904, 'samples': 9507648, 'steps': 49518, 'loss/train': 1.0500565767288208} 08/30/2021 22:10:53 - INFO - __main__ - Step 49520: {'lr': 0.0003832435165734491, 'samples': 9507840, 'steps': 49519, 'loss/train': 0.098548024892807} 08/30/2021 22:10:55 - INFO - __main__ - Step 49521: {'lr': 0.0003832390263394704, 'samples': 9508032, 'steps': 49520, 'loss/train': 1.14603853225708} 08/30/2021 22:10:55 - INFO - __main__ - Step 49522: {'lr': 0.0003832345360454561, 'samples': 9508224, 'steps': 49521, 'loss/train': 1.502983570098877} 08/30/2021 22:10:56 - INFO - __main__ - Step 49523: {'lr': 0.00038323004569140853, 'samples': 9508416, 'steps': 49522, 'loss/train': 0.08808526396751404} 08/30/2021 22:10:56 - INFO - __main__ - Step 49524: {'lr': 0.0003832255552773295, 'samples': 9508608, 'steps': 49523, 'loss/train': 0.9545467495918274} 08/30/2021 22:10:56 - INFO - __main__ - Step 49525: {'lr': 0.00038322106480322105, 'samples': 9508800, 'steps': 49524, 'loss/train': 1.339537262916565} 08/30/2021 22:10:58 - INFO - __main__ - Step 49526: {'lr': 0.00038321657426908527, 'samples': 9508992, 'steps': 49525, 'loss/train': 1.5905567407608032} 08/30/2021 22:10:58 - INFO - __main__ - Step 49527: {'lr': 0.0003832120836749242, 'samples': 9509184, 'steps': 49526, 'loss/train': 3.320098638534546} 08/30/2021 22:10:59 - INFO - __main__ - Step 49528: {'lr': 0.0003832075930207398, 'samples': 9509376, 'steps': 49527, 'loss/train': 0.9618931412696838} 08/30/2021 22:10:59 - INFO - __main__ - Step 49529: {'lr': 0.0003832031023065341, 'samples': 9509568, 'steps': 49528, 'loss/train': 1.247646450996399} 08/30/2021 22:11:00 - INFO - __main__ - Step 49530: {'lr': 0.0003831986115323092, 'samples': 9509760, 'steps': 49529, 'loss/train': 0.8380870223045349} 08/30/2021 22:11:02 - INFO - __main__ - Step 49531: {'lr': 0.00038319412069806694, 'samples': 9509952, 'steps': 49530, 'loss/train': 1.433803915977478} 08/30/2021 22:11:02 - INFO - __main__ - Step 49532: {'lr': 0.00038318962980380956, 'samples': 9510144, 'steps': 49531, 'loss/train': 1.0234384536743164} 08/30/2021 22:11:02 - INFO - __main__ - Step 49533: {'lr': 0.0003831851388495389, 'samples': 9510336, 'steps': 49532, 'loss/train': 0.9962560534477234} 08/30/2021 22:11:03 - INFO - __main__ - Step 49534: {'lr': 0.0003831806478352572, 'samples': 9510528, 'steps': 49533, 'loss/train': 1.8146426677703857} 08/30/2021 22:11:03 - INFO - __main__ - Step 49535: {'lr': 0.00038317615676096623, 'samples': 9510720, 'steps': 49534, 'loss/train': 1.069488525390625} 08/30/2021 22:11:05 - INFO - __main__ - Step 49536: {'lr': 0.00038317166562666817, 'samples': 9510912, 'steps': 49535, 'loss/train': 2.022279977798462} 08/30/2021 22:11:05 - INFO - __main__ - Step 49537: {'lr': 0.00038316717443236505, 'samples': 9511104, 'steps': 49536, 'loss/train': 1.5333529710769653} 08/30/2021 22:11:06 - INFO - __main__ - Step 49538: {'lr': 0.0003831626831780588, 'samples': 9511296, 'steps': 49537, 'loss/train': 1.7128392457962036} 08/30/2021 22:11:06 - INFO - __main__ - Step 49539: {'lr': 0.0003831581918637516, 'samples': 9511488, 'steps': 49538, 'loss/train': 1.4405306577682495} 08/30/2021 22:11:06 - INFO - __main__ - Step 49540: {'lr': 0.0003831537004894453, 'samples': 9511680, 'steps': 49539, 'loss/train': 0.8412823677062988} 08/30/2021 22:11:07 - INFO - __main__ - Step 49541: {'lr': 0.000383149209055142, 'samples': 9511872, 'steps': 49540, 'loss/train': 1.2243174314498901} 08/30/2021 22:11:08 - INFO - __main__ - Step 49542: {'lr': 0.00038314471756084373, 'samples': 9512064, 'steps': 49541, 'loss/train': 1.3091679811477661} 08/30/2021 22:11:09 - INFO - __main__ - Step 49543: {'lr': 0.0003831402260065525, 'samples': 9512256, 'steps': 49542, 'loss/train': 0.5797540545463562} 08/30/2021 22:11:09 - INFO - __main__ - Step 49544: {'lr': 0.00038313573439227035, 'samples': 9512448, 'steps': 49543, 'loss/train': 1.5811721086502075} 08/30/2021 22:11:09 - INFO - __main__ - Step 49545: {'lr': 0.0003831312427179993, 'samples': 9512640, 'steps': 49544, 'loss/train': 0.9819427132606506} 08/30/2021 22:11:10 - INFO - __main__ - Step 49546: {'lr': 0.00038312675098374136, 'samples': 9512832, 'steps': 49545, 'loss/train': 0.9778226017951965} 08/30/2021 22:11:11 - INFO - __main__ - Step 49547: {'lr': 0.0003831222591894985, 'samples': 9513024, 'steps': 49546, 'loss/train': 1.5419055223464966} 08/30/2021 22:11:12 - INFO - __main__ - Step 49548: {'lr': 0.0003831177673352729, 'samples': 9513216, 'steps': 49547, 'loss/train': 0.6110632419586182} 08/30/2021 22:11:12 - INFO - __main__ - Step 49549: {'lr': 0.00038311327542106646, 'samples': 9513408, 'steps': 49548, 'loss/train': 1.0220229625701904} 08/30/2021 22:11:13 - INFO - __main__ - Step 49550: {'lr': 0.00038310878344688116, 'samples': 9513600, 'steps': 49549, 'loss/train': 1.3049097061157227} 08/30/2021 22:11:13 - INFO - __main__ - Step 49551: {'lr': 0.0003831042914127192, 'samples': 9513792, 'steps': 49550, 'loss/train': 0.6687270402908325} 08/30/2021 22:11:14 - INFO - __main__ - Step 49552: {'lr': 0.00038309979931858243, 'samples': 9513984, 'steps': 49551, 'loss/train': 1.1881481409072876} 08/30/2021 22:11:15 - INFO - __main__ - Step 49553: {'lr': 0.00038309530716447297, 'samples': 9514176, 'steps': 49552, 'loss/train': 1.430482029914856} 08/30/2021 22:11:15 - INFO - __main__ - Step 49554: {'lr': 0.00038309081495039275, 'samples': 9514368, 'steps': 49553, 'loss/train': 1.108932375907898} 08/30/2021 22:11:16 - INFO - __main__ - Step 49555: {'lr': 0.00038308632267634396, 'samples': 9514560, 'steps': 49554, 'loss/train': 1.0717090368270874} 08/30/2021 22:11:16 - INFO - __main__ - Step 49556: {'lr': 0.00038308183034232844, 'samples': 9514752, 'steps': 49555, 'loss/train': 1.1739131212234497} 08/30/2021 22:11:17 - INFO - __main__ - Step 49557: {'lr': 0.0003830773379483484, 'samples': 9514944, 'steps': 49556, 'loss/train': 1.8572793006896973} 08/30/2021 22:11:18 - INFO - __main__ - Step 49558: {'lr': 0.0003830728454944057, 'samples': 9515136, 'steps': 49557, 'loss/train': 0.8058309555053711} 08/30/2021 22:11:18 - INFO - __main__ - Step 49559: {'lr': 0.00038306835298050255, 'samples': 9515328, 'steps': 49558, 'loss/train': 1.7848989963531494} 08/30/2021 22:11:18 - INFO - __main__ - Step 49560: {'lr': 0.0003830638604066407, 'samples': 9515520, 'steps': 49559, 'loss/train': 1.4342689514160156} 08/30/2021 22:11:19 - INFO - __main__ - Step 49561: {'lr': 0.00038305936777282233, 'samples': 9515712, 'steps': 49560, 'loss/train': 1.6363073587417603} 08/30/2021 22:11:20 - INFO - __main__ - Step 49562: {'lr': 0.00038305487507904956, 'samples': 9515904, 'steps': 49561, 'loss/train': 1.8470708131790161} 08/30/2021 22:11:21 - INFO - __main__ - Step 49563: {'lr': 0.0003830503823253243, 'samples': 9516096, 'steps': 49562, 'loss/train': 1.5975967645645142} 08/30/2021 22:11:21 - INFO - __main__ - Step 49564: {'lr': 0.0003830458895116485, 'samples': 9516288, 'steps': 49563, 'loss/train': 1.101426362991333} 08/30/2021 22:11:21 - INFO - __main__ - Step 49565: {'lr': 0.0003830413966380243, 'samples': 9516480, 'steps': 49564, 'loss/train': 1.2336184978485107} 08/30/2021 22:11:22 - INFO - __main__ - Step 49566: {'lr': 0.00038303690370445384, 'samples': 9516672, 'steps': 49565, 'loss/train': 1.0507433414459229} 08/30/2021 22:11:23 - INFO - __main__ - Step 49567: {'lr': 0.00038303241071093884, 'samples': 9516864, 'steps': 49566, 'loss/train': 1.242356300354004} 08/30/2021 22:11:24 - INFO - __main__ - Step 49568: {'lr': 0.00038302791765748156, 'samples': 9517056, 'steps': 49567, 'loss/train': 1.2988349199295044} 08/30/2021 22:11:24 - INFO - __main__ - Step 49569: {'lr': 0.0003830234245440839, 'samples': 9517248, 'steps': 49568, 'loss/train': 2.0660808086395264} 08/30/2021 22:11:24 - INFO - __main__ - Step 49570: {'lr': 0.000383018931370748, 'samples': 9517440, 'steps': 49569, 'loss/train': 1.0381982326507568} 08/30/2021 22:11:25 - INFO - __main__ - Step 49571: {'lr': 0.00038301443813747583, 'samples': 9517632, 'steps': 49570, 'loss/train': 1.5061399936676025} 08/30/2021 22:11:25 - INFO - __main__ - Step 49572: {'lr': 0.00038300994484426936, 'samples': 9517824, 'steps': 49571, 'loss/train': 1.7023953199386597} 08/30/2021 22:11:27 - INFO - __main__ - Step 49573: {'lr': 0.0003830054514911307, 'samples': 9518016, 'steps': 49572, 'loss/train': 1.211342215538025} 08/30/2021 22:11:28 - INFO - __main__ - Step 49574: {'lr': 0.0003830009580780618, 'samples': 9518208, 'steps': 49573, 'loss/train': 0.4964197874069214} 08/30/2021 22:11:28 - INFO - __main__ - Step 49575: {'lr': 0.00038299646460506474, 'samples': 9518400, 'steps': 49574, 'loss/train': 1.1801362037658691} 08/30/2021 22:11:29 - INFO - __main__ - Step 49576: {'lr': 0.0003829919710721415, 'samples': 9518592, 'steps': 49575, 'loss/train': 1.0538371801376343} 08/30/2021 22:11:29 - INFO - __main__ - Step 49577: {'lr': 0.0003829874774792941, 'samples': 9518784, 'steps': 49576, 'loss/train': 1.0418047904968262} 08/30/2021 22:11:31 - INFO - __main__ - Step 49578: {'lr': 0.00038298298382652467, 'samples': 9518976, 'steps': 49577, 'loss/train': 1.5571428537368774} 08/30/2021 22:11:31 - INFO - __main__ - Step 49579: {'lr': 0.00038297849011383517, 'samples': 9519168, 'steps': 49578, 'loss/train': 0.24694758653640747} 08/30/2021 22:11:31 - INFO - __main__ - Step 49580: {'lr': 0.0003829739963412276, 'samples': 9519360, 'steps': 49579, 'loss/train': 1.2840710878372192} 08/30/2021 22:11:32 - INFO - __main__ - Step 49581: {'lr': 0.000382969502508704, 'samples': 9519552, 'steps': 49580, 'loss/train': 1.3830649852752686} 08/30/2021 22:11:32 - INFO - __main__ - Step 49582: {'lr': 0.0003829650086162663, 'samples': 9519744, 'steps': 49581, 'loss/train': 1.7510303258895874} 08/30/2021 22:11:32 - INFO - __main__ - Step 49583: {'lr': 0.0003829605146639167, 'samples': 9519936, 'steps': 49582, 'loss/train': 2.331678628921509} 08/30/2021 22:11:35 - INFO - __main__ - Step 49584: {'lr': 0.00038295602065165714, 'samples': 9520128, 'steps': 49583, 'loss/train': 1.3477237224578857} 08/30/2021 22:11:35 - INFO - __main__ - Step 49585: {'lr': 0.0003829515265794896, 'samples': 9520320, 'steps': 49584, 'loss/train': 1.3703932762145996} 08/30/2021 22:11:35 - INFO - __main__ - Step 49586: {'lr': 0.00038294703244741625, 'samples': 9520512, 'steps': 49585, 'loss/train': 0.8562800884246826} 08/30/2021 22:11:36 - INFO - __main__ - Step 49587: {'lr': 0.000382942538255439, 'samples': 9520704, 'steps': 49586, 'loss/train': 1.125615119934082} 08/30/2021 22:11:36 - INFO - __main__ - Step 49588: {'lr': 0.0003829380440035598, 'samples': 9520896, 'steps': 49587, 'loss/train': 1.6854792833328247} 08/30/2021 22:11:38 - INFO - __main__ - Step 49589: {'lr': 0.0003829335496917808, 'samples': 9521088, 'steps': 49588, 'loss/train': 1.639472484588623} 08/30/2021 22:11:38 - INFO - __main__ - Step 49590: {'lr': 0.000382929055320104, 'samples': 9521280, 'steps': 49589, 'loss/train': 1.0702298879623413} 08/30/2021 22:11:38 - INFO - __main__ - Step 49591: {'lr': 0.0003829245608885315, 'samples': 9521472, 'steps': 49590, 'loss/train': 0.6162208914756775} 08/30/2021 22:11:39 - INFO - __main__ - Step 49592: {'lr': 0.0003829200663970652, 'samples': 9521664, 'steps': 49591, 'loss/train': 1.1267777681350708} 08/30/2021 22:11:39 - INFO - __main__ - Step 49593: {'lr': 0.00038291557184570713, 'samples': 9521856, 'steps': 49592, 'loss/train': 1.9720985889434814} 08/30/2021 22:11:41 - INFO - __main__ - Step 49594: {'lr': 0.0003829110772344594, 'samples': 9522048, 'steps': 49593, 'loss/train': 0.8776063919067383} 08/30/2021 22:11:41 - INFO - __main__ - Step 49595: {'lr': 0.000382906582563324, 'samples': 9522240, 'steps': 49594, 'loss/train': 0.8313174247741699} 08/30/2021 22:11:41 - INFO - __main__ - Step 49596: {'lr': 0.00038290208783230286, 'samples': 9522432, 'steps': 49595, 'loss/train': 0.8462598323822021} 08/30/2021 22:11:42 - INFO - __main__ - Step 49597: {'lr': 0.00038289759304139815, 'samples': 9522624, 'steps': 49596, 'loss/train': 1.3606739044189453} 08/30/2021 22:11:42 - INFO - __main__ - Step 49598: {'lr': 0.0003828930981906118, 'samples': 9522816, 'steps': 49597, 'loss/train': 0.4701923727989197} 08/30/2021 22:11:44 - INFO - __main__ - Step 49599: {'lr': 0.000382888603279946, 'samples': 9523008, 'steps': 49598, 'loss/train': 1.1950565576553345} 08/30/2021 22:11:44 - INFO - __main__ - Step 49600: {'lr': 0.00038288410830940246, 'samples': 9523200, 'steps': 49599, 'loss/train': 0.8796842694282532} 08/30/2021 22:11:45 - INFO - __main__ - Step 49601: {'lr': 0.00038287961327898346, 'samples': 9523392, 'steps': 49600, 'loss/train': 1.0335707664489746} 08/30/2021 22:11:45 - INFO - __main__ - Step 49602: {'lr': 0.000382875118188691, 'samples': 9523584, 'steps': 49601, 'loss/train': 0.765018880367279} 08/30/2021 22:11:45 - INFO - __main__ - Step 49603: {'lr': 0.000382870623038527, 'samples': 9523776, 'steps': 49602, 'loss/train': 1.7459690570831299} 08/30/2021 22:11:47 - INFO - __main__ - Step 49604: {'lr': 0.0003828661278284936, 'samples': 9523968, 'steps': 49603, 'loss/train': 0.6471412181854248} 08/30/2021 22:11:47 - INFO - __main__ - Step 49605: {'lr': 0.00038286163255859276, 'samples': 9524160, 'steps': 49604, 'loss/train': 1.786392331123352} 08/30/2021 22:11:48 - INFO - __main__ - Step 49606: {'lr': 0.0003828571372288265, 'samples': 9524352, 'steps': 49605, 'loss/train': 1.6381694078445435} 08/30/2021 22:11:48 - INFO - __main__ - Step 49607: {'lr': 0.00038285264183919696, 'samples': 9524544, 'steps': 49606, 'loss/train': 2.197564125061035} 08/30/2021 22:11:48 - INFO - __main__ - Step 49608: {'lr': 0.00038284814638970594, 'samples': 9524736, 'steps': 49607, 'loss/train': 1.5324078798294067} 08/30/2021 22:11:50 - INFO - __main__ - Step 49609: {'lr': 0.00038284365088035564, 'samples': 9524928, 'steps': 49608, 'loss/train': 1.219322681427002} 08/30/2021 22:11:50 - INFO - __main__ - Step 49610: {'lr': 0.00038283915531114806, 'samples': 9525120, 'steps': 49609, 'loss/train': 1.273169755935669} 08/30/2021 22:11:51 - INFO - __main__ - Step 49611: {'lr': 0.0003828346596820852, 'samples': 9525312, 'steps': 49610, 'loss/train': 1.4314746856689453} 08/30/2021 22:11:51 - INFO - __main__ - Step 49612: {'lr': 0.00038283016399316905, 'samples': 9525504, 'steps': 49611, 'loss/train': 2.4046475887298584} 08/30/2021 22:11:51 - INFO - __main__ - Step 49613: {'lr': 0.00038282566824440176, 'samples': 9525696, 'steps': 49612, 'loss/train': 0.26548632979393005} 08/30/2021 22:11:52 - INFO - __main__ - Step 49614: {'lr': 0.0003828211724357852, 'samples': 9525888, 'steps': 49613, 'loss/train': 1.704612135887146} 08/30/2021 22:11:53 - INFO - __main__ - Step 49615: {'lr': 0.00038281667656732144, 'samples': 9526080, 'steps': 49614, 'loss/train': 0.39868637919425964} 08/30/2021 22:11:54 - INFO - __main__ - Step 49616: {'lr': 0.0003828121806390126, 'samples': 9526272, 'steps': 49615, 'loss/train': 1.5058345794677734} 08/30/2021 22:11:54 - INFO - __main__ - Step 49617: {'lr': 0.0003828076846508606, 'samples': 9526464, 'steps': 49616, 'loss/train': 1.2298740148544312} 08/30/2021 22:11:55 - INFO - __main__ - Step 49618: {'lr': 0.00038280318860286756, 'samples': 9526656, 'steps': 49617, 'loss/train': 1.2124298810958862} 08/30/2021 22:11:55 - INFO - __main__ - Step 49619: {'lr': 0.0003827986924950354, 'samples': 9526848, 'steps': 49618, 'loss/train': 1.8423925638198853} 08/30/2021 22:11:57 - INFO - __main__ - Step 49620: {'lr': 0.0003827941963273663, 'samples': 9527040, 'steps': 49619, 'loss/train': 0.8608068227767944} 08/30/2021 22:11:57 - INFO - __main__ - Step 49621: {'lr': 0.00038278970009986206, 'samples': 9527232, 'steps': 49620, 'loss/train': 1.0913867950439453} 08/30/2021 22:11:57 - INFO - __main__ - Step 49622: {'lr': 0.0003827852038125249, 'samples': 9527424, 'steps': 49621, 'loss/train': 1.6545668840408325} 08/30/2021 22:11:58 - INFO - __main__ - Step 49623: {'lr': 0.00038278070746535674, 'samples': 9527616, 'steps': 49622, 'loss/train': 1.1301075220108032} 08/30/2021 22:11:58 - INFO - __main__ - Step 49624: {'lr': 0.0003827762110583597, 'samples': 9527808, 'steps': 49623, 'loss/train': 0.03578347712755203} 08/30/2021 22:12:00 - INFO - __main__ - Step 49625: {'lr': 0.0003827717145915357, 'samples': 9528000, 'steps': 49624, 'loss/train': 2.1218557357788086} 08/30/2021 22:12:00 - INFO - __main__ - Step 49626: {'lr': 0.0003827672180648868, 'samples': 9528192, 'steps': 49625, 'loss/train': 1.7013319730758667} 08/30/2021 22:12:00 - INFO - __main__ - Step 49627: {'lr': 0.0003827627214784151, 'samples': 9528384, 'steps': 49626, 'loss/train': 0.7905079126358032} 08/30/2021 22:12:01 - INFO - __main__ - Step 49628: {'lr': 0.0003827582248321225, 'samples': 9528576, 'steps': 49627, 'loss/train': 1.1278719902038574} 08/30/2021 22:12:01 - INFO - __main__ - Step 49629: {'lr': 0.0003827537281260111, 'samples': 9528768, 'steps': 49628, 'loss/train': 0.26504695415496826} 08/30/2021 22:12:03 - INFO - __main__ - Step 49630: {'lr': 0.00038274923136008294, 'samples': 9528960, 'steps': 49629, 'loss/train': 1.3159563541412354} 08/30/2021 22:12:03 - INFO - __main__ - Step 49631: {'lr': 0.00038274473453434, 'samples': 9529152, 'steps': 49630, 'loss/train': 1.014441967010498} 08/30/2021 22:12:03 - INFO - __main__ - Step 49632: {'lr': 0.0003827402376487844, 'samples': 9529344, 'steps': 49631, 'loss/train': 1.3989652395248413} 08/30/2021 22:12:04 - INFO - __main__ - Step 49633: {'lr': 0.0003827357407034181, 'samples': 9529536, 'steps': 49632, 'loss/train': 1.4955639839172363} 08/30/2021 22:12:04 - INFO - __main__ - Step 49634: {'lr': 0.00038273124369824304, 'samples': 9529728, 'steps': 49633, 'loss/train': 1.5302200317382812} 08/30/2021 22:12:05 - INFO - __main__ - Step 49635: {'lr': 0.00038272674663326136, 'samples': 9529920, 'steps': 49634, 'loss/train': 1.4749906063079834} 08/30/2021 22:12:06 - INFO - __main__ - Step 49636: {'lr': 0.000382722249508475, 'samples': 9530112, 'steps': 49635, 'loss/train': 1.2865924835205078} 08/30/2021 22:12:06 - INFO - __main__ - Step 49637: {'lr': 0.00038271775232388616, 'samples': 9530304, 'steps': 49636, 'loss/train': 1.2680777311325073} 08/30/2021 22:12:07 - INFO - __main__ - Step 49638: {'lr': 0.00038271325507949666, 'samples': 9530496, 'steps': 49637, 'loss/train': 1.290576457977295} 08/30/2021 22:12:07 - INFO - __main__ - Step 49639: {'lr': 0.00038270875777530864, 'samples': 9530688, 'steps': 49638, 'loss/train': 1.6442703008651733} 08/30/2021 22:12:09 - INFO - __main__ - Step 49640: {'lr': 0.0003827042604113241, 'samples': 9530880, 'steps': 49639, 'loss/train': 1.3259234428405762} 08/30/2021 22:12:09 - INFO - __main__ - Step 49641: {'lr': 0.0003826997629875451, 'samples': 9531072, 'steps': 49640, 'loss/train': 1.1789066791534424} 08/30/2021 22:12:10 - INFO - __main__ - Step 49642: {'lr': 0.0003826952655039736, 'samples': 9531264, 'steps': 49641, 'loss/train': 1.4378935098648071} 08/30/2021 22:12:10 - INFO - __main__ - Step 49643: {'lr': 0.0003826907679606117, 'samples': 9531456, 'steps': 49642, 'loss/train': 1.1316323280334473} 08/30/2021 22:12:10 - INFO - __main__ - Step 49644: {'lr': 0.00038268627035746133, 'samples': 9531648, 'steps': 49643, 'loss/train': 0.5237854719161987} 08/30/2021 22:12:11 - INFO - __main__ - Step 49645: {'lr': 0.00038268177269452463, 'samples': 9531840, 'steps': 49644, 'loss/train': 1.2391196489334106} 08/30/2021 22:12:13 - INFO - __main__ - Step 49646: {'lr': 0.0003826772749718036, 'samples': 9532032, 'steps': 49645, 'loss/train': 0.7716188430786133} 08/30/2021 22:12:13 - INFO - __main__ - Step 49647: {'lr': 0.00038267277718930014, 'samples': 9532224, 'steps': 49646, 'loss/train': 1.127185344696045} 08/30/2021 22:12:13 - INFO - __main__ - Step 49648: {'lr': 0.0003826682793470164, 'samples': 9532416, 'steps': 49647, 'loss/train': 1.1896660327911377} 08/30/2021 22:12:14 - INFO - __main__ - Step 49649: {'lr': 0.0003826637814449544, 'samples': 9532608, 'steps': 49648, 'loss/train': 1.9542824029922485} 08/30/2021 22:12:14 - INFO - __main__ - Step 49650: {'lr': 0.00038265928348311614, 'samples': 9532800, 'steps': 49649, 'loss/train': 1.5729920864105225} 08/30/2021 22:12:16 - INFO - __main__ - Step 49651: {'lr': 0.0003826547854615037, 'samples': 9532992, 'steps': 49650, 'loss/train': 0.04735864698886871} 08/30/2021 22:12:16 - INFO - __main__ - Step 49652: {'lr': 0.000382650287380119, 'samples': 9533184, 'steps': 49651, 'loss/train': 1.5125199556350708} 08/30/2021 22:12:16 - INFO - __main__ - Step 49653: {'lr': 0.00038264578923896415, 'samples': 9533376, 'steps': 49652, 'loss/train': 1.7394583225250244} 08/30/2021 22:12:17 - INFO - __main__ - Step 49654: {'lr': 0.00038264129103804113, 'samples': 9533568, 'steps': 49653, 'loss/train': 1.409911036491394} 08/30/2021 22:12:17 - INFO - __main__ - Step 49655: {'lr': 0.00038263679277735196, 'samples': 9533760, 'steps': 49654, 'loss/train': 0.8430184721946716} 08/30/2021 22:12:19 - INFO - __main__ - Step 49656: {'lr': 0.0003826322944568988, 'samples': 9533952, 'steps': 49655, 'loss/train': 1.3635603189468384} 08/30/2021 22:12:19 - INFO - __main__ - Step 49657: {'lr': 0.00038262779607668354, 'samples': 9534144, 'steps': 49656, 'loss/train': 0.9720028042793274} 08/30/2021 22:12:19 - INFO - __main__ - Step 49658: {'lr': 0.0003826232976367082, 'samples': 9534336, 'steps': 49657, 'loss/train': 1.8901889324188232} 08/30/2021 22:12:20 - INFO - __main__ - Step 49659: {'lr': 0.0003826187991369749, 'samples': 9534528, 'steps': 49658, 'loss/train': 1.0283443927764893} 08/30/2021 22:12:20 - INFO - __main__ - Step 49660: {'lr': 0.00038261430057748557, 'samples': 9534720, 'steps': 49659, 'loss/train': 1.441989779472351} 08/30/2021 22:12:22 - INFO - __main__ - Step 49661: {'lr': 0.0003826098019582423, 'samples': 9534912, 'steps': 49660, 'loss/train': 0.9568517208099365} 08/30/2021 22:12:22 - INFO - __main__ - Step 49662: {'lr': 0.00038260530327924715, 'samples': 9535104, 'steps': 49661, 'loss/train': 1.2110334634780884} 08/30/2021 22:12:22 - INFO - __main__ - Step 49663: {'lr': 0.00038260080454050207, 'samples': 9535296, 'steps': 49662, 'loss/train': 0.420901894569397} 08/30/2021 22:12:23 - INFO - __main__ - Step 49664: {'lr': 0.00038259630574200904, 'samples': 9535488, 'steps': 49663, 'loss/train': 1.2216628789901733} 08/30/2021 22:12:23 - INFO - __main__ - Step 49665: {'lr': 0.0003825918068837702, 'samples': 9535680, 'steps': 49664, 'loss/train': 1.2758723497390747} 08/30/2021 22:12:25 - INFO - __main__ - Step 49666: {'lr': 0.00038258730796578757, 'samples': 9535872, 'steps': 49665, 'loss/train': 1.599077820777893} 08/30/2021 22:12:25 - INFO - __main__ - Step 49667: {'lr': 0.0003825828089880631, 'samples': 9536064, 'steps': 49666, 'loss/train': 0.9477130174636841} 08/30/2021 22:12:26 - INFO - __main__ - Step 49668: {'lr': 0.00038257830995059894, 'samples': 9536256, 'steps': 49667, 'loss/train': 1.3110496997833252} 08/30/2021 22:12:26 - INFO - __main__ - Step 49669: {'lr': 0.00038257381085339694, 'samples': 9536448, 'steps': 49668, 'loss/train': 0.9027947783470154} 08/30/2021 22:12:26 - INFO - __main__ - Step 49670: {'lr': 0.00038256931169645925, 'samples': 9536640, 'steps': 49669, 'loss/train': 1.4737378358840942} 08/30/2021 22:12:28 - INFO - __main__ - Step 49671: {'lr': 0.00038256481247978793, 'samples': 9536832, 'steps': 49670, 'loss/train': 1.3816382884979248} 08/30/2021 22:12:28 - INFO - __main__ - Step 49672: {'lr': 0.00038256031320338494, 'samples': 9537024, 'steps': 49671, 'loss/train': 1.2973017692565918} 08/30/2021 22:12:28 - INFO - __main__ - Step 49673: {'lr': 0.0003825558138672523, 'samples': 9537216, 'steps': 49672, 'loss/train': 0.9309566617012024} 08/30/2021 22:12:29 - INFO - __main__ - Step 49674: {'lr': 0.00038255131447139203, 'samples': 9537408, 'steps': 49673, 'loss/train': 1.5804880857467651} 08/30/2021 22:12:29 - INFO - __main__ - Step 49675: {'lr': 0.00038254681501580625, 'samples': 9537600, 'steps': 49674, 'loss/train': 1.2980644702911377} 08/30/2021 22:12:31 - INFO - __main__ - Step 49676: {'lr': 0.00038254231550049686, 'samples': 9537792, 'steps': 49675, 'loss/train': 1.7197462320327759} 08/30/2021 22:12:31 - INFO - __main__ - Step 49677: {'lr': 0.00038253781592546593, 'samples': 9537984, 'steps': 49676, 'loss/train': 0.36219343543052673} 08/30/2021 22:12:31 - INFO - __main__ - Step 49678: {'lr': 0.0003825333162907155, 'samples': 9538176, 'steps': 49677, 'loss/train': 0.4128420054912567} 08/30/2021 22:12:32 - INFO - __main__ - Step 49679: {'lr': 0.0003825288165962477, 'samples': 9538368, 'steps': 49678, 'loss/train': 1.2414288520812988} 08/30/2021 22:12:32 - INFO - __main__ - Step 49680: {'lr': 0.0003825243168420644, 'samples': 9538560, 'steps': 49679, 'loss/train': 1.3402949571609497} 08/30/2021 22:12:34 - INFO - __main__ - Step 49681: {'lr': 0.00038251981702816767, 'samples': 9538752, 'steps': 49680, 'loss/train': 1.510880947113037} 08/30/2021 22:12:34 - INFO - __main__ - Step 49682: {'lr': 0.00038251531715455955, 'samples': 9538944, 'steps': 49681, 'loss/train': 1.0666968822479248} 08/30/2021 22:12:34 - INFO - __main__ - Step 49683: {'lr': 0.00038251081722124214, 'samples': 9539136, 'steps': 49682, 'loss/train': 0.9895131587982178} 08/30/2021 22:12:35 - INFO - __main__ - Step 49684: {'lr': 0.0003825063172282174, 'samples': 9539328, 'steps': 49683, 'loss/train': 0.8254391551017761} 08/30/2021 22:12:35 - INFO - __main__ - Step 49685: {'lr': 0.00038250181717548726, 'samples': 9539520, 'steps': 49684, 'loss/train': 1.0771102905273438} 08/30/2021 22:12:37 - INFO - __main__ - Step 49686: {'lr': 0.0003824973170630539, 'samples': 9539712, 'steps': 49685, 'loss/train': 1.2612708806991577} 08/30/2021 22:12:37 - INFO - __main__ - Step 49687: {'lr': 0.0003824928168909193, 'samples': 9539904, 'steps': 49686, 'loss/train': 1.3444955348968506} 08/30/2021 22:12:37 - INFO - __main__ - Step 49688: {'lr': 0.00038248831665908546, 'samples': 9540096, 'steps': 49687, 'loss/train': 1.7309826612472534} 08/30/2021 22:12:38 - INFO - __main__ - Step 49689: {'lr': 0.0003824838163675545, 'samples': 9540288, 'steps': 49688, 'loss/train': 0.333211213350296} 08/30/2021 22:12:38 - INFO - __main__ - Step 49690: {'lr': 0.0003824793160163283, 'samples': 9540480, 'steps': 49689, 'loss/train': 1.595306158065796} 08/30/2021 22:12:40 - INFO - __main__ - Step 49691: {'lr': 0.000382474815605409, 'samples': 9540672, 'steps': 49690, 'loss/train': 0.7322412133216858} 08/30/2021 22:12:41 - INFO - __main__ - Step 49692: {'lr': 0.00038247031513479856, 'samples': 9540864, 'steps': 49691, 'loss/train': 0.041530169546604156} 08/30/2021 22:12:41 - INFO - __main__ - Step 49693: {'lr': 0.0003824658146044991, 'samples': 9541056, 'steps': 49692, 'loss/train': 1.3264636993408203} 08/30/2021 22:12:42 - INFO - __main__ - Step 49694: {'lr': 0.0003824613140145125, 'samples': 9541248, 'steps': 49693, 'loss/train': 1.4436217546463013} 08/30/2021 22:12:42 - INFO - __main__ - Step 49695: {'lr': 0.00038245681336484096, 'samples': 9541440, 'steps': 49694, 'loss/train': 1.6068975925445557} 08/30/2021 22:12:42 - INFO - __main__ - Step 49696: {'lr': 0.00038245231265548633, 'samples': 9541632, 'steps': 49695, 'loss/train': 0.9332612156867981} 08/30/2021 22:12:44 - INFO - __main__ - Step 49697: {'lr': 0.0003824478118864508, 'samples': 9541824, 'steps': 49696, 'loss/train': 0.031258419156074524} 08/30/2021 22:12:45 - INFO - __main__ - Step 49698: {'lr': 0.0003824433110577363, 'samples': 9542016, 'steps': 49697, 'loss/train': 1.2822026014328003} 08/30/2021 22:12:45 - INFO - __main__ - Step 49699: {'lr': 0.0003824388101693449, 'samples': 9542208, 'steps': 49698, 'loss/train': 0.2977379262447357} 08/30/2021 22:12:45 - INFO - __main__ - Step 49700: {'lr': 0.00038243430922127865, 'samples': 9542400, 'steps': 49699, 'loss/train': 1.7197608947753906} 08/30/2021 22:12:46 - INFO - __main__ - Step 49701: {'lr': 0.00038242980821353954, 'samples': 9542592, 'steps': 49700, 'loss/train': 1.38543701171875} 08/30/2021 22:12:46 - INFO - __main__ - Step 49702: {'lr': 0.00038242530714612953, 'samples': 9542784, 'steps': 49701, 'loss/train': 0.06924241781234741} 08/30/2021 22:12:47 - INFO - __main__ - Step 49703: {'lr': 0.00038242080601905083, 'samples': 9542976, 'steps': 49702, 'loss/train': 0.6161973476409912} 08/30/2021 22:12:48 - INFO - __main__ - Step 49704: {'lr': 0.0003824163048323053, 'samples': 9543168, 'steps': 49703, 'loss/train': 1.0991592407226562} 08/30/2021 22:12:48 - INFO - __main__ - Step 49705: {'lr': 0.000382411803585895, 'samples': 9543360, 'steps': 49704, 'loss/train': 1.4899581670761108} 08/30/2021 22:12:49 - INFO - __main__ - Step 49706: {'lr': 0.000382407302279822, 'samples': 9543552, 'steps': 49705, 'loss/train': 1.731083631515503} 08/30/2021 22:12:49 - INFO - __main__ - Step 49707: {'lr': 0.0003824028009140883, 'samples': 9543744, 'steps': 49706, 'loss/train': 1.0906201601028442} 08/30/2021 22:12:51 - INFO - __main__ - Step 49708: {'lr': 0.000382398299488696, 'samples': 9543936, 'steps': 49707, 'loss/train': 1.4632432460784912} 08/30/2021 22:12:51 - INFO - __main__ - Step 49709: {'lr': 0.000382393798003647, 'samples': 9544128, 'steps': 49708, 'loss/train': 1.1668860912322998} 08/30/2021 22:12:52 - INFO - __main__ - Step 49710: {'lr': 0.00038238929645894345, 'samples': 9544320, 'steps': 49709, 'loss/train': 0.9777527451515198} 08/30/2021 22:12:52 - INFO - __main__ - Step 49711: {'lr': 0.00038238479485458725, 'samples': 9544512, 'steps': 49710, 'loss/train': 1.2632591724395752} 08/30/2021 22:12:52 - INFO - __main__ - Step 49712: {'lr': 0.0003823802931905806, 'samples': 9544704, 'steps': 49711, 'loss/train': 1.6812973022460938} 08/30/2021 22:12:54 - INFO - __main__ - Step 49713: {'lr': 0.0003823757914669254, 'samples': 9544896, 'steps': 49712, 'loss/train': 1.3029990196228027} 08/30/2021 22:12:54 - INFO - __main__ - Step 49714: {'lr': 0.00038237128968362366, 'samples': 9545088, 'steps': 49713, 'loss/train': 0.8617534637451172} 08/30/2021 22:12:55 - INFO - __main__ - Step 49715: {'lr': 0.0003823667878406776, 'samples': 9545280, 'steps': 49714, 'loss/train': 0.7684113383293152} 08/30/2021 22:12:55 - INFO - __main__ - Step 49716: {'lr': 0.000382362285938089, 'samples': 9545472, 'steps': 49715, 'loss/train': 2.6685233116149902} 08/30/2021 22:12:55 - INFO - __main__ - Step 49717: {'lr': 0.00038235778397586, 'samples': 9545664, 'steps': 49716, 'loss/train': 1.2324090003967285} 08/30/2021 22:12:56 - INFO - __main__ - Step 49718: {'lr': 0.00038235328195399253, 'samples': 9545856, 'steps': 49717, 'loss/train': 1.503272533416748} 08/30/2021 22:12:57 - INFO - __main__ - Step 49719: {'lr': 0.0003823487798724888, 'samples': 9546048, 'steps': 49718, 'loss/train': 0.04580173268914223} 08/30/2021 22:12:58 - INFO - __main__ - Step 49720: {'lr': 0.00038234427773135084, 'samples': 9546240, 'steps': 49719, 'loss/train': 1.355670690536499} 08/30/2021 22:12:58 - INFO - __main__ - Step 49721: {'lr': 0.00038233977553058055, 'samples': 9546432, 'steps': 49720, 'loss/train': 2.0083348751068115} 08/30/2021 22:12:59 - INFO - __main__ - Step 49722: {'lr': 0.0003823352732701799, 'samples': 9546624, 'steps': 49721, 'loss/train': 1.3676416873931885} 08/30/2021 22:12:59 - INFO - __main__ - Step 49723: {'lr': 0.0003823307709501511, 'samples': 9546816, 'steps': 49722, 'loss/train': 1.2437701225280762} 08/30/2021 22:13:00 - INFO - __main__ - Step 49724: {'lr': 0.0003823262685704961, 'samples': 9547008, 'steps': 49723, 'loss/train': 0.050234027206897736} 08/30/2021 22:13:01 - INFO - __main__ - Step 49725: {'lr': 0.00038232176613121687, 'samples': 9547200, 'steps': 49724, 'loss/train': 0.9303320050239563} 08/30/2021 22:13:01 - INFO - __main__ - Step 49726: {'lr': 0.00038231726363231554, 'samples': 9547392, 'steps': 49725, 'loss/train': 1.0685924291610718} 08/30/2021 22:13:01 - INFO - __main__ - Step 49727: {'lr': 0.0003823127610737941, 'samples': 9547584, 'steps': 49726, 'loss/train': 0.8104143142700195} 08/30/2021 22:13:02 - INFO - __main__ - Step 49728: {'lr': 0.00038230825845565454, 'samples': 9547776, 'steps': 49727, 'loss/train': 0.8963868618011475} 08/30/2021 22:13:03 - INFO - __main__ - Step 49729: {'lr': 0.00038230375577789894, 'samples': 9547968, 'steps': 49728, 'loss/train': 1.4387993812561035} 08/30/2021 22:13:04 - INFO - __main__ - Step 49730: {'lr': 0.0003822992530405293, 'samples': 9548160, 'steps': 49729, 'loss/train': 1.1440261602401733} 08/30/2021 22:13:04 - INFO - __main__ - Step 49731: {'lr': 0.00038229475024354766, 'samples': 9548352, 'steps': 49730, 'loss/train': 1.3108282089233398} 08/30/2021 22:13:04 - INFO - __main__ - Step 49732: {'lr': 0.00038229024738695605, 'samples': 9548544, 'steps': 49731, 'loss/train': 1.523683786392212} 08/30/2021 22:13:05 - INFO - __main__ - Step 49733: {'lr': 0.0003822857444707565, 'samples': 9548736, 'steps': 49732, 'loss/train': 1.5838416814804077} 08/30/2021 22:13:06 - INFO - __main__ - Step 49734: {'lr': 0.00038228124149495104, 'samples': 9548928, 'steps': 49733, 'loss/train': 1.4662511348724365} 08/30/2021 22:13:07 - INFO - __main__ - Step 49735: {'lr': 0.0003822767384595417, 'samples': 9549120, 'steps': 49734, 'loss/train': 1.0484226942062378} 08/30/2021 22:13:07 - INFO - __main__ - Step 49736: {'lr': 0.0003822722353645305, 'samples': 9549312, 'steps': 49735, 'loss/train': 0.8739673495292664} 08/30/2021 22:13:07 - INFO - __main__ - Step 49737: {'lr': 0.00038226773220991937, 'samples': 9549504, 'steps': 49736, 'loss/train': 1.1348925828933716} 08/30/2021 22:13:08 - INFO - __main__ - Step 49738: {'lr': 0.0003822632289957105, 'samples': 9549696, 'steps': 49737, 'loss/train': 1.018144130706787} 08/30/2021 22:13:09 - INFO - __main__ - Step 49739: {'lr': 0.000382258725721906, 'samples': 9549888, 'steps': 49738, 'loss/train': 1.5319018363952637} 08/30/2021 22:13:10 - INFO - __main__ - Step 49740: {'lr': 0.0003822542223885076, 'samples': 9550080, 'steps': 49739, 'loss/train': 1.4723345041275024} 08/30/2021 22:13:10 - INFO - __main__ - Step 49741: {'lr': 0.0003822497189955175, 'samples': 9550272, 'steps': 49740, 'loss/train': 1.5046100616455078} 08/30/2021 22:13:11 - INFO - __main__ - Step 49742: {'lr': 0.0003822452155429378, 'samples': 9550464, 'steps': 49741, 'loss/train': 1.0838719606399536} 08/30/2021 22:13:11 - INFO - __main__ - Step 49743: {'lr': 0.0003822407120307704, 'samples': 9550656, 'steps': 49742, 'loss/train': 1.1902461051940918} 08/30/2021 22:13:12 - INFO - __main__ - Step 49744: {'lr': 0.0003822362084590174, 'samples': 9550848, 'steps': 49743, 'loss/train': 1.4791418313980103} 08/30/2021 22:13:13 - INFO - __main__ - Step 49745: {'lr': 0.0003822317048276808, 'samples': 9551040, 'steps': 49744, 'loss/train': 1.482893466949463} 08/30/2021 22:13:13 - INFO - __main__ - Step 49746: {'lr': 0.0003822272011367626, 'samples': 9551232, 'steps': 49745, 'loss/train': 0.046908844262361526} 08/30/2021 22:13:14 - INFO - __main__ - Step 49747: {'lr': 0.0003822226973862649, 'samples': 9551424, 'steps': 49746, 'loss/train': 1.421980619430542} 08/30/2021 22:13:14 - INFO - __main__ - Step 49748: {'lr': 0.00038221819357618967, 'samples': 9551616, 'steps': 49747, 'loss/train': 0.943286120891571} 08/30/2021 22:13:14 - INFO - __main__ - Step 49749: {'lr': 0.0003822136897065389, 'samples': 9551808, 'steps': 49748, 'loss/train': 0.44666239619255066} 08/30/2021 22:13:16 - INFO - __main__ - Step 49750: {'lr': 0.0003822091857773148, 'samples': 9552000, 'steps': 49749, 'loss/train': 1.1273568868637085} 08/30/2021 22:13:17 - INFO - __main__ - Step 49751: {'lr': 0.00038220468178851917, 'samples': 9552192, 'steps': 49750, 'loss/train': 2.1853973865509033} 08/30/2021 22:13:17 - INFO - __main__ - Step 49752: {'lr': 0.00038220017774015427, 'samples': 9552384, 'steps': 49751, 'loss/train': 1.0996079444885254} 08/30/2021 22:13:18 - INFO - __main__ - Step 49753: {'lr': 0.00038219567363222183, 'samples': 9552576, 'steps': 49752, 'loss/train': 0.9311907887458801} 08/30/2021 22:13:18 - INFO - __main__ - Step 49754: {'lr': 0.00038219116946472425, 'samples': 9552768, 'steps': 49753, 'loss/train': 1.5368413925170898} 08/30/2021 22:13:19 - INFO - __main__ - Step 49755: {'lr': 0.0003821866652376633, 'samples': 9552960, 'steps': 49754, 'loss/train': 1.522527813911438} 08/30/2021 22:13:20 - INFO - __main__ - Step 49756: {'lr': 0.0003821821609510411, 'samples': 9553152, 'steps': 49755, 'loss/train': 0.6353611946105957} 08/30/2021 22:13:20 - INFO - __main__ - Step 49757: {'lr': 0.0003821776566048596, 'samples': 9553344, 'steps': 49756, 'loss/train': 1.2988874912261963} 08/30/2021 22:13:21 - INFO - __main__ - Step 49758: {'lr': 0.0003821731521991209, 'samples': 9553536, 'steps': 49757, 'loss/train': 1.1676123142242432} 08/30/2021 22:13:21 - INFO - __main__ - Step 49759: {'lr': 0.00038216864773382703, 'samples': 9553728, 'steps': 49758, 'loss/train': 1.4098976850509644} 08/30/2021 22:13:23 - INFO - __main__ - Step 49760: {'lr': 0.00038216414320898004, 'samples': 9553920, 'steps': 49759, 'loss/train': 1.2838845252990723} 08/30/2021 22:13:23 - INFO - __main__ - Step 49761: {'lr': 0.0003821596386245819, 'samples': 9554112, 'steps': 49760, 'loss/train': 1.0469671487808228} 08/30/2021 22:13:23 - INFO - __main__ - Step 49762: {'lr': 0.00038215513398063465, 'samples': 9554304, 'steps': 49761, 'loss/train': 1.294045329093933} 08/30/2021 22:13:24 - INFO - __main__ - Step 49763: {'lr': 0.00038215062927714037, 'samples': 9554496, 'steps': 49762, 'loss/train': 1.5076699256896973} 08/30/2021 22:13:24 - INFO - __main__ - Step 49764: {'lr': 0.000382146124514101, 'samples': 9554688, 'steps': 49763, 'loss/train': 1.3536831140518188} 08/30/2021 22:13:26 - INFO - __main__ - Step 49765: {'lr': 0.00038214161969151865, 'samples': 9554880, 'steps': 49764, 'loss/train': 0.9425990581512451} 08/30/2021 22:13:26 - INFO - __main__ - Step 49766: {'lr': 0.0003821371148093954, 'samples': 9555072, 'steps': 49765, 'loss/train': 1.1800950765609741} 08/30/2021 22:13:27 - INFO - __main__ - Step 49767: {'lr': 0.0003821326098677331, 'samples': 9555264, 'steps': 49766, 'loss/train': 0.9455059766769409} 08/30/2021 22:13:27 - INFO - __main__ - Step 49768: {'lr': 0.00038212810486653394, 'samples': 9555456, 'steps': 49767, 'loss/train': 1.3309293985366821} 08/30/2021 22:13:28 - INFO - __main__ - Step 49769: {'lr': 0.0003821235998057999, 'samples': 9555648, 'steps': 49768, 'loss/train': 3.0551741123199463} 08/30/2021 22:13:28 - INFO - __main__ - Step 49770: {'lr': 0.00038211909468553295, 'samples': 9555840, 'steps': 49769, 'loss/train': 4.082547187805176} 08/30/2021 22:13:30 - INFO - __main__ - Step 49771: {'lr': 0.00038211458950573526, 'samples': 9556032, 'steps': 49770, 'loss/train': 1.1977760791778564} 08/30/2021 22:13:30 - INFO - __main__ - Step 49772: {'lr': 0.0003821100842664087, 'samples': 9556224, 'steps': 49771, 'loss/train': 1.6944628953933716} 08/30/2021 22:13:30 - INFO - __main__ - Step 49773: {'lr': 0.00038210557896755536, 'samples': 9556416, 'steps': 49772, 'loss/train': 0.04313196241855621} 08/30/2021 22:13:31 - INFO - __main__ - Step 49774: {'lr': 0.0003821010736091774, 'samples': 9556608, 'steps': 49773, 'loss/train': 1.4688575267791748} 08/30/2021 22:13:31 - INFO - __main__ - Step 49775: {'lr': 0.00038209656819127664, 'samples': 9556800, 'steps': 49774, 'loss/train': 1.7247586250305176} 08/30/2021 22:13:33 - INFO - __main__ - Step 49776: {'lr': 0.0003820920627138552, 'samples': 9556992, 'steps': 49775, 'loss/train': 0.9166179299354553} 08/30/2021 22:13:33 - INFO - __main__ - Step 49777: {'lr': 0.00038208755717691515, 'samples': 9557184, 'steps': 49776, 'loss/train': 1.9556865692138672} 08/30/2021 22:13:33 - INFO - __main__ - Step 49778: {'lr': 0.00038208305158045846, 'samples': 9557376, 'steps': 49777, 'loss/train': 1.462591528892517} 08/30/2021 22:13:34 - INFO - __main__ - Step 49779: {'lr': 0.0003820785459244872, 'samples': 9557568, 'steps': 49778, 'loss/train': 0.6248871684074402} 08/30/2021 22:13:34 - INFO - __main__ - Step 49780: {'lr': 0.00038207404020900343, 'samples': 9557760, 'steps': 49779, 'loss/train': 1.3465285301208496} 08/30/2021 22:13:36 - INFO - __main__ - Step 49781: {'lr': 0.0003820695344340091, 'samples': 9557952, 'steps': 49780, 'loss/train': 2.1117501258850098} 08/30/2021 22:13:36 - INFO - __main__ - Step 49782: {'lr': 0.00038206502859950624, 'samples': 9558144, 'steps': 49781, 'loss/train': 1.4538969993591309} 08/30/2021 22:13:37 - INFO - __main__ - Step 49783: {'lr': 0.000382060522705497, 'samples': 9558336, 'steps': 49782, 'loss/train': 1.5920535326004028} 08/30/2021 22:13:37 - INFO - __main__ - Step 49784: {'lr': 0.0003820560167519832, 'samples': 9558528, 'steps': 49783, 'loss/train': 1.7279406785964966} 08/30/2021 22:13:37 - INFO - __main__ - Step 49785: {'lr': 0.000382051510738967, 'samples': 9558720, 'steps': 49784, 'loss/train': 1.3205997943878174} 08/30/2021 22:13:38 - INFO - __main__ - Step 49786: {'lr': 0.0003820470046664506, 'samples': 9558912, 'steps': 49785, 'loss/train': 1.0998303890228271} 08/30/2021 22:13:39 - INFO - __main__ - Step 49787: {'lr': 0.0003820424985344357, 'samples': 9559104, 'steps': 49786, 'loss/train': 1.9888184070587158} 08/30/2021 22:13:40 - INFO - __main__ - Step 49788: {'lr': 0.0003820379923429246, 'samples': 9559296, 'steps': 49787, 'loss/train': 1.4241983890533447} 08/30/2021 22:13:40 - INFO - __main__ - Step 49789: {'lr': 0.00038203348609191915, 'samples': 9559488, 'steps': 49788, 'loss/train': 1.0431121587753296} 08/30/2021 22:13:40 - INFO - __main__ - Step 49790: {'lr': 0.00038202897978142144, 'samples': 9559680, 'steps': 49789, 'loss/train': 1.8512325286865234} 08/30/2021 22:13:41 - INFO - __main__ - Step 49791: {'lr': 0.00038202447341143355, 'samples': 9559872, 'steps': 49790, 'loss/train': 1.1772205829620361} 08/30/2021 22:13:42 - INFO - __main__ - Step 49792: {'lr': 0.0003820199669819574, 'samples': 9560064, 'steps': 49791, 'loss/train': 1.40646493434906} 08/30/2021 22:13:43 - INFO - __main__ - Step 49793: {'lr': 0.00038201546049299517, 'samples': 9560256, 'steps': 49792, 'loss/train': 1.4943504333496094} 08/30/2021 22:13:43 - INFO - __main__ - Step 49794: {'lr': 0.00038201095394454874, 'samples': 9560448, 'steps': 49793, 'loss/train': 0.9948331117630005} 08/30/2021 22:13:43 - INFO - __main__ - Step 49795: {'lr': 0.0003820064473366203, 'samples': 9560640, 'steps': 49794, 'loss/train': 1.3066593408584595} 08/30/2021 22:13:44 - INFO - __main__ - Step 49796: {'lr': 0.00038200194066921166, 'samples': 9560832, 'steps': 49795, 'loss/train': 1.463216781616211} 08/30/2021 22:13:45 - INFO - __main__ - Step 49797: {'lr': 0.00038199743394232513, 'samples': 9561024, 'steps': 49796, 'loss/train': 1.5691516399383545} 08/30/2021 22:13:46 - INFO - __main__ - Step 49798: {'lr': 0.0003819929271559625, 'samples': 9561216, 'steps': 49797, 'loss/train': 0.4486684203147888} 08/30/2021 22:13:46 - INFO - __main__ - Step 49799: {'lr': 0.00038198842031012594, 'samples': 9561408, 'steps': 49798, 'loss/train': 0.9006960988044739} 08/30/2021 22:13:46 - INFO - __main__ - Step 49800: {'lr': 0.00038198391340481735, 'samples': 9561600, 'steps': 49799, 'loss/train': 1.9151670932769775} 08/30/2021 22:13:47 - INFO - __main__ - Step 49801: {'lr': 0.0003819794064400389, 'samples': 9561792, 'steps': 49800, 'loss/train': 1.4824037551879883} 08/30/2021 22:13:49 - INFO - __main__ - Step 49802: {'lr': 0.00038197489941579264, 'samples': 9561984, 'steps': 49801, 'loss/train': 1.3782626390457153} 08/30/2021 22:13:49 - INFO - __main__ - Step 49803: {'lr': 0.00038197039233208043, 'samples': 9562176, 'steps': 49802, 'loss/train': 1.398019552230835} 08/30/2021 22:13:49 - INFO - __main__ - Step 49804: {'lr': 0.0003819658851889044, 'samples': 9562368, 'steps': 49803, 'loss/train': 1.6332396268844604} 08/30/2021 22:13:50 - INFO - __main__ - Step 49805: {'lr': 0.00038196137798626663, 'samples': 9562560, 'steps': 49804, 'loss/train': 1.5197279453277588} 08/30/2021 22:13:50 - INFO - __main__ - Step 49806: {'lr': 0.00038195687072416906, 'samples': 9562752, 'steps': 49805, 'loss/train': 1.3784159421920776} 08/30/2021 22:13:50 - INFO - __main__ - Step 49807: {'lr': 0.00038195236340261374, 'samples': 9562944, 'steps': 49806, 'loss/train': 1.3762362003326416} 08/30/2021 22:13:52 - INFO - __main__ - Step 49808: {'lr': 0.0003819478560216029, 'samples': 9563136, 'steps': 49807, 'loss/train': 1.9439811706542969} 08/30/2021 22:13:53 - INFO - __main__ - Step 49809: {'lr': 0.00038194334858113817, 'samples': 9563328, 'steps': 49808, 'loss/train': 1.3838212490081787} 08/30/2021 22:13:53 - INFO - __main__ - Step 49810: {'lr': 0.0003819388410812219, 'samples': 9563520, 'steps': 49809, 'loss/train': 1.0086147785186768} 08/30/2021 22:13:53 - INFO - __main__ - Step 49811: {'lr': 0.00038193433352185597, 'samples': 9563712, 'steps': 49810, 'loss/train': 1.0823484659194946} 08/30/2021 22:13:54 - INFO - __main__ - Step 49812: {'lr': 0.0003819298259030425, 'samples': 9563904, 'steps': 49811, 'loss/train': 1.707214593887329} 08/30/2021 22:13:55 - INFO - __main__ - Step 49813: {'lr': 0.00038192531822478347, 'samples': 9564096, 'steps': 49812, 'loss/train': 0.020786872133612633} 08/30/2021 22:13:56 - INFO - __main__ - Step 49814: {'lr': 0.000381920810487081, 'samples': 9564288, 'steps': 49813, 'loss/train': 0.21956177055835724} 08/30/2021 22:13:56 - INFO - __main__ - Step 49815: {'lr': 0.0003819163026899369, 'samples': 9564480, 'steps': 49814, 'loss/train': 2.2562546730041504} 08/30/2021 22:13:56 - INFO - __main__ - Step 49816: {'lr': 0.00038191179483335346, 'samples': 9564672, 'steps': 49815, 'loss/train': 1.0328961610794067} 08/30/2021 22:13:57 - INFO - __main__ - Step 49817: {'lr': 0.0003819072869173326, 'samples': 9564864, 'steps': 49816, 'loss/train': 1.1331558227539062} 08/30/2021 22:13:57 - INFO - __main__ - Step 49818: {'lr': 0.0003819027789418764, 'samples': 9565056, 'steps': 49817, 'loss/train': 0.9301910400390625} 08/30/2021 22:13:59 - INFO - __main__ - Step 49819: {'lr': 0.0003818982709069867, 'samples': 9565248, 'steps': 49818, 'loss/train': 1.204207181930542} 08/30/2021 22:13:59 - INFO - __main__ - Step 49820: {'lr': 0.00038189376281266575, 'samples': 9565440, 'steps': 49819, 'loss/train': 0.8300979137420654} 08/30/2021 22:14:00 - INFO - __main__ - Step 49821: {'lr': 0.00038188925465891554, 'samples': 9565632, 'steps': 49820, 'loss/train': 1.497221827507019} 08/30/2021 22:14:00 - INFO - __main__ - Step 49822: {'lr': 0.000381884746445738, 'samples': 9565824, 'steps': 49821, 'loss/train': 1.5963858366012573} 08/30/2021 22:14:00 - INFO - __main__ - Step 49823: {'lr': 0.0003818802381731353, 'samples': 9566016, 'steps': 49822, 'loss/train': 1.3128944635391235} 08/30/2021 22:14:02 - INFO - __main__ - Step 49824: {'lr': 0.00038187572984110937, 'samples': 9566208, 'steps': 49823, 'loss/train': 1.3278546333312988} 08/30/2021 22:14:02 - INFO - __main__ - Step 49825: {'lr': 0.00038187122144966225, 'samples': 9566400, 'steps': 49824, 'loss/train': 1.9274048805236816} 08/30/2021 22:14:03 - INFO - __main__ - Step 49826: {'lr': 0.000381866712998796, 'samples': 9566592, 'steps': 49825, 'loss/train': 1.241894006729126} 08/30/2021 22:14:03 - INFO - __main__ - Step 49827: {'lr': 0.0003818622044885126, 'samples': 9566784, 'steps': 49826, 'loss/train': 1.2455166578292847} 08/30/2021 22:14:03 - INFO - __main__ - Step 49828: {'lr': 0.00038185769591881426, 'samples': 9566976, 'steps': 49827, 'loss/train': 0.985876739025116} 08/30/2021 22:14:05 - INFO - __main__ - Step 49829: {'lr': 0.00038185318728970277, 'samples': 9567168, 'steps': 49828, 'loss/train': 2.085016965866089} 08/30/2021 22:14:06 - INFO - __main__ - Step 49830: {'lr': 0.00038184867860118036, 'samples': 9567360, 'steps': 49829, 'loss/train': 1.0317169427871704} 08/30/2021 22:14:06 - INFO - __main__ - Step 49831: {'lr': 0.0003818441698532488, 'samples': 9567552, 'steps': 49830, 'loss/train': 1.3614450693130493} 08/30/2021 22:14:06 - INFO - __main__ - Step 49832: {'lr': 0.00038183966104591037, 'samples': 9567744, 'steps': 49831, 'loss/train': 1.1619430780410767} 08/30/2021 22:14:07 - INFO - __main__ - Step 49833: {'lr': 0.0003818351521791671, 'samples': 9567936, 'steps': 49832, 'loss/train': 0.08117188513278961} 08/30/2021 22:14:08 - INFO - __main__ - Step 49834: {'lr': 0.0003818306432530209, 'samples': 9568128, 'steps': 49833, 'loss/train': 0.24984338879585266} 08/30/2021 22:14:09 - INFO - __main__ - Step 49835: {'lr': 0.0003818261342674738, 'samples': 9568320, 'steps': 49834, 'loss/train': 1.6425518989562988} 08/30/2021 22:14:09 - INFO - __main__ - Step 49836: {'lr': 0.00038182162522252795, 'samples': 9568512, 'steps': 49835, 'loss/train': 1.0567774772644043} 08/30/2021 22:14:09 - INFO - __main__ - Step 49837: {'lr': 0.0003818171161181853, 'samples': 9568704, 'steps': 49836, 'loss/train': 3.106945276260376} 08/30/2021 22:14:10 - INFO - __main__ - Step 49838: {'lr': 0.00038181260695444784, 'samples': 9568896, 'steps': 49837, 'loss/train': 1.4562439918518066} 08/30/2021 22:14:11 - INFO - __main__ - Step 49839: {'lr': 0.00038180809773131764, 'samples': 9569088, 'steps': 49838, 'loss/train': 1.548840880393982} 08/30/2021 22:14:12 - INFO - __main__ - Step 49840: {'lr': 0.0003818035884487968, 'samples': 9569280, 'steps': 49839, 'loss/train': 1.1457788944244385} 08/30/2021 22:14:12 - INFO - __main__ - Step 49841: {'lr': 0.0003817990791068873, 'samples': 9569472, 'steps': 49840, 'loss/train': 1.4783170223236084} 08/30/2021 22:14:12 - INFO - __main__ - Step 49842: {'lr': 0.00038179456970559116, 'samples': 9569664, 'steps': 49841, 'loss/train': 0.8052507042884827} 08/30/2021 22:14:13 - INFO - __main__ - Step 49843: {'lr': 0.0003817900602449104, 'samples': 9569856, 'steps': 49842, 'loss/train': 1.5514938831329346} 08/30/2021 22:14:14 - INFO - __main__ - Step 49844: {'lr': 0.0003817855507248471, 'samples': 9570048, 'steps': 49843, 'loss/train': 0.9434102773666382} 08/30/2021 22:14:15 - INFO - __main__ - Step 49845: {'lr': 0.00038178104114540326, 'samples': 9570240, 'steps': 49844, 'loss/train': 1.6355791091918945} 08/30/2021 22:14:15 - INFO - __main__ - Step 49846: {'lr': 0.0003817765315065809, 'samples': 9570432, 'steps': 49845, 'loss/train': 1.291693091392517} 08/30/2021 22:14:15 - INFO - __main__ - Step 49847: {'lr': 0.000381772021808382, 'samples': 9570624, 'steps': 49846, 'loss/train': 0.9509743452072144} 08/30/2021 22:14:16 - INFO - __main__ - Step 49848: {'lr': 0.00038176751205080885, 'samples': 9570816, 'steps': 49847, 'loss/train': 1.1592611074447632} 08/30/2021 22:14:17 - INFO - __main__ - Step 49849: {'lr': 0.00038176300223386313, 'samples': 9571008, 'steps': 49848, 'loss/train': 0.9572741389274597} 08/30/2021 22:14:18 - INFO - __main__ - Step 49850: {'lr': 0.00038175849235754704, 'samples': 9571200, 'steps': 49849, 'loss/train': 1.5450934171676636} 08/30/2021 22:14:18 - INFO - __main__ - Step 49851: {'lr': 0.00038175398242186264, 'samples': 9571392, 'steps': 49850, 'loss/train': 1.2566306591033936} 08/30/2021 22:14:18 - INFO - __main__ - Step 49852: {'lr': 0.00038174947242681194, 'samples': 9571584, 'steps': 49851, 'loss/train': 1.3757431507110596} 08/30/2021 22:14:19 - INFO - __main__ - Step 49853: {'lr': 0.000381744962372397, 'samples': 9571776, 'steps': 49852, 'loss/train': 0.3873279392719269} 08/30/2021 22:14:21 - INFO - __main__ - Step 49854: {'lr': 0.00038174045225861976, 'samples': 9571968, 'steps': 49853, 'loss/train': 1.4917348623275757} 08/30/2021 22:14:21 - INFO - __main__ - Step 49855: {'lr': 0.00038173594208548234, 'samples': 9572160, 'steps': 49854, 'loss/train': 1.7407726049423218} 08/30/2021 22:14:22 - INFO - __main__ - Step 49856: {'lr': 0.00038173143185298665, 'samples': 9572352, 'steps': 49855, 'loss/train': 0.6799062490463257} 08/30/2021 22:14:22 - INFO - __main__ - Step 49857: {'lr': 0.00038172692156113484, 'samples': 9572544, 'steps': 49856, 'loss/train': 2.867138385772705} 08/30/2021 22:14:22 - INFO - __main__ - Step 49858: {'lr': 0.000381722411209929, 'samples': 9572736, 'steps': 49857, 'loss/train': 0.786793053150177} 08/30/2021 22:14:23 - INFO - __main__ - Step 49859: {'lr': 0.00038171790079937097, 'samples': 9572928, 'steps': 49858, 'loss/train': 0.5406507849693298} 08/30/2021 22:14:24 - INFO - __main__ - Step 49860: {'lr': 0.000381713390329463, 'samples': 9573120, 'steps': 49859, 'loss/train': 0.47808048129081726} 08/30/2021 22:14:25 - INFO - __main__ - Step 49861: {'lr': 0.00038170887980020683, 'samples': 9573312, 'steps': 49860, 'loss/train': 1.080627202987671} 08/30/2021 22:14:25 - INFO - __main__ - Step 49862: {'lr': 0.0003817043692116049, 'samples': 9573504, 'steps': 49861, 'loss/train': 1.9295005798339844} 08/30/2021 22:14:25 - INFO - __main__ - Step 49863: {'lr': 0.00038169985856365885, 'samples': 9573696, 'steps': 49862, 'loss/train': 1.2276242971420288} 08/30/2021 22:14:26 - INFO - __main__ - Step 49864: {'lr': 0.00038169534785637097, 'samples': 9573888, 'steps': 49863, 'loss/train': 0.9743057489395142} 08/30/2021 22:14:27 - INFO - __main__ - Step 49865: {'lr': 0.00038169083708974313, 'samples': 9574080, 'steps': 49864, 'loss/train': 1.4043761491775513} 08/30/2021 22:14:28 - INFO - __main__ - Step 49866: {'lr': 0.0003816863262637774, 'samples': 9574272, 'steps': 49865, 'loss/train': 1.5645949840545654} 08/30/2021 22:14:28 - INFO - __main__ - Step 49867: {'lr': 0.0003816818153784759, 'samples': 9574464, 'steps': 49866, 'loss/train': 0.762726902961731} 08/30/2021 22:14:28 - INFO - __main__ - Step 49868: {'lr': 0.00038167730443384063, 'samples': 9574656, 'steps': 49867, 'loss/train': 1.2686876058578491} 08/30/2021 22:14:29 - INFO - __main__ - Step 49869: {'lr': 0.0003816727934298736, 'samples': 9574848, 'steps': 49868, 'loss/train': 1.263796329498291} 08/30/2021 22:14:30 - INFO - __main__ - Step 49870: {'lr': 0.0003816682823665768, 'samples': 9575040, 'steps': 49869, 'loss/train': 1.100020408630371} 08/30/2021 22:14:31 - INFO - __main__ - Step 49871: {'lr': 0.0003816637712439523, 'samples': 9575232, 'steps': 49870, 'loss/train': 1.3270772695541382} 08/30/2021 22:14:31 - INFO - __main__ - Step 49872: {'lr': 0.0003816592600620021, 'samples': 9575424, 'steps': 49871, 'loss/train': 5.723047733306885} 08/30/2021 22:14:31 - INFO - __main__ - Step 49873: {'lr': 0.0003816547488207284, 'samples': 9575616, 'steps': 49872, 'loss/train': 1.449615716934204} 08/30/2021 22:14:32 - INFO - __main__ - Step 49874: {'lr': 0.00038165023752013294, 'samples': 9575808, 'steps': 49873, 'loss/train': 1.69248628616333} 08/30/2021 22:14:33 - INFO - __main__ - Step 49875: {'lr': 0.00038164572616021807, 'samples': 9576000, 'steps': 49874, 'loss/train': 1.406014323234558} 08/30/2021 22:14:34 - INFO - __main__ - Step 49876: {'lr': 0.0003816412147409856, 'samples': 9576192, 'steps': 49875, 'loss/train': 1.1755253076553345} 08/30/2021 22:14:34 - INFO - __main__ - Step 49877: {'lr': 0.0003816367032624376, 'samples': 9576384, 'steps': 49876, 'loss/train': 0.09784774482250214} 08/30/2021 22:14:35 - INFO - __main__ - Step 49878: {'lr': 0.0003816321917245761, 'samples': 9576576, 'steps': 49877, 'loss/train': 1.019940733909607} 08/30/2021 22:14:35 - INFO - __main__ - Step 49879: {'lr': 0.00038162768012740323, 'samples': 9576768, 'steps': 49878, 'loss/train': 1.0620776414871216} 08/30/2021 22:14:37 - INFO - __main__ - Step 49880: {'lr': 0.00038162316847092096, 'samples': 9576960, 'steps': 49879, 'loss/train': 1.82549250125885} 08/30/2021 22:14:37 - INFO - __main__ - Step 49881: {'lr': 0.0003816186567551313, 'samples': 9577152, 'steps': 49880, 'loss/train': 0.7739014625549316} 08/30/2021 22:14:38 - INFO - __main__ - Step 49882: {'lr': 0.0003816141449800364, 'samples': 9577344, 'steps': 49881, 'loss/train': 1.5781736373901367} 08/30/2021 22:14:38 - INFO - __main__ - Step 49883: {'lr': 0.00038160963314563806, 'samples': 9577536, 'steps': 49882, 'loss/train': 2.0784504413604736} 08/30/2021 22:14:38 - INFO - __main__ - Step 49884: {'lr': 0.00038160512125193853, 'samples': 9577728, 'steps': 49883, 'loss/train': 1.4156413078308105} 08/30/2021 22:14:39 - INFO - __main__ - Step 49885: {'lr': 0.0003816006092989397, 'samples': 9577920, 'steps': 49884, 'loss/train': 4.68715763092041} 08/30/2021 22:14:40 - INFO - __main__ - Step 49886: {'lr': 0.0003815960972866437, 'samples': 9578112, 'steps': 49885, 'loss/train': 1.1393882036209106} 08/30/2021 22:14:41 - INFO - __main__ - Step 49887: {'lr': 0.00038159158521505255, 'samples': 9578304, 'steps': 49886, 'loss/train': 1.1316070556640625} 08/30/2021 22:14:41 - INFO - __main__ - Step 49888: {'lr': 0.0003815870730841683, 'samples': 9578496, 'steps': 49887, 'loss/train': 1.9979842901229858} 08/30/2021 22:14:41 - INFO - __main__ - Step 49889: {'lr': 0.00038158256089399287, 'samples': 9578688, 'steps': 49888, 'loss/train': 1.2268280982971191} 08/30/2021 22:14:42 - INFO - __main__ - Step 49890: {'lr': 0.0003815780486445284, 'samples': 9578880, 'steps': 49889, 'loss/train': 1.1332812309265137} 08/30/2021 22:14:43 - INFO - __main__ - Step 49891: {'lr': 0.00038157353633577686, 'samples': 9579072, 'steps': 49890, 'loss/train': 1.4598584175109863} 08/30/2021 22:14:44 - INFO - __main__ - Step 49892: {'lr': 0.0003815690239677403, 'samples': 9579264, 'steps': 49891, 'loss/train': 1.551299810409546} 08/30/2021 22:14:44 - INFO - __main__ - Step 49893: {'lr': 0.00038156451154042084, 'samples': 9579456, 'steps': 49892, 'loss/train': 2.0841121673583984} 08/30/2021 22:14:44 - INFO - __main__ - Step 49894: {'lr': 0.0003815599990538203, 'samples': 9579648, 'steps': 49893, 'loss/train': 3.4649205207824707} 08/30/2021 22:14:45 - INFO - __main__ - Step 49895: {'lr': 0.00038155548650794103, 'samples': 9579840, 'steps': 49894, 'loss/train': 0.7513778209686279} 08/30/2021 22:14:45 - INFO - __main__ - Step 49896: {'lr': 0.00038155097390278484, 'samples': 9580032, 'steps': 49895, 'loss/train': 0.6828315258026123} 08/30/2021 22:14:47 - INFO - __main__ - Step 49897: {'lr': 0.0003815464612383538, 'samples': 9580224, 'steps': 49896, 'loss/train': 1.1336301565170288} 08/30/2021 22:14:47 - INFO - __main__ - Step 49898: {'lr': 0.0003815419485146499, 'samples': 9580416, 'steps': 49897, 'loss/train': 1.6544756889343262} 08/30/2021 22:14:47 - INFO - __main__ - Step 49899: {'lr': 0.0003815374357316753, 'samples': 9580608, 'steps': 49898, 'loss/train': 0.8168324828147888} 08/30/2021 22:14:48 - INFO - __main__ - Step 49900: {'lr': 0.0003815329228894319, 'samples': 9580800, 'steps': 49899, 'loss/train': 1.5095332860946655} 08/30/2021 22:14:48 - INFO - __main__ - Step 49901: {'lr': 0.0003815284099879218, 'samples': 9580992, 'steps': 49900, 'loss/train': 1.1146937608718872} 08/30/2021 22:14:50 - INFO - __main__ - Step 49902: {'lr': 0.00038152389702714705, 'samples': 9581184, 'steps': 49901, 'loss/train': 1.2158877849578857} 08/30/2021 22:14:50 - INFO - __main__ - Step 49903: {'lr': 0.0003815193840071097, 'samples': 9581376, 'steps': 49902, 'loss/train': 1.292009711265564} 08/30/2021 22:14:50 - INFO - __main__ - Step 49904: {'lr': 0.0003815148709278117, 'samples': 9581568, 'steps': 49903, 'loss/train': 1.187833547592163} 08/30/2021 22:14:51 - INFO - __main__ - Step 49905: {'lr': 0.00038151035778925514, 'samples': 9581760, 'steps': 49904, 'loss/train': 1.393072247505188} 08/30/2021 22:14:51 - INFO - __main__ - Step 49906: {'lr': 0.000381505844591442, 'samples': 9581952, 'steps': 49905, 'loss/train': 1.677585244178772} 08/30/2021 22:14:53 - INFO - __main__ - Step 49907: {'lr': 0.0003815013313343744, 'samples': 9582144, 'steps': 49906, 'loss/train': 0.9656486511230469} 08/30/2021 22:14:53 - INFO - __main__ - Step 49908: {'lr': 0.0003814968180180544, 'samples': 9582336, 'steps': 49907, 'loss/train': 0.9414292573928833} 08/30/2021 22:14:54 - INFO - __main__ - Step 49909: {'lr': 0.00038149230464248386, 'samples': 9582528, 'steps': 49908, 'loss/train': 1.4174463748931885} 08/30/2021 22:14:54 - INFO - __main__ - Step 49910: {'lr': 0.000381487791207665, 'samples': 9582720, 'steps': 49909, 'loss/train': 1.4325464963912964} 08/30/2021 22:14:54 - INFO - __main__ - Step 49911: {'lr': 0.0003814832777135997, 'samples': 9582912, 'steps': 49910, 'loss/train': 1.3477137088775635} 08/30/2021 22:14:56 - INFO - __main__ - Step 49912: {'lr': 0.00038147876416029004, 'samples': 9583104, 'steps': 49911, 'loss/train': 1.5271865129470825} 08/30/2021 22:14:57 - INFO - __main__ - Step 49913: {'lr': 0.0003814742505477381, 'samples': 9583296, 'steps': 49912, 'loss/train': 1.6888169050216675} 08/30/2021 22:14:57 - INFO - __main__ - Step 49914: {'lr': 0.0003814697368759459, 'samples': 9583488, 'steps': 49913, 'loss/train': 1.732778787612915} 08/30/2021 22:14:57 - INFO - __main__ - Step 49915: {'lr': 0.0003814652231449155, 'samples': 9583680, 'steps': 49914, 'loss/train': 0.14118877053260803} 08/30/2021 22:14:58 - INFO - __main__ - Step 49916: {'lr': 0.0003814607093546489, 'samples': 9583872, 'steps': 49915, 'loss/train': 2.1029610633850098} 08/30/2021 22:14:58 - INFO - __main__ - Step 49917: {'lr': 0.0003814561955051481, 'samples': 9584064, 'steps': 49916, 'loss/train': 1.1900182962417603} 08/30/2021 22:15:00 - INFO - __main__ - Step 49918: {'lr': 0.00038145168159641515, 'samples': 9584256, 'steps': 49917, 'loss/train': 1.322786808013916} 08/30/2021 22:15:00 - INFO - __main__ - Step 49919: {'lr': 0.0003814471676284521, 'samples': 9584448, 'steps': 49918, 'loss/train': 1.9398250579833984} 08/30/2021 22:15:01 - INFO - __main__ - Step 49920: {'lr': 0.00038144265360126107, 'samples': 9584640, 'steps': 49919, 'loss/train': 0.888759434223175} 08/30/2021 22:15:01 - INFO - __main__ - Step 49921: {'lr': 0.00038143813951484396, 'samples': 9584832, 'steps': 49920, 'loss/train': 1.331196904182434} 08/30/2021 22:15:01 - INFO - __main__ - Step 49922: {'lr': 0.0003814336253692028, 'samples': 9585024, 'steps': 49921, 'loss/train': 1.416749119758606} 08/30/2021 22:15:03 - INFO - __main__ - Step 49923: {'lr': 0.0003814291111643397, 'samples': 9585216, 'steps': 49922, 'loss/train': 0.09901145100593567} 08/30/2021 22:15:03 - INFO - __main__ - Step 49924: {'lr': 0.00038142459690025665, 'samples': 9585408, 'steps': 49923, 'loss/train': 1.4845200777053833} 08/30/2021 22:15:04 - INFO - __main__ - Step 49925: {'lr': 0.0003814200825769558, 'samples': 9585600, 'steps': 49924, 'loss/train': 1.0127054452896118} 08/30/2021 22:15:04 - INFO - __main__ - Step 49926: {'lr': 0.000381415568194439, 'samples': 9585792, 'steps': 49925, 'loss/train': 2.016517162322998} 08/30/2021 22:15:04 - INFO - __main__ - Step 49927: {'lr': 0.00038141105375270846, 'samples': 9585984, 'steps': 49926, 'loss/train': 1.6244580745697021} 08/30/2021 22:15:06 - INFO - __main__ - Step 49928: {'lr': 0.00038140653925176606, 'samples': 9586176, 'steps': 49927, 'loss/train': 1.630874514579773} 08/30/2021 22:15:06 - INFO - __main__ - Step 49929: {'lr': 0.0003814020246916139, 'samples': 9586368, 'steps': 49928, 'loss/train': 0.8663868308067322} 08/30/2021 22:15:07 - INFO - __main__ - Step 49930: {'lr': 0.000381397510072254, 'samples': 9586560, 'steps': 49929, 'loss/train': 0.6792960166931152} 08/30/2021 22:15:07 - INFO - __main__ - Step 49931: {'lr': 0.0003813929953936884, 'samples': 9586752, 'steps': 49930, 'loss/train': 1.2131116390228271} 08/30/2021 22:15:07 - INFO - __main__ - Step 49932: {'lr': 0.00038138848065591923, 'samples': 9586944, 'steps': 49931, 'loss/train': 0.6229634881019592} 08/30/2021 22:15:09 - INFO - __main__ - Step 49933: {'lr': 0.00038138396585894843, 'samples': 9587136, 'steps': 49932, 'loss/train': 1.458230972290039} 08/30/2021 22:15:09 - INFO - __main__ - Step 49934: {'lr': 0.0003813794510027779, 'samples': 9587328, 'steps': 49933, 'loss/train': 0.5613172650337219} 08/30/2021 22:15:10 - INFO - __main__ - Step 49935: {'lr': 0.00038137493608741, 'samples': 9587520, 'steps': 49934, 'loss/train': 1.5147184133529663} 08/30/2021 22:15:10 - INFO - __main__ - Step 49936: {'lr': 0.0003813704211128465, 'samples': 9587712, 'steps': 49935, 'loss/train': 1.3081154823303223} 08/30/2021 22:15:10 - INFO - __main__ - Step 49937: {'lr': 0.0003813659060790895, 'samples': 9587904, 'steps': 49936, 'loss/train': 1.000442385673523} 08/30/2021 22:15:11 - INFO - __main__ - Step 49938: {'lr': 0.00038136139098614107, 'samples': 9588096, 'steps': 49937, 'loss/train': 1.4864379167556763} 08/30/2021 22:15:12 - INFO - __main__ - Step 49939: {'lr': 0.00038135687583400326, 'samples': 9588288, 'steps': 49938, 'loss/train': 1.852515697479248} 08/30/2021 22:15:13 - INFO - __main__ - Step 49940: {'lr': 0.000381352360622678, 'samples': 9588480, 'steps': 49939, 'loss/train': 1.3297425508499146} 08/30/2021 22:15:13 - INFO - __main__ - Step 49941: {'lr': 0.00038134784535216737, 'samples': 9588672, 'steps': 49940, 'loss/train': 1.7343114614486694} 08/30/2021 22:15:14 - INFO - __main__ - Step 49942: {'lr': 0.0003813433300224735, 'samples': 9588864, 'steps': 49941, 'loss/train': 0.04141373187303543} 08/30/2021 22:15:14 - INFO - __main__ - Step 49943: {'lr': 0.0003813388146335983, 'samples': 9589056, 'steps': 49942, 'loss/train': 1.479673981666565} 08/30/2021 22:15:14 - INFO - __main__ - Step 49944: {'lr': 0.00038133429918554395, 'samples': 9589248, 'steps': 49943, 'loss/train': 1.3206608295440674} 08/30/2021 22:15:16 - INFO - __main__ - Step 49945: {'lr': 0.00038132978367831226, 'samples': 9589440, 'steps': 49944, 'loss/train': 1.159934163093567} 08/30/2021 22:15:16 - INFO - __main__ - Step 49946: {'lr': 0.00038132526811190547, 'samples': 9589632, 'steps': 49945, 'loss/train': 0.05921933427453041} 08/30/2021 22:15:17 - INFO - __main__ - Step 49947: {'lr': 0.00038132075248632557, 'samples': 9589824, 'steps': 49946, 'loss/train': 2.090723991394043} 08/30/2021 22:15:17 - INFO - __main__ - Step 49948: {'lr': 0.0003813162368015745, 'samples': 9590016, 'steps': 49947, 'loss/train': 1.540015697479248} 08/30/2021 22:15:17 - INFO - __main__ - Step 49949: {'lr': 0.00038131172105765446, 'samples': 9590208, 'steps': 49948, 'loss/train': 1.2368717193603516} 08/30/2021 22:15:19 - INFO - __main__ - Step 49950: {'lr': 0.0003813072052545673, 'samples': 9590400, 'steps': 49949, 'loss/train': 1.4749137163162231} 08/30/2021 22:15:19 - INFO - __main__ - Step 49951: {'lr': 0.00038130268939231513, 'samples': 9590592, 'steps': 49950, 'loss/train': 1.6987398862838745} 08/30/2021 22:15:20 - INFO - __main__ - Step 49952: {'lr': 0.0003812981734709, 'samples': 9590784, 'steps': 49951, 'loss/train': 1.3168388605117798} 08/30/2021 22:15:20 - INFO - __main__ - Step 49953: {'lr': 0.00038129365749032395, 'samples': 9590976, 'steps': 49952, 'loss/train': 1.61680006980896} 08/30/2021 22:15:20 - INFO - __main__ - Step 49954: {'lr': 0.000381289141450589, 'samples': 9591168, 'steps': 49953, 'loss/train': 1.9050722122192383} 08/30/2021 22:15:21 - INFO - __main__ - Step 49955: {'lr': 0.00038128462535169715, 'samples': 9591360, 'steps': 49954, 'loss/train': 1.700305461883545} 08/30/2021 22:15:22 - INFO - __main__ - Step 49956: {'lr': 0.00038128010919365066, 'samples': 9591552, 'steps': 49955, 'loss/train': 1.3154253959655762} 08/30/2021 22:15:23 - INFO - __main__ - Step 49957: {'lr': 0.0003812755929764512, 'samples': 9591744, 'steps': 49956, 'loss/train': 0.9426714181900024} 08/30/2021 22:15:23 - INFO - __main__ - Step 49958: {'lr': 0.000381271076700101, 'samples': 9591936, 'steps': 49957, 'loss/train': 0.10984140634536743} 08/30/2021 22:15:24 - INFO - __main__ - Step 49959: {'lr': 0.00038126656036460206, 'samples': 9592128, 'steps': 49958, 'loss/train': 0.8538442254066467} 08/30/2021 22:15:24 - INFO - __main__ - Step 49960: {'lr': 0.0003812620439699565, 'samples': 9592320, 'steps': 49959, 'loss/train': 1.570562720298767} 08/30/2021 22:15:26 - INFO - __main__ - Step 49961: {'lr': 0.00038125752751616625, 'samples': 9592512, 'steps': 49960, 'loss/train': 0.10712048411369324} 08/30/2021 22:15:27 - INFO - __main__ - Step 49962: {'lr': 0.00038125301100323344, 'samples': 9592704, 'steps': 49961, 'loss/train': 0.9405786991119385} 08/30/2021 22:15:27 - INFO - __main__ - Step 49963: {'lr': 0.00038124849443116, 'samples': 9592896, 'steps': 49962, 'loss/train': 1.2084598541259766} 08/30/2021 22:15:28 - INFO - __main__ - Step 49964: {'lr': 0.000381243977799948, 'samples': 9593088, 'steps': 49963, 'loss/train': 1.7010899782180786} 08/30/2021 22:15:28 - INFO - __main__ - Step 49965: {'lr': 0.0003812394611095995, 'samples': 9593280, 'steps': 49964, 'loss/train': 1.2085901498794556} 08/30/2021 22:15:30 - INFO - __main__ - Step 49966: {'lr': 0.0003812349443601165, 'samples': 9593472, 'steps': 49965, 'loss/train': 1.409525752067566} 08/30/2021 22:15:30 - INFO - __main__ - Step 49967: {'lr': 0.0003812304275515012, 'samples': 9593664, 'steps': 49966, 'loss/train': 1.1673520803451538} 08/30/2021 22:15:31 - INFO - __main__ - Step 49968: {'lr': 0.00038122591068375536, 'samples': 9593856, 'steps': 49967, 'loss/train': 0.3900246024131775} 08/30/2021 22:15:31 - INFO - __main__ - Step 49969: {'lr': 0.00038122139375688116, 'samples': 9594048, 'steps': 49968, 'loss/train': 1.0771349668502808} 08/30/2021 22:15:32 - INFO - __main__ - Step 49970: {'lr': 0.0003812168767708807, 'samples': 9594240, 'steps': 49969, 'loss/train': 0.16064275801181793} 08/30/2021 22:15:32 - INFO - __main__ - Step 49971: {'lr': 0.0003812123597257559, 'samples': 9594432, 'steps': 49970, 'loss/train': 1.4943517446517944} 08/30/2021 22:15:33 - INFO - __main__ - Step 49972: {'lr': 0.00038120784262150875, 'samples': 9594624, 'steps': 49971, 'loss/train': 0.05315021425485611} 08/30/2021 22:15:34 - INFO - __main__ - Step 49973: {'lr': 0.0003812033254581414, 'samples': 9594816, 'steps': 49972, 'loss/train': 2.0069777965545654} 08/30/2021 22:15:34 - INFO - __main__ - Step 49974: {'lr': 0.0003811988082356559, 'samples': 9595008, 'steps': 49973, 'loss/train': 1.4596290588378906} 08/30/2021 22:15:34 - INFO - __main__ - Step 49975: {'lr': 0.0003811942909540542, 'samples': 9595200, 'steps': 49974, 'loss/train': 1.361367106437683} 08/30/2021 22:15:35 - INFO - __main__ - Step 49976: {'lr': 0.0003811897736133385, 'samples': 9595392, 'steps': 49975, 'loss/train': 1.651120901107788} 08/30/2021 22:15:36 - INFO - __main__ - Step 49977: {'lr': 0.0003811852562135106, 'samples': 9595584, 'steps': 49976, 'loss/train': 1.5983085632324219} 08/30/2021 22:15:37 - INFO - __main__ - Step 49978: {'lr': 0.0003811807387545727, 'samples': 9595776, 'steps': 49977, 'loss/train': 1.715244174003601} 08/30/2021 22:15:37 - INFO - __main__ - Step 49979: {'lr': 0.0003811762212365267, 'samples': 9595968, 'steps': 49978, 'loss/train': 1.5426217317581177} 08/30/2021 22:15:37 - INFO - __main__ - Step 49980: {'lr': 0.0003811717036593748, 'samples': 9596160, 'steps': 49979, 'loss/train': 1.709546685218811} 08/30/2021 22:15:38 - INFO - __main__ - Step 49981: {'lr': 0.00038116718602311896, 'samples': 9596352, 'steps': 49980, 'loss/train': 1.6222771406173706} 08/30/2021 22:15:39 - INFO - __main__ - Step 49982: {'lr': 0.00038116266832776113, 'samples': 9596544, 'steps': 49981, 'loss/train': 1.7393566370010376} 08/30/2021 22:15:40 - INFO - __main__ - Step 49983: {'lr': 0.0003811581505733035, 'samples': 9596736, 'steps': 49982, 'loss/train': 1.9680745601654053} 08/30/2021 22:15:40 - INFO - __main__ - Step 49984: {'lr': 0.000381153632759748, 'samples': 9596928, 'steps': 49983, 'loss/train': 1.2211098670959473} 08/30/2021 22:15:40 - INFO - __main__ - Step 49985: {'lr': 0.0003811491148870967, 'samples': 9597120, 'steps': 49984, 'loss/train': 1.4524140357971191} 08/30/2021 22:15:41 - INFO - __main__ - Step 49986: {'lr': 0.0003811445969553516, 'samples': 9597312, 'steps': 49985, 'loss/train': 1.1627111434936523} 08/30/2021 22:15:42 - INFO - __main__ - Step 49987: {'lr': 0.00038114007896451486, 'samples': 9597504, 'steps': 49986, 'loss/train': 1.5767033100128174} 08/30/2021 22:15:43 - INFO - __main__ - Step 49988: {'lr': 0.0003811355609145883, 'samples': 9597696, 'steps': 49987, 'loss/train': 1.5722547769546509} 08/30/2021 22:15:43 - INFO - __main__ - Step 49989: {'lr': 0.0003811310428055742, 'samples': 9597888, 'steps': 49988, 'loss/train': 0.6168616414070129} 08/30/2021 22:15:43 - INFO - __main__ - Step 49990: {'lr': 0.00038112652463747444, 'samples': 9598080, 'steps': 49989, 'loss/train': 1.0592572689056396} 08/30/2021 22:15:44 - INFO - __main__ - Step 49991: {'lr': 0.00038112200641029104, 'samples': 9598272, 'steps': 49990, 'loss/train': 1.398459792137146} 08/30/2021 22:15:45 - INFO - __main__ - Step 49992: {'lr': 0.00038111748812402616, 'samples': 9598464, 'steps': 49991, 'loss/train': 0.803909957408905} 08/30/2021 22:15:46 - INFO - __main__ - Step 49993: {'lr': 0.0003811129697786817, 'samples': 9598656, 'steps': 49992, 'loss/train': 1.50918710231781} 08/30/2021 22:15:46 - INFO - __main__ - Step 49994: {'lr': 0.00038110845137425976, 'samples': 9598848, 'steps': 49993, 'loss/train': 1.0690501928329468} 08/30/2021 22:15:46 - INFO - __main__ - Step 49995: {'lr': 0.0003811039329107624, 'samples': 9599040, 'steps': 49994, 'loss/train': 1.7483011484146118} 08/30/2021 22:15:47 - INFO - __main__ - Step 49996: {'lr': 0.00038109941438819165, 'samples': 9599232, 'steps': 49995, 'loss/train': 1.6299405097961426} 08/30/2021 22:15:47 - INFO - __main__ - Step 49997: {'lr': 0.00038109489580654955, 'samples': 9599424, 'steps': 49996, 'loss/train': 0.7644880414009094} 08/30/2021 22:15:49 - INFO - __main__ - Step 49998: {'lr': 0.00038109037716583806, 'samples': 9599616, 'steps': 49997, 'loss/train': 1.2841774225234985} 08/30/2021 22:15:50 - INFO - __main__ - Step 49999: {'lr': 0.0003810858584660593, 'samples': 9599808, 'steps': 49998, 'loss/train': 1.5746294260025024} 08/30/2021 22:15:50 - INFO - __main__ - Step 50000: {'lr': 0.0003810813397072152, 'samples': 9600000, 'steps': 49999, 'loss/train': 1.3064301013946533} 08/30/2021 22:15:50 - INFO - __main__ - Step 50001: {'lr': 0.00038107682088930797, 'samples': 9600192, 'steps': 50000, 'loss/train': 1.0298306941986084} 08/30/2021 22:15:51 - INFO - __main__ - Step 50002: {'lr': 0.00038107230201233944, 'samples': 9600384, 'steps': 50001, 'loss/train': 0.0941631868481636} 08/30/2021 22:15:52 - INFO - __main__ - Step 50003: {'lr': 0.00038106778307631187, 'samples': 9600576, 'steps': 50002, 'loss/train': 0.1259710192680359} 08/30/2021 22:15:53 - INFO - __main__ - Step 50004: {'lr': 0.0003810632640812271, 'samples': 9600768, 'steps': 50003, 'loss/train': 1.1675041913986206} 08/30/2021 22:15:53 - INFO - __main__ - Step 50005: {'lr': 0.00038105874502708726, 'samples': 9600960, 'steps': 50004, 'loss/train': 1.560531735420227} 08/30/2021 22:15:53 - INFO - __main__ - Step 50006: {'lr': 0.0003810542259138944, 'samples': 9601152, 'steps': 50005, 'loss/train': 1.4806926250457764} 08/30/2021 22:15:54 - INFO - __main__ - Step 50007: {'lr': 0.0003810497067416505, 'samples': 9601344, 'steps': 50006, 'loss/train': 1.1481035947799683} 08/30/2021 22:15:55 - INFO - __main__ - Step 50008: {'lr': 0.0003810451875103576, 'samples': 9601536, 'steps': 50007, 'loss/train': 1.7544904947280884} 08/30/2021 22:15:56 - INFO - __main__ - Step 50009: {'lr': 0.0003810406682200178, 'samples': 9601728, 'steps': 50008, 'loss/train': 1.4128069877624512} 08/30/2021 22:15:56 - INFO - __main__ - Step 50010: {'lr': 0.0003810361488706331, 'samples': 9601920, 'steps': 50009, 'loss/train': 0.9419867396354675} 08/30/2021 22:15:56 - INFO - __main__ - Step 50011: {'lr': 0.0003810316294622056, 'samples': 9602112, 'steps': 50010, 'loss/train': 0.8903459906578064} 08/30/2021 22:15:57 - INFO - __main__ - Step 50012: {'lr': 0.0003810271099947371, 'samples': 9602304, 'steps': 50011, 'loss/train': 1.6325072050094604} 08/30/2021 22:15:59 - INFO - __main__ - Step 50013: {'lr': 0.00038102259046822993, 'samples': 9602496, 'steps': 50012, 'loss/train': 1.376466155052185} 08/30/2021 22:15:59 - INFO - __main__ - Step 50014: {'lr': 0.00038101807088268595, 'samples': 9602688, 'steps': 50013, 'loss/train': 1.5262771844863892} 08/30/2021 22:16:00 - INFO - __main__ - Step 50015: {'lr': 0.00038101355123810733, 'samples': 9602880, 'steps': 50014, 'loss/train': 1.2302452325820923} 08/30/2021 22:16:00 - INFO - __main__ - Step 50016: {'lr': 0.00038100903153449596, 'samples': 9603072, 'steps': 50015, 'loss/train': 1.1891863346099854} 08/30/2021 22:16:00 - INFO - __main__ - Step 50017: {'lr': 0.00038100451177185395, 'samples': 9603264, 'steps': 50016, 'loss/train': 1.2596502304077148} 08/30/2021 22:16:02 - INFO - __main__ - Step 50018: {'lr': 0.0003809999919501833, 'samples': 9603456, 'steps': 50017, 'loss/train': 1.7209770679473877} 08/30/2021 22:16:03 - INFO - __main__ - Step 50019: {'lr': 0.00038099547206948617, 'samples': 9603648, 'steps': 50018, 'loss/train': 1.014421820640564} 08/30/2021 22:16:03 - INFO - __main__ - Step 50020: {'lr': 0.0003809909521297644, 'samples': 9603840, 'steps': 50019, 'loss/train': 1.2036447525024414} 08/30/2021 22:16:03 - INFO - __main__ - Step 50021: {'lr': 0.00038098643213102014, 'samples': 9604032, 'steps': 50020, 'loss/train': 0.49280133843421936} 08/30/2021 22:16:04 - INFO - __main__ - Step 50022: {'lr': 0.0003809819120732554, 'samples': 9604224, 'steps': 50021, 'loss/train': 1.688100814819336} 08/30/2021 22:16:04 - INFO - __main__ - Step 50023: {'lr': 0.00038097739195647233, 'samples': 9604416, 'steps': 50022, 'loss/train': 1.0814008712768555} 08/30/2021 22:16:05 - INFO - __main__ - Step 50024: {'lr': 0.0003809728717806728, 'samples': 9604608, 'steps': 50023, 'loss/train': 0.11027158796787262} 08/30/2021 22:16:06 - INFO - __main__ - Step 50025: {'lr': 0.00038096835154585897, 'samples': 9604800, 'steps': 50024, 'loss/train': 1.3086692094802856} 08/30/2021 22:16:06 - INFO - __main__ - Step 50026: {'lr': 0.0003809638312520327, 'samples': 9604992, 'steps': 50025, 'loss/train': 1.3395917415618896} 08/30/2021 22:16:07 - INFO - __main__ - Step 50027: {'lr': 0.0003809593108991962, 'samples': 9605184, 'steps': 50026, 'loss/train': 1.5631290674209595} 08/30/2021 22:16:07 - INFO - __main__ - Step 50028: {'lr': 0.0003809547904873515, 'samples': 9605376, 'steps': 50027, 'loss/train': 1.7063641548156738} 08/30/2021 22:16:09 - INFO - __main__ - Step 50029: {'lr': 0.0003809502700165006, 'samples': 9605568, 'steps': 50028, 'loss/train': 1.2550994157791138} 08/30/2021 22:16:09 - INFO - __main__ - Step 50030: {'lr': 0.00038094574948664554, 'samples': 9605760, 'steps': 50029, 'loss/train': 0.6143820881843567} 08/30/2021 22:16:10 - INFO - __main__ - Step 50031: {'lr': 0.00038094122889778824, 'samples': 9605952, 'steps': 50030, 'loss/train': 0.872804582118988} 08/30/2021 22:16:10 - INFO - __main__ - Step 50032: {'lr': 0.000380936708249931, 'samples': 9606144, 'steps': 50031, 'loss/train': 1.2021774053573608} 08/30/2021 22:16:10 - INFO - __main__ - Step 50033: {'lr': 0.0003809321875430756, 'samples': 9606336, 'steps': 50032, 'loss/train': 1.6694682836532593} 08/30/2021 22:16:12 - INFO - __main__ - Step 50034: {'lr': 0.0003809276667772241, 'samples': 9606528, 'steps': 50033, 'loss/train': 2.275981903076172} 08/30/2021 22:16:12 - INFO - __main__ - Step 50035: {'lr': 0.00038092314595237873, 'samples': 9606720, 'steps': 50034, 'loss/train': 1.3710722923278809} 08/30/2021 22:16:13 - INFO - __main__ - Step 50036: {'lr': 0.0003809186250685414, 'samples': 9606912, 'steps': 50035, 'loss/train': 1.6243427991867065} 08/30/2021 22:16:13 - INFO - __main__ - Step 50037: {'lr': 0.0003809141041257141, 'samples': 9607104, 'steps': 50036, 'loss/train': 0.24902775883674622} 08/30/2021 22:16:13 - INFO - __main__ - Step 50038: {'lr': 0.000380909583123899, 'samples': 9607296, 'steps': 50037, 'loss/train': 1.0140602588653564} 08/30/2021 22:16:14 - INFO - __main__ - Step 50039: {'lr': 0.00038090506206309805, 'samples': 9607488, 'steps': 50038, 'loss/train': 1.3978636264801025} 08/30/2021 22:16:16 - INFO - __main__ - Step 50040: {'lr': 0.00038090054094331324, 'samples': 9607680, 'steps': 50039, 'loss/train': 1.7784162759780884} 08/30/2021 22:16:16 - INFO - __main__ - Step 50041: {'lr': 0.0003808960197645467, 'samples': 9607872, 'steps': 50040, 'loss/train': 1.0483201742172241} 08/30/2021 22:16:16 - INFO - __main__ - Step 50042: {'lr': 0.00038089149852680036, 'samples': 9608064, 'steps': 50041, 'loss/train': 1.3781033754348755} 08/30/2021 22:16:17 - INFO - __main__ - Step 50043: {'lr': 0.00038088697723007647, 'samples': 9608256, 'steps': 50042, 'loss/train': 1.945577621459961} 08/30/2021 22:16:17 - INFO - __main__ - Step 50044: {'lr': 0.00038088245587437685, 'samples': 9608448, 'steps': 50043, 'loss/train': 0.03787803649902344} 08/30/2021 22:16:17 - INFO - __main__ - Step 50045: {'lr': 0.00038087793445970363, 'samples': 9608640, 'steps': 50044, 'loss/train': 1.1329152584075928} 08/30/2021 22:16:19 - INFO - __main__ - Step 50046: {'lr': 0.0003808734129860588, 'samples': 9608832, 'steps': 50045, 'loss/train': 1.4633455276489258} 08/30/2021 22:16:20 - INFO - __main__ - Step 50047: {'lr': 0.0003808688914534445, 'samples': 9609024, 'steps': 50046, 'loss/train': 0.5694299340248108} 08/30/2021 22:16:20 - INFO - __main__ - Step 50048: {'lr': 0.00038086436986186267, 'samples': 9609216, 'steps': 50047, 'loss/train': 1.269545555114746} 08/30/2021 22:16:20 - INFO - __main__ - Step 50049: {'lr': 0.00038085984821131536, 'samples': 9609408, 'steps': 50048, 'loss/train': 1.433971643447876} 08/30/2021 22:16:21 - INFO - __main__ - Step 50050: {'lr': 0.00038085532650180464, 'samples': 9609600, 'steps': 50049, 'loss/train': 1.0071122646331787} 08/30/2021 22:16:22 - INFO - __main__ - Step 50051: {'lr': 0.0003808508047333325, 'samples': 9609792, 'steps': 50050, 'loss/train': 0.8194466829299927} 08/30/2021 22:16:23 - INFO - __main__ - Step 50052: {'lr': 0.000380846282905901, 'samples': 9609984, 'steps': 50051, 'loss/train': 1.3815641403198242} 08/30/2021 22:16:23 - INFO - __main__ - Step 50053: {'lr': 0.0003808417610195122, 'samples': 9610176, 'steps': 50052, 'loss/train': 1.128920078277588} 08/30/2021 22:16:23 - INFO - __main__ - Step 50054: {'lr': 0.0003808372390741681, 'samples': 9610368, 'steps': 50053, 'loss/train': 0.8643597960472107} 08/30/2021 22:16:24 - INFO - __main__ - Step 50055: {'lr': 0.0003808327170698708, 'samples': 9610560, 'steps': 50054, 'loss/train': 1.538956642150879} 08/30/2021 22:16:25 - INFO - __main__ - Step 50056: {'lr': 0.0003808281950066223, 'samples': 9610752, 'steps': 50055, 'loss/train': 1.0728232860565186} 08/30/2021 22:16:26 - INFO - __main__ - Step 50057: {'lr': 0.0003808236728844246, 'samples': 9610944, 'steps': 50056, 'loss/train': 1.6719036102294922} 08/30/2021 22:16:26 - INFO - __main__ - Step 50058: {'lr': 0.0003808191507032798, 'samples': 9611136, 'steps': 50057, 'loss/train': 1.0060703754425049} 08/30/2021 22:16:26 - INFO - __main__ - Step 50059: {'lr': 0.00038081462846318984, 'samples': 9611328, 'steps': 50058, 'loss/train': 1.6246259212493896} 08/30/2021 22:16:27 - INFO - __main__ - Step 50060: {'lr': 0.000380810106164157, 'samples': 9611520, 'steps': 50059, 'loss/train': 1.2512034177780151} 08/30/2021 22:16:28 - INFO - __main__ - Step 50061: {'lr': 0.000380805583806183, 'samples': 9611712, 'steps': 50060, 'loss/train': 1.6808745861053467} 08/30/2021 22:16:29 - INFO - __main__ - Step 50062: {'lr': 0.00038080106138927, 'samples': 9611904, 'steps': 50061, 'loss/train': 0.9136414527893066} 08/30/2021 22:16:29 - INFO - __main__ - Step 50063: {'lr': 0.00038079653891342016, 'samples': 9612096, 'steps': 50062, 'loss/train': 2.0557808876037598} 08/30/2021 22:16:29 - INFO - __main__ - Step 50064: {'lr': 0.0003807920163786353, 'samples': 9612288, 'steps': 50063, 'loss/train': 1.7106549739837646} 08/30/2021 22:16:30 - INFO - __main__ - Step 50065: {'lr': 0.00038078749378491763, 'samples': 9612480, 'steps': 50064, 'loss/train': 1.437264323234558} 08/30/2021 22:16:31 - INFO - __main__ - Step 50066: {'lr': 0.00038078297113226925, 'samples': 9612672, 'steps': 50065, 'loss/train': 1.0924086570739746} 08/30/2021 22:16:32 - INFO - __main__ - Step 50067: {'lr': 0.00038077844842069193, 'samples': 9612864, 'steps': 50066, 'loss/train': 1.2689344882965088} 08/30/2021 22:16:32 - INFO - __main__ - Step 50068: {'lr': 0.00038077392565018784, 'samples': 9613056, 'steps': 50067, 'loss/train': 1.675586462020874} 08/30/2021 22:16:32 - INFO - __main__ - Step 50069: {'lr': 0.0003807694028207591, 'samples': 9613248, 'steps': 50068, 'loss/train': 1.4385607242584229} 08/30/2021 22:16:33 - INFO - __main__ - Step 50070: {'lr': 0.0003807648799324077, 'samples': 9613440, 'steps': 50069, 'loss/train': 1.1776790618896484} 08/30/2021 22:16:33 - INFO - __main__ - Step 50071: {'lr': 0.0003807603569851357, 'samples': 9613632, 'steps': 50070, 'loss/train': 0.06844732910394669} 08/30/2021 22:16:36 - INFO - __main__ - Step 50072: {'lr': 0.0003807558339789451, 'samples': 9613824, 'steps': 50071, 'loss/train': 1.8619381189346313} 08/30/2021 22:16:36 - INFO - __main__ - Step 50073: {'lr': 0.00038075131091383783, 'samples': 9614016, 'steps': 50072, 'loss/train': 1.88219153881073} 08/30/2021 22:16:37 - INFO - __main__ - Step 50074: {'lr': 0.0003807467877898161, 'samples': 9614208, 'steps': 50073, 'loss/train': 1.1046810150146484} 08/30/2021 22:16:37 - INFO - __main__ - Step 50075: {'lr': 0.00038074226460688186, 'samples': 9614400, 'steps': 50074, 'loss/train': 0.528259813785553} 08/30/2021 22:16:38 - INFO - __main__ - Step 50076: {'lr': 0.0003807377413650372, 'samples': 9614592, 'steps': 50075, 'loss/train': 0.4769894778728485} 08/30/2021 22:16:38 - INFO - __main__ - Step 50077: {'lr': 0.0003807332180642842, 'samples': 9614784, 'steps': 50076, 'loss/train': 1.3407303094863892} 08/30/2021 22:16:39 - INFO - __main__ - Step 50078: {'lr': 0.00038072869470462465, 'samples': 9614976, 'steps': 50077, 'loss/train': 0.6660121083259583} 08/30/2021 22:16:40 - INFO - __main__ - Step 50079: {'lr': 0.00038072417128606095, 'samples': 9615168, 'steps': 50078, 'loss/train': 1.3219343423843384} 08/30/2021 22:16:40 - INFO - __main__ - Step 50080: {'lr': 0.00038071964780859486, 'samples': 9615360, 'steps': 50079, 'loss/train': 1.218739628791809} 08/30/2021 22:16:41 - INFO - __main__ - Step 50081: {'lr': 0.0003807151242722285, 'samples': 9615552, 'steps': 50080, 'loss/train': 1.5216811895370483} 08/30/2021 22:16:41 - INFO - __main__ - Step 50082: {'lr': 0.00038071060067696393, 'samples': 9615744, 'steps': 50081, 'loss/train': 1.7325550317764282} 08/30/2021 22:16:43 - INFO - __main__ - Step 50083: {'lr': 0.00038070607702280325, 'samples': 9615936, 'steps': 50082, 'loss/train': 1.2911477088928223} 08/30/2021 22:16:43 - INFO - __main__ - Step 50084: {'lr': 0.00038070155330974844, 'samples': 9616128, 'steps': 50083, 'loss/train': 1.4418026208877563} 08/30/2021 22:16:43 - INFO - __main__ - Step 50085: {'lr': 0.0003806970295378014, 'samples': 9616320, 'steps': 50084, 'loss/train': 1.720677375793457} 08/30/2021 22:16:44 - INFO - __main__ - Step 50086: {'lr': 0.00038069250570696433, 'samples': 9616512, 'steps': 50085, 'loss/train': 1.7577153444290161} 08/30/2021 22:16:44 - INFO - __main__ - Step 50087: {'lr': 0.00038068798181723927, 'samples': 9616704, 'steps': 50086, 'loss/train': 1.112426996231079} 08/30/2021 22:16:46 - INFO - __main__ - Step 50088: {'lr': 0.00038068345786862825, 'samples': 9616896, 'steps': 50087, 'loss/train': 1.7923065423965454} 08/30/2021 22:16:46 - INFO - __main__ - Step 50089: {'lr': 0.0003806789338611333, 'samples': 9617088, 'steps': 50088, 'loss/train': 1.0503278970718384} 08/30/2021 22:16:47 - INFO - __main__ - Step 50090: {'lr': 0.00038067440979475635, 'samples': 9617280, 'steps': 50089, 'loss/train': 1.3894175291061401} 08/30/2021 22:16:47 - INFO - __main__ - Step 50091: {'lr': 0.0003806698856694996, 'samples': 9617472, 'steps': 50090, 'loss/train': 1.0337897539138794} 08/30/2021 22:16:47 - INFO - __main__ - Step 50092: {'lr': 0.00038066536148536495, 'samples': 9617664, 'steps': 50091, 'loss/train': 0.5578261613845825} 08/30/2021 22:16:48 - INFO - __main__ - Step 50093: {'lr': 0.00038066083724235455, 'samples': 9617856, 'steps': 50092, 'loss/train': 1.3270683288574219} 08/30/2021 22:16:49 - INFO - __main__ - Step 50094: {'lr': 0.00038065631294047035, 'samples': 9618048, 'steps': 50093, 'loss/train': 1.4695450067520142} 08/30/2021 22:16:50 - INFO - __main__ - Step 50095: {'lr': 0.0003806517885797145, 'samples': 9618240, 'steps': 50094, 'loss/train': 1.1843640804290771} 08/30/2021 22:16:50 - INFO - __main__ - Step 50096: {'lr': 0.0003806472641600889, 'samples': 9618432, 'steps': 50095, 'loss/train': 0.98862624168396} 08/30/2021 22:16:50 - INFO - __main__ - Step 50097: {'lr': 0.00038064273968159575, 'samples': 9618624, 'steps': 50096, 'loss/train': 1.46336030960083} 08/30/2021 22:16:51 - INFO - __main__ - Step 50098: {'lr': 0.00038063821514423694, 'samples': 9618816, 'steps': 50097, 'loss/train': 1.015445590019226} 08/30/2021 22:16:52 - INFO - __main__ - Step 50099: {'lr': 0.00038063369054801456, 'samples': 9619008, 'steps': 50098, 'loss/train': 2.0989749431610107} 08/30/2021 22:16:53 - INFO - __main__ - Step 50100: {'lr': 0.00038062916589293064, 'samples': 9619200, 'steps': 50099, 'loss/train': 0.8163864612579346} 08/30/2021 22:16:53 - INFO - __main__ - Step 50101: {'lr': 0.0003806246411789872, 'samples': 9619392, 'steps': 50100, 'loss/train': 1.8185945749282837} 08/30/2021 22:16:53 - INFO - __main__ - Step 50102: {'lr': 0.00038062011640618636, 'samples': 9619584, 'steps': 50101, 'loss/train': 1.1335031986236572} 08/30/2021 22:16:54 - INFO - __main__ - Step 50103: {'lr': 0.00038061559157453014, 'samples': 9619776, 'steps': 50102, 'loss/train': 1.093127727508545} 08/30/2021 22:16:55 - INFO - __main__ - Step 50104: {'lr': 0.00038061106668402055, 'samples': 9619968, 'steps': 50103, 'loss/train': 0.33705976605415344} 08/30/2021 22:16:56 - INFO - __main__ - Step 50105: {'lr': 0.0003806065417346596, 'samples': 9620160, 'steps': 50104, 'loss/train': 1.2665024995803833} 08/30/2021 22:16:56 - INFO - __main__ - Step 50106: {'lr': 0.00038060201672644934, 'samples': 9620352, 'steps': 50105, 'loss/train': 1.192352294921875} 08/30/2021 22:16:56 - INFO - __main__ - Step 50107: {'lr': 0.00038059749165939184, 'samples': 9620544, 'steps': 50106, 'loss/train': 1.0885837078094482} 08/30/2021 22:16:57 - INFO - __main__ - Step 50108: {'lr': 0.00038059296653348917, 'samples': 9620736, 'steps': 50107, 'loss/train': 1.464859962463379} 08/30/2021 22:16:58 - INFO - __main__ - Step 50109: {'lr': 0.00038058844134874326, 'samples': 9620928, 'steps': 50108, 'loss/train': 0.5432927012443542} 08/30/2021 22:16:59 - INFO - __main__ - Step 50110: {'lr': 0.0003805839161051563, 'samples': 9621120, 'steps': 50109, 'loss/train': 1.8091411590576172} 08/30/2021 22:16:59 - INFO - __main__ - Step 50111: {'lr': 0.00038057939080273016, 'samples': 9621312, 'steps': 50110, 'loss/train': 1.6873996257781982} 08/30/2021 22:16:59 - INFO - __main__ - Step 50112: {'lr': 0.00038057486544146703, 'samples': 9621504, 'steps': 50111, 'loss/train': 1.5108884572982788} 08/30/2021 22:17:00 - INFO - __main__ - Step 50113: {'lr': 0.0003805703400213688, 'samples': 9621696, 'steps': 50112, 'loss/train': 0.902436375617981} 08/30/2021 22:17:01 - INFO - __main__ - Step 50114: {'lr': 0.0003805658145424376, 'samples': 9621888, 'steps': 50113, 'loss/train': 1.0551910400390625} 08/30/2021 22:17:02 - INFO - __main__ - Step 50115: {'lr': 0.00038056128900467546, 'samples': 9622080, 'steps': 50114, 'loss/train': 0.05183906480669975} 08/30/2021 22:17:02 - INFO - __main__ - Step 50116: {'lr': 0.00038055676340808446, 'samples': 9622272, 'steps': 50115, 'loss/train': 1.3731881380081177} 08/30/2021 22:17:03 - INFO - __main__ - Step 50117: {'lr': 0.00038055223775266666, 'samples': 9622464, 'steps': 50116, 'loss/train': 1.4042104482650757} 08/30/2021 22:17:03 - INFO - __main__ - Step 50118: {'lr': 0.0003805477120384239, 'samples': 9622656, 'steps': 50117, 'loss/train': 1.8434213399887085} 08/30/2021 22:17:04 - INFO - __main__ - Step 50119: {'lr': 0.00038054318626535845, 'samples': 9622848, 'steps': 50118, 'loss/train': 0.9863468408584595} 08/30/2021 22:17:05 - INFO - __main__ - Step 50120: {'lr': 0.00038053866043347216, 'samples': 9623040, 'steps': 50119, 'loss/train': 1.615834355354309} 08/30/2021 22:17:05 - INFO - __main__ - Step 50121: {'lr': 0.00038053413454276725, 'samples': 9623232, 'steps': 50120, 'loss/train': 2.0354504585266113} 08/30/2021 22:17:06 - INFO - __main__ - Step 50122: {'lr': 0.00038052960859324557, 'samples': 9623424, 'steps': 50121, 'loss/train': 0.7636065483093262} 08/30/2021 22:17:06 - INFO - __main__ - Step 50123: {'lr': 0.0003805250825849094, 'samples': 9623616, 'steps': 50122, 'loss/train': 1.6923234462738037} 08/30/2021 22:17:08 - INFO - __main__ - Step 50124: {'lr': 0.0003805205565177606, 'samples': 9623808, 'steps': 50123, 'loss/train': 1.1398009061813354} 08/30/2021 22:17:08 - INFO - __main__ - Step 50125: {'lr': 0.0003805160303918013, 'samples': 9624000, 'steps': 50124, 'loss/train': 0.85948246717453} 08/30/2021 22:17:09 - INFO - __main__ - Step 50126: {'lr': 0.0003805115042070333, 'samples': 9624192, 'steps': 50125, 'loss/train': 1.2117767333984375} 08/30/2021 22:17:09 - INFO - __main__ - Step 50127: {'lr': 0.000380506977963459, 'samples': 9624384, 'steps': 50126, 'loss/train': 1.723537564277649} 08/30/2021 22:17:09 - INFO - __main__ - Step 50128: {'lr': 0.00038050245166108024, 'samples': 9624576, 'steps': 50127, 'loss/train': 1.4526232481002808} 08/30/2021 22:17:11 - INFO - __main__ - Step 50129: {'lr': 0.000380497925299899, 'samples': 9624768, 'steps': 50128, 'loss/train': 1.0510504245758057} 08/30/2021 22:17:12 - INFO - __main__ - Step 50130: {'lr': 0.0003804933988799175, 'samples': 9624960, 'steps': 50129, 'loss/train': 0.7681604623794556} 08/30/2021 22:17:12 - INFO - __main__ - Step 50131: {'lr': 0.0003804888724011377, 'samples': 9625152, 'steps': 50130, 'loss/train': 1.7104781866073608} 08/30/2021 22:17:12 - INFO - __main__ - Step 50132: {'lr': 0.00038048434586356164, 'samples': 9625344, 'steps': 50131, 'loss/train': 0.9986642599105835} 08/30/2021 22:17:13 - INFO - __main__ - Step 50133: {'lr': 0.0003804798192671912, 'samples': 9625536, 'steps': 50132, 'loss/train': 1.1631078720092773} 08/30/2021 22:17:15 - INFO - __main__ - Step 50134: {'lr': 0.00038047529261202876, 'samples': 9625728, 'steps': 50133, 'loss/train': 0.39178749918937683} 08/30/2021 22:17:15 - INFO - __main__ - Step 50135: {'lr': 0.0003804707658980761, 'samples': 9625920, 'steps': 50134, 'loss/train': 1.1198288202285767} 08/30/2021 22:17:16 - INFO - __main__ - Step 50136: {'lr': 0.0003804662391253352, 'samples': 9626112, 'steps': 50135, 'loss/train': 1.1382800340652466} 08/30/2021 22:17:16 - INFO - __main__ - Step 50137: {'lr': 0.00038046171229380837, 'samples': 9626304, 'steps': 50136, 'loss/train': 1.644508957862854} 08/30/2021 22:17:16 - INFO - __main__ - Step 50138: {'lr': 0.0003804571854034975, 'samples': 9626496, 'steps': 50137, 'loss/train': 0.9787462949752808} 08/30/2021 22:17:17 - INFO - __main__ - Step 50139: {'lr': 0.0003804526584544046, 'samples': 9626688, 'steps': 50138, 'loss/train': 0.9741015434265137} 08/30/2021 22:17:18 - INFO - __main__ - Step 50140: {'lr': 0.0003804481314465317, 'samples': 9626880, 'steps': 50139, 'loss/train': 0.9444351196289062} 08/30/2021 22:17:19 - INFO - __main__ - Step 50141: {'lr': 0.0003804436043798809, 'samples': 9627072, 'steps': 50140, 'loss/train': 1.2524003982543945} 08/30/2021 22:17:19 - INFO - __main__ - Step 50142: {'lr': 0.00038043907725445424, 'samples': 9627264, 'steps': 50141, 'loss/train': 1.5802050828933716} 08/30/2021 22:17:19 - INFO - __main__ - Step 50143: {'lr': 0.00038043455007025375, 'samples': 9627456, 'steps': 50142, 'loss/train': 1.3089563846588135} 08/30/2021 22:17:20 - INFO - __main__ - Step 50144: {'lr': 0.00038043002282728153, 'samples': 9627648, 'steps': 50143, 'loss/train': 1.042677879333496} 08/30/2021 22:17:21 - INFO - __main__ - Step 50145: {'lr': 0.00038042549552553954, 'samples': 9627840, 'steps': 50144, 'loss/train': 1.0575764179229736} 08/30/2021 22:17:22 - INFO - __main__ - Step 50146: {'lr': 0.00038042096816502967, 'samples': 9628032, 'steps': 50145, 'loss/train': 0.6534714698791504} 08/30/2021 22:17:22 - INFO - __main__ - Step 50147: {'lr': 0.0003804164407457543, 'samples': 9628224, 'steps': 50146, 'loss/train': 1.341222882270813} 08/30/2021 22:17:22 - INFO - __main__ - Step 50148: {'lr': 0.0003804119132677152, 'samples': 9628416, 'steps': 50147, 'loss/train': 1.072319746017456} 08/30/2021 22:17:23 - INFO - __main__ - Step 50149: {'lr': 0.0003804073857309145, 'samples': 9628608, 'steps': 50148, 'loss/train': 1.2148807048797607} 08/30/2021 22:17:24 - INFO - __main__ - Step 50150: {'lr': 0.00038040285813535434, 'samples': 9628800, 'steps': 50149, 'loss/train': 1.297415018081665} 08/30/2021 22:17:25 - INFO - __main__ - Step 50151: {'lr': 0.0003803983304810367, 'samples': 9628992, 'steps': 50150, 'loss/train': 1.0965957641601562} 08/30/2021 22:17:25 - INFO - __main__ - Step 50152: {'lr': 0.0003803938027679634, 'samples': 9629184, 'steps': 50151, 'loss/train': 1.2132761478424072} 08/30/2021 22:17:25 - INFO - __main__ - Step 50153: {'lr': 0.0003803892749961368, 'samples': 9629376, 'steps': 50152, 'loss/train': 1.1536738872528076} 08/30/2021 22:17:26 - INFO - __main__ - Step 50154: {'lr': 0.0003803847471655587, 'samples': 9629568, 'steps': 50153, 'loss/train': 1.0383530855178833} 08/30/2021 22:17:26 - INFO - __main__ - Step 50155: {'lr': 0.00038038021927623133, 'samples': 9629760, 'steps': 50154, 'loss/train': 5.870924472808838} 08/30/2021 22:17:28 - INFO - __main__ - Step 50156: {'lr': 0.00038037569132815663, 'samples': 9629952, 'steps': 50155, 'loss/train': 0.046317603439092636} 08/30/2021 22:17:28 - INFO - __main__ - Step 50157: {'lr': 0.0003803711633213367, 'samples': 9630144, 'steps': 50156, 'loss/train': 1.8635798692703247} 08/30/2021 22:17:29 - INFO - __main__ - Step 50158: {'lr': 0.0003803666352557735, 'samples': 9630336, 'steps': 50157, 'loss/train': 1.14349365234375} 08/30/2021 22:17:29 - INFO - __main__ - Step 50159: {'lr': 0.0003803621071314691, 'samples': 9630528, 'steps': 50158, 'loss/train': 0.5619362592697144} 08/30/2021 22:17:29 - INFO - __main__ - Step 50160: {'lr': 0.0003803575789484255, 'samples': 9630720, 'steps': 50159, 'loss/train': 1.2430082559585571} 08/30/2021 22:17:31 - INFO - __main__ - Step 50161: {'lr': 0.0003803530507066448, 'samples': 9630912, 'steps': 50160, 'loss/train': 1.3744922876358032} 08/30/2021 22:17:32 - INFO - __main__ - Step 50162: {'lr': 0.00038034852240612907, 'samples': 9631104, 'steps': 50161, 'loss/train': 1.3385076522827148} 08/30/2021 22:17:32 - INFO - __main__ - Step 50163: {'lr': 0.00038034399404688024, 'samples': 9631296, 'steps': 50162, 'loss/train': 0.037527214735746384} 08/30/2021 22:17:32 - INFO - __main__ - Step 50164: {'lr': 0.00038033946562890055, 'samples': 9631488, 'steps': 50163, 'loss/train': 1.4838230609893799} 08/30/2021 22:17:33 - INFO - __main__ - Step 50165: {'lr': 0.0003803349371521918, 'samples': 9631680, 'steps': 50164, 'loss/train': 1.676430106163025} 08/30/2021 22:17:33 - INFO - __main__ - Step 50166: {'lr': 0.00038033040861675617, 'samples': 9631872, 'steps': 50165, 'loss/train': 1.8885140419006348} 08/30/2021 22:17:33 - INFO - __main__ - Step 50167: {'lr': 0.0003803258800225956, 'samples': 9632064, 'steps': 50166, 'loss/train': 1.8753783702850342} 08/30/2021 22:17:35 - INFO - __main__ - Step 50168: {'lr': 0.0003803213513697123, 'samples': 9632256, 'steps': 50167, 'loss/train': 1.232132911682129} 08/30/2021 22:17:35 - INFO - __main__ - Step 50169: {'lr': 0.0003803168226581082, 'samples': 9632448, 'steps': 50168, 'loss/train': 1.1798596382141113} 08/30/2021 22:17:36 - INFO - __main__ - Step 50170: {'lr': 0.00038031229388778526, 'samples': 9632640, 'steps': 50169, 'loss/train': 1.291684627532959} 08/30/2021 22:17:36 - INFO - __main__ - Step 50171: {'lr': 0.00038030776505874577, 'samples': 9632832, 'steps': 50170, 'loss/train': 1.5367623567581177} 08/30/2021 22:17:36 - INFO - __main__ - Step 50172: {'lr': 0.0003803032361709915, 'samples': 9633024, 'steps': 50171, 'loss/train': 1.1160755157470703} 08/30/2021 22:17:38 - INFO - __main__ - Step 50173: {'lr': 0.00038029870722452455, 'samples': 9633216, 'steps': 50172, 'loss/train': 1.8505613803863525} 08/30/2021 22:17:38 - INFO - __main__ - Step 50174: {'lr': 0.0003802941782193471, 'samples': 9633408, 'steps': 50173, 'loss/train': 1.6613337993621826} 08/30/2021 22:17:39 - INFO - __main__ - Step 50175: {'lr': 0.00038028964915546107, 'samples': 9633600, 'steps': 50174, 'loss/train': 1.0176063776016235} 08/30/2021 22:17:39 - INFO - __main__ - Step 50176: {'lr': 0.00038028512003286853, 'samples': 9633792, 'steps': 50175, 'loss/train': 1.6487009525299072} 08/30/2021 22:17:39 - INFO - __main__ - Step 50177: {'lr': 0.00038028059085157165, 'samples': 9633984, 'steps': 50176, 'loss/train': 1.3987069129943848} 08/30/2021 22:17:40 - INFO - __main__ - Step 50178: {'lr': 0.0003802760616115722, 'samples': 9634176, 'steps': 50177, 'loss/train': 1.7523374557495117} 08/30/2021 22:17:42 - INFO - __main__ - Step 50179: {'lr': 0.0003802715323128724, 'samples': 9634368, 'steps': 50178, 'loss/train': 1.3484731912612915} 08/30/2021 22:17:42 - INFO - __main__ - Step 50180: {'lr': 0.00038026700295547424, 'samples': 9634560, 'steps': 50179, 'loss/train': 1.0260473489761353} 08/30/2021 22:17:42 - INFO - __main__ - Step 50181: {'lr': 0.0003802624735393798, 'samples': 9634752, 'steps': 50180, 'loss/train': 1.3888907432556152} 08/30/2021 22:17:43 - INFO - __main__ - Step 50182: {'lr': 0.00038025794406459115, 'samples': 9634944, 'steps': 50181, 'loss/train': 1.3685919046401978} 08/30/2021 22:17:43 - INFO - __main__ - Step 50183: {'lr': 0.00038025341453111017, 'samples': 9635136, 'steps': 50182, 'loss/train': 0.9743738174438477} 08/30/2021 22:17:45 - INFO - __main__ - Step 50184: {'lr': 0.0003802488849389391, 'samples': 9635328, 'steps': 50183, 'loss/train': 1.1471487283706665} 08/30/2021 22:17:45 - INFO - __main__ - Step 50185: {'lr': 0.0003802443552880799, 'samples': 9635520, 'steps': 50184, 'loss/train': 0.0739254504442215} 08/30/2021 22:17:46 - INFO - __main__ - Step 50186: {'lr': 0.00038023982557853456, 'samples': 9635712, 'steps': 50185, 'loss/train': 1.7395588159561157} 08/30/2021 22:17:46 - INFO - __main__ - Step 50187: {'lr': 0.00038023529581030516, 'samples': 9635904, 'steps': 50186, 'loss/train': 1.0424436330795288} 08/30/2021 22:17:46 - INFO - __main__ - Step 50188: {'lr': 0.00038023076598339375, 'samples': 9636096, 'steps': 50187, 'loss/train': 0.9814770817756653} 08/30/2021 22:17:48 - INFO - __main__ - Step 50189: {'lr': 0.0003802262360978024, 'samples': 9636288, 'steps': 50188, 'loss/train': 1.5759168863296509} 08/30/2021 22:17:48 - INFO - __main__ - Step 50190: {'lr': 0.00038022170615353314, 'samples': 9636480, 'steps': 50189, 'loss/train': 1.680824875831604} 08/30/2021 22:17:49 - INFO - __main__ - Step 50191: {'lr': 0.00038021717615058795, 'samples': 9636672, 'steps': 50190, 'loss/train': 1.755846619606018} 08/30/2021 22:17:49 - INFO - __main__ - Step 50192: {'lr': 0.00038021264608896884, 'samples': 9636864, 'steps': 50191, 'loss/train': 0.7993203997612} 08/30/2021 22:17:49 - INFO - __main__ - Step 50193: {'lr': 0.000380208115968678, 'samples': 9637056, 'steps': 50192, 'loss/train': 1.2606840133666992} 08/30/2021 22:17:51 - INFO - __main__ - Step 50194: {'lr': 0.00038020358578971737, 'samples': 9637248, 'steps': 50193, 'loss/train': 0.9867759346961975} 08/30/2021 22:17:51 - INFO - __main__ - Step 50195: {'lr': 0.000380199055552089, 'samples': 9637440, 'steps': 50194, 'loss/train': 0.3496303856372833} 08/30/2021 22:17:52 - INFO - __main__ - Step 50196: {'lr': 0.000380194525255795, 'samples': 9637632, 'steps': 50195, 'loss/train': 1.1464449167251587} 08/30/2021 22:17:52 - INFO - __main__ - Step 50197: {'lr': 0.0003801899949008373, 'samples': 9637824, 'steps': 50196, 'loss/train': 0.5101274847984314} 08/30/2021 22:17:52 - INFO - __main__ - Step 50198: {'lr': 0.000380185464487218, 'samples': 9638016, 'steps': 50197, 'loss/train': 1.5690900087356567} 08/30/2021 22:17:54 - INFO - __main__ - Step 50199: {'lr': 0.00038018093401493916, 'samples': 9638208, 'steps': 50198, 'loss/train': 0.6451753973960876} 08/30/2021 22:17:54 - INFO - __main__ - Step 50200: {'lr': 0.00038017640348400286, 'samples': 9638400, 'steps': 50199, 'loss/train': 1.6852253675460815} 08/30/2021 22:17:55 - INFO - __main__ - Step 50201: {'lr': 0.000380171872894411, 'samples': 9638592, 'steps': 50200, 'loss/train': 1.1046643257141113} 08/30/2021 22:17:55 - INFO - __main__ - Step 50202: {'lr': 0.00038016734224616565, 'samples': 9638784, 'steps': 50201, 'loss/train': 2.0317699909210205} 08/30/2021 22:17:55 - INFO - __main__ - Step 50203: {'lr': 0.000380162811539269, 'samples': 9638976, 'steps': 50202, 'loss/train': 1.5801845788955688} 08/30/2021 22:17:56 - INFO - __main__ - Step 50204: {'lr': 0.0003801582807737229, 'samples': 9639168, 'steps': 50203, 'loss/train': 1.3906358480453491} 08/30/2021 22:17:57 - INFO - __main__ - Step 50205: {'lr': 0.00038015374994952966, 'samples': 9639360, 'steps': 50204, 'loss/train': 1.4581975936889648} 08/30/2021 22:17:58 - INFO - __main__ - Step 50206: {'lr': 0.0003801492190666911, 'samples': 9639552, 'steps': 50205, 'loss/train': 1.3912845849990845} 08/30/2021 22:17:58 - INFO - __main__ - Step 50207: {'lr': 0.00038014468812520917, 'samples': 9639744, 'steps': 50206, 'loss/train': 1.1278738975524902} 08/30/2021 22:17:59 - INFO - __main__ - Step 50208: {'lr': 0.00038014015712508617, 'samples': 9639936, 'steps': 50207, 'loss/train': 1.8937790393829346} 08/30/2021 22:17:59 - INFO - __main__ - Step 50209: {'lr': 0.000380135626066324, 'samples': 9640128, 'steps': 50208, 'loss/train': 1.2781879901885986} 08/30/2021 22:18:00 - INFO - __main__ - Step 50210: {'lr': 0.00038013109494892467, 'samples': 9640320, 'steps': 50209, 'loss/train': 0.06123127415776253} 08/30/2021 22:18:01 - INFO - __main__ - Step 50211: {'lr': 0.00038012656377289035, 'samples': 9640512, 'steps': 50210, 'loss/train': 1.832229495048523} 08/30/2021 22:18:01 - INFO - __main__ - Step 50212: {'lr': 0.000380122032538223, 'samples': 9640704, 'steps': 50211, 'loss/train': 1.796499252319336} 08/30/2021 22:18:02 - INFO - __main__ - Step 50213: {'lr': 0.0003801175012449246, 'samples': 9640896, 'steps': 50212, 'loss/train': 1.6021469831466675} 08/30/2021 22:18:02 - INFO - __main__ - Step 50214: {'lr': 0.0003801129698929974, 'samples': 9641088, 'steps': 50213, 'loss/train': 0.9251230359077454} 08/30/2021 22:18:03 - INFO - __main__ - Step 50215: {'lr': 0.00038010843848244316, 'samples': 9641280, 'steps': 50214, 'loss/train': 1.1046028137207031} 08/30/2021 22:18:04 - INFO - __main__ - Step 50216: {'lr': 0.00038010390701326415, 'samples': 9641472, 'steps': 50215, 'loss/train': 1.921939730644226} 08/30/2021 22:18:04 - INFO - __main__ - Step 50217: {'lr': 0.00038009937548546223, 'samples': 9641664, 'steps': 50216, 'loss/train': 1.8867669105529785} 08/30/2021 22:18:04 - INFO - __main__ - Step 50218: {'lr': 0.0003800948438990397, 'samples': 9641856, 'steps': 50217, 'loss/train': 1.297231674194336} 08/30/2021 22:18:05 - INFO - __main__ - Step 50219: {'lr': 0.0003800903122539983, 'samples': 9642048, 'steps': 50218, 'loss/train': 3.336740016937256} 08/30/2021 22:18:06 - INFO - __main__ - Step 50220: {'lr': 0.00038008578055034024, 'samples': 9642240, 'steps': 50219, 'loss/train': 1.1903597116470337} 08/30/2021 22:18:07 - INFO - __main__ - Step 50221: {'lr': 0.0003800812487880676, 'samples': 9642432, 'steps': 50220, 'loss/train': 1.0843539237976074} 08/30/2021 22:18:07 - INFO - __main__ - Step 50222: {'lr': 0.00038007671696718226, 'samples': 9642624, 'steps': 50221, 'loss/train': 1.0503097772598267} 08/30/2021 22:18:07 - INFO - __main__ - Step 50223: {'lr': 0.0003800721850876864, 'samples': 9642816, 'steps': 50222, 'loss/train': 1.3597859144210815} 08/30/2021 22:18:08 - INFO - __main__ - Step 50224: {'lr': 0.00038006765314958205, 'samples': 9643008, 'steps': 50223, 'loss/train': 1.6349124908447266} 08/30/2021 22:18:09 - INFO - __main__ - Step 50225: {'lr': 0.00038006312115287125, 'samples': 9643200, 'steps': 50224, 'loss/train': 1.5726463794708252} 08/30/2021 22:18:10 - INFO - __main__ - Step 50226: {'lr': 0.00038005858909755596, 'samples': 9643392, 'steps': 50225, 'loss/train': 1.8197311162948608} 08/30/2021 22:18:10 - INFO - __main__ - Step 50227: {'lr': 0.00038005405698363824, 'samples': 9643584, 'steps': 50226, 'loss/train': 0.7995738387107849} 08/30/2021 22:18:10 - INFO - __main__ - Step 50228: {'lr': 0.0003800495248111202, 'samples': 9643776, 'steps': 50227, 'loss/train': 1.4944809675216675} 08/30/2021 22:18:11 - INFO - __main__ - Step 50229: {'lr': 0.00038004499258000393, 'samples': 9643968, 'steps': 50228, 'loss/train': 1.3478763103485107} 08/30/2021 22:18:11 - INFO - __main__ - Step 50230: {'lr': 0.0003800404602902913, 'samples': 9644160, 'steps': 50229, 'loss/train': 1.4178478717803955} 08/30/2021 22:18:12 - INFO - __main__ - Step 50231: {'lr': 0.0003800359279419845, 'samples': 9644352, 'steps': 50230, 'loss/train': 1.462038278579712} 08/30/2021 22:18:13 - INFO - __main__ - Step 50232: {'lr': 0.0003800313955350855, 'samples': 9644544, 'steps': 50231, 'loss/train': 2.0806963443756104} 08/30/2021 22:18:13 - INFO - __main__ - Step 50233: {'lr': 0.0003800268630695963, 'samples': 9644736, 'steps': 50232, 'loss/train': 1.3585331439971924} 08/30/2021 22:18:14 - INFO - __main__ - Step 50234: {'lr': 0.00038002233054551906, 'samples': 9644928, 'steps': 50233, 'loss/train': 1.4059019088745117} 08/30/2021 22:18:14 - INFO - __main__ - Step 50235: {'lr': 0.00038001779796285575, 'samples': 9645120, 'steps': 50234, 'loss/train': 1.7459365129470825} 08/30/2021 22:18:16 - INFO - __main__ - Step 50236: {'lr': 0.0003800132653216084, 'samples': 9645312, 'steps': 50235, 'loss/train': 1.4470959901809692} 08/30/2021 22:18:16 - INFO - __main__ - Step 50237: {'lr': 0.00038000873262177914, 'samples': 9645504, 'steps': 50236, 'loss/train': 1.6705679893493652} 08/30/2021 22:18:17 - INFO - __main__ - Step 50238: {'lr': 0.00038000419986336997, 'samples': 9645696, 'steps': 50237, 'loss/train': 1.4107708930969238} 08/30/2021 22:18:17 - INFO - __main__ - Step 50239: {'lr': 0.0003799996670463828, 'samples': 9645888, 'steps': 50238, 'loss/train': 1.6455039978027344} 08/30/2021 22:18:17 - INFO - __main__ - Step 50240: {'lr': 0.0003799951341708199, 'samples': 9646080, 'steps': 50239, 'loss/train': 1.4050010442733765} 08/30/2021 22:18:19 - INFO - __main__ - Step 50241: {'lr': 0.0003799906012366832, 'samples': 9646272, 'steps': 50240, 'loss/train': 1.0024943351745605} 08/30/2021 22:18:20 - INFO - __main__ - Step 50242: {'lr': 0.0003799860682439746, 'samples': 9646464, 'steps': 50241, 'loss/train': 0.7941561341285706} 08/30/2021 22:18:20 - INFO - __main__ - Step 50243: {'lr': 0.0003799815351926964, 'samples': 9646656, 'steps': 50242, 'loss/train': 0.028776539489626884} 08/30/2021 22:18:20 - INFO - __main__ - Step 50244: {'lr': 0.0003799770020828505, 'samples': 9646848, 'steps': 50243, 'loss/train': 1.7470147609710693} 08/30/2021 22:18:21 - INFO - __main__ - Step 50245: {'lr': 0.000379972468914439, 'samples': 9647040, 'steps': 50244, 'loss/train': 1.233689546585083} 08/30/2021 22:18:21 - INFO - __main__ - Step 50246: {'lr': 0.0003799679356874639, 'samples': 9647232, 'steps': 50245, 'loss/train': 4.052657604217529} 08/30/2021 22:18:23 - INFO - __main__ - Step 50247: {'lr': 0.0003799634024019272, 'samples': 9647424, 'steps': 50246, 'loss/train': 0.2852233946323395} 08/30/2021 22:18:23 - INFO - __main__ - Step 50248: {'lr': 0.0003799588690578311, 'samples': 9647616, 'steps': 50247, 'loss/train': 1.3783186674118042} 08/30/2021 22:18:23 - INFO - __main__ - Step 50249: {'lr': 0.0003799543356551773, 'samples': 9647808, 'steps': 50248, 'loss/train': 0.5411971807479858} 08/30/2021 22:18:24 - INFO - __main__ - Step 50250: {'lr': 0.00037994980219396835, 'samples': 9648000, 'steps': 50249, 'loss/train': 1.6253989934921265} 08/30/2021 22:18:24 - INFO - __main__ - Step 50251: {'lr': 0.00037994526867420595, 'samples': 9648192, 'steps': 50250, 'loss/train': 1.4940087795257568} 08/30/2021 22:18:26 - INFO - __main__ - Step 50252: {'lr': 0.0003799407350958922, 'samples': 9648384, 'steps': 50251, 'loss/train': 1.0193008184432983} 08/30/2021 22:18:26 - INFO - __main__ - Step 50253: {'lr': 0.00037993620145902914, 'samples': 9648576, 'steps': 50252, 'loss/train': 1.3059289455413818} 08/30/2021 22:18:26 - INFO - __main__ - Step 50254: {'lr': 0.00037993166776361883, 'samples': 9648768, 'steps': 50253, 'loss/train': 1.4135570526123047} 08/30/2021 22:18:27 - INFO - __main__ - Step 50255: {'lr': 0.0003799271340096633, 'samples': 9648960, 'steps': 50254, 'loss/train': 1.5801522731781006} 08/30/2021 22:18:27 - INFO - __main__ - Step 50256: {'lr': 0.00037992260019716463, 'samples': 9649152, 'steps': 50255, 'loss/train': 0.34532809257507324} 08/30/2021 22:18:29 - INFO - __main__ - Step 50257: {'lr': 0.00037991806632612485, 'samples': 9649344, 'steps': 50256, 'loss/train': 1.2366377115249634} 08/30/2021 22:18:29 - INFO - __main__ - Step 50258: {'lr': 0.000379913532396546, 'samples': 9649536, 'steps': 50257, 'loss/train': 1.3541903495788574} 08/30/2021 22:18:29 - INFO - __main__ - Step 50259: {'lr': 0.0003799089984084302, 'samples': 9649728, 'steps': 50258, 'loss/train': 0.9174428582191467} 08/30/2021 22:18:30 - INFO - __main__ - Step 50260: {'lr': 0.00037990446436177925, 'samples': 9649920, 'steps': 50259, 'loss/train': 1.7744241952896118} 08/30/2021 22:18:30 - INFO - __main__ - Step 50261: {'lr': 0.0003798999302565954, 'samples': 9650112, 'steps': 50260, 'loss/train': 0.7895450592041016} 08/30/2021 22:18:32 - INFO - __main__ - Step 50262: {'lr': 0.0003798953960928807, 'samples': 9650304, 'steps': 50261, 'loss/train': 1.240599274635315} 08/30/2021 22:18:32 - INFO - __main__ - Step 50263: {'lr': 0.0003798908618706371, 'samples': 9650496, 'steps': 50262, 'loss/train': 1.2873766422271729} 08/30/2021 22:18:32 - INFO - __main__ - Step 50264: {'lr': 0.0003798863275898667, 'samples': 9650688, 'steps': 50263, 'loss/train': 1.3467903137207031} 08/30/2021 22:18:33 - INFO - __main__ - Step 50265: {'lr': 0.00037988179325057156, 'samples': 9650880, 'steps': 50264, 'loss/train': 1.462780237197876} 08/30/2021 22:18:33 - INFO - __main__ - Step 50266: {'lr': 0.0003798772588527536, 'samples': 9651072, 'steps': 50265, 'loss/train': 1.1951463222503662} 08/30/2021 22:18:35 - INFO - __main__ - Step 50267: {'lr': 0.000379872724396415, 'samples': 9651264, 'steps': 50266, 'loss/train': 0.9749053716659546} 08/30/2021 22:18:35 - INFO - __main__ - Step 50268: {'lr': 0.00037986818988155775, 'samples': 9651456, 'steps': 50267, 'loss/train': 1.768110752105713} 08/30/2021 22:18:36 - INFO - __main__ - Step 50269: {'lr': 0.0003798636553081839, 'samples': 9651648, 'steps': 50268, 'loss/train': 1.5099670886993408} 08/30/2021 22:18:36 - INFO - __main__ - Step 50270: {'lr': 0.0003798591206762955, 'samples': 9651840, 'steps': 50269, 'loss/train': 1.041815996170044} 08/30/2021 22:18:36 - INFO - __main__ - Step 50271: {'lr': 0.0003798545859858945, 'samples': 9652032, 'steps': 50270, 'loss/train': 1.6618454456329346} 08/30/2021 22:18:37 - INFO - __main__ - Step 50272: {'lr': 0.0003798500512369832, 'samples': 9652224, 'steps': 50271, 'loss/train': 1.0841186046600342} 08/30/2021 22:18:38 - INFO - __main__ - Step 50273: {'lr': 0.00037984551642956336, 'samples': 9652416, 'steps': 50272, 'loss/train': 1.355236291885376} 08/30/2021 22:18:39 - INFO - __main__ - Step 50274: {'lr': 0.0003798409815636371, 'samples': 9652608, 'steps': 50273, 'loss/train': 1.4197198152542114} 08/30/2021 22:18:39 - INFO - __main__ - Step 50275: {'lr': 0.00037983644663920656, 'samples': 9652800, 'steps': 50274, 'loss/train': 1.5416332483291626} 08/30/2021 22:18:39 - INFO - __main__ - Step 50276: {'lr': 0.0003798319116562737, 'samples': 9652992, 'steps': 50275, 'loss/train': 1.149187684059143} 08/30/2021 22:18:40 - INFO - __main__ - Step 50277: {'lr': 0.00037982737661484056, 'samples': 9653184, 'steps': 50276, 'loss/train': 1.7272168397903442} 08/30/2021 22:18:41 - INFO - __main__ - Step 50278: {'lr': 0.00037982284151490933, 'samples': 9653376, 'steps': 50277, 'loss/train': 1.2712172269821167} 08/30/2021 22:18:41 - INFO - __main__ - Step 50279: {'lr': 0.00037981830635648177, 'samples': 9653568, 'steps': 50278, 'loss/train': 1.16634202003479} 08/30/2021 22:18:42 - INFO - __main__ - Step 50280: {'lr': 0.0003798137711395602, 'samples': 9653760, 'steps': 50279, 'loss/train': 1.7253309488296509} 08/30/2021 22:18:42 - INFO - __main__ - Step 50281: {'lr': 0.00037980923586414646, 'samples': 9653952, 'steps': 50280, 'loss/train': 1.3690147399902344} 08/30/2021 22:18:43 - INFO - __main__ - Step 50282: {'lr': 0.0003798047005302427, 'samples': 9654144, 'steps': 50281, 'loss/train': 1.2669169902801514} 08/30/2021 22:18:44 - INFO - __main__ - Step 50283: {'lr': 0.000379800165137851, 'samples': 9654336, 'steps': 50282, 'loss/train': 1.4882246255874634} 08/30/2021 22:18:45 - INFO - __main__ - Step 50284: {'lr': 0.00037979562968697324, 'samples': 9654528, 'steps': 50283, 'loss/train': 1.9820116758346558} 08/30/2021 22:18:45 - INFO - __main__ - Step 50285: {'lr': 0.0003797910941776117, 'samples': 9654720, 'steps': 50284, 'loss/train': 1.7118568420410156} 08/30/2021 22:18:46 - INFO - __main__ - Step 50286: {'lr': 0.00037978655860976826, 'samples': 9654912, 'steps': 50285, 'loss/train': 1.5190916061401367} 08/30/2021 22:18:46 - INFO - __main__ - Step 50287: {'lr': 0.00037978202298344496, 'samples': 9655104, 'steps': 50286, 'loss/train': 1.8288257122039795} 08/30/2021 22:18:48 - INFO - __main__ - Step 50288: {'lr': 0.0003797774872986439, 'samples': 9655296, 'steps': 50287, 'loss/train': 0.6033830642700195} 08/30/2021 22:18:49 - INFO - __main__ - Step 50289: {'lr': 0.00037977295155536706, 'samples': 9655488, 'steps': 50288, 'loss/train': 1.1985756158828735} 08/30/2021 22:18:49 - INFO - __main__ - Step 50290: {'lr': 0.00037976841575361665, 'samples': 9655680, 'steps': 50289, 'loss/train': 0.9769416451454163} 08/30/2021 22:18:49 - INFO - __main__ - Step 50291: {'lr': 0.00037976387989339445, 'samples': 9655872, 'steps': 50290, 'loss/train': 1.0939730405807495} 08/30/2021 22:18:50 - INFO - __main__ - Step 50292: {'lr': 0.0003797593439747028, 'samples': 9656064, 'steps': 50291, 'loss/train': 1.545101523399353} 08/30/2021 22:18:50 - INFO - __main__ - Step 50293: {'lr': 0.0003797548079975435, 'samples': 9656256, 'steps': 50292, 'loss/train': 1.7050976753234863} 08/30/2021 22:18:51 - INFO - __main__ - Step 50294: {'lr': 0.0003797502719619187, 'samples': 9656448, 'steps': 50293, 'loss/train': 0.9694483876228333} 08/30/2021 22:18:52 - INFO - __main__ - Step 50295: {'lr': 0.0003797457358678304, 'samples': 9656640, 'steps': 50294, 'loss/train': 2.092941999435425} 08/30/2021 22:18:52 - INFO - __main__ - Step 50296: {'lr': 0.0003797411997152807, 'samples': 9656832, 'steps': 50295, 'loss/train': 0.906765341758728} 08/30/2021 22:18:53 - INFO - __main__ - Step 50297: {'lr': 0.0003797366635042716, 'samples': 9657024, 'steps': 50296, 'loss/train': 1.4587798118591309} 08/30/2021 22:18:53 - INFO - __main__ - Step 50298: {'lr': 0.0003797321272348052, 'samples': 9657216, 'steps': 50297, 'loss/train': 1.3294745683670044} 08/30/2021 22:18:54 - INFO - __main__ - Step 50299: {'lr': 0.00037972759090688354, 'samples': 9657408, 'steps': 50298, 'loss/train': 1.305353045463562} 08/30/2021 22:18:55 - INFO - __main__ - Step 50300: {'lr': 0.0003797230545205086, 'samples': 9657600, 'steps': 50299, 'loss/train': 1.376690149307251} 08/30/2021 22:18:55 - INFO - __main__ - Step 50301: {'lr': 0.00037971851807568237, 'samples': 9657792, 'steps': 50300, 'loss/train': 1.4243135452270508} 08/30/2021 22:18:56 - INFO - __main__ - Step 50302: {'lr': 0.000379713981572407, 'samples': 9657984, 'steps': 50301, 'loss/train': 1.6837401390075684} 08/30/2021 22:18:56 - INFO - __main__ - Step 50303: {'lr': 0.0003797094450106846, 'samples': 9658176, 'steps': 50302, 'loss/train': 0.6461941599845886} 08/30/2021 22:18:57 - INFO - __main__ - Step 50304: {'lr': 0.00037970490839051707, 'samples': 9658368, 'steps': 50303, 'loss/train': 1.561486840248108} 08/30/2021 22:18:58 - INFO - __main__ - Step 50305: {'lr': 0.00037970037171190655, 'samples': 9658560, 'steps': 50304, 'loss/train': 1.327067494392395} 08/30/2021 22:18:58 - INFO - __main__ - Step 50306: {'lr': 0.000379695834974855, 'samples': 9658752, 'steps': 50305, 'loss/train': 1.5158920288085938} 08/30/2021 22:18:58 - INFO - __main__ - Step 50307: {'lr': 0.0003796912981793645, 'samples': 9658944, 'steps': 50306, 'loss/train': 1.2947555780410767} 08/30/2021 22:18:59 - INFO - __main__ - Step 50308: {'lr': 0.0003796867613254371, 'samples': 9659136, 'steps': 50307, 'loss/train': 1.4602837562561035} 08/30/2021 22:19:00 - INFO - __main__ - Step 50309: {'lr': 0.0003796822244130749, 'samples': 9659328, 'steps': 50308, 'loss/train': 1.7762531042099} 08/30/2021 22:19:01 - INFO - __main__ - Step 50310: {'lr': 0.00037967768744227984, 'samples': 9659520, 'steps': 50309, 'loss/train': 1.1557931900024414} 08/30/2021 22:19:01 - INFO - __main__ - Step 50311: {'lr': 0.000379673150413054, 'samples': 9659712, 'steps': 50310, 'loss/train': 1.5500409603118896} 08/30/2021 22:19:01 - INFO - __main__ - Step 50312: {'lr': 0.00037966861332539947, 'samples': 9659904, 'steps': 50311, 'loss/train': 1.2352476119995117} 08/30/2021 22:19:02 - INFO - __main__ - Step 50313: {'lr': 0.0003796640761793183, 'samples': 9660096, 'steps': 50312, 'loss/train': 1.4126312732696533} 08/30/2021 22:19:03 - INFO - __main__ - Step 50314: {'lr': 0.00037965953897481244, 'samples': 9660288, 'steps': 50313, 'loss/train': 1.2851961851119995} 08/30/2021 22:19:04 - INFO - __main__ - Step 50315: {'lr': 0.00037965500171188406, 'samples': 9660480, 'steps': 50314, 'loss/train': 0.9955987334251404} 08/30/2021 22:19:04 - INFO - __main__ - Step 50316: {'lr': 0.00037965046439053507, 'samples': 9660672, 'steps': 50315, 'loss/train': 1.4403796195983887} 08/30/2021 22:19:04 - INFO - __main__ - Step 50317: {'lr': 0.00037964592701076753, 'samples': 9660864, 'steps': 50316, 'loss/train': 0.4701976180076599} 08/30/2021 22:19:05 - INFO - __main__ - Step 50318: {'lr': 0.00037964138957258367, 'samples': 9661056, 'steps': 50317, 'loss/train': 1.1875450611114502} 08/30/2021 22:19:06 - INFO - __main__ - Step 50319: {'lr': 0.0003796368520759854, 'samples': 9661248, 'steps': 50318, 'loss/train': 1.6138051748275757} 08/30/2021 22:19:07 - INFO - __main__ - Step 50320: {'lr': 0.00037963231452097467, 'samples': 9661440, 'steps': 50319, 'loss/train': 0.9892135262489319} 08/30/2021 22:19:07 - INFO - __main__ - Step 50321: {'lr': 0.00037962777690755365, 'samples': 9661632, 'steps': 50320, 'loss/train': 1.0777478218078613} 08/30/2021 22:19:07 - INFO - __main__ - Step 50322: {'lr': 0.00037962323923572427, 'samples': 9661824, 'steps': 50321, 'loss/train': 1.306260347366333} 08/30/2021 22:19:08 - INFO - __main__ - Step 50323: {'lr': 0.0003796187015054888, 'samples': 9662016, 'steps': 50322, 'loss/train': 1.6018210649490356} 08/30/2021 22:19:09 - INFO - __main__ - Step 50324: {'lr': 0.00037961416371684907, 'samples': 9662208, 'steps': 50323, 'loss/train': 1.436275839805603} 08/30/2021 22:19:10 - INFO - __main__ - Step 50325: {'lr': 0.0003796096258698073, 'samples': 9662400, 'steps': 50324, 'loss/train': 5.0564165115356445} 08/30/2021 22:19:10 - INFO - __main__ - Step 50326: {'lr': 0.0003796050879643653, 'samples': 9662592, 'steps': 50325, 'loss/train': 0.43818843364715576} 08/30/2021 22:19:10 - INFO - __main__ - Step 50327: {'lr': 0.0003796005500005253, 'samples': 9662784, 'steps': 50326, 'loss/train': 1.1391857862472534} 08/30/2021 22:19:11 - INFO - __main__ - Step 50328: {'lr': 0.0003795960119782893, 'samples': 9662976, 'steps': 50327, 'loss/train': 0.9795698523521423} 08/30/2021 22:19:11 - INFO - __main__ - Step 50329: {'lr': 0.0003795914738976594, 'samples': 9663168, 'steps': 50328, 'loss/train': 1.904693841934204} 08/30/2021 22:19:13 - INFO - __main__ - Step 50330: {'lr': 0.00037958693575863747, 'samples': 9663360, 'steps': 50329, 'loss/train': 1.0364373922348022} 08/30/2021 22:19:13 - INFO - __main__ - Step 50331: {'lr': 0.0003795823975612257, 'samples': 9663552, 'steps': 50330, 'loss/train': 1.6892534494400024} 08/30/2021 22:19:13 - INFO - __main__ - Step 50332: {'lr': 0.0003795778593054261, 'samples': 9663744, 'steps': 50331, 'loss/train': 1.587531566619873} 08/30/2021 22:19:14 - INFO - __main__ - Step 50333: {'lr': 0.00037957332099124066, 'samples': 9663936, 'steps': 50332, 'loss/train': 1.622420072555542} 08/30/2021 22:19:14 - INFO - __main__ - Step 50334: {'lr': 0.00037956878261867163, 'samples': 9664128, 'steps': 50333, 'loss/train': 0.9953628182411194} 08/30/2021 22:19:16 - INFO - __main__ - Step 50335: {'lr': 0.0003795642441877208, 'samples': 9664320, 'steps': 50334, 'loss/train': 0.8345320224761963} 08/30/2021 22:19:16 - INFO - __main__ - Step 50336: {'lr': 0.0003795597056983903, 'samples': 9664512, 'steps': 50335, 'loss/train': 1.5275577306747437} 08/30/2021 22:19:17 - INFO - __main__ - Step 50337: {'lr': 0.0003795551671506823, 'samples': 9664704, 'steps': 50336, 'loss/train': 0.9670859575271606} 08/30/2021 22:19:17 - INFO - __main__ - Step 50338: {'lr': 0.0003795506285445987, 'samples': 9664896, 'steps': 50337, 'loss/train': 1.4572319984436035} 08/30/2021 22:19:18 - INFO - __main__ - Step 50339: {'lr': 0.0003795460898801415, 'samples': 9665088, 'steps': 50338, 'loss/train': 0.7685204148292542} 08/30/2021 22:19:18 - INFO - __main__ - Step 50340: {'lr': 0.00037954155115731294, 'samples': 9665280, 'steps': 50339, 'loss/train': 0.5451868772506714} 08/30/2021 22:19:20 - INFO - __main__ - Step 50341: {'lr': 0.0003795370123761149, 'samples': 9665472, 'steps': 50340, 'loss/train': 0.10526406764984131} 08/30/2021 22:19:20 - INFO - __main__ - Step 50342: {'lr': 0.00037953247353654946, 'samples': 9665664, 'steps': 50341, 'loss/train': 1.0455020666122437} 08/30/2021 22:19:21 - INFO - __main__ - Step 50343: {'lr': 0.00037952793463861867, 'samples': 9665856, 'steps': 50342, 'loss/train': 1.2337244749069214} 08/30/2021 22:19:21 - INFO - __main__ - Step 50344: {'lr': 0.0003795233956823246, 'samples': 9666048, 'steps': 50343, 'loss/train': 1.4961755275726318} 08/30/2021 22:19:21 - INFO - __main__ - Step 50345: {'lr': 0.0003795188566676694, 'samples': 9666240, 'steps': 50344, 'loss/train': 1.1911262273788452} 08/30/2021 22:19:23 - INFO - __main__ - Step 50346: {'lr': 0.00037951431759465496, 'samples': 9666432, 'steps': 50345, 'loss/train': 1.1223008632659912} 08/30/2021 22:19:23 - INFO - __main__ - Step 50347: {'lr': 0.0003795097784632833, 'samples': 9666624, 'steps': 50346, 'loss/train': 1.3112791776657104} 08/30/2021 22:19:24 - INFO - __main__ - Step 50348: {'lr': 0.00037950523927355657, 'samples': 9666816, 'steps': 50347, 'loss/train': 1.2560820579528809} 08/30/2021 22:19:24 - INFO - __main__ - Step 50349: {'lr': 0.0003795007000254768, 'samples': 9667008, 'steps': 50348, 'loss/train': 1.2496765851974487} 08/30/2021 22:19:24 - INFO - __main__ - Step 50350: {'lr': 0.00037949616071904593, 'samples': 9667200, 'steps': 50349, 'loss/train': 1.2681217193603516} 08/30/2021 22:19:26 - INFO - __main__ - Step 50351: {'lr': 0.0003794916213542662, 'samples': 9667392, 'steps': 50350, 'loss/train': 1.5068633556365967} 08/30/2021 22:19:26 - INFO - __main__ - Step 50352: {'lr': 0.00037948708193113947, 'samples': 9667584, 'steps': 50351, 'loss/train': 1.3616275787353516} 08/30/2021 22:19:27 - INFO - __main__ - Step 50353: {'lr': 0.00037948254244966786, 'samples': 9667776, 'steps': 50352, 'loss/train': 0.043509628623723984} 08/30/2021 22:19:27 - INFO - __main__ - Step 50354: {'lr': 0.00037947800290985344, 'samples': 9667968, 'steps': 50353, 'loss/train': 0.15662576258182526} 08/30/2021 22:19:27 - INFO - __main__ - Step 50355: {'lr': 0.00037947346331169816, 'samples': 9668160, 'steps': 50354, 'loss/train': 1.4839528799057007} 08/30/2021 22:19:29 - INFO - __main__ - Step 50356: {'lr': 0.00037946892365520423, 'samples': 9668352, 'steps': 50355, 'loss/train': 1.3777185678482056} 08/30/2021 22:19:29 - INFO - __main__ - Step 50357: {'lr': 0.00037946438394037356, 'samples': 9668544, 'steps': 50356, 'loss/train': 1.4273455142974854} 08/30/2021 22:19:30 - INFO - __main__ - Step 50358: {'lr': 0.00037945984416720826, 'samples': 9668736, 'steps': 50357, 'loss/train': 0.8957129716873169} 08/30/2021 22:19:30 - INFO - __main__ - Step 50359: {'lr': 0.0003794553043357104, 'samples': 9668928, 'steps': 50358, 'loss/train': 0.31405848264694214} 08/30/2021 22:19:30 - INFO - __main__ - Step 50360: {'lr': 0.0003794507644458819, 'samples': 9669120, 'steps': 50359, 'loss/train': 1.2366201877593994} 08/30/2021 22:19:32 - INFO - __main__ - Step 50361: {'lr': 0.00037944622449772485, 'samples': 9669312, 'steps': 50360, 'loss/train': 2.2917444705963135} 08/30/2021 22:19:33 - INFO - __main__ - Step 50362: {'lr': 0.0003794416844912414, 'samples': 9669504, 'steps': 50361, 'loss/train': 1.1970480680465698} 08/30/2021 22:19:33 - INFO - __main__ - Step 50363: {'lr': 0.0003794371444264335, 'samples': 9669696, 'steps': 50362, 'loss/train': 1.3240857124328613} 08/30/2021 22:19:33 - INFO - __main__ - Step 50364: {'lr': 0.00037943260430330317, 'samples': 9669888, 'steps': 50363, 'loss/train': 1.0201549530029297} 08/30/2021 22:19:34 - INFO - __main__ - Step 50365: {'lr': 0.00037942806412185254, 'samples': 9670080, 'steps': 50364, 'loss/train': 0.054349396377801895} 08/30/2021 22:19:35 - INFO - __main__ - Step 50366: {'lr': 0.0003794235238820837, 'samples': 9670272, 'steps': 50365, 'loss/train': 1.5971604585647583} 08/30/2021 22:19:35 - INFO - __main__ - Step 50367: {'lr': 0.0003794189835839985, 'samples': 9670464, 'steps': 50366, 'loss/train': 1.0613186359405518} 08/30/2021 22:19:36 - INFO - __main__ - Step 50368: {'lr': 0.0003794144432275992, 'samples': 9670656, 'steps': 50367, 'loss/train': 1.5632760524749756} 08/30/2021 22:19:36 - INFO - __main__ - Step 50369: {'lr': 0.0003794099028128877, 'samples': 9670848, 'steps': 50368, 'loss/train': 0.7975529432296753} 08/30/2021 22:19:37 - INFO - __main__ - Step 50370: {'lr': 0.0003794053623398661, 'samples': 9671040, 'steps': 50369, 'loss/train': 1.3893669843673706} 08/30/2021 22:19:37 - INFO - __main__ - Step 50371: {'lr': 0.00037940082180853643, 'samples': 9671232, 'steps': 50370, 'loss/train': 1.3412561416625977} 08/30/2021 22:19:38 - INFO - __main__ - Step 50372: {'lr': 0.0003793962812189008, 'samples': 9671424, 'steps': 50371, 'loss/train': 0.7391544580459595} 08/30/2021 22:19:39 - INFO - __main__ - Step 50373: {'lr': 0.00037939174057096114, 'samples': 9671616, 'steps': 50372, 'loss/train': 0.9940875768661499} 08/30/2021 22:19:39 - INFO - __main__ - Step 50374: {'lr': 0.0003793871998647196, 'samples': 9671808, 'steps': 50373, 'loss/train': 1.8421117067337036} 08/30/2021 22:19:40 - INFO - __main__ - Step 50375: {'lr': 0.00037938265910017813, 'samples': 9672000, 'steps': 50374, 'loss/train': 1.3282018899917603} 08/30/2021 22:19:40 - INFO - __main__ - Step 50376: {'lr': 0.0003793781182773388, 'samples': 9672192, 'steps': 50375, 'loss/train': 1.5118070840835571} 08/30/2021 22:19:41 - INFO - __main__ - Step 50377: {'lr': 0.00037937357739620383, 'samples': 9672384, 'steps': 50376, 'loss/train': 1.5946418046951294} 08/30/2021 22:19:42 - INFO - __main__ - Step 50378: {'lr': 0.000379369036456775, 'samples': 9672576, 'steps': 50377, 'loss/train': 1.3112256526947021} 08/30/2021 22:19:42 - INFO - __main__ - Step 50379: {'lr': 0.00037936449545905457, 'samples': 9672768, 'steps': 50378, 'loss/train': 1.4268401861190796} 08/30/2021 22:19:43 - INFO - __main__ - Step 50380: {'lr': 0.0003793599544030444, 'samples': 9672960, 'steps': 50379, 'loss/train': 1.6437456607818604} 08/30/2021 22:19:43 - INFO - __main__ - Step 50381: {'lr': 0.00037935541328874665, 'samples': 9673152, 'steps': 50380, 'loss/train': 1.082747459411621} 08/30/2021 22:19:45 - INFO - __main__ - Step 50382: {'lr': 0.0003793508721161634, 'samples': 9673344, 'steps': 50381, 'loss/train': 0.9482505321502686} 08/30/2021 22:19:45 - INFO - __main__ - Step 50383: {'lr': 0.00037934633088529656, 'samples': 9673536, 'steps': 50382, 'loss/train': 1.4113882780075073} 08/30/2021 22:19:45 - INFO - __main__ - Step 50384: {'lr': 0.00037934178959614834, 'samples': 9673728, 'steps': 50383, 'loss/train': 1.3113954067230225} 08/30/2021 22:19:46 - INFO - __main__ - Step 50385: {'lr': 0.00037933724824872067, 'samples': 9673920, 'steps': 50384, 'loss/train': 0.44477683305740356} 08/30/2021 22:19:46 - INFO - __main__ - Step 50386: {'lr': 0.00037933270684301567, 'samples': 9674112, 'steps': 50385, 'loss/train': 1.4813883304595947} 08/30/2021 22:19:46 - INFO - __main__ - Step 50387: {'lr': 0.00037932816537903535, 'samples': 9674304, 'steps': 50386, 'loss/train': 1.17421293258667} 08/30/2021 22:19:48 - INFO - __main__ - Step 50388: {'lr': 0.0003793236238567817, 'samples': 9674496, 'steps': 50387, 'loss/train': 0.2824392318725586} 08/30/2021 22:19:48 - INFO - __main__ - Step 50389: {'lr': 0.00037931908227625686, 'samples': 9674688, 'steps': 50388, 'loss/train': 1.0637861490249634} 08/30/2021 22:19:49 - INFO - __main__ - Step 50390: {'lr': 0.0003793145406374628, 'samples': 9674880, 'steps': 50389, 'loss/train': 2.0855588912963867} 08/30/2021 22:19:49 - INFO - __main__ - Step 50391: {'lr': 0.0003793099989404016, 'samples': 9675072, 'steps': 50390, 'loss/train': 2.438366651535034} 08/30/2021 22:19:50 - INFO - __main__ - Step 50392: {'lr': 0.00037930545718507536, 'samples': 9675264, 'steps': 50391, 'loss/train': 0.3896178603172302} 08/30/2021 22:19:51 - INFO - __main__ - Step 50393: {'lr': 0.000379300915371486, 'samples': 9675456, 'steps': 50392, 'loss/train': 0.053256504237651825} 08/30/2021 22:19:52 - INFO - __main__ - Step 50394: {'lr': 0.00037929637349963573, 'samples': 9675648, 'steps': 50393, 'loss/train': 1.3573461771011353} 08/30/2021 22:19:52 - INFO - __main__ - Step 50395: {'lr': 0.00037929183156952653, 'samples': 9675840, 'steps': 50394, 'loss/train': 1.1020805835723877} 08/30/2021 22:19:52 - INFO - __main__ - Step 50396: {'lr': 0.00037928728958116034, 'samples': 9676032, 'steps': 50395, 'loss/train': 1.466937780380249} 08/30/2021 22:19:53 - INFO - __main__ - Step 50397: {'lr': 0.0003792827475345393, 'samples': 9676224, 'steps': 50396, 'loss/train': 2.017697334289551} 08/30/2021 22:19:55 - INFO - __main__ - Step 50398: {'lr': 0.00037927820542966545, 'samples': 9676416, 'steps': 50397, 'loss/train': 0.3912416100502014} 08/30/2021 22:19:55 - INFO - __main__ - Step 50399: {'lr': 0.0003792736632665409, 'samples': 9676608, 'steps': 50398, 'loss/train': 0.9029219150543213} 08/30/2021 22:19:55 - INFO - __main__ - Step 50400: {'lr': 0.0003792691210451676, 'samples': 9676800, 'steps': 50399, 'loss/train': 1.422010064125061} 08/30/2021 22:19:56 - INFO - __main__ - Step 50401: {'lr': 0.0003792645787655476, 'samples': 9676992, 'steps': 50400, 'loss/train': 1.333550214767456} 08/30/2021 22:19:56 - INFO - __main__ - Step 50402: {'lr': 0.000379260036427683, 'samples': 9677184, 'steps': 50401, 'loss/train': 1.3777899742126465} 08/30/2021 22:19:58 - INFO - __main__ - Step 50403: {'lr': 0.0003792554940315758, 'samples': 9677376, 'steps': 50402, 'loss/train': 1.3697956800460815} 08/30/2021 22:19:58 - INFO - __main__ - Step 50404: {'lr': 0.00037925095157722807, 'samples': 9677568, 'steps': 50403, 'loss/train': 1.6141688823699951} 08/30/2021 22:19:59 - INFO - __main__ - Step 50405: {'lr': 0.0003792464090646419, 'samples': 9677760, 'steps': 50404, 'loss/train': 1.0716619491577148} 08/30/2021 22:19:59 - INFO - __main__ - Step 50406: {'lr': 0.00037924186649381924, 'samples': 9677952, 'steps': 50405, 'loss/train': 1.2296751737594604} 08/30/2021 22:19:59 - INFO - __main__ - Step 50407: {'lr': 0.00037923732386476225, 'samples': 9678144, 'steps': 50406, 'loss/train': 1.3345345258712769} 08/30/2021 22:20:01 - INFO - __main__ - Step 50408: {'lr': 0.0003792327811774728, 'samples': 9678336, 'steps': 50407, 'loss/train': 0.9169405698776245} 08/30/2021 22:20:01 - INFO - __main__ - Step 50409: {'lr': 0.00037922823843195317, 'samples': 9678528, 'steps': 50408, 'loss/train': 1.1381680965423584} 08/30/2021 22:20:02 - INFO - __main__ - Step 50410: {'lr': 0.00037922369562820525, 'samples': 9678720, 'steps': 50409, 'loss/train': 1.4404726028442383} 08/30/2021 22:20:02 - INFO - __main__ - Step 50411: {'lr': 0.00037921915276623106, 'samples': 9678912, 'steps': 50410, 'loss/train': 1.7571897506713867} 08/30/2021 22:20:02 - INFO - __main__ - Step 50412: {'lr': 0.00037921460984603284, 'samples': 9679104, 'steps': 50411, 'loss/train': 1.0104024410247803} 08/30/2021 22:20:03 - INFO - __main__ - Step 50413: {'lr': 0.0003792100668676125, 'samples': 9679296, 'steps': 50412, 'loss/train': 0.17325729131698608} 08/30/2021 22:20:04 - INFO - __main__ - Step 50414: {'lr': 0.000379205523830972, 'samples': 9679488, 'steps': 50413, 'loss/train': 1.3279976844787598} 08/30/2021 22:20:05 - INFO - __main__ - Step 50415: {'lr': 0.0003792009807361135, 'samples': 9679680, 'steps': 50414, 'loss/train': 1.4849002361297607} 08/30/2021 22:20:05 - INFO - __main__ - Step 50416: {'lr': 0.00037919643758303913, 'samples': 9679872, 'steps': 50415, 'loss/train': 1.2370009422302246} 08/30/2021 22:20:05 - INFO - __main__ - Step 50417: {'lr': 0.0003791918943717507, 'samples': 9680064, 'steps': 50416, 'loss/train': 0.8366214632987976} 08/30/2021 22:20:06 - INFO - __main__ - Step 50418: {'lr': 0.0003791873511022505, 'samples': 9680256, 'steps': 50417, 'loss/train': 0.03460828959941864} 08/30/2021 22:20:07 - INFO - __main__ - Step 50419: {'lr': 0.0003791828077745405, 'samples': 9680448, 'steps': 50418, 'loss/train': 1.2640575170516968} 08/30/2021 22:20:08 - INFO - __main__ - Step 50420: {'lr': 0.00037917826438862263, 'samples': 9680640, 'steps': 50419, 'loss/train': 1.0997360944747925} 08/30/2021 22:20:08 - INFO - __main__ - Step 50421: {'lr': 0.0003791737209444991, 'samples': 9680832, 'steps': 50420, 'loss/train': 0.8631041646003723} 08/30/2021 22:20:08 - INFO - __main__ - Step 50422: {'lr': 0.00037916917744217185, 'samples': 9681024, 'steps': 50421, 'loss/train': 1.4901387691497803} 08/30/2021 22:20:09 - INFO - __main__ - Step 50423: {'lr': 0.0003791646338816429, 'samples': 9681216, 'steps': 50422, 'loss/train': 1.4181979894638062} 08/30/2021 22:20:10 - INFO - __main__ - Step 50424: {'lr': 0.0003791600902629144, 'samples': 9681408, 'steps': 50423, 'loss/train': 1.0080450773239136} 08/30/2021 22:20:11 - INFO - __main__ - Step 50425: {'lr': 0.0003791555465859884, 'samples': 9681600, 'steps': 50424, 'loss/train': 1.7133841514587402} 08/30/2021 22:20:11 - INFO - __main__ - Step 50426: {'lr': 0.0003791510028508669, 'samples': 9681792, 'steps': 50425, 'loss/train': 1.6686477661132812} 08/30/2021 22:20:12 - INFO - __main__ - Step 50427: {'lr': 0.0003791464590575519, 'samples': 9681984, 'steps': 50426, 'loss/train': 1.200631022453308} 08/30/2021 22:20:12 - INFO - __main__ - Step 50428: {'lr': 0.0003791419152060455, 'samples': 9682176, 'steps': 50427, 'loss/train': 0.030982481315732002} 08/30/2021 22:20:12 - INFO - __main__ - Step 50429: {'lr': 0.00037913737129634977, 'samples': 9682368, 'steps': 50428, 'loss/train': 1.3544490337371826} 08/30/2021 22:20:14 - INFO - __main__ - Step 50430: {'lr': 0.00037913282732846676, 'samples': 9682560, 'steps': 50429, 'loss/train': 1.3566209077835083} 08/30/2021 22:20:14 - INFO - __main__ - Step 50431: {'lr': 0.0003791282833023985, 'samples': 9682752, 'steps': 50430, 'loss/train': 1.3717893362045288} 08/30/2021 22:20:15 - INFO - __main__ - Step 50432: {'lr': 0.0003791237392181469, 'samples': 9682944, 'steps': 50431, 'loss/train': 1.493273377418518} 08/30/2021 22:20:15 - INFO - __main__ - Step 50433: {'lr': 0.0003791191950757143, 'samples': 9683136, 'steps': 50432, 'loss/train': 1.629561424255371} 08/30/2021 22:20:15 - INFO - __main__ - Step 50434: {'lr': 0.0003791146508751025, 'samples': 9683328, 'steps': 50433, 'loss/train': 0.8616991639137268} 08/30/2021 22:20:17 - INFO - __main__ - Step 50435: {'lr': 0.00037911010661631364, 'samples': 9683520, 'steps': 50434, 'loss/train': 1.4288216829299927} 08/30/2021 22:20:17 - INFO - __main__ - Step 50436: {'lr': 0.0003791055622993498, 'samples': 9683712, 'steps': 50435, 'loss/train': 1.7565444707870483} 08/30/2021 22:20:18 - INFO - __main__ - Step 50437: {'lr': 0.0003791010179242129, 'samples': 9683904, 'steps': 50436, 'loss/train': 1.4624242782592773} 08/30/2021 22:20:18 - INFO - __main__ - Step 50438: {'lr': 0.0003790964734909051, 'samples': 9684096, 'steps': 50437, 'loss/train': 1.2148696184158325} 08/30/2021 22:20:18 - INFO - __main__ - Step 50439: {'lr': 0.00037909192899942846, 'samples': 9684288, 'steps': 50438, 'loss/train': 1.2736929655075073} 08/30/2021 22:20:20 - INFO - __main__ - Step 50440: {'lr': 0.00037908738444978495, 'samples': 9684480, 'steps': 50439, 'loss/train': 1.385855793952942} 08/30/2021 22:20:20 - INFO - __main__ - Step 50441: {'lr': 0.00037908283984197666, 'samples': 9684672, 'steps': 50440, 'loss/train': 0.09207213670015335} 08/30/2021 22:20:21 - INFO - __main__ - Step 50442: {'lr': 0.0003790782951760057, 'samples': 9684864, 'steps': 50441, 'loss/train': 1.4321266412734985} 08/30/2021 22:20:21 - INFO - __main__ - Step 50443: {'lr': 0.000379073750451874, 'samples': 9685056, 'steps': 50442, 'loss/train': 0.9199109077453613} 08/30/2021 22:20:21 - INFO - __main__ - Step 50444: {'lr': 0.00037906920566958363, 'samples': 9685248, 'steps': 50443, 'loss/train': 1.519266128540039} 08/30/2021 22:20:22 - INFO - __main__ - Step 50445: {'lr': 0.0003790646608291367, 'samples': 9685440, 'steps': 50444, 'loss/train': 1.294013500213623} 08/30/2021 22:20:23 - INFO - __main__ - Step 50446: {'lr': 0.00037906011593053527, 'samples': 9685632, 'steps': 50445, 'loss/train': 1.2787879705429077} 08/30/2021 22:20:24 - INFO - __main__ - Step 50447: {'lr': 0.00037905557097378127, 'samples': 9685824, 'steps': 50446, 'loss/train': 2.162569999694824} 08/30/2021 22:20:24 - INFO - __main__ - Step 50448: {'lr': 0.00037905102595887685, 'samples': 9686016, 'steps': 50447, 'loss/train': 0.8693594932556152} 08/30/2021 22:20:25 - INFO - __main__ - Step 50449: {'lr': 0.00037904648088582407, 'samples': 9686208, 'steps': 50448, 'loss/train': 1.4210799932479858} 08/30/2021 22:20:25 - INFO - __main__ - Step 50450: {'lr': 0.0003790419357546249, 'samples': 9686400, 'steps': 50449, 'loss/train': 1.338752269744873} 08/30/2021 22:20:27 - INFO - __main__ - Step 50451: {'lr': 0.0003790373905652814, 'samples': 9686592, 'steps': 50450, 'loss/train': 1.6669880151748657} 08/30/2021 22:20:28 - INFO - __main__ - Step 50452: {'lr': 0.0003790328453177957, 'samples': 9686784, 'steps': 50451, 'loss/train': 0.9682377576828003} 08/30/2021 22:20:28 - INFO - __main__ - Step 50453: {'lr': 0.0003790283000121697, 'samples': 9686976, 'steps': 50452, 'loss/train': 1.7377610206604004} 08/30/2021 22:20:28 - INFO - __main__ - Step 50454: {'lr': 0.0003790237546484056, 'samples': 9687168, 'steps': 50453, 'loss/train': 2.087350368499756} 08/30/2021 22:20:29 - INFO - __main__ - Step 50455: {'lr': 0.00037901920922650534, 'samples': 9687360, 'steps': 50454, 'loss/train': 0.06459533423185349} 08/30/2021 22:20:30 - INFO - __main__ - Step 50456: {'lr': 0.0003790146637464711, 'samples': 9687552, 'steps': 50455, 'loss/train': 1.022745132446289} 08/30/2021 22:20:31 - INFO - __main__ - Step 50457: {'lr': 0.0003790101182083048, 'samples': 9687744, 'steps': 50456, 'loss/train': 1.688386082649231} 08/30/2021 22:20:31 - INFO - __main__ - Step 50458: {'lr': 0.0003790055726120085, 'samples': 9687936, 'steps': 50457, 'loss/train': 1.0698438882827759} 08/30/2021 22:20:31 - INFO - __main__ - Step 50459: {'lr': 0.0003790010269575844, 'samples': 9688128, 'steps': 50458, 'loss/train': 1.3004378080368042} 08/30/2021 22:20:32 - INFO - __main__ - Step 50460: {'lr': 0.00037899648124503426, 'samples': 9688320, 'steps': 50459, 'loss/train': 1.3318828344345093} 08/30/2021 22:20:33 - INFO - __main__ - Step 50461: {'lr': 0.0003789919354743604, 'samples': 9688512, 'steps': 50460, 'loss/train': 1.0920735597610474} 08/30/2021 22:20:34 - INFO - __main__ - Step 50462: {'lr': 0.00037898738964556474, 'samples': 9688704, 'steps': 50461, 'loss/train': 1.713529109954834} 08/30/2021 22:20:34 - INFO - __main__ - Step 50463: {'lr': 0.0003789828437586494, 'samples': 9688896, 'steps': 50462, 'loss/train': 1.3665308952331543} 08/30/2021 22:20:34 - INFO - __main__ - Step 50464: {'lr': 0.0003789782978136163, 'samples': 9689088, 'steps': 50463, 'loss/train': 1.498956561088562} 08/30/2021 22:20:35 - INFO - __main__ - Step 50465: {'lr': 0.0003789737518104676, 'samples': 9689280, 'steps': 50464, 'loss/train': 2.150615930557251} 08/30/2021 22:20:36 - INFO - __main__ - Step 50466: {'lr': 0.0003789692057492053, 'samples': 9689472, 'steps': 50465, 'loss/train': 1.1512203216552734} 08/30/2021 22:20:37 - INFO - __main__ - Step 50467: {'lr': 0.0003789646596298315, 'samples': 9689664, 'steps': 50466, 'loss/train': 1.5628005266189575} 08/30/2021 22:20:37 - INFO - __main__ - Step 50468: {'lr': 0.0003789601134523482, 'samples': 9689856, 'steps': 50467, 'loss/train': 1.2388564348220825} 08/30/2021 22:20:37 - INFO - __main__ - Step 50469: {'lr': 0.0003789555672167575, 'samples': 9690048, 'steps': 50468, 'loss/train': 0.8184484839439392} 08/30/2021 22:20:38 - INFO - __main__ - Step 50470: {'lr': 0.00037895102092306134, 'samples': 9690240, 'steps': 50469, 'loss/train': 1.483014702796936} 08/30/2021 22:20:39 - INFO - __main__ - Step 50471: {'lr': 0.00037894647457126186, 'samples': 9690432, 'steps': 50470, 'loss/train': 1.4407098293304443} 08/30/2021 22:20:40 - INFO - __main__ - Step 50472: {'lr': 0.00037894192816136107, 'samples': 9690624, 'steps': 50471, 'loss/train': 1.1762523651123047} 08/30/2021 22:20:40 - INFO - __main__ - Step 50473: {'lr': 0.00037893738169336114, 'samples': 9690816, 'steps': 50472, 'loss/train': 1.4748085737228394} 08/30/2021 22:20:40 - INFO - __main__ - Step 50474: {'lr': 0.00037893283516726397, 'samples': 9691008, 'steps': 50473, 'loss/train': 1.5161131620407104} 08/30/2021 22:20:41 - INFO - __main__ - Step 50475: {'lr': 0.0003789282885830716, 'samples': 9691200, 'steps': 50474, 'loss/train': 1.1971051692962646} 08/30/2021 22:20:42 - INFO - __main__ - Step 50476: {'lr': 0.0003789237419407862, 'samples': 9691392, 'steps': 50475, 'loss/train': 1.5350041389465332} 08/30/2021 22:20:43 - INFO - __main__ - Step 50477: {'lr': 0.00037891919524040964, 'samples': 9691584, 'steps': 50476, 'loss/train': 1.3255949020385742} 08/30/2021 22:20:43 - INFO - __main__ - Step 50478: {'lr': 0.0003789146484819442, 'samples': 9691776, 'steps': 50477, 'loss/train': 1.07156240940094} 08/30/2021 22:20:43 - INFO - __main__ - Step 50479: {'lr': 0.00037891010166539175, 'samples': 9691968, 'steps': 50478, 'loss/train': 1.3630187511444092} 08/30/2021 22:20:44 - INFO - __main__ - Step 50480: {'lr': 0.00037890555479075437, 'samples': 9692160, 'steps': 50479, 'loss/train': 0.5146199464797974} 08/30/2021 22:20:44 - INFO - __main__ - Step 50481: {'lr': 0.0003789010078580342, 'samples': 9692352, 'steps': 50480, 'loss/train': 1.1166805028915405} 08/30/2021 22:20:46 - INFO - __main__ - Step 50482: {'lr': 0.00037889646086723325, 'samples': 9692544, 'steps': 50481, 'loss/train': 1.5784718990325928} 08/30/2021 22:20:46 - INFO - __main__ - Step 50483: {'lr': 0.0003788919138183534, 'samples': 9692736, 'steps': 50482, 'loss/train': 0.40377771854400635} 08/30/2021 22:20:46 - INFO - __main__ - Step 50484: {'lr': 0.000378887366711397, 'samples': 9692928, 'steps': 50483, 'loss/train': 0.8656853437423706} 08/30/2021 22:20:47 - INFO - __main__ - Step 50485: {'lr': 0.0003788828195463658, 'samples': 9693120, 'steps': 50484, 'loss/train': 1.388512134552002} 08/30/2021 22:20:47 - INFO - __main__ - Step 50486: {'lr': 0.0003788782723232621, 'samples': 9693312, 'steps': 50485, 'loss/train': 1.1282594203948975} 08/30/2021 22:20:49 - INFO - __main__ - Step 50487: {'lr': 0.00037887372504208784, 'samples': 9693504, 'steps': 50486, 'loss/train': 0.29486918449401855} 08/30/2021 22:20:49 - INFO - __main__ - Step 50488: {'lr': 0.000378869177702845, 'samples': 9693696, 'steps': 50487, 'loss/train': 0.04244080185890198} 08/30/2021 22:20:50 - INFO - __main__ - Step 50489: {'lr': 0.00037886463030553576, 'samples': 9693888, 'steps': 50488, 'loss/train': 1.0847463607788086} 08/30/2021 22:20:50 - INFO - __main__ - Step 50490: {'lr': 0.0003788600828501621, 'samples': 9694080, 'steps': 50489, 'loss/train': 1.067902684211731} 08/30/2021 22:20:51 - INFO - __main__ - Step 50491: {'lr': 0.000378855535336726, 'samples': 9694272, 'steps': 50490, 'loss/train': 1.4128140211105347} 08/30/2021 22:20:52 - INFO - __main__ - Step 50492: {'lr': 0.00037885098776522966, 'samples': 9694464, 'steps': 50491, 'loss/train': 1.4622515439987183} 08/30/2021 22:20:53 - INFO - __main__ - Step 50493: {'lr': 0.00037884644013567504, 'samples': 9694656, 'steps': 50492, 'loss/train': 1.5088398456573486} 08/30/2021 22:20:53 - INFO - __main__ - Step 50494: {'lr': 0.0003788418924480642, 'samples': 9694848, 'steps': 50493, 'loss/train': 1.3884984254837036} 08/30/2021 22:20:54 - INFO - __main__ - Step 50495: {'lr': 0.00037883734470239914, 'samples': 9695040, 'steps': 50494, 'loss/train': 1.083364725112915} 08/30/2021 22:20:54 - INFO - __main__ - Step 50496: {'lr': 0.00037883279689868203, 'samples': 9695232, 'steps': 50495, 'loss/train': 2.148885726928711} 08/30/2021 22:20:54 - INFO - __main__ - Step 50497: {'lr': 0.00037882824903691484, 'samples': 9695424, 'steps': 50496, 'loss/train': 1.3913482427597046} 08/30/2021 22:20:56 - INFO - __main__ - Step 50498: {'lr': 0.00037882370111709963, 'samples': 9695616, 'steps': 50497, 'loss/train': 1.215844750404358} 08/30/2021 22:20:57 - INFO - __main__ - Step 50499: {'lr': 0.00037881915313923845, 'samples': 9695808, 'steps': 50498, 'loss/train': 0.9273170232772827} 08/30/2021 22:20:57 - INFO - __main__ - Step 50500: {'lr': 0.0003788146051033333, 'samples': 9696000, 'steps': 50499, 'loss/train': 0.028722768649458885} 08/30/2021 22:20:57 - INFO - __main__ - Step 50501: {'lr': 0.0003788100570093863, 'samples': 9696192, 'steps': 50500, 'loss/train': 1.482971429824829} 08/30/2021 22:20:58 - INFO - __main__ - Step 50502: {'lr': 0.0003788055088573995, 'samples': 9696384, 'steps': 50501, 'loss/train': 0.9697481989860535} 08/30/2021 22:20:58 - INFO - __main__ - Step 50503: {'lr': 0.0003788009606473749, 'samples': 9696576, 'steps': 50502, 'loss/train': 1.6186118125915527} 08/30/2021 22:21:00 - INFO - __main__ - Step 50504: {'lr': 0.0003787964123793146, 'samples': 9696768, 'steps': 50503, 'loss/train': 0.5148093104362488} 08/30/2021 22:21:00 - INFO - __main__ - Step 50505: {'lr': 0.0003787918640532206, 'samples': 9696960, 'steps': 50504, 'loss/train': 1.8639370203018188} 08/30/2021 22:21:00 - INFO - __main__ - Step 50506: {'lr': 0.000378787315669095, 'samples': 9697152, 'steps': 50505, 'loss/train': 1.7922765016555786} 08/30/2021 22:21:01 - INFO - __main__ - Step 50507: {'lr': 0.00037878276722693984, 'samples': 9697344, 'steps': 50506, 'loss/train': 1.0665982961654663} 08/30/2021 22:21:01 - INFO - __main__ - Step 50508: {'lr': 0.00037877821872675705, 'samples': 9697536, 'steps': 50507, 'loss/train': 2.1430463790893555} 08/30/2021 22:21:03 - INFO - __main__ - Step 50509: {'lr': 0.00037877367016854886, 'samples': 9697728, 'steps': 50508, 'loss/train': 1.5658303499221802} 08/30/2021 22:21:04 - INFO - __main__ - Step 50510: {'lr': 0.00037876912155231725, 'samples': 9697920, 'steps': 50509, 'loss/train': 1.7043001651763916} 08/30/2021 22:21:04 - INFO - __main__ - Step 50511: {'lr': 0.0003787645728780642, 'samples': 9698112, 'steps': 50510, 'loss/train': 1.4626330137252808} 08/30/2021 22:21:05 - INFO - __main__ - Step 50512: {'lr': 0.0003787600241457918, 'samples': 9698304, 'steps': 50511, 'loss/train': 0.7246716618537903} 08/30/2021 22:21:05 - INFO - __main__ - Step 50513: {'lr': 0.0003787554753555022, 'samples': 9698496, 'steps': 50512, 'loss/train': 0.1511334329843521} 08/30/2021 22:21:05 - INFO - __main__ - Step 50514: {'lr': 0.00037875092650719737, 'samples': 9698688, 'steps': 50513, 'loss/train': 1.238606572151184} 08/30/2021 22:21:07 - INFO - __main__ - Step 50515: {'lr': 0.0003787463776008794, 'samples': 9698880, 'steps': 50514, 'loss/train': 1.3823033571243286} 08/30/2021 22:21:07 - INFO - __main__ - Step 50516: {'lr': 0.00037874182863655015, 'samples': 9699072, 'steps': 50515, 'loss/train': 1.6361545324325562} 08/30/2021 22:21:08 - INFO - __main__ - Step 50517: {'lr': 0.00037873727961421197, 'samples': 9699264, 'steps': 50516, 'loss/train': 0.05841180682182312} 08/30/2021 22:21:08 - INFO - __main__ - Step 50518: {'lr': 0.00037873273053386664, 'samples': 9699456, 'steps': 50517, 'loss/train': 1.4625422954559326} 08/30/2021 22:21:09 - INFO - __main__ - Step 50519: {'lr': 0.00037872818139551633, 'samples': 9699648, 'steps': 50518, 'loss/train': 1.781665563583374} 08/30/2021 22:21:10 - INFO - __main__ - Step 50520: {'lr': 0.0003787236321991632, 'samples': 9699840, 'steps': 50519, 'loss/train': 0.7029191851615906} 08/30/2021 22:21:11 - INFO - __main__ - Step 50521: {'lr': 0.0003787190829448092, 'samples': 9700032, 'steps': 50520, 'loss/train': 1.6387474536895752} 08/30/2021 22:21:11 - INFO - __main__ - Step 50522: {'lr': 0.00037871453363245625, 'samples': 9700224, 'steps': 50521, 'loss/train': 0.0813499167561531} 08/30/2021 22:21:12 - INFO - __main__ - Step 50523: {'lr': 0.0003787099842621066, 'samples': 9700416, 'steps': 50522, 'loss/train': 1.9128237962722778} 08/30/2021 22:21:12 - INFO - __main__ - Step 50524: {'lr': 0.0003787054348337621, 'samples': 9700608, 'steps': 50523, 'loss/train': 1.0082141160964966} 08/30/2021 22:21:13 - INFO - __main__ - Step 50525: {'lr': 0.000378700885347425, 'samples': 9700800, 'steps': 50524, 'loss/train': 1.7036052942276} 08/30/2021 22:21:14 - INFO - __main__ - Step 50526: {'lr': 0.0003786963358030973, 'samples': 9700992, 'steps': 50525, 'loss/train': 1.4115265607833862} 08/30/2021 22:21:14 - INFO - __main__ - Step 50527: {'lr': 0.000378691786200781, 'samples': 9701184, 'steps': 50526, 'loss/train': 0.047478705644607544} 08/30/2021 22:21:15 - INFO - __main__ - Step 50528: {'lr': 0.0003786872365404781, 'samples': 9701376, 'steps': 50527, 'loss/train': 1.170424222946167} 08/30/2021 22:21:15 - INFO - __main__ - Step 50529: {'lr': 0.00037868268682219073, 'samples': 9701568, 'steps': 50528, 'loss/train': 1.1574803590774536} 08/30/2021 22:21:16 - INFO - __main__ - Step 50530: {'lr': 0.000378678137045921, 'samples': 9701760, 'steps': 50529, 'loss/train': 0.46257394552230835} 08/30/2021 22:21:17 - INFO - __main__ - Step 50531: {'lr': 0.0003786735872116709, 'samples': 9701952, 'steps': 50530, 'loss/train': 1.9290759563446045} 08/30/2021 22:21:17 - INFO - __main__ - Step 50532: {'lr': 0.00037866903731944234, 'samples': 9702144, 'steps': 50531, 'loss/train': 1.5081276893615723} 08/30/2021 22:21:18 - INFO - __main__ - Step 50533: {'lr': 0.0003786644873692376, 'samples': 9702336, 'steps': 50532, 'loss/train': 1.5965487957000732} 08/30/2021 22:21:18 - INFO - __main__ - Step 50534: {'lr': 0.0003786599373610586, 'samples': 9702528, 'steps': 50533, 'loss/train': 0.8760868906974792} 08/30/2021 22:21:19 - INFO - __main__ - Step 50535: {'lr': 0.00037865538729490745, 'samples': 9702720, 'steps': 50534, 'loss/train': 0.978447675704956} 08/30/2021 22:21:20 - INFO - __main__ - Step 50536: {'lr': 0.00037865083717078605, 'samples': 9702912, 'steps': 50535, 'loss/train': 1.0426462888717651} 08/30/2021 22:21:20 - INFO - __main__ - Step 50537: {'lr': 0.00037864628698869676, 'samples': 9703104, 'steps': 50536, 'loss/train': 1.335335612297058} 08/30/2021 22:21:21 - INFO - __main__ - Step 50538: {'lr': 0.0003786417367486413, 'samples': 9703296, 'steps': 50537, 'loss/train': 1.4903407096862793} 08/30/2021 22:21:21 - INFO - __main__ - Step 50539: {'lr': 0.00037863718645062184, 'samples': 9703488, 'steps': 50538, 'loss/train': 1.087868332862854} 08/30/2021 22:21:23 - INFO - __main__ - Step 50540: {'lr': 0.00037863263609464056, 'samples': 9703680, 'steps': 50539, 'loss/train': 0.1528826504945755} 08/30/2021 22:21:23 - INFO - __main__ - Step 50541: {'lr': 0.00037862808568069935, 'samples': 9703872, 'steps': 50540, 'loss/train': 1.6069130897521973} 08/30/2021 22:21:23 - INFO - __main__ - Step 50542: {'lr': 0.00037862353520880026, 'samples': 9704064, 'steps': 50541, 'loss/train': 0.04344052076339722} 08/30/2021 22:21:24 - INFO - __main__ - Step 50543: {'lr': 0.0003786189846789454, 'samples': 9704256, 'steps': 50542, 'loss/train': 1.616071105003357} 08/30/2021 22:21:24 - INFO - __main__ - Step 50544: {'lr': 0.00037861443409113683, 'samples': 9704448, 'steps': 50543, 'loss/train': 0.6492910981178284} 08/30/2021 22:21:26 - INFO - __main__ - Step 50545: {'lr': 0.0003786098834453766, 'samples': 9704640, 'steps': 50544, 'loss/train': 1.0638542175292969} 08/30/2021 22:21:26 - INFO - __main__ - Step 50546: {'lr': 0.00037860533274166675, 'samples': 9704832, 'steps': 50545, 'loss/train': 0.8705479502677917} 08/30/2021 22:21:27 - INFO - __main__ - Step 50547: {'lr': 0.0003786007819800094, 'samples': 9705024, 'steps': 50546, 'loss/train': 1.601859211921692} 08/30/2021 22:21:27 - INFO - __main__ - Step 50548: {'lr': 0.00037859623116040633, 'samples': 9705216, 'steps': 50547, 'loss/train': 1.2495027780532837} 08/30/2021 22:21:27 - INFO - __main__ - Step 50549: {'lr': 0.00037859168028285984, 'samples': 9705408, 'steps': 50548, 'loss/train': 1.7164394855499268} 08/30/2021 22:21:29 - INFO - __main__ - Step 50550: {'lr': 0.000378587129347372, 'samples': 9705600, 'steps': 50549, 'loss/train': 0.05807496979832649} 08/30/2021 22:21:29 - INFO - __main__ - Step 50551: {'lr': 0.00037858257835394473, 'samples': 9705792, 'steps': 50550, 'loss/train': 1.4299025535583496} 08/30/2021 22:21:30 - INFO - __main__ - Step 50552: {'lr': 0.0003785780273025802, 'samples': 9705984, 'steps': 50551, 'loss/train': 2.5643904209136963} 08/30/2021 22:21:30 - INFO - __main__ - Step 50553: {'lr': 0.00037857347619328033, 'samples': 9706176, 'steps': 50552, 'loss/train': 1.5339922904968262} 08/30/2021 22:21:30 - INFO - __main__ - Step 50554: {'lr': 0.0003785689250260472, 'samples': 9706368, 'steps': 50553, 'loss/train': 1.4461265802383423} 08/30/2021 22:21:31 - INFO - __main__ - Step 50555: {'lr': 0.00037856437380088295, 'samples': 9706560, 'steps': 50554, 'loss/train': 0.8127725124359131} 08/30/2021 22:21:33 - INFO - __main__ - Step 50556: {'lr': 0.0003785598225177896, 'samples': 9706752, 'steps': 50555, 'loss/train': 1.147077202796936} 08/30/2021 22:21:33 - INFO - __main__ - Step 50557: {'lr': 0.0003785552711767691, 'samples': 9706944, 'steps': 50556, 'loss/train': 1.4499472379684448} 08/30/2021 22:21:33 - INFO - __main__ - Step 50558: {'lr': 0.0003785507197778236, 'samples': 9707136, 'steps': 50557, 'loss/train': 1.9343966245651245} 08/30/2021 22:21:34 - INFO - __main__ - Step 50559: {'lr': 0.0003785461683209552, 'samples': 9707328, 'steps': 50558, 'loss/train': 0.39147353172302246} 08/30/2021 22:21:34 - INFO - __main__ - Step 50560: {'lr': 0.00037854161680616586, 'samples': 9707520, 'steps': 50559, 'loss/train': 0.29870110750198364} 08/30/2021 22:21:36 - INFO - __main__ - Step 50561: {'lr': 0.00037853706523345766, 'samples': 9707712, 'steps': 50560, 'loss/train': 1.3760384321212769} 08/30/2021 22:21:37 - INFO - __main__ - Step 50562: {'lr': 0.0003785325136028326, 'samples': 9707904, 'steps': 50561, 'loss/train': 1.5541393756866455} 08/30/2021 22:21:37 - INFO - __main__ - Step 50563: {'lr': 0.0003785279619142927, 'samples': 9708096, 'steps': 50562, 'loss/train': 1.1044286489486694} 08/30/2021 22:21:37 - INFO - __main__ - Step 50564: {'lr': 0.0003785234101678402, 'samples': 9708288, 'steps': 50563, 'loss/train': 1.921372890472412} 08/30/2021 22:21:38 - INFO - __main__ - Step 50565: {'lr': 0.000378518858363477, 'samples': 9708480, 'steps': 50564, 'loss/train': 1.6993879079818726} 08/30/2021 22:21:40 - INFO - __main__ - Step 50566: {'lr': 0.00037851430650120516, 'samples': 9708672, 'steps': 50565, 'loss/train': 1.389115810394287} 08/30/2021 22:21:40 - INFO - __main__ - Step 50567: {'lr': 0.00037850975458102686, 'samples': 9708864, 'steps': 50566, 'loss/train': 1.2794448137283325} 08/30/2021 22:21:41 - INFO - __main__ - Step 50568: {'lr': 0.000378505202602944, 'samples': 9709056, 'steps': 50567, 'loss/train': 0.5103938579559326} 08/30/2021 22:21:41 - INFO - __main__ - Step 50569: {'lr': 0.0003785006505669586, 'samples': 9709248, 'steps': 50568, 'loss/train': 1.9048649072647095} 08/30/2021 22:21:42 - INFO - __main__ - Step 50570: {'lr': 0.0003784960984730728, 'samples': 9709440, 'steps': 50569, 'loss/train': 1.2146530151367188} 08/30/2021 22:21:42 - INFO - __main__ - Step 50571: {'lr': 0.00037849154632128867, 'samples': 9709632, 'steps': 50570, 'loss/train': 1.0356727838516235} 08/30/2021 22:21:43 - INFO - __main__ - Step 50572: {'lr': 0.0003784869941116082, 'samples': 9709824, 'steps': 50571, 'loss/train': 1.3006784915924072} 08/30/2021 22:21:44 - INFO - __main__ - Step 50573: {'lr': 0.00037848244184403356, 'samples': 9710016, 'steps': 50572, 'loss/train': 0.6703782677650452} 08/30/2021 22:21:44 - INFO - __main__ - Step 50574: {'lr': 0.0003784778895185667, 'samples': 9710208, 'steps': 50573, 'loss/train': 2.58648681640625} 08/30/2021 22:21:45 - INFO - __main__ - Step 50575: {'lr': 0.00037847333713520966, 'samples': 9710400, 'steps': 50574, 'loss/train': 1.1255229711532593} 08/30/2021 22:21:45 - INFO - __main__ - Step 50576: {'lr': 0.0003784687846939645, 'samples': 9710592, 'steps': 50575, 'loss/train': 1.249817967414856} 08/30/2021 22:21:45 - INFO - __main__ - Step 50577: {'lr': 0.00037846423219483325, 'samples': 9710784, 'steps': 50576, 'loss/train': 1.1773347854614258} 08/30/2021 22:21:47 - INFO - __main__ - Step 50578: {'lr': 0.00037845967963781807, 'samples': 9710976, 'steps': 50577, 'loss/train': 1.519844651222229} 08/30/2021 22:21:48 - INFO - __main__ - Step 50579: {'lr': 0.00037845512702292097, 'samples': 9711168, 'steps': 50578, 'loss/train': 0.25411728024482727} 08/30/2021 22:21:48 - INFO - __main__ - Step 50580: {'lr': 0.00037845057435014384, 'samples': 9711360, 'steps': 50579, 'loss/train': 1.3524072170257568} 08/30/2021 22:21:48 - INFO - __main__ - Step 50581: {'lr': 0.000378446021619489, 'samples': 9711552, 'steps': 50580, 'loss/train': 0.03329068422317505} 08/30/2021 22:21:49 - INFO - __main__ - Step 50582: {'lr': 0.0003784414688309583, 'samples': 9711744, 'steps': 50581, 'loss/train': 0.5245922803878784} 08/30/2021 22:21:49 - INFO - __main__ - Step 50583: {'lr': 0.0003784369159845539, 'samples': 9711936, 'steps': 50582, 'loss/train': 1.2498857975006104} 08/30/2021 22:21:50 - INFO - __main__ - Step 50584: {'lr': 0.00037843236308027776, 'samples': 9712128, 'steps': 50583, 'loss/train': 1.6137168407440186} 08/30/2021 22:21:51 - INFO - __main__ - Step 50585: {'lr': 0.000378427810118132, 'samples': 9712320, 'steps': 50584, 'loss/train': 1.053935170173645} 08/30/2021 22:21:51 - INFO - __main__ - Step 50586: {'lr': 0.0003784232570981186, 'samples': 9712512, 'steps': 50585, 'loss/train': 1.5806196928024292} 08/30/2021 22:21:52 - INFO - __main__ - Step 50587: {'lr': 0.0003784187040202398, 'samples': 9712704, 'steps': 50586, 'loss/train': 1.338905692100525} 08/30/2021 22:21:52 - INFO - __main__ - Step 50588: {'lr': 0.0003784141508844974, 'samples': 9712896, 'steps': 50587, 'loss/train': 0.5765265822410583} 08/30/2021 22:21:54 - INFO - __main__ - Step 50589: {'lr': 0.00037840959769089354, 'samples': 9713088, 'steps': 50588, 'loss/train': 1.534320592880249} 08/30/2021 22:21:54 - INFO - __main__ - Step 50590: {'lr': 0.00037840504443943033, 'samples': 9713280, 'steps': 50589, 'loss/train': 0.05563338100910187} 08/30/2021 22:21:54 - INFO - __main__ - Step 50591: {'lr': 0.00037840049113010976, 'samples': 9713472, 'steps': 50590, 'loss/train': 0.9809242486953735} 08/30/2021 22:21:55 - INFO - __main__ - Step 50592: {'lr': 0.000378395937762934, 'samples': 9713664, 'steps': 50591, 'loss/train': 0.6632370948791504} 08/30/2021 22:21:55 - INFO - __main__ - Step 50593: {'lr': 0.000378391384337905, 'samples': 9713856, 'steps': 50592, 'loss/train': 0.3154948949813843} 08/30/2021 22:21:57 - INFO - __main__ - Step 50594: {'lr': 0.00037838683085502473, 'samples': 9714048, 'steps': 50593, 'loss/train': 1.2037947177886963} 08/30/2021 22:21:57 - INFO - __main__ - Step 50595: {'lr': 0.0003783822773142954, 'samples': 9714240, 'steps': 50594, 'loss/train': 1.5460710525512695} 08/30/2021 22:21:58 - INFO - __main__ - Step 50596: {'lr': 0.00037837772371571897, 'samples': 9714432, 'steps': 50595, 'loss/train': 1.322776198387146} 08/30/2021 22:21:58 - INFO - __main__ - Step 50597: {'lr': 0.0003783731700592975, 'samples': 9714624, 'steps': 50596, 'loss/train': 1.6035116910934448} 08/30/2021 22:21:58 - INFO - __main__ - Step 50598: {'lr': 0.0003783686163450332, 'samples': 9714816, 'steps': 50597, 'loss/train': 1.2744885683059692} 08/30/2021 22:21:59 - INFO - __main__ - Step 50599: {'lr': 0.0003783640625729278, 'samples': 9715008, 'steps': 50598, 'loss/train': 2.1898765563964844} 08/30/2021 22:22:00 - INFO - __main__ - Step 50600: {'lr': 0.00037835950874298365, 'samples': 9715200, 'steps': 50599, 'loss/train': 1.3047624826431274} 08/30/2021 22:22:01 - INFO - __main__ - Step 50601: {'lr': 0.0003783549548552027, 'samples': 9715392, 'steps': 50600, 'loss/train': 1.4861668348312378} 08/30/2021 22:22:01 - INFO - __main__ - Step 50602: {'lr': 0.00037835040090958684, 'samples': 9715584, 'steps': 50601, 'loss/train': 1.672282338142395} 08/30/2021 22:22:02 - INFO - __main__ - Step 50603: {'lr': 0.0003783458469061384, 'samples': 9715776, 'steps': 50602, 'loss/train': 0.045012570917606354} 08/30/2021 22:22:02 - INFO - __main__ - Step 50604: {'lr': 0.0003783412928448593, 'samples': 9715968, 'steps': 50603, 'loss/train': 0.03242423012852669} 08/30/2021 22:22:02 - INFO - __main__ - Step 50605: {'lr': 0.00037833673872575153, 'samples': 9716160, 'steps': 50604, 'loss/train': 0.6731354594230652} 08/30/2021 22:22:04 - INFO - __main__ - Step 50606: {'lr': 0.00037833218454881725, 'samples': 9716352, 'steps': 50605, 'loss/train': 1.4134920835494995} 08/30/2021 22:22:04 - INFO - __main__ - Step 50607: {'lr': 0.0003783276303140584, 'samples': 9716544, 'steps': 50606, 'loss/train': 1.3130464553833008} 08/30/2021 22:22:05 - INFO - __main__ - Step 50608: {'lr': 0.0003783230760214772, 'samples': 9716736, 'steps': 50607, 'loss/train': 1.403700828552246} 08/30/2021 22:22:05 - INFO - __main__ - Step 50609: {'lr': 0.00037831852167107563, 'samples': 9716928, 'steps': 50608, 'loss/train': 0.7292937636375427} 08/30/2021 22:22:05 - INFO - __main__ - Step 50610: {'lr': 0.0003783139672628556, 'samples': 9717120, 'steps': 50609, 'loss/train': 1.15536630153656} 08/30/2021 22:22:07 - INFO - __main__ - Step 50611: {'lr': 0.0003783094127968193, 'samples': 9717312, 'steps': 50610, 'loss/train': 1.1272286176681519} 08/30/2021 22:22:07 - INFO - __main__ - Step 50612: {'lr': 0.0003783048582729688, 'samples': 9717504, 'steps': 50611, 'loss/train': 1.3782473802566528} 08/30/2021 22:22:08 - INFO - __main__ - Step 50613: {'lr': 0.0003783003036913061, 'samples': 9717696, 'steps': 50612, 'loss/train': 1.7438559532165527} 08/30/2021 22:22:08 - INFO - __main__ - Step 50614: {'lr': 0.0003782957490518332, 'samples': 9717888, 'steps': 50613, 'loss/train': 1.1090965270996094} 08/30/2021 22:22:08 - INFO - __main__ - Step 50615: {'lr': 0.00037829119435455226, 'samples': 9718080, 'steps': 50614, 'loss/train': 1.247815489768982} 08/30/2021 22:22:10 - INFO - __main__ - Step 50616: {'lr': 0.00037828663959946527, 'samples': 9718272, 'steps': 50615, 'loss/train': 0.22780205309391022} 08/30/2021 22:22:11 - INFO - __main__ - Step 50617: {'lr': 0.0003782820847865743, 'samples': 9718464, 'steps': 50616, 'loss/train': 0.8544297218322754} 08/30/2021 22:22:11 - INFO - __main__ - Step 50618: {'lr': 0.0003782775299158815, 'samples': 9718656, 'steps': 50617, 'loss/train': 1.479225516319275} 08/30/2021 22:22:12 - INFO - __main__ - Step 50619: {'lr': 0.0003782729749873887, 'samples': 9718848, 'steps': 50618, 'loss/train': 1.4865379333496094} 08/30/2021 22:22:12 - INFO - __main__ - Step 50620: {'lr': 0.0003782684200010981, 'samples': 9719040, 'steps': 50619, 'loss/train': 1.1960105895996094} 08/30/2021 22:22:12 - INFO - __main__ - Step 50621: {'lr': 0.0003782638649570118, 'samples': 9719232, 'steps': 50620, 'loss/train': 1.5717151165008545} 08/30/2021 22:22:14 - INFO - __main__ - Step 50622: {'lr': 0.00037825930985513177, 'samples': 9719424, 'steps': 50621, 'loss/train': 1.8007010221481323} 08/30/2021 22:22:15 - INFO - __main__ - Step 50623: {'lr': 0.00037825475469546, 'samples': 9719616, 'steps': 50622, 'loss/train': 0.6238455176353455} 08/30/2021 22:22:15 - INFO - __main__ - Step 50624: {'lr': 0.00037825019947799863, 'samples': 9719808, 'steps': 50623, 'loss/train': 1.347244143486023} 08/30/2021 22:22:15 - INFO - __main__ - Step 50625: {'lr': 0.0003782456442027498, 'samples': 9720000, 'steps': 50624, 'loss/train': 0.048339203000068665} 08/30/2021 22:22:16 - INFO - __main__ - Step 50626: {'lr': 0.0003782410888697153, 'samples': 9720192, 'steps': 50625, 'loss/train': 0.06834381073713303} 08/30/2021 22:22:16 - INFO - __main__ - Step 50627: {'lr': 0.00037823653347889745, 'samples': 9720384, 'steps': 50626, 'loss/train': 1.3234820365905762} 08/30/2021 22:22:18 - INFO - __main__ - Step 50628: {'lr': 0.0003782319780302982, 'samples': 9720576, 'steps': 50627, 'loss/train': 0.47812315821647644} 08/30/2021 22:22:18 - INFO - __main__ - Step 50629: {'lr': 0.00037822742252391963, 'samples': 9720768, 'steps': 50628, 'loss/train': 1.8109053373336792} 08/30/2021 22:22:18 - INFO - __main__ - Step 50630: {'lr': 0.0003782228669597637, 'samples': 9720960, 'steps': 50629, 'loss/train': 1.818223476409912} 08/30/2021 22:22:19 - INFO - __main__ - Step 50631: {'lr': 0.00037821831133783246, 'samples': 9721152, 'steps': 50630, 'loss/train': 1.5177974700927734} 08/30/2021 22:22:19 - INFO - __main__ - Step 50632: {'lr': 0.00037821375565812816, 'samples': 9721344, 'steps': 50631, 'loss/train': 1.5178747177124023} 08/30/2021 22:22:21 - INFO - __main__ - Step 50633: {'lr': 0.00037820919992065263, 'samples': 9721536, 'steps': 50632, 'loss/train': 0.8809749484062195} 08/30/2021 22:22:21 - INFO - __main__ - Step 50634: {'lr': 0.00037820464412540805, 'samples': 9721728, 'steps': 50633, 'loss/train': 1.5660545825958252} 08/30/2021 22:22:22 - INFO - __main__ - Step 50635: {'lr': 0.0003782000882723965, 'samples': 9721920, 'steps': 50634, 'loss/train': 1.637805700302124} 08/30/2021 22:22:22 - INFO - __main__ - Step 50636: {'lr': 0.00037819553236161985, 'samples': 9722112, 'steps': 50635, 'loss/train': 1.397648572921753} 08/30/2021 22:22:22 - INFO - __main__ - Step 50637: {'lr': 0.0003781909763930803, 'samples': 9722304, 'steps': 50636, 'loss/train': 0.9804012775421143} 08/30/2021 22:22:24 - INFO - __main__ - Step 50638: {'lr': 0.00037818642036677993, 'samples': 9722496, 'steps': 50637, 'loss/train': 0.0505664125084877} 08/30/2021 22:22:24 - INFO - __main__ - Step 50639: {'lr': 0.00037818186428272064, 'samples': 9722688, 'steps': 50638, 'loss/train': 1.3688198328018188} 08/30/2021 22:22:25 - INFO - __main__ - Step 50640: {'lr': 0.00037817730814090466, 'samples': 9722880, 'steps': 50639, 'loss/train': 1.3044573068618774} 08/30/2021 22:22:25 - INFO - __main__ - Step 50641: {'lr': 0.000378172751941334, 'samples': 9723072, 'steps': 50640, 'loss/train': 1.3556833267211914} 08/30/2021 22:22:25 - INFO - __main__ - Step 50642: {'lr': 0.0003781681956840106, 'samples': 9723264, 'steps': 50641, 'loss/train': 1.100357174873352} 08/30/2021 22:22:27 - INFO - __main__ - Step 50643: {'lr': 0.0003781636393689366, 'samples': 9723456, 'steps': 50642, 'loss/train': 1.4393939971923828} 08/30/2021 22:22:27 - INFO - __main__ - Step 50644: {'lr': 0.0003781590829961141, 'samples': 9723648, 'steps': 50643, 'loss/train': 1.3772292137145996} 08/30/2021 22:22:28 - INFO - __main__ - Step 50645: {'lr': 0.000378154526565545, 'samples': 9723840, 'steps': 50644, 'loss/train': 0.7441801428794861} 08/30/2021 22:22:28 - INFO - __main__ - Step 50646: {'lr': 0.00037814997007723153, 'samples': 9724032, 'steps': 50645, 'loss/train': 1.5719969272613525} 08/30/2021 22:22:28 - INFO - __main__ - Step 50647: {'lr': 0.0003781454135311756, 'samples': 9724224, 'steps': 50646, 'loss/train': 1.1818315982818604} 08/30/2021 22:22:29 - INFO - __main__ - Step 50648: {'lr': 0.0003781408569273794, 'samples': 9724416, 'steps': 50647, 'loss/train': 1.627143144607544} 08/30/2021 22:22:30 - INFO - __main__ - Step 50649: {'lr': 0.0003781363002658448, 'samples': 9724608, 'steps': 50648, 'loss/train': 1.5164395570755005} 08/30/2021 22:22:31 - INFO - __main__ - Step 50650: {'lr': 0.000378131743546574, 'samples': 9724800, 'steps': 50649, 'loss/train': 1.37466561794281} 08/30/2021 22:22:31 - INFO - __main__ - Step 50651: {'lr': 0.000378127186769569, 'samples': 9724992, 'steps': 50650, 'loss/train': 1.1438621282577515} 08/30/2021 22:22:32 - INFO - __main__ - Step 50652: {'lr': 0.00037812262993483194, 'samples': 9725184, 'steps': 50651, 'loss/train': 0.6153126358985901} 08/30/2021 22:22:32 - INFO - __main__ - Step 50653: {'lr': 0.0003781180730423648, 'samples': 9725376, 'steps': 50652, 'loss/train': 1.7729638814926147} 08/30/2021 22:22:34 - INFO - __main__ - Step 50654: {'lr': 0.00037811351609216956, 'samples': 9725568, 'steps': 50653, 'loss/train': 0.06994570046663284} 08/30/2021 22:22:34 - INFO - __main__ - Step 50655: {'lr': 0.00037810895908424837, 'samples': 9725760, 'steps': 50654, 'loss/train': 1.0513792037963867} 08/30/2021 22:22:35 - INFO - __main__ - Step 50656: {'lr': 0.0003781044020186033, 'samples': 9725952, 'steps': 50655, 'loss/train': 1.371777057647705} 08/30/2021 22:22:35 - INFO - __main__ - Step 50657: {'lr': 0.0003780998448952363, 'samples': 9726144, 'steps': 50656, 'loss/train': 1.4858083724975586} 08/30/2021 22:22:35 - INFO - __main__ - Step 50658: {'lr': 0.0003780952877141495, 'samples': 9726336, 'steps': 50657, 'loss/train': 1.456172227859497} 08/30/2021 22:22:36 - INFO - __main__ - Step 50659: {'lr': 0.0003780907304753449, 'samples': 9726528, 'steps': 50658, 'loss/train': 2.0115907192230225} 08/30/2021 22:22:37 - INFO - __main__ - Step 50660: {'lr': 0.0003780861731788247, 'samples': 9726720, 'steps': 50659, 'loss/train': 0.04644060879945755} 08/30/2021 22:22:38 - INFO - __main__ - Step 50661: {'lr': 0.0003780816158245908, 'samples': 9726912, 'steps': 50660, 'loss/train': 1.6447889804840088} 08/30/2021 22:22:38 - INFO - __main__ - Step 50662: {'lr': 0.0003780770584126453, 'samples': 9727104, 'steps': 50661, 'loss/train': 0.19531315565109253} 08/30/2021 22:22:39 - INFO - __main__ - Step 50663: {'lr': 0.0003780725009429903, 'samples': 9727296, 'steps': 50662, 'loss/train': 1.3399301767349243} 08/30/2021 22:22:39 - INFO - __main__ - Step 50664: {'lr': 0.00037806794341562773, 'samples': 9727488, 'steps': 50663, 'loss/train': 1.8560758829116821} 08/30/2021 22:22:39 - INFO - __main__ - Step 50665: {'lr': 0.00037806338583055976, 'samples': 9727680, 'steps': 50664, 'loss/train': 1.35336172580719} 08/30/2021 22:22:41 - INFO - __main__ - Step 50666: {'lr': 0.0003780588281877884, 'samples': 9727872, 'steps': 50665, 'loss/train': 1.3639845848083496} 08/30/2021 22:22:41 - INFO - __main__ - Step 50667: {'lr': 0.00037805427048731566, 'samples': 9728064, 'steps': 50666, 'loss/train': 1.2685130834579468} 08/30/2021 22:22:42 - INFO - __main__ - Step 50668: {'lr': 0.0003780497127291437, 'samples': 9728256, 'steps': 50667, 'loss/train': 1.0669279098510742} 08/30/2021 22:22:42 - INFO - __main__ - Step 50669: {'lr': 0.0003780451549132745, 'samples': 9728448, 'steps': 50668, 'loss/train': 1.935593843460083} 08/30/2021 22:22:42 - INFO - __main__ - Step 50670: {'lr': 0.00037804059703971016, 'samples': 9728640, 'steps': 50669, 'loss/train': 1.0550918579101562} 08/30/2021 22:22:44 - INFO - __main__ - Step 50671: {'lr': 0.00037803603910845264, 'samples': 9728832, 'steps': 50670, 'loss/train': 1.9273122549057007} 08/30/2021 22:22:44 - INFO - __main__ - Step 50672: {'lr': 0.00037803148111950407, 'samples': 9729024, 'steps': 50671, 'loss/train': 1.7545077800750732} 08/30/2021 22:22:45 - INFO - __main__ - Step 50673: {'lr': 0.0003780269230728665, 'samples': 9729216, 'steps': 50672, 'loss/train': 0.3329651653766632} 08/30/2021 22:22:45 - INFO - __main__ - Step 50674: {'lr': 0.000378022364968542, 'samples': 9729408, 'steps': 50673, 'loss/train': 1.3416147232055664} 08/30/2021 22:22:45 - INFO - __main__ - Step 50675: {'lr': 0.00037801780680653263, 'samples': 9729600, 'steps': 50674, 'loss/train': 1.5747259855270386} 08/30/2021 22:22:48 - INFO - __main__ - Step 50676: {'lr': 0.0003780132485868403, 'samples': 9729792, 'steps': 50675, 'loss/train': 0.9510841369628906} 08/30/2021 22:22:48 - INFO - __main__ - Step 50677: {'lr': 0.0003780086903094673, 'samples': 9729984, 'steps': 50676, 'loss/train': 0.2769656777381897} 08/30/2021 22:22:49 - INFO - __main__ - Step 50678: {'lr': 0.0003780041319744154, 'samples': 9730176, 'steps': 50677, 'loss/train': 1.0700489282608032} 08/30/2021 22:22:49 - INFO - __main__ - Step 50679: {'lr': 0.00037799957358168693, 'samples': 9730368, 'steps': 50678, 'loss/train': 0.45007649064064026} 08/30/2021 22:22:49 - INFO - __main__ - Step 50680: {'lr': 0.0003779950151312838, 'samples': 9730560, 'steps': 50679, 'loss/train': 0.2423430234193802} 08/30/2021 22:22:50 - INFO - __main__ - Step 50681: {'lr': 0.0003779904566232081, 'samples': 9730752, 'steps': 50680, 'loss/train': 1.6182368993759155} 08/30/2021 22:22:51 - INFO - __main__ - Step 50682: {'lr': 0.0003779858980574619, 'samples': 9730944, 'steps': 50681, 'loss/train': 1.6783785820007324} 08/30/2021 22:22:52 - INFO - __main__ - Step 50683: {'lr': 0.0003779813394340472, 'samples': 9731136, 'steps': 50682, 'loss/train': 1.2892950773239136} 08/30/2021 22:22:52 - INFO - __main__ - Step 50684: {'lr': 0.0003779767807529661, 'samples': 9731328, 'steps': 50683, 'loss/train': 1.0813039541244507} 08/30/2021 22:22:52 - INFO - __main__ - Step 50685: {'lr': 0.0003779722220142206, 'samples': 9731520, 'steps': 50684, 'loss/train': 1.3954010009765625} 08/30/2021 22:22:53 - INFO - __main__ - Step 50686: {'lr': 0.00037796766321781286, 'samples': 9731712, 'steps': 50685, 'loss/train': 1.099147915840149} 08/30/2021 22:22:53 - INFO - __main__ - Step 50687: {'lr': 0.00037796310436374474, 'samples': 9731904, 'steps': 50686, 'loss/train': 1.5850473642349243} 08/30/2021 22:22:55 - INFO - __main__ - Step 50688: {'lr': 0.0003779585454520186, 'samples': 9732096, 'steps': 50687, 'loss/train': 1.374234914779663} 08/30/2021 22:22:55 - INFO - __main__ - Step 50689: {'lr': 0.0003779539864826362, 'samples': 9732288, 'steps': 50688, 'loss/train': 1.4728293418884277} 08/30/2021 22:22:56 - INFO - __main__ - Step 50690: {'lr': 0.0003779494274555997, 'samples': 9732480, 'steps': 50689, 'loss/train': 0.2392479032278061} 08/30/2021 22:22:56 - INFO - __main__ - Step 50691: {'lr': 0.0003779448683709111, 'samples': 9732672, 'steps': 50690, 'loss/train': 1.3580857515335083} 08/30/2021 22:22:56 - INFO - __main__ - Step 50692: {'lr': 0.0003779403092285727, 'samples': 9732864, 'steps': 50691, 'loss/train': 1.157630205154419} 08/30/2021 22:22:58 - INFO - __main__ - Step 50693: {'lr': 0.00037793575002858625, 'samples': 9733056, 'steps': 50692, 'loss/train': 0.6986561417579651} 08/30/2021 22:22:58 - INFO - __main__ - Step 50694: {'lr': 0.00037793119077095396, 'samples': 9733248, 'steps': 50693, 'loss/train': 1.0183249711990356} 08/30/2021 22:22:59 - INFO - __main__ - Step 50695: {'lr': 0.00037792663145567784, 'samples': 9733440, 'steps': 50694, 'loss/train': 0.871319055557251} 08/30/2021 22:22:59 - INFO - __main__ - Step 50696: {'lr': 0.00037792207208275995, 'samples': 9733632, 'steps': 50695, 'loss/train': 1.73435640335083} 08/30/2021 22:23:00 - INFO - __main__ - Step 50697: {'lr': 0.0003779175126522023, 'samples': 9733824, 'steps': 50696, 'loss/train': 1.746621012687683} 08/30/2021 22:23:01 - INFO - __main__ - Step 50698: {'lr': 0.0003779129531640071, 'samples': 9734016, 'steps': 50697, 'loss/train': 1.3059147596359253} 08/30/2021 22:23:01 - INFO - __main__ - Step 50699: {'lr': 0.0003779083936181762, 'samples': 9734208, 'steps': 50698, 'loss/train': 1.700587511062622} 08/30/2021 22:23:02 - INFO - __main__ - Step 50700: {'lr': 0.0003779038340147118, 'samples': 9734400, 'steps': 50699, 'loss/train': 1.0194019079208374} 08/30/2021 22:23:02 - INFO - __main__ - Step 50701: {'lr': 0.0003778992743536159, 'samples': 9734592, 'steps': 50700, 'loss/train': 1.5755808353424072} 08/30/2021 22:23:02 - INFO - __main__ - Step 50702: {'lr': 0.0003778947146348906, 'samples': 9734784, 'steps': 50701, 'loss/train': 1.6223037242889404} 08/30/2021 22:23:04 - INFO - __main__ - Step 50703: {'lr': 0.00037789015485853786, 'samples': 9734976, 'steps': 50702, 'loss/train': 1.345376968383789} 08/30/2021 22:23:04 - INFO - __main__ - Step 50704: {'lr': 0.0003778855950245598, 'samples': 9735168, 'steps': 50703, 'loss/train': 1.318848729133606} 08/30/2021 22:23:05 - INFO - __main__ - Step 50705: {'lr': 0.00037788103513295844, 'samples': 9735360, 'steps': 50704, 'loss/train': 1.4883267879486084} 08/30/2021 22:23:05 - INFO - __main__ - Step 50706: {'lr': 0.00037787647518373586, 'samples': 9735552, 'steps': 50705, 'loss/train': 0.7998714447021484} 08/30/2021 22:23:05 - INFO - __main__ - Step 50707: {'lr': 0.0003778719151768941, 'samples': 9735744, 'steps': 50706, 'loss/train': 1.5309160947799683} 08/30/2021 22:23:07 - INFO - __main__ - Step 50708: {'lr': 0.0003778673551124353, 'samples': 9735936, 'steps': 50707, 'loss/train': 1.6601982116699219} 08/30/2021 22:23:07 - INFO - __main__ - Step 50709: {'lr': 0.0003778627949903615, 'samples': 9736128, 'steps': 50708, 'loss/train': 1.2267168760299683} 08/30/2021 22:23:08 - INFO - __main__ - Step 50710: {'lr': 0.00037785823481067455, 'samples': 9736320, 'steps': 50709, 'loss/train': 1.2138028144836426} 08/30/2021 22:23:08 - INFO - __main__ - Step 50711: {'lr': 0.0003778536745733767, 'samples': 9736512, 'steps': 50710, 'loss/train': 1.454527497291565} 08/30/2021 22:23:08 - INFO - __main__ - Step 50712: {'lr': 0.00037784911427846997, 'samples': 9736704, 'steps': 50711, 'loss/train': 1.4463690519332886} 08/30/2021 22:23:10 - INFO - __main__ - Step 50713: {'lr': 0.0003778445539259564, 'samples': 9736896, 'steps': 50712, 'loss/train': 1.2544445991516113} 08/30/2021 22:23:10 - INFO - __main__ - Step 50714: {'lr': 0.000377839993515838, 'samples': 9737088, 'steps': 50713, 'loss/train': 1.6325585842132568} 08/30/2021 22:23:11 - INFO - __main__ - Step 50715: {'lr': 0.000377835433048117, 'samples': 9737280, 'steps': 50714, 'loss/train': 1.6144853830337524} 08/30/2021 22:23:11 - INFO - __main__ - Step 50716: {'lr': 0.00037783087252279523, 'samples': 9737472, 'steps': 50715, 'loss/train': 1.4328558444976807} 08/30/2021 22:23:11 - INFO - __main__ - Step 50717: {'lr': 0.0003778263119398748, 'samples': 9737664, 'steps': 50716, 'loss/train': 4.1941819190979} 08/30/2021 22:23:13 - INFO - __main__ - Step 50718: {'lr': 0.00037782175129935793, 'samples': 9737856, 'steps': 50717, 'loss/train': 1.4083696603775024} 08/30/2021 22:23:13 - INFO - __main__ - Step 50719: {'lr': 0.0003778171906012464, 'samples': 9738048, 'steps': 50718, 'loss/train': 1.7509175539016724} 08/30/2021 22:23:14 - INFO - __main__ - Step 50720: {'lr': 0.0003778126298455425, 'samples': 9738240, 'steps': 50719, 'loss/train': 1.3796314001083374} 08/30/2021 22:23:14 - INFO - __main__ - Step 50721: {'lr': 0.0003778080690322483, 'samples': 9738432, 'steps': 50720, 'loss/train': 1.4508436918258667} 08/30/2021 22:23:14 - INFO - __main__ - Step 50722: {'lr': 0.0003778035081613656, 'samples': 9738624, 'steps': 50721, 'loss/train': 1.225346565246582} 08/30/2021 22:23:15 - INFO - __main__ - Step 50723: {'lr': 0.00037779894723289666, 'samples': 9738816, 'steps': 50722, 'loss/train': 1.5549176931381226} 08/30/2021 22:23:16 - INFO - __main__ - Step 50724: {'lr': 0.00037779438624684346, 'samples': 9739008, 'steps': 50723, 'loss/train': 1.0372271537780762} 08/30/2021 22:23:17 - INFO - __main__ - Step 50725: {'lr': 0.00037778982520320813, 'samples': 9739200, 'steps': 50724, 'loss/train': 1.463087797164917} 08/30/2021 22:23:17 - INFO - __main__ - Step 50726: {'lr': 0.00037778526410199266, 'samples': 9739392, 'steps': 50725, 'loss/train': 1.1884992122650146} 08/30/2021 22:23:17 - INFO - __main__ - Step 50727: {'lr': 0.0003777807029431992, 'samples': 9739584, 'steps': 50726, 'loss/train': 1.1037424802780151} 08/30/2021 22:23:18 - INFO - __main__ - Step 50728: {'lr': 0.0003777761417268296, 'samples': 9739776, 'steps': 50727, 'loss/train': 1.0655313730239868} 08/30/2021 22:23:20 - INFO - __main__ - Step 50729: {'lr': 0.00037777158045288606, 'samples': 9739968, 'steps': 50728, 'loss/train': 1.3737667798995972} 08/30/2021 22:23:20 - INFO - __main__ - Step 50730: {'lr': 0.00037776701912137066, 'samples': 9740160, 'steps': 50729, 'loss/train': 1.2113629579544067} 08/30/2021 22:23:20 - INFO - __main__ - Step 50731: {'lr': 0.00037776245773228547, 'samples': 9740352, 'steps': 50730, 'loss/train': 0.4998539388179779} 08/30/2021 22:23:21 - INFO - __main__ - Step 50732: {'lr': 0.0003777578962856324, 'samples': 9740544, 'steps': 50731, 'loss/train': 0.7186129093170166} 08/30/2021 22:23:21 - INFO - __main__ - Step 50733: {'lr': 0.0003777533347814136, 'samples': 9740736, 'steps': 50732, 'loss/train': 1.3341388702392578} 08/30/2021 22:23:23 - INFO - __main__ - Step 50734: {'lr': 0.0003777487732196312, 'samples': 9740928, 'steps': 50733, 'loss/train': 1.3012912273406982} 08/30/2021 22:23:24 - INFO - __main__ - Step 50735: {'lr': 0.00037774421160028705, 'samples': 9741120, 'steps': 50734, 'loss/train': 1.3807263374328613} 08/30/2021 22:23:24 - INFO - __main__ - Step 50736: {'lr': 0.0003777396499233834, 'samples': 9741312, 'steps': 50735, 'loss/train': 1.053460717201233} 08/30/2021 22:23:24 - INFO - __main__ - Step 50737: {'lr': 0.00037773508818892223, 'samples': 9741504, 'steps': 50736, 'loss/train': 0.1664726883172989} 08/30/2021 22:23:25 - INFO - __main__ - Step 50738: {'lr': 0.0003777305263969056, 'samples': 9741696, 'steps': 50737, 'loss/train': 0.3396371304988861} 08/30/2021 22:23:25 - INFO - __main__ - Step 50739: {'lr': 0.00037772596454733554, 'samples': 9741888, 'steps': 50738, 'loss/train': 0.07335926592350006} 08/30/2021 22:23:26 - INFO - __main__ - Step 50740: {'lr': 0.00037772140264021416, 'samples': 9742080, 'steps': 50739, 'loss/train': 1.772095799446106} 08/30/2021 22:23:27 - INFO - __main__ - Step 50741: {'lr': 0.00037771684067554345, 'samples': 9742272, 'steps': 50740, 'loss/train': 2.0000312328338623} 08/30/2021 22:23:27 - INFO - __main__ - Step 50742: {'lr': 0.0003777122786533255, 'samples': 9742464, 'steps': 50741, 'loss/train': 0.5390012860298157} 08/30/2021 22:23:28 - INFO - __main__ - Step 50743: {'lr': 0.0003777077165735625, 'samples': 9742656, 'steps': 50742, 'loss/train': 1.1910369396209717} 08/30/2021 22:23:28 - INFO - __main__ - Step 50744: {'lr': 0.0003777031544362562, 'samples': 9742848, 'steps': 50743, 'loss/train': 1.55131995677948} 08/30/2021 22:23:29 - INFO - __main__ - Step 50745: {'lr': 0.0003776985922414089, 'samples': 9743040, 'steps': 50744, 'loss/train': 1.2937159538269043} 08/30/2021 22:23:30 - INFO - __main__ - Step 50746: {'lr': 0.0003776940299890226, 'samples': 9743232, 'steps': 50745, 'loss/train': 1.1952322721481323} 08/30/2021 22:23:30 - INFO - __main__ - Step 50747: {'lr': 0.0003776894676790993, 'samples': 9743424, 'steps': 50746, 'loss/train': 0.9407305717468262} 08/30/2021 22:23:31 - INFO - __main__ - Step 50748: {'lr': 0.0003776849053116411, 'samples': 9743616, 'steps': 50747, 'loss/train': 1.1303645372390747} 08/30/2021 22:23:31 - INFO - __main__ - Step 50749: {'lr': 0.00037768034288665015, 'samples': 9743808, 'steps': 50748, 'loss/train': 0.8534497618675232} 08/30/2021 22:23:33 - INFO - __main__ - Step 50750: {'lr': 0.0003776757804041283, 'samples': 9744000, 'steps': 50749, 'loss/train': 0.7190511226654053} 08/30/2021 22:23:33 - INFO - __main__ - Step 50751: {'lr': 0.00037767121786407774, 'samples': 9744192, 'steps': 50750, 'loss/train': 1.504826545715332} 08/30/2021 22:23:33 - INFO - __main__ - Step 50752: {'lr': 0.00037766665526650054, 'samples': 9744384, 'steps': 50751, 'loss/train': 0.06696536391973495} 08/30/2021 22:23:34 - INFO - __main__ - Step 50753: {'lr': 0.0003776620926113986, 'samples': 9744576, 'steps': 50752, 'loss/train': 1.5380003452301025} 08/30/2021 22:23:34 - INFO - __main__ - Step 50754: {'lr': 0.0003776575298987742, 'samples': 9744768, 'steps': 50753, 'loss/train': 1.5041019916534424} 08/30/2021 22:23:34 - INFO - __main__ - Step 50755: {'lr': 0.00037765296712862927, 'samples': 9744960, 'steps': 50754, 'loss/train': 0.3582809269428253} 08/30/2021 22:23:36 - INFO - __main__ - Step 50756: {'lr': 0.00037764840430096593, 'samples': 9745152, 'steps': 50755, 'loss/train': 1.0493816137313843} 08/30/2021 22:23:37 - INFO - __main__ - Step 50757: {'lr': 0.0003776438414157861, 'samples': 9745344, 'steps': 50756, 'loss/train': 1.361534833908081} 08/30/2021 22:23:37 - INFO - __main__ - Step 50758: {'lr': 0.00037763927847309195, 'samples': 9745536, 'steps': 50757, 'loss/train': 0.1652563065290451} 08/30/2021 22:23:38 - INFO - __main__ - Step 50759: {'lr': 0.00037763471547288554, 'samples': 9745728, 'steps': 50758, 'loss/train': 0.8140980005264282} 08/30/2021 22:23:38 - INFO - __main__ - Step 50760: {'lr': 0.00037763015241516887, 'samples': 9745920, 'steps': 50759, 'loss/train': 0.7804386615753174} 08/30/2021 22:23:40 - INFO - __main__ - Step 50761: {'lr': 0.00037762558929994394, 'samples': 9746112, 'steps': 50760, 'loss/train': 0.8359727263450623} 08/30/2021 22:23:40 - INFO - __main__ - Step 50762: {'lr': 0.00037762102612721305, 'samples': 9746304, 'steps': 50761, 'loss/train': 0.09572537243366241} 08/30/2021 22:23:41 - INFO - __main__ - Step 50763: {'lr': 0.00037761646289697796, 'samples': 9746496, 'steps': 50762, 'loss/train': 0.6907109618186951} 08/30/2021 22:23:41 - INFO - __main__ - Step 50764: {'lr': 0.0003776118996092409, 'samples': 9746688, 'steps': 50763, 'loss/train': 0.20398925244808197} 08/30/2021 22:23:42 - INFO - __main__ - Step 50765: {'lr': 0.00037760733626400396, 'samples': 9746880, 'steps': 50764, 'loss/train': 1.4890995025634766} 08/30/2021 22:23:42 - INFO - __main__ - Step 50766: {'lr': 0.00037760277286126906, 'samples': 9747072, 'steps': 50765, 'loss/train': 1.0068615674972534} 08/30/2021 22:23:43 - INFO - __main__ - Step 50767: {'lr': 0.00037759820940103827, 'samples': 9747264, 'steps': 50766, 'loss/train': 1.196533203125} 08/30/2021 22:23:44 - INFO - __main__ - Step 50768: {'lr': 0.0003775936458833138, 'samples': 9747456, 'steps': 50767, 'loss/train': 1.5830824375152588} 08/30/2021 22:23:44 - INFO - __main__ - Step 50769: {'lr': 0.00037758908230809757, 'samples': 9747648, 'steps': 50768, 'loss/train': 1.7705957889556885} 08/30/2021 22:23:44 - INFO - __main__ - Step 50770: {'lr': 0.0003775845186753917, 'samples': 9747840, 'steps': 50769, 'loss/train': 1.1866025924682617} 08/30/2021 22:23:45 - INFO - __main__ - Step 50771: {'lr': 0.00037757995498519814, 'samples': 9748032, 'steps': 50770, 'loss/train': 2.459285020828247} 08/30/2021 22:23:46 - INFO - __main__ - Step 50772: {'lr': 0.00037757539123751906, 'samples': 9748224, 'steps': 50771, 'loss/train': 1.2626683712005615} 08/30/2021 22:23:47 - INFO - __main__ - Step 50773: {'lr': 0.00037757082743235644, 'samples': 9748416, 'steps': 50772, 'loss/train': 2.0133116245269775} 08/30/2021 22:23:47 - INFO - __main__ - Step 50774: {'lr': 0.00037756626356971236, 'samples': 9748608, 'steps': 50773, 'loss/train': 1.4486150741577148} 08/30/2021 22:23:47 - INFO - __main__ - Step 50775: {'lr': 0.00037756169964958897, 'samples': 9748800, 'steps': 50774, 'loss/train': 1.3006083965301514} 08/30/2021 22:23:48 - INFO - __main__ - Step 50776: {'lr': 0.00037755713567198823, 'samples': 9748992, 'steps': 50775, 'loss/train': 1.3877253532409668} 08/30/2021 22:23:48 - INFO - __main__ - Step 50777: {'lr': 0.00037755257163691214, 'samples': 9749184, 'steps': 50776, 'loss/train': 1.1668713092803955} 08/30/2021 22:23:50 - INFO - __main__ - Step 50778: {'lr': 0.00037754800754436293, 'samples': 9749376, 'steps': 50777, 'loss/train': 1.3054708242416382} 08/30/2021 22:23:50 - INFO - __main__ - Step 50779: {'lr': 0.0003775434433943425, 'samples': 9749568, 'steps': 50778, 'loss/train': 0.7419930696487427} 08/30/2021 22:23:51 - INFO - __main__ - Step 50780: {'lr': 0.00037753887918685295, 'samples': 9749760, 'steps': 50779, 'loss/train': 1.4362772703170776} 08/30/2021 22:23:51 - INFO - __main__ - Step 50781: {'lr': 0.0003775343149218964, 'samples': 9749952, 'steps': 50780, 'loss/train': 1.3387871980667114} 08/30/2021 22:23:51 - INFO - __main__ - Step 50782: {'lr': 0.0003775297505994748, 'samples': 9750144, 'steps': 50781, 'loss/train': 0.7080039381980896} 08/30/2021 22:23:53 - INFO - __main__ - Step 50783: {'lr': 0.0003775251862195903, 'samples': 9750336, 'steps': 50782, 'loss/train': 0.0829143077135086} 08/30/2021 22:23:53 - INFO - __main__ - Step 50784: {'lr': 0.0003775206217822449, 'samples': 9750528, 'steps': 50783, 'loss/train': 1.8504304885864258} 08/30/2021 22:23:54 - INFO - __main__ - Step 50785: {'lr': 0.00037751605728744063, 'samples': 9750720, 'steps': 50784, 'loss/train': 0.8786010146141052} 08/30/2021 22:23:54 - INFO - __main__ - Step 50786: {'lr': 0.0003775114927351797, 'samples': 9750912, 'steps': 50785, 'loss/train': 2.1746597290039062} 08/30/2021 22:23:54 - INFO - __main__ - Step 50787: {'lr': 0.00037750692812546396, 'samples': 9751104, 'steps': 50786, 'loss/train': 1.4306563138961792} 08/30/2021 22:23:56 - INFO - __main__ - Step 50788: {'lr': 0.00037750236345829557, 'samples': 9751296, 'steps': 50787, 'loss/train': 1.1955486536026} 08/30/2021 22:23:57 - INFO - __main__ - Step 50789: {'lr': 0.0003774977987336767, 'samples': 9751488, 'steps': 50788, 'loss/train': 1.3215488195419312} 08/30/2021 22:23:57 - INFO - __main__ - Step 50790: {'lr': 0.0003774932339516092, 'samples': 9751680, 'steps': 50789, 'loss/train': 1.497776746749878} 08/30/2021 22:23:58 - INFO - __main__ - Step 50791: {'lr': 0.00037748866911209525, 'samples': 9751872, 'steps': 50790, 'loss/train': 0.5976358652114868} 08/30/2021 22:23:58 - INFO - __main__ - Step 50792: {'lr': 0.00037748410421513677, 'samples': 9752064, 'steps': 50791, 'loss/train': 1.2239258289337158} 08/30/2021 22:24:00 - INFO - __main__ - Step 50793: {'lr': 0.000377479539260736, 'samples': 9752256, 'steps': 50792, 'loss/train': 0.9326513409614563} 08/30/2021 22:24:00 - INFO - __main__ - Step 50794: {'lr': 0.0003774749742488949, 'samples': 9752448, 'steps': 50793, 'loss/train': 1.2791025638580322} 08/30/2021 22:24:00 - INFO - __main__ - Step 50795: {'lr': 0.0003774704091796156, 'samples': 9752640, 'steps': 50794, 'loss/train': 1.532116413116455} 08/30/2021 22:24:01 - INFO - __main__ - Step 50796: {'lr': 0.00037746584405290006, 'samples': 9752832, 'steps': 50795, 'loss/train': 1.0717099905014038} 08/30/2021 22:24:01 - INFO - __main__ - Step 50797: {'lr': 0.00037746127886875035, 'samples': 9753024, 'steps': 50796, 'loss/train': 0.7889087796211243} 08/30/2021 22:24:03 - INFO - __main__ - Step 50798: {'lr': 0.0003774567136271686, 'samples': 9753216, 'steps': 50797, 'loss/train': 1.5086945295333862} 08/30/2021 22:24:03 - INFO - __main__ - Step 50799: {'lr': 0.0003774521483281568, 'samples': 9753408, 'steps': 50798, 'loss/train': 0.9860463738441467} 08/30/2021 22:24:03 - INFO - __main__ - Step 50800: {'lr': 0.00037744758297171706, 'samples': 9753600, 'steps': 50799, 'loss/train': 1.648983359336853} 08/30/2021 22:24:04 - INFO - __main__ - Step 50801: {'lr': 0.00037744301755785137, 'samples': 9753792, 'steps': 50800, 'loss/train': 1.3219642639160156} 08/30/2021 22:24:04 - INFO - __main__ - Step 50802: {'lr': 0.0003774384520865618, 'samples': 9753984, 'steps': 50801, 'loss/train': 2.6102852821350098} 08/30/2021 22:24:06 - INFO - __main__ - Step 50803: {'lr': 0.0003774338865578505, 'samples': 9754176, 'steps': 50802, 'loss/train': 1.436866283416748} 08/30/2021 22:24:06 - INFO - __main__ - Step 50804: {'lr': 0.00037742932097171945, 'samples': 9754368, 'steps': 50803, 'loss/train': 0.9029049277305603} 08/30/2021 22:24:07 - INFO - __main__ - Step 50805: {'lr': 0.0003774247553281707, 'samples': 9754560, 'steps': 50804, 'loss/train': 0.15741406381130219} 08/30/2021 22:24:07 - INFO - __main__ - Step 50806: {'lr': 0.00037742018962720625, 'samples': 9754752, 'steps': 50805, 'loss/train': 1.3621734380722046} 08/30/2021 22:24:07 - INFO - __main__ - Step 50807: {'lr': 0.0003774156238688282, 'samples': 9754944, 'steps': 50806, 'loss/train': 1.3569810390472412} 08/30/2021 22:24:09 - INFO - __main__ - Step 50808: {'lr': 0.00037741105805303874, 'samples': 9755136, 'steps': 50807, 'loss/train': 0.6315385103225708} 08/30/2021 22:24:09 - INFO - __main__ - Step 50809: {'lr': 0.0003774064921798399, 'samples': 9755328, 'steps': 50808, 'loss/train': 1.1026027202606201} 08/30/2021 22:24:10 - INFO - __main__ - Step 50810: {'lr': 0.00037740192624923354, 'samples': 9755520, 'steps': 50809, 'loss/train': 1.164373517036438} 08/30/2021 22:24:10 - INFO - __main__ - Step 50811: {'lr': 0.00037739736026122186, 'samples': 9755712, 'steps': 50810, 'loss/train': 1.2390820980072021} 08/30/2021 22:24:10 - INFO - __main__ - Step 50812: {'lr': 0.00037739279421580683, 'samples': 9755904, 'steps': 50811, 'loss/train': 1.2341911792755127} 08/30/2021 22:24:11 - INFO - __main__ - Step 50813: {'lr': 0.00037738822811299067, 'samples': 9756096, 'steps': 50812, 'loss/train': 1.5592031478881836} 08/30/2021 22:24:13 - INFO - __main__ - Step 50814: {'lr': 0.00037738366195277527, 'samples': 9756288, 'steps': 50813, 'loss/train': 0.9190251231193542} 08/30/2021 22:24:13 - INFO - __main__ - Step 50815: {'lr': 0.0003773790957351628, 'samples': 9756480, 'steps': 50814, 'loss/train': 1.2230150699615479} 08/30/2021 22:24:14 - INFO - __main__ - Step 50816: {'lr': 0.00037737452946015533, 'samples': 9756672, 'steps': 50815, 'loss/train': 1.4425054788589478} 08/30/2021 22:24:14 - INFO - __main__ - Step 50817: {'lr': 0.0003773699631277548, 'samples': 9756864, 'steps': 50816, 'loss/train': 1.3997374773025513} 08/30/2021 22:24:14 - INFO - __main__ - Step 50818: {'lr': 0.00037736539673796334, 'samples': 9757056, 'steps': 50817, 'loss/train': 1.0377663373947144} 08/30/2021 22:24:15 - INFO - __main__ - Step 50819: {'lr': 0.00037736083029078294, 'samples': 9757248, 'steps': 50818, 'loss/train': 0.18664397299289703} 08/30/2021 22:24:16 - INFO - __main__ - Step 50820: {'lr': 0.00037735626378621577, 'samples': 9757440, 'steps': 50819, 'loss/train': 0.09894146770238876} 08/30/2021 22:24:17 - INFO - __main__ - Step 50821: {'lr': 0.00037735169722426384, 'samples': 9757632, 'steps': 50820, 'loss/train': 1.3256279230117798} 08/30/2021 22:24:17 - INFO - __main__ - Step 50822: {'lr': 0.0003773471306049292, 'samples': 9757824, 'steps': 50821, 'loss/train': 0.5024879574775696} 08/30/2021 22:24:17 - INFO - __main__ - Step 50823: {'lr': 0.00037734256392821393, 'samples': 9758016, 'steps': 50822, 'loss/train': 1.3245830535888672} 08/30/2021 22:24:18 - INFO - __main__ - Step 50824: {'lr': 0.00037733799719411997, 'samples': 9758208, 'steps': 50823, 'loss/train': 1.5943431854248047} 08/30/2021 22:24:19 - INFO - __main__ - Step 50825: {'lr': 0.00037733343040264954, 'samples': 9758400, 'steps': 50824, 'loss/train': 1.8687024116516113} 08/30/2021 22:24:19 - INFO - __main__ - Step 50826: {'lr': 0.00037732886355380465, 'samples': 9758592, 'steps': 50825, 'loss/train': 1.554660439491272} 08/30/2021 22:24:20 - INFO - __main__ - Step 50827: {'lr': 0.00037732429664758725, 'samples': 9758784, 'steps': 50826, 'loss/train': 1.1154029369354248} 08/30/2021 22:24:20 - INFO - __main__ - Step 50828: {'lr': 0.0003773197296839996, 'samples': 9758976, 'steps': 50827, 'loss/train': 0.7243592739105225} 08/30/2021 22:24:21 - INFO - __main__ - Step 50829: {'lr': 0.00037731516266304355, 'samples': 9759168, 'steps': 50828, 'loss/train': 1.5961356163024902} 08/30/2021 22:24:22 - INFO - __main__ - Step 50830: {'lr': 0.00037731059558472136, 'samples': 9759360, 'steps': 50829, 'loss/train': 1.117758870124817} 08/30/2021 22:24:22 - INFO - __main__ - Step 50831: {'lr': 0.00037730602844903495, 'samples': 9759552, 'steps': 50830, 'loss/train': 1.626081943511963} 08/30/2021 22:24:23 - INFO - __main__ - Step 50832: {'lr': 0.00037730146125598634, 'samples': 9759744, 'steps': 50831, 'loss/train': 1.2703133821487427} 08/30/2021 22:24:23 - INFO - __main__ - Step 50833: {'lr': 0.0003772968940055777, 'samples': 9759936, 'steps': 50832, 'loss/train': 1.4722568988800049} 08/30/2021 22:24:24 - INFO - __main__ - Step 50834: {'lr': 0.000377292326697811, 'samples': 9760128, 'steps': 50833, 'loss/train': 2.081751585006714} 08/30/2021 22:24:25 - INFO - __main__ - Step 50835: {'lr': 0.00037728775933268844, 'samples': 9760320, 'steps': 50834, 'loss/train': 1.4873360395431519} 08/30/2021 22:24:26 - INFO - __main__ - Step 50836: {'lr': 0.0003772831919102119, 'samples': 9760512, 'steps': 50835, 'loss/train': 1.6102399826049805} 08/30/2021 22:24:26 - INFO - __main__ - Step 50837: {'lr': 0.00037727862443038353, 'samples': 9760704, 'steps': 50836, 'loss/train': 0.8270599842071533} 08/30/2021 22:24:26 - INFO - __main__ - Step 50838: {'lr': 0.00037727405689320535, 'samples': 9760896, 'steps': 50837, 'loss/train': 1.7081242799758911} 08/30/2021 22:24:27 - INFO - __main__ - Step 50839: {'lr': 0.00037726948929867955, 'samples': 9761088, 'steps': 50838, 'loss/train': 1.9270517826080322} 08/30/2021 22:24:29 - INFO - __main__ - Step 50840: {'lr': 0.00037726492164680796, 'samples': 9761280, 'steps': 50839, 'loss/train': 1.621097207069397} 08/30/2021 22:24:30 - INFO - __main__ - Step 50841: {'lr': 0.00037726035393759286, 'samples': 9761472, 'steps': 50840, 'loss/train': 0.26181456446647644} 08/30/2021 22:24:30 - INFO - __main__ - Step 50842: {'lr': 0.00037725578617103605, 'samples': 9761664, 'steps': 50841, 'loss/train': 0.050110358744859695} 08/30/2021 22:24:30 - INFO - __main__ - Step 50843: {'lr': 0.00037725121834713995, 'samples': 9761856, 'steps': 50842, 'loss/train': 1.1070399284362793} 08/30/2021 22:24:31 - INFO - __main__ - Step 50844: {'lr': 0.0003772466504659063, 'samples': 9762048, 'steps': 50843, 'loss/train': 2.2391281127929688} 08/30/2021 22:24:31 - INFO - __main__ - Step 50845: {'lr': 0.00037724208252733725, 'samples': 9762240, 'steps': 50844, 'loss/train': 1.3113831281661987} 08/30/2021 22:24:32 - INFO - __main__ - Step 50846: {'lr': 0.000377237514531435, 'samples': 9762432, 'steps': 50845, 'loss/train': 1.7394315004348755} 08/30/2021 22:24:33 - INFO - __main__ - Step 50847: {'lr': 0.0003772329464782014, 'samples': 9762624, 'steps': 50846, 'loss/train': 0.8904613852500916} 08/30/2021 22:24:33 - INFO - __main__ - Step 50848: {'lr': 0.00037722837836763856, 'samples': 9762816, 'steps': 50847, 'loss/train': 1.858169674873352} 08/30/2021 22:24:34 - INFO - __main__ - Step 50849: {'lr': 0.0003772238101997486, 'samples': 9763008, 'steps': 50848, 'loss/train': 1.2896208763122559} 08/30/2021 22:24:34 - INFO - __main__ - Step 50850: {'lr': 0.0003772192419745336, 'samples': 9763200, 'steps': 50849, 'loss/train': 1.2179913520812988} 08/30/2021 22:24:35 - INFO - __main__ - Step 50851: {'lr': 0.0003772146736919956, 'samples': 9763392, 'steps': 50850, 'loss/train': 1.60283625125885} 08/30/2021 22:24:36 - INFO - __main__ - Step 50852: {'lr': 0.0003772101053521366, 'samples': 9763584, 'steps': 50851, 'loss/train': 1.0214512348175049} 08/30/2021 22:24:36 - INFO - __main__ - Step 50853: {'lr': 0.0003772055369549586, 'samples': 9763776, 'steps': 50852, 'loss/train': 1.3520445823669434} 08/30/2021 22:24:37 - INFO - __main__ - Step 50854: {'lr': 0.0003772009685004638, 'samples': 9763968, 'steps': 50853, 'loss/train': 1.1115528345108032} 08/30/2021 22:24:37 - INFO - __main__ - Step 50855: {'lr': 0.0003771963999886543, 'samples': 9764160, 'steps': 50854, 'loss/train': 1.5564624071121216} 08/30/2021 22:24:38 - INFO - __main__ - Step 50856: {'lr': 0.000377191831419532, 'samples': 9764352, 'steps': 50855, 'loss/train': 1.6926746368408203} 08/30/2021 22:24:39 - INFO - __main__ - Step 50857: {'lr': 0.000377187262793099, 'samples': 9764544, 'steps': 50856, 'loss/train': 1.6538127660751343} 08/30/2021 22:24:39 - INFO - __main__ - Step 50858: {'lr': 0.0003771826941093574, 'samples': 9764736, 'steps': 50857, 'loss/train': 1.132995843887329} 08/30/2021 22:24:40 - INFO - __main__ - Step 50859: {'lr': 0.0003771781253683092, 'samples': 9764928, 'steps': 50858, 'loss/train': 1.0015689134597778} 08/30/2021 22:24:40 - INFO - __main__ - Step 50860: {'lr': 0.00037717355656995653, 'samples': 9765120, 'steps': 50859, 'loss/train': 1.5820631980895996} 08/30/2021 22:24:42 - INFO - __main__ - Step 50861: {'lr': 0.0003771689877143015, 'samples': 9765312, 'steps': 50860, 'loss/train': 1.3109848499298096} 08/30/2021 22:24:42 - INFO - __main__ - Step 50862: {'lr': 0.000377164418801346, 'samples': 9765504, 'steps': 50861, 'loss/train': 1.454015851020813} 08/30/2021 22:24:42 - INFO - __main__ - Step 50863: {'lr': 0.0003771598498310922, 'samples': 9765696, 'steps': 50862, 'loss/train': 0.051448971033096313} 08/30/2021 22:24:43 - INFO - __main__ - Step 50864: {'lr': 0.0003771552808035421, 'samples': 9765888, 'steps': 50863, 'loss/train': 1.291578769683838} 08/30/2021 22:24:43 - INFO - __main__ - Step 50865: {'lr': 0.0003771507117186978, 'samples': 9766080, 'steps': 50864, 'loss/train': 1.318737506866455} 08/30/2021 22:24:43 - INFO - __main__ - Step 50866: {'lr': 0.0003771461425765614, 'samples': 9766272, 'steps': 50865, 'loss/train': 1.200408697128296} 08/30/2021 22:24:45 - INFO - __main__ - Step 50867: {'lr': 0.00037714157337713483, 'samples': 9766464, 'steps': 50866, 'loss/train': 0.03980109468102455} 08/30/2021 22:24:45 - INFO - __main__ - Step 50868: {'lr': 0.0003771370041204203, 'samples': 9766656, 'steps': 50867, 'loss/train': 1.5331251621246338} 08/30/2021 22:24:46 - INFO - __main__ - Step 50869: {'lr': 0.0003771324348064198, 'samples': 9766848, 'steps': 50868, 'loss/train': 1.0888392925262451} 08/30/2021 22:24:46 - INFO - __main__ - Step 50870: {'lr': 0.00037712786543513534, 'samples': 9767040, 'steps': 50869, 'loss/train': 1.5546096563339233} 08/30/2021 22:24:46 - INFO - __main__ - Step 50871: {'lr': 0.000377123296006569, 'samples': 9767232, 'steps': 50870, 'loss/train': 0.9032530784606934} 08/30/2021 22:24:48 - INFO - __main__ - Step 50872: {'lr': 0.000377118726520723, 'samples': 9767424, 'steps': 50871, 'loss/train': 1.0285224914550781} 08/30/2021 22:24:48 - INFO - __main__ - Step 50873: {'lr': 0.0003771141569775991, 'samples': 9767616, 'steps': 50872, 'loss/train': 1.7842652797698975} 08/30/2021 22:24:49 - INFO - __main__ - Step 50874: {'lr': 0.0003771095873771996, 'samples': 9767808, 'steps': 50873, 'loss/train': 2.094590902328491} 08/30/2021 22:24:49 - INFO - __main__ - Step 50875: {'lr': 0.0003771050177195265, 'samples': 9768000, 'steps': 50874, 'loss/train': 1.2735671997070312} 08/30/2021 22:24:49 - INFO - __main__ - Step 50876: {'lr': 0.0003771004480045818, 'samples': 9768192, 'steps': 50875, 'loss/train': 0.539814829826355} 08/30/2021 22:24:51 - INFO - __main__ - Step 50877: {'lr': 0.00037709587823236767, 'samples': 9768384, 'steps': 50876, 'loss/train': 1.3838486671447754} 08/30/2021 22:24:52 - INFO - __main__ - Step 50878: {'lr': 0.00037709130840288605, 'samples': 9768576, 'steps': 50877, 'loss/train': 0.22401279211044312} 08/30/2021 22:24:52 - INFO - __main__ - Step 50879: {'lr': 0.00037708673851613903, 'samples': 9768768, 'steps': 50878, 'loss/train': 1.4722766876220703} 08/30/2021 22:24:52 - INFO - __main__ - Step 50880: {'lr': 0.00037708216857212863, 'samples': 9768960, 'steps': 50879, 'loss/train': 1.3142516613006592} 08/30/2021 22:24:53 - INFO - __main__ - Step 50881: {'lr': 0.0003770775985708571, 'samples': 9769152, 'steps': 50880, 'loss/train': 1.6077675819396973} 08/30/2021 22:24:54 - INFO - __main__ - Step 50882: {'lr': 0.0003770730285123263, 'samples': 9769344, 'steps': 50881, 'loss/train': 1.0561434030532837} 08/30/2021 22:24:55 - INFO - __main__ - Step 50883: {'lr': 0.0003770684583965384, 'samples': 9769536, 'steps': 50882, 'loss/train': 1.8479206562042236} 08/30/2021 22:24:55 - INFO - __main__ - Step 50884: {'lr': 0.0003770638882234953, 'samples': 9769728, 'steps': 50883, 'loss/train': 0.8280871510505676} 08/30/2021 22:24:55 - INFO - __main__ - Step 50885: {'lr': 0.0003770593179931993, 'samples': 9769920, 'steps': 50884, 'loss/train': 1.3128963708877563} 08/30/2021 22:24:56 - INFO - __main__ - Step 50886: {'lr': 0.00037705474770565215, 'samples': 9770112, 'steps': 50885, 'loss/train': 1.4274985790252686} 08/30/2021 22:24:56 - INFO - __main__ - Step 50887: {'lr': 0.00037705017736085623, 'samples': 9770304, 'steps': 50886, 'loss/train': 1.536376714706421} 08/30/2021 22:24:58 - INFO - __main__ - Step 50888: {'lr': 0.00037704560695881346, 'samples': 9770496, 'steps': 50887, 'loss/train': 1.8148274421691895} 08/30/2021 22:24:58 - INFO - __main__ - Step 50889: {'lr': 0.0003770410364995259, 'samples': 9770688, 'steps': 50888, 'loss/train': 0.20914511382579803} 08/30/2021 22:24:58 - INFO - __main__ - Step 50890: {'lr': 0.00037703646598299554, 'samples': 9770880, 'steps': 50889, 'loss/train': 1.3130958080291748} 08/30/2021 22:24:59 - INFO - __main__ - Step 50891: {'lr': 0.00037703189540922463, 'samples': 9771072, 'steps': 50890, 'loss/train': 1.4951297044754028} 08/30/2021 22:24:59 - INFO - __main__ - Step 50892: {'lr': 0.000377027324778215, 'samples': 9771264, 'steps': 50891, 'loss/train': 0.37270689010620117} 08/30/2021 22:25:02 - INFO - __main__ - Step 50893: {'lr': 0.0003770227540899689, 'samples': 9771456, 'steps': 50892, 'loss/train': 1.3048276901245117} 08/30/2021 22:25:02 - INFO - __main__ - Step 50894: {'lr': 0.0003770181833444882, 'samples': 9771648, 'steps': 50893, 'loss/train': 1.3916434049606323} 08/30/2021 22:25:02 - INFO - __main__ - Step 50895: {'lr': 0.0003770136125417751, 'samples': 9771840, 'steps': 50894, 'loss/train': 1.4974582195281982} 08/30/2021 22:25:03 - INFO - __main__ - Step 50896: {'lr': 0.0003770090416818317, 'samples': 9772032, 'steps': 50895, 'loss/train': 0.9585852026939392} 08/30/2021 22:25:03 - INFO - __main__ - Step 50897: {'lr': 0.00037700447076465996, 'samples': 9772224, 'steps': 50896, 'loss/train': 1.51726233959198} 08/30/2021 22:25:03 - INFO - __main__ - Step 50898: {'lr': 0.0003769998997902619, 'samples': 9772416, 'steps': 50897, 'loss/train': 1.329371690750122} 08/30/2021 22:25:05 - INFO - __main__ - Step 50899: {'lr': 0.00037699532875863976, 'samples': 9772608, 'steps': 50898, 'loss/train': 1.7552887201309204} 08/30/2021 22:25:05 - INFO - __main__ - Step 50900: {'lr': 0.0003769907576697954, 'samples': 9772800, 'steps': 50899, 'loss/train': 1.707064151763916} 08/30/2021 22:25:06 - INFO - __main__ - Step 50901: {'lr': 0.000376986186523731, 'samples': 9772992, 'steps': 50900, 'loss/train': 0.8977749943733215} 08/30/2021 22:25:06 - INFO - __main__ - Step 50902: {'lr': 0.0003769816153204485, 'samples': 9773184, 'steps': 50901, 'loss/train': 0.9819461107254028} 08/30/2021 22:25:06 - INFO - __main__ - Step 50903: {'lr': 0.00037697704405995015, 'samples': 9773376, 'steps': 50902, 'loss/train': 1.3400992155075073} 08/30/2021 22:25:08 - INFO - __main__ - Step 50904: {'lr': 0.0003769724727422379, 'samples': 9773568, 'steps': 50903, 'loss/train': 1.7477514743804932} 08/30/2021 22:25:09 - INFO - __main__ - Step 50905: {'lr': 0.0003769679013673137, 'samples': 9773760, 'steps': 50904, 'loss/train': 0.528209924697876} 08/30/2021 22:25:09 - INFO - __main__ - Step 50906: {'lr': 0.00037696332993517983, 'samples': 9773952, 'steps': 50905, 'loss/train': 1.5773422718048096} 08/30/2021 22:25:09 - INFO - __main__ - Step 50907: {'lr': 0.0003769587584458382, 'samples': 9774144, 'steps': 50906, 'loss/train': 0.6630872488021851} 08/30/2021 22:25:10 - INFO - __main__ - Step 50908: {'lr': 0.00037695418689929095, 'samples': 9774336, 'steps': 50907, 'loss/train': 1.2419148683547974} 08/30/2021 22:25:11 - INFO - __main__ - Step 50909: {'lr': 0.00037694961529554006, 'samples': 9774528, 'steps': 50908, 'loss/train': 1.29733407497406} 08/30/2021 22:25:11 - INFO - __main__ - Step 50910: {'lr': 0.0003769450436345877, 'samples': 9774720, 'steps': 50909, 'loss/train': 1.2948863506317139} 08/30/2021 22:25:12 - INFO - __main__ - Step 50911: {'lr': 0.00037694047191643576, 'samples': 9774912, 'steps': 50910, 'loss/train': 1.1586613655090332} 08/30/2021 22:25:12 - INFO - __main__ - Step 50912: {'lr': 0.00037693590014108646, 'samples': 9775104, 'steps': 50911, 'loss/train': 1.039445161819458} 08/30/2021 22:25:13 - INFO - __main__ - Step 50913: {'lr': 0.0003769313283085418, 'samples': 9775296, 'steps': 50912, 'loss/train': 1.25136137008667} 08/30/2021 22:25:14 - INFO - __main__ - Step 50914: {'lr': 0.0003769267564188038, 'samples': 9775488, 'steps': 50913, 'loss/train': 1.4407514333724976} 08/30/2021 22:25:15 - INFO - __main__ - Step 50915: {'lr': 0.0003769221844718746, 'samples': 9775680, 'steps': 50914, 'loss/train': 1.3715497255325317} 08/30/2021 22:25:15 - INFO - __main__ - Step 50916: {'lr': 0.00037691761246775625, 'samples': 9775872, 'steps': 50915, 'loss/train': 1.3548270463943481} 08/30/2021 22:25:15 - INFO - __main__ - Step 50917: {'lr': 0.00037691304040645074, 'samples': 9776064, 'steps': 50916, 'loss/train': 1.1928681135177612} 08/30/2021 22:25:16 - INFO - __main__ - Step 50918: {'lr': 0.00037690846828796024, 'samples': 9776256, 'steps': 50917, 'loss/train': 1.4730546474456787} 08/30/2021 22:25:17 - INFO - __main__ - Step 50919: {'lr': 0.00037690389611228664, 'samples': 9776448, 'steps': 50918, 'loss/train': 0.21903111040592194} 08/30/2021 22:25:18 - INFO - __main__ - Step 50920: {'lr': 0.00037689932387943216, 'samples': 9776640, 'steps': 50919, 'loss/train': 1.240023136138916} 08/30/2021 22:25:18 - INFO - __main__ - Step 50921: {'lr': 0.0003768947515893988, 'samples': 9776832, 'steps': 50920, 'loss/train': 1.4727351665496826} 08/30/2021 22:25:18 - INFO - __main__ - Step 50922: {'lr': 0.0003768901792421886, 'samples': 9777024, 'steps': 50921, 'loss/train': 0.9558790326118469} 08/30/2021 22:25:19 - INFO - __main__ - Step 50923: {'lr': 0.0003768856068378036, 'samples': 9777216, 'steps': 50922, 'loss/train': 1.3771542310714722} 08/30/2021 22:25:20 - INFO - __main__ - Step 50924: {'lr': 0.000376881034376246, 'samples': 9777408, 'steps': 50923, 'loss/train': 0.45340245962142944} 08/30/2021 22:25:21 - INFO - __main__ - Step 50925: {'lr': 0.0003768764618575178, 'samples': 9777600, 'steps': 50924, 'loss/train': 1.293688178062439} 08/30/2021 22:25:21 - INFO - __main__ - Step 50926: {'lr': 0.00037687188928162087, 'samples': 9777792, 'steps': 50925, 'loss/train': 1.6255319118499756} 08/30/2021 22:25:21 - INFO - __main__ - Step 50927: {'lr': 0.00037686731664855755, 'samples': 9777984, 'steps': 50926, 'loss/train': 1.837478756904602} 08/30/2021 22:25:22 - INFO - __main__ - Step 50928: {'lr': 0.0003768627439583297, 'samples': 9778176, 'steps': 50927, 'loss/train': 1.4847376346588135} 08/30/2021 22:25:22 - INFO - __main__ - Step 50929: {'lr': 0.00037685817121093946, 'samples': 9778368, 'steps': 50928, 'loss/train': 1.1166173219680786} 08/30/2021 22:25:24 - INFO - __main__ - Step 50930: {'lr': 0.000376853598406389, 'samples': 9778560, 'steps': 50929, 'loss/train': 1.0932608842849731} 08/30/2021 22:25:24 - INFO - __main__ - Step 50931: {'lr': 0.00037684902554468015, 'samples': 9778752, 'steps': 50930, 'loss/train': 1.0910321474075317} 08/30/2021 22:25:24 - INFO - __main__ - Step 50932: {'lr': 0.0003768444526258151, 'samples': 9778944, 'steps': 50931, 'loss/train': 1.4822059869766235} 08/30/2021 22:25:25 - INFO - __main__ - Step 50933: {'lr': 0.0003768398796497959, 'samples': 9779136, 'steps': 50932, 'loss/train': 0.870415985584259} 08/30/2021 22:25:25 - INFO - __main__ - Step 50934: {'lr': 0.00037683530661662457, 'samples': 9779328, 'steps': 50933, 'loss/train': 1.47185218334198} 08/30/2021 22:25:27 - INFO - __main__ - Step 50935: {'lr': 0.00037683073352630327, 'samples': 9779520, 'steps': 50934, 'loss/train': 1.5783512592315674} 08/30/2021 22:25:27 - INFO - __main__ - Step 50936: {'lr': 0.000376826160378834, 'samples': 9779712, 'steps': 50935, 'loss/train': 0.9159941673278809} 08/30/2021 22:25:27 - INFO - __main__ - Step 50937: {'lr': 0.0003768215871742188, 'samples': 9779904, 'steps': 50936, 'loss/train': 1.404692530632019} 08/30/2021 22:25:28 - INFO - __main__ - Step 50938: {'lr': 0.00037681701391245983, 'samples': 9780096, 'steps': 50937, 'loss/train': 1.6873672008514404} 08/30/2021 22:25:28 - INFO - __main__ - Step 50939: {'lr': 0.0003768124405935589, 'samples': 9780288, 'steps': 50938, 'loss/train': 1.4844799041748047} 08/30/2021 22:25:30 - INFO - __main__ - Step 50940: {'lr': 0.00037680786721751834, 'samples': 9780480, 'steps': 50939, 'loss/train': 1.6213657855987549} 08/30/2021 22:25:30 - INFO - __main__ - Step 50941: {'lr': 0.0003768032937843401, 'samples': 9780672, 'steps': 50940, 'loss/train': 0.6705363392829895} 08/30/2021 22:25:30 - INFO - __main__ - Step 50942: {'lr': 0.00037679872029402627, 'samples': 9780864, 'steps': 50941, 'loss/train': 0.8061746954917908} 08/30/2021 22:25:31 - INFO - __main__ - Step 50943: {'lr': 0.0003767941467465789, 'samples': 9781056, 'steps': 50942, 'loss/train': 1.5418555736541748} 08/30/2021 22:25:31 - INFO - __main__ - Step 50944: {'lr': 0.000376789573142, 'samples': 9781248, 'steps': 50943, 'loss/train': 1.365171194076538} 08/30/2021 22:25:33 - INFO - __main__ - Step 50945: {'lr': 0.0003767849994802918, 'samples': 9781440, 'steps': 50944, 'loss/train': 1.3933255672454834} 08/30/2021 22:25:33 - INFO - __main__ - Step 50946: {'lr': 0.0003767804257614561, 'samples': 9781632, 'steps': 50945, 'loss/train': 1.0017657279968262} 08/30/2021 22:25:34 - INFO - __main__ - Step 50947: {'lr': 0.00037677585198549516, 'samples': 9781824, 'steps': 50946, 'loss/train': 1.5424386262893677} 08/30/2021 22:25:34 - INFO - __main__ - Step 50948: {'lr': 0.00037677127815241086, 'samples': 9782016, 'steps': 50947, 'loss/train': 1.5783275365829468} 08/30/2021 22:25:34 - INFO - __main__ - Step 50949: {'lr': 0.00037676670426220547, 'samples': 9782208, 'steps': 50948, 'loss/train': 1.4499647617340088} 08/30/2021 22:25:35 - INFO - __main__ - Step 50950: {'lr': 0.00037676213031488095, 'samples': 9782400, 'steps': 50949, 'loss/train': 0.8235907554626465} 08/30/2021 22:25:37 - INFO - __main__ - Step 50951: {'lr': 0.0003767575563104394, 'samples': 9782592, 'steps': 50950, 'loss/train': 1.3277612924575806} 08/30/2021 22:25:37 - INFO - __main__ - Step 50952: {'lr': 0.00037675298224888287, 'samples': 9782784, 'steps': 50951, 'loss/train': 1.6856927871704102} 08/30/2021 22:25:37 - INFO - __main__ - Step 50953: {'lr': 0.0003767484081302133, 'samples': 9782976, 'steps': 50952, 'loss/train': 1.3247592449188232} 08/30/2021 22:25:38 - INFO - __main__ - Step 50954: {'lr': 0.000376743833954433, 'samples': 9783168, 'steps': 50953, 'loss/train': 1.1527340412139893} 08/30/2021 22:25:38 - INFO - __main__ - Step 50955: {'lr': 0.00037673925972154376, 'samples': 9783360, 'steps': 50954, 'loss/train': 0.8363124132156372} 08/30/2021 22:25:40 - INFO - __main__ - Step 50956: {'lr': 0.00037673468543154777, 'samples': 9783552, 'steps': 50955, 'loss/train': 1.054368257522583} 08/30/2021 22:25:40 - INFO - __main__ - Step 50957: {'lr': 0.0003767301110844472, 'samples': 9783744, 'steps': 50956, 'loss/train': 2.1103508472442627} 08/30/2021 22:25:41 - INFO - __main__ - Step 50958: {'lr': 0.0003767255366802439, 'samples': 9783936, 'steps': 50957, 'loss/train': 1.6950081586837769} 08/30/2021 22:25:41 - INFO - __main__ - Step 50959: {'lr': 0.00037672096221894004, 'samples': 9784128, 'steps': 50958, 'loss/train': 1.2313460111618042} 08/30/2021 22:25:41 - INFO - __main__ - Step 50960: {'lr': 0.0003767163877005376, 'samples': 9784320, 'steps': 50959, 'loss/train': 1.5555827617645264} 08/30/2021 22:25:43 - INFO - __main__ - Step 50961: {'lr': 0.0003767118131250388, 'samples': 9784512, 'steps': 50960, 'loss/train': 1.2279070615768433} 08/30/2021 22:25:43 - INFO - __main__ - Step 50962: {'lr': 0.00037670723849244557, 'samples': 9784704, 'steps': 50961, 'loss/train': 0.7368555665016174} 08/30/2021 22:25:44 - INFO - __main__ - Step 50963: {'lr': 0.0003767026638027601, 'samples': 9784896, 'steps': 50962, 'loss/train': 1.827950119972229} 08/30/2021 22:25:44 - INFO - __main__ - Step 50964: {'lr': 0.00037669808905598434, 'samples': 9785088, 'steps': 50963, 'loss/train': 1.7964262962341309} 08/30/2021 22:25:44 - INFO - __main__ - Step 50965: {'lr': 0.0003766935142521203, 'samples': 9785280, 'steps': 50964, 'loss/train': 0.9194609522819519} 08/30/2021 22:25:46 - INFO - __main__ - Step 50966: {'lr': 0.00037668893939117023, 'samples': 9785472, 'steps': 50965, 'loss/train': 1.1977851390838623} 08/30/2021 22:25:46 - INFO - __main__ - Step 50967: {'lr': 0.000376684364473136, 'samples': 9785664, 'steps': 50966, 'loss/train': 0.770944356918335} 08/30/2021 22:25:47 - INFO - __main__ - Step 50968: {'lr': 0.00037667978949801974, 'samples': 9785856, 'steps': 50967, 'loss/train': 1.216599464416504} 08/30/2021 22:25:47 - INFO - __main__ - Step 50969: {'lr': 0.00037667521446582355, 'samples': 9786048, 'steps': 50968, 'loss/train': 1.0586565732955933} 08/30/2021 22:25:47 - INFO - __main__ - Step 50970: {'lr': 0.00037667063937654944, 'samples': 9786240, 'steps': 50969, 'loss/train': 1.0758748054504395} 08/30/2021 22:25:49 - INFO - __main__ - Step 50971: {'lr': 0.00037666606423019956, 'samples': 9786432, 'steps': 50970, 'loss/train': 1.2091621160507202} 08/30/2021 22:25:49 - INFO - __main__ - Step 50972: {'lr': 0.00037666148902677576, 'samples': 9786624, 'steps': 50971, 'loss/train': 1.2704368829727173} 08/30/2021 22:25:50 - INFO - __main__ - Step 50973: {'lr': 0.0003766569137662804, 'samples': 9786816, 'steps': 50972, 'loss/train': 0.9434016942977905} 08/30/2021 22:25:50 - INFO - __main__ - Step 50974: {'lr': 0.00037665233844871534, 'samples': 9787008, 'steps': 50973, 'loss/train': 1.3591214418411255} 08/30/2021 22:25:50 - INFO - __main__ - Step 50975: {'lr': 0.0003766477630740827, 'samples': 9787200, 'steps': 50974, 'loss/train': 1.1668370962142944} 08/30/2021 22:25:52 - INFO - __main__ - Step 50976: {'lr': 0.00037664318764238445, 'samples': 9787392, 'steps': 50975, 'loss/train': 1.9410172700881958} 08/30/2021 22:25:52 - INFO - __main__ - Step 50977: {'lr': 0.0003766386121536228, 'samples': 9787584, 'steps': 50976, 'loss/train': 1.7867932319641113} 08/30/2021 22:25:52 - INFO - __main__ - Step 50978: {'lr': 0.00037663403660779984, 'samples': 9787776, 'steps': 50977, 'loss/train': 1.4452104568481445} 08/30/2021 22:25:53 - INFO - __main__ - Step 50979: {'lr': 0.00037662946100491736, 'samples': 9787968, 'steps': 50978, 'loss/train': 1.193568468093872} 08/30/2021 22:25:53 - INFO - __main__ - Step 50980: {'lr': 0.00037662488534497766, 'samples': 9788160, 'steps': 50979, 'loss/train': 0.6591973304748535} 08/30/2021 22:25:54 - INFO - __main__ - Step 50981: {'lr': 0.0003766203096279828, 'samples': 9788352, 'steps': 50980, 'loss/train': 1.4129118919372559} 08/30/2021 22:25:55 - INFO - __main__ - Step 50982: {'lr': 0.00037661573385393477, 'samples': 9788544, 'steps': 50981, 'loss/train': 1.5191997289657593} 08/30/2021 22:25:55 - INFO - __main__ - Step 50983: {'lr': 0.0003766111580228356, 'samples': 9788736, 'steps': 50982, 'loss/train': 1.4790685176849365} 08/30/2021 22:25:56 - INFO - __main__ - Step 50984: {'lr': 0.00037660658213468744, 'samples': 9788928, 'steps': 50983, 'loss/train': 2.0044775009155273} 08/30/2021 22:25:56 - INFO - __main__ - Step 50985: {'lr': 0.00037660200618949225, 'samples': 9789120, 'steps': 50984, 'loss/train': 1.2575911283493042} 08/30/2021 22:25:56 - INFO - __main__ - Step 50986: {'lr': 0.0003765974301872522, 'samples': 9789312, 'steps': 50985, 'loss/train': 1.569093942642212} 08/30/2021 22:25:58 - INFO - __main__ - Step 50987: {'lr': 0.0003765928541279693, 'samples': 9789504, 'steps': 50986, 'loss/train': 0.814099907875061} 08/30/2021 22:25:58 - INFO - __main__ - Step 50988: {'lr': 0.0003765882780116455, 'samples': 9789696, 'steps': 50987, 'loss/train': 1.704711675643921} 08/30/2021 22:25:59 - INFO - __main__ - Step 50989: {'lr': 0.0003765837018382831, 'samples': 9789888, 'steps': 50988, 'loss/train': 0.9379704594612122} 08/30/2021 22:25:59 - INFO - __main__ - Step 50990: {'lr': 0.0003765791256078841, 'samples': 9790080, 'steps': 50989, 'loss/train': 1.3221157789230347} 08/30/2021 22:25:59 - INFO - __main__ - Step 50991: {'lr': 0.00037657454932045036, 'samples': 9790272, 'steps': 50990, 'loss/train': 1.6199997663497925} 08/30/2021 22:26:02 - INFO - __main__ - Step 50992: {'lr': 0.00037656997297598417, 'samples': 9790464, 'steps': 50991, 'loss/train': 1.477184772491455} 08/30/2021 22:26:02 - INFO - __main__ - Step 50993: {'lr': 0.0003765653965744874, 'samples': 9790656, 'steps': 50992, 'loss/train': 0.8813958764076233} 08/30/2021 22:26:02 - INFO - __main__ - Step 50994: {'lr': 0.00037656082011596224, 'samples': 9790848, 'steps': 50993, 'loss/train': 1.374882698059082} 08/30/2021 22:26:03 - INFO - __main__ - Step 50995: {'lr': 0.00037655624360041084, 'samples': 9791040, 'steps': 50994, 'loss/train': 0.09208963811397552} 08/30/2021 22:26:03 - INFO - __main__ - Step 50996: {'lr': 0.00037655166702783507, 'samples': 9791232, 'steps': 50995, 'loss/train': 1.3419182300567627} 08/30/2021 22:26:05 - INFO - __main__ - Step 50997: {'lr': 0.0003765470903982371, 'samples': 9791424, 'steps': 50996, 'loss/train': 1.0198330879211426} 08/30/2021 22:26:05 - INFO - __main__ - Step 50998: {'lr': 0.0003765425137116189, 'samples': 9791616, 'steps': 50997, 'loss/train': 0.6795632243156433} 08/30/2021 22:26:06 - INFO - __main__ - Step 50999: {'lr': 0.00037653793696798267, 'samples': 9791808, 'steps': 50998, 'loss/train': 0.1587800830602646} 08/30/2021 22:26:06 - INFO - __main__ - Step 51000: {'lr': 0.0003765333601673303, 'samples': 9792000, 'steps': 50999, 'loss/train': 1.6997179985046387} 08/30/2021 22:26:07 - INFO - __main__ - Step 51001: {'lr': 0.0003765287833096641, 'samples': 9792192, 'steps': 51000, 'loss/train': 0.9439852833747864} 08/30/2021 22:26:07 - INFO - __main__ - Step 51002: {'lr': 0.00037652420639498583, 'samples': 9792384, 'steps': 51001, 'loss/train': 0.8181083798408508} 08/30/2021 22:26:09 - INFO - __main__ - Step 51003: {'lr': 0.00037651962942329784, 'samples': 9792576, 'steps': 51002, 'loss/train': 2.2781405448913574} 08/30/2021 22:26:10 - INFO - __main__ - Step 51004: {'lr': 0.0003765150523946019, 'samples': 9792768, 'steps': 51003, 'loss/train': 1.070449709892273} 08/30/2021 22:26:10 - INFO - __main__ - Step 51005: {'lr': 0.00037651047530890035, 'samples': 9792960, 'steps': 51004, 'loss/train': 1.507706880569458} 08/30/2021 22:26:10 - INFO - __main__ - Step 51006: {'lr': 0.0003765058981661952, 'samples': 9793152, 'steps': 51005, 'loss/train': 1.3608185052871704} 08/30/2021 22:26:11 - INFO - __main__ - Step 51007: {'lr': 0.0003765013209664883, 'samples': 9793344, 'steps': 51006, 'loss/train': 1.2262402772903442} 08/30/2021 22:26:12 - INFO - __main__ - Step 51008: {'lr': 0.00037649674370978195, 'samples': 9793536, 'steps': 51007, 'loss/train': 1.3377485275268555} 08/30/2021 22:26:13 - INFO - __main__ - Step 51009: {'lr': 0.000376492166396078, 'samples': 9793728, 'steps': 51008, 'loss/train': 1.5474079847335815} 08/30/2021 22:26:13 - INFO - __main__ - Step 51010: {'lr': 0.0003764875890253787, 'samples': 9793920, 'steps': 51009, 'loss/train': 1.4240821599960327} 08/30/2021 22:26:14 - INFO - __main__ - Step 51011: {'lr': 0.0003764830115976861, 'samples': 9794112, 'steps': 51010, 'loss/train': 0.49576616287231445} 08/30/2021 22:26:14 - INFO - __main__ - Step 51012: {'lr': 0.00037647843411300213, 'samples': 9794304, 'steps': 51011, 'loss/train': 0.06136703118681908} 08/30/2021 22:26:16 - INFO - __main__ - Step 51013: {'lr': 0.00037647385657132895, 'samples': 9794496, 'steps': 51012, 'loss/train': 1.6304805278778076} 08/30/2021 22:26:16 - INFO - __main__ - Step 51014: {'lr': 0.0003764692789726686, 'samples': 9794688, 'steps': 51013, 'loss/train': 1.4706993103027344} 08/30/2021 22:26:16 - INFO - __main__ - Step 51015: {'lr': 0.00037646470131702314, 'samples': 9794880, 'steps': 51014, 'loss/train': 0.032574210315942764} 08/30/2021 22:26:17 - INFO - __main__ - Step 51016: {'lr': 0.00037646012360439463, 'samples': 9795072, 'steps': 51015, 'loss/train': 1.276258945465088} 08/30/2021 22:26:17 - INFO - __main__ - Step 51017: {'lr': 0.0003764555458347851, 'samples': 9795264, 'steps': 51016, 'loss/train': 1.5600028038024902} 08/30/2021 22:26:17 - INFO - __main__ - Step 51018: {'lr': 0.00037645096800819684, 'samples': 9795456, 'steps': 51017, 'loss/train': 1.8636372089385986} 08/30/2021 22:26:19 - INFO - __main__ - Step 51019: {'lr': 0.00037644639012463155, 'samples': 9795648, 'steps': 51018, 'loss/train': 0.23138362169265747} 08/30/2021 22:26:19 - INFO - __main__ - Step 51020: {'lr': 0.00037644181218409156, 'samples': 9795840, 'steps': 51019, 'loss/train': 1.5921701192855835} 08/30/2021 22:26:20 - INFO - __main__ - Step 51021: {'lr': 0.0003764372341865788, 'samples': 9796032, 'steps': 51020, 'loss/train': 1.307142734527588} 08/30/2021 22:26:20 - INFO - __main__ - Step 51022: {'lr': 0.00037643265613209533, 'samples': 9796224, 'steps': 51021, 'loss/train': 1.2661389112472534} 08/30/2021 22:26:21 - INFO - __main__ - Step 51023: {'lr': 0.00037642807802064327, 'samples': 9796416, 'steps': 51022, 'loss/train': 0.9044985175132751} 08/30/2021 22:26:22 - INFO - __main__ - Step 51024: {'lr': 0.00037642349985222474, 'samples': 9796608, 'steps': 51023, 'loss/train': 0.41017019748687744} 08/30/2021 22:26:23 - INFO - __main__ - Step 51025: {'lr': 0.0003764189216268417, 'samples': 9796800, 'steps': 51024, 'loss/train': 1.484224796295166} 08/30/2021 22:26:23 - INFO - __main__ - Step 51026: {'lr': 0.0003764143433444962, 'samples': 9796992, 'steps': 51025, 'loss/train': 1.3008670806884766} 08/30/2021 22:26:23 - INFO - __main__ - Step 51027: {'lr': 0.00037640976500519035, 'samples': 9797184, 'steps': 51026, 'loss/train': 0.5754580497741699} 08/30/2021 22:26:24 - INFO - __main__ - Step 51028: {'lr': 0.0003764051866089262, 'samples': 9797376, 'steps': 51027, 'loss/train': 1.3381850719451904} 08/30/2021 22:26:25 - INFO - __main__ - Step 51029: {'lr': 0.00037640060815570585, 'samples': 9797568, 'steps': 51028, 'loss/train': 1.01432204246521} 08/30/2021 22:26:26 - INFO - __main__ - Step 51030: {'lr': 0.0003763960296455314, 'samples': 9797760, 'steps': 51029, 'loss/train': 1.67357337474823} 08/30/2021 22:26:26 - INFO - __main__ - Step 51031: {'lr': 0.0003763914510784048, 'samples': 9797952, 'steps': 51030, 'loss/train': 1.4265296459197998} 08/30/2021 22:26:27 - INFO - __main__ - Step 51032: {'lr': 0.00037638687245432817, 'samples': 9798144, 'steps': 51031, 'loss/train': 1.2338874340057373} 08/30/2021 22:26:27 - INFO - __main__ - Step 51033: {'lr': 0.00037638229377330356, 'samples': 9798336, 'steps': 51032, 'loss/train': 5.946896553039551} 08/30/2021 22:26:27 - INFO - __main__ - Step 51034: {'lr': 0.00037637771503533303, 'samples': 9798528, 'steps': 51033, 'loss/train': 5.8254241943359375} 08/30/2021 22:26:29 - INFO - __main__ - Step 51035: {'lr': 0.00037637313624041863, 'samples': 9798720, 'steps': 51034, 'loss/train': 1.847798466682434} 08/30/2021 22:26:29 - INFO - __main__ - Step 51036: {'lr': 0.00037636855738856247, 'samples': 9798912, 'steps': 51035, 'loss/train': 0.8923953175544739} 08/30/2021 22:26:30 - INFO - __main__ - Step 51037: {'lr': 0.00037636397847976656, 'samples': 9799104, 'steps': 51036, 'loss/train': 1.4600393772125244} 08/30/2021 22:26:30 - INFO - __main__ - Step 51038: {'lr': 0.00037635939951403307, 'samples': 9799296, 'steps': 51037, 'loss/train': 2.040217161178589} 08/30/2021 22:26:30 - INFO - __main__ - Step 51039: {'lr': 0.00037635482049136395, 'samples': 9799488, 'steps': 51038, 'loss/train': 1.0636835098266602} 08/30/2021 22:26:31 - INFO - __main__ - Step 51040: {'lr': 0.0003763502414117612, 'samples': 9799680, 'steps': 51039, 'loss/train': 1.5607802867889404} 08/30/2021 22:26:32 - INFO - __main__ - Step 51041: {'lr': 0.0003763456622752271, 'samples': 9799872, 'steps': 51040, 'loss/train': 1.3773200511932373} 08/30/2021 22:26:33 - INFO - __main__ - Step 51042: {'lr': 0.0003763410830817635, 'samples': 9800064, 'steps': 51041, 'loss/train': 0.6044677495956421} 08/30/2021 22:26:33 - INFO - __main__ - Step 51043: {'lr': 0.00037633650383137263, 'samples': 9800256, 'steps': 51042, 'loss/train': 1.3890656232833862} 08/30/2021 22:26:33 - INFO - __main__ - Step 51044: {'lr': 0.0003763319245240565, 'samples': 9800448, 'steps': 51043, 'loss/train': 0.9743980169296265} 08/30/2021 22:26:34 - INFO - __main__ - Step 51045: {'lr': 0.00037632734515981715, 'samples': 9800640, 'steps': 51044, 'loss/train': 1.0391114950180054} 08/30/2021 22:26:35 - INFO - __main__ - Step 51046: {'lr': 0.00037632276573865657, 'samples': 9800832, 'steps': 51045, 'loss/train': 1.7304145097732544} 08/30/2021 22:26:36 - INFO - __main__ - Step 51047: {'lr': 0.00037631818626057695, 'samples': 9801024, 'steps': 51046, 'loss/train': 0.8279850482940674} 08/30/2021 22:26:36 - INFO - __main__ - Step 51048: {'lr': 0.0003763136067255803, 'samples': 9801216, 'steps': 51047, 'loss/train': 1.1320995092391968} 08/30/2021 22:26:36 - INFO - __main__ - Step 51049: {'lr': 0.00037630902713366865, 'samples': 9801408, 'steps': 51048, 'loss/train': 1.310449242591858} 08/30/2021 22:26:37 - INFO - __main__ - Step 51050: {'lr': 0.00037630444748484415, 'samples': 9801600, 'steps': 51049, 'loss/train': 1.2691503763198853} 08/30/2021 22:26:38 - INFO - __main__ - Step 51051: {'lr': 0.00037629986777910885, 'samples': 9801792, 'steps': 51050, 'loss/train': 1.329351782798767} 08/30/2021 22:26:39 - INFO - __main__ - Step 51052: {'lr': 0.00037629528801646475, 'samples': 9801984, 'steps': 51051, 'loss/train': 1.1222641468048096} 08/30/2021 22:26:39 - INFO - __main__ - Step 51053: {'lr': 0.0003762907081969139, 'samples': 9802176, 'steps': 51052, 'loss/train': 1.2861281633377075} 08/30/2021 22:26:39 - INFO - __main__ - Step 51054: {'lr': 0.00037628612832045846, 'samples': 9802368, 'steps': 51053, 'loss/train': 1.512338638305664} 08/30/2021 22:26:40 - INFO - __main__ - Step 51055: {'lr': 0.0003762815483871004, 'samples': 9802560, 'steps': 51054, 'loss/train': 1.5725440979003906} 08/30/2021 22:26:42 - INFO - __main__ - Step 51056: {'lr': 0.00037627696839684176, 'samples': 9802752, 'steps': 51055, 'loss/train': 1.3401360511779785} 08/30/2021 22:26:42 - INFO - __main__ - Step 51057: {'lr': 0.0003762723883496848, 'samples': 9802944, 'steps': 51056, 'loss/train': 1.83293879032135} 08/30/2021 22:26:43 - INFO - __main__ - Step 51058: {'lr': 0.00037626780824563145, 'samples': 9803136, 'steps': 51057, 'loss/train': 1.2921923398971558} 08/30/2021 22:26:43 - INFO - __main__ - Step 51059: {'lr': 0.0003762632280846837, 'samples': 9803328, 'steps': 51058, 'loss/train': 1.3698080778121948} 08/30/2021 22:26:43 - INFO - __main__ - Step 51060: {'lr': 0.00037625864786684364, 'samples': 9803520, 'steps': 51059, 'loss/train': 0.8140104413032532} 08/30/2021 22:26:45 - INFO - __main__ - Step 51061: {'lr': 0.00037625406759211346, 'samples': 9803712, 'steps': 51060, 'loss/train': 1.9415984153747559} 08/30/2021 22:26:45 - INFO - __main__ - Step 51062: {'lr': 0.00037624948726049513, 'samples': 9803904, 'steps': 51061, 'loss/train': 0.5403301119804382} 08/30/2021 22:26:46 - INFO - __main__ - Step 51063: {'lr': 0.0003762449068719907, 'samples': 9804096, 'steps': 51062, 'loss/train': 0.5302300453186035} 08/30/2021 22:26:46 - INFO - __main__ - Step 51064: {'lr': 0.00037624032642660234, 'samples': 9804288, 'steps': 51063, 'loss/train': 0.9016693234443665} 08/30/2021 22:26:46 - INFO - __main__ - Step 51065: {'lr': 0.00037623574592433195, 'samples': 9804480, 'steps': 51064, 'loss/train': 1.92802095413208} 08/30/2021 22:26:48 - INFO - __main__ - Step 51066: {'lr': 0.00037623116536518176, 'samples': 9804672, 'steps': 51065, 'loss/train': 1.5189765691757202} 08/30/2021 22:26:48 - INFO - __main__ - Step 51067: {'lr': 0.00037622658474915373, 'samples': 9804864, 'steps': 51066, 'loss/train': 0.8574656248092651} 08/30/2021 22:26:49 - INFO - __main__ - Step 51068: {'lr': 0.0003762220040762499, 'samples': 9805056, 'steps': 51067, 'loss/train': 1.0047905445098877} 08/30/2021 22:26:49 - INFO - __main__ - Step 51069: {'lr': 0.0003762174233464724, 'samples': 9805248, 'steps': 51068, 'loss/train': 1.1985036134719849} 08/30/2021 22:26:49 - INFO - __main__ - Step 51070: {'lr': 0.00037621284255982324, 'samples': 9805440, 'steps': 51069, 'loss/train': 1.8381924629211426} 08/30/2021 22:26:51 - INFO - __main__ - Step 51071: {'lr': 0.0003762082617163046, 'samples': 9805632, 'steps': 51070, 'loss/train': 1.524709701538086} 08/30/2021 22:26:52 - INFO - __main__ - Step 51072: {'lr': 0.0003762036808159185, 'samples': 9805824, 'steps': 51071, 'loss/train': 1.2687848806381226} 08/30/2021 22:26:52 - INFO - __main__ - Step 51073: {'lr': 0.0003761990998586669, 'samples': 9806016, 'steps': 51072, 'loss/train': 0.7302113175392151} 08/30/2021 22:26:52 - INFO - __main__ - Step 51074: {'lr': 0.0003761945188445519, 'samples': 9806208, 'steps': 51073, 'loss/train': 1.64555823802948} 08/30/2021 22:26:53 - INFO - __main__ - Step 51075: {'lr': 0.00037618993777357567, 'samples': 9806400, 'steps': 51074, 'loss/train': 0.1517094522714615} 08/30/2021 22:26:54 - INFO - __main__ - Step 51076: {'lr': 0.00037618535664574014, 'samples': 9806592, 'steps': 51075, 'loss/train': 0.7418529391288757} 08/30/2021 22:26:55 - INFO - __main__ - Step 51077: {'lr': 0.0003761807754610475, 'samples': 9806784, 'steps': 51076, 'loss/train': 1.3080519437789917} 08/30/2021 22:26:55 - INFO - __main__ - Step 51078: {'lr': 0.0003761761942194997, 'samples': 9806976, 'steps': 51077, 'loss/train': 1.0140433311462402} 08/30/2021 22:26:55 - INFO - __main__ - Step 51079: {'lr': 0.00037617161292109887, 'samples': 9807168, 'steps': 51078, 'loss/train': 1.57699453830719} 08/30/2021 22:26:56 - INFO - __main__ - Step 51080: {'lr': 0.0003761670315658471, 'samples': 9807360, 'steps': 51079, 'loss/train': 1.6466772556304932} 08/30/2021 22:26:57 - INFO - __main__ - Step 51081: {'lr': 0.0003761624501537463, 'samples': 9807552, 'steps': 51080, 'loss/train': 1.5381520986557007} 08/30/2021 22:26:57 - INFO - __main__ - Step 51082: {'lr': 0.00037615786868479875, 'samples': 9807744, 'steps': 51081, 'loss/train': 1.18941330909729} 08/30/2021 22:26:58 - INFO - __main__ - Step 51083: {'lr': 0.0003761532871590063, 'samples': 9807936, 'steps': 51082, 'loss/train': 1.2548831701278687} 08/30/2021 22:26:58 - INFO - __main__ - Step 51084: {'lr': 0.0003761487055763713, 'samples': 9808128, 'steps': 51083, 'loss/train': 1.1112098693847656} 08/30/2021 22:26:59 - INFO - __main__ - Step 51085: {'lr': 0.0003761441239368955, 'samples': 9808320, 'steps': 51084, 'loss/train': 1.2736133337020874} 08/30/2021 22:27:00 - INFO - __main__ - Step 51086: {'lr': 0.0003761395422405811, 'samples': 9808512, 'steps': 51085, 'loss/train': 1.235261082649231} 08/30/2021 22:27:00 - INFO - __main__ - Step 51087: {'lr': 0.00037613496048743023, 'samples': 9808704, 'steps': 51086, 'loss/train': 1.9329742193222046} 08/30/2021 22:27:01 - INFO - __main__ - Step 51088: {'lr': 0.00037613037867744494, 'samples': 9808896, 'steps': 51087, 'loss/train': 1.3166897296905518} 08/30/2021 22:27:01 - INFO - __main__ - Step 51089: {'lr': 0.00037612579681062713, 'samples': 9809088, 'steps': 51088, 'loss/train': 1.9982270002365112} 08/30/2021 22:27:01 - INFO - __main__ - Step 51090: {'lr': 0.000376121214886979, 'samples': 9809280, 'steps': 51089, 'loss/train': 1.3550151586532593} 08/30/2021 22:27:03 - INFO - __main__ - Step 51091: {'lr': 0.00037611663290650267, 'samples': 9809472, 'steps': 51090, 'loss/train': 1.4045321941375732} 08/30/2021 22:27:03 - INFO - __main__ - Step 51092: {'lr': 0.0003761120508692001, 'samples': 9809664, 'steps': 51091, 'loss/train': 1.3623402118682861} 08/30/2021 22:27:04 - INFO - __main__ - Step 51093: {'lr': 0.00037610746877507343, 'samples': 9809856, 'steps': 51092, 'loss/train': 1.6759140491485596} 08/30/2021 22:27:04 - INFO - __main__ - Step 51094: {'lr': 0.0003761028866241246, 'samples': 9810048, 'steps': 51093, 'loss/train': 1.1017138957977295} 08/30/2021 22:27:04 - INFO - __main__ - Step 51095: {'lr': 0.00037609830441635573, 'samples': 9810240, 'steps': 51094, 'loss/train': 1.4433974027633667} 08/30/2021 22:27:05 - INFO - __main__ - Step 51096: {'lr': 0.00037609372215176897, 'samples': 9810432, 'steps': 51095, 'loss/train': 1.3323721885681152} 08/30/2021 22:27:06 - INFO - __main__ - Step 51097: {'lr': 0.0003760891398303663, 'samples': 9810624, 'steps': 51096, 'loss/train': 1.3992011547088623} 08/30/2021 22:27:07 - INFO - __main__ - Step 51098: {'lr': 0.0003760845574521499, 'samples': 9810816, 'steps': 51097, 'loss/train': 1.0762879848480225} 08/30/2021 22:27:07 - INFO - __main__ - Step 51099: {'lr': 0.00037607997501712165, 'samples': 9811008, 'steps': 51098, 'loss/train': 1.576791763305664} 08/30/2021 22:27:07 - INFO - __main__ - Step 51100: {'lr': 0.0003760753925252838, 'samples': 9811200, 'steps': 51099, 'loss/train': 1.6294625997543335} 08/30/2021 22:27:08 - INFO - __main__ - Step 51101: {'lr': 0.0003760708099766382, 'samples': 9811392, 'steps': 51100, 'loss/train': 1.4208580255508423} 08/30/2021 22:27:10 - INFO - __main__ - Step 51102: {'lr': 0.00037606622737118713, 'samples': 9811584, 'steps': 51101, 'loss/train': 1.3910399675369263} 08/30/2021 22:27:10 - INFO - __main__ - Step 51103: {'lr': 0.00037606164470893247, 'samples': 9811776, 'steps': 51102, 'loss/train': 1.2674756050109863} 08/30/2021 22:27:11 - INFO - __main__ - Step 51104: {'lr': 0.00037605706198987646, 'samples': 9811968, 'steps': 51103, 'loss/train': 1.0044111013412476} 08/30/2021 22:27:11 - INFO - __main__ - Step 51105: {'lr': 0.0003760524792140211, 'samples': 9812160, 'steps': 51104, 'loss/train': 1.3432573080062866} 08/30/2021 22:27:11 - INFO - __main__ - Step 51106: {'lr': 0.0003760478963813684, 'samples': 9812352, 'steps': 51105, 'loss/train': 0.8721525073051453} 08/30/2021 22:27:13 - INFO - __main__ - Step 51107: {'lr': 0.00037604331349192047, 'samples': 9812544, 'steps': 51106, 'loss/train': 1.1137263774871826} 08/30/2021 22:27:14 - INFO - __main__ - Step 51108: {'lr': 0.00037603873054567927, 'samples': 9812736, 'steps': 51107, 'loss/train': 1.4222512245178223} 08/30/2021 22:27:14 - INFO - __main__ - Step 51109: {'lr': 0.00037603414754264707, 'samples': 9812928, 'steps': 51108, 'loss/train': 1.319298267364502} 08/30/2021 22:27:15 - INFO - __main__ - Step 51110: {'lr': 0.00037602956448282577, 'samples': 9813120, 'steps': 51109, 'loss/train': 1.4606393575668335} 08/30/2021 22:27:15 - INFO - __main__ - Step 51111: {'lr': 0.00037602498136621754, 'samples': 9813312, 'steps': 51110, 'loss/train': 1.8039977550506592} 08/30/2021 22:27:15 - INFO - __main__ - Step 51112: {'lr': 0.00037602039819282444, 'samples': 9813504, 'steps': 51111, 'loss/train': 1.6095964908599854} 08/30/2021 22:27:16 - INFO - __main__ - Step 51113: {'lr': 0.00037601581496264847, 'samples': 9813696, 'steps': 51112, 'loss/train': 1.3599810600280762} 08/30/2021 22:27:18 - INFO - __main__ - Step 51114: {'lr': 0.0003760112316756917, 'samples': 9813888, 'steps': 51113, 'loss/train': 0.9863927960395813} 08/30/2021 22:27:18 - INFO - __main__ - Step 51115: {'lr': 0.0003760066483319562, 'samples': 9814080, 'steps': 51114, 'loss/train': 0.5862434506416321} 08/30/2021 22:27:19 - INFO - __main__ - Step 51116: {'lr': 0.000376002064931444, 'samples': 9814272, 'steps': 51115, 'loss/train': 2.3102502822875977} 08/30/2021 22:27:19 - INFO - __main__ - Step 51117: {'lr': 0.00037599748147415724, 'samples': 9814464, 'steps': 51116, 'loss/train': 1.5437085628509521} 08/30/2021 22:27:19 - INFO - __main__ - Step 51118: {'lr': 0.000375992897960098, 'samples': 9814656, 'steps': 51117, 'loss/train': 1.741047978401184} 08/30/2021 22:27:21 - INFO - __main__ - Step 51119: {'lr': 0.0003759883143892683, 'samples': 9814848, 'steps': 51118, 'loss/train': 1.3197335004806519} 08/30/2021 22:27:21 - INFO - __main__ - Step 51120: {'lr': 0.00037598373076167023, 'samples': 9815040, 'steps': 51119, 'loss/train': 1.4412221908569336} 08/30/2021 22:27:22 - INFO - __main__ - Step 51121: {'lr': 0.0003759791470773058, 'samples': 9815232, 'steps': 51120, 'loss/train': 1.1492435932159424} 08/30/2021 22:27:22 - INFO - __main__ - Step 51122: {'lr': 0.0003759745633361771, 'samples': 9815424, 'steps': 51121, 'loss/train': 1.8508864641189575} 08/30/2021 22:27:22 - INFO - __main__ - Step 51123: {'lr': 0.0003759699795382863, 'samples': 9815616, 'steps': 51122, 'loss/train': 1.3926717042922974} 08/30/2021 22:27:24 - INFO - __main__ - Step 51124: {'lr': 0.00037596539568363524, 'samples': 9815808, 'steps': 51123, 'loss/train': 1.5257015228271484} 08/30/2021 22:27:24 - INFO - __main__ - Step 51125: {'lr': 0.0003759608117722262, 'samples': 9816000, 'steps': 51124, 'loss/train': 0.9977713823318481} 08/30/2021 22:27:25 - INFO - __main__ - Step 51126: {'lr': 0.00037595622780406114, 'samples': 9816192, 'steps': 51125, 'loss/train': 1.4593037366867065} 08/30/2021 22:27:25 - INFO - __main__ - Step 51127: {'lr': 0.0003759516437791421, 'samples': 9816384, 'steps': 51126, 'loss/train': 1.0894402265548706} 08/30/2021 22:27:25 - INFO - __main__ - Step 51128: {'lr': 0.0003759470596974712, 'samples': 9816576, 'steps': 51127, 'loss/train': 1.4496800899505615} 08/30/2021 22:27:27 - INFO - __main__ - Step 51129: {'lr': 0.0003759424755590505, 'samples': 9816768, 'steps': 51128, 'loss/train': 1.4660627841949463} 08/30/2021 22:27:27 - INFO - __main__ - Step 51130: {'lr': 0.0003759378913638822, 'samples': 9816960, 'steps': 51129, 'loss/train': 1.0081418752670288} 08/30/2021 22:27:28 - INFO - __main__ - Step 51131: {'lr': 0.0003759333071119681, 'samples': 9817152, 'steps': 51130, 'loss/train': 1.3580737113952637} 08/30/2021 22:27:28 - INFO - __main__ - Step 51132: {'lr': 0.0003759287228033104, 'samples': 9817344, 'steps': 51131, 'loss/train': 1.2268321514129639} 08/30/2021 22:27:28 - INFO - __main__ - Step 51133: {'lr': 0.0003759241384379112, 'samples': 9817536, 'steps': 51132, 'loss/train': 1.9298758506774902} 08/30/2021 22:27:30 - INFO - __main__ - Step 51134: {'lr': 0.0003759195540157725, 'samples': 9817728, 'steps': 51133, 'loss/train': 1.9323010444641113} 08/30/2021 22:27:31 - INFO - __main__ - Step 51135: {'lr': 0.00037591496953689644, 'samples': 9817920, 'steps': 51134, 'loss/train': 1.1901570558547974} 08/30/2021 22:27:31 - INFO - __main__ - Step 51136: {'lr': 0.00037591038500128495, 'samples': 9818112, 'steps': 51135, 'loss/train': 1.7500919103622437} 08/30/2021 22:27:31 - INFO - __main__ - Step 51137: {'lr': 0.00037590580040894024, 'samples': 9818304, 'steps': 51136, 'loss/train': 1.491097331047058} 08/30/2021 22:27:32 - INFO - __main__ - Step 51138: {'lr': 0.0003759012157598643, 'samples': 9818496, 'steps': 51137, 'loss/train': 1.2977385520935059} 08/30/2021 22:27:32 - INFO - __main__ - Step 51139: {'lr': 0.00037589663105405924, 'samples': 9818688, 'steps': 51138, 'loss/train': 0.034214574843645096} 08/30/2021 22:27:34 - INFO - __main__ - Step 51140: {'lr': 0.00037589204629152705, 'samples': 9818880, 'steps': 51139, 'loss/train': 1.4670284986495972} 08/30/2021 22:27:34 - INFO - __main__ - Step 51141: {'lr': 0.00037588746147226994, 'samples': 9819072, 'steps': 51140, 'loss/train': 1.605432152748108} 08/30/2021 22:27:34 - INFO - __main__ - Step 51142: {'lr': 0.00037588287659628977, 'samples': 9819264, 'steps': 51141, 'loss/train': 1.2759867906570435} 08/30/2021 22:27:35 - INFO - __main__ - Step 51143: {'lr': 0.0003758782916635888, 'samples': 9819456, 'steps': 51142, 'loss/train': 1.6266380548477173} 08/30/2021 22:27:35 - INFO - __main__ - Step 51144: {'lr': 0.000375873706674169, 'samples': 9819648, 'steps': 51143, 'loss/train': 1.7305018901824951} 08/30/2021 22:27:37 - INFO - __main__ - Step 51145: {'lr': 0.0003758691216280324, 'samples': 9819840, 'steps': 51144, 'loss/train': 1.1952332258224487} 08/30/2021 22:27:37 - INFO - __main__ - Step 51146: {'lr': 0.00037586453652518117, 'samples': 9820032, 'steps': 51145, 'loss/train': 1.9703680276870728} 08/30/2021 22:27:37 - INFO - __main__ - Step 51147: {'lr': 0.00037585995136561734, 'samples': 9820224, 'steps': 51146, 'loss/train': 0.6473832726478577} 08/30/2021 22:27:38 - INFO - __main__ - Step 51148: {'lr': 0.0003758553661493429, 'samples': 9820416, 'steps': 51147, 'loss/train': 0.26936134696006775} 08/30/2021 22:27:38 - INFO - __main__ - Step 51149: {'lr': 0.00037585078087635994, 'samples': 9820608, 'steps': 51148, 'loss/train': 1.6861234903335571} 08/30/2021 22:27:40 - INFO - __main__ - Step 51150: {'lr': 0.00037584619554667065, 'samples': 9820800, 'steps': 51149, 'loss/train': 1.373807668685913} 08/30/2021 22:27:41 - INFO - __main__ - Step 51151: {'lr': 0.000375841610160277, 'samples': 9820992, 'steps': 51150, 'loss/train': 1.2162147760391235} 08/30/2021 22:27:41 - INFO - __main__ - Step 51152: {'lr': 0.00037583702471718106, 'samples': 9821184, 'steps': 51151, 'loss/train': 0.9273143410682678} 08/30/2021 22:27:41 - INFO - __main__ - Step 51153: {'lr': 0.00037583243921738484, 'samples': 9821376, 'steps': 51152, 'loss/train': 1.786708116531372} 08/30/2021 22:27:42 - INFO - __main__ - Step 51154: {'lr': 0.0003758278536608905, 'samples': 9821568, 'steps': 51153, 'loss/train': 1.7401949167251587} 08/30/2021 22:27:42 - INFO - __main__ - Step 51155: {'lr': 0.00037582326804770004, 'samples': 9821760, 'steps': 51154, 'loss/train': 1.1159836053848267} 08/30/2021 22:27:43 - INFO - __main__ - Step 51156: {'lr': 0.0003758186823778156, 'samples': 9821952, 'steps': 51155, 'loss/train': 1.6246800422668457} 08/30/2021 22:27:44 - INFO - __main__ - Step 51157: {'lr': 0.0003758140966512392, 'samples': 9822144, 'steps': 51156, 'loss/train': 1.1771578788757324} 08/30/2021 22:27:44 - INFO - __main__ - Step 51158: {'lr': 0.0003758095108679729, 'samples': 9822336, 'steps': 51157, 'loss/train': 1.7330979108810425} 08/30/2021 22:27:45 - INFO - __main__ - Step 51159: {'lr': 0.0003758049250280188, 'samples': 9822528, 'steps': 51158, 'loss/train': 0.45754772424697876} 08/30/2021 22:27:45 - INFO - __main__ - Step 51160: {'lr': 0.0003758003391313789, 'samples': 9822720, 'steps': 51159, 'loss/train': 1.5674817562103271} 08/30/2021 22:27:47 - INFO - __main__ - Step 51161: {'lr': 0.00037579575317805525, 'samples': 9822912, 'steps': 51160, 'loss/train': 0.47780969738960266} 08/30/2021 22:27:47 - INFO - __main__ - Step 51162: {'lr': 0.00037579116716805007, 'samples': 9823104, 'steps': 51161, 'loss/train': 1.261548399925232} 08/30/2021 22:27:47 - INFO - __main__ - Step 51163: {'lr': 0.00037578658110136535, 'samples': 9823296, 'steps': 51162, 'loss/train': 1.2016081809997559} 08/30/2021 22:27:48 - INFO - __main__ - Step 51164: {'lr': 0.00037578199497800304, 'samples': 9823488, 'steps': 51163, 'loss/train': 1.8022922277450562} 08/30/2021 22:27:48 - INFO - __main__ - Step 51165: {'lr': 0.0003757774087979654, 'samples': 9823680, 'steps': 51164, 'loss/train': 1.188241720199585} 08/30/2021 22:27:49 - INFO - __main__ - Step 51166: {'lr': 0.0003757728225612543, 'samples': 9823872, 'steps': 51165, 'loss/train': 1.1344610452651978} 08/30/2021 22:27:51 - INFO - __main__ - Step 51167: {'lr': 0.00037576823626787203, 'samples': 9824064, 'steps': 51166, 'loss/train': 1.4764689207077026} 08/30/2021 22:27:51 - INFO - __main__ - Step 51168: {'lr': 0.00037576364991782045, 'samples': 9824256, 'steps': 51167, 'loss/train': 1.1658306121826172} 08/30/2021 22:27:51 - INFO - __main__ - Step 51169: {'lr': 0.00037575906351110174, 'samples': 9824448, 'steps': 51168, 'loss/train': 1.5185136795043945} 08/30/2021 22:27:52 - INFO - __main__ - Step 51170: {'lr': 0.0003757544770477179, 'samples': 9824640, 'steps': 51169, 'loss/train': 1.618928074836731} 08/30/2021 22:27:52 - INFO - __main__ - Step 51171: {'lr': 0.00037574989052767106, 'samples': 9824832, 'steps': 51170, 'loss/train': 1.0890928506851196} 08/30/2021 22:27:54 - INFO - __main__ - Step 51172: {'lr': 0.0003757453039509633, 'samples': 9825024, 'steps': 51171, 'loss/train': 1.8198953866958618} 08/30/2021 22:27:54 - INFO - __main__ - Step 51173: {'lr': 0.0003757407173175966, 'samples': 9825216, 'steps': 51172, 'loss/train': 1.3152436017990112} 08/30/2021 22:27:55 - INFO - __main__ - Step 51174: {'lr': 0.00037573613062757304, 'samples': 9825408, 'steps': 51173, 'loss/train': 1.2258979082107544} 08/30/2021 22:27:55 - INFO - __main__ - Step 51175: {'lr': 0.00037573154388089483, 'samples': 9825600, 'steps': 51174, 'loss/train': 1.0650404691696167} 08/30/2021 22:27:55 - INFO - __main__ - Step 51176: {'lr': 0.00037572695707756385, 'samples': 9825792, 'steps': 51175, 'loss/train': 1.4242565631866455} 08/30/2021 22:27:57 - INFO - __main__ - Step 51177: {'lr': 0.0003757223702175822, 'samples': 9825984, 'steps': 51176, 'loss/train': 1.0386673212051392} 08/30/2021 22:27:57 - INFO - __main__ - Step 51178: {'lr': 0.00037571778330095206, 'samples': 9826176, 'steps': 51177, 'loss/train': 1.1864923238754272} 08/30/2021 22:27:58 - INFO - __main__ - Step 51179: {'lr': 0.00037571319632767543, 'samples': 9826368, 'steps': 51178, 'loss/train': 1.5223625898361206} 08/30/2021 22:27:58 - INFO - __main__ - Step 51180: {'lr': 0.0003757086092977544, 'samples': 9826560, 'steps': 51179, 'loss/train': 1.0784481763839722} 08/30/2021 22:27:58 - INFO - __main__ - Step 51181: {'lr': 0.00037570402221119093, 'samples': 9826752, 'steps': 51180, 'loss/train': 1.181361198425293} 08/30/2021 22:27:59 - INFO - __main__ - Step 51182: {'lr': 0.0003756994350679872, 'samples': 9826944, 'steps': 51181, 'loss/train': 1.0486514568328857} 08/30/2021 22:28:00 - INFO - __main__ - Step 51183: {'lr': 0.00037569484786814525, 'samples': 9827136, 'steps': 51182, 'loss/train': 0.5431240200996399} 08/30/2021 22:28:01 - INFO - __main__ - Step 51184: {'lr': 0.0003756902606116671, 'samples': 9827328, 'steps': 51183, 'loss/train': 0.3380163609981537} 08/30/2021 22:28:01 - INFO - __main__ - Step 51185: {'lr': 0.00037568567329855483, 'samples': 9827520, 'steps': 51184, 'loss/train': 1.1516462564468384} 08/30/2021 22:28:01 - INFO - __main__ - Step 51186: {'lr': 0.00037568108592881067, 'samples': 9827712, 'steps': 51185, 'loss/train': 1.8121020793914795} 08/30/2021 22:28:02 - INFO - __main__ - Step 51187: {'lr': 0.00037567649850243646, 'samples': 9827904, 'steps': 51186, 'loss/train': 1.3071725368499756} 08/30/2021 22:28:03 - INFO - __main__ - Step 51188: {'lr': 0.00037567191101943437, 'samples': 9828096, 'steps': 51187, 'loss/train': 0.9554001688957214} 08/30/2021 22:28:04 - INFO - __main__ - Step 51189: {'lr': 0.00037566732347980647, 'samples': 9828288, 'steps': 51188, 'loss/train': 1.4962131977081299} 08/30/2021 22:28:04 - INFO - __main__ - Step 51190: {'lr': 0.0003756627358835548, 'samples': 9828480, 'steps': 51189, 'loss/train': 2.084181070327759} 08/30/2021 22:28:05 - INFO - __main__ - Step 51191: {'lr': 0.00037565814823068143, 'samples': 9828672, 'steps': 51190, 'loss/train': 1.4744069576263428} 08/30/2021 22:28:05 - INFO - __main__ - Step 51192: {'lr': 0.0003756535605211885, 'samples': 9828864, 'steps': 51191, 'loss/train': 1.8504951000213623} 08/30/2021 22:28:06 - INFO - __main__ - Step 51193: {'lr': 0.000375648972755078, 'samples': 9829056, 'steps': 51192, 'loss/train': 0.9381686449050903} 08/30/2021 22:28:07 - INFO - __main__ - Step 51194: {'lr': 0.00037564438493235195, 'samples': 9829248, 'steps': 51193, 'loss/train': 1.825701355934143} 08/30/2021 22:28:07 - INFO - __main__ - Step 51195: {'lr': 0.0003756397970530125, 'samples': 9829440, 'steps': 51194, 'loss/train': 1.492292046546936} 08/30/2021 22:28:08 - INFO - __main__ - Step 51196: {'lr': 0.00037563520911706175, 'samples': 9829632, 'steps': 51195, 'loss/train': 1.1246968507766724} 08/30/2021 22:28:08 - INFO - __main__ - Step 51197: {'lr': 0.0003756306211245016, 'samples': 9829824, 'steps': 51196, 'loss/train': 1.5996488332748413} 08/30/2021 22:28:10 - INFO - __main__ - Step 51198: {'lr': 0.0003756260330753343, 'samples': 9830016, 'steps': 51197, 'loss/train': 0.8708871006965637} 08/30/2021 22:28:10 - INFO - __main__ - Step 51199: {'lr': 0.00037562144496956193, 'samples': 9830208, 'steps': 51198, 'loss/train': 1.4325201511383057} 08/30/2021 22:28:11 - INFO - __main__ - Step 51200: {'lr': 0.0003756168568071864, 'samples': 9830400, 'steps': 51199, 'loss/train': 1.40663480758667} 08/30/2021 22:28:11 - INFO - __main__ - Step 51201: {'lr': 0.0003756122685882098, 'samples': 9830592, 'steps': 51200, 'loss/train': 1.6266249418258667} 08/30/2021 22:28:11 - INFO - __main__ - Step 51202: {'lr': 0.00037560768031263427, 'samples': 9830784, 'steps': 51201, 'loss/train': 1.7748383283615112} 08/30/2021 22:28:12 - INFO - __main__ - Step 51203: {'lr': 0.0003756030919804619, 'samples': 9830976, 'steps': 51202, 'loss/train': 0.03139752894639969} 08/30/2021 22:28:13 - INFO - __main__ - Step 51204: {'lr': 0.00037559850359169465, 'samples': 9831168, 'steps': 51203, 'loss/train': 1.3134340047836304} 08/30/2021 22:28:14 - INFO - __main__ - Step 51205: {'lr': 0.0003755939151463347, 'samples': 9831360, 'steps': 51204, 'loss/train': 0.9820114970207214} 08/30/2021 22:28:14 - INFO - __main__ - Step 51206: {'lr': 0.0003755893266443842, 'samples': 9831552, 'steps': 51205, 'loss/train': 0.6933907270431519} 08/30/2021 22:28:14 - INFO - __main__ - Step 51207: {'lr': 0.0003755847380858449, 'samples': 9831744, 'steps': 51206, 'loss/train': 1.7568676471710205} 08/30/2021 22:28:15 - INFO - __main__ - Step 51208: {'lr': 0.0003755801494707191, 'samples': 9831936, 'steps': 51207, 'loss/train': 0.8567339777946472} 08/30/2021 22:28:15 - INFO - __main__ - Step 51209: {'lr': 0.00037557556079900886, 'samples': 9832128, 'steps': 51208, 'loss/train': 0.8565500974655151} 08/30/2021 22:28:17 - INFO - __main__ - Step 51210: {'lr': 0.0003755709720707161, 'samples': 9832320, 'steps': 51209, 'loss/train': 1.8114852905273438} 08/30/2021 22:28:17 - INFO - __main__ - Step 51211: {'lr': 0.00037556638328584314, 'samples': 9832512, 'steps': 51210, 'loss/train': 1.401003360748291} 08/30/2021 22:28:17 - INFO - __main__ - Step 51212: {'lr': 0.0003755617944443919, 'samples': 9832704, 'steps': 51211, 'loss/train': 1.4610581398010254} 08/30/2021 22:28:18 - INFO - __main__ - Step 51213: {'lr': 0.00037555720554636443, 'samples': 9832896, 'steps': 51212, 'loss/train': 1.4754494428634644} 08/30/2021 22:28:18 - INFO - __main__ - Step 51214: {'lr': 0.00037555261659176275, 'samples': 9833088, 'steps': 51213, 'loss/train': 1.045066475868225} 08/30/2021 22:28:20 - INFO - __main__ - Step 51215: {'lr': 0.00037554802758058903, 'samples': 9833280, 'steps': 51214, 'loss/train': 1.2011256217956543} 08/30/2021 22:28:20 - INFO - __main__ - Step 51216: {'lr': 0.0003755434385128453, 'samples': 9833472, 'steps': 51215, 'loss/train': 1.1464295387268066} 08/30/2021 22:28:21 - INFO - __main__ - Step 51217: {'lr': 0.00037553884938853365, 'samples': 9833664, 'steps': 51216, 'loss/train': 1.6095163822174072} 08/30/2021 22:28:21 - INFO - __main__ - Step 51218: {'lr': 0.0003755342602076561, 'samples': 9833856, 'steps': 51217, 'loss/train': 1.522133469581604} 08/30/2021 22:28:21 - INFO - __main__ - Step 51219: {'lr': 0.0003755296709702148, 'samples': 9834048, 'steps': 51218, 'loss/train': 1.2341580390930176} 08/30/2021 22:28:24 - INFO - __main__ - Step 51220: {'lr': 0.0003755250816762118, 'samples': 9834240, 'steps': 51219, 'loss/train': 0.7191727161407471} 08/30/2021 22:28:24 - INFO - __main__ - Step 51221: {'lr': 0.00037552049232564906, 'samples': 9834432, 'steps': 51220, 'loss/train': 1.31636643409729} 08/30/2021 22:28:25 - INFO - __main__ - Step 51222: {'lr': 0.0003755159029185288, 'samples': 9834624, 'steps': 51221, 'loss/train': 1.9489468336105347} 08/30/2021 22:28:25 - INFO - __main__ - Step 51223: {'lr': 0.0003755113134548529, 'samples': 9834816, 'steps': 51222, 'loss/train': 1.0711981058120728} 08/30/2021 22:28:25 - INFO - __main__ - Step 51224: {'lr': 0.00037550672393462357, 'samples': 9835008, 'steps': 51223, 'loss/train': 1.2760934829711914} 08/30/2021 22:28:27 - INFO - __main__ - Step 51225: {'lr': 0.0003755021343578429, 'samples': 9835200, 'steps': 51224, 'loss/train': 1.8748730421066284} 08/30/2021 22:28:27 - INFO - __main__ - Step 51226: {'lr': 0.0003754975447245129, 'samples': 9835392, 'steps': 51225, 'loss/train': 0.5550345778465271} 08/30/2021 22:28:28 - INFO - __main__ - Step 51227: {'lr': 0.00037549295503463563, 'samples': 9835584, 'steps': 51226, 'loss/train': 1.4395395517349243} 08/30/2021 22:28:28 - INFO - __main__ - Step 51228: {'lr': 0.0003754883652882132, 'samples': 9835776, 'steps': 51227, 'loss/train': 1.1457983255386353} 08/30/2021 22:28:28 - INFO - __main__ - Step 51229: {'lr': 0.00037548377548524755, 'samples': 9835968, 'steps': 51228, 'loss/train': 1.4728339910507202} 08/30/2021 22:28:29 - INFO - __main__ - Step 51230: {'lr': 0.0003754791856257409, 'samples': 9836160, 'steps': 51229, 'loss/train': 1.1951260566711426} 08/30/2021 22:28:30 - INFO - __main__ - Step 51231: {'lr': 0.00037547459570969527, 'samples': 9836352, 'steps': 51230, 'loss/train': 1.1749898195266724} 08/30/2021 22:28:31 - INFO - __main__ - Step 51232: {'lr': 0.0003754700057371127, 'samples': 9836544, 'steps': 51231, 'loss/train': 0.9670997858047485} 08/30/2021 22:28:31 - INFO - __main__ - Step 51233: {'lr': 0.0003754654157079954, 'samples': 9836736, 'steps': 51232, 'loss/train': 1.418890118598938} 08/30/2021 22:28:31 - INFO - __main__ - Step 51234: {'lr': 0.00037546082562234516, 'samples': 9836928, 'steps': 51233, 'loss/train': 1.05770742893219} 08/30/2021 22:28:33 - INFO - __main__ - Step 51235: {'lr': 0.00037545623548016426, 'samples': 9837120, 'steps': 51234, 'loss/train': 1.0730671882629395} 08/30/2021 22:28:34 - INFO - __main__ - Step 51236: {'lr': 0.00037545164528145474, 'samples': 9837312, 'steps': 51235, 'loss/train': 1.0975688695907593} 08/30/2021 22:28:34 - INFO - __main__ - Step 51237: {'lr': 0.00037544705502621866, 'samples': 9837504, 'steps': 51236, 'loss/train': 1.9775018692016602} 08/30/2021 22:28:34 - INFO - __main__ - Step 51238: {'lr': 0.000375442464714458, 'samples': 9837696, 'steps': 51237, 'loss/train': 0.09726051241159439} 08/30/2021 22:28:35 - INFO - __main__ - Step 51239: {'lr': 0.000375437874346175, 'samples': 9837888, 'steps': 51238, 'loss/train': 1.9660171270370483} 08/30/2021 22:28:35 - INFO - __main__ - Step 51240: {'lr': 0.0003754332839213716, 'samples': 9838080, 'steps': 51239, 'loss/train': 0.04566191881895065} 08/30/2021 22:28:36 - INFO - __main__ - Step 51241: {'lr': 0.00037542869344004987, 'samples': 9838272, 'steps': 51240, 'loss/train': 1.3567794561386108} 08/30/2021 22:28:37 - INFO - __main__ - Step 51242: {'lr': 0.0003754241029022119, 'samples': 9838464, 'steps': 51241, 'loss/train': 1.5516606569290161} 08/30/2021 22:28:37 - INFO - __main__ - Step 51243: {'lr': 0.00037541951230785975, 'samples': 9838656, 'steps': 51242, 'loss/train': 0.9326587915420532} 08/30/2021 22:28:38 - INFO - __main__ - Step 51244: {'lr': 0.00037541492165699554, 'samples': 9838848, 'steps': 51243, 'loss/train': 2.3089091777801514} 08/30/2021 22:28:38 - INFO - __main__ - Step 51245: {'lr': 0.0003754103309496213, 'samples': 9839040, 'steps': 51244, 'loss/train': 1.4722384214401245} 08/30/2021 22:28:40 - INFO - __main__ - Step 51246: {'lr': 0.00037540574018573913, 'samples': 9839232, 'steps': 51245, 'loss/train': 1.128090739250183} 08/30/2021 22:28:40 - INFO - __main__ - Step 51247: {'lr': 0.00037540114936535107, 'samples': 9839424, 'steps': 51246, 'loss/train': 0.14142058789730072} 08/30/2021 22:28:40 - INFO - __main__ - Step 51248: {'lr': 0.0003753965584884591, 'samples': 9839616, 'steps': 51247, 'loss/train': 1.6668299436569214} 08/30/2021 22:28:41 - INFO - __main__ - Step 51249: {'lr': 0.00037539196755506546, 'samples': 9839808, 'steps': 51248, 'loss/train': 1.832000732421875} 08/30/2021 22:28:41 - INFO - __main__ - Step 51250: {'lr': 0.0003753873765651721, 'samples': 9840000, 'steps': 51249, 'loss/train': 1.020297646522522} 08/30/2021 22:28:43 - INFO - __main__ - Step 51251: {'lr': 0.0003753827855187811, 'samples': 9840192, 'steps': 51250, 'loss/train': 1.5167356729507446} 08/30/2021 22:28:43 - INFO - __main__ - Step 51252: {'lr': 0.00037537819441589457, 'samples': 9840384, 'steps': 51251, 'loss/train': 1.5461879968643188} 08/30/2021 22:28:43 - INFO - __main__ - Step 51253: {'lr': 0.0003753736032565146, 'samples': 9840576, 'steps': 51252, 'loss/train': 1.443919062614441} 08/30/2021 22:28:44 - INFO - __main__ - Step 51254: {'lr': 0.0003753690120406432, 'samples': 9840768, 'steps': 51253, 'loss/train': 1.263695478439331} 08/30/2021 22:28:44 - INFO - __main__ - Step 51255: {'lr': 0.00037536442076828235, 'samples': 9840960, 'steps': 51254, 'loss/train': 0.6945824027061462} 08/30/2021 22:28:46 - INFO - __main__ - Step 51256: {'lr': 0.00037535982943943437, 'samples': 9841152, 'steps': 51255, 'loss/train': 1.1249960660934448} 08/30/2021 22:28:46 - INFO - __main__ - Step 51257: {'lr': 0.0003753552380541011, 'samples': 9841344, 'steps': 51256, 'loss/train': 1.596789002418518} 08/30/2021 22:28:46 - INFO - __main__ - Step 51258: {'lr': 0.00037535064661228476, 'samples': 9841536, 'steps': 51257, 'loss/train': 1.0218546390533447} 08/30/2021 22:28:47 - INFO - __main__ - Step 51259: {'lr': 0.00037534605511398736, 'samples': 9841728, 'steps': 51258, 'loss/train': 1.5047143697738647} 08/30/2021 22:28:47 - INFO - __main__ - Step 51260: {'lr': 0.0003753414635592109, 'samples': 9841920, 'steps': 51259, 'loss/train': 1.1775612831115723} 08/30/2021 22:28:49 - INFO - __main__ - Step 51261: {'lr': 0.0003753368719479575, 'samples': 9842112, 'steps': 51260, 'loss/train': 1.62895667552948} 08/30/2021 22:28:49 - INFO - __main__ - Step 51262: {'lr': 0.00037533228028022923, 'samples': 9842304, 'steps': 51261, 'loss/train': 1.2367775440216064} 08/30/2021 22:28:50 - INFO - __main__ - Step 51263: {'lr': 0.0003753276885560283, 'samples': 9842496, 'steps': 51262, 'loss/train': 1.105407476425171} 08/30/2021 22:28:50 - INFO - __main__ - Step 51264: {'lr': 0.0003753230967753566, 'samples': 9842688, 'steps': 51263, 'loss/train': 1.9365652799606323} 08/30/2021 22:28:50 - INFO - __main__ - Step 51265: {'lr': 0.00037531850493821616, 'samples': 9842880, 'steps': 51264, 'loss/train': 1.5902912616729736} 08/30/2021 22:28:52 - INFO - __main__ - Step 51266: {'lr': 0.00037531391304460916, 'samples': 9843072, 'steps': 51265, 'loss/train': 1.4760328531265259} 08/30/2021 22:28:52 - INFO - __main__ - Step 51267: {'lr': 0.00037530932109453767, 'samples': 9843264, 'steps': 51266, 'loss/train': 1.6036605834960938} 08/30/2021 22:28:53 - INFO - __main__ - Step 51268: {'lr': 0.00037530472908800375, 'samples': 9843456, 'steps': 51267, 'loss/train': 1.474384069442749} 08/30/2021 22:28:53 - INFO - __main__ - Step 51269: {'lr': 0.0003753001370250094, 'samples': 9843648, 'steps': 51268, 'loss/train': 1.5217070579528809} 08/30/2021 22:28:53 - INFO - __main__ - Step 51270: {'lr': 0.00037529554490555686, 'samples': 9843840, 'steps': 51269, 'loss/train': 0.9764329791069031} 08/30/2021 22:28:55 - INFO - __main__ - Step 51271: {'lr': 0.00037529095272964796, 'samples': 9844032, 'steps': 51270, 'loss/train': 1.4690406322479248} 08/30/2021 22:28:55 - INFO - __main__ - Step 51272: {'lr': 0.0003752863604972849, 'samples': 9844224, 'steps': 51271, 'loss/train': 1.3600951433181763} 08/30/2021 22:28:56 - INFO - __main__ - Step 51273: {'lr': 0.00037528176820846975, 'samples': 9844416, 'steps': 51272, 'loss/train': 1.4935764074325562} 08/30/2021 22:28:56 - INFO - __main__ - Step 51274: {'lr': 0.00037527717586320457, 'samples': 9844608, 'steps': 51273, 'loss/train': 1.0626734495162964} 08/30/2021 22:28:56 - INFO - __main__ - Step 51275: {'lr': 0.00037527258346149153, 'samples': 9844800, 'steps': 51274, 'loss/train': 1.2351486682891846} 08/30/2021 22:28:57 - INFO - __main__ - Step 51276: {'lr': 0.0003752679910033325, 'samples': 9844992, 'steps': 51275, 'loss/train': 1.9000072479248047} 08/30/2021 22:28:59 - INFO - __main__ - Step 51277: {'lr': 0.00037526339848872956, 'samples': 9845184, 'steps': 51276, 'loss/train': 1.7238506078720093} 08/30/2021 22:28:59 - INFO - __main__ - Step 51278: {'lr': 0.000375258805917685, 'samples': 9845376, 'steps': 51277, 'loss/train': 1.5105801820755005} 08/30/2021 22:29:00 - INFO - __main__ - Step 51279: {'lr': 0.0003752542132902007, 'samples': 9845568, 'steps': 51278, 'loss/train': 1.4521934986114502} 08/30/2021 22:29:00 - INFO - __main__ - Step 51280: {'lr': 0.00037524962060627885, 'samples': 9845760, 'steps': 51279, 'loss/train': 1.3687751293182373} 08/30/2021 22:29:00 - INFO - __main__ - Step 51281: {'lr': 0.0003752450278659214, 'samples': 9845952, 'steps': 51280, 'loss/train': 1.4386978149414062} 08/30/2021 22:29:02 - INFO - __main__ - Step 51282: {'lr': 0.00037524043506913045, 'samples': 9846144, 'steps': 51281, 'loss/train': 1.0775789022445679} 08/30/2021 22:29:02 - INFO - __main__ - Step 51283: {'lr': 0.0003752358422159081, 'samples': 9846336, 'steps': 51282, 'loss/train': 1.1652660369873047} 08/30/2021 22:29:03 - INFO - __main__ - Step 51284: {'lr': 0.0003752312493062564, 'samples': 9846528, 'steps': 51283, 'loss/train': 1.4689677953720093} 08/30/2021 22:29:03 - INFO - __main__ - Step 51285: {'lr': 0.0003752266563401775, 'samples': 9846720, 'steps': 51284, 'loss/train': 0.9760374426841736} 08/30/2021 22:29:04 - INFO - __main__ - Step 51286: {'lr': 0.00037522206331767335, 'samples': 9846912, 'steps': 51285, 'loss/train': 0.7064561247825623} 08/30/2021 22:29:05 - INFO - __main__ - Step 51287: {'lr': 0.00037521747023874606, 'samples': 9847104, 'steps': 51286, 'loss/train': 2.410125970840454} 08/30/2021 22:29:05 - INFO - __main__ - Step 51288: {'lr': 0.0003752128771033978, 'samples': 9847296, 'steps': 51287, 'loss/train': 1.2347930669784546} 08/30/2021 22:29:06 - INFO - __main__ - Step 51289: {'lr': 0.0003752082839116304, 'samples': 9847488, 'steps': 51288, 'loss/train': 0.9653266072273254} 08/30/2021 22:29:06 - INFO - __main__ - Step 51290: {'lr': 0.0003752036906634462, 'samples': 9847680, 'steps': 51289, 'loss/train': 1.2839741706848145} 08/30/2021 22:29:06 - INFO - __main__ - Step 51291: {'lr': 0.0003751990973588471, 'samples': 9847872, 'steps': 51290, 'loss/train': 1.5282231569290161} 08/30/2021 22:29:08 - INFO - __main__ - Step 51292: {'lr': 0.0003751945039978353, 'samples': 9848064, 'steps': 51291, 'loss/train': 1.4868710041046143} 08/30/2021 22:29:08 - INFO - __main__ - Step 51293: {'lr': 0.00037518991058041267, 'samples': 9848256, 'steps': 51292, 'loss/train': 1.5949047803878784} 08/30/2021 22:29:09 - INFO - __main__ - Step 51294: {'lr': 0.00037518531710658144, 'samples': 9848448, 'steps': 51293, 'loss/train': 1.6631672382354736} 08/30/2021 22:29:09 - INFO - __main__ - Step 51295: {'lr': 0.0003751807235763437, 'samples': 9848640, 'steps': 51294, 'loss/train': 1.4661540985107422} 08/30/2021 22:29:09 - INFO - __main__ - Step 51296: {'lr': 0.00037517612998970136, 'samples': 9848832, 'steps': 51295, 'loss/train': 1.4969547986984253} 08/30/2021 22:29:11 - INFO - __main__ - Step 51297: {'lr': 0.00037517153634665664, 'samples': 9849024, 'steps': 51296, 'loss/train': 1.6464662551879883} 08/30/2021 22:29:11 - INFO - __main__ - Step 51298: {'lr': 0.0003751669426472115, 'samples': 9849216, 'steps': 51297, 'loss/train': 0.9657031297683716} 08/30/2021 22:29:12 - INFO - __main__ - Step 51299: {'lr': 0.0003751623488913681, 'samples': 9849408, 'steps': 51298, 'loss/train': 1.131405234336853} 08/30/2021 22:29:12 - INFO - __main__ - Step 51300: {'lr': 0.00037515775507912855, 'samples': 9849600, 'steps': 51299, 'loss/train': 1.3076097965240479} 08/30/2021 22:29:12 - INFO - __main__ - Step 51301: {'lr': 0.0003751531612104948, 'samples': 9849792, 'steps': 51300, 'loss/train': 0.25848427414894104} 08/30/2021 22:29:14 - INFO - __main__ - Step 51302: {'lr': 0.00037514856728546893, 'samples': 9849984, 'steps': 51301, 'loss/train': 1.4348535537719727} 08/30/2021 22:29:14 - INFO - __main__ - Step 51303: {'lr': 0.00037514397330405306, 'samples': 9850176, 'steps': 51302, 'loss/train': 1.7946664094924927} 08/30/2021 22:29:15 - INFO - __main__ - Step 51304: {'lr': 0.00037513937926624924, 'samples': 9850368, 'steps': 51303, 'loss/train': 1.256117820739746} 08/30/2021 22:29:15 - INFO - __main__ - Step 51305: {'lr': 0.0003751347851720596, 'samples': 9850560, 'steps': 51304, 'loss/train': 1.2072410583496094} 08/30/2021 22:29:15 - INFO - __main__ - Step 51306: {'lr': 0.00037513019102148606, 'samples': 9850752, 'steps': 51305, 'loss/train': 0.5593969821929932} 08/30/2021 22:29:17 - INFO - __main__ - Step 51307: {'lr': 0.0003751255968145309, 'samples': 9850944, 'steps': 51306, 'loss/train': 1.917822241783142} 08/30/2021 22:29:18 - INFO - __main__ - Step 51308: {'lr': 0.00037512100255119603, 'samples': 9851136, 'steps': 51307, 'loss/train': 0.7802227139472961} 08/30/2021 22:29:18 - INFO - __main__ - Step 51309: {'lr': 0.0003751164082314835, 'samples': 9851328, 'steps': 51308, 'loss/train': 0.05756458640098572} 08/30/2021 22:29:18 - INFO - __main__ - Step 51310: {'lr': 0.00037511181385539553, 'samples': 9851520, 'steps': 51309, 'loss/train': 0.9711182117462158} 08/30/2021 22:29:19 - INFO - __main__ - Step 51311: {'lr': 0.00037510721942293415, 'samples': 9851712, 'steps': 51310, 'loss/train': 1.6188971996307373} 08/30/2021 22:29:19 - INFO - __main__ - Step 51312: {'lr': 0.0003751026249341013, 'samples': 9851904, 'steps': 51311, 'loss/train': 1.1854959726333618} 08/30/2021 22:29:21 - INFO - __main__ - Step 51313: {'lr': 0.0003750980303888991, 'samples': 9852096, 'steps': 51312, 'loss/train': 1.1292489767074585} 08/30/2021 22:29:21 - INFO - __main__ - Step 51314: {'lr': 0.0003750934357873298, 'samples': 9852288, 'steps': 51313, 'loss/train': 0.8393359780311584} 08/30/2021 22:29:22 - INFO - __main__ - Step 51315: {'lr': 0.00037508884112939523, 'samples': 9852480, 'steps': 51314, 'loss/train': 1.280697226524353} 08/30/2021 22:29:22 - INFO - __main__ - Step 51316: {'lr': 0.0003750842464150975, 'samples': 9852672, 'steps': 51315, 'loss/train': 1.4953235387802124} 08/30/2021 22:29:22 - INFO - __main__ - Step 51317: {'lr': 0.0003750796516444389, 'samples': 9852864, 'steps': 51316, 'loss/train': 1.2516376972198486} 08/30/2021 22:29:24 - INFO - __main__ - Step 51318: {'lr': 0.0003750750568174212, 'samples': 9853056, 'steps': 51317, 'loss/train': 1.1759735345840454} 08/30/2021 22:29:24 - INFO - __main__ - Step 51319: {'lr': 0.00037507046193404665, 'samples': 9853248, 'steps': 51318, 'loss/train': 1.674957275390625} 08/30/2021 22:29:25 - INFO - __main__ - Step 51320: {'lr': 0.0003750658669943173, 'samples': 9853440, 'steps': 51319, 'loss/train': 1.8563592433929443} 08/30/2021 22:29:25 - INFO - __main__ - Step 51321: {'lr': 0.00037506127199823523, 'samples': 9853632, 'steps': 51320, 'loss/train': 0.7560064792633057} 08/30/2021 22:29:25 - INFO - __main__ - Step 51322: {'lr': 0.00037505667694580244, 'samples': 9853824, 'steps': 51321, 'loss/train': 1.113816261291504} 08/30/2021 22:29:27 - INFO - __main__ - Step 51323: {'lr': 0.000375052081837021, 'samples': 9854016, 'steps': 51322, 'loss/train': 0.9332059621810913} 08/30/2021 22:29:27 - INFO - __main__ - Step 51324: {'lr': 0.0003750474866718931, 'samples': 9854208, 'steps': 51323, 'loss/train': 1.5627442598342896} 08/30/2021 22:29:28 - INFO - __main__ - Step 51325: {'lr': 0.0003750428914504207, 'samples': 9854400, 'steps': 51324, 'loss/train': 0.509478747844696} 08/30/2021 22:29:28 - INFO - __main__ - Step 51326: {'lr': 0.0003750382961726059, 'samples': 9854592, 'steps': 51325, 'loss/train': 1.2357443571090698} 08/30/2021 22:29:28 - INFO - __main__ - Step 51327: {'lr': 0.0003750337008384508, 'samples': 9854784, 'steps': 51326, 'loss/train': 1.1114829778671265} 08/30/2021 22:29:30 - INFO - __main__ - Step 51328: {'lr': 0.0003750291054479574, 'samples': 9854976, 'steps': 51327, 'loss/train': 1.0996270179748535} 08/30/2021 22:29:31 - INFO - __main__ - Step 51329: {'lr': 0.0003750245100011278, 'samples': 9855168, 'steps': 51328, 'loss/train': 1.6564158201217651} 08/30/2021 22:29:31 - INFO - __main__ - Step 51330: {'lr': 0.00037501991449796415, 'samples': 9855360, 'steps': 51329, 'loss/train': 2.057136297225952} 08/30/2021 22:29:32 - INFO - __main__ - Step 51331: {'lr': 0.0003750153189384684, 'samples': 9855552, 'steps': 51330, 'loss/train': 1.3453997373580933} 08/30/2021 22:29:32 - INFO - __main__ - Step 51332: {'lr': 0.00037501072332264267, 'samples': 9855744, 'steps': 51331, 'loss/train': 2.3266890048980713} 08/30/2021 22:29:33 - INFO - __main__ - Step 51333: {'lr': 0.0003750061276504891, 'samples': 9855936, 'steps': 51332, 'loss/train': 1.254947304725647} 08/30/2021 22:29:34 - INFO - __main__ - Step 51334: {'lr': 0.0003750015319220097, 'samples': 9856128, 'steps': 51333, 'loss/train': 1.49747633934021} 08/30/2021 22:29:34 - INFO - __main__ - Step 51335: {'lr': 0.0003749969361372065, 'samples': 9856320, 'steps': 51334, 'loss/train': 1.5871186256408691} 08/30/2021 22:29:35 - INFO - __main__ - Step 51336: {'lr': 0.0003749923402960816, 'samples': 9856512, 'steps': 51335, 'loss/train': 1.6737924814224243} 08/30/2021 22:29:35 - INFO - __main__ - Step 51337: {'lr': 0.00037498774439863704, 'samples': 9856704, 'steps': 51336, 'loss/train': 1.835592269897461} 08/30/2021 22:29:35 - INFO - __main__ - Step 51338: {'lr': 0.000374983148444875, 'samples': 9856896, 'steps': 51337, 'loss/train': 1.2666033506393433} 08/30/2021 22:29:37 - INFO - __main__ - Step 51339: {'lr': 0.00037497855243479744, 'samples': 9857088, 'steps': 51338, 'loss/train': 1.1092997789382935} 08/30/2021 22:29:37 - INFO - __main__ - Step 51340: {'lr': 0.0003749739563684065, 'samples': 9857280, 'steps': 51339, 'loss/train': 1.1301703453063965} 08/30/2021 22:29:38 - INFO - __main__ - Step 51341: {'lr': 0.00037496936024570426, 'samples': 9857472, 'steps': 51340, 'loss/train': 1.421207308769226} 08/30/2021 22:29:38 - INFO - __main__ - Step 51342: {'lr': 0.0003749647640666927, 'samples': 9857664, 'steps': 51341, 'loss/train': 1.42851984500885} 08/30/2021 22:29:38 - INFO - __main__ - Step 51343: {'lr': 0.000374960167831374, 'samples': 9857856, 'steps': 51342, 'loss/train': 1.6294177770614624} 08/30/2021 22:29:40 - INFO - __main__ - Step 51344: {'lr': 0.00037495557153975016, 'samples': 9858048, 'steps': 51343, 'loss/train': 1.4724314212799072} 08/30/2021 22:29:40 - INFO - __main__ - Step 51345: {'lr': 0.0003749509751918232, 'samples': 9858240, 'steps': 51344, 'loss/train': 1.4510048627853394} 08/30/2021 22:29:41 - INFO - __main__ - Step 51346: {'lr': 0.0003749463787875953, 'samples': 9858432, 'steps': 51345, 'loss/train': 1.2277531623840332} 08/30/2021 22:29:41 - INFO - __main__ - Step 51347: {'lr': 0.00037494178232706847, 'samples': 9858624, 'steps': 51346, 'loss/train': 1.0561978816986084} 08/30/2021 22:29:42 - INFO - __main__ - Step 51348: {'lr': 0.00037493718581024484, 'samples': 9858816, 'steps': 51347, 'loss/train': 1.7972724437713623} 08/30/2021 22:29:43 - INFO - __main__ - Step 51349: {'lr': 0.0003749325892371264, 'samples': 9859008, 'steps': 51348, 'loss/train': 1.624428391456604} 08/30/2021 22:29:44 - INFO - __main__ - Step 51350: {'lr': 0.0003749279926077153, 'samples': 9859200, 'steps': 51349, 'loss/train': 0.8268048763275146} 08/30/2021 22:29:44 - INFO - __main__ - Step 51351: {'lr': 0.0003749233959220136, 'samples': 9859392, 'steps': 51350, 'loss/train': 0.9024322032928467} 08/30/2021 22:29:44 - INFO - __main__ - Step 51352: {'lr': 0.00037491879918002323, 'samples': 9859584, 'steps': 51351, 'loss/train': 0.89680415391922} 08/30/2021 22:29:45 - INFO - __main__ - Step 51353: {'lr': 0.0003749142023817465, 'samples': 9859776, 'steps': 51352, 'loss/train': 1.2557790279388428} 08/30/2021 22:29:45 - INFO - __main__ - Step 51354: {'lr': 0.00037490960552718534, 'samples': 9859968, 'steps': 51353, 'loss/train': 5.8465094566345215} 08/30/2021 22:29:47 - INFO - __main__ - Step 51355: {'lr': 0.00037490500861634183, 'samples': 9860160, 'steps': 51354, 'loss/train': 1.375968337059021} 08/30/2021 22:29:47 - INFO - __main__ - Step 51356: {'lr': 0.00037490041164921803, 'samples': 9860352, 'steps': 51355, 'loss/train': 1.1428078413009644} 08/30/2021 22:29:48 - INFO - __main__ - Step 51357: {'lr': 0.000374895814625816, 'samples': 9860544, 'steps': 51356, 'loss/train': 0.0932147428393364} 08/30/2021 22:29:48 - INFO - __main__ - Step 51358: {'lr': 0.00037489121754613787, 'samples': 9860736, 'steps': 51357, 'loss/train': 1.2024534940719604} 08/30/2021 22:29:48 - INFO - __main__ - Step 51359: {'lr': 0.00037488662041018574, 'samples': 9860928, 'steps': 51358, 'loss/train': 1.1072344779968262} 08/30/2021 22:29:50 - INFO - __main__ - Step 51360: {'lr': 0.00037488202321796156, 'samples': 9861120, 'steps': 51359, 'loss/train': 1.6473231315612793} 08/30/2021 22:29:50 - INFO - __main__ - Step 51361: {'lr': 0.0003748774259694675, 'samples': 9861312, 'steps': 51360, 'loss/train': 1.4028126001358032} 08/30/2021 22:29:50 - INFO - __main__ - Step 51362: {'lr': 0.00037487282866470565, 'samples': 9861504, 'steps': 51361, 'loss/train': 0.8303579092025757} 08/30/2021 22:29:51 - INFO - __main__ - Step 51363: {'lr': 0.00037486823130367786, 'samples': 9861696, 'steps': 51362, 'loss/train': 1.4941444396972656} 08/30/2021 22:29:51 - INFO - __main__ - Step 51364: {'lr': 0.0003748636338863865, 'samples': 9861888, 'steps': 51363, 'loss/train': 1.4180796146392822} 08/30/2021 22:29:53 - INFO - __main__ - Step 51365: {'lr': 0.0003748590364128335, 'samples': 9862080, 'steps': 51364, 'loss/train': 0.11163672059774399} 08/30/2021 22:29:54 - INFO - __main__ - Step 51366: {'lr': 0.00037485443888302095, 'samples': 9862272, 'steps': 51365, 'loss/train': 1.5435107946395874} 08/30/2021 22:29:54 - INFO - __main__ - Step 51367: {'lr': 0.00037484984129695096, 'samples': 9862464, 'steps': 51366, 'loss/train': 1.807789921760559} 08/30/2021 22:29:54 - INFO - __main__ - Step 51368: {'lr': 0.00037484524365462545, 'samples': 9862656, 'steps': 51367, 'loss/train': 0.9509342312812805} 08/30/2021 22:29:55 - INFO - __main__ - Step 51369: {'lr': 0.0003748406459560466, 'samples': 9862848, 'steps': 51368, 'loss/train': 1.2699956893920898} 08/30/2021 22:29:55 - INFO - __main__ - Step 51370: {'lr': 0.0003748360482012166, 'samples': 9863040, 'steps': 51369, 'loss/train': 0.11819048970937729} 08/30/2021 22:29:56 - INFO - __main__ - Step 51371: {'lr': 0.00037483145039013735, 'samples': 9863232, 'steps': 51370, 'loss/train': 1.3368152379989624} 08/30/2021 22:29:57 - INFO - __main__ - Step 51372: {'lr': 0.0003748268525228109, 'samples': 9863424, 'steps': 51371, 'loss/train': 1.1307731866836548} 08/30/2021 22:29:57 - INFO - __main__ - Step 51373: {'lr': 0.00037482225459923945, 'samples': 9863616, 'steps': 51372, 'loss/train': 1.1255041360855103} 08/30/2021 22:29:58 - INFO - __main__ - Step 51374: {'lr': 0.00037481765661942506, 'samples': 9863808, 'steps': 51373, 'loss/train': 0.43376192450523376} 08/30/2021 22:29:58 - INFO - __main__ - Step 51375: {'lr': 0.0003748130585833697, 'samples': 9864000, 'steps': 51374, 'loss/train': 0.8339983820915222} 08/30/2021 22:29:59 - INFO - __main__ - Step 51376: {'lr': 0.0003748084604910755, 'samples': 9864192, 'steps': 51375, 'loss/train': 1.5910978317260742} 08/30/2021 22:30:00 - INFO - __main__ - Step 51377: {'lr': 0.0003748038623425446, 'samples': 9864384, 'steps': 51376, 'loss/train': 1.4316824674606323} 08/30/2021 22:30:00 - INFO - __main__ - Step 51378: {'lr': 0.00037479926413777896, 'samples': 9864576, 'steps': 51377, 'loss/train': 1.5871822834014893} 08/30/2021 22:30:01 - INFO - __main__ - Step 51379: {'lr': 0.0003747946658767807, 'samples': 9864768, 'steps': 51378, 'loss/train': 1.4499775171279907} 08/30/2021 22:30:01 - INFO - __main__ - Step 51380: {'lr': 0.0003747900675595519, 'samples': 9864960, 'steps': 51379, 'loss/train': 1.1597874164581299} 08/30/2021 22:30:03 - INFO - __main__ - Step 51381: {'lr': 0.00037478546918609464, 'samples': 9865152, 'steps': 51380, 'loss/train': 1.4608900547027588} 08/30/2021 22:30:03 - INFO - __main__ - Step 51382: {'lr': 0.00037478087075641095, 'samples': 9865344, 'steps': 51381, 'loss/train': 1.5292834043502808} 08/30/2021 22:30:03 - INFO - __main__ - Step 51383: {'lr': 0.00037477627227050286, 'samples': 9865536, 'steps': 51382, 'loss/train': 2.05181884765625} 08/30/2021 22:30:04 - INFO - __main__ - Step 51384: {'lr': 0.0003747716737283726, 'samples': 9865728, 'steps': 51383, 'loss/train': 0.7129995226860046} 08/30/2021 22:30:04 - INFO - __main__ - Step 51385: {'lr': 0.00037476707513002213, 'samples': 9865920, 'steps': 51384, 'loss/train': 1.353680968284607} 08/30/2021 22:30:06 - INFO - __main__ - Step 51386: {'lr': 0.0003747624764754535, 'samples': 9866112, 'steps': 51385, 'loss/train': 0.06397978961467743} 08/30/2021 22:30:07 - INFO - __main__ - Step 51387: {'lr': 0.00037475787776466887, 'samples': 9866304, 'steps': 51386, 'loss/train': 0.8257332444190979} 08/30/2021 22:30:07 - INFO - __main__ - Step 51388: {'lr': 0.00037475327899767026, 'samples': 9866496, 'steps': 51387, 'loss/train': 1.0156002044677734} 08/30/2021 22:30:07 - INFO - __main__ - Step 51389: {'lr': 0.0003747486801744597, 'samples': 9866688, 'steps': 51388, 'loss/train': 1.4870741367340088} 08/30/2021 22:30:08 - INFO - __main__ - Step 51390: {'lr': 0.0003747440812950393, 'samples': 9866880, 'steps': 51389, 'loss/train': 1.0778515338897705} 08/30/2021 22:30:10 - INFO - __main__ - Step 51391: {'lr': 0.0003747394823594112, 'samples': 9867072, 'steps': 51390, 'loss/train': 1.197513461112976} 08/30/2021 22:30:11 - INFO - __main__ - Step 51392: {'lr': 0.00037473488336757743, 'samples': 9867264, 'steps': 51391, 'loss/train': 1.507083535194397} 08/30/2021 22:30:11 - INFO - __main__ - Step 51393: {'lr': 0.00037473028431954006, 'samples': 9867456, 'steps': 51392, 'loss/train': 0.9903676509857178} 08/30/2021 22:30:11 - INFO - __main__ - Step 51394: {'lr': 0.00037472568521530107, 'samples': 9867648, 'steps': 51393, 'loss/train': 1.18123197555542} 08/30/2021 22:30:12 - INFO - __main__ - Step 51395: {'lr': 0.0003747210860548627, 'samples': 9867840, 'steps': 51394, 'loss/train': 1.7999238967895508} 08/30/2021 22:30:12 - INFO - __main__ - Step 51396: {'lr': 0.00037471648683822683, 'samples': 9868032, 'steps': 51395, 'loss/train': 1.7751226425170898} 08/30/2021 22:30:12 - INFO - __main__ - Step 51397: {'lr': 0.0003747118875653957, 'samples': 9868224, 'steps': 51396, 'loss/train': 1.803802728652954} 08/30/2021 22:30:13 - INFO - __main__ - Step 51398: {'lr': 0.00037470728823637135, 'samples': 9868416, 'steps': 51397, 'loss/train': 0.15961065888404846} 08/30/2021 22:30:14 - INFO - __main__ - Step 51399: {'lr': 0.0003747026888511558, 'samples': 9868608, 'steps': 51398, 'loss/train': 1.3193204402923584} 08/30/2021 22:30:15 - INFO - __main__ - Step 51400: {'lr': 0.00037469808940975106, 'samples': 9868800, 'steps': 51399, 'loss/train': 1.1885268688201904} 08/30/2021 22:30:15 - INFO - __main__ - Step 51401: {'lr': 0.00037469348991215934, 'samples': 9868992, 'steps': 51400, 'loss/train': 1.084804892539978} 08/30/2021 22:30:15 - INFO - __main__ - Step 51402: {'lr': 0.00037468889035838264, 'samples': 9869184, 'steps': 51401, 'loss/train': 1.316615343093872} 08/30/2021 22:30:16 - INFO - __main__ - Step 51403: {'lr': 0.0003746842907484231, 'samples': 9869376, 'steps': 51402, 'loss/train': 1.0453486442565918} 08/30/2021 22:30:17 - INFO - __main__ - Step 51404: {'lr': 0.0003746796910822827, 'samples': 9869568, 'steps': 51403, 'loss/train': 0.6009833812713623} 08/30/2021 22:30:18 - INFO - __main__ - Step 51405: {'lr': 0.0003746750913599636, 'samples': 9869760, 'steps': 51404, 'loss/train': 1.174621343612671} 08/30/2021 22:30:18 - INFO - __main__ - Step 51406: {'lr': 0.00037467049158146777, 'samples': 9869952, 'steps': 51405, 'loss/train': 1.8217114210128784} 08/30/2021 22:30:18 - INFO - __main__ - Step 51407: {'lr': 0.00037466589174679733, 'samples': 9870144, 'steps': 51406, 'loss/train': 1.3290667533874512} 08/30/2021 22:30:19 - INFO - __main__ - Step 51408: {'lr': 0.0003746612918559544, 'samples': 9870336, 'steps': 51407, 'loss/train': 1.3627574443817139} 08/30/2021 22:30:20 - INFO - __main__ - Step 51409: {'lr': 0.00037465669190894107, 'samples': 9870528, 'steps': 51408, 'loss/train': 1.7998628616333008} 08/30/2021 22:30:21 - INFO - __main__ - Step 51410: {'lr': 0.00037465209190575927, 'samples': 9870720, 'steps': 51409, 'loss/train': 0.9656294584274292} 08/30/2021 22:30:21 - INFO - __main__ - Step 51411: {'lr': 0.00037464749184641123, 'samples': 9870912, 'steps': 51410, 'loss/train': 1.280968427658081} 08/30/2021 22:30:22 - INFO - __main__ - Step 51412: {'lr': 0.0003746428917308989, 'samples': 9871104, 'steps': 51411, 'loss/train': 1.2487115859985352} 08/30/2021 22:30:22 - INFO - __main__ - Step 51413: {'lr': 0.0003746382915592244, 'samples': 9871296, 'steps': 51412, 'loss/train': 1.6149616241455078} 08/30/2021 22:30:22 - INFO - __main__ - Step 51414: {'lr': 0.0003746336913313898, 'samples': 9871488, 'steps': 51413, 'loss/train': 1.5198841094970703} 08/30/2021 22:30:24 - INFO - __main__ - Step 51415: {'lr': 0.0003746290910473973, 'samples': 9871680, 'steps': 51414, 'loss/train': 4.683076858520508} 08/30/2021 22:30:25 - INFO - __main__ - Step 51416: {'lr': 0.00037462449070724876, 'samples': 9871872, 'steps': 51415, 'loss/train': 1.9120951890945435} 08/30/2021 22:30:25 - INFO - __main__ - Step 51417: {'lr': 0.00037461989031094636, 'samples': 9872064, 'steps': 51416, 'loss/train': 1.7031983137130737} 08/30/2021 22:30:25 - INFO - __main__ - Step 51418: {'lr': 0.00037461528985849215, 'samples': 9872256, 'steps': 51417, 'loss/train': 0.8126934766769409} 08/30/2021 22:30:26 - INFO - __main__ - Step 51419: {'lr': 0.0003746106893498882, 'samples': 9872448, 'steps': 51418, 'loss/train': 1.5206992626190186} 08/30/2021 22:30:27 - INFO - __main__ - Step 51420: {'lr': 0.00037460608878513656, 'samples': 9872640, 'steps': 51419, 'loss/train': 1.5701783895492554} 08/30/2021 22:30:28 - INFO - __main__ - Step 51421: {'lr': 0.00037460148816423946, 'samples': 9872832, 'steps': 51420, 'loss/train': 1.339674472808838} 08/30/2021 22:30:28 - INFO - __main__ - Step 51422: {'lr': 0.0003745968874871988, 'samples': 9873024, 'steps': 51421, 'loss/train': 1.094204068183899} 08/30/2021 22:30:28 - INFO - __main__ - Step 51423: {'lr': 0.00037459228675401667, 'samples': 9873216, 'steps': 51422, 'loss/train': 0.7770503759384155} 08/30/2021 22:30:29 - INFO - __main__ - Step 51424: {'lr': 0.00037458768596469516, 'samples': 9873408, 'steps': 51423, 'loss/train': 1.3026182651519775} 08/30/2021 22:30:31 - INFO - __main__ - Step 51425: {'lr': 0.0003745830851192364, 'samples': 9873600, 'steps': 51424, 'loss/train': 0.05961012840270996} 08/30/2021 22:30:31 - INFO - __main__ - Step 51426: {'lr': 0.00037457848421764247, 'samples': 9873792, 'steps': 51425, 'loss/train': 1.2662992477416992} 08/30/2021 22:30:32 - INFO - __main__ - Step 51427: {'lr': 0.0003745738832599153, 'samples': 9873984, 'steps': 51426, 'loss/train': 0.8151814937591553} 08/30/2021 22:30:32 - INFO - __main__ - Step 51428: {'lr': 0.0003745692822460572, 'samples': 9874176, 'steps': 51427, 'loss/train': 1.4519838094711304} 08/30/2021 22:30:32 - INFO - __main__ - Step 51429: {'lr': 0.00037456468117607, 'samples': 9874368, 'steps': 51428, 'loss/train': 1.6214792728424072} 08/30/2021 22:30:33 - INFO - __main__ - Step 51430: {'lr': 0.0003745600800499559, 'samples': 9874560, 'steps': 51429, 'loss/train': 1.1946426630020142} 08/30/2021 22:30:34 - INFO - __main__ - Step 51431: {'lr': 0.0003745554788677169, 'samples': 9874752, 'steps': 51430, 'loss/train': 0.8256950378417969} 08/30/2021 22:30:35 - INFO - __main__ - Step 51432: {'lr': 0.0003745508776293551, 'samples': 9874944, 'steps': 51431, 'loss/train': 1.9110429286956787} 08/30/2021 22:30:35 - INFO - __main__ - Step 51433: {'lr': 0.0003745462763348727, 'samples': 9875136, 'steps': 51432, 'loss/train': 1.3494125604629517} 08/30/2021 22:30:35 - INFO - __main__ - Step 51434: {'lr': 0.00037454167498427165, 'samples': 9875328, 'steps': 51433, 'loss/train': 1.4760828018188477} 08/30/2021 22:30:36 - INFO - __main__ - Step 51435: {'lr': 0.0003745370735775541, 'samples': 9875520, 'steps': 51434, 'loss/train': 0.4241074323654175} 08/30/2021 22:30:36 - INFO - __main__ - Step 51436: {'lr': 0.00037453247211472195, 'samples': 9875712, 'steps': 51435, 'loss/train': 1.6919045448303223} 08/30/2021 22:30:38 - INFO - __main__ - Step 51437: {'lr': 0.0003745278705957774, 'samples': 9875904, 'steps': 51436, 'loss/train': 1.81698477268219} 08/30/2021 22:30:39 - INFO - __main__ - Step 51438: {'lr': 0.00037452326902072256, 'samples': 9876096, 'steps': 51437, 'loss/train': 1.704921841621399} 08/30/2021 22:30:39 - INFO - __main__ - Step 51439: {'lr': 0.0003745186673895594, 'samples': 9876288, 'steps': 51438, 'loss/train': 1.6699382066726685} 08/30/2021 22:30:39 - INFO - __main__ - Step 51440: {'lr': 0.0003745140657022901, 'samples': 9876480, 'steps': 51439, 'loss/train': 0.807083010673523} 08/30/2021 22:30:40 - INFO - __main__ - Step 51441: {'lr': 0.0003745094639589167, 'samples': 9876672, 'steps': 51440, 'loss/train': 1.2464178800582886} 08/30/2021 22:30:41 - INFO - __main__ - Step 51442: {'lr': 0.00037450486215944123, 'samples': 9876864, 'steps': 51441, 'loss/train': 0.7804450392723083} 08/30/2021 22:30:42 - INFO - __main__ - Step 51443: {'lr': 0.0003745002603038658, 'samples': 9877056, 'steps': 51442, 'loss/train': 1.2219847440719604} 08/30/2021 22:30:42 - INFO - __main__ - Step 51444: {'lr': 0.00037449565839219246, 'samples': 9877248, 'steps': 51443, 'loss/train': 1.6360878944396973} 08/30/2021 22:30:43 - INFO - __main__ - Step 51445: {'lr': 0.0003744910564244233, 'samples': 9877440, 'steps': 51444, 'loss/train': 0.06180236488580704} 08/30/2021 22:30:43 - INFO - __main__ - Step 51446: {'lr': 0.0003744864544005604, 'samples': 9877632, 'steps': 51445, 'loss/train': 2.03151273727417} 08/30/2021 22:30:44 - INFO - __main__ - Step 51447: {'lr': 0.0003744818523206058, 'samples': 9877824, 'steps': 51446, 'loss/train': 1.0139405727386475} 08/30/2021 22:30:45 - INFO - __main__ - Step 51448: {'lr': 0.00037447725018456167, 'samples': 9878016, 'steps': 51447, 'loss/train': 0.9331154227256775} 08/30/2021 22:30:45 - INFO - __main__ - Step 51449: {'lr': 0.00037447264799243, 'samples': 9878208, 'steps': 51448, 'loss/train': 1.5400375127792358} 08/30/2021 22:30:46 - INFO - __main__ - Step 51450: {'lr': 0.00037446804574421276, 'samples': 9878400, 'steps': 51449, 'loss/train': 1.3505369424819946} 08/30/2021 22:30:46 - INFO - __main__ - Step 51451: {'lr': 0.00037446344343991224, 'samples': 9878592, 'steps': 51450, 'loss/train': 1.5118086338043213} 08/30/2021 22:30:47 - INFO - __main__ - Step 51452: {'lr': 0.0003744588410795304, 'samples': 9878784, 'steps': 51451, 'loss/train': 0.2807227373123169} 08/30/2021 22:30:48 - INFO - __main__ - Step 51453: {'lr': 0.00037445423866306926, 'samples': 9878976, 'steps': 51452, 'loss/train': 1.968727707862854} 08/30/2021 22:30:48 - INFO - __main__ - Step 51454: {'lr': 0.00037444963619053103, 'samples': 9879168, 'steps': 51453, 'loss/train': 1.283005952835083} 08/30/2021 22:30:49 - INFO - __main__ - Step 51455: {'lr': 0.00037444503366191776, 'samples': 9879360, 'steps': 51454, 'loss/train': 1.7621018886566162} 08/30/2021 22:30:49 - INFO - __main__ - Step 51456: {'lr': 0.00037444043107723134, 'samples': 9879552, 'steps': 51455, 'loss/train': 1.3220256567001343} 08/30/2021 22:30:50 - INFO - __main__ - Step 51457: {'lr': 0.0003744358284364741, 'samples': 9879744, 'steps': 51456, 'loss/train': 0.8543890714645386} 08/30/2021 22:30:51 - INFO - __main__ - Step 51458: {'lr': 0.00037443122573964794, 'samples': 9879936, 'steps': 51457, 'loss/train': 1.2022067308425903} 08/30/2021 22:30:51 - INFO - __main__ - Step 51459: {'lr': 0.000374426622986755, 'samples': 9880128, 'steps': 51458, 'loss/train': 1.0412627458572388} 08/30/2021 22:30:51 - INFO - __main__ - Step 51460: {'lr': 0.0003744220201777974, 'samples': 9880320, 'steps': 51459, 'loss/train': 1.9175645112991333} 08/30/2021 22:30:52 - INFO - __main__ - Step 51461: {'lr': 0.0003744174173127771, 'samples': 9880512, 'steps': 51460, 'loss/train': 1.3595013618469238} 08/30/2021 22:30:53 - INFO - __main__ - Step 51462: {'lr': 0.00037441281439169624, 'samples': 9880704, 'steps': 51461, 'loss/train': 1.637851357460022} 08/30/2021 22:30:54 - INFO - __main__ - Step 51463: {'lr': 0.0003744082114145568, 'samples': 9880896, 'steps': 51462, 'loss/train': 1.3366448879241943} 08/30/2021 22:30:54 - INFO - __main__ - Step 51464: {'lr': 0.00037440360838136106, 'samples': 9881088, 'steps': 51463, 'loss/train': 1.0917524099349976} 08/30/2021 22:30:55 - INFO - __main__ - Step 51465: {'lr': 0.0003743990052921109, 'samples': 9881280, 'steps': 51464, 'loss/train': 1.0069018602371216} 08/30/2021 22:30:55 - INFO - __main__ - Step 51466: {'lr': 0.00037439440214680854, 'samples': 9881472, 'steps': 51465, 'loss/train': 0.7022767663002014} 08/30/2021 22:30:57 - INFO - __main__ - Step 51467: {'lr': 0.00037438979894545595, 'samples': 9881664, 'steps': 51466, 'loss/train': 1.1021631956100464} 08/30/2021 22:30:58 - INFO - __main__ - Step 51468: {'lr': 0.0003743851956880553, 'samples': 9881856, 'steps': 51467, 'loss/train': 1.211194396018982} 08/30/2021 22:30:58 - INFO - __main__ - Step 51469: {'lr': 0.00037438059237460846, 'samples': 9882048, 'steps': 51468, 'loss/train': 1.7911427021026611} 08/30/2021 22:30:58 - INFO - __main__ - Step 51470: {'lr': 0.0003743759890051177, 'samples': 9882240, 'steps': 51469, 'loss/train': 1.8580384254455566} 08/30/2021 22:30:59 - INFO - __main__ - Step 51471: {'lr': 0.00037437138557958505, 'samples': 9882432, 'steps': 51470, 'loss/train': 1.078689694404602} 08/30/2021 22:30:59 - INFO - __main__ - Step 51472: {'lr': 0.0003743667820980126, 'samples': 9882624, 'steps': 51471, 'loss/train': 0.030787423253059387} 08/30/2021 22:30:59 - INFO - __main__ - Step 51473: {'lr': 0.0003743621785604024, 'samples': 9882816, 'steps': 51472, 'loss/train': 2.127434253692627} 08/30/2021 22:31:01 - INFO - __main__ - Step 51474: {'lr': 0.00037435757496675646, 'samples': 9883008, 'steps': 51473, 'loss/train': 0.20036016404628754} 08/30/2021 22:31:01 - INFO - __main__ - Step 51475: {'lr': 0.000374352971317077, 'samples': 9883200, 'steps': 51474, 'loss/train': 0.9834887981414795} 08/30/2021 22:31:02 - INFO - __main__ - Step 51476: {'lr': 0.0003743483676113659, 'samples': 9883392, 'steps': 51475, 'loss/train': 1.5811645984649658} 08/30/2021 22:31:02 - INFO - __main__ - Step 51477: {'lr': 0.00037434376384962544, 'samples': 9883584, 'steps': 51476, 'loss/train': 1.6965177059173584} 08/30/2021 22:31:02 - INFO - __main__ - Step 51478: {'lr': 0.00037433916003185757, 'samples': 9883776, 'steps': 51477, 'loss/train': 1.8264700174331665} 08/30/2021 22:31:03 - INFO - __main__ - Step 51479: {'lr': 0.0003743345561580644, 'samples': 9883968, 'steps': 51478, 'loss/train': 1.6330749988555908} 08/30/2021 22:31:04 - INFO - __main__ - Step 51480: {'lr': 0.0003743299522282479, 'samples': 9884160, 'steps': 51479, 'loss/train': 1.5845221281051636} 08/30/2021 22:31:05 - INFO - __main__ - Step 51481: {'lr': 0.0003743253482424104, 'samples': 9884352, 'steps': 51480, 'loss/train': 1.718029260635376} 08/30/2021 22:31:05 - INFO - __main__ - Step 51482: {'lr': 0.00037432074420055376, 'samples': 9884544, 'steps': 51481, 'loss/train': 1.2749820947647095} 08/30/2021 22:31:05 - INFO - __main__ - Step 51483: {'lr': 0.00037431614010268013, 'samples': 9884736, 'steps': 51482, 'loss/train': 1.039206862449646} 08/30/2021 22:31:06 - INFO - __main__ - Step 51484: {'lr': 0.0003743115359487915, 'samples': 9884928, 'steps': 51483, 'loss/train': 1.1909019947052002} 08/30/2021 22:31:07 - INFO - __main__ - Step 51485: {'lr': 0.00037430693173889, 'samples': 9885120, 'steps': 51484, 'loss/train': 1.4576939344406128} 08/30/2021 22:31:08 - INFO - __main__ - Step 51486: {'lr': 0.00037430232747297774, 'samples': 9885312, 'steps': 51485, 'loss/train': 1.173467755317688} 08/30/2021 22:31:08 - INFO - __main__ - Step 51487: {'lr': 0.00037429772315105683, 'samples': 9885504, 'steps': 51486, 'loss/train': 1.9440302848815918} 08/30/2021 22:31:08 - INFO - __main__ - Step 51488: {'lr': 0.0003742931187731293, 'samples': 9885696, 'steps': 51487, 'loss/train': 1.4747331142425537} 08/30/2021 22:31:09 - INFO - __main__ - Step 51489: {'lr': 0.00037428851433919707, 'samples': 9885888, 'steps': 51488, 'loss/train': 1.3980581760406494} 08/30/2021 22:31:11 - INFO - __main__ - Step 51490: {'lr': 0.0003742839098492625, 'samples': 9886080, 'steps': 51489, 'loss/train': 1.4674938917160034} 08/30/2021 22:31:11 - INFO - __main__ - Step 51491: {'lr': 0.0003742793053033274, 'samples': 9886272, 'steps': 51490, 'loss/train': 1.2544020414352417} 08/30/2021 22:31:12 - INFO - __main__ - Step 51492: {'lr': 0.000374274700701394, 'samples': 9886464, 'steps': 51491, 'loss/train': 1.1741329431533813} 08/30/2021 22:31:12 - INFO - __main__ - Step 51493: {'lr': 0.00037427009604346437, 'samples': 9886656, 'steps': 51492, 'loss/train': 1.168109655380249} 08/30/2021 22:31:12 - INFO - __main__ - Step 51494: {'lr': 0.0003742654913295405, 'samples': 9886848, 'steps': 51493, 'loss/train': 0.13102193176746368} 08/30/2021 22:31:14 - INFO - __main__ - Step 51495: {'lr': 0.0003742608865596246, 'samples': 9887040, 'steps': 51494, 'loss/train': 1.9099037647247314} 08/30/2021 22:31:14 - INFO - __main__ - Step 51496: {'lr': 0.0003742562817337186, 'samples': 9887232, 'steps': 51495, 'loss/train': 1.4433385133743286} 08/30/2021 22:31:15 - INFO - __main__ - Step 51497: {'lr': 0.0003742516768518247, 'samples': 9887424, 'steps': 51496, 'loss/train': 1.8039155006408691} 08/30/2021 22:31:15 - INFO - __main__ - Step 51498: {'lr': 0.0003742470719139448, 'samples': 9887616, 'steps': 51497, 'loss/train': 1.3243900537490845} 08/30/2021 22:31:15 - INFO - __main__ - Step 51499: {'lr': 0.0003742424669200811, 'samples': 9887808, 'steps': 51498, 'loss/train': 1.358375072479248} 08/30/2021 22:31:17 - INFO - __main__ - Step 51500: {'lr': 0.00037423786187023574, 'samples': 9888000, 'steps': 51499, 'loss/train': 1.7329976558685303} 08/30/2021 22:31:17 - INFO - __main__ - Step 51501: {'lr': 0.00037423325676441064, 'samples': 9888192, 'steps': 51500, 'loss/train': 1.1874157190322876} 08/30/2021 22:31:18 - INFO - __main__ - Step 51502: {'lr': 0.0003742286516026081, 'samples': 9888384, 'steps': 51501, 'loss/train': 0.9082269668579102} 08/30/2021 22:31:18 - INFO - __main__ - Step 51503: {'lr': 0.0003742240463848299, 'samples': 9888576, 'steps': 51502, 'loss/train': 1.2705663442611694} 08/30/2021 22:31:18 - INFO - __main__ - Step 51504: {'lr': 0.0003742194411110783, 'samples': 9888768, 'steps': 51503, 'loss/train': 1.6481341123580933} 08/30/2021 22:31:19 - INFO - __main__ - Step 51505: {'lr': 0.00037421483578135536, 'samples': 9888960, 'steps': 51504, 'loss/train': 1.2350645065307617} 08/30/2021 22:31:20 - INFO - __main__ - Step 51506: {'lr': 0.0003742102303956631, 'samples': 9889152, 'steps': 51505, 'loss/train': 0.5643467307090759} 08/30/2021 22:31:21 - INFO - __main__ - Step 51507: {'lr': 0.0003742056249540036, 'samples': 9889344, 'steps': 51506, 'loss/train': 1.4980963468551636} 08/30/2021 22:31:21 - INFO - __main__ - Step 51508: {'lr': 0.00037420101945637906, 'samples': 9889536, 'steps': 51507, 'loss/train': 1.1526356935501099} 08/30/2021 22:31:21 - INFO - __main__ - Step 51509: {'lr': 0.00037419641390279136, 'samples': 9889728, 'steps': 51508, 'loss/train': 0.9649524688720703} 08/30/2021 22:31:22 - INFO - __main__ - Step 51510: {'lr': 0.00037419180829324273, 'samples': 9889920, 'steps': 51509, 'loss/train': 1.904329538345337} 08/30/2021 22:31:23 - INFO - __main__ - Step 51511: {'lr': 0.0003741872026277351, 'samples': 9890112, 'steps': 51510, 'loss/train': 0.3085313141345978} 08/30/2021 22:31:24 - INFO - __main__ - Step 51512: {'lr': 0.00037418259690627075, 'samples': 9890304, 'steps': 51511, 'loss/train': 1.0710434913635254} 08/30/2021 22:31:24 - INFO - __main__ - Step 51513: {'lr': 0.0003741779911288516, 'samples': 9890496, 'steps': 51512, 'loss/train': 1.2834514379501343} 08/30/2021 22:31:25 - INFO - __main__ - Step 51514: {'lr': 0.0003741733852954797, 'samples': 9890688, 'steps': 51513, 'loss/train': 1.7014063596725464} 08/30/2021 22:31:25 - INFO - __main__ - Step 51515: {'lr': 0.00037416877940615737, 'samples': 9890880, 'steps': 51514, 'loss/train': 1.2408925294876099} 08/30/2021 22:31:27 - INFO - __main__ - Step 51516: {'lr': 0.00037416417346088635, 'samples': 9891072, 'steps': 51515, 'loss/train': 1.4154435396194458} 08/30/2021 22:31:27 - INFO - __main__ - Step 51517: {'lr': 0.0003741595674596688, 'samples': 9891264, 'steps': 51516, 'loss/train': 1.280374526977539} 08/30/2021 22:31:27 - INFO - __main__ - Step 51518: {'lr': 0.000374154961402507, 'samples': 9891456, 'steps': 51517, 'loss/train': 5.858405113220215} 08/30/2021 22:31:28 - INFO - __main__ - Step 51519: {'lr': 0.00037415035528940284, 'samples': 9891648, 'steps': 51518, 'loss/train': 1.4920510053634644} 08/30/2021 22:31:28 - INFO - __main__ - Step 51520: {'lr': 0.00037414574912035845, 'samples': 9891840, 'steps': 51519, 'loss/train': 2.1044516563415527} 08/30/2021 22:31:28 - INFO - __main__ - Step 51521: {'lr': 0.0003741411428953759, 'samples': 9892032, 'steps': 51520, 'loss/train': 1.1028512716293335} 08/30/2021 22:31:30 - INFO - __main__ - Step 51522: {'lr': 0.00037413653661445736, 'samples': 9892224, 'steps': 51521, 'loss/train': 0.17945143580436707} 08/30/2021 22:31:31 - INFO - __main__ - Step 51523: {'lr': 0.00037413193027760466, 'samples': 9892416, 'steps': 51522, 'loss/train': 1.2250851392745972} 08/30/2021 22:31:31 - INFO - __main__ - Step 51524: {'lr': 0.00037412732388482015, 'samples': 9892608, 'steps': 51523, 'loss/train': 1.5527629852294922} 08/30/2021 22:31:31 - INFO - __main__ - Step 51525: {'lr': 0.0003741227174361057, 'samples': 9892800, 'steps': 51524, 'loss/train': 1.3103173971176147} 08/30/2021 22:31:32 - INFO - __main__ - Step 51526: {'lr': 0.00037411811093146345, 'samples': 9892992, 'steps': 51525, 'loss/train': 1.5848549604415894} 08/30/2021 22:31:34 - INFO - __main__ - Step 51527: {'lr': 0.0003741135043708956, 'samples': 9893184, 'steps': 51526, 'loss/train': 1.7637684345245361} 08/30/2021 22:31:34 - INFO - __main__ - Step 51528: {'lr': 0.000374108897754404, 'samples': 9893376, 'steps': 51527, 'loss/train': 1.4846374988555908} 08/30/2021 22:31:34 - INFO - __main__ - Step 51529: {'lr': 0.00037410429108199097, 'samples': 9893568, 'steps': 51528, 'loss/train': 1.4613293409347534} 08/30/2021 22:31:35 - INFO - __main__ - Step 51530: {'lr': 0.0003740996843536584, 'samples': 9893760, 'steps': 51529, 'loss/train': 0.06214777007699013} 08/30/2021 22:31:35 - INFO - __main__ - Step 51531: {'lr': 0.00037409507756940843, 'samples': 9893952, 'steps': 51530, 'loss/train': 1.5488176345825195} 08/30/2021 22:31:35 - INFO - __main__ - Step 51532: {'lr': 0.00037409047072924307, 'samples': 9894144, 'steps': 51531, 'loss/train': 0.15970462560653687} 08/30/2021 22:31:37 - INFO - __main__ - Step 51533: {'lr': 0.0003740858638331646, 'samples': 9894336, 'steps': 51532, 'loss/train': 0.24809174239635468} 08/30/2021 22:31:38 - INFO - __main__ - Step 51534: {'lr': 0.0003740812568811748, 'samples': 9894528, 'steps': 51533, 'loss/train': 0.7790964841842651} 08/30/2021 22:31:38 - INFO - __main__ - Step 51535: {'lr': 0.000374076649873276, 'samples': 9894720, 'steps': 51534, 'loss/train': 1.446571946144104} 08/30/2021 22:31:38 - INFO - __main__ - Step 51536: {'lr': 0.00037407204280947014, 'samples': 9894912, 'steps': 51535, 'loss/train': 1.1602075099945068} 08/30/2021 22:31:39 - INFO - __main__ - Step 51537: {'lr': 0.0003740674356897593, 'samples': 9895104, 'steps': 51536, 'loss/train': 1.8485909700393677} 08/30/2021 22:31:41 - INFO - __main__ - Step 51538: {'lr': 0.0003740628285141457, 'samples': 9895296, 'steps': 51537, 'loss/train': 1.1973363161087036} 08/30/2021 22:31:41 - INFO - __main__ - Step 51539: {'lr': 0.00037405822128263125, 'samples': 9895488, 'steps': 51538, 'loss/train': 1.3499199151992798} 08/30/2021 22:31:42 - INFO - __main__ - Step 51540: {'lr': 0.000374053613995218, 'samples': 9895680, 'steps': 51539, 'loss/train': 1.5263172388076782} 08/30/2021 22:31:42 - INFO - __main__ - Step 51541: {'lr': 0.0003740490066519082, 'samples': 9895872, 'steps': 51540, 'loss/train': 1.528464436531067} 08/30/2021 22:31:42 - INFO - __main__ - Step 51542: {'lr': 0.0003740443992527038, 'samples': 9896064, 'steps': 51541, 'loss/train': 1.3877899646759033} 08/30/2021 22:31:43 - INFO - __main__ - Step 51543: {'lr': 0.00037403979179760687, 'samples': 9896256, 'steps': 51542, 'loss/train': 0.10983399301767349} 08/30/2021 22:31:43 - INFO - __main__ - Step 51544: {'lr': 0.0003740351842866196, 'samples': 9896448, 'steps': 51543, 'loss/train': 1.4278217554092407} 08/30/2021 22:31:45 - INFO - __main__ - Step 51545: {'lr': 0.0003740305767197439, 'samples': 9896640, 'steps': 51544, 'loss/train': 1.0563499927520752} 08/30/2021 22:31:45 - INFO - __main__ - Step 51546: {'lr': 0.0003740259690969821, 'samples': 9896832, 'steps': 51545, 'loss/train': 1.3931564092636108} 08/30/2021 22:31:46 - INFO - __main__ - Step 51547: {'lr': 0.00037402136141833595, 'samples': 9897024, 'steps': 51546, 'loss/train': 1.6741191148757935} 08/30/2021 22:31:46 - INFO - __main__ - Step 51548: {'lr': 0.0003740167536838077, 'samples': 9897216, 'steps': 51547, 'loss/train': 1.303240418434143} 08/30/2021 22:31:46 - INFO - __main__ - Step 51549: {'lr': 0.0003740121458933995, 'samples': 9897408, 'steps': 51548, 'loss/train': 1.633860468864441} 08/30/2021 22:31:48 - INFO - __main__ - Step 51550: {'lr': 0.0003740075380471133, 'samples': 9897600, 'steps': 51549, 'loss/train': 1.4947450160980225} 08/30/2021 22:31:48 - INFO - __main__ - Step 51551: {'lr': 0.0003740029301449512, 'samples': 9897792, 'steps': 51550, 'loss/train': 1.934906005859375} 08/30/2021 22:31:49 - INFO - __main__ - Step 51552: {'lr': 0.0003739983221869153, 'samples': 9897984, 'steps': 51551, 'loss/train': 1.3299869298934937} 08/30/2021 22:31:49 - INFO - __main__ - Step 51553: {'lr': 0.00037399371417300766, 'samples': 9898176, 'steps': 51552, 'loss/train': 1.2477569580078125} 08/30/2021 22:31:50 - INFO - __main__ - Step 51554: {'lr': 0.00037398910610323034, 'samples': 9898368, 'steps': 51553, 'loss/train': 1.0288652181625366} 08/30/2021 22:31:50 - INFO - __main__ - Step 51555: {'lr': 0.0003739844979775855, 'samples': 9898560, 'steps': 51554, 'loss/train': 1.0303795337677002} 08/30/2021 22:31:51 - INFO - __main__ - Step 51556: {'lr': 0.0003739798897960752, 'samples': 9898752, 'steps': 51555, 'loss/train': 1.1251752376556396} 08/30/2021 22:31:52 - INFO - __main__ - Step 51557: {'lr': 0.00037397528155870134, 'samples': 9898944, 'steps': 51556, 'loss/train': 1.8401908874511719} 08/30/2021 22:31:52 - INFO - __main__ - Step 51558: {'lr': 0.00037397067326546616, 'samples': 9899136, 'steps': 51557, 'loss/train': 2.5792136192321777} 08/30/2021 22:31:53 - INFO - __main__ - Step 51559: {'lr': 0.0003739660649163718, 'samples': 9899328, 'steps': 51558, 'loss/train': 1.583563208580017} 08/30/2021 22:31:53 - INFO - __main__ - Step 51560: {'lr': 0.0003739614565114202, 'samples': 9899520, 'steps': 51559, 'loss/train': 1.0671730041503906} 08/30/2021 22:31:55 - INFO - __main__ - Step 51561: {'lr': 0.00037395684805061345, 'samples': 9899712, 'steps': 51560, 'loss/train': 1.0895830392837524} 08/30/2021 22:31:55 - INFO - __main__ - Step 51562: {'lr': 0.00037395223953395375, 'samples': 9899904, 'steps': 51561, 'loss/train': 0.8633602261543274} 08/30/2021 22:31:55 - INFO - __main__ - Step 51563: {'lr': 0.000373947630961443, 'samples': 9900096, 'steps': 51562, 'loss/train': 1.289513349533081} 08/30/2021 22:31:56 - INFO - __main__ - Step 51564: {'lr': 0.00037394302233308336, 'samples': 9900288, 'steps': 51563, 'loss/train': 0.9341845512390137} 08/30/2021 22:31:56 - INFO - __main__ - Step 51565: {'lr': 0.0003739384136488769, 'samples': 9900480, 'steps': 51564, 'loss/train': 1.650567889213562} 08/30/2021 22:31:58 - INFO - __main__ - Step 51566: {'lr': 0.00037393380490882575, 'samples': 9900672, 'steps': 51565, 'loss/train': 1.0414856672286987} 08/30/2021 22:31:58 - INFO - __main__ - Step 51567: {'lr': 0.0003739291961129319, 'samples': 9900864, 'steps': 51566, 'loss/train': 1.7716565132141113} 08/30/2021 22:31:58 - INFO - __main__ - Step 51568: {'lr': 0.0003739245872611975, 'samples': 9901056, 'steps': 51567, 'loss/train': 1.4202914237976074} 08/30/2021 22:31:59 - INFO - __main__ - Step 51569: {'lr': 0.0003739199783536246, 'samples': 9901248, 'steps': 51568, 'loss/train': 1.3330029249191284} 08/30/2021 22:31:59 - INFO - __main__ - Step 51570: {'lr': 0.0003739153693902152, 'samples': 9901440, 'steps': 51569, 'loss/train': 1.644285798072815} 08/30/2021 22:32:00 - INFO - __main__ - Step 51571: {'lr': 0.0003739107603709715, 'samples': 9901632, 'steps': 51570, 'loss/train': 1.5177286863327026} 08/30/2021 22:32:01 - INFO - __main__ - Step 51572: {'lr': 0.00037390615129589554, 'samples': 9901824, 'steps': 51571, 'loss/train': 1.6142197847366333} 08/30/2021 22:32:01 - INFO - __main__ - Step 51573: {'lr': 0.00037390154216498933, 'samples': 9902016, 'steps': 51572, 'loss/train': 1.4646210670471191} 08/30/2021 22:32:02 - INFO - __main__ - Step 51574: {'lr': 0.000373896932978255, 'samples': 9902208, 'steps': 51573, 'loss/train': 1.1083478927612305} 08/30/2021 22:32:02 - INFO - __main__ - Step 51575: {'lr': 0.00037389232373569463, 'samples': 9902400, 'steps': 51574, 'loss/train': 1.113458275794983} 08/30/2021 22:32:04 - INFO - __main__ - Step 51576: {'lr': 0.0003738877144373104, 'samples': 9902592, 'steps': 51575, 'loss/train': 1.0290260314941406} 08/30/2021 22:32:04 - INFO - __main__ - Step 51577: {'lr': 0.0003738831050831042, 'samples': 9902784, 'steps': 51576, 'loss/train': 1.7404829263687134} 08/30/2021 22:32:05 - INFO - __main__ - Step 51578: {'lr': 0.0003738784956730781, 'samples': 9902976, 'steps': 51577, 'loss/train': 1.306673288345337} 08/30/2021 22:32:05 - INFO - __main__ - Step 51579: {'lr': 0.0003738738862072343, 'samples': 9903168, 'steps': 51578, 'loss/train': 1.9081714153289795} 08/30/2021 22:32:05 - INFO - __main__ - Step 51580: {'lr': 0.00037386927668557493, 'samples': 9903360, 'steps': 51579, 'loss/train': 1.2259036302566528} 08/30/2021 22:32:07 - INFO - __main__ - Step 51581: {'lr': 0.0003738646671081019, 'samples': 9903552, 'steps': 51580, 'loss/train': 0.6796914935112} 08/30/2021 22:32:07 - INFO - __main__ - Step 51582: {'lr': 0.00037386005747481744, 'samples': 9903744, 'steps': 51581, 'loss/train': 1.4337469339370728} 08/30/2021 22:32:07 - INFO - __main__ - Step 51583: {'lr': 0.00037385544778572346, 'samples': 9903936, 'steps': 51582, 'loss/train': 1.0164211988449097} 08/30/2021 22:32:08 - INFO - __main__ - Step 51584: {'lr': 0.00037385083804082213, 'samples': 9904128, 'steps': 51583, 'loss/train': 1.9585940837860107} 08/30/2021 22:32:08 - INFO - __main__ - Step 51585: {'lr': 0.00037384622824011555, 'samples': 9904320, 'steps': 51584, 'loss/train': 2.0327370166778564} 08/30/2021 22:32:10 - INFO - __main__ - Step 51586: {'lr': 0.00037384161838360574, 'samples': 9904512, 'steps': 51585, 'loss/train': 1.8917208909988403} 08/30/2021 22:32:11 - INFO - __main__ - Step 51587: {'lr': 0.00037383700847129487, 'samples': 9904704, 'steps': 51586, 'loss/train': 0.3373853266239166} 08/30/2021 22:32:11 - INFO - __main__ - Step 51588: {'lr': 0.0003738323985031849, 'samples': 9904896, 'steps': 51587, 'loss/train': 0.38460031151771545} 08/30/2021 22:32:11 - INFO - __main__ - Step 51589: {'lr': 0.000373827788479278, 'samples': 9905088, 'steps': 51588, 'loss/train': 1.1099581718444824} 08/30/2021 22:32:12 - INFO - __main__ - Step 51590: {'lr': 0.0003738231783995762, 'samples': 9905280, 'steps': 51589, 'loss/train': 1.6286319494247437} 08/30/2021 22:32:12 - INFO - __main__ - Step 51591: {'lr': 0.00037381856826408156, 'samples': 9905472, 'steps': 51590, 'loss/train': 1.7703702449798584} 08/30/2021 22:32:12 - INFO - __main__ - Step 51592: {'lr': 0.00037381395807279625, 'samples': 9905664, 'steps': 51591, 'loss/train': 0.03311726450920105} 08/30/2021 22:32:14 - INFO - __main__ - Step 51593: {'lr': 0.0003738093478257222, 'samples': 9905856, 'steps': 51592, 'loss/train': 0.029038993641734123} 08/30/2021 22:32:14 - INFO - __main__ - Step 51594: {'lr': 0.0003738047375228616, 'samples': 9906048, 'steps': 51593, 'loss/train': 1.3370366096496582} 08/30/2021 22:32:15 - INFO - __main__ - Step 51595: {'lr': 0.00037380012716421647, 'samples': 9906240, 'steps': 51594, 'loss/train': 1.0302993059158325} 08/30/2021 22:32:15 - INFO - __main__ - Step 51596: {'lr': 0.00037379551674978896, 'samples': 9906432, 'steps': 51595, 'loss/train': 1.2916898727416992} 08/30/2021 22:32:15 - INFO - __main__ - Step 51597: {'lr': 0.0003737909062795811, 'samples': 9906624, 'steps': 51596, 'loss/train': 1.0558297634124756} 08/30/2021 22:32:17 - INFO - __main__ - Step 51598: {'lr': 0.00037378629575359493, 'samples': 9906816, 'steps': 51597, 'loss/train': 0.9440423250198364} 08/30/2021 22:32:18 - INFO - __main__ - Step 51599: {'lr': 0.0003737816851718326, 'samples': 9907008, 'steps': 51598, 'loss/train': 1.2873013019561768} 08/30/2021 22:32:18 - INFO - __main__ - Step 51600: {'lr': 0.0003737770745342961, 'samples': 9907200, 'steps': 51599, 'loss/train': 0.8846646547317505} 08/30/2021 22:32:19 - INFO - __main__ - Step 51601: {'lr': 0.0003737724638409876, 'samples': 9907392, 'steps': 51600, 'loss/train': 0.7183449268341064} 08/30/2021 22:32:19 - INFO - __main__ - Step 51602: {'lr': 0.00037376785309190913, 'samples': 9907584, 'steps': 51601, 'loss/train': 1.514360785484314} 08/30/2021 22:32:20 - INFO - __main__ - Step 51603: {'lr': 0.0003737632422870628, 'samples': 9907776, 'steps': 51602, 'loss/train': 1.33913254737854} 08/30/2021 22:32:21 - INFO - __main__ - Step 51604: {'lr': 0.00037375863142645064, 'samples': 9907968, 'steps': 51603, 'loss/train': 1.5239001512527466} 08/30/2021 22:32:21 - INFO - __main__ - Step 51605: {'lr': 0.00037375402051007477, 'samples': 9908160, 'steps': 51604, 'loss/train': 1.7382969856262207} 08/30/2021 22:32:22 - INFO - __main__ - Step 51606: {'lr': 0.00037374940953793724, 'samples': 9908352, 'steps': 51605, 'loss/train': 1.2390068769454956} 08/30/2021 22:32:22 - INFO - __main__ - Step 51607: {'lr': 0.00037374479851004006, 'samples': 9908544, 'steps': 51606, 'loss/train': 1.884042501449585} 08/30/2021 22:32:24 - INFO - __main__ - Step 51608: {'lr': 0.0003737401874263855, 'samples': 9908736, 'steps': 51607, 'loss/train': 1.6969270706176758} 08/30/2021 22:32:24 - INFO - __main__ - Step 51609: {'lr': 0.0003737355762869755, 'samples': 9908928, 'steps': 51608, 'loss/train': 0.8311616778373718} 08/30/2021 22:32:25 - INFO - __main__ - Step 51610: {'lr': 0.0003737309650918121, 'samples': 9909120, 'steps': 51609, 'loss/train': 0.01981472037732601} 08/30/2021 22:32:25 - INFO - __main__ - Step 51611: {'lr': 0.0003737263538408975, 'samples': 9909312, 'steps': 51610, 'loss/train': 1.2087864875793457} 08/30/2021 22:32:25 - INFO - __main__ - Step 51612: {'lr': 0.0003737217425342336, 'samples': 9909504, 'steps': 51611, 'loss/train': 0.050863899290561676} 08/30/2021 22:32:26 - INFO - __main__ - Step 51613: {'lr': 0.0003737171311718227, 'samples': 9909696, 'steps': 51612, 'loss/train': 1.2529886960983276} 08/30/2021 22:32:28 - INFO - __main__ - Step 51614: {'lr': 0.0003737125197536667, 'samples': 9909888, 'steps': 51613, 'loss/train': 0.04510089010000229} 08/30/2021 22:32:28 - INFO - __main__ - Step 51615: {'lr': 0.0003737079082797678, 'samples': 9910080, 'steps': 51614, 'loss/train': 1.7643711566925049} 08/30/2021 22:32:29 - INFO - __main__ - Step 51616: {'lr': 0.000373703296750128, 'samples': 9910272, 'steps': 51615, 'loss/train': 1.0789111852645874} 08/30/2021 22:32:29 - INFO - __main__ - Step 51617: {'lr': 0.0003736986851647495, 'samples': 9910464, 'steps': 51616, 'loss/train': 1.516789436340332} 08/30/2021 22:32:29 - INFO - __main__ - Step 51618: {'lr': 0.00037369407352363417, 'samples': 9910656, 'steps': 51617, 'loss/train': 0.03868023306131363} 08/30/2021 22:32:30 - INFO - __main__ - Step 51619: {'lr': 0.0003736894618267842, 'samples': 9910848, 'steps': 51618, 'loss/train': 0.22338785231113434} 08/30/2021 22:32:31 - INFO - __main__ - Step 51620: {'lr': 0.0003736848500742017, 'samples': 9911040, 'steps': 51619, 'loss/train': 1.5001274347305298} 08/30/2021 22:32:32 - INFO - __main__ - Step 51621: {'lr': 0.0003736802382658887, 'samples': 9911232, 'steps': 51620, 'loss/train': 1.1166435480117798} 08/30/2021 22:32:32 - INFO - __main__ - Step 51622: {'lr': 0.00037367562640184735, 'samples': 9911424, 'steps': 51621, 'loss/train': 0.5407716631889343} 08/30/2021 22:32:32 - INFO - __main__ - Step 51623: {'lr': 0.0003736710144820796, 'samples': 9911616, 'steps': 51622, 'loss/train': 1.6106802225112915} 08/30/2021 22:32:33 - INFO - __main__ - Step 51624: {'lr': 0.00037366640250658767, 'samples': 9911808, 'steps': 51623, 'loss/train': 1.1158663034439087} 08/30/2021 22:32:34 - INFO - __main__ - Step 51625: {'lr': 0.00037366179047537354, 'samples': 9912000, 'steps': 51624, 'loss/train': 1.6539461612701416} 08/30/2021 22:32:35 - INFO - __main__ - Step 51626: {'lr': 0.0003736571783884393, 'samples': 9912192, 'steps': 51625, 'loss/train': 0.9302570819854736} 08/30/2021 22:32:35 - INFO - __main__ - Step 51627: {'lr': 0.00037365256624578695, 'samples': 9912384, 'steps': 51626, 'loss/train': 1.5809532403945923} 08/30/2021 22:32:35 - INFO - __main__ - Step 51628: {'lr': 0.0003736479540474188, 'samples': 9912576, 'steps': 51627, 'loss/train': 1.4287220239639282} 08/30/2021 22:32:36 - INFO - __main__ - Step 51629: {'lr': 0.00037364334179333674, 'samples': 9912768, 'steps': 51628, 'loss/train': 1.338386058807373} 08/30/2021 22:32:37 - INFO - __main__ - Step 51630: {'lr': 0.00037363872948354294, 'samples': 9912960, 'steps': 51629, 'loss/train': 1.6858468055725098} 08/30/2021 22:32:38 - INFO - __main__ - Step 51631: {'lr': 0.00037363411711803935, 'samples': 9913152, 'steps': 51630, 'loss/train': 1.7678496837615967} 08/30/2021 22:32:38 - INFO - __main__ - Step 51632: {'lr': 0.0003736295046968282, 'samples': 9913344, 'steps': 51631, 'loss/train': 1.4017808437347412} 08/30/2021 22:32:38 - INFO - __main__ - Step 51633: {'lr': 0.0003736248922199115, 'samples': 9913536, 'steps': 51632, 'loss/train': 1.5283550024032593} 08/30/2021 22:32:39 - INFO - __main__ - Step 51634: {'lr': 0.0003736202796872913, 'samples': 9913728, 'steps': 51633, 'loss/train': 1.1208016872406006} 08/30/2021 22:32:40 - INFO - __main__ - Step 51635: {'lr': 0.00037361566709896964, 'samples': 9913920, 'steps': 51634, 'loss/train': 1.4629861116409302} 08/30/2021 22:32:41 - INFO - __main__ - Step 51636: {'lr': 0.00037361105445494884, 'samples': 9914112, 'steps': 51635, 'loss/train': 0.7506587505340576} 08/30/2021 22:32:41 - INFO - __main__ - Step 51637: {'lr': 0.0003736064417552307, 'samples': 9914304, 'steps': 51636, 'loss/train': 1.307244062423706} 08/30/2021 22:32:41 - INFO - __main__ - Step 51638: {'lr': 0.0003736018289998174, 'samples': 9914496, 'steps': 51637, 'loss/train': 1.3700740337371826} 08/30/2021 22:32:42 - INFO - __main__ - Step 51639: {'lr': 0.00037359721618871107, 'samples': 9914688, 'steps': 51638, 'loss/train': 1.2720520496368408} 08/30/2021 22:32:43 - INFO - __main__ - Step 51640: {'lr': 0.0003735926033219137, 'samples': 9914880, 'steps': 51639, 'loss/train': 1.3028295040130615} 08/30/2021 22:32:44 - INFO - __main__ - Step 51641: {'lr': 0.00037358799039942744, 'samples': 9915072, 'steps': 51640, 'loss/train': 1.4700137376785278} 08/30/2021 22:32:44 - INFO - __main__ - Step 51642: {'lr': 0.00037358337742125433, 'samples': 9915264, 'steps': 51641, 'loss/train': 1.4409149885177612} 08/30/2021 22:32:44 - INFO - __main__ - Step 51643: {'lr': 0.0003735787643873965, 'samples': 9915456, 'steps': 51642, 'loss/train': 1.2647240161895752} 08/30/2021 22:32:45 - INFO - __main__ - Step 51644: {'lr': 0.00037357415129785586, 'samples': 9915648, 'steps': 51643, 'loss/train': 1.546258807182312} 08/30/2021 22:32:46 - INFO - __main__ - Step 51645: {'lr': 0.00037356953815263473, 'samples': 9915840, 'steps': 51644, 'loss/train': 1.5272432565689087} 08/30/2021 22:32:47 - INFO - __main__ - Step 51646: {'lr': 0.00037356492495173505, 'samples': 9916032, 'steps': 51645, 'loss/train': 1.1103973388671875} 08/30/2021 22:32:47 - INFO - __main__ - Step 51647: {'lr': 0.00037356031169515894, 'samples': 9916224, 'steps': 51646, 'loss/train': 1.0418039560317993} 08/30/2021 22:32:47 - INFO - __main__ - Step 51648: {'lr': 0.0003735556983829084, 'samples': 9916416, 'steps': 51647, 'loss/train': 1.464951992034912} 08/30/2021 22:32:48 - INFO - __main__ - Step 51649: {'lr': 0.00037355108501498557, 'samples': 9916608, 'steps': 51648, 'loss/train': 0.9551159143447876} 08/30/2021 22:32:49 - INFO - __main__ - Step 51650: {'lr': 0.0003735464715913926, 'samples': 9916800, 'steps': 51649, 'loss/train': 1.679457426071167} 08/30/2021 22:32:50 - INFO - __main__ - Step 51651: {'lr': 0.00037354185811213145, 'samples': 9916992, 'steps': 51650, 'loss/train': 1.5624104738235474} 08/30/2021 22:32:50 - INFO - __main__ - Step 51652: {'lr': 0.0003735372445772042, 'samples': 9917184, 'steps': 51651, 'loss/train': 1.495266318321228} 08/30/2021 22:32:50 - INFO - __main__ - Step 51653: {'lr': 0.00037353263098661304, 'samples': 9917376, 'steps': 51652, 'loss/train': 1.7803412675857544} 08/30/2021 22:32:51 - INFO - __main__ - Step 51654: {'lr': 0.00037352801734036, 'samples': 9917568, 'steps': 51653, 'loss/train': 1.6657036542892456} 08/30/2021 22:32:51 - INFO - __main__ - Step 51655: {'lr': 0.00037352340363844706, 'samples': 9917760, 'steps': 51654, 'loss/train': 1.3105398416519165} 08/30/2021 22:32:53 - INFO - __main__ - Step 51656: {'lr': 0.00037351878988087646, 'samples': 9917952, 'steps': 51655, 'loss/train': 1.1532460451126099} 08/30/2021 22:32:54 - INFO - __main__ - Step 51657: {'lr': 0.0003735141760676501, 'samples': 9918144, 'steps': 51656, 'loss/train': 1.3362302780151367} 08/30/2021 22:32:54 - INFO - __main__ - Step 51658: {'lr': 0.0003735095621987703, 'samples': 9918336, 'steps': 51657, 'loss/train': 0.12950551509857178} 08/30/2021 22:32:55 - INFO - __main__ - Step 51659: {'lr': 0.00037350494827423884, 'samples': 9918528, 'steps': 51658, 'loss/train': 0.2063923329114914} 08/30/2021 22:32:55 - INFO - __main__ - Step 51660: {'lr': 0.00037350033429405806, 'samples': 9918720, 'steps': 51659, 'loss/train': 1.121277928352356} 08/30/2021 22:32:57 - INFO - __main__ - Step 51661: {'lr': 0.0003734957202582299, 'samples': 9918912, 'steps': 51660, 'loss/train': 1.0919702053070068} 08/30/2021 22:32:57 - INFO - __main__ - Step 51662: {'lr': 0.00037349110616675653, 'samples': 9919104, 'steps': 51661, 'loss/train': 1.8586196899414062} 08/30/2021 22:32:57 - INFO - __main__ - Step 51663: {'lr': 0.0003734864920196399, 'samples': 9919296, 'steps': 51662, 'loss/train': 1.7960128784179688} 08/30/2021 22:32:58 - INFO - __main__ - Step 51664: {'lr': 0.0003734818778168823, 'samples': 9919488, 'steps': 51663, 'loss/train': 0.9504808187484741} 08/30/2021 22:32:58 - INFO - __main__ - Step 51665: {'lr': 0.0003734772635584855, 'samples': 9919680, 'steps': 51664, 'loss/train': 1.0689635276794434} 08/30/2021 22:32:59 - INFO - __main__ - Step 51666: {'lr': 0.0003734726492444518, 'samples': 9919872, 'steps': 51665, 'loss/train': 1.3270063400268555} 08/30/2021 22:33:00 - INFO - __main__ - Step 51667: {'lr': 0.00037346803487478325, 'samples': 9920064, 'steps': 51666, 'loss/train': 1.2435252666473389} 08/30/2021 22:33:00 - INFO - __main__ - Step 51668: {'lr': 0.0003734634204494819, 'samples': 9920256, 'steps': 51667, 'loss/train': 1.430754542350769} 08/30/2021 22:33:01 - INFO - __main__ - Step 51669: {'lr': 0.0003734588059685499, 'samples': 9920448, 'steps': 51668, 'loss/train': 0.7625913619995117} 08/30/2021 22:33:01 - INFO - __main__ - Step 51670: {'lr': 0.0003734541914319892, 'samples': 9920640, 'steps': 51669, 'loss/train': 1.5677143335342407} 08/30/2021 22:33:03 - INFO - __main__ - Step 51671: {'lr': 0.0003734495768398019, 'samples': 9920832, 'steps': 51670, 'loss/train': 1.373456358909607} 08/30/2021 22:33:03 - INFO - __main__ - Step 51672: {'lr': 0.00037344496219199016, 'samples': 9921024, 'steps': 51671, 'loss/train': 1.219123363494873} 08/30/2021 22:33:04 - INFO - __main__ - Step 51673: {'lr': 0.0003734403474885561, 'samples': 9921216, 'steps': 51672, 'loss/train': 1.0996557474136353} 08/30/2021 22:33:04 - INFO - __main__ - Step 51674: {'lr': 0.00037343573272950167, 'samples': 9921408, 'steps': 51673, 'loss/train': 1.3817435503005981} 08/30/2021 22:33:04 - INFO - __main__ - Step 51675: {'lr': 0.00037343111791482897, 'samples': 9921600, 'steps': 51674, 'loss/train': 0.978774905204773} 08/30/2021 22:33:05 - INFO - __main__ - Step 51676: {'lr': 0.0003734265030445401, 'samples': 9921792, 'steps': 51675, 'loss/train': 1.0237514972686768} 08/30/2021 22:33:05 - INFO - __main__ - Step 51677: {'lr': 0.0003734218881186372, 'samples': 9921984, 'steps': 51676, 'loss/train': 0.02279912680387497} 08/30/2021 22:33:07 - INFO - __main__ - Step 51678: {'lr': 0.00037341727313712237, 'samples': 9922176, 'steps': 51677, 'loss/train': 0.025808101519942284} 08/30/2021 22:33:07 - INFO - __main__ - Step 51679: {'lr': 0.0003734126580999975, 'samples': 9922368, 'steps': 51678, 'loss/train': 1.399193286895752} 08/30/2021 22:33:07 - INFO - __main__ - Step 51680: {'lr': 0.0003734080430072649, 'samples': 9922560, 'steps': 51679, 'loss/train': 0.9727354049682617} 08/30/2021 22:33:08 - INFO - __main__ - Step 51681: {'lr': 0.0003734034278589265, 'samples': 9922752, 'steps': 51680, 'loss/train': 1.0413569211959839} 08/30/2021 22:33:08 - INFO - __main__ - Step 51682: {'lr': 0.0003733988126549843, 'samples': 9922944, 'steps': 51681, 'loss/train': 1.3695199489593506} 08/30/2021 22:33:09 - INFO - __main__ - Step 51683: {'lr': 0.0003733941973954407, 'samples': 9923136, 'steps': 51682, 'loss/train': 1.441453218460083} 08/30/2021 22:33:10 - INFO - __main__ - Step 51684: {'lr': 0.00037338958208029744, 'samples': 9923328, 'steps': 51683, 'loss/train': 4.008942604064941} 08/30/2021 22:33:10 - INFO - __main__ - Step 51685: {'lr': 0.0003733849667095568, 'samples': 9923520, 'steps': 51684, 'loss/train': 1.1269786357879639} 08/30/2021 22:33:11 - INFO - __main__ - Step 51686: {'lr': 0.00037338035128322075, 'samples': 9923712, 'steps': 51685, 'loss/train': 1.1578725576400757} 08/30/2021 22:33:11 - INFO - __main__ - Step 51687: {'lr': 0.00037337573580129143, 'samples': 9923904, 'steps': 51686, 'loss/train': 1.2276599407196045} 08/30/2021 22:33:12 - INFO - __main__ - Step 51688: {'lr': 0.0003733711202637709, 'samples': 9924096, 'steps': 51687, 'loss/train': 1.360328197479248} 08/30/2021 22:33:13 - INFO - __main__ - Step 51689: {'lr': 0.00037336650467066125, 'samples': 9924288, 'steps': 51688, 'loss/train': 1.8080074787139893} 08/30/2021 22:33:13 - INFO - __main__ - Step 51690: {'lr': 0.0003733618890219646, 'samples': 9924480, 'steps': 51689, 'loss/train': 1.5439468622207642} 08/30/2021 22:33:14 - INFO - __main__ - Step 51691: {'lr': 0.000373357273317683, 'samples': 9924672, 'steps': 51690, 'loss/train': 1.2663969993591309} 08/30/2021 22:33:14 - INFO - __main__ - Step 51692: {'lr': 0.00037335265755781844, 'samples': 9924864, 'steps': 51691, 'loss/train': 1.1125068664550781} 08/30/2021 22:33:14 - INFO - __main__ - Step 51693: {'lr': 0.00037334804174237314, 'samples': 9925056, 'steps': 51692, 'loss/train': 1.7361685037612915} 08/30/2021 22:33:16 - INFO - __main__ - Step 51694: {'lr': 0.0003733434258713491, 'samples': 9925248, 'steps': 51693, 'loss/train': 1.3808708190917969} 08/30/2021 22:33:16 - INFO - __main__ - Step 51695: {'lr': 0.00037333880994474834, 'samples': 9925440, 'steps': 51694, 'loss/train': 0.7133839130401611} 08/30/2021 22:33:17 - INFO - __main__ - Step 51696: {'lr': 0.00037333419396257307, 'samples': 9925632, 'steps': 51695, 'loss/train': 1.6381560564041138} 08/30/2021 22:33:17 - INFO - __main__ - Step 51697: {'lr': 0.00037332957792482534, 'samples': 9925824, 'steps': 51696, 'loss/train': 1.2527058124542236} 08/30/2021 22:33:17 - INFO - __main__ - Step 51698: {'lr': 0.0003733249618315072, 'samples': 9926016, 'steps': 51697, 'loss/train': 2.36087965965271} 08/30/2021 22:33:19 - INFO - __main__ - Step 51699: {'lr': 0.0003733203456826207, 'samples': 9926208, 'steps': 51698, 'loss/train': 1.3819410800933838} 08/30/2021 22:33:19 - INFO - __main__ - Step 51700: {'lr': 0.000373315729478168, 'samples': 9926400, 'steps': 51699, 'loss/train': 1.3410474061965942} 08/30/2021 22:33:20 - INFO - __main__ - Step 51701: {'lr': 0.0003733111132181511, 'samples': 9926592, 'steps': 51700, 'loss/train': 1.00484037399292} 08/30/2021 22:33:20 - INFO - __main__ - Step 51702: {'lr': 0.0003733064969025721, 'samples': 9926784, 'steps': 51701, 'loss/train': 1.4844087362289429} 08/30/2021 22:33:20 - INFO - __main__ - Step 51703: {'lr': 0.00037330188053143323, 'samples': 9926976, 'steps': 51702, 'loss/train': 0.9071732759475708} 08/30/2021 22:33:22 - INFO - __main__ - Step 51704: {'lr': 0.0003732972641047363, 'samples': 9927168, 'steps': 51703, 'loss/train': 0.8955970406532288} 08/30/2021 22:33:22 - INFO - __main__ - Step 51705: {'lr': 0.0003732926476224835, 'samples': 9927360, 'steps': 51704, 'loss/train': 1.646584391593933} 08/30/2021 22:33:23 - INFO - __main__ - Step 51706: {'lr': 0.00037328803108467704, 'samples': 9927552, 'steps': 51705, 'loss/train': 1.074128270149231} 08/30/2021 22:33:23 - INFO - __main__ - Step 51707: {'lr': 0.0003732834144913188, 'samples': 9927744, 'steps': 51706, 'loss/train': 1.4815008640289307} 08/30/2021 22:33:23 - INFO - __main__ - Step 51708: {'lr': 0.00037327879784241095, 'samples': 9927936, 'steps': 51707, 'loss/train': 0.9861049652099609} 08/30/2021 22:33:26 - INFO - __main__ - Step 51709: {'lr': 0.00037327418113795565, 'samples': 9928128, 'steps': 51708, 'loss/train': 1.559061050415039} 08/30/2021 22:33:26 - INFO - __main__ - Step 51710: {'lr': 0.0003732695643779549, 'samples': 9928320, 'steps': 51709, 'loss/train': 1.484695553779602} 08/30/2021 22:33:27 - INFO - __main__ - Step 51711: {'lr': 0.0003732649475624108, 'samples': 9928512, 'steps': 51710, 'loss/train': 0.01932797208428383} 08/30/2021 22:33:27 - INFO - __main__ - Step 51712: {'lr': 0.0003732603306913254, 'samples': 9928704, 'steps': 51711, 'loss/train': 1.8199025392532349} 08/30/2021 22:33:27 - INFO - __main__ - Step 51713: {'lr': 0.00037325571376470074, 'samples': 9928896, 'steps': 51712, 'loss/train': 0.43242818117141724} 08/30/2021 22:33:28 - INFO - __main__ - Step 51714: {'lr': 0.00037325109678253897, 'samples': 9929088, 'steps': 51713, 'loss/train': 1.3795090913772583} 08/30/2021 22:33:29 - INFO - __main__ - Step 51715: {'lr': 0.0003732464797448422, 'samples': 9929280, 'steps': 51714, 'loss/train': 2.0980629920959473} 08/30/2021 22:33:30 - INFO - __main__ - Step 51716: {'lr': 0.0003732418626516125, 'samples': 9929472, 'steps': 51715, 'loss/train': 1.4240823984146118} 08/30/2021 22:33:30 - INFO - __main__ - Step 51717: {'lr': 0.0003732372455028519, 'samples': 9929664, 'steps': 51716, 'loss/train': 0.6917343735694885} 08/30/2021 22:33:30 - INFO - __main__ - Step 51718: {'lr': 0.00037323262829856246, 'samples': 9929856, 'steps': 51717, 'loss/train': 1.3072789907455444} 08/30/2021 22:33:31 - INFO - __main__ - Step 51719: {'lr': 0.00037322801103874633, 'samples': 9930048, 'steps': 51718, 'loss/train': 0.7716614007949829} 08/30/2021 22:33:32 - INFO - __main__ - Step 51720: {'lr': 0.00037322339372340555, 'samples': 9930240, 'steps': 51719, 'loss/train': 1.0582247972488403} 08/30/2021 22:33:33 - INFO - __main__ - Step 51721: {'lr': 0.0003732187763525421, 'samples': 9930432, 'steps': 51720, 'loss/train': 1.6641348600387573} 08/30/2021 22:33:33 - INFO - __main__ - Step 51722: {'lr': 0.00037321415892615833, 'samples': 9930624, 'steps': 51721, 'loss/train': 0.6993993520736694} 08/30/2021 22:33:33 - INFO - __main__ - Step 51723: {'lr': 0.0003732095414442561, 'samples': 9930816, 'steps': 51722, 'loss/train': 1.1004928350448608} 08/30/2021 22:33:34 - INFO - __main__ - Step 51724: {'lr': 0.00037320492390683756, 'samples': 9931008, 'steps': 51723, 'loss/train': 0.07755095511674881} 08/30/2021 22:33:35 - INFO - __main__ - Step 51725: {'lr': 0.00037320030631390476, 'samples': 9931200, 'steps': 51724, 'loss/train': 1.4266318082809448} 08/30/2021 22:33:36 - INFO - __main__ - Step 51726: {'lr': 0.00037319568866545983, 'samples': 9931392, 'steps': 51725, 'loss/train': 0.8921300768852234} 08/30/2021 22:33:36 - INFO - __main__ - Step 51727: {'lr': 0.00037319107096150483, 'samples': 9931584, 'steps': 51726, 'loss/train': 0.575541615486145} 08/30/2021 22:33:37 - INFO - __main__ - Step 51728: {'lr': 0.00037318645320204183, 'samples': 9931776, 'steps': 51727, 'loss/train': 1.354965329170227} 08/30/2021 22:33:37 - INFO - __main__ - Step 51729: {'lr': 0.0003731818353870729, 'samples': 9931968, 'steps': 51728, 'loss/train': 3.0695176124572754} 08/30/2021 22:33:37 - INFO - __main__ - Step 51730: {'lr': 0.00037317721751660014, 'samples': 9932160, 'steps': 51729, 'loss/train': 3.347961187362671} 08/30/2021 22:33:39 - INFO - __main__ - Step 51731: {'lr': 0.00037317259959062564, 'samples': 9932352, 'steps': 51730, 'loss/train': 0.39453622698783875} 08/30/2021 22:33:39 - INFO - __main__ - Step 51732: {'lr': 0.0003731679816091514, 'samples': 9932544, 'steps': 51731, 'loss/train': 1.9897546768188477} 08/30/2021 22:33:40 - INFO - __main__ - Step 51733: {'lr': 0.00037316336357217966, 'samples': 9932736, 'steps': 51732, 'loss/train': 1.697346568107605} 08/30/2021 22:33:40 - INFO - __main__ - Step 51734: {'lr': 0.0003731587454797124, 'samples': 9932928, 'steps': 51733, 'loss/train': 1.220609188079834} 08/30/2021 22:33:40 - INFO - __main__ - Step 51735: {'lr': 0.0003731541273317517, 'samples': 9933120, 'steps': 51734, 'loss/train': 1.3236980438232422} 08/30/2021 22:33:42 - INFO - __main__ - Step 51736: {'lr': 0.0003731495091282996, 'samples': 9933312, 'steps': 51735, 'loss/train': 1.49858558177948} 08/30/2021 22:33:42 - INFO - __main__ - Step 51737: {'lr': 0.0003731448908693583, 'samples': 9933504, 'steps': 51736, 'loss/train': 1.320495367050171} 08/30/2021 22:33:43 - INFO - __main__ - Step 51738: {'lr': 0.0003731402725549298, 'samples': 9933696, 'steps': 51737, 'loss/train': 1.24888277053833} 08/30/2021 22:33:43 - INFO - __main__ - Step 51739: {'lr': 0.0003731356541850162, 'samples': 9933888, 'steps': 51738, 'loss/train': 1.5330533981323242} 08/30/2021 22:33:43 - INFO - __main__ - Step 51740: {'lr': 0.0003731310357596195, 'samples': 9934080, 'steps': 51739, 'loss/train': 1.260166883468628} 08/30/2021 22:33:45 - INFO - __main__ - Step 51741: {'lr': 0.0003731264172787419, 'samples': 9934272, 'steps': 51740, 'loss/train': 1.1915870904922485} 08/30/2021 22:33:45 - INFO - __main__ - Step 51742: {'lr': 0.0003731217987423854, 'samples': 9934464, 'steps': 51741, 'loss/train': 1.5375360250473022} 08/30/2021 22:33:46 - INFO - __main__ - Step 51743: {'lr': 0.00037311718015055215, 'samples': 9934656, 'steps': 51742, 'loss/train': 1.421510934829712} 08/30/2021 22:33:46 - INFO - __main__ - Step 51744: {'lr': 0.0003731125615032442, 'samples': 9934848, 'steps': 51743, 'loss/train': 1.353835105895996} 08/30/2021 22:33:46 - INFO - __main__ - Step 51745: {'lr': 0.0003731079428004637, 'samples': 9935040, 'steps': 51744, 'loss/train': 1.5584110021591187} 08/30/2021 22:33:47 - INFO - __main__ - Step 51746: {'lr': 0.00037310332404221256, 'samples': 9935232, 'steps': 51745, 'loss/train': 1.5493760108947754} 08/30/2021 22:33:49 - INFO - __main__ - Step 51747: {'lr': 0.000373098705228493, 'samples': 9935424, 'steps': 51746, 'loss/train': 1.2706648111343384} 08/30/2021 22:33:49 - INFO - __main__ - Step 51748: {'lr': 0.00037309408635930705, 'samples': 9935616, 'steps': 51747, 'loss/train': 0.3625568747520447} 08/30/2021 22:33:49 - INFO - __main__ - Step 51749: {'lr': 0.0003730894674346568, 'samples': 9935808, 'steps': 51748, 'loss/train': 1.7290058135986328} 08/30/2021 22:33:50 - INFO - __main__ - Step 51750: {'lr': 0.00037308484845454434, 'samples': 9936000, 'steps': 51749, 'loss/train': 1.467778205871582} 08/30/2021 22:33:50 - INFO - __main__ - Step 51751: {'lr': 0.0003730802294189718, 'samples': 9936192, 'steps': 51750, 'loss/train': 1.6475639343261719} 08/30/2021 22:33:51 - INFO - __main__ - Step 51752: {'lr': 0.00037307561032794113, 'samples': 9936384, 'steps': 51751, 'loss/train': 0.9193523526191711} 08/30/2021 22:33:52 - INFO - __main__ - Step 51753: {'lr': 0.0003730709911814545, 'samples': 9936576, 'steps': 51752, 'loss/train': 1.5737004280090332} 08/30/2021 22:33:52 - INFO - __main__ - Step 51754: {'lr': 0.000373066371979514, 'samples': 9936768, 'steps': 51753, 'loss/train': 1.540323257446289} 08/30/2021 22:33:53 - INFO - __main__ - Step 51755: {'lr': 0.00037306175272212166, 'samples': 9936960, 'steps': 51754, 'loss/train': 1.3289436101913452} 08/30/2021 22:33:53 - INFO - __main__ - Step 51756: {'lr': 0.0003730571334092796, 'samples': 9937152, 'steps': 51755, 'loss/train': 0.7925437092781067} 08/30/2021 22:33:54 - INFO - __main__ - Step 51757: {'lr': 0.00037305251404099, 'samples': 9937344, 'steps': 51756, 'loss/train': 0.5316606163978577} 08/30/2021 22:33:55 - INFO - __main__ - Step 51758: {'lr': 0.00037304789461725473, 'samples': 9937536, 'steps': 51757, 'loss/train': 1.3171734809875488} 08/30/2021 22:33:55 - INFO - __main__ - Step 51759: {'lr': 0.000373043275138076, 'samples': 9937728, 'steps': 51758, 'loss/train': 0.9147374629974365} 08/30/2021 22:33:56 - INFO - __main__ - Step 51760: {'lr': 0.00037303865560345587, 'samples': 9937920, 'steps': 51759, 'loss/train': 1.0636916160583496} 08/30/2021 22:33:56 - INFO - __main__ - Step 51761: {'lr': 0.00037303403601339643, 'samples': 9938112, 'steps': 51760, 'loss/train': 0.508759081363678} 08/30/2021 22:33:58 - INFO - __main__ - Step 51762: {'lr': 0.0003730294163678997, 'samples': 9938304, 'steps': 51761, 'loss/train': 1.5808589458465576} 08/30/2021 22:33:58 - INFO - __main__ - Step 51763: {'lr': 0.00037302479666696787, 'samples': 9938496, 'steps': 51762, 'loss/train': 1.274237871170044} 08/30/2021 22:33:58 - INFO - __main__ - Step 51764: {'lr': 0.000373020176910603, 'samples': 9938688, 'steps': 51763, 'loss/train': 0.7507188320159912} 08/30/2021 22:33:59 - INFO - __main__ - Step 51765: {'lr': 0.00037301555709880706, 'samples': 9938880, 'steps': 51764, 'loss/train': 1.6534377336502075} 08/30/2021 22:33:59 - INFO - __main__ - Step 51766: {'lr': 0.00037301093723158223, 'samples': 9939072, 'steps': 51765, 'loss/train': 0.9131073355674744} 08/30/2021 22:33:59 - INFO - __main__ - Step 51767: {'lr': 0.0003730063173089306, 'samples': 9939264, 'steps': 51766, 'loss/train': 2.0918335914611816} 08/30/2021 22:34:02 - INFO - __main__ - Step 51768: {'lr': 0.0003730016973308542, 'samples': 9939456, 'steps': 51767, 'loss/train': 1.227973222732544} 08/30/2021 22:34:02 - INFO - __main__ - Step 51769: {'lr': 0.0003729970772973551, 'samples': 9939648, 'steps': 51768, 'loss/train': 1.1515026092529297} 08/30/2021 22:34:02 - INFO - __main__ - Step 51770: {'lr': 0.00037299245720843544, 'samples': 9939840, 'steps': 51769, 'loss/train': 1.055242657661438} 08/30/2021 22:34:03 - INFO - __main__ - Step 51771: {'lr': 0.0003729878370640973, 'samples': 9940032, 'steps': 51770, 'loss/train': 0.9286774396896362} 08/30/2021 22:34:03 - INFO - __main__ - Step 51772: {'lr': 0.0003729832168643428, 'samples': 9940224, 'steps': 51771, 'loss/train': 1.4751461744308472} 08/30/2021 22:34:06 - INFO - __main__ - Step 51773: {'lr': 0.00037297859660917384, 'samples': 9940416, 'steps': 51772, 'loss/train': 1.6746792793273926} 08/30/2021 22:34:06 - INFO - __main__ - Step 51774: {'lr': 0.00037297397629859266, 'samples': 9940608, 'steps': 51773, 'loss/train': 1.4278478622436523} 08/30/2021 22:34:07 - INFO - __main__ - Step 51775: {'lr': 0.0003729693559326013, 'samples': 9940800, 'steps': 51774, 'loss/train': 1.2316800355911255} 08/30/2021 22:34:07 - INFO - __main__ - Step 51776: {'lr': 0.00037296473551120185, 'samples': 9940992, 'steps': 51775, 'loss/train': 1.0251357555389404} 08/30/2021 22:34:07 - INFO - __main__ - Step 51777: {'lr': 0.00037296011503439643, 'samples': 9941184, 'steps': 51776, 'loss/train': 1.8975722789764404} 08/30/2021 22:34:08 - INFO - __main__ - Step 51778: {'lr': 0.00037295549450218704, 'samples': 9941376, 'steps': 51777, 'loss/train': 0.37099891901016235} 08/30/2021 22:34:08 - INFO - __main__ - Step 51779: {'lr': 0.0003729508739145758, 'samples': 9941568, 'steps': 51778, 'loss/train': 0.3667130172252655} 08/30/2021 22:34:10 - INFO - __main__ - Step 51780: {'lr': 0.0003729462532715648, 'samples': 9941760, 'steps': 51779, 'loss/train': 0.33669188618659973} 08/30/2021 22:34:10 - INFO - __main__ - Step 51781: {'lr': 0.0003729416325731561, 'samples': 9941952, 'steps': 51780, 'loss/train': 2.044456720352173} 08/30/2021 22:34:10 - INFO - __main__ - Step 51782: {'lr': 0.0003729370118193518, 'samples': 9942144, 'steps': 51781, 'loss/train': 1.579751968383789} 08/30/2021 22:34:11 - INFO - __main__ - Step 51783: {'lr': 0.00037293239101015397, 'samples': 9942336, 'steps': 51782, 'loss/train': 0.8203944563865662} 08/30/2021 22:34:11 - INFO - __main__ - Step 51784: {'lr': 0.0003729277701455648, 'samples': 9942528, 'steps': 51783, 'loss/train': 1.1906901597976685} 08/30/2021 22:34:12 - INFO - __main__ - Step 51785: {'lr': 0.00037292314922558615, 'samples': 9942720, 'steps': 51784, 'loss/train': 1.8912532329559326} 08/30/2021 22:34:13 - INFO - __main__ - Step 51786: {'lr': 0.0003729185282502203, 'samples': 9942912, 'steps': 51785, 'loss/train': 0.4631793797016144} 08/30/2021 22:34:13 - INFO - __main__ - Step 51787: {'lr': 0.00037291390721946914, 'samples': 9943104, 'steps': 51786, 'loss/train': 1.1479171514511108} 08/30/2021 22:34:14 - INFO - __main__ - Step 51788: {'lr': 0.00037290928613333495, 'samples': 9943296, 'steps': 51787, 'loss/train': 1.2784167528152466} 08/30/2021 22:34:14 - INFO - __main__ - Step 51789: {'lr': 0.00037290466499181977, 'samples': 9943488, 'steps': 51788, 'loss/train': 0.28819194436073303} 08/30/2021 22:34:14 - INFO - __main__ - Step 51790: {'lr': 0.0003729000437949256, 'samples': 9943680, 'steps': 51789, 'loss/train': 1.7119340896606445} 08/30/2021 22:34:16 - INFO - __main__ - Step 51791: {'lr': 0.0003728954225426546, 'samples': 9943872, 'steps': 51790, 'loss/train': 1.2977453470230103} 08/30/2021 22:34:17 - INFO - __main__ - Step 51792: {'lr': 0.00037289080123500886, 'samples': 9944064, 'steps': 51791, 'loss/train': 1.437566876411438} 08/30/2021 22:34:17 - INFO - __main__ - Step 51793: {'lr': 0.0003728861798719903, 'samples': 9944256, 'steps': 51792, 'loss/train': 0.8412335515022278} 08/30/2021 22:34:17 - INFO - __main__ - Step 51794: {'lr': 0.00037288155845360116, 'samples': 9944448, 'steps': 51793, 'loss/train': 1.403337836265564} 08/30/2021 22:34:18 - INFO - __main__ - Step 51795: {'lr': 0.00037287693697984355, 'samples': 9944640, 'steps': 51794, 'loss/train': 1.5479451417922974} 08/30/2021 22:34:19 - INFO - __main__ - Step 51796: {'lr': 0.0003728723154507195, 'samples': 9944832, 'steps': 51795, 'loss/train': 1.93978750705719} 08/30/2021 22:34:20 - INFO - __main__ - Step 51797: {'lr': 0.000372867693866231, 'samples': 9945024, 'steps': 51796, 'loss/train': 1.2946497201919556} 08/30/2021 22:34:20 - INFO - __main__ - Step 51798: {'lr': 0.0003728630722263803, 'samples': 9945216, 'steps': 51797, 'loss/train': 1.226035714149475} 08/30/2021 22:34:20 - INFO - __main__ - Step 51799: {'lr': 0.0003728584505311693, 'samples': 9945408, 'steps': 51798, 'loss/train': 1.3603320121765137} 08/30/2021 22:34:21 - INFO - __main__ - Step 51800: {'lr': 0.0003728538287806002, 'samples': 9945600, 'steps': 51799, 'loss/train': 1.6623071432113647} 08/30/2021 22:34:22 - INFO - __main__ - Step 51801: {'lr': 0.00037284920697467505, 'samples': 9945792, 'steps': 51800, 'loss/train': 1.3876612186431885} 08/30/2021 22:34:23 - INFO - __main__ - Step 51802: {'lr': 0.00037284458511339604, 'samples': 9945984, 'steps': 51801, 'loss/train': 1.4863940477371216} 08/30/2021 22:34:23 - INFO - __main__ - Step 51803: {'lr': 0.00037283996319676505, 'samples': 9946176, 'steps': 51802, 'loss/train': 1.1048009395599365} 08/30/2021 22:34:23 - INFO - __main__ - Step 51804: {'lr': 0.0003728353412247843, 'samples': 9946368, 'steps': 51803, 'loss/train': 1.4630974531173706} 08/30/2021 22:34:24 - INFO - __main__ - Step 51805: {'lr': 0.0003728307191974558, 'samples': 9946560, 'steps': 51804, 'loss/train': 1.4835635423660278} 08/30/2021 22:34:25 - INFO - __main__ - Step 51806: {'lr': 0.00037282609711478175, 'samples': 9946752, 'steps': 51805, 'loss/train': 1.3914366960525513} 08/30/2021 22:34:26 - INFO - __main__ - Step 51807: {'lr': 0.00037282147497676415, 'samples': 9946944, 'steps': 51806, 'loss/train': 1.6220390796661377} 08/30/2021 22:34:26 - INFO - __main__ - Step 51808: {'lr': 0.000372816852783405, 'samples': 9947136, 'steps': 51807, 'loss/train': 1.3874956369400024} 08/30/2021 22:34:26 - INFO - __main__ - Step 51809: {'lr': 0.0003728122305347066, 'samples': 9947328, 'steps': 51808, 'loss/train': 1.1157251596450806} 08/30/2021 22:34:27 - INFO - __main__ - Step 51810: {'lr': 0.00037280760823067086, 'samples': 9947520, 'steps': 51809, 'loss/train': 1.3168820142745972} 08/30/2021 22:34:28 - INFO - __main__ - Step 51811: {'lr': 0.00037280298587129984, 'samples': 9947712, 'steps': 51810, 'loss/train': 0.6487297415733337} 08/30/2021 22:34:29 - INFO - __main__ - Step 51812: {'lr': 0.0003727983634565958, 'samples': 9947904, 'steps': 51811, 'loss/train': 1.470218300819397} 08/30/2021 22:34:29 - INFO - __main__ - Step 51813: {'lr': 0.0003727937409865606, 'samples': 9948096, 'steps': 51812, 'loss/train': 0.892719566822052} 08/30/2021 22:34:29 - INFO - __main__ - Step 51814: {'lr': 0.0003727891184611965, 'samples': 9948288, 'steps': 51813, 'loss/train': 1.0866458415985107} 08/30/2021 22:34:30 - INFO - __main__ - Step 51815: {'lr': 0.0003727844958805055, 'samples': 9948480, 'steps': 51814, 'loss/train': 1.1836897134780884} 08/30/2021 22:34:31 - INFO - __main__ - Step 51816: {'lr': 0.0003727798732444897, 'samples': 9948672, 'steps': 51815, 'loss/train': 1.414215087890625} 08/30/2021 22:34:32 - INFO - __main__ - Step 51817: {'lr': 0.00037277525055315114, 'samples': 9948864, 'steps': 51816, 'loss/train': 2.360086441040039} 08/30/2021 22:34:32 - INFO - __main__ - Step 51818: {'lr': 0.0003727706278064921, 'samples': 9949056, 'steps': 51817, 'loss/train': 1.2951818704605103} 08/30/2021 22:34:32 - INFO - __main__ - Step 51819: {'lr': 0.00037276600500451434, 'samples': 9949248, 'steps': 51818, 'loss/train': 1.3951317071914673} 08/30/2021 22:34:33 - INFO - __main__ - Step 51820: {'lr': 0.00037276138214722016, 'samples': 9949440, 'steps': 51819, 'loss/train': 1.3718186616897583} 08/30/2021 22:34:33 - INFO - __main__ - Step 51821: {'lr': 0.0003727567592346116, 'samples': 9949632, 'steps': 51820, 'loss/train': 0.9237263202667236} 08/30/2021 22:34:35 - INFO - __main__ - Step 51822: {'lr': 0.00037275213626669076, 'samples': 9949824, 'steps': 51821, 'loss/train': 1.4530959129333496} 08/30/2021 22:34:36 - INFO - __main__ - Step 51823: {'lr': 0.00037274751324345966, 'samples': 9950016, 'steps': 51822, 'loss/train': 1.5151957273483276} 08/30/2021 22:34:36 - INFO - __main__ - Step 51824: {'lr': 0.0003727428901649205, 'samples': 9950208, 'steps': 51823, 'loss/train': 1.773315668106079} 08/30/2021 22:34:36 - INFO - __main__ - Step 51825: {'lr': 0.00037273826703107527, 'samples': 9950400, 'steps': 51824, 'loss/train': 1.4654994010925293} 08/30/2021 22:34:37 - INFO - __main__ - Step 51826: {'lr': 0.000372733643841926, 'samples': 9950592, 'steps': 51825, 'loss/train': 1.6336032152175903} 08/30/2021 22:34:39 - INFO - __main__ - Step 51827: {'lr': 0.00037272902059747487, 'samples': 9950784, 'steps': 51826, 'loss/train': 0.771109402179718} 08/30/2021 22:34:39 - INFO - __main__ - Step 51828: {'lr': 0.00037272439729772397, 'samples': 9950976, 'steps': 51827, 'loss/train': 1.550333023071289} 08/30/2021 22:34:40 - INFO - __main__ - Step 51829: {'lr': 0.00037271977394267534, 'samples': 9951168, 'steps': 51828, 'loss/train': 0.03464927524328232} 08/30/2021 22:34:40 - INFO - __main__ - Step 51830: {'lr': 0.0003727151505323311, 'samples': 9951360, 'steps': 51829, 'loss/train': 0.025755373761057854} 08/30/2021 22:34:40 - INFO - __main__ - Step 51831: {'lr': 0.0003727105270666933, 'samples': 9951552, 'steps': 51830, 'loss/train': 1.8752171993255615} 08/30/2021 22:34:41 - INFO - __main__ - Step 51832: {'lr': 0.00037270590354576396, 'samples': 9951744, 'steps': 51831, 'loss/train': 1.1250269412994385} 08/30/2021 22:34:42 - INFO - __main__ - Step 51833: {'lr': 0.0003727012799695453, 'samples': 9951936, 'steps': 51832, 'loss/train': 1.627541184425354} 08/30/2021 22:34:43 - INFO - __main__ - Step 51834: {'lr': 0.0003726966563380393, 'samples': 9952128, 'steps': 51833, 'loss/train': 1.692149043083191} 08/30/2021 22:34:43 - INFO - __main__ - Step 51835: {'lr': 0.00037269203265124807, 'samples': 9952320, 'steps': 51834, 'loss/train': 1.229498267173767} 08/30/2021 22:34:44 - INFO - __main__ - Step 51836: {'lr': 0.00037268740890917374, 'samples': 9952512, 'steps': 51835, 'loss/train': 0.7132439613342285} 08/30/2021 22:34:44 - INFO - __main__ - Step 51837: {'lr': 0.0003726827851118183, 'samples': 9952704, 'steps': 51836, 'loss/train': 1.7350763082504272} 08/30/2021 22:34:44 - INFO - __main__ - Step 51838: {'lr': 0.00037267816125918394, 'samples': 9952896, 'steps': 51837, 'loss/train': 1.4118082523345947} 08/30/2021 22:34:46 - INFO - __main__ - Step 51839: {'lr': 0.00037267353735127276, 'samples': 9953088, 'steps': 51838, 'loss/train': 0.5707834959030151} 08/30/2021 22:34:46 - INFO - __main__ - Step 51840: {'lr': 0.00037266891338808667, 'samples': 9953280, 'steps': 51839, 'loss/train': 1.6818580627441406} 08/30/2021 22:34:47 - INFO - __main__ - Step 51841: {'lr': 0.00037266428936962785, 'samples': 9953472, 'steps': 51840, 'loss/train': 1.5431554317474365} 08/30/2021 22:34:47 - INFO - __main__ - Step 51842: {'lr': 0.00037265966529589846, 'samples': 9953664, 'steps': 51841, 'loss/train': 1.2983708381652832} 08/30/2021 22:34:47 - INFO - __main__ - Step 51843: {'lr': 0.0003726550411669005, 'samples': 9953856, 'steps': 51842, 'loss/train': 1.130833625793457} 08/30/2021 22:34:49 - INFO - __main__ - Step 51844: {'lr': 0.000372650416982636, 'samples': 9954048, 'steps': 51843, 'loss/train': 1.2864400148391724} 08/30/2021 22:34:50 - INFO - __main__ - Step 51845: {'lr': 0.0003726457927431073, 'samples': 9954240, 'steps': 51844, 'loss/train': 1.660396695137024} 08/30/2021 22:34:50 - INFO - __main__ - Step 51846: {'lr': 0.0003726411684483161, 'samples': 9954432, 'steps': 51845, 'loss/train': 0.02651946246623993} 08/30/2021 22:34:51 - INFO - __main__ - Step 51847: {'lr': 0.0003726365440982648, 'samples': 9954624, 'steps': 51846, 'loss/train': 0.06892168521881104} 08/30/2021 22:34:51 - INFO - __main__ - Step 51848: {'lr': 0.00037263191969295537, 'samples': 9954816, 'steps': 51847, 'loss/train': 2.1675353050231934} 08/30/2021 22:34:51 - INFO - __main__ - Step 51849: {'lr': 0.0003726272952323898, 'samples': 9955008, 'steps': 51848, 'loss/train': 0.35434576869010925} 08/30/2021 22:34:53 - INFO - __main__ - Step 51850: {'lr': 0.0003726226707165703, 'samples': 9955200, 'steps': 51849, 'loss/train': 1.1533006429672241} 08/30/2021 22:34:53 - INFO - __main__ - Step 51851: {'lr': 0.000372618046145499, 'samples': 9955392, 'steps': 51850, 'loss/train': 1.7156795263290405} 08/30/2021 22:34:54 - INFO - __main__ - Step 51852: {'lr': 0.0003726134215191778, 'samples': 9955584, 'steps': 51851, 'loss/train': 0.8948954939842224} 08/30/2021 22:34:54 - INFO - __main__ - Step 51853: {'lr': 0.0003726087968376089, 'samples': 9955776, 'steps': 51852, 'loss/train': 1.0862714052200317} 08/30/2021 22:34:55 - INFO - __main__ - Step 51854: {'lr': 0.0003726041721007944, 'samples': 9955968, 'steps': 51853, 'loss/train': 1.7077580690383911} 08/30/2021 22:34:56 - INFO - __main__ - Step 51855: {'lr': 0.0003725995473087363, 'samples': 9956160, 'steps': 51854, 'loss/train': 1.6299303770065308} 08/30/2021 22:34:57 - INFO - __main__ - Step 51856: {'lr': 0.0003725949224614368, 'samples': 9956352, 'steps': 51855, 'loss/train': 1.7085137367248535} 08/30/2021 22:34:57 - INFO - __main__ - Step 51857: {'lr': 0.00037259029755889783, 'samples': 9956544, 'steps': 51856, 'loss/train': 1.4361802339553833} 08/30/2021 22:34:58 - INFO - __main__ - Step 51858: {'lr': 0.00037258567260112165, 'samples': 9956736, 'steps': 51857, 'loss/train': 0.0754077360033989} 08/30/2021 22:34:58 - INFO - __main__ - Step 51859: {'lr': 0.00037258104758811024, 'samples': 9956928, 'steps': 51858, 'loss/train': 1.4254209995269775} 08/30/2021 22:34:59 - INFO - __main__ - Step 51860: {'lr': 0.00037257642251986567, 'samples': 9957120, 'steps': 51859, 'loss/train': 0.05069465562701225} 08/30/2021 22:35:00 - INFO - __main__ - Step 51861: {'lr': 0.00037257179739639006, 'samples': 9957312, 'steps': 51860, 'loss/train': 1.6155613660812378} 08/30/2021 22:35:00 - INFO - __main__ - Step 51862: {'lr': 0.00037256717221768556, 'samples': 9957504, 'steps': 51861, 'loss/train': 1.1297948360443115} 08/30/2021 22:35:01 - INFO - __main__ - Step 51863: {'lr': 0.0003725625469837541, 'samples': 9957696, 'steps': 51862, 'loss/train': 1.1255016326904297} 08/30/2021 22:35:01 - INFO - __main__ - Step 51864: {'lr': 0.00037255792169459785, 'samples': 9957888, 'steps': 51863, 'loss/train': 1.4773226976394653} 08/30/2021 22:35:01 - INFO - __main__ - Step 51865: {'lr': 0.00037255329635021896, 'samples': 9958080, 'steps': 51864, 'loss/train': 1.4688013792037964} 08/30/2021 22:35:03 - INFO - __main__ - Step 51866: {'lr': 0.0003725486709506194, 'samples': 9958272, 'steps': 51865, 'loss/train': 1.5012935400009155} 08/30/2021 22:35:04 - INFO - __main__ - Step 51867: {'lr': 0.0003725440454958013, 'samples': 9958464, 'steps': 51866, 'loss/train': 1.6771867275238037} 08/30/2021 22:35:04 - INFO - __main__ - Step 51868: {'lr': 0.0003725394199857667, 'samples': 9958656, 'steps': 51867, 'loss/train': 0.592327356338501} 08/30/2021 22:35:04 - INFO - __main__ - Step 51869: {'lr': 0.0003725347944205178, 'samples': 9958848, 'steps': 51868, 'loss/train': 0.18364876508712769} 08/30/2021 22:35:05 - INFO - __main__ - Step 51870: {'lr': 0.0003725301688000566, 'samples': 9959040, 'steps': 51869, 'loss/train': 0.5639804005622864} 08/30/2021 22:35:06 - INFO - __main__ - Step 51871: {'lr': 0.0003725255431243852, 'samples': 9959232, 'steps': 51870, 'loss/train': 1.3463943004608154} 08/30/2021 22:35:07 - INFO - __main__ - Step 51872: {'lr': 0.00037252091739350566, 'samples': 9959424, 'steps': 51871, 'loss/train': 0.9146784543991089} 08/30/2021 22:35:07 - INFO - __main__ - Step 51873: {'lr': 0.0003725162916074201, 'samples': 9959616, 'steps': 51872, 'loss/train': 1.3303477764129639} 08/30/2021 22:35:07 - INFO - __main__ - Step 51874: {'lr': 0.0003725116657661306, 'samples': 9959808, 'steps': 51873, 'loss/train': 1.2069082260131836} 08/30/2021 22:35:08 - INFO - __main__ - Step 51875: {'lr': 0.00037250703986963917, 'samples': 9960000, 'steps': 51874, 'loss/train': 0.5643643736839294} 08/30/2021 22:35:10 - INFO - __main__ - Step 51876: {'lr': 0.000372502413917948, 'samples': 9960192, 'steps': 51875, 'loss/train': 1.7402911186218262} 08/30/2021 22:35:10 - INFO - __main__ - Step 51877: {'lr': 0.00037249778791105916, 'samples': 9960384, 'steps': 51876, 'loss/train': 1.5554461479187012} 08/30/2021 22:35:10 - INFO - __main__ - Step 51878: {'lr': 0.0003724931618489747, 'samples': 9960576, 'steps': 51877, 'loss/train': 1.2836854457855225} 08/30/2021 22:35:11 - INFO - __main__ - Step 51879: {'lr': 0.0003724885357316967, 'samples': 9960768, 'steps': 51878, 'loss/train': 0.6971196532249451} 08/30/2021 22:35:11 - INFO - __main__ - Step 51880: {'lr': 0.00037248390955922726, 'samples': 9960960, 'steps': 51879, 'loss/train': 1.4496119022369385} 08/30/2021 22:35:13 - INFO - __main__ - Step 51881: {'lr': 0.00037247928333156844, 'samples': 9961152, 'steps': 51880, 'loss/train': 1.3063400983810425} 08/30/2021 22:35:13 - INFO - __main__ - Step 51882: {'lr': 0.0003724746570487223, 'samples': 9961344, 'steps': 51881, 'loss/train': 1.3679530620574951} 08/30/2021 22:35:14 - INFO - __main__ - Step 51883: {'lr': 0.00037247003071069106, 'samples': 9961536, 'steps': 51882, 'loss/train': 1.1247488260269165} 08/30/2021 22:35:14 - INFO - __main__ - Step 51884: {'lr': 0.0003724654043174767, 'samples': 9961728, 'steps': 51883, 'loss/train': 1.2774298191070557} 08/30/2021 22:35:14 - INFO - __main__ - Step 51885: {'lr': 0.0003724607778690813, 'samples': 9961920, 'steps': 51884, 'loss/train': 1.5299878120422363} 08/30/2021 22:35:15 - INFO - __main__ - Step 51886: {'lr': 0.00037245615136550695, 'samples': 9962112, 'steps': 51885, 'loss/train': 1.7156078815460205} 08/30/2021 22:35:16 - INFO - __main__ - Step 51887: {'lr': 0.00037245152480675577, 'samples': 9962304, 'steps': 51886, 'loss/train': 0.4460705816745758} 08/30/2021 22:35:17 - INFO - __main__ - Step 51888: {'lr': 0.0003724468981928298, 'samples': 9962496, 'steps': 51887, 'loss/train': 1.4482715129852295} 08/30/2021 22:35:17 - INFO - __main__ - Step 51889: {'lr': 0.00037244227152373113, 'samples': 9962688, 'steps': 51888, 'loss/train': 0.8630905151367188} 08/30/2021 22:35:17 - INFO - __main__ - Step 51890: {'lr': 0.0003724376447994619, 'samples': 9962880, 'steps': 51889, 'loss/train': 1.7183257341384888} 08/30/2021 22:35:18 - INFO - __main__ - Step 51891: {'lr': 0.00037243301802002414, 'samples': 9963072, 'steps': 51890, 'loss/train': 1.396705150604248} 08/30/2021 22:35:19 - INFO - __main__ - Step 51892: {'lr': 0.00037242839118542, 'samples': 9963264, 'steps': 51891, 'loss/train': 1.525964617729187} 08/30/2021 22:35:20 - INFO - __main__ - Step 51893: {'lr': 0.00037242376429565143, 'samples': 9963456, 'steps': 51892, 'loss/train': 0.7317933440208435} 08/30/2021 22:35:20 - INFO - __main__ - Step 51894: {'lr': 0.0003724191373507206, 'samples': 9963648, 'steps': 51893, 'loss/train': 0.027184000238776207} 08/30/2021 22:35:21 - INFO - __main__ - Step 51895: {'lr': 0.00037241451035062965, 'samples': 9963840, 'steps': 51894, 'loss/train': 1.7417263984680176} 08/30/2021 22:35:21 - INFO - __main__ - Step 51896: {'lr': 0.0003724098832953806, 'samples': 9964032, 'steps': 51895, 'loss/train': 1.6496121883392334} 08/30/2021 22:35:22 - INFO - __main__ - Step 51897: {'lr': 0.00037240525618497555, 'samples': 9964224, 'steps': 51896, 'loss/train': 1.286798357963562} 08/30/2021 22:35:23 - INFO - __main__ - Step 51898: {'lr': 0.00037240062901941663, 'samples': 9964416, 'steps': 51897, 'loss/train': 1.3271620273590088} 08/30/2021 22:35:23 - INFO - __main__ - Step 51899: {'lr': 0.0003723960017987058, 'samples': 9964608, 'steps': 51898, 'loss/train': 1.5280787944793701} 08/30/2021 22:35:24 - INFO - __main__ - Step 51900: {'lr': 0.00037239137452284527, 'samples': 9964800, 'steps': 51899, 'loss/train': 2.311554193496704} 08/30/2021 22:35:24 - INFO - __main__ - Step 51901: {'lr': 0.0003723867471918371, 'samples': 9964992, 'steps': 51900, 'loss/train': 1.63205885887146} 08/30/2021 22:35:26 - INFO - __main__ - Step 51902: {'lr': 0.00037238211980568326, 'samples': 9965184, 'steps': 51901, 'loss/train': 1.3498841524124146} 08/30/2021 22:35:26 - INFO - __main__ - Step 51903: {'lr': 0.00037237749236438593, 'samples': 9965376, 'steps': 51902, 'loss/train': 1.3161925077438354} 08/30/2021 22:35:26 - INFO - __main__ - Step 51904: {'lr': 0.0003723728648679472, 'samples': 9965568, 'steps': 51903, 'loss/train': 0.850733757019043} 08/30/2021 22:35:27 - INFO - __main__ - Step 51905: {'lr': 0.0003723682373163693, 'samples': 9965760, 'steps': 51904, 'loss/train': 1.23153817653656} 08/30/2021 22:35:27 - INFO - __main__ - Step 51906: {'lr': 0.0003723636097096539, 'samples': 9965952, 'steps': 51905, 'loss/train': 1.7081217765808105} 08/30/2021 22:35:27 - INFO - __main__ - Step 51907: {'lr': 0.00037235898204780347, 'samples': 9966144, 'steps': 51906, 'loss/train': 0.5396932363510132} 08/30/2021 22:35:29 - INFO - __main__ - Step 51908: {'lr': 0.00037235435433082004, 'samples': 9966336, 'steps': 51907, 'loss/train': 1.856209397315979} 08/30/2021 22:35:29 - INFO - __main__ - Step 51909: {'lr': 0.0003723497265587055, 'samples': 9966528, 'steps': 51908, 'loss/train': 1.919226884841919} 08/30/2021 22:35:30 - INFO - __main__ - Step 51910: {'lr': 0.0003723450987314622, 'samples': 9966720, 'steps': 51909, 'loss/train': 1.2813091278076172} 08/30/2021 22:35:30 - INFO - __main__ - Step 51911: {'lr': 0.00037234047084909195, 'samples': 9966912, 'steps': 51910, 'loss/train': 1.027509331703186} 08/30/2021 22:35:31 - INFO - __main__ - Step 51912: {'lr': 0.0003723358429115971, 'samples': 9967104, 'steps': 51911, 'loss/train': 1.440931797027588} 08/30/2021 22:35:32 - INFO - __main__ - Step 51913: {'lr': 0.00037233121491897953, 'samples': 9967296, 'steps': 51912, 'loss/train': 1.0619441270828247} 08/30/2021 22:35:33 - INFO - __main__ - Step 51914: {'lr': 0.00037232658687124135, 'samples': 9967488, 'steps': 51913, 'loss/train': 0.057625818997621536} 08/30/2021 22:35:33 - INFO - __main__ - Step 51915: {'lr': 0.00037232195876838484, 'samples': 9967680, 'steps': 51914, 'loss/train': 1.4565588235855103} 08/30/2021 22:35:33 - INFO - __main__ - Step 51916: {'lr': 0.00037231733061041176, 'samples': 9967872, 'steps': 51915, 'loss/train': 0.8500802516937256} 08/30/2021 22:35:34 - INFO - __main__ - Step 51917: {'lr': 0.0003723127023973245, 'samples': 9968064, 'steps': 51916, 'loss/train': 2.0979974269866943} 08/30/2021 22:35:35 - INFO - __main__ - Step 51918: {'lr': 0.00037230807412912505, 'samples': 9968256, 'steps': 51917, 'loss/train': 1.2710801362991333} 08/30/2021 22:35:36 - INFO - __main__ - Step 51919: {'lr': 0.00037230344580581543, 'samples': 9968448, 'steps': 51918, 'loss/train': 1.476787805557251} 08/30/2021 22:35:36 - INFO - __main__ - Step 51920: {'lr': 0.00037229881742739776, 'samples': 9968640, 'steps': 51919, 'loss/train': 1.0626276731491089} 08/30/2021 22:35:36 - INFO - __main__ - Step 51921: {'lr': 0.0003722941889938741, 'samples': 9968832, 'steps': 51920, 'loss/train': 0.6248576641082764} 08/30/2021 22:35:37 - INFO - __main__ - Step 51922: {'lr': 0.0003722895605052466, 'samples': 9969024, 'steps': 51921, 'loss/train': 0.8725528717041016} 08/30/2021 22:35:37 - INFO - __main__ - Step 51923: {'lr': 0.0003722849319615173, 'samples': 9969216, 'steps': 51922, 'loss/train': 1.7207883596420288} 08/30/2021 22:35:39 - INFO - __main__ - Step 51924: {'lr': 0.0003722803033626883, 'samples': 9969408, 'steps': 51923, 'loss/train': 1.4032286405563354} 08/30/2021 22:35:39 - INFO - __main__ - Step 51925: {'lr': 0.0003722756747087617, 'samples': 9969600, 'steps': 51924, 'loss/train': 1.3273437023162842} 08/30/2021 22:35:40 - INFO - __main__ - Step 51926: {'lr': 0.0003722710459997395, 'samples': 9969792, 'steps': 51925, 'loss/train': 0.8548556566238403} 08/30/2021 22:35:40 - INFO - __main__ - Step 51927: {'lr': 0.00037226641723562393, 'samples': 9969984, 'steps': 51926, 'loss/train': 1.0427029132843018} 08/30/2021 22:35:40 - INFO - __main__ - Step 51928: {'lr': 0.000372261788416417, 'samples': 9970176, 'steps': 51927, 'loss/train': 0.09846016764640808} 08/30/2021 22:35:42 - INFO - __main__ - Step 51929: {'lr': 0.00037225715954212075, 'samples': 9970368, 'steps': 51928, 'loss/train': 0.4199332892894745} 08/30/2021 22:35:42 - INFO - __main__ - Step 51930: {'lr': 0.00037225253061273734, 'samples': 9970560, 'steps': 51929, 'loss/train': 1.4638190269470215} 08/30/2021 22:35:43 - INFO - __main__ - Step 51931: {'lr': 0.0003722479016282688, 'samples': 9970752, 'steps': 51930, 'loss/train': 0.0759798064827919} 08/30/2021 22:35:43 - INFO - __main__ - Step 51932: {'lr': 0.00037224327258871724, 'samples': 9970944, 'steps': 51931, 'loss/train': 1.5944095849990845} 08/30/2021 22:35:43 - INFO - __main__ - Step 51933: {'lr': 0.00037223864349408484, 'samples': 9971136, 'steps': 51932, 'loss/train': 1.1476593017578125} 08/30/2021 22:35:44 - INFO - __main__ - Step 51934: {'lr': 0.0003722340143443735, 'samples': 9971328, 'steps': 51933, 'loss/train': 1.0609651803970337} 08/30/2021 22:35:46 - INFO - __main__ - Step 51935: {'lr': 0.0003722293851395854, 'samples': 9971520, 'steps': 51934, 'loss/train': 1.1517436504364014} 08/30/2021 22:35:46 - INFO - __main__ - Step 51936: {'lr': 0.00037222475587972263, 'samples': 9971712, 'steps': 51935, 'loss/train': 0.8537135720252991} 08/30/2021 22:35:47 - INFO - __main__ - Step 51937: {'lr': 0.00037222012656478733, 'samples': 9971904, 'steps': 51936, 'loss/train': 0.8171143531799316} 08/30/2021 22:35:47 - INFO - __main__ - Step 51938: {'lr': 0.00037221549719478145, 'samples': 9972096, 'steps': 51937, 'loss/train': 1.122235655784607} 08/30/2021 22:35:48 - INFO - __main__ - Step 51939: {'lr': 0.0003722108677697072, 'samples': 9972288, 'steps': 51938, 'loss/train': 0.7304782867431641} 08/30/2021 22:35:49 - INFO - __main__ - Step 51940: {'lr': 0.00037220623828956655, 'samples': 9972480, 'steps': 51939, 'loss/train': 1.3031141757965088} 08/30/2021 22:35:50 - INFO - __main__ - Step 51941: {'lr': 0.00037220160875436176, 'samples': 9972672, 'steps': 51940, 'loss/train': 1.3918569087982178} 08/30/2021 22:35:50 - INFO - __main__ - Step 51942: {'lr': 0.0003721969791640948, 'samples': 9972864, 'steps': 51941, 'loss/train': 1.4810817241668701} 08/30/2021 22:35:50 - INFO - __main__ - Step 51943: {'lr': 0.0003721923495187677, 'samples': 9973056, 'steps': 51942, 'loss/train': 1.3126007318496704} 08/30/2021 22:35:51 - INFO - __main__ - Step 51944: {'lr': 0.00037218771981838264, 'samples': 9973248, 'steps': 51943, 'loss/train': 1.2253798246383667} 08/30/2021 22:35:51 - INFO - __main__ - Step 51945: {'lr': 0.0003721830900629416, 'samples': 9973440, 'steps': 51944, 'loss/train': 2.083449363708496} 08/30/2021 22:35:53 - INFO - __main__ - Step 51946: {'lr': 0.00037217846025244686, 'samples': 9973632, 'steps': 51945, 'loss/train': 1.0989153385162354} 08/30/2021 22:35:53 - INFO - __main__ - Step 51947: {'lr': 0.0003721738303869004, 'samples': 9973824, 'steps': 51946, 'loss/train': 1.8225184679031372} 08/30/2021 22:35:53 - INFO - __main__ - Step 51948: {'lr': 0.0003721692004663042, 'samples': 9974016, 'steps': 51947, 'loss/train': 0.9767679572105408} 08/30/2021 22:35:54 - INFO - __main__ - Step 51949: {'lr': 0.0003721645704906605, 'samples': 9974208, 'steps': 51948, 'loss/train': 1.4346401691436768} 08/30/2021 22:35:54 - INFO - __main__ - Step 51950: {'lr': 0.0003721599404599713, 'samples': 9974400, 'steps': 51949, 'loss/train': 0.3948131501674652} 08/30/2021 22:35:56 - INFO - __main__ - Step 51951: {'lr': 0.0003721553103742388, 'samples': 9974592, 'steps': 51950, 'loss/train': 1.1726425886154175} 08/30/2021 22:35:56 - INFO - __main__ - Step 51952: {'lr': 0.00037215068023346495, 'samples': 9974784, 'steps': 51951, 'loss/train': 1.3587422370910645} 08/30/2021 22:35:57 - INFO - __main__ - Step 51953: {'lr': 0.0003721460500376518, 'samples': 9974976, 'steps': 51952, 'loss/train': 1.444991111755371} 08/30/2021 22:35:57 - INFO - __main__ - Step 51954: {'lr': 0.00037214141978680166, 'samples': 9975168, 'steps': 51953, 'loss/train': 1.0682071447372437} 08/30/2021 22:35:57 - INFO - __main__ - Step 51955: {'lr': 0.00037213678948091637, 'samples': 9975360, 'steps': 51954, 'loss/train': 1.6608946323394775} 08/30/2021 22:35:59 - INFO - __main__ - Step 51956: {'lr': 0.0003721321591199982, 'samples': 9975552, 'steps': 51955, 'loss/train': 0.06225641071796417} 08/30/2021 22:36:00 - INFO - __main__ - Step 51957: {'lr': 0.00037212752870404917, 'samples': 9975744, 'steps': 51956, 'loss/train': 1.4211546182632446} 08/30/2021 22:36:00 - INFO - __main__ - Step 51958: {'lr': 0.0003721228982330713, 'samples': 9975936, 'steps': 51957, 'loss/train': 1.5941846370697021} 08/30/2021 22:36:00 - INFO - __main__ - Step 51959: {'lr': 0.0003721182677070668, 'samples': 9976128, 'steps': 51958, 'loss/train': 0.2025655210018158} 08/30/2021 22:36:01 - INFO - __main__ - Step 51960: {'lr': 0.00037211363712603767, 'samples': 9976320, 'steps': 51959, 'loss/train': 1.375752329826355} 08/30/2021 22:36:02 - INFO - __main__ - Step 51961: {'lr': 0.00037210900648998604, 'samples': 9976512, 'steps': 51960, 'loss/train': 0.9909582734107971} 08/30/2021 22:36:03 - INFO - __main__ - Step 51962: {'lr': 0.0003721043757989139, 'samples': 9976704, 'steps': 51961, 'loss/train': 1.0279664993286133} 08/30/2021 22:36:03 - INFO - __main__ - Step 51963: {'lr': 0.0003720997450528235, 'samples': 9976896, 'steps': 51962, 'loss/train': 1.1620796918869019} 08/30/2021 22:36:03 - INFO - __main__ - Step 51964: {'lr': 0.0003720951142517168, 'samples': 9977088, 'steps': 51963, 'loss/train': 1.258919596672058} 08/30/2021 22:36:04 - INFO - __main__ - Step 51965: {'lr': 0.0003720904833955959, 'samples': 9977280, 'steps': 51964, 'loss/train': 1.443966031074524} 08/30/2021 22:36:05 - INFO - __main__ - Step 51966: {'lr': 0.000372085852484463, 'samples': 9977472, 'steps': 51965, 'loss/train': 1.1282204389572144} 08/30/2021 22:36:06 - INFO - __main__ - Step 51967: {'lr': 0.00037208122151832004, 'samples': 9977664, 'steps': 51966, 'loss/train': 1.1799874305725098} 08/30/2021 22:36:06 - INFO - __main__ - Step 51968: {'lr': 0.0003720765904971691, 'samples': 9977856, 'steps': 51967, 'loss/train': 1.1374404430389404} 08/30/2021 22:36:06 - INFO - __main__ - Step 51969: {'lr': 0.0003720719594210124, 'samples': 9978048, 'steps': 51968, 'loss/train': 2.00117826461792} 08/30/2021 22:36:07 - INFO - __main__ - Step 51970: {'lr': 0.00037206732828985197, 'samples': 9978240, 'steps': 51969, 'loss/train': 0.6365982294082642} 08/30/2021 22:36:08 - INFO - __main__ - Step 51971: {'lr': 0.00037206269710368987, 'samples': 9978432, 'steps': 51970, 'loss/train': 1.8698856830596924} 08/30/2021 22:36:09 - INFO - __main__ - Step 51972: {'lr': 0.0003720580658625282, 'samples': 9978624, 'steps': 51971, 'loss/train': 1.4233675003051758} 08/30/2021 22:36:09 - INFO - __main__ - Step 51973: {'lr': 0.00037205343456636907, 'samples': 9978816, 'steps': 51972, 'loss/train': 1.457370638847351} 08/30/2021 22:36:10 - INFO - __main__ - Step 51974: {'lr': 0.0003720488032152145, 'samples': 9979008, 'steps': 51973, 'loss/train': 0.949581503868103} 08/30/2021 22:36:10 - INFO - __main__ - Step 51975: {'lr': 0.0003720441718090667, 'samples': 9979200, 'steps': 51974, 'loss/train': 0.05510852485895157} 08/30/2021 22:36:12 - INFO - __main__ - Step 51976: {'lr': 0.0003720395403479276, 'samples': 9979392, 'steps': 51975, 'loss/train': 1.61943781375885} 08/30/2021 22:36:12 - INFO - __main__ - Step 51977: {'lr': 0.00037203490883179935, 'samples': 9979584, 'steps': 51976, 'loss/train': 1.7899806499481201} 08/30/2021 22:36:12 - INFO - __main__ - Step 51978: {'lr': 0.0003720302772606841, 'samples': 9979776, 'steps': 51977, 'loss/train': 1.0794782638549805} 08/30/2021 22:36:13 - INFO - __main__ - Step 51979: {'lr': 0.00037202564563458394, 'samples': 9979968, 'steps': 51978, 'loss/train': 1.0243253707885742} 08/30/2021 22:36:13 - INFO - __main__ - Step 51980: {'lr': 0.00037202101395350084, 'samples': 9980160, 'steps': 51979, 'loss/train': 1.1207071542739868} 08/30/2021 22:36:13 - INFO - __main__ - Step 51981: {'lr': 0.0003720163822174369, 'samples': 9980352, 'steps': 51980, 'loss/train': 1.4508756399154663} 08/30/2021 22:36:15 - INFO - __main__ - Step 51982: {'lr': 0.0003720117504263944, 'samples': 9980544, 'steps': 51981, 'loss/train': 0.9407844543457031} 08/30/2021 22:36:15 - INFO - __main__ - Step 51983: {'lr': 0.0003720071185803752, 'samples': 9980736, 'steps': 51982, 'loss/train': 1.5013949871063232} 08/30/2021 22:36:16 - INFO - __main__ - Step 51984: {'lr': 0.00037200248667938155, 'samples': 9980928, 'steps': 51983, 'loss/train': 1.2867027521133423} 08/30/2021 22:36:16 - INFO - __main__ - Step 51985: {'lr': 0.00037199785472341536, 'samples': 9981120, 'steps': 51984, 'loss/train': 0.037992969155311584} 08/30/2021 22:36:16 - INFO - __main__ - Step 51986: {'lr': 0.00037199322271247887, 'samples': 9981312, 'steps': 51985, 'loss/train': 0.4052225947380066} 08/30/2021 22:36:19 - INFO - __main__ - Step 51987: {'lr': 0.00037198859064657415, 'samples': 9981504, 'steps': 51986, 'loss/train': 1.1930993795394897} 08/30/2021 22:36:19 - INFO - __main__ - Step 51988: {'lr': 0.0003719839585257032, 'samples': 9981696, 'steps': 51987, 'loss/train': 1.5854802131652832} 08/30/2021 22:36:19 - INFO - __main__ - Step 51989: {'lr': 0.0003719793263498681, 'samples': 9981888, 'steps': 51988, 'loss/train': 0.11612052470445633} 08/30/2021 22:36:20 - INFO - __main__ - Step 51990: {'lr': 0.00037197469411907115, 'samples': 9982080, 'steps': 51989, 'loss/train': 1.6547197103500366} 08/30/2021 22:36:20 - INFO - __main__ - Step 51991: {'lr': 0.0003719700618333142, 'samples': 9982272, 'steps': 51990, 'loss/train': 1.1363204717636108} 08/30/2021 22:36:20 - INFO - __main__ - Step 51992: {'lr': 0.0003719654294925994, 'samples': 9982464, 'steps': 51991, 'loss/train': 0.4997813105583191} 08/30/2021 22:36:22 - INFO - __main__ - Step 51993: {'lr': 0.00037196079709692894, 'samples': 9982656, 'steps': 51992, 'loss/train': 1.7195322513580322} 08/30/2021 22:36:23 - INFO - __main__ - Step 51994: {'lr': 0.0003719561646463048, 'samples': 9982848, 'steps': 51993, 'loss/train': 1.1932653188705444} 08/30/2021 22:36:23 - INFO - __main__ - Step 51995: {'lr': 0.00037195153214072903, 'samples': 9983040, 'steps': 51994, 'loss/train': 1.6880711317062378} 08/30/2021 22:36:23 - INFO - __main__ - Step 51996: {'lr': 0.0003719468995802038, 'samples': 9983232, 'steps': 51995, 'loss/train': 0.8421748280525208} 08/30/2021 22:36:24 - INFO - __main__ - Step 51997: {'lr': 0.0003719422669647312, 'samples': 9983424, 'steps': 51996, 'loss/train': 1.7453234195709229} 08/30/2021 22:36:25 - INFO - __main__ - Step 51998: {'lr': 0.0003719376342943133, 'samples': 9983616, 'steps': 51997, 'loss/train': 1.647517442703247} 08/30/2021 22:36:26 - INFO - __main__ - Step 51999: {'lr': 0.00037193300156895223, 'samples': 9983808, 'steps': 51998, 'loss/train': 1.2749403715133667} 08/30/2021 22:36:26 - INFO - __main__ - Step 52000: {'lr': 0.00037192836878864995, 'samples': 9984000, 'steps': 51999, 'loss/train': 0.9716050624847412} 08/30/2021 22:36:26 - INFO - __main__ - Step 52001: {'lr': 0.00037192373595340864, 'samples': 9984192, 'steps': 52000, 'loss/train': 1.064461350440979} 08/30/2021 22:36:27 - INFO - __main__ - Step 52002: {'lr': 0.0003719191030632304, 'samples': 9984384, 'steps': 52001, 'loss/train': 0.6413258910179138} 08/30/2021 22:36:28 - INFO - __main__ - Step 52003: {'lr': 0.0003719144701181173, 'samples': 9984576, 'steps': 52002, 'loss/train': 2.2944822311401367} 08/30/2021 22:36:29 - INFO - __main__ - Step 52004: {'lr': 0.0003719098371180714, 'samples': 9984768, 'steps': 52003, 'loss/train': 1.0969287157058716} 08/30/2021 22:36:29 - INFO - __main__ - Step 52005: {'lr': 0.00037190520406309483, 'samples': 9984960, 'steps': 52004, 'loss/train': 0.8896622061729431} 08/30/2021 22:36:29 - INFO - __main__ - Step 52006: {'lr': 0.00037190057095318966, 'samples': 9985152, 'steps': 52005, 'loss/train': 1.1797174215316772} 08/30/2021 22:36:30 - INFO - __main__ - Step 52007: {'lr': 0.00037189593778835794, 'samples': 9985344, 'steps': 52006, 'loss/train': 1.0873112678527832} 08/30/2021 22:36:30 - INFO - __main__ - Step 52008: {'lr': 0.0003718913045686018, 'samples': 9985536, 'steps': 52007, 'loss/train': 1.479310154914856} 08/30/2021 22:36:33 - INFO - __main__ - Step 52009: {'lr': 0.0003718866712939233, 'samples': 9985728, 'steps': 52008, 'loss/train': 0.2769359350204468} 08/30/2021 22:36:33 - INFO - __main__ - Step 52010: {'lr': 0.00037188203796432464, 'samples': 9985920, 'steps': 52009, 'loss/train': 1.4753742218017578} 08/30/2021 22:36:34 - INFO - __main__ - Step 52011: {'lr': 0.00037187740457980776, 'samples': 9986112, 'steps': 52010, 'loss/train': 0.6255351901054382} 08/30/2021 22:36:34 - INFO - __main__ - Step 52012: {'lr': 0.0003718727711403748, 'samples': 9986304, 'steps': 52011, 'loss/train': 1.1509250402450562} 08/30/2021 22:36:34 - INFO - __main__ - Step 52013: {'lr': 0.00037186813764602785, 'samples': 9986496, 'steps': 52012, 'loss/train': 1.5531744956970215} 08/30/2021 22:36:35 - INFO - __main__ - Step 52014: {'lr': 0.00037186350409676894, 'samples': 9986688, 'steps': 52013, 'loss/train': 1.7630598545074463} 08/30/2021 22:36:35 - INFO - __main__ - Step 52015: {'lr': 0.00037185887049260023, 'samples': 9986880, 'steps': 52014, 'loss/train': 0.562222421169281} 08/30/2021 22:36:37 - INFO - __main__ - Step 52016: {'lr': 0.0003718542368335239, 'samples': 9987072, 'steps': 52015, 'loss/train': 0.5183826088905334} 08/30/2021 22:36:37 - INFO - __main__ - Step 52017: {'lr': 0.0003718496031195419, 'samples': 9987264, 'steps': 52016, 'loss/train': 1.7556639909744263} 08/30/2021 22:36:37 - INFO - __main__ - Step 52018: {'lr': 0.00037184496935065625, 'samples': 9987456, 'steps': 52017, 'loss/train': 1.5615830421447754} 08/30/2021 22:36:38 - INFO - __main__ - Step 52019: {'lr': 0.0003718403355268692, 'samples': 9987648, 'steps': 52018, 'loss/train': 0.07880722731351852} 08/30/2021 22:36:38 - INFO - __main__ - Step 52020: {'lr': 0.0003718357016481828, 'samples': 9987840, 'steps': 52019, 'loss/train': 0.891784131526947} 08/30/2021 22:36:40 - INFO - __main__ - Step 52021: {'lr': 0.00037183106771459905, 'samples': 9988032, 'steps': 52020, 'loss/train': 1.7741683721542358} 08/30/2021 22:36:40 - INFO - __main__ - Step 52022: {'lr': 0.00037182643372612014, 'samples': 9988224, 'steps': 52021, 'loss/train': 1.2698322534561157} 08/30/2021 22:36:40 - INFO - __main__ - Step 52023: {'lr': 0.00037182179968274807, 'samples': 9988416, 'steps': 52022, 'loss/train': 4.820176124572754} 08/30/2021 22:36:41 - INFO - __main__ - Step 52024: {'lr': 0.00037181716558448507, 'samples': 9988608, 'steps': 52023, 'loss/train': 1.3155553340911865} 08/30/2021 22:36:41 - INFO - __main__ - Step 52025: {'lr': 0.0003718125314313331, 'samples': 9988800, 'steps': 52024, 'loss/train': 1.8372255563735962} 08/30/2021 22:36:42 - INFO - __main__ - Step 52026: {'lr': 0.0003718078972232943, 'samples': 9988992, 'steps': 52025, 'loss/train': 1.7179555892944336} 08/30/2021 22:36:43 - INFO - __main__ - Step 52027: {'lr': 0.0003718032629603707, 'samples': 9989184, 'steps': 52026, 'loss/train': 1.6634650230407715} 08/30/2021 22:36:43 - INFO - __main__ - Step 52028: {'lr': 0.00037179862864256444, 'samples': 9989376, 'steps': 52027, 'loss/train': 1.3627899885177612} 08/30/2021 22:36:44 - INFO - __main__ - Step 52029: {'lr': 0.00037179399426987757, 'samples': 9989568, 'steps': 52028, 'loss/train': 0.6802630424499512} 08/30/2021 22:36:44 - INFO - __main__ - Step 52030: {'lr': 0.0003717893598423122, 'samples': 9989760, 'steps': 52029, 'loss/train': 1.467929720878601} 08/30/2021 22:36:45 - INFO - __main__ - Step 52031: {'lr': 0.0003717847253598705, 'samples': 9989952, 'steps': 52030, 'loss/train': 1.5111241340637207} 08/30/2021 22:36:46 - INFO - __main__ - Step 52032: {'lr': 0.0003717800908225544, 'samples': 9990144, 'steps': 52031, 'loss/train': 0.6221545338630676} 08/30/2021 22:36:46 - INFO - __main__ - Step 52033: {'lr': 0.0003717754562303661, 'samples': 9990336, 'steps': 52032, 'loss/train': 1.3588640689849854} 08/30/2021 22:36:47 - INFO - __main__ - Step 52034: {'lr': 0.00037177082158330773, 'samples': 9990528, 'steps': 52033, 'loss/train': 1.880616307258606} 08/30/2021 22:36:47 - INFO - __main__ - Step 52035: {'lr': 0.0003717661868813812, 'samples': 9990720, 'steps': 52034, 'loss/train': 1.8729760646820068} 08/30/2021 22:36:49 - INFO - __main__ - Step 52036: {'lr': 0.00037176155212458875, 'samples': 9990912, 'steps': 52035, 'loss/train': 1.0188407897949219} 08/30/2021 22:36:49 - INFO - __main__ - Step 52037: {'lr': 0.0003717569173129324, 'samples': 9991104, 'steps': 52036, 'loss/train': 1.1100980043411255} 08/30/2021 22:36:50 - INFO - __main__ - Step 52038: {'lr': 0.0003717522824464143, 'samples': 9991296, 'steps': 52037, 'loss/train': 1.7405463457107544} 08/30/2021 22:36:50 - INFO - __main__ - Step 52039: {'lr': 0.0003717476475250365, 'samples': 9991488, 'steps': 52038, 'loss/train': 1.369011640548706} 08/30/2021 22:36:50 - INFO - __main__ - Step 52040: {'lr': 0.0003717430125488011, 'samples': 9991680, 'steps': 52039, 'loss/train': 1.4352734088897705} 08/30/2021 22:36:51 - INFO - __main__ - Step 52041: {'lr': 0.0003717383775177101, 'samples': 9991872, 'steps': 52040, 'loss/train': 1.677634835243225} 08/30/2021 22:36:52 - INFO - __main__ - Step 52042: {'lr': 0.0003717337424317657, 'samples': 9992064, 'steps': 52041, 'loss/train': 1.1222599744796753} 08/30/2021 22:36:53 - INFO - __main__ - Step 52043: {'lr': 0.00037172910729097006, 'samples': 9992256, 'steps': 52042, 'loss/train': 1.6967636346817017} 08/30/2021 22:36:53 - INFO - __main__ - Step 52044: {'lr': 0.000371724472095325, 'samples': 9992448, 'steps': 52043, 'loss/train': 1.6835474967956543} 08/30/2021 22:36:54 - INFO - __main__ - Step 52045: {'lr': 0.00037171983684483286, 'samples': 9992640, 'steps': 52044, 'loss/train': 1.676937222480774} 08/30/2021 22:36:54 - INFO - __main__ - Step 52046: {'lr': 0.00037171520153949565, 'samples': 9992832, 'steps': 52045, 'loss/train': 1.9934661388397217} 08/30/2021 22:36:54 - INFO - __main__ - Step 52047: {'lr': 0.00037171056617931543, 'samples': 9993024, 'steps': 52046, 'loss/train': 1.194975733757019} 08/30/2021 22:36:56 - INFO - __main__ - Step 52048: {'lr': 0.00037170593076429426, 'samples': 9993216, 'steps': 52047, 'loss/train': 0.9336037039756775} 08/30/2021 22:36:57 - INFO - __main__ - Step 52049: {'lr': 0.00037170129529443436, 'samples': 9993408, 'steps': 52048, 'loss/train': 1.780676245689392} 08/30/2021 22:36:57 - INFO - __main__ - Step 52050: {'lr': 0.0003716966597697377, 'samples': 9993600, 'steps': 52049, 'loss/train': 1.480969786643982} 08/30/2021 22:36:58 - INFO - __main__ - Step 52051: {'lr': 0.0003716920241902064, 'samples': 9993792, 'steps': 52050, 'loss/train': 1.4542555809020996} 08/30/2021 22:36:58 - INFO - __main__ - Step 52052: {'lr': 0.0003716873885558425, 'samples': 9993984, 'steps': 52051, 'loss/train': 1.0908305644989014} 08/30/2021 22:37:00 - INFO - __main__ - Step 52053: {'lr': 0.0003716827528666482, 'samples': 9994176, 'steps': 52052, 'loss/train': 1.7947149276733398} 08/30/2021 22:37:00 - INFO - __main__ - Step 52054: {'lr': 0.0003716781171226255, 'samples': 9994368, 'steps': 52053, 'loss/train': 1.534867286682129} 08/30/2021 22:37:00 - INFO - __main__ - Step 52055: {'lr': 0.00037167348132377656, 'samples': 9994560, 'steps': 52054, 'loss/train': 1.3611438274383545} 08/30/2021 22:37:01 - INFO - __main__ - Step 52056: {'lr': 0.0003716688454701034, 'samples': 9994752, 'steps': 52055, 'loss/train': 1.6660186052322388} 08/30/2021 22:37:01 - INFO - __main__ - Step 52057: {'lr': 0.00037166420956160815, 'samples': 9994944, 'steps': 52056, 'loss/train': 1.7995336055755615} 08/30/2021 22:37:03 - INFO - __main__ - Step 52058: {'lr': 0.0003716595735982928, 'samples': 9995136, 'steps': 52057, 'loss/train': 0.8728925585746765} 08/30/2021 22:37:03 - INFO - __main__ - Step 52059: {'lr': 0.0003716549375801597, 'samples': 9995328, 'steps': 52058, 'loss/train': 1.3943653106689453} 08/30/2021 22:37:04 - INFO - __main__ - Step 52060: {'lr': 0.0003716503015072106, 'samples': 9995520, 'steps': 52059, 'loss/train': 1.5521290302276611} 08/30/2021 22:37:04 - INFO - __main__ - Step 52061: {'lr': 0.00037164566537944776, 'samples': 9995712, 'steps': 52060, 'loss/train': 1.5097190141677856} 08/30/2021 22:37:04 - INFO - __main__ - Step 52062: {'lr': 0.00037164102919687335, 'samples': 9995904, 'steps': 52061, 'loss/train': 1.5647640228271484} 08/30/2021 22:37:06 - INFO - __main__ - Step 52063: {'lr': 0.00037163639295948933, 'samples': 9996096, 'steps': 52062, 'loss/train': 0.07066015899181366} 08/30/2021 22:37:07 - INFO - __main__ - Step 52064: {'lr': 0.0003716317566672978, 'samples': 9996288, 'steps': 52063, 'loss/train': 1.2351046800613403} 08/30/2021 22:37:07 - INFO - __main__ - Step 52065: {'lr': 0.00037162712032030095, 'samples': 9996480, 'steps': 52064, 'loss/train': 1.1107736825942993} 08/30/2021 22:37:07 - INFO - __main__ - Step 52066: {'lr': 0.00037162248391850076, 'samples': 9996672, 'steps': 52065, 'loss/train': 1.7825418710708618} 08/30/2021 22:37:08 - INFO - __main__ - Step 52067: {'lr': 0.0003716178474618993, 'samples': 9996864, 'steps': 52066, 'loss/train': 0.6627397537231445} 08/30/2021 22:37:09 - INFO - __main__ - Step 52068: {'lr': 0.0003716132109504988, 'samples': 9997056, 'steps': 52067, 'loss/train': 1.4266213178634644} 08/30/2021 22:37:10 - INFO - __main__ - Step 52069: {'lr': 0.0003716085743843012, 'samples': 9997248, 'steps': 52068, 'loss/train': 1.1553900241851807} 08/30/2021 22:37:10 - INFO - __main__ - Step 52070: {'lr': 0.0003716039377633087, 'samples': 9997440, 'steps': 52069, 'loss/train': 1.0581462383270264} 08/30/2021 22:37:10 - INFO - __main__ - Step 52071: {'lr': 0.00037159930108752326, 'samples': 9997632, 'steps': 52070, 'loss/train': 1.471582055091858} 08/30/2021 22:37:11 - INFO - __main__ - Step 52072: {'lr': 0.0003715946643569471, 'samples': 9997824, 'steps': 52071, 'loss/train': 1.2319146394729614} 08/30/2021 22:37:11 - INFO - __main__ - Step 52073: {'lr': 0.0003715900275715823, 'samples': 9998016, 'steps': 52072, 'loss/train': 1.4516321420669556} 08/30/2021 22:37:12 - INFO - __main__ - Step 52074: {'lr': 0.0003715853907314309, 'samples': 9998208, 'steps': 52073, 'loss/train': 1.4245095252990723} 08/30/2021 22:37:13 - INFO - __main__ - Step 52075: {'lr': 0.0003715807538364949, 'samples': 9998400, 'steps': 52074, 'loss/train': 1.6345106363296509} 08/30/2021 22:37:13 - INFO - __main__ - Step 52076: {'lr': 0.00037157611688677666, 'samples': 9998592, 'steps': 52075, 'loss/train': 0.7477751970291138} 08/30/2021 22:37:14 - INFO - __main__ - Step 52077: {'lr': 0.000371571479882278, 'samples': 9998784, 'steps': 52076, 'loss/train': 1.1907473802566528} 08/30/2021 22:37:14 - INFO - __main__ - Step 52078: {'lr': 0.00037156684282300105, 'samples': 9998976, 'steps': 52077, 'loss/train': 0.293177992105484} 08/30/2021 22:37:15 - INFO - __main__ - Step 52079: {'lr': 0.00037156220570894806, 'samples': 9999168, 'steps': 52078, 'loss/train': 1.0104323625564575} 08/30/2021 22:37:16 - INFO - __main__ - Step 52080: {'lr': 0.00037155756854012097, 'samples': 9999360, 'steps': 52079, 'loss/train': 1.7753924131393433} 08/30/2021 22:37:16 - INFO - __main__ - Step 52081: {'lr': 0.000371552931316522, 'samples': 9999552, 'steps': 52080, 'loss/train': 1.3313931226730347} 08/30/2021 22:37:17 - INFO - __main__ - Step 52082: {'lr': 0.00037154829403815307, 'samples': 9999744, 'steps': 52081, 'loss/train': 0.6239817142486572} 08/30/2021 22:37:17 - INFO - __main__ - Step 52083: {'lr': 0.0003715436567050163, 'samples': 9999936, 'steps': 52082, 'loss/train': 1.0077084302902222} 08/30/2021 22:37:18 - INFO - __main__ - Step 52084: {'lr': 0.0003715390193171139, 'samples': 10000128, 'steps': 52083, 'loss/train': 1.0066760778427124} 08/30/2021 22:37:19 - INFO - __main__ - Step 52085: {'lr': 0.0003715343818744479, 'samples': 10000320, 'steps': 52084, 'loss/train': 1.5821036100387573} 08/30/2021 22:37:19 - INFO - __main__ - Step 52086: {'lr': 0.0003715297443770203, 'samples': 10000512, 'steps': 52085, 'loss/train': 1.5655094385147095} 08/30/2021 22:37:20 - INFO - __main__ - Step 52087: {'lr': 0.0003715251068248334, 'samples': 10000704, 'steps': 52086, 'loss/train': 1.7501640319824219} 08/30/2021 22:37:20 - INFO - __main__ - Step 52088: {'lr': 0.00037152046921788906, 'samples': 10000896, 'steps': 52087, 'loss/train': 1.6460504531860352} 08/30/2021 22:37:21 - INFO - __main__ - Step 52089: {'lr': 0.00037151583155618957, 'samples': 10001088, 'steps': 52088, 'loss/train': 1.6560243368148804} 08/30/2021 22:37:22 - INFO - __main__ - Step 52090: {'lr': 0.00037151119383973684, 'samples': 10001280, 'steps': 52089, 'loss/train': 1.2341288328170776} 08/30/2021 22:37:22 - INFO - __main__ - Step 52091: {'lr': 0.0003715065560685331, 'samples': 10001472, 'steps': 52090, 'loss/train': 0.990084171295166} 08/30/2021 22:37:23 - INFO - __main__ - Step 52092: {'lr': 0.00037150191824258027, 'samples': 10001664, 'steps': 52091, 'loss/train': 1.0835883617401123} 08/30/2021 22:37:23 - INFO - __main__ - Step 52093: {'lr': 0.00037149728036188067, 'samples': 10001856, 'steps': 52092, 'loss/train': 1.2725456953048706} 08/30/2021 22:37:25 - INFO - __main__ - Step 52094: {'lr': 0.0003714926424264363, 'samples': 10002048, 'steps': 52093, 'loss/train': 1.4082059860229492} 08/30/2021 22:37:25 - INFO - __main__ - Step 52095: {'lr': 0.00037148800443624906, 'samples': 10002240, 'steps': 52094, 'loss/train': 1.820439100265503} 08/30/2021 22:37:25 - INFO - __main__ - Step 52096: {'lr': 0.0003714833663913213, 'samples': 10002432, 'steps': 52095, 'loss/train': 1.0115790367126465} 08/30/2021 22:37:26 - INFO - __main__ - Step 52097: {'lr': 0.00037147872829165497, 'samples': 10002624, 'steps': 52096, 'loss/train': 1.428789734840393} 08/30/2021 22:37:26 - INFO - __main__ - Step 52098: {'lr': 0.00037147409013725226, 'samples': 10002816, 'steps': 52097, 'loss/train': 1.3908092975616455} 08/30/2021 22:37:29 - INFO - __main__ - Step 52099: {'lr': 0.00037146945192811513, 'samples': 10003008, 'steps': 52098, 'loss/train': 1.1992634534835815} 08/30/2021 22:37:29 - INFO - __main__ - Step 52100: {'lr': 0.00037146481366424585, 'samples': 10003200, 'steps': 52099, 'loss/train': 2.1207642555236816} 08/30/2021 22:37:29 - INFO - __main__ - Step 52101: {'lr': 0.0003714601753456463, 'samples': 10003392, 'steps': 52100, 'loss/train': 1.0706340074539185} 08/30/2021 22:37:30 - INFO - __main__ - Step 52102: {'lr': 0.0003714555369723187, 'samples': 10003584, 'steps': 52101, 'loss/train': 1.0396418571472168} 08/30/2021 22:37:30 - INFO - __main__ - Step 52103: {'lr': 0.00037145089854426504, 'samples': 10003776, 'steps': 52102, 'loss/train': 1.6776082515716553} 08/30/2021 22:37:30 - INFO - __main__ - Step 52104: {'lr': 0.0003714462600614876, 'samples': 10003968, 'steps': 52103, 'loss/train': 1.7215911149978638} 08/30/2021 22:37:31 - INFO - __main__ - Step 52105: {'lr': 0.0003714416215239883, 'samples': 10004160, 'steps': 52104, 'loss/train': 1.7245113849639893} 08/30/2021 22:37:32 - INFO - __main__ - Step 52106: {'lr': 0.00037143698293176923, 'samples': 10004352, 'steps': 52105, 'loss/train': 1.390758752822876} 08/30/2021 22:37:33 - INFO - __main__ - Step 52107: {'lr': 0.0003714323442848326, 'samples': 10004544, 'steps': 52106, 'loss/train': 1.1921907663345337} 08/30/2021 22:37:33 - INFO - __main__ - Step 52108: {'lr': 0.0003714277055831804, 'samples': 10004736, 'steps': 52107, 'loss/train': 0.7346904277801514} 08/30/2021 22:37:33 - INFO - __main__ - Step 52109: {'lr': 0.00037142306682681476, 'samples': 10004928, 'steps': 52108, 'loss/train': 1.2465084791183472} 08/30/2021 22:37:34 - INFO - __main__ - Step 52110: {'lr': 0.00037141842801573775, 'samples': 10005120, 'steps': 52109, 'loss/train': 1.4384232759475708} 08/30/2021 22:37:35 - INFO - __main__ - Step 52111: {'lr': 0.00037141378914995146, 'samples': 10005312, 'steps': 52110, 'loss/train': 1.146830439567566} 08/30/2021 22:37:36 - INFO - __main__ - Step 52112: {'lr': 0.000371409150229458, 'samples': 10005504, 'steps': 52111, 'loss/train': 1.3251440525054932} 08/30/2021 22:37:36 - INFO - __main__ - Step 52113: {'lr': 0.00037140451125425945, 'samples': 10005696, 'steps': 52112, 'loss/train': 1.4773778915405273} 08/30/2021 22:37:36 - INFO - __main__ - Step 52114: {'lr': 0.0003713998722243579, 'samples': 10005888, 'steps': 52113, 'loss/train': 1.0111289024353027} 08/30/2021 22:37:37 - INFO - __main__ - Step 52115: {'lr': 0.00037139523313975544, 'samples': 10006080, 'steps': 52114, 'loss/train': 1.1920995712280273} 08/30/2021 22:37:38 - INFO - __main__ - Step 52116: {'lr': 0.00037139059400045416, 'samples': 10006272, 'steps': 52115, 'loss/train': 1.3523542881011963} 08/30/2021 22:37:39 - INFO - __main__ - Step 52117: {'lr': 0.00037138595480645613, 'samples': 10006464, 'steps': 52116, 'loss/train': 1.4828168153762817} 08/30/2021 22:37:39 - INFO - __main__ - Step 52118: {'lr': 0.0003713813155577635, 'samples': 10006656, 'steps': 52117, 'loss/train': 1.3772011995315552} 08/30/2021 22:37:39 - INFO - __main__ - Step 52119: {'lr': 0.0003713766762543783, 'samples': 10006848, 'steps': 52118, 'loss/train': 0.9362785220146179} 08/30/2021 22:37:40 - INFO - __main__ - Step 52120: {'lr': 0.0003713720368963027, 'samples': 10007040, 'steps': 52119, 'loss/train': 0.9265331029891968} 08/30/2021 22:37:41 - INFO - __main__ - Step 52121: {'lr': 0.0003713673974835387, 'samples': 10007232, 'steps': 52120, 'loss/train': 1.0374274253845215} 08/30/2021 22:37:42 - INFO - __main__ - Step 52122: {'lr': 0.0003713627580160884, 'samples': 10007424, 'steps': 52121, 'loss/train': 0.9954937696456909} 08/30/2021 22:37:42 - INFO - __main__ - Step 52123: {'lr': 0.0003713581184939539, 'samples': 10007616, 'steps': 52122, 'loss/train': 0.8861151933670044} 08/30/2021 22:37:42 - INFO - __main__ - Step 52124: {'lr': 0.00037135347891713733, 'samples': 10007808, 'steps': 52123, 'loss/train': 1.0496761798858643} 08/30/2021 22:37:43 - INFO - __main__ - Step 52125: {'lr': 0.00037134883928564074, 'samples': 10008000, 'steps': 52124, 'loss/train': 0.9004316926002502} 08/30/2021 22:37:44 - INFO - __main__ - Step 52126: {'lr': 0.00037134419959946626, 'samples': 10008192, 'steps': 52125, 'loss/train': 0.8226781487464905} 08/30/2021 22:37:45 - INFO - __main__ - Step 52127: {'lr': 0.00037133955985861595, 'samples': 10008384, 'steps': 52126, 'loss/train': 1.577428936958313} 08/30/2021 22:37:45 - INFO - __main__ - Step 52128: {'lr': 0.00037133492006309187, 'samples': 10008576, 'steps': 52127, 'loss/train': 1.1534955501556396} 08/30/2021 22:37:45 - INFO - __main__ - Step 52129: {'lr': 0.00037133028021289625, 'samples': 10008768, 'steps': 52128, 'loss/train': 1.4131879806518555} 08/30/2021 22:37:46 - INFO - __main__ - Step 52130: {'lr': 0.000371325640308031, 'samples': 10008960, 'steps': 52129, 'loss/train': 1.516191840171814} 08/30/2021 22:37:47 - INFO - __main__ - Step 52131: {'lr': 0.0003713210003484982, 'samples': 10009152, 'steps': 52130, 'loss/train': 0.9559731483459473} 08/30/2021 22:37:48 - INFO - __main__ - Step 52132: {'lr': 0.00037131636033430017, 'samples': 10009344, 'steps': 52131, 'loss/train': 1.8400068283081055} 08/30/2021 22:37:48 - INFO - __main__ - Step 52133: {'lr': 0.0003713117202654388, 'samples': 10009536, 'steps': 52132, 'loss/train': 1.833272933959961} 08/30/2021 22:37:49 - INFO - __main__ - Step 52134: {'lr': 0.0003713070801419163, 'samples': 10009728, 'steps': 52133, 'loss/train': 0.6838832497596741} 08/30/2021 22:37:49 - INFO - __main__ - Step 52135: {'lr': 0.00037130243996373466, 'samples': 10009920, 'steps': 52134, 'loss/train': 1.1680952310562134} 08/30/2021 22:37:50 - INFO - __main__ - Step 52136: {'lr': 0.00037129779973089596, 'samples': 10010112, 'steps': 52135, 'loss/train': 0.8663227558135986} 08/30/2021 22:37:51 - INFO - __main__ - Step 52137: {'lr': 0.0003712931594434024, 'samples': 10010304, 'steps': 52136, 'loss/train': 0.971187174320221} 08/30/2021 22:37:51 - INFO - __main__ - Step 52138: {'lr': 0.000371288519101256, 'samples': 10010496, 'steps': 52137, 'loss/train': 1.7072018384933472} 08/30/2021 22:37:52 - INFO - __main__ - Step 52139: {'lr': 0.00037128387870445883, 'samples': 10010688, 'steps': 52138, 'loss/train': 1.5136617422103882} 08/30/2021 22:37:52 - INFO - __main__ - Step 52140: {'lr': 0.00037127923825301315, 'samples': 10010880, 'steps': 52139, 'loss/train': 1.391979694366455} 08/30/2021 22:37:53 - INFO - __main__ - Step 52141: {'lr': 0.0003712745977469208, 'samples': 10011072, 'steps': 52140, 'loss/train': 1.9358543157577515} 08/30/2021 22:37:54 - INFO - __main__ - Step 52142: {'lr': 0.000371269957186184, 'samples': 10011264, 'steps': 52141, 'loss/train': 1.4657580852508545} 08/30/2021 22:37:54 - INFO - __main__ - Step 52143: {'lr': 0.0003712653165708048, 'samples': 10011456, 'steps': 52142, 'loss/train': 1.6507071256637573} 08/30/2021 22:37:55 - INFO - __main__ - Step 52144: {'lr': 0.00037126067590078537, 'samples': 10011648, 'steps': 52143, 'loss/train': 1.2737295627593994} 08/30/2021 22:37:55 - INFO - __main__ - Step 52145: {'lr': 0.00037125603517612773, 'samples': 10011840, 'steps': 52144, 'loss/train': 1.0407233238220215} 08/30/2021 22:37:55 - INFO - __main__ - Step 52146: {'lr': 0.00037125139439683405, 'samples': 10012032, 'steps': 52145, 'loss/train': 1.5681606531143188} 08/30/2021 22:37:57 - INFO - __main__ - Step 52147: {'lr': 0.00037124675356290635, 'samples': 10012224, 'steps': 52146, 'loss/train': 1.1434236764907837} 08/30/2021 22:37:57 - INFO - __main__ - Step 52148: {'lr': 0.00037124211267434667, 'samples': 10012416, 'steps': 52147, 'loss/train': 0.8472527861595154} 08/30/2021 22:37:58 - INFO - __main__ - Step 52149: {'lr': 0.0003712374717311572, 'samples': 10012608, 'steps': 52148, 'loss/train': 0.7128331065177917} 08/30/2021 22:37:58 - INFO - __main__ - Step 52150: {'lr': 0.00037123283073333996, 'samples': 10012800, 'steps': 52149, 'loss/train': 1.4185506105422974} 08/30/2021 22:37:59 - INFO - __main__ - Step 52151: {'lr': 0.0003712281896808971, 'samples': 10012992, 'steps': 52150, 'loss/train': 0.8081114888191223} 08/30/2021 22:38:01 - INFO - __main__ - Step 52152: {'lr': 0.0003712235485738307, 'samples': 10013184, 'steps': 52151, 'loss/train': 1.2397840023040771} 08/30/2021 22:38:01 - INFO - __main__ - Step 52153: {'lr': 0.0003712189074121428, 'samples': 10013376, 'steps': 52152, 'loss/train': 1.8307979106903076} 08/30/2021 22:38:01 - INFO - __main__ - Step 52154: {'lr': 0.0003712142661958356, 'samples': 10013568, 'steps': 52153, 'loss/train': 1.4430568218231201} 08/30/2021 22:38:02 - INFO - __main__ - Step 52155: {'lr': 0.0003712096249249111, 'samples': 10013760, 'steps': 52154, 'loss/train': 1.2210968732833862} 08/30/2021 22:38:02 - INFO - __main__ - Step 52156: {'lr': 0.00037120498359937136, 'samples': 10013952, 'steps': 52155, 'loss/train': 1.3309707641601562} 08/30/2021 22:38:04 - INFO - __main__ - Step 52157: {'lr': 0.0003712003422192186, 'samples': 10014144, 'steps': 52156, 'loss/train': 1.5481278896331787} 08/30/2021 22:38:04 - INFO - __main__ - Step 52158: {'lr': 0.00037119570078445477, 'samples': 10014336, 'steps': 52157, 'loss/train': 0.0915670245885849} 08/30/2021 22:38:05 - INFO - __main__ - Step 52159: {'lr': 0.00037119105929508207, 'samples': 10014528, 'steps': 52158, 'loss/train': 1.116216778755188} 08/30/2021 22:38:05 - INFO - __main__ - Step 52160: {'lr': 0.0003711864177511025, 'samples': 10014720, 'steps': 52159, 'loss/train': 1.5935803651809692} 08/30/2021 22:38:05 - INFO - __main__ - Step 52161: {'lr': 0.0003711817761525183, 'samples': 10014912, 'steps': 52160, 'loss/train': 1.2124431133270264} 08/30/2021 22:38:07 - INFO - __main__ - Step 52162: {'lr': 0.00037117713449933136, 'samples': 10015104, 'steps': 52161, 'loss/train': 1.8988696336746216} 08/30/2021 22:38:08 - INFO - __main__ - Step 52163: {'lr': 0.0003711724927915439, 'samples': 10015296, 'steps': 52162, 'loss/train': 0.6315200328826904} 08/30/2021 22:38:08 - INFO - __main__ - Step 52164: {'lr': 0.000371167851029158, 'samples': 10015488, 'steps': 52163, 'loss/train': 1.9108906984329224} 08/30/2021 22:38:08 - INFO - __main__ - Step 52165: {'lr': 0.0003711632092121757, 'samples': 10015680, 'steps': 52164, 'loss/train': 0.9522110223770142} 08/30/2021 22:38:09 - INFO - __main__ - Step 52166: {'lr': 0.00037115856734059916, 'samples': 10015872, 'steps': 52165, 'loss/train': 1.7165749073028564} 08/30/2021 22:38:09 - INFO - __main__ - Step 52167: {'lr': 0.0003711539254144305, 'samples': 10016064, 'steps': 52166, 'loss/train': 2.210855484008789} 08/30/2021 22:38:10 - INFO - __main__ - Step 52168: {'lr': 0.0003711492834336717, 'samples': 10016256, 'steps': 52167, 'loss/train': 1.2202154397964478} 08/30/2021 22:38:11 - INFO - __main__ - Step 52169: {'lr': 0.00037114464139832487, 'samples': 10016448, 'steps': 52168, 'loss/train': 1.1902647018432617} 08/30/2021 22:38:11 - INFO - __main__ - Step 52170: {'lr': 0.00037113999930839215, 'samples': 10016640, 'steps': 52169, 'loss/train': 1.1605207920074463} 08/30/2021 22:38:12 - INFO - __main__ - Step 52171: {'lr': 0.00037113535716387565, 'samples': 10016832, 'steps': 52170, 'loss/train': 0.37961018085479736} 08/30/2021 22:38:12 - INFO - __main__ - Step 52172: {'lr': 0.00037113071496477733, 'samples': 10017024, 'steps': 52171, 'loss/train': 2.154611349105835} 08/30/2021 22:38:13 - INFO - __main__ - Step 52173: {'lr': 0.0003711260727110995, 'samples': 10017216, 'steps': 52172, 'loss/train': 1.8900772333145142} 08/30/2021 22:38:14 - INFO - __main__ - Step 52174: {'lr': 0.0003711214304028441, 'samples': 10017408, 'steps': 52173, 'loss/train': 1.3742018938064575} 08/30/2021 22:38:14 - INFO - __main__ - Step 52175: {'lr': 0.00037111678804001324, 'samples': 10017600, 'steps': 52174, 'loss/train': 0.8828253149986267} 08/30/2021 22:38:15 - INFO - __main__ - Step 52176: {'lr': 0.00037111214562260896, 'samples': 10017792, 'steps': 52175, 'loss/train': 1.2733354568481445} 08/30/2021 22:38:15 - INFO - __main__ - Step 52177: {'lr': 0.0003711075031506335, 'samples': 10017984, 'steps': 52176, 'loss/train': 1.278172254562378} 08/30/2021 22:38:17 - INFO - __main__ - Step 52178: {'lr': 0.0003711028606240888, 'samples': 10018176, 'steps': 52177, 'loss/train': 1.385245680809021} 08/30/2021 22:38:17 - INFO - __main__ - Step 52179: {'lr': 0.00037109821804297706, 'samples': 10018368, 'steps': 52178, 'loss/train': 1.2209218740463257} 08/30/2021 22:38:17 - INFO - __main__ - Step 52180: {'lr': 0.00037109357540730033, 'samples': 10018560, 'steps': 52179, 'loss/train': 0.7813698649406433} 08/30/2021 22:38:18 - INFO - __main__ - Step 52181: {'lr': 0.00037108893271706075, 'samples': 10018752, 'steps': 52180, 'loss/train': 1.4978376626968384} 08/30/2021 22:38:18 - INFO - __main__ - Step 52182: {'lr': 0.0003710842899722603, 'samples': 10018944, 'steps': 52181, 'loss/train': 1.4047669172286987} 08/30/2021 22:38:20 - INFO - __main__ - Step 52183: {'lr': 0.00037107964717290117, 'samples': 10019136, 'steps': 52182, 'loss/train': 1.5158789157867432} 08/30/2021 22:38:20 - INFO - __main__ - Step 52184: {'lr': 0.0003710750043189854, 'samples': 10019328, 'steps': 52183, 'loss/train': 1.3145015239715576} 08/30/2021 22:38:20 - INFO - __main__ - Step 52185: {'lr': 0.0003710703614105151, 'samples': 10019520, 'steps': 52184, 'loss/train': 1.0919619798660278} 08/30/2021 22:38:21 - INFO - __main__ - Step 52186: {'lr': 0.0003710657184474924, 'samples': 10019712, 'steps': 52185, 'loss/train': 1.3718923330307007} 08/30/2021 22:38:21 - INFO - __main__ - Step 52187: {'lr': 0.00037106107542991937, 'samples': 10019904, 'steps': 52186, 'loss/train': 1.3808432817459106} 08/30/2021 22:38:23 - INFO - __main__ - Step 52188: {'lr': 0.00037105643235779803, 'samples': 10020096, 'steps': 52187, 'loss/train': 1.8743278980255127} 08/30/2021 22:38:23 - INFO - __main__ - Step 52189: {'lr': 0.0003710517892311305, 'samples': 10020288, 'steps': 52188, 'loss/train': 1.4995646476745605} 08/30/2021 22:38:23 - INFO - __main__ - Step 52190: {'lr': 0.00037104714604991896, 'samples': 10020480, 'steps': 52189, 'loss/train': 1.7942461967468262} 08/30/2021 22:38:24 - INFO - __main__ - Step 52191: {'lr': 0.0003710425028141654, 'samples': 10020672, 'steps': 52190, 'loss/train': 0.6056779623031616} 08/30/2021 22:38:24 - INFO - __main__ - Step 52192: {'lr': 0.000371037859523872, 'samples': 10020864, 'steps': 52191, 'loss/train': 0.7994875311851501} 08/30/2021 22:38:25 - INFO - __main__ - Step 52193: {'lr': 0.00037103321617904076, 'samples': 10021056, 'steps': 52192, 'loss/train': 2.1128311157226562} 08/30/2021 22:38:26 - INFO - __main__ - Step 52194: {'lr': 0.00037102857277967387, 'samples': 10021248, 'steps': 52193, 'loss/train': 0.6603522896766663} 08/30/2021 22:38:26 - INFO - __main__ - Step 52195: {'lr': 0.0003710239293257734, 'samples': 10021440, 'steps': 52194, 'loss/train': 1.5604076385498047} 08/30/2021 22:38:27 - INFO - __main__ - Step 52196: {'lr': 0.00037101928581734136, 'samples': 10021632, 'steps': 52195, 'loss/train': 1.013862133026123} 08/30/2021 22:38:27 - INFO - __main__ - Step 52197: {'lr': 0.00037101464225437986, 'samples': 10021824, 'steps': 52196, 'loss/train': 1.314492106437683} 08/30/2021 22:38:28 - INFO - __main__ - Step 52198: {'lr': 0.0003710099986368911, 'samples': 10022016, 'steps': 52197, 'loss/train': 1.556799292564392} 08/30/2021 22:38:29 - INFO - __main__ - Step 52199: {'lr': 0.0003710053549648771, 'samples': 10022208, 'steps': 52198, 'loss/train': 1.0115553140640259} 08/30/2021 22:38:29 - INFO - __main__ - Step 52200: {'lr': 0.00037100071123833994, 'samples': 10022400, 'steps': 52199, 'loss/train': 1.64149808883667} 08/30/2021 22:38:30 - INFO - __main__ - Step 52201: {'lr': 0.0003709960674572817, 'samples': 10022592, 'steps': 52200, 'loss/train': 1.6783696413040161} 08/30/2021 22:38:30 - INFO - __main__ - Step 52202: {'lr': 0.00037099142362170454, 'samples': 10022784, 'steps': 52201, 'loss/train': 1.3250700235366821} 08/30/2021 22:38:32 - INFO - __main__ - Step 52203: {'lr': 0.0003709867797316105, 'samples': 10022976, 'steps': 52202, 'loss/train': 1.408653974533081} 08/30/2021 22:38:32 - INFO - __main__ - Step 52204: {'lr': 0.0003709821357870016, 'samples': 10023168, 'steps': 52203, 'loss/train': 1.126314640045166} 08/30/2021 22:38:33 - INFO - __main__ - Step 52205: {'lr': 0.0003709774917878802, 'samples': 10023360, 'steps': 52204, 'loss/train': 1.7212632894515991} 08/30/2021 22:38:33 - INFO - __main__ - Step 52206: {'lr': 0.00037097284773424805, 'samples': 10023552, 'steps': 52205, 'loss/train': 0.5544514060020447} 08/30/2021 22:38:33 - INFO - __main__ - Step 52207: {'lr': 0.0003709682036261075, 'samples': 10023744, 'steps': 52206, 'loss/train': 0.03223726153373718} 08/30/2021 22:38:34 - INFO - __main__ - Step 52208: {'lr': 0.00037096355946346045, 'samples': 10023936, 'steps': 52207, 'loss/train': 1.404617190361023} 08/30/2021 22:38:36 - INFO - __main__ - Step 52209: {'lr': 0.00037095891524630914, 'samples': 10024128, 'steps': 52208, 'loss/train': 1.5098602771759033} 08/30/2021 22:38:36 - INFO - __main__ - Step 52210: {'lr': 0.00037095427097465564, 'samples': 10024320, 'steps': 52209, 'loss/train': 1.3243461847305298} 08/30/2021 22:38:37 - INFO - __main__ - Step 52211: {'lr': 0.00037094962664850194, 'samples': 10024512, 'steps': 52210, 'loss/train': 1.4143859148025513} 08/30/2021 22:38:37 - INFO - __main__ - Step 52212: {'lr': 0.00037094498226785023, 'samples': 10024704, 'steps': 52211, 'loss/train': 0.0280526801943779} 08/30/2021 22:38:37 - INFO - __main__ - Step 52213: {'lr': 0.00037094033783270256, 'samples': 10024896, 'steps': 52212, 'loss/train': 1.2864248752593994} 08/30/2021 22:38:39 - INFO - __main__ - Step 52214: {'lr': 0.0003709356933430611, 'samples': 10025088, 'steps': 52213, 'loss/train': 0.8989865779876709} 08/30/2021 22:38:39 - INFO - __main__ - Step 52215: {'lr': 0.00037093104879892786, 'samples': 10025280, 'steps': 52214, 'loss/train': 1.8137493133544922} 08/30/2021 22:38:40 - INFO - __main__ - Step 52216: {'lr': 0.000370926404200305, 'samples': 10025472, 'steps': 52215, 'loss/train': 1.4083799123764038} 08/30/2021 22:38:40 - INFO - __main__ - Step 52217: {'lr': 0.0003709217595471945, 'samples': 10025664, 'steps': 52216, 'loss/train': 0.9888001680374146} 08/30/2021 22:38:40 - INFO - __main__ - Step 52218: {'lr': 0.0003709171148395985, 'samples': 10025856, 'steps': 52217, 'loss/train': 1.1968246698379517} 08/30/2021 22:38:41 - INFO - __main__ - Step 52219: {'lr': 0.00037091247007751916, 'samples': 10026048, 'steps': 52218, 'loss/train': 1.0894849300384521} 08/30/2021 22:38:42 - INFO - __main__ - Step 52220: {'lr': 0.0003709078252609585, 'samples': 10026240, 'steps': 52219, 'loss/train': 1.170340895652771} 08/30/2021 22:38:43 - INFO - __main__ - Step 52221: {'lr': 0.0003709031803899187, 'samples': 10026432, 'steps': 52220, 'loss/train': 0.9565987586975098} 08/30/2021 22:38:43 - INFO - __main__ - Step 52222: {'lr': 0.0003708985354644017, 'samples': 10026624, 'steps': 52221, 'loss/train': 1.477920413017273} 08/30/2021 22:38:43 - INFO - __main__ - Step 52223: {'lr': 0.00037089389048440975, 'samples': 10026816, 'steps': 52222, 'loss/train': 1.4444735050201416} 08/30/2021 22:38:44 - INFO - __main__ - Step 52224: {'lr': 0.0003708892454499448, 'samples': 10027008, 'steps': 52223, 'loss/train': 0.848482608795166} 08/30/2021 22:38:45 - INFO - __main__ - Step 52225: {'lr': 0.00037088460036100915, 'samples': 10027200, 'steps': 52224, 'loss/train': 1.201964259147644} 08/30/2021 22:38:46 - INFO - __main__ - Step 52226: {'lr': 0.0003708799552176046, 'samples': 10027392, 'steps': 52225, 'loss/train': 1.1147754192352295} 08/30/2021 22:38:46 - INFO - __main__ - Step 52227: {'lr': 0.0003708753100197336, 'samples': 10027584, 'steps': 52226, 'loss/train': 1.2671598196029663} 08/30/2021 22:38:46 - INFO - __main__ - Step 52228: {'lr': 0.00037087066476739795, 'samples': 10027776, 'steps': 52227, 'loss/train': 0.6710507869720459} 08/30/2021 22:38:47 - INFO - __main__ - Step 52229: {'lr': 0.0003708660194605998, 'samples': 10027968, 'steps': 52228, 'loss/train': 0.7408491969108582} 08/30/2021 22:38:48 - INFO - __main__ - Step 52230: {'lr': 0.0003708613740993414, 'samples': 10028160, 'steps': 52229, 'loss/train': 0.5190768837928772} 08/30/2021 22:38:49 - INFO - __main__ - Step 52231: {'lr': 0.00037085672868362464, 'samples': 10028352, 'steps': 52230, 'loss/train': 1.8946200609207153} 08/30/2021 22:38:49 - INFO - __main__ - Step 52232: {'lr': 0.0003708520832134518, 'samples': 10028544, 'steps': 52231, 'loss/train': 1.4070595502853394} 08/30/2021 22:38:49 - INFO - __main__ - Step 52233: {'lr': 0.00037084743768882474, 'samples': 10028736, 'steps': 52232, 'loss/train': 1.028970718383789} 08/30/2021 22:38:50 - INFO - __main__ - Step 52234: {'lr': 0.00037084279210974577, 'samples': 10028928, 'steps': 52233, 'loss/train': 0.7259479761123657} 08/30/2021 22:38:51 - INFO - __main__ - Step 52235: {'lr': 0.00037083814647621686, 'samples': 10029120, 'steps': 52234, 'loss/train': 0.802712082862854} 08/30/2021 22:38:52 - INFO - __main__ - Step 52236: {'lr': 0.0003708335007882402, 'samples': 10029312, 'steps': 52235, 'loss/train': 1.1849919557571411} 08/30/2021 22:38:52 - INFO - __main__ - Step 52237: {'lr': 0.00037082885504581775, 'samples': 10029504, 'steps': 52236, 'loss/train': 1.521113634109497} 08/30/2021 22:38:52 - INFO - __main__ - Step 52238: {'lr': 0.0003708242092489518, 'samples': 10029696, 'steps': 52237, 'loss/train': 1.4894156455993652} 08/30/2021 22:38:53 - INFO - __main__ - Step 52239: {'lr': 0.0003708195633976442, 'samples': 10029888, 'steps': 52238, 'loss/train': 1.1013530492782593} 08/30/2021 22:38:54 - INFO - __main__ - Step 52240: {'lr': 0.0003708149174918972, 'samples': 10030080, 'steps': 52239, 'loss/train': 1.670696496963501} 08/30/2021 22:38:55 - INFO - __main__ - Step 52241: {'lr': 0.000370810271531713, 'samples': 10030272, 'steps': 52240, 'loss/train': 2.102803945541382} 08/30/2021 22:38:55 - INFO - __main__ - Step 52242: {'lr': 0.0003708056255170934, 'samples': 10030464, 'steps': 52241, 'loss/train': 0.8963179588317871} 08/30/2021 22:38:55 - INFO - __main__ - Step 52243: {'lr': 0.0003708009794480407, 'samples': 10030656, 'steps': 52242, 'loss/train': 1.285918951034546} 08/30/2021 22:38:56 - INFO - __main__ - Step 52244: {'lr': 0.0003707963333245569, 'samples': 10030848, 'steps': 52243, 'loss/train': 1.614464521408081} 08/30/2021 22:38:57 - INFO - __main__ - Step 52245: {'lr': 0.0003707916871466442, 'samples': 10031040, 'steps': 52244, 'loss/train': 1.2795166969299316} 08/30/2021 22:38:58 - INFO - __main__ - Step 52246: {'lr': 0.0003707870409143046, 'samples': 10031232, 'steps': 52245, 'loss/train': 1.3110697269439697} 08/30/2021 22:38:58 - INFO - __main__ - Step 52247: {'lr': 0.00037078239462754023, 'samples': 10031424, 'steps': 52246, 'loss/train': 1.2178854942321777} 08/30/2021 22:38:59 - INFO - __main__ - Step 52248: {'lr': 0.0003707777482863532, 'samples': 10031616, 'steps': 52247, 'loss/train': 0.05008105933666229} 08/30/2021 22:38:59 - INFO - __main__ - Step 52249: {'lr': 0.00037077310189074554, 'samples': 10031808, 'steps': 52248, 'loss/train': 1.2083594799041748} 08/30/2021 22:39:00 - INFO - __main__ - Step 52250: {'lr': 0.0003707684554407194, 'samples': 10032000, 'steps': 52249, 'loss/train': 1.4056837558746338} 08/30/2021 22:39:01 - INFO - __main__ - Step 52251: {'lr': 0.0003707638089362769, 'samples': 10032192, 'steps': 52250, 'loss/train': 1.2372404336929321} 08/30/2021 22:39:01 - INFO - __main__ - Step 52252: {'lr': 0.00037075916237742, 'samples': 10032384, 'steps': 52251, 'loss/train': 0.036106839776039124} 08/30/2021 22:39:02 - INFO - __main__ - Step 52253: {'lr': 0.00037075451576415095, 'samples': 10032576, 'steps': 52252, 'loss/train': 1.2156604528427124} 08/30/2021 22:39:02 - INFO - __main__ - Step 52254: {'lr': 0.00037074986909647173, 'samples': 10032768, 'steps': 52253, 'loss/train': 1.2154524326324463} 08/30/2021 22:39:02 - INFO - __main__ - Step 52255: {'lr': 0.00037074522237438455, 'samples': 10032960, 'steps': 52254, 'loss/train': 1.1037936210632324} 08/30/2021 22:39:04 - INFO - __main__ - Step 52256: {'lr': 0.0003707405755978914, 'samples': 10033152, 'steps': 52255, 'loss/train': 0.24889405071735382} 08/30/2021 22:39:04 - INFO - __main__ - Step 52257: {'lr': 0.00037073592876699443, 'samples': 10033344, 'steps': 52256, 'loss/train': 1.2274162769317627} 08/30/2021 22:39:05 - INFO - __main__ - Step 52258: {'lr': 0.0003707312818816956, 'samples': 10033536, 'steps': 52257, 'loss/train': 1.145326018333435} 08/30/2021 22:39:05 - INFO - __main__ - Step 52259: {'lr': 0.00037072663494199724, 'samples': 10033728, 'steps': 52258, 'loss/train': 1.2771406173706055} 08/30/2021 22:39:05 - INFO - __main__ - Step 52260: {'lr': 0.0003707219879479013, 'samples': 10033920, 'steps': 52259, 'loss/train': 1.2544595003128052} 08/30/2021 22:39:08 - INFO - __main__ - Step 52261: {'lr': 0.0003707173408994099, 'samples': 10034112, 'steps': 52260, 'loss/train': 1.2631003856658936} 08/30/2021 22:39:08 - INFO - __main__ - Step 52262: {'lr': 0.0003707126937965251, 'samples': 10034304, 'steps': 52261, 'loss/train': 2.133697509765625} 08/30/2021 22:39:08 - INFO - __main__ - Step 52263: {'lr': 0.0003707080466392491, 'samples': 10034496, 'steps': 52262, 'loss/train': 1.2249665260314941} 08/30/2021 22:39:09 - INFO - __main__ - Step 52264: {'lr': 0.0003707033994275838, 'samples': 10034688, 'steps': 52263, 'loss/train': 1.5853255987167358} 08/30/2021 22:39:09 - INFO - __main__ - Step 52265: {'lr': 0.0003706987521615315, 'samples': 10034880, 'steps': 52264, 'loss/train': 1.1202856302261353} 08/30/2021 22:39:11 - INFO - __main__ - Step 52266: {'lr': 0.0003706941048410941, 'samples': 10035072, 'steps': 52265, 'loss/train': 1.6441651582717896} 08/30/2021 22:39:11 - INFO - __main__ - Step 52267: {'lr': 0.0003706894574662739, 'samples': 10035264, 'steps': 52266, 'loss/train': 1.4115123748779297} 08/30/2021 22:39:12 - INFO - __main__ - Step 52268: {'lr': 0.0003706848100370729, 'samples': 10035456, 'steps': 52267, 'loss/train': 1.4814977645874023} 08/30/2021 22:39:12 - INFO - __main__ - Step 52269: {'lr': 0.00037068016255349315, 'samples': 10035648, 'steps': 52268, 'loss/train': 1.3032234907150269} 08/30/2021 22:39:12 - INFO - __main__ - Step 52270: {'lr': 0.0003706755150155368, 'samples': 10035840, 'steps': 52269, 'loss/train': 1.1801214218139648} 08/30/2021 22:39:14 - INFO - __main__ - Step 52271: {'lr': 0.0003706708674232059, 'samples': 10036032, 'steps': 52270, 'loss/train': 2.0028908252716064} 08/30/2021 22:39:14 - INFO - __main__ - Step 52272: {'lr': 0.0003706662197765025, 'samples': 10036224, 'steps': 52271, 'loss/train': 1.1603450775146484} 08/30/2021 22:39:15 - INFO - __main__ - Step 52273: {'lr': 0.00037066157207542885, 'samples': 10036416, 'steps': 52272, 'loss/train': 0.9355124831199646} 08/30/2021 22:39:15 - INFO - __main__ - Step 52274: {'lr': 0.00037065692431998695, 'samples': 10036608, 'steps': 52273, 'loss/train': 1.1618053913116455} 08/30/2021 22:39:15 - INFO - __main__ - Step 52275: {'lr': 0.00037065227651017897, 'samples': 10036800, 'steps': 52274, 'loss/train': 1.3768295049667358} 08/30/2021 22:39:17 - INFO - __main__ - Step 52276: {'lr': 0.0003706476286460068, 'samples': 10036992, 'steps': 52275, 'loss/train': 1.458606481552124} 08/30/2021 22:39:17 - INFO - __main__ - Step 52277: {'lr': 0.0003706429807274728, 'samples': 10037184, 'steps': 52276, 'loss/train': 0.9733828902244568} 08/30/2021 22:39:18 - INFO - __main__ - Step 52278: {'lr': 0.0003706383327545788, 'samples': 10037376, 'steps': 52277, 'loss/train': 0.6269864439964294} 08/30/2021 22:39:18 - INFO - __main__ - Step 52279: {'lr': 0.0003706336847273271, 'samples': 10037568, 'steps': 52278, 'loss/train': 1.1764856576919556} 08/30/2021 22:39:18 - INFO - __main__ - Step 52280: {'lr': 0.00037062903664571975, 'samples': 10037760, 'steps': 52279, 'loss/train': 1.7229739427566528} 08/30/2021 22:39:19 - INFO - __main__ - Step 52281: {'lr': 0.00037062438850975877, 'samples': 10037952, 'steps': 52280, 'loss/train': 0.32705265283584595} 08/30/2021 22:39:20 - INFO - __main__ - Step 52282: {'lr': 0.00037061974031944635, 'samples': 10038144, 'steps': 52281, 'loss/train': 1.6630194187164307} 08/30/2021 22:39:21 - INFO - __main__ - Step 52283: {'lr': 0.0003706150920747845, 'samples': 10038336, 'steps': 52282, 'loss/train': 1.8692938089370728} 08/30/2021 22:39:21 - INFO - __main__ - Step 52284: {'lr': 0.00037061044377577535, 'samples': 10038528, 'steps': 52283, 'loss/train': 1.044979453086853} 08/30/2021 22:39:21 - INFO - __main__ - Step 52285: {'lr': 0.00037060579542242094, 'samples': 10038720, 'steps': 52284, 'loss/train': 1.1428381204605103} 08/30/2021 22:39:22 - INFO - __main__ - Step 52286: {'lr': 0.00037060114701472355, 'samples': 10038912, 'steps': 52285, 'loss/train': 1.7768486738204956} 08/30/2021 22:39:23 - INFO - __main__ - Step 52287: {'lr': 0.00037059649855268503, 'samples': 10039104, 'steps': 52286, 'loss/train': 1.559008002281189} 08/30/2021 22:39:24 - INFO - __main__ - Step 52288: {'lr': 0.0003705918500363077, 'samples': 10039296, 'steps': 52287, 'loss/train': 1.487499475479126} 08/30/2021 22:39:24 - INFO - __main__ - Step 52289: {'lr': 0.0003705872014655934, 'samples': 10039488, 'steps': 52288, 'loss/train': 1.2089561223983765} 08/30/2021 22:39:24 - INFO - __main__ - Step 52290: {'lr': 0.0003705825528405445, 'samples': 10039680, 'steps': 52289, 'loss/train': 1.0980134010314941} 08/30/2021 22:39:25 - INFO - __main__ - Step 52291: {'lr': 0.0003705779041611629, 'samples': 10039872, 'steps': 52290, 'loss/train': 0.9486036896705627} 08/30/2021 22:39:27 - INFO - __main__ - Step 52292: {'lr': 0.00037057325542745075, 'samples': 10040064, 'steps': 52291, 'loss/train': 0.9440996646881104} 08/30/2021 22:39:27 - INFO - __main__ - Step 52293: {'lr': 0.00037056860663941014, 'samples': 10040256, 'steps': 52292, 'loss/train': 1.1637372970581055} 08/30/2021 22:39:28 - INFO - __main__ - Step 52294: {'lr': 0.0003705639577970432, 'samples': 10040448, 'steps': 52293, 'loss/train': 0.6139895915985107} 08/30/2021 22:39:28 - INFO - __main__ - Step 52295: {'lr': 0.00037055930890035203, 'samples': 10040640, 'steps': 52294, 'loss/train': 1.789811372756958} 08/30/2021 22:39:28 - INFO - __main__ - Step 52296: {'lr': 0.00037055465994933866, 'samples': 10040832, 'steps': 52295, 'loss/train': 1.6707935333251953} 08/30/2021 22:39:29 - INFO - __main__ - Step 52297: {'lr': 0.00037055001094400523, 'samples': 10041024, 'steps': 52296, 'loss/train': 0.9426714181900024} 08/30/2021 22:39:29 - INFO - __main__ - Step 52298: {'lr': 0.0003705453618843538, 'samples': 10041216, 'steps': 52297, 'loss/train': 1.2685478925704956} 08/30/2021 22:39:31 - INFO - __main__ - Step 52299: {'lr': 0.00037054071277038654, 'samples': 10041408, 'steps': 52298, 'loss/train': 1.4617962837219238} 08/30/2021 22:39:31 - INFO - __main__ - Step 52300: {'lr': 0.00037053606360210544, 'samples': 10041600, 'steps': 52299, 'loss/train': 1.7167713642120361} 08/30/2021 22:39:32 - INFO - __main__ - Step 52301: {'lr': 0.00037053141437951264, 'samples': 10041792, 'steps': 52300, 'loss/train': 1.043386459350586} 08/30/2021 22:39:32 - INFO - __main__ - Step 52302: {'lr': 0.00037052676510261043, 'samples': 10041984, 'steps': 52301, 'loss/train': 1.5842963457107544} 08/30/2021 22:39:32 - INFO - __main__ - Step 52303: {'lr': 0.00037052211577140047, 'samples': 10042176, 'steps': 52302, 'loss/train': 0.8494521975517273} 08/30/2021 22:39:34 - INFO - __main__ - Step 52304: {'lr': 0.00037051746638588526, 'samples': 10042368, 'steps': 52303, 'loss/train': 1.5008400678634644} 08/30/2021 22:39:34 - INFO - __main__ - Step 52305: {'lr': 0.00037051281694606666, 'samples': 10042560, 'steps': 52304, 'loss/train': 1.7783734798431396} 08/30/2021 22:39:35 - INFO - __main__ - Step 52306: {'lr': 0.00037050816745194686, 'samples': 10042752, 'steps': 52305, 'loss/train': 1.68411386013031} 08/30/2021 22:39:35 - INFO - __main__ - Step 52307: {'lr': 0.00037050351790352795, 'samples': 10042944, 'steps': 52306, 'loss/train': 1.420371174812317} 08/30/2021 22:39:35 - INFO - __main__ - Step 52308: {'lr': 0.00037049886830081203, 'samples': 10043136, 'steps': 52307, 'loss/train': 1.277109980583191} 08/30/2021 22:39:37 - INFO - __main__ - Step 52309: {'lr': 0.00037049421864380116, 'samples': 10043328, 'steps': 52308, 'loss/train': 0.07898920774459839} 08/30/2021 22:39:37 - INFO - __main__ - Step 52310: {'lr': 0.00037048956893249746, 'samples': 10043520, 'steps': 52309, 'loss/train': 1.2166470289230347} 08/30/2021 22:39:38 - INFO - __main__ - Step 52311: {'lr': 0.00037048491916690304, 'samples': 10043712, 'steps': 52310, 'loss/train': 1.446404218673706} 08/30/2021 22:39:38 - INFO - __main__ - Step 52312: {'lr': 0.00037048026934701997, 'samples': 10043904, 'steps': 52311, 'loss/train': 0.5290502309799194} 08/30/2021 22:39:38 - INFO - __main__ - Step 52313: {'lr': 0.0003704756194728503, 'samples': 10044096, 'steps': 52312, 'loss/train': 0.045182596892118454} 08/30/2021 22:39:40 - INFO - __main__ - Step 52314: {'lr': 0.0003704709695443962, 'samples': 10044288, 'steps': 52313, 'loss/train': 1.4563908576965332} 08/30/2021 22:39:41 - INFO - __main__ - Step 52315: {'lr': 0.00037046631956165975, 'samples': 10044480, 'steps': 52314, 'loss/train': 1.4502958059310913} 08/30/2021 22:39:41 - INFO - __main__ - Step 52316: {'lr': 0.00037046166952464307, 'samples': 10044672, 'steps': 52315, 'loss/train': 3.084468126296997} 08/30/2021 22:39:42 - INFO - __main__ - Step 52317: {'lr': 0.00037045701943334814, 'samples': 10044864, 'steps': 52316, 'loss/train': 0.8483191728591919} 08/30/2021 22:39:42 - INFO - __main__ - Step 52318: {'lr': 0.0003704523692877772, 'samples': 10045056, 'steps': 52317, 'loss/train': 1.269869327545166} 08/30/2021 22:39:43 - INFO - __main__ - Step 52319: {'lr': 0.00037044771908793225, 'samples': 10045248, 'steps': 52318, 'loss/train': 4.282064914703369} 08/30/2021 22:39:44 - INFO - __main__ - Step 52320: {'lr': 0.0003704430688338154, 'samples': 10045440, 'steps': 52319, 'loss/train': 0.5108669996261597} 08/30/2021 22:39:44 - INFO - __main__ - Step 52321: {'lr': 0.0003704384185254288, 'samples': 10045632, 'steps': 52320, 'loss/train': 0.8352671265602112} 08/30/2021 22:39:45 - INFO - __main__ - Step 52322: {'lr': 0.00037043376816277453, 'samples': 10045824, 'steps': 52321, 'loss/train': 1.8320648670196533} 08/30/2021 22:39:45 - INFO - __main__ - Step 52323: {'lr': 0.00037042911774585465, 'samples': 10046016, 'steps': 52322, 'loss/train': 1.0616240501403809} 08/30/2021 22:39:45 - INFO - __main__ - Step 52324: {'lr': 0.0003704244672746712, 'samples': 10046208, 'steps': 52323, 'loss/train': 0.8754017949104309} 08/30/2021 22:39:47 - INFO - __main__ - Step 52325: {'lr': 0.00037041981674922644, 'samples': 10046400, 'steps': 52324, 'loss/train': 1.6019108295440674} 08/30/2021 22:39:47 - INFO - __main__ - Step 52326: {'lr': 0.00037041516616952223, 'samples': 10046592, 'steps': 52325, 'loss/train': 0.7316842675209045} 08/30/2021 22:39:48 - INFO - __main__ - Step 52327: {'lr': 0.0003704105155355609, 'samples': 10046784, 'steps': 52326, 'loss/train': 1.4071804285049438} 08/30/2021 22:39:48 - INFO - __main__ - Step 52328: {'lr': 0.0003704058648473445, 'samples': 10046976, 'steps': 52327, 'loss/train': 1.074450135231018} 08/30/2021 22:39:48 - INFO - __main__ - Step 52329: {'lr': 0.000370401214104875, 'samples': 10047168, 'steps': 52328, 'loss/train': 2.788742780685425} 08/30/2021 22:39:50 - INFO - __main__ - Step 52330: {'lr': 0.0003703965633081546, 'samples': 10047360, 'steps': 52329, 'loss/train': 1.180933952331543} 08/30/2021 22:39:50 - INFO - __main__ - Step 52331: {'lr': 0.00037039191245718536, 'samples': 10047552, 'steps': 52330, 'loss/train': 1.1655426025390625} 08/30/2021 22:39:51 - INFO - __main__ - Step 52332: {'lr': 0.00037038726155196934, 'samples': 10047744, 'steps': 52331, 'loss/train': 0.07808967679738998} 08/30/2021 22:39:51 - INFO - __main__ - Step 52333: {'lr': 0.00037038261059250873, 'samples': 10047936, 'steps': 52332, 'loss/train': 1.2504870891571045} 08/30/2021 22:39:51 - INFO - __main__ - Step 52334: {'lr': 0.0003703779595788056, 'samples': 10048128, 'steps': 52333, 'loss/train': 1.4041295051574707} 08/30/2021 22:39:53 - INFO - __main__ - Step 52335: {'lr': 0.00037037330851086194, 'samples': 10048320, 'steps': 52334, 'loss/train': 1.4801279306411743} 08/30/2021 22:39:53 - INFO - __main__ - Step 52336: {'lr': 0.00037036865738868, 'samples': 10048512, 'steps': 52335, 'loss/train': 1.13273024559021} 08/30/2021 22:39:54 - INFO - __main__ - Step 52337: {'lr': 0.00037036400621226175, 'samples': 10048704, 'steps': 52336, 'loss/train': 1.8517225980758667} 08/30/2021 22:39:54 - INFO - __main__ - Step 52338: {'lr': 0.00037035935498160933, 'samples': 10048896, 'steps': 52337, 'loss/train': 1.3364348411560059} 08/30/2021 22:39:54 - INFO - __main__ - Step 52339: {'lr': 0.00037035470369672484, 'samples': 10049088, 'steps': 52338, 'loss/train': 0.5864757299423218} 08/30/2021 22:39:56 - INFO - __main__ - Step 52340: {'lr': 0.0003703500523576104, 'samples': 10049280, 'steps': 52339, 'loss/train': 1.467815637588501} 08/30/2021 22:39:56 - INFO - __main__ - Step 52341: {'lr': 0.0003703454009642681, 'samples': 10049472, 'steps': 52340, 'loss/train': 1.2310173511505127} 08/30/2021 22:39:57 - INFO - __main__ - Step 52342: {'lr': 0.0003703407495167, 'samples': 10049664, 'steps': 52341, 'loss/train': 1.3627800941467285} 08/30/2021 22:39:57 - INFO - __main__ - Step 52343: {'lr': 0.0003703360980149082, 'samples': 10049856, 'steps': 52342, 'loss/train': 1.3972407579421997} 08/30/2021 22:39:57 - INFO - __main__ - Step 52344: {'lr': 0.00037033144645889487, 'samples': 10050048, 'steps': 52343, 'loss/train': 1.2970020771026611} 08/30/2021 22:39:59 - INFO - __main__ - Step 52345: {'lr': 0.000370326794848662, 'samples': 10050240, 'steps': 52344, 'loss/train': 1.2972080707550049} 08/30/2021 22:39:59 - INFO - __main__ - Step 52346: {'lr': 0.00037032214318421174, 'samples': 10050432, 'steps': 52345, 'loss/train': 1.8222229480743408} 08/30/2021 22:40:00 - INFO - __main__ - Step 52347: {'lr': 0.00037031749146554616, 'samples': 10050624, 'steps': 52346, 'loss/train': 1.2135664224624634} 08/30/2021 22:40:00 - INFO - __main__ - Step 52348: {'lr': 0.00037031283969266737, 'samples': 10050816, 'steps': 52347, 'loss/train': 1.1267591714859009} 08/30/2021 22:40:00 - INFO - __main__ - Step 52349: {'lr': 0.0003703081878655775, 'samples': 10051008, 'steps': 52348, 'loss/train': 1.8772066831588745} 08/30/2021 22:40:02 - INFO - __main__ - Step 52350: {'lr': 0.00037030353598427866, 'samples': 10051200, 'steps': 52349, 'loss/train': 1.3223580121994019} 08/30/2021 22:40:02 - INFO - __main__ - Step 52351: {'lr': 0.0003702988840487728, 'samples': 10051392, 'steps': 52350, 'loss/train': 1.4786609411239624} 08/30/2021 22:40:03 - INFO - __main__ - Step 52352: {'lr': 0.0003702942320590622, 'samples': 10051584, 'steps': 52351, 'loss/train': 1.244758129119873} 08/30/2021 22:40:03 - INFO - __main__ - Step 52353: {'lr': 0.00037028958001514886, 'samples': 10051776, 'steps': 52352, 'loss/train': 1.202074646949768} 08/30/2021 22:40:03 - INFO - __main__ - Step 52354: {'lr': 0.00037028492791703484, 'samples': 10051968, 'steps': 52353, 'loss/train': 0.9333009123802185} 08/30/2021 22:40:05 - INFO - __main__ - Step 52355: {'lr': 0.0003702802757647223, 'samples': 10052160, 'steps': 52354, 'loss/train': 0.4106811583042145} 08/30/2021 22:40:05 - INFO - __main__ - Step 52356: {'lr': 0.0003702756235582134, 'samples': 10052352, 'steps': 52355, 'loss/train': 1.2768062353134155} 08/30/2021 22:40:06 - INFO - __main__ - Step 52357: {'lr': 0.00037027097129751016, 'samples': 10052544, 'steps': 52356, 'loss/train': 0.8792566061019897} 08/30/2021 22:40:06 - INFO - __main__ - Step 52358: {'lr': 0.0003702663189826146, 'samples': 10052736, 'steps': 52357, 'loss/train': 1.7622770071029663} 08/30/2021 22:40:06 - INFO - __main__ - Step 52359: {'lr': 0.0003702616666135289, 'samples': 10052928, 'steps': 52358, 'loss/train': 1.0969775915145874} 08/30/2021 22:40:08 - INFO - __main__ - Step 52360: {'lr': 0.0003702570141902552, 'samples': 10053120, 'steps': 52359, 'loss/train': 1.6986440420150757} 08/30/2021 22:40:08 - INFO - __main__ - Step 52361: {'lr': 0.00037025236171279546, 'samples': 10053312, 'steps': 52360, 'loss/train': 1.5727958679199219} 08/30/2021 22:40:08 - INFO - __main__ - Step 52362: {'lr': 0.000370247709181152, 'samples': 10053504, 'steps': 52361, 'loss/train': 1.4509665966033936} 08/30/2021 22:40:09 - INFO - __main__ - Step 52363: {'lr': 0.00037024305659532665, 'samples': 10053696, 'steps': 52362, 'loss/train': 1.1041913032531738} 08/30/2021 22:40:09 - INFO - __main__ - Step 52364: {'lr': 0.00037023840395532167, 'samples': 10053888, 'steps': 52363, 'loss/train': 1.389992594718933} 08/30/2021 22:40:10 - INFO - __main__ - Step 52365: {'lr': 0.0003702337512611391, 'samples': 10054080, 'steps': 52364, 'loss/train': 1.3814351558685303} 08/30/2021 22:40:11 - INFO - __main__ - Step 52366: {'lr': 0.00037022909851278107, 'samples': 10054272, 'steps': 52365, 'loss/train': 0.6395887136459351} 08/30/2021 22:40:11 - INFO - __main__ - Step 52367: {'lr': 0.0003702244457102497, 'samples': 10054464, 'steps': 52366, 'loss/train': 1.6485730409622192} 08/30/2021 22:40:12 - INFO - __main__ - Step 52368: {'lr': 0.000370219792853547, 'samples': 10054656, 'steps': 52367, 'loss/train': 1.6054531335830688} 08/30/2021 22:40:12 - INFO - __main__ - Step 52369: {'lr': 0.0003702151399426752, 'samples': 10054848, 'steps': 52368, 'loss/train': 1.5226519107818604} 08/30/2021 22:40:13 - INFO - __main__ - Step 52370: {'lr': 0.0003702104869776362, 'samples': 10055040, 'steps': 52369, 'loss/train': 1.3941231966018677} 08/30/2021 22:40:14 - INFO - __main__ - Step 52371: {'lr': 0.0003702058339584323, 'samples': 10055232, 'steps': 52370, 'loss/train': 1.1772795915603638} 08/30/2021 22:40:15 - INFO - __main__ - Step 52372: {'lr': 0.00037020118088506546, 'samples': 10055424, 'steps': 52371, 'loss/train': 1.3694539070129395} 08/30/2021 22:40:15 - INFO - __main__ - Step 52373: {'lr': 0.0003701965277575378, 'samples': 10055616, 'steps': 52372, 'loss/train': 1.0295183658599854} 08/30/2021 22:40:16 - INFO - __main__ - Step 52374: {'lr': 0.0003701918745758515, 'samples': 10055808, 'steps': 52373, 'loss/train': 1.2487298250198364} 08/30/2021 22:40:16 - INFO - __main__ - Step 52375: {'lr': 0.00037018722134000856, 'samples': 10056000, 'steps': 52374, 'loss/train': 1.340018391609192} 08/30/2021 22:40:18 - INFO - __main__ - Step 52376: {'lr': 0.00037018256805001115, 'samples': 10056192, 'steps': 52375, 'loss/train': 0.907055139541626} 08/30/2021 22:40:18 - INFO - __main__ - Step 52377: {'lr': 0.00037017791470586126, 'samples': 10056384, 'steps': 52376, 'loss/train': 0.720424234867096} 08/30/2021 22:40:18 - INFO - __main__ - Step 52378: {'lr': 0.0003701732613075611, 'samples': 10056576, 'steps': 52377, 'loss/train': 1.5016816854476929} 08/30/2021 22:40:19 - INFO - __main__ - Step 52379: {'lr': 0.00037016860785511274, 'samples': 10056768, 'steps': 52378, 'loss/train': 1.357456922531128} 08/30/2021 22:40:19 - INFO - __main__ - Step 52380: {'lr': 0.00037016395434851825, 'samples': 10056960, 'steps': 52379, 'loss/train': 1.652008056640625} 08/30/2021 22:40:21 - INFO - __main__ - Step 52381: {'lr': 0.0003701593007877797, 'samples': 10057152, 'steps': 52380, 'loss/train': 1.3944809436798096} 08/30/2021 22:40:21 - INFO - __main__ - Step 52382: {'lr': 0.00037015464717289924, 'samples': 10057344, 'steps': 52381, 'loss/train': 1.0370922088623047} 08/30/2021 22:40:21 - INFO - __main__ - Step 52383: {'lr': 0.000370149993503879, 'samples': 10057536, 'steps': 52382, 'loss/train': 1.397559404373169} 08/30/2021 22:40:22 - INFO - __main__ - Step 52384: {'lr': 0.000370145339780721, 'samples': 10057728, 'steps': 52383, 'loss/train': 0.9382269382476807} 08/30/2021 22:40:22 - INFO - __main__ - Step 52385: {'lr': 0.0003701406860034273, 'samples': 10057920, 'steps': 52384, 'loss/train': 0.9200490713119507} 08/30/2021 22:40:24 - INFO - __main__ - Step 52386: {'lr': 0.0003701360321720001, 'samples': 10058112, 'steps': 52385, 'loss/train': 1.21071457862854} 08/30/2021 22:40:24 - INFO - __main__ - Step 52387: {'lr': 0.0003701313782864415, 'samples': 10058304, 'steps': 52386, 'loss/train': 1.793806552886963} 08/30/2021 22:40:24 - INFO - __main__ - Step 52388: {'lr': 0.0003701267243467535, 'samples': 10058496, 'steps': 52387, 'loss/train': 1.447556734085083} 08/30/2021 22:40:25 - INFO - __main__ - Step 52389: {'lr': 0.00037012207035293834, 'samples': 10058688, 'steps': 52388, 'loss/train': 0.9450122117996216} 08/30/2021 22:40:25 - INFO - __main__ - Step 52390: {'lr': 0.00037011741630499796, 'samples': 10058880, 'steps': 52389, 'loss/train': 0.9967343807220459} 08/30/2021 22:40:27 - INFO - __main__ - Step 52391: {'lr': 0.00037011276220293447, 'samples': 10059072, 'steps': 52390, 'loss/train': 0.8369120955467224} 08/30/2021 22:40:27 - INFO - __main__ - Step 52392: {'lr': 0.0003701081080467501, 'samples': 10059264, 'steps': 52391, 'loss/train': 1.4139078855514526} 08/30/2021 22:40:28 - INFO - __main__ - Step 52393: {'lr': 0.0003701034538364468, 'samples': 10059456, 'steps': 52392, 'loss/train': 1.3424862623214722} 08/30/2021 22:40:28 - INFO - __main__ - Step 52394: {'lr': 0.0003700987995720269, 'samples': 10059648, 'steps': 52393, 'loss/train': 0.15181411802768707} 08/30/2021 22:40:28 - INFO - __main__ - Step 52395: {'lr': 0.0003700941452534922, 'samples': 10059840, 'steps': 52394, 'loss/train': 1.1930989027023315} 08/30/2021 22:40:30 - INFO - __main__ - Step 52396: {'lr': 0.0003700894908808449, 'samples': 10060032, 'steps': 52395, 'loss/train': 1.1837990283966064} 08/30/2021 22:40:30 - INFO - __main__ - Step 52397: {'lr': 0.0003700848364540872, 'samples': 10060224, 'steps': 52396, 'loss/train': 1.0149868726730347} 08/30/2021 22:40:31 - INFO - __main__ - Step 52398: {'lr': 0.0003700801819732211, 'samples': 10060416, 'steps': 52397, 'loss/train': 1.2782669067382812} 08/30/2021 22:40:31 - INFO - __main__ - Step 52399: {'lr': 0.0003700755274382487, 'samples': 10060608, 'steps': 52398, 'loss/train': 1.7821123600006104} 08/30/2021 22:40:31 - INFO - __main__ - Step 52400: {'lr': 0.0003700708728491722, 'samples': 10060800, 'steps': 52399, 'loss/train': 1.3672199249267578} 08/30/2021 22:40:32 - INFO - __main__ - Step 52401: {'lr': 0.0003700662182059936, 'samples': 10060992, 'steps': 52400, 'loss/train': 1.58430814743042} 08/30/2021 22:40:33 - INFO - __main__ - Step 52402: {'lr': 0.0003700615635087149, 'samples': 10061184, 'steps': 52401, 'loss/train': 1.5426716804504395} 08/30/2021 22:40:34 - INFO - __main__ - Step 52403: {'lr': 0.00037005690875733843, 'samples': 10061376, 'steps': 52402, 'loss/train': 1.6156574487686157} 08/30/2021 22:40:34 - INFO - __main__ - Step 52404: {'lr': 0.00037005225395186616, 'samples': 10061568, 'steps': 52403, 'loss/train': 0.9607453942298889} 08/30/2021 22:40:34 - INFO - __main__ - Step 52405: {'lr': 0.00037004759909230016, 'samples': 10061760, 'steps': 52404, 'loss/train': 1.4426928758621216} 08/30/2021 22:40:35 - INFO - __main__ - Step 52406: {'lr': 0.0003700429441786426, 'samples': 10061952, 'steps': 52405, 'loss/train': 2.022247791290283} 08/30/2021 22:40:36 - INFO - __main__ - Step 52407: {'lr': 0.0003700382892108955, 'samples': 10062144, 'steps': 52406, 'loss/train': 1.1005101203918457} 08/30/2021 22:40:37 - INFO - __main__ - Step 52408: {'lr': 0.000370033634189061, 'samples': 10062336, 'steps': 52407, 'loss/train': 1.1651203632354736} 08/30/2021 22:40:37 - INFO - __main__ - Step 52409: {'lr': 0.00037002897911314126, 'samples': 10062528, 'steps': 52408, 'loss/train': 1.8726836442947388} 08/30/2021 22:40:37 - INFO - __main__ - Step 52410: {'lr': 0.0003700243239831382, 'samples': 10062720, 'steps': 52409, 'loss/train': 1.4716858863830566} 08/30/2021 22:40:38 - INFO - __main__ - Step 52411: {'lr': 0.00037001966879905414, 'samples': 10062912, 'steps': 52410, 'loss/train': 0.6313852071762085} 08/30/2021 22:40:39 - INFO - __main__ - Step 52412: {'lr': 0.00037001501356089103, 'samples': 10063104, 'steps': 52411, 'loss/train': 0.39188385009765625} 08/30/2021 22:40:40 - INFO - __main__ - Step 52413: {'lr': 0.00037001035826865096, 'samples': 10063296, 'steps': 52412, 'loss/train': 1.2267366647720337} 08/30/2021 22:40:40 - INFO - __main__ - Step 52414: {'lr': 0.00037000570292233613, 'samples': 10063488, 'steps': 52413, 'loss/train': 1.1633687019348145} 08/30/2021 22:40:40 - INFO - __main__ - Step 52415: {'lr': 0.00037000104752194857, 'samples': 10063680, 'steps': 52414, 'loss/train': 1.654394507408142} 08/30/2021 22:40:41 - INFO - __main__ - Step 52416: {'lr': 0.0003699963920674905, 'samples': 10063872, 'steps': 52415, 'loss/train': 0.7835513949394226} 08/30/2021 22:40:42 - INFO - __main__ - Step 52417: {'lr': 0.00036999173655896374, 'samples': 10064064, 'steps': 52416, 'loss/train': 0.6513194441795349} 08/30/2021 22:40:43 - INFO - __main__ - Step 52418: {'lr': 0.00036998708099637064, 'samples': 10064256, 'steps': 52417, 'loss/train': 1.0289289951324463} 08/30/2021 22:40:43 - INFO - __main__ - Step 52419: {'lr': 0.00036998242537971315, 'samples': 10064448, 'steps': 52418, 'loss/train': 1.5378395318984985} 08/30/2021 22:40:43 - INFO - __main__ - Step 52420: {'lr': 0.00036997776970899344, 'samples': 10064640, 'steps': 52419, 'loss/train': 0.5900610089302063} 08/30/2021 22:40:44 - INFO - __main__ - Step 52421: {'lr': 0.0003699731139842136, 'samples': 10064832, 'steps': 52420, 'loss/train': 1.4941169023513794} 08/30/2021 22:40:46 - INFO - __main__ - Step 52422: {'lr': 0.0003699684582053758, 'samples': 10065024, 'steps': 52421, 'loss/train': 1.9544343948364258} 08/30/2021 22:40:46 - INFO - __main__ - Step 52423: {'lr': 0.00036996380237248205, 'samples': 10065216, 'steps': 52422, 'loss/train': 1.8961485624313354} 08/30/2021 22:40:46 - INFO - __main__ - Step 52424: {'lr': 0.0003699591464855344, 'samples': 10065408, 'steps': 52423, 'loss/train': 1.8910959959030151} 08/30/2021 22:40:47 - INFO - __main__ - Step 52425: {'lr': 0.00036995449054453503, 'samples': 10065600, 'steps': 52424, 'loss/train': 1.1313529014587402} 08/30/2021 22:40:47 - INFO - __main__ - Step 52426: {'lr': 0.00036994983454948605, 'samples': 10065792, 'steps': 52425, 'loss/train': 1.0586100816726685} 08/30/2021 22:40:48 - INFO - __main__ - Step 52427: {'lr': 0.0003699451785003895, 'samples': 10065984, 'steps': 52426, 'loss/train': 0.24465444684028625} 08/30/2021 22:40:49 - INFO - __main__ - Step 52428: {'lr': 0.0003699405223972475, 'samples': 10066176, 'steps': 52427, 'loss/train': 1.4322913885116577} 08/30/2021 22:40:49 - INFO - __main__ - Step 52429: {'lr': 0.0003699358662400622, 'samples': 10066368, 'steps': 52428, 'loss/train': 1.0574884414672852} 08/30/2021 22:40:50 - INFO - __main__ - Step 52430: {'lr': 0.00036993121002883557, 'samples': 10066560, 'steps': 52429, 'loss/train': 1.6161199808120728} 08/30/2021 22:40:50 - INFO - __main__ - Step 52431: {'lr': 0.0003699265537635698, 'samples': 10066752, 'steps': 52430, 'loss/train': 1.2440955638885498} 08/30/2021 22:40:50 - INFO - __main__ - Step 52432: {'lr': 0.000369921897444267, 'samples': 10066944, 'steps': 52431, 'loss/train': 1.5929423570632935} 08/30/2021 22:40:52 - INFO - __main__ - Step 52433: {'lr': 0.00036991724107092927, 'samples': 10067136, 'steps': 52432, 'loss/train': 0.774193525314331} 08/30/2021 22:40:53 - INFO - __main__ - Step 52434: {'lr': 0.00036991258464355863, 'samples': 10067328, 'steps': 52433, 'loss/train': 1.5099691152572632} 08/30/2021 22:40:53 - INFO - __main__ - Step 52435: {'lr': 0.00036990792816215726, 'samples': 10067520, 'steps': 52434, 'loss/train': 0.6877488493919373} 08/30/2021 22:40:53 - INFO - __main__ - Step 52436: {'lr': 0.0003699032716267273, 'samples': 10067712, 'steps': 52435, 'loss/train': 1.5035206079483032} 08/30/2021 22:40:54 - INFO - __main__ - Step 52437: {'lr': 0.00036989861503727064, 'samples': 10067904, 'steps': 52436, 'loss/train': 0.06316174566745758} 08/30/2021 22:40:56 - INFO - __main__ - Step 52438: {'lr': 0.0003698939583937896, 'samples': 10068096, 'steps': 52437, 'loss/train': 1.3215692043304443} 08/30/2021 22:40:56 - INFO - __main__ - Step 52439: {'lr': 0.0003698893016962861, 'samples': 10068288, 'steps': 52438, 'loss/train': 1.4051921367645264} 08/30/2021 22:40:57 - INFO - __main__ - Step 52440: {'lr': 0.00036988464494476243, 'samples': 10068480, 'steps': 52439, 'loss/train': 1.5172953605651855} 08/30/2021 22:40:57 - INFO - __main__ - Step 52441: {'lr': 0.0003698799881392205, 'samples': 10068672, 'steps': 52440, 'loss/train': 2.1231069564819336} 08/30/2021 22:40:57 - INFO - __main__ - Step 52442: {'lr': 0.00036987533127966253, 'samples': 10068864, 'steps': 52441, 'loss/train': 2.6003541946411133} 08/30/2021 22:40:58 - INFO - __main__ - Step 52443: {'lr': 0.0003698706743660907, 'samples': 10069056, 'steps': 52442, 'loss/train': 1.0377814769744873} 08/30/2021 22:40:59 - INFO - __main__ - Step 52444: {'lr': 0.0003698660173985069, 'samples': 10069248, 'steps': 52443, 'loss/train': 1.5682061910629272} 08/30/2021 22:41:00 - INFO - __main__ - Step 52445: {'lr': 0.0003698613603769133, 'samples': 10069440, 'steps': 52444, 'loss/train': 0.562687873840332} 08/30/2021 22:41:00 - INFO - __main__ - Step 52446: {'lr': 0.00036985670330131205, 'samples': 10069632, 'steps': 52445, 'loss/train': 0.48358389735221863} 08/30/2021 22:41:01 - INFO - __main__ - Step 52447: {'lr': 0.0003698520461717052, 'samples': 10069824, 'steps': 52446, 'loss/train': 1.5141595602035522} 08/30/2021 22:41:01 - INFO - __main__ - Step 52448: {'lr': 0.0003698473889880949, 'samples': 10070016, 'steps': 52447, 'loss/train': 1.0403631925582886} 08/30/2021 22:41:01 - INFO - __main__ - Step 52449: {'lr': 0.0003698427317504832, 'samples': 10070208, 'steps': 52448, 'loss/train': 1.3709241151809692} 08/30/2021 22:41:03 - INFO - __main__ - Step 52450: {'lr': 0.00036983807445887217, 'samples': 10070400, 'steps': 52449, 'loss/train': 1.142431378364563} 08/30/2021 22:41:04 - INFO - __main__ - Step 52451: {'lr': 0.00036983341711326403, 'samples': 10070592, 'steps': 52450, 'loss/train': 0.9625751972198486} 08/30/2021 22:41:04 - INFO - __main__ - Step 52452: {'lr': 0.00036982875971366074, 'samples': 10070784, 'steps': 52451, 'loss/train': 0.9042155146598816} 08/30/2021 22:41:04 - INFO - __main__ - Step 52453: {'lr': 0.00036982410226006445, 'samples': 10070976, 'steps': 52452, 'loss/train': 0.9322705864906311} 08/30/2021 22:41:05 - INFO - __main__ - Step 52454: {'lr': 0.0003698194447524773, 'samples': 10071168, 'steps': 52453, 'loss/train': 0.038686178624629974} 08/30/2021 22:41:06 - INFO - __main__ - Step 52455: {'lr': 0.0003698147871909014, 'samples': 10071360, 'steps': 52454, 'loss/train': 1.4055453538894653} 08/30/2021 22:41:07 - INFO - __main__ - Step 52456: {'lr': 0.0003698101295753388, 'samples': 10071552, 'steps': 52455, 'loss/train': 0.5228376388549805} 08/30/2021 22:41:07 - INFO - __main__ - Step 52457: {'lr': 0.00036980547190579153, 'samples': 10071744, 'steps': 52456, 'loss/train': 2.513827085494995} 08/30/2021 22:41:07 - INFO - __main__ - Step 52458: {'lr': 0.0003698008141822618, 'samples': 10071936, 'steps': 52457, 'loss/train': 0.13966025412082672} 08/30/2021 22:41:08 - INFO - __main__ - Step 52459: {'lr': 0.00036979615640475165, 'samples': 10072128, 'steps': 52458, 'loss/train': 1.3464133739471436} 08/30/2021 22:41:10 - INFO - __main__ - Step 52460: {'lr': 0.0003697914985732632, 'samples': 10072320, 'steps': 52459, 'loss/train': 1.2128422260284424} 08/30/2021 22:41:10 - INFO - __main__ - Step 52461: {'lr': 0.0003697868406877986, 'samples': 10072512, 'steps': 52460, 'loss/train': 0.7102416157722473} 08/30/2021 22:41:11 - INFO - __main__ - Step 52462: {'lr': 0.00036978218274835993, 'samples': 10072704, 'steps': 52461, 'loss/train': 1.5965269804000854} 08/30/2021 22:41:11 - INFO - __main__ - Step 52463: {'lr': 0.0003697775247549492, 'samples': 10072896, 'steps': 52462, 'loss/train': 1.4233697652816772} 08/30/2021 22:41:11 - INFO - __main__ - Step 52464: {'lr': 0.00036977286670756854, 'samples': 10073088, 'steps': 52463, 'loss/train': 0.836117148399353} 08/30/2021 22:41:12 - INFO - __main__ - Step 52465: {'lr': 0.00036976820860622005, 'samples': 10073280, 'steps': 52464, 'loss/train': 1.2603391408920288} 08/30/2021 22:41:13 - INFO - __main__ - Step 52466: {'lr': 0.00036976355045090594, 'samples': 10073472, 'steps': 52465, 'loss/train': 0.262428879737854} 08/30/2021 22:41:14 - INFO - __main__ - Step 52467: {'lr': 0.00036975889224162816, 'samples': 10073664, 'steps': 52466, 'loss/train': 1.2860455513000488} 08/30/2021 22:41:14 - INFO - __main__ - Step 52468: {'lr': 0.000369754233978389, 'samples': 10073856, 'steps': 52467, 'loss/train': 1.350841760635376} 08/30/2021 22:41:14 - INFO - __main__ - Step 52469: {'lr': 0.00036974957566119027, 'samples': 10074048, 'steps': 52468, 'loss/train': 1.792843222618103} 08/30/2021 22:41:15 - INFO - __main__ - Step 52470: {'lr': 0.00036974491729003427, 'samples': 10074240, 'steps': 52469, 'loss/train': 1.0194296836853027} 08/30/2021 22:41:15 - INFO - __main__ - Step 52471: {'lr': 0.00036974025886492306, 'samples': 10074432, 'steps': 52470, 'loss/train': 1.2405890226364136} 08/30/2021 22:41:16 - INFO - __main__ - Step 52472: {'lr': 0.00036973560038585876, 'samples': 10074624, 'steps': 52471, 'loss/train': 0.6181724071502686} 08/30/2021 22:41:17 - INFO - __main__ - Step 52473: {'lr': 0.0003697309418528435, 'samples': 10074816, 'steps': 52472, 'loss/train': 1.273592472076416} 08/30/2021 22:41:17 - INFO - __main__ - Step 52474: {'lr': 0.0003697262832658792, 'samples': 10075008, 'steps': 52473, 'loss/train': 1.6522210836410522} 08/30/2021 22:41:18 - INFO - __main__ - Step 52475: {'lr': 0.00036972162462496817, 'samples': 10075200, 'steps': 52474, 'loss/train': 1.5360100269317627} 08/30/2021 22:41:18 - INFO - __main__ - Step 52476: {'lr': 0.0003697169659301124, 'samples': 10075392, 'steps': 52475, 'loss/train': 1.3837968111038208} 08/30/2021 22:41:20 - INFO - __main__ - Step 52477: {'lr': 0.000369712307181314, 'samples': 10075584, 'steps': 52476, 'loss/train': 0.6994937658309937} 08/30/2021 22:41:20 - INFO - __main__ - Step 52478: {'lr': 0.00036970764837857505, 'samples': 10075776, 'steps': 52477, 'loss/train': 1.1775614023208618} 08/30/2021 22:41:21 - INFO - __main__ - Step 52479: {'lr': 0.0003697029895218978, 'samples': 10075968, 'steps': 52478, 'loss/train': 0.9720891118049622} 08/30/2021 22:41:21 - INFO - __main__ - Step 52480: {'lr': 0.0003696983306112842, 'samples': 10076160, 'steps': 52479, 'loss/train': 1.5918302536010742} 08/30/2021 22:41:21 - INFO - __main__ - Step 52481: {'lr': 0.00036969367164673626, 'samples': 10076352, 'steps': 52480, 'loss/train': 1.1739903688430786} 08/30/2021 22:41:23 - INFO - __main__ - Step 52482: {'lr': 0.0003696890126282563, 'samples': 10076544, 'steps': 52481, 'loss/train': 1.0913363695144653} 08/30/2021 22:41:24 - INFO - __main__ - Step 52483: {'lr': 0.0003696843535558463, 'samples': 10076736, 'steps': 52482, 'loss/train': 1.670129656791687} 08/30/2021 22:41:24 - INFO - __main__ - Step 52484: {'lr': 0.0003696796944295084, 'samples': 10076928, 'steps': 52483, 'loss/train': 1.112436294555664} 08/30/2021 22:41:25 - INFO - __main__ - Step 52485: {'lr': 0.00036967503524924463, 'samples': 10077120, 'steps': 52484, 'loss/train': 1.0224189758300781} 08/30/2021 22:41:25 - INFO - __main__ - Step 52486: {'lr': 0.00036967037601505715, 'samples': 10077312, 'steps': 52485, 'loss/train': 0.052959855645895004} 08/30/2021 22:41:27 - INFO - __main__ - Step 52487: {'lr': 0.000369665716726948, 'samples': 10077504, 'steps': 52486, 'loss/train': 0.562862753868103} 08/30/2021 22:41:27 - INFO - __main__ - Step 52488: {'lr': 0.0003696610573849194, 'samples': 10077696, 'steps': 52487, 'loss/train': 1.8712139129638672} 08/30/2021 22:41:28 - INFO - __main__ - Step 52489: {'lr': 0.0003696563979889733, 'samples': 10077888, 'steps': 52488, 'loss/train': 1.3993226289749146} 08/30/2021 22:41:28 - INFO - __main__ - Step 52490: {'lr': 0.00036965173853911195, 'samples': 10078080, 'steps': 52489, 'loss/train': 1.3976120948791504} 08/30/2021 22:41:28 - INFO - __main__ - Step 52491: {'lr': 0.0003696470790353373, 'samples': 10078272, 'steps': 52490, 'loss/train': 0.6348013281822205} 08/30/2021 22:41:29 - INFO - __main__ - Step 52492: {'lr': 0.0003696424194776516, 'samples': 10078464, 'steps': 52491, 'loss/train': 0.23405209183692932} 08/30/2021 22:41:30 - INFO - __main__ - Step 52493: {'lr': 0.0003696377598660569, 'samples': 10078656, 'steps': 52492, 'loss/train': 1.1613837480545044} 08/30/2021 22:41:31 - INFO - __main__ - Step 52494: {'lr': 0.0003696331002005551, 'samples': 10078848, 'steps': 52493, 'loss/train': 1.0103240013122559} 08/30/2021 22:41:31 - INFO - __main__ - Step 52495: {'lr': 0.00036962844048114856, 'samples': 10079040, 'steps': 52494, 'loss/train': 0.973655104637146} 08/30/2021 22:41:31 - INFO - __main__ - Step 52496: {'lr': 0.0003696237807078393, 'samples': 10079232, 'steps': 52495, 'loss/train': 1.0134670734405518} 08/30/2021 22:41:32 - INFO - __main__ - Step 52497: {'lr': 0.00036961912088062947, 'samples': 10079424, 'steps': 52496, 'loss/train': 1.5024104118347168} 08/30/2021 22:41:33 - INFO - __main__ - Step 52498: {'lr': 0.00036961446099952104, 'samples': 10079616, 'steps': 52497, 'loss/train': 0.07937592267990112} 08/30/2021 22:41:34 - INFO - __main__ - Step 52499: {'lr': 0.0003696098010645162, 'samples': 10079808, 'steps': 52498, 'loss/train': 1.2193210124969482} 08/30/2021 22:41:34 - INFO - __main__ - Step 52500: {'lr': 0.00036960514107561707, 'samples': 10080000, 'steps': 52499, 'loss/train': 1.5616309642791748} 08/30/2021 22:41:34 - INFO - __main__ - Step 52501: {'lr': 0.00036960048103282564, 'samples': 10080192, 'steps': 52500, 'loss/train': 1.1157374382019043} 08/30/2021 22:41:35 - INFO - __main__ - Step 52502: {'lr': 0.00036959582093614406, 'samples': 10080384, 'steps': 52501, 'loss/train': 0.07532504945993423} 08/30/2021 22:41:37 - INFO - __main__ - Step 52503: {'lr': 0.00036959116078557453, 'samples': 10080576, 'steps': 52502, 'loss/train': 1.396376132965088} 08/30/2021 22:41:37 - INFO - __main__ - Step 52504: {'lr': 0.000369586500581119, 'samples': 10080768, 'steps': 52503, 'loss/train': 1.2233335971832275} 08/30/2021 22:41:37 - INFO - __main__ - Step 52505: {'lr': 0.00036958184032277974, 'samples': 10080960, 'steps': 52504, 'loss/train': 3.483546018600464} 08/30/2021 22:41:38 - INFO - __main__ - Step 52506: {'lr': 0.0003695771800105586, 'samples': 10081152, 'steps': 52505, 'loss/train': 1.3218752145767212} 08/30/2021 22:41:38 - INFO - __main__ - Step 52507: {'lr': 0.0003695725196444579, 'samples': 10081344, 'steps': 52506, 'loss/train': 1.6886030435562134} 08/30/2021 22:41:39 - INFO - __main__ - Step 52508: {'lr': 0.0003695678592244797, 'samples': 10081536, 'steps': 52507, 'loss/train': 1.9253101348876953} 08/30/2021 22:41:40 - INFO - __main__ - Step 52509: {'lr': 0.00036956319875062604, 'samples': 10081728, 'steps': 52508, 'loss/train': 1.2918356657028198} 08/30/2021 22:41:40 - INFO - __main__ - Step 52510: {'lr': 0.0003695585382228991, 'samples': 10081920, 'steps': 52509, 'loss/train': 1.4245799779891968} 08/30/2021 22:41:40 - INFO - __main__ - Step 52511: {'lr': 0.0003695538776413009, 'samples': 10082112, 'steps': 52510, 'loss/train': 0.7877821326255798} 08/30/2021 22:41:41 - INFO - __main__ - Step 52512: {'lr': 0.0003695492170058335, 'samples': 10082304, 'steps': 52511, 'loss/train': 1.5490591526031494} 08/30/2021 22:41:41 - INFO - __main__ - Step 52513: {'lr': 0.0003695445563164991, 'samples': 10082496, 'steps': 52512, 'loss/train': 1.1672179698944092} 08/30/2021 22:41:43 - INFO - __main__ - Step 52514: {'lr': 0.00036953989557329976, 'samples': 10082688, 'steps': 52513, 'loss/train': 0.7706567049026489} 08/30/2021 22:41:43 - INFO - __main__ - Step 52515: {'lr': 0.0003695352347762376, 'samples': 10082880, 'steps': 52514, 'loss/train': 0.786012589931488} 08/30/2021 22:41:44 - INFO - __main__ - Step 52516: {'lr': 0.00036953057392531474, 'samples': 10083072, 'steps': 52515, 'loss/train': 0.6681938767433167} 08/30/2021 22:41:44 - INFO - __main__ - Step 52517: {'lr': 0.00036952591302053325, 'samples': 10083264, 'steps': 52516, 'loss/train': 1.8670202493667603} 08/30/2021 22:41:44 - INFO - __main__ - Step 52518: {'lr': 0.00036952125206189516, 'samples': 10083456, 'steps': 52517, 'loss/train': 1.0553967952728271} 08/30/2021 22:41:46 - INFO - __main__ - Step 52519: {'lr': 0.00036951659104940274, 'samples': 10083648, 'steps': 52518, 'loss/train': 1.5796645879745483} 08/30/2021 22:41:46 - INFO - __main__ - Step 52520: {'lr': 0.0003695119299830579, 'samples': 10083840, 'steps': 52519, 'loss/train': 0.9981122016906738} 08/30/2021 22:41:47 - INFO - __main__ - Step 52521: {'lr': 0.0003695072688628628, 'samples': 10084032, 'steps': 52520, 'loss/train': 1.8536217212677002} 08/30/2021 22:41:47 - INFO - __main__ - Step 52522: {'lr': 0.00036950260768881963, 'samples': 10084224, 'steps': 52521, 'loss/train': 1.5423587560653687} 08/30/2021 22:41:47 - INFO - __main__ - Step 52523: {'lr': 0.00036949794646093045, 'samples': 10084416, 'steps': 52522, 'loss/train': 1.0003702640533447} 08/30/2021 22:41:49 - INFO - __main__ - Step 52524: {'lr': 0.00036949328517919735, 'samples': 10084608, 'steps': 52523, 'loss/train': 0.9841527938842773} 08/30/2021 22:41:49 - INFO - __main__ - Step 52525: {'lr': 0.0003694886238436224, 'samples': 10084800, 'steps': 52524, 'loss/train': 1.6726547479629517} 08/30/2021 22:41:50 - INFO - __main__ - Step 52526: {'lr': 0.0003694839624542077, 'samples': 10084992, 'steps': 52525, 'loss/train': 1.4632002115249634} 08/30/2021 22:41:50 - INFO - __main__ - Step 52527: {'lr': 0.0003694793010109553, 'samples': 10085184, 'steps': 52526, 'loss/train': 1.161631464958191} 08/30/2021 22:41:50 - INFO - __main__ - Step 52528: {'lr': 0.00036947463951386743, 'samples': 10085376, 'steps': 52527, 'loss/train': 1.6286373138427734} 08/30/2021 22:41:52 - INFO - __main__ - Step 52529: {'lr': 0.0003694699779629461, 'samples': 10085568, 'steps': 52528, 'loss/train': 1.0300238132476807} 08/30/2021 22:41:52 - INFO - __main__ - Step 52530: {'lr': 0.0003694653163581936, 'samples': 10085760, 'steps': 52529, 'loss/train': 1.3218671083450317} 08/30/2021 22:41:52 - INFO - __main__ - Step 52531: {'lr': 0.0003694606546996117, 'samples': 10085952, 'steps': 52530, 'loss/train': 1.1095834970474243} 08/30/2021 22:41:53 - INFO - __main__ - Step 52532: {'lr': 0.0003694559929872028, 'samples': 10086144, 'steps': 52531, 'loss/train': 1.039170265197754} 08/30/2021 22:41:53 - INFO - __main__ - Step 52533: {'lr': 0.00036945133122096875, 'samples': 10086336, 'steps': 52532, 'loss/train': 1.1130396127700806} 08/30/2021 22:41:56 - INFO - __main__ - Step 52534: {'lr': 0.0003694466694009118, 'samples': 10086528, 'steps': 52533, 'loss/train': 1.0446165800094604} 08/30/2021 22:41:56 - INFO - __main__ - Step 52535: {'lr': 0.00036944200752703405, 'samples': 10086720, 'steps': 52534, 'loss/train': 0.8081503510475159} 08/30/2021 22:41:56 - INFO - __main__ - Step 52536: {'lr': 0.0003694373455993376, 'samples': 10086912, 'steps': 52535, 'loss/train': 1.6280200481414795} 08/30/2021 22:41:57 - INFO - __main__ - Step 52537: {'lr': 0.0003694326836178245, 'samples': 10087104, 'steps': 52536, 'loss/train': 1.4756191968917847} 08/30/2021 22:41:57 - INFO - __main__ - Step 52538: {'lr': 0.0003694280215824969, 'samples': 10087296, 'steps': 52537, 'loss/train': 1.6719201803207397} 08/30/2021 22:41:59 - INFO - __main__ - Step 52539: {'lr': 0.0003694233594933568, 'samples': 10087488, 'steps': 52538, 'loss/train': 0.06519880890846252} 08/30/2021 22:41:59 - INFO - __main__ - Step 52540: {'lr': 0.00036941869735040647, 'samples': 10087680, 'steps': 52539, 'loss/train': 1.1394243240356445} 08/30/2021 22:41:59 - INFO - __main__ - Step 52541: {'lr': 0.0003694140351536479, 'samples': 10087872, 'steps': 52540, 'loss/train': 0.9822244048118591} 08/30/2021 22:42:00 - INFO - __main__ - Step 52542: {'lr': 0.00036940937290308315, 'samples': 10088064, 'steps': 52541, 'loss/train': 0.8806066513061523} 08/30/2021 22:42:00 - INFO - __main__ - Step 52543: {'lr': 0.0003694047105987144, 'samples': 10088256, 'steps': 52542, 'loss/train': 0.9883493185043335} 08/30/2021 22:42:01 - INFO - __main__ - Step 52544: {'lr': 0.00036940004824054376, 'samples': 10088448, 'steps': 52543, 'loss/train': 1.0795314311981201} 08/30/2021 22:42:02 - INFO - __main__ - Step 52545: {'lr': 0.0003693953858285733, 'samples': 10088640, 'steps': 52544, 'loss/train': 1.1583116054534912} 08/30/2021 22:42:02 - INFO - __main__ - Step 52546: {'lr': 0.0003693907233628051, 'samples': 10088832, 'steps': 52545, 'loss/train': 1.451675534248352} 08/30/2021 22:42:03 - INFO - __main__ - Step 52547: {'lr': 0.00036938606084324123, 'samples': 10089024, 'steps': 52546, 'loss/train': 1.2852673530578613} 08/30/2021 22:42:03 - INFO - __main__ - Step 52548: {'lr': 0.00036938139826988393, 'samples': 10089216, 'steps': 52547, 'loss/train': 0.8709478378295898} 08/30/2021 22:42:03 - INFO - __main__ - Step 52549: {'lr': 0.0003693767356427352, 'samples': 10089408, 'steps': 52548, 'loss/train': 2.075584650039673} 08/30/2021 22:42:05 - INFO - __main__ - Step 52550: {'lr': 0.00036937207296179717, 'samples': 10089600, 'steps': 52549, 'loss/train': 1.4703457355499268} 08/30/2021 22:42:06 - INFO - __main__ - Step 52551: {'lr': 0.0003693674102270719, 'samples': 10089792, 'steps': 52550, 'loss/train': 4.392197608947754} 08/30/2021 22:42:06 - INFO - __main__ - Step 52552: {'lr': 0.0003693627474385615, 'samples': 10089984, 'steps': 52551, 'loss/train': 1.2339626550674438} 08/30/2021 22:42:06 - INFO - __main__ - Step 52553: {'lr': 0.00036935808459626806, 'samples': 10090176, 'steps': 52552, 'loss/train': 0.08571885526180267} 08/30/2021 22:42:07 - INFO - __main__ - Step 52554: {'lr': 0.00036935342170019375, 'samples': 10090368, 'steps': 52553, 'loss/train': 0.11021265387535095} 08/30/2021 22:42:07 - INFO - __main__ - Step 52555: {'lr': 0.00036934875875034063, 'samples': 10090560, 'steps': 52554, 'loss/train': 0.6586523652076721} 08/30/2021 22:42:09 - INFO - __main__ - Step 52556: {'lr': 0.0003693440957467108, 'samples': 10090752, 'steps': 52555, 'loss/train': 1.1877292394638062} 08/30/2021 22:42:09 - INFO - __main__ - Step 52557: {'lr': 0.00036933943268930636, 'samples': 10090944, 'steps': 52556, 'loss/train': 1.6580500602722168} 08/30/2021 22:42:09 - INFO - __main__ - Step 52558: {'lr': 0.00036933476957812944, 'samples': 10091136, 'steps': 52557, 'loss/train': 1.4758145809173584} 08/30/2021 22:42:10 - INFO - __main__ - Step 52559: {'lr': 0.0003693301064131821, 'samples': 10091328, 'steps': 52558, 'loss/train': 1.507752537727356} 08/30/2021 22:42:10 - INFO - __main__ - Step 52560: {'lr': 0.0003693254431944664, 'samples': 10091520, 'steps': 52559, 'loss/train': 1.9612290859222412} 08/30/2021 22:42:10 - INFO - __main__ - Step 52561: {'lr': 0.00036932077992198455, 'samples': 10091712, 'steps': 52560, 'loss/train': 0.7714027762413025} 08/30/2021 22:42:12 - INFO - __main__ - Step 52562: {'lr': 0.0003693161165957386, 'samples': 10091904, 'steps': 52561, 'loss/train': 0.5221697688102722} 08/30/2021 22:42:12 - INFO - __main__ - Step 52563: {'lr': 0.0003693114532157306, 'samples': 10092096, 'steps': 52562, 'loss/train': 1.4347823858261108} 08/30/2021 22:42:13 - INFO - __main__ - Step 52564: {'lr': 0.00036930678978196283, 'samples': 10092288, 'steps': 52563, 'loss/train': 1.3313177824020386} 08/30/2021 22:42:13 - INFO - __main__ - Step 52565: {'lr': 0.00036930212629443716, 'samples': 10092480, 'steps': 52564, 'loss/train': 1.804288625717163} 08/30/2021 22:42:13 - INFO - __main__ - Step 52566: {'lr': 0.00036929746275315577, 'samples': 10092672, 'steps': 52565, 'loss/train': 1.411015510559082} 08/30/2021 22:42:15 - INFO - __main__ - Step 52567: {'lr': 0.0003692927991581208, 'samples': 10092864, 'steps': 52566, 'loss/train': 1.4452924728393555} 08/30/2021 22:42:15 - INFO - __main__ - Step 52568: {'lr': 0.0003692881355093344, 'samples': 10093056, 'steps': 52567, 'loss/train': 1.1412122249603271} 08/30/2021 22:42:16 - INFO - __main__ - Step 52569: {'lr': 0.00036928347180679847, 'samples': 10093248, 'steps': 52568, 'loss/train': 1.6784499883651733} 08/30/2021 22:42:16 - INFO - __main__ - Step 52570: {'lr': 0.0003692788080505154, 'samples': 10093440, 'steps': 52569, 'loss/train': 1.5619900226593018} 08/30/2021 22:42:16 - INFO - __main__ - Step 52571: {'lr': 0.0003692741442404871, 'samples': 10093632, 'steps': 52570, 'loss/train': 1.658601999282837} 08/30/2021 22:42:18 - INFO - __main__ - Step 52572: {'lr': 0.0003692694803767157, 'samples': 10093824, 'steps': 52571, 'loss/train': 1.1120797395706177} 08/30/2021 22:42:19 - INFO - __main__ - Step 52573: {'lr': 0.0003692648164592033, 'samples': 10094016, 'steps': 52572, 'loss/train': 1.9891489744186401} 08/30/2021 22:42:19 - INFO - __main__ - Step 52574: {'lr': 0.00036926015248795195, 'samples': 10094208, 'steps': 52573, 'loss/train': 1.211263656616211} 08/30/2021 22:42:19 - INFO - __main__ - Step 52575: {'lr': 0.0003692554884629639, 'samples': 10094400, 'steps': 52574, 'loss/train': 1.5121631622314453} 08/30/2021 22:42:20 - INFO - __main__ - Step 52576: {'lr': 0.00036925082438424116, 'samples': 10094592, 'steps': 52575, 'loss/train': 0.8200514912605286} 08/30/2021 22:42:21 - INFO - __main__ - Step 52577: {'lr': 0.00036924616025178585, 'samples': 10094784, 'steps': 52576, 'loss/train': 1.1563302278518677} 08/30/2021 22:42:22 - INFO - __main__ - Step 52578: {'lr': 0.0003692414960656, 'samples': 10094976, 'steps': 52577, 'loss/train': 1.3313965797424316} 08/30/2021 22:42:22 - INFO - __main__ - Step 52579: {'lr': 0.00036923683182568586, 'samples': 10095168, 'steps': 52578, 'loss/train': 1.2651478052139282} 08/30/2021 22:42:22 - INFO - __main__ - Step 52580: {'lr': 0.00036923216753204536, 'samples': 10095360, 'steps': 52579, 'loss/train': 1.4931687116622925} 08/30/2021 22:42:23 - INFO - __main__ - Step 52581: {'lr': 0.00036922750318468074, 'samples': 10095552, 'steps': 52580, 'loss/train': 1.0046278238296509} 08/30/2021 22:42:24 - INFO - __main__ - Step 52582: {'lr': 0.00036922283878359396, 'samples': 10095744, 'steps': 52581, 'loss/train': 0.8828812837600708} 08/30/2021 22:42:25 - INFO - __main__ - Step 52583: {'lr': 0.0003692181743287873, 'samples': 10095936, 'steps': 52582, 'loss/train': 0.6817058324813843} 08/30/2021 22:42:25 - INFO - __main__ - Step 52584: {'lr': 0.0003692135098202628, 'samples': 10096128, 'steps': 52583, 'loss/train': 1.639438271522522} 08/30/2021 22:42:25 - INFO - __main__ - Step 52585: {'lr': 0.0003692088452580225, 'samples': 10096320, 'steps': 52584, 'loss/train': 1.2934675216674805} 08/30/2021 22:42:26 - INFO - __main__ - Step 52586: {'lr': 0.00036920418064206845, 'samples': 10096512, 'steps': 52585, 'loss/train': 1.506569266319275} 08/30/2021 22:42:28 - INFO - __main__ - Step 52587: {'lr': 0.0003691995159724029, 'samples': 10096704, 'steps': 52586, 'loss/train': 1.4008046388626099} 08/30/2021 22:42:28 - INFO - __main__ - Step 52588: {'lr': 0.00036919485124902785, 'samples': 10096896, 'steps': 52587, 'loss/train': 0.9199028015136719} 08/30/2021 22:42:28 - INFO - __main__ - Step 52589: {'lr': 0.00036919018647194545, 'samples': 10097088, 'steps': 52588, 'loss/train': 1.547400712966919} 08/30/2021 22:42:29 - INFO - __main__ - Step 52590: {'lr': 0.0003691855216411578, 'samples': 10097280, 'steps': 52589, 'loss/train': 1.3237316608428955} 08/30/2021 22:42:29 - INFO - __main__ - Step 52591: {'lr': 0.00036918085675666706, 'samples': 10097472, 'steps': 52590, 'loss/train': 0.9180843234062195} 08/30/2021 22:42:30 - INFO - __main__ - Step 52592: {'lr': 0.00036917619181847525, 'samples': 10097664, 'steps': 52591, 'loss/train': 1.5750412940979004} 08/30/2021 22:42:31 - INFO - __main__ - Step 52593: {'lr': 0.00036917152682658437, 'samples': 10097856, 'steps': 52592, 'loss/train': 0.6543641090393066} 08/30/2021 22:42:32 - INFO - __main__ - Step 52594: {'lr': 0.0003691668617809968, 'samples': 10098048, 'steps': 52593, 'loss/train': 1.0030410289764404} 08/30/2021 22:42:32 - INFO - __main__ - Step 52595: {'lr': 0.00036916219668171435, 'samples': 10098240, 'steps': 52594, 'loss/train': 0.15339718759059906} 08/30/2021 22:42:33 - INFO - __main__ - Step 52596: {'lr': 0.0003691575315287393, 'samples': 10098432, 'steps': 52595, 'loss/train': 1.2302451133728027} 08/30/2021 22:42:33 - INFO - __main__ - Step 52597: {'lr': 0.00036915286632207374, 'samples': 10098624, 'steps': 52596, 'loss/train': 1.6820393800735474} 08/30/2021 22:42:34 - INFO - __main__ - Step 52598: {'lr': 0.0003691482010617197, 'samples': 10098816, 'steps': 52597, 'loss/train': 0.985542893409729} 08/30/2021 22:42:35 - INFO - __main__ - Step 52599: {'lr': 0.00036914353574767935, 'samples': 10099008, 'steps': 52598, 'loss/train': 1.9780583381652832} 08/30/2021 22:42:35 - INFO - __main__ - Step 52600: {'lr': 0.0003691388703799547, 'samples': 10099200, 'steps': 52599, 'loss/train': 1.3220382928848267} 08/30/2021 22:42:36 - INFO - __main__ - Step 52601: {'lr': 0.00036913420495854793, 'samples': 10099392, 'steps': 52600, 'loss/train': 1.5783418416976929} 08/30/2021 22:42:36 - INFO - __main__ - Step 52602: {'lr': 0.00036912953948346115, 'samples': 10099584, 'steps': 52601, 'loss/train': 1.1676360368728638} 08/30/2021 22:42:38 - INFO - __main__ - Step 52603: {'lr': 0.00036912487395469645, 'samples': 10099776, 'steps': 52602, 'loss/train': 1.9210675954818726} 08/30/2021 22:42:38 - INFO - __main__ - Step 52604: {'lr': 0.0003691202083722559, 'samples': 10099968, 'steps': 52603, 'loss/train': 1.2477043867111206} 08/30/2021 22:42:39 - INFO - __main__ - Step 52605: {'lr': 0.0003691155427361416, 'samples': 10100160, 'steps': 52604, 'loss/train': 0.9537261724472046} 08/30/2021 22:42:39 - INFO - __main__ - Step 52606: {'lr': 0.0003691108770463557, 'samples': 10100352, 'steps': 52605, 'loss/train': 1.6194697618484497} 08/30/2021 22:42:39 - INFO - __main__ - Step 52607: {'lr': 0.00036910621130290027, 'samples': 10100544, 'steps': 52606, 'loss/train': 1.5384349822998047} 08/30/2021 22:42:41 - INFO - __main__ - Step 52608: {'lr': 0.0003691015455057775, 'samples': 10100736, 'steps': 52607, 'loss/train': 0.14303551614284515} 08/30/2021 22:42:42 - INFO - __main__ - Step 52609: {'lr': 0.0003690968796549893, 'samples': 10100928, 'steps': 52608, 'loss/train': 1.1941648721694946} 08/30/2021 22:42:42 - INFO - __main__ - Step 52610: {'lr': 0.0003690922137505379, 'samples': 10101120, 'steps': 52609, 'loss/train': 1.174319863319397} 08/30/2021 22:42:42 - INFO - __main__ - Step 52611: {'lr': 0.00036908754779242545, 'samples': 10101312, 'steps': 52610, 'loss/train': 0.8619337677955627} 08/30/2021 22:42:43 - INFO - __main__ - Step 52612: {'lr': 0.00036908288178065393, 'samples': 10101504, 'steps': 52611, 'loss/train': 1.4088321924209595} 08/30/2021 22:42:43 - INFO - __main__ - Step 52613: {'lr': 0.00036907821571522553, 'samples': 10101696, 'steps': 52612, 'loss/train': 1.6077200174331665} 08/30/2021 22:42:45 - INFO - __main__ - Step 52614: {'lr': 0.0003690735495961423, 'samples': 10101888, 'steps': 52613, 'loss/train': 1.0514719486236572} 08/30/2021 22:42:45 - INFO - __main__ - Step 52615: {'lr': 0.0003690688834234064, 'samples': 10102080, 'steps': 52614, 'loss/train': 1.4516382217407227} 08/30/2021 22:42:45 - INFO - __main__ - Step 52616: {'lr': 0.0003690642171970198, 'samples': 10102272, 'steps': 52615, 'loss/train': 1.3071733713150024} 08/30/2021 22:42:46 - INFO - __main__ - Step 52617: {'lr': 0.0003690595509169848, 'samples': 10102464, 'steps': 52616, 'loss/train': 1.0561918020248413} 08/30/2021 22:42:46 - INFO - __main__ - Step 52618: {'lr': 0.00036905488458330337, 'samples': 10102656, 'steps': 52617, 'loss/train': 0.8344602584838867} 08/30/2021 22:42:48 - INFO - __main__ - Step 52619: {'lr': 0.00036905021819597767, 'samples': 10102848, 'steps': 52618, 'loss/train': 1.8325072526931763} 08/30/2021 22:42:48 - INFO - __main__ - Step 52620: {'lr': 0.00036904555175500977, 'samples': 10103040, 'steps': 52619, 'loss/train': 1.5285195112228394} 08/30/2021 22:42:49 - INFO - __main__ - Step 52621: {'lr': 0.00036904088526040177, 'samples': 10103232, 'steps': 52620, 'loss/train': 0.07646815478801727} 08/30/2021 22:42:49 - INFO - __main__ - Step 52622: {'lr': 0.00036903621871215575, 'samples': 10103424, 'steps': 52621, 'loss/train': 1.5410460233688354} 08/30/2021 22:42:49 - INFO - __main__ - Step 52623: {'lr': 0.0003690315521102739, 'samples': 10103616, 'steps': 52622, 'loss/train': 1.5301294326782227} 08/30/2021 22:42:51 - INFO - __main__ - Step 52624: {'lr': 0.0003690268854547583, 'samples': 10103808, 'steps': 52623, 'loss/train': 0.24799980223178864} 08/30/2021 22:42:51 - INFO - __main__ - Step 52625: {'lr': 0.00036902221874561097, 'samples': 10104000, 'steps': 52624, 'loss/train': 1.080647587776184} 08/30/2021 22:42:52 - INFO - __main__ - Step 52626: {'lr': 0.00036901755198283403, 'samples': 10104192, 'steps': 52625, 'loss/train': 2.303861379623413} 08/30/2021 22:42:52 - INFO - __main__ - Step 52627: {'lr': 0.0003690128851664297, 'samples': 10104384, 'steps': 52626, 'loss/train': 0.7482075691223145} 08/30/2021 22:42:52 - INFO - __main__ - Step 52628: {'lr': 0.0003690082182964, 'samples': 10104576, 'steps': 52627, 'loss/train': 1.6616662740707397} 08/30/2021 22:42:54 - INFO - __main__ - Step 52629: {'lr': 0.00036900355137274696, 'samples': 10104768, 'steps': 52628, 'loss/train': 1.4044233560562134} 08/30/2021 22:42:54 - INFO - __main__ - Step 52630: {'lr': 0.00036899888439547276, 'samples': 10104960, 'steps': 52629, 'loss/train': 1.37495756149292} 08/30/2021 22:42:55 - INFO - __main__ - Step 52631: {'lr': 0.00036899421736457955, 'samples': 10105152, 'steps': 52630, 'loss/train': 1.475831151008606} 08/30/2021 22:42:55 - INFO - __main__ - Step 52632: {'lr': 0.00036898955028006936, 'samples': 10105344, 'steps': 52631, 'loss/train': 1.1597403287887573} 08/30/2021 22:42:55 - INFO - __main__ - Step 52633: {'lr': 0.0003689848831419443, 'samples': 10105536, 'steps': 52632, 'loss/train': 0.05094965919852257} 08/30/2021 22:42:57 - INFO - __main__ - Step 52634: {'lr': 0.0003689802159502065, 'samples': 10105728, 'steps': 52633, 'loss/train': 1.598905086517334} 08/30/2021 22:42:58 - INFO - __main__ - Step 52635: {'lr': 0.00036897554870485804, 'samples': 10105920, 'steps': 52634, 'loss/train': 1.7844258546829224} 08/30/2021 22:42:58 - INFO - __main__ - Step 52636: {'lr': 0.000368970881405901, 'samples': 10106112, 'steps': 52635, 'loss/train': 1.5041440725326538} 08/30/2021 22:42:58 - INFO - __main__ - Step 52637: {'lr': 0.0003689662140533376, 'samples': 10106304, 'steps': 52636, 'loss/train': 1.1380068063735962} 08/30/2021 22:42:59 - INFO - __main__ - Step 52638: {'lr': 0.00036896154664716987, 'samples': 10106496, 'steps': 52637, 'loss/train': 1.655505895614624} 08/30/2021 22:43:01 - INFO - __main__ - Step 52639: {'lr': 0.00036895687918739984, 'samples': 10106688, 'steps': 52638, 'loss/train': 1.340161919593811} 08/30/2021 22:43:01 - INFO - __main__ - Step 52640: {'lr': 0.0003689522116740296, 'samples': 10106880, 'steps': 52639, 'loss/train': 1.5741502046585083} 08/30/2021 22:43:02 - INFO - __main__ - Step 52641: {'lr': 0.0003689475441070615, 'samples': 10107072, 'steps': 52640, 'loss/train': 0.921815037727356} 08/30/2021 22:43:02 - INFO - __main__ - Step 52642: {'lr': 0.0003689428764864974, 'samples': 10107264, 'steps': 52641, 'loss/train': 1.598400354385376} 08/30/2021 22:43:02 - INFO - __main__ - Step 52643: {'lr': 0.0003689382088123394, 'samples': 10107456, 'steps': 52642, 'loss/train': 1.4491839408874512} 08/30/2021 22:43:03 - INFO - __main__ - Step 52644: {'lr': 0.0003689335410845898, 'samples': 10107648, 'steps': 52643, 'loss/train': 0.5983690023422241} 08/30/2021 22:43:05 - INFO - __main__ - Step 52645: {'lr': 0.00036892887330325054, 'samples': 10107840, 'steps': 52644, 'loss/train': 1.2478861808776855} 08/30/2021 22:43:05 - INFO - __main__ - Step 52646: {'lr': 0.00036892420546832375, 'samples': 10108032, 'steps': 52645, 'loss/train': 1.0929803848266602} 08/30/2021 22:43:05 - INFO - __main__ - Step 52647: {'lr': 0.0003689195375798115, 'samples': 10108224, 'steps': 52646, 'loss/train': 2.4148240089416504} 08/30/2021 22:43:06 - INFO - __main__ - Step 52648: {'lr': 0.00036891486963771603, 'samples': 10108416, 'steps': 52647, 'loss/train': 1.5363584756851196} 08/30/2021 22:43:06 - INFO - __main__ - Step 52649: {'lr': 0.00036891020164203924, 'samples': 10108608, 'steps': 52648, 'loss/train': 1.0536298751831055} 08/30/2021 22:43:07 - INFO - __main__ - Step 52650: {'lr': 0.00036890553359278345, 'samples': 10108800, 'steps': 52649, 'loss/train': 0.6469190716743469} 08/30/2021 22:43:08 - INFO - __main__ - Step 52651: {'lr': 0.0003689008654899507, 'samples': 10108992, 'steps': 52650, 'loss/train': 5.747594356536865} 08/30/2021 22:43:08 - INFO - __main__ - Step 52652: {'lr': 0.00036889619733354297, 'samples': 10109184, 'steps': 52651, 'loss/train': 1.6629053354263306} 08/30/2021 22:43:09 - INFO - __main__ - Step 52653: {'lr': 0.0003688915291235625, 'samples': 10109376, 'steps': 52652, 'loss/train': 1.4267748594284058} 08/30/2021 22:43:09 - INFO - __main__ - Step 52654: {'lr': 0.0003688868608600113, 'samples': 10109568, 'steps': 52653, 'loss/train': 0.9135183095932007} 08/30/2021 22:43:09 - INFO - __main__ - Step 52655: {'lr': 0.00036888219254289147, 'samples': 10109760, 'steps': 52654, 'loss/train': 1.3949719667434692} 08/30/2021 22:43:11 - INFO - __main__ - Step 52656: {'lr': 0.0003688775241722052, 'samples': 10109952, 'steps': 52655, 'loss/train': 0.8932076096534729} 08/30/2021 22:43:11 - INFO - __main__ - Step 52657: {'lr': 0.0003688728557479546, 'samples': 10110144, 'steps': 52656, 'loss/train': 1.6523542404174805} 08/30/2021 22:43:12 - INFO - __main__ - Step 52658: {'lr': 0.00036886818727014173, 'samples': 10110336, 'steps': 52657, 'loss/train': 1.1122334003448486} 08/30/2021 22:43:12 - INFO - __main__ - Step 52659: {'lr': 0.0003688635187387686, 'samples': 10110528, 'steps': 52658, 'loss/train': 1.2266416549682617} 08/30/2021 22:43:12 - INFO - __main__ - Step 52660: {'lr': 0.0003688588501538375, 'samples': 10110720, 'steps': 52659, 'loss/train': 1.3486294746398926} 08/30/2021 22:43:14 - INFO - __main__ - Step 52661: {'lr': 0.00036885418151535033, 'samples': 10110912, 'steps': 52660, 'loss/train': 0.9828211665153503} 08/30/2021 22:43:15 - INFO - __main__ - Step 52662: {'lr': 0.00036884951282330935, 'samples': 10111104, 'steps': 52661, 'loss/train': 0.13739511370658875} 08/30/2021 22:43:15 - INFO - __main__ - Step 52663: {'lr': 0.00036884484407771664, 'samples': 10111296, 'steps': 52662, 'loss/train': 0.30096691846847534} 08/30/2021 22:43:15 - INFO - __main__ - Step 52664: {'lr': 0.00036884017527857426, 'samples': 10111488, 'steps': 52663, 'loss/train': 0.5852181911468506} 08/30/2021 22:43:16 - INFO - __main__ - Step 52665: {'lr': 0.0003688355064258844, 'samples': 10111680, 'steps': 52664, 'loss/train': 1.3313403129577637} 08/30/2021 22:43:16 - INFO - __main__ - Step 52666: {'lr': 0.00036883083751964896, 'samples': 10111872, 'steps': 52665, 'loss/train': 1.8639763593673706} 08/30/2021 22:43:17 - INFO - __main__ - Step 52667: {'lr': 0.00036882616855987027, 'samples': 10112064, 'steps': 52666, 'loss/train': 0.8944418430328369} 08/30/2021 22:43:18 - INFO - __main__ - Step 52668: {'lr': 0.0003688214995465503, 'samples': 10112256, 'steps': 52667, 'loss/train': 1.2589043378829956} 08/30/2021 22:43:18 - INFO - __main__ - Step 52669: {'lr': 0.00036881683047969115, 'samples': 10112448, 'steps': 52668, 'loss/train': 1.3450703620910645} 08/30/2021 22:43:19 - INFO - __main__ - Step 52670: {'lr': 0.00036881216135929506, 'samples': 10112640, 'steps': 52669, 'loss/train': 1.783084750175476} 08/30/2021 22:43:19 - INFO - __main__ - Step 52671: {'lr': 0.0003688074921853641, 'samples': 10112832, 'steps': 52670, 'loss/train': 0.8529743552207947} 08/30/2021 22:43:20 - INFO - __main__ - Step 52672: {'lr': 0.0003688028229579002, 'samples': 10113024, 'steps': 52671, 'loss/train': 1.4379161596298218} 08/30/2021 22:43:21 - INFO - __main__ - Step 52673: {'lr': 0.0003687981536769056, 'samples': 10113216, 'steps': 52672, 'loss/train': 1.2739863395690918} 08/30/2021 22:43:21 - INFO - __main__ - Step 52674: {'lr': 0.00036879348434238235, 'samples': 10113408, 'steps': 52673, 'loss/train': 0.9519485831260681} 08/30/2021 22:43:22 - INFO - __main__ - Step 52675: {'lr': 0.00036878881495433264, 'samples': 10113600, 'steps': 52674, 'loss/train': 1.9314029216766357} 08/30/2021 22:43:22 - INFO - __main__ - Step 52676: {'lr': 0.0003687841455127585, 'samples': 10113792, 'steps': 52675, 'loss/train': 1.0641555786132812} 08/30/2021 22:43:23 - INFO - __main__ - Step 52677: {'lr': 0.0003687794760176621, 'samples': 10113984, 'steps': 52676, 'loss/train': 1.4101535081863403} 08/30/2021 22:43:24 - INFO - __main__ - Step 52678: {'lr': 0.0003687748064690455, 'samples': 10114176, 'steps': 52677, 'loss/train': 0.6032649278640747} 08/30/2021 22:43:24 - INFO - __main__ - Step 52679: {'lr': 0.0003687701368669108, 'samples': 10114368, 'steps': 52678, 'loss/train': 0.7004330158233643} 08/30/2021 22:43:25 - INFO - __main__ - Step 52680: {'lr': 0.0003687654672112601, 'samples': 10114560, 'steps': 52679, 'loss/train': 0.7790058255195618} 08/30/2021 22:43:25 - INFO - __main__ - Step 52681: {'lr': 0.00036876079750209544, 'samples': 10114752, 'steps': 52680, 'loss/train': 1.4016163349151611} 08/30/2021 22:43:25 - INFO - __main__ - Step 52682: {'lr': 0.00036875612773941906, 'samples': 10114944, 'steps': 52681, 'loss/train': 1.2279847860336304} 08/30/2021 22:43:27 - INFO - __main__ - Step 52683: {'lr': 0.00036875145792323303, 'samples': 10115136, 'steps': 52682, 'loss/train': 1.1010525226593018} 08/30/2021 22:43:27 - INFO - __main__ - Step 52684: {'lr': 0.0003687467880535394, 'samples': 10115328, 'steps': 52683, 'loss/train': 0.8829358816146851} 08/30/2021 22:43:28 - INFO - __main__ - Step 52685: {'lr': 0.00036874211813034034, 'samples': 10115520, 'steps': 52684, 'loss/train': 0.8388954401016235} 08/30/2021 22:43:28 - INFO - __main__ - Step 52686: {'lr': 0.00036873744815363785, 'samples': 10115712, 'steps': 52685, 'loss/train': 1.8235160112380981} 08/30/2021 22:43:28 - INFO - __main__ - Step 52687: {'lr': 0.0003687327781234341, 'samples': 10115904, 'steps': 52686, 'loss/train': 1.9645105600357056} 08/30/2021 22:43:30 - INFO - __main__ - Step 52688: {'lr': 0.0003687281080397312, 'samples': 10116096, 'steps': 52687, 'loss/train': 0.9194105267524719} 08/30/2021 22:43:30 - INFO - __main__ - Step 52689: {'lr': 0.0003687234379025313, 'samples': 10116288, 'steps': 52688, 'loss/train': 1.5918776988983154} 08/30/2021 22:43:31 - INFO - __main__ - Step 52690: {'lr': 0.00036871876771183635, 'samples': 10116480, 'steps': 52689, 'loss/train': 1.2447401285171509} 08/30/2021 22:43:31 - INFO - __main__ - Step 52691: {'lr': 0.0003687140974676486, 'samples': 10116672, 'steps': 52690, 'loss/train': 1.4222571849822998} 08/30/2021 22:43:31 - INFO - __main__ - Step 52692: {'lr': 0.0003687094271699702, 'samples': 10116864, 'steps': 52691, 'loss/train': 1.7469810247421265} 08/30/2021 22:43:33 - INFO - __main__ - Step 52693: {'lr': 0.00036870475681880313, 'samples': 10117056, 'steps': 52692, 'loss/train': 0.7537859082221985} 08/30/2021 22:43:33 - INFO - __main__ - Step 52694: {'lr': 0.00036870008641414945, 'samples': 10117248, 'steps': 52693, 'loss/train': 1.3100506067276} 08/30/2021 22:43:34 - INFO - __main__ - Step 52695: {'lr': 0.0003686954159560114, 'samples': 10117440, 'steps': 52694, 'loss/train': 0.9604321718215942} 08/30/2021 22:43:34 - INFO - __main__ - Step 52696: {'lr': 0.00036869074544439097, 'samples': 10117632, 'steps': 52695, 'loss/train': 0.7988246083259583} 08/30/2021 22:43:34 - INFO - __main__ - Step 52697: {'lr': 0.00036868607487929034, 'samples': 10117824, 'steps': 52696, 'loss/train': 1.2913399934768677} 08/30/2021 22:43:37 - INFO - __main__ - Step 52698: {'lr': 0.00036868140426071165, 'samples': 10118016, 'steps': 52697, 'loss/train': 2.644193649291992} 08/30/2021 22:43:37 - INFO - __main__ - Step 52699: {'lr': 0.00036867673358865696, 'samples': 10118208, 'steps': 52698, 'loss/train': 1.2751719951629639} 08/30/2021 22:43:37 - INFO - __main__ - Step 52700: {'lr': 0.0003686720628631283, 'samples': 10118400, 'steps': 52699, 'loss/train': 1.481706976890564} 08/30/2021 22:43:38 - INFO - __main__ - Step 52701: {'lr': 0.0003686673920841278, 'samples': 10118592, 'steps': 52700, 'loss/train': 1.2402658462524414} 08/30/2021 22:43:38 - INFO - __main__ - Step 52702: {'lr': 0.0003686627212516577, 'samples': 10118784, 'steps': 52701, 'loss/train': 1.3068758249282837} 08/30/2021 22:43:40 - INFO - __main__ - Step 52703: {'lr': 0.0003686580503657199, 'samples': 10118976, 'steps': 52702, 'loss/train': 1.7609869241714478} 08/30/2021 22:43:40 - INFO - __main__ - Step 52704: {'lr': 0.00036865337942631674, 'samples': 10119168, 'steps': 52703, 'loss/train': 0.024495387449860573} 08/30/2021 22:43:41 - INFO - __main__ - Step 52705: {'lr': 0.00036864870843345015, 'samples': 10119360, 'steps': 52704, 'loss/train': 0.024711281061172485} 08/30/2021 22:43:41 - INFO - __main__ - Step 52706: {'lr': 0.00036864403738712226, 'samples': 10119552, 'steps': 52705, 'loss/train': 1.6923173666000366} 08/30/2021 22:43:41 - INFO - __main__ - Step 52707: {'lr': 0.00036863936628733524, 'samples': 10119744, 'steps': 52706, 'loss/train': 1.699450135231018} 08/30/2021 22:43:42 - INFO - __main__ - Step 52708: {'lr': 0.0003686346951340911, 'samples': 10119936, 'steps': 52707, 'loss/train': 1.4208524227142334} 08/30/2021 22:43:43 - INFO - __main__ - Step 52709: {'lr': 0.000368630023927392, 'samples': 10120128, 'steps': 52708, 'loss/train': 1.3344050645828247} 08/30/2021 22:43:44 - INFO - __main__ - Step 52710: {'lr': 0.00036862535266724006, 'samples': 10120320, 'steps': 52709, 'loss/train': 1.0172569751739502} 08/30/2021 22:43:44 - INFO - __main__ - Step 52711: {'lr': 0.0003686206813536374, 'samples': 10120512, 'steps': 52710, 'loss/train': 1.1167689561843872} 08/30/2021 22:43:44 - INFO - __main__ - Step 52712: {'lr': 0.0003686160099865861, 'samples': 10120704, 'steps': 52711, 'loss/train': 1.4729176759719849} 08/30/2021 22:43:45 - INFO - __main__ - Step 52713: {'lr': 0.00036861133856608817, 'samples': 10120896, 'steps': 52712, 'loss/train': 1.7260874509811401} 08/30/2021 22:43:46 - INFO - __main__ - Step 52714: {'lr': 0.0003686066670921459, 'samples': 10121088, 'steps': 52713, 'loss/train': 0.37413209676742554} 08/30/2021 22:43:47 - INFO - __main__ - Step 52715: {'lr': 0.00036860199556476125, 'samples': 10121280, 'steps': 52714, 'loss/train': 1.3504774570465088} 08/30/2021 22:43:47 - INFO - __main__ - Step 52716: {'lr': 0.0003685973239839364, 'samples': 10121472, 'steps': 52715, 'loss/train': 1.494686484336853} 08/30/2021 22:43:47 - INFO - __main__ - Step 52717: {'lr': 0.0003685926523496733, 'samples': 10121664, 'steps': 52716, 'loss/train': 1.6282421350479126} 08/30/2021 22:43:48 - INFO - __main__ - Step 52718: {'lr': 0.0003685879806619743, 'samples': 10121856, 'steps': 52717, 'loss/train': 1.5516606569290161} 08/30/2021 22:43:50 - INFO - __main__ - Step 52719: {'lr': 0.0003685833089208414, 'samples': 10122048, 'steps': 52718, 'loss/train': 1.2628803253173828} 08/30/2021 22:43:50 - INFO - __main__ - Step 52720: {'lr': 0.00036857863712627664, 'samples': 10122240, 'steps': 52719, 'loss/train': 1.076051950454712} 08/30/2021 22:43:50 - INFO - __main__ - Step 52721: {'lr': 0.0003685739652782822, 'samples': 10122432, 'steps': 52720, 'loss/train': 1.0960218906402588} 08/30/2021 22:43:51 - INFO - __main__ - Step 52722: {'lr': 0.00036856929337686015, 'samples': 10122624, 'steps': 52721, 'loss/train': 1.4360874891281128} 08/30/2021 22:43:51 - INFO - __main__ - Step 52723: {'lr': 0.0003685646214220126, 'samples': 10122816, 'steps': 52722, 'loss/train': 1.5417126417160034} 08/30/2021 22:43:52 - INFO - __main__ - Step 52724: {'lr': 0.00036855994941374165, 'samples': 10123008, 'steps': 52723, 'loss/train': 0.7886225581169128} 08/30/2021 22:43:53 - INFO - __main__ - Step 52725: {'lr': 0.0003685552773520495, 'samples': 10123200, 'steps': 52724, 'loss/train': 0.16519133746623993} 08/30/2021 22:43:54 - INFO - __main__ - Step 52726: {'lr': 0.0003685506052369381, 'samples': 10123392, 'steps': 52725, 'loss/train': 1.3718961477279663} 08/30/2021 22:43:54 - INFO - __main__ - Step 52727: {'lr': 0.00036854593306840955, 'samples': 10123584, 'steps': 52726, 'loss/train': 2.813539505004883} 08/30/2021 22:43:54 - INFO - __main__ - Step 52728: {'lr': 0.0003685412608464661, 'samples': 10123776, 'steps': 52727, 'loss/train': 0.997939944267273} 08/30/2021 22:43:55 - INFO - __main__ - Step 52729: {'lr': 0.00036853658857110986, 'samples': 10123968, 'steps': 52728, 'loss/train': 1.1285297870635986} 08/30/2021 22:43:56 - INFO - __main__ - Step 52730: {'lr': 0.0003685319162423428, 'samples': 10124160, 'steps': 52729, 'loss/train': 1.2043447494506836} 08/30/2021 22:43:57 - INFO - __main__ - Step 52731: {'lr': 0.0003685272438601671, 'samples': 10124352, 'steps': 52730, 'loss/train': 1.3782126903533936} 08/30/2021 22:43:57 - INFO - __main__ - Step 52732: {'lr': 0.0003685225714245848, 'samples': 10124544, 'steps': 52731, 'loss/train': 0.021239491179585457} 08/30/2021 22:43:58 - INFO - __main__ - Step 52733: {'lr': 0.0003685178989355981, 'samples': 10124736, 'steps': 52732, 'loss/train': 1.3095142841339111} 08/30/2021 22:43:58 - INFO - __main__ - Step 52734: {'lr': 0.00036851322639320903, 'samples': 10124928, 'steps': 52733, 'loss/train': 1.214749813079834} 08/30/2021 22:43:58 - INFO - __main__ - Step 52735: {'lr': 0.00036850855379741984, 'samples': 10125120, 'steps': 52734, 'loss/train': 1.3897874355316162} 08/30/2021 22:44:00 - INFO - __main__ - Step 52736: {'lr': 0.0003685038811482324, 'samples': 10125312, 'steps': 52735, 'loss/train': 0.20550435781478882} 08/30/2021 22:44:00 - INFO - __main__ - Step 52737: {'lr': 0.00036849920844564903, 'samples': 10125504, 'steps': 52736, 'loss/train': 1.525870442390442} 08/30/2021 22:44:01 - INFO - __main__ - Step 52738: {'lr': 0.00036849453568967174, 'samples': 10125696, 'steps': 52737, 'loss/train': 1.565938949584961} 08/30/2021 22:44:01 - INFO - __main__ - Step 52739: {'lr': 0.0003684898628803026, 'samples': 10125888, 'steps': 52738, 'loss/train': 1.300466537475586} 08/30/2021 22:44:01 - INFO - __main__ - Step 52740: {'lr': 0.00036848519001754374, 'samples': 10126080, 'steps': 52739, 'loss/train': 1.3676319122314453} 08/30/2021 22:44:03 - INFO - __main__ - Step 52741: {'lr': 0.0003684805171013973, 'samples': 10126272, 'steps': 52740, 'loss/train': 1.0476268529891968} 08/30/2021 22:44:03 - INFO - __main__ - Step 52742: {'lr': 0.00036847584413186537, 'samples': 10126464, 'steps': 52741, 'loss/train': 0.9034698605537415} 08/30/2021 22:44:04 - INFO - __main__ - Step 52743: {'lr': 0.0003684711711089501, 'samples': 10126656, 'steps': 52742, 'loss/train': 1.2026904821395874} 08/30/2021 22:44:04 - INFO - __main__ - Step 52744: {'lr': 0.00036846649803265344, 'samples': 10126848, 'steps': 52743, 'loss/train': 1.3953644037246704} 08/30/2021 22:44:04 - INFO - __main__ - Step 52745: {'lr': 0.0003684618249029776, 'samples': 10127040, 'steps': 52744, 'loss/train': 1.542578935623169} 08/30/2021 22:44:07 - INFO - __main__ - Step 52746: {'lr': 0.0003684571517199248, 'samples': 10127232, 'steps': 52745, 'loss/train': 1.8095014095306396} 08/30/2021 22:44:07 - INFO - __main__ - Step 52747: {'lr': 0.000368452478483497, 'samples': 10127424, 'steps': 52746, 'loss/train': 0.9871047735214233} 08/30/2021 22:44:07 - INFO - __main__ - Step 52748: {'lr': 0.0003684478051936964, 'samples': 10127616, 'steps': 52747, 'loss/train': 0.023514069616794586} 08/30/2021 22:44:08 - INFO - __main__ - Step 52749: {'lr': 0.0003684431318505249, 'samples': 10127808, 'steps': 52748, 'loss/train': 0.7879209518432617} 08/30/2021 22:44:08 - INFO - __main__ - Step 52750: {'lr': 0.0003684384584539848, 'samples': 10128000, 'steps': 52749, 'loss/train': 1.3596289157867432} 08/30/2021 22:44:09 - INFO - __main__ - Step 52751: {'lr': 0.0003684337850040782, 'samples': 10128192, 'steps': 52750, 'loss/train': 1.2347923517227173} 08/30/2021 22:44:09 - INFO - __main__ - Step 52752: {'lr': 0.00036842911150080716, 'samples': 10128384, 'steps': 52751, 'loss/train': 0.4994010627269745} 08/30/2021 22:44:09 - INFO - __main__ - Step 52753: {'lr': 0.0003684244379441738, 'samples': 10128576, 'steps': 52752, 'loss/train': 0.3623597025871277} 08/30/2021 22:44:11 - INFO - __main__ - Step 52754: {'lr': 0.00036841976433418024, 'samples': 10128768, 'steps': 52753, 'loss/train': 0.3428556025028229} 08/30/2021 22:44:12 - INFO - __main__ - Step 52755: {'lr': 0.0003684150906708285, 'samples': 10128960, 'steps': 52754, 'loss/train': 1.9974740743637085} 08/30/2021 22:44:12 - INFO - __main__ - Step 52756: {'lr': 0.00036841041695412076, 'samples': 10129152, 'steps': 52755, 'loss/train': 1.3867050409317017} 08/30/2021 22:44:12 - INFO - __main__ - Step 52757: {'lr': 0.00036840574318405914, 'samples': 10129344, 'steps': 52756, 'loss/train': 1.2944309711456299} 08/30/2021 22:44:13 - INFO - __main__ - Step 52758: {'lr': 0.00036840106936064567, 'samples': 10129536, 'steps': 52757, 'loss/train': 0.9662535190582275} 08/30/2021 22:44:14 - INFO - __main__ - Step 52759: {'lr': 0.0003683963954838826, 'samples': 10129728, 'steps': 52758, 'loss/train': 1.1422621011734009} 08/30/2021 22:44:15 - INFO - __main__ - Step 52760: {'lr': 0.00036839172155377184, 'samples': 10129920, 'steps': 52759, 'loss/train': 1.7032216787338257} 08/30/2021 22:44:15 - INFO - __main__ - Step 52761: {'lr': 0.0003683870475703156, 'samples': 10130112, 'steps': 52760, 'loss/train': 0.7078521847724915} 08/30/2021 22:44:15 - INFO - __main__ - Step 52762: {'lr': 0.000368382373533516, 'samples': 10130304, 'steps': 52761, 'loss/train': 0.4826919138431549} 08/30/2021 22:44:16 - INFO - __main__ - Step 52763: {'lr': 0.0003683776994433752, 'samples': 10130496, 'steps': 52762, 'loss/train': 0.8229062557220459} 08/30/2021 22:44:17 - INFO - __main__ - Step 52764: {'lr': 0.0003683730252998951, 'samples': 10130688, 'steps': 52763, 'loss/train': 1.6432713270187378} 08/30/2021 22:44:18 - INFO - __main__ - Step 52765: {'lr': 0.00036836835110307803, 'samples': 10130880, 'steps': 52764, 'loss/train': 1.085395336151123} 08/30/2021 22:44:18 - INFO - __main__ - Step 52766: {'lr': 0.00036836367685292605, 'samples': 10131072, 'steps': 52765, 'loss/train': 0.8023868799209595} 08/30/2021 22:44:18 - INFO - __main__ - Step 52767: {'lr': 0.00036835900254944114, 'samples': 10131264, 'steps': 52766, 'loss/train': 1.3463640213012695} 08/30/2021 22:44:19 - INFO - __main__ - Step 52768: {'lr': 0.0003683543281926255, 'samples': 10131456, 'steps': 52767, 'loss/train': 1.7986454963684082} 08/30/2021 22:44:20 - INFO - __main__ - Step 52769: {'lr': 0.0003683496537824813, 'samples': 10131648, 'steps': 52768, 'loss/train': 0.844243586063385} 08/30/2021 22:44:20 - INFO - __main__ - Step 52770: {'lr': 0.0003683449793190105, 'samples': 10131840, 'steps': 52769, 'loss/train': 1.4779090881347656} 08/30/2021 22:44:21 - INFO - __main__ - Step 52771: {'lr': 0.0003683403048022153, 'samples': 10132032, 'steps': 52770, 'loss/train': 1.3560630083084106} 08/30/2021 22:44:21 - INFO - __main__ - Step 52772: {'lr': 0.0003683356302320978, 'samples': 10132224, 'steps': 52771, 'loss/train': 1.6022785902023315} 08/30/2021 22:44:22 - INFO - __main__ - Step 52773: {'lr': 0.00036833095560866007, 'samples': 10132416, 'steps': 52772, 'loss/train': 1.4472960233688354} 08/30/2021 22:44:24 - INFO - __main__ - Step 52774: {'lr': 0.00036832628093190424, 'samples': 10132608, 'steps': 52773, 'loss/train': 1.2739747762680054} 08/30/2021 22:44:24 - INFO - __main__ - Step 52775: {'lr': 0.0003683216062018324, 'samples': 10132800, 'steps': 52774, 'loss/train': 0.766843318939209} 08/30/2021 22:44:24 - INFO - __main__ - Step 52776: {'lr': 0.0003683169314184467, 'samples': 10132992, 'steps': 52775, 'loss/train': 1.2117451429367065} 08/30/2021 22:44:25 - INFO - __main__ - Step 52777: {'lr': 0.00036831225658174915, 'samples': 10133184, 'steps': 52776, 'loss/train': 1.4466413259506226} 08/30/2021 22:44:25 - INFO - __main__ - Step 52778: {'lr': 0.000368307581691742, 'samples': 10133376, 'steps': 52777, 'loss/train': 6.41992712020874} 08/30/2021 22:44:26 - INFO - __main__ - Step 52779: {'lr': 0.0003683029067484273, 'samples': 10133568, 'steps': 52778, 'loss/train': 0.06106307730078697} 08/30/2021 22:44:27 - INFO - __main__ - Step 52780: {'lr': 0.0003682982317518071, 'samples': 10133760, 'steps': 52779, 'loss/train': 1.038874626159668} 08/30/2021 22:44:28 - INFO - __main__ - Step 52781: {'lr': 0.00036829355670188355, 'samples': 10133952, 'steps': 52780, 'loss/train': 1.8153637647628784} 08/30/2021 22:44:28 - INFO - __main__ - Step 52782: {'lr': 0.0003682888815986587, 'samples': 10134144, 'steps': 52781, 'loss/train': 1.672353744506836} 08/30/2021 22:44:28 - INFO - __main__ - Step 52783: {'lr': 0.00036828420644213474, 'samples': 10134336, 'steps': 52782, 'loss/train': 1.8601869344711304} 08/30/2021 22:44:29 - INFO - __main__ - Step 52784: {'lr': 0.00036827953123231373, 'samples': 10134528, 'steps': 52783, 'loss/train': 1.755374789237976} 08/30/2021 22:44:29 - INFO - __main__ - Step 52785: {'lr': 0.00036827485596919773, 'samples': 10134720, 'steps': 52784, 'loss/train': 1.6547623872756958} 08/30/2021 22:44:30 - INFO - __main__ - Step 52786: {'lr': 0.00036827018065278903, 'samples': 10134912, 'steps': 52785, 'loss/train': 1.2991185188293457} 08/30/2021 22:44:31 - INFO - __main__ - Step 52787: {'lr': 0.00036826550528308956, 'samples': 10135104, 'steps': 52786, 'loss/train': 1.0934385061264038} 08/30/2021 22:44:31 - INFO - __main__ - Step 52788: {'lr': 0.00036826082986010145, 'samples': 10135296, 'steps': 52787, 'loss/train': 1.4156596660614014} 08/30/2021 22:44:32 - INFO - __main__ - Step 52789: {'lr': 0.00036825615438382687, 'samples': 10135488, 'steps': 52788, 'loss/train': 1.6095339059829712} 08/30/2021 22:44:32 - INFO - __main__ - Step 52790: {'lr': 0.00036825147885426786, 'samples': 10135680, 'steps': 52789, 'loss/train': 1.0748971700668335} 08/30/2021 22:44:34 - INFO - __main__ - Step 52791: {'lr': 0.00036824680327142656, 'samples': 10135872, 'steps': 52790, 'loss/train': 1.3358403444290161} 08/30/2021 22:44:34 - INFO - __main__ - Step 52792: {'lr': 0.0003682421276353051, 'samples': 10136064, 'steps': 52791, 'loss/train': 1.1452604532241821} 08/30/2021 22:44:34 - INFO - __main__ - Step 52793: {'lr': 0.0003682374519459056, 'samples': 10136256, 'steps': 52792, 'loss/train': 1.3747785091400146} 08/30/2021 22:44:35 - INFO - __main__ - Step 52794: {'lr': 0.00036823277620323, 'samples': 10136448, 'steps': 52793, 'loss/train': 1.704042673110962} 08/30/2021 22:44:35 - INFO - __main__ - Step 52795: {'lr': 0.00036822810040728065, 'samples': 10136640, 'steps': 52794, 'loss/train': 1.478071928024292} 08/30/2021 22:44:36 - INFO - __main__ - Step 52796: {'lr': 0.00036822342455805954, 'samples': 10136832, 'steps': 52795, 'loss/train': 1.4351744651794434} 08/30/2021 22:44:37 - INFO - __main__ - Step 52797: {'lr': 0.0003682187486555687, 'samples': 10137024, 'steps': 52796, 'loss/train': 1.449101209640503} 08/30/2021 22:44:37 - INFO - __main__ - Step 52798: {'lr': 0.0003682140726998104, 'samples': 10137216, 'steps': 52797, 'loss/train': 1.6020257472991943} 08/30/2021 22:44:38 - INFO - __main__ - Step 52799: {'lr': 0.0003682093966907867, 'samples': 10137408, 'steps': 52798, 'loss/train': 0.8282920718193054} 08/30/2021 22:44:38 - INFO - __main__ - Step 52800: {'lr': 0.00036820472062849954, 'samples': 10137600, 'steps': 52799, 'loss/train': 1.7056143283843994} 08/30/2021 22:44:40 - INFO - __main__ - Step 52801: {'lr': 0.0003682000445129512, 'samples': 10137792, 'steps': 52800, 'loss/train': 1.5834660530090332} 08/30/2021 22:44:40 - INFO - __main__ - Step 52802: {'lr': 0.00036819536834414374, 'samples': 10137984, 'steps': 52801, 'loss/train': 1.1081442832946777} 08/30/2021 22:44:40 - INFO - __main__ - Step 52803: {'lr': 0.00036819069212207933, 'samples': 10138176, 'steps': 52802, 'loss/train': 1.2475008964538574} 08/30/2021 22:44:41 - INFO - __main__ - Step 52804: {'lr': 0.00036818601584675994, 'samples': 10138368, 'steps': 52803, 'loss/train': 1.6573153734207153} 08/30/2021 22:44:41 - INFO - __main__ - Step 52805: {'lr': 0.0003681813395181878, 'samples': 10138560, 'steps': 52804, 'loss/train': 1.216860294342041} 08/30/2021 22:44:43 - INFO - __main__ - Step 52806: {'lr': 0.000368176663136365, 'samples': 10138752, 'steps': 52805, 'loss/train': 1.4358131885528564} 08/30/2021 22:44:44 - INFO - __main__ - Step 52807: {'lr': 0.00036817198670129357, 'samples': 10138944, 'steps': 52806, 'loss/train': 1.004723072052002} 08/30/2021 22:44:44 - INFO - __main__ - Step 52808: {'lr': 0.00036816731021297567, 'samples': 10139136, 'steps': 52807, 'loss/train': 1.0727159976959229} 08/30/2021 22:44:45 - INFO - __main__ - Step 52809: {'lr': 0.0003681626336714134, 'samples': 10139328, 'steps': 52808, 'loss/train': 2.0693864822387695} 08/30/2021 22:44:45 - INFO - __main__ - Step 52810: {'lr': 0.00036815795707660886, 'samples': 10139520, 'steps': 52809, 'loss/train': 0.33582019805908203} 08/30/2021 22:44:45 - INFO - __main__ - Step 52811: {'lr': 0.00036815328042856424, 'samples': 10139712, 'steps': 52810, 'loss/train': 1.613366961479187} 08/30/2021 22:44:47 - INFO - __main__ - Step 52812: {'lr': 0.0003681486037272815, 'samples': 10139904, 'steps': 52811, 'loss/train': 1.600266933441162} 08/30/2021 22:44:47 - INFO - __main__ - Step 52813: {'lr': 0.0003681439269727629, 'samples': 10140096, 'steps': 52812, 'loss/train': 1.3165990114212036} 08/30/2021 22:44:48 - INFO - __main__ - Step 52814: {'lr': 0.00036813925016501036, 'samples': 10140288, 'steps': 52813, 'loss/train': 1.8699873685836792} 08/30/2021 22:44:48 - INFO - __main__ - Step 52815: {'lr': 0.00036813457330402616, 'samples': 10140480, 'steps': 52814, 'loss/train': 1.1939752101898193} 08/30/2021 22:44:48 - INFO - __main__ - Step 52816: {'lr': 0.0003681298963898124, 'samples': 10140672, 'steps': 52815, 'loss/train': 1.0365192890167236} 08/30/2021 22:44:50 - INFO - __main__ - Step 52817: {'lr': 0.000368125219422371, 'samples': 10140864, 'steps': 52816, 'loss/train': 1.1778470277786255} 08/30/2021 22:44:50 - INFO - __main__ - Step 52818: {'lr': 0.00036812054240170427, 'samples': 10141056, 'steps': 52817, 'loss/train': 2.0488033294677734} 08/30/2021 22:44:51 - INFO - __main__ - Step 52819: {'lr': 0.00036811586532781425, 'samples': 10141248, 'steps': 52818, 'loss/train': 0.12901750206947327} 08/30/2021 22:44:51 - INFO - __main__ - Step 52820: {'lr': 0.0003681111882007031, 'samples': 10141440, 'steps': 52819, 'loss/train': 1.6754236221313477} 08/30/2021 22:44:51 - INFO - __main__ - Step 52821: {'lr': 0.0003681065110203728, 'samples': 10141632, 'steps': 52820, 'loss/train': 1.4286178350448608} 08/30/2021 22:44:53 - INFO - __main__ - Step 52822: {'lr': 0.0003681018337868255, 'samples': 10141824, 'steps': 52821, 'loss/train': 1.1651772260665894} 08/30/2021 22:44:54 - INFO - __main__ - Step 52823: {'lr': 0.00036809715650006335, 'samples': 10142016, 'steps': 52822, 'loss/train': 1.5365095138549805} 08/30/2021 22:44:54 - INFO - __main__ - Step 52824: {'lr': 0.0003680924791600885, 'samples': 10142208, 'steps': 52823, 'loss/train': 1.7767486572265625} 08/30/2021 22:44:54 - INFO - __main__ - Step 52825: {'lr': 0.000368087801766903, 'samples': 10142400, 'steps': 52824, 'loss/train': 0.14912737905979156} 08/30/2021 22:44:55 - INFO - __main__ - Step 52826: {'lr': 0.0003680831243205089, 'samples': 10142592, 'steps': 52825, 'loss/train': 0.8397039175033569} 08/30/2021 22:44:56 - INFO - __main__ - Step 52827: {'lr': 0.00036807844682090843, 'samples': 10142784, 'steps': 52826, 'loss/train': 0.9851338863372803} 08/30/2021 22:44:57 - INFO - __main__ - Step 52828: {'lr': 0.0003680737692681036, 'samples': 10142976, 'steps': 52827, 'loss/train': 1.3993828296661377} 08/30/2021 22:44:57 - INFO - __main__ - Step 52829: {'lr': 0.0003680690916620966, 'samples': 10143168, 'steps': 52828, 'loss/train': 1.6471260786056519} 08/30/2021 22:44:57 - INFO - __main__ - Step 52830: {'lr': 0.00036806441400288935, 'samples': 10143360, 'steps': 52829, 'loss/train': 0.07215423882007599} 08/30/2021 22:44:58 - INFO - __main__ - Step 52831: {'lr': 0.00036805973629048416, 'samples': 10143552, 'steps': 52830, 'loss/train': 3.7563297748565674} 08/30/2021 22:44:58 - INFO - __main__ - Step 52832: {'lr': 0.0003680550585248831, 'samples': 10143744, 'steps': 52831, 'loss/train': 1.5225003957748413} 08/30/2021 22:45:00 - INFO - __main__ - Step 52833: {'lr': 0.0003680503807060883, 'samples': 10143936, 'steps': 52832, 'loss/train': 0.7888264060020447} 08/30/2021 22:45:00 - INFO - __main__ - Step 52834: {'lr': 0.0003680457028341018, 'samples': 10144128, 'steps': 52833, 'loss/train': 1.6530288457870483} 08/30/2021 22:45:01 - INFO - __main__ - Step 52835: {'lr': 0.00036804102490892567, 'samples': 10144320, 'steps': 52834, 'loss/train': 1.5260083675384521} 08/30/2021 22:45:01 - INFO - __main__ - Step 52836: {'lr': 0.0003680363469305621, 'samples': 10144512, 'steps': 52835, 'loss/train': 1.8343027830123901} 08/30/2021 22:45:01 - INFO - __main__ - Step 52837: {'lr': 0.00036803166889901316, 'samples': 10144704, 'steps': 52836, 'loss/train': 1.5902246236801147} 08/30/2021 22:45:03 - INFO - __main__ - Step 52838: {'lr': 0.000368026990814281, 'samples': 10144896, 'steps': 52837, 'loss/train': 1.5834227800369263} 08/30/2021 22:45:03 - INFO - __main__ - Step 52839: {'lr': 0.00036802231267636773, 'samples': 10145088, 'steps': 52838, 'loss/train': 0.12509818375110626} 08/30/2021 22:45:04 - INFO - __main__ - Step 52840: {'lr': 0.0003680176344852754, 'samples': 10145280, 'steps': 52839, 'loss/train': 1.5758237838745117} 08/30/2021 22:45:04 - INFO - __main__ - Step 52841: {'lr': 0.00036801295624100616, 'samples': 10145472, 'steps': 52840, 'loss/train': 0.2538892328739166} 08/30/2021 22:45:04 - INFO - __main__ - Step 52842: {'lr': 0.00036800827794356206, 'samples': 10145664, 'steps': 52841, 'loss/train': 2.8197221755981445} 08/30/2021 22:45:06 - INFO - __main__ - Step 52843: {'lr': 0.0003680035995929453, 'samples': 10145856, 'steps': 52842, 'loss/train': 1.5177109241485596} 08/30/2021 22:45:06 - INFO - __main__ - Step 52844: {'lr': 0.00036799892118915785, 'samples': 10146048, 'steps': 52843, 'loss/train': 1.5815762281417847} 08/30/2021 22:45:07 - INFO - __main__ - Step 52845: {'lr': 0.0003679942427322019, 'samples': 10146240, 'steps': 52844, 'loss/train': 0.985563337802887} 08/30/2021 22:45:07 - INFO - __main__ - Step 52846: {'lr': 0.00036798956422207975, 'samples': 10146432, 'steps': 52845, 'loss/train': 0.5850203037261963} 08/30/2021 22:45:07 - INFO - __main__ - Step 52847: {'lr': 0.0003679848856587932, 'samples': 10146624, 'steps': 52846, 'loss/train': 1.5630192756652832} 08/30/2021 22:45:09 - INFO - __main__ - Step 52848: {'lr': 0.0003679802070423445, 'samples': 10146816, 'steps': 52847, 'loss/train': 1.2434501647949219} 08/30/2021 22:45:10 - INFO - __main__ - Step 52849: {'lr': 0.0003679755283727357, 'samples': 10147008, 'steps': 52848, 'loss/train': 4.8473052978515625} 08/30/2021 22:45:10 - INFO - __main__ - Step 52850: {'lr': 0.0003679708496499689, 'samples': 10147200, 'steps': 52849, 'loss/train': 0.43993982672691345} 08/30/2021 22:45:10 - INFO - __main__ - Step 52851: {'lr': 0.0003679661708740463, 'samples': 10147392, 'steps': 52850, 'loss/train': 1.4335788488388062} 08/30/2021 22:45:11 - INFO - __main__ - Step 52852: {'lr': 0.00036796149204497, 'samples': 10147584, 'steps': 52851, 'loss/train': 1.569490909576416} 08/30/2021 22:45:11 - INFO - __main__ - Step 52853: {'lr': 0.0003679568131627421, 'samples': 10147776, 'steps': 52852, 'loss/train': 1.167616605758667} 08/30/2021 22:45:13 - INFO - __main__ - Step 52854: {'lr': 0.0003679521342273647, 'samples': 10147968, 'steps': 52853, 'loss/train': 1.3393454551696777} 08/30/2021 22:45:13 - INFO - __main__ - Step 52855: {'lr': 0.00036794745523883977, 'samples': 10148160, 'steps': 52854, 'loss/train': 1.5885943174362183} 08/30/2021 22:45:14 - INFO - __main__ - Step 52856: {'lr': 0.0003679427761971696, 'samples': 10148352, 'steps': 52855, 'loss/train': 0.5337668061256409} 08/30/2021 22:45:14 - INFO - __main__ - Step 52857: {'lr': 0.0003679380971023562, 'samples': 10148544, 'steps': 52856, 'loss/train': 0.060671236366033554} 08/30/2021 22:45:14 - INFO - __main__ - Step 52858: {'lr': 0.00036793341795440175, 'samples': 10148736, 'steps': 52857, 'loss/train': 1.6230326890945435} 08/30/2021 22:45:16 - INFO - __main__ - Step 52859: {'lr': 0.00036792873875330837, 'samples': 10148928, 'steps': 52858, 'loss/train': 0.6809663772583008} 08/30/2021 22:45:16 - INFO - __main__ - Step 52860: {'lr': 0.000367924059499078, 'samples': 10149120, 'steps': 52859, 'loss/train': 1.2868061065673828} 08/30/2021 22:45:17 - INFO - __main__ - Step 52861: {'lr': 0.000367919380191713, 'samples': 10149312, 'steps': 52860, 'loss/train': 1.0583810806274414} 08/30/2021 22:45:17 - INFO - __main__ - Step 52862: {'lr': 0.0003679147008312153, 'samples': 10149504, 'steps': 52861, 'loss/train': 2.0262184143066406} 08/30/2021 22:45:17 - INFO - __main__ - Step 52863: {'lr': 0.000367910021417587, 'samples': 10149696, 'steps': 52862, 'loss/train': 1.402963399887085} 08/30/2021 22:45:19 - INFO - __main__ - Step 52864: {'lr': 0.0003679053419508303, 'samples': 10149888, 'steps': 52863, 'loss/train': 0.9775792360305786} 08/30/2021 22:45:20 - INFO - __main__ - Step 52865: {'lr': 0.0003679006624309472, 'samples': 10150080, 'steps': 52864, 'loss/train': 0.4156869649887085} 08/30/2021 22:45:20 - INFO - __main__ - Step 52866: {'lr': 0.00036789598285794003, 'samples': 10150272, 'steps': 52865, 'loss/train': 1.5188993215560913} 08/30/2021 22:45:20 - INFO - __main__ - Step 52867: {'lr': 0.0003678913032318107, 'samples': 10150464, 'steps': 52866, 'loss/train': 1.3779767751693726} 08/30/2021 22:45:21 - INFO - __main__ - Step 52868: {'lr': 0.0003678866235525613, 'samples': 10150656, 'steps': 52867, 'loss/train': 0.6728357076644897} 08/30/2021 22:45:21 - INFO - __main__ - Step 52869: {'lr': 0.00036788194382019406, 'samples': 10150848, 'steps': 52868, 'loss/train': 1.3757350444793701} 08/30/2021 22:45:23 - INFO - __main__ - Step 52870: {'lr': 0.000367877264034711, 'samples': 10151040, 'steps': 52869, 'loss/train': 1.8382889032363892} 08/30/2021 22:45:23 - INFO - __main__ - Step 52871: {'lr': 0.0003678725841961144, 'samples': 10151232, 'steps': 52870, 'loss/train': 1.571977138519287} 08/30/2021 22:45:23 - INFO - __main__ - Step 52872: {'lr': 0.00036786790430440606, 'samples': 10151424, 'steps': 52871, 'loss/train': 1.1862865686416626} 08/30/2021 22:45:24 - INFO - __main__ - Step 52873: {'lr': 0.0003678632243595883, 'samples': 10151616, 'steps': 52872, 'loss/train': 1.3522124290466309} 08/30/2021 22:45:24 - INFO - __main__ - Step 52874: {'lr': 0.0003678585443616632, 'samples': 10151808, 'steps': 52873, 'loss/train': 1.2177828550338745} 08/30/2021 22:45:26 - INFO - __main__ - Step 52875: {'lr': 0.0003678538643106329, 'samples': 10152000, 'steps': 52874, 'loss/train': 0.6633574962615967} 08/30/2021 22:45:26 - INFO - __main__ - Step 52876: {'lr': 0.0003678491842064995, 'samples': 10152192, 'steps': 52875, 'loss/train': 1.3696953058242798} 08/30/2021 22:45:26 - INFO - __main__ - Step 52877: {'lr': 0.00036784450404926493, 'samples': 10152384, 'steps': 52876, 'loss/train': 1.2297606468200684} 08/30/2021 22:45:27 - INFO - __main__ - Step 52878: {'lr': 0.00036783982383893155, 'samples': 10152576, 'steps': 52877, 'loss/train': 1.6480772495269775} 08/30/2021 22:45:27 - INFO - __main__ - Step 52879: {'lr': 0.0003678351435755014, 'samples': 10152768, 'steps': 52878, 'loss/train': 1.6736863851547241} 08/30/2021 22:45:29 - INFO - __main__ - Step 52880: {'lr': 0.0003678304632589764, 'samples': 10152960, 'steps': 52879, 'loss/train': 1.8834729194641113} 08/30/2021 22:45:29 - INFO - __main__ - Step 52881: {'lr': 0.00036782578288935893, 'samples': 10153152, 'steps': 52880, 'loss/train': 1.7674905061721802} 08/30/2021 22:45:30 - INFO - __main__ - Step 52882: {'lr': 0.000367821102466651, 'samples': 10153344, 'steps': 52881, 'loss/train': 1.6400136947631836} 08/30/2021 22:45:30 - INFO - __main__ - Step 52883: {'lr': 0.0003678164219908546, 'samples': 10153536, 'steps': 52882, 'loss/train': 9.2638578414917} 08/30/2021 22:45:30 - INFO - __main__ - Step 52884: {'lr': 0.00036781174146197207, 'samples': 10153728, 'steps': 52883, 'loss/train': 2.1339919567108154} 08/30/2021 22:45:31 - INFO - __main__ - Step 52885: {'lr': 0.00036780706088000524, 'samples': 10153920, 'steps': 52884, 'loss/train': 1.4225355386734009} 08/30/2021 22:45:32 - INFO - __main__ - Step 52886: {'lr': 0.0003678023802449564, 'samples': 10154112, 'steps': 52885, 'loss/train': 1.3051801919937134} 08/30/2021 22:45:33 - INFO - __main__ - Step 52887: {'lr': 0.0003677976995568277, 'samples': 10154304, 'steps': 52886, 'loss/train': 0.088077612221241} 08/30/2021 22:45:33 - INFO - __main__ - Step 52888: {'lr': 0.00036779301881562115, 'samples': 10154496, 'steps': 52887, 'loss/train': 1.0581823587417603} 08/30/2021 22:45:33 - INFO - __main__ - Step 52889: {'lr': 0.00036778833802133886, 'samples': 10154688, 'steps': 52888, 'loss/train': 1.6545796394348145} 08/30/2021 22:45:34 - INFO - __main__ - Step 52890: {'lr': 0.000367783657173983, 'samples': 10154880, 'steps': 52889, 'loss/train': 1.7570533752441406} 08/30/2021 22:45:35 - INFO - __main__ - Step 52891: {'lr': 0.0003677789762735556, 'samples': 10155072, 'steps': 52890, 'loss/train': 1.131620168685913} 08/30/2021 22:45:36 - INFO - __main__ - Step 52892: {'lr': 0.0003677742953200588, 'samples': 10155264, 'steps': 52891, 'loss/train': 1.521576166152954} 08/30/2021 22:45:36 - INFO - __main__ - Step 52893: {'lr': 0.0003677696143134948, 'samples': 10155456, 'steps': 52892, 'loss/train': 1.0028271675109863} 08/30/2021 22:45:36 - INFO - __main__ - Step 52894: {'lr': 0.00036776493325386554, 'samples': 10155648, 'steps': 52893, 'loss/train': 4.157871246337891} 08/30/2021 22:45:37 - INFO - __main__ - Step 52895: {'lr': 0.00036776025214117325, 'samples': 10155840, 'steps': 52894, 'loss/train': 2.172318935394287} 08/30/2021 22:45:38 - INFO - __main__ - Step 52896: {'lr': 0.00036775557097542, 'samples': 10156032, 'steps': 52895, 'loss/train': 1.2730040550231934} 08/30/2021 22:45:39 - INFO - __main__ - Step 52897: {'lr': 0.00036775088975660793, 'samples': 10156224, 'steps': 52896, 'loss/train': 1.6778171062469482} 08/30/2021 22:45:39 - INFO - __main__ - Step 52898: {'lr': 0.0003677462084847391, 'samples': 10156416, 'steps': 52897, 'loss/train': 1.2212762832641602} 08/30/2021 22:45:40 - INFO - __main__ - Step 52899: {'lr': 0.0003677415271598157, 'samples': 10156608, 'steps': 52898, 'loss/train': 0.9911786317825317} 08/30/2021 22:45:40 - INFO - __main__ - Step 52900: {'lr': 0.00036773684578183976, 'samples': 10156800, 'steps': 52899, 'loss/train': 1.7771943807601929} 08/30/2021 22:45:42 - INFO - __main__ - Step 52901: {'lr': 0.00036773216435081335, 'samples': 10156992, 'steps': 52900, 'loss/train': 1.9092345237731934} 08/30/2021 22:45:42 - INFO - __main__ - Step 52902: {'lr': 0.00036772748286673866, 'samples': 10157184, 'steps': 52901, 'loss/train': 1.510646104812622} 08/30/2021 22:45:42 - INFO - __main__ - Step 52903: {'lr': 0.00036772280132961786, 'samples': 10157376, 'steps': 52902, 'loss/train': 1.662872076034546} 08/30/2021 22:45:43 - INFO - __main__ - Step 52904: {'lr': 0.0003677181197394529, 'samples': 10157568, 'steps': 52903, 'loss/train': 1.9470168352127075} 08/30/2021 22:45:43 - INFO - __main__ - Step 52905: {'lr': 0.000367713438096246, 'samples': 10157760, 'steps': 52904, 'loss/train': 1.2834594249725342} 08/30/2021 22:45:44 - INFO - __main__ - Step 52906: {'lr': 0.00036770875639999923, 'samples': 10157952, 'steps': 52905, 'loss/train': 1.3543715476989746} 08/30/2021 22:45:45 - INFO - __main__ - Step 52907: {'lr': 0.0003677040746507148, 'samples': 10158144, 'steps': 52906, 'loss/train': 0.7779142260551453} 08/30/2021 22:45:45 - INFO - __main__ - Step 52908: {'lr': 0.00036769939284839463, 'samples': 10158336, 'steps': 52907, 'loss/train': 1.8947523832321167} 08/30/2021 22:45:46 - INFO - __main__ - Step 52909: {'lr': 0.000367694710993041, 'samples': 10158528, 'steps': 52908, 'loss/train': 1.7517786026000977} 08/30/2021 22:45:46 - INFO - __main__ - Step 52910: {'lr': 0.00036769002908465585, 'samples': 10158720, 'steps': 52909, 'loss/train': 1.7450008392333984} 08/30/2021 22:45:46 - INFO - __main__ - Step 52911: {'lr': 0.0003676853471232415, 'samples': 10158912, 'steps': 52910, 'loss/train': 1.2192262411117554} 08/30/2021 22:45:48 - INFO - __main__ - Step 52912: {'lr': 0.00036768066510879985, 'samples': 10159104, 'steps': 52911, 'loss/train': 1.3875399827957153} 08/30/2021 22:45:48 - INFO - __main__ - Step 52913: {'lr': 0.0003676759830413332, 'samples': 10159296, 'steps': 52912, 'loss/train': 0.710380494594574} 08/30/2021 22:45:49 - INFO - __main__ - Step 52914: {'lr': 0.0003676713009208435, 'samples': 10159488, 'steps': 52913, 'loss/train': 1.0504858493804932} 08/30/2021 22:45:49 - INFO - __main__ - Step 52915: {'lr': 0.000367666618747333, 'samples': 10159680, 'steps': 52914, 'loss/train': 2.033491373062134} 08/30/2021 22:45:49 - INFO - __main__ - Step 52916: {'lr': 0.0003676619365208036, 'samples': 10159872, 'steps': 52915, 'loss/train': 1.360023021697998} 08/30/2021 22:45:51 - INFO - __main__ - Step 52917: {'lr': 0.0003676572542412576, 'samples': 10160064, 'steps': 52916, 'loss/train': 1.6952009201049805} 08/30/2021 22:45:51 - INFO - __main__ - Step 52918: {'lr': 0.00036765257190869715, 'samples': 10160256, 'steps': 52917, 'loss/train': 1.649714708328247} 08/30/2021 22:45:52 - INFO - __main__ - Step 52919: {'lr': 0.0003676478895231242, 'samples': 10160448, 'steps': 52918, 'loss/train': 1.833362340927124} 08/30/2021 22:45:52 - INFO - __main__ - Step 52920: {'lr': 0.00036764320708454094, 'samples': 10160640, 'steps': 52919, 'loss/train': 2.5058720111846924} 08/30/2021 22:45:52 - INFO - __main__ - Step 52921: {'lr': 0.0003676385245929494, 'samples': 10160832, 'steps': 52920, 'loss/train': 1.0672963857650757} 08/30/2021 22:45:55 - INFO - __main__ - Step 52922: {'lr': 0.00036763384204835186, 'samples': 10161024, 'steps': 52921, 'loss/train': 1.3552619218826294} 08/30/2021 22:45:55 - INFO - __main__ - Step 52923: {'lr': 0.0003676291594507503, 'samples': 10161216, 'steps': 52922, 'loss/train': 1.1720116138458252} 08/30/2021 22:45:55 - INFO - __main__ - Step 52924: {'lr': 0.0003676244768001468, 'samples': 10161408, 'steps': 52923, 'loss/train': 1.8418108224868774} 08/30/2021 22:45:56 - INFO - __main__ - Step 52925: {'lr': 0.00036761979409654353, 'samples': 10161600, 'steps': 52924, 'loss/train': 1.462021827697754} 08/30/2021 22:45:56 - INFO - __main__ - Step 52926: {'lr': 0.0003676151113399427, 'samples': 10161792, 'steps': 52925, 'loss/train': 1.1038837432861328} 08/30/2021 22:45:57 - INFO - __main__ - Step 52927: {'lr': 0.0003676104285303463, 'samples': 10161984, 'steps': 52926, 'loss/train': 0.15758973360061646} 08/30/2021 22:45:58 - INFO - __main__ - Step 52928: {'lr': 0.00036760574566775634, 'samples': 10162176, 'steps': 52927, 'loss/train': 1.0593544244766235} 08/30/2021 22:45:58 - INFO - __main__ - Step 52929: {'lr': 0.0003676010627521751, 'samples': 10162368, 'steps': 52928, 'loss/train': 1.4163261651992798} 08/30/2021 22:45:59 - INFO - __main__ - Step 52930: {'lr': 0.00036759637978360467, 'samples': 10162560, 'steps': 52929, 'loss/train': 1.3818470239639282} 08/30/2021 22:45:59 - INFO - __main__ - Step 52931: {'lr': 0.00036759169676204705, 'samples': 10162752, 'steps': 52930, 'loss/train': 1.3914273977279663} 08/30/2021 22:45:59 - INFO - __main__ - Step 52932: {'lr': 0.0003675870136875045, 'samples': 10162944, 'steps': 52931, 'loss/train': 1.4438437223434448} 08/30/2021 22:46:01 - INFO - __main__ - Step 52933: {'lr': 0.00036758233055997905, 'samples': 10163136, 'steps': 52932, 'loss/train': 1.2895777225494385} 08/30/2021 22:46:01 - INFO - __main__ - Step 52934: {'lr': 0.0003675776473794728, 'samples': 10163328, 'steps': 52933, 'loss/train': 0.2727830410003662} 08/30/2021 22:46:02 - INFO - __main__ - Step 52935: {'lr': 0.00036757296414598786, 'samples': 10163520, 'steps': 52934, 'loss/train': 1.4995088577270508} 08/30/2021 22:46:02 - INFO - __main__ - Step 52936: {'lr': 0.00036756828085952637, 'samples': 10163712, 'steps': 52935, 'loss/train': 1.610569953918457} 08/30/2021 22:46:02 - INFO - __main__ - Step 52937: {'lr': 0.0003675635975200904, 'samples': 10163904, 'steps': 52936, 'loss/train': 0.9813700318336487} 08/30/2021 22:46:04 - INFO - __main__ - Step 52938: {'lr': 0.0003675589141276821, 'samples': 10164096, 'steps': 52937, 'loss/train': 2.048440456390381} 08/30/2021 22:46:04 - INFO - __main__ - Step 52939: {'lr': 0.0003675542306823036, 'samples': 10164288, 'steps': 52938, 'loss/train': 1.1392234563827515} 08/30/2021 22:46:05 - INFO - __main__ - Step 52940: {'lr': 0.000367549547183957, 'samples': 10164480, 'steps': 52939, 'loss/train': 1.495479941368103} 08/30/2021 22:46:05 - INFO - __main__ - Step 52941: {'lr': 0.0003675448636326443, 'samples': 10164672, 'steps': 52940, 'loss/train': 1.6654627323150635} 08/30/2021 22:46:05 - INFO - __main__ - Step 52942: {'lr': 0.0003675401800283678, 'samples': 10164864, 'steps': 52941, 'loss/train': 1.827637791633606} 08/30/2021 22:46:07 - INFO - __main__ - Step 52943: {'lr': 0.0003675354963711294, 'samples': 10165056, 'steps': 52942, 'loss/train': 1.5564132928848267} 08/30/2021 22:46:08 - INFO - __main__ - Step 52944: {'lr': 0.00036753081266093136, 'samples': 10165248, 'steps': 52943, 'loss/train': 0.9640160202980042} 08/30/2021 22:46:08 - INFO - __main__ - Step 52945: {'lr': 0.00036752612889777577, 'samples': 10165440, 'steps': 52944, 'loss/train': 1.2663378715515137} 08/30/2021 22:46:08 - INFO - __main__ - Step 52946: {'lr': 0.0003675214450816647, 'samples': 10165632, 'steps': 52945, 'loss/train': 2.169135332107544} 08/30/2021 22:46:09 - INFO - __main__ - Step 52947: {'lr': 0.00036751676121260035, 'samples': 10165824, 'steps': 52946, 'loss/train': 0.6767752170562744} 08/30/2021 22:46:10 - INFO - __main__ - Step 52948: {'lr': 0.00036751207729058465, 'samples': 10166016, 'steps': 52947, 'loss/train': 1.3219033479690552} 08/30/2021 22:46:10 - INFO - __main__ - Step 52949: {'lr': 0.00036750739331561986, 'samples': 10166208, 'steps': 52948, 'loss/train': 1.090736746788025} 08/30/2021 22:46:11 - INFO - __main__ - Step 52950: {'lr': 0.0003675027092877081, 'samples': 10166400, 'steps': 52949, 'loss/train': 1.9434583187103271} 08/30/2021 22:46:11 - INFO - __main__ - Step 52951: {'lr': 0.0003674980252068514, 'samples': 10166592, 'steps': 52950, 'loss/train': 0.6372240781784058} 08/30/2021 22:46:12 - INFO - __main__ - Step 52952: {'lr': 0.0003674933410730519, 'samples': 10166784, 'steps': 52951, 'loss/train': 1.5540742874145508} 08/30/2021 22:46:13 - INFO - __main__ - Step 52953: {'lr': 0.00036748865688631175, 'samples': 10166976, 'steps': 52952, 'loss/train': 1.0596449375152588} 08/30/2021 22:46:13 - INFO - __main__ - Step 52954: {'lr': 0.000367483972646633, 'samples': 10167168, 'steps': 52953, 'loss/train': 1.7599678039550781} 08/30/2021 22:46:14 - INFO - __main__ - Step 52955: {'lr': 0.00036747928835401773, 'samples': 10167360, 'steps': 52954, 'loss/train': 1.2872885465621948} 08/30/2021 22:46:14 - INFO - __main__ - Step 52956: {'lr': 0.00036747460400846815, 'samples': 10167552, 'steps': 52955, 'loss/train': 1.8222973346710205} 08/30/2021 22:46:14 - INFO - __main__ - Step 52957: {'lr': 0.00036746991960998635, 'samples': 10167744, 'steps': 52956, 'loss/train': 1.5619595050811768} 08/30/2021 22:46:16 - INFO - __main__ - Step 52958: {'lr': 0.00036746523515857434, 'samples': 10167936, 'steps': 52957, 'loss/train': 1.4632941484451294} 08/30/2021 22:46:16 - INFO - __main__ - Step 52959: {'lr': 0.00036746055065423435, 'samples': 10168128, 'steps': 52958, 'loss/train': 1.4835357666015625} 08/30/2021 22:46:17 - INFO - __main__ - Step 52960: {'lr': 0.0003674558660969685, 'samples': 10168320, 'steps': 52959, 'loss/train': 1.514636516571045} 08/30/2021 22:46:17 - INFO - __main__ - Step 52961: {'lr': 0.0003674511814867788, 'samples': 10168512, 'steps': 52960, 'loss/train': 1.3876765966415405} 08/30/2021 22:46:18 - INFO - __main__ - Step 52962: {'lr': 0.00036744649682366744, 'samples': 10168704, 'steps': 52961, 'loss/train': 1.4712228775024414} 08/30/2021 22:46:18 - INFO - __main__ - Step 52963: {'lr': 0.0003674418121076365, 'samples': 10168896, 'steps': 52962, 'loss/train': 0.9659256339073181} 08/30/2021 22:46:19 - INFO - __main__ - Step 52964: {'lr': 0.00036743712733868807, 'samples': 10169088, 'steps': 52963, 'loss/train': 0.9840158224105835} 08/30/2021 22:46:20 - INFO - __main__ - Step 52965: {'lr': 0.00036743244251682424, 'samples': 10169280, 'steps': 52964, 'loss/train': 1.1047409772872925} 08/30/2021 22:46:20 - INFO - __main__ - Step 52966: {'lr': 0.00036742775764204717, 'samples': 10169472, 'steps': 52965, 'loss/train': 1.4516327381134033} 08/30/2021 22:46:21 - INFO - __main__ - Step 52967: {'lr': 0.000367423072714359, 'samples': 10169664, 'steps': 52966, 'loss/train': 1.3878978490829468} 08/30/2021 22:46:21 - INFO - __main__ - Step 52968: {'lr': 0.00036741838773376187, 'samples': 10169856, 'steps': 52967, 'loss/train': 1.4295021295547485} 08/30/2021 22:46:23 - INFO - __main__ - Step 52969: {'lr': 0.00036741370270025776, 'samples': 10170048, 'steps': 52968, 'loss/train': 1.4250948429107666} 08/30/2021 22:46:23 - INFO - __main__ - Step 52970: {'lr': 0.0003674090176138488, 'samples': 10170240, 'steps': 52969, 'loss/train': 1.7038239240646362} 08/30/2021 22:46:23 - INFO - __main__ - Step 52971: {'lr': 0.0003674043324745372, 'samples': 10170432, 'steps': 52970, 'loss/train': 1.3187508583068848} 08/30/2021 22:46:24 - INFO - __main__ - Step 52972: {'lr': 0.000367399647282325, 'samples': 10170624, 'steps': 52971, 'loss/train': 1.6203367710113525} 08/30/2021 22:46:24 - INFO - __main__ - Step 52973: {'lr': 0.0003673949620372143, 'samples': 10170816, 'steps': 52972, 'loss/train': 1.4784064292907715} 08/30/2021 22:46:26 - INFO - __main__ - Step 52974: {'lr': 0.0003673902767392074, 'samples': 10171008, 'steps': 52973, 'loss/train': 1.2993137836456299} 08/30/2021 22:46:26 - INFO - __main__ - Step 52975: {'lr': 0.00036738559138830613, 'samples': 10171200, 'steps': 52974, 'loss/train': 1.7943003177642822} 08/30/2021 22:46:26 - INFO - __main__ - Step 52976: {'lr': 0.0003673809059845127, 'samples': 10171392, 'steps': 52975, 'loss/train': 1.8203996419906616} 08/30/2021 22:46:27 - INFO - __main__ - Step 52977: {'lr': 0.00036737622052782933, 'samples': 10171584, 'steps': 52976, 'loss/train': 1.5651434659957886} 08/30/2021 22:46:27 - INFO - __main__ - Step 52978: {'lr': 0.000367371535018258, 'samples': 10171776, 'steps': 52977, 'loss/train': 1.6012505292892456} 08/30/2021 22:46:28 - INFO - __main__ - Step 52979: {'lr': 0.00036736684945580083, 'samples': 10171968, 'steps': 52978, 'loss/train': 0.6337563395500183} 08/30/2021 22:46:29 - INFO - __main__ - Step 52980: {'lr': 0.00036736216384046, 'samples': 10172160, 'steps': 52979, 'loss/train': 1.217097520828247} 08/30/2021 22:46:30 - INFO - __main__ - Step 52981: {'lr': 0.00036735747817223766, 'samples': 10172352, 'steps': 52980, 'loss/train': 1.2732174396514893} 08/30/2021 22:46:30 - INFO - __main__ - Step 52982: {'lr': 0.00036735279245113573, 'samples': 10172544, 'steps': 52981, 'loss/train': 1.4605273008346558} 08/30/2021 22:46:31 - INFO - __main__ - Step 52983: {'lr': 0.0003673481066771565, 'samples': 10172736, 'steps': 52982, 'loss/train': 1.8992276191711426} 08/30/2021 22:46:31 - INFO - __main__ - Step 52984: {'lr': 0.00036734342085030205, 'samples': 10172928, 'steps': 52983, 'loss/train': 1.651639461517334} 08/30/2021 22:46:32 - INFO - __main__ - Step 52985: {'lr': 0.0003673387349705744, 'samples': 10173120, 'steps': 52984, 'loss/train': 1.3642909526824951} 08/30/2021 22:46:33 - INFO - __main__ - Step 52986: {'lr': 0.00036733404903797575, 'samples': 10173312, 'steps': 52985, 'loss/train': 1.6846660375595093} 08/30/2021 22:46:33 - INFO - __main__ - Step 52987: {'lr': 0.00036732936305250826, 'samples': 10173504, 'steps': 52986, 'loss/train': 0.7596871852874756} 08/30/2021 22:46:34 - INFO - __main__ - Step 52988: {'lr': 0.00036732467701417387, 'samples': 10173696, 'steps': 52987, 'loss/train': 1.7918012142181396} 08/30/2021 22:46:34 - INFO - __main__ - Step 52989: {'lr': 0.00036731999092297487, 'samples': 10173888, 'steps': 52988, 'loss/train': 0.9866682291030884} 08/30/2021 22:46:36 - INFO - __main__ - Step 52990: {'lr': 0.0003673153047789132, 'samples': 10174080, 'steps': 52989, 'loss/train': 1.1140183210372925} 08/30/2021 22:46:36 - INFO - __main__ - Step 52991: {'lr': 0.0003673106185819911, 'samples': 10174272, 'steps': 52990, 'loss/train': 1.376823902130127} 08/30/2021 22:46:36 - INFO - __main__ - Step 52992: {'lr': 0.00036730593233221074, 'samples': 10174464, 'steps': 52991, 'loss/train': 1.2224533557891846} 08/30/2021 22:46:37 - INFO - __main__ - Step 52993: {'lr': 0.000367301246029574, 'samples': 10174656, 'steps': 52992, 'loss/train': 1.5230166912078857} 08/30/2021 22:46:37 - INFO - __main__ - Step 52994: {'lr': 0.00036729655967408326, 'samples': 10174848, 'steps': 52993, 'loss/train': 0.0942855179309845} 08/30/2021 22:46:39 - INFO - __main__ - Step 52995: {'lr': 0.00036729187326574043, 'samples': 10175040, 'steps': 52994, 'loss/train': 1.4928103685379028} 08/30/2021 22:46:39 - INFO - __main__ - Step 52996: {'lr': 0.00036728718680454763, 'samples': 10175232, 'steps': 52995, 'loss/train': 1.3302651643753052} 08/30/2021 22:46:40 - INFO - __main__ - Step 52997: {'lr': 0.0003672825002905071, 'samples': 10175424, 'steps': 52996, 'loss/train': 2.0062875747680664} 08/30/2021 22:46:40 - INFO - __main__ - Step 52998: {'lr': 0.0003672778137236209, 'samples': 10175616, 'steps': 52997, 'loss/train': 1.104461908340454} 08/30/2021 22:46:40 - INFO - __main__ - Step 52999: {'lr': 0.0003672731271038911, 'samples': 10175808, 'steps': 52998, 'loss/train': 1.7488676309585571} 08/30/2021 22:46:42 - INFO - __main__ - Step 53000: {'lr': 0.0003672684404313199, 'samples': 10176000, 'steps': 52999, 'loss/train': 1.5353302955627441} 08/30/2021 22:46:42 - INFO - __main__ - Step 53001: {'lr': 0.00036726375370590926, 'samples': 10176192, 'steps': 53000, 'loss/train': 1.9689027070999146} 08/30/2021 22:46:43 - INFO - __main__ - Step 53002: {'lr': 0.0003672590669276614, 'samples': 10176384, 'steps': 53001, 'loss/train': 1.2587339878082275} 08/30/2021 22:46:43 - INFO - __main__ - Step 53003: {'lr': 0.0003672543800965784, 'samples': 10176576, 'steps': 53002, 'loss/train': 0.8535210490226746} 08/30/2021 22:46:43 - INFO - __main__ - Step 53004: {'lr': 0.00036724969321266245, 'samples': 10176768, 'steps': 53003, 'loss/train': 1.713154911994934} 08/30/2021 22:46:44 - INFO - __main__ - Step 53005: {'lr': 0.0003672450062759156, 'samples': 10176960, 'steps': 53004, 'loss/train': 1.4972234964370728} 08/30/2021 22:46:45 - INFO - __main__ - Step 53006: {'lr': 0.00036724031928633995, 'samples': 10177152, 'steps': 53005, 'loss/train': 3.3697025775909424} 08/30/2021 22:46:46 - INFO - __main__ - Step 53007: {'lr': 0.00036723563224393753, 'samples': 10177344, 'steps': 53006, 'loss/train': 1.5223716497421265} 08/30/2021 22:46:46 - INFO - __main__ - Step 53008: {'lr': 0.0003672309451487106, 'samples': 10177536, 'steps': 53007, 'loss/train': 1.276400089263916} 08/30/2021 22:46:46 - INFO - __main__ - Step 53009: {'lr': 0.0003672262580006612, 'samples': 10177728, 'steps': 53008, 'loss/train': 1.304882287979126} 08/30/2021 22:46:47 - INFO - __main__ - Step 53010: {'lr': 0.00036722157079979153, 'samples': 10177920, 'steps': 53009, 'loss/train': 1.6667906045913696} 08/30/2021 22:46:48 - INFO - __main__ - Step 53011: {'lr': 0.0003672168835461036, 'samples': 10178112, 'steps': 53010, 'loss/train': 1.0986615419387817} 08/30/2021 22:46:49 - INFO - __main__ - Step 53012: {'lr': 0.00036721219623959956, 'samples': 10178304, 'steps': 53011, 'loss/train': 1.2280393838882446} 08/30/2021 22:46:49 - INFO - __main__ - Step 53013: {'lr': 0.00036720750888028143, 'samples': 10178496, 'steps': 53012, 'loss/train': 1.118146300315857} 08/30/2021 22:46:50 - INFO - __main__ - Step 53014: {'lr': 0.0003672028214681515, 'samples': 10178688, 'steps': 53013, 'loss/train': 0.0921279564499855} 08/30/2021 22:46:50 - INFO - __main__ - Step 53015: {'lr': 0.00036719813400321174, 'samples': 10178880, 'steps': 53014, 'loss/train': 1.11503005027771} 08/30/2021 22:46:52 - INFO - __main__ - Step 53016: {'lr': 0.0003671934464854643, 'samples': 10179072, 'steps': 53015, 'loss/train': 1.5488438606262207} 08/30/2021 22:46:52 - INFO - __main__ - Step 53017: {'lr': 0.00036718875891491134, 'samples': 10179264, 'steps': 53016, 'loss/train': 0.9068090915679932} 08/30/2021 22:46:52 - INFO - __main__ - Step 53018: {'lr': 0.0003671840712915549, 'samples': 10179456, 'steps': 53017, 'loss/train': 1.3363335132598877} 08/30/2021 22:46:53 - INFO - __main__ - Step 53019: {'lr': 0.0003671793836153972, 'samples': 10179648, 'steps': 53018, 'loss/train': 1.0532034635543823} 08/30/2021 22:46:53 - INFO - __main__ - Step 53020: {'lr': 0.00036717469588644017, 'samples': 10179840, 'steps': 53019, 'loss/train': 1.3713171482086182} 08/30/2021 22:46:54 - INFO - __main__ - Step 53021: {'lr': 0.000367170008104686, 'samples': 10180032, 'steps': 53020, 'loss/train': 1.546654224395752} 08/30/2021 22:46:55 - INFO - __main__ - Step 53022: {'lr': 0.000367165320270137, 'samples': 10180224, 'steps': 53021, 'loss/train': 1.233120322227478} 08/30/2021 22:46:55 - INFO - __main__ - Step 53023: {'lr': 0.000367160632382795, 'samples': 10180416, 'steps': 53022, 'loss/train': 1.8887003660202026} 08/30/2021 22:46:56 - INFO - __main__ - Step 53024: {'lr': 0.00036715594444266224, 'samples': 10180608, 'steps': 53023, 'loss/train': 2.006420612335205} 08/30/2021 22:46:56 - INFO - __main__ - Step 53025: {'lr': 0.0003671512564497408, 'samples': 10180800, 'steps': 53024, 'loss/train': 1.4312664270401} 08/30/2021 22:46:58 - INFO - __main__ - Step 53026: {'lr': 0.0003671465684040328, 'samples': 10180992, 'steps': 53025, 'loss/train': 1.4332363605499268} 08/30/2021 22:46:58 - INFO - __main__ - Step 53027: {'lr': 0.00036714188030554046, 'samples': 10181184, 'steps': 53026, 'loss/train': 1.1092573404312134} 08/30/2021 22:46:58 - INFO - __main__ - Step 53028: {'lr': 0.00036713719215426577, 'samples': 10181376, 'steps': 53027, 'loss/train': 0.8608169555664062} 08/30/2021 22:46:59 - INFO - __main__ - Step 53029: {'lr': 0.0003671325039502108, 'samples': 10181568, 'steps': 53028, 'loss/train': 1.4866570234298706} 08/30/2021 22:46:59 - INFO - __main__ - Step 53030: {'lr': 0.0003671278156933778, 'samples': 10181760, 'steps': 53029, 'loss/train': 0.697790801525116} 08/30/2021 22:46:59 - INFO - __main__ - Step 53031: {'lr': 0.00036712312738376875, 'samples': 10181952, 'steps': 53030, 'loss/train': 0.49303168058395386} 08/30/2021 22:47:01 - INFO - __main__ - Step 53032: {'lr': 0.00036711843902138586, 'samples': 10182144, 'steps': 53031, 'loss/train': 1.3356133699417114} 08/30/2021 22:47:02 - INFO - __main__ - Step 53033: {'lr': 0.0003671137506062312, 'samples': 10182336, 'steps': 53032, 'loss/train': 1.5197365283966064} 08/30/2021 22:47:02 - INFO - __main__ - Step 53034: {'lr': 0.000367109062138307, 'samples': 10182528, 'steps': 53033, 'loss/train': 1.443939447402954} 08/30/2021 22:47:03 - INFO - __main__ - Step 53035: {'lr': 0.00036710437361761513, 'samples': 10182720, 'steps': 53034, 'loss/train': 1.565474033355713} 08/30/2021 22:47:03 - INFO - __main__ - Step 53036: {'lr': 0.00036709968504415786, 'samples': 10182912, 'steps': 53035, 'loss/train': 1.7932683229446411} 08/30/2021 22:47:05 - INFO - __main__ - Step 53037: {'lr': 0.00036709499641793725, 'samples': 10183104, 'steps': 53036, 'loss/train': 1.0941112041473389} 08/30/2021 22:47:05 - INFO - __main__ - Step 53038: {'lr': 0.00036709030773895545, 'samples': 10183296, 'steps': 53037, 'loss/train': 0.04810842499136925} 08/30/2021 22:47:05 - INFO - __main__ - Step 53039: {'lr': 0.0003670856190072146, 'samples': 10183488, 'steps': 53038, 'loss/train': 1.2002418041229248} 08/30/2021 22:47:06 - INFO - __main__ - Step 53040: {'lr': 0.00036708093022271677, 'samples': 10183680, 'steps': 53039, 'loss/train': 0.39169299602508545} 08/30/2021 22:47:06 - INFO - __main__ - Step 53041: {'lr': 0.0003670762413854641, 'samples': 10183872, 'steps': 53040, 'loss/train': 1.084177017211914} 08/30/2021 22:47:08 - INFO - __main__ - Step 53042: {'lr': 0.0003670715524954587, 'samples': 10184064, 'steps': 53041, 'loss/train': 1.513096570968628} 08/30/2021 22:47:08 - INFO - __main__ - Step 53043: {'lr': 0.0003670668635527026, 'samples': 10184256, 'steps': 53042, 'loss/train': 1.4138253927230835} 08/30/2021 22:47:09 - INFO - __main__ - Step 53044: {'lr': 0.00036706217455719805, 'samples': 10184448, 'steps': 53043, 'loss/train': 0.12862081825733185} 08/30/2021 22:47:09 - INFO - __main__ - Step 53045: {'lr': 0.000367057485508947, 'samples': 10184640, 'steps': 53044, 'loss/train': 0.04579971358180046} 08/30/2021 22:47:10 - INFO - __main__ - Step 53046: {'lr': 0.0003670527964079517, 'samples': 10184832, 'steps': 53045, 'loss/train': 1.066494345664978} 08/30/2021 22:47:10 - INFO - __main__ - Step 53047: {'lr': 0.0003670481072542142, 'samples': 10185024, 'steps': 53046, 'loss/train': 0.6270720362663269} 08/30/2021 22:47:11 - INFO - __main__ - Step 53048: {'lr': 0.0003670434180477367, 'samples': 10185216, 'steps': 53047, 'loss/train': 1.6485673189163208} 08/30/2021 22:47:12 - INFO - __main__ - Step 53049: {'lr': 0.00036703872878852115, 'samples': 10185408, 'steps': 53048, 'loss/train': 1.623889446258545} 08/30/2021 22:47:12 - INFO - __main__ - Step 53050: {'lr': 0.00036703403947656977, 'samples': 10185600, 'steps': 53049, 'loss/train': 1.3428325653076172} 08/30/2021 22:47:12 - INFO - __main__ - Step 53051: {'lr': 0.0003670293501118847, 'samples': 10185792, 'steps': 53050, 'loss/train': 0.9774247407913208} 08/30/2021 22:47:13 - INFO - __main__ - Step 53052: {'lr': 0.00036702466069446797, 'samples': 10185984, 'steps': 53051, 'loss/train': 1.6507772207260132} 08/30/2021 22:47:15 - INFO - __main__ - Step 53053: {'lr': 0.00036701997122432173, 'samples': 10186176, 'steps': 53052, 'loss/train': 0.6613092422485352} 08/30/2021 22:47:15 - INFO - __main__ - Step 53054: {'lr': 0.00036701528170144813, 'samples': 10186368, 'steps': 53053, 'loss/train': 1.5881325006484985} 08/30/2021 22:47:16 - INFO - __main__ - Step 53055: {'lr': 0.0003670105921258493, 'samples': 10186560, 'steps': 53054, 'loss/train': 0.9100768566131592} 08/30/2021 22:47:16 - INFO - __main__ - Step 53056: {'lr': 0.0003670059024975272, 'samples': 10186752, 'steps': 53055, 'loss/train': 0.02837066724896431} 08/30/2021 22:47:16 - INFO - __main__ - Step 53057: {'lr': 0.00036700121281648415, 'samples': 10186944, 'steps': 53056, 'loss/train': 1.1765162944793701} 08/30/2021 22:47:17 - INFO - __main__ - Step 53058: {'lr': 0.000366996523082722, 'samples': 10187136, 'steps': 53057, 'loss/train': 1.3230974674224854} 08/30/2021 22:47:19 - INFO - __main__ - Step 53059: {'lr': 0.00036699183329624315, 'samples': 10187328, 'steps': 53058, 'loss/train': 0.1231624037027359} 08/30/2021 22:47:19 - INFO - __main__ - Step 53060: {'lr': 0.00036698714345704956, 'samples': 10187520, 'steps': 53059, 'loss/train': 1.0395394563674927} 08/30/2021 22:47:20 - INFO - __main__ - Step 53061: {'lr': 0.00036698245356514336, 'samples': 10187712, 'steps': 53060, 'loss/train': 1.0675544738769531} 08/30/2021 22:47:20 - INFO - __main__ - Step 53062: {'lr': 0.0003669777636205267, 'samples': 10187904, 'steps': 53061, 'loss/train': 0.022404806688427925} 08/30/2021 22:47:20 - INFO - __main__ - Step 53063: {'lr': 0.00036697307362320165, 'samples': 10188096, 'steps': 53062, 'loss/train': 0.022075502201914787} 08/30/2021 22:47:21 - INFO - __main__ - Step 53064: {'lr': 0.0003669683835731703, 'samples': 10188288, 'steps': 53063, 'loss/train': 1.3558034896850586} 08/30/2021 22:47:21 - INFO - __main__ - Step 53065: {'lr': 0.00036696369347043477, 'samples': 10188480, 'steps': 53064, 'loss/train': 1.1132031679153442} 08/30/2021 22:47:22 - INFO - __main__ - Step 53066: {'lr': 0.00036695900331499735, 'samples': 10188672, 'steps': 53065, 'loss/train': 0.710574746131897} 08/30/2021 22:47:23 - INFO - __main__ - Step 53067: {'lr': 0.0003669543131068599, 'samples': 10188864, 'steps': 53066, 'loss/train': 1.6990859508514404} 08/30/2021 22:47:23 - INFO - __main__ - Step 53068: {'lr': 0.0003669496228460247, 'samples': 10189056, 'steps': 53067, 'loss/train': 1.8454500436782837} 08/30/2021 22:47:24 - INFO - __main__ - Step 53069: {'lr': 0.00036694493253249373, 'samples': 10189248, 'steps': 53068, 'loss/train': 1.8786671161651611} 08/30/2021 22:47:24 - INFO - __main__ - Step 53070: {'lr': 0.0003669402421662692, 'samples': 10189440, 'steps': 53069, 'loss/train': 1.2989208698272705} 08/30/2021 22:47:26 - INFO - __main__ - Step 53071: {'lr': 0.0003669355517473532, 'samples': 10189632, 'steps': 53070, 'loss/train': 1.2290717363357544} 08/30/2021 22:47:26 - INFO - __main__ - Step 53072: {'lr': 0.0003669308612757479, 'samples': 10189824, 'steps': 53071, 'loss/train': 1.2725080251693726} 08/30/2021 22:47:27 - INFO - __main__ - Step 53073: {'lr': 0.0003669261707514553, 'samples': 10190016, 'steps': 53072, 'loss/train': 0.49253711104393005} 08/30/2021 22:47:27 - INFO - __main__ - Step 53074: {'lr': 0.0003669214801744776, 'samples': 10190208, 'steps': 53073, 'loss/train': 1.5833349227905273} 08/30/2021 22:47:27 - INFO - __main__ - Step 53075: {'lr': 0.0003669167895448169, 'samples': 10190400, 'steps': 53074, 'loss/train': 1.4562004804611206} 08/30/2021 22:47:29 - INFO - __main__ - Step 53076: {'lr': 0.0003669120988624752, 'samples': 10190592, 'steps': 53075, 'loss/train': 1.7953530550003052} 08/30/2021 22:47:29 - INFO - __main__ - Step 53077: {'lr': 0.0003669074081274548, 'samples': 10190784, 'steps': 53076, 'loss/train': 1.2561743259429932} 08/30/2021 22:47:30 - INFO - __main__ - Step 53078: {'lr': 0.0003669027173397577, 'samples': 10190976, 'steps': 53077, 'loss/train': 1.3289263248443604} 08/30/2021 22:47:30 - INFO - __main__ - Step 53079: {'lr': 0.00036689802649938607, 'samples': 10191168, 'steps': 53078, 'loss/train': 0.41601547598838806} 08/30/2021 22:47:30 - INFO - __main__ - Step 53080: {'lr': 0.00036689333560634195, 'samples': 10191360, 'steps': 53079, 'loss/train': 1.1768739223480225} 08/30/2021 22:47:32 - INFO - __main__ - Step 53081: {'lr': 0.00036688864466062756, 'samples': 10191552, 'steps': 53080, 'loss/train': 1.187766432762146} 08/30/2021 22:47:32 - INFO - __main__ - Step 53082: {'lr': 0.0003668839536622449, 'samples': 10191744, 'steps': 53081, 'loss/train': 1.200555682182312} 08/30/2021 22:47:33 - INFO - __main__ - Step 53083: {'lr': 0.0003668792626111962, 'samples': 10191936, 'steps': 53082, 'loss/train': 1.66214120388031} 08/30/2021 22:47:33 - INFO - __main__ - Step 53084: {'lr': 0.0003668745715074834, 'samples': 10192128, 'steps': 53083, 'loss/train': 1.0854735374450684} 08/30/2021 22:47:33 - INFO - __main__ - Step 53085: {'lr': 0.00036686988035110877, 'samples': 10192320, 'steps': 53084, 'loss/train': 0.23303203284740448} 08/30/2021 22:47:35 - INFO - __main__ - Step 53086: {'lr': 0.0003668651891420744, 'samples': 10192512, 'steps': 53085, 'loss/train': 1.7780293226242065} 08/30/2021 22:47:35 - INFO - __main__ - Step 53087: {'lr': 0.0003668604978803823, 'samples': 10192704, 'steps': 53086, 'loss/train': 0.5159832239151001} 08/30/2021 22:47:36 - INFO - __main__ - Step 53088: {'lr': 0.0003668558065660348, 'samples': 10192896, 'steps': 53087, 'loss/train': 1.6527228355407715} 08/30/2021 22:47:36 - INFO - __main__ - Step 53089: {'lr': 0.0003668511151990338, 'samples': 10193088, 'steps': 53088, 'loss/train': 1.2927652597427368} 08/30/2021 22:47:36 - INFO - __main__ - Step 53090: {'lr': 0.0003668464237793815, 'samples': 10193280, 'steps': 53089, 'loss/train': 1.52219557762146} 08/30/2021 22:47:37 - INFO - __main__ - Step 53091: {'lr': 0.00036684173230707996, 'samples': 10193472, 'steps': 53090, 'loss/train': 2.626725673675537} 08/30/2021 22:47:39 - INFO - __main__ - Step 53092: {'lr': 0.00036683704078213137, 'samples': 10193664, 'steps': 53091, 'loss/train': 1.0025660991668701} 08/30/2021 22:47:39 - INFO - __main__ - Step 53093: {'lr': 0.00036683234920453783, 'samples': 10193856, 'steps': 53092, 'loss/train': 0.6256605982780457} 08/30/2021 22:47:40 - INFO - __main__ - Step 53094: {'lr': 0.0003668276575743014, 'samples': 10194048, 'steps': 53093, 'loss/train': 1.2839723825454712} 08/30/2021 22:47:40 - INFO - __main__ - Step 53095: {'lr': 0.0003668229658914243, 'samples': 10194240, 'steps': 53094, 'loss/train': 1.1742956638336182} 08/30/2021 22:47:40 - INFO - __main__ - Step 53096: {'lr': 0.0003668182741559085, 'samples': 10194432, 'steps': 53095, 'loss/train': 1.7711315155029297} 08/30/2021 22:47:42 - INFO - __main__ - Step 53097: {'lr': 0.00036681358236775625, 'samples': 10194624, 'steps': 53096, 'loss/train': 1.163830280303955} 08/30/2021 22:47:42 - INFO - __main__ - Step 53098: {'lr': 0.00036680889052696954, 'samples': 10194816, 'steps': 53097, 'loss/train': 1.4291363954544067} 08/30/2021 22:47:43 - INFO - __main__ - Step 53099: {'lr': 0.00036680419863355056, 'samples': 10195008, 'steps': 53098, 'loss/train': 1.1183979511260986} 08/30/2021 22:47:43 - INFO - __main__ - Step 53100: {'lr': 0.0003667995066875014, 'samples': 10195200, 'steps': 53099, 'loss/train': 1.6739184856414795} 08/30/2021 22:47:43 - INFO - __main__ - Step 53101: {'lr': 0.00036679481468882425, 'samples': 10195392, 'steps': 53100, 'loss/train': 1.6509748697280884} 08/30/2021 22:47:45 - INFO - __main__ - Step 53102: {'lr': 0.00036679012263752115, 'samples': 10195584, 'steps': 53101, 'loss/train': 1.403045654296875} 08/30/2021 22:47:45 - INFO - __main__ - Step 53103: {'lr': 0.00036678543053359413, 'samples': 10195776, 'steps': 53102, 'loss/train': 1.9423904418945312} 08/30/2021 22:47:46 - INFO - __main__ - Step 53104: {'lr': 0.0003667807383770455, 'samples': 10195968, 'steps': 53103, 'loss/train': 1.424591302871704} 08/30/2021 22:47:46 - INFO - __main__ - Step 53105: {'lr': 0.00036677604616787717, 'samples': 10196160, 'steps': 53104, 'loss/train': 0.9685341119766235} 08/30/2021 22:47:47 - INFO - __main__ - Step 53106: {'lr': 0.00036677135390609145, 'samples': 10196352, 'steps': 53105, 'loss/train': 2.101757287979126} 08/30/2021 22:47:48 - INFO - __main__ - Step 53107: {'lr': 0.0003667666615916903, 'samples': 10196544, 'steps': 53106, 'loss/train': 0.03861301764845848} 08/30/2021 22:47:49 - INFO - __main__ - Step 53108: {'lr': 0.00036676196922467595, 'samples': 10196736, 'steps': 53107, 'loss/train': 0.8503670692443848} 08/30/2021 22:47:49 - INFO - __main__ - Step 53109: {'lr': 0.00036675727680505045, 'samples': 10196928, 'steps': 53108, 'loss/train': 1.0691540241241455} 08/30/2021 22:47:49 - INFO - __main__ - Step 53110: {'lr': 0.0003667525843328159, 'samples': 10197120, 'steps': 53109, 'loss/train': 1.2914034128189087} 08/30/2021 22:47:50 - INFO - __main__ - Step 53111: {'lr': 0.0003667478918079744, 'samples': 10197312, 'steps': 53110, 'loss/train': 1.4227043390274048} 08/30/2021 22:47:51 - INFO - __main__ - Step 53112: {'lr': 0.0003667431992305281, 'samples': 10197504, 'steps': 53111, 'loss/train': 1.1425765752792358} 08/30/2021 22:47:52 - INFO - __main__ - Step 53113: {'lr': 0.0003667385066004792, 'samples': 10197696, 'steps': 53112, 'loss/train': 1.0420361757278442} 08/30/2021 22:47:52 - INFO - __main__ - Step 53114: {'lr': 0.0003667338139178297, 'samples': 10197888, 'steps': 53113, 'loss/train': 0.8898513913154602} 08/30/2021 22:47:52 - INFO - __main__ - Step 53115: {'lr': 0.0003667291211825817, 'samples': 10198080, 'steps': 53114, 'loss/train': 1.3359873294830322} 08/30/2021 22:47:53 - INFO - __main__ - Step 53116: {'lr': 0.0003667244283947374, 'samples': 10198272, 'steps': 53115, 'loss/train': 1.20332670211792} 08/30/2021 22:47:53 - INFO - __main__ - Step 53117: {'lr': 0.0003667197355542989, 'samples': 10198464, 'steps': 53116, 'loss/train': 0.6552751660346985} 08/30/2021 22:47:55 - INFO - __main__ - Step 53118: {'lr': 0.0003667150426612682, 'samples': 10198656, 'steps': 53117, 'loss/train': 1.5831595659255981} 08/30/2021 22:47:55 - INFO - __main__ - Step 53119: {'lr': 0.0003667103497156475, 'samples': 10198848, 'steps': 53118, 'loss/train': 1.1328293085098267} 08/30/2021 22:47:55 - INFO - __main__ - Step 53120: {'lr': 0.00036670565671743905, 'samples': 10199040, 'steps': 53119, 'loss/train': 1.2508949041366577} 08/30/2021 22:47:56 - INFO - __main__ - Step 53121: {'lr': 0.0003667009636666447, 'samples': 10199232, 'steps': 53120, 'loss/train': 1.647360920906067} 08/30/2021 22:47:56 - INFO - __main__ - Step 53122: {'lr': 0.00036669627056326685, 'samples': 10199424, 'steps': 53121, 'loss/train': 0.7447426915168762} 08/30/2021 22:47:58 - INFO - __main__ - Step 53123: {'lr': 0.0003666915774073073, 'samples': 10199616, 'steps': 53122, 'loss/train': 1.2288435697555542} 08/30/2021 22:47:58 - INFO - __main__ - Step 53124: {'lr': 0.00036668688419876837, 'samples': 10199808, 'steps': 53123, 'loss/train': 0.4710957407951355} 08/30/2021 22:47:58 - INFO - __main__ - Step 53125: {'lr': 0.0003666821909376522, 'samples': 10200000, 'steps': 53124, 'loss/train': 1.7645479440689087} 08/30/2021 22:47:59 - INFO - __main__ - Step 53126: {'lr': 0.00036667749762396074, 'samples': 10200192, 'steps': 53125, 'loss/train': 1.1250778436660767} 08/30/2021 22:47:59 - INFO - __main__ - Step 53127: {'lr': 0.0003666728042576962, 'samples': 10200384, 'steps': 53126, 'loss/train': 1.566033959388733} 08/30/2021 22:48:01 - INFO - __main__ - Step 53128: {'lr': 0.0003666681108388608, 'samples': 10200576, 'steps': 53127, 'loss/train': 1.7354872226715088} 08/30/2021 22:48:01 - INFO - __main__ - Step 53129: {'lr': 0.0003666634173674565, 'samples': 10200768, 'steps': 53128, 'loss/train': 1.3731133937835693} 08/30/2021 22:48:01 - INFO - __main__ - Step 53130: {'lr': 0.00036665872384348543, 'samples': 10200960, 'steps': 53129, 'loss/train': 1.2538998126983643} 08/30/2021 22:48:02 - INFO - __main__ - Step 53131: {'lr': 0.00036665403026694976, 'samples': 10201152, 'steps': 53130, 'loss/train': 0.9703413844108582} 08/30/2021 22:48:02 - INFO - __main__ - Step 53132: {'lr': 0.0003666493366378516, 'samples': 10201344, 'steps': 53131, 'loss/train': 1.2547544240951538} 08/30/2021 22:48:04 - INFO - __main__ - Step 53133: {'lr': 0.00036664464295619296, 'samples': 10201536, 'steps': 53132, 'loss/train': 1.7632980346679688} 08/30/2021 22:48:04 - INFO - __main__ - Step 53134: {'lr': 0.0003666399492219762, 'samples': 10201728, 'steps': 53133, 'loss/train': 1.574918508529663} 08/30/2021 22:48:05 - INFO - __main__ - Step 53135: {'lr': 0.0003666352554352032, 'samples': 10201920, 'steps': 53134, 'loss/train': 1.9045681953430176} 08/30/2021 22:48:05 - INFO - __main__ - Step 53136: {'lr': 0.00036663056159587614, 'samples': 10202112, 'steps': 53135, 'loss/train': 0.059278469532728195} 08/30/2021 22:48:05 - INFO - __main__ - Step 53137: {'lr': 0.0003666258677039971, 'samples': 10202304, 'steps': 53136, 'loss/train': 1.2600656747817993} 08/30/2021 22:48:06 - INFO - __main__ - Step 53138: {'lr': 0.00036662117375956834, 'samples': 10202496, 'steps': 53137, 'loss/train': 1.1118632555007935} 08/30/2021 22:48:07 - INFO - __main__ - Step 53139: {'lr': 0.00036661647976259185, 'samples': 10202688, 'steps': 53138, 'loss/train': 1.5370559692382812} 08/30/2021 22:48:08 - INFO - __main__ - Step 53140: {'lr': 0.0003666117857130698, 'samples': 10202880, 'steps': 53139, 'loss/train': 1.055375337600708} 08/30/2021 22:48:08 - INFO - __main__ - Step 53141: {'lr': 0.00036660709161100423, 'samples': 10203072, 'steps': 53140, 'loss/train': 1.829869270324707} 08/30/2021 22:48:08 - INFO - __main__ - Step 53142: {'lr': 0.0003666023974563973, 'samples': 10203264, 'steps': 53141, 'loss/train': 1.3564083576202393} 08/30/2021 22:48:09 - INFO - __main__ - Step 53143: {'lr': 0.0003665977032492511, 'samples': 10203456, 'steps': 53142, 'loss/train': 1.0254392623901367} 08/30/2021 22:48:11 - INFO - __main__ - Step 53144: {'lr': 0.00036659300898956784, 'samples': 10203648, 'steps': 53143, 'loss/train': 1.7108354568481445} 08/30/2021 22:48:11 - INFO - __main__ - Step 53145: {'lr': 0.0003665883146773496, 'samples': 10203840, 'steps': 53144, 'loss/train': 1.274196743965149} 08/30/2021 22:48:11 - INFO - __main__ - Step 53146: {'lr': 0.0003665836203125984, 'samples': 10204032, 'steps': 53145, 'loss/train': 1.2545244693756104} 08/30/2021 22:48:12 - INFO - __main__ - Step 53147: {'lr': 0.0003665789258953164, 'samples': 10204224, 'steps': 53146, 'loss/train': 1.4287270307540894} 08/30/2021 22:48:12 - INFO - __main__ - Step 53148: {'lr': 0.00036657423142550576, 'samples': 10204416, 'steps': 53147, 'loss/train': 1.3680726289749146} 08/30/2021 22:48:14 - INFO - __main__ - Step 53149: {'lr': 0.00036656953690316865, 'samples': 10204608, 'steps': 53148, 'loss/train': 2.4107770919799805} 08/30/2021 22:48:14 - INFO - __main__ - Step 53150: {'lr': 0.000366564842328307, 'samples': 10204800, 'steps': 53149, 'loss/train': 1.1396530866622925} 08/30/2021 22:48:14 - INFO - __main__ - Step 53151: {'lr': 0.0003665601477009231, 'samples': 10204992, 'steps': 53150, 'loss/train': 0.936739981174469} 08/30/2021 22:48:15 - INFO - __main__ - Step 53152: {'lr': 0.00036655545302101894, 'samples': 10205184, 'steps': 53151, 'loss/train': 2.040178060531616} 08/30/2021 22:48:15 - INFO - __main__ - Step 53153: {'lr': 0.00036655075828859673, 'samples': 10205376, 'steps': 53152, 'loss/train': 0.8591750264167786} 08/30/2021 22:48:17 - INFO - __main__ - Step 53154: {'lr': 0.0003665460635036585, 'samples': 10205568, 'steps': 53153, 'loss/train': 1.7109917402267456} 08/30/2021 22:48:17 - INFO - __main__ - Step 53155: {'lr': 0.00036654136866620646, 'samples': 10205760, 'steps': 53154, 'loss/train': 1.1160075664520264} 08/30/2021 22:48:17 - INFO - __main__ - Step 53156: {'lr': 0.0003665366737762427, 'samples': 10205952, 'steps': 53155, 'loss/train': 1.077751874923706} 08/30/2021 22:48:18 - INFO - __main__ - Step 53157: {'lr': 0.0003665319788337692, 'samples': 10206144, 'steps': 53156, 'loss/train': 1.0127267837524414} 08/30/2021 22:48:18 - INFO - __main__ - Step 53158: {'lr': 0.0003665272838387883, 'samples': 10206336, 'steps': 53157, 'loss/train': 1.58287513256073} 08/30/2021 22:48:20 - INFO - __main__ - Step 53159: {'lr': 0.00036652258879130194, 'samples': 10206528, 'steps': 53158, 'loss/train': 1.1335201263427734} 08/30/2021 22:48:20 - INFO - __main__ - Step 53160: {'lr': 0.0003665178936913123, 'samples': 10206720, 'steps': 53159, 'loss/train': 0.8323636651039124} 08/30/2021 22:48:21 - INFO - __main__ - Step 53161: {'lr': 0.0003665131985388215, 'samples': 10206912, 'steps': 53160, 'loss/train': 1.0658328533172607} 08/30/2021 22:48:21 - INFO - __main__ - Step 53162: {'lr': 0.00036650850333383174, 'samples': 10207104, 'steps': 53161, 'loss/train': 1.0367801189422607} 08/30/2021 22:48:21 - INFO - __main__ - Step 53163: {'lr': 0.000366503808076345, 'samples': 10207296, 'steps': 53162, 'loss/train': 1.3140429258346558} 08/30/2021 22:48:22 - INFO - __main__ - Step 53164: {'lr': 0.00036649911276636336, 'samples': 10207488, 'steps': 53163, 'loss/train': 1.3835654258728027} 08/30/2021 22:48:23 - INFO - __main__ - Step 53165: {'lr': 0.0003664944174038891, 'samples': 10207680, 'steps': 53164, 'loss/train': 2.0678176879882812} 08/30/2021 22:48:24 - INFO - __main__ - Step 53166: {'lr': 0.0003664897219889242, 'samples': 10207872, 'steps': 53165, 'loss/train': 1.299597978591919} 08/30/2021 22:48:24 - INFO - __main__ - Step 53167: {'lr': 0.0003664850265214709, 'samples': 10208064, 'steps': 53166, 'loss/train': 1.2662023305892944} 08/30/2021 22:48:24 - INFO - __main__ - Step 53168: {'lr': 0.00036648033100153117, 'samples': 10208256, 'steps': 53167, 'loss/train': 1.2045398950576782} 08/30/2021 22:48:25 - INFO - __main__ - Step 53169: {'lr': 0.0003664756354291073, 'samples': 10208448, 'steps': 53168, 'loss/train': 1.1443707942962646} 08/30/2021 22:48:26 - INFO - __main__ - Step 53170: {'lr': 0.0003664709398042012, 'samples': 10208640, 'steps': 53169, 'loss/train': 0.04853302612900734} 08/30/2021 22:48:27 - INFO - __main__ - Step 53171: {'lr': 0.00036646624412681514, 'samples': 10208832, 'steps': 53170, 'loss/train': 1.3704601526260376} 08/30/2021 22:48:27 - INFO - __main__ - Step 53172: {'lr': 0.0003664615483969511, 'samples': 10209024, 'steps': 53171, 'loss/train': 1.043784260749817} 08/30/2021 22:48:27 - INFO - __main__ - Step 53173: {'lr': 0.0003664568526146114, 'samples': 10209216, 'steps': 53172, 'loss/train': 1.3911161422729492} 08/30/2021 22:48:28 - INFO - __main__ - Step 53174: {'lr': 0.000366452156779798, 'samples': 10209408, 'steps': 53173, 'loss/train': 1.2773371934890747} 08/30/2021 22:48:29 - INFO - __main__ - Step 53175: {'lr': 0.000366447460892513, 'samples': 10209600, 'steps': 53174, 'loss/train': 1.1461070775985718} 08/30/2021 22:48:29 - INFO - __main__ - Step 53176: {'lr': 0.0003664427649527587, 'samples': 10209792, 'steps': 53175, 'loss/train': 1.1184347867965698} 08/30/2021 22:48:30 - INFO - __main__ - Step 53177: {'lr': 0.000366438068960537, 'samples': 10209984, 'steps': 53176, 'loss/train': 1.164221167564392} 08/30/2021 22:48:30 - INFO - __main__ - Step 53178: {'lr': 0.0003664333729158501, 'samples': 10210176, 'steps': 53177, 'loss/train': 1.2854918241500854} 08/30/2021 22:48:31 - INFO - __main__ - Step 53179: {'lr': 0.0003664286768187002, 'samples': 10210368, 'steps': 53178, 'loss/train': 1.6035661697387695} 08/30/2021 22:48:32 - INFO - __main__ - Step 53180: {'lr': 0.0003664239806690892, 'samples': 10210560, 'steps': 53179, 'loss/train': 0.7715705037117004} 08/30/2021 22:48:32 - INFO - __main__ - Step 53181: {'lr': 0.00036641928446701943, 'samples': 10210752, 'steps': 53180, 'loss/train': 1.0717874765396118} 08/30/2021 22:48:33 - INFO - __main__ - Step 53182: {'lr': 0.00036641458821249295, 'samples': 10210944, 'steps': 53181, 'loss/train': 1.0671672821044922} 08/30/2021 22:48:33 - INFO - __main__ - Step 53183: {'lr': 0.00036640989190551184, 'samples': 10211136, 'steps': 53182, 'loss/train': 1.3902512788772583} 08/30/2021 22:48:33 - INFO - __main__ - Step 53184: {'lr': 0.00036640519554607823, 'samples': 10211328, 'steps': 53183, 'loss/train': 1.3211222887039185} 08/30/2021 22:48:35 - INFO - __main__ - Step 53185: {'lr': 0.00036640049913419417, 'samples': 10211520, 'steps': 53184, 'loss/train': 1.404670238494873} 08/30/2021 22:48:35 - INFO - __main__ - Step 53186: {'lr': 0.00036639580266986183, 'samples': 10211712, 'steps': 53185, 'loss/train': 1.5652908086776733} 08/30/2021 22:48:36 - INFO - __main__ - Step 53187: {'lr': 0.00036639110615308343, 'samples': 10211904, 'steps': 53186, 'loss/train': 1.5481977462768555} 08/30/2021 22:48:36 - INFO - __main__ - Step 53188: {'lr': 0.0003663864095838609, 'samples': 10212096, 'steps': 53187, 'loss/train': 0.6847036480903625} 08/30/2021 22:48:36 - INFO - __main__ - Step 53189: {'lr': 0.0003663817129621966, 'samples': 10212288, 'steps': 53188, 'loss/train': 0.2752286493778229} 08/30/2021 22:48:38 - INFO - __main__ - Step 53190: {'lr': 0.0003663770162880924, 'samples': 10212480, 'steps': 53189, 'loss/train': 1.2976406812667847} 08/30/2021 22:48:39 - INFO - __main__ - Step 53191: {'lr': 0.00036637231956155046, 'samples': 10212672, 'steps': 53190, 'loss/train': 2.2436041831970215} 08/30/2021 22:48:39 - INFO - __main__ - Step 53192: {'lr': 0.000366367622782573, 'samples': 10212864, 'steps': 53191, 'loss/train': 1.1812256574630737} 08/30/2021 22:48:39 - INFO - __main__ - Step 53193: {'lr': 0.0003663629259511621, 'samples': 10213056, 'steps': 53192, 'loss/train': 1.5116875171661377} 08/30/2021 22:48:40 - INFO - __main__ - Step 53194: {'lr': 0.00036635822906731986, 'samples': 10213248, 'steps': 53193, 'loss/train': 1.1701563596725464} 08/30/2021 22:48:40 - INFO - __main__ - Step 53195: {'lr': 0.0003663535321310484, 'samples': 10213440, 'steps': 53194, 'loss/train': 1.5494961738586426} 08/30/2021 22:48:42 - INFO - __main__ - Step 53196: {'lr': 0.00036634883514234987, 'samples': 10213632, 'steps': 53195, 'loss/train': 1.2427462339401245} 08/30/2021 22:48:42 - INFO - __main__ - Step 53197: {'lr': 0.00036634413810122626, 'samples': 10213824, 'steps': 53196, 'loss/train': 1.6782783269882202} 08/30/2021 22:48:42 - INFO - __main__ - Step 53198: {'lr': 0.0003663394410076798, 'samples': 10214016, 'steps': 53197, 'loss/train': 1.3597197532653809} 08/30/2021 22:48:43 - INFO - __main__ - Step 53199: {'lr': 0.00036633474386171263, 'samples': 10214208, 'steps': 53198, 'loss/train': 0.4300593137741089} 08/30/2021 22:48:43 - INFO - __main__ - Step 53200: {'lr': 0.00036633004666332674, 'samples': 10214400, 'steps': 53199, 'loss/train': 1.6808253526687622} 08/30/2021 22:48:45 - INFO - __main__ - Step 53201: {'lr': 0.0003663253494125244, 'samples': 10214592, 'steps': 53200, 'loss/train': 1.1583746671676636} 08/30/2021 22:48:46 - INFO - __main__ - Step 53202: {'lr': 0.0003663206521093076, 'samples': 10214784, 'steps': 53201, 'loss/train': 2.1961965560913086} 08/30/2021 22:48:46 - INFO - __main__ - Step 53203: {'lr': 0.00036631595475367855, 'samples': 10214976, 'steps': 53202, 'loss/train': 1.0480351448059082} 08/30/2021 22:48:46 - INFO - __main__ - Step 53204: {'lr': 0.0003663112573456393, 'samples': 10215168, 'steps': 53203, 'loss/train': 1.6802586317062378} 08/30/2021 22:48:47 - INFO - __main__ - Step 53205: {'lr': 0.00036630655988519203, 'samples': 10215360, 'steps': 53204, 'loss/train': 1.7026524543762207} 08/30/2021 22:48:48 - INFO - __main__ - Step 53206: {'lr': 0.00036630186237233877, 'samples': 10215552, 'steps': 53205, 'loss/train': 1.1888130903244019} 08/30/2021 22:48:49 - INFO - __main__ - Step 53207: {'lr': 0.00036629716480708174, 'samples': 10215744, 'steps': 53206, 'loss/train': 1.4900892972946167} 08/30/2021 22:48:49 - INFO - __main__ - Step 53208: {'lr': 0.00036629246718942294, 'samples': 10215936, 'steps': 53207, 'loss/train': 0.8244256377220154} 08/30/2021 22:48:49 - INFO - __main__ - Step 53209: {'lr': 0.0003662877695193646, 'samples': 10216128, 'steps': 53208, 'loss/train': 1.4629201889038086} 08/30/2021 22:48:50 - INFO - __main__ - Step 53210: {'lr': 0.00036628307179690877, 'samples': 10216320, 'steps': 53209, 'loss/train': 0.2627696692943573} 08/30/2021 22:48:52 - INFO - __main__ - Step 53211: {'lr': 0.0003662783740220576, 'samples': 10216512, 'steps': 53210, 'loss/train': 1.0426281690597534} 08/30/2021 22:48:53 - INFO - __main__ - Step 53212: {'lr': 0.00036627367619481316, 'samples': 10216704, 'steps': 53211, 'loss/train': 1.1042983531951904} 08/30/2021 22:48:53 - INFO - __main__ - Step 53213: {'lr': 0.00036626897831517756, 'samples': 10216896, 'steps': 53212, 'loss/train': 1.2236188650131226} 08/30/2021 22:48:53 - INFO - __main__ - Step 53214: {'lr': 0.000366264280383153, 'samples': 10217088, 'steps': 53213, 'loss/train': 1.517566204071045} 08/30/2021 22:48:54 - INFO - __main__ - Step 53215: {'lr': 0.00036625958239874156, 'samples': 10217280, 'steps': 53214, 'loss/train': 0.4312618374824524} 08/30/2021 22:48:54 - INFO - __main__ - Step 53216: {'lr': 0.0003662548843619454, 'samples': 10217472, 'steps': 53215, 'loss/train': 0.4052829444408417} 08/30/2021 22:48:54 - INFO - __main__ - Step 53217: {'lr': 0.00036625018627276646, 'samples': 10217664, 'steps': 53216, 'loss/train': 1.099495768547058} 08/30/2021 22:48:56 - INFO - __main__ - Step 53218: {'lr': 0.0003662454881312071, 'samples': 10217856, 'steps': 53217, 'loss/train': 1.353546380996704} 08/30/2021 22:48:56 - INFO - __main__ - Step 53219: {'lr': 0.0003662407899372692, 'samples': 10218048, 'steps': 53218, 'loss/train': 1.8712952136993408} 08/30/2021 22:48:56 - INFO - __main__ - Step 53220: {'lr': 0.000366236091690955, 'samples': 10218240, 'steps': 53219, 'loss/train': 1.2671988010406494} 08/30/2021 22:48:57 - INFO - __main__ - Step 53221: {'lr': 0.00036623139339226664, 'samples': 10218432, 'steps': 53220, 'loss/train': 1.942024827003479} 08/30/2021 22:48:57 - INFO - __main__ - Step 53222: {'lr': 0.00036622669504120627, 'samples': 10218624, 'steps': 53221, 'loss/train': 1.6858413219451904} 08/30/2021 22:48:59 - INFO - __main__ - Step 53223: {'lr': 0.0003662219966377759, 'samples': 10218816, 'steps': 53222, 'loss/train': 1.6491044759750366} 08/30/2021 22:48:59 - INFO - __main__ - Step 53224: {'lr': 0.0003662172981819777, 'samples': 10219008, 'steps': 53223, 'loss/train': 1.4158514738082886} 08/30/2021 22:49:00 - INFO - __main__ - Step 53225: {'lr': 0.00036621259967381374, 'samples': 10219200, 'steps': 53224, 'loss/train': 0.0857100561261177} 08/30/2021 22:49:00 - INFO - __main__ - Step 53226: {'lr': 0.0003662079011132862, 'samples': 10219392, 'steps': 53225, 'loss/train': 2.865140199661255} 08/30/2021 22:49:00 - INFO - __main__ - Step 53227: {'lr': 0.0003662032025003972, 'samples': 10219584, 'steps': 53226, 'loss/train': 1.760138750076294} 08/30/2021 22:49:02 - INFO - __main__ - Step 53228: {'lr': 0.0003661985038351488, 'samples': 10219776, 'steps': 53227, 'loss/train': 1.2502361536026} 08/30/2021 22:49:02 - INFO - __main__ - Step 53229: {'lr': 0.0003661938051175432, 'samples': 10219968, 'steps': 53228, 'loss/train': 0.8863047957420349} 08/30/2021 22:49:03 - INFO - __main__ - Step 53230: {'lr': 0.0003661891063475824, 'samples': 10220160, 'steps': 53229, 'loss/train': 1.418977975845337} 08/30/2021 22:49:03 - INFO - __main__ - Step 53231: {'lr': 0.0003661844075252686, 'samples': 10220352, 'steps': 53230, 'loss/train': 1.4624571800231934} 08/30/2021 22:49:03 - INFO - __main__ - Step 53232: {'lr': 0.0003661797086506039, 'samples': 10220544, 'steps': 53231, 'loss/train': 1.3781826496124268} 08/30/2021 22:49:05 - INFO - __main__ - Step 53233: {'lr': 0.0003661750097235904, 'samples': 10220736, 'steps': 53232, 'loss/train': 1.2332086563110352} 08/30/2021 22:49:06 - INFO - __main__ - Step 53234: {'lr': 0.00036617031074423023, 'samples': 10220928, 'steps': 53233, 'loss/train': 1.2848411798477173} 08/30/2021 22:49:06 - INFO - __main__ - Step 53235: {'lr': 0.00036616561171252547, 'samples': 10221120, 'steps': 53234, 'loss/train': 1.5117601156234741} 08/30/2021 22:49:06 - INFO - __main__ - Step 53236: {'lr': 0.0003661609126284784, 'samples': 10221312, 'steps': 53235, 'loss/train': 1.5077972412109375} 08/30/2021 22:49:07 - INFO - __main__ - Step 53237: {'lr': 0.00036615621349209094, 'samples': 10221504, 'steps': 53236, 'loss/train': 0.6492274403572083} 08/30/2021 22:49:07 - INFO - __main__ - Step 53238: {'lr': 0.00036615151430336536, 'samples': 10221696, 'steps': 53237, 'loss/train': 1.3716254234313965} 08/30/2021 22:49:08 - INFO - __main__ - Step 53239: {'lr': 0.0003661468150623036, 'samples': 10221888, 'steps': 53238, 'loss/train': 1.6493276357650757} 08/30/2021 22:49:09 - INFO - __main__ - Step 53240: {'lr': 0.0003661421157689079, 'samples': 10222080, 'steps': 53239, 'loss/train': 0.5903933048248291} 08/30/2021 22:49:09 - INFO - __main__ - Step 53241: {'lr': 0.00036613741642318033, 'samples': 10222272, 'steps': 53240, 'loss/train': 0.7079034447669983} 08/30/2021 22:49:10 - INFO - __main__ - Step 53242: {'lr': 0.00036613271702512306, 'samples': 10222464, 'steps': 53241, 'loss/train': 1.8750361204147339} 08/30/2021 22:49:10 - INFO - __main__ - Step 53243: {'lr': 0.00036612801757473823, 'samples': 10222656, 'steps': 53242, 'loss/train': 1.4853777885437012} 08/30/2021 22:49:11 - INFO - __main__ - Step 53244: {'lr': 0.00036612331807202785, 'samples': 10222848, 'steps': 53243, 'loss/train': 1.665930986404419} 08/30/2021 22:49:12 - INFO - __main__ - Step 53245: {'lr': 0.00036611861851699415, 'samples': 10223040, 'steps': 53244, 'loss/train': 1.3020669221878052} 08/30/2021 22:49:12 - INFO - __main__ - Step 53246: {'lr': 0.00036611391890963913, 'samples': 10223232, 'steps': 53245, 'loss/train': 1.5422465801239014} 08/30/2021 22:49:13 - INFO - __main__ - Step 53247: {'lr': 0.000366109219249965, 'samples': 10223424, 'steps': 53246, 'loss/train': 1.1618731021881104} 08/30/2021 22:49:13 - INFO - __main__ - Step 53248: {'lr': 0.00036610451953797386, 'samples': 10223616, 'steps': 53247, 'loss/train': 1.1686583757400513} 08/30/2021 22:49:14 - INFO - __main__ - Step 53249: {'lr': 0.0003660998197736677, 'samples': 10223808, 'steps': 53248, 'loss/train': 1.0477544069290161} 08/30/2021 22:49:15 - INFO - __main__ - Step 53250: {'lr': 0.00036609511995704894, 'samples': 10224000, 'steps': 53249, 'loss/train': 0.7289081811904907} 08/30/2021 22:49:15 - INFO - __main__ - Step 53251: {'lr': 0.0003660904200881194, 'samples': 10224192, 'steps': 53250, 'loss/train': 1.335196852684021} 08/30/2021 22:49:16 - INFO - __main__ - Step 53252: {'lr': 0.00036608572016688136, 'samples': 10224384, 'steps': 53251, 'loss/train': 1.3050537109375} 08/30/2021 22:49:16 - INFO - __main__ - Step 53253: {'lr': 0.00036608102019333684, 'samples': 10224576, 'steps': 53252, 'loss/train': 1.310990571975708} 08/30/2021 22:49:18 - INFO - __main__ - Step 53254: {'lr': 0.00036607632016748796, 'samples': 10224768, 'steps': 53253, 'loss/train': 1.2805341482162476} 08/30/2021 22:49:19 - INFO - __main__ - Step 53255: {'lr': 0.00036607162008933696, 'samples': 10224960, 'steps': 53254, 'loss/train': 1.602102518081665} 08/30/2021 22:49:19 - INFO - __main__ - Step 53256: {'lr': 0.00036606691995888594, 'samples': 10225152, 'steps': 53255, 'loss/train': 1.5757710933685303} 08/30/2021 22:49:19 - INFO - __main__ - Step 53257: {'lr': 0.00036606221977613686, 'samples': 10225344, 'steps': 53256, 'loss/train': 0.6729387640953064} 08/30/2021 22:49:20 - INFO - __main__ - Step 53258: {'lr': 0.0003660575195410919, 'samples': 10225536, 'steps': 53257, 'loss/train': 1.706623911857605} 08/30/2021 22:49:20 - INFO - __main__ - Step 53259: {'lr': 0.0003660528192537533, 'samples': 10225728, 'steps': 53258, 'loss/train': 1.0621718168258667} 08/30/2021 22:49:21 - INFO - __main__ - Step 53260: {'lr': 0.00036604811891412296, 'samples': 10225920, 'steps': 53259, 'loss/train': 1.0937594175338745} 08/30/2021 22:49:22 - INFO - __main__ - Step 53261: {'lr': 0.00036604341852220325, 'samples': 10226112, 'steps': 53260, 'loss/train': 1.6766093969345093} 08/30/2021 22:49:22 - INFO - __main__ - Step 53262: {'lr': 0.00036603871807799616, 'samples': 10226304, 'steps': 53261, 'loss/train': 0.7190766930580139} 08/30/2021 22:49:23 - INFO - __main__ - Step 53263: {'lr': 0.0003660340175815038, 'samples': 10226496, 'steps': 53262, 'loss/train': 1.536271095275879} 08/30/2021 22:49:23 - INFO - __main__ - Step 53264: {'lr': 0.0003660293170327283, 'samples': 10226688, 'steps': 53263, 'loss/train': 0.6218279600143433} 08/30/2021 22:49:24 - INFO - __main__ - Step 53265: {'lr': 0.0003660246164316717, 'samples': 10226880, 'steps': 53264, 'loss/train': 1.1906983852386475} 08/30/2021 22:49:25 - INFO - __main__ - Step 53266: {'lr': 0.00036601991577833634, 'samples': 10227072, 'steps': 53265, 'loss/train': 1.0640814304351807} 08/30/2021 22:49:25 - INFO - __main__ - Step 53267: {'lr': 0.00036601521507272414, 'samples': 10227264, 'steps': 53266, 'loss/train': 0.5387945175170898} 08/30/2021 22:49:26 - INFO - __main__ - Step 53268: {'lr': 0.00036601051431483725, 'samples': 10227456, 'steps': 53267, 'loss/train': 1.8342547416687012} 08/30/2021 22:49:26 - INFO - __main__ - Step 53269: {'lr': 0.0003660058135046778, 'samples': 10227648, 'steps': 53268, 'loss/train': 1.051466941833496} 08/30/2021 22:49:27 - INFO - __main__ - Step 53270: {'lr': 0.000366001112642248, 'samples': 10227840, 'steps': 53269, 'loss/train': 0.9883494973182678} 08/30/2021 22:49:28 - INFO - __main__ - Step 53271: {'lr': 0.00036599641172754984, 'samples': 10228032, 'steps': 53270, 'loss/train': 1.3072794675827026} 08/30/2021 22:49:28 - INFO - __main__ - Step 53272: {'lr': 0.0003659917107605854, 'samples': 10228224, 'steps': 53271, 'loss/train': 1.2601321935653687} 08/30/2021 22:49:29 - INFO - __main__ - Step 53273: {'lr': 0.000365987009741357, 'samples': 10228416, 'steps': 53272, 'loss/train': 1.71773099899292} 08/30/2021 22:49:29 - INFO - __main__ - Step 53274: {'lr': 0.0003659823086698666, 'samples': 10228608, 'steps': 53273, 'loss/train': 1.490798830986023} 08/30/2021 22:49:30 - INFO - __main__ - Step 53275: {'lr': 0.0003659776075461164, 'samples': 10228800, 'steps': 53274, 'loss/train': 1.0880540609359741} 08/30/2021 22:49:31 - INFO - __main__ - Step 53276: {'lr': 0.0003659729063701084, 'samples': 10228992, 'steps': 53275, 'loss/train': 1.42315673828125} 08/30/2021 22:49:31 - INFO - __main__ - Step 53277: {'lr': 0.00036596820514184485, 'samples': 10229184, 'steps': 53276, 'loss/train': 1.5079480409622192} 08/30/2021 22:49:32 - INFO - __main__ - Step 53278: {'lr': 0.00036596350386132784, 'samples': 10229376, 'steps': 53277, 'loss/train': 1.35906183719635} 08/30/2021 22:49:32 - INFO - __main__ - Step 53279: {'lr': 0.0003659588025285594, 'samples': 10229568, 'steps': 53278, 'loss/train': 1.203540325164795} 08/30/2021 22:49:33 - INFO - __main__ - Step 53280: {'lr': 0.0003659541011435418, 'samples': 10229760, 'steps': 53279, 'loss/train': 0.21066060662269592} 08/30/2021 22:49:34 - INFO - __main__ - Step 53281: {'lr': 0.00036594939970627704, 'samples': 10229952, 'steps': 53280, 'loss/train': 0.9715648889541626} 08/30/2021 22:49:34 - INFO - __main__ - Step 53282: {'lr': 0.0003659446982167672, 'samples': 10230144, 'steps': 53281, 'loss/train': 0.45380842685699463} 08/30/2021 22:49:35 - INFO - __main__ - Step 53283: {'lr': 0.00036593999667501457, 'samples': 10230336, 'steps': 53282, 'loss/train': 1.51667320728302} 08/30/2021 22:49:35 - INFO - __main__ - Step 53284: {'lr': 0.0003659352950810211, 'samples': 10230528, 'steps': 53283, 'loss/train': 1.5380358695983887} 08/30/2021 22:49:36 - INFO - __main__ - Step 53285: {'lr': 0.00036593059343478904, 'samples': 10230720, 'steps': 53284, 'loss/train': 1.4115374088287354} 08/30/2021 22:49:37 - INFO - __main__ - Step 53286: {'lr': 0.0003659258917363204, 'samples': 10230912, 'steps': 53285, 'loss/train': 1.128061056137085} 08/30/2021 22:49:37 - INFO - __main__ - Step 53287: {'lr': 0.0003659211899856173, 'samples': 10231104, 'steps': 53286, 'loss/train': 1.0784072875976562} 08/30/2021 22:49:37 - INFO - __main__ - Step 53288: {'lr': 0.0003659164881826819, 'samples': 10231296, 'steps': 53287, 'loss/train': 1.7698003053665161} 08/30/2021 22:49:38 - INFO - __main__ - Step 53289: {'lr': 0.00036591178632751635, 'samples': 10231488, 'steps': 53288, 'loss/train': 1.0029443502426147} 08/30/2021 22:49:40 - INFO - __main__ - Step 53290: {'lr': 0.00036590708442012275, 'samples': 10231680, 'steps': 53289, 'loss/train': 1.8331496715545654} 08/30/2021 22:49:40 - INFO - __main__ - Step 53291: {'lr': 0.0003659023824605033, 'samples': 10231872, 'steps': 53290, 'loss/train': 1.4333231449127197} 08/30/2021 22:49:41 - INFO - __main__ - Step 53292: {'lr': 0.0003658976804486599, 'samples': 10232064, 'steps': 53291, 'loss/train': 0.10715776681900024} 08/30/2021 22:49:41 - INFO - __main__ - Step 53293: {'lr': 0.0003658929783845948, 'samples': 10232256, 'steps': 53292, 'loss/train': 1.3528579473495483} 08/30/2021 22:49:41 - INFO - __main__ - Step 53294: {'lr': 0.0003658882762683101, 'samples': 10232448, 'steps': 53293, 'loss/train': 2.088239908218384} 08/30/2021 22:49:43 - INFO - __main__ - Step 53295: {'lr': 0.000365883574099808, 'samples': 10232640, 'steps': 53294, 'loss/train': 1.1306835412979126} 08/30/2021 22:49:43 - INFO - __main__ - Step 53296: {'lr': 0.00036587887187909045, 'samples': 10232832, 'steps': 53295, 'loss/train': 1.503839135169983} 08/30/2021 22:49:44 - INFO - __main__ - Step 53297: {'lr': 0.0003658741696061598, 'samples': 10233024, 'steps': 53296, 'loss/train': 1.6324217319488525} 08/30/2021 22:49:44 - INFO - __main__ - Step 53298: {'lr': 0.0003658694672810179, 'samples': 10233216, 'steps': 53297, 'loss/train': 1.487068772315979} 08/30/2021 22:49:44 - INFO - __main__ - Step 53299: {'lr': 0.00036586476490366713, 'samples': 10233408, 'steps': 53298, 'loss/train': 1.649052619934082} 08/30/2021 22:49:46 - INFO - __main__ - Step 53300: {'lr': 0.0003658600624741094, 'samples': 10233600, 'steps': 53299, 'loss/train': 0.8337749242782593} 08/30/2021 22:49:47 - INFO - __main__ - Step 53301: {'lr': 0.00036585535999234697, 'samples': 10233792, 'steps': 53300, 'loss/train': 1.2434320449829102} 08/30/2021 22:49:47 - INFO - __main__ - Step 53302: {'lr': 0.0003658506574583819, 'samples': 10233984, 'steps': 53301, 'loss/train': 1.61161208152771} 08/30/2021 22:49:47 - INFO - __main__ - Step 53303: {'lr': 0.0003658459548722163, 'samples': 10234176, 'steps': 53302, 'loss/train': 0.10066486150026321} 08/30/2021 22:49:48 - INFO - __main__ - Step 53304: {'lr': 0.00036584125223385224, 'samples': 10234368, 'steps': 53303, 'loss/train': 1.3928028345108032} 08/30/2021 22:49:49 - INFO - __main__ - Step 53305: {'lr': 0.0003658365495432919, 'samples': 10234560, 'steps': 53304, 'loss/train': 0.902204692363739} 08/30/2021 22:49:50 - INFO - __main__ - Step 53306: {'lr': 0.0003658318468005375, 'samples': 10234752, 'steps': 53305, 'loss/train': 1.4073790311813354} 08/30/2021 22:49:50 - INFO - __main__ - Step 53307: {'lr': 0.000365827144005591, 'samples': 10234944, 'steps': 53306, 'loss/train': 0.7341249585151672} 08/30/2021 22:49:50 - INFO - __main__ - Step 53308: {'lr': 0.0003658224411584545, 'samples': 10235136, 'steps': 53307, 'loss/train': 1.2515068054199219} 08/30/2021 22:49:51 - INFO - __main__ - Step 53309: {'lr': 0.0003658177382591303, 'samples': 10235328, 'steps': 53308, 'loss/train': 1.8078511953353882} 08/30/2021 22:49:51 - INFO - __main__ - Step 53310: {'lr': 0.0003658130353076204, 'samples': 10235520, 'steps': 53309, 'loss/train': 1.35354745388031} 08/30/2021 22:49:53 - INFO - __main__ - Step 53311: {'lr': 0.00036580833230392696, 'samples': 10235712, 'steps': 53310, 'loss/train': 1.947704792022705} 08/30/2021 22:49:54 - INFO - __main__ - Step 53312: {'lr': 0.00036580362924805204, 'samples': 10235904, 'steps': 53311, 'loss/train': 1.1198803186416626} 08/30/2021 22:49:54 - INFO - __main__ - Step 53313: {'lr': 0.0003657989261399978, 'samples': 10236096, 'steps': 53312, 'loss/train': 1.2369558811187744} 08/30/2021 22:49:54 - INFO - __main__ - Step 53314: {'lr': 0.0003657942229797663, 'samples': 10236288, 'steps': 53313, 'loss/train': 1.7686184644699097} 08/30/2021 22:49:55 - INFO - __main__ - Step 53315: {'lr': 0.00036578951976735973, 'samples': 10236480, 'steps': 53314, 'loss/train': 1.7382127046585083} 08/30/2021 22:49:57 - INFO - __main__ - Step 53316: {'lr': 0.00036578481650278023, 'samples': 10236672, 'steps': 53315, 'loss/train': 1.2438435554504395} 08/30/2021 22:49:57 - INFO - __main__ - Step 53317: {'lr': 0.0003657801131860299, 'samples': 10236864, 'steps': 53316, 'loss/train': 1.2964054346084595} 08/30/2021 22:49:57 - INFO - __main__ - Step 53318: {'lr': 0.0003657754098171108, 'samples': 10237056, 'steps': 53317, 'loss/train': 0.5095234513282776} 08/30/2021 22:49:58 - INFO - __main__ - Step 53319: {'lr': 0.0003657707063960251, 'samples': 10237248, 'steps': 53318, 'loss/train': 0.06290942430496216} 08/30/2021 22:49:58 - INFO - __main__ - Step 53320: {'lr': 0.00036576600292277477, 'samples': 10237440, 'steps': 53319, 'loss/train': 1.496840238571167} 08/30/2021 22:50:00 - INFO - __main__ - Step 53321: {'lr': 0.0003657612993973622, 'samples': 10237632, 'steps': 53320, 'loss/train': 0.04907238483428955} 08/30/2021 22:50:01 - INFO - __main__ - Step 53322: {'lr': 0.00036575659581978935, 'samples': 10237824, 'steps': 53321, 'loss/train': 1.3841993808746338} 08/30/2021 22:50:01 - INFO - __main__ - Step 53323: {'lr': 0.0003657518921900583, 'samples': 10238016, 'steps': 53322, 'loss/train': 1.1822389364242554} 08/30/2021 22:50:01 - INFO - __main__ - Step 53324: {'lr': 0.0003657471885081714, 'samples': 10238208, 'steps': 53323, 'loss/train': 1.4025685787200928} 08/30/2021 22:50:02 - INFO - __main__ - Step 53325: {'lr': 0.0003657424847741305, 'samples': 10238400, 'steps': 53324, 'loss/train': 0.6211552023887634} 08/30/2021 22:50:03 - INFO - __main__ - Step 53326: {'lr': 0.0003657377809879378, 'samples': 10238592, 'steps': 53325, 'loss/train': 0.05562727153301239} 08/30/2021 22:50:03 - INFO - __main__ - Step 53327: {'lr': 0.0003657330771495955, 'samples': 10238784, 'steps': 53326, 'loss/train': 1.2233649492263794} 08/30/2021 22:50:04 - INFO - __main__ - Step 53328: {'lr': 0.0003657283732591056, 'samples': 10238976, 'steps': 53327, 'loss/train': 0.9608726501464844} 08/30/2021 22:50:04 - INFO - __main__ - Step 53329: {'lr': 0.00036572366931647034, 'samples': 10239168, 'steps': 53328, 'loss/train': 1.360880732536316} 08/30/2021 22:50:05 - INFO - __main__ - Step 53330: {'lr': 0.0003657189653216918, 'samples': 10239360, 'steps': 53329, 'loss/train': 1.8871315717697144} 08/30/2021 22:50:05 - INFO - __main__ - Step 53331: {'lr': 0.000365714261274772, 'samples': 10239552, 'steps': 53330, 'loss/train': 0.4087035059928894} 08/30/2021 22:50:06 - INFO - __main__ - Step 53332: {'lr': 0.00036570955717571315, 'samples': 10239744, 'steps': 53331, 'loss/train': 1.1405770778656006} 08/30/2021 22:50:07 - INFO - __main__ - Step 53333: {'lr': 0.0003657048530245174, 'samples': 10239936, 'steps': 53332, 'loss/train': 1.3580645322799683} 08/30/2021 22:50:07 - INFO - __main__ - Step 53334: {'lr': 0.0003657001488211868, 'samples': 10240128, 'steps': 53333, 'loss/train': 1.4621342420578003} 08/30/2021 22:50:08 - INFO - __main__ - Step 53335: {'lr': 0.00036569544456572346, 'samples': 10240320, 'steps': 53334, 'loss/train': 1.2501530647277832} 08/30/2021 22:50:08 - INFO - __main__ - Step 53336: {'lr': 0.0003656907402581296, 'samples': 10240512, 'steps': 53335, 'loss/train': 1.380635142326355} 08/30/2021 22:50:09 - INFO - __main__ - Step 53337: {'lr': 0.00036568603589840734, 'samples': 10240704, 'steps': 53336, 'loss/train': 1.2424951791763306} 08/30/2021 22:50:10 - INFO - __main__ - Step 53338: {'lr': 0.00036568133148655855, 'samples': 10240896, 'steps': 53337, 'loss/train': 0.7611114382743835} 08/30/2021 22:50:10 - INFO - __main__ - Step 53339: {'lr': 0.0003656766270225857, 'samples': 10241088, 'steps': 53338, 'loss/train': 1.4231979846954346} 08/30/2021 22:50:11 - INFO - __main__ - Step 53340: {'lr': 0.00036567192250649066, 'samples': 10241280, 'steps': 53339, 'loss/train': 1.501531720161438} 08/30/2021 22:50:11 - INFO - __main__ - Step 53341: {'lr': 0.0003656672179382757, 'samples': 10241472, 'steps': 53340, 'loss/train': 1.5909029245376587} 08/30/2021 22:50:12 - INFO - __main__ - Step 53342: {'lr': 0.00036566251331794284, 'samples': 10241664, 'steps': 53341, 'loss/train': 1.3575444221496582} 08/30/2021 22:50:13 - INFO - __main__ - Step 53343: {'lr': 0.00036565780864549423, 'samples': 10241856, 'steps': 53342, 'loss/train': 0.8783314824104309} 08/30/2021 22:50:13 - INFO - __main__ - Step 53344: {'lr': 0.00036565310392093204, 'samples': 10242048, 'steps': 53343, 'loss/train': 0.6195229291915894} 08/30/2021 22:50:14 - INFO - __main__ - Step 53345: {'lr': 0.0003656483991442583, 'samples': 10242240, 'steps': 53344, 'loss/train': 0.7540102005004883} 08/30/2021 22:50:14 - INFO - __main__ - Step 53346: {'lr': 0.0003656436943154752, 'samples': 10242432, 'steps': 53345, 'loss/train': 1.4529738426208496} 08/30/2021 22:50:16 - INFO - __main__ - Step 53347: {'lr': 0.0003656389894345848, 'samples': 10242624, 'steps': 53346, 'loss/train': 1.165108323097229} 08/30/2021 22:50:16 - INFO - __main__ - Step 53348: {'lr': 0.0003656342845015893, 'samples': 10242816, 'steps': 53347, 'loss/train': 0.38638120889663696} 08/30/2021 22:50:17 - INFO - __main__ - Step 53349: {'lr': 0.00036562957951649075, 'samples': 10243008, 'steps': 53348, 'loss/train': 2.063819169998169} 08/30/2021 22:50:17 - INFO - __main__ - Step 53350: {'lr': 0.00036562487447929133, 'samples': 10243200, 'steps': 53349, 'loss/train': 1.6993876695632935} 08/30/2021 22:50:17 - INFO - __main__ - Step 53351: {'lr': 0.0003656201693899931, 'samples': 10243392, 'steps': 53350, 'loss/train': 1.561079978942871} 08/30/2021 22:50:18 - INFO - __main__ - Step 53352: {'lr': 0.0003656154642485982, 'samples': 10243584, 'steps': 53351, 'loss/train': 1.5431150197982788} 08/30/2021 22:50:19 - INFO - __main__ - Step 53353: {'lr': 0.00036561075905510874, 'samples': 10243776, 'steps': 53352, 'loss/train': 1.9697879552841187} 08/30/2021 22:50:20 - INFO - __main__ - Step 53354: {'lr': 0.00036560605380952686, 'samples': 10243968, 'steps': 53353, 'loss/train': 1.225656270980835} 08/30/2021 22:50:20 - INFO - __main__ - Step 53355: {'lr': 0.00036560134851185475, 'samples': 10244160, 'steps': 53354, 'loss/train': 1.7060719728469849} 08/30/2021 22:50:20 - INFO - __main__ - Step 53356: {'lr': 0.00036559664316209437, 'samples': 10244352, 'steps': 53355, 'loss/train': 2.1476950645446777} 08/30/2021 22:50:21 - INFO - __main__ - Step 53357: {'lr': 0.00036559193776024794, 'samples': 10244544, 'steps': 53356, 'loss/train': 1.9014744758605957} 08/30/2021 22:50:22 - INFO - __main__ - Step 53358: {'lr': 0.00036558723230631764, 'samples': 10244736, 'steps': 53357, 'loss/train': 1.180708885192871} 08/30/2021 22:50:23 - INFO - __main__ - Step 53359: {'lr': 0.00036558252680030546, 'samples': 10244928, 'steps': 53358, 'loss/train': 1.5608084201812744} 08/30/2021 22:50:23 - INFO - __main__ - Step 53360: {'lr': 0.0003655778212422135, 'samples': 10245120, 'steps': 53359, 'loss/train': 1.2837883234024048} 08/30/2021 22:50:23 - INFO - __main__ - Step 53361: {'lr': 0.0003655731156320441, 'samples': 10245312, 'steps': 53360, 'loss/train': 1.1438615322113037} 08/30/2021 22:50:24 - INFO - __main__ - Step 53362: {'lr': 0.00036556840996979914, 'samples': 10245504, 'steps': 53361, 'loss/train': 0.6098493337631226} 08/30/2021 22:50:26 - INFO - __main__ - Step 53363: {'lr': 0.0003655637042554809, 'samples': 10245696, 'steps': 53362, 'loss/train': 1.3798049688339233} 08/30/2021 22:50:26 - INFO - __main__ - Step 53364: {'lr': 0.0003655589984890914, 'samples': 10245888, 'steps': 53363, 'loss/train': 0.43864381313323975} 08/30/2021 22:50:26 - INFO - __main__ - Step 53365: {'lr': 0.00036555429267063277, 'samples': 10246080, 'steps': 53364, 'loss/train': 1.6588486433029175} 08/30/2021 22:50:27 - INFO - __main__ - Step 53366: {'lr': 0.0003655495868001072, 'samples': 10246272, 'steps': 53365, 'loss/train': 0.6482540965080261} 08/30/2021 22:50:27 - INFO - __main__ - Step 53367: {'lr': 0.00036554488087751674, 'samples': 10246464, 'steps': 53366, 'loss/train': 1.4537341594696045} 08/30/2021 22:50:29 - INFO - __main__ - Step 53368: {'lr': 0.00036554017490286354, 'samples': 10246656, 'steps': 53367, 'loss/train': 0.735163688659668} 08/30/2021 22:50:29 - INFO - __main__ - Step 53369: {'lr': 0.0003655354688761498, 'samples': 10246848, 'steps': 53368, 'loss/train': 1.0079963207244873} 08/30/2021 22:50:29 - INFO - __main__ - Step 53370: {'lr': 0.00036553076279737743, 'samples': 10247040, 'steps': 53369, 'loss/train': 2.027679204940796} 08/30/2021 22:50:30 - INFO - __main__ - Step 53371: {'lr': 0.0003655260566665488, 'samples': 10247232, 'steps': 53370, 'loss/train': 1.3684278726577759} 08/30/2021 22:50:30 - INFO - __main__ - Step 53372: {'lr': 0.0003655213504836659, 'samples': 10247424, 'steps': 53371, 'loss/train': 0.054646577686071396} 08/30/2021 22:50:32 - INFO - __main__ - Step 53373: {'lr': 0.00036551664424873084, 'samples': 10247616, 'steps': 53372, 'loss/train': 0.9775164723396301} 08/30/2021 22:50:32 - INFO - __main__ - Step 53374: {'lr': 0.00036551193796174577, 'samples': 10247808, 'steps': 53373, 'loss/train': 0.478732705116272} 08/30/2021 22:50:32 - INFO - __main__ - Step 53375: {'lr': 0.0003655072316227127, 'samples': 10248000, 'steps': 53374, 'loss/train': 1.375588059425354} 08/30/2021 22:50:33 - INFO - __main__ - Step 53376: {'lr': 0.000365502525231634, 'samples': 10248192, 'steps': 53375, 'loss/train': 1.2375893592834473} 08/30/2021 22:50:33 - INFO - __main__ - Step 53377: {'lr': 0.00036549781878851155, 'samples': 10248384, 'steps': 53376, 'loss/train': 1.5337711572647095} 08/30/2021 22:50:36 - INFO - __main__ - Step 53378: {'lr': 0.0003654931122933476, 'samples': 10248576, 'steps': 53377, 'loss/train': 0.7631622552871704} 08/30/2021 22:50:36 - INFO - __main__ - Step 53379: {'lr': 0.0003654884057461443, 'samples': 10248768, 'steps': 53378, 'loss/train': 0.9616112112998962} 08/30/2021 22:50:36 - INFO - __main__ - Step 53380: {'lr': 0.0003654836991469036, 'samples': 10248960, 'steps': 53379, 'loss/train': 1.5635032653808594} 08/30/2021 22:50:37 - INFO - __main__ - Step 53381: {'lr': 0.00036547899249562776, 'samples': 10249152, 'steps': 53380, 'loss/train': 1.335044503211975} 08/30/2021 22:50:37 - INFO - __main__ - Step 53382: {'lr': 0.00036547428579231886, 'samples': 10249344, 'steps': 53381, 'loss/train': 0.7292966246604919} 08/30/2021 22:50:38 - INFO - __main__ - Step 53383: {'lr': 0.000365469579036979, 'samples': 10249536, 'steps': 53382, 'loss/train': 0.7539511919021606} 08/30/2021 22:50:38 - INFO - __main__ - Step 53384: {'lr': 0.00036546487222961045, 'samples': 10249728, 'steps': 53383, 'loss/train': 0.9448441863059998} 08/30/2021 22:50:39 - INFO - __main__ - Step 53385: {'lr': 0.0003654601653702151, 'samples': 10249920, 'steps': 53384, 'loss/train': 1.141711711883545} 08/30/2021 22:50:40 - INFO - __main__ - Step 53386: {'lr': 0.0003654554584587952, 'samples': 10250112, 'steps': 53385, 'loss/train': 0.6322513222694397} 08/30/2021 22:50:40 - INFO - __main__ - Step 53387: {'lr': 0.0003654507514953529, 'samples': 10250304, 'steps': 53386, 'loss/train': 1.5990222692489624} 08/30/2021 22:50:41 - INFO - __main__ - Step 53388: {'lr': 0.0003654460444798902, 'samples': 10250496, 'steps': 53387, 'loss/train': 1.595096468925476} 08/30/2021 22:50:41 - INFO - __main__ - Step 53389: {'lr': 0.00036544133741240936, 'samples': 10250688, 'steps': 53388, 'loss/train': 1.534311294555664} 08/30/2021 22:50:42 - INFO - __main__ - Step 53390: {'lr': 0.0003654366302929124, 'samples': 10250880, 'steps': 53389, 'loss/train': 1.4573383331298828} 08/30/2021 22:50:43 - INFO - __main__ - Step 53391: {'lr': 0.0003654319231214015, 'samples': 10251072, 'steps': 53390, 'loss/train': 1.0705103874206543} 08/30/2021 22:50:43 - INFO - __main__ - Step 53392: {'lr': 0.00036542721589787877, 'samples': 10251264, 'steps': 53391, 'loss/train': 1.228500485420227} 08/30/2021 22:50:44 - INFO - __main__ - Step 53393: {'lr': 0.0003654225086223463, 'samples': 10251456, 'steps': 53392, 'loss/train': 1.6676151752471924} 08/30/2021 22:50:44 - INFO - __main__ - Step 53394: {'lr': 0.00036541780129480616, 'samples': 10251648, 'steps': 53393, 'loss/train': 1.5204026699066162} 08/30/2021 22:50:44 - INFO - __main__ - Step 53395: {'lr': 0.00036541309391526064, 'samples': 10251840, 'steps': 53394, 'loss/train': 0.040608614683151245} 08/30/2021 22:50:46 - INFO - __main__ - Step 53396: {'lr': 0.0003654083864837117, 'samples': 10252032, 'steps': 53395, 'loss/train': 0.45272374153137207} 08/30/2021 22:50:46 - INFO - __main__ - Step 53397: {'lr': 0.0003654036790001616, 'samples': 10252224, 'steps': 53396, 'loss/train': 1.3975297212600708} 08/30/2021 22:50:46 - INFO - __main__ - Step 53398: {'lr': 0.00036539897146461227, 'samples': 10252416, 'steps': 53397, 'loss/train': 0.8202672600746155} 08/30/2021 22:50:47 - INFO - __main__ - Step 53399: {'lr': 0.000365394263877066, 'samples': 10252608, 'steps': 53398, 'loss/train': 1.1654084920883179} 08/30/2021 22:50:47 - INFO - __main__ - Step 53400: {'lr': 0.0003653895562375248, 'samples': 10252800, 'steps': 53399, 'loss/train': 1.170444369316101} 08/30/2021 22:50:49 - INFO - __main__ - Step 53401: {'lr': 0.0003653848485459909, 'samples': 10252992, 'steps': 53400, 'loss/train': 1.4426257610321045} 08/30/2021 22:50:49 - INFO - __main__ - Step 53402: {'lr': 0.0003653801408024664, 'samples': 10253184, 'steps': 53401, 'loss/train': 1.434010624885559} 08/30/2021 22:50:49 - INFO - __main__ - Step 53403: {'lr': 0.00036537543300695335, 'samples': 10253376, 'steps': 53402, 'loss/train': 1.500929355621338} 08/30/2021 22:50:50 - INFO - __main__ - Step 53404: {'lr': 0.0003653707251594539, 'samples': 10253568, 'steps': 53403, 'loss/train': 1.3784416913986206} 08/30/2021 22:50:50 - INFO - __main__ - Step 53405: {'lr': 0.0003653660172599702, 'samples': 10253760, 'steps': 53404, 'loss/train': 1.2231831550598145} 08/30/2021 22:50:52 - INFO - __main__ - Step 53406: {'lr': 0.00036536130930850435, 'samples': 10253952, 'steps': 53405, 'loss/train': 1.5195879936218262} 08/30/2021 22:50:52 - INFO - __main__ - Step 53407: {'lr': 0.0003653566013050585, 'samples': 10254144, 'steps': 53406, 'loss/train': 0.8204035758972168} 08/30/2021 22:50:52 - INFO - __main__ - Step 53408: {'lr': 0.0003653518932496347, 'samples': 10254336, 'steps': 53407, 'loss/train': 0.37187647819519043} 08/30/2021 22:50:53 - INFO - __main__ - Step 53409: {'lr': 0.00036534718514223517, 'samples': 10254528, 'steps': 53408, 'loss/train': 1.2747961282730103} 08/30/2021 22:50:53 - INFO - __main__ - Step 53410: {'lr': 0.00036534247698286195, 'samples': 10254720, 'steps': 53409, 'loss/train': 0.8585013747215271} 08/30/2021 22:50:55 - INFO - __main__ - Step 53411: {'lr': 0.0003653377687715171, 'samples': 10254912, 'steps': 53410, 'loss/train': 1.2029095888137817} 08/30/2021 22:50:55 - INFO - __main__ - Step 53412: {'lr': 0.00036533306050820296, 'samples': 10255104, 'steps': 53411, 'loss/train': 1.298954725265503} 08/30/2021 22:50:56 - INFO - __main__ - Step 53413: {'lr': 0.00036532835219292147, 'samples': 10255296, 'steps': 53412, 'loss/train': 1.1649186611175537} 08/30/2021 22:50:56 - INFO - __main__ - Step 53414: {'lr': 0.0003653236438256748, 'samples': 10255488, 'steps': 53413, 'loss/train': 1.058119535446167} 08/30/2021 22:50:56 - INFO - __main__ - Step 53415: {'lr': 0.0003653189354064652, 'samples': 10255680, 'steps': 53414, 'loss/train': 0.74858158826828} 08/30/2021 22:50:57 - INFO - __main__ - Step 53416: {'lr': 0.0003653142269352945, 'samples': 10255872, 'steps': 53415, 'loss/train': 1.3596488237380981} 08/30/2021 22:50:58 - INFO - __main__ - Step 53417: {'lr': 0.00036530951841216505, 'samples': 10256064, 'steps': 53416, 'loss/train': 1.2551789283752441} 08/30/2021 22:50:59 - INFO - __main__ - Step 53418: {'lr': 0.00036530480983707885, 'samples': 10256256, 'steps': 53417, 'loss/train': 1.7117927074432373} 08/30/2021 22:50:59 - INFO - __main__ - Step 53419: {'lr': 0.0003653001012100382, 'samples': 10256448, 'steps': 53418, 'loss/train': 0.9548460841178894} 08/30/2021 22:50:59 - INFO - __main__ - Step 53420: {'lr': 0.00036529539253104507, 'samples': 10256640, 'steps': 53419, 'loss/train': 1.1545995473861694} 08/30/2021 22:51:00 - INFO - __main__ - Step 53421: {'lr': 0.00036529068380010155, 'samples': 10256832, 'steps': 53420, 'loss/train': 1.5638716220855713} 08/30/2021 22:51:02 - INFO - __main__ - Step 53422: {'lr': 0.00036528597501720984, 'samples': 10257024, 'steps': 53421, 'loss/train': 1.3269634246826172} 08/30/2021 22:51:02 - INFO - __main__ - Step 53423: {'lr': 0.00036528126618237206, 'samples': 10257216, 'steps': 53422, 'loss/train': 0.14268846809864044} 08/30/2021 22:51:03 - INFO - __main__ - Step 53424: {'lr': 0.00036527655729559036, 'samples': 10257408, 'steps': 53423, 'loss/train': 0.7545961141586304} 08/30/2021 22:51:03 - INFO - __main__ - Step 53425: {'lr': 0.0003652718483568668, 'samples': 10257600, 'steps': 53424, 'loss/train': 2.6051790714263916} 08/30/2021 22:51:03 - INFO - __main__ - Step 53426: {'lr': 0.00036526713936620354, 'samples': 10257792, 'steps': 53425, 'loss/train': 1.2532936334609985} 08/30/2021 22:51:05 - INFO - __main__ - Step 53427: {'lr': 0.00036526243032360264, 'samples': 10257984, 'steps': 53426, 'loss/train': 0.9665814638137817} 08/30/2021 22:51:05 - INFO - __main__ - Step 53428: {'lr': 0.0003652577212290663, 'samples': 10258176, 'steps': 53427, 'loss/train': 1.752152919769287} 08/30/2021 22:51:06 - INFO - __main__ - Step 53429: {'lr': 0.0003652530120825966, 'samples': 10258368, 'steps': 53428, 'loss/train': 1.6265177726745605} 08/30/2021 22:51:06 - INFO - __main__ - Step 53430: {'lr': 0.0003652483028841956, 'samples': 10258560, 'steps': 53429, 'loss/train': 1.3366334438323975} 08/30/2021 22:51:06 - INFO - __main__ - Step 53431: {'lr': 0.0003652435936338656, 'samples': 10258752, 'steps': 53430, 'loss/train': 1.371620535850525} 08/30/2021 22:51:08 - INFO - __main__ - Step 53432: {'lr': 0.00036523888433160864, 'samples': 10258944, 'steps': 53431, 'loss/train': 1.4021217823028564} 08/30/2021 22:51:08 - INFO - __main__ - Step 53433: {'lr': 0.00036523417497742673, 'samples': 10259136, 'steps': 53432, 'loss/train': 1.6641066074371338} 08/30/2021 22:51:09 - INFO - __main__ - Step 53434: {'lr': 0.00036522946557132206, 'samples': 10259328, 'steps': 53433, 'loss/train': 1.2567930221557617} 08/30/2021 22:51:09 - INFO - __main__ - Step 53435: {'lr': 0.00036522475611329685, 'samples': 10259520, 'steps': 53434, 'loss/train': 1.4252620935440063} 08/30/2021 22:51:09 - INFO - __main__ - Step 53436: {'lr': 0.00036522004660335304, 'samples': 10259712, 'steps': 53435, 'loss/train': 0.14292070269584656} 08/30/2021 22:51:11 - INFO - __main__ - Step 53437: {'lr': 0.000365215337041493, 'samples': 10259904, 'steps': 53436, 'loss/train': 1.4430783987045288} 08/30/2021 22:51:12 - INFO - __main__ - Step 53438: {'lr': 0.00036521062742771865, 'samples': 10260096, 'steps': 53437, 'loss/train': 1.1252435445785522} 08/30/2021 22:51:12 - INFO - __main__ - Step 53439: {'lr': 0.0003652059177620322, 'samples': 10260288, 'steps': 53438, 'loss/train': 1.7982990741729736} 08/30/2021 22:51:12 - INFO - __main__ - Step 53440: {'lr': 0.00036520120804443563, 'samples': 10260480, 'steps': 53439, 'loss/train': 1.3511203527450562} 08/30/2021 22:51:13 - INFO - __main__ - Step 53441: {'lr': 0.00036519649827493117, 'samples': 10260672, 'steps': 53440, 'loss/train': 0.39136233925819397} 08/30/2021 22:51:14 - INFO - __main__ - Step 53442: {'lr': 0.000365191788453521, 'samples': 10260864, 'steps': 53441, 'loss/train': 1.3825815916061401} 08/30/2021 22:51:15 - INFO - __main__ - Step 53443: {'lr': 0.0003651870785802072, 'samples': 10261056, 'steps': 53442, 'loss/train': 0.5633563995361328} 08/30/2021 22:51:15 - INFO - __main__ - Step 53444: {'lr': 0.00036518236865499187, 'samples': 10261248, 'steps': 53443, 'loss/train': 1.306609869003296} 08/30/2021 22:51:15 - INFO - __main__ - Step 53445: {'lr': 0.0003651776586778772, 'samples': 10261440, 'steps': 53444, 'loss/train': 1.2627437114715576} 08/30/2021 22:51:16 - INFO - __main__ - Step 53446: {'lr': 0.00036517294864886517, 'samples': 10261632, 'steps': 53445, 'loss/train': 0.8276983499526978} 08/30/2021 22:51:16 - INFO - __main__ - Step 53447: {'lr': 0.00036516823856795806, 'samples': 10261824, 'steps': 53446, 'loss/train': 1.5608497858047485} 08/30/2021 22:51:17 - INFO - __main__ - Step 53448: {'lr': 0.0003651635284351579, 'samples': 10262016, 'steps': 53447, 'loss/train': 1.156587839126587} 08/30/2021 22:51:18 - INFO - __main__ - Step 53449: {'lr': 0.00036515881825046676, 'samples': 10262208, 'steps': 53448, 'loss/train': 1.5529667139053345} 08/30/2021 22:51:18 - INFO - __main__ - Step 53450: {'lr': 0.00036515410801388686, 'samples': 10262400, 'steps': 53449, 'loss/train': 0.9423414468765259} 08/30/2021 22:51:19 - INFO - __main__ - Step 53451: {'lr': 0.0003651493977254204, 'samples': 10262592, 'steps': 53450, 'loss/train': 0.8619718551635742} 08/30/2021 22:51:20 - INFO - __main__ - Step 53452: {'lr': 0.0003651446873850693, 'samples': 10262784, 'steps': 53451, 'loss/train': 0.8839391469955444} 08/30/2021 22:51:21 - INFO - __main__ - Step 53453: {'lr': 0.0003651399769928358, 'samples': 10262976, 'steps': 53452, 'loss/train': 1.1584831476211548} 08/30/2021 22:51:21 - INFO - __main__ - Step 53454: {'lr': 0.000365135266548722, 'samples': 10263168, 'steps': 53453, 'loss/train': 1.6461392641067505} 08/30/2021 22:51:21 - INFO - __main__ - Step 53455: {'lr': 0.00036513055605273, 'samples': 10263360, 'steps': 53454, 'loss/train': 1.6310418844223022} 08/30/2021 22:51:22 - INFO - __main__ - Step 53456: {'lr': 0.0003651258455048619, 'samples': 10263552, 'steps': 53455, 'loss/train': 0.8739601969718933} 08/30/2021 22:51:22 - INFO - __main__ - Step 53457: {'lr': 0.00036512113490512, 'samples': 10263744, 'steps': 53456, 'loss/train': 1.4671311378479004} 08/30/2021 22:51:23 - INFO - __main__ - Step 53458: {'lr': 0.00036511642425350626, 'samples': 10263936, 'steps': 53457, 'loss/train': 0.11801846325397491} 08/30/2021 22:51:24 - INFO - __main__ - Step 53459: {'lr': 0.00036511171355002283, 'samples': 10264128, 'steps': 53458, 'loss/train': 0.5840108394622803} 08/30/2021 22:51:24 - INFO - __main__ - Step 53460: {'lr': 0.0003651070027946718, 'samples': 10264320, 'steps': 53459, 'loss/train': 1.3782750368118286} 08/30/2021 22:51:25 - INFO - __main__ - Step 53461: {'lr': 0.0003651022919874554, 'samples': 10264512, 'steps': 53460, 'loss/train': 1.2199827432632446} 08/30/2021 22:51:25 - INFO - __main__ - Step 53462: {'lr': 0.0003650975811283756, 'samples': 10264704, 'steps': 53461, 'loss/train': 1.2753008604049683} 08/30/2021 22:51:26 - INFO - __main__ - Step 53463: {'lr': 0.00036509287021743465, 'samples': 10264896, 'steps': 53462, 'loss/train': 1.5252403020858765} 08/30/2021 22:51:27 - INFO - __main__ - Step 53464: {'lr': 0.00036508815925463456, 'samples': 10265088, 'steps': 53463, 'loss/train': 0.8326263427734375} 08/30/2021 22:51:27 - INFO - __main__ - Step 53465: {'lr': 0.0003650834482399776, 'samples': 10265280, 'steps': 53464, 'loss/train': 0.8398168087005615} 08/30/2021 22:51:28 - INFO - __main__ - Step 53466: {'lr': 0.00036507873717346584, 'samples': 10265472, 'steps': 53465, 'loss/train': 1.22458815574646} 08/30/2021 22:51:28 - INFO - __main__ - Step 53467: {'lr': 0.00036507402605510134, 'samples': 10265664, 'steps': 53466, 'loss/train': 1.3852087259292603} 08/30/2021 22:51:30 - INFO - __main__ - Step 53468: {'lr': 0.00036506931488488627, 'samples': 10265856, 'steps': 53467, 'loss/train': 1.3797937631607056} 08/30/2021 22:51:30 - INFO - __main__ - Step 53469: {'lr': 0.0003650646036628227, 'samples': 10266048, 'steps': 53468, 'loss/train': 1.412377119064331} 08/30/2021 22:51:30 - INFO - __main__ - Step 53470: {'lr': 0.0003650598923889128, 'samples': 10266240, 'steps': 53469, 'loss/train': 0.08793564140796661} 08/30/2021 22:51:31 - INFO - __main__ - Step 53471: {'lr': 0.0003650551810631587, 'samples': 10266432, 'steps': 53470, 'loss/train': 1.978947401046753} 08/30/2021 22:51:31 - INFO - __main__ - Step 53472: {'lr': 0.00036505046968556253, 'samples': 10266624, 'steps': 53471, 'loss/train': 1.0977704524993896} 08/30/2021 22:51:33 - INFO - __main__ - Step 53473: {'lr': 0.0003650457582561264, 'samples': 10266816, 'steps': 53472, 'loss/train': 1.2934050559997559} 08/30/2021 22:51:34 - INFO - __main__ - Step 53474: {'lr': 0.0003650410467748524, 'samples': 10267008, 'steps': 53473, 'loss/train': 1.2697805166244507} 08/30/2021 22:51:34 - INFO - __main__ - Step 53475: {'lr': 0.0003650363352417427, 'samples': 10267200, 'steps': 53474, 'loss/train': 1.6234385967254639} 08/30/2021 22:51:35 - INFO - __main__ - Step 53476: {'lr': 0.00036503162365679936, 'samples': 10267392, 'steps': 53475, 'loss/train': 0.7800869941711426} 08/30/2021 22:51:35 - INFO - __main__ - Step 53477: {'lr': 0.00036502691202002456, 'samples': 10267584, 'steps': 53476, 'loss/train': 1.6124154329299927} 08/30/2021 22:51:35 - INFO - __main__ - Step 53478: {'lr': 0.00036502220033142045, 'samples': 10267776, 'steps': 53477, 'loss/train': 1.523951768875122} 08/30/2021 22:51:37 - INFO - __main__ - Step 53479: {'lr': 0.0003650174885909891, 'samples': 10267968, 'steps': 53478, 'loss/train': 1.639223337173462} 08/30/2021 22:51:38 - INFO - __main__ - Step 53480: {'lr': 0.0003650127767987326, 'samples': 10268160, 'steps': 53479, 'loss/train': 0.05455992743372917} 08/30/2021 22:51:38 - INFO - __main__ - Step 53481: {'lr': 0.00036500806495465315, 'samples': 10268352, 'steps': 53480, 'loss/train': 0.4502923786640167} 08/30/2021 22:51:38 - INFO - __main__ - Step 53482: {'lr': 0.0003650033530587529, 'samples': 10268544, 'steps': 53481, 'loss/train': 1.1247785091400146} 08/30/2021 22:51:39 - INFO - __main__ - Step 53483: {'lr': 0.00036499864111103384, 'samples': 10268736, 'steps': 53482, 'loss/train': 0.3981146812438965} 08/30/2021 22:51:40 - INFO - __main__ - Step 53484: {'lr': 0.00036499392911149817, 'samples': 10268928, 'steps': 53483, 'loss/train': 1.386189579963684} 08/30/2021 22:51:41 - INFO - __main__ - Step 53485: {'lr': 0.00036498921706014804, 'samples': 10269120, 'steps': 53484, 'loss/train': 1.434557318687439} 08/30/2021 22:51:41 - INFO - __main__ - Step 53486: {'lr': 0.00036498450495698557, 'samples': 10269312, 'steps': 53485, 'loss/train': 1.1038395166397095} 08/30/2021 22:51:41 - INFO - __main__ - Step 53487: {'lr': 0.00036497979280201276, 'samples': 10269504, 'steps': 53486, 'loss/train': 1.2938913106918335} 08/30/2021 22:51:42 - INFO - __main__ - Step 53488: {'lr': 0.0003649750805952319, 'samples': 10269696, 'steps': 53487, 'loss/train': 1.657962441444397} 08/30/2021 22:51:43 - INFO - __main__ - Step 53489: {'lr': 0.000364970368336645, 'samples': 10269888, 'steps': 53488, 'loss/train': 2.8993301391601562} 08/30/2021 22:51:44 - INFO - __main__ - Step 53490: {'lr': 0.0003649656560262542, 'samples': 10270080, 'steps': 53489, 'loss/train': 1.1926651000976562} 08/30/2021 22:51:44 - INFO - __main__ - Step 53491: {'lr': 0.00036496094366406166, 'samples': 10270272, 'steps': 53490, 'loss/train': 0.9238526225090027} 08/30/2021 22:51:45 - INFO - __main__ - Step 53492: {'lr': 0.0003649562312500696, 'samples': 10270464, 'steps': 53491, 'loss/train': 1.444689154624939} 08/30/2021 22:51:45 - INFO - __main__ - Step 53493: {'lr': 0.00036495151878427994, 'samples': 10270656, 'steps': 53492, 'loss/train': 1.4126598834991455} 08/30/2021 22:51:46 - INFO - __main__ - Step 53494: {'lr': 0.00036494680626669495, 'samples': 10270848, 'steps': 53493, 'loss/train': 1.0082255601882935} 08/30/2021 22:51:47 - INFO - __main__ - Step 53495: {'lr': 0.00036494209369731666, 'samples': 10271040, 'steps': 53494, 'loss/train': 0.8961471319198608} 08/30/2021 22:51:47 - INFO - __main__ - Step 53496: {'lr': 0.0003649373810761473, 'samples': 10271232, 'steps': 53495, 'loss/train': 0.65122389793396} 08/30/2021 22:51:48 - INFO - __main__ - Step 53497: {'lr': 0.00036493266840318886, 'samples': 10271424, 'steps': 53496, 'loss/train': 1.2869007587432861} 08/30/2021 22:51:48 - INFO - __main__ - Step 53498: {'lr': 0.0003649279556784436, 'samples': 10271616, 'steps': 53497, 'loss/train': 0.5302497744560242} 08/30/2021 22:51:49 - INFO - __main__ - Step 53499: {'lr': 0.0003649232429019135, 'samples': 10271808, 'steps': 53498, 'loss/train': 1.598929524421692} 08/30/2021 22:51:50 - INFO - __main__ - Step 53500: {'lr': 0.0003649185300736008, 'samples': 10272000, 'steps': 53499, 'loss/train': 1.7576169967651367} 08/30/2021 22:51:50 - INFO - __main__ - Step 53501: {'lr': 0.0003649138171935076, 'samples': 10272192, 'steps': 53500, 'loss/train': 1.0426875352859497} 08/30/2021 22:51:51 - INFO - __main__ - Step 53502: {'lr': 0.0003649091042616359, 'samples': 10272384, 'steps': 53501, 'loss/train': 1.349707007408142} 08/30/2021 22:51:51 - INFO - __main__ - Step 53503: {'lr': 0.000364904391277988, 'samples': 10272576, 'steps': 53502, 'loss/train': 1.4303089380264282} 08/30/2021 22:51:51 - INFO - __main__ - Step 53504: {'lr': 0.00036489967824256597, 'samples': 10272768, 'steps': 53503, 'loss/train': 3.495563507080078} 08/30/2021 22:51:53 - INFO - __main__ - Step 53505: {'lr': 0.000364894965155372, 'samples': 10272960, 'steps': 53504, 'loss/train': 1.4231292009353638} 08/30/2021 22:51:54 - INFO - __main__ - Step 53506: {'lr': 0.000364890252016408, 'samples': 10273152, 'steps': 53505, 'loss/train': 1.551091194152832} 08/30/2021 22:51:54 - INFO - __main__ - Step 53507: {'lr': 0.0003648855388256763, 'samples': 10273344, 'steps': 53506, 'loss/train': 1.722885012626648} 08/30/2021 22:51:54 - INFO - __main__ - Step 53508: {'lr': 0.0003648808255831789, 'samples': 10273536, 'steps': 53507, 'loss/train': 1.0195305347442627} 08/30/2021 22:51:55 - INFO - __main__ - Step 53509: {'lr': 0.00036487611228891805, 'samples': 10273728, 'steps': 53508, 'loss/train': 1.283014178276062} 08/30/2021 22:51:56 - INFO - __main__ - Step 53510: {'lr': 0.00036487139894289566, 'samples': 10273920, 'steps': 53509, 'loss/train': 1.020158052444458} 08/30/2021 22:51:57 - INFO - __main__ - Step 53511: {'lr': 0.0003648666855451141, 'samples': 10274112, 'steps': 53510, 'loss/train': 1.0939558744430542} 08/30/2021 22:51:57 - INFO - __main__ - Step 53512: {'lr': 0.0003648619720955754, 'samples': 10274304, 'steps': 53511, 'loss/train': 2.010610818862915} 08/30/2021 22:51:57 - INFO - __main__ - Step 53513: {'lr': 0.00036485725859428163, 'samples': 10274496, 'steps': 53512, 'loss/train': 1.1178526878356934} 08/30/2021 22:51:58 - INFO - __main__ - Step 53514: {'lr': 0.00036485254504123495, 'samples': 10274688, 'steps': 53513, 'loss/train': 1.5793871879577637} 08/30/2021 22:51:59 - INFO - __main__ - Step 53515: {'lr': 0.00036484783143643745, 'samples': 10274880, 'steps': 53514, 'loss/train': 1.0669639110565186} 08/30/2021 22:52:00 - INFO - __main__ - Step 53516: {'lr': 0.0003648431177798913, 'samples': 10275072, 'steps': 53515, 'loss/train': 2.1173694133758545} 08/30/2021 22:52:00 - INFO - __main__ - Step 53517: {'lr': 0.00036483840407159864, 'samples': 10275264, 'steps': 53516, 'loss/train': 1.7722991704940796} 08/30/2021 22:52:00 - INFO - __main__ - Step 53518: {'lr': 0.0003648336903115616, 'samples': 10275456, 'steps': 53517, 'loss/train': 1.443000078201294} 08/30/2021 22:52:01 - INFO - __main__ - Step 53519: {'lr': 0.0003648289764997823, 'samples': 10275648, 'steps': 53518, 'loss/train': 1.2102855443954468} 08/30/2021 22:52:02 - INFO - __main__ - Step 53520: {'lr': 0.00036482426263626265, 'samples': 10275840, 'steps': 53519, 'loss/train': 1.4799578189849854} 08/30/2021 22:52:03 - INFO - __main__ - Step 53521: {'lr': 0.0003648195487210051, 'samples': 10276032, 'steps': 53520, 'loss/train': 1.193872094154358} 08/30/2021 22:52:03 - INFO - __main__ - Step 53522: {'lr': 0.0003648148347540116, 'samples': 10276224, 'steps': 53521, 'loss/train': 1.3264586925506592} 08/30/2021 22:52:03 - INFO - __main__ - Step 53523: {'lr': 0.0003648101207352843, 'samples': 10276416, 'steps': 53522, 'loss/train': 1.4574564695358276} 08/30/2021 22:52:04 - INFO - __main__ - Step 53524: {'lr': 0.00036480540666482535, 'samples': 10276608, 'steps': 53523, 'loss/train': 1.1356863975524902} 08/30/2021 22:52:06 - INFO - __main__ - Step 53525: {'lr': 0.00036480069254263693, 'samples': 10276800, 'steps': 53524, 'loss/train': 0.6236507296562195} 08/30/2021 22:52:07 - INFO - __main__ - Step 53526: {'lr': 0.000364795978368721, 'samples': 10276992, 'steps': 53525, 'loss/train': 1.2939671277999878} 08/30/2021 22:52:07 - INFO - __main__ - Step 53527: {'lr': 0.0003647912641430798, 'samples': 10277184, 'steps': 53526, 'loss/train': 0.9056761264801025} 08/30/2021 22:52:07 - INFO - __main__ - Step 53528: {'lr': 0.0003647865498657154, 'samples': 10277376, 'steps': 53527, 'loss/train': 1.0268940925598145} 08/30/2021 22:52:08 - INFO - __main__ - Step 53529: {'lr': 0.0003647818355366299, 'samples': 10277568, 'steps': 53528, 'loss/train': 2.517875909805298} 08/30/2021 22:52:08 - INFO - __main__ - Step 53530: {'lr': 0.00036477712115582555, 'samples': 10277760, 'steps': 53529, 'loss/train': 1.992435336112976} 08/30/2021 22:52:10 - INFO - __main__ - Step 53531: {'lr': 0.0003647724067233044, 'samples': 10277952, 'steps': 53530, 'loss/train': 0.8576481938362122} 08/30/2021 22:52:10 - INFO - __main__ - Step 53532: {'lr': 0.00036476769223906864, 'samples': 10278144, 'steps': 53531, 'loss/train': 1.5434718132019043} 08/30/2021 22:52:11 - INFO - __main__ - Step 53533: {'lr': 0.0003647629777031202, 'samples': 10278336, 'steps': 53532, 'loss/train': 1.200901985168457} 08/30/2021 22:52:11 - INFO - __main__ - Step 53534: {'lr': 0.0003647582631154614, 'samples': 10278528, 'steps': 53533, 'loss/train': 1.8989466428756714} 08/30/2021 22:52:11 - INFO - __main__ - Step 53535: {'lr': 0.00036475354847609434, 'samples': 10278720, 'steps': 53534, 'loss/train': 1.4029427766799927} 08/30/2021 22:52:13 - INFO - __main__ - Step 53536: {'lr': 0.000364748833785021, 'samples': 10278912, 'steps': 53535, 'loss/train': 1.9528943300247192} 08/30/2021 22:52:13 - INFO - __main__ - Step 53537: {'lr': 0.0003647441190422437, 'samples': 10279104, 'steps': 53536, 'loss/train': 1.6159769296646118} 08/30/2021 22:52:14 - INFO - __main__ - Step 53538: {'lr': 0.00036473940424776443, 'samples': 10279296, 'steps': 53537, 'loss/train': 1.4012949466705322} 08/30/2021 22:52:14 - INFO - __main__ - Step 53539: {'lr': 0.0003647346894015853, 'samples': 10279488, 'steps': 53538, 'loss/train': 1.6042912006378174} 08/30/2021 22:52:14 - INFO - __main__ - Step 53540: {'lr': 0.0003647299745037085, 'samples': 10279680, 'steps': 53539, 'loss/train': 1.0776602029800415} 08/30/2021 22:52:16 - INFO - __main__ - Step 53541: {'lr': 0.00036472525955413626, 'samples': 10279872, 'steps': 53540, 'loss/train': 1.5056815147399902} 08/30/2021 22:52:16 - INFO - __main__ - Step 53542: {'lr': 0.00036472054455287053, 'samples': 10280064, 'steps': 53541, 'loss/train': 1.3808598518371582} 08/30/2021 22:52:17 - INFO - __main__ - Step 53543: {'lr': 0.00036471582949991347, 'samples': 10280256, 'steps': 53542, 'loss/train': 2.001156806945801} 08/30/2021 22:52:17 - INFO - __main__ - Step 53544: {'lr': 0.0003647111143952672, 'samples': 10280448, 'steps': 53543, 'loss/train': 1.7043068408966064} 08/30/2021 22:52:17 - INFO - __main__ - Step 53545: {'lr': 0.0003647063992389339, 'samples': 10280640, 'steps': 53544, 'loss/train': 1.573975682258606} 08/30/2021 22:52:19 - INFO - __main__ - Step 53546: {'lr': 0.00036470168403091567, 'samples': 10280832, 'steps': 53545, 'loss/train': 1.301865577697754} 08/30/2021 22:52:20 - INFO - __main__ - Step 53547: {'lr': 0.00036469696877121464, 'samples': 10281024, 'steps': 53546, 'loss/train': 1.6805670261383057} 08/30/2021 22:52:20 - INFO - __main__ - Step 53548: {'lr': 0.000364692253459833, 'samples': 10281216, 'steps': 53547, 'loss/train': 0.7505008578300476} 08/30/2021 22:52:20 - INFO - __main__ - Step 53549: {'lr': 0.0003646875380967727, 'samples': 10281408, 'steps': 53548, 'loss/train': 1.2794783115386963} 08/30/2021 22:52:21 - INFO - __main__ - Step 53550: {'lr': 0.00036468282268203595, 'samples': 10281600, 'steps': 53549, 'loss/train': 2.3715789318084717} 08/30/2021 22:52:21 - INFO - __main__ - Step 53551: {'lr': 0.0003646781072156249, 'samples': 10281792, 'steps': 53550, 'loss/train': 1.349063515663147} 08/30/2021 22:52:23 - INFO - __main__ - Step 53552: {'lr': 0.00036467339169754173, 'samples': 10281984, 'steps': 53551, 'loss/train': 0.6878082752227783} 08/30/2021 22:52:23 - INFO - __main__ - Step 53553: {'lr': 0.0003646686761277884, 'samples': 10282176, 'steps': 53552, 'loss/train': 1.3104041814804077} 08/30/2021 22:52:23 - INFO - __main__ - Step 53554: {'lr': 0.00036466396050636725, 'samples': 10282368, 'steps': 53553, 'loss/train': 1.3920091390609741} 08/30/2021 22:52:24 - INFO - __main__ - Step 53555: {'lr': 0.0003646592448332802, 'samples': 10282560, 'steps': 53554, 'loss/train': 0.8019581437110901} 08/30/2021 22:52:24 - INFO - __main__ - Step 53556: {'lr': 0.00036465452910852946, 'samples': 10282752, 'steps': 53555, 'loss/train': 1.3756120204925537} 08/30/2021 22:52:26 - INFO - __main__ - Step 53557: {'lr': 0.00036464981333211724, 'samples': 10282944, 'steps': 53556, 'loss/train': 1.5004515647888184} 08/30/2021 22:52:26 - INFO - __main__ - Step 53558: {'lr': 0.0003646450975040455, 'samples': 10283136, 'steps': 53557, 'loss/train': 1.5661299228668213} 08/30/2021 22:52:27 - INFO - __main__ - Step 53559: {'lr': 0.00036464038162431657, 'samples': 10283328, 'steps': 53558, 'loss/train': 1.9571486711502075} 08/30/2021 22:52:27 - INFO - __main__ - Step 53560: {'lr': 0.00036463566569293235, 'samples': 10283520, 'steps': 53559, 'loss/train': 1.5035619735717773} 08/30/2021 22:52:27 - INFO - __main__ - Step 53561: {'lr': 0.0003646309497098951, 'samples': 10283712, 'steps': 53560, 'loss/train': 1.8263338804244995} 08/30/2021 22:52:28 - INFO - __main__ - Step 53562: {'lr': 0.00036462623367520684, 'samples': 10283904, 'steps': 53561, 'loss/train': 1.520851731300354} 08/30/2021 22:52:29 - INFO - __main__ - Step 53563: {'lr': 0.00036462151758886985, 'samples': 10284096, 'steps': 53562, 'loss/train': 2.425801992416382} 08/30/2021 22:52:30 - INFO - __main__ - Step 53564: {'lr': 0.0003646168014508861, 'samples': 10284288, 'steps': 53563, 'loss/train': 1.1778380870819092} 08/30/2021 22:52:30 - INFO - __main__ - Step 53565: {'lr': 0.00036461208526125785, 'samples': 10284480, 'steps': 53564, 'loss/train': 1.2143785953521729} 08/30/2021 22:52:31 - INFO - __main__ - Step 53566: {'lr': 0.0003646073690199872, 'samples': 10284672, 'steps': 53565, 'loss/train': 1.1335147619247437} 08/30/2021 22:52:31 - INFO - __main__ - Step 53567: {'lr': 0.00036460265272707617, 'samples': 10284864, 'steps': 53566, 'loss/train': 1.2677206993103027} 08/30/2021 22:52:32 - INFO - __main__ - Step 53568: {'lr': 0.000364597936382527, 'samples': 10285056, 'steps': 53567, 'loss/train': 1.5351126194000244} 08/30/2021 22:52:33 - INFO - __main__ - Step 53569: {'lr': 0.0003645932199863417, 'samples': 10285248, 'steps': 53568, 'loss/train': 1.2966172695159912} 08/30/2021 22:52:33 - INFO - __main__ - Step 53570: {'lr': 0.00036458850353852246, 'samples': 10285440, 'steps': 53569, 'loss/train': 0.4543309807777405} 08/30/2021 22:52:33 - INFO - __main__ - Step 53571: {'lr': 0.0003645837870390715, 'samples': 10285632, 'steps': 53570, 'loss/train': 1.1566879749298096} 08/30/2021 22:52:34 - INFO - __main__ - Step 53572: {'lr': 0.00036457907048799084, 'samples': 10285824, 'steps': 53571, 'loss/train': 1.687994360923767} 08/30/2021 22:52:36 - INFO - __main__ - Step 53573: {'lr': 0.00036457435388528257, 'samples': 10286016, 'steps': 53572, 'loss/train': 0.6456499099731445} 08/30/2021 22:52:36 - INFO - __main__ - Step 53574: {'lr': 0.0003645696372309488, 'samples': 10286208, 'steps': 53573, 'loss/train': 1.6295289993286133} 08/30/2021 22:52:36 - INFO - __main__ - Step 53575: {'lr': 0.00036456492052499185, 'samples': 10286400, 'steps': 53574, 'loss/train': 1.1518089771270752} 08/30/2021 22:52:37 - INFO - __main__ - Step 53576: {'lr': 0.00036456020376741363, 'samples': 10286592, 'steps': 53575, 'loss/train': 1.277836561203003} 08/30/2021 22:52:37 - INFO - __main__ - Step 53577: {'lr': 0.0003645554869582164, 'samples': 10286784, 'steps': 53576, 'loss/train': 0.33677440881729126} 08/30/2021 22:52:37 - INFO - __main__ - Step 53578: {'lr': 0.0003645507700974022, 'samples': 10286976, 'steps': 53577, 'loss/train': 1.091191053390503} 08/30/2021 22:52:38 - INFO - __main__ - Step 53579: {'lr': 0.00036454605318497323, 'samples': 10287168, 'steps': 53578, 'loss/train': 1.3166148662567139} 08/30/2021 22:52:39 - INFO - __main__ - Step 53580: {'lr': 0.00036454133622093154, 'samples': 10287360, 'steps': 53579, 'loss/train': 0.6587302684783936} 08/30/2021 22:52:40 - INFO - __main__ - Step 53581: {'lr': 0.00036453661920527933, 'samples': 10287552, 'steps': 53580, 'loss/train': 1.1824767589569092} 08/30/2021 22:52:40 - INFO - __main__ - Step 53582: {'lr': 0.0003645319021380186, 'samples': 10287744, 'steps': 53581, 'loss/train': 1.2667876482009888} 08/30/2021 22:52:40 - INFO - __main__ - Step 53583: {'lr': 0.00036452718501915165, 'samples': 10287936, 'steps': 53582, 'loss/train': 0.3757949769496918} 08/30/2021 22:52:41 - INFO - __main__ - Step 53584: {'lr': 0.00036452246784868047, 'samples': 10288128, 'steps': 53583, 'loss/train': 0.5303133130073547} 08/30/2021 22:52:43 - INFO - __main__ - Step 53585: {'lr': 0.0003645177506266072, 'samples': 10288320, 'steps': 53584, 'loss/train': 1.7345420122146606} 08/30/2021 22:52:43 - INFO - __main__ - Step 53586: {'lr': 0.0003645130333529342, 'samples': 10288512, 'steps': 53585, 'loss/train': 1.2740157842636108} 08/30/2021 22:52:44 - INFO - __main__ - Step 53587: {'lr': 0.0003645083160276632, 'samples': 10288704, 'steps': 53586, 'loss/train': 1.4862607717514038} 08/30/2021 22:52:44 - INFO - __main__ - Step 53588: {'lr': 0.0003645035986507966, 'samples': 10288896, 'steps': 53587, 'loss/train': 1.404309630393982} 08/30/2021 22:52:44 - INFO - __main__ - Step 53589: {'lr': 0.00036449888122233636, 'samples': 10289088, 'steps': 53588, 'loss/train': 1.5585339069366455} 08/30/2021 22:52:46 - INFO - __main__ - Step 53590: {'lr': 0.00036449416374228474, 'samples': 10289280, 'steps': 53589, 'loss/train': 1.390363335609436} 08/30/2021 22:52:47 - INFO - __main__ - Step 53591: {'lr': 0.00036448944621064386, 'samples': 10289472, 'steps': 53590, 'loss/train': 2.0829086303710938} 08/30/2021 22:52:47 - INFO - __main__ - Step 53592: {'lr': 0.00036448472862741577, 'samples': 10289664, 'steps': 53591, 'loss/train': 1.330190658569336} 08/30/2021 22:52:47 - INFO - __main__ - Step 53593: {'lr': 0.0003644800109926026, 'samples': 10289856, 'steps': 53592, 'loss/train': 1.5439928770065308} 08/30/2021 22:52:48 - INFO - __main__ - Step 53594: {'lr': 0.00036447529330620653, 'samples': 10290048, 'steps': 53593, 'loss/train': 0.9738254547119141} 08/30/2021 22:52:49 - INFO - __main__ - Step 53595: {'lr': 0.0003644705755682296, 'samples': 10290240, 'steps': 53594, 'loss/train': 1.4617013931274414} 08/30/2021 22:52:50 - INFO - __main__ - Step 53596: {'lr': 0.00036446585777867406, 'samples': 10290432, 'steps': 53595, 'loss/train': 1.7266370058059692} 08/30/2021 22:52:50 - INFO - __main__ - Step 53597: {'lr': 0.0003644611399375419, 'samples': 10290624, 'steps': 53596, 'loss/train': 1.4301815032958984} 08/30/2021 22:52:50 - INFO - __main__ - Step 53598: {'lr': 0.0003644564220448354, 'samples': 10290816, 'steps': 53597, 'loss/train': 1.1844182014465332} 08/30/2021 22:52:51 - INFO - __main__ - Step 53599: {'lr': 0.0003644517041005566, 'samples': 10291008, 'steps': 53598, 'loss/train': 1.2154752016067505} 08/30/2021 22:52:52 - INFO - __main__ - Step 53600: {'lr': 0.0003644469861047076, 'samples': 10291200, 'steps': 53599, 'loss/train': 1.3206616640090942} 08/30/2021 22:52:53 - INFO - __main__ - Step 53601: {'lr': 0.0003644422680572906, 'samples': 10291392, 'steps': 53600, 'loss/train': 0.04915463551878929} 08/30/2021 22:52:53 - INFO - __main__ - Step 53602: {'lr': 0.00036443754995830763, 'samples': 10291584, 'steps': 53601, 'loss/train': 0.9714437127113342} 08/30/2021 22:52:53 - INFO - __main__ - Step 53603: {'lr': 0.0003644328318077609, 'samples': 10291776, 'steps': 53602, 'loss/train': 1.9094164371490479} 08/30/2021 22:52:54 - INFO - __main__ - Step 53604: {'lr': 0.0003644281136056524, 'samples': 10291968, 'steps': 53603, 'loss/train': 1.4263784885406494} 08/30/2021 22:52:55 - INFO - __main__ - Step 53605: {'lr': 0.00036442339535198444, 'samples': 10292160, 'steps': 53604, 'loss/train': 1.1671565771102905} 08/30/2021 22:52:56 - INFO - __main__ - Step 53606: {'lr': 0.00036441867704675913, 'samples': 10292352, 'steps': 53605, 'loss/train': 1.1522252559661865} 08/30/2021 22:52:56 - INFO - __main__ - Step 53607: {'lr': 0.00036441395868997843, 'samples': 10292544, 'steps': 53606, 'loss/train': 0.9276661276817322} 08/30/2021 22:52:56 - INFO - __main__ - Step 53608: {'lr': 0.00036440924028164457, 'samples': 10292736, 'steps': 53607, 'loss/train': 1.4873414039611816} 08/30/2021 22:52:57 - INFO - __main__ - Step 53609: {'lr': 0.0003644045218217597, 'samples': 10292928, 'steps': 53608, 'loss/train': 1.9295828342437744} 08/30/2021 22:52:57 - INFO - __main__ - Step 53610: {'lr': 0.000364399803310326, 'samples': 10293120, 'steps': 53609, 'loss/train': 1.6021238565444946} 08/30/2021 22:52:59 - INFO - __main__ - Step 53611: {'lr': 0.0003643950847473453, 'samples': 10293312, 'steps': 53610, 'loss/train': 1.492674708366394} 08/30/2021 22:52:59 - INFO - __main__ - Step 53612: {'lr': 0.0003643903661328201, 'samples': 10293504, 'steps': 53611, 'loss/train': 0.8950345516204834} 08/30/2021 22:52:59 - INFO - __main__ - Step 53613: {'lr': 0.0003643856474667524, 'samples': 10293696, 'steps': 53612, 'loss/train': 1.5756936073303223} 08/30/2021 22:53:00 - INFO - __main__ - Step 53614: {'lr': 0.0003643809287491442, 'samples': 10293888, 'steps': 53613, 'loss/train': 2.132282257080078} 08/30/2021 22:53:00 - INFO - __main__ - Step 53615: {'lr': 0.00036437620997999777, 'samples': 10294080, 'steps': 53614, 'loss/train': 1.177676796913147} 08/30/2021 22:53:02 - INFO - __main__ - Step 53616: {'lr': 0.0003643714911593151, 'samples': 10294272, 'steps': 53615, 'loss/train': 1.4318127632141113} 08/30/2021 22:53:02 - INFO - __main__ - Step 53617: {'lr': 0.00036436677228709845, 'samples': 10294464, 'steps': 53616, 'loss/train': 1.320518970489502} 08/30/2021 22:53:02 - INFO - __main__ - Step 53618: {'lr': 0.00036436205336334995, 'samples': 10294656, 'steps': 53617, 'loss/train': 1.4042026996612549} 08/30/2021 22:53:03 - INFO - __main__ - Step 53619: {'lr': 0.0003643573343880716, 'samples': 10294848, 'steps': 53618, 'loss/train': 1.5927362442016602} 08/30/2021 22:53:03 - INFO - __main__ - Step 53620: {'lr': 0.00036435261536126566, 'samples': 10295040, 'steps': 53619, 'loss/train': 1.2768652439117432} 08/30/2021 22:53:05 - INFO - __main__ - Step 53621: {'lr': 0.0003643478962829342, 'samples': 10295232, 'steps': 53620, 'loss/train': 1.4479957818984985} 08/30/2021 22:53:05 - INFO - __main__ - Step 53622: {'lr': 0.0003643431771530793, 'samples': 10295424, 'steps': 53621, 'loss/train': 0.927509069442749} 08/30/2021 22:53:05 - INFO - __main__ - Step 53623: {'lr': 0.0003643384579717031, 'samples': 10295616, 'steps': 53622, 'loss/train': 1.726568579673767} 08/30/2021 22:53:06 - INFO - __main__ - Step 53624: {'lr': 0.0003643337387388078, 'samples': 10295808, 'steps': 53623, 'loss/train': 1.381607174873352} 08/30/2021 22:53:06 - INFO - __main__ - Step 53625: {'lr': 0.00036432901945439544, 'samples': 10296000, 'steps': 53624, 'loss/train': 1.8157492876052856} 08/30/2021 22:53:08 - INFO - __main__ - Step 53626: {'lr': 0.0003643243001184683, 'samples': 10296192, 'steps': 53625, 'loss/train': 0.9247584939002991} 08/30/2021 22:53:08 - INFO - __main__ - Step 53627: {'lr': 0.00036431958073102825, 'samples': 10296384, 'steps': 53626, 'loss/train': 1.437009334564209} 08/30/2021 22:53:08 - INFO - __main__ - Step 53628: {'lr': 0.00036431486129207767, 'samples': 10296576, 'steps': 53627, 'loss/train': 1.3408094644546509} 08/30/2021 22:53:09 - INFO - __main__ - Step 53629: {'lr': 0.00036431014180161853, 'samples': 10296768, 'steps': 53628, 'loss/train': 1.5201278924942017} 08/30/2021 22:53:09 - INFO - __main__ - Step 53630: {'lr': 0.000364305422259653, 'samples': 10296960, 'steps': 53629, 'loss/train': 1.462058424949646} 08/30/2021 22:53:11 - INFO - __main__ - Step 53631: {'lr': 0.0003643007026661832, 'samples': 10297152, 'steps': 53630, 'loss/train': 1.388784646987915} 08/30/2021 22:53:11 - INFO - __main__ - Step 53632: {'lr': 0.0003642959830212113, 'samples': 10297344, 'steps': 53631, 'loss/train': 0.9494279623031616} 08/30/2021 22:53:12 - INFO - __main__ - Step 53633: {'lr': 0.0003642912633247394, 'samples': 10297536, 'steps': 53632, 'loss/train': 1.1987769603729248} 08/30/2021 22:53:12 - INFO - __main__ - Step 53634: {'lr': 0.0003642865435767696, 'samples': 10297728, 'steps': 53633, 'loss/train': 2.458717107772827} 08/30/2021 22:53:12 - INFO - __main__ - Step 53635: {'lr': 0.00036428182377730407, 'samples': 10297920, 'steps': 53634, 'loss/train': 1.3919092416763306} 08/30/2021 22:53:13 - INFO - __main__ - Step 53636: {'lr': 0.00036427710392634483, 'samples': 10298112, 'steps': 53635, 'loss/train': 0.031980302184820175} 08/30/2021 22:53:15 - INFO - __main__ - Step 53637: {'lr': 0.0003642723840238942, 'samples': 10298304, 'steps': 53636, 'loss/train': 1.202775001525879} 08/30/2021 22:53:16 - INFO - __main__ - Step 53638: {'lr': 0.0003642676640699542, 'samples': 10298496, 'steps': 53637, 'loss/train': 1.4996012449264526} 08/30/2021 22:53:16 - INFO - __main__ - Step 53639: {'lr': 0.0003642629440645269, 'samples': 10298688, 'steps': 53638, 'loss/train': 1.7215982675552368} 08/30/2021 22:53:16 - INFO - __main__ - Step 53640: {'lr': 0.00036425822400761444, 'samples': 10298880, 'steps': 53639, 'loss/train': 1.4854384660720825} 08/30/2021 22:53:17 - INFO - __main__ - Step 53641: {'lr': 0.000364253503899219, 'samples': 10299072, 'steps': 53640, 'loss/train': 1.1110572814941406} 08/30/2021 22:53:18 - INFO - __main__ - Step 53642: {'lr': 0.00036424878373934275, 'samples': 10299264, 'steps': 53641, 'loss/train': 1.4678090810775757} 08/30/2021 22:53:19 - INFO - __main__ - Step 53643: {'lr': 0.0003642440635279877, 'samples': 10299456, 'steps': 53642, 'loss/train': 1.320936679840088} 08/30/2021 22:53:19 - INFO - __main__ - Step 53644: {'lr': 0.0003642393432651561, 'samples': 10299648, 'steps': 53643, 'loss/train': 2.0022051334381104} 08/30/2021 22:53:19 - INFO - __main__ - Step 53645: {'lr': 0.00036423462295085, 'samples': 10299840, 'steps': 53644, 'loss/train': 0.9051774740219116} 08/30/2021 22:53:20 - INFO - __main__ - Step 53646: {'lr': 0.00036422990258507155, 'samples': 10300032, 'steps': 53645, 'loss/train': 0.39250320196151733} 08/30/2021 22:53:21 - INFO - __main__ - Step 53647: {'lr': 0.00036422518216782285, 'samples': 10300224, 'steps': 53646, 'loss/train': 1.6496013402938843} 08/30/2021 22:53:22 - INFO - __main__ - Step 53648: {'lr': 0.00036422046169910604, 'samples': 10300416, 'steps': 53647, 'loss/train': 1.0909745693206787} 08/30/2021 22:53:22 - INFO - __main__ - Step 53649: {'lr': 0.00036421574117892323, 'samples': 10300608, 'steps': 53648, 'loss/train': 0.055397044867277145} 08/30/2021 22:53:23 - INFO - __main__ - Step 53650: {'lr': 0.0003642110206072766, 'samples': 10300800, 'steps': 53649, 'loss/train': 0.6435099244117737} 08/30/2021 22:53:23 - INFO - __main__ - Step 53651: {'lr': 0.0003642062999841682, 'samples': 10300992, 'steps': 53650, 'loss/train': 1.5886059999465942} 08/30/2021 22:53:24 - INFO - __main__ - Step 53652: {'lr': 0.00036420157930960027, 'samples': 10301184, 'steps': 53651, 'loss/train': 0.5165435075759888} 08/30/2021 22:53:25 - INFO - __main__ - Step 53653: {'lr': 0.00036419685858357485, 'samples': 10301376, 'steps': 53652, 'loss/train': 1.1679151058197021} 08/30/2021 22:53:25 - INFO - __main__ - Step 53654: {'lr': 0.0003641921378060941, 'samples': 10301568, 'steps': 53653, 'loss/train': 1.5994067192077637} 08/30/2021 22:53:25 - INFO - __main__ - Step 53655: {'lr': 0.00036418741697716013, 'samples': 10301760, 'steps': 53654, 'loss/train': 0.8237423896789551} 08/30/2021 22:53:26 - INFO - __main__ - Step 53656: {'lr': 0.00036418269609677506, 'samples': 10301952, 'steps': 53655, 'loss/train': 1.3924806118011475} 08/30/2021 22:53:27 - INFO - __main__ - Step 53657: {'lr': 0.000364177975164941, 'samples': 10302144, 'steps': 53656, 'loss/train': 0.8165030479431152} 08/30/2021 22:53:28 - INFO - __main__ - Step 53658: {'lr': 0.0003641732541816601, 'samples': 10302336, 'steps': 53657, 'loss/train': 1.3477058410644531} 08/30/2021 22:53:28 - INFO - __main__ - Step 53659: {'lr': 0.0003641685331469346, 'samples': 10302528, 'steps': 53658, 'loss/train': 1.491005539894104} 08/30/2021 22:53:28 - INFO - __main__ - Step 53660: {'lr': 0.0003641638120607665, 'samples': 10302720, 'steps': 53659, 'loss/train': 1.7326476573944092} 08/30/2021 22:53:29 - INFO - __main__ - Step 53661: {'lr': 0.00036415909092315786, 'samples': 10302912, 'steps': 53660, 'loss/train': 0.343622624874115} 08/30/2021 22:53:29 - INFO - __main__ - Step 53662: {'lr': 0.00036415436973411095, 'samples': 10303104, 'steps': 53661, 'loss/train': 1.4072625637054443} 08/30/2021 22:53:31 - INFO - __main__ - Step 53663: {'lr': 0.0003641496484936278, 'samples': 10303296, 'steps': 53662, 'loss/train': 0.9885417819023132} 08/30/2021 22:53:31 - INFO - __main__ - Step 53664: {'lr': 0.0003641449272017106, 'samples': 10303488, 'steps': 53663, 'loss/train': 0.91515052318573} 08/30/2021 22:53:32 - INFO - __main__ - Step 53665: {'lr': 0.00036414020585836144, 'samples': 10303680, 'steps': 53664, 'loss/train': 1.0116825103759766} 08/30/2021 22:53:32 - INFO - __main__ - Step 53666: {'lr': 0.00036413548446358255, 'samples': 10303872, 'steps': 53665, 'loss/train': 0.559353232383728} 08/30/2021 22:53:32 - INFO - __main__ - Step 53667: {'lr': 0.0003641307630173759, 'samples': 10304064, 'steps': 53666, 'loss/train': 1.0364325046539307} 08/30/2021 22:53:34 - INFO - __main__ - Step 53668: {'lr': 0.0003641260415197437, 'samples': 10304256, 'steps': 53667, 'loss/train': 1.8374452590942383} 08/30/2021 22:53:34 - INFO - __main__ - Step 53669: {'lr': 0.0003641213199706881, 'samples': 10304448, 'steps': 53668, 'loss/train': 1.1233552694320679} 08/30/2021 22:53:35 - INFO - __main__ - Step 53670: {'lr': 0.0003641165983702111, 'samples': 10304640, 'steps': 53669, 'loss/train': 1.882941722869873} 08/30/2021 22:53:35 - INFO - __main__ - Step 53671: {'lr': 0.000364111876718315, 'samples': 10304832, 'steps': 53670, 'loss/train': 0.7725663185119629} 08/30/2021 22:53:36 - INFO - __main__ - Step 53672: {'lr': 0.0003641071550150019, 'samples': 10305024, 'steps': 53671, 'loss/train': 0.8464277386665344} 08/30/2021 22:53:36 - INFO - __main__ - Step 53673: {'lr': 0.00036410243326027373, 'samples': 10305216, 'steps': 53672, 'loss/train': 1.7000603675842285} 08/30/2021 22:53:38 - INFO - __main__ - Step 53674: {'lr': 0.0003640977114541328, 'samples': 10305408, 'steps': 53673, 'loss/train': 1.5568926334381104} 08/30/2021 22:53:38 - INFO - __main__ - Step 53675: {'lr': 0.0003640929895965813, 'samples': 10305600, 'steps': 53674, 'loss/train': 0.826578676700592} 08/30/2021 22:53:39 - INFO - __main__ - Step 53676: {'lr': 0.0003640882676876212, 'samples': 10305792, 'steps': 53675, 'loss/train': 1.554081678390503} 08/30/2021 22:53:39 - INFO - __main__ - Step 53677: {'lr': 0.0003640835457272547, 'samples': 10305984, 'steps': 53676, 'loss/train': 1.6683779954910278} 08/30/2021 22:53:39 - INFO - __main__ - Step 53678: {'lr': 0.00036407882371548394, 'samples': 10306176, 'steps': 53677, 'loss/train': 1.8408193588256836} 08/30/2021 22:53:41 - INFO - __main__ - Step 53679: {'lr': 0.00036407410165231096, 'samples': 10306368, 'steps': 53678, 'loss/train': 0.4423947334289551} 08/30/2021 22:53:41 - INFO - __main__ - Step 53680: {'lr': 0.000364069379537738, 'samples': 10306560, 'steps': 53679, 'loss/train': 1.6478915214538574} 08/30/2021 22:53:42 - INFO - __main__ - Step 53681: {'lr': 0.0003640646573717671, 'samples': 10306752, 'steps': 53680, 'loss/train': 1.6639094352722168} 08/30/2021 22:53:42 - INFO - __main__ - Step 53682: {'lr': 0.00036405993515440044, 'samples': 10306944, 'steps': 53681, 'loss/train': 0.8151056170463562} 08/30/2021 22:53:42 - INFO - __main__ - Step 53683: {'lr': 0.0003640552128856401, 'samples': 10307136, 'steps': 53682, 'loss/train': 1.445812702178955} 08/30/2021 22:53:44 - INFO - __main__ - Step 53684: {'lr': 0.00036405049056548834, 'samples': 10307328, 'steps': 53683, 'loss/train': 1.7645049095153809} 08/30/2021 22:53:45 - INFO - __main__ - Step 53685: {'lr': 0.0003640457681939471, 'samples': 10307520, 'steps': 53684, 'loss/train': 1.2873436212539673} 08/30/2021 22:53:45 - INFO - __main__ - Step 53686: {'lr': 0.0003640410457710186, 'samples': 10307712, 'steps': 53685, 'loss/train': 1.4765723943710327} 08/30/2021 22:53:45 - INFO - __main__ - Step 53687: {'lr': 0.000364036323296705, 'samples': 10307904, 'steps': 53686, 'loss/train': 1.4670441150665283} 08/30/2021 22:53:46 - INFO - __main__ - Step 53688: {'lr': 0.0003640316007710084, 'samples': 10308096, 'steps': 53687, 'loss/train': 1.1963099241256714} 08/30/2021 22:53:46 - INFO - __main__ - Step 53689: {'lr': 0.0003640268781939309, 'samples': 10308288, 'steps': 53688, 'loss/train': 1.2051911354064941} 08/30/2021 22:53:48 - INFO - __main__ - Step 53690: {'lr': 0.0003640221555654747, 'samples': 10308480, 'steps': 53689, 'loss/train': 0.9849037528038025} 08/30/2021 22:53:48 - INFO - __main__ - Step 53691: {'lr': 0.0003640174328856418, 'samples': 10308672, 'steps': 53690, 'loss/train': 1.4371440410614014} 08/30/2021 22:53:48 - INFO - __main__ - Step 53692: {'lr': 0.0003640127101544344, 'samples': 10308864, 'steps': 53691, 'loss/train': 1.3826385736465454} 08/30/2021 22:53:49 - INFO - __main__ - Step 53693: {'lr': 0.00036400798737185465, 'samples': 10309056, 'steps': 53692, 'loss/train': 1.2004871368408203} 08/30/2021 22:53:49 - INFO - __main__ - Step 53694: {'lr': 0.0003640032645379047, 'samples': 10309248, 'steps': 53693, 'loss/train': 0.4266481399536133} 08/30/2021 22:53:51 - INFO - __main__ - Step 53695: {'lr': 0.0003639985416525866, 'samples': 10309440, 'steps': 53694, 'loss/train': 1.4924750328063965} 08/30/2021 22:53:52 - INFO - __main__ - Step 53696: {'lr': 0.00036399381871590254, 'samples': 10309632, 'steps': 53695, 'loss/train': 0.5292871594429016} 08/30/2021 22:53:52 - INFO - __main__ - Step 53697: {'lr': 0.0003639890957278546, 'samples': 10309824, 'steps': 53696, 'loss/train': 1.360403060913086} 08/30/2021 22:53:52 - INFO - __main__ - Step 53698: {'lr': 0.0003639843726884449, 'samples': 10310016, 'steps': 53697, 'loss/train': 1.595663070678711} 08/30/2021 22:53:53 - INFO - __main__ - Step 53699: {'lr': 0.0003639796495976757, 'samples': 10310208, 'steps': 53698, 'loss/train': 1.8290520906448364} 08/30/2021 22:53:55 - INFO - __main__ - Step 53700: {'lr': 0.000363974926455549, 'samples': 10310400, 'steps': 53699, 'loss/train': 1.1834489107131958} 08/30/2021 22:53:55 - INFO - __main__ - Step 53701: {'lr': 0.0003639702032620669, 'samples': 10310592, 'steps': 53700, 'loss/train': 1.1344308853149414} 08/30/2021 22:53:55 - INFO - __main__ - Step 53702: {'lr': 0.00036396548001723164, 'samples': 10310784, 'steps': 53701, 'loss/train': 1.1612474918365479} 08/30/2021 22:53:56 - INFO - __main__ - Step 53703: {'lr': 0.00036396075672104523, 'samples': 10310976, 'steps': 53702, 'loss/train': 1.5016802549362183} 08/30/2021 22:53:56 - INFO - __main__ - Step 53704: {'lr': 0.00036395603337350987, 'samples': 10311168, 'steps': 53703, 'loss/train': 0.2191607803106308} 08/30/2021 22:53:58 - INFO - __main__ - Step 53705: {'lr': 0.0003639513099746277, 'samples': 10311360, 'steps': 53704, 'loss/train': 1.7161669731140137} 08/30/2021 22:53:58 - INFO - __main__ - Step 53706: {'lr': 0.0003639465865244008, 'samples': 10311552, 'steps': 53705, 'loss/train': 0.9623885750770569} 08/30/2021 22:53:59 - INFO - __main__ - Step 53707: {'lr': 0.0003639418630228314, 'samples': 10311744, 'steps': 53706, 'loss/train': 0.3749837279319763} 08/30/2021 22:53:59 - INFO - __main__ - Step 53708: {'lr': 0.00036393713946992156, 'samples': 10311936, 'steps': 53707, 'loss/train': 1.331856369972229} 08/30/2021 22:53:59 - INFO - __main__ - Step 53709: {'lr': 0.0003639324158656733, 'samples': 10312128, 'steps': 53708, 'loss/train': 1.3522496223449707} 08/30/2021 22:54:01 - INFO - __main__ - Step 53710: {'lr': 0.00036392769221008895, 'samples': 10312320, 'steps': 53709, 'loss/train': 1.4969886541366577} 08/30/2021 22:54:02 - INFO - __main__ - Step 53711: {'lr': 0.0003639229685031705, 'samples': 10312512, 'steps': 53710, 'loss/train': 1.0851818323135376} 08/30/2021 22:54:02 - INFO - __main__ - Step 53712: {'lr': 0.0003639182447449201, 'samples': 10312704, 'steps': 53711, 'loss/train': 1.4043091535568237} 08/30/2021 22:54:02 - INFO - __main__ - Step 53713: {'lr': 0.00036391352093533995, 'samples': 10312896, 'steps': 53712, 'loss/train': 1.6672462224960327} 08/30/2021 22:54:03 - INFO - __main__ - Step 53714: {'lr': 0.0003639087970744321, 'samples': 10313088, 'steps': 53713, 'loss/train': 1.19981050491333} 08/30/2021 22:54:03 - INFO - __main__ - Step 53715: {'lr': 0.00036390407316219865, 'samples': 10313280, 'steps': 53714, 'loss/train': 1.2523813247680664} 08/30/2021 22:54:04 - INFO - __main__ - Step 53716: {'lr': 0.0003638993491986419, 'samples': 10313472, 'steps': 53715, 'loss/train': 1.0711724758148193} 08/30/2021 22:54:05 - INFO - __main__ - Step 53717: {'lr': 0.0003638946251837637, 'samples': 10313664, 'steps': 53716, 'loss/train': 0.2546384632587433} 08/30/2021 22:54:05 - INFO - __main__ - Step 53718: {'lr': 0.0003638899011175664, 'samples': 10313856, 'steps': 53717, 'loss/train': 1.007988452911377} 08/30/2021 22:54:06 - INFO - __main__ - Step 53719: {'lr': 0.00036388517700005214, 'samples': 10314048, 'steps': 53718, 'loss/train': 2.3122098445892334} 08/30/2021 22:54:06 - INFO - __main__ - Step 53720: {'lr': 0.00036388045283122295, 'samples': 10314240, 'steps': 53719, 'loss/train': 1.3735408782958984} 08/30/2021 22:54:07 - INFO - __main__ - Step 53721: {'lr': 0.00036387572861108097, 'samples': 10314432, 'steps': 53720, 'loss/train': 1.0783125162124634} 08/30/2021 22:54:08 - INFO - __main__ - Step 53722: {'lr': 0.0003638710043396283, 'samples': 10314624, 'steps': 53721, 'loss/train': 1.3310192823410034} 08/30/2021 22:54:08 - INFO - __main__ - Step 53723: {'lr': 0.0003638662800168672, 'samples': 10314816, 'steps': 53722, 'loss/train': 1.37336003780365} 08/30/2021 22:54:09 - INFO - __main__ - Step 53724: {'lr': 0.00036386155564279967, 'samples': 10315008, 'steps': 53723, 'loss/train': 1.2942947149276733} 08/30/2021 22:54:09 - INFO - __main__ - Step 53725: {'lr': 0.00036385683121742786, 'samples': 10315200, 'steps': 53724, 'loss/train': 1.5524836778640747} 08/30/2021 22:54:11 - INFO - __main__ - Step 53726: {'lr': 0.00036385210674075394, 'samples': 10315392, 'steps': 53725, 'loss/train': 1.1527496576309204} 08/30/2021 22:54:11 - INFO - __main__ - Step 53727: {'lr': 0.00036384738221278, 'samples': 10315584, 'steps': 53726, 'loss/train': 0.9081522822380066} 08/30/2021 22:54:11 - INFO - __main__ - Step 53728: {'lr': 0.0003638426576335082, 'samples': 10315776, 'steps': 53727, 'loss/train': 1.3712269067764282} 08/30/2021 22:54:12 - INFO - __main__ - Step 53729: {'lr': 0.00036383793300294063, 'samples': 10315968, 'steps': 53728, 'loss/train': 1.0714738368988037} 08/30/2021 22:54:12 - INFO - __main__ - Step 53730: {'lr': 0.00036383320832107945, 'samples': 10316160, 'steps': 53729, 'loss/train': 0.9009466171264648} 08/30/2021 22:54:14 - INFO - __main__ - Step 53731: {'lr': 0.0003638284835879268, 'samples': 10316352, 'steps': 53730, 'loss/train': 1.203413963317871} 08/30/2021 22:54:14 - INFO - __main__ - Step 53732: {'lr': 0.0003638237588034848, 'samples': 10316544, 'steps': 53731, 'loss/train': 1.6881147623062134} 08/30/2021 22:54:14 - INFO - __main__ - Step 53733: {'lr': 0.00036381903396775556, 'samples': 10316736, 'steps': 53732, 'loss/train': 1.3158241510391235} 08/30/2021 22:54:15 - INFO - __main__ - Step 53734: {'lr': 0.00036381430908074126, 'samples': 10316928, 'steps': 53733, 'loss/train': 1.3051568269729614} 08/30/2021 22:54:15 - INFO - __main__ - Step 53735: {'lr': 0.00036380958414244393, 'samples': 10317120, 'steps': 53734, 'loss/train': 1.6689780950546265} 08/30/2021 22:54:16 - INFO - __main__ - Step 53736: {'lr': 0.0003638048591528658, 'samples': 10317312, 'steps': 53735, 'loss/train': 1.6852327585220337} 08/30/2021 22:54:17 - INFO - __main__ - Step 53737: {'lr': 0.0003638001341120089, 'samples': 10317504, 'steps': 53736, 'loss/train': 1.3018109798431396} 08/30/2021 22:54:17 - INFO - __main__ - Step 53738: {'lr': 0.00036379540901987546, 'samples': 10317696, 'steps': 53737, 'loss/train': 1.543308138847351} 08/30/2021 22:54:18 - INFO - __main__ - Step 53739: {'lr': 0.0003637906838764675, 'samples': 10317888, 'steps': 53738, 'loss/train': 1.4458061456680298} 08/30/2021 22:54:18 - INFO - __main__ - Step 53740: {'lr': 0.00036378595868178737, 'samples': 10318080, 'steps': 53739, 'loss/train': 1.2234148979187012} 08/30/2021 22:54:18 - INFO - __main__ - Step 53741: {'lr': 0.00036378123343583694, 'samples': 10318272, 'steps': 53740, 'loss/train': 1.3705779314041138} 08/30/2021 22:54:20 - INFO - __main__ - Step 53742: {'lr': 0.0003637765081386184, 'samples': 10318464, 'steps': 53741, 'loss/train': 1.3987308740615845} 08/30/2021 22:54:20 - INFO - __main__ - Step 53743: {'lr': 0.000363771782790134, 'samples': 10318656, 'steps': 53742, 'loss/train': 1.2078702449798584} 08/30/2021 22:54:21 - INFO - __main__ - Step 53744: {'lr': 0.0003637670573903857, 'samples': 10318848, 'steps': 53743, 'loss/train': 1.135398030281067} 08/30/2021 22:54:21 - INFO - __main__ - Step 53745: {'lr': 0.0003637623319393758, 'samples': 10319040, 'steps': 53744, 'loss/train': 1.2414087057113647} 08/30/2021 22:54:21 - INFO - __main__ - Step 53746: {'lr': 0.0003637576064371063, 'samples': 10319232, 'steps': 53745, 'loss/train': 1.2687788009643555} 08/30/2021 22:54:23 - INFO - __main__ - Step 53747: {'lr': 0.0003637528808835794, 'samples': 10319424, 'steps': 53746, 'loss/train': 1.3661324977874756} 08/30/2021 22:54:24 - INFO - __main__ - Step 53748: {'lr': 0.00036374815527879725, 'samples': 10319616, 'steps': 53747, 'loss/train': 1.5377265214920044} 08/30/2021 22:54:24 - INFO - __main__ - Step 53749: {'lr': 0.0003637434296227619, 'samples': 10319808, 'steps': 53748, 'loss/train': 1.4059460163116455} 08/30/2021 22:54:25 - INFO - __main__ - Step 53750: {'lr': 0.0003637387039154755, 'samples': 10320000, 'steps': 53749, 'loss/train': 1.0428352355957031} 08/30/2021 22:54:25 - INFO - __main__ - Step 53751: {'lr': 0.0003637339781569402, 'samples': 10320192, 'steps': 53750, 'loss/train': 1.9516690969467163} 08/30/2021 22:54:27 - INFO - __main__ - Step 53752: {'lr': 0.0003637292523471581, 'samples': 10320384, 'steps': 53751, 'loss/train': 1.1140462160110474} 08/30/2021 22:54:27 - INFO - __main__ - Step 53753: {'lr': 0.0003637245264861314, 'samples': 10320576, 'steps': 53752, 'loss/train': 1.531790018081665} 08/30/2021 22:54:27 - INFO - __main__ - Step 53754: {'lr': 0.0003637198005738622, 'samples': 10320768, 'steps': 53753, 'loss/train': 0.9442309141159058} 08/30/2021 22:54:28 - INFO - __main__ - Step 53755: {'lr': 0.0003637150746103526, 'samples': 10320960, 'steps': 53754, 'loss/train': 1.8018577098846436} 08/30/2021 22:54:28 - INFO - __main__ - Step 53756: {'lr': 0.0003637103485956047, 'samples': 10321152, 'steps': 53755, 'loss/train': 0.9417364597320557} 08/30/2021 22:54:30 - INFO - __main__ - Step 53757: {'lr': 0.0003637056225296207, 'samples': 10321344, 'steps': 53756, 'loss/train': 0.40262842178344727} 08/30/2021 22:54:30 - INFO - __main__ - Step 53758: {'lr': 0.00036370089641240264, 'samples': 10321536, 'steps': 53757, 'loss/train': 1.619067907333374} 08/30/2021 22:54:30 - INFO - __main__ - Step 53759: {'lr': 0.0003636961702439527, 'samples': 10321728, 'steps': 53758, 'loss/train': 0.3672869801521301} 08/30/2021 22:54:31 - INFO - __main__ - Step 53760: {'lr': 0.0003636914440242732, 'samples': 10321920, 'steps': 53759, 'loss/train': 1.1589772701263428} 08/30/2021 22:54:31 - INFO - __main__ - Step 53761: {'lr': 0.00036368671775336597, 'samples': 10322112, 'steps': 53760, 'loss/train': 1.4277900457382202} 08/30/2021 22:54:33 - INFO - __main__ - Step 53762: {'lr': 0.00036368199143123326, 'samples': 10322304, 'steps': 53761, 'loss/train': 1.608929991722107} 08/30/2021 22:54:33 - INFO - __main__ - Step 53763: {'lr': 0.0003636772650578772, 'samples': 10322496, 'steps': 53762, 'loss/train': 1.774794578552246} 08/30/2021 22:54:33 - INFO - __main__ - Step 53764: {'lr': 0.0003636725386332999, 'samples': 10322688, 'steps': 53763, 'loss/train': 1.3371376991271973} 08/30/2021 22:54:34 - INFO - __main__ - Step 53765: {'lr': 0.00036366781215750355, 'samples': 10322880, 'steps': 53764, 'loss/train': 0.15669012069702148} 08/30/2021 22:54:34 - INFO - __main__ - Step 53766: {'lr': 0.0003636630856304902, 'samples': 10323072, 'steps': 53765, 'loss/train': 1.6438034772872925} 08/30/2021 22:54:34 - INFO - __main__ - Step 53767: {'lr': 0.0003636583590522621, 'samples': 10323264, 'steps': 53766, 'loss/train': 1.8038415908813477} 08/30/2021 22:54:36 - INFO - __main__ - Step 53768: {'lr': 0.00036365363242282117, 'samples': 10323456, 'steps': 53767, 'loss/train': 0.9586418271064758} 08/30/2021 22:54:36 - INFO - __main__ - Step 53769: {'lr': 0.00036364890574216974, 'samples': 10323648, 'steps': 53768, 'loss/train': 1.5184835195541382} 08/30/2021 22:54:37 - INFO - __main__ - Step 53770: {'lr': 0.0003636441790103098, 'samples': 10323840, 'steps': 53769, 'loss/train': 0.9286397695541382} 08/30/2021 22:54:37 - INFO - __main__ - Step 53771: {'lr': 0.00036363945222724363, 'samples': 10324032, 'steps': 53770, 'loss/train': 0.04186157509684563} 08/30/2021 22:54:37 - INFO - __main__ - Step 53772: {'lr': 0.0003636347253929733, 'samples': 10324224, 'steps': 53771, 'loss/train': 1.4541516304016113} 08/30/2021 22:54:39 - INFO - __main__ - Step 53773: {'lr': 0.0003636299985075008, 'samples': 10324416, 'steps': 53772, 'loss/train': 1.3696902990341187} 08/30/2021 22:54:40 - INFO - __main__ - Step 53774: {'lr': 0.00036362527157082845, 'samples': 10324608, 'steps': 53773, 'loss/train': 0.9283785223960876} 08/30/2021 22:54:40 - INFO - __main__ - Step 53775: {'lr': 0.00036362054458295836, 'samples': 10324800, 'steps': 53774, 'loss/train': 4.218986988067627} 08/30/2021 22:54:40 - INFO - __main__ - Step 53776: {'lr': 0.0003636158175438925, 'samples': 10324992, 'steps': 53775, 'loss/train': 1.4279903173446655} 08/30/2021 22:54:41 - INFO - __main__ - Step 53777: {'lr': 0.00036361109045363315, 'samples': 10325184, 'steps': 53776, 'loss/train': 0.647429347038269} 08/30/2021 22:54:42 - INFO - __main__ - Step 53778: {'lr': 0.0003636063633121824, 'samples': 10325376, 'steps': 53777, 'loss/train': 1.633341670036316} 08/30/2021 22:54:43 - INFO - __main__ - Step 53779: {'lr': 0.0003636016361195423, 'samples': 10325568, 'steps': 53778, 'loss/train': 1.1774834394454956} 08/30/2021 22:54:43 - INFO - __main__ - Step 53780: {'lr': 0.0003635969088757152, 'samples': 10325760, 'steps': 53779, 'loss/train': 1.7628194093704224} 08/30/2021 22:54:43 - INFO - __main__ - Step 53781: {'lr': 0.000363592181580703, 'samples': 10325952, 'steps': 53780, 'loss/train': 1.734178066253662} 08/30/2021 22:54:44 - INFO - __main__ - Step 53782: {'lr': 0.00036358745423450793, 'samples': 10326144, 'steps': 53781, 'loss/train': 1.1131432056427002} 08/30/2021 22:54:45 - INFO - __main__ - Step 53783: {'lr': 0.00036358272683713214, 'samples': 10326336, 'steps': 53782, 'loss/train': 0.9000319242477417} 08/30/2021 22:54:46 - INFO - __main__ - Step 53784: {'lr': 0.00036357799938857766, 'samples': 10326528, 'steps': 53783, 'loss/train': 1.101102352142334} 08/30/2021 22:54:46 - INFO - __main__ - Step 53785: {'lr': 0.0003635732718888467, 'samples': 10326720, 'steps': 53784, 'loss/train': 1.3329943418502808} 08/30/2021 22:54:46 - INFO - __main__ - Step 53786: {'lr': 0.0003635685443379414, 'samples': 10326912, 'steps': 53785, 'loss/train': 1.4994231462478638} 08/30/2021 22:54:47 - INFO - __main__ - Step 53787: {'lr': 0.0003635638167358639, 'samples': 10327104, 'steps': 53786, 'loss/train': 1.1487504243850708} 08/30/2021 22:54:48 - INFO - __main__ - Step 53788: {'lr': 0.00036355908908261624, 'samples': 10327296, 'steps': 53787, 'loss/train': 1.141757607460022} 08/30/2021 22:54:49 - INFO - __main__ - Step 53789: {'lr': 0.0003635543613782006, 'samples': 10327488, 'steps': 53788, 'loss/train': 1.693282961845398} 08/30/2021 22:54:49 - INFO - __main__ - Step 53790: {'lr': 0.0003635496336226192, 'samples': 10327680, 'steps': 53789, 'loss/train': 1.257690668106079} 08/30/2021 22:54:49 - INFO - __main__ - Step 53791: {'lr': 0.00036354490581587396, 'samples': 10327872, 'steps': 53790, 'loss/train': 1.3951411247253418} 08/30/2021 22:54:50 - INFO - __main__ - Step 53792: {'lr': 0.0003635401779579672, 'samples': 10328064, 'steps': 53791, 'loss/train': 1.1577696800231934} 08/30/2021 22:54:50 - INFO - __main__ - Step 53793: {'lr': 0.000363535450048901, 'samples': 10328256, 'steps': 53792, 'loss/train': 1.5145190954208374} 08/30/2021 22:54:52 - INFO - __main__ - Step 53794: {'lr': 0.00036353072208867746, 'samples': 10328448, 'steps': 53793, 'loss/train': 1.4275929927825928} 08/30/2021 22:54:52 - INFO - __main__ - Step 53795: {'lr': 0.00036352599407729873, 'samples': 10328640, 'steps': 53794, 'loss/train': 0.7977818846702576} 08/30/2021 22:54:53 - INFO - __main__ - Step 53796: {'lr': 0.00036352126601476697, 'samples': 10328832, 'steps': 53795, 'loss/train': 1.3475801944732666} 08/30/2021 22:54:53 - INFO - __main__ - Step 53797: {'lr': 0.0003635165379010842, 'samples': 10329024, 'steps': 53796, 'loss/train': 0.8868166208267212} 08/30/2021 22:54:53 - INFO - __main__ - Step 53798: {'lr': 0.0003635118097362528, 'samples': 10329216, 'steps': 53797, 'loss/train': 1.4683239459991455} 08/30/2021 22:54:56 - INFO - __main__ - Step 53799: {'lr': 0.0003635070815202746, 'samples': 10329408, 'steps': 53798, 'loss/train': 1.843313455581665} 08/30/2021 22:54:56 - INFO - __main__ - Step 53800: {'lr': 0.0003635023532531518, 'samples': 10329600, 'steps': 53799, 'loss/train': 1.0365461111068726} 08/30/2021 22:54:57 - INFO - __main__ - Step 53801: {'lr': 0.00036349762493488667, 'samples': 10329792, 'steps': 53800, 'loss/train': 1.181510090827942} 08/30/2021 22:54:57 - INFO - __main__ - Step 53802: {'lr': 0.0003634928965654813, 'samples': 10329984, 'steps': 53801, 'loss/train': 1.5654984712600708} 08/30/2021 22:54:57 - INFO - __main__ - Step 53803: {'lr': 0.0003634881681449377, 'samples': 10330176, 'steps': 53802, 'loss/train': 1.6878654956817627} 08/30/2021 22:54:58 - INFO - __main__ - Step 53804: {'lr': 0.00036348343967325814, 'samples': 10330368, 'steps': 53803, 'loss/train': 1.4503865242004395} 08/30/2021 22:55:00 - INFO - __main__ - Step 53805: {'lr': 0.00036347871115044466, 'samples': 10330560, 'steps': 53804, 'loss/train': 0.06338923424482346} 08/30/2021 22:55:00 - INFO - __main__ - Step 53806: {'lr': 0.0003634739825764995, 'samples': 10330752, 'steps': 53805, 'loss/train': 1.5886942148208618} 08/30/2021 22:55:01 - INFO - __main__ - Step 53807: {'lr': 0.00036346925395142467, 'samples': 10330944, 'steps': 53806, 'loss/train': 0.026798652485013008} 08/30/2021 22:55:01 - INFO - __main__ - Step 53808: {'lr': 0.00036346452527522233, 'samples': 10331136, 'steps': 53807, 'loss/train': 1.2169519662857056} 08/30/2021 22:55:01 - INFO - __main__ - Step 53809: {'lr': 0.0003634597965478946, 'samples': 10331328, 'steps': 53808, 'loss/train': 1.4164702892303467} 08/30/2021 22:55:02 - INFO - __main__ - Step 53810: {'lr': 0.00036345506776944364, 'samples': 10331520, 'steps': 53809, 'loss/train': 1.6290335655212402} 08/30/2021 22:55:03 - INFO - __main__ - Step 53811: {'lr': 0.00036345033893987164, 'samples': 10331712, 'steps': 53810, 'loss/train': 1.6554316282272339} 08/30/2021 22:55:03 - INFO - __main__ - Step 53812: {'lr': 0.00036344561005918064, 'samples': 10331904, 'steps': 53811, 'loss/train': 0.05251317471265793} 08/30/2021 22:55:04 - INFO - __main__ - Step 53813: {'lr': 0.00036344088112737276, 'samples': 10332096, 'steps': 53812, 'loss/train': 1.0993233919143677} 08/30/2021 22:55:04 - INFO - __main__ - Step 53814: {'lr': 0.0003634361521444502, 'samples': 10332288, 'steps': 53813, 'loss/train': 1.4712518453598022} 08/30/2021 22:55:04 - INFO - __main__ - Step 53815: {'lr': 0.00036343142311041503, 'samples': 10332480, 'steps': 53814, 'loss/train': 1.4359511137008667} 08/30/2021 22:55:06 - INFO - __main__ - Step 53816: {'lr': 0.00036342669402526946, 'samples': 10332672, 'steps': 53815, 'loss/train': 1.2964413166046143} 08/30/2021 22:55:06 - INFO - __main__ - Step 53817: {'lr': 0.0003634219648890156, 'samples': 10332864, 'steps': 53816, 'loss/train': 0.898953914642334} 08/30/2021 22:55:07 - INFO - __main__ - Step 53818: {'lr': 0.00036341723570165545, 'samples': 10333056, 'steps': 53817, 'loss/train': 0.24019961059093475} 08/30/2021 22:55:07 - INFO - __main__ - Step 53819: {'lr': 0.0003634125064631913, 'samples': 10333248, 'steps': 53818, 'loss/train': 1.1429471969604492} 08/30/2021 22:55:07 - INFO - __main__ - Step 53820: {'lr': 0.0003634077771736252, 'samples': 10333440, 'steps': 53819, 'loss/train': 1.3382513523101807} 08/30/2021 22:55:09 - INFO - __main__ - Step 53821: {'lr': 0.00036340304783295937, 'samples': 10333632, 'steps': 53820, 'loss/train': 1.240190029144287} 08/30/2021 22:55:09 - INFO - __main__ - Step 53822: {'lr': 0.0003633983184411958, 'samples': 10333824, 'steps': 53821, 'loss/train': 1.386380672454834} 08/30/2021 22:55:10 - INFO - __main__ - Step 53823: {'lr': 0.00036339358899833675, 'samples': 10334016, 'steps': 53822, 'loss/train': 1.5180798768997192} 08/30/2021 22:55:10 - INFO - __main__ - Step 53824: {'lr': 0.00036338885950438425, 'samples': 10334208, 'steps': 53823, 'loss/train': 1.8599827289581299} 08/30/2021 22:55:10 - INFO - __main__ - Step 53825: {'lr': 0.00036338412995934056, 'samples': 10334400, 'steps': 53824, 'loss/train': 1.0703608989715576} 08/30/2021 22:55:11 - INFO - __main__ - Step 53826: {'lr': 0.00036337940036320764, 'samples': 10334592, 'steps': 53825, 'loss/train': 1.29691481590271} 08/30/2021 22:55:12 - INFO - __main__ - Step 53827: {'lr': 0.0003633746707159877, 'samples': 10334784, 'steps': 53826, 'loss/train': 1.7954680919647217} 08/30/2021 22:55:13 - INFO - __main__ - Step 53828: {'lr': 0.00036336994101768304, 'samples': 10334976, 'steps': 53827, 'loss/train': 1.0407906770706177} 08/30/2021 22:55:13 - INFO - __main__ - Step 53829: {'lr': 0.00036336521126829554, 'samples': 10335168, 'steps': 53828, 'loss/train': 1.5656089782714844} 08/30/2021 22:55:14 - INFO - __main__ - Step 53830: {'lr': 0.00036336048146782743, 'samples': 10335360, 'steps': 53829, 'loss/train': 1.61233651638031} 08/30/2021 22:55:14 - INFO - __main__ - Step 53831: {'lr': 0.00036335575161628076, 'samples': 10335552, 'steps': 53830, 'loss/train': 1.5402565002441406} 08/30/2021 22:55:16 - INFO - __main__ - Step 53832: {'lr': 0.0003633510217136578, 'samples': 10335744, 'steps': 53831, 'loss/train': 2.119866371154785} 08/30/2021 22:55:16 - INFO - __main__ - Step 53833: {'lr': 0.0003633462917599606, 'samples': 10335936, 'steps': 53832, 'loss/train': 0.0717109814286232} 08/30/2021 22:55:16 - INFO - __main__ - Step 53834: {'lr': 0.0003633415617551914, 'samples': 10336128, 'steps': 53833, 'loss/train': 1.3708863258361816} 08/30/2021 22:55:17 - INFO - __main__ - Step 53835: {'lr': 0.0003633368316993521, 'samples': 10336320, 'steps': 53834, 'loss/train': 0.06664194911718369} 08/30/2021 22:55:17 - INFO - __main__ - Step 53836: {'lr': 0.0003633321015924451, 'samples': 10336512, 'steps': 53835, 'loss/train': 1.407045841217041} 08/30/2021 22:55:18 - INFO - __main__ - Step 53837: {'lr': 0.0003633273714344723, 'samples': 10336704, 'steps': 53836, 'loss/train': 1.3898102045059204} 08/30/2021 22:55:19 - INFO - __main__ - Step 53838: {'lr': 0.00036332264122543594, 'samples': 10336896, 'steps': 53837, 'loss/train': 1.17030668258667} 08/30/2021 22:55:19 - INFO - __main__ - Step 53839: {'lr': 0.00036331791096533815, 'samples': 10337088, 'steps': 53838, 'loss/train': 2.188324213027954} 08/30/2021 22:55:20 - INFO - __main__ - Step 53840: {'lr': 0.0003633131806541811, 'samples': 10337280, 'steps': 53839, 'loss/train': 2.024200439453125} 08/30/2021 22:55:20 - INFO - __main__ - Step 53841: {'lr': 0.000363308450291967, 'samples': 10337472, 'steps': 53840, 'loss/train': 1.4124239683151245} 08/30/2021 22:55:22 - INFO - __main__ - Step 53842: {'lr': 0.0003633037198786977, 'samples': 10337664, 'steps': 53841, 'loss/train': 1.634394884109497} 08/30/2021 22:55:22 - INFO - __main__ - Step 53843: {'lr': 0.0003632989894143755, 'samples': 10337856, 'steps': 53842, 'loss/train': 0.44994378089904785} 08/30/2021 22:55:22 - INFO - __main__ - Step 53844: {'lr': 0.0003632942588990025, 'samples': 10338048, 'steps': 53843, 'loss/train': 1.3941727876663208} 08/30/2021 22:55:23 - INFO - __main__ - Step 53845: {'lr': 0.00036328952833258096, 'samples': 10338240, 'steps': 53844, 'loss/train': 1.7511320114135742} 08/30/2021 22:55:23 - INFO - __main__ - Step 53846: {'lr': 0.0003632847977151128, 'samples': 10338432, 'steps': 53845, 'loss/train': 0.9932016730308533} 08/30/2021 22:55:25 - INFO - __main__ - Step 53847: {'lr': 0.0003632800670466003, 'samples': 10338624, 'steps': 53846, 'loss/train': 1.3834797143936157} 08/30/2021 22:55:25 - INFO - __main__ - Step 53848: {'lr': 0.0003632753363270456, 'samples': 10338816, 'steps': 53847, 'loss/train': 1.1966313123703003} 08/30/2021 22:55:26 - INFO - __main__ - Step 53849: {'lr': 0.00036327060555645075, 'samples': 10339008, 'steps': 53848, 'loss/train': 1.1063379049301147} 08/30/2021 22:55:26 - INFO - __main__ - Step 53850: {'lr': 0.0003632658747348179, 'samples': 10339200, 'steps': 53849, 'loss/train': 1.4359912872314453} 08/30/2021 22:55:26 - INFO - __main__ - Step 53851: {'lr': 0.0003632611438621492, 'samples': 10339392, 'steps': 53850, 'loss/train': 1.3796417713165283} 08/30/2021 22:55:27 - INFO - __main__ - Step 53852: {'lr': 0.00036325641293844674, 'samples': 10339584, 'steps': 53851, 'loss/train': 1.2238281965255737} 08/30/2021 22:55:28 - INFO - __main__ - Step 53853: {'lr': 0.0003632516819637127, 'samples': 10339776, 'steps': 53852, 'loss/train': 0.28428390622138977} 08/30/2021 22:55:29 - INFO - __main__ - Step 53854: {'lr': 0.0003632469509379492, 'samples': 10339968, 'steps': 53853, 'loss/train': 1.5513300895690918} 08/30/2021 22:55:29 - INFO - __main__ - Step 53855: {'lr': 0.00036324221986115847, 'samples': 10340160, 'steps': 53854, 'loss/train': 1.444474697113037} 08/30/2021 22:55:30 - INFO - __main__ - Step 53856: {'lr': 0.00036323748873334246, 'samples': 10340352, 'steps': 53855, 'loss/train': 0.8947063684463501} 08/30/2021 22:55:30 - INFO - __main__ - Step 53857: {'lr': 0.00036323275755450335, 'samples': 10340544, 'steps': 53856, 'loss/train': 0.8642876148223877} 08/30/2021 22:55:32 - INFO - __main__ - Step 53858: {'lr': 0.00036322802632464336, 'samples': 10340736, 'steps': 53857, 'loss/train': 0.17101213335990906} 08/30/2021 22:55:32 - INFO - __main__ - Step 53859: {'lr': 0.00036322329504376457, 'samples': 10340928, 'steps': 53858, 'loss/train': 1.3581503629684448} 08/30/2021 22:55:33 - INFO - __main__ - Step 53860: {'lr': 0.0003632185637118691, 'samples': 10341120, 'steps': 53859, 'loss/train': 1.2883199453353882} 08/30/2021 22:55:33 - INFO - __main__ - Step 53861: {'lr': 0.0003632138323289591, 'samples': 10341312, 'steps': 53860, 'loss/train': 1.0590550899505615} 08/30/2021 22:55:34 - INFO - __main__ - Step 53862: {'lr': 0.00036320910089503665, 'samples': 10341504, 'steps': 53861, 'loss/train': 0.952043354511261} 08/30/2021 22:55:35 - INFO - __main__ - Step 53863: {'lr': 0.00036320436941010396, 'samples': 10341696, 'steps': 53862, 'loss/train': 0.9984175562858582} 08/30/2021 22:55:35 - INFO - __main__ - Step 53864: {'lr': 0.00036319963787416313, 'samples': 10341888, 'steps': 53863, 'loss/train': 1.4564708471298218} 08/30/2021 22:55:36 - INFO - __main__ - Step 53865: {'lr': 0.0003631949062872163, 'samples': 10342080, 'steps': 53864, 'loss/train': 1.277030110359192} 08/30/2021 22:55:36 - INFO - __main__ - Step 53866: {'lr': 0.0003631901746492656, 'samples': 10342272, 'steps': 53865, 'loss/train': 0.8510956168174744} 08/30/2021 22:55:36 - INFO - __main__ - Step 53867: {'lr': 0.0003631854429603131, 'samples': 10342464, 'steps': 53866, 'loss/train': 0.8105121850967407} 08/30/2021 22:55:38 - INFO - __main__ - Step 53868: {'lr': 0.00036318071122036104, 'samples': 10342656, 'steps': 53867, 'loss/train': 1.434144377708435} 08/30/2021 22:55:38 - INFO - __main__ - Step 53869: {'lr': 0.0003631759794294115, 'samples': 10342848, 'steps': 53868, 'loss/train': 1.513204574584961} 08/30/2021 22:55:39 - INFO - __main__ - Step 53870: {'lr': 0.00036317124758746656, 'samples': 10343040, 'steps': 53869, 'loss/train': 0.8377476930618286} 08/30/2021 22:55:39 - INFO - __main__ - Step 53871: {'lr': 0.0003631665156945284, 'samples': 10343232, 'steps': 53870, 'loss/train': 1.0416661500930786} 08/30/2021 22:55:39 - INFO - __main__ - Step 53872: {'lr': 0.0003631617837505992, 'samples': 10343424, 'steps': 53871, 'loss/train': 1.3112215995788574} 08/30/2021 22:55:41 - INFO - __main__ - Step 53873: {'lr': 0.00036315705175568103, 'samples': 10343616, 'steps': 53872, 'loss/train': 1.3337771892547607} 08/30/2021 22:55:42 - INFO - __main__ - Step 53874: {'lr': 0.000363152319709776, 'samples': 10343808, 'steps': 53873, 'loss/train': 1.4580767154693604} 08/30/2021 22:55:42 - INFO - __main__ - Step 53875: {'lr': 0.00036314758761288643, 'samples': 10344000, 'steps': 53874, 'loss/train': 0.9202516674995422} 08/30/2021 22:55:42 - INFO - __main__ - Step 53876: {'lr': 0.00036314285546501415, 'samples': 10344192, 'steps': 53875, 'loss/train': 1.021802544593811} 08/30/2021 22:55:43 - INFO - __main__ - Step 53877: {'lr': 0.0003631381232661615, 'samples': 10344384, 'steps': 53876, 'loss/train': 0.9923377633094788} 08/30/2021 22:55:44 - INFO - __main__ - Step 53878: {'lr': 0.0003631333910163305, 'samples': 10344576, 'steps': 53877, 'loss/train': 1.2320740222930908} 08/30/2021 22:55:44 - INFO - __main__ - Step 53879: {'lr': 0.0003631286587155234, 'samples': 10344768, 'steps': 53878, 'loss/train': 1.076094627380371} 08/30/2021 22:55:45 - INFO - __main__ - Step 53880: {'lr': 0.00036312392636374225, 'samples': 10344960, 'steps': 53879, 'loss/train': 2.010040044784546} 08/30/2021 22:55:45 - INFO - __main__ - Step 53881: {'lr': 0.00036311919396098927, 'samples': 10345152, 'steps': 53880, 'loss/train': 0.6335082650184631} 08/30/2021 22:55:46 - INFO - __main__ - Step 53882: {'lr': 0.0003631144615072665, 'samples': 10345344, 'steps': 53881, 'loss/train': 1.3972604274749756} 08/30/2021 22:55:46 - INFO - __main__ - Step 53883: {'lr': 0.000363109729002576, 'samples': 10345536, 'steps': 53882, 'loss/train': 0.9202935099601746} 08/30/2021 22:55:47 - INFO - __main__ - Step 53884: {'lr': 0.0003631049964469201, 'samples': 10345728, 'steps': 53883, 'loss/train': 0.7065900564193726} 08/30/2021 22:55:48 - INFO - __main__ - Step 53885: {'lr': 0.0003631002638403008, 'samples': 10345920, 'steps': 53884, 'loss/train': 1.275734543800354} 08/30/2021 22:55:48 - INFO - __main__ - Step 53886: {'lr': 0.0003630955311827202, 'samples': 10346112, 'steps': 53885, 'loss/train': 1.6717591285705566} 08/30/2021 22:55:49 - INFO - __main__ - Step 53887: {'lr': 0.0003630907984741806, 'samples': 10346304, 'steps': 53886, 'loss/train': 1.4089205265045166} 08/30/2021 22:55:49 - INFO - __main__ - Step 53888: {'lr': 0.00036308606571468406, 'samples': 10346496, 'steps': 53887, 'loss/train': 0.8983347415924072} 08/30/2021 22:55:50 - INFO - __main__ - Step 53889: {'lr': 0.00036308133290423257, 'samples': 10346688, 'steps': 53888, 'loss/train': 1.1579469442367554} 08/30/2021 22:55:51 - INFO - __main__ - Step 53890: {'lr': 0.00036307660004282846, 'samples': 10346880, 'steps': 53889, 'loss/train': 1.1339261531829834} 08/30/2021 22:55:51 - INFO - __main__ - Step 53891: {'lr': 0.0003630718671304737, 'samples': 10347072, 'steps': 53890, 'loss/train': 1.322121500968933} 08/30/2021 22:55:52 - INFO - __main__ - Step 53892: {'lr': 0.0003630671341671705, 'samples': 10347264, 'steps': 53891, 'loss/train': 1.0415552854537964} 08/30/2021 22:55:52 - INFO - __main__ - Step 53893: {'lr': 0.0003630624011529211, 'samples': 10347456, 'steps': 53892, 'loss/train': 1.352339744567871} 08/30/2021 22:55:53 - INFO - __main__ - Step 53894: {'lr': 0.00036305766808772746, 'samples': 10347648, 'steps': 53893, 'loss/train': 0.7083971500396729} 08/30/2021 22:55:54 - INFO - __main__ - Step 53895: {'lr': 0.0003630529349715918, 'samples': 10347840, 'steps': 53894, 'loss/train': 0.7098364233970642} 08/30/2021 22:55:54 - INFO - __main__ - Step 53896: {'lr': 0.0003630482018045163, 'samples': 10348032, 'steps': 53895, 'loss/train': 1.2295888662338257} 08/30/2021 22:55:55 - INFO - __main__ - Step 53897: {'lr': 0.0003630434685865029, 'samples': 10348224, 'steps': 53896, 'loss/train': 0.9266245365142822} 08/30/2021 22:55:55 - INFO - __main__ - Step 53898: {'lr': 0.0003630387353175539, 'samples': 10348416, 'steps': 53897, 'loss/train': 0.2742985486984253} 08/30/2021 22:55:57 - INFO - __main__ - Step 53899: {'lr': 0.0003630340019976713, 'samples': 10348608, 'steps': 53898, 'loss/train': 1.3300591707229614} 08/30/2021 22:55:57 - INFO - __main__ - Step 53900: {'lr': 0.0003630292686268575, 'samples': 10348800, 'steps': 53899, 'loss/train': 0.9842734932899475} 08/30/2021 22:55:57 - INFO - __main__ - Step 53901: {'lr': 0.00036302453520511437, 'samples': 10348992, 'steps': 53900, 'loss/train': 1.2373638153076172} 08/30/2021 22:55:58 - INFO - __main__ - Step 53902: {'lr': 0.0003630198017324441, 'samples': 10349184, 'steps': 53901, 'loss/train': 1.3236435651779175} 08/30/2021 22:55:58 - INFO - __main__ - Step 53903: {'lr': 0.0003630150682088489, 'samples': 10349376, 'steps': 53902, 'loss/train': 0.3450353741645813} 08/30/2021 22:56:00 - INFO - __main__ - Step 53904: {'lr': 0.00036301033463433086, 'samples': 10349568, 'steps': 53903, 'loss/train': 1.9662925004959106} 08/30/2021 22:56:00 - INFO - __main__ - Step 53905: {'lr': 0.0003630056010088921, 'samples': 10349760, 'steps': 53904, 'loss/train': 1.322086215019226} 08/30/2021 22:56:00 - INFO - __main__ - Step 53906: {'lr': 0.00036300086733253466, 'samples': 10349952, 'steps': 53905, 'loss/train': 1.309656023979187} 08/30/2021 22:56:01 - INFO - __main__ - Step 53907: {'lr': 0.0003629961336052609, 'samples': 10350144, 'steps': 53906, 'loss/train': 1.6261889934539795} 08/30/2021 22:56:01 - INFO - __main__ - Step 53908: {'lr': 0.0003629913998270728, 'samples': 10350336, 'steps': 53907, 'loss/train': 1.274661660194397} 08/30/2021 22:56:02 - INFO - __main__ - Step 53909: {'lr': 0.00036298666599797247, 'samples': 10350528, 'steps': 53908, 'loss/train': 1.071433186531067} 08/30/2021 22:56:04 - INFO - __main__ - Step 53910: {'lr': 0.00036298193211796215, 'samples': 10350720, 'steps': 53909, 'loss/train': 1.5784220695495605} 08/30/2021 22:56:04 - INFO - __main__ - Step 53911: {'lr': 0.0003629771981870439, 'samples': 10350912, 'steps': 53910, 'loss/train': 1.6543148756027222} 08/30/2021 22:56:05 - INFO - __main__ - Step 53912: {'lr': 0.0003629724642052198, 'samples': 10351104, 'steps': 53911, 'loss/train': 0.030927233397960663} 08/30/2021 22:56:05 - INFO - __main__ - Step 53913: {'lr': 0.00036296773017249214, 'samples': 10351296, 'steps': 53912, 'loss/train': 0.40828219056129456} 08/30/2021 22:56:05 - INFO - __main__ - Step 53914: {'lr': 0.0003629629960888629, 'samples': 10351488, 'steps': 53913, 'loss/train': 1.3829665184020996} 08/30/2021 22:56:06 - INFO - __main__ - Step 53915: {'lr': 0.00036295826195433434, 'samples': 10351680, 'steps': 53914, 'loss/train': 1.3375792503356934} 08/30/2021 22:56:07 - INFO - __main__ - Step 53916: {'lr': 0.0003629535277689085, 'samples': 10351872, 'steps': 53915, 'loss/train': 1.258182168006897} 08/30/2021 22:56:08 - INFO - __main__ - Step 53917: {'lr': 0.00036294879353258755, 'samples': 10352064, 'steps': 53916, 'loss/train': 1.6508598327636719} 08/30/2021 22:56:08 - INFO - __main__ - Step 53918: {'lr': 0.0003629440592453736, 'samples': 10352256, 'steps': 53917, 'loss/train': 1.5212675333023071} 08/30/2021 22:56:08 - INFO - __main__ - Step 53919: {'lr': 0.0003629393249072688, 'samples': 10352448, 'steps': 53918, 'loss/train': 1.06631600856781} 08/30/2021 22:56:09 - INFO - __main__ - Step 53920: {'lr': 0.00036293459051827526, 'samples': 10352640, 'steps': 53919, 'loss/train': 1.6450555324554443} 08/30/2021 22:56:10 - INFO - __main__ - Step 53921: {'lr': 0.0003629298560783952, 'samples': 10352832, 'steps': 53920, 'loss/train': 1.2475587129592896} 08/30/2021 22:56:11 - INFO - __main__ - Step 53922: {'lr': 0.0003629251215876307, 'samples': 10353024, 'steps': 53921, 'loss/train': 0.6523019075393677} 08/30/2021 22:56:11 - INFO - __main__ - Step 53923: {'lr': 0.0003629203870459838, 'samples': 10353216, 'steps': 53922, 'loss/train': 1.228450059890747} 08/30/2021 22:56:11 - INFO - __main__ - Step 53924: {'lr': 0.00036291565245345677, 'samples': 10353408, 'steps': 53923, 'loss/train': 2.0210907459259033} 08/30/2021 22:56:12 - INFO - __main__ - Step 53925: {'lr': 0.0003629109178100516, 'samples': 10353600, 'steps': 53924, 'loss/train': 1.5081448554992676} 08/30/2021 22:56:13 - INFO - __main__ - Step 53926: {'lr': 0.0003629061831157706, 'samples': 10353792, 'steps': 53925, 'loss/train': 0.6194517612457275} 08/30/2021 22:56:14 - INFO - __main__ - Step 53927: {'lr': 0.00036290144837061586, 'samples': 10353984, 'steps': 53926, 'loss/train': 0.7502023577690125} 08/30/2021 22:56:14 - INFO - __main__ - Step 53928: {'lr': 0.00036289671357458937, 'samples': 10354176, 'steps': 53927, 'loss/train': 1.3222026824951172} 08/30/2021 22:56:14 - INFO - __main__ - Step 53929: {'lr': 0.00036289197872769346, 'samples': 10354368, 'steps': 53928, 'loss/train': 1.545782446861267} 08/30/2021 22:56:15 - INFO - __main__ - Step 53930: {'lr': 0.0003628872438299301, 'samples': 10354560, 'steps': 53929, 'loss/train': 1.1636182069778442} 08/30/2021 22:56:16 - INFO - __main__ - Step 53931: {'lr': 0.0003628825088813015, 'samples': 10354752, 'steps': 53930, 'loss/train': 1.2877557277679443} 08/30/2021 22:56:17 - INFO - __main__ - Step 53932: {'lr': 0.00036287777388180977, 'samples': 10354944, 'steps': 53931, 'loss/train': 1.791764497756958} 08/30/2021 22:56:17 - INFO - __main__ - Step 53933: {'lr': 0.00036287303883145703, 'samples': 10355136, 'steps': 53932, 'loss/train': 1.1045094728469849} 08/30/2021 22:56:17 - INFO - __main__ - Step 53934: {'lr': 0.00036286830373024546, 'samples': 10355328, 'steps': 53933, 'loss/train': 1.4776878356933594} 08/30/2021 22:56:18 - INFO - __main__ - Step 53935: {'lr': 0.00036286356857817727, 'samples': 10355520, 'steps': 53934, 'loss/train': 0.37960898876190186} 08/30/2021 22:56:19 - INFO - __main__ - Step 53936: {'lr': 0.0003628588333752544, 'samples': 10355712, 'steps': 53935, 'loss/train': 0.4761931896209717} 08/30/2021 22:56:20 - INFO - __main__ - Step 53937: {'lr': 0.0003628540981214791, 'samples': 10355904, 'steps': 53936, 'loss/train': 0.9485270380973816} 08/30/2021 22:56:20 - INFO - __main__ - Step 53938: {'lr': 0.00036284936281685354, 'samples': 10356096, 'steps': 53937, 'loss/train': 1.2968593835830688} 08/30/2021 22:56:20 - INFO - __main__ - Step 53939: {'lr': 0.0003628446274613797, 'samples': 10356288, 'steps': 53938, 'loss/train': 1.0184592008590698} 08/30/2021 22:56:21 - INFO - __main__ - Step 53940: {'lr': 0.00036283989205505987, 'samples': 10356480, 'steps': 53939, 'loss/train': 1.2882018089294434} 08/30/2021 22:56:22 - INFO - __main__ - Step 53941: {'lr': 0.00036283515659789615, 'samples': 10356672, 'steps': 53940, 'loss/train': 1.6255367994308472} 08/30/2021 22:56:23 - INFO - __main__ - Step 53942: {'lr': 0.0003628304210898906, 'samples': 10356864, 'steps': 53941, 'loss/train': 1.82087242603302} 08/30/2021 22:56:23 - INFO - __main__ - Step 53943: {'lr': 0.00036282568553104545, 'samples': 10357056, 'steps': 53942, 'loss/train': 1.032686710357666} 08/30/2021 22:56:23 - INFO - __main__ - Step 53944: {'lr': 0.00036282094992136273, 'samples': 10357248, 'steps': 53943, 'loss/train': 1.8840587139129639} 08/30/2021 22:56:24 - INFO - __main__ - Step 53945: {'lr': 0.00036281621426084465, 'samples': 10357440, 'steps': 53944, 'loss/train': 1.3175116777420044} 08/30/2021 22:56:26 - INFO - __main__ - Step 53946: {'lr': 0.0003628114785494934, 'samples': 10357632, 'steps': 53945, 'loss/train': 1.7962939739227295} 08/30/2021 22:56:26 - INFO - __main__ - Step 53947: {'lr': 0.00036280674278731096, 'samples': 10357824, 'steps': 53946, 'loss/train': 0.9019666910171509} 08/30/2021 22:56:27 - INFO - __main__ - Step 53948: {'lr': 0.00036280200697429957, 'samples': 10358016, 'steps': 53947, 'loss/train': 1.2212061882019043} 08/30/2021 22:56:27 - INFO - __main__ - Step 53949: {'lr': 0.00036279727111046127, 'samples': 10358208, 'steps': 53948, 'loss/train': 0.2895715534687042} 08/30/2021 22:56:27 - INFO - __main__ - Step 53950: {'lr': 0.0003627925351957983, 'samples': 10358400, 'steps': 53949, 'loss/train': 1.3136773109436035} 08/30/2021 22:56:28 - INFO - __main__ - Step 53951: {'lr': 0.0003627877992303128, 'samples': 10358592, 'steps': 53950, 'loss/train': 0.860072672367096} 08/30/2021 22:56:29 - INFO - __main__ - Step 53952: {'lr': 0.0003627830632140068, 'samples': 10358784, 'steps': 53951, 'loss/train': 1.6536394357681274} 08/30/2021 22:56:30 - INFO - __main__ - Step 53953: {'lr': 0.0003627783271468825, 'samples': 10358976, 'steps': 53952, 'loss/train': 1.5553181171417236} 08/30/2021 22:56:30 - INFO - __main__ - Step 53954: {'lr': 0.0003627735910289421, 'samples': 10359168, 'steps': 53953, 'loss/train': 1.3697348833084106} 08/30/2021 22:56:30 - INFO - __main__ - Step 53955: {'lr': 0.0003627688548601876, 'samples': 10359360, 'steps': 53954, 'loss/train': 1.366170883178711} 08/30/2021 22:56:31 - INFO - __main__ - Step 53956: {'lr': 0.00036276411864062116, 'samples': 10359552, 'steps': 53955, 'loss/train': 0.8351635336875916} 08/30/2021 22:56:31 - INFO - __main__ - Step 53957: {'lr': 0.00036275938237024505, 'samples': 10359744, 'steps': 53956, 'loss/train': 0.4959670305252075} 08/30/2021 22:56:33 - INFO - __main__ - Step 53958: {'lr': 0.00036275464604906116, 'samples': 10359936, 'steps': 53957, 'loss/train': 0.8398715257644653} 08/30/2021 22:56:34 - INFO - __main__ - Step 53959: {'lr': 0.0003627499096770719, 'samples': 10360128, 'steps': 53958, 'loss/train': 0.6449087262153625} 08/30/2021 22:56:34 - INFO - __main__ - Step 53960: {'lr': 0.0003627451732542791, 'samples': 10360320, 'steps': 53959, 'loss/train': 1.228438138961792} 08/30/2021 22:56:35 - INFO - __main__ - Step 53961: {'lr': 0.00036274043678068526, 'samples': 10360512, 'steps': 53960, 'loss/train': 2.020247459411621} 08/30/2021 22:56:35 - INFO - __main__ - Step 53962: {'lr': 0.0003627357002562923, 'samples': 10360704, 'steps': 53961, 'loss/train': 1.0533267259597778} 08/30/2021 22:56:37 - INFO - __main__ - Step 53963: {'lr': 0.0003627309636811023, 'samples': 10360896, 'steps': 53962, 'loss/train': 1.6192445755004883} 08/30/2021 22:56:37 - INFO - __main__ - Step 53964: {'lr': 0.00036272622705511745, 'samples': 10361088, 'steps': 53963, 'loss/train': 1.4473854303359985} 08/30/2021 22:56:38 - INFO - __main__ - Step 53965: {'lr': 0.0003627214903783399, 'samples': 10361280, 'steps': 53964, 'loss/train': 1.6189736127853394} 08/30/2021 22:56:38 - INFO - __main__ - Step 53966: {'lr': 0.00036271675365077185, 'samples': 10361472, 'steps': 53965, 'loss/train': 1.1956008672714233} 08/30/2021 22:56:38 - INFO - __main__ - Step 53967: {'lr': 0.0003627120168724153, 'samples': 10361664, 'steps': 53966, 'loss/train': 1.1789737939834595} 08/30/2021 22:56:40 - INFO - __main__ - Step 53968: {'lr': 0.00036270728004327246, 'samples': 10361856, 'steps': 53967, 'loss/train': 1.464616060256958} 08/30/2021 22:56:41 - INFO - __main__ - Step 53969: {'lr': 0.0003627025431633455, 'samples': 10362048, 'steps': 53968, 'loss/train': 1.041573166847229} 08/30/2021 22:56:41 - INFO - __main__ - Step 53970: {'lr': 0.00036269780623263647, 'samples': 10362240, 'steps': 53969, 'loss/train': 0.054159682244062424} 08/30/2021 22:56:41 - INFO - __main__ - Step 53971: {'lr': 0.00036269306925114765, 'samples': 10362432, 'steps': 53970, 'loss/train': 1.5363587141036987} 08/30/2021 22:56:42 - INFO - __main__ - Step 53972: {'lr': 0.000362688332218881, 'samples': 10362624, 'steps': 53971, 'loss/train': 1.858013391494751} 08/30/2021 22:56:43 - INFO - __main__ - Step 53973: {'lr': 0.0003626835951358387, 'samples': 10362816, 'steps': 53972, 'loss/train': 1.1408942937850952} 08/30/2021 22:56:44 - INFO - __main__ - Step 53974: {'lr': 0.00036267885800202296, 'samples': 10363008, 'steps': 53973, 'loss/train': 1.701961636543274} 08/30/2021 22:56:44 - INFO - __main__ - Step 53975: {'lr': 0.00036267412081743576, 'samples': 10363200, 'steps': 53974, 'loss/train': 1.3819730281829834} 08/30/2021 22:56:45 - INFO - __main__ - Step 53976: {'lr': 0.00036266938358207944, 'samples': 10363392, 'steps': 53975, 'loss/train': 1.580741047859192} 08/30/2021 22:56:45 - INFO - __main__ - Step 53977: {'lr': 0.0003626646462959561, 'samples': 10363584, 'steps': 53976, 'loss/train': 1.0083789825439453} 08/30/2021 22:56:46 - INFO - __main__ - Step 53978: {'lr': 0.00036265990895906767, 'samples': 10363776, 'steps': 53977, 'loss/train': 0.06872133910655975} 08/30/2021 22:56:47 - INFO - __main__ - Step 53979: {'lr': 0.0003626551715714165, 'samples': 10363968, 'steps': 53978, 'loss/train': 1.282861351966858} 08/30/2021 22:56:47 - INFO - __main__ - Step 53980: {'lr': 0.00036265043413300456, 'samples': 10364160, 'steps': 53979, 'loss/train': 1.0948063135147095} 08/30/2021 22:56:47 - INFO - __main__ - Step 53981: {'lr': 0.0003626456966438342, 'samples': 10364352, 'steps': 53980, 'loss/train': 0.9879094958305359} 08/30/2021 22:56:48 - INFO - __main__ - Step 53982: {'lr': 0.00036264095910390736, 'samples': 10364544, 'steps': 53981, 'loss/train': 0.9718050360679626} 08/30/2021 22:56:48 - INFO - __main__ - Step 53983: {'lr': 0.0003626362215132263, 'samples': 10364736, 'steps': 53982, 'loss/train': 1.7662581205368042} 08/30/2021 22:56:50 - INFO - __main__ - Step 53984: {'lr': 0.00036263148387179303, 'samples': 10364928, 'steps': 53983, 'loss/train': 1.705222725868225} 08/30/2021 22:56:50 - INFO - __main__ - Step 53985: {'lr': 0.0003626267461796097, 'samples': 10365120, 'steps': 53984, 'loss/train': 1.0252137184143066} 08/30/2021 22:56:51 - INFO - __main__ - Step 53986: {'lr': 0.0003626220084366786, 'samples': 10365312, 'steps': 53985, 'loss/train': 1.329757571220398} 08/30/2021 22:56:51 - INFO - __main__ - Step 53987: {'lr': 0.0003626172706430017, 'samples': 10365504, 'steps': 53986, 'loss/train': 1.3617582321166992} 08/30/2021 22:56:51 - INFO - __main__ - Step 53988: {'lr': 0.0003626125327985812, 'samples': 10365696, 'steps': 53987, 'loss/train': 1.3035142421722412} 08/30/2021 22:56:53 - INFO - __main__ - Step 53989: {'lr': 0.0003626077949034193, 'samples': 10365888, 'steps': 53988, 'loss/train': 1.2522143125534058} 08/30/2021 22:56:53 - INFO - __main__ - Step 53990: {'lr': 0.000362603056957518, 'samples': 10366080, 'steps': 53989, 'loss/train': 0.7440615296363831} 08/30/2021 22:56:54 - INFO - __main__ - Step 53991: {'lr': 0.0003625983189608795, 'samples': 10366272, 'steps': 53990, 'loss/train': 1.0405722856521606} 08/30/2021 22:56:54 - INFO - __main__ - Step 53992: {'lr': 0.00036259358091350597, 'samples': 10366464, 'steps': 53991, 'loss/train': 0.7481604218482971} 08/30/2021 22:56:54 - INFO - __main__ - Step 53993: {'lr': 0.0003625888428153995, 'samples': 10366656, 'steps': 53992, 'loss/train': 1.3331502676010132} 08/30/2021 22:56:56 - INFO - __main__ - Step 53994: {'lr': 0.0003625841046665622, 'samples': 10366848, 'steps': 53993, 'loss/train': 0.9002139568328857} 08/30/2021 22:56:57 - INFO - __main__ - Step 53995: {'lr': 0.00036257936646699626, 'samples': 10367040, 'steps': 53994, 'loss/train': 1.5377739667892456} 08/30/2021 22:56:57 - INFO - __main__ - Step 53996: {'lr': 0.00036257462821670387, 'samples': 10367232, 'steps': 53995, 'loss/train': 1.515584111213684} 08/30/2021 22:56:57 - INFO - __main__ - Step 53997: {'lr': 0.00036256988991568696, 'samples': 10367424, 'steps': 53996, 'loss/train': 1.3562283515930176} 08/30/2021 22:56:58 - INFO - __main__ - Step 53998: {'lr': 0.0003625651515639479, 'samples': 10367616, 'steps': 53997, 'loss/train': 1.437071681022644} 08/30/2021 22:57:00 - INFO - __main__ - Step 53999: {'lr': 0.00036256041316148864, 'samples': 10367808, 'steps': 53998, 'loss/train': 1.1273692846298218} 08/30/2021 22:57:00 - INFO - __main__ - Step 54000: {'lr': 0.0003625556747083114, 'samples': 10368000, 'steps': 53999, 'loss/train': 0.9582331776618958} 08/30/2021 22:57:01 - INFO - __main__ - Step 54001: {'lr': 0.0003625509362044183, 'samples': 10368192, 'steps': 54000, 'loss/train': 0.9439205527305603} 08/30/2021 22:57:01 - INFO - __main__ - Step 54002: {'lr': 0.00036254619764981155, 'samples': 10368384, 'steps': 54001, 'loss/train': 1.3519387245178223} 08/30/2021 22:57:01 - INFO - __main__ - Step 54003: {'lr': 0.0003625414590444932, 'samples': 10368576, 'steps': 54002, 'loss/train': 1.909079670906067} 08/30/2021 22:57:02 - INFO - __main__ - Step 54004: {'lr': 0.0003625367203884654, 'samples': 10368768, 'steps': 54003, 'loss/train': 1.7615684270858765} 08/30/2021 22:57:04 - INFO - __main__ - Step 54005: {'lr': 0.0003625319816817303, 'samples': 10368960, 'steps': 54004, 'loss/train': 1.708850622177124} 08/30/2021 22:57:04 - INFO - __main__ - Step 54006: {'lr': 0.00036252724292429, 'samples': 10369152, 'steps': 54005, 'loss/train': 1.1089848279953003} 08/30/2021 22:57:04 - INFO - __main__ - Step 54007: {'lr': 0.00036252250411614666, 'samples': 10369344, 'steps': 54006, 'loss/train': 1.6467301845550537} 08/30/2021 22:57:05 - INFO - __main__ - Step 54008: {'lr': 0.0003625177652573024, 'samples': 10369536, 'steps': 54007, 'loss/train': 1.2013165950775146} 08/30/2021 22:57:05 - INFO - __main__ - Step 54009: {'lr': 0.0003625130263477595, 'samples': 10369728, 'steps': 54008, 'loss/train': 1.2774794101715088} 08/30/2021 22:57:05 - INFO - __main__ - Step 54010: {'lr': 0.00036250828738751986, 'samples': 10369920, 'steps': 54009, 'loss/train': 2.4317800998687744} 08/30/2021 22:57:07 - INFO - __main__ - Step 54011: {'lr': 0.0003625035483765857, 'samples': 10370112, 'steps': 54010, 'loss/train': 1.6654589176177979} 08/30/2021 22:57:08 - INFO - __main__ - Step 54012: {'lr': 0.00036249880931495923, 'samples': 10370304, 'steps': 54011, 'loss/train': 1.2266253232955933} 08/30/2021 22:57:08 - INFO - __main__ - Step 54013: {'lr': 0.00036249407020264246, 'samples': 10370496, 'steps': 54012, 'loss/train': 1.8434330224990845} 08/30/2021 22:57:08 - INFO - __main__ - Step 54014: {'lr': 0.00036248933103963767, 'samples': 10370688, 'steps': 54013, 'loss/train': 0.9791733622550964} 08/30/2021 22:57:09 - INFO - __main__ - Step 54015: {'lr': 0.0003624845918259469, 'samples': 10370880, 'steps': 54014, 'loss/train': 1.4361388683319092} 08/30/2021 22:57:09 - INFO - __main__ - Step 54016: {'lr': 0.00036247985256157236, 'samples': 10371072, 'steps': 54015, 'loss/train': 1.578568458557129} 08/30/2021 22:57:11 - INFO - __main__ - Step 54017: {'lr': 0.0003624751132465161, 'samples': 10371264, 'steps': 54016, 'loss/train': 1.1097666025161743} 08/30/2021 22:57:12 - INFO - __main__ - Step 54018: {'lr': 0.00036247037388078017, 'samples': 10371456, 'steps': 54017, 'loss/train': 1.1587128639221191} 08/30/2021 22:57:12 - INFO - __main__ - Step 54019: {'lr': 0.00036246563446436697, 'samples': 10371648, 'steps': 54018, 'loss/train': 1.7240855693817139} 08/30/2021 22:57:12 - INFO - __main__ - Step 54020: {'lr': 0.00036246089499727843, 'samples': 10371840, 'steps': 54019, 'loss/train': 1.9333378076553345} 08/30/2021 22:57:13 - INFO - __main__ - Step 54021: {'lr': 0.0003624561554795168, 'samples': 10372032, 'steps': 54020, 'loss/train': 1.7124807834625244} 08/30/2021 22:57:14 - INFO - __main__ - Step 54022: {'lr': 0.0003624514159110841, 'samples': 10372224, 'steps': 54021, 'loss/train': 0.33069729804992676} 08/30/2021 22:57:15 - INFO - __main__ - Step 54023: {'lr': 0.0003624466762919826, 'samples': 10372416, 'steps': 54022, 'loss/train': 1.3345967531204224} 08/30/2021 22:57:15 - INFO - __main__ - Step 54024: {'lr': 0.00036244193662221427, 'samples': 10372608, 'steps': 54023, 'loss/train': 1.2936688661575317} 08/30/2021 22:57:16 - INFO - __main__ - Step 54025: {'lr': 0.0003624371969017814, 'samples': 10372800, 'steps': 54024, 'loss/train': 1.475222110748291} 08/30/2021 22:57:16 - INFO - __main__ - Step 54026: {'lr': 0.000362432457130686, 'samples': 10372992, 'steps': 54025, 'loss/train': 1.2372760772705078} 08/30/2021 22:57:17 - INFO - __main__ - Step 54027: {'lr': 0.0003624277173089303, 'samples': 10373184, 'steps': 54026, 'loss/train': 1.0800518989562988} 08/30/2021 22:57:18 - INFO - __main__ - Step 54028: {'lr': 0.0003624229774365165, 'samples': 10373376, 'steps': 54027, 'loss/train': 1.245154619216919} 08/30/2021 22:57:18 - INFO - __main__ - Step 54029: {'lr': 0.00036241823751344656, 'samples': 10373568, 'steps': 54028, 'loss/train': 1.5563030242919922} 08/30/2021 22:57:18 - INFO - __main__ - Step 54030: {'lr': 0.0003624134975397227, 'samples': 10373760, 'steps': 54029, 'loss/train': 1.5903006792068481} 08/30/2021 22:57:19 - INFO - __main__ - Step 54031: {'lr': 0.0003624087575153471, 'samples': 10373952, 'steps': 54030, 'loss/train': 1.2951852083206177} 08/30/2021 22:57:20 - INFO - __main__ - Step 54032: {'lr': 0.00036240401744032174, 'samples': 10374144, 'steps': 54031, 'loss/train': 0.353877991437912} 08/30/2021 22:57:21 - INFO - __main__ - Step 54033: {'lr': 0.00036239927731464896, 'samples': 10374336, 'steps': 54032, 'loss/train': 0.9869309067726135} 08/30/2021 22:57:21 - INFO - __main__ - Step 54034: {'lr': 0.0003623945371383307, 'samples': 10374528, 'steps': 54033, 'loss/train': 1.4709755182266235} 08/30/2021 22:57:22 - INFO - __main__ - Step 54035: {'lr': 0.0003623897969113693, 'samples': 10374720, 'steps': 54034, 'loss/train': 3.0739753246307373} 08/30/2021 22:57:22 - INFO - __main__ - Step 54036: {'lr': 0.00036238505663376675, 'samples': 10374912, 'steps': 54035, 'loss/train': 1.386664867401123} 08/30/2021 22:57:22 - INFO - __main__ - Step 54037: {'lr': 0.00036238031630552527, 'samples': 10375104, 'steps': 54036, 'loss/train': 1.0370498895645142} 08/30/2021 22:57:24 - INFO - __main__ - Step 54038: {'lr': 0.0003623755759266469, 'samples': 10375296, 'steps': 54037, 'loss/train': 0.8300610780715942} 08/30/2021 22:57:24 - INFO - __main__ - Step 54039: {'lr': 0.00036237083549713387, 'samples': 10375488, 'steps': 54038, 'loss/train': 1.830101490020752} 08/30/2021 22:57:25 - INFO - __main__ - Step 54040: {'lr': 0.0003623660950169882, 'samples': 10375680, 'steps': 54039, 'loss/train': 1.7232962846755981} 08/30/2021 22:57:25 - INFO - __main__ - Step 54041: {'lr': 0.00036236135448621215, 'samples': 10375872, 'steps': 54040, 'loss/train': 1.449582815170288} 08/30/2021 22:57:25 - INFO - __main__ - Step 54042: {'lr': 0.0003623566139048078, 'samples': 10376064, 'steps': 54041, 'loss/train': 1.3240938186645508} 08/30/2021 22:57:27 - INFO - __main__ - Step 54043: {'lr': 0.00036235187327277735, 'samples': 10376256, 'steps': 54042, 'loss/train': 1.7063496112823486} 08/30/2021 22:57:27 - INFO - __main__ - Step 54044: {'lr': 0.0003623471325901228, 'samples': 10376448, 'steps': 54043, 'loss/train': 0.9686894416809082} 08/30/2021 22:57:28 - INFO - __main__ - Step 54045: {'lr': 0.00036234239185684643, 'samples': 10376640, 'steps': 54044, 'loss/train': 1.565123200416565} 08/30/2021 22:57:28 - INFO - __main__ - Step 54046: {'lr': 0.00036233765107295023, 'samples': 10376832, 'steps': 54045, 'loss/train': 1.407694935798645} 08/30/2021 22:57:28 - INFO - __main__ - Step 54047: {'lr': 0.00036233291023843653, 'samples': 10377024, 'steps': 54046, 'loss/train': 1.0453904867172241} 08/30/2021 22:57:30 - INFO - __main__ - Step 54048: {'lr': 0.00036232816935330723, 'samples': 10377216, 'steps': 54047, 'loss/train': 1.4748709201812744} 08/30/2021 22:57:30 - INFO - __main__ - Step 54049: {'lr': 0.00036232342841756467, 'samples': 10377408, 'steps': 54048, 'loss/train': 1.144144058227539} 08/30/2021 22:57:31 - INFO - __main__ - Step 54050: {'lr': 0.00036231868743121095, 'samples': 10377600, 'steps': 54049, 'loss/train': 1.3348273038864136} 08/30/2021 22:57:31 - INFO - __main__ - Step 54051: {'lr': 0.0003623139463942481, 'samples': 10377792, 'steps': 54050, 'loss/train': 0.9061219096183777} 08/30/2021 22:57:32 - INFO - __main__ - Step 54052: {'lr': 0.0003623092053066783, 'samples': 10377984, 'steps': 54051, 'loss/train': 2.7090871334075928} 08/30/2021 22:57:33 - INFO - __main__ - Step 54053: {'lr': 0.0003623044641685037, 'samples': 10378176, 'steps': 54052, 'loss/train': 1.5605658292770386} 08/30/2021 22:57:34 - INFO - __main__ - Step 54054: {'lr': 0.00036229972297972644, 'samples': 10378368, 'steps': 54053, 'loss/train': 1.7433743476867676} 08/30/2021 22:57:34 - INFO - __main__ - Step 54055: {'lr': 0.00036229498174034867, 'samples': 10378560, 'steps': 54054, 'loss/train': 2.418992042541504} 08/30/2021 22:57:34 - INFO - __main__ - Step 54056: {'lr': 0.00036229024045037264, 'samples': 10378752, 'steps': 54055, 'loss/train': 1.3381084203720093} 08/30/2021 22:57:35 - INFO - __main__ - Step 54057: {'lr': 0.00036228549910980026, 'samples': 10378944, 'steps': 54056, 'loss/train': 1.6885634660720825} 08/30/2021 22:57:35 - INFO - __main__ - Step 54058: {'lr': 0.0003622807577186337, 'samples': 10379136, 'steps': 54057, 'loss/train': 1.3403220176696777} 08/30/2021 22:57:37 - INFO - __main__ - Step 54059: {'lr': 0.0003622760162768752, 'samples': 10379328, 'steps': 54058, 'loss/train': 1.2096168994903564} 08/30/2021 22:57:37 - INFO - __main__ - Step 54060: {'lr': 0.0003622712747845269, 'samples': 10379520, 'steps': 54059, 'loss/train': 1.6528197526931763} 08/30/2021 22:57:37 - INFO - __main__ - Step 54061: {'lr': 0.0003622665332415909, 'samples': 10379712, 'steps': 54060, 'loss/train': 0.06437007337808609} 08/30/2021 22:57:38 - INFO - __main__ - Step 54062: {'lr': 0.00036226179164806926, 'samples': 10379904, 'steps': 54061, 'loss/train': 1.6419748067855835} 08/30/2021 22:57:38 - INFO - __main__ - Step 54063: {'lr': 0.00036225705000396424, 'samples': 10380096, 'steps': 54062, 'loss/train': 0.9441823959350586} 08/30/2021 22:57:40 - INFO - __main__ - Step 54064: {'lr': 0.000362252308309278, 'samples': 10380288, 'steps': 54063, 'loss/train': 1.6567384004592896} 08/30/2021 22:57:40 - INFO - __main__ - Step 54065: {'lr': 0.00036224756656401245, 'samples': 10380480, 'steps': 54064, 'loss/train': 1.1339386701583862} 08/30/2021 22:57:40 - INFO - __main__ - Step 54066: {'lr': 0.0003622428247681699, 'samples': 10380672, 'steps': 54065, 'loss/train': 1.6598219871520996} 08/30/2021 22:57:41 - INFO - __main__ - Step 54067: {'lr': 0.0003622380829217526, 'samples': 10380864, 'steps': 54066, 'loss/train': 1.626612663269043} 08/30/2021 22:57:41 - INFO - __main__ - Step 54068: {'lr': 0.00036223334102476247, 'samples': 10381056, 'steps': 54067, 'loss/train': 1.0829334259033203} 08/30/2021 22:57:43 - INFO - __main__ - Step 54069: {'lr': 0.00036222859907720167, 'samples': 10381248, 'steps': 54068, 'loss/train': 0.7254710793495178} 08/30/2021 22:57:43 - INFO - __main__ - Step 54070: {'lr': 0.00036222385707907254, 'samples': 10381440, 'steps': 54069, 'loss/train': 1.5907626152038574} 08/30/2021 22:57:43 - INFO - __main__ - Step 54071: {'lr': 0.000362219115030377, 'samples': 10381632, 'steps': 54070, 'loss/train': 1.2088876962661743} 08/30/2021 22:57:44 - INFO - __main__ - Step 54072: {'lr': 0.0003622143729311172, 'samples': 10381824, 'steps': 54071, 'loss/train': 1.6792110204696655} 08/30/2021 22:57:44 - INFO - __main__ - Step 54073: {'lr': 0.00036220963078129536, 'samples': 10382016, 'steps': 54072, 'loss/train': 1.7058193683624268} 08/30/2021 22:57:46 - INFO - __main__ - Step 54074: {'lr': 0.0003622048885809136, 'samples': 10382208, 'steps': 54073, 'loss/train': 1.7429540157318115} 08/30/2021 22:57:47 - INFO - __main__ - Step 54075: {'lr': 0.0003622001463299741, 'samples': 10382400, 'steps': 54074, 'loss/train': 1.2515110969543457} 08/30/2021 22:57:47 - INFO - __main__ - Step 54076: {'lr': 0.0003621954040284789, 'samples': 10382592, 'steps': 54075, 'loss/train': 0.630169689655304} 08/30/2021 22:57:47 - INFO - __main__ - Step 54077: {'lr': 0.00036219066167643015, 'samples': 10382784, 'steps': 54076, 'loss/train': 1.4024375677108765} 08/30/2021 22:57:48 - INFO - __main__ - Step 54078: {'lr': 0.00036218591927383, 'samples': 10382976, 'steps': 54077, 'loss/train': 1.435202956199646} 08/30/2021 22:57:49 - INFO - __main__ - Step 54079: {'lr': 0.00036218117682068076, 'samples': 10383168, 'steps': 54078, 'loss/train': 0.29466712474823} 08/30/2021 22:57:50 - INFO - __main__ - Step 54080: {'lr': 0.0003621764343169843, 'samples': 10383360, 'steps': 54079, 'loss/train': 1.1778478622436523} 08/30/2021 22:57:50 - INFO - __main__ - Step 54081: {'lr': 0.0003621716917627429, 'samples': 10383552, 'steps': 54080, 'loss/train': 0.09834454953670502} 08/30/2021 22:57:50 - INFO - __main__ - Step 54082: {'lr': 0.0003621669491579587, 'samples': 10383744, 'steps': 54081, 'loss/train': 1.401611089706421} 08/30/2021 22:57:51 - INFO - __main__ - Step 54083: {'lr': 0.0003621622065026337, 'samples': 10383936, 'steps': 54082, 'loss/train': 1.4323993921279907} 08/30/2021 22:57:52 - INFO - __main__ - Step 54084: {'lr': 0.0003621574637967702, 'samples': 10384128, 'steps': 54083, 'loss/train': 1.2989877462387085} 08/30/2021 22:57:53 - INFO - __main__ - Step 54085: {'lr': 0.00036215272104037023, 'samples': 10384320, 'steps': 54084, 'loss/train': 1.7603942155838013} 08/30/2021 22:57:53 - INFO - __main__ - Step 54086: {'lr': 0.0003621479782334361, 'samples': 10384512, 'steps': 54085, 'loss/train': 1.627334475517273} 08/30/2021 22:57:53 - INFO - __main__ - Step 54087: {'lr': 0.00036214323537596974, 'samples': 10384704, 'steps': 54086, 'loss/train': 1.3577144145965576} 08/30/2021 22:57:54 - INFO - __main__ - Step 54088: {'lr': 0.0003621384924679733, 'samples': 10384896, 'steps': 54087, 'loss/train': 1.2363277673721313} 08/30/2021 22:57:54 - INFO - __main__ - Step 54089: {'lr': 0.00036213374950944913, 'samples': 10385088, 'steps': 54088, 'loss/train': 1.3616971969604492} 08/30/2021 22:57:55 - INFO - __main__ - Step 54090: {'lr': 0.0003621290065003991, 'samples': 10385280, 'steps': 54089, 'loss/train': 1.0444917678833008} 08/30/2021 22:57:56 - INFO - __main__ - Step 54091: {'lr': 0.00036212426344082554, 'samples': 10385472, 'steps': 54090, 'loss/train': 1.1713694334030151} 08/30/2021 22:57:56 - INFO - __main__ - Step 54092: {'lr': 0.0003621195203307305, 'samples': 10385664, 'steps': 54091, 'loss/train': 1.3787810802459717} 08/30/2021 22:57:57 - INFO - __main__ - Step 54093: {'lr': 0.0003621147771701161, 'samples': 10385856, 'steps': 54092, 'loss/train': 1.375692367553711} 08/30/2021 22:57:57 - INFO - __main__ - Step 54094: {'lr': 0.00036211003395898456, 'samples': 10386048, 'steps': 54093, 'loss/train': 1.5688828229904175} 08/30/2021 22:57:59 - INFO - __main__ - Step 54095: {'lr': 0.0003621052906973379, 'samples': 10386240, 'steps': 54094, 'loss/train': 1.0351804494857788} 08/30/2021 22:57:59 - INFO - __main__ - Step 54096: {'lr': 0.0003621005473851784, 'samples': 10386432, 'steps': 54095, 'loss/train': 0.8776874542236328} 08/30/2021 22:57:59 - INFO - __main__ - Step 54097: {'lr': 0.0003620958040225081, 'samples': 10386624, 'steps': 54096, 'loss/train': 1.390691876411438} 08/30/2021 22:58:00 - INFO - __main__ - Step 54098: {'lr': 0.0003620910606093292, 'samples': 10386816, 'steps': 54097, 'loss/train': 1.2313324213027954} 08/30/2021 22:58:00 - INFO - __main__ - Step 54099: {'lr': 0.0003620863171456437, 'samples': 10387008, 'steps': 54098, 'loss/train': 0.034721489995718} 08/30/2021 22:58:02 - INFO - __main__ - Step 54100: {'lr': 0.0003620815736314539, 'samples': 10387200, 'steps': 54099, 'loss/train': 0.8360977172851562} 08/30/2021 22:58:02 - INFO - __main__ - Step 54101: {'lr': 0.0003620768300667618, 'samples': 10387392, 'steps': 54100, 'loss/train': 0.8581121563911438} 08/30/2021 22:58:03 - INFO - __main__ - Step 54102: {'lr': 0.00036207208645156977, 'samples': 10387584, 'steps': 54101, 'loss/train': 0.03505820780992508} 08/30/2021 22:58:03 - INFO - __main__ - Step 54103: {'lr': 0.00036206734278587964, 'samples': 10387776, 'steps': 54102, 'loss/train': 1.4135011434555054} 08/30/2021 22:58:04 - INFO - __main__ - Step 54104: {'lr': 0.0003620625990696937, 'samples': 10387968, 'steps': 54103, 'loss/train': 1.3703819513320923} 08/30/2021 22:58:04 - INFO - __main__ - Step 54105: {'lr': 0.00036205785530301417, 'samples': 10388160, 'steps': 54104, 'loss/train': 1.5602731704711914} 08/30/2021 22:58:05 - INFO - __main__ - Step 54106: {'lr': 0.00036205311148584306, 'samples': 10388352, 'steps': 54105, 'loss/train': 1.3221800327301025} 08/30/2021 22:58:06 - INFO - __main__ - Step 54107: {'lr': 0.00036204836761818255, 'samples': 10388544, 'steps': 54106, 'loss/train': 1.3876063823699951} 08/30/2021 22:58:06 - INFO - __main__ - Step 54108: {'lr': 0.00036204362370003475, 'samples': 10388736, 'steps': 54107, 'loss/train': 0.9098288416862488} 08/30/2021 22:58:07 - INFO - __main__ - Step 54109: {'lr': 0.00036203887973140184, 'samples': 10388928, 'steps': 54108, 'loss/train': 1.562433123588562} 08/30/2021 22:58:07 - INFO - __main__ - Step 54110: {'lr': 0.000362034135712286, 'samples': 10389120, 'steps': 54109, 'loss/train': 1.390947937965393} 08/30/2021 22:58:08 - INFO - __main__ - Step 54111: {'lr': 0.00036202939164268924, 'samples': 10389312, 'steps': 54110, 'loss/train': 1.441522240638733} 08/30/2021 22:58:09 - INFO - __main__ - Step 54112: {'lr': 0.0003620246475226138, 'samples': 10389504, 'steps': 54111, 'loss/train': 1.498203158378601} 08/30/2021 22:58:09 - INFO - __main__ - Step 54113: {'lr': 0.0003620199033520617, 'samples': 10389696, 'steps': 54112, 'loss/train': 1.418110966682434} 08/30/2021 22:58:09 - INFO - __main__ - Step 54114: {'lr': 0.0003620151591310352, 'samples': 10389888, 'steps': 54113, 'loss/train': 1.5095621347427368} 08/30/2021 22:58:10 - INFO - __main__ - Step 54115: {'lr': 0.0003620104148595364, 'samples': 10390080, 'steps': 54114, 'loss/train': 1.5566352605819702} 08/30/2021 22:58:11 - INFO - __main__ - Step 54116: {'lr': 0.00036200567053756746, 'samples': 10390272, 'steps': 54115, 'loss/train': 1.2761110067367554} 08/30/2021 22:58:12 - INFO - __main__ - Step 54117: {'lr': 0.0003620009261651305, 'samples': 10390464, 'steps': 54116, 'loss/train': 1.213962197303772} 08/30/2021 22:58:12 - INFO - __main__ - Step 54118: {'lr': 0.0003619961817422276, 'samples': 10390656, 'steps': 54117, 'loss/train': 1.5254822969436646} 08/30/2021 22:58:12 - INFO - __main__ - Step 54119: {'lr': 0.00036199143726886097, 'samples': 10390848, 'steps': 54118, 'loss/train': 1.5034877061843872} 08/30/2021 22:58:13 - INFO - __main__ - Step 54120: {'lr': 0.00036198669274503274, 'samples': 10391040, 'steps': 54119, 'loss/train': 1.5984971523284912} 08/30/2021 22:58:15 - INFO - __main__ - Step 54121: {'lr': 0.00036198194817074503, 'samples': 10391232, 'steps': 54120, 'loss/train': 1.1868547201156616} 08/30/2021 22:58:15 - INFO - __main__ - Step 54122: {'lr': 0.00036197720354599997, 'samples': 10391424, 'steps': 54121, 'loss/train': 1.0521479845046997} 08/30/2021 22:58:15 - INFO - __main__ - Step 54123: {'lr': 0.0003619724588707997, 'samples': 10391616, 'steps': 54122, 'loss/train': 1.8686732053756714} 08/30/2021 22:58:16 - INFO - __main__ - Step 54124: {'lr': 0.00036196771414514643, 'samples': 10391808, 'steps': 54123, 'loss/train': 1.7459044456481934} 08/30/2021 22:58:16 - INFO - __main__ - Step 54125: {'lr': 0.0003619629693690422, 'samples': 10392000, 'steps': 54124, 'loss/train': 0.03861915320158005} 08/30/2021 22:58:17 - INFO - __main__ - Step 54126: {'lr': 0.00036195822454248916, 'samples': 10392192, 'steps': 54125, 'loss/train': 0.7102423906326294} 08/30/2021 22:58:17 - INFO - __main__ - Step 54127: {'lr': 0.00036195347966548955, 'samples': 10392384, 'steps': 54126, 'loss/train': 1.558639407157898} 08/30/2021 22:58:19 - INFO - __main__ - Step 54128: {'lr': 0.0003619487347380454, 'samples': 10392576, 'steps': 54127, 'loss/train': 2.4915640354156494} 08/30/2021 22:58:20 - INFO - __main__ - Step 54129: {'lr': 0.00036194398976015875, 'samples': 10392768, 'steps': 54128, 'loss/train': 0.8673027157783508} 08/30/2021 22:58:20 - INFO - __main__ - Step 54130: {'lr': 0.00036193924473183205, 'samples': 10392960, 'steps': 54129, 'loss/train': 1.2030518054962158} 08/30/2021 22:58:20 - INFO - __main__ - Step 54131: {'lr': 0.00036193449965306714, 'samples': 10393152, 'steps': 54130, 'loss/train': 1.3709392547607422} 08/30/2021 22:58:21 - INFO - __main__ - Step 54132: {'lr': 0.0003619297545238663, 'samples': 10393344, 'steps': 54131, 'loss/train': 1.8056080341339111} 08/30/2021 22:58:22 - INFO - __main__ - Step 54133: {'lr': 0.00036192500934423163, 'samples': 10393536, 'steps': 54132, 'loss/train': 0.1497471034526825} 08/30/2021 22:58:23 - INFO - __main__ - Step 54134: {'lr': 0.0003619202641141652, 'samples': 10393728, 'steps': 54133, 'loss/train': 1.1492186784744263} 08/30/2021 22:58:23 - INFO - __main__ - Step 54135: {'lr': 0.00036191551883366937, 'samples': 10393920, 'steps': 54134, 'loss/train': 1.6520380973815918} 08/30/2021 22:58:23 - INFO - __main__ - Step 54136: {'lr': 0.000361910773502746, 'samples': 10394112, 'steps': 54135, 'loss/train': 0.6784459352493286} 08/30/2021 22:58:24 - INFO - __main__ - Step 54137: {'lr': 0.00036190602812139757, 'samples': 10394304, 'steps': 54136, 'loss/train': 1.8451042175292969} 08/30/2021 22:58:26 - INFO - __main__ - Step 54138: {'lr': 0.00036190128268962586, 'samples': 10394496, 'steps': 54137, 'loss/train': 0.33997997641563416} 08/30/2021 22:58:26 - INFO - __main__ - Step 54139: {'lr': 0.00036189653720743317, 'samples': 10394688, 'steps': 54138, 'loss/train': 1.1718989610671997} 08/30/2021 22:58:26 - INFO - __main__ - Step 54140: {'lr': 0.0003618917916748216, 'samples': 10394880, 'steps': 54139, 'loss/train': 1.874208927154541} 08/30/2021 22:58:27 - INFO - __main__ - Step 54141: {'lr': 0.00036188704609179333, 'samples': 10395072, 'steps': 54140, 'loss/train': 0.07980351895093918} 08/30/2021 22:58:27 - INFO - __main__ - Step 54142: {'lr': 0.00036188230045835053, 'samples': 10395264, 'steps': 54141, 'loss/train': 1.3706554174423218} 08/30/2021 22:58:29 - INFO - __main__ - Step 54143: {'lr': 0.00036187755477449525, 'samples': 10395456, 'steps': 54142, 'loss/train': 0.09378743171691895} 08/30/2021 22:58:29 - INFO - __main__ - Step 54144: {'lr': 0.00036187280904022973, 'samples': 10395648, 'steps': 54143, 'loss/train': 1.2493839263916016} 08/30/2021 22:58:30 - INFO - __main__ - Step 54145: {'lr': 0.000361868063255556, 'samples': 10395840, 'steps': 54144, 'loss/train': 1.3576929569244385} 08/30/2021 22:58:30 - INFO - __main__ - Step 54146: {'lr': 0.00036186331742047627, 'samples': 10396032, 'steps': 54145, 'loss/train': 1.3930189609527588} 08/30/2021 22:58:30 - INFO - __main__ - Step 54147: {'lr': 0.0003618585715349926, 'samples': 10396224, 'steps': 54146, 'loss/train': 0.05383821204304695} 08/30/2021 22:58:32 - INFO - __main__ - Step 54148: {'lr': 0.00036185382559910723, 'samples': 10396416, 'steps': 54147, 'loss/train': 1.3092625141143799} 08/30/2021 22:58:32 - INFO - __main__ - Step 54149: {'lr': 0.0003618490796128222, 'samples': 10396608, 'steps': 54148, 'loss/train': 0.9480769038200378} 08/30/2021 22:58:33 - INFO - __main__ - Step 54150: {'lr': 0.0003618443335761398, 'samples': 10396800, 'steps': 54149, 'loss/train': 1.4428114891052246} 08/30/2021 22:58:33 - INFO - __main__ - Step 54151: {'lr': 0.00036183958748906204, 'samples': 10396992, 'steps': 54150, 'loss/train': 1.3658024072647095} 08/30/2021 22:58:33 - INFO - __main__ - Step 54152: {'lr': 0.00036183484135159105, 'samples': 10397184, 'steps': 54151, 'loss/train': 1.4825936555862427} 08/30/2021 22:58:35 - INFO - __main__ - Step 54153: {'lr': 0.000361830095163729, 'samples': 10397376, 'steps': 54152, 'loss/train': 1.2851667404174805} 08/30/2021 22:58:35 - INFO - __main__ - Step 54154: {'lr': 0.000361825348925478, 'samples': 10397568, 'steps': 54153, 'loss/train': 1.2316964864730835} 08/30/2021 22:58:36 - INFO - __main__ - Step 54155: {'lr': 0.0003618206026368403, 'samples': 10397760, 'steps': 54154, 'loss/train': 1.2137839794158936} 08/30/2021 22:58:36 - INFO - __main__ - Step 54156: {'lr': 0.00036181585629781795, 'samples': 10397952, 'steps': 54155, 'loss/train': 1.1795769929885864} 08/30/2021 22:58:36 - INFO - __main__ - Step 54157: {'lr': 0.0003618111099084131, 'samples': 10398144, 'steps': 54156, 'loss/train': 1.2153394222259521} 08/30/2021 22:58:37 - INFO - __main__ - Step 54158: {'lr': 0.00036180636346862786, 'samples': 10398336, 'steps': 54157, 'loss/train': 1.553842544555664} 08/30/2021 22:58:38 - INFO - __main__ - Step 54159: {'lr': 0.0003618016169784645, 'samples': 10398528, 'steps': 54158, 'loss/train': 1.4840449094772339} 08/30/2021 22:58:39 - INFO - __main__ - Step 54160: {'lr': 0.0003617968704379249, 'samples': 10398720, 'steps': 54159, 'loss/train': 1.10103440284729} 08/30/2021 22:58:39 - INFO - __main__ - Step 54161: {'lr': 0.0003617921238470114, 'samples': 10398912, 'steps': 54160, 'loss/train': 1.065316081047058} 08/30/2021 22:58:40 - INFO - __main__ - Step 54162: {'lr': 0.00036178737720572615, 'samples': 10399104, 'steps': 54161, 'loss/train': 0.03477616608142853} 08/30/2021 22:58:40 - INFO - __main__ - Step 54163: {'lr': 0.0003617826305140712, 'samples': 10399296, 'steps': 54162, 'loss/train': 0.9488590359687805} 08/30/2021 22:58:41 - INFO - __main__ - Step 54164: {'lr': 0.0003617778837720488, 'samples': 10399488, 'steps': 54163, 'loss/train': 2.0428566932678223} 08/30/2021 22:58:42 - INFO - __main__ - Step 54165: {'lr': 0.00036177313697966087, 'samples': 10399680, 'steps': 54164, 'loss/train': 0.647103488445282} 08/30/2021 22:58:42 - INFO - __main__ - Step 54166: {'lr': 0.00036176839013690975, 'samples': 10399872, 'steps': 54165, 'loss/train': 0.9498745799064636} 08/30/2021 22:58:43 - INFO - __main__ - Step 54167: {'lr': 0.0003617636432437975, 'samples': 10400064, 'steps': 54166, 'loss/train': 1.2474161386489868} 08/30/2021 22:58:43 - INFO - __main__ - Step 54168: {'lr': 0.00036175889630032633, 'samples': 10400256, 'steps': 54167, 'loss/train': 1.1814148426055908} 08/30/2021 22:58:44 - INFO - __main__ - Step 54169: {'lr': 0.0003617541493064983, 'samples': 10400448, 'steps': 54168, 'loss/train': 1.4715523719787598} 08/30/2021 22:58:45 - INFO - __main__ - Step 54170: {'lr': 0.00036174940226231555, 'samples': 10400640, 'steps': 54169, 'loss/train': 1.2243895530700684} 08/30/2021 22:58:45 - INFO - __main__ - Step 54171: {'lr': 0.0003617446551677803, 'samples': 10400832, 'steps': 54170, 'loss/train': 0.5915573239326477} 08/30/2021 22:58:46 - INFO - __main__ - Step 54172: {'lr': 0.0003617399080228946, 'samples': 10401024, 'steps': 54171, 'loss/train': 1.074485421180725} 08/30/2021 22:58:46 - INFO - __main__ - Step 54173: {'lr': 0.0003617351608276606, 'samples': 10401216, 'steps': 54172, 'loss/train': 1.0588046312332153} 08/30/2021 22:58:48 - INFO - __main__ - Step 54174: {'lr': 0.00036173041358208047, 'samples': 10401408, 'steps': 54173, 'loss/train': 1.5918129682540894} 08/30/2021 22:58:49 - INFO - __main__ - Step 54175: {'lr': 0.0003617256662861563, 'samples': 10401600, 'steps': 54174, 'loss/train': 1.5564087629318237} 08/30/2021 22:58:49 - INFO - __main__ - Step 54176: {'lr': 0.00036172091893989033, 'samples': 10401792, 'steps': 54175, 'loss/train': 1.3992847204208374} 08/30/2021 22:58:50 - INFO - __main__ - Step 54177: {'lr': 0.0003617161715432847, 'samples': 10401984, 'steps': 54176, 'loss/train': 1.37216055393219} 08/30/2021 22:58:50 - INFO - __main__ - Step 54178: {'lr': 0.0003617114240963414, 'samples': 10402176, 'steps': 54177, 'loss/train': 1.7359832525253296} 08/30/2021 22:58:50 - INFO - __main__ - Step 54179: {'lr': 0.00036170667659906263, 'samples': 10402368, 'steps': 54178, 'loss/train': 0.7494610548019409} 08/30/2021 22:58:51 - INFO - __main__ - Step 54180: {'lr': 0.0003617019290514506, 'samples': 10402560, 'steps': 54179, 'loss/train': 0.42284879088401794} 08/30/2021 22:58:53 - INFO - __main__ - Step 54181: {'lr': 0.0003616971814535074, 'samples': 10402752, 'steps': 54180, 'loss/train': 0.35809949040412903} 08/30/2021 22:58:53 - INFO - __main__ - Step 54182: {'lr': 0.0003616924338052352, 'samples': 10402944, 'steps': 54181, 'loss/train': 1.7498009204864502} 08/30/2021 22:58:54 - INFO - __main__ - Step 54183: {'lr': 0.00036168768610663605, 'samples': 10403136, 'steps': 54182, 'loss/train': 1.431233525276184} 08/30/2021 22:58:54 - INFO - __main__ - Step 54184: {'lr': 0.0003616829383577123, 'samples': 10403328, 'steps': 54183, 'loss/train': 1.1427468061447144} 08/30/2021 22:58:54 - INFO - __main__ - Step 54185: {'lr': 0.00036167819055846575, 'samples': 10403520, 'steps': 54184, 'loss/train': 1.3367365598678589} 08/30/2021 22:58:56 - INFO - __main__ - Step 54186: {'lr': 0.0003616734427088988, 'samples': 10403712, 'steps': 54185, 'loss/train': 0.16596487164497375} 08/30/2021 22:58:56 - INFO - __main__ - Step 54187: {'lr': 0.00036166869480901354, 'samples': 10403904, 'steps': 54186, 'loss/train': 1.194364309310913} 08/30/2021 22:58:57 - INFO - __main__ - Step 54188: {'lr': 0.0003616639468588121, 'samples': 10404096, 'steps': 54187, 'loss/train': 1.3934091329574585} 08/30/2021 22:58:57 - INFO - __main__ - Step 54189: {'lr': 0.00036165919885829654, 'samples': 10404288, 'steps': 54188, 'loss/train': 0.9677462577819824} 08/30/2021 22:58:57 - INFO - __main__ - Step 54190: {'lr': 0.0003616544508074691, 'samples': 10404480, 'steps': 54189, 'loss/train': 1.6321250200271606} 08/30/2021 22:58:59 - INFO - __main__ - Step 54191: {'lr': 0.00036164970270633195, 'samples': 10404672, 'steps': 54190, 'loss/train': 0.7174428105354309} 08/30/2021 22:58:59 - INFO - __main__ - Step 54192: {'lr': 0.0003616449545548871, 'samples': 10404864, 'steps': 54191, 'loss/train': 1.8042601346969604} 08/30/2021 22:59:00 - INFO - __main__ - Step 54193: {'lr': 0.00036164020635313677, 'samples': 10405056, 'steps': 54192, 'loss/train': 1.4498096704483032} 08/30/2021 22:59:00 - INFO - __main__ - Step 54194: {'lr': 0.0003616354581010831, 'samples': 10405248, 'steps': 54193, 'loss/train': 1.6507689952850342} 08/30/2021 22:59:00 - INFO - __main__ - Step 54195: {'lr': 0.0003616307097987282, 'samples': 10405440, 'steps': 54194, 'loss/train': 1.632206916809082} 08/30/2021 22:59:02 - INFO - __main__ - Step 54196: {'lr': 0.00036162596144607425, 'samples': 10405632, 'steps': 54195, 'loss/train': 1.4007915258407593} 08/30/2021 22:59:03 - INFO - __main__ - Step 54197: {'lr': 0.00036162121304312336, 'samples': 10405824, 'steps': 54196, 'loss/train': 1.2193647623062134} 08/30/2021 22:59:03 - INFO - __main__ - Step 54198: {'lr': 0.0003616164645898776, 'samples': 10406016, 'steps': 54197, 'loss/train': 1.065858006477356} 08/30/2021 22:59:03 - INFO - __main__ - Step 54199: {'lr': 0.0003616117160863393, 'samples': 10406208, 'steps': 54198, 'loss/train': 1.6092778444290161} 08/30/2021 22:59:04 - INFO - __main__ - Step 54200: {'lr': 0.00036160696753251043, 'samples': 10406400, 'steps': 54199, 'loss/train': 3.4266304969787598} 08/30/2021 22:59:04 - INFO - __main__ - Step 54201: {'lr': 0.0003616022189283932, 'samples': 10406592, 'steps': 54200, 'loss/train': 1.0664523839950562} 08/30/2021 22:59:05 - INFO - __main__ - Step 54202: {'lr': 0.00036159747027398963, 'samples': 10406784, 'steps': 54201, 'loss/train': 0.6084858775138855} 08/30/2021 22:59:06 - INFO - __main__ - Step 54203: {'lr': 0.0003615927215693021, 'samples': 10406976, 'steps': 54202, 'loss/train': 0.879784107208252} 08/30/2021 22:59:06 - INFO - __main__ - Step 54204: {'lr': 0.0003615879728143325, 'samples': 10407168, 'steps': 54203, 'loss/train': 1.2554460763931274} 08/30/2021 22:59:07 - INFO - __main__ - Step 54205: {'lr': 0.00036158322400908316, 'samples': 10407360, 'steps': 54204, 'loss/train': 1.0786643028259277} 08/30/2021 22:59:07 - INFO - __main__ - Step 54206: {'lr': 0.00036157847515355614, 'samples': 10407552, 'steps': 54205, 'loss/train': 0.7475901246070862} 08/30/2021 22:59:09 - INFO - __main__ - Step 54207: {'lr': 0.0003615737262477535, 'samples': 10407744, 'steps': 54206, 'loss/train': 1.323480486869812} 08/30/2021 22:59:10 - INFO - __main__ - Step 54208: {'lr': 0.0003615689772916776, 'samples': 10407936, 'steps': 54207, 'loss/train': 0.803510844707489} 08/30/2021 22:59:10 - INFO - __main__ - Step 54209: {'lr': 0.00036156422828533035, 'samples': 10408128, 'steps': 54208, 'loss/train': 0.7921726703643799} 08/30/2021 22:59:11 - INFO - __main__ - Step 54210: {'lr': 0.000361559479228714, 'samples': 10408320, 'steps': 54209, 'loss/train': 1.9012155532836914} 08/30/2021 22:59:11 - INFO - __main__ - Step 54211: {'lr': 0.00036155473012183066, 'samples': 10408512, 'steps': 54210, 'loss/train': 1.127052903175354} 08/30/2021 22:59:11 - INFO - __main__ - Step 54212: {'lr': 0.00036154998096468244, 'samples': 10408704, 'steps': 54211, 'loss/train': 1.3459440469741821} 08/30/2021 22:59:12 - INFO - __main__ - Step 54213: {'lr': 0.00036154523175727153, 'samples': 10408896, 'steps': 54212, 'loss/train': 1.5702800750732422} 08/30/2021 22:59:13 - INFO - __main__ - Step 54214: {'lr': 0.00036154048249960015, 'samples': 10409088, 'steps': 54213, 'loss/train': 1.400362253189087} 08/30/2021 22:59:14 - INFO - __main__ - Step 54215: {'lr': 0.0003615357331916703, 'samples': 10409280, 'steps': 54214, 'loss/train': 1.5849727392196655} 08/30/2021 22:59:14 - INFO - __main__ - Step 54216: {'lr': 0.0003615309838334841, 'samples': 10409472, 'steps': 54215, 'loss/train': 1.2600560188293457} 08/30/2021 22:59:15 - INFO - __main__ - Step 54217: {'lr': 0.00036152623442504386, 'samples': 10409664, 'steps': 54216, 'loss/train': 1.2272979021072388} 08/30/2021 22:59:15 - INFO - __main__ - Step 54218: {'lr': 0.0003615214849663516, 'samples': 10409856, 'steps': 54217, 'loss/train': 0.1535966694355011} 08/30/2021 22:59:16 - INFO - __main__ - Step 54219: {'lr': 0.0003615167354574094, 'samples': 10410048, 'steps': 54218, 'loss/train': 1.2791833877563477} 08/30/2021 22:59:17 - INFO - __main__ - Step 54220: {'lr': 0.0003615119858982196, 'samples': 10410240, 'steps': 54219, 'loss/train': 1.2066028118133545} 08/30/2021 22:59:17 - INFO - __main__ - Step 54221: {'lr': 0.0003615072362887841, 'samples': 10410432, 'steps': 54220, 'loss/train': 1.60999596118927} 08/30/2021 22:59:18 - INFO - __main__ - Step 54222: {'lr': 0.0003615024866291052, 'samples': 10410624, 'steps': 54221, 'loss/train': 0.7926939129829407} 08/30/2021 22:59:18 - INFO - __main__ - Step 54223: {'lr': 0.0003614977369191851, 'samples': 10410816, 'steps': 54222, 'loss/train': 1.4695885181427002} 08/30/2021 22:59:19 - INFO - __main__ - Step 54224: {'lr': 0.00036149298715902573, 'samples': 10411008, 'steps': 54223, 'loss/train': 1.1728781461715698} 08/30/2021 22:59:20 - INFO - __main__ - Step 54225: {'lr': 0.00036148823734862934, 'samples': 10411200, 'steps': 54224, 'loss/train': 1.0331125259399414} 08/30/2021 22:59:20 - INFO - __main__ - Step 54226: {'lr': 0.00036148348748799816, 'samples': 10411392, 'steps': 54225, 'loss/train': 1.4559595584869385} 08/30/2021 22:59:21 - INFO - __main__ - Step 54227: {'lr': 0.00036147873757713417, 'samples': 10411584, 'steps': 54226, 'loss/train': 1.544517159461975} 08/30/2021 22:59:21 - INFO - __main__ - Step 54228: {'lr': 0.0003614739876160396, 'samples': 10411776, 'steps': 54227, 'loss/train': 1.3546228408813477} 08/30/2021 22:59:23 - INFO - __main__ - Step 54229: {'lr': 0.0003614692376047165, 'samples': 10411968, 'steps': 54228, 'loss/train': 1.2377036809921265} 08/30/2021 22:59:23 - INFO - __main__ - Step 54230: {'lr': 0.00036146448754316717, 'samples': 10412160, 'steps': 54229, 'loss/train': 1.2535866498947144} 08/30/2021 22:59:23 - INFO - __main__ - Step 54231: {'lr': 0.0003614597374313937, 'samples': 10412352, 'steps': 54230, 'loss/train': 1.4869279861450195} 08/30/2021 22:59:24 - INFO - __main__ - Step 54232: {'lr': 0.00036145498726939806, 'samples': 10412544, 'steps': 54231, 'loss/train': 0.9444723129272461} 08/30/2021 22:59:24 - INFO - __main__ - Step 54233: {'lr': 0.0003614502370571826, 'samples': 10412736, 'steps': 54232, 'loss/train': 0.5442521572113037} 08/30/2021 22:59:24 - INFO - __main__ - Step 54234: {'lr': 0.00036144548679474943, 'samples': 10412928, 'steps': 54233, 'loss/train': 0.5774440765380859} 08/30/2021 22:59:26 - INFO - __main__ - Step 54235: {'lr': 0.0003614407364821005, 'samples': 10413120, 'steps': 54234, 'loss/train': 3.4268136024475098} 08/30/2021 22:59:27 - INFO - __main__ - Step 54236: {'lr': 0.0003614359861192382, 'samples': 10413312, 'steps': 54235, 'loss/train': 1.2223607301712036} 08/30/2021 22:59:27 - INFO - __main__ - Step 54237: {'lr': 0.00036143123570616455, 'samples': 10413504, 'steps': 54236, 'loss/train': 1.7738897800445557} 08/30/2021 22:59:27 - INFO - __main__ - Step 54238: {'lr': 0.0003614264852428817, 'samples': 10413696, 'steps': 54237, 'loss/train': 1.0485506057739258} 08/30/2021 22:59:28 - INFO - __main__ - Step 54239: {'lr': 0.0003614217347293918, 'samples': 10413888, 'steps': 54238, 'loss/train': 0.057003192603588104} 08/30/2021 22:59:28 - INFO - __main__ - Step 54240: {'lr': 0.000361416984165697, 'samples': 10414080, 'steps': 54239, 'loss/train': 1.8271238803863525} 08/30/2021 22:59:30 - INFO - __main__ - Step 54241: {'lr': 0.0003614122335517994, 'samples': 10414272, 'steps': 54240, 'loss/train': 1.7151165008544922} 08/30/2021 22:59:31 - INFO - __main__ - Step 54242: {'lr': 0.0003614074828877012, 'samples': 10414464, 'steps': 54241, 'loss/train': 1.3838129043579102} 08/30/2021 22:59:31 - INFO - __main__ - Step 54243: {'lr': 0.00036140273217340446, 'samples': 10414656, 'steps': 54242, 'loss/train': 1.9005241394042969} 08/30/2021 22:59:31 - INFO - __main__ - Step 54244: {'lr': 0.00036139798140891134, 'samples': 10414848, 'steps': 54243, 'loss/train': 1.2426371574401855} 08/30/2021 22:59:32 - INFO - __main__ - Step 54245: {'lr': 0.0003613932305942241, 'samples': 10415040, 'steps': 54244, 'loss/train': 1.113200306892395} 08/30/2021 22:59:33 - INFO - __main__ - Step 54246: {'lr': 0.00036138847972934477, 'samples': 10415232, 'steps': 54245, 'loss/train': 1.407149076461792} 08/30/2021 22:59:34 - INFO - __main__ - Step 54247: {'lr': 0.0003613837288142755, 'samples': 10415424, 'steps': 54246, 'loss/train': 1.5452519655227661} 08/30/2021 22:59:34 - INFO - __main__ - Step 54248: {'lr': 0.00036137897784901843, 'samples': 10415616, 'steps': 54247, 'loss/train': 0.7409790754318237} 08/30/2021 22:59:34 - INFO - __main__ - Step 54249: {'lr': 0.00036137422683357566, 'samples': 10415808, 'steps': 54248, 'loss/train': 1.4738839864730835} 08/30/2021 22:59:35 - INFO - __main__ - Step 54250: {'lr': 0.00036136947576794945, 'samples': 10416000, 'steps': 54249, 'loss/train': 1.518761396408081} 08/30/2021 22:59:36 - INFO - __main__ - Step 54251: {'lr': 0.00036136472465214187, 'samples': 10416192, 'steps': 54250, 'loss/train': 1.5369452238082886} 08/30/2021 22:59:37 - INFO - __main__ - Step 54252: {'lr': 0.00036135997348615503, 'samples': 10416384, 'steps': 54251, 'loss/train': 1.0127211809158325} 08/30/2021 22:59:37 - INFO - __main__ - Step 54253: {'lr': 0.00036135522226999115, 'samples': 10416576, 'steps': 54252, 'loss/train': 0.9309428930282593} 08/30/2021 22:59:37 - INFO - __main__ - Step 54254: {'lr': 0.00036135047100365223, 'samples': 10416768, 'steps': 54253, 'loss/train': 0.9776472449302673} 08/30/2021 22:59:38 - INFO - __main__ - Step 54255: {'lr': 0.00036134571968714056, 'samples': 10416960, 'steps': 54254, 'loss/train': 0.6639416813850403} 08/30/2021 22:59:38 - INFO - __main__ - Step 54256: {'lr': 0.00036134096832045825, 'samples': 10417152, 'steps': 54255, 'loss/train': 1.078926682472229} 08/30/2021 22:59:40 - INFO - __main__ - Step 54257: {'lr': 0.0003613362169036074, 'samples': 10417344, 'steps': 54256, 'loss/train': 1.7038991451263428} 08/30/2021 22:59:40 - INFO - __main__ - Step 54258: {'lr': 0.00036133146543659026, 'samples': 10417536, 'steps': 54257, 'loss/train': 1.41621994972229} 08/30/2021 22:59:40 - INFO - __main__ - Step 54259: {'lr': 0.00036132671391940875, 'samples': 10417728, 'steps': 54258, 'loss/train': 1.4720511436462402} 08/30/2021 22:59:41 - INFO - __main__ - Step 54260: {'lr': 0.0003613219623520652, 'samples': 10417920, 'steps': 54259, 'loss/train': 1.2003247737884521} 08/30/2021 22:59:41 - INFO - __main__ - Step 54261: {'lr': 0.00036131721073456163, 'samples': 10418112, 'steps': 54260, 'loss/train': 1.0252692699432373} 08/30/2021 22:59:43 - INFO - __main__ - Step 54262: {'lr': 0.0003613124590669003, 'samples': 10418304, 'steps': 54261, 'loss/train': 0.974557101726532} 08/30/2021 22:59:43 - INFO - __main__ - Step 54263: {'lr': 0.0003613077073490832, 'samples': 10418496, 'steps': 54262, 'loss/train': 1.3212673664093018} 08/30/2021 22:59:44 - INFO - __main__ - Step 54264: {'lr': 0.0003613029555811127, 'samples': 10418688, 'steps': 54263, 'loss/train': 0.159384086728096} 08/30/2021 22:59:44 - INFO - __main__ - Step 54265: {'lr': 0.0003612982037629908, 'samples': 10418880, 'steps': 54264, 'loss/train': 1.466238260269165} 08/30/2021 22:59:44 - INFO - __main__ - Step 54266: {'lr': 0.0003612934518947196, 'samples': 10419072, 'steps': 54265, 'loss/train': 1.327729344367981} 08/30/2021 22:59:46 - INFO - __main__ - Step 54267: {'lr': 0.00036128869997630134, 'samples': 10419264, 'steps': 54266, 'loss/train': 1.7651138305664062} 08/30/2021 22:59:46 - INFO - __main__ - Step 54268: {'lr': 0.000361283948007738, 'samples': 10419456, 'steps': 54267, 'loss/train': 1.2321785688400269} 08/30/2021 22:59:47 - INFO - __main__ - Step 54269: {'lr': 0.00036127919598903186, 'samples': 10419648, 'steps': 54268, 'loss/train': 1.2316728830337524} 08/30/2021 22:59:47 - INFO - __main__ - Step 54270: {'lr': 0.00036127444392018503, 'samples': 10419840, 'steps': 54269, 'loss/train': 1.0768077373504639} 08/30/2021 22:59:47 - INFO - __main__ - Step 54271: {'lr': 0.00036126969180119977, 'samples': 10420032, 'steps': 54270, 'loss/train': 2.1287810802459717} 08/30/2021 22:59:49 - INFO - __main__ - Step 54272: {'lr': 0.000361264939632078, 'samples': 10420224, 'steps': 54271, 'loss/train': 0.8181988596916199} 08/30/2021 22:59:50 - INFO - __main__ - Step 54273: {'lr': 0.00036126018741282194, 'samples': 10420416, 'steps': 54272, 'loss/train': 1.167194128036499} 08/30/2021 22:59:50 - INFO - __main__ - Step 54274: {'lr': 0.0003612554351434338, 'samples': 10420608, 'steps': 54273, 'loss/train': 1.6690635681152344} 08/30/2021 22:59:50 - INFO - __main__ - Step 54275: {'lr': 0.0003612506828239157, 'samples': 10420800, 'steps': 54274, 'loss/train': 1.6225290298461914} 08/30/2021 22:59:51 - INFO - __main__ - Step 54276: {'lr': 0.00036124593045426973, 'samples': 10420992, 'steps': 54275, 'loss/train': 1.4091507196426392} 08/30/2021 22:59:51 - INFO - __main__ - Step 54277: {'lr': 0.00036124117803449805, 'samples': 10421184, 'steps': 54276, 'loss/train': 1.0258644819259644} 08/30/2021 22:59:53 - INFO - __main__ - Step 54278: {'lr': 0.00036123642556460284, 'samples': 10421376, 'steps': 54277, 'loss/train': 0.03130926191806793} 08/30/2021 22:59:53 - INFO - __main__ - Step 54279: {'lr': 0.0003612316730445862, 'samples': 10421568, 'steps': 54278, 'loss/train': 1.3339954614639282} 08/30/2021 22:59:53 - INFO - __main__ - Step 54280: {'lr': 0.00036122692047445027, 'samples': 10421760, 'steps': 54279, 'loss/train': 0.13934817910194397} 08/30/2021 22:59:54 - INFO - __main__ - Step 54281: {'lr': 0.00036122216785419725, 'samples': 10421952, 'steps': 54280, 'loss/train': 1.2006418704986572} 08/30/2021 22:59:54 - INFO - __main__ - Step 54282: {'lr': 0.00036121741518382915, 'samples': 10422144, 'steps': 54281, 'loss/train': 1.534908413887024} 08/30/2021 22:59:56 - INFO - __main__ - Step 54283: {'lr': 0.00036121266246334825, 'samples': 10422336, 'steps': 54282, 'loss/train': 1.3351444005966187} 08/30/2021 22:59:56 - INFO - __main__ - Step 54284: {'lr': 0.00036120790969275667, 'samples': 10422528, 'steps': 54283, 'loss/train': 1.4599113464355469} 08/30/2021 22:59:56 - INFO - __main__ - Step 54285: {'lr': 0.0003612031568720565, 'samples': 10422720, 'steps': 54284, 'loss/train': 1.071659803390503} 08/30/2021 22:59:57 - INFO - __main__ - Step 54286: {'lr': 0.0003611984040012499, 'samples': 10422912, 'steps': 54285, 'loss/train': 0.8707094192504883} 08/30/2021 22:59:57 - INFO - __main__ - Step 54287: {'lr': 0.000361193651080339, 'samples': 10423104, 'steps': 54286, 'loss/train': 1.6434024572372437} 08/30/2021 22:59:59 - INFO - __main__ - Step 54288: {'lr': 0.000361188898109326, 'samples': 10423296, 'steps': 54287, 'loss/train': 1.622084617614746} 08/30/2021 22:59:59 - INFO - __main__ - Step 54289: {'lr': 0.00036118414508821295, 'samples': 10423488, 'steps': 54288, 'loss/train': 1.411124587059021} 08/30/2021 22:59:59 - INFO - __main__ - Step 54290: {'lr': 0.0003611793920170021, 'samples': 10423680, 'steps': 54289, 'loss/train': 1.420058012008667} 08/30/2021 23:00:00 - INFO - __main__ - Step 54291: {'lr': 0.0003611746388956955, 'samples': 10423872, 'steps': 54290, 'loss/train': 1.2150386571884155} 08/30/2021 23:00:00 - INFO - __main__ - Step 54292: {'lr': 0.00036116988572429534, 'samples': 10424064, 'steps': 54291, 'loss/train': 1.2232204675674438} 08/30/2021 23:00:02 - INFO - __main__ - Step 54293: {'lr': 0.0003611651325028037, 'samples': 10424256, 'steps': 54292, 'loss/train': 0.9685659408569336} 08/30/2021 23:00:03 - INFO - __main__ - Step 54294: {'lr': 0.0003611603792312228, 'samples': 10424448, 'steps': 54293, 'loss/train': 1.0455782413482666} 08/30/2021 23:00:03 - INFO - __main__ - Step 54295: {'lr': 0.0003611556259095547, 'samples': 10424640, 'steps': 54294, 'loss/train': 1.7435473203659058} 08/30/2021 23:00:04 - INFO - __main__ - Step 54296: {'lr': 0.00036115087253780164, 'samples': 10424832, 'steps': 54295, 'loss/train': 1.2525943517684937} 08/30/2021 23:00:04 - INFO - __main__ - Step 54297: {'lr': 0.0003611461191159657, 'samples': 10425024, 'steps': 54296, 'loss/train': 1.840232014656067} 08/30/2021 23:00:04 - INFO - __main__ - Step 54298: {'lr': 0.00036114136564404905, 'samples': 10425216, 'steps': 54297, 'loss/train': 0.4785672128200531} 08/30/2021 23:00:06 - INFO - __main__ - Step 54299: {'lr': 0.0003611366121220538, 'samples': 10425408, 'steps': 54298, 'loss/train': 1.0064611434936523} 08/30/2021 23:00:06 - INFO - __main__ - Step 54300: {'lr': 0.0003611318585499821, 'samples': 10425600, 'steps': 54299, 'loss/train': 1.299284815788269} 08/30/2021 23:00:07 - INFO - __main__ - Step 54301: {'lr': 0.00036112710492783605, 'samples': 10425792, 'steps': 54300, 'loss/train': 0.7138924598693848} 08/30/2021 23:00:07 - INFO - __main__ - Step 54302: {'lr': 0.0003611223512556179, 'samples': 10425984, 'steps': 54301, 'loss/train': 0.9210470914840698} 08/30/2021 23:00:07 - INFO - __main__ - Step 54303: {'lr': 0.0003611175975333297, 'samples': 10426176, 'steps': 54302, 'loss/train': 1.1328192949295044} 08/30/2021 23:00:09 - INFO - __main__ - Step 54304: {'lr': 0.0003611128437609737, 'samples': 10426368, 'steps': 54303, 'loss/train': 1.5380455255508423} 08/30/2021 23:00:09 - INFO - __main__ - Step 54305: {'lr': 0.00036110808993855195, 'samples': 10426560, 'steps': 54304, 'loss/train': 1.72883939743042} 08/30/2021 23:00:10 - INFO - __main__ - Step 54306: {'lr': 0.0003611033360660666, 'samples': 10426752, 'steps': 54305, 'loss/train': 1.994649887084961} 08/30/2021 23:00:10 - INFO - __main__ - Step 54307: {'lr': 0.00036109858214351977, 'samples': 10426944, 'steps': 54306, 'loss/train': 0.8268476724624634} 08/30/2021 23:00:10 - INFO - __main__ - Step 54308: {'lr': 0.0003610938281709136, 'samples': 10427136, 'steps': 54307, 'loss/train': 3.1488285064697266} 08/30/2021 23:00:12 - INFO - __main__ - Step 54309: {'lr': 0.0003610890741482503, 'samples': 10427328, 'steps': 54308, 'loss/train': 0.8107359409332275} 08/30/2021 23:00:12 - INFO - __main__ - Step 54310: {'lr': 0.000361084320075532, 'samples': 10427520, 'steps': 54309, 'loss/train': 1.6099568605422974} 08/30/2021 23:00:13 - INFO - __main__ - Step 54311: {'lr': 0.00036107956595276083, 'samples': 10427712, 'steps': 54310, 'loss/train': 1.3700376749038696} 08/30/2021 23:00:13 - INFO - __main__ - Step 54312: {'lr': 0.00036107481177993897, 'samples': 10427904, 'steps': 54311, 'loss/train': 0.1530822068452835} 08/30/2021 23:00:14 - INFO - __main__ - Step 54313: {'lr': 0.0003610700575570684, 'samples': 10428096, 'steps': 54312, 'loss/train': 1.2222754955291748} 08/30/2021 23:00:15 - INFO - __main__ - Step 54314: {'lr': 0.00036106530328415136, 'samples': 10428288, 'steps': 54313, 'loss/train': 1.2541207075119019} 08/30/2021 23:00:15 - INFO - __main__ - Step 54315: {'lr': 0.0003610605489611901, 'samples': 10428480, 'steps': 54314, 'loss/train': 0.7728841304779053} 08/30/2021 23:00:16 - INFO - __main__ - Step 54316: {'lr': 0.0003610557945881866, 'samples': 10428672, 'steps': 54315, 'loss/train': 1.279334545135498} 08/30/2021 23:00:16 - INFO - __main__ - Step 54317: {'lr': 0.0003610510401651431, 'samples': 10428864, 'steps': 54316, 'loss/train': 1.0612679719924927} 08/30/2021 23:00:17 - INFO - __main__ - Step 54318: {'lr': 0.00036104628569206176, 'samples': 10429056, 'steps': 54317, 'loss/train': 0.7022980451583862} 08/30/2021 23:00:17 - INFO - __main__ - Step 54319: {'lr': 0.00036104153116894465, 'samples': 10429248, 'steps': 54318, 'loss/train': 0.8806092143058777} 08/30/2021 23:00:18 - INFO - __main__ - Step 54320: {'lr': 0.00036103677659579393, 'samples': 10429440, 'steps': 54319, 'loss/train': 1.2294496297836304} 08/30/2021 23:00:19 - INFO - __main__ - Step 54321: {'lr': 0.0003610320219726118, 'samples': 10429632, 'steps': 54320, 'loss/train': 1.6851475238800049} 08/30/2021 23:00:19 - INFO - __main__ - Step 54322: {'lr': 0.00036102726729940026, 'samples': 10429824, 'steps': 54321, 'loss/train': 1.4001877307891846} 08/30/2021 23:00:19 - INFO - __main__ - Step 54323: {'lr': 0.0003610225125761616, 'samples': 10430016, 'steps': 54322, 'loss/train': 1.3912405967712402} 08/30/2021 23:00:20 - INFO - __main__ - Step 54324: {'lr': 0.0003610177578028979, 'samples': 10430208, 'steps': 54323, 'loss/train': 1.9676052331924438} 08/30/2021 23:00:21 - INFO - __main__ - Step 54325: {'lr': 0.0003610130029796114, 'samples': 10430400, 'steps': 54324, 'loss/train': 1.4980096817016602} 08/30/2021 23:00:22 - INFO - __main__ - Step 54326: {'lr': 0.000361008248106304, 'samples': 10430592, 'steps': 54325, 'loss/train': 1.413459300994873} 08/30/2021 23:00:22 - INFO - __main__ - Step 54327: {'lr': 0.0003610034931829781, 'samples': 10430784, 'steps': 54326, 'loss/train': 1.151256799697876} 08/30/2021 23:00:22 - INFO - __main__ - Step 54328: {'lr': 0.0003609987382096357, 'samples': 10430976, 'steps': 54327, 'loss/train': 1.3196914196014404} 08/30/2021 23:00:23 - INFO - __main__ - Step 54329: {'lr': 0.00036099398318627896, 'samples': 10431168, 'steps': 54328, 'loss/train': 1.2981704473495483} 08/30/2021 23:00:24 - INFO - __main__ - Step 54330: {'lr': 0.00036098922811291, 'samples': 10431360, 'steps': 54329, 'loss/train': 1.1940737962722778} 08/30/2021 23:00:25 - INFO - __main__ - Step 54331: {'lr': 0.00036098447298953107, 'samples': 10431552, 'steps': 54330, 'loss/train': 1.2637882232666016} 08/30/2021 23:00:25 - INFO - __main__ - Step 54332: {'lr': 0.00036097971781614435, 'samples': 10431744, 'steps': 54331, 'loss/train': 1.6388776302337646} 08/30/2021 23:00:25 - INFO - __main__ - Step 54333: {'lr': 0.0003609749625927518, 'samples': 10431936, 'steps': 54332, 'loss/train': 1.606168508529663} 08/30/2021 23:00:26 - INFO - __main__ - Step 54334: {'lr': 0.0003609702073193556, 'samples': 10432128, 'steps': 54333, 'loss/train': 0.9753102660179138} 08/30/2021 23:00:27 - INFO - __main__ - Step 54335: {'lr': 0.000360965451995958, 'samples': 10432320, 'steps': 54334, 'loss/train': 1.518958330154419} 08/30/2021 23:00:28 - INFO - __main__ - Step 54336: {'lr': 0.000360960696622561, 'samples': 10432512, 'steps': 54335, 'loss/train': 0.04328807443380356} 08/30/2021 23:00:28 - INFO - __main__ - Step 54337: {'lr': 0.0003609559411991669, 'samples': 10432704, 'steps': 54336, 'loss/train': 0.8732128739356995} 08/30/2021 23:00:29 - INFO - __main__ - Step 54338: {'lr': 0.00036095118572577773, 'samples': 10432896, 'steps': 54337, 'loss/train': 0.049343254417181015} 08/30/2021 23:00:29 - INFO - __main__ - Step 54339: {'lr': 0.00036094643020239564, 'samples': 10433088, 'steps': 54338, 'loss/train': 1.0345513820648193} 08/30/2021 23:00:30 - INFO - __main__ - Step 54340: {'lr': 0.0003609416746290228, 'samples': 10433280, 'steps': 54339, 'loss/train': 1.2922474145889282} 08/30/2021 23:00:31 - INFO - __main__ - Step 54341: {'lr': 0.00036093691900566146, 'samples': 10433472, 'steps': 54340, 'loss/train': 1.583540678024292} 08/30/2021 23:00:31 - INFO - __main__ - Step 54342: {'lr': 0.00036093216333231356, 'samples': 10433664, 'steps': 54341, 'loss/train': 1.385217308998108} 08/30/2021 23:00:32 - INFO - __main__ - Step 54343: {'lr': 0.0003609274076089813, 'samples': 10433856, 'steps': 54342, 'loss/train': 1.4844633340835571} 08/30/2021 23:00:32 - INFO - __main__ - Step 54344: {'lr': 0.00036092265183566705, 'samples': 10434048, 'steps': 54343, 'loss/train': 1.3687350749969482} 08/30/2021 23:00:33 - INFO - __main__ - Step 54345: {'lr': 0.0003609178960123726, 'samples': 10434240, 'steps': 54344, 'loss/train': 0.6998049020767212} 08/30/2021 23:00:34 - INFO - __main__ - Step 54346: {'lr': 0.0003609131401391003, 'samples': 10434432, 'steps': 54345, 'loss/train': 1.0882056951522827} 08/30/2021 23:00:34 - INFO - __main__ - Step 54347: {'lr': 0.00036090838421585223, 'samples': 10434624, 'steps': 54346, 'loss/train': 1.3963369131088257} 08/30/2021 23:00:34 - INFO - __main__ - Step 54348: {'lr': 0.0003609036282426306, 'samples': 10434816, 'steps': 54347, 'loss/train': 1.0777093172073364} 08/30/2021 23:00:35 - INFO - __main__ - Step 54349: {'lr': 0.0003608988722194375, 'samples': 10435008, 'steps': 54348, 'loss/train': 1.2569193840026855} 08/30/2021 23:00:37 - INFO - __main__ - Step 54350: {'lr': 0.000360894116146275, 'samples': 10435200, 'steps': 54349, 'loss/train': 1.5837812423706055} 08/30/2021 23:00:37 - INFO - __main__ - Step 54351: {'lr': 0.0003608893600231454, 'samples': 10435392, 'steps': 54350, 'loss/train': 1.5440295934677124} 08/30/2021 23:00:38 - INFO - __main__ - Step 54352: {'lr': 0.00036088460385005076, 'samples': 10435584, 'steps': 54351, 'loss/train': 0.9434706568717957} 08/30/2021 23:00:38 - INFO - __main__ - Step 54353: {'lr': 0.00036087984762699316, 'samples': 10435776, 'steps': 54352, 'loss/train': 1.3542704582214355} 08/30/2021 23:00:38 - INFO - __main__ - Step 54354: {'lr': 0.00036087509135397487, 'samples': 10435968, 'steps': 54353, 'loss/train': 0.21786858141422272} 08/30/2021 23:00:40 - INFO - __main__ - Step 54355: {'lr': 0.00036087033503099796, 'samples': 10436160, 'steps': 54354, 'loss/train': 1.5578293800354004} 08/30/2021 23:00:40 - INFO - __main__ - Step 54356: {'lr': 0.00036086557865806464, 'samples': 10436352, 'steps': 54355, 'loss/train': 1.0738296508789062} 08/30/2021 23:00:41 - INFO - __main__ - Step 54357: {'lr': 0.000360860822235177, 'samples': 10436544, 'steps': 54356, 'loss/train': 1.2405059337615967} 08/30/2021 23:00:41 - INFO - __main__ - Step 54358: {'lr': 0.0003608560657623371, 'samples': 10436736, 'steps': 54357, 'loss/train': 0.8637553453445435} 08/30/2021 23:00:41 - INFO - __main__ - Step 54359: {'lr': 0.0003608513092395472, 'samples': 10436928, 'steps': 54358, 'loss/train': 1.900701880455017} 08/30/2021 23:00:43 - INFO - __main__ - Step 54360: {'lr': 0.00036084655266680946, 'samples': 10437120, 'steps': 54359, 'loss/train': 0.2656385004520416} 08/30/2021 23:00:43 - INFO - __main__ - Step 54361: {'lr': 0.00036084179604412594, 'samples': 10437312, 'steps': 54360, 'loss/train': 1.4094173908233643} 08/30/2021 23:00:44 - INFO - __main__ - Step 54362: {'lr': 0.00036083703937149877, 'samples': 10437504, 'steps': 54361, 'loss/train': 1.896064043045044} 08/30/2021 23:00:44 - INFO - __main__ - Step 54363: {'lr': 0.0003608322826489302, 'samples': 10437696, 'steps': 54362, 'loss/train': 0.8309762477874756} 08/30/2021 23:00:44 - INFO - __main__ - Step 54364: {'lr': 0.00036082752587642225, 'samples': 10437888, 'steps': 54363, 'loss/train': 0.1629410833120346} 08/30/2021 23:00:45 - INFO - __main__ - Step 54365: {'lr': 0.00036082276905397714, 'samples': 10438080, 'steps': 54364, 'loss/train': 0.3419945538043976} 08/30/2021 23:00:46 - INFO - __main__ - Step 54366: {'lr': 0.0003608180121815971, 'samples': 10438272, 'steps': 54365, 'loss/train': 1.1949297189712524} 08/30/2021 23:00:47 - INFO - __main__ - Step 54367: {'lr': 0.0003608132552592841, 'samples': 10438464, 'steps': 54366, 'loss/train': 1.0680665969848633} 08/30/2021 23:00:47 - INFO - __main__ - Step 54368: {'lr': 0.0003608084982870404, 'samples': 10438656, 'steps': 54367, 'loss/train': 0.6926573514938354} 08/30/2021 23:00:47 - INFO - __main__ - Step 54369: {'lr': 0.00036080374126486804, 'samples': 10438848, 'steps': 54368, 'loss/train': 1.5133802890777588} 08/30/2021 23:00:48 - INFO - __main__ - Step 54370: {'lr': 0.00036079898419276923, 'samples': 10439040, 'steps': 54369, 'loss/train': 1.3536357879638672} 08/30/2021 23:00:49 - INFO - __main__ - Step 54371: {'lr': 0.0003607942270707461, 'samples': 10439232, 'steps': 54370, 'loss/train': 0.04309569299221039} 08/30/2021 23:00:50 - INFO - __main__ - Step 54372: {'lr': 0.0003607894698988009, 'samples': 10439424, 'steps': 54371, 'loss/train': 0.8834048509597778} 08/30/2021 23:00:50 - INFO - __main__ - Step 54373: {'lr': 0.0003607847126769356, 'samples': 10439616, 'steps': 54372, 'loss/train': 0.8419795036315918} 08/30/2021 23:00:50 - INFO - __main__ - Step 54374: {'lr': 0.0003607799554051524, 'samples': 10439808, 'steps': 54373, 'loss/train': 1.3162957429885864} 08/30/2021 23:00:51 - INFO - __main__ - Step 54375: {'lr': 0.0003607751980834535, 'samples': 10440000, 'steps': 54374, 'loss/train': 0.9299314618110657} 08/30/2021 23:00:51 - INFO - __main__ - Step 54376: {'lr': 0.00036077044071184094, 'samples': 10440192, 'steps': 54375, 'loss/train': 1.0959758758544922} 08/30/2021 23:00:53 - INFO - __main__ - Step 54377: {'lr': 0.00036076568329031694, 'samples': 10440384, 'steps': 54376, 'loss/train': 1.0444085597991943} 08/30/2021 23:00:53 - INFO - __main__ - Step 54378: {'lr': 0.0003607609258188837, 'samples': 10440576, 'steps': 54377, 'loss/train': 1.097976803779602} 08/30/2021 23:00:53 - INFO - __main__ - Step 54379: {'lr': 0.00036075616829754333, 'samples': 10440768, 'steps': 54378, 'loss/train': 1.7999595403671265} 08/30/2021 23:00:54 - INFO - __main__ - Step 54380: {'lr': 0.0003607514107262978, 'samples': 10440960, 'steps': 54379, 'loss/train': 1.6188349723815918} 08/30/2021 23:00:54 - INFO - __main__ - Step 54381: {'lr': 0.0003607466531051495, 'samples': 10441152, 'steps': 54380, 'loss/train': 1.3003886938095093} 08/30/2021 23:00:55 - INFO - __main__ - Step 54382: {'lr': 0.0003607418954341004, 'samples': 10441344, 'steps': 54381, 'loss/train': 2.1505913734436035} 08/30/2021 23:00:56 - INFO - __main__ - Step 54383: {'lr': 0.00036073713771315276, 'samples': 10441536, 'steps': 54382, 'loss/train': 1.0358531475067139} 08/30/2021 23:00:56 - INFO - __main__ - Step 54384: {'lr': 0.00036073237994230863, 'samples': 10441728, 'steps': 54383, 'loss/train': 1.5749377012252808} 08/30/2021 23:00:57 - INFO - __main__ - Step 54385: {'lr': 0.0003607276221215702, 'samples': 10441920, 'steps': 54384, 'loss/train': 0.6855916380882263} 08/30/2021 23:00:57 - INFO - __main__ - Step 54386: {'lr': 0.0003607228642509397, 'samples': 10442112, 'steps': 54385, 'loss/train': 0.33559802174568176} 08/30/2021 23:00:59 - INFO - __main__ - Step 54387: {'lr': 0.00036071810633041913, 'samples': 10442304, 'steps': 54386, 'loss/train': 2.230074882507324} 08/30/2021 23:00:59 - INFO - __main__ - Step 54388: {'lr': 0.0003607133483600107, 'samples': 10442496, 'steps': 54387, 'loss/train': 1.9957389831542969} 08/30/2021 23:00:59 - INFO - __main__ - Step 54389: {'lr': 0.00036070859033971646, 'samples': 10442688, 'steps': 54388, 'loss/train': 0.13232050836086273} 08/30/2021 23:01:00 - INFO - __main__ - Step 54390: {'lr': 0.00036070383226953875, 'samples': 10442880, 'steps': 54389, 'loss/train': 1.6840497255325317} 08/30/2021 23:01:00 - INFO - __main__ - Step 54391: {'lr': 0.0003606990741494795, 'samples': 10443072, 'steps': 54390, 'loss/train': 1.5031099319458008} 08/30/2021 23:01:02 - INFO - __main__ - Step 54392: {'lr': 0.00036069431597954103, 'samples': 10443264, 'steps': 54391, 'loss/train': 1.273067831993103} 08/30/2021 23:01:03 - INFO - __main__ - Step 54393: {'lr': 0.0003606895577597254, 'samples': 10443456, 'steps': 54392, 'loss/train': 0.6100627779960632} 08/30/2021 23:01:03 - INFO - __main__ - Step 54394: {'lr': 0.0003606847994900347, 'samples': 10443648, 'steps': 54393, 'loss/train': 1.554357886314392} 08/30/2021 23:01:03 - INFO - __main__ - Step 54395: {'lr': 0.00036068004117047127, 'samples': 10443840, 'steps': 54394, 'loss/train': 1.1624020338058472} 08/30/2021 23:01:04 - INFO - __main__ - Step 54396: {'lr': 0.000360675282801037, 'samples': 10444032, 'steps': 54395, 'loss/train': 1.2031679153442383} 08/30/2021 23:01:04 - INFO - __main__ - Step 54397: {'lr': 0.0003606705243817342, 'samples': 10444224, 'steps': 54396, 'loss/train': 1.2400147914886475} 08/30/2021 23:01:06 - INFO - __main__ - Step 54398: {'lr': 0.00036066576591256496, 'samples': 10444416, 'steps': 54397, 'loss/train': 1.6306027173995972} 08/30/2021 23:01:06 - INFO - __main__ - Step 54399: {'lr': 0.00036066100739353145, 'samples': 10444608, 'steps': 54398, 'loss/train': 1.288132905960083} 08/30/2021 23:01:06 - INFO - __main__ - Step 54400: {'lr': 0.0003606562488246358, 'samples': 10444800, 'steps': 54399, 'loss/train': 1.6223887205123901} 08/30/2021 23:01:07 - INFO - __main__ - Step 54401: {'lr': 0.00036065149020588015, 'samples': 10444992, 'steps': 54400, 'loss/train': 0.9524000287055969} 08/30/2021 23:01:07 - INFO - __main__ - Step 54402: {'lr': 0.00036064673153726664, 'samples': 10445184, 'steps': 54401, 'loss/train': 1.3720989227294922} 08/30/2021 23:01:09 - INFO - __main__ - Step 54403: {'lr': 0.0003606419728187974, 'samples': 10445376, 'steps': 54402, 'loss/train': 1.35567307472229} 08/30/2021 23:01:10 - INFO - __main__ - Step 54404: {'lr': 0.00036063721405047463, 'samples': 10445568, 'steps': 54403, 'loss/train': 1.614539623260498} 08/30/2021 23:01:10 - INFO - __main__ - Step 54405: {'lr': 0.00036063245523230037, 'samples': 10445760, 'steps': 54404, 'loss/train': 1.5119376182556152} 08/30/2021 23:01:10 - INFO - __main__ - Step 54406: {'lr': 0.0003606276963642769, 'samples': 10445952, 'steps': 54405, 'loss/train': 1.8646962642669678} 08/30/2021 23:01:11 - INFO - __main__ - Step 54407: {'lr': 0.00036062293744640637, 'samples': 10446144, 'steps': 54406, 'loss/train': 1.4430432319641113} 08/30/2021 23:01:11 - INFO - __main__ - Step 54408: {'lr': 0.0003606181784786907, 'samples': 10446336, 'steps': 54407, 'loss/train': 0.9834067821502686} 08/30/2021 23:01:13 - INFO - __main__ - Step 54409: {'lr': 0.00036061341946113225, 'samples': 10446528, 'steps': 54408, 'loss/train': 0.208884134888649} 08/30/2021 23:01:13 - INFO - __main__ - Step 54410: {'lr': 0.0003606086603937331, 'samples': 10446720, 'steps': 54409, 'loss/train': 1.9072211980819702} 08/30/2021 23:01:14 - INFO - __main__ - Step 54411: {'lr': 0.00036060390127649536, 'samples': 10446912, 'steps': 54410, 'loss/train': 0.8430742025375366} 08/30/2021 23:01:14 - INFO - __main__ - Step 54412: {'lr': 0.00036059914210942126, 'samples': 10447104, 'steps': 54411, 'loss/train': 2.041823387145996} 08/30/2021 23:01:14 - INFO - __main__ - Step 54413: {'lr': 0.0003605943828925129, 'samples': 10447296, 'steps': 54412, 'loss/train': 0.1184265986084938} 08/30/2021 23:01:16 - INFO - __main__ - Step 54414: {'lr': 0.0003605896236257724, 'samples': 10447488, 'steps': 54413, 'loss/train': 1.146912693977356} 08/30/2021 23:01:16 - INFO - __main__ - Step 54415: {'lr': 0.0003605848643092019, 'samples': 10447680, 'steps': 54414, 'loss/train': 0.8741188049316406} 08/30/2021 23:01:17 - INFO - __main__ - Step 54416: {'lr': 0.00036058010494280357, 'samples': 10447872, 'steps': 54415, 'loss/train': 0.8910341262817383} 08/30/2021 23:01:17 - INFO - __main__ - Step 54417: {'lr': 0.00036057534552657954, 'samples': 10448064, 'steps': 54416, 'loss/train': 0.7433121204376221} 08/30/2021 23:01:17 - INFO - __main__ - Step 54418: {'lr': 0.000360570586060532, 'samples': 10448256, 'steps': 54417, 'loss/train': 1.8967901468276978} 08/30/2021 23:01:19 - INFO - __main__ - Step 54419: {'lr': 0.0003605658265446631, 'samples': 10448448, 'steps': 54418, 'loss/train': 0.9716705679893494} 08/30/2021 23:01:19 - INFO - __main__ - Step 54420: {'lr': 0.00036056106697897485, 'samples': 10448640, 'steps': 54419, 'loss/train': 0.08413762599229813} 08/30/2021 23:01:20 - INFO - __main__ - Step 54421: {'lr': 0.0003605563073634696, 'samples': 10448832, 'steps': 54420, 'loss/train': 1.1478928327560425} 08/30/2021 23:01:20 - INFO - __main__ - Step 54422: {'lr': 0.00036055154769814923, 'samples': 10449024, 'steps': 54421, 'loss/train': 1.341420292854309} 08/30/2021 23:01:20 - INFO - __main__ - Step 54423: {'lr': 0.0003605467879830161, 'samples': 10449216, 'steps': 54422, 'loss/train': 1.4099433422088623} 08/30/2021 23:01:21 - INFO - __main__ - Step 54424: {'lr': 0.00036054202821807235, 'samples': 10449408, 'steps': 54423, 'loss/train': 1.181523323059082} 08/30/2021 23:01:22 - INFO - __main__ - Step 54425: {'lr': 0.00036053726840332004, 'samples': 10449600, 'steps': 54424, 'loss/train': 0.3803408741950989} 08/30/2021 23:01:23 - INFO - __main__ - Step 54426: {'lr': 0.00036053250853876134, 'samples': 10449792, 'steps': 54425, 'loss/train': 1.6077316999435425} 08/30/2021 23:01:23 - INFO - __main__ - Step 54427: {'lr': 0.0003605277486243984, 'samples': 10449984, 'steps': 54426, 'loss/train': 1.8009928464889526} 08/30/2021 23:01:23 - INFO - __main__ - Step 54428: {'lr': 0.0003605229886602334, 'samples': 10450176, 'steps': 54427, 'loss/train': 0.8881281614303589} 08/30/2021 23:01:24 - INFO - __main__ - Step 54429: {'lr': 0.0003605182286462683, 'samples': 10450368, 'steps': 54428, 'loss/train': 1.1170265674591064} 08/30/2021 23:01:25 - INFO - __main__ - Step 54430: {'lr': 0.00036051346858250556, 'samples': 10450560, 'steps': 54429, 'loss/train': 1.2654304504394531} 08/30/2021 23:01:26 - INFO - __main__ - Step 54431: {'lr': 0.0003605087084689471, 'samples': 10450752, 'steps': 54430, 'loss/train': 1.262196660041809} 08/30/2021 23:01:26 - INFO - __main__ - Step 54432: {'lr': 0.0003605039483055951, 'samples': 10450944, 'steps': 54431, 'loss/train': 1.9821951389312744} 08/30/2021 23:01:26 - INFO - __main__ - Step 54433: {'lr': 0.00036049918809245173, 'samples': 10451136, 'steps': 54432, 'loss/train': 1.5487759113311768} 08/30/2021 23:01:27 - INFO - __main__ - Step 54434: {'lr': 0.00036049442782951915, 'samples': 10451328, 'steps': 54433, 'loss/train': 1.6200807094573975} 08/30/2021 23:01:28 - INFO - __main__ - Step 54435: {'lr': 0.00036048966751679945, 'samples': 10451520, 'steps': 54434, 'loss/train': 2.2839179039001465} 08/30/2021 23:01:29 - INFO - __main__ - Step 54436: {'lr': 0.0003604849071542948, 'samples': 10451712, 'steps': 54435, 'loss/train': 1.0905177593231201} 08/30/2021 23:01:29 - INFO - __main__ - Step 54437: {'lr': 0.0003604801467420074, 'samples': 10451904, 'steps': 54436, 'loss/train': 1.3238178491592407} 08/30/2021 23:01:29 - INFO - __main__ - Step 54438: {'lr': 0.00036047538627993937, 'samples': 10452096, 'steps': 54437, 'loss/train': 1.1375893354415894} 08/30/2021 23:01:30 - INFO - __main__ - Step 54439: {'lr': 0.00036047062576809283, 'samples': 10452288, 'steps': 54438, 'loss/train': 1.2887464761734009} 08/30/2021 23:01:32 - INFO - __main__ - Step 54440: {'lr': 0.0003604658652064699, 'samples': 10452480, 'steps': 54439, 'loss/train': 1.3201395273208618} 08/30/2021 23:01:33 - INFO - __main__ - Step 54441: {'lr': 0.00036046110459507275, 'samples': 10452672, 'steps': 54440, 'loss/train': 1.0068236589431763} 08/30/2021 23:01:33 - INFO - __main__ - Step 54442: {'lr': 0.00036045634393390354, 'samples': 10452864, 'steps': 54441, 'loss/train': 1.1214576959609985} 08/30/2021 23:01:33 - INFO - __main__ - Step 54443: {'lr': 0.0003604515832229644, 'samples': 10453056, 'steps': 54442, 'loss/train': 1.3695833683013916} 08/30/2021 23:01:34 - INFO - __main__ - Step 54444: {'lr': 0.0003604468224622575, 'samples': 10453248, 'steps': 54443, 'loss/train': 0.32771575450897217} 08/30/2021 23:01:34 - INFO - __main__ - Step 54445: {'lr': 0.00036044206165178496, 'samples': 10453440, 'steps': 54444, 'loss/train': 2.2965939044952393} 08/30/2021 23:01:34 - INFO - __main__ - Step 54446: {'lr': 0.00036043730079154897, 'samples': 10453632, 'steps': 54445, 'loss/train': 2.2613685131073} 08/30/2021 23:01:36 - INFO - __main__ - Step 54447: {'lr': 0.00036043253988155157, 'samples': 10453824, 'steps': 54446, 'loss/train': 0.7324656248092651} 08/30/2021 23:01:37 - INFO - __main__ - Step 54448: {'lr': 0.00036042777892179503, 'samples': 10454016, 'steps': 54447, 'loss/train': 1.4372731447219849} 08/30/2021 23:01:37 - INFO - __main__ - Step 54449: {'lr': 0.0003604230179122814, 'samples': 10454208, 'steps': 54448, 'loss/train': 1.3258905410766602} 08/30/2021 23:01:38 - INFO - __main__ - Step 54450: {'lr': 0.0003604182568530128, 'samples': 10454400, 'steps': 54449, 'loss/train': 1.7881958484649658} 08/30/2021 23:01:38 - INFO - __main__ - Step 54451: {'lr': 0.0003604134957439915, 'samples': 10454592, 'steps': 54450, 'loss/train': 1.5566935539245605} 08/30/2021 23:01:40 - INFO - __main__ - Step 54452: {'lr': 0.00036040873458521963, 'samples': 10454784, 'steps': 54451, 'loss/train': 1.0344430208206177} 08/30/2021 23:01:40 - INFO - __main__ - Step 54453: {'lr': 0.0003604039733766992, 'samples': 10454976, 'steps': 54452, 'loss/train': 1.550994634628296} 08/30/2021 23:01:41 - INFO - __main__ - Step 54454: {'lr': 0.00036039921211843254, 'samples': 10455168, 'steps': 54453, 'loss/train': 1.847101092338562} 08/30/2021 23:01:41 - INFO - __main__ - Step 54455: {'lr': 0.0003603944508104216, 'samples': 10455360, 'steps': 54454, 'loss/train': 0.6563199758529663} 08/30/2021 23:01:41 - INFO - __main__ - Step 54456: {'lr': 0.0003603896894526687, 'samples': 10455552, 'steps': 54455, 'loss/train': 1.5809701681137085} 08/30/2021 23:01:42 - INFO - __main__ - Step 54457: {'lr': 0.00036038492804517586, 'samples': 10455744, 'steps': 54456, 'loss/train': 1.3193213939666748} 08/30/2021 23:01:44 - INFO - __main__ - Step 54458: {'lr': 0.00036038016658794525, 'samples': 10455936, 'steps': 54457, 'loss/train': 1.637620210647583} 08/30/2021 23:01:44 - INFO - __main__ - Step 54459: {'lr': 0.0003603754050809791, 'samples': 10456128, 'steps': 54458, 'loss/train': 0.02939906343817711} 08/30/2021 23:01:44 - INFO - __main__ - Step 54460: {'lr': 0.0003603706435242795, 'samples': 10456320, 'steps': 54459, 'loss/train': 1.4809588193893433} 08/30/2021 23:01:45 - INFO - __main__ - Step 54461: {'lr': 0.00036036588191784856, 'samples': 10456512, 'steps': 54460, 'loss/train': 1.7653968334197998} 08/30/2021 23:01:45 - INFO - __main__ - Step 54462: {'lr': 0.0003603611202616885, 'samples': 10456704, 'steps': 54461, 'loss/train': 1.6733763217926025} 08/30/2021 23:01:45 - INFO - __main__ - Step 54463: {'lr': 0.0003603563585558014, 'samples': 10456896, 'steps': 54462, 'loss/train': 1.5711159706115723} 08/30/2021 23:01:47 - INFO - __main__ - Step 54464: {'lr': 0.00036035159680018937, 'samples': 10457088, 'steps': 54463, 'loss/train': 1.2288029193878174} 08/30/2021 23:01:47 - INFO - __main__ - Step 54465: {'lr': 0.00036034683499485467, 'samples': 10457280, 'steps': 54464, 'loss/train': 1.8389629125595093} 08/30/2021 23:01:48 - INFO - __main__ - Step 54466: {'lr': 0.0003603420731397994, 'samples': 10457472, 'steps': 54465, 'loss/train': 0.7039991021156311} 08/30/2021 23:01:48 - INFO - __main__ - Step 54467: {'lr': 0.00036033731123502567, 'samples': 10457664, 'steps': 54466, 'loss/train': 1.7743483781814575} 08/30/2021 23:01:49 - INFO - __main__ - Step 54468: {'lr': 0.00036033254928053565, 'samples': 10457856, 'steps': 54467, 'loss/train': 1.220398187637329} 08/30/2021 23:01:51 - INFO - __main__ - Step 54469: {'lr': 0.0003603277872763315, 'samples': 10458048, 'steps': 54468, 'loss/train': 1.172669768333435} 08/30/2021 23:01:51 - INFO - __main__ - Step 54470: {'lr': 0.0003603230252224153, 'samples': 10458240, 'steps': 54469, 'loss/train': 1.4810055494308472} 08/30/2021 23:01:52 - INFO - __main__ - Step 54471: {'lr': 0.0003603182631187893, 'samples': 10458432, 'steps': 54470, 'loss/train': 1.2743890285491943} 08/30/2021 23:01:52 - INFO - __main__ - Step 54472: {'lr': 0.00036031350096545555, 'samples': 10458624, 'steps': 54471, 'loss/train': 1.6858956813812256} 08/30/2021 23:01:52 - INFO - __main__ - Step 54473: {'lr': 0.0003603087387624163, 'samples': 10458816, 'steps': 54472, 'loss/train': 1.0888733863830566} 08/30/2021 23:01:53 - INFO - __main__ - Step 54474: {'lr': 0.0003603039765096736, 'samples': 10459008, 'steps': 54473, 'loss/train': 1.8485932350158691} 08/30/2021 23:01:53 - INFO - __main__ - Step 54475: {'lr': 0.00036029921420722966, 'samples': 10459200, 'steps': 54474, 'loss/train': 0.028074083849787712} 08/30/2021 23:01:55 - INFO - __main__ - Step 54476: {'lr': 0.0003602944518550866, 'samples': 10459392, 'steps': 54475, 'loss/train': 0.024364106357097626} 08/30/2021 23:01:55 - INFO - __main__ - Step 54477: {'lr': 0.00036028968945324647, 'samples': 10459584, 'steps': 54476, 'loss/train': 1.4906941652297974} 08/30/2021 23:01:55 - INFO - __main__ - Step 54478: {'lr': 0.00036028492700171166, 'samples': 10459776, 'steps': 54477, 'loss/train': 1.7284191846847534} 08/30/2021 23:01:56 - INFO - __main__ - Step 54479: {'lr': 0.0003602801645004841, 'samples': 10459968, 'steps': 54478, 'loss/train': 1.2206257581710815} 08/30/2021 23:01:56 - INFO - __main__ - Step 54480: {'lr': 0.00036027540194956593, 'samples': 10460160, 'steps': 54479, 'loss/train': 0.6962655186653137} 08/30/2021 23:01:58 - INFO - __main__ - Step 54481: {'lr': 0.00036027063934895935, 'samples': 10460352, 'steps': 54480, 'loss/train': 1.462016224861145} 08/30/2021 23:01:58 - INFO - __main__ - Step 54482: {'lr': 0.0003602658766986666, 'samples': 10460544, 'steps': 54481, 'loss/train': 0.15552367269992828} 08/30/2021 23:01:58 - INFO - __main__ - Step 54483: {'lr': 0.00036026111399868973, 'samples': 10460736, 'steps': 54482, 'loss/train': 1.1515041589736938} 08/30/2021 23:01:59 - INFO - __main__ - Step 54484: {'lr': 0.00036025635124903093, 'samples': 10460928, 'steps': 54483, 'loss/train': 1.2796595096588135} 08/30/2021 23:01:59 - INFO - __main__ - Step 54485: {'lr': 0.0003602515884496923, 'samples': 10461120, 'steps': 54484, 'loss/train': 1.388633370399475} 08/30/2021 23:01:59 - INFO - __main__ - Step 54486: {'lr': 0.00036024682560067603, 'samples': 10461312, 'steps': 54485, 'loss/train': 1.4794923067092896} 08/30/2021 23:02:01 - INFO - __main__ - Step 54487: {'lr': 0.00036024206270198416, 'samples': 10461504, 'steps': 54486, 'loss/train': 1.326303482055664} 08/30/2021 23:02:02 - INFO - __main__ - Step 54488: {'lr': 0.00036023729975361897, 'samples': 10461696, 'steps': 54487, 'loss/train': 1.296088695526123} 08/30/2021 23:02:02 - INFO - __main__ - Step 54489: {'lr': 0.00036023253675558257, 'samples': 10461888, 'steps': 54488, 'loss/train': 1.447489857673645} 08/30/2021 23:02:02 - INFO - __main__ - Step 54490: {'lr': 0.0003602277737078771, 'samples': 10462080, 'steps': 54489, 'loss/train': 1.4102386236190796} 08/30/2021 23:02:03 - INFO - __main__ - Step 54491: {'lr': 0.00036022301061050467, 'samples': 10462272, 'steps': 54490, 'loss/train': 1.5670452117919922} 08/30/2021 23:02:04 - INFO - __main__ - Step 54492: {'lr': 0.00036021824746346746, 'samples': 10462464, 'steps': 54491, 'loss/train': 1.3059052228927612} 08/30/2021 23:02:05 - INFO - __main__ - Step 54493: {'lr': 0.00036021348426676754, 'samples': 10462656, 'steps': 54492, 'loss/train': 0.5022376179695129} 08/30/2021 23:02:05 - INFO - __main__ - Step 54494: {'lr': 0.00036020872102040727, 'samples': 10462848, 'steps': 54493, 'loss/train': 1.5012847185134888} 08/30/2021 23:02:05 - INFO - __main__ - Step 54495: {'lr': 0.00036020395772438853, 'samples': 10463040, 'steps': 54494, 'loss/train': 0.9884690642356873} 08/30/2021 23:02:06 - INFO - __main__ - Step 54496: {'lr': 0.00036019919437871355, 'samples': 10463232, 'steps': 54495, 'loss/train': 1.2300623655319214} 08/30/2021 23:02:07 - INFO - __main__ - Step 54497: {'lr': 0.0003601944309833846, 'samples': 10463424, 'steps': 54496, 'loss/train': 1.1033459901809692} 08/30/2021 23:02:08 - INFO - __main__ - Step 54498: {'lr': 0.0003601896675384037, 'samples': 10463616, 'steps': 54497, 'loss/train': 0.9350084066390991} 08/30/2021 23:02:08 - INFO - __main__ - Step 54499: {'lr': 0.0003601849040437731, 'samples': 10463808, 'steps': 54498, 'loss/train': 1.571579933166504} 08/30/2021 23:02:08 - INFO - __main__ - Step 54500: {'lr': 0.0003601801404994949, 'samples': 10464000, 'steps': 54499, 'loss/train': 1.4422886371612549} 08/30/2021 23:02:09 - INFO - __main__ - Step 54501: {'lr': 0.0003601753769055711, 'samples': 10464192, 'steps': 54500, 'loss/train': 1.3957128524780273} 08/30/2021 23:02:09 - INFO - __main__ - Step 54502: {'lr': 0.00036017061326200405, 'samples': 10464384, 'steps': 54501, 'loss/train': 1.102375864982605} 08/30/2021 23:02:11 - INFO - __main__ - Step 54503: {'lr': 0.0003601658495687958, 'samples': 10464576, 'steps': 54502, 'loss/train': 1.2521449327468872} 08/30/2021 23:02:11 - INFO - __main__ - Step 54504: {'lr': 0.0003601610858259485, 'samples': 10464768, 'steps': 54503, 'loss/train': 1.0305943489074707} 08/30/2021 23:02:12 - INFO - __main__ - Step 54505: {'lr': 0.0003601563220334644, 'samples': 10464960, 'steps': 54504, 'loss/train': 1.1198049783706665} 08/30/2021 23:02:12 - INFO - __main__ - Step 54506: {'lr': 0.0003601515581913455, 'samples': 10465152, 'steps': 54505, 'loss/train': 1.1192988157272339} 08/30/2021 23:02:12 - INFO - __main__ - Step 54507: {'lr': 0.0003601467942995941, 'samples': 10465344, 'steps': 54506, 'loss/train': 0.694641649723053} 08/30/2021 23:02:14 - INFO - __main__ - Step 54508: {'lr': 0.00036014203035821213, 'samples': 10465536, 'steps': 54507, 'loss/train': 1.024565577507019} 08/30/2021 23:02:15 - INFO - __main__ - Step 54509: {'lr': 0.0003601372663672019, 'samples': 10465728, 'steps': 54508, 'loss/train': 0.6277898550033569} 08/30/2021 23:02:15 - INFO - __main__ - Step 54510: {'lr': 0.00036013250232656553, 'samples': 10465920, 'steps': 54509, 'loss/train': 1.8217884302139282} 08/30/2021 23:02:16 - INFO - __main__ - Step 54511: {'lr': 0.0003601277382363051, 'samples': 10466112, 'steps': 54510, 'loss/train': 1.3990466594696045} 08/30/2021 23:02:16 - INFO - __main__ - Step 54512: {'lr': 0.0003601229740964229, 'samples': 10466304, 'steps': 54511, 'loss/train': 1.249825119972229} 08/30/2021 23:02:17 - INFO - __main__ - Step 54513: {'lr': 0.000360118209906921, 'samples': 10466496, 'steps': 54512, 'loss/train': 1.5219441652297974} 08/30/2021 23:02:18 - INFO - __main__ - Step 54514: {'lr': 0.0003601134456678014, 'samples': 10466688, 'steps': 54513, 'loss/train': 2.0387253761291504} 08/30/2021 23:02:18 - INFO - __main__ - Step 54515: {'lr': 0.0003601086813790665, 'samples': 10466880, 'steps': 54514, 'loss/train': 1.3793940544128418} 08/30/2021 23:02:19 - INFO - __main__ - Step 54516: {'lr': 0.00036010391704071823, 'samples': 10467072, 'steps': 54515, 'loss/train': 1.2549033164978027} 08/30/2021 23:02:19 - INFO - __main__ - Step 54517: {'lr': 0.0003600991526527589, 'samples': 10467264, 'steps': 54516, 'loss/train': 1.8614650964736938} 08/30/2021 23:02:20 - INFO - __main__ - Step 54518: {'lr': 0.00036009438821519056, 'samples': 10467456, 'steps': 54517, 'loss/train': 1.3409873247146606} 08/30/2021 23:02:21 - INFO - __main__ - Step 54519: {'lr': 0.0003600896237280154, 'samples': 10467648, 'steps': 54518, 'loss/train': 1.1305326223373413} 08/30/2021 23:02:21 - INFO - __main__ - Step 54520: {'lr': 0.0003600848591912356, 'samples': 10467840, 'steps': 54519, 'loss/train': 1.3710821866989136} 08/30/2021 23:02:21 - INFO - __main__ - Step 54521: {'lr': 0.00036008009460485323, 'samples': 10468032, 'steps': 54520, 'loss/train': 1.0729775428771973} 08/30/2021 23:02:22 - INFO - __main__ - Step 54522: {'lr': 0.00036007532996887043, 'samples': 10468224, 'steps': 54521, 'loss/train': 0.0646027997136116} 08/30/2021 23:02:23 - INFO - __main__ - Step 54523: {'lr': 0.0003600705652832894, 'samples': 10468416, 'steps': 54522, 'loss/train': 1.3067927360534668} 08/30/2021 23:02:24 - INFO - __main__ - Step 54524: {'lr': 0.00036006580054811235, 'samples': 10468608, 'steps': 54523, 'loss/train': 1.1525671482086182} 08/30/2021 23:02:24 - INFO - __main__ - Step 54525: {'lr': 0.00036006103576334124, 'samples': 10468800, 'steps': 54524, 'loss/train': 2.3152549266815186} 08/30/2021 23:02:24 - INFO - __main__ - Step 54526: {'lr': 0.00036005627092897835, 'samples': 10468992, 'steps': 54525, 'loss/train': 1.1291697025299072} 08/30/2021 23:02:25 - INFO - __main__ - Step 54527: {'lr': 0.0003600515060450259, 'samples': 10469184, 'steps': 54526, 'loss/train': 1.5302352905273438} 08/30/2021 23:02:26 - INFO - __main__ - Step 54528: {'lr': 0.0003600467411114858, 'samples': 10469376, 'steps': 54527, 'loss/train': 0.7366635203361511} 08/30/2021 23:02:27 - INFO - __main__ - Step 54529: {'lr': 0.00036004197612836045, 'samples': 10469568, 'steps': 54528, 'loss/train': 1.5393773317337036} 08/30/2021 23:02:27 - INFO - __main__ - Step 54530: {'lr': 0.0003600372110956518, 'samples': 10469760, 'steps': 54529, 'loss/train': 0.6021180152893066} 08/30/2021 23:02:27 - INFO - __main__ - Step 54531: {'lr': 0.0003600324460133621, 'samples': 10469952, 'steps': 54530, 'loss/train': 1.0634032487869263} 08/30/2021 23:02:28 - INFO - __main__ - Step 54532: {'lr': 0.0003600276808814935, 'samples': 10470144, 'steps': 54531, 'loss/train': 1.748326301574707} 08/30/2021 23:02:30 - INFO - __main__ - Step 54533: {'lr': 0.00036002291570004806, 'samples': 10470336, 'steps': 54532, 'loss/train': 0.1036919355392456} 08/30/2021 23:02:30 - INFO - __main__ - Step 54534: {'lr': 0.0003600181504690281, 'samples': 10470528, 'steps': 54533, 'loss/train': 1.3171173334121704} 08/30/2021 23:02:30 - INFO - __main__ - Step 54535: {'lr': 0.00036001338518843563, 'samples': 10470720, 'steps': 54534, 'loss/train': 0.883816123008728} 08/30/2021 23:02:31 - INFO - __main__ - Step 54536: {'lr': 0.0003600086198582728, 'samples': 10470912, 'steps': 54535, 'loss/train': 1.1281777620315552} 08/30/2021 23:02:31 - INFO - __main__ - Step 54537: {'lr': 0.00036000385447854176, 'samples': 10471104, 'steps': 54536, 'loss/train': 1.4809339046478271} 08/30/2021 23:02:31 - INFO - __main__ - Step 54538: {'lr': 0.0003599990890492447, 'samples': 10471296, 'steps': 54537, 'loss/train': 1.6544737815856934} 08/30/2021 23:02:33 - INFO - __main__ - Step 54539: {'lr': 0.00035999432357038374, 'samples': 10471488, 'steps': 54538, 'loss/train': 0.8396620750427246} 08/30/2021 23:02:34 - INFO - __main__ - Step 54540: {'lr': 0.0003599895580419611, 'samples': 10471680, 'steps': 54539, 'loss/train': 0.5185154676437378} 08/30/2021 23:02:34 - INFO - __main__ - Step 54541: {'lr': 0.0003599847924639788, 'samples': 10471872, 'steps': 54540, 'loss/train': 1.1997580528259277} 08/30/2021 23:02:34 - INFO - __main__ - Step 54542: {'lr': 0.00035998002683643903, 'samples': 10472064, 'steps': 54541, 'loss/train': 1.8566733598709106} 08/30/2021 23:02:35 - INFO - __main__ - Step 54543: {'lr': 0.00035997526115934405, 'samples': 10472256, 'steps': 54542, 'loss/train': 1.5253015756607056} 08/30/2021 23:02:35 - INFO - __main__ - Step 54544: {'lr': 0.00035997049543269583, 'samples': 10472448, 'steps': 54543, 'loss/train': 0.7787737250328064} 08/30/2021 23:02:37 - INFO - __main__ - Step 54545: {'lr': 0.0003599657296564966, 'samples': 10472640, 'steps': 54544, 'loss/train': 1.1299768686294556} 08/30/2021 23:02:37 - INFO - __main__ - Step 54546: {'lr': 0.00035996096383074855, 'samples': 10472832, 'steps': 54545, 'loss/train': 1.0124627351760864} 08/30/2021 23:02:38 - INFO - __main__ - Step 54547: {'lr': 0.0003599561979554538, 'samples': 10473024, 'steps': 54546, 'loss/train': 0.45943358540534973} 08/30/2021 23:02:38 - INFO - __main__ - Step 54548: {'lr': 0.0003599514320306144, 'samples': 10473216, 'steps': 54547, 'loss/train': 0.040136393159627914} 08/30/2021 23:02:38 - INFO - __main__ - Step 54549: {'lr': 0.0003599466660562327, 'samples': 10473408, 'steps': 54548, 'loss/train': 1.3302639722824097} 08/30/2021 23:02:40 - INFO - __main__ - Step 54550: {'lr': 0.00035994190003231063, 'samples': 10473600, 'steps': 54549, 'loss/train': 0.9709994792938232} 08/30/2021 23:02:40 - INFO - __main__ - Step 54551: {'lr': 0.0003599371339588505, 'samples': 10473792, 'steps': 54550, 'loss/train': 1.1999484300613403} 08/30/2021 23:02:40 - INFO - __main__ - Step 54552: {'lr': 0.00035993236783585437, 'samples': 10473984, 'steps': 54551, 'loss/train': 1.5302873849868774} 08/30/2021 23:02:41 - INFO - __main__ - Step 54553: {'lr': 0.00035992760166332437, 'samples': 10474176, 'steps': 54552, 'loss/train': 1.2610130310058594} 08/30/2021 23:02:41 - INFO - __main__ - Step 54554: {'lr': 0.00035992283544126276, 'samples': 10474368, 'steps': 54553, 'loss/train': 1.8108878135681152} 08/30/2021 23:02:43 - INFO - __main__ - Step 54555: {'lr': 0.00035991806916967154, 'samples': 10474560, 'steps': 54554, 'loss/train': 1.02792489528656} 08/30/2021 23:02:43 - INFO - __main__ - Step 54556: {'lr': 0.000359913302848553, 'samples': 10474752, 'steps': 54555, 'loss/train': 0.6806752681732178} 08/30/2021 23:02:43 - INFO - __main__ - Step 54557: {'lr': 0.0003599085364779092, 'samples': 10474944, 'steps': 54556, 'loss/train': 1.5947924852371216} 08/30/2021 23:02:44 - INFO - __main__ - Step 54558: {'lr': 0.0003599037700577423, 'samples': 10475136, 'steps': 54557, 'loss/train': 1.4165140390396118} 08/30/2021 23:02:44 - INFO - __main__ - Step 54559: {'lr': 0.0003598990035880545, 'samples': 10475328, 'steps': 54558, 'loss/train': 1.9224787950515747} 08/30/2021 23:02:46 - INFO - __main__ - Step 54560: {'lr': 0.0003598942370688479, 'samples': 10475520, 'steps': 54559, 'loss/train': 1.3067187070846558} 08/30/2021 23:02:47 - INFO - __main__ - Step 54561: {'lr': 0.0003598894705001246, 'samples': 10475712, 'steps': 54560, 'loss/train': 0.4878981411457062} 08/30/2021 23:02:47 - INFO - __main__ - Step 54562: {'lr': 0.00035988470388188684, 'samples': 10475904, 'steps': 54561, 'loss/train': 0.5279180407524109} 08/30/2021 23:02:47 - INFO - __main__ - Step 54563: {'lr': 0.0003598799372141367, 'samples': 10476096, 'steps': 54562, 'loss/train': 1.3532823324203491} 08/30/2021 23:02:48 - INFO - __main__ - Step 54564: {'lr': 0.00035987517049687633, 'samples': 10476288, 'steps': 54563, 'loss/train': 1.0842735767364502} 08/30/2021 23:02:48 - INFO - __main__ - Step 54565: {'lr': 0.0003598704037301079, 'samples': 10476480, 'steps': 54564, 'loss/train': 1.6678783893585205} 08/30/2021 23:02:50 - INFO - __main__ - Step 54566: {'lr': 0.00035986563691383364, 'samples': 10476672, 'steps': 54565, 'loss/train': 1.3109883069992065} 08/30/2021 23:02:50 - INFO - __main__ - Step 54567: {'lr': 0.0003598608700480556, 'samples': 10476864, 'steps': 54566, 'loss/train': 1.0542044639587402} 08/30/2021 23:02:50 - INFO - __main__ - Step 54568: {'lr': 0.00035985610313277595, 'samples': 10477056, 'steps': 54567, 'loss/train': 1.556660532951355} 08/30/2021 23:02:51 - INFO - __main__ - Step 54569: {'lr': 0.0003598513361679968, 'samples': 10477248, 'steps': 54568, 'loss/train': 0.9612125754356384} 08/30/2021 23:02:51 - INFO - __main__ - Step 54570: {'lr': 0.00035984656915372034, 'samples': 10477440, 'steps': 54569, 'loss/train': 1.0310747623443604} 08/30/2021 23:02:53 - INFO - __main__ - Step 54571: {'lr': 0.0003598418020899487, 'samples': 10477632, 'steps': 54570, 'loss/train': 1.6246334314346313} 08/30/2021 23:02:53 - INFO - __main__ - Step 54572: {'lr': 0.0003598370349766841, 'samples': 10477824, 'steps': 54571, 'loss/train': 0.3843275308609009} 08/30/2021 23:02:53 - INFO - __main__ - Step 54573: {'lr': 0.0003598322678139285, 'samples': 10478016, 'steps': 54572, 'loss/train': 1.4062119722366333} 08/30/2021 23:02:54 - INFO - __main__ - Step 54574: {'lr': 0.00035982750060168436, 'samples': 10478208, 'steps': 54573, 'loss/train': 1.4864474534988403} 08/30/2021 23:02:54 - INFO - __main__ - Step 54575: {'lr': 0.0003598227333399535, 'samples': 10478400, 'steps': 54574, 'loss/train': 1.512558937072754} 08/30/2021 23:02:56 - INFO - __main__ - Step 54576: {'lr': 0.00035981796602873825, 'samples': 10478592, 'steps': 54575, 'loss/train': 1.2762151956558228} 08/30/2021 23:02:56 - INFO - __main__ - Step 54577: {'lr': 0.00035981319866804074, 'samples': 10478784, 'steps': 54576, 'loss/train': 1.2455973625183105} 08/30/2021 23:02:56 - INFO - __main__ - Step 54578: {'lr': 0.00035980843125786306, 'samples': 10478976, 'steps': 54577, 'loss/train': 1.2093178033828735} 08/30/2021 23:02:57 - INFO - __main__ - Step 54579: {'lr': 0.0003598036637982074, 'samples': 10479168, 'steps': 54578, 'loss/train': 5.774199485778809} 08/30/2021 23:02:57 - INFO - __main__ - Step 54580: {'lr': 0.00035979889628907593, 'samples': 10479360, 'steps': 54579, 'loss/train': 1.66202712059021} 08/30/2021 23:02:58 - INFO - __main__ - Step 54581: {'lr': 0.0003597941287304708, 'samples': 10479552, 'steps': 54580, 'loss/train': 1.4471526145935059} 08/30/2021 23:02:59 - INFO - __main__ - Step 54582: {'lr': 0.0003597893611223941, 'samples': 10479744, 'steps': 54581, 'loss/train': 1.4222338199615479} 08/30/2021 23:02:59 - INFO - __main__ - Step 54583: {'lr': 0.00035978459346484794, 'samples': 10479936, 'steps': 54582, 'loss/train': 1.6904886960983276} 08/30/2021 23:03:00 - INFO - __main__ - Step 54584: {'lr': 0.0003597798257578346, 'samples': 10480128, 'steps': 54583, 'loss/train': 1.4182924032211304} 08/30/2021 23:03:00 - INFO - __main__ - Step 54585: {'lr': 0.0003597750580013561, 'samples': 10480320, 'steps': 54584, 'loss/train': 1.649872064590454} 08/30/2021 23:03:00 - INFO - __main__ - Step 54586: {'lr': 0.0003597702901954147, 'samples': 10480512, 'steps': 54585, 'loss/train': 1.757237195968628} 08/30/2021 23:03:02 - INFO - __main__ - Step 54587: {'lr': 0.00035976552234001256, 'samples': 10480704, 'steps': 54586, 'loss/train': 1.4790384769439697} 08/30/2021 23:03:02 - INFO - __main__ - Step 54588: {'lr': 0.00035976075443515176, 'samples': 10480896, 'steps': 54587, 'loss/train': 0.1956343799829483} 08/30/2021 23:03:03 - INFO - __main__ - Step 54589: {'lr': 0.0003597559864808344, 'samples': 10481088, 'steps': 54588, 'loss/train': 0.8604037761688232} 08/30/2021 23:03:03 - INFO - __main__ - Step 54590: {'lr': 0.0003597512184770627, 'samples': 10481280, 'steps': 54589, 'loss/train': 2.722109317779541} 08/30/2021 23:03:04 - INFO - __main__ - Step 54591: {'lr': 0.0003597464504238388, 'samples': 10481472, 'steps': 54590, 'loss/train': 1.6503816843032837} 08/30/2021 23:03:05 - INFO - __main__ - Step 54592: {'lr': 0.00035974168232116486, 'samples': 10481664, 'steps': 54591, 'loss/train': 1.8491023778915405} 08/30/2021 23:03:05 - INFO - __main__ - Step 54593: {'lr': 0.00035973691416904297, 'samples': 10481856, 'steps': 54592, 'loss/train': 1.453162670135498} 08/30/2021 23:03:06 - INFO - __main__ - Step 54594: {'lr': 0.0003597321459674754, 'samples': 10482048, 'steps': 54593, 'loss/train': 1.3821334838867188} 08/30/2021 23:03:06 - INFO - __main__ - Step 54595: {'lr': 0.0003597273777164641, 'samples': 10482240, 'steps': 54594, 'loss/train': 1.3869150876998901} 08/30/2021 23:03:07 - INFO - __main__ - Step 54596: {'lr': 0.00035972260941601145, 'samples': 10482432, 'steps': 54595, 'loss/train': 0.9404004216194153} 08/30/2021 23:03:08 - INFO - __main__ - Step 54597: {'lr': 0.0003597178410661194, 'samples': 10482624, 'steps': 54596, 'loss/train': 1.1494826078414917} 08/30/2021 23:03:08 - INFO - __main__ - Step 54598: {'lr': 0.00035971307266679023, 'samples': 10482816, 'steps': 54597, 'loss/train': 1.094840168952942} 08/30/2021 23:03:09 - INFO - __main__ - Step 54599: {'lr': 0.000359708304218026, 'samples': 10483008, 'steps': 54598, 'loss/train': 1.6898934841156006} 08/30/2021 23:03:09 - INFO - __main__ - Step 54600: {'lr': 0.00035970353571982897, 'samples': 10483200, 'steps': 54599, 'loss/train': 1.682647705078125} 08/30/2021 23:03:09 - INFO - __main__ - Step 54601: {'lr': 0.0003596987671722012, 'samples': 10483392, 'steps': 54600, 'loss/train': 1.36082923412323} 08/30/2021 23:03:11 - INFO - __main__ - Step 54602: {'lr': 0.00035969399857514484, 'samples': 10483584, 'steps': 54601, 'loss/train': 0.7325038313865662} 08/30/2021 23:03:11 - INFO - __main__ - Step 54603: {'lr': 0.00035968922992866205, 'samples': 10483776, 'steps': 54602, 'loss/train': 1.1663405895233154} 08/30/2021 23:03:12 - INFO - __main__ - Step 54604: {'lr': 0.00035968446123275493, 'samples': 10483968, 'steps': 54603, 'loss/train': 1.9017565250396729} 08/30/2021 23:03:12 - INFO - __main__ - Step 54605: {'lr': 0.00035967969248742576, 'samples': 10484160, 'steps': 54604, 'loss/train': 1.2085704803466797} 08/30/2021 23:03:12 - INFO - __main__ - Step 54606: {'lr': 0.00035967492369267664, 'samples': 10484352, 'steps': 54605, 'loss/train': 1.9153189659118652} 08/30/2021 23:03:13 - INFO - __main__ - Step 54607: {'lr': 0.00035967015484850964, 'samples': 10484544, 'steps': 54606, 'loss/train': 1.165961503982544} 08/30/2021 23:03:14 - INFO - __main__ - Step 54608: {'lr': 0.000359665385954927, 'samples': 10484736, 'steps': 54607, 'loss/train': 1.1614915132522583} 08/30/2021 23:03:15 - INFO - __main__ - Step 54609: {'lr': 0.00035966061701193073, 'samples': 10484928, 'steps': 54608, 'loss/train': 0.6280215978622437} 08/30/2021 23:03:15 - INFO - __main__ - Step 54610: {'lr': 0.00035965584801952316, 'samples': 10485120, 'steps': 54609, 'loss/train': 1.087389349937439} 08/30/2021 23:03:16 - INFO - __main__ - Step 54611: {'lr': 0.0003596510789777064, 'samples': 10485312, 'steps': 54610, 'loss/train': 1.3975533246994019} 08/30/2021 23:03:16 - INFO - __main__ - Step 54612: {'lr': 0.0003596463098864825, 'samples': 10485504, 'steps': 54611, 'loss/train': 1.3112858533859253} 08/30/2021 23:03:18 - INFO - __main__ - Step 54613: {'lr': 0.00035964154074585365, 'samples': 10485696, 'steps': 54612, 'loss/train': 1.4799295663833618} 08/30/2021 23:03:18 - INFO - __main__ - Step 54614: {'lr': 0.00035963677155582204, 'samples': 10485888, 'steps': 54613, 'loss/train': 1.3409079313278198} 08/30/2021 23:03:19 - INFO - __main__ - Step 54615: {'lr': 0.0003596320023163898, 'samples': 10486080, 'steps': 54614, 'loss/train': 0.8664289116859436} 08/30/2021 23:03:19 - INFO - __main__ - Step 54616: {'lr': 0.000359627233027559, 'samples': 10486272, 'steps': 54615, 'loss/train': 0.8100765943527222} 08/30/2021 23:03:20 - INFO - __main__ - Step 54617: {'lr': 0.0003596224636893319, 'samples': 10486464, 'steps': 54616, 'loss/train': 1.4202203750610352} 08/30/2021 23:03:21 - INFO - __main__ - Step 54618: {'lr': 0.0003596176943017107, 'samples': 10486656, 'steps': 54617, 'loss/train': 1.6955711841583252} 08/30/2021 23:03:22 - INFO - __main__ - Step 54619: {'lr': 0.0003596129248646974, 'samples': 10486848, 'steps': 54618, 'loss/train': 1.487973690032959} 08/30/2021 23:03:22 - INFO - __main__ - Step 54620: {'lr': 0.0003596081553782942, 'samples': 10487040, 'steps': 54619, 'loss/train': 1.3339719772338867} 08/30/2021 23:03:23 - INFO - __main__ - Step 54621: {'lr': 0.0003596033858425032, 'samples': 10487232, 'steps': 54620, 'loss/train': 1.9933583736419678} 08/30/2021 23:03:23 - INFO - __main__ - Step 54622: {'lr': 0.00035959861625732667, 'samples': 10487424, 'steps': 54621, 'loss/train': 1.547165870666504} 08/30/2021 23:03:24 - INFO - __main__ - Step 54623: {'lr': 0.0003595938466227667, 'samples': 10487616, 'steps': 54622, 'loss/train': 1.145972728729248} 08/30/2021 23:03:25 - INFO - __main__ - Step 54624: {'lr': 0.0003595890769388254, 'samples': 10487808, 'steps': 54623, 'loss/train': 1.2730042934417725} 08/30/2021 23:03:25 - INFO - __main__ - Step 54625: {'lr': 0.00035958430720550494, 'samples': 10488000, 'steps': 54624, 'loss/train': 1.6948461532592773} 08/30/2021 23:03:26 - INFO - __main__ - Step 54626: {'lr': 0.00035957953742280754, 'samples': 10488192, 'steps': 54625, 'loss/train': 1.0461784601211548} 08/30/2021 23:03:26 - INFO - __main__ - Step 54627: {'lr': 0.0003595747675907352, 'samples': 10488384, 'steps': 54626, 'loss/train': 1.3459765911102295} 08/30/2021 23:03:27 - INFO - __main__ - Step 54628: {'lr': 0.0003595699977092902, 'samples': 10488576, 'steps': 54627, 'loss/train': 1.5525670051574707} 08/30/2021 23:03:28 - INFO - __main__ - Step 54629: {'lr': 0.00035956522777847474, 'samples': 10488768, 'steps': 54628, 'loss/train': 1.1322119235992432} 08/30/2021 23:03:28 - INFO - __main__ - Step 54630: {'lr': 0.00035956045779829085, 'samples': 10488960, 'steps': 54629, 'loss/train': 1.0116513967514038} 08/30/2021 23:03:29 - INFO - __main__ - Step 54631: {'lr': 0.00035955568776874057, 'samples': 10489152, 'steps': 54630, 'loss/train': 1.490096926689148} 08/30/2021 23:03:29 - INFO - __main__ - Step 54632: {'lr': 0.0003595509176898263, 'samples': 10489344, 'steps': 54631, 'loss/train': 1.4106022119522095} 08/30/2021 23:03:31 - INFO - __main__ - Step 54633: {'lr': 0.0003595461475615501, 'samples': 10489536, 'steps': 54632, 'loss/train': 1.5777695178985596} 08/30/2021 23:03:31 - INFO - __main__ - Step 54634: {'lr': 0.00035954137738391405, 'samples': 10489728, 'steps': 54633, 'loss/train': 1.5173395872116089} 08/30/2021 23:03:32 - INFO - __main__ - Step 54635: {'lr': 0.00035953660715692037, 'samples': 10489920, 'steps': 54634, 'loss/train': 1.6186579465866089} 08/30/2021 23:03:32 - INFO - __main__ - Step 54636: {'lr': 0.0003595318368805711, 'samples': 10490112, 'steps': 54635, 'loss/train': 1.632763385772705} 08/30/2021 23:03:32 - INFO - __main__ - Step 54637: {'lr': 0.00035952706655486855, 'samples': 10490304, 'steps': 54636, 'loss/train': 1.479754090309143} 08/30/2021 23:03:33 - INFO - __main__ - Step 54638: {'lr': 0.0003595222961798148, 'samples': 10490496, 'steps': 54637, 'loss/train': 1.2317792177200317} 08/30/2021 23:03:34 - INFO - __main__ - Step 54639: {'lr': 0.000359517525755412, 'samples': 10490688, 'steps': 54638, 'loss/train': 1.6764943599700928} 08/30/2021 23:03:35 - INFO - __main__ - Step 54640: {'lr': 0.0003595127552816623, 'samples': 10490880, 'steps': 54639, 'loss/train': 0.9140795469284058} 08/30/2021 23:03:35 - INFO - __main__ - Step 54641: {'lr': 0.00035950798475856783, 'samples': 10491072, 'steps': 54640, 'loss/train': 1.450689435005188} 08/30/2021 23:03:35 - INFO - __main__ - Step 54642: {'lr': 0.0003595032141861307, 'samples': 10491264, 'steps': 54641, 'loss/train': 1.4408491849899292} 08/30/2021 23:03:36 - INFO - __main__ - Step 54643: {'lr': 0.00035949844356435314, 'samples': 10491456, 'steps': 54642, 'loss/train': 1.7538901567459106} 08/30/2021 23:03:37 - INFO - __main__ - Step 54644: {'lr': 0.00035949367289323723, 'samples': 10491648, 'steps': 54643, 'loss/train': 1.5709326267242432} 08/30/2021 23:03:37 - INFO - __main__ - Step 54645: {'lr': 0.00035948890217278525, 'samples': 10491840, 'steps': 54644, 'loss/train': 1.1291842460632324} 08/30/2021 23:03:38 - INFO - __main__ - Step 54646: {'lr': 0.0003594841314029992, 'samples': 10492032, 'steps': 54645, 'loss/train': 0.7814945578575134} 08/30/2021 23:03:38 - INFO - __main__ - Step 54647: {'lr': 0.00035947936058388134, 'samples': 10492224, 'steps': 54646, 'loss/train': 1.2533886432647705} 08/30/2021 23:03:39 - INFO - __main__ - Step 54648: {'lr': 0.00035947458971543375, 'samples': 10492416, 'steps': 54647, 'loss/train': 1.6516329050064087} 08/30/2021 23:03:40 - INFO - __main__ - Step 54649: {'lr': 0.00035946981879765854, 'samples': 10492608, 'steps': 54648, 'loss/train': 1.001318335533142} 08/30/2021 23:03:40 - INFO - __main__ - Step 54650: {'lr': 0.000359465047830558, 'samples': 10492800, 'steps': 54649, 'loss/train': 0.6158228516578674} 08/30/2021 23:03:41 - INFO - __main__ - Step 54651: {'lr': 0.0003594602768141342, 'samples': 10492992, 'steps': 54650, 'loss/train': 1.5872671604156494} 08/30/2021 23:03:41 - INFO - __main__ - Step 54652: {'lr': 0.0003594555057483892, 'samples': 10493184, 'steps': 54651, 'loss/train': 0.7219210267066956} 08/30/2021 23:03:41 - INFO - __main__ - Step 54653: {'lr': 0.0003594507346333253, 'samples': 10493376, 'steps': 54652, 'loss/train': 1.807542085647583} 08/30/2021 23:03:43 - INFO - __main__ - Step 54654: {'lr': 0.00035944596346894456, 'samples': 10493568, 'steps': 54653, 'loss/train': 0.4334940016269684} 08/30/2021 23:03:44 - INFO - __main__ - Step 54655: {'lr': 0.00035944119225524916, 'samples': 10493760, 'steps': 54654, 'loss/train': 0.6189199686050415} 08/30/2021 23:03:44 - INFO - __main__ - Step 54656: {'lr': 0.00035943642099224126, 'samples': 10493952, 'steps': 54655, 'loss/train': 1.6385068893432617} 08/30/2021 23:03:44 - INFO - __main__ - Step 54657: {'lr': 0.00035943164967992304, 'samples': 10494144, 'steps': 54656, 'loss/train': 1.5558799505233765} 08/30/2021 23:03:45 - INFO - __main__ - Step 54658: {'lr': 0.00035942687831829655, 'samples': 10494336, 'steps': 54657, 'loss/train': 1.5776126384735107} 08/30/2021 23:03:45 - INFO - __main__ - Step 54659: {'lr': 0.000359422106907364, 'samples': 10494528, 'steps': 54658, 'loss/train': 1.2401173114776611} 08/30/2021 23:03:46 - INFO - __main__ - Step 54660: {'lr': 0.00035941733544712755, 'samples': 10494720, 'steps': 54659, 'loss/train': 1.4024578332901} 08/30/2021 23:03:47 - INFO - __main__ - Step 54661: {'lr': 0.0003594125639375894, 'samples': 10494912, 'steps': 54660, 'loss/train': 1.390967845916748} 08/30/2021 23:03:47 - INFO - __main__ - Step 54662: {'lr': 0.00035940779237875154, 'samples': 10495104, 'steps': 54661, 'loss/train': 1.1025558710098267} 08/30/2021 23:03:47 - INFO - __main__ - Step 54663: {'lr': 0.00035940302077061624, 'samples': 10495296, 'steps': 54662, 'loss/train': 1.749678134918213} 08/30/2021 23:03:48 - INFO - __main__ - Step 54664: {'lr': 0.0003593982491131857, 'samples': 10495488, 'steps': 54663, 'loss/train': 1.2479114532470703} 08/30/2021 23:03:49 - INFO - __main__ - Step 54665: {'lr': 0.00035939347740646186, 'samples': 10495680, 'steps': 54664, 'loss/train': 1.4891436100006104} 08/30/2021 23:03:50 - INFO - __main__ - Step 54666: {'lr': 0.00035938870565044713, 'samples': 10495872, 'steps': 54665, 'loss/train': 1.5442767143249512} 08/30/2021 23:03:50 - INFO - __main__ - Step 54667: {'lr': 0.0003593839338451435, 'samples': 10496064, 'steps': 54666, 'loss/train': 1.1562092304229736} 08/30/2021 23:03:51 - INFO - __main__ - Step 54668: {'lr': 0.0003593791619905532, 'samples': 10496256, 'steps': 54667, 'loss/train': 1.853531002998352} 08/30/2021 23:03:51 - INFO - __main__ - Step 54669: {'lr': 0.00035937439008667827, 'samples': 10496448, 'steps': 54668, 'loss/train': 1.4185580015182495} 08/30/2021 23:03:53 - INFO - __main__ - Step 54670: {'lr': 0.00035936961813352094, 'samples': 10496640, 'steps': 54669, 'loss/train': 0.33569204807281494} 08/30/2021 23:03:54 - INFO - __main__ - Step 54671: {'lr': 0.0003593648461310833, 'samples': 10496832, 'steps': 54670, 'loss/train': 1.240635633468628} 08/30/2021 23:03:54 - INFO - __main__ - Step 54672: {'lr': 0.0003593600740793676, 'samples': 10497024, 'steps': 54671, 'loss/train': 1.147263526916504} 08/30/2021 23:03:55 - INFO - __main__ - Step 54673: {'lr': 0.00035935530197837596, 'samples': 10497216, 'steps': 54672, 'loss/train': 0.6365401744842529} 08/30/2021 23:03:55 - INFO - __main__ - Step 54674: {'lr': 0.00035935052982811046, 'samples': 10497408, 'steps': 54673, 'loss/train': 0.9249856472015381} 08/30/2021 23:03:57 - INFO - __main__ - Step 54675: {'lr': 0.00035934575762857333, 'samples': 10497600, 'steps': 54674, 'loss/train': 1.630801796913147} 08/30/2021 23:03:57 - INFO - __main__ - Step 54676: {'lr': 0.00035934098537976675, 'samples': 10497792, 'steps': 54675, 'loss/train': 1.8333457708358765} 08/30/2021 23:03:58 - INFO - __main__ - Step 54677: {'lr': 0.00035933621308169273, 'samples': 10497984, 'steps': 54676, 'loss/train': 0.16368624567985535} 08/30/2021 23:03:58 - INFO - __main__ - Step 54678: {'lr': 0.0003593314407343535, 'samples': 10498176, 'steps': 54677, 'loss/train': 0.24434149265289307} 08/30/2021 23:03:58 - INFO - __main__ - Step 54679: {'lr': 0.00035932666833775117, 'samples': 10498368, 'steps': 54678, 'loss/train': 1.4497014284133911} 08/30/2021 23:03:59 - INFO - __main__ - Step 54680: {'lr': 0.00035932189589188803, 'samples': 10498560, 'steps': 54679, 'loss/train': 1.4546630382537842} 08/30/2021 23:04:00 - INFO - __main__ - Step 54681: {'lr': 0.00035931712339676617, 'samples': 10498752, 'steps': 54680, 'loss/train': 0.8067395091056824} 08/30/2021 23:04:00 - INFO - __main__ - Step 54682: {'lr': 0.00035931235085238754, 'samples': 10498944, 'steps': 54681, 'loss/train': 1.4721364974975586} 08/30/2021 23:04:01 - INFO - __main__ - Step 54683: {'lr': 0.0003593075782587545, 'samples': 10499136, 'steps': 54682, 'loss/train': 0.8990991115570068} 08/30/2021 23:04:01 - INFO - __main__ - Step 54684: {'lr': 0.0003593028056158692, 'samples': 10499328, 'steps': 54683, 'loss/train': 1.0903825759887695} 08/30/2021 23:04:02 - INFO - __main__ - Step 54685: {'lr': 0.0003592980329237337, 'samples': 10499520, 'steps': 54684, 'loss/train': 1.6617538928985596} 08/30/2021 23:04:03 - INFO - __main__ - Step 54686: {'lr': 0.0003592932601823502, 'samples': 10499712, 'steps': 54685, 'loss/train': 0.9660040736198425} 08/30/2021 23:04:04 - INFO - __main__ - Step 54687: {'lr': 0.0003592884873917209, 'samples': 10499904, 'steps': 54686, 'loss/train': 1.1456538438796997} 08/30/2021 23:04:04 - INFO - __main__ - Step 54688: {'lr': 0.0003592837145518479, 'samples': 10500096, 'steps': 54687, 'loss/train': 2.5816855430603027} 08/30/2021 23:04:04 - INFO - __main__ - Step 54689: {'lr': 0.00035927894166273323, 'samples': 10500288, 'steps': 54688, 'loss/train': 0.042873017489910126} 08/30/2021 23:04:05 - INFO - __main__ - Step 54690: {'lr': 0.0003592741687243792, 'samples': 10500480, 'steps': 54689, 'loss/train': 0.6734894514083862} 08/30/2021 23:04:06 - INFO - __main__ - Step 54691: {'lr': 0.00035926939573678796, 'samples': 10500672, 'steps': 54690, 'loss/train': 0.19261178374290466} 08/30/2021 23:04:07 - INFO - __main__ - Step 54692: {'lr': 0.0003592646226999616, 'samples': 10500864, 'steps': 54691, 'loss/train': 1.3513233661651611} 08/30/2021 23:04:07 - INFO - __main__ - Step 54693: {'lr': 0.0003592598496139023, 'samples': 10501056, 'steps': 54692, 'loss/train': 0.6984632015228271} 08/30/2021 23:04:07 - INFO - __main__ - Step 54694: {'lr': 0.0003592550764786122, 'samples': 10501248, 'steps': 54693, 'loss/train': 1.274774432182312} 08/30/2021 23:04:08 - INFO - __main__ - Step 54695: {'lr': 0.00035925030329409343, 'samples': 10501440, 'steps': 54694, 'loss/train': 1.4966890811920166} 08/30/2021 23:04:08 - INFO - __main__ - Step 54696: {'lr': 0.0003592455300603481, 'samples': 10501632, 'steps': 54695, 'loss/train': 1.3233423233032227} 08/30/2021 23:04:09 - INFO - __main__ - Step 54697: {'lr': 0.0003592407567773785, 'samples': 10501824, 'steps': 54696, 'loss/train': 1.7010083198547363} 08/30/2021 23:04:10 - INFO - __main__ - Step 54698: {'lr': 0.0003592359834451866, 'samples': 10502016, 'steps': 54697, 'loss/train': 1.6510733366012573} 08/30/2021 23:04:10 - INFO - __main__ - Step 54699: {'lr': 0.0003592312100637748, 'samples': 10502208, 'steps': 54698, 'loss/train': 1.4536194801330566} 08/30/2021 23:04:11 - INFO - __main__ - Step 54700: {'lr': 0.00035922643663314504, 'samples': 10502400, 'steps': 54699, 'loss/train': 1.4917083978652954} 08/30/2021 23:04:11 - INFO - __main__ - Step 54701: {'lr': 0.00035922166315329954, 'samples': 10502592, 'steps': 54700, 'loss/train': 1.3184608221054077} 08/30/2021 23:04:13 - INFO - __main__ - Step 54702: {'lr': 0.0003592168896242404, 'samples': 10502784, 'steps': 54701, 'loss/train': 0.8541215062141418} 08/30/2021 23:04:13 - INFO - __main__ - Step 54703: {'lr': 0.00035921211604596985, 'samples': 10502976, 'steps': 54702, 'loss/train': 0.5011487007141113} 08/30/2021 23:04:13 - INFO - __main__ - Step 54704: {'lr': 0.00035920734241849, 'samples': 10503168, 'steps': 54703, 'loss/train': 1.5765939950942993} 08/30/2021 23:04:14 - INFO - __main__ - Step 54705: {'lr': 0.00035920256874180304, 'samples': 10503360, 'steps': 54704, 'loss/train': 0.9782493710517883} 08/30/2021 23:04:14 - INFO - __main__ - Step 54706: {'lr': 0.00035919779501591097, 'samples': 10503552, 'steps': 54705, 'loss/train': 1.5047963857650757} 08/30/2021 23:04:15 - INFO - __main__ - Step 54707: {'lr': 0.00035919302124081613, 'samples': 10503744, 'steps': 54706, 'loss/train': 1.508135199546814} 08/30/2021 23:04:16 - INFO - __main__ - Step 54708: {'lr': 0.0003591882474165207, 'samples': 10503936, 'steps': 54707, 'loss/train': 1.7539702653884888} 08/30/2021 23:04:16 - INFO - __main__ - Step 54709: {'lr': 0.00035918347354302663, 'samples': 10504128, 'steps': 54708, 'loss/train': 1.267782211303711} 08/30/2021 23:04:17 - INFO - __main__ - Step 54710: {'lr': 0.00035917869962033615, 'samples': 10504320, 'steps': 54709, 'loss/train': 1.2069759368896484} 08/30/2021 23:04:17 - INFO - __main__ - Step 54711: {'lr': 0.00035917392564845146, 'samples': 10504512, 'steps': 54710, 'loss/train': 0.7255215644836426} 08/30/2021 23:04:18 - INFO - __main__ - Step 54712: {'lr': 0.00035916915162737467, 'samples': 10504704, 'steps': 54711, 'loss/train': 1.448610782623291} 08/30/2021 23:04:19 - INFO - __main__ - Step 54713: {'lr': 0.00035916437755710795, 'samples': 10504896, 'steps': 54712, 'loss/train': 1.2432438135147095} 08/30/2021 23:04:19 - INFO - __main__ - Step 54714: {'lr': 0.0003591596034376535, 'samples': 10505088, 'steps': 54713, 'loss/train': 1.4643007516860962} 08/30/2021 23:04:20 - INFO - __main__ - Step 54715: {'lr': 0.0003591548292690134, 'samples': 10505280, 'steps': 54714, 'loss/train': 1.5806128978729248} 08/30/2021 23:04:20 - INFO - __main__ - Step 54716: {'lr': 0.0003591500550511898, 'samples': 10505472, 'steps': 54715, 'loss/train': 1.3093656301498413} 08/30/2021 23:04:21 - INFO - __main__ - Step 54717: {'lr': 0.00035914528078418486, 'samples': 10505664, 'steps': 54716, 'loss/train': 1.8600953817367554} 08/30/2021 23:04:22 - INFO - __main__ - Step 54718: {'lr': 0.0003591405064680007, 'samples': 10505856, 'steps': 54717, 'loss/train': 1.120902419090271} 08/30/2021 23:04:22 - INFO - __main__ - Step 54719: {'lr': 0.0003591357321026396, 'samples': 10506048, 'steps': 54718, 'loss/train': 1.6283214092254639} 08/30/2021 23:04:23 - INFO - __main__ - Step 54720: {'lr': 0.00035913095768810356, 'samples': 10506240, 'steps': 54719, 'loss/train': 1.5333529710769653} 08/30/2021 23:04:23 - INFO - __main__ - Step 54721: {'lr': 0.00035912618322439483, 'samples': 10506432, 'steps': 54720, 'loss/train': 1.8235855102539062} 08/30/2021 23:04:25 - INFO - __main__ - Step 54722: {'lr': 0.00035912140871151554, 'samples': 10506624, 'steps': 54721, 'loss/train': 1.3883310556411743} 08/30/2021 23:04:26 - INFO - __main__ - Step 54723: {'lr': 0.0003591166341494678, 'samples': 10506816, 'steps': 54722, 'loss/train': 0.9013878703117371} 08/30/2021 23:04:26 - INFO - __main__ - Step 54724: {'lr': 0.00035911185953825373, 'samples': 10507008, 'steps': 54723, 'loss/train': 1.7986218929290771} 08/30/2021 23:04:26 - INFO - __main__ - Step 54725: {'lr': 0.0003591070848778756, 'samples': 10507200, 'steps': 54724, 'loss/train': 1.0796217918395996} 08/30/2021 23:04:27 - INFO - __main__ - Step 54726: {'lr': 0.0003591023101683355, 'samples': 10507392, 'steps': 54725, 'loss/train': 1.3720126152038574} 08/30/2021 23:04:27 - INFO - __main__ - Step 54727: {'lr': 0.0003590975354096356, 'samples': 10507584, 'steps': 54726, 'loss/train': 1.1427823305130005} 08/30/2021 23:04:29 - INFO - __main__ - Step 54728: {'lr': 0.000359092760601778, 'samples': 10507776, 'steps': 54727, 'loss/train': 0.9771320819854736} 08/30/2021 23:04:29 - INFO - __main__ - Step 54729: {'lr': 0.0003590879857447649, 'samples': 10507968, 'steps': 54728, 'loss/train': 1.170641303062439} 08/30/2021 23:04:30 - INFO - __main__ - Step 54730: {'lr': 0.0003590832108385985, 'samples': 10508160, 'steps': 54729, 'loss/train': 1.526761770248413} 08/30/2021 23:04:30 - INFO - __main__ - Step 54731: {'lr': 0.0003590784358832808, 'samples': 10508352, 'steps': 54730, 'loss/train': 0.8689559698104858} 08/30/2021 23:04:30 - INFO - __main__ - Step 54732: {'lr': 0.00035907366087881403, 'samples': 10508544, 'steps': 54731, 'loss/train': 1.3794056177139282} 08/30/2021 23:04:32 - INFO - __main__ - Step 54733: {'lr': 0.00035906888582520034, 'samples': 10508736, 'steps': 54732, 'loss/train': 2.078857421875} 08/30/2021 23:04:32 - INFO - __main__ - Step 54734: {'lr': 0.000359064110722442, 'samples': 10508928, 'steps': 54733, 'loss/train': 1.4995900392532349} 08/30/2021 23:04:33 - INFO - __main__ - Step 54735: {'lr': 0.00035905933557054103, 'samples': 10509120, 'steps': 54734, 'loss/train': 1.1124764680862427} 08/30/2021 23:04:33 - INFO - __main__ - Step 54736: {'lr': 0.0003590545603694996, 'samples': 10509312, 'steps': 54735, 'loss/train': 0.06038980185985565} 08/30/2021 23:04:33 - INFO - __main__ - Step 54737: {'lr': 0.0003590497851193198, 'samples': 10509504, 'steps': 54736, 'loss/train': 1.0883455276489258} 08/30/2021 23:04:35 - INFO - __main__ - Step 54738: {'lr': 0.00035904500982000386, 'samples': 10509696, 'steps': 54737, 'loss/train': 0.20443525910377502} 08/30/2021 23:04:36 - INFO - __main__ - Step 54739: {'lr': 0.0003590402344715539, 'samples': 10509888, 'steps': 54738, 'loss/train': 1.583376169204712} 08/30/2021 23:04:36 - INFO - __main__ - Step 54740: {'lr': 0.00035903545907397215, 'samples': 10510080, 'steps': 54739, 'loss/train': 0.8244765996932983} 08/30/2021 23:04:36 - INFO - __main__ - Step 54741: {'lr': 0.0003590306836272608, 'samples': 10510272, 'steps': 54740, 'loss/train': 1.1616321802139282} 08/30/2021 23:04:37 - INFO - __main__ - Step 54742: {'lr': 0.0003590259081314218, 'samples': 10510464, 'steps': 54741, 'loss/train': 1.4172818660736084} 08/30/2021 23:04:37 - INFO - __main__ - Step 54743: {'lr': 0.00035902113258645733, 'samples': 10510656, 'steps': 54742, 'loss/train': 0.019485360011458397} 08/30/2021 23:04:39 - INFO - __main__ - Step 54744: {'lr': 0.0003590163569923697, 'samples': 10510848, 'steps': 54743, 'loss/train': 1.5700057744979858} 08/30/2021 23:04:40 - INFO - __main__ - Step 54745: {'lr': 0.000359011581349161, 'samples': 10511040, 'steps': 54744, 'loss/train': 1.7024787664413452} 08/30/2021 23:04:40 - INFO - __main__ - Step 54746: {'lr': 0.00035900680565683333, 'samples': 10511232, 'steps': 54745, 'loss/train': 1.552464246749878} 08/30/2021 23:04:41 - INFO - __main__ - Step 54747: {'lr': 0.00035900202991538894, 'samples': 10511424, 'steps': 54746, 'loss/train': 0.4057244062423706} 08/30/2021 23:04:41 - INFO - __main__ - Step 54748: {'lr': 0.00035899725412482985, 'samples': 10511616, 'steps': 54747, 'loss/train': 0.37845394015312195} 08/30/2021 23:04:41 - INFO - __main__ - Step 54749: {'lr': 0.00035899247828515837, 'samples': 10511808, 'steps': 54748, 'loss/train': 0.3141857385635376} 08/30/2021 23:04:43 - INFO - __main__ - Step 54750: {'lr': 0.0003589877023963765, 'samples': 10512000, 'steps': 54749, 'loss/train': 1.2904633283615112} 08/30/2021 23:04:43 - INFO - __main__ - Step 54751: {'lr': 0.0003589829264584864, 'samples': 10512192, 'steps': 54750, 'loss/train': 1.0025943517684937} 08/30/2021 23:04:44 - INFO - __main__ - Step 54752: {'lr': 0.00035897815047149033, 'samples': 10512384, 'steps': 54751, 'loss/train': 1.240922212600708} 08/30/2021 23:04:44 - INFO - __main__ - Step 54753: {'lr': 0.00035897337443539036, 'samples': 10512576, 'steps': 54752, 'loss/train': 1.5903171300888062} 08/30/2021 23:04:44 - INFO - __main__ - Step 54754: {'lr': 0.0003589685983501887, 'samples': 10512768, 'steps': 54753, 'loss/train': 0.7101109027862549} 08/30/2021 23:04:45 - INFO - __main__ - Step 54755: {'lr': 0.0003589638222158874, 'samples': 10512960, 'steps': 54754, 'loss/train': 1.090273141860962} 08/30/2021 23:04:46 - INFO - __main__ - Step 54756: {'lr': 0.00035895904603248875, 'samples': 10513152, 'steps': 54755, 'loss/train': 1.601698875427246} 08/30/2021 23:04:47 - INFO - __main__ - Step 54757: {'lr': 0.0003589542697999948, 'samples': 10513344, 'steps': 54756, 'loss/train': 3.522212028503418} 08/30/2021 23:04:47 - INFO - __main__ - Step 54758: {'lr': 0.00035894949351840784, 'samples': 10513536, 'steps': 54757, 'loss/train': 2.6060585975646973} 08/30/2021 23:04:47 - INFO - __main__ - Step 54759: {'lr': 0.0003589447171877298, 'samples': 10513728, 'steps': 54758, 'loss/train': 1.4959547519683838} 08/30/2021 23:04:48 - INFO - __main__ - Step 54760: {'lr': 0.000358939940807963, 'samples': 10513920, 'steps': 54759, 'loss/train': 0.6446624994277954} 08/30/2021 23:04:49 - INFO - __main__ - Step 54761: {'lr': 0.00035893516437910956, 'samples': 10514112, 'steps': 54760, 'loss/train': 1.4268418550491333} 08/30/2021 23:04:50 - INFO - __main__ - Step 54762: {'lr': 0.00035893038790117156, 'samples': 10514304, 'steps': 54761, 'loss/train': 1.3592456579208374} 08/30/2021 23:04:50 - INFO - __main__ - Step 54763: {'lr': 0.0003589256113741513, 'samples': 10514496, 'steps': 54762, 'loss/train': 1.4319016933441162} 08/30/2021 23:04:51 - INFO - __main__ - Step 54764: {'lr': 0.00035892083479805077, 'samples': 10514688, 'steps': 54763, 'loss/train': 1.1870619058609009} 08/30/2021 23:04:51 - INFO - __main__ - Step 54765: {'lr': 0.0003589160581728722, 'samples': 10514880, 'steps': 54764, 'loss/train': 1.6153000593185425} 08/30/2021 23:04:53 - INFO - __main__ - Step 54766: {'lr': 0.0003589112814986177, 'samples': 10515072, 'steps': 54765, 'loss/train': 0.8619815707206726} 08/30/2021 23:04:53 - INFO - __main__ - Step 54767: {'lr': 0.00035890650477528953, 'samples': 10515264, 'steps': 54766, 'loss/train': 0.8369243144989014} 08/30/2021 23:04:53 - INFO - __main__ - Step 54768: {'lr': 0.00035890172800288965, 'samples': 10515456, 'steps': 54767, 'loss/train': 1.1500431299209595} 08/30/2021 23:04:54 - INFO - __main__ - Step 54769: {'lr': 0.0003588969511814205, 'samples': 10515648, 'steps': 54768, 'loss/train': 1.7910209894180298} 08/30/2021 23:04:54 - INFO - __main__ - Step 54770: {'lr': 0.00035889217431088396, 'samples': 10515840, 'steps': 54769, 'loss/train': 1.439741849899292} 08/30/2021 23:04:56 - INFO - __main__ - Step 54771: {'lr': 0.00035888739739128227, 'samples': 10516032, 'steps': 54770, 'loss/train': 0.945563554763794} 08/30/2021 23:04:56 - INFO - __main__ - Step 54772: {'lr': 0.00035888262042261767, 'samples': 10516224, 'steps': 54771, 'loss/train': 1.5466349124908447} 08/30/2021 23:04:57 - INFO - __main__ - Step 54773: {'lr': 0.0003588778434048922, 'samples': 10516416, 'steps': 54772, 'loss/train': 1.614445447921753} 08/30/2021 23:04:57 - INFO - __main__ - Step 54774: {'lr': 0.0003588730663381081, 'samples': 10516608, 'steps': 54773, 'loss/train': 1.1095051765441895} 08/30/2021 23:04:57 - INFO - __main__ - Step 54775: {'lr': 0.00035886828922226737, 'samples': 10516800, 'steps': 54774, 'loss/train': 0.934881329536438} 08/30/2021 23:04:58 - INFO - __main__ - Step 54776: {'lr': 0.00035886351205737237, 'samples': 10516992, 'steps': 54775, 'loss/train': 0.8662691712379456} 08/30/2021 23:04:59 - INFO - __main__ - Step 54777: {'lr': 0.00035885873484342514, 'samples': 10517184, 'steps': 54776, 'loss/train': 0.26917487382888794} 08/30/2021 23:05:00 - INFO - __main__ - Step 54778: {'lr': 0.00035885395758042784, 'samples': 10517376, 'steps': 54777, 'loss/train': 1.4882285594940186} 08/30/2021 23:05:00 - INFO - __main__ - Step 54779: {'lr': 0.0003588491802683826, 'samples': 10517568, 'steps': 54778, 'loss/train': 1.3917410373687744} 08/30/2021 23:05:00 - INFO - __main__ - Step 54780: {'lr': 0.0003588444029072916, 'samples': 10517760, 'steps': 54779, 'loss/train': 0.669773280620575} 08/30/2021 23:05:01 - INFO - __main__ - Step 54781: {'lr': 0.000358839625497157, 'samples': 10517952, 'steps': 54780, 'loss/train': 0.9478147625923157} 08/30/2021 23:05:03 - INFO - __main__ - Step 54782: {'lr': 0.0003588348480379809, 'samples': 10518144, 'steps': 54781, 'loss/train': 1.8828073740005493} 08/30/2021 23:05:03 - INFO - __main__ - Step 54783: {'lr': 0.0003588300705297656, 'samples': 10518336, 'steps': 54782, 'loss/train': 0.32478082180023193} 08/30/2021 23:05:04 - INFO - __main__ - Step 54784: {'lr': 0.0003588252929725131, 'samples': 10518528, 'steps': 54783, 'loss/train': 1.2364157438278198} 08/30/2021 23:05:04 - INFO - __main__ - Step 54785: {'lr': 0.0003588205153662256, 'samples': 10518720, 'steps': 54784, 'loss/train': 0.6688212752342224} 08/30/2021 23:05:04 - INFO - __main__ - Step 54786: {'lr': 0.0003588157377109052, 'samples': 10518912, 'steps': 54785, 'loss/train': 1.8014135360717773} 08/30/2021 23:05:06 - INFO - __main__ - Step 54787: {'lr': 0.0003588109600065541, 'samples': 10519104, 'steps': 54786, 'loss/train': 1.2262176275253296} 08/30/2021 23:05:06 - INFO - __main__ - Step 54788: {'lr': 0.0003588061822531745, 'samples': 10519296, 'steps': 54787, 'loss/train': 1.5536518096923828} 08/30/2021 23:05:07 - INFO - __main__ - Step 54789: {'lr': 0.00035880140445076857, 'samples': 10519488, 'steps': 54788, 'loss/train': 1.193449854850769} 08/30/2021 23:05:07 - INFO - __main__ - Step 54790: {'lr': 0.0003587966265993384, 'samples': 10519680, 'steps': 54789, 'loss/train': 1.524629831314087} 08/30/2021 23:05:07 - INFO - __main__ - Step 54791: {'lr': 0.0003587918486988861, 'samples': 10519872, 'steps': 54790, 'loss/train': 1.247126579284668} 08/30/2021 23:05:09 - INFO - __main__ - Step 54792: {'lr': 0.0003587870707494139, 'samples': 10520064, 'steps': 54791, 'loss/train': 1.4787753820419312} 08/30/2021 23:05:09 - INFO - __main__ - Step 54793: {'lr': 0.0003587822927509239, 'samples': 10520256, 'steps': 54792, 'loss/train': 2.1730892658233643} 08/30/2021 23:05:10 - INFO - __main__ - Step 54794: {'lr': 0.00035877751470341824, 'samples': 10520448, 'steps': 54793, 'loss/train': 1.630399465560913} 08/30/2021 23:05:10 - INFO - __main__ - Step 54795: {'lr': 0.00035877273660689916, 'samples': 10520640, 'steps': 54794, 'loss/train': 1.3768742084503174} 08/30/2021 23:05:10 - INFO - __main__ - Step 54796: {'lr': 0.0003587679584613688, 'samples': 10520832, 'steps': 54795, 'loss/train': 1.5608149766921997} 08/30/2021 23:05:12 - INFO - __main__ - Step 54797: {'lr': 0.00035876318026682925, 'samples': 10521024, 'steps': 54796, 'loss/train': 0.5692048072814941} 08/30/2021 23:05:12 - INFO - __main__ - Step 54798: {'lr': 0.0003587584020232827, 'samples': 10521216, 'steps': 54797, 'loss/train': 1.264999508857727} 08/30/2021 23:05:13 - INFO - __main__ - Step 54799: {'lr': 0.00035875362373073125, 'samples': 10521408, 'steps': 54798, 'loss/train': 1.406759262084961} 08/30/2021 23:05:13 - INFO - __main__ - Step 54800: {'lr': 0.00035874884538917705, 'samples': 10521600, 'steps': 54799, 'loss/train': 1.4888978004455566} 08/30/2021 23:05:13 - INFO - __main__ - Step 54801: {'lr': 0.0003587440669986224, 'samples': 10521792, 'steps': 54800, 'loss/train': 1.008644938468933} 08/30/2021 23:05:15 - INFO - __main__ - Step 54802: {'lr': 0.00035873928855906933, 'samples': 10521984, 'steps': 54801, 'loss/train': 0.9551413655281067} 08/30/2021 23:05:15 - INFO - __main__ - Step 54803: {'lr': 0.00035873451007052, 'samples': 10522176, 'steps': 54802, 'loss/train': 1.6367748975753784} 08/30/2021 23:05:16 - INFO - __main__ - Step 54804: {'lr': 0.00035872973153297657, 'samples': 10522368, 'steps': 54803, 'loss/train': 1.3025861978530884} 08/30/2021 23:05:16 - INFO - __main__ - Step 54805: {'lr': 0.0003587249529464412, 'samples': 10522560, 'steps': 54804, 'loss/train': 1.1687612533569336} 08/30/2021 23:05:16 - INFO - __main__ - Step 54806: {'lr': 0.00035872017431091605, 'samples': 10522752, 'steps': 54805, 'loss/train': 1.6905964612960815} 08/30/2021 23:05:18 - INFO - __main__ - Step 54807: {'lr': 0.0003587153956264033, 'samples': 10522944, 'steps': 54806, 'loss/train': 1.4622339010238647} 08/30/2021 23:05:18 - INFO - __main__ - Step 54808: {'lr': 0.00035871061689290496, 'samples': 10523136, 'steps': 54807, 'loss/train': 1.3033421039581299} 08/30/2021 23:05:19 - INFO - __main__ - Step 54809: {'lr': 0.00035870583811042347, 'samples': 10523328, 'steps': 54808, 'loss/train': 1.251278042793274} 08/30/2021 23:05:19 - INFO - __main__ - Step 54810: {'lr': 0.0003587010592789607, 'samples': 10523520, 'steps': 54809, 'loss/train': 0.07526694238185883} 08/30/2021 23:05:19 - INFO - __main__ - Step 54811: {'lr': 0.0003586962803985189, 'samples': 10523712, 'steps': 54810, 'loss/train': 1.7876299619674683} 08/30/2021 23:05:21 - INFO - __main__ - Step 54812: {'lr': 0.00035869150146910025, 'samples': 10523904, 'steps': 54811, 'loss/train': 0.04926743730902672} 08/30/2021 23:05:21 - INFO - __main__ - Step 54813: {'lr': 0.00035868672249070684, 'samples': 10524096, 'steps': 54812, 'loss/train': 1.7865430116653442} 08/30/2021 23:05:22 - INFO - __main__ - Step 54814: {'lr': 0.00035868194346334094, 'samples': 10524288, 'steps': 54813, 'loss/train': 0.6404796838760376} 08/30/2021 23:05:22 - INFO - __main__ - Step 54815: {'lr': 0.0003586771643870046, 'samples': 10524480, 'steps': 54814, 'loss/train': 1.2337820529937744} 08/30/2021 23:05:22 - INFO - __main__ - Step 54816: {'lr': 0.0003586723852617, 'samples': 10524672, 'steps': 54815, 'loss/train': 1.2930505275726318} 08/30/2021 23:05:24 - INFO - __main__ - Step 54817: {'lr': 0.00035866760608742934, 'samples': 10524864, 'steps': 54816, 'loss/train': 2.1130659580230713} 08/30/2021 23:05:25 - INFO - __main__ - Step 54818: {'lr': 0.0003586628268641947, 'samples': 10525056, 'steps': 54817, 'loss/train': 1.547697901725769} 08/30/2021 23:05:25 - INFO - __main__ - Step 54819: {'lr': 0.00035865804759199825, 'samples': 10525248, 'steps': 54818, 'loss/train': 1.5298622846603394} 08/30/2021 23:05:25 - INFO - __main__ - Step 54820: {'lr': 0.00035865326827084224, 'samples': 10525440, 'steps': 54819, 'loss/train': 0.06545507907867432} 08/30/2021 23:05:26 - INFO - __main__ - Step 54821: {'lr': 0.00035864848890072864, 'samples': 10525632, 'steps': 54820, 'loss/train': 1.5919142961502075} 08/30/2021 23:05:26 - INFO - __main__ - Step 54822: {'lr': 0.0003586437094816598, 'samples': 10525824, 'steps': 54821, 'loss/train': 1.3524130582809448} 08/30/2021 23:05:28 - INFO - __main__ - Step 54823: {'lr': 0.00035863893001363776, 'samples': 10526016, 'steps': 54822, 'loss/train': 1.1815134286880493} 08/30/2021 23:05:28 - INFO - __main__ - Step 54824: {'lr': 0.0003586341504966647, 'samples': 10526208, 'steps': 54823, 'loss/train': 1.728411078453064} 08/30/2021 23:05:28 - INFO - __main__ - Step 54825: {'lr': 0.00035862937093074273, 'samples': 10526400, 'steps': 54824, 'loss/train': 1.0831817388534546} 08/30/2021 23:05:29 - INFO - __main__ - Step 54826: {'lr': 0.000358624591315874, 'samples': 10526592, 'steps': 54825, 'loss/train': 1.2711889743804932} 08/30/2021 23:05:29 - INFO - __main__ - Step 54827: {'lr': 0.0003586198116520608, 'samples': 10526784, 'steps': 54826, 'loss/train': 1.3327785730361938} 08/30/2021 23:05:31 - INFO - __main__ - Step 54828: {'lr': 0.0003586150319393051, 'samples': 10526976, 'steps': 54827, 'loss/train': 1.2027246952056885} 08/30/2021 23:05:32 - INFO - __main__ - Step 54829: {'lr': 0.00035861025217760924, 'samples': 10527168, 'steps': 54828, 'loss/train': 0.3271122872829437} 08/30/2021 23:05:32 - INFO - __main__ - Step 54830: {'lr': 0.00035860547236697525, 'samples': 10527360, 'steps': 54829, 'loss/train': 0.8940494060516357} 08/30/2021 23:05:32 - INFO - __main__ - Step 54831: {'lr': 0.0003586006925074053, 'samples': 10527552, 'steps': 54830, 'loss/train': 0.4592224955558777} 08/30/2021 23:05:33 - INFO - __main__ - Step 54832: {'lr': 0.0003585959125989015, 'samples': 10527744, 'steps': 54831, 'loss/train': 0.039446692913770676} 08/30/2021 23:05:34 - INFO - __main__ - Step 54833: {'lr': 0.00035859113264146607, 'samples': 10527936, 'steps': 54832, 'loss/train': 1.3696197271347046} 08/30/2021 23:05:35 - INFO - __main__ - Step 54834: {'lr': 0.00035858635263510117, 'samples': 10528128, 'steps': 54833, 'loss/train': 0.044821009039878845} 08/30/2021 23:05:35 - INFO - __main__ - Step 54835: {'lr': 0.00035858157257980894, 'samples': 10528320, 'steps': 54834, 'loss/train': 2.080129861831665} 08/30/2021 23:05:36 - INFO - __main__ - Step 54836: {'lr': 0.0003585767924755916, 'samples': 10528512, 'steps': 54835, 'loss/train': 1.3405967950820923} 08/30/2021 23:05:36 - INFO - __main__ - Step 54837: {'lr': 0.0003585720123224512, 'samples': 10528704, 'steps': 54836, 'loss/train': 0.7504355311393738} 08/30/2021 23:05:38 - INFO - __main__ - Step 54838: {'lr': 0.00035856723212038987, 'samples': 10528896, 'steps': 54837, 'loss/train': 1.0238993167877197} 08/30/2021 23:05:38 - INFO - __main__ - Step 54839: {'lr': 0.0003585624518694098, 'samples': 10529088, 'steps': 54838, 'loss/train': 1.0686841011047363} 08/30/2021 23:05:39 - INFO - __main__ - Step 54840: {'lr': 0.00035855767156951323, 'samples': 10529280, 'steps': 54839, 'loss/train': 1.5319374799728394} 08/30/2021 23:05:39 - INFO - __main__ - Step 54841: {'lr': 0.0003585528912207022, 'samples': 10529472, 'steps': 54840, 'loss/train': 0.13145770132541656} 08/30/2021 23:05:39 - INFO - __main__ - Step 54842: {'lr': 0.0003585481108229789, 'samples': 10529664, 'steps': 54841, 'loss/train': 1.5246318578720093} 08/30/2021 23:05:41 - INFO - __main__ - Step 54843: {'lr': 0.0003585433303763456, 'samples': 10529856, 'steps': 54842, 'loss/train': 1.3429349660873413} 08/30/2021 23:05:41 - INFO - __main__ - Step 54844: {'lr': 0.0003585385498808043, 'samples': 10530048, 'steps': 54843, 'loss/train': 1.8032245635986328} 08/30/2021 23:05:42 - INFO - __main__ - Step 54845: {'lr': 0.00035853376933635717, 'samples': 10530240, 'steps': 54844, 'loss/train': 1.2749818563461304} 08/30/2021 23:05:42 - INFO - __main__ - Step 54846: {'lr': 0.0003585289887430064, 'samples': 10530432, 'steps': 54845, 'loss/train': 1.229638695716858} 08/30/2021 23:05:42 - INFO - __main__ - Step 54847: {'lr': 0.0003585242081007542, 'samples': 10530624, 'steps': 54846, 'loss/train': 0.7809693217277527} 08/30/2021 23:05:43 - INFO - __main__ - Step 54848: {'lr': 0.0003585194274096026, 'samples': 10530816, 'steps': 54847, 'loss/train': 1.448364019393921} 08/30/2021 23:05:44 - INFO - __main__ - Step 54849: {'lr': 0.00035851464666955383, 'samples': 10531008, 'steps': 54848, 'loss/train': 0.1762140840291977} 08/30/2021 23:05:45 - INFO - __main__ - Step 54850: {'lr': 0.0003585098658806101, 'samples': 10531200, 'steps': 54849, 'loss/train': 0.20571884512901306} 08/30/2021 23:05:45 - INFO - __main__ - Step 54851: {'lr': 0.00035850508504277345, 'samples': 10531392, 'steps': 54850, 'loss/train': 1.350258469581604} 08/30/2021 23:05:45 - INFO - __main__ - Step 54852: {'lr': 0.0003585003041560461, 'samples': 10531584, 'steps': 54851, 'loss/train': 0.23520395159721375} 08/30/2021 23:05:46 - INFO - __main__ - Step 54853: {'lr': 0.00035849552322043016, 'samples': 10531776, 'steps': 54852, 'loss/train': 1.3796825408935547} 08/30/2021 23:05:47 - INFO - __main__ - Step 54854: {'lr': 0.0003584907422359278, 'samples': 10531968, 'steps': 54853, 'loss/train': 1.9507673978805542} 08/30/2021 23:05:48 - INFO - __main__ - Step 54855: {'lr': 0.00035848596120254125, 'samples': 10532160, 'steps': 54854, 'loss/train': 1.103347659111023} 08/30/2021 23:05:48 - INFO - __main__ - Step 54856: {'lr': 0.0003584811801202726, 'samples': 10532352, 'steps': 54855, 'loss/train': 1.323451042175293} 08/30/2021 23:05:49 - INFO - __main__ - Step 54857: {'lr': 0.00035847639898912395, 'samples': 10532544, 'steps': 54856, 'loss/train': 1.736045241355896} 08/30/2021 23:05:49 - INFO - __main__ - Step 54858: {'lr': 0.00035847161780909746, 'samples': 10532736, 'steps': 54857, 'loss/train': 0.24536152184009552} 08/30/2021 23:05:50 - INFO - __main__ - Step 54859: {'lr': 0.0003584668365801954, 'samples': 10532928, 'steps': 54858, 'loss/train': 1.7416924238204956} 08/30/2021 23:05:51 - INFO - __main__ - Step 54860: {'lr': 0.00035846205530241985, 'samples': 10533120, 'steps': 54859, 'loss/train': 1.98043692111969} 08/30/2021 23:05:51 - INFO - __main__ - Step 54861: {'lr': 0.00035845727397577296, 'samples': 10533312, 'steps': 54860, 'loss/train': 1.6187208890914917} 08/30/2021 23:05:51 - INFO - __main__ - Step 54862: {'lr': 0.0003584524926002569, 'samples': 10533504, 'steps': 54861, 'loss/train': 1.2378475666046143} 08/30/2021 23:05:52 - INFO - __main__ - Step 54863: {'lr': 0.00035844771117587396, 'samples': 10533696, 'steps': 54862, 'loss/train': 1.2186185121536255} 08/30/2021 23:05:53 - INFO - __main__ - Step 54864: {'lr': 0.0003584429297026259, 'samples': 10533888, 'steps': 54863, 'loss/train': 1.3283289670944214} 08/30/2021 23:05:54 - INFO - __main__ - Step 54865: {'lr': 0.00035843814818051537, 'samples': 10534080, 'steps': 54864, 'loss/train': 1.1565790176391602} 08/30/2021 23:05:54 - INFO - __main__ - Step 54866: {'lr': 0.0003584333666095441, 'samples': 10534272, 'steps': 54865, 'loss/train': 1.7562763690948486} 08/30/2021 23:05:54 - INFO - __main__ - Step 54867: {'lr': 0.0003584285849897145, 'samples': 10534464, 'steps': 54866, 'loss/train': 1.3092586994171143} 08/30/2021 23:05:55 - INFO - __main__ - Step 54868: {'lr': 0.00035842380332102864, 'samples': 10534656, 'steps': 54867, 'loss/train': 0.49937012791633606} 08/30/2021 23:05:56 - INFO - __main__ - Step 54869: {'lr': 0.0003584190216034887, 'samples': 10534848, 'steps': 54868, 'loss/train': 1.8234986066818237} 08/30/2021 23:05:57 - INFO - __main__ - Step 54870: {'lr': 0.0003584142398370969, 'samples': 10535040, 'steps': 54869, 'loss/train': 1.2728663682937622} 08/30/2021 23:05:57 - INFO - __main__ - Step 54871: {'lr': 0.0003584094580218552, 'samples': 10535232, 'steps': 54870, 'loss/train': 0.6441253423690796} 08/30/2021 23:05:57 - INFO - __main__ - Step 54872: {'lr': 0.00035840467615776584, 'samples': 10535424, 'steps': 54871, 'loss/train': 1.3929755687713623} 08/30/2021 23:05:58 - INFO - __main__ - Step 54873: {'lr': 0.0003583998942448311, 'samples': 10535616, 'steps': 54872, 'loss/train': 1.5756875276565552} 08/30/2021 23:05:58 - INFO - __main__ - Step 54874: {'lr': 0.000358395112283053, 'samples': 10535808, 'steps': 54873, 'loss/train': 1.4279135465621948} 08/30/2021 23:06:00 - INFO - __main__ - Step 54875: {'lr': 0.00035839033027243374, 'samples': 10536000, 'steps': 54874, 'loss/train': 0.47282174229621887} 08/30/2021 23:06:00 - INFO - __main__ - Step 54876: {'lr': 0.0003583855482129755, 'samples': 10536192, 'steps': 54875, 'loss/train': 3.4893805980682373} 08/30/2021 23:06:01 - INFO - __main__ - Step 54877: {'lr': 0.0003583807661046804, 'samples': 10536384, 'steps': 54876, 'loss/train': 1.4225763082504272} 08/30/2021 23:06:01 - INFO - __main__ - Step 54878: {'lr': 0.0003583759839475506, 'samples': 10536576, 'steps': 54877, 'loss/train': 1.8133624792099} 08/30/2021 23:06:01 - INFO - __main__ - Step 54879: {'lr': 0.00035837120174158824, 'samples': 10536768, 'steps': 54878, 'loss/train': 1.230550765991211} 08/30/2021 23:06:03 - INFO - __main__ - Step 54880: {'lr': 0.00035836641948679544, 'samples': 10536960, 'steps': 54879, 'loss/train': 1.5679596662521362} 08/30/2021 23:06:03 - INFO - __main__ - Step 54881: {'lr': 0.0003583616371831745, 'samples': 10537152, 'steps': 54880, 'loss/train': 1.2508623600006104} 08/30/2021 23:06:03 - INFO - __main__ - Step 54882: {'lr': 0.0003583568548307274, 'samples': 10537344, 'steps': 54881, 'loss/train': 1.2757011651992798} 08/30/2021 23:06:04 - INFO - __main__ - Step 54883: {'lr': 0.0003583520724294564, 'samples': 10537536, 'steps': 54882, 'loss/train': 1.3630807399749756} 08/30/2021 23:06:04 - INFO - __main__ - Step 54884: {'lr': 0.0003583472899793636, 'samples': 10537728, 'steps': 54883, 'loss/train': 1.0713759660720825} 08/30/2021 23:06:06 - INFO - __main__ - Step 54885: {'lr': 0.0003583425074804512, 'samples': 10537920, 'steps': 54884, 'loss/train': 1.2241028547286987} 08/30/2021 23:06:07 - INFO - __main__ - Step 54886: {'lr': 0.0003583377249327213, 'samples': 10538112, 'steps': 54885, 'loss/train': 1.2938129901885986} 08/30/2021 23:06:07 - INFO - __main__ - Step 54887: {'lr': 0.00035833294233617626, 'samples': 10538304, 'steps': 54886, 'loss/train': 1.2591966390609741} 08/30/2021 23:06:07 - INFO - __main__ - Step 54888: {'lr': 0.0003583281596908179, 'samples': 10538496, 'steps': 54887, 'loss/train': 1.1956291198730469} 08/30/2021 23:06:08 - INFO - __main__ - Step 54889: {'lr': 0.00035832337699664865, 'samples': 10538688, 'steps': 54888, 'loss/train': 0.8087176084518433} 08/30/2021 23:06:08 - INFO - __main__ - Step 54890: {'lr': 0.0003583185942536704, 'samples': 10538880, 'steps': 54889, 'loss/train': 1.428797960281372} 08/30/2021 23:06:10 - INFO - __main__ - Step 54891: {'lr': 0.00035831381146188556, 'samples': 10539072, 'steps': 54890, 'loss/train': 1.2802742719650269} 08/30/2021 23:06:10 - INFO - __main__ - Step 54892: {'lr': 0.00035830902862129627, 'samples': 10539264, 'steps': 54891, 'loss/train': 1.5453442335128784} 08/30/2021 23:06:10 - INFO - __main__ - Step 54893: {'lr': 0.0003583042457319045, 'samples': 10539456, 'steps': 54892, 'loss/train': 1.4810283184051514} 08/30/2021 23:06:11 - INFO - __main__ - Step 54894: {'lr': 0.0003582994627937125, 'samples': 10539648, 'steps': 54893, 'loss/train': 1.3638290166854858} 08/30/2021 23:06:11 - INFO - __main__ - Step 54895: {'lr': 0.00035829467980672247, 'samples': 10539840, 'steps': 54894, 'loss/train': 0.5878710746765137} 08/30/2021 23:06:13 - INFO - __main__ - Step 54896: {'lr': 0.00035828989677093656, 'samples': 10540032, 'steps': 54895, 'loss/train': 1.2077194452285767} 08/30/2021 23:06:13 - INFO - __main__ - Step 54897: {'lr': 0.00035828511368635684, 'samples': 10540224, 'steps': 54896, 'loss/train': 1.7178305387496948} 08/30/2021 23:06:14 - INFO - __main__ - Step 54898: {'lr': 0.0003582803305529856, 'samples': 10540416, 'steps': 54897, 'loss/train': 1.2981431484222412} 08/30/2021 23:06:14 - INFO - __main__ - Step 54899: {'lr': 0.0003582755473708248, 'samples': 10540608, 'steps': 54898, 'loss/train': 2.0900206565856934} 08/30/2021 23:06:14 - INFO - __main__ - Step 54900: {'lr': 0.00035827076413987675, 'samples': 10540800, 'steps': 54899, 'loss/train': 0.36701083183288574} 08/30/2021 23:06:16 - INFO - __main__ - Step 54901: {'lr': 0.00035826598086014357, 'samples': 10540992, 'steps': 54900, 'loss/train': 1.1260123252868652} 08/30/2021 23:06:16 - INFO - __main__ - Step 54902: {'lr': 0.0003582611975316274, 'samples': 10541184, 'steps': 54901, 'loss/train': 1.3970805406570435} 08/30/2021 23:06:16 - INFO - __main__ - Step 54903: {'lr': 0.00035825641415433045, 'samples': 10541376, 'steps': 54902, 'loss/train': 0.8591406345367432} 08/30/2021 23:06:17 - INFO - __main__ - Step 54904: {'lr': 0.0003582516307282548, 'samples': 10541568, 'steps': 54903, 'loss/train': 1.7223007678985596} 08/30/2021 23:06:17 - INFO - __main__ - Step 54905: {'lr': 0.00035824684725340263, 'samples': 10541760, 'steps': 54904, 'loss/train': 1.793871521949768} 08/30/2021 23:06:18 - INFO - __main__ - Step 54906: {'lr': 0.00035824206372977606, 'samples': 10541952, 'steps': 54905, 'loss/train': 1.8346998691558838} 08/30/2021 23:06:19 - INFO - __main__ - Step 54907: {'lr': 0.00035823728015737735, 'samples': 10542144, 'steps': 54906, 'loss/train': 1.0726392269134521} 08/30/2021 23:06:20 - INFO - __main__ - Step 54908: {'lr': 0.0003582324965362086, 'samples': 10542336, 'steps': 54907, 'loss/train': 1.670105218887329} 08/30/2021 23:06:20 - INFO - __main__ - Step 54909: {'lr': 0.0003582277128662719, 'samples': 10542528, 'steps': 54908, 'loss/train': 1.3964343070983887} 08/30/2021 23:06:20 - INFO - __main__ - Step 54910: {'lr': 0.00035822292914756954, 'samples': 10542720, 'steps': 54909, 'loss/train': 5.732332706451416} 08/30/2021 23:06:21 - INFO - __main__ - Step 54911: {'lr': 0.00035821814538010356, 'samples': 10542912, 'steps': 54910, 'loss/train': 1.5952101945877075} 08/30/2021 23:06:21 - INFO - __main__ - Step 54912: {'lr': 0.00035821336156387614, 'samples': 10543104, 'steps': 54911, 'loss/train': 1.186787724494934} 08/30/2021 23:06:23 - INFO - __main__ - Step 54913: {'lr': 0.00035820857769888943, 'samples': 10543296, 'steps': 54912, 'loss/train': 1.4470399618148804} 08/30/2021 23:06:23 - INFO - __main__ - Step 54914: {'lr': 0.0003582037937851456, 'samples': 10543488, 'steps': 54913, 'loss/train': 1.3439602851867676} 08/30/2021 23:06:24 - INFO - __main__ - Step 54915: {'lr': 0.00035819900982264684, 'samples': 10543680, 'steps': 54914, 'loss/train': 0.03276611492037773} 08/30/2021 23:06:24 - INFO - __main__ - Step 54916: {'lr': 0.0003581942258113953, 'samples': 10543872, 'steps': 54915, 'loss/train': 0.13259555399417877} 08/30/2021 23:06:24 - INFO - __main__ - Step 54917: {'lr': 0.00035818944175139314, 'samples': 10544064, 'steps': 54916, 'loss/train': 1.2883217334747314} 08/30/2021 23:06:25 - INFO - __main__ - Step 54918: {'lr': 0.0003581846576426423, 'samples': 10544256, 'steps': 54917, 'loss/train': 2.121966600418091} 08/30/2021 23:06:26 - INFO - __main__ - Step 54919: {'lr': 0.0003581798734851453, 'samples': 10544448, 'steps': 54918, 'loss/train': 1.3454232215881348} 08/30/2021 23:06:27 - INFO - __main__ - Step 54920: {'lr': 0.00035817508927890406, 'samples': 10544640, 'steps': 54919, 'loss/train': 0.8300412893295288} 08/30/2021 23:06:27 - INFO - __main__ - Step 54921: {'lr': 0.00035817030502392083, 'samples': 10544832, 'steps': 54920, 'loss/train': 0.5394120812416077} 08/30/2021 23:06:27 - INFO - __main__ - Step 54922: {'lr': 0.0003581655207201977, 'samples': 10545024, 'steps': 54921, 'loss/train': 1.1002658605575562} 08/30/2021 23:06:28 - INFO - __main__ - Step 54923: {'lr': 0.00035816073636773686, 'samples': 10545216, 'steps': 54922, 'loss/train': 1.1501874923706055} 08/30/2021 23:06:29 - INFO - __main__ - Step 54924: {'lr': 0.0003581559519665405, 'samples': 10545408, 'steps': 54923, 'loss/train': 1.3494172096252441} 08/30/2021 23:06:30 - INFO - __main__ - Step 54925: {'lr': 0.0003581511675166107, 'samples': 10545600, 'steps': 54924, 'loss/train': 0.944462239742279} 08/30/2021 23:06:30 - INFO - __main__ - Step 54926: {'lr': 0.00035814638301794966, 'samples': 10545792, 'steps': 54925, 'loss/train': 1.0862692594528198} 08/30/2021 23:06:30 - INFO - __main__ - Step 54927: {'lr': 0.0003581415984705595, 'samples': 10545984, 'steps': 54926, 'loss/train': 1.0773601531982422} 08/30/2021 23:06:31 - INFO - __main__ - Step 54928: {'lr': 0.0003581368138744424, 'samples': 10546176, 'steps': 54927, 'loss/train': 1.6194422245025635} 08/30/2021 23:06:32 - INFO - __main__ - Step 54929: {'lr': 0.00035813202922960056, 'samples': 10546368, 'steps': 54928, 'loss/train': 1.0069372653961182} 08/30/2021 23:06:33 - INFO - __main__ - Step 54930: {'lr': 0.00035812724453603614, 'samples': 10546560, 'steps': 54929, 'loss/train': 1.9901037216186523} 08/30/2021 23:06:33 - INFO - __main__ - Step 54931: {'lr': 0.00035812245979375114, 'samples': 10546752, 'steps': 54930, 'loss/train': 1.2745238542556763} 08/30/2021 23:06:33 - INFO - __main__ - Step 54932: {'lr': 0.0003581176750027479, 'samples': 10546944, 'steps': 54931, 'loss/train': 1.440755009651184} 08/30/2021 23:06:34 - INFO - __main__ - Step 54933: {'lr': 0.00035811289016302847, 'samples': 10547136, 'steps': 54932, 'loss/train': 1.6475715637207031} 08/30/2021 23:06:35 - INFO - __main__ - Step 54934: {'lr': 0.000358108105274595, 'samples': 10547328, 'steps': 54933, 'loss/train': 1.3965115547180176} 08/30/2021 23:06:36 - INFO - __main__ - Step 54935: {'lr': 0.0003581033203374498, 'samples': 10547520, 'steps': 54934, 'loss/train': 1.4318008422851562} 08/30/2021 23:06:36 - INFO - __main__ - Step 54936: {'lr': 0.0003580985353515948, 'samples': 10547712, 'steps': 54935, 'loss/train': 0.05075906962156296} 08/30/2021 23:06:36 - INFO - __main__ - Step 54937: {'lr': 0.0003580937503170324, 'samples': 10547904, 'steps': 54936, 'loss/train': 1.081440806388855} 08/30/2021 23:06:37 - INFO - __main__ - Step 54938: {'lr': 0.00035808896523376456, 'samples': 10548096, 'steps': 54937, 'loss/train': 1.7787302732467651} 08/30/2021 23:06:37 - INFO - __main__ - Step 54939: {'lr': 0.00035808418010179345, 'samples': 10548288, 'steps': 54938, 'loss/train': 1.4462049007415771} 08/30/2021 23:06:39 - INFO - __main__ - Step 54940: {'lr': 0.0003580793949211213, 'samples': 10548480, 'steps': 54939, 'loss/train': 1.5302996635437012} 08/30/2021 23:06:39 - INFO - __main__ - Step 54941: {'lr': 0.00035807460969175027, 'samples': 10548672, 'steps': 54940, 'loss/train': 0.3005818724632263} 08/30/2021 23:06:39 - INFO - __main__ - Step 54942: {'lr': 0.0003580698244136825, 'samples': 10548864, 'steps': 54941, 'loss/train': 1.421354055404663} 08/30/2021 23:06:40 - INFO - __main__ - Step 54943: {'lr': 0.0003580650390869201, 'samples': 10549056, 'steps': 54942, 'loss/train': 1.8839118480682373} 08/30/2021 23:06:40 - INFO - __main__ - Step 54944: {'lr': 0.0003580602537114653, 'samples': 10549248, 'steps': 54943, 'loss/train': 1.4408870935440063} 08/30/2021 23:06:42 - INFO - __main__ - Step 54945: {'lr': 0.0003580554682873202, 'samples': 10549440, 'steps': 54944, 'loss/train': 0.9393563866615295} 08/30/2021 23:06:43 - INFO - __main__ - Step 54946: {'lr': 0.00035805068281448687, 'samples': 10549632, 'steps': 54945, 'loss/train': 1.4167850017547607} 08/30/2021 23:06:43 - INFO - __main__ - Step 54947: {'lr': 0.00035804589729296766, 'samples': 10549824, 'steps': 54946, 'loss/train': 1.6197949647903442} 08/30/2021 23:06:43 - INFO - __main__ - Step 54948: {'lr': 0.00035804111172276464, 'samples': 10550016, 'steps': 54947, 'loss/train': 1.4808942079544067} 08/30/2021 23:06:44 - INFO - __main__ - Step 54949: {'lr': 0.00035803632610388, 'samples': 10550208, 'steps': 54948, 'loss/train': 1.371775507926941} 08/30/2021 23:06:45 - INFO - __main__ - Step 54950: {'lr': 0.0003580315404363158, 'samples': 10550400, 'steps': 54949, 'loss/train': 1.5300039052963257} 08/30/2021 23:06:46 - INFO - __main__ - Step 54951: {'lr': 0.0003580267547200743, 'samples': 10550592, 'steps': 54950, 'loss/train': 1.7046653032302856} 08/30/2021 23:06:46 - INFO - __main__ - Step 54952: {'lr': 0.00035802196895515757, 'samples': 10550784, 'steps': 54951, 'loss/train': 2.027310371398926} 08/30/2021 23:06:46 - INFO - __main__ - Step 54953: {'lr': 0.00035801718314156785, 'samples': 10550976, 'steps': 54952, 'loss/train': 1.3124637603759766} 08/30/2021 23:06:47 - INFO - __main__ - Step 54954: {'lr': 0.00035801239727930716, 'samples': 10551168, 'steps': 54953, 'loss/train': 1.684937834739685} 08/30/2021 23:06:48 - INFO - __main__ - Step 54955: {'lr': 0.00035800761136837783, 'samples': 10551360, 'steps': 54954, 'loss/train': 1.320955753326416} 08/30/2021 23:06:49 - INFO - __main__ - Step 54956: {'lr': 0.0003580028254087819, 'samples': 10551552, 'steps': 54955, 'loss/train': 1.2315248250961304} 08/30/2021 23:06:49 - INFO - __main__ - Step 54957: {'lr': 0.00035799803940052163, 'samples': 10551744, 'steps': 54956, 'loss/train': 0.8882100582122803} 08/30/2021 23:06:50 - INFO - __main__ - Step 54958: {'lr': 0.00035799325334359906, 'samples': 10551936, 'steps': 54957, 'loss/train': 1.4985897541046143} 08/30/2021 23:06:50 - INFO - __main__ - Step 54959: {'lr': 0.00035798846723801635, 'samples': 10552128, 'steps': 54958, 'loss/train': 1.1715972423553467} 08/30/2021 23:06:51 - INFO - __main__ - Step 54960: {'lr': 0.0003579836810837758, 'samples': 10552320, 'steps': 54959, 'loss/train': 0.6490328311920166} 08/30/2021 23:06:52 - INFO - __main__ - Step 54961: {'lr': 0.0003579788948808794, 'samples': 10552512, 'steps': 54960, 'loss/train': 1.6627075672149658} 08/30/2021 23:06:52 - INFO - __main__ - Step 54962: {'lr': 0.0003579741086293294, 'samples': 10552704, 'steps': 54961, 'loss/train': 1.0530335903167725} 08/30/2021 23:06:52 - INFO - __main__ - Step 54963: {'lr': 0.00035796932232912793, 'samples': 10552896, 'steps': 54962, 'loss/train': 1.2151793241500854} 08/30/2021 23:06:53 - INFO - __main__ - Step 54964: {'lr': 0.00035796453598027725, 'samples': 10553088, 'steps': 54963, 'loss/train': 1.501438856124878} 08/30/2021 23:06:55 - INFO - __main__ - Step 54965: {'lr': 0.0003579597495827793, 'samples': 10553280, 'steps': 54964, 'loss/train': 1.1869953870773315} 08/30/2021 23:06:55 - INFO - __main__ - Step 54966: {'lr': 0.0003579549631366363, 'samples': 10553472, 'steps': 54965, 'loss/train': 1.5104602575302124} 08/30/2021 23:06:55 - INFO - __main__ - Step 54967: {'lr': 0.0003579501766418505, 'samples': 10553664, 'steps': 54966, 'loss/train': 0.08363619446754456} 08/30/2021 23:06:56 - INFO - __main__ - Step 54968: {'lr': 0.0003579453900984241, 'samples': 10553856, 'steps': 54967, 'loss/train': 1.1528701782226562} 08/30/2021 23:06:56 - INFO - __main__ - Step 54969: {'lr': 0.0003579406035063591, 'samples': 10554048, 'steps': 54968, 'loss/train': 1.2789623737335205} 08/30/2021 23:06:58 - INFO - __main__ - Step 54970: {'lr': 0.0003579358168656577, 'samples': 10554240, 'steps': 54969, 'loss/train': 1.9498343467712402} 08/30/2021 23:06:58 - INFO - __main__ - Step 54971: {'lr': 0.00035793103017632224, 'samples': 10554432, 'steps': 54970, 'loss/train': 0.9954383969306946} 08/30/2021 23:06:58 - INFO - __main__ - Step 54972: {'lr': 0.0003579262434383546, 'samples': 10554624, 'steps': 54971, 'loss/train': 1.353716254234314} 08/30/2021 23:06:59 - INFO - __main__ - Step 54973: {'lr': 0.0003579214566517571, 'samples': 10554816, 'steps': 54972, 'loss/train': 1.2005674839019775} 08/30/2021 23:06:59 - INFO - __main__ - Step 54974: {'lr': 0.00035791666981653184, 'samples': 10555008, 'steps': 54973, 'loss/train': 1.0817415714263916} 08/30/2021 23:06:59 - INFO - __main__ - Step 54975: {'lr': 0.00035791188293268094, 'samples': 10555200, 'steps': 54974, 'loss/train': 0.9809725284576416} 08/30/2021 23:07:01 - INFO - __main__ - Step 54976: {'lr': 0.00035790709600020667, 'samples': 10555392, 'steps': 54975, 'loss/train': 1.1118978261947632} 08/30/2021 23:07:02 - INFO - __main__ - Step 54977: {'lr': 0.00035790230901911114, 'samples': 10555584, 'steps': 54976, 'loss/train': 0.5985836386680603} 08/30/2021 23:07:02 - INFO - __main__ - Step 54978: {'lr': 0.00035789752198939646, 'samples': 10555776, 'steps': 54977, 'loss/train': 1.522956371307373} 08/30/2021 23:07:02 - INFO - __main__ - Step 54979: {'lr': 0.00035789273491106485, 'samples': 10555968, 'steps': 54978, 'loss/train': 1.1329950094223022} 08/30/2021 23:07:03 - INFO - __main__ - Step 54980: {'lr': 0.00035788794778411837, 'samples': 10556160, 'steps': 54979, 'loss/train': 1.0635946989059448} 08/30/2021 23:07:04 - INFO - __main__ - Step 54981: {'lr': 0.0003578831606085593, 'samples': 10556352, 'steps': 54980, 'loss/train': 1.4733490943908691} 08/30/2021 23:07:04 - INFO - __main__ - Step 54982: {'lr': 0.00035787837338438976, 'samples': 10556544, 'steps': 54981, 'loss/train': 1.2858651876449585} 08/30/2021 23:07:05 - INFO - __main__ - Step 54983: {'lr': 0.00035787358611161186, 'samples': 10556736, 'steps': 54982, 'loss/train': 1.5461442470550537} 08/30/2021 23:07:05 - INFO - __main__ - Step 54984: {'lr': 0.0003578687987902278, 'samples': 10556928, 'steps': 54983, 'loss/train': 1.275929570198059} 08/30/2021 23:07:06 - INFO - __main__ - Step 54985: {'lr': 0.00035786401142023975, 'samples': 10557120, 'steps': 54984, 'loss/train': 1.9827232360839844} 08/30/2021 23:07:07 - INFO - __main__ - Step 54986: {'lr': 0.00035785922400164983, 'samples': 10557312, 'steps': 54985, 'loss/train': 0.40761321783065796} 08/30/2021 23:07:07 - INFO - __main__ - Step 54987: {'lr': 0.00035785443653446017, 'samples': 10557504, 'steps': 54986, 'loss/train': 1.1394426822662354} 08/30/2021 23:07:08 - INFO - __main__ - Step 54988: {'lr': 0.000357849649018673, 'samples': 10557696, 'steps': 54987, 'loss/train': 1.377744197845459} 08/30/2021 23:07:08 - INFO - __main__ - Step 54989: {'lr': 0.0003578448614542904, 'samples': 10557888, 'steps': 54988, 'loss/train': 3.8520419597625732} 08/30/2021 23:07:09 - INFO - __main__ - Step 54990: {'lr': 0.0003578400738413146, 'samples': 10558080, 'steps': 54989, 'loss/train': 1.7007616758346558} 08/30/2021 23:07:09 - INFO - __main__ - Step 54991: {'lr': 0.00035783528617974774, 'samples': 10558272, 'steps': 54990, 'loss/train': 1.5789684057235718} 08/30/2021 23:07:10 - INFO - __main__ - Step 54992: {'lr': 0.000357830498469592, 'samples': 10558464, 'steps': 54991, 'loss/train': 1.027137279510498} 08/30/2021 23:07:11 - INFO - __main__ - Step 54993: {'lr': 0.0003578257107108494, 'samples': 10558656, 'steps': 54992, 'loss/train': 1.401201605796814} 08/30/2021 23:07:11 - INFO - __main__ - Step 54994: {'lr': 0.0003578209229035222, 'samples': 10558848, 'steps': 54993, 'loss/train': 0.49661901593208313} 08/30/2021 23:07:12 - INFO - __main__ - Step 54995: {'lr': 0.0003578161350476127, 'samples': 10559040, 'steps': 54994, 'loss/train': 1.6620147228240967} 08/30/2021 23:07:12 - INFO - __main__ - Step 54996: {'lr': 0.00035781134714312277, 'samples': 10559232, 'steps': 54995, 'loss/train': 1.3671543598175049} 08/30/2021 23:07:14 - INFO - __main__ - Step 54997: {'lr': 0.0003578065591900548, 'samples': 10559424, 'steps': 54996, 'loss/train': 1.5685914754867554} 08/30/2021 23:07:15 - INFO - __main__ - Step 54998: {'lr': 0.0003578017711884108, 'samples': 10559616, 'steps': 54997, 'loss/train': 1.2992208003997803} 08/30/2021 23:07:15 - INFO - __main__ - Step 54999: {'lr': 0.000357796983138193, 'samples': 10559808, 'steps': 54998, 'loss/train': 2.0973896980285645} 08/30/2021 23:07:15 - INFO - __main__ - Step 55000: {'lr': 0.0003577921950394035, 'samples': 10560000, 'steps': 54999, 'loss/train': 1.237603783607483} 08/30/2021 23:07:16 - INFO - __main__ - Step 55001: {'lr': 0.00035778740689204456, 'samples': 10560192, 'steps': 55000, 'loss/train': 1.12308669090271} 08/30/2021 23:07:18 - INFO - __main__ - Step 55002: {'lr': 0.0003577826186961183, 'samples': 10560384, 'steps': 55001, 'loss/train': 1.4274318218231201} 08/30/2021 23:07:18 - INFO - __main__ - Step 55003: {'lr': 0.0003577778304516268, 'samples': 10560576, 'steps': 55002, 'loss/train': 1.2917907238006592} 08/30/2021 23:07:18 - INFO - __main__ - Step 55004: {'lr': 0.0003577730421585723, 'samples': 10560768, 'steps': 55003, 'loss/train': 1.1044116020202637} 08/30/2021 23:07:19 - INFO - __main__ - Step 55005: {'lr': 0.00035776825381695693, 'samples': 10560960, 'steps': 55004, 'loss/train': 0.7519664764404297} 08/30/2021 23:07:19 - INFO - __main__ - Step 55006: {'lr': 0.0003577634654267828, 'samples': 10561152, 'steps': 55005, 'loss/train': 1.126876711845398} 08/30/2021 23:07:19 - INFO - __main__ - Step 55007: {'lr': 0.0003577586769880522, 'samples': 10561344, 'steps': 55006, 'loss/train': 0.052810702472925186} 08/30/2021 23:07:21 - INFO - __main__ - Step 55008: {'lr': 0.00035775388850076714, 'samples': 10561536, 'steps': 55007, 'loss/train': 0.6534317135810852} 08/30/2021 23:07:21 - INFO - __main__ - Step 55009: {'lr': 0.0003577490999649298, 'samples': 10561728, 'steps': 55008, 'loss/train': 1.0166409015655518} 08/30/2021 23:07:22 - INFO - __main__ - Step 55010: {'lr': 0.0003577443113805425, 'samples': 10561920, 'steps': 55009, 'loss/train': 1.301195740699768} 08/30/2021 23:07:22 - INFO - __main__ - Step 55011: {'lr': 0.00035773952274760723, 'samples': 10562112, 'steps': 55010, 'loss/train': 1.6746796369552612} 08/30/2021 23:07:22 - INFO - __main__ - Step 55012: {'lr': 0.00035773473406612615, 'samples': 10562304, 'steps': 55011, 'loss/train': 1.20713472366333} 08/30/2021 23:07:24 - INFO - __main__ - Step 55013: {'lr': 0.0003577299453361015, 'samples': 10562496, 'steps': 55012, 'loss/train': 0.48610928654670715} 08/30/2021 23:07:25 - INFO - __main__ - Step 55014: {'lr': 0.00035772515655753536, 'samples': 10562688, 'steps': 55013, 'loss/train': 0.7487718462944031} 08/30/2021 23:07:25 - INFO - __main__ - Step 55015: {'lr': 0.00035772036773042994, 'samples': 10562880, 'steps': 55014, 'loss/train': 1.2261285781860352} 08/30/2021 23:07:26 - INFO - __main__ - Step 55016: {'lr': 0.00035771557885478744, 'samples': 10563072, 'steps': 55015, 'loss/train': 0.030547644942998886} 08/30/2021 23:07:26 - INFO - __main__ - Step 55017: {'lr': 0.0003577107899306099, 'samples': 10563264, 'steps': 55016, 'loss/train': 0.028325550258159637} 08/30/2021 23:07:26 - INFO - __main__ - Step 55018: {'lr': 0.00035770600095789957, 'samples': 10563456, 'steps': 55017, 'loss/train': 1.2087516784667969} 08/30/2021 23:07:28 - INFO - __main__ - Step 55019: {'lr': 0.0003577012119366586, 'samples': 10563648, 'steps': 55018, 'loss/train': 1.76043701171875} 08/30/2021 23:07:29 - INFO - __main__ - Step 55020: {'lr': 0.00035769642286688903, 'samples': 10563840, 'steps': 55019, 'loss/train': 1.0970418453216553} 08/30/2021 23:07:29 - INFO - __main__ - Step 55021: {'lr': 0.00035769163374859325, 'samples': 10564032, 'steps': 55020, 'loss/train': 0.07455174624919891} 08/30/2021 23:07:29 - INFO - __main__ - Step 55022: {'lr': 0.0003576868445817732, 'samples': 10564224, 'steps': 55021, 'loss/train': 1.4707401990890503} 08/30/2021 23:07:30 - INFO - __main__ - Step 55023: {'lr': 0.0003576820553664311, 'samples': 10564416, 'steps': 55022, 'loss/train': 0.24428652226924896} 08/30/2021 23:07:31 - INFO - __main__ - Step 55024: {'lr': 0.0003576772661025691, 'samples': 10564608, 'steps': 55023, 'loss/train': 1.034194827079773} 08/30/2021 23:07:32 - INFO - __main__ - Step 55025: {'lr': 0.0003576724767901895, 'samples': 10564800, 'steps': 55024, 'loss/train': 1.277866005897522} 08/30/2021 23:07:32 - INFO - __main__ - Step 55026: {'lr': 0.00035766768742929436, 'samples': 10564992, 'steps': 55025, 'loss/train': 0.9819884896278381} 08/30/2021 23:07:32 - INFO - __main__ - Step 55027: {'lr': 0.00035766289801988574, 'samples': 10565184, 'steps': 55026, 'loss/train': 1.26042640209198} 08/30/2021 23:07:33 - INFO - __main__ - Step 55028: {'lr': 0.00035765810856196585, 'samples': 10565376, 'steps': 55027, 'loss/train': 1.7677744626998901} 08/30/2021 23:07:33 - INFO - __main__ - Step 55029: {'lr': 0.00035765331905553686, 'samples': 10565568, 'steps': 55028, 'loss/train': 1.4031389951705933} 08/30/2021 23:07:35 - INFO - __main__ - Step 55030: {'lr': 0.000357648529500601, 'samples': 10565760, 'steps': 55029, 'loss/train': 1.2488181591033936} 08/30/2021 23:07:35 - INFO - __main__ - Step 55031: {'lr': 0.00035764373989716035, 'samples': 10565952, 'steps': 55030, 'loss/train': 1.5468528270721436} 08/30/2021 23:07:35 - INFO - __main__ - Step 55032: {'lr': 0.0003576389502452172, 'samples': 10566144, 'steps': 55031, 'loss/train': 1.3943970203399658} 08/30/2021 23:07:36 - INFO - __main__ - Step 55033: {'lr': 0.0003576341605447735, 'samples': 10566336, 'steps': 55032, 'loss/train': 1.2777832746505737} 08/30/2021 23:07:36 - INFO - __main__ - Step 55034: {'lr': 0.0003576293707958315, 'samples': 10566528, 'steps': 55033, 'loss/train': 1.7076354026794434} 08/30/2021 23:07:38 - INFO - __main__ - Step 55035: {'lr': 0.0003576245809983934, 'samples': 10566720, 'steps': 55034, 'loss/train': 1.0923969745635986} 08/30/2021 23:07:38 - INFO - __main__ - Step 55036: {'lr': 0.0003576197911524613, 'samples': 10566912, 'steps': 55035, 'loss/train': 0.9455087780952454} 08/30/2021 23:07:38 - INFO - __main__ - Step 55037: {'lr': 0.0003576150012580374, 'samples': 10567104, 'steps': 55036, 'loss/train': 0.31596988439559937} 08/30/2021 23:07:39 - INFO - __main__ - Step 55038: {'lr': 0.00035761021131512383, 'samples': 10567296, 'steps': 55037, 'loss/train': 1.116105556488037} 08/30/2021 23:07:39 - INFO - __main__ - Step 55039: {'lr': 0.00035760542132372275, 'samples': 10567488, 'steps': 55038, 'loss/train': 1.5040106773376465} 08/30/2021 23:07:41 - INFO - __main__ - Step 55040: {'lr': 0.00035760063128383637, 'samples': 10567680, 'steps': 55039, 'loss/train': 1.1676915884017944} 08/30/2021 23:07:41 - INFO - __main__ - Step 55041: {'lr': 0.0003575958411954668, 'samples': 10567872, 'steps': 55040, 'loss/train': 1.7205227613449097} 08/30/2021 23:07:41 - INFO - __main__ - Step 55042: {'lr': 0.00035759105105861614, 'samples': 10568064, 'steps': 55041, 'loss/train': 0.3357863426208496} 08/30/2021 23:07:42 - INFO - __main__ - Step 55043: {'lr': 0.00035758626087328664, 'samples': 10568256, 'steps': 55042, 'loss/train': 1.2908999919891357} 08/30/2021 23:07:42 - INFO - __main__ - Step 55044: {'lr': 0.00035758147063948056, 'samples': 10568448, 'steps': 55043, 'loss/train': 1.5278897285461426} 08/30/2021 23:07:44 - INFO - __main__ - Step 55045: {'lr': 0.00035757668035719974, 'samples': 10568640, 'steps': 55044, 'loss/train': 1.9774776697158813} 08/30/2021 23:07:44 - INFO - __main__ - Step 55046: {'lr': 0.00035757189002644664, 'samples': 10568832, 'steps': 55045, 'loss/train': 1.4386043548583984} 08/30/2021 23:07:44 - INFO - __main__ - Step 55047: {'lr': 0.00035756709964722324, 'samples': 10569024, 'steps': 55046, 'loss/train': 0.4118565320968628} 08/30/2021 23:07:45 - INFO - __main__ - Step 55048: {'lr': 0.00035756230921953183, 'samples': 10569216, 'steps': 55047, 'loss/train': 1.394034504890442} 08/30/2021 23:07:45 - INFO - __main__ - Step 55049: {'lr': 0.0003575575187433744, 'samples': 10569408, 'steps': 55048, 'loss/train': 1.6256165504455566} 08/30/2021 23:07:47 - INFO - __main__ - Step 55050: {'lr': 0.0003575527282187533, 'samples': 10569600, 'steps': 55049, 'loss/train': 1.8410624265670776} 08/30/2021 23:07:47 - INFO - __main__ - Step 55051: {'lr': 0.00035754793764567063, 'samples': 10569792, 'steps': 55050, 'loss/train': 0.6237562894821167} 08/30/2021 23:07:48 - INFO - __main__ - Step 55052: {'lr': 0.0003575431470241285, 'samples': 10569984, 'steps': 55051, 'loss/train': 0.8426141142845154} 08/30/2021 23:07:48 - INFO - __main__ - Step 55053: {'lr': 0.000357538356354129, 'samples': 10570176, 'steps': 55052, 'loss/train': 1.5356061458587646} 08/30/2021 23:07:48 - INFO - __main__ - Step 55054: {'lr': 0.0003575335656356744, 'samples': 10570368, 'steps': 55053, 'loss/train': 1.3171186447143555} 08/30/2021 23:07:49 - INFO - __main__ - Step 55055: {'lr': 0.0003575287748687669, 'samples': 10570560, 'steps': 55054, 'loss/train': 1.7285407781600952} 08/30/2021 23:07:51 - INFO - __main__ - Step 55056: {'lr': 0.0003575239840534086, 'samples': 10570752, 'steps': 55055, 'loss/train': 1.579219102859497} 08/30/2021 23:07:51 - INFO - __main__ - Step 55057: {'lr': 0.00035751919318960157, 'samples': 10570944, 'steps': 55056, 'loss/train': 1.2343171834945679} 08/30/2021 23:07:51 - INFO - __main__ - Step 55058: {'lr': 0.0003575144022773481, 'samples': 10571136, 'steps': 55057, 'loss/train': 1.174000859260559} 08/30/2021 23:07:52 - INFO - __main__ - Step 55059: {'lr': 0.00035750961131665034, 'samples': 10571328, 'steps': 55058, 'loss/train': 0.9515050053596497} 08/30/2021 23:07:52 - INFO - __main__ - Step 55060: {'lr': 0.0003575048203075103, 'samples': 10571520, 'steps': 55059, 'loss/train': 1.121878981590271} 08/30/2021 23:07:53 - INFO - __main__ - Step 55061: {'lr': 0.0003575000292499303, 'samples': 10571712, 'steps': 55060, 'loss/train': 0.8917629718780518} 08/30/2021 23:07:54 - INFO - __main__ - Step 55062: {'lr': 0.0003574952381439125, 'samples': 10571904, 'steps': 55061, 'loss/train': 0.8872008323669434} 08/30/2021 23:07:54 - INFO - __main__ - Step 55063: {'lr': 0.0003574904469894589, 'samples': 10572096, 'steps': 55062, 'loss/train': 1.0737521648406982} 08/30/2021 23:07:55 - INFO - __main__ - Step 55064: {'lr': 0.00035748565578657185, 'samples': 10572288, 'steps': 55063, 'loss/train': 1.4406421184539795} 08/30/2021 23:07:55 - INFO - __main__ - Step 55065: {'lr': 0.0003574808645352534, 'samples': 10572480, 'steps': 55064, 'loss/train': 1.4197230339050293} 08/30/2021 23:07:57 - INFO - __main__ - Step 55066: {'lr': 0.00035747607323550573, 'samples': 10572672, 'steps': 55065, 'loss/train': 1.5644071102142334} 08/30/2021 23:07:57 - INFO - __main__ - Step 55067: {'lr': 0.000357471281887331, 'samples': 10572864, 'steps': 55066, 'loss/train': 0.8464855551719666} 08/30/2021 23:07:58 - INFO - __main__ - Step 55068: {'lr': 0.0003574664904907314, 'samples': 10573056, 'steps': 55067, 'loss/train': 1.206516981124878} 08/30/2021 23:07:58 - INFO - __main__ - Step 55069: {'lr': 0.00035746169904570896, 'samples': 10573248, 'steps': 55068, 'loss/train': 0.5651645660400391} 08/30/2021 23:07:58 - INFO - __main__ - Step 55070: {'lr': 0.000357456907552266, 'samples': 10573440, 'steps': 55069, 'loss/train': 1.661095380783081} 08/30/2021 23:08:00 - INFO - __main__ - Step 55071: {'lr': 0.00035745211601040464, 'samples': 10573632, 'steps': 55070, 'loss/train': 1.5638982057571411} 08/30/2021 23:08:00 - INFO - __main__ - Step 55072: {'lr': 0.000357447324420127, 'samples': 10573824, 'steps': 55071, 'loss/train': 0.7424582839012146} 08/30/2021 23:08:00 - INFO - __main__ - Step 55073: {'lr': 0.00035744253278143526, 'samples': 10574016, 'steps': 55072, 'loss/train': 0.4229337275028229} 08/30/2021 23:08:01 - INFO - __main__ - Step 55074: {'lr': 0.0003574377410943315, 'samples': 10574208, 'steps': 55073, 'loss/train': 1.8057987689971924} 08/30/2021 23:08:01 - INFO - __main__ - Step 55075: {'lr': 0.00035743294935881804, 'samples': 10574400, 'steps': 55074, 'loss/train': 2.08233904838562} 08/30/2021 23:08:02 - INFO - __main__ - Step 55076: {'lr': 0.0003574281575748969, 'samples': 10574592, 'steps': 55075, 'loss/train': 1.3846652507781982} 08/30/2021 23:08:03 - INFO - __main__ - Step 55077: {'lr': 0.0003574233657425703, 'samples': 10574784, 'steps': 55076, 'loss/train': 1.3039796352386475} 08/30/2021 23:08:04 - INFO - __main__ - Step 55078: {'lr': 0.0003574185738618404, 'samples': 10574976, 'steps': 55077, 'loss/train': 0.7944549322128296} 08/30/2021 23:08:04 - INFO - __main__ - Step 55079: {'lr': 0.00035741378193270934, 'samples': 10575168, 'steps': 55078, 'loss/train': 1.7391003370285034} 08/30/2021 23:08:04 - INFO - __main__ - Step 55080: {'lr': 0.00035740898995517933, 'samples': 10575360, 'steps': 55079, 'loss/train': 1.6497116088867188} 08/30/2021 23:08:06 - INFO - __main__ - Step 55081: {'lr': 0.00035740419792925244, 'samples': 10575552, 'steps': 55080, 'loss/train': 1.5516760349273682} 08/30/2021 23:08:06 - INFO - __main__ - Step 55082: {'lr': 0.0003573994058549309, 'samples': 10575744, 'steps': 55081, 'loss/train': 1.091497540473938} 08/30/2021 23:08:07 - INFO - __main__ - Step 55083: {'lr': 0.00035739461373221677, 'samples': 10575936, 'steps': 55082, 'loss/train': 1.3975498676300049} 08/30/2021 23:08:07 - INFO - __main__ - Step 55084: {'lr': 0.00035738982156111233, 'samples': 10576128, 'steps': 55083, 'loss/train': 1.4310529232025146} 08/30/2021 23:08:07 - INFO - __main__ - Step 55085: {'lr': 0.0003573850293416198, 'samples': 10576320, 'steps': 55084, 'loss/train': 1.4916080236434937} 08/30/2021 23:08:08 - INFO - __main__ - Step 55086: {'lr': 0.00035738023707374114, 'samples': 10576512, 'steps': 55085, 'loss/train': 1.1713804006576538} 08/30/2021 23:08:09 - INFO - __main__ - Step 55087: {'lr': 0.0003573754447574785, 'samples': 10576704, 'steps': 55086, 'loss/train': 1.2049801349639893} 08/30/2021 23:08:10 - INFO - __main__ - Step 55088: {'lr': 0.0003573706523928343, 'samples': 10576896, 'steps': 55087, 'loss/train': 2.430856466293335} 08/30/2021 23:08:10 - INFO - __main__ - Step 55089: {'lr': 0.00035736585997981046, 'samples': 10577088, 'steps': 55088, 'loss/train': 1.8722506761550903} 08/30/2021 23:08:11 - INFO - __main__ - Step 55090: {'lr': 0.00035736106751840926, 'samples': 10577280, 'steps': 55089, 'loss/train': 0.03832166641950607} 08/30/2021 23:08:11 - INFO - __main__ - Step 55091: {'lr': 0.00035735627500863275, 'samples': 10577472, 'steps': 55090, 'loss/train': 1.4132860898971558} 08/30/2021 23:08:12 - INFO - __main__ - Step 55092: {'lr': 0.00035735148245048326, 'samples': 10577664, 'steps': 55091, 'loss/train': 1.1814210414886475} 08/30/2021 23:08:13 - INFO - __main__ - Step 55093: {'lr': 0.0003573466898439628, 'samples': 10577856, 'steps': 55092, 'loss/train': 0.3999745845794678} 08/30/2021 23:08:13 - INFO - __main__ - Step 55094: {'lr': 0.00035734189718907364, 'samples': 10578048, 'steps': 55093, 'loss/train': 1.448533058166504} 08/30/2021 23:08:14 - INFO - __main__ - Step 55095: {'lr': 0.00035733710448581773, 'samples': 10578240, 'steps': 55094, 'loss/train': 0.6460314989089966} 08/30/2021 23:08:14 - INFO - __main__ - Step 55096: {'lr': 0.0003573323117341975, 'samples': 10578432, 'steps': 55095, 'loss/train': 1.314246416091919} 08/30/2021 23:08:16 - INFO - __main__ - Step 55097: {'lr': 0.00035732751893421494, 'samples': 10578624, 'steps': 55096, 'loss/train': 1.3325467109680176} 08/30/2021 23:08:16 - INFO - __main__ - Step 55098: {'lr': 0.0003573227260858723, 'samples': 10578816, 'steps': 55097, 'loss/train': 0.9245617985725403} 08/30/2021 23:08:16 - INFO - __main__ - Step 55099: {'lr': 0.00035731793318917167, 'samples': 10579008, 'steps': 55098, 'loss/train': 1.5939275026321411} 08/30/2021 23:08:17 - INFO - __main__ - Step 55100: {'lr': 0.0003573131402441152, 'samples': 10579200, 'steps': 55099, 'loss/train': 1.321107268333435} 08/30/2021 23:08:17 - INFO - __main__ - Step 55101: {'lr': 0.0003573083472507051, 'samples': 10579392, 'steps': 55100, 'loss/train': 1.3674732446670532} 08/30/2021 23:08:19 - INFO - __main__ - Step 55102: {'lr': 0.00035730355420894355, 'samples': 10579584, 'steps': 55101, 'loss/train': 0.9711707830429077} 08/30/2021 23:08:20 - INFO - __main__ - Step 55103: {'lr': 0.00035729876111883265, 'samples': 10579776, 'steps': 55102, 'loss/train': 1.4389941692352295} 08/30/2021 23:08:20 - INFO - __main__ - Step 55104: {'lr': 0.0003572939679803746, 'samples': 10579968, 'steps': 55103, 'loss/train': 5.5494465827941895} 08/30/2021 23:08:20 - INFO - __main__ - Step 55105: {'lr': 0.00035728917479357154, 'samples': 10580160, 'steps': 55104, 'loss/train': 1.235867977142334} 08/30/2021 23:08:21 - INFO - __main__ - Step 55106: {'lr': 0.00035728438155842556, 'samples': 10580352, 'steps': 55105, 'loss/train': 1.4290612936019897} 08/30/2021 23:08:21 - INFO - __main__ - Step 55107: {'lr': 0.000357279588274939, 'samples': 10580544, 'steps': 55106, 'loss/train': 1.3626823425292969} 08/30/2021 23:08:21 - INFO - __main__ - Step 55108: {'lr': 0.00035727479494311387, 'samples': 10580736, 'steps': 55107, 'loss/train': 0.023736894130706787} 08/30/2021 23:08:23 - INFO - __main__ - Step 55109: {'lr': 0.0003572700015629524, 'samples': 10580928, 'steps': 55108, 'loss/train': 0.3429291844367981} 08/30/2021 23:08:24 - INFO - __main__ - Step 55110: {'lr': 0.0003572652081344566, 'samples': 10581120, 'steps': 55109, 'loss/train': 1.2814936637878418} 08/30/2021 23:08:24 - INFO - __main__ - Step 55111: {'lr': 0.00035726041465762885, 'samples': 10581312, 'steps': 55110, 'loss/train': 1.0668532848358154} 08/30/2021 23:08:25 - INFO - __main__ - Step 55112: {'lr': 0.0003572556211324713, 'samples': 10581504, 'steps': 55111, 'loss/train': 1.3139017820358276} 08/30/2021 23:08:25 - INFO - __main__ - Step 55113: {'lr': 0.0003572508275589859, 'samples': 10581696, 'steps': 55112, 'loss/train': 0.03465397283434868} 08/30/2021 23:08:26 - INFO - __main__ - Step 55114: {'lr': 0.00035724603393717493, 'samples': 10581888, 'steps': 55113, 'loss/train': 0.9880599975585938} 08/30/2021 23:08:27 - INFO - __main__ - Step 55115: {'lr': 0.00035724124026704064, 'samples': 10582080, 'steps': 55114, 'loss/train': 0.9760531187057495} 08/30/2021 23:08:27 - INFO - __main__ - Step 55116: {'lr': 0.000357236446548585, 'samples': 10582272, 'steps': 55115, 'loss/train': 1.3435084819793701} 08/30/2021 23:08:28 - INFO - __main__ - Step 55117: {'lr': 0.0003572316527818103, 'samples': 10582464, 'steps': 55116, 'loss/train': 0.9737823009490967} 08/30/2021 23:08:28 - INFO - __main__ - Step 55118: {'lr': 0.00035722685896671876, 'samples': 10582656, 'steps': 55117, 'loss/train': 0.9305632710456848} 08/30/2021 23:08:30 - INFO - __main__ - Step 55119: {'lr': 0.00035722206510331237, 'samples': 10582848, 'steps': 55118, 'loss/train': 1.0313795804977417} 08/30/2021 23:08:30 - INFO - __main__ - Step 55120: {'lr': 0.0003572172711915934, 'samples': 10583040, 'steps': 55119, 'loss/train': 1.3543974161148071} 08/30/2021 23:08:31 - INFO - __main__ - Step 55121: {'lr': 0.0003572124772315639, 'samples': 10583232, 'steps': 55120, 'loss/train': 0.037722066044807434} 08/30/2021 23:08:31 - INFO - __main__ - Step 55122: {'lr': 0.0003572076832232262, 'samples': 10583424, 'steps': 55121, 'loss/train': 0.018370719626545906} 08/30/2021 23:08:31 - INFO - __main__ - Step 55123: {'lr': 0.0003572028891665823, 'samples': 10583616, 'steps': 55122, 'loss/train': 1.138566255569458} 08/30/2021 23:08:32 - INFO - __main__ - Step 55124: {'lr': 0.00035719809506163454, 'samples': 10583808, 'steps': 55123, 'loss/train': 1.4620976448059082} 08/30/2021 23:08:33 - INFO - __main__ - Step 55125: {'lr': 0.0003571933009083849, 'samples': 10584000, 'steps': 55124, 'loss/train': 1.9055577516555786} 08/30/2021 23:08:34 - INFO - __main__ - Step 55126: {'lr': 0.00035718850670683565, 'samples': 10584192, 'steps': 55125, 'loss/train': 0.9276150465011597} 08/30/2021 23:08:34 - INFO - __main__ - Step 55127: {'lr': 0.00035718371245698887, 'samples': 10584384, 'steps': 55126, 'loss/train': 1.2083185911178589} 08/30/2021 23:08:34 - INFO - __main__ - Step 55128: {'lr': 0.0003571789181588468, 'samples': 10584576, 'steps': 55127, 'loss/train': 1.5655773878097534} 08/30/2021 23:08:35 - INFO - __main__ - Step 55129: {'lr': 0.00035717412381241153, 'samples': 10584768, 'steps': 55128, 'loss/train': 1.1169935464859009} 08/30/2021 23:08:36 - INFO - __main__ - Step 55130: {'lr': 0.00035716932941768525, 'samples': 10584960, 'steps': 55129, 'loss/train': 1.4624617099761963} 08/30/2021 23:08:37 - INFO - __main__ - Step 55131: {'lr': 0.0003571645349746702, 'samples': 10585152, 'steps': 55130, 'loss/train': 0.9173088073730469} 08/30/2021 23:08:37 - INFO - __main__ - Step 55132: {'lr': 0.00035715974048336843, 'samples': 10585344, 'steps': 55131, 'loss/train': 0.3494126796722412} 08/30/2021 23:08:37 - INFO - __main__ - Step 55133: {'lr': 0.0003571549459437821, 'samples': 10585536, 'steps': 55132, 'loss/train': 2.1418423652648926} 08/30/2021 23:08:38 - INFO - __main__ - Step 55134: {'lr': 0.00035715015135591346, 'samples': 10585728, 'steps': 55133, 'loss/train': 0.3453420400619507} 08/30/2021 23:08:39 - INFO - __main__ - Step 55135: {'lr': 0.0003571453567197645, 'samples': 10585920, 'steps': 55134, 'loss/train': 0.8115973472595215} 08/30/2021 23:08:40 - INFO - __main__ - Step 55136: {'lr': 0.0003571405620353376, 'samples': 10586112, 'steps': 55135, 'loss/train': 0.6397712826728821} 08/30/2021 23:08:40 - INFO - __main__ - Step 55137: {'lr': 0.00035713576730263475, 'samples': 10586304, 'steps': 55136, 'loss/train': 1.467289924621582} 08/30/2021 23:08:40 - INFO - __main__ - Step 55138: {'lr': 0.0003571309725216582, 'samples': 10586496, 'steps': 55137, 'loss/train': 1.0287584066390991} 08/30/2021 23:08:41 - INFO - __main__ - Step 55139: {'lr': 0.0003571261776924102, 'samples': 10586688, 'steps': 55138, 'loss/train': 1.2748109102249146} 08/30/2021 23:08:42 - INFO - __main__ - Step 55140: {'lr': 0.00035712138281489264, 'samples': 10586880, 'steps': 55139, 'loss/train': 1.642458200454712} 08/30/2021 23:08:43 - INFO - __main__ - Step 55141: {'lr': 0.0003571165878891079, 'samples': 10587072, 'steps': 55140, 'loss/train': 1.6107332706451416} 08/30/2021 23:08:43 - INFO - __main__ - Step 55142: {'lr': 0.00035711179291505806, 'samples': 10587264, 'steps': 55141, 'loss/train': 1.0473591089248657} 08/30/2021 23:08:43 - INFO - __main__ - Step 55143: {'lr': 0.0003571069978927453, 'samples': 10587456, 'steps': 55142, 'loss/train': 1.4788432121276855} 08/30/2021 23:08:44 - INFO - __main__ - Step 55144: {'lr': 0.00035710220282217175, 'samples': 10587648, 'steps': 55143, 'loss/train': 0.8276771903038025} 08/30/2021 23:08:45 - INFO - __main__ - Step 55145: {'lr': 0.0003570974077033397, 'samples': 10587840, 'steps': 55144, 'loss/train': 1.0953863859176636} 08/30/2021 23:08:46 - INFO - __main__ - Step 55146: {'lr': 0.00035709261253625115, 'samples': 10588032, 'steps': 55145, 'loss/train': 1.3230887651443481} 08/30/2021 23:08:46 - INFO - __main__ - Step 55147: {'lr': 0.00035708781732090835, 'samples': 10588224, 'steps': 55146, 'loss/train': 1.5432312488555908} 08/30/2021 23:08:46 - INFO - __main__ - Step 55148: {'lr': 0.00035708302205731334, 'samples': 10588416, 'steps': 55147, 'loss/train': 0.7514558434486389} 08/30/2021 23:08:47 - INFO - __main__ - Step 55149: {'lr': 0.00035707822674546847, 'samples': 10588608, 'steps': 55148, 'loss/train': 1.9047784805297852} 08/30/2021 23:08:48 - INFO - __main__ - Step 55150: {'lr': 0.00035707343138537584, 'samples': 10588800, 'steps': 55149, 'loss/train': 0.6529859304428101} 08/30/2021 23:08:49 - INFO - __main__ - Step 55151: {'lr': 0.00035706863597703746, 'samples': 10588992, 'steps': 55150, 'loss/train': 1.2995728254318237} 08/30/2021 23:08:49 - INFO - __main__ - Step 55152: {'lr': 0.00035706384052045567, 'samples': 10589184, 'steps': 55151, 'loss/train': 1.429237723350525} 08/30/2021 23:08:49 - INFO - __main__ - Step 55153: {'lr': 0.0003570590450156325, 'samples': 10589376, 'steps': 55152, 'loss/train': 1.0988893508911133} 08/30/2021 23:08:50 - INFO - __main__ - Step 55154: {'lr': 0.00035705424946257027, 'samples': 10589568, 'steps': 55153, 'loss/train': 1.1754755973815918} 08/30/2021 23:08:51 - INFO - __main__ - Step 55155: {'lr': 0.000357049453861271, 'samples': 10589760, 'steps': 55154, 'loss/train': 1.3264036178588867} 08/30/2021 23:08:52 - INFO - __main__ - Step 55156: {'lr': 0.00035704465821173695, 'samples': 10589952, 'steps': 55155, 'loss/train': 1.3289949893951416} 08/30/2021 23:08:52 - INFO - __main__ - Step 55157: {'lr': 0.00035703986251397015, 'samples': 10590144, 'steps': 55156, 'loss/train': 0.5880630016326904} 08/30/2021 23:08:52 - INFO - __main__ - Step 55158: {'lr': 0.00035703506676797284, 'samples': 10590336, 'steps': 55157, 'loss/train': 1.032106637954712} 08/30/2021 23:08:53 - INFO - __main__ - Step 55159: {'lr': 0.00035703027097374717, 'samples': 10590528, 'steps': 55158, 'loss/train': 2.063770055770874} 08/30/2021 23:08:53 - INFO - __main__ - Step 55160: {'lr': 0.00035702547513129533, 'samples': 10590720, 'steps': 55159, 'loss/train': 1.5039185285568237} 08/30/2021 23:08:54 - INFO - __main__ - Step 55161: {'lr': 0.0003570206792406195, 'samples': 10590912, 'steps': 55160, 'loss/train': 0.9168261885643005} 08/30/2021 23:08:55 - INFO - __main__ - Step 55162: {'lr': 0.0003570158833017219, 'samples': 10591104, 'steps': 55161, 'loss/train': 1.7124944925308228} 08/30/2021 23:08:55 - INFO - __main__ - Step 55163: {'lr': 0.0003570110873146044, 'samples': 10591296, 'steps': 55162, 'loss/train': 1.1841684579849243} 08/30/2021 23:08:56 - INFO - __main__ - Step 55164: {'lr': 0.0003570062912792694, 'samples': 10591488, 'steps': 55163, 'loss/train': 1.186103105545044} 08/30/2021 23:08:56 - INFO - __main__ - Step 55165: {'lr': 0.0003570014951957191, 'samples': 10591680, 'steps': 55164, 'loss/train': 1.5367989540100098} 08/30/2021 23:08:58 - INFO - __main__ - Step 55166: {'lr': 0.00035699669906395554, 'samples': 10591872, 'steps': 55165, 'loss/train': 2.0744001865386963} 08/30/2021 23:08:58 - INFO - __main__ - Step 55167: {'lr': 0.00035699190288398093, 'samples': 10592064, 'steps': 55166, 'loss/train': 1.5010182857513428} 08/30/2021 23:08:59 - INFO - __main__ - Step 55168: {'lr': 0.0003569871066557974, 'samples': 10592256, 'steps': 55167, 'loss/train': 0.8028724789619446} 08/30/2021 23:08:59 - INFO - __main__ - Step 55169: {'lr': 0.0003569823103794071, 'samples': 10592448, 'steps': 55168, 'loss/train': 1.589728832244873} 08/30/2021 23:08:59 - INFO - __main__ - Step 55170: {'lr': 0.0003569775140548122, 'samples': 10592640, 'steps': 55169, 'loss/train': 2.010615587234497} 08/30/2021 23:09:01 - INFO - __main__ - Step 55171: {'lr': 0.00035697271768201494, 'samples': 10592832, 'steps': 55170, 'loss/train': 1.6273012161254883} 08/30/2021 23:09:02 - INFO - __main__ - Step 55172: {'lr': 0.0003569679212610175, 'samples': 10593024, 'steps': 55171, 'loss/train': 1.2307910919189453} 08/30/2021 23:09:02 - INFO - __main__ - Step 55173: {'lr': 0.00035696312479182186, 'samples': 10593216, 'steps': 55172, 'loss/train': 0.07663355022668839} 08/30/2021 23:09:02 - INFO - __main__ - Step 55174: {'lr': 0.0003569583282744303, 'samples': 10593408, 'steps': 55173, 'loss/train': 1.1500461101531982} 08/30/2021 23:09:03 - INFO - __main__ - Step 55175: {'lr': 0.00035695353170884494, 'samples': 10593600, 'steps': 55174, 'loss/train': 1.2212440967559814} 08/30/2021 23:09:04 - INFO - __main__ - Step 55176: {'lr': 0.000356948735095068, 'samples': 10593792, 'steps': 55175, 'loss/train': 0.7729575634002686} 08/30/2021 23:09:05 - INFO - __main__ - Step 55177: {'lr': 0.0003569439384331016, 'samples': 10593984, 'steps': 55176, 'loss/train': 0.9950864911079407} 08/30/2021 23:09:05 - INFO - __main__ - Step 55178: {'lr': 0.00035693914172294796, 'samples': 10594176, 'steps': 55177, 'loss/train': 1.153062343597412} 08/30/2021 23:09:05 - INFO - __main__ - Step 55179: {'lr': 0.0003569343449646092, 'samples': 10594368, 'steps': 55178, 'loss/train': 1.444591760635376} 08/30/2021 23:09:06 - INFO - __main__ - Step 55180: {'lr': 0.0003569295481580874, 'samples': 10594560, 'steps': 55179, 'loss/train': 1.8953707218170166} 08/30/2021 23:09:08 - INFO - __main__ - Step 55181: {'lr': 0.0003569247513033848, 'samples': 10594752, 'steps': 55180, 'loss/train': 1.341706395149231} 08/30/2021 23:09:08 - INFO - __main__ - Step 55182: {'lr': 0.00035691995440050364, 'samples': 10594944, 'steps': 55181, 'loss/train': 1.5464110374450684} 08/30/2021 23:09:08 - INFO - __main__ - Step 55183: {'lr': 0.0003569151574494459, 'samples': 10595136, 'steps': 55182, 'loss/train': 1.1986277103424072} 08/30/2021 23:09:09 - INFO - __main__ - Step 55184: {'lr': 0.00035691036045021384, 'samples': 10595328, 'steps': 55183, 'loss/train': 0.5342109799385071} 08/30/2021 23:09:09 - INFO - __main__ - Step 55185: {'lr': 0.0003569055634028097, 'samples': 10595520, 'steps': 55184, 'loss/train': 1.1683378219604492} 08/30/2021 23:09:09 - INFO - __main__ - Step 55186: {'lr': 0.00035690076630723555, 'samples': 10595712, 'steps': 55185, 'loss/train': 1.2338920831680298} 08/30/2021 23:09:11 - INFO - __main__ - Step 55187: {'lr': 0.0003568959691634935, 'samples': 10595904, 'steps': 55186, 'loss/train': 1.3028740882873535} 08/30/2021 23:09:11 - INFO - __main__ - Step 55188: {'lr': 0.0003568911719715858, 'samples': 10596096, 'steps': 55187, 'loss/train': 1.3566453456878662} 08/30/2021 23:09:12 - INFO - __main__ - Step 55189: {'lr': 0.00035688637473151464, 'samples': 10596288, 'steps': 55188, 'loss/train': 1.7473326921463013} 08/30/2021 23:09:12 - INFO - __main__ - Step 55190: {'lr': 0.0003568815774432821, 'samples': 10596480, 'steps': 55189, 'loss/train': 1.631582498550415} 08/30/2021 23:09:12 - INFO - __main__ - Step 55191: {'lr': 0.00035687678010689033, 'samples': 10596672, 'steps': 55190, 'loss/train': 1.0861504077911377} 08/30/2021 23:09:14 - INFO - __main__ - Step 55192: {'lr': 0.00035687198272234163, 'samples': 10596864, 'steps': 55191, 'loss/train': 1.4811815023422241} 08/30/2021 23:09:14 - INFO - __main__ - Step 55193: {'lr': 0.00035686718528963804, 'samples': 10597056, 'steps': 55192, 'loss/train': 1.5605378150939941} 08/30/2021 23:09:15 - INFO - __main__ - Step 55194: {'lr': 0.00035686238780878167, 'samples': 10597248, 'steps': 55193, 'loss/train': 1.0274966955184937} 08/30/2021 23:09:15 - INFO - __main__ - Step 55195: {'lr': 0.0003568575902797748, 'samples': 10597440, 'steps': 55194, 'loss/train': 1.2675894498825073} 08/30/2021 23:09:15 - INFO - __main__ - Step 55196: {'lr': 0.0003568527927026195, 'samples': 10597632, 'steps': 55195, 'loss/train': 1.0265432596206665} 08/30/2021 23:09:17 - INFO - __main__ - Step 55197: {'lr': 0.000356847995077318, 'samples': 10597824, 'steps': 55196, 'loss/train': 1.2248847484588623} 08/30/2021 23:09:18 - INFO - __main__ - Step 55198: {'lr': 0.0003568431974038725, 'samples': 10598016, 'steps': 55197, 'loss/train': 1.6994012594223022} 08/30/2021 23:09:18 - INFO - __main__ - Step 55199: {'lr': 0.0003568383996822851, 'samples': 10598208, 'steps': 55198, 'loss/train': 1.3403412103652954} 08/30/2021 23:09:18 - INFO - __main__ - Step 55200: {'lr': 0.0003568336019125579, 'samples': 10598400, 'steps': 55199, 'loss/train': 0.9988178014755249} 08/30/2021 23:09:19 - INFO - __main__ - Step 55201: {'lr': 0.0003568288040946931, 'samples': 10598592, 'steps': 55200, 'loss/train': 1.150381326675415} 08/30/2021 23:09:20 - INFO - __main__ - Step 55202: {'lr': 0.000356824006228693, 'samples': 10598784, 'steps': 55201, 'loss/train': 0.30949753522872925} 08/30/2021 23:09:21 - INFO - __main__ - Step 55203: {'lr': 0.0003568192083145596, 'samples': 10598976, 'steps': 55202, 'loss/train': 0.9256338477134705} 08/30/2021 23:09:21 - INFO - __main__ - Step 55204: {'lr': 0.0003568144103522951, 'samples': 10599168, 'steps': 55203, 'loss/train': 1.4142298698425293} 08/30/2021 23:09:22 - INFO - __main__ - Step 55205: {'lr': 0.00035680961234190166, 'samples': 10599360, 'steps': 55204, 'loss/train': 0.08180546015501022} 08/30/2021 23:09:22 - INFO - __main__ - Step 55206: {'lr': 0.00035680481428338156, 'samples': 10599552, 'steps': 55205, 'loss/train': 1.1518126726150513} 08/30/2021 23:09:24 - INFO - __main__ - Step 55207: {'lr': 0.0003568000161767368, 'samples': 10599744, 'steps': 55206, 'loss/train': 1.2232271432876587} 08/30/2021 23:09:24 - INFO - __main__ - Step 55208: {'lr': 0.0003567952180219696, 'samples': 10599936, 'steps': 55207, 'loss/train': 1.1638550758361816} 08/30/2021 23:09:24 - INFO - __main__ - Step 55209: {'lr': 0.00035679041981908206, 'samples': 10600128, 'steps': 55208, 'loss/train': 1.3882882595062256} 08/30/2021 23:09:25 - INFO - __main__ - Step 55210: {'lr': 0.0003567856215680765, 'samples': 10600320, 'steps': 55209, 'loss/train': 0.9962772727012634} 08/30/2021 23:09:25 - INFO - __main__ - Step 55211: {'lr': 0.0003567808232689549, 'samples': 10600512, 'steps': 55210, 'loss/train': 1.2523547410964966} 08/30/2021 23:09:27 - INFO - __main__ - Step 55212: {'lr': 0.00035677602492171953, 'samples': 10600704, 'steps': 55211, 'loss/train': 1.8029344081878662} 08/30/2021 23:09:27 - INFO - __main__ - Step 55213: {'lr': 0.0003567712265263726, 'samples': 10600896, 'steps': 55212, 'loss/train': 1.1729871034622192} 08/30/2021 23:09:27 - INFO - __main__ - Step 55214: {'lr': 0.0003567664280829161, 'samples': 10601088, 'steps': 55213, 'loss/train': 1.4841314554214478} 08/30/2021 23:09:28 - INFO - __main__ - Step 55215: {'lr': 0.0003567616295913524, 'samples': 10601280, 'steps': 55214, 'loss/train': 1.266242265701294} 08/30/2021 23:09:28 - INFO - __main__ - Step 55216: {'lr': 0.0003567568310516834, 'samples': 10601472, 'steps': 55215, 'loss/train': 0.7293866276741028} 08/30/2021 23:09:28 - INFO - __main__ - Step 55217: {'lr': 0.0003567520324639116, 'samples': 10601664, 'steps': 55216, 'loss/train': 0.7984895706176758} 08/30/2021 23:09:30 - INFO - __main__ - Step 55218: {'lr': 0.0003567472338280389, 'samples': 10601856, 'steps': 55217, 'loss/train': 1.240403413772583} 08/30/2021 23:09:31 - INFO - __main__ - Step 55219: {'lr': 0.00035674243514406754, 'samples': 10602048, 'steps': 55218, 'loss/train': 0.9931859970092773} 08/30/2021 23:09:31 - INFO - __main__ - Step 55220: {'lr': 0.00035673763641199974, 'samples': 10602240, 'steps': 55219, 'loss/train': 1.7366400957107544} 08/30/2021 23:09:32 - INFO - __main__ - Step 55221: {'lr': 0.0003567328376318375, 'samples': 10602432, 'steps': 55220, 'loss/train': 1.8007313013076782} 08/30/2021 23:09:32 - INFO - __main__ - Step 55222: {'lr': 0.0003567280388035832, 'samples': 10602624, 'steps': 55221, 'loss/train': 1.0405681133270264} 08/30/2021 23:09:34 - INFO - __main__ - Step 55223: {'lr': 0.0003567232399272388, 'samples': 10602816, 'steps': 55222, 'loss/train': 1.0924535989761353} 08/30/2021 23:09:34 - INFO - __main__ - Step 55224: {'lr': 0.0003567184410028066, 'samples': 10603008, 'steps': 55223, 'loss/train': 0.13639983534812927} 08/30/2021 23:09:35 - INFO - __main__ - Step 55225: {'lr': 0.0003567136420302887, 'samples': 10603200, 'steps': 55224, 'loss/train': 1.3539752960205078} 08/30/2021 23:09:35 - INFO - __main__ - Step 55226: {'lr': 0.00035670884300968735, 'samples': 10603392, 'steps': 55225, 'loss/train': 1.052544355392456} 08/30/2021 23:09:35 - INFO - __main__ - Step 55227: {'lr': 0.0003567040439410046, 'samples': 10603584, 'steps': 55226, 'loss/train': 1.6347931623458862} 08/30/2021 23:09:37 - INFO - __main__ - Step 55228: {'lr': 0.0003566992448242427, 'samples': 10603776, 'steps': 55227, 'loss/train': 1.0890344381332397} 08/30/2021 23:09:37 - INFO - __main__ - Step 55229: {'lr': 0.0003566944456594036, 'samples': 10603968, 'steps': 55228, 'loss/train': 1.7391352653503418} 08/30/2021 23:09:38 - INFO - __main__ - Step 55230: {'lr': 0.00035668964644648975, 'samples': 10604160, 'steps': 55229, 'loss/train': 0.8697241544723511} 08/30/2021 23:09:38 - INFO - __main__ - Step 55231: {'lr': 0.0003566848471855032, 'samples': 10604352, 'steps': 55230, 'loss/train': 0.6922517418861389} 08/30/2021 23:09:38 - INFO - __main__ - Step 55232: {'lr': 0.0003566800478764461, 'samples': 10604544, 'steps': 55231, 'loss/train': 0.861565351486206} 08/30/2021 23:09:40 - INFO - __main__ - Step 55233: {'lr': 0.00035667524851932066, 'samples': 10604736, 'steps': 55232, 'loss/train': 1.5160175561904907} 08/30/2021 23:09:40 - INFO - __main__ - Step 55234: {'lr': 0.0003566704491141289, 'samples': 10604928, 'steps': 55233, 'loss/train': 1.7381420135498047} 08/30/2021 23:09:41 - INFO - __main__ - Step 55235: {'lr': 0.0003566656496608731, 'samples': 10605120, 'steps': 55234, 'loss/train': 1.8258566856384277} 08/30/2021 23:09:41 - INFO - __main__ - Step 55236: {'lr': 0.0003566608501595554, 'samples': 10605312, 'steps': 55235, 'loss/train': 1.2742383480072021} 08/30/2021 23:09:41 - INFO - __main__ - Step 55237: {'lr': 0.000356656050610178, 'samples': 10605504, 'steps': 55236, 'loss/train': 1.397837519645691} 08/30/2021 23:09:43 - INFO - __main__ - Step 55238: {'lr': 0.000356651251012743, 'samples': 10605696, 'steps': 55237, 'loss/train': 1.0106456279754639} 08/30/2021 23:09:43 - INFO - __main__ - Step 55239: {'lr': 0.0003566464513672527, 'samples': 10605888, 'steps': 55238, 'loss/train': 1.1335854530334473} 08/30/2021 23:09:44 - INFO - __main__ - Step 55240: {'lr': 0.00035664165167370907, 'samples': 10606080, 'steps': 55239, 'loss/train': 1.4258606433868408} 08/30/2021 23:09:44 - INFO - __main__ - Step 55241: {'lr': 0.0003566368519321144, 'samples': 10606272, 'steps': 55240, 'loss/train': 1.9990119934082031} 08/30/2021 23:09:44 - INFO - __main__ - Step 55242: {'lr': 0.0003566320521424707, 'samples': 10606464, 'steps': 55241, 'loss/train': 1.1276401281356812} 08/30/2021 23:09:46 - INFO - __main__ - Step 55243: {'lr': 0.0003566272523047803, 'samples': 10606656, 'steps': 55242, 'loss/train': 1.390738606452942} 08/30/2021 23:09:46 - INFO - __main__ - Step 55244: {'lr': 0.00035662245241904533, 'samples': 10606848, 'steps': 55243, 'loss/train': 1.3159795999526978} 08/30/2021 23:09:47 - INFO - __main__ - Step 55245: {'lr': 0.0003566176524852679, 'samples': 10607040, 'steps': 55244, 'loss/train': 0.6738126873970032} 08/30/2021 23:09:47 - INFO - __main__ - Step 55246: {'lr': 0.00035661285250345023, 'samples': 10607232, 'steps': 55245, 'loss/train': 0.24185334146022797} 08/30/2021 23:09:47 - INFO - __main__ - Step 55247: {'lr': 0.00035660805247359444, 'samples': 10607424, 'steps': 55246, 'loss/train': 1.2494441270828247} 08/30/2021 23:09:49 - INFO - __main__ - Step 55248: {'lr': 0.0003566032523957027, 'samples': 10607616, 'steps': 55247, 'loss/train': 1.6309080123901367} 08/30/2021 23:09:49 - INFO - __main__ - Step 55249: {'lr': 0.00035659845226977715, 'samples': 10607808, 'steps': 55248, 'loss/train': 1.243443489074707} 08/30/2021 23:09:50 - INFO - __main__ - Step 55250: {'lr': 0.00035659365209582004, 'samples': 10608000, 'steps': 55249, 'loss/train': 1.7340915203094482} 08/30/2021 23:09:50 - INFO - __main__ - Step 55251: {'lr': 0.00035658885187383343, 'samples': 10608192, 'steps': 55250, 'loss/train': 0.9365938305854797} 08/30/2021 23:09:50 - INFO - __main__ - Step 55252: {'lr': 0.0003565840516038196, 'samples': 10608384, 'steps': 55251, 'loss/train': 1.5120447874069214} 08/30/2021 23:09:52 - INFO - __main__ - Step 55253: {'lr': 0.00035657925128578064, 'samples': 10608576, 'steps': 55252, 'loss/train': 1.5985994338989258} 08/30/2021 23:09:52 - INFO - __main__ - Step 55254: {'lr': 0.00035657445091971863, 'samples': 10608768, 'steps': 55253, 'loss/train': 1.6367053985595703} 08/30/2021 23:09:53 - INFO - __main__ - Step 55255: {'lr': 0.00035656965050563584, 'samples': 10608960, 'steps': 55254, 'loss/train': 0.8891958594322205} 08/30/2021 23:09:53 - INFO - __main__ - Step 55256: {'lr': 0.0003565648500435344, 'samples': 10609152, 'steps': 55255, 'loss/train': 1.3963193893432617} 08/30/2021 23:09:53 - INFO - __main__ - Step 55257: {'lr': 0.0003565600495334165, 'samples': 10609344, 'steps': 55256, 'loss/train': 0.7875350713729858} 08/30/2021 23:09:54 - INFO - __main__ - Step 55258: {'lr': 0.0003565552489752843, 'samples': 10609536, 'steps': 55257, 'loss/train': 1.0236879587173462} 08/30/2021 23:09:55 - INFO - __main__ - Step 55259: {'lr': 0.0003565504483691399, 'samples': 10609728, 'steps': 55258, 'loss/train': 1.2806881666183472} 08/30/2021 23:09:56 - INFO - __main__ - Step 55260: {'lr': 0.0003565456477149856, 'samples': 10609920, 'steps': 55259, 'loss/train': 1.293763279914856} 08/30/2021 23:09:56 - INFO - __main__ - Step 55261: {'lr': 0.0003565408470128234, 'samples': 10610112, 'steps': 55260, 'loss/train': 1.6316332817077637} 08/30/2021 23:09:56 - INFO - __main__ - Step 55262: {'lr': 0.00035653604626265556, 'samples': 10610304, 'steps': 55261, 'loss/train': 1.100925087928772} 08/30/2021 23:09:57 - INFO - __main__ - Step 55263: {'lr': 0.00035653124546448423, 'samples': 10610496, 'steps': 55262, 'loss/train': 1.580403208732605} 08/30/2021 23:09:58 - INFO - __main__ - Step 55264: {'lr': 0.0003565264446183116, 'samples': 10610688, 'steps': 55263, 'loss/train': 1.4981789588928223} 08/30/2021 23:09:58 - INFO - __main__ - Step 55265: {'lr': 0.00035652164372413975, 'samples': 10610880, 'steps': 55264, 'loss/train': 1.0928590297698975} 08/30/2021 23:09:59 - INFO - __main__ - Step 55266: {'lr': 0.0003565168427819709, 'samples': 10611072, 'steps': 55265, 'loss/train': 0.9962037801742554} 08/30/2021 23:09:59 - INFO - __main__ - Step 55267: {'lr': 0.00035651204179180723, 'samples': 10611264, 'steps': 55266, 'loss/train': 1.5822793245315552} 08/30/2021 23:10:00 - INFO - __main__ - Step 55268: {'lr': 0.00035650724075365084, 'samples': 10611456, 'steps': 55267, 'loss/train': 1.0196447372436523} 08/30/2021 23:10:02 - INFO - __main__ - Step 55269: {'lr': 0.000356502439667504, 'samples': 10611648, 'steps': 55268, 'loss/train': 1.847999930381775} 08/30/2021 23:10:02 - INFO - __main__ - Step 55270: {'lr': 0.0003564976385333687, 'samples': 10611840, 'steps': 55269, 'loss/train': 1.2942416667938232} 08/30/2021 23:10:02 - INFO - __main__ - Step 55271: {'lr': 0.00035649283735124723, 'samples': 10612032, 'steps': 55270, 'loss/train': 2.068279266357422} 08/30/2021 23:10:03 - INFO - __main__ - Step 55272: {'lr': 0.0003564880361211418, 'samples': 10612224, 'steps': 55271, 'loss/train': 1.2610375881195068} 08/30/2021 23:10:03 - INFO - __main__ - Step 55273: {'lr': 0.00035648323484305445, 'samples': 10612416, 'steps': 55272, 'loss/train': 1.0171916484832764} 08/30/2021 23:10:05 - INFO - __main__ - Step 55274: {'lr': 0.00035647843351698736, 'samples': 10612608, 'steps': 55273, 'loss/train': 0.059180378913879395} 08/30/2021 23:10:05 - INFO - __main__ - Step 55275: {'lr': 0.0003564736321429428, 'samples': 10612800, 'steps': 55274, 'loss/train': 0.7148613929748535} 08/30/2021 23:10:05 - INFO - __main__ - Step 55276: {'lr': 0.00035646883072092285, 'samples': 10612992, 'steps': 55275, 'loss/train': 1.365022897720337} 08/30/2021 23:10:06 - INFO - __main__ - Step 55277: {'lr': 0.00035646402925092966, 'samples': 10613184, 'steps': 55276, 'loss/train': 1.5075931549072266} 08/30/2021 23:10:06 - INFO - __main__ - Step 55278: {'lr': 0.00035645922773296546, 'samples': 10613376, 'steps': 55277, 'loss/train': 1.8225433826446533} 08/30/2021 23:10:07 - INFO - __main__ - Step 55279: {'lr': 0.0003564544261670324, 'samples': 10613568, 'steps': 55278, 'loss/train': 1.1647119522094727} 08/30/2021 23:10:08 - INFO - __main__ - Step 55280: {'lr': 0.0003564496245531326, 'samples': 10613760, 'steps': 55279, 'loss/train': 1.2166565656661987} 08/30/2021 23:10:08 - INFO - __main__ - Step 55281: {'lr': 0.0003564448228912682, 'samples': 10613952, 'steps': 55280, 'loss/train': 1.0484657287597656} 08/30/2021 23:10:09 - INFO - __main__ - Step 55282: {'lr': 0.0003564400211814414, 'samples': 10614144, 'steps': 55281, 'loss/train': 1.6991456747055054} 08/30/2021 23:10:09 - INFO - __main__ - Step 55283: {'lr': 0.0003564352194236544, 'samples': 10614336, 'steps': 55282, 'loss/train': 0.7457453012466431} 08/30/2021 23:10:11 - INFO - __main__ - Step 55284: {'lr': 0.00035643041761790936, 'samples': 10614528, 'steps': 55283, 'loss/train': 1.294876217842102} 08/30/2021 23:10:11 - INFO - __main__ - Step 55285: {'lr': 0.00035642561576420834, 'samples': 10614720, 'steps': 55284, 'loss/train': 0.3047093152999878} 08/30/2021 23:10:11 - INFO - __main__ - Step 55286: {'lr': 0.00035642081386255366, 'samples': 10614912, 'steps': 55285, 'loss/train': 1.044171690940857} 08/30/2021 23:10:12 - INFO - __main__ - Step 55287: {'lr': 0.0003564160119129473, 'samples': 10615104, 'steps': 55286, 'loss/train': 1.004141926765442} 08/30/2021 23:10:12 - INFO - __main__ - Step 55288: {'lr': 0.0003564112099153916, 'samples': 10615296, 'steps': 55287, 'loss/train': 1.2524629831314087} 08/30/2021 23:10:13 - INFO - __main__ - Step 55289: {'lr': 0.00035640640786988866, 'samples': 10615488, 'steps': 55288, 'loss/train': 0.9085763096809387} 08/30/2021 23:10:14 - INFO - __main__ - Step 55290: {'lr': 0.0003564016057764406, 'samples': 10615680, 'steps': 55289, 'loss/train': 1.1156152486801147} 08/30/2021 23:10:14 - INFO - __main__ - Step 55291: {'lr': 0.00035639680363504965, 'samples': 10615872, 'steps': 55290, 'loss/train': 1.3552489280700684} 08/30/2021 23:10:15 - INFO - __main__ - Step 55292: {'lr': 0.0003563920014457179, 'samples': 10616064, 'steps': 55291, 'loss/train': 0.042330436408519745} 08/30/2021 23:10:15 - INFO - __main__ - Step 55293: {'lr': 0.0003563871992084476, 'samples': 10616256, 'steps': 55292, 'loss/train': 1.5442012548446655} 08/30/2021 23:10:17 - INFO - __main__ - Step 55294: {'lr': 0.0003563823969232409, 'samples': 10616448, 'steps': 55293, 'loss/train': 1.1046733856201172} 08/30/2021 23:10:17 - INFO - __main__ - Step 55295: {'lr': 0.0003563775945900999, 'samples': 10616640, 'steps': 55294, 'loss/train': 1.1372112035751343} 08/30/2021 23:10:18 - INFO - __main__ - Step 55296: {'lr': 0.00035637279220902677, 'samples': 10616832, 'steps': 55295, 'loss/train': 1.1792093515396118} 08/30/2021 23:10:18 - INFO - __main__ - Step 55297: {'lr': 0.00035636798978002374, 'samples': 10617024, 'steps': 55296, 'loss/train': 1.0071793794631958} 08/30/2021 23:10:18 - INFO - __main__ - Step 55298: {'lr': 0.00035636318730309285, 'samples': 10617216, 'steps': 55297, 'loss/train': 1.6232167482376099} 08/30/2021 23:10:20 - INFO - __main__ - Step 55299: {'lr': 0.0003563583847782364, 'samples': 10617408, 'steps': 55298, 'loss/train': 1.3834015130996704} 08/30/2021 23:10:21 - INFO - __main__ - Step 55300: {'lr': 0.0003563535822054565, 'samples': 10617600, 'steps': 55299, 'loss/train': 0.7916845083236694} 08/30/2021 23:10:21 - INFO - __main__ - Step 55301: {'lr': 0.00035634877958475535, 'samples': 10617792, 'steps': 55300, 'loss/train': 1.506651520729065} 08/30/2021 23:10:21 - INFO - __main__ - Step 55302: {'lr': 0.0003563439769161351, 'samples': 10617984, 'steps': 55301, 'loss/train': 1.3220170736312866} 08/30/2021 23:10:22 - INFO - __main__ - Step 55303: {'lr': 0.00035633917419959784, 'samples': 10618176, 'steps': 55302, 'loss/train': 1.0774294137954712} 08/30/2021 23:10:22 - INFO - __main__ - Step 55304: {'lr': 0.0003563343714351458, 'samples': 10618368, 'steps': 55303, 'loss/train': 2.262615203857422} 08/30/2021 23:10:23 - INFO - __main__ - Step 55305: {'lr': 0.0003563295686227811, 'samples': 10618560, 'steps': 55304, 'loss/train': 1.303059697151184} 08/30/2021 23:10:24 - INFO - __main__ - Step 55306: {'lr': 0.000356324765762506, 'samples': 10618752, 'steps': 55305, 'loss/train': 0.9564140439033508} 08/30/2021 23:10:24 - INFO - __main__ - Step 55307: {'lr': 0.0003563199628543226, 'samples': 10618944, 'steps': 55306, 'loss/train': 1.0562925338745117} 08/30/2021 23:10:25 - INFO - __main__ - Step 55308: {'lr': 0.00035631515989823306, 'samples': 10619136, 'steps': 55307, 'loss/train': 1.583857774734497} 08/30/2021 23:10:25 - INFO - __main__ - Step 55309: {'lr': 0.0003563103568942395, 'samples': 10619328, 'steps': 55308, 'loss/train': 1.736372947692871} 08/30/2021 23:10:26 - INFO - __main__ - Step 55310: {'lr': 0.0003563055538423441, 'samples': 10619520, 'steps': 55309, 'loss/train': 0.5877330303192139} 08/30/2021 23:10:27 - INFO - __main__ - Step 55311: {'lr': 0.00035630075074254917, 'samples': 10619712, 'steps': 55310, 'loss/train': 1.0950294733047485} 08/30/2021 23:10:27 - INFO - __main__ - Step 55312: {'lr': 0.0003562959475948567, 'samples': 10619904, 'steps': 55311, 'loss/train': 0.3165510892868042} 08/30/2021 23:10:28 - INFO - __main__ - Step 55313: {'lr': 0.00035629114439926897, 'samples': 10620096, 'steps': 55312, 'loss/train': 1.2183908224105835} 08/30/2021 23:10:28 - INFO - __main__ - Step 55314: {'lr': 0.00035628634115578806, 'samples': 10620288, 'steps': 55313, 'loss/train': 1.3466416597366333} 08/30/2021 23:10:29 - INFO - __main__ - Step 55315: {'lr': 0.00035628153786441616, 'samples': 10620480, 'steps': 55314, 'loss/train': 1.0653544664382935} 08/30/2021 23:10:30 - INFO - __main__ - Step 55316: {'lr': 0.0003562767345251554, 'samples': 10620672, 'steps': 55315, 'loss/train': 0.7332490682601929} 08/30/2021 23:10:30 - INFO - __main__ - Step 55317: {'lr': 0.00035627193113800797, 'samples': 10620864, 'steps': 55316, 'loss/train': 0.8477377891540527} 08/30/2021 23:10:31 - INFO - __main__ - Step 55318: {'lr': 0.0003562671277029761, 'samples': 10621056, 'steps': 55317, 'loss/train': 1.7145271301269531} 08/30/2021 23:10:31 - INFO - __main__ - Step 55319: {'lr': 0.00035626232422006186, 'samples': 10621248, 'steps': 55318, 'loss/train': 1.4092390537261963} 08/30/2021 23:10:33 - INFO - __main__ - Step 55320: {'lr': 0.0003562575206892676, 'samples': 10621440, 'steps': 55319, 'loss/train': 1.437728762626648} 08/30/2021 23:10:34 - INFO - __main__ - Step 55321: {'lr': 0.0003562527171105952, 'samples': 10621632, 'steps': 55320, 'loss/train': 0.6264386177062988} 08/30/2021 23:10:34 - INFO - __main__ - Step 55322: {'lr': 0.000356247913484047, 'samples': 10621824, 'steps': 55321, 'loss/train': 1.5079323053359985} 08/30/2021 23:10:34 - INFO - __main__ - Step 55323: {'lr': 0.00035624310980962516, 'samples': 10622016, 'steps': 55322, 'loss/train': 1.302291989326477} 08/30/2021 23:10:35 - INFO - __main__ - Step 55324: {'lr': 0.0003562383060873318, 'samples': 10622208, 'steps': 55323, 'loss/train': 1.4527934789657593} 08/30/2021 23:10:35 - INFO - __main__ - Step 55325: {'lr': 0.000356233502317169, 'samples': 10622400, 'steps': 55324, 'loss/train': 1.5112656354904175} 08/30/2021 23:10:37 - INFO - __main__ - Step 55326: {'lr': 0.00035622869849913916, 'samples': 10622592, 'steps': 55325, 'loss/train': 0.46029818058013916} 08/30/2021 23:10:37 - INFO - __main__ - Step 55327: {'lr': 0.00035622389463324424, 'samples': 10622784, 'steps': 55326, 'loss/train': 0.0676017478108406} 08/30/2021 23:10:38 - INFO - __main__ - Step 55328: {'lr': 0.0003562190907194865, 'samples': 10622976, 'steps': 55327, 'loss/train': 0.026389867067337036} 08/30/2021 23:10:38 - INFO - __main__ - Step 55329: {'lr': 0.00035621428675786804, 'samples': 10623168, 'steps': 55328, 'loss/train': 1.9485284090042114} 08/30/2021 23:10:39 - INFO - __main__ - Step 55330: {'lr': 0.0003562094827483911, 'samples': 10623360, 'steps': 55329, 'loss/train': 1.7217789888381958} 08/30/2021 23:10:39 - INFO - __main__ - Step 55331: {'lr': 0.0003562046786910578, 'samples': 10623552, 'steps': 55330, 'loss/train': 1.1546274423599243} 08/30/2021 23:10:40 - INFO - __main__ - Step 55332: {'lr': 0.0003561998745858703, 'samples': 10623744, 'steps': 55331, 'loss/train': 0.8172891139984131} 08/30/2021 23:10:41 - INFO - __main__ - Step 55333: {'lr': 0.00035619507043283075, 'samples': 10623936, 'steps': 55332, 'loss/train': 0.809817373752594} 08/30/2021 23:10:41 - INFO - __main__ - Step 55334: {'lr': 0.0003561902662319414, 'samples': 10624128, 'steps': 55333, 'loss/train': 1.9766159057617188} 08/30/2021 23:10:42 - INFO - __main__ - Step 55335: {'lr': 0.00035618546198320426, 'samples': 10624320, 'steps': 55334, 'loss/train': 1.3971039056777954} 08/30/2021 23:10:42 - INFO - __main__ - Step 55336: {'lr': 0.0003561806576866217, 'samples': 10624512, 'steps': 55335, 'loss/train': 0.38044917583465576} 08/30/2021 23:10:44 - INFO - __main__ - Step 55337: {'lr': 0.0003561758533421957, 'samples': 10624704, 'steps': 55336, 'loss/train': 1.1008824110031128} 08/30/2021 23:10:44 - INFO - __main__ - Step 55338: {'lr': 0.00035617104894992854, 'samples': 10624896, 'steps': 55337, 'loss/train': 1.2946010828018188} 08/30/2021 23:10:45 - INFO - __main__ - Step 55339: {'lr': 0.00035616624450982227, 'samples': 10625088, 'steps': 55338, 'loss/train': 1.4345452785491943} 08/30/2021 23:10:45 - INFO - __main__ - Step 55340: {'lr': 0.0003561614400218792, 'samples': 10625280, 'steps': 55339, 'loss/train': 1.0193989276885986} 08/30/2021 23:10:45 - INFO - __main__ - Step 55341: {'lr': 0.00035615663548610145, 'samples': 10625472, 'steps': 55340, 'loss/train': 0.01815672777593136} 08/30/2021 23:10:46 - INFO - __main__ - Step 55342: {'lr': 0.0003561518309024911, 'samples': 10625664, 'steps': 55341, 'loss/train': 1.6040068864822388} 08/30/2021 23:10:46 - INFO - __main__ - Step 55343: {'lr': 0.0003561470262710504, 'samples': 10625856, 'steps': 55342, 'loss/train': 0.7478710412979126} 08/30/2021 23:10:48 - INFO - __main__ - Step 55344: {'lr': 0.00035614222159178143, 'samples': 10626048, 'steps': 55343, 'loss/train': 1.6130714416503906} 08/30/2021 23:10:48 - INFO - __main__ - Step 55345: {'lr': 0.00035613741686468646, 'samples': 10626240, 'steps': 55344, 'loss/train': 1.321609616279602} 08/30/2021 23:10:48 - INFO - __main__ - Step 55346: {'lr': 0.0003561326120897676, 'samples': 10626432, 'steps': 55345, 'loss/train': 0.9996790289878845} 08/30/2021 23:10:49 - INFO - __main__ - Step 55347: {'lr': 0.00035612780726702707, 'samples': 10626624, 'steps': 55346, 'loss/train': 1.4161497354507446} 08/30/2021 23:10:49 - INFO - __main__ - Step 55348: {'lr': 0.00035612300239646694, 'samples': 10626816, 'steps': 55347, 'loss/train': 1.2000510692596436} 08/30/2021 23:10:51 - INFO - __main__ - Step 55349: {'lr': 0.00035611819747808943, 'samples': 10627008, 'steps': 55348, 'loss/train': 1.8668888807296753} 08/30/2021 23:10:51 - INFO - __main__ - Step 55350: {'lr': 0.00035611339251189665, 'samples': 10627200, 'steps': 55349, 'loss/train': 1.280078411102295} 08/30/2021 23:10:52 - INFO - __main__ - Step 55351: {'lr': 0.0003561085874978909, 'samples': 10627392, 'steps': 55350, 'loss/train': 1.2095434665679932} 08/30/2021 23:10:52 - INFO - __main__ - Step 55352: {'lr': 0.00035610378243607424, 'samples': 10627584, 'steps': 55351, 'loss/train': 1.4801084995269775} 08/30/2021 23:10:52 - INFO - __main__ - Step 55353: {'lr': 0.0003560989773264488, 'samples': 10627776, 'steps': 55352, 'loss/train': 1.151530385017395} 08/30/2021 23:10:54 - INFO - __main__ - Step 55354: {'lr': 0.00035609417216901683, 'samples': 10627968, 'steps': 55353, 'loss/train': 0.8998567461967468} 08/30/2021 23:10:55 - INFO - __main__ - Step 55355: {'lr': 0.00035608936696378046, 'samples': 10628160, 'steps': 55354, 'loss/train': 1.4569636583328247} 08/30/2021 23:10:55 - INFO - __main__ - Step 55356: {'lr': 0.0003560845617107419, 'samples': 10628352, 'steps': 55355, 'loss/train': 0.854587197303772} 08/30/2021 23:10:56 - INFO - __main__ - Step 55357: {'lr': 0.0003560797564099032, 'samples': 10628544, 'steps': 55356, 'loss/train': 0.018760357052087784} 08/30/2021 23:10:56 - INFO - __main__ - Step 55358: {'lr': 0.00035607495106126664, 'samples': 10628736, 'steps': 55357, 'loss/train': 1.4873825311660767} 08/30/2021 23:10:56 - INFO - __main__ - Step 55359: {'lr': 0.0003560701456648343, 'samples': 10628928, 'steps': 55358, 'loss/train': 1.258956789970398} 08/30/2021 23:10:58 - INFO - __main__ - Step 55360: {'lr': 0.0003560653402206085, 'samples': 10629120, 'steps': 55359, 'loss/train': 1.7666727304458618} 08/30/2021 23:10:58 - INFO - __main__ - Step 55361: {'lr': 0.0003560605347285912, 'samples': 10629312, 'steps': 55360, 'loss/train': 1.3753219842910767} 08/30/2021 23:10:59 - INFO - __main__ - Step 55362: {'lr': 0.0003560557291887847, 'samples': 10629504, 'steps': 55361, 'loss/train': 1.6132206916809082} 08/30/2021 23:10:59 - INFO - __main__ - Step 55363: {'lr': 0.0003560509236011911, 'samples': 10629696, 'steps': 55362, 'loss/train': 1.3108277320861816} 08/30/2021 23:10:59 - INFO - __main__ - Step 55364: {'lr': 0.0003560461179658125, 'samples': 10629888, 'steps': 55363, 'loss/train': 1.2954736948013306} 08/30/2021 23:11:01 - INFO - __main__ - Step 55365: {'lr': 0.0003560413122826513, 'samples': 10630080, 'steps': 55364, 'loss/train': 1.3421114683151245} 08/30/2021 23:11:01 - INFO - __main__ - Step 55366: {'lr': 0.0003560365065517095, 'samples': 10630272, 'steps': 55365, 'loss/train': 0.8554668426513672} 08/30/2021 23:11:01 - INFO - __main__ - Step 55367: {'lr': 0.0003560317007729893, 'samples': 10630464, 'steps': 55366, 'loss/train': 0.07721702009439468} 08/30/2021 23:11:02 - INFO - __main__ - Step 55368: {'lr': 0.00035602689494649274, 'samples': 10630656, 'steps': 55367, 'loss/train': 1.06834876537323} 08/30/2021 23:11:02 - INFO - __main__ - Step 55369: {'lr': 0.0003560220890722222, 'samples': 10630848, 'steps': 55368, 'loss/train': 1.087509274482727} 08/30/2021 23:11:04 - INFO - __main__ - Step 55370: {'lr': 0.00035601728315017966, 'samples': 10631040, 'steps': 55369, 'loss/train': 1.802738070487976} 08/30/2021 23:11:04 - INFO - __main__ - Step 55371: {'lr': 0.00035601247718036744, 'samples': 10631232, 'steps': 55370, 'loss/train': 1.0252283811569214} 08/30/2021 23:11:04 - INFO - __main__ - Step 55372: {'lr': 0.00035600767116278765, 'samples': 10631424, 'steps': 55371, 'loss/train': 1.8033604621887207} 08/30/2021 23:11:05 - INFO - __main__ - Step 55373: {'lr': 0.0003560028650974424, 'samples': 10631616, 'steps': 55372, 'loss/train': 1.3439714908599854} 08/30/2021 23:11:05 - INFO - __main__ - Step 55374: {'lr': 0.0003559980589843339, 'samples': 10631808, 'steps': 55373, 'loss/train': 1.2238050699234009} 08/30/2021 23:11:07 - INFO - __main__ - Step 55375: {'lr': 0.0003559932528234643, 'samples': 10632000, 'steps': 55374, 'loss/train': 0.7990780472755432} 08/30/2021 23:11:07 - INFO - __main__ - Step 55376: {'lr': 0.0003559884466148358, 'samples': 10632192, 'steps': 55375, 'loss/train': 1.2638812065124512} 08/30/2021 23:11:07 - INFO - __main__ - Step 55377: {'lr': 0.0003559836403584505, 'samples': 10632384, 'steps': 55376, 'loss/train': 1.2138592004776} 08/30/2021 23:11:08 - INFO - __main__ - Step 55378: {'lr': 0.00035597883405431066, 'samples': 10632576, 'steps': 55377, 'loss/train': 1.200518012046814} 08/30/2021 23:11:08 - INFO - __main__ - Step 55379: {'lr': 0.0003559740277024183, 'samples': 10632768, 'steps': 55378, 'loss/train': 1.6666280031204224} 08/30/2021 23:11:10 - INFO - __main__ - Step 55380: {'lr': 0.0003559692213027758, 'samples': 10632960, 'steps': 55379, 'loss/train': 1.1910959482192993} 08/30/2021 23:11:11 - INFO - __main__ - Step 55381: {'lr': 0.00035596441485538513, 'samples': 10633152, 'steps': 55380, 'loss/train': 1.3170758485794067} 08/30/2021 23:11:11 - INFO - __main__ - Step 55382: {'lr': 0.00035595960836024856, 'samples': 10633344, 'steps': 55381, 'loss/train': 1.7013992071151733} 08/30/2021 23:11:11 - INFO - __main__ - Step 55383: {'lr': 0.00035595480181736816, 'samples': 10633536, 'steps': 55382, 'loss/train': 1.2633439302444458} 08/30/2021 23:11:12 - INFO - __main__ - Step 55384: {'lr': 0.0003559499952267462, 'samples': 10633728, 'steps': 55383, 'loss/train': 1.5431526899337769} 08/30/2021 23:11:12 - INFO - __main__ - Step 55385: {'lr': 0.00035594518858838485, 'samples': 10633920, 'steps': 55384, 'loss/train': 1.5441824197769165} 08/30/2021 23:11:14 - INFO - __main__ - Step 55386: {'lr': 0.0003559403819022862, 'samples': 10634112, 'steps': 55385, 'loss/train': 1.0448249578475952} 08/30/2021 23:11:14 - INFO - __main__ - Step 55387: {'lr': 0.0003559355751684525, 'samples': 10634304, 'steps': 55386, 'loss/train': 1.5194307565689087} 08/30/2021 23:11:15 - INFO - __main__ - Step 55388: {'lr': 0.00035593076838688576, 'samples': 10634496, 'steps': 55387, 'loss/train': 0.6773468852043152} 08/30/2021 23:11:15 - INFO - __main__ - Step 55389: {'lr': 0.0003559259615575883, 'samples': 10634688, 'steps': 55388, 'loss/train': 0.06502977013587952} 08/30/2021 23:11:15 - INFO - __main__ - Step 55390: {'lr': 0.00035592115468056223, 'samples': 10634880, 'steps': 55389, 'loss/train': 1.2024701833724976} 08/30/2021 23:11:17 - INFO - __main__ - Step 55391: {'lr': 0.0003559163477558098, 'samples': 10635072, 'steps': 55390, 'loss/train': 1.704396367073059} 08/30/2021 23:11:18 - INFO - __main__ - Step 55392: {'lr': 0.000355911540783333, 'samples': 10635264, 'steps': 55391, 'loss/train': 0.7037349939346313} 08/30/2021 23:11:18 - INFO - __main__ - Step 55393: {'lr': 0.0003559067337631341, 'samples': 10635456, 'steps': 55392, 'loss/train': 1.6579787731170654} 08/30/2021 23:11:18 - INFO - __main__ - Step 55394: {'lr': 0.0003559019266952153, 'samples': 10635648, 'steps': 55393, 'loss/train': 1.601279616355896} 08/30/2021 23:11:19 - INFO - __main__ - Step 55395: {'lr': 0.0003558971195795787, 'samples': 10635840, 'steps': 55394, 'loss/train': 1.461321234703064} 08/30/2021 23:11:21 - INFO - __main__ - Step 55396: {'lr': 0.00035589231241622653, 'samples': 10636032, 'steps': 55395, 'loss/train': 1.3567804098129272} 08/30/2021 23:11:21 - INFO - __main__ - Step 55397: {'lr': 0.0003558875052051609, 'samples': 10636224, 'steps': 55396, 'loss/train': 0.5615561008453369} 08/30/2021 23:11:22 - INFO - __main__ - Step 55398: {'lr': 0.000355882697946384, 'samples': 10636416, 'steps': 55397, 'loss/train': 1.4395231008529663} 08/30/2021 23:11:22 - INFO - __main__ - Step 55399: {'lr': 0.00035587789063989793, 'samples': 10636608, 'steps': 55398, 'loss/train': 1.357488751411438} 08/30/2021 23:11:22 - INFO - __main__ - Step 55400: {'lr': 0.0003558730832857049, 'samples': 10636800, 'steps': 55399, 'loss/train': 1.5035920143127441} 08/30/2021 23:11:23 - INFO - __main__ - Step 55401: {'lr': 0.00035586827588380724, 'samples': 10636992, 'steps': 55400, 'loss/train': 0.9984560608863831} 08/30/2021 23:11:24 - INFO - __main__ - Step 55402: {'lr': 0.00035586346843420694, 'samples': 10637184, 'steps': 55401, 'loss/train': 0.8850058913230896} 08/30/2021 23:11:25 - INFO - __main__ - Step 55403: {'lr': 0.0003558586609369061, 'samples': 10637376, 'steps': 55402, 'loss/train': 1.0557961463928223} 08/30/2021 23:11:25 - INFO - __main__ - Step 55404: {'lr': 0.000355853853391907, 'samples': 10637568, 'steps': 55403, 'loss/train': 1.8525205850601196} 08/30/2021 23:11:25 - INFO - __main__ - Step 55405: {'lr': 0.0003558490457992118, 'samples': 10637760, 'steps': 55404, 'loss/train': 1.0172795057296753} 08/30/2021 23:11:26 - INFO - __main__ - Step 55406: {'lr': 0.00035584423815882265, 'samples': 10637952, 'steps': 55405, 'loss/train': 0.7502500414848328} 08/30/2021 23:11:27 - INFO - __main__ - Step 55407: {'lr': 0.00035583943047074173, 'samples': 10638144, 'steps': 55406, 'loss/train': 0.35627129673957825} 08/30/2021 23:11:28 - INFO - __main__ - Step 55408: {'lr': 0.00035583462273497125, 'samples': 10638336, 'steps': 55407, 'loss/train': 1.2644280195236206} 08/30/2021 23:11:28 - INFO - __main__ - Step 55409: {'lr': 0.0003558298149515132, 'samples': 10638528, 'steps': 55408, 'loss/train': 1.445717453956604} 08/30/2021 23:11:28 - INFO - __main__ - Step 55410: {'lr': 0.00035582500712037, 'samples': 10638720, 'steps': 55409, 'loss/train': 1.1638656854629517} 08/30/2021 23:11:29 - INFO - __main__ - Step 55411: {'lr': 0.0003558201992415436, 'samples': 10638912, 'steps': 55410, 'loss/train': 1.0031850337982178} 08/30/2021 23:11:30 - INFO - __main__ - Step 55412: {'lr': 0.00035581539131503625, 'samples': 10639104, 'steps': 55411, 'loss/train': 1.0247963666915894} 08/30/2021 23:11:31 - INFO - __main__ - Step 55413: {'lr': 0.00035581058334085015, 'samples': 10639296, 'steps': 55412, 'loss/train': 1.5131694078445435} 08/30/2021 23:11:31 - INFO - __main__ - Step 55414: {'lr': 0.00035580577531898745, 'samples': 10639488, 'steps': 55413, 'loss/train': 1.1767997741699219} 08/30/2021 23:11:31 - INFO - __main__ - Step 55415: {'lr': 0.00035580096724945027, 'samples': 10639680, 'steps': 55414, 'loss/train': 2.3571736812591553} 08/30/2021 23:11:32 - INFO - __main__ - Step 55416: {'lr': 0.00035579615913224077, 'samples': 10639872, 'steps': 55415, 'loss/train': 1.2972009181976318} 08/30/2021 23:11:33 - INFO - __main__ - Step 55417: {'lr': 0.0003557913509673612, 'samples': 10640064, 'steps': 55416, 'loss/train': 1.812063455581665} 08/30/2021 23:11:34 - INFO - __main__ - Step 55418: {'lr': 0.0003557865427548137, 'samples': 10640256, 'steps': 55417, 'loss/train': 1.5160012245178223} 08/30/2021 23:11:34 - INFO - __main__ - Step 55419: {'lr': 0.0003557817344946004, 'samples': 10640448, 'steps': 55418, 'loss/train': 1.3852494955062866} 08/30/2021 23:11:35 - INFO - __main__ - Step 55420: {'lr': 0.0003557769261867235, 'samples': 10640640, 'steps': 55419, 'loss/train': 1.396045207977295} 08/30/2021 23:11:35 - INFO - __main__ - Step 55421: {'lr': 0.0003557721178311851, 'samples': 10640832, 'steps': 55420, 'loss/train': 1.4583454132080078} 08/30/2021 23:11:36 - INFO - __main__ - Step 55422: {'lr': 0.0003557673094279874, 'samples': 10641024, 'steps': 55421, 'loss/train': 1.254266381263733} 08/30/2021 23:11:37 - INFO - __main__ - Step 55423: {'lr': 0.00035576250097713263, 'samples': 10641216, 'steps': 55422, 'loss/train': 1.3631420135498047} 08/30/2021 23:11:37 - INFO - __main__ - Step 55424: {'lr': 0.00035575769247862295, 'samples': 10641408, 'steps': 55423, 'loss/train': 0.8063216209411621} 08/30/2021 23:11:38 - INFO - __main__ - Step 55425: {'lr': 0.0003557528839324604, 'samples': 10641600, 'steps': 55424, 'loss/train': 1.1090645790100098} 08/30/2021 23:11:38 - INFO - __main__ - Step 55426: {'lr': 0.0003557480753386473, 'samples': 10641792, 'steps': 55425, 'loss/train': 1.2671951055526733} 08/30/2021 23:11:39 - INFO - __main__ - Step 55427: {'lr': 0.0003557432666971857, 'samples': 10641984, 'steps': 55426, 'loss/train': 0.8759759068489075} 08/30/2021 23:11:40 - INFO - __main__ - Step 55428: {'lr': 0.0003557384580080778, 'samples': 10642176, 'steps': 55427, 'loss/train': 0.041155535727739334} 08/30/2021 23:11:40 - INFO - __main__ - Step 55429: {'lr': 0.0003557336492713258, 'samples': 10642368, 'steps': 55428, 'loss/train': 1.3602029085159302} 08/30/2021 23:11:40 - INFO - __main__ - Step 55430: {'lr': 0.00035572884048693193, 'samples': 10642560, 'steps': 55429, 'loss/train': 1.2522928714752197} 08/30/2021 23:11:41 - INFO - __main__ - Step 55431: {'lr': 0.0003557240316548982, 'samples': 10642752, 'steps': 55430, 'loss/train': 1.0957622528076172} 08/30/2021 23:11:43 - INFO - __main__ - Step 55432: {'lr': 0.0003557192227752268, 'samples': 10642944, 'steps': 55431, 'loss/train': 0.9033432006835938} 08/30/2021 23:11:44 - INFO - __main__ - Step 55433: {'lr': 0.00035571441384792005, 'samples': 10643136, 'steps': 55432, 'loss/train': 1.8867671489715576} 08/30/2021 23:11:44 - INFO - __main__ - Step 55434: {'lr': 0.00035570960487298, 'samples': 10643328, 'steps': 55433, 'loss/train': 1.381144642829895} 08/30/2021 23:11:44 - INFO - __main__ - Step 55435: {'lr': 0.00035570479585040883, 'samples': 10643520, 'steps': 55434, 'loss/train': 0.932345986366272} 08/30/2021 23:11:45 - INFO - __main__ - Step 55436: {'lr': 0.00035569998678020866, 'samples': 10643712, 'steps': 55435, 'loss/train': 1.2663263082504272} 08/30/2021 23:11:45 - INFO - __main__ - Step 55437: {'lr': 0.0003556951776623817, 'samples': 10643904, 'steps': 55436, 'loss/train': 1.147674798965454} 08/30/2021 23:11:46 - INFO - __main__ - Step 55438: {'lr': 0.0003556903684969302, 'samples': 10644096, 'steps': 55437, 'loss/train': 0.4004209041595459} 08/30/2021 23:11:46 - INFO - __main__ - Step 55439: {'lr': 0.0003556855592838562, 'samples': 10644288, 'steps': 55438, 'loss/train': 0.02406122162938118} 08/30/2021 23:11:47 - INFO - __main__ - Step 55440: {'lr': 0.00035568075002316194, 'samples': 10644480, 'steps': 55439, 'loss/train': 1.3831521272659302} 08/30/2021 23:11:48 - INFO - __main__ - Step 55441: {'lr': 0.0003556759407148496, 'samples': 10644672, 'steps': 55440, 'loss/train': 1.5924197435379028} 08/30/2021 23:11:48 - INFO - __main__ - Step 55442: {'lr': 0.00035567113135892125, 'samples': 10644864, 'steps': 55441, 'loss/train': 1.2679743766784668} 08/30/2021 23:11:49 - INFO - __main__ - Step 55443: {'lr': 0.0003556663219553791, 'samples': 10645056, 'steps': 55442, 'loss/train': 1.531531572341919} 08/30/2021 23:11:49 - INFO - __main__ - Step 55444: {'lr': 0.00035566151250422543, 'samples': 10645248, 'steps': 55443, 'loss/train': 1.22312593460083} 08/30/2021 23:11:51 - INFO - __main__ - Step 55445: {'lr': 0.0003556567030054622, 'samples': 10645440, 'steps': 55444, 'loss/train': 1.1894237995147705} 08/30/2021 23:11:51 - INFO - __main__ - Step 55446: {'lr': 0.00035565189345909177, 'samples': 10645632, 'steps': 55445, 'loss/train': 1.5968416929244995} 08/30/2021 23:11:51 - INFO - __main__ - Step 55447: {'lr': 0.0003556470838651162, 'samples': 10645824, 'steps': 55446, 'loss/train': 1.0069166421890259} 08/30/2021 23:11:52 - INFO - __main__ - Step 55448: {'lr': 0.0003556422742235377, 'samples': 10646016, 'steps': 55447, 'loss/train': 1.3170974254608154} 08/30/2021 23:11:52 - INFO - __main__ - Step 55449: {'lr': 0.0003556374645343584, 'samples': 10646208, 'steps': 55448, 'loss/train': 0.7269425392150879} 08/30/2021 23:11:53 - INFO - __main__ - Step 55450: {'lr': 0.0003556326547975805, 'samples': 10646400, 'steps': 55449, 'loss/train': 1.6099789142608643} 08/30/2021 23:11:54 - INFO - __main__ - Step 55451: {'lr': 0.0003556278450132062, 'samples': 10646592, 'steps': 55450, 'loss/train': 0.9493165016174316} 08/30/2021 23:11:54 - INFO - __main__ - Step 55452: {'lr': 0.0003556230351812375, 'samples': 10646784, 'steps': 55451, 'loss/train': 1.639000415802002} 08/30/2021 23:11:55 - INFO - __main__ - Step 55453: {'lr': 0.00035561822530167677, 'samples': 10646976, 'steps': 55452, 'loss/train': 1.3469408750534058} 08/30/2021 23:11:55 - INFO - __main__ - Step 55454: {'lr': 0.0003556134153745261, 'samples': 10647168, 'steps': 55453, 'loss/train': 1.2902514934539795} 08/30/2021 23:11:56 - INFO - __main__ - Step 55455: {'lr': 0.0003556086053997877, 'samples': 10647360, 'steps': 55454, 'loss/train': 1.410627841949463} 08/30/2021 23:11:57 - INFO - __main__ - Step 55456: {'lr': 0.0003556037953774636, 'samples': 10647552, 'steps': 55455, 'loss/train': 1.404201865196228} 08/30/2021 23:11:57 - INFO - __main__ - Step 55457: {'lr': 0.0003555989853075561, 'samples': 10647744, 'steps': 55456, 'loss/train': 0.5927403569221497} 08/30/2021 23:11:58 - INFO - __main__ - Step 55458: {'lr': 0.0003555941751900673, 'samples': 10647936, 'steps': 55457, 'loss/train': 1.3797026872634888} 08/30/2021 23:11:58 - INFO - __main__ - Step 55459: {'lr': 0.00035558936502499944, 'samples': 10648128, 'steps': 55458, 'loss/train': 1.6795721054077148} 08/30/2021 23:12:00 - INFO - __main__ - Step 55460: {'lr': 0.00035558455481235463, 'samples': 10648320, 'steps': 55459, 'loss/train': 0.06003996729850769} 08/30/2021 23:12:00 - INFO - __main__ - Step 55461: {'lr': 0.000355579744552135, 'samples': 10648512, 'steps': 55460, 'loss/train': 1.2382827997207642} 08/30/2021 23:12:01 - INFO - __main__ - Step 55462: {'lr': 0.00035557493424434285, 'samples': 10648704, 'steps': 55461, 'loss/train': 1.3931047916412354} 08/30/2021 23:12:01 - INFO - __main__ - Step 55463: {'lr': 0.0003555701238889802, 'samples': 10648896, 'steps': 55462, 'loss/train': 1.2699464559555054} 08/30/2021 23:12:01 - INFO - __main__ - Step 55464: {'lr': 0.0003555653134860493, 'samples': 10649088, 'steps': 55463, 'loss/train': 1.0769644975662231} 08/30/2021 23:12:02 - INFO - __main__ - Step 55465: {'lr': 0.00035556050303555233, 'samples': 10649280, 'steps': 55464, 'loss/train': 0.04139209911227226} 08/30/2021 23:12:03 - INFO - __main__ - Step 55466: {'lr': 0.00035555569253749135, 'samples': 10649472, 'steps': 55465, 'loss/train': 0.0201834999024868} 08/30/2021 23:12:04 - INFO - __main__ - Step 55467: {'lr': 0.0003555508819918687, 'samples': 10649664, 'steps': 55466, 'loss/train': 0.6248383522033691} 08/30/2021 23:12:04 - INFO - __main__ - Step 55468: {'lr': 0.0003555460713986864, 'samples': 10649856, 'steps': 55467, 'loss/train': 1.3763900995254517} 08/30/2021 23:12:04 - INFO - __main__ - Step 55469: {'lr': 0.00035554126075794666, 'samples': 10650048, 'steps': 55468, 'loss/train': 0.9383394718170166} 08/30/2021 23:12:05 - INFO - __main__ - Step 55470: {'lr': 0.0003555364500696517, 'samples': 10650240, 'steps': 55469, 'loss/train': 1.3142777681350708} 08/30/2021 23:12:06 - INFO - __main__ - Step 55471: {'lr': 0.0003555316393338036, 'samples': 10650432, 'steps': 55470, 'loss/train': 1.1927725076675415} 08/30/2021 23:12:07 - INFO - __main__ - Step 55472: {'lr': 0.0003555268285504045, 'samples': 10650624, 'steps': 55471, 'loss/train': 0.09798042476177216} 08/30/2021 23:12:07 - INFO - __main__ - Step 55473: {'lr': 0.00035552201771945675, 'samples': 10650816, 'steps': 55472, 'loss/train': 0.5897518396377563} 08/30/2021 23:12:08 - INFO - __main__ - Step 55474: {'lr': 0.0003555172068409624, 'samples': 10651008, 'steps': 55473, 'loss/train': 1.325345754623413} 08/30/2021 23:12:08 - INFO - __main__ - Step 55475: {'lr': 0.0003555123959149236, 'samples': 10651200, 'steps': 55474, 'loss/train': 0.7527827620506287} 08/30/2021 23:12:10 - INFO - __main__ - Step 55476: {'lr': 0.00035550758494134257, 'samples': 10651392, 'steps': 55475, 'loss/train': 0.890178382396698} 08/30/2021 23:12:10 - INFO - __main__ - Step 55477: {'lr': 0.0003555027739202214, 'samples': 10651584, 'steps': 55476, 'loss/train': 1.0366718769073486} 08/30/2021 23:12:10 - INFO - __main__ - Step 55478: {'lr': 0.00035549796285156234, 'samples': 10651776, 'steps': 55477, 'loss/train': 0.7136321663856506} 08/30/2021 23:12:11 - INFO - __main__ - Step 55479: {'lr': 0.0003554931517353675, 'samples': 10651968, 'steps': 55478, 'loss/train': 1.4436877965927124} 08/30/2021 23:12:11 - INFO - __main__ - Step 55480: {'lr': 0.0003554883405716391, 'samples': 10652160, 'steps': 55479, 'loss/train': 1.5136303901672363} 08/30/2021 23:12:13 - INFO - __main__ - Step 55481: {'lr': 0.0003554835293603793, 'samples': 10652352, 'steps': 55480, 'loss/train': 0.7693046927452087} 08/30/2021 23:12:13 - INFO - __main__ - Step 55482: {'lr': 0.0003554787181015903, 'samples': 10652544, 'steps': 55481, 'loss/train': 0.10480514913797379} 08/30/2021 23:12:13 - INFO - __main__ - Step 55483: {'lr': 0.0003554739067952741, 'samples': 10652736, 'steps': 55482, 'loss/train': 1.1686795949935913} 08/30/2021 23:12:14 - INFO - __main__ - Step 55484: {'lr': 0.00035546909544143304, 'samples': 10652928, 'steps': 55483, 'loss/train': 2.042349338531494} 08/30/2021 23:12:14 - INFO - __main__ - Step 55485: {'lr': 0.00035546428404006913, 'samples': 10653120, 'steps': 55484, 'loss/train': 1.565883755683899} 08/30/2021 23:12:14 - INFO - __main__ - Step 55486: {'lr': 0.0003554594725911848, 'samples': 10653312, 'steps': 55485, 'loss/train': 1.542165756225586} 08/30/2021 23:12:17 - INFO - __main__ - Step 55487: {'lr': 0.00035545466109478195, 'samples': 10653504, 'steps': 55486, 'loss/train': 0.9397889375686646} 08/30/2021 23:12:17 - INFO - __main__ - Step 55488: {'lr': 0.00035544984955086296, 'samples': 10653696, 'steps': 55487, 'loss/train': 0.05148085579276085} 08/30/2021 23:12:18 - INFO - __main__ - Step 55489: {'lr': 0.00035544503795942984, 'samples': 10653888, 'steps': 55488, 'loss/train': 1.193132758140564} 08/30/2021 23:12:18 - INFO - __main__ - Step 55490: {'lr': 0.00035544022632048476, 'samples': 10654080, 'steps': 55489, 'loss/train': 1.1140227317810059} 08/30/2021 23:12:18 - INFO - __main__ - Step 55491: {'lr': 0.00035543541463402994, 'samples': 10654272, 'steps': 55490, 'loss/train': 1.3388952016830444} 08/30/2021 23:12:20 - INFO - __main__ - Step 55492: {'lr': 0.0003554306029000676, 'samples': 10654464, 'steps': 55491, 'loss/train': 1.8331475257873535} 08/30/2021 23:12:21 - INFO - __main__ - Step 55493: {'lr': 0.00035542579111859986, 'samples': 10654656, 'steps': 55492, 'loss/train': 1.1105254888534546} 08/30/2021 23:12:21 - INFO - __main__ - Step 55494: {'lr': 0.0003554209792896289, 'samples': 10654848, 'steps': 55493, 'loss/train': 0.9644830822944641} 08/30/2021 23:12:21 - INFO - __main__ - Step 55495: {'lr': 0.00035541616741315685, 'samples': 10655040, 'steps': 55494, 'loss/train': 1.385136365890503} 08/30/2021 23:12:22 - INFO - __main__ - Step 55496: {'lr': 0.0003554113554891859, 'samples': 10655232, 'steps': 55495, 'loss/train': 0.09133853763341904} 08/30/2021 23:12:23 - INFO - __main__ - Step 55497: {'lr': 0.0003554065435177183, 'samples': 10655424, 'steps': 55496, 'loss/train': 0.07849901914596558} 08/30/2021 23:12:23 - INFO - __main__ - Step 55498: {'lr': 0.00035540173149875597, 'samples': 10655616, 'steps': 55497, 'loss/train': 1.8646738529205322} 08/30/2021 23:12:24 - INFO - __main__ - Step 55499: {'lr': 0.00035539691943230135, 'samples': 10655808, 'steps': 55498, 'loss/train': 1.2672700881958008} 08/30/2021 23:12:24 - INFO - __main__ - Step 55500: {'lr': 0.00035539210731835646, 'samples': 10656000, 'steps': 55499, 'loss/train': 1.5393143892288208} 08/30/2021 23:12:25 - INFO - __main__ - Step 55501: {'lr': 0.00035538729515692356, 'samples': 10656192, 'steps': 55500, 'loss/train': 1.4273806810379028} 08/30/2021 23:12:27 - INFO - __main__ - Step 55502: {'lr': 0.0003553824829480048, 'samples': 10656384, 'steps': 55501, 'loss/train': 1.3791733980178833} 08/30/2021 23:12:27 - INFO - __main__ - Step 55503: {'lr': 0.00035537767069160234, 'samples': 10656576, 'steps': 55502, 'loss/train': 1.339461088180542} 08/30/2021 23:12:28 - INFO - __main__ - Step 55504: {'lr': 0.00035537285838771823, 'samples': 10656768, 'steps': 55503, 'loss/train': 1.4004014730453491} 08/30/2021 23:12:28 - INFO - __main__ - Step 55505: {'lr': 0.00035536804603635474, 'samples': 10656960, 'steps': 55504, 'loss/train': 1.37777841091156} 08/30/2021 23:12:28 - INFO - __main__ - Step 55506: {'lr': 0.00035536323363751405, 'samples': 10657152, 'steps': 55505, 'loss/train': 1.558566689491272} 08/30/2021 23:12:29 - INFO - __main__ - Step 55507: {'lr': 0.0003553584211911983, 'samples': 10657344, 'steps': 55506, 'loss/train': 1.4632781744003296} 08/30/2021 23:12:29 - INFO - __main__ - Step 55508: {'lr': 0.00035535360869740973, 'samples': 10657536, 'steps': 55507, 'loss/train': 1.114112377166748} 08/30/2021 23:12:31 - INFO - __main__ - Step 55509: {'lr': 0.00035534879615615046, 'samples': 10657728, 'steps': 55508, 'loss/train': 1.3278900384902954} 08/30/2021 23:12:31 - INFO - __main__ - Step 55510: {'lr': 0.0003553439835674226, 'samples': 10657920, 'steps': 55509, 'loss/train': 1.4269146919250488} 08/30/2021 23:12:31 - INFO - __main__ - Step 55511: {'lr': 0.00035533917093122835, 'samples': 10658112, 'steps': 55510, 'loss/train': 1.3330708742141724} 08/30/2021 23:12:32 - INFO - __main__ - Step 55512: {'lr': 0.00035533435824756986, 'samples': 10658304, 'steps': 55511, 'loss/train': 0.44845032691955566} 08/30/2021 23:12:32 - INFO - __main__ - Step 55513: {'lr': 0.00035532954551644944, 'samples': 10658496, 'steps': 55512, 'loss/train': 1.5402897596359253} 08/30/2021 23:12:34 - INFO - __main__ - Step 55514: {'lr': 0.0003553247327378691, 'samples': 10658688, 'steps': 55513, 'loss/train': 1.9340276718139648} 08/30/2021 23:12:35 - INFO - __main__ - Step 55515: {'lr': 0.0003553199199118311, 'samples': 10658880, 'steps': 55514, 'loss/train': 5.878765106201172} 08/30/2021 23:12:35 - INFO - __main__ - Step 55516: {'lr': 0.00035531510703833754, 'samples': 10659072, 'steps': 55515, 'loss/train': 5.910140514373779} 08/30/2021 23:12:35 - INFO - __main__ - Step 55517: {'lr': 0.00035531029411739056, 'samples': 10659264, 'steps': 55516, 'loss/train': 5.913590431213379} 08/30/2021 23:12:36 - INFO - __main__ - Step 55518: {'lr': 0.00035530548114899243, 'samples': 10659456, 'steps': 55517, 'loss/train': 1.2726004123687744} 08/30/2021 23:12:36 - INFO - __main__ - Step 55519: {'lr': 0.00035530066813314534, 'samples': 10659648, 'steps': 55518, 'loss/train': 1.4622379541397095} 08/30/2021 23:12:37 - INFO - __main__ - Step 55520: {'lr': 0.0003552958550698513, 'samples': 10659840, 'steps': 55519, 'loss/train': 1.734806776046753} 08/30/2021 23:12:38 - INFO - __main__ - Step 55521: {'lr': 0.00035529104195911255, 'samples': 10660032, 'steps': 55520, 'loss/train': 1.0233968496322632} 08/30/2021 23:12:38 - INFO - __main__ - Step 55522: {'lr': 0.00035528622880093145, 'samples': 10660224, 'steps': 55521, 'loss/train': 1.0475138425827026} 08/30/2021 23:12:39 - INFO - __main__ - Step 55523: {'lr': 0.00035528141559530984, 'samples': 10660416, 'steps': 55522, 'loss/train': 1.530788779258728} 08/30/2021 23:12:39 - INFO - __main__ - Step 55524: {'lr': 0.0003552766023422501, 'samples': 10660608, 'steps': 55523, 'loss/train': 1.2065110206604004} 08/30/2021 23:12:39 - INFO - __main__ - Step 55525: {'lr': 0.00035527178904175435, 'samples': 10660800, 'steps': 55524, 'loss/train': 0.8463578820228577} 08/30/2021 23:12:41 - INFO - __main__ - Step 55526: {'lr': 0.0003552669756938247, 'samples': 10660992, 'steps': 55525, 'loss/train': 1.3025094270706177} 08/30/2021 23:12:41 - INFO - __main__ - Step 55527: {'lr': 0.0003552621622984634, 'samples': 10661184, 'steps': 55526, 'loss/train': 0.4661639332771301} 08/30/2021 23:12:42 - INFO - __main__ - Step 55528: {'lr': 0.00035525734885567275, 'samples': 10661376, 'steps': 55527, 'loss/train': 1.4807226657867432} 08/30/2021 23:12:42 - INFO - __main__ - Step 55529: {'lr': 0.0003552525353654546, 'samples': 10661568, 'steps': 55528, 'loss/train': 0.054604776203632355} 08/30/2021 23:12:42 - INFO - __main__ - Step 55530: {'lr': 0.0003552477218278113, 'samples': 10661760, 'steps': 55529, 'loss/train': 0.7658342123031616} 08/30/2021 23:12:43 - INFO - __main__ - Step 55531: {'lr': 0.00035524290824274504, 'samples': 10661952, 'steps': 55530, 'loss/train': 1.4331191778182983} 08/30/2021 23:12:44 - INFO - __main__ - Step 55532: {'lr': 0.0003552380946102579, 'samples': 10662144, 'steps': 55531, 'loss/train': 1.0050603151321411} 08/30/2021 23:12:45 - INFO - __main__ - Step 55533: {'lr': 0.0003552332809303521, 'samples': 10662336, 'steps': 55532, 'loss/train': 1.4581477642059326} 08/30/2021 23:12:45 - INFO - __main__ - Step 55534: {'lr': 0.0003552284672030298, 'samples': 10662528, 'steps': 55533, 'loss/train': 1.2428696155548096} 08/30/2021 23:12:46 - INFO - __main__ - Step 55535: {'lr': 0.0003552236534282933, 'samples': 10662720, 'steps': 55534, 'loss/train': 1.391614317893982} 08/30/2021 23:12:46 - INFO - __main__ - Step 55536: {'lr': 0.00035521883960614456, 'samples': 10662912, 'steps': 55535, 'loss/train': 1.3651405572891235} 08/30/2021 23:12:48 - INFO - __main__ - Step 55537: {'lr': 0.0003552140257365858, 'samples': 10663104, 'steps': 55536, 'loss/train': 0.24041101336479187} 08/30/2021 23:12:48 - INFO - __main__ - Step 55538: {'lr': 0.00035520921181961924, 'samples': 10663296, 'steps': 55537, 'loss/train': 1.1786699295043945} 08/30/2021 23:12:48 - INFO - __main__ - Step 55539: {'lr': 0.00035520439785524703, 'samples': 10663488, 'steps': 55538, 'loss/train': 0.39626067876815796} 08/30/2021 23:12:49 - INFO - __main__ - Step 55540: {'lr': 0.00035519958384347134, 'samples': 10663680, 'steps': 55539, 'loss/train': 1.8849173784255981} 08/30/2021 23:12:49 - INFO - __main__ - Step 55541: {'lr': 0.00035519476978429433, 'samples': 10663872, 'steps': 55540, 'loss/train': 1.102056860923767} 08/30/2021 23:12:51 - INFO - __main__ - Step 55542: {'lr': 0.0003551899556777183, 'samples': 10664064, 'steps': 55541, 'loss/train': 1.7890520095825195} 08/30/2021 23:12:52 - INFO - __main__ - Step 55543: {'lr': 0.00035518514152374514, 'samples': 10664256, 'steps': 55542, 'loss/train': 1.18366277217865} 08/30/2021 23:12:52 - INFO - __main__ - Step 55544: {'lr': 0.00035518032732237724, 'samples': 10664448, 'steps': 55543, 'loss/train': 1.1753648519515991} 08/30/2021 23:12:52 - INFO - __main__ - Step 55545: {'lr': 0.00035517551307361674, 'samples': 10664640, 'steps': 55544, 'loss/train': 6.13233757019043} 08/30/2021 23:12:53 - INFO - __main__ - Step 55546: {'lr': 0.0003551706987774657, 'samples': 10664832, 'steps': 55545, 'loss/train': 1.3345859050750732} 08/30/2021 23:12:53 - INFO - __main__ - Step 55547: {'lr': 0.00035516588443392644, 'samples': 10665024, 'steps': 55546, 'loss/train': 3.279421091079712} 08/30/2021 23:12:55 - INFO - __main__ - Step 55548: {'lr': 0.00035516107004300107, 'samples': 10665216, 'steps': 55547, 'loss/train': 1.5045636892318726} 08/30/2021 23:12:55 - INFO - __main__ - Step 55549: {'lr': 0.00035515625560469174, 'samples': 10665408, 'steps': 55548, 'loss/train': 1.1609314680099487} 08/30/2021 23:12:56 - INFO - __main__ - Step 55550: {'lr': 0.00035515144111900054, 'samples': 10665600, 'steps': 55549, 'loss/train': 2.206282138824463} 08/30/2021 23:12:56 - INFO - __main__ - Step 55551: {'lr': 0.00035514662658592977, 'samples': 10665792, 'steps': 55550, 'loss/train': 0.7513319849967957} 08/30/2021 23:12:56 - INFO - __main__ - Step 55552: {'lr': 0.0003551418120054816, 'samples': 10665984, 'steps': 55551, 'loss/train': 0.7058324217796326} 08/30/2021 23:12:58 - INFO - __main__ - Step 55553: {'lr': 0.0003551369973776581, 'samples': 10666176, 'steps': 55552, 'loss/train': 1.3419108390808105} 08/30/2021 23:12:58 - INFO - __main__ - Step 55554: {'lr': 0.0003551321827024615, 'samples': 10666368, 'steps': 55553, 'loss/train': 1.0806262493133545} 08/30/2021 23:12:59 - INFO - __main__ - Step 55555: {'lr': 0.0003551273679798939, 'samples': 10666560, 'steps': 55554, 'loss/train': 1.4196597337722778} 08/30/2021 23:12:59 - INFO - __main__ - Step 55556: {'lr': 0.00035512255320995764, 'samples': 10666752, 'steps': 55555, 'loss/train': 0.7956951856613159} 08/30/2021 23:12:59 - INFO - __main__ - Step 55557: {'lr': 0.0003551177383926547, 'samples': 10666944, 'steps': 55556, 'loss/train': 1.6736340522766113} 08/30/2021 23:13:01 - INFO - __main__ - Step 55558: {'lr': 0.00035511292352798736, 'samples': 10667136, 'steps': 55557, 'loss/train': 1.126220703125} 08/30/2021 23:13:01 - INFO - __main__ - Step 55559: {'lr': 0.0003551081086159578, 'samples': 10667328, 'steps': 55558, 'loss/train': 1.382939100265503} 08/30/2021 23:13:02 - INFO - __main__ - Step 55560: {'lr': 0.0003551032936565681, 'samples': 10667520, 'steps': 55559, 'loss/train': 1.303977608680725} 08/30/2021 23:13:02 - INFO - __main__ - Step 55561: {'lr': 0.0003550984786498205, 'samples': 10667712, 'steps': 55560, 'loss/train': 1.3649529218673706} 08/30/2021 23:13:02 - INFO - __main__ - Step 55562: {'lr': 0.0003550936635957171, 'samples': 10667904, 'steps': 55561, 'loss/train': 1.1614124774932861} 08/30/2021 23:13:04 - INFO - __main__ - Step 55563: {'lr': 0.00035508884849426014, 'samples': 10668096, 'steps': 55562, 'loss/train': 1.6265507936477661} 08/30/2021 23:13:04 - INFO - __main__ - Step 55564: {'lr': 0.0003550840333454518, 'samples': 10668288, 'steps': 55563, 'loss/train': 1.1556559801101685} 08/30/2021 23:13:05 - INFO - __main__ - Step 55565: {'lr': 0.00035507921814929415, 'samples': 10668480, 'steps': 55564, 'loss/train': 0.9558085799217224} 08/30/2021 23:13:05 - INFO - __main__ - Step 55566: {'lr': 0.0003550744029057895, 'samples': 10668672, 'steps': 55565, 'loss/train': 2.92163348197937} 08/30/2021 23:13:05 - INFO - __main__ - Step 55567: {'lr': 0.0003550695876149399, 'samples': 10668864, 'steps': 55566, 'loss/train': 1.0279262065887451} 08/30/2021 23:13:07 - INFO - __main__ - Step 55568: {'lr': 0.00035506477227674753, 'samples': 10669056, 'steps': 55567, 'loss/train': 0.048378534615039825} 08/30/2021 23:13:07 - INFO - __main__ - Step 55569: {'lr': 0.0003550599568912147, 'samples': 10669248, 'steps': 55568, 'loss/train': 0.9692768454551697} 08/30/2021 23:13:08 - INFO - __main__ - Step 55570: {'lr': 0.00035505514145834337, 'samples': 10669440, 'steps': 55569, 'loss/train': 0.4592815041542053} 08/30/2021 23:13:08 - INFO - __main__ - Step 55571: {'lr': 0.0003550503259781359, 'samples': 10669632, 'steps': 55570, 'loss/train': 2.1162960529327393} 08/30/2021 23:13:08 - INFO - __main__ - Step 55572: {'lr': 0.0003550455104505943, 'samples': 10669824, 'steps': 55571, 'loss/train': 1.6123930215835571} 08/30/2021 23:13:09 - INFO - __main__ - Step 55573: {'lr': 0.00035504069487572086, 'samples': 10670016, 'steps': 55572, 'loss/train': 2.04437255859375} 08/30/2021 23:13:10 - INFO - __main__ - Step 55574: {'lr': 0.00035503587925351767, 'samples': 10670208, 'steps': 55573, 'loss/train': 0.9854397177696228} 08/30/2021 23:13:11 - INFO - __main__ - Step 55575: {'lr': 0.00035503106358398694, 'samples': 10670400, 'steps': 55574, 'loss/train': 1.2532223463058472} 08/30/2021 23:13:11 - INFO - __main__ - Step 55576: {'lr': 0.0003550262478671309, 'samples': 10670592, 'steps': 55575, 'loss/train': 1.0182878971099854} 08/30/2021 23:13:11 - INFO - __main__ - Step 55577: {'lr': 0.00035502143210295163, 'samples': 10670784, 'steps': 55576, 'loss/train': 1.5405141115188599} 08/30/2021 23:13:12 - INFO - __main__ - Step 55578: {'lr': 0.0003550166162914513, 'samples': 10670976, 'steps': 55577, 'loss/train': 0.820939302444458} 08/30/2021 23:13:13 - INFO - __main__ - Step 55579: {'lr': 0.00035501180043263203, 'samples': 10671168, 'steps': 55578, 'loss/train': 1.1022518873214722} 08/30/2021 23:13:14 - INFO - __main__ - Step 55580: {'lr': 0.00035500698452649613, 'samples': 10671360, 'steps': 55579, 'loss/train': 1.6348439455032349} 08/30/2021 23:13:14 - INFO - __main__ - Step 55581: {'lr': 0.00035500216857304575, 'samples': 10671552, 'steps': 55580, 'loss/train': 0.8381043076515198} 08/30/2021 23:13:14 - INFO - __main__ - Step 55582: {'lr': 0.000354997352572283, 'samples': 10671744, 'steps': 55581, 'loss/train': 0.9342495799064636} 08/30/2021 23:13:15 - INFO - __main__ - Step 55583: {'lr': 0.00035499253652421, 'samples': 10671936, 'steps': 55582, 'loss/train': 1.182405948638916} 08/30/2021 23:13:16 - INFO - __main__ - Step 55584: {'lr': 0.000354987720428829, 'samples': 10672128, 'steps': 55583, 'loss/train': 1.4739466905593872} 08/30/2021 23:13:17 - INFO - __main__ - Step 55585: {'lr': 0.00035498290428614217, 'samples': 10672320, 'steps': 55584, 'loss/train': 1.0474975109100342} 08/30/2021 23:13:17 - INFO - __main__ - Step 55586: {'lr': 0.0003549780880961516, 'samples': 10672512, 'steps': 55585, 'loss/train': 1.4440350532531738} 08/30/2021 23:13:17 - INFO - __main__ - Step 55587: {'lr': 0.00035497327185885966, 'samples': 10672704, 'steps': 55586, 'loss/train': 0.9955775737762451} 08/30/2021 23:13:18 - INFO - __main__ - Step 55588: {'lr': 0.00035496845557426824, 'samples': 10672896, 'steps': 55587, 'loss/train': 0.3096802830696106} 08/30/2021 23:13:19 - INFO - __main__ - Step 55589: {'lr': 0.0003549636392423798, 'samples': 10673088, 'steps': 55588, 'loss/train': 1.285921335220337} 08/30/2021 23:13:20 - INFO - __main__ - Step 55590: {'lr': 0.00035495882286319625, 'samples': 10673280, 'steps': 55589, 'loss/train': 1.078321933746338} 08/30/2021 23:13:20 - INFO - __main__ - Step 55591: {'lr': 0.0003549540064367199, 'samples': 10673472, 'steps': 55590, 'loss/train': 0.3283541798591614} 08/30/2021 23:13:20 - INFO - __main__ - Step 55592: {'lr': 0.0003549491899629529, 'samples': 10673664, 'steps': 55591, 'loss/train': 1.2631309032440186} 08/30/2021 23:13:21 - INFO - __main__ - Step 55593: {'lr': 0.00035494437344189746, 'samples': 10673856, 'steps': 55592, 'loss/train': 1.4361330270767212} 08/30/2021 23:13:22 - INFO - __main__ - Step 55594: {'lr': 0.0003549395568735556, 'samples': 10674048, 'steps': 55593, 'loss/train': 1.1085577011108398} 08/30/2021 23:13:23 - INFO - __main__ - Step 55595: {'lr': 0.00035493474025792966, 'samples': 10674240, 'steps': 55594, 'loss/train': 1.2822076082229614} 08/30/2021 23:13:23 - INFO - __main__ - Step 55596: {'lr': 0.0003549299235950218, 'samples': 10674432, 'steps': 55595, 'loss/train': 1.6605780124664307} 08/30/2021 23:13:23 - INFO - __main__ - Step 55597: {'lr': 0.000354925106884834, 'samples': 10674624, 'steps': 55596, 'loss/train': 0.48490074276924133} 08/30/2021 23:13:24 - INFO - __main__ - Step 55598: {'lr': 0.0003549202901273687, 'samples': 10674816, 'steps': 55597, 'loss/train': 1.458268404006958} 08/30/2021 23:13:26 - INFO - __main__ - Step 55599: {'lr': 0.00035491547332262786, 'samples': 10675008, 'steps': 55598, 'loss/train': 1.5057588815689087} 08/30/2021 23:13:26 - INFO - __main__ - Step 55600: {'lr': 0.00035491065647061377, 'samples': 10675200, 'steps': 55599, 'loss/train': 1.568816900253296} 08/30/2021 23:13:27 - INFO - __main__ - Step 55601: {'lr': 0.0003549058395713285, 'samples': 10675392, 'steps': 55600, 'loss/train': 1.5766630172729492} 08/30/2021 23:13:27 - INFO - __main__ - Step 55602: {'lr': 0.00035490102262477436, 'samples': 10675584, 'steps': 55601, 'loss/train': 1.638654112815857} 08/30/2021 23:13:27 - INFO - __main__ - Step 55603: {'lr': 0.0003548962056309534, 'samples': 10675776, 'steps': 55602, 'loss/train': 1.4436196088790894} 08/30/2021 23:13:29 - INFO - __main__ - Step 55604: {'lr': 0.0003548913885898678, 'samples': 10675968, 'steps': 55603, 'loss/train': 1.1649856567382812} 08/30/2021 23:13:29 - INFO - __main__ - Step 55605: {'lr': 0.0003548865715015198, 'samples': 10676160, 'steps': 55604, 'loss/train': 2.042722702026367} 08/30/2021 23:13:30 - INFO - __main__ - Step 55606: {'lr': 0.00035488175436591146, 'samples': 10676352, 'steps': 55605, 'loss/train': 1.488159418106079} 08/30/2021 23:13:30 - INFO - __main__ - Step 55607: {'lr': 0.00035487693718304504, 'samples': 10676544, 'steps': 55606, 'loss/train': 1.6831434965133667} 08/30/2021 23:13:30 - INFO - __main__ - Step 55608: {'lr': 0.00035487211995292276, 'samples': 10676736, 'steps': 55607, 'loss/train': 1.2747161388397217} 08/30/2021 23:13:31 - INFO - __main__ - Step 55609: {'lr': 0.00035486730267554666, 'samples': 10676928, 'steps': 55608, 'loss/train': 1.5266501903533936} 08/30/2021 23:13:32 - INFO - __main__ - Step 55610: {'lr': 0.000354862485350919, 'samples': 10677120, 'steps': 55609, 'loss/train': 0.7851687669754028} 08/30/2021 23:13:33 - INFO - __main__ - Step 55611: {'lr': 0.0003548576679790419, 'samples': 10677312, 'steps': 55610, 'loss/train': 1.3484630584716797} 08/30/2021 23:13:33 - INFO - __main__ - Step 55612: {'lr': 0.00035485285055991754, 'samples': 10677504, 'steps': 55611, 'loss/train': 0.7398014664649963} 08/30/2021 23:13:33 - INFO - __main__ - Step 55613: {'lr': 0.00035484803309354814, 'samples': 10677696, 'steps': 55612, 'loss/train': 1.5234750509262085} 08/30/2021 23:13:35 - INFO - __main__ - Step 55614: {'lr': 0.0003548432155799358, 'samples': 10677888, 'steps': 55613, 'loss/train': 1.6633076667785645} 08/30/2021 23:13:35 - INFO - __main__ - Step 55615: {'lr': 0.00035483839801908276, 'samples': 10678080, 'steps': 55614, 'loss/train': 0.8639807105064392} 08/30/2021 23:13:36 - INFO - __main__ - Step 55616: {'lr': 0.00035483358041099117, 'samples': 10678272, 'steps': 55615, 'loss/train': 1.6672723293304443} 08/30/2021 23:13:36 - INFO - __main__ - Step 55617: {'lr': 0.00035482876275566317, 'samples': 10678464, 'steps': 55616, 'loss/train': 1.2261906862258911} 08/30/2021 23:13:36 - INFO - __main__ - Step 55618: {'lr': 0.00035482394505310087, 'samples': 10678656, 'steps': 55617, 'loss/train': 0.7856540083885193} 08/30/2021 23:13:37 - INFO - __main__ - Step 55619: {'lr': 0.0003548191273033066, 'samples': 10678848, 'steps': 55618, 'loss/train': 1.6973035335540771} 08/30/2021 23:13:38 - INFO - __main__ - Step 55620: {'lr': 0.0003548143095062825, 'samples': 10679040, 'steps': 55619, 'loss/train': 1.1280386447906494} 08/30/2021 23:13:39 - INFO - __main__ - Step 55621: {'lr': 0.00035480949166203057, 'samples': 10679232, 'steps': 55620, 'loss/train': 0.9099001884460449} 08/30/2021 23:13:39 - INFO - __main__ - Step 55622: {'lr': 0.00035480467377055314, 'samples': 10679424, 'steps': 55621, 'loss/train': 1.3519760370254517} 08/30/2021 23:13:39 - INFO - __main__ - Step 55623: {'lr': 0.00035479985583185237, 'samples': 10679616, 'steps': 55622, 'loss/train': 0.9619577527046204} 08/30/2021 23:13:40 - INFO - __main__ - Step 55624: {'lr': 0.0003547950378459304, 'samples': 10679808, 'steps': 55623, 'loss/train': 1.2956039905548096} 08/30/2021 23:13:41 - INFO - __main__ - Step 55625: {'lr': 0.00035479021981278935, 'samples': 10680000, 'steps': 55624, 'loss/train': 1.389266014099121} 08/30/2021 23:13:42 - INFO - __main__ - Step 55626: {'lr': 0.0003547854017324315, 'samples': 10680192, 'steps': 55625, 'loss/train': 1.6224184036254883} 08/30/2021 23:13:42 - INFO - __main__ - Step 55627: {'lr': 0.000354780583604859, 'samples': 10680384, 'steps': 55626, 'loss/train': 0.5724973678588867} 08/30/2021 23:13:42 - INFO - __main__ - Step 55628: {'lr': 0.0003547757654300739, 'samples': 10680576, 'steps': 55627, 'loss/train': 1.5860828161239624} 08/30/2021 23:13:43 - INFO - __main__ - Step 55629: {'lr': 0.0003547709472080785, 'samples': 10680768, 'steps': 55628, 'loss/train': 1.051838755607605} 08/30/2021 23:13:44 - INFO - __main__ - Step 55630: {'lr': 0.00035476612893887494, 'samples': 10680960, 'steps': 55629, 'loss/train': 1.8453034162521362} 08/30/2021 23:13:45 - INFO - __main__ - Step 55631: {'lr': 0.0003547613106224653, 'samples': 10681152, 'steps': 55630, 'loss/train': 1.211069107055664} 08/30/2021 23:13:45 - INFO - __main__ - Step 55632: {'lr': 0.0003547564922588519, 'samples': 10681344, 'steps': 55631, 'loss/train': 1.1199408769607544} 08/30/2021 23:13:45 - INFO - __main__ - Step 55633: {'lr': 0.0003547516738480369, 'samples': 10681536, 'steps': 55632, 'loss/train': 0.511131763458252} 08/30/2021 23:13:46 - INFO - __main__ - Step 55634: {'lr': 0.0003547468553900223, 'samples': 10681728, 'steps': 55633, 'loss/train': 1.5302780866622925} 08/30/2021 23:13:47 - INFO - __main__ - Step 55635: {'lr': 0.0003547420368848104, 'samples': 10681920, 'steps': 55634, 'loss/train': 1.2150541543960571} 08/30/2021 23:13:48 - INFO - __main__ - Step 55636: {'lr': 0.0003547372183324034, 'samples': 10682112, 'steps': 55635, 'loss/train': 0.9853528141975403} 08/30/2021 23:13:48 - INFO - __main__ - Step 55637: {'lr': 0.0003547323997328034, 'samples': 10682304, 'steps': 55636, 'loss/train': 1.2307056188583374} 08/30/2021 23:13:48 - INFO - __main__ - Step 55638: {'lr': 0.0003547275810860126, 'samples': 10682496, 'steps': 55637, 'loss/train': 0.9249447584152222} 08/30/2021 23:13:49 - INFO - __main__ - Step 55639: {'lr': 0.00035472276239203315, 'samples': 10682688, 'steps': 55638, 'loss/train': 1.2306729555130005} 08/30/2021 23:13:50 - INFO - __main__ - Step 55640: {'lr': 0.00035471794365086724, 'samples': 10682880, 'steps': 55639, 'loss/train': 1.4465547800064087} 08/30/2021 23:13:51 - INFO - __main__ - Step 55641: {'lr': 0.00035471312486251707, 'samples': 10683072, 'steps': 55640, 'loss/train': 1.8672592639923096} 08/30/2021 23:13:51 - INFO - __main__ - Step 55642: {'lr': 0.0003547083060269848, 'samples': 10683264, 'steps': 55641, 'loss/train': 1.3993582725524902} 08/30/2021 23:13:52 - INFO - __main__ - Step 55643: {'lr': 0.00035470348714427256, 'samples': 10683456, 'steps': 55642, 'loss/train': 1.5673904418945312} 08/30/2021 23:13:52 - INFO - __main__ - Step 55644: {'lr': 0.0003546986682143825, 'samples': 10683648, 'steps': 55643, 'loss/train': 1.1614502668380737} 08/30/2021 23:13:52 - INFO - __main__ - Step 55645: {'lr': 0.0003546938492373169, 'samples': 10683840, 'steps': 55644, 'loss/train': 0.09984840452671051} 08/30/2021 23:13:54 - INFO - __main__ - Step 55646: {'lr': 0.0003546890302130778, 'samples': 10684032, 'steps': 55645, 'loss/train': 0.0841052308678627} 08/30/2021 23:13:54 - INFO - __main__ - Step 55647: {'lr': 0.0003546842111416675, 'samples': 10684224, 'steps': 55646, 'loss/train': 0.9936304092407227} 08/30/2021 23:13:55 - INFO - __main__ - Step 55648: {'lr': 0.0003546793920230881, 'samples': 10684416, 'steps': 55647, 'loss/train': 1.5294994115829468} 08/30/2021 23:13:55 - INFO - __main__ - Step 55649: {'lr': 0.0003546745728573418, 'samples': 10684608, 'steps': 55648, 'loss/train': 0.883396565914154} 08/30/2021 23:13:55 - INFO - __main__ - Step 55650: {'lr': 0.0003546697536444307, 'samples': 10684800, 'steps': 55649, 'loss/train': 1.0118926763534546} 08/30/2021 23:13:57 - INFO - __main__ - Step 55651: {'lr': 0.00035466493438435703, 'samples': 10684992, 'steps': 55650, 'loss/train': 0.9946087002754211} 08/30/2021 23:13:58 - INFO - __main__ - Step 55652: {'lr': 0.000354660115077123, 'samples': 10685184, 'steps': 55651, 'loss/train': 1.253925085067749} 08/30/2021 23:13:58 - INFO - __main__ - Step 55653: {'lr': 0.0003546552957227307, 'samples': 10685376, 'steps': 55652, 'loss/train': 0.864951491355896} 08/30/2021 23:13:58 - INFO - __main__ - Step 55654: {'lr': 0.0003546504763211823, 'samples': 10685568, 'steps': 55653, 'loss/train': 0.3088420033454895} 08/30/2021 23:13:59 - INFO - __main__ - Step 55655: {'lr': 0.0003546456568724801, 'samples': 10685760, 'steps': 55654, 'loss/train': 1.0639262199401855} 08/30/2021 23:13:59 - INFO - __main__ - Step 55656: {'lr': 0.0003546408373766262, 'samples': 10685952, 'steps': 55655, 'loss/train': 0.39806151390075684} 08/30/2021 23:14:01 - INFO - __main__ - Step 55657: {'lr': 0.0003546360178336226, 'samples': 10686144, 'steps': 55656, 'loss/train': 0.05974964052438736} 08/30/2021 23:14:02 - INFO - __main__ - Step 55658: {'lr': 0.0003546311982434717, 'samples': 10686336, 'steps': 55657, 'loss/train': 1.8015832901000977} 08/30/2021 23:14:02 - INFO - __main__ - Step 55659: {'lr': 0.00035462637860617563, 'samples': 10686528, 'steps': 55658, 'loss/train': 0.8492950797080994} 08/30/2021 23:14:02 - INFO - __main__ - Step 55660: {'lr': 0.00035462155892173654, 'samples': 10686720, 'steps': 55659, 'loss/train': 1.9669959545135498} 08/30/2021 23:14:03 - INFO - __main__ - Step 55661: {'lr': 0.0003546167391901566, 'samples': 10686912, 'steps': 55660, 'loss/train': 0.8186646699905396} 08/30/2021 23:14:04 - INFO - __main__ - Step 55662: {'lr': 0.0003546119194114379, 'samples': 10687104, 'steps': 55661, 'loss/train': 1.4092613458633423} 08/30/2021 23:14:05 - INFO - __main__ - Step 55663: {'lr': 0.00035460709958558273, 'samples': 10687296, 'steps': 55662, 'loss/train': 1.1991801261901855} 08/30/2021 23:14:05 - INFO - __main__ - Step 55664: {'lr': 0.0003546022797125932, 'samples': 10687488, 'steps': 55663, 'loss/train': 1.2259601354599} 08/30/2021 23:14:05 - INFO - __main__ - Step 55665: {'lr': 0.00035459745979247146, 'samples': 10687680, 'steps': 55664, 'loss/train': 1.7016760110855103} 08/30/2021 23:14:06 - INFO - __main__ - Step 55666: {'lr': 0.00035459263982521975, 'samples': 10687872, 'steps': 55665, 'loss/train': 0.9808220863342285} 08/30/2021 23:14:07 - INFO - __main__ - Step 55667: {'lr': 0.00035458781981084026, 'samples': 10688064, 'steps': 55666, 'loss/train': 1.1275321245193481} 08/30/2021 23:14:08 - INFO - __main__ - Step 55668: {'lr': 0.00035458299974933506, 'samples': 10688256, 'steps': 55667, 'loss/train': 1.314697265625} 08/30/2021 23:14:08 - INFO - __main__ - Step 55669: {'lr': 0.00035457817964070637, 'samples': 10688448, 'steps': 55668, 'loss/train': 1.503603219985962} 08/30/2021 23:14:09 - INFO - __main__ - Step 55670: {'lr': 0.0003545733594849564, 'samples': 10688640, 'steps': 55669, 'loss/train': 1.1797946691513062} 08/30/2021 23:14:09 - INFO - __main__ - Step 55671: {'lr': 0.0003545685392820873, 'samples': 10688832, 'steps': 55670, 'loss/train': 1.623259425163269} 08/30/2021 23:14:10 - INFO - __main__ - Step 55672: {'lr': 0.0003545637190321012, 'samples': 10689024, 'steps': 55671, 'loss/train': 1.3980627059936523} 08/30/2021 23:14:11 - INFO - __main__ - Step 55673: {'lr': 0.00035455889873500026, 'samples': 10689216, 'steps': 55672, 'loss/train': 1.5831059217453003} 08/30/2021 23:14:11 - INFO - __main__ - Step 55674: {'lr': 0.00035455407839078673, 'samples': 10689408, 'steps': 55673, 'loss/train': 1.4477463960647583} 08/30/2021 23:14:12 - INFO - __main__ - Step 55675: {'lr': 0.00035454925799946273, 'samples': 10689600, 'steps': 55674, 'loss/train': 1.7354828119277954} 08/30/2021 23:14:12 - INFO - __main__ - Step 55676: {'lr': 0.0003545444375610306, 'samples': 10689792, 'steps': 55675, 'loss/train': 1.2588073015213013} 08/30/2021 23:14:12 - INFO - __main__ - Step 55677: {'lr': 0.0003545396170754922, 'samples': 10689984, 'steps': 55676, 'loss/train': 1.2677406072616577} 08/30/2021 23:14:14 - INFO - __main__ - Step 55678: {'lr': 0.0003545347965428498, 'samples': 10690176, 'steps': 55677, 'loss/train': 1.289686918258667} 08/30/2021 23:14:15 - INFO - __main__ - Step 55679: {'lr': 0.00035452997596310576, 'samples': 10690368, 'steps': 55678, 'loss/train': 0.6954678893089294} 08/30/2021 23:14:15 - INFO - __main__ - Step 55680: {'lr': 0.00035452515533626204, 'samples': 10690560, 'steps': 55679, 'loss/train': 1.1525535583496094} 08/30/2021 23:14:15 - INFO - __main__ - Step 55681: {'lr': 0.00035452033466232095, 'samples': 10690752, 'steps': 55680, 'loss/train': 1.5572208166122437} 08/30/2021 23:14:16 - INFO - __main__ - Step 55682: {'lr': 0.0003545155139412847, 'samples': 10690944, 'steps': 55681, 'loss/train': 0.6655292510986328} 08/30/2021 23:14:17 - INFO - __main__ - Step 55683: {'lr': 0.00035451069317315526, 'samples': 10691136, 'steps': 55682, 'loss/train': 1.54902982711792} 08/30/2021 23:14:18 - INFO - __main__ - Step 55684: {'lr': 0.00035450587235793493, 'samples': 10691328, 'steps': 55683, 'loss/train': 1.3780467510223389} 08/30/2021 23:14:18 - INFO - __main__ - Step 55685: {'lr': 0.0003545010514956258, 'samples': 10691520, 'steps': 55684, 'loss/train': 1.3956325054168701} 08/30/2021 23:14:18 - INFO - __main__ - Step 55686: {'lr': 0.0003544962305862302, 'samples': 10691712, 'steps': 55685, 'loss/train': 2.8110406398773193} 08/30/2021 23:14:19 - INFO - __main__ - Step 55687: {'lr': 0.0003544914096297502, 'samples': 10691904, 'steps': 55686, 'loss/train': 1.5897676944732666} 08/30/2021 23:14:20 - INFO - __main__ - Step 55688: {'lr': 0.000354486588626188, 'samples': 10692096, 'steps': 55687, 'loss/train': 1.5517693758010864} 08/30/2021 23:14:21 - INFO - __main__ - Step 55689: {'lr': 0.00035448176757554574, 'samples': 10692288, 'steps': 55688, 'loss/train': 1.3772660493850708} 08/30/2021 23:14:21 - INFO - __main__ - Step 55690: {'lr': 0.0003544769464778256, 'samples': 10692480, 'steps': 55689, 'loss/train': 0.22232332825660706} 08/30/2021 23:14:21 - INFO - __main__ - Step 55691: {'lr': 0.00035447212533302975, 'samples': 10692672, 'steps': 55690, 'loss/train': 1.047350525856018} 08/30/2021 23:14:22 - INFO - __main__ - Step 55692: {'lr': 0.00035446730414116036, 'samples': 10692864, 'steps': 55691, 'loss/train': 1.302718162536621} 08/30/2021 23:14:23 - INFO - __main__ - Step 55693: {'lr': 0.00035446248290221967, 'samples': 10693056, 'steps': 55692, 'loss/train': 1.6574903726577759} 08/30/2021 23:14:24 - INFO - __main__ - Step 55694: {'lr': 0.00035445766161620976, 'samples': 10693248, 'steps': 55693, 'loss/train': 1.5358338356018066} 08/30/2021 23:14:24 - INFO - __main__ - Step 55695: {'lr': 0.00035445284028313284, 'samples': 10693440, 'steps': 55694, 'loss/train': 2.3100669384002686} 08/30/2021 23:14:24 - INFO - __main__ - Step 55696: {'lr': 0.00035444801890299103, 'samples': 10693632, 'steps': 55695, 'loss/train': 1.6347917318344116} 08/30/2021 23:14:25 - INFO - __main__ - Step 55697: {'lr': 0.0003544431974757866, 'samples': 10693824, 'steps': 55696, 'loss/train': 0.661130964756012} 08/30/2021 23:14:26 - INFO - __main__ - Step 55698: {'lr': 0.00035443837600152174, 'samples': 10694016, 'steps': 55697, 'loss/train': 1.2135374546051025} 08/30/2021 23:14:26 - INFO - __main__ - Step 55699: {'lr': 0.00035443355448019854, 'samples': 10694208, 'steps': 55698, 'loss/train': 1.3254491090774536} 08/30/2021 23:14:27 - INFO - __main__ - Step 55700: {'lr': 0.0003544287329118191, 'samples': 10694400, 'steps': 55699, 'loss/train': 1.1920199394226074} 08/30/2021 23:14:27 - INFO - __main__ - Step 55701: {'lr': 0.0003544239112963857, 'samples': 10694592, 'steps': 55700, 'loss/train': 1.1277209520339966} 08/30/2021 23:14:27 - INFO - __main__ - Step 55702: {'lr': 0.0003544190896339006, 'samples': 10694784, 'steps': 55701, 'loss/train': 0.9427372217178345} 08/30/2021 23:14:28 - INFO - __main__ - Step 55703: {'lr': 0.00035441426792436574, 'samples': 10694976, 'steps': 55702, 'loss/train': 0.8381898403167725} 08/30/2021 23:14:30 - INFO - __main__ - Step 55704: {'lr': 0.0003544094461677836, 'samples': 10695168, 'steps': 55703, 'loss/train': 0.9238675236701965} 08/30/2021 23:14:30 - INFO - __main__ - Step 55705: {'lr': 0.000354404624364156, 'samples': 10695360, 'steps': 55704, 'loss/train': 0.638308584690094} 08/30/2021 23:14:31 - INFO - __main__ - Step 55706: {'lr': 0.00035439980251348533, 'samples': 10695552, 'steps': 55705, 'loss/train': 1.2406498193740845} 08/30/2021 23:14:31 - INFO - __main__ - Step 55707: {'lr': 0.0003543949806157738, 'samples': 10695744, 'steps': 55706, 'loss/train': 0.041314493864774704} 08/30/2021 23:14:31 - INFO - __main__ - Step 55708: {'lr': 0.0003543901586710234, 'samples': 10695936, 'steps': 55707, 'loss/train': 1.1343141794204712} 08/30/2021 23:14:33 - INFO - __main__ - Step 55709: {'lr': 0.00035438533667923644, 'samples': 10696128, 'steps': 55708, 'loss/train': 0.538677990436554} 08/30/2021 23:14:33 - INFO - __main__ - Step 55710: {'lr': 0.0003543805146404151, 'samples': 10696320, 'steps': 55709, 'loss/train': 1.5439282655715942} 08/30/2021 23:14:34 - INFO - __main__ - Step 55711: {'lr': 0.0003543756925545615, 'samples': 10696512, 'steps': 55710, 'loss/train': 1.7141923904418945} 08/30/2021 23:14:34 - INFO - __main__ - Step 55712: {'lr': 0.0003543708704216778, 'samples': 10696704, 'steps': 55711, 'loss/train': 1.2219743728637695} 08/30/2021 23:14:34 - INFO - __main__ - Step 55713: {'lr': 0.00035436604824176616, 'samples': 10696896, 'steps': 55712, 'loss/train': 0.8718641400337219} 08/30/2021 23:14:36 - INFO - __main__ - Step 55714: {'lr': 0.0003543612260148288, 'samples': 10697088, 'steps': 55713, 'loss/train': 1.0926668643951416} 08/30/2021 23:14:37 - INFO - __main__ - Step 55715: {'lr': 0.0003543564037408679, 'samples': 10697280, 'steps': 55714, 'loss/train': 1.4930851459503174} 08/30/2021 23:14:37 - INFO - __main__ - Step 55716: {'lr': 0.00035435158141988564, 'samples': 10697472, 'steps': 55715, 'loss/train': 0.6779083609580994} 08/30/2021 23:14:37 - INFO - __main__ - Step 55717: {'lr': 0.0003543467590518842, 'samples': 10697664, 'steps': 55716, 'loss/train': 1.1186442375183105} 08/30/2021 23:14:38 - INFO - __main__ - Step 55718: {'lr': 0.00035434193663686566, 'samples': 10697856, 'steps': 55717, 'loss/train': 0.6522392630577087} 08/30/2021 23:14:39 - INFO - __main__ - Step 55719: {'lr': 0.0003543371141748323, 'samples': 10698048, 'steps': 55718, 'loss/train': 1.231892704963684} 08/30/2021 23:14:40 - INFO - __main__ - Step 55720: {'lr': 0.0003543322916657862, 'samples': 10698240, 'steps': 55719, 'loss/train': 1.8002524375915527} 08/30/2021 23:14:40 - INFO - __main__ - Step 55721: {'lr': 0.0003543274691097295, 'samples': 10698432, 'steps': 55720, 'loss/train': 0.7160958647727966} 08/30/2021 23:14:41 - INFO - __main__ - Step 55722: {'lr': 0.00035432264650666457, 'samples': 10698624, 'steps': 55721, 'loss/train': 1.4103093147277832} 08/30/2021 23:14:41 - INFO - __main__ - Step 55723: {'lr': 0.0003543178238565935, 'samples': 10698816, 'steps': 55722, 'loss/train': 1.3467888832092285} 08/30/2021 23:14:43 - INFO - __main__ - Step 55724: {'lr': 0.0003543130011595183, 'samples': 10699008, 'steps': 55723, 'loss/train': 1.4478784799575806} 08/30/2021 23:14:43 - INFO - __main__ - Step 55725: {'lr': 0.0003543081784154414, 'samples': 10699200, 'steps': 55724, 'loss/train': 1.8630198240280151} 08/30/2021 23:14:43 - INFO - __main__ - Step 55726: {'lr': 0.00035430335562436474, 'samples': 10699392, 'steps': 55725, 'loss/train': 0.8415594100952148} 08/30/2021 23:14:44 - INFO - __main__ - Step 55727: {'lr': 0.00035429853278629063, 'samples': 10699584, 'steps': 55726, 'loss/train': 0.14067301154136658} 08/30/2021 23:14:44 - INFO - __main__ - Step 55728: {'lr': 0.00035429370990122124, 'samples': 10699776, 'steps': 55727, 'loss/train': 1.494025707244873} 08/30/2021 23:14:46 - INFO - __main__ - Step 55729: {'lr': 0.0003542888869691586, 'samples': 10699968, 'steps': 55728, 'loss/train': 1.278326153755188} 08/30/2021 23:14:46 - INFO - __main__ - Step 55730: {'lr': 0.00035428406399010516, 'samples': 10700160, 'steps': 55729, 'loss/train': 0.7158213257789612} 08/30/2021 23:14:46 - INFO - __main__ - Step 55731: {'lr': 0.00035427924096406287, 'samples': 10700352, 'steps': 55730, 'loss/train': 2.846364736557007} 08/30/2021 23:14:47 - INFO - __main__ - Step 55732: {'lr': 0.00035427441789103397, 'samples': 10700544, 'steps': 55731, 'loss/train': 0.8122023344039917} 08/30/2021 23:14:47 - INFO - __main__ - Step 55733: {'lr': 0.0003542695947710206, 'samples': 10700736, 'steps': 55732, 'loss/train': 1.566859483718872} 08/30/2021 23:14:47 - INFO - __main__ - Step 55734: {'lr': 0.00035426477160402495, 'samples': 10700928, 'steps': 55733, 'loss/train': 1.5851231813430786} 08/30/2021 23:14:49 - INFO - __main__ - Step 55735: {'lr': 0.0003542599483900492, 'samples': 10701120, 'steps': 55734, 'loss/train': 1.6320836544036865} 08/30/2021 23:14:49 - INFO - __main__ - Step 55736: {'lr': 0.00035425512512909555, 'samples': 10701312, 'steps': 55735, 'loss/train': 1.3067712783813477} 08/30/2021 23:14:50 - INFO - __main__ - Step 55737: {'lr': 0.00035425030182116617, 'samples': 10701504, 'steps': 55736, 'loss/train': 1.2268667221069336} 08/30/2021 23:14:50 - INFO - __main__ - Step 55738: {'lr': 0.0003542454784662632, 'samples': 10701696, 'steps': 55737, 'loss/train': 1.8341413736343384} 08/30/2021 23:14:50 - INFO - __main__ - Step 55739: {'lr': 0.00035424065506438877, 'samples': 10701888, 'steps': 55738, 'loss/train': 0.8880284428596497} 08/30/2021 23:14:52 - INFO - __main__ - Step 55740: {'lr': 0.0003542358316155452, 'samples': 10702080, 'steps': 55739, 'loss/train': 1.4299170970916748} 08/30/2021 23:14:53 - INFO - __main__ - Step 55741: {'lr': 0.00035423100811973453, 'samples': 10702272, 'steps': 55740, 'loss/train': 1.304391622543335} 08/30/2021 23:14:53 - INFO - __main__ - Step 55742: {'lr': 0.00035422618457695893, 'samples': 10702464, 'steps': 55741, 'loss/train': 1.3320468664169312} 08/30/2021 23:14:54 - INFO - __main__ - Step 55743: {'lr': 0.0003542213609872207, 'samples': 10702656, 'steps': 55742, 'loss/train': 1.636850118637085} 08/30/2021 23:14:54 - INFO - __main__ - Step 55744: {'lr': 0.0003542165373505219, 'samples': 10702848, 'steps': 55743, 'loss/train': 1.6292940378189087} 08/30/2021 23:14:55 - INFO - __main__ - Step 55745: {'lr': 0.0003542117136668647, 'samples': 10703040, 'steps': 55744, 'loss/train': 0.8332457542419434} 08/30/2021 23:14:55 - INFO - __main__ - Step 55746: {'lr': 0.0003542068899362514, 'samples': 10703232, 'steps': 55745, 'loss/train': 1.1777420043945312} 08/30/2021 23:14:57 - INFO - __main__ - Step 55747: {'lr': 0.000354202066158684, 'samples': 10703424, 'steps': 55746, 'loss/train': 1.5863596200942993} 08/30/2021 23:14:57 - INFO - __main__ - Step 55748: {'lr': 0.0003541972423341648, 'samples': 10703616, 'steps': 55747, 'loss/train': 1.2048829793930054} 08/30/2021 23:14:57 - INFO - __main__ - Step 55749: {'lr': 0.0003541924184626959, 'samples': 10703808, 'steps': 55748, 'loss/train': 1.4137334823608398} 08/30/2021 23:14:58 - INFO - __main__ - Step 55750: {'lr': 0.00035418759454427953, 'samples': 10704000, 'steps': 55749, 'loss/train': 1.1200039386749268} 08/30/2021 23:14:58 - INFO - __main__ - Step 55751: {'lr': 0.00035418277057891776, 'samples': 10704192, 'steps': 55750, 'loss/train': 0.7291431427001953} 08/30/2021 23:15:00 - INFO - __main__ - Step 55752: {'lr': 0.00035417794656661297, 'samples': 10704384, 'steps': 55751, 'loss/train': 1.0747979879379272} 08/30/2021 23:15:00 - INFO - __main__ - Step 55753: {'lr': 0.0003541731225073671, 'samples': 10704576, 'steps': 55752, 'loss/train': 1.8460533618927002} 08/30/2021 23:15:00 - INFO - __main__ - Step 55754: {'lr': 0.0003541682984011825, 'samples': 10704768, 'steps': 55753, 'loss/train': 0.9102686047554016} 08/30/2021 23:15:01 - INFO - __main__ - Step 55755: {'lr': 0.00035416347424806124, 'samples': 10704960, 'steps': 55754, 'loss/train': 1.715810775756836} 08/30/2021 23:15:01 - INFO - __main__ - Step 55756: {'lr': 0.00035415865004800553, 'samples': 10705152, 'steps': 55755, 'loss/train': 1.778009295463562} 08/30/2021 23:15:03 - INFO - __main__ - Step 55757: {'lr': 0.00035415382580101753, 'samples': 10705344, 'steps': 55756, 'loss/train': 2.1117496490478516} 08/30/2021 23:15:03 - INFO - __main__ - Step 55758: {'lr': 0.00035414900150709946, 'samples': 10705536, 'steps': 55757, 'loss/train': 1.0899864435195923} 08/30/2021 23:15:03 - INFO - __main__ - Step 55759: {'lr': 0.00035414417716625343, 'samples': 10705728, 'steps': 55758, 'loss/train': 1.1682169437408447} 08/30/2021 23:15:04 - INFO - __main__ - Step 55760: {'lr': 0.00035413935277848156, 'samples': 10705920, 'steps': 55759, 'loss/train': 0.08942674845457077} 08/30/2021 23:15:04 - INFO - __main__ - Step 55761: {'lr': 0.00035413452834378624, 'samples': 10706112, 'steps': 55760, 'loss/train': 1.2167680263519287} 08/30/2021 23:15:06 - INFO - __main__ - Step 55762: {'lr': 0.0003541297038621694, 'samples': 10706304, 'steps': 55761, 'loss/train': 1.4061381816864014} 08/30/2021 23:15:07 - INFO - __main__ - Step 55763: {'lr': 0.00035412487933363335, 'samples': 10706496, 'steps': 55762, 'loss/train': 1.9082527160644531} 08/30/2021 23:15:07 - INFO - __main__ - Step 55764: {'lr': 0.00035412005475818033, 'samples': 10706688, 'steps': 55763, 'loss/train': 1.1674234867095947} 08/30/2021 23:15:07 - INFO - __main__ - Step 55765: {'lr': 0.0003541152301358124, 'samples': 10706880, 'steps': 55764, 'loss/train': 1.508541226387024} 08/30/2021 23:15:08 - INFO - __main__ - Step 55766: {'lr': 0.0003541104054665316, 'samples': 10707072, 'steps': 55765, 'loss/train': 1.5136747360229492} 08/30/2021 23:15:09 - INFO - __main__ - Step 55767: {'lr': 0.0003541055807503404, 'samples': 10707264, 'steps': 55766, 'loss/train': 1.5840827226638794} 08/30/2021 23:15:10 - INFO - __main__ - Step 55768: {'lr': 0.0003541007559872408, 'samples': 10707456, 'steps': 55767, 'loss/train': 1.5111762285232544} 08/30/2021 23:15:10 - INFO - __main__ - Step 55769: {'lr': 0.000354095931177235, 'samples': 10707648, 'steps': 55768, 'loss/train': 1.3580626249313354} 08/30/2021 23:15:10 - INFO - __main__ - Step 55770: {'lr': 0.0003540911063203252, 'samples': 10707840, 'steps': 55769, 'loss/train': 1.2443751096725464} 08/30/2021 23:15:11 - INFO - __main__ - Step 55771: {'lr': 0.00035408628141651356, 'samples': 10708032, 'steps': 55770, 'loss/train': 0.5195919275283813} 08/30/2021 23:15:12 - INFO - __main__ - Step 55772: {'lr': 0.0003540814564658022, 'samples': 10708224, 'steps': 55771, 'loss/train': 0.8362556099891663} 08/30/2021 23:15:13 - INFO - __main__ - Step 55773: {'lr': 0.00035407663146819337, 'samples': 10708416, 'steps': 55772, 'loss/train': 1.8281182050704956} 08/30/2021 23:15:13 - INFO - __main__ - Step 55774: {'lr': 0.0003540718064236892, 'samples': 10708608, 'steps': 55773, 'loss/train': 0.7100035548210144} 08/30/2021 23:15:14 - INFO - __main__ - Step 55775: {'lr': 0.0003540669813322919, 'samples': 10708800, 'steps': 55774, 'loss/train': 1.6116893291473389} 08/30/2021 23:15:14 - INFO - __main__ - Step 55776: {'lr': 0.00035406215619400357, 'samples': 10708992, 'steps': 55775, 'loss/train': 0.6807646751403809} 08/30/2021 23:15:15 - INFO - __main__ - Step 55777: {'lr': 0.00035405733100882654, 'samples': 10709184, 'steps': 55776, 'loss/train': 1.3845784664154053} 08/30/2021 23:15:16 - INFO - __main__ - Step 55778: {'lr': 0.0003540525057767628, 'samples': 10709376, 'steps': 55777, 'loss/train': 1.4464852809906006} 08/30/2021 23:15:16 - INFO - __main__ - Step 55779: {'lr': 0.0003540476804978146, 'samples': 10709568, 'steps': 55778, 'loss/train': 1.1956968307495117} 08/30/2021 23:15:17 - INFO - __main__ - Step 55780: {'lr': 0.00035404285517198417, 'samples': 10709760, 'steps': 55779, 'loss/train': 1.3396869897842407} 08/30/2021 23:15:17 - INFO - __main__ - Step 55781: {'lr': 0.00035403802979927355, 'samples': 10709952, 'steps': 55780, 'loss/train': 2.1580255031585693} 08/30/2021 23:15:17 - INFO - __main__ - Step 55782: {'lr': 0.0003540332043796851, 'samples': 10710144, 'steps': 55781, 'loss/train': 1.0538784265518188} 08/30/2021 23:15:19 - INFO - __main__ - Step 55783: {'lr': 0.00035402837891322083, 'samples': 10710336, 'steps': 55782, 'loss/train': 1.8561463356018066} 08/30/2021 23:15:19 - INFO - __main__ - Step 55784: {'lr': 0.00035402355339988307, 'samples': 10710528, 'steps': 55783, 'loss/train': 1.161104679107666} 08/30/2021 23:15:19 - INFO - __main__ - Step 55785: {'lr': 0.00035401872783967384, 'samples': 10710720, 'steps': 55784, 'loss/train': 1.2689498662948608} 08/30/2021 23:15:20 - INFO - __main__ - Step 55786: {'lr': 0.00035401390223259536, 'samples': 10710912, 'steps': 55785, 'loss/train': 1.2551660537719727} 08/30/2021 23:15:20 - INFO - __main__ - Step 55787: {'lr': 0.0003540090765786498, 'samples': 10711104, 'steps': 55786, 'loss/train': 0.769989550113678} 08/30/2021 23:15:22 - INFO - __main__ - Step 55788: {'lr': 0.0003540042508778394, 'samples': 10711296, 'steps': 55787, 'loss/train': 0.9293236136436462} 08/30/2021 23:15:23 - INFO - __main__ - Step 55789: {'lr': 0.00035399942513016623, 'samples': 10711488, 'steps': 55788, 'loss/train': 0.7601248025894165} 08/30/2021 23:15:23 - INFO - __main__ - Step 55790: {'lr': 0.0003539945993356326, 'samples': 10711680, 'steps': 55789, 'loss/train': 1.398922085762024} 08/30/2021 23:15:23 - INFO - __main__ - Step 55791: {'lr': 0.0003539897734942406, 'samples': 10711872, 'steps': 55790, 'loss/train': 1.108388066291809} 08/30/2021 23:15:24 - INFO - __main__ - Step 55792: {'lr': 0.00035398494760599243, 'samples': 10712064, 'steps': 55791, 'loss/train': 1.6827489137649536} 08/30/2021 23:15:24 - INFO - __main__ - Step 55793: {'lr': 0.00035398012167089016, 'samples': 10712256, 'steps': 55792, 'loss/train': 2.2388172149658203} 08/30/2021 23:15:25 - INFO - __main__ - Step 55794: {'lr': 0.0003539752956889361, 'samples': 10712448, 'steps': 55793, 'loss/train': 1.8627614974975586} 08/30/2021 23:15:26 - INFO - __main__ - Step 55795: {'lr': 0.00035397046966013235, 'samples': 10712640, 'steps': 55794, 'loss/train': 0.41283100843429565} 08/30/2021 23:15:26 - INFO - __main__ - Step 55796: {'lr': 0.00035396564358448115, 'samples': 10712832, 'steps': 55795, 'loss/train': 1.7279332876205444} 08/30/2021 23:15:27 - INFO - __main__ - Step 55797: {'lr': 0.00035396081746198467, 'samples': 10713024, 'steps': 55796, 'loss/train': 1.4764454364776611} 08/30/2021 23:15:27 - INFO - __main__ - Step 55798: {'lr': 0.000353955991292645, 'samples': 10713216, 'steps': 55797, 'loss/train': 1.5802695751190186} 08/30/2021 23:15:29 - INFO - __main__ - Step 55799: {'lr': 0.00035395116507646435, 'samples': 10713408, 'steps': 55798, 'loss/train': 1.715330958366394} 08/30/2021 23:15:29 - INFO - __main__ - Step 55800: {'lr': 0.00035394633881344497, 'samples': 10713600, 'steps': 55799, 'loss/train': 0.9424576163291931} 08/30/2021 23:15:29 - INFO - __main__ - Step 55801: {'lr': 0.00035394151250358886, 'samples': 10713792, 'steps': 55800, 'loss/train': 1.2360484600067139} 08/30/2021 23:15:30 - INFO - __main__ - Step 55802: {'lr': 0.00035393668614689837, 'samples': 10713984, 'steps': 55801, 'loss/train': 1.7449965476989746} 08/30/2021 23:15:30 - INFO - __main__ - Step 55803: {'lr': 0.00035393185974337565, 'samples': 10714176, 'steps': 55802, 'loss/train': 1.1759607791900635} 08/30/2021 23:15:32 - INFO - __main__ - Step 55804: {'lr': 0.0003539270332930228, 'samples': 10714368, 'steps': 55803, 'loss/train': 1.5261110067367554} 08/30/2021 23:15:32 - INFO - __main__ - Step 55805: {'lr': 0.00035392220679584206, 'samples': 10714560, 'steps': 55804, 'loss/train': 1.4128800630569458} 08/30/2021 23:15:32 - INFO - __main__ - Step 55806: {'lr': 0.0003539173802518356, 'samples': 10714752, 'steps': 55805, 'loss/train': 1.658766508102417} 08/30/2021 23:15:33 - INFO - __main__ - Step 55807: {'lr': 0.0003539125536610055, 'samples': 10714944, 'steps': 55806, 'loss/train': 1.805196762084961} 08/30/2021 23:15:33 - INFO - __main__ - Step 55808: {'lr': 0.00035390772702335405, 'samples': 10715136, 'steps': 55807, 'loss/train': 1.1509133577346802} 08/30/2021 23:15:35 - INFO - __main__ - Step 55809: {'lr': 0.0003539029003388833, 'samples': 10715328, 'steps': 55808, 'loss/train': 1.3984332084655762} 08/30/2021 23:15:35 - INFO - __main__ - Step 55810: {'lr': 0.0003538980736075956, 'samples': 10715520, 'steps': 55809, 'loss/train': 0.8859710693359375} 08/30/2021 23:15:35 - INFO - __main__ - Step 55811: {'lr': 0.0003538932468294931, 'samples': 10715712, 'steps': 55810, 'loss/train': 0.07919716089963913} 08/30/2021 23:15:36 - INFO - __main__ - Step 55812: {'lr': 0.0003538884200045778, 'samples': 10715904, 'steps': 55811, 'loss/train': 1.267533779144287} 08/30/2021 23:15:36 - INFO - __main__ - Step 55813: {'lr': 0.00035388359313285196, 'samples': 10716096, 'steps': 55812, 'loss/train': 1.0388505458831787} 08/30/2021 23:15:38 - INFO - __main__ - Step 55814: {'lr': 0.0003538787662143178, 'samples': 10716288, 'steps': 55813, 'loss/train': 1.569204568862915} 08/30/2021 23:15:38 - INFO - __main__ - Step 55815: {'lr': 0.00035387393924897747, 'samples': 10716480, 'steps': 55814, 'loss/train': 1.1774855852127075} 08/30/2021 23:15:38 - INFO - __main__ - Step 55816: {'lr': 0.0003538691122368332, 'samples': 10716672, 'steps': 55815, 'loss/train': 2.1934115886688232} 08/30/2021 23:15:39 - INFO - __main__ - Step 55817: {'lr': 0.00035386428517788707, 'samples': 10716864, 'steps': 55816, 'loss/train': 1.1093050241470337} 08/30/2021 23:15:39 - INFO - __main__ - Step 55818: {'lr': 0.00035385945807214124, 'samples': 10717056, 'steps': 55817, 'loss/train': 1.2497345209121704} 08/30/2021 23:15:39 - INFO - __main__ - Step 55819: {'lr': 0.000353854630919598, 'samples': 10717248, 'steps': 55818, 'loss/train': 1.3594471216201782} 08/30/2021 23:15:41 - INFO - __main__ - Step 55820: {'lr': 0.0003538498037202595, 'samples': 10717440, 'steps': 55819, 'loss/train': 0.9753965139389038} 08/30/2021 23:15:42 - INFO - __main__ - Step 55821: {'lr': 0.0003538449764741278, 'samples': 10717632, 'steps': 55820, 'loss/train': 1.3397353887557983} 08/30/2021 23:15:42 - INFO - __main__ - Step 55822: {'lr': 0.00035384014918120527, 'samples': 10717824, 'steps': 55821, 'loss/train': 1.1480140686035156} 08/30/2021 23:15:42 - INFO - __main__ - Step 55823: {'lr': 0.00035383532184149393, 'samples': 10718016, 'steps': 55822, 'loss/train': 0.8578100204467773} 08/30/2021 23:15:43 - INFO - __main__ - Step 55824: {'lr': 0.00035383049445499596, 'samples': 10718208, 'steps': 55823, 'loss/train': 0.9850677847862244} 08/30/2021 23:15:44 - INFO - __main__ - Step 55825: {'lr': 0.0003538256670217135, 'samples': 10718400, 'steps': 55824, 'loss/train': 0.15087755024433136} 08/30/2021 23:15:45 - INFO - __main__ - Step 55826: {'lr': 0.0003538208395416489, 'samples': 10718592, 'steps': 55825, 'loss/train': 1.3199774026870728} 08/30/2021 23:15:45 - INFO - __main__ - Step 55827: {'lr': 0.00035381601201480426, 'samples': 10718784, 'steps': 55826, 'loss/train': 1.394762635231018} 08/30/2021 23:15:45 - INFO - __main__ - Step 55828: {'lr': 0.00035381118444118167, 'samples': 10718976, 'steps': 55827, 'loss/train': 0.9617253541946411} 08/30/2021 23:15:46 - INFO - __main__ - Step 55829: {'lr': 0.00035380635682078334, 'samples': 10719168, 'steps': 55828, 'loss/train': 1.202509880065918} 08/30/2021 23:15:47 - INFO - __main__ - Step 55830: {'lr': 0.00035380152915361144, 'samples': 10719360, 'steps': 55829, 'loss/train': 1.505242109298706} 08/30/2021 23:15:48 - INFO - __main__ - Step 55831: {'lr': 0.00035379670143966826, 'samples': 10719552, 'steps': 55830, 'loss/train': 1.1661467552185059} 08/30/2021 23:15:48 - INFO - __main__ - Step 55832: {'lr': 0.00035379187367895584, 'samples': 10719744, 'steps': 55831, 'loss/train': 1.1387711763381958} 08/30/2021 23:15:48 - INFO - __main__ - Step 55833: {'lr': 0.0003537870458714765, 'samples': 10719936, 'steps': 55832, 'loss/train': 1.4760973453521729} 08/30/2021 23:15:49 - INFO - __main__ - Step 55834: {'lr': 0.0003537822180172322, 'samples': 10720128, 'steps': 55833, 'loss/train': 2.007533073425293} 08/30/2021 23:15:50 - INFO - __main__ - Step 55835: {'lr': 0.00035377739011622524, 'samples': 10720320, 'steps': 55834, 'loss/train': 1.4700040817260742} 08/30/2021 23:15:51 - INFO - __main__ - Step 55836: {'lr': 0.0003537725621684578, 'samples': 10720512, 'steps': 55835, 'loss/train': 0.4767780900001526} 08/30/2021 23:15:51 - INFO - __main__ - Step 55837: {'lr': 0.0003537677341739321, 'samples': 10720704, 'steps': 55836, 'loss/train': 0.8098054528236389} 08/30/2021 23:15:51 - INFO - __main__ - Step 55838: {'lr': 0.0003537629061326503, 'samples': 10720896, 'steps': 55837, 'loss/train': 1.8151724338531494} 08/30/2021 23:15:52 - INFO - __main__ - Step 55839: {'lr': 0.0003537580780446144, 'samples': 10721088, 'steps': 55838, 'loss/train': 1.3703428506851196} 08/30/2021 23:15:53 - INFO - __main__ - Step 55840: {'lr': 0.0003537532499098268, 'samples': 10721280, 'steps': 55839, 'loss/train': 1.0196481943130493} 08/30/2021 23:15:54 - INFO - __main__ - Step 55841: {'lr': 0.0003537484217282895, 'samples': 10721472, 'steps': 55840, 'loss/train': 1.4531360864639282} 08/30/2021 23:15:54 - INFO - __main__ - Step 55842: {'lr': 0.00035374359350000484, 'samples': 10721664, 'steps': 55841, 'loss/train': 1.2399746179580688} 08/30/2021 23:15:54 - INFO - __main__ - Step 55843: {'lr': 0.0003537387652249749, 'samples': 10721856, 'steps': 55842, 'loss/train': 0.21520744264125824} 08/30/2021 23:15:55 - INFO - __main__ - Step 55844: {'lr': 0.0003537339369032019, 'samples': 10722048, 'steps': 55843, 'loss/train': 1.1945297718048096} 08/30/2021 23:15:56 - INFO - __main__ - Step 55845: {'lr': 0.0003537291085346879, 'samples': 10722240, 'steps': 55844, 'loss/train': 1.0215296745300293} 08/30/2021 23:15:57 - INFO - __main__ - Step 55846: {'lr': 0.0003537242801194353, 'samples': 10722432, 'steps': 55845, 'loss/train': 0.8148331642150879} 08/30/2021 23:15:57 - INFO - __main__ - Step 55847: {'lr': 0.000353719451657446, 'samples': 10722624, 'steps': 55846, 'loss/train': 1.0143702030181885} 08/30/2021 23:15:57 - INFO - __main__ - Step 55848: {'lr': 0.0003537146231487224, 'samples': 10722816, 'steps': 55847, 'loss/train': 1.4620976448059082} 08/30/2021 23:15:58 - INFO - __main__ - Step 55849: {'lr': 0.0003537097945932666, 'samples': 10723008, 'steps': 55848, 'loss/train': 1.8522289991378784} 08/30/2021 23:15:58 - INFO - __main__ - Step 55850: {'lr': 0.00035370496599108073, 'samples': 10723200, 'steps': 55849, 'loss/train': 1.8698945045471191} 08/30/2021 23:16:00 - INFO - __main__ - Step 55851: {'lr': 0.00035370013734216697, 'samples': 10723392, 'steps': 55850, 'loss/train': 1.5686043500900269} 08/30/2021 23:16:00 - INFO - __main__ - Step 55852: {'lr': 0.0003536953086465276, 'samples': 10723584, 'steps': 55851, 'loss/train': 1.6252377033233643} 08/30/2021 23:16:00 - INFO - __main__ - Step 55853: {'lr': 0.0003536904799041647, 'samples': 10723776, 'steps': 55852, 'loss/train': 0.36260825395584106} 08/30/2021 23:16:01 - INFO - __main__ - Step 55854: {'lr': 0.00035368565111508043, 'samples': 10723968, 'steps': 55853, 'loss/train': 1.5042622089385986} 08/30/2021 23:16:01 - INFO - __main__ - Step 55855: {'lr': 0.000353680822279277, 'samples': 10724160, 'steps': 55854, 'loss/train': 1.1740037202835083} 08/30/2021 23:16:03 - INFO - __main__ - Step 55856: {'lr': 0.00035367599339675664, 'samples': 10724352, 'steps': 55855, 'loss/train': 1.195548415184021} 08/30/2021 23:16:03 - INFO - __main__ - Step 55857: {'lr': 0.0003536711644675215, 'samples': 10724544, 'steps': 55856, 'loss/train': 0.34780389070510864} 08/30/2021 23:16:04 - INFO - __main__ - Step 55858: {'lr': 0.0003536663354915737, 'samples': 10724736, 'steps': 55857, 'loss/train': 1.343656301498413} 08/30/2021 23:16:04 - INFO - __main__ - Step 55859: {'lr': 0.00035366150646891543, 'samples': 10724928, 'steps': 55858, 'loss/train': 0.7453269362449646} 08/30/2021 23:16:04 - INFO - __main__ - Step 55860: {'lr': 0.0003536566773995489, 'samples': 10725120, 'steps': 55859, 'loss/train': 0.6729212999343872} 08/30/2021 23:16:07 - INFO - __main__ - Step 55861: {'lr': 0.0003536518482834763, 'samples': 10725312, 'steps': 55860, 'loss/train': 1.1075812578201294} 08/30/2021 23:16:07 - INFO - __main__ - Step 55862: {'lr': 0.0003536470191206997, 'samples': 10725504, 'steps': 55861, 'loss/train': 1.1422550678253174} 08/30/2021 23:16:07 - INFO - __main__ - Step 55863: {'lr': 0.00035364218991122145, 'samples': 10725696, 'steps': 55862, 'loss/train': 1.2442809343338013} 08/30/2021 23:16:08 - INFO - __main__ - Step 55864: {'lr': 0.00035363736065504355, 'samples': 10725888, 'steps': 55863, 'loss/train': 1.4324740171432495} 08/30/2021 23:16:08 - INFO - __main__ - Step 55865: {'lr': 0.0003536325313521683, 'samples': 10726080, 'steps': 55864, 'loss/train': 1.1130757331848145} 08/30/2021 23:16:10 - INFO - __main__ - Step 55866: {'lr': 0.0003536277020025978, 'samples': 10726272, 'steps': 55865, 'loss/train': 0.3150434195995331} 08/30/2021 23:16:10 - INFO - __main__ - Step 55867: {'lr': 0.0003536228726063343, 'samples': 10726464, 'steps': 55866, 'loss/train': 1.6082249879837036} 08/30/2021 23:16:10 - INFO - __main__ - Step 55868: {'lr': 0.00035361804316337987, 'samples': 10726656, 'steps': 55867, 'loss/train': 1.2010414600372314} 08/30/2021 23:16:11 - INFO - __main__ - Step 55869: {'lr': 0.00035361321367373676, 'samples': 10726848, 'steps': 55868, 'loss/train': 1.2699295282363892} 08/30/2021 23:16:11 - INFO - __main__ - Step 55870: {'lr': 0.00035360838413740715, 'samples': 10727040, 'steps': 55869, 'loss/train': 6.135015964508057} 08/30/2021 23:16:12 - INFO - __main__ - Step 55871: {'lr': 0.0003536035545543933, 'samples': 10727232, 'steps': 55870, 'loss/train': 0.6468329429626465} 08/30/2021 23:16:13 - INFO - __main__ - Step 55872: {'lr': 0.00035359872492469715, 'samples': 10727424, 'steps': 55871, 'loss/train': 1.0681915283203125} 08/30/2021 23:16:13 - INFO - __main__ - Step 55873: {'lr': 0.0003535938952483211, 'samples': 10727616, 'steps': 55872, 'loss/train': 1.4447047710418701} 08/30/2021 23:16:14 - INFO - __main__ - Step 55874: {'lr': 0.00035358906552526714, 'samples': 10727808, 'steps': 55873, 'loss/train': 0.7339169383049011} 08/30/2021 23:16:14 - INFO - __main__ - Step 55875: {'lr': 0.0003535842357555376, 'samples': 10728000, 'steps': 55874, 'loss/train': 1.700046420097351} 08/30/2021 23:16:14 - INFO - __main__ - Step 55876: {'lr': 0.0003535794059391346, 'samples': 10728192, 'steps': 55875, 'loss/train': 1.1830312013626099} 08/30/2021 23:16:16 - INFO - __main__ - Step 55877: {'lr': 0.00035357457607606034, 'samples': 10728384, 'steps': 55876, 'loss/train': 1.050166130065918} 08/30/2021 23:16:17 - INFO - __main__ - Step 55878: {'lr': 0.00035356974616631697, 'samples': 10728576, 'steps': 55877, 'loss/train': 0.2922050952911377} 08/30/2021 23:16:17 - INFO - __main__ - Step 55879: {'lr': 0.00035356491620990667, 'samples': 10728768, 'steps': 55878, 'loss/train': 1.3382513523101807} 08/30/2021 23:16:17 - INFO - __main__ - Step 55880: {'lr': 0.0003535600862068316, 'samples': 10728960, 'steps': 55879, 'loss/train': 1.0374191999435425} 08/30/2021 23:16:18 - INFO - __main__ - Step 55881: {'lr': 0.00035355525615709393, 'samples': 10729152, 'steps': 55880, 'loss/train': 0.9945430755615234} 08/30/2021 23:16:19 - INFO - __main__ - Step 55882: {'lr': 0.0003535504260606959, 'samples': 10729344, 'steps': 55881, 'loss/train': 0.8950099349021912} 08/30/2021 23:16:20 - INFO - __main__ - Step 55883: {'lr': 0.00035354559591763965, 'samples': 10729536, 'steps': 55882, 'loss/train': 1.1675432920455933} 08/30/2021 23:16:20 - INFO - __main__ - Step 55884: {'lr': 0.0003535407657279273, 'samples': 10729728, 'steps': 55883, 'loss/train': 1.177507758140564} 08/30/2021 23:16:21 - INFO - __main__ - Step 55885: {'lr': 0.00035353593549156115, 'samples': 10729920, 'steps': 55884, 'loss/train': 1.4942655563354492} 08/30/2021 23:16:21 - INFO - __main__ - Step 55886: {'lr': 0.00035353110520854324, 'samples': 10730112, 'steps': 55885, 'loss/train': 1.0644011497497559} 08/30/2021 23:16:22 - INFO - __main__ - Step 55887: {'lr': 0.0003535262748788759, 'samples': 10730304, 'steps': 55886, 'loss/train': 0.5848406553268433} 08/30/2021 23:16:23 - INFO - __main__ - Step 55888: {'lr': 0.00035352144450256115, 'samples': 10730496, 'steps': 55887, 'loss/train': 1.3748239278793335} 08/30/2021 23:16:23 - INFO - __main__ - Step 55889: {'lr': 0.00035351661407960125, 'samples': 10730688, 'steps': 55888, 'loss/train': 1.9253418445587158} 08/30/2021 23:16:24 - INFO - __main__ - Step 55890: {'lr': 0.0003535117836099983, 'samples': 10730880, 'steps': 55889, 'loss/train': 0.8561276793479919} 08/30/2021 23:16:24 - INFO - __main__ - Step 55891: {'lr': 0.00035350695309375465, 'samples': 10731072, 'steps': 55890, 'loss/train': 2.533564567565918} 08/30/2021 23:16:25 - INFO - __main__ - Step 55892: {'lr': 0.00035350212253087233, 'samples': 10731264, 'steps': 55891, 'loss/train': 1.2324904203414917} 08/30/2021 23:16:26 - INFO - __main__ - Step 55893: {'lr': 0.0003534972919213535, 'samples': 10731456, 'steps': 55892, 'loss/train': 1.5151067972183228} 08/30/2021 23:16:26 - INFO - __main__ - Step 55894: {'lr': 0.0003534924612652004, 'samples': 10731648, 'steps': 55893, 'loss/train': 1.3352891206741333} 08/30/2021 23:16:26 - INFO - __main__ - Step 55895: {'lr': 0.00035348763056241515, 'samples': 10731840, 'steps': 55894, 'loss/train': 1.1198841333389282} 08/30/2021 23:16:27 - INFO - __main__ - Step 55896: {'lr': 0.0003534827998130001, 'samples': 10732032, 'steps': 55895, 'loss/train': 0.7932049632072449} 08/30/2021 23:16:27 - INFO - __main__ - Step 55897: {'lr': 0.00035347796901695716, 'samples': 10732224, 'steps': 55896, 'loss/train': 1.6382561922073364} 08/30/2021 23:16:29 - INFO - __main__ - Step 55898: {'lr': 0.0003534731381742888, 'samples': 10732416, 'steps': 55897, 'loss/train': 1.0531342029571533} 08/30/2021 23:16:29 - INFO - __main__ - Step 55899: {'lr': 0.0003534683072849969, 'samples': 10732608, 'steps': 55898, 'loss/train': 1.0077290534973145} 08/30/2021 23:16:30 - INFO - __main__ - Step 55900: {'lr': 0.0003534634763490838, 'samples': 10732800, 'steps': 55899, 'loss/train': 0.5583030581474304} 08/30/2021 23:16:30 - INFO - __main__ - Step 55901: {'lr': 0.0003534586453665517, 'samples': 10732992, 'steps': 55900, 'loss/train': 1.0922681093215942} 08/30/2021 23:16:30 - INFO - __main__ - Step 55902: {'lr': 0.00035345381433740273, 'samples': 10733184, 'steps': 55901, 'loss/train': 1.7224851846694946} 08/30/2021 23:16:32 - INFO - __main__ - Step 55903: {'lr': 0.00035344898326163907, 'samples': 10733376, 'steps': 55902, 'loss/train': 1.4505985975265503} 08/30/2021 23:16:33 - INFO - __main__ - Step 55904: {'lr': 0.00035344415213926284, 'samples': 10733568, 'steps': 55903, 'loss/train': 0.9378485679626465} 08/30/2021 23:16:33 - INFO - __main__ - Step 55905: {'lr': 0.0003534393209702764, 'samples': 10733760, 'steps': 55904, 'loss/train': 0.7283466458320618} 08/30/2021 23:16:33 - INFO - __main__ - Step 55906: {'lr': 0.0003534344897546816, 'samples': 10733952, 'steps': 55905, 'loss/train': 0.4423246681690216} 08/30/2021 23:16:34 - INFO - __main__ - Step 55907: {'lr': 0.00035342965849248097, 'samples': 10734144, 'steps': 55906, 'loss/train': 1.1748298406600952} 08/30/2021 23:16:35 - INFO - __main__ - Step 55908: {'lr': 0.00035342482718367645, 'samples': 10734336, 'steps': 55907, 'loss/train': 1.6168564558029175} 08/30/2021 23:16:36 - INFO - __main__ - Step 55909: {'lr': 0.0003534199958282703, 'samples': 10734528, 'steps': 55908, 'loss/train': 1.5999308824539185} 08/30/2021 23:16:36 - INFO - __main__ - Step 55910: {'lr': 0.00035341516442626475, 'samples': 10734720, 'steps': 55909, 'loss/train': 1.3619261980056763} 08/30/2021 23:16:37 - INFO - __main__ - Step 55911: {'lr': 0.0003534103329776619, 'samples': 10734912, 'steps': 55910, 'loss/train': 0.03599366545677185} 08/30/2021 23:16:37 - INFO - __main__ - Step 55912: {'lr': 0.000353405501482464, 'samples': 10735104, 'steps': 55911, 'loss/train': 1.2787939310073853} 08/30/2021 23:16:37 - INFO - __main__ - Step 55913: {'lr': 0.0003534006699406731, 'samples': 10735296, 'steps': 55912, 'loss/train': 1.267722725868225} 08/30/2021 23:16:38 - INFO - __main__ - Step 55914: {'lr': 0.0003533958383522915, 'samples': 10735488, 'steps': 55913, 'loss/train': 0.19397404789924622} 08/30/2021 23:16:40 - INFO - __main__ - Step 55915: {'lr': 0.0003533910067173213, 'samples': 10735680, 'steps': 55914, 'loss/train': 1.641342282295227} 08/30/2021 23:16:40 - INFO - __main__ - Step 55916: {'lr': 0.0003533861750357647, 'samples': 10735872, 'steps': 55915, 'loss/train': 1.713496208190918} 08/30/2021 23:16:40 - INFO - __main__ - Step 55917: {'lr': 0.0003533813433076239, 'samples': 10736064, 'steps': 55916, 'loss/train': 1.640536904335022} 08/30/2021 23:16:41 - INFO - __main__ - Step 55918: {'lr': 0.00035337651153290113, 'samples': 10736256, 'steps': 55917, 'loss/train': 1.3281631469726562} 08/30/2021 23:16:41 - INFO - __main__ - Step 55919: {'lr': 0.00035337167971159837, 'samples': 10736448, 'steps': 55918, 'loss/train': 1.2087630033493042} 08/30/2021 23:16:43 - INFO - __main__ - Step 55920: {'lr': 0.000353366847843718, 'samples': 10736640, 'steps': 55919, 'loss/train': 1.74284827709198} 08/30/2021 23:16:43 - INFO - __main__ - Step 55921: {'lr': 0.0003533620159292621, 'samples': 10736832, 'steps': 55920, 'loss/train': 1.6198315620422363} 08/30/2021 23:16:44 - INFO - __main__ - Step 55922: {'lr': 0.0003533571839682329, 'samples': 10737024, 'steps': 55921, 'loss/train': 1.3473113775253296} 08/30/2021 23:16:44 - INFO - __main__ - Step 55923: {'lr': 0.00035335235196063254, 'samples': 10737216, 'steps': 55922, 'loss/train': 3.014082431793213} 08/30/2021 23:16:44 - INFO - __main__ - Step 55924: {'lr': 0.0003533475199064632, 'samples': 10737408, 'steps': 55923, 'loss/train': 0.45372748374938965} 08/30/2021 23:16:46 - INFO - __main__ - Step 55925: {'lr': 0.00035334268780572707, 'samples': 10737600, 'steps': 55924, 'loss/train': 1.1645843982696533} 08/30/2021 23:16:47 - INFO - __main__ - Step 55926: {'lr': 0.0003533378556584263, 'samples': 10737792, 'steps': 55925, 'loss/train': 1.228293776512146} 08/30/2021 23:16:47 - INFO - __main__ - Step 55927: {'lr': 0.0003533330234645631, 'samples': 10737984, 'steps': 55926, 'loss/train': 1.7800734043121338} 08/30/2021 23:16:47 - INFO - __main__ - Step 55928: {'lr': 0.00035332819122413963, 'samples': 10738176, 'steps': 55927, 'loss/train': 0.6804536581039429} 08/30/2021 23:16:48 - INFO - __main__ - Step 55929: {'lr': 0.00035332335893715805, 'samples': 10738368, 'steps': 55928, 'loss/train': 1.5049625635147095} 08/30/2021 23:16:48 - INFO - __main__ - Step 55930: {'lr': 0.00035331852660362055, 'samples': 10738560, 'steps': 55929, 'loss/train': 0.024609217420220375} 08/30/2021 23:16:50 - INFO - __main__ - Step 55931: {'lr': 0.00035331369422352937, 'samples': 10738752, 'steps': 55930, 'loss/train': 1.2362762689590454} 08/30/2021 23:16:50 - INFO - __main__ - Step 55932: {'lr': 0.00035330886179688666, 'samples': 10738944, 'steps': 55931, 'loss/train': 1.341709852218628} 08/30/2021 23:16:50 - INFO - __main__ - Step 55933: {'lr': 0.0003533040293236945, 'samples': 10739136, 'steps': 55932, 'loss/train': 1.4676406383514404} 08/30/2021 23:16:51 - INFO - __main__ - Step 55934: {'lr': 0.0003532991968039552, 'samples': 10739328, 'steps': 55933, 'loss/train': 1.3624273538589478} 08/30/2021 23:16:51 - INFO - __main__ - Step 55935: {'lr': 0.0003532943642376708, 'samples': 10739520, 'steps': 55934, 'loss/train': 1.358296275138855} 08/30/2021 23:16:53 - INFO - __main__ - Step 55936: {'lr': 0.00035328953162484355, 'samples': 10739712, 'steps': 55935, 'loss/train': 1.3077239990234375} 08/30/2021 23:16:53 - INFO - __main__ - Step 55937: {'lr': 0.00035328469896547566, 'samples': 10739904, 'steps': 55936, 'loss/train': 1.3262988328933716} 08/30/2021 23:16:53 - INFO - __main__ - Step 55938: {'lr': 0.0003532798662595693, 'samples': 10740096, 'steps': 55937, 'loss/train': 1.6996756792068481} 08/30/2021 23:16:54 - INFO - __main__ - Step 55939: {'lr': 0.00035327503350712666, 'samples': 10740288, 'steps': 55938, 'loss/train': 1.3272464275360107} 08/30/2021 23:16:54 - INFO - __main__ - Step 55940: {'lr': 0.0003532702007081498, 'samples': 10740480, 'steps': 55939, 'loss/train': 1.7512575387954712} 08/30/2021 23:16:54 - INFO - __main__ - Step 55941: {'lr': 0.000353265367862641, 'samples': 10740672, 'steps': 55940, 'loss/train': 1.2952749729156494} 08/30/2021 23:16:56 - INFO - __main__ - Step 55942: {'lr': 0.0003532605349706025, 'samples': 10740864, 'steps': 55941, 'loss/train': 1.7662429809570312} 08/30/2021 23:16:56 - INFO - __main__ - Step 55943: {'lr': 0.00035325570203203626, 'samples': 10741056, 'steps': 55942, 'loss/train': 1.521077036857605} 08/30/2021 23:16:57 - INFO - __main__ - Step 55944: {'lr': 0.0003532508690469447, 'samples': 10741248, 'steps': 55943, 'loss/train': 0.4328659474849701} 08/30/2021 23:16:57 - INFO - __main__ - Step 55945: {'lr': 0.0003532460360153299, 'samples': 10741440, 'steps': 55944, 'loss/train': 2.03222918510437} 08/30/2021 23:16:57 - INFO - __main__ - Step 55946: {'lr': 0.000353241202937194, 'samples': 10741632, 'steps': 55945, 'loss/train': 0.24276189506053925} 08/30/2021 23:16:59 - INFO - __main__ - Step 55947: {'lr': 0.00035323636981253914, 'samples': 10741824, 'steps': 55946, 'loss/train': 0.6861918568611145} 08/30/2021 23:16:59 - INFO - __main__ - Step 55948: {'lr': 0.00035323153664136765, 'samples': 10742016, 'steps': 55947, 'loss/train': 0.6402886509895325} 08/30/2021 23:17:00 - INFO - __main__ - Step 55949: {'lr': 0.00035322670342368155, 'samples': 10742208, 'steps': 55948, 'loss/train': 0.5976836681365967} 08/30/2021 23:17:00 - INFO - __main__ - Step 55950: {'lr': 0.0003532218701594832, 'samples': 10742400, 'steps': 55949, 'loss/train': 1.0029876232147217} 08/30/2021 23:17:00 - INFO - __main__ - Step 55951: {'lr': 0.0003532170368487746, 'samples': 10742592, 'steps': 55950, 'loss/train': 1.2363777160644531} 08/30/2021 23:17:01 - INFO - __main__ - Step 55952: {'lr': 0.00035321220349155796, 'samples': 10742784, 'steps': 55951, 'loss/train': 1.3930597305297852} 08/30/2021 23:17:02 - INFO - __main__ - Step 55953: {'lr': 0.00035320737008783556, 'samples': 10742976, 'steps': 55952, 'loss/train': 1.1704849004745483} 08/30/2021 23:17:03 - INFO - __main__ - Step 55954: {'lr': 0.0003532025366376095, 'samples': 10743168, 'steps': 55953, 'loss/train': 1.309885859489441} 08/30/2021 23:17:03 - INFO - __main__ - Step 55955: {'lr': 0.0003531977031408819, 'samples': 10743360, 'steps': 55954, 'loss/train': 0.8559950590133667} 08/30/2021 23:17:03 - INFO - __main__ - Step 55956: {'lr': 0.0003531928695976551, 'samples': 10743552, 'steps': 55955, 'loss/train': 0.036718856543302536} 08/30/2021 23:17:04 - INFO - __main__ - Step 55957: {'lr': 0.00035318803600793117, 'samples': 10743744, 'steps': 55956, 'loss/train': 1.1626948118209839} 08/30/2021 23:17:05 - INFO - __main__ - Step 55958: {'lr': 0.00035318320237171224, 'samples': 10743936, 'steps': 55957, 'loss/train': 1.7497190237045288} 08/30/2021 23:17:06 - INFO - __main__ - Step 55959: {'lr': 0.0003531783686890006, 'samples': 10744128, 'steps': 55958, 'loss/train': 1.4779517650604248} 08/30/2021 23:17:06 - INFO - __main__ - Step 55960: {'lr': 0.0003531735349597984, 'samples': 10744320, 'steps': 55959, 'loss/train': 1.5500249862670898} 08/30/2021 23:17:06 - INFO - __main__ - Step 55961: {'lr': 0.0003531687011841077, 'samples': 10744512, 'steps': 55960, 'loss/train': 1.1005122661590576} 08/30/2021 23:17:07 - INFO - __main__ - Step 55962: {'lr': 0.0003531638673619309, 'samples': 10744704, 'steps': 55961, 'loss/train': 2.1470508575439453} 08/30/2021 23:17:08 - INFO - __main__ - Step 55963: {'lr': 0.00035315903349327, 'samples': 10744896, 'steps': 55962, 'loss/train': 4.586358070373535} 08/30/2021 23:17:09 - INFO - __main__ - Step 55964: {'lr': 0.00035315419957812725, 'samples': 10745088, 'steps': 55963, 'loss/train': 1.56167733669281} 08/30/2021 23:17:09 - INFO - __main__ - Step 55965: {'lr': 0.0003531493656165047, 'samples': 10745280, 'steps': 55964, 'loss/train': 1.7028981447219849} 08/30/2021 23:17:10 - INFO - __main__ - Step 55966: {'lr': 0.00035314453160840476, 'samples': 10745472, 'steps': 55965, 'loss/train': 1.1989740133285522} 08/30/2021 23:17:10 - INFO - __main__ - Step 55967: {'lr': 0.00035313969755382946, 'samples': 10745664, 'steps': 55966, 'loss/train': 1.065708875656128} 08/30/2021 23:17:11 - INFO - __main__ - Step 55968: {'lr': 0.000353134863452781, 'samples': 10745856, 'steps': 55967, 'loss/train': 0.7986748814582825} 08/30/2021 23:17:12 - INFO - __main__ - Step 55969: {'lr': 0.00035313002930526156, 'samples': 10746048, 'steps': 55968, 'loss/train': 1.3339710235595703} 08/30/2021 23:17:12 - INFO - __main__ - Step 55970: {'lr': 0.00035312519511127325, 'samples': 10746240, 'steps': 55969, 'loss/train': 0.46650388836860657} 08/30/2021 23:17:13 - INFO - __main__ - Step 55971: {'lr': 0.0003531203608708184, 'samples': 10746432, 'steps': 55970, 'loss/train': 1.0030601024627686} 08/30/2021 23:17:13 - INFO - __main__ - Step 55972: {'lr': 0.00035311552658389914, 'samples': 10746624, 'steps': 55971, 'loss/train': 0.7478862404823303} 08/30/2021 23:17:13 - INFO - __main__ - Step 55973: {'lr': 0.00035311069225051755, 'samples': 10746816, 'steps': 55972, 'loss/train': 1.30539870262146} 08/30/2021 23:17:15 - INFO - __main__ - Step 55974: {'lr': 0.0003531058578706759, 'samples': 10747008, 'steps': 55973, 'loss/train': 1.0208511352539062} 08/30/2021 23:17:16 - INFO - __main__ - Step 55975: {'lr': 0.00035310102344437636, 'samples': 10747200, 'steps': 55974, 'loss/train': 2.058894634246826} 08/30/2021 23:17:16 - INFO - __main__ - Step 55976: {'lr': 0.00035309618897162097, 'samples': 10747392, 'steps': 55975, 'loss/train': 1.3556779623031616} 08/30/2021 23:17:17 - INFO - __main__ - Step 55977: {'lr': 0.0003530913544524121, 'samples': 10747584, 'steps': 55976, 'loss/train': 1.1167582273483276} 08/30/2021 23:17:17 - INFO - __main__ - Step 55978: {'lr': 0.00035308651988675194, 'samples': 10747776, 'steps': 55977, 'loss/train': 0.8025023937225342} 08/30/2021 23:17:19 - INFO - __main__ - Step 55979: {'lr': 0.0003530816852746426, 'samples': 10747968, 'steps': 55978, 'loss/train': 1.558971881866455} 08/30/2021 23:17:19 - INFO - __main__ - Step 55980: {'lr': 0.00035307685061608605, 'samples': 10748160, 'steps': 55979, 'loss/train': 2.797186851501465} 08/30/2021 23:17:19 - INFO - __main__ - Step 55981: {'lr': 0.00035307201591108485, 'samples': 10748352, 'steps': 55980, 'loss/train': 0.6650704145431519} 08/30/2021 23:17:20 - INFO - __main__ - Step 55982: {'lr': 0.0003530671811596409, 'samples': 10748544, 'steps': 55981, 'loss/train': 0.13816869258880615} 08/30/2021 23:17:20 - INFO - __main__ - Step 55983: {'lr': 0.00035306234636175646, 'samples': 10748736, 'steps': 55982, 'loss/train': 0.6538945436477661} 08/30/2021 23:17:20 - INFO - __main__ - Step 55984: {'lr': 0.0003530575115174337, 'samples': 10748928, 'steps': 55983, 'loss/train': 0.9080739617347717} 08/30/2021 23:17:22 - INFO - __main__ - Step 55985: {'lr': 0.00035305267662667485, 'samples': 10749120, 'steps': 55984, 'loss/train': 5.056089401245117} 08/30/2021 23:17:23 - INFO - __main__ - Step 55986: {'lr': 0.0003530478416894821, 'samples': 10749312, 'steps': 55985, 'loss/train': 1.0960655212402344} 08/30/2021 23:17:23 - INFO - __main__ - Step 55987: {'lr': 0.00035304300670585754, 'samples': 10749504, 'steps': 55986, 'loss/train': 1.725856900215149} 08/30/2021 23:17:23 - INFO - __main__ - Step 55988: {'lr': 0.0003530381716758034, 'samples': 10749696, 'steps': 55987, 'loss/train': 1.5876543521881104} 08/30/2021 23:17:24 - INFO - __main__ - Step 55989: {'lr': 0.00035303333659932187, 'samples': 10749888, 'steps': 55988, 'loss/train': 1.1360228061676025} 08/30/2021 23:17:25 - INFO - __main__ - Step 55990: {'lr': 0.000353028501476415, 'samples': 10750080, 'steps': 55989, 'loss/train': 1.5563544034957886} 08/30/2021 23:17:26 - INFO - __main__ - Step 55991: {'lr': 0.0003530236663070852, 'samples': 10750272, 'steps': 55990, 'loss/train': 1.1620291471481323} 08/30/2021 23:17:26 - INFO - __main__ - Step 55992: {'lr': 0.00035301883109133456, 'samples': 10750464, 'steps': 55991, 'loss/train': 0.83155357837677} 08/30/2021 23:17:26 - INFO - __main__ - Step 55993: {'lr': 0.0003530139958291651, 'samples': 10750656, 'steps': 55992, 'loss/train': 0.9680225849151611} 08/30/2021 23:17:27 - INFO - __main__ - Step 55994: {'lr': 0.0003530091605205792, 'samples': 10750848, 'steps': 55993, 'loss/train': 1.6920452117919922} 08/30/2021 23:17:28 - INFO - __main__ - Step 55995: {'lr': 0.0003530043251655789, 'samples': 10751040, 'steps': 55994, 'loss/train': 1.4270563125610352} 08/30/2021 23:17:29 - INFO - __main__ - Step 55996: {'lr': 0.00035299948976416645, 'samples': 10751232, 'steps': 55995, 'loss/train': 1.6408499479293823} 08/30/2021 23:17:29 - INFO - __main__ - Step 55997: {'lr': 0.00035299465431634403, 'samples': 10751424, 'steps': 55996, 'loss/train': 1.7302969694137573} 08/30/2021 23:17:29 - INFO - __main__ - Step 55998: {'lr': 0.00035298981882211385, 'samples': 10751616, 'steps': 55997, 'loss/train': 1.7459830045700073} 08/30/2021 23:17:30 - INFO - __main__ - Step 55999: {'lr': 0.00035298498328147803, 'samples': 10751808, 'steps': 55998, 'loss/train': 1.2702487707138062} 08/30/2021 23:17:31 - INFO - __main__ - Step 56000: {'lr': 0.00035298014769443874, 'samples': 10752000, 'steps': 55999, 'loss/train': 2.059731960296631} 08/30/2021 23:17:32 - INFO - __main__ - Step 56001: {'lr': 0.0003529753120609982, 'samples': 10752192, 'steps': 56000, 'loss/train': 1.4488636255264282} 08/30/2021 23:17:32 - INFO - __main__ - Step 56002: {'lr': 0.0003529704763811585, 'samples': 10752384, 'steps': 56001, 'loss/train': 2.2082808017730713} 08/30/2021 23:17:32 - INFO - __main__ - Step 56003: {'lr': 0.000352965640654922, 'samples': 10752576, 'steps': 56002, 'loss/train': 0.9415165781974792} 08/30/2021 23:17:33 - INFO - __main__ - Step 56004: {'lr': 0.0003529608048822908, 'samples': 10752768, 'steps': 56003, 'loss/train': 1.3292121887207031} 08/30/2021 23:17:34 - INFO - __main__ - Step 56005: {'lr': 0.0003529559690632669, 'samples': 10752960, 'steps': 56004, 'loss/train': 1.4700969457626343} 08/30/2021 23:17:35 - INFO - __main__ - Step 56006: {'lr': 0.00035295113319785276, 'samples': 10753152, 'steps': 56005, 'loss/train': 1.6381988525390625} 08/30/2021 23:17:35 - INFO - __main__ - Step 56007: {'lr': 0.0003529462972860504, 'samples': 10753344, 'steps': 56006, 'loss/train': 1.5033495426177979} 08/30/2021 23:17:35 - INFO - __main__ - Step 56008: {'lr': 0.000352941461327862, 'samples': 10753536, 'steps': 56007, 'loss/train': 1.196776270866394} 08/30/2021 23:17:36 - INFO - __main__ - Step 56009: {'lr': 0.0003529366253232897, 'samples': 10753728, 'steps': 56008, 'loss/train': 1.2818739414215088} 08/30/2021 23:17:37 - INFO - __main__ - Step 56010: {'lr': 0.00035293178927233587, 'samples': 10753920, 'steps': 56009, 'loss/train': 0.7002621293067932} 08/30/2021 23:17:38 - INFO - __main__ - Step 56011: {'lr': 0.0003529269531750025, 'samples': 10754112, 'steps': 56010, 'loss/train': 0.8729087114334106} 08/30/2021 23:17:38 - INFO - __main__ - Step 56012: {'lr': 0.0003529221170312919, 'samples': 10754304, 'steps': 56011, 'loss/train': 1.4013751745224} 08/30/2021 23:17:39 - INFO - __main__ - Step 56013: {'lr': 0.0003529172808412061, 'samples': 10754496, 'steps': 56012, 'loss/train': 1.402565836906433} 08/30/2021 23:17:39 - INFO - __main__ - Step 56014: {'lr': 0.0003529124446047474, 'samples': 10754688, 'steps': 56013, 'loss/train': 1.1653759479522705} 08/30/2021 23:17:39 - INFO - __main__ - Step 56015: {'lr': 0.0003529076083219179, 'samples': 10754880, 'steps': 56014, 'loss/train': 0.6954762935638428} 08/30/2021 23:17:41 - INFO - __main__ - Step 56016: {'lr': 0.0003529027719927199, 'samples': 10755072, 'steps': 56015, 'loss/train': 1.5562806129455566} 08/30/2021 23:17:41 - INFO - __main__ - Step 56017: {'lr': 0.00035289793561715544, 'samples': 10755264, 'steps': 56016, 'loss/train': 1.1072672605514526} 08/30/2021 23:17:42 - INFO - __main__ - Step 56018: {'lr': 0.0003528930991952267, 'samples': 10755456, 'steps': 56017, 'loss/train': 1.633586049079895} 08/30/2021 23:17:42 - INFO - __main__ - Step 56019: {'lr': 0.00035288826272693606, 'samples': 10755648, 'steps': 56018, 'loss/train': 1.2012773752212524} 08/30/2021 23:17:42 - INFO - __main__ - Step 56020: {'lr': 0.0003528834262122855, 'samples': 10755840, 'steps': 56019, 'loss/train': 1.118121862411499} 08/30/2021 23:17:44 - INFO - __main__ - Step 56021: {'lr': 0.00035287858965127723, 'samples': 10756032, 'steps': 56020, 'loss/train': 1.5564519166946411} 08/30/2021 23:17:44 - INFO - __main__ - Step 56022: {'lr': 0.00035287375304391343, 'samples': 10756224, 'steps': 56021, 'loss/train': 1.4478741884231567} 08/30/2021 23:17:45 - INFO - __main__ - Step 56023: {'lr': 0.00035286891639019636, 'samples': 10756416, 'steps': 56022, 'loss/train': 1.6184475421905518} 08/30/2021 23:17:45 - INFO - __main__ - Step 56024: {'lr': 0.00035286407969012813, 'samples': 10756608, 'steps': 56023, 'loss/train': 0.6426447629928589} 08/30/2021 23:17:45 - INFO - __main__ - Step 56025: {'lr': 0.00035285924294371085, 'samples': 10756800, 'steps': 56024, 'loss/train': 1.3158751726150513} 08/30/2021 23:17:47 - INFO - __main__ - Step 56026: {'lr': 0.00035285440615094696, 'samples': 10756992, 'steps': 56025, 'loss/train': 1.6479753255844116} 08/30/2021 23:17:48 - INFO - __main__ - Step 56027: {'lr': 0.0003528495693118383, 'samples': 10757184, 'steps': 56026, 'loss/train': 1.2189514636993408} 08/30/2021 23:17:48 - INFO - __main__ - Step 56028: {'lr': 0.0003528447324263873, 'samples': 10757376, 'steps': 56027, 'loss/train': 1.6366844177246094} 08/30/2021 23:17:48 - INFO - __main__ - Step 56029: {'lr': 0.000352839895494596, 'samples': 10757568, 'steps': 56028, 'loss/train': 1.5302352905273438} 08/30/2021 23:17:49 - INFO - __main__ - Step 56030: {'lr': 0.00035283505851646665, 'samples': 10757760, 'steps': 56029, 'loss/train': 1.88230562210083} 08/30/2021 23:17:50 - INFO - __main__ - Step 56031: {'lr': 0.0003528302214920014, 'samples': 10757952, 'steps': 56030, 'loss/train': 1.1060776710510254} 08/30/2021 23:17:51 - INFO - __main__ - Step 56032: {'lr': 0.0003528253844212024, 'samples': 10758144, 'steps': 56031, 'loss/train': 1.2878245115280151} 08/30/2021 23:17:51 - INFO - __main__ - Step 56033: {'lr': 0.00035282054730407196, 'samples': 10758336, 'steps': 56032, 'loss/train': 1.1769263744354248} 08/30/2021 23:17:51 - INFO - __main__ - Step 56034: {'lr': 0.00035281571014061214, 'samples': 10758528, 'steps': 56033, 'loss/train': 1.1614952087402344} 08/30/2021 23:17:52 - INFO - __main__ - Step 56035: {'lr': 0.0003528108729308251, 'samples': 10758720, 'steps': 56034, 'loss/train': 1.446807622909546} 08/30/2021 23:17:53 - INFO - __main__ - Step 56036: {'lr': 0.0003528060356747131, 'samples': 10758912, 'steps': 56035, 'loss/train': 1.337592363357544} 08/30/2021 23:17:54 - INFO - __main__ - Step 56037: {'lr': 0.0003528011983722783, 'samples': 10759104, 'steps': 56036, 'loss/train': 0.8057197332382202} 08/30/2021 23:17:54 - INFO - __main__ - Step 56038: {'lr': 0.0003527963610235229, 'samples': 10759296, 'steps': 56037, 'loss/train': 1.2137131690979004} 08/30/2021 23:17:55 - INFO - __main__ - Step 56039: {'lr': 0.000352791523628449, 'samples': 10759488, 'steps': 56038, 'loss/train': 1.5632894039154053} 08/30/2021 23:17:55 - INFO - __main__ - Step 56040: {'lr': 0.0003527866861870588, 'samples': 10759680, 'steps': 56039, 'loss/train': 1.262122392654419} 08/30/2021 23:17:55 - INFO - __main__ - Step 56041: {'lr': 0.00035278184869935454, 'samples': 10759872, 'steps': 56040, 'loss/train': 1.5366052389144897} 08/30/2021 23:17:57 - INFO - __main__ - Step 56042: {'lr': 0.0003527770111653383, 'samples': 10760064, 'steps': 56041, 'loss/train': 0.9623920917510986} 08/30/2021 23:17:58 - INFO - __main__ - Step 56043: {'lr': 0.0003527721735850124, 'samples': 10760256, 'steps': 56042, 'loss/train': 1.455899715423584} 08/30/2021 23:17:58 - INFO - __main__ - Step 56044: {'lr': 0.0003527673359583789, 'samples': 10760448, 'steps': 56043, 'loss/train': 0.3491433560848236} 08/30/2021 23:17:59 - INFO - __main__ - Step 56045: {'lr': 0.00035276249828544004, 'samples': 10760640, 'steps': 56044, 'loss/train': 1.0315723419189453} 08/30/2021 23:17:59 - INFO - __main__ - Step 56046: {'lr': 0.0003527576605661981, 'samples': 10760832, 'steps': 56045, 'loss/train': 1.898078441619873} 08/30/2021 23:17:59 - INFO - __main__ - Step 56047: {'lr': 0.00035275282280065493, 'samples': 10761024, 'steps': 56046, 'loss/train': 0.8580057621002197} 08/30/2021 23:18:01 - INFO - __main__ - Step 56048: {'lr': 0.00035274798498881305, 'samples': 10761216, 'steps': 56047, 'loss/train': 0.8985004425048828} 08/30/2021 23:18:01 - INFO - __main__ - Step 56049: {'lr': 0.00035274314713067454, 'samples': 10761408, 'steps': 56048, 'loss/train': 1.4637941122055054} 08/30/2021 23:18:02 - INFO - __main__ - Step 56050: {'lr': 0.00035273830922624147, 'samples': 10761600, 'steps': 56049, 'loss/train': 1.1327402591705322} 08/30/2021 23:18:02 - INFO - __main__ - Step 56051: {'lr': 0.00035273347127551616, 'samples': 10761792, 'steps': 56050, 'loss/train': 1.7856755256652832} 08/30/2021 23:18:02 - INFO - __main__ - Step 56052: {'lr': 0.00035272863327850067, 'samples': 10761984, 'steps': 56051, 'loss/train': 1.7522681951522827} 08/30/2021 23:18:03 - INFO - __main__ - Step 56053: {'lr': 0.00035272379523519734, 'samples': 10762176, 'steps': 56052, 'loss/train': 1.6141204833984375} 08/30/2021 23:18:04 - INFO - __main__ - Step 56054: {'lr': 0.0003527189571456082, 'samples': 10762368, 'steps': 56053, 'loss/train': 1.451524257659912} 08/30/2021 23:18:05 - INFO - __main__ - Step 56055: {'lr': 0.00035271411900973545, 'samples': 10762560, 'steps': 56054, 'loss/train': 1.6046028137207031} 08/30/2021 23:18:05 - INFO - __main__ - Step 56056: {'lr': 0.00035270928082758134, 'samples': 10762752, 'steps': 56055, 'loss/train': 1.204519510269165} 08/30/2021 23:18:05 - INFO - __main__ - Step 56057: {'lr': 0.00035270444259914794, 'samples': 10762944, 'steps': 56056, 'loss/train': 1.9650378227233887} 08/30/2021 23:18:06 - INFO - __main__ - Step 56058: {'lr': 0.0003526996043244376, 'samples': 10763136, 'steps': 56057, 'loss/train': 1.672080397605896} 08/30/2021 23:18:07 - INFO - __main__ - Step 56059: {'lr': 0.0003526947660034524, 'samples': 10763328, 'steps': 56058, 'loss/train': 0.6025868058204651} 08/30/2021 23:18:08 - INFO - __main__ - Step 56060: {'lr': 0.0003526899276361945, 'samples': 10763520, 'steps': 56059, 'loss/train': 1.8122081756591797} 08/30/2021 23:18:08 - INFO - __main__ - Step 56061: {'lr': 0.00035268508922266614, 'samples': 10763712, 'steps': 56060, 'loss/train': 1.5484557151794434} 08/30/2021 23:18:09 - INFO - __main__ - Step 56062: {'lr': 0.00035268025076286936, 'samples': 10763904, 'steps': 56061, 'loss/train': 1.7149593830108643} 08/30/2021 23:18:09 - INFO - __main__ - Step 56063: {'lr': 0.00035267541225680654, 'samples': 10764096, 'steps': 56062, 'loss/train': 1.268869400024414} 08/30/2021 23:18:10 - INFO - __main__ - Step 56064: {'lr': 0.00035267057370447967, 'samples': 10764288, 'steps': 56063, 'loss/train': 1.5896377563476562} 08/30/2021 23:18:11 - INFO - __main__ - Step 56065: {'lr': 0.00035266573510589114, 'samples': 10764480, 'steps': 56064, 'loss/train': 0.9475966095924377} 08/30/2021 23:18:11 - INFO - __main__ - Step 56066: {'lr': 0.00035266089646104296, 'samples': 10764672, 'steps': 56065, 'loss/train': 1.5359894037246704} 08/30/2021 23:18:12 - INFO - __main__ - Step 56067: {'lr': 0.00035265605776993735, 'samples': 10764864, 'steps': 56066, 'loss/train': 1.6587549448013306} 08/30/2021 23:18:12 - INFO - __main__ - Step 56068: {'lr': 0.0003526512190325765, 'samples': 10765056, 'steps': 56067, 'loss/train': 0.628121554851532} 08/30/2021 23:18:14 - INFO - __main__ - Step 56069: {'lr': 0.0003526463802489626, 'samples': 10765248, 'steps': 56068, 'loss/train': 1.3799668550491333} 08/30/2021 23:18:14 - INFO - __main__ - Step 56070: {'lr': 0.00035264154141909787, 'samples': 10765440, 'steps': 56069, 'loss/train': 1.812149167060852} 08/30/2021 23:18:15 - INFO - __main__ - Step 56071: {'lr': 0.00035263670254298443, 'samples': 10765632, 'steps': 56070, 'loss/train': 1.2185698747634888} 08/30/2021 23:18:15 - INFO - __main__ - Step 56072: {'lr': 0.0003526318636206244, 'samples': 10765824, 'steps': 56071, 'loss/train': 1.196087121963501} 08/30/2021 23:18:15 - INFO - __main__ - Step 56073: {'lr': 0.0003526270246520201, 'samples': 10766016, 'steps': 56072, 'loss/train': 1.5084068775177002} 08/30/2021 23:18:17 - INFO - __main__ - Step 56074: {'lr': 0.0003526221856371737, 'samples': 10766208, 'steps': 56073, 'loss/train': 0.15835455060005188} 08/30/2021 23:18:17 - INFO - __main__ - Step 56075: {'lr': 0.0003526173465760872, 'samples': 10766400, 'steps': 56074, 'loss/train': 1.6262229681015015} 08/30/2021 23:18:18 - INFO - __main__ - Step 56076: {'lr': 0.000352612507468763, 'samples': 10766592, 'steps': 56075, 'loss/train': 0.9375470876693726} 08/30/2021 23:18:18 - INFO - __main__ - Step 56077: {'lr': 0.00035260766831520315, 'samples': 10766784, 'steps': 56076, 'loss/train': 1.4606602191925049} 08/30/2021 23:18:18 - INFO - __main__ - Step 56078: {'lr': 0.0003526028291154099, 'samples': 10766976, 'steps': 56077, 'loss/train': 1.2322391271591187} 08/30/2021 23:18:19 - INFO - __main__ - Step 56079: {'lr': 0.00035259798986938537, 'samples': 10767168, 'steps': 56078, 'loss/train': 1.2986236810684204} 08/30/2021 23:18:21 - INFO - __main__ - Step 56080: {'lr': 0.00035259315057713177, 'samples': 10767360, 'steps': 56079, 'loss/train': 1.610724925994873} 08/30/2021 23:18:22 - INFO - __main__ - Step 56081: {'lr': 0.0003525883112386513, 'samples': 10767552, 'steps': 56080, 'loss/train': 0.18006126582622528} 08/30/2021 23:18:22 - INFO - __main__ - Step 56082: {'lr': 0.00035258347185394606, 'samples': 10767744, 'steps': 56081, 'loss/train': 1.3237583637237549} 08/30/2021 23:18:22 - INFO - __main__ - Step 56083: {'lr': 0.00035257863242301834, 'samples': 10767936, 'steps': 56082, 'loss/train': 1.254301905632019} 08/30/2021 23:18:23 - INFO - __main__ - Step 56084: {'lr': 0.0003525737929458703, 'samples': 10768128, 'steps': 56083, 'loss/train': 1.6901192665100098} 08/30/2021 23:18:24 - INFO - __main__ - Step 56085: {'lr': 0.0003525689534225041, 'samples': 10768320, 'steps': 56084, 'loss/train': 0.5801014304161072} 08/30/2021 23:18:25 - INFO - __main__ - Step 56086: {'lr': 0.00035256411385292186, 'samples': 10768512, 'steps': 56085, 'loss/train': 0.875618040561676} 08/30/2021 23:18:25 - INFO - __main__ - Step 56087: {'lr': 0.0003525592742371258, 'samples': 10768704, 'steps': 56086, 'loss/train': 1.3801052570343018} 08/30/2021 23:18:25 - INFO - __main__ - Step 56088: {'lr': 0.0003525544345751182, 'samples': 10768896, 'steps': 56087, 'loss/train': 1.2382384538650513} 08/30/2021 23:18:26 - INFO - __main__ - Step 56089: {'lr': 0.00035254959486690103, 'samples': 10769088, 'steps': 56088, 'loss/train': 1.844489336013794} 08/30/2021 23:18:28 - INFO - __main__ - Step 56090: {'lr': 0.0003525447551124766, 'samples': 10769280, 'steps': 56089, 'loss/train': 1.1721967458724976} 08/30/2021 23:18:28 - INFO - __main__ - Step 56091: {'lr': 0.0003525399153118472, 'samples': 10769472, 'steps': 56090, 'loss/train': 1.5204496383666992} 08/30/2021 23:18:28 - INFO - __main__ - Step 56092: {'lr': 0.00035253507546501484, 'samples': 10769664, 'steps': 56091, 'loss/train': 1.4560885429382324} 08/30/2021 23:18:29 - INFO - __main__ - Step 56093: {'lr': 0.0003525302355719818, 'samples': 10769856, 'steps': 56092, 'loss/train': 0.09196337312459946} 08/30/2021 23:18:29 - INFO - __main__ - Step 56094: {'lr': 0.0003525253956327501, 'samples': 10770048, 'steps': 56093, 'loss/train': 1.0260504484176636} 08/30/2021 23:18:31 - INFO - __main__ - Step 56095: {'lr': 0.0003525205556473221, 'samples': 10770240, 'steps': 56094, 'loss/train': 1.2777884006500244} 08/30/2021 23:18:31 - INFO - __main__ - Step 56096: {'lr': 0.0003525157156157, 'samples': 10770432, 'steps': 56095, 'loss/train': 0.978280246257782} 08/30/2021 23:18:32 - INFO - __main__ - Step 56097: {'lr': 0.00035251087553788584, 'samples': 10770624, 'steps': 56096, 'loss/train': 0.2951096296310425} 08/30/2021 23:18:32 - INFO - __main__ - Step 56098: {'lr': 0.00035250603541388183, 'samples': 10770816, 'steps': 56097, 'loss/train': 1.4409778118133545} 08/30/2021 23:18:32 - INFO - __main__ - Step 56099: {'lr': 0.00035250119524369016, 'samples': 10771008, 'steps': 56098, 'loss/train': 1.1865261793136597} 08/30/2021 23:18:34 - INFO - __main__ - Step 56100: {'lr': 0.00035249635502731315, 'samples': 10771200, 'steps': 56099, 'loss/train': 1.577815055847168} 08/30/2021 23:18:34 - INFO - __main__ - Step 56101: {'lr': 0.0003524915147647528, 'samples': 10771392, 'steps': 56100, 'loss/train': 0.9136101603507996} 08/30/2021 23:18:35 - INFO - __main__ - Step 56102: {'lr': 0.00035248667445601133, 'samples': 10771584, 'steps': 56101, 'loss/train': 1.368881344795227} 08/30/2021 23:18:35 - INFO - __main__ - Step 56103: {'lr': 0.00035248183410109096, 'samples': 10771776, 'steps': 56102, 'loss/train': 1.2927809953689575} 08/30/2021 23:18:35 - INFO - __main__ - Step 56104: {'lr': 0.0003524769936999939, 'samples': 10771968, 'steps': 56103, 'loss/train': 1.1680505275726318} 08/30/2021 23:18:37 - INFO - __main__ - Step 56105: {'lr': 0.0003524721532527222, 'samples': 10772160, 'steps': 56104, 'loss/train': 0.5859238505363464} 08/30/2021 23:18:38 - INFO - __main__ - Step 56106: {'lr': 0.0003524673127592782, 'samples': 10772352, 'steps': 56105, 'loss/train': 1.632218837738037} 08/30/2021 23:18:38 - INFO - __main__ - Step 56107: {'lr': 0.000352462472219664, 'samples': 10772544, 'steps': 56106, 'loss/train': 1.3636125326156616} 08/30/2021 23:18:38 - INFO - __main__ - Step 56108: {'lr': 0.0003524576316338818, 'samples': 10772736, 'steps': 56107, 'loss/train': 1.5793567895889282} 08/30/2021 23:18:39 - INFO - __main__ - Step 56109: {'lr': 0.0003524527910019337, 'samples': 10772928, 'steps': 56108, 'loss/train': 0.7637110352516174} 08/30/2021 23:18:39 - INFO - __main__ - Step 56110: {'lr': 0.00035244795032382206, 'samples': 10773120, 'steps': 56109, 'loss/train': 1.433558702468872} 08/30/2021 23:18:41 - INFO - __main__ - Step 56111: {'lr': 0.00035244310959954886, 'samples': 10773312, 'steps': 56110, 'loss/train': 1.1827833652496338} 08/30/2021 23:18:41 - INFO - __main__ - Step 56112: {'lr': 0.0003524382688291164, 'samples': 10773504, 'steps': 56111, 'loss/train': 1.3213157653808594} 08/30/2021 23:18:41 - INFO - __main__ - Step 56113: {'lr': 0.0003524334280125269, 'samples': 10773696, 'steps': 56112, 'loss/train': 1.2803272008895874} 08/30/2021 23:18:42 - INFO - __main__ - Step 56114: {'lr': 0.0003524285871497824, 'samples': 10773888, 'steps': 56113, 'loss/train': 1.3229001760482788} 08/30/2021 23:18:42 - INFO - __main__ - Step 56115: {'lr': 0.0003524237462408852, 'samples': 10774080, 'steps': 56114, 'loss/train': 1.3458489179611206} 08/30/2021 23:18:43 - INFO - __main__ - Step 56116: {'lr': 0.0003524189052858374, 'samples': 10774272, 'steps': 56115, 'loss/train': 1.4338762760162354} 08/30/2021 23:18:44 - INFO - __main__ - Step 56117: {'lr': 0.0003524140642846413, 'samples': 10774464, 'steps': 56116, 'loss/train': 0.9339413046836853} 08/30/2021 23:18:44 - INFO - __main__ - Step 56118: {'lr': 0.0003524092232372989, 'samples': 10774656, 'steps': 56117, 'loss/train': 1.4327658414840698} 08/30/2021 23:18:45 - INFO - __main__ - Step 56119: {'lr': 0.00035240438214381253, 'samples': 10774848, 'steps': 56118, 'loss/train': 0.6079670190811157} 08/30/2021 23:18:45 - INFO - __main__ - Step 56120: {'lr': 0.00035239954100418436, 'samples': 10775040, 'steps': 56119, 'loss/train': 1.5516875982284546} 08/30/2021 23:18:47 - INFO - __main__ - Step 56121: {'lr': 0.00035239469981841656, 'samples': 10775232, 'steps': 56120, 'loss/train': 1.196666955947876} 08/30/2021 23:18:47 - INFO - __main__ - Step 56122: {'lr': 0.0003523898585865112, 'samples': 10775424, 'steps': 56121, 'loss/train': 0.13357695937156677} 08/30/2021 23:18:48 - INFO - __main__ - Step 56123: {'lr': 0.0003523850173084706, 'samples': 10775616, 'steps': 56122, 'loss/train': 0.09028620272874832} 08/30/2021 23:18:48 - INFO - __main__ - Step 56124: {'lr': 0.00035238017598429686, 'samples': 10775808, 'steps': 56123, 'loss/train': 1.5310717821121216} 08/30/2021 23:18:48 - INFO - __main__ - Step 56125: {'lr': 0.0003523753346139922, 'samples': 10776000, 'steps': 56124, 'loss/train': 0.033919867128133774} 08/30/2021 23:18:50 - INFO - __main__ - Step 56126: {'lr': 0.0003523704931975588, 'samples': 10776192, 'steps': 56125, 'loss/train': 1.2060437202453613} 08/30/2021 23:18:50 - INFO - __main__ - Step 56127: {'lr': 0.0003523656517349989, 'samples': 10776384, 'steps': 56126, 'loss/train': 0.9775595664978027} 08/30/2021 23:18:51 - INFO - __main__ - Step 56128: {'lr': 0.0003523608102263145, 'samples': 10776576, 'steps': 56127, 'loss/train': 1.4229363203048706} 08/30/2021 23:18:51 - INFO - __main__ - Step 56129: {'lr': 0.00035235596867150797, 'samples': 10776768, 'steps': 56128, 'loss/train': 1.6255919933319092} 08/30/2021 23:18:51 - INFO - __main__ - Step 56130: {'lr': 0.0003523511270705814, 'samples': 10776960, 'steps': 56129, 'loss/train': 1.526809811592102} 08/30/2021 23:18:53 - INFO - __main__ - Step 56131: {'lr': 0.000352346285423537, 'samples': 10777152, 'steps': 56130, 'loss/train': 1.7387748956680298} 08/30/2021 23:18:54 - INFO - __main__ - Step 56132: {'lr': 0.0003523414437303769, 'samples': 10777344, 'steps': 56131, 'loss/train': 1.50251042842865} 08/30/2021 23:18:54 - INFO - __main__ - Step 56133: {'lr': 0.0003523366019911035, 'samples': 10777536, 'steps': 56132, 'loss/train': 1.5491119623184204} 08/30/2021 23:18:54 - INFO - __main__ - Step 56134: {'lr': 0.00035233176020571863, 'samples': 10777728, 'steps': 56133, 'loss/train': 1.5228233337402344} 08/30/2021 23:18:55 - INFO - __main__ - Step 56135: {'lr': 0.0003523269183742246, 'samples': 10777920, 'steps': 56134, 'loss/train': 0.19605764746665955} 08/30/2021 23:18:57 - INFO - __main__ - Step 56136: {'lr': 0.0003523220764966238, 'samples': 10778112, 'steps': 56135, 'loss/train': 0.9463578462600708} 08/30/2021 23:18:57 - INFO - __main__ - Step 56137: {'lr': 0.00035231723457291816, 'samples': 10778304, 'steps': 56136, 'loss/train': 1.3300654888153076} 08/30/2021 23:18:58 - INFO - __main__ - Step 56138: {'lr': 0.00035231239260311, 'samples': 10778496, 'steps': 56137, 'loss/train': 1.4234219789505005} 08/30/2021 23:18:58 - INFO - __main__ - Step 56139: {'lr': 0.0003523075505872014, 'samples': 10778688, 'steps': 56138, 'loss/train': 1.4116520881652832} 08/30/2021 23:18:58 - INFO - __main__ - Step 56140: {'lr': 0.00035230270852519465, 'samples': 10778880, 'steps': 56139, 'loss/train': 1.6587998867034912} 08/30/2021 23:19:00 - INFO - __main__ - Step 56141: {'lr': 0.00035229786641709183, 'samples': 10779072, 'steps': 56140, 'loss/train': 1.2101954221725464} 08/30/2021 23:19:00 - INFO - __main__ - Step 56142: {'lr': 0.00035229302426289524, 'samples': 10779264, 'steps': 56141, 'loss/train': 1.4990845918655396} 08/30/2021 23:19:01 - INFO - __main__ - Step 56143: {'lr': 0.00035228818206260693, 'samples': 10779456, 'steps': 56142, 'loss/train': 0.03902850300073624} 08/30/2021 23:19:01 - INFO - __main__ - Step 56144: {'lr': 0.00035228333981622914, 'samples': 10779648, 'steps': 56143, 'loss/train': 1.2967021465301514} 08/30/2021 23:19:02 - INFO - __main__ - Step 56145: {'lr': 0.0003522784975237641, 'samples': 10779840, 'steps': 56144, 'loss/train': 2.1445465087890625} 08/30/2021 23:19:02 - INFO - __main__ - Step 56146: {'lr': 0.00035227365518521387, 'samples': 10780032, 'steps': 56145, 'loss/train': 1.4401345252990723} 08/30/2021 23:19:02 - INFO - __main__ - Step 56147: {'lr': 0.00035226881280058084, 'samples': 10780224, 'steps': 56146, 'loss/train': 2.1475000381469727} 08/30/2021 23:19:04 - INFO - __main__ - Step 56148: {'lr': 0.00035226397036986694, 'samples': 10780416, 'steps': 56147, 'loss/train': 0.6699005365371704} 08/30/2021 23:19:04 - INFO - __main__ - Step 56149: {'lr': 0.0003522591278930745, 'samples': 10780608, 'steps': 56148, 'loss/train': 1.2636817693710327} 08/30/2021 23:19:05 - INFO - __main__ - Step 56150: {'lr': 0.0003522542853702057, 'samples': 10780800, 'steps': 56149, 'loss/train': 1.2275676727294922} 08/30/2021 23:19:05 - INFO - __main__ - Step 56151: {'lr': 0.0003522494428012627, 'samples': 10780992, 'steps': 56150, 'loss/train': 1.235756754875183} 08/30/2021 23:19:05 - INFO - __main__ - Step 56152: {'lr': 0.0003522446001862476, 'samples': 10781184, 'steps': 56151, 'loss/train': 0.8936092853546143} 08/30/2021 23:19:07 - INFO - __main__ - Step 56153: {'lr': 0.00035223975752516273, 'samples': 10781376, 'steps': 56152, 'loss/train': 1.486735463142395} 08/30/2021 23:19:07 - INFO - __main__ - Step 56154: {'lr': 0.0003522349148180103, 'samples': 10781568, 'steps': 56153, 'loss/train': 1.398812174797058} 08/30/2021 23:19:08 - INFO - __main__ - Step 56155: {'lr': 0.00035223007206479226, 'samples': 10781760, 'steps': 56154, 'loss/train': 1.2574031352996826} 08/30/2021 23:19:08 - INFO - __main__ - Step 56156: {'lr': 0.00035222522926551094, 'samples': 10781952, 'steps': 56155, 'loss/train': 1.2187272310256958} 08/30/2021 23:19:08 - INFO - __main__ - Step 56157: {'lr': 0.0003522203864201685, 'samples': 10782144, 'steps': 56156, 'loss/train': 1.5818597078323364} 08/30/2021 23:19:10 - INFO - __main__ - Step 56158: {'lr': 0.00035221554352876715, 'samples': 10782336, 'steps': 56157, 'loss/train': 1.8235902786254883} 08/30/2021 23:19:10 - INFO - __main__ - Step 56159: {'lr': 0.00035221070059130913, 'samples': 10782528, 'steps': 56158, 'loss/train': 0.8171112537384033} 08/30/2021 23:19:11 - INFO - __main__ - Step 56160: {'lr': 0.0003522058576077965, 'samples': 10782720, 'steps': 56159, 'loss/train': 1.5544496774673462} 08/30/2021 23:19:11 - INFO - __main__ - Step 56161: {'lr': 0.00035220101457823143, 'samples': 10782912, 'steps': 56160, 'loss/train': 0.9186850786209106} 08/30/2021 23:19:11 - INFO - __main__ - Step 56162: {'lr': 0.0003521961715026162, 'samples': 10783104, 'steps': 56161, 'loss/train': 0.8501166105270386} 08/30/2021 23:19:13 - INFO - __main__ - Step 56163: {'lr': 0.0003521913283809529, 'samples': 10783296, 'steps': 56162, 'loss/train': 0.8954331278800964} 08/30/2021 23:19:14 - INFO - __main__ - Step 56164: {'lr': 0.00035218648521324387, 'samples': 10783488, 'steps': 56163, 'loss/train': 0.6433175206184387} 08/30/2021 23:19:14 - INFO - __main__ - Step 56165: {'lr': 0.0003521816419994911, 'samples': 10783680, 'steps': 56164, 'loss/train': 1.3150888681411743} 08/30/2021 23:19:14 - INFO - __main__ - Step 56166: {'lr': 0.0003521767987396969, 'samples': 10783872, 'steps': 56165, 'loss/train': 0.16733968257904053} 08/30/2021 23:19:15 - INFO - __main__ - Step 56167: {'lr': 0.00035217195543386345, 'samples': 10784064, 'steps': 56166, 'loss/train': 0.23477235436439514} 08/30/2021 23:19:16 - INFO - __main__ - Step 56168: {'lr': 0.0003521671120819928, 'samples': 10784256, 'steps': 56167, 'loss/train': 2.9166364669799805} 08/30/2021 23:19:17 - INFO - __main__ - Step 56169: {'lr': 0.0003521622686840873, 'samples': 10784448, 'steps': 56168, 'loss/train': 1.4661478996276855} 08/30/2021 23:19:17 - INFO - __main__ - Step 56170: {'lr': 0.000352157425240149, 'samples': 10784640, 'steps': 56169, 'loss/train': 1.411795973777771} 08/30/2021 23:19:17 - INFO - __main__ - Step 56171: {'lr': 0.00035215258175018015, 'samples': 10784832, 'steps': 56170, 'loss/train': 1.772681713104248} 08/30/2021 23:19:18 - INFO - __main__ - Step 56172: {'lr': 0.00035214773821418295, 'samples': 10785024, 'steps': 56171, 'loss/train': 1.4317295551300049} 08/30/2021 23:19:19 - INFO - __main__ - Step 56173: {'lr': 0.00035214289463215954, 'samples': 10785216, 'steps': 56172, 'loss/train': 1.6848418712615967} 08/30/2021 23:19:20 - INFO - __main__ - Step 56174: {'lr': 0.00035213805100411217, 'samples': 10785408, 'steps': 56173, 'loss/train': 1.1198793649673462} 08/30/2021 23:19:20 - INFO - __main__ - Step 56175: {'lr': 0.00035213320733004297, 'samples': 10785600, 'steps': 56174, 'loss/train': 1.8251439332962036} 08/30/2021 23:19:20 - INFO - __main__ - Step 56176: {'lr': 0.00035212836360995405, 'samples': 10785792, 'steps': 56175, 'loss/train': 1.3288264274597168} 08/30/2021 23:19:21 - INFO - __main__ - Step 56177: {'lr': 0.0003521235198438477, 'samples': 10785984, 'steps': 56176, 'loss/train': 1.2904421091079712} 08/30/2021 23:19:21 - INFO - __main__ - Step 56178: {'lr': 0.000352118676031726, 'samples': 10786176, 'steps': 56177, 'loss/train': 1.4400594234466553} 08/30/2021 23:19:23 - INFO - __main__ - Step 56179: {'lr': 0.0003521138321735913, 'samples': 10786368, 'steps': 56178, 'loss/train': 1.3378797769546509} 08/30/2021 23:19:23 - INFO - __main__ - Step 56180: {'lr': 0.0003521089882694456, 'samples': 10786560, 'steps': 56179, 'loss/train': 1.5753055810928345} 08/30/2021 23:19:23 - INFO - __main__ - Step 56181: {'lr': 0.0003521041443192913, 'samples': 10786752, 'steps': 56180, 'loss/train': 1.7837469577789307} 08/30/2021 23:19:24 - INFO - __main__ - Step 56182: {'lr': 0.00035209930032313033, 'samples': 10786944, 'steps': 56181, 'loss/train': 1.1433008909225464} 08/30/2021 23:19:24 - INFO - __main__ - Step 56183: {'lr': 0.000352094456280965, 'samples': 10787136, 'steps': 56182, 'loss/train': 1.3171823024749756} 08/30/2021 23:19:26 - INFO - __main__ - Step 56184: {'lr': 0.0003520896121927975, 'samples': 10787328, 'steps': 56183, 'loss/train': 1.5922255516052246} 08/30/2021 23:19:26 - INFO - __main__ - Step 56185: {'lr': 0.00035208476805863, 'samples': 10787520, 'steps': 56184, 'loss/train': 0.9351261258125305} 08/30/2021 23:19:26 - INFO - __main__ - Step 56186: {'lr': 0.00035207992387846466, 'samples': 10787712, 'steps': 56185, 'loss/train': 1.7132059335708618} 08/30/2021 23:19:27 - INFO - __main__ - Step 56187: {'lr': 0.0003520750796523037, 'samples': 10787904, 'steps': 56186, 'loss/train': 1.6543177366256714} 08/30/2021 23:19:27 - INFO - __main__ - Step 56188: {'lr': 0.0003520702353801493, 'samples': 10788096, 'steps': 56187, 'loss/train': 1.239197850227356} 08/30/2021 23:19:28 - INFO - __main__ - Step 56189: {'lr': 0.0003520653910620036, 'samples': 10788288, 'steps': 56188, 'loss/train': 0.5263615846633911} 08/30/2021 23:19:29 - INFO - __main__ - Step 56190: {'lr': 0.0003520605466978688, 'samples': 10788480, 'steps': 56189, 'loss/train': 1.5944441556930542} 08/30/2021 23:19:30 - INFO - __main__ - Step 56191: {'lr': 0.00035205570228774715, 'samples': 10788672, 'steps': 56190, 'loss/train': 1.3017621040344238} 08/30/2021 23:19:30 - INFO - __main__ - Step 56192: {'lr': 0.0003520508578316407, 'samples': 10788864, 'steps': 56191, 'loss/train': 1.1193162202835083} 08/30/2021 23:19:31 - INFO - __main__ - Step 56193: {'lr': 0.0003520460133295518, 'samples': 10789056, 'steps': 56192, 'loss/train': 0.788877010345459} 08/30/2021 23:19:31 - INFO - __main__ - Step 56194: {'lr': 0.0003520411687814825, 'samples': 10789248, 'steps': 56193, 'loss/train': 1.5324747562408447} 08/30/2021 23:19:33 - INFO - __main__ - Step 56195: {'lr': 0.000352036324187435, 'samples': 10789440, 'steps': 56194, 'loss/train': 1.3240686655044556} 08/30/2021 23:19:33 - INFO - __main__ - Step 56196: {'lr': 0.0003520314795474115, 'samples': 10789632, 'steps': 56195, 'loss/train': 0.29671040177345276} 08/30/2021 23:19:34 - INFO - __main__ - Step 56197: {'lr': 0.00035202663486141417, 'samples': 10789824, 'steps': 56196, 'loss/train': 0.5146790146827698} 08/30/2021 23:19:34 - INFO - __main__ - Step 56198: {'lr': 0.00035202179012944527, 'samples': 10790016, 'steps': 56197, 'loss/train': 1.2441060543060303} 08/30/2021 23:19:34 - INFO - __main__ - Step 56199: {'lr': 0.0003520169453515069, 'samples': 10790208, 'steps': 56198, 'loss/train': 0.26361212134361267} 08/30/2021 23:19:36 - INFO - __main__ - Step 56200: {'lr': 0.00035201210052760123, 'samples': 10790400, 'steps': 56199, 'loss/train': 0.14536148309707642} 08/30/2021 23:19:36 - INFO - __main__ - Step 56201: {'lr': 0.0003520072556577306, 'samples': 10790592, 'steps': 56200, 'loss/train': 1.5028141736984253} 08/30/2021 23:19:37 - INFO - __main__ - Step 56202: {'lr': 0.000352002410741897, 'samples': 10790784, 'steps': 56201, 'loss/train': 0.7295525074005127} 08/30/2021 23:19:37 - INFO - __main__ - Step 56203: {'lr': 0.00035199756578010267, 'samples': 10790976, 'steps': 56202, 'loss/train': 1.3582055568695068} 08/30/2021 23:19:38 - INFO - __main__ - Step 56204: {'lr': 0.0003519927207723498, 'samples': 10791168, 'steps': 56203, 'loss/train': 0.6318374276161194} 08/30/2021 23:19:39 - INFO - __main__ - Step 56205: {'lr': 0.00035198787571864067, 'samples': 10791360, 'steps': 56204, 'loss/train': 0.31698113679885864} 08/30/2021 23:19:40 - INFO - __main__ - Step 56206: {'lr': 0.0003519830306189773, 'samples': 10791552, 'steps': 56205, 'loss/train': 1.2460066080093384} 08/30/2021 23:19:40 - INFO - __main__ - Step 56207: {'lr': 0.000351978185473362, 'samples': 10791744, 'steps': 56206, 'loss/train': 1.2279210090637207} 08/30/2021 23:19:40 - INFO - __main__ - Step 56208: {'lr': 0.0003519733402817968, 'samples': 10791936, 'steps': 56207, 'loss/train': 1.6996444463729858} 08/30/2021 23:19:41 - INFO - __main__ - Step 56209: {'lr': 0.0003519684950442841, 'samples': 10792128, 'steps': 56208, 'loss/train': 1.4328835010528564} 08/30/2021 23:19:42 - INFO - __main__ - Step 56210: {'lr': 0.00035196364976082593, 'samples': 10792320, 'steps': 56209, 'loss/train': 1.3060847520828247} 08/30/2021 23:19:43 - INFO - __main__ - Step 56211: {'lr': 0.0003519588044314245, 'samples': 10792512, 'steps': 56210, 'loss/train': 0.7972104549407959} 08/30/2021 23:19:43 - INFO - __main__ - Step 56212: {'lr': 0.000351953959056082, 'samples': 10792704, 'steps': 56211, 'loss/train': 1.6470961570739746} 08/30/2021 23:19:43 - INFO - __main__ - Step 56213: {'lr': 0.0003519491136348006, 'samples': 10792896, 'steps': 56212, 'loss/train': 1.480650544166565} 08/30/2021 23:19:44 - INFO - __main__ - Step 56214: {'lr': 0.0003519442681675826, 'samples': 10793088, 'steps': 56213, 'loss/train': 1.7162854671478271} 08/30/2021 23:19:45 - INFO - __main__ - Step 56215: {'lr': 0.00035193942265443, 'samples': 10793280, 'steps': 56214, 'loss/train': 1.61748468875885} 08/30/2021 23:19:46 - INFO - __main__ - Step 56216: {'lr': 0.0003519345770953452, 'samples': 10793472, 'steps': 56215, 'loss/train': 1.6915357112884521} 08/30/2021 23:19:46 - INFO - __main__ - Step 56217: {'lr': 0.00035192973149033007, 'samples': 10793664, 'steps': 56216, 'loss/train': 1.4703187942504883} 08/30/2021 23:19:46 - INFO - __main__ - Step 56218: {'lr': 0.0003519248858393871, 'samples': 10793856, 'steps': 56217, 'loss/train': 0.48813164234161377} 08/30/2021 23:19:47 - INFO - __main__ - Step 56219: {'lr': 0.0003519200401425183, 'samples': 10794048, 'steps': 56218, 'loss/train': 0.8728643655776978} 08/30/2021 23:19:49 - INFO - __main__ - Step 56220: {'lr': 0.0003519151943997259, 'samples': 10794240, 'steps': 56219, 'loss/train': 1.487473487854004} 08/30/2021 23:19:49 - INFO - __main__ - Step 56221: {'lr': 0.0003519103486110121, 'samples': 10794432, 'steps': 56220, 'loss/train': 1.0937063694000244} 08/30/2021 23:19:49 - INFO - __main__ - Step 56222: {'lr': 0.0003519055027763791, 'samples': 10794624, 'steps': 56221, 'loss/train': 0.11141691356897354} 08/30/2021 23:19:50 - INFO - __main__ - Step 56223: {'lr': 0.00035190065689582895, 'samples': 10794816, 'steps': 56222, 'loss/train': 0.18188953399658203} 08/30/2021 23:19:50 - INFO - __main__ - Step 56224: {'lr': 0.00035189581096936395, 'samples': 10795008, 'steps': 56223, 'loss/train': 0.844398021697998} 08/30/2021 23:19:50 - INFO - __main__ - Step 56225: {'lr': 0.0003518909649969864, 'samples': 10795200, 'steps': 56224, 'loss/train': 1.4655299186706543} 08/30/2021 23:19:52 - INFO - __main__ - Step 56226: {'lr': 0.00035188611897869824, 'samples': 10795392, 'steps': 56225, 'loss/train': 1.1828337907791138} 08/30/2021 23:19:52 - INFO - __main__ - Step 56227: {'lr': 0.00035188127291450183, 'samples': 10795584, 'steps': 56226, 'loss/train': 1.137499451637268} 08/30/2021 23:19:53 - INFO - __main__ - Step 56228: {'lr': 0.00035187642680439927, 'samples': 10795776, 'steps': 56227, 'loss/train': 0.6767659783363342} 08/30/2021 23:19:53 - INFO - __main__ - Step 56229: {'lr': 0.0003518715806483928, 'samples': 10795968, 'steps': 56228, 'loss/train': 1.9900949001312256} 08/30/2021 23:19:53 - INFO - __main__ - Step 56230: {'lr': 0.0003518667344464845, 'samples': 10796160, 'steps': 56229, 'loss/train': 1.5314913988113403} 08/30/2021 23:19:55 - INFO - __main__ - Step 56231: {'lr': 0.00035186188819867663, 'samples': 10796352, 'steps': 56230, 'loss/train': 1.2715846300125122} 08/30/2021 23:19:56 - INFO - __main__ - Step 56232: {'lr': 0.00035185704190497137, 'samples': 10796544, 'steps': 56231, 'loss/train': 1.6737961769104004} 08/30/2021 23:19:56 - INFO - __main__ - Step 56233: {'lr': 0.0003518521955653709, 'samples': 10796736, 'steps': 56232, 'loss/train': 1.781301498413086} 08/30/2021 23:19:56 - INFO - __main__ - Step 56234: {'lr': 0.0003518473491798774, 'samples': 10796928, 'steps': 56233, 'loss/train': 1.2351044416427612} 08/30/2021 23:19:57 - INFO - __main__ - Step 56235: {'lr': 0.00035184250274849306, 'samples': 10797120, 'steps': 56234, 'loss/train': 1.651589274406433} 08/30/2021 23:19:58 - INFO - __main__ - Step 56236: {'lr': 0.0003518376562712201, 'samples': 10797312, 'steps': 56235, 'loss/train': 0.6935270428657532} 08/30/2021 23:19:59 - INFO - __main__ - Step 56237: {'lr': 0.00035183280974806065, 'samples': 10797504, 'steps': 56236, 'loss/train': 0.6373516321182251} 08/30/2021 23:19:59 - INFO - __main__ - Step 56238: {'lr': 0.0003518279631790169, 'samples': 10797696, 'steps': 56237, 'loss/train': 1.2254695892333984} 08/30/2021 23:19:59 - INFO - __main__ - Step 56239: {'lr': 0.000351823116564091, 'samples': 10797888, 'steps': 56238, 'loss/train': 0.9763191342353821} 08/30/2021 23:20:00 - INFO - __main__ - Step 56240: {'lr': 0.0003518182699032852, 'samples': 10798080, 'steps': 56239, 'loss/train': 0.75439453125} 08/30/2021 23:20:01 - INFO - __main__ - Step 56241: {'lr': 0.0003518134231966017, 'samples': 10798272, 'steps': 56240, 'loss/train': 1.5486811399459839} 08/30/2021 23:20:02 - INFO - __main__ - Step 56242: {'lr': 0.0003518085764440426, 'samples': 10798464, 'steps': 56241, 'loss/train': 1.3664119243621826} 08/30/2021 23:20:02 - INFO - __main__ - Step 56243: {'lr': 0.00035180372964561013, 'samples': 10798656, 'steps': 56242, 'loss/train': 1.2818729877471924} 08/30/2021 23:20:02 - INFO - __main__ - Step 56244: {'lr': 0.00035179888280130646, 'samples': 10798848, 'steps': 56243, 'loss/train': 1.0736815929412842} 08/30/2021 23:20:03 - INFO - __main__ - Step 56245: {'lr': 0.00035179403591113377, 'samples': 10799040, 'steps': 56244, 'loss/train': 1.0455563068389893} 08/30/2021 23:20:05 - INFO - __main__ - Step 56246: {'lr': 0.0003517891889750943, 'samples': 10799232, 'steps': 56245, 'loss/train': 1.1921799182891846} 08/30/2021 23:20:05 - INFO - __main__ - Step 56247: {'lr': 0.0003517843419931902, 'samples': 10799424, 'steps': 56246, 'loss/train': 0.8170264959335327} 08/30/2021 23:20:06 - INFO - __main__ - Step 56248: {'lr': 0.0003517794949654236, 'samples': 10799616, 'steps': 56247, 'loss/train': 1.2851195335388184} 08/30/2021 23:20:06 - INFO - __main__ - Step 56249: {'lr': 0.00035177464789179675, 'samples': 10799808, 'steps': 56248, 'loss/train': 1.3435691595077515} 08/30/2021 23:20:06 - INFO - __main__ - Step 56250: {'lr': 0.0003517698007723118, 'samples': 10800000, 'steps': 56249, 'loss/train': 1.5542590618133545} 08/30/2021 23:20:08 - INFO - __main__ - Step 56251: {'lr': 0.00035176495360697096, 'samples': 10800192, 'steps': 56250, 'loss/train': 1.3107409477233887} 08/30/2021 23:20:08 - INFO - __main__ - Step 56252: {'lr': 0.0003517601063957764, 'samples': 10800384, 'steps': 56251, 'loss/train': 0.9203411340713501} 08/30/2021 23:20:09 - INFO - __main__ - Step 56253: {'lr': 0.0003517552591387303, 'samples': 10800576, 'steps': 56252, 'loss/train': 1.6615418195724487} 08/30/2021 23:20:09 - INFO - __main__ - Step 56254: {'lr': 0.0003517504118358349, 'samples': 10800768, 'steps': 56253, 'loss/train': 1.0183117389678955} 08/30/2021 23:20:09 - INFO - __main__ - Step 56255: {'lr': 0.0003517455644870923, 'samples': 10800960, 'steps': 56254, 'loss/train': 1.3904917240142822} 08/30/2021 23:20:11 - INFO - __main__ - Step 56256: {'lr': 0.00035174071709250475, 'samples': 10801152, 'steps': 56255, 'loss/train': 0.9888782501220703} 08/30/2021 23:20:11 - INFO - __main__ - Step 56257: {'lr': 0.00035173586965207436, 'samples': 10801344, 'steps': 56256, 'loss/train': 1.1724299192428589} 08/30/2021 23:20:12 - INFO - __main__ - Step 56258: {'lr': 0.0003517310221658033, 'samples': 10801536, 'steps': 56257, 'loss/train': 1.6633081436157227} 08/30/2021 23:20:12 - INFO - __main__ - Step 56259: {'lr': 0.00035172617463369397, 'samples': 10801728, 'steps': 56258, 'loss/train': 1.1430174112319946} 08/30/2021 23:20:12 - INFO - __main__ - Step 56260: {'lr': 0.0003517213270557482, 'samples': 10801920, 'steps': 56259, 'loss/train': 1.0456026792526245} 08/30/2021 23:20:14 - INFO - __main__ - Step 56261: {'lr': 0.00035171647943196854, 'samples': 10802112, 'steps': 56260, 'loss/train': 0.9139151573181152} 08/30/2021 23:20:14 - INFO - __main__ - Step 56262: {'lr': 0.00035171163176235694, 'samples': 10802304, 'steps': 56261, 'loss/train': 1.6453360319137573} 08/30/2021 23:20:15 - INFO - __main__ - Step 56263: {'lr': 0.00035170678404691563, 'samples': 10802496, 'steps': 56262, 'loss/train': 0.6549670100212097} 08/30/2021 23:20:15 - INFO - __main__ - Step 56264: {'lr': 0.00035170193628564683, 'samples': 10802688, 'steps': 56263, 'loss/train': 1.2884488105773926} 08/30/2021 23:20:15 - INFO - __main__ - Step 56265: {'lr': 0.0003516970884785527, 'samples': 10802880, 'steps': 56264, 'loss/train': 1.3687598705291748} 08/30/2021 23:20:17 - INFO - __main__ - Step 56266: {'lr': 0.00035169224062563543, 'samples': 10803072, 'steps': 56265, 'loss/train': 1.206392765045166} 08/30/2021 23:20:18 - INFO - __main__ - Step 56267: {'lr': 0.0003516873927268972, 'samples': 10803264, 'steps': 56266, 'loss/train': 1.0268909931182861} 08/30/2021 23:20:18 - INFO - __main__ - Step 56268: {'lr': 0.0003516825447823403, 'samples': 10803456, 'steps': 56267, 'loss/train': 0.7114416360855103} 08/30/2021 23:20:19 - INFO - __main__ - Step 56269: {'lr': 0.0003516776967919667, 'samples': 10803648, 'steps': 56268, 'loss/train': 0.028562083840370178} 08/30/2021 23:20:19 - INFO - __main__ - Step 56270: {'lr': 0.0003516728487557787, 'samples': 10803840, 'steps': 56269, 'loss/train': 3.810262441635132} 08/30/2021 23:20:19 - INFO - __main__ - Step 56271: {'lr': 0.00035166800067377855, 'samples': 10804032, 'steps': 56270, 'loss/train': 0.9921672344207764} 08/30/2021 23:20:20 - INFO - __main__ - Step 56272: {'lr': 0.00035166315254596826, 'samples': 10804224, 'steps': 56271, 'loss/train': 1.1992790699005127} 08/30/2021 23:20:21 - INFO - __main__ - Step 56273: {'lr': 0.0003516583043723502, 'samples': 10804416, 'steps': 56272, 'loss/train': 1.5328330993652344} 08/30/2021 23:20:22 - INFO - __main__ - Step 56274: {'lr': 0.0003516534561529264, 'samples': 10804608, 'steps': 56273, 'loss/train': 0.9591448307037354} 08/30/2021 23:20:22 - INFO - __main__ - Step 56275: {'lr': 0.00035164860788769925, 'samples': 10804800, 'steps': 56274, 'loss/train': 1.5115023851394653} 08/30/2021 23:20:22 - INFO - __main__ - Step 56276: {'lr': 0.0003516437595766708, 'samples': 10804992, 'steps': 56275, 'loss/train': 1.0127558708190918} 08/30/2021 23:20:23 - INFO - __main__ - Step 56277: {'lr': 0.00035163891121984316, 'samples': 10805184, 'steps': 56276, 'loss/train': 1.7689074277877808} 08/30/2021 23:20:24 - INFO - __main__ - Step 56278: {'lr': 0.0003516340628172186, 'samples': 10805376, 'steps': 56277, 'loss/train': 1.2849451303482056} 08/30/2021 23:20:25 - INFO - __main__ - Step 56279: {'lr': 0.0003516292143687993, 'samples': 10805568, 'steps': 56278, 'loss/train': 1.4143896102905273} 08/30/2021 23:20:25 - INFO - __main__ - Step 56280: {'lr': 0.00035162436587458744, 'samples': 10805760, 'steps': 56279, 'loss/train': 0.24738809466362} 08/30/2021 23:20:25 - INFO - __main__ - Step 56281: {'lr': 0.0003516195173345853, 'samples': 10805952, 'steps': 56280, 'loss/train': 0.4486299157142639} 08/30/2021 23:20:26 - INFO - __main__ - Step 56282: {'lr': 0.0003516146687487949, 'samples': 10806144, 'steps': 56281, 'loss/train': 0.7672046422958374} 08/30/2021 23:20:28 - INFO - __main__ - Step 56283: {'lr': 0.0003516098201172185, 'samples': 10806336, 'steps': 56282, 'loss/train': 0.9187241792678833} 08/30/2021 23:20:28 - INFO - __main__ - Step 56284: {'lr': 0.00035160497143985823, 'samples': 10806528, 'steps': 56283, 'loss/train': 1.5133743286132812} 08/30/2021 23:20:28 - INFO - __main__ - Step 56285: {'lr': 0.0003516001227167164, 'samples': 10806720, 'steps': 56284, 'loss/train': 0.8918207883834839} 08/30/2021 23:20:29 - INFO - __main__ - Step 56286: {'lr': 0.0003515952739477951, 'samples': 10806912, 'steps': 56285, 'loss/train': 0.6635756492614746} 08/30/2021 23:20:29 - INFO - __main__ - Step 56287: {'lr': 0.0003515904251330965, 'samples': 10807104, 'steps': 56286, 'loss/train': 0.9633187651634216} 08/30/2021 23:20:31 - INFO - __main__ - Step 56288: {'lr': 0.00035158557627262295, 'samples': 10807296, 'steps': 56287, 'loss/train': 1.0384821891784668} 08/30/2021 23:20:31 - INFO - __main__ - Step 56289: {'lr': 0.00035158072736637643, 'samples': 10807488, 'steps': 56288, 'loss/train': 1.444690465927124} 08/30/2021 23:20:31 - INFO - __main__ - Step 56290: {'lr': 0.0003515758784143592, 'samples': 10807680, 'steps': 56289, 'loss/train': 0.9422166347503662} 08/30/2021 23:20:32 - INFO - __main__ - Step 56291: {'lr': 0.00035157102941657336, 'samples': 10807872, 'steps': 56290, 'loss/train': 1.3602656126022339} 08/30/2021 23:20:32 - INFO - __main__ - Step 56292: {'lr': 0.0003515661803730213, 'samples': 10808064, 'steps': 56291, 'loss/train': 0.9585633873939514} 08/30/2021 23:20:32 - INFO - __main__ - Step 56293: {'lr': 0.000351561331283705, 'samples': 10808256, 'steps': 56292, 'loss/train': 1.4210909605026245} 08/30/2021 23:20:34 - INFO - __main__ - Step 56294: {'lr': 0.0003515564821486268, 'samples': 10808448, 'steps': 56293, 'loss/train': 1.1082032918930054} 08/30/2021 23:20:35 - INFO - __main__ - Step 56295: {'lr': 0.00035155163296778883, 'samples': 10808640, 'steps': 56294, 'loss/train': 1.853243112564087} 08/30/2021 23:20:35 - INFO - __main__ - Step 56296: {'lr': 0.0003515467837411932, 'samples': 10808832, 'steps': 56295, 'loss/train': 1.3389308452606201} 08/30/2021 23:20:35 - INFO - __main__ - Step 56297: {'lr': 0.0003515419344688422, 'samples': 10809024, 'steps': 56296, 'loss/train': 1.6399043798446655} 08/30/2021 23:20:36 - INFO - __main__ - Step 56298: {'lr': 0.00035153708515073793, 'samples': 10809216, 'steps': 56297, 'loss/train': 1.5292176008224487} 08/30/2021 23:20:38 - INFO - __main__ - Step 56299: {'lr': 0.00035153223578688263, 'samples': 10809408, 'steps': 56298, 'loss/train': 0.882011890411377} 08/30/2021 23:20:39 - INFO - __main__ - Step 56300: {'lr': 0.0003515273863772785, 'samples': 10809600, 'steps': 56299, 'loss/train': 0.8975883722305298} 08/30/2021 23:20:39 - INFO - __main__ - Step 56301: {'lr': 0.00035152253692192765, 'samples': 10809792, 'steps': 56300, 'loss/train': 1.4098734855651855} 08/30/2021 23:20:39 - INFO - __main__ - Step 56302: {'lr': 0.0003515176874208324, 'samples': 10809984, 'steps': 56301, 'loss/train': 1.7833385467529297} 08/30/2021 23:20:40 - INFO - __main__ - Step 56303: {'lr': 0.0003515128378739948, 'samples': 10810176, 'steps': 56302, 'loss/train': 1.7411781549453735} 08/30/2021 23:20:42 - INFO - __main__ - Step 56304: {'lr': 0.0003515079882814171, 'samples': 10810368, 'steps': 56303, 'loss/train': 1.065727949142456} 08/30/2021 23:20:42 - INFO - __main__ - Step 56305: {'lr': 0.00035150313864310137, 'samples': 10810560, 'steps': 56304, 'loss/train': 1.5781422853469849} 08/30/2021 23:20:42 - INFO - __main__ - Step 56306: {'lr': 0.00035149828895904994, 'samples': 10810752, 'steps': 56305, 'loss/train': 1.477195382118225} 08/30/2021 23:20:43 - INFO - __main__ - Step 56307: {'lr': 0.00035149343922926497, 'samples': 10810944, 'steps': 56306, 'loss/train': 0.04176757112145424} 08/30/2021 23:20:43 - INFO - __main__ - Step 56308: {'lr': 0.0003514885894537486, 'samples': 10811136, 'steps': 56307, 'loss/train': 0.04284767806529999} 08/30/2021 23:20:43 - INFO - __main__ - Step 56309: {'lr': 0.00035148373963250307, 'samples': 10811328, 'steps': 56308, 'loss/train': 1.548675537109375} 08/30/2021 23:20:44 - INFO - __main__ - Step 56310: {'lr': 0.0003514788897655305, 'samples': 10811520, 'steps': 56309, 'loss/train': 1.342390537261963} 08/30/2021 23:20:46 - INFO - __main__ - Step 56311: {'lr': 0.0003514740398528331, 'samples': 10811712, 'steps': 56310, 'loss/train': 1.5789802074432373} 08/30/2021 23:20:46 - INFO - __main__ - Step 56312: {'lr': 0.0003514691898944131, 'samples': 10811904, 'steps': 56311, 'loss/train': 0.7250506281852722} 08/30/2021 23:20:46 - INFO - __main__ - Step 56313: {'lr': 0.0003514643398902727, 'samples': 10812096, 'steps': 56312, 'loss/train': 0.9135230779647827} 08/30/2021 23:20:47 - INFO - __main__ - Step 56314: {'lr': 0.00035145948984041393, 'samples': 10812288, 'steps': 56313, 'loss/train': 1.0178760290145874} 08/30/2021 23:20:47 - INFO - __main__ - Step 56315: {'lr': 0.00035145463974483915, 'samples': 10812480, 'steps': 56314, 'loss/train': 0.05449938401579857} 08/30/2021 23:20:48 - INFO - __main__ - Step 56316: {'lr': 0.00035144978960355045, 'samples': 10812672, 'steps': 56315, 'loss/train': 1.1534762382507324} 08/30/2021 23:20:49 - INFO - __main__ - Step 56317: {'lr': 0.00035144493941655, 'samples': 10812864, 'steps': 56316, 'loss/train': 0.04490484297275543} 08/30/2021 23:20:49 - INFO - __main__ - Step 56318: {'lr': 0.00035144008918384006, 'samples': 10813056, 'steps': 56317, 'loss/train': 0.7149926424026489} 08/30/2021 23:20:50 - INFO - __main__ - Step 56319: {'lr': 0.0003514352389054228, 'samples': 10813248, 'steps': 56318, 'loss/train': 1.9637274742126465} 08/30/2021 23:20:50 - INFO - __main__ - Step 56320: {'lr': 0.00035143038858130034, 'samples': 10813440, 'steps': 56319, 'loss/train': 1.1326920986175537} 08/30/2021 23:20:50 - INFO - __main__ - Step 56321: {'lr': 0.00035142553821147494, 'samples': 10813632, 'steps': 56320, 'loss/train': 0.5537501573562622} 08/30/2021 23:20:52 - INFO - __main__ - Step 56322: {'lr': 0.00035142068779594885, 'samples': 10813824, 'steps': 56321, 'loss/train': 1.706468939781189} 08/30/2021 23:20:52 - INFO - __main__ - Step 56323: {'lr': 0.00035141583733472407, 'samples': 10814016, 'steps': 56322, 'loss/train': 0.6052045822143555} 08/30/2021 23:20:53 - INFO - __main__ - Step 56324: {'lr': 0.0003514109868278028, 'samples': 10814208, 'steps': 56323, 'loss/train': 0.7911117076873779} 08/30/2021 23:20:53 - INFO - __main__ - Step 56325: {'lr': 0.0003514061362751874, 'samples': 10814400, 'steps': 56324, 'loss/train': 1.2599706649780273} 08/30/2021 23:20:54 - INFO - __main__ - Step 56326: {'lr': 0.0003514012856768799, 'samples': 10814592, 'steps': 56325, 'loss/train': 1.321623682975769} 08/30/2021 23:20:55 - INFO - __main__ - Step 56327: {'lr': 0.0003513964350328826, 'samples': 10814784, 'steps': 56326, 'loss/train': 2.7075531482696533} 08/30/2021 23:20:55 - INFO - __main__ - Step 56328: {'lr': 0.0003513915843431977, 'samples': 10814976, 'steps': 56327, 'loss/train': 1.152888536453247} 08/30/2021 23:20:56 - INFO - __main__ - Step 56329: {'lr': 0.0003513867336078272, 'samples': 10815168, 'steps': 56328, 'loss/train': 1.200417399406433} 08/30/2021 23:20:56 - INFO - __main__ - Step 56330: {'lr': 0.00035138188282677344, 'samples': 10815360, 'steps': 56329, 'loss/train': 1.5218689441680908} 08/30/2021 23:20:56 - INFO - __main__ - Step 56331: {'lr': 0.00035137703200003857, 'samples': 10815552, 'steps': 56330, 'loss/train': 1.597712516784668} 08/30/2021 23:20:58 - INFO - __main__ - Step 56332: {'lr': 0.00035137218112762475, 'samples': 10815744, 'steps': 56331, 'loss/train': 0.7616521120071411} 08/30/2021 23:20:58 - INFO - __main__ - Step 56333: {'lr': 0.0003513673302095342, 'samples': 10815936, 'steps': 56332, 'loss/train': 1.5828900337219238} 08/30/2021 23:20:59 - INFO - __main__ - Step 56334: {'lr': 0.0003513624792457691, 'samples': 10816128, 'steps': 56333, 'loss/train': 1.4141948223114014} 08/30/2021 23:20:59 - INFO - __main__ - Step 56335: {'lr': 0.00035135762823633167, 'samples': 10816320, 'steps': 56334, 'loss/train': 1.3798741102218628} 08/30/2021 23:20:59 - INFO - __main__ - Step 56336: {'lr': 0.00035135277718122403, 'samples': 10816512, 'steps': 56335, 'loss/train': 1.0160465240478516} 08/30/2021 23:21:01 - INFO - __main__ - Step 56337: {'lr': 0.0003513479260804484, 'samples': 10816704, 'steps': 56336, 'loss/train': 1.274591326713562} 08/30/2021 23:21:01 - INFO - __main__ - Step 56338: {'lr': 0.0003513430749340069, 'samples': 10816896, 'steps': 56337, 'loss/train': 0.8275808691978455} 08/30/2021 23:21:02 - INFO - __main__ - Step 56339: {'lr': 0.0003513382237419018, 'samples': 10817088, 'steps': 56338, 'loss/train': 1.0999596118927002} 08/30/2021 23:21:02 - INFO - __main__ - Step 56340: {'lr': 0.00035133337250413534, 'samples': 10817280, 'steps': 56339, 'loss/train': 1.9294317960739136} 08/30/2021 23:21:02 - INFO - __main__ - Step 56341: {'lr': 0.00035132852122070953, 'samples': 10817472, 'steps': 56340, 'loss/train': 0.9169614911079407} 08/30/2021 23:21:03 - INFO - __main__ - Step 56342: {'lr': 0.0003513236698916267, 'samples': 10817664, 'steps': 56341, 'loss/train': 1.5714478492736816} 08/30/2021 23:21:05 - INFO - __main__ - Step 56343: {'lr': 0.00035131881851688896, 'samples': 10817856, 'steps': 56342, 'loss/train': 0.48499056696891785} 08/30/2021 23:21:05 - INFO - __main__ - Step 56344: {'lr': 0.00035131396709649855, 'samples': 10818048, 'steps': 56343, 'loss/train': 1.3771110773086548} 08/30/2021 23:21:06 - INFO - __main__ - Step 56345: {'lr': 0.00035130911563045764, 'samples': 10818240, 'steps': 56344, 'loss/train': 1.4886866807937622} 08/30/2021 23:21:06 - INFO - __main__ - Step 56346: {'lr': 0.00035130426411876834, 'samples': 10818432, 'steps': 56345, 'loss/train': 0.8399190306663513} 08/30/2021 23:21:06 - INFO - __main__ - Step 56347: {'lr': 0.00035129941256143295, 'samples': 10818624, 'steps': 56346, 'loss/train': 2.588120222091675} 08/30/2021 23:21:07 - INFO - __main__ - Step 56348: {'lr': 0.0003512945609584536, 'samples': 10818816, 'steps': 56347, 'loss/train': 0.9279683232307434} 08/30/2021 23:21:09 - INFO - __main__ - Step 56349: {'lr': 0.0003512897093098325, 'samples': 10819008, 'steps': 56348, 'loss/train': 0.05068553611636162} 08/30/2021 23:21:09 - INFO - __main__ - Step 56350: {'lr': 0.0003512848576155718, 'samples': 10819200, 'steps': 56349, 'loss/train': 1.3194245100021362} 08/30/2021 23:21:09 - INFO - __main__ - Step 56351: {'lr': 0.0003512800058756738, 'samples': 10819392, 'steps': 56350, 'loss/train': 0.02751103788614273} 08/30/2021 23:21:10 - INFO - __main__ - Step 56352: {'lr': 0.00035127515409014046, 'samples': 10819584, 'steps': 56351, 'loss/train': 1.3289200067520142} 08/30/2021 23:21:10 - INFO - __main__ - Step 56353: {'lr': 0.00035127030225897413, 'samples': 10819776, 'steps': 56352, 'loss/train': 1.2871557474136353} 08/30/2021 23:21:10 - INFO - __main__ - Step 56354: {'lr': 0.000351265450382177, 'samples': 10819968, 'steps': 56353, 'loss/train': 1.5532402992248535} 08/30/2021 23:21:12 - INFO - __main__ - Step 56355: {'lr': 0.0003512605984597512, 'samples': 10820160, 'steps': 56354, 'loss/train': 1.0814402103424072} 08/30/2021 23:21:12 - INFO - __main__ - Step 56356: {'lr': 0.00035125574649169894, 'samples': 10820352, 'steps': 56355, 'loss/train': 1.309942364692688} 08/30/2021 23:21:13 - INFO - __main__ - Step 56357: {'lr': 0.0003512508944780224, 'samples': 10820544, 'steps': 56356, 'loss/train': 0.991716742515564} 08/30/2021 23:21:13 - INFO - __main__ - Step 56358: {'lr': 0.0003512460424187237, 'samples': 10820736, 'steps': 56357, 'loss/train': 1.267741322517395} 08/30/2021 23:21:13 - INFO - __main__ - Step 56359: {'lr': 0.00035124119031380526, 'samples': 10820928, 'steps': 56358, 'loss/train': 1.6119405031204224} 08/30/2021 23:21:15 - INFO - __main__ - Step 56360: {'lr': 0.000351236338163269, 'samples': 10821120, 'steps': 56359, 'loss/train': 1.0107890367507935} 08/30/2021 23:21:16 - INFO - __main__ - Step 56361: {'lr': 0.00035123148596711716, 'samples': 10821312, 'steps': 56360, 'loss/train': 0.6051582098007202} 08/30/2021 23:21:16 - INFO - __main__ - Step 56362: {'lr': 0.0003512266337253521, 'samples': 10821504, 'steps': 56361, 'loss/train': 1.6000652313232422} 08/30/2021 23:21:16 - INFO - __main__ - Step 56363: {'lr': 0.0003512217814379758, 'samples': 10821696, 'steps': 56362, 'loss/train': 1.2335125207901} 08/30/2021 23:21:17 - INFO - __main__ - Step 56364: {'lr': 0.0003512169291049905, 'samples': 10821888, 'steps': 56363, 'loss/train': 1.6763275861740112} 08/30/2021 23:21:18 - INFO - __main__ - Step 56365: {'lr': 0.0003512120767263985, 'samples': 10822080, 'steps': 56364, 'loss/train': 1.0438852310180664} 08/30/2021 23:21:19 - INFO - __main__ - Step 56366: {'lr': 0.0003512072243022018, 'samples': 10822272, 'steps': 56365, 'loss/train': 1.2271020412445068} 08/30/2021 23:21:19 - INFO - __main__ - Step 56367: {'lr': 0.00035120237183240276, 'samples': 10822464, 'steps': 56366, 'loss/train': 0.9846289157867432} 08/30/2021 23:21:19 - INFO - __main__ - Step 56368: {'lr': 0.00035119751931700344, 'samples': 10822656, 'steps': 56367, 'loss/train': 1.552603006362915} 08/30/2021 23:21:20 - INFO - __main__ - Step 56369: {'lr': 0.00035119266675600615, 'samples': 10822848, 'steps': 56368, 'loss/train': 1.2388850450515747} 08/30/2021 23:21:21 - INFO - __main__ - Step 56370: {'lr': 0.00035118781414941296, 'samples': 10823040, 'steps': 56369, 'loss/train': 1.216059923171997} 08/30/2021 23:21:22 - INFO - __main__ - Step 56371: {'lr': 0.00035118296149722614, 'samples': 10823232, 'steps': 56370, 'loss/train': 2.545923948287964} 08/30/2021 23:21:22 - INFO - __main__ - Step 56372: {'lr': 0.0003511781087994478, 'samples': 10823424, 'steps': 56371, 'loss/train': 0.9165162444114685} 08/30/2021 23:21:23 - INFO - __main__ - Step 56373: {'lr': 0.00035117325605608013, 'samples': 10823616, 'steps': 56372, 'loss/train': 1.1739851236343384} 08/30/2021 23:21:23 - INFO - __main__ - Step 56374: {'lr': 0.0003511684032671254, 'samples': 10823808, 'steps': 56373, 'loss/train': 0.2769080102443695} 08/30/2021 23:21:23 - INFO - __main__ - Step 56375: {'lr': 0.0003511635504325857, 'samples': 10824000, 'steps': 56374, 'loss/train': 1.0504651069641113} 08/30/2021 23:21:25 - INFO - __main__ - Step 56376: {'lr': 0.0003511586975524634, 'samples': 10824192, 'steps': 56375, 'loss/train': 1.4656623601913452} 08/30/2021 23:21:26 - INFO - __main__ - Step 56377: {'lr': 0.0003511538446267604, 'samples': 10824384, 'steps': 56376, 'loss/train': 1.472334384918213} 08/30/2021 23:21:26 - INFO - __main__ - Step 56378: {'lr': 0.00035114899165547916, 'samples': 10824576, 'steps': 56377, 'loss/train': 1.6079140901565552} 08/30/2021 23:21:26 - INFO - __main__ - Step 56379: {'lr': 0.00035114413863862164, 'samples': 10824768, 'steps': 56378, 'loss/train': 0.03344573825597763} 08/30/2021 23:21:27 - INFO - __main__ - Step 56380: {'lr': 0.0003511392855761902, 'samples': 10824960, 'steps': 56379, 'loss/train': 0.03081243485212326} 08/30/2021 23:21:28 - INFO - __main__ - Step 56381: {'lr': 0.0003511344324681869, 'samples': 10825152, 'steps': 56380, 'loss/train': 1.1805614233016968} 08/30/2021 23:21:28 - INFO - __main__ - Step 56382: {'lr': 0.00035112957931461407, 'samples': 10825344, 'steps': 56381, 'loss/train': 1.4443172216415405} 08/30/2021 23:21:29 - INFO - __main__ - Step 56383: {'lr': 0.00035112472611547376, 'samples': 10825536, 'steps': 56382, 'loss/train': 1.27548086643219} 08/30/2021 23:21:29 - INFO - __main__ - Step 56384: {'lr': 0.0003511198728707682, 'samples': 10825728, 'steps': 56383, 'loss/train': 1.2274144887924194} 08/30/2021 23:21:30 - INFO - __main__ - Step 56385: {'lr': 0.0003511150195804996, 'samples': 10825920, 'steps': 56384, 'loss/train': 1.4640270471572876} 08/30/2021 23:21:31 - INFO - __main__ - Step 56386: {'lr': 0.00035111016624467007, 'samples': 10826112, 'steps': 56385, 'loss/train': 1.3278813362121582} 08/30/2021 23:21:31 - INFO - __main__ - Step 56387: {'lr': 0.00035110531286328193, 'samples': 10826304, 'steps': 56386, 'loss/train': 1.2180472612380981} 08/30/2021 23:21:32 - INFO - __main__ - Step 56388: {'lr': 0.0003511004594363373, 'samples': 10826496, 'steps': 56387, 'loss/train': 1.208565592765808} 08/30/2021 23:21:32 - INFO - __main__ - Step 56389: {'lr': 0.0003510956059638384, 'samples': 10826688, 'steps': 56388, 'loss/train': 1.4527655839920044} 08/30/2021 23:21:33 - INFO - __main__ - Step 56390: {'lr': 0.0003510907524457873, 'samples': 10826880, 'steps': 56389, 'loss/train': 1.8823432922363281} 08/30/2021 23:21:34 - INFO - __main__ - Step 56391: {'lr': 0.0003510858988821863, 'samples': 10827072, 'steps': 56390, 'loss/train': 1.5455334186553955} 08/30/2021 23:21:34 - INFO - __main__ - Step 56392: {'lr': 0.00035108104527303754, 'samples': 10827264, 'steps': 56391, 'loss/train': 1.289292812347412} 08/30/2021 23:21:35 - INFO - __main__ - Step 56393: {'lr': 0.0003510761916183432, 'samples': 10827456, 'steps': 56392, 'loss/train': 1.3379442691802979} 08/30/2021 23:21:35 - INFO - __main__ - Step 56394: {'lr': 0.00035107133791810555, 'samples': 10827648, 'steps': 56393, 'loss/train': 1.9926207065582275} 08/30/2021 23:21:36 - INFO - __main__ - Step 56395: {'lr': 0.00035106648417232666, 'samples': 10827840, 'steps': 56394, 'loss/train': 1.126552700996399} 08/30/2021 23:21:36 - INFO - __main__ - Step 56396: {'lr': 0.0003510616303810088, 'samples': 10828032, 'steps': 56395, 'loss/train': 2.8981428146362305} 08/30/2021 23:21:38 - INFO - __main__ - Step 56397: {'lr': 0.00035105677654415416, 'samples': 10828224, 'steps': 56396, 'loss/train': 1.3787848949432373} 08/30/2021 23:21:38 - INFO - __main__ - Step 56398: {'lr': 0.0003510519226617648, 'samples': 10828416, 'steps': 56397, 'loss/train': 1.388511061668396} 08/30/2021 23:21:38 - INFO - __main__ - Step 56399: {'lr': 0.00035104706873384305, 'samples': 10828608, 'steps': 56398, 'loss/train': 1.3289058208465576} 08/30/2021 23:21:39 - INFO - __main__ - Step 56400: {'lr': 0.0003510422147603911, 'samples': 10828800, 'steps': 56399, 'loss/train': 0.04551689699292183} 08/30/2021 23:21:39 - INFO - __main__ - Step 56401: {'lr': 0.00035103736074141103, 'samples': 10828992, 'steps': 56400, 'loss/train': 1.2905093431472778} 08/30/2021 23:21:41 - INFO - __main__ - Step 56402: {'lr': 0.0003510325066769051, 'samples': 10829184, 'steps': 56401, 'loss/train': 1.3818747997283936} 08/30/2021 23:21:41 - INFO - __main__ - Step 56403: {'lr': 0.00035102765256687555, 'samples': 10829376, 'steps': 56402, 'loss/train': 5.8501877784729} 08/30/2021 23:21:41 - INFO - __main__ - Step 56404: {'lr': 0.0003510227984113244, 'samples': 10829568, 'steps': 56403, 'loss/train': 0.8995800018310547} 08/30/2021 23:21:42 - INFO - __main__ - Step 56405: {'lr': 0.00035101794421025395, 'samples': 10829760, 'steps': 56404, 'loss/train': 1.3171738386154175} 08/30/2021 23:21:42 - INFO - __main__ - Step 56406: {'lr': 0.00035101308996366635, 'samples': 10829952, 'steps': 56405, 'loss/train': 1.2439517974853516} 08/30/2021 23:21:44 - INFO - __main__ - Step 56407: {'lr': 0.00035100823567156385, 'samples': 10830144, 'steps': 56406, 'loss/train': 1.37333345413208} 08/30/2021 23:21:44 - INFO - __main__ - Step 56408: {'lr': 0.0003510033813339486, 'samples': 10830336, 'steps': 56407, 'loss/train': 1.2654346227645874} 08/30/2021 23:21:44 - INFO - __main__ - Step 56409: {'lr': 0.00035099852695082286, 'samples': 10830528, 'steps': 56408, 'loss/train': 1.1296823024749756} 08/30/2021 23:21:45 - INFO - __main__ - Step 56410: {'lr': 0.0003509936725221886, 'samples': 10830720, 'steps': 56409, 'loss/train': 1.2942525148391724} 08/30/2021 23:21:45 - INFO - __main__ - Step 56411: {'lr': 0.0003509888180480483, 'samples': 10830912, 'steps': 56410, 'loss/train': 1.6736493110656738} 08/30/2021 23:21:45 - INFO - __main__ - Step 56412: {'lr': 0.00035098396352840384, 'samples': 10831104, 'steps': 56411, 'loss/train': 1.037999153137207} 08/30/2021 23:21:48 - INFO - __main__ - Step 56413: {'lr': 0.00035097910896325765, 'samples': 10831296, 'steps': 56412, 'loss/train': 1.4722040891647339} 08/30/2021 23:21:48 - INFO - __main__ - Step 56414: {'lr': 0.0003509742543526118, 'samples': 10831488, 'steps': 56413, 'loss/train': 1.3150835037231445} 08/30/2021 23:21:48 - INFO - __main__ - Step 56415: {'lr': 0.00035096939969646854, 'samples': 10831680, 'steps': 56414, 'loss/train': 0.40805065631866455} 08/30/2021 23:21:49 - INFO - __main__ - Step 56416: {'lr': 0.00035096454499483, 'samples': 10831872, 'steps': 56415, 'loss/train': 0.9750242233276367} 08/30/2021 23:21:49 - INFO - __main__ - Step 56417: {'lr': 0.0003509596902476985, 'samples': 10832064, 'steps': 56416, 'loss/train': 1.2096073627471924} 08/30/2021 23:21:51 - INFO - __main__ - Step 56418: {'lr': 0.000350954835455076, 'samples': 10832256, 'steps': 56417, 'loss/train': 1.6839812994003296} 08/30/2021 23:21:51 - INFO - __main__ - Step 56419: {'lr': 0.00035094998061696483, 'samples': 10832448, 'steps': 56418, 'loss/train': 1.9249850511550903} 08/30/2021 23:21:52 - INFO - __main__ - Step 56420: {'lr': 0.0003509451257333671, 'samples': 10832640, 'steps': 56419, 'loss/train': 0.9475346803665161} 08/30/2021 23:21:52 - INFO - __main__ - Step 56421: {'lr': 0.00035094027080428514, 'samples': 10832832, 'steps': 56420, 'loss/train': 1.3457587957382202} 08/30/2021 23:21:52 - INFO - __main__ - Step 56422: {'lr': 0.00035093541582972105, 'samples': 10833024, 'steps': 56421, 'loss/train': 0.9765965342521667} 08/30/2021 23:21:54 - INFO - __main__ - Step 56423: {'lr': 0.000350930560809677, 'samples': 10833216, 'steps': 56422, 'loss/train': 1.2351179122924805} 08/30/2021 23:21:54 - INFO - __main__ - Step 56424: {'lr': 0.0003509257057441552, 'samples': 10833408, 'steps': 56423, 'loss/train': 1.6799372434616089} 08/30/2021 23:21:55 - INFO - __main__ - Step 56425: {'lr': 0.00035092085063315783, 'samples': 10833600, 'steps': 56424, 'loss/train': 1.5770337581634521} 08/30/2021 23:21:55 - INFO - __main__ - Step 56426: {'lr': 0.00035091599547668707, 'samples': 10833792, 'steps': 56425, 'loss/train': 1.8400212526321411} 08/30/2021 23:21:55 - INFO - __main__ - Step 56427: {'lr': 0.00035091114027474514, 'samples': 10833984, 'steps': 56426, 'loss/train': 1.5495290756225586} 08/30/2021 23:21:56 - INFO - __main__ - Step 56428: {'lr': 0.0003509062850273342, 'samples': 10834176, 'steps': 56427, 'loss/train': 0.5808155536651611} 08/30/2021 23:21:57 - INFO - __main__ - Step 56429: {'lr': 0.0003509014297344565, 'samples': 10834368, 'steps': 56428, 'loss/train': 1.4561634063720703} 08/30/2021 23:21:58 - INFO - __main__ - Step 56430: {'lr': 0.0003508965743961141, 'samples': 10834560, 'steps': 56429, 'loss/train': 0.9111874103546143} 08/30/2021 23:21:58 - INFO - __main__ - Step 56431: {'lr': 0.00035089171901230926, 'samples': 10834752, 'steps': 56430, 'loss/train': 1.1718239784240723} 08/30/2021 23:21:59 - INFO - __main__ - Step 56432: {'lr': 0.0003508868635830442, 'samples': 10834944, 'steps': 56431, 'loss/train': 1.7609952688217163} 08/30/2021 23:21:59 - INFO - __main__ - Step 56433: {'lr': 0.00035088200810832104, 'samples': 10835136, 'steps': 56432, 'loss/train': 0.9224588871002197} 08/30/2021 23:22:00 - INFO - __main__ - Step 56434: {'lr': 0.00035087715258814203, 'samples': 10835328, 'steps': 56433, 'loss/train': 0.3581213653087616} 08/30/2021 23:22:01 - INFO - __main__ - Step 56435: {'lr': 0.00035087229702250936, 'samples': 10835520, 'steps': 56434, 'loss/train': 1.6546635627746582} 08/30/2021 23:22:01 - INFO - __main__ - Step 56436: {'lr': 0.00035086744141142514, 'samples': 10835712, 'steps': 56435, 'loss/train': 0.5147892236709595} 08/30/2021 23:22:02 - INFO - __main__ - Step 56437: {'lr': 0.0003508625857548916, 'samples': 10835904, 'steps': 56436, 'loss/train': 0.7432236671447754} 08/30/2021 23:22:02 - INFO - __main__ - Step 56438: {'lr': 0.000350857730052911, 'samples': 10836096, 'steps': 56437, 'loss/train': 1.392895221710205} 08/30/2021 23:22:04 - INFO - __main__ - Step 56439: {'lr': 0.0003508528743054854, 'samples': 10836288, 'steps': 56438, 'loss/train': 1.4067773818969727} 08/30/2021 23:22:04 - INFO - __main__ - Step 56440: {'lr': 0.00035084801851261707, 'samples': 10836480, 'steps': 56439, 'loss/train': 1.563826322555542} 08/30/2021 23:22:04 - INFO - __main__ - Step 56441: {'lr': 0.00035084316267430815, 'samples': 10836672, 'steps': 56440, 'loss/train': 1.4754047393798828} 08/30/2021 23:22:05 - INFO - __main__ - Step 56442: {'lr': 0.0003508383067905609, 'samples': 10836864, 'steps': 56441, 'loss/train': 1.0166155099868774} 08/30/2021 23:22:05 - INFO - __main__ - Step 56443: {'lr': 0.0003508334508613775, 'samples': 10837056, 'steps': 56442, 'loss/train': 0.9441992044448853} 08/30/2021 23:22:07 - INFO - __main__ - Step 56444: {'lr': 0.00035082859488676005, 'samples': 10837248, 'steps': 56443, 'loss/train': 1.2128995656967163} 08/30/2021 23:22:07 - INFO - __main__ - Step 56445: {'lr': 0.0003508237388667108, 'samples': 10837440, 'steps': 56444, 'loss/train': 1.2033194303512573} 08/30/2021 23:22:08 - INFO - __main__ - Step 56446: {'lr': 0.00035081888280123194, 'samples': 10837632, 'steps': 56445, 'loss/train': 1.7337194681167603} 08/30/2021 23:22:08 - INFO - __main__ - Step 56447: {'lr': 0.0003508140266903256, 'samples': 10837824, 'steps': 56446, 'loss/train': 0.08774230629205704} 08/30/2021 23:22:08 - INFO - __main__ - Step 56448: {'lr': 0.0003508091705339941, 'samples': 10838016, 'steps': 56447, 'loss/train': 1.4886800050735474} 08/30/2021 23:22:09 - INFO - __main__ - Step 56449: {'lr': 0.00035080431433223946, 'samples': 10838208, 'steps': 56448, 'loss/train': 0.8500186800956726} 08/30/2021 23:22:10 - INFO - __main__ - Step 56450: {'lr': 0.000350799458085064, 'samples': 10838400, 'steps': 56449, 'loss/train': 1.0560827255249023} 08/30/2021 23:22:11 - INFO - __main__ - Step 56451: {'lr': 0.00035079460179246984, 'samples': 10838592, 'steps': 56450, 'loss/train': 1.252631664276123} 08/30/2021 23:22:11 - INFO - __main__ - Step 56452: {'lr': 0.0003507897454544592, 'samples': 10838784, 'steps': 56451, 'loss/train': 0.3698769509792328} 08/30/2021 23:22:11 - INFO - __main__ - Step 56453: {'lr': 0.0003507848890710342, 'samples': 10838976, 'steps': 56452, 'loss/train': 1.3823071718215942} 08/30/2021 23:22:12 - INFO - __main__ - Step 56454: {'lr': 0.00035078003264219713, 'samples': 10839168, 'steps': 56453, 'loss/train': 1.3327810764312744} 08/30/2021 23:22:13 - INFO - __main__ - Step 56455: {'lr': 0.0003507751761679502, 'samples': 10839360, 'steps': 56454, 'loss/train': 1.5613362789154053} 08/30/2021 23:22:14 - INFO - __main__ - Step 56456: {'lr': 0.0003507703196482955, 'samples': 10839552, 'steps': 56455, 'loss/train': 1.0154962539672852} 08/30/2021 23:22:14 - INFO - __main__ - Step 56457: {'lr': 0.0003507654630832352, 'samples': 10839744, 'steps': 56456, 'loss/train': 1.4267102479934692} 08/30/2021 23:22:14 - INFO - __main__ - Step 56458: {'lr': 0.0003507606064727715, 'samples': 10839936, 'steps': 56457, 'loss/train': 1.0416288375854492} 08/30/2021 23:22:15 - INFO - __main__ - Step 56459: {'lr': 0.0003507557498169067, 'samples': 10840128, 'steps': 56458, 'loss/train': 1.4540621042251587} 08/30/2021 23:22:16 - INFO - __main__ - Step 56460: {'lr': 0.0003507508931156429, 'samples': 10840320, 'steps': 56459, 'loss/train': 1.6540557146072388} 08/30/2021 23:22:17 - INFO - __main__ - Step 56461: {'lr': 0.0003507460363689823, 'samples': 10840512, 'steps': 56460, 'loss/train': 1.3665308952331543} 08/30/2021 23:22:17 - INFO - __main__ - Step 56462: {'lr': 0.00035074117957692707, 'samples': 10840704, 'steps': 56461, 'loss/train': 1.4076887369155884} 08/30/2021 23:22:18 - INFO - __main__ - Step 56463: {'lr': 0.0003507363227394795, 'samples': 10840896, 'steps': 56462, 'loss/train': 1.3722600936889648} 08/30/2021 23:22:18 - INFO - __main__ - Step 56464: {'lr': 0.00035073146585664163, 'samples': 10841088, 'steps': 56463, 'loss/train': 1.7906204462051392} 08/30/2021 23:22:20 - INFO - __main__ - Step 56465: {'lr': 0.00035072660892841566, 'samples': 10841280, 'steps': 56464, 'loss/train': 1.2597562074661255} 08/30/2021 23:22:21 - INFO - __main__ - Step 56466: {'lr': 0.0003507217519548039, 'samples': 10841472, 'steps': 56465, 'loss/train': 0.7803432941436768} 08/30/2021 23:22:21 - INFO - __main__ - Step 56467: {'lr': 0.00035071689493580845, 'samples': 10841664, 'steps': 56466, 'loss/train': 1.1418205499649048} 08/30/2021 23:22:21 - INFO - __main__ - Step 56468: {'lr': 0.0003507120378714315, 'samples': 10841856, 'steps': 56467, 'loss/train': 1.3491010665893555} 08/30/2021 23:22:22 - INFO - __main__ - Step 56469: {'lr': 0.0003507071807616753, 'samples': 10842048, 'steps': 56468, 'loss/train': 1.0862956047058105} 08/30/2021 23:22:22 - INFO - __main__ - Step 56470: {'lr': 0.0003507023236065421, 'samples': 10842240, 'steps': 56469, 'loss/train': 1.5986477136611938} 08/30/2021 23:22:23 - INFO - __main__ - Step 56471: {'lr': 0.0003506974664060338, 'samples': 10842432, 'steps': 56470, 'loss/train': 0.05688268691301346} 08/30/2021 23:22:24 - INFO - __main__ - Step 56472: {'lr': 0.00035069260916015287, 'samples': 10842624, 'steps': 56471, 'loss/train': 1.4795644283294678} 08/30/2021 23:22:24 - INFO - __main__ - Step 56473: {'lr': 0.0003506877518689014, 'samples': 10842816, 'steps': 56472, 'loss/train': 1.4247878789901733} 08/30/2021 23:22:25 - INFO - __main__ - Step 56474: {'lr': 0.0003506828945322816, 'samples': 10843008, 'steps': 56473, 'loss/train': 1.583120584487915} 08/30/2021 23:22:25 - INFO - __main__ - Step 56475: {'lr': 0.0003506780371502956, 'samples': 10843200, 'steps': 56474, 'loss/train': 0.48261404037475586} 08/30/2021 23:22:27 - INFO - __main__ - Step 56476: {'lr': 0.00035067317972294564, 'samples': 10843392, 'steps': 56475, 'loss/train': 0.9055414199829102} 08/30/2021 23:22:27 - INFO - __main__ - Step 56477: {'lr': 0.00035066832225023393, 'samples': 10843584, 'steps': 56476, 'loss/train': 1.215675950050354} 08/30/2021 23:22:27 - INFO - __main__ - Step 56478: {'lr': 0.0003506634647321626, 'samples': 10843776, 'steps': 56477, 'loss/train': 0.32339316606521606} 08/30/2021 23:22:28 - INFO - __main__ - Step 56479: {'lr': 0.0003506586071687338, 'samples': 10843968, 'steps': 56478, 'loss/train': 0.07090987265110016} 08/30/2021 23:22:28 - INFO - __main__ - Step 56480: {'lr': 0.0003506537495599499, 'samples': 10844160, 'steps': 56479, 'loss/train': 1.2480740547180176} 08/30/2021 23:22:30 - INFO - __main__ - Step 56481: {'lr': 0.0003506488919058129, 'samples': 10844352, 'steps': 56480, 'loss/train': 1.4660922288894653} 08/30/2021 23:22:30 - INFO - __main__ - Step 56482: {'lr': 0.00035064403420632505, 'samples': 10844544, 'steps': 56481, 'loss/train': 0.5766159296035767} 08/30/2021 23:22:31 - INFO - __main__ - Step 56483: {'lr': 0.0003506391764614887, 'samples': 10844736, 'steps': 56482, 'loss/train': 0.8548250794410706} 08/30/2021 23:22:31 - INFO - __main__ - Step 56484: {'lr': 0.00035063431867130576, 'samples': 10844928, 'steps': 56483, 'loss/train': 1.335131287574768} 08/30/2021 23:22:31 - INFO - __main__ - Step 56485: {'lr': 0.00035062946083577853, 'samples': 10845120, 'steps': 56484, 'loss/train': 1.0710281133651733} 08/30/2021 23:22:33 - INFO - __main__ - Step 56486: {'lr': 0.00035062460295490926, 'samples': 10845312, 'steps': 56485, 'loss/train': 0.9134763479232788} 08/30/2021 23:22:33 - INFO - __main__ - Step 56487: {'lr': 0.00035061974502870007, 'samples': 10845504, 'steps': 56486, 'loss/train': 1.432463526725769} 08/30/2021 23:22:34 - INFO - __main__ - Step 56488: {'lr': 0.0003506148870571533, 'samples': 10845696, 'steps': 56487, 'loss/train': 1.6364357471466064} 08/30/2021 23:22:34 - INFO - __main__ - Step 56489: {'lr': 0.00035061002904027084, 'samples': 10845888, 'steps': 56488, 'loss/train': 1.7500250339508057} 08/30/2021 23:22:34 - INFO - __main__ - Step 56490: {'lr': 0.0003506051709780551, 'samples': 10846080, 'steps': 56489, 'loss/train': 1.61838698387146} 08/30/2021 23:22:36 - INFO - __main__ - Step 56491: {'lr': 0.0003506003128705083, 'samples': 10846272, 'steps': 56490, 'loss/train': 1.5849438905715942} 08/30/2021 23:22:36 - INFO - __main__ - Step 56492: {'lr': 0.0003505954547176325, 'samples': 10846464, 'steps': 56491, 'loss/train': 1.2359497547149658} 08/30/2021 23:22:37 - INFO - __main__ - Step 56493: {'lr': 0.00035059059651942995, 'samples': 10846656, 'steps': 56492, 'loss/train': 1.3019310235977173} 08/30/2021 23:22:37 - INFO - __main__ - Step 56494: {'lr': 0.00035058573827590286, 'samples': 10846848, 'steps': 56493, 'loss/train': 1.1675150394439697} 08/30/2021 23:22:37 - INFO - __main__ - Step 56495: {'lr': 0.0003505808799870533, 'samples': 10847040, 'steps': 56494, 'loss/train': 0.03174806386232376} 08/30/2021 23:22:38 - INFO - __main__ - Step 56496: {'lr': 0.0003505760216528836, 'samples': 10847232, 'steps': 56495, 'loss/train': 1.9629825353622437} 08/30/2021 23:22:40 - INFO - __main__ - Step 56497: {'lr': 0.0003505711632733959, 'samples': 10847424, 'steps': 56496, 'loss/train': 1.8223012685775757} 08/30/2021 23:22:40 - INFO - __main__ - Step 56498: {'lr': 0.00035056630484859235, 'samples': 10847616, 'steps': 56497, 'loss/train': 1.0175421237945557} 08/30/2021 23:22:40 - INFO - __main__ - Step 56499: {'lr': 0.00035056144637847525, 'samples': 10847808, 'steps': 56498, 'loss/train': 0.28747323155403137} 08/30/2021 23:22:41 - INFO - __main__ - Step 56500: {'lr': 0.0003505565878630467, 'samples': 10848000, 'steps': 56499, 'loss/train': 1.129755973815918} 08/30/2021 23:22:41 - INFO - __main__ - Step 56501: {'lr': 0.0003505517293023088, 'samples': 10848192, 'steps': 56500, 'loss/train': 1.0732613801956177} 08/30/2021 23:22:43 - INFO - __main__ - Step 56502: {'lr': 0.0003505468706962639, 'samples': 10848384, 'steps': 56501, 'loss/train': 0.10525637865066528} 08/30/2021 23:22:43 - INFO - __main__ - Step 56503: {'lr': 0.00035054201204491413, 'samples': 10848576, 'steps': 56502, 'loss/train': 1.207919955253601} 08/30/2021 23:22:43 - INFO - __main__ - Step 56504: {'lr': 0.00035053715334826176, 'samples': 10848768, 'steps': 56503, 'loss/train': 1.325360655784607} 08/30/2021 23:22:44 - INFO - __main__ - Step 56505: {'lr': 0.0003505322946063089, 'samples': 10848960, 'steps': 56504, 'loss/train': 1.4062741994857788} 08/30/2021 23:22:44 - INFO - __main__ - Step 56506: {'lr': 0.0003505274358190576, 'samples': 10849152, 'steps': 56505, 'loss/train': 1.12855863571167} 08/30/2021 23:22:46 - INFO - __main__ - Step 56507: {'lr': 0.00035052257698651025, 'samples': 10849344, 'steps': 56506, 'loss/train': 1.360582709312439} 08/30/2021 23:22:46 - INFO - __main__ - Step 56508: {'lr': 0.000350517718108669, 'samples': 10849536, 'steps': 56507, 'loss/train': 1.701041579246521} 08/30/2021 23:22:46 - INFO - __main__ - Step 56509: {'lr': 0.000350512859185536, 'samples': 10849728, 'steps': 56508, 'loss/train': 1.7182844877243042} 08/30/2021 23:22:47 - INFO - __main__ - Step 56510: {'lr': 0.00035050800021711346, 'samples': 10849920, 'steps': 56509, 'loss/train': 1.9650938510894775} 08/30/2021 23:22:47 - INFO - __main__ - Step 56511: {'lr': 0.00035050314120340357, 'samples': 10850112, 'steps': 56510, 'loss/train': 1.4075977802276611} 08/30/2021 23:22:49 - INFO - __main__ - Step 56512: {'lr': 0.00035049828214440856, 'samples': 10850304, 'steps': 56511, 'loss/train': 1.6018834114074707} 08/30/2021 23:22:49 - INFO - __main__ - Step 56513: {'lr': 0.00035049342304013055, 'samples': 10850496, 'steps': 56512, 'loss/train': 1.0976426601409912} 08/30/2021 23:22:49 - INFO - __main__ - Step 56514: {'lr': 0.0003504885638905717, 'samples': 10850688, 'steps': 56513, 'loss/train': 1.7953767776489258} 08/30/2021 23:22:50 - INFO - __main__ - Step 56515: {'lr': 0.0003504837046957343, 'samples': 10850880, 'steps': 56514, 'loss/train': 1.3804914951324463} 08/30/2021 23:22:50 - INFO - __main__ - Step 56516: {'lr': 0.0003504788454556205, 'samples': 10851072, 'steps': 56515, 'loss/train': 1.636925220489502} 08/30/2021 23:22:51 - INFO - __main__ - Step 56517: {'lr': 0.00035047398617023246, 'samples': 10851264, 'steps': 56516, 'loss/train': 0.7687824368476868} 08/30/2021 23:22:53 - INFO - __main__ - Step 56518: {'lr': 0.0003504691268395724, 'samples': 10851456, 'steps': 56517, 'loss/train': 1.6216387748718262} 08/30/2021 23:22:53 - INFO - __main__ - Step 56519: {'lr': 0.00035046426746364247, 'samples': 10851648, 'steps': 56518, 'loss/train': 1.1298202276229858} 08/30/2021 23:22:53 - INFO - __main__ - Step 56520: {'lr': 0.0003504594080424449, 'samples': 10851840, 'steps': 56519, 'loss/train': 1.0394850969314575} 08/30/2021 23:22:54 - INFO - __main__ - Step 56521: {'lr': 0.00035045454857598194, 'samples': 10852032, 'steps': 56520, 'loss/train': 1.0864089727401733} 08/30/2021 23:22:54 - INFO - __main__ - Step 56522: {'lr': 0.0003504496890642556, 'samples': 10852224, 'steps': 56521, 'loss/train': 1.5368640422821045} 08/30/2021 23:22:56 - INFO - __main__ - Step 56523: {'lr': 0.0003504448295072683, 'samples': 10852416, 'steps': 56522, 'loss/train': 1.122554898262024} 08/30/2021 23:22:56 - INFO - __main__ - Step 56524: {'lr': 0.00035043996990502204, 'samples': 10852608, 'steps': 56523, 'loss/train': 1.0034229755401611} 08/30/2021 23:22:56 - INFO - __main__ - Step 56525: {'lr': 0.00035043511025751906, 'samples': 10852800, 'steps': 56524, 'loss/train': 1.3032256364822388} 08/30/2021 23:22:57 - INFO - __main__ - Step 56526: {'lr': 0.00035043025056476164, 'samples': 10852992, 'steps': 56525, 'loss/train': 0.8567964434623718} 08/30/2021 23:22:57 - INFO - __main__ - Step 56527: {'lr': 0.00035042539082675184, 'samples': 10853184, 'steps': 56526, 'loss/train': 2.180180311203003} 08/30/2021 23:22:59 - INFO - __main__ - Step 56528: {'lr': 0.00035042053104349195, 'samples': 10853376, 'steps': 56527, 'loss/train': 1.3048216104507446} 08/30/2021 23:22:59 - INFO - __main__ - Step 56529: {'lr': 0.00035041567121498406, 'samples': 10853568, 'steps': 56528, 'loss/train': 1.3458185195922852} 08/30/2021 23:23:00 - INFO - __main__ - Step 56530: {'lr': 0.0003504108113412305, 'samples': 10853760, 'steps': 56529, 'loss/train': 0.025860119611024857} 08/30/2021 23:23:00 - INFO - __main__ - Step 56531: {'lr': 0.0003504059514222333, 'samples': 10853952, 'steps': 56530, 'loss/train': 1.1303489208221436} 08/30/2021 23:23:00 - INFO - __main__ - Step 56532: {'lr': 0.00035040109145799474, 'samples': 10854144, 'steps': 56531, 'loss/train': 1.4384759664535522} 08/30/2021 23:23:01 - INFO - __main__ - Step 56533: {'lr': 0.0003503962314485171, 'samples': 10854336, 'steps': 56532, 'loss/train': 1.4004967212677002} 08/30/2021 23:23:02 - INFO - __main__ - Step 56534: {'lr': 0.00035039137139380235, 'samples': 10854528, 'steps': 56533, 'loss/train': 1.4151445627212524} 08/30/2021 23:23:03 - INFO - __main__ - Step 56535: {'lr': 0.0003503865112938528, 'samples': 10854720, 'steps': 56534, 'loss/train': 1.4511741399765015} 08/30/2021 23:23:03 - INFO - __main__ - Step 56536: {'lr': 0.00035038165114867066, 'samples': 10854912, 'steps': 56535, 'loss/train': 1.2138116359710693} 08/30/2021 23:23:04 - INFO - __main__ - Step 56537: {'lr': 0.00035037679095825815, 'samples': 10855104, 'steps': 56536, 'loss/train': 1.4829049110412598} 08/30/2021 23:23:04 - INFO - __main__ - Step 56538: {'lr': 0.00035037193072261734, 'samples': 10855296, 'steps': 56537, 'loss/train': 0.8143882155418396} 08/30/2021 23:23:05 - INFO - __main__ - Step 56539: {'lr': 0.00035036707044175055, 'samples': 10855488, 'steps': 56538, 'loss/train': 0.9588643312454224} 08/30/2021 23:23:06 - INFO - __main__ - Step 56540: {'lr': 0.00035036221011565985, 'samples': 10855680, 'steps': 56539, 'loss/train': 0.704169511795044} 08/30/2021 23:23:06 - INFO - __main__ - Step 56541: {'lr': 0.00035035734974434745, 'samples': 10855872, 'steps': 56540, 'loss/train': 1.5803643465042114} 08/30/2021 23:23:06 - INFO - __main__ - Step 56542: {'lr': 0.00035035248932781564, 'samples': 10856064, 'steps': 56541, 'loss/train': 1.4250285625457764} 08/30/2021 23:23:07 - INFO - __main__ - Step 56543: {'lr': 0.0003503476288660665, 'samples': 10856256, 'steps': 56542, 'loss/train': 1.3363053798675537} 08/30/2021 23:23:08 - INFO - __main__ - Step 56544: {'lr': 0.0003503427683591024, 'samples': 10856448, 'steps': 56543, 'loss/train': 1.5413345098495483} 08/30/2021 23:23:09 - INFO - __main__ - Step 56545: {'lr': 0.00035033790780692527, 'samples': 10856640, 'steps': 56544, 'loss/train': 0.9046850800514221} 08/30/2021 23:23:09 - INFO - __main__ - Step 56546: {'lr': 0.0003503330472095375, 'samples': 10856832, 'steps': 56545, 'loss/train': 0.8477411866188049} 08/30/2021 23:23:10 - INFO - __main__ - Step 56547: {'lr': 0.0003503281865669411, 'samples': 10857024, 'steps': 56546, 'loss/train': 1.3381098508834839} 08/30/2021 23:23:10 - INFO - __main__ - Step 56548: {'lr': 0.00035032332587913844, 'samples': 10857216, 'steps': 56547, 'loss/train': 2.5551445484161377} 08/30/2021 23:23:10 - INFO - __main__ - Step 56549: {'lr': 0.00035031846514613164, 'samples': 10857408, 'steps': 56548, 'loss/train': 1.2439919710159302} 08/30/2021 23:23:12 - INFO - __main__ - Step 56550: {'lr': 0.00035031360436792294, 'samples': 10857600, 'steps': 56549, 'loss/train': 1.2165690660476685} 08/30/2021 23:23:12 - INFO - __main__ - Step 56551: {'lr': 0.00035030874354451434, 'samples': 10857792, 'steps': 56550, 'loss/train': 1.7179961204528809} 08/30/2021 23:23:13 - INFO - __main__ - Step 56552: {'lr': 0.0003503038826759083, 'samples': 10857984, 'steps': 56551, 'loss/train': 1.5298376083374023} 08/30/2021 23:23:13 - INFO - __main__ - Step 56553: {'lr': 0.00035029902176210675, 'samples': 10858176, 'steps': 56552, 'loss/train': 0.7448773980140686} 08/30/2021 23:23:13 - INFO - __main__ - Step 56554: {'lr': 0.0003502941608031121, 'samples': 10858368, 'steps': 56553, 'loss/train': 0.826343297958374} 08/30/2021 23:23:15 - INFO - __main__ - Step 56555: {'lr': 0.00035028929979892645, 'samples': 10858560, 'steps': 56554, 'loss/train': 1.3980389833450317} 08/30/2021 23:23:15 - INFO - __main__ - Step 56556: {'lr': 0.00035028443874955196, 'samples': 10858752, 'steps': 56555, 'loss/train': 1.7466596364974976} 08/30/2021 23:23:16 - INFO - __main__ - Step 56557: {'lr': 0.00035027957765499084, 'samples': 10858944, 'steps': 56556, 'loss/train': 1.0910674333572388} 08/30/2021 23:23:16 - INFO - __main__ - Step 56558: {'lr': 0.00035027471651524533, 'samples': 10859136, 'steps': 56557, 'loss/train': 0.9672409296035767} 08/30/2021 23:23:16 - INFO - __main__ - Step 56559: {'lr': 0.00035026985533031754, 'samples': 10859328, 'steps': 56558, 'loss/train': 1.0487531423568726} 08/30/2021 23:23:18 - INFO - __main__ - Step 56560: {'lr': 0.00035026499410020974, 'samples': 10859520, 'steps': 56559, 'loss/train': 1.6387578248977661} 08/30/2021 23:23:18 - INFO - __main__ - Step 56561: {'lr': 0.00035026013282492404, 'samples': 10859712, 'steps': 56560, 'loss/train': 1.244329810142517} 08/30/2021 23:23:18 - INFO - __main__ - Step 56562: {'lr': 0.0003502552715044627, 'samples': 10859904, 'steps': 56561, 'loss/train': 1.9325666427612305} 08/30/2021 23:23:19 - INFO - __main__ - Step 56563: {'lr': 0.0003502504101388279, 'samples': 10860096, 'steps': 56562, 'loss/train': 1.1325589418411255} 08/30/2021 23:23:19 - INFO - __main__ - Step 56564: {'lr': 0.0003502455487280218, 'samples': 10860288, 'steps': 56563, 'loss/train': 0.8093452453613281} 08/30/2021 23:23:21 - INFO - __main__ - Step 56565: {'lr': 0.00035024068727204655, 'samples': 10860480, 'steps': 56564, 'loss/train': 0.7579498887062073} 08/30/2021 23:23:21 - INFO - __main__ - Step 56566: {'lr': 0.0003502358257709044, 'samples': 10860672, 'steps': 56565, 'loss/train': 0.9509707093238831} 08/30/2021 23:23:22 - INFO - __main__ - Step 56567: {'lr': 0.00035023096422459756, 'samples': 10860864, 'steps': 56566, 'loss/train': 1.457160234451294} 08/30/2021 23:23:22 - INFO - __main__ - Step 56568: {'lr': 0.0003502261026331282, 'samples': 10861056, 'steps': 56567, 'loss/train': 1.0944246053695679} 08/30/2021 23:23:22 - INFO - __main__ - Step 56569: {'lr': 0.0003502212409964985, 'samples': 10861248, 'steps': 56568, 'loss/train': 1.9922066926956177} 08/30/2021 23:23:24 - INFO - __main__ - Step 56570: {'lr': 0.00035021637931471075, 'samples': 10861440, 'steps': 56569, 'loss/train': 0.17963860929012299} 08/30/2021 23:23:24 - INFO - __main__ - Step 56571: {'lr': 0.00035021151758776693, 'samples': 10861632, 'steps': 56570, 'loss/train': 0.925829291343689} 08/30/2021 23:23:25 - INFO - __main__ - Step 56572: {'lr': 0.00035020665581566934, 'samples': 10861824, 'steps': 56571, 'loss/train': 1.26144540309906} 08/30/2021 23:23:25 - INFO - __main__ - Step 56573: {'lr': 0.0003502017939984202, 'samples': 10862016, 'steps': 56572, 'loss/train': 0.13490994274616241} 08/30/2021 23:23:25 - INFO - __main__ - Step 56574: {'lr': 0.0003501969321360217, 'samples': 10862208, 'steps': 56573, 'loss/train': 1.880601167678833} 08/30/2021 23:23:27 - INFO - __main__ - Step 56575: {'lr': 0.00035019207022847596, 'samples': 10862400, 'steps': 56574, 'loss/train': 1.5790601968765259} 08/30/2021 23:23:28 - INFO - __main__ - Step 56576: {'lr': 0.0003501872082757852, 'samples': 10862592, 'steps': 56575, 'loss/train': 2.4476702213287354} 08/30/2021 23:23:28 - INFO - __main__ - Step 56577: {'lr': 0.0003501823462779518, 'samples': 10862784, 'steps': 56576, 'loss/train': 1.4351774454116821} 08/30/2021 23:23:29 - INFO - __main__ - Step 56578: {'lr': 0.00035017748423497766, 'samples': 10862976, 'steps': 56577, 'loss/train': 5.935507297515869} 08/30/2021 23:23:29 - INFO - __main__ - Step 56579: {'lr': 0.00035017262214686505, 'samples': 10863168, 'steps': 56578, 'loss/train': 1.0497462749481201} 08/30/2021 23:23:29 - INFO - __main__ - Step 56580: {'lr': 0.00035016776001361625, 'samples': 10863360, 'steps': 56579, 'loss/train': 0.9540074467658997} 08/30/2021 23:23:31 - INFO - __main__ - Step 56581: {'lr': 0.00035016289783523335, 'samples': 10863552, 'steps': 56580, 'loss/train': 0.8396463990211487} 08/30/2021 23:23:31 - INFO - __main__ - Step 56582: {'lr': 0.00035015803561171864, 'samples': 10863744, 'steps': 56581, 'loss/train': 1.3876549005508423} 08/30/2021 23:23:32 - INFO - __main__ - Step 56583: {'lr': 0.0003501531733430743, 'samples': 10863936, 'steps': 56582, 'loss/train': 1.3443472385406494} 08/30/2021 23:23:32 - INFO - __main__ - Step 56584: {'lr': 0.00035014831102930246, 'samples': 10864128, 'steps': 56583, 'loss/train': 1.109544277191162} 08/30/2021 23:23:32 - INFO - __main__ - Step 56585: {'lr': 0.0003501434486704053, 'samples': 10864320, 'steps': 56584, 'loss/train': 1.376772403717041} 08/30/2021 23:23:34 - INFO - __main__ - Step 56586: {'lr': 0.0003501385862663851, 'samples': 10864512, 'steps': 56585, 'loss/train': 1.4383704662322998} 08/30/2021 23:23:35 - INFO - __main__ - Step 56587: {'lr': 0.00035013372381724397, 'samples': 10864704, 'steps': 56586, 'loss/train': 0.9084556698799133} 08/30/2021 23:23:35 - INFO - __main__ - Step 56588: {'lr': 0.00035012886132298413, 'samples': 10864896, 'steps': 56587, 'loss/train': 1.3339368104934692} 08/30/2021 23:23:35 - INFO - __main__ - Step 56589: {'lr': 0.0003501239987836078, 'samples': 10865088, 'steps': 56588, 'loss/train': 0.8530402183532715} 08/30/2021 23:23:36 - INFO - __main__ - Step 56590: {'lr': 0.00035011913619911706, 'samples': 10865280, 'steps': 56589, 'loss/train': 0.7599702477455139} 08/30/2021 23:23:37 - INFO - __main__ - Step 56591: {'lr': 0.0003501142735695143, 'samples': 10865472, 'steps': 56590, 'loss/train': 1.4078866243362427} 08/30/2021 23:23:38 - INFO - __main__ - Step 56592: {'lr': 0.0003501094108948015, 'samples': 10865664, 'steps': 56591, 'loss/train': 1.8844475746154785} 08/30/2021 23:23:38 - INFO - __main__ - Step 56593: {'lr': 0.000350104548174981, 'samples': 10865856, 'steps': 56592, 'loss/train': 1.167657494544983} 08/30/2021 23:23:38 - INFO - __main__ - Step 56594: {'lr': 0.00035009968541005487, 'samples': 10866048, 'steps': 56593, 'loss/train': 1.3433687686920166} 08/30/2021 23:23:39 - INFO - __main__ - Step 56595: {'lr': 0.00035009482260002544, 'samples': 10866240, 'steps': 56594, 'loss/train': 1.2328038215637207} 08/30/2021 23:23:40 - INFO - __main__ - Step 56596: {'lr': 0.00035008995974489477, 'samples': 10866432, 'steps': 56595, 'loss/train': 1.149763822555542} 08/30/2021 23:23:41 - INFO - __main__ - Step 56597: {'lr': 0.0003500850968446652, 'samples': 10866624, 'steps': 56596, 'loss/train': 1.0382232666015625} 08/30/2021 23:23:41 - INFO - __main__ - Step 56598: {'lr': 0.00035008023389933876, 'samples': 10866816, 'steps': 56597, 'loss/train': 1.346388816833496} 08/30/2021 23:23:41 - INFO - __main__ - Step 56599: {'lr': 0.00035007537090891766, 'samples': 10867008, 'steps': 56598, 'loss/train': 1.5968866348266602} 08/30/2021 23:23:42 - INFO - __main__ - Step 56600: {'lr': 0.0003500705078734042, 'samples': 10867200, 'steps': 56599, 'loss/train': 1.2582712173461914} 08/30/2021 23:23:43 - INFO - __main__ - Step 56601: {'lr': 0.0003500656447928005, 'samples': 10867392, 'steps': 56600, 'loss/train': 1.04105544090271} 08/30/2021 23:23:44 - INFO - __main__ - Step 56602: {'lr': 0.00035006078166710877, 'samples': 10867584, 'steps': 56601, 'loss/train': 0.8569434285163879} 08/30/2021 23:23:44 - INFO - __main__ - Step 56603: {'lr': 0.00035005591849633123, 'samples': 10867776, 'steps': 56602, 'loss/train': 1.3504642248153687} 08/30/2021 23:23:44 - INFO - __main__ - Step 56604: {'lr': 0.00035005105528047, 'samples': 10867968, 'steps': 56603, 'loss/train': 1.5873371362686157} 08/30/2021 23:23:45 - INFO - __main__ - Step 56605: {'lr': 0.00035004619201952736, 'samples': 10868160, 'steps': 56604, 'loss/train': 1.3577191829681396} 08/30/2021 23:23:46 - INFO - __main__ - Step 56606: {'lr': 0.00035004132871350535, 'samples': 10868352, 'steps': 56605, 'loss/train': 1.0760232210159302} 08/30/2021 23:23:47 - INFO - __main__ - Step 56607: {'lr': 0.0003500364653624063, 'samples': 10868544, 'steps': 56606, 'loss/train': 1.4970009326934814} 08/30/2021 23:23:47 - INFO - __main__ - Step 56608: {'lr': 0.0003500316019662324, 'samples': 10868736, 'steps': 56607, 'loss/train': 0.9397467374801636} 08/30/2021 23:23:47 - INFO - __main__ - Step 56609: {'lr': 0.00035002673852498577, 'samples': 10868928, 'steps': 56608, 'loss/train': 1.0903841257095337} 08/30/2021 23:23:48 - INFO - __main__ - Step 56610: {'lr': 0.0003500218750386687, 'samples': 10869120, 'steps': 56609, 'loss/train': 1.455434799194336} 08/30/2021 23:23:48 - INFO - __main__ - Step 56611: {'lr': 0.0003500170115072833, 'samples': 10869312, 'steps': 56610, 'loss/train': 0.5159206986427307} 08/30/2021 23:23:50 - INFO - __main__ - Step 56612: {'lr': 0.00035001214793083167, 'samples': 10869504, 'steps': 56611, 'loss/train': 1.6880433559417725} 08/30/2021 23:23:50 - INFO - __main__ - Step 56613: {'lr': 0.00035000728430931616, 'samples': 10869696, 'steps': 56612, 'loss/train': 1.370440125465393} 08/30/2021 23:23:51 - INFO - __main__ - Step 56614: {'lr': 0.000350002420642739, 'samples': 10869888, 'steps': 56613, 'loss/train': 0.8158270716667175} 08/30/2021 23:23:51 - INFO - __main__ - Step 56615: {'lr': 0.0003499975569311022, 'samples': 10870080, 'steps': 56614, 'loss/train': 1.3353149890899658} 08/30/2021 23:23:51 - INFO - __main__ - Step 56616: {'lr': 0.00034999269317440804, 'samples': 10870272, 'steps': 56615, 'loss/train': 1.0273514986038208} 08/30/2021 23:23:53 - INFO - __main__ - Step 56617: {'lr': 0.0003499878293726588, 'samples': 10870464, 'steps': 56616, 'loss/train': 1.0854586362838745} 08/30/2021 23:23:53 - INFO - __main__ - Step 56618: {'lr': 0.0003499829655258565, 'samples': 10870656, 'steps': 56617, 'loss/train': 1.2031031847000122} 08/30/2021 23:23:54 - INFO - __main__ - Step 56619: {'lr': 0.00034997810163400343, 'samples': 10870848, 'steps': 56618, 'loss/train': 1.568880558013916} 08/30/2021 23:23:54 - INFO - __main__ - Step 56620: {'lr': 0.0003499732376971018, 'samples': 10871040, 'steps': 56619, 'loss/train': 1.4042338132858276} 08/30/2021 23:23:54 - INFO - __main__ - Step 56621: {'lr': 0.0003499683737151538, 'samples': 10871232, 'steps': 56620, 'loss/train': 0.9379310607910156} 08/30/2021 23:23:56 - INFO - __main__ - Step 56622: {'lr': 0.0003499635096881615, 'samples': 10871424, 'steps': 56621, 'loss/train': 1.0947391986846924} 08/30/2021 23:23:57 - INFO - __main__ - Step 56623: {'lr': 0.0003499586456161273, 'samples': 10871616, 'steps': 56622, 'loss/train': 1.7475011348724365} 08/30/2021 23:23:57 - INFO - __main__ - Step 56624: {'lr': 0.0003499537814990532, 'samples': 10871808, 'steps': 56623, 'loss/train': 0.9848609566688538} 08/30/2021 23:23:58 - INFO - __main__ - Step 56625: {'lr': 0.0003499489173369415, 'samples': 10872000, 'steps': 56624, 'loss/train': 1.363951563835144} 08/30/2021 23:23:58 - INFO - __main__ - Step 56626: {'lr': 0.00034994405312979433, 'samples': 10872192, 'steps': 56625, 'loss/train': 0.3817296326160431} 08/30/2021 23:23:58 - INFO - __main__ - Step 56627: {'lr': 0.00034993918887761386, 'samples': 10872384, 'steps': 56626, 'loss/train': 1.5850646495819092} 08/30/2021 23:24:00 - INFO - __main__ - Step 56628: {'lr': 0.0003499343245804025, 'samples': 10872576, 'steps': 56627, 'loss/train': 0.09053673595190048} 08/30/2021 23:24:01 - INFO - __main__ - Step 56629: {'lr': 0.00034992946023816216, 'samples': 10872768, 'steps': 56628, 'loss/train': 1.0626736879348755} 08/30/2021 23:24:01 - INFO - __main__ - Step 56630: {'lr': 0.00034992459585089515, 'samples': 10872960, 'steps': 56629, 'loss/train': 1.168748378753662} 08/30/2021 23:24:02 - INFO - __main__ - Step 56631: {'lr': 0.00034991973141860366, 'samples': 10873152, 'steps': 56630, 'loss/train': 0.9976434707641602} 08/30/2021 23:24:02 - INFO - __main__ - Step 56632: {'lr': 0.00034991486694128986, 'samples': 10873344, 'steps': 56631, 'loss/train': 1.0813840627670288} 08/30/2021 23:24:03 - INFO - __main__ - Step 56633: {'lr': 0.000349910002418956, 'samples': 10873536, 'steps': 56632, 'loss/train': 0.950526773929596} 08/30/2021 23:24:04 - INFO - __main__ - Step 56634: {'lr': 0.0003499051378516043, 'samples': 10873728, 'steps': 56633, 'loss/train': 3.013725996017456} 08/30/2021 23:24:04 - INFO - __main__ - Step 56635: {'lr': 0.0003499002732392368, 'samples': 10873920, 'steps': 56634, 'loss/train': 1.4134043455123901} 08/30/2021 23:24:05 - INFO - __main__ - Step 56636: {'lr': 0.0003498954085818558, 'samples': 10874112, 'steps': 56635, 'loss/train': 1.0327482223510742} 08/30/2021 23:24:05 - INFO - __main__ - Step 56637: {'lr': 0.00034989054387946344, 'samples': 10874304, 'steps': 56636, 'loss/train': 1.5457371473312378} 08/30/2021 23:24:07 - INFO - __main__ - Step 56638: {'lr': 0.000349885679132062, 'samples': 10874496, 'steps': 56637, 'loss/train': 1.0211865901947021} 08/30/2021 23:24:07 - INFO - __main__ - Step 56639: {'lr': 0.00034988081433965355, 'samples': 10874688, 'steps': 56638, 'loss/train': 1.5246831178665161} 08/30/2021 23:24:07 - INFO - __main__ - Step 56640: {'lr': 0.00034987594950224043, 'samples': 10874880, 'steps': 56639, 'loss/train': 1.2874032258987427} 08/30/2021 23:24:08 - INFO - __main__ - Step 56641: {'lr': 0.0003498710846198247, 'samples': 10875072, 'steps': 56640, 'loss/train': 1.2398040294647217} 08/30/2021 23:24:08 - INFO - __main__ - Step 56642: {'lr': 0.0003498662196924086, 'samples': 10875264, 'steps': 56641, 'loss/train': 1.2766425609588623} 08/30/2021 23:24:08 - INFO - __main__ - Step 56643: {'lr': 0.00034986135471999424, 'samples': 10875456, 'steps': 56642, 'loss/train': 1.6594924926757812} 08/30/2021 23:24:10 - INFO - __main__ - Step 56644: {'lr': 0.00034985648970258404, 'samples': 10875648, 'steps': 56643, 'loss/train': 0.2604610025882721} 08/30/2021 23:24:10 - INFO - __main__ - Step 56645: {'lr': 0.00034985162464018, 'samples': 10875840, 'steps': 56644, 'loss/train': 1.013767123222351} 08/30/2021 23:24:11 - INFO - __main__ - Step 56646: {'lr': 0.00034984675953278433, 'samples': 10876032, 'steps': 56645, 'loss/train': 1.6603326797485352} 08/30/2021 23:24:11 - INFO - __main__ - Step 56647: {'lr': 0.00034984189438039926, 'samples': 10876224, 'steps': 56646, 'loss/train': 1.3607041835784912} 08/30/2021 23:24:11 - INFO - __main__ - Step 56648: {'lr': 0.00034983702918302696, 'samples': 10876416, 'steps': 56647, 'loss/train': 1.0277810096740723} 08/30/2021 23:24:13 - INFO - __main__ - Step 56649: {'lr': 0.00034983216394066964, 'samples': 10876608, 'steps': 56648, 'loss/train': 1.5826700925827026} 08/30/2021 23:24:13 - INFO - __main__ - Step 56650: {'lr': 0.00034982729865332953, 'samples': 10876800, 'steps': 56649, 'loss/train': 0.9722830057144165} 08/30/2021 23:24:14 - INFO - __main__ - Step 56651: {'lr': 0.0003498224333210087, 'samples': 10876992, 'steps': 56650, 'loss/train': 1.1788796186447144} 08/30/2021 23:24:14 - INFO - __main__ - Step 56652: {'lr': 0.0003498175679437095, 'samples': 10877184, 'steps': 56651, 'loss/train': 1.1582777500152588} 08/30/2021 23:24:14 - INFO - __main__ - Step 56653: {'lr': 0.00034981270252143406, 'samples': 10877376, 'steps': 56652, 'loss/train': 1.3549057245254517} 08/30/2021 23:24:16 - INFO - __main__ - Step 56654: {'lr': 0.0003498078370541845, 'samples': 10877568, 'steps': 56653, 'loss/train': 0.986901044845581} 08/30/2021 23:24:16 - INFO - __main__ - Step 56655: {'lr': 0.00034980297154196306, 'samples': 10877760, 'steps': 56654, 'loss/train': 0.9739421606063843} 08/30/2021 23:24:17 - INFO - __main__ - Step 56656: {'lr': 0.0003497981059847719, 'samples': 10877952, 'steps': 56655, 'loss/train': 2.0031135082244873} 08/30/2021 23:24:17 - INFO - __main__ - Step 56657: {'lr': 0.00034979324038261327, 'samples': 10878144, 'steps': 56656, 'loss/train': 1.2580126523971558} 08/30/2021 23:24:17 - INFO - __main__ - Step 56658: {'lr': 0.00034978837473548946, 'samples': 10878336, 'steps': 56657, 'loss/train': 1.0706145763397217} 08/30/2021 23:24:19 - INFO - __main__ - Step 56659: {'lr': 0.0003497835090434025, 'samples': 10878528, 'steps': 56658, 'loss/train': 0.9589179754257202} 08/30/2021 23:24:19 - INFO - __main__ - Step 56660: {'lr': 0.00034977864330635455, 'samples': 10878720, 'steps': 56659, 'loss/train': 1.719821810722351} 08/30/2021 23:24:20 - INFO - __main__ - Step 56661: {'lr': 0.00034977377752434797, 'samples': 10878912, 'steps': 56660, 'loss/train': 1.4731706380844116} 08/30/2021 23:24:20 - INFO - __main__ - Step 56662: {'lr': 0.0003497689116973848, 'samples': 10879104, 'steps': 56661, 'loss/train': 1.4630749225616455} 08/30/2021 23:24:20 - INFO - __main__ - Step 56663: {'lr': 0.00034976404582546736, 'samples': 10879296, 'steps': 56662, 'loss/train': 1.4608070850372314} 08/30/2021 23:24:22 - INFO - __main__ - Step 56664: {'lr': 0.00034975917990859773, 'samples': 10879488, 'steps': 56663, 'loss/train': 1.4274542331695557} 08/30/2021 23:24:22 - INFO - __main__ - Step 56665: {'lr': 0.00034975431394677827, 'samples': 10879680, 'steps': 56664, 'loss/train': 1.1619678735733032} 08/30/2021 23:24:23 - INFO - __main__ - Step 56666: {'lr': 0.0003497494479400109, 'samples': 10879872, 'steps': 56665, 'loss/train': 3.0610134601593018} 08/30/2021 23:24:23 - INFO - __main__ - Step 56667: {'lr': 0.00034974458188829805, 'samples': 10880064, 'steps': 56666, 'loss/train': 1.2682088613510132} 08/30/2021 23:24:23 - INFO - __main__ - Step 56668: {'lr': 0.0003497397157916418, 'samples': 10880256, 'steps': 56667, 'loss/train': 1.2507548332214355} 08/30/2021 23:24:25 - INFO - __main__ - Step 56669: {'lr': 0.00034973484965004437, 'samples': 10880448, 'steps': 56668, 'loss/train': 1.1496018171310425} 08/30/2021 23:24:26 - INFO - __main__ - Step 56670: {'lr': 0.0003497299834635079, 'samples': 10880640, 'steps': 56669, 'loss/train': 1.297471046447754} 08/30/2021 23:24:26 - INFO - __main__ - Step 56671: {'lr': 0.0003497251172320348, 'samples': 10880832, 'steps': 56670, 'loss/train': 0.5607073903083801} 08/30/2021 23:24:26 - INFO - __main__ - Step 56672: {'lr': 0.00034972025095562697, 'samples': 10881024, 'steps': 56671, 'loss/train': 1.6480882167816162} 08/30/2021 23:24:27 - INFO - __main__ - Step 56673: {'lr': 0.00034971538463428683, 'samples': 10881216, 'steps': 56672, 'loss/train': 0.019913876429200172} 08/30/2021 23:24:27 - INFO - __main__ - Step 56674: {'lr': 0.0003497105182680164, 'samples': 10881408, 'steps': 56673, 'loss/train': 1.1580127477645874} 08/30/2021 23:24:28 - INFO - __main__ - Step 56675: {'lr': 0.00034970565185681794, 'samples': 10881600, 'steps': 56674, 'loss/train': 1.5405628681182861} 08/30/2021 23:24:29 - INFO - __main__ - Step 56676: {'lr': 0.0003497007854006937, 'samples': 10881792, 'steps': 56675, 'loss/train': 1.0766236782073975} 08/30/2021 23:24:30 - INFO - __main__ - Step 56677: {'lr': 0.0003496959188996458, 'samples': 10881984, 'steps': 56676, 'loss/train': 1.1496772766113281} 08/30/2021 23:24:30 - INFO - __main__ - Step 56678: {'lr': 0.00034969105235367647, 'samples': 10882176, 'steps': 56677, 'loss/train': 2.5835843086242676} 08/30/2021 23:24:31 - INFO - __main__ - Step 56679: {'lr': 0.0003496861857627879, 'samples': 10882368, 'steps': 56678, 'loss/train': 1.807704210281372} 08/30/2021 23:24:31 - INFO - __main__ - Step 56680: {'lr': 0.0003496813191269822, 'samples': 10882560, 'steps': 56679, 'loss/train': 1.1195123195648193} 08/30/2021 23:24:31 - INFO - __main__ - Step 56681: {'lr': 0.0003496764524462617, 'samples': 10882752, 'steps': 56680, 'loss/train': 0.673947274684906} 08/30/2021 23:24:33 - INFO - __main__ - Step 56682: {'lr': 0.00034967158572062854, 'samples': 10882944, 'steps': 56681, 'loss/train': 1.3062444925308228} 08/30/2021 23:24:34 - INFO - __main__ - Step 56683: {'lr': 0.00034966671895008485, 'samples': 10883136, 'steps': 56682, 'loss/train': 1.4439219236373901} 08/30/2021 23:24:34 - INFO - __main__ - Step 56684: {'lr': 0.0003496618521346329, 'samples': 10883328, 'steps': 56683, 'loss/train': 1.268198847770691} 08/30/2021 23:24:35 - INFO - __main__ - Step 56685: {'lr': 0.00034965698527427493, 'samples': 10883520, 'steps': 56684, 'loss/train': 1.6766000986099243} 08/30/2021 23:24:35 - INFO - __main__ - Step 56686: {'lr': 0.00034965211836901293, 'samples': 10883712, 'steps': 56685, 'loss/train': 1.562535047531128} 08/30/2021 23:24:37 - INFO - __main__ - Step 56687: {'lr': 0.00034964725141884936, 'samples': 10883904, 'steps': 56686, 'loss/train': 1.2752197980880737} 08/30/2021 23:24:37 - INFO - __main__ - Step 56688: {'lr': 0.00034964238442378615, 'samples': 10884096, 'steps': 56687, 'loss/train': 1.4188339710235596} 08/30/2021 23:24:38 - INFO - __main__ - Step 56689: {'lr': 0.00034963751738382564, 'samples': 10884288, 'steps': 56688, 'loss/train': 0.740077018737793} 08/30/2021 23:24:38 - INFO - __main__ - Step 56690: {'lr': 0.00034963265029897006, 'samples': 10884480, 'steps': 56689, 'loss/train': 0.5276865363121033} 08/30/2021 23:24:39 - INFO - __main__ - Step 56691: {'lr': 0.00034962778316922156, 'samples': 10884672, 'steps': 56690, 'loss/train': 1.2058615684509277} 08/30/2021 23:24:40 - INFO - __main__ - Step 56692: {'lr': 0.0003496229159945823, 'samples': 10884864, 'steps': 56691, 'loss/train': 1.067211627960205} 08/30/2021 23:24:40 - INFO - __main__ - Step 56693: {'lr': 0.0003496180487750544, 'samples': 10885056, 'steps': 56692, 'loss/train': 0.30880534648895264} 08/30/2021 23:24:41 - INFO - __main__ - Step 56694: {'lr': 0.00034961318151064026, 'samples': 10885248, 'steps': 56693, 'loss/train': 1.328700065612793} 08/30/2021 23:24:41 - INFO - __main__ - Step 56695: {'lr': 0.00034960831420134187, 'samples': 10885440, 'steps': 56694, 'loss/train': 0.9614832401275635} 08/30/2021 23:24:41 - INFO - __main__ - Step 56696: {'lr': 0.0003496034468471616, 'samples': 10885632, 'steps': 56695, 'loss/train': 1.3397225141525269} 08/30/2021 23:24:43 - INFO - __main__ - Step 56697: {'lr': 0.00034959857944810144, 'samples': 10885824, 'steps': 56696, 'loss/train': 1.4187637567520142} 08/30/2021 23:24:43 - INFO - __main__ - Step 56698: {'lr': 0.0003495937120041638, 'samples': 10886016, 'steps': 56697, 'loss/train': 1.4306093454360962} 08/30/2021 23:24:44 - INFO - __main__ - Step 56699: {'lr': 0.00034958884451535073, 'samples': 10886208, 'steps': 56698, 'loss/train': 1.4021881818771362} 08/30/2021 23:24:44 - INFO - __main__ - Step 56700: {'lr': 0.00034958397698166445, 'samples': 10886400, 'steps': 56699, 'loss/train': 1.840881586074829} 08/30/2021 23:24:44 - INFO - __main__ - Step 56701: {'lr': 0.00034957910940310716, 'samples': 10886592, 'steps': 56700, 'loss/train': 0.26254332065582275} 08/30/2021 23:24:46 - INFO - __main__ - Step 56702: {'lr': 0.00034957424177968114, 'samples': 10886784, 'steps': 56701, 'loss/train': 1.6205044984817505} 08/30/2021 23:24:46 - INFO - __main__ - Step 56703: {'lr': 0.0003495693741113884, 'samples': 10886976, 'steps': 56702, 'loss/train': 1.2337194681167603} 08/30/2021 23:24:47 - INFO - __main__ - Step 56704: {'lr': 0.00034956450639823125, 'samples': 10887168, 'steps': 56703, 'loss/train': 1.2526735067367554} 08/30/2021 23:24:47 - INFO - __main__ - Step 56705: {'lr': 0.00034955963864021194, 'samples': 10887360, 'steps': 56704, 'loss/train': 0.7252885103225708} 08/30/2021 23:24:47 - INFO - __main__ - Step 56706: {'lr': 0.00034955477083733257, 'samples': 10887552, 'steps': 56705, 'loss/train': 0.5901670455932617} 08/30/2021 23:24:49 - INFO - __main__ - Step 56707: {'lr': 0.0003495499029895953, 'samples': 10887744, 'steps': 56706, 'loss/train': 1.3329631090164185} 08/30/2021 23:24:49 - INFO - __main__ - Step 56708: {'lr': 0.00034954503509700244, 'samples': 10887936, 'steps': 56707, 'loss/train': 1.696196436882019} 08/30/2021 23:24:50 - INFO - __main__ - Step 56709: {'lr': 0.0003495401671595561, 'samples': 10888128, 'steps': 56708, 'loss/train': 1.3466346263885498} 08/30/2021 23:24:50 - INFO - __main__ - Step 56710: {'lr': 0.0003495352991772585, 'samples': 10888320, 'steps': 56709, 'loss/train': 1.4730360507965088} 08/30/2021 23:24:50 - INFO - __main__ - Step 56711: {'lr': 0.0003495304311501118, 'samples': 10888512, 'steps': 56710, 'loss/train': 1.1673533916473389} 08/30/2021 23:24:52 - INFO - __main__ - Step 56712: {'lr': 0.0003495255630781183, 'samples': 10888704, 'steps': 56711, 'loss/train': 1.339542269706726} 08/30/2021 23:24:52 - INFO - __main__ - Step 56713: {'lr': 0.00034952069496128007, 'samples': 10888896, 'steps': 56712, 'loss/train': 1.0222094058990479} 08/30/2021 23:24:53 - INFO - __main__ - Step 56714: {'lr': 0.0003495158267995994, 'samples': 10889088, 'steps': 56713, 'loss/train': 1.2242183685302734} 08/30/2021 23:24:53 - INFO - __main__ - Step 56715: {'lr': 0.0003495109585930784, 'samples': 10889280, 'steps': 56714, 'loss/train': 1.646255612373352} 08/30/2021 23:24:53 - INFO - __main__ - Step 56716: {'lr': 0.0003495060903417192, 'samples': 10889472, 'steps': 56715, 'loss/train': 1.3751050233840942} 08/30/2021 23:24:55 - INFO - __main__ - Step 56717: {'lr': 0.00034950122204552417, 'samples': 10889664, 'steps': 56716, 'loss/train': 1.5611677169799805} 08/30/2021 23:24:55 - INFO - __main__ - Step 56718: {'lr': 0.00034949635370449546, 'samples': 10889856, 'steps': 56717, 'loss/train': 1.5401617288589478} 08/30/2021 23:24:56 - INFO - __main__ - Step 56719: {'lr': 0.00034949148531863517, 'samples': 10890048, 'steps': 56718, 'loss/train': 1.436754822731018} 08/30/2021 23:24:56 - INFO - __main__ - Step 56720: {'lr': 0.0003494866168879456, 'samples': 10890240, 'steps': 56719, 'loss/train': 1.4176748991012573} 08/30/2021 23:24:56 - INFO - __main__ - Step 56721: {'lr': 0.0003494817484124289, 'samples': 10890432, 'steps': 56720, 'loss/train': 1.3382786512374878} 08/30/2021 23:24:57 - INFO - __main__ - Step 56722: {'lr': 0.0003494768798920872, 'samples': 10890624, 'steps': 56721, 'loss/train': 1.5689197778701782} 08/30/2021 23:24:59 - INFO - __main__ - Step 56723: {'lr': 0.0003494720113269227, 'samples': 10890816, 'steps': 56722, 'loss/train': 1.1819244623184204} 08/30/2021 23:24:59 - INFO - __main__ - Step 56724: {'lr': 0.00034946714271693783, 'samples': 10891008, 'steps': 56723, 'loss/train': 1.3029106855392456} 08/30/2021 23:25:00 - INFO - __main__ - Step 56725: {'lr': 0.0003494622740621345, 'samples': 10891200, 'steps': 56724, 'loss/train': 1.4662553071975708} 08/30/2021 23:25:00 - INFO - __main__ - Step 56726: {'lr': 0.00034945740536251505, 'samples': 10891392, 'steps': 56725, 'loss/train': 1.4535045623779297} 08/30/2021 23:25:00 - INFO - __main__ - Step 56727: {'lr': 0.0003494525366180815, 'samples': 10891584, 'steps': 56726, 'loss/train': 0.8776691555976868} 08/30/2021 23:25:01 - INFO - __main__ - Step 56728: {'lr': 0.0003494476678288363, 'samples': 10891776, 'steps': 56727, 'loss/train': 0.9184784293174744} 08/30/2021 23:25:02 - INFO - __main__ - Step 56729: {'lr': 0.00034944279899478146, 'samples': 10891968, 'steps': 56728, 'loss/train': 0.019302329048514366} 08/30/2021 23:25:03 - INFO - __main__ - Step 56730: {'lr': 0.00034943793011591926, 'samples': 10892160, 'steps': 56729, 'loss/train': 1.2300323247909546} 08/30/2021 23:25:03 - INFO - __main__ - Step 56731: {'lr': 0.0003494330611922518, 'samples': 10892352, 'steps': 56730, 'loss/train': 1.545109510421753} 08/30/2021 23:25:03 - INFO - __main__ - Step 56732: {'lr': 0.0003494281922237814, 'samples': 10892544, 'steps': 56731, 'loss/train': 0.9021186232566833} 08/30/2021 23:25:04 - INFO - __main__ - Step 56733: {'lr': 0.0003494233232105102, 'samples': 10892736, 'steps': 56732, 'loss/train': 1.418137550354004} 08/30/2021 23:25:06 - INFO - __main__ - Step 56734: {'lr': 0.0003494184541524403, 'samples': 10892928, 'steps': 56733, 'loss/train': 1.6505248546600342} 08/30/2021 23:25:06 - INFO - __main__ - Step 56735: {'lr': 0.0003494135850495741, 'samples': 10893120, 'steps': 56734, 'loss/train': 1.2418785095214844} 08/30/2021 23:25:07 - INFO - __main__ - Step 56736: {'lr': 0.0003494087159019136, 'samples': 10893312, 'steps': 56735, 'loss/train': 1.7590183019638062} 08/30/2021 23:25:07 - INFO - __main__ - Step 56737: {'lr': 0.0003494038467094611, 'samples': 10893504, 'steps': 56736, 'loss/train': 0.854834258556366} 08/30/2021 23:25:07 - INFO - __main__ - Step 56738: {'lr': 0.00034939897747221873, 'samples': 10893696, 'steps': 56737, 'loss/train': 0.8972604870796204} 08/30/2021 23:25:09 - INFO - __main__ - Step 56739: {'lr': 0.00034939410819018874, 'samples': 10893888, 'steps': 56738, 'loss/train': 1.434583067893982} 08/30/2021 23:25:09 - INFO - __main__ - Step 56740: {'lr': 0.0003493892388633733, 'samples': 10894080, 'steps': 56739, 'loss/train': 1.1860287189483643} 08/30/2021 23:25:10 - INFO - __main__ - Step 56741: {'lr': 0.0003493843694917745, 'samples': 10894272, 'steps': 56740, 'loss/train': 1.689272403717041} 08/30/2021 23:25:10 - INFO - __main__ - Step 56742: {'lr': 0.00034937950007539475, 'samples': 10894464, 'steps': 56741, 'loss/train': 1.592295527458191} 08/30/2021 23:25:10 - INFO - __main__ - Step 56743: {'lr': 0.0003493746306142361, 'samples': 10894656, 'steps': 56742, 'loss/train': 1.311223030090332} 08/30/2021 23:25:12 - INFO - __main__ - Step 56744: {'lr': 0.00034936976110830077, 'samples': 10894848, 'steps': 56743, 'loss/train': 1.7671316862106323} 08/30/2021 23:25:12 - INFO - __main__ - Step 56745: {'lr': 0.000349364891557591, 'samples': 10895040, 'steps': 56744, 'loss/train': 1.3961111307144165} 08/30/2021 23:25:13 - INFO - __main__ - Step 56746: {'lr': 0.00034936002196210895, 'samples': 10895232, 'steps': 56745, 'loss/train': 0.8962607383728027} 08/30/2021 23:25:13 - INFO - __main__ - Step 56747: {'lr': 0.0003493551523218567, 'samples': 10895424, 'steps': 56746, 'loss/train': 1.892096996307373} 08/30/2021 23:25:13 - INFO - __main__ - Step 56748: {'lr': 0.0003493502826368366, 'samples': 10895616, 'steps': 56747, 'loss/train': 1.541806697845459} 08/30/2021 23:25:15 - INFO - __main__ - Step 56749: {'lr': 0.0003493454129070508, 'samples': 10895808, 'steps': 56748, 'loss/train': 0.867680013179779} 08/30/2021 23:25:15 - INFO - __main__ - Step 56750: {'lr': 0.0003493405431325015, 'samples': 10896000, 'steps': 56749, 'loss/train': 0.8825818300247192} 08/30/2021 23:25:16 - INFO - __main__ - Step 56751: {'lr': 0.0003493356733131909, 'samples': 10896192, 'steps': 56750, 'loss/train': 1.3202054500579834} 08/30/2021 23:25:16 - INFO - __main__ - Step 56752: {'lr': 0.0003493308034491212, 'samples': 10896384, 'steps': 56751, 'loss/train': 1.2743120193481445} 08/30/2021 23:25:16 - INFO - __main__ - Step 56753: {'lr': 0.00034932593354029454, 'samples': 10896576, 'steps': 56752, 'loss/train': 1.5536842346191406} 08/30/2021 23:25:17 - INFO - __main__ - Step 56754: {'lr': 0.00034932106358671314, 'samples': 10896768, 'steps': 56753, 'loss/train': 0.7229862809181213} 08/30/2021 23:25:19 - INFO - __main__ - Step 56755: {'lr': 0.0003493161935883792, 'samples': 10896960, 'steps': 56754, 'loss/train': 1.5224770307540894} 08/30/2021 23:25:19 - INFO - __main__ - Step 56756: {'lr': 0.0003493113235452949, 'samples': 10897152, 'steps': 56755, 'loss/train': 1.5602049827575684} 08/30/2021 23:25:19 - INFO - __main__ - Step 56757: {'lr': 0.00034930645345746246, 'samples': 10897344, 'steps': 56756, 'loss/train': 0.06777407974004745} 08/30/2021 23:25:20 - INFO - __main__ - Step 56758: {'lr': 0.0003493015833248841, 'samples': 10897536, 'steps': 56757, 'loss/train': 0.028674036264419556} 08/30/2021 23:25:20 - INFO - __main__ - Step 56759: {'lr': 0.00034929671314756197, 'samples': 10897728, 'steps': 56758, 'loss/train': 1.5826789140701294} 08/30/2021 23:25:20 - INFO - __main__ - Step 56760: {'lr': 0.0003492918429254983, 'samples': 10897920, 'steps': 56759, 'loss/train': 1.2855006456375122} 08/30/2021 23:25:22 - INFO - __main__ - Step 56761: {'lr': 0.00034928697265869515, 'samples': 10898112, 'steps': 56760, 'loss/train': 1.0997174978256226} 08/30/2021 23:25:23 - INFO - __main__ - Step 56762: {'lr': 0.00034928210234715497, 'samples': 10898304, 'steps': 56761, 'loss/train': 1.3132038116455078} 08/30/2021 23:25:23 - INFO - __main__ - Step 56763: {'lr': 0.0003492772319908797, 'samples': 10898496, 'steps': 56762, 'loss/train': 1.33661687374115} 08/30/2021 23:25:24 - INFO - __main__ - Step 56764: {'lr': 0.0003492723615898716, 'samples': 10898688, 'steps': 56763, 'loss/train': 1.5947891473770142} 08/30/2021 23:25:24 - INFO - __main__ - Step 56765: {'lr': 0.000349267491144133, 'samples': 10898880, 'steps': 56764, 'loss/train': 1.292133092880249} 08/30/2021 23:25:24 - INFO - __main__ - Step 56766: {'lr': 0.00034926262065366597, 'samples': 10899072, 'steps': 56765, 'loss/train': 0.025055456906557083} 08/30/2021 23:25:26 - INFO - __main__ - Step 56767: {'lr': 0.0003492577501184727, 'samples': 10899264, 'steps': 56766, 'loss/train': 1.1451060771942139} 08/30/2021 23:25:26 - INFO - __main__ - Step 56768: {'lr': 0.0003492528795385556, 'samples': 10899456, 'steps': 56767, 'loss/train': 1.6359162330627441} 08/30/2021 23:25:26 - INFO - __main__ - Step 56769: {'lr': 0.00034924800891391645, 'samples': 10899648, 'steps': 56768, 'loss/train': 1.3535114526748657} 08/30/2021 23:25:27 - INFO - __main__ - Step 56770: {'lr': 0.0003492431382445578, 'samples': 10899840, 'steps': 56769, 'loss/train': 1.6838936805725098} 08/30/2021 23:25:27 - INFO - __main__ - Step 56771: {'lr': 0.00034923826753048163, 'samples': 10900032, 'steps': 56770, 'loss/train': 1.3130229711532593} 08/30/2021 23:25:29 - INFO - __main__ - Step 56772: {'lr': 0.00034923339677169033, 'samples': 10900224, 'steps': 56771, 'loss/train': 1.0998550653457642} 08/30/2021 23:25:29 - INFO - __main__ - Step 56773: {'lr': 0.000349228525968186, 'samples': 10900416, 'steps': 56772, 'loss/train': 0.7550140619277954} 08/30/2021 23:25:30 - INFO - __main__ - Step 56774: {'lr': 0.0003492236551199707, 'samples': 10900608, 'steps': 56773, 'loss/train': 1.5905202627182007} 08/30/2021 23:25:30 - INFO - __main__ - Step 56775: {'lr': 0.0003492187842270469, 'samples': 10900800, 'steps': 56774, 'loss/train': 1.6662850379943848} 08/30/2021 23:25:30 - INFO - __main__ - Step 56776: {'lr': 0.00034921391328941655, 'samples': 10900992, 'steps': 56775, 'loss/train': 1.7697941064834595} 08/30/2021 23:25:31 - INFO - __main__ - Step 56777: {'lr': 0.00034920904230708195, 'samples': 10901184, 'steps': 56776, 'loss/train': 1.188982605934143} 08/30/2021 23:25:32 - INFO - __main__ - Step 56778: {'lr': 0.0003492041712800453, 'samples': 10901376, 'steps': 56777, 'loss/train': 1.1459029912948608} 08/30/2021 23:25:33 - INFO - __main__ - Step 56779: {'lr': 0.0003491993002083088, 'samples': 10901568, 'steps': 56778, 'loss/train': 1.34610915184021} 08/30/2021 23:25:33 - INFO - __main__ - Step 56780: {'lr': 0.00034919442909187465, 'samples': 10901760, 'steps': 56779, 'loss/train': 1.0940742492675781} 08/30/2021 23:25:33 - INFO - __main__ - Step 56781: {'lr': 0.000349189557930745, 'samples': 10901952, 'steps': 56780, 'loss/train': 1.2429697513580322} 08/30/2021 23:25:34 - INFO - __main__ - Step 56782: {'lr': 0.000349184686724922, 'samples': 10902144, 'steps': 56781, 'loss/train': 1.6308033466339111} 08/30/2021 23:25:35 - INFO - __main__ - Step 56783: {'lr': 0.00034917981547440797, 'samples': 10902336, 'steps': 56782, 'loss/train': 1.8578672409057617} 08/30/2021 23:25:36 - INFO - __main__ - Step 56784: {'lr': 0.00034917494417920504, 'samples': 10902528, 'steps': 56783, 'loss/train': 1.044552206993103} 08/30/2021 23:25:36 - INFO - __main__ - Step 56785: {'lr': 0.0003491700728393154, 'samples': 10902720, 'steps': 56784, 'loss/train': 1.0783411264419556} 08/30/2021 23:25:36 - INFO - __main__ - Step 56786: {'lr': 0.0003491652014547413, 'samples': 10902912, 'steps': 56785, 'loss/train': 1.473204493522644} 08/30/2021 23:25:37 - INFO - __main__ - Step 56787: {'lr': 0.00034916033002548486, 'samples': 10903104, 'steps': 56786, 'loss/train': 1.4723454713821411} 08/30/2021 23:25:38 - INFO - __main__ - Step 56788: {'lr': 0.00034915545855154827, 'samples': 10903296, 'steps': 56787, 'loss/train': 1.5283957719802856} 08/30/2021 23:25:39 - INFO - __main__ - Step 56789: {'lr': 0.00034915058703293377, 'samples': 10903488, 'steps': 56788, 'loss/train': 1.1729637384414673} 08/30/2021 23:25:39 - INFO - __main__ - Step 56790: {'lr': 0.0003491457154696436, 'samples': 10903680, 'steps': 56789, 'loss/train': 1.6620131731033325} 08/30/2021 23:25:40 - INFO - __main__ - Step 56791: {'lr': 0.0003491408438616798, 'samples': 10903872, 'steps': 56790, 'loss/train': 1.578089714050293} 08/30/2021 23:25:40 - INFO - __main__ - Step 56792: {'lr': 0.0003491359722090448, 'samples': 10904064, 'steps': 56791, 'loss/train': 0.05951777100563049} 08/30/2021 23:25:42 - INFO - __main__ - Step 56793: {'lr': 0.00034913110051174056, 'samples': 10904256, 'steps': 56792, 'loss/train': 1.0769128799438477} 08/30/2021 23:25:42 - INFO - __main__ - Step 56794: {'lr': 0.0003491262287697694, 'samples': 10904448, 'steps': 56793, 'loss/train': 1.943314552307129} 08/30/2021 23:25:43 - INFO - __main__ - Step 56795: {'lr': 0.0003491213569831335, 'samples': 10904640, 'steps': 56794, 'loss/train': 0.9825982451438904} 08/30/2021 23:25:43 - INFO - __main__ - Step 56796: {'lr': 0.000349116485151835, 'samples': 10904832, 'steps': 56795, 'loss/train': 0.2731589078903198} 08/30/2021 23:25:44 - INFO - __main__ - Step 56797: {'lr': 0.00034911161327587625, 'samples': 10905024, 'steps': 56796, 'loss/train': 0.3056858479976654} 08/30/2021 23:25:45 - INFO - __main__ - Step 56798: {'lr': 0.00034910674135525926, 'samples': 10905216, 'steps': 56797, 'loss/train': 1.4800364971160889} 08/30/2021 23:25:46 - INFO - __main__ - Step 56799: {'lr': 0.0003491018693899863, 'samples': 10905408, 'steps': 56798, 'loss/train': 1.1802165508270264} 08/30/2021 23:25:46 - INFO - __main__ - Step 56800: {'lr': 0.00034909699738005964, 'samples': 10905600, 'steps': 56799, 'loss/train': 1.3026938438415527} 08/30/2021 23:25:46 - INFO - __main__ - Step 56801: {'lr': 0.0003490921253254813, 'samples': 10905792, 'steps': 56800, 'loss/train': 1.7394874095916748} 08/30/2021 23:25:47 - INFO - __main__ - Step 56802: {'lr': 0.00034908725322625365, 'samples': 10905984, 'steps': 56801, 'loss/train': 1.2614617347717285} 08/30/2021 23:25:47 - INFO - __main__ - Step 56803: {'lr': 0.0003490823810823788, 'samples': 10906176, 'steps': 56802, 'loss/train': 1.4205695390701294} 08/30/2021 23:25:48 - INFO - __main__ - Step 56804: {'lr': 0.0003490775088938589, 'samples': 10906368, 'steps': 56803, 'loss/train': 1.3422627449035645} 08/30/2021 23:25:49 - INFO - __main__ - Step 56805: {'lr': 0.00034907263666069624, 'samples': 10906560, 'steps': 56804, 'loss/train': 1.2066166400909424} 08/30/2021 23:25:49 - INFO - __main__ - Step 56806: {'lr': 0.000349067764382893, 'samples': 10906752, 'steps': 56805, 'loss/train': 1.4579092264175415} 08/30/2021 23:25:50 - INFO - __main__ - Step 56807: {'lr': 0.0003490628920604513, 'samples': 10906944, 'steps': 56806, 'loss/train': 1.0985229015350342} 08/30/2021 23:25:50 - INFO - __main__ - Step 56808: {'lr': 0.00034905801969337347, 'samples': 10907136, 'steps': 56807, 'loss/train': 1.2382231950759888} 08/30/2021 23:25:51 - INFO - __main__ - Step 56809: {'lr': 0.0003490531472816616, 'samples': 10907328, 'steps': 56808, 'loss/train': 1.6478755474090576} 08/30/2021 23:25:52 - INFO - __main__ - Step 56810: {'lr': 0.00034904827482531785, 'samples': 10907520, 'steps': 56809, 'loss/train': 1.44677734375} 08/30/2021 23:25:52 - INFO - __main__ - Step 56811: {'lr': 0.0003490434023243445, 'samples': 10907712, 'steps': 56810, 'loss/train': 0.957885205745697} 08/30/2021 23:25:53 - INFO - __main__ - Step 56812: {'lr': 0.0003490385297787438, 'samples': 10907904, 'steps': 56811, 'loss/train': 1.7826210260391235} 08/30/2021 23:25:53 - INFO - __main__ - Step 56813: {'lr': 0.00034903365718851775, 'samples': 10908096, 'steps': 56812, 'loss/train': 1.4312103986740112} 08/30/2021 23:25:55 - INFO - __main__ - Step 56814: {'lr': 0.00034902878455366876, 'samples': 10908288, 'steps': 56813, 'loss/train': 1.0159746408462524} 08/30/2021 23:25:55 - INFO - __main__ - Step 56815: {'lr': 0.0003490239118741989, 'samples': 10908480, 'steps': 56814, 'loss/train': 1.5728769302368164} 08/30/2021 23:25:56 - INFO - __main__ - Step 56816: {'lr': 0.00034901903915011035, 'samples': 10908672, 'steps': 56815, 'loss/train': 0.8968613147735596} 08/30/2021 23:25:56 - INFO - __main__ - Step 56817: {'lr': 0.0003490141663814054, 'samples': 10908864, 'steps': 56816, 'loss/train': 1.3985726833343506} 08/30/2021 23:25:56 - INFO - __main__ - Step 56818: {'lr': 0.00034900929356808613, 'samples': 10909056, 'steps': 56817, 'loss/train': 0.9104251861572266} 08/30/2021 23:25:58 - INFO - __main__ - Step 56819: {'lr': 0.00034900442071015485, 'samples': 10909248, 'steps': 56818, 'loss/train': 0.7776812314987183} 08/30/2021 23:25:59 - INFO - __main__ - Step 56820: {'lr': 0.00034899954780761373, 'samples': 10909440, 'steps': 56819, 'loss/train': 0.6282814741134644} 08/30/2021 23:25:59 - INFO - __main__ - Step 56821: {'lr': 0.00034899467486046486, 'samples': 10909632, 'steps': 56820, 'loss/train': 0.8602657318115234} 08/30/2021 23:25:59 - INFO - __main__ - Step 56822: {'lr': 0.0003489898018687106, 'samples': 10909824, 'steps': 56821, 'loss/train': 3.6292970180511475} 08/30/2021 23:26:00 - INFO - __main__ - Step 56823: {'lr': 0.000348984928832353, 'samples': 10910016, 'steps': 56822, 'loss/train': 5.065361976623535} 08/30/2021 23:26:00 - INFO - __main__ - Step 56824: {'lr': 0.00034898005575139437, 'samples': 10910208, 'steps': 56823, 'loss/train': 0.7015039920806885} 08/30/2021 23:26:02 - INFO - __main__ - Step 56825: {'lr': 0.00034897518262583683, 'samples': 10910400, 'steps': 56824, 'loss/train': 1.567171573638916} 08/30/2021 23:26:02 - INFO - __main__ - Step 56826: {'lr': 0.00034897030945568264, 'samples': 10910592, 'steps': 56825, 'loss/train': 0.8680390119552612} 08/30/2021 23:26:02 - INFO - __main__ - Step 56827: {'lr': 0.0003489654362409339, 'samples': 10910784, 'steps': 56826, 'loss/train': 1.1843427419662476} 08/30/2021 23:26:03 - INFO - __main__ - Step 56828: {'lr': 0.00034896056298159287, 'samples': 10910976, 'steps': 56827, 'loss/train': 1.2504146099090576} 08/30/2021 23:26:03 - INFO - __main__ - Step 56829: {'lr': 0.0003489556896776618, 'samples': 10911168, 'steps': 56828, 'loss/train': 0.038397036492824554} 08/30/2021 23:26:05 - INFO - __main__ - Step 56830: {'lr': 0.00034895081632914274, 'samples': 10911360, 'steps': 56829, 'loss/train': 1.4052339792251587} 08/30/2021 23:26:05 - INFO - __main__ - Step 56831: {'lr': 0.000348945942936038, 'samples': 10911552, 'steps': 56830, 'loss/train': 0.9070042967796326} 08/30/2021 23:26:05 - INFO - __main__ - Step 56832: {'lr': 0.0003489410694983497, 'samples': 10911744, 'steps': 56831, 'loss/train': 1.30417001247406} 08/30/2021 23:26:06 - INFO - __main__ - Step 56833: {'lr': 0.00034893619601608015, 'samples': 10911936, 'steps': 56832, 'loss/train': 1.014424443244934} 08/30/2021 23:26:06 - INFO - __main__ - Step 56834: {'lr': 0.0003489313224892314, 'samples': 10912128, 'steps': 56833, 'loss/train': 1.1177945137023926} 08/30/2021 23:26:08 - INFO - __main__ - Step 56835: {'lr': 0.0003489264489178058, 'samples': 10912320, 'steps': 56834, 'loss/train': 1.3818050622940063} 08/30/2021 23:26:08 - INFO - __main__ - Step 56836: {'lr': 0.00034892157530180546, 'samples': 10912512, 'steps': 56835, 'loss/train': 0.2655915915966034} 08/30/2021 23:26:09 - INFO - __main__ - Step 56837: {'lr': 0.0003489167016412326, 'samples': 10912704, 'steps': 56836, 'loss/train': 2.8492355346679688} 08/30/2021 23:26:09 - INFO - __main__ - Step 56838: {'lr': 0.00034891182793608935, 'samples': 10912896, 'steps': 56837, 'loss/train': 1.2801843881607056} 08/30/2021 23:26:09 - INFO - __main__ - Step 56839: {'lr': 0.000348906954186378, 'samples': 10913088, 'steps': 56838, 'loss/train': 0.9203802347183228} 08/30/2021 23:26:11 - INFO - __main__ - Step 56840: {'lr': 0.0003489020803921007, 'samples': 10913280, 'steps': 56839, 'loss/train': 2.1670665740966797} 08/30/2021 23:26:11 - INFO - __main__ - Step 56841: {'lr': 0.00034889720655325955, 'samples': 10913472, 'steps': 56840, 'loss/train': 1.4316847324371338} 08/30/2021 23:26:12 - INFO - __main__ - Step 56842: {'lr': 0.000348892332669857, 'samples': 10913664, 'steps': 56841, 'loss/train': 1.415387511253357} 08/30/2021 23:26:12 - INFO - __main__ - Step 56843: {'lr': 0.000348887458741895, 'samples': 10913856, 'steps': 56842, 'loss/train': 1.4527703523635864} 08/30/2021 23:26:12 - INFO - __main__ - Step 56844: {'lr': 0.0003488825847693758, 'samples': 10914048, 'steps': 56843, 'loss/train': 1.2186700105667114} 08/30/2021 23:26:14 - INFO - __main__ - Step 56845: {'lr': 0.0003488777107523017, 'samples': 10914240, 'steps': 56844, 'loss/train': 1.547472596168518} 08/30/2021 23:26:15 - INFO - __main__ - Step 56846: {'lr': 0.0003488728366906748, 'samples': 10914432, 'steps': 56845, 'loss/train': 0.6210740208625793} 08/30/2021 23:26:15 - INFO - __main__ - Step 56847: {'lr': 0.0003488679625844974, 'samples': 10914624, 'steps': 56846, 'loss/train': 1.1037166118621826} 08/30/2021 23:26:16 - INFO - __main__ - Step 56848: {'lr': 0.0003488630884337715, 'samples': 10914816, 'steps': 56847, 'loss/train': 0.44309526681900024} 08/30/2021 23:26:16 - INFO - __main__ - Step 56849: {'lr': 0.0003488582142384995, 'samples': 10915008, 'steps': 56848, 'loss/train': 1.3238654136657715} 08/30/2021 23:26:16 - INFO - __main__ - Step 56850: {'lr': 0.00034885333999868344, 'samples': 10915200, 'steps': 56849, 'loss/train': 1.545961618423462} 08/30/2021 23:26:18 - INFO - __main__ - Step 56851: {'lr': 0.0003488484657143257, 'samples': 10915392, 'steps': 56850, 'loss/train': 1.3489965200424194} 08/30/2021 23:26:18 - INFO - __main__ - Step 56852: {'lr': 0.00034884359138542825, 'samples': 10915584, 'steps': 56851, 'loss/train': 0.876106858253479} 08/30/2021 23:26:19 - INFO - __main__ - Step 56853: {'lr': 0.0003488387170119935, 'samples': 10915776, 'steps': 56852, 'loss/train': 1.4807602167129517} 08/30/2021 23:26:19 - INFO - __main__ - Step 56854: {'lr': 0.0003488338425940235, 'samples': 10915968, 'steps': 56853, 'loss/train': 1.5972204208374023} 08/30/2021 23:26:19 - INFO - __main__ - Step 56855: {'lr': 0.00034882896813152056, 'samples': 10916160, 'steps': 56854, 'loss/train': 1.1075756549835205} 08/30/2021 23:26:21 - INFO - __main__ - Step 56856: {'lr': 0.0003488240936244867, 'samples': 10916352, 'steps': 56855, 'loss/train': 1.2491711378097534} 08/30/2021 23:26:21 - INFO - __main__ - Step 56857: {'lr': 0.0003488192190729243, 'samples': 10916544, 'steps': 56856, 'loss/train': 0.11716333776712418} 08/30/2021 23:26:22 - INFO - __main__ - Step 56858: {'lr': 0.0003488143444768355, 'samples': 10916736, 'steps': 56857, 'loss/train': 1.8950672149658203} 08/30/2021 23:26:22 - INFO - __main__ - Step 56859: {'lr': 0.0003488094698362224, 'samples': 10916928, 'steps': 56858, 'loss/train': 1.0557746887207031} 08/30/2021 23:26:22 - INFO - __main__ - Step 56860: {'lr': 0.00034880459515108735, 'samples': 10917120, 'steps': 56859, 'loss/train': 1.2659811973571777} 08/30/2021 23:26:24 - INFO - __main__ - Step 56861: {'lr': 0.0003487997204214325, 'samples': 10917312, 'steps': 56860, 'loss/train': 1.2838890552520752} 08/30/2021 23:26:25 - INFO - __main__ - Step 56862: {'lr': 0.00034879484564725993, 'samples': 10917504, 'steps': 56861, 'loss/train': 1.4361438751220703} 08/30/2021 23:26:25 - INFO - __main__ - Step 56863: {'lr': 0.00034878997082857195, 'samples': 10917696, 'steps': 56862, 'loss/train': 1.1798934936523438} 08/30/2021 23:26:25 - INFO - __main__ - Step 56864: {'lr': 0.0003487850959653708, 'samples': 10917888, 'steps': 56863, 'loss/train': 1.8737319707870483} 08/30/2021 23:26:26 - INFO - __main__ - Step 56865: {'lr': 0.0003487802210576585, 'samples': 10918080, 'steps': 56864, 'loss/train': 0.5395573973655701} 08/30/2021 23:26:27 - INFO - __main__ - Step 56866: {'lr': 0.0003487753461054375, 'samples': 10918272, 'steps': 56865, 'loss/train': 1.3379285335540771} 08/30/2021 23:26:28 - INFO - __main__ - Step 56867: {'lr': 0.00034877047110870975, 'samples': 10918464, 'steps': 56866, 'loss/train': 0.8064634799957275} 08/30/2021 23:26:28 - INFO - __main__ - Step 56868: {'lr': 0.0003487655960674776, 'samples': 10918656, 'steps': 56867, 'loss/train': 1.0082318782806396} 08/30/2021 23:26:28 - INFO - __main__ - Step 56869: {'lr': 0.00034876072098174315, 'samples': 10918848, 'steps': 56868, 'loss/train': 1.1583197116851807} 08/30/2021 23:26:29 - INFO - __main__ - Step 56870: {'lr': 0.00034875584585150864, 'samples': 10919040, 'steps': 56869, 'loss/train': 1.3216029405593872} 08/30/2021 23:26:30 - INFO - __main__ - Step 56871: {'lr': 0.0003487509706767763, 'samples': 10919232, 'steps': 56870, 'loss/train': 1.0175455808639526} 08/30/2021 23:26:31 - INFO - __main__ - Step 56872: {'lr': 0.00034874609545754826, 'samples': 10919424, 'steps': 56871, 'loss/train': 1.420638918876648} 08/30/2021 23:26:31 - INFO - __main__ - Step 56873: {'lr': 0.00034874122019382684, 'samples': 10919616, 'steps': 56872, 'loss/train': 1.0788238048553467} 08/30/2021 23:26:31 - INFO - __main__ - Step 56874: {'lr': 0.0003487363448856141, 'samples': 10919808, 'steps': 56873, 'loss/train': 1.0165424346923828} 08/30/2021 23:26:32 - INFO - __main__ - Step 56875: {'lr': 0.00034873146953291224, 'samples': 10920000, 'steps': 56874, 'loss/train': 2.25630521774292} 08/30/2021 23:26:33 - INFO - __main__ - Step 56876: {'lr': 0.0003487265941357236, 'samples': 10920192, 'steps': 56875, 'loss/train': 1.7111485004425049} 08/30/2021 23:26:34 - INFO - __main__ - Step 56877: {'lr': 0.00034872171869405015, 'samples': 10920384, 'steps': 56876, 'loss/train': 0.8773935437202454} 08/30/2021 23:26:34 - INFO - __main__ - Step 56878: {'lr': 0.0003487168432078943, 'samples': 10920576, 'steps': 56877, 'loss/train': 1.4601478576660156} 08/30/2021 23:26:34 - INFO - __main__ - Step 56879: {'lr': 0.0003487119676772582, 'samples': 10920768, 'steps': 56878, 'loss/train': 1.274673342704773} 08/30/2021 23:26:35 - INFO - __main__ - Step 56880: {'lr': 0.00034870709210214397, 'samples': 10920960, 'steps': 56879, 'loss/train': 1.341761589050293} 08/30/2021 23:26:35 - INFO - __main__ - Step 56881: {'lr': 0.00034870221648255383, 'samples': 10921152, 'steps': 56880, 'loss/train': 1.0112030506134033} 08/30/2021 23:26:37 - INFO - __main__ - Step 56882: {'lr': 0.00034869734081849, 'samples': 10921344, 'steps': 56881, 'loss/train': 0.8431229591369629} 08/30/2021 23:26:37 - INFO - __main__ - Step 56883: {'lr': 0.0003486924651099547, 'samples': 10921536, 'steps': 56882, 'loss/train': 1.5484871864318848} 08/30/2021 23:26:37 - INFO - __main__ - Step 56884: {'lr': 0.00034868758935695, 'samples': 10921728, 'steps': 56883, 'loss/train': 1.8331186771392822} 08/30/2021 23:26:38 - INFO - __main__ - Step 56885: {'lr': 0.0003486827135594783, 'samples': 10921920, 'steps': 56884, 'loss/train': 0.8448839783668518} 08/30/2021 23:26:38 - INFO - __main__ - Step 56886: {'lr': 0.0003486778377175417, 'samples': 10922112, 'steps': 56885, 'loss/train': 1.600650668144226} 08/30/2021 23:26:40 - INFO - __main__ - Step 56887: {'lr': 0.00034867296183114236, 'samples': 10922304, 'steps': 56886, 'loss/train': 0.9846146106719971} 08/30/2021 23:26:40 - INFO - __main__ - Step 56888: {'lr': 0.0003486680859002825, 'samples': 10922496, 'steps': 56887, 'loss/train': 0.8097743391990662} 08/30/2021 23:26:40 - INFO - __main__ - Step 56889: {'lr': 0.00034866320992496427, 'samples': 10922688, 'steps': 56888, 'loss/train': 1.458606481552124} 08/30/2021 23:26:41 - INFO - __main__ - Step 56890: {'lr': 0.00034865833390518996, 'samples': 10922880, 'steps': 56889, 'loss/train': 1.0616099834442139} 08/30/2021 23:26:41 - INFO - __main__ - Step 56891: {'lr': 0.0003486534578409618, 'samples': 10923072, 'steps': 56890, 'loss/train': 1.6899924278259277} 08/30/2021 23:26:43 - INFO - __main__ - Step 56892: {'lr': 0.0003486485817322819, 'samples': 10923264, 'steps': 56891, 'loss/train': 1.4150826930999756} 08/30/2021 23:26:43 - INFO - __main__ - Step 56893: {'lr': 0.0003486437055791524, 'samples': 10923456, 'steps': 56892, 'loss/train': 1.5813283920288086} 08/30/2021 23:26:43 - INFO - __main__ - Step 56894: {'lr': 0.00034863882938157553, 'samples': 10923648, 'steps': 56893, 'loss/train': 1.9637569189071655} 08/30/2021 23:26:44 - INFO - __main__ - Step 56895: {'lr': 0.0003486339531395536, 'samples': 10923840, 'steps': 56894, 'loss/train': 1.0609982013702393} 08/30/2021 23:26:44 - INFO - __main__ - Step 56896: {'lr': 0.0003486290768530887, 'samples': 10924032, 'steps': 56895, 'loss/train': 2.417832374572754} 08/30/2021 23:26:46 - INFO - __main__ - Step 56897: {'lr': 0.00034862420052218313, 'samples': 10924224, 'steps': 56896, 'loss/train': 1.2900514602661133} 08/30/2021 23:26:46 - INFO - __main__ - Step 56898: {'lr': 0.00034861932414683897, 'samples': 10924416, 'steps': 56897, 'loss/train': 1.1638840436935425} 08/30/2021 23:26:46 - INFO - __main__ - Step 56899: {'lr': 0.00034861444772705846, 'samples': 10924608, 'steps': 56898, 'loss/train': 0.8779194951057434} 08/30/2021 23:26:47 - INFO - __main__ - Step 56900: {'lr': 0.0003486095712628438, 'samples': 10924800, 'steps': 56899, 'loss/train': 1.247465968132019} 08/30/2021 23:26:47 - INFO - __main__ - Step 56901: {'lr': 0.00034860469475419723, 'samples': 10924992, 'steps': 56900, 'loss/train': 2.773620128631592} 08/30/2021 23:26:49 - INFO - __main__ - Step 56902: {'lr': 0.00034859981820112084, 'samples': 10925184, 'steps': 56901, 'loss/train': 0.9942734837532043} 08/30/2021 23:26:50 - INFO - __main__ - Step 56903: {'lr': 0.00034859494160361694, 'samples': 10925376, 'steps': 56902, 'loss/train': 1.575143814086914} 08/30/2021 23:26:50 - INFO - __main__ - Step 56904: {'lr': 0.00034859006496168764, 'samples': 10925568, 'steps': 56903, 'loss/train': 1.643119215965271} 08/30/2021 23:26:50 - INFO - __main__ - Step 56905: {'lr': 0.0003485851882753352, 'samples': 10925760, 'steps': 56904, 'loss/train': 1.9424742460250854} 08/30/2021 23:26:51 - INFO - __main__ - Step 56906: {'lr': 0.00034858031154456177, 'samples': 10925952, 'steps': 56905, 'loss/train': 0.7926269769668579} 08/30/2021 23:26:51 - INFO - __main__ - Step 56907: {'lr': 0.0003485754347693696, 'samples': 10926144, 'steps': 56906, 'loss/train': 2.12726092338562} 08/30/2021 23:26:53 - INFO - __main__ - Step 56908: {'lr': 0.0003485705579497609, 'samples': 10926336, 'steps': 56907, 'loss/train': 0.6451771259307861} 08/30/2021 23:26:53 - INFO - __main__ - Step 56909: {'lr': 0.0003485656810857378, 'samples': 10926528, 'steps': 56908, 'loss/train': 1.4209744930267334} 08/30/2021 23:26:53 - INFO - __main__ - Step 56910: {'lr': 0.00034856080417730253, 'samples': 10926720, 'steps': 56909, 'loss/train': 1.2591547966003418} 08/30/2021 23:26:54 - INFO - __main__ - Step 56911: {'lr': 0.0003485559272244572, 'samples': 10926912, 'steps': 56910, 'loss/train': 0.6976348161697388} 08/30/2021 23:26:54 - INFO - __main__ - Step 56912: {'lr': 0.0003485510502272042, 'samples': 10927104, 'steps': 56911, 'loss/train': 1.039771556854248} 08/30/2021 23:26:56 - INFO - __main__ - Step 56913: {'lr': 0.0003485461731855456, 'samples': 10927296, 'steps': 56912, 'loss/train': 1.0598288774490356} 08/30/2021 23:26:56 - INFO - __main__ - Step 56914: {'lr': 0.0003485412960994836, 'samples': 10927488, 'steps': 56913, 'loss/train': 1.3684484958648682} 08/30/2021 23:26:57 - INFO - __main__ - Step 56915: {'lr': 0.0003485364189690203, 'samples': 10927680, 'steps': 56914, 'loss/train': 1.4023346900939941} 08/30/2021 23:26:57 - INFO - __main__ - Step 56916: {'lr': 0.0003485315417941581, 'samples': 10927872, 'steps': 56915, 'loss/train': 0.8421781659126282} 08/30/2021 23:26:57 - INFO - __main__ - Step 56917: {'lr': 0.00034852666457489917, 'samples': 10928064, 'steps': 56916, 'loss/train': 2.3677730560302734} 08/30/2021 23:26:59 - INFO - __main__ - Step 56918: {'lr': 0.00034852178731124557, 'samples': 10928256, 'steps': 56917, 'loss/train': 1.5544217824935913} 08/30/2021 23:26:59 - INFO - __main__ - Step 56919: {'lr': 0.00034851691000319963, 'samples': 10928448, 'steps': 56918, 'loss/train': 1.5356897115707397} 08/30/2021 23:27:00 - INFO - __main__ - Step 56920: {'lr': 0.0003485120326507635, 'samples': 10928640, 'steps': 56919, 'loss/train': 1.115616798400879} 08/30/2021 23:27:00 - INFO - __main__ - Step 56921: {'lr': 0.0003485071552539393, 'samples': 10928832, 'steps': 56920, 'loss/train': 1.0191221237182617} 08/30/2021 23:27:00 - INFO - __main__ - Step 56922: {'lr': 0.0003485022778127293, 'samples': 10929024, 'steps': 56921, 'loss/train': 0.8920819163322449} 08/30/2021 23:27:02 - INFO - __main__ - Step 56923: {'lr': 0.0003484974003271357, 'samples': 10929216, 'steps': 56922, 'loss/train': 1.4527028799057007} 08/30/2021 23:27:03 - INFO - __main__ - Step 56924: {'lr': 0.0003484925227971607, 'samples': 10929408, 'steps': 56923, 'loss/train': 1.4513757228851318} 08/30/2021 23:27:03 - INFO - __main__ - Step 56925: {'lr': 0.0003484876452228065, 'samples': 10929600, 'steps': 56924, 'loss/train': 0.3260684311389923} 08/30/2021 23:27:03 - INFO - __main__ - Step 56926: {'lr': 0.00034848276760407525, 'samples': 10929792, 'steps': 56925, 'loss/train': 0.9382138848304749} 08/30/2021 23:27:04 - INFO - __main__ - Step 56927: {'lr': 0.0003484778899409693, 'samples': 10929984, 'steps': 56926, 'loss/train': 1.441593885421753} 08/30/2021 23:27:04 - INFO - __main__ - Step 56928: {'lr': 0.0003484730122334906, 'samples': 10930176, 'steps': 56927, 'loss/train': 1.32077956199646} 08/30/2021 23:27:06 - INFO - __main__ - Step 56929: {'lr': 0.00034846813448164153, 'samples': 10930368, 'steps': 56928, 'loss/train': 1.025976300239563} 08/30/2021 23:27:06 - INFO - __main__ - Step 56930: {'lr': 0.00034846325668542425, 'samples': 10930560, 'steps': 56929, 'loss/train': 0.12417766451835632} 08/30/2021 23:27:07 - INFO - __main__ - Step 56931: {'lr': 0.00034845837884484086, 'samples': 10930752, 'steps': 56930, 'loss/train': 1.356216311454773} 08/30/2021 23:27:07 - INFO - __main__ - Step 56932: {'lr': 0.00034845350095989377, 'samples': 10930944, 'steps': 56931, 'loss/train': 0.8414885401725769} 08/30/2021 23:27:07 - INFO - __main__ - Step 56933: {'lr': 0.000348448623030585, 'samples': 10931136, 'steps': 56932, 'loss/train': 1.196163296699524} 08/30/2021 23:27:09 - INFO - __main__ - Step 56934: {'lr': 0.00034844374505691686, 'samples': 10931328, 'steps': 56933, 'loss/train': 1.2735474109649658} 08/30/2021 23:27:09 - INFO - __main__ - Step 56935: {'lr': 0.0003484388670388914, 'samples': 10931520, 'steps': 56934, 'loss/train': 0.7008181214332581} 08/30/2021 23:27:10 - INFO - __main__ - Step 56936: {'lr': 0.0003484339889765109, 'samples': 10931712, 'steps': 56935, 'loss/train': 1.571568250656128} 08/30/2021 23:27:10 - INFO - __main__ - Step 56937: {'lr': 0.0003484291108697776, 'samples': 10931904, 'steps': 56936, 'loss/train': 0.09991992264986038} 08/30/2021 23:27:10 - INFO - __main__ - Step 56938: {'lr': 0.0003484242327186936, 'samples': 10932096, 'steps': 56937, 'loss/train': 0.8290556073188782} 08/30/2021 23:27:12 - INFO - __main__ - Step 56939: {'lr': 0.0003484193545232612, 'samples': 10932288, 'steps': 56938, 'loss/train': 1.17635977268219} 08/30/2021 23:27:12 - INFO - __main__ - Step 56940: {'lr': 0.00034841447628348267, 'samples': 10932480, 'steps': 56939, 'loss/train': 1.0960227251052856} 08/30/2021 23:27:13 - INFO - __main__ - Step 56941: {'lr': 0.00034840959799936, 'samples': 10932672, 'steps': 56940, 'loss/train': 0.6932271718978882} 08/30/2021 23:27:13 - INFO - __main__ - Step 56942: {'lr': 0.0003484047196708955, 'samples': 10932864, 'steps': 56941, 'loss/train': 1.5163533687591553} 08/30/2021 23:27:13 - INFO - __main__ - Step 56943: {'lr': 0.00034839984129809125, 'samples': 10933056, 'steps': 56942, 'loss/train': 0.9830710291862488} 08/30/2021 23:27:15 - INFO - __main__ - Step 56944: {'lr': 0.00034839496288094964, 'samples': 10933248, 'steps': 56943, 'loss/train': 1.827366590499878} 08/30/2021 23:27:16 - INFO - __main__ - Step 56945: {'lr': 0.0003483900844194728, 'samples': 10933440, 'steps': 56944, 'loss/train': 2.0420448780059814} 08/30/2021 23:27:16 - INFO - __main__ - Step 56946: {'lr': 0.00034838520591366285, 'samples': 10933632, 'steps': 56945, 'loss/train': 1.186514139175415} 08/30/2021 23:27:16 - INFO - __main__ - Step 56947: {'lr': 0.0003483803273635221, 'samples': 10933824, 'steps': 56946, 'loss/train': 1.5188438892364502} 08/30/2021 23:27:17 - INFO - __main__ - Step 56948: {'lr': 0.0003483754487690527, 'samples': 10934016, 'steps': 56947, 'loss/train': 1.1046955585479736} 08/30/2021 23:27:19 - INFO - __main__ - Step 56949: {'lr': 0.0003483705701302567, 'samples': 10934208, 'steps': 56948, 'loss/train': 0.31348347663879395} 08/30/2021 23:27:19 - INFO - __main__ - Step 56950: {'lr': 0.0003483656914471366, 'samples': 10934400, 'steps': 56949, 'loss/train': 1.2855521440505981} 08/30/2021 23:27:19 - INFO - __main__ - Step 56951: {'lr': 0.00034836081271969436, 'samples': 10934592, 'steps': 56950, 'loss/train': 1.785689115524292} 08/30/2021 23:27:20 - INFO - __main__ - Step 56952: {'lr': 0.0003483559339479323, 'samples': 10934784, 'steps': 56951, 'loss/train': 0.675041139125824} 08/30/2021 23:27:20 - INFO - __main__ - Step 56953: {'lr': 0.00034835105513185253, 'samples': 10934976, 'steps': 56952, 'loss/train': 0.06716547906398773} 08/30/2021 23:27:20 - INFO - __main__ - Step 56954: {'lr': 0.00034834617627145737, 'samples': 10935168, 'steps': 56953, 'loss/train': 1.3539644479751587} 08/30/2021 23:27:22 - INFO - __main__ - Step 56955: {'lr': 0.00034834129736674885, 'samples': 10935360, 'steps': 56954, 'loss/train': 1.0353893041610718} 08/30/2021 23:27:23 - INFO - __main__ - Step 56956: {'lr': 0.0003483364184177293, 'samples': 10935552, 'steps': 56955, 'loss/train': 1.4986668825149536} 08/30/2021 23:27:23 - INFO - __main__ - Step 56957: {'lr': 0.0003483315394244009, 'samples': 10935744, 'steps': 56956, 'loss/train': 1.6922856569290161} 08/30/2021 23:27:23 - INFO - __main__ - Step 56958: {'lr': 0.00034832666038676576, 'samples': 10935936, 'steps': 56957, 'loss/train': 1.0952831506729126} 08/30/2021 23:27:24 - INFO - __main__ - Step 56959: {'lr': 0.0003483217813048262, 'samples': 10936128, 'steps': 56958, 'loss/train': 1.5478628873825073} 08/30/2021 23:27:25 - INFO - __main__ - Step 56960: {'lr': 0.0003483169021785844, 'samples': 10936320, 'steps': 56959, 'loss/train': 1.2977089881896973} 08/30/2021 23:27:26 - INFO - __main__ - Step 56961: {'lr': 0.00034831202300804245, 'samples': 10936512, 'steps': 56960, 'loss/train': 0.5518299341201782} 08/30/2021 23:27:26 - INFO - __main__ - Step 56962: {'lr': 0.0003483071437932026, 'samples': 10936704, 'steps': 56961, 'loss/train': 0.92521733045578} 08/30/2021 23:27:27 - INFO - __main__ - Step 56963: {'lr': 0.0003483022645340671, 'samples': 10936896, 'steps': 56962, 'loss/train': 1.1264383792877197} 08/30/2021 23:27:27 - INFO - __main__ - Step 56964: {'lr': 0.0003482973852306381, 'samples': 10937088, 'steps': 56963, 'loss/train': 1.4245665073394775} 08/30/2021 23:27:29 - INFO - __main__ - Step 56965: {'lr': 0.00034829250588291785, 'samples': 10937280, 'steps': 56964, 'loss/train': 0.8493406772613525} 08/30/2021 23:27:29 - INFO - __main__ - Step 56966: {'lr': 0.00034828762649090843, 'samples': 10937472, 'steps': 56965, 'loss/train': 1.405874252319336} 08/30/2021 23:27:29 - INFO - __main__ - Step 56967: {'lr': 0.0003482827470546123, 'samples': 10937664, 'steps': 56966, 'loss/train': 1.0573389530181885} 08/30/2021 23:27:30 - INFO - __main__ - Step 56968: {'lr': 0.00034827786757403136, 'samples': 10937856, 'steps': 56967, 'loss/train': 1.6176581382751465} 08/30/2021 23:27:30 - INFO - __main__ - Step 56969: {'lr': 0.00034827298804916793, 'samples': 10938048, 'steps': 56968, 'loss/train': 1.7509671449661255} 08/30/2021 23:27:31 - INFO - __main__ - Step 56970: {'lr': 0.00034826810848002416, 'samples': 10938240, 'steps': 56969, 'loss/train': 1.8563398122787476} 08/30/2021 23:27:32 - INFO - __main__ - Step 56971: {'lr': 0.00034826322886660234, 'samples': 10938432, 'steps': 56970, 'loss/train': 0.7419421076774597} 08/30/2021 23:27:33 - INFO - __main__ - Step 56972: {'lr': 0.00034825834920890463, 'samples': 10938624, 'steps': 56971, 'loss/train': 3.262617588043213} 08/30/2021 23:27:33 - INFO - __main__ - Step 56973: {'lr': 0.00034825346950693325, 'samples': 10938816, 'steps': 56972, 'loss/train': 1.5513989925384521} 08/30/2021 23:27:33 - INFO - __main__ - Step 56974: {'lr': 0.00034824858976069043, 'samples': 10939008, 'steps': 56973, 'loss/train': 1.1741607189178467} 08/30/2021 23:27:34 - INFO - __main__ - Step 56975: {'lr': 0.00034824370997017817, 'samples': 10939200, 'steps': 56974, 'loss/train': 1.5733639001846313} 08/30/2021 23:27:35 - INFO - __main__ - Step 56976: {'lr': 0.0003482388301353989, 'samples': 10939392, 'steps': 56975, 'loss/train': 1.2643074989318848} 08/30/2021 23:27:36 - INFO - __main__ - Step 56977: {'lr': 0.0003482339502563547, 'samples': 10939584, 'steps': 56976, 'loss/train': 1.3019770383834839} 08/30/2021 23:27:36 - INFO - __main__ - Step 56978: {'lr': 0.0003482290703330478, 'samples': 10939776, 'steps': 56977, 'loss/train': 1.7001034021377563} 08/30/2021 23:27:36 - INFO - __main__ - Step 56979: {'lr': 0.0003482241903654804, 'samples': 10939968, 'steps': 56978, 'loss/train': 1.3058631420135498} 08/30/2021 23:27:37 - INFO - __main__ - Step 56980: {'lr': 0.00034821931035365465, 'samples': 10940160, 'steps': 56979, 'loss/train': 1.4733809232711792} 08/30/2021 23:27:37 - INFO - __main__ - Step 56981: {'lr': 0.0003482144302975729, 'samples': 10940352, 'steps': 56980, 'loss/train': 1.1822497844696045} 08/30/2021 23:27:38 - INFO - __main__ - Step 56982: {'lr': 0.0003482095501972372, 'samples': 10940544, 'steps': 56981, 'loss/train': 0.8622186779975891} 08/30/2021 23:27:39 - INFO - __main__ - Step 56983: {'lr': 0.0003482046700526498, 'samples': 10940736, 'steps': 56982, 'loss/train': 1.3584232330322266} 08/30/2021 23:27:39 - INFO - __main__ - Step 56984: {'lr': 0.0003481997898638128, 'samples': 10940928, 'steps': 56983, 'loss/train': 0.6189478635787964} 08/30/2021 23:27:40 - INFO - __main__ - Step 56985: {'lr': 0.0003481949096307285, 'samples': 10941120, 'steps': 56984, 'loss/train': 1.907167673110962} 08/30/2021 23:27:40 - INFO - __main__ - Step 56986: {'lr': 0.0003481900293533992, 'samples': 10941312, 'steps': 56985, 'loss/train': 1.4248418807983398} 08/30/2021 23:27:42 - INFO - __main__ - Step 56987: {'lr': 0.00034818514903182696, 'samples': 10941504, 'steps': 56986, 'loss/train': 1.3281067609786987} 08/30/2021 23:27:42 - INFO - __main__ - Step 56988: {'lr': 0.000348180268666014, 'samples': 10941696, 'steps': 56987, 'loss/train': 0.9966983199119568} 08/30/2021 23:27:43 - INFO - __main__ - Step 56989: {'lr': 0.00034817538825596253, 'samples': 10941888, 'steps': 56988, 'loss/train': 0.027598761022090912} 08/30/2021 23:27:43 - INFO - __main__ - Step 56990: {'lr': 0.0003481705078016747, 'samples': 10942080, 'steps': 56989, 'loss/train': 1.2920674085617065} 08/30/2021 23:27:43 - INFO - __main__ - Step 56991: {'lr': 0.0003481656273031527, 'samples': 10942272, 'steps': 56990, 'loss/train': 0.04102129861712456} 08/30/2021 23:27:44 - INFO - __main__ - Step 56992: {'lr': 0.0003481607467603989, 'samples': 10942464, 'steps': 56991, 'loss/train': 1.7848039865493774} 08/30/2021 23:27:45 - INFO - __main__ - Step 56993: {'lr': 0.00034815586617341533, 'samples': 10942656, 'steps': 56992, 'loss/train': 1.2939101457595825} 08/30/2021 23:27:46 - INFO - __main__ - Step 56994: {'lr': 0.0003481509855422043, 'samples': 10942848, 'steps': 56993, 'loss/train': 1.4614652395248413} 08/30/2021 23:27:46 - INFO - __main__ - Step 56995: {'lr': 0.0003481461048667679, 'samples': 10943040, 'steps': 56994, 'loss/train': 1.739587426185608} 08/30/2021 23:27:46 - INFO - __main__ - Step 56996: {'lr': 0.00034814122414710837, 'samples': 10943232, 'steps': 56995, 'loss/train': 1.281952977180481} 08/30/2021 23:27:47 - INFO - __main__ - Step 56997: {'lr': 0.0003481363433832279, 'samples': 10943424, 'steps': 56996, 'loss/train': 1.574078917503357} 08/30/2021 23:27:48 - INFO - __main__ - Step 56998: {'lr': 0.00034813146257512876, 'samples': 10943616, 'steps': 56997, 'loss/train': 1.3837085962295532} 08/30/2021 23:27:49 - INFO - __main__ - Step 56999: {'lr': 0.0003481265817228131, 'samples': 10943808, 'steps': 56998, 'loss/train': 0.921924889087677} 08/30/2021 23:27:49 - INFO - __main__ - Step 57000: {'lr': 0.00034812170082628303, 'samples': 10944000, 'steps': 56999, 'loss/train': 0.2893299460411072} 08/30/2021 23:27:49 - INFO - __main__ - Step 57001: {'lr': 0.00034811681988554095, 'samples': 10944192, 'steps': 57000, 'loss/train': 1.6056768894195557} 08/30/2021 23:27:50 - INFO - __main__ - Step 57002: {'lr': 0.0003481119389005889, 'samples': 10944384, 'steps': 57001, 'loss/train': 1.6358243227005005} 08/30/2021 23:27:51 - INFO - __main__ - Step 57003: {'lr': 0.0003481070578714291, 'samples': 10944576, 'steps': 57002, 'loss/train': 0.12685905396938324} 08/30/2021 23:27:52 - INFO - __main__ - Step 57004: {'lr': 0.0003481021767980638, 'samples': 10944768, 'steps': 57003, 'loss/train': 1.4461734294891357} 08/30/2021 23:27:52 - INFO - __main__ - Step 57005: {'lr': 0.00034809729568049513, 'samples': 10944960, 'steps': 57004, 'loss/train': 1.7054307460784912} 08/30/2021 23:27:52 - INFO - __main__ - Step 57006: {'lr': 0.0003480924145187254, 'samples': 10945152, 'steps': 57005, 'loss/train': 1.0822632312774658} 08/30/2021 23:27:53 - INFO - __main__ - Step 57007: {'lr': 0.0003480875333127567, 'samples': 10945344, 'steps': 57006, 'loss/train': 1.6099203824996948} 08/30/2021 23:27:54 - INFO - __main__ - Step 57008: {'lr': 0.0003480826520625913, 'samples': 10945536, 'steps': 57007, 'loss/train': 1.3697259426116943} 08/30/2021 23:27:55 - INFO - __main__ - Step 57009: {'lr': 0.0003480777707682313, 'samples': 10945728, 'steps': 57008, 'loss/train': 1.7698712348937988} 08/30/2021 23:27:55 - INFO - __main__ - Step 57010: {'lr': 0.00034807288942967905, 'samples': 10945920, 'steps': 57009, 'loss/train': 1.7093955278396606} 08/30/2021 23:27:55 - INFO - __main__ - Step 57011: {'lr': 0.0003480680080469366, 'samples': 10946112, 'steps': 57010, 'loss/train': 2.058028221130371} 08/30/2021 23:27:56 - INFO - __main__ - Step 57012: {'lr': 0.0003480631266200063, 'samples': 10946304, 'steps': 57011, 'loss/train': 1.3001831769943237} 08/30/2021 23:27:58 - INFO - __main__ - Step 57013: {'lr': 0.0003480582451488902, 'samples': 10946496, 'steps': 57012, 'loss/train': 0.9852659702301025} 08/30/2021 23:27:58 - INFO - __main__ - Step 57014: {'lr': 0.00034805336363359066, 'samples': 10946688, 'steps': 57013, 'loss/train': 1.2243127822875977} 08/30/2021 23:27:59 - INFO - __main__ - Step 57015: {'lr': 0.00034804848207410974, 'samples': 10946880, 'steps': 57014, 'loss/train': 1.3231433629989624} 08/30/2021 23:27:59 - INFO - __main__ - Step 57016: {'lr': 0.00034804360047044965, 'samples': 10947072, 'steps': 57015, 'loss/train': 1.360616683959961} 08/30/2021 23:27:59 - INFO - __main__ - Step 57017: {'lr': 0.0003480387188226126, 'samples': 10947264, 'steps': 57016, 'loss/train': 1.3785102367401123} 08/30/2021 23:28:01 - INFO - __main__ - Step 57018: {'lr': 0.0003480338371306009, 'samples': 10947456, 'steps': 57017, 'loss/train': 0.46699249744415283} 08/30/2021 23:28:01 - INFO - __main__ - Step 57019: {'lr': 0.0003480289553944166, 'samples': 10947648, 'steps': 57018, 'loss/train': 1.6604140996932983} 08/30/2021 23:28:02 - INFO - __main__ - Step 57020: {'lr': 0.000348024073614062, 'samples': 10947840, 'steps': 57019, 'loss/train': 1.2705460786819458} 08/30/2021 23:28:02 - INFO - __main__ - Step 57021: {'lr': 0.0003480191917895393, 'samples': 10948032, 'steps': 57020, 'loss/train': 1.3671238422393799} 08/30/2021 23:28:03 - INFO - __main__ - Step 57022: {'lr': 0.0003480143099208506, 'samples': 10948224, 'steps': 57021, 'loss/train': 1.883851170539856} 08/30/2021 23:28:03 - INFO - __main__ - Step 57023: {'lr': 0.00034800942800799817, 'samples': 10948416, 'steps': 57022, 'loss/train': 0.9469725489616394} 08/30/2021 23:28:04 - INFO - __main__ - Step 57024: {'lr': 0.00034800454605098417, 'samples': 10948608, 'steps': 57023, 'loss/train': 1.3060386180877686} 08/30/2021 23:28:05 - INFO - __main__ - Step 57025: {'lr': 0.00034799966404981095, 'samples': 10948800, 'steps': 57024, 'loss/train': 1.7397828102111816} 08/30/2021 23:28:05 - INFO - __main__ - Step 57026: {'lr': 0.00034799478200448056, 'samples': 10948992, 'steps': 57025, 'loss/train': 1.2919104099273682} 08/30/2021 23:28:05 - INFO - __main__ - Step 57027: {'lr': 0.0003479898999149952, 'samples': 10949184, 'steps': 57026, 'loss/train': 1.7795907258987427} 08/30/2021 23:28:06 - INFO - __main__ - Step 57028: {'lr': 0.00034798501778135704, 'samples': 10949376, 'steps': 57027, 'loss/train': 1.0661389827728271} 08/30/2021 23:28:07 - INFO - __main__ - Step 57029: {'lr': 0.0003479801356035684, 'samples': 10949568, 'steps': 57028, 'loss/train': 1.827704668045044} 08/30/2021 23:28:08 - INFO - __main__ - Step 57030: {'lr': 0.0003479752533816315, 'samples': 10949760, 'steps': 57029, 'loss/train': 1.6550542116165161} 08/30/2021 23:28:08 - INFO - __main__ - Step 57031: {'lr': 0.0003479703711155484, 'samples': 10949952, 'steps': 57030, 'loss/train': 1.2261172533035278} 08/30/2021 23:28:08 - INFO - __main__ - Step 57032: {'lr': 0.00034796548880532135, 'samples': 10950144, 'steps': 57031, 'loss/train': 1.2753974199295044} 08/30/2021 23:28:09 - INFO - __main__ - Step 57033: {'lr': 0.0003479606064509526, 'samples': 10950336, 'steps': 57032, 'loss/train': 1.0902739763259888} 08/30/2021 23:28:10 - INFO - __main__ - Step 57034: {'lr': 0.00034795572405244425, 'samples': 10950528, 'steps': 57033, 'loss/train': 1.6735591888427734} 08/30/2021 23:28:11 - INFO - __main__ - Step 57035: {'lr': 0.0003479508416097986, 'samples': 10950720, 'steps': 57034, 'loss/train': 0.887643575668335} 08/30/2021 23:28:11 - INFO - __main__ - Step 57036: {'lr': 0.0003479459591230177, 'samples': 10950912, 'steps': 57035, 'loss/train': 1.2060307264328003} 08/30/2021 23:28:12 - INFO - __main__ - Step 57037: {'lr': 0.0003479410765921041, 'samples': 10951104, 'steps': 57036, 'loss/train': 1.460170030593872} 08/30/2021 23:28:12 - INFO - __main__ - Step 57038: {'lr': 0.0003479361940170596, 'samples': 10951296, 'steps': 57037, 'loss/train': 1.211076259613037} 08/30/2021 23:28:13 - INFO - __main__ - Step 57039: {'lr': 0.0003479313113978866, 'samples': 10951488, 'steps': 57038, 'loss/train': 1.531976342201233} 08/30/2021 23:28:14 - INFO - __main__ - Step 57040: {'lr': 0.00034792642873458725, 'samples': 10951680, 'steps': 57039, 'loss/train': 0.9424772262573242} 08/30/2021 23:28:14 - INFO - __main__ - Step 57041: {'lr': 0.00034792154602716376, 'samples': 10951872, 'steps': 57040, 'loss/train': 1.2763078212738037} 08/30/2021 23:28:15 - INFO - __main__ - Step 57042: {'lr': 0.0003479166632756184, 'samples': 10952064, 'steps': 57041, 'loss/train': 1.8003580570220947} 08/30/2021 23:28:15 - INFO - __main__ - Step 57043: {'lr': 0.0003479117804799532, 'samples': 10952256, 'steps': 57042, 'loss/train': 1.2753196954727173} 08/30/2021 23:28:17 - INFO - __main__ - Step 57044: {'lr': 0.00034790689764017046, 'samples': 10952448, 'steps': 57043, 'loss/train': 2.989809036254883} 08/30/2021 23:28:17 - INFO - __main__ - Step 57045: {'lr': 0.00034790201475627246, 'samples': 10952640, 'steps': 57044, 'loss/train': 1.1062965393066406} 08/30/2021 23:28:18 - INFO - __main__ - Step 57046: {'lr': 0.00034789713182826126, 'samples': 10952832, 'steps': 57045, 'loss/train': 0.4613654911518097} 08/30/2021 23:28:18 - INFO - __main__ - Step 57047: {'lr': 0.0003478922488561392, 'samples': 10953024, 'steps': 57046, 'loss/train': 1.091480016708374} 08/30/2021 23:28:18 - INFO - __main__ - Step 57048: {'lr': 0.0003478873658399084, 'samples': 10953216, 'steps': 57047, 'loss/train': 1.351733684539795} 08/30/2021 23:28:19 - INFO - __main__ - Step 57049: {'lr': 0.000347882482779571, 'samples': 10953408, 'steps': 57048, 'loss/train': 1.7358691692352295} 08/30/2021 23:28:20 - INFO - __main__ - Step 57050: {'lr': 0.00034787759967512923, 'samples': 10953600, 'steps': 57049, 'loss/train': 1.3204859495162964} 08/30/2021 23:28:21 - INFO - __main__ - Step 57051: {'lr': 0.00034787271652658534, 'samples': 10953792, 'steps': 57050, 'loss/train': 0.9837892651557922} 08/30/2021 23:28:21 - INFO - __main__ - Step 57052: {'lr': 0.0003478678333339416, 'samples': 10953984, 'steps': 57051, 'loss/train': 1.5108966827392578} 08/30/2021 23:28:21 - INFO - __main__ - Step 57053: {'lr': 0.0003478629500972, 'samples': 10954176, 'steps': 57052, 'loss/train': 2.1211483478546143} 08/30/2021 23:28:22 - INFO - __main__ - Step 57054: {'lr': 0.0003478580668163631, 'samples': 10954368, 'steps': 57053, 'loss/train': 0.46269649267196655} 08/30/2021 23:28:23 - INFO - __main__ - Step 57055: {'lr': 0.0003478531834914326, 'samples': 10954560, 'steps': 57054, 'loss/train': 1.3709542751312256} 08/30/2021 23:28:24 - INFO - __main__ - Step 57056: {'lr': 0.0003478483001224111, 'samples': 10954752, 'steps': 57055, 'loss/train': 0.7645677924156189} 08/30/2021 23:28:24 - INFO - __main__ - Step 57057: {'lr': 0.00034784341670930066, 'samples': 10954944, 'steps': 57056, 'loss/train': 1.2185145616531372} 08/30/2021 23:28:24 - INFO - __main__ - Step 57058: {'lr': 0.00034783853325210344, 'samples': 10955136, 'steps': 57057, 'loss/train': 1.0981371402740479} 08/30/2021 23:28:25 - INFO - __main__ - Step 57059: {'lr': 0.0003478336497508217, 'samples': 10955328, 'steps': 57058, 'loss/train': 1.5518289804458618} 08/30/2021 23:28:27 - INFO - __main__ - Step 57060: {'lr': 0.0003478287662054576, 'samples': 10955520, 'steps': 57059, 'loss/train': 1.1390094757080078} 08/30/2021 23:28:27 - INFO - __main__ - Step 57061: {'lr': 0.0003478238826160135, 'samples': 10955712, 'steps': 57060, 'loss/train': 1.8684204816818237} 08/30/2021 23:28:27 - INFO - __main__ - Step 57062: {'lr': 0.00034781899898249136, 'samples': 10955904, 'steps': 57061, 'loss/train': 1.1276425123214722} 08/30/2021 23:28:28 - INFO - __main__ - Step 57063: {'lr': 0.0003478141153048935, 'samples': 10956096, 'steps': 57062, 'loss/train': 1.4150640964508057} 08/30/2021 23:28:28 - INFO - __main__ - Step 57064: {'lr': 0.0003478092315832221, 'samples': 10956288, 'steps': 57063, 'loss/train': 0.06745883077383041} 08/30/2021 23:28:30 - INFO - __main__ - Step 57065: {'lr': 0.00034780434781747936, 'samples': 10956480, 'steps': 57064, 'loss/train': 1.5051709413528442} 08/30/2021 23:28:31 - INFO - __main__ - Step 57066: {'lr': 0.0003477994640076675, 'samples': 10956672, 'steps': 57065, 'loss/train': 1.1805298328399658} 08/30/2021 23:28:31 - INFO - __main__ - Step 57067: {'lr': 0.00034779458015378874, 'samples': 10956864, 'steps': 57066, 'loss/train': 1.2429498434066772} 08/30/2021 23:28:31 - INFO - __main__ - Step 57068: {'lr': 0.00034778969625584523, 'samples': 10957056, 'steps': 57067, 'loss/train': 1.4781283140182495} 08/30/2021 23:28:32 - INFO - __main__ - Step 57069: {'lr': 0.0003477848123138392, 'samples': 10957248, 'steps': 57068, 'loss/train': 1.6229937076568604} 08/30/2021 23:28:33 - INFO - __main__ - Step 57070: {'lr': 0.0003477799283277728, 'samples': 10957440, 'steps': 57069, 'loss/train': 1.5744439363479614} 08/30/2021 23:28:34 - INFO - __main__ - Step 57071: {'lr': 0.0003477750442976483, 'samples': 10957632, 'steps': 57070, 'loss/train': 1.632590413093567} 08/30/2021 23:28:34 - INFO - __main__ - Step 57072: {'lr': 0.0003477701602234679, 'samples': 10957824, 'steps': 57071, 'loss/train': 1.1744002103805542} 08/30/2021 23:28:34 - INFO - __main__ - Step 57073: {'lr': 0.00034776527610523377, 'samples': 10958016, 'steps': 57072, 'loss/train': 0.2698575556278229} 08/30/2021 23:28:35 - INFO - __main__ - Step 57074: {'lr': 0.00034776039194294806, 'samples': 10958208, 'steps': 57073, 'loss/train': 1.3911490440368652} 08/30/2021 23:28:35 - INFO - __main__ - Step 57075: {'lr': 0.0003477555077366131, 'samples': 10958400, 'steps': 57074, 'loss/train': 1.7398079633712769} 08/30/2021 23:28:37 - INFO - __main__ - Step 57076: {'lr': 0.000347750623486231, 'samples': 10958592, 'steps': 57075, 'loss/train': 1.3328917026519775} 08/30/2021 23:28:37 - INFO - __main__ - Step 57077: {'lr': 0.00034774573919180396, 'samples': 10958784, 'steps': 57076, 'loss/train': 1.9911900758743286} 08/30/2021 23:28:37 - INFO - __main__ - Step 57078: {'lr': 0.0003477408548533342, 'samples': 10958976, 'steps': 57077, 'loss/train': 1.19882071018219} 08/30/2021 23:28:38 - INFO - __main__ - Step 57079: {'lr': 0.0003477359704708239, 'samples': 10959168, 'steps': 57078, 'loss/train': 0.9224775433540344} 08/30/2021 23:28:38 - INFO - __main__ - Step 57080: {'lr': 0.00034773108604427527, 'samples': 10959360, 'steps': 57079, 'loss/train': 0.20800741016864777} 08/30/2021 23:28:40 - INFO - __main__ - Step 57081: {'lr': 0.0003477262015736906, 'samples': 10959552, 'steps': 57080, 'loss/train': 1.3875374794006348} 08/30/2021 23:28:40 - INFO - __main__ - Step 57082: {'lr': 0.000347721317059072, 'samples': 10959744, 'steps': 57081, 'loss/train': 1.4149136543273926} 08/30/2021 23:28:41 - INFO - __main__ - Step 57083: {'lr': 0.00034771643250042163, 'samples': 10959936, 'steps': 57082, 'loss/train': 1.4568796157836914} 08/30/2021 23:28:41 - INFO - __main__ - Step 57084: {'lr': 0.0003477115478977417, 'samples': 10960128, 'steps': 57083, 'loss/train': 1.1072320938110352} 08/30/2021 23:28:42 - INFO - __main__ - Step 57085: {'lr': 0.0003477066632510346, 'samples': 10960320, 'steps': 57084, 'loss/train': 1.9716097116470337} 08/30/2021 23:28:43 - INFO - __main__ - Step 57086: {'lr': 0.00034770177856030223, 'samples': 10960512, 'steps': 57085, 'loss/train': 1.5158183574676514} 08/30/2021 23:28:43 - INFO - __main__ - Step 57087: {'lr': 0.00034769689382554704, 'samples': 10960704, 'steps': 57086, 'loss/train': 1.1423659324645996} 08/30/2021 23:28:44 - INFO - __main__ - Step 57088: {'lr': 0.0003476920090467711, 'samples': 10960896, 'steps': 57087, 'loss/train': 1.2910465002059937} 08/30/2021 23:28:44 - INFO - __main__ - Step 57089: {'lr': 0.0003476871242239767, 'samples': 10961088, 'steps': 57088, 'loss/train': 1.1581976413726807} 08/30/2021 23:28:44 - INFO - __main__ - Step 57090: {'lr': 0.0003476822393571659, 'samples': 10961280, 'steps': 57089, 'loss/train': 0.948721706867218} 08/30/2021 23:28:46 - INFO - __main__ - Step 57091: {'lr': 0.00034767735444634105, 'samples': 10961472, 'steps': 57090, 'loss/train': 1.1170225143432617} 08/30/2021 23:28:46 - INFO - __main__ - Step 57092: {'lr': 0.00034767246949150425, 'samples': 10961664, 'steps': 57091, 'loss/train': 1.2649356126785278} 08/30/2021 23:28:47 - INFO - __main__ - Step 57093: {'lr': 0.0003476675844926578, 'samples': 10961856, 'steps': 57092, 'loss/train': 0.8574861288070679} 08/30/2021 23:28:47 - INFO - __main__ - Step 57094: {'lr': 0.0003476626994498038, 'samples': 10962048, 'steps': 57093, 'loss/train': 1.4239813089370728} 08/30/2021 23:28:48 - INFO - __main__ - Step 57095: {'lr': 0.0003476578143629445, 'samples': 10962240, 'steps': 57094, 'loss/train': 1.4719583988189697} 08/30/2021 23:28:49 - INFO - __main__ - Step 57096: {'lr': 0.0003476529292320821, 'samples': 10962432, 'steps': 57095, 'loss/train': 0.0870312973856926} 08/30/2021 23:28:50 - INFO - __main__ - Step 57097: {'lr': 0.00034764804405721885, 'samples': 10962624, 'steps': 57096, 'loss/train': 1.0821385383605957} 08/30/2021 23:28:50 - INFO - __main__ - Step 57098: {'lr': 0.0003476431588383568, 'samples': 10962816, 'steps': 57097, 'loss/train': 0.9208717942237854} 08/30/2021 23:28:51 - INFO - __main__ - Step 57099: {'lr': 0.0003476382735754983, 'samples': 10963008, 'steps': 57098, 'loss/train': 2.2821109294891357} 08/30/2021 23:28:51 - INFO - __main__ - Step 57100: {'lr': 0.00034763338826864556, 'samples': 10963200, 'steps': 57099, 'loss/train': 1.2312923669815063} 08/30/2021 23:28:51 - INFO - __main__ - Step 57101: {'lr': 0.0003476285029178006, 'samples': 10963392, 'steps': 57100, 'loss/train': 1.197237253189087} 08/30/2021 23:28:53 - INFO - __main__ - Step 57102: {'lr': 0.0003476236175229659, 'samples': 10963584, 'steps': 57101, 'loss/train': 1.3694525957107544} 08/30/2021 23:28:53 - INFO - __main__ - Step 57103: {'lr': 0.0003476187320841434, 'samples': 10963776, 'steps': 57102, 'loss/train': 0.8848452568054199} 08/30/2021 23:28:54 - INFO - __main__ - Step 57104: {'lr': 0.0003476138466013354, 'samples': 10963968, 'steps': 57103, 'loss/train': 1.741289734840393} 08/30/2021 23:28:54 - INFO - __main__ - Step 57105: {'lr': 0.00034760896107454407, 'samples': 10964160, 'steps': 57104, 'loss/train': 1.1370725631713867} 08/30/2021 23:28:54 - INFO - __main__ - Step 57106: {'lr': 0.0003476040755037717, 'samples': 10964352, 'steps': 57105, 'loss/train': 0.9621631503105164} 08/30/2021 23:28:56 - INFO - __main__ - Step 57107: {'lr': 0.00034759918988902045, 'samples': 10964544, 'steps': 57106, 'loss/train': 1.4363473653793335} 08/30/2021 23:28:56 - INFO - __main__ - Step 57108: {'lr': 0.00034759430423029255, 'samples': 10964736, 'steps': 57107, 'loss/train': 1.2451115846633911} 08/30/2021 23:28:56 - INFO - __main__ - Step 57109: {'lr': 0.0003475894185275901, 'samples': 10964928, 'steps': 57108, 'loss/train': 1.2458856105804443} 08/30/2021 23:28:57 - INFO - __main__ - Step 57110: {'lr': 0.00034758453278091537, 'samples': 10965120, 'steps': 57109, 'loss/train': 1.2270549535751343} 08/30/2021 23:28:57 - INFO - __main__ - Step 57111: {'lr': 0.00034757964699027054, 'samples': 10965312, 'steps': 57110, 'loss/train': 0.7215399146080017} 08/30/2021 23:28:59 - INFO - __main__ - Step 57112: {'lr': 0.0003475747611556579, 'samples': 10965504, 'steps': 57111, 'loss/train': 1.2529476881027222} 08/30/2021 23:28:59 - INFO - __main__ - Step 57113: {'lr': 0.0003475698752770795, 'samples': 10965696, 'steps': 57112, 'loss/train': 1.3845411539077759} 08/30/2021 23:29:00 - INFO - __main__ - Step 57114: {'lr': 0.0003475649893545376, 'samples': 10965888, 'steps': 57113, 'loss/train': 1.965736985206604} 08/30/2021 23:29:00 - INFO - __main__ - Step 57115: {'lr': 0.0003475601033880346, 'samples': 10966080, 'steps': 57114, 'loss/train': 1.243262529373169} 08/30/2021 23:29:00 - INFO - __main__ - Step 57116: {'lr': 0.00034755521737757237, 'samples': 10966272, 'steps': 57115, 'loss/train': 0.61931973695755} 08/30/2021 23:29:02 - INFO - __main__ - Step 57117: {'lr': 0.0003475503313231533, 'samples': 10966464, 'steps': 57116, 'loss/train': 1.5781577825546265} 08/30/2021 23:29:03 - INFO - __main__ - Step 57118: {'lr': 0.0003475454452247795, 'samples': 10966656, 'steps': 57117, 'loss/train': 1.2548880577087402} 08/30/2021 23:29:03 - INFO - __main__ - Step 57119: {'lr': 0.00034754055908245326, 'samples': 10966848, 'steps': 57118, 'loss/train': 1.4524797201156616} 08/30/2021 23:29:03 - INFO - __main__ - Step 57120: {'lr': 0.0003475356728961767, 'samples': 10967040, 'steps': 57119, 'loss/train': 0.4162448048591614} 08/30/2021 23:29:04 - INFO - __main__ - Step 57121: {'lr': 0.0003475307866659522, 'samples': 10967232, 'steps': 57120, 'loss/train': 1.1524730920791626} 08/30/2021 23:29:04 - INFO - __main__ - Step 57122: {'lr': 0.00034752590039178175, 'samples': 10967424, 'steps': 57121, 'loss/train': 1.103222131729126} 08/30/2021 23:29:06 - INFO - __main__ - Step 57123: {'lr': 0.00034752101407366763, 'samples': 10967616, 'steps': 57122, 'loss/train': 1.4923452138900757} 08/30/2021 23:29:06 - INFO - __main__ - Step 57124: {'lr': 0.00034751612771161214, 'samples': 10967808, 'steps': 57123, 'loss/train': 0.8017433285713196} 08/30/2021 23:29:07 - INFO - __main__ - Step 57125: {'lr': 0.0003475112413056173, 'samples': 10968000, 'steps': 57124, 'loss/train': 1.3620872497558594} 08/30/2021 23:29:07 - INFO - __main__ - Step 57126: {'lr': 0.0003475063548556854, 'samples': 10968192, 'steps': 57125, 'loss/train': 1.1595778465270996} 08/30/2021 23:29:07 - INFO - __main__ - Step 57127: {'lr': 0.0003475014683618186, 'samples': 10968384, 'steps': 57126, 'loss/train': 1.7068578004837036} 08/30/2021 23:29:09 - INFO - __main__ - Step 57128: {'lr': 0.00034749658182401923, 'samples': 10968576, 'steps': 57127, 'loss/train': 1.121332049369812} 08/30/2021 23:29:09 - INFO - __main__ - Step 57129: {'lr': 0.00034749169524228937, 'samples': 10968768, 'steps': 57128, 'loss/train': 1.7508058547973633} 08/30/2021 23:29:10 - INFO - __main__ - Step 57130: {'lr': 0.0003474868086166312, 'samples': 10968960, 'steps': 57129, 'loss/train': 1.5395227670669556} 08/30/2021 23:29:10 - INFO - __main__ - Step 57131: {'lr': 0.0003474819219470471, 'samples': 10969152, 'steps': 57130, 'loss/train': 0.41437631845474243} 08/30/2021 23:29:10 - INFO - __main__ - Step 57132: {'lr': 0.0003474770352335391, 'samples': 10969344, 'steps': 57131, 'loss/train': 1.6383030414581299} 08/30/2021 23:29:12 - INFO - __main__ - Step 57133: {'lr': 0.00034747214847610943, 'samples': 10969536, 'steps': 57132, 'loss/train': 1.3294097185134888} 08/30/2021 23:29:13 - INFO - __main__ - Step 57134: {'lr': 0.00034746726167476027, 'samples': 10969728, 'steps': 57133, 'loss/train': 1.0824010372161865} 08/30/2021 23:29:13 - INFO - __main__ - Step 57135: {'lr': 0.00034746237482949393, 'samples': 10969920, 'steps': 57134, 'loss/train': 1.1900538206100464} 08/30/2021 23:29:13 - INFO - __main__ - Step 57136: {'lr': 0.0003474574879403126, 'samples': 10970112, 'steps': 57135, 'loss/train': 1.5479648113250732} 08/30/2021 23:29:14 - INFO - __main__ - Step 57137: {'lr': 0.0003474526010072183, 'samples': 10970304, 'steps': 57136, 'loss/train': 1.5143964290618896} 08/30/2021 23:29:15 - INFO - __main__ - Step 57138: {'lr': 0.0003474477140302134, 'samples': 10970496, 'steps': 57137, 'loss/train': 1.0015833377838135} 08/30/2021 23:29:16 - INFO - __main__ - Step 57139: {'lr': 0.0003474428270093001, 'samples': 10970688, 'steps': 57138, 'loss/train': 1.3740386962890625} 08/30/2021 23:29:16 - INFO - __main__ - Step 57140: {'lr': 0.00034743793994448057, 'samples': 10970880, 'steps': 57139, 'loss/train': 0.6994947195053101} 08/30/2021 23:29:16 - INFO - __main__ - Step 57141: {'lr': 0.000347433052835757, 'samples': 10971072, 'steps': 57140, 'loss/train': 1.0940190553665161} 08/30/2021 23:29:17 - INFO - __main__ - Step 57142: {'lr': 0.00034742816568313165, 'samples': 10971264, 'steps': 57141, 'loss/train': 1.4684149026870728} 08/30/2021 23:29:18 - INFO - __main__ - Step 57143: {'lr': 0.0003474232784866066, 'samples': 10971456, 'steps': 57142, 'loss/train': 1.1760928630828857} 08/30/2021 23:29:19 - INFO - __main__ - Step 57144: {'lr': 0.0003474183912461841, 'samples': 10971648, 'steps': 57143, 'loss/train': 2.027261257171631} 08/30/2021 23:29:19 - INFO - __main__ - Step 57145: {'lr': 0.00034741350396186646, 'samples': 10971840, 'steps': 57144, 'loss/train': 1.074097990989685} 08/30/2021 23:29:19 - INFO - __main__ - Step 57146: {'lr': 0.0003474086166336557, 'samples': 10972032, 'steps': 57145, 'loss/train': 1.24247407913208} 08/30/2021 23:29:20 - INFO - __main__ - Step 57147: {'lr': 0.0003474037292615542, 'samples': 10972224, 'steps': 57146, 'loss/train': 0.44781938195228577} 08/30/2021 23:29:20 - INFO - __main__ - Step 57148: {'lr': 0.000347398841845564, 'samples': 10972416, 'steps': 57147, 'loss/train': 2.132817029953003} 08/30/2021 23:29:22 - INFO - __main__ - Step 57149: {'lr': 0.0003473939543856875, 'samples': 10972608, 'steps': 57148, 'loss/train': 2.1498522758483887} 08/30/2021 23:29:22 - INFO - __main__ - Step 57150: {'lr': 0.00034738906688192673, 'samples': 10972800, 'steps': 57149, 'loss/train': 1.2391046285629272} 08/30/2021 23:29:22 - INFO - __main__ - Step 57151: {'lr': 0.0003473841793342839, 'samples': 10972992, 'steps': 57150, 'loss/train': 1.5860317945480347} 08/30/2021 23:29:23 - INFO - __main__ - Step 57152: {'lr': 0.00034737929174276133, 'samples': 10973184, 'steps': 57151, 'loss/train': 0.9298214912414551} 08/30/2021 23:29:23 - INFO - __main__ - Step 57153: {'lr': 0.0003473744041073611, 'samples': 10973376, 'steps': 57152, 'loss/train': 1.6825424432754517} 08/30/2021 23:29:25 - INFO - __main__ - Step 57154: {'lr': 0.0003473695164280855, 'samples': 10973568, 'steps': 57153, 'loss/train': 1.3954739570617676} 08/30/2021 23:29:25 - INFO - __main__ - Step 57155: {'lr': 0.0003473646287049368, 'samples': 10973760, 'steps': 57154, 'loss/train': 1.3306450843811035} 08/30/2021 23:29:25 - INFO - __main__ - Step 57156: {'lr': 0.00034735974093791697, 'samples': 10973952, 'steps': 57155, 'loss/train': 0.9474577307701111} 08/30/2021 23:29:26 - INFO - __main__ - Step 57157: {'lr': 0.00034735485312702835, 'samples': 10974144, 'steps': 57156, 'loss/train': 1.37650465965271} 08/30/2021 23:29:26 - INFO - __main__ - Step 57158: {'lr': 0.00034734996527227313, 'samples': 10974336, 'steps': 57157, 'loss/train': 1.4231430292129517} 08/30/2021 23:29:28 - INFO - __main__ - Step 57159: {'lr': 0.0003473450773736536, 'samples': 10974528, 'steps': 57158, 'loss/train': 1.218062400817871} 08/30/2021 23:29:29 - INFO - __main__ - Step 57160: {'lr': 0.00034734018943117183, 'samples': 10974720, 'steps': 57159, 'loss/train': 0.9181489944458008} 08/30/2021 23:29:29 - INFO - __main__ - Step 57161: {'lr': 0.00034733530144483003, 'samples': 10974912, 'steps': 57160, 'loss/train': 1.6676217317581177} 08/30/2021 23:29:29 - INFO - __main__ - Step 57162: {'lr': 0.0003473304134146305, 'samples': 10975104, 'steps': 57161, 'loss/train': 1.4537638425827026} 08/30/2021 23:29:30 - INFO - __main__ - Step 57163: {'lr': 0.0003473255253405754, 'samples': 10975296, 'steps': 57162, 'loss/train': 1.1282438039779663} 08/30/2021 23:29:30 - INFO - __main__ - Step 57164: {'lr': 0.0003473206372226668, 'samples': 10975488, 'steps': 57163, 'loss/train': 0.19694505631923676} 08/30/2021 23:29:32 - INFO - __main__ - Step 57165: {'lr': 0.0003473157490609071, 'samples': 10975680, 'steps': 57164, 'loss/train': 1.4446901082992554} 08/30/2021 23:29:32 - INFO - __main__ - Step 57166: {'lr': 0.0003473108608552985, 'samples': 10975872, 'steps': 57165, 'loss/train': 1.3291525840759277} 08/30/2021 23:29:32 - INFO - __main__ - Step 57167: {'lr': 0.00034730597260584304, 'samples': 10976064, 'steps': 57166, 'loss/train': 1.3511080741882324} 08/30/2021 23:29:33 - INFO - __main__ - Step 57168: {'lr': 0.0003473010843125431, 'samples': 10976256, 'steps': 57167, 'loss/train': 0.6470757126808167} 08/30/2021 23:29:33 - INFO - __main__ - Step 57169: {'lr': 0.0003472961959754007, 'samples': 10976448, 'steps': 57168, 'loss/train': 1.8624001741409302} 08/30/2021 23:29:35 - INFO - __main__ - Step 57170: {'lr': 0.0003472913075944182, 'samples': 10976640, 'steps': 57169, 'loss/train': 1.0622985363006592} 08/30/2021 23:29:36 - INFO - __main__ - Step 57171: {'lr': 0.00034728641916959767, 'samples': 10976832, 'steps': 57170, 'loss/train': 1.5070276260375977} 08/30/2021 23:29:36 - INFO - __main__ - Step 57172: {'lr': 0.00034728153070094143, 'samples': 10977024, 'steps': 57171, 'loss/train': 0.49868151545524597} 08/30/2021 23:29:36 - INFO - __main__ - Step 57173: {'lr': 0.0003472766421884516, 'samples': 10977216, 'steps': 57172, 'loss/train': 1.0507540702819824} 08/30/2021 23:29:37 - INFO - __main__ - Step 57174: {'lr': 0.00034727175363213046, 'samples': 10977408, 'steps': 57173, 'loss/train': 0.611548900604248} 08/30/2021 23:29:38 - INFO - __main__ - Step 57175: {'lr': 0.0003472668650319801, 'samples': 10977600, 'steps': 57174, 'loss/train': 1.2241181135177612} 08/30/2021 23:29:39 - INFO - __main__ - Step 57176: {'lr': 0.0003472619763880029, 'samples': 10977792, 'steps': 57175, 'loss/train': 0.6720014214515686} 08/30/2021 23:29:39 - INFO - __main__ - Step 57177: {'lr': 0.00034725708770020085, 'samples': 10977984, 'steps': 57176, 'loss/train': 1.5641393661499023} 08/30/2021 23:29:39 - INFO - __main__ - Step 57178: {'lr': 0.0003472521989685763, 'samples': 10978176, 'steps': 57177, 'loss/train': 1.117599606513977} 08/30/2021 23:29:40 - INFO - __main__ - Step 57179: {'lr': 0.00034724731019313145, 'samples': 10978368, 'steps': 57178, 'loss/train': 0.8109197020530701} 08/30/2021 23:29:41 - INFO - __main__ - Step 57180: {'lr': 0.0003472424213738684, 'samples': 10978560, 'steps': 57179, 'loss/train': 1.2628936767578125} 08/30/2021 23:29:42 - INFO - __main__ - Step 57181: {'lr': 0.0003472375325107894, 'samples': 10978752, 'steps': 57180, 'loss/train': 2.362213611602783} 08/30/2021 23:29:42 - INFO - __main__ - Step 57182: {'lr': 0.00034723264360389674, 'samples': 10978944, 'steps': 57181, 'loss/train': 1.6982719898223877} 08/30/2021 23:29:43 - INFO - __main__ - Step 57183: {'lr': 0.0003472277546531925, 'samples': 10979136, 'steps': 57182, 'loss/train': 1.5797861814498901} 08/30/2021 23:29:43 - INFO - __main__ - Step 57184: {'lr': 0.00034722286565867897, 'samples': 10979328, 'steps': 57183, 'loss/train': 0.6407620310783386} 08/30/2021 23:29:43 - INFO - __main__ - Step 57185: {'lr': 0.00034721797662035824, 'samples': 10979520, 'steps': 57184, 'loss/train': 1.0531861782073975} 08/30/2021 23:29:45 - INFO - __main__ - Step 57186: {'lr': 0.00034721308753823266, 'samples': 10979712, 'steps': 57185, 'loss/train': 1.7869772911071777} 08/30/2021 23:29:46 - INFO - __main__ - Step 57187: {'lr': 0.00034720819841230433, 'samples': 10979904, 'steps': 57186, 'loss/train': 1.6745402812957764} 08/30/2021 23:29:46 - INFO - __main__ - Step 57188: {'lr': 0.0003472033092425755, 'samples': 10980096, 'steps': 57187, 'loss/train': 0.025158895179629326} 08/30/2021 23:29:46 - INFO - __main__ - Step 57189: {'lr': 0.00034719842002904844, 'samples': 10980288, 'steps': 57188, 'loss/train': 2.543149709701538} 08/30/2021 23:29:47 - INFO - __main__ - Step 57190: {'lr': 0.00034719353077172516, 'samples': 10980480, 'steps': 57189, 'loss/train': 1.196667194366455} 08/30/2021 23:29:47 - INFO - __main__ - Step 57191: {'lr': 0.00034718864147060803, 'samples': 10980672, 'steps': 57190, 'loss/train': 1.6503345966339111} 08/30/2021 23:29:47 - INFO - __main__ - Step 57192: {'lr': 0.00034718375212569916, 'samples': 10980864, 'steps': 57191, 'loss/train': 1.6431115865707397} 08/30/2021 23:29:49 - INFO - __main__ - Step 57193: {'lr': 0.0003471788627370008, 'samples': 10981056, 'steps': 57192, 'loss/train': 1.0220423936843872} 08/30/2021 23:29:49 - INFO - __main__ - Step 57194: {'lr': 0.0003471739733045151, 'samples': 10981248, 'steps': 57193, 'loss/train': 1.6716105937957764} 08/30/2021 23:29:50 - INFO - __main__ - Step 57195: {'lr': 0.00034716908382824435, 'samples': 10981440, 'steps': 57194, 'loss/train': 0.39487341046333313} 08/30/2021 23:29:50 - INFO - __main__ - Step 57196: {'lr': 0.0003471641943081908, 'samples': 10981632, 'steps': 57195, 'loss/train': 1.2871283292770386} 08/30/2021 23:29:50 - INFO - __main__ - Step 57197: {'lr': 0.0003471593047443564, 'samples': 10981824, 'steps': 57196, 'loss/train': 0.6628235578536987} 08/30/2021 23:29:52 - INFO - __main__ - Step 57198: {'lr': 0.00034715441513674363, 'samples': 10982016, 'steps': 57197, 'loss/train': 1.3066422939300537} 08/30/2021 23:29:52 - INFO - __main__ - Step 57199: {'lr': 0.00034714952548535455, 'samples': 10982208, 'steps': 57198, 'loss/train': 2.057615041732788} 08/30/2021 23:29:53 - INFO - __main__ - Step 57200: {'lr': 0.0003471446357901914, 'samples': 10982400, 'steps': 57199, 'loss/train': 1.4142051935195923} 08/30/2021 23:29:53 - INFO - __main__ - Step 57201: {'lr': 0.0003471397460512563, 'samples': 10982592, 'steps': 57200, 'loss/train': 1.210719347000122} 08/30/2021 23:29:53 - INFO - __main__ - Step 57202: {'lr': 0.0003471348562685517, 'samples': 10982784, 'steps': 57201, 'loss/train': 0.9110336303710938} 08/30/2021 23:29:55 - INFO - __main__ - Step 57203: {'lr': 0.0003471299664420795, 'samples': 10982976, 'steps': 57202, 'loss/train': 0.9891413450241089} 08/30/2021 23:29:56 - INFO - __main__ - Step 57204: {'lr': 0.00034712507657184207, 'samples': 10983168, 'steps': 57203, 'loss/train': 1.6618365049362183} 08/30/2021 23:29:56 - INFO - __main__ - Step 57205: {'lr': 0.00034712018665784155, 'samples': 10983360, 'steps': 57204, 'loss/train': 0.1505172848701477} 08/30/2021 23:29:56 - INFO - __main__ - Step 57206: {'lr': 0.0003471152967000802, 'samples': 10983552, 'steps': 57205, 'loss/train': 1.5891050100326538} 08/30/2021 23:29:57 - INFO - __main__ - Step 57207: {'lr': 0.0003471104066985602, 'samples': 10983744, 'steps': 57206, 'loss/train': 1.4278366565704346} 08/30/2021 23:29:59 - INFO - __main__ - Step 57208: {'lr': 0.0003471055166532837, 'samples': 10983936, 'steps': 57207, 'loss/train': 1.1990008354187012} 08/30/2021 23:29:59 - INFO - __main__ - Step 57209: {'lr': 0.00034710062656425304, 'samples': 10984128, 'steps': 57208, 'loss/train': 1.2362653017044067} 08/30/2021 23:29:59 - INFO - __main__ - Step 57210: {'lr': 0.0003470957364314703, 'samples': 10984320, 'steps': 57209, 'loss/train': 1.130739688873291} 08/30/2021 23:30:00 - INFO - __main__ - Step 57211: {'lr': 0.0003470908462549377, 'samples': 10984512, 'steps': 57210, 'loss/train': 0.7444148063659668} 08/30/2021 23:30:00 - INFO - __main__ - Step 57212: {'lr': 0.00034708595603465743, 'samples': 10984704, 'steps': 57211, 'loss/train': 1.5857688188552856} 08/30/2021 23:30:02 - INFO - __main__ - Step 57213: {'lr': 0.0003470810657706318, 'samples': 10984896, 'steps': 57212, 'loss/train': 0.6763535141944885} 08/30/2021 23:30:03 - INFO - __main__ - Step 57214: {'lr': 0.0003470761754628629, 'samples': 10985088, 'steps': 57213, 'loss/train': 1.6995245218276978} 08/30/2021 23:30:03 - INFO - __main__ - Step 57215: {'lr': 0.000347071285111353, 'samples': 10985280, 'steps': 57214, 'loss/train': 1.137797236442566} 08/30/2021 23:30:03 - INFO - __main__ - Step 57216: {'lr': 0.00034706639471610424, 'samples': 10985472, 'steps': 57215, 'loss/train': 1.124526858329773} 08/30/2021 23:30:04 - INFO - __main__ - Step 57217: {'lr': 0.0003470615042771189, 'samples': 10985664, 'steps': 57216, 'loss/train': 0.02836763486266136} 08/30/2021 23:30:04 - INFO - __main__ - Step 57218: {'lr': 0.00034705661379439914, 'samples': 10985856, 'steps': 57217, 'loss/train': 0.025227637961506844} 08/30/2021 23:30:04 - INFO - __main__ - Step 57219: {'lr': 0.0003470517232679471, 'samples': 10986048, 'steps': 57218, 'loss/train': 1.5040104389190674} 08/30/2021 23:30:06 - INFO - __main__ - Step 57220: {'lr': 0.0003470468326977651, 'samples': 10986240, 'steps': 57219, 'loss/train': 0.09342114627361298} 08/30/2021 23:30:06 - INFO - __main__ - Step 57221: {'lr': 0.0003470419420838553, 'samples': 10986432, 'steps': 57220, 'loss/train': 1.388344645500183} 08/30/2021 23:30:07 - INFO - __main__ - Step 57222: {'lr': 0.0003470370514262199, 'samples': 10986624, 'steps': 57221, 'loss/train': 1.7109969854354858} 08/30/2021 23:30:07 - INFO - __main__ - Step 57223: {'lr': 0.0003470321607248611, 'samples': 10986816, 'steps': 57222, 'loss/train': 1.293199896812439} 08/30/2021 23:30:07 - INFO - __main__ - Step 57224: {'lr': 0.0003470272699797811, 'samples': 10987008, 'steps': 57223, 'loss/train': 1.299668788909912} 08/30/2021 23:30:09 - INFO - __main__ - Step 57225: {'lr': 0.0003470223791909821, 'samples': 10987200, 'steps': 57224, 'loss/train': 1.9548366069793701} 08/30/2021 23:30:09 - INFO - __main__ - Step 57226: {'lr': 0.0003470174883584664, 'samples': 10987392, 'steps': 57225, 'loss/train': 4.906742572784424} 08/30/2021 23:30:10 - INFO - __main__ - Step 57227: {'lr': 0.00034701259748223595, 'samples': 10987584, 'steps': 57226, 'loss/train': 1.3088277578353882} 08/30/2021 23:30:10 - INFO - __main__ - Step 57228: {'lr': 0.00034700770656229324, 'samples': 10987776, 'steps': 57227, 'loss/train': 1.0579522848129272} 08/30/2021 23:30:11 - INFO - __main__ - Step 57229: {'lr': 0.00034700281559864034, 'samples': 10987968, 'steps': 57228, 'loss/train': 1.9059362411499023} 08/30/2021 23:30:11 - INFO - __main__ - Step 57230: {'lr': 0.00034699792459127945, 'samples': 10988160, 'steps': 57229, 'loss/train': 1.5767570734024048} 08/30/2021 23:30:13 - INFO - __main__ - Step 57231: {'lr': 0.00034699303354021285, 'samples': 10988352, 'steps': 57230, 'loss/train': 0.7629421353340149} 08/30/2021 23:30:14 - INFO - __main__ - Step 57232: {'lr': 0.0003469881424454426, 'samples': 10988544, 'steps': 57231, 'loss/train': 1.4237111806869507} 08/30/2021 23:30:14 - INFO - __main__ - Step 57233: {'lr': 0.000346983251306971, 'samples': 10988736, 'steps': 57232, 'loss/train': 1.1473923921585083} 08/30/2021 23:30:14 - INFO - __main__ - Step 57234: {'lr': 0.0003469783601248002, 'samples': 10988928, 'steps': 57233, 'loss/train': 0.9404387474060059} 08/30/2021 23:30:15 - INFO - __main__ - Step 57235: {'lr': 0.0003469734688989326, 'samples': 10989120, 'steps': 57234, 'loss/train': 0.8312382698059082} 08/30/2021 23:30:16 - INFO - __main__ - Step 57236: {'lr': 0.0003469685776293702, 'samples': 10989312, 'steps': 57235, 'loss/train': 1.2217953205108643} 08/30/2021 23:30:17 - INFO - __main__ - Step 57237: {'lr': 0.0003469636863161152, 'samples': 10989504, 'steps': 57236, 'loss/train': 1.2138937711715698} 08/30/2021 23:30:17 - INFO - __main__ - Step 57238: {'lr': 0.0003469587949591698, 'samples': 10989696, 'steps': 57237, 'loss/train': 1.8392994403839111} 08/30/2021 23:30:17 - INFO - __main__ - Step 57239: {'lr': 0.0003469539035585364, 'samples': 10989888, 'steps': 57238, 'loss/train': 0.6179540753364563} 08/30/2021 23:30:18 - INFO - __main__ - Step 57240: {'lr': 0.00034694901211421695, 'samples': 10990080, 'steps': 57239, 'loss/train': 1.163027048110962} 08/30/2021 23:30:19 - INFO - __main__ - Step 57241: {'lr': 0.00034694412062621384, 'samples': 10990272, 'steps': 57240, 'loss/train': 1.2579842805862427} 08/30/2021 23:30:20 - INFO - __main__ - Step 57242: {'lr': 0.0003469392290945292, 'samples': 10990464, 'steps': 57241, 'loss/train': 1.4809110164642334} 08/30/2021 23:30:20 - INFO - __main__ - Step 57243: {'lr': 0.00034693433751916525, 'samples': 10990656, 'steps': 57242, 'loss/train': 1.5301992893218994} 08/30/2021 23:30:20 - INFO - __main__ - Step 57244: {'lr': 0.0003469294459001242, 'samples': 10990848, 'steps': 57243, 'loss/train': 0.4008890986442566} 08/30/2021 23:30:21 - INFO - __main__ - Step 57245: {'lr': 0.0003469245542374082, 'samples': 10991040, 'steps': 57244, 'loss/train': 0.9658870697021484} 08/30/2021 23:30:22 - INFO - __main__ - Step 57246: {'lr': 0.00034691966253101947, 'samples': 10991232, 'steps': 57245, 'loss/train': 1.5814244747161865} 08/30/2021 23:30:23 - INFO - __main__ - Step 57247: {'lr': 0.00034691477078096025, 'samples': 10991424, 'steps': 57246, 'loss/train': 0.972419023513794} 08/30/2021 23:30:23 - INFO - __main__ - Step 57248: {'lr': 0.0003469098789872327, 'samples': 10991616, 'steps': 57247, 'loss/train': 1.6710761785507202} 08/30/2021 23:30:23 - INFO - __main__ - Step 57249: {'lr': 0.0003469049871498392, 'samples': 10991808, 'steps': 57248, 'loss/train': 0.604178786277771} 08/30/2021 23:30:24 - INFO - __main__ - Step 57250: {'lr': 0.0003469000952687817, 'samples': 10992000, 'steps': 57249, 'loss/train': 1.6566071510314941} 08/30/2021 23:30:24 - INFO - __main__ - Step 57251: {'lr': 0.0003468952033440625, 'samples': 10992192, 'steps': 57250, 'loss/train': 0.11098971962928772} 08/30/2021 23:30:26 - INFO - __main__ - Step 57252: {'lr': 0.00034689031137568384, 'samples': 10992384, 'steps': 57251, 'loss/train': 1.3981941938400269} 08/30/2021 23:30:26 - INFO - __main__ - Step 57253: {'lr': 0.0003468854193636479, 'samples': 10992576, 'steps': 57252, 'loss/train': 1.324788212776184} 08/30/2021 23:30:26 - INFO - __main__ - Step 57254: {'lr': 0.00034688052730795683, 'samples': 10992768, 'steps': 57253, 'loss/train': 1.0446434020996094} 08/30/2021 23:30:27 - INFO - __main__ - Step 57255: {'lr': 0.00034687563520861294, 'samples': 10992960, 'steps': 57254, 'loss/train': 1.1589691638946533} 08/30/2021 23:30:27 - INFO - __main__ - Step 57256: {'lr': 0.0003468707430656184, 'samples': 10993152, 'steps': 57255, 'loss/train': 1.2001605033874512} 08/30/2021 23:30:29 - INFO - __main__ - Step 57257: {'lr': 0.00034686585087897537, 'samples': 10993344, 'steps': 57256, 'loss/train': 1.5355124473571777} 08/30/2021 23:30:29 - INFO - __main__ - Step 57258: {'lr': 0.0003468609586486861, 'samples': 10993536, 'steps': 57257, 'loss/train': 1.371069073677063} 08/30/2021 23:30:29 - INFO - __main__ - Step 57259: {'lr': 0.00034685606637475274, 'samples': 10993728, 'steps': 57258, 'loss/train': 1.434818148612976} 08/30/2021 23:30:30 - INFO - __main__ - Step 57260: {'lr': 0.0003468511740571776, 'samples': 10993920, 'steps': 57259, 'loss/train': 0.7995344400405884} 08/30/2021 23:30:30 - INFO - __main__ - Step 57261: {'lr': 0.00034684628169596277, 'samples': 10994112, 'steps': 57260, 'loss/train': 1.8994543552398682} 08/30/2021 23:30:32 - INFO - __main__ - Step 57262: {'lr': 0.0003468413892911105, 'samples': 10994304, 'steps': 57261, 'loss/train': 2.1002390384674072} 08/30/2021 23:30:32 - INFO - __main__ - Step 57263: {'lr': 0.00034683649684262303, 'samples': 10994496, 'steps': 57262, 'loss/train': 1.83897066116333} 08/30/2021 23:30:32 - INFO - __main__ - Step 57264: {'lr': 0.0003468316043505025, 'samples': 10994688, 'steps': 57263, 'loss/train': 1.3655487298965454} 08/30/2021 23:30:33 - INFO - __main__ - Step 57265: {'lr': 0.00034682671181475113, 'samples': 10994880, 'steps': 57264, 'loss/train': 0.42163142561912537} 08/30/2021 23:30:33 - INFO - __main__ - Step 57266: {'lr': 0.00034682181923537114, 'samples': 10995072, 'steps': 57265, 'loss/train': 1.3709806203842163} 08/30/2021 23:30:35 - INFO - __main__ - Step 57267: {'lr': 0.0003468169266123647, 'samples': 10995264, 'steps': 57266, 'loss/train': 1.3205724954605103} 08/30/2021 23:30:35 - INFO - __main__ - Step 57268: {'lr': 0.0003468120339457341, 'samples': 10995456, 'steps': 57267, 'loss/train': 1.3158334493637085} 08/30/2021 23:30:35 - INFO - __main__ - Step 57269: {'lr': 0.00034680714123548146, 'samples': 10995648, 'steps': 57268, 'loss/train': 0.8541487455368042} 08/30/2021 23:30:36 - INFO - __main__ - Step 57270: {'lr': 0.0003468022484816091, 'samples': 10995840, 'steps': 57269, 'loss/train': 0.060717690736055374} 08/30/2021 23:30:36 - INFO - __main__ - Step 57271: {'lr': 0.0003467973556841191, 'samples': 10996032, 'steps': 57270, 'loss/train': 1.8877067565917969} 08/30/2021 23:30:38 - INFO - __main__ - Step 57272: {'lr': 0.00034679246284301365, 'samples': 10996224, 'steps': 57271, 'loss/train': 0.3249967396259308} 08/30/2021 23:30:38 - INFO - __main__ - Step 57273: {'lr': 0.000346787569958295, 'samples': 10996416, 'steps': 57272, 'loss/train': 1.5828485488891602} 08/30/2021 23:30:38 - INFO - __main__ - Step 57274: {'lr': 0.0003467826770299654, 'samples': 10996608, 'steps': 57273, 'loss/train': 1.472226619720459} 08/30/2021 23:30:39 - INFO - __main__ - Step 57275: {'lr': 0.000346777784058027, 'samples': 10996800, 'steps': 57274, 'loss/train': 1.2954763174057007} 08/30/2021 23:30:39 - INFO - __main__ - Step 57276: {'lr': 0.0003467728910424821, 'samples': 10996992, 'steps': 57275, 'loss/train': 1.5763912200927734} 08/30/2021 23:30:40 - INFO - __main__ - Step 57277: {'lr': 0.0003467679979833328, 'samples': 10997184, 'steps': 57276, 'loss/train': 1.3015037775039673} 08/30/2021 23:30:41 - INFO - __main__ - Step 57278: {'lr': 0.00034676310488058126, 'samples': 10997376, 'steps': 57277, 'loss/train': 1.4174572229385376} 08/30/2021 23:30:41 - INFO - __main__ - Step 57279: {'lr': 0.00034675821173422983, 'samples': 10997568, 'steps': 57278, 'loss/train': 0.16137470304965973} 08/30/2021 23:30:42 - INFO - __main__ - Step 57280: {'lr': 0.0003467533185442806, 'samples': 10997760, 'steps': 57279, 'loss/train': 1.961804747581482} 08/30/2021 23:30:42 - INFO - __main__ - Step 57281: {'lr': 0.00034674842531073587, 'samples': 10997952, 'steps': 57280, 'loss/train': 1.2561326026916504} 08/30/2021 23:30:44 - INFO - __main__ - Step 57282: {'lr': 0.0003467435320335978, 'samples': 10998144, 'steps': 57281, 'loss/train': 1.0557690858840942} 08/30/2021 23:30:44 - INFO - __main__ - Step 57283: {'lr': 0.00034673863871286854, 'samples': 10998336, 'steps': 57282, 'loss/train': 0.20197616517543793} 08/30/2021 23:30:45 - INFO - __main__ - Step 57284: {'lr': 0.00034673374534855035, 'samples': 10998528, 'steps': 57283, 'loss/train': 0.9004855155944824} 08/30/2021 23:30:45 - INFO - __main__ - Step 57285: {'lr': 0.0003467288519406454, 'samples': 10998720, 'steps': 57284, 'loss/train': 1.4420886039733887} 08/30/2021 23:30:46 - INFO - __main__ - Step 57286: {'lr': 0.00034672395848915594, 'samples': 10998912, 'steps': 57285, 'loss/train': 0.196761816740036} 08/30/2021 23:30:46 - INFO - __main__ - Step 57287: {'lr': 0.00034671906499408417, 'samples': 10999104, 'steps': 57286, 'loss/train': 1.5899916887283325} 08/30/2021 23:30:47 - INFO - __main__ - Step 57288: {'lr': 0.0003467141714554323, 'samples': 10999296, 'steps': 57287, 'loss/train': 0.96351557970047} 08/30/2021 23:30:48 - INFO - __main__ - Step 57289: {'lr': 0.0003467092778732025, 'samples': 10999488, 'steps': 57288, 'loss/train': 1.1077650785446167} 08/30/2021 23:30:48 - INFO - __main__ - Step 57290: {'lr': 0.00034670438424739695, 'samples': 10999680, 'steps': 57289, 'loss/train': 1.1022433042526245} 08/30/2021 23:30:49 - INFO - __main__ - Step 57291: {'lr': 0.000346699490578018, 'samples': 10999872, 'steps': 57290, 'loss/train': 1.5361850261688232} 08/30/2021 23:30:49 - INFO - __main__ - Step 57292: {'lr': 0.00034669459686506766, 'samples': 11000064, 'steps': 57291, 'loss/train': 0.9836366176605225} 08/30/2021 23:30:50 - INFO - __main__ - Step 57293: {'lr': 0.0003466897031085482, 'samples': 11000256, 'steps': 57292, 'loss/train': 0.29051727056503296} 08/30/2021 23:30:51 - INFO - __main__ - Step 57294: {'lr': 0.000346684809308462, 'samples': 11000448, 'steps': 57293, 'loss/train': 1.387253999710083} 08/30/2021 23:30:51 - INFO - __main__ - Step 57295: {'lr': 0.00034667991546481096, 'samples': 11000640, 'steps': 57294, 'loss/train': 0.2907862067222595} 08/30/2021 23:30:52 - INFO - __main__ - Step 57296: {'lr': 0.0003466750215775975, 'samples': 11000832, 'steps': 57295, 'loss/train': 1.8339520692825317} 08/30/2021 23:30:52 - INFO - __main__ - Step 57297: {'lr': 0.0003466701276468238, 'samples': 11001024, 'steps': 57296, 'loss/train': 1.5265629291534424} 08/30/2021 23:30:53 - INFO - __main__ - Step 57298: {'lr': 0.00034666523367249196, 'samples': 11001216, 'steps': 57297, 'loss/train': 1.4608943462371826} 08/30/2021 23:30:54 - INFO - __main__ - Step 57299: {'lr': 0.0003466603396546043, 'samples': 11001408, 'steps': 57298, 'loss/train': 1.4062610864639282} 08/30/2021 23:30:54 - INFO - __main__ - Step 57300: {'lr': 0.00034665544559316303, 'samples': 11001600, 'steps': 57299, 'loss/train': 1.1037054061889648} 08/30/2021 23:30:55 - INFO - __main__ - Step 57301: {'lr': 0.0003466505514881703, 'samples': 11001792, 'steps': 57300, 'loss/train': 1.4081497192382812} 08/30/2021 23:30:55 - INFO - __main__ - Step 57302: {'lr': 0.00034664565733962823, 'samples': 11001984, 'steps': 57301, 'loss/train': 1.5334961414337158} 08/30/2021 23:30:56 - INFO - __main__ - Step 57303: {'lr': 0.0003466407631475392, 'samples': 11002176, 'steps': 57302, 'loss/train': 1.279776692390442} 08/30/2021 23:30:57 - INFO - __main__ - Step 57304: {'lr': 0.00034663586891190524, 'samples': 11002368, 'steps': 57303, 'loss/train': 1.3260341882705688} 08/30/2021 23:30:57 - INFO - __main__ - Step 57305: {'lr': 0.0003466309746327288, 'samples': 11002560, 'steps': 57304, 'loss/train': 1.4453420639038086} 08/30/2021 23:30:58 - INFO - __main__ - Step 57306: {'lr': 0.0003466260803100118, 'samples': 11002752, 'steps': 57305, 'loss/train': 1.8678979873657227} 08/30/2021 23:30:58 - INFO - __main__ - Step 57307: {'lr': 0.0003466211859437566, 'samples': 11002944, 'steps': 57306, 'loss/train': 1.5966711044311523} 08/30/2021 23:30:59 - INFO - __main__ - Step 57308: {'lr': 0.00034661629153396543, 'samples': 11003136, 'steps': 57307, 'loss/train': 0.9747397303581238} 08/30/2021 23:31:00 - INFO - __main__ - Step 57309: {'lr': 0.00034661139708064043, 'samples': 11003328, 'steps': 57308, 'loss/train': 1.411629557609558} 08/30/2021 23:31:00 - INFO - __main__ - Step 57310: {'lr': 0.00034660650258378384, 'samples': 11003520, 'steps': 57309, 'loss/train': 1.2113087177276611} 08/30/2021 23:31:00 - INFO - __main__ - Step 57311: {'lr': 0.00034660160804339784, 'samples': 11003712, 'steps': 57310, 'loss/train': 0.812248945236206} 08/30/2021 23:31:01 - INFO - __main__ - Step 57312: {'lr': 0.0003465967134594847, 'samples': 11003904, 'steps': 57311, 'loss/train': 1.4831023216247559} 08/30/2021 23:31:02 - INFO - __main__ - Step 57313: {'lr': 0.0003465918188320465, 'samples': 11004096, 'steps': 57312, 'loss/train': 1.0299956798553467} 08/30/2021 23:31:03 - INFO - __main__ - Step 57314: {'lr': 0.0003465869241610855, 'samples': 11004288, 'steps': 57313, 'loss/train': 1.2239888906478882} 08/30/2021 23:31:03 - INFO - __main__ - Step 57315: {'lr': 0.00034658202944660396, 'samples': 11004480, 'steps': 57314, 'loss/train': 0.9121844172477722} 08/30/2021 23:31:03 - INFO - __main__ - Step 57316: {'lr': 0.000346577134688604, 'samples': 11004672, 'steps': 57315, 'loss/train': 0.7463312149047852} 08/30/2021 23:31:04 - INFO - __main__ - Step 57317: {'lr': 0.00034657223988708796, 'samples': 11004864, 'steps': 57316, 'loss/train': 1.2851439714431763} 08/30/2021 23:31:05 - INFO - __main__ - Step 57318: {'lr': 0.0003465673450420579, 'samples': 11005056, 'steps': 57317, 'loss/train': 1.7752279043197632} 08/30/2021 23:31:06 - INFO - __main__ - Step 57319: {'lr': 0.0003465624501535161, 'samples': 11005248, 'steps': 57318, 'loss/train': 0.5596683025360107} 08/30/2021 23:31:06 - INFO - __main__ - Step 57320: {'lr': 0.0003465575552214648, 'samples': 11005440, 'steps': 57319, 'loss/train': 0.9630799293518066} 08/30/2021 23:31:06 - INFO - __main__ - Step 57321: {'lr': 0.00034655266024590604, 'samples': 11005632, 'steps': 57320, 'loss/train': 0.9939124584197998} 08/30/2021 23:31:07 - INFO - __main__ - Step 57322: {'lr': 0.0003465477652268422, 'samples': 11005824, 'steps': 57321, 'loss/train': 1.6171754598617554} 08/30/2021 23:31:07 - INFO - __main__ - Step 57323: {'lr': 0.0003465428701642755, 'samples': 11006016, 'steps': 57322, 'loss/train': 1.4679523706436157} 08/30/2021 23:31:09 - INFO - __main__ - Step 57324: {'lr': 0.00034653797505820795, 'samples': 11006208, 'steps': 57323, 'loss/train': 1.0676627159118652} 08/30/2021 23:31:09 - INFO - __main__ - Step 57325: {'lr': 0.000346533079908642, 'samples': 11006400, 'steps': 57324, 'loss/train': 1.207576036453247} 08/30/2021 23:31:09 - INFO - __main__ - Step 57326: {'lr': 0.0003465281847155796, 'samples': 11006592, 'steps': 57325, 'loss/train': 0.9534304141998291} 08/30/2021 23:31:10 - INFO - __main__ - Step 57327: {'lr': 0.00034652328947902317, 'samples': 11006784, 'steps': 57326, 'loss/train': 0.3770281672477722} 08/30/2021 23:31:10 - INFO - __main__ - Step 57328: {'lr': 0.0003465183941989748, 'samples': 11006976, 'steps': 57327, 'loss/train': 2.1630043983459473} 08/30/2021 23:31:12 - INFO - __main__ - Step 57329: {'lr': 0.00034651349887543674, 'samples': 11007168, 'steps': 57328, 'loss/train': 1.3944100141525269} 08/30/2021 23:31:13 - INFO - __main__ - Step 57330: {'lr': 0.00034650860350841125, 'samples': 11007360, 'steps': 57329, 'loss/train': 1.5637726783752441} 08/30/2021 23:31:13 - INFO - __main__ - Step 57331: {'lr': 0.0003465037080979004, 'samples': 11007552, 'steps': 57330, 'loss/train': 1.1711291074752808} 08/30/2021 23:31:13 - INFO - __main__ - Step 57332: {'lr': 0.0003464988126439065, 'samples': 11007744, 'steps': 57331, 'loss/train': 1.5800998210906982} 08/30/2021 23:31:14 - INFO - __main__ - Step 57333: {'lr': 0.0003464939171464317, 'samples': 11007936, 'steps': 57332, 'loss/train': 1.5062569379806519} 08/30/2021 23:31:15 - INFO - __main__ - Step 57334: {'lr': 0.0003464890216054782, 'samples': 11008128, 'steps': 57333, 'loss/train': 0.6435001492500305} 08/30/2021 23:31:16 - INFO - __main__ - Step 57335: {'lr': 0.0003464841260210483, 'samples': 11008320, 'steps': 57334, 'loss/train': 1.5605562925338745} 08/30/2021 23:31:16 - INFO - __main__ - Step 57336: {'lr': 0.0003464792303931441, 'samples': 11008512, 'steps': 57335, 'loss/train': 1.2090848684310913} 08/30/2021 23:31:16 - INFO - __main__ - Step 57337: {'lr': 0.0003464743347217679, 'samples': 11008704, 'steps': 57336, 'loss/train': 1.2363115549087524} 08/30/2021 23:31:17 - INFO - __main__ - Step 57338: {'lr': 0.00034646943900692187, 'samples': 11008896, 'steps': 57337, 'loss/train': 1.659374713897705} 08/30/2021 23:31:17 - INFO - __main__ - Step 57339: {'lr': 0.0003464645432486081, 'samples': 11009088, 'steps': 57338, 'loss/train': 1.7757110595703125} 08/30/2021 23:31:18 - INFO - __main__ - Step 57340: {'lr': 0.000346459647446829, 'samples': 11009280, 'steps': 57339, 'loss/train': 0.7484453320503235} 08/30/2021 23:31:19 - INFO - __main__ - Step 57341: {'lr': 0.0003464547516015866, 'samples': 11009472, 'steps': 57340, 'loss/train': 1.7045379877090454} 08/30/2021 23:31:19 - INFO - __main__ - Step 57342: {'lr': 0.0003464498557128832, 'samples': 11009664, 'steps': 57341, 'loss/train': 0.5957180261611938} 08/30/2021 23:31:20 - INFO - __main__ - Step 57343: {'lr': 0.00034644495978072094, 'samples': 11009856, 'steps': 57342, 'loss/train': 1.2689871788024902} 08/30/2021 23:31:20 - INFO - __main__ - Step 57344: {'lr': 0.00034644006380510215, 'samples': 11010048, 'steps': 57343, 'loss/train': 1.3786475658416748} 08/30/2021 23:31:22 - INFO - __main__ - Step 57345: {'lr': 0.0003464351677860289, 'samples': 11010240, 'steps': 57344, 'loss/train': 1.326842188835144} 08/30/2021 23:31:22 - INFO - __main__ - Step 57346: {'lr': 0.00034643027172350345, 'samples': 11010432, 'steps': 57345, 'loss/train': 0.49562159180641174} 08/30/2021 23:31:23 - INFO - __main__ - Step 57347: {'lr': 0.000346425375617528, 'samples': 11010624, 'steps': 57346, 'loss/train': 0.0715513676404953} 08/30/2021 23:31:23 - INFO - __main__ - Step 57348: {'lr': 0.00034642047946810477, 'samples': 11010816, 'steps': 57347, 'loss/train': 1.4194996356964111} 08/30/2021 23:31:23 - INFO - __main__ - Step 57349: {'lr': 0.000346415583275236, 'samples': 11011008, 'steps': 57348, 'loss/train': 2.7789392471313477} 08/30/2021 23:31:25 - INFO - __main__ - Step 57350: {'lr': 0.00034641068703892387, 'samples': 11011200, 'steps': 57349, 'loss/train': 1.1572437286376953} 08/30/2021 23:31:26 - INFO - __main__ - Step 57351: {'lr': 0.00034640579075917053, 'samples': 11011392, 'steps': 57350, 'loss/train': 1.1089028120040894} 08/30/2021 23:31:26 - INFO - __main__ - Step 57352: {'lr': 0.0003464008944359782, 'samples': 11011584, 'steps': 57351, 'loss/train': 1.3850922584533691} 08/30/2021 23:31:26 - INFO - __main__ - Step 57353: {'lr': 0.00034639599806934917, 'samples': 11011776, 'steps': 57352, 'loss/train': 0.5813507437705994} 08/30/2021 23:31:27 - INFO - __main__ - Step 57354: {'lr': 0.0003463911016592856, 'samples': 11011968, 'steps': 57353, 'loss/train': 1.7996010780334473} 08/30/2021 23:31:27 - INFO - __main__ - Step 57355: {'lr': 0.0003463862052057896, 'samples': 11012160, 'steps': 57354, 'loss/train': 1.597270131111145} 08/30/2021 23:31:29 - INFO - __main__ - Step 57356: {'lr': 0.00034638130870886353, 'samples': 11012352, 'steps': 57355, 'loss/train': 1.2265816926956177} 08/30/2021 23:31:29 - INFO - __main__ - Step 57357: {'lr': 0.0003463764121685096, 'samples': 11012544, 'steps': 57356, 'loss/train': 2.6046159267425537} 08/30/2021 23:31:30 - INFO - __main__ - Step 57358: {'lr': 0.0003463715155847298, 'samples': 11012736, 'steps': 57357, 'loss/train': 1.6963657140731812} 08/30/2021 23:31:30 - INFO - __main__ - Step 57359: {'lr': 0.00034636661895752653, 'samples': 11012928, 'steps': 57358, 'loss/train': 1.3072112798690796} 08/30/2021 23:31:30 - INFO - __main__ - Step 57360: {'lr': 0.000346361722286902, 'samples': 11013120, 'steps': 57359, 'loss/train': 2.336559534072876} 08/30/2021 23:31:32 - INFO - __main__ - Step 57361: {'lr': 0.0003463568255728583, 'samples': 11013312, 'steps': 57360, 'loss/train': 1.2347654104232788} 08/30/2021 23:31:33 - INFO - __main__ - Step 57362: {'lr': 0.0003463519288153977, 'samples': 11013504, 'steps': 57361, 'loss/train': 1.929038643836975} 08/30/2021 23:31:33 - INFO - __main__ - Step 57363: {'lr': 0.00034634703201452243, 'samples': 11013696, 'steps': 57362, 'loss/train': 1.1651383638381958} 08/30/2021 23:31:33 - INFO - __main__ - Step 57364: {'lr': 0.00034634213517023473, 'samples': 11013888, 'steps': 57363, 'loss/train': 1.8477355241775513} 08/30/2021 23:31:34 - INFO - __main__ - Step 57365: {'lr': 0.0003463372382825367, 'samples': 11014080, 'steps': 57364, 'loss/train': 1.1793138980865479} 08/30/2021 23:31:34 - INFO - __main__ - Step 57366: {'lr': 0.0003463323413514306, 'samples': 11014272, 'steps': 57365, 'loss/train': 1.0213637351989746} 08/30/2021 23:31:35 - INFO - __main__ - Step 57367: {'lr': 0.0003463274443769186, 'samples': 11014464, 'steps': 57366, 'loss/train': 1.834344744682312} 08/30/2021 23:31:36 - INFO - __main__ - Step 57368: {'lr': 0.000346322547359003, 'samples': 11014656, 'steps': 57367, 'loss/train': 1.634212851524353} 08/30/2021 23:31:36 - INFO - __main__ - Step 57369: {'lr': 0.00034631765029768594, 'samples': 11014848, 'steps': 57368, 'loss/train': 1.4976794719696045} 08/30/2021 23:31:37 - INFO - __main__ - Step 57370: {'lr': 0.0003463127531929696, 'samples': 11015040, 'steps': 57369, 'loss/train': 1.355198621749878} 08/30/2021 23:31:37 - INFO - __main__ - Step 57371: {'lr': 0.0003463078560448562, 'samples': 11015232, 'steps': 57370, 'loss/train': 0.6016204953193665} 08/30/2021 23:31:39 - INFO - __main__ - Step 57372: {'lr': 0.000346302958853348, 'samples': 11015424, 'steps': 57371, 'loss/train': 1.2660144567489624} 08/30/2021 23:31:39 - INFO - __main__ - Step 57373: {'lr': 0.0003462980616184472, 'samples': 11015616, 'steps': 57372, 'loss/train': 1.4212183952331543} 08/30/2021 23:31:40 - INFO - __main__ - Step 57374: {'lr': 0.0003462931643401559, 'samples': 11015808, 'steps': 57373, 'loss/train': 0.12295351922512054} 08/30/2021 23:31:40 - INFO - __main__ - Step 57375: {'lr': 0.00034628826701847644, 'samples': 11016000, 'steps': 57374, 'loss/train': 0.24981556832790375} 08/30/2021 23:31:40 - INFO - __main__ - Step 57376: {'lr': 0.000346283369653411, 'samples': 11016192, 'steps': 57375, 'loss/train': 1.6498953104019165} 08/30/2021 23:31:41 - INFO - __main__ - Step 57377: {'lr': 0.0003462784722449617, 'samples': 11016384, 'steps': 57376, 'loss/train': 1.4843896627426147} 08/30/2021 23:31:42 - INFO - __main__ - Step 57378: {'lr': 0.00034627357479313087, 'samples': 11016576, 'steps': 57377, 'loss/train': 1.4692051410675049} 08/30/2021 23:31:43 - INFO - __main__ - Step 57379: {'lr': 0.0003462686772979206, 'samples': 11016768, 'steps': 57378, 'loss/train': 1.530622959136963} 08/30/2021 23:31:43 - INFO - __main__ - Step 57380: {'lr': 0.00034626377975933314, 'samples': 11016960, 'steps': 57379, 'loss/train': 1.1929035186767578} 08/30/2021 23:31:43 - INFO - __main__ - Step 57381: {'lr': 0.00034625888217737076, 'samples': 11017152, 'steps': 57380, 'loss/train': 1.2990503311157227} 08/30/2021 23:31:44 - INFO - __main__ - Step 57382: {'lr': 0.0003462539845520356, 'samples': 11017344, 'steps': 57381, 'loss/train': 1.8029626607894897} 08/30/2021 23:31:45 - INFO - __main__ - Step 57383: {'lr': 0.0003462490868833298, 'samples': 11017536, 'steps': 57382, 'loss/train': 1.5081582069396973} 08/30/2021 23:31:46 - INFO - __main__ - Step 57384: {'lr': 0.00034624418917125575, 'samples': 11017728, 'steps': 57383, 'loss/train': 0.750413715839386} 08/30/2021 23:31:46 - INFO - __main__ - Step 57385: {'lr': 0.00034623929141581555, 'samples': 11017920, 'steps': 57384, 'loss/train': 1.3719102144241333} 08/30/2021 23:31:46 - INFO - __main__ - Step 57386: {'lr': 0.0003462343936170114, 'samples': 11018112, 'steps': 57385, 'loss/train': 0.7519006133079529} 08/30/2021 23:31:47 - INFO - __main__ - Step 57387: {'lr': 0.0003462294957748455, 'samples': 11018304, 'steps': 57386, 'loss/train': 1.6113674640655518} 08/30/2021 23:31:49 - INFO - __main__ - Step 57388: {'lr': 0.00034622459788932004, 'samples': 11018496, 'steps': 57387, 'loss/train': 1.7479612827301025} 08/30/2021 23:31:50 - INFO - __main__ - Step 57389: {'lr': 0.00034621969996043725, 'samples': 11018688, 'steps': 57388, 'loss/train': 1.1651045083999634} 08/30/2021 23:31:50 - INFO - __main__ - Step 57390: {'lr': 0.0003462148019881994, 'samples': 11018880, 'steps': 57389, 'loss/train': 1.542141318321228} 08/30/2021 23:31:50 - INFO - __main__ - Step 57391: {'lr': 0.0003462099039726087, 'samples': 11019072, 'steps': 57390, 'loss/train': 1.809544563293457} 08/30/2021 23:31:51 - INFO - __main__ - Step 57392: {'lr': 0.0003462050059136672, 'samples': 11019264, 'steps': 57391, 'loss/train': 0.29521748423576355} 08/30/2021 23:31:51 - INFO - __main__ - Step 57393: {'lr': 0.00034620010781137724, 'samples': 11019456, 'steps': 57392, 'loss/train': 0.07345857471227646} 08/30/2021 23:31:52 - INFO - __main__ - Step 57394: {'lr': 0.000346195209665741, 'samples': 11019648, 'steps': 57393, 'loss/train': 0.1919942945241928} 08/30/2021 23:31:53 - INFO - __main__ - Step 57395: {'lr': 0.0003461903114767607, 'samples': 11019840, 'steps': 57394, 'loss/train': 1.1142783164978027} 08/30/2021 23:31:53 - INFO - __main__ - Step 57396: {'lr': 0.00034618541324443844, 'samples': 11020032, 'steps': 57395, 'loss/train': 1.2094385623931885} 08/30/2021 23:31:54 - INFO - __main__ - Step 57397: {'lr': 0.0003461805149687767, 'samples': 11020224, 'steps': 57396, 'loss/train': 1.3354653120040894} 08/30/2021 23:31:54 - INFO - __main__ - Step 57398: {'lr': 0.0003461756166497773, 'samples': 11020416, 'steps': 57397, 'loss/train': 1.1025032997131348} 08/30/2021 23:31:55 - INFO - __main__ - Step 57399: {'lr': 0.00034617071828744274, 'samples': 11020608, 'steps': 57398, 'loss/train': 1.3498547077178955} 08/30/2021 23:31:56 - INFO - __main__ - Step 57400: {'lr': 0.00034616581988177516, 'samples': 11020800, 'steps': 57399, 'loss/train': 1.1205404996871948} 08/30/2021 23:31:56 - INFO - __main__ - Step 57401: {'lr': 0.00034616092143277674, 'samples': 11020992, 'steps': 57400, 'loss/train': 1.4811197519302368} 08/30/2021 23:31:57 - INFO - __main__ - Step 57402: {'lr': 0.0003461560229404497, 'samples': 11021184, 'steps': 57401, 'loss/train': 1.1703927516937256} 08/30/2021 23:31:57 - INFO - __main__ - Step 57403: {'lr': 0.0003461511244047962, 'samples': 11021376, 'steps': 57402, 'loss/train': 1.2746347188949585} 08/30/2021 23:31:58 - INFO - __main__ - Step 57404: {'lr': 0.0003461462258258185, 'samples': 11021568, 'steps': 57403, 'loss/train': 1.725419044494629} 08/30/2021 23:31:59 - INFO - __main__ - Step 57405: {'lr': 0.00034614132720351884, 'samples': 11021760, 'steps': 57404, 'loss/train': 1.8319494724273682} 08/30/2021 23:31:59 - INFO - __main__ - Step 57406: {'lr': 0.00034613642853789927, 'samples': 11021952, 'steps': 57405, 'loss/train': 1.7207472324371338} 08/30/2021 23:32:00 - INFO - __main__ - Step 57407: {'lr': 0.00034613152982896224, 'samples': 11022144, 'steps': 57406, 'loss/train': 1.7767510414123535} 08/30/2021 23:32:00 - INFO - __main__ - Step 57408: {'lr': 0.0003461266310767097, 'samples': 11022336, 'steps': 57407, 'loss/train': 1.6346405744552612} 08/30/2021 23:32:01 - INFO - __main__ - Step 57409: {'lr': 0.00034612173228114405, 'samples': 11022528, 'steps': 57408, 'loss/train': 1.8527367115020752} 08/30/2021 23:32:02 - INFO - __main__ - Step 57410: {'lr': 0.00034611683344226745, 'samples': 11022720, 'steps': 57409, 'loss/train': 1.2960453033447266} 08/30/2021 23:32:02 - INFO - __main__ - Step 57411: {'lr': 0.0003461119345600821, 'samples': 11022912, 'steps': 57410, 'loss/train': 1.781599998474121} 08/30/2021 23:32:03 - INFO - __main__ - Step 57412: {'lr': 0.0003461070356345902, 'samples': 11023104, 'steps': 57411, 'loss/train': 1.507386565208435} 08/30/2021 23:32:03 - INFO - __main__ - Step 57413: {'lr': 0.0003461021366657939, 'samples': 11023296, 'steps': 57412, 'loss/train': 1.5147545337677002} 08/30/2021 23:32:05 - INFO - __main__ - Step 57414: {'lr': 0.00034609723765369546, 'samples': 11023488, 'steps': 57413, 'loss/train': 0.9106054902076721} 08/30/2021 23:32:05 - INFO - __main__ - Step 57415: {'lr': 0.00034609233859829707, 'samples': 11023680, 'steps': 57414, 'loss/train': 1.2979462146759033} 08/30/2021 23:32:06 - INFO - __main__ - Step 57416: {'lr': 0.00034608743949960096, 'samples': 11023872, 'steps': 57415, 'loss/train': 1.0761560201644897} 08/30/2021 23:32:06 - INFO - __main__ - Step 57417: {'lr': 0.00034608254035760946, 'samples': 11024064, 'steps': 57416, 'loss/train': 1.3184657096862793} 08/30/2021 23:32:06 - INFO - __main__ - Step 57418: {'lr': 0.0003460776411723245, 'samples': 11024256, 'steps': 57417, 'loss/train': 0.8684802651405334} 08/30/2021 23:32:07 - INFO - __main__ - Step 57419: {'lr': 0.00034607274194374847, 'samples': 11024448, 'steps': 57418, 'loss/train': 1.115295171737671} 08/30/2021 23:32:07 - INFO - __main__ - Step 57420: {'lr': 0.00034606784267188364, 'samples': 11024640, 'steps': 57419, 'loss/train': 0.036703579127788544} 08/30/2021 23:32:09 - INFO - __main__ - Step 57421: {'lr': 0.000346062943356732, 'samples': 11024832, 'steps': 57420, 'loss/train': 0.02843855880200863} 08/30/2021 23:32:09 - INFO - __main__ - Step 57422: {'lr': 0.00034605804399829595, 'samples': 11025024, 'steps': 57421, 'loss/train': 0.05390862002968788} 08/30/2021 23:32:10 - INFO - __main__ - Step 57423: {'lr': 0.00034605314459657763, 'samples': 11025216, 'steps': 57422, 'loss/train': 0.08192064613103867} 08/30/2021 23:32:10 - INFO - __main__ - Step 57424: {'lr': 0.00034604824515157916, 'samples': 11025408, 'steps': 57423, 'loss/train': 1.0345810651779175} 08/30/2021 23:32:10 - INFO - __main__ - Step 57425: {'lr': 0.0003460433456633029, 'samples': 11025600, 'steps': 57424, 'loss/train': 1.5606253147125244} 08/30/2021 23:32:11 - INFO - __main__ - Step 57426: {'lr': 0.000346038446131751, 'samples': 11025792, 'steps': 57425, 'loss/train': 0.9615251421928406} 08/30/2021 23:32:12 - INFO - __main__ - Step 57427: {'lr': 0.0003460335465569256, 'samples': 11025984, 'steps': 57426, 'loss/train': 1.2716492414474487} 08/30/2021 23:32:13 - INFO - __main__ - Step 57428: {'lr': 0.0003460286469388291, 'samples': 11026176, 'steps': 57427, 'loss/train': 1.3033071756362915} 08/30/2021 23:32:13 - INFO - __main__ - Step 57429: {'lr': 0.0003460237472774634, 'samples': 11026368, 'steps': 57428, 'loss/train': 0.9254215359687805} 08/30/2021 23:32:14 - INFO - __main__ - Step 57430: {'lr': 0.000346018847572831, 'samples': 11026560, 'steps': 57429, 'loss/train': 1.2488702535629272} 08/30/2021 23:32:14 - INFO - __main__ - Step 57431: {'lr': 0.00034601394782493393, 'samples': 11026752, 'steps': 57430, 'loss/train': 1.6453608274459839} 08/30/2021 23:32:16 - INFO - __main__ - Step 57432: {'lr': 0.00034600904803377454, 'samples': 11026944, 'steps': 57431, 'loss/train': 1.4031685590744019} 08/30/2021 23:32:16 - INFO - __main__ - Step 57433: {'lr': 0.0003460041481993549, 'samples': 11027136, 'steps': 57432, 'loss/train': 0.7683749794960022} 08/30/2021 23:32:17 - INFO - __main__ - Step 57434: {'lr': 0.0003459992483216773, 'samples': 11027328, 'steps': 57433, 'loss/train': 0.18001098930835724} 08/30/2021 23:32:17 - INFO - __main__ - Step 57435: {'lr': 0.0003459943484007438, 'samples': 11027520, 'steps': 57434, 'loss/train': 1.100398302078247} 08/30/2021 23:32:17 - INFO - __main__ - Step 57436: {'lr': 0.0003459894484365568, 'samples': 11027712, 'steps': 57435, 'loss/train': 0.6147298812866211} 08/30/2021 23:32:18 - INFO - __main__ - Step 57437: {'lr': 0.0003459845484291185, 'samples': 11027904, 'steps': 57436, 'loss/train': 1.4119763374328613} 08/30/2021 23:32:19 - INFO - __main__ - Step 57438: {'lr': 0.00034597964837843097, 'samples': 11028096, 'steps': 57437, 'loss/train': 0.039573926478624344} 08/30/2021 23:32:20 - INFO - __main__ - Step 57439: {'lr': 0.00034597474828449646, 'samples': 11028288, 'steps': 57438, 'loss/train': 1.083383321762085} 08/30/2021 23:32:20 - INFO - __main__ - Step 57440: {'lr': 0.00034596984814731736, 'samples': 11028480, 'steps': 57439, 'loss/train': 1.9350773096084595} 08/30/2021 23:32:20 - INFO - __main__ - Step 57441: {'lr': 0.0003459649479668956, 'samples': 11028672, 'steps': 57440, 'loss/train': 0.753420889377594} 08/30/2021 23:32:21 - INFO - __main__ - Step 57442: {'lr': 0.00034596004774323355, 'samples': 11028864, 'steps': 57441, 'loss/train': 1.6271330118179321} 08/30/2021 23:32:21 - INFO - __main__ - Step 57443: {'lr': 0.0003459551474763334, 'samples': 11029056, 'steps': 57442, 'loss/train': 1.282515048980713} 08/30/2021 23:32:24 - INFO - __main__ - Step 57444: {'lr': 0.00034595024716619726, 'samples': 11029248, 'steps': 57443, 'loss/train': 1.2012004852294922} 08/30/2021 23:32:24 - INFO - __main__ - Step 57445: {'lr': 0.0003459453468128276, 'samples': 11029440, 'steps': 57444, 'loss/train': 1.1732220649719238} 08/30/2021 23:32:24 - INFO - __main__ - Step 57446: {'lr': 0.0003459404464162263, 'samples': 11029632, 'steps': 57445, 'loss/train': 1.3930153846740723} 08/30/2021 23:32:25 - INFO - __main__ - Step 57447: {'lr': 0.0003459355459763957, 'samples': 11029824, 'steps': 57446, 'loss/train': 1.8122808933258057} 08/30/2021 23:32:25 - INFO - __main__ - Step 57448: {'lr': 0.0003459306454933381, 'samples': 11030016, 'steps': 57447, 'loss/train': 0.04777875915169716} 08/30/2021 23:32:25 - INFO - __main__ - Step 57449: {'lr': 0.0003459257449670555, 'samples': 11030208, 'steps': 57448, 'loss/train': 1.219847559928894} 08/30/2021 23:32:27 - INFO - __main__ - Step 57450: {'lr': 0.0003459208443975504, 'samples': 11030400, 'steps': 57449, 'loss/train': 1.7973581552505493} 08/30/2021 23:32:27 - INFO - __main__ - Step 57451: {'lr': 0.00034591594378482484, 'samples': 11030592, 'steps': 57450, 'loss/train': 1.3826237916946411} 08/30/2021 23:32:28 - INFO - __main__ - Step 57452: {'lr': 0.00034591104312888096, 'samples': 11030784, 'steps': 57451, 'loss/train': 1.0369007587432861} 08/30/2021 23:32:28 - INFO - __main__ - Step 57453: {'lr': 0.00034590614242972106, 'samples': 11030976, 'steps': 57452, 'loss/train': 1.347379207611084} 08/30/2021 23:32:28 - INFO - __main__ - Step 57454: {'lr': 0.00034590124168734735, 'samples': 11031168, 'steps': 57453, 'loss/train': 1.9416102170944214} 08/30/2021 23:32:30 - INFO - __main__ - Step 57455: {'lr': 0.00034589634090176195, 'samples': 11031360, 'steps': 57454, 'loss/train': 0.7941985130310059} 08/30/2021 23:32:30 - INFO - __main__ - Step 57456: {'lr': 0.0003458914400729672, 'samples': 11031552, 'steps': 57455, 'loss/train': 2.0067849159240723} 08/30/2021 23:32:31 - INFO - __main__ - Step 57457: {'lr': 0.00034588653920096524, 'samples': 11031744, 'steps': 57456, 'loss/train': 0.9747812151908875} 08/30/2021 23:32:31 - INFO - __main__ - Step 57458: {'lr': 0.00034588163828575837, 'samples': 11031936, 'steps': 57457, 'loss/train': 0.9822937250137329} 08/30/2021 23:32:31 - INFO - __main__ - Step 57459: {'lr': 0.0003458767373273486, 'samples': 11032128, 'steps': 57458, 'loss/train': 1.1482160091400146} 08/30/2021 23:32:32 - INFO - __main__ - Step 57460: {'lr': 0.00034587183632573825, 'samples': 11032320, 'steps': 57459, 'loss/train': 1.1093323230743408} 08/30/2021 23:32:33 - INFO - __main__ - Step 57461: {'lr': 0.00034586693528092954, 'samples': 11032512, 'steps': 57460, 'loss/train': 1.3924261331558228} 08/30/2021 23:32:34 - INFO - __main__ - Step 57462: {'lr': 0.0003458620341929247, 'samples': 11032704, 'steps': 57461, 'loss/train': 1.6451566219329834} 08/30/2021 23:32:34 - INFO - __main__ - Step 57463: {'lr': 0.0003458571330617259, 'samples': 11032896, 'steps': 57462, 'loss/train': 1.2803077697753906} 08/30/2021 23:32:34 - INFO - __main__ - Step 57464: {'lr': 0.00034585223188733535, 'samples': 11033088, 'steps': 57463, 'loss/train': 1.0794323682785034} 08/30/2021 23:32:35 - INFO - __main__ - Step 57465: {'lr': 0.0003458473306697553, 'samples': 11033280, 'steps': 57464, 'loss/train': 1.2126712799072266} 08/30/2021 23:32:36 - INFO - __main__ - Step 57466: {'lr': 0.0003458424294089879, 'samples': 11033472, 'steps': 57465, 'loss/train': 1.098444938659668} 08/30/2021 23:32:37 - INFO - __main__ - Step 57467: {'lr': 0.00034583752810503533, 'samples': 11033664, 'steps': 57466, 'loss/train': 1.3321839570999146} 08/30/2021 23:32:37 - INFO - __main__ - Step 57468: {'lr': 0.0003458326267578999, 'samples': 11033856, 'steps': 57467, 'loss/train': 0.8548885583877563} 08/30/2021 23:32:38 - INFO - __main__ - Step 57469: {'lr': 0.0003458277253675837, 'samples': 11034048, 'steps': 57468, 'loss/train': 1.1701687574386597} 08/30/2021 23:32:38 - INFO - __main__ - Step 57470: {'lr': 0.0003458228239340891, 'samples': 11034240, 'steps': 57469, 'loss/train': 1.7661478519439697} 08/30/2021 23:32:39 - INFO - __main__ - Step 57471: {'lr': 0.0003458179224574182, 'samples': 11034432, 'steps': 57470, 'loss/train': 1.9364041090011597} 08/30/2021 23:32:40 - INFO - __main__ - Step 57472: {'lr': 0.00034581302093757317, 'samples': 11034624, 'steps': 57471, 'loss/train': 0.749711811542511} 08/30/2021 23:32:40 - INFO - __main__ - Step 57473: {'lr': 0.0003458081193745563, 'samples': 11034816, 'steps': 57472, 'loss/train': 0.73874431848526} 08/30/2021 23:32:41 - INFO - __main__ - Step 57474: {'lr': 0.00034580321776836974, 'samples': 11035008, 'steps': 57473, 'loss/train': 1.2635341882705688} 08/30/2021 23:32:41 - INFO - __main__ - Step 57475: {'lr': 0.0003457983161190158, 'samples': 11035200, 'steps': 57474, 'loss/train': 1.393290400505066} 08/30/2021 23:32:43 - INFO - __main__ - Step 57476: {'lr': 0.00034579341442649654, 'samples': 11035392, 'steps': 57475, 'loss/train': 1.0002593994140625} 08/30/2021 23:32:43 - INFO - __main__ - Step 57477: {'lr': 0.00034578851269081426, 'samples': 11035584, 'steps': 57476, 'loss/train': 0.9912737607955933} 08/30/2021 23:32:44 - INFO - __main__ - Step 57478: {'lr': 0.0003457836109119712, 'samples': 11035776, 'steps': 57477, 'loss/train': 1.3044018745422363} 08/30/2021 23:32:44 - INFO - __main__ - Step 57479: {'lr': 0.0003457787090899695, 'samples': 11035968, 'steps': 57478, 'loss/train': 0.8418999910354614} 08/30/2021 23:32:44 - INFO - __main__ - Step 57480: {'lr': 0.00034577380722481137, 'samples': 11036160, 'steps': 57479, 'loss/train': 2.2630624771118164} 08/30/2021 23:32:45 - INFO - __main__ - Step 57481: {'lr': 0.00034576890531649905, 'samples': 11036352, 'steps': 57480, 'loss/train': 1.2399497032165527} 08/30/2021 23:32:46 - INFO - __main__ - Step 57482: {'lr': 0.0003457640033650348, 'samples': 11036544, 'steps': 57481, 'loss/train': 1.7686729431152344} 08/30/2021 23:32:47 - INFO - __main__ - Step 57483: {'lr': 0.00034575910137042064, 'samples': 11036736, 'steps': 57482, 'loss/train': 1.6249058246612549} 08/30/2021 23:32:47 - INFO - __main__ - Step 57484: {'lr': 0.000345754199332659, 'samples': 11036928, 'steps': 57483, 'loss/train': 1.4051047563552856} 08/30/2021 23:32:47 - INFO - __main__ - Step 57485: {'lr': 0.00034574929725175203, 'samples': 11037120, 'steps': 57484, 'loss/train': 1.0107982158660889} 08/30/2021 23:32:48 - INFO - __main__ - Step 57486: {'lr': 0.0003457443951277018, 'samples': 11037312, 'steps': 57485, 'loss/train': 1.4943259954452515} 08/30/2021 23:32:49 - INFO - __main__ - Step 57487: {'lr': 0.00034573949296051065, 'samples': 11037504, 'steps': 57486, 'loss/train': 1.3099762201309204} 08/30/2021 23:32:50 - INFO - __main__ - Step 57488: {'lr': 0.0003457345907501808, 'samples': 11037696, 'steps': 57487, 'loss/train': 2.354846239089966} 08/30/2021 23:32:50 - INFO - __main__ - Step 57489: {'lr': 0.0003457296884967144, 'samples': 11037888, 'steps': 57488, 'loss/train': 0.8203210234642029} 08/30/2021 23:32:50 - INFO - __main__ - Step 57490: {'lr': 0.0003457247862001137, 'samples': 11038080, 'steps': 57489, 'loss/train': 1.1483343839645386} 08/30/2021 23:32:51 - INFO - __main__ - Step 57491: {'lr': 0.0003457198838603809, 'samples': 11038272, 'steps': 57490, 'loss/train': 0.8238843083381653} 08/30/2021 23:32:51 - INFO - __main__ - Step 57492: {'lr': 0.0003457149814775182, 'samples': 11038464, 'steps': 57491, 'loss/train': 1.485921025276184} 08/30/2021 23:32:53 - INFO - __main__ - Step 57493: {'lr': 0.00034571007905152774, 'samples': 11038656, 'steps': 57492, 'loss/train': 0.8518865704536438} 08/30/2021 23:32:53 - INFO - __main__ - Step 57494: {'lr': 0.00034570517658241186, 'samples': 11038848, 'steps': 57493, 'loss/train': 1.4750962257385254} 08/30/2021 23:32:53 - INFO - __main__ - Step 57495: {'lr': 0.00034570027407017264, 'samples': 11039040, 'steps': 57494, 'loss/train': 1.601528286933899} 08/30/2021 23:32:54 - INFO - __main__ - Step 57496: {'lr': 0.0003456953715148124, 'samples': 11039232, 'steps': 57495, 'loss/train': 1.5654919147491455} 08/30/2021 23:32:54 - INFO - __main__ - Step 57497: {'lr': 0.0003456904689163333, 'samples': 11039424, 'steps': 57496, 'loss/train': 1.1852360963821411} 08/30/2021 23:32:56 - INFO - __main__ - Step 57498: {'lr': 0.0003456855662747376, 'samples': 11039616, 'steps': 57497, 'loss/train': 1.0496329069137573} 08/30/2021 23:32:56 - INFO - __main__ - Step 57499: {'lr': 0.0003456806635900274, 'samples': 11039808, 'steps': 57498, 'loss/train': 1.67026948928833} 08/30/2021 23:32:57 - INFO - __main__ - Step 57500: {'lr': 0.00034567576086220493, 'samples': 11040000, 'steps': 57499, 'loss/train': 1.298622727394104} 08/30/2021 23:32:57 - INFO - __main__ - Step 57501: {'lr': 0.0003456708580912725, 'samples': 11040192, 'steps': 57500, 'loss/train': 1.5156292915344238} 08/30/2021 23:32:57 - INFO - __main__ - Step 57502: {'lr': 0.0003456659552772322, 'samples': 11040384, 'steps': 57501, 'loss/train': 1.4259544610977173} 08/30/2021 23:32:59 - INFO - __main__ - Step 57503: {'lr': 0.0003456610524200863, 'samples': 11040576, 'steps': 57502, 'loss/train': 1.458237886428833} 08/30/2021 23:33:00 - INFO - __main__ - Step 57504: {'lr': 0.00034565614951983706, 'samples': 11040768, 'steps': 57503, 'loss/train': 0.942168653011322} 08/30/2021 23:33:00 - INFO - __main__ - Step 57505: {'lr': 0.00034565124657648665, 'samples': 11040960, 'steps': 57504, 'loss/train': 1.7458330392837524} 08/30/2021 23:33:00 - INFO - __main__ - Step 57506: {'lr': 0.0003456463435900372, 'samples': 11041152, 'steps': 57505, 'loss/train': 0.35200047492980957} 08/30/2021 23:33:01 - INFO - __main__ - Step 57507: {'lr': 0.0003456414405604911, 'samples': 11041344, 'steps': 57506, 'loss/train': 1.487480640411377} 08/30/2021 23:33:02 - INFO - __main__ - Step 57508: {'lr': 0.0003456365374878503, 'samples': 11041536, 'steps': 57507, 'loss/train': 1.1866015195846558} 08/30/2021 23:33:03 - INFO - __main__ - Step 57509: {'lr': 0.00034563163437211717, 'samples': 11041728, 'steps': 57508, 'loss/train': 1.4239046573638916} 08/30/2021 23:33:03 - INFO - __main__ - Step 57510: {'lr': 0.000345626731213294, 'samples': 11041920, 'steps': 57509, 'loss/train': 1.2445242404937744} 08/30/2021 23:33:03 - INFO - __main__ - Step 57511: {'lr': 0.00034562182801138277, 'samples': 11042112, 'steps': 57510, 'loss/train': 1.2954127788543701} 08/30/2021 23:33:04 - INFO - __main__ - Step 57512: {'lr': 0.00034561692476638595, 'samples': 11042304, 'steps': 57511, 'loss/train': 1.1406797170639038} 08/30/2021 23:33:05 - INFO - __main__ - Step 57513: {'lr': 0.00034561202147830554, 'samples': 11042496, 'steps': 57512, 'loss/train': 1.5891255140304565} 08/30/2021 23:33:06 - INFO - __main__ - Step 57514: {'lr': 0.00034560711814714387, 'samples': 11042688, 'steps': 57513, 'loss/train': 0.9233707785606384} 08/30/2021 23:33:06 - INFO - __main__ - Step 57515: {'lr': 0.0003456022147729031, 'samples': 11042880, 'steps': 57514, 'loss/train': 1.3124396800994873} 08/30/2021 23:33:06 - INFO - __main__ - Step 57516: {'lr': 0.00034559731135558536, 'samples': 11043072, 'steps': 57515, 'loss/train': 0.9970801472663879} 08/30/2021 23:33:07 - INFO - __main__ - Step 57517: {'lr': 0.000345592407895193, 'samples': 11043264, 'steps': 57516, 'loss/train': 1.049660563468933} 08/30/2021 23:33:08 - INFO - __main__ - Step 57518: {'lr': 0.00034558750439172826, 'samples': 11043456, 'steps': 57517, 'loss/train': 0.8449531197547913} 08/30/2021 23:33:09 - INFO - __main__ - Step 57519: {'lr': 0.0003455826008451932, 'samples': 11043648, 'steps': 57518, 'loss/train': 1.3629741668701172} 08/30/2021 23:33:09 - INFO - __main__ - Step 57520: {'lr': 0.00034557769725559014, 'samples': 11043840, 'steps': 57519, 'loss/train': 1.1600923538208008} 08/30/2021 23:33:09 - INFO - __main__ - Step 57521: {'lr': 0.00034557279362292117, 'samples': 11044032, 'steps': 57520, 'loss/train': 0.5266602635383606} 08/30/2021 23:33:10 - INFO - __main__ - Step 57522: {'lr': 0.00034556788994718855, 'samples': 11044224, 'steps': 57521, 'loss/train': 1.2160521745681763} 08/30/2021 23:33:10 - INFO - __main__ - Step 57523: {'lr': 0.00034556298622839463, 'samples': 11044416, 'steps': 57522, 'loss/train': 1.2337080240249634} 08/30/2021 23:33:12 - INFO - __main__ - Step 57524: {'lr': 0.0003455580824665414, 'samples': 11044608, 'steps': 57523, 'loss/train': 1.113364338874817} 08/30/2021 23:33:12 - INFO - __main__ - Step 57525: {'lr': 0.0003455531786616313, 'samples': 11044800, 'steps': 57524, 'loss/train': 1.587162733078003} 08/30/2021 23:33:12 - INFO - __main__ - Step 57526: {'lr': 0.0003455482748136663, 'samples': 11044992, 'steps': 57525, 'loss/train': 0.8753715753555298} 08/30/2021 23:33:13 - INFO - __main__ - Step 57527: {'lr': 0.00034554337092264874, 'samples': 11045184, 'steps': 57526, 'loss/train': 1.1568371057510376} 08/30/2021 23:33:13 - INFO - __main__ - Step 57528: {'lr': 0.00034553846698858083, 'samples': 11045376, 'steps': 57527, 'loss/train': 2.292367935180664} 08/30/2021 23:33:15 - INFO - __main__ - Step 57529: {'lr': 0.00034553356301146473, 'samples': 11045568, 'steps': 57528, 'loss/train': 1.4185253381729126} 08/30/2021 23:33:15 - INFO - __main__ - Step 57530: {'lr': 0.0003455286589913027, 'samples': 11045760, 'steps': 57529, 'loss/train': 1.5858784914016724} 08/30/2021 23:33:15 - INFO - __main__ - Step 57531: {'lr': 0.0003455237549280969, 'samples': 11045952, 'steps': 57530, 'loss/train': 0.8337659239768982} 08/30/2021 23:33:16 - INFO - __main__ - Step 57532: {'lr': 0.0003455188508218496, 'samples': 11046144, 'steps': 57531, 'loss/train': 1.371749758720398} 08/30/2021 23:33:16 - INFO - __main__ - Step 57533: {'lr': 0.000345513946672563, 'samples': 11046336, 'steps': 57532, 'loss/train': 1.3756765127182007} 08/30/2021 23:33:18 - INFO - __main__ - Step 57534: {'lr': 0.0003455090424802393, 'samples': 11046528, 'steps': 57533, 'loss/train': 1.0895546674728394} 08/30/2021 23:33:18 - INFO - __main__ - Step 57535: {'lr': 0.00034550413824488066, 'samples': 11046720, 'steps': 57534, 'loss/train': 1.26651930809021} 08/30/2021 23:33:19 - INFO - __main__ - Step 57536: {'lr': 0.0003454992339664893, 'samples': 11046912, 'steps': 57535, 'loss/train': 1.100299596786499} 08/30/2021 23:33:19 - INFO - __main__ - Step 57537: {'lr': 0.00034549432964506755, 'samples': 11047104, 'steps': 57536, 'loss/train': 1.2957290410995483} 08/30/2021 23:33:19 - INFO - __main__ - Step 57538: {'lr': 0.0003454894252806175, 'samples': 11047296, 'steps': 57537, 'loss/train': 0.0267304889857769} 08/30/2021 23:33:20 - INFO - __main__ - Step 57539: {'lr': 0.00034548452087314135, 'samples': 11047488, 'steps': 57538, 'loss/train': 0.022666100412607193} 08/30/2021 23:33:22 - INFO - __main__ - Step 57540: {'lr': 0.0003454796164226414, 'samples': 11047680, 'steps': 57539, 'loss/train': 1.9569488763809204} 08/30/2021 23:33:22 - INFO - __main__ - Step 57541: {'lr': 0.00034547471192911973, 'samples': 11047872, 'steps': 57540, 'loss/train': 1.228626012802124} 08/30/2021 23:33:22 - INFO - __main__ - Step 57542: {'lr': 0.0003454698073925787, 'samples': 11048064, 'steps': 57541, 'loss/train': 1.2397302389144897} 08/30/2021 23:33:23 - INFO - __main__ - Step 57543: {'lr': 0.00034546490281302033, 'samples': 11048256, 'steps': 57542, 'loss/train': 0.6691275835037231} 08/30/2021 23:33:23 - INFO - __main__ - Step 57544: {'lr': 0.000345459998190447, 'samples': 11048448, 'steps': 57543, 'loss/train': 1.49228036403656} 08/30/2021 23:33:25 - INFO - __main__ - Step 57545: {'lr': 0.000345455093524861, 'samples': 11048640, 'steps': 57544, 'loss/train': 1.1912755966186523} 08/30/2021 23:33:25 - INFO - __main__ - Step 57546: {'lr': 0.00034545018881626435, 'samples': 11048832, 'steps': 57545, 'loss/train': 1.4535815715789795} 08/30/2021 23:33:26 - INFO - __main__ - Step 57547: {'lr': 0.00034544528406465927, 'samples': 11049024, 'steps': 57546, 'loss/train': 1.5673638582229614} 08/30/2021 23:33:26 - INFO - __main__ - Step 57548: {'lr': 0.000345440379270048, 'samples': 11049216, 'steps': 57547, 'loss/train': 1.0576817989349365} 08/30/2021 23:33:26 - INFO - __main__ - Step 57549: {'lr': 0.0003454354744324328, 'samples': 11049408, 'steps': 57548, 'loss/train': 1.4908499717712402} 08/30/2021 23:33:27 - INFO - __main__ - Step 57550: {'lr': 0.00034543056955181584, 'samples': 11049600, 'steps': 57549, 'loss/train': 1.5017606019973755} 08/30/2021 23:33:28 - INFO - __main__ - Step 57551: {'lr': 0.0003454256646281993, 'samples': 11049792, 'steps': 57550, 'loss/train': 1.3556101322174072} 08/30/2021 23:33:29 - INFO - __main__ - Step 57552: {'lr': 0.0003454207596615855, 'samples': 11049984, 'steps': 57551, 'loss/train': 1.4647105932235718} 08/30/2021 23:33:29 - INFO - __main__ - Step 57553: {'lr': 0.00034541585465197653, 'samples': 11050176, 'steps': 57552, 'loss/train': 1.4885293245315552} 08/30/2021 23:33:29 - INFO - __main__ - Step 57554: {'lr': 0.0003454109495993747, 'samples': 11050368, 'steps': 57553, 'loss/train': 0.9432709217071533} 08/30/2021 23:33:30 - INFO - __main__ - Step 57555: {'lr': 0.0003454060445037821, 'samples': 11050560, 'steps': 57554, 'loss/train': 0.7419079542160034} 08/30/2021 23:33:32 - INFO - __main__ - Step 57556: {'lr': 0.0003454011393652011, 'samples': 11050752, 'steps': 57555, 'loss/train': 1.0104891061782837} 08/30/2021 23:33:32 - INFO - __main__ - Step 57557: {'lr': 0.0003453962341836337, 'samples': 11050944, 'steps': 57556, 'loss/train': 0.6945191621780396} 08/30/2021 23:33:33 - INFO - __main__ - Step 57558: {'lr': 0.0003453913289590823, 'samples': 11051136, 'steps': 57557, 'loss/train': 1.7103712558746338} 08/30/2021 23:33:33 - INFO - __main__ - Step 57559: {'lr': 0.00034538642369154907, 'samples': 11051328, 'steps': 57558, 'loss/train': 1.8439635038375854} 08/30/2021 23:33:33 - INFO - __main__ - Step 57560: {'lr': 0.00034538151838103614, 'samples': 11051520, 'steps': 57559, 'loss/train': 1.214728832244873} 08/30/2021 23:33:35 - INFO - __main__ - Step 57561: {'lr': 0.00034537661302754577, 'samples': 11051712, 'steps': 57560, 'loss/train': 1.7380664348602295} 08/30/2021 23:33:35 - INFO - __main__ - Step 57562: {'lr': 0.00034537170763108017, 'samples': 11051904, 'steps': 57561, 'loss/train': 0.4132211208343506} 08/30/2021 23:33:36 - INFO - __main__ - Step 57563: {'lr': 0.00034536680219164156, 'samples': 11052096, 'steps': 57562, 'loss/train': 1.7337266206741333} 08/30/2021 23:33:36 - INFO - __main__ - Step 57564: {'lr': 0.0003453618967092322, 'samples': 11052288, 'steps': 57563, 'loss/train': 0.9239173531532288} 08/30/2021 23:33:37 - INFO - __main__ - Step 57565: {'lr': 0.00034535699118385413, 'samples': 11052480, 'steps': 57564, 'loss/train': 0.8764766454696655} 08/30/2021 23:33:38 - INFO - __main__ - Step 57566: {'lr': 0.00034535208561550974, 'samples': 11052672, 'steps': 57565, 'loss/train': 1.3058198690414429} 08/30/2021 23:33:38 - INFO - __main__ - Step 57567: {'lr': 0.00034534718000420113, 'samples': 11052864, 'steps': 57566, 'loss/train': 1.596453309059143} 08/30/2021 23:33:39 - INFO - __main__ - Step 57568: {'lr': 0.0003453422743499306, 'samples': 11053056, 'steps': 57567, 'loss/train': 1.6370819807052612} 08/30/2021 23:33:39 - INFO - __main__ - Step 57569: {'lr': 0.00034533736865270025, 'samples': 11053248, 'steps': 57568, 'loss/train': 1.4883334636688232} 08/30/2021 23:33:39 - INFO - __main__ - Step 57570: {'lr': 0.0003453324629125124, 'samples': 11053440, 'steps': 57569, 'loss/train': 1.3380407094955444} 08/30/2021 23:33:41 - INFO - __main__ - Step 57571: {'lr': 0.00034532755712936926, 'samples': 11053632, 'steps': 57570, 'loss/train': 1.3347805738449097} 08/30/2021 23:33:42 - INFO - __main__ - Step 57572: {'lr': 0.0003453226513032729, 'samples': 11053824, 'steps': 57571, 'loss/train': 0.980475664138794} 08/30/2021 23:33:42 - INFO - __main__ - Step 57573: {'lr': 0.00034531774543422567, 'samples': 11054016, 'steps': 57572, 'loss/train': 1.2035059928894043} 08/30/2021 23:33:42 - INFO - __main__ - Step 57574: {'lr': 0.00034531283952222975, 'samples': 11054208, 'steps': 57573, 'loss/train': 1.177834153175354} 08/30/2021 23:33:43 - INFO - __main__ - Step 57575: {'lr': 0.00034530793356728727, 'samples': 11054400, 'steps': 57574, 'loss/train': 1.4501341581344604} 08/30/2021 23:33:44 - INFO - __main__ - Step 57576: {'lr': 0.0003453030275694006, 'samples': 11054592, 'steps': 57575, 'loss/train': 1.279768466949463} 08/30/2021 23:33:45 - INFO - __main__ - Step 57577: {'lr': 0.0003452981215285718, 'samples': 11054784, 'steps': 57576, 'loss/train': 1.2387789487838745} 08/30/2021 23:33:45 - INFO - __main__ - Step 57578: {'lr': 0.0003452932154448031, 'samples': 11054976, 'steps': 57577, 'loss/train': 1.4210563898086548} 08/30/2021 23:33:45 - INFO - __main__ - Step 57579: {'lr': 0.0003452883093180968, 'samples': 11055168, 'steps': 57578, 'loss/train': 1.2626224756240845} 08/30/2021 23:33:46 - INFO - __main__ - Step 57580: {'lr': 0.0003452834031484551, 'samples': 11055360, 'steps': 57579, 'loss/train': 0.8644973635673523} 08/30/2021 23:33:47 - INFO - __main__ - Step 57581: {'lr': 0.0003452784969358801, 'samples': 11055552, 'steps': 57580, 'loss/train': 1.5270440578460693} 08/30/2021 23:33:48 - INFO - __main__ - Step 57582: {'lr': 0.0003452735906803741, 'samples': 11055744, 'steps': 57581, 'loss/train': 1.7835882902145386} 08/30/2021 23:33:48 - INFO - __main__ - Step 57583: {'lr': 0.0003452686843819393, 'samples': 11055936, 'steps': 57582, 'loss/train': 1.4282037019729614} 08/30/2021 23:33:49 - INFO - __main__ - Step 57584: {'lr': 0.0003452637780405778, 'samples': 11056128, 'steps': 57583, 'loss/train': 1.4931445121765137} 08/30/2021 23:33:49 - INFO - __main__ - Step 57585: {'lr': 0.000345258871656292, 'samples': 11056320, 'steps': 57584, 'loss/train': 1.939090371131897} 08/30/2021 23:33:49 - INFO - __main__ - Step 57586: {'lr': 0.0003452539652290841, 'samples': 11056512, 'steps': 57585, 'loss/train': 1.1673301458358765} 08/30/2021 23:33:51 - INFO - __main__ - Step 57587: {'lr': 0.00034524905875895614, 'samples': 11056704, 'steps': 57586, 'loss/train': 1.9163360595703125} 08/30/2021 23:33:51 - INFO - __main__ - Step 57588: {'lr': 0.00034524415224591046, 'samples': 11056896, 'steps': 57587, 'loss/train': 1.6837005615234375} 08/30/2021 23:33:52 - INFO - __main__ - Step 57589: {'lr': 0.00034523924568994913, 'samples': 11057088, 'steps': 57588, 'loss/train': 1.4500340223312378} 08/30/2021 23:33:52 - INFO - __main__ - Step 57590: {'lr': 0.00034523433909107454, 'samples': 11057280, 'steps': 57589, 'loss/train': 1.8550750017166138} 08/30/2021 23:33:52 - INFO - __main__ - Step 57591: {'lr': 0.00034522943244928885, 'samples': 11057472, 'steps': 57590, 'loss/train': 1.1731996536254883} 08/30/2021 23:33:54 - INFO - __main__ - Step 57592: {'lr': 0.0003452245257645943, 'samples': 11057664, 'steps': 57591, 'loss/train': 0.8706366419792175} 08/30/2021 23:33:54 - INFO - __main__ - Step 57593: {'lr': 0.00034521961903699296, 'samples': 11057856, 'steps': 57592, 'loss/train': 1.7030678987503052} 08/30/2021 23:33:55 - INFO - __main__ - Step 57594: {'lr': 0.00034521471226648716, 'samples': 11058048, 'steps': 57593, 'loss/train': 1.2411733865737915} 08/30/2021 23:33:55 - INFO - __main__ - Step 57595: {'lr': 0.000345209805453079, 'samples': 11058240, 'steps': 57594, 'loss/train': 1.1184347867965698} 08/30/2021 23:33:55 - INFO - __main__ - Step 57596: {'lr': 0.00034520489859677083, 'samples': 11058432, 'steps': 57595, 'loss/train': 1.0869066715240479} 08/30/2021 23:33:57 - INFO - __main__ - Step 57597: {'lr': 0.0003451999916975648, 'samples': 11058624, 'steps': 57596, 'loss/train': 1.3778116703033447} 08/30/2021 23:33:58 - INFO - __main__ - Step 57598: {'lr': 0.00034519508475546314, 'samples': 11058816, 'steps': 57597, 'loss/train': 2.072032928466797} 08/30/2021 23:33:58 - INFO - __main__ - Step 57599: {'lr': 0.0003451901777704681, 'samples': 11059008, 'steps': 57598, 'loss/train': 0.8535974025726318} 08/30/2021 23:33:58 - INFO - __main__ - Step 57600: {'lr': 0.00034518527074258175, 'samples': 11059200, 'steps': 57599, 'loss/train': 1.1968071460723877} 08/30/2021 23:33:59 - INFO - __main__ - Step 57601: {'lr': 0.00034518036367180637, 'samples': 11059392, 'steps': 57600, 'loss/train': 0.21868842840194702} 08/30/2021 23:34:00 - INFO - __main__ - Step 57602: {'lr': 0.00034517545655814424, 'samples': 11059584, 'steps': 57601, 'loss/train': 1.3872748613357544} 08/30/2021 23:34:01 - INFO - __main__ - Step 57603: {'lr': 0.0003451705494015975, 'samples': 11059776, 'steps': 57602, 'loss/train': 1.2841793298721313} 08/30/2021 23:34:01 - INFO - __main__ - Step 57604: {'lr': 0.0003451656422021684, 'samples': 11059968, 'steps': 57603, 'loss/train': 1.5994257926940918} 08/30/2021 23:34:01 - INFO - __main__ - Step 57605: {'lr': 0.0003451607349598591, 'samples': 11060160, 'steps': 57604, 'loss/train': 1.85781991481781} 08/30/2021 23:34:02 - INFO - __main__ - Step 57606: {'lr': 0.0003451558276746719, 'samples': 11060352, 'steps': 57605, 'loss/train': 1.6756277084350586} 08/30/2021 23:34:03 - INFO - __main__ - Step 57607: {'lr': 0.0003451509203466089, 'samples': 11060544, 'steps': 57606, 'loss/train': 1.3493287563323975} 08/30/2021 23:34:04 - INFO - __main__ - Step 57608: {'lr': 0.00034514601297567235, 'samples': 11060736, 'steps': 57607, 'loss/train': 1.264882206916809} 08/30/2021 23:34:04 - INFO - __main__ - Step 57609: {'lr': 0.00034514110556186446, 'samples': 11060928, 'steps': 57608, 'loss/train': 1.5122637748718262} 08/30/2021 23:34:04 - INFO - __main__ - Step 57610: {'lr': 0.0003451361981051875, 'samples': 11061120, 'steps': 57609, 'loss/train': 0.8713572025299072} 08/30/2021 23:34:05 - INFO - __main__ - Step 57611: {'lr': 0.00034513129060564365, 'samples': 11061312, 'steps': 57610, 'loss/train': 1.1754547357559204} 08/30/2021 23:34:05 - INFO - __main__ - Step 57612: {'lr': 0.00034512638306323506, 'samples': 11061504, 'steps': 57611, 'loss/train': 1.165854573249817} 08/30/2021 23:34:07 - INFO - __main__ - Step 57613: {'lr': 0.000345121475477964, 'samples': 11061696, 'steps': 57612, 'loss/train': 1.0446141958236694} 08/30/2021 23:34:08 - INFO - __main__ - Step 57614: {'lr': 0.0003451165678498327, 'samples': 11061888, 'steps': 57613, 'loss/train': 1.2917474508285522} 08/30/2021 23:34:08 - INFO - __main__ - Step 57615: {'lr': 0.00034511166017884334, 'samples': 11062080, 'steps': 57614, 'loss/train': 0.7459553480148315} 08/30/2021 23:34:08 - INFO - __main__ - Step 57616: {'lr': 0.0003451067524649981, 'samples': 11062272, 'steps': 57615, 'loss/train': 0.8307577967643738} 08/30/2021 23:34:09 - INFO - __main__ - Step 57617: {'lr': 0.00034510184470829924, 'samples': 11062464, 'steps': 57616, 'loss/train': 0.6022247672080994} 08/30/2021 23:34:10 - INFO - __main__ - Step 57618: {'lr': 0.000345096936908749, 'samples': 11062656, 'steps': 57617, 'loss/train': 1.2412227392196655} 08/30/2021 23:34:11 - INFO - __main__ - Step 57619: {'lr': 0.0003450920290663495, 'samples': 11062848, 'steps': 57618, 'loss/train': 0.7889207601547241} 08/30/2021 23:34:11 - INFO - __main__ - Step 57620: {'lr': 0.000345087121181103, 'samples': 11063040, 'steps': 57619, 'loss/train': 1.3664442300796509} 08/30/2021 23:34:11 - INFO - __main__ - Step 57621: {'lr': 0.0003450822132530117, 'samples': 11063232, 'steps': 57620, 'loss/train': 0.8068606853485107} 08/30/2021 23:34:12 - INFO - __main__ - Step 57622: {'lr': 0.0003450773052820779, 'samples': 11063424, 'steps': 57621, 'loss/train': 1.3867192268371582} 08/30/2021 23:34:13 - INFO - __main__ - Step 57623: {'lr': 0.0003450723972683036, 'samples': 11063616, 'steps': 57622, 'loss/train': 1.0013068914413452} 08/30/2021 23:34:14 - INFO - __main__ - Step 57624: {'lr': 0.00034506748921169124, 'samples': 11063808, 'steps': 57623, 'loss/train': 0.9682133793830872} 08/30/2021 23:34:14 - INFO - __main__ - Step 57625: {'lr': 0.00034506258111224294, 'samples': 11064000, 'steps': 57624, 'loss/train': 1.3219531774520874} 08/30/2021 23:34:15 - INFO - __main__ - Step 57626: {'lr': 0.00034505767296996086, 'samples': 11064192, 'steps': 57625, 'loss/train': 1.5804495811462402} 08/30/2021 23:34:15 - INFO - __main__ - Step 57627: {'lr': 0.0003450527647848473, 'samples': 11064384, 'steps': 57626, 'loss/train': 1.340441346168518} 08/30/2021 23:34:16 - INFO - __main__ - Step 57628: {'lr': 0.0003450478565569044, 'samples': 11064576, 'steps': 57627, 'loss/train': 0.831775426864624} 08/30/2021 23:34:17 - INFO - __main__ - Step 57629: {'lr': 0.0003450429482861344, 'samples': 11064768, 'steps': 57628, 'loss/train': 1.503279685974121} 08/30/2021 23:34:17 - INFO - __main__ - Step 57630: {'lr': 0.0003450380399725396, 'samples': 11064960, 'steps': 57629, 'loss/train': 1.498227596282959} 08/30/2021 23:34:18 - INFO - __main__ - Step 57631: {'lr': 0.000345033131616122, 'samples': 11065152, 'steps': 57630, 'loss/train': 1.1055716276168823} 08/30/2021 23:34:18 - INFO - __main__ - Step 57632: {'lr': 0.000345028223216884, 'samples': 11065344, 'steps': 57631, 'loss/train': 1.2551686763763428} 08/30/2021 23:34:19 - INFO - __main__ - Step 57633: {'lr': 0.0003450233147748278, 'samples': 11065536, 'steps': 57632, 'loss/train': 1.4205131530761719} 08/30/2021 23:34:20 - INFO - __main__ - Step 57634: {'lr': 0.00034501840628995545, 'samples': 11065728, 'steps': 57633, 'loss/train': 1.5272709131240845} 08/30/2021 23:34:20 - INFO - __main__ - Step 57635: {'lr': 0.0003450134977622693, 'samples': 11065920, 'steps': 57634, 'loss/train': 0.944395899772644} 08/30/2021 23:34:21 - INFO - __main__ - Step 57636: {'lr': 0.0003450085891917716, 'samples': 11066112, 'steps': 57635, 'loss/train': 1.1037479639053345} 08/30/2021 23:34:21 - INFO - __main__ - Step 57637: {'lr': 0.00034500368057846444, 'samples': 11066304, 'steps': 57636, 'loss/train': 1.895972728729248} 08/30/2021 23:34:22 - INFO - __main__ - Step 57638: {'lr': 0.00034499877192235005, 'samples': 11066496, 'steps': 57637, 'loss/train': 0.9974783062934875} 08/30/2021 23:34:23 - INFO - __main__ - Step 57639: {'lr': 0.00034499386322343087, 'samples': 11066688, 'steps': 57638, 'loss/train': 1.1062231063842773} 08/30/2021 23:34:23 - INFO - __main__ - Step 57640: {'lr': 0.00034498895448170874, 'samples': 11066880, 'steps': 57639, 'loss/train': 1.6630113124847412} 08/30/2021 23:34:23 - INFO - __main__ - Step 57641: {'lr': 0.0003449840456971861, 'samples': 11067072, 'steps': 57640, 'loss/train': 0.5174520015716553} 08/30/2021 23:34:24 - INFO - __main__ - Step 57642: {'lr': 0.0003449791368698651, 'samples': 11067264, 'steps': 57641, 'loss/train': 1.4498767852783203} 08/30/2021 23:34:26 - INFO - __main__ - Step 57643: {'lr': 0.000344974227999748, 'samples': 11067456, 'steps': 57642, 'loss/train': 0.5241720080375671} 08/30/2021 23:34:26 - INFO - __main__ - Step 57644: {'lr': 0.0003449693190868369, 'samples': 11067648, 'steps': 57643, 'loss/train': 0.9886839389801025} 08/30/2021 23:34:26 - INFO - __main__ - Step 57645: {'lr': 0.0003449644101311341, 'samples': 11067840, 'steps': 57644, 'loss/train': 1.1314173936843872} 08/30/2021 23:34:27 - INFO - __main__ - Step 57646: {'lr': 0.00034495950113264194, 'samples': 11068032, 'steps': 57645, 'loss/train': 1.3463867902755737} 08/30/2021 23:34:27 - INFO - __main__ - Step 57647: {'lr': 0.0003449545920913624, 'samples': 11068224, 'steps': 57646, 'loss/train': 0.8864731788635254} 08/30/2021 23:34:27 - INFO - __main__ - Step 57648: {'lr': 0.0003449496830072978, 'samples': 11068416, 'steps': 57647, 'loss/train': 0.8631796836853027} 08/30/2021 23:34:29 - INFO - __main__ - Step 57649: {'lr': 0.0003449447738804503, 'samples': 11068608, 'steps': 57648, 'loss/train': 0.43476948142051697} 08/30/2021 23:34:30 - INFO - __main__ - Step 57650: {'lr': 0.00034493986471082215, 'samples': 11068800, 'steps': 57649, 'loss/train': 1.7842961549758911} 08/30/2021 23:34:30 - INFO - __main__ - Step 57651: {'lr': 0.0003449349554984156, 'samples': 11068992, 'steps': 57650, 'loss/train': 1.1075594425201416} 08/30/2021 23:34:30 - INFO - __main__ - Step 57652: {'lr': 0.0003449300462432328, 'samples': 11069184, 'steps': 57651, 'loss/train': 1.211912751197815} 08/30/2021 23:34:31 - INFO - __main__ - Step 57653: {'lr': 0.0003449251369452761, 'samples': 11069376, 'steps': 57652, 'loss/train': 1.6299463510513306} 08/30/2021 23:34:32 - INFO - __main__ - Step 57654: {'lr': 0.00034492022760454743, 'samples': 11069568, 'steps': 57653, 'loss/train': 1.9488661289215088} 08/30/2021 23:34:33 - INFO - __main__ - Step 57655: {'lr': 0.00034491531822104923, 'samples': 11069760, 'steps': 57654, 'loss/train': 1.3055777549743652} 08/30/2021 23:34:33 - INFO - __main__ - Step 57656: {'lr': 0.00034491040879478364, 'samples': 11069952, 'steps': 57655, 'loss/train': 2.427436113357544} 08/30/2021 23:34:33 - INFO - __main__ - Step 57657: {'lr': 0.0003449054993257529, 'samples': 11070144, 'steps': 57656, 'loss/train': 1.5588815212249756} 08/30/2021 23:34:34 - INFO - __main__ - Step 57658: {'lr': 0.0003449005898139592, 'samples': 11070336, 'steps': 57657, 'loss/train': 1.192208170890808} 08/30/2021 23:34:34 - INFO - __main__ - Step 57659: {'lr': 0.0003448956802594048, 'samples': 11070528, 'steps': 57658, 'loss/train': 0.7147905826568604} 08/30/2021 23:34:35 - INFO - __main__ - Step 57660: {'lr': 0.00034489077066209185, 'samples': 11070720, 'steps': 57659, 'loss/train': 1.7572073936462402} 08/30/2021 23:34:36 - INFO - __main__ - Step 57661: {'lr': 0.0003448858610220226, 'samples': 11070912, 'steps': 57660, 'loss/train': 1.4784742593765259} 08/30/2021 23:34:36 - INFO - __main__ - Step 57662: {'lr': 0.00034488095133919914, 'samples': 11071104, 'steps': 57661, 'loss/train': 1.6818466186523438} 08/30/2021 23:34:37 - INFO - __main__ - Step 57663: {'lr': 0.0003448760416136239, 'samples': 11071296, 'steps': 57662, 'loss/train': 1.5901094675064087} 08/30/2021 23:34:37 - INFO - __main__ - Step 57664: {'lr': 0.00034487113184529896, 'samples': 11071488, 'steps': 57663, 'loss/train': 1.5783939361572266} 08/30/2021 23:34:39 - INFO - __main__ - Step 57665: {'lr': 0.0003448662220342265, 'samples': 11071680, 'steps': 57664, 'loss/train': 2.082850217819214} 08/30/2021 23:34:39 - INFO - __main__ - Step 57666: {'lr': 0.0003448613121804088, 'samples': 11071872, 'steps': 57665, 'loss/train': 1.508696436882019} 08/30/2021 23:34:40 - INFO - __main__ - Step 57667: {'lr': 0.0003448564022838481, 'samples': 11072064, 'steps': 57666, 'loss/train': 1.1992400884628296} 08/30/2021 23:34:40 - INFO - __main__ - Step 57668: {'lr': 0.0003448514923445466, 'samples': 11072256, 'steps': 57667, 'loss/train': 1.7660138607025146} 08/30/2021 23:34:40 - INFO - __main__ - Step 57669: {'lr': 0.00034484658236250636, 'samples': 11072448, 'steps': 57668, 'loss/train': 0.876061201095581} 08/30/2021 23:34:42 - INFO - __main__ - Step 57670: {'lr': 0.0003448416723377298, 'samples': 11072640, 'steps': 57669, 'loss/train': 1.0351300239562988} 08/30/2021 23:34:43 - INFO - __main__ - Step 57671: {'lr': 0.00034483676227021906, 'samples': 11072832, 'steps': 57670, 'loss/train': 1.0887587070465088} 08/30/2021 23:34:43 - INFO - __main__ - Step 57672: {'lr': 0.00034483185215997624, 'samples': 11073024, 'steps': 57671, 'loss/train': 1.7450810670852661} 08/30/2021 23:34:43 - INFO - __main__ - Step 57673: {'lr': 0.00034482694200700377, 'samples': 11073216, 'steps': 57672, 'loss/train': 1.477314829826355} 08/30/2021 23:34:44 - INFO - __main__ - Step 57674: {'lr': 0.00034482203181130365, 'samples': 11073408, 'steps': 57673, 'loss/train': 0.24988338351249695} 08/30/2021 23:34:45 - INFO - __main__ - Step 57675: {'lr': 0.00034481712157287826, 'samples': 11073600, 'steps': 57674, 'loss/train': 1.4812304973602295} 08/30/2021 23:34:45 - INFO - __main__ - Step 57676: {'lr': 0.00034481221129172967, 'samples': 11073792, 'steps': 57675, 'loss/train': 0.9994809031486511} 08/30/2021 23:34:46 - INFO - __main__ - Step 57677: {'lr': 0.0003448073009678602, 'samples': 11073984, 'steps': 57676, 'loss/train': 1.4245047569274902} 08/30/2021 23:34:46 - INFO - __main__ - Step 57678: {'lr': 0.00034480239060127204, 'samples': 11074176, 'steps': 57677, 'loss/train': 1.153174877166748} 08/30/2021 23:34:47 - INFO - __main__ - Step 57679: {'lr': 0.00034479748019196734, 'samples': 11074368, 'steps': 57678, 'loss/train': 1.445250391960144} 08/30/2021 23:34:48 - INFO - __main__ - Step 57680: {'lr': 0.00034479256973994843, 'samples': 11074560, 'steps': 57679, 'loss/train': 0.6847001314163208} 08/30/2021 23:34:48 - INFO - __main__ - Step 57681: {'lr': 0.0003447876592452174, 'samples': 11074752, 'steps': 57680, 'loss/train': 1.2577377557754517} 08/30/2021 23:34:49 - INFO - __main__ - Step 57682: {'lr': 0.00034478274870777646, 'samples': 11074944, 'steps': 57681, 'loss/train': 1.187567114830017} 08/30/2021 23:34:49 - INFO - __main__ - Step 57683: {'lr': 0.00034477783812762795, 'samples': 11075136, 'steps': 57682, 'loss/train': 1.3287125825881958} 08/30/2021 23:34:49 - INFO - __main__ - Step 57684: {'lr': 0.00034477292750477396, 'samples': 11075328, 'steps': 57683, 'loss/train': 1.7312740087509155} 08/30/2021 23:34:51 - INFO - __main__ - Step 57685: {'lr': 0.00034476801683921683, 'samples': 11075520, 'steps': 57684, 'loss/train': 1.308159589767456} 08/30/2021 23:34:51 - INFO - __main__ - Step 57686: {'lr': 0.00034476310613095867, 'samples': 11075712, 'steps': 57685, 'loss/train': 0.866007387638092} 08/30/2021 23:34:52 - INFO - __main__ - Step 57687: {'lr': 0.0003447581953800017, 'samples': 11075904, 'steps': 57686, 'loss/train': 1.1797256469726562} 08/30/2021 23:34:52 - INFO - __main__ - Step 57688: {'lr': 0.00034475328458634814, 'samples': 11076096, 'steps': 57687, 'loss/train': 1.34390127658844} 08/30/2021 23:34:52 - INFO - __main__ - Step 57689: {'lr': 0.00034474837375000016, 'samples': 11076288, 'steps': 57688, 'loss/train': 1.7094366550445557} 08/30/2021 23:34:55 - INFO - __main__ - Step 57690: {'lr': 0.0003447434628709601, 'samples': 11076480, 'steps': 57689, 'loss/train': 1.3257652521133423} 08/30/2021 23:34:55 - INFO - __main__ - Step 57691: {'lr': 0.00034473855194923006, 'samples': 11076672, 'steps': 57690, 'loss/train': 0.8218780755996704} 08/30/2021 23:34:55 - INFO - __main__ - Step 57692: {'lr': 0.0003447336409848124, 'samples': 11076864, 'steps': 57691, 'loss/train': 1.311018466949463} 08/30/2021 23:34:56 - INFO - __main__ - Step 57693: {'lr': 0.0003447287299777091, 'samples': 11077056, 'steps': 57692, 'loss/train': 0.5102701187133789} 08/30/2021 23:34:56 - INFO - __main__ - Step 57694: {'lr': 0.0003447238189279225, 'samples': 11077248, 'steps': 57693, 'loss/train': 2.0247859954833984} 08/30/2021 23:34:56 - INFO - __main__ - Step 57695: {'lr': 0.0003447189078354548, 'samples': 11077440, 'steps': 57694, 'loss/train': 1.5504810810089111} 08/30/2021 23:34:58 - INFO - __main__ - Step 57696: {'lr': 0.00034471399670030824, 'samples': 11077632, 'steps': 57695, 'loss/train': 0.8103264570236206} 08/30/2021 23:34:58 - INFO - __main__ - Step 57697: {'lr': 0.00034470908552248504, 'samples': 11077824, 'steps': 57696, 'loss/train': 0.17652305960655212} 08/30/2021 23:34:59 - INFO - __main__ - Step 57698: {'lr': 0.00034470417430198743, 'samples': 11078016, 'steps': 57697, 'loss/train': 0.7908549308776855} 08/30/2021 23:34:59 - INFO - __main__ - Step 57699: {'lr': 0.00034469926303881747, 'samples': 11078208, 'steps': 57698, 'loss/train': 1.545953631401062} 08/30/2021 23:34:59 - INFO - __main__ - Step 57700: {'lr': 0.0003446943517329776, 'samples': 11078400, 'steps': 57699, 'loss/train': 0.47651827335357666} 08/30/2021 23:35:01 - INFO - __main__ - Step 57701: {'lr': 0.0003446894403844698, 'samples': 11078592, 'steps': 57700, 'loss/train': 1.7272061109542847} 08/30/2021 23:35:02 - INFO - __main__ - Step 57702: {'lr': 0.0003446845289932965, 'samples': 11078784, 'steps': 57701, 'loss/train': 1.343973159790039} 08/30/2021 23:35:02 - INFO - __main__ - Step 57703: {'lr': 0.0003446796175594598, 'samples': 11078976, 'steps': 57702, 'loss/train': 1.253000020980835} 08/30/2021 23:35:02 - INFO - __main__ - Step 57704: {'lr': 0.00034467470608296185, 'samples': 11079168, 'steps': 57703, 'loss/train': 1.3533598184585571} 08/30/2021 23:35:03 - INFO - __main__ - Step 57705: {'lr': 0.00034466979456380497, 'samples': 11079360, 'steps': 57704, 'loss/train': 5.671090126037598} 08/30/2021 23:35:03 - INFO - __main__ - Step 57706: {'lr': 0.0003446648830019914, 'samples': 11079552, 'steps': 57705, 'loss/train': 2.1126325130462646} 08/30/2021 23:35:05 - INFO - __main__ - Step 57707: {'lr': 0.00034465997139752327, 'samples': 11079744, 'steps': 57706, 'loss/train': 1.5409153699874878} 08/30/2021 23:35:05 - INFO - __main__ - Step 57708: {'lr': 0.00034465505975040273, 'samples': 11079936, 'steps': 57707, 'loss/train': 1.7867683172225952} 08/30/2021 23:35:06 - INFO - __main__ - Step 57709: {'lr': 0.0003446501480606322, 'samples': 11080128, 'steps': 57708, 'loss/train': 1.0364409685134888} 08/30/2021 23:35:06 - INFO - __main__ - Step 57710: {'lr': 0.0003446452363282137, 'samples': 11080320, 'steps': 57709, 'loss/train': 1.5341821908950806} 08/30/2021 23:35:06 - INFO - __main__ - Step 57711: {'lr': 0.00034464032455314955, 'samples': 11080512, 'steps': 57710, 'loss/train': 1.1671291589736938} 08/30/2021 23:35:08 - INFO - __main__ - Step 57712: {'lr': 0.0003446354127354419, 'samples': 11080704, 'steps': 57711, 'loss/train': 1.4817571640014648} 08/30/2021 23:35:08 - INFO - __main__ - Step 57713: {'lr': 0.000344630500875093, 'samples': 11080896, 'steps': 57712, 'loss/train': 1.438253402709961} 08/30/2021 23:35:08 - INFO - __main__ - Step 57714: {'lr': 0.0003446255889721051, 'samples': 11081088, 'steps': 57713, 'loss/train': 1.4417246580123901} 08/30/2021 23:35:09 - INFO - __main__ - Step 57715: {'lr': 0.00034462067702648036, 'samples': 11081280, 'steps': 57714, 'loss/train': 1.0315977334976196} 08/30/2021 23:35:09 - INFO - __main__ - Step 57716: {'lr': 0.000344615765038221, 'samples': 11081472, 'steps': 57715, 'loss/train': 1.712326169013977} 08/30/2021 23:35:12 - INFO - __main__ - Step 57717: {'lr': 0.0003446108530073292, 'samples': 11081664, 'steps': 57716, 'loss/train': 1.1476267576217651} 08/30/2021 23:35:12 - INFO - __main__ - Step 57718: {'lr': 0.0003446059409338072, 'samples': 11081856, 'steps': 57717, 'loss/train': 1.0954937934875488} 08/30/2021 23:35:12 - INFO - __main__ - Step 57719: {'lr': 0.00034460102881765723, 'samples': 11082048, 'steps': 57718, 'loss/train': 1.0650982856750488} 08/30/2021 23:35:13 - INFO - __main__ - Step 57720: {'lr': 0.0003445961166588816, 'samples': 11082240, 'steps': 57719, 'loss/train': 1.8287652730941772} 08/30/2021 23:35:13 - INFO - __main__ - Step 57721: {'lr': 0.0003445912044574823, 'samples': 11082432, 'steps': 57720, 'loss/train': 1.3199036121368408} 08/30/2021 23:35:14 - INFO - __main__ - Step 57722: {'lr': 0.00034458629221346173, 'samples': 11082624, 'steps': 57721, 'loss/train': 1.1869730949401855} 08/30/2021 23:35:15 - INFO - __main__ - Step 57723: {'lr': 0.000344581379926822, 'samples': 11082816, 'steps': 57722, 'loss/train': 0.5886616706848145} 08/30/2021 23:35:15 - INFO - __main__ - Step 57724: {'lr': 0.00034457646759756535, 'samples': 11083008, 'steps': 57723, 'loss/train': 1.2401893138885498} 08/30/2021 23:35:16 - INFO - __main__ - Step 57725: {'lr': 0.00034457155522569393, 'samples': 11083200, 'steps': 57724, 'loss/train': 0.4214799106121063} 08/30/2021 23:35:16 - INFO - __main__ - Step 57726: {'lr': 0.00034456664281121017, 'samples': 11083392, 'steps': 57725, 'loss/train': 1.436943769454956} 08/30/2021 23:35:16 - INFO - __main__ - Step 57727: {'lr': 0.00034456173035411606, 'samples': 11083584, 'steps': 57726, 'loss/train': 1.079527497291565} 08/30/2021 23:35:18 - INFO - __main__ - Step 57728: {'lr': 0.00034455681785441395, 'samples': 11083776, 'steps': 57727, 'loss/train': 1.3954976797103882} 08/30/2021 23:35:18 - INFO - __main__ - Step 57729: {'lr': 0.00034455190531210595, 'samples': 11083968, 'steps': 57728, 'loss/train': 0.8561622500419617} 08/30/2021 23:35:19 - INFO - __main__ - Step 57730: {'lr': 0.0003445469927271944, 'samples': 11084160, 'steps': 57729, 'loss/train': 1.1404969692230225} 08/30/2021 23:35:19 - INFO - __main__ - Step 57731: {'lr': 0.0003445420800996813, 'samples': 11084352, 'steps': 57730, 'loss/train': 1.301236629486084} 08/30/2021 23:35:19 - INFO - __main__ - Step 57732: {'lr': 0.0003445371674295691, 'samples': 11084544, 'steps': 57731, 'loss/train': 1.877077579498291} 08/30/2021 23:35:21 - INFO - __main__ - Step 57733: {'lr': 0.0003445322547168599, 'samples': 11084736, 'steps': 57732, 'loss/train': 1.3867772817611694} 08/30/2021 23:35:21 - INFO - __main__ - Step 57734: {'lr': 0.0003445273419615559, 'samples': 11084928, 'steps': 57733, 'loss/train': 1.3879948854446411} 08/30/2021 23:35:22 - INFO - __main__ - Step 57735: {'lr': 0.00034452242916365935, 'samples': 11085120, 'steps': 57734, 'loss/train': 1.122413992881775} 08/30/2021 23:35:22 - INFO - __main__ - Step 57736: {'lr': 0.0003445175163231724, 'samples': 11085312, 'steps': 57735, 'loss/train': 1.109182357788086} 08/30/2021 23:35:23 - INFO - __main__ - Step 57737: {'lr': 0.00034451260344009737, 'samples': 11085504, 'steps': 57736, 'loss/train': 0.9724215865135193} 08/30/2021 23:35:24 - INFO - __main__ - Step 57738: {'lr': 0.00034450769051443635, 'samples': 11085696, 'steps': 57737, 'loss/train': 1.587076187133789} 08/30/2021 23:35:24 - INFO - __main__ - Step 57739: {'lr': 0.0003445027775461917, 'samples': 11085888, 'steps': 57738, 'loss/train': 1.295042872428894} 08/30/2021 23:35:25 - INFO - __main__ - Step 57740: {'lr': 0.0003444978645353656, 'samples': 11086080, 'steps': 57739, 'loss/train': 1.1635597944259644} 08/30/2021 23:35:25 - INFO - __main__ - Step 57741: {'lr': 0.0003444929514819601, 'samples': 11086272, 'steps': 57740, 'loss/train': 1.6778360605239868} 08/30/2021 23:35:26 - INFO - __main__ - Step 57742: {'lr': 0.00034448803838597766, 'samples': 11086464, 'steps': 57741, 'loss/train': 1.3427680730819702} 08/30/2021 23:35:27 - INFO - __main__ - Step 57743: {'lr': 0.00034448312524742027, 'samples': 11086656, 'steps': 57742, 'loss/train': 1.3636891841888428} 08/30/2021 23:35:27 - INFO - __main__ - Step 57744: {'lr': 0.00034447821206629026, 'samples': 11086848, 'steps': 57743, 'loss/train': 0.6368964314460754} 08/30/2021 23:35:28 - INFO - __main__ - Step 57745: {'lr': 0.0003444732988425898, 'samples': 11087040, 'steps': 57744, 'loss/train': 0.5811021327972412} 08/30/2021 23:35:28 - INFO - __main__ - Step 57746: {'lr': 0.0003444683855763212, 'samples': 11087232, 'steps': 57745, 'loss/train': 1.5221400260925293} 08/30/2021 23:35:28 - INFO - __main__ - Step 57747: {'lr': 0.0003444634722674866, 'samples': 11087424, 'steps': 57746, 'loss/train': 1.543156385421753} 08/30/2021 23:35:29 - INFO - __main__ - Step 57748: {'lr': 0.0003444585589160882, 'samples': 11087616, 'steps': 57747, 'loss/train': 1.1631295680999756} 08/30/2021 23:35:30 - INFO - __main__ - Step 57749: {'lr': 0.0003444536455221282, 'samples': 11087808, 'steps': 57748, 'loss/train': 1.7758017778396606} 08/30/2021 23:35:31 - INFO - __main__ - Step 57750: {'lr': 0.00034444873208560884, 'samples': 11088000, 'steps': 57749, 'loss/train': 0.3763757050037384} 08/30/2021 23:35:31 - INFO - __main__ - Step 57751: {'lr': 0.00034444381860653233, 'samples': 11088192, 'steps': 57750, 'loss/train': 1.2167519330978394} 08/30/2021 23:35:31 - INFO - __main__ - Step 57752: {'lr': 0.00034443890508490093, 'samples': 11088384, 'steps': 57751, 'loss/train': 1.0028660297393799} 08/30/2021 23:35:32 - INFO - __main__ - Step 57753: {'lr': 0.0003444339915207168, 'samples': 11088576, 'steps': 57752, 'loss/train': 1.0443212985992432} 08/30/2021 23:35:33 - INFO - __main__ - Step 57754: {'lr': 0.0003444290779139823, 'samples': 11088768, 'steps': 57753, 'loss/train': 1.092671513557434} 08/30/2021 23:35:34 - INFO - __main__ - Step 57755: {'lr': 0.00034442416426469936, 'samples': 11088960, 'steps': 57754, 'loss/train': 0.5585522651672363} 08/30/2021 23:35:34 - INFO - __main__ - Step 57756: {'lr': 0.0003444192505728704, 'samples': 11089152, 'steps': 57755, 'loss/train': 0.9616211652755737} 08/30/2021 23:35:35 - INFO - __main__ - Step 57757: {'lr': 0.0003444143368384975, 'samples': 11089344, 'steps': 57756, 'loss/train': 0.5474900603294373} 08/30/2021 23:35:35 - INFO - __main__ - Step 57758: {'lr': 0.000344409423061583, 'samples': 11089536, 'steps': 57757, 'loss/train': 0.8820144534111023} 08/30/2021 23:35:36 - INFO - __main__ - Step 57759: {'lr': 0.00034440450924212913, 'samples': 11089728, 'steps': 57758, 'loss/train': 0.8886938095092773} 08/30/2021 23:35:37 - INFO - __main__ - Step 57760: {'lr': 0.00034439959538013805, 'samples': 11089920, 'steps': 57759, 'loss/train': 1.1811778545379639} 08/30/2021 23:35:37 - INFO - __main__ - Step 57761: {'lr': 0.0003443946814756119, 'samples': 11090112, 'steps': 57760, 'loss/train': 1.266503930091858} 08/30/2021 23:35:38 - INFO - __main__ - Step 57762: {'lr': 0.000344389767528553, 'samples': 11090304, 'steps': 57761, 'loss/train': 1.295312523841858} 08/30/2021 23:35:38 - INFO - __main__ - Step 57763: {'lr': 0.0003443848535389635, 'samples': 11090496, 'steps': 57762, 'loss/train': 1.5202609300613403} 08/30/2021 23:35:39 - INFO - __main__ - Step 57764: {'lr': 0.00034437993950684566, 'samples': 11090688, 'steps': 57763, 'loss/train': 1.4758069515228271} 08/30/2021 23:35:40 - INFO - __main__ - Step 57765: {'lr': 0.00034437502543220166, 'samples': 11090880, 'steps': 57764, 'loss/train': 1.0895005464553833} 08/30/2021 23:35:40 - INFO - __main__ - Step 57766: {'lr': 0.0003443701113150337, 'samples': 11091072, 'steps': 57765, 'loss/train': 1.5651397705078125} 08/30/2021 23:35:41 - INFO - __main__ - Step 57767: {'lr': 0.00034436519715534415, 'samples': 11091264, 'steps': 57766, 'loss/train': 0.9641022086143494} 08/30/2021 23:35:41 - INFO - __main__ - Step 57768: {'lr': 0.00034436028295313503, 'samples': 11091456, 'steps': 57767, 'loss/train': 1.4775365591049194} 08/30/2021 23:35:43 - INFO - __main__ - Step 57769: {'lr': 0.00034435536870840855, 'samples': 11091648, 'steps': 57768, 'loss/train': 1.7708853483200073} 08/30/2021 23:35:43 - INFO - __main__ - Step 57770: {'lr': 0.0003443504544211671, 'samples': 11091840, 'steps': 57769, 'loss/train': 1.1335792541503906} 08/30/2021 23:35:44 - INFO - __main__ - Step 57771: {'lr': 0.0003443455400914127, 'samples': 11092032, 'steps': 57770, 'loss/train': 0.9590129256248474} 08/30/2021 23:35:44 - INFO - __main__ - Step 57772: {'lr': 0.0003443406257191477, 'samples': 11092224, 'steps': 57771, 'loss/train': 1.0170713663101196} 08/30/2021 23:35:45 - INFO - __main__ - Step 57773: {'lr': 0.0003443357113043743, 'samples': 11092416, 'steps': 57772, 'loss/train': 1.997900128364563} 08/30/2021 23:35:45 - INFO - __main__ - Step 57774: {'lr': 0.00034433079684709466, 'samples': 11092608, 'steps': 57773, 'loss/train': 0.973318338394165} 08/30/2021 23:35:46 - INFO - __main__ - Step 57775: {'lr': 0.000344325882347311, 'samples': 11092800, 'steps': 57774, 'loss/train': 0.6636830568313599} 08/30/2021 23:35:47 - INFO - __main__ - Step 57776: {'lr': 0.00034432096780502564, 'samples': 11092992, 'steps': 57775, 'loss/train': 1.1859796047210693} 08/30/2021 23:35:47 - INFO - __main__ - Step 57777: {'lr': 0.0003443160532202406, 'samples': 11093184, 'steps': 57776, 'loss/train': 0.8080893754959106} 08/30/2021 23:35:48 - INFO - __main__ - Step 57778: {'lr': 0.00034431113859295827, 'samples': 11093376, 'steps': 57777, 'loss/train': 1.5912752151489258} 08/30/2021 23:35:48 - INFO - __main__ - Step 57779: {'lr': 0.00034430622392318073, 'samples': 11093568, 'steps': 57778, 'loss/train': 1.5313411951065063} 08/30/2021 23:35:49 - INFO - __main__ - Step 57780: {'lr': 0.0003443013092109103, 'samples': 11093760, 'steps': 57779, 'loss/train': 1.464087724685669} 08/30/2021 23:35:50 - INFO - __main__ - Step 57781: {'lr': 0.0003442963944561492, 'samples': 11093952, 'steps': 57780, 'loss/train': 1.627342939376831} 08/30/2021 23:35:50 - INFO - __main__ - Step 57782: {'lr': 0.0003442914796588995, 'samples': 11094144, 'steps': 57781, 'loss/train': 1.3642815351486206} 08/30/2021 23:35:51 - INFO - __main__ - Step 57783: {'lr': 0.00034428656481916357, 'samples': 11094336, 'steps': 57782, 'loss/train': 1.1529780626296997} 08/30/2021 23:35:51 - INFO - __main__ - Step 57784: {'lr': 0.00034428164993694356, 'samples': 11094528, 'steps': 57783, 'loss/train': 1.4525541067123413} 08/30/2021 23:35:51 - INFO - __main__ - Step 57785: {'lr': 0.0003442767350122417, 'samples': 11094720, 'steps': 57784, 'loss/train': 1.0132561922073364} 08/30/2021 23:35:53 - INFO - __main__ - Step 57786: {'lr': 0.0003442718200450602, 'samples': 11094912, 'steps': 57785, 'loss/train': 1.0175509452819824} 08/30/2021 23:35:53 - INFO - __main__ - Step 57787: {'lr': 0.0003442669050354013, 'samples': 11095104, 'steps': 57786, 'loss/train': 1.4026432037353516} 08/30/2021 23:35:54 - INFO - __main__ - Step 57788: {'lr': 0.00034426198998326713, 'samples': 11095296, 'steps': 57787, 'loss/train': 1.24473237991333} 08/30/2021 23:35:54 - INFO - __main__ - Step 57789: {'lr': 0.00034425707488866, 'samples': 11095488, 'steps': 57788, 'loss/train': 1.5531615018844604} 08/30/2021 23:35:54 - INFO - __main__ - Step 57790: {'lr': 0.0003442521597515821, 'samples': 11095680, 'steps': 57789, 'loss/train': 1.4984086751937866} 08/30/2021 23:35:57 - INFO - __main__ - Step 57791: {'lr': 0.00034424724457203553, 'samples': 11095872, 'steps': 57790, 'loss/train': 0.32216769456863403} 08/30/2021 23:35:57 - INFO - __main__ - Step 57792: {'lr': 0.0003442423293500227, 'samples': 11096064, 'steps': 57791, 'loss/train': 0.3440251648426056} 08/30/2021 23:35:58 - INFO - __main__ - Step 57793: {'lr': 0.0003442374140855457, 'samples': 11096256, 'steps': 57792, 'loss/train': 1.1713815927505493} 08/30/2021 23:35:58 - INFO - __main__ - Step 57794: {'lr': 0.00034423249877860683, 'samples': 11096448, 'steps': 57793, 'loss/train': 5.887346267700195} 08/30/2021 23:35:58 - INFO - __main__ - Step 57795: {'lr': 0.0003442275834292082, 'samples': 11096640, 'steps': 57794, 'loss/train': 5.646505832672119} 08/30/2021 23:35:59 - INFO - __main__ - Step 57796: {'lr': 0.0003442226680373521, 'samples': 11096832, 'steps': 57795, 'loss/train': 5.670462131500244} 08/30/2021 23:35:59 - INFO - __main__ - Step 57797: {'lr': 0.00034421775260304067, 'samples': 11097024, 'steps': 57796, 'loss/train': 5.702449798583984} 08/30/2021 23:36:01 - INFO - __main__ - Step 57798: {'lr': 0.0003442128371262762, 'samples': 11097216, 'steps': 57797, 'loss/train': 1.6899532079696655} 08/30/2021 23:36:01 - INFO - __main__ - Step 57799: {'lr': 0.00034420792160706087, 'samples': 11097408, 'steps': 57798, 'loss/train': 1.3607299327850342} 08/30/2021 23:36:01 - INFO - __main__ - Step 57800: {'lr': 0.0003442030060453969, 'samples': 11097600, 'steps': 57799, 'loss/train': 1.086534857749939} 08/30/2021 23:36:02 - INFO - __main__ - Step 57801: {'lr': 0.0003441980904412866, 'samples': 11097792, 'steps': 57800, 'loss/train': 1.604187250137329} 08/30/2021 23:36:02 - INFO - __main__ - Step 57802: {'lr': 0.000344193174794732, 'samples': 11097984, 'steps': 57801, 'loss/train': 1.3944400548934937} 08/30/2021 23:36:04 - INFO - __main__ - Step 57803: {'lr': 0.00034418825910573545, 'samples': 11098176, 'steps': 57802, 'loss/train': 1.3489320278167725} 08/30/2021 23:36:04 - INFO - __main__ - Step 57804: {'lr': 0.00034418334337429907, 'samples': 11098368, 'steps': 57803, 'loss/train': 1.7557225227355957} 08/30/2021 23:36:04 - INFO - __main__ - Step 57805: {'lr': 0.00034417842760042517, 'samples': 11098560, 'steps': 57804, 'loss/train': 1.3637171983718872} 08/30/2021 23:36:05 - INFO - __main__ - Step 57806: {'lr': 0.0003441735117841159, 'samples': 11098752, 'steps': 57805, 'loss/train': 1.4032765626907349} 08/30/2021 23:36:05 - INFO - __main__ - Step 57807: {'lr': 0.0003441685959253736, 'samples': 11098944, 'steps': 57806, 'loss/train': 1.4107378721237183} 08/30/2021 23:36:07 - INFO - __main__ - Step 57808: {'lr': 0.0003441636800242003, 'samples': 11099136, 'steps': 57807, 'loss/train': 1.7993744611740112} 08/30/2021 23:36:07 - INFO - __main__ - Step 57809: {'lr': 0.0003441587640805983, 'samples': 11099328, 'steps': 57808, 'loss/train': 0.7229326963424683} 08/30/2021 23:36:08 - INFO - __main__ - Step 57810: {'lr': 0.0003441538480945697, 'samples': 11099520, 'steps': 57809, 'loss/train': 1.1483817100524902} 08/30/2021 23:36:08 - INFO - __main__ - Step 57811: {'lr': 0.00034414893206611695, 'samples': 11099712, 'steps': 57810, 'loss/train': 1.3096764087677002} 08/30/2021 23:36:08 - INFO - __main__ - Step 57812: {'lr': 0.0003441440159952422, 'samples': 11099904, 'steps': 57811, 'loss/train': 1.5808639526367188} 08/30/2021 23:36:09 - INFO - __main__ - Step 57813: {'lr': 0.00034413909988194753, 'samples': 11100096, 'steps': 57812, 'loss/train': 1.2514926195144653} 08/30/2021 23:36:10 - INFO - __main__ - Step 57814: {'lr': 0.0003441341837262353, 'samples': 11100288, 'steps': 57813, 'loss/train': 0.10937996953725815} 08/30/2021 23:36:11 - INFO - __main__ - Step 57815: {'lr': 0.00034412926752810756, 'samples': 11100480, 'steps': 57814, 'loss/train': 0.21634015440940857} 08/30/2021 23:36:11 - INFO - __main__ - Step 57816: {'lr': 0.0003441243512875667, 'samples': 11100672, 'steps': 57815, 'loss/train': 1.3703187704086304} 08/30/2021 23:36:11 - INFO - __main__ - Step 57817: {'lr': 0.00034411943500461484, 'samples': 11100864, 'steps': 57816, 'loss/train': 1.9440540075302124} 08/30/2021 23:36:12 - INFO - __main__ - Step 57818: {'lr': 0.0003441145186792542, 'samples': 11101056, 'steps': 57817, 'loss/train': 1.3769536018371582} 08/30/2021 23:36:13 - INFO - __main__ - Step 57819: {'lr': 0.000344109602311487, 'samples': 11101248, 'steps': 57818, 'loss/train': 1.109779715538025} 08/30/2021 23:36:14 - INFO - __main__ - Step 57820: {'lr': 0.0003441046859013155, 'samples': 11101440, 'steps': 57819, 'loss/train': 1.5465869903564453} 08/30/2021 23:36:14 - INFO - __main__ - Step 57821: {'lr': 0.00034409976944874186, 'samples': 11101632, 'steps': 57820, 'loss/train': 0.7728293538093567} 08/30/2021 23:36:14 - INFO - __main__ - Step 57822: {'lr': 0.0003440948529537683, 'samples': 11101824, 'steps': 57821, 'loss/train': 1.0767645835876465} 08/30/2021 23:36:15 - INFO - __main__ - Step 57823: {'lr': 0.00034408993641639707, 'samples': 11102016, 'steps': 57822, 'loss/train': 1.489098072052002} 08/30/2021 23:36:17 - INFO - __main__ - Step 57824: {'lr': 0.0003440850198366304, 'samples': 11102208, 'steps': 57823, 'loss/train': 0.8877474069595337} 08/30/2021 23:36:17 - INFO - __main__ - Step 57825: {'lr': 0.0003440801032144704, 'samples': 11102400, 'steps': 57824, 'loss/train': 0.616609513759613} 08/30/2021 23:36:18 - INFO - __main__ - Step 57826: {'lr': 0.00034407518654991945, 'samples': 11102592, 'steps': 57825, 'loss/train': 0.9271731972694397} 08/30/2021 23:36:18 - INFO - __main__ - Step 57827: {'lr': 0.00034407026984297964, 'samples': 11102784, 'steps': 57826, 'loss/train': 0.9796440601348877} 08/30/2021 23:36:19 - INFO - __main__ - Step 57828: {'lr': 0.00034406535309365317, 'samples': 11102976, 'steps': 57827, 'loss/train': 0.7911518812179565} 08/30/2021 23:36:19 - INFO - __main__ - Step 57829: {'lr': 0.0003440604363019423, 'samples': 11103168, 'steps': 57828, 'loss/train': 0.47116604447364807} 08/30/2021 23:36:21 - INFO - __main__ - Step 57830: {'lr': 0.0003440555194678493, 'samples': 11103360, 'steps': 57829, 'loss/train': 0.5575730800628662} 08/30/2021 23:36:22 - INFO - __main__ - Step 57831: {'lr': 0.0003440506025913763, 'samples': 11103552, 'steps': 57830, 'loss/train': 1.621256947517395} 08/30/2021 23:36:22 - INFO - __main__ - Step 57832: {'lr': 0.0003440456856725256, 'samples': 11103744, 'steps': 57831, 'loss/train': 1.3650532960891724} 08/30/2021 23:36:22 - INFO - __main__ - Step 57833: {'lr': 0.0003440407687112993, 'samples': 11103936, 'steps': 57832, 'loss/train': 1.0273456573486328} 08/30/2021 23:36:23 - INFO - __main__ - Step 57834: {'lr': 0.0003440358517076997, 'samples': 11104128, 'steps': 57833, 'loss/train': 1.679181694984436} 08/30/2021 23:36:24 - INFO - __main__ - Step 57835: {'lr': 0.00034403093466172903, 'samples': 11104320, 'steps': 57834, 'loss/train': 1.6843326091766357} 08/30/2021 23:36:25 - INFO - __main__ - Step 57836: {'lr': 0.00034402601757338946, 'samples': 11104512, 'steps': 57835, 'loss/train': 0.2866305112838745} 08/30/2021 23:36:25 - INFO - __main__ - Step 57837: {'lr': 0.00034402110044268327, 'samples': 11104704, 'steps': 57836, 'loss/train': 1.659409761428833} 08/30/2021 23:36:25 - INFO - __main__ - Step 57838: {'lr': 0.00034401618326961253, 'samples': 11104896, 'steps': 57837, 'loss/train': 1.2834805250167847} 08/30/2021 23:36:26 - INFO - __main__ - Step 57839: {'lr': 0.0003440112660541795, 'samples': 11105088, 'steps': 57838, 'loss/train': 0.12566542625427246} 08/30/2021 23:36:27 - INFO - __main__ - Step 57840: {'lr': 0.0003440063487963866, 'samples': 11105280, 'steps': 57839, 'loss/train': 1.818826675415039} 08/30/2021 23:36:28 - INFO - __main__ - Step 57841: {'lr': 0.00034400143149623574, 'samples': 11105472, 'steps': 57840, 'loss/train': 1.8270034790039062} 08/30/2021 23:36:28 - INFO - __main__ - Step 57842: {'lr': 0.0003439965141537294, 'samples': 11105664, 'steps': 57841, 'loss/train': 1.3017204999923706} 08/30/2021 23:36:28 - INFO - __main__ - Step 57843: {'lr': 0.00034399159676886965, 'samples': 11105856, 'steps': 57842, 'loss/train': 1.2645552158355713} 08/30/2021 23:36:29 - INFO - __main__ - Step 57844: {'lr': 0.00034398667934165873, 'samples': 11106048, 'steps': 57843, 'loss/train': 1.4458588361740112} 08/30/2021 23:36:30 - INFO - __main__ - Step 57845: {'lr': 0.00034398176187209887, 'samples': 11106240, 'steps': 57844, 'loss/train': 0.04177282005548477} 08/30/2021 23:36:31 - INFO - __main__ - Step 57846: {'lr': 0.0003439768443601923, 'samples': 11106432, 'steps': 57845, 'loss/train': 1.368549108505249} 08/30/2021 23:36:31 - INFO - __main__ - Step 57847: {'lr': 0.0003439719268059411, 'samples': 11106624, 'steps': 57846, 'loss/train': 0.920562744140625} 08/30/2021 23:36:31 - INFO - __main__ - Step 57848: {'lr': 0.0003439670092093478, 'samples': 11106816, 'steps': 57847, 'loss/train': 0.9704640507698059} 08/30/2021 23:36:32 - INFO - __main__ - Step 57849: {'lr': 0.00034396209157041424, 'samples': 11107008, 'steps': 57848, 'loss/train': 1.2088522911071777} 08/30/2021 23:36:33 - INFO - __main__ - Step 57850: {'lr': 0.0003439571738891428, 'samples': 11107200, 'steps': 57849, 'loss/train': 1.0287530422210693} 08/30/2021 23:36:34 - INFO - __main__ - Step 57851: {'lr': 0.00034395225616553585, 'samples': 11107392, 'steps': 57850, 'loss/train': 1.0662367343902588} 08/30/2021 23:36:34 - INFO - __main__ - Step 57852: {'lr': 0.00034394733839959534, 'samples': 11107584, 'steps': 57851, 'loss/train': 0.16599543392658234} 08/30/2021 23:36:34 - INFO - __main__ - Step 57853: {'lr': 0.0003439424205913236, 'samples': 11107776, 'steps': 57852, 'loss/train': 0.8803872466087341} 08/30/2021 23:36:35 - INFO - __main__ - Step 57854: {'lr': 0.000343937502740723, 'samples': 11107968, 'steps': 57853, 'loss/train': 1.306980848312378} 08/30/2021 23:36:35 - INFO - __main__ - Step 57855: {'lr': 0.00034393258484779555, 'samples': 11108160, 'steps': 57854, 'loss/train': 1.2254265546798706} 08/30/2021 23:36:37 - INFO - __main__ - Step 57856: {'lr': 0.0003439276669125435, 'samples': 11108352, 'steps': 57855, 'loss/train': 1.018570065498352} 08/30/2021 23:36:37 - INFO - __main__ - Step 57857: {'lr': 0.00034392274893496903, 'samples': 11108544, 'steps': 57856, 'loss/train': 1.033927083015442} 08/30/2021 23:36:37 - INFO - __main__ - Step 57858: {'lr': 0.0003439178309150745, 'samples': 11108736, 'steps': 57857, 'loss/train': 1.6335034370422363} 08/30/2021 23:36:38 - INFO - __main__ - Step 57859: {'lr': 0.000343912912852862, 'samples': 11108928, 'steps': 57858, 'loss/train': 0.8771165013313293} 08/30/2021 23:36:38 - INFO - __main__ - Step 57860: {'lr': 0.00034390799474833385, 'samples': 11109120, 'steps': 57859, 'loss/train': 1.149033784866333} 08/30/2021 23:36:39 - INFO - __main__ - Step 57861: {'lr': 0.0003439030766014922, 'samples': 11109312, 'steps': 57860, 'loss/train': 1.5801451206207275} 08/30/2021 23:36:40 - INFO - __main__ - Step 57862: {'lr': 0.0003438981584123392, 'samples': 11109504, 'steps': 57861, 'loss/train': 1.4704382419586182} 08/30/2021 23:36:40 - INFO - __main__ - Step 57863: {'lr': 0.0003438932401808772, 'samples': 11109696, 'steps': 57862, 'loss/train': 1.1314772367477417} 08/30/2021 23:36:41 - INFO - __main__ - Step 57864: {'lr': 0.0003438883219071083, 'samples': 11109888, 'steps': 57863, 'loss/train': 1.182839035987854} 08/30/2021 23:36:41 - INFO - __main__ - Step 57865: {'lr': 0.00034388340359103485, 'samples': 11110080, 'steps': 57864, 'loss/train': 1.3338888883590698} 08/30/2021 23:36:43 - INFO - __main__ - Step 57866: {'lr': 0.0003438784852326589, 'samples': 11110272, 'steps': 57865, 'loss/train': 1.6208808422088623} 08/30/2021 23:36:43 - INFO - __main__ - Step 57867: {'lr': 0.0003438735668319828, 'samples': 11110464, 'steps': 57866, 'loss/train': 1.4217983484268188} 08/30/2021 23:36:43 - INFO - __main__ - Step 57868: {'lr': 0.00034386864838900877, 'samples': 11110656, 'steps': 57867, 'loss/train': 1.821641445159912} 08/30/2021 23:36:44 - INFO - __main__ - Step 57869: {'lr': 0.00034386372990373893, 'samples': 11110848, 'steps': 57868, 'loss/train': 1.2849440574645996} 08/30/2021 23:36:44 - INFO - __main__ - Step 57870: {'lr': 0.0003438588113761755, 'samples': 11111040, 'steps': 57869, 'loss/train': 1.7026925086975098} 08/30/2021 23:36:46 - INFO - __main__ - Step 57871: {'lr': 0.00034385389280632077, 'samples': 11111232, 'steps': 57870, 'loss/train': 1.6099143028259277} 08/30/2021 23:36:46 - INFO - __main__ - Step 57872: {'lr': 0.00034384897419417694, 'samples': 11111424, 'steps': 57871, 'loss/train': 0.5960713028907776} 08/30/2021 23:36:46 - INFO - __main__ - Step 57873: {'lr': 0.0003438440555397462, 'samples': 11111616, 'steps': 57872, 'loss/train': 2.930335760116577} 08/30/2021 23:36:47 - INFO - __main__ - Step 57874: {'lr': 0.00034383913684303075, 'samples': 11111808, 'steps': 57873, 'loss/train': 1.212746500968933} 08/30/2021 23:36:47 - INFO - __main__ - Step 57875: {'lr': 0.00034383421810403294, 'samples': 11112000, 'steps': 57874, 'loss/train': 1.3006385564804077} 08/30/2021 23:36:49 - INFO - __main__ - Step 57876: {'lr': 0.00034382929932275476, 'samples': 11112192, 'steps': 57875, 'loss/train': 1.3369630575180054} 08/30/2021 23:36:49 - INFO - __main__ - Step 57877: {'lr': 0.0003438243804991986, 'samples': 11112384, 'steps': 57876, 'loss/train': 1.265333890914917} 08/30/2021 23:36:50 - INFO - __main__ - Step 57878: {'lr': 0.0003438194616333666, 'samples': 11112576, 'steps': 57877, 'loss/train': 1.7464908361434937} 08/30/2021 23:36:50 - INFO - __main__ - Step 57879: {'lr': 0.00034381454272526096, 'samples': 11112768, 'steps': 57878, 'loss/train': 0.16650265455245972} 08/30/2021 23:36:50 - INFO - __main__ - Step 57880: {'lr': 0.000343809623774884, 'samples': 11112960, 'steps': 57879, 'loss/train': 1.6911827325820923} 08/30/2021 23:36:52 - INFO - __main__ - Step 57881: {'lr': 0.0003438047047822379, 'samples': 11113152, 'steps': 57880, 'loss/train': 0.08717140555381775} 08/30/2021 23:36:53 - INFO - __main__ - Step 57882: {'lr': 0.0003437997857473248, 'samples': 11113344, 'steps': 57881, 'loss/train': 0.9880353808403015} 08/30/2021 23:36:53 - INFO - __main__ - Step 57883: {'lr': 0.0003437948666701469, 'samples': 11113536, 'steps': 57882, 'loss/train': 1.7614012956619263} 08/30/2021 23:36:54 - INFO - __main__ - Step 57884: {'lr': 0.00034378994755070657, 'samples': 11113728, 'steps': 57883, 'loss/train': 1.565075159072876} 08/30/2021 23:36:54 - INFO - __main__ - Step 57885: {'lr': 0.00034378502838900587, 'samples': 11113920, 'steps': 57884, 'loss/train': 1.5057799816131592} 08/30/2021 23:36:54 - INFO - __main__ - Step 57886: {'lr': 0.00034378010918504714, 'samples': 11114112, 'steps': 57885, 'loss/train': 1.13325834274292} 08/30/2021 23:36:56 - INFO - __main__ - Step 57887: {'lr': 0.0003437751899388325, 'samples': 11114304, 'steps': 57886, 'loss/train': 1.3970110416412354} 08/30/2021 23:36:56 - INFO - __main__ - Step 57888: {'lr': 0.00034377027065036423, 'samples': 11114496, 'steps': 57887, 'loss/train': 1.3978787660598755} 08/30/2021 23:36:57 - INFO - __main__ - Step 57889: {'lr': 0.0003437653513196446, 'samples': 11114688, 'steps': 57888, 'loss/train': 1.4013556241989136} 08/30/2021 23:36:57 - INFO - __main__ - Step 57890: {'lr': 0.0003437604319466756, 'samples': 11114880, 'steps': 57889, 'loss/train': 1.4467740058898926} 08/30/2021 23:36:57 - INFO - __main__ - Step 57891: {'lr': 0.0003437555125314597, 'samples': 11115072, 'steps': 57890, 'loss/train': 1.6815907955169678} 08/30/2021 23:36:59 - INFO - __main__ - Step 57892: {'lr': 0.00034375059307399896, 'samples': 11115264, 'steps': 57891, 'loss/train': 1.770148754119873} 08/30/2021 23:36:59 - INFO - __main__ - Step 57893: {'lr': 0.00034374567357429563, 'samples': 11115456, 'steps': 57892, 'loss/train': 1.8611518144607544} 08/30/2021 23:37:00 - INFO - __main__ - Step 57894: {'lr': 0.000343740754032352, 'samples': 11115648, 'steps': 57893, 'loss/train': 1.2542556524276733} 08/30/2021 23:37:00 - INFO - __main__ - Step 57895: {'lr': 0.00034373583444817024, 'samples': 11115840, 'steps': 57894, 'loss/train': 1.2793387174606323} 08/30/2021 23:37:00 - INFO - __main__ - Step 57896: {'lr': 0.0003437309148217526, 'samples': 11116032, 'steps': 57895, 'loss/train': 1.2916450500488281} 08/30/2021 23:37:02 - INFO - __main__ - Step 57897: {'lr': 0.00034372599515310117, 'samples': 11116224, 'steps': 57896, 'loss/train': 0.9101265668869019} 08/30/2021 23:37:03 - INFO - __main__ - Step 57898: {'lr': 0.00034372107544221824, 'samples': 11116416, 'steps': 57897, 'loss/train': 1.8328304290771484} 08/30/2021 23:37:03 - INFO - __main__ - Step 57899: {'lr': 0.00034371615568910607, 'samples': 11116608, 'steps': 57898, 'loss/train': 1.337120771408081} 08/30/2021 23:37:03 - INFO - __main__ - Step 57900: {'lr': 0.00034371123589376683, 'samples': 11116800, 'steps': 57899, 'loss/train': 0.08235103636980057} 08/30/2021 23:37:04 - INFO - __main__ - Step 57901: {'lr': 0.00034370631605620285, 'samples': 11116992, 'steps': 57900, 'loss/train': 1.3802589178085327} 08/30/2021 23:37:05 - INFO - __main__ - Step 57902: {'lr': 0.0003437013961764162, 'samples': 11117184, 'steps': 57901, 'loss/train': 1.0558006763458252} 08/30/2021 23:37:06 - INFO - __main__ - Step 57903: {'lr': 0.00034369647625440906, 'samples': 11117376, 'steps': 57902, 'loss/train': 1.6199114322662354} 08/30/2021 23:37:06 - INFO - __main__ - Step 57904: {'lr': 0.00034369155629018376, 'samples': 11117568, 'steps': 57903, 'loss/train': 2.112682342529297} 08/30/2021 23:37:06 - INFO - __main__ - Step 57905: {'lr': 0.00034368663628374255, 'samples': 11117760, 'steps': 57904, 'loss/train': 1.5754579305648804} 08/30/2021 23:37:07 - INFO - __main__ - Step 57906: {'lr': 0.0003436817162350876, 'samples': 11117952, 'steps': 57905, 'loss/train': 1.8452544212341309} 08/30/2021 23:37:07 - INFO - __main__ - Step 57907: {'lr': 0.00034367679614422103, 'samples': 11118144, 'steps': 57906, 'loss/train': 1.4249106645584106} 08/30/2021 23:37:08 - INFO - __main__ - Step 57908: {'lr': 0.0003436718760111452, 'samples': 11118336, 'steps': 57907, 'loss/train': 1.1053876876831055} 08/30/2021 23:37:09 - INFO - __main__ - Step 57909: {'lr': 0.0003436669558358623, 'samples': 11118528, 'steps': 57908, 'loss/train': 1.2126071453094482} 08/30/2021 23:37:09 - INFO - __main__ - Step 57910: {'lr': 0.00034366203561837446, 'samples': 11118720, 'steps': 57909, 'loss/train': 0.7809210419654846} 08/30/2021 23:37:10 - INFO - __main__ - Step 57911: {'lr': 0.00034365711535868396, 'samples': 11118912, 'steps': 57910, 'loss/train': 1.4636561870574951} 08/30/2021 23:37:10 - INFO - __main__ - Step 57912: {'lr': 0.000343652195056793, 'samples': 11119104, 'steps': 57911, 'loss/train': 1.1502405405044556} 08/30/2021 23:37:11 - INFO - __main__ - Step 57913: {'lr': 0.0003436472747127038, 'samples': 11119296, 'steps': 57912, 'loss/train': 1.3437775373458862} 08/30/2021 23:37:12 - INFO - __main__ - Step 57914: {'lr': 0.0003436423543264186, 'samples': 11119488, 'steps': 57913, 'loss/train': 0.23785971105098724} 08/30/2021 23:37:12 - INFO - __main__ - Step 57915: {'lr': 0.00034363743389793965, 'samples': 11119680, 'steps': 57914, 'loss/train': 1.0402017831802368} 08/30/2021 23:37:13 - INFO - __main__ - Step 57916: {'lr': 0.0003436325134272691, 'samples': 11119872, 'steps': 57915, 'loss/train': 0.9781309366226196} 08/30/2021 23:37:13 - INFO - __main__ - Step 57917: {'lr': 0.0003436275929144091, 'samples': 11120064, 'steps': 57916, 'loss/train': 1.1634918451309204} 08/30/2021 23:37:15 - INFO - __main__ - Step 57918: {'lr': 0.000343622672359362, 'samples': 11120256, 'steps': 57917, 'loss/train': 1.6962443590164185} 08/30/2021 23:37:15 - INFO - __main__ - Step 57919: {'lr': 0.0003436177517621299, 'samples': 11120448, 'steps': 57918, 'loss/train': 0.9304451942443848} 08/30/2021 23:37:15 - INFO - __main__ - Step 57920: {'lr': 0.0003436128311227152, 'samples': 11120640, 'steps': 57919, 'loss/train': 1.8049160242080688} 08/30/2021 23:37:16 - INFO - __main__ - Step 57921: {'lr': 0.00034360791044111996, 'samples': 11120832, 'steps': 57920, 'loss/train': 0.9886671304702759} 08/30/2021 23:37:16 - INFO - __main__ - Step 57922: {'lr': 0.00034360298971734647, 'samples': 11121024, 'steps': 57921, 'loss/train': 1.065738320350647} 08/30/2021 23:37:17 - INFO - __main__ - Step 57923: {'lr': 0.00034359806895139686, 'samples': 11121216, 'steps': 57922, 'loss/train': 0.43623223900794983} 08/30/2021 23:37:18 - INFO - __main__ - Step 57924: {'lr': 0.0003435931481432735, 'samples': 11121408, 'steps': 57923, 'loss/train': 1.290938138961792} 08/30/2021 23:37:18 - INFO - __main__ - Step 57925: {'lr': 0.00034358822729297847, 'samples': 11121600, 'steps': 57924, 'loss/train': 1.566215991973877} 08/30/2021 23:37:19 - INFO - __main__ - Step 57926: {'lr': 0.00034358330640051396, 'samples': 11121792, 'steps': 57925, 'loss/train': 2.0767035484313965} 08/30/2021 23:37:19 - INFO - __main__ - Step 57927: {'lr': 0.0003435783854658823, 'samples': 11121984, 'steps': 57926, 'loss/train': 0.6464002728462219} 08/30/2021 23:37:21 - INFO - __main__ - Step 57928: {'lr': 0.00034357346448908566, 'samples': 11122176, 'steps': 57927, 'loss/train': 0.6116719245910645} 08/30/2021 23:37:21 - INFO - __main__ - Step 57929: {'lr': 0.00034356854347012626, 'samples': 11122368, 'steps': 57928, 'loss/train': 0.2873060703277588} 08/30/2021 23:37:22 - INFO - __main__ - Step 57930: {'lr': 0.00034356362240900635, 'samples': 11122560, 'steps': 57929, 'loss/train': 1.1154003143310547} 08/30/2021 23:37:22 - INFO - __main__ - Step 57931: {'lr': 0.0003435587013057281, 'samples': 11122752, 'steps': 57930, 'loss/train': 1.5685776472091675} 08/30/2021 23:37:22 - INFO - __main__ - Step 57932: {'lr': 0.0003435537801602937, 'samples': 11122944, 'steps': 57931, 'loss/train': 1.1144810914993286} 08/30/2021 23:37:23 - INFO - __main__ - Step 57933: {'lr': 0.00034354885897270546, 'samples': 11123136, 'steps': 57932, 'loss/train': 1.18936288356781} 08/30/2021 23:37:24 - INFO - __main__ - Step 57934: {'lr': 0.0003435439377429655, 'samples': 11123328, 'steps': 57933, 'loss/train': 1.4783251285552979} 08/30/2021 23:37:25 - INFO - __main__ - Step 57935: {'lr': 0.00034353901647107615, 'samples': 11123520, 'steps': 57934, 'loss/train': 1.7091912031173706} 08/30/2021 23:37:25 - INFO - __main__ - Step 57936: {'lr': 0.0003435340951570395, 'samples': 11123712, 'steps': 57935, 'loss/train': 0.7045174241065979} 08/30/2021 23:37:25 - INFO - __main__ - Step 57937: {'lr': 0.00034352917380085784, 'samples': 11123904, 'steps': 57936, 'loss/train': 0.8868584632873535} 08/30/2021 23:37:26 - INFO - __main__ - Step 57938: {'lr': 0.00034352425240253344, 'samples': 11124096, 'steps': 57937, 'loss/train': 1.1050552129745483} 08/30/2021 23:37:28 - INFO - __main__ - Step 57939: {'lr': 0.0003435193309620684, 'samples': 11124288, 'steps': 57938, 'loss/train': 0.7417891025543213} 08/30/2021 23:37:29 - INFO - __main__ - Step 57940: {'lr': 0.000343514409479465, 'samples': 11124480, 'steps': 57939, 'loss/train': 0.11086741089820862} 08/30/2021 23:37:29 - INFO - __main__ - Step 57941: {'lr': 0.00034350948795472543, 'samples': 11124672, 'steps': 57940, 'loss/train': 1.1636950969696045} 08/30/2021 23:37:29 - INFO - __main__ - Step 57942: {'lr': 0.000343504566387852, 'samples': 11124864, 'steps': 57941, 'loss/train': 1.2470804452896118} 08/30/2021 23:37:30 - INFO - __main__ - Step 57943: {'lr': 0.0003434996447788468, 'samples': 11125056, 'steps': 57942, 'loss/train': 0.9283044934272766} 08/30/2021 23:37:31 - INFO - __main__ - Step 57944: {'lr': 0.0003434947231277121, 'samples': 11125248, 'steps': 57943, 'loss/train': 0.2703121304512024} 08/30/2021 23:37:32 - INFO - __main__ - Step 57945: {'lr': 0.0003434898014344501, 'samples': 11125440, 'steps': 57944, 'loss/train': 1.449692726135254} 08/30/2021 23:37:32 - INFO - __main__ - Step 57946: {'lr': 0.00034348487969906307, 'samples': 11125632, 'steps': 57945, 'loss/train': 0.9957125186920166} 08/30/2021 23:37:32 - INFO - __main__ - Step 57947: {'lr': 0.00034347995792155316, 'samples': 11125824, 'steps': 57946, 'loss/train': 0.34559452533721924} 08/30/2021 23:37:33 - INFO - __main__ - Step 57948: {'lr': 0.00034347503610192265, 'samples': 11126016, 'steps': 57947, 'loss/train': 0.7299861907958984} 08/30/2021 23:37:34 - INFO - __main__ - Step 57949: {'lr': 0.0003434701142401738, 'samples': 11126208, 'steps': 57948, 'loss/train': 1.3295950889587402} 08/30/2021 23:37:35 - INFO - __main__ - Step 57950: {'lr': 0.0003434651923363087, 'samples': 11126400, 'steps': 57949, 'loss/train': 1.3353164196014404} 08/30/2021 23:37:35 - INFO - __main__ - Step 57951: {'lr': 0.0003434602703903296, 'samples': 11126592, 'steps': 57950, 'loss/train': 1.6220121383666992} 08/30/2021 23:37:35 - INFO - __main__ - Step 57952: {'lr': 0.0003434553484022388, 'samples': 11126784, 'steps': 57951, 'loss/train': 1.4216296672821045} 08/30/2021 23:37:36 - INFO - __main__ - Step 57953: {'lr': 0.0003434504263720384, 'samples': 11126976, 'steps': 57952, 'loss/train': 1.7862017154693604} 08/30/2021 23:37:36 - INFO - __main__ - Step 57954: {'lr': 0.0003434455042997307, 'samples': 11127168, 'steps': 57953, 'loss/train': 1.262322187423706} 08/30/2021 23:37:38 - INFO - __main__ - Step 57955: {'lr': 0.00034344058218531794, 'samples': 11127360, 'steps': 57954, 'loss/train': 1.8173655271530151} 08/30/2021 23:37:38 - INFO - __main__ - Step 57956: {'lr': 0.0003434356600288023, 'samples': 11127552, 'steps': 57955, 'loss/train': 1.0475902557373047} 08/30/2021 23:37:38 - INFO - __main__ - Step 57957: {'lr': 0.00034343073783018593, 'samples': 11127744, 'steps': 57956, 'loss/train': 1.4100340604782104} 08/30/2021 23:37:39 - INFO - __main__ - Step 57958: {'lr': 0.00034342581558947113, 'samples': 11127936, 'steps': 57957, 'loss/train': 1.584753155708313} 08/30/2021 23:37:39 - INFO - __main__ - Step 57959: {'lr': 0.00034342089330666, 'samples': 11128128, 'steps': 57958, 'loss/train': 1.344902515411377} 08/30/2021 23:37:41 - INFO - __main__ - Step 57960: {'lr': 0.00034341597098175503, 'samples': 11128320, 'steps': 57959, 'loss/train': 0.5916837453842163} 08/30/2021 23:37:41 - INFO - __main__ - Step 57961: {'lr': 0.0003434110486147582, 'samples': 11128512, 'steps': 57960, 'loss/train': 1.376560926437378} 08/30/2021 23:37:41 - INFO - __main__ - Step 57962: {'lr': 0.0003434061262056718, 'samples': 11128704, 'steps': 57961, 'loss/train': 0.968560516834259} 08/30/2021 23:37:42 - INFO - __main__ - Step 57963: {'lr': 0.0003434012037544981, 'samples': 11128896, 'steps': 57962, 'loss/train': 0.9626744985580444} 08/30/2021 23:37:42 - INFO - __main__ - Step 57964: {'lr': 0.0003433962812612391, 'samples': 11129088, 'steps': 57963, 'loss/train': 1.3924027681350708} 08/30/2021 23:37:44 - INFO - __main__ - Step 57965: {'lr': 0.0003433913587258973, 'samples': 11129280, 'steps': 57964, 'loss/train': 1.6076587438583374} 08/30/2021 23:37:44 - INFO - __main__ - Step 57966: {'lr': 0.0003433864361484748, 'samples': 11129472, 'steps': 57965, 'loss/train': 0.9695044755935669} 08/30/2021 23:37:44 - INFO - __main__ - Step 57967: {'lr': 0.00034338151352897376, 'samples': 11129664, 'steps': 57966, 'loss/train': 1.0120548009872437} 08/30/2021 23:37:45 - INFO - __main__ - Step 57968: {'lr': 0.00034337659086739646, 'samples': 11129856, 'steps': 57967, 'loss/train': 0.5006092190742493} 08/30/2021 23:37:45 - INFO - __main__ - Step 57969: {'lr': 0.0003433716681637451, 'samples': 11130048, 'steps': 57968, 'loss/train': 0.7030481696128845} 08/30/2021 23:37:47 - INFO - __main__ - Step 57970: {'lr': 0.0003433667454180219, 'samples': 11130240, 'steps': 57969, 'loss/train': 1.6818792819976807} 08/30/2021 23:37:47 - INFO - __main__ - Step 57971: {'lr': 0.00034336182263022916, 'samples': 11130432, 'steps': 57970, 'loss/train': 1.3140954971313477} 08/30/2021 23:37:47 - INFO - __main__ - Step 57972: {'lr': 0.000343356899800369, 'samples': 11130624, 'steps': 57971, 'loss/train': 2.077301263809204} 08/30/2021 23:37:48 - INFO - __main__ - Step 57973: {'lr': 0.0003433519769284436, 'samples': 11130816, 'steps': 57972, 'loss/train': 1.0022573471069336} 08/30/2021 23:37:48 - INFO - __main__ - Step 57974: {'lr': 0.00034334705401445527, 'samples': 11131008, 'steps': 57973, 'loss/train': 0.963807225227356} 08/30/2021 23:37:48 - INFO - __main__ - Step 57975: {'lr': 0.00034334213105840616, 'samples': 11131200, 'steps': 57974, 'loss/train': 1.4510246515274048} 08/30/2021 23:37:50 - INFO - __main__ - Step 57976: {'lr': 0.00034333720806029863, 'samples': 11131392, 'steps': 57975, 'loss/train': 0.7574708461761475} 08/30/2021 23:37:51 - INFO - __main__ - Step 57977: {'lr': 0.00034333228502013473, 'samples': 11131584, 'steps': 57976, 'loss/train': 1.8057149648666382} 08/30/2021 23:37:51 - INFO - __main__ - Step 57978: {'lr': 0.00034332736193791675, 'samples': 11131776, 'steps': 57977, 'loss/train': 0.050422124564647675} 08/30/2021 23:37:51 - INFO - __main__ - Step 57979: {'lr': 0.0003433224388136469, 'samples': 11131968, 'steps': 57978, 'loss/train': 1.2794603109359741} 08/30/2021 23:37:52 - INFO - __main__ - Step 57980: {'lr': 0.0003433175156473274, 'samples': 11132160, 'steps': 57979, 'loss/train': 0.64133620262146} 08/30/2021 23:37:53 - INFO - __main__ - Step 57981: {'lr': 0.0003433125924389604, 'samples': 11132352, 'steps': 57980, 'loss/train': 0.9147558808326721} 08/30/2021 23:37:54 - INFO - __main__ - Step 57982: {'lr': 0.00034330766918854827, 'samples': 11132544, 'steps': 57981, 'loss/train': 1.220578908920288} 08/30/2021 23:37:54 - INFO - __main__ - Step 57983: {'lr': 0.0003433027458960932, 'samples': 11132736, 'steps': 57982, 'loss/train': 0.924926221370697} 08/30/2021 23:37:54 - INFO - __main__ - Step 57984: {'lr': 0.00034329782256159724, 'samples': 11132928, 'steps': 57983, 'loss/train': 0.9357183575630188} 08/30/2021 23:37:55 - INFO - __main__ - Step 57985: {'lr': 0.00034329289918506276, 'samples': 11133120, 'steps': 57984, 'loss/train': 0.48311126232147217} 08/30/2021 23:37:56 - INFO - __main__ - Step 57986: {'lr': 0.0003432879757664919, 'samples': 11133312, 'steps': 57985, 'loss/train': 1.353756070137024} 08/30/2021 23:37:57 - INFO - __main__ - Step 57987: {'lr': 0.00034328305230588694, 'samples': 11133504, 'steps': 57986, 'loss/train': 1.4232285022735596} 08/30/2021 23:37:57 - INFO - __main__ - Step 57988: {'lr': 0.0003432781288032501, 'samples': 11133696, 'steps': 57987, 'loss/train': 1.144094467163086} 08/30/2021 23:37:57 - INFO - __main__ - Step 57989: {'lr': 0.00034327320525858357, 'samples': 11133888, 'steps': 57988, 'loss/train': 1.37705659866333} 08/30/2021 23:37:58 - INFO - __main__ - Step 57990: {'lr': 0.00034326828167188957, 'samples': 11134080, 'steps': 57989, 'loss/train': 1.6144942045211792} 08/30/2021 23:38:00 - INFO - __main__ - Step 57991: {'lr': 0.0003432633580431703, 'samples': 11134272, 'steps': 57990, 'loss/train': 0.28187695145606995} 08/30/2021 23:38:00 - INFO - __main__ - Step 57992: {'lr': 0.00034325843437242804, 'samples': 11134464, 'steps': 57991, 'loss/train': 1.456911325454712} 08/30/2021 23:38:01 - INFO - __main__ - Step 57993: {'lr': 0.0003432535106596649, 'samples': 11134656, 'steps': 57992, 'loss/train': 1.2609857320785522} 08/30/2021 23:38:01 - INFO - __main__ - Step 57994: {'lr': 0.00034324858690488324, 'samples': 11134848, 'steps': 57993, 'loss/train': 1.2759424448013306} 08/30/2021 23:38:01 - INFO - __main__ - Step 57995: {'lr': 0.0003432436631080851, 'samples': 11135040, 'steps': 57994, 'loss/train': 0.049883775413036346} 08/30/2021 23:38:03 - INFO - __main__ - Step 57996: {'lr': 0.00034323873926927296, 'samples': 11135232, 'steps': 57995, 'loss/train': 1.5175528526306152} 08/30/2021 23:38:04 - INFO - __main__ - Step 57997: {'lr': 0.00034323381538844884, 'samples': 11135424, 'steps': 57996, 'loss/train': 1.4376996755599976} 08/30/2021 23:38:04 - INFO - __main__ - Step 57998: {'lr': 0.0003432288914656149, 'samples': 11135616, 'steps': 57997, 'loss/train': 1.3499665260314941} 08/30/2021 23:38:04 - INFO - __main__ - Step 57999: {'lr': 0.00034322396750077354, 'samples': 11135808, 'steps': 57998, 'loss/train': 0.4412687420845032} 08/30/2021 23:38:05 - INFO - __main__ - Step 58000: {'lr': 0.0003432190434939269, 'samples': 11136000, 'steps': 57999, 'loss/train': 0.8755688071250916} 08/30/2021 23:38:05 - INFO - __main__ - Step 58001: {'lr': 0.0003432141194450772, 'samples': 11136192, 'steps': 58000, 'loss/train': 1.8476886749267578} 08/30/2021 23:38:06 - INFO - __main__ - Step 58002: {'lr': 0.0003432091953542267, 'samples': 11136384, 'steps': 58001, 'loss/train': 1.8664937019348145} 08/30/2021 23:38:07 - INFO - __main__ - Step 58003: {'lr': 0.00034320427122137745, 'samples': 11136576, 'steps': 58002, 'loss/train': 1.1659661531448364} 08/30/2021 23:38:07 - INFO - __main__ - Step 58004: {'lr': 0.0003431993470465319, 'samples': 11136768, 'steps': 58003, 'loss/train': 1.7013026475906372} 08/30/2021 23:38:08 - INFO - __main__ - Step 58005: {'lr': 0.00034319442282969206, 'samples': 11136960, 'steps': 58004, 'loss/train': 1.0599287748336792} 08/30/2021 23:38:08 - INFO - __main__ - Step 58006: {'lr': 0.0003431894985708603, 'samples': 11137152, 'steps': 58005, 'loss/train': 0.33406367897987366} 08/30/2021 23:38:10 - INFO - __main__ - Step 58007: {'lr': 0.0003431845742700388, 'samples': 11137344, 'steps': 58006, 'loss/train': 1.542755365371704} 08/30/2021 23:38:10 - INFO - __main__ - Step 58008: {'lr': 0.00034317964992722975, 'samples': 11137536, 'steps': 58007, 'loss/train': 1.7368049621582031} 08/30/2021 23:38:10 - INFO - __main__ - Step 58009: {'lr': 0.00034317472554243545, 'samples': 11137728, 'steps': 58008, 'loss/train': 1.5427500009536743} 08/30/2021 23:38:11 - INFO - __main__ - Step 58010: {'lr': 0.00034316980111565796, 'samples': 11137920, 'steps': 58009, 'loss/train': 0.0430852472782135} 08/30/2021 23:38:11 - INFO - __main__ - Step 58011: {'lr': 0.00034316487664689974, 'samples': 11138112, 'steps': 58010, 'loss/train': 0.23498308658599854} 08/30/2021 23:38:13 - INFO - __main__ - Step 58012: {'lr': 0.00034315995213616266, 'samples': 11138304, 'steps': 58011, 'loss/train': 1.2453813552856445} 08/30/2021 23:38:13 - INFO - __main__ - Step 58013: {'lr': 0.0003431550275834493, 'samples': 11138496, 'steps': 58012, 'loss/train': 1.4866456985473633} 08/30/2021 23:38:13 - INFO - __main__ - Step 58014: {'lr': 0.0003431501029887617, 'samples': 11138688, 'steps': 58013, 'loss/train': 0.29162171483039856} 08/30/2021 23:38:14 - INFO - __main__ - Step 58015: {'lr': 0.00034314517835210207, 'samples': 11138880, 'steps': 58014, 'loss/train': 1.2801259756088257} 08/30/2021 23:38:14 - INFO - __main__ - Step 58016: {'lr': 0.00034314025367347266, 'samples': 11139072, 'steps': 58015, 'loss/train': 1.3407461643218994} 08/30/2021 23:38:15 - INFO - __main__ - Step 58017: {'lr': 0.00034313532895287574, 'samples': 11139264, 'steps': 58016, 'loss/train': 1.511190414428711} 08/30/2021 23:38:16 - INFO - __main__ - Step 58018: {'lr': 0.00034313040419031336, 'samples': 11139456, 'steps': 58017, 'loss/train': 1.372041940689087} 08/30/2021 23:38:16 - INFO - __main__ - Step 58019: {'lr': 0.00034312547938578796, 'samples': 11139648, 'steps': 58018, 'loss/train': 0.784022331237793} 08/30/2021 23:38:17 - INFO - __main__ - Step 58020: {'lr': 0.0003431205545393016, 'samples': 11139840, 'steps': 58019, 'loss/train': 0.9925459027290344} 08/30/2021 23:38:17 - INFO - __main__ - Step 58021: {'lr': 0.00034311562965085664, 'samples': 11140032, 'steps': 58020, 'loss/train': 0.5568354725837708} 08/30/2021 23:38:19 - INFO - __main__ - Step 58022: {'lr': 0.0003431107047204552, 'samples': 11140224, 'steps': 58021, 'loss/train': 1.1519273519515991} 08/30/2021 23:38:19 - INFO - __main__ - Step 58023: {'lr': 0.00034310577974809944, 'samples': 11140416, 'steps': 58022, 'loss/train': 0.3109199106693268} 08/30/2021 23:38:20 - INFO - __main__ - Step 58024: {'lr': 0.0003431008547337917, 'samples': 11140608, 'steps': 58023, 'loss/train': 1.9225962162017822} 08/30/2021 23:38:20 - INFO - __main__ - Step 58025: {'lr': 0.0003430959296775341, 'samples': 11140800, 'steps': 58024, 'loss/train': 1.2298303842544556} 08/30/2021 23:38:20 - INFO - __main__ - Step 58026: {'lr': 0.00034309100457932895, 'samples': 11140992, 'steps': 58025, 'loss/train': 1.7570264339447021} 08/30/2021 23:38:22 - INFO - __main__ - Step 58027: {'lr': 0.0003430860794391784, 'samples': 11141184, 'steps': 58026, 'loss/train': 1.6850838661193848} 08/30/2021 23:38:22 - INFO - __main__ - Step 58028: {'lr': 0.00034308115425708477, 'samples': 11141376, 'steps': 58027, 'loss/train': 1.1719732284545898} 08/30/2021 23:38:23 - INFO - __main__ - Step 58029: {'lr': 0.0003430762290330501, 'samples': 11141568, 'steps': 58028, 'loss/train': 1.4778354167938232} 08/30/2021 23:38:23 - INFO - __main__ - Step 58030: {'lr': 0.00034307130376707684, 'samples': 11141760, 'steps': 58029, 'loss/train': 0.5399166345596313} 08/30/2021 23:38:23 - INFO - __main__ - Step 58031: {'lr': 0.000343066378459167, 'samples': 11141952, 'steps': 58030, 'loss/train': 0.8089847564697266} 08/30/2021 23:38:25 - INFO - __main__ - Step 58032: {'lr': 0.00034306145310932293, 'samples': 11142144, 'steps': 58031, 'loss/train': 1.3842999935150146} 08/30/2021 23:38:25 - INFO - __main__ - Step 58033: {'lr': 0.0003430565277175468, 'samples': 11142336, 'steps': 58032, 'loss/train': 2.5330135822296143} 08/30/2021 23:38:26 - INFO - __main__ - Step 58034: {'lr': 0.0003430516022838408, 'samples': 11142528, 'steps': 58033, 'loss/train': 1.1577410697937012} 08/30/2021 23:38:26 - INFO - __main__ - Step 58035: {'lr': 0.00034304667680820714, 'samples': 11142720, 'steps': 58034, 'loss/train': 1.5663037300109863} 08/30/2021 23:38:26 - INFO - __main__ - Step 58036: {'lr': 0.0003430417512906482, 'samples': 11142912, 'steps': 58035, 'loss/train': 0.8629599213600159} 08/30/2021 23:38:28 - INFO - __main__ - Step 58037: {'lr': 0.0003430368257311661, 'samples': 11143104, 'steps': 58036, 'loss/train': 0.31418338418006897} 08/30/2021 23:38:28 - INFO - __main__ - Step 58038: {'lr': 0.0003430319001297629, 'samples': 11143296, 'steps': 58037, 'loss/train': 1.5538597106933594} 08/30/2021 23:38:29 - INFO - __main__ - Step 58039: {'lr': 0.00034302697448644105, 'samples': 11143488, 'steps': 58038, 'loss/train': 1.2497516870498657} 08/30/2021 23:38:29 - INFO - __main__ - Step 58040: {'lr': 0.00034302204880120267, 'samples': 11143680, 'steps': 58039, 'loss/train': 1.4606926441192627} 08/30/2021 23:38:29 - INFO - __main__ - Step 58041: {'lr': 0.00034301712307404996, 'samples': 11143872, 'steps': 58040, 'loss/train': 0.864867091178894} 08/30/2021 23:38:30 - INFO - __main__ - Step 58042: {'lr': 0.00034301219730498524, 'samples': 11144064, 'steps': 58041, 'loss/train': 1.0711973905563354} 08/30/2021 23:38:32 - INFO - __main__ - Step 58043: {'lr': 0.00034300727149401064, 'samples': 11144256, 'steps': 58042, 'loss/train': 1.1949002742767334} 08/30/2021 23:38:32 - INFO - __main__ - Step 58044: {'lr': 0.00034300234564112837, 'samples': 11144448, 'steps': 58043, 'loss/train': 0.9533157348632812} 08/30/2021 23:38:33 - INFO - __main__ - Step 58045: {'lr': 0.0003429974197463407, 'samples': 11144640, 'steps': 58044, 'loss/train': 1.811410665512085} 08/30/2021 23:38:33 - INFO - __main__ - Step 58046: {'lr': 0.00034299249380964977, 'samples': 11144832, 'steps': 58045, 'loss/train': 1.1357166767120361} 08/30/2021 23:38:33 - INFO - __main__ - Step 58047: {'lr': 0.0003429875678310579, 'samples': 11145024, 'steps': 58046, 'loss/train': 0.8524813652038574} 08/30/2021 23:38:34 - INFO - __main__ - Step 58048: {'lr': 0.0003429826418105673, 'samples': 11145216, 'steps': 58047, 'loss/train': 0.9991881847381592} 08/30/2021 23:38:35 - INFO - __main__ - Step 58049: {'lr': 0.0003429777157481801, 'samples': 11145408, 'steps': 58048, 'loss/train': 0.9006020426750183} 08/30/2021 23:38:36 - INFO - __main__ - Step 58050: {'lr': 0.0003429727896438986, 'samples': 11145600, 'steps': 58049, 'loss/train': 1.8354930877685547} 08/30/2021 23:38:36 - INFO - __main__ - Step 58051: {'lr': 0.00034296786349772494, 'samples': 11145792, 'steps': 58050, 'loss/train': 1.11492121219635} 08/30/2021 23:38:37 - INFO - __main__ - Step 58052: {'lr': 0.0003429629373096615, 'samples': 11145984, 'steps': 58051, 'loss/train': 0.3116246163845062} 08/30/2021 23:38:37 - INFO - __main__ - Step 58053: {'lr': 0.0003429580110797103, 'samples': 11146176, 'steps': 58052, 'loss/train': 0.9807584881782532} 08/30/2021 23:38:38 - INFO - __main__ - Step 58054: {'lr': 0.0003429530848078737, 'samples': 11146368, 'steps': 58053, 'loss/train': 0.9870104193687439} 08/30/2021 23:38:39 - INFO - __main__ - Step 58055: {'lr': 0.0003429481584941538, 'samples': 11146560, 'steps': 58054, 'loss/train': 1.261991262435913} 08/30/2021 23:38:39 - INFO - __main__ - Step 58056: {'lr': 0.0003429432321385531, 'samples': 11146752, 'steps': 58055, 'loss/train': 0.07171699404716492} 08/30/2021 23:38:40 - INFO - __main__ - Step 58057: {'lr': 0.00034293830574107345, 'samples': 11146944, 'steps': 58056, 'loss/train': 1.0180670022964478} 08/30/2021 23:38:40 - INFO - __main__ - Step 58058: {'lr': 0.0003429333793017173, 'samples': 11147136, 'steps': 58057, 'loss/train': 0.8893603086471558} 08/30/2021 23:38:42 - INFO - __main__ - Step 58059: {'lr': 0.00034292845282048667, 'samples': 11147328, 'steps': 58058, 'loss/train': 1.1295841932296753} 08/30/2021 23:38:42 - INFO - __main__ - Step 58060: {'lr': 0.00034292352629738406, 'samples': 11147520, 'steps': 58059, 'loss/train': 0.6821733713150024} 08/30/2021 23:38:42 - INFO - __main__ - Step 58061: {'lr': 0.00034291859973241146, 'samples': 11147712, 'steps': 58060, 'loss/train': 1.295778751373291} 08/30/2021 23:38:43 - INFO - __main__ - Step 58062: {'lr': 0.0003429136731255712, 'samples': 11147904, 'steps': 58061, 'loss/train': 1.119515299797058} 08/30/2021 23:38:43 - INFO - __main__ - Step 58063: {'lr': 0.0003429087464768655, 'samples': 11148096, 'steps': 58062, 'loss/train': 4.730381488800049} 08/30/2021 23:38:45 - INFO - __main__ - Step 58064: {'lr': 0.00034290381978629655, 'samples': 11148288, 'steps': 58063, 'loss/train': 1.125172734260559} 08/30/2021 23:38:45 - INFO - __main__ - Step 58065: {'lr': 0.00034289889305386654, 'samples': 11148480, 'steps': 58064, 'loss/train': 1.5220035314559937} 08/30/2021 23:38:45 - INFO - __main__ - Step 58066: {'lr': 0.0003428939662795777, 'samples': 11148672, 'steps': 58065, 'loss/train': 1.163615107536316} 08/30/2021 23:38:46 - INFO - __main__ - Step 58067: {'lr': 0.0003428890394634323, 'samples': 11148864, 'steps': 58066, 'loss/train': 1.710109829902649} 08/30/2021 23:38:46 - INFO - __main__ - Step 58068: {'lr': 0.0003428841126054326, 'samples': 11149056, 'steps': 58067, 'loss/train': 1.0260673761367798} 08/30/2021 23:38:48 - INFO - __main__ - Step 58069: {'lr': 0.0003428791857055806, 'samples': 11149248, 'steps': 58068, 'loss/train': 1.0518882274627686} 08/30/2021 23:38:48 - INFO - __main__ - Step 58070: {'lr': 0.0003428742587638788, 'samples': 11149440, 'steps': 58069, 'loss/train': 1.4251055717468262} 08/30/2021 23:38:48 - INFO - __main__ - Step 58071: {'lr': 0.0003428693317803293, 'samples': 11149632, 'steps': 58070, 'loss/train': 1.4703441858291626} 08/30/2021 23:38:49 - INFO - __main__ - Step 58072: {'lr': 0.00034286440475493423, 'samples': 11149824, 'steps': 58071, 'loss/train': 0.5448579788208008} 08/30/2021 23:38:49 - INFO - __main__ - Step 58073: {'lr': 0.0003428594776876959, 'samples': 11150016, 'steps': 58072, 'loss/train': 1.0383001565933228} 08/30/2021 23:38:51 - INFO - __main__ - Step 58074: {'lr': 0.0003428545505786166, 'samples': 11150208, 'steps': 58073, 'loss/train': 1.2746344804763794} 08/30/2021 23:38:51 - INFO - __main__ - Step 58075: {'lr': 0.0003428496234276984, 'samples': 11150400, 'steps': 58074, 'loss/train': 1.3985235691070557} 08/30/2021 23:38:51 - INFO - __main__ - Step 58076: {'lr': 0.0003428446962349437, 'samples': 11150592, 'steps': 58075, 'loss/train': 1.4720648527145386} 08/30/2021 23:38:52 - INFO - __main__ - Step 58077: {'lr': 0.0003428397690003545, 'samples': 11150784, 'steps': 58076, 'loss/train': 1.631380558013916} 08/30/2021 23:38:52 - INFO - __main__ - Step 58078: {'lr': 0.00034283484172393315, 'samples': 11150976, 'steps': 58077, 'loss/train': 2.1027185916900635} 08/30/2021 23:38:52 - INFO - __main__ - Step 58079: {'lr': 0.0003428299144056818, 'samples': 11151168, 'steps': 58078, 'loss/train': 1.1716820001602173} 08/30/2021 23:38:54 - INFO - __main__ - Step 58080: {'lr': 0.00034282498704560284, 'samples': 11151360, 'steps': 58079, 'loss/train': 1.6995404958724976} 08/30/2021 23:38:54 - INFO - __main__ - Step 58081: {'lr': 0.0003428200596436983, 'samples': 11151552, 'steps': 58080, 'loss/train': 0.9309347867965698} 08/30/2021 23:38:55 - INFO - __main__ - Step 58082: {'lr': 0.00034281513219997054, 'samples': 11151744, 'steps': 58081, 'loss/train': 1.289864182472229} 08/30/2021 23:38:55 - INFO - __main__ - Step 58083: {'lr': 0.0003428102047144217, 'samples': 11151936, 'steps': 58082, 'loss/train': 1.2866483926773071} 08/30/2021 23:38:55 - INFO - __main__ - Step 58084: {'lr': 0.00034280527718705397, 'samples': 11152128, 'steps': 58083, 'loss/train': 1.8010245561599731} 08/30/2021 23:38:57 - INFO - __main__ - Step 58085: {'lr': 0.0003428003496178696, 'samples': 11152320, 'steps': 58084, 'loss/train': 1.253327488899231} 08/30/2021 23:38:58 - INFO - __main__ - Step 58086: {'lr': 0.00034279542200687087, 'samples': 11152512, 'steps': 58085, 'loss/train': 1.142523169517517} 08/30/2021 23:38:58 - INFO - __main__ - Step 58087: {'lr': 0.0003427904943540599, 'samples': 11152704, 'steps': 58086, 'loss/train': 0.3590722680091858} 08/30/2021 23:38:59 - INFO - __main__ - Step 58088: {'lr': 0.000342785566659439, 'samples': 11152896, 'steps': 58087, 'loss/train': 0.9169415235519409} 08/30/2021 23:38:59 - INFO - __main__ - Step 58089: {'lr': 0.00034278063892301036, 'samples': 11153088, 'steps': 58088, 'loss/train': 1.6978827714920044} 08/30/2021 23:39:00 - INFO - __main__ - Step 58090: {'lr': 0.00034277571114477623, 'samples': 11153280, 'steps': 58089, 'loss/train': 1.3921388387680054} 08/30/2021 23:39:01 - INFO - __main__ - Step 58091: {'lr': 0.0003427707833247388, 'samples': 11153472, 'steps': 58090, 'loss/train': 1.1821303367614746} 08/30/2021 23:39:01 - INFO - __main__ - Step 58092: {'lr': 0.0003427658554629002, 'samples': 11153664, 'steps': 58091, 'loss/train': 1.3248728513717651} 08/30/2021 23:39:02 - INFO - __main__ - Step 58093: {'lr': 0.00034276092755926275, 'samples': 11153856, 'steps': 58092, 'loss/train': 1.3602943420410156} 08/30/2021 23:39:02 - INFO - __main__ - Step 58094: {'lr': 0.0003427559996138287, 'samples': 11154048, 'steps': 58093, 'loss/train': 1.1875736713409424} 08/30/2021 23:39:04 - INFO - __main__ - Step 58095: {'lr': 0.00034275107162660024, 'samples': 11154240, 'steps': 58094, 'loss/train': 2.1526896953582764} 08/30/2021 23:39:04 - INFO - __main__ - Step 58096: {'lr': 0.0003427461435975796, 'samples': 11154432, 'steps': 58095, 'loss/train': 1.4964807033538818} 08/30/2021 23:39:04 - INFO - __main__ - Step 58097: {'lr': 0.0003427412155267688, 'samples': 11154624, 'steps': 58096, 'loss/train': 1.0730723142623901} 08/30/2021 23:39:05 - INFO - __main__ - Step 58098: {'lr': 0.00034273628741417043, 'samples': 11154816, 'steps': 58097, 'loss/train': 1.528784990310669} 08/30/2021 23:39:05 - INFO - __main__ - Step 58099: {'lr': 0.0003427313592597865, 'samples': 11155008, 'steps': 58098, 'loss/train': 1.0968055725097656} 08/30/2021 23:39:05 - INFO - __main__ - Step 58100: {'lr': 0.00034272643106361916, 'samples': 11155200, 'steps': 58099, 'loss/train': 0.8010907173156738} 08/30/2021 23:39:07 - INFO - __main__ - Step 58101: {'lr': 0.00034272150282567084, 'samples': 11155392, 'steps': 58100, 'loss/train': 0.555972695350647} 08/30/2021 23:39:08 - INFO - __main__ - Step 58102: {'lr': 0.00034271657454594355, 'samples': 11155584, 'steps': 58101, 'loss/train': 1.4861379861831665} 08/30/2021 23:39:08 - INFO - __main__ - Step 58103: {'lr': 0.0003427116462244396, 'samples': 11155776, 'steps': 58102, 'loss/train': 1.5160166025161743} 08/30/2021 23:39:09 - INFO - __main__ - Step 58104: {'lr': 0.00034270671786116127, 'samples': 11155968, 'steps': 58103, 'loss/train': 1.2457619905471802} 08/30/2021 23:39:09 - INFO - __main__ - Step 58105: {'lr': 0.00034270178945611067, 'samples': 11156160, 'steps': 58104, 'loss/train': 1.4042640924453735} 08/30/2021 23:39:10 - INFO - __main__ - Step 58106: {'lr': 0.00034269686100929015, 'samples': 11156352, 'steps': 58105, 'loss/train': 1.5230947732925415} 08/30/2021 23:39:11 - INFO - __main__ - Step 58107: {'lr': 0.0003426919325207018, 'samples': 11156544, 'steps': 58106, 'loss/train': 1.4654512405395508} 08/30/2021 23:39:11 - INFO - __main__ - Step 58108: {'lr': 0.0003426870039903479, 'samples': 11156736, 'steps': 58107, 'loss/train': 1.616666555404663} 08/30/2021 23:39:12 - INFO - __main__ - Step 58109: {'lr': 0.00034268207541823066, 'samples': 11156928, 'steps': 58108, 'loss/train': 0.9702644944190979} 08/30/2021 23:39:12 - INFO - __main__ - Step 58110: {'lr': 0.0003426771468043523, 'samples': 11157120, 'steps': 58109, 'loss/train': 1.0503275394439697} 08/30/2021 23:39:14 - INFO - __main__ - Step 58111: {'lr': 0.00034267221814871505, 'samples': 11157312, 'steps': 58110, 'loss/train': 1.0737967491149902} 08/30/2021 23:39:14 - INFO - __main__ - Step 58112: {'lr': 0.0003426672894513212, 'samples': 11157504, 'steps': 58111, 'loss/train': 0.12731744349002838} 08/30/2021 23:39:15 - INFO - __main__ - Step 58113: {'lr': 0.00034266236071217284, 'samples': 11157696, 'steps': 58112, 'loss/train': 0.9806870222091675} 08/30/2021 23:39:15 - INFO - __main__ - Step 58114: {'lr': 0.00034265743193127217, 'samples': 11157888, 'steps': 58113, 'loss/train': 1.0589088201522827} 08/30/2021 23:39:15 - INFO - __main__ - Step 58115: {'lr': 0.00034265250310862164, 'samples': 11158080, 'steps': 58114, 'loss/train': 1.0427807569503784} 08/30/2021 23:39:17 - INFO - __main__ - Step 58116: {'lr': 0.0003426475742442232, 'samples': 11158272, 'steps': 58115, 'loss/train': 0.7752166986465454} 08/30/2021 23:39:17 - INFO - __main__ - Step 58117: {'lr': 0.0003426426453380793, 'samples': 11158464, 'steps': 58116, 'loss/train': 1.6357320547103882} 08/30/2021 23:39:18 - INFO - __main__ - Step 58118: {'lr': 0.000342637716390192, 'samples': 11158656, 'steps': 58117, 'loss/train': 1.2135121822357178} 08/30/2021 23:39:18 - INFO - __main__ - Step 58119: {'lr': 0.0003426327874005636, 'samples': 11158848, 'steps': 58118, 'loss/train': 0.7144802808761597} 08/30/2021 23:39:18 - INFO - __main__ - Step 58120: {'lr': 0.00034262785836919617, 'samples': 11159040, 'steps': 58119, 'loss/train': 1.4486844539642334} 08/30/2021 23:39:19 - INFO - __main__ - Step 58121: {'lr': 0.00034262292929609217, 'samples': 11159232, 'steps': 58120, 'loss/train': 0.778864860534668} 08/30/2021 23:39:20 - INFO - __main__ - Step 58122: {'lr': 0.0003426180001812537, 'samples': 11159424, 'steps': 58121, 'loss/train': 1.2206759452819824} 08/30/2021 23:39:21 - INFO - __main__ - Step 58123: {'lr': 0.000342613071024683, 'samples': 11159616, 'steps': 58122, 'loss/train': 1.220629096031189} 08/30/2021 23:39:21 - INFO - __main__ - Step 58124: {'lr': 0.0003426081418263823, 'samples': 11159808, 'steps': 58123, 'loss/train': 0.3379243016242981} 08/30/2021 23:39:21 - INFO - __main__ - Step 58125: {'lr': 0.00034260321258635377, 'samples': 11160000, 'steps': 58124, 'loss/train': 1.3498263359069824} 08/30/2021 23:39:22 - INFO - __main__ - Step 58126: {'lr': 0.0003425982833045996, 'samples': 11160192, 'steps': 58125, 'loss/train': 1.2787257432937622} 08/30/2021 23:39:23 - INFO - __main__ - Step 58127: {'lr': 0.0003425933539811221, 'samples': 11160384, 'steps': 58126, 'loss/train': 1.6527032852172852} 08/30/2021 23:39:24 - INFO - __main__ - Step 58128: {'lr': 0.0003425884246159235, 'samples': 11160576, 'steps': 58127, 'loss/train': 1.2861199378967285} 08/30/2021 23:39:24 - INFO - __main__ - Step 58129: {'lr': 0.00034258349520900595, 'samples': 11160768, 'steps': 58128, 'loss/train': 1.4614211320877075} 08/30/2021 23:39:24 - INFO - __main__ - Step 58130: {'lr': 0.0003425785657603718, 'samples': 11160960, 'steps': 58129, 'loss/train': 0.9837599396705627} 08/30/2021 23:39:25 - INFO - __main__ - Step 58131: {'lr': 0.0003425736362700231, 'samples': 11161152, 'steps': 58130, 'loss/train': 2.0948567390441895} 08/30/2021 23:39:26 - INFO - __main__ - Step 58132: {'lr': 0.00034256870673796217, 'samples': 11161344, 'steps': 58131, 'loss/train': 1.559877872467041} 08/30/2021 23:39:27 - INFO - __main__ - Step 58133: {'lr': 0.0003425637771641911, 'samples': 11161536, 'steps': 58132, 'loss/train': 1.761301875114441} 08/30/2021 23:39:27 - INFO - __main__ - Step 58134: {'lr': 0.00034255884754871233, 'samples': 11161728, 'steps': 58133, 'loss/train': 0.8404830098152161} 08/30/2021 23:39:27 - INFO - __main__ - Step 58135: {'lr': 0.000342553917891528, 'samples': 11161920, 'steps': 58134, 'loss/train': 1.1599462032318115} 08/30/2021 23:39:28 - INFO - __main__ - Step 58136: {'lr': 0.0003425489881926402, 'samples': 11162112, 'steps': 58135, 'loss/train': 1.2159727811813354} 08/30/2021 23:39:29 - INFO - __main__ - Step 58137: {'lr': 0.0003425440584520514, 'samples': 11162304, 'steps': 58136, 'loss/train': 1.6771095991134644} 08/30/2021 23:39:30 - INFO - __main__ - Step 58138: {'lr': 0.00034253912866976353, 'samples': 11162496, 'steps': 58137, 'loss/train': 1.4760503768920898} 08/30/2021 23:39:30 - INFO - __main__ - Step 58139: {'lr': 0.000342534198845779, 'samples': 11162688, 'steps': 58138, 'loss/train': 1.6011906862258911} 08/30/2021 23:39:30 - INFO - __main__ - Step 58140: {'lr': 0.0003425292689801, 'samples': 11162880, 'steps': 58139, 'loss/train': 1.0824955701828003} 08/30/2021 23:39:31 - INFO - __main__ - Step 58141: {'lr': 0.00034252433907272875, 'samples': 11163072, 'steps': 58140, 'loss/train': 1.5095313787460327} 08/30/2021 23:39:31 - INFO - __main__ - Step 58142: {'lr': 0.0003425194091236674, 'samples': 11163264, 'steps': 58141, 'loss/train': 1.1028271913528442} 08/30/2021 23:39:33 - INFO - __main__ - Step 58143: {'lr': 0.0003425144791329183, 'samples': 11163456, 'steps': 58142, 'loss/train': 2.8132710456848145} 08/30/2021 23:39:33 - INFO - __main__ - Step 58144: {'lr': 0.00034250954910048357, 'samples': 11163648, 'steps': 58143, 'loss/train': 1.0607272386550903} 08/30/2021 23:39:33 - INFO - __main__ - Step 58145: {'lr': 0.0003425046190263655, 'samples': 11163840, 'steps': 58144, 'loss/train': 0.9200980067253113} 08/30/2021 23:39:34 - INFO - __main__ - Step 58146: {'lr': 0.00034249968891056625, 'samples': 11164032, 'steps': 58145, 'loss/train': 0.7144595980644226} 08/30/2021 23:39:34 - INFO - __main__ - Step 58147: {'lr': 0.00034249475875308813, 'samples': 11164224, 'steps': 58146, 'loss/train': 2.6284947395324707} 08/30/2021 23:39:36 - INFO - __main__ - Step 58148: {'lr': 0.00034248982855393317, 'samples': 11164416, 'steps': 58147, 'loss/train': 1.1523993015289307} 08/30/2021 23:39:36 - INFO - __main__ - Step 58149: {'lr': 0.0003424848983131038, 'samples': 11164608, 'steps': 58148, 'loss/train': 0.9722750186920166} 08/30/2021 23:39:36 - INFO - __main__ - Step 58150: {'lr': 0.0003424799680306022, 'samples': 11164800, 'steps': 58149, 'loss/train': 1.4469280242919922} 08/30/2021 23:39:37 - INFO - __main__ - Step 58151: {'lr': 0.0003424750377064305, 'samples': 11164992, 'steps': 58150, 'loss/train': 1.351000189781189} 08/30/2021 23:39:37 - INFO - __main__ - Step 58152: {'lr': 0.000342470107340591, 'samples': 11165184, 'steps': 58151, 'loss/train': 1.644476056098938} 08/30/2021 23:39:40 - INFO - __main__ - Step 58153: {'lr': 0.0003424651769330859, 'samples': 11165376, 'steps': 58152, 'loss/train': 0.9190403819084167} 08/30/2021 23:39:40 - INFO - __main__ - Step 58154: {'lr': 0.0003424602464839173, 'samples': 11165568, 'steps': 58153, 'loss/train': 1.2978562116622925} 08/30/2021 23:39:40 - INFO - __main__ - Step 58155: {'lr': 0.0003424553159930877, 'samples': 11165760, 'steps': 58154, 'loss/train': 0.713495671749115} 08/30/2021 23:39:41 - INFO - __main__ - Step 58156: {'lr': 0.00034245038546059904, 'samples': 11165952, 'steps': 58155, 'loss/train': 1.877809762954712} 08/30/2021 23:39:41 - INFO - __main__ - Step 58157: {'lr': 0.0003424454548864538, 'samples': 11166144, 'steps': 58156, 'loss/train': 0.409132182598114} 08/30/2021 23:39:43 - INFO - __main__ - Step 58158: {'lr': 0.00034244052427065397, 'samples': 11166336, 'steps': 58157, 'loss/train': 1.1318840980529785} 08/30/2021 23:39:43 - INFO - __main__ - Step 58159: {'lr': 0.00034243559361320187, 'samples': 11166528, 'steps': 58158, 'loss/train': 1.2086416482925415} 08/30/2021 23:39:44 - INFO - __main__ - Step 58160: {'lr': 0.00034243066291409977, 'samples': 11166720, 'steps': 58159, 'loss/train': 1.0776487588882446} 08/30/2021 23:39:44 - INFO - __main__ - Step 58161: {'lr': 0.0003424257321733497, 'samples': 11166912, 'steps': 58160, 'loss/train': 1.3231314420700073} 08/30/2021 23:39:44 - INFO - __main__ - Step 58162: {'lr': 0.00034242080139095416, 'samples': 11167104, 'steps': 58161, 'loss/train': 0.48137930035591125} 08/30/2021 23:39:45 - INFO - __main__ - Step 58163: {'lr': 0.0003424158705669152, 'samples': 11167296, 'steps': 58162, 'loss/train': 1.2340216636657715} 08/30/2021 23:39:46 - INFO - __main__ - Step 58164: {'lr': 0.0003424109397012351, 'samples': 11167488, 'steps': 58163, 'loss/train': 1.5349849462509155} 08/30/2021 23:39:47 - INFO - __main__ - Step 58165: {'lr': 0.000342406008793916, 'samples': 11167680, 'steps': 58164, 'loss/train': 1.677738070487976} 08/30/2021 23:39:47 - INFO - __main__ - Step 58166: {'lr': 0.00034240107784496023, 'samples': 11167872, 'steps': 58165, 'loss/train': 0.9596205949783325} 08/30/2021 23:39:48 - INFO - __main__ - Step 58167: {'lr': 0.00034239614685436994, 'samples': 11168064, 'steps': 58166, 'loss/train': 0.029650403186678886} 08/30/2021 23:39:48 - INFO - __main__ - Step 58168: {'lr': 0.0003423912158221473, 'samples': 11168256, 'steps': 58167, 'loss/train': 0.7860967516899109} 08/30/2021 23:39:48 - INFO - __main__ - Step 58169: {'lr': 0.0003423862847482947, 'samples': 11168448, 'steps': 58168, 'loss/train': 1.541067123413086} 08/30/2021 23:39:50 - INFO - __main__ - Step 58170: {'lr': 0.0003423813536328143, 'samples': 11168640, 'steps': 58169, 'loss/train': 1.5356074571609497} 08/30/2021 23:39:50 - INFO - __main__ - Step 58171: {'lr': 0.00034237642247570815, 'samples': 11168832, 'steps': 58170, 'loss/train': 1.2269033193588257} 08/30/2021 23:39:51 - INFO - __main__ - Step 58172: {'lr': 0.0003423714912769787, 'samples': 11169024, 'steps': 58171, 'loss/train': 1.423087239265442} 08/30/2021 23:39:51 - INFO - __main__ - Step 58173: {'lr': 0.000342366560036628, 'samples': 11169216, 'steps': 58172, 'loss/train': 1.5837994813919067} 08/30/2021 23:39:52 - INFO - __main__ - Step 58174: {'lr': 0.0003423616287546585, 'samples': 11169408, 'steps': 58173, 'loss/train': 1.5073819160461426} 08/30/2021 23:39:53 - INFO - __main__ - Step 58175: {'lr': 0.00034235669743107214, 'samples': 11169600, 'steps': 58174, 'loss/train': 0.06718748062849045} 08/30/2021 23:39:54 - INFO - __main__ - Step 58176: {'lr': 0.0003423517660658713, 'samples': 11169792, 'steps': 58175, 'loss/train': 1.3589560985565186} 08/30/2021 23:39:54 - INFO - __main__ - Step 58177: {'lr': 0.0003423468346590583, 'samples': 11169984, 'steps': 58176, 'loss/train': 1.500417947769165} 08/30/2021 23:39:54 - INFO - __main__ - Step 58178: {'lr': 0.00034234190321063516, 'samples': 11170176, 'steps': 58177, 'loss/train': 1.2618979215621948} 08/30/2021 23:39:55 - INFO - __main__ - Step 58179: {'lr': 0.00034233697172060415, 'samples': 11170368, 'steps': 58178, 'loss/train': 1.6957918405532837} 08/30/2021 23:39:55 - INFO - __main__ - Step 58180: {'lr': 0.00034233204018896754, 'samples': 11170560, 'steps': 58179, 'loss/train': 1.4949250221252441} 08/30/2021 23:39:56 - INFO - __main__ - Step 58181: {'lr': 0.00034232710861572754, 'samples': 11170752, 'steps': 58180, 'loss/train': 1.021200180053711} 08/30/2021 23:39:57 - INFO - __main__ - Step 58182: {'lr': 0.0003423221770008864, 'samples': 11170944, 'steps': 58181, 'loss/train': 1.15692138671875} 08/30/2021 23:39:57 - INFO - __main__ - Step 58183: {'lr': 0.0003423172453444462, 'samples': 11171136, 'steps': 58182, 'loss/train': 1.4904612302780151} 08/30/2021 23:39:58 - INFO - __main__ - Step 58184: {'lr': 0.00034231231364640946, 'samples': 11171328, 'steps': 58183, 'loss/train': 1.2064727544784546} 08/30/2021 23:39:58 - INFO - __main__ - Step 58185: {'lr': 0.0003423073819067781, 'samples': 11171520, 'steps': 58184, 'loss/train': 1.015325665473938} 08/30/2021 23:40:00 - INFO - __main__ - Step 58186: {'lr': 0.00034230245012555445, 'samples': 11171712, 'steps': 58185, 'loss/train': 1.2468750476837158} 08/30/2021 23:40:00 - INFO - __main__ - Step 58187: {'lr': 0.00034229751830274077, 'samples': 11171904, 'steps': 58186, 'loss/train': 1.3481324911117554} 08/30/2021 23:40:00 - INFO - __main__ - Step 58188: {'lr': 0.0003422925864383392, 'samples': 11172096, 'steps': 58187, 'loss/train': 1.331291675567627} 08/30/2021 23:40:01 - INFO - __main__ - Step 58189: {'lr': 0.00034228765453235213, 'samples': 11172288, 'steps': 58188, 'loss/train': 1.913342833518982} 08/30/2021 23:40:01 - INFO - __main__ - Step 58190: {'lr': 0.0003422827225847816, 'samples': 11172480, 'steps': 58189, 'loss/train': 1.7874317169189453} 08/30/2021 23:40:02 - INFO - __main__ - Step 58191: {'lr': 0.0003422777905956299, 'samples': 11172672, 'steps': 58190, 'loss/train': 1.4271373748779297} 08/30/2021 23:40:03 - INFO - __main__ - Step 58192: {'lr': 0.0003422728585648992, 'samples': 11172864, 'steps': 58191, 'loss/train': 0.4440106451511383} 08/30/2021 23:40:03 - INFO - __main__ - Step 58193: {'lr': 0.00034226792649259184, 'samples': 11173056, 'steps': 58192, 'loss/train': 0.7758225202560425} 08/30/2021 23:40:04 - INFO - __main__ - Step 58194: {'lr': 0.00034226299437870993, 'samples': 11173248, 'steps': 58193, 'loss/train': 1.1746567487716675} 08/30/2021 23:40:04 - INFO - __main__ - Step 58195: {'lr': 0.0003422580622232558, 'samples': 11173440, 'steps': 58194, 'loss/train': 1.041857361793518} 08/30/2021 23:40:05 - INFO - __main__ - Step 58196: {'lr': 0.0003422531300262316, 'samples': 11173632, 'steps': 58195, 'loss/train': 0.7676185965538025} 08/30/2021 23:40:06 - INFO - __main__ - Step 58197: {'lr': 0.00034224819778763953, 'samples': 11173824, 'steps': 58196, 'loss/train': 0.8987600207328796} 08/30/2021 23:40:06 - INFO - __main__ - Step 58198: {'lr': 0.0003422432655074819, 'samples': 11174016, 'steps': 58197, 'loss/train': 1.578316569328308} 08/30/2021 23:40:07 - INFO - __main__ - Step 58199: {'lr': 0.0003422383331857608, 'samples': 11174208, 'steps': 58198, 'loss/train': 1.4160542488098145} 08/30/2021 23:40:07 - INFO - __main__ - Step 58200: {'lr': 0.00034223340082247856, 'samples': 11174400, 'steps': 58199, 'loss/train': 1.7254291772842407} 08/30/2021 23:40:09 - INFO - __main__ - Step 58201: {'lr': 0.0003422284684176374, 'samples': 11174592, 'steps': 58200, 'loss/train': 2.102698564529419} 08/30/2021 23:40:09 - INFO - __main__ - Step 58202: {'lr': 0.00034222353597123946, 'samples': 11174784, 'steps': 58201, 'loss/train': 1.5819694995880127} 08/30/2021 23:40:10 - INFO - __main__ - Step 58203: {'lr': 0.00034221860348328703, 'samples': 11174976, 'steps': 58202, 'loss/train': 0.9942245483398438} 08/30/2021 23:40:10 - INFO - __main__ - Step 58204: {'lr': 0.0003422136709537824, 'samples': 11175168, 'steps': 58203, 'loss/train': 0.6993240118026733} 08/30/2021 23:40:10 - INFO - __main__ - Step 58205: {'lr': 0.00034220873838272767, 'samples': 11175360, 'steps': 58204, 'loss/train': 0.020276373252272606} 08/30/2021 23:40:11 - INFO - __main__ - Step 58206: {'lr': 0.00034220380577012506, 'samples': 11175552, 'steps': 58205, 'loss/train': 1.6438995599746704} 08/30/2021 23:40:13 - INFO - __main__ - Step 58207: {'lr': 0.00034219887311597686, 'samples': 11175744, 'steps': 58206, 'loss/train': 0.9736303687095642} 08/30/2021 23:40:13 - INFO - __main__ - Step 58208: {'lr': 0.0003421939404202853, 'samples': 11175936, 'steps': 58207, 'loss/train': 1.4000822305679321} 08/30/2021 23:40:14 - INFO - __main__ - Step 58209: {'lr': 0.0003421890076830525, 'samples': 11176128, 'steps': 58208, 'loss/train': 1.3235080242156982} 08/30/2021 23:40:14 - INFO - __main__ - Step 58210: {'lr': 0.00034218407490428085, 'samples': 11176320, 'steps': 58209, 'loss/train': 1.377208948135376} 08/30/2021 23:40:14 - INFO - __main__ - Step 58211: {'lr': 0.0003421791420839724, 'samples': 11176512, 'steps': 58210, 'loss/train': 2.112405776977539} 08/30/2021 23:40:15 - INFO - __main__ - Step 58212: {'lr': 0.00034217420922212947, 'samples': 11176704, 'steps': 58211, 'loss/train': 1.55793297290802} 08/30/2021 23:40:16 - INFO - __main__ - Step 58213: {'lr': 0.0003421692763187543, 'samples': 11176896, 'steps': 58212, 'loss/train': 1.438162922859192} 08/30/2021 23:40:17 - INFO - __main__ - Step 58214: {'lr': 0.00034216434337384905, 'samples': 11177088, 'steps': 58213, 'loss/train': 1.5120490789413452} 08/30/2021 23:40:17 - INFO - __main__ - Step 58215: {'lr': 0.000342159410387416, 'samples': 11177280, 'steps': 58214, 'loss/train': 1.5225783586502075} 08/30/2021 23:40:18 - INFO - __main__ - Step 58216: {'lr': 0.0003421544773594573, 'samples': 11177472, 'steps': 58215, 'loss/train': 0.18304598331451416} 08/30/2021 23:40:18 - INFO - __main__ - Step 58217: {'lr': 0.0003421495442899753, 'samples': 11177664, 'steps': 58216, 'loss/train': 0.8368443250656128} 08/30/2021 23:40:20 - INFO - __main__ - Step 58218: {'lr': 0.0003421446111789721, 'samples': 11177856, 'steps': 58217, 'loss/train': 0.056102342903614044} 08/30/2021 23:40:20 - INFO - __main__ - Step 58219: {'lr': 0.00034213967802644986, 'samples': 11178048, 'steps': 58218, 'loss/train': 0.07792620360851288} 08/30/2021 23:40:21 - INFO - __main__ - Step 58220: {'lr': 0.000342134744832411, 'samples': 11178240, 'steps': 58219, 'loss/train': 1.8799257278442383} 08/30/2021 23:40:21 - INFO - __main__ - Step 58221: {'lr': 0.0003421298115968576, 'samples': 11178432, 'steps': 58220, 'loss/train': 1.6056959629058838} 08/30/2021 23:40:21 - INFO - __main__ - Step 58222: {'lr': 0.0003421248783197919, 'samples': 11178624, 'steps': 58221, 'loss/train': 1.4657942056655884} 08/30/2021 23:40:23 - INFO - __main__ - Step 58223: {'lr': 0.0003421199450012162, 'samples': 11178816, 'steps': 58222, 'loss/train': 1.5119634866714478} 08/30/2021 23:40:23 - INFO - __main__ - Step 58224: {'lr': 0.00034211501164113276, 'samples': 11179008, 'steps': 58223, 'loss/train': 0.9850744009017944} 08/30/2021 23:40:24 - INFO - __main__ - Step 58225: {'lr': 0.0003421100782395436, 'samples': 11179200, 'steps': 58224, 'loss/train': 1.5450838804244995} 08/30/2021 23:40:24 - INFO - __main__ - Step 58226: {'lr': 0.000342105144796451, 'samples': 11179392, 'steps': 58225, 'loss/train': 1.1443885564804077} 08/30/2021 23:40:24 - INFO - __main__ - Step 58227: {'lr': 0.0003421002113118574, 'samples': 11179584, 'steps': 58226, 'loss/train': 0.7151418924331665} 08/30/2021 23:40:26 - INFO - __main__ - Step 58228: {'lr': 0.00034209527778576477, 'samples': 11179776, 'steps': 58227, 'loss/train': 1.2697087526321411} 08/30/2021 23:40:26 - INFO - __main__ - Step 58229: {'lr': 0.0003420903442181755, 'samples': 11179968, 'steps': 58228, 'loss/train': 1.485098123550415} 08/30/2021 23:40:27 - INFO - __main__ - Step 58230: {'lr': 0.0003420854106090917, 'samples': 11180160, 'steps': 58229, 'loss/train': 1.1717568635940552} 08/30/2021 23:40:27 - INFO - __main__ - Step 58231: {'lr': 0.00034208047695851563, 'samples': 11180352, 'steps': 58230, 'loss/train': 1.856194257736206} 08/30/2021 23:40:27 - INFO - __main__ - Step 58232: {'lr': 0.0003420755432664495, 'samples': 11180544, 'steps': 58231, 'loss/train': 1.4531867504119873} 08/30/2021 23:40:29 - INFO - __main__ - Step 58233: {'lr': 0.0003420706095328956, 'samples': 11180736, 'steps': 58232, 'loss/train': 1.579209566116333} 08/30/2021 23:40:29 - INFO - __main__ - Step 58234: {'lr': 0.0003420656757578561, 'samples': 11180928, 'steps': 58233, 'loss/train': 1.068538784980774} 08/30/2021 23:40:30 - INFO - __main__ - Step 58235: {'lr': 0.00034206074194133323, 'samples': 11181120, 'steps': 58234, 'loss/train': 1.6517542600631714} 08/30/2021 23:40:30 - INFO - __main__ - Step 58236: {'lr': 0.00034205580808332916, 'samples': 11181312, 'steps': 58235, 'loss/train': 1.0482072830200195} 08/30/2021 23:40:30 - INFO - __main__ - Step 58237: {'lr': 0.0003420508741838462, 'samples': 11181504, 'steps': 58236, 'loss/train': 0.9779049158096313} 08/30/2021 23:40:32 - INFO - __main__ - Step 58238: {'lr': 0.0003420459402428865, 'samples': 11181696, 'steps': 58237, 'loss/train': 0.3572382628917694} 08/30/2021 23:40:32 - INFO - __main__ - Step 58239: {'lr': 0.00034204100626045235, 'samples': 11181888, 'steps': 58238, 'loss/train': 0.6780773997306824} 08/30/2021 23:40:33 - INFO - __main__ - Step 58240: {'lr': 0.00034203607223654594, 'samples': 11182080, 'steps': 58239, 'loss/train': 1.6863313913345337} 08/30/2021 23:40:33 - INFO - __main__ - Step 58241: {'lr': 0.00034203113817116957, 'samples': 11182272, 'steps': 58240, 'loss/train': 0.5363484621047974} 08/30/2021 23:40:33 - INFO - __main__ - Step 58242: {'lr': 0.0003420262040643253, 'samples': 11182464, 'steps': 58241, 'loss/train': 1.9159166812896729} 08/30/2021 23:40:35 - INFO - __main__ - Step 58243: {'lr': 0.0003420212699160154, 'samples': 11182656, 'steps': 58242, 'loss/train': 1.2834962606430054} 08/30/2021 23:40:35 - INFO - __main__ - Step 58244: {'lr': 0.00034201633572624216, 'samples': 11182848, 'steps': 58243, 'loss/train': 0.8463221788406372} 08/30/2021 23:40:36 - INFO - __main__ - Step 58245: {'lr': 0.00034201140149500784, 'samples': 11183040, 'steps': 58244, 'loss/train': 1.6710035800933838} 08/30/2021 23:40:36 - INFO - __main__ - Step 58246: {'lr': 0.0003420064672223146, 'samples': 11183232, 'steps': 58245, 'loss/train': 1.238175630569458} 08/30/2021 23:40:36 - INFO - __main__ - Step 58247: {'lr': 0.0003420015329081647, 'samples': 11183424, 'steps': 58246, 'loss/train': 0.28725066781044006} 08/30/2021 23:40:38 - INFO - __main__ - Step 58248: {'lr': 0.00034199659855256023, 'samples': 11183616, 'steps': 58247, 'loss/train': 1.1709293127059937} 08/30/2021 23:40:38 - INFO - __main__ - Step 58249: {'lr': 0.00034199166415550353, 'samples': 11183808, 'steps': 58248, 'loss/train': 1.6371533870697021} 08/30/2021 23:40:38 - INFO - __main__ - Step 58250: {'lr': 0.0003419867297169968, 'samples': 11184000, 'steps': 58249, 'loss/train': 1.169621467590332} 08/30/2021 23:40:39 - INFO - __main__ - Step 58251: {'lr': 0.00034198179523704233, 'samples': 11184192, 'steps': 58250, 'loss/train': 0.8364565968513489} 08/30/2021 23:40:39 - INFO - __main__ - Step 58252: {'lr': 0.0003419768607156423, 'samples': 11184384, 'steps': 58251, 'loss/train': 1.2661550045013428} 08/30/2021 23:40:40 - INFO - __main__ - Step 58253: {'lr': 0.0003419719261527988, 'samples': 11184576, 'steps': 58252, 'loss/train': 1.004204511642456} 08/30/2021 23:40:41 - INFO - __main__ - Step 58254: {'lr': 0.0003419669915485142, 'samples': 11184768, 'steps': 58253, 'loss/train': 0.036508191376924515} 08/30/2021 23:40:41 - INFO - __main__ - Step 58255: {'lr': 0.00034196205690279076, 'samples': 11184960, 'steps': 58254, 'loss/train': 1.972454309463501} 08/30/2021 23:40:42 - INFO - __main__ - Step 58256: {'lr': 0.00034195712221563057, 'samples': 11185152, 'steps': 58255, 'loss/train': 1.0577110052108765} 08/30/2021 23:40:42 - INFO - __main__ - Step 58257: {'lr': 0.00034195218748703596, 'samples': 11185344, 'steps': 58256, 'loss/train': 1.7430599927902222} 08/30/2021 23:40:42 - INFO - __main__ - Step 58258: {'lr': 0.00034194725271700915, 'samples': 11185536, 'steps': 58257, 'loss/train': 1.645064353942871} 08/30/2021 23:40:44 - INFO - __main__ - Step 58259: {'lr': 0.0003419423179055523, 'samples': 11185728, 'steps': 58258, 'loss/train': 0.9579575657844543} 08/30/2021 23:40:44 - INFO - __main__ - Step 58260: {'lr': 0.0003419373830526676, 'samples': 11185920, 'steps': 58259, 'loss/train': 0.7023940682411194} 08/30/2021 23:40:45 - INFO - __main__ - Step 58261: {'lr': 0.0003419324481583574, 'samples': 11186112, 'steps': 58260, 'loss/train': 1.455538272857666} 08/30/2021 23:40:45 - INFO - __main__ - Step 58262: {'lr': 0.00034192751322262375, 'samples': 11186304, 'steps': 58261, 'loss/train': 1.2937004566192627} 08/30/2021 23:40:45 - INFO - __main__ - Step 58263: {'lr': 0.0003419225782454691, 'samples': 11186496, 'steps': 58262, 'loss/train': 0.028503045439720154} 08/30/2021 23:40:48 - INFO - __main__ - Step 58264: {'lr': 0.00034191764322689553, 'samples': 11186688, 'steps': 58263, 'loss/train': 1.3785802125930786} 08/30/2021 23:40:48 - INFO - __main__ - Step 58265: {'lr': 0.00034191270816690526, 'samples': 11186880, 'steps': 58264, 'loss/train': 1.3031697273254395} 08/30/2021 23:40:49 - INFO - __main__ - Step 58266: {'lr': 0.0003419077730655006, 'samples': 11187072, 'steps': 58265, 'loss/train': 1.474822998046875} 08/30/2021 23:40:49 - INFO - __main__ - Step 58267: {'lr': 0.00034190283792268365, 'samples': 11187264, 'steps': 58266, 'loss/train': 1.697913646697998} 08/30/2021 23:40:49 - INFO - __main__ - Step 58268: {'lr': 0.0003418979027384567, 'samples': 11187456, 'steps': 58267, 'loss/train': 1.3406145572662354} 08/30/2021 23:40:51 - INFO - __main__ - Step 58269: {'lr': 0.00034189296751282203, 'samples': 11187648, 'steps': 58268, 'loss/train': 0.7187969088554382} 08/30/2021 23:40:51 - INFO - __main__ - Step 58270: {'lr': 0.0003418880322457817, 'samples': 11187840, 'steps': 58269, 'loss/train': 1.5781772136688232} 08/30/2021 23:40:52 - INFO - __main__ - Step 58271: {'lr': 0.0003418830969373382, 'samples': 11188032, 'steps': 58270, 'loss/train': 1.324567437171936} 08/30/2021 23:40:52 - INFO - __main__ - Step 58272: {'lr': 0.00034187816158749354, 'samples': 11188224, 'steps': 58271, 'loss/train': 1.1467859745025635} 08/30/2021 23:40:52 - INFO - __main__ - Step 58273: {'lr': 0.00034187322619624996, 'samples': 11188416, 'steps': 58272, 'loss/train': 1.5315423011779785} 08/30/2021 23:40:54 - INFO - __main__ - Step 58274: {'lr': 0.0003418682907636097, 'samples': 11188608, 'steps': 58273, 'loss/train': 0.8884255290031433} 08/30/2021 23:40:54 - INFO - __main__ - Step 58275: {'lr': 0.000341863355289575, 'samples': 11188800, 'steps': 58274, 'loss/train': 1.6121199131011963} 08/30/2021 23:40:55 - INFO - __main__ - Step 58276: {'lr': 0.0003418584197741481, 'samples': 11188992, 'steps': 58275, 'loss/train': 1.1168267726898193} 08/30/2021 23:40:55 - INFO - __main__ - Step 58277: {'lr': 0.00034185348421733125, 'samples': 11189184, 'steps': 58276, 'loss/train': 1.1643896102905273} 08/30/2021 23:40:55 - INFO - __main__ - Step 58278: {'lr': 0.0003418485486191267, 'samples': 11189376, 'steps': 58277, 'loss/train': 0.6503121256828308} 08/30/2021 23:40:56 - INFO - __main__ - Step 58279: {'lr': 0.0003418436129795365, 'samples': 11189568, 'steps': 58278, 'loss/train': 0.6299277544021606} 08/30/2021 23:40:58 - INFO - __main__ - Step 58280: {'lr': 0.000341838677298563, 'samples': 11189760, 'steps': 58279, 'loss/train': 1.1273937225341797} 08/30/2021 23:40:58 - INFO - __main__ - Step 58281: {'lr': 0.00034183374157620847, 'samples': 11189952, 'steps': 58280, 'loss/train': 1.6415847539901733} 08/30/2021 23:40:59 - INFO - __main__ - Step 58282: {'lr': 0.000341828805812475, 'samples': 11190144, 'steps': 58281, 'loss/train': 0.8988140821456909} 08/30/2021 23:40:59 - INFO - __main__ - Step 58283: {'lr': 0.0003418238700073649, 'samples': 11190336, 'steps': 58282, 'loss/train': 1.3404672145843506} 08/30/2021 23:40:59 - INFO - __main__ - Step 58284: {'lr': 0.0003418189341608804, 'samples': 11190528, 'steps': 58283, 'loss/train': 0.4190874397754669} 08/30/2021 23:41:00 - INFO - __main__ - Step 58285: {'lr': 0.0003418139982730237, 'samples': 11190720, 'steps': 58284, 'loss/train': 0.07678170502185822} 08/30/2021 23:41:02 - INFO - __main__ - Step 58286: {'lr': 0.0003418090623437971, 'samples': 11190912, 'steps': 58285, 'loss/train': 0.20437584817409515} 08/30/2021 23:41:02 - INFO - __main__ - Step 58287: {'lr': 0.00034180412637320267, 'samples': 11191104, 'steps': 58286, 'loss/train': 0.07539796084165573} 08/30/2021 23:41:02 - INFO - __main__ - Step 58288: {'lr': 0.0003417991903612427, 'samples': 11191296, 'steps': 58287, 'loss/train': 1.7511036396026611} 08/30/2021 23:41:03 - INFO - __main__ - Step 58289: {'lr': 0.0003417942543079195, 'samples': 11191488, 'steps': 58288, 'loss/train': 1.6025481224060059} 08/30/2021 23:41:03 - INFO - __main__ - Step 58290: {'lr': 0.00034178931821323517, 'samples': 11191680, 'steps': 58289, 'loss/train': 1.0312312841415405} 08/30/2021 23:41:05 - INFO - __main__ - Step 58291: {'lr': 0.0003417843820771921, 'samples': 11191872, 'steps': 58290, 'loss/train': 1.3161014318466187} 08/30/2021 23:41:05 - INFO - __main__ - Step 58292: {'lr': 0.00034177944589979225, 'samples': 11192064, 'steps': 58291, 'loss/train': 0.8433822393417358} 08/30/2021 23:41:05 - INFO - __main__ - Step 58293: {'lr': 0.0003417745096810381, 'samples': 11192256, 'steps': 58292, 'loss/train': 1.5228179693222046} 08/30/2021 23:41:06 - INFO - __main__ - Step 58294: {'lr': 0.00034176957342093174, 'samples': 11192448, 'steps': 58293, 'loss/train': 1.3527491092681885} 08/30/2021 23:41:06 - INFO - __main__ - Step 58295: {'lr': 0.0003417646371194754, 'samples': 11192640, 'steps': 58294, 'loss/train': 1.499741792678833} 08/30/2021 23:41:07 - INFO - __main__ - Step 58296: {'lr': 0.00034175970077667136, 'samples': 11192832, 'steps': 58295, 'loss/train': 1.403458833694458} 08/30/2021 23:41:08 - INFO - __main__ - Step 58297: {'lr': 0.00034175476439252177, 'samples': 11193024, 'steps': 58296, 'loss/train': 0.5339193940162659} 08/30/2021 23:41:08 - INFO - __main__ - Step 58298: {'lr': 0.00034174982796702895, 'samples': 11193216, 'steps': 58297, 'loss/train': 1.1196876764297485} 08/30/2021 23:41:09 - INFO - __main__ - Step 58299: {'lr': 0.00034174489150019506, 'samples': 11193408, 'steps': 58298, 'loss/train': 1.637571096420288} 08/30/2021 23:41:09 - INFO - __main__ - Step 58300: {'lr': 0.0003417399549920224, 'samples': 11193600, 'steps': 58299, 'loss/train': 1.0556622743606567} 08/30/2021 23:41:11 - INFO - __main__ - Step 58301: {'lr': 0.00034173501844251305, 'samples': 11193792, 'steps': 58300, 'loss/train': 1.6106003522872925} 08/30/2021 23:41:11 - INFO - __main__ - Step 58302: {'lr': 0.0003417300818516693, 'samples': 11193984, 'steps': 58301, 'loss/train': 0.8166095614433289} 08/30/2021 23:41:11 - INFO - __main__ - Step 58303: {'lr': 0.00034172514521949336, 'samples': 11194176, 'steps': 58302, 'loss/train': 0.6534811854362488} 08/30/2021 23:41:12 - INFO - __main__ - Step 58304: {'lr': 0.0003417202085459876, 'samples': 11194368, 'steps': 58303, 'loss/train': 1.320803165435791} 08/30/2021 23:41:12 - INFO - __main__ - Step 58305: {'lr': 0.00034171527183115413, 'samples': 11194560, 'steps': 58304, 'loss/train': 0.17822426557540894} 08/30/2021 23:41:14 - INFO - __main__ - Step 58306: {'lr': 0.0003417103350749951, 'samples': 11194752, 'steps': 58305, 'loss/train': 0.942302942276001} 08/30/2021 23:41:14 - INFO - __main__ - Step 58307: {'lr': 0.00034170539827751284, 'samples': 11194944, 'steps': 58306, 'loss/train': 1.3024427890777588} 08/30/2021 23:41:14 - INFO - __main__ - Step 58308: {'lr': 0.0003417004614387095, 'samples': 11195136, 'steps': 58307, 'loss/train': 1.1807435750961304} 08/30/2021 23:41:15 - INFO - __main__ - Step 58309: {'lr': 0.0003416955245585874, 'samples': 11195328, 'steps': 58308, 'loss/train': 1.454353928565979} 08/30/2021 23:41:15 - INFO - __main__ - Step 58310: {'lr': 0.00034169058763714865, 'samples': 11195520, 'steps': 58309, 'loss/train': 0.9266914129257202} 08/30/2021 23:41:17 - INFO - __main__ - Step 58311: {'lr': 0.0003416856506743956, 'samples': 11195712, 'steps': 58310, 'loss/train': 1.1807876825332642} 08/30/2021 23:41:17 - INFO - __main__ - Step 58312: {'lr': 0.00034168071367033043, 'samples': 11195904, 'steps': 58311, 'loss/train': 1.4732695817947388} 08/30/2021 23:41:18 - INFO - __main__ - Step 58313: {'lr': 0.0003416757766249553, 'samples': 11196096, 'steps': 58312, 'loss/train': 1.3171892166137695} 08/30/2021 23:41:18 - INFO - __main__ - Step 58314: {'lr': 0.0003416708395382725, 'samples': 11196288, 'steps': 58313, 'loss/train': 1.5048414468765259} 08/30/2021 23:41:18 - INFO - __main__ - Step 58315: {'lr': 0.00034166590241028425, 'samples': 11196480, 'steps': 58314, 'loss/train': 1.036845326423645} 08/30/2021 23:41:20 - INFO - __main__ - Step 58316: {'lr': 0.00034166096524099264, 'samples': 11196672, 'steps': 58315, 'loss/train': 1.2998428344726562} 08/30/2021 23:41:20 - INFO - __main__ - Step 58317: {'lr': 0.00034165602803040013, 'samples': 11196864, 'steps': 58316, 'loss/train': 1.593919277191162} 08/30/2021 23:41:20 - INFO - __main__ - Step 58318: {'lr': 0.00034165109077850884, 'samples': 11197056, 'steps': 58317, 'loss/train': 1.820627212524414} 08/30/2021 23:41:21 - INFO - __main__ - Step 58319: {'lr': 0.00034164615348532094, 'samples': 11197248, 'steps': 58318, 'loss/train': 1.5240626335144043} 08/30/2021 23:41:21 - INFO - __main__ - Step 58320: {'lr': 0.0003416412161508387, 'samples': 11197440, 'steps': 58319, 'loss/train': 1.3691742420196533} 08/30/2021 23:41:23 - INFO - __main__ - Step 58321: {'lr': 0.0003416362787750643, 'samples': 11197632, 'steps': 58320, 'loss/train': 1.2240175008773804} 08/30/2021 23:41:24 - INFO - __main__ - Step 58322: {'lr': 0.00034163134135800004, 'samples': 11197824, 'steps': 58321, 'loss/train': 1.71846342086792} 08/30/2021 23:41:24 - INFO - __main__ - Step 58323: {'lr': 0.00034162640389964814, 'samples': 11198016, 'steps': 58322, 'loss/train': 1.1008986234664917} 08/30/2021 23:41:24 - INFO - __main__ - Step 58324: {'lr': 0.0003416214664000108, 'samples': 11198208, 'steps': 58323, 'loss/train': 1.53416907787323} 08/30/2021 23:41:25 - INFO - __main__ - Step 58325: {'lr': 0.00034161652885909025, 'samples': 11198400, 'steps': 58324, 'loss/train': 0.2563075125217438} 08/30/2021 23:41:25 - INFO - __main__ - Step 58326: {'lr': 0.0003416115912768887, 'samples': 11198592, 'steps': 58325, 'loss/train': 0.9635010361671448} 08/30/2021 23:41:27 - INFO - __main__ - Step 58327: {'lr': 0.0003416066536534083, 'samples': 11198784, 'steps': 58326, 'loss/train': 1.0989446640014648} 08/30/2021 23:41:27 - INFO - __main__ - Step 58328: {'lr': 0.0003416017159886514, 'samples': 11198976, 'steps': 58327, 'loss/train': 0.6972031593322754} 08/30/2021 23:41:27 - INFO - __main__ - Step 58329: {'lr': 0.0003415967782826202, 'samples': 11199168, 'steps': 58328, 'loss/train': 1.3485358953475952} 08/30/2021 23:41:28 - INFO - __main__ - Step 58330: {'lr': 0.0003415918405353169, 'samples': 11199360, 'steps': 58329, 'loss/train': 1.6061773300170898} 08/30/2021 23:41:28 - INFO - __main__ - Step 58331: {'lr': 0.0003415869027467437, 'samples': 11199552, 'steps': 58330, 'loss/train': 1.1461906433105469} 08/30/2021 23:41:29 - INFO - __main__ - Step 58332: {'lr': 0.000341581964916903, 'samples': 11199744, 'steps': 58331, 'loss/train': 1.0337737798690796} 08/30/2021 23:41:30 - INFO - __main__ - Step 58333: {'lr': 0.00034157702704579667, 'samples': 11199936, 'steps': 58332, 'loss/train': 1.602339506149292} 08/30/2021 23:41:30 - INFO - __main__ - Step 58334: {'lr': 0.00034157208913342726, 'samples': 11200128, 'steps': 58333, 'loss/train': 0.9502540230751038} 08/30/2021 23:41:31 - INFO - __main__ - Step 58335: {'lr': 0.00034156715117979685, 'samples': 11200320, 'steps': 58334, 'loss/train': 1.6734758615493774} 08/30/2021 23:41:31 - INFO - __main__ - Step 58336: {'lr': 0.00034156221318490767, 'samples': 11200512, 'steps': 58335, 'loss/train': 0.8886157870292664} 08/30/2021 23:41:33 - INFO - __main__ - Step 58337: {'lr': 0.000341557275148762, 'samples': 11200704, 'steps': 58336, 'loss/train': 1.6553969383239746} 08/30/2021 23:41:33 - INFO - __main__ - Step 58338: {'lr': 0.0003415523370713621, 'samples': 11200896, 'steps': 58337, 'loss/train': 0.9717940092086792} 08/30/2021 23:41:33 - INFO - __main__ - Step 58339: {'lr': 0.00034154739895271005, 'samples': 11201088, 'steps': 58338, 'loss/train': 1.4921331405639648} 08/30/2021 23:41:34 - INFO - __main__ - Step 58340: {'lr': 0.00034154246079280817, 'samples': 11201280, 'steps': 58339, 'loss/train': 1.2828714847564697} 08/30/2021 23:41:34 - INFO - __main__ - Step 58341: {'lr': 0.0003415375225916586, 'samples': 11201472, 'steps': 58340, 'loss/train': 1.5482741594314575} 08/30/2021 23:41:36 - INFO - __main__ - Step 58342: {'lr': 0.0003415325843492637, 'samples': 11201664, 'steps': 58341, 'loss/train': 0.8064612150192261} 08/30/2021 23:41:36 - INFO - __main__ - Step 58343: {'lr': 0.00034152764606562564, 'samples': 11201856, 'steps': 58342, 'loss/train': 1.6249662637710571} 08/30/2021 23:41:36 - INFO - __main__ - Step 58344: {'lr': 0.0003415227077407466, 'samples': 11202048, 'steps': 58343, 'loss/train': 1.5568772554397583} 08/30/2021 23:41:37 - INFO - __main__ - Step 58345: {'lr': 0.00034151776937462895, 'samples': 11202240, 'steps': 58344, 'loss/train': 1.4553463459014893} 08/30/2021 23:41:37 - INFO - __main__ - Step 58346: {'lr': 0.0003415128309672747, 'samples': 11202432, 'steps': 58345, 'loss/train': 3.9053075313568115} 08/30/2021 23:41:39 - INFO - __main__ - Step 58347: {'lr': 0.0003415078925186862, 'samples': 11202624, 'steps': 58346, 'loss/train': 1.044439673423767} 08/30/2021 23:41:39 - INFO - __main__ - Step 58348: {'lr': 0.00034150295402886566, 'samples': 11202816, 'steps': 58347, 'loss/train': 1.4932725429534912} 08/30/2021 23:41:39 - INFO - __main__ - Step 58349: {'lr': 0.0003414980154978153, 'samples': 11203008, 'steps': 58348, 'loss/train': 1.1157665252685547} 08/30/2021 23:41:40 - INFO - __main__ - Step 58350: {'lr': 0.00034149307692553734, 'samples': 11203200, 'steps': 58349, 'loss/train': 1.2668721675872803} 08/30/2021 23:41:40 - INFO - __main__ - Step 58351: {'lr': 0.000341488138312034, 'samples': 11203392, 'steps': 58350, 'loss/train': 1.0727137327194214} 08/30/2021 23:41:42 - INFO - __main__ - Step 58352: {'lr': 0.00034148319965730757, 'samples': 11203584, 'steps': 58351, 'loss/train': 2.1890830993652344} 08/30/2021 23:41:42 - INFO - __main__ - Step 58353: {'lr': 0.0003414782609613602, 'samples': 11203776, 'steps': 58352, 'loss/train': 1.31967031955719} 08/30/2021 23:41:43 - INFO - __main__ - Step 58354: {'lr': 0.0003414733222241941, 'samples': 11203968, 'steps': 58353, 'loss/train': 1.557159423828125} 08/30/2021 23:41:43 - INFO - __main__ - Step 58355: {'lr': 0.00034146838344581155, 'samples': 11204160, 'steps': 58354, 'loss/train': 1.4454480409622192} 08/30/2021 23:41:43 - INFO - __main__ - Step 58356: {'lr': 0.00034146344462621477, 'samples': 11204352, 'steps': 58355, 'loss/train': 1.3503144979476929} 08/30/2021 23:41:44 - INFO - __main__ - Step 58357: {'lr': 0.00034145850576540595, 'samples': 11204544, 'steps': 58356, 'loss/train': 0.9911277890205383} 08/30/2021 23:41:45 - INFO - __main__ - Step 58358: {'lr': 0.00034145356686338736, 'samples': 11204736, 'steps': 58357, 'loss/train': 1.2887252569198608} 08/30/2021 23:41:46 - INFO - __main__ - Step 58359: {'lr': 0.00034144862792016123, 'samples': 11204928, 'steps': 58358, 'loss/train': 1.0167911052703857} 08/30/2021 23:41:46 - INFO - __main__ - Step 58360: {'lr': 0.00034144368893572973, 'samples': 11205120, 'steps': 58359, 'loss/train': 1.5796236991882324} 08/30/2021 23:41:46 - INFO - __main__ - Step 58361: {'lr': 0.00034143874991009513, 'samples': 11205312, 'steps': 58360, 'loss/train': 1.3113913536071777} 08/30/2021 23:41:47 - INFO - __main__ - Step 58362: {'lr': 0.0003414338108432596, 'samples': 11205504, 'steps': 58361, 'loss/train': 1.3880691528320312} 08/30/2021 23:41:48 - INFO - __main__ - Step 58363: {'lr': 0.0003414288717352254, 'samples': 11205696, 'steps': 58362, 'loss/train': 0.9511662125587463} 08/30/2021 23:41:49 - INFO - __main__ - Step 58364: {'lr': 0.00034142393258599485, 'samples': 11205888, 'steps': 58363, 'loss/train': 1.5379542112350464} 08/30/2021 23:41:49 - INFO - __main__ - Step 58365: {'lr': 0.00034141899339557003, 'samples': 11206080, 'steps': 58364, 'loss/train': 1.3214648962020874} 08/30/2021 23:41:50 - INFO - __main__ - Step 58366: {'lr': 0.0003414140541639532, 'samples': 11206272, 'steps': 58365, 'loss/train': 0.6372202634811401} 08/30/2021 23:41:50 - INFO - __main__ - Step 58367: {'lr': 0.0003414091148911466, 'samples': 11206464, 'steps': 58366, 'loss/train': 0.2655096650123596} 08/30/2021 23:41:50 - INFO - __main__ - Step 58368: {'lr': 0.00034140417557715255, 'samples': 11206656, 'steps': 58367, 'loss/train': 0.029668845236301422} 08/30/2021 23:41:52 - INFO - __main__ - Step 58369: {'lr': 0.0003413992362219731, 'samples': 11206848, 'steps': 58368, 'loss/train': 0.02448113076388836} 08/30/2021 23:41:52 - INFO - __main__ - Step 58370: {'lr': 0.0003413942968256106, 'samples': 11207040, 'steps': 58369, 'loss/train': 1.6676126718521118} 08/30/2021 23:41:53 - INFO - __main__ - Step 58371: {'lr': 0.00034138935738806727, 'samples': 11207232, 'steps': 58370, 'loss/train': 1.2436788082122803} 08/30/2021 23:41:53 - INFO - __main__ - Step 58372: {'lr': 0.0003413844179093453, 'samples': 11207424, 'steps': 58371, 'loss/train': 1.169629454612732} 08/30/2021 23:41:53 - INFO - __main__ - Step 58373: {'lr': 0.0003413794783894468, 'samples': 11207616, 'steps': 58372, 'loss/train': 1.327942132949829} 08/30/2021 23:41:56 - INFO - __main__ - Step 58374: {'lr': 0.0003413745388283742, 'samples': 11207808, 'steps': 58373, 'loss/train': 1.7049061059951782} 08/30/2021 23:41:56 - INFO - __main__ - Step 58375: {'lr': 0.00034136959922612977, 'samples': 11208000, 'steps': 58374, 'loss/train': 0.10986167192459106} 08/30/2021 23:41:56 - INFO - __main__ - Step 58376: {'lr': 0.00034136465958271546, 'samples': 11208192, 'steps': 58375, 'loss/train': 1.5120428800582886} 08/30/2021 23:41:57 - INFO - __main__ - Step 58377: {'lr': 0.00034135971989813363, 'samples': 11208384, 'steps': 58376, 'loss/train': 0.8108828067779541} 08/30/2021 23:41:57 - INFO - __main__ - Step 58378: {'lr': 0.0003413547801723866, 'samples': 11208576, 'steps': 58377, 'loss/train': 1.3272757530212402} 08/30/2021 23:41:58 - INFO - __main__ - Step 58379: {'lr': 0.00034134984040547645, 'samples': 11208768, 'steps': 58378, 'loss/train': 1.148912787437439} 08/30/2021 23:42:00 - INFO - __main__ - Step 58380: {'lr': 0.0003413449005974055, 'samples': 11208960, 'steps': 58379, 'loss/train': 1.270913004875183} 08/30/2021 23:42:00 - INFO - __main__ - Step 58381: {'lr': 0.00034133996074817597, 'samples': 11209152, 'steps': 58380, 'loss/train': 1.4343620538711548} 08/30/2021 23:42:00 - INFO - __main__ - Step 58382: {'lr': 0.00034133502085779006, 'samples': 11209344, 'steps': 58381, 'loss/train': 1.547174096107483} 08/30/2021 23:42:01 - INFO - __main__ - Step 58383: {'lr': 0.00034133008092624995, 'samples': 11209536, 'steps': 58382, 'loss/train': 1.1758009195327759} 08/30/2021 23:42:01 - INFO - __main__ - Step 58384: {'lr': 0.0003413251409535579, 'samples': 11209728, 'steps': 58383, 'loss/train': 0.631420910358429} 08/30/2021 23:42:02 - INFO - __main__ - Step 58385: {'lr': 0.0003413202009397163, 'samples': 11209920, 'steps': 58384, 'loss/train': 0.18398058414459229} 08/30/2021 23:42:03 - INFO - __main__ - Step 58386: {'lr': 0.0003413152608847271, 'samples': 11210112, 'steps': 58385, 'loss/train': 1.3006185293197632} 08/30/2021 23:42:03 - INFO - __main__ - Step 58387: {'lr': 0.0003413103207885927, 'samples': 11210304, 'steps': 58386, 'loss/train': 0.7882906794548035} 08/30/2021 23:42:04 - INFO - __main__ - Step 58388: {'lr': 0.00034130538065131524, 'samples': 11210496, 'steps': 58387, 'loss/train': 1.257989764213562} 08/30/2021 23:42:04 - INFO - __main__ - Step 58389: {'lr': 0.000341300440472897, 'samples': 11210688, 'steps': 58388, 'loss/train': 1.9831308126449585} 08/30/2021 23:42:06 - INFO - __main__ - Step 58390: {'lr': 0.00034129550025334014, 'samples': 11210880, 'steps': 58389, 'loss/train': 1.1269623041152954} 08/30/2021 23:42:06 - INFO - __main__ - Step 58391: {'lr': 0.00034129055999264704, 'samples': 11211072, 'steps': 58390, 'loss/train': 1.4731924533843994} 08/30/2021 23:42:06 - INFO - __main__ - Step 58392: {'lr': 0.0003412856196908198, 'samples': 11211264, 'steps': 58391, 'loss/train': 0.9884055852890015} 08/30/2021 23:42:07 - INFO - __main__ - Step 58393: {'lr': 0.00034128067934786064, 'samples': 11211456, 'steps': 58392, 'loss/train': 1.8362431526184082} 08/30/2021 23:42:07 - INFO - __main__ - Step 58394: {'lr': 0.0003412757389637718, 'samples': 11211648, 'steps': 58393, 'loss/train': 0.9452770352363586} 08/30/2021 23:42:08 - INFO - __main__ - Step 58395: {'lr': 0.00034127079853855545, 'samples': 11211840, 'steps': 58394, 'loss/train': 1.2396337985992432} 08/30/2021 23:42:09 - INFO - __main__ - Step 58396: {'lr': 0.00034126585807221397, 'samples': 11212032, 'steps': 58395, 'loss/train': 1.246291160583496} 08/30/2021 23:42:09 - INFO - __main__ - Step 58397: {'lr': 0.0003412609175647495, 'samples': 11212224, 'steps': 58396, 'loss/train': 1.094338297843933} 08/30/2021 23:42:10 - INFO - __main__ - Step 58398: {'lr': 0.0003412559770161643, 'samples': 11212416, 'steps': 58397, 'loss/train': 0.86078280210495} 08/30/2021 23:42:10 - INFO - __main__ - Step 58399: {'lr': 0.0003412510364264606, 'samples': 11212608, 'steps': 58398, 'loss/train': 0.33593595027923584} 08/30/2021 23:42:10 - INFO - __main__ - Step 58400: {'lr': 0.0003412460957956405, 'samples': 11212800, 'steps': 58399, 'loss/train': 1.7203713655471802} 08/30/2021 23:42:12 - INFO - __main__ - Step 58401: {'lr': 0.00034124115512370636, 'samples': 11212992, 'steps': 58400, 'loss/train': 1.215850830078125} 08/30/2021 23:42:12 - INFO - __main__ - Step 58402: {'lr': 0.0003412362144106603, 'samples': 11213184, 'steps': 58401, 'loss/train': 2.255078077316284} 08/30/2021 23:42:13 - INFO - __main__ - Step 58403: {'lr': 0.00034123127365650463, 'samples': 11213376, 'steps': 58402, 'loss/train': 0.6384060382843018} 08/30/2021 23:42:13 - INFO - __main__ - Step 58404: {'lr': 0.0003412263328612416, 'samples': 11213568, 'steps': 58403, 'loss/train': 0.7852904796600342} 08/30/2021 23:42:13 - INFO - __main__ - Step 58405: {'lr': 0.00034122139202487334, 'samples': 11213760, 'steps': 58404, 'loss/train': 1.2657862901687622} 08/30/2021 23:42:15 - INFO - __main__ - Step 58406: {'lr': 0.00034121645114740224, 'samples': 11213952, 'steps': 58405, 'loss/train': 1.1440041065216064} 08/30/2021 23:42:16 - INFO - __main__ - Step 58407: {'lr': 0.00034121151022883033, 'samples': 11214144, 'steps': 58406, 'loss/train': 0.7610243558883667} 08/30/2021 23:42:16 - INFO - __main__ - Step 58408: {'lr': 0.00034120656926915995, 'samples': 11214336, 'steps': 58407, 'loss/train': 1.120870590209961} 08/30/2021 23:42:16 - INFO - __main__ - Step 58409: {'lr': 0.0003412016282683932, 'samples': 11214528, 'steps': 58408, 'loss/train': 1.2031358480453491} 08/30/2021 23:42:17 - INFO - __main__ - Step 58410: {'lr': 0.0003411966872265325, 'samples': 11214720, 'steps': 58409, 'loss/train': 0.04337947070598602} 08/30/2021 23:42:18 - INFO - __main__ - Step 58411: {'lr': 0.00034119174614357994, 'samples': 11214912, 'steps': 58410, 'loss/train': 1.2732492685317993} 08/30/2021 23:42:19 - INFO - __main__ - Step 58412: {'lr': 0.00034118680501953784, 'samples': 11215104, 'steps': 58411, 'loss/train': 1.3456593751907349} 08/30/2021 23:42:19 - INFO - __main__ - Step 58413: {'lr': 0.00034118186385440833, 'samples': 11215296, 'steps': 58412, 'loss/train': 1.5052320957183838} 08/30/2021 23:42:19 - INFO - __main__ - Step 58414: {'lr': 0.00034117692264819374, 'samples': 11215488, 'steps': 58413, 'loss/train': 0.8616198301315308} 08/30/2021 23:42:20 - INFO - __main__ - Step 58415: {'lr': 0.0003411719814008961, 'samples': 11215680, 'steps': 58414, 'loss/train': 1.5524102449417114} 08/30/2021 23:42:20 - INFO - __main__ - Step 58416: {'lr': 0.0003411670401125179, 'samples': 11215872, 'steps': 58415, 'loss/train': 1.472939133644104} 08/30/2021 23:42:21 - INFO - __main__ - Step 58417: {'lr': 0.00034116209878306116, 'samples': 11216064, 'steps': 58416, 'loss/train': 1.1102699041366577} 08/30/2021 23:42:22 - INFO - __main__ - Step 58418: {'lr': 0.00034115715741252824, 'samples': 11216256, 'steps': 58417, 'loss/train': 0.19590973854064941} 08/30/2021 23:42:22 - INFO - __main__ - Step 58419: {'lr': 0.0003411522160009213, 'samples': 11216448, 'steps': 58418, 'loss/train': 1.494523048400879} 08/30/2021 23:42:23 - INFO - __main__ - Step 58420: {'lr': 0.00034114727454824257, 'samples': 11216640, 'steps': 58419, 'loss/train': 1.3751004934310913} 08/30/2021 23:42:23 - INFO - __main__ - Step 58421: {'lr': 0.00034114233305449426, 'samples': 11216832, 'steps': 58420, 'loss/train': 1.1613978147506714} 08/30/2021 23:42:24 - INFO - __main__ - Step 58422: {'lr': 0.00034113739151967864, 'samples': 11217024, 'steps': 58421, 'loss/train': 0.4387499690055847} 08/30/2021 23:42:25 - INFO - __main__ - Step 58423: {'lr': 0.00034113244994379794, 'samples': 11217216, 'steps': 58422, 'loss/train': 1.5585343837738037} 08/30/2021 23:42:25 - INFO - __main__ - Step 58424: {'lr': 0.00034112750832685434, 'samples': 11217408, 'steps': 58423, 'loss/train': 1.387988567352295} 08/30/2021 23:42:26 - INFO - __main__ - Step 58425: {'lr': 0.0003411225666688501, 'samples': 11217600, 'steps': 58424, 'loss/train': 1.0463138818740845} 08/30/2021 23:42:26 - INFO - __main__ - Step 58426: {'lr': 0.0003411176249697875, 'samples': 11217792, 'steps': 58425, 'loss/train': 1.821783423423767} 08/30/2021 23:42:28 - INFO - __main__ - Step 58427: {'lr': 0.0003411126832296686, 'samples': 11217984, 'steps': 58426, 'loss/train': 1.3335225582122803} 08/30/2021 23:42:29 - INFO - __main__ - Step 58428: {'lr': 0.00034110774144849575, 'samples': 11218176, 'steps': 58427, 'loss/train': 1.253514289855957} 08/30/2021 23:42:29 - INFO - __main__ - Step 58429: {'lr': 0.00034110279962627115, 'samples': 11218368, 'steps': 58428, 'loss/train': 1.5873173475265503} 08/30/2021 23:42:29 - INFO - __main__ - Step 58430: {'lr': 0.0003410978577629971, 'samples': 11218560, 'steps': 58429, 'loss/train': 0.23265917599201202} 08/30/2021 23:42:30 - INFO - __main__ - Step 58431: {'lr': 0.0003410929158586757, 'samples': 11218752, 'steps': 58430, 'loss/train': 1.1849981546401978} 08/30/2021 23:42:31 - INFO - __main__ - Step 58432: {'lr': 0.0003410879739133093, 'samples': 11218944, 'steps': 58431, 'loss/train': 1.8296526670455933} 08/30/2021 23:42:32 - INFO - __main__ - Step 58433: {'lr': 0.00034108303192690003, 'samples': 11219136, 'steps': 58432, 'loss/train': 1.786566972732544} 08/30/2021 23:42:32 - INFO - __main__ - Step 58434: {'lr': 0.0003410780898994501, 'samples': 11219328, 'steps': 58433, 'loss/train': 1.3981993198394775} 08/30/2021 23:42:32 - INFO - __main__ - Step 58435: {'lr': 0.00034107314783096183, 'samples': 11219520, 'steps': 58434, 'loss/train': 1.4601951837539673} 08/30/2021 23:42:33 - INFO - __main__ - Step 58436: {'lr': 0.0003410682057214374, 'samples': 11219712, 'steps': 58435, 'loss/train': 2.132354497909546} 08/30/2021 23:42:34 - INFO - __main__ - Step 58437: {'lr': 0.00034106326357087905, 'samples': 11219904, 'steps': 58436, 'loss/train': 1.478259801864624} 08/30/2021 23:42:35 - INFO - __main__ - Step 58438: {'lr': 0.000341058321379289, 'samples': 11220096, 'steps': 58437, 'loss/train': 1.3704030513763428} 08/30/2021 23:42:35 - INFO - __main__ - Step 58439: {'lr': 0.0003410533791466695, 'samples': 11220288, 'steps': 58438, 'loss/train': 1.217626929283142} 08/30/2021 23:42:35 - INFO - __main__ - Step 58440: {'lr': 0.0003410484368730227, 'samples': 11220480, 'steps': 58439, 'loss/train': 1.5148245096206665} 08/30/2021 23:42:36 - INFO - __main__ - Step 58441: {'lr': 0.00034104349455835094, 'samples': 11220672, 'steps': 58440, 'loss/train': 1.871681571006775} 08/30/2021 23:42:36 - INFO - __main__ - Step 58442: {'lr': 0.0003410385522026563, 'samples': 11220864, 'steps': 58441, 'loss/train': 1.5324757099151611} 08/30/2021 23:42:37 - INFO - __main__ - Step 58443: {'lr': 0.0003410336098059412, 'samples': 11221056, 'steps': 58442, 'loss/train': 1.0603808164596558} 08/30/2021 23:42:38 - INFO - __main__ - Step 58444: {'lr': 0.0003410286673682077, 'samples': 11221248, 'steps': 58443, 'loss/train': 1.6743876934051514} 08/30/2021 23:42:38 - INFO - __main__ - Step 58445: {'lr': 0.0003410237248894581, 'samples': 11221440, 'steps': 58444, 'loss/train': 1.8098150491714478} 08/30/2021 23:42:39 - INFO - __main__ - Step 58446: {'lr': 0.00034101878236969464, 'samples': 11221632, 'steps': 58445, 'loss/train': 1.6807851791381836} 08/30/2021 23:42:39 - INFO - __main__ - Step 58447: {'lr': 0.0003410138398089195, 'samples': 11221824, 'steps': 58446, 'loss/train': 1.5474516153335571} 08/30/2021 23:42:40 - INFO - __main__ - Step 58448: {'lr': 0.0003410088972071349, 'samples': 11222016, 'steps': 58447, 'loss/train': 0.9095951914787292} 08/30/2021 23:42:41 - INFO - __main__ - Step 58449: {'lr': 0.0003410039545643431, 'samples': 11222208, 'steps': 58448, 'loss/train': 1.4669469594955444} 08/30/2021 23:42:41 - INFO - __main__ - Step 58450: {'lr': 0.0003409990118805463, 'samples': 11222400, 'steps': 58449, 'loss/train': 1.2733420133590698} 08/30/2021 23:42:42 - INFO - __main__ - Step 58451: {'lr': 0.0003409940691557468, 'samples': 11222592, 'steps': 58450, 'loss/train': 1.3465402126312256} 08/30/2021 23:42:42 - INFO - __main__ - Step 58452: {'lr': 0.0003409891263899467, 'samples': 11222784, 'steps': 58451, 'loss/train': 1.3954256772994995} 08/30/2021 23:42:44 - INFO - __main__ - Step 58453: {'lr': 0.0003409841835831484, 'samples': 11222976, 'steps': 58452, 'loss/train': 0.5714172720909119} 08/30/2021 23:42:44 - INFO - __main__ - Step 58454: {'lr': 0.000340979240735354, 'samples': 11223168, 'steps': 58453, 'loss/train': 1.2832716703414917} 08/30/2021 23:42:44 - INFO - __main__ - Step 58455: {'lr': 0.00034097429784656574, 'samples': 11223360, 'steps': 58454, 'loss/train': 0.8252901434898376} 08/30/2021 23:42:45 - INFO - __main__ - Step 58456: {'lr': 0.00034096935491678595, 'samples': 11223552, 'steps': 58455, 'loss/train': 1.4410642385482788} 08/30/2021 23:42:45 - INFO - __main__ - Step 58457: {'lr': 0.0003409644119460166, 'samples': 11223744, 'steps': 58456, 'loss/train': 1.3467967510223389} 08/30/2021 23:42:47 - INFO - __main__ - Step 58458: {'lr': 0.00034095946893426024, 'samples': 11223936, 'steps': 58457, 'loss/train': 1.1955325603485107} 08/30/2021 23:42:47 - INFO - __main__ - Step 58459: {'lr': 0.0003409545258815189, 'samples': 11224128, 'steps': 58458, 'loss/train': 2.233649969100952} 08/30/2021 23:42:47 - INFO - __main__ - Step 58460: {'lr': 0.00034094958278779486, 'samples': 11224320, 'steps': 58459, 'loss/train': 1.1679543256759644} 08/30/2021 23:42:48 - INFO - __main__ - Step 58461: {'lr': 0.00034094463965309035, 'samples': 11224512, 'steps': 58460, 'loss/train': 1.3892271518707275} 08/30/2021 23:42:48 - INFO - __main__ - Step 58462: {'lr': 0.00034093969647740755, 'samples': 11224704, 'steps': 58461, 'loss/train': 1.3748226165771484} 08/30/2021 23:42:50 - INFO - __main__ - Step 58463: {'lr': 0.00034093475326074874, 'samples': 11224896, 'steps': 58462, 'loss/train': 1.650243878364563} 08/30/2021 23:42:50 - INFO - __main__ - Step 58464: {'lr': 0.00034092981000311614, 'samples': 11225088, 'steps': 58463, 'loss/train': 0.25024887919425964} 08/30/2021 23:42:51 - INFO - __main__ - Step 58465: {'lr': 0.00034092486670451197, 'samples': 11225280, 'steps': 58464, 'loss/train': 0.8582757115364075} 08/30/2021 23:42:51 - INFO - __main__ - Step 58466: {'lr': 0.0003409199233649385, 'samples': 11225472, 'steps': 58465, 'loss/train': 1.2698558568954468} 08/30/2021 23:42:51 - INFO - __main__ - Step 58467: {'lr': 0.0003409149799843979, 'samples': 11225664, 'steps': 58466, 'loss/train': 1.504538655281067} 08/30/2021 23:42:52 - INFO - __main__ - Step 58468: {'lr': 0.00034091003656289235, 'samples': 11225856, 'steps': 58467, 'loss/train': 1.4923176765441895} 08/30/2021 23:42:53 - INFO - __main__ - Step 58469: {'lr': 0.00034090509310042414, 'samples': 11226048, 'steps': 58468, 'loss/train': 1.2800734043121338} 08/30/2021 23:42:54 - INFO - __main__ - Step 58470: {'lr': 0.00034090014959699554, 'samples': 11226240, 'steps': 58469, 'loss/train': 1.1687654256820679} 08/30/2021 23:42:54 - INFO - __main__ - Step 58471: {'lr': 0.0003408952060526087, 'samples': 11226432, 'steps': 58470, 'loss/train': 1.4248583316802979} 08/30/2021 23:42:54 - INFO - __main__ - Step 58472: {'lr': 0.00034089026246726596, 'samples': 11226624, 'steps': 58471, 'loss/train': 1.5376399755477905} 08/30/2021 23:42:55 - INFO - __main__ - Step 58473: {'lr': 0.00034088531884096944, 'samples': 11226816, 'steps': 58472, 'loss/train': 1.5004537105560303} 08/30/2021 23:42:56 - INFO - __main__ - Step 58474: {'lr': 0.0003408803751737214, 'samples': 11227008, 'steps': 58473, 'loss/train': 1.8636672496795654} 08/30/2021 23:42:57 - INFO - __main__ - Step 58475: {'lr': 0.00034087543146552404, 'samples': 11227200, 'steps': 58474, 'loss/train': 1.744942307472229} 08/30/2021 23:42:57 - INFO - __main__ - Step 58476: {'lr': 0.0003408704877163796, 'samples': 11227392, 'steps': 58475, 'loss/train': 1.6072520017623901} 08/30/2021 23:42:57 - INFO - __main__ - Step 58477: {'lr': 0.00034086554392629033, 'samples': 11227584, 'steps': 58476, 'loss/train': 0.9681432843208313} 08/30/2021 23:42:58 - INFO - __main__ - Step 58478: {'lr': 0.00034086060009525844, 'samples': 11227776, 'steps': 58477, 'loss/train': 1.4817302227020264} 08/30/2021 23:43:00 - INFO - __main__ - Step 58479: {'lr': 0.0003408556562232862, 'samples': 11227968, 'steps': 58478, 'loss/train': 1.2142415046691895} 08/30/2021 23:43:00 - INFO - __main__ - Step 58480: {'lr': 0.00034085071231037585, 'samples': 11228160, 'steps': 58479, 'loss/train': 1.4783388376235962} 08/30/2021 23:43:00 - INFO - __main__ - Step 58481: {'lr': 0.0003408457683565295, 'samples': 11228352, 'steps': 58480, 'loss/train': 1.5649255514144897} 08/30/2021 23:43:01 - INFO - __main__ - Step 58482: {'lr': 0.00034084082436174946, 'samples': 11228544, 'steps': 58481, 'loss/train': 1.256433367729187} 08/30/2021 23:43:01 - INFO - __main__ - Step 58483: {'lr': 0.0003408358803260379, 'samples': 11228736, 'steps': 58482, 'loss/train': 1.355131983757019} 08/30/2021 23:43:01 - INFO - __main__ - Step 58484: {'lr': 0.00034083093624939716, 'samples': 11228928, 'steps': 58483, 'loss/train': 1.467124342918396} 08/30/2021 23:43:03 - INFO - __main__ - Step 58485: {'lr': 0.00034082599213182933, 'samples': 11229120, 'steps': 58484, 'loss/train': 1.0623458623886108} 08/30/2021 23:43:04 - INFO - __main__ - Step 58486: {'lr': 0.0003408210479733368, 'samples': 11229312, 'steps': 58485, 'loss/train': 0.13869057595729828} 08/30/2021 23:43:04 - INFO - __main__ - Step 58487: {'lr': 0.0003408161037739217, 'samples': 11229504, 'steps': 58486, 'loss/train': 1.1083955764770508} 08/30/2021 23:43:05 - INFO - __main__ - Step 58488: {'lr': 0.0003408111595335862, 'samples': 11229696, 'steps': 58487, 'loss/train': 1.5257197618484497} 08/30/2021 23:43:05 - INFO - __main__ - Step 58489: {'lr': 0.00034080621525233264, 'samples': 11229888, 'steps': 58488, 'loss/train': 1.21271550655365} 08/30/2021 23:43:06 - INFO - __main__ - Step 58490: {'lr': 0.0003408012709301632, 'samples': 11230080, 'steps': 58489, 'loss/train': 1.4456794261932373} 08/30/2021 23:43:07 - INFO - __main__ - Step 58491: {'lr': 0.00034079632656708005, 'samples': 11230272, 'steps': 58490, 'loss/train': 1.403703212738037} 08/30/2021 23:43:07 - INFO - __main__ - Step 58492: {'lr': 0.00034079138216308553, 'samples': 11230464, 'steps': 58491, 'loss/train': 1.660502314567566} 08/30/2021 23:43:08 - INFO - __main__ - Step 58493: {'lr': 0.00034078643771818184, 'samples': 11230656, 'steps': 58492, 'loss/train': 1.5445058345794678} 08/30/2021 23:43:08 - INFO - __main__ - Step 58494: {'lr': 0.00034078149323237114, 'samples': 11230848, 'steps': 58493, 'loss/train': 1.618409514427185} 08/30/2021 23:43:10 - INFO - __main__ - Step 58495: {'lr': 0.00034077654870565566, 'samples': 11231040, 'steps': 58494, 'loss/train': 0.9836156368255615} 08/30/2021 23:43:10 - INFO - __main__ - Step 58496: {'lr': 0.00034077160413803774, 'samples': 11231232, 'steps': 58495, 'loss/train': 1.3215492963790894} 08/30/2021 23:43:10 - INFO - __main__ - Step 58497: {'lr': 0.0003407666595295195, 'samples': 11231424, 'steps': 58496, 'loss/train': 0.4603157639503479} 08/30/2021 23:43:11 - INFO - __main__ - Step 58498: {'lr': 0.0003407617148801033, 'samples': 11231616, 'steps': 58497, 'loss/train': 1.0663371086120605} 08/30/2021 23:43:11 - INFO - __main__ - Step 58499: {'lr': 0.0003407567701897911, 'samples': 11231808, 'steps': 58498, 'loss/train': 1.4457542896270752} 08/30/2021 23:43:13 - INFO - __main__ - Step 58500: {'lr': 0.0003407518254585854, 'samples': 11232000, 'steps': 58499, 'loss/train': 0.9328857660293579} 08/30/2021 23:43:13 - INFO - __main__ - Step 58501: {'lr': 0.0003407468806864883, 'samples': 11232192, 'steps': 58500, 'loss/train': 1.7675741910934448} 08/30/2021 23:43:13 - INFO - __main__ - Step 58502: {'lr': 0.0003407419358735021, 'samples': 11232384, 'steps': 58501, 'loss/train': 0.7371501922607422} 08/30/2021 23:43:14 - INFO - __main__ - Step 58503: {'lr': 0.0003407369910196289, 'samples': 11232576, 'steps': 58502, 'loss/train': 1.3097244501113892} 08/30/2021 23:43:14 - INFO - __main__ - Step 58504: {'lr': 0.0003407320461248711, 'samples': 11232768, 'steps': 58503, 'loss/train': 0.7195886373519897} 08/30/2021 23:43:16 - INFO - __main__ - Step 58505: {'lr': 0.00034072710118923086, 'samples': 11232960, 'steps': 58504, 'loss/train': 0.927277684211731} 08/30/2021 23:43:16 - INFO - __main__ - Step 58506: {'lr': 0.0003407221562127103, 'samples': 11233152, 'steps': 58505, 'loss/train': 1.2948977947235107} 08/30/2021 23:43:16 - INFO - __main__ - Step 58507: {'lr': 0.0003407172111953117, 'samples': 11233344, 'steps': 58506, 'loss/train': 1.105934977531433} 08/30/2021 23:43:17 - INFO - __main__ - Step 58508: {'lr': 0.00034071226613703744, 'samples': 11233536, 'steps': 58507, 'loss/train': 1.422202467918396} 08/30/2021 23:43:17 - INFO - __main__ - Step 58509: {'lr': 0.0003407073210378897, 'samples': 11233728, 'steps': 58508, 'loss/train': 1.1649856567382812} 08/30/2021 23:43:17 - INFO - __main__ - Step 58510: {'lr': 0.00034070237589787047, 'samples': 11233920, 'steps': 58509, 'loss/train': 1.3617955446243286} 08/30/2021 23:43:19 - INFO - __main__ - Step 58511: {'lr': 0.00034069743071698215, 'samples': 11234112, 'steps': 58510, 'loss/train': 1.4471343755722046} 08/30/2021 23:43:19 - INFO - __main__ - Step 58512: {'lr': 0.000340692485495227, 'samples': 11234304, 'steps': 58511, 'loss/train': 1.0367512702941895} 08/30/2021 23:43:20 - INFO - __main__ - Step 58513: {'lr': 0.0003406875402326073, 'samples': 11234496, 'steps': 58512, 'loss/train': 1.8381812572479248} 08/30/2021 23:43:20 - INFO - __main__ - Step 58514: {'lr': 0.00034068259492912514, 'samples': 11234688, 'steps': 58513, 'loss/train': 1.0300136804580688} 08/30/2021 23:43:21 - INFO - __main__ - Step 58515: {'lr': 0.00034067764958478283, 'samples': 11234880, 'steps': 58514, 'loss/train': 1.3457248210906982} 08/30/2021 23:43:22 - INFO - __main__ - Step 58516: {'lr': 0.0003406727041995825, 'samples': 11235072, 'steps': 58515, 'loss/train': 1.3284367322921753} 08/30/2021 23:43:22 - INFO - __main__ - Step 58517: {'lr': 0.00034066775877352644, 'samples': 11235264, 'steps': 58516, 'loss/train': 0.7124446034431458} 08/30/2021 23:43:23 - INFO - __main__ - Step 58518: {'lr': 0.00034066281330661697, 'samples': 11235456, 'steps': 58517, 'loss/train': 0.8736456632614136} 08/30/2021 23:43:23 - INFO - __main__ - Step 58519: {'lr': 0.0003406578677988562, 'samples': 11235648, 'steps': 58518, 'loss/train': 1.5253947973251343} 08/30/2021 23:43:23 - INFO - __main__ - Step 58520: {'lr': 0.00034065292225024643, 'samples': 11235840, 'steps': 58519, 'loss/train': 1.394162893295288} 08/30/2021 23:43:25 - INFO - __main__ - Step 58521: {'lr': 0.0003406479766607898, 'samples': 11236032, 'steps': 58520, 'loss/train': 0.8299336433410645} 08/30/2021 23:43:25 - INFO - __main__ - Step 58522: {'lr': 0.00034064303103048863, 'samples': 11236224, 'steps': 58521, 'loss/train': 1.7708333730697632} 08/30/2021 23:43:26 - INFO - __main__ - Step 58523: {'lr': 0.000340638085359345, 'samples': 11236416, 'steps': 58522, 'loss/train': 1.3864572048187256} 08/30/2021 23:43:26 - INFO - __main__ - Step 58524: {'lr': 0.00034063313964736135, 'samples': 11236608, 'steps': 58523, 'loss/train': 1.2743518352508545} 08/30/2021 23:43:26 - INFO - __main__ - Step 58525: {'lr': 0.0003406281938945398, 'samples': 11236800, 'steps': 58524, 'loss/train': 1.696038842201233} 08/30/2021 23:43:28 - INFO - __main__ - Step 58526: {'lr': 0.0003406232481008825, 'samples': 11236992, 'steps': 58525, 'loss/train': 1.4155510663986206} 08/30/2021 23:43:28 - INFO - __main__ - Step 58527: {'lr': 0.0003406183022663919, 'samples': 11237184, 'steps': 58526, 'loss/train': 0.8133142590522766} 08/30/2021 23:43:29 - INFO - __main__ - Step 58528: {'lr': 0.00034061335639107006, 'samples': 11237376, 'steps': 58527, 'loss/train': 1.2449642419815063} 08/30/2021 23:43:29 - INFO - __main__ - Step 58529: {'lr': 0.0003406084104749192, 'samples': 11237568, 'steps': 58528, 'loss/train': 1.313981533050537} 08/30/2021 23:43:29 - INFO - __main__ - Step 58530: {'lr': 0.00034060346451794156, 'samples': 11237760, 'steps': 58529, 'loss/train': 1.017622947692871} 08/30/2021 23:43:31 - INFO - __main__ - Step 58531: {'lr': 0.0003405985185201394, 'samples': 11237952, 'steps': 58530, 'loss/train': 1.13120698928833} 08/30/2021 23:43:32 - INFO - __main__ - Step 58532: {'lr': 0.000340593572481515, 'samples': 11238144, 'steps': 58531, 'loss/train': 1.9550281763076782} 08/30/2021 23:43:32 - INFO - __main__ - Step 58533: {'lr': 0.0003405886264020706, 'samples': 11238336, 'steps': 58532, 'loss/train': 1.1073040962219238} 08/30/2021 23:43:32 - INFO - __main__ - Step 58534: {'lr': 0.0003405836802818082, 'samples': 11238528, 'steps': 58533, 'loss/train': 0.8942179679870605} 08/30/2021 23:43:33 - INFO - __main__ - Step 58535: {'lr': 0.00034057873412073026, 'samples': 11238720, 'steps': 58534, 'loss/train': 0.8154551982879639} 08/30/2021 23:43:35 - INFO - __main__ - Step 58536: {'lr': 0.0003405737879188389, 'samples': 11238912, 'steps': 58535, 'loss/train': 0.7828736305236816} 08/30/2021 23:43:35 - INFO - __main__ - Step 58537: {'lr': 0.0003405688416761364, 'samples': 11239104, 'steps': 58536, 'loss/train': 1.2096621990203857} 08/30/2021 23:43:36 - INFO - __main__ - Step 58538: {'lr': 0.00034056389539262506, 'samples': 11239296, 'steps': 58537, 'loss/train': 1.1198557615280151} 08/30/2021 23:43:36 - INFO - __main__ - Step 58539: {'lr': 0.000340558949068307, 'samples': 11239488, 'steps': 58538, 'loss/train': 1.1630693674087524} 08/30/2021 23:43:37 - INFO - __main__ - Step 58540: {'lr': 0.0003405540027031845, 'samples': 11239680, 'steps': 58539, 'loss/train': 1.561592698097229} 08/30/2021 23:43:38 - INFO - __main__ - Step 58541: {'lr': 0.00034054905629725965, 'samples': 11239872, 'steps': 58540, 'loss/train': 1.2983131408691406} 08/30/2021 23:43:39 - INFO - __main__ - Step 58542: {'lr': 0.00034054410985053483, 'samples': 11240064, 'steps': 58541, 'loss/train': 1.3339262008666992} 08/30/2021 23:43:39 - INFO - __main__ - Step 58543: {'lr': 0.00034053916336301225, 'samples': 11240256, 'steps': 58542, 'loss/train': 1.4180879592895508} 08/30/2021 23:43:39 - INFO - __main__ - Step 58544: {'lr': 0.00034053421683469416, 'samples': 11240448, 'steps': 58543, 'loss/train': 1.3751170635223389} 08/30/2021 23:43:40 - INFO - __main__ - Step 58545: {'lr': 0.00034052927026558265, 'samples': 11240640, 'steps': 58544, 'loss/train': 0.98646080493927} 08/30/2021 23:43:40 - INFO - __main__ - Step 58546: {'lr': 0.00034052432365568015, 'samples': 11240832, 'steps': 58545, 'loss/train': 0.5625841021537781} 08/30/2021 23:43:41 - INFO - __main__ - Step 58547: {'lr': 0.0003405193770049888, 'samples': 11241024, 'steps': 58546, 'loss/train': 1.4577291011810303} 08/30/2021 23:43:42 - INFO - __main__ - Step 58548: {'lr': 0.0003405144303135108, 'samples': 11241216, 'steps': 58547, 'loss/train': 1.2476330995559692} 08/30/2021 23:43:42 - INFO - __main__ - Step 58549: {'lr': 0.00034050948358124836, 'samples': 11241408, 'steps': 58548, 'loss/train': 1.0030964612960815} 08/30/2021 23:43:43 - INFO - __main__ - Step 58550: {'lr': 0.00034050453680820373, 'samples': 11241600, 'steps': 58549, 'loss/train': 1.7929127216339111} 08/30/2021 23:43:43 - INFO - __main__ - Step 58551: {'lr': 0.0003404995899943791, 'samples': 11241792, 'steps': 58550, 'loss/train': 1.6089800596237183} 08/30/2021 23:43:44 - INFO - __main__ - Step 58552: {'lr': 0.00034049464313977684, 'samples': 11241984, 'steps': 58551, 'loss/train': 1.3833897113800049} 08/30/2021 23:43:45 - INFO - __main__ - Step 58553: {'lr': 0.0003404896962443991, 'samples': 11242176, 'steps': 58552, 'loss/train': 1.0605577230453491} 08/30/2021 23:43:45 - INFO - __main__ - Step 58554: {'lr': 0.0003404847493082481, 'samples': 11242368, 'steps': 58553, 'loss/train': 0.8979097604751587} 08/30/2021 23:43:46 - INFO - __main__ - Step 58555: {'lr': 0.000340479802331326, 'samples': 11242560, 'steps': 58554, 'loss/train': 4.266524791717529} 08/30/2021 23:43:46 - INFO - __main__ - Step 58556: {'lr': 0.0003404748553136351, 'samples': 11242752, 'steps': 58555, 'loss/train': 1.3507206439971924} 08/30/2021 23:43:47 - INFO - __main__ - Step 58557: {'lr': 0.00034046990825517765, 'samples': 11242944, 'steps': 58556, 'loss/train': 1.5242642164230347} 08/30/2021 23:43:48 - INFO - __main__ - Step 58558: {'lr': 0.0003404649611559559, 'samples': 11243136, 'steps': 58557, 'loss/train': 1.3444191217422485} 08/30/2021 23:43:48 - INFO - __main__ - Step 58559: {'lr': 0.0003404600140159719, 'samples': 11243328, 'steps': 58558, 'loss/train': 1.7055398225784302} 08/30/2021 23:43:49 - INFO - __main__ - Step 58560: {'lr': 0.0003404550668352282, 'samples': 11243520, 'steps': 58559, 'loss/train': 0.5438639521598816} 08/30/2021 23:43:49 - INFO - __main__ - Step 58561: {'lr': 0.00034045011961372676, 'samples': 11243712, 'steps': 58560, 'loss/train': 1.2897387742996216} 08/30/2021 23:43:50 - INFO - __main__ - Step 58562: {'lr': 0.0003404451723514699, 'samples': 11243904, 'steps': 58561, 'loss/train': 1.2012020349502563} 08/30/2021 23:43:51 - INFO - __main__ - Step 58563: {'lr': 0.00034044022504845986, 'samples': 11244096, 'steps': 58562, 'loss/train': 1.4125726222991943} 08/30/2021 23:43:51 - INFO - __main__ - Step 58564: {'lr': 0.00034043527770469874, 'samples': 11244288, 'steps': 58563, 'loss/train': 1.2554422616958618} 08/30/2021 23:43:52 - INFO - __main__ - Step 58565: {'lr': 0.00034043033032018897, 'samples': 11244480, 'steps': 58564, 'loss/train': 1.2383854389190674} 08/30/2021 23:43:52 - INFO - __main__ - Step 58566: {'lr': 0.00034042538289493266, 'samples': 11244672, 'steps': 58565, 'loss/train': 2.2003026008605957} 08/30/2021 23:43:54 - INFO - __main__ - Step 58567: {'lr': 0.00034042043542893214, 'samples': 11244864, 'steps': 58566, 'loss/train': 0.8212010860443115} 08/30/2021 23:43:54 - INFO - __main__ - Step 58568: {'lr': 0.0003404154879221895, 'samples': 11245056, 'steps': 58567, 'loss/train': 1.3356879949569702} 08/30/2021 23:43:54 - INFO - __main__ - Step 58569: {'lr': 0.00034041054037470703, 'samples': 11245248, 'steps': 58568, 'loss/train': 1.1337552070617676} 08/30/2021 23:43:55 - INFO - __main__ - Step 58570: {'lr': 0.00034040559278648695, 'samples': 11245440, 'steps': 58569, 'loss/train': 1.671465516090393} 08/30/2021 23:43:55 - INFO - __main__ - Step 58571: {'lr': 0.00034040064515753154, 'samples': 11245632, 'steps': 58570, 'loss/train': 2.649855852127075} 08/30/2021 23:43:57 - INFO - __main__ - Step 58572: {'lr': 0.000340395697487843, 'samples': 11245824, 'steps': 58571, 'loss/train': 1.4615247249603271} 08/30/2021 23:43:57 - INFO - __main__ - Step 58573: {'lr': 0.00034039074977742356, 'samples': 11246016, 'steps': 58572, 'loss/train': 1.5947604179382324} 08/30/2021 23:43:57 - INFO - __main__ - Step 58574: {'lr': 0.00034038580202627543, 'samples': 11246208, 'steps': 58573, 'loss/train': 0.818996787071228} 08/30/2021 23:43:58 - INFO - __main__ - Step 58575: {'lr': 0.0003403808542344009, 'samples': 11246400, 'steps': 58574, 'loss/train': 1.6902351379394531} 08/30/2021 23:43:58 - INFO - __main__ - Step 58576: {'lr': 0.00034037590640180205, 'samples': 11246592, 'steps': 58575, 'loss/train': 1.5108747482299805} 08/30/2021 23:44:00 - INFO - __main__ - Step 58577: {'lr': 0.00034037095852848125, 'samples': 11246784, 'steps': 58576, 'loss/train': 1.452622890472412} 08/30/2021 23:44:00 - INFO - __main__ - Step 58578: {'lr': 0.00034036601061444074, 'samples': 11246976, 'steps': 58577, 'loss/train': 1.2887787818908691} 08/30/2021 23:44:01 - INFO - __main__ - Step 58579: {'lr': 0.00034036106265968263, 'samples': 11247168, 'steps': 58578, 'loss/train': 1.8293622732162476} 08/30/2021 23:44:01 - INFO - __main__ - Step 58580: {'lr': 0.00034035611466420927, 'samples': 11247360, 'steps': 58579, 'loss/train': 1.3499797582626343} 08/30/2021 23:44:01 - INFO - __main__ - Step 58581: {'lr': 0.00034035116662802287, 'samples': 11247552, 'steps': 58580, 'loss/train': 1.6696134805679321} 08/30/2021 23:44:02 - INFO - __main__ - Step 58582: {'lr': 0.0003403462185511256, 'samples': 11247744, 'steps': 58581, 'loss/train': 1.1487683057785034} 08/30/2021 23:44:03 - INFO - __main__ - Step 58583: {'lr': 0.0003403412704335196, 'samples': 11247936, 'steps': 58582, 'loss/train': 1.540053367614746} 08/30/2021 23:44:04 - INFO - __main__ - Step 58584: {'lr': 0.0003403363222752074, 'samples': 11248128, 'steps': 58583, 'loss/train': 0.6843742728233337} 08/30/2021 23:44:04 - INFO - __main__ - Step 58585: {'lr': 0.0003403313740761909, 'samples': 11248320, 'steps': 58584, 'loss/train': 0.9619364738464355} 08/30/2021 23:44:04 - INFO - __main__ - Step 58586: {'lr': 0.00034032642583647254, 'samples': 11248512, 'steps': 58585, 'loss/train': 1.7156606912612915} 08/30/2021 23:44:05 - INFO - __main__ - Step 58587: {'lr': 0.0003403214775560545, 'samples': 11248704, 'steps': 58586, 'loss/train': 0.714686393737793} 08/30/2021 23:44:07 - INFO - __main__ - Step 58588: {'lr': 0.000340316529234939, 'samples': 11248896, 'steps': 58587, 'loss/train': 0.9419745802879333} 08/30/2021 23:44:07 - INFO - __main__ - Step 58589: {'lr': 0.00034031158087312823, 'samples': 11249088, 'steps': 58588, 'loss/train': 0.6213420033454895} 08/30/2021 23:44:08 - INFO - __main__ - Step 58590: {'lr': 0.0003403066324706245, 'samples': 11249280, 'steps': 58589, 'loss/train': 1.5234297513961792} 08/30/2021 23:44:08 - INFO - __main__ - Step 58591: {'lr': 0.00034030168402742996, 'samples': 11249472, 'steps': 58590, 'loss/train': 1.1701195240020752} 08/30/2021 23:44:08 - INFO - __main__ - Step 58592: {'lr': 0.0003402967355435469, 'samples': 11249664, 'steps': 58591, 'loss/train': 1.2197644710540771} 08/30/2021 23:44:10 - INFO - __main__ - Step 58593: {'lr': 0.00034029178701897744, 'samples': 11249856, 'steps': 58592, 'loss/train': 1.5269335508346558} 08/30/2021 23:44:11 - INFO - __main__ - Step 58594: {'lr': 0.00034028683845372407, 'samples': 11250048, 'steps': 58593, 'loss/train': 1.262350082397461} 08/30/2021 23:44:11 - INFO - __main__ - Step 58595: {'lr': 0.00034028188984778867, 'samples': 11250240, 'steps': 58594, 'loss/train': 0.04223304241895676} 08/30/2021 23:44:11 - INFO - __main__ - Step 58596: {'lr': 0.0003402769412011737, 'samples': 11250432, 'steps': 58595, 'loss/train': 0.06784778833389282} 08/30/2021 23:44:12 - INFO - __main__ - Step 58597: {'lr': 0.00034027199251388137, 'samples': 11250624, 'steps': 58596, 'loss/train': 1.508138656616211} 08/30/2021 23:44:12 - INFO - __main__ - Step 58598: {'lr': 0.0003402670437859138, 'samples': 11250816, 'steps': 58597, 'loss/train': 0.7740739583969116} 08/30/2021 23:44:14 - INFO - __main__ - Step 58599: {'lr': 0.0003402620950172733, 'samples': 11251008, 'steps': 58598, 'loss/train': 1.517117977142334} 08/30/2021 23:44:15 - INFO - __main__ - Step 58600: {'lr': 0.00034025714620796225, 'samples': 11251200, 'steps': 58599, 'loss/train': 0.7694681882858276} 08/30/2021 23:44:15 - INFO - __main__ - Step 58601: {'lr': 0.0003402521973579826, 'samples': 11251392, 'steps': 58600, 'loss/train': 1.7149394750595093} 08/30/2021 23:44:15 - INFO - __main__ - Step 58602: {'lr': 0.00034024724846733667, 'samples': 11251584, 'steps': 58601, 'loss/train': 1.1592369079589844} 08/30/2021 23:44:16 - INFO - __main__ - Step 58603: {'lr': 0.0003402422995360268, 'samples': 11251776, 'steps': 58602, 'loss/train': 1.1043370962142944} 08/30/2021 23:44:16 - INFO - __main__ - Step 58604: {'lr': 0.00034023735056405507, 'samples': 11251968, 'steps': 58603, 'loss/train': 1.4269009828567505} 08/30/2021 23:44:18 - INFO - __main__ - Step 58605: {'lr': 0.00034023240155142383, 'samples': 11252160, 'steps': 58604, 'loss/train': 0.9237139821052551} 08/30/2021 23:44:18 - INFO - __main__ - Step 58606: {'lr': 0.00034022745249813523, 'samples': 11252352, 'steps': 58605, 'loss/train': 1.3100820779800415} 08/30/2021 23:44:19 - INFO - __main__ - Step 58607: {'lr': 0.0003402225034041916, 'samples': 11252544, 'steps': 58606, 'loss/train': 1.4197008609771729} 08/30/2021 23:44:19 - INFO - __main__ - Step 58608: {'lr': 0.000340217554269595, 'samples': 11252736, 'steps': 58607, 'loss/train': 4.563615798950195} 08/30/2021 23:44:19 - INFO - __main__ - Step 58609: {'lr': 0.00034021260509434784, 'samples': 11252928, 'steps': 58608, 'loss/train': 1.6371595859527588} 08/30/2021 23:44:21 - INFO - __main__ - Step 58610: {'lr': 0.0003402076558784522, 'samples': 11253120, 'steps': 58609, 'loss/train': 1.1750199794769287} 08/30/2021 23:44:21 - INFO - __main__ - Step 58611: {'lr': 0.00034020270662191046, 'samples': 11253312, 'steps': 58610, 'loss/train': 1.3374089002609253} 08/30/2021 23:44:22 - INFO - __main__ - Step 58612: {'lr': 0.00034019775732472467, 'samples': 11253504, 'steps': 58611, 'loss/train': 5.810057640075684} 08/30/2021 23:44:22 - INFO - __main__ - Step 58613: {'lr': 0.0003401928079868973, 'samples': 11253696, 'steps': 58612, 'loss/train': 2.313693046569824} 08/30/2021 23:44:23 - INFO - __main__ - Step 58614: {'lr': 0.0003401878586084304, 'samples': 11253888, 'steps': 58613, 'loss/train': 1.7675833702087402} 08/30/2021 23:44:23 - INFO - __main__ - Step 58615: {'lr': 0.0003401829091893262, 'samples': 11254080, 'steps': 58614, 'loss/train': 1.431160569190979} 08/30/2021 23:44:25 - INFO - __main__ - Step 58616: {'lr': 0.000340177959729587, 'samples': 11254272, 'steps': 58615, 'loss/train': 3.1185641288757324} 08/30/2021 23:44:25 - INFO - __main__ - Step 58617: {'lr': 0.000340173010229215, 'samples': 11254464, 'steps': 58616, 'loss/train': 2.082977056503296} 08/30/2021 23:44:25 - INFO - __main__ - Step 58618: {'lr': 0.0003401680606882124, 'samples': 11254656, 'steps': 58617, 'loss/train': 1.5103776454925537} 08/30/2021 23:44:26 - INFO - __main__ - Step 58619: {'lr': 0.0003401631111065815, 'samples': 11254848, 'steps': 58618, 'loss/train': 1.5038206577301025} 08/30/2021 23:44:26 - INFO - __main__ - Step 58620: {'lr': 0.0003401581614843244, 'samples': 11255040, 'steps': 58619, 'loss/train': 1.5555760860443115} 08/30/2021 23:44:26 - INFO - __main__ - Step 58621: {'lr': 0.00034015321182144357, 'samples': 11255232, 'steps': 58620, 'loss/train': 1.083202838897705} 08/30/2021 23:44:28 - INFO - __main__ - Step 58622: {'lr': 0.00034014826211794104, 'samples': 11255424, 'steps': 58621, 'loss/train': 0.03790397197008133} 08/30/2021 23:44:28 - INFO - __main__ - Step 58623: {'lr': 0.0003401433123738191, 'samples': 11255616, 'steps': 58622, 'loss/train': 1.2019463777542114} 08/30/2021 23:44:29 - INFO - __main__ - Step 58624: {'lr': 0.00034013836258907994, 'samples': 11255808, 'steps': 58623, 'loss/train': 1.3544248342514038} 08/30/2021 23:44:29 - INFO - __main__ - Step 58625: {'lr': 0.0003401334127637258, 'samples': 11256000, 'steps': 58624, 'loss/train': 1.3162786960601807} 08/30/2021 23:44:29 - INFO - __main__ - Step 58626: {'lr': 0.000340128462897759, 'samples': 11256192, 'steps': 58625, 'loss/train': 1.0081450939178467} 08/30/2021 23:44:31 - INFO - __main__ - Step 58627: {'lr': 0.0003401235129911817, 'samples': 11256384, 'steps': 58626, 'loss/train': 1.1143519878387451} 08/30/2021 23:44:31 - INFO - __main__ - Step 58628: {'lr': 0.0003401185630439961, 'samples': 11256576, 'steps': 58627, 'loss/train': 1.4830524921417236} 08/30/2021 23:44:32 - INFO - __main__ - Step 58629: {'lr': 0.0003401136130562045, 'samples': 11256768, 'steps': 58628, 'loss/train': 1.7404817342758179} 08/30/2021 23:44:32 - INFO - __main__ - Step 58630: {'lr': 0.0003401086630278091, 'samples': 11256960, 'steps': 58629, 'loss/train': 2.3203773498535156} 08/30/2021 23:44:33 - INFO - __main__ - Step 58631: {'lr': 0.00034010371295881207, 'samples': 11257152, 'steps': 58630, 'loss/train': 1.4743072986602783} 08/30/2021 23:44:33 - INFO - __main__ - Step 58632: {'lr': 0.00034009876284921576, 'samples': 11257344, 'steps': 58631, 'loss/train': 1.2115086317062378} 08/30/2021 23:44:34 - INFO - __main__ - Step 58633: {'lr': 0.00034009381269902236, 'samples': 11257536, 'steps': 58632, 'loss/train': 1.8946534395217896} 08/30/2021 23:44:35 - INFO - __main__ - Step 58634: {'lr': 0.000340088862508234, 'samples': 11257728, 'steps': 58633, 'loss/train': 1.355635643005371} 08/30/2021 23:44:35 - INFO - __main__ - Step 58635: {'lr': 0.00034008391227685305, 'samples': 11257920, 'steps': 58634, 'loss/train': 1.6156717538833618} 08/30/2021 23:44:35 - INFO - __main__ - Step 58636: {'lr': 0.00034007896200488163, 'samples': 11258112, 'steps': 58635, 'loss/train': 1.2679417133331299} 08/30/2021 23:44:36 - INFO - __main__ - Step 58637: {'lr': 0.0003400740116923221, 'samples': 11258304, 'steps': 58636, 'loss/train': 1.526999831199646} 08/30/2021 23:44:37 - INFO - __main__ - Step 58638: {'lr': 0.00034006906133917655, 'samples': 11258496, 'steps': 58637, 'loss/train': 1.8030425310134888} 08/30/2021 23:44:38 - INFO - __main__ - Step 58639: {'lr': 0.0003400641109454473, 'samples': 11258688, 'steps': 58638, 'loss/train': 1.4153028726577759} 08/30/2021 23:44:38 - INFO - __main__ - Step 58640: {'lr': 0.0003400591605111364, 'samples': 11258880, 'steps': 58639, 'loss/train': 1.526519775390625} 08/30/2021 23:44:38 - INFO - __main__ - Step 58641: {'lr': 0.0003400542100362464, 'samples': 11259072, 'steps': 58640, 'loss/train': 1.9305524826049805} 08/30/2021 23:44:39 - INFO - __main__ - Step 58642: {'lr': 0.0003400492595207793, 'samples': 11259264, 'steps': 58641, 'loss/train': 1.3647828102111816} 08/30/2021 23:44:41 - INFO - __main__ - Step 58643: {'lr': 0.00034004430896473743, 'samples': 11259456, 'steps': 58642, 'loss/train': 1.3243318796157837} 08/30/2021 23:44:41 - INFO - __main__ - Step 58644: {'lr': 0.000340039358368123, 'samples': 11259648, 'steps': 58643, 'loss/train': 1.6915072202682495} 08/30/2021 23:44:42 - INFO - __main__ - Step 58645: {'lr': 0.00034003440773093817, 'samples': 11259840, 'steps': 58644, 'loss/train': 1.0202341079711914} 08/30/2021 23:44:42 - INFO - __main__ - Step 58646: {'lr': 0.0003400294570531852, 'samples': 11260032, 'steps': 58645, 'loss/train': 2.145146608352661} 08/30/2021 23:44:42 - INFO - __main__ - Step 58647: {'lr': 0.0003400245063348664, 'samples': 11260224, 'steps': 58646, 'loss/train': 1.1356542110443115} 08/30/2021 23:44:44 - INFO - __main__ - Step 58648: {'lr': 0.000340019555575984, 'samples': 11260416, 'steps': 58647, 'loss/train': 1.5575954914093018} 08/30/2021 23:44:45 - INFO - __main__ - Step 58649: {'lr': 0.00034001460477654013, 'samples': 11260608, 'steps': 58648, 'loss/train': 0.9656021595001221} 08/30/2021 23:44:45 - INFO - __main__ - Step 58650: {'lr': 0.00034000965393653703, 'samples': 11260800, 'steps': 58649, 'loss/train': 0.6885381937026978} 08/30/2021 23:44:45 - INFO - __main__ - Step 58651: {'lr': 0.00034000470305597697, 'samples': 11260992, 'steps': 58650, 'loss/train': 1.862221360206604} 08/30/2021 23:44:46 - INFO - __main__ - Step 58652: {'lr': 0.0003399997521348622, 'samples': 11261184, 'steps': 58651, 'loss/train': 0.7823901176452637} 08/30/2021 23:44:47 - INFO - __main__ - Step 58653: {'lr': 0.00033999480117319494, 'samples': 11261376, 'steps': 58652, 'loss/train': 1.2422887086868286} 08/30/2021 23:44:48 - INFO - __main__ - Step 58654: {'lr': 0.0003399898501709774, 'samples': 11261568, 'steps': 58653, 'loss/train': 1.086638331413269} 08/30/2021 23:44:48 - INFO - __main__ - Step 58655: {'lr': 0.00033998489912821187, 'samples': 11261760, 'steps': 58654, 'loss/train': 1.4552615880966187} 08/30/2021 23:44:48 - INFO - __main__ - Step 58656: {'lr': 0.00033997994804490047, 'samples': 11261952, 'steps': 58655, 'loss/train': 1.1426972150802612} 08/30/2021 23:44:49 - INFO - __main__ - Step 58657: {'lr': 0.0003399749969210455, 'samples': 11262144, 'steps': 58656, 'loss/train': 1.7824389934539795} 08/30/2021 23:44:50 - INFO - __main__ - Step 58658: {'lr': 0.0003399700457566492, 'samples': 11262336, 'steps': 58657, 'loss/train': 2.321087121963501} 08/30/2021 23:44:51 - INFO - __main__ - Step 58659: {'lr': 0.00033996509455171375, 'samples': 11262528, 'steps': 58658, 'loss/train': 1.4311717748641968} 08/30/2021 23:44:51 - INFO - __main__ - Step 58660: {'lr': 0.0003399601433062415, 'samples': 11262720, 'steps': 58659, 'loss/train': 1.6147359609603882} 08/30/2021 23:44:51 - INFO - __main__ - Step 58661: {'lr': 0.00033995519202023453, 'samples': 11262912, 'steps': 58660, 'loss/train': 1.6489475965499878} 08/30/2021 23:44:52 - INFO - __main__ - Step 58662: {'lr': 0.00033995024069369517, 'samples': 11263104, 'steps': 58661, 'loss/train': 1.4745396375656128} 08/30/2021 23:44:53 - INFO - __main__ - Step 58663: {'lr': 0.0003399452893266256, 'samples': 11263296, 'steps': 58662, 'loss/train': 0.812257707118988} 08/30/2021 23:44:54 - INFO - __main__ - Step 58664: {'lr': 0.000339940337919028, 'samples': 11263488, 'steps': 58663, 'loss/train': 0.9347754120826721} 08/30/2021 23:44:54 - INFO - __main__ - Step 58665: {'lr': 0.0003399353864709048, 'samples': 11263680, 'steps': 58664, 'loss/train': 0.5399097204208374} 08/30/2021 23:44:54 - INFO - __main__ - Step 58666: {'lr': 0.000339930434982258, 'samples': 11263872, 'steps': 58665, 'loss/train': 1.2221934795379639} 08/30/2021 23:44:55 - INFO - __main__ - Step 58667: {'lr': 0.00033992548345309, 'samples': 11264064, 'steps': 58666, 'loss/train': 1.701217532157898} 08/30/2021 23:44:56 - INFO - __main__ - Step 58668: {'lr': 0.000339920531883403, 'samples': 11264256, 'steps': 58667, 'loss/train': 1.641194224357605} 08/30/2021 23:44:57 - INFO - __main__ - Step 58669: {'lr': 0.0003399155802731991, 'samples': 11264448, 'steps': 58668, 'loss/train': 1.5220270156860352} 08/30/2021 23:44:57 - INFO - __main__ - Step 58670: {'lr': 0.0003399106286224807, 'samples': 11264640, 'steps': 58669, 'loss/train': 1.4254704713821411} 08/30/2021 23:44:57 - INFO - __main__ - Step 58671: {'lr': 0.0003399056769312499, 'samples': 11264832, 'steps': 58670, 'loss/train': 1.2846100330352783} 08/30/2021 23:44:58 - INFO - __main__ - Step 58672: {'lr': 0.000339900725199509, 'samples': 11265024, 'steps': 58671, 'loss/train': 1.6533279418945312} 08/30/2021 23:44:59 - INFO - __main__ - Step 58673: {'lr': 0.0003398957734272602, 'samples': 11265216, 'steps': 58672, 'loss/train': 0.9581900835037231} 08/30/2021 23:45:00 - INFO - __main__ - Step 58674: {'lr': 0.00033989082161450584, 'samples': 11265408, 'steps': 58673, 'loss/train': 0.7161738872528076} 08/30/2021 23:45:00 - INFO - __main__ - Step 58675: {'lr': 0.000339885869761248, 'samples': 11265600, 'steps': 58674, 'loss/train': 1.6511728763580322} 08/30/2021 23:45:00 - INFO - __main__ - Step 58676: {'lr': 0.000339880917867489, 'samples': 11265792, 'steps': 58675, 'loss/train': 1.2187076807022095} 08/30/2021 23:45:01 - INFO - __main__ - Step 58677: {'lr': 0.00033987596593323103, 'samples': 11265984, 'steps': 58676, 'loss/train': 1.5846315622329712} 08/30/2021 23:45:02 - INFO - __main__ - Step 58678: {'lr': 0.00033987101395847636, 'samples': 11266176, 'steps': 58677, 'loss/train': 1.285315990447998} 08/30/2021 23:45:03 - INFO - __main__ - Step 58679: {'lr': 0.00033986606194322716, 'samples': 11266368, 'steps': 58678, 'loss/train': 1.5435011386871338} 08/30/2021 23:45:03 - INFO - __main__ - Step 58680: {'lr': 0.00033986110988748567, 'samples': 11266560, 'steps': 58679, 'loss/train': 1.130240797996521} 08/30/2021 23:45:03 - INFO - __main__ - Step 58681: {'lr': 0.00033985615779125427, 'samples': 11266752, 'steps': 58680, 'loss/train': 1.0424315929412842} 08/30/2021 23:45:04 - INFO - __main__ - Step 58682: {'lr': 0.00033985120565453497, 'samples': 11266944, 'steps': 58681, 'loss/train': 1.1715854406356812} 08/30/2021 23:45:04 - INFO - __main__ - Step 58683: {'lr': 0.00033984625347733015, 'samples': 11267136, 'steps': 58682, 'loss/train': 1.004608154296875} 08/30/2021 23:45:06 - INFO - __main__ - Step 58684: {'lr': 0.000339841301259642, 'samples': 11267328, 'steps': 58683, 'loss/train': 1.897889256477356} 08/30/2021 23:45:06 - INFO - __main__ - Step 58685: {'lr': 0.0003398363490014727, 'samples': 11267520, 'steps': 58684, 'loss/train': 1.8558295965194702} 08/30/2021 23:45:06 - INFO - __main__ - Step 58686: {'lr': 0.0003398313967028245, 'samples': 11267712, 'steps': 58685, 'loss/train': 1.3434743881225586} 08/30/2021 23:45:07 - INFO - __main__ - Step 58687: {'lr': 0.00033982644436369975, 'samples': 11267904, 'steps': 58686, 'loss/train': 0.8997907638549805} 08/30/2021 23:45:07 - INFO - __main__ - Step 58688: {'lr': 0.00033982149198410057, 'samples': 11268096, 'steps': 58687, 'loss/train': 1.4189918041229248} 08/30/2021 23:45:09 - INFO - __main__ - Step 58689: {'lr': 0.0003398165395640292, 'samples': 11268288, 'steps': 58688, 'loss/train': 0.751264750957489} 08/30/2021 23:45:09 - INFO - __main__ - Step 58690: {'lr': 0.00033981158710348787, 'samples': 11268480, 'steps': 58689, 'loss/train': 0.5940876007080078} 08/30/2021 23:45:09 - INFO - __main__ - Step 58691: {'lr': 0.0003398066346024788, 'samples': 11268672, 'steps': 58690, 'loss/train': 1.5481352806091309} 08/30/2021 23:45:10 - INFO - __main__ - Step 58692: {'lr': 0.0003398016820610043, 'samples': 11268864, 'steps': 58691, 'loss/train': 1.2806178331375122} 08/30/2021 23:45:10 - INFO - __main__ - Step 58693: {'lr': 0.00033979672947906646, 'samples': 11269056, 'steps': 58692, 'loss/train': 1.1124917268753052} 08/30/2021 23:45:12 - INFO - __main__ - Step 58694: {'lr': 0.0003397917768566677, 'samples': 11269248, 'steps': 58693, 'loss/train': 1.04927396774292} 08/30/2021 23:45:13 - INFO - __main__ - Step 58695: {'lr': 0.0003397868241938101, 'samples': 11269440, 'steps': 58694, 'loss/train': 2.4703054428100586} 08/30/2021 23:45:13 - INFO - __main__ - Step 58696: {'lr': 0.00033978187149049597, 'samples': 11269632, 'steps': 58695, 'loss/train': 0.9833458662033081} 08/30/2021 23:45:13 - INFO - __main__ - Step 58697: {'lr': 0.0003397769187467275, 'samples': 11269824, 'steps': 58696, 'loss/train': 1.6109654903411865} 08/30/2021 23:45:14 - INFO - __main__ - Step 58698: {'lr': 0.0003397719659625069, 'samples': 11270016, 'steps': 58697, 'loss/train': 1.714380145072937} 08/30/2021 23:45:16 - INFO - __main__ - Step 58699: {'lr': 0.0003397670131378365, 'samples': 11270208, 'steps': 58698, 'loss/train': 1.5342620611190796} 08/30/2021 23:45:17 - INFO - __main__ - Step 58700: {'lr': 0.0003397620602727184, 'samples': 11270400, 'steps': 58699, 'loss/train': 1.062547206878662} 08/30/2021 23:45:17 - INFO - __main__ - Step 58701: {'lr': 0.00033975710736715504, 'samples': 11270592, 'steps': 58700, 'loss/train': 1.8590065240859985} 08/30/2021 23:45:17 - INFO - __main__ - Step 58702: {'lr': 0.00033975215442114836, 'samples': 11270784, 'steps': 58701, 'loss/train': 0.4686267673969269} 08/30/2021 23:45:18 - INFO - __main__ - Step 58703: {'lr': 0.00033974720143470084, 'samples': 11270976, 'steps': 58702, 'loss/train': 0.417143851518631} 08/30/2021 23:45:18 - INFO - __main__ - Step 58704: {'lr': 0.00033974224840781453, 'samples': 11271168, 'steps': 58703, 'loss/train': 0.34511134028434753} 08/30/2021 23:45:19 - INFO - __main__ - Step 58705: {'lr': 0.0003397372953404918, 'samples': 11271360, 'steps': 58704, 'loss/train': 0.9673738479614258} 08/30/2021 23:45:20 - INFO - __main__ - Step 58706: {'lr': 0.0003397323422327348, 'samples': 11271552, 'steps': 58705, 'loss/train': 1.2641791105270386} 08/30/2021 23:45:20 - INFO - __main__ - Step 58707: {'lr': 0.0003397273890845458, 'samples': 11271744, 'steps': 58706, 'loss/train': 1.498709797859192} 08/30/2021 23:45:21 - INFO - __main__ - Step 58708: {'lr': 0.0003397224358959271, 'samples': 11271936, 'steps': 58707, 'loss/train': 1.4560626745224} 08/30/2021 23:45:21 - INFO - __main__ - Step 58709: {'lr': 0.0003397174826668808, 'samples': 11272128, 'steps': 58708, 'loss/train': 1.497673511505127} 08/30/2021 23:45:23 - INFO - __main__ - Step 58710: {'lr': 0.00033971252939740915, 'samples': 11272320, 'steps': 58709, 'loss/train': 1.4968241453170776} 08/30/2021 23:45:23 - INFO - __main__ - Step 58711: {'lr': 0.00033970757608751446, 'samples': 11272512, 'steps': 58710, 'loss/train': 1.7436162233352661} 08/30/2021 23:45:23 - INFO - __main__ - Step 58712: {'lr': 0.0003397026227371989, 'samples': 11272704, 'steps': 58711, 'loss/train': 1.6594783067703247} 08/30/2021 23:45:24 - INFO - __main__ - Step 58713: {'lr': 0.0003396976693464647, 'samples': 11272896, 'steps': 58712, 'loss/train': 1.2630974054336548} 08/30/2021 23:45:24 - INFO - __main__ - Step 58714: {'lr': 0.0003396927159153141, 'samples': 11273088, 'steps': 58713, 'loss/train': 1.672326683998108} 08/30/2021 23:45:26 - INFO - __main__ - Step 58715: {'lr': 0.0003396877624437495, 'samples': 11273280, 'steps': 58714, 'loss/train': 1.6367125511169434} 08/30/2021 23:45:26 - INFO - __main__ - Step 58716: {'lr': 0.0003396828089317728, 'samples': 11273472, 'steps': 58715, 'loss/train': 1.2915154695510864} 08/30/2021 23:45:26 - INFO - __main__ - Step 58717: {'lr': 0.0003396778553793865, 'samples': 11273664, 'steps': 58716, 'loss/train': 1.3781403303146362} 08/30/2021 23:45:27 - INFO - __main__ - Step 58718: {'lr': 0.00033967290178659273, 'samples': 11273856, 'steps': 58717, 'loss/train': 1.4711723327636719} 08/30/2021 23:45:27 - INFO - __main__ - Step 58719: {'lr': 0.0003396679481533937, 'samples': 11274048, 'steps': 58718, 'loss/train': 1.56981360912323} 08/30/2021 23:45:29 - INFO - __main__ - Step 58720: {'lr': 0.0003396629944797917, 'samples': 11274240, 'steps': 58719, 'loss/train': 1.521945595741272} 08/30/2021 23:45:29 - INFO - __main__ - Step 58721: {'lr': 0.0003396580407657889, 'samples': 11274432, 'steps': 58720, 'loss/train': 1.1058169603347778} 08/30/2021 23:45:30 - INFO - __main__ - Step 58722: {'lr': 0.0003396530870113877, 'samples': 11274624, 'steps': 58721, 'loss/train': 1.5603090524673462} 08/30/2021 23:45:30 - INFO - __main__ - Step 58723: {'lr': 0.0003396481332165901, 'samples': 11274816, 'steps': 58722, 'loss/train': 0.8087930083274841} 08/30/2021 23:45:31 - INFO - __main__ - Step 58724: {'lr': 0.00033964317938139845, 'samples': 11275008, 'steps': 58723, 'loss/train': 1.806008219718933} 08/30/2021 23:45:31 - INFO - __main__ - Step 58725: {'lr': 0.00033963822550581494, 'samples': 11275200, 'steps': 58724, 'loss/train': 1.690191388130188} 08/30/2021 23:45:32 - INFO - __main__ - Step 58726: {'lr': 0.0003396332715898418, 'samples': 11275392, 'steps': 58725, 'loss/train': 1.7882498502731323} 08/30/2021 23:45:33 - INFO - __main__ - Step 58727: {'lr': 0.00033962831763348133, 'samples': 11275584, 'steps': 58726, 'loss/train': 1.1820712089538574} 08/30/2021 23:45:33 - INFO - __main__ - Step 58728: {'lr': 0.00033962336363673585, 'samples': 11275776, 'steps': 58727, 'loss/train': 0.594863772392273} 08/30/2021 23:45:34 - INFO - __main__ - Step 58729: {'lr': 0.00033961840959960735, 'samples': 11275968, 'steps': 58728, 'loss/train': 1.3980870246887207} 08/30/2021 23:45:34 - INFO - __main__ - Step 58730: {'lr': 0.0003396134555220982, 'samples': 11276160, 'steps': 58729, 'loss/train': 0.8610799312591553} 08/30/2021 23:45:36 - INFO - __main__ - Step 58731: {'lr': 0.0003396085014042105, 'samples': 11276352, 'steps': 58730, 'loss/train': 1.176416277885437} 08/30/2021 23:45:37 - INFO - __main__ - Step 58732: {'lr': 0.00033960354724594665, 'samples': 11276544, 'steps': 58731, 'loss/train': 1.1247687339782715} 08/30/2021 23:45:37 - INFO - __main__ - Step 58733: {'lr': 0.0003395985930473089, 'samples': 11276736, 'steps': 58732, 'loss/train': 1.7837703227996826} 08/30/2021 23:45:37 - INFO - __main__ - Step 58734: {'lr': 0.00033959363880829935, 'samples': 11276928, 'steps': 58733, 'loss/train': 1.5966030359268188} 08/30/2021 23:45:38 - INFO - __main__ - Step 58735: {'lr': 0.00033958868452892035, 'samples': 11277120, 'steps': 58734, 'loss/train': 1.230141520500183} 08/30/2021 23:45:38 - INFO - __main__ - Step 58736: {'lr': 0.000339583730209174, 'samples': 11277312, 'steps': 58735, 'loss/train': 1.9571155309677124} 08/30/2021 23:45:40 - INFO - __main__ - Step 58737: {'lr': 0.0003395787758490626, 'samples': 11277504, 'steps': 58736, 'loss/train': 0.08838306367397308} 08/30/2021 23:45:40 - INFO - __main__ - Step 58738: {'lr': 0.0003395738214485884, 'samples': 11277696, 'steps': 58737, 'loss/train': 1.3713037967681885} 08/30/2021 23:45:40 - INFO - __main__ - Step 58739: {'lr': 0.0003395688670077536, 'samples': 11277888, 'steps': 58738, 'loss/train': 2.0473649501800537} 08/30/2021 23:45:41 - INFO - __main__ - Step 58740: {'lr': 0.0003395639125265605, 'samples': 11278080, 'steps': 58739, 'loss/train': 1.5242501497268677} 08/30/2021 23:45:41 - INFO - __main__ - Step 58741: {'lr': 0.00033955895800501126, 'samples': 11278272, 'steps': 58740, 'loss/train': 0.818575382232666} 08/30/2021 23:45:43 - INFO - __main__ - Step 58742: {'lr': 0.0003395540034431082, 'samples': 11278464, 'steps': 58741, 'loss/train': 1.6052708625793457} 08/30/2021 23:45:43 - INFO - __main__ - Step 58743: {'lr': 0.0003395490488408534, 'samples': 11278656, 'steps': 58742, 'loss/train': 1.3403186798095703} 08/30/2021 23:45:44 - INFO - __main__ - Step 58744: {'lr': 0.00033954409419824924, 'samples': 11278848, 'steps': 58743, 'loss/train': 0.07083722949028015} 08/30/2021 23:45:44 - INFO - __main__ - Step 58745: {'lr': 0.0003395391395152978, 'samples': 11279040, 'steps': 58744, 'loss/train': 1.3406776189804077} 08/30/2021 23:45:44 - INFO - __main__ - Step 58746: {'lr': 0.0003395341847920015, 'samples': 11279232, 'steps': 58745, 'loss/train': 1.767698049545288} 08/30/2021 23:45:45 - INFO - __main__ - Step 58747: {'lr': 0.00033952923002836244, 'samples': 11279424, 'steps': 58746, 'loss/train': 1.6017245054244995} 08/30/2021 23:45:46 - INFO - __main__ - Step 58748: {'lr': 0.0003395242752243829, 'samples': 11279616, 'steps': 58747, 'loss/train': 1.5462589263916016} 08/30/2021 23:45:47 - INFO - __main__ - Step 58749: {'lr': 0.00033951932038006513, 'samples': 11279808, 'steps': 58748, 'loss/train': 3.0614047050476074} 08/30/2021 23:45:47 - INFO - __main__ - Step 58750: {'lr': 0.00033951436549541124, 'samples': 11280000, 'steps': 58749, 'loss/train': 1.471692442893982} 08/30/2021 23:45:47 - INFO - __main__ - Step 58751: {'lr': 0.0003395094105704236, 'samples': 11280192, 'steps': 58750, 'loss/train': 1.6002084016799927} 08/30/2021 23:45:48 - INFO - __main__ - Step 58752: {'lr': 0.00033950445560510445, 'samples': 11280384, 'steps': 58751, 'loss/train': 1.1745747327804565} 08/30/2021 23:45:50 - INFO - __main__ - Step 58753: {'lr': 0.00033949950059945593, 'samples': 11280576, 'steps': 58752, 'loss/train': 5.314432621002197} 08/30/2021 23:45:50 - INFO - __main__ - Step 58754: {'lr': 0.00033949454555348035, 'samples': 11280768, 'steps': 58753, 'loss/train': 1.212120771408081} 08/30/2021 23:45:51 - INFO - __main__ - Step 58755: {'lr': 0.0003394895904671799, 'samples': 11280960, 'steps': 58754, 'loss/train': 1.1921107769012451} 08/30/2021 23:45:51 - INFO - __main__ - Step 58756: {'lr': 0.00033948463534055683, 'samples': 11281152, 'steps': 58755, 'loss/train': 1.5529626607894897} 08/30/2021 23:45:51 - INFO - __main__ - Step 58757: {'lr': 0.0003394796801736133, 'samples': 11281344, 'steps': 58756, 'loss/train': 1.4435099363327026} 08/30/2021 23:45:53 - INFO - __main__ - Step 58758: {'lr': 0.0003394747249663517, 'samples': 11281536, 'steps': 58757, 'loss/train': 1.6918872594833374} 08/30/2021 23:45:53 - INFO - __main__ - Step 58759: {'lr': 0.0003394697697187741, 'samples': 11281728, 'steps': 58758, 'loss/train': 1.1807827949523926} 08/30/2021 23:45:54 - INFO - __main__ - Step 58760: {'lr': 0.00033946481443088286, 'samples': 11281920, 'steps': 58759, 'loss/train': 1.160259485244751} 08/30/2021 23:45:54 - INFO - __main__ - Step 58761: {'lr': 0.00033945985910268007, 'samples': 11282112, 'steps': 58760, 'loss/train': 1.1233793497085571} 08/30/2021 23:45:54 - INFO - __main__ - Step 58762: {'lr': 0.0003394549037341681, 'samples': 11282304, 'steps': 58761, 'loss/train': 1.3589684963226318} 08/30/2021 23:45:55 - INFO - __main__ - Step 58763: {'lr': 0.00033944994832534915, 'samples': 11282496, 'steps': 58762, 'loss/train': 1.213646411895752} 08/30/2021 23:45:56 - INFO - __main__ - Step 58764: {'lr': 0.0003394449928762254, 'samples': 11282688, 'steps': 58763, 'loss/train': 1.695613145828247} 08/30/2021 23:45:57 - INFO - __main__ - Step 58765: {'lr': 0.0003394400373867991, 'samples': 11282880, 'steps': 58764, 'loss/train': 1.9866008758544922} 08/30/2021 23:45:57 - INFO - __main__ - Step 58766: {'lr': 0.00033943508185707257, 'samples': 11283072, 'steps': 58765, 'loss/train': 0.10850531607866287} 08/30/2021 23:45:57 - INFO - __main__ - Step 58767: {'lr': 0.0003394301262870479, 'samples': 11283264, 'steps': 58766, 'loss/train': 0.7525590658187866} 08/30/2021 23:45:58 - INFO - __main__ - Step 58768: {'lr': 0.00033942517067672744, 'samples': 11283456, 'steps': 58767, 'loss/train': 1.0791841745376587} 08/30/2021 23:45:59 - INFO - __main__ - Step 58769: {'lr': 0.00033942021502611334, 'samples': 11283648, 'steps': 58768, 'loss/train': 2.1386630535125732} 08/30/2021 23:46:00 - INFO - __main__ - Step 58770: {'lr': 0.0003394152593352079, 'samples': 11283840, 'steps': 58769, 'loss/train': 1.8796067237854004} 08/30/2021 23:46:00 - INFO - __main__ - Step 58771: {'lr': 0.0003394103036040133, 'samples': 11284032, 'steps': 58770, 'loss/train': 1.3748698234558105} 08/30/2021 23:46:00 - INFO - __main__ - Step 58772: {'lr': 0.00033940534783253185, 'samples': 11284224, 'steps': 58771, 'loss/train': 1.4511990547180176} 08/30/2021 23:46:01 - INFO - __main__ - Step 58773: {'lr': 0.00033940039202076574, 'samples': 11284416, 'steps': 58772, 'loss/train': 1.3540029525756836} 08/30/2021 23:46:02 - INFO - __main__ - Step 58774: {'lr': 0.0003393954361687172, 'samples': 11284608, 'steps': 58773, 'loss/train': 2.319308042526245} 08/30/2021 23:46:03 - INFO - __main__ - Step 58775: {'lr': 0.0003393904802763883, 'samples': 11284800, 'steps': 58774, 'loss/train': 1.7409207820892334} 08/30/2021 23:46:03 - INFO - __main__ - Step 58776: {'lr': 0.00033938552434378155, 'samples': 11284992, 'steps': 58775, 'loss/train': 1.778612732887268} 08/30/2021 23:46:03 - INFO - __main__ - Step 58777: {'lr': 0.00033938056837089903, 'samples': 11285184, 'steps': 58776, 'loss/train': 2.207735776901245} 08/30/2021 23:46:04 - INFO - __main__ - Step 58778: {'lr': 0.00033937561235774307, 'samples': 11285376, 'steps': 58777, 'loss/train': 1.5242668390274048} 08/30/2021 23:46:05 - INFO - __main__ - Step 58779: {'lr': 0.00033937065630431577, 'samples': 11285568, 'steps': 58778, 'loss/train': 1.7153576612472534} 08/30/2021 23:46:06 - INFO - __main__ - Step 58780: {'lr': 0.00033936570021061947, 'samples': 11285760, 'steps': 58779, 'loss/train': 0.9997885823249817} 08/30/2021 23:46:06 - INFO - __main__ - Step 58781: {'lr': 0.0003393607440766563, 'samples': 11285952, 'steps': 58780, 'loss/train': 1.0471984148025513} 08/30/2021 23:46:06 - INFO - __main__ - Step 58782: {'lr': 0.0003393557879024286, 'samples': 11286144, 'steps': 58781, 'loss/train': 1.6037567853927612} 08/30/2021 23:46:07 - INFO - __main__ - Step 58783: {'lr': 0.00033935083168793855, 'samples': 11286336, 'steps': 58782, 'loss/train': 1.3418024778366089} 08/30/2021 23:46:08 - INFO - __main__ - Step 58784: {'lr': 0.00033934587543318846, 'samples': 11286528, 'steps': 58783, 'loss/train': 0.46251997351646423} 08/30/2021 23:46:09 - INFO - __main__ - Step 58785: {'lr': 0.00033934091913818043, 'samples': 11286720, 'steps': 58784, 'loss/train': 0.38408803939819336} 08/30/2021 23:46:09 - INFO - __main__ - Step 58786: {'lr': 0.0003393359628029168, 'samples': 11286912, 'steps': 58785, 'loss/train': 1.3493787050247192} 08/30/2021 23:46:10 - INFO - __main__ - Step 58787: {'lr': 0.0003393310064273997, 'samples': 11287104, 'steps': 58786, 'loss/train': 1.2061803340911865} 08/30/2021 23:46:10 - INFO - __main__ - Step 58788: {'lr': 0.0003393260500116315, 'samples': 11287296, 'steps': 58787, 'loss/train': 1.2767568826675415} 08/30/2021 23:46:10 - INFO - __main__ - Step 58789: {'lr': 0.0003393210935556143, 'samples': 11287488, 'steps': 58788, 'loss/train': 0.4508485794067383} 08/30/2021 23:46:12 - INFO - __main__ - Step 58790: {'lr': 0.00033931613705935046, 'samples': 11287680, 'steps': 58789, 'loss/train': 0.9270490407943726} 08/30/2021 23:46:13 - INFO - __main__ - Step 58791: {'lr': 0.000339311180522842, 'samples': 11287872, 'steps': 58790, 'loss/train': 1.1681022644042969} 08/30/2021 23:46:13 - INFO - __main__ - Step 58792: {'lr': 0.00033930622394609143, 'samples': 11288064, 'steps': 58791, 'loss/train': 1.6185396909713745} 08/30/2021 23:46:14 - INFO - __main__ - Step 58793: {'lr': 0.00033930126732910083, 'samples': 11288256, 'steps': 58792, 'loss/train': 0.310821533203125} 08/30/2021 23:46:14 - INFO - __main__ - Step 58794: {'lr': 0.0003392963106718725, 'samples': 11288448, 'steps': 58793, 'loss/train': 0.33043384552001953} 08/30/2021 23:46:15 - INFO - __main__ - Step 58795: {'lr': 0.00033929135397440857, 'samples': 11288640, 'steps': 58794, 'loss/train': 1.2291858196258545} 08/30/2021 23:46:16 - INFO - __main__ - Step 58796: {'lr': 0.0003392863972367114, 'samples': 11288832, 'steps': 58795, 'loss/train': 1.4721119403839111} 08/30/2021 23:46:16 - INFO - __main__ - Step 58797: {'lr': 0.0003392814404587831, 'samples': 11289024, 'steps': 58796, 'loss/train': 0.9029848575592041} 08/30/2021 23:46:17 - INFO - __main__ - Step 58798: {'lr': 0.00033927648364062593, 'samples': 11289216, 'steps': 58797, 'loss/train': 1.0951250791549683} 08/30/2021 23:46:17 - INFO - __main__ - Step 58799: {'lr': 0.00033927152678224216, 'samples': 11289408, 'steps': 58798, 'loss/train': 0.37975120544433594} 08/30/2021 23:46:19 - INFO - __main__ - Step 58800: {'lr': 0.00033926656988363406, 'samples': 11289600, 'steps': 58799, 'loss/train': 1.0550575256347656} 08/30/2021 23:46:20 - INFO - __main__ - Step 58801: {'lr': 0.00033926161294480384, 'samples': 11289792, 'steps': 58800, 'loss/train': 1.6219799518585205} 08/30/2021 23:46:20 - INFO - __main__ - Step 58802: {'lr': 0.00033925665596575374, 'samples': 11289984, 'steps': 58801, 'loss/train': 1.3891360759735107} 08/30/2021 23:46:20 - INFO - __main__ - Step 58803: {'lr': 0.00033925169894648586, 'samples': 11290176, 'steps': 58802, 'loss/train': 1.2500232458114624} 08/30/2021 23:46:21 - INFO - __main__ - Step 58804: {'lr': 0.0003392467418870026, 'samples': 11290368, 'steps': 58803, 'loss/train': 1.4036320447921753} 08/30/2021 23:46:23 - INFO - __main__ - Step 58805: {'lr': 0.0003392417847873061, 'samples': 11290560, 'steps': 58804, 'loss/train': 0.954932689666748} 08/30/2021 23:46:23 - INFO - __main__ - Step 58806: {'lr': 0.00033923682764739867, 'samples': 11290752, 'steps': 58805, 'loss/train': 1.85524582862854} 08/30/2021 23:46:24 - INFO - __main__ - Step 58807: {'lr': 0.0003392318704672825, 'samples': 11290944, 'steps': 58806, 'loss/train': 1.5074431896209717} 08/30/2021 23:46:24 - INFO - __main__ - Step 58808: {'lr': 0.00033922691324695975, 'samples': 11291136, 'steps': 58807, 'loss/train': 2.3309195041656494} 08/30/2021 23:46:24 - INFO - __main__ - Step 58809: {'lr': 0.00033922195598643293, 'samples': 11291328, 'steps': 58808, 'loss/train': 0.2112676203250885} 08/30/2021 23:46:25 - INFO - __main__ - Step 58810: {'lr': 0.0003392169986857039, 'samples': 11291520, 'steps': 58809, 'loss/train': 1.3284920454025269} 08/30/2021 23:46:26 - INFO - __main__ - Step 58811: {'lr': 0.0003392120413447751, 'samples': 11291712, 'steps': 58810, 'loss/train': 1.4437609910964966} 08/30/2021 23:46:27 - INFO - __main__ - Step 58812: {'lr': 0.0003392070839636487, 'samples': 11291904, 'steps': 58811, 'loss/train': 1.9267053604125977} 08/30/2021 23:46:27 - INFO - __main__ - Step 58813: {'lr': 0.000339202126542327, 'samples': 11292096, 'steps': 58812, 'loss/train': 1.9604454040527344} 08/30/2021 23:46:27 - INFO - __main__ - Step 58814: {'lr': 0.00033919716908081224, 'samples': 11292288, 'steps': 58813, 'loss/train': 1.5966546535491943} 08/30/2021 23:46:28 - INFO - __main__ - Step 58815: {'lr': 0.0003391922115791065, 'samples': 11292480, 'steps': 58814, 'loss/train': 1.403215765953064} 08/30/2021 23:46:29 - INFO - __main__ - Step 58816: {'lr': 0.0003391872540372123, 'samples': 11292672, 'steps': 58815, 'loss/train': 0.7499516606330872} 08/30/2021 23:46:30 - INFO - __main__ - Step 58817: {'lr': 0.00033918229645513154, 'samples': 11292864, 'steps': 58816, 'loss/train': 1.1831259727478027} 08/30/2021 23:46:30 - INFO - __main__ - Step 58818: {'lr': 0.0003391773388328667, 'samples': 11293056, 'steps': 58817, 'loss/train': 0.07153192162513733} 08/30/2021 23:46:31 - INFO - __main__ - Step 58819: {'lr': 0.0003391723811704199, 'samples': 11293248, 'steps': 58818, 'loss/train': 1.3652219772338867} 08/30/2021 23:46:31 - INFO - __main__ - Step 58820: {'lr': 0.0003391674234677934, 'samples': 11293440, 'steps': 58819, 'loss/train': 0.9032937288284302} 08/30/2021 23:46:32 - INFO - __main__ - Step 58821: {'lr': 0.0003391624657249894, 'samples': 11293632, 'steps': 58820, 'loss/train': 1.301866054534912} 08/30/2021 23:46:33 - INFO - __main__ - Step 58822: {'lr': 0.0003391575079420102, 'samples': 11293824, 'steps': 58821, 'loss/train': 2.0473484992980957} 08/30/2021 23:46:33 - INFO - __main__ - Step 58823: {'lr': 0.00033915255011885803, 'samples': 11294016, 'steps': 58822, 'loss/train': 1.455654501914978} 08/30/2021 23:46:34 - INFO - __main__ - Step 58824: {'lr': 0.000339147592255535, 'samples': 11294208, 'steps': 58823, 'loss/train': 1.7569061517715454} 08/30/2021 23:46:34 - INFO - __main__ - Step 58825: {'lr': 0.00033914263435204356, 'samples': 11294400, 'steps': 58824, 'loss/train': 0.42737406492233276} 08/30/2021 23:46:35 - INFO - __main__ - Step 58826: {'lr': 0.0003391376764083858, 'samples': 11294592, 'steps': 58825, 'loss/train': 1.7902110815048218} 08/30/2021 23:46:36 - INFO - __main__ - Step 58827: {'lr': 0.00033913271842456394, 'samples': 11294784, 'steps': 58826, 'loss/train': 1.0986599922180176} 08/30/2021 23:46:36 - INFO - __main__ - Step 58828: {'lr': 0.0003391277604005802, 'samples': 11294976, 'steps': 58827, 'loss/train': 1.656203269958496} 08/30/2021 23:46:37 - INFO - __main__ - Step 58829: {'lr': 0.00033912280233643706, 'samples': 11295168, 'steps': 58828, 'loss/train': 1.275792121887207} 08/30/2021 23:46:37 - INFO - __main__ - Step 58830: {'lr': 0.00033911784423213645, 'samples': 11295360, 'steps': 58829, 'loss/train': 1.1996405124664307} 08/30/2021 23:46:37 - INFO - __main__ - Step 58831: {'lr': 0.00033911288608768063, 'samples': 11295552, 'steps': 58830, 'loss/train': 1.6678252220153809} 08/30/2021 23:46:39 - INFO - __main__ - Step 58832: {'lr': 0.000339107927903072, 'samples': 11295744, 'steps': 58831, 'loss/train': 1.1973662376403809} 08/30/2021 23:46:39 - INFO - __main__ - Step 58833: {'lr': 0.00033910296967831267, 'samples': 11295936, 'steps': 58832, 'loss/train': 1.5865659713745117} 08/30/2021 23:46:40 - INFO - __main__ - Step 58834: {'lr': 0.00033909801141340497, 'samples': 11296128, 'steps': 58833, 'loss/train': 1.3550770282745361} 08/30/2021 23:46:40 - INFO - __main__ - Step 58835: {'lr': 0.00033909305310835105, 'samples': 11296320, 'steps': 58834, 'loss/train': 1.2268120050430298} 08/30/2021 23:46:40 - INFO - __main__ - Step 58836: {'lr': 0.00033908809476315325, 'samples': 11296512, 'steps': 58835, 'loss/train': 1.1937689781188965} 08/30/2021 23:46:42 - INFO - __main__ - Step 58837: {'lr': 0.0003390831363778136, 'samples': 11296704, 'steps': 58836, 'loss/train': 1.7368097305297852} 08/30/2021 23:46:42 - INFO - __main__ - Step 58838: {'lr': 0.00033907817795233454, 'samples': 11296896, 'steps': 58837, 'loss/train': 1.6836061477661133} 08/30/2021 23:46:43 - INFO - __main__ - Step 58839: {'lr': 0.0003390732194867182, 'samples': 11297088, 'steps': 58838, 'loss/train': 1.6274300813674927} 08/30/2021 23:46:43 - INFO - __main__ - Step 58840: {'lr': 0.00033906826098096686, 'samples': 11297280, 'steps': 58839, 'loss/train': 1.0285338163375854} 08/30/2021 23:46:43 - INFO - __main__ - Step 58841: {'lr': 0.0003390633024350827, 'samples': 11297472, 'steps': 58840, 'loss/train': 1.7333099842071533} 08/30/2021 23:46:45 - INFO - __main__ - Step 58842: {'lr': 0.000339058343849068, 'samples': 11297664, 'steps': 58841, 'loss/train': 1.0773276090621948} 08/30/2021 23:46:46 - INFO - __main__ - Step 58843: {'lr': 0.00033905338522292514, 'samples': 11297856, 'steps': 58842, 'loss/train': 0.7455134391784668} 08/30/2021 23:46:46 - INFO - __main__ - Step 58844: {'lr': 0.00033904842655665604, 'samples': 11298048, 'steps': 58843, 'loss/train': 0.9754507541656494} 08/30/2021 23:46:47 - INFO - __main__ - Step 58845: {'lr': 0.00033904346785026306, 'samples': 11298240, 'steps': 58844, 'loss/train': 1.5566054582595825} 08/30/2021 23:46:47 - INFO - __main__ - Step 58846: {'lr': 0.0003390385091037486, 'samples': 11298432, 'steps': 58845, 'loss/train': 1.260424256324768} 08/30/2021 23:46:49 - INFO - __main__ - Step 58847: {'lr': 0.0003390335503171146, 'samples': 11298624, 'steps': 58846, 'loss/train': 0.07344728708267212} 08/30/2021 23:46:49 - INFO - __main__ - Step 58848: {'lr': 0.0003390285914903636, 'samples': 11298816, 'steps': 58847, 'loss/train': 1.616707444190979} 08/30/2021 23:46:49 - INFO - __main__ - Step 58849: {'lr': 0.0003390236326234977, 'samples': 11299008, 'steps': 58848, 'loss/train': 1.1169241666793823} 08/30/2021 23:46:50 - INFO - __main__ - Step 58850: {'lr': 0.000339018673716519, 'samples': 11299200, 'steps': 58849, 'loss/train': 0.04388076066970825} 08/30/2021 23:46:50 - INFO - __main__ - Step 58851: {'lr': 0.0003390137147694299, 'samples': 11299392, 'steps': 58850, 'loss/train': 2.0828006267547607} 08/30/2021 23:46:52 - INFO - __main__ - Step 58852: {'lr': 0.0003390087557822326, 'samples': 11299584, 'steps': 58851, 'loss/train': 2.091796398162842} 08/30/2021 23:46:52 - INFO - __main__ - Step 58853: {'lr': 0.00033900379675492933, 'samples': 11299776, 'steps': 58852, 'loss/train': 1.4529201984405518} 08/30/2021 23:46:53 - INFO - __main__ - Step 58854: {'lr': 0.00033899883768752234, 'samples': 11299968, 'steps': 58853, 'loss/train': 1.5650910139083862} 08/30/2021 23:46:53 - INFO - __main__ - Step 58855: {'lr': 0.00033899387858001386, 'samples': 11300160, 'steps': 58854, 'loss/train': 1.2085142135620117} 08/30/2021 23:46:53 - INFO - __main__ - Step 58856: {'lr': 0.0003389889194324061, 'samples': 11300352, 'steps': 58855, 'loss/train': 1.4862236976623535} 08/30/2021 23:46:54 - INFO - __main__ - Step 58857: {'lr': 0.0003389839602447013, 'samples': 11300544, 'steps': 58856, 'loss/train': 1.5161347389221191} 08/30/2021 23:46:55 - INFO - __main__ - Step 58858: {'lr': 0.0003389790010169017, 'samples': 11300736, 'steps': 58857, 'loss/train': 1.302025556564331} 08/30/2021 23:46:56 - INFO - __main__ - Step 58859: {'lr': 0.00033897404174900955, 'samples': 11300928, 'steps': 58858, 'loss/train': 1.1080756187438965} 08/30/2021 23:46:56 - INFO - __main__ - Step 58860: {'lr': 0.000338969082441027, 'samples': 11301120, 'steps': 58859, 'loss/train': 0.7732256054878235} 08/30/2021 23:46:56 - INFO - __main__ - Step 58861: {'lr': 0.00033896412309295643, 'samples': 11301312, 'steps': 58860, 'loss/train': 1.7619364261627197} 08/30/2021 23:46:57 - INFO - __main__ - Step 58862: {'lr': 0.00033895916370479994, 'samples': 11301504, 'steps': 58861, 'loss/train': 1.0133110284805298} 08/30/2021 23:46:59 - INFO - __main__ - Step 58863: {'lr': 0.00033895420427655995, 'samples': 11301696, 'steps': 58862, 'loss/train': 0.7115636467933655} 08/30/2021 23:46:59 - INFO - __main__ - Step 58864: {'lr': 0.0003389492448082384, 'samples': 11301888, 'steps': 58863, 'loss/train': 0.5410496592521667} 08/30/2021 23:47:00 - INFO - __main__ - Step 58865: {'lr': 0.0003389442852998378, 'samples': 11302080, 'steps': 58864, 'loss/train': 1.9697915315628052} 08/30/2021 23:47:00 - INFO - __main__ - Step 58866: {'lr': 0.0003389393257513602, 'samples': 11302272, 'steps': 58865, 'loss/train': 1.2539417743682861} 08/30/2021 23:47:00 - INFO - __main__ - Step 58867: {'lr': 0.00033893436616280796, 'samples': 11302464, 'steps': 58866, 'loss/train': 1.4076707363128662} 08/30/2021 23:47:01 - INFO - __main__ - Step 58868: {'lr': 0.0003389294065341833, 'samples': 11302656, 'steps': 58867, 'loss/train': 0.05458477884531021} 08/30/2021 23:47:02 - INFO - __main__ - Step 58869: {'lr': 0.0003389244468654884, 'samples': 11302848, 'steps': 58868, 'loss/train': 0.03862815350294113} 08/30/2021 23:47:03 - INFO - __main__ - Step 58870: {'lr': 0.0003389194871567255, 'samples': 11303040, 'steps': 58869, 'loss/train': 2.052201747894287} 08/30/2021 23:47:03 - INFO - __main__ - Step 58871: {'lr': 0.00033891452740789687, 'samples': 11303232, 'steps': 58870, 'loss/train': 1.4117408990859985} 08/30/2021 23:47:03 - INFO - __main__ - Step 58872: {'lr': 0.0003389095676190047, 'samples': 11303424, 'steps': 58871, 'loss/train': 1.2843350172042847} 08/30/2021 23:47:04 - INFO - __main__ - Step 58873: {'lr': 0.00033890460779005126, 'samples': 11303616, 'steps': 58872, 'loss/train': 1.5725042819976807} 08/30/2021 23:47:05 - INFO - __main__ - Step 58874: {'lr': 0.0003388996479210388, 'samples': 11303808, 'steps': 58873, 'loss/train': 1.3877595663070679} 08/30/2021 23:47:06 - INFO - __main__ - Step 58875: {'lr': 0.0003388946880119695, 'samples': 11304000, 'steps': 58874, 'loss/train': 0.31325653195381165} 08/30/2021 23:47:06 - INFO - __main__ - Step 58876: {'lr': 0.0003388897280628457, 'samples': 11304192, 'steps': 58875, 'loss/train': 1.5564548969268799} 08/30/2021 23:47:06 - INFO - __main__ - Step 58877: {'lr': 0.00033888476807366946, 'samples': 11304384, 'steps': 58876, 'loss/train': 0.035363029688596725} 08/30/2021 23:47:07 - INFO - __main__ - Step 58878: {'lr': 0.00033887980804444314, 'samples': 11304576, 'steps': 58877, 'loss/train': 0.7051045894622803} 08/30/2021 23:47:08 - INFO - __main__ - Step 58879: {'lr': 0.00033887484797516895, 'samples': 11304768, 'steps': 58878, 'loss/train': 1.4129315614700317} 08/30/2021 23:47:09 - INFO - __main__ - Step 58880: {'lr': 0.00033886988786584914, 'samples': 11304960, 'steps': 58879, 'loss/train': 1.2098859548568726} 08/30/2021 23:47:09 - INFO - __main__ - Step 58881: {'lr': 0.0003388649277164859, 'samples': 11305152, 'steps': 58880, 'loss/train': 1.4665073156356812} 08/30/2021 23:47:09 - INFO - __main__ - Step 58882: {'lr': 0.0003388599675270815, 'samples': 11305344, 'steps': 58881, 'loss/train': 1.6331019401550293} 08/30/2021 23:47:10 - INFO - __main__ - Step 58883: {'lr': 0.00033885500729763824, 'samples': 11305536, 'steps': 58882, 'loss/train': 1.9003345966339111} 08/30/2021 23:47:10 - INFO - __main__ - Step 58884: {'lr': 0.00033885004702815825, 'samples': 11305728, 'steps': 58883, 'loss/train': 1.5604912042617798} 08/30/2021 23:47:12 - INFO - __main__ - Step 58885: {'lr': 0.00033884508671864377, 'samples': 11305920, 'steps': 58884, 'loss/train': 1.8833619356155396} 08/30/2021 23:47:12 - INFO - __main__ - Step 58886: {'lr': 0.0003388401263690971, 'samples': 11306112, 'steps': 58885, 'loss/train': 0.11321484297513962} 08/30/2021 23:47:12 - INFO - __main__ - Step 58887: {'lr': 0.00033883516597952033, 'samples': 11306304, 'steps': 58886, 'loss/train': 1.7042204141616821} 08/30/2021 23:47:13 - INFO - __main__ - Step 58888: {'lr': 0.00033883020554991594, 'samples': 11306496, 'steps': 58887, 'loss/train': 1.1117045879364014} 08/30/2021 23:47:13 - INFO - __main__ - Step 58889: {'lr': 0.000338825245080286, 'samples': 11306688, 'steps': 58888, 'loss/train': 1.708659052848816} 08/30/2021 23:47:15 - INFO - __main__ - Step 58890: {'lr': 0.0003388202845706328, 'samples': 11306880, 'steps': 58889, 'loss/train': 1.3224077224731445} 08/30/2021 23:47:15 - INFO - __main__ - Step 58891: {'lr': 0.0003388153240209585, 'samples': 11307072, 'steps': 58890, 'loss/train': 1.2200595140457153} 08/30/2021 23:47:16 - INFO - __main__ - Step 58892: {'lr': 0.0003388103634312654, 'samples': 11307264, 'steps': 58891, 'loss/train': 1.4970959424972534} 08/30/2021 23:47:16 - INFO - __main__ - Step 58893: {'lr': 0.0003388054028015557, 'samples': 11307456, 'steps': 58892, 'loss/train': 1.5872451066970825} 08/30/2021 23:47:16 - INFO - __main__ - Step 58894: {'lr': 0.00033880044213183163, 'samples': 11307648, 'steps': 58893, 'loss/train': 1.0694379806518555} 08/30/2021 23:47:18 - INFO - __main__ - Step 58895: {'lr': 0.00033879548142209546, 'samples': 11307840, 'steps': 58894, 'loss/train': 1.3389191627502441} 08/30/2021 23:47:18 - INFO - __main__ - Step 58896: {'lr': 0.0003387905206723496, 'samples': 11308032, 'steps': 58895, 'loss/train': 1.2320886850357056} 08/30/2021 23:47:18 - INFO - __main__ - Step 58897: {'lr': 0.00033878555988259583, 'samples': 11308224, 'steps': 58896, 'loss/train': 1.192296028137207} 08/30/2021 23:47:19 - INFO - __main__ - Step 58898: {'lr': 0.0003387805990528368, 'samples': 11308416, 'steps': 58897, 'loss/train': 1.6647263765335083} 08/30/2021 23:47:19 - INFO - __main__ - Step 58899: {'lr': 0.0003387756381830746, 'samples': 11308608, 'steps': 58898, 'loss/train': 0.4628666043281555} 08/30/2021 23:47:21 - INFO - __main__ - Step 58900: {'lr': 0.00033877067727331145, 'samples': 11308800, 'steps': 58899, 'loss/train': 1.670591950416565} 08/30/2021 23:47:21 - INFO - __main__ - Step 58901: {'lr': 0.00033876571632354956, 'samples': 11308992, 'steps': 58900, 'loss/train': 1.3814274072647095} 08/30/2021 23:47:21 - INFO - __main__ - Step 58902: {'lr': 0.0003387607553337913, 'samples': 11309184, 'steps': 58901, 'loss/train': 1.4355747699737549} 08/30/2021 23:47:22 - INFO - __main__ - Step 58903: {'lr': 0.00033875579430403877, 'samples': 11309376, 'steps': 58902, 'loss/train': 1.0601228475570679} 08/30/2021 23:47:22 - INFO - __main__ - Step 58904: {'lr': 0.00033875083323429425, 'samples': 11309568, 'steps': 58903, 'loss/train': 1.3985990285873413} 08/30/2021 23:47:24 - INFO - __main__ - Step 58905: {'lr': 0.0003387458721245599, 'samples': 11309760, 'steps': 58904, 'loss/train': 3.1908650398254395} 08/30/2021 23:47:25 - INFO - __main__ - Step 58906: {'lr': 0.0003387409109748381, 'samples': 11309952, 'steps': 58905, 'loss/train': 1.2943027019500732} 08/30/2021 23:47:25 - INFO - __main__ - Step 58907: {'lr': 0.0003387359497851311, 'samples': 11310144, 'steps': 58906, 'loss/train': 1.2246050834655762} 08/30/2021 23:47:25 - INFO - __main__ - Step 58908: {'lr': 0.00033873098855544093, 'samples': 11310336, 'steps': 58907, 'loss/train': 1.6925221681594849} 08/30/2021 23:47:26 - INFO - __main__ - Step 58909: {'lr': 0.00033872602728576997, 'samples': 11310528, 'steps': 58908, 'loss/train': 1.3939054012298584} 08/30/2021 23:47:27 - INFO - __main__ - Step 58910: {'lr': 0.0003387210659761204, 'samples': 11310720, 'steps': 58909, 'loss/train': 1.2687801122665405} 08/30/2021 23:47:28 - INFO - __main__ - Step 58911: {'lr': 0.00033871610462649456, 'samples': 11310912, 'steps': 58910, 'loss/train': 1.27236807346344} 08/30/2021 23:47:28 - INFO - __main__ - Step 58912: {'lr': 0.00033871114323689457, 'samples': 11311104, 'steps': 58911, 'loss/train': 1.5317920446395874} 08/30/2021 23:47:29 - INFO - __main__ - Step 58913: {'lr': 0.0003387061818073227, 'samples': 11311296, 'steps': 58912, 'loss/train': 1.1287299394607544} 08/30/2021 23:47:29 - INFO - __main__ - Step 58914: {'lr': 0.00033870122033778123, 'samples': 11311488, 'steps': 58913, 'loss/train': 1.429857850074768} 08/30/2021 23:47:29 - INFO - __main__ - Step 58915: {'lr': 0.00033869625882827233, 'samples': 11311680, 'steps': 58914, 'loss/train': 1.5617824792861938} 08/30/2021 23:47:31 - INFO - __main__ - Step 58916: {'lr': 0.00033869129727879827, 'samples': 11311872, 'steps': 58915, 'loss/train': 1.4296057224273682} 08/30/2021 23:47:31 - INFO - __main__ - Step 58917: {'lr': 0.0003386863356893612, 'samples': 11312064, 'steps': 58916, 'loss/train': 3.536475419998169} 08/30/2021 23:47:32 - INFO - __main__ - Step 58918: {'lr': 0.00033868137405996363, 'samples': 11312256, 'steps': 58917, 'loss/train': 0.32338494062423706} 08/30/2021 23:47:32 - INFO - __main__ - Step 58919: {'lr': 0.0003386764123906075, 'samples': 11312448, 'steps': 58918, 'loss/train': 1.9184119701385498} 08/30/2021 23:47:32 - INFO - __main__ - Step 58920: {'lr': 0.00033867145068129515, 'samples': 11312640, 'steps': 58919, 'loss/train': 0.4450545907020569} 08/30/2021 23:47:34 - INFO - __main__ - Step 58921: {'lr': 0.0003386664889320287, 'samples': 11312832, 'steps': 58920, 'loss/train': 1.4108160734176636} 08/30/2021 23:47:34 - INFO - __main__ - Step 58922: {'lr': 0.0003386615271428106, 'samples': 11313024, 'steps': 58921, 'loss/train': 1.092791199684143} 08/30/2021 23:47:35 - INFO - __main__ - Step 58923: {'lr': 0.000338656565313643, 'samples': 11313216, 'steps': 58922, 'loss/train': 1.4416844844818115} 08/30/2021 23:47:35 - INFO - __main__ - Step 58924: {'lr': 0.0003386516034445281, 'samples': 11313408, 'steps': 58923, 'loss/train': 1.1677485704421997} 08/30/2021 23:47:35 - INFO - __main__ - Step 58925: {'lr': 0.0003386466415354682, 'samples': 11313600, 'steps': 58924, 'loss/train': 1.599466323852539} 08/30/2021 23:47:37 - INFO - __main__ - Step 58926: {'lr': 0.00033864167958646543, 'samples': 11313792, 'steps': 58925, 'loss/train': 1.5058428049087524} 08/30/2021 23:47:37 - INFO - __main__ - Step 58927: {'lr': 0.00033863671759752206, 'samples': 11313984, 'steps': 58926, 'loss/train': 0.9152516722679138} 08/30/2021 23:47:38 - INFO - __main__ - Step 58928: {'lr': 0.0003386317555686404, 'samples': 11314176, 'steps': 58927, 'loss/train': 1.6576542854309082} 08/30/2021 23:47:38 - INFO - __main__ - Step 58929: {'lr': 0.0003386267934998226, 'samples': 11314368, 'steps': 58928, 'loss/train': 0.9393288493156433} 08/30/2021 23:47:38 - INFO - __main__ - Step 58930: {'lr': 0.00033862183139107106, 'samples': 11314560, 'steps': 58929, 'loss/train': 0.2901025414466858} 08/30/2021 23:47:40 - INFO - __main__ - Step 58931: {'lr': 0.0003386168692423878, 'samples': 11314752, 'steps': 58930, 'loss/train': 1.3556660413742065} 08/30/2021 23:47:40 - INFO - __main__ - Step 58932: {'lr': 0.0003386119070537751, 'samples': 11314944, 'steps': 58931, 'loss/train': 1.1427834033966064} 08/30/2021 23:47:41 - INFO - __main__ - Step 58933: {'lr': 0.0003386069448252353, 'samples': 11315136, 'steps': 58932, 'loss/train': 1.4643630981445312} 08/30/2021 23:47:41 - INFO - __main__ - Step 58934: {'lr': 0.00033860198255677054, 'samples': 11315328, 'steps': 58933, 'loss/train': 1.835627555847168} 08/30/2021 23:47:41 - INFO - __main__ - Step 58935: {'lr': 0.0003385970202483831, 'samples': 11315520, 'steps': 58934, 'loss/train': 1.5601670742034912} 08/30/2021 23:47:43 - INFO - __main__ - Step 58936: {'lr': 0.0003385920579000752, 'samples': 11315712, 'steps': 58935, 'loss/train': 1.200656533241272} 08/30/2021 23:47:43 - INFO - __main__ - Step 58937: {'lr': 0.0003385870955118492, 'samples': 11315904, 'steps': 58936, 'loss/train': 1.4566508531570435} 08/30/2021 23:47:44 - INFO - __main__ - Step 58938: {'lr': 0.0003385821330837071, 'samples': 11316096, 'steps': 58937, 'loss/train': 1.1573736667633057} 08/30/2021 23:47:44 - INFO - __main__ - Step 58939: {'lr': 0.0003385771706156513, 'samples': 11316288, 'steps': 58938, 'loss/train': 1.4861280918121338} 08/30/2021 23:47:44 - INFO - __main__ - Step 58940: {'lr': 0.00033857220810768395, 'samples': 11316480, 'steps': 58939, 'loss/train': 0.06638515740633011} 08/30/2021 23:47:46 - INFO - __main__ - Step 58941: {'lr': 0.00033856724555980736, 'samples': 11316672, 'steps': 58940, 'loss/train': 1.3598262071609497} 08/30/2021 23:47:46 - INFO - __main__ - Step 58942: {'lr': 0.00033856228297202373, 'samples': 11316864, 'steps': 58941, 'loss/train': 1.0139168500900269} 08/30/2021 23:47:47 - INFO - __main__ - Step 58943: {'lr': 0.0003385573203443354, 'samples': 11317056, 'steps': 58942, 'loss/train': 1.6325628757476807} 08/30/2021 23:47:47 - INFO - __main__ - Step 58944: {'lr': 0.0003385523576767444, 'samples': 11317248, 'steps': 58943, 'loss/train': 1.5046268701553345} 08/30/2021 23:47:47 - INFO - __main__ - Step 58945: {'lr': 0.0003385473949692531, 'samples': 11317440, 'steps': 58944, 'loss/train': 1.1434009075164795} 08/30/2021 23:47:48 - INFO - __main__ - Step 58946: {'lr': 0.0003385424322218637, 'samples': 11317632, 'steps': 58945, 'loss/train': 1.1483182907104492} 08/30/2021 23:47:49 - INFO - __main__ - Step 58947: {'lr': 0.0003385374694345784, 'samples': 11317824, 'steps': 58946, 'loss/train': 1.209281086921692} 08/30/2021 23:47:50 - INFO - __main__ - Step 58948: {'lr': 0.00033853250660739954, 'samples': 11318016, 'steps': 58947, 'loss/train': 1.050894021987915} 08/30/2021 23:47:50 - INFO - __main__ - Step 58949: {'lr': 0.00033852754374032927, 'samples': 11318208, 'steps': 58948, 'loss/train': 1.9154123067855835} 08/30/2021 23:47:50 - INFO - __main__ - Step 58950: {'lr': 0.00033852258083336996, 'samples': 11318400, 'steps': 58949, 'loss/train': 1.8694238662719727} 08/30/2021 23:47:51 - INFO - __main__ - Step 58951: {'lr': 0.0003385176178865236, 'samples': 11318592, 'steps': 58950, 'loss/train': 0.9341641068458557} 08/30/2021 23:47:52 - INFO - __main__ - Step 58952: {'lr': 0.00033851265489979267, 'samples': 11318784, 'steps': 58951, 'loss/train': 1.2058618068695068} 08/30/2021 23:47:53 - INFO - __main__ - Step 58953: {'lr': 0.00033850769187317923, 'samples': 11318976, 'steps': 58952, 'loss/train': 1.5634336471557617} 08/30/2021 23:47:53 - INFO - __main__ - Step 58954: {'lr': 0.00033850272880668565, 'samples': 11319168, 'steps': 58953, 'loss/train': 2.0675899982452393} 08/30/2021 23:47:53 - INFO - __main__ - Step 58955: {'lr': 0.000338497765700314, 'samples': 11319360, 'steps': 58954, 'loss/train': 1.2280032634735107} 08/30/2021 23:47:54 - INFO - __main__ - Step 58956: {'lr': 0.00033849280255406674, 'samples': 11319552, 'steps': 58955, 'loss/train': 0.1917537897825241} 08/30/2021 23:47:55 - INFO - __main__ - Step 58957: {'lr': 0.000338487839367946, 'samples': 11319744, 'steps': 58956, 'loss/train': 1.537724256515503} 08/30/2021 23:47:56 - INFO - __main__ - Step 58958: {'lr': 0.00033848287614195394, 'samples': 11319936, 'steps': 58957, 'loss/train': 0.9597919583320618} 08/30/2021 23:47:56 - INFO - __main__ - Step 58959: {'lr': 0.00033847791287609287, 'samples': 11320128, 'steps': 58958, 'loss/train': 1.011679768562317} 08/30/2021 23:47:56 - INFO - __main__ - Step 58960: {'lr': 0.00033847294957036503, 'samples': 11320320, 'steps': 58959, 'loss/train': 1.364578127861023} 08/30/2021 23:47:57 - INFO - __main__ - Step 58961: {'lr': 0.0003384679862247726, 'samples': 11320512, 'steps': 58960, 'loss/train': 1.002401351928711} 08/30/2021 23:47:59 - INFO - __main__ - Step 58962: {'lr': 0.0003384630228393179, 'samples': 11320704, 'steps': 58961, 'loss/train': 0.7703489661216736} 08/30/2021 23:47:59 - INFO - __main__ - Step 58963: {'lr': 0.0003384580594140031, 'samples': 11320896, 'steps': 58962, 'loss/train': 1.4097155332565308} 08/30/2021 23:48:00 - INFO - __main__ - Step 58964: {'lr': 0.00033845309594883054, 'samples': 11321088, 'steps': 58963, 'loss/train': 1.8449395895004272} 08/30/2021 23:48:00 - INFO - __main__ - Step 58965: {'lr': 0.0003384481324438023, 'samples': 11321280, 'steps': 58964, 'loss/train': 1.6552140712738037} 08/30/2021 23:48:00 - INFO - __main__ - Step 58966: {'lr': 0.00033844316889892074, 'samples': 11321472, 'steps': 58965, 'loss/train': 1.1037263870239258} 08/30/2021 23:48:01 - INFO - __main__ - Step 58967: {'lr': 0.000338438205314188, 'samples': 11321664, 'steps': 58966, 'loss/train': 1.5210975408554077} 08/30/2021 23:48:02 - INFO - __main__ - Step 58968: {'lr': 0.00033843324168960644, 'samples': 11321856, 'steps': 58967, 'loss/train': 1.3310660123825073} 08/30/2021 23:48:03 - INFO - __main__ - Step 58969: {'lr': 0.0003384282780251782, 'samples': 11322048, 'steps': 58968, 'loss/train': 1.5004477500915527} 08/30/2021 23:48:03 - INFO - __main__ - Step 58970: {'lr': 0.0003384233143209056, 'samples': 11322240, 'steps': 58969, 'loss/train': 1.1517926454544067} 08/30/2021 23:48:03 - INFO - __main__ - Step 58971: {'lr': 0.0003384183505767907, 'samples': 11322432, 'steps': 58970, 'loss/train': 0.8498528003692627} 08/30/2021 23:48:04 - INFO - __main__ - Step 58972: {'lr': 0.0003384133867928359, 'samples': 11322624, 'steps': 58971, 'loss/train': 1.4209383726119995} 08/30/2021 23:48:05 - INFO - __main__ - Step 58973: {'lr': 0.0003384084229690434, 'samples': 11322816, 'steps': 58972, 'loss/train': 1.0733853578567505} 08/30/2021 23:48:06 - INFO - __main__ - Step 58974: {'lr': 0.0003384034591054154, 'samples': 11323008, 'steps': 58973, 'loss/train': 1.5427162647247314} 08/30/2021 23:48:06 - INFO - __main__ - Step 58975: {'lr': 0.0003383984952019542, 'samples': 11323200, 'steps': 58974, 'loss/train': 1.3531625270843506} 08/30/2021 23:48:06 - INFO - __main__ - Step 58976: {'lr': 0.00033839353125866194, 'samples': 11323392, 'steps': 58975, 'loss/train': 1.6280808448791504} 08/30/2021 23:48:07 - INFO - __main__ - Step 58977: {'lr': 0.00033838856727554106, 'samples': 11323584, 'steps': 58976, 'loss/train': 1.229718565940857} 08/30/2021 23:48:08 - INFO - __main__ - Step 58978: {'lr': 0.00033838360325259354, 'samples': 11323776, 'steps': 58977, 'loss/train': 1.2192788124084473} 08/30/2021 23:48:09 - INFO - __main__ - Step 58979: {'lr': 0.00033837863918982175, 'samples': 11323968, 'steps': 58978, 'loss/train': 0.9179202318191528} 08/30/2021 23:48:09 - INFO - __main__ - Step 58980: {'lr': 0.0003383736750872279, 'samples': 11324160, 'steps': 58979, 'loss/train': 1.4866210222244263} 08/30/2021 23:48:10 - INFO - __main__ - Step 58981: {'lr': 0.00033836871094481433, 'samples': 11324352, 'steps': 58980, 'loss/train': 1.1453936100006104} 08/30/2021 23:48:10 - INFO - __main__ - Step 58982: {'lr': 0.0003383637467625831, 'samples': 11324544, 'steps': 58981, 'loss/train': 1.502899408340454} 08/30/2021 23:48:11 - INFO - __main__ - Step 58983: {'lr': 0.00033835878254053647, 'samples': 11324736, 'steps': 58982, 'loss/train': 1.1553280353546143} 08/30/2021 23:48:12 - INFO - __main__ - Step 58984: {'lr': 0.00033835381827867686, 'samples': 11324928, 'steps': 58983, 'loss/train': 1.4467045068740845} 08/30/2021 23:48:12 - INFO - __main__ - Step 58985: {'lr': 0.00033834885397700633, 'samples': 11325120, 'steps': 58984, 'loss/train': 0.916881799697876} 08/30/2021 23:48:13 - INFO - __main__ - Step 58986: {'lr': 0.00033834388963552715, 'samples': 11325312, 'steps': 58985, 'loss/train': 1.1837950944900513} 08/30/2021 23:48:13 - INFO - __main__ - Step 58987: {'lr': 0.0003383389252542416, 'samples': 11325504, 'steps': 58986, 'loss/train': 1.0867846012115479} 08/30/2021 23:48:14 - INFO - __main__ - Step 58988: {'lr': 0.0003383339608331519, 'samples': 11325696, 'steps': 58987, 'loss/train': 1.5615942478179932} 08/30/2021 23:48:15 - INFO - __main__ - Step 58989: {'lr': 0.00033832899637226024, 'samples': 11325888, 'steps': 58988, 'loss/train': 1.42579185962677} 08/30/2021 23:48:15 - INFO - __main__ - Step 58990: {'lr': 0.0003383240318715689, 'samples': 11326080, 'steps': 58989, 'loss/train': 1.702448844909668} 08/30/2021 23:48:16 - INFO - __main__ - Step 58991: {'lr': 0.0003383190673310802, 'samples': 11326272, 'steps': 58990, 'loss/train': 1.080240249633789} 08/30/2021 23:48:16 - INFO - __main__ - Step 58992: {'lr': 0.0003383141027507962, 'samples': 11326464, 'steps': 58991, 'loss/train': 1.2901581525802612} 08/30/2021 23:48:18 - INFO - __main__ - Step 58993: {'lr': 0.0003383091381307193, 'samples': 11326656, 'steps': 58992, 'loss/train': 1.146825909614563} 08/30/2021 23:48:18 - INFO - __main__ - Step 58994: {'lr': 0.0003383041734708516, 'samples': 11326848, 'steps': 58993, 'loss/train': 0.5573970675468445} 08/30/2021 23:48:18 - INFO - __main__ - Step 58995: {'lr': 0.0003382992087711954, 'samples': 11327040, 'steps': 58994, 'loss/train': 1.556983470916748} 08/30/2021 23:48:19 - INFO - __main__ - Step 58996: {'lr': 0.00033829424403175297, 'samples': 11327232, 'steps': 58995, 'loss/train': 1.2523374557495117} 08/30/2021 23:48:19 - INFO - __main__ - Step 58997: {'lr': 0.00033828927925252657, 'samples': 11327424, 'steps': 58996, 'loss/train': 1.083922028541565} 08/30/2021 23:48:19 - INFO - __main__ - Step 58998: {'lr': 0.0003382843144335183, 'samples': 11327616, 'steps': 58997, 'loss/train': 1.3436797857284546} 08/30/2021 23:48:21 - INFO - __main__ - Step 58999: {'lr': 0.0003382793495747305, 'samples': 11327808, 'steps': 58998, 'loss/train': 1.4055079221725464} 08/30/2021 23:48:21 - INFO - __main__ - Step 59000: {'lr': 0.0003382743846761654, 'samples': 11328000, 'steps': 58999, 'loss/train': 1.1837085485458374} 08/30/2021 23:48:22 - INFO - __main__ - Step 59001: {'lr': 0.0003382694197378252, 'samples': 11328192, 'steps': 59000, 'loss/train': 1.110337495803833} 08/30/2021 23:48:22 - INFO - __main__ - Step 59002: {'lr': 0.00033826445475971216, 'samples': 11328384, 'steps': 59001, 'loss/train': 0.901333749294281} 08/30/2021 23:48:22 - INFO - __main__ - Step 59003: {'lr': 0.0003382594897418285, 'samples': 11328576, 'steps': 59002, 'loss/train': 0.9534628391265869} 08/30/2021 23:48:24 - INFO - __main__ - Step 59004: {'lr': 0.0003382545246841766, 'samples': 11328768, 'steps': 59003, 'loss/train': 1.4020612239837646} 08/30/2021 23:48:24 - INFO - __main__ - Step 59005: {'lr': 0.00033824955958675843, 'samples': 11328960, 'steps': 59004, 'loss/train': 1.4572243690490723} 08/30/2021 23:48:25 - INFO - __main__ - Step 59006: {'lr': 0.00033824459444957645, 'samples': 11329152, 'steps': 59005, 'loss/train': 0.939325213432312} 08/30/2021 23:48:25 - INFO - __main__ - Step 59007: {'lr': 0.0003382396292726328, 'samples': 11329344, 'steps': 59006, 'loss/train': 1.294857144355774} 08/30/2021 23:48:25 - INFO - __main__ - Step 59008: {'lr': 0.00033823466405592974, 'samples': 11329536, 'steps': 59007, 'loss/train': 1.5731358528137207} 08/30/2021 23:48:27 - INFO - __main__ - Step 59009: {'lr': 0.00033822969879946947, 'samples': 11329728, 'steps': 59008, 'loss/train': 1.6323109865188599} 08/30/2021 23:48:27 - INFO - __main__ - Step 59010: {'lr': 0.0003382247335032542, 'samples': 11329920, 'steps': 59009, 'loss/train': 0.602820873260498} 08/30/2021 23:48:28 - INFO - __main__ - Step 59011: {'lr': 0.0003382197681672864, 'samples': 11330112, 'steps': 59010, 'loss/train': 1.5404332876205444} 08/30/2021 23:48:28 - INFO - __main__ - Step 59012: {'lr': 0.000338214802791568, 'samples': 11330304, 'steps': 59011, 'loss/train': 0.7720848321914673} 08/30/2021 23:48:28 - INFO - __main__ - Step 59013: {'lr': 0.00033820983737610147, 'samples': 11330496, 'steps': 59012, 'loss/train': 1.432164192199707} 08/30/2021 23:48:30 - INFO - __main__ - Step 59014: {'lr': 0.00033820487192088883, 'samples': 11330688, 'steps': 59013, 'loss/train': 1.2767586708068848} 08/30/2021 23:48:31 - INFO - __main__ - Step 59015: {'lr': 0.0003381999064259325, 'samples': 11330880, 'steps': 59014, 'loss/train': 0.8357781767845154} 08/30/2021 23:48:31 - INFO - __main__ - Step 59016: {'lr': 0.00033819494089123466, 'samples': 11331072, 'steps': 59015, 'loss/train': 1.465734601020813} 08/30/2021 23:48:32 - INFO - __main__ - Step 59017: {'lr': 0.00033818997531679756, 'samples': 11331264, 'steps': 59016, 'loss/train': 1.323067307472229} 08/30/2021 23:48:32 - INFO - __main__ - Step 59018: {'lr': 0.0003381850097026234, 'samples': 11331456, 'steps': 59017, 'loss/train': 1.5994404554367065} 08/30/2021 23:48:34 - INFO - __main__ - Step 59019: {'lr': 0.0003381800440487144, 'samples': 11331648, 'steps': 59018, 'loss/train': 1.5859649181365967} 08/30/2021 23:48:34 - INFO - __main__ - Step 59020: {'lr': 0.00033817507835507283, 'samples': 11331840, 'steps': 59019, 'loss/train': 1.1988579034805298} 08/30/2021 23:48:34 - INFO - __main__ - Step 59021: {'lr': 0.00033817011262170097, 'samples': 11332032, 'steps': 59020, 'loss/train': 1.52346932888031} 08/30/2021 23:48:35 - INFO - __main__ - Step 59022: {'lr': 0.000338165146848601, 'samples': 11332224, 'steps': 59021, 'loss/train': 1.3233613967895508} 08/30/2021 23:48:35 - INFO - __main__ - Step 59023: {'lr': 0.0003381601810357752, 'samples': 11332416, 'steps': 59022, 'loss/train': 1.3584074974060059} 08/30/2021 23:48:35 - INFO - __main__ - Step 59024: {'lr': 0.00033815521518322576, 'samples': 11332608, 'steps': 59023, 'loss/train': 1.6075634956359863} 08/30/2021 23:48:37 - INFO - __main__ - Step 59025: {'lr': 0.00033815024929095496, 'samples': 11332800, 'steps': 59024, 'loss/train': 1.31549870967865} 08/30/2021 23:48:37 - INFO - __main__ - Step 59026: {'lr': 0.000338145283358965, 'samples': 11332992, 'steps': 59025, 'loss/train': 1.880662202835083} 08/30/2021 23:48:38 - INFO - __main__ - Step 59027: {'lr': 0.0003381403173872581, 'samples': 11333184, 'steps': 59026, 'loss/train': 1.2815799713134766} 08/30/2021 23:48:38 - INFO - __main__ - Step 59028: {'lr': 0.00033813535137583656, 'samples': 11333376, 'steps': 59027, 'loss/train': 0.9613404870033264} 08/30/2021 23:48:38 - INFO - __main__ - Step 59029: {'lr': 0.0003381303853247026, 'samples': 11333568, 'steps': 59028, 'loss/train': 1.2405524253845215} 08/30/2021 23:48:40 - INFO - __main__ - Step 59030: {'lr': 0.0003381254192338585, 'samples': 11333760, 'steps': 59029, 'loss/train': 1.5383808612823486} 08/30/2021 23:48:40 - INFO - __main__ - Step 59031: {'lr': 0.00033812045310330636, 'samples': 11333952, 'steps': 59030, 'loss/train': 1.4398000240325928} 08/30/2021 23:48:41 - INFO - __main__ - Step 59032: {'lr': 0.0003381154869330485, 'samples': 11334144, 'steps': 59031, 'loss/train': 1.3044570684432983} 08/30/2021 23:48:41 - INFO - __main__ - Step 59033: {'lr': 0.00033811052072308724, 'samples': 11334336, 'steps': 59032, 'loss/train': 1.601513385772705} 08/30/2021 23:48:41 - INFO - __main__ - Step 59034: {'lr': 0.0003381055544734247, 'samples': 11334528, 'steps': 59033, 'loss/train': 1.3422828912734985} 08/30/2021 23:48:43 - INFO - __main__ - Step 59035: {'lr': 0.00033810058818406307, 'samples': 11334720, 'steps': 59034, 'loss/train': 1.0054799318313599} 08/30/2021 23:48:43 - INFO - __main__ - Step 59036: {'lr': 0.0003380956218550049, 'samples': 11334912, 'steps': 59035, 'loss/train': 1.39080810546875} 08/30/2021 23:48:44 - INFO - __main__ - Step 59037: {'lr': 0.000338090655486252, 'samples': 11335104, 'steps': 59036, 'loss/train': 1.2374229431152344} 08/30/2021 23:48:44 - INFO - __main__ - Step 59038: {'lr': 0.00033808568907780687, 'samples': 11335296, 'steps': 59037, 'loss/train': 1.4884473085403442} 08/30/2021 23:48:44 - INFO - __main__ - Step 59039: {'lr': 0.00033808072262967164, 'samples': 11335488, 'steps': 59038, 'loss/train': 1.3518229722976685} 08/30/2021 23:48:46 - INFO - __main__ - Step 59040: {'lr': 0.00033807575614184864, 'samples': 11335680, 'steps': 59039, 'loss/train': 1.1372982263565063} 08/30/2021 23:48:46 - INFO - __main__ - Step 59041: {'lr': 0.0003380707896143401, 'samples': 11335872, 'steps': 59040, 'loss/train': 1.4580377340316772} 08/30/2021 23:48:47 - INFO - __main__ - Step 59042: {'lr': 0.0003380658230471482, 'samples': 11336064, 'steps': 59041, 'loss/train': 1.2731351852416992} 08/30/2021 23:48:47 - INFO - __main__ - Step 59043: {'lr': 0.0003380608564402752, 'samples': 11336256, 'steps': 59042, 'loss/train': 1.2429674863815308} 08/30/2021 23:48:47 - INFO - __main__ - Step 59044: {'lr': 0.0003380558897937233, 'samples': 11336448, 'steps': 59043, 'loss/train': 1.0650434494018555} 08/30/2021 23:48:48 - INFO - __main__ - Step 59045: {'lr': 0.0003380509231074948, 'samples': 11336640, 'steps': 59044, 'loss/train': 5.785302639007568} 08/30/2021 23:48:49 - INFO - __main__ - Step 59046: {'lr': 0.0003380459563815919, 'samples': 11336832, 'steps': 59045, 'loss/train': 1.0075180530548096} 08/30/2021 23:48:50 - INFO - __main__ - Step 59047: {'lr': 0.0003380409896160169, 'samples': 11337024, 'steps': 59046, 'loss/train': 1.0697202682495117} 08/30/2021 23:48:50 - INFO - __main__ - Step 59048: {'lr': 0.00033803602281077194, 'samples': 11337216, 'steps': 59047, 'loss/train': 1.5564501285552979} 08/30/2021 23:48:51 - INFO - __main__ - Step 59049: {'lr': 0.0003380310559658593, 'samples': 11337408, 'steps': 59048, 'loss/train': 1.1588890552520752} 08/30/2021 23:48:51 - INFO - __main__ - Step 59050: {'lr': 0.00033802608908128126, 'samples': 11337600, 'steps': 59049, 'loss/train': 1.327578067779541} 08/30/2021 23:48:53 - INFO - __main__ - Step 59051: {'lr': 0.00033802112215704, 'samples': 11337792, 'steps': 59050, 'loss/train': 1.9613319635391235} 08/30/2021 23:48:53 - INFO - __main__ - Step 59052: {'lr': 0.0003380161551931378, 'samples': 11337984, 'steps': 59051, 'loss/train': 1.2050180435180664} 08/30/2021 23:48:53 - INFO - __main__ - Step 59053: {'lr': 0.00033801118818957686, 'samples': 11338176, 'steps': 59052, 'loss/train': 0.047572895884513855} 08/30/2021 23:48:54 - INFO - __main__ - Step 59054: {'lr': 0.00033800622114635943, 'samples': 11338368, 'steps': 59053, 'loss/train': 1.2006944417953491} 08/30/2021 23:48:54 - INFO - __main__ - Step 59055: {'lr': 0.0003380012540634878, 'samples': 11338560, 'steps': 59054, 'loss/train': 1.3729872703552246} 08/30/2021 23:48:56 - INFO - __main__ - Step 59056: {'lr': 0.00033799628694096407, 'samples': 11338752, 'steps': 59055, 'loss/train': 0.04436753690242767} 08/30/2021 23:48:56 - INFO - __main__ - Step 59057: {'lr': 0.0003379913197787907, 'samples': 11338944, 'steps': 59056, 'loss/train': 1.5208933353424072} 08/30/2021 23:48:56 - INFO - __main__ - Step 59058: {'lr': 0.00033798635257696976, 'samples': 11339136, 'steps': 59057, 'loss/train': 2.2768805027008057} 08/30/2021 23:48:57 - INFO - __main__ - Step 59059: {'lr': 0.0003379813853355034, 'samples': 11339328, 'steps': 59058, 'loss/train': 1.1997323036193848} 08/30/2021 23:48:57 - INFO - __main__ - Step 59060: {'lr': 0.0003379764180543941, 'samples': 11339520, 'steps': 59059, 'loss/train': 0.6003795266151428} 08/30/2021 23:48:59 - INFO - __main__ - Step 59061: {'lr': 0.000337971450733644, 'samples': 11339712, 'steps': 59060, 'loss/train': 0.8755113482475281} 08/30/2021 23:48:59 - INFO - __main__ - Step 59062: {'lr': 0.00033796648337325525, 'samples': 11339904, 'steps': 59061, 'loss/train': 1.215303659439087} 08/30/2021 23:48:59 - INFO - __main__ - Step 59063: {'lr': 0.0003379615159732302, 'samples': 11340096, 'steps': 59062, 'loss/train': 1.6083595752716064} 08/30/2021 23:49:00 - INFO - __main__ - Step 59064: {'lr': 0.00033795654853357104, 'samples': 11340288, 'steps': 59063, 'loss/train': 1.7363594770431519} 08/30/2021 23:49:00 - INFO - __main__ - Step 59065: {'lr': 0.00033795158105428, 'samples': 11340480, 'steps': 59064, 'loss/train': 1.5962884426116943} 08/30/2021 23:49:00 - INFO - __main__ - Step 59066: {'lr': 0.0003379466135353594, 'samples': 11340672, 'steps': 59065, 'loss/train': 1.250943899154663} 08/30/2021 23:49:03 - INFO - __main__ - Step 59067: {'lr': 0.0003379416459768114, 'samples': 11340864, 'steps': 59066, 'loss/train': 1.5900511741638184} 08/30/2021 23:49:03 - INFO - __main__ - Step 59068: {'lr': 0.00033793667837863815, 'samples': 11341056, 'steps': 59067, 'loss/train': 0.9030623435974121} 08/30/2021 23:49:04 - INFO - __main__ - Step 59069: {'lr': 0.0003379317107408421, 'samples': 11341248, 'steps': 59068, 'loss/train': 0.7467013597488403} 08/30/2021 23:49:04 - INFO - __main__ - Step 59070: {'lr': 0.0003379267430634253, 'samples': 11341440, 'steps': 59069, 'loss/train': 2.026566982269287} 08/30/2021 23:49:04 - INFO - __main__ - Step 59071: {'lr': 0.00033792177534639015, 'samples': 11341632, 'steps': 59070, 'loss/train': 1.216873288154602} 08/30/2021 23:49:06 - INFO - __main__ - Step 59072: {'lr': 0.00033791680758973874, 'samples': 11341824, 'steps': 59071, 'loss/train': 1.1709107160568237} 08/30/2021 23:49:06 - INFO - __main__ - Step 59073: {'lr': 0.0003379118397934734, 'samples': 11342016, 'steps': 59072, 'loss/train': 0.9876223206520081} 08/30/2021 23:49:07 - INFO - __main__ - Step 59074: {'lr': 0.00033790687195759636, 'samples': 11342208, 'steps': 59073, 'loss/train': 1.1833842992782593} 08/30/2021 23:49:07 - INFO - __main__ - Step 59075: {'lr': 0.00033790190408210973, 'samples': 11342400, 'steps': 59074, 'loss/train': 1.0073257684707642} 08/30/2021 23:49:08 - INFO - __main__ - Step 59076: {'lr': 0.000337896936167016, 'samples': 11342592, 'steps': 59075, 'loss/train': 1.2722294330596924} 08/30/2021 23:49:09 - INFO - __main__ - Step 59077: {'lr': 0.00033789196821231717, 'samples': 11342784, 'steps': 59076, 'loss/train': 1.9959516525268555} 08/30/2021 23:49:10 - INFO - __main__ - Step 59078: {'lr': 0.00033788700021801564, 'samples': 11342976, 'steps': 59077, 'loss/train': 0.9849477410316467} 08/30/2021 23:49:10 - INFO - __main__ - Step 59079: {'lr': 0.00033788203218411357, 'samples': 11343168, 'steps': 59078, 'loss/train': 1.8005661964416504} 08/30/2021 23:49:10 - INFO - __main__ - Step 59080: {'lr': 0.0003378770641106132, 'samples': 11343360, 'steps': 59079, 'loss/train': 0.6836938858032227} 08/30/2021 23:49:11 - INFO - __main__ - Step 59081: {'lr': 0.00033787209599751676, 'samples': 11343552, 'steps': 59080, 'loss/train': 0.7835308909416199} 08/30/2021 23:49:11 - INFO - __main__ - Step 59082: {'lr': 0.0003378671278448265, 'samples': 11343744, 'steps': 59081, 'loss/train': 1.1010427474975586} 08/30/2021 23:49:12 - INFO - __main__ - Step 59083: {'lr': 0.00033786215965254474, 'samples': 11343936, 'steps': 59082, 'loss/train': 1.2064543962478638} 08/30/2021 23:49:13 - INFO - __main__ - Step 59084: {'lr': 0.00033785719142067364, 'samples': 11344128, 'steps': 59083, 'loss/train': 1.5590165853500366} 08/30/2021 23:49:13 - INFO - __main__ - Step 59085: {'lr': 0.0003378522231492154, 'samples': 11344320, 'steps': 59084, 'loss/train': 1.6903339624404907} 08/30/2021 23:49:13 - INFO - __main__ - Step 59086: {'lr': 0.0003378472548381723, 'samples': 11344512, 'steps': 59085, 'loss/train': 1.6603060960769653} 08/30/2021 23:49:14 - INFO - __main__ - Step 59087: {'lr': 0.0003378422864875466, 'samples': 11344704, 'steps': 59086, 'loss/train': 0.8950554728507996} 08/30/2021 23:49:15 - INFO - __main__ - Step 59088: {'lr': 0.0003378373180973405, 'samples': 11344896, 'steps': 59087, 'loss/train': 1.310755968093872} 08/30/2021 23:49:16 - INFO - __main__ - Step 59089: {'lr': 0.0003378323496675563, 'samples': 11345088, 'steps': 59088, 'loss/train': 1.4918195009231567} 08/30/2021 23:49:16 - INFO - __main__ - Step 59090: {'lr': 0.0003378273811981961, 'samples': 11345280, 'steps': 59089, 'loss/train': 1.6184768676757812} 08/30/2021 23:49:16 - INFO - __main__ - Step 59091: {'lr': 0.00033782241268926237, 'samples': 11345472, 'steps': 59090, 'loss/train': 1.0371448993682861} 08/30/2021 23:49:17 - INFO - __main__ - Step 59092: {'lr': 0.00033781744414075723, 'samples': 11345664, 'steps': 59091, 'loss/train': 1.642082691192627} 08/30/2021 23:49:19 - INFO - __main__ - Step 59093: {'lr': 0.0003378124755526828, 'samples': 11345856, 'steps': 59092, 'loss/train': 3.4553022384643555} 08/30/2021 23:49:19 - INFO - __main__ - Step 59094: {'lr': 0.0003378075069250414, 'samples': 11346048, 'steps': 59093, 'loss/train': 1.6642855405807495} 08/30/2021 23:49:19 - INFO - __main__ - Step 59095: {'lr': 0.00033780253825783533, 'samples': 11346240, 'steps': 59094, 'loss/train': 1.227319359779358} 08/30/2021 23:49:20 - INFO - __main__ - Step 59096: {'lr': 0.0003377975695510668, 'samples': 11346432, 'steps': 59095, 'loss/train': 1.1008540391921997} 08/30/2021 23:49:20 - INFO - __main__ - Step 59097: {'lr': 0.0003377926008047381, 'samples': 11346624, 'steps': 59096, 'loss/train': 1.3149657249450684} 08/30/2021 23:49:22 - INFO - __main__ - Step 59098: {'lr': 0.0003377876320188514, 'samples': 11346816, 'steps': 59097, 'loss/train': 0.7430916428565979} 08/30/2021 23:49:22 - INFO - __main__ - Step 59099: {'lr': 0.0003377826631934089, 'samples': 11347008, 'steps': 59098, 'loss/train': 1.5956075191497803} 08/30/2021 23:49:22 - INFO - __main__ - Step 59100: {'lr': 0.0003377776943284129, 'samples': 11347200, 'steps': 59099, 'loss/train': 1.4470906257629395} 08/30/2021 23:49:23 - INFO - __main__ - Step 59101: {'lr': 0.00033777272542386564, 'samples': 11347392, 'steps': 59100, 'loss/train': 0.04764091223478317} 08/30/2021 23:49:23 - INFO - __main__ - Step 59102: {'lr': 0.0003377677564797693, 'samples': 11347584, 'steps': 59101, 'loss/train': 0.8679090142250061} 08/30/2021 23:49:25 - INFO - __main__ - Step 59103: {'lr': 0.00033776278749612617, 'samples': 11347776, 'steps': 59102, 'loss/train': 0.6373335719108582} 08/30/2021 23:49:25 - INFO - __main__ - Step 59104: {'lr': 0.00033775781847293846, 'samples': 11347968, 'steps': 59103, 'loss/train': 0.9824668169021606} 08/30/2021 23:49:25 - INFO - __main__ - Step 59105: {'lr': 0.00033775284941020854, 'samples': 11348160, 'steps': 59104, 'loss/train': 1.4114757776260376} 08/30/2021 23:49:26 - INFO - __main__ - Step 59106: {'lr': 0.0003377478803079385, 'samples': 11348352, 'steps': 59105, 'loss/train': 1.3459184169769287} 08/30/2021 23:49:26 - INFO - __main__ - Step 59107: {'lr': 0.00033774291116613054, 'samples': 11348544, 'steps': 59106, 'loss/train': 1.4335577487945557} 08/30/2021 23:49:28 - INFO - __main__ - Step 59108: {'lr': 0.000337737941984787, 'samples': 11348736, 'steps': 59107, 'loss/train': 1.279528260231018} 08/30/2021 23:49:28 - INFO - __main__ - Step 59109: {'lr': 0.00033773297276391015, 'samples': 11348928, 'steps': 59108, 'loss/train': 1.2339500188827515} 08/30/2021 23:49:28 - INFO - __main__ - Step 59110: {'lr': 0.00033772800350350215, 'samples': 11349120, 'steps': 59109, 'loss/train': 1.626023530960083} 08/30/2021 23:49:29 - INFO - __main__ - Step 59111: {'lr': 0.0003377230342035653, 'samples': 11349312, 'steps': 59110, 'loss/train': 1.2343449592590332} 08/30/2021 23:49:29 - INFO - __main__ - Step 59112: {'lr': 0.00033771806486410176, 'samples': 11349504, 'steps': 59111, 'loss/train': 1.349181056022644} 08/30/2021 23:49:29 - INFO - __main__ - Step 59113: {'lr': 0.0003377130954851138, 'samples': 11349696, 'steps': 59112, 'loss/train': 1.0913158655166626} 08/30/2021 23:49:31 - INFO - __main__ - Step 59114: {'lr': 0.0003377081260666037, 'samples': 11349888, 'steps': 59113, 'loss/train': 1.4126912355422974} 08/30/2021 23:49:31 - INFO - __main__ - Step 59115: {'lr': 0.00033770315660857367, 'samples': 11350080, 'steps': 59114, 'loss/train': 1.5371184349060059} 08/30/2021 23:49:32 - INFO - __main__ - Step 59116: {'lr': 0.00033769818711102594, 'samples': 11350272, 'steps': 59115, 'loss/train': 1.3325474262237549} 08/30/2021 23:49:32 - INFO - __main__ - Step 59117: {'lr': 0.0003376932175739628, 'samples': 11350464, 'steps': 59116, 'loss/train': 1.24488365650177} 08/30/2021 23:49:33 - INFO - __main__ - Step 59118: {'lr': 0.00033768824799738646, 'samples': 11350656, 'steps': 59117, 'loss/train': 1.6751515865325928} 08/30/2021 23:49:34 - INFO - __main__ - Step 59119: {'lr': 0.0003376832783812991, 'samples': 11350848, 'steps': 59118, 'loss/train': 0.6848888397216797} 08/30/2021 23:49:35 - INFO - __main__ - Step 59120: {'lr': 0.000337678308725703, 'samples': 11351040, 'steps': 59119, 'loss/train': 1.3367704153060913} 08/30/2021 23:49:35 - INFO - __main__ - Step 59121: {'lr': 0.0003376733390306004, 'samples': 11351232, 'steps': 59120, 'loss/train': 1.1341562271118164} 08/30/2021 23:49:35 - INFO - __main__ - Step 59122: {'lr': 0.00033766836929599353, 'samples': 11351424, 'steps': 59121, 'loss/train': 0.6218701004981995} 08/30/2021 23:49:36 - INFO - __main__ - Step 59123: {'lr': 0.00033766339952188474, 'samples': 11351616, 'steps': 59122, 'loss/train': 0.9765797853469849} 08/30/2021 23:49:38 - INFO - __main__ - Step 59124: {'lr': 0.0003376584297082761, 'samples': 11351808, 'steps': 59123, 'loss/train': 1.1154900789260864} 08/30/2021 23:49:38 - INFO - __main__ - Step 59125: {'lr': 0.00033765345985517, 'samples': 11352000, 'steps': 59124, 'loss/train': 1.4942351579666138} 08/30/2021 23:49:39 - INFO - __main__ - Step 59126: {'lr': 0.0003376484899625685, 'samples': 11352192, 'steps': 59125, 'loss/train': 0.7903887629508972} 08/30/2021 23:49:39 - INFO - __main__ - Step 59127: {'lr': 0.00033764352003047397, 'samples': 11352384, 'steps': 59126, 'loss/train': 1.0410959720611572} 08/30/2021 23:49:39 - INFO - __main__ - Step 59128: {'lr': 0.00033763855005888865, 'samples': 11352576, 'steps': 59127, 'loss/train': 1.1598892211914062} 08/30/2021 23:49:41 - INFO - __main__ - Step 59129: {'lr': 0.00033763358004781474, 'samples': 11352768, 'steps': 59128, 'loss/train': 1.5421558618545532} 08/30/2021 23:49:41 - INFO - __main__ - Step 59130: {'lr': 0.00033762860999725456, 'samples': 11352960, 'steps': 59129, 'loss/train': 1.5244030952453613} 08/30/2021 23:49:42 - INFO - __main__ - Step 59131: {'lr': 0.0003376236399072101, 'samples': 11353152, 'steps': 59130, 'loss/train': 1.486205816268921} 08/30/2021 23:49:42 - INFO - __main__ - Step 59132: {'lr': 0.000337618669777684, 'samples': 11353344, 'steps': 59131, 'loss/train': 1.4284369945526123} 08/30/2021 23:49:42 - INFO - __main__ - Step 59133: {'lr': 0.0003376136996086782, 'samples': 11353536, 'steps': 59132, 'loss/train': 1.327958106994629} 08/30/2021 23:49:44 - INFO - __main__ - Step 59134: {'lr': 0.00033760872940019496, 'samples': 11353728, 'steps': 59133, 'loss/train': 0.91539466381073} 08/30/2021 23:49:44 - INFO - __main__ - Step 59135: {'lr': 0.00033760375915223664, 'samples': 11353920, 'steps': 59134, 'loss/train': 1.392862319946289} 08/30/2021 23:49:45 - INFO - __main__ - Step 59136: {'lr': 0.00033759878886480534, 'samples': 11354112, 'steps': 59135, 'loss/train': 1.9612127542495728} 08/30/2021 23:49:45 - INFO - __main__ - Step 59137: {'lr': 0.00033759381853790344, 'samples': 11354304, 'steps': 59136, 'loss/train': 1.0899419784545898} 08/30/2021 23:49:45 - INFO - __main__ - Step 59138: {'lr': 0.0003375888481715331, 'samples': 11354496, 'steps': 59137, 'loss/train': 1.32756507396698} 08/30/2021 23:49:47 - INFO - __main__ - Step 59139: {'lr': 0.0003375838777656966, 'samples': 11354688, 'steps': 59138, 'loss/train': 1.245195746421814} 08/30/2021 23:49:47 - INFO - __main__ - Step 59140: {'lr': 0.00033757890732039617, 'samples': 11354880, 'steps': 59139, 'loss/train': 1.583940029144287} 08/30/2021 23:49:48 - INFO - __main__ - Step 59141: {'lr': 0.000337573936835634, 'samples': 11355072, 'steps': 59140, 'loss/train': 1.5980420112609863} 08/30/2021 23:49:48 - INFO - __main__ - Step 59142: {'lr': 0.0003375689663114123, 'samples': 11355264, 'steps': 59141, 'loss/train': 1.2343775033950806} 08/30/2021 23:49:48 - INFO - __main__ - Step 59143: {'lr': 0.00033756399574773343, 'samples': 11355456, 'steps': 59142, 'loss/train': 1.2602927684783936} 08/30/2021 23:49:49 - INFO - __main__ - Step 59144: {'lr': 0.00033755902514459964, 'samples': 11355648, 'steps': 59143, 'loss/train': 0.9806532263755798} 08/30/2021 23:49:50 - INFO - __main__ - Step 59145: {'lr': 0.0003375540545020131, 'samples': 11355840, 'steps': 59144, 'loss/train': 1.2947758436203003} 08/30/2021 23:49:51 - INFO - __main__ - Step 59146: {'lr': 0.00033754908381997595, 'samples': 11356032, 'steps': 59145, 'loss/train': 1.7343069314956665} 08/30/2021 23:49:51 - INFO - __main__ - Step 59147: {'lr': 0.00033754411309849065, 'samples': 11356224, 'steps': 59146, 'loss/train': 1.4165982007980347} 08/30/2021 23:49:51 - INFO - __main__ - Step 59148: {'lr': 0.0003375391423375592, 'samples': 11356416, 'steps': 59147, 'loss/train': 0.9391774535179138} 08/30/2021 23:49:52 - INFO - __main__ - Step 59149: {'lr': 0.00033753417153718405, 'samples': 11356608, 'steps': 59148, 'loss/train': 1.4960434436798096} 08/30/2021 23:49:53 - INFO - __main__ - Step 59150: {'lr': 0.0003375292006973673, 'samples': 11356800, 'steps': 59149, 'loss/train': 1.2977248430252075} 08/30/2021 23:49:54 - INFO - __main__ - Step 59151: {'lr': 0.0003375242298181113, 'samples': 11356992, 'steps': 59150, 'loss/train': 1.2777845859527588} 08/30/2021 23:49:54 - INFO - __main__ - Step 59152: {'lr': 0.0003375192588994183, 'samples': 11357184, 'steps': 59151, 'loss/train': 1.3735532760620117} 08/30/2021 23:49:55 - INFO - __main__ - Step 59153: {'lr': 0.0003375142879412903, 'samples': 11357376, 'steps': 59152, 'loss/train': 0.027669517323374748} 08/30/2021 23:49:55 - INFO - __main__ - Step 59154: {'lr': 0.0003375093169437298, 'samples': 11357568, 'steps': 59153, 'loss/train': 0.028685377910733223} 08/30/2021 23:49:57 - INFO - __main__ - Step 59155: {'lr': 0.00033750434590673893, 'samples': 11357760, 'steps': 59154, 'loss/train': 0.8482067584991455} 08/30/2021 23:49:57 - INFO - __main__ - Step 59156: {'lr': 0.00033749937483031994, 'samples': 11357952, 'steps': 59155, 'loss/train': 1.3036620616912842} 08/30/2021 23:49:57 - INFO - __main__ - Step 59157: {'lr': 0.00033749440371447513, 'samples': 11358144, 'steps': 59156, 'loss/train': 1.0252490043640137} 08/30/2021 23:49:58 - INFO - __main__ - Step 59158: {'lr': 0.00033748943255920667, 'samples': 11358336, 'steps': 59157, 'loss/train': 1.1696373224258423} 08/30/2021 23:49:58 - INFO - __main__ - Step 59159: {'lr': 0.00033748446136451683, 'samples': 11358528, 'steps': 59158, 'loss/train': 1.4819964170455933} 08/30/2021 23:49:58 - INFO - __main__ - Step 59160: {'lr': 0.00033747949013040784, 'samples': 11358720, 'steps': 59159, 'loss/train': 1.4724578857421875} 08/30/2021 23:50:00 - INFO - __main__ - Step 59161: {'lr': 0.000337474518856882, 'samples': 11358912, 'steps': 59160, 'loss/train': 0.4776204526424408} 08/30/2021 23:50:00 - INFO - __main__ - Step 59162: {'lr': 0.0003374695475439413, 'samples': 11359104, 'steps': 59161, 'loss/train': 1.6590086221694946} 08/30/2021 23:50:01 - INFO - __main__ - Step 59163: {'lr': 0.0003374645761915883, 'samples': 11359296, 'steps': 59162, 'loss/train': 1.0549745559692383} 08/30/2021 23:50:01 - INFO - __main__ - Step 59164: {'lr': 0.00033745960479982515, 'samples': 11359488, 'steps': 59163, 'loss/train': 1.7718043327331543} 08/30/2021 23:50:01 - INFO - __main__ - Step 59165: {'lr': 0.00033745463336865407, 'samples': 11359680, 'steps': 59164, 'loss/train': 0.9100641012191772} 08/30/2021 23:50:03 - INFO - __main__ - Step 59166: {'lr': 0.0003374496618980772, 'samples': 11359872, 'steps': 59165, 'loss/train': 0.932635486125946} 08/30/2021 23:50:03 - INFO - __main__ - Step 59167: {'lr': 0.0003374446903880969, 'samples': 11360064, 'steps': 59166, 'loss/train': 0.7368623614311218} 08/30/2021 23:50:04 - INFO - __main__ - Step 59168: {'lr': 0.0003374397188387153, 'samples': 11360256, 'steps': 59167, 'loss/train': 1.3862361907958984} 08/30/2021 23:50:04 - INFO - __main__ - Step 59169: {'lr': 0.0003374347472499348, 'samples': 11360448, 'steps': 59168, 'loss/train': 0.9291672110557556} 08/30/2021 23:50:04 - INFO - __main__ - Step 59170: {'lr': 0.00033742977562175756, 'samples': 11360640, 'steps': 59169, 'loss/train': 0.8995817303657532} 08/30/2021 23:50:06 - INFO - __main__ - Step 59171: {'lr': 0.00033742480395418574, 'samples': 11360832, 'steps': 59170, 'loss/train': 1.3394420146942139} 08/30/2021 23:50:06 - INFO - __main__ - Step 59172: {'lr': 0.0003374198322472217, 'samples': 11361024, 'steps': 59171, 'loss/train': 1.3764405250549316} 08/30/2021 23:50:07 - INFO - __main__ - Step 59173: {'lr': 0.00033741486050086763, 'samples': 11361216, 'steps': 59172, 'loss/train': 0.6670469045639038} 08/30/2021 23:50:07 - INFO - __main__ - Step 59174: {'lr': 0.00033740988871512574, 'samples': 11361408, 'steps': 59173, 'loss/train': 1.5665777921676636} 08/30/2021 23:50:07 - INFO - __main__ - Step 59175: {'lr': 0.0003374049168899983, 'samples': 11361600, 'steps': 59174, 'loss/train': 1.2131277322769165} 08/30/2021 23:50:10 - INFO - __main__ - Step 59176: {'lr': 0.00033739994502548766, 'samples': 11361792, 'steps': 59175, 'loss/train': 1.4755932092666626} 08/30/2021 23:50:10 - INFO - __main__ - Step 59177: {'lr': 0.0003373949731215958, 'samples': 11361984, 'steps': 59176, 'loss/train': 1.3366997241973877} 08/30/2021 23:50:11 - INFO - __main__ - Step 59178: {'lr': 0.0003373900011783252, 'samples': 11362176, 'steps': 59177, 'loss/train': 1.3102545738220215} 08/30/2021 23:50:11 - INFO - __main__ - Step 59179: {'lr': 0.000337385029195678, 'samples': 11362368, 'steps': 59178, 'loss/train': 1.5608906745910645} 08/30/2021 23:50:11 - INFO - __main__ - Step 59180: {'lr': 0.00033738005717365646, 'samples': 11362560, 'steps': 59179, 'loss/train': 0.5504551529884338} 08/30/2021 23:50:12 - INFO - __main__ - Step 59181: {'lr': 0.00033737508511226283, 'samples': 11362752, 'steps': 59180, 'loss/train': 0.8778849840164185} 08/30/2021 23:50:13 - INFO - __main__ - Step 59182: {'lr': 0.00033737011301149933, 'samples': 11362944, 'steps': 59181, 'loss/train': 1.2649993896484375} 08/30/2021 23:50:14 - INFO - __main__ - Step 59183: {'lr': 0.0003373651408713682, 'samples': 11363136, 'steps': 59182, 'loss/train': 1.1484754085540771} 08/30/2021 23:50:14 - INFO - __main__ - Step 59184: {'lr': 0.00033736016869187165, 'samples': 11363328, 'steps': 59183, 'loss/train': 1.557829737663269} 08/30/2021 23:50:14 - INFO - __main__ - Step 59185: {'lr': 0.0003373551964730119, 'samples': 11363520, 'steps': 59184, 'loss/train': 1.0870318412780762} 08/30/2021 23:50:15 - INFO - __main__ - Step 59186: {'lr': 0.00033735022421479136, 'samples': 11363712, 'steps': 59185, 'loss/train': 1.6649073362350464} 08/30/2021 23:50:17 - INFO - __main__ - Step 59187: {'lr': 0.00033734525191721215, 'samples': 11363904, 'steps': 59186, 'loss/train': 0.9039666056632996} 08/30/2021 23:50:17 - INFO - __main__ - Step 59188: {'lr': 0.00033734027958027646, 'samples': 11364096, 'steps': 59187, 'loss/train': 1.5094884634017944} 08/30/2021 23:50:17 - INFO - __main__ - Step 59189: {'lr': 0.00033733530720398666, 'samples': 11364288, 'steps': 59188, 'loss/train': 1.1415201425552368} 08/30/2021 23:50:18 - INFO - __main__ - Step 59190: {'lr': 0.00033733033478834483, 'samples': 11364480, 'steps': 59189, 'loss/train': 1.6091244220733643} 08/30/2021 23:50:18 - INFO - __main__ - Step 59191: {'lr': 0.00033732536233335334, 'samples': 11364672, 'steps': 59190, 'loss/train': 1.1276490688323975} 08/30/2021 23:50:18 - INFO - __main__ - Step 59192: {'lr': 0.0003373203898390145, 'samples': 11364864, 'steps': 59191, 'loss/train': 1.5039596557617188} 08/30/2021 23:50:19 - INFO - __main__ - Step 59193: {'lr': 0.0003373154173053303, 'samples': 11365056, 'steps': 59192, 'loss/train': 0.027178999036550522} 08/30/2021 23:50:20 - INFO - __main__ - Step 59194: {'lr': 0.0003373104447323031, 'samples': 11365248, 'steps': 59193, 'loss/train': 1.0749531984329224} 08/30/2021 23:50:21 - INFO - __main__ - Step 59195: {'lr': 0.00033730547211993525, 'samples': 11365440, 'steps': 59194, 'loss/train': 1.5997252464294434} 08/30/2021 23:50:21 - INFO - __main__ - Step 59196: {'lr': 0.00033730049946822883, 'samples': 11365632, 'steps': 59195, 'loss/train': 0.8369849324226379} 08/30/2021 23:50:21 - INFO - __main__ - Step 59197: {'lr': 0.0003372955267771862, 'samples': 11365824, 'steps': 59196, 'loss/train': 0.8300724625587463} 08/30/2021 23:50:22 - INFO - __main__ - Step 59198: {'lr': 0.00033729055404680953, 'samples': 11366016, 'steps': 59197, 'loss/train': 1.1340458393096924} 08/30/2021 23:50:23 - INFO - __main__ - Step 59199: {'lr': 0.00033728558127710115, 'samples': 11366208, 'steps': 59198, 'loss/train': 1.2824549674987793} 08/30/2021 23:50:24 - INFO - __main__ - Step 59200: {'lr': 0.0003372806084680632, 'samples': 11366400, 'steps': 59199, 'loss/train': 1.3560410737991333} 08/30/2021 23:50:24 - INFO - __main__ - Step 59201: {'lr': 0.0003372756356196979, 'samples': 11366592, 'steps': 59200, 'loss/train': 1.1852643489837646} 08/30/2021 23:50:24 - INFO - __main__ - Step 59202: {'lr': 0.0003372706627320076, 'samples': 11366784, 'steps': 59201, 'loss/train': 0.07068157941102982} 08/30/2021 23:50:25 - INFO - __main__ - Step 59203: {'lr': 0.0003372656898049944, 'samples': 11366976, 'steps': 59202, 'loss/train': 1.2502074241638184} 08/30/2021 23:50:26 - INFO - __main__ - Step 59204: {'lr': 0.0003372607168386607, 'samples': 11367168, 'steps': 59203, 'loss/train': 1.4712998867034912} 08/30/2021 23:50:27 - INFO - __main__ - Step 59205: {'lr': 0.00033725574383300865, 'samples': 11367360, 'steps': 59204, 'loss/train': 1.6538299322128296} 08/30/2021 23:50:27 - INFO - __main__ - Step 59206: {'lr': 0.0003372507707880406, 'samples': 11367552, 'steps': 59205, 'loss/train': 1.634321689605713} 08/30/2021 23:50:27 - INFO - __main__ - Step 59207: {'lr': 0.0003372457977037586, 'samples': 11367744, 'steps': 59206, 'loss/train': 1.3178449869155884} 08/30/2021 23:50:28 - INFO - __main__ - Step 59208: {'lr': 0.000337240824580165, 'samples': 11367936, 'steps': 59207, 'loss/train': 0.8513045310974121} 08/30/2021 23:50:29 - INFO - __main__ - Step 59209: {'lr': 0.00033723585141726196, 'samples': 11368128, 'steps': 59208, 'loss/train': 1.4241957664489746} 08/30/2021 23:50:30 - INFO - __main__ - Step 59210: {'lr': 0.0003372308782150519, 'samples': 11368320, 'steps': 59209, 'loss/train': 0.6088467836380005} 08/30/2021 23:50:30 - INFO - __main__ - Step 59211: {'lr': 0.0003372259049735369, 'samples': 11368512, 'steps': 59210, 'loss/train': 1.6015602350234985} 08/30/2021 23:50:31 - INFO - __main__ - Step 59212: {'lr': 0.00033722093169271934, 'samples': 11368704, 'steps': 59211, 'loss/train': 1.5628141164779663} 08/30/2021 23:50:31 - INFO - __main__ - Step 59213: {'lr': 0.00033721595837260125, 'samples': 11368896, 'steps': 59212, 'loss/train': 1.4928135871887207} 08/30/2021 23:50:32 - INFO - __main__ - Step 59214: {'lr': 0.00033721098501318506, 'samples': 11369088, 'steps': 59213, 'loss/train': 1.8468180894851685} 08/30/2021 23:50:33 - INFO - __main__ - Step 59215: {'lr': 0.00033720601161447294, 'samples': 11369280, 'steps': 59214, 'loss/train': 1.0922880172729492} 08/30/2021 23:50:33 - INFO - __main__ - Step 59216: {'lr': 0.0003372010381764671, 'samples': 11369472, 'steps': 59215, 'loss/train': 1.5723910331726074} 08/30/2021 23:50:34 - INFO - __main__ - Step 59217: {'lr': 0.00033719606469916985, 'samples': 11369664, 'steps': 59216, 'loss/train': 1.4356945753097534} 08/30/2021 23:50:34 - INFO - __main__ - Step 59218: {'lr': 0.0003371910911825834, 'samples': 11369856, 'steps': 59217, 'loss/train': 1.427831768989563} 08/30/2021 23:50:35 - INFO - __main__ - Step 59219: {'lr': 0.00033718611762671003, 'samples': 11370048, 'steps': 59218, 'loss/train': 1.24912428855896} 08/30/2021 23:50:36 - INFO - __main__ - Step 59220: {'lr': 0.0003371811440315519, 'samples': 11370240, 'steps': 59219, 'loss/train': 1.1611627340316772} 08/30/2021 23:50:36 - INFO - __main__ - Step 59221: {'lr': 0.0003371761703971113, 'samples': 11370432, 'steps': 59220, 'loss/train': 1.7564440965652466} 08/30/2021 23:50:37 - INFO - __main__ - Step 59222: {'lr': 0.0003371711967233905, 'samples': 11370624, 'steps': 59221, 'loss/train': 1.4979043006896973} 08/30/2021 23:50:37 - INFO - __main__ - Step 59223: {'lr': 0.00033716622301039164, 'samples': 11370816, 'steps': 59222, 'loss/train': 1.5645051002502441} 08/30/2021 23:50:39 - INFO - __main__ - Step 59224: {'lr': 0.000337161249258117, 'samples': 11371008, 'steps': 59223, 'loss/train': 0.06679113954305649} 08/30/2021 23:50:40 - INFO - __main__ - Step 59225: {'lr': 0.0003371562754665689, 'samples': 11371200, 'steps': 59224, 'loss/train': 0.7724702954292297} 08/30/2021 23:50:40 - INFO - __main__ - Step 59226: {'lr': 0.0003371513016357496, 'samples': 11371392, 'steps': 59225, 'loss/train': 1.2717159986495972} 08/30/2021 23:50:40 - INFO - __main__ - Step 59227: {'lr': 0.0003371463277656611, 'samples': 11371584, 'steps': 59226, 'loss/train': 2.083587169647217} 08/30/2021 23:50:41 - INFO - __main__ - Step 59228: {'lr': 0.00033714135385630597, 'samples': 11371776, 'steps': 59227, 'loss/train': 1.528214693069458} 08/30/2021 23:50:41 - INFO - __main__ - Step 59229: {'lr': 0.0003371363799076862, 'samples': 11371968, 'steps': 59228, 'loss/train': 0.02398977428674698} 08/30/2021 23:50:42 - INFO - __main__ - Step 59230: {'lr': 0.00033713140591980407, 'samples': 11372160, 'steps': 59229, 'loss/train': 0.7743310332298279} 08/30/2021 23:50:43 - INFO - __main__ - Step 59231: {'lr': 0.00033712643189266197, 'samples': 11372352, 'steps': 59230, 'loss/train': 1.37897789478302} 08/30/2021 23:50:43 - INFO - __main__ - Step 59232: {'lr': 0.00033712145782626205, 'samples': 11372544, 'steps': 59231, 'loss/train': 1.1560449600219727} 08/30/2021 23:50:44 - INFO - __main__ - Step 59233: {'lr': 0.0003371164837206065, 'samples': 11372736, 'steps': 59232, 'loss/train': 1.9193859100341797} 08/30/2021 23:50:44 - INFO - __main__ - Step 59234: {'lr': 0.00033711150957569763, 'samples': 11372928, 'steps': 59233, 'loss/train': 1.3624557256698608} 08/30/2021 23:50:46 - INFO - __main__ - Step 59235: {'lr': 0.00033710653539153763, 'samples': 11373120, 'steps': 59234, 'loss/train': 1.0654305219650269} 08/30/2021 23:50:47 - INFO - __main__ - Step 59236: {'lr': 0.0003371015611681288, 'samples': 11373312, 'steps': 59235, 'loss/train': 1.335206151008606} 08/30/2021 23:50:47 - INFO - __main__ - Step 59237: {'lr': 0.0003370965869054733, 'samples': 11373504, 'steps': 59236, 'loss/train': 0.5567643046379089} 08/30/2021 23:50:47 - INFO - __main__ - Step 59238: {'lr': 0.0003370916126035735, 'samples': 11373696, 'steps': 59237, 'loss/train': 1.6595019102096558} 08/30/2021 23:50:48 - INFO - __main__ - Step 59239: {'lr': 0.0003370866382624315, 'samples': 11373888, 'steps': 59238, 'loss/train': 0.995984673500061} 08/30/2021 23:50:48 - INFO - __main__ - Step 59240: {'lr': 0.00033708166388204963, 'samples': 11374080, 'steps': 59239, 'loss/train': 1.346091628074646} 08/30/2021 23:50:50 - INFO - __main__ - Step 59241: {'lr': 0.0003370766894624301, 'samples': 11374272, 'steps': 59240, 'loss/train': 1.6816624402999878} 08/30/2021 23:50:50 - INFO - __main__ - Step 59242: {'lr': 0.00033707171500357516, 'samples': 11374464, 'steps': 59241, 'loss/train': 0.720859706401825} 08/30/2021 23:50:51 - INFO - __main__ - Step 59243: {'lr': 0.000337066740505487, 'samples': 11374656, 'steps': 59242, 'loss/train': 2.220306873321533} 08/30/2021 23:50:51 - INFO - __main__ - Step 59244: {'lr': 0.00033706176596816795, 'samples': 11374848, 'steps': 59243, 'loss/train': 0.36801525950431824} 08/30/2021 23:50:51 - INFO - __main__ - Step 59245: {'lr': 0.0003370567913916203, 'samples': 11375040, 'steps': 59244, 'loss/train': 1.36960768699646} 08/30/2021 23:50:53 - INFO - __main__ - Step 59246: {'lr': 0.0003370518167758461, 'samples': 11375232, 'steps': 59245, 'loss/train': 1.4784328937530518} 08/30/2021 23:50:54 - INFO - __main__ - Step 59247: {'lr': 0.00033704684212084774, 'samples': 11375424, 'steps': 59246, 'loss/train': 0.7090513706207275} 08/30/2021 23:50:54 - INFO - __main__ - Step 59248: {'lr': 0.0003370418674266273, 'samples': 11375616, 'steps': 59247, 'loss/train': 1.4179662466049194} 08/30/2021 23:50:54 - INFO - __main__ - Step 59249: {'lr': 0.00033703689269318725, 'samples': 11375808, 'steps': 59248, 'loss/train': 1.3202729225158691} 08/30/2021 23:50:55 - INFO - __main__ - Step 59250: {'lr': 0.00033703191792052974, 'samples': 11376000, 'steps': 59249, 'loss/train': 0.5380207300186157} 08/30/2021 23:50:56 - INFO - __main__ - Step 59251: {'lr': 0.00033702694310865696, 'samples': 11376192, 'steps': 59250, 'loss/train': 1.65398108959198} 08/30/2021 23:50:56 - INFO - __main__ - Step 59252: {'lr': 0.00033702196825757114, 'samples': 11376384, 'steps': 59251, 'loss/train': 1.7687321901321411} 08/30/2021 23:50:57 - INFO - __main__ - Step 59253: {'lr': 0.00033701699336727465, 'samples': 11376576, 'steps': 59252, 'loss/train': 0.9318382143974304} 08/30/2021 23:50:57 - INFO - __main__ - Step 59254: {'lr': 0.00033701201843776957, 'samples': 11376768, 'steps': 59253, 'loss/train': 1.4884229898452759} 08/30/2021 23:50:57 - INFO - __main__ - Step 59255: {'lr': 0.0003370070434690583, 'samples': 11376960, 'steps': 59254, 'loss/train': 1.2110114097595215} 08/30/2021 23:50:59 - INFO - __main__ - Step 59256: {'lr': 0.0003370020684611429, 'samples': 11377152, 'steps': 59255, 'loss/train': 1.1395328044891357} 08/30/2021 23:50:59 - INFO - __main__ - Step 59257: {'lr': 0.0003369970934140257, 'samples': 11377344, 'steps': 59256, 'loss/train': 1.4840216636657715} 08/30/2021 23:51:00 - INFO - __main__ - Step 59258: {'lr': 0.00033699211832770906, 'samples': 11377536, 'steps': 59257, 'loss/train': 1.5603110790252686} 08/30/2021 23:51:00 - INFO - __main__ - Step 59259: {'lr': 0.000336987143202195, 'samples': 11377728, 'steps': 59258, 'loss/train': 1.1304256916046143} 08/30/2021 23:51:00 - INFO - __main__ - Step 59260: {'lr': 0.000336982168037486, 'samples': 11377920, 'steps': 59259, 'loss/train': 1.4614261388778687} 08/30/2021 23:51:03 - INFO - __main__ - Step 59261: {'lr': 0.0003369771928335841, 'samples': 11378112, 'steps': 59260, 'loss/train': 1.1103240251541138} 08/30/2021 23:51:03 - INFO - __main__ - Step 59262: {'lr': 0.00033697221759049163, 'samples': 11378304, 'steps': 59261, 'loss/train': 1.5771194696426392} 08/30/2021 23:51:03 - INFO - __main__ - Step 59263: {'lr': 0.0003369672423082108, 'samples': 11378496, 'steps': 59262, 'loss/train': 0.5105088949203491} 08/30/2021 23:51:04 - INFO - __main__ - Step 59264: {'lr': 0.00033696226698674386, 'samples': 11378688, 'steps': 59263, 'loss/train': 2.739560127258301} 08/30/2021 23:51:04 - INFO - __main__ - Step 59265: {'lr': 0.0003369572916260931, 'samples': 11378880, 'steps': 59264, 'loss/train': 2.1617205142974854} 08/30/2021 23:51:04 - INFO - __main__ - Step 59266: {'lr': 0.0003369523162262608, 'samples': 11379072, 'steps': 59265, 'loss/train': 1.4375048875808716} 08/30/2021 23:51:05 - INFO - __main__ - Step 59267: {'lr': 0.00033694734078724904, 'samples': 11379264, 'steps': 59266, 'loss/train': 1.400809407234192} 08/30/2021 23:51:07 - INFO - __main__ - Step 59268: {'lr': 0.00033694236530906014, 'samples': 11379456, 'steps': 59267, 'loss/train': 1.6229270696640015} 08/30/2021 23:51:07 - INFO - __main__ - Step 59269: {'lr': 0.00033693738979169636, 'samples': 11379648, 'steps': 59268, 'loss/train': 1.2574315071105957} 08/30/2021 23:51:07 - INFO - __main__ - Step 59270: {'lr': 0.0003369324142351599, 'samples': 11379840, 'steps': 59269, 'loss/train': 1.1877094507217407} 08/30/2021 23:51:08 - INFO - __main__ - Step 59271: {'lr': 0.0003369274386394531, 'samples': 11380032, 'steps': 59270, 'loss/train': 1.8981167078018188} 08/30/2021 23:51:08 - INFO - __main__ - Step 59272: {'lr': 0.0003369224630045781, 'samples': 11380224, 'steps': 59271, 'loss/train': 1.360382080078125} 08/30/2021 23:51:10 - INFO - __main__ - Step 59273: {'lr': 0.0003369174873305373, 'samples': 11380416, 'steps': 59272, 'loss/train': 1.6627168655395508} 08/30/2021 23:51:10 - INFO - __main__ - Step 59274: {'lr': 0.0003369125116173327, 'samples': 11380608, 'steps': 59273, 'loss/train': 1.6665995121002197} 08/30/2021 23:51:10 - INFO - __main__ - Step 59275: {'lr': 0.00033690753586496666, 'samples': 11380800, 'steps': 59274, 'loss/train': 0.9362266063690186} 08/30/2021 23:51:11 - INFO - __main__ - Step 59276: {'lr': 0.00033690256007344144, 'samples': 11380992, 'steps': 59275, 'loss/train': 1.3537232875823975} 08/30/2021 23:51:11 - INFO - __main__ - Step 59277: {'lr': 0.0003368975842427592, 'samples': 11381184, 'steps': 59276, 'loss/train': 0.5287055969238281} 08/30/2021 23:51:12 - INFO - __main__ - Step 59278: {'lr': 0.00033689260837292234, 'samples': 11381376, 'steps': 59277, 'loss/train': 0.8119242787361145} 08/30/2021 23:51:13 - INFO - __main__ - Step 59279: {'lr': 0.000336887632463933, 'samples': 11381568, 'steps': 59278, 'loss/train': 1.715207815170288} 08/30/2021 23:51:13 - INFO - __main__ - Step 59280: {'lr': 0.00033688265651579354, 'samples': 11381760, 'steps': 59279, 'loss/train': 1.3267779350280762} 08/30/2021 23:51:14 - INFO - __main__ - Step 59281: {'lr': 0.0003368776805285059, 'samples': 11381952, 'steps': 59280, 'loss/train': 1.1703482866287231} 08/30/2021 23:51:14 - INFO - __main__ - Step 59282: {'lr': 0.0003368727045020726, 'samples': 11382144, 'steps': 59281, 'loss/train': 1.4100213050842285} 08/30/2021 23:51:16 - INFO - __main__ - Step 59283: {'lr': 0.00033686772843649583, 'samples': 11382336, 'steps': 59282, 'loss/train': 1.1155202388763428} 08/30/2021 23:51:17 - INFO - __main__ - Step 59284: {'lr': 0.00033686275233177777, 'samples': 11382528, 'steps': 59283, 'loss/train': 0.8511165380477905} 08/30/2021 23:51:17 - INFO - __main__ - Step 59285: {'lr': 0.00033685777618792066, 'samples': 11382720, 'steps': 59284, 'loss/train': 1.948175072669983} 08/30/2021 23:51:17 - INFO - __main__ - Step 59286: {'lr': 0.0003368528000049269, 'samples': 11382912, 'steps': 59285, 'loss/train': 1.2594410181045532} 08/30/2021 23:51:18 - INFO - __main__ - Step 59287: {'lr': 0.00033684782378279847, 'samples': 11383104, 'steps': 59286, 'loss/train': 1.8910175561904907} 08/30/2021 23:51:18 - INFO - __main__ - Step 59288: {'lr': 0.0003368428475215378, 'samples': 11383296, 'steps': 59287, 'loss/train': 1.1009361743927002} 08/30/2021 23:51:20 - INFO - __main__ - Step 59289: {'lr': 0.00033683787122114713, 'samples': 11383488, 'steps': 59288, 'loss/train': 3.395280361175537} 08/30/2021 23:51:20 - INFO - __main__ - Step 59290: {'lr': 0.0003368328948816286, 'samples': 11383680, 'steps': 59289, 'loss/train': 0.5369886755943298} 08/30/2021 23:51:21 - INFO - __main__ - Step 59291: {'lr': 0.0003368279185029845, 'samples': 11383872, 'steps': 59290, 'loss/train': 1.105175495147705} 08/30/2021 23:51:21 - INFO - __main__ - Step 59292: {'lr': 0.0003368229420852171, 'samples': 11384064, 'steps': 59291, 'loss/train': 1.9590833187103271} 08/30/2021 23:51:22 - INFO - __main__ - Step 59293: {'lr': 0.00033681796562832865, 'samples': 11384256, 'steps': 59292, 'loss/train': 1.5062144994735718} 08/30/2021 23:51:23 - INFO - __main__ - Step 59294: {'lr': 0.0003368129891323213, 'samples': 11384448, 'steps': 59293, 'loss/train': 1.5120887756347656} 08/30/2021 23:51:24 - INFO - __main__ - Step 59295: {'lr': 0.0003368080125971974, 'samples': 11384640, 'steps': 59294, 'loss/train': 1.087343692779541} 08/30/2021 23:51:24 - INFO - __main__ - Step 59296: {'lr': 0.00033680303602295913, 'samples': 11384832, 'steps': 59295, 'loss/train': 1.5824439525604248} 08/30/2021 23:51:24 - INFO - __main__ - Step 59297: {'lr': 0.00033679805940960877, 'samples': 11385024, 'steps': 59296, 'loss/train': 0.4324478507041931} 08/30/2021 23:51:25 - INFO - __main__ - Step 59298: {'lr': 0.0003367930827571485, 'samples': 11385216, 'steps': 59297, 'loss/train': 1.225721836090088} 08/30/2021 23:51:27 - INFO - __main__ - Step 59299: {'lr': 0.00033678810606558077, 'samples': 11385408, 'steps': 59298, 'loss/train': 0.47869542241096497} 08/30/2021 23:51:27 - INFO - __main__ - Step 59300: {'lr': 0.00033678312933490753, 'samples': 11385600, 'steps': 59299, 'loss/train': 1.7402771711349487} 08/30/2021 23:51:28 - INFO - __main__ - Step 59301: {'lr': 0.00033677815256513114, 'samples': 11385792, 'steps': 59300, 'loss/train': 1.4555498361587524} 08/30/2021 23:51:28 - INFO - __main__ - Step 59302: {'lr': 0.0003367731757562538, 'samples': 11385984, 'steps': 59301, 'loss/train': 0.8659315705299377} 08/30/2021 23:51:28 - INFO - __main__ - Step 59303: {'lr': 0.0003367681989082779, 'samples': 11386176, 'steps': 59302, 'loss/train': 0.028186127543449402} 08/30/2021 23:51:29 - INFO - __main__ - Step 59304: {'lr': 0.0003367632220212056, 'samples': 11386368, 'steps': 59303, 'loss/train': 1.7209151983261108} 08/30/2021 23:51:30 - INFO - __main__ - Step 59305: {'lr': 0.0003367582450950391, 'samples': 11386560, 'steps': 59304, 'loss/train': 1.6405874490737915} 08/30/2021 23:51:31 - INFO - __main__ - Step 59306: {'lr': 0.0003367532681297807, 'samples': 11386752, 'steps': 59305, 'loss/train': 0.9548050165176392} 08/30/2021 23:51:31 - INFO - __main__ - Step 59307: {'lr': 0.0003367482911254325, 'samples': 11386944, 'steps': 59306, 'loss/train': 1.6253842115402222} 08/30/2021 23:51:31 - INFO - __main__ - Step 59308: {'lr': 0.000336743314081997, 'samples': 11387136, 'steps': 59307, 'loss/train': 0.05865844339132309} 08/30/2021 23:51:32 - INFO - __main__ - Step 59309: {'lr': 0.0003367383369994762, 'samples': 11387328, 'steps': 59308, 'loss/train': 2.0783345699310303} 08/30/2021 23:51:33 - INFO - __main__ - Step 59310: {'lr': 0.0003367333598778725, 'samples': 11387520, 'steps': 59309, 'loss/train': 1.1801239252090454} 08/30/2021 23:51:34 - INFO - __main__ - Step 59311: {'lr': 0.0003367283827171881, 'samples': 11387712, 'steps': 59310, 'loss/train': 1.1335481405258179} 08/30/2021 23:51:34 - INFO - __main__ - Step 59312: {'lr': 0.0003367234055174252, 'samples': 11387904, 'steps': 59311, 'loss/train': 0.7261341214179993} 08/30/2021 23:51:34 - INFO - __main__ - Step 59313: {'lr': 0.00033671842827858605, 'samples': 11388096, 'steps': 59312, 'loss/train': 1.2450182437896729} 08/30/2021 23:51:35 - INFO - __main__ - Step 59314: {'lr': 0.000336713451000673, 'samples': 11388288, 'steps': 59313, 'loss/train': 0.8941906690597534} 08/30/2021 23:51:36 - INFO - __main__ - Step 59315: {'lr': 0.00033670847368368805, 'samples': 11388480, 'steps': 59314, 'loss/train': 0.6869674921035767} 08/30/2021 23:51:37 - INFO - __main__ - Step 59316: {'lr': 0.00033670349632763377, 'samples': 11388672, 'steps': 59315, 'loss/train': 1.5804328918457031} 08/30/2021 23:51:37 - INFO - __main__ - Step 59317: {'lr': 0.0003366985189325121, 'samples': 11388864, 'steps': 59316, 'loss/train': 0.6346843242645264} 08/30/2021 23:51:37 - INFO - __main__ - Step 59318: {'lr': 0.00033669354149832556, 'samples': 11389056, 'steps': 59317, 'loss/train': 1.1809628009796143} 08/30/2021 23:51:38 - INFO - __main__ - Step 59319: {'lr': 0.0003366885640250761, 'samples': 11389248, 'steps': 59318, 'loss/train': 1.1110634803771973} 08/30/2021 23:51:39 - INFO - __main__ - Step 59320: {'lr': 0.00033668358651276614, 'samples': 11389440, 'steps': 59319, 'loss/train': 1.554908275604248} 08/30/2021 23:51:40 - INFO - __main__ - Step 59321: {'lr': 0.000336678608961398, 'samples': 11389632, 'steps': 59320, 'loss/train': 1.4517171382904053} 08/30/2021 23:51:40 - INFO - __main__ - Step 59322: {'lr': 0.00033667363137097374, 'samples': 11389824, 'steps': 59321, 'loss/train': 0.8605591654777527} 08/30/2021 23:51:40 - INFO - __main__ - Step 59323: {'lr': 0.0003366686537414957, 'samples': 11390016, 'steps': 59322, 'loss/train': 0.647480309009552} 08/30/2021 23:51:41 - INFO - __main__ - Step 59324: {'lr': 0.00033666367607296607, 'samples': 11390208, 'steps': 59323, 'loss/train': 1.4006738662719727} 08/30/2021 23:51:41 - INFO - __main__ - Step 59325: {'lr': 0.0003366586983653871, 'samples': 11390400, 'steps': 59324, 'loss/train': 0.8329690098762512} 08/30/2021 23:51:42 - INFO - __main__ - Step 59326: {'lr': 0.0003366537206187611, 'samples': 11390592, 'steps': 59325, 'loss/train': 0.9495279788970947} 08/30/2021 23:51:43 - INFO - __main__ - Step 59327: {'lr': 0.0003366487428330903, 'samples': 11390784, 'steps': 59326, 'loss/train': 1.6387280225753784} 08/30/2021 23:51:43 - INFO - __main__ - Step 59328: {'lr': 0.0003366437650083768, 'samples': 11390976, 'steps': 59327, 'loss/train': 1.099772334098816} 08/30/2021 23:51:44 - INFO - __main__ - Step 59329: {'lr': 0.0003366387871446231, 'samples': 11391168, 'steps': 59328, 'loss/train': 1.3461673259735107} 08/30/2021 23:51:44 - INFO - __main__ - Step 59330: {'lr': 0.00033663380924183123, 'samples': 11391360, 'steps': 59329, 'loss/train': 1.021415114402771} 08/30/2021 23:51:46 - INFO - __main__ - Step 59331: {'lr': 0.0003366288313000035, 'samples': 11391552, 'steps': 59330, 'loss/train': 2.0180437564849854} 08/30/2021 23:51:46 - INFO - __main__ - Step 59332: {'lr': 0.00033662385331914216, 'samples': 11391744, 'steps': 59331, 'loss/train': 1.7529054880142212} 08/30/2021 23:51:46 - INFO - __main__ - Step 59333: {'lr': 0.0003366188752992495, 'samples': 11391936, 'steps': 59332, 'loss/train': 1.6668756008148193} 08/30/2021 23:51:47 - INFO - __main__ - Step 59334: {'lr': 0.00033661389724032765, 'samples': 11392128, 'steps': 59333, 'loss/train': 0.9454957842826843} 08/30/2021 23:51:47 - INFO - __main__ - Step 59335: {'lr': 0.0003366089191423789, 'samples': 11392320, 'steps': 59334, 'loss/train': 1.3477146625518799} 08/30/2021 23:51:49 - INFO - __main__ - Step 59336: {'lr': 0.00033660394100540553, 'samples': 11392512, 'steps': 59335, 'loss/train': 1.110459804534912} 08/30/2021 23:51:49 - INFO - __main__ - Step 59337: {'lr': 0.00033659896282940975, 'samples': 11392704, 'steps': 59336, 'loss/train': 1.854459285736084} 08/30/2021 23:51:50 - INFO - __main__ - Step 59338: {'lr': 0.0003365939846143938, 'samples': 11392896, 'steps': 59337, 'loss/train': 1.4341622591018677} 08/30/2021 23:51:50 - INFO - __main__ - Step 59339: {'lr': 0.00033658900636036, 'samples': 11393088, 'steps': 59338, 'loss/train': 0.17963233590126038} 08/30/2021 23:51:50 - INFO - __main__ - Step 59340: {'lr': 0.00033658402806731054, 'samples': 11393280, 'steps': 59339, 'loss/train': 1.1999081373214722} 08/30/2021 23:51:51 - INFO - __main__ - Step 59341: {'lr': 0.00033657904973524754, 'samples': 11393472, 'steps': 59340, 'loss/train': 1.6364575624465942} 08/30/2021 23:51:53 - INFO - __main__ - Step 59342: {'lr': 0.00033657407136417343, 'samples': 11393664, 'steps': 59341, 'loss/train': 1.584562063217163} 08/30/2021 23:51:53 - INFO - __main__ - Step 59343: {'lr': 0.0003365690929540904, 'samples': 11393856, 'steps': 59342, 'loss/train': 1.4495015144348145} 08/30/2021 23:51:54 - INFO - __main__ - Step 59344: {'lr': 0.0003365641145050006, 'samples': 11394048, 'steps': 59343, 'loss/train': 1.253187894821167} 08/30/2021 23:51:54 - INFO - __main__ - Step 59345: {'lr': 0.0003365591360169064, 'samples': 11394240, 'steps': 59344, 'loss/train': 1.6525559425354004} 08/30/2021 23:51:54 - INFO - __main__ - Step 59346: {'lr': 0.00033655415748981, 'samples': 11394432, 'steps': 59345, 'loss/train': 1.1778801679611206} 08/30/2021 23:51:56 - INFO - __main__ - Step 59347: {'lr': 0.00033654917892371363, 'samples': 11394624, 'steps': 59346, 'loss/train': 0.9295195937156677} 08/30/2021 23:51:56 - INFO - __main__ - Step 59348: {'lr': 0.00033654420031861953, 'samples': 11394816, 'steps': 59347, 'loss/train': 1.1585581302642822} 08/30/2021 23:51:57 - INFO - __main__ - Step 59349: {'lr': 0.0003365392216745299, 'samples': 11395008, 'steps': 59348, 'loss/train': 1.3422008752822876} 08/30/2021 23:51:57 - INFO - __main__ - Step 59350: {'lr': 0.0003365342429914471, 'samples': 11395200, 'steps': 59349, 'loss/train': 0.6726939082145691} 08/30/2021 23:51:57 - INFO - __main__ - Step 59351: {'lr': 0.0003365292642693733, 'samples': 11395392, 'steps': 59350, 'loss/train': 0.6640406847000122} 08/30/2021 23:51:59 - INFO - __main__ - Step 59352: {'lr': 0.0003365242855083107, 'samples': 11395584, 'steps': 59351, 'loss/train': 1.1594438552856445} 08/30/2021 23:51:59 - INFO - __main__ - Step 59353: {'lr': 0.00033651930670826157, 'samples': 11395776, 'steps': 59352, 'loss/train': 1.3292087316513062} 08/30/2021 23:52:00 - INFO - __main__ - Step 59354: {'lr': 0.0003365143278692283, 'samples': 11395968, 'steps': 59353, 'loss/train': 1.1059421300888062} 08/30/2021 23:52:00 - INFO - __main__ - Step 59355: {'lr': 0.0003365093489912129, 'samples': 11396160, 'steps': 59354, 'loss/train': 1.8915578126907349} 08/30/2021 23:52:00 - INFO - __main__ - Step 59356: {'lr': 0.00033650437007421775, 'samples': 11396352, 'steps': 59355, 'loss/train': 1.1315854787826538} 08/30/2021 23:52:01 - INFO - __main__ - Step 59357: {'lr': 0.0003364993911182451, 'samples': 11396544, 'steps': 59356, 'loss/train': 1.7106071710586548} 08/30/2021 23:52:02 - INFO - __main__ - Step 59358: {'lr': 0.0003364944121232971, 'samples': 11396736, 'steps': 59357, 'loss/train': 1.3781297206878662} 08/30/2021 23:52:03 - INFO - __main__ - Step 59359: {'lr': 0.0003364894330893761, 'samples': 11396928, 'steps': 59358, 'loss/train': 1.326269268989563} 08/30/2021 23:52:03 - INFO - __main__ - Step 59360: {'lr': 0.0003364844540164843, 'samples': 11397120, 'steps': 59359, 'loss/train': 1.568508267402649} 08/30/2021 23:52:03 - INFO - __main__ - Step 59361: {'lr': 0.00033647947490462386, 'samples': 11397312, 'steps': 59360, 'loss/train': 1.4494833946228027} 08/30/2021 23:52:04 - INFO - __main__ - Step 59362: {'lr': 0.0003364744957537972, 'samples': 11397504, 'steps': 59361, 'loss/train': 1.247589111328125} 08/30/2021 23:52:05 - INFO - __main__ - Step 59363: {'lr': 0.00033646951656400635, 'samples': 11397696, 'steps': 59362, 'loss/train': 1.2490839958190918} 08/30/2021 23:52:06 - INFO - __main__ - Step 59364: {'lr': 0.0003364645373352538, 'samples': 11397888, 'steps': 59363, 'loss/train': 1.6518312692642212} 08/30/2021 23:52:06 - INFO - __main__ - Step 59365: {'lr': 0.00033645955806754156, 'samples': 11398080, 'steps': 59364, 'loss/train': 1.267189621925354} 08/30/2021 23:52:06 - INFO - __main__ - Step 59366: {'lr': 0.00033645457876087205, 'samples': 11398272, 'steps': 59365, 'loss/train': 1.0230413675308228} 08/30/2021 23:52:07 - INFO - __main__ - Step 59367: {'lr': 0.0003364495994152474, 'samples': 11398464, 'steps': 59366, 'loss/train': 1.295203685760498} 08/30/2021 23:52:08 - INFO - __main__ - Step 59368: {'lr': 0.00033644462003066996, 'samples': 11398656, 'steps': 59367, 'loss/train': 0.8491498827934265} 08/30/2021 23:52:09 - INFO - __main__ - Step 59369: {'lr': 0.00033643964060714183, 'samples': 11398848, 'steps': 59368, 'loss/train': 1.7447905540466309} 08/30/2021 23:52:09 - INFO - __main__ - Step 59370: {'lr': 0.00033643466114466537, 'samples': 11399040, 'steps': 59369, 'loss/train': 1.0838088989257812} 08/30/2021 23:52:09 - INFO - __main__ - Step 59371: {'lr': 0.0003364296816432428, 'samples': 11399232, 'steps': 59370, 'loss/train': 1.4862943887710571} 08/30/2021 23:52:10 - INFO - __main__ - Step 59372: {'lr': 0.0003364247021028763, 'samples': 11399424, 'steps': 59371, 'loss/train': 2.0120232105255127} 08/30/2021 23:52:11 - INFO - __main__ - Step 59373: {'lr': 0.0003364197225235682, 'samples': 11399616, 'steps': 59372, 'loss/train': 0.9148479700088501} 08/30/2021 23:52:12 - INFO - __main__ - Step 59374: {'lr': 0.0003364147429053207, 'samples': 11399808, 'steps': 59373, 'loss/train': 0.7984991073608398} 08/30/2021 23:52:12 - INFO - __main__ - Step 59375: {'lr': 0.00033640976324813605, 'samples': 11400000, 'steps': 59374, 'loss/train': 1.5747536420822144} 08/30/2021 23:52:12 - INFO - __main__ - Step 59376: {'lr': 0.00033640478355201646, 'samples': 11400192, 'steps': 59375, 'loss/train': 1.3024396896362305} 08/30/2021 23:52:13 - INFO - __main__ - Step 59377: {'lr': 0.00033639980381696425, 'samples': 11400384, 'steps': 59376, 'loss/train': 0.5121721625328064} 08/30/2021 23:52:14 - INFO - __main__ - Step 59378: {'lr': 0.0003363948240429816, 'samples': 11400576, 'steps': 59377, 'loss/train': 1.3542097806930542} 08/30/2021 23:52:15 - INFO - __main__ - Step 59379: {'lr': 0.0003363898442300708, 'samples': 11400768, 'steps': 59378, 'loss/train': 0.9155076146125793} 08/30/2021 23:52:15 - INFO - __main__ - Step 59380: {'lr': 0.0003363848643782341, 'samples': 11400960, 'steps': 59379, 'loss/train': 1.4796979427337646} 08/30/2021 23:52:16 - INFO - __main__ - Step 59381: {'lr': 0.00033637988448747365, 'samples': 11401152, 'steps': 59380, 'loss/train': 0.8945176601409912} 08/30/2021 23:52:16 - INFO - __main__ - Step 59382: {'lr': 0.00033637490455779175, 'samples': 11401344, 'steps': 59381, 'loss/train': 1.4898449182510376} 08/30/2021 23:52:16 - INFO - __main__ - Step 59383: {'lr': 0.0003363699245891907, 'samples': 11401536, 'steps': 59382, 'loss/train': 1.3867021799087524} 08/30/2021 23:52:17 - INFO - __main__ - Step 59384: {'lr': 0.00033636494458167267, 'samples': 11401728, 'steps': 59383, 'loss/train': 5.8033928871154785} 08/30/2021 23:52:18 - INFO - __main__ - Step 59385: {'lr': 0.00033635996453523987, 'samples': 11401920, 'steps': 59384, 'loss/train': 0.8983581066131592} 08/30/2021 23:52:19 - INFO - __main__ - Step 59386: {'lr': 0.0003363549844498947, 'samples': 11402112, 'steps': 59385, 'loss/train': 1.5056425333023071} 08/30/2021 23:52:19 - INFO - __main__ - Step 59387: {'lr': 0.00033635000432563926, 'samples': 11402304, 'steps': 59386, 'loss/train': 0.9520968198776245} 08/30/2021 23:52:19 - INFO - __main__ - Step 59388: {'lr': 0.0003363450241624759, 'samples': 11402496, 'steps': 59387, 'loss/train': 1.5993014574050903} 08/30/2021 23:52:20 - INFO - __main__ - Step 59389: {'lr': 0.00033634004396040673, 'samples': 11402688, 'steps': 59388, 'loss/train': 0.9830499291419983} 08/30/2021 23:52:21 - INFO - __main__ - Step 59390: {'lr': 0.0003363350637194341, 'samples': 11402880, 'steps': 59389, 'loss/train': 1.2680844068527222} 08/30/2021 23:52:22 - INFO - __main__ - Step 59391: {'lr': 0.0003363300834395602, 'samples': 11403072, 'steps': 59390, 'loss/train': 1.7563400268554688} 08/30/2021 23:52:22 - INFO - __main__ - Step 59392: {'lr': 0.0003363251031207873, 'samples': 11403264, 'steps': 59391, 'loss/train': 1.650937557220459} 08/30/2021 23:52:22 - INFO - __main__ - Step 59393: {'lr': 0.00033632012276311763, 'samples': 11403456, 'steps': 59392, 'loss/train': 1.5559488534927368} 08/30/2021 23:52:23 - INFO - __main__ - Step 59394: {'lr': 0.00033631514236655345, 'samples': 11403648, 'steps': 59393, 'loss/train': 1.7367321252822876} 08/30/2021 23:52:25 - INFO - __main__ - Step 59395: {'lr': 0.00033631016193109704, 'samples': 11403840, 'steps': 59394, 'loss/train': 1.3136630058288574} 08/30/2021 23:52:25 - INFO - __main__ - Step 59396: {'lr': 0.00033630518145675057, 'samples': 11404032, 'steps': 59395, 'loss/train': 1.7318987846374512} 08/30/2021 23:52:26 - INFO - __main__ - Step 59397: {'lr': 0.0003363002009435163, 'samples': 11404224, 'steps': 59396, 'loss/train': 1.2763962745666504} 08/30/2021 23:52:26 - INFO - __main__ - Step 59398: {'lr': 0.00033629522039139656, 'samples': 11404416, 'steps': 59397, 'loss/train': 0.9393520951271057} 08/30/2021 23:52:26 - INFO - __main__ - Step 59399: {'lr': 0.00033629023980039346, 'samples': 11404608, 'steps': 59398, 'loss/train': 0.5364485383033752} 08/30/2021 23:52:28 - INFO - __main__ - Step 59400: {'lr': 0.00033628525917050935, 'samples': 11404800, 'steps': 59399, 'loss/train': 0.8415135741233826} 08/30/2021 23:52:28 - INFO - __main__ - Step 59401: {'lr': 0.0003362802785017464, 'samples': 11404992, 'steps': 59400, 'loss/train': 1.508277416229248} 08/30/2021 23:52:29 - INFO - __main__ - Step 59402: {'lr': 0.00033627529779410695, 'samples': 11405184, 'steps': 59401, 'loss/train': 0.9456004500389099} 08/30/2021 23:52:29 - INFO - __main__ - Step 59403: {'lr': 0.0003362703170475931, 'samples': 11405376, 'steps': 59402, 'loss/train': 1.3428499698638916} 08/30/2021 23:52:29 - INFO - __main__ - Step 59404: {'lr': 0.00033626533626220724, 'samples': 11405568, 'steps': 59403, 'loss/train': 1.3293548822402954} 08/30/2021 23:52:31 - INFO - __main__ - Step 59405: {'lr': 0.0003362603554379515, 'samples': 11405760, 'steps': 59404, 'loss/train': 0.9952874183654785} 08/30/2021 23:52:31 - INFO - __main__ - Step 59406: {'lr': 0.0003362553745748281, 'samples': 11405952, 'steps': 59405, 'loss/train': 1.782294511795044} 08/30/2021 23:52:32 - INFO - __main__ - Step 59407: {'lr': 0.00033625039367283957, 'samples': 11406144, 'steps': 59406, 'loss/train': 1.5301787853240967} 08/30/2021 23:52:32 - INFO - __main__ - Step 59408: {'lr': 0.00033624541273198785, 'samples': 11406336, 'steps': 59407, 'loss/train': 1.4580206871032715} 08/30/2021 23:52:32 - INFO - __main__ - Step 59409: {'lr': 0.0003362404317522752, 'samples': 11406528, 'steps': 59408, 'loss/train': 1.8322279453277588} 08/30/2021 23:52:34 - INFO - __main__ - Step 59410: {'lr': 0.000336235450733704, 'samples': 11406720, 'steps': 59409, 'loss/train': 0.08567579835653305} 08/30/2021 23:52:35 - INFO - __main__ - Step 59411: {'lr': 0.00033623046967627647, 'samples': 11406912, 'steps': 59410, 'loss/train': 0.27010083198547363} 08/30/2021 23:52:35 - INFO - __main__ - Step 59412: {'lr': 0.00033622548857999477, 'samples': 11407104, 'steps': 59411, 'loss/train': 0.9477778673171997} 08/30/2021 23:52:35 - INFO - __main__ - Step 59413: {'lr': 0.00033622050744486117, 'samples': 11407296, 'steps': 59412, 'loss/train': 1.8144454956054688} 08/30/2021 23:52:36 - INFO - __main__ - Step 59414: {'lr': 0.000336215526270878, 'samples': 11407488, 'steps': 59413, 'loss/train': 1.3649078607559204} 08/30/2021 23:52:37 - INFO - __main__ - Step 59415: {'lr': 0.00033621054505804745, 'samples': 11407680, 'steps': 59414, 'loss/train': 0.09282448887825012} 08/30/2021 23:52:38 - INFO - __main__ - Step 59416: {'lr': 0.0003362055638063717, 'samples': 11407872, 'steps': 59415, 'loss/train': 1.3905246257781982} 08/30/2021 23:52:38 - INFO - __main__ - Step 59417: {'lr': 0.00033620058251585314, 'samples': 11408064, 'steps': 59416, 'loss/train': 0.6932212114334106} 08/30/2021 23:52:38 - INFO - __main__ - Step 59418: {'lr': 0.00033619560118649383, 'samples': 11408256, 'steps': 59417, 'loss/train': 1.1944527626037598} 08/30/2021 23:52:39 - INFO - __main__ - Step 59419: {'lr': 0.0003361906198182961, 'samples': 11408448, 'steps': 59418, 'loss/train': 1.8040827512741089} 08/30/2021 23:52:39 - INFO - __main__ - Step 59420: {'lr': 0.0003361856384112623, 'samples': 11408640, 'steps': 59419, 'loss/train': 1.327609896659851} 08/30/2021 23:52:41 - INFO - __main__ - Step 59421: {'lr': 0.00033618065696539457, 'samples': 11408832, 'steps': 59420, 'loss/train': 1.1794135570526123} 08/30/2021 23:52:41 - INFO - __main__ - Step 59422: {'lr': 0.00033617567548069517, 'samples': 11409024, 'steps': 59421, 'loss/train': 0.27892613410949707} 08/30/2021 23:52:41 - INFO - __main__ - Step 59423: {'lr': 0.00033617069395716626, 'samples': 11409216, 'steps': 59422, 'loss/train': 1.4374927282333374} 08/30/2021 23:52:42 - INFO - __main__ - Step 59424: {'lr': 0.0003361657123948103, 'samples': 11409408, 'steps': 59423, 'loss/train': 1.213124394416809} 08/30/2021 23:52:42 - INFO - __main__ - Step 59425: {'lr': 0.00033616073079362923, 'samples': 11409600, 'steps': 59424, 'loss/train': 0.9420284032821655} 08/30/2021 23:52:44 - INFO - __main__ - Step 59426: {'lr': 0.00033615574915362556, 'samples': 11409792, 'steps': 59425, 'loss/train': 2.133023262023926} 08/30/2021 23:52:44 - INFO - __main__ - Step 59427: {'lr': 0.0003361507674748015, 'samples': 11409984, 'steps': 59426, 'loss/train': 1.1065961122512817} 08/30/2021 23:52:45 - INFO - __main__ - Step 59428: {'lr': 0.00033614578575715914, 'samples': 11410176, 'steps': 59427, 'loss/train': 1.06520676612854} 08/30/2021 23:52:45 - INFO - __main__ - Step 59429: {'lr': 0.0003361408040007008, 'samples': 11410368, 'steps': 59428, 'loss/train': 0.032700277864933014} 08/30/2021 23:52:45 - INFO - __main__ - Step 59430: {'lr': 0.00033613582220542884, 'samples': 11410560, 'steps': 59429, 'loss/train': 1.1022206544876099} 08/30/2021 23:52:47 - INFO - __main__ - Step 59431: {'lr': 0.00033613084037134534, 'samples': 11410752, 'steps': 59430, 'loss/train': 1.8937164545059204} 08/30/2021 23:52:48 - INFO - __main__ - Step 59432: {'lr': 0.00033612585849845256, 'samples': 11410944, 'steps': 59431, 'loss/train': 1.244881510734558} 08/30/2021 23:52:48 - INFO - __main__ - Step 59433: {'lr': 0.00033612087658675287, 'samples': 11411136, 'steps': 59432, 'loss/train': 1.126632809638977} 08/30/2021 23:52:48 - INFO - __main__ - Step 59434: {'lr': 0.0003361158946362485, 'samples': 11411328, 'steps': 59433, 'loss/train': 0.6648529767990112} 08/30/2021 23:52:49 - INFO - __main__ - Step 59435: {'lr': 0.00033611091264694156, 'samples': 11411520, 'steps': 59434, 'loss/train': 1.1737480163574219} 08/30/2021 23:52:49 - INFO - __main__ - Step 59436: {'lr': 0.0003361059306188344, 'samples': 11411712, 'steps': 59435, 'loss/train': 0.9358706474304199} 08/30/2021 23:52:51 - INFO - __main__ - Step 59437: {'lr': 0.0003361009485519292, 'samples': 11411904, 'steps': 59436, 'loss/train': 0.14283666014671326} 08/30/2021 23:52:51 - INFO - __main__ - Step 59438: {'lr': 0.0003360959664462282, 'samples': 11412096, 'steps': 59437, 'loss/train': 0.18070244789123535} 08/30/2021 23:52:52 - INFO - __main__ - Step 59439: {'lr': 0.0003360909843017338, 'samples': 11412288, 'steps': 59438, 'loss/train': 0.04775748774409294} 08/30/2021 23:52:52 - INFO - __main__ - Step 59440: {'lr': 0.0003360860021184481, 'samples': 11412480, 'steps': 59439, 'loss/train': 1.5097215175628662} 08/30/2021 23:52:52 - INFO - __main__ - Step 59441: {'lr': 0.0003360810198963733, 'samples': 11412672, 'steps': 59440, 'loss/train': 1.2952772378921509} 08/30/2021 23:52:54 - INFO - __main__ - Step 59442: {'lr': 0.0003360760376355118, 'samples': 11412864, 'steps': 59441, 'loss/train': 1.2062057256698608} 08/30/2021 23:52:54 - INFO - __main__ - Step 59443: {'lr': 0.00033607105533586573, 'samples': 11413056, 'steps': 59442, 'loss/train': 1.3953914642333984} 08/30/2021 23:52:55 - INFO - __main__ - Step 59444: {'lr': 0.0003360660729974374, 'samples': 11413248, 'steps': 59443, 'loss/train': 1.484487533569336} 08/30/2021 23:52:55 - INFO - __main__ - Step 59445: {'lr': 0.00033606109062022906, 'samples': 11413440, 'steps': 59444, 'loss/train': 0.9972631931304932} 08/30/2021 23:52:55 - INFO - __main__ - Step 59446: {'lr': 0.0003360561082042428, 'samples': 11413632, 'steps': 59445, 'loss/train': 1.2883492708206177} 08/30/2021 23:52:56 - INFO - __main__ - Step 59447: {'lr': 0.00033605112574948106, 'samples': 11413824, 'steps': 59446, 'loss/train': 1.44814133644104} 08/30/2021 23:52:58 - INFO - __main__ - Step 59448: {'lr': 0.000336046143255946, 'samples': 11414016, 'steps': 59447, 'loss/train': 1.2546206712722778} 08/30/2021 23:52:58 - INFO - __main__ - Step 59449: {'lr': 0.0003360411607236399, 'samples': 11414208, 'steps': 59448, 'loss/train': 0.024742096662521362} 08/30/2021 23:52:58 - INFO - __main__ - Step 59450: {'lr': 0.0003360361781525649, 'samples': 11414400, 'steps': 59449, 'loss/train': 0.09804750978946686} 08/30/2021 23:52:59 - INFO - __main__ - Step 59451: {'lr': 0.00033603119554272343, 'samples': 11414592, 'steps': 59450, 'loss/train': 0.9889927506446838} 08/30/2021 23:52:59 - INFO - __main__ - Step 59452: {'lr': 0.0003360262128941176, 'samples': 11414784, 'steps': 59451, 'loss/train': 0.8895063400268555} 08/30/2021 23:52:59 - INFO - __main__ - Step 59453: {'lr': 0.00033602123020674965, 'samples': 11414976, 'steps': 59452, 'loss/train': 0.8405062556266785} 08/30/2021 23:53:01 - INFO - __main__ - Step 59454: {'lr': 0.0003360162474806219, 'samples': 11415168, 'steps': 59453, 'loss/train': 1.0882436037063599} 08/30/2021 23:53:02 - INFO - __main__ - Step 59455: {'lr': 0.0003360112647157366, 'samples': 11415360, 'steps': 59454, 'loss/train': 1.3447877168655396} 08/30/2021 23:53:02 - INFO - __main__ - Step 59456: {'lr': 0.0003360062819120958, 'samples': 11415552, 'steps': 59455, 'loss/train': 1.5456767082214355} 08/30/2021 23:53:02 - INFO - __main__ - Step 59457: {'lr': 0.000336001299069702, 'samples': 11415744, 'steps': 59456, 'loss/train': 1.0125421285629272} 08/30/2021 23:53:03 - INFO - __main__ - Step 59458: {'lr': 0.0003359963161885573, 'samples': 11415936, 'steps': 59457, 'loss/train': 1.1881515979766846} 08/30/2021 23:53:04 - INFO - __main__ - Step 59459: {'lr': 0.000335991333268664, 'samples': 11416128, 'steps': 59458, 'loss/train': 1.4432138204574585} 08/30/2021 23:53:05 - INFO - __main__ - Step 59460: {'lr': 0.0003359863503100244, 'samples': 11416320, 'steps': 59459, 'loss/train': 1.9680920839309692} 08/30/2021 23:53:05 - INFO - __main__ - Step 59461: {'lr': 0.0003359813673126406, 'samples': 11416512, 'steps': 59460, 'loss/train': 1.1212599277496338} 08/30/2021 23:53:06 - INFO - __main__ - Step 59462: {'lr': 0.000335976384276515, 'samples': 11416704, 'steps': 59461, 'loss/train': 1.3377097845077515} 08/30/2021 23:53:06 - INFO - __main__ - Step 59463: {'lr': 0.0003359714012016497, 'samples': 11416896, 'steps': 59462, 'loss/train': 1.8361855745315552} 08/30/2021 23:53:07 - INFO - __main__ - Step 59464: {'lr': 0.000335966418088047, 'samples': 11417088, 'steps': 59463, 'loss/train': 1.5688608884811401} 08/30/2021 23:53:08 - INFO - __main__ - Step 59465: {'lr': 0.0003359614349357092, 'samples': 11417280, 'steps': 59464, 'loss/train': 1.2281084060668945} 08/30/2021 23:53:08 - INFO - __main__ - Step 59466: {'lr': 0.00033595645174463843, 'samples': 11417472, 'steps': 59465, 'loss/train': 1.424838900566101} 08/30/2021 23:53:09 - INFO - __main__ - Step 59467: {'lr': 0.0003359514685148371, 'samples': 11417664, 'steps': 59466, 'loss/train': 0.48817774653434753} 08/30/2021 23:53:09 - INFO - __main__ - Step 59468: {'lr': 0.0003359464852463074, 'samples': 11417856, 'steps': 59467, 'loss/train': 1.618391752243042} 08/30/2021 23:53:11 - INFO - __main__ - Step 59469: {'lr': 0.00033594150193905144, 'samples': 11418048, 'steps': 59468, 'loss/train': 1.1780403852462769} 08/30/2021 23:53:11 - INFO - __main__ - Step 59470: {'lr': 0.0003359365185930716, 'samples': 11418240, 'steps': 59469, 'loss/train': 1.3403642177581787} 08/30/2021 23:53:12 - INFO - __main__ - Step 59471: {'lr': 0.00033593153520837006, 'samples': 11418432, 'steps': 59470, 'loss/train': 1.5577113628387451} 08/30/2021 23:53:12 - INFO - __main__ - Step 59472: {'lr': 0.0003359265517849491, 'samples': 11418624, 'steps': 59471, 'loss/train': 1.8197662830352783} 08/30/2021 23:53:12 - INFO - __main__ - Step 59473: {'lr': 0.000335921568322811, 'samples': 11418816, 'steps': 59472, 'loss/train': 1.2587448358535767} 08/30/2021 23:53:13 - INFO - __main__ - Step 59474: {'lr': 0.00033591658482195796, 'samples': 11419008, 'steps': 59473, 'loss/train': 1.377042531967163} 08/30/2021 23:53:14 - INFO - __main__ - Step 59475: {'lr': 0.0003359116012823923, 'samples': 11419200, 'steps': 59474, 'loss/train': 0.890034019947052} 08/30/2021 23:53:15 - INFO - __main__ - Step 59476: {'lr': 0.0003359066177041161, 'samples': 11419392, 'steps': 59475, 'loss/train': 0.7871702313423157} 08/30/2021 23:53:15 - INFO - __main__ - Step 59477: {'lr': 0.0003359016340871317, 'samples': 11419584, 'steps': 59476, 'loss/train': 1.1494500637054443} 08/30/2021 23:53:15 - INFO - __main__ - Step 59478: {'lr': 0.0003358966504314414, 'samples': 11419776, 'steps': 59477, 'loss/train': 1.4305261373519897} 08/30/2021 23:53:16 - INFO - __main__ - Step 59479: {'lr': 0.00033589166673704735, 'samples': 11419968, 'steps': 59478, 'loss/train': 1.5579413175582886} 08/30/2021 23:53:17 - INFO - __main__ - Step 59480: {'lr': 0.0003358866830039519, 'samples': 11420160, 'steps': 59479, 'loss/train': 0.15474049746990204} 08/30/2021 23:53:18 - INFO - __main__ - Step 59481: {'lr': 0.0003358816992321572, 'samples': 11420352, 'steps': 59480, 'loss/train': 1.7838441133499146} 08/30/2021 23:53:18 - INFO - __main__ - Step 59482: {'lr': 0.0003358767154216655, 'samples': 11420544, 'steps': 59481, 'loss/train': 1.1977540254592896} 08/30/2021 23:53:18 - INFO - __main__ - Step 59483: {'lr': 0.00033587173157247915, 'samples': 11420736, 'steps': 59482, 'loss/train': 0.8217096328735352} 08/30/2021 23:53:19 - INFO - __main__ - Step 59484: {'lr': 0.00033586674768460025, 'samples': 11420928, 'steps': 59483, 'loss/train': 0.8427931666374207} 08/30/2021 23:53:20 - INFO - __main__ - Step 59485: {'lr': 0.0003358617637580311, 'samples': 11421120, 'steps': 59484, 'loss/train': 1.143505573272705} 08/30/2021 23:53:21 - INFO - __main__ - Step 59486: {'lr': 0.00033585677979277407, 'samples': 11421312, 'steps': 59485, 'loss/train': 1.8316614627838135} 08/30/2021 23:53:21 - INFO - __main__ - Step 59487: {'lr': 0.00033585179578883123, 'samples': 11421504, 'steps': 59486, 'loss/train': 1.2786799669265747} 08/30/2021 23:53:21 - INFO - __main__ - Step 59488: {'lr': 0.00033584681174620497, 'samples': 11421696, 'steps': 59487, 'loss/train': 1.5275200605392456} 08/30/2021 23:53:22 - INFO - __main__ - Step 59489: {'lr': 0.00033584182766489736, 'samples': 11421888, 'steps': 59488, 'loss/train': 1.025773286819458} 08/30/2021 23:53:22 - INFO - __main__ - Step 59490: {'lr': 0.0003358368435449108, 'samples': 11422080, 'steps': 59489, 'loss/train': 1.2890390157699585} 08/30/2021 23:53:24 - INFO - __main__ - Step 59491: {'lr': 0.0003358318593862474, 'samples': 11422272, 'steps': 59490, 'loss/train': 1.0115821361541748} 08/30/2021 23:53:24 - INFO - __main__ - Step 59492: {'lr': 0.0003358268751889096, 'samples': 11422464, 'steps': 59491, 'loss/train': 1.2791686058044434} 08/30/2021 23:53:24 - INFO - __main__ - Step 59493: {'lr': 0.0003358218909528995, 'samples': 11422656, 'steps': 59492, 'loss/train': 1.580369234085083} 08/30/2021 23:53:25 - INFO - __main__ - Step 59494: {'lr': 0.00033581690667821933, 'samples': 11422848, 'steps': 59493, 'loss/train': 0.8855935335159302} 08/30/2021 23:53:25 - INFO - __main__ - Step 59495: {'lr': 0.00033581192236487153, 'samples': 11423040, 'steps': 59494, 'loss/train': 1.394609808921814} 08/30/2021 23:53:27 - INFO - __main__ - Step 59496: {'lr': 0.00033580693801285805, 'samples': 11423232, 'steps': 59495, 'loss/train': 1.3154865503311157} 08/30/2021 23:53:27 - INFO - __main__ - Step 59497: {'lr': 0.0003358019536221814, 'samples': 11423424, 'steps': 59496, 'loss/train': 1.1394550800323486} 08/30/2021 23:53:27 - INFO - __main__ - Step 59498: {'lr': 0.00033579696919284357, 'samples': 11423616, 'steps': 59497, 'loss/train': 1.101121425628662} 08/30/2021 23:53:28 - INFO - __main__ - Step 59499: {'lr': 0.00033579198472484707, 'samples': 11423808, 'steps': 59498, 'loss/train': 0.9729105830192566} 08/30/2021 23:53:28 - INFO - __main__ - Step 59500: {'lr': 0.000335787000218194, 'samples': 11424000, 'steps': 59499, 'loss/train': 0.8507187962532043} 08/30/2021 23:53:30 - INFO - __main__ - Step 59501: {'lr': 0.0003357820156728866, 'samples': 11424192, 'steps': 59500, 'loss/train': 1.3423972129821777} 08/30/2021 23:53:30 - INFO - __main__ - Step 59502: {'lr': 0.0003357770310889272, 'samples': 11424384, 'steps': 59501, 'loss/train': 1.171541452407837} 08/30/2021 23:53:30 - INFO - __main__ - Step 59503: {'lr': 0.0003357720464663179, 'samples': 11424576, 'steps': 59502, 'loss/train': 1.242734432220459} 08/30/2021 23:53:31 - INFO - __main__ - Step 59504: {'lr': 0.0003357670618050611, 'samples': 11424768, 'steps': 59503, 'loss/train': 1.0610122680664062} 08/30/2021 23:53:31 - INFO - __main__ - Step 59505: {'lr': 0.000335762077105159, 'samples': 11424960, 'steps': 59504, 'loss/train': 1.6891008615493774} 08/30/2021 23:53:33 - INFO - __main__ - Step 59506: {'lr': 0.0003357570923666138, 'samples': 11425152, 'steps': 59505, 'loss/train': 1.1201844215393066} 08/30/2021 23:53:34 - INFO - __main__ - Step 59507: {'lr': 0.0003357521075894278, 'samples': 11425344, 'steps': 59506, 'loss/train': 0.989077627658844} 08/30/2021 23:53:34 - INFO - __main__ - Step 59508: {'lr': 0.00033574712277360325, 'samples': 11425536, 'steps': 59507, 'loss/train': 1.706749439239502} 08/30/2021 23:53:34 - INFO - __main__ - Step 59509: {'lr': 0.00033574213791914235, 'samples': 11425728, 'steps': 59508, 'loss/train': 1.0681970119476318} 08/30/2021 23:53:35 - INFO - __main__ - Step 59510: {'lr': 0.00033573715302604736, 'samples': 11425920, 'steps': 59509, 'loss/train': 1.2094299793243408} 08/30/2021 23:53:35 - INFO - __main__ - Step 59511: {'lr': 0.0003357321680943205, 'samples': 11426112, 'steps': 59510, 'loss/train': 1.408000111579895} 08/30/2021 23:53:37 - INFO - __main__ - Step 59512: {'lr': 0.00033572718312396404, 'samples': 11426304, 'steps': 59511, 'loss/train': 1.633359670639038} 08/30/2021 23:53:38 - INFO - __main__ - Step 59513: {'lr': 0.0003357221981149803, 'samples': 11426496, 'steps': 59512, 'loss/train': 1.8050627708435059} 08/30/2021 23:53:38 - INFO - __main__ - Step 59514: {'lr': 0.0003357172130673714, 'samples': 11426688, 'steps': 59513, 'loss/train': 0.9116045236587524} 08/30/2021 23:53:39 - INFO - __main__ - Step 59515: {'lr': 0.00033571222798113977, 'samples': 11426880, 'steps': 59514, 'loss/train': 1.1150002479553223} 08/30/2021 23:53:39 - INFO - __main__ - Step 59516: {'lr': 0.0003357072428562874, 'samples': 11427072, 'steps': 59515, 'loss/train': 1.2428091764450073} 08/30/2021 23:53:39 - INFO - __main__ - Step 59517: {'lr': 0.0003357022576928167, 'samples': 11427264, 'steps': 59516, 'loss/train': 1.238661289215088} 08/30/2021 23:53:40 - INFO - __main__ - Step 59518: {'lr': 0.0003356972724907299, 'samples': 11427456, 'steps': 59517, 'loss/train': 1.9126455783843994} 08/30/2021 23:53:41 - INFO - __main__ - Step 59519: {'lr': 0.0003356922872500292, 'samples': 11427648, 'steps': 59518, 'loss/train': 2.0081751346588135} 08/30/2021 23:53:42 - INFO - __main__ - Step 59520: {'lr': 0.0003356873019707169, 'samples': 11427840, 'steps': 59519, 'loss/train': 1.8880316019058228} 08/30/2021 23:53:42 - INFO - __main__ - Step 59521: {'lr': 0.0003356823166527952, 'samples': 11428032, 'steps': 59520, 'loss/train': 1.7752128839492798} 08/30/2021 23:53:42 - INFO - __main__ - Step 59522: {'lr': 0.00033567733129626645, 'samples': 11428224, 'steps': 59521, 'loss/train': 0.9479182362556458} 08/30/2021 23:53:43 - INFO - __main__ - Step 59523: {'lr': 0.00033567234590113274, 'samples': 11428416, 'steps': 59522, 'loss/train': 1.2158397436141968} 08/30/2021 23:53:45 - INFO - __main__ - Step 59524: {'lr': 0.00033566736046739643, 'samples': 11428608, 'steps': 59523, 'loss/train': 1.3037676811218262} 08/30/2021 23:53:45 - INFO - __main__ - Step 59525: {'lr': 0.0003356623749950597, 'samples': 11428800, 'steps': 59524, 'loss/train': 1.5904158353805542} 08/30/2021 23:53:46 - INFO - __main__ - Step 59526: {'lr': 0.0003356573894841248, 'samples': 11428992, 'steps': 59525, 'loss/train': 0.08511671423912048} 08/30/2021 23:53:46 - INFO - __main__ - Step 59527: {'lr': 0.0003356524039345941, 'samples': 11429184, 'steps': 59526, 'loss/train': 1.3012559413909912} 08/30/2021 23:53:46 - INFO - __main__ - Step 59528: {'lr': 0.00033564741834646967, 'samples': 11429376, 'steps': 59527, 'loss/train': 1.6012877225875854} 08/30/2021 23:53:48 - INFO - __main__ - Step 59529: {'lr': 0.0003356424327197539, 'samples': 11429568, 'steps': 59528, 'loss/train': 1.9932719469070435} 08/30/2021 23:53:48 - INFO - __main__ - Step 59530: {'lr': 0.00033563744705444886, 'samples': 11429760, 'steps': 59529, 'loss/train': 2.1074087619781494} 08/30/2021 23:53:48 - INFO - __main__ - Step 59531: {'lr': 0.000335632461350557, 'samples': 11429952, 'steps': 59530, 'loss/train': 1.8902236223220825} 08/30/2021 23:53:49 - INFO - __main__ - Step 59532: {'lr': 0.00033562747560808044, 'samples': 11430144, 'steps': 59531, 'loss/train': 1.0934573411941528} 08/30/2021 23:53:49 - INFO - __main__ - Step 59533: {'lr': 0.00033562248982702144, 'samples': 11430336, 'steps': 59532, 'loss/train': 1.6786918640136719} 08/30/2021 23:53:51 - INFO - __main__ - Step 59534: {'lr': 0.0003356175040073823, 'samples': 11430528, 'steps': 59533, 'loss/train': 1.8935232162475586} 08/30/2021 23:53:51 - INFO - __main__ - Step 59535: {'lr': 0.0003356125181491653, 'samples': 11430720, 'steps': 59534, 'loss/train': 5.017116546630859} 08/30/2021 23:53:51 - INFO - __main__ - Step 59536: {'lr': 0.0003356075322523725, 'samples': 11430912, 'steps': 59535, 'loss/train': 1.4133442640304565} 08/30/2021 23:53:52 - INFO - __main__ - Step 59537: {'lr': 0.00033560254631700634, 'samples': 11431104, 'steps': 59536, 'loss/train': 1.377843976020813} 08/30/2021 23:53:52 - INFO - __main__ - Step 59538: {'lr': 0.0003355975603430689, 'samples': 11431296, 'steps': 59537, 'loss/train': 1.8543263673782349} 08/30/2021 23:53:52 - INFO - __main__ - Step 59539: {'lr': 0.0003355925743305626, 'samples': 11431488, 'steps': 59538, 'loss/train': 1.44297194480896} 08/30/2021 23:53:54 - INFO - __main__ - Step 59540: {'lr': 0.0003355875882794896, 'samples': 11431680, 'steps': 59539, 'loss/train': 1.0738028287887573} 08/30/2021 23:53:54 - INFO - __main__ - Step 59541: {'lr': 0.00033558260218985214, 'samples': 11431872, 'steps': 59540, 'loss/train': 1.1790761947631836} 08/30/2021 23:53:55 - INFO - __main__ - Step 59542: {'lr': 0.00033557761606165253, 'samples': 11432064, 'steps': 59541, 'loss/train': 1.3438873291015625} 08/30/2021 23:53:55 - INFO - __main__ - Step 59543: {'lr': 0.00033557262989489294, 'samples': 11432256, 'steps': 59542, 'loss/train': 1.1743943691253662} 08/30/2021 23:53:55 - INFO - __main__ - Step 59544: {'lr': 0.0003355676436895756, 'samples': 11432448, 'steps': 59543, 'loss/train': 1.444443702697754} 08/30/2021 23:53:57 - INFO - __main__ - Step 59545: {'lr': 0.0003355626574457029, 'samples': 11432640, 'steps': 59544, 'loss/train': 1.572969675064087} 08/30/2021 23:53:57 - INFO - __main__ - Step 59546: {'lr': 0.00033555767116327686, 'samples': 11432832, 'steps': 59545, 'loss/train': 1.5157380104064941} 08/30/2021 23:53:58 - INFO - __main__ - Step 59547: {'lr': 0.00033555268484229987, 'samples': 11433024, 'steps': 59546, 'loss/train': 1.563647747039795} 08/30/2021 23:53:58 - INFO - __main__ - Step 59548: {'lr': 0.0003355476984827743, 'samples': 11433216, 'steps': 59547, 'loss/train': 1.581427812576294} 08/30/2021 23:53:58 - INFO - __main__ - Step 59549: {'lr': 0.0003355427120847021, 'samples': 11433408, 'steps': 59548, 'loss/train': 1.9217238426208496} 08/30/2021 23:54:00 - INFO - __main__ - Step 59550: {'lr': 0.0003355377256480858, 'samples': 11433600, 'steps': 59549, 'loss/train': 1.5115524530410767} 08/30/2021 23:54:00 - INFO - __main__ - Step 59551: {'lr': 0.00033553273917292744, 'samples': 11433792, 'steps': 59550, 'loss/train': 1.2947574853897095} 08/30/2021 23:54:01 - INFO - __main__ - Step 59552: {'lr': 0.0003355277526592293, 'samples': 11433984, 'steps': 59551, 'loss/train': 1.548445224761963} 08/30/2021 23:54:01 - INFO - __main__ - Step 59553: {'lr': 0.00033552276610699375, 'samples': 11434176, 'steps': 59552, 'loss/train': 1.0060101747512817} 08/30/2021 23:54:01 - INFO - __main__ - Step 59554: {'lr': 0.00033551777951622297, 'samples': 11434368, 'steps': 59553, 'loss/train': 1.2337366342544556} 08/30/2021 23:54:03 - INFO - __main__ - Step 59555: {'lr': 0.0003355127928869192, 'samples': 11434560, 'steps': 59554, 'loss/train': 1.2919800281524658} 08/30/2021 23:54:03 - INFO - __main__ - Step 59556: {'lr': 0.0003355078062190847, 'samples': 11434752, 'steps': 59555, 'loss/train': 1.3907957077026367} 08/30/2021 23:54:04 - INFO - __main__ - Step 59557: {'lr': 0.00033550281951272163, 'samples': 11434944, 'steps': 59556, 'loss/train': 0.7404875755310059} 08/30/2021 23:54:04 - INFO - __main__ - Step 59558: {'lr': 0.0003354978327678323, 'samples': 11435136, 'steps': 59557, 'loss/train': 1.3297829627990723} 08/30/2021 23:54:04 - INFO - __main__ - Step 59559: {'lr': 0.00033549284598441897, 'samples': 11435328, 'steps': 59558, 'loss/train': 1.1501740217208862} 08/30/2021 23:54:06 - INFO - __main__ - Step 59560: {'lr': 0.0003354878591624839, 'samples': 11435520, 'steps': 59559, 'loss/train': 1.3025771379470825} 08/30/2021 23:54:06 - INFO - __main__ - Step 59561: {'lr': 0.0003354828723020294, 'samples': 11435712, 'steps': 59560, 'loss/train': 1.3005484342575073} 08/30/2021 23:54:07 - INFO - __main__ - Step 59562: {'lr': 0.0003354778854030576, 'samples': 11435904, 'steps': 59561, 'loss/train': 1.8889622688293457} 08/30/2021 23:54:07 - INFO - __main__ - Step 59563: {'lr': 0.0003354728984655708, 'samples': 11436096, 'steps': 59562, 'loss/train': 0.100043386220932} 08/30/2021 23:54:08 - INFO - __main__ - Step 59564: {'lr': 0.0003354679114895711, 'samples': 11436288, 'steps': 59563, 'loss/train': 1.8457481861114502} 08/30/2021 23:54:10 - INFO - __main__ - Step 59565: {'lr': 0.000335462924475061, 'samples': 11436480, 'steps': 59564, 'loss/train': 1.0684540271759033} 08/30/2021 23:54:11 - INFO - __main__ - Step 59566: {'lr': 0.00033545793742204255, 'samples': 11436672, 'steps': 59565, 'loss/train': 1.7257028818130493} 08/30/2021 23:54:11 - INFO - __main__ - Step 59567: {'lr': 0.00033545295033051814, 'samples': 11436864, 'steps': 59566, 'loss/train': 2.5105414390563965} 08/30/2021 23:54:11 - INFO - __main__ - Step 59568: {'lr': 0.00033544796320048996, 'samples': 11437056, 'steps': 59567, 'loss/train': 0.9362022280693054} 08/30/2021 23:54:12 - INFO - __main__ - Step 59569: {'lr': 0.0003354429760319602, 'samples': 11437248, 'steps': 59568, 'loss/train': 1.3529255390167236} 08/30/2021 23:54:12 - INFO - __main__ - Step 59570: {'lr': 0.00033543798882493123, 'samples': 11437440, 'steps': 59569, 'loss/train': 0.2671198844909668} 08/30/2021 23:54:13 - INFO - __main__ - Step 59571: {'lr': 0.0003354330015794051, 'samples': 11437632, 'steps': 59570, 'loss/train': 0.12280721217393875} 08/30/2021 23:54:14 - INFO - __main__ - Step 59572: {'lr': 0.00033542801429538424, 'samples': 11437824, 'steps': 59571, 'loss/train': 1.2619775533676147} 08/30/2021 23:54:14 - INFO - __main__ - Step 59573: {'lr': 0.0003354230269728709, 'samples': 11438016, 'steps': 59572, 'loss/train': 0.9547221660614014} 08/30/2021 23:54:15 - INFO - __main__ - Step 59574: {'lr': 0.0003354180396118671, 'samples': 11438208, 'steps': 59573, 'loss/train': 1.591331958770752} 08/30/2021 23:54:15 - INFO - __main__ - Step 59575: {'lr': 0.0003354130522123754, 'samples': 11438400, 'steps': 59574, 'loss/train': 0.8355203866958618} 08/30/2021 23:54:16 - INFO - __main__ - Step 59576: {'lr': 0.0003354080647743978, 'samples': 11438592, 'steps': 59575, 'loss/train': 1.5975719690322876} 08/30/2021 23:54:17 - INFO - __main__ - Step 59577: {'lr': 0.0003354030772979367, 'samples': 11438784, 'steps': 59576, 'loss/train': 0.4746231734752655} 08/30/2021 23:54:17 - INFO - __main__ - Step 59578: {'lr': 0.00033539808978299423, 'samples': 11438976, 'steps': 59577, 'loss/train': 1.2841274738311768} 08/30/2021 23:54:18 - INFO - __main__ - Step 59579: {'lr': 0.0003353931022295728, 'samples': 11439168, 'steps': 59578, 'loss/train': 1.2729490995407104} 08/30/2021 23:54:18 - INFO - __main__ - Step 59580: {'lr': 0.0003353881146376745, 'samples': 11439360, 'steps': 59579, 'loss/train': 1.0510896444320679} 08/30/2021 23:54:19 - INFO - __main__ - Step 59581: {'lr': 0.0003353831270073016, 'samples': 11439552, 'steps': 59580, 'loss/train': 0.9666589498519897} 08/30/2021 23:54:20 - INFO - __main__ - Step 59582: {'lr': 0.0003353781393384564, 'samples': 11439744, 'steps': 59581, 'loss/train': 1.0285776853561401} 08/30/2021 23:54:20 - INFO - __main__ - Step 59583: {'lr': 0.0003353731516311411, 'samples': 11439936, 'steps': 59582, 'loss/train': 1.6774648427963257} 08/30/2021 23:54:20 - INFO - __main__ - Step 59584: {'lr': 0.00033536816388535814, 'samples': 11440128, 'steps': 59583, 'loss/train': 1.4264315366744995} 08/30/2021 23:54:21 - INFO - __main__ - Step 59585: {'lr': 0.0003353631761011094, 'samples': 11440320, 'steps': 59584, 'loss/train': 1.6628700494766235} 08/30/2021 23:54:22 - INFO - __main__ - Step 59586: {'lr': 0.00033535818827839744, 'samples': 11440512, 'steps': 59585, 'loss/train': 1.84689462184906} 08/30/2021 23:54:23 - INFO - __main__ - Step 59587: {'lr': 0.0003353532004172244, 'samples': 11440704, 'steps': 59586, 'loss/train': 2.0278661251068115} 08/30/2021 23:54:23 - INFO - __main__ - Step 59588: {'lr': 0.00033534821251759246, 'samples': 11440896, 'steps': 59587, 'loss/train': 1.2155430316925049} 08/30/2021 23:54:24 - INFO - __main__ - Step 59589: {'lr': 0.00033534322457950396, 'samples': 11441088, 'steps': 59588, 'loss/train': 1.6607884168624878} 08/30/2021 23:54:24 - INFO - __main__ - Step 59590: {'lr': 0.00033533823660296115, 'samples': 11441280, 'steps': 59589, 'loss/train': 2.0612988471984863} 08/30/2021 23:54:26 - INFO - __main__ - Step 59591: {'lr': 0.00033533324858796623, 'samples': 11441472, 'steps': 59590, 'loss/train': 1.382971167564392} 08/30/2021 23:54:26 - INFO - __main__ - Step 59592: {'lr': 0.00033532826053452145, 'samples': 11441664, 'steps': 59591, 'loss/train': 0.9431319236755371} 08/30/2021 23:54:26 - INFO - __main__ - Step 59593: {'lr': 0.00033532327244262906, 'samples': 11441856, 'steps': 59592, 'loss/train': 0.8664615750312805} 08/30/2021 23:54:27 - INFO - __main__ - Step 59594: {'lr': 0.0003353182843122913, 'samples': 11442048, 'steps': 59593, 'loss/train': 1.3683347702026367} 08/30/2021 23:54:27 - INFO - __main__ - Step 59595: {'lr': 0.0003353132961435105, 'samples': 11442240, 'steps': 59594, 'loss/train': 2.2648630142211914} 08/30/2021 23:54:28 - INFO - __main__ - Step 59596: {'lr': 0.00033530830793628886, 'samples': 11442432, 'steps': 59595, 'loss/train': 1.2228997945785522} 08/30/2021 23:54:29 - INFO - __main__ - Step 59597: {'lr': 0.00033530331969062853, 'samples': 11442624, 'steps': 59596, 'loss/train': 0.13200846314430237} 08/30/2021 23:54:30 - INFO - __main__ - Step 59598: {'lr': 0.00033529833140653187, 'samples': 11442816, 'steps': 59597, 'loss/train': 0.8539416193962097} 08/30/2021 23:54:30 - INFO - __main__ - Step 59599: {'lr': 0.0003352933430840011, 'samples': 11443008, 'steps': 59598, 'loss/train': 1.2471369504928589} 08/30/2021 23:54:30 - INFO - __main__ - Step 59600: {'lr': 0.0003352883547230385, 'samples': 11443200, 'steps': 59599, 'loss/train': 1.1926660537719727} 08/30/2021 23:54:31 - INFO - __main__ - Step 59601: {'lr': 0.00033528336632364624, 'samples': 11443392, 'steps': 59600, 'loss/train': 1.6726816892623901} 08/30/2021 23:54:32 - INFO - __main__ - Step 59602: {'lr': 0.00033527837788582663, 'samples': 11443584, 'steps': 59601, 'loss/train': 2.3026862144470215} 08/30/2021 23:54:33 - INFO - __main__ - Step 59603: {'lr': 0.00033527338940958197, 'samples': 11443776, 'steps': 59602, 'loss/train': 1.251391887664795} 08/30/2021 23:54:33 - INFO - __main__ - Step 59604: {'lr': 0.00033526840089491433, 'samples': 11443968, 'steps': 59603, 'loss/train': 1.8059701919555664} 08/30/2021 23:54:34 - INFO - __main__ - Step 59605: {'lr': 0.00033526341234182613, 'samples': 11444160, 'steps': 59604, 'loss/train': 1.0970380306243896} 08/30/2021 23:54:34 - INFO - __main__ - Step 59606: {'lr': 0.00033525842375031946, 'samples': 11444352, 'steps': 59605, 'loss/train': 1.2555947303771973} 08/30/2021 23:54:35 - INFO - __main__ - Step 59607: {'lr': 0.00033525343512039673, 'samples': 11444544, 'steps': 59606, 'loss/train': 1.5133765935897827} 08/30/2021 23:54:36 - INFO - __main__ - Step 59608: {'lr': 0.0003352484464520601, 'samples': 11444736, 'steps': 59607, 'loss/train': 1.4554907083511353} 08/30/2021 23:54:36 - INFO - __main__ - Step 59609: {'lr': 0.0003352434577453119, 'samples': 11444928, 'steps': 59608, 'loss/train': 1.9755858182907104} 08/30/2021 23:54:37 - INFO - __main__ - Step 59610: {'lr': 0.00033523846900015427, 'samples': 11445120, 'steps': 59609, 'loss/train': 1.738843321800232} 08/30/2021 23:54:37 - INFO - __main__ - Step 59611: {'lr': 0.00033523348021658947, 'samples': 11445312, 'steps': 59610, 'loss/train': 0.053249672055244446} 08/30/2021 23:54:39 - INFO - __main__ - Step 59612: {'lr': 0.00033522849139461973, 'samples': 11445504, 'steps': 59611, 'loss/train': 1.449386477470398} 08/30/2021 23:54:39 - INFO - __main__ - Step 59613: {'lr': 0.0003352235025342475, 'samples': 11445696, 'steps': 59612, 'loss/train': 0.05001894012093544} 08/30/2021 23:54:39 - INFO - __main__ - Step 59614: {'lr': 0.00033521851363547473, 'samples': 11445888, 'steps': 59613, 'loss/train': 1.0461491346359253} 08/30/2021 23:54:40 - INFO - __main__ - Step 59615: {'lr': 0.0003352135246983039, 'samples': 11446080, 'steps': 59614, 'loss/train': 1.3499770164489746} 08/30/2021 23:54:40 - INFO - __main__ - Step 59616: {'lr': 0.0003352085357227372, 'samples': 11446272, 'steps': 59615, 'loss/train': 1.6037282943725586} 08/30/2021 23:54:42 - INFO - __main__ - Step 59617: {'lr': 0.00033520354670877673, 'samples': 11446464, 'steps': 59616, 'loss/train': 0.32540133595466614} 08/30/2021 23:54:43 - INFO - __main__ - Step 59618: {'lr': 0.00033519855765642493, 'samples': 11446656, 'steps': 59617, 'loss/train': 1.161939263343811} 08/30/2021 23:54:43 - INFO - __main__ - Step 59619: {'lr': 0.00033519356856568397, 'samples': 11446848, 'steps': 59618, 'loss/train': 1.3406963348388672} 08/30/2021 23:54:43 - INFO - __main__ - Step 59620: {'lr': 0.00033518857943655607, 'samples': 11447040, 'steps': 59619, 'loss/train': 1.1450269222259521} 08/30/2021 23:54:44 - INFO - __main__ - Step 59621: {'lr': 0.00033518359026904357, 'samples': 11447232, 'steps': 59620, 'loss/train': 1.5163629055023193} 08/30/2021 23:54:45 - INFO - __main__ - Step 59622: {'lr': 0.00033517860106314863, 'samples': 11447424, 'steps': 59621, 'loss/train': 1.7235796451568604} 08/30/2021 23:54:46 - INFO - __main__ - Step 59623: {'lr': 0.00033517361181887353, 'samples': 11447616, 'steps': 59622, 'loss/train': 0.22339722514152527} 08/30/2021 23:54:46 - INFO - __main__ - Step 59624: {'lr': 0.0003351686225362205, 'samples': 11447808, 'steps': 59623, 'loss/train': 2.0765442848205566} 08/30/2021 23:54:46 - INFO - __main__ - Step 59625: {'lr': 0.00033516363321519185, 'samples': 11448000, 'steps': 59624, 'loss/train': 1.6375408172607422} 08/30/2021 23:54:47 - INFO - __main__ - Step 59626: {'lr': 0.0003351586438557897, 'samples': 11448192, 'steps': 59625, 'loss/train': 1.228614330291748} 08/30/2021 23:54:47 - INFO - __main__ - Step 59627: {'lr': 0.00033515365445801635, 'samples': 11448384, 'steps': 59626, 'loss/train': 1.0468555688858032} 08/30/2021 23:54:49 - INFO - __main__ - Step 59628: {'lr': 0.00033514866502187417, 'samples': 11448576, 'steps': 59627, 'loss/train': 1.2167309522628784} 08/30/2021 23:54:49 - INFO - __main__ - Step 59629: {'lr': 0.0003351436755473654, 'samples': 11448768, 'steps': 59628, 'loss/train': 1.053054690361023} 08/30/2021 23:54:50 - INFO - __main__ - Step 59630: {'lr': 0.00033513868603449203, 'samples': 11448960, 'steps': 59629, 'loss/train': 1.5874356031417847} 08/30/2021 23:54:50 - INFO - __main__ - Step 59631: {'lr': 0.00033513369648325653, 'samples': 11449152, 'steps': 59630, 'loss/train': 0.7195480465888977} 08/30/2021 23:54:50 - INFO - __main__ - Step 59632: {'lr': 0.00033512870689366114, 'samples': 11449344, 'steps': 59631, 'loss/train': 1.3263505697250366} 08/30/2021 23:54:52 - INFO - __main__ - Step 59633: {'lr': 0.0003351237172657081, 'samples': 11449536, 'steps': 59632, 'loss/train': 1.3192288875579834} 08/30/2021 23:54:52 - INFO - __main__ - Step 59634: {'lr': 0.00033511872759939954, 'samples': 11449728, 'steps': 59633, 'loss/train': 1.0848983526229858} 08/30/2021 23:54:52 - INFO - __main__ - Step 59635: {'lr': 0.0003351137378947378, 'samples': 11449920, 'steps': 59634, 'loss/train': 2.0865628719329834} 08/30/2021 23:54:53 - INFO - __main__ - Step 59636: {'lr': 0.00033510874815172523, 'samples': 11450112, 'steps': 59635, 'loss/train': 1.2444217205047607} 08/30/2021 23:54:53 - INFO - __main__ - Step 59637: {'lr': 0.00033510375837036386, 'samples': 11450304, 'steps': 59636, 'loss/train': 1.2617526054382324} 08/30/2021 23:54:55 - INFO - __main__ - Step 59638: {'lr': 0.0003350987685506561, 'samples': 11450496, 'steps': 59637, 'loss/train': 1.1474472284317017} 08/30/2021 23:54:55 - INFO - __main__ - Step 59639: {'lr': 0.0003350937786926041, 'samples': 11450688, 'steps': 59638, 'loss/train': 0.5737676024436951} 08/30/2021 23:54:55 - INFO - __main__ - Step 59640: {'lr': 0.0003350887887962102, 'samples': 11450880, 'steps': 59639, 'loss/train': 1.4543455839157104} 08/30/2021 23:54:56 - INFO - __main__ - Step 59641: {'lr': 0.00033508379886147655, 'samples': 11451072, 'steps': 59640, 'loss/train': 1.3561283349990845} 08/30/2021 23:54:56 - INFO - __main__ - Step 59642: {'lr': 0.00033507880888840547, 'samples': 11451264, 'steps': 59641, 'loss/train': 1.263848066329956} 08/30/2021 23:54:58 - INFO - __main__ - Step 59643: {'lr': 0.00033507381887699927, 'samples': 11451456, 'steps': 59642, 'loss/train': 1.8754993677139282} 08/30/2021 23:54:58 - INFO - __main__ - Step 59644: {'lr': 0.0003350688288272601, 'samples': 11451648, 'steps': 59643, 'loss/train': 2.172424077987671} 08/30/2021 23:54:59 - INFO - __main__ - Step 59645: {'lr': 0.00033506383873919016, 'samples': 11451840, 'steps': 59644, 'loss/train': 2.2921624183654785} 08/30/2021 23:54:59 - INFO - __main__ - Step 59646: {'lr': 0.0003350588486127918, 'samples': 11452032, 'steps': 59645, 'loss/train': 1.8611721992492676} 08/30/2021 23:54:59 - INFO - __main__ - Step 59647: {'lr': 0.0003350538584480672, 'samples': 11452224, 'steps': 59646, 'loss/train': 1.0862886905670166} 08/30/2021 23:55:01 - INFO - __main__ - Step 59648: {'lr': 0.0003350488682450187, 'samples': 11452416, 'steps': 59647, 'loss/train': 1.4954073429107666} 08/30/2021 23:55:01 - INFO - __main__ - Step 59649: {'lr': 0.00033504387800364856, 'samples': 11452608, 'steps': 59648, 'loss/train': 1.7261111736297607} 08/30/2021 23:55:02 - INFO - __main__ - Step 59650: {'lr': 0.00033503888772395886, 'samples': 11452800, 'steps': 59649, 'loss/train': 1.1935325860977173} 08/30/2021 23:55:02 - INFO - __main__ - Step 59651: {'lr': 0.0003350338974059519, 'samples': 11452992, 'steps': 59650, 'loss/train': 1.6750245094299316} 08/30/2021 23:55:02 - INFO - __main__ - Step 59652: {'lr': 0.0003350289070496301, 'samples': 11453184, 'steps': 59651, 'loss/train': 1.7220368385314941} 08/30/2021 23:55:04 - INFO - __main__ - Step 59653: {'lr': 0.0003350239166549955, 'samples': 11453376, 'steps': 59652, 'loss/train': 1.2379019260406494} 08/30/2021 23:55:04 - INFO - __main__ - Step 59654: {'lr': 0.0003350189262220504, 'samples': 11453568, 'steps': 59653, 'loss/train': 1.7653824090957642} 08/30/2021 23:55:05 - INFO - __main__ - Step 59655: {'lr': 0.0003350139357507972, 'samples': 11453760, 'steps': 59654, 'loss/train': 1.6006726026535034} 08/30/2021 23:55:05 - INFO - __main__ - Step 59656: {'lr': 0.00033500894524123796, 'samples': 11453952, 'steps': 59655, 'loss/train': 1.2506486177444458} 08/30/2021 23:55:05 - INFO - __main__ - Step 59657: {'lr': 0.0003350039546933751, 'samples': 11454144, 'steps': 59656, 'loss/train': 0.8107120394706726} 08/30/2021 23:55:06 - INFO - __main__ - Step 59658: {'lr': 0.00033499896410721066, 'samples': 11454336, 'steps': 59657, 'loss/train': 1.5907068252563477} 08/30/2021 23:55:07 - INFO - __main__ - Step 59659: {'lr': 0.000334993973482747, 'samples': 11454528, 'steps': 59658, 'loss/train': 1.9400674104690552} 08/30/2021 23:55:08 - INFO - __main__ - Step 59660: {'lr': 0.0003349889828199864, 'samples': 11454720, 'steps': 59659, 'loss/train': 1.310667634010315} 08/30/2021 23:55:08 - INFO - __main__ - Step 59661: {'lr': 0.000334983992118931, 'samples': 11454912, 'steps': 59660, 'loss/train': 0.6708696484565735} 08/30/2021 23:55:08 - INFO - __main__ - Step 59662: {'lr': 0.00033497900137958325, 'samples': 11455104, 'steps': 59661, 'loss/train': 1.6113548278808594} 08/30/2021 23:55:09 - INFO - __main__ - Step 59663: {'lr': 0.00033497401060194525, 'samples': 11455296, 'steps': 59662, 'loss/train': 1.5807186365127563} 08/30/2021 23:55:10 - INFO - __main__ - Step 59664: {'lr': 0.00033496901978601924, 'samples': 11455488, 'steps': 59663, 'loss/train': 1.902320384979248} 08/30/2021 23:55:11 - INFO - __main__ - Step 59665: {'lr': 0.0003349640289318075, 'samples': 11455680, 'steps': 59664, 'loss/train': 1.3955453634262085} 08/30/2021 23:55:11 - INFO - __main__ - Step 59666: {'lr': 0.0003349590380393123, 'samples': 11455872, 'steps': 59665, 'loss/train': 1.8161306381225586} 08/30/2021 23:55:12 - INFO - __main__ - Step 59667: {'lr': 0.0003349540471085358, 'samples': 11456064, 'steps': 59666, 'loss/train': 1.3871043920516968} 08/30/2021 23:55:12 - INFO - __main__ - Step 59668: {'lr': 0.00033494905613948035, 'samples': 11456256, 'steps': 59667, 'loss/train': 1.646823525428772} 08/30/2021 23:55:14 - INFO - __main__ - Step 59669: {'lr': 0.00033494406513214826, 'samples': 11456448, 'steps': 59668, 'loss/train': 1.4401887655258179} 08/30/2021 23:55:15 - INFO - __main__ - Step 59670: {'lr': 0.0003349390740865416, 'samples': 11456640, 'steps': 59669, 'loss/train': 1.7677853107452393} 08/30/2021 23:55:15 - INFO - __main__ - Step 59671: {'lr': 0.0003349340830026627, 'samples': 11456832, 'steps': 59670, 'loss/train': 0.047431644052267075} 08/30/2021 23:55:16 - INFO - __main__ - Step 59672: {'lr': 0.0003349290918805138, 'samples': 11457024, 'steps': 59671, 'loss/train': 0.036663372069597244} 08/30/2021 23:55:16 - INFO - __main__ - Step 59673: {'lr': 0.0003349241007200972, 'samples': 11457216, 'steps': 59672, 'loss/train': 1.2027740478515625} 08/30/2021 23:55:16 - INFO - __main__ - Step 59674: {'lr': 0.0003349191095214151, 'samples': 11457408, 'steps': 59673, 'loss/train': 1.6536368131637573} 08/30/2021 23:55:18 - INFO - __main__ - Step 59675: {'lr': 0.00033491411828446974, 'samples': 11457600, 'steps': 59674, 'loss/train': 0.9581016302108765} 08/30/2021 23:55:18 - INFO - __main__ - Step 59676: {'lr': 0.00033490912700926345, 'samples': 11457792, 'steps': 59675, 'loss/train': 2.5357964038848877} 08/30/2021 23:55:19 - INFO - __main__ - Step 59677: {'lr': 0.00033490413569579837, 'samples': 11457984, 'steps': 59676, 'loss/train': 1.1402490139007568} 08/30/2021 23:55:19 - INFO - __main__ - Step 59678: {'lr': 0.00033489914434407683, 'samples': 11458176, 'steps': 59677, 'loss/train': 1.1416606903076172} 08/30/2021 23:55:19 - INFO - __main__ - Step 59679: {'lr': 0.00033489415295410096, 'samples': 11458368, 'steps': 59678, 'loss/train': 2.04219126701355} 08/30/2021 23:55:21 - INFO - __main__ - Step 59680: {'lr': 0.0003348891615258732, 'samples': 11458560, 'steps': 59679, 'loss/train': 1.275970697402954} 08/30/2021 23:55:21 - INFO - __main__ - Step 59681: {'lr': 0.0003348841700593956, 'samples': 11458752, 'steps': 59680, 'loss/train': 0.6447604298591614} 08/30/2021 23:55:22 - INFO - __main__ - Step 59682: {'lr': 0.00033487917855467056, 'samples': 11458944, 'steps': 59681, 'loss/train': 1.9180761575698853} 08/30/2021 23:55:22 - INFO - __main__ - Step 59683: {'lr': 0.0003348741870117003, 'samples': 11459136, 'steps': 59682, 'loss/train': 1.2197058200836182} 08/30/2021 23:55:22 - INFO - __main__ - Step 59684: {'lr': 0.000334869195430487, 'samples': 11459328, 'steps': 59683, 'loss/train': 1.4845428466796875} 08/30/2021 23:55:23 - INFO - __main__ - Step 59685: {'lr': 0.0003348642038110329, 'samples': 11459520, 'steps': 59684, 'loss/train': 0.928158700466156} 08/30/2021 23:55:24 - INFO - __main__ - Step 59686: {'lr': 0.0003348592121533404, 'samples': 11459712, 'steps': 59685, 'loss/train': 1.0008618831634521} 08/30/2021 23:55:25 - INFO - __main__ - Step 59687: {'lr': 0.00033485422045741154, 'samples': 11459904, 'steps': 59686, 'loss/train': 0.965795636177063} 08/30/2021 23:55:25 - INFO - __main__ - Step 59688: {'lr': 0.00033484922872324875, 'samples': 11460096, 'steps': 59687, 'loss/train': 1.744931697845459} 08/30/2021 23:55:26 - INFO - __main__ - Step 59689: {'lr': 0.0003348442369508542, 'samples': 11460288, 'steps': 59688, 'loss/train': 1.3161970376968384} 08/30/2021 23:55:26 - INFO - __main__ - Step 59690: {'lr': 0.0003348392451402302, 'samples': 11460480, 'steps': 59689, 'loss/train': 1.1430429220199585} 08/30/2021 23:55:27 - INFO - __main__ - Step 59691: {'lr': 0.00033483425329137886, 'samples': 11460672, 'steps': 59690, 'loss/train': 1.626570463180542} 08/30/2021 23:55:28 - INFO - __main__ - Step 59692: {'lr': 0.00033482926140430253, 'samples': 11460864, 'steps': 59691, 'loss/train': 1.1314787864685059} 08/30/2021 23:55:28 - INFO - __main__ - Step 59693: {'lr': 0.00033482426947900346, 'samples': 11461056, 'steps': 59692, 'loss/train': 0.9415705800056458} 08/30/2021 23:55:29 - INFO - __main__ - Step 59694: {'lr': 0.0003348192775154839, 'samples': 11461248, 'steps': 59693, 'loss/train': 1.9621731042861938} 08/30/2021 23:55:29 - INFO - __main__ - Step 59695: {'lr': 0.000334814285513746, 'samples': 11461440, 'steps': 59694, 'loss/train': 1.3592627048492432} 08/30/2021 23:55:31 - INFO - __main__ - Step 59696: {'lr': 0.0003348092934737922, 'samples': 11461632, 'steps': 59695, 'loss/train': 1.2920070886611938} 08/30/2021 23:55:31 - INFO - __main__ - Step 59697: {'lr': 0.00033480430139562456, 'samples': 11461824, 'steps': 59696, 'loss/train': 1.2732104063034058} 08/30/2021 23:55:31 - INFO - __main__ - Step 59698: {'lr': 0.00033479930927924543, 'samples': 11462016, 'steps': 59697, 'loss/train': 1.5100641250610352} 08/30/2021 23:55:32 - INFO - __main__ - Step 59699: {'lr': 0.000334794317124657, 'samples': 11462208, 'steps': 59698, 'loss/train': 1.5801640748977661} 08/30/2021 23:55:32 - INFO - __main__ - Step 59700: {'lr': 0.00033478932493186163, 'samples': 11462400, 'steps': 59699, 'loss/train': 0.9741455316543579} 08/30/2021 23:55:34 - INFO - __main__ - Step 59701: {'lr': 0.0003347843327008615, 'samples': 11462592, 'steps': 59700, 'loss/train': 1.263201355934143} 08/30/2021 23:55:34 - INFO - __main__ - Step 59702: {'lr': 0.0003347793404316589, 'samples': 11462784, 'steps': 59701, 'loss/train': 1.4084205627441406} 08/30/2021 23:55:34 - INFO - __main__ - Step 59703: {'lr': 0.00033477434812425596, 'samples': 11462976, 'steps': 59702, 'loss/train': 1.3989253044128418} 08/30/2021 23:55:35 - INFO - __main__ - Step 59704: {'lr': 0.00033476935577865497, 'samples': 11463168, 'steps': 59703, 'loss/train': 1.5004475116729736} 08/30/2021 23:55:35 - INFO - __main__ - Step 59705: {'lr': 0.0003347643633948583, 'samples': 11463360, 'steps': 59704, 'loss/train': 1.8358335494995117} 08/30/2021 23:55:37 - INFO - __main__ - Step 59706: {'lr': 0.00033475937097286805, 'samples': 11463552, 'steps': 59705, 'loss/train': 1.3572688102722168} 08/30/2021 23:55:37 - INFO - __main__ - Step 59707: {'lr': 0.00033475437851268657, 'samples': 11463744, 'steps': 59706, 'loss/train': 1.1815388202667236} 08/30/2021 23:55:38 - INFO - __main__ - Step 59708: {'lr': 0.0003347493860143161, 'samples': 11463936, 'steps': 59707, 'loss/train': 0.8684139847755432} 08/30/2021 23:55:38 - INFO - __main__ - Step 59709: {'lr': 0.0003347443934777589, 'samples': 11464128, 'steps': 59708, 'loss/train': 1.5310202836990356} 08/30/2021 23:55:38 - INFO - __main__ - Step 59710: {'lr': 0.0003347394009030171, 'samples': 11464320, 'steps': 59709, 'loss/train': 0.36027631163597107} 08/30/2021 23:55:39 - INFO - __main__ - Step 59711: {'lr': 0.00033473440829009303, 'samples': 11464512, 'steps': 59710, 'loss/train': 1.3714977502822876} 08/30/2021 23:55:40 - INFO - __main__ - Step 59712: {'lr': 0.00033472941563898897, 'samples': 11464704, 'steps': 59711, 'loss/train': 0.7579142451286316} 08/30/2021 23:55:41 - INFO - __main__ - Step 59713: {'lr': 0.00033472442294970716, 'samples': 11464896, 'steps': 59712, 'loss/train': 0.32478347420692444} 08/30/2021 23:55:41 - INFO - __main__ - Step 59714: {'lr': 0.00033471943022224984, 'samples': 11465088, 'steps': 59713, 'loss/train': 0.04143539443612099} 08/30/2021 23:55:42 - INFO - __main__ - Step 59715: {'lr': 0.0003347144374566192, 'samples': 11465280, 'steps': 59714, 'loss/train': 0.5237289071083069} 08/30/2021 23:55:42 - INFO - __main__ - Step 59716: {'lr': 0.00033470944465281753, 'samples': 11465472, 'steps': 59715, 'loss/train': 1.9920235872268677} 08/30/2021 23:55:44 - INFO - __main__ - Step 59717: {'lr': 0.00033470445181084716, 'samples': 11465664, 'steps': 59716, 'loss/train': 1.4423717260360718} 08/30/2021 23:55:44 - INFO - __main__ - Step 59718: {'lr': 0.0003346994589307102, 'samples': 11465856, 'steps': 59717, 'loss/train': 1.4636828899383545} 08/30/2021 23:55:44 - INFO - __main__ - Step 59719: {'lr': 0.00033469446601240907, 'samples': 11466048, 'steps': 59718, 'loss/train': 1.0583508014678955} 08/30/2021 23:55:45 - INFO - __main__ - Step 59720: {'lr': 0.00033468947305594586, 'samples': 11466240, 'steps': 59719, 'loss/train': 1.0116227865219116} 08/30/2021 23:55:45 - INFO - __main__ - Step 59721: {'lr': 0.0003346844800613229, 'samples': 11466432, 'steps': 59720, 'loss/train': 1.2756251096725464} 08/30/2021 23:55:46 - INFO - __main__ - Step 59722: {'lr': 0.00033467948702854233, 'samples': 11466624, 'steps': 59721, 'loss/train': 1.3189589977264404} 08/30/2021 23:55:47 - INFO - __main__ - Step 59723: {'lr': 0.00033467449395760656, 'samples': 11466816, 'steps': 59722, 'loss/train': 1.0390872955322266} 08/30/2021 23:55:47 - INFO - __main__ - Step 59724: {'lr': 0.0003346695008485179, 'samples': 11467008, 'steps': 59723, 'loss/train': 1.437348484992981} 08/30/2021 23:55:48 - INFO - __main__ - Step 59725: {'lr': 0.00033466450770127824, 'samples': 11467200, 'steps': 59724, 'loss/train': 1.2895927429199219} 08/30/2021 23:55:48 - INFO - __main__ - Step 59726: {'lr': 0.0003346595145158902, 'samples': 11467392, 'steps': 59725, 'loss/train': 1.1519036293029785} 08/30/2021 23:55:50 - INFO - __main__ - Step 59727: {'lr': 0.00033465452129235584, 'samples': 11467584, 'steps': 59726, 'loss/train': 1.6210496425628662} 08/30/2021 23:55:51 - INFO - __main__ - Step 59728: {'lr': 0.00033464952803067746, 'samples': 11467776, 'steps': 59727, 'loss/train': 1.3351916074752808} 08/30/2021 23:55:51 - INFO - __main__ - Step 59729: {'lr': 0.0003346445347308573, 'samples': 11467968, 'steps': 59728, 'loss/train': 1.0022586584091187} 08/30/2021 23:55:51 - INFO - __main__ - Step 59730: {'lr': 0.0003346395413928977, 'samples': 11468160, 'steps': 59729, 'loss/train': 0.0895194411277771} 08/30/2021 23:55:52 - INFO - __main__ - Step 59731: {'lr': 0.0003346345480168007, 'samples': 11468352, 'steps': 59730, 'loss/train': 1.2002934217453003} 08/30/2021 23:55:52 - INFO - __main__ - Step 59732: {'lr': 0.00033462955460256876, 'samples': 11468544, 'steps': 59731, 'loss/train': 1.5982295274734497} 08/30/2021 23:55:53 - INFO - __main__ - Step 59733: {'lr': 0.00033462456115020405, 'samples': 11468736, 'steps': 59732, 'loss/train': 1.6238337755203247} 08/30/2021 23:55:54 - INFO - __main__ - Step 59734: {'lr': 0.0003346195676597088, 'samples': 11468928, 'steps': 59733, 'loss/train': 1.6143372058868408} 08/30/2021 23:55:54 - INFO - __main__ - Step 59735: {'lr': 0.00033461457413108524, 'samples': 11469120, 'steps': 59734, 'loss/train': 1.692519187927246} 08/30/2021 23:55:55 - INFO - __main__ - Step 59736: {'lr': 0.00033460958056433574, 'samples': 11469312, 'steps': 59735, 'loss/train': 0.8821504712104797} 08/30/2021 23:55:55 - INFO - __main__ - Step 59737: {'lr': 0.00033460458695946244, 'samples': 11469504, 'steps': 59736, 'loss/train': 1.8254777193069458} 08/30/2021 23:55:57 - INFO - __main__ - Step 59738: {'lr': 0.0003345995933164676, 'samples': 11469696, 'steps': 59737, 'loss/train': 1.6471219062805176} 08/30/2021 23:55:57 - INFO - __main__ - Step 59739: {'lr': 0.0003345945996353535, 'samples': 11469888, 'steps': 59738, 'loss/train': 1.2928080558776855} 08/30/2021 23:55:57 - INFO - __main__ - Step 59740: {'lr': 0.0003345896059161224, 'samples': 11470080, 'steps': 59739, 'loss/train': 0.8101669549942017} 08/30/2021 23:55:58 - INFO - __main__ - Step 59741: {'lr': 0.00033458461215877644, 'samples': 11470272, 'steps': 59740, 'loss/train': 1.3493016958236694} 08/30/2021 23:55:58 - INFO - __main__ - Step 59742: {'lr': 0.000334579618363318, 'samples': 11470464, 'steps': 59741, 'loss/train': 1.7585716247558594} 08/30/2021 23:55:59 - INFO - __main__ - Step 59743: {'lr': 0.0003345746245297494, 'samples': 11470656, 'steps': 59742, 'loss/train': 0.2537163496017456} 08/30/2021 23:56:00 - INFO - __main__ - Step 59744: {'lr': 0.00033456963065807264, 'samples': 11470848, 'steps': 59743, 'loss/train': 1.1767010688781738} 08/30/2021 23:56:00 - INFO - __main__ - Step 59745: {'lr': 0.0003345646367482902, 'samples': 11471040, 'steps': 59744, 'loss/train': 1.826465368270874} 08/30/2021 23:56:01 - INFO - __main__ - Step 59746: {'lr': 0.00033455964280040417, 'samples': 11471232, 'steps': 59745, 'loss/train': 1.0680867433547974} 08/30/2021 23:56:01 - INFO - __main__ - Step 59747: {'lr': 0.0003345546488144169, 'samples': 11471424, 'steps': 59746, 'loss/train': 1.2335466146469116} 08/30/2021 23:56:03 - INFO - __main__ - Step 59748: {'lr': 0.0003345496547903306, 'samples': 11471616, 'steps': 59747, 'loss/train': 1.3852471113204956} 08/30/2021 23:56:03 - INFO - __main__ - Step 59749: {'lr': 0.0003345446607281475, 'samples': 11471808, 'steps': 59748, 'loss/train': 1.362723469734192} 08/30/2021 23:56:03 - INFO - __main__ - Step 59750: {'lr': 0.00033453966662786995, 'samples': 11472000, 'steps': 59749, 'loss/train': 1.731467604637146} 08/30/2021 23:56:04 - INFO - __main__ - Step 59751: {'lr': 0.0003345346724895001, 'samples': 11472192, 'steps': 59750, 'loss/train': 0.04695221409201622} 08/30/2021 23:56:04 - INFO - __main__ - Step 59752: {'lr': 0.0003345296783130402, 'samples': 11472384, 'steps': 59751, 'loss/train': 0.7827739715576172} 08/30/2021 23:56:06 - INFO - __main__ - Step 59753: {'lr': 0.0003345246840984926, 'samples': 11472576, 'steps': 59752, 'loss/train': 1.3239326477050781} 08/30/2021 23:56:06 - INFO - __main__ - Step 59754: {'lr': 0.0003345196898458594, 'samples': 11472768, 'steps': 59753, 'loss/train': 0.9566469192504883} 08/30/2021 23:56:07 - INFO - __main__ - Step 59755: {'lr': 0.00033451469555514294, 'samples': 11472960, 'steps': 59754, 'loss/train': 1.815759301185608} 08/30/2021 23:56:07 - INFO - __main__ - Step 59756: {'lr': 0.0003345097012263456, 'samples': 11473152, 'steps': 59755, 'loss/train': 1.2994920015335083} 08/30/2021 23:56:07 - INFO - __main__ - Step 59757: {'lr': 0.0003345047068594694, 'samples': 11473344, 'steps': 59756, 'loss/train': 1.2464489936828613} 08/30/2021 23:56:08 - INFO - __main__ - Step 59758: {'lr': 0.0003344997124545166, 'samples': 11473536, 'steps': 59757, 'loss/train': 0.05283069238066673} 08/30/2021 23:56:09 - INFO - __main__ - Step 59759: {'lr': 0.00033449471801148963, 'samples': 11473728, 'steps': 59758, 'loss/train': 2.0384433269500732} 08/30/2021 23:56:10 - INFO - __main__ - Step 59760: {'lr': 0.00033448972353039065, 'samples': 11473920, 'steps': 59759, 'loss/train': 1.4910094738006592} 08/30/2021 23:56:10 - INFO - __main__ - Step 59761: {'lr': 0.00033448472901122185, 'samples': 11474112, 'steps': 59760, 'loss/train': 1.7265764474868774} 08/30/2021 23:56:10 - INFO - __main__ - Step 59762: {'lr': 0.0003344797344539855, 'samples': 11474304, 'steps': 59761, 'loss/train': 1.7909163236618042} 08/30/2021 23:56:11 - INFO - __main__ - Step 59763: {'lr': 0.000334474739858684, 'samples': 11474496, 'steps': 59762, 'loss/train': 1.116208791732788} 08/30/2021 23:56:12 - INFO - __main__ - Step 59764: {'lr': 0.0003344697452253195, 'samples': 11474688, 'steps': 59763, 'loss/train': 1.0572972297668457} 08/30/2021 23:56:13 - INFO - __main__ - Step 59765: {'lr': 0.00033446475055389413, 'samples': 11474880, 'steps': 59764, 'loss/train': 1.1873688697814941} 08/30/2021 23:56:13 - INFO - __main__ - Step 59766: {'lr': 0.00033445975584441023, 'samples': 11475072, 'steps': 59765, 'loss/train': 1.6671496629714966} 08/30/2021 23:56:14 - INFO - __main__ - Step 59767: {'lr': 0.00033445476109687013, 'samples': 11475264, 'steps': 59766, 'loss/train': 1.2718393802642822} 08/30/2021 23:56:14 - INFO - __main__ - Step 59768: {'lr': 0.000334449766311276, 'samples': 11475456, 'steps': 59767, 'loss/train': 1.464003086090088} 08/30/2021 23:56:15 - INFO - __main__ - Step 59769: {'lr': 0.00033444477148763006, 'samples': 11475648, 'steps': 59768, 'loss/train': 0.8690761923789978} 08/30/2021 23:56:16 - INFO - __main__ - Step 59770: {'lr': 0.0003344397766259348, 'samples': 11475840, 'steps': 59769, 'loss/train': 1.0399092435836792} 08/30/2021 23:56:16 - INFO - __main__ - Step 59771: {'lr': 0.0003344347817261921, 'samples': 11476032, 'steps': 59770, 'loss/train': 1.2288081645965576} 08/30/2021 23:56:17 - INFO - __main__ - Step 59772: {'lr': 0.0003344297867884044, 'samples': 11476224, 'steps': 59771, 'loss/train': 1.487261414527893} 08/30/2021 23:56:17 - INFO - __main__ - Step 59773: {'lr': 0.000334424791812574, 'samples': 11476416, 'steps': 59772, 'loss/train': 1.0129410028457642} 08/30/2021 23:56:18 - INFO - __main__ - Step 59774: {'lr': 0.00033441979679870305, 'samples': 11476608, 'steps': 59773, 'loss/train': 1.3561673164367676} 08/30/2021 23:56:19 - INFO - __main__ - Step 59775: {'lr': 0.00033441480174679385, 'samples': 11476800, 'steps': 59774, 'loss/train': 1.1367835998535156} 08/30/2021 23:56:19 - INFO - __main__ - Step 59776: {'lr': 0.00033440980665684866, 'samples': 11476992, 'steps': 59775, 'loss/train': 1.3179066181182861} 08/30/2021 23:56:20 - INFO - __main__ - Step 59777: {'lr': 0.00033440481152886977, 'samples': 11477184, 'steps': 59776, 'loss/train': 0.6363301277160645} 08/30/2021 23:56:20 - INFO - __main__ - Step 59778: {'lr': 0.00033439981636285935, 'samples': 11477376, 'steps': 59777, 'loss/train': 0.5855116844177246} 08/30/2021 23:56:22 - INFO - __main__ - Step 59779: {'lr': 0.0003343948211588196, 'samples': 11477568, 'steps': 59778, 'loss/train': 1.2617617845535278} 08/30/2021 23:56:22 - INFO - __main__ - Step 59780: {'lr': 0.00033438982591675284, 'samples': 11477760, 'steps': 59779, 'loss/train': 0.06369766592979431} 08/30/2021 23:56:23 - INFO - __main__ - Step 59781: {'lr': 0.00033438483063666136, 'samples': 11477952, 'steps': 59780, 'loss/train': 1.5154879093170166} 08/30/2021 23:56:23 - INFO - __main__ - Step 59782: {'lr': 0.0003343798353185474, 'samples': 11478144, 'steps': 59781, 'loss/train': 1.9766372442245483} 08/30/2021 23:56:24 - INFO - __main__ - Step 59783: {'lr': 0.0003343748399624131, 'samples': 11478336, 'steps': 59782, 'loss/train': 1.3903272151947021} 08/30/2021 23:56:25 - INFO - __main__ - Step 59784: {'lr': 0.00033436984456826097, 'samples': 11478528, 'steps': 59783, 'loss/train': 1.8117170333862305} 08/30/2021 23:56:25 - INFO - __main__ - Step 59785: {'lr': 0.000334364849136093, 'samples': 11478720, 'steps': 59784, 'loss/train': 1.3325172662734985} 08/30/2021 23:56:26 - INFO - __main__ - Step 59786: {'lr': 0.0003343598536659115, 'samples': 11478912, 'steps': 59785, 'loss/train': 1.488703966140747} 08/30/2021 23:56:26 - INFO - __main__ - Step 59787: {'lr': 0.00033435485815771875, 'samples': 11479104, 'steps': 59786, 'loss/train': 1.30879807472229} 08/30/2021 23:56:27 - INFO - __main__ - Step 59788: {'lr': 0.00033434986261151705, 'samples': 11479296, 'steps': 59787, 'loss/train': 0.7776273488998413} 08/30/2021 23:56:28 - INFO - __main__ - Step 59789: {'lr': 0.0003343448670273086, 'samples': 11479488, 'steps': 59788, 'loss/train': 1.7939506769180298} 08/30/2021 23:56:28 - INFO - __main__ - Step 59790: {'lr': 0.00033433987140509566, 'samples': 11479680, 'steps': 59789, 'loss/train': 1.5992141962051392} 08/30/2021 23:56:29 - INFO - __main__ - Step 59791: {'lr': 0.0003343348757448804, 'samples': 11479872, 'steps': 59790, 'loss/train': 1.2350643873214722} 08/30/2021 23:56:29 - INFO - __main__ - Step 59792: {'lr': 0.0003343298800466652, 'samples': 11480064, 'steps': 59791, 'loss/train': 0.997530460357666} 08/30/2021 23:56:29 - INFO - __main__ - Step 59793: {'lr': 0.0003343248843104523, 'samples': 11480256, 'steps': 59792, 'loss/train': 1.1343399286270142} 08/30/2021 23:56:31 - INFO - __main__ - Step 59794: {'lr': 0.00033431988853624384, 'samples': 11480448, 'steps': 59793, 'loss/train': 1.1660022735595703} 08/30/2021 23:56:31 - INFO - __main__ - Step 59795: {'lr': 0.00033431489272404215, 'samples': 11480640, 'steps': 59794, 'loss/train': 1.2844220399856567} 08/30/2021 23:56:32 - INFO - __main__ - Step 59796: {'lr': 0.0003343098968738495, 'samples': 11480832, 'steps': 59795, 'loss/train': 0.9138148427009583} 08/30/2021 23:56:32 - INFO - __main__ - Step 59797: {'lr': 0.00033430490098566813, 'samples': 11481024, 'steps': 59796, 'loss/train': 1.4196208715438843} 08/30/2021 23:56:32 - INFO - __main__ - Step 59798: {'lr': 0.00033429990505950025, 'samples': 11481216, 'steps': 59797, 'loss/train': 1.470782995223999} 08/30/2021 23:56:33 - INFO - __main__ - Step 59799: {'lr': 0.0003342949090953481, 'samples': 11481408, 'steps': 59798, 'loss/train': 1.1563445329666138} 08/30/2021 23:56:35 - INFO - __main__ - Step 59800: {'lr': 0.000334289913093214, 'samples': 11481600, 'steps': 59799, 'loss/train': 0.7588146924972534} 08/30/2021 23:56:35 - INFO - __main__ - Step 59801: {'lr': 0.0003342849170531001, 'samples': 11481792, 'steps': 59800, 'loss/train': 1.3940439224243164} 08/30/2021 23:56:35 - INFO - __main__ - Step 59802: {'lr': 0.00033427992097500876, 'samples': 11481984, 'steps': 59801, 'loss/train': 1.6214178800582886} 08/30/2021 23:56:36 - INFO - __main__ - Step 59803: {'lr': 0.00033427492485894216, 'samples': 11482176, 'steps': 59802, 'loss/train': 1.1407142877578735} 08/30/2021 23:56:36 - INFO - __main__ - Step 59804: {'lr': 0.0003342699287049027, 'samples': 11482368, 'steps': 59803, 'loss/train': 1.1118789911270142} 08/30/2021 23:56:37 - INFO - __main__ - Step 59805: {'lr': 0.0003342649325128924, 'samples': 11482560, 'steps': 59804, 'loss/train': 1.1539078950881958} 08/30/2021 23:56:38 - INFO - __main__ - Step 59806: {'lr': 0.00033425993628291367, 'samples': 11482752, 'steps': 59805, 'loss/train': 0.8938167095184326} 08/30/2021 23:56:38 - INFO - __main__ - Step 59807: {'lr': 0.0003342549400149687, 'samples': 11482944, 'steps': 59806, 'loss/train': 1.771031141281128} 08/30/2021 23:56:39 - INFO - __main__ - Step 59808: {'lr': 0.0003342499437090597, 'samples': 11483136, 'steps': 59807, 'loss/train': 1.3330076932907104} 08/30/2021 23:56:39 - INFO - __main__ - Step 59809: {'lr': 0.000334244947365189, 'samples': 11483328, 'steps': 59808, 'loss/train': 1.23978853225708} 08/30/2021 23:56:40 - INFO - __main__ - Step 59810: {'lr': 0.00033423995098335886, 'samples': 11483520, 'steps': 59809, 'loss/train': 1.120497226715088} 08/30/2021 23:56:41 - INFO - __main__ - Step 59811: {'lr': 0.00033423495456357156, 'samples': 11483712, 'steps': 59810, 'loss/train': 1.323451280593872} 08/30/2021 23:56:41 - INFO - __main__ - Step 59812: {'lr': 0.00033422995810582917, 'samples': 11483904, 'steps': 59811, 'loss/train': 1.096530795097351} 08/30/2021 23:56:42 - INFO - __main__ - Step 59813: {'lr': 0.0003342249616101341, 'samples': 11484096, 'steps': 59812, 'loss/train': 1.330569863319397} 08/30/2021 23:56:42 - INFO - __main__ - Step 59814: {'lr': 0.0003342199650764886, 'samples': 11484288, 'steps': 59813, 'loss/train': 1.453934669494629} 08/30/2021 23:56:44 - INFO - __main__ - Step 59815: {'lr': 0.0003342149685048949, 'samples': 11484480, 'steps': 59814, 'loss/train': 1.1754119396209717} 08/30/2021 23:56:44 - INFO - __main__ - Step 59816: {'lr': 0.0003342099718953551, 'samples': 11484672, 'steps': 59815, 'loss/train': 1.1980715990066528} 08/30/2021 23:56:44 - INFO - __main__ - Step 59817: {'lr': 0.00033420497524787177, 'samples': 11484864, 'steps': 59816, 'loss/train': 1.5578720569610596} 08/30/2021 23:56:45 - INFO - __main__ - Step 59818: {'lr': 0.0003341999785624468, 'samples': 11485056, 'steps': 59817, 'loss/train': 0.9726073145866394} 08/30/2021 23:56:45 - INFO - __main__ - Step 59819: {'lr': 0.0003341949818390827, 'samples': 11485248, 'steps': 59818, 'loss/train': 1.4954408407211304} 08/30/2021 23:56:45 - INFO - __main__ - Step 59820: {'lr': 0.00033418998507778164, 'samples': 11485440, 'steps': 59819, 'loss/train': 1.964455246925354} 08/30/2021 23:56:47 - INFO - __main__ - Step 59821: {'lr': 0.00033418498827854587, 'samples': 11485632, 'steps': 59820, 'loss/train': 0.9344597458839417} 08/30/2021 23:56:47 - INFO - __main__ - Step 59822: {'lr': 0.0003341799914413776, 'samples': 11485824, 'steps': 59821, 'loss/train': 1.8223085403442383} 08/30/2021 23:56:48 - INFO - __main__ - Step 59823: {'lr': 0.0003341749945662792, 'samples': 11486016, 'steps': 59822, 'loss/train': 1.943886160850525} 08/30/2021 23:56:48 - INFO - __main__ - Step 59824: {'lr': 0.00033416999765325286, 'samples': 11486208, 'steps': 59823, 'loss/train': 1.70814847946167} 08/30/2021 23:56:48 - INFO - __main__ - Step 59825: {'lr': 0.0003341650007023008, 'samples': 11486400, 'steps': 59824, 'loss/train': 0.05768867954611778} 08/30/2021 23:56:50 - INFO - __main__ - Step 59826: {'lr': 0.0003341600037134252, 'samples': 11486592, 'steps': 59825, 'loss/train': 1.1454423666000366} 08/30/2021 23:56:50 - INFO - __main__ - Step 59827: {'lr': 0.00033415500668662845, 'samples': 11486784, 'steps': 59826, 'loss/train': 1.0220969915390015} 08/30/2021 23:56:51 - INFO - __main__ - Step 59828: {'lr': 0.00033415000962191277, 'samples': 11486976, 'steps': 59827, 'loss/train': 1.5042085647583008} 08/30/2021 23:56:51 - INFO - __main__ - Step 59829: {'lr': 0.0003341450125192804, 'samples': 11487168, 'steps': 59828, 'loss/train': 1.5808707475662231} 08/30/2021 23:56:51 - INFO - __main__ - Step 59830: {'lr': 0.0003341400153787336, 'samples': 11487360, 'steps': 59829, 'loss/train': 1.0826679468154907} 08/30/2021 23:56:53 - INFO - __main__ - Step 59831: {'lr': 0.00033413501820027456, 'samples': 11487552, 'steps': 59830, 'loss/train': 1.0123571157455444} 08/30/2021 23:56:53 - INFO - __main__ - Step 59832: {'lr': 0.00033413002098390567, 'samples': 11487744, 'steps': 59831, 'loss/train': 1.1429065465927124} 08/30/2021 23:56:54 - INFO - __main__ - Step 59833: {'lr': 0.00033412502372962894, 'samples': 11487936, 'steps': 59832, 'loss/train': 1.335215449333191} 08/30/2021 23:56:54 - INFO - __main__ - Step 59834: {'lr': 0.0003341200264374469, 'samples': 11488128, 'steps': 59833, 'loss/train': 1.3216681480407715} 08/30/2021 23:56:54 - INFO - __main__ - Step 59835: {'lr': 0.0003341150291073616, 'samples': 11488320, 'steps': 59834, 'loss/train': 1.0301731824874878} 08/30/2021 23:56:57 - INFO - __main__ - Step 59836: {'lr': 0.0003341100317393754, 'samples': 11488512, 'steps': 59835, 'loss/train': 1.4344308376312256} 08/30/2021 23:56:57 - INFO - __main__ - Step 59837: {'lr': 0.00033410503433349055, 'samples': 11488704, 'steps': 59836, 'loss/train': 0.5759755969047546} 08/30/2021 23:56:57 - INFO - __main__ - Step 59838: {'lr': 0.00033410003688970927, 'samples': 11488896, 'steps': 59837, 'loss/train': 1.4586576223373413} 08/30/2021 23:56:58 - INFO - __main__ - Step 59839: {'lr': 0.0003340950394080337, 'samples': 11489088, 'steps': 59838, 'loss/train': 1.195893406867981} 08/30/2021 23:56:58 - INFO - __main__ - Step 59840: {'lr': 0.0003340900418884663, 'samples': 11489280, 'steps': 59839, 'loss/train': 0.9461076855659485} 08/30/2021 23:56:59 - INFO - __main__ - Step 59841: {'lr': 0.00033408504433100916, 'samples': 11489472, 'steps': 59840, 'loss/train': 1.8688420057296753} 08/30/2021 23:57:00 - INFO - __main__ - Step 59842: {'lr': 0.0003340800467356647, 'samples': 11489664, 'steps': 59841, 'loss/train': 1.3909554481506348} 08/30/2021 23:57:00 - INFO - __main__ - Step 59843: {'lr': 0.00033407504910243504, 'samples': 11489856, 'steps': 59842, 'loss/train': 0.9482306241989136} 08/30/2021 23:57:01 - INFO - __main__ - Step 59844: {'lr': 0.0003340700514313224, 'samples': 11490048, 'steps': 59843, 'loss/train': 1.2253609895706177} 08/30/2021 23:57:01 - INFO - __main__ - Step 59845: {'lr': 0.0003340650537223291, 'samples': 11490240, 'steps': 59844, 'loss/train': 0.9642473459243774} 08/30/2021 23:57:02 - INFO - __main__ - Step 59846: {'lr': 0.0003340600559754574, 'samples': 11490432, 'steps': 59845, 'loss/train': 1.307847023010254} 08/30/2021 23:57:03 - INFO - __main__ - Step 59847: {'lr': 0.0003340550581907095, 'samples': 11490624, 'steps': 59846, 'loss/train': 1.3682631254196167} 08/30/2021 23:57:03 - INFO - __main__ - Step 59848: {'lr': 0.0003340500603680878, 'samples': 11490816, 'steps': 59847, 'loss/train': 1.4190080165863037} 08/30/2021 23:57:04 - INFO - __main__ - Step 59849: {'lr': 0.00033404506250759436, 'samples': 11491008, 'steps': 59848, 'loss/train': 1.7067573070526123} 08/30/2021 23:57:04 - INFO - __main__ - Step 59850: {'lr': 0.0003340400646092315, 'samples': 11491200, 'steps': 59849, 'loss/train': 1.9834634065628052} 08/30/2021 23:57:06 - INFO - __main__ - Step 59851: {'lr': 0.0003340350666730015, 'samples': 11491392, 'steps': 59850, 'loss/train': 0.5499975085258484} 08/30/2021 23:57:06 - INFO - __main__ - Step 59852: {'lr': 0.0003340300686989066, 'samples': 11491584, 'steps': 59851, 'loss/train': 0.4791135787963867} 08/30/2021 23:57:07 - INFO - __main__ - Step 59853: {'lr': 0.0003340250706869491, 'samples': 11491776, 'steps': 59852, 'loss/train': 0.043618444353342056} 08/30/2021 23:57:07 - INFO - __main__ - Step 59854: {'lr': 0.00033402007263713115, 'samples': 11491968, 'steps': 59853, 'loss/train': 0.031721729785203934} 08/30/2021 23:57:07 - INFO - __main__ - Step 59855: {'lr': 0.000334015074549455, 'samples': 11492160, 'steps': 59854, 'loss/train': 1.2451456785202026} 08/30/2021 23:57:08 - INFO - __main__ - Step 59856: {'lr': 0.000334010076423923, 'samples': 11492352, 'steps': 59855, 'loss/train': 1.618203043937683} 08/30/2021 23:57:09 - INFO - __main__ - Step 59857: {'lr': 0.00033400507826053733, 'samples': 11492544, 'steps': 59856, 'loss/train': 1.1706225872039795} 08/30/2021 23:57:10 - INFO - __main__ - Step 59858: {'lr': 0.0003340000800593004, 'samples': 11492736, 'steps': 59857, 'loss/train': 1.5623292922973633} 08/30/2021 23:57:10 - INFO - __main__ - Step 59859: {'lr': 0.0003339950818202142, 'samples': 11492928, 'steps': 59858, 'loss/train': 1.1343538761138916} 08/30/2021 23:57:10 - INFO - __main__ - Step 59860: {'lr': 0.00033399008354328106, 'samples': 11493120, 'steps': 59859, 'loss/train': 1.705298662185669} 08/30/2021 23:57:11 - INFO - __main__ - Step 59861: {'lr': 0.0003339850852285034, 'samples': 11493312, 'steps': 59860, 'loss/train': 1.181028962135315} 08/30/2021 23:57:12 - INFO - __main__ - Step 59862: {'lr': 0.00033398008687588333, 'samples': 11493504, 'steps': 59861, 'loss/train': 1.382114052772522} 08/30/2021 23:57:13 - INFO - __main__ - Step 59863: {'lr': 0.00033397508848542306, 'samples': 11493696, 'steps': 59862, 'loss/train': 1.5730162858963013} 08/30/2021 23:57:13 - INFO - __main__ - Step 59864: {'lr': 0.000333970090057125, 'samples': 11493888, 'steps': 59863, 'loss/train': 0.9286319613456726} 08/30/2021 23:57:13 - INFO - __main__ - Step 59865: {'lr': 0.00033396509159099133, 'samples': 11494080, 'steps': 59864, 'loss/train': 1.2114009857177734} 08/30/2021 23:57:14 - INFO - __main__ - Step 59866: {'lr': 0.00033396009308702426, 'samples': 11494272, 'steps': 59865, 'loss/train': 1.3148281574249268} 08/30/2021 23:57:14 - INFO - __main__ - Step 59867: {'lr': 0.000333955094545226, 'samples': 11494464, 'steps': 59866, 'loss/train': 1.6499541997909546} 08/30/2021 23:57:15 - INFO - __main__ - Step 59868: {'lr': 0.00033395009596559887, 'samples': 11494656, 'steps': 59867, 'loss/train': 0.9818961024284363} 08/30/2021 23:57:16 - INFO - __main__ - Step 59869: {'lr': 0.00033394509734814516, 'samples': 11494848, 'steps': 59868, 'loss/train': 1.1983884572982788} 08/30/2021 23:57:16 - INFO - __main__ - Step 59870: {'lr': 0.0003339400986928671, 'samples': 11495040, 'steps': 59869, 'loss/train': 1.9102174043655396} 08/30/2021 23:57:17 - INFO - __main__ - Step 59871: {'lr': 0.000333935099999767, 'samples': 11495232, 'steps': 59870, 'loss/train': 1.401785135269165} 08/30/2021 23:57:17 - INFO - __main__ - Step 59872: {'lr': 0.00033393010126884696, 'samples': 11495424, 'steps': 59871, 'loss/train': 1.3177196979522705} 08/30/2021 23:57:18 - INFO - __main__ - Step 59873: {'lr': 0.00033392510250010926, 'samples': 11495616, 'steps': 59872, 'loss/train': 1.6992017030715942} 08/30/2021 23:57:19 - INFO - __main__ - Step 59874: {'lr': 0.00033392010369355627, 'samples': 11495808, 'steps': 59873, 'loss/train': 0.8227543830871582} 08/30/2021 23:57:19 - INFO - __main__ - Step 59875: {'lr': 0.00033391510484919015, 'samples': 11496000, 'steps': 59874, 'loss/train': 1.7897945642471313} 08/30/2021 23:57:20 - INFO - __main__ - Step 59876: {'lr': 0.00033391010596701314, 'samples': 11496192, 'steps': 59875, 'loss/train': 1.1453529596328735} 08/30/2021 23:57:20 - INFO - __main__ - Step 59877: {'lr': 0.0003339051070470276, 'samples': 11496384, 'steps': 59876, 'loss/train': 0.8803033232688904} 08/30/2021 23:57:22 - INFO - __main__ - Step 59878: {'lr': 0.00033390010808923573, 'samples': 11496576, 'steps': 59877, 'loss/train': 1.0257887840270996} 08/30/2021 23:57:22 - INFO - __main__ - Step 59879: {'lr': 0.00033389510909363974, 'samples': 11496768, 'steps': 59878, 'loss/train': 1.421064853668213} 08/30/2021 23:57:23 - INFO - __main__ - Step 59880: {'lr': 0.00033389011006024183, 'samples': 11496960, 'steps': 59879, 'loss/train': 0.3296405076980591} 08/30/2021 23:57:23 - INFO - __main__ - Step 59881: {'lr': 0.0003338851109890444, 'samples': 11497152, 'steps': 59880, 'loss/train': 0.059413522481918335} 08/30/2021 23:57:23 - INFO - __main__ - Step 59882: {'lr': 0.00033388011188004965, 'samples': 11497344, 'steps': 59881, 'loss/train': 0.3087981641292572} 08/30/2021 23:57:25 - INFO - __main__ - Step 59883: {'lr': 0.00033387511273325976, 'samples': 11497536, 'steps': 59882, 'loss/train': 1.4966094493865967} 08/30/2021 23:57:25 - INFO - __main__ - Step 59884: {'lr': 0.0003338701135486771, 'samples': 11497728, 'steps': 59883, 'loss/train': 1.114499807357788} 08/30/2021 23:57:26 - INFO - __main__ - Step 59885: {'lr': 0.0003338651143263038, 'samples': 11497920, 'steps': 59884, 'loss/train': 0.1135730892419815} 08/30/2021 23:57:26 - INFO - __main__ - Step 59886: {'lr': 0.0003338601150661423, 'samples': 11498112, 'steps': 59885, 'loss/train': 0.5827957391738892} 08/30/2021 23:57:26 - INFO - __main__ - Step 59887: {'lr': 0.0003338551157681946, 'samples': 11498304, 'steps': 59886, 'loss/train': 0.7452296018600464} 08/30/2021 23:57:28 - INFO - __main__ - Step 59888: {'lr': 0.00033385011643246313, 'samples': 11498496, 'steps': 59887, 'loss/train': 1.2587543725967407} 08/30/2021 23:57:29 - INFO - __main__ - Step 59889: {'lr': 0.00033384511705895003, 'samples': 11498688, 'steps': 59888, 'loss/train': 1.1873503923416138} 08/30/2021 23:57:29 - INFO - __main__ - Step 59890: {'lr': 0.00033384011764765764, 'samples': 11498880, 'steps': 59889, 'loss/train': 1.2524337768554688} 08/30/2021 23:57:30 - INFO - __main__ - Step 59891: {'lr': 0.0003338351181985882, 'samples': 11499072, 'steps': 59890, 'loss/train': 0.9410980939865112} 08/30/2021 23:57:30 - INFO - __main__ - Step 59892: {'lr': 0.000333830118711744, 'samples': 11499264, 'steps': 59891, 'loss/train': 1.0223844051361084} 08/30/2021 23:57:30 - INFO - __main__ - Step 59893: {'lr': 0.00033382511918712723, 'samples': 11499456, 'steps': 59892, 'loss/train': 1.0214662551879883} 08/30/2021 23:57:32 - INFO - __main__ - Step 59894: {'lr': 0.00033382011962474004, 'samples': 11499648, 'steps': 59893, 'loss/train': 1.7625105381011963} 08/30/2021 23:57:32 - INFO - __main__ - Step 59895: {'lr': 0.0003338151200245849, 'samples': 11499840, 'steps': 59894, 'loss/train': 1.229467511177063} 08/30/2021 23:57:33 - INFO - __main__ - Step 59896: {'lr': 0.000333810120386664, 'samples': 11500032, 'steps': 59895, 'loss/train': 1.0320736169815063} 08/30/2021 23:57:33 - INFO - __main__ - Step 59897: {'lr': 0.00033380512071097947, 'samples': 11500224, 'steps': 59896, 'loss/train': 1.7375085353851318} 08/30/2021 23:57:33 - INFO - __main__ - Step 59898: {'lr': 0.00033380012099753364, 'samples': 11500416, 'steps': 59897, 'loss/train': 1.5975598096847534} 08/30/2021 23:57:35 - INFO - __main__ - Step 59899: {'lr': 0.00033379512124632885, 'samples': 11500608, 'steps': 59898, 'loss/train': 1.06941819190979} 08/30/2021 23:57:35 - INFO - __main__ - Step 59900: {'lr': 0.0003337901214573672, 'samples': 11500800, 'steps': 59899, 'loss/train': 1.3083606958389282} 08/30/2021 23:57:36 - INFO - __main__ - Step 59901: {'lr': 0.000333785121630651, 'samples': 11500992, 'steps': 59900, 'loss/train': 1.334172248840332} 08/30/2021 23:57:36 - INFO - __main__ - Step 59902: {'lr': 0.0003337801217661826, 'samples': 11501184, 'steps': 59901, 'loss/train': 1.0839506387710571} 08/30/2021 23:57:36 - INFO - __main__ - Step 59903: {'lr': 0.0003337751218639641, 'samples': 11501376, 'steps': 59902, 'loss/train': 1.4798659086227417} 08/30/2021 23:57:38 - INFO - __main__ - Step 59904: {'lr': 0.0003337701219239978, 'samples': 11501568, 'steps': 59903, 'loss/train': 1.450107216835022} 08/30/2021 23:57:38 - INFO - __main__ - Step 59905: {'lr': 0.00033376512194628605, 'samples': 11501760, 'steps': 59904, 'loss/train': 1.417326807975769} 08/30/2021 23:57:39 - INFO - __main__ - Step 59906: {'lr': 0.000333760121930831, 'samples': 11501952, 'steps': 59905, 'loss/train': 1.63825261592865} 08/30/2021 23:57:39 - INFO - __main__ - Step 59907: {'lr': 0.0003337551218776349, 'samples': 11502144, 'steps': 59906, 'loss/train': 1.145716905593872} 08/30/2021 23:57:39 - INFO - __main__ - Step 59908: {'lr': 0.0003337501217867001, 'samples': 11502336, 'steps': 59907, 'loss/train': 1.6498032808303833} 08/30/2021 23:57:41 - INFO - __main__ - Step 59909: {'lr': 0.00033374512165802874, 'samples': 11502528, 'steps': 59908, 'loss/train': 1.8988059759140015} 08/30/2021 23:57:41 - INFO - __main__ - Step 59910: {'lr': 0.00033374012149162314, 'samples': 11502720, 'steps': 59909, 'loss/train': 0.2469071000814438} 08/30/2021 23:57:42 - INFO - __main__ - Step 59911: {'lr': 0.0003337351212874856, 'samples': 11502912, 'steps': 59910, 'loss/train': 0.5788956880569458} 08/30/2021 23:57:42 - INFO - __main__ - Step 59912: {'lr': 0.00033373012104561815, 'samples': 11503104, 'steps': 59911, 'loss/train': 1.4770945310592651} 08/30/2021 23:57:42 - INFO - __main__ - Step 59913: {'lr': 0.0003337251207660233, 'samples': 11503296, 'steps': 59912, 'loss/train': 1.744764804840088} 08/30/2021 23:57:44 - INFO - __main__ - Step 59914: {'lr': 0.00033372012044870317, 'samples': 11503488, 'steps': 59913, 'loss/train': 1.0111316442489624} 08/30/2021 23:57:44 - INFO - __main__ - Step 59915: {'lr': 0.00033371512009366006, 'samples': 11503680, 'steps': 59914, 'loss/train': 1.3482054471969604} 08/30/2021 23:57:45 - INFO - __main__ - Step 59916: {'lr': 0.0003337101197008962, 'samples': 11503872, 'steps': 59915, 'loss/train': 0.8457168936729431} 08/30/2021 23:57:45 - INFO - __main__ - Step 59917: {'lr': 0.00033370511927041386, 'samples': 11504064, 'steps': 59916, 'loss/train': 1.6057029962539673} 08/30/2021 23:57:45 - INFO - __main__ - Step 59918: {'lr': 0.0003337001188022153, 'samples': 11504256, 'steps': 59917, 'loss/train': 1.407637357711792} 08/30/2021 23:57:46 - INFO - __main__ - Step 59919: {'lr': 0.0003336951182963027, 'samples': 11504448, 'steps': 59918, 'loss/train': 1.4570865631103516} 08/30/2021 23:57:48 - INFO - __main__ - Step 59920: {'lr': 0.0003336901177526784, 'samples': 11504640, 'steps': 59919, 'loss/train': 1.4743255376815796} 08/30/2021 23:57:48 - INFO - __main__ - Step 59921: {'lr': 0.0003336851171713447, 'samples': 11504832, 'steps': 59920, 'loss/train': 1.1863462924957275} 08/30/2021 23:57:49 - INFO - __main__ - Step 59922: {'lr': 0.00033368011655230366, 'samples': 11505024, 'steps': 59921, 'loss/train': 1.4263556003570557} 08/30/2021 23:57:49 - INFO - __main__ - Step 59923: {'lr': 0.0003336751158955577, 'samples': 11505216, 'steps': 59922, 'loss/train': 0.6447646021842957} 08/30/2021 23:57:49 - INFO - __main__ - Step 59924: {'lr': 0.00033367011520110906, 'samples': 11505408, 'steps': 59923, 'loss/train': 1.1414626836776733} 08/30/2021 23:57:51 - INFO - __main__ - Step 59925: {'lr': 0.00033366511446896, 'samples': 11505600, 'steps': 59924, 'loss/train': 1.3145540952682495} 08/30/2021 23:57:51 - INFO - __main__ - Step 59926: {'lr': 0.0003336601136991126, 'samples': 11505792, 'steps': 59925, 'loss/train': 0.9927424192428589} 08/30/2021 23:57:52 - INFO - __main__ - Step 59927: {'lr': 0.0003336551128915693, 'samples': 11505984, 'steps': 59926, 'loss/train': 1.2483415603637695} 08/30/2021 23:57:52 - INFO - __main__ - Step 59928: {'lr': 0.00033365011204633234, 'samples': 11506176, 'steps': 59927, 'loss/train': 1.9663574695587158} 08/30/2021 23:57:52 - INFO - __main__ - Step 59929: {'lr': 0.0003336451111634038, 'samples': 11506368, 'steps': 59928, 'loss/train': 1.0541672706604004} 08/30/2021 23:57:54 - INFO - __main__ - Step 59930: {'lr': 0.00033364011024278616, 'samples': 11506560, 'steps': 59929, 'loss/train': 1.6667582988739014} 08/30/2021 23:57:54 - INFO - __main__ - Step 59931: {'lr': 0.0003336351092844816, 'samples': 11506752, 'steps': 59930, 'loss/train': 0.2971011996269226} 08/30/2021 23:57:55 - INFO - __main__ - Step 59932: {'lr': 0.0003336301082884924, 'samples': 11506944, 'steps': 59931, 'loss/train': 1.9761375188827515} 08/30/2021 23:57:55 - INFO - __main__ - Step 59933: {'lr': 0.00033362510725482063, 'samples': 11507136, 'steps': 59932, 'loss/train': 1.3288410902023315} 08/30/2021 23:57:55 - INFO - __main__ - Step 59934: {'lr': 0.0003336201061834687, 'samples': 11507328, 'steps': 59933, 'loss/train': 1.4965769052505493} 08/30/2021 23:57:57 - INFO - __main__ - Step 59935: {'lr': 0.0003336151050744389, 'samples': 11507520, 'steps': 59934, 'loss/train': 1.2845549583435059} 08/30/2021 23:57:57 - INFO - __main__ - Step 59936: {'lr': 0.00033361010392773336, 'samples': 11507712, 'steps': 59935, 'loss/train': 0.32606035470962524} 08/30/2021 23:57:57 - INFO - __main__ - Step 59937: {'lr': 0.0003336051027433544, 'samples': 11507904, 'steps': 59936, 'loss/train': 1.5637669563293457} 08/30/2021 23:57:58 - INFO - __main__ - Step 59938: {'lr': 0.00033360010152130436, 'samples': 11508096, 'steps': 59937, 'loss/train': 1.0551283359527588} 08/30/2021 23:57:58 - INFO - __main__ - Step 59939: {'lr': 0.00033359510026158534, 'samples': 11508288, 'steps': 59938, 'loss/train': 1.6106975078582764} 08/30/2021 23:58:01 - INFO - __main__ - Step 59940: {'lr': 0.00033359009896419966, 'samples': 11508480, 'steps': 59939, 'loss/train': 1.4372414350509644} 08/30/2021 23:58:01 - INFO - __main__ - Step 59941: {'lr': 0.00033358509762914957, 'samples': 11508672, 'steps': 59940, 'loss/train': 1.8201642036437988} 08/30/2021 23:58:01 - INFO - __main__ - Step 59942: {'lr': 0.0003335800962564374, 'samples': 11508864, 'steps': 59941, 'loss/train': 1.0826791524887085} 08/30/2021 23:58:02 - INFO - __main__ - Step 59943: {'lr': 0.0003335750948460652, 'samples': 11509056, 'steps': 59942, 'loss/train': 0.5303946137428284} 08/30/2021 23:58:02 - INFO - __main__ - Step 59944: {'lr': 0.0003335700933980354, 'samples': 11509248, 'steps': 59943, 'loss/train': 0.4935438334941864} 08/30/2021 23:58:02 - INFO - __main__ - Step 59945: {'lr': 0.0003335650919123503, 'samples': 11509440, 'steps': 59944, 'loss/train': 0.03718230128288269} 08/30/2021 23:58:04 - INFO - __main__ - Step 59946: {'lr': 0.0003335600903890119, 'samples': 11509632, 'steps': 59945, 'loss/train': 0.03926106169819832} 08/30/2021 23:58:04 - INFO - __main__ - Step 59947: {'lr': 0.0003335550888280227, 'samples': 11509824, 'steps': 59946, 'loss/train': 1.1444340944290161} 08/30/2021 23:58:05 - INFO - __main__ - Step 59948: {'lr': 0.00033355008722938485, 'samples': 11510016, 'steps': 59947, 'loss/train': 1.2942636013031006} 08/30/2021 23:58:05 - INFO - __main__ - Step 59949: {'lr': 0.0003335450855931006, 'samples': 11510208, 'steps': 59948, 'loss/train': 1.9871902465820312} 08/30/2021 23:58:06 - INFO - __main__ - Step 59950: {'lr': 0.00033354008391917224, 'samples': 11510400, 'steps': 59949, 'loss/train': 1.2428416013717651} 08/30/2021 23:58:07 - INFO - __main__ - Step 59951: {'lr': 0.00033353508220760204, 'samples': 11510592, 'steps': 59950, 'loss/train': 1.0078407526016235} 08/30/2021 23:58:08 - INFO - __main__ - Step 59952: {'lr': 0.00033353008045839224, 'samples': 11510784, 'steps': 59951, 'loss/train': 0.8023725152015686} 08/30/2021 23:58:08 - INFO - __main__ - Step 59953: {'lr': 0.000333525078671545, 'samples': 11510976, 'steps': 59952, 'loss/train': 1.3900474309921265} 08/30/2021 23:58:08 - INFO - __main__ - Step 59954: {'lr': 0.0003335200768470627, 'samples': 11511168, 'steps': 59953, 'loss/train': 1.2211180925369263} 08/30/2021 23:58:09 - INFO - __main__ - Step 59955: {'lr': 0.0003335150749849475, 'samples': 11511360, 'steps': 59954, 'loss/train': 0.9000880122184753} 08/30/2021 23:58:10 - INFO - __main__ - Step 59956: {'lr': 0.0003335100730852017, 'samples': 11511552, 'steps': 59955, 'loss/train': 1.6677347421646118} 08/30/2021 23:58:10 - INFO - __main__ - Step 59957: {'lr': 0.0003335050711478276, 'samples': 11511744, 'steps': 59956, 'loss/train': 1.5843745470046997} 08/30/2021 23:58:11 - INFO - __main__ - Step 59958: {'lr': 0.0003335000691728273, 'samples': 11511936, 'steps': 59957, 'loss/train': 0.874744176864624} 08/30/2021 23:58:11 - INFO - __main__ - Step 59959: {'lr': 0.0003334950671602033, 'samples': 11512128, 'steps': 59958, 'loss/train': 1.0463758707046509} 08/30/2021 23:58:12 - INFO - __main__ - Step 59960: {'lr': 0.00033349006510995766, 'samples': 11512320, 'steps': 59959, 'loss/train': 0.8631131052970886} 08/30/2021 23:58:12 - INFO - __main__ - Step 59961: {'lr': 0.00033348506302209265, 'samples': 11512512, 'steps': 59960, 'loss/train': 1.395923376083374} 08/30/2021 23:58:13 - INFO - __main__ - Step 59962: {'lr': 0.00033348006089661055, 'samples': 11512704, 'steps': 59961, 'loss/train': 1.5277764797210693} 08/30/2021 23:58:14 - INFO - __main__ - Step 59963: {'lr': 0.0003334750587335136, 'samples': 11512896, 'steps': 59962, 'loss/train': 1.312781810760498} 08/30/2021 23:58:14 - INFO - __main__ - Step 59964: {'lr': 0.00033347005653280414, 'samples': 11513088, 'steps': 59963, 'loss/train': 1.4424299001693726} 08/30/2021 23:58:14 - INFO - __main__ - Step 59965: {'lr': 0.0003334650542944844, 'samples': 11513280, 'steps': 59964, 'loss/train': 1.5940728187561035} 08/30/2021 23:58:15 - INFO - __main__ - Step 59966: {'lr': 0.00033346005201855656, 'samples': 11513472, 'steps': 59965, 'loss/train': 1.9113858938217163} 08/30/2021 23:58:16 - INFO - __main__ - Step 59967: {'lr': 0.00033345504970502284, 'samples': 11513664, 'steps': 59966, 'loss/train': 1.5821585655212402} 08/30/2021 23:58:17 - INFO - __main__ - Step 59968: {'lr': 0.0003334500473538856, 'samples': 11513856, 'steps': 59967, 'loss/train': 1.1747950315475464} 08/30/2021 23:58:17 - INFO - __main__ - Step 59969: {'lr': 0.00033344504496514703, 'samples': 11514048, 'steps': 59968, 'loss/train': 1.3834439516067505} 08/30/2021 23:58:17 - INFO - __main__ - Step 59970: {'lr': 0.0003334400425388095, 'samples': 11514240, 'steps': 59969, 'loss/train': 1.16960608959198} 08/30/2021 23:58:18 - INFO - __main__ - Step 59971: {'lr': 0.00033343504007487515, 'samples': 11514432, 'steps': 59970, 'loss/train': 1.699402093887329} 08/30/2021 23:58:19 - INFO - __main__ - Step 59972: {'lr': 0.00033343003757334625, 'samples': 11514624, 'steps': 59971, 'loss/train': 1.7500873804092407} 08/30/2021 23:58:20 - INFO - __main__ - Step 59973: {'lr': 0.000333425035034225, 'samples': 11514816, 'steps': 59972, 'loss/train': 1.920077919960022} 08/30/2021 23:58:20 - INFO - __main__ - Step 59974: {'lr': 0.00033342003245751374, 'samples': 11515008, 'steps': 59973, 'loss/train': 1.5325719118118286} 08/30/2021 23:58:20 - INFO - __main__ - Step 59975: {'lr': 0.0003334150298432147, 'samples': 11515200, 'steps': 59974, 'loss/train': 1.2195863723754883} 08/30/2021 23:58:21 - INFO - __main__ - Step 59976: {'lr': 0.00033341002719133016, 'samples': 11515392, 'steps': 59975, 'loss/train': 0.8065526485443115} 08/30/2021 23:58:22 - INFO - __main__ - Step 59977: {'lr': 0.0003334050245018624, 'samples': 11515584, 'steps': 59976, 'loss/train': 1.0746419429779053} 08/30/2021 23:58:23 - INFO - __main__ - Step 59978: {'lr': 0.00033340002177481353, 'samples': 11515776, 'steps': 59977, 'loss/train': 1.3480299711227417} 08/30/2021 23:58:23 - INFO - __main__ - Step 59979: {'lr': 0.00033339501901018595, 'samples': 11515968, 'steps': 59978, 'loss/train': 0.912415087223053} 08/30/2021 23:58:24 - INFO - __main__ - Step 59980: {'lr': 0.0003333900162079818, 'samples': 11516160, 'steps': 59979, 'loss/train': 0.5242136120796204} 08/30/2021 23:58:24 - INFO - __main__ - Step 59981: {'lr': 0.00033338501336820347, 'samples': 11516352, 'steps': 59980, 'loss/train': 1.3247582912445068} 08/30/2021 23:58:26 - INFO - __main__ - Step 59982: {'lr': 0.0003333800104908531, 'samples': 11516544, 'steps': 59981, 'loss/train': 2.3978195190429688} 08/30/2021 23:58:26 - INFO - __main__ - Step 59983: {'lr': 0.00033337500757593306, 'samples': 11516736, 'steps': 59982, 'loss/train': 0.7306232452392578} 08/30/2021 23:58:26 - INFO - __main__ - Step 59984: {'lr': 0.0003333700046234454, 'samples': 11516928, 'steps': 59983, 'loss/train': 1.4217044115066528} 08/30/2021 23:58:27 - INFO - __main__ - Step 59985: {'lr': 0.00033336500163339255, 'samples': 11517120, 'steps': 59984, 'loss/train': 2.6274688243865967} 08/30/2021 23:58:27 - INFO - __main__ - Step 59986: {'lr': 0.00033335999860577677, 'samples': 11517312, 'steps': 59985, 'loss/train': 2.3362929821014404} 08/30/2021 23:58:29 - INFO - __main__ - Step 59987: {'lr': 0.0003333549955406002, 'samples': 11517504, 'steps': 59986, 'loss/train': 0.8453044891357422} 08/30/2021 23:58:29 - INFO - __main__ - Step 59988: {'lr': 0.0003333499924378652, 'samples': 11517696, 'steps': 59987, 'loss/train': 1.0473734140396118} 08/30/2021 23:58:29 - INFO - __main__ - Step 59989: {'lr': 0.00033334498929757394, 'samples': 11517888, 'steps': 59988, 'loss/train': 1.5850181579589844} 08/30/2021 23:58:30 - INFO - __main__ - Step 59990: {'lr': 0.0003333399861197287, 'samples': 11518080, 'steps': 59989, 'loss/train': 1.8422579765319824} 08/30/2021 23:58:30 - INFO - __main__ - Step 59991: {'lr': 0.00033333498290433184, 'samples': 11518272, 'steps': 59990, 'loss/train': 1.579368233680725} 08/30/2021 23:58:30 - INFO - __main__ - Step 59992: {'lr': 0.00033332997965138545, 'samples': 11518464, 'steps': 59991, 'loss/train': 1.1963123083114624} 08/30/2021 23:58:32 - INFO - __main__ - Step 59993: {'lr': 0.0003333249763608919, 'samples': 11518656, 'steps': 59992, 'loss/train': 1.4305427074432373} 08/30/2021 23:58:32 - INFO - __main__ - Step 59994: {'lr': 0.00033331997303285334, 'samples': 11518848, 'steps': 59993, 'loss/train': 1.2449132204055786} 08/30/2021 23:58:33 - INFO - __main__ - Step 59995: {'lr': 0.00033331496966727207, 'samples': 11519040, 'steps': 59994, 'loss/train': 1.3063499927520752} 08/30/2021 23:58:33 - INFO - __main__ - Step 59996: {'lr': 0.00033330996626415046, 'samples': 11519232, 'steps': 59995, 'loss/train': 0.9000343680381775} 08/30/2021 23:58:33 - INFO - __main__ - Step 59997: {'lr': 0.0003333049628234906, 'samples': 11519424, 'steps': 59996, 'loss/train': 1.6371190547943115} 08/30/2021 23:58:36 - INFO - __main__ - Step 59998: {'lr': 0.0003332999593452948, 'samples': 11519616, 'steps': 59997, 'loss/train': 1.5421613454818726} 08/30/2021 23:58:36 - INFO - __main__ - Step 59999: {'lr': 0.0003332949558295654, 'samples': 11519808, 'steps': 59998, 'loss/train': 1.0983376502990723} 08/30/2021 23:58:36 - INFO - __main__ - Step 60000: {'lr': 0.0003332899522763045, 'samples': 11520000, 'steps': 59999, 'loss/train': 1.3309777975082397} 08/30/2021 23:58:37 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 00:07:18 - INFO - __main__ - Step 60000: {'loss/eval': 1.1882071495056152, 'perplexity': 3.281193256378174} 08/31/2021 00:07:18 - INFO - __main__ - Saving model checkpoint 08/31/2021 00:08:12 - INFO - __main__ - Step 60001: {'lr': 0.0003332849486855144, 'samples': 11520192, 'steps': 60000, 'loss/train': 1.2972759008407593} 08/31/2021 00:08:12 - INFO - __main__ - Step 60002: {'lr': 0.0003332799450571975, 'samples': 11520384, 'steps': 60001, 'loss/train': 4.64774751663208} 08/31/2021 00:08:14 - INFO - __main__ - Step 60003: {'lr': 0.0003332749413913558, 'samples': 11520576, 'steps': 60002, 'loss/train': 1.2953698635101318} 08/31/2021 00:08:14 - INFO - __main__ - Step 60004: {'lr': 0.0003332699376879918, 'samples': 11520768, 'steps': 60003, 'loss/train': 0.49881166219711304} 08/31/2021 00:08:15 - INFO - __main__ - Step 60005: {'lr': 0.00033326493394710764, 'samples': 11520960, 'steps': 60004, 'loss/train': 1.5542618036270142} 08/31/2021 00:08:15 - INFO - __main__ - Step 60006: {'lr': 0.0003332599301687056, 'samples': 11521152, 'steps': 60005, 'loss/train': 1.7142119407653809} 08/31/2021 00:08:15 - INFO - __main__ - Step 60007: {'lr': 0.0003332549263527879, 'samples': 11521344, 'steps': 60006, 'loss/train': 1.6181656122207642} 08/31/2021 00:08:17 - INFO - __main__ - Step 60008: {'lr': 0.00033324992249935683, 'samples': 11521536, 'steps': 60007, 'loss/train': 0.0495404489338398} 08/31/2021 00:08:17 - INFO - __main__ - Step 60009: {'lr': 0.00033324491860841455, 'samples': 11521728, 'steps': 60008, 'loss/train': 1.4749304056167603} 08/31/2021 00:08:18 - INFO - __main__ - Step 60010: {'lr': 0.0003332399146799635, 'samples': 11521920, 'steps': 60009, 'loss/train': 1.482228398323059} 08/31/2021 00:08:18 - INFO - __main__ - Step 60011: {'lr': 0.00033323491071400574, 'samples': 11522112, 'steps': 60010, 'loss/train': 1.006319522857666} 08/31/2021 00:08:18 - INFO - __main__ - Step 60012: {'lr': 0.0003332299067105437, 'samples': 11522304, 'steps': 60011, 'loss/train': 1.1756583452224731} 08/31/2021 00:08:20 - INFO - __main__ - Step 60013: {'lr': 0.0003332249026695795, 'samples': 11522496, 'steps': 60012, 'loss/train': 1.9447542428970337} 08/31/2021 00:08:20 - INFO - __main__ - Step 60014: {'lr': 0.00033321989859111547, 'samples': 11522688, 'steps': 60013, 'loss/train': 0.4262857139110565} 08/31/2021 00:08:21 - INFO - __main__ - Step 60015: {'lr': 0.0003332148944751538, 'samples': 11522880, 'steps': 60014, 'loss/train': 1.0019820928573608} 08/31/2021 00:08:21 - INFO - __main__ - Step 60016: {'lr': 0.0003332098903216968, 'samples': 11523072, 'steps': 60015, 'loss/train': 0.10112756490707397} 08/31/2021 00:08:22 - INFO - __main__ - Step 60017: {'lr': 0.00033320488613074666, 'samples': 11523264, 'steps': 60016, 'loss/train': 1.199479103088379} 08/31/2021 00:08:23 - INFO - __main__ - Step 60018: {'lr': 0.00033319988190230575, 'samples': 11523456, 'steps': 60017, 'loss/train': 1.6514631509780884} 08/31/2021 00:08:23 - INFO - __main__ - Step 60019: {'lr': 0.00033319487763637626, 'samples': 11523648, 'steps': 60018, 'loss/train': 1.1836614608764648} 08/31/2021 00:08:24 - INFO - __main__ - Step 60020: {'lr': 0.00033318987333296043, 'samples': 11523840, 'steps': 60019, 'loss/train': 1.260380744934082} 08/31/2021 00:08:24 - INFO - __main__ - Step 60021: {'lr': 0.0003331848689920605, 'samples': 11524032, 'steps': 60020, 'loss/train': 1.5377185344696045} 08/31/2021 00:08:25 - INFO - __main__ - Step 60022: {'lr': 0.0003331798646136788, 'samples': 11524224, 'steps': 60021, 'loss/train': 1.7488408088684082} 08/31/2021 00:08:26 - INFO - __main__ - Step 60023: {'lr': 0.00033317486019781743, 'samples': 11524416, 'steps': 60022, 'loss/train': 1.462122917175293} 08/31/2021 00:08:27 - INFO - __main__ - Step 60024: {'lr': 0.0003331698557444788, 'samples': 11524608, 'steps': 60023, 'loss/train': 1.1569880247116089} 08/31/2021 00:08:27 - INFO - __main__ - Step 60025: {'lr': 0.00033316485125366516, 'samples': 11524800, 'steps': 60024, 'loss/train': 0.7016485333442688} 08/31/2021 00:08:27 - INFO - __main__ - Step 60026: {'lr': 0.00033315984672537875, 'samples': 11524992, 'steps': 60025, 'loss/train': 1.4048203229904175} 08/31/2021 00:08:28 - INFO - __main__ - Step 60027: {'lr': 0.00033315484215962177, 'samples': 11525184, 'steps': 60026, 'loss/train': 0.7508453726768494} 08/31/2021 00:08:28 - INFO - __main__ - Step 60028: {'lr': 0.00033314983755639645, 'samples': 11525376, 'steps': 60027, 'loss/train': 1.4858659505844116} 08/31/2021 00:08:29 - INFO - __main__ - Step 60029: {'lr': 0.00033314483291570506, 'samples': 11525568, 'steps': 60028, 'loss/train': 0.6955882906913757} 08/31/2021 00:08:30 - INFO - __main__ - Step 60030: {'lr': 0.00033313982823755003, 'samples': 11525760, 'steps': 60029, 'loss/train': 0.9450391530990601} 08/31/2021 00:08:30 - INFO - __main__ - Step 60031: {'lr': 0.0003331348235219334, 'samples': 11525952, 'steps': 60030, 'loss/train': 0.6588352918624878} 08/31/2021 00:08:31 - INFO - __main__ - Step 60032: {'lr': 0.0003331298187688575, 'samples': 11526144, 'steps': 60031, 'loss/train': 1.549399733543396} 08/31/2021 00:08:31 - INFO - __main__ - Step 60033: {'lr': 0.0003331248139783246, 'samples': 11526336, 'steps': 60032, 'loss/train': 1.6086046695709229} 08/31/2021 00:08:33 - INFO - __main__ - Step 60034: {'lr': 0.0003331198091503369, 'samples': 11526528, 'steps': 60033, 'loss/train': 0.8546505570411682} 08/31/2021 00:08:34 - INFO - __main__ - Step 60035: {'lr': 0.00033311480428489674, 'samples': 11526720, 'steps': 60034, 'loss/train': 0.3667406141757965} 08/31/2021 00:08:34 - INFO - __main__ - Step 60036: {'lr': 0.0003331097993820063, 'samples': 11526912, 'steps': 60035, 'loss/train': 1.3652185201644897} 08/31/2021 00:08:34 - INFO - __main__ - Step 60037: {'lr': 0.0003331047944416679, 'samples': 11527104, 'steps': 60036, 'loss/train': 0.7326347231864929} 08/31/2021 00:08:35 - INFO - __main__ - Step 60038: {'lr': 0.00033309978946388376, 'samples': 11527296, 'steps': 60037, 'loss/train': 1.674830436706543} 08/31/2021 00:08:36 - INFO - __main__ - Step 60039: {'lr': 0.00033309478444865613, 'samples': 11527488, 'steps': 60038, 'loss/train': 0.09844669699668884} 08/31/2021 00:08:37 - INFO - __main__ - Step 60040: {'lr': 0.00033308977939598727, 'samples': 11527680, 'steps': 60039, 'loss/train': 0.8991588354110718} 08/31/2021 00:08:37 - INFO - __main__ - Step 60041: {'lr': 0.0003330847743058795, 'samples': 11527872, 'steps': 60040, 'loss/train': 0.7903271317481995} 08/31/2021 00:08:37 - INFO - __main__ - Step 60042: {'lr': 0.00033307976917833486, 'samples': 11528064, 'steps': 60041, 'loss/train': 1.7950891256332397} 08/31/2021 00:08:38 - INFO - __main__ - Step 60043: {'lr': 0.0003330747640133558, 'samples': 11528256, 'steps': 60042, 'loss/train': 1.7557862997055054} 08/31/2021 00:08:38 - INFO - __main__ - Step 60044: {'lr': 0.00033306975881094465, 'samples': 11528448, 'steps': 60043, 'loss/train': 1.4198211431503296} 08/31/2021 00:08:40 - INFO - __main__ - Step 60045: {'lr': 0.00033306475357110346, 'samples': 11528640, 'steps': 60044, 'loss/train': 0.6986801028251648} 08/31/2021 00:08:40 - INFO - __main__ - Step 60046: {'lr': 0.00033305974829383464, 'samples': 11528832, 'steps': 60045, 'loss/train': 2.469728469848633} 08/31/2021 00:08:41 - INFO - __main__ - Step 60047: {'lr': 0.0003330547429791403, 'samples': 11529024, 'steps': 60046, 'loss/train': 1.3144723176956177} 08/31/2021 00:08:41 - INFO - __main__ - Step 60048: {'lr': 0.00033304973762702286, 'samples': 11529216, 'steps': 60047, 'loss/train': 1.368259310722351} 08/31/2021 00:08:41 - INFO - __main__ - Step 60049: {'lr': 0.00033304473223748436, 'samples': 11529408, 'steps': 60048, 'loss/train': 0.8613365292549133} 08/31/2021 00:08:43 - INFO - __main__ - Step 60050: {'lr': 0.0003330397268105273, 'samples': 11529600, 'steps': 60049, 'loss/train': 1.1581356525421143} 08/31/2021 00:08:44 - INFO - __main__ - Step 60051: {'lr': 0.00033303472134615377, 'samples': 11529792, 'steps': 60050, 'loss/train': 0.9885343909263611} 08/31/2021 00:08:44 - INFO - __main__ - Step 60052: {'lr': 0.00033302971584436603, 'samples': 11529984, 'steps': 60051, 'loss/train': 0.8095047473907471} 08/31/2021 00:08:45 - INFO - __main__ - Step 60053: {'lr': 0.00033302471030516653, 'samples': 11530176, 'steps': 60052, 'loss/train': 0.7560599446296692} 08/31/2021 00:08:45 - INFO - __main__ - Step 60054: {'lr': 0.00033301970472855724, 'samples': 11530368, 'steps': 60053, 'loss/train': 1.4431241750717163} 08/31/2021 00:08:46 - INFO - __main__ - Step 60055: {'lr': 0.00033301469911454064, 'samples': 11530560, 'steps': 60054, 'loss/train': 0.8499153852462769} 08/31/2021 00:08:47 - INFO - __main__ - Step 60056: {'lr': 0.00033300969346311885, 'samples': 11530752, 'steps': 60055, 'loss/train': 1.5730628967285156} 08/31/2021 00:08:47 - INFO - __main__ - Step 60057: {'lr': 0.00033300468777429414, 'samples': 11530944, 'steps': 60056, 'loss/train': 1.0352609157562256} 08/31/2021 00:08:48 - INFO - __main__ - Step 60058: {'lr': 0.00033299968204806885, 'samples': 11531136, 'steps': 60057, 'loss/train': 1.514284610748291} 08/31/2021 00:08:48 - INFO - __main__ - Step 60059: {'lr': 0.0003329946762844452, 'samples': 11531328, 'steps': 60058, 'loss/train': 1.1267112493515015} 08/31/2021 00:08:49 - INFO - __main__ - Step 60060: {'lr': 0.00033298967048342535, 'samples': 11531520, 'steps': 60059, 'loss/train': 1.2298067808151245} 08/31/2021 00:08:50 - INFO - __main__ - Step 60061: {'lr': 0.0003329846646450117, 'samples': 11531712, 'steps': 60060, 'loss/train': 1.6344356536865234} 08/31/2021 00:08:50 - INFO - __main__ - Step 60062: {'lr': 0.00033297965876920646, 'samples': 11531904, 'steps': 60061, 'loss/train': 1.468831181526184} 08/31/2021 00:08:50 - INFO - __main__ - Step 60063: {'lr': 0.0003329746528560118, 'samples': 11532096, 'steps': 60062, 'loss/train': 2.2605841159820557} 08/31/2021 00:08:51 - INFO - __main__ - Step 60064: {'lr': 0.00033296964690543007, 'samples': 11532288, 'steps': 60063, 'loss/train': 0.9294488430023193} 08/31/2021 00:08:52 - INFO - __main__ - Step 60065: {'lr': 0.00033296464091746346, 'samples': 11532480, 'steps': 60064, 'loss/train': 1.3387190103530884} 08/31/2021 00:08:53 - INFO - __main__ - Step 60066: {'lr': 0.0003329596348921144, 'samples': 11532672, 'steps': 60065, 'loss/train': 1.3215045928955078} 08/31/2021 00:08:53 - INFO - __main__ - Step 60067: {'lr': 0.0003329546288293849, 'samples': 11532864, 'steps': 60066, 'loss/train': 1.2913378477096558} 08/31/2021 00:08:53 - INFO - __main__ - Step 60068: {'lr': 0.0003329496227292773, 'samples': 11533056, 'steps': 60067, 'loss/train': 1.1616389751434326} 08/31/2021 00:08:54 - INFO - __main__ - Step 60069: {'lr': 0.0003329446165917939, 'samples': 11533248, 'steps': 60068, 'loss/train': 0.7035391330718994} 08/31/2021 00:08:55 - INFO - __main__ - Step 60070: {'lr': 0.00033293961041693697, 'samples': 11533440, 'steps': 60069, 'loss/train': 1.0431679487228394} 08/31/2021 00:08:56 - INFO - __main__ - Step 60071: {'lr': 0.00033293460420470873, 'samples': 11533632, 'steps': 60070, 'loss/train': 0.8371301293373108} 08/31/2021 00:08:56 - INFO - __main__ - Step 60072: {'lr': 0.0003329295979551114, 'samples': 11533824, 'steps': 60071, 'loss/train': 1.6500439643859863} 08/31/2021 00:08:57 - INFO - __main__ - Step 60073: {'lr': 0.0003329245916681473, 'samples': 11534016, 'steps': 60072, 'loss/train': 1.0213032960891724} 08/31/2021 00:08:57 - INFO - __main__ - Step 60074: {'lr': 0.00033291958534381865, 'samples': 11534208, 'steps': 60073, 'loss/train': 0.6346418857574463} 08/31/2021 00:08:58 - INFO - __main__ - Step 60075: {'lr': 0.0003329145789821277, 'samples': 11534400, 'steps': 60074, 'loss/train': 0.9433410167694092} 08/31/2021 00:08:59 - INFO - __main__ - Step 60076: {'lr': 0.00033290957258307676, 'samples': 11534592, 'steps': 60075, 'loss/train': 0.033422160893678665} 08/31/2021 00:08:59 - INFO - __main__ - Step 60077: {'lr': 0.00033290456614666804, 'samples': 11534784, 'steps': 60076, 'loss/train': 1.6570587158203125} 08/31/2021 00:09:00 - INFO - __main__ - Step 60078: {'lr': 0.0003328995596729038, 'samples': 11534976, 'steps': 60077, 'loss/train': 0.94438636302948} 08/31/2021 00:09:00 - INFO - __main__ - Step 60079: {'lr': 0.00033289455316178626, 'samples': 11535168, 'steps': 60078, 'loss/train': 0.3913606107234955} 08/31/2021 00:09:01 - INFO - __main__ - Step 60080: {'lr': 0.00033288954661331776, 'samples': 11535360, 'steps': 60079, 'loss/train': 0.7851139903068542} 08/31/2021 00:09:02 - INFO - __main__ - Step 60081: {'lr': 0.00033288454002750045, 'samples': 11535552, 'steps': 60080, 'loss/train': 0.2262125015258789} 08/31/2021 00:09:02 - INFO - __main__ - Step 60082: {'lr': 0.0003328795334043367, 'samples': 11535744, 'steps': 60081, 'loss/train': 1.4178731441497803} 08/31/2021 00:09:03 - INFO - __main__ - Step 60083: {'lr': 0.00033287452674382866, 'samples': 11535936, 'steps': 60082, 'loss/train': 1.2387561798095703} 08/31/2021 00:09:03 - INFO - __main__ - Step 60084: {'lr': 0.0003328695200459787, 'samples': 11536128, 'steps': 60083, 'loss/train': 1.1196649074554443} 08/31/2021 00:09:04 - INFO - __main__ - Step 60085: {'lr': 0.00033286451331078894, 'samples': 11536320, 'steps': 60084, 'loss/train': 1.6934295892715454} 08/31/2021 00:09:05 - INFO - __main__ - Step 60086: {'lr': 0.0003328595065382618, 'samples': 11536512, 'steps': 60085, 'loss/train': 1.2111176252365112} 08/31/2021 00:09:05 - INFO - __main__ - Step 60087: {'lr': 0.00033285449972839944, 'samples': 11536704, 'steps': 60086, 'loss/train': 1.3483394384384155} 08/31/2021 00:09:06 - INFO - __main__ - Step 60088: {'lr': 0.00033284949288120403, 'samples': 11536896, 'steps': 60087, 'loss/train': 1.4528834819793701} 08/31/2021 00:09:06 - INFO - __main__ - Step 60089: {'lr': 0.00033284448599667796, 'samples': 11537088, 'steps': 60088, 'loss/train': 1.2051458358764648} 08/31/2021 00:09:07 - INFO - __main__ - Step 60090: {'lr': 0.0003328394790748234, 'samples': 11537280, 'steps': 60089, 'loss/train': 1.454270362854004} 08/31/2021 00:09:08 - INFO - __main__ - Step 60091: {'lr': 0.0003328344721156427, 'samples': 11537472, 'steps': 60090, 'loss/train': 1.2128543853759766} 08/31/2021 00:09:08 - INFO - __main__ - Step 60092: {'lr': 0.00033282946511913806, 'samples': 11537664, 'steps': 60091, 'loss/train': 1.510218620300293} 08/31/2021 00:09:09 - INFO - __main__ - Step 60093: {'lr': 0.0003328244580853118, 'samples': 11537856, 'steps': 60092, 'loss/train': 1.6353236436843872} 08/31/2021 00:09:09 - INFO - __main__ - Step 60094: {'lr': 0.00033281945101416605, 'samples': 11538048, 'steps': 60093, 'loss/train': 1.304059624671936} 08/31/2021 00:09:09 - INFO - __main__ - Step 60095: {'lr': 0.00033281444390570317, 'samples': 11538240, 'steps': 60094, 'loss/train': 1.6399394273757935} 08/31/2021 00:09:11 - INFO - __main__ - Step 60096: {'lr': 0.0003328094367599253, 'samples': 11538432, 'steps': 60095, 'loss/train': 1.213486909866333} 08/31/2021 00:09:11 - INFO - __main__ - Step 60097: {'lr': 0.0003328044295768349, 'samples': 11538624, 'steps': 60096, 'loss/train': 1.2678625583648682} 08/31/2021 00:09:12 - INFO - __main__ - Step 60098: {'lr': 0.00033279942235643395, 'samples': 11538816, 'steps': 60097, 'loss/train': 1.038098692893982} 08/31/2021 00:09:12 - INFO - __main__ - Step 60099: {'lr': 0.00033279441509872495, 'samples': 11539008, 'steps': 60098, 'loss/train': 1.3335622549057007} 08/31/2021 00:09:12 - INFO - __main__ - Step 60100: {'lr': 0.0003327894078037101, 'samples': 11539200, 'steps': 60099, 'loss/train': 1.2306169271469116} 08/31/2021 00:09:14 - INFO - __main__ - Step 60101: {'lr': 0.0003327844004713916, 'samples': 11539392, 'steps': 60100, 'loss/train': 1.4174306392669678} 08/31/2021 00:09:14 - INFO - __main__ - Step 60102: {'lr': 0.0003327793931017716, 'samples': 11539584, 'steps': 60101, 'loss/train': 1.6573516130447388} 08/31/2021 00:09:14 - INFO - __main__ - Step 60103: {'lr': 0.0003327743856948526, 'samples': 11539776, 'steps': 60102, 'loss/train': 2.409411907196045} 08/31/2021 00:09:15 - INFO - __main__ - Step 60104: {'lr': 0.00033276937825063677, 'samples': 11539968, 'steps': 60103, 'loss/train': 1.160085678100586} 08/31/2021 00:09:15 - INFO - __main__ - Step 60105: {'lr': 0.0003327643707691263, 'samples': 11540160, 'steps': 60104, 'loss/train': 1.0521042346954346} 08/31/2021 00:09:17 - INFO - __main__ - Step 60106: {'lr': 0.00033275936325032345, 'samples': 11540352, 'steps': 60105, 'loss/train': 1.5557016134262085} 08/31/2021 00:09:18 - INFO - __main__ - Step 60107: {'lr': 0.0003327543556942305, 'samples': 11540544, 'steps': 60106, 'loss/train': 1.1395726203918457} 08/31/2021 00:09:18 - INFO - __main__ - Step 60108: {'lr': 0.00033274934810084976, 'samples': 11540736, 'steps': 60107, 'loss/train': 1.4974645376205444} 08/31/2021 00:09:18 - INFO - __main__ - Step 60109: {'lr': 0.0003327443404701834, 'samples': 11540928, 'steps': 60108, 'loss/train': 0.6820330619812012} 08/31/2021 00:09:19 - INFO - __main__ - Step 60110: {'lr': 0.0003327393328022337, 'samples': 11541120, 'steps': 60109, 'loss/train': 1.1678228378295898} 08/31/2021 00:09:21 - INFO - __main__ - Step 60111: {'lr': 0.0003327343250970031, 'samples': 11541312, 'steps': 60110, 'loss/train': 1.1418994665145874} 08/31/2021 00:09:21 - INFO - __main__ - Step 60112: {'lr': 0.0003327293173544935, 'samples': 11541504, 'steps': 60111, 'loss/train': 1.3388363122940063} 08/31/2021 00:09:21 - INFO - __main__ - Step 60113: {'lr': 0.00033272430957470746, 'samples': 11541696, 'steps': 60112, 'loss/train': 1.0505011081695557} 08/31/2021 00:09:22 - INFO - __main__ - Step 60114: {'lr': 0.000332719301757647, 'samples': 11541888, 'steps': 60113, 'loss/train': 0.07528826594352722} 08/31/2021 00:09:22 - INFO - __main__ - Step 60115: {'lr': 0.00033271429390331457, 'samples': 11542080, 'steps': 60114, 'loss/train': 1.2715234756469727} 08/31/2021 00:09:23 - INFO - __main__ - Step 60116: {'lr': 0.0003327092860117124, 'samples': 11542272, 'steps': 60115, 'loss/train': 1.5777912139892578} 08/31/2021 00:09:24 - INFO - __main__ - Step 60117: {'lr': 0.00033270427808284263, 'samples': 11542464, 'steps': 60116, 'loss/train': 0.6261931657791138} 08/31/2021 00:09:24 - INFO - __main__ - Step 60118: {'lr': 0.00033269927011670764, 'samples': 11542656, 'steps': 60117, 'loss/train': 1.0921987295150757} 08/31/2021 00:09:25 - INFO - __main__ - Step 60119: {'lr': 0.0003326942621133096, 'samples': 11542848, 'steps': 60118, 'loss/train': 1.6336169242858887} 08/31/2021 00:09:25 - INFO - __main__ - Step 60120: {'lr': 0.00033268925407265083, 'samples': 11543040, 'steps': 60119, 'loss/train': 1.0872206687927246} 08/31/2021 00:09:26 - INFO - __main__ - Step 60121: {'lr': 0.0003326842459947335, 'samples': 11543232, 'steps': 60120, 'loss/train': 1.1955230236053467} 08/31/2021 00:09:27 - INFO - __main__ - Step 60122: {'lr': 0.00033267923787956, 'samples': 11543424, 'steps': 60121, 'loss/train': 1.3193414211273193} 08/31/2021 00:09:27 - INFO - __main__ - Step 60123: {'lr': 0.0003326742297271325, 'samples': 11543616, 'steps': 60122, 'loss/train': 0.9418550729751587} 08/31/2021 00:09:28 - INFO - __main__ - Step 60124: {'lr': 0.0003326692215374532, 'samples': 11543808, 'steps': 60123, 'loss/train': 1.8475033044815063} 08/31/2021 00:09:28 - INFO - __main__ - Step 60125: {'lr': 0.0003326642133105245, 'samples': 11544000, 'steps': 60124, 'loss/train': 1.2618434429168701} 08/31/2021 00:09:29 - INFO - __main__ - Step 60126: {'lr': 0.0003326592050463485, 'samples': 11544192, 'steps': 60125, 'loss/train': 0.8485507369041443} 08/31/2021 00:09:30 - INFO - __main__ - Step 60127: {'lr': 0.00033265419674492763, 'samples': 11544384, 'steps': 60126, 'loss/train': 1.478633999824524} 08/31/2021 00:09:30 - INFO - __main__ - Step 60128: {'lr': 0.000332649188406264, 'samples': 11544576, 'steps': 60127, 'loss/train': 0.7242812514305115} 08/31/2021 00:09:31 - INFO - __main__ - Step 60129: {'lr': 0.00033264418003035997, 'samples': 11544768, 'steps': 60128, 'loss/train': 1.6428250074386597} 08/31/2021 00:09:31 - INFO - __main__ - Step 60130: {'lr': 0.0003326391716172177, 'samples': 11544960, 'steps': 60129, 'loss/train': 0.9529979825019836} 08/31/2021 00:09:33 - INFO - __main__ - Step 60131: {'lr': 0.00033263416316683947, 'samples': 11545152, 'steps': 60130, 'loss/train': 1.4649274349212646} 08/31/2021 00:09:33 - INFO - __main__ - Step 60132: {'lr': 0.0003326291546792276, 'samples': 11545344, 'steps': 60131, 'loss/train': 2.0348055362701416} 08/31/2021 00:09:33 - INFO - __main__ - Step 60133: {'lr': 0.00033262414615438434, 'samples': 11545536, 'steps': 60132, 'loss/train': 1.2795755863189697} 08/31/2021 00:09:34 - INFO - __main__ - Step 60134: {'lr': 0.0003326191375923119, 'samples': 11545728, 'steps': 60133, 'loss/train': 1.0602686405181885} 08/31/2021 00:09:34 - INFO - __main__ - Step 60135: {'lr': 0.00033261412899301246, 'samples': 11545920, 'steps': 60134, 'loss/train': 1.0414323806762695} 08/31/2021 00:09:35 - INFO - __main__ - Step 60136: {'lr': 0.0003326091203564885, 'samples': 11546112, 'steps': 60135, 'loss/train': 1.3726235628128052} 08/31/2021 00:09:36 - INFO - __main__ - Step 60137: {'lr': 0.00033260411168274206, 'samples': 11546304, 'steps': 60136, 'loss/train': 0.7685718536376953} 08/31/2021 00:09:36 - INFO - __main__ - Step 60138: {'lr': 0.00033259910297177547, 'samples': 11546496, 'steps': 60137, 'loss/train': 1.6121705770492554} 08/31/2021 00:09:37 - INFO - __main__ - Step 60139: {'lr': 0.00033259409422359103, 'samples': 11546688, 'steps': 60138, 'loss/train': 1.1799811124801636} 08/31/2021 00:09:37 - INFO - __main__ - Step 60140: {'lr': 0.000332589085438191, 'samples': 11546880, 'steps': 60139, 'loss/train': 1.1943933963775635} 08/31/2021 00:09:39 - INFO - __main__ - Step 60141: {'lr': 0.0003325840766155776, 'samples': 11547072, 'steps': 60140, 'loss/train': 1.2976558208465576} 08/31/2021 00:09:39 - INFO - __main__ - Step 60142: {'lr': 0.00033257906775575305, 'samples': 11547264, 'steps': 60141, 'loss/train': 0.32158827781677246} 08/31/2021 00:09:39 - INFO - __main__ - Step 60143: {'lr': 0.00033257405885871963, 'samples': 11547456, 'steps': 60142, 'loss/train': 1.211794376373291} 08/31/2021 00:09:40 - INFO - __main__ - Step 60144: {'lr': 0.00033256904992447965, 'samples': 11547648, 'steps': 60143, 'loss/train': 0.737737774848938} 08/31/2021 00:09:40 - INFO - __main__ - Step 60145: {'lr': 0.00033256404095303527, 'samples': 11547840, 'steps': 60144, 'loss/train': 0.21765901148319244} 08/31/2021 00:09:40 - INFO - __main__ - Step 60146: {'lr': 0.0003325590319443889, 'samples': 11548032, 'steps': 60145, 'loss/train': 1.1548829078674316} 08/31/2021 00:09:42 - INFO - __main__ - Step 60147: {'lr': 0.0003325540228985427, 'samples': 11548224, 'steps': 60146, 'loss/train': 1.1916950941085815} 08/31/2021 00:09:43 - INFO - __main__ - Step 60148: {'lr': 0.00033254901381549884, 'samples': 11548416, 'steps': 60147, 'loss/train': 0.7617013454437256} 08/31/2021 00:09:43 - INFO - __main__ - Step 60149: {'lr': 0.00033254400469525974, 'samples': 11548608, 'steps': 60148, 'loss/train': 1.288809061050415} 08/31/2021 00:09:44 - INFO - __main__ - Step 60150: {'lr': 0.0003325389955378276, 'samples': 11548800, 'steps': 60149, 'loss/train': 0.10411245375871658} 08/31/2021 00:09:44 - INFO - __main__ - Step 60151: {'lr': 0.0003325339863432046, 'samples': 11548992, 'steps': 60150, 'loss/train': 0.7179861664772034} 08/31/2021 00:09:46 - INFO - __main__ - Step 60152: {'lr': 0.00033252897711139306, 'samples': 11549184, 'steps': 60151, 'loss/train': 1.4920991659164429} 08/31/2021 00:09:46 - INFO - __main__ - Step 60153: {'lr': 0.00033252396784239535, 'samples': 11549376, 'steps': 60152, 'loss/train': 0.5249976515769958} 08/31/2021 00:09:47 - INFO - __main__ - Step 60154: {'lr': 0.0003325189585362135, 'samples': 11549568, 'steps': 60153, 'loss/train': 0.3324809670448303} 08/31/2021 00:09:47 - INFO - __main__ - Step 60155: {'lr': 0.0003325139491928499, 'samples': 11549760, 'steps': 60154, 'loss/train': 1.6590317487716675} 08/31/2021 00:09:47 - INFO - __main__ - Step 60156: {'lr': 0.0003325089398123068, 'samples': 11549952, 'steps': 60155, 'loss/train': 1.0094221830368042} 08/31/2021 00:09:49 - INFO - __main__ - Step 60157: {'lr': 0.0003325039303945864, 'samples': 11550144, 'steps': 60156, 'loss/train': 0.7263345122337341} 08/31/2021 00:09:50 - INFO - __main__ - Step 60158: {'lr': 0.000332498920939691, 'samples': 11550336, 'steps': 60157, 'loss/train': 1.1035490036010742} 08/31/2021 00:09:50 - INFO - __main__ - Step 60159: {'lr': 0.000332493911447623, 'samples': 11550528, 'steps': 60158, 'loss/train': 1.2705899477005005} 08/31/2021 00:09:51 - INFO - __main__ - Step 60160: {'lr': 0.0003324889019183844, 'samples': 11550720, 'steps': 60159, 'loss/train': 1.480417251586914} 08/31/2021 00:09:51 - INFO - __main__ - Step 60161: {'lr': 0.00033248389235197764, 'samples': 11550912, 'steps': 60160, 'loss/train': 0.8360716104507446} 08/31/2021 00:09:52 - INFO - __main__ - Step 60162: {'lr': 0.00033247888274840485, 'samples': 11551104, 'steps': 60161, 'loss/train': 0.9765027761459351} 08/31/2021 00:09:53 - INFO - __main__ - Step 60163: {'lr': 0.0003324738731076683, 'samples': 11551296, 'steps': 60162, 'loss/train': 0.9496419429779053} 08/31/2021 00:09:53 - INFO - __main__ - Step 60164: {'lr': 0.0003324688634297704, 'samples': 11551488, 'steps': 60163, 'loss/train': 0.8524519801139832} 08/31/2021 00:09:54 - INFO - __main__ - Step 60165: {'lr': 0.0003324638537147132, 'samples': 11551680, 'steps': 60164, 'loss/train': 1.5842492580413818} 08/31/2021 00:09:54 - INFO - __main__ - Step 60166: {'lr': 0.00033245884396249916, 'samples': 11551872, 'steps': 60165, 'loss/train': 1.914107322692871} 08/31/2021 00:09:54 - INFO - __main__ - Step 60167: {'lr': 0.0003324538341731304, 'samples': 11552064, 'steps': 60166, 'loss/train': 0.760219156742096} 08/31/2021 00:09:56 - INFO - __main__ - Step 60168: {'lr': 0.0003324488243466092, 'samples': 11552256, 'steps': 60167, 'loss/train': 1.1035394668579102} 08/31/2021 00:09:56 - INFO - __main__ - Step 60169: {'lr': 0.0003324438144829379, 'samples': 11552448, 'steps': 60168, 'loss/train': 1.0865193605422974} 08/31/2021 00:09:57 - INFO - __main__ - Step 60170: {'lr': 0.0003324388045821186, 'samples': 11552640, 'steps': 60169, 'loss/train': 1.2656662464141846} 08/31/2021 00:09:57 - INFO - __main__ - Step 60171: {'lr': 0.0003324337946441537, 'samples': 11552832, 'steps': 60170, 'loss/train': 1.4522892236709595} 08/31/2021 00:09:57 - INFO - __main__ - Step 60172: {'lr': 0.00033242878466904535, 'samples': 11553024, 'steps': 60171, 'loss/train': 0.9000025987625122} 08/31/2021 00:09:59 - INFO - __main__ - Step 60173: {'lr': 0.00033242377465679583, 'samples': 11553216, 'steps': 60172, 'loss/train': 1.3283611536026} 08/31/2021 00:10:00 - INFO - __main__ - Step 60174: {'lr': 0.0003324187646074076, 'samples': 11553408, 'steps': 60173, 'loss/train': 1.2042791843414307} 08/31/2021 00:10:00 - INFO - __main__ - Step 60175: {'lr': 0.0003324137545208826, 'samples': 11553600, 'steps': 60174, 'loss/train': 1.2529441118240356} 08/31/2021 00:10:00 - INFO - __main__ - Step 60176: {'lr': 0.0003324087443972233, 'samples': 11553792, 'steps': 60175, 'loss/train': 0.7163498997688293} 08/31/2021 00:10:01 - INFO - __main__ - Step 60177: {'lr': 0.0003324037342364319, 'samples': 11553984, 'steps': 60176, 'loss/train': 1.1999297142028809} 08/31/2021 00:10:02 - INFO - __main__ - Step 60178: {'lr': 0.0003323987240385106, 'samples': 11554176, 'steps': 60177, 'loss/train': 0.9774019718170166} 08/31/2021 00:10:03 - INFO - __main__ - Step 60179: {'lr': 0.00033239371380346165, 'samples': 11554368, 'steps': 60178, 'loss/train': 1.6640262603759766} 08/31/2021 00:10:03 - INFO - __main__ - Step 60180: {'lr': 0.0003323887035312875, 'samples': 11554560, 'steps': 60179, 'loss/train': 1.5631481409072876} 08/31/2021 00:10:03 - INFO - __main__ - Step 60181: {'lr': 0.0003323836932219902, 'samples': 11554752, 'steps': 60180, 'loss/train': 3.403134822845459} 08/31/2021 00:10:04 - INFO - __main__ - Step 60182: {'lr': 0.0003323786828755721, 'samples': 11554944, 'steps': 60181, 'loss/train': 1.0378100872039795} 08/31/2021 00:10:05 - INFO - __main__ - Step 60183: {'lr': 0.00033237367249203543, 'samples': 11555136, 'steps': 60182, 'loss/train': 1.2663544416427612} 08/31/2021 00:10:06 - INFO - __main__ - Step 60184: {'lr': 0.0003323686620713824, 'samples': 11555328, 'steps': 60183, 'loss/train': 1.9294840097427368} 08/31/2021 00:10:06 - INFO - __main__ - Step 60185: {'lr': 0.00033236365161361535, 'samples': 11555520, 'steps': 60184, 'loss/train': 1.8616522550582886} 08/31/2021 00:10:06 - INFO - __main__ - Step 60186: {'lr': 0.00033235864111873654, 'samples': 11555712, 'steps': 60185, 'loss/train': 1.6042371988296509} 08/31/2021 00:10:07 - INFO - __main__ - Step 60187: {'lr': 0.00033235363058674826, 'samples': 11555904, 'steps': 60186, 'loss/train': 0.7571687698364258} 08/31/2021 00:10:08 - INFO - __main__ - Step 60188: {'lr': 0.0003323486200176526, 'samples': 11556096, 'steps': 60187, 'loss/train': 1.308175802230835} 08/31/2021 00:10:09 - INFO - __main__ - Step 60189: {'lr': 0.000332343609411452, 'samples': 11556288, 'steps': 60188, 'loss/train': 0.22077259421348572} 08/31/2021 00:10:09 - INFO - __main__ - Step 60190: {'lr': 0.00033233859876814856, 'samples': 11556480, 'steps': 60189, 'loss/train': 1.5308239459991455} 08/31/2021 00:10:09 - INFO - __main__ - Step 60191: {'lr': 0.0003323335880877446, 'samples': 11556672, 'steps': 60190, 'loss/train': 0.9127170443534851} 08/31/2021 00:10:10 - INFO - __main__ - Step 60192: {'lr': 0.00033232857737024244, 'samples': 11556864, 'steps': 60191, 'loss/train': 1.960649013519287} 08/31/2021 00:10:11 - INFO - __main__ - Step 60193: {'lr': 0.00033232356661564436, 'samples': 11557056, 'steps': 60192, 'loss/train': 1.1997768878936768} 08/31/2021 00:10:12 - INFO - __main__ - Step 60194: {'lr': 0.00033231855582395247, 'samples': 11557248, 'steps': 60193, 'loss/train': 1.0303661823272705} 08/31/2021 00:10:12 - INFO - __main__ - Step 60195: {'lr': 0.00033231354499516915, 'samples': 11557440, 'steps': 60194, 'loss/train': 0.9834473729133606} 08/31/2021 00:10:13 - INFO - __main__ - Step 60196: {'lr': 0.00033230853412929664, 'samples': 11557632, 'steps': 60195, 'loss/train': 1.28888738155365} 08/31/2021 00:10:13 - INFO - __main__ - Step 60197: {'lr': 0.00033230352322633703, 'samples': 11557824, 'steps': 60196, 'loss/train': 1.2350497245788574} 08/31/2021 00:10:13 - INFO - __main__ - Step 60198: {'lr': 0.0003322985122862929, 'samples': 11558016, 'steps': 60197, 'loss/train': 4.287916660308838} 08/31/2021 00:10:15 - INFO - __main__ - Step 60199: {'lr': 0.00033229350130916627, 'samples': 11558208, 'steps': 60198, 'loss/train': 1.462287425994873} 08/31/2021 00:10:15 - INFO - __main__ - Step 60200: {'lr': 0.0003322884902949594, 'samples': 11558400, 'steps': 60199, 'loss/train': 1.3029133081436157} 08/31/2021 00:10:15 - INFO - __main__ - Step 60201: {'lr': 0.0003322834792436747, 'samples': 11558592, 'steps': 60200, 'loss/train': 1.4473686218261719} 08/31/2021 00:10:16 - INFO - __main__ - Step 60202: {'lr': 0.00033227846815531424, 'samples': 11558784, 'steps': 60201, 'loss/train': 1.3337373733520508} 08/31/2021 00:10:16 - INFO - __main__ - Step 60203: {'lr': 0.0003322734570298804, 'samples': 11558976, 'steps': 60202, 'loss/train': 1.106595516204834} 08/31/2021 00:10:18 - INFO - __main__ - Step 60204: {'lr': 0.00033226844586737545, 'samples': 11559168, 'steps': 60203, 'loss/train': 1.695377230644226} 08/31/2021 00:10:18 - INFO - __main__ - Step 60205: {'lr': 0.00033226343466780155, 'samples': 11559360, 'steps': 60204, 'loss/train': 1.321352243423462} 08/31/2021 00:10:18 - INFO - __main__ - Step 60206: {'lr': 0.0003322584234311611, 'samples': 11559552, 'steps': 60205, 'loss/train': 1.3192273378372192} 08/31/2021 00:10:19 - INFO - __main__ - Step 60207: {'lr': 0.0003322534121574562, 'samples': 11559744, 'steps': 60206, 'loss/train': 1.3878896236419678} 08/31/2021 00:10:19 - INFO - __main__ - Step 60208: {'lr': 0.0003322484008466892, 'samples': 11559936, 'steps': 60207, 'loss/train': 1.4487552642822266} 08/31/2021 00:10:21 - INFO - __main__ - Step 60209: {'lr': 0.00033224338949886233, 'samples': 11560128, 'steps': 60208, 'loss/train': 0.845102846622467} 08/31/2021 00:10:21 - INFO - __main__ - Step 60210: {'lr': 0.0003322383781139779, 'samples': 11560320, 'steps': 60209, 'loss/train': 1.4197179079055786} 08/31/2021 00:10:22 - INFO - __main__ - Step 60211: {'lr': 0.0003322333666920381, 'samples': 11560512, 'steps': 60210, 'loss/train': 1.659337043762207} 08/31/2021 00:10:22 - INFO - __main__ - Step 60212: {'lr': 0.0003322283552330452, 'samples': 11560704, 'steps': 60211, 'loss/train': 1.293723702430725} 08/31/2021 00:10:22 - INFO - __main__ - Step 60213: {'lr': 0.00033222334373700146, 'samples': 11560896, 'steps': 60212, 'loss/train': 1.1464941501617432} 08/31/2021 00:10:24 - INFO - __main__ - Step 60214: {'lr': 0.00033221833220390925, 'samples': 11561088, 'steps': 60213, 'loss/train': 1.117966651916504} 08/31/2021 00:10:25 - INFO - __main__ - Step 60215: {'lr': 0.00033221332063377066, 'samples': 11561280, 'steps': 60214, 'loss/train': 1.3943637609481812} 08/31/2021 00:10:25 - INFO - __main__ - Step 60216: {'lr': 0.0003322083090265879, 'samples': 11561472, 'steps': 60215, 'loss/train': 1.4071078300476074} 08/31/2021 00:10:25 - INFO - __main__ - Step 60217: {'lr': 0.0003322032973823635, 'samples': 11561664, 'steps': 60216, 'loss/train': 1.1966400146484375} 08/31/2021 00:10:26 - INFO - __main__ - Step 60218: {'lr': 0.0003321982857010995, 'samples': 11561856, 'steps': 60217, 'loss/train': 1.4019486904144287} 08/31/2021 00:10:27 - INFO - __main__ - Step 60219: {'lr': 0.00033219327398279825, 'samples': 11562048, 'steps': 60218, 'loss/train': 1.8193714618682861} 08/31/2021 00:10:28 - INFO - __main__ - Step 60220: {'lr': 0.00033218826222746194, 'samples': 11562240, 'steps': 60219, 'loss/train': 1.4006807804107666} 08/31/2021 00:10:28 - INFO - __main__ - Step 60221: {'lr': 0.00033218325043509297, 'samples': 11562432, 'steps': 60220, 'loss/train': 1.5504953861236572} 08/31/2021 00:10:28 - INFO - __main__ - Step 60222: {'lr': 0.0003321782386056934, 'samples': 11562624, 'steps': 60221, 'loss/train': 1.9871253967285156} 08/31/2021 00:10:29 - INFO - __main__ - Step 60223: {'lr': 0.0003321732267392656, 'samples': 11562816, 'steps': 60222, 'loss/train': 1.3209891319274902} 08/31/2021 00:10:30 - INFO - __main__ - Step 60224: {'lr': 0.0003321682148358118, 'samples': 11563008, 'steps': 60223, 'loss/train': 0.8474820256233215} 08/31/2021 00:10:31 - INFO - __main__ - Step 60225: {'lr': 0.0003321632028953343, 'samples': 11563200, 'steps': 60224, 'loss/train': 1.3612407445907593} 08/31/2021 00:10:31 - INFO - __main__ - Step 60226: {'lr': 0.0003321581909178353, 'samples': 11563392, 'steps': 60225, 'loss/train': 2.175848960876465} 08/31/2021 00:10:31 - INFO - __main__ - Step 60227: {'lr': 0.0003321531789033171, 'samples': 11563584, 'steps': 60226, 'loss/train': 1.2056708335876465} 08/31/2021 00:10:32 - INFO - __main__ - Step 60228: {'lr': 0.00033214816685178195, 'samples': 11563776, 'steps': 60227, 'loss/train': 0.6313652992248535} 08/31/2021 00:10:32 - INFO - __main__ - Step 60229: {'lr': 0.0003321431547632321, 'samples': 11563968, 'steps': 60228, 'loss/train': 1.3936631679534912} 08/31/2021 00:10:33 - INFO - __main__ - Step 60230: {'lr': 0.00033213814263766985, 'samples': 11564160, 'steps': 60229, 'loss/train': 1.6905999183654785} 08/31/2021 00:10:34 - INFO - __main__ - Step 60231: {'lr': 0.0003321331304750973, 'samples': 11564352, 'steps': 60230, 'loss/train': 1.762645959854126} 08/31/2021 00:10:34 - INFO - __main__ - Step 60232: {'lr': 0.00033212811827551693, 'samples': 11564544, 'steps': 60231, 'loss/train': 1.4228452444076538} 08/31/2021 00:10:35 - INFO - __main__ - Step 60233: {'lr': 0.00033212310603893087, 'samples': 11564736, 'steps': 60232, 'loss/train': 1.1680828332901} 08/31/2021 00:10:35 - INFO - __main__ - Step 60234: {'lr': 0.0003321180937653415, 'samples': 11564928, 'steps': 60233, 'loss/train': 0.7829660773277283} 08/31/2021 00:10:37 - INFO - __main__ - Step 60235: {'lr': 0.0003321130814547508, 'samples': 11565120, 'steps': 60234, 'loss/train': 1.4716321229934692} 08/31/2021 00:10:37 - INFO - __main__ - Step 60236: {'lr': 0.00033210806910716136, 'samples': 11565312, 'steps': 60235, 'loss/train': 1.3114255666732788} 08/31/2021 00:10:37 - INFO - __main__ - Step 60237: {'lr': 0.00033210305672257525, 'samples': 11565504, 'steps': 60236, 'loss/train': 1.5797470808029175} 08/31/2021 00:10:38 - INFO - __main__ - Step 60238: {'lr': 0.0003320980443009947, 'samples': 11565696, 'steps': 60237, 'loss/train': 1.3993897438049316} 08/31/2021 00:10:38 - INFO - __main__ - Step 60239: {'lr': 0.00033209303184242214, 'samples': 11565888, 'steps': 60238, 'loss/train': 0.836115837097168} 08/31/2021 00:10:39 - INFO - __main__ - Step 60240: {'lr': 0.00033208801934685975, 'samples': 11566080, 'steps': 60239, 'loss/train': 1.7352356910705566} 08/31/2021 00:10:40 - INFO - __main__ - Step 60241: {'lr': 0.00033208300681430964, 'samples': 11566272, 'steps': 60240, 'loss/train': 1.336983323097229} 08/31/2021 00:10:40 - INFO - __main__ - Step 60242: {'lr': 0.00033207799424477425, 'samples': 11566464, 'steps': 60241, 'loss/train': 0.745293378829956} 08/31/2021 00:10:41 - INFO - __main__ - Step 60243: {'lr': 0.0003320729816382558, 'samples': 11566656, 'steps': 60242, 'loss/train': 1.6232794523239136} 08/31/2021 00:10:41 - INFO - __main__ - Step 60244: {'lr': 0.0003320679689947565, 'samples': 11566848, 'steps': 60243, 'loss/train': 0.1253427267074585} 08/31/2021 00:10:43 - INFO - __main__ - Step 60245: {'lr': 0.0003320629563142787, 'samples': 11567040, 'steps': 60244, 'loss/train': 0.2749100625514984} 08/31/2021 00:10:44 - INFO - __main__ - Step 60246: {'lr': 0.00033205794359682456, 'samples': 11567232, 'steps': 60245, 'loss/train': 1.2620420455932617} 08/31/2021 00:10:44 - INFO - __main__ - Step 60247: {'lr': 0.0003320529308423963, 'samples': 11567424, 'steps': 60246, 'loss/train': 1.0784786939620972} 08/31/2021 00:10:44 - INFO - __main__ - Step 60248: {'lr': 0.00033204791805099636, 'samples': 11567616, 'steps': 60247, 'loss/train': 1.96487557888031} 08/31/2021 00:10:45 - INFO - __main__ - Step 60249: {'lr': 0.00033204290522262684, 'samples': 11567808, 'steps': 60248, 'loss/train': 1.5282940864562988} 08/31/2021 00:10:46 - INFO - __main__ - Step 60250: {'lr': 0.0003320378923572901, 'samples': 11568000, 'steps': 60249, 'loss/train': 1.239259958267212} 08/31/2021 00:10:47 - INFO - __main__ - Step 60251: {'lr': 0.0003320328794549884, 'samples': 11568192, 'steps': 60250, 'loss/train': 1.1194987297058105} 08/31/2021 00:10:47 - INFO - __main__ - Step 60252: {'lr': 0.0003320278665157238, 'samples': 11568384, 'steps': 60251, 'loss/train': 0.04040104150772095} 08/31/2021 00:10:48 - INFO - __main__ - Step 60253: {'lr': 0.0003320228535394988, 'samples': 11568576, 'steps': 60252, 'loss/train': 1.200568437576294} 08/31/2021 00:10:48 - INFO - __main__ - Step 60254: {'lr': 0.0003320178405263156, 'samples': 11568768, 'steps': 60253, 'loss/train': 0.03392427787184715} 08/31/2021 00:10:48 - INFO - __main__ - Step 60255: {'lr': 0.00033201282747617636, 'samples': 11568960, 'steps': 60254, 'loss/train': 0.441148042678833} 08/31/2021 00:10:50 - INFO - __main__ - Step 60256: {'lr': 0.00033200781438908345, 'samples': 11569152, 'steps': 60255, 'loss/train': 1.3545482158660889} 08/31/2021 00:10:50 - INFO - __main__ - Step 60257: {'lr': 0.00033200280126503904, 'samples': 11569344, 'steps': 60256, 'loss/train': 1.0978565216064453} 08/31/2021 00:10:51 - INFO - __main__ - Step 60258: {'lr': 0.00033199778810404546, 'samples': 11569536, 'steps': 60257, 'loss/train': 1.3304052352905273} 08/31/2021 00:10:51 - INFO - __main__ - Step 60259: {'lr': 0.0003319927749061049, 'samples': 11569728, 'steps': 60258, 'loss/train': 1.5412062406539917} 08/31/2021 00:10:51 - INFO - __main__ - Step 60260: {'lr': 0.0003319877616712197, 'samples': 11569920, 'steps': 60259, 'loss/train': 1.4174349308013916} 08/31/2021 00:10:52 - INFO - __main__ - Step 60261: {'lr': 0.0003319827483993921, 'samples': 11570112, 'steps': 60260, 'loss/train': 0.9134895205497742} 08/31/2021 00:10:53 - INFO - __main__ - Step 60262: {'lr': 0.00033197773509062434, 'samples': 11570304, 'steps': 60261, 'loss/train': 1.7960963249206543} 08/31/2021 00:10:54 - INFO - __main__ - Step 60263: {'lr': 0.00033197272174491864, 'samples': 11570496, 'steps': 60262, 'loss/train': 1.3382799625396729} 08/31/2021 00:10:54 - INFO - __main__ - Step 60264: {'lr': 0.0003319677083622773, 'samples': 11570688, 'steps': 60263, 'loss/train': 1.6539627313613892} 08/31/2021 00:10:54 - INFO - __main__ - Step 60265: {'lr': 0.0003319626949427026, 'samples': 11570880, 'steps': 60264, 'loss/train': 1.0526838302612305} 08/31/2021 00:10:55 - INFO - __main__ - Step 60266: {'lr': 0.00033195768148619676, 'samples': 11571072, 'steps': 60265, 'loss/train': 1.0978180170059204} 08/31/2021 00:10:56 - INFO - __main__ - Step 60267: {'lr': 0.000331952667992762, 'samples': 11571264, 'steps': 60266, 'loss/train': 1.2064249515533447} 08/31/2021 00:10:57 - INFO - __main__ - Step 60268: {'lr': 0.0003319476544624007, 'samples': 11571456, 'steps': 60267, 'loss/train': 0.7735380530357361} 08/31/2021 00:10:57 - INFO - __main__ - Step 60269: {'lr': 0.0003319426408951151, 'samples': 11571648, 'steps': 60268, 'loss/train': 0.933678925037384} 08/31/2021 00:10:57 - INFO - __main__ - Step 60270: {'lr': 0.0003319376272909073, 'samples': 11571840, 'steps': 60269, 'loss/train': 0.9170669913291931} 08/31/2021 00:10:58 - INFO - __main__ - Step 60271: {'lr': 0.0003319326136497797, 'samples': 11572032, 'steps': 60270, 'loss/train': 0.7026209831237793} 08/31/2021 00:10:59 - INFO - __main__ - Step 60272: {'lr': 0.00033192759997173455, 'samples': 11572224, 'steps': 60271, 'loss/train': 1.3755789995193481} 08/31/2021 00:11:00 - INFO - __main__ - Step 60273: {'lr': 0.0003319225862567741, 'samples': 11572416, 'steps': 60272, 'loss/train': 0.8568756580352783} 08/31/2021 00:11:00 - INFO - __main__ - Step 60274: {'lr': 0.0003319175725049006, 'samples': 11572608, 'steps': 60273, 'loss/train': 1.1309394836425781} 08/31/2021 00:11:00 - INFO - __main__ - Step 60275: {'lr': 0.00033191255871611625, 'samples': 11572800, 'steps': 60274, 'loss/train': 1.2364755868911743} 08/31/2021 00:11:01 - INFO - __main__ - Step 60276: {'lr': 0.0003319075448904234, 'samples': 11572992, 'steps': 60275, 'loss/train': 1.4485098123550415} 08/31/2021 00:11:02 - INFO - __main__ - Step 60277: {'lr': 0.00033190253102782433, 'samples': 11573184, 'steps': 60276, 'loss/train': 1.458683967590332} 08/31/2021 00:11:03 - INFO - __main__ - Step 60278: {'lr': 0.0003318975171283212, 'samples': 11573376, 'steps': 60277, 'loss/train': 2.39847993850708} 08/31/2021 00:11:03 - INFO - __main__ - Step 60279: {'lr': 0.0003318925031919162, 'samples': 11573568, 'steps': 60278, 'loss/train': 0.33864325284957886} 08/31/2021 00:11:03 - INFO - __main__ - Step 60280: {'lr': 0.00033188748921861186, 'samples': 11573760, 'steps': 60279, 'loss/train': 0.590010941028595} 08/31/2021 00:11:04 - INFO - __main__ - Step 60281: {'lr': 0.00033188247520841025, 'samples': 11573952, 'steps': 60280, 'loss/train': 1.0796841382980347} 08/31/2021 00:11:04 - INFO - __main__ - Step 60282: {'lr': 0.0003318774611613136, 'samples': 11574144, 'steps': 60281, 'loss/train': 1.328955054283142} 08/31/2021 00:11:05 - INFO - __main__ - Step 60283: {'lr': 0.00033187244707732425, 'samples': 11574336, 'steps': 60282, 'loss/train': 1.217310905456543} 08/31/2021 00:11:06 - INFO - __main__ - Step 60284: {'lr': 0.00033186743295644447, 'samples': 11574528, 'steps': 60283, 'loss/train': 1.6464617252349854} 08/31/2021 00:11:06 - INFO - __main__ - Step 60285: {'lr': 0.00033186241879867644, 'samples': 11574720, 'steps': 60284, 'loss/train': 1.449338436126709} 08/31/2021 00:11:07 - INFO - __main__ - Step 60286: {'lr': 0.00033185740460402245, 'samples': 11574912, 'steps': 60285, 'loss/train': 1.3312088251113892} 08/31/2021 00:11:07 - INFO - __main__ - Step 60287: {'lr': 0.0003318523903724849, 'samples': 11575104, 'steps': 60286, 'loss/train': 1.597050428390503} 08/31/2021 00:11:08 - INFO - __main__ - Step 60288: {'lr': 0.00033184737610406583, 'samples': 11575296, 'steps': 60287, 'loss/train': 1.1477980613708496} 08/31/2021 00:11:09 - INFO - __main__ - Step 60289: {'lr': 0.00033184236179876765, 'samples': 11575488, 'steps': 60288, 'loss/train': 1.4914497137069702} 08/31/2021 00:11:09 - INFO - __main__ - Step 60290: {'lr': 0.0003318373474565925, 'samples': 11575680, 'steps': 60289, 'loss/train': 0.26942139863967896} 08/31/2021 00:11:10 - INFO - __main__ - Step 60291: {'lr': 0.0003318323330775427, 'samples': 11575872, 'steps': 60290, 'loss/train': 1.4353026151657104} 08/31/2021 00:11:10 - INFO - __main__ - Step 60292: {'lr': 0.00033182731866162056, 'samples': 11576064, 'steps': 60291, 'loss/train': 0.7990664839744568} 08/31/2021 00:11:12 - INFO - __main__ - Step 60293: {'lr': 0.00033182230420882833, 'samples': 11576256, 'steps': 60292, 'loss/train': 0.8479326367378235} 08/31/2021 00:11:12 - INFO - __main__ - Step 60294: {'lr': 0.00033181728971916813, 'samples': 11576448, 'steps': 60293, 'loss/train': 1.309434175491333} 08/31/2021 00:11:12 - INFO - __main__ - Step 60295: {'lr': 0.0003318122751926424, 'samples': 11576640, 'steps': 60294, 'loss/train': 1.2069813013076782} 08/31/2021 00:11:13 - INFO - __main__ - Step 60296: {'lr': 0.0003318072606292533, 'samples': 11576832, 'steps': 60295, 'loss/train': 1.4196017980575562} 08/31/2021 00:11:13 - INFO - __main__ - Step 60297: {'lr': 0.0003318022460290031, 'samples': 11577024, 'steps': 60296, 'loss/train': 1.4089969396591187} 08/31/2021 00:11:14 - INFO - __main__ - Step 60298: {'lr': 0.00033179723139189403, 'samples': 11577216, 'steps': 60297, 'loss/train': 1.336656928062439} 08/31/2021 00:11:15 - INFO - __main__ - Step 60299: {'lr': 0.00033179221671792846, 'samples': 11577408, 'steps': 60298, 'loss/train': 0.6161110401153564} 08/31/2021 00:11:15 - INFO - __main__ - Step 60300: {'lr': 0.0003317872020071085, 'samples': 11577600, 'steps': 60299, 'loss/train': 1.0466936826705933} 08/31/2021 00:11:16 - INFO - __main__ - Step 60301: {'lr': 0.00033178218725943666, 'samples': 11577792, 'steps': 60300, 'loss/train': 1.2039142847061157} 08/31/2021 00:11:16 - INFO - __main__ - Step 60302: {'lr': 0.0003317771724749149, 'samples': 11577984, 'steps': 60301, 'loss/train': 1.341113567352295} 08/31/2021 00:11:16 - INFO - __main__ - Step 60303: {'lr': 0.0003317721576535456, 'samples': 11578176, 'steps': 60302, 'loss/train': 1.5836873054504395} 08/31/2021 00:11:18 - INFO - __main__ - Step 60304: {'lr': 0.00033176714279533107, 'samples': 11578368, 'steps': 60303, 'loss/train': 1.4137672185897827} 08/31/2021 00:11:19 - INFO - __main__ - Step 60305: {'lr': 0.0003317621279002734, 'samples': 11578560, 'steps': 60304, 'loss/train': 1.700409173965454} 08/31/2021 00:11:19 - INFO - __main__ - Step 60306: {'lr': 0.0003317571129683751, 'samples': 11578752, 'steps': 60305, 'loss/train': 1.6068167686462402} 08/31/2021 00:11:20 - INFO - __main__ - Step 60307: {'lr': 0.0003317520979996383, 'samples': 11578944, 'steps': 60306, 'loss/train': 1.4562729597091675} 08/31/2021 00:11:20 - INFO - __main__ - Step 60308: {'lr': 0.0003317470829940653, 'samples': 11579136, 'steps': 60307, 'loss/train': 1.6945327520370483} 08/31/2021 00:11:22 - INFO - __main__ - Step 60309: {'lr': 0.0003317420679516583, 'samples': 11579328, 'steps': 60308, 'loss/train': 1.2346830368041992} 08/31/2021 00:11:22 - INFO - __main__ - Step 60310: {'lr': 0.0003317370528724195, 'samples': 11579520, 'steps': 60309, 'loss/train': 1.838549017906189} 08/31/2021 00:11:23 - INFO - __main__ - Step 60311: {'lr': 0.0003317320377563514, 'samples': 11579712, 'steps': 60310, 'loss/train': 1.2829636335372925} 08/31/2021 00:11:23 - INFO - __main__ - Step 60312: {'lr': 0.0003317270226034559, 'samples': 11579904, 'steps': 60311, 'loss/train': 1.9913313388824463} 08/31/2021 00:11:23 - INFO - __main__ - Step 60313: {'lr': 0.0003317220074137356, 'samples': 11580096, 'steps': 60312, 'loss/train': 1.0334579944610596} 08/31/2021 00:11:24 - INFO - __main__ - Step 60314: {'lr': 0.00033171699218719267, 'samples': 11580288, 'steps': 60313, 'loss/train': 1.7307034730911255} 08/31/2021 00:11:25 - INFO - __main__ - Step 60315: {'lr': 0.00033171197692382926, 'samples': 11580480, 'steps': 60314, 'loss/train': 1.2682709693908691} 08/31/2021 00:11:26 - INFO - __main__ - Step 60316: {'lr': 0.00033170696162364765, 'samples': 11580672, 'steps': 60315, 'loss/train': 0.6465211510658264} 08/31/2021 00:11:26 - INFO - __main__ - Step 60317: {'lr': 0.00033170194628665017, 'samples': 11580864, 'steps': 60316, 'loss/train': 1.4975218772888184} 08/31/2021 00:11:26 - INFO - __main__ - Step 60318: {'lr': 0.0003316969309128391, 'samples': 11581056, 'steps': 60317, 'loss/train': 1.1036548614501953} 08/31/2021 00:11:27 - INFO - __main__ - Step 60319: {'lr': 0.00033169191550221663, 'samples': 11581248, 'steps': 60318, 'loss/train': 1.6645416021347046} 08/31/2021 00:11:28 - INFO - __main__ - Step 60320: {'lr': 0.000331686900054785, 'samples': 11581440, 'steps': 60319, 'loss/train': 1.3431522846221924} 08/31/2021 00:11:28 - INFO - __main__ - Step 60321: {'lr': 0.00033168188457054654, 'samples': 11581632, 'steps': 60320, 'loss/train': 1.122436285018921} 08/31/2021 00:11:29 - INFO - __main__ - Step 60322: {'lr': 0.00033167686904950357, 'samples': 11581824, 'steps': 60321, 'loss/train': 0.8162508010864258} 08/31/2021 00:11:29 - INFO - __main__ - Step 60323: {'lr': 0.00033167185349165817, 'samples': 11582016, 'steps': 60322, 'loss/train': 1.4935452938079834} 08/31/2021 00:11:30 - INFO - __main__ - Step 60324: {'lr': 0.00033166683789701267, 'samples': 11582208, 'steps': 60323, 'loss/train': 1.4199950695037842} 08/31/2021 00:11:31 - INFO - __main__ - Step 60325: {'lr': 0.0003316618222655694, 'samples': 11582400, 'steps': 60324, 'loss/train': 1.3622243404388428} 08/31/2021 00:11:32 - INFO - __main__ - Step 60326: {'lr': 0.00033165680659733054, 'samples': 11582592, 'steps': 60325, 'loss/train': 1.240186095237732} 08/31/2021 00:11:32 - INFO - __main__ - Step 60327: {'lr': 0.00033165179089229846, 'samples': 11582784, 'steps': 60326, 'loss/train': 1.55793297290802} 08/31/2021 00:11:32 - INFO - __main__ - Step 60328: {'lr': 0.00033164677515047533, 'samples': 11582976, 'steps': 60327, 'loss/train': 1.6186213493347168} 08/31/2021 00:11:33 - INFO - __main__ - Step 60329: {'lr': 0.0003316417593718634, 'samples': 11583168, 'steps': 60328, 'loss/train': 1.080291509628296} 08/31/2021 00:11:34 - INFO - __main__ - Step 60330: {'lr': 0.0003316367435564649, 'samples': 11583360, 'steps': 60329, 'loss/train': 0.7183910012245178} 08/31/2021 00:11:35 - INFO - __main__ - Step 60331: {'lr': 0.0003316317277042822, 'samples': 11583552, 'steps': 60330, 'loss/train': 1.3136295080184937} 08/31/2021 00:11:35 - INFO - __main__ - Step 60332: {'lr': 0.0003316267118153175, 'samples': 11583744, 'steps': 60331, 'loss/train': 1.8518997430801392} 08/31/2021 00:11:35 - INFO - __main__ - Step 60333: {'lr': 0.00033162169588957295, 'samples': 11583936, 'steps': 60332, 'loss/train': 1.163999080657959} 08/31/2021 00:11:36 - INFO - __main__ - Step 60334: {'lr': 0.00033161667992705104, 'samples': 11584128, 'steps': 60333, 'loss/train': 1.0423681735992432} 08/31/2021 00:11:37 - INFO - __main__ - Step 60335: {'lr': 0.0003316116639277539, 'samples': 11584320, 'steps': 60334, 'loss/train': 0.8895910978317261} 08/31/2021 00:11:38 - INFO - __main__ - Step 60336: {'lr': 0.00033160664789168385, 'samples': 11584512, 'steps': 60335, 'loss/train': 3.193119764328003} 08/31/2021 00:11:38 - INFO - __main__ - Step 60337: {'lr': 0.00033160163181884307, 'samples': 11584704, 'steps': 60336, 'loss/train': 1.0169010162353516} 08/31/2021 00:11:39 - INFO - __main__ - Step 60338: {'lr': 0.00033159661570923384, 'samples': 11584896, 'steps': 60337, 'loss/train': 1.174673080444336} 08/31/2021 00:11:39 - INFO - __main__ - Step 60339: {'lr': 0.0003315915995628584, 'samples': 11585088, 'steps': 60338, 'loss/train': 1.3688039779663086} 08/31/2021 00:11:39 - INFO - __main__ - Step 60340: {'lr': 0.000331586583379719, 'samples': 11585280, 'steps': 60339, 'loss/train': 0.6828625798225403} 08/31/2021 00:11:42 - INFO - __main__ - Step 60341: {'lr': 0.0003315815671598181, 'samples': 11585472, 'steps': 60340, 'loss/train': 1.0378942489624023} 08/31/2021 00:11:42 - INFO - __main__ - Step 60342: {'lr': 0.00033157655090315777, 'samples': 11585664, 'steps': 60341, 'loss/train': 1.3874262571334839} 08/31/2021 00:11:43 - INFO - __main__ - Step 60343: {'lr': 0.0003315715346097402, 'samples': 11585856, 'steps': 60342, 'loss/train': 1.4406784772872925} 08/31/2021 00:11:43 - INFO - __main__ - Step 60344: {'lr': 0.0003315665182795678, 'samples': 11586048, 'steps': 60343, 'loss/train': 0.37431472539901733} 08/31/2021 00:11:43 - INFO - __main__ - Step 60345: {'lr': 0.00033156150191264276, 'samples': 11586240, 'steps': 60344, 'loss/train': 0.3436039984226227} 08/31/2021 00:11:44 - INFO - __main__ - Step 60346: {'lr': 0.00033155648550896744, 'samples': 11586432, 'steps': 60345, 'loss/train': 1.2472261190414429} 08/31/2021 00:11:45 - INFO - __main__ - Step 60347: {'lr': 0.000331551469068544, 'samples': 11586624, 'steps': 60346, 'loss/train': 1.5506470203399658} 08/31/2021 00:11:46 - INFO - __main__ - Step 60348: {'lr': 0.00033154645259137475, 'samples': 11586816, 'steps': 60347, 'loss/train': 1.4927746057510376} 08/31/2021 00:11:46 - INFO - __main__ - Step 60349: {'lr': 0.0003315414360774619, 'samples': 11587008, 'steps': 60348, 'loss/train': 1.3477593660354614} 08/31/2021 00:11:46 - INFO - __main__ - Step 60350: {'lr': 0.00033153641952680767, 'samples': 11587200, 'steps': 60349, 'loss/train': 0.8148848414421082} 08/31/2021 00:11:47 - INFO - __main__ - Step 60351: {'lr': 0.00033153140293941445, 'samples': 11587392, 'steps': 60350, 'loss/train': 1.6264551877975464} 08/31/2021 00:11:48 - INFO - __main__ - Step 60352: {'lr': 0.00033152638631528446, 'samples': 11587584, 'steps': 60351, 'loss/train': 1.5322579145431519} 08/31/2021 00:11:49 - INFO - __main__ - Step 60353: {'lr': 0.0003315213696544199, 'samples': 11587776, 'steps': 60352, 'loss/train': 0.3728165030479431} 08/31/2021 00:11:49 - INFO - __main__ - Step 60354: {'lr': 0.00033151635295682307, 'samples': 11587968, 'steps': 60353, 'loss/train': 1.4196499586105347} 08/31/2021 00:11:49 - INFO - __main__ - Step 60355: {'lr': 0.0003315113362224963, 'samples': 11588160, 'steps': 60354, 'loss/train': 1.5698379278182983} 08/31/2021 00:11:50 - INFO - __main__ - Step 60356: {'lr': 0.0003315063194514417, 'samples': 11588352, 'steps': 60355, 'loss/train': 1.9463809728622437} 08/31/2021 00:11:52 - INFO - __main__ - Step 60357: {'lr': 0.00033150130264366165, 'samples': 11588544, 'steps': 60356, 'loss/train': 0.672339677810669} 08/31/2021 00:11:52 - INFO - __main__ - Step 60358: {'lr': 0.00033149628579915835, 'samples': 11588736, 'steps': 60357, 'loss/train': 1.8708930015563965} 08/31/2021 00:11:52 - INFO - __main__ - Step 60359: {'lr': 0.0003314912689179341, 'samples': 11588928, 'steps': 60358, 'loss/train': 1.63127863407135} 08/31/2021 00:11:53 - INFO - __main__ - Step 60360: {'lr': 0.0003314862519999911, 'samples': 11589120, 'steps': 60359, 'loss/train': 1.6937084197998047} 08/31/2021 00:11:53 - INFO - __main__ - Step 60361: {'lr': 0.0003314812350453317, 'samples': 11589312, 'steps': 60360, 'loss/train': 1.251577377319336} 08/31/2021 00:11:55 - INFO - __main__ - Step 60362: {'lr': 0.0003314762180539581, 'samples': 11589504, 'steps': 60361, 'loss/train': 1.838907241821289} 08/31/2021 00:11:55 - INFO - __main__ - Step 60363: {'lr': 0.00033147120102587256, 'samples': 11589696, 'steps': 60362, 'loss/train': 2.5482020378112793} 08/31/2021 00:11:55 - INFO - __main__ - Step 60364: {'lr': 0.00033146618396107737, 'samples': 11589888, 'steps': 60363, 'loss/train': 1.2322988510131836} 08/31/2021 00:11:56 - INFO - __main__ - Step 60365: {'lr': 0.00033146116685957473, 'samples': 11590080, 'steps': 60364, 'loss/train': 1.5653669834136963} 08/31/2021 00:11:56 - INFO - __main__ - Step 60366: {'lr': 0.00033145614972136697, 'samples': 11590272, 'steps': 60365, 'loss/train': 1.6869094371795654} 08/31/2021 00:11:58 - INFO - __main__ - Step 60367: {'lr': 0.0003314511325464563, 'samples': 11590464, 'steps': 60366, 'loss/train': 1.6838195323944092} 08/31/2021 00:11:58 - INFO - __main__ - Step 60368: {'lr': 0.0003314461153348451, 'samples': 11590656, 'steps': 60367, 'loss/train': 0.28776559233665466} 08/31/2021 00:11:59 - INFO - __main__ - Step 60369: {'lr': 0.0003314410980865355, 'samples': 11590848, 'steps': 60368, 'loss/train': 1.2067416906356812} 08/31/2021 00:11:59 - INFO - __main__ - Step 60370: {'lr': 0.00033143608080152975, 'samples': 11591040, 'steps': 60369, 'loss/train': 0.9765161275863647} 08/31/2021 00:11:59 - INFO - __main__ - Step 60371: {'lr': 0.0003314310634798302, 'samples': 11591232, 'steps': 60370, 'loss/train': 1.4381332397460938} 08/31/2021 00:12:00 - INFO - __main__ - Step 60372: {'lr': 0.00033142604612143903, 'samples': 11591424, 'steps': 60371, 'loss/train': 0.049426667392253876} 08/31/2021 00:12:01 - INFO - __main__ - Step 60373: {'lr': 0.0003314210287263586, 'samples': 11591616, 'steps': 60372, 'loss/train': 1.8455766439437866} 08/31/2021 00:12:02 - INFO - __main__ - Step 60374: {'lr': 0.0003314160112945911, 'samples': 11591808, 'steps': 60373, 'loss/train': 0.994685173034668} 08/31/2021 00:12:02 - INFO - __main__ - Step 60375: {'lr': 0.00033141099382613876, 'samples': 11592000, 'steps': 60374, 'loss/train': 1.2110471725463867} 08/31/2021 00:12:02 - INFO - __main__ - Step 60376: {'lr': 0.00033140597632100386, 'samples': 11592192, 'steps': 60375, 'loss/train': 1.4159609079360962} 08/31/2021 00:12:03 - INFO - __main__ - Step 60377: {'lr': 0.0003314009587791887, 'samples': 11592384, 'steps': 60376, 'loss/train': 1.8318697214126587} 08/31/2021 00:12:04 - INFO - __main__ - Step 60378: {'lr': 0.0003313959412006956, 'samples': 11592576, 'steps': 60377, 'loss/train': 1.016021490097046} 08/31/2021 00:12:05 - INFO - __main__ - Step 60379: {'lr': 0.00033139092358552667, 'samples': 11592768, 'steps': 60378, 'loss/train': 0.8370298147201538} 08/31/2021 00:12:05 - INFO - __main__ - Step 60380: {'lr': 0.00033138590593368437, 'samples': 11592960, 'steps': 60379, 'loss/train': 1.8253849744796753} 08/31/2021 00:12:05 - INFO - __main__ - Step 60381: {'lr': 0.00033138088824517066, 'samples': 11593152, 'steps': 60380, 'loss/train': 1.1023796796798706} 08/31/2021 00:12:06 - INFO - __main__ - Step 60382: {'lr': 0.0003313758705199881, 'samples': 11593344, 'steps': 60381, 'loss/train': 1.3106153011322021} 08/31/2021 00:12:07 - INFO - __main__ - Step 60383: {'lr': 0.00033137085275813873, 'samples': 11593536, 'steps': 60382, 'loss/train': 0.8525026440620422} 08/31/2021 00:12:08 - INFO - __main__ - Step 60384: {'lr': 0.00033136583495962496, 'samples': 11593728, 'steps': 60383, 'loss/train': 1.1116852760314941} 08/31/2021 00:12:08 - INFO - __main__ - Step 60385: {'lr': 0.00033136081712444905, 'samples': 11593920, 'steps': 60384, 'loss/train': 1.2298930883407593} 08/31/2021 00:12:09 - INFO - __main__ - Step 60386: {'lr': 0.0003313557992526132, 'samples': 11594112, 'steps': 60385, 'loss/train': 0.8678454756736755} 08/31/2021 00:12:09 - INFO - __main__ - Step 60387: {'lr': 0.00033135078134411956, 'samples': 11594304, 'steps': 60386, 'loss/train': 1.2418711185455322} 08/31/2021 00:12:10 - INFO - __main__ - Step 60388: {'lr': 0.0003313457633989706, 'samples': 11594496, 'steps': 60387, 'loss/train': 1.7272489070892334} 08/31/2021 00:12:11 - INFO - __main__ - Step 60389: {'lr': 0.00033134074541716854, 'samples': 11594688, 'steps': 60388, 'loss/train': 1.8202967643737793} 08/31/2021 00:12:11 - INFO - __main__ - Step 60390: {'lr': 0.00033133572739871546, 'samples': 11594880, 'steps': 60389, 'loss/train': 1.3522862195968628} 08/31/2021 00:12:12 - INFO - __main__ - Step 60391: {'lr': 0.0003313307093436139, 'samples': 11595072, 'steps': 60390, 'loss/train': 1.457590937614441} 08/31/2021 00:12:12 - INFO - __main__ - Step 60392: {'lr': 0.00033132569125186596, 'samples': 11595264, 'steps': 60391, 'loss/train': 1.8065991401672363} 08/31/2021 00:12:13 - INFO - __main__ - Step 60393: {'lr': 0.00033132067312347386, 'samples': 11595456, 'steps': 60392, 'loss/train': 1.474544882774353} 08/31/2021 00:12:14 - INFO - __main__ - Step 60394: {'lr': 0.0003313156549584399, 'samples': 11595648, 'steps': 60393, 'loss/train': 0.6970931887626648} 08/31/2021 00:12:14 - INFO - __main__ - Step 60395: {'lr': 0.0003313106367567664, 'samples': 11595840, 'steps': 60394, 'loss/train': 1.0465571880340576} 08/31/2021 00:12:15 - INFO - __main__ - Step 60396: {'lr': 0.00033130561851845564, 'samples': 11596032, 'steps': 60395, 'loss/train': 1.6268978118896484} 08/31/2021 00:12:15 - INFO - __main__ - Step 60397: {'lr': 0.0003313006002435097, 'samples': 11596224, 'steps': 60396, 'loss/train': 1.3335387706756592} 08/31/2021 00:12:17 - INFO - __main__ - Step 60398: {'lr': 0.00033129558193193103, 'samples': 11596416, 'steps': 60397, 'loss/train': 1.1411972045898438} 08/31/2021 00:12:17 - INFO - __main__ - Step 60399: {'lr': 0.0003312905635837218, 'samples': 11596608, 'steps': 60398, 'loss/train': 2.974416971206665} 08/31/2021 00:12:18 - INFO - __main__ - Step 60400: {'lr': 0.00033128554519888437, 'samples': 11596800, 'steps': 60399, 'loss/train': 1.1877052783966064} 08/31/2021 00:12:18 - INFO - __main__ - Step 60401: {'lr': 0.0003312805267774209, 'samples': 11596992, 'steps': 60400, 'loss/train': 1.4984740018844604} 08/31/2021 00:12:18 - INFO - __main__ - Step 60402: {'lr': 0.0003312755083193337, 'samples': 11597184, 'steps': 60401, 'loss/train': 0.12828083336353302} 08/31/2021 00:12:20 - INFO - __main__ - Step 60403: {'lr': 0.0003312704898246249, 'samples': 11597376, 'steps': 60402, 'loss/train': 0.26412689685821533} 08/31/2021 00:12:20 - INFO - __main__ - Step 60404: {'lr': 0.00033126547129329694, 'samples': 11597568, 'steps': 60403, 'loss/train': 1.203357219696045} 08/31/2021 00:12:21 - INFO - __main__ - Step 60405: {'lr': 0.000331260452725352, 'samples': 11597760, 'steps': 60404, 'loss/train': 1.3144261837005615} 08/31/2021 00:12:21 - INFO - __main__ - Step 60406: {'lr': 0.0003312554341207924, 'samples': 11597952, 'steps': 60405, 'loss/train': 1.2659518718719482} 08/31/2021 00:12:21 - INFO - __main__ - Step 60407: {'lr': 0.0003312504154796203, 'samples': 11598144, 'steps': 60406, 'loss/train': 1.4227607250213623} 08/31/2021 00:12:23 - INFO - __main__ - Step 60408: {'lr': 0.000331245396801838, 'samples': 11598336, 'steps': 60407, 'loss/train': 1.2059197425842285} 08/31/2021 00:12:24 - INFO - __main__ - Step 60409: {'lr': 0.0003312403780874479, 'samples': 11598528, 'steps': 60408, 'loss/train': 1.4765843152999878} 08/31/2021 00:12:24 - INFO - __main__ - Step 60410: {'lr': 0.000331235359336452, 'samples': 11598720, 'steps': 60409, 'loss/train': 1.2210763692855835} 08/31/2021 00:12:24 - INFO - __main__ - Step 60411: {'lr': 0.00033123034054885275, 'samples': 11598912, 'steps': 60410, 'loss/train': 1.6073172092437744} 08/31/2021 00:12:25 - INFO - __main__ - Step 60412: {'lr': 0.0003312253217246524, 'samples': 11599104, 'steps': 60411, 'loss/train': 0.792102038860321} 08/31/2021 00:12:25 - INFO - __main__ - Step 60413: {'lr': 0.0003312203028638531, 'samples': 11599296, 'steps': 60412, 'loss/train': 0.5221032500267029} 08/31/2021 00:12:27 - INFO - __main__ - Step 60414: {'lr': 0.0003312152839664572, 'samples': 11599488, 'steps': 60413, 'loss/train': 1.408699870109558} 08/31/2021 00:12:28 - INFO - __main__ - Step 60415: {'lr': 0.00033121026503246697, 'samples': 11599680, 'steps': 60414, 'loss/train': 0.9591354131698608} 08/31/2021 00:12:28 - INFO - __main__ - Step 60416: {'lr': 0.0003312052460618847, 'samples': 11599872, 'steps': 60415, 'loss/train': 1.2039215564727783} 08/31/2021 00:12:28 - INFO - __main__ - Step 60417: {'lr': 0.0003312002270547125, 'samples': 11600064, 'steps': 60416, 'loss/train': 1.229177474975586} 08/31/2021 00:12:29 - INFO - __main__ - Step 60418: {'lr': 0.0003311952080109528, 'samples': 11600256, 'steps': 60417, 'loss/train': 1.5038683414459229} 08/31/2021 00:12:29 - INFO - __main__ - Step 60419: {'lr': 0.00033119018893060774, 'samples': 11600448, 'steps': 60418, 'loss/train': 1.5189183950424194} 08/31/2021 00:12:31 - INFO - __main__ - Step 60420: {'lr': 0.0003311851698136797, 'samples': 11600640, 'steps': 60419, 'loss/train': 0.7495490312576294} 08/31/2021 00:12:31 - INFO - __main__ - Step 60421: {'lr': 0.00033118015066017085, 'samples': 11600832, 'steps': 60420, 'loss/train': 0.7823761701583862} 08/31/2021 00:12:31 - INFO - __main__ - Step 60422: {'lr': 0.0003311751314700835, 'samples': 11601024, 'steps': 60421, 'loss/train': 1.2178876399993896} 08/31/2021 00:12:32 - INFO - __main__ - Step 60423: {'lr': 0.0003311701122434198, 'samples': 11601216, 'steps': 60422, 'loss/train': 1.9483580589294434} 08/31/2021 00:12:32 - INFO - __main__ - Step 60424: {'lr': 0.00033116509298018217, 'samples': 11601408, 'steps': 60423, 'loss/train': 0.5578188896179199} 08/31/2021 00:12:33 - INFO - __main__ - Step 60425: {'lr': 0.0003311600736803728, 'samples': 11601600, 'steps': 60424, 'loss/train': 0.8236679434776306} 08/31/2021 00:12:34 - INFO - __main__ - Step 60426: {'lr': 0.0003311550543439939, 'samples': 11601792, 'steps': 60425, 'loss/train': 1.149922490119934} 08/31/2021 00:12:34 - INFO - __main__ - Step 60427: {'lr': 0.00033115003497104787, 'samples': 11601984, 'steps': 60426, 'loss/train': 2.199061870574951} 08/31/2021 00:12:35 - INFO - __main__ - Step 60428: {'lr': 0.00033114501556153673, 'samples': 11602176, 'steps': 60427, 'loss/train': 1.4222172498703003} 08/31/2021 00:12:35 - INFO - __main__ - Step 60429: {'lr': 0.0003311399961154631, 'samples': 11602368, 'steps': 60428, 'loss/train': 1.0871350765228271} 08/31/2021 00:12:36 - INFO - __main__ - Step 60430: {'lr': 0.00033113497663282893, 'samples': 11602560, 'steps': 60429, 'loss/train': 1.4562244415283203} 08/31/2021 00:12:37 - INFO - __main__ - Step 60431: {'lr': 0.00033112995711363666, 'samples': 11602752, 'steps': 60430, 'loss/train': 1.3269928693771362} 08/31/2021 00:12:37 - INFO - __main__ - Step 60432: {'lr': 0.0003311249375578884, 'samples': 11602944, 'steps': 60431, 'loss/train': 2.0376150608062744} 08/31/2021 00:12:38 - INFO - __main__ - Step 60433: {'lr': 0.0003311199179655865, 'samples': 11603136, 'steps': 60432, 'loss/train': 1.5448188781738281} 08/31/2021 00:12:38 - INFO - __main__ - Step 60434: {'lr': 0.00033111489833673326, 'samples': 11603328, 'steps': 60433, 'loss/train': 1.3089960813522339} 08/31/2021 00:12:40 - INFO - __main__ - Step 60435: {'lr': 0.00033110987867133085, 'samples': 11603520, 'steps': 60434, 'loss/train': 1.2144715785980225} 08/31/2021 00:12:40 - INFO - __main__ - Step 60436: {'lr': 0.0003311048589693817, 'samples': 11603712, 'steps': 60435, 'loss/train': 1.063226580619812} 08/31/2021 00:12:40 - INFO - __main__ - Step 60437: {'lr': 0.0003310998392308878, 'samples': 11603904, 'steps': 60436, 'loss/train': 1.6190192699432373} 08/31/2021 00:12:41 - INFO - __main__ - Step 60438: {'lr': 0.00033109481945585163, 'samples': 11604096, 'steps': 60437, 'loss/train': 1.2257462739944458} 08/31/2021 00:12:41 - INFO - __main__ - Step 60439: {'lr': 0.0003310897996442754, 'samples': 11604288, 'steps': 60438, 'loss/train': 1.3799394369125366} 08/31/2021 00:12:42 - INFO - __main__ - Step 60440: {'lr': 0.0003310847797961613, 'samples': 11604480, 'steps': 60439, 'loss/train': 1.9235883951187134} 08/31/2021 00:12:43 - INFO - __main__ - Step 60441: {'lr': 0.0003310797599115117, 'samples': 11604672, 'steps': 60440, 'loss/train': 1.6775695085525513} 08/31/2021 00:12:43 - INFO - __main__ - Step 60442: {'lr': 0.0003310747399903288, 'samples': 11604864, 'steps': 60441, 'loss/train': 1.9950459003448486} 08/31/2021 00:12:44 - INFO - __main__ - Step 60443: {'lr': 0.00033106972003261494, 'samples': 11605056, 'steps': 60442, 'loss/train': 1.5072650909423828} 08/31/2021 00:12:44 - INFO - __main__ - Step 60444: {'lr': 0.00033106470003837227, 'samples': 11605248, 'steps': 60443, 'loss/train': 0.8327584862709045} 08/31/2021 00:12:44 - INFO - __main__ - Step 60445: {'lr': 0.000331059680007603, 'samples': 11605440, 'steps': 60444, 'loss/train': 0.14451263844966888} 08/31/2021 00:12:46 - INFO - __main__ - Step 60446: {'lr': 0.0003310546599403096, 'samples': 11605632, 'steps': 60445, 'loss/train': 1.388903021812439} 08/31/2021 00:12:47 - INFO - __main__ - Step 60447: {'lr': 0.00033104963983649415, 'samples': 11605824, 'steps': 60446, 'loss/train': 1.102540135383606} 08/31/2021 00:12:47 - INFO - __main__ - Step 60448: {'lr': 0.0003310446196961591, 'samples': 11606016, 'steps': 60447, 'loss/train': 1.2386173009872437} 08/31/2021 00:12:47 - INFO - __main__ - Step 60449: {'lr': 0.0003310395995193065, 'samples': 11606208, 'steps': 60448, 'loss/train': 0.12193600088357925} 08/31/2021 00:12:48 - INFO - __main__ - Step 60450: {'lr': 0.00033103457930593874, 'samples': 11606400, 'steps': 60449, 'loss/train': 1.696481704711914} 08/31/2021 00:12:49 - INFO - __main__ - Step 60451: {'lr': 0.000331029559056058, 'samples': 11606592, 'steps': 60450, 'loss/train': 1.144974946975708} 08/31/2021 00:12:50 - INFO - __main__ - Step 60452: {'lr': 0.0003310245387696666, 'samples': 11606784, 'steps': 60451, 'loss/train': 1.4007295370101929} 08/31/2021 00:12:50 - INFO - __main__ - Step 60453: {'lr': 0.0003310195184467668, 'samples': 11606976, 'steps': 60452, 'loss/train': 1.0676978826522827} 08/31/2021 00:12:50 - INFO - __main__ - Step 60454: {'lr': 0.0003310144980873609, 'samples': 11607168, 'steps': 60453, 'loss/train': 1.5546892881393433} 08/31/2021 00:12:51 - INFO - __main__ - Step 60455: {'lr': 0.00033100947769145107, 'samples': 11607360, 'steps': 60454, 'loss/train': 1.2304344177246094} 08/31/2021 00:12:52 - INFO - __main__ - Step 60456: {'lr': 0.0003310044572590397, 'samples': 11607552, 'steps': 60455, 'loss/train': 1.2712090015411377} 08/31/2021 00:12:53 - INFO - __main__ - Step 60457: {'lr': 0.0003309994367901289, 'samples': 11607744, 'steps': 60456, 'loss/train': 1.2261570692062378} 08/31/2021 00:12:53 - INFO - __main__ - Step 60458: {'lr': 0.000330994416284721, 'samples': 11607936, 'steps': 60457, 'loss/train': 1.4707269668579102} 08/31/2021 00:12:53 - INFO - __main__ - Step 60459: {'lr': 0.0003309893957428183, 'samples': 11608128, 'steps': 60458, 'loss/train': 0.9982607960700989} 08/31/2021 00:12:54 - INFO - __main__ - Step 60460: {'lr': 0.00033098437516442295, 'samples': 11608320, 'steps': 60459, 'loss/train': 1.5477131605148315} 08/31/2021 00:12:55 - INFO - __main__ - Step 60461: {'lr': 0.00033097935454953737, 'samples': 11608512, 'steps': 60460, 'loss/train': 1.7032121419906616} 08/31/2021 00:12:56 - INFO - __main__ - Step 60462: {'lr': 0.00033097433389816367, 'samples': 11608704, 'steps': 60461, 'loss/train': 1.4048399925231934} 08/31/2021 00:12:56 - INFO - __main__ - Step 60463: {'lr': 0.00033096931321030434, 'samples': 11608896, 'steps': 60462, 'loss/train': 1.2823371887207031} 08/31/2021 00:12:56 - INFO - __main__ - Step 60464: {'lr': 0.00033096429248596134, 'samples': 11609088, 'steps': 60463, 'loss/train': 1.4811387062072754} 08/31/2021 00:12:57 - INFO - __main__ - Step 60465: {'lr': 0.0003309592717251371, 'samples': 11609280, 'steps': 60464, 'loss/train': 1.391880989074707} 08/31/2021 00:12:59 - INFO - __main__ - Step 60466: {'lr': 0.00033095425092783385, 'samples': 11609472, 'steps': 60465, 'loss/train': 1.3268910646438599} 08/31/2021 00:12:59 - INFO - __main__ - Step 60467: {'lr': 0.0003309492300940539, 'samples': 11609664, 'steps': 60466, 'loss/train': 1.5366034507751465} 08/31/2021 00:12:59 - INFO - __main__ - Step 60468: {'lr': 0.0003309442092237995, 'samples': 11609856, 'steps': 60467, 'loss/train': 2.1999599933624268} 08/31/2021 00:13:00 - INFO - __main__ - Step 60469: {'lr': 0.0003309391883170729, 'samples': 11610048, 'steps': 60468, 'loss/train': 0.964584469795227} 08/31/2021 00:13:00 - INFO - __main__ - Step 60470: {'lr': 0.0003309341673738763, 'samples': 11610240, 'steps': 60469, 'loss/train': 1.389843463897705} 08/31/2021 00:13:02 - INFO - __main__ - Step 60471: {'lr': 0.000330929146394212, 'samples': 11610432, 'steps': 60470, 'loss/train': 0.7556208968162537} 08/31/2021 00:13:02 - INFO - __main__ - Step 60472: {'lr': 0.0003309241253780823, 'samples': 11610624, 'steps': 60471, 'loss/train': 1.0427144765853882} 08/31/2021 00:13:02 - INFO - __main__ - Step 60473: {'lr': 0.00033091910432548943, 'samples': 11610816, 'steps': 60472, 'loss/train': 0.06130722910165787} 08/31/2021 00:13:03 - INFO - __main__ - Step 60474: {'lr': 0.00033091408323643567, 'samples': 11611008, 'steps': 60473, 'loss/train': 0.8202654123306274} 08/31/2021 00:13:03 - INFO - __main__ - Step 60475: {'lr': 0.00033090906211092323, 'samples': 11611200, 'steps': 60474, 'loss/train': 0.8919296860694885} 08/31/2021 00:13:05 - INFO - __main__ - Step 60476: {'lr': 0.00033090404094895454, 'samples': 11611392, 'steps': 60475, 'loss/train': 0.6880930662155151} 08/31/2021 00:13:05 - INFO - __main__ - Step 60477: {'lr': 0.0003308990197505316, 'samples': 11611584, 'steps': 60476, 'loss/train': 0.9579542875289917} 08/31/2021 00:13:05 - INFO - __main__ - Step 60478: {'lr': 0.0003308939985156569, 'samples': 11611776, 'steps': 60477, 'loss/train': 0.8220546841621399} 08/31/2021 00:13:06 - INFO - __main__ - Step 60479: {'lr': 0.00033088897724433254, 'samples': 11611968, 'steps': 60478, 'loss/train': 1.678728461265564} 08/31/2021 00:13:06 - INFO - __main__ - Step 60480: {'lr': 0.0003308839559365609, 'samples': 11612160, 'steps': 60479, 'loss/train': 1.0802751779556274} 08/31/2021 00:13:06 - INFO - __main__ - Step 60481: {'lr': 0.0003308789345923442, 'samples': 11612352, 'steps': 60480, 'loss/train': 1.48484468460083} 08/31/2021 00:13:08 - INFO - __main__ - Step 60482: {'lr': 0.0003308739132116847, 'samples': 11612544, 'steps': 60481, 'loss/train': 1.0155105590820312} 08/31/2021 00:13:09 - INFO - __main__ - Step 60483: {'lr': 0.0003308688917945847, 'samples': 11612736, 'steps': 60482, 'loss/train': 0.6625715494155884} 08/31/2021 00:13:09 - INFO - __main__ - Step 60484: {'lr': 0.00033086387034104634, 'samples': 11612928, 'steps': 60483, 'loss/train': 0.025800196453928947} 08/31/2021 00:13:10 - INFO - __main__ - Step 60485: {'lr': 0.00033085884885107196, 'samples': 11613120, 'steps': 60484, 'loss/train': 0.80370032787323} 08/31/2021 00:13:10 - INFO - __main__ - Step 60486: {'lr': 0.0003308538273246639, 'samples': 11613312, 'steps': 60485, 'loss/train': 1.4681864976882935} 08/31/2021 00:13:10 - INFO - __main__ - Step 60487: {'lr': 0.0003308488057618243, 'samples': 11613504, 'steps': 60486, 'loss/train': 1.3346201181411743} 08/31/2021 00:13:12 - INFO - __main__ - Step 60488: {'lr': 0.0003308437841625555, 'samples': 11613696, 'steps': 60487, 'loss/train': 2.396306037902832} 08/31/2021 00:13:12 - INFO - __main__ - Step 60489: {'lr': 0.00033083876252685976, 'samples': 11613888, 'steps': 60488, 'loss/train': 0.8303453326225281} 08/31/2021 00:13:13 - INFO - __main__ - Step 60490: {'lr': 0.0003308337408547393, 'samples': 11614080, 'steps': 60489, 'loss/train': 1.465124249458313} 08/31/2021 00:13:13 - INFO - __main__ - Step 60491: {'lr': 0.00033082871914619645, 'samples': 11614272, 'steps': 60490, 'loss/train': 1.1517164707183838} 08/31/2021 00:13:13 - INFO - __main__ - Step 60492: {'lr': 0.00033082369740123333, 'samples': 11614464, 'steps': 60491, 'loss/train': 0.8270076513290405} 08/31/2021 00:13:15 - INFO - __main__ - Step 60493: {'lr': 0.00033081867561985236, 'samples': 11614656, 'steps': 60492, 'loss/train': 1.235714316368103} 08/31/2021 00:13:15 - INFO - __main__ - Step 60494: {'lr': 0.00033081365380205574, 'samples': 11614848, 'steps': 60493, 'loss/train': 1.4502731561660767} 08/31/2021 00:13:16 - INFO - __main__ - Step 60495: {'lr': 0.0003308086319478457, 'samples': 11615040, 'steps': 60494, 'loss/train': 1.5684279203414917} 08/31/2021 00:13:16 - INFO - __main__ - Step 60496: {'lr': 0.0003308036100572246, 'samples': 11615232, 'steps': 60495, 'loss/train': 0.9025578498840332} 08/31/2021 00:13:16 - INFO - __main__ - Step 60497: {'lr': 0.00033079858813019465, 'samples': 11615424, 'steps': 60496, 'loss/train': 0.8225917816162109} 08/31/2021 00:13:18 - INFO - __main__ - Step 60498: {'lr': 0.000330793566166758, 'samples': 11615616, 'steps': 60497, 'loss/train': 1.3306248188018799} 08/31/2021 00:13:18 - INFO - __main__ - Step 60499: {'lr': 0.0003307885441669171, 'samples': 11615808, 'steps': 60498, 'loss/train': 0.5718063116073608} 08/31/2021 00:13:19 - INFO - __main__ - Step 60500: {'lr': 0.0003307835221306741, 'samples': 11616000, 'steps': 60499, 'loss/train': 1.384158968925476} 08/31/2021 00:13:19 - INFO - __main__ - Step 60501: {'lr': 0.0003307785000580313, 'samples': 11616192, 'steps': 60500, 'loss/train': 1.593672513961792} 08/31/2021 00:13:19 - INFO - __main__ - Step 60502: {'lr': 0.00033077347794899096, 'samples': 11616384, 'steps': 60501, 'loss/train': 1.5521025657653809} 08/31/2021 00:13:21 - INFO - __main__ - Step 60503: {'lr': 0.00033076845580355533, 'samples': 11616576, 'steps': 60502, 'loss/train': 0.3624441921710968} 08/31/2021 00:13:21 - INFO - __main__ - Step 60504: {'lr': 0.00033076343362172666, 'samples': 11616768, 'steps': 60503, 'loss/train': 1.5851473808288574} 08/31/2021 00:13:22 - INFO - __main__ - Step 60505: {'lr': 0.00033075841140350724, 'samples': 11616960, 'steps': 60504, 'loss/train': 1.1970030069351196} 08/31/2021 00:13:22 - INFO - __main__ - Step 60506: {'lr': 0.00033075338914889934, 'samples': 11617152, 'steps': 60505, 'loss/train': 1.1802911758422852} 08/31/2021 00:13:22 - INFO - __main__ - Step 60507: {'lr': 0.00033074836685790523, 'samples': 11617344, 'steps': 60506, 'loss/train': 1.4733142852783203} 08/31/2021 00:13:24 - INFO - __main__ - Step 60508: {'lr': 0.0003307433445305271, 'samples': 11617536, 'steps': 60507, 'loss/train': 1.5139144659042358} 08/31/2021 00:13:24 - INFO - __main__ - Step 60509: {'lr': 0.0003307383221667673, 'samples': 11617728, 'steps': 60508, 'loss/train': 1.203710913658142} 08/31/2021 00:13:25 - INFO - __main__ - Step 60510: {'lr': 0.00033073329976662807, 'samples': 11617920, 'steps': 60509, 'loss/train': 1.4265788793563843} 08/31/2021 00:13:25 - INFO - __main__ - Step 60511: {'lr': 0.00033072827733011164, 'samples': 11618112, 'steps': 60510, 'loss/train': 1.6443067789077759} 08/31/2021 00:13:25 - INFO - __main__ - Step 60512: {'lr': 0.0003307232548572203, 'samples': 11618304, 'steps': 60511, 'loss/train': 1.396070122718811} 08/31/2021 00:13:27 - INFO - __main__ - Step 60513: {'lr': 0.0003307182323479563, 'samples': 11618496, 'steps': 60512, 'loss/train': 0.809962809085846} 08/31/2021 00:13:27 - INFO - __main__ - Step 60514: {'lr': 0.0003307132098023219, 'samples': 11618688, 'steps': 60513, 'loss/train': 1.5171945095062256} 08/31/2021 00:13:28 - INFO - __main__ - Step 60515: {'lr': 0.00033070818722031936, 'samples': 11618880, 'steps': 60514, 'loss/train': 1.0924291610717773} 08/31/2021 00:13:28 - INFO - __main__ - Step 60516: {'lr': 0.00033070316460195106, 'samples': 11619072, 'steps': 60515, 'loss/train': 1.259294033050537} 08/31/2021 00:13:29 - INFO - __main__ - Step 60517: {'lr': 0.00033069814194721905, 'samples': 11619264, 'steps': 60516, 'loss/train': 1.21195387840271} 08/31/2021 00:13:31 - INFO - __main__ - Step 60518: {'lr': 0.0003306931192561257, 'samples': 11619456, 'steps': 60517, 'loss/train': 1.010054588317871} 08/31/2021 00:13:31 - INFO - __main__ - Step 60519: {'lr': 0.0003306880965286734, 'samples': 11619648, 'steps': 60518, 'loss/train': 1.3959003686904907} 08/31/2021 00:13:32 - INFO - __main__ - Step 60520: {'lr': 0.0003306830737648642, 'samples': 11619840, 'steps': 60519, 'loss/train': 0.025668708607554436} 08/31/2021 00:13:32 - INFO - __main__ - Step 60521: {'lr': 0.0003306780509647004, 'samples': 11620032, 'steps': 60520, 'loss/train': 1.2932367324829102} 08/31/2021 00:13:32 - INFO - __main__ - Step 60522: {'lr': 0.0003306730281281843, 'samples': 11620224, 'steps': 60521, 'loss/train': 1.5845367908477783} 08/31/2021 00:13:33 - INFO - __main__ - Step 60523: {'lr': 0.00033066800525531826, 'samples': 11620416, 'steps': 60522, 'loss/train': 1.4490114450454712} 08/31/2021 00:13:34 - INFO - __main__ - Step 60524: {'lr': 0.0003306629823461045, 'samples': 11620608, 'steps': 60523, 'loss/train': 0.10794229805469513} 08/31/2021 00:13:35 - INFO - __main__ - Step 60525: {'lr': 0.0003306579594005452, 'samples': 11620800, 'steps': 60524, 'loss/train': 0.8630304932594299} 08/31/2021 00:13:35 - INFO - __main__ - Step 60526: {'lr': 0.0003306529364186426, 'samples': 11620992, 'steps': 60525, 'loss/train': 1.655598521232605} 08/31/2021 00:13:35 - INFO - __main__ - Step 60527: {'lr': 0.00033064791340039915, 'samples': 11621184, 'steps': 60526, 'loss/train': 1.2752817869186401} 08/31/2021 00:13:36 - INFO - __main__ - Step 60528: {'lr': 0.0003306428903458169, 'samples': 11621376, 'steps': 60527, 'loss/train': 1.0588268041610718} 08/31/2021 00:13:37 - INFO - __main__ - Step 60529: {'lr': 0.0003306378672548982, 'samples': 11621568, 'steps': 60528, 'loss/train': 0.8007386922836304} 08/31/2021 00:13:38 - INFO - __main__ - Step 60530: {'lr': 0.0003306328441276454, 'samples': 11621760, 'steps': 60529, 'loss/train': 1.0762463808059692} 08/31/2021 00:13:38 - INFO - __main__ - Step 60531: {'lr': 0.0003306278209640607, 'samples': 11621952, 'steps': 60530, 'loss/train': 1.1662883758544922} 08/31/2021 00:13:38 - INFO - __main__ - Step 60532: {'lr': 0.0003306227977641463, 'samples': 11622144, 'steps': 60531, 'loss/train': 1.2670129537582397} 08/31/2021 00:13:39 - INFO - __main__ - Step 60533: {'lr': 0.0003306177745279045, 'samples': 11622336, 'steps': 60532, 'loss/train': 1.4009122848510742} 08/31/2021 00:13:39 - INFO - __main__ - Step 60534: {'lr': 0.0003306127512553375, 'samples': 11622528, 'steps': 60533, 'loss/train': 1.1814063787460327} 08/31/2021 00:13:41 - INFO - __main__ - Step 60535: {'lr': 0.00033060772794644776, 'samples': 11622720, 'steps': 60534, 'loss/train': 1.5915875434875488} 08/31/2021 00:13:41 - INFO - __main__ - Step 60536: {'lr': 0.00033060270460123737, 'samples': 11622912, 'steps': 60535, 'loss/train': 1.4565396308898926} 08/31/2021 00:13:41 - INFO - __main__ - Step 60537: {'lr': 0.0003305976812197087, 'samples': 11623104, 'steps': 60536, 'loss/train': 0.6746528148651123} 08/31/2021 00:13:42 - INFO - __main__ - Step 60538: {'lr': 0.00033059265780186386, 'samples': 11623296, 'steps': 60537, 'loss/train': 1.5971070528030396} 08/31/2021 00:13:42 - INFO - __main__ - Step 60539: {'lr': 0.00033058763434770536, 'samples': 11623488, 'steps': 60538, 'loss/train': 1.3221648931503296} 08/31/2021 00:13:44 - INFO - __main__ - Step 60540: {'lr': 0.0003305826108572352, 'samples': 11623680, 'steps': 60539, 'loss/train': 1.0142250061035156} 08/31/2021 00:13:44 - INFO - __main__ - Step 60541: {'lr': 0.00033057758733045573, 'samples': 11623872, 'steps': 60540, 'loss/train': 1.3702799081802368} 08/31/2021 00:13:45 - INFO - __main__ - Step 60542: {'lr': 0.0003305725637673693, 'samples': 11624064, 'steps': 60541, 'loss/train': 1.3934818506240845} 08/31/2021 00:13:45 - INFO - __main__ - Step 60543: {'lr': 0.00033056754016797814, 'samples': 11624256, 'steps': 60542, 'loss/train': 1.3226337432861328} 08/31/2021 00:13:45 - INFO - __main__ - Step 60544: {'lr': 0.00033056251653228446, 'samples': 11624448, 'steps': 60543, 'loss/train': 1.2137924432754517} 08/31/2021 00:13:47 - INFO - __main__ - Step 60545: {'lr': 0.00033055749286029054, 'samples': 11624640, 'steps': 60544, 'loss/train': 1.494553804397583} 08/31/2021 00:13:48 - INFO - __main__ - Step 60546: {'lr': 0.0003305524691519987, 'samples': 11624832, 'steps': 60545, 'loss/train': 1.3502453565597534} 08/31/2021 00:13:48 - INFO - __main__ - Step 60547: {'lr': 0.0003305474454074111, 'samples': 11625024, 'steps': 60546, 'loss/train': 1.655605435371399} 08/31/2021 00:13:49 - INFO - __main__ - Step 60548: {'lr': 0.0003305424216265301, 'samples': 11625216, 'steps': 60547, 'loss/train': 1.561128854751587} 08/31/2021 00:13:49 - INFO - __main__ - Step 60549: {'lr': 0.0003305373978093579, 'samples': 11625408, 'steps': 60548, 'loss/train': 0.6555415987968445} 08/31/2021 00:13:49 - INFO - __main__ - Step 60550: {'lr': 0.0003305323739558969, 'samples': 11625600, 'steps': 60549, 'loss/train': 4.302450656890869} 08/31/2021 00:13:51 - INFO - __main__ - Step 60551: {'lr': 0.0003305273500661491, 'samples': 11625792, 'steps': 60550, 'loss/train': 1.842113971710205} 08/31/2021 00:13:51 - INFO - __main__ - Step 60552: {'lr': 0.000330522326140117, 'samples': 11625984, 'steps': 60551, 'loss/train': 1.0292036533355713} 08/31/2021 00:13:52 - INFO - __main__ - Step 60553: {'lr': 0.00033051730217780275, 'samples': 11626176, 'steps': 60552, 'loss/train': 1.4182952642440796} 08/31/2021 00:13:52 - INFO - __main__ - Step 60554: {'lr': 0.00033051227817920865, 'samples': 11626368, 'steps': 60553, 'loss/train': 1.1555945873260498} 08/31/2021 00:13:52 - INFO - __main__ - Step 60555: {'lr': 0.000330507254144337, 'samples': 11626560, 'steps': 60554, 'loss/train': 1.372071385383606} 08/31/2021 00:13:54 - INFO - __main__ - Step 60556: {'lr': 0.00033050223007319, 'samples': 11626752, 'steps': 60555, 'loss/train': 1.061646580696106} 08/31/2021 00:13:54 - INFO - __main__ - Step 60557: {'lr': 0.00033049720596576996, 'samples': 11626944, 'steps': 60556, 'loss/train': 1.6282472610473633} 08/31/2021 00:13:55 - INFO - __main__ - Step 60558: {'lr': 0.0003304921818220791, 'samples': 11627136, 'steps': 60557, 'loss/train': 1.6301857233047485} 08/31/2021 00:13:55 - INFO - __main__ - Step 60559: {'lr': 0.00033048715764211965, 'samples': 11627328, 'steps': 60558, 'loss/train': 1.558638334274292} 08/31/2021 00:13:55 - INFO - __main__ - Step 60560: {'lr': 0.00033048213342589403, 'samples': 11627520, 'steps': 60559, 'loss/train': 1.4244258403778076} 08/31/2021 00:13:57 - INFO - __main__ - Step 60561: {'lr': 0.0003304771091734043, 'samples': 11627712, 'steps': 60560, 'loss/train': 0.6724921464920044} 08/31/2021 00:13:57 - INFO - __main__ - Step 60562: {'lr': 0.00033047208488465286, 'samples': 11627904, 'steps': 60561, 'loss/train': 1.2370409965515137} 08/31/2021 00:13:58 - INFO - __main__ - Step 60563: {'lr': 0.00033046706055964197, 'samples': 11628096, 'steps': 60562, 'loss/train': 1.5433382987976074} 08/31/2021 00:13:58 - INFO - __main__ - Step 60564: {'lr': 0.0003304620361983739, 'samples': 11628288, 'steps': 60563, 'loss/train': 2.412384033203125} 08/31/2021 00:13:58 - INFO - __main__ - Step 60565: {'lr': 0.00033045701180085086, 'samples': 11628480, 'steps': 60564, 'loss/train': 0.9748832583427429} 08/31/2021 00:13:59 - INFO - __main__ - Step 60566: {'lr': 0.00033045198736707503, 'samples': 11628672, 'steps': 60565, 'loss/train': 1.9306397438049316} 08/31/2021 00:14:00 - INFO - __main__ - Step 60567: {'lr': 0.0003304469628970489, 'samples': 11628864, 'steps': 60566, 'loss/train': 1.1560189723968506} 08/31/2021 00:14:01 - INFO - __main__ - Step 60568: {'lr': 0.00033044193839077454, 'samples': 11629056, 'steps': 60567, 'loss/train': 0.09417995065450668} 08/31/2021 00:14:01 - INFO - __main__ - Step 60569: {'lr': 0.0003304369138482543, 'samples': 11629248, 'steps': 60568, 'loss/train': 1.3969594240188599} 08/31/2021 00:14:01 - INFO - __main__ - Step 60570: {'lr': 0.00033043188926949046, 'samples': 11629440, 'steps': 60569, 'loss/train': 1.845184087753296} 08/31/2021 00:14:02 - INFO - __main__ - Step 60571: {'lr': 0.00033042686465448526, 'samples': 11629632, 'steps': 60570, 'loss/train': 1.9541877508163452} 08/31/2021 00:14:04 - INFO - __main__ - Step 60572: {'lr': 0.00033042184000324086, 'samples': 11629824, 'steps': 60571, 'loss/train': 1.2152516841888428} 08/31/2021 00:14:04 - INFO - __main__ - Step 60573: {'lr': 0.00033041681531575966, 'samples': 11630016, 'steps': 60572, 'loss/train': 1.4160863161087036} 08/31/2021 00:14:05 - INFO - __main__ - Step 60574: {'lr': 0.0003304117905920439, 'samples': 11630208, 'steps': 60573, 'loss/train': 0.999356746673584} 08/31/2021 00:14:05 - INFO - __main__ - Step 60575: {'lr': 0.0003304067658320958, 'samples': 11630400, 'steps': 60574, 'loss/train': 1.022537350654602} 08/31/2021 00:14:05 - INFO - __main__ - Step 60576: {'lr': 0.0003304017410359177, 'samples': 11630592, 'steps': 60575, 'loss/train': 1.231192946434021} 08/31/2021 00:14:07 - INFO - __main__ - Step 60577: {'lr': 0.00033039671620351186, 'samples': 11630784, 'steps': 60576, 'loss/train': 1.5841426849365234} 08/31/2021 00:14:07 - INFO - __main__ - Step 60578: {'lr': 0.00033039169133488043, 'samples': 11630976, 'steps': 60577, 'loss/train': 0.7280839681625366} 08/31/2021 00:14:08 - INFO - __main__ - Step 60579: {'lr': 0.00033038666643002575, 'samples': 11631168, 'steps': 60578, 'loss/train': 1.5225389003753662} 08/31/2021 00:14:08 - INFO - __main__ - Step 60580: {'lr': 0.0003303816414889501, 'samples': 11631360, 'steps': 60579, 'loss/train': 1.4284199476242065} 08/31/2021 00:14:08 - INFO - __main__ - Step 60581: {'lr': 0.0003303766165116557, 'samples': 11631552, 'steps': 60580, 'loss/train': 1.0416592359542847} 08/31/2021 00:14:10 - INFO - __main__ - Step 60582: {'lr': 0.00033037159149814483, 'samples': 11631744, 'steps': 60581, 'loss/train': 2.5735278129577637} 08/31/2021 00:14:10 - INFO - __main__ - Step 60583: {'lr': 0.00033036656644841976, 'samples': 11631936, 'steps': 60582, 'loss/train': 1.6707029342651367} 08/31/2021 00:14:11 - INFO - __main__ - Step 60584: {'lr': 0.0003303615413624828, 'samples': 11632128, 'steps': 60583, 'loss/train': 1.1897313594818115} 08/31/2021 00:14:11 - INFO - __main__ - Step 60585: {'lr': 0.00033035651624033614, 'samples': 11632320, 'steps': 60584, 'loss/train': 1.180619716644287} 08/31/2021 00:14:11 - INFO - __main__ - Step 60586: {'lr': 0.00033035149108198204, 'samples': 11632512, 'steps': 60585, 'loss/train': 3.2266786098480225} 08/31/2021 00:14:13 - INFO - __main__ - Step 60587: {'lr': 0.00033034646588742285, 'samples': 11632704, 'steps': 60586, 'loss/train': 1.4231605529785156} 08/31/2021 00:14:13 - INFO - __main__ - Step 60588: {'lr': 0.00033034144065666074, 'samples': 11632896, 'steps': 60587, 'loss/train': 1.4200921058654785} 08/31/2021 00:14:14 - INFO - __main__ - Step 60589: {'lr': 0.00033033641538969804, 'samples': 11633088, 'steps': 60588, 'loss/train': 1.1584250926971436} 08/31/2021 00:14:14 - INFO - __main__ - Step 60590: {'lr': 0.000330331390086537, 'samples': 11633280, 'steps': 60589, 'loss/train': 1.2732515335083008} 08/31/2021 00:14:14 - INFO - __main__ - Step 60591: {'lr': 0.0003303263647471799, 'samples': 11633472, 'steps': 60590, 'loss/train': 1.4212919473648071} 08/31/2021 00:14:16 - INFO - __main__ - Step 60592: {'lr': 0.00033032133937162895, 'samples': 11633664, 'steps': 60591, 'loss/train': 1.487404704093933} 08/31/2021 00:14:16 - INFO - __main__ - Step 60593: {'lr': 0.00033031631395988645, 'samples': 11633856, 'steps': 60592, 'loss/train': 1.5735009908676147} 08/31/2021 00:14:17 - INFO - __main__ - Step 60594: {'lr': 0.0003303112885119546, 'samples': 11634048, 'steps': 60593, 'loss/train': 1.390844702720642} 08/31/2021 00:14:17 - INFO - __main__ - Step 60595: {'lr': 0.0003303062630278357, 'samples': 11634240, 'steps': 60594, 'loss/train': 1.1341440677642822} 08/31/2021 00:14:17 - INFO - __main__ - Step 60596: {'lr': 0.00033030123750753216, 'samples': 11634432, 'steps': 60595, 'loss/train': 0.0672595351934433} 08/31/2021 00:14:19 - INFO - __main__ - Step 60597: {'lr': 0.00033029621195104607, 'samples': 11634624, 'steps': 60596, 'loss/train': 1.2149734497070312} 08/31/2021 00:14:19 - INFO - __main__ - Step 60598: {'lr': 0.0003302911863583798, 'samples': 11634816, 'steps': 60597, 'loss/train': 1.3728946447372437} 08/31/2021 00:14:20 - INFO - __main__ - Step 60599: {'lr': 0.0003302861607295355, 'samples': 11635008, 'steps': 60598, 'loss/train': 1.318097710609436} 08/31/2021 00:14:20 - INFO - __main__ - Step 60600: {'lr': 0.0003302811350645155, 'samples': 11635200, 'steps': 60599, 'loss/train': 1.4894386529922485} 08/31/2021 00:14:20 - INFO - __main__ - Step 60601: {'lr': 0.000330276109363322, 'samples': 11635392, 'steps': 60600, 'loss/train': 0.9829367995262146} 08/31/2021 00:14:21 - INFO - __main__ - Step 60602: {'lr': 0.0003302710836259574, 'samples': 11635584, 'steps': 60601, 'loss/train': 0.9130802154541016} 08/31/2021 00:14:23 - INFO - __main__ - Step 60603: {'lr': 0.00033026605785242387, 'samples': 11635776, 'steps': 60602, 'loss/train': 2.4142491817474365} 08/31/2021 00:14:23 - INFO - __main__ - Step 60604: {'lr': 0.0003302610320427237, 'samples': 11635968, 'steps': 60603, 'loss/train': 1.9535034894943237} 08/31/2021 00:14:23 - INFO - __main__ - Step 60605: {'lr': 0.0003302560061968591, 'samples': 11636160, 'steps': 60604, 'loss/train': 1.4590672254562378} 08/31/2021 00:14:24 - INFO - __main__ - Step 60606: {'lr': 0.0003302509803148325, 'samples': 11636352, 'steps': 60605, 'loss/train': 0.8835111856460571} 08/31/2021 00:14:24 - INFO - __main__ - Step 60607: {'lr': 0.000330245954396646, 'samples': 11636544, 'steps': 60606, 'loss/train': 2.1058948040008545} 08/31/2021 00:14:26 - INFO - __main__ - Step 60608: {'lr': 0.0003302409284423018, 'samples': 11636736, 'steps': 60607, 'loss/train': 1.1673234701156616} 08/31/2021 00:14:26 - INFO - __main__ - Step 60609: {'lr': 0.00033023590245180237, 'samples': 11636928, 'steps': 60608, 'loss/train': 1.7236104011535645} 08/31/2021 00:14:26 - INFO - __main__ - Step 60610: {'lr': 0.0003302308764251499, 'samples': 11637120, 'steps': 60609, 'loss/train': 1.3624069690704346} 08/31/2021 00:14:27 - INFO - __main__ - Step 60611: {'lr': 0.0003302258503623466, 'samples': 11637312, 'steps': 60610, 'loss/train': 1.5170865058898926} 08/31/2021 00:14:27 - INFO - __main__ - Step 60612: {'lr': 0.0003302208242633948, 'samples': 11637504, 'steps': 60611, 'loss/train': 1.7276371717453003} 08/31/2021 00:14:27 - INFO - __main__ - Step 60613: {'lr': 0.00033021579812829666, 'samples': 11637696, 'steps': 60612, 'loss/train': 1.549794316291809} 08/31/2021 00:14:29 - INFO - __main__ - Step 60614: {'lr': 0.0003302107719570546, 'samples': 11637888, 'steps': 60613, 'loss/train': 2.3761510848999023} 08/31/2021 00:14:30 - INFO - __main__ - Step 60615: {'lr': 0.0003302057457496707, 'samples': 11638080, 'steps': 60614, 'loss/train': 1.1595903635025024} 08/31/2021 00:14:30 - INFO - __main__ - Step 60616: {'lr': 0.0003302007195061474, 'samples': 11638272, 'steps': 60615, 'loss/train': 1.1430233716964722} 08/31/2021 00:14:31 - INFO - __main__ - Step 60617: {'lr': 0.00033019569322648693, 'samples': 11638464, 'steps': 60616, 'loss/train': 1.3216044902801514} 08/31/2021 00:14:31 - INFO - __main__ - Step 60618: {'lr': 0.0003301906669106915, 'samples': 11638656, 'steps': 60617, 'loss/train': 1.7412623167037964} 08/31/2021 00:14:32 - INFO - __main__ - Step 60619: {'lr': 0.0003301856405587634, 'samples': 11638848, 'steps': 60618, 'loss/train': 1.7554080486297607} 08/31/2021 00:14:33 - INFO - __main__ - Step 60620: {'lr': 0.0003301806141707048, 'samples': 11639040, 'steps': 60619, 'loss/train': 1.2947684526443481} 08/31/2021 00:14:33 - INFO - __main__ - Step 60621: {'lr': 0.0003301755877465181, 'samples': 11639232, 'steps': 60620, 'loss/train': 1.2298349142074585} 08/31/2021 00:14:34 - INFO - __main__ - Step 60622: {'lr': 0.0003301705612862055, 'samples': 11639424, 'steps': 60621, 'loss/train': 1.8158543109893799} 08/31/2021 00:14:34 - INFO - __main__ - Step 60623: {'lr': 0.0003301655347897694, 'samples': 11639616, 'steps': 60622, 'loss/train': 1.7284468412399292} 08/31/2021 00:14:34 - INFO - __main__ - Step 60624: {'lr': 0.0003301605082572119, 'samples': 11639808, 'steps': 60623, 'loss/train': 1.304116129875183} 08/31/2021 00:14:36 - INFO - __main__ - Step 60625: {'lr': 0.0003301554816885352, 'samples': 11640000, 'steps': 60624, 'loss/train': 1.4619067907333374} 08/31/2021 00:14:36 - INFO - __main__ - Step 60626: {'lr': 0.00033015045508374177, 'samples': 11640192, 'steps': 60625, 'loss/train': 1.3858367204666138} 08/31/2021 00:14:37 - INFO - __main__ - Step 60627: {'lr': 0.00033014542844283373, 'samples': 11640384, 'steps': 60626, 'loss/train': 1.6725398302078247} 08/31/2021 00:14:37 - INFO - __main__ - Step 60628: {'lr': 0.00033014040176581347, 'samples': 11640576, 'steps': 60627, 'loss/train': 1.4925991296768188} 08/31/2021 00:14:37 - INFO - __main__ - Step 60629: {'lr': 0.0003301353750526831, 'samples': 11640768, 'steps': 60628, 'loss/train': 1.1612128019332886} 08/31/2021 00:14:39 - INFO - __main__ - Step 60630: {'lr': 0.000330130348303445, 'samples': 11640960, 'steps': 60629, 'loss/train': 1.088147521018982} 08/31/2021 00:14:40 - INFO - __main__ - Step 60631: {'lr': 0.00033012532151810144, 'samples': 11641152, 'steps': 60630, 'loss/train': 1.4679912328720093} 08/31/2021 00:14:40 - INFO - __main__ - Step 60632: {'lr': 0.0003301202946966546, 'samples': 11641344, 'steps': 60631, 'loss/train': 1.4811158180236816} 08/31/2021 00:14:41 - INFO - __main__ - Step 60633: {'lr': 0.0003301152678391068, 'samples': 11641536, 'steps': 60632, 'loss/train': 1.2964566946029663} 08/31/2021 00:14:41 - INFO - __main__ - Step 60634: {'lr': 0.00033011024094546025, 'samples': 11641728, 'steps': 60633, 'loss/train': 5.816245079040527} 08/31/2021 00:14:41 - INFO - __main__ - Step 60635: {'lr': 0.00033010521401571734, 'samples': 11641920, 'steps': 60634, 'loss/train': 0.3415491282939911} 08/31/2021 00:14:43 - INFO - __main__ - Step 60636: {'lr': 0.0003301001870498802, 'samples': 11642112, 'steps': 60635, 'loss/train': 0.8252285122871399} 08/31/2021 00:14:43 - INFO - __main__ - Step 60637: {'lr': 0.00033009516004795127, 'samples': 11642304, 'steps': 60636, 'loss/train': 1.7476574182510376} 08/31/2021 00:14:44 - INFO - __main__ - Step 60638: {'lr': 0.0003300901330099326, 'samples': 11642496, 'steps': 60637, 'loss/train': 1.5832675695419312} 08/31/2021 00:14:44 - INFO - __main__ - Step 60639: {'lr': 0.0003300851059358265, 'samples': 11642688, 'steps': 60638, 'loss/train': 1.7585622072219849} 08/31/2021 00:14:44 - INFO - __main__ - Step 60640: {'lr': 0.0003300800788256354, 'samples': 11642880, 'steps': 60639, 'loss/train': 1.3875161409378052} 08/31/2021 00:14:46 - INFO - __main__ - Step 60641: {'lr': 0.00033007505167936135, 'samples': 11643072, 'steps': 60640, 'loss/train': 2.3415465354919434} 08/31/2021 00:14:47 - INFO - __main__ - Step 60642: {'lr': 0.0003300700244970068, 'samples': 11643264, 'steps': 60641, 'loss/train': 1.150951862335205} 08/31/2021 00:14:47 - INFO - __main__ - Step 60643: {'lr': 0.00033006499727857393, 'samples': 11643456, 'steps': 60642, 'loss/train': 1.6095805168151855} 08/31/2021 00:14:47 - INFO - __main__ - Step 60644: {'lr': 0.000330059970024065, 'samples': 11643648, 'steps': 60643, 'loss/train': 0.18649858236312866} 08/31/2021 00:14:48 - INFO - __main__ - Step 60645: {'lr': 0.00033005494273348224, 'samples': 11643840, 'steps': 60644, 'loss/train': 1.603870153427124} 08/31/2021 00:14:48 - INFO - __main__ - Step 60646: {'lr': 0.00033004991540682793, 'samples': 11644032, 'steps': 60645, 'loss/train': 0.9376243352890015} 08/31/2021 00:14:50 - INFO - __main__ - Step 60647: {'lr': 0.00033004488804410444, 'samples': 11644224, 'steps': 60646, 'loss/train': 0.07360725104808807} 08/31/2021 00:14:50 - INFO - __main__ - Step 60648: {'lr': 0.000330039860645314, 'samples': 11644416, 'steps': 60647, 'loss/train': 1.2967559099197388} 08/31/2021 00:14:51 - INFO - __main__ - Step 60649: {'lr': 0.00033003483321045874, 'samples': 11644608, 'steps': 60648, 'loss/train': 1.2513560056686401} 08/31/2021 00:14:51 - INFO - __main__ - Step 60650: {'lr': 0.000330029805739541, 'samples': 11644800, 'steps': 60649, 'loss/train': 0.5528667569160461} 08/31/2021 00:14:51 - INFO - __main__ - Step 60651: {'lr': 0.0003300247782325631, 'samples': 11644992, 'steps': 60650, 'loss/train': 1.8648611307144165} 08/31/2021 00:14:52 - INFO - __main__ - Step 60652: {'lr': 0.0003300197506895273, 'samples': 11645184, 'steps': 60651, 'loss/train': 1.4140468835830688} 08/31/2021 00:14:53 - INFO - __main__ - Step 60653: {'lr': 0.0003300147231104358, 'samples': 11645376, 'steps': 60652, 'loss/train': 1.3466625213623047} 08/31/2021 00:14:54 - INFO - __main__ - Step 60654: {'lr': 0.0003300096954952909, 'samples': 11645568, 'steps': 60653, 'loss/train': 1.5392335653305054} 08/31/2021 00:14:54 - INFO - __main__ - Step 60655: {'lr': 0.00033000466784409487, 'samples': 11645760, 'steps': 60654, 'loss/train': 1.4391062259674072} 08/31/2021 00:14:54 - INFO - __main__ - Step 60656: {'lr': 0.00032999964015685004, 'samples': 11645952, 'steps': 60655, 'loss/train': 1.2984840869903564} 08/31/2021 00:14:55 - INFO - __main__ - Step 60657: {'lr': 0.0003299946124335585, 'samples': 11646144, 'steps': 60656, 'loss/train': 1.5266196727752686} 08/31/2021 00:14:56 - INFO - __main__ - Step 60658: {'lr': 0.0003299895846742227, 'samples': 11646336, 'steps': 60657, 'loss/train': 0.8545458316802979} 08/31/2021 00:14:57 - INFO - __main__ - Step 60659: {'lr': 0.0003299845568788448, 'samples': 11646528, 'steps': 60658, 'loss/train': 1.7119450569152832} 08/31/2021 00:14:57 - INFO - __main__ - Step 60660: {'lr': 0.0003299795290474271, 'samples': 11646720, 'steps': 60659, 'loss/train': 1.7828364372253418} 08/31/2021 00:14:57 - INFO - __main__ - Step 60661: {'lr': 0.00032997450117997184, 'samples': 11646912, 'steps': 60660, 'loss/train': 1.8855534791946411} 08/31/2021 00:14:58 - INFO - __main__ - Step 60662: {'lr': 0.0003299694732764813, 'samples': 11647104, 'steps': 60661, 'loss/train': 0.9263318181037903} 08/31/2021 00:14:59 - INFO - __main__ - Step 60663: {'lr': 0.00032996444533695777, 'samples': 11647296, 'steps': 60662, 'loss/train': 0.6784809827804565} 08/31/2021 00:15:00 - INFO - __main__ - Step 60664: {'lr': 0.00032995941736140347, 'samples': 11647488, 'steps': 60663, 'loss/train': 0.7558525204658508} 08/31/2021 00:15:00 - INFO - __main__ - Step 60665: {'lr': 0.00032995438934982075, 'samples': 11647680, 'steps': 60664, 'loss/train': 1.4267064332962036} 08/31/2021 00:15:00 - INFO - __main__ - Step 60666: {'lr': 0.00032994936130221174, 'samples': 11647872, 'steps': 60665, 'loss/train': 1.1506080627441406} 08/31/2021 00:15:01 - INFO - __main__ - Step 60667: {'lr': 0.00032994433321857885, 'samples': 11648064, 'steps': 60666, 'loss/train': 0.051675986498594284} 08/31/2021 00:15:02 - INFO - __main__ - Step 60668: {'lr': 0.0003299393050989242, 'samples': 11648256, 'steps': 60667, 'loss/train': 1.3571091890335083} 08/31/2021 00:15:03 - INFO - __main__ - Step 60669: {'lr': 0.00032993427694325017, 'samples': 11648448, 'steps': 60668, 'loss/train': 1.600926399230957} 08/31/2021 00:15:03 - INFO - __main__ - Step 60670: {'lr': 0.000329929248751559, 'samples': 11648640, 'steps': 60669, 'loss/train': 1.1345895528793335} 08/31/2021 00:15:03 - INFO - __main__ - Step 60671: {'lr': 0.00032992422052385297, 'samples': 11648832, 'steps': 60670, 'loss/train': 1.1684709787368774} 08/31/2021 00:15:04 - INFO - __main__ - Step 60672: {'lr': 0.00032991919226013427, 'samples': 11649024, 'steps': 60671, 'loss/train': 1.0802710056304932} 08/31/2021 00:15:06 - INFO - __main__ - Step 60673: {'lr': 0.00032991416396040526, 'samples': 11649216, 'steps': 60672, 'loss/train': 1.2598577737808228} 08/31/2021 00:15:06 - INFO - __main__ - Step 60674: {'lr': 0.00032990913562466805, 'samples': 11649408, 'steps': 60673, 'loss/train': 1.1942334175109863} 08/31/2021 00:15:06 - INFO - __main__ - Step 60675: {'lr': 0.00032990410725292513, 'samples': 11649600, 'steps': 60674, 'loss/train': 2.4056310653686523} 08/31/2021 00:15:07 - INFO - __main__ - Step 60676: {'lr': 0.00032989907884517863, 'samples': 11649792, 'steps': 60675, 'loss/train': 1.6584465503692627} 08/31/2021 00:15:07 - INFO - __main__ - Step 60677: {'lr': 0.0003298940504014308, 'samples': 11649984, 'steps': 60676, 'loss/train': 0.9945623874664307} 08/31/2021 00:15:09 - INFO - __main__ - Step 60678: {'lr': 0.000329889021921684, 'samples': 11650176, 'steps': 60677, 'loss/train': 1.146183729171753} 08/31/2021 00:15:09 - INFO - __main__ - Step 60679: {'lr': 0.00032988399340594046, 'samples': 11650368, 'steps': 60678, 'loss/train': 1.0067156553268433} 08/31/2021 00:15:09 - INFO - __main__ - Step 60680: {'lr': 0.0003298789648542023, 'samples': 11650560, 'steps': 60679, 'loss/train': 1.0830985307693481} 08/31/2021 00:15:10 - INFO - __main__ - Step 60681: {'lr': 0.000329873936266472, 'samples': 11650752, 'steps': 60680, 'loss/train': 1.2604851722717285} 08/31/2021 00:15:10 - INFO - __main__ - Step 60682: {'lr': 0.00032986890764275174, 'samples': 11650944, 'steps': 60681, 'loss/train': 1.1123318672180176} 08/31/2021 00:15:12 - INFO - __main__ - Step 60683: {'lr': 0.00032986387898304375, 'samples': 11651136, 'steps': 60682, 'loss/train': 0.7169027328491211} 08/31/2021 00:15:12 - INFO - __main__ - Step 60684: {'lr': 0.00032985885028735033, 'samples': 11651328, 'steps': 60683, 'loss/train': 1.3454762697219849} 08/31/2021 00:15:13 - INFO - __main__ - Step 60685: {'lr': 0.00032985382155567377, 'samples': 11651520, 'steps': 60684, 'loss/train': 0.904625415802002} 08/31/2021 00:15:13 - INFO - __main__ - Step 60686: {'lr': 0.0003298487927880163, 'samples': 11651712, 'steps': 60685, 'loss/train': 1.7950773239135742} 08/31/2021 00:15:13 - INFO - __main__ - Step 60687: {'lr': 0.00032984376398438023, 'samples': 11651904, 'steps': 60686, 'loss/train': 1.0013551712036133} 08/31/2021 00:15:14 - INFO - __main__ - Step 60688: {'lr': 0.00032983873514476776, 'samples': 11652096, 'steps': 60687, 'loss/train': 1.2102426290512085} 08/31/2021 00:15:16 - INFO - __main__ - Step 60689: {'lr': 0.0003298337062691812, 'samples': 11652288, 'steps': 60688, 'loss/train': 1.0805251598358154} 08/31/2021 00:15:16 - INFO - __main__ - Step 60690: {'lr': 0.00032982867735762274, 'samples': 11652480, 'steps': 60689, 'loss/train': 1.6269575357437134} 08/31/2021 00:15:16 - INFO - __main__ - Step 60691: {'lr': 0.0003298236484100948, 'samples': 11652672, 'steps': 60690, 'loss/train': 1.7308107614517212} 08/31/2021 00:15:17 - INFO - __main__ - Step 60692: {'lr': 0.00032981861942659954, 'samples': 11652864, 'steps': 60691, 'loss/train': 1.3134046792984009} 08/31/2021 00:15:17 - INFO - __main__ - Step 60693: {'lr': 0.00032981359040713923, 'samples': 11653056, 'steps': 60692, 'loss/train': 1.348225474357605} 08/31/2021 00:15:18 - INFO - __main__ - Step 60694: {'lr': 0.0003298085613517161, 'samples': 11653248, 'steps': 60693, 'loss/train': 0.90365070104599} 08/31/2021 00:15:19 - INFO - __main__ - Step 60695: {'lr': 0.0003298035322603324, 'samples': 11653440, 'steps': 60694, 'loss/train': 0.9060843586921692} 08/31/2021 00:15:19 - INFO - __main__ - Step 60696: {'lr': 0.00032979850313299064, 'samples': 11653632, 'steps': 60695, 'loss/train': 1.0107507705688477} 08/31/2021 00:15:20 - INFO - __main__ - Step 60697: {'lr': 0.0003297934739696928, 'samples': 11653824, 'steps': 60696, 'loss/train': 1.0631651878356934} 08/31/2021 00:15:20 - INFO - __main__ - Step 60698: {'lr': 0.00032978844477044136, 'samples': 11654016, 'steps': 60697, 'loss/train': 1.172106385231018} 08/31/2021 00:15:21 - INFO - __main__ - Step 60699: {'lr': 0.0003297834155352383, 'samples': 11654208, 'steps': 60698, 'loss/train': 0.8791998624801636} 08/31/2021 00:15:22 - INFO - __main__ - Step 60700: {'lr': 0.00032977838626408617, 'samples': 11654400, 'steps': 60699, 'loss/train': 0.9804980754852295} 08/31/2021 00:15:22 - INFO - __main__ - Step 60701: {'lr': 0.00032977335695698714, 'samples': 11654592, 'steps': 60700, 'loss/train': 0.9967959523200989} 08/31/2021 00:15:23 - INFO - __main__ - Step 60702: {'lr': 0.00032976832761394344, 'samples': 11654784, 'steps': 60701, 'loss/train': 1.3841763734817505} 08/31/2021 00:15:23 - INFO - __main__ - Step 60703: {'lr': 0.0003297632982349573, 'samples': 11654976, 'steps': 60702, 'loss/train': 1.386694073677063} 08/31/2021 00:15:25 - INFO - __main__ - Step 60704: {'lr': 0.0003297582688200311, 'samples': 11655168, 'steps': 60703, 'loss/train': 1.1500427722930908} 08/31/2021 00:15:25 - INFO - __main__ - Step 60705: {'lr': 0.0003297532393691672, 'samples': 11655360, 'steps': 60704, 'loss/train': 1.094079613685608} 08/31/2021 00:15:25 - INFO - __main__ - Step 60706: {'lr': 0.00032974820988236755, 'samples': 11655552, 'steps': 60705, 'loss/train': 1.7720434665679932} 08/31/2021 00:15:26 - INFO - __main__ - Step 60707: {'lr': 0.00032974318035963463, 'samples': 11655744, 'steps': 60706, 'loss/train': 1.53734290599823} 08/31/2021 00:15:26 - INFO - __main__ - Step 60708: {'lr': 0.00032973815080097066, 'samples': 11655936, 'steps': 60707, 'loss/train': 1.6936179399490356} 08/31/2021 00:15:27 - INFO - __main__ - Step 60709: {'lr': 0.0003297331212063779, 'samples': 11656128, 'steps': 60708, 'loss/train': 1.7159866094589233} 08/31/2021 00:15:28 - INFO - __main__ - Step 60710: {'lr': 0.00032972809157585866, 'samples': 11656320, 'steps': 60709, 'loss/train': 1.2854629755020142} 08/31/2021 00:15:28 - INFO - __main__ - Step 60711: {'lr': 0.0003297230619094151, 'samples': 11656512, 'steps': 60710, 'loss/train': 1.7291699647903442} 08/31/2021 00:15:29 - INFO - __main__ - Step 60712: {'lr': 0.00032971803220704964, 'samples': 11656704, 'steps': 60711, 'loss/train': 1.0817159414291382} 08/31/2021 00:15:29 - INFO - __main__ - Step 60713: {'lr': 0.00032971300246876443, 'samples': 11656896, 'steps': 60712, 'loss/train': 0.7783119678497314} 08/31/2021 00:15:31 - INFO - __main__ - Step 60714: {'lr': 0.00032970797269456177, 'samples': 11657088, 'steps': 60713, 'loss/train': 1.517508864402771} 08/31/2021 00:15:31 - INFO - __main__ - Step 60715: {'lr': 0.00032970294288444394, 'samples': 11657280, 'steps': 60714, 'loss/train': 0.9170249700546265} 08/31/2021 00:15:32 - INFO - __main__ - Step 60716: {'lr': 0.00032969791303841316, 'samples': 11657472, 'steps': 60715, 'loss/train': 1.1548460721969604} 08/31/2021 00:15:32 - INFO - __main__ - Step 60717: {'lr': 0.00032969288315647176, 'samples': 11657664, 'steps': 60716, 'loss/train': 1.9083272218704224} 08/31/2021 00:15:32 - INFO - __main__ - Step 60718: {'lr': 0.00032968785323862207, 'samples': 11657856, 'steps': 60717, 'loss/train': 1.7930254936218262} 08/31/2021 00:15:33 - INFO - __main__ - Step 60719: {'lr': 0.0003296828232848661, 'samples': 11658048, 'steps': 60718, 'loss/train': 0.7317922115325928} 08/31/2021 00:15:34 - INFO - __main__ - Step 60720: {'lr': 0.0003296777932952064, 'samples': 11658240, 'steps': 60719, 'loss/train': 0.9367513656616211} 08/31/2021 00:15:35 - INFO - __main__ - Step 60721: {'lr': 0.000329672763269645, 'samples': 11658432, 'steps': 60720, 'loss/train': 1.616318941116333} 08/31/2021 00:15:35 - INFO - __main__ - Step 60722: {'lr': 0.00032966773320818434, 'samples': 11658624, 'steps': 60721, 'loss/train': 1.4660578966140747} 08/31/2021 00:15:35 - INFO - __main__ - Step 60723: {'lr': 0.00032966270311082666, 'samples': 11658816, 'steps': 60722, 'loss/train': 1.4881625175476074} 08/31/2021 00:15:36 - INFO - __main__ - Step 60724: {'lr': 0.0003296576729775741, 'samples': 11659008, 'steps': 60723, 'loss/train': 1.21040940284729} 08/31/2021 00:15:37 - INFO - __main__ - Step 60725: {'lr': 0.00032965264280842915, 'samples': 11659200, 'steps': 60724, 'loss/train': 1.5296629667282104} 08/31/2021 00:15:37 - INFO - __main__ - Step 60726: {'lr': 0.00032964761260339387, 'samples': 11659392, 'steps': 60725, 'loss/train': 0.9708404541015625} 08/31/2021 00:15:38 - INFO - __main__ - Step 60727: {'lr': 0.00032964258236247064, 'samples': 11659584, 'steps': 60726, 'loss/train': 1.4020755290985107} 08/31/2021 00:15:38 - INFO - __main__ - Step 60728: {'lr': 0.00032963755208566167, 'samples': 11659776, 'steps': 60727, 'loss/train': 1.2961914539337158} 08/31/2021 00:15:38 - INFO - __main__ - Step 60729: {'lr': 0.0003296325217729692, 'samples': 11659968, 'steps': 60728, 'loss/train': 1.2812464237213135} 08/31/2021 00:15:40 - INFO - __main__ - Step 60730: {'lr': 0.0003296274914243956, 'samples': 11660160, 'steps': 60729, 'loss/train': 1.21956467628479} 08/31/2021 00:15:41 - INFO - __main__ - Step 60731: {'lr': 0.0003296224610399431, 'samples': 11660352, 'steps': 60730, 'loss/train': 0.03261396288871765} 08/31/2021 00:15:41 - INFO - __main__ - Step 60732: {'lr': 0.00032961743061961395, 'samples': 11660544, 'steps': 60731, 'loss/train': 1.451003074645996} 08/31/2021 00:15:42 - INFO - __main__ - Step 60733: {'lr': 0.0003296124001634104, 'samples': 11660736, 'steps': 60732, 'loss/train': 1.3208227157592773} 08/31/2021 00:15:42 - INFO - __main__ - Step 60734: {'lr': 0.0003296073696713347, 'samples': 11660928, 'steps': 60733, 'loss/train': 1.5906808376312256} 08/31/2021 00:15:42 - INFO - __main__ - Step 60735: {'lr': 0.0003296023391433892, 'samples': 11661120, 'steps': 60734, 'loss/train': 1.8119999170303345} 08/31/2021 00:15:44 - INFO - __main__ - Step 60736: {'lr': 0.00032959730857957606, 'samples': 11661312, 'steps': 60735, 'loss/train': 1.3561067581176758} 08/31/2021 00:15:44 - INFO - __main__ - Step 60737: {'lr': 0.0003295922779798976, 'samples': 11661504, 'steps': 60736, 'loss/train': 1.6483004093170166} 08/31/2021 00:15:45 - INFO - __main__ - Step 60738: {'lr': 0.00032958724734435615, 'samples': 11661696, 'steps': 60737, 'loss/train': 1.5537890195846558} 08/31/2021 00:15:45 - INFO - __main__ - Step 60739: {'lr': 0.00032958221667295386, 'samples': 11661888, 'steps': 60738, 'loss/train': 1.2498745918273926} 08/31/2021 00:15:45 - INFO - __main__ - Step 60740: {'lr': 0.0003295771859656931, 'samples': 11662080, 'steps': 60739, 'loss/train': 0.3396289348602295} 08/31/2021 00:15:47 - INFO - __main__ - Step 60741: {'lr': 0.000329572155222576, 'samples': 11662272, 'steps': 60740, 'loss/train': 0.40921059250831604} 08/31/2021 00:15:48 - INFO - __main__ - Step 60742: {'lr': 0.000329567124443605, 'samples': 11662464, 'steps': 60741, 'loss/train': 1.105696201324463} 08/31/2021 00:15:48 - INFO - __main__ - Step 60743: {'lr': 0.0003295620936287822, 'samples': 11662656, 'steps': 60742, 'loss/train': 0.7204613089561462} 08/31/2021 00:15:49 - INFO - __main__ - Step 60744: {'lr': 0.00032955706277811004, 'samples': 11662848, 'steps': 60743, 'loss/train': 0.8393903970718384} 08/31/2021 00:15:49 - INFO - __main__ - Step 60745: {'lr': 0.00032955203189159065, 'samples': 11663040, 'steps': 60744, 'loss/train': 0.9226095080375671} 08/31/2021 00:15:50 - INFO - __main__ - Step 60746: {'lr': 0.00032954700096922635, 'samples': 11663232, 'steps': 60745, 'loss/train': 0.741275429725647} 08/31/2021 00:15:51 - INFO - __main__ - Step 60747: {'lr': 0.00032954197001101935, 'samples': 11663424, 'steps': 60746, 'loss/train': 1.0742111206054688} 08/31/2021 00:15:51 - INFO - __main__ - Step 60748: {'lr': 0.000329536939016972, 'samples': 11663616, 'steps': 60747, 'loss/train': 1.036885142326355} 08/31/2021 00:15:52 - INFO - __main__ - Step 60749: {'lr': 0.0003295319079870866, 'samples': 11663808, 'steps': 60748, 'loss/train': 1.3159154653549194} 08/31/2021 00:15:52 - INFO - __main__ - Step 60750: {'lr': 0.0003295268769213653, 'samples': 11664000, 'steps': 60749, 'loss/train': 1.793104887008667} 08/31/2021 00:15:54 - INFO - __main__ - Step 60751: {'lr': 0.0003295218458198104, 'samples': 11664192, 'steps': 60750, 'loss/train': 0.900732159614563} 08/31/2021 00:15:54 - INFO - __main__ - Step 60752: {'lr': 0.00032951681468242424, 'samples': 11664384, 'steps': 60751, 'loss/train': 1.5382874011993408} 08/31/2021 00:15:54 - INFO - __main__ - Step 60753: {'lr': 0.00032951178350920895, 'samples': 11664576, 'steps': 60752, 'loss/train': 1.2733757495880127} 08/31/2021 00:15:55 - INFO - __main__ - Step 60754: {'lr': 0.0003295067523001669, 'samples': 11664768, 'steps': 60753, 'loss/train': 0.04271407797932625} 08/31/2021 00:15:55 - INFO - __main__ - Step 60755: {'lr': 0.0003295017210553003, 'samples': 11664960, 'steps': 60754, 'loss/train': 1.8166708946228027} 08/31/2021 00:15:57 - INFO - __main__ - Step 60756: {'lr': 0.0003294966897746115, 'samples': 11665152, 'steps': 60755, 'loss/train': 1.3497676849365234} 08/31/2021 00:15:57 - INFO - __main__ - Step 60757: {'lr': 0.0003294916584581027, 'samples': 11665344, 'steps': 60756, 'loss/train': 1.4783297777175903} 08/31/2021 00:15:57 - INFO - __main__ - Step 60758: {'lr': 0.00032948662710577625, 'samples': 11665536, 'steps': 60757, 'loss/train': 1.096864938735962} 08/31/2021 00:15:58 - INFO - __main__ - Step 60759: {'lr': 0.0003294815957176343, 'samples': 11665728, 'steps': 60758, 'loss/train': 1.4725667238235474} 08/31/2021 00:15:58 - INFO - __main__ - Step 60760: {'lr': 0.00032947656429367915, 'samples': 11665920, 'steps': 60759, 'loss/train': 1.0439128875732422} 08/31/2021 00:15:58 - INFO - __main__ - Step 60761: {'lr': 0.00032947153283391313, 'samples': 11666112, 'steps': 60760, 'loss/train': 1.0733011960983276} 08/31/2021 00:16:00 - INFO - __main__ - Step 60762: {'lr': 0.00032946650133833846, 'samples': 11666304, 'steps': 60761, 'loss/train': 1.193015456199646} 08/31/2021 00:16:01 - INFO - __main__ - Step 60763: {'lr': 0.00032946146980695736, 'samples': 11666496, 'steps': 60762, 'loss/train': 0.7267287373542786} 08/31/2021 00:16:01 - INFO - __main__ - Step 60764: {'lr': 0.00032945643823977216, 'samples': 11666688, 'steps': 60763, 'loss/train': 1.0590028762817383} 08/31/2021 00:16:01 - INFO - __main__ - Step 60765: {'lr': 0.0003294514066367852, 'samples': 11666880, 'steps': 60764, 'loss/train': 1.1051914691925049} 08/31/2021 00:16:02 - INFO - __main__ - Step 60766: {'lr': 0.0003294463749979986, 'samples': 11667072, 'steps': 60765, 'loss/train': 0.6557971835136414} 08/31/2021 00:16:03 - INFO - __main__ - Step 60767: {'lr': 0.00032944134332341465, 'samples': 11667264, 'steps': 60766, 'loss/train': 1.116518497467041} 08/31/2021 00:16:04 - INFO - __main__ - Step 60768: {'lr': 0.0003294363116130357, 'samples': 11667456, 'steps': 60767, 'loss/train': 1.1040042638778687} 08/31/2021 00:16:04 - INFO - __main__ - Step 60769: {'lr': 0.00032943127986686393, 'samples': 11667648, 'steps': 60768, 'loss/train': 0.9811849594116211} 08/31/2021 00:16:05 - INFO - __main__ - Step 60770: {'lr': 0.0003294262480849017, 'samples': 11667840, 'steps': 60769, 'loss/train': 0.8726362586021423} 08/31/2021 00:16:05 - INFO - __main__ - Step 60771: {'lr': 0.0003294212162671512, 'samples': 11668032, 'steps': 60770, 'loss/train': 0.3170013427734375} 08/31/2021 00:16:06 - INFO - __main__ - Step 60772: {'lr': 0.00032941618441361477, 'samples': 11668224, 'steps': 60771, 'loss/train': 2.195876121520996} 08/31/2021 00:16:07 - INFO - __main__ - Step 60773: {'lr': 0.0003294111525242946, 'samples': 11668416, 'steps': 60772, 'loss/train': 1.2566720247268677} 08/31/2021 00:16:07 - INFO - __main__ - Step 60774: {'lr': 0.000329406120599193, 'samples': 11668608, 'steps': 60773, 'loss/train': 1.4474880695343018} 08/31/2021 00:16:07 - INFO - __main__ - Step 60775: {'lr': 0.0003294010886383122, 'samples': 11668800, 'steps': 60774, 'loss/train': 3.012838840484619} 08/31/2021 00:16:08 - INFO - __main__ - Step 60776: {'lr': 0.0003293960566416545, 'samples': 11668992, 'steps': 60775, 'loss/train': 1.5380284786224365} 08/31/2021 00:16:10 - INFO - __main__ - Step 60777: {'lr': 0.00032939102460922227, 'samples': 11669184, 'steps': 60776, 'loss/train': 0.8499827980995178} 08/31/2021 00:16:10 - INFO - __main__ - Step 60778: {'lr': 0.00032938599254101755, 'samples': 11669376, 'steps': 60777, 'loss/train': 1.6205542087554932} 08/31/2021 00:16:10 - INFO - __main__ - Step 60779: {'lr': 0.0003293809604370427, 'samples': 11669568, 'steps': 60778, 'loss/train': 1.5246360301971436} 08/31/2021 00:16:11 - INFO - __main__ - Step 60780: {'lr': 0.0003293759282973001, 'samples': 11669760, 'steps': 60779, 'loss/train': 1.3279404640197754} 08/31/2021 00:16:11 - INFO - __main__ - Step 60781: {'lr': 0.0003293708961217919, 'samples': 11669952, 'steps': 60780, 'loss/train': 1.274374008178711} 08/31/2021 00:16:13 - INFO - __main__ - Step 60782: {'lr': 0.00032936586391052035, 'samples': 11670144, 'steps': 60781, 'loss/train': 1.0742563009262085} 08/31/2021 00:16:13 - INFO - __main__ - Step 60783: {'lr': 0.0003293608316634879, 'samples': 11670336, 'steps': 60782, 'loss/train': 0.7794846296310425} 08/31/2021 00:16:13 - INFO - __main__ - Step 60784: {'lr': 0.0003293557993806966, 'samples': 11670528, 'steps': 60783, 'loss/train': 0.3305763304233551} 08/31/2021 00:16:14 - INFO - __main__ - Step 60785: {'lr': 0.0003293507670621488, 'samples': 11670720, 'steps': 60784, 'loss/train': 1.2741334438323975} 08/31/2021 00:16:14 - INFO - __main__ - Step 60786: {'lr': 0.00032934573470784674, 'samples': 11670912, 'steps': 60785, 'loss/train': 1.5204484462738037} 08/31/2021 00:16:14 - INFO - __main__ - Step 60787: {'lr': 0.00032934070231779275, 'samples': 11671104, 'steps': 60786, 'loss/train': 0.8618792295455933} 08/31/2021 00:16:16 - INFO - __main__ - Step 60788: {'lr': 0.0003293356698919891, 'samples': 11671296, 'steps': 60787, 'loss/train': 0.9110966324806213} 08/31/2021 00:16:17 - INFO - __main__ - Step 60789: {'lr': 0.000329330637430438, 'samples': 11671488, 'steps': 60788, 'loss/train': 1.5866801738739014} 08/31/2021 00:16:17 - INFO - __main__ - Step 60790: {'lr': 0.00032932560493314166, 'samples': 11671680, 'steps': 60789, 'loss/train': 1.3766427040100098} 08/31/2021 00:16:17 - INFO - __main__ - Step 60791: {'lr': 0.0003293205724001025, 'samples': 11671872, 'steps': 60790, 'loss/train': 1.1334152221679688} 08/31/2021 00:16:18 - INFO - __main__ - Step 60792: {'lr': 0.00032931553983132266, 'samples': 11672064, 'steps': 60791, 'loss/train': 1.8883439302444458} 08/31/2021 00:16:20 - INFO - __main__ - Step 60793: {'lr': 0.00032931050722680453, 'samples': 11672256, 'steps': 60792, 'loss/train': 1.3811379671096802} 08/31/2021 00:16:20 - INFO - __main__ - Step 60794: {'lr': 0.00032930547458655035, 'samples': 11672448, 'steps': 60793, 'loss/train': 1.5925748348236084} 08/31/2021 00:16:20 - INFO - __main__ - Step 60795: {'lr': 0.00032930044191056227, 'samples': 11672640, 'steps': 60794, 'loss/train': 0.5234602689743042} 08/31/2021 00:16:21 - INFO - __main__ - Step 60796: {'lr': 0.0003292954091988426, 'samples': 11672832, 'steps': 60795, 'loss/train': 1.185200572013855} 08/31/2021 00:16:21 - INFO - __main__ - Step 60797: {'lr': 0.0003292903764513937, 'samples': 11673024, 'steps': 60796, 'loss/train': 1.7545127868652344} 08/31/2021 00:16:23 - INFO - __main__ - Step 60798: {'lr': 0.0003292853436682177, 'samples': 11673216, 'steps': 60797, 'loss/train': 1.8552430868148804} 08/31/2021 00:16:23 - INFO - __main__ - Step 60799: {'lr': 0.0003292803108493171, 'samples': 11673408, 'steps': 60798, 'loss/train': 0.9833294153213501} 08/31/2021 00:16:23 - INFO - __main__ - Step 60800: {'lr': 0.0003292752779946939, 'samples': 11673600, 'steps': 60799, 'loss/train': 1.2119405269622803} 08/31/2021 00:16:24 - INFO - __main__ - Step 60801: {'lr': 0.00032927024510435055, 'samples': 11673792, 'steps': 60800, 'loss/train': 1.212566614151001} 08/31/2021 00:16:24 - INFO - __main__ - Step 60802: {'lr': 0.0003292652121782892, 'samples': 11673984, 'steps': 60801, 'loss/train': 1.2565501928329468} 08/31/2021 00:16:25 - INFO - __main__ - Step 60803: {'lr': 0.0003292601792165122, 'samples': 11674176, 'steps': 60802, 'loss/train': 0.9810609817504883} 08/31/2021 00:16:26 - INFO - __main__ - Step 60804: {'lr': 0.00032925514621902173, 'samples': 11674368, 'steps': 60803, 'loss/train': 1.267059326171875} 08/31/2021 00:16:26 - INFO - __main__ - Step 60805: {'lr': 0.0003292501131858201, 'samples': 11674560, 'steps': 60804, 'loss/train': 1.0787220001220703} 08/31/2021 00:16:27 - INFO - __main__ - Step 60806: {'lr': 0.0003292450801169097, 'samples': 11674752, 'steps': 60805, 'loss/train': 1.6085383892059326} 08/31/2021 00:16:27 - INFO - __main__ - Step 60807: {'lr': 0.00032924004701229267, 'samples': 11674944, 'steps': 60806, 'loss/train': 1.254012942314148} 08/31/2021 00:16:28 - INFO - __main__ - Step 60808: {'lr': 0.00032923501387197127, 'samples': 11675136, 'steps': 60807, 'loss/train': 1.220617651939392} 08/31/2021 00:16:29 - INFO - __main__ - Step 60809: {'lr': 0.00032922998069594774, 'samples': 11675328, 'steps': 60808, 'loss/train': 1.5795457363128662} 08/31/2021 00:16:29 - INFO - __main__ - Step 60810: {'lr': 0.0003292249474842244, 'samples': 11675520, 'steps': 60809, 'loss/train': 1.0548620223999023} 08/31/2021 00:16:30 - INFO - __main__ - Step 60811: {'lr': 0.00032921991423680356, 'samples': 11675712, 'steps': 60810, 'loss/train': 1.8005635738372803} 08/31/2021 00:16:30 - INFO - __main__ - Step 60812: {'lr': 0.0003292148809536876, 'samples': 11675904, 'steps': 60811, 'loss/train': 0.9220402240753174} 08/31/2021 00:16:32 - INFO - __main__ - Step 60813: {'lr': 0.0003292098476348784, 'samples': 11676096, 'steps': 60812, 'loss/train': 0.9478226900100708} 08/31/2021 00:16:32 - INFO - __main__ - Step 60814: {'lr': 0.00032920481428037857, 'samples': 11676288, 'steps': 60813, 'loss/train': 0.4688386619091034} 08/31/2021 00:16:32 - INFO - __main__ - Step 60815: {'lr': 0.00032919978089019026, 'samples': 11676480, 'steps': 60814, 'loss/train': 0.9995197653770447} 08/31/2021 00:16:33 - INFO - __main__ - Step 60816: {'lr': 0.00032919474746431575, 'samples': 11676672, 'steps': 60815, 'loss/train': 0.7100570201873779} 08/31/2021 00:16:33 - INFO - __main__ - Step 60817: {'lr': 0.00032918971400275733, 'samples': 11676864, 'steps': 60816, 'loss/train': 0.0731353834271431} 08/31/2021 00:16:33 - INFO - __main__ - Step 60818: {'lr': 0.0003291846805055172, 'samples': 11677056, 'steps': 60817, 'loss/train': 1.729759931564331} 08/31/2021 00:16:35 - INFO - __main__ - Step 60819: {'lr': 0.0003291796469725977, 'samples': 11677248, 'steps': 60818, 'loss/train': 1.2741224765777588} 08/31/2021 00:16:36 - INFO - __main__ - Step 60820: {'lr': 0.0003291746134040011, 'samples': 11677440, 'steps': 60819, 'loss/train': 1.4283480644226074} 08/31/2021 00:16:36 - INFO - __main__ - Step 60821: {'lr': 0.00032916957979972964, 'samples': 11677632, 'steps': 60820, 'loss/train': 1.1145867109298706} 08/31/2021 00:16:36 - INFO - __main__ - Step 60822: {'lr': 0.00032916454615978554, 'samples': 11677824, 'steps': 60821, 'loss/train': 1.477480173110962} 08/31/2021 00:16:37 - INFO - __main__ - Step 60823: {'lr': 0.00032915951248417113, 'samples': 11678016, 'steps': 60822, 'loss/train': 1.3662242889404297} 08/31/2021 00:16:38 - INFO - __main__ - Step 60824: {'lr': 0.0003291544787728887, 'samples': 11678208, 'steps': 60823, 'loss/train': 1.2402024269104004} 08/31/2021 00:16:39 - INFO - __main__ - Step 60825: {'lr': 0.00032914944502594046, 'samples': 11678400, 'steps': 60824, 'loss/train': 1.6582037210464478} 08/31/2021 00:16:39 - INFO - __main__ - Step 60826: {'lr': 0.00032914441124332874, 'samples': 11678592, 'steps': 60825, 'loss/train': 1.3923076391220093} 08/31/2021 00:16:39 - INFO - __main__ - Step 60827: {'lr': 0.0003291393774250557, 'samples': 11678784, 'steps': 60826, 'loss/train': 1.3514188528060913} 08/31/2021 00:16:40 - INFO - __main__ - Step 60828: {'lr': 0.0003291343435711237, 'samples': 11678976, 'steps': 60827, 'loss/train': 0.46013152599334717} 08/31/2021 00:16:42 - INFO - __main__ - Step 60829: {'lr': 0.000329129309681535, 'samples': 11679168, 'steps': 60828, 'loss/train': 1.5298720598220825} 08/31/2021 00:16:42 - INFO - __main__ - Step 60830: {'lr': 0.0003291242757562919, 'samples': 11679360, 'steps': 60829, 'loss/train': 0.8822082281112671} 08/31/2021 00:16:42 - INFO - __main__ - Step 60831: {'lr': 0.00032911924179539653, 'samples': 11679552, 'steps': 60830, 'loss/train': 0.030323954299092293} 08/31/2021 00:16:43 - INFO - __main__ - Step 60832: {'lr': 0.00032911420779885135, 'samples': 11679744, 'steps': 60831, 'loss/train': 0.027424486353993416} 08/31/2021 00:16:43 - INFO - __main__ - Step 60833: {'lr': 0.00032910917376665846, 'samples': 11679936, 'steps': 60832, 'loss/train': 0.8531773686408997} 08/31/2021 00:16:43 - INFO - __main__ - Step 60834: {'lr': 0.0003291041396988202, 'samples': 11680128, 'steps': 60833, 'loss/train': 1.082950472831726} 08/31/2021 00:16:45 - INFO - __main__ - Step 60835: {'lr': 0.00032909910559533886, 'samples': 11680320, 'steps': 60834, 'loss/train': 1.6544766426086426} 08/31/2021 00:16:45 - INFO - __main__ - Step 60836: {'lr': 0.00032909407145621664, 'samples': 11680512, 'steps': 60835, 'loss/train': 0.3441605269908905} 08/31/2021 00:16:46 - INFO - __main__ - Step 60837: {'lr': 0.0003290890372814559, 'samples': 11680704, 'steps': 60836, 'loss/train': 0.6750202775001526} 08/31/2021 00:16:46 - INFO - __main__ - Step 60838: {'lr': 0.0003290840030710588, 'samples': 11680896, 'steps': 60837, 'loss/train': 1.3810170888900757} 08/31/2021 00:16:46 - INFO - __main__ - Step 60839: {'lr': 0.00032907896882502775, 'samples': 11681088, 'steps': 60838, 'loss/train': 1.1959484815597534} 08/31/2021 00:16:48 - INFO - __main__ - Step 60840: {'lr': 0.00032907393454336493, 'samples': 11681280, 'steps': 60839, 'loss/train': 1.3892009258270264} 08/31/2021 00:16:48 - INFO - __main__ - Step 60841: {'lr': 0.0003290689002260726, 'samples': 11681472, 'steps': 60840, 'loss/train': 1.2675433158874512} 08/31/2021 00:16:49 - INFO - __main__ - Step 60842: {'lr': 0.00032906386587315295, 'samples': 11681664, 'steps': 60841, 'loss/train': 1.0872855186462402} 08/31/2021 00:16:49 - INFO - __main__ - Step 60843: {'lr': 0.00032905883148460845, 'samples': 11681856, 'steps': 60842, 'loss/train': 1.2092442512512207} 08/31/2021 00:16:49 - INFO - __main__ - Step 60844: {'lr': 0.0003290537970604412, 'samples': 11682048, 'steps': 60843, 'loss/train': 1.2999162673950195} 08/31/2021 00:16:51 - INFO - __main__ - Step 60845: {'lr': 0.00032904876260065355, 'samples': 11682240, 'steps': 60844, 'loss/train': 1.3339420557022095} 08/31/2021 00:16:52 - INFO - __main__ - Step 60846: {'lr': 0.0003290437281052478, 'samples': 11682432, 'steps': 60845, 'loss/train': 0.9629106521606445} 08/31/2021 00:16:52 - INFO - __main__ - Step 60847: {'lr': 0.00032903869357422613, 'samples': 11682624, 'steps': 60846, 'loss/train': 1.1771756410598755} 08/31/2021 00:16:52 - INFO - __main__ - Step 60848: {'lr': 0.0003290336590075908, 'samples': 11682816, 'steps': 60847, 'loss/train': 1.4259010553359985} 08/31/2021 00:16:53 - INFO - __main__ - Step 60849: {'lr': 0.00032902862440534414, 'samples': 11683008, 'steps': 60848, 'loss/train': 0.4653834104537964} 08/31/2021 00:16:53 - INFO - __main__ - Step 60850: {'lr': 0.00032902358976748844, 'samples': 11683200, 'steps': 60849, 'loss/train': 1.4879531860351562} 08/31/2021 00:16:55 - INFO - __main__ - Step 60851: {'lr': 0.0003290185550940259, 'samples': 11683392, 'steps': 60850, 'loss/train': 1.418919563293457} 08/31/2021 00:16:55 - INFO - __main__ - Step 60852: {'lr': 0.0003290135203849588, 'samples': 11683584, 'steps': 60851, 'loss/train': 1.5684155225753784} 08/31/2021 00:16:56 - INFO - __main__ - Step 60853: {'lr': 0.00032900848564028953, 'samples': 11683776, 'steps': 60852, 'loss/train': 1.4621504545211792} 08/31/2021 00:16:56 - INFO - __main__ - Step 60854: {'lr': 0.00032900345086002013, 'samples': 11683968, 'steps': 60853, 'loss/train': 1.0745116472244263} 08/31/2021 00:16:56 - INFO - __main__ - Step 60855: {'lr': 0.00032899841604415306, 'samples': 11684160, 'steps': 60854, 'loss/train': 1.6760693788528442} 08/31/2021 00:16:58 - INFO - __main__ - Step 60856: {'lr': 0.0003289933811926905, 'samples': 11684352, 'steps': 60855, 'loss/train': 0.5155673027038574} 08/31/2021 00:16:58 - INFO - __main__ - Step 60857: {'lr': 0.0003289883463056347, 'samples': 11684544, 'steps': 60856, 'loss/train': 1.4757695198059082} 08/31/2021 00:16:59 - INFO - __main__ - Step 60858: {'lr': 0.0003289833113829881, 'samples': 11684736, 'steps': 60857, 'loss/train': 1.0419198274612427} 08/31/2021 00:16:59 - INFO - __main__ - Step 60859: {'lr': 0.0003289782764247528, 'samples': 11684928, 'steps': 60858, 'loss/train': 1.1122032403945923} 08/31/2021 00:17:00 - INFO - __main__ - Step 60860: {'lr': 0.000328973241430931, 'samples': 11685120, 'steps': 60859, 'loss/train': 1.5142967700958252} 08/31/2021 00:17:01 - INFO - __main__ - Step 60861: {'lr': 0.0003289682064015251, 'samples': 11685312, 'steps': 60860, 'loss/train': 2.4052252769470215} 08/31/2021 00:17:02 - INFO - __main__ - Step 60862: {'lr': 0.0003289631713365374, 'samples': 11685504, 'steps': 60861, 'loss/train': 1.5836747884750366} 08/31/2021 00:17:02 - INFO - __main__ - Step 60863: {'lr': 0.00032895813623597017, 'samples': 11685696, 'steps': 60862, 'loss/train': 1.7119629383087158} 08/31/2021 00:17:03 - INFO - __main__ - Step 60864: {'lr': 0.0003289531010998255, 'samples': 11685888, 'steps': 60863, 'loss/train': 1.6984703540802002} 08/31/2021 00:17:03 - INFO - __main__ - Step 60865: {'lr': 0.0003289480659281058, 'samples': 11686080, 'steps': 60864, 'loss/train': 1.428051471710205} 08/31/2021 00:17:03 - INFO - __main__ - Step 60866: {'lr': 0.0003289430307208134, 'samples': 11686272, 'steps': 60865, 'loss/train': 1.6384544372558594} 08/31/2021 00:17:04 - INFO - __main__ - Step 60867: {'lr': 0.00032893799547795046, 'samples': 11686464, 'steps': 60866, 'loss/train': 0.0900164321064949} 08/31/2021 00:17:05 - INFO - __main__ - Step 60868: {'lr': 0.0003289329601995192, 'samples': 11686656, 'steps': 60867, 'loss/train': 0.028450096026062965} 08/31/2021 00:17:06 - INFO - __main__ - Step 60869: {'lr': 0.00032892792488552203, 'samples': 11686848, 'steps': 60868, 'loss/train': 1.1894243955612183} 08/31/2021 00:17:06 - INFO - __main__ - Step 60870: {'lr': 0.00032892288953596116, 'samples': 11687040, 'steps': 60869, 'loss/train': 1.2376741170883179} 08/31/2021 00:17:06 - INFO - __main__ - Step 60871: {'lr': 0.00032891785415083884, 'samples': 11687232, 'steps': 60870, 'loss/train': 1.0540080070495605} 08/31/2021 00:17:07 - INFO - __main__ - Step 60872: {'lr': 0.00032891281873015734, 'samples': 11687424, 'steps': 60871, 'loss/train': 1.4553371667861938} 08/31/2021 00:17:08 - INFO - __main__ - Step 60873: {'lr': 0.000328907783273919, 'samples': 11687616, 'steps': 60872, 'loss/train': 1.3950319290161133} 08/31/2021 00:17:09 - INFO - __main__ - Step 60874: {'lr': 0.000328902747782126, 'samples': 11687808, 'steps': 60873, 'loss/train': 0.6284448504447937} 08/31/2021 00:17:09 - INFO - __main__ - Step 60875: {'lr': 0.0003288977122547806, 'samples': 11688000, 'steps': 60874, 'loss/train': 0.4288201928138733} 08/31/2021 00:17:09 - INFO - __main__ - Step 60876: {'lr': 0.00032889267669188515, 'samples': 11688192, 'steps': 60875, 'loss/train': 1.5895003080368042} 08/31/2021 00:17:10 - INFO - __main__ - Step 60877: {'lr': 0.0003288876410934418, 'samples': 11688384, 'steps': 60876, 'loss/train': 0.860230565071106} 08/31/2021 00:17:11 - INFO - __main__ - Step 60878: {'lr': 0.000328882605459453, 'samples': 11688576, 'steps': 60877, 'loss/train': 1.9047797918319702} 08/31/2021 00:17:12 - INFO - __main__ - Step 60879: {'lr': 0.0003288775697899209, 'samples': 11688768, 'steps': 60878, 'loss/train': 1.422298550605774} 08/31/2021 00:17:12 - INFO - __main__ - Step 60880: {'lr': 0.00032887253408484776, 'samples': 11688960, 'steps': 60879, 'loss/train': 0.05121016129851341} 08/31/2021 00:17:13 - INFO - __main__ - Step 60881: {'lr': 0.0003288674983442358, 'samples': 11689152, 'steps': 60880, 'loss/train': 0.0405525378882885} 08/31/2021 00:17:13 - INFO - __main__ - Step 60882: {'lr': 0.0003288624625680875, 'samples': 11689344, 'steps': 60881, 'loss/train': 1.2622898817062378} 08/31/2021 00:17:14 - INFO - __main__ - Step 60883: {'lr': 0.0003288574267564049, 'samples': 11689536, 'steps': 60882, 'loss/train': 2.3077378273010254} 08/31/2021 00:17:15 - INFO - __main__ - Step 60884: {'lr': 0.0003288523909091904, 'samples': 11689728, 'steps': 60883, 'loss/train': 1.5439753532409668} 08/31/2021 00:17:15 - INFO - __main__ - Step 60885: {'lr': 0.0003288473550264462, 'samples': 11689920, 'steps': 60884, 'loss/train': 1.5379588603973389} 08/31/2021 00:17:16 - INFO - __main__ - Step 60886: {'lr': 0.00032884231910817465, 'samples': 11690112, 'steps': 60885, 'loss/train': 0.8179649114608765} 08/31/2021 00:17:16 - INFO - __main__ - Step 60887: {'lr': 0.0003288372831543779, 'samples': 11690304, 'steps': 60886, 'loss/train': 1.8635584115982056} 08/31/2021 00:17:17 - INFO - __main__ - Step 60888: {'lr': 0.0003288322471650583, 'samples': 11690496, 'steps': 60887, 'loss/train': 1.789287805557251} 08/31/2021 00:17:18 - INFO - __main__ - Step 60889: {'lr': 0.0003288272111402181, 'samples': 11690688, 'steps': 60888, 'loss/train': 1.5436419248580933} 08/31/2021 00:17:18 - INFO - __main__ - Step 60890: {'lr': 0.0003288221750798596, 'samples': 11690880, 'steps': 60889, 'loss/train': 0.8435717821121216} 08/31/2021 00:17:19 - INFO - __main__ - Step 60891: {'lr': 0.0003288171389839851, 'samples': 11691072, 'steps': 60890, 'loss/train': 1.379912257194519} 08/31/2021 00:17:19 - INFO - __main__ - Step 60892: {'lr': 0.0003288121028525967, 'samples': 11691264, 'steps': 60891, 'loss/train': 1.6559628248214722} 08/31/2021 00:17:20 - INFO - __main__ - Step 60893: {'lr': 0.0003288070666856969, 'samples': 11691456, 'steps': 60892, 'loss/train': 1.3113824129104614} 08/31/2021 00:17:21 - INFO - __main__ - Step 60894: {'lr': 0.00032880203048328777, 'samples': 11691648, 'steps': 60893, 'loss/train': 1.658996343612671} 08/31/2021 00:17:21 - INFO - __main__ - Step 60895: {'lr': 0.0003287969942453717, 'samples': 11691840, 'steps': 60894, 'loss/train': 0.8740580677986145} 08/31/2021 00:17:22 - INFO - __main__ - Step 60896: {'lr': 0.0003287919579719509, 'samples': 11692032, 'steps': 60895, 'loss/train': 1.2922654151916504} 08/31/2021 00:17:22 - INFO - __main__ - Step 60897: {'lr': 0.00032878692166302766, 'samples': 11692224, 'steps': 60896, 'loss/train': 0.6373283267021179} 08/31/2021 00:17:23 - INFO - __main__ - Step 60898: {'lr': 0.0003287818853186042, 'samples': 11692416, 'steps': 60897, 'loss/train': 0.5428177714347839} 08/31/2021 00:17:24 - INFO - __main__ - Step 60899: {'lr': 0.0003287768489386829, 'samples': 11692608, 'steps': 60898, 'loss/train': 0.9184427857398987} 08/31/2021 00:17:24 - INFO - __main__ - Step 60900: {'lr': 0.000328771812523266, 'samples': 11692800, 'steps': 60899, 'loss/train': 1.572549819946289} 08/31/2021 00:17:25 - INFO - __main__ - Step 60901: {'lr': 0.00032876677607235566, 'samples': 11692992, 'steps': 60900, 'loss/train': 1.2439367771148682} 08/31/2021 00:17:25 - INFO - __main__ - Step 60902: {'lr': 0.0003287617395859543, 'samples': 11693184, 'steps': 60901, 'loss/train': 1.9165685176849365} 08/31/2021 00:17:25 - INFO - __main__ - Step 60903: {'lr': 0.00032875670306406403, 'samples': 11693376, 'steps': 60902, 'loss/train': 1.5849153995513916} 08/31/2021 00:17:28 - INFO - __main__ - Step 60904: {'lr': 0.00032875166650668725, 'samples': 11693568, 'steps': 60903, 'loss/train': 1.332240104675293} 08/31/2021 00:17:28 - INFO - __main__ - Step 60905: {'lr': 0.0003287466299138262, 'samples': 11693760, 'steps': 60904, 'loss/train': 1.795551061630249} 08/31/2021 00:17:28 - INFO - __main__ - Step 60906: {'lr': 0.00032874159328548315, 'samples': 11693952, 'steps': 60905, 'loss/train': 1.2973361015319824} 08/31/2021 00:17:29 - INFO - __main__ - Step 60907: {'lr': 0.0003287365566216603, 'samples': 11694144, 'steps': 60906, 'loss/train': 1.3099952936172485} 08/31/2021 00:17:29 - INFO - __main__ - Step 60908: {'lr': 0.00032873151992236, 'samples': 11694336, 'steps': 60907, 'loss/train': 1.0235047340393066} 08/31/2021 00:17:31 - INFO - __main__ - Step 60909: {'lr': 0.00032872648318758445, 'samples': 11694528, 'steps': 60908, 'loss/train': 1.043179988861084} 08/31/2021 00:17:31 - INFO - __main__ - Step 60910: {'lr': 0.000328721446417336, 'samples': 11694720, 'steps': 60909, 'loss/train': 1.425424337387085} 08/31/2021 00:17:32 - INFO - __main__ - Step 60911: {'lr': 0.00032871640961161687, 'samples': 11694912, 'steps': 60910, 'loss/train': 1.7192606925964355} 08/31/2021 00:17:32 - INFO - __main__ - Step 60912: {'lr': 0.0003287113727704294, 'samples': 11695104, 'steps': 60911, 'loss/train': 1.407414436340332} 08/31/2021 00:17:32 - INFO - __main__ - Step 60913: {'lr': 0.00032870633589377575, 'samples': 11695296, 'steps': 60912, 'loss/train': 1.187281847000122} 08/31/2021 00:17:34 - INFO - __main__ - Step 60914: {'lr': 0.00032870129898165826, 'samples': 11695488, 'steps': 60913, 'loss/train': 1.5347634553909302} 08/31/2021 00:17:34 - INFO - __main__ - Step 60915: {'lr': 0.00032869626203407907, 'samples': 11695680, 'steps': 60914, 'loss/train': 1.2651172876358032} 08/31/2021 00:17:35 - INFO - __main__ - Step 60916: {'lr': 0.00032869122505104067, 'samples': 11695872, 'steps': 60915, 'loss/train': 1.3684056997299194} 08/31/2021 00:17:35 - INFO - __main__ - Step 60917: {'lr': 0.0003286861880325452, 'samples': 11696064, 'steps': 60916, 'loss/train': 1.2069724798202515} 08/31/2021 00:17:35 - INFO - __main__ - Step 60918: {'lr': 0.00032868115097859496, 'samples': 11696256, 'steps': 60917, 'loss/train': 0.9542529582977295} 08/31/2021 00:17:37 - INFO - __main__ - Step 60919: {'lr': 0.00032867611388919215, 'samples': 11696448, 'steps': 60918, 'loss/train': 1.2149425745010376} 08/31/2021 00:17:37 - INFO - __main__ - Step 60920: {'lr': 0.0003286710767643392, 'samples': 11696640, 'steps': 60919, 'loss/train': 0.12941573560237885} 08/31/2021 00:17:38 - INFO - __main__ - Step 60921: {'lr': 0.0003286660396040382, 'samples': 11696832, 'steps': 60920, 'loss/train': 1.27705979347229} 08/31/2021 00:17:38 - INFO - __main__ - Step 60922: {'lr': 0.0003286610024082915, 'samples': 11697024, 'steps': 60921, 'loss/train': 1.4377602338790894} 08/31/2021 00:17:38 - INFO - __main__ - Step 60923: {'lr': 0.0003286559651771014, 'samples': 11697216, 'steps': 60922, 'loss/train': 1.2633132934570312} 08/31/2021 00:17:39 - INFO - __main__ - Step 60924: {'lr': 0.00032865092791047013, 'samples': 11697408, 'steps': 60923, 'loss/train': 1.690728783607483} 08/31/2021 00:17:40 - INFO - __main__ - Step 60925: {'lr': 0.0003286458906083999, 'samples': 11697600, 'steps': 60924, 'loss/train': 0.5259474515914917} 08/31/2021 00:17:41 - INFO - __main__ - Step 60926: {'lr': 0.0003286408532708931, 'samples': 11697792, 'steps': 60925, 'loss/train': 1.0369387865066528} 08/31/2021 00:17:41 - INFO - __main__ - Step 60927: {'lr': 0.00032863581589795193, 'samples': 11697984, 'steps': 60926, 'loss/train': 1.456861138343811} 08/31/2021 00:17:41 - INFO - __main__ - Step 60928: {'lr': 0.00032863077848957874, 'samples': 11698176, 'steps': 60927, 'loss/train': 1.1485673189163208} 08/31/2021 00:17:42 - INFO - __main__ - Step 60929: {'lr': 0.00032862574104577567, 'samples': 11698368, 'steps': 60928, 'loss/train': 1.2103546857833862} 08/31/2021 00:17:43 - INFO - __main__ - Step 60930: {'lr': 0.00032862070356654504, 'samples': 11698560, 'steps': 60929, 'loss/train': 1.7522212266921997} 08/31/2021 00:17:44 - INFO - __main__ - Step 60931: {'lr': 0.00032861566605188914, 'samples': 11698752, 'steps': 60930, 'loss/train': 1.1365278959274292} 08/31/2021 00:17:44 - INFO - __main__ - Step 60932: {'lr': 0.00032861062850181023, 'samples': 11698944, 'steps': 60931, 'loss/train': 0.2107314020395279} 08/31/2021 00:17:44 - INFO - __main__ - Step 60933: {'lr': 0.00032860559091631066, 'samples': 11699136, 'steps': 60932, 'loss/train': 0.9449143409729004} 08/31/2021 00:17:45 - INFO - __main__ - Step 60934: {'lr': 0.0003286005532953926, 'samples': 11699328, 'steps': 60933, 'loss/train': 1.197424054145813} 08/31/2021 00:17:47 - INFO - __main__ - Step 60935: {'lr': 0.00032859551563905825, 'samples': 11699520, 'steps': 60934, 'loss/train': 1.5418397188186646} 08/31/2021 00:17:47 - INFO - __main__ - Step 60936: {'lr': 0.00032859047794731, 'samples': 11699712, 'steps': 60935, 'loss/train': 0.9390974640846252} 08/31/2021 00:17:47 - INFO - __main__ - Step 60937: {'lr': 0.00032858544022015015, 'samples': 11699904, 'steps': 60936, 'loss/train': 1.69832444190979} 08/31/2021 00:17:48 - INFO - __main__ - Step 60938: {'lr': 0.0003285804024575809, 'samples': 11700096, 'steps': 60937, 'loss/train': 0.018984410911798477} 08/31/2021 00:17:48 - INFO - __main__ - Step 60939: {'lr': 0.0003285753646596045, 'samples': 11700288, 'steps': 60938, 'loss/train': 1.1642876863479614} 08/31/2021 00:17:48 - INFO - __main__ - Step 60940: {'lr': 0.00032857032682622335, 'samples': 11700480, 'steps': 60939, 'loss/train': 1.641979694366455} 08/31/2021 00:17:50 - INFO - __main__ - Step 60941: {'lr': 0.00032856528895743953, 'samples': 11700672, 'steps': 60940, 'loss/train': 1.4450418949127197} 08/31/2021 00:17:50 - INFO - __main__ - Step 60942: {'lr': 0.00032856025105325537, 'samples': 11700864, 'steps': 60941, 'loss/train': 1.0915957689285278} 08/31/2021 00:17:51 - INFO - __main__ - Step 60943: {'lr': 0.00032855521311367326, 'samples': 11701056, 'steps': 60942, 'loss/train': 1.2752375602722168} 08/31/2021 00:17:51 - INFO - __main__ - Step 60944: {'lr': 0.00032855017513869537, 'samples': 11701248, 'steps': 60943, 'loss/train': 1.564825415611267} 08/31/2021 00:17:52 - INFO - __main__ - Step 60945: {'lr': 0.0003285451371283239, 'samples': 11701440, 'steps': 60944, 'loss/train': 2.0824248790740967} 08/31/2021 00:17:53 - INFO - __main__ - Step 60946: {'lr': 0.00032854009908256127, 'samples': 11701632, 'steps': 60945, 'loss/train': 1.4236174821853638} 08/31/2021 00:17:54 - INFO - __main__ - Step 60947: {'lr': 0.00032853506100140973, 'samples': 11701824, 'steps': 60946, 'loss/train': 0.8661724328994751} 08/31/2021 00:17:54 - INFO - __main__ - Step 60948: {'lr': 0.00032853002288487146, 'samples': 11702016, 'steps': 60947, 'loss/train': 1.5438612699508667} 08/31/2021 00:17:54 - INFO - __main__ - Step 60949: {'lr': 0.00032852498473294874, 'samples': 11702208, 'steps': 60948, 'loss/train': 1.6641490459442139} 08/31/2021 00:17:55 - INFO - __main__ - Step 60950: {'lr': 0.0003285199465456439, 'samples': 11702400, 'steps': 60949, 'loss/train': 1.228949785232544} 08/31/2021 00:17:55 - INFO - __main__ - Step 60951: {'lr': 0.0003285149083229592, 'samples': 11702592, 'steps': 60950, 'loss/train': 1.4152759313583374} 08/31/2021 00:17:57 - INFO - __main__ - Step 60952: {'lr': 0.00032850987006489686, 'samples': 11702784, 'steps': 60951, 'loss/train': 0.7748353481292725} 08/31/2021 00:17:57 - INFO - __main__ - Step 60953: {'lr': 0.00032850483177145924, 'samples': 11702976, 'steps': 60952, 'loss/train': 1.4725346565246582} 08/31/2021 00:17:57 - INFO - __main__ - Step 60954: {'lr': 0.00032849979344264844, 'samples': 11703168, 'steps': 60953, 'loss/train': 1.416073203086853} 08/31/2021 00:17:58 - INFO - __main__ - Step 60955: {'lr': 0.00032849475507846696, 'samples': 11703360, 'steps': 60954, 'loss/train': 0.6622111201286316} 08/31/2021 00:17:58 - INFO - __main__ - Step 60956: {'lr': 0.0003284897166789169, 'samples': 11703552, 'steps': 60955, 'loss/train': 1.5539501905441284} 08/31/2021 00:17:59 - INFO - __main__ - Step 60957: {'lr': 0.0003284846782440006, 'samples': 11703744, 'steps': 60956, 'loss/train': 1.417553186416626} 08/31/2021 00:18:00 - INFO - __main__ - Step 60958: {'lr': 0.0003284796397737203, 'samples': 11703936, 'steps': 60957, 'loss/train': 0.14378130435943604} 08/31/2021 00:18:00 - INFO - __main__ - Step 60959: {'lr': 0.0003284746012680783, 'samples': 11704128, 'steps': 60958, 'loss/train': 1.0456891059875488} 08/31/2021 00:18:01 - INFO - __main__ - Step 60960: {'lr': 0.0003284695627270769, 'samples': 11704320, 'steps': 60959, 'loss/train': 1.2894251346588135} 08/31/2021 00:18:01 - INFO - __main__ - Step 60961: {'lr': 0.00032846452415071826, 'samples': 11704512, 'steps': 60960, 'loss/train': 1.2101048231124878} 08/31/2021 00:18:03 - INFO - __main__ - Step 60962: {'lr': 0.00032845948553900475, 'samples': 11704704, 'steps': 60961, 'loss/train': 2.140444040298462} 08/31/2021 00:18:04 - INFO - __main__ - Step 60963: {'lr': 0.0003284544468919386, 'samples': 11704896, 'steps': 60962, 'loss/train': 1.0522469282150269} 08/31/2021 00:18:04 - INFO - __main__ - Step 60964: {'lr': 0.0003284494082095221, 'samples': 11705088, 'steps': 60963, 'loss/train': 1.1602725982666016} 08/31/2021 00:18:04 - INFO - __main__ - Step 60965: {'lr': 0.00032844436949175745, 'samples': 11705280, 'steps': 60964, 'loss/train': 0.8529567718505859} 08/31/2021 00:18:05 - INFO - __main__ - Step 60966: {'lr': 0.00032843933073864695, 'samples': 11705472, 'steps': 60965, 'loss/train': 0.9699711799621582} 08/31/2021 00:18:06 - INFO - __main__ - Step 60967: {'lr': 0.00032843429195019303, 'samples': 11705664, 'steps': 60966, 'loss/train': 1.2551178932189941} 08/31/2021 00:18:07 - INFO - __main__ - Step 60968: {'lr': 0.00032842925312639775, 'samples': 11705856, 'steps': 60967, 'loss/train': 1.5408012866973877} 08/31/2021 00:18:07 - INFO - __main__ - Step 60969: {'lr': 0.0003284242142672635, 'samples': 11706048, 'steps': 60968, 'loss/train': 0.9813641905784607} 08/31/2021 00:18:07 - INFO - __main__ - Step 60970: {'lr': 0.00032841917537279245, 'samples': 11706240, 'steps': 60969, 'loss/train': 1.5694364309310913} 08/31/2021 00:18:08 - INFO - __main__ - Step 60971: {'lr': 0.00032841413644298697, 'samples': 11706432, 'steps': 60970, 'loss/train': 6.122105598449707} 08/31/2021 00:18:08 - INFO - __main__ - Step 60972: {'lr': 0.00032840909747784924, 'samples': 11706624, 'steps': 60971, 'loss/train': 1.6372052431106567} 08/31/2021 00:18:09 - INFO - __main__ - Step 60973: {'lr': 0.00032840405847738165, 'samples': 11706816, 'steps': 60972, 'loss/train': 0.5130667090415955} 08/31/2021 00:18:10 - INFO - __main__ - Step 60974: {'lr': 0.0003283990194415864, 'samples': 11707008, 'steps': 60973, 'loss/train': 1.381510615348816} 08/31/2021 00:18:10 - INFO - __main__ - Step 60975: {'lr': 0.0003283939803704657, 'samples': 11707200, 'steps': 60974, 'loss/train': 1.7866002321243286} 08/31/2021 00:18:11 - INFO - __main__ - Step 60976: {'lr': 0.0003283889412640219, 'samples': 11707392, 'steps': 60975, 'loss/train': 1.0769041776657104} 08/31/2021 00:18:11 - INFO - __main__ - Step 60977: {'lr': 0.0003283839021222573, 'samples': 11707584, 'steps': 60976, 'loss/train': 1.106912612915039} 08/31/2021 00:18:12 - INFO - __main__ - Step 60978: {'lr': 0.000328378862945174, 'samples': 11707776, 'steps': 60977, 'loss/train': 1.4185634851455688} 08/31/2021 00:18:13 - INFO - __main__ - Step 60979: {'lr': 0.0003283738237327745, 'samples': 11707968, 'steps': 60978, 'loss/train': 1.6879802942276} 08/31/2021 00:18:13 - INFO - __main__ - Step 60980: {'lr': 0.000328368784485061, 'samples': 11708160, 'steps': 60979, 'loss/train': 1.6290922164916992} 08/31/2021 00:18:14 - INFO - __main__ - Step 60981: {'lr': 0.00032836374520203574, 'samples': 11708352, 'steps': 60980, 'loss/train': 1.525710940361023} 08/31/2021 00:18:14 - INFO - __main__ - Step 60982: {'lr': 0.0003283587058837009, 'samples': 11708544, 'steps': 60981, 'loss/train': 0.8686908483505249} 08/31/2021 00:18:14 - INFO - __main__ - Step 60983: {'lr': 0.0003283536665300588, 'samples': 11708736, 'steps': 60982, 'loss/train': 1.4634039402008057} 08/31/2021 00:18:16 - INFO - __main__ - Step 60984: {'lr': 0.00032834862714111184, 'samples': 11708928, 'steps': 60983, 'loss/train': 1.5325714349746704} 08/31/2021 00:18:16 - INFO - __main__ - Step 60985: {'lr': 0.0003283435877168622, 'samples': 11709120, 'steps': 60984, 'loss/train': 1.329017996788025} 08/31/2021 00:18:17 - INFO - __main__ - Step 60986: {'lr': 0.00032833854825731207, 'samples': 11709312, 'steps': 60985, 'loss/train': 1.5312433242797852} 08/31/2021 00:18:17 - INFO - __main__ - Step 60987: {'lr': 0.00032833350876246395, 'samples': 11709504, 'steps': 60986, 'loss/train': 1.5850193500518799} 08/31/2021 00:18:17 - INFO - __main__ - Step 60988: {'lr': 0.0003283284692323198, 'samples': 11709696, 'steps': 60987, 'loss/train': 0.9462196230888367} 08/31/2021 00:18:19 - INFO - __main__ - Step 60989: {'lr': 0.0003283234296668821, 'samples': 11709888, 'steps': 60988, 'loss/train': 0.9655730128288269} 08/31/2021 00:18:20 - INFO - __main__ - Step 60990: {'lr': 0.00032831839006615307, 'samples': 11710080, 'steps': 60989, 'loss/train': 0.07147926092147827} 08/31/2021 00:18:20 - INFO - __main__ - Step 60991: {'lr': 0.000328313350430135, 'samples': 11710272, 'steps': 60990, 'loss/train': 1.4452961683273315} 08/31/2021 00:18:20 - INFO - __main__ - Step 60992: {'lr': 0.0003283083107588301, 'samples': 11710464, 'steps': 60991, 'loss/train': 1.3454625606536865} 08/31/2021 00:18:21 - INFO - __main__ - Step 60993: {'lr': 0.0003283032710522407, 'samples': 11710656, 'steps': 60992, 'loss/train': 1.081005573272705} 08/31/2021 00:18:22 - INFO - __main__ - Step 60994: {'lr': 0.0003282982313103691, 'samples': 11710848, 'steps': 60993, 'loss/train': 0.8829039931297302} 08/31/2021 00:18:23 - INFO - __main__ - Step 60995: {'lr': 0.0003282931915332175, 'samples': 11711040, 'steps': 60994, 'loss/train': 0.8636853694915771} 08/31/2021 00:18:23 - INFO - __main__ - Step 60996: {'lr': 0.0003282881517207882, 'samples': 11711232, 'steps': 60995, 'loss/train': 1.4603875875473022} 08/31/2021 00:18:24 - INFO - __main__ - Step 60997: {'lr': 0.00032828311187308346, 'samples': 11711424, 'steps': 60996, 'loss/train': 0.906135618686676} 08/31/2021 00:18:24 - INFO - __main__ - Step 60998: {'lr': 0.00032827807199010554, 'samples': 11711616, 'steps': 60997, 'loss/train': 1.5555613040924072} 08/31/2021 00:18:26 - INFO - __main__ - Step 60999: {'lr': 0.00032827303207185675, 'samples': 11711808, 'steps': 60998, 'loss/train': 1.247078776359558} 08/31/2021 00:18:26 - INFO - __main__ - Step 61000: {'lr': 0.00032826799211833934, 'samples': 11712000, 'steps': 60999, 'loss/train': 1.8086693286895752} 08/31/2021 00:18:27 - INFO - __main__ - Step 61001: {'lr': 0.0003282629521295556, 'samples': 11712192, 'steps': 61000, 'loss/train': 1.1671571731567383} 08/31/2021 00:18:27 - INFO - __main__ - Step 61002: {'lr': 0.00032825791210550775, 'samples': 11712384, 'steps': 61001, 'loss/train': 0.7880164980888367} 08/31/2021 00:18:27 - INFO - __main__ - Step 61003: {'lr': 0.00032825287204619807, 'samples': 11712576, 'steps': 61002, 'loss/train': 0.9423691034317017} 08/31/2021 00:18:28 - INFO - __main__ - Step 61004: {'lr': 0.0003282478319516289, 'samples': 11712768, 'steps': 61003, 'loss/train': 1.2262691259384155} 08/31/2021 00:18:30 - INFO - __main__ - Step 61005: {'lr': 0.00032824279182180243, 'samples': 11712960, 'steps': 61004, 'loss/train': 0.6972643733024597} 08/31/2021 00:18:30 - INFO - __main__ - Step 61006: {'lr': 0.00032823775165672096, 'samples': 11713152, 'steps': 61005, 'loss/train': 1.3197712898254395} 08/31/2021 00:18:30 - INFO - __main__ - Step 61007: {'lr': 0.0003282327114563869, 'samples': 11713344, 'steps': 61006, 'loss/train': 1.0663093328475952} 08/31/2021 00:18:31 - INFO - __main__ - Step 61008: {'lr': 0.0003282276712208022, 'samples': 11713536, 'steps': 61007, 'loss/train': 0.44108346104621887} 08/31/2021 00:18:31 - INFO - __main__ - Step 61009: {'lr': 0.0003282226309499694, 'samples': 11713728, 'steps': 61008, 'loss/train': 1.050757646560669} 08/31/2021 00:18:31 - INFO - __main__ - Step 61010: {'lr': 0.0003282175906438907, 'samples': 11713920, 'steps': 61009, 'loss/train': 0.17793524265289307} 08/31/2021 00:18:33 - INFO - __main__ - Step 61011: {'lr': 0.00032821255030256836, 'samples': 11714112, 'steps': 61010, 'loss/train': 0.9329459071159363} 08/31/2021 00:18:33 - INFO - __main__ - Step 61012: {'lr': 0.00032820750992600464, 'samples': 11714304, 'steps': 61011, 'loss/train': 1.4363083839416504} 08/31/2021 00:18:34 - INFO - __main__ - Step 61013: {'lr': 0.0003282024695142018, 'samples': 11714496, 'steps': 61012, 'loss/train': 1.1003907918930054} 08/31/2021 00:18:34 - INFO - __main__ - Step 61014: {'lr': 0.0003281974290671622, 'samples': 11714688, 'steps': 61013, 'loss/train': 0.8983328938484192} 08/31/2021 00:18:34 - INFO - __main__ - Step 61015: {'lr': 0.000328192388584888, 'samples': 11714880, 'steps': 61014, 'loss/train': 0.10990507155656815} 08/31/2021 00:18:36 - INFO - __main__ - Step 61016: {'lr': 0.00032818734806738147, 'samples': 11715072, 'steps': 61015, 'loss/train': 0.461252361536026} 08/31/2021 00:18:37 - INFO - __main__ - Step 61017: {'lr': 0.00032818230751464493, 'samples': 11715264, 'steps': 61016, 'loss/train': 0.7553821802139282} 08/31/2021 00:18:37 - INFO - __main__ - Step 61018: {'lr': 0.0003281772669266807, 'samples': 11715456, 'steps': 61017, 'loss/train': 1.1697139739990234} 08/31/2021 00:18:38 - INFO - __main__ - Step 61019: {'lr': 0.00032817222630349103, 'samples': 11715648, 'steps': 61018, 'loss/train': 1.6747676134109497} 08/31/2021 00:18:38 - INFO - __main__ - Step 61020: {'lr': 0.00032816718564507806, 'samples': 11715840, 'steps': 61019, 'loss/train': 1.405562162399292} 08/31/2021 00:18:40 - INFO - __main__ - Step 61021: {'lr': 0.0003281621449514443, 'samples': 11716032, 'steps': 61020, 'loss/train': 0.917891800403595} 08/31/2021 00:18:40 - INFO - __main__ - Step 61022: {'lr': 0.0003281571042225918, 'samples': 11716224, 'steps': 61021, 'loss/train': 1.5005216598510742} 08/31/2021 00:18:41 - INFO - __main__ - Step 61023: {'lr': 0.0003281520634585229, 'samples': 11716416, 'steps': 61022, 'loss/train': 0.6175127625465393} 08/31/2021 00:18:41 - INFO - __main__ - Step 61024: {'lr': 0.0003281470226592399, 'samples': 11716608, 'steps': 61023, 'loss/train': 1.6916131973266602} 08/31/2021 00:18:41 - INFO - __main__ - Step 61025: {'lr': 0.0003281419818247451, 'samples': 11716800, 'steps': 61024, 'loss/train': 1.8966525793075562} 08/31/2021 00:18:43 - INFO - __main__ - Step 61026: {'lr': 0.00032813694095504064, 'samples': 11716992, 'steps': 61025, 'loss/train': 1.5016406774520874} 08/31/2021 00:18:43 - INFO - __main__ - Step 61027: {'lr': 0.000328131900050129, 'samples': 11717184, 'steps': 61026, 'loss/train': 1.569472312927246} 08/31/2021 00:18:44 - INFO - __main__ - Step 61028: {'lr': 0.0003281268591100123, 'samples': 11717376, 'steps': 61027, 'loss/train': 1.7178599834442139} 08/31/2021 00:18:44 - INFO - __main__ - Step 61029: {'lr': 0.00032812181813469276, 'samples': 11717568, 'steps': 61028, 'loss/train': 1.7901506423950195} 08/31/2021 00:18:44 - INFO - __main__ - Step 61030: {'lr': 0.0003281167771241728, 'samples': 11717760, 'steps': 61029, 'loss/train': 1.1544075012207031} 08/31/2021 00:18:46 - INFO - __main__ - Step 61031: {'lr': 0.00032811173607845455, 'samples': 11717952, 'steps': 61030, 'loss/train': 0.9069138765335083} 08/31/2021 00:18:46 - INFO - __main__ - Step 61032: {'lr': 0.0003281066949975404, 'samples': 11718144, 'steps': 61031, 'loss/train': 1.351637601852417} 08/31/2021 00:18:47 - INFO - __main__ - Step 61033: {'lr': 0.00032810165388143264, 'samples': 11718336, 'steps': 61032, 'loss/train': 1.7730392217636108} 08/31/2021 00:18:47 - INFO - __main__ - Step 61034: {'lr': 0.00032809661273013345, 'samples': 11718528, 'steps': 61033, 'loss/train': 1.2893695831298828} 08/31/2021 00:18:47 - INFO - __main__ - Step 61035: {'lr': 0.0003280915715436451, 'samples': 11718720, 'steps': 61034, 'loss/train': 1.8777556419372559} 08/31/2021 00:18:48 - INFO - __main__ - Step 61036: {'lr': 0.00032808653032196993, 'samples': 11718912, 'steps': 61035, 'loss/train': 0.8511022925376892} 08/31/2021 00:18:49 - INFO - __main__ - Step 61037: {'lr': 0.00032808148906511017, 'samples': 11719104, 'steps': 61036, 'loss/train': 0.9609043002128601} 08/31/2021 00:18:50 - INFO - __main__ - Step 61038: {'lr': 0.00032807644777306804, 'samples': 11719296, 'steps': 61037, 'loss/train': 0.2671143710613251} 08/31/2021 00:18:50 - INFO - __main__ - Step 61039: {'lr': 0.00032807140644584593, 'samples': 11719488, 'steps': 61038, 'loss/train': 1.2363827228546143} 08/31/2021 00:18:50 - INFO - __main__ - Step 61040: {'lr': 0.000328066365083446, 'samples': 11719680, 'steps': 61039, 'loss/train': 2.8801965713500977} 08/31/2021 00:18:51 - INFO - __main__ - Step 61041: {'lr': 0.0003280613236858707, 'samples': 11719872, 'steps': 61040, 'loss/train': 1.2371386289596558} 08/31/2021 00:18:53 - INFO - __main__ - Step 61042: {'lr': 0.000328056282253122, 'samples': 11720064, 'steps': 61041, 'loss/train': 0.7439656257629395} 08/31/2021 00:18:53 - INFO - __main__ - Step 61043: {'lr': 0.0003280512407852024, 'samples': 11720256, 'steps': 61042, 'loss/train': 1.2413874864578247} 08/31/2021 00:18:54 - INFO - __main__ - Step 61044: {'lr': 0.00032804619928211416, 'samples': 11720448, 'steps': 61043, 'loss/train': 1.4910584688186646} 08/31/2021 00:18:54 - INFO - __main__ - Step 61045: {'lr': 0.0003280411577438595, 'samples': 11720640, 'steps': 61044, 'loss/train': 0.39347589015960693} 08/31/2021 00:18:54 - INFO - __main__ - Step 61046: {'lr': 0.00032803611617044065, 'samples': 11720832, 'steps': 61045, 'loss/train': 2.3526036739349365} 08/31/2021 00:18:55 - INFO - __main__ - Step 61047: {'lr': 0.00032803107456186, 'samples': 11721024, 'steps': 61046, 'loss/train': 0.6442875266075134} 08/31/2021 00:18:56 - INFO - __main__ - Step 61048: {'lr': 0.00032802603291811965, 'samples': 11721216, 'steps': 61047, 'loss/train': 1.5090078115463257} 08/31/2021 00:18:57 - INFO - __main__ - Step 61049: {'lr': 0.00032802099123922204, 'samples': 11721408, 'steps': 61048, 'loss/train': 1.5666401386260986} 08/31/2021 00:18:57 - INFO - __main__ - Step 61050: {'lr': 0.00032801594952516934, 'samples': 11721600, 'steps': 61049, 'loss/train': 1.5682719945907593} 08/31/2021 00:18:57 - INFO - __main__ - Step 61051: {'lr': 0.0003280109077759639, 'samples': 11721792, 'steps': 61050, 'loss/train': 0.7576197385787964} 08/31/2021 00:18:58 - INFO - __main__ - Step 61052: {'lr': 0.000328005865991608, 'samples': 11721984, 'steps': 61051, 'loss/train': 1.193703055381775} 08/31/2021 00:18:58 - INFO - __main__ - Step 61053: {'lr': 0.0003280008241721038, 'samples': 11722176, 'steps': 61052, 'loss/train': 1.5048394203186035} 08/31/2021 00:18:59 - INFO - __main__ - Step 61054: {'lr': 0.00032799578231745353, 'samples': 11722368, 'steps': 61053, 'loss/train': 1.5158356428146362} 08/31/2021 00:19:00 - INFO - __main__ - Step 61055: {'lr': 0.0003279907404276596, 'samples': 11722560, 'steps': 61054, 'loss/train': 1.2846405506134033} 08/31/2021 00:19:00 - INFO - __main__ - Step 61056: {'lr': 0.00032798569850272434, 'samples': 11722752, 'steps': 61055, 'loss/train': 1.0021626949310303} 08/31/2021 00:19:01 - INFO - __main__ - Step 61057: {'lr': 0.00032798065654264996, 'samples': 11722944, 'steps': 61056, 'loss/train': 1.4858157634735107} 08/31/2021 00:19:01 - INFO - __main__ - Step 61058: {'lr': 0.00032797561454743864, 'samples': 11723136, 'steps': 61057, 'loss/train': 1.5950180292129517} 08/31/2021 00:19:03 - INFO - __main__ - Step 61059: {'lr': 0.00032797057251709267, 'samples': 11723328, 'steps': 61058, 'loss/train': 0.5621628761291504} 08/31/2021 00:19:03 - INFO - __main__ - Step 61060: {'lr': 0.0003279655304516144, 'samples': 11723520, 'steps': 61059, 'loss/train': 1.560630202293396} 08/31/2021 00:19:04 - INFO - __main__ - Step 61061: {'lr': 0.00032796048835100603, 'samples': 11723712, 'steps': 61060, 'loss/train': 0.041458528488874435} 08/31/2021 00:19:04 - INFO - __main__ - Step 61062: {'lr': 0.00032795544621527, 'samples': 11723904, 'steps': 61061, 'loss/train': 1.5827049016952515} 08/31/2021 00:19:04 - INFO - __main__ - Step 61063: {'lr': 0.0003279504040444083, 'samples': 11724096, 'steps': 61062, 'loss/train': 1.3766496181488037} 08/31/2021 00:19:05 - INFO - __main__ - Step 61064: {'lr': 0.0003279453618384234, 'samples': 11724288, 'steps': 61063, 'loss/train': 1.7317955493927002} 08/31/2021 00:19:06 - INFO - __main__ - Step 61065: {'lr': 0.0003279403195973175, 'samples': 11724480, 'steps': 61064, 'loss/train': 0.9640958905220032} 08/31/2021 00:19:07 - INFO - __main__ - Step 61066: {'lr': 0.0003279352773210929, 'samples': 11724672, 'steps': 61065, 'loss/train': 0.8561829328536987} 08/31/2021 00:19:07 - INFO - __main__ - Step 61067: {'lr': 0.0003279302350097519, 'samples': 11724864, 'steps': 61066, 'loss/train': 1.1107045412063599} 08/31/2021 00:19:07 - INFO - __main__ - Step 61068: {'lr': 0.00032792519266329674, 'samples': 11725056, 'steps': 61067, 'loss/train': 1.3815345764160156} 08/31/2021 00:19:08 - INFO - __main__ - Step 61069: {'lr': 0.00032792015028172965, 'samples': 11725248, 'steps': 61068, 'loss/train': 1.6764148473739624} 08/31/2021 00:19:10 - INFO - __main__ - Step 61070: {'lr': 0.00032791510786505296, 'samples': 11725440, 'steps': 61069, 'loss/train': 0.8220440149307251} 08/31/2021 00:19:10 - INFO - __main__ - Step 61071: {'lr': 0.00032791006541326893, 'samples': 11725632, 'steps': 61070, 'loss/train': 1.6422380208969116} 08/31/2021 00:19:11 - INFO - __main__ - Step 61072: {'lr': 0.0003279050229263798, 'samples': 11725824, 'steps': 61071, 'loss/train': 1.2191030979156494} 08/31/2021 00:19:11 - INFO - __main__ - Step 61073: {'lr': 0.0003278999804043879, 'samples': 11726016, 'steps': 61072, 'loss/train': 0.39788302779197693} 08/31/2021 00:19:11 - INFO - __main__ - Step 61074: {'lr': 0.0003278949378472955, 'samples': 11726208, 'steps': 61073, 'loss/train': 1.405429720878601} 08/31/2021 00:19:13 - INFO - __main__ - Step 61075: {'lr': 0.0003278898952551048, 'samples': 11726400, 'steps': 61074, 'loss/train': 1.3737901449203491} 08/31/2021 00:19:13 - INFO - __main__ - Step 61076: {'lr': 0.0003278848526278181, 'samples': 11726592, 'steps': 61075, 'loss/train': 1.5439820289611816} 08/31/2021 00:19:14 - INFO - __main__ - Step 61077: {'lr': 0.0003278798099654377, 'samples': 11726784, 'steps': 61076, 'loss/train': 1.3812949657440186} 08/31/2021 00:19:14 - INFO - __main__ - Step 61078: {'lr': 0.0003278747672679659, 'samples': 11726976, 'steps': 61077, 'loss/train': 1.5674508810043335} 08/31/2021 00:19:14 - INFO - __main__ - Step 61079: {'lr': 0.00032786972453540487, 'samples': 11727168, 'steps': 61078, 'loss/train': 0.11234335601329803} 08/31/2021 00:19:16 - INFO - __main__ - Step 61080: {'lr': 0.00032786468176775697, 'samples': 11727360, 'steps': 61079, 'loss/train': 0.05526755377650261} 08/31/2021 00:19:17 - INFO - __main__ - Step 61081: {'lr': 0.00032785963896502445, 'samples': 11727552, 'steps': 61080, 'loss/train': 1.416216254234314} 08/31/2021 00:19:17 - INFO - __main__ - Step 61082: {'lr': 0.0003278545961272096, 'samples': 11727744, 'steps': 61081, 'loss/train': 1.1813768148422241} 08/31/2021 00:19:17 - INFO - __main__ - Step 61083: {'lr': 0.00032784955325431466, 'samples': 11727936, 'steps': 61082, 'loss/train': 1.9838345050811768} 08/31/2021 00:19:18 - INFO - __main__ - Step 61084: {'lr': 0.0003278445103463419, 'samples': 11728128, 'steps': 61083, 'loss/train': 1.0289620161056519} 08/31/2021 00:19:18 - INFO - __main__ - Step 61085: {'lr': 0.00032783946740329355, 'samples': 11728320, 'steps': 61084, 'loss/train': 0.7302217483520508} 08/31/2021 00:19:19 - INFO - __main__ - Step 61086: {'lr': 0.00032783442442517203, 'samples': 11728512, 'steps': 61085, 'loss/train': 1.4677797555923462} 08/31/2021 00:19:20 - INFO - __main__ - Step 61087: {'lr': 0.0003278293814119795, 'samples': 11728704, 'steps': 61086, 'loss/train': 1.7066965103149414} 08/31/2021 00:19:20 - INFO - __main__ - Step 61088: {'lr': 0.0003278243383637182, 'samples': 11728896, 'steps': 61087, 'loss/train': 1.2087154388427734} 08/31/2021 00:19:21 - INFO - __main__ - Step 61089: {'lr': 0.0003278192952803905, 'samples': 11729088, 'steps': 61088, 'loss/train': 1.507563829421997} 08/31/2021 00:19:21 - INFO - __main__ - Step 61090: {'lr': 0.00032781425216199864, 'samples': 11729280, 'steps': 61089, 'loss/train': 1.3726431131362915} 08/31/2021 00:19:22 - INFO - __main__ - Step 61091: {'lr': 0.0003278092090085448, 'samples': 11729472, 'steps': 61090, 'loss/train': 1.4436445236206055} 08/31/2021 00:19:23 - INFO - __main__ - Step 61092: {'lr': 0.00032780416582003143, 'samples': 11729664, 'steps': 61091, 'loss/train': 1.9212977886199951} 08/31/2021 00:19:23 - INFO - __main__ - Step 61093: {'lr': 0.0003277991225964606, 'samples': 11729856, 'steps': 61092, 'loss/train': 1.5532174110412598} 08/31/2021 00:19:24 - INFO - __main__ - Step 61094: {'lr': 0.00032779407933783476, 'samples': 11730048, 'steps': 61093, 'loss/train': 1.5405871868133545} 08/31/2021 00:19:24 - INFO - __main__ - Step 61095: {'lr': 0.0003277890360441561, 'samples': 11730240, 'steps': 61094, 'loss/train': 1.7270458936691284} 08/31/2021 00:19:25 - INFO - __main__ - Step 61096: {'lr': 0.0003277839927154269, 'samples': 11730432, 'steps': 61095, 'loss/train': 1.5105092525482178} 08/31/2021 00:19:26 - INFO - __main__ - Step 61097: {'lr': 0.0003277789493516494, 'samples': 11730624, 'steps': 61096, 'loss/train': 1.7091821432113647} 08/31/2021 00:19:26 - INFO - __main__ - Step 61098: {'lr': 0.00032777390595282595, 'samples': 11730816, 'steps': 61097, 'loss/train': 1.5780292749404907} 08/31/2021 00:19:27 - INFO - __main__ - Step 61099: {'lr': 0.00032776886251895874, 'samples': 11731008, 'steps': 61098, 'loss/train': 1.8692671060562134} 08/31/2021 00:19:27 - INFO - __main__ - Step 61100: {'lr': 0.0003277638190500501, 'samples': 11731200, 'steps': 61099, 'loss/train': 1.1492915153503418} 08/31/2021 00:19:28 - INFO - __main__ - Step 61101: {'lr': 0.0003277587755461023, 'samples': 11731392, 'steps': 61100, 'loss/train': 0.5263776779174805} 08/31/2021 00:19:29 - INFO - __main__ - Step 61102: {'lr': 0.0003277537320071176, 'samples': 11731584, 'steps': 61101, 'loss/train': 1.5483336448669434} 08/31/2021 00:19:29 - INFO - __main__ - Step 61103: {'lr': 0.00032774868843309823, 'samples': 11731776, 'steps': 61102, 'loss/train': 1.2841910123825073} 08/31/2021 00:19:30 - INFO - __main__ - Step 61104: {'lr': 0.0003277436448240465, 'samples': 11731968, 'steps': 61103, 'loss/train': 1.6456305980682373} 08/31/2021 00:19:30 - INFO - __main__ - Step 61105: {'lr': 0.00032773860117996475, 'samples': 11732160, 'steps': 61104, 'loss/train': 1.2274614572525024} 08/31/2021 00:19:32 - INFO - __main__ - Step 61106: {'lr': 0.0003277335575008551, 'samples': 11732352, 'steps': 61105, 'loss/train': 1.6625293493270874} 08/31/2021 00:19:32 - INFO - __main__ - Step 61107: {'lr': 0.00032772851378672, 'samples': 11732544, 'steps': 61106, 'loss/train': 1.4460946321487427} 08/31/2021 00:19:33 - INFO - __main__ - Step 61108: {'lr': 0.00032772347003756153, 'samples': 11732736, 'steps': 61107, 'loss/train': 1.0599334239959717} 08/31/2021 00:19:33 - INFO - __main__ - Step 61109: {'lr': 0.0003277184262533821, 'samples': 11732928, 'steps': 61108, 'loss/train': 1.590850830078125} 08/31/2021 00:19:33 - INFO - __main__ - Step 61110: {'lr': 0.00032771338243418397, 'samples': 11733120, 'steps': 61109, 'loss/train': 0.880145251750946} 08/31/2021 00:19:35 - INFO - __main__ - Step 61111: {'lr': 0.0003277083385799694, 'samples': 11733312, 'steps': 61110, 'loss/train': 0.06853080540895462} 08/31/2021 00:19:35 - INFO - __main__ - Step 61112: {'lr': 0.0003277032946907406, 'samples': 11733504, 'steps': 61111, 'loss/train': 0.4581465423107147} 08/31/2021 00:19:36 - INFO - __main__ - Step 61113: {'lr': 0.0003276982507664999, 'samples': 11733696, 'steps': 61112, 'loss/train': 1.3159600496292114} 08/31/2021 00:19:36 - INFO - __main__ - Step 61114: {'lr': 0.00032769320680724954, 'samples': 11733888, 'steps': 61113, 'loss/train': 1.6719226837158203} 08/31/2021 00:19:36 - INFO - __main__ - Step 61115: {'lr': 0.00032768816281299195, 'samples': 11734080, 'steps': 61114, 'loss/train': 1.0182238817214966} 08/31/2021 00:19:38 - INFO - __main__ - Step 61116: {'lr': 0.0003276831187837292, 'samples': 11734272, 'steps': 61115, 'loss/train': 1.4083366394042969} 08/31/2021 00:19:38 - INFO - __main__ - Step 61117: {'lr': 0.00032767807471946366, 'samples': 11734464, 'steps': 61116, 'loss/train': 1.082654595375061} 08/31/2021 00:19:39 - INFO - __main__ - Step 61118: {'lr': 0.00032767303062019746, 'samples': 11734656, 'steps': 61117, 'loss/train': 1.3139147758483887} 08/31/2021 00:19:39 - INFO - __main__ - Step 61119: {'lr': 0.0003276679864859331, 'samples': 11734848, 'steps': 61118, 'loss/train': 1.4837007522583008} 08/31/2021 00:19:39 - INFO - __main__ - Step 61120: {'lr': 0.0003276629423166727, 'samples': 11735040, 'steps': 61119, 'loss/train': 1.8163628578186035} 08/31/2021 00:19:40 - INFO - __main__ - Step 61121: {'lr': 0.00032765789811241866, 'samples': 11735232, 'steps': 61120, 'loss/train': 1.9407447576522827} 08/31/2021 00:19:42 - INFO - __main__ - Step 61122: {'lr': 0.0003276528538731731, 'samples': 11735424, 'steps': 61121, 'loss/train': 2.051004409790039} 08/31/2021 00:19:42 - INFO - __main__ - Step 61123: {'lr': 0.0003276478095989384, 'samples': 11735616, 'steps': 61122, 'loss/train': 1.6110403537750244} 08/31/2021 00:19:43 - INFO - __main__ - Step 61124: {'lr': 0.0003276427652897167, 'samples': 11735808, 'steps': 61123, 'loss/train': 1.0905259847640991} 08/31/2021 00:19:43 - INFO - __main__ - Step 61125: {'lr': 0.0003276377209455104, 'samples': 11736000, 'steps': 61124, 'loss/train': 1.100840449333191} 08/31/2021 00:19:43 - INFO - __main__ - Step 61126: {'lr': 0.0003276326765663218, 'samples': 11736192, 'steps': 61125, 'loss/train': 1.444406270980835} 08/31/2021 00:19:45 - INFO - __main__ - Step 61127: {'lr': 0.0003276276321521531, 'samples': 11736384, 'steps': 61126, 'loss/train': 0.6600518226623535} 08/31/2021 00:19:46 - INFO - __main__ - Step 61128: {'lr': 0.00032762258770300656, 'samples': 11736576, 'steps': 61127, 'loss/train': 0.8549165725708008} 08/31/2021 00:19:46 - INFO - __main__ - Step 61129: {'lr': 0.0003276175432188845, 'samples': 11736768, 'steps': 61128, 'loss/train': 1.558617353439331} 08/31/2021 00:19:47 - INFO - __main__ - Step 61130: {'lr': 0.00032761249869978917, 'samples': 11736960, 'steps': 61129, 'loss/train': 1.8856247663497925} 08/31/2021 00:19:47 - INFO - __main__ - Step 61131: {'lr': 0.00032760745414572287, 'samples': 11737152, 'steps': 61130, 'loss/train': 0.0230430755764246} 08/31/2021 00:19:47 - INFO - __main__ - Step 61132: {'lr': 0.0003276024095566878, 'samples': 11737344, 'steps': 61131, 'loss/train': 0.023182177916169167} 08/31/2021 00:19:48 - INFO - __main__ - Step 61133: {'lr': 0.0003275973649326863, 'samples': 11737536, 'steps': 61132, 'loss/train': 1.4052624702453613} 08/31/2021 00:19:49 - INFO - __main__ - Step 61134: {'lr': 0.0003275923202737206, 'samples': 11737728, 'steps': 61133, 'loss/train': 3.955207109451294} 08/31/2021 00:19:50 - INFO - __main__ - Step 61135: {'lr': 0.00032758727557979304, 'samples': 11737920, 'steps': 61134, 'loss/train': 1.2735923528671265} 08/31/2021 00:19:50 - INFO - __main__ - Step 61136: {'lr': 0.00032758223085090586, 'samples': 11738112, 'steps': 61135, 'loss/train': 0.9468958973884583} 08/31/2021 00:19:51 - INFO - __main__ - Step 61137: {'lr': 0.0003275771860870613, 'samples': 11738304, 'steps': 61136, 'loss/train': 1.4523452520370483} 08/31/2021 00:19:51 - INFO - __main__ - Step 61138: {'lr': 0.0003275721412882616, 'samples': 11738496, 'steps': 61137, 'loss/train': 1.7736979722976685} 08/31/2021 00:19:52 - INFO - __main__ - Step 61139: {'lr': 0.00032756709645450916, 'samples': 11738688, 'steps': 61138, 'loss/train': 1.7052640914916992} 08/31/2021 00:19:53 - INFO - __main__ - Step 61140: {'lr': 0.00032756205158580615, 'samples': 11738880, 'steps': 61139, 'loss/train': 1.5109690427780151} 08/31/2021 00:19:53 - INFO - __main__ - Step 61141: {'lr': 0.00032755700668215496, 'samples': 11739072, 'steps': 61140, 'loss/train': 1.3310860395431519} 08/31/2021 00:19:54 - INFO - __main__ - Step 61142: {'lr': 0.0003275519617435577, 'samples': 11739264, 'steps': 61141, 'loss/train': 0.9538983106613159} 08/31/2021 00:19:54 - INFO - __main__ - Step 61143: {'lr': 0.00032754691677001674, 'samples': 11739456, 'steps': 61142, 'loss/train': 1.4271910190582275} 08/31/2021 00:19:56 - INFO - __main__ - Step 61144: {'lr': 0.0003275418717615343, 'samples': 11739648, 'steps': 61143, 'loss/train': 2.773566722869873} 08/31/2021 00:19:56 - INFO - __main__ - Step 61145: {'lr': 0.00032753682671811277, 'samples': 11739840, 'steps': 61144, 'loss/train': 1.286678433418274} 08/31/2021 00:19:56 - INFO - __main__ - Step 61146: {'lr': 0.00032753178163975427, 'samples': 11740032, 'steps': 61145, 'loss/train': 0.6474354863166809} 08/31/2021 00:19:57 - INFO - __main__ - Step 61147: {'lr': 0.00032752673652646115, 'samples': 11740224, 'steps': 61146, 'loss/train': 1.1163780689239502} 08/31/2021 00:19:57 - INFO - __main__ - Step 61148: {'lr': 0.00032752169137823575, 'samples': 11740416, 'steps': 61147, 'loss/train': 0.7857344150543213} 08/31/2021 00:19:59 - INFO - __main__ - Step 61149: {'lr': 0.0003275166461950802, 'samples': 11740608, 'steps': 61148, 'loss/train': 1.5075643062591553} 08/31/2021 00:19:59 - INFO - __main__ - Step 61150: {'lr': 0.0003275116009769969, 'samples': 11740800, 'steps': 61149, 'loss/train': 1.4889731407165527} 08/31/2021 00:19:59 - INFO - __main__ - Step 61151: {'lr': 0.000327506555723988, 'samples': 11740992, 'steps': 61150, 'loss/train': 1.0703009366989136} 08/31/2021 00:20:00 - INFO - __main__ - Step 61152: {'lr': 0.00032750151043605584, 'samples': 11741184, 'steps': 61151, 'loss/train': 2.0273659229278564} 08/31/2021 00:20:00 - INFO - __main__ - Step 61153: {'lr': 0.00032749646511320276, 'samples': 11741376, 'steps': 61152, 'loss/train': 0.9114996790885925} 08/31/2021 00:20:00 - INFO - __main__ - Step 61154: {'lr': 0.00032749141975543095, 'samples': 11741568, 'steps': 61153, 'loss/train': 0.7823309302330017} 08/31/2021 00:20:02 - INFO - __main__ - Step 61155: {'lr': 0.0003274863743627427, 'samples': 11741760, 'steps': 61154, 'loss/train': 1.442337989807129} 08/31/2021 00:20:02 - INFO - __main__ - Step 61156: {'lr': 0.00032748132893514027, 'samples': 11741952, 'steps': 61155, 'loss/train': 1.5938256978988647} 08/31/2021 00:20:03 - INFO - __main__ - Step 61157: {'lr': 0.00032747628347262595, 'samples': 11742144, 'steps': 61156, 'loss/train': 1.5276442766189575} 08/31/2021 00:20:03 - INFO - __main__ - Step 61158: {'lr': 0.00032747123797520207, 'samples': 11742336, 'steps': 61157, 'loss/train': 1.6072266101837158} 08/31/2021 00:20:03 - INFO - __main__ - Step 61159: {'lr': 0.0003274661924428707, 'samples': 11742528, 'steps': 61158, 'loss/train': 1.3707114458084106} 08/31/2021 00:20:05 - INFO - __main__ - Step 61160: {'lr': 0.0003274611468756344, 'samples': 11742720, 'steps': 61159, 'loss/train': 1.003156304359436} 08/31/2021 00:20:06 - INFO - __main__ - Step 61161: {'lr': 0.00032745610127349524, 'samples': 11742912, 'steps': 61160, 'loss/train': 0.47165486216545105} 08/31/2021 00:20:06 - INFO - __main__ - Step 61162: {'lr': 0.0003274510556364556, 'samples': 11743104, 'steps': 61161, 'loss/train': 0.6438629031181335} 08/31/2021 00:20:06 - INFO - __main__ - Step 61163: {'lr': 0.00032744600996451766, 'samples': 11743296, 'steps': 61162, 'loss/train': 0.2054624706506729} 08/31/2021 00:20:07 - INFO - __main__ - Step 61164: {'lr': 0.00032744096425768376, 'samples': 11743488, 'steps': 61163, 'loss/train': 0.5543643832206726} 08/31/2021 00:20:08 - INFO - __main__ - Step 61165: {'lr': 0.0003274359185159562, 'samples': 11743680, 'steps': 61164, 'loss/train': 5.060672283172607} 08/31/2021 00:20:09 - INFO - __main__ - Step 61166: {'lr': 0.00032743087273933715, 'samples': 11743872, 'steps': 61165, 'loss/train': 1.5116273164749146} 08/31/2021 00:20:09 - INFO - __main__ - Step 61167: {'lr': 0.00032742582692782895, 'samples': 11744064, 'steps': 61166, 'loss/train': 1.042984127998352} 08/31/2021 00:20:09 - INFO - __main__ - Step 61168: {'lr': 0.00032742078108143394, 'samples': 11744256, 'steps': 61167, 'loss/train': 1.6195974349975586} 08/31/2021 00:20:10 - INFO - __main__ - Step 61169: {'lr': 0.0003274157352001543, 'samples': 11744448, 'steps': 61168, 'loss/train': 0.8830614686012268} 08/31/2021 00:20:11 - INFO - __main__ - Step 61170: {'lr': 0.0003274106892839923, 'samples': 11744640, 'steps': 61169, 'loss/train': 1.2835217714309692} 08/31/2021 00:20:12 - INFO - __main__ - Step 61171: {'lr': 0.00032740564333295013, 'samples': 11744832, 'steps': 61170, 'loss/train': 1.7069846391677856} 08/31/2021 00:20:12 - INFO - __main__ - Step 61172: {'lr': 0.00032740059734703034, 'samples': 11745024, 'steps': 61171, 'loss/train': 1.2707682847976685} 08/31/2021 00:20:12 - INFO - __main__ - Step 61173: {'lr': 0.0003273955513262349, 'samples': 11745216, 'steps': 61172, 'loss/train': 1.9661275148391724} 08/31/2021 00:20:13 - INFO - __main__ - Step 61174: {'lr': 0.0003273905052705663, 'samples': 11745408, 'steps': 61173, 'loss/train': 2.02245831489563} 08/31/2021 00:20:14 - INFO - __main__ - Step 61175: {'lr': 0.0003273854591800267, 'samples': 11745600, 'steps': 61174, 'loss/train': 1.3822482824325562} 08/31/2021 00:20:15 - INFO - __main__ - Step 61176: {'lr': 0.00032738041305461845, 'samples': 11745792, 'steps': 61175, 'loss/train': 1.3674185276031494} 08/31/2021 00:20:15 - INFO - __main__ - Step 61177: {'lr': 0.00032737536689434377, 'samples': 11745984, 'steps': 61176, 'loss/train': 1.2052803039550781} 08/31/2021 00:20:15 - INFO - __main__ - Step 61178: {'lr': 0.00032737032069920494, 'samples': 11746176, 'steps': 61177, 'loss/train': 1.3770087957382202} 08/31/2021 00:20:16 - INFO - __main__ - Step 61179: {'lr': 0.0003273652744692042, 'samples': 11746368, 'steps': 61178, 'loss/train': 1.2967581748962402} 08/31/2021 00:20:18 - INFO - __main__ - Step 61180: {'lr': 0.0003273602282043439, 'samples': 11746560, 'steps': 61179, 'loss/train': 1.257643461227417} 08/31/2021 00:20:18 - INFO - __main__ - Step 61181: {'lr': 0.0003273551819046263, 'samples': 11746752, 'steps': 61180, 'loss/train': 1.313439130783081} 08/31/2021 00:20:18 - INFO - __main__ - Step 61182: {'lr': 0.00032735013557005357, 'samples': 11746944, 'steps': 61181, 'loss/train': 1.0963799953460693} 08/31/2021 00:20:19 - INFO - __main__ - Step 61183: {'lr': 0.00032734508920062805, 'samples': 11747136, 'steps': 61182, 'loss/train': 1.4408990144729614} 08/31/2021 00:20:19 - INFO - __main__ - Step 61184: {'lr': 0.0003273400427963521, 'samples': 11747328, 'steps': 61183, 'loss/train': 1.2016987800598145} 08/31/2021 00:20:19 - INFO - __main__ - Step 61185: {'lr': 0.0003273349963572279, 'samples': 11747520, 'steps': 61184, 'loss/train': 0.32649290561676025} 08/31/2021 00:20:21 - INFO - __main__ - Step 61186: {'lr': 0.0003273299498832578, 'samples': 11747712, 'steps': 61185, 'loss/train': 1.0214259624481201} 08/31/2021 00:20:21 - INFO - __main__ - Step 61187: {'lr': 0.00032732490337444387, 'samples': 11747904, 'steps': 61186, 'loss/train': 1.5396941900253296} 08/31/2021 00:20:22 - INFO - __main__ - Step 61188: {'lr': 0.0003273198568307886, 'samples': 11748096, 'steps': 61187, 'loss/train': 1.8003039360046387} 08/31/2021 00:20:22 - INFO - __main__ - Step 61189: {'lr': 0.0003273148102522943, 'samples': 11748288, 'steps': 61188, 'loss/train': 1.649388074874878} 08/31/2021 00:20:22 - INFO - __main__ - Step 61190: {'lr': 0.00032730976363896296, 'samples': 11748480, 'steps': 61189, 'loss/train': 0.04684526473283768} 08/31/2021 00:20:24 - INFO - __main__ - Step 61191: {'lr': 0.00032730471699079724, 'samples': 11748672, 'steps': 61190, 'loss/train': 1.363345980644226} 08/31/2021 00:20:24 - INFO - __main__ - Step 61192: {'lr': 0.00032729967030779904, 'samples': 11748864, 'steps': 61191, 'loss/train': 1.5105751752853394} 08/31/2021 00:20:25 - INFO - __main__ - Step 61193: {'lr': 0.00032729462358997084, 'samples': 11749056, 'steps': 61192, 'loss/train': 1.947221279144287} 08/31/2021 00:20:25 - INFO - __main__ - Step 61194: {'lr': 0.0003272895768373149, 'samples': 11749248, 'steps': 61193, 'loss/train': 1.2125365734100342} 08/31/2021 00:20:25 - INFO - __main__ - Step 61195: {'lr': 0.0003272845300498335, 'samples': 11749440, 'steps': 61194, 'loss/train': 1.2553117275238037} 08/31/2021 00:20:27 - INFO - __main__ - Step 61196: {'lr': 0.00032727948322752883, 'samples': 11749632, 'steps': 61195, 'loss/train': 1.4062708616256714} 08/31/2021 00:20:27 - INFO - __main__ - Step 61197: {'lr': 0.0003272744363704032, 'samples': 11749824, 'steps': 61196, 'loss/train': 1.462844967842102} 08/31/2021 00:20:28 - INFO - __main__ - Step 61198: {'lr': 0.00032726938947845897, 'samples': 11750016, 'steps': 61197, 'loss/train': 0.8005989789962769} 08/31/2021 00:20:28 - INFO - __main__ - Step 61199: {'lr': 0.0003272643425516983, 'samples': 11750208, 'steps': 61198, 'loss/train': 0.8861374855041504} 08/31/2021 00:20:28 - INFO - __main__ - Step 61200: {'lr': 0.0003272592955901235, 'samples': 11750400, 'steps': 61199, 'loss/train': 1.684177279472351} 08/31/2021 00:20:30 - INFO - __main__ - Step 61201: {'lr': 0.00032725424859373687, 'samples': 11750592, 'steps': 61200, 'loss/train': 1.3542227745056152} 08/31/2021 00:20:30 - INFO - __main__ - Step 61202: {'lr': 0.00032724920156254074, 'samples': 11750784, 'steps': 61201, 'loss/train': 0.9960847496986389} 08/31/2021 00:20:31 - INFO - __main__ - Step 61203: {'lr': 0.0003272441544965372, 'samples': 11750976, 'steps': 61202, 'loss/train': 0.7249767184257507} 08/31/2021 00:20:31 - INFO - __main__ - Step 61204: {'lr': 0.0003272391073957287, 'samples': 11751168, 'steps': 61203, 'loss/train': 1.1000840663909912} 08/31/2021 00:20:31 - INFO - __main__ - Step 61205: {'lr': 0.00032723406026011735, 'samples': 11751360, 'steps': 61204, 'loss/train': 1.5033016204833984} 08/31/2021 00:20:32 - INFO - __main__ - Step 61206: {'lr': 0.00032722901308970565, 'samples': 11751552, 'steps': 61205, 'loss/train': 0.7867974638938904} 08/31/2021 00:20:33 - INFO - __main__ - Step 61207: {'lr': 0.00032722396588449567, 'samples': 11751744, 'steps': 61206, 'loss/train': 1.2952877283096313} 08/31/2021 00:20:34 - INFO - __main__ - Step 61208: {'lr': 0.00032721891864448985, 'samples': 11751936, 'steps': 61207, 'loss/train': 1.907981514930725} 08/31/2021 00:20:34 - INFO - __main__ - Step 61209: {'lr': 0.00032721387136969035, 'samples': 11752128, 'steps': 61208, 'loss/train': 1.0281286239624023} 08/31/2021 00:20:34 - INFO - __main__ - Step 61210: {'lr': 0.0003272088240600994, 'samples': 11752320, 'steps': 61209, 'loss/train': 1.474767804145813} 08/31/2021 00:20:35 - INFO - __main__ - Step 61211: {'lr': 0.0003272037767157194, 'samples': 11752512, 'steps': 61210, 'loss/train': 1.308868408203125} 08/31/2021 00:20:36 - INFO - __main__ - Step 61212: {'lr': 0.00032719872933655253, 'samples': 11752704, 'steps': 61211, 'loss/train': 1.630486011505127} 08/31/2021 00:20:37 - INFO - __main__ - Step 61213: {'lr': 0.0003271936819226011, 'samples': 11752896, 'steps': 61212, 'loss/train': 0.9101489186286926} 08/31/2021 00:20:37 - INFO - __main__ - Step 61214: {'lr': 0.00032718863447386745, 'samples': 11753088, 'steps': 61213, 'loss/train': 1.3155701160430908} 08/31/2021 00:20:38 - INFO - __main__ - Step 61215: {'lr': 0.0003271835869903537, 'samples': 11753280, 'steps': 61214, 'loss/train': 0.825534462928772} 08/31/2021 00:20:38 - INFO - __main__ - Step 61216: {'lr': 0.0003271785394720623, 'samples': 11753472, 'steps': 61215, 'loss/train': 0.8008548617362976} 08/31/2021 00:20:39 - INFO - __main__ - Step 61217: {'lr': 0.0003271734919189955, 'samples': 11753664, 'steps': 61216, 'loss/train': 1.0594099760055542} 08/31/2021 00:20:40 - INFO - __main__ - Step 61218: {'lr': 0.0003271684443311554, 'samples': 11753856, 'steps': 61217, 'loss/train': 1.247135877609253} 08/31/2021 00:20:40 - INFO - __main__ - Step 61219: {'lr': 0.0003271633967085444, 'samples': 11754048, 'steps': 61218, 'loss/train': 1.0369118452072144} 08/31/2021 00:20:41 - INFO - __main__ - Step 61220: {'lr': 0.00032715834905116474, 'samples': 11754240, 'steps': 61219, 'loss/train': 1.395243525505066} 08/31/2021 00:20:41 - INFO - __main__ - Step 61221: {'lr': 0.0003271533013590188, 'samples': 11754432, 'steps': 61220, 'loss/train': 0.7759563326835632} 08/31/2021 00:20:42 - INFO - __main__ - Step 61222: {'lr': 0.0003271482536321088, 'samples': 11754624, 'steps': 61221, 'loss/train': 1.3067792654037476} 08/31/2021 00:20:43 - INFO - __main__ - Step 61223: {'lr': 0.00032714320587043686, 'samples': 11754816, 'steps': 61222, 'loss/train': 1.444617748260498} 08/31/2021 00:20:43 - INFO - __main__ - Step 61224: {'lr': 0.0003271381580740055, 'samples': 11755008, 'steps': 61223, 'loss/train': 1.1963424682617188} 08/31/2021 00:20:44 - INFO - __main__ - Step 61225: {'lr': 0.0003271331102428168, 'samples': 11755200, 'steps': 61224, 'loss/train': 1.1987119913101196} 08/31/2021 00:20:44 - INFO - __main__ - Step 61226: {'lr': 0.0003271280623768731, 'samples': 11755392, 'steps': 61225, 'loss/train': 0.9269762635231018} 08/31/2021 00:20:44 - INFO - __main__ - Step 61227: {'lr': 0.00032712301447617673, 'samples': 11755584, 'steps': 61226, 'loss/train': 1.4210556745529175} 08/31/2021 00:20:46 - INFO - __main__ - Step 61228: {'lr': 0.0003271179665407299, 'samples': 11755776, 'steps': 61227, 'loss/train': 1.0656934976577759} 08/31/2021 00:20:46 - INFO - __main__ - Step 61229: {'lr': 0.0003271129185705349, 'samples': 11755968, 'steps': 61228, 'loss/train': 1.0045796632766724} 08/31/2021 00:20:47 - INFO - __main__ - Step 61230: {'lr': 0.00032710787056559404, 'samples': 11756160, 'steps': 61229, 'loss/train': 1.9128682613372803} 08/31/2021 00:20:47 - INFO - __main__ - Step 61231: {'lr': 0.00032710282252590954, 'samples': 11756352, 'steps': 61230, 'loss/train': 0.6251883506774902} 08/31/2021 00:20:47 - INFO - __main__ - Step 61232: {'lr': 0.00032709777445148367, 'samples': 11756544, 'steps': 61231, 'loss/train': 1.1070295572280884} 08/31/2021 00:20:49 - INFO - __main__ - Step 61233: {'lr': 0.0003270927263423188, 'samples': 11756736, 'steps': 61232, 'loss/train': 1.306586503982544} 08/31/2021 00:20:50 - INFO - __main__ - Step 61234: {'lr': 0.0003270876781984171, 'samples': 11756928, 'steps': 61233, 'loss/train': 2.0031120777130127} 08/31/2021 00:20:50 - INFO - __main__ - Step 61235: {'lr': 0.0003270826300197809, 'samples': 11757120, 'steps': 61234, 'loss/train': 0.9297638535499573} 08/31/2021 00:20:51 - INFO - __main__ - Step 61236: {'lr': 0.00032707758180641245, 'samples': 11757312, 'steps': 61235, 'loss/train': 1.6073139905929565} 08/31/2021 00:20:51 - INFO - __main__ - Step 61237: {'lr': 0.000327072533558314, 'samples': 11757504, 'steps': 61236, 'loss/train': 1.7208237648010254} 08/31/2021 00:20:52 - INFO - __main__ - Step 61238: {'lr': 0.00032706748527548793, 'samples': 11757696, 'steps': 61237, 'loss/train': 2.0510239601135254} 08/31/2021 00:20:53 - INFO - __main__ - Step 61239: {'lr': 0.00032706243695793634, 'samples': 11757888, 'steps': 61238, 'loss/train': 1.692330002784729} 08/31/2021 00:20:53 - INFO - __main__ - Step 61240: {'lr': 0.00032705738860566166, 'samples': 11758080, 'steps': 61239, 'loss/train': 1.3163203001022339} 08/31/2021 00:20:54 - INFO - __main__ - Step 61241: {'lr': 0.0003270523402186661, 'samples': 11758272, 'steps': 61240, 'loss/train': 1.1207728385925293} 08/31/2021 00:20:54 - INFO - __main__ - Step 61242: {'lr': 0.0003270472917969519, 'samples': 11758464, 'steps': 61241, 'loss/train': 1.0566020011901855} 08/31/2021 00:20:55 - INFO - __main__ - Step 61243: {'lr': 0.0003270422433405215, 'samples': 11758656, 'steps': 61242, 'loss/train': 1.5804052352905273} 08/31/2021 00:20:56 - INFO - __main__ - Step 61244: {'lr': 0.000327037194849377, 'samples': 11758848, 'steps': 61243, 'loss/train': 1.185219168663025} 08/31/2021 00:20:56 - INFO - __main__ - Step 61245: {'lr': 0.0003270321463235207, 'samples': 11759040, 'steps': 61244, 'loss/train': 1.7715961933135986} 08/31/2021 00:20:57 - INFO - __main__ - Step 61246: {'lr': 0.00032702709776295493, 'samples': 11759232, 'steps': 61245, 'loss/train': 1.2961440086364746} 08/31/2021 00:20:57 - INFO - __main__ - Step 61247: {'lr': 0.00032702204916768186, 'samples': 11759424, 'steps': 61246, 'loss/train': 1.884964942932129} 08/31/2021 00:20:58 - INFO - __main__ - Step 61248: {'lr': 0.00032701700053770386, 'samples': 11759616, 'steps': 61247, 'loss/train': 1.2012170553207397} 08/31/2021 00:20:59 - INFO - __main__ - Step 61249: {'lr': 0.00032701195187302337, 'samples': 11759808, 'steps': 61248, 'loss/train': 1.483516812324524} 08/31/2021 00:20:59 - INFO - __main__ - Step 61250: {'lr': 0.0003270069031736423, 'samples': 11760000, 'steps': 61249, 'loss/train': 1.4483683109283447} 08/31/2021 00:20:59 - INFO - __main__ - Step 61251: {'lr': 0.00032700185443956315, 'samples': 11760192, 'steps': 61250, 'loss/train': 1.2277618646621704} 08/31/2021 00:21:00 - INFO - __main__ - Step 61252: {'lr': 0.00032699680567078814, 'samples': 11760384, 'steps': 61251, 'loss/train': 0.567305326461792} 08/31/2021 00:21:01 - INFO - __main__ - Step 61253: {'lr': 0.0003269917568673196, 'samples': 11760576, 'steps': 61252, 'loss/train': 1.228359341621399} 08/31/2021 00:21:02 - INFO - __main__ - Step 61254: {'lr': 0.0003269867080291597, 'samples': 11760768, 'steps': 61253, 'loss/train': 1.2067729234695435} 08/31/2021 00:21:02 - INFO - __main__ - Step 61255: {'lr': 0.0003269816591563108, 'samples': 11760960, 'steps': 61254, 'loss/train': 1.3617606163024902} 08/31/2021 00:21:03 - INFO - __main__ - Step 61256: {'lr': 0.0003269766102487752, 'samples': 11761152, 'steps': 61255, 'loss/train': 1.2801610231399536} 08/31/2021 00:21:03 - INFO - __main__ - Step 61257: {'lr': 0.00032697156130655507, 'samples': 11761344, 'steps': 61256, 'loss/train': 1.7355157136917114} 08/31/2021 00:21:04 - INFO - __main__ - Step 61258: {'lr': 0.0003269665123296528, 'samples': 11761536, 'steps': 61257, 'loss/train': 1.2448410987854004} 08/31/2021 00:21:05 - INFO - __main__ - Step 61259: {'lr': 0.0003269614633180705, 'samples': 11761728, 'steps': 61258, 'loss/train': 1.3955192565917969} 08/31/2021 00:21:05 - INFO - __main__ - Step 61260: {'lr': 0.00032695641427181064, 'samples': 11761920, 'steps': 61259, 'loss/train': 1.7894303798675537} 08/31/2021 00:21:06 - INFO - __main__ - Step 61261: {'lr': 0.00032695136519087545, 'samples': 11762112, 'steps': 61260, 'loss/train': 1.4900646209716797} 08/31/2021 00:21:06 - INFO - __main__ - Step 61262: {'lr': 0.00032694631607526703, 'samples': 11762304, 'steps': 61261, 'loss/train': 0.6922158598899841} 08/31/2021 00:21:06 - INFO - __main__ - Step 61263: {'lr': 0.00032694126692498794, 'samples': 11762496, 'steps': 61262, 'loss/train': 2.0844664573669434} 08/31/2021 00:21:08 - INFO - __main__ - Step 61264: {'lr': 0.00032693621774004025, 'samples': 11762688, 'steps': 61263, 'loss/train': 0.7161959409713745} 08/31/2021 00:21:09 - INFO - __main__ - Step 61265: {'lr': 0.0003269311685204262, 'samples': 11762880, 'steps': 61264, 'loss/train': 1.1176773309707642} 08/31/2021 00:21:09 - INFO - __main__ - Step 61266: {'lr': 0.00032692611926614823, 'samples': 11763072, 'steps': 61265, 'loss/train': 1.0953627824783325} 08/31/2021 00:21:09 - INFO - __main__ - Step 61267: {'lr': 0.00032692106997720847, 'samples': 11763264, 'steps': 61266, 'loss/train': 1.8049408197402954} 08/31/2021 00:21:10 - INFO - __main__ - Step 61268: {'lr': 0.0003269160206536093, 'samples': 11763456, 'steps': 61267, 'loss/train': 1.3782100677490234} 08/31/2021 00:21:11 - INFO - __main__ - Step 61269: {'lr': 0.0003269109712953531, 'samples': 11763648, 'steps': 61268, 'loss/train': 1.4210937023162842} 08/31/2021 00:21:12 - INFO - __main__ - Step 61270: {'lr': 0.0003269059219024418, 'samples': 11763840, 'steps': 61269, 'loss/train': 0.7435450553894043} 08/31/2021 00:21:12 - INFO - __main__ - Step 61271: {'lr': 0.00032690087247487797, 'samples': 11764032, 'steps': 61270, 'loss/train': 1.3170247077941895} 08/31/2021 00:21:12 - INFO - __main__ - Step 61272: {'lr': 0.0003268958230126637, 'samples': 11764224, 'steps': 61271, 'loss/train': 0.4133140444755554} 08/31/2021 00:21:13 - INFO - __main__ - Step 61273: {'lr': 0.00032689077351580147, 'samples': 11764416, 'steps': 61272, 'loss/train': 0.9075626134872437} 08/31/2021 00:21:15 - INFO - __main__ - Step 61274: {'lr': 0.00032688572398429337, 'samples': 11764608, 'steps': 61273, 'loss/train': 1.5067369937896729} 08/31/2021 00:21:15 - INFO - __main__ - Step 61275: {'lr': 0.0003268806744181418, 'samples': 11764800, 'steps': 61274, 'loss/train': 0.1887337565422058} 08/31/2021 00:21:16 - INFO - __main__ - Step 61276: {'lr': 0.0003268756248173491, 'samples': 11764992, 'steps': 61275, 'loss/train': 1.3513767719268799} 08/31/2021 00:21:16 - INFO - __main__ - Step 61277: {'lr': 0.0003268705751819173, 'samples': 11765184, 'steps': 61276, 'loss/train': 2.086031913757324} 08/31/2021 00:21:16 - INFO - __main__ - Step 61278: {'lr': 0.00032686552551184874, 'samples': 11765376, 'steps': 61277, 'loss/train': 1.1325925588607788} 08/31/2021 00:21:17 - INFO - __main__ - Step 61279: {'lr': 0.00032686047580714585, 'samples': 11765568, 'steps': 61278, 'loss/train': 1.1796436309814453} 08/31/2021 00:21:18 - INFO - __main__ - Step 61280: {'lr': 0.0003268554260678108, 'samples': 11765760, 'steps': 61279, 'loss/train': 0.8051164150238037} 08/31/2021 00:21:19 - INFO - __main__ - Step 61281: {'lr': 0.00032685037629384586, 'samples': 11765952, 'steps': 61280, 'loss/train': 1.43119215965271} 08/31/2021 00:21:19 - INFO - __main__ - Step 61282: {'lr': 0.0003268453264852533, 'samples': 11766144, 'steps': 61281, 'loss/train': 0.04922258481383324} 08/31/2021 00:21:20 - INFO - __main__ - Step 61283: {'lr': 0.0003268402766420355, 'samples': 11766336, 'steps': 61282, 'loss/train': 1.3817238807678223} 08/31/2021 00:21:20 - INFO - __main__ - Step 61284: {'lr': 0.00032683522676419465, 'samples': 11766528, 'steps': 61283, 'loss/train': 1.652438998222351} 08/31/2021 00:21:20 - INFO - __main__ - Step 61285: {'lr': 0.000326830176851733, 'samples': 11766720, 'steps': 61284, 'loss/train': 1.522010087966919} 08/31/2021 00:21:22 - INFO - __main__ - Step 61286: {'lr': 0.00032682512690465284, 'samples': 11766912, 'steps': 61285, 'loss/train': 0.6142302751541138} 08/31/2021 00:21:22 - INFO - __main__ - Step 61287: {'lr': 0.00032682007692295647, 'samples': 11767104, 'steps': 61286, 'loss/train': 1.3081895112991333} 08/31/2021 00:21:22 - INFO - __main__ - Step 61288: {'lr': 0.0003268150269066462, 'samples': 11767296, 'steps': 61287, 'loss/train': 1.4275108575820923} 08/31/2021 00:21:23 - INFO - __main__ - Step 61289: {'lr': 0.0003268099768557242, 'samples': 11767488, 'steps': 61288, 'loss/train': 1.0768778324127197} 08/31/2021 00:21:23 - INFO - __main__ - Step 61290: {'lr': 0.00032680492677019285, 'samples': 11767680, 'steps': 61289, 'loss/train': 2.0059404373168945} 08/31/2021 00:21:25 - INFO - __main__ - Step 61291: {'lr': 0.0003267998766500544, 'samples': 11767872, 'steps': 61290, 'loss/train': 1.4630860090255737} 08/31/2021 00:21:26 - INFO - __main__ - Step 61292: {'lr': 0.00032679482649531104, 'samples': 11768064, 'steps': 61291, 'loss/train': 2.1287600994110107} 08/31/2021 00:21:26 - INFO - __main__ - Step 61293: {'lr': 0.00032678977630596517, 'samples': 11768256, 'steps': 61292, 'loss/train': 1.9810289144515991} 08/31/2021 00:21:26 - INFO - __main__ - Step 61294: {'lr': 0.00032678472608201905, 'samples': 11768448, 'steps': 61293, 'loss/train': 1.055755853652954} 08/31/2021 00:21:27 - INFO - __main__ - Step 61295: {'lr': 0.00032677967582347484, 'samples': 11768640, 'steps': 61294, 'loss/train': 1.3414320945739746} 08/31/2021 00:21:28 - INFO - __main__ - Step 61296: {'lr': 0.000326774625530335, 'samples': 11768832, 'steps': 61295, 'loss/train': 0.6420021057128906} 08/31/2021 00:21:29 - INFO - __main__ - Step 61297: {'lr': 0.00032676957520260156, 'samples': 11769024, 'steps': 61296, 'loss/train': 0.8865283131599426} 08/31/2021 00:21:29 - INFO - __main__ - Step 61298: {'lr': 0.00032676452484027704, 'samples': 11769216, 'steps': 61297, 'loss/train': 1.30565345287323} 08/31/2021 00:21:29 - INFO - __main__ - Step 61299: {'lr': 0.0003267594744433636, 'samples': 11769408, 'steps': 61298, 'loss/train': 1.271059513092041} 08/31/2021 00:21:30 - INFO - __main__ - Step 61300: {'lr': 0.00032675442401186344, 'samples': 11769600, 'steps': 61299, 'loss/train': 1.3196715116500854} 08/31/2021 00:21:31 - INFO - __main__ - Step 61301: {'lr': 0.000326749373545779, 'samples': 11769792, 'steps': 61300, 'loss/train': 1.8951236009597778} 08/31/2021 00:21:32 - INFO - __main__ - Step 61302: {'lr': 0.00032674432304511243, 'samples': 11769984, 'steps': 61301, 'loss/train': 1.32239830493927} 08/31/2021 00:21:32 - INFO - __main__ - Step 61303: {'lr': 0.0003267392725098661, 'samples': 11770176, 'steps': 61302, 'loss/train': 0.467693954706192} 08/31/2021 00:21:32 - INFO - __main__ - Step 61304: {'lr': 0.0003267342219400422, 'samples': 11770368, 'steps': 61303, 'loss/train': 0.7526280879974365} 08/31/2021 00:21:33 - INFO - __main__ - Step 61305: {'lr': 0.00032672917133564304, 'samples': 11770560, 'steps': 61304, 'loss/train': 1.3240830898284912} 08/31/2021 00:21:34 - INFO - __main__ - Step 61306: {'lr': 0.00032672412069667094, 'samples': 11770752, 'steps': 61305, 'loss/train': 2.525357246398926} 08/31/2021 00:21:35 - INFO - __main__ - Step 61307: {'lr': 0.00032671907002312814, 'samples': 11770944, 'steps': 61306, 'loss/train': 2.2069361209869385} 08/31/2021 00:21:35 - INFO - __main__ - Step 61308: {'lr': 0.0003267140193150169, 'samples': 11771136, 'steps': 61307, 'loss/train': 1.122924566268921} 08/31/2021 00:21:35 - INFO - __main__ - Step 61309: {'lr': 0.0003267089685723395, 'samples': 11771328, 'steps': 61308, 'loss/train': 1.416560411453247} 08/31/2021 00:21:36 - INFO - __main__ - Step 61310: {'lr': 0.00032670391779509824, 'samples': 11771520, 'steps': 61309, 'loss/train': 0.2908235192298889} 08/31/2021 00:21:37 - INFO - __main__ - Step 61311: {'lr': 0.0003266988669832953, 'samples': 11771712, 'steps': 61310, 'loss/train': 1.3817726373672485} 08/31/2021 00:21:38 - INFO - __main__ - Step 61312: {'lr': 0.00032669381613693307, 'samples': 11771904, 'steps': 61311, 'loss/train': 1.002173900604248} 08/31/2021 00:21:38 - INFO - __main__ - Step 61313: {'lr': 0.00032668876525601383, 'samples': 11772096, 'steps': 61312, 'loss/train': 1.6699888706207275} 08/31/2021 00:21:38 - INFO - __main__ - Step 61314: {'lr': 0.00032668371434053977, 'samples': 11772288, 'steps': 61313, 'loss/train': 1.3260730504989624} 08/31/2021 00:21:39 - INFO - __main__ - Step 61315: {'lr': 0.00032667866339051326, 'samples': 11772480, 'steps': 61314, 'loss/train': 1.9837570190429688} 08/31/2021 00:21:40 - INFO - __main__ - Step 61316: {'lr': 0.0003266736124059365, 'samples': 11772672, 'steps': 61315, 'loss/train': 1.6358872652053833} 08/31/2021 00:21:41 - INFO - __main__ - Step 61317: {'lr': 0.0003266685613868118, 'samples': 11772864, 'steps': 61316, 'loss/train': 1.5299158096313477} 08/31/2021 00:21:41 - INFO - __main__ - Step 61318: {'lr': 0.0003266635103331414, 'samples': 11773056, 'steps': 61317, 'loss/train': 1.6048800945281982} 08/31/2021 00:21:41 - INFO - __main__ - Step 61319: {'lr': 0.00032665845924492764, 'samples': 11773248, 'steps': 61318, 'loss/train': 0.9813629984855652} 08/31/2021 00:21:42 - INFO - __main__ - Step 61320: {'lr': 0.0003266534081221728, 'samples': 11773440, 'steps': 61319, 'loss/train': 1.1777901649475098} 08/31/2021 00:21:42 - INFO - __main__ - Step 61321: {'lr': 0.00032664835696487906, 'samples': 11773632, 'steps': 61320, 'loss/train': 0.9790706634521484} 08/31/2021 00:21:44 - INFO - __main__ - Step 61322: {'lr': 0.00032664330577304875, 'samples': 11773824, 'steps': 61321, 'loss/train': 1.2914150953292847} 08/31/2021 00:21:44 - INFO - __main__ - Step 61323: {'lr': 0.00032663825454668416, 'samples': 11774016, 'steps': 61322, 'loss/train': 1.3164125680923462} 08/31/2021 00:21:45 - INFO - __main__ - Step 61324: {'lr': 0.0003266332032857875, 'samples': 11774208, 'steps': 61323, 'loss/train': 1.4017161130905151} 08/31/2021 00:21:45 - INFO - __main__ - Step 61325: {'lr': 0.0003266281519903612, 'samples': 11774400, 'steps': 61324, 'loss/train': 1.1293972730636597} 08/31/2021 00:21:45 - INFO - __main__ - Step 61326: {'lr': 0.0003266231006604074, 'samples': 11774592, 'steps': 61325, 'loss/train': 2.110351324081421} 08/31/2021 00:21:47 - INFO - __main__ - Step 61327: {'lr': 0.00032661804929592843, 'samples': 11774784, 'steps': 61326, 'loss/train': 0.6818169355392456} 08/31/2021 00:21:47 - INFO - __main__ - Step 61328: {'lr': 0.0003266129978969265, 'samples': 11774976, 'steps': 61327, 'loss/train': 1.3717198371887207} 08/31/2021 00:21:48 - INFO - __main__ - Step 61329: {'lr': 0.000326607946463404, 'samples': 11775168, 'steps': 61328, 'loss/train': 4.719514846801758} 08/31/2021 00:21:48 - INFO - __main__ - Step 61330: {'lr': 0.00032660289499536303, 'samples': 11775360, 'steps': 61329, 'loss/train': 1.3467472791671753} 08/31/2021 00:21:48 - INFO - __main__ - Step 61331: {'lr': 0.00032659784349280607, 'samples': 11775552, 'steps': 61330, 'loss/train': 1.257340431213379} 08/31/2021 00:21:50 - INFO - __main__ - Step 61332: {'lr': 0.0003265927919557353, 'samples': 11775744, 'steps': 61331, 'loss/train': 1.580973744392395} 08/31/2021 00:21:50 - INFO - __main__ - Step 61333: {'lr': 0.000326587740384153, 'samples': 11775936, 'steps': 61332, 'loss/train': 1.0580066442489624} 08/31/2021 00:21:51 - INFO - __main__ - Step 61334: {'lr': 0.0003265826887780614, 'samples': 11776128, 'steps': 61333, 'loss/train': 1.7486871480941772} 08/31/2021 00:21:51 - INFO - __main__ - Step 61335: {'lr': 0.00032657763713746284, 'samples': 11776320, 'steps': 61334, 'loss/train': 2.5752031803131104} 08/31/2021 00:21:51 - INFO - __main__ - Step 61336: {'lr': 0.0003265725854623596, 'samples': 11776512, 'steps': 61335, 'loss/train': 0.6905205845832825} 08/31/2021 00:21:53 - INFO - __main__ - Step 61337: {'lr': 0.00032656753375275396, 'samples': 11776704, 'steps': 61336, 'loss/train': 1.5949304103851318} 08/31/2021 00:21:54 - INFO - __main__ - Step 61338: {'lr': 0.00032656248200864813, 'samples': 11776896, 'steps': 61337, 'loss/train': 1.0146936178207397} 08/31/2021 00:21:54 - INFO - __main__ - Step 61339: {'lr': 0.0003265574302300444, 'samples': 11777088, 'steps': 61338, 'loss/train': 0.8023651242256165} 08/31/2021 00:21:54 - INFO - __main__ - Step 61340: {'lr': 0.0003265523784169451, 'samples': 11777280, 'steps': 61339, 'loss/train': 1.8536564111709595} 08/31/2021 00:21:55 - INFO - __main__ - Step 61341: {'lr': 0.0003265473265693525, 'samples': 11777472, 'steps': 61340, 'loss/train': 0.6223291754722595} 08/31/2021 00:21:55 - INFO - __main__ - Step 61342: {'lr': 0.00032654227468726884, 'samples': 11777664, 'steps': 61341, 'loss/train': 1.211379051208496} 08/31/2021 00:21:57 - INFO - __main__ - Step 61343: {'lr': 0.00032653722277069643, 'samples': 11777856, 'steps': 61342, 'loss/train': 0.06714785844087601} 08/31/2021 00:21:58 - INFO - __main__ - Step 61344: {'lr': 0.00032653217081963755, 'samples': 11778048, 'steps': 61343, 'loss/train': 1.0869958400726318} 08/31/2021 00:21:58 - INFO - __main__ - Step 61345: {'lr': 0.0003265271188340944, 'samples': 11778240, 'steps': 61344, 'loss/train': 1.2708845138549805} 08/31/2021 00:21:58 - INFO - __main__ - Step 61346: {'lr': 0.0003265220668140693, 'samples': 11778432, 'steps': 61345, 'loss/train': 1.4840798377990723} 08/31/2021 00:21:59 - INFO - __main__ - Step 61347: {'lr': 0.0003265170147595646, 'samples': 11778624, 'steps': 61346, 'loss/train': 1.4672025442123413} 08/31/2021 00:22:00 - INFO - __main__ - Step 61348: {'lr': 0.00032651196267058244, 'samples': 11778816, 'steps': 61347, 'loss/train': 0.6301930546760559} 08/31/2021 00:22:01 - INFO - __main__ - Step 61349: {'lr': 0.00032650691054712523, 'samples': 11779008, 'steps': 61348, 'loss/train': 1.1871235370635986} 08/31/2021 00:22:01 - INFO - __main__ - Step 61350: {'lr': 0.00032650185838919516, 'samples': 11779200, 'steps': 61349, 'loss/train': 0.8605415225028992} 08/31/2021 00:22:01 - INFO - __main__ - Step 61351: {'lr': 0.00032649680619679456, 'samples': 11779392, 'steps': 61350, 'loss/train': 0.5550278425216675} 08/31/2021 00:22:02 - INFO - __main__ - Step 61352: {'lr': 0.00032649175396992565, 'samples': 11779584, 'steps': 61351, 'loss/train': 1.441185712814331} 08/31/2021 00:22:03 - INFO - __main__ - Step 61353: {'lr': 0.0003264867017085907, 'samples': 11779776, 'steps': 61352, 'loss/train': 1.195102334022522} 08/31/2021 00:22:04 - INFO - __main__ - Step 61354: {'lr': 0.0003264816494127921, 'samples': 11779968, 'steps': 61353, 'loss/train': 0.859699547290802} 08/31/2021 00:22:04 - INFO - __main__ - Step 61355: {'lr': 0.000326476597082532, 'samples': 11780160, 'steps': 61354, 'loss/train': 1.4201257228851318} 08/31/2021 00:22:04 - INFO - __main__ - Step 61356: {'lr': 0.0003264715447178127, 'samples': 11780352, 'steps': 61355, 'loss/train': 1.5027704238891602} 08/31/2021 00:22:05 - INFO - __main__ - Step 61357: {'lr': 0.0003264664923186366, 'samples': 11780544, 'steps': 61356, 'loss/train': 1.4847159385681152} 08/31/2021 00:22:05 - INFO - __main__ - Step 61358: {'lr': 0.0003264614398850058, 'samples': 11780736, 'steps': 61357, 'loss/train': 1.7724993228912354} 08/31/2021 00:22:07 - INFO - __main__ - Step 61359: {'lr': 0.0003264563874169227, 'samples': 11780928, 'steps': 61358, 'loss/train': 1.4593428373336792} 08/31/2021 00:22:07 - INFO - __main__ - Step 61360: {'lr': 0.00032645133491438947, 'samples': 11781120, 'steps': 61359, 'loss/train': 1.3819656372070312} 08/31/2021 00:22:07 - INFO - __main__ - Step 61361: {'lr': 0.0003264462823774085, 'samples': 11781312, 'steps': 61360, 'loss/train': 0.5293810963630676} 08/31/2021 00:22:08 - INFO - __main__ - Step 61362: {'lr': 0.000326441229805982, 'samples': 11781504, 'steps': 61361, 'loss/train': 1.62050461769104} 08/31/2021 00:22:08 - INFO - __main__ - Step 61363: {'lr': 0.00032643617720011227, 'samples': 11781696, 'steps': 61362, 'loss/train': 0.3133053183555603} 08/31/2021 00:22:10 - INFO - __main__ - Step 61364: {'lr': 0.0003264311245598016, 'samples': 11781888, 'steps': 61363, 'loss/train': 2.0147924423217773} 08/31/2021 00:22:10 - INFO - __main__ - Step 61365: {'lr': 0.0003264260718850522, 'samples': 11782080, 'steps': 61364, 'loss/train': 1.3735227584838867} 08/31/2021 00:22:10 - INFO - __main__ - Step 61366: {'lr': 0.00032642101917586643, 'samples': 11782272, 'steps': 61365, 'loss/train': 1.6877514123916626} 08/31/2021 00:22:11 - INFO - __main__ - Step 61367: {'lr': 0.00032641596643224644, 'samples': 11782464, 'steps': 61366, 'loss/train': 1.845852017402649} 08/31/2021 00:22:11 - INFO - __main__ - Step 61368: {'lr': 0.0003264109136541947, 'samples': 11782656, 'steps': 61367, 'loss/train': 0.8946561217308044} 08/31/2021 00:22:13 - INFO - __main__ - Step 61369: {'lr': 0.00032640586084171333, 'samples': 11782848, 'steps': 61368, 'loss/train': 1.010861873626709} 08/31/2021 00:22:13 - INFO - __main__ - Step 61370: {'lr': 0.0003264008079948047, 'samples': 11783040, 'steps': 61369, 'loss/train': 1.5691567659378052} 08/31/2021 00:22:13 - INFO - __main__ - Step 61371: {'lr': 0.000326395755113471, 'samples': 11783232, 'steps': 61370, 'loss/train': 1.2529481649398804} 08/31/2021 00:22:14 - INFO - __main__ - Step 61372: {'lr': 0.00032639070219771455, 'samples': 11783424, 'steps': 61371, 'loss/train': 0.9987752437591553} 08/31/2021 00:22:14 - INFO - __main__ - Step 61373: {'lr': 0.0003263856492475377, 'samples': 11783616, 'steps': 61372, 'loss/train': 1.082466721534729} 08/31/2021 00:22:16 - INFO - __main__ - Step 61374: {'lr': 0.00032638059626294253, 'samples': 11783808, 'steps': 61373, 'loss/train': 1.6434762477874756} 08/31/2021 00:22:16 - INFO - __main__ - Step 61375: {'lr': 0.0003263755432439315, 'samples': 11784000, 'steps': 61374, 'loss/train': 1.7081499099731445} 08/31/2021 00:22:17 - INFO - __main__ - Step 61376: {'lr': 0.00032637049019050687, 'samples': 11784192, 'steps': 61375, 'loss/train': 0.06946693360805511} 08/31/2021 00:22:17 - INFO - __main__ - Step 61377: {'lr': 0.00032636543710267085, 'samples': 11784384, 'steps': 61376, 'loss/train': 1.2467776536941528} 08/31/2021 00:22:17 - INFO - __main__ - Step 61378: {'lr': 0.00032636038398042573, 'samples': 11784576, 'steps': 61377, 'loss/train': 1.140404462814331} 08/31/2021 00:22:19 - INFO - __main__ - Step 61379: {'lr': 0.0003263553308237738, 'samples': 11784768, 'steps': 61378, 'loss/train': 1.3790568113327026} 08/31/2021 00:22:19 - INFO - __main__ - Step 61380: {'lr': 0.00032635027763271737, 'samples': 11784960, 'steps': 61379, 'loss/train': 1.3994486331939697} 08/31/2021 00:22:20 - INFO - __main__ - Step 61381: {'lr': 0.00032634522440725864, 'samples': 11785152, 'steps': 61380, 'loss/train': 1.355697751045227} 08/31/2021 00:22:20 - INFO - __main__ - Step 61382: {'lr': 0.00032634017114739996, 'samples': 11785344, 'steps': 61381, 'loss/train': 1.3825318813323975} 08/31/2021 00:22:21 - INFO - __main__ - Step 61383: {'lr': 0.0003263351178531435, 'samples': 11785536, 'steps': 61382, 'loss/train': 1.3989161252975464} 08/31/2021 00:22:21 - INFO - __main__ - Step 61384: {'lr': 0.00032633006452449176, 'samples': 11785728, 'steps': 61383, 'loss/train': 0.6282069087028503} 08/31/2021 00:22:23 - INFO - __main__ - Step 61385: {'lr': 0.00032632501116144674, 'samples': 11785920, 'steps': 61384, 'loss/train': 0.29018059372901917} 08/31/2021 00:22:23 - INFO - __main__ - Step 61386: {'lr': 0.0003263199577640109, 'samples': 11786112, 'steps': 61385, 'loss/train': 1.4617395401000977} 08/31/2021 00:22:24 - INFO - __main__ - Step 61387: {'lr': 0.00032631490433218647, 'samples': 11786304, 'steps': 61386, 'loss/train': 1.2456398010253906} 08/31/2021 00:22:24 - INFO - __main__ - Step 61388: {'lr': 0.0003263098508659757, 'samples': 11786496, 'steps': 61387, 'loss/train': 1.2827537059783936} 08/31/2021 00:22:24 - INFO - __main__ - Step 61389: {'lr': 0.0003263047973653809, 'samples': 11786688, 'steps': 61388, 'loss/train': 0.973333477973938} 08/31/2021 00:22:25 - INFO - __main__ - Step 61390: {'lr': 0.0003262997438304044, 'samples': 11786880, 'steps': 61389, 'loss/train': 1.3468514680862427} 08/31/2021 00:22:26 - INFO - __main__ - Step 61391: {'lr': 0.0003262946902610483, 'samples': 11787072, 'steps': 61390, 'loss/train': 0.02316771261394024} 08/31/2021 00:22:27 - INFO - __main__ - Step 61392: {'lr': 0.00032628963665731504, 'samples': 11787264, 'steps': 61391, 'loss/train': 1.7114007472991943} 08/31/2021 00:22:27 - INFO - __main__ - Step 61393: {'lr': 0.00032628458301920684, 'samples': 11787456, 'steps': 61392, 'loss/train': 1.4769282341003418} 08/31/2021 00:22:28 - INFO - __main__ - Step 61394: {'lr': 0.000326279529346726, 'samples': 11787648, 'steps': 61393, 'loss/train': 1.1955771446228027} 08/31/2021 00:22:28 - INFO - __main__ - Step 61395: {'lr': 0.0003262744756398748, 'samples': 11787840, 'steps': 61394, 'loss/train': 1.3599498271942139} 08/31/2021 00:22:30 - INFO - __main__ - Step 61396: {'lr': 0.0003262694218986554, 'samples': 11788032, 'steps': 61395, 'loss/train': 0.9979591369628906} 08/31/2021 00:22:31 - INFO - __main__ - Step 61397: {'lr': 0.0003262643681230703, 'samples': 11788224, 'steps': 61396, 'loss/train': 1.0175598859786987} 08/31/2021 00:22:31 - INFO - __main__ - Step 61398: {'lr': 0.0003262593143131216, 'samples': 11788416, 'steps': 61397, 'loss/train': 1.1614660024642944} 08/31/2021 00:22:31 - INFO - __main__ - Step 61399: {'lr': 0.0003262542604688116, 'samples': 11788608, 'steps': 61398, 'loss/train': 1.4417214393615723} 08/31/2021 00:22:32 - INFO - __main__ - Step 61400: {'lr': 0.00032624920659014264, 'samples': 11788800, 'steps': 61399, 'loss/train': 1.4987540245056152} 08/31/2021 00:22:33 - INFO - __main__ - Step 61401: {'lr': 0.00032624415267711694, 'samples': 11788992, 'steps': 61400, 'loss/train': 1.0346181392669678} 08/31/2021 00:22:34 - INFO - __main__ - Step 61402: {'lr': 0.00032623909872973677, 'samples': 11789184, 'steps': 61401, 'loss/train': 1.3168528079986572} 08/31/2021 00:22:34 - INFO - __main__ - Step 61403: {'lr': 0.00032623404474800457, 'samples': 11789376, 'steps': 61402, 'loss/train': 1.4080958366394043} 08/31/2021 00:22:35 - INFO - __main__ - Step 61404: {'lr': 0.0003262289907319224, 'samples': 11789568, 'steps': 61403, 'loss/train': 1.6580662727355957} 08/31/2021 00:22:35 - INFO - __main__ - Step 61405: {'lr': 0.0003262239366814926, 'samples': 11789760, 'steps': 61404, 'loss/train': 1.0347108840942383} 08/31/2021 00:22:36 - INFO - __main__ - Step 61406: {'lr': 0.0003262188825967175, 'samples': 11789952, 'steps': 61405, 'loss/train': 0.778626561164856} 08/31/2021 00:22:37 - INFO - __main__ - Step 61407: {'lr': 0.00032621382847759935, 'samples': 11790144, 'steps': 61406, 'loss/train': 1.2421923875808716} 08/31/2021 00:22:37 - INFO - __main__ - Step 61408: {'lr': 0.00032620877432414043, 'samples': 11790336, 'steps': 61407, 'loss/train': 1.0655134916305542} 08/31/2021 00:22:38 - INFO - __main__ - Step 61409: {'lr': 0.000326203720136343, 'samples': 11790528, 'steps': 61408, 'loss/train': 1.6360299587249756} 08/31/2021 00:22:38 - INFO - __main__ - Step 61410: {'lr': 0.00032619866591420934, 'samples': 11790720, 'steps': 61409, 'loss/train': 1.5982191562652588} 08/31/2021 00:22:38 - INFO - __main__ - Step 61411: {'lr': 0.0003261936116577418, 'samples': 11790912, 'steps': 61410, 'loss/train': 1.0817009210586548} 08/31/2021 00:22:40 - INFO - __main__ - Step 61412: {'lr': 0.0003261885573669425, 'samples': 11791104, 'steps': 61411, 'loss/train': 1.0340968370437622} 08/31/2021 00:22:40 - INFO - __main__ - Step 61413: {'lr': 0.0003261835030418139, 'samples': 11791296, 'steps': 61412, 'loss/train': 2.0112576484680176} 08/31/2021 00:22:41 - INFO - __main__ - Step 61414: {'lr': 0.0003261784486823581, 'samples': 11791488, 'steps': 61413, 'loss/train': 1.805314064025879} 08/31/2021 00:22:41 - INFO - __main__ - Step 61415: {'lr': 0.0003261733942885775, 'samples': 11791680, 'steps': 61414, 'loss/train': 1.1975208520889282} 08/31/2021 00:22:41 - INFO - __main__ - Step 61416: {'lr': 0.00032616833986047434, 'samples': 11791872, 'steps': 61415, 'loss/train': 0.4186960458755493} 08/31/2021 00:22:43 - INFO - __main__ - Step 61417: {'lr': 0.000326163285398051, 'samples': 11792064, 'steps': 61416, 'loss/train': 1.2835755348205566} 08/31/2021 00:22:43 - INFO - __main__ - Step 61418: {'lr': 0.0003261582309013095, 'samples': 11792256, 'steps': 61417, 'loss/train': 0.701703667640686} 08/31/2021 00:22:44 - INFO - __main__ - Step 61419: {'lr': 0.00032615317637025237, 'samples': 11792448, 'steps': 61418, 'loss/train': 0.30393198132514954} 08/31/2021 00:22:44 - INFO - __main__ - Step 61420: {'lr': 0.00032614812180488173, 'samples': 11792640, 'steps': 61419, 'loss/train': 1.3318305015563965} 08/31/2021 00:22:44 - INFO - __main__ - Step 61421: {'lr': 0.0003261430672052, 'samples': 11792832, 'steps': 61420, 'loss/train': 0.9928742051124573} 08/31/2021 00:22:46 - INFO - __main__ - Step 61422: {'lr': 0.00032613801257120933, 'samples': 11793024, 'steps': 61421, 'loss/train': 0.985354483127594} 08/31/2021 00:22:47 - INFO - __main__ - Step 61423: {'lr': 0.0003261329579029121, 'samples': 11793216, 'steps': 61422, 'loss/train': 0.06323324888944626} 08/31/2021 00:22:47 - INFO - __main__ - Step 61424: {'lr': 0.0003261279032003105, 'samples': 11793408, 'steps': 61423, 'loss/train': 0.5743527412414551} 08/31/2021 00:22:47 - INFO - __main__ - Step 61425: {'lr': 0.0003261228484634068, 'samples': 11793600, 'steps': 61424, 'loss/train': 1.589694619178772} 08/31/2021 00:22:48 - INFO - __main__ - Step 61426: {'lr': 0.0003261177936922034, 'samples': 11793792, 'steps': 61425, 'loss/train': 0.8438405990600586} 08/31/2021 00:22:49 - INFO - __main__ - Step 61427: {'lr': 0.0003261127388867024, 'samples': 11793984, 'steps': 61426, 'loss/train': 0.7163046002388} 08/31/2021 00:22:50 - INFO - __main__ - Step 61428: {'lr': 0.0003261076840469062, 'samples': 11794176, 'steps': 61427, 'loss/train': 0.959408700466156} 08/31/2021 00:22:50 - INFO - __main__ - Step 61429: {'lr': 0.0003261026291728171, 'samples': 11794368, 'steps': 61428, 'loss/train': 0.6273329257965088} 08/31/2021 00:22:50 - INFO - __main__ - Step 61430: {'lr': 0.0003260975742644373, 'samples': 11794560, 'steps': 61429, 'loss/train': 0.8535453081130981} 08/31/2021 00:22:51 - INFO - __main__ - Step 61431: {'lr': 0.0003260925193217692, 'samples': 11794752, 'steps': 61430, 'loss/train': 1.1766436100006104} 08/31/2021 00:22:51 - INFO - __main__ - Step 61432: {'lr': 0.00032608746434481485, 'samples': 11794944, 'steps': 61431, 'loss/train': 1.1617236137390137} 08/31/2021 00:22:52 - INFO - __main__ - Step 61433: {'lr': 0.0003260824093335767, 'samples': 11795136, 'steps': 61432, 'loss/train': 0.1509706825017929} 08/31/2021 00:22:53 - INFO - __main__ - Step 61434: {'lr': 0.00032607735428805704, 'samples': 11795328, 'steps': 61433, 'loss/train': 1.103403091430664} 08/31/2021 00:22:53 - INFO - __main__ - Step 61435: {'lr': 0.00032607229920825806, 'samples': 11795520, 'steps': 61434, 'loss/train': 1.404532790184021} 08/31/2021 00:22:54 - INFO - __main__ - Step 61436: {'lr': 0.000326067244094182, 'samples': 11795712, 'steps': 61435, 'loss/train': 1.8905019760131836} 08/31/2021 00:22:54 - INFO - __main__ - Step 61437: {'lr': 0.0003260621889458314, 'samples': 11795904, 'steps': 61436, 'loss/train': 1.0694340467453003} 08/31/2021 00:22:56 - INFO - __main__ - Step 61438: {'lr': 0.00032605713376320823, 'samples': 11796096, 'steps': 61437, 'loss/train': 1.2557474374771118} 08/31/2021 00:22:57 - INFO - __main__ - Step 61439: {'lr': 0.00032605207854631487, 'samples': 11796288, 'steps': 61438, 'loss/train': 1.2843735218048096} 08/31/2021 00:22:57 - INFO - __main__ - Step 61440: {'lr': 0.00032604702329515367, 'samples': 11796480, 'steps': 61439, 'loss/train': 1.5661633014678955} 08/31/2021 00:22:57 - INFO - __main__ - Step 61441: {'lr': 0.0003260419680097268, 'samples': 11796672, 'steps': 61440, 'loss/train': 0.6869682669639587} 08/31/2021 00:22:58 - INFO - __main__ - Step 61442: {'lr': 0.0003260369126900366, 'samples': 11796864, 'steps': 61441, 'loss/train': 0.06265687942504883} 08/31/2021 00:23:00 - INFO - __main__ - Step 61443: {'lr': 0.0003260318573360854, 'samples': 11797056, 'steps': 61442, 'loss/train': 0.7855767011642456} 08/31/2021 00:23:00 - INFO - __main__ - Step 61444: {'lr': 0.00032602680194787544, 'samples': 11797248, 'steps': 61443, 'loss/train': 0.7329050898551941} 08/31/2021 00:23:00 - INFO - __main__ - Step 61445: {'lr': 0.0003260217465254089, 'samples': 11797440, 'steps': 61444, 'loss/train': 1.0960506200790405} 08/31/2021 00:23:01 - INFO - __main__ - Step 61446: {'lr': 0.00032601669106868816, 'samples': 11797632, 'steps': 61445, 'loss/train': 0.17022275924682617} 08/31/2021 00:23:01 - INFO - __main__ - Step 61447: {'lr': 0.0003260116355777154, 'samples': 11797824, 'steps': 61446, 'loss/train': 1.320034384727478} 08/31/2021 00:23:01 - INFO - __main__ - Step 61448: {'lr': 0.00032600658005249307, 'samples': 11798016, 'steps': 61447, 'loss/train': 0.019461382180452347} 08/31/2021 00:23:04 - INFO - __main__ - Step 61449: {'lr': 0.00032600152449302337, 'samples': 11798208, 'steps': 61448, 'loss/train': 1.673912763595581} 08/31/2021 00:23:04 - INFO - __main__ - Step 61450: {'lr': 0.00032599646889930843, 'samples': 11798400, 'steps': 61449, 'loss/train': 0.8825443387031555} 08/31/2021 00:23:04 - INFO - __main__ - Step 61451: {'lr': 0.0003259914132713507, 'samples': 11798592, 'steps': 61450, 'loss/train': 1.1266183853149414} 08/31/2021 00:23:05 - INFO - __main__ - Step 61452: {'lr': 0.00032598635760915253, 'samples': 11798784, 'steps': 61451, 'loss/train': 1.240041732788086} 08/31/2021 00:23:05 - INFO - __main__ - Step 61453: {'lr': 0.0003259813019127159, 'samples': 11798976, 'steps': 61452, 'loss/train': 1.3365064859390259} 08/31/2021 00:23:06 - INFO - __main__ - Step 61454: {'lr': 0.00032597624618204335, 'samples': 11799168, 'steps': 61453, 'loss/train': 1.4610346555709839} 08/31/2021 00:23:07 - INFO - __main__ - Step 61455: {'lr': 0.0003259711904171372, 'samples': 11799360, 'steps': 61454, 'loss/train': 1.1172791719436646} 08/31/2021 00:23:07 - INFO - __main__ - Step 61456: {'lr': 0.00032596613461799944, 'samples': 11799552, 'steps': 61455, 'loss/train': 1.0271488428115845} 08/31/2021 00:23:08 - INFO - __main__ - Step 61457: {'lr': 0.00032596107878463256, 'samples': 11799744, 'steps': 61456, 'loss/train': 1.4272918701171875} 08/31/2021 00:23:08 - INFO - __main__ - Step 61458: {'lr': 0.00032595602291703873, 'samples': 11799936, 'steps': 61457, 'loss/train': 1.4617313146591187} 08/31/2021 00:23:10 - INFO - __main__ - Step 61459: {'lr': 0.0003259509670152204, 'samples': 11800128, 'steps': 61458, 'loss/train': 1.0384761095046997} 08/31/2021 00:23:10 - INFO - __main__ - Step 61460: {'lr': 0.0003259459110791797, 'samples': 11800320, 'steps': 61459, 'loss/train': 1.202850103378296} 08/31/2021 00:23:10 - INFO - __main__ - Step 61461: {'lr': 0.00032594085510891894, 'samples': 11800512, 'steps': 61460, 'loss/train': 1.242191195487976} 08/31/2021 00:23:11 - INFO - __main__ - Step 61462: {'lr': 0.0003259357991044404, 'samples': 11800704, 'steps': 61461, 'loss/train': 0.3466338515281677} 08/31/2021 00:23:11 - INFO - __main__ - Step 61463: {'lr': 0.00032593074306574635, 'samples': 11800896, 'steps': 61462, 'loss/train': 0.7159785628318787} 08/31/2021 00:23:13 - INFO - __main__ - Step 61464: {'lr': 0.00032592568699283905, 'samples': 11801088, 'steps': 61463, 'loss/train': 1.2980542182922363} 08/31/2021 00:23:13 - INFO - __main__ - Step 61465: {'lr': 0.0003259206308857208, 'samples': 11801280, 'steps': 61464, 'loss/train': 0.9452191591262817} 08/31/2021 00:23:13 - INFO - __main__ - Step 61466: {'lr': 0.0003259155747443939, 'samples': 11801472, 'steps': 61465, 'loss/train': 1.5669925212860107} 08/31/2021 00:23:14 - INFO - __main__ - Step 61467: {'lr': 0.00032591051856886065, 'samples': 11801664, 'steps': 61466, 'loss/train': 1.2888438701629639} 08/31/2021 00:23:14 - INFO - __main__ - Step 61468: {'lr': 0.00032590546235912335, 'samples': 11801856, 'steps': 61467, 'loss/train': 1.880226969718933} 08/31/2021 00:23:16 - INFO - __main__ - Step 61469: {'lr': 0.0003259004061151841, 'samples': 11802048, 'steps': 61468, 'loss/train': 1.2725915908813477} 08/31/2021 00:23:16 - INFO - __main__ - Step 61470: {'lr': 0.00032589534983704533, 'samples': 11802240, 'steps': 61469, 'loss/train': 1.2489300966262817} 08/31/2021 00:23:17 - INFO - __main__ - Step 61471: {'lr': 0.0003258902935247093, 'samples': 11802432, 'steps': 61470, 'loss/train': 1.633742094039917} 08/31/2021 00:23:17 - INFO - __main__ - Step 61472: {'lr': 0.0003258852371781783, 'samples': 11802624, 'steps': 61471, 'loss/train': 0.5805555582046509} 08/31/2021 00:23:17 - INFO - __main__ - Step 61473: {'lr': 0.0003258801807974545, 'samples': 11802816, 'steps': 61472, 'loss/train': 1.7697831392288208} 08/31/2021 00:23:19 - INFO - __main__ - Step 61474: {'lr': 0.00032587512438254034, 'samples': 11803008, 'steps': 61473, 'loss/train': 1.3385519981384277} 08/31/2021 00:23:20 - INFO - __main__ - Step 61475: {'lr': 0.000325870067933438, 'samples': 11803200, 'steps': 61474, 'loss/train': 1.4819897413253784} 08/31/2021 00:23:20 - INFO - __main__ - Step 61476: {'lr': 0.0003258650114501498, 'samples': 11803392, 'steps': 61475, 'loss/train': 0.6162469983100891} 08/31/2021 00:23:20 - INFO - __main__ - Step 61477: {'lr': 0.000325859954932678, 'samples': 11803584, 'steps': 61476, 'loss/train': 1.864418625831604} 08/31/2021 00:23:21 - INFO - __main__ - Step 61478: {'lr': 0.00032585489838102483, 'samples': 11803776, 'steps': 61477, 'loss/train': 1.7504050731658936} 08/31/2021 00:23:21 - INFO - __main__ - Step 61479: {'lr': 0.0003258498417951926, 'samples': 11803968, 'steps': 61478, 'loss/train': 1.5824533700942993} 08/31/2021 00:23:23 - INFO - __main__ - Step 61480: {'lr': 0.00032584478517518365, 'samples': 11804160, 'steps': 61479, 'loss/train': 1.1792484521865845} 08/31/2021 00:23:23 - INFO - __main__ - Step 61481: {'lr': 0.00032583972852100017, 'samples': 11804352, 'steps': 61480, 'loss/train': 1.2903721332550049} 08/31/2021 00:23:23 - INFO - __main__ - Step 61482: {'lr': 0.0003258346718326445, 'samples': 11804544, 'steps': 61481, 'loss/train': 1.2549662590026855} 08/31/2021 00:23:24 - INFO - __main__ - Step 61483: {'lr': 0.0003258296151101189, 'samples': 11804736, 'steps': 61482, 'loss/train': 0.9688969850540161} 08/31/2021 00:23:24 - INFO - __main__ - Step 61484: {'lr': 0.0003258245583534256, 'samples': 11804928, 'steps': 61483, 'loss/train': 1.3488510847091675} 08/31/2021 00:23:24 - INFO - __main__ - Step 61485: {'lr': 0.00032581950156256707, 'samples': 11805120, 'steps': 61484, 'loss/train': 0.9495869278907776} 08/31/2021 00:23:26 - INFO - __main__ - Step 61486: {'lr': 0.0003258144447375453, 'samples': 11805312, 'steps': 61485, 'loss/train': 0.7709207534790039} 08/31/2021 00:23:26 - INFO - __main__ - Step 61487: {'lr': 0.00032580938787836277, 'samples': 11805504, 'steps': 61486, 'loss/train': 2.016496181488037} 08/31/2021 00:23:27 - INFO - __main__ - Step 61488: {'lr': 0.0003258043309850217, 'samples': 11805696, 'steps': 61487, 'loss/train': 1.1083611249923706} 08/31/2021 00:23:27 - INFO - __main__ - Step 61489: {'lr': 0.0003257992740575243, 'samples': 11805888, 'steps': 61488, 'loss/train': 1.1834642887115479} 08/31/2021 00:23:27 - INFO - __main__ - Step 61490: {'lr': 0.000325794217095873, 'samples': 11806080, 'steps': 61489, 'loss/train': 1.8471219539642334} 08/31/2021 00:23:29 - INFO - __main__ - Step 61491: {'lr': 0.00032578916010006997, 'samples': 11806272, 'steps': 61490, 'loss/train': 0.13773368299007416} 08/31/2021 00:23:30 - INFO - __main__ - Step 61492: {'lr': 0.0003257841030701175, 'samples': 11806464, 'steps': 61491, 'loss/train': 0.5722821354866028} 08/31/2021 00:23:30 - INFO - __main__ - Step 61493: {'lr': 0.0003257790460060179, 'samples': 11806656, 'steps': 61492, 'loss/train': 1.294654369354248} 08/31/2021 00:23:30 - INFO - __main__ - Step 61494: {'lr': 0.0003257739889077734, 'samples': 11806848, 'steps': 61493, 'loss/train': 0.42620331048965454} 08/31/2021 00:23:31 - INFO - __main__ - Step 61495: {'lr': 0.0003257689317753863, 'samples': 11807040, 'steps': 61494, 'loss/train': 0.7546752691268921} 08/31/2021 00:23:32 - INFO - __main__ - Step 61496: {'lr': 0.00032576387460885893, 'samples': 11807232, 'steps': 61495, 'loss/train': 1.4549689292907715} 08/31/2021 00:23:33 - INFO - __main__ - Step 61497: {'lr': 0.00032575881740819353, 'samples': 11807424, 'steps': 61496, 'loss/train': 1.5331889390945435} 08/31/2021 00:23:33 - INFO - __main__ - Step 61498: {'lr': 0.00032575376017339236, 'samples': 11807616, 'steps': 61497, 'loss/train': 1.0547373294830322} 08/31/2021 00:23:34 - INFO - __main__ - Step 61499: {'lr': 0.00032574870290445773, 'samples': 11807808, 'steps': 61498, 'loss/train': 1.1496069431304932} 08/31/2021 00:23:34 - INFO - __main__ - Step 61500: {'lr': 0.0003257436456013919, 'samples': 11808000, 'steps': 61499, 'loss/train': 1.3712652921676636} 08/31/2021 00:23:35 - INFO - __main__ - Step 61501: {'lr': 0.0003257385882641971, 'samples': 11808192, 'steps': 61500, 'loss/train': 1.191573977470398} 08/31/2021 00:23:36 - INFO - __main__ - Step 61502: {'lr': 0.0003257335308928757, 'samples': 11808384, 'steps': 61501, 'loss/train': 1.5917102098464966} 08/31/2021 00:23:36 - INFO - __main__ - Step 61503: {'lr': 0.00032572847348742994, 'samples': 11808576, 'steps': 61502, 'loss/train': 0.9459768533706665} 08/31/2021 00:23:37 - INFO - __main__ - Step 61504: {'lr': 0.0003257234160478621, 'samples': 11808768, 'steps': 61503, 'loss/train': 0.9482108950614929} 08/31/2021 00:23:37 - INFO - __main__ - Step 61505: {'lr': 0.0003257183585741745, 'samples': 11808960, 'steps': 61504, 'loss/train': 0.278058260679245} 08/31/2021 00:23:37 - INFO - __main__ - Step 61506: {'lr': 0.0003257133010663693, 'samples': 11809152, 'steps': 61505, 'loss/train': 1.1990065574645996} 08/31/2021 00:23:40 - INFO - __main__ - Step 61507: {'lr': 0.0003257082435244489, 'samples': 11809344, 'steps': 61506, 'loss/train': 1.063726782798767} 08/31/2021 00:23:40 - INFO - __main__ - Step 61508: {'lr': 0.0003257031859484155, 'samples': 11809536, 'steps': 61507, 'loss/train': 0.8984032869338989} 08/31/2021 00:23:41 - INFO - __main__ - Step 61509: {'lr': 0.00032569812833827146, 'samples': 11809728, 'steps': 61508, 'loss/train': 0.6271889209747314} 08/31/2021 00:23:41 - INFO - __main__ - Step 61510: {'lr': 0.000325693070694019, 'samples': 11809920, 'steps': 61509, 'loss/train': 0.7531551122665405} 08/31/2021 00:23:41 - INFO - __main__ - Step 61511: {'lr': 0.0003256880130156604, 'samples': 11810112, 'steps': 61510, 'loss/train': 1.1196280717849731} 08/31/2021 00:23:43 - INFO - __main__ - Step 61512: {'lr': 0.0003256829553031979, 'samples': 11810304, 'steps': 61511, 'loss/train': 1.4381685256958008} 08/31/2021 00:23:44 - INFO - __main__ - Step 61513: {'lr': 0.0003256778975566339, 'samples': 11810496, 'steps': 61512, 'loss/train': 1.1017731428146362} 08/31/2021 00:23:44 - INFO - __main__ - Step 61514: {'lr': 0.00032567283977597055, 'samples': 11810688, 'steps': 61513, 'loss/train': 1.4427094459533691} 08/31/2021 00:23:44 - INFO - __main__ - Step 61515: {'lr': 0.0003256677819612102, 'samples': 11810880, 'steps': 61514, 'loss/train': 5.829209327697754} 08/31/2021 00:23:45 - INFO - __main__ - Step 61516: {'lr': 0.00032566272411235515, 'samples': 11811072, 'steps': 61515, 'loss/train': 5.786766529083252} 08/31/2021 00:23:45 - INFO - __main__ - Step 61517: {'lr': 0.0003256576662294076, 'samples': 11811264, 'steps': 61516, 'loss/train': 1.3108755350112915} 08/31/2021 00:23:47 - INFO - __main__ - Step 61518: {'lr': 0.00032565260831237, 'samples': 11811456, 'steps': 61517, 'loss/train': 1.410096287727356} 08/31/2021 00:23:47 - INFO - __main__ - Step 61519: {'lr': 0.0003256475503612444, 'samples': 11811648, 'steps': 61518, 'loss/train': 1.55074143409729} 08/31/2021 00:23:47 - INFO - __main__ - Step 61520: {'lr': 0.0003256424923760332, 'samples': 11811840, 'steps': 61519, 'loss/train': 0.9918625354766846} 08/31/2021 00:23:48 - INFO - __main__ - Step 61521: {'lr': 0.00032563743435673855, 'samples': 11812032, 'steps': 61520, 'loss/train': 0.6744417548179626} 08/31/2021 00:23:48 - INFO - __main__ - Step 61522: {'lr': 0.00032563237630336294, 'samples': 11812224, 'steps': 61521, 'loss/train': 1.137869954109192} 08/31/2021 00:23:50 - INFO - __main__ - Step 61523: {'lr': 0.00032562731821590853, 'samples': 11812416, 'steps': 61522, 'loss/train': 1.4245737791061401} 08/31/2021 00:23:51 - INFO - __main__ - Step 61524: {'lr': 0.00032562226009437764, 'samples': 11812608, 'steps': 61523, 'loss/train': 1.9509456157684326} 08/31/2021 00:23:51 - INFO - __main__ - Step 61525: {'lr': 0.00032561720193877256, 'samples': 11812800, 'steps': 61524, 'loss/train': 0.6704294681549072} 08/31/2021 00:23:51 - INFO - __main__ - Step 61526: {'lr': 0.0003256121437490955, 'samples': 11812992, 'steps': 61525, 'loss/train': 1.1844860315322876} 08/31/2021 00:23:52 - INFO - __main__ - Step 61527: {'lr': 0.00032560708552534874, 'samples': 11813184, 'steps': 61526, 'loss/train': 1.4244403839111328} 08/31/2021 00:23:52 - INFO - __main__ - Step 61528: {'lr': 0.0003256020272675346, 'samples': 11813376, 'steps': 61527, 'loss/train': 5.96382999420166} 08/31/2021 00:23:53 - INFO - __main__ - Step 61529: {'lr': 0.0003255969689756554, 'samples': 11813568, 'steps': 61528, 'loss/train': 5.886960983276367} 08/31/2021 00:23:54 - INFO - __main__ - Step 61530: {'lr': 0.00032559191064971326, 'samples': 11813760, 'steps': 61529, 'loss/train': 1.0781563520431519} 08/31/2021 00:23:54 - INFO - __main__ - Step 61531: {'lr': 0.0003255868522897107, 'samples': 11813952, 'steps': 61530, 'loss/train': 0.31383979320526123} 08/31/2021 00:23:55 - INFO - __main__ - Step 61532: {'lr': 0.0003255817938956498, 'samples': 11814144, 'steps': 61531, 'loss/train': 1.3931504487991333} 08/31/2021 00:23:55 - INFO - __main__ - Step 61533: {'lr': 0.00032557673546753296, 'samples': 11814336, 'steps': 61532, 'loss/train': 1.664932131767273} 08/31/2021 00:23:55 - INFO - __main__ - Step 61534: {'lr': 0.0003255716770053624, 'samples': 11814528, 'steps': 61533, 'loss/train': 1.4944278001785278} 08/31/2021 00:23:57 - INFO - __main__ - Step 61535: {'lr': 0.0003255666185091404, 'samples': 11814720, 'steps': 61534, 'loss/train': 1.3045837879180908} 08/31/2021 00:23:57 - INFO - __main__ - Step 61536: {'lr': 0.0003255615599788692, 'samples': 11814912, 'steps': 61535, 'loss/train': 1.2458432912826538} 08/31/2021 00:23:58 - INFO - __main__ - Step 61537: {'lr': 0.00032555650141455117, 'samples': 11815104, 'steps': 61536, 'loss/train': 1.4673155546188354} 08/31/2021 00:23:58 - INFO - __main__ - Step 61538: {'lr': 0.0003255514428161886, 'samples': 11815296, 'steps': 61537, 'loss/train': 1.02493417263031} 08/31/2021 00:23:58 - INFO - __main__ - Step 61539: {'lr': 0.0003255463841837837, 'samples': 11815488, 'steps': 61538, 'loss/train': 2.1453306674957275} 08/31/2021 00:24:00 - INFO - __main__ - Step 61540: {'lr': 0.00032554132551733866, 'samples': 11815680, 'steps': 61539, 'loss/train': 1.3259326219558716} 08/31/2021 00:24:01 - INFO - __main__ - Step 61541: {'lr': 0.00032553626681685596, 'samples': 11815872, 'steps': 61540, 'loss/train': 1.2988921403884888} 08/31/2021 00:24:01 - INFO - __main__ - Step 61542: {'lr': 0.0003255312080823377, 'samples': 11816064, 'steps': 61541, 'loss/train': 1.446980357170105} 08/31/2021 00:24:01 - INFO - __main__ - Step 61543: {'lr': 0.0003255261493137863, 'samples': 11816256, 'steps': 61542, 'loss/train': 2.644291639328003} 08/31/2021 00:24:02 - INFO - __main__ - Step 61544: {'lr': 0.000325521090511204, 'samples': 11816448, 'steps': 61543, 'loss/train': 1.118293046951294} 08/31/2021 00:24:02 - INFO - __main__ - Step 61545: {'lr': 0.0003255160316745931, 'samples': 11816640, 'steps': 61544, 'loss/train': 1.4611917734146118} 08/31/2021 00:24:04 - INFO - __main__ - Step 61546: {'lr': 0.00032551097280395576, 'samples': 11816832, 'steps': 61545, 'loss/train': 2.0038974285125732} 08/31/2021 00:24:04 - INFO - __main__ - Step 61547: {'lr': 0.00032550591389929437, 'samples': 11817024, 'steps': 61546, 'loss/train': 1.1816316843032837} 08/31/2021 00:24:04 - INFO - __main__ - Step 61548: {'lr': 0.0003255008549606111, 'samples': 11817216, 'steps': 61547, 'loss/train': 0.6127081513404846} 08/31/2021 00:24:05 - INFO - __main__ - Step 61549: {'lr': 0.0003254957959879084, 'samples': 11817408, 'steps': 61548, 'loss/train': 1.432588815689087} 08/31/2021 00:24:05 - INFO - __main__ - Step 61550: {'lr': 0.0003254907369811885, 'samples': 11817600, 'steps': 61549, 'loss/train': 1.312138319015503} 08/31/2021 00:24:07 - INFO - __main__ - Step 61551: {'lr': 0.00032548567794045354, 'samples': 11817792, 'steps': 61550, 'loss/train': 1.419482707977295} 08/31/2021 00:24:07 - INFO - __main__ - Step 61552: {'lr': 0.000325480618865706, 'samples': 11817984, 'steps': 61551, 'loss/train': 1.2455546855926514} 08/31/2021 00:24:07 - INFO - __main__ - Step 61553: {'lr': 0.00032547555975694797, 'samples': 11818176, 'steps': 61552, 'loss/train': 1.4872130155563354} 08/31/2021 00:24:08 - INFO - __main__ - Step 61554: {'lr': 0.0003254705006141818, 'samples': 11818368, 'steps': 61553, 'loss/train': 1.9815887212753296} 08/31/2021 00:24:08 - INFO - __main__ - Step 61555: {'lr': 0.00032546544143740983, 'samples': 11818560, 'steps': 61554, 'loss/train': 1.1569088697433472} 08/31/2021 00:24:10 - INFO - __main__ - Step 61556: {'lr': 0.0003254603822266343, 'samples': 11818752, 'steps': 61555, 'loss/train': 1.347487449645996} 08/31/2021 00:24:10 - INFO - __main__ - Step 61557: {'lr': 0.0003254553229818575, 'samples': 11818944, 'steps': 61556, 'loss/train': 1.357451319694519} 08/31/2021 00:24:11 - INFO - __main__ - Step 61558: {'lr': 0.00032545026370308175, 'samples': 11819136, 'steps': 61557, 'loss/train': 0.32529136538505554} 08/31/2021 00:24:11 - INFO - __main__ - Step 61559: {'lr': 0.00032544520439030915, 'samples': 11819328, 'steps': 61558, 'loss/train': 0.23144900798797607} 08/31/2021 00:24:11 - INFO - __main__ - Step 61560: {'lr': 0.00032544014504354215, 'samples': 11819520, 'steps': 61559, 'loss/train': 0.5133909583091736} 08/31/2021 00:24:13 - INFO - __main__ - Step 61561: {'lr': 0.000325435085662783, 'samples': 11819712, 'steps': 61560, 'loss/train': 0.04931097850203514} 08/31/2021 00:24:13 - INFO - __main__ - Step 61562: {'lr': 0.000325430026248034, 'samples': 11819904, 'steps': 61561, 'loss/train': 1.1856831312179565} 08/31/2021 00:24:14 - INFO - __main__ - Step 61563: {'lr': 0.00032542496679929735, 'samples': 11820096, 'steps': 61562, 'loss/train': 1.3713566064834595} 08/31/2021 00:24:14 - INFO - __main__ - Step 61564: {'lr': 0.00032541990731657536, 'samples': 11820288, 'steps': 61563, 'loss/train': 1.6022552251815796} 08/31/2021 00:24:14 - INFO - __main__ - Step 61565: {'lr': 0.00032541484779987034, 'samples': 11820480, 'steps': 61564, 'loss/train': 1.5828309059143066} 08/31/2021 00:24:16 - INFO - __main__ - Step 61566: {'lr': 0.00032540978824918454, 'samples': 11820672, 'steps': 61565, 'loss/train': 1.6494194269180298} 08/31/2021 00:24:17 - INFO - __main__ - Step 61567: {'lr': 0.0003254047286645203, 'samples': 11820864, 'steps': 61566, 'loss/train': 1.282508134841919} 08/31/2021 00:24:17 - INFO - __main__ - Step 61568: {'lr': 0.0003253996690458798, 'samples': 11821056, 'steps': 61567, 'loss/train': 0.7252542972564697} 08/31/2021 00:24:18 - INFO - __main__ - Step 61569: {'lr': 0.00032539460939326535, 'samples': 11821248, 'steps': 61568, 'loss/train': 0.7074411511421204} 08/31/2021 00:24:18 - INFO - __main__ - Step 61570: {'lr': 0.00032538954970667936, 'samples': 11821440, 'steps': 61569, 'loss/train': 1.4048383235931396} 08/31/2021 00:24:19 - INFO - __main__ - Step 61571: {'lr': 0.0003253844899861239, 'samples': 11821632, 'steps': 61570, 'loss/train': 0.8941242098808289} 08/31/2021 00:24:20 - INFO - __main__ - Step 61572: {'lr': 0.0003253794302316014, 'samples': 11821824, 'steps': 61571, 'loss/train': 1.4645757675170898} 08/31/2021 00:24:20 - INFO - __main__ - Step 61573: {'lr': 0.00032537437044311414, 'samples': 11822016, 'steps': 61572, 'loss/train': 1.8832898139953613} 08/31/2021 00:24:21 - INFO - __main__ - Step 61574: {'lr': 0.0003253693106206643, 'samples': 11822208, 'steps': 61573, 'loss/train': 1.3773918151855469} 08/31/2021 00:24:21 - INFO - __main__ - Step 61575: {'lr': 0.0003253642507642541, 'samples': 11822400, 'steps': 61574, 'loss/train': 0.8925369381904602} 08/31/2021 00:24:22 - INFO - __main__ - Step 61576: {'lr': 0.0003253591908738861, 'samples': 11822592, 'steps': 61575, 'loss/train': 1.1983656883239746} 08/31/2021 00:24:23 - INFO - __main__ - Step 61577: {'lr': 0.00032535413094956237, 'samples': 11822784, 'steps': 61576, 'loss/train': 1.4087897539138794} 08/31/2021 00:24:23 - INFO - __main__ - Step 61578: {'lr': 0.0003253490709912852, 'samples': 11822976, 'steps': 61577, 'loss/train': 1.211853265762329} 08/31/2021 00:24:24 - INFO - __main__ - Step 61579: {'lr': 0.0003253440109990569, 'samples': 11823168, 'steps': 61578, 'loss/train': 1.2404204607009888} 08/31/2021 00:24:24 - INFO - __main__ - Step 61580: {'lr': 0.0003253389509728798, 'samples': 11823360, 'steps': 61579, 'loss/train': 1.3774334192276} 08/31/2021 00:24:25 - INFO - __main__ - Step 61581: {'lr': 0.0003253338909127561, 'samples': 11823552, 'steps': 61580, 'loss/train': 1.3028075695037842} 08/31/2021 00:24:26 - INFO - __main__ - Step 61582: {'lr': 0.00032532883081868804, 'samples': 11823744, 'steps': 61581, 'loss/train': 1.5160951614379883} 08/31/2021 00:24:26 - INFO - __main__ - Step 61583: {'lr': 0.000325323770690678, 'samples': 11823936, 'steps': 61582, 'loss/train': 1.3680591583251953} 08/31/2021 00:24:26 - INFO - __main__ - Step 61584: {'lr': 0.00032531871052872836, 'samples': 11824128, 'steps': 61583, 'loss/train': 1.561838984489441} 08/31/2021 00:24:27 - INFO - __main__ - Step 61585: {'lr': 0.00032531365033284116, 'samples': 11824320, 'steps': 61584, 'loss/train': 1.104370355606079} 08/31/2021 00:24:27 - INFO - __main__ - Step 61586: {'lr': 0.0003253085901030188, 'samples': 11824512, 'steps': 61585, 'loss/train': 0.4576624035835266} 08/31/2021 00:24:29 - INFO - __main__ - Step 61587: {'lr': 0.0003253035298392636, 'samples': 11824704, 'steps': 61586, 'loss/train': 1.2294578552246094} 08/31/2021 00:24:29 - INFO - __main__ - Step 61588: {'lr': 0.0003252984695415777, 'samples': 11824896, 'steps': 61587, 'loss/train': 1.5012516975402832} 08/31/2021 00:24:30 - INFO - __main__ - Step 61589: {'lr': 0.0003252934092099636, 'samples': 11825088, 'steps': 61588, 'loss/train': 1.3170855045318604} 08/31/2021 00:24:30 - INFO - __main__ - Step 61590: {'lr': 0.00032528834884442337, 'samples': 11825280, 'steps': 61589, 'loss/train': 1.220700740814209} 08/31/2021 00:24:30 - INFO - __main__ - Step 61591: {'lr': 0.0003252832884449594, 'samples': 11825472, 'steps': 61590, 'loss/train': 0.8238400816917419} 08/31/2021 00:24:32 - INFO - __main__ - Step 61592: {'lr': 0.00032527822801157384, 'samples': 11825664, 'steps': 61591, 'loss/train': 0.5120631456375122} 08/31/2021 00:24:32 - INFO - __main__ - Step 61593: {'lr': 0.00032527316754426915, 'samples': 11825856, 'steps': 61592, 'loss/train': 1.4506065845489502} 08/31/2021 00:24:32 - INFO - __main__ - Step 61594: {'lr': 0.0003252681070430476, 'samples': 11826048, 'steps': 61593, 'loss/train': 1.6031575202941895} 08/31/2021 00:24:33 - INFO - __main__ - Step 61595: {'lr': 0.00032526304650791135, 'samples': 11826240, 'steps': 61594, 'loss/train': 1.0435556173324585} 08/31/2021 00:24:33 - INFO - __main__ - Step 61596: {'lr': 0.0003252579859388627, 'samples': 11826432, 'steps': 61595, 'loss/train': 0.2987871468067169} 08/31/2021 00:24:35 - INFO - __main__ - Step 61597: {'lr': 0.000325252925335904, 'samples': 11826624, 'steps': 61596, 'loss/train': 1.392291784286499} 08/31/2021 00:24:35 - INFO - __main__ - Step 61598: {'lr': 0.00032524786469903744, 'samples': 11826816, 'steps': 61597, 'loss/train': 1.4544073343276978} 08/31/2021 00:24:35 - INFO - __main__ - Step 61599: {'lr': 0.0003252428040282654, 'samples': 11827008, 'steps': 61598, 'loss/train': 1.3925453424453735} 08/31/2021 00:24:36 - INFO - __main__ - Step 61600: {'lr': 0.00032523774332359016, 'samples': 11827200, 'steps': 61599, 'loss/train': 1.5761696100234985} 08/31/2021 00:24:36 - INFO - __main__ - Step 61601: {'lr': 0.00032523268258501385, 'samples': 11827392, 'steps': 61600, 'loss/train': 1.0877801179885864} 08/31/2021 00:24:38 - INFO - __main__ - Step 61602: {'lr': 0.0003252276218125389, 'samples': 11827584, 'steps': 61601, 'loss/train': 1.3422201871871948} 08/31/2021 00:24:38 - INFO - __main__ - Step 61603: {'lr': 0.00032522256100616753, 'samples': 11827776, 'steps': 61602, 'loss/train': 1.0424445867538452} 08/31/2021 00:24:39 - INFO - __main__ - Step 61604: {'lr': 0.00032521750016590206, 'samples': 11827968, 'steps': 61603, 'loss/train': 0.9929898381233215} 08/31/2021 00:24:39 - INFO - __main__ - Step 61605: {'lr': 0.0003252124392917447, 'samples': 11828160, 'steps': 61604, 'loss/train': 0.907509446144104} 08/31/2021 00:24:39 - INFO - __main__ - Step 61606: {'lr': 0.00032520737838369785, 'samples': 11828352, 'steps': 61605, 'loss/train': 1.3392136096954346} 08/31/2021 00:24:40 - INFO - __main__ - Step 61607: {'lr': 0.0003252023174417637, 'samples': 11828544, 'steps': 61606, 'loss/train': 0.9852229952812195} 08/31/2021 00:24:42 - INFO - __main__ - Step 61608: {'lr': 0.0003251972564659445, 'samples': 11828736, 'steps': 61607, 'loss/train': 1.1921606063842773} 08/31/2021 00:24:42 - INFO - __main__ - Step 61609: {'lr': 0.0003251921954562426, 'samples': 11828928, 'steps': 61608, 'loss/train': 1.0905529260635376} 08/31/2021 00:24:43 - INFO - __main__ - Step 61610: {'lr': 0.00032518713441266026, 'samples': 11829120, 'steps': 61609, 'loss/train': 1.1209497451782227} 08/31/2021 00:24:43 - INFO - __main__ - Step 61611: {'lr': 0.0003251820733351997, 'samples': 11829312, 'steps': 61610, 'loss/train': 1.4915714263916016} 08/31/2021 00:24:43 - INFO - __main__ - Step 61612: {'lr': 0.0003251770122238634, 'samples': 11829504, 'steps': 61611, 'loss/train': 1.472586989402771} 08/31/2021 00:24:44 - INFO - __main__ - Step 61613: {'lr': 0.0003251719510786534, 'samples': 11829696, 'steps': 61612, 'loss/train': 0.7957358360290527} 08/31/2021 00:24:45 - INFO - __main__ - Step 61614: {'lr': 0.0003251668898995721, 'samples': 11829888, 'steps': 61613, 'loss/train': 0.042749810963869095} 08/31/2021 00:24:45 - INFO - __main__ - Step 61615: {'lr': 0.0003251618286866217, 'samples': 11830080, 'steps': 61614, 'loss/train': 0.868034303188324} 08/31/2021 00:24:46 - INFO - __main__ - Step 61616: {'lr': 0.0003251567674398046, 'samples': 11830272, 'steps': 61615, 'loss/train': 1.9249500036239624} 08/31/2021 00:24:46 - INFO - __main__ - Step 61617: {'lr': 0.00032515170615912296, 'samples': 11830464, 'steps': 61616, 'loss/train': 0.5533629059791565} 08/31/2021 00:24:47 - INFO - __main__ - Step 61618: {'lr': 0.00032514664484457916, 'samples': 11830656, 'steps': 61617, 'loss/train': 1.583204746246338} 08/31/2021 00:24:49 - INFO - __main__ - Step 61619: {'lr': 0.0003251415834961755, 'samples': 11830848, 'steps': 61618, 'loss/train': 1.578773856163025} 08/31/2021 00:24:49 - INFO - __main__ - Step 61620: {'lr': 0.0003251365221139142, 'samples': 11831040, 'steps': 61619, 'loss/train': 0.08003528416156769} 08/31/2021 00:24:50 - INFO - __main__ - Step 61621: {'lr': 0.0003251314606977975, 'samples': 11831232, 'steps': 61620, 'loss/train': 0.5764644742012024} 08/31/2021 00:24:50 - INFO - __main__ - Step 61622: {'lr': 0.0003251263992478277, 'samples': 11831424, 'steps': 61621, 'loss/train': 1.4581990242004395} 08/31/2021 00:24:50 - INFO - __main__ - Step 61623: {'lr': 0.0003251213377640071, 'samples': 11831616, 'steps': 61622, 'loss/train': 1.4880990982055664} 08/31/2021 00:24:51 - INFO - __main__ - Step 61624: {'lr': 0.000325116276246338, 'samples': 11831808, 'steps': 61623, 'loss/train': 1.6477514505386353} 08/31/2021 00:24:52 - INFO - __main__ - Step 61625: {'lr': 0.00032511121469482263, 'samples': 11832000, 'steps': 61624, 'loss/train': 1.6432732343673706} 08/31/2021 00:24:53 - INFO - __main__ - Step 61626: {'lr': 0.0003251061531094634, 'samples': 11832192, 'steps': 61625, 'loss/train': 1.2673031091690063} 08/31/2021 00:24:53 - INFO - __main__ - Step 61627: {'lr': 0.00032510109149026247, 'samples': 11832384, 'steps': 61626, 'loss/train': 1.1021595001220703} 08/31/2021 00:24:53 - INFO - __main__ - Step 61628: {'lr': 0.0003250960298372221, 'samples': 11832576, 'steps': 61627, 'loss/train': 1.1433745622634888} 08/31/2021 00:24:54 - INFO - __main__ - Step 61629: {'lr': 0.0003250909681503446, 'samples': 11832768, 'steps': 61628, 'loss/train': 0.7088781595230103} 08/31/2021 00:24:55 - INFO - __main__ - Step 61630: {'lr': 0.00032508590642963233, 'samples': 11832960, 'steps': 61629, 'loss/train': 1.3170939683914185} 08/31/2021 00:24:56 - INFO - __main__ - Step 61631: {'lr': 0.00032508084467508747, 'samples': 11833152, 'steps': 61630, 'loss/train': 1.3777683973312378} 08/31/2021 00:24:56 - INFO - __main__ - Step 61632: {'lr': 0.0003250757828867124, 'samples': 11833344, 'steps': 61631, 'loss/train': 0.9492822289466858} 08/31/2021 00:24:56 - INFO - __main__ - Step 61633: {'lr': 0.0003250707210645093, 'samples': 11833536, 'steps': 61632, 'loss/train': 1.217972755432129} 08/31/2021 00:24:57 - INFO - __main__ - Step 61634: {'lr': 0.0003250656592084805, 'samples': 11833728, 'steps': 61633, 'loss/train': 1.560431957244873} 08/31/2021 00:24:58 - INFO - __main__ - Step 61635: {'lr': 0.00032506059731862827, 'samples': 11833920, 'steps': 61634, 'loss/train': 1.9131455421447754} 08/31/2021 00:24:59 - INFO - __main__ - Step 61636: {'lr': 0.0003250555353949548, 'samples': 11834112, 'steps': 61635, 'loss/train': 1.3659495115280151} 08/31/2021 00:24:59 - INFO - __main__ - Step 61637: {'lr': 0.0003250504734374626, 'samples': 11834304, 'steps': 61636, 'loss/train': 1.293955683708191} 08/31/2021 00:24:59 - INFO - __main__ - Step 61638: {'lr': 0.0003250454114461537, 'samples': 11834496, 'steps': 61637, 'loss/train': 0.8856723308563232} 08/31/2021 00:25:00 - INFO - __main__ - Step 61639: {'lr': 0.0003250403494210306, 'samples': 11834688, 'steps': 61638, 'loss/train': 1.7899491786956787} 08/31/2021 00:25:01 - INFO - __main__ - Step 61640: {'lr': 0.00032503528736209543, 'samples': 11834880, 'steps': 61639, 'loss/train': 1.4393724203109741} 08/31/2021 00:25:02 - INFO - __main__ - Step 61641: {'lr': 0.00032503022526935056, 'samples': 11835072, 'steps': 61640, 'loss/train': 1.345940351486206} 08/31/2021 00:25:02 - INFO - __main__ - Step 61642: {'lr': 0.00032502516314279815, 'samples': 11835264, 'steps': 61641, 'loss/train': 1.4636180400848389} 08/31/2021 00:25:02 - INFO - __main__ - Step 61643: {'lr': 0.0003250201009824406, 'samples': 11835456, 'steps': 61642, 'loss/train': 1.434397578239441} 08/31/2021 00:25:03 - INFO - __main__ - Step 61644: {'lr': 0.00032501503878828016, 'samples': 11835648, 'steps': 61643, 'loss/train': 1.2061984539031982} 08/31/2021 00:25:04 - INFO - __main__ - Step 61645: {'lr': 0.00032500997656031907, 'samples': 11835840, 'steps': 61644, 'loss/train': 1.6741113662719727} 08/31/2021 00:25:05 - INFO - __main__ - Step 61646: {'lr': 0.0003250049142985597, 'samples': 11836032, 'steps': 61645, 'loss/train': 0.8708042502403259} 08/31/2021 00:25:05 - INFO - __main__ - Step 61647: {'lr': 0.0003249998520030042, 'samples': 11836224, 'steps': 61646, 'loss/train': 1.4896221160888672} 08/31/2021 00:25:05 - INFO - __main__ - Step 61648: {'lr': 0.00032499478967365497, 'samples': 11836416, 'steps': 61647, 'loss/train': 1.28041672706604} 08/31/2021 00:25:06 - INFO - __main__ - Step 61649: {'lr': 0.00032498972731051425, 'samples': 11836608, 'steps': 61648, 'loss/train': 1.7720552682876587} 08/31/2021 00:25:07 - INFO - __main__ - Step 61650: {'lr': 0.00032498466491358427, 'samples': 11836800, 'steps': 61649, 'loss/train': 1.3812153339385986} 08/31/2021 00:25:08 - INFO - __main__ - Step 61651: {'lr': 0.0003249796024828674, 'samples': 11836992, 'steps': 61650, 'loss/train': 1.3565776348114014} 08/31/2021 00:25:08 - INFO - __main__ - Step 61652: {'lr': 0.00032497454001836586, 'samples': 11837184, 'steps': 61651, 'loss/train': 1.122170329093933} 08/31/2021 00:25:08 - INFO - __main__ - Step 61653: {'lr': 0.000324969477520082, 'samples': 11837376, 'steps': 61652, 'loss/train': 1.1148302555084229} 08/31/2021 00:25:09 - INFO - __main__ - Step 61654: {'lr': 0.000324964414988018, 'samples': 11837568, 'steps': 61653, 'loss/train': 0.6475325226783752} 08/31/2021 00:25:09 - INFO - __main__ - Step 61655: {'lr': 0.0003249593524221762, 'samples': 11837760, 'steps': 61654, 'loss/train': 1.4871201515197754} 08/31/2021 00:25:11 - INFO - __main__ - Step 61656: {'lr': 0.0003249542898225588, 'samples': 11837952, 'steps': 61655, 'loss/train': 0.2427823841571808} 08/31/2021 00:25:11 - INFO - __main__ - Step 61657: {'lr': 0.00032494922718916824, 'samples': 11838144, 'steps': 61656, 'loss/train': 1.811215877532959} 08/31/2021 00:25:12 - INFO - __main__ - Step 61658: {'lr': 0.0003249441645220067, 'samples': 11838336, 'steps': 61657, 'loss/train': 1.406896948814392} 08/31/2021 00:25:12 - INFO - __main__ - Step 61659: {'lr': 0.0003249391018210765, 'samples': 11838528, 'steps': 61658, 'loss/train': 0.0928245410323143} 08/31/2021 00:25:12 - INFO - __main__ - Step 61660: {'lr': 0.0003249340390863799, 'samples': 11838720, 'steps': 61659, 'loss/train': 1.7563753128051758} 08/31/2021 00:25:14 - INFO - __main__ - Step 61661: {'lr': 0.00032492897631791913, 'samples': 11838912, 'steps': 61660, 'loss/train': 1.815104365348816} 08/31/2021 00:25:14 - INFO - __main__ - Step 61662: {'lr': 0.0003249239135156965, 'samples': 11839104, 'steps': 61661, 'loss/train': 1.0409648418426514} 08/31/2021 00:25:15 - INFO - __main__ - Step 61663: {'lr': 0.0003249188506797144, 'samples': 11839296, 'steps': 61662, 'loss/train': 0.5471335053443909} 08/31/2021 00:25:15 - INFO - __main__ - Step 61664: {'lr': 0.00032491378780997494, 'samples': 11839488, 'steps': 61663, 'loss/train': 1.1925173997879028} 08/31/2021 00:25:15 - INFO - __main__ - Step 61665: {'lr': 0.0003249087249064805, 'samples': 11839680, 'steps': 61664, 'loss/train': 1.3407034873962402} 08/31/2021 00:25:17 - INFO - __main__ - Step 61666: {'lr': 0.00032490366196923336, 'samples': 11839872, 'steps': 61665, 'loss/train': 1.3204448223114014} 08/31/2021 00:25:18 - INFO - __main__ - Step 61667: {'lr': 0.00032489859899823584, 'samples': 11840064, 'steps': 61666, 'loss/train': 1.0101540088653564} 08/31/2021 00:25:18 - INFO - __main__ - Step 61668: {'lr': 0.0003248935359934901, 'samples': 11840256, 'steps': 61667, 'loss/train': 0.04883047193288803} 08/31/2021 00:25:18 - INFO - __main__ - Step 61669: {'lr': 0.00032488847295499847, 'samples': 11840448, 'steps': 61668, 'loss/train': 1.2941408157348633} 08/31/2021 00:25:19 - INFO - __main__ - Step 61670: {'lr': 0.0003248834098827633, 'samples': 11840640, 'steps': 61669, 'loss/train': 1.1264632940292358} 08/31/2021 00:25:19 - INFO - __main__ - Step 61671: {'lr': 0.0003248783467767867, 'samples': 11840832, 'steps': 61670, 'loss/train': 0.4100927710533142} 08/31/2021 00:25:21 - INFO - __main__ - Step 61672: {'lr': 0.00032487328363707123, 'samples': 11841024, 'steps': 61671, 'loss/train': 1.5320886373519897} 08/31/2021 00:25:22 - INFO - __main__ - Step 61673: {'lr': 0.00032486822046361895, 'samples': 11841216, 'steps': 61672, 'loss/train': 1.7680808305740356} 08/31/2021 00:25:22 - INFO - __main__ - Step 61674: {'lr': 0.0003248631572564322, 'samples': 11841408, 'steps': 61673, 'loss/train': 1.6427550315856934} 08/31/2021 00:25:22 - INFO - __main__ - Step 61675: {'lr': 0.0003248580940155133, 'samples': 11841600, 'steps': 61674, 'loss/train': 1.2946466207504272} 08/31/2021 00:25:23 - INFO - __main__ - Step 61676: {'lr': 0.0003248530307408645, 'samples': 11841792, 'steps': 61675, 'loss/train': 2.0517308712005615} 08/31/2021 00:25:25 - INFO - __main__ - Step 61677: {'lr': 0.00032484796743248803, 'samples': 11841984, 'steps': 61676, 'loss/train': 2.751971960067749} 08/31/2021 00:25:25 - INFO - __main__ - Step 61678: {'lr': 0.00032484290409038626, 'samples': 11842176, 'steps': 61677, 'loss/train': 0.1273297369480133} 08/31/2021 00:25:26 - INFO - __main__ - Step 61679: {'lr': 0.00032483784071456146, 'samples': 11842368, 'steps': 61678, 'loss/train': 0.34657809138298035} 08/31/2021 00:25:26 - INFO - __main__ - Step 61680: {'lr': 0.0003248327773050158, 'samples': 11842560, 'steps': 61679, 'loss/train': 1.3876729011535645} 08/31/2021 00:25:26 - INFO - __main__ - Step 61681: {'lr': 0.0003248277138617517, 'samples': 11842752, 'steps': 61680, 'loss/train': 1.5825897455215454} 08/31/2021 00:25:28 - INFO - __main__ - Step 61682: {'lr': 0.0003248226503847714, 'samples': 11842944, 'steps': 61681, 'loss/train': 0.9642598628997803} 08/31/2021 00:25:29 - INFO - __main__ - Step 61683: {'lr': 0.0003248175868740771, 'samples': 11843136, 'steps': 61682, 'loss/train': 1.561469316482544} 08/31/2021 00:25:29 - INFO - __main__ - Step 61684: {'lr': 0.0003248125233296712, 'samples': 11843328, 'steps': 61683, 'loss/train': 1.4193835258483887} 08/31/2021 00:25:29 - INFO - __main__ - Step 61685: {'lr': 0.0003248074597515559, 'samples': 11843520, 'steps': 61684, 'loss/train': 0.16702589392662048} 08/31/2021 00:25:30 - INFO - __main__ - Step 61686: {'lr': 0.0003248023961397336, 'samples': 11843712, 'steps': 61685, 'loss/train': 0.41531768441200256} 08/31/2021 00:25:30 - INFO - __main__ - Step 61687: {'lr': 0.0003247973324942064, 'samples': 11843904, 'steps': 61686, 'loss/train': 0.9130374789237976} 08/31/2021 00:25:31 - INFO - __main__ - Step 61688: {'lr': 0.0003247922688149767, 'samples': 11844096, 'steps': 61687, 'loss/train': 0.1466338038444519} 08/31/2021 00:25:32 - INFO - __main__ - Step 61689: {'lr': 0.0003247872051020468, 'samples': 11844288, 'steps': 61688, 'loss/train': 0.21166403591632843} 08/31/2021 00:25:32 - INFO - __main__ - Step 61690: {'lr': 0.0003247821413554188, 'samples': 11844480, 'steps': 61689, 'loss/train': 1.5313704013824463} 08/31/2021 00:25:33 - INFO - __main__ - Step 61691: {'lr': 0.00032477707757509527, 'samples': 11844672, 'steps': 61690, 'loss/train': 1.4712797403335571} 08/31/2021 00:25:33 - INFO - __main__ - Step 61692: {'lr': 0.0003247720137610783, 'samples': 11844864, 'steps': 61691, 'loss/train': 1.2196170091629028} 08/31/2021 00:25:35 - INFO - __main__ - Step 61693: {'lr': 0.0003247669499133702, 'samples': 11845056, 'steps': 61692, 'loss/train': 0.8636454343795776} 08/31/2021 00:25:35 - INFO - __main__ - Step 61694: {'lr': 0.00032476188603197334, 'samples': 11845248, 'steps': 61693, 'loss/train': 0.8991870880126953} 08/31/2021 00:25:35 - INFO - __main__ - Step 61695: {'lr': 0.00032475682211688986, 'samples': 11845440, 'steps': 61694, 'loss/train': 1.7546366453170776} 08/31/2021 00:25:36 - INFO - __main__ - Step 61696: {'lr': 0.00032475175816812206, 'samples': 11845632, 'steps': 61695, 'loss/train': 1.3264589309692383} 08/31/2021 00:25:36 - INFO - __main__ - Step 61697: {'lr': 0.0003247466941856724, 'samples': 11845824, 'steps': 61696, 'loss/train': 1.7313196659088135} 08/31/2021 00:25:37 - INFO - __main__ - Step 61698: {'lr': 0.00032474163016954293, 'samples': 11846016, 'steps': 61697, 'loss/train': 0.715316653251648} 08/31/2021 00:25:38 - INFO - __main__ - Step 61699: {'lr': 0.00032473656611973605, 'samples': 11846208, 'steps': 61698, 'loss/train': 0.5454854965209961} 08/31/2021 00:25:38 - INFO - __main__ - Step 61700: {'lr': 0.00032473150203625407, 'samples': 11846400, 'steps': 61699, 'loss/train': 1.1384847164154053} 08/31/2021 00:25:39 - INFO - __main__ - Step 61701: {'lr': 0.0003247264379190992, 'samples': 11846592, 'steps': 61700, 'loss/train': 1.1349167823791504} 08/31/2021 00:25:39 - INFO - __main__ - Step 61702: {'lr': 0.00032472137376827375, 'samples': 11846784, 'steps': 61701, 'loss/train': 0.9783865213394165} 08/31/2021 00:25:40 - INFO - __main__ - Step 61703: {'lr': 0.00032471630958378, 'samples': 11846976, 'steps': 61702, 'loss/train': 1.6328257322311401} 08/31/2021 00:25:41 - INFO - __main__ - Step 61704: {'lr': 0.0003247112453656202, 'samples': 11847168, 'steps': 61703, 'loss/train': 1.4172316789627075} 08/31/2021 00:25:41 - INFO - __main__ - Step 61705: {'lr': 0.0003247061811137967, 'samples': 11847360, 'steps': 61704, 'loss/train': 1.360416054725647} 08/31/2021 00:25:42 - INFO - __main__ - Step 61706: {'lr': 0.00032470111682831183, 'samples': 11847552, 'steps': 61705, 'loss/train': 1.2427173852920532} 08/31/2021 00:25:42 - INFO - __main__ - Step 61707: {'lr': 0.00032469605250916766, 'samples': 11847744, 'steps': 61706, 'loss/train': 1.3855103254318237} 08/31/2021 00:25:44 - INFO - __main__ - Step 61708: {'lr': 0.00032469098815636667, 'samples': 11847936, 'steps': 61707, 'loss/train': 1.275707483291626} 08/31/2021 00:25:44 - INFO - __main__ - Step 61709: {'lr': 0.000324685923769911, 'samples': 11848128, 'steps': 61708, 'loss/train': 1.9543116092681885} 08/31/2021 00:25:44 - INFO - __main__ - Step 61710: {'lr': 0.00032468085934980306, 'samples': 11848320, 'steps': 61709, 'loss/train': 1.4494297504425049} 08/31/2021 00:25:45 - INFO - __main__ - Step 61711: {'lr': 0.0003246757948960451, 'samples': 11848512, 'steps': 61710, 'loss/train': 1.489911437034607} 08/31/2021 00:25:45 - INFO - __main__ - Step 61712: {'lr': 0.00032467073040863943, 'samples': 11848704, 'steps': 61711, 'loss/train': 0.9391356110572815} 08/31/2021 00:25:46 - INFO - __main__ - Step 61713: {'lr': 0.00032466566588758815, 'samples': 11848896, 'steps': 61712, 'loss/train': 1.3538992404937744} 08/31/2021 00:25:47 - INFO - __main__ - Step 61714: {'lr': 0.00032466060133289374, 'samples': 11849088, 'steps': 61713, 'loss/train': 0.6737422943115234} 08/31/2021 00:25:48 - INFO - __main__ - Step 61715: {'lr': 0.0003246555367445584, 'samples': 11849280, 'steps': 61714, 'loss/train': 0.9506126642227173} 08/31/2021 00:25:48 - INFO - __main__ - Step 61716: {'lr': 0.0003246504721225844, 'samples': 11849472, 'steps': 61715, 'loss/train': 1.3098273277282715} 08/31/2021 00:25:48 - INFO - __main__ - Step 61717: {'lr': 0.00032464540746697415, 'samples': 11849664, 'steps': 61716, 'loss/train': 1.267270565032959} 08/31/2021 00:25:49 - INFO - __main__ - Step 61718: {'lr': 0.00032464034277772977, 'samples': 11849856, 'steps': 61717, 'loss/train': 1.346571445465088} 08/31/2021 00:25:50 - INFO - __main__ - Step 61719: {'lr': 0.0003246352780548536, 'samples': 11850048, 'steps': 61718, 'loss/train': 1.5764418840408325} 08/31/2021 00:25:51 - INFO - __main__ - Step 61720: {'lr': 0.0003246302132983479, 'samples': 11850240, 'steps': 61719, 'loss/train': 0.6532245874404907} 08/31/2021 00:25:51 - INFO - __main__ - Step 61721: {'lr': 0.000324625148508215, 'samples': 11850432, 'steps': 61720, 'loss/train': 1.040414810180664} 08/31/2021 00:25:51 - INFO - __main__ - Step 61722: {'lr': 0.00032462008368445717, 'samples': 11850624, 'steps': 61721, 'loss/train': 0.7537640333175659} 08/31/2021 00:25:52 - INFO - __main__ - Step 61723: {'lr': 0.00032461501882707667, 'samples': 11850816, 'steps': 61722, 'loss/train': 1.0497034788131714} 08/31/2021 00:25:54 - INFO - __main__ - Step 61724: {'lr': 0.0003246099539360758, 'samples': 11851008, 'steps': 61723, 'loss/train': 1.0722224712371826} 08/31/2021 00:25:54 - INFO - __main__ - Step 61725: {'lr': 0.0003246048890114568, 'samples': 11851200, 'steps': 61724, 'loss/train': 1.0762724876403809} 08/31/2021 00:25:54 - INFO - __main__ - Step 61726: {'lr': 0.00032459982405322205, 'samples': 11851392, 'steps': 61725, 'loss/train': 1.5215147733688354} 08/31/2021 00:25:55 - INFO - __main__ - Step 61727: {'lr': 0.0003245947590613737, 'samples': 11851584, 'steps': 61726, 'loss/train': 0.7172834873199463} 08/31/2021 00:25:55 - INFO - __main__ - Step 61728: {'lr': 0.00032458969403591415, 'samples': 11851776, 'steps': 61727, 'loss/train': 1.571946144104004} 08/31/2021 00:25:57 - INFO - __main__ - Step 61729: {'lr': 0.00032458462897684564, 'samples': 11851968, 'steps': 61728, 'loss/train': 0.271742045879364} 08/31/2021 00:25:57 - INFO - __main__ - Step 61730: {'lr': 0.00032457956388417045, 'samples': 11852160, 'steps': 61729, 'loss/train': 1.18363618850708} 08/31/2021 00:25:58 - INFO - __main__ - Step 61731: {'lr': 0.00032457449875789084, 'samples': 11852352, 'steps': 61730, 'loss/train': 0.9047630429267883} 08/31/2021 00:25:58 - INFO - __main__ - Step 61732: {'lr': 0.0003245694335980091, 'samples': 11852544, 'steps': 61731, 'loss/train': 1.4249035120010376} 08/31/2021 00:25:58 - INFO - __main__ - Step 61733: {'lr': 0.00032456436840452754, 'samples': 11852736, 'steps': 61732, 'loss/train': 0.7241594195365906} 08/31/2021 00:25:59 - INFO - __main__ - Step 61734: {'lr': 0.00032455930317744846, 'samples': 11852928, 'steps': 61733, 'loss/train': 0.06505557894706726} 08/31/2021 00:26:01 - INFO - __main__ - Step 61735: {'lr': 0.0003245542379167741, 'samples': 11853120, 'steps': 61734, 'loss/train': 0.7906770706176758} 08/31/2021 00:26:01 - INFO - __main__ - Step 61736: {'lr': 0.0003245491726225067, 'samples': 11853312, 'steps': 61735, 'loss/train': 1.1695952415466309} 08/31/2021 00:26:02 - INFO - __main__ - Step 61737: {'lr': 0.00032454410729464855, 'samples': 11853504, 'steps': 61736, 'loss/train': 0.6432914137840271} 08/31/2021 00:26:02 - INFO - __main__ - Step 61738: {'lr': 0.00032453904193320207, 'samples': 11853696, 'steps': 61737, 'loss/train': 1.571433663368225} 08/31/2021 00:26:02 - INFO - __main__ - Step 61739: {'lr': 0.0003245339765381694, 'samples': 11853888, 'steps': 61738, 'loss/train': 1.3935928344726562} 08/31/2021 00:26:04 - INFO - __main__ - Step 61740: {'lr': 0.00032452891110955296, 'samples': 11854080, 'steps': 61739, 'loss/train': 1.7350441217422485} 08/31/2021 00:26:04 - INFO - __main__ - Step 61741: {'lr': 0.0003245238456473549, 'samples': 11854272, 'steps': 61740, 'loss/train': 1.073574185371399} 08/31/2021 00:26:05 - INFO - __main__ - Step 61742: {'lr': 0.0003245187801515775, 'samples': 11854464, 'steps': 61741, 'loss/train': 1.0946937799453735} 08/31/2021 00:26:05 - INFO - __main__ - Step 61743: {'lr': 0.00032451371462222307, 'samples': 11854656, 'steps': 61742, 'loss/train': 2.117478609085083} 08/31/2021 00:26:05 - INFO - __main__ - Step 61744: {'lr': 0.00032450864905929393, 'samples': 11854848, 'steps': 61743, 'loss/train': 1.8307740688323975} 08/31/2021 00:26:06 - INFO - __main__ - Step 61745: {'lr': 0.00032450358346279237, 'samples': 11855040, 'steps': 61744, 'loss/train': 1.4272785186767578} 08/31/2021 00:26:07 - INFO - __main__ - Step 61746: {'lr': 0.0003244985178327206, 'samples': 11855232, 'steps': 61745, 'loss/train': 0.27117565274238586} 08/31/2021 00:26:08 - INFO - __main__ - Step 61747: {'lr': 0.00032449345216908107, 'samples': 11855424, 'steps': 61746, 'loss/train': 0.45317405462265015} 08/31/2021 00:26:08 - INFO - __main__ - Step 61748: {'lr': 0.0003244883864718758, 'samples': 11855616, 'steps': 61747, 'loss/train': 0.32297828793525696} 08/31/2021 00:26:08 - INFO - __main__ - Step 61749: {'lr': 0.00032448332074110726, 'samples': 11855808, 'steps': 61748, 'loss/train': 1.4664949178695679} 08/31/2021 00:26:09 - INFO - __main__ - Step 61750: {'lr': 0.0003244782549767777, 'samples': 11856000, 'steps': 61749, 'loss/train': 0.8218688368797302} 08/31/2021 00:26:10 - INFO - __main__ - Step 61751: {'lr': 0.00032447318917888933, 'samples': 11856192, 'steps': 61750, 'loss/train': 1.5461678504943848} 08/31/2021 00:26:11 - INFO - __main__ - Step 61752: {'lr': 0.0003244681233474446, 'samples': 11856384, 'steps': 61751, 'loss/train': 1.0417486429214478} 08/31/2021 00:26:11 - INFO - __main__ - Step 61753: {'lr': 0.00032446305748244566, 'samples': 11856576, 'steps': 61752, 'loss/train': 1.2180107831954956} 08/31/2021 00:26:12 - INFO - __main__ - Step 61754: {'lr': 0.0003244579915838947, 'samples': 11856768, 'steps': 61753, 'loss/train': 1.0347816944122314} 08/31/2021 00:26:12 - INFO - __main__ - Step 61755: {'lr': 0.0003244529256517942, 'samples': 11856960, 'steps': 61754, 'loss/train': 1.4659639596939087} 08/31/2021 00:26:13 - INFO - __main__ - Step 61756: {'lr': 0.0003244478596861464, 'samples': 11857152, 'steps': 61755, 'loss/train': 2.2268893718719482} 08/31/2021 00:26:14 - INFO - __main__ - Step 61757: {'lr': 0.00032444279368695343, 'samples': 11857344, 'steps': 61756, 'loss/train': 0.8314436078071594} 08/31/2021 00:26:14 - INFO - __main__ - Step 61758: {'lr': 0.00032443772765421776, 'samples': 11857536, 'steps': 61757, 'loss/train': 1.1692105531692505} 08/31/2021 00:26:15 - INFO - __main__ - Step 61759: {'lr': 0.0003244326615879416, 'samples': 11857728, 'steps': 61758, 'loss/train': 1.128157615661621} 08/31/2021 00:26:15 - INFO - __main__ - Step 61760: {'lr': 0.0003244275954881273, 'samples': 11857920, 'steps': 61759, 'loss/train': 1.8145129680633545} 08/31/2021 00:26:15 - INFO - __main__ - Step 61761: {'lr': 0.00032442252935477696, 'samples': 11858112, 'steps': 61760, 'loss/train': 1.8003342151641846} 08/31/2021 00:26:17 - INFO - __main__ - Step 61762: {'lr': 0.000324417463187893, 'samples': 11858304, 'steps': 61761, 'loss/train': 1.3243412971496582} 08/31/2021 00:26:17 - INFO - __main__ - Step 61763: {'lr': 0.00032441239698747766, 'samples': 11858496, 'steps': 61762, 'loss/train': 1.1160547733306885} 08/31/2021 00:26:18 - INFO - __main__ - Step 61764: {'lr': 0.0003244073307535333, 'samples': 11858688, 'steps': 61763, 'loss/train': 1.5877680778503418} 08/31/2021 00:26:18 - INFO - __main__ - Step 61765: {'lr': 0.00032440226448606207, 'samples': 11858880, 'steps': 61764, 'loss/train': 1.2912209033966064} 08/31/2021 00:26:18 - INFO - __main__ - Step 61766: {'lr': 0.0003243971981850664, 'samples': 11859072, 'steps': 61765, 'loss/train': 1.0869743824005127} 08/31/2021 00:26:20 - INFO - __main__ - Step 61767: {'lr': 0.0003243921318505485, 'samples': 11859264, 'steps': 61766, 'loss/train': 0.9860609769821167} 08/31/2021 00:26:20 - INFO - __main__ - Step 61768: {'lr': 0.0003243870654825106, 'samples': 11859456, 'steps': 61767, 'loss/train': 1.4942890405654907} 08/31/2021 00:26:20 - INFO - __main__ - Step 61769: {'lr': 0.0003243819990809551, 'samples': 11859648, 'steps': 61768, 'loss/train': 1.5406317710876465} 08/31/2021 00:26:21 - INFO - __main__ - Step 61770: {'lr': 0.0003243769326458842, 'samples': 11859840, 'steps': 61769, 'loss/train': 0.7772985100746155} 08/31/2021 00:26:21 - INFO - __main__ - Step 61771: {'lr': 0.00032437186617730013, 'samples': 11860032, 'steps': 61770, 'loss/train': 1.2047470808029175} 08/31/2021 00:26:23 - INFO - __main__ - Step 61772: {'lr': 0.0003243667996752053, 'samples': 11860224, 'steps': 61771, 'loss/train': 1.3957327604293823} 08/31/2021 00:26:23 - INFO - __main__ - Step 61773: {'lr': 0.00032436173313960193, 'samples': 11860416, 'steps': 61772, 'loss/train': 1.8422348499298096} 08/31/2021 00:26:24 - INFO - __main__ - Step 61774: {'lr': 0.00032435666657049236, 'samples': 11860608, 'steps': 61773, 'loss/train': 1.6239207983016968} 08/31/2021 00:26:24 - INFO - __main__ - Step 61775: {'lr': 0.0003243515999678788, 'samples': 11860800, 'steps': 61774, 'loss/train': 1.2605873346328735} 08/31/2021 00:26:24 - INFO - __main__ - Step 61776: {'lr': 0.0003243465333317635, 'samples': 11860992, 'steps': 61775, 'loss/train': 1.3309577703475952} 08/31/2021 00:26:26 - INFO - __main__ - Step 61777: {'lr': 0.0003243414666621489, 'samples': 11861184, 'steps': 61776, 'loss/train': 1.5772809982299805} 08/31/2021 00:26:27 - INFO - __main__ - Step 61778: {'lr': 0.0003243363999590371, 'samples': 11861376, 'steps': 61777, 'loss/train': 1.310600757598877} 08/31/2021 00:26:27 - INFO - __main__ - Step 61779: {'lr': 0.00032433133322243047, 'samples': 11861568, 'steps': 61778, 'loss/train': 0.300110399723053} 08/31/2021 00:26:27 - INFO - __main__ - Step 61780: {'lr': 0.00032432626645233133, 'samples': 11861760, 'steps': 61779, 'loss/train': 0.2743918001651764} 08/31/2021 00:26:28 - INFO - __main__ - Step 61781: {'lr': 0.0003243211996487419, 'samples': 11861952, 'steps': 61780, 'loss/train': 1.460902452468872} 08/31/2021 00:26:28 - INFO - __main__ - Step 61782: {'lr': 0.00032431613281166445, 'samples': 11862144, 'steps': 61781, 'loss/train': 1.5838216543197632} 08/31/2021 00:26:30 - INFO - __main__ - Step 61783: {'lr': 0.0003243110659411013, 'samples': 11862336, 'steps': 61782, 'loss/train': 1.5826767683029175} 08/31/2021 00:26:30 - INFO - __main__ - Step 61784: {'lr': 0.0003243059990370548, 'samples': 11862528, 'steps': 61783, 'loss/train': 1.5861722230911255} 08/31/2021 00:26:31 - INFO - __main__ - Step 61785: {'lr': 0.0003243009320995271, 'samples': 11862720, 'steps': 61784, 'loss/train': 1.5824708938598633} 08/31/2021 00:26:31 - INFO - __main__ - Step 61786: {'lr': 0.0003242958651285206, 'samples': 11862912, 'steps': 61785, 'loss/train': 2.073467254638672} 08/31/2021 00:26:31 - INFO - __main__ - Step 61787: {'lr': 0.0003242907981240375, 'samples': 11863104, 'steps': 61786, 'loss/train': 1.8397575616836548} 08/31/2021 00:26:33 - INFO - __main__ - Step 61788: {'lr': 0.00032428573108608013, 'samples': 11863296, 'steps': 61787, 'loss/train': 1.0434529781341553} 08/31/2021 00:26:33 - INFO - __main__ - Step 61789: {'lr': 0.00032428066401465075, 'samples': 11863488, 'steps': 61788, 'loss/train': 1.0501391887664795} 08/31/2021 00:26:34 - INFO - __main__ - Step 61790: {'lr': 0.0003242755969097516, 'samples': 11863680, 'steps': 61789, 'loss/train': 1.1045458316802979} 08/31/2021 00:26:34 - INFO - __main__ - Step 61791: {'lr': 0.00032427052977138506, 'samples': 11863872, 'steps': 61790, 'loss/train': 1.1223586797714233} 08/31/2021 00:26:34 - INFO - __main__ - Step 61792: {'lr': 0.0003242654625995533, 'samples': 11864064, 'steps': 61791, 'loss/train': 1.35598886013031} 08/31/2021 00:26:35 - INFO - __main__ - Step 61793: {'lr': 0.0003242603953942587, 'samples': 11864256, 'steps': 61792, 'loss/train': 1.2135090827941895} 08/31/2021 00:26:37 - INFO - __main__ - Step 61794: {'lr': 0.0003242553281555036, 'samples': 11864448, 'steps': 61793, 'loss/train': 1.5103174448013306} 08/31/2021 00:26:37 - INFO - __main__ - Step 61795: {'lr': 0.0003242502608832901, 'samples': 11864640, 'steps': 61794, 'loss/train': 1.4616001844406128} 08/31/2021 00:26:38 - INFO - __main__ - Step 61796: {'lr': 0.0003242451935776206, 'samples': 11864832, 'steps': 61795, 'loss/train': 1.9884456396102905} 08/31/2021 00:26:38 - INFO - __main__ - Step 61797: {'lr': 0.0003242401262384974, 'samples': 11865024, 'steps': 61796, 'loss/train': 0.0785907730460167} 08/31/2021 00:26:38 - INFO - __main__ - Step 61798: {'lr': 0.0003242350588659227, 'samples': 11865216, 'steps': 61797, 'loss/train': 1.6737899780273438} 08/31/2021 00:26:40 - INFO - __main__ - Step 61799: {'lr': 0.00032422999145989887, 'samples': 11865408, 'steps': 61798, 'loss/train': 1.5266315937042236} 08/31/2021 00:26:40 - INFO - __main__ - Step 61800: {'lr': 0.0003242249240204281, 'samples': 11865600, 'steps': 61799, 'loss/train': 1.360296368598938} 08/31/2021 00:26:41 - INFO - __main__ - Step 61801: {'lr': 0.00032421985654751276, 'samples': 11865792, 'steps': 61800, 'loss/train': 1.1182353496551514} 08/31/2021 00:26:41 - INFO - __main__ - Step 61802: {'lr': 0.0003242147890411551, 'samples': 11865984, 'steps': 61801, 'loss/train': 1.5140279531478882} 08/31/2021 00:26:41 - INFO - __main__ - Step 61803: {'lr': 0.00032420972150135736, 'samples': 11866176, 'steps': 61802, 'loss/train': 1.5568301677703857} 08/31/2021 00:26:43 - INFO - __main__ - Step 61804: {'lr': 0.00032420465392812186, 'samples': 11866368, 'steps': 61803, 'loss/train': 1.5560259819030762} 08/31/2021 00:26:43 - INFO - __main__ - Step 61805: {'lr': 0.0003241995863214509, 'samples': 11866560, 'steps': 61804, 'loss/train': 1.358837604522705} 08/31/2021 00:26:44 - INFO - __main__ - Step 61806: {'lr': 0.00032419451868134677, 'samples': 11866752, 'steps': 61805, 'loss/train': 1.2595902681350708} 08/31/2021 00:26:44 - INFO - __main__ - Step 61807: {'lr': 0.0003241894510078118, 'samples': 11866944, 'steps': 61806, 'loss/train': 1.4026288986206055} 08/31/2021 00:26:44 - INFO - __main__ - Step 61808: {'lr': 0.0003241843833008481, 'samples': 11867136, 'steps': 61807, 'loss/train': 1.5253815650939941} 08/31/2021 00:26:46 - INFO - __main__ - Step 61809: {'lr': 0.0003241793155604581, 'samples': 11867328, 'steps': 61808, 'loss/train': 1.0532941818237305} 08/31/2021 00:26:46 - INFO - __main__ - Step 61810: {'lr': 0.00032417424778664406, 'samples': 11867520, 'steps': 61809, 'loss/train': 1.5637239217758179} 08/31/2021 00:26:46 - INFO - __main__ - Step 61811: {'lr': 0.00032416917997940824, 'samples': 11867712, 'steps': 61810, 'loss/train': 1.4023340940475464} 08/31/2021 00:26:47 - INFO - __main__ - Step 61812: {'lr': 0.0003241641121387529, 'samples': 11867904, 'steps': 61811, 'loss/train': 1.2021195888519287} 08/31/2021 00:26:47 - INFO - __main__ - Step 61813: {'lr': 0.0003241590442646804, 'samples': 11868096, 'steps': 61812, 'loss/train': 2.1751348972320557} 08/31/2021 00:26:49 - INFO - __main__ - Step 61814: {'lr': 0.000324153976357193, 'samples': 11868288, 'steps': 61813, 'loss/train': 1.1596958637237549} 08/31/2021 00:26:49 - INFO - __main__ - Step 61815: {'lr': 0.0003241489084162929, 'samples': 11868480, 'steps': 61814, 'loss/train': 1.6136140823364258} 08/31/2021 00:26:49 - INFO - __main__ - Step 61816: {'lr': 0.0003241438404419825, 'samples': 11868672, 'steps': 61815, 'loss/train': 2.0195484161376953} 08/31/2021 00:26:50 - INFO - __main__ - Step 61817: {'lr': 0.000324138772434264, 'samples': 11868864, 'steps': 61816, 'loss/train': 1.1753790378570557} 08/31/2021 00:26:50 - INFO - __main__ - Step 61818: {'lr': 0.00032413370439313973, 'samples': 11869056, 'steps': 61817, 'loss/train': 1.2050665616989136} 08/31/2021 00:26:52 - INFO - __main__ - Step 61819: {'lr': 0.00032412863631861187, 'samples': 11869248, 'steps': 61818, 'loss/train': 1.3778958320617676} 08/31/2021 00:26:52 - INFO - __main__ - Step 61820: {'lr': 0.0003241235682106829, 'samples': 11869440, 'steps': 61819, 'loss/train': 1.375396490097046} 08/31/2021 00:26:52 - INFO - __main__ - Step 61821: {'lr': 0.000324118500069355, 'samples': 11869632, 'steps': 61820, 'loss/train': 1.2171167135238647} 08/31/2021 00:26:53 - INFO - __main__ - Step 61822: {'lr': 0.00032411343189463036, 'samples': 11869824, 'steps': 61821, 'loss/train': 1.5142568349838257} 08/31/2021 00:26:53 - INFO - __main__ - Step 61823: {'lr': 0.00032410836368651144, 'samples': 11870016, 'steps': 61822, 'loss/train': 1.7272295951843262} 08/31/2021 00:26:55 - INFO - __main__ - Step 61824: {'lr': 0.00032410329544500034, 'samples': 11870208, 'steps': 61823, 'loss/train': 1.5031906366348267} 08/31/2021 00:26:55 - INFO - __main__ - Step 61825: {'lr': 0.0003240982271700995, 'samples': 11870400, 'steps': 61824, 'loss/train': 1.2842304706573486} 08/31/2021 00:26:55 - INFO - __main__ - Step 61826: {'lr': 0.00032409315886181115, 'samples': 11870592, 'steps': 61825, 'loss/train': 0.768780529499054} 08/31/2021 00:26:56 - INFO - __main__ - Step 61827: {'lr': 0.00032408809052013755, 'samples': 11870784, 'steps': 61826, 'loss/train': 1.104913592338562} 08/31/2021 00:26:56 - INFO - __main__ - Step 61828: {'lr': 0.000324083022145081, 'samples': 11870976, 'steps': 61827, 'loss/train': 0.1678829789161682} 08/31/2021 00:26:56 - INFO - __main__ - Step 61829: {'lr': 0.0003240779537366438, 'samples': 11871168, 'steps': 61828, 'loss/train': 1.2148476839065552} 08/31/2021 00:26:58 - INFO - __main__ - Step 61830: {'lr': 0.0003240728852948281, 'samples': 11871360, 'steps': 61829, 'loss/train': 3.738508701324463} 08/31/2021 00:26:58 - INFO - __main__ - Step 61831: {'lr': 0.0003240678168196365, 'samples': 11871552, 'steps': 61830, 'loss/train': 1.448274850845337} 08/31/2021 00:26:59 - INFO - __main__ - Step 61832: {'lr': 0.00032406274831107095, 'samples': 11871744, 'steps': 61831, 'loss/train': 1.7673752307891846} 08/31/2021 00:26:59 - INFO - __main__ - Step 61833: {'lr': 0.0003240576797691339, 'samples': 11871936, 'steps': 61832, 'loss/train': 1.0718644857406616} 08/31/2021 00:26:59 - INFO - __main__ - Step 61834: {'lr': 0.0003240526111938276, 'samples': 11872128, 'steps': 61833, 'loss/train': 1.0848267078399658} 08/31/2021 00:27:01 - INFO - __main__ - Step 61835: {'lr': 0.0003240475425851543, 'samples': 11872320, 'steps': 61834, 'loss/train': 1.147347331047058} 08/31/2021 00:27:01 - INFO - __main__ - Step 61836: {'lr': 0.00032404247394311644, 'samples': 11872512, 'steps': 61835, 'loss/train': 1.2893966436386108} 08/31/2021 00:27:02 - INFO - __main__ - Step 61837: {'lr': 0.0003240374052677161, 'samples': 11872704, 'steps': 61836, 'loss/train': 1.3828238248825073} 08/31/2021 00:27:02 - INFO - __main__ - Step 61838: {'lr': 0.0003240323365589556, 'samples': 11872896, 'steps': 61837, 'loss/train': 0.973318338394165} 08/31/2021 00:27:02 - INFO - __main__ - Step 61839: {'lr': 0.00032402726781683734, 'samples': 11873088, 'steps': 61838, 'loss/train': 1.2865686416625977} 08/31/2021 00:27:04 - INFO - __main__ - Step 61840: {'lr': 0.0003240221990413635, 'samples': 11873280, 'steps': 61839, 'loss/train': 0.3606998026371002} 08/31/2021 00:27:04 - INFO - __main__ - Step 61841: {'lr': 0.0003240171302325364, 'samples': 11873472, 'steps': 61840, 'loss/train': 1.0549955368041992} 08/31/2021 00:27:05 - INFO - __main__ - Step 61842: {'lr': 0.0003240120613903584, 'samples': 11873664, 'steps': 61841, 'loss/train': 1.366371750831604} 08/31/2021 00:27:05 - INFO - __main__ - Step 61843: {'lr': 0.0003240069925148316, 'samples': 11873856, 'steps': 61842, 'loss/train': 1.5965888500213623} 08/31/2021 00:27:05 - INFO - __main__ - Step 61844: {'lr': 0.0003240019236059585, 'samples': 11874048, 'steps': 61843, 'loss/train': 1.5522422790527344} 08/31/2021 00:27:07 - INFO - __main__ - Step 61845: {'lr': 0.0003239968546637412, 'samples': 11874240, 'steps': 61844, 'loss/train': 1.2759246826171875} 08/31/2021 00:27:08 - INFO - __main__ - Step 61846: {'lr': 0.00032399178568818203, 'samples': 11874432, 'steps': 61845, 'loss/train': 1.2321768999099731} 08/31/2021 00:27:09 - INFO - __main__ - Step 61847: {'lr': 0.00032398671667928337, 'samples': 11874624, 'steps': 61846, 'loss/train': 1.6666526794433594} 08/31/2021 00:27:09 - INFO - __main__ - Step 61848: {'lr': 0.0003239816476370474, 'samples': 11874816, 'steps': 61847, 'loss/train': 1.3511021137237549} 08/31/2021 00:27:09 - INFO - __main__ - Step 61849: {'lr': 0.0003239765785614765, 'samples': 11875008, 'steps': 61848, 'loss/train': 1.6540908813476562} 08/31/2021 00:27:11 - INFO - __main__ - Step 61850: {'lr': 0.0003239715094525728, 'samples': 11875200, 'steps': 61849, 'loss/train': 1.3980361223220825} 08/31/2021 00:27:11 - INFO - __main__ - Step 61851: {'lr': 0.0003239664403103387, 'samples': 11875392, 'steps': 61850, 'loss/train': 1.079322099685669} 08/31/2021 00:27:12 - INFO - __main__ - Step 61852: {'lr': 0.0003239613711347766, 'samples': 11875584, 'steps': 61851, 'loss/train': 1.3408278226852417} 08/31/2021 00:27:12 - INFO - __main__ - Step 61853: {'lr': 0.00032395630192588856, 'samples': 11875776, 'steps': 61852, 'loss/train': 2.1200897693634033} 08/31/2021 00:27:12 - INFO - __main__ - Step 61854: {'lr': 0.00032395123268367685, 'samples': 11875968, 'steps': 61853, 'loss/train': 1.5994396209716797} 08/31/2021 00:27:14 - INFO - __main__ - Step 61855: {'lr': 0.000323946163408144, 'samples': 11876160, 'steps': 61854, 'loss/train': 1.2375305891036987} 08/31/2021 00:27:14 - INFO - __main__ - Step 61856: {'lr': 0.00032394109409929206, 'samples': 11876352, 'steps': 61855, 'loss/train': 1.4735348224639893} 08/31/2021 00:27:15 - INFO - __main__ - Step 61857: {'lr': 0.0003239360247571234, 'samples': 11876544, 'steps': 61856, 'loss/train': 0.6805081367492676} 08/31/2021 00:27:15 - INFO - __main__ - Step 61858: {'lr': 0.0003239309553816404, 'samples': 11876736, 'steps': 61857, 'loss/train': 1.231063723564148} 08/31/2021 00:27:15 - INFO - __main__ - Step 61859: {'lr': 0.0003239258859728452, 'samples': 11876928, 'steps': 61858, 'loss/train': 1.6579378843307495} 08/31/2021 00:27:17 - INFO - __main__ - Step 61860: {'lr': 0.0003239208165307401, 'samples': 11877120, 'steps': 61859, 'loss/train': 1.4571477174758911} 08/31/2021 00:27:18 - INFO - __main__ - Step 61861: {'lr': 0.00032391574705532746, 'samples': 11877312, 'steps': 61860, 'loss/train': 1.6594268083572388} 08/31/2021 00:27:18 - INFO - __main__ - Step 61862: {'lr': 0.0003239106775466095, 'samples': 11877504, 'steps': 61861, 'loss/train': 0.0815814733505249} 08/31/2021 00:27:18 - INFO - __main__ - Step 61863: {'lr': 0.00032390560800458855, 'samples': 11877696, 'steps': 61862, 'loss/train': 1.7084590196609497} 08/31/2021 00:27:19 - INFO - __main__ - Step 61864: {'lr': 0.00032390053842926684, 'samples': 11877888, 'steps': 61863, 'loss/train': 1.331950306892395} 08/31/2021 00:27:19 - INFO - __main__ - Step 61865: {'lr': 0.00032389546882064673, 'samples': 11878080, 'steps': 61864, 'loss/train': 1.2178192138671875} 08/31/2021 00:27:20 - INFO - __main__ - Step 61866: {'lr': 0.0003238903991787304, 'samples': 11878272, 'steps': 61865, 'loss/train': 0.7030106782913208} 08/31/2021 00:27:21 - INFO - __main__ - Step 61867: {'lr': 0.0003238853295035203, 'samples': 11878464, 'steps': 61866, 'loss/train': 1.2215286493301392} 08/31/2021 00:27:21 - INFO - __main__ - Step 61868: {'lr': 0.0003238802597950186, 'samples': 11878656, 'steps': 61867, 'loss/train': 1.2187975645065308} 08/31/2021 00:27:22 - INFO - __main__ - Step 61869: {'lr': 0.0003238751900532275, 'samples': 11878848, 'steps': 61868, 'loss/train': 1.3562283515930176} 08/31/2021 00:27:22 - INFO - __main__ - Step 61870: {'lr': 0.00032387012027814945, 'samples': 11879040, 'steps': 61869, 'loss/train': 0.9702643752098083} 08/31/2021 00:27:24 - INFO - __main__ - Step 61871: {'lr': 0.00032386505046978667, 'samples': 11879232, 'steps': 61870, 'loss/train': 1.1529492139816284} 08/31/2021 00:27:24 - INFO - __main__ - Step 61872: {'lr': 0.00032385998062814137, 'samples': 11879424, 'steps': 61871, 'loss/train': 0.43910929560661316} 08/31/2021 00:27:24 - INFO - __main__ - Step 61873: {'lr': 0.00032385491075321595, 'samples': 11879616, 'steps': 61872, 'loss/train': 1.1602637767791748} 08/31/2021 00:27:25 - INFO - __main__ - Step 61874: {'lr': 0.00032384984084501267, 'samples': 11879808, 'steps': 61873, 'loss/train': 1.3645265102386475} 08/31/2021 00:27:25 - INFO - __main__ - Step 61875: {'lr': 0.00032384477090353377, 'samples': 11880000, 'steps': 61874, 'loss/train': 0.05973939225077629} 08/31/2021 00:27:27 - INFO - __main__ - Step 61876: {'lr': 0.0003238397009287815, 'samples': 11880192, 'steps': 61875, 'loss/train': 1.1755825281143188} 08/31/2021 00:27:27 - INFO - __main__ - Step 61877: {'lr': 0.00032383463092075824, 'samples': 11880384, 'steps': 61876, 'loss/train': 0.9211164712905884} 08/31/2021 00:27:28 - INFO - __main__ - Step 61878: {'lr': 0.0003238295608794662, 'samples': 11880576, 'steps': 61877, 'loss/train': 1.1074765920639038} 08/31/2021 00:27:28 - INFO - __main__ - Step 61879: {'lr': 0.0003238244908049078, 'samples': 11880768, 'steps': 61878, 'loss/train': 1.620261311531067} 08/31/2021 00:27:28 - INFO - __main__ - Step 61880: {'lr': 0.0003238194206970851, 'samples': 11880960, 'steps': 61879, 'loss/train': 1.5727553367614746} 08/31/2021 00:27:30 - INFO - __main__ - Step 61881: {'lr': 0.0003238143505560007, 'samples': 11881152, 'steps': 61880, 'loss/train': 0.19050878286361694} 08/31/2021 00:27:30 - INFO - __main__ - Step 61882: {'lr': 0.0003238092803816565, 'samples': 11881344, 'steps': 61881, 'loss/train': 0.8797162175178528} 08/31/2021 00:27:31 - INFO - __main__ - Step 61883: {'lr': 0.00032380421017405504, 'samples': 11881536, 'steps': 61882, 'loss/train': 1.354994297027588} 08/31/2021 00:27:31 - INFO - __main__ - Step 61884: {'lr': 0.00032379913993319854, 'samples': 11881728, 'steps': 61883, 'loss/train': 0.977351188659668} 08/31/2021 00:27:31 - INFO - __main__ - Step 61885: {'lr': 0.0003237940696590893, 'samples': 11881920, 'steps': 61884, 'loss/train': 0.7308764457702637} 08/31/2021 00:27:33 - INFO - __main__ - Step 61886: {'lr': 0.00032378899935172955, 'samples': 11882112, 'steps': 61885, 'loss/train': 2.417555809020996} 08/31/2021 00:27:34 - INFO - __main__ - Step 61887: {'lr': 0.0003237839290111216, 'samples': 11882304, 'steps': 61886, 'loss/train': 1.150500774383545} 08/31/2021 00:27:34 - INFO - __main__ - Step 61888: {'lr': 0.0003237788586372679, 'samples': 11882496, 'steps': 61887, 'loss/train': 0.7841753363609314} 08/31/2021 00:27:34 - INFO - __main__ - Step 61889: {'lr': 0.00032377378823017044, 'samples': 11882688, 'steps': 61888, 'loss/train': 0.8208878636360168} 08/31/2021 00:27:35 - INFO - __main__ - Step 61890: {'lr': 0.0003237687177898317, 'samples': 11882880, 'steps': 61889, 'loss/train': 1.100653886795044} 08/31/2021 00:27:35 - INFO - __main__ - Step 61891: {'lr': 0.0003237636473162539, 'samples': 11883072, 'steps': 61890, 'loss/train': 0.05412857234477997} 08/31/2021 00:27:37 - INFO - __main__ - Step 61892: {'lr': 0.0003237585768094393, 'samples': 11883264, 'steps': 61891, 'loss/train': 0.2609153389930725} 08/31/2021 00:27:37 - INFO - __main__ - Step 61893: {'lr': 0.00032375350626939026, 'samples': 11883456, 'steps': 61892, 'loss/train': 1.4252562522888184} 08/31/2021 00:27:38 - INFO - __main__ - Step 61894: {'lr': 0.0003237484356961091, 'samples': 11883648, 'steps': 61893, 'loss/train': 1.1087359189987183} 08/31/2021 00:27:38 - INFO - __main__ - Step 61895: {'lr': 0.00032374336508959796, 'samples': 11883840, 'steps': 61894, 'loss/train': 0.07503261417150497} 08/31/2021 00:27:39 - INFO - __main__ - Step 61896: {'lr': 0.0003237382944498592, 'samples': 11884032, 'steps': 61895, 'loss/train': 1.0311472415924072} 08/31/2021 00:27:39 - INFO - __main__ - Step 61897: {'lr': 0.0003237332237768951, 'samples': 11884224, 'steps': 61896, 'loss/train': 1.6732323169708252} 08/31/2021 00:27:41 - INFO - __main__ - Step 61898: {'lr': 0.000323728153070708, 'samples': 11884416, 'steps': 61897, 'loss/train': 1.4148602485656738} 08/31/2021 00:27:42 - INFO - __main__ - Step 61899: {'lr': 0.0003237230823313, 'samples': 11884608, 'steps': 61898, 'loss/train': 1.8403747081756592} 08/31/2021 00:27:42 - INFO - __main__ - Step 61900: {'lr': 0.00032371801155867363, 'samples': 11884800, 'steps': 61899, 'loss/train': 1.2154850959777832} 08/31/2021 00:27:42 - INFO - __main__ - Step 61901: {'lr': 0.0003237129407528311, 'samples': 11884992, 'steps': 61900, 'loss/train': 1.1585829257965088} 08/31/2021 00:27:43 - INFO - __main__ - Step 61902: {'lr': 0.00032370786991377454, 'samples': 11885184, 'steps': 61901, 'loss/train': 1.7520875930786133} 08/31/2021 00:27:44 - INFO - __main__ - Step 61903: {'lr': 0.0003237027990415064, 'samples': 11885376, 'steps': 61902, 'loss/train': 1.6035808324813843} 08/31/2021 00:27:44 - INFO - __main__ - Step 61904: {'lr': 0.0003236977281360289, 'samples': 11885568, 'steps': 61903, 'loss/train': 1.8928123712539673} 08/31/2021 00:27:45 - INFO - __main__ - Step 61905: {'lr': 0.0003236926571973444, 'samples': 11885760, 'steps': 61904, 'loss/train': 1.9558082818984985} 08/31/2021 00:27:45 - INFO - __main__ - Step 61906: {'lr': 0.000323687586225455, 'samples': 11885952, 'steps': 61905, 'loss/train': 1.2910594940185547} 08/31/2021 00:27:45 - INFO - __main__ - Step 61907: {'lr': 0.0003236825152203632, 'samples': 11886144, 'steps': 61906, 'loss/train': 1.3816477060317993} 08/31/2021 00:27:47 - INFO - __main__ - Step 61908: {'lr': 0.0003236774441820713, 'samples': 11886336, 'steps': 61907, 'loss/train': 1.600801706314087} 08/31/2021 00:27:47 - INFO - __main__ - Step 61909: {'lr': 0.00032367237311058133, 'samples': 11886528, 'steps': 61908, 'loss/train': 1.020050048828125} 08/31/2021 00:27:48 - INFO - __main__ - Step 61910: {'lr': 0.0003236673020058958, 'samples': 11886720, 'steps': 61909, 'loss/train': 1.7938153743743896} 08/31/2021 00:27:48 - INFO - __main__ - Step 61911: {'lr': 0.0003236622308680168, 'samples': 11886912, 'steps': 61910, 'loss/train': 1.005918025970459} 08/31/2021 00:27:48 - INFO - __main__ - Step 61912: {'lr': 0.0003236571596969469, 'samples': 11887104, 'steps': 61911, 'loss/train': 1.6285700798034668} 08/31/2021 00:27:50 - INFO - __main__ - Step 61913: {'lr': 0.0003236520884926881, 'samples': 11887296, 'steps': 61912, 'loss/train': 1.193048357963562} 08/31/2021 00:27:51 - INFO - __main__ - Step 61914: {'lr': 0.00032364701725524285, 'samples': 11887488, 'steps': 61913, 'loss/train': 1.646818995475769} 08/31/2021 00:27:51 - INFO - __main__ - Step 61915: {'lr': 0.00032364194598461345, 'samples': 11887680, 'steps': 61914, 'loss/train': 1.5947703123092651} 08/31/2021 00:27:52 - INFO - __main__ - Step 61916: {'lr': 0.00032363687468080205, 'samples': 11887872, 'steps': 61915, 'loss/train': 0.8964608907699585} 08/31/2021 00:27:52 - INFO - __main__ - Step 61917: {'lr': 0.000323631803343811, 'samples': 11888064, 'steps': 61916, 'loss/train': 1.3514294624328613} 08/31/2021 00:27:53 - INFO - __main__ - Step 61918: {'lr': 0.0003236267319736426, 'samples': 11888256, 'steps': 61917, 'loss/train': 0.11480039358139038} 08/31/2021 00:27:54 - INFO - __main__ - Step 61919: {'lr': 0.00032362166057029915, 'samples': 11888448, 'steps': 61918, 'loss/train': 1.8158414363861084} 08/31/2021 00:27:54 - INFO - __main__ - Step 61920: {'lr': 0.0003236165891337829, 'samples': 11888640, 'steps': 61919, 'loss/train': 1.503604769706726} 08/31/2021 00:27:55 - INFO - __main__ - Step 61921: {'lr': 0.00032361151766409623, 'samples': 11888832, 'steps': 61920, 'loss/train': 1.3554543256759644} 08/31/2021 00:27:55 - INFO - __main__ - Step 61922: {'lr': 0.0003236064461612413, 'samples': 11889024, 'steps': 61921, 'loss/train': 1.7969409227371216} 08/31/2021 00:27:55 - INFO - __main__ - Step 61923: {'lr': 0.00032360137462522046, 'samples': 11889216, 'steps': 61922, 'loss/train': 1.0620641708374023} 08/31/2021 00:27:57 - INFO - __main__ - Step 61924: {'lr': 0.0003235963030560359, 'samples': 11889408, 'steps': 61923, 'loss/train': 1.6128774881362915} 08/31/2021 00:27:58 - INFO - __main__ - Step 61925: {'lr': 0.00032359123145369, 'samples': 11889600, 'steps': 61924, 'loss/train': 1.2138316631317139} 08/31/2021 00:27:58 - INFO - __main__ - Step 61926: {'lr': 0.00032358615981818505, 'samples': 11889792, 'steps': 61925, 'loss/train': 1.3721897602081299} 08/31/2021 00:27:58 - INFO - __main__ - Step 61927: {'lr': 0.0003235810881495233, 'samples': 11889984, 'steps': 61926, 'loss/train': 1.4215227365493774} 08/31/2021 00:27:59 - INFO - __main__ - Step 61928: {'lr': 0.00032357601644770714, 'samples': 11890176, 'steps': 61927, 'loss/train': 0.1013554185628891} 08/31/2021 00:28:00 - INFO - __main__ - Step 61929: {'lr': 0.0003235709447127386, 'samples': 11890368, 'steps': 61928, 'loss/train': 1.9199272394180298} 08/31/2021 00:28:01 - INFO - __main__ - Step 61930: {'lr': 0.00032356587294462023, 'samples': 11890560, 'steps': 61929, 'loss/train': 1.2082939147949219} 08/31/2021 00:28:01 - INFO - __main__ - Step 61931: {'lr': 0.00032356080114335416, 'samples': 11890752, 'steps': 61930, 'loss/train': 1.4354299306869507} 08/31/2021 00:28:01 - INFO - __main__ - Step 61932: {'lr': 0.0003235557293089428, 'samples': 11890944, 'steps': 61931, 'loss/train': 1.1029071807861328} 08/31/2021 00:28:02 - INFO - __main__ - Step 61933: {'lr': 0.00032355065744138836, 'samples': 11891136, 'steps': 61932, 'loss/train': 0.06955356150865555} 08/31/2021 00:28:03 - INFO - __main__ - Step 61934: {'lr': 0.00032354558554069303, 'samples': 11891328, 'steps': 61933, 'loss/train': 1.4311988353729248} 08/31/2021 00:28:04 - INFO - __main__ - Step 61935: {'lr': 0.00032354051360685934, 'samples': 11891520, 'steps': 61934, 'loss/train': 1.7651145458221436} 08/31/2021 00:28:04 - INFO - __main__ - Step 61936: {'lr': 0.0003235354416398893, 'samples': 11891712, 'steps': 61935, 'loss/train': 1.382755994796753} 08/31/2021 00:28:04 - INFO - __main__ - Step 61937: {'lr': 0.0003235303696397854, 'samples': 11891904, 'steps': 61936, 'loss/train': 1.593224048614502} 08/31/2021 00:28:05 - INFO - __main__ - Step 61938: {'lr': 0.0003235252976065498, 'samples': 11892096, 'steps': 61937, 'loss/train': 1.642390489578247} 08/31/2021 00:28:06 - INFO - __main__ - Step 61939: {'lr': 0.00032352022554018483, 'samples': 11892288, 'steps': 61938, 'loss/train': 1.2347290515899658} 08/31/2021 00:28:07 - INFO - __main__ - Step 61940: {'lr': 0.00032351515344069285, 'samples': 11892480, 'steps': 61939, 'loss/train': 0.9886916279792786} 08/31/2021 00:28:07 - INFO - __main__ - Step 61941: {'lr': 0.000323510081308076, 'samples': 11892672, 'steps': 61940, 'loss/train': 0.8102436065673828} 08/31/2021 00:28:07 - INFO - __main__ - Step 61942: {'lr': 0.0003235050091423367, 'samples': 11892864, 'steps': 61941, 'loss/train': 1.3957579135894775} 08/31/2021 00:28:08 - INFO - __main__ - Step 61943: {'lr': 0.0003234999369434771, 'samples': 11893056, 'steps': 61942, 'loss/train': 0.7226584553718567} 08/31/2021 00:28:09 - INFO - __main__ - Step 61944: {'lr': 0.00032349486471149963, 'samples': 11893248, 'steps': 61943, 'loss/train': 1.6994242668151855} 08/31/2021 00:28:10 - INFO - __main__ - Step 61945: {'lr': 0.0003234897924464065, 'samples': 11893440, 'steps': 61944, 'loss/train': 1.4048821926116943} 08/31/2021 00:28:10 - INFO - __main__ - Step 61946: {'lr': 0.00032348472014819994, 'samples': 11893632, 'steps': 61945, 'loss/train': 1.455976128578186} 08/31/2021 00:28:10 - INFO - __main__ - Step 61947: {'lr': 0.0003234796478168824, 'samples': 11893824, 'steps': 61946, 'loss/train': 1.450798511505127} 08/31/2021 00:28:11 - INFO - __main__ - Step 61948: {'lr': 0.00032347457545245606, 'samples': 11894016, 'steps': 61947, 'loss/train': 0.14934737980365753} 08/31/2021 00:28:11 - INFO - __main__ - Step 61949: {'lr': 0.0003234695030549232, 'samples': 11894208, 'steps': 61948, 'loss/train': 0.8729341626167297} 08/31/2021 00:28:13 - INFO - __main__ - Step 61950: {'lr': 0.00032346443062428605, 'samples': 11894400, 'steps': 61949, 'loss/train': 0.7009657621383667} 08/31/2021 00:28:13 - INFO - __main__ - Step 61951: {'lr': 0.000323459358160547, 'samples': 11894592, 'steps': 61950, 'loss/train': 1.662534475326538} 08/31/2021 00:28:13 - INFO - __main__ - Step 61952: {'lr': 0.0003234542856637083, 'samples': 11894784, 'steps': 61951, 'loss/train': 1.3344610929489136} 08/31/2021 00:28:14 - INFO - __main__ - Step 61953: {'lr': 0.0003234492131337722, 'samples': 11894976, 'steps': 61952, 'loss/train': 1.3348758220672607} 08/31/2021 00:28:14 - INFO - __main__ - Step 61954: {'lr': 0.000323444140570741, 'samples': 11895168, 'steps': 61953, 'loss/train': 1.1941618919372559} 08/31/2021 00:28:16 - INFO - __main__ - Step 61955: {'lr': 0.00032343906797461716, 'samples': 11895360, 'steps': 61954, 'loss/train': 1.2108455896377563} 08/31/2021 00:28:17 - INFO - __main__ - Step 61956: {'lr': 0.00032343399534540265, 'samples': 11895552, 'steps': 61955, 'loss/train': 0.9750126004219055} 08/31/2021 00:28:17 - INFO - __main__ - Step 61957: {'lr': 0.00032342892268309996, 'samples': 11895744, 'steps': 61956, 'loss/train': 1.5191537141799927} 08/31/2021 00:28:18 - INFO - __main__ - Step 61958: {'lr': 0.00032342384998771133, 'samples': 11895936, 'steps': 61957, 'loss/train': 1.4126828908920288} 08/31/2021 00:28:18 - INFO - __main__ - Step 61959: {'lr': 0.000323418777259239, 'samples': 11896128, 'steps': 61958, 'loss/train': 0.7146937251091003} 08/31/2021 00:28:19 - INFO - __main__ - Step 61960: {'lr': 0.0003234137044976854, 'samples': 11896320, 'steps': 61959, 'loss/train': 1.4789469242095947} 08/31/2021 00:28:20 - INFO - __main__ - Step 61961: {'lr': 0.0003234086317030526, 'samples': 11896512, 'steps': 61960, 'loss/train': 1.2842680215835571} 08/31/2021 00:28:20 - INFO - __main__ - Step 61962: {'lr': 0.00032340355887534313, 'samples': 11896704, 'steps': 61961, 'loss/train': 1.4884533882141113} 08/31/2021 00:28:21 - INFO - __main__ - Step 61963: {'lr': 0.00032339848601455913, 'samples': 11896896, 'steps': 61962, 'loss/train': 1.4382739067077637} 08/31/2021 00:28:21 - INFO - __main__ - Step 61964: {'lr': 0.0003233934131207028, 'samples': 11897088, 'steps': 61963, 'loss/train': 1.0822412967681885} 08/31/2021 00:28:22 - INFO - __main__ - Step 61965: {'lr': 0.0003233883401937766, 'samples': 11897280, 'steps': 61964, 'loss/train': 0.05824177712202072} 08/31/2021 00:28:23 - INFO - __main__ - Step 61966: {'lr': 0.00032338326723378274, 'samples': 11897472, 'steps': 61965, 'loss/train': 1.5620145797729492} 08/31/2021 00:28:23 - INFO - __main__ - Step 61967: {'lr': 0.00032337819424072353, 'samples': 11897664, 'steps': 61966, 'loss/train': 1.4519472122192383} 08/31/2021 00:28:24 - INFO - __main__ - Step 61968: {'lr': 0.00032337312121460125, 'samples': 11897856, 'steps': 61967, 'loss/train': 1.4982157945632935} 08/31/2021 00:28:24 - INFO - __main__ - Step 61969: {'lr': 0.00032336804815541817, 'samples': 11898048, 'steps': 61968, 'loss/train': 1.5004189014434814} 08/31/2021 00:28:26 - INFO - __main__ - Step 61970: {'lr': 0.0003233629750631765, 'samples': 11898240, 'steps': 61969, 'loss/train': 1.0272243022918701} 08/31/2021 00:28:26 - INFO - __main__ - Step 61971: {'lr': 0.0003233579019378787, 'samples': 11898432, 'steps': 61970, 'loss/train': 1.7215603590011597} 08/31/2021 00:28:26 - INFO - __main__ - Step 61972: {'lr': 0.0003233528287795269, 'samples': 11898624, 'steps': 61971, 'loss/train': 1.3422313928604126} 08/31/2021 00:28:27 - INFO - __main__ - Step 61973: {'lr': 0.00032334775558812346, 'samples': 11898816, 'steps': 61972, 'loss/train': 1.0418425798416138} 08/31/2021 00:28:27 - INFO - __main__ - Step 61974: {'lr': 0.0003233426823636706, 'samples': 11899008, 'steps': 61973, 'loss/train': 1.3128032684326172} 08/31/2021 00:28:29 - INFO - __main__ - Step 61975: {'lr': 0.0003233376091061708, 'samples': 11899200, 'steps': 61974, 'loss/train': 0.6724111437797546} 08/31/2021 00:28:29 - INFO - __main__ - Step 61976: {'lr': 0.00032333253581562615, 'samples': 11899392, 'steps': 61975, 'loss/train': 1.4781886339187622} 08/31/2021 00:28:29 - INFO - __main__ - Step 61977: {'lr': 0.0003233274624920389, 'samples': 11899584, 'steps': 61976, 'loss/train': 0.877514123916626} 08/31/2021 00:28:30 - INFO - __main__ - Step 61978: {'lr': 0.0003233223891354116, 'samples': 11899776, 'steps': 61977, 'loss/train': 1.3515714406967163} 08/31/2021 00:28:30 - INFO - __main__ - Step 61979: {'lr': 0.00032331731574574617, 'samples': 11899968, 'steps': 61978, 'loss/train': 1.0311676263809204} 08/31/2021 00:28:32 - INFO - __main__ - Step 61980: {'lr': 0.00032331224232304517, 'samples': 11900160, 'steps': 61979, 'loss/train': 1.7601743936538696} 08/31/2021 00:28:32 - INFO - __main__ - Step 61981: {'lr': 0.00032330716886731087, 'samples': 11900352, 'steps': 61980, 'loss/train': 0.9581984281539917} 08/31/2021 00:28:33 - INFO - __main__ - Step 61982: {'lr': 0.0003233020953785454, 'samples': 11900544, 'steps': 61981, 'loss/train': 1.957992672920227} 08/31/2021 00:28:33 - INFO - __main__ - Step 61983: {'lr': 0.00032329702185675117, 'samples': 11900736, 'steps': 61982, 'loss/train': 0.3073367774486542} 08/31/2021 00:28:33 - INFO - __main__ - Step 61984: {'lr': 0.00032329194830193044, 'samples': 11900928, 'steps': 61983, 'loss/train': 0.1045897826552391} 08/31/2021 00:28:34 - INFO - __main__ - Step 61985: {'lr': 0.00032328687471408545, 'samples': 11901120, 'steps': 61984, 'loss/train': 1.3060327768325806} 08/31/2021 00:28:35 - INFO - __main__ - Step 61986: {'lr': 0.0003232818010932186, 'samples': 11901312, 'steps': 61985, 'loss/train': 1.809540867805481} 08/31/2021 00:28:36 - INFO - __main__ - Step 61987: {'lr': 0.0003232767274393321, 'samples': 11901504, 'steps': 61986, 'loss/train': 1.0905022621154785} 08/31/2021 00:28:36 - INFO - __main__ - Step 61988: {'lr': 0.0003232716537524282, 'samples': 11901696, 'steps': 61987, 'loss/train': 1.915473222732544} 08/31/2021 00:28:36 - INFO - __main__ - Step 61989: {'lr': 0.00032326658003250917, 'samples': 11901888, 'steps': 61988, 'loss/train': 1.6565803289413452} 08/31/2021 00:28:37 - INFO - __main__ - Step 61990: {'lr': 0.0003232615062795774, 'samples': 11902080, 'steps': 61989, 'loss/train': 1.061877727508545} 08/31/2021 00:28:38 - INFO - __main__ - Step 61991: {'lr': 0.0003232564324936351, 'samples': 11902272, 'steps': 61990, 'loss/train': 0.7578836679458618} 08/31/2021 00:28:39 - INFO - __main__ - Step 61992: {'lr': 0.0003232513586746847, 'samples': 11902464, 'steps': 61991, 'loss/train': 1.8407105207443237} 08/31/2021 00:28:39 - INFO - __main__ - Step 61993: {'lr': 0.00032324628482272824, 'samples': 11902656, 'steps': 61992, 'loss/train': 0.04763659089803696} 08/31/2021 00:28:40 - INFO - __main__ - Step 61994: {'lr': 0.00032324121093776817, 'samples': 11902848, 'steps': 61993, 'loss/train': 1.376470685005188} 08/31/2021 00:28:40 - INFO - __main__ - Step 61995: {'lr': 0.0003232361370198067, 'samples': 11903040, 'steps': 61994, 'loss/train': 1.3200786113739014} 08/31/2021 00:28:42 - INFO - __main__ - Step 61996: {'lr': 0.0003232310630688462, 'samples': 11903232, 'steps': 61995, 'loss/train': 1.1402989625930786} 08/31/2021 00:28:42 - INFO - __main__ - Step 61997: {'lr': 0.00032322598908488887, 'samples': 11903424, 'steps': 61996, 'loss/train': 0.885474681854248} 08/31/2021 00:28:42 - INFO - __main__ - Step 61998: {'lr': 0.00032322091506793715, 'samples': 11903616, 'steps': 61997, 'loss/train': 1.7326539754867554} 08/31/2021 00:28:43 - INFO - __main__ - Step 61999: {'lr': 0.00032321584101799316, 'samples': 11903808, 'steps': 61998, 'loss/train': 1.1699498891830444} 08/31/2021 00:28:43 - INFO - __main__ - Step 62000: {'lr': 0.0003232107669350592, 'samples': 11904000, 'steps': 61999, 'loss/train': 1.5457381010055542} 08/31/2021 00:28:44 - INFO - __main__ - Step 62001: {'lr': 0.0003232056928191376, 'samples': 11904192, 'steps': 62000, 'loss/train': 1.116162657737732} 08/31/2021 00:28:45 - INFO - __main__ - Step 62002: {'lr': 0.00032320061867023066, 'samples': 11904384, 'steps': 62001, 'loss/train': 1.4379998445510864} 08/31/2021 00:28:45 - INFO - __main__ - Step 62003: {'lr': 0.0003231955444883407, 'samples': 11904576, 'steps': 62002, 'loss/train': 1.1688098907470703} 08/31/2021 00:28:46 - INFO - __main__ - Step 62004: {'lr': 0.0003231904702734699, 'samples': 11904768, 'steps': 62003, 'loss/train': 1.1867269277572632} 08/31/2021 00:28:46 - INFO - __main__ - Step 62005: {'lr': 0.00032318539602562064, 'samples': 11904960, 'steps': 62004, 'loss/train': 0.6888496279716492} 08/31/2021 00:28:46 - INFO - __main__ - Step 62006: {'lr': 0.00032318032174479515, 'samples': 11905152, 'steps': 62005, 'loss/train': 1.8393336534500122} 08/31/2021 00:28:49 - INFO - __main__ - Step 62007: {'lr': 0.0003231752474309957, 'samples': 11905344, 'steps': 62006, 'loss/train': 1.1252741813659668} 08/31/2021 00:28:49 - INFO - __main__ - Step 62008: {'lr': 0.00032317017308422464, 'samples': 11905536, 'steps': 62007, 'loss/train': 0.7000430822372437} 08/31/2021 00:28:49 - INFO - __main__ - Step 62009: {'lr': 0.0003231650987044843, 'samples': 11905728, 'steps': 62008, 'loss/train': 0.897852897644043} 08/31/2021 00:28:50 - INFO - __main__ - Step 62010: {'lr': 0.00032316002429177683, 'samples': 11905920, 'steps': 62009, 'loss/train': 1.4379156827926636} 08/31/2021 00:28:50 - INFO - __main__ - Step 62011: {'lr': 0.00032315494984610463, 'samples': 11906112, 'steps': 62010, 'loss/train': 1.0100082159042358} 08/31/2021 00:28:52 - INFO - __main__ - Step 62012: {'lr': 0.0003231498753674698, 'samples': 11906304, 'steps': 62011, 'loss/train': 1.558280348777771} 08/31/2021 00:28:52 - INFO - __main__ - Step 62013: {'lr': 0.00032314480085587487, 'samples': 11906496, 'steps': 62012, 'loss/train': 1.5839390754699707} 08/31/2021 00:28:52 - INFO - __main__ - Step 62014: {'lr': 0.00032313972631132197, 'samples': 11906688, 'steps': 62013, 'loss/train': 1.2856876850128174} 08/31/2021 00:28:53 - INFO - __main__ - Step 62015: {'lr': 0.0003231346517338135, 'samples': 11906880, 'steps': 62014, 'loss/train': 1.1809320449829102} 08/31/2021 00:28:53 - INFO - __main__ - Step 62016: {'lr': 0.00032312957712335173, 'samples': 11907072, 'steps': 62015, 'loss/train': 1.3888925313949585} 08/31/2021 00:28:55 - INFO - __main__ - Step 62017: {'lr': 0.0003231245024799388, 'samples': 11907264, 'steps': 62016, 'loss/train': 1.2251664400100708} 08/31/2021 00:28:55 - INFO - __main__ - Step 62018: {'lr': 0.00032311942780357714, 'samples': 11907456, 'steps': 62017, 'loss/train': 1.3376727104187012} 08/31/2021 00:28:56 - INFO - __main__ - Step 62019: {'lr': 0.00032311435309426894, 'samples': 11907648, 'steps': 62018, 'loss/train': 1.3280434608459473} 08/31/2021 00:28:56 - INFO - __main__ - Step 62020: {'lr': 0.00032310927835201665, 'samples': 11907840, 'steps': 62019, 'loss/train': 1.5164204835891724} 08/31/2021 00:28:56 - INFO - __main__ - Step 62021: {'lr': 0.00032310420357682234, 'samples': 11908032, 'steps': 62020, 'loss/train': 0.808944821357727} 08/31/2021 00:28:57 - INFO - __main__ - Step 62022: {'lr': 0.0003230991287686885, 'samples': 11908224, 'steps': 62021, 'loss/train': 5.377835273742676} 08/31/2021 00:28:58 - INFO - __main__ - Step 62023: {'lr': 0.00032309405392761726, 'samples': 11908416, 'steps': 62022, 'loss/train': 1.4022575616836548} 08/31/2021 00:28:59 - INFO - __main__ - Step 62024: {'lr': 0.00032308897905361094, 'samples': 11908608, 'steps': 62023, 'loss/train': 0.9787282347679138} 08/31/2021 00:28:59 - INFO - __main__ - Step 62025: {'lr': 0.00032308390414667186, 'samples': 11908800, 'steps': 62024, 'loss/train': 1.493695616722107} 08/31/2021 00:29:00 - INFO - __main__ - Step 62026: {'lr': 0.00032307882920680237, 'samples': 11908992, 'steps': 62025, 'loss/train': 1.1117514371871948} 08/31/2021 00:29:00 - INFO - __main__ - Step 62027: {'lr': 0.0003230737542340046, 'samples': 11909184, 'steps': 62026, 'loss/train': 1.2842400074005127} 08/31/2021 00:29:01 - INFO - __main__ - Step 62028: {'lr': 0.00032306867922828096, 'samples': 11909376, 'steps': 62027, 'loss/train': 2.0613350868225098} 08/31/2021 00:29:02 - INFO - __main__ - Step 62029: {'lr': 0.00032306360418963377, 'samples': 11909568, 'steps': 62028, 'loss/train': 1.465010166168213} 08/31/2021 00:29:02 - INFO - __main__ - Step 62030: {'lr': 0.0003230585291180652, 'samples': 11909760, 'steps': 62029, 'loss/train': 1.5952656269073486} 08/31/2021 00:29:03 - INFO - __main__ - Step 62031: {'lr': 0.00032305345401357756, 'samples': 11909952, 'steps': 62030, 'loss/train': 1.414678692817688} 08/31/2021 00:29:03 - INFO - __main__ - Step 62032: {'lr': 0.00032304837887617315, 'samples': 11910144, 'steps': 62031, 'loss/train': 1.470585584640503} 08/31/2021 00:29:04 - INFO - __main__ - Step 62033: {'lr': 0.0003230433037058543, 'samples': 11910336, 'steps': 62032, 'loss/train': 1.0566835403442383} 08/31/2021 00:29:05 - INFO - __main__ - Step 62034: {'lr': 0.00032303822850262323, 'samples': 11910528, 'steps': 62033, 'loss/train': 1.7630714178085327} 08/31/2021 00:29:05 - INFO - __main__ - Step 62035: {'lr': 0.0003230331532664823, 'samples': 11910720, 'steps': 62034, 'loss/train': 1.5345633029937744} 08/31/2021 00:29:06 - INFO - __main__ - Step 62036: {'lr': 0.00032302807799743376, 'samples': 11910912, 'steps': 62035, 'loss/train': 1.436813473701477} 08/31/2021 00:29:06 - INFO - __main__ - Step 62037: {'lr': 0.0003230230026954799, 'samples': 11911104, 'steps': 62036, 'loss/train': 1.3085664510726929} 08/31/2021 00:29:06 - INFO - __main__ - Step 62038: {'lr': 0.00032301792736062296, 'samples': 11911296, 'steps': 62037, 'loss/train': 1.2014225721359253} 08/31/2021 00:29:08 - INFO - __main__ - Step 62039: {'lr': 0.00032301285199286527, 'samples': 11911488, 'steps': 62038, 'loss/train': 1.4054869413375854} 08/31/2021 00:29:08 - INFO - __main__ - Step 62040: {'lr': 0.00032300777659220915, 'samples': 11911680, 'steps': 62039, 'loss/train': 0.9760551452636719} 08/31/2021 00:29:09 - INFO - __main__ - Step 62041: {'lr': 0.0003230027011586568, 'samples': 11911872, 'steps': 62040, 'loss/train': 1.4530835151672363} 08/31/2021 00:29:09 - INFO - __main__ - Step 62042: {'lr': 0.0003229976256922107, 'samples': 11912064, 'steps': 62041, 'loss/train': 0.2919674515724182} 08/31/2021 00:29:09 - INFO - __main__ - Step 62043: {'lr': 0.0003229925501928729, 'samples': 11912256, 'steps': 62042, 'loss/train': 1.5835251808166504} 08/31/2021 00:29:11 - INFO - __main__ - Step 62044: {'lr': 0.0003229874746606457, 'samples': 11912448, 'steps': 62043, 'loss/train': 1.3495559692382812} 08/31/2021 00:29:11 - INFO - __main__ - Step 62045: {'lr': 0.00032298239909553156, 'samples': 11912640, 'steps': 62044, 'loss/train': 2.004794120788574} 08/31/2021 00:29:12 - INFO - __main__ - Step 62046: {'lr': 0.0003229773234975327, 'samples': 11912832, 'steps': 62045, 'loss/train': 1.293025255203247} 08/31/2021 00:29:12 - INFO - __main__ - Step 62047: {'lr': 0.0003229722478666513, 'samples': 11913024, 'steps': 62046, 'loss/train': 2.36100172996521} 08/31/2021 00:29:12 - INFO - __main__ - Step 62048: {'lr': 0.0003229671722028898, 'samples': 11913216, 'steps': 62047, 'loss/train': 1.307456374168396} 08/31/2021 00:29:13 - INFO - __main__ - Step 62049: {'lr': 0.0003229620965062504, 'samples': 11913408, 'steps': 62048, 'loss/train': 0.9301515221595764} 08/31/2021 00:29:14 - INFO - __main__ - Step 62050: {'lr': 0.0003229570207767354, 'samples': 11913600, 'steps': 62049, 'loss/train': 1.7047202587127686} 08/31/2021 00:29:15 - INFO - __main__ - Step 62051: {'lr': 0.0003229519450143471, 'samples': 11913792, 'steps': 62050, 'loss/train': 0.9947953820228577} 08/31/2021 00:29:15 - INFO - __main__ - Step 62052: {'lr': 0.0003229468692190878, 'samples': 11913984, 'steps': 62051, 'loss/train': 1.1678783893585205} 08/31/2021 00:29:16 - INFO - __main__ - Step 62053: {'lr': 0.0003229417933909597, 'samples': 11914176, 'steps': 62052, 'loss/train': 1.02947199344635} 08/31/2021 00:29:16 - INFO - __main__ - Step 62054: {'lr': 0.0003229367175299652, 'samples': 11914368, 'steps': 62053, 'loss/train': 0.871828556060791} 08/31/2021 00:29:17 - INFO - __main__ - Step 62055: {'lr': 0.0003229316416361065, 'samples': 11914560, 'steps': 62054, 'loss/train': 0.3220118284225464} 08/31/2021 00:29:18 - INFO - __main__ - Step 62056: {'lr': 0.00032292656570938604, 'samples': 11914752, 'steps': 62055, 'loss/train': 1.7351361513137817} 08/31/2021 00:29:18 - INFO - __main__ - Step 62057: {'lr': 0.0003229214897498059, 'samples': 11914944, 'steps': 62056, 'loss/train': 1.324765682220459} 08/31/2021 00:29:19 - INFO - __main__ - Step 62058: {'lr': 0.00032291641375736845, 'samples': 11915136, 'steps': 62057, 'loss/train': 1.4860166311264038} 08/31/2021 00:29:19 - INFO - __main__ - Step 62059: {'lr': 0.00032291133773207603, 'samples': 11915328, 'steps': 62058, 'loss/train': 1.3958845138549805} 08/31/2021 00:29:21 - INFO - __main__ - Step 62060: {'lr': 0.00032290626167393087, 'samples': 11915520, 'steps': 62059, 'loss/train': 1.357555866241455} 08/31/2021 00:29:21 - INFO - __main__ - Step 62061: {'lr': 0.00032290118558293525, 'samples': 11915712, 'steps': 62060, 'loss/train': 2.2721972465515137} 08/31/2021 00:29:22 - INFO - __main__ - Step 62062: {'lr': 0.0003228961094590915, 'samples': 11915904, 'steps': 62061, 'loss/train': 0.5334951281547546} 08/31/2021 00:29:22 - INFO - __main__ - Step 62063: {'lr': 0.0003228910333024019, 'samples': 11916096, 'steps': 62062, 'loss/train': 1.8572564125061035} 08/31/2021 00:29:22 - INFO - __main__ - Step 62064: {'lr': 0.0003228859571128688, 'samples': 11916288, 'steps': 62063, 'loss/train': 1.5175050497055054} 08/31/2021 00:29:23 - INFO - __main__ - Step 62065: {'lr': 0.0003228808808904943, 'samples': 11916480, 'steps': 62064, 'loss/train': 1.0473829507827759} 08/31/2021 00:29:25 - INFO - __main__ - Step 62066: {'lr': 0.0003228758046352808, 'samples': 11916672, 'steps': 62065, 'loss/train': 1.2574235200881958} 08/31/2021 00:29:25 - INFO - __main__ - Step 62067: {'lr': 0.0003228707283472306, 'samples': 11916864, 'steps': 62066, 'loss/train': 1.2564067840576172} 08/31/2021 00:29:25 - INFO - __main__ - Step 62068: {'lr': 0.000322865652026346, 'samples': 11917056, 'steps': 62067, 'loss/train': 0.8123065233230591} 08/31/2021 00:29:26 - INFO - __main__ - Step 62069: {'lr': 0.0003228605756726293, 'samples': 11917248, 'steps': 62068, 'loss/train': 1.5204906463623047} 08/31/2021 00:29:26 - INFO - __main__ - Step 62070: {'lr': 0.00032285549928608273, 'samples': 11917440, 'steps': 62069, 'loss/train': 1.4316250085830688} 08/31/2021 00:29:28 - INFO - __main__ - Step 62071: {'lr': 0.00032285042286670857, 'samples': 11917632, 'steps': 62070, 'loss/train': 0.3027515113353729} 08/31/2021 00:29:28 - INFO - __main__ - Step 62072: {'lr': 0.00032284534641450916, 'samples': 11917824, 'steps': 62071, 'loss/train': 1.0027127265930176} 08/31/2021 00:29:29 - INFO - __main__ - Step 62073: {'lr': 0.00032284026992948666, 'samples': 11918016, 'steps': 62072, 'loss/train': 1.825935959815979} 08/31/2021 00:29:29 - INFO - __main__ - Step 62074: {'lr': 0.0003228351934116436, 'samples': 11918208, 'steps': 62073, 'loss/train': 2.2095251083374023} 08/31/2021 00:29:29 - INFO - __main__ - Step 62075: {'lr': 0.000322830116860982, 'samples': 11918400, 'steps': 62074, 'loss/train': 1.516528844833374} 08/31/2021 00:29:31 - INFO - __main__ - Step 62076: {'lr': 0.00032282504027750437, 'samples': 11918592, 'steps': 62075, 'loss/train': 0.729846715927124} 08/31/2021 00:29:32 - INFO - __main__ - Step 62077: {'lr': 0.00032281996366121285, 'samples': 11918784, 'steps': 62076, 'loss/train': 0.3953096270561218} 08/31/2021 00:29:32 - INFO - __main__ - Step 62078: {'lr': 0.0003228148870121098, 'samples': 11918976, 'steps': 62077, 'loss/train': 1.5952686071395874} 08/31/2021 00:29:32 - INFO - __main__ - Step 62079: {'lr': 0.00032280981033019744, 'samples': 11919168, 'steps': 62078, 'loss/train': 0.8124315738677979} 08/31/2021 00:29:33 - INFO - __main__ - Step 62080: {'lr': 0.0003228047336154782, 'samples': 11919360, 'steps': 62079, 'loss/train': 1.500165581703186} 08/31/2021 00:29:34 - INFO - __main__ - Step 62081: {'lr': 0.0003227996568679542, 'samples': 11919552, 'steps': 62080, 'loss/train': 1.3186407089233398} 08/31/2021 00:29:34 - INFO - __main__ - Step 62082: {'lr': 0.0003227945800876278, 'samples': 11919744, 'steps': 62081, 'loss/train': 0.6733141541481018} 08/31/2021 00:29:35 - INFO - __main__ - Step 62083: {'lr': 0.0003227895032745013, 'samples': 11919936, 'steps': 62082, 'loss/train': 1.245147466659546} 08/31/2021 00:29:35 - INFO - __main__ - Step 62084: {'lr': 0.00032278442642857697, 'samples': 11920128, 'steps': 62083, 'loss/train': 1.3650890588760376} 08/31/2021 00:29:36 - INFO - __main__ - Step 62085: {'lr': 0.0003227793495498571, 'samples': 11920320, 'steps': 62084, 'loss/train': 1.558658480644226} 08/31/2021 00:29:36 - INFO - __main__ - Step 62086: {'lr': 0.000322774272638344, 'samples': 11920512, 'steps': 62085, 'loss/train': 4.629883766174316} 08/31/2021 00:29:37 - INFO - __main__ - Step 62087: {'lr': 0.00032276919569403984, 'samples': 11920704, 'steps': 62086, 'loss/train': 1.3735359907150269} 08/31/2021 00:29:38 - INFO - __main__ - Step 62088: {'lr': 0.0003227641187169471, 'samples': 11920896, 'steps': 62087, 'loss/train': 1.6280704736709595} 08/31/2021 00:29:38 - INFO - __main__ - Step 62089: {'lr': 0.0003227590417070679, 'samples': 11921088, 'steps': 62088, 'loss/train': 1.0250027179718018} 08/31/2021 00:29:39 - INFO - __main__ - Step 62090: {'lr': 0.0003227539646644048, 'samples': 11921280, 'steps': 62089, 'loss/train': 1.9823790788650513} 08/31/2021 00:29:39 - INFO - __main__ - Step 62091: {'lr': 0.00032274888758895967, 'samples': 11921472, 'steps': 62090, 'loss/train': 1.422263741493225} 08/31/2021 00:29:41 - INFO - __main__ - Step 62092: {'lr': 0.00032274381048073505, 'samples': 11921664, 'steps': 62091, 'loss/train': 1.556844711303711} 08/31/2021 00:29:41 - INFO - __main__ - Step 62093: {'lr': 0.0003227387333397332, 'samples': 11921856, 'steps': 62092, 'loss/train': 0.9031374454498291} 08/31/2021 00:29:41 - INFO - __main__ - Step 62094: {'lr': 0.0003227336561659564, 'samples': 11922048, 'steps': 62093, 'loss/train': 0.6298803687095642} 08/31/2021 00:29:42 - INFO - __main__ - Step 62095: {'lr': 0.000322728578959407, 'samples': 11922240, 'steps': 62094, 'loss/train': 1.4293303489685059} 08/31/2021 00:29:42 - INFO - __main__ - Step 62096: {'lr': 0.0003227235017200872, 'samples': 11922432, 'steps': 62095, 'loss/train': 1.0383602380752563} 08/31/2021 00:29:44 - INFO - __main__ - Step 62097: {'lr': 0.00032271842444799926, 'samples': 11922624, 'steps': 62096, 'loss/train': 1.4700368642807007} 08/31/2021 00:29:44 - INFO - __main__ - Step 62098: {'lr': 0.0003227133471431455, 'samples': 11922816, 'steps': 62097, 'loss/train': 1.5081194639205933} 08/31/2021 00:29:44 - INFO - __main__ - Step 62099: {'lr': 0.0003227082698055283, 'samples': 11923008, 'steps': 62098, 'loss/train': 1.2465488910675049} 08/31/2021 00:29:45 - INFO - __main__ - Step 62100: {'lr': 0.0003227031924351499, 'samples': 11923200, 'steps': 62099, 'loss/train': 1.28041410446167} 08/31/2021 00:29:45 - INFO - __main__ - Step 62101: {'lr': 0.00032269811503201246, 'samples': 11923392, 'steps': 62100, 'loss/train': 1.6417253017425537} 08/31/2021 00:29:47 - INFO - __main__ - Step 62102: {'lr': 0.0003226930375961185, 'samples': 11923584, 'steps': 62101, 'loss/train': 1.2785519361495972} 08/31/2021 00:29:47 - INFO - __main__ - Step 62103: {'lr': 0.0003226879601274701, 'samples': 11923776, 'steps': 62102, 'loss/train': 1.5266602039337158} 08/31/2021 00:29:47 - INFO - __main__ - Step 62104: {'lr': 0.0003226828826260696, 'samples': 11923968, 'steps': 62103, 'loss/train': 1.686399221420288} 08/31/2021 00:29:48 - INFO - __main__ - Step 62105: {'lr': 0.00032267780509191935, 'samples': 11924160, 'steps': 62104, 'loss/train': 1.145574688911438} 08/31/2021 00:29:48 - INFO - __main__ - Step 62106: {'lr': 0.0003226727275250216, 'samples': 11924352, 'steps': 62105, 'loss/train': 0.6806468963623047} 08/31/2021 00:29:50 - INFO - __main__ - Step 62107: {'lr': 0.0003226676499253786, 'samples': 11924544, 'steps': 62106, 'loss/train': 0.9891972541809082} 08/31/2021 00:29:50 - INFO - __main__ - Step 62108: {'lr': 0.0003226625722929927, 'samples': 11924736, 'steps': 62107, 'loss/train': 1.7486824989318848} 08/31/2021 00:29:51 - INFO - __main__ - Step 62109: {'lr': 0.0003226574946278662, 'samples': 11924928, 'steps': 62108, 'loss/train': 0.049533553421497345} 08/31/2021 00:29:51 - INFO - __main__ - Step 62110: {'lr': 0.0003226524169300014, 'samples': 11925120, 'steps': 62109, 'loss/train': 1.4752607345581055} 08/31/2021 00:29:51 - INFO - __main__ - Step 62111: {'lr': 0.00032264733919940046, 'samples': 11925312, 'steps': 62110, 'loss/train': 1.8396939039230347} 08/31/2021 00:29:52 - INFO - __main__ - Step 62112: {'lr': 0.00032264226143606577, 'samples': 11925504, 'steps': 62111, 'loss/train': 0.042662233114242554} 08/31/2021 00:29:53 - INFO - __main__ - Step 62113: {'lr': 0.0003226371836399996, 'samples': 11925696, 'steps': 62112, 'loss/train': 0.3536195456981659} 08/31/2021 00:29:54 - INFO - __main__ - Step 62114: {'lr': 0.00032263210581120425, 'samples': 11925888, 'steps': 62113, 'loss/train': 1.7436681985855103} 08/31/2021 00:29:54 - INFO - __main__ - Step 62115: {'lr': 0.000322627027949682, 'samples': 11926080, 'steps': 62114, 'loss/train': 1.2114923000335693} 08/31/2021 00:29:54 - INFO - __main__ - Step 62116: {'lr': 0.0003226219500554351, 'samples': 11926272, 'steps': 62115, 'loss/train': 1.4756966829299927} 08/31/2021 00:29:55 - INFO - __main__ - Step 62117: {'lr': 0.0003226168721284659, 'samples': 11926464, 'steps': 62116, 'loss/train': 1.2059239149093628} 08/31/2021 00:29:57 - INFO - __main__ - Step 62118: {'lr': 0.00032261179416877663, 'samples': 11926656, 'steps': 62117, 'loss/train': 0.6347556114196777} 08/31/2021 00:29:57 - INFO - __main__ - Step 62119: {'lr': 0.0003226067161763696, 'samples': 11926848, 'steps': 62118, 'loss/train': 0.7063751816749573} 08/31/2021 00:29:57 - INFO - __main__ - Step 62120: {'lr': 0.0003226016381512471, 'samples': 11927040, 'steps': 62119, 'loss/train': 1.1728096008300781} 08/31/2021 00:29:58 - INFO - __main__ - Step 62121: {'lr': 0.0003225965600934115, 'samples': 11927232, 'steps': 62120, 'loss/train': 1.7103556394577026} 08/31/2021 00:29:58 - INFO - __main__ - Step 62122: {'lr': 0.0003225914820028649, 'samples': 11927424, 'steps': 62121, 'loss/train': 1.1099724769592285} 08/31/2021 00:30:00 - INFO - __main__ - Step 62123: {'lr': 0.0003225864038796098, 'samples': 11927616, 'steps': 62122, 'loss/train': 1.3882592916488647} 08/31/2021 00:30:00 - INFO - __main__ - Step 62124: {'lr': 0.0003225813257236483, 'samples': 11927808, 'steps': 62123, 'loss/train': 1.4165942668914795} 08/31/2021 00:30:00 - INFO - __main__ - Step 62125: {'lr': 0.00032257624753498284, 'samples': 11928000, 'steps': 62124, 'loss/train': 1.0956660509109497} 08/31/2021 00:30:01 - INFO - __main__ - Step 62126: {'lr': 0.00032257116931361555, 'samples': 11928192, 'steps': 62125, 'loss/train': 0.5244861245155334} 08/31/2021 00:30:01 - INFO - __main__ - Step 62127: {'lr': 0.00032256609105954894, 'samples': 11928384, 'steps': 62126, 'loss/train': 1.2824463844299316} 08/31/2021 00:30:03 - INFO - __main__ - Step 62128: {'lr': 0.0003225610127727851, 'samples': 11928576, 'steps': 62127, 'loss/train': 1.019234299659729} 08/31/2021 00:30:03 - INFO - __main__ - Step 62129: {'lr': 0.00032255593445332644, 'samples': 11928768, 'steps': 62128, 'loss/train': 0.2888886034488678} 08/31/2021 00:30:04 - INFO - __main__ - Step 62130: {'lr': 0.0003225508561011751, 'samples': 11928960, 'steps': 62129, 'loss/train': 1.5596588850021362} 08/31/2021 00:30:04 - INFO - __main__ - Step 62131: {'lr': 0.0003225457777163335, 'samples': 11929152, 'steps': 62130, 'loss/train': 0.9422298073768616} 08/31/2021 00:30:04 - INFO - __main__ - Step 62132: {'lr': 0.00032254069929880393, 'samples': 11929344, 'steps': 62131, 'loss/train': 0.8432231545448303} 08/31/2021 00:30:06 - INFO - __main__ - Step 62133: {'lr': 0.0003225356208485886, 'samples': 11929536, 'steps': 62132, 'loss/train': 1.5907222032546997} 08/31/2021 00:30:07 - INFO - __main__ - Step 62134: {'lr': 0.00032253054236568987, 'samples': 11929728, 'steps': 62133, 'loss/train': 0.12718158960342407} 08/31/2021 00:30:07 - INFO - __main__ - Step 62135: {'lr': 0.00032252546385010995, 'samples': 11929920, 'steps': 62134, 'loss/train': 0.04638001695275307} 08/31/2021 00:30:08 - INFO - __main__ - Step 62136: {'lr': 0.0003225203853018512, 'samples': 11930112, 'steps': 62135, 'loss/train': 0.06735315173864365} 08/31/2021 00:30:08 - INFO - __main__ - Step 62137: {'lr': 0.00032251530672091597, 'samples': 11930304, 'steps': 62136, 'loss/train': 1.0163525342941284} 08/31/2021 00:30:08 - INFO - __main__ - Step 62138: {'lr': 0.00032251022810730635, 'samples': 11930496, 'steps': 62137, 'loss/train': 1.5652885437011719} 08/31/2021 00:30:09 - INFO - __main__ - Step 62139: {'lr': 0.0003225051494610248, 'samples': 11930688, 'steps': 62138, 'loss/train': 1.158571481704712} 08/31/2021 00:30:09 - INFO - __main__ - Step 62140: {'lr': 0.00032250007078207343, 'samples': 11930880, 'steps': 62139, 'loss/train': 1.7934945821762085} 08/31/2021 00:30:10 - INFO - __main__ - Step 62141: {'lr': 0.00032249499207045475, 'samples': 11931072, 'steps': 62140, 'loss/train': 1.4962220191955566} 08/31/2021 00:30:11 - INFO - __main__ - Step 62142: {'lr': 0.00032248991332617095, 'samples': 11931264, 'steps': 62141, 'loss/train': 1.259709358215332} 08/31/2021 00:30:11 - INFO - __main__ - Step 62143: {'lr': 0.0003224848345492243, 'samples': 11931456, 'steps': 62142, 'loss/train': 1.2803266048431396} 08/31/2021 00:30:12 - INFO - __main__ - Step 62144: {'lr': 0.0003224797557396171, 'samples': 11931648, 'steps': 62143, 'loss/train': 1.2685163021087646} 08/31/2021 00:30:12 - INFO - __main__ - Step 62145: {'lr': 0.00032247467689735165, 'samples': 11931840, 'steps': 62144, 'loss/train': 1.4875248670578003} 08/31/2021 00:30:13 - INFO - __main__ - Step 62146: {'lr': 0.0003224695980224302, 'samples': 11932032, 'steps': 62145, 'loss/train': 1.4802601337432861} 08/31/2021 00:30:14 - INFO - __main__ - Step 62147: {'lr': 0.00032246451911485506, 'samples': 11932224, 'steps': 62146, 'loss/train': 1.3432211875915527} 08/31/2021 00:30:14 - INFO - __main__ - Step 62148: {'lr': 0.00032245944017462856, 'samples': 11932416, 'steps': 62147, 'loss/train': 0.17599882185459137} 08/31/2021 00:30:15 - INFO - __main__ - Step 62149: {'lr': 0.00032245436120175293, 'samples': 11932608, 'steps': 62148, 'loss/train': 1.5965579748153687} 08/31/2021 00:30:15 - INFO - __main__ - Step 62150: {'lr': 0.00032244928219623056, 'samples': 11932800, 'steps': 62149, 'loss/train': 1.1913256645202637} 08/31/2021 00:30:17 - INFO - __main__ - Step 62151: {'lr': 0.0003224442031580636, 'samples': 11932992, 'steps': 62150, 'loss/train': 1.0482738018035889} 08/31/2021 00:30:17 - INFO - __main__ - Step 62152: {'lr': 0.00032243912408725435, 'samples': 11933184, 'steps': 62151, 'loss/train': 1.3246104717254639} 08/31/2021 00:30:17 - INFO - __main__ - Step 62153: {'lr': 0.00032243404498380517, 'samples': 11933376, 'steps': 62152, 'loss/train': 1.1420526504516602} 08/31/2021 00:30:18 - INFO - __main__ - Step 62154: {'lr': 0.00032242896584771836, 'samples': 11933568, 'steps': 62153, 'loss/train': 1.363254189491272} 08/31/2021 00:30:18 - INFO - __main__ - Step 62155: {'lr': 0.00032242388667899614, 'samples': 11933760, 'steps': 62154, 'loss/train': 1.2261842489242554} 08/31/2021 00:30:20 - INFO - __main__ - Step 62156: {'lr': 0.00032241880747764084, 'samples': 11933952, 'steps': 62155, 'loss/train': 1.4200483560562134} 08/31/2021 00:30:20 - INFO - __main__ - Step 62157: {'lr': 0.00032241372824365485, 'samples': 11934144, 'steps': 62156, 'loss/train': 2.5620310306549072} 08/31/2021 00:30:21 - INFO - __main__ - Step 62158: {'lr': 0.00032240864897704023, 'samples': 11934336, 'steps': 62157, 'loss/train': 1.125840663909912} 08/31/2021 00:30:21 - INFO - __main__ - Step 62159: {'lr': 0.0003224035696777994, 'samples': 11934528, 'steps': 62158, 'loss/train': 1.9522401094436646} 08/31/2021 00:30:21 - INFO - __main__ - Step 62160: {'lr': 0.0003223984903459347, 'samples': 11934720, 'steps': 62159, 'loss/train': 1.6023826599121094} 08/31/2021 00:30:22 - INFO - __main__ - Step 62161: {'lr': 0.0003223934109814483, 'samples': 11934912, 'steps': 62160, 'loss/train': 1.1794382333755493} 08/31/2021 00:30:23 - INFO - __main__ - Step 62162: {'lr': 0.00032238833158434256, 'samples': 11935104, 'steps': 62161, 'loss/train': 1.8639326095581055} 08/31/2021 00:30:24 - INFO - __main__ - Step 62163: {'lr': 0.0003223832521546198, 'samples': 11935296, 'steps': 62162, 'loss/train': 2.69934344291687} 08/31/2021 00:30:24 - INFO - __main__ - Step 62164: {'lr': 0.00032237817269228225, 'samples': 11935488, 'steps': 62163, 'loss/train': 0.07185327261686325} 08/31/2021 00:30:25 - INFO - __main__ - Step 62165: {'lr': 0.0003223730931973322, 'samples': 11935680, 'steps': 62164, 'loss/train': 2.150378465652466} 08/31/2021 00:30:25 - INFO - __main__ - Step 62166: {'lr': 0.0003223680136697719, 'samples': 11935872, 'steps': 62165, 'loss/train': 1.3807694911956787} 08/31/2021 00:30:27 - INFO - __main__ - Step 62167: {'lr': 0.0003223629341096037, 'samples': 11936064, 'steps': 62166, 'loss/train': 1.3861796855926514} 08/31/2021 00:30:27 - INFO - __main__ - Step 62168: {'lr': 0.0003223578545168299, 'samples': 11936256, 'steps': 62167, 'loss/train': 1.5271663665771484} 08/31/2021 00:30:27 - INFO - __main__ - Step 62169: {'lr': 0.0003223527748914528, 'samples': 11936448, 'steps': 62168, 'loss/train': 1.1993569135665894} 08/31/2021 00:30:28 - INFO - __main__ - Step 62170: {'lr': 0.0003223476952334747, 'samples': 11936640, 'steps': 62169, 'loss/train': 1.7354191541671753} 08/31/2021 00:30:28 - INFO - __main__ - Step 62171: {'lr': 0.0003223426155428977, 'samples': 11936832, 'steps': 62170, 'loss/train': 2.3340303897857666} 08/31/2021 00:30:30 - INFO - __main__ - Step 62172: {'lr': 0.0003223375358197244, 'samples': 11937024, 'steps': 62171, 'loss/train': 1.275244116783142} 08/31/2021 00:30:31 - INFO - __main__ - Step 62173: {'lr': 0.00032233245606395677, 'samples': 11937216, 'steps': 62172, 'loss/train': 0.837317705154419} 08/31/2021 00:30:31 - INFO - __main__ - Step 62174: {'lr': 0.00032232737627559734, 'samples': 11937408, 'steps': 62173, 'loss/train': 0.9813233613967896} 08/31/2021 00:30:31 - INFO - __main__ - Step 62175: {'lr': 0.00032232229645464826, 'samples': 11937600, 'steps': 62174, 'loss/train': 5.809079170227051} 08/31/2021 00:30:32 - INFO - __main__ - Step 62176: {'lr': 0.0003223172166011119, 'samples': 11937792, 'steps': 62175, 'loss/train': 1.2909774780273438} 08/31/2021 00:30:32 - INFO - __main__ - Step 62177: {'lr': 0.00032231213671499057, 'samples': 11937984, 'steps': 62176, 'loss/train': 1.1421080827713013} 08/31/2021 00:30:34 - INFO - __main__ - Step 62178: {'lr': 0.0003223070567962864, 'samples': 11938176, 'steps': 62177, 'loss/train': 1.3693910837173462} 08/31/2021 00:30:34 - INFO - __main__ - Step 62179: {'lr': 0.00032230197684500185, 'samples': 11938368, 'steps': 62178, 'loss/train': 1.4819272756576538} 08/31/2021 00:30:34 - INFO - __main__ - Step 62180: {'lr': 0.0003222968968611391, 'samples': 11938560, 'steps': 62179, 'loss/train': 1.3498570919036865} 08/31/2021 00:30:35 - INFO - __main__ - Step 62181: {'lr': 0.00032229181684470054, 'samples': 11938752, 'steps': 62180, 'loss/train': 1.5401829481124878} 08/31/2021 00:30:35 - INFO - __main__ - Step 62182: {'lr': 0.00032228673679568834, 'samples': 11938944, 'steps': 62181, 'loss/train': 0.912170946598053} 08/31/2021 00:30:37 - INFO - __main__ - Step 62183: {'lr': 0.00032228165671410486, 'samples': 11939136, 'steps': 62182, 'loss/train': 0.5482463836669922} 08/31/2021 00:30:37 - INFO - __main__ - Step 62184: {'lr': 0.00032227657659995244, 'samples': 11939328, 'steps': 62183, 'loss/train': 1.7622801065444946} 08/31/2021 00:30:37 - INFO - __main__ - Step 62185: {'lr': 0.0003222714964532333, 'samples': 11939520, 'steps': 62184, 'loss/train': 1.394641637802124} 08/31/2021 00:30:38 - INFO - __main__ - Step 62186: {'lr': 0.0003222664162739497, 'samples': 11939712, 'steps': 62185, 'loss/train': 0.6228518486022949} 08/31/2021 00:30:38 - INFO - __main__ - Step 62187: {'lr': 0.000322261336062104, 'samples': 11939904, 'steps': 62186, 'loss/train': 1.455897331237793} 08/31/2021 00:30:40 - INFO - __main__ - Step 62188: {'lr': 0.00032225625581769844, 'samples': 11940096, 'steps': 62187, 'loss/train': 1.4177913665771484} 08/31/2021 00:30:40 - INFO - __main__ - Step 62189: {'lr': 0.0003222511755407353, 'samples': 11940288, 'steps': 62188, 'loss/train': 1.8088947534561157} 08/31/2021 00:30:40 - INFO - __main__ - Step 62190: {'lr': 0.000322246095231217, 'samples': 11940480, 'steps': 62189, 'loss/train': 1.3709163665771484} 08/31/2021 00:30:41 - INFO - __main__ - Step 62191: {'lr': 0.00032224101488914566, 'samples': 11940672, 'steps': 62190, 'loss/train': 1.0422593355178833} 08/31/2021 00:30:41 - INFO - __main__ - Step 62192: {'lr': 0.0003222359345145236, 'samples': 11940864, 'steps': 62191, 'loss/train': 0.8500306010246277} 08/31/2021 00:30:41 - INFO - __main__ - Step 62193: {'lr': 0.00032223085410735316, 'samples': 11941056, 'steps': 62192, 'loss/train': 1.2659908533096313} 08/31/2021 00:30:43 - INFO - __main__ - Step 62194: {'lr': 0.0003222257736676366, 'samples': 11941248, 'steps': 62193, 'loss/train': 1.3088645935058594} 08/31/2021 00:30:43 - INFO - __main__ - Step 62195: {'lr': 0.0003222206931953762, 'samples': 11941440, 'steps': 62194, 'loss/train': 1.3922561407089233} 08/31/2021 00:30:44 - INFO - __main__ - Step 62196: {'lr': 0.0003222156126905743, 'samples': 11941632, 'steps': 62195, 'loss/train': 1.358748197555542} 08/31/2021 00:30:44 - INFO - __main__ - Step 62197: {'lr': 0.0003222105321532333, 'samples': 11941824, 'steps': 62196, 'loss/train': 1.0592703819274902} 08/31/2021 00:30:45 - INFO - __main__ - Step 62198: {'lr': 0.0003222054515833551, 'samples': 11942016, 'steps': 62197, 'loss/train': 1.3141721487045288} 08/31/2021 00:30:46 - INFO - __main__ - Step 62199: {'lr': 0.0003222003709809424, 'samples': 11942208, 'steps': 62198, 'loss/train': 1.1804289817810059} 08/31/2021 00:30:47 - INFO - __main__ - Step 62200: {'lr': 0.00032219529034599725, 'samples': 11942400, 'steps': 62199, 'loss/train': 1.1183453798294067} 08/31/2021 00:30:47 - INFO - __main__ - Step 62201: {'lr': 0.000322190209678522, 'samples': 11942592, 'steps': 62200, 'loss/train': 0.047436706721782684} 08/31/2021 00:30:47 - INFO - __main__ - Step 62202: {'lr': 0.00032218512897851906, 'samples': 11942784, 'steps': 62201, 'loss/train': 1.0044341087341309} 08/31/2021 00:30:48 - INFO - __main__ - Step 62203: {'lr': 0.00032218004824599057, 'samples': 11942976, 'steps': 62202, 'loss/train': 1.2013407945632935} 08/31/2021 00:30:49 - INFO - __main__ - Step 62204: {'lr': 0.0003221749674809389, 'samples': 11943168, 'steps': 62203, 'loss/train': 0.9608385562896729} 08/31/2021 00:30:50 - INFO - __main__ - Step 62205: {'lr': 0.00032216988668336624, 'samples': 11943360, 'steps': 62204, 'loss/train': 0.7716181874275208} 08/31/2021 00:30:50 - INFO - __main__ - Step 62206: {'lr': 0.0003221648058532749, 'samples': 11943552, 'steps': 62205, 'loss/train': 1.497243046760559} 08/31/2021 00:30:51 - INFO - __main__ - Step 62207: {'lr': 0.00032215972499066725, 'samples': 11943744, 'steps': 62206, 'loss/train': 1.373687744140625} 08/31/2021 00:30:51 - INFO - __main__ - Step 62208: {'lr': 0.00032215464409554557, 'samples': 11943936, 'steps': 62207, 'loss/train': 1.556892991065979} 08/31/2021 00:30:53 - INFO - __main__ - Step 62209: {'lr': 0.00032214956316791213, 'samples': 11944128, 'steps': 62208, 'loss/train': 0.24045009911060333} 08/31/2021 00:30:53 - INFO - __main__ - Step 62210: {'lr': 0.00032214448220776917, 'samples': 11944320, 'steps': 62209, 'loss/train': 1.1032979488372803} 08/31/2021 00:30:53 - INFO - __main__ - Step 62211: {'lr': 0.0003221394012151191, 'samples': 11944512, 'steps': 62210, 'loss/train': 1.8008497953414917} 08/31/2021 00:30:54 - INFO - __main__ - Step 62212: {'lr': 0.000322134320189964, 'samples': 11944704, 'steps': 62211, 'loss/train': 0.7906494736671448} 08/31/2021 00:30:54 - INFO - __main__ - Step 62213: {'lr': 0.0003221292391323064, 'samples': 11944896, 'steps': 62212, 'loss/train': 0.8060088157653809} 08/31/2021 00:30:56 - INFO - __main__ - Step 62214: {'lr': 0.00032212415804214845, 'samples': 11945088, 'steps': 62213, 'loss/train': 0.06113201007246971} 08/31/2021 00:30:56 - INFO - __main__ - Step 62215: {'lr': 0.00032211907691949237, 'samples': 11945280, 'steps': 62214, 'loss/train': 1.5485162734985352} 08/31/2021 00:30:57 - INFO - __main__ - Step 62216: {'lr': 0.0003221139957643406, 'samples': 11945472, 'steps': 62215, 'loss/train': 0.5129861235618591} 08/31/2021 00:30:57 - INFO - __main__ - Step 62217: {'lr': 0.00032210891457669556, 'samples': 11945664, 'steps': 62216, 'loss/train': 1.535826563835144} 08/31/2021 00:30:57 - INFO - __main__ - Step 62218: {'lr': 0.0003221038333565591, 'samples': 11945856, 'steps': 62217, 'loss/train': 1.1988376379013062} 08/31/2021 00:30:59 - INFO - __main__ - Step 62219: {'lr': 0.0003220987521039339, 'samples': 11946048, 'steps': 62218, 'loss/train': 1.090638279914856} 08/31/2021 00:30:59 - INFO - __main__ - Step 62220: {'lr': 0.00032209367081882206, 'samples': 11946240, 'steps': 62219, 'loss/train': 1.189371943473816} 08/31/2021 00:31:00 - INFO - __main__ - Step 62221: {'lr': 0.000322088589501226, 'samples': 11946432, 'steps': 62220, 'loss/train': 0.7681282758712769} 08/31/2021 00:31:00 - INFO - __main__ - Step 62222: {'lr': 0.00032208350815114787, 'samples': 11946624, 'steps': 62221, 'loss/train': 0.9722975492477417} 08/31/2021 00:31:00 - INFO - __main__ - Step 62223: {'lr': 0.00032207842676859, 'samples': 11946816, 'steps': 62222, 'loss/train': 1.5767236948013306} 08/31/2021 00:31:02 - INFO - __main__ - Step 62224: {'lr': 0.0003220733453535548, 'samples': 11947008, 'steps': 62223, 'loss/train': 1.8711419105529785} 08/31/2021 00:31:02 - INFO - __main__ - Step 62225: {'lr': 0.0003220682639060444, 'samples': 11947200, 'steps': 62224, 'loss/train': 1.2730368375778198} 08/31/2021 00:31:03 - INFO - __main__ - Step 62226: {'lr': 0.00032206318242606116, 'samples': 11947392, 'steps': 62225, 'loss/train': 1.2138148546218872} 08/31/2021 00:31:03 - INFO - __main__ - Step 62227: {'lr': 0.00032205810091360734, 'samples': 11947584, 'steps': 62226, 'loss/train': 1.332945704460144} 08/31/2021 00:31:03 - INFO - __main__ - Step 62228: {'lr': 0.00032205301936868525, 'samples': 11947776, 'steps': 62227, 'loss/train': 1.2840443849563599} 08/31/2021 00:31:04 - INFO - __main__ - Step 62229: {'lr': 0.00032204793779129715, 'samples': 11947968, 'steps': 62228, 'loss/train': 0.9250892400741577} 08/31/2021 00:31:06 - INFO - __main__ - Step 62230: {'lr': 0.00032204285618144543, 'samples': 11948160, 'steps': 62229, 'loss/train': 1.0051709413528442} 08/31/2021 00:31:06 - INFO - __main__ - Step 62231: {'lr': 0.0003220377745391323, 'samples': 11948352, 'steps': 62230, 'loss/train': 0.08009758591651917} 08/31/2021 00:31:07 - INFO - __main__ - Step 62232: {'lr': 0.00032203269286436005, 'samples': 11948544, 'steps': 62231, 'loss/train': 1.6777496337890625} 08/31/2021 00:31:07 - INFO - __main__ - Step 62233: {'lr': 0.000322027611157131, 'samples': 11948736, 'steps': 62232, 'loss/train': 1.3828814029693604} 08/31/2021 00:31:07 - INFO - __main__ - Step 62234: {'lr': 0.00032202252941744737, 'samples': 11948928, 'steps': 62233, 'loss/train': 0.8148970007896423} 08/31/2021 00:31:09 - INFO - __main__ - Step 62235: {'lr': 0.00032201744764531157, 'samples': 11949120, 'steps': 62234, 'loss/train': 0.9804708361625671} 08/31/2021 00:31:09 - INFO - __main__ - Step 62236: {'lr': 0.00032201236584072576, 'samples': 11949312, 'steps': 62235, 'loss/train': 0.7428198456764221} 08/31/2021 00:31:10 - INFO - __main__ - Step 62237: {'lr': 0.00032200728400369233, 'samples': 11949504, 'steps': 62236, 'loss/train': 0.5924504399299622} 08/31/2021 00:31:10 - INFO - __main__ - Step 62238: {'lr': 0.0003220022021342135, 'samples': 11949696, 'steps': 62237, 'loss/train': 0.3945274353027344} 08/31/2021 00:31:10 - INFO - __main__ - Step 62239: {'lr': 0.00032199712023229154, 'samples': 11949888, 'steps': 62238, 'loss/train': 1.358620524406433} 08/31/2021 00:31:12 - INFO - __main__ - Step 62240: {'lr': 0.0003219920382979289, 'samples': 11950080, 'steps': 62239, 'loss/train': 1.21094810962677} 08/31/2021 00:31:12 - INFO - __main__ - Step 62241: {'lr': 0.0003219869563311277, 'samples': 11950272, 'steps': 62240, 'loss/train': 0.29690998792648315} 08/31/2021 00:31:13 - INFO - __main__ - Step 62242: {'lr': 0.00032198187433189025, 'samples': 11950464, 'steps': 62241, 'loss/train': 1.1558167934417725} 08/31/2021 00:31:13 - INFO - __main__ - Step 62243: {'lr': 0.00032197679230021894, 'samples': 11950656, 'steps': 62242, 'loss/train': 1.4844900369644165} 08/31/2021 00:31:13 - INFO - __main__ - Step 62244: {'lr': 0.000321971710236116, 'samples': 11950848, 'steps': 62243, 'loss/train': 1.7453809976577759} 08/31/2021 00:31:15 - INFO - __main__ - Step 62245: {'lr': 0.00032196662813958367, 'samples': 11951040, 'steps': 62244, 'loss/train': 1.2090004682540894} 08/31/2021 00:31:15 - INFO - __main__ - Step 62246: {'lr': 0.0003219615460106243, 'samples': 11951232, 'steps': 62245, 'loss/train': 0.8964786529541016} 08/31/2021 00:31:16 - INFO - __main__ - Step 62247: {'lr': 0.0003219564638492402, 'samples': 11951424, 'steps': 62246, 'loss/train': 1.1222351789474487} 08/31/2021 00:31:16 - INFO - __main__ - Step 62248: {'lr': 0.0003219513816554336, 'samples': 11951616, 'steps': 62247, 'loss/train': 1.0546106100082397} 08/31/2021 00:31:16 - INFO - __main__ - Step 62249: {'lr': 0.00032194629942920684, 'samples': 11951808, 'steps': 62248, 'loss/train': 1.1501131057739258} 08/31/2021 00:31:17 - INFO - __main__ - Step 62250: {'lr': 0.0003219412171705622, 'samples': 11952000, 'steps': 62249, 'loss/train': 1.1774364709854126} 08/31/2021 00:31:18 - INFO - __main__ - Step 62251: {'lr': 0.0003219361348795019, 'samples': 11952192, 'steps': 62250, 'loss/train': 0.7918271422386169} 08/31/2021 00:31:19 - INFO - __main__ - Step 62252: {'lr': 0.00032193105255602834, 'samples': 11952384, 'steps': 62251, 'loss/train': 0.9348809719085693} 08/31/2021 00:31:19 - INFO - __main__ - Step 62253: {'lr': 0.00032192597020014367, 'samples': 11952576, 'steps': 62252, 'loss/train': 0.6057593822479248} 08/31/2021 00:31:19 - INFO - __main__ - Step 62254: {'lr': 0.00032192088781185036, 'samples': 11952768, 'steps': 62253, 'loss/train': 1.537322998046875} 08/31/2021 00:31:20 - INFO - __main__ - Step 62255: {'lr': 0.0003219158053911506, 'samples': 11952960, 'steps': 62254, 'loss/train': 1.4610110521316528} 08/31/2021 00:31:21 - INFO - __main__ - Step 62256: {'lr': 0.0003219107229380467, 'samples': 11953152, 'steps': 62255, 'loss/train': 1.4554375410079956} 08/31/2021 00:31:22 - INFO - __main__ - Step 62257: {'lr': 0.00032190564045254087, 'samples': 11953344, 'steps': 62256, 'loss/train': 1.9010543823242188} 08/31/2021 00:31:22 - INFO - __main__ - Step 62258: {'lr': 0.0003219005579346355, 'samples': 11953536, 'steps': 62257, 'loss/train': 0.9164466261863708} 08/31/2021 00:31:23 - INFO - __main__ - Step 62259: {'lr': 0.0003218954753843329, 'samples': 11953728, 'steps': 62258, 'loss/train': 0.8782499432563782} 08/31/2021 00:31:23 - INFO - __main__ - Step 62260: {'lr': 0.0003218903928016352, 'samples': 11953920, 'steps': 62259, 'loss/train': 1.4192861318588257} 08/31/2021 00:31:24 - INFO - __main__ - Step 62261: {'lr': 0.00032188531018654496, 'samples': 11954112, 'steps': 62260, 'loss/train': 0.8742344975471497} 08/31/2021 00:31:25 - INFO - __main__ - Step 62262: {'lr': 0.0003218802275390642, 'samples': 11954304, 'steps': 62261, 'loss/train': 1.5585228204727173} 08/31/2021 00:31:25 - INFO - __main__ - Step 62263: {'lr': 0.00032187514485919534, 'samples': 11954496, 'steps': 62262, 'loss/train': 1.3701876401901245} 08/31/2021 00:31:25 - INFO - __main__ - Step 62264: {'lr': 0.00032187006214694057, 'samples': 11954688, 'steps': 62263, 'loss/train': 3.0160255432128906} 08/31/2021 00:31:26 - INFO - __main__ - Step 62265: {'lr': 0.00032186497940230236, 'samples': 11954880, 'steps': 62264, 'loss/train': 1.093552827835083} 08/31/2021 00:31:27 - INFO - __main__ - Step 62266: {'lr': 0.00032185989662528294, 'samples': 11955072, 'steps': 62265, 'loss/train': 1.2222559452056885} 08/31/2021 00:31:28 - INFO - __main__ - Step 62267: {'lr': 0.0003218548138158844, 'samples': 11955264, 'steps': 62266, 'loss/train': 1.284352421760559} 08/31/2021 00:31:28 - INFO - __main__ - Step 62268: {'lr': 0.0003218497309741093, 'samples': 11955456, 'steps': 62267, 'loss/train': 4.383668899536133} 08/31/2021 00:31:28 - INFO - __main__ - Step 62269: {'lr': 0.00032184464809995977, 'samples': 11955648, 'steps': 62268, 'loss/train': 0.9428014159202576} 08/31/2021 00:31:29 - INFO - __main__ - Step 62270: {'lr': 0.00032183956519343815, 'samples': 11955840, 'steps': 62269, 'loss/train': 1.2881768941879272} 08/31/2021 00:31:29 - INFO - __main__ - Step 62271: {'lr': 0.00032183448225454674, 'samples': 11956032, 'steps': 62270, 'loss/train': 1.710982084274292} 08/31/2021 00:31:31 - INFO - __main__ - Step 62272: {'lr': 0.0003218293992832879, 'samples': 11956224, 'steps': 62271, 'loss/train': 0.9087924361228943} 08/31/2021 00:31:31 - INFO - __main__ - Step 62273: {'lr': 0.0003218243162796638, 'samples': 11956416, 'steps': 62272, 'loss/train': 1.6481451988220215} 08/31/2021 00:31:31 - INFO - __main__ - Step 62274: {'lr': 0.00032181923324367675, 'samples': 11956608, 'steps': 62273, 'loss/train': 1.3371226787567139} 08/31/2021 00:31:32 - INFO - __main__ - Step 62275: {'lr': 0.000321814150175329, 'samples': 11956800, 'steps': 62274, 'loss/train': 1.6483714580535889} 08/31/2021 00:31:32 - INFO - __main__ - Step 62276: {'lr': 0.000321809067074623, 'samples': 11956992, 'steps': 62275, 'loss/train': 1.7196013927459717} 08/31/2021 00:31:34 - INFO - __main__ - Step 62277: {'lr': 0.00032180398394156083, 'samples': 11957184, 'steps': 62276, 'loss/train': 0.15421375632286072} 08/31/2021 00:31:34 - INFO - __main__ - Step 62278: {'lr': 0.00032179890077614506, 'samples': 11957376, 'steps': 62277, 'loss/train': 1.0859968662261963} 08/31/2021 00:31:35 - INFO - __main__ - Step 62279: {'lr': 0.00032179381757837773, 'samples': 11957568, 'steps': 62278, 'loss/train': 1.1580053567886353} 08/31/2021 00:31:35 - INFO - __main__ - Step 62280: {'lr': 0.00032178873434826117, 'samples': 11957760, 'steps': 62279, 'loss/train': 0.34500446915626526} 08/31/2021 00:31:35 - INFO - __main__ - Step 62281: {'lr': 0.00032178365108579776, 'samples': 11957952, 'steps': 62280, 'loss/train': 1.0619680881500244} 08/31/2021 00:31:37 - INFO - __main__ - Step 62282: {'lr': 0.0003217785677909897, 'samples': 11958144, 'steps': 62281, 'loss/train': 1.451377272605896} 08/31/2021 00:31:38 - INFO - __main__ - Step 62283: {'lr': 0.00032177348446383935, 'samples': 11958336, 'steps': 62282, 'loss/train': 0.7134572863578796} 08/31/2021 00:31:38 - INFO - __main__ - Step 62284: {'lr': 0.000321768401104349, 'samples': 11958528, 'steps': 62283, 'loss/train': 2.0055058002471924} 08/31/2021 00:31:38 - INFO - __main__ - Step 62285: {'lr': 0.0003217633177125209, 'samples': 11958720, 'steps': 62284, 'loss/train': 1.3261750936508179} 08/31/2021 00:31:39 - INFO - __main__ - Step 62286: {'lr': 0.0003217582342883574, 'samples': 11958912, 'steps': 62285, 'loss/train': 1.0916410684585571} 08/31/2021 00:31:40 - INFO - __main__ - Step 62287: {'lr': 0.0003217531508318607, 'samples': 11959104, 'steps': 62286, 'loss/train': 1.3785709142684937} 08/31/2021 00:31:41 - INFO - __main__ - Step 62288: {'lr': 0.00032174806734303307, 'samples': 11959296, 'steps': 62287, 'loss/train': 0.9012096524238586} 08/31/2021 00:31:41 - INFO - __main__ - Step 62289: {'lr': 0.00032174298382187696, 'samples': 11959488, 'steps': 62288, 'loss/train': 1.3953458070755005} 08/31/2021 00:31:42 - INFO - __main__ - Step 62290: {'lr': 0.00032173790026839455, 'samples': 11959680, 'steps': 62289, 'loss/train': 1.373857855796814} 08/31/2021 00:31:42 - INFO - __main__ - Step 62291: {'lr': 0.0003217328166825882, 'samples': 11959872, 'steps': 62290, 'loss/train': 1.3067028522491455} 08/31/2021 00:31:44 - INFO - __main__ - Step 62292: {'lr': 0.00032172773306446005, 'samples': 11960064, 'steps': 62291, 'loss/train': 1.1975376605987549} 08/31/2021 00:31:44 - INFO - __main__ - Step 62293: {'lr': 0.0003217226494140125, 'samples': 11960256, 'steps': 62292, 'loss/train': 1.4231469631195068} 08/31/2021 00:31:44 - INFO - __main__ - Step 62294: {'lr': 0.0003217175657312479, 'samples': 11960448, 'steps': 62293, 'loss/train': 1.4960918426513672} 08/31/2021 00:31:45 - INFO - __main__ - Step 62295: {'lr': 0.00032171248201616845, 'samples': 11960640, 'steps': 62294, 'loss/train': 0.9206927418708801} 08/31/2021 00:31:45 - INFO - __main__ - Step 62296: {'lr': 0.0003217073982687764, 'samples': 11960832, 'steps': 62295, 'loss/train': 1.3765289783477783} 08/31/2021 00:31:45 - INFO - __main__ - Step 62297: {'lr': 0.00032170231448907415, 'samples': 11961024, 'steps': 62296, 'loss/train': 1.4603825807571411} 08/31/2021 00:31:47 - INFO - __main__ - Step 62298: {'lr': 0.000321697230677064, 'samples': 11961216, 'steps': 62297, 'loss/train': 0.0319746769964695} 08/31/2021 00:31:47 - INFO - __main__ - Step 62299: {'lr': 0.00032169214683274816, 'samples': 11961408, 'steps': 62298, 'loss/train': 0.7399267554283142} 08/31/2021 00:31:48 - INFO - __main__ - Step 62300: {'lr': 0.00032168706295612894, 'samples': 11961600, 'steps': 62299, 'loss/train': 0.4629809260368347} 08/31/2021 00:31:48 - INFO - __main__ - Step 62301: {'lr': 0.0003216819790472085, 'samples': 11961792, 'steps': 62300, 'loss/train': 1.622847557067871} 08/31/2021 00:31:49 - INFO - __main__ - Step 62302: {'lr': 0.0003216768951059894, 'samples': 11961984, 'steps': 62301, 'loss/train': 1.4226542711257935} 08/31/2021 00:31:50 - INFO - __main__ - Step 62303: {'lr': 0.0003216718111324738, 'samples': 11962176, 'steps': 62302, 'loss/train': 0.7613059878349304} 08/31/2021 00:31:51 - INFO - __main__ - Step 62304: {'lr': 0.00032166672712666397, 'samples': 11962368, 'steps': 62303, 'loss/train': 1.6567084789276123} 08/31/2021 00:31:51 - INFO - __main__ - Step 62305: {'lr': 0.0003216616430885622, 'samples': 11962560, 'steps': 62304, 'loss/train': 3.0639326572418213} 08/31/2021 00:31:51 - INFO - __main__ - Step 62306: {'lr': 0.0003216565590181708, 'samples': 11962752, 'steps': 62305, 'loss/train': 1.0783061981201172} 08/31/2021 00:31:52 - INFO - __main__ - Step 62307: {'lr': 0.0003216514749154921, 'samples': 11962944, 'steps': 62306, 'loss/train': 1.0854521989822388} 08/31/2021 00:31:53 - INFO - __main__ - Step 62308: {'lr': 0.0003216463907805283, 'samples': 11963136, 'steps': 62307, 'loss/train': 0.6296263933181763} 08/31/2021 00:31:54 - INFO - __main__ - Step 62309: {'lr': 0.0003216413066132818, 'samples': 11963328, 'steps': 62308, 'loss/train': 0.9980742931365967} 08/31/2021 00:31:54 - INFO - __main__ - Step 62310: {'lr': 0.00032163622241375477, 'samples': 11963520, 'steps': 62309, 'loss/train': 1.9203672409057617} 08/31/2021 00:31:54 - INFO - __main__ - Step 62311: {'lr': 0.0003216311381819496, 'samples': 11963712, 'steps': 62310, 'loss/train': 0.7199133634567261} 08/31/2021 00:31:55 - INFO - __main__ - Step 62312: {'lr': 0.00032162605391786853, 'samples': 11963904, 'steps': 62311, 'loss/train': 1.569016933441162} 08/31/2021 00:31:55 - INFO - __main__ - Step 62313: {'lr': 0.0003216209696215139, 'samples': 11964096, 'steps': 62312, 'loss/train': 0.8560441136360168} 08/31/2021 00:31:57 - INFO - __main__ - Step 62314: {'lr': 0.0003216158852928879, 'samples': 11964288, 'steps': 62313, 'loss/train': 1.3734025955200195} 08/31/2021 00:31:57 - INFO - __main__ - Step 62315: {'lr': 0.00032161080093199293, 'samples': 11964480, 'steps': 62314, 'loss/train': 0.9211986660957336} 08/31/2021 00:31:57 - INFO - __main__ - Step 62316: {'lr': 0.0003216057165388312, 'samples': 11964672, 'steps': 62315, 'loss/train': 2.051877737045288} 08/31/2021 00:31:58 - INFO - __main__ - Step 62317: {'lr': 0.0003216006321134051, 'samples': 11964864, 'steps': 62316, 'loss/train': 1.2914131879806519} 08/31/2021 00:31:58 - INFO - __main__ - Step 62318: {'lr': 0.0003215955476557169, 'samples': 11965056, 'steps': 62317, 'loss/train': 1.2870811223983765} 08/31/2021 00:32:00 - INFO - __main__ - Step 62319: {'lr': 0.0003215904631657687, 'samples': 11965248, 'steps': 62318, 'loss/train': 1.3394590616226196} 08/31/2021 00:32:00 - INFO - __main__ - Step 62320: {'lr': 0.00032158537864356306, 'samples': 11965440, 'steps': 62319, 'loss/train': 1.3708089590072632} 08/31/2021 00:32:01 - INFO - __main__ - Step 62321: {'lr': 0.0003215802940891021, 'samples': 11965632, 'steps': 62320, 'loss/train': 0.9109838008880615} 08/31/2021 00:32:01 - INFO - __main__ - Step 62322: {'lr': 0.00032157520950238814, 'samples': 11965824, 'steps': 62321, 'loss/train': 1.010701298713684} 08/31/2021 00:32:01 - INFO - __main__ - Step 62323: {'lr': 0.00032157012488342356, 'samples': 11966016, 'steps': 62322, 'loss/train': 1.6001845598220825} 08/31/2021 00:32:03 - INFO - __main__ - Step 62324: {'lr': 0.0003215650402322106, 'samples': 11966208, 'steps': 62323, 'loss/train': 0.6125072836875916} 08/31/2021 00:32:04 - INFO - __main__ - Step 62325: {'lr': 0.0003215599555487515, 'samples': 11966400, 'steps': 62324, 'loss/train': 0.06726004183292389} 08/31/2021 00:32:04 - INFO - __main__ - Step 62326: {'lr': 0.00032155487083304857, 'samples': 11966592, 'steps': 62325, 'loss/train': 0.779845118522644} 08/31/2021 00:32:04 - INFO - __main__ - Step 62327: {'lr': 0.00032154978608510415, 'samples': 11966784, 'steps': 62326, 'loss/train': 0.8295971751213074} 08/31/2021 00:32:05 - INFO - __main__ - Step 62328: {'lr': 0.0003215447013049205, 'samples': 11966976, 'steps': 62327, 'loss/train': 1.541180968284607} 08/31/2021 00:32:06 - INFO - __main__ - Step 62329: {'lr': 0.00032153961649249987, 'samples': 11967168, 'steps': 62328, 'loss/train': 1.1336588859558105} 08/31/2021 00:32:06 - INFO - __main__ - Step 62330: {'lr': 0.0003215345316478446, 'samples': 11967360, 'steps': 62329, 'loss/train': 1.438570261001587} 08/31/2021 00:32:07 - INFO - __main__ - Step 62331: {'lr': 0.00032152944677095696, 'samples': 11967552, 'steps': 62330, 'loss/train': 1.244158148765564} 08/31/2021 00:32:07 - INFO - __main__ - Step 62332: {'lr': 0.0003215243618618394, 'samples': 11967744, 'steps': 62331, 'loss/train': 0.9234000444412231} 08/31/2021 00:32:08 - INFO - __main__ - Step 62333: {'lr': 0.00032151927692049395, 'samples': 11967936, 'steps': 62332, 'loss/train': 1.253640055656433} 08/31/2021 00:32:08 - INFO - __main__ - Step 62334: {'lr': 0.000321514191946923, 'samples': 11968128, 'steps': 62333, 'loss/train': 1.558366060256958} 08/31/2021 00:32:09 - INFO - __main__ - Step 62335: {'lr': 0.0003215091069411289, 'samples': 11968320, 'steps': 62334, 'loss/train': 1.5695983171463013} 08/31/2021 00:32:10 - INFO - __main__ - Step 62336: {'lr': 0.00032150402190311383, 'samples': 11968512, 'steps': 62335, 'loss/train': 1.2305208444595337} 08/31/2021 00:32:10 - INFO - __main__ - Step 62337: {'lr': 0.00032149893683288024, 'samples': 11968704, 'steps': 62336, 'loss/train': 1.308262825012207} 08/31/2021 00:32:11 - INFO - __main__ - Step 62338: {'lr': 0.00032149385173043033, 'samples': 11968896, 'steps': 62337, 'loss/train': 1.2703298330307007} 08/31/2021 00:32:11 - INFO - __main__ - Step 62339: {'lr': 0.0003214887665957663, 'samples': 11969088, 'steps': 62338, 'loss/train': 0.853405237197876} 08/31/2021 00:32:13 - INFO - __main__ - Step 62340: {'lr': 0.0003214836814288906, 'samples': 11969280, 'steps': 62339, 'loss/train': 1.4834030866622925} 08/31/2021 00:32:14 - INFO - __main__ - Step 62341: {'lr': 0.0003214785962298055, 'samples': 11969472, 'steps': 62340, 'loss/train': 1.8730696439743042} 08/31/2021 00:32:14 - INFO - __main__ - Step 62342: {'lr': 0.0003214735109985131, 'samples': 11969664, 'steps': 62341, 'loss/train': 1.6602709293365479} 08/31/2021 00:32:14 - INFO - __main__ - Step 62343: {'lr': 0.000321468425735016, 'samples': 11969856, 'steps': 62342, 'loss/train': 1.4387755393981934} 08/31/2021 00:32:15 - INFO - __main__ - Step 62344: {'lr': 0.00032146334043931625, 'samples': 11970048, 'steps': 62343, 'loss/train': 1.7495567798614502} 08/31/2021 00:32:16 - INFO - __main__ - Step 62345: {'lr': 0.00032145825511141626, 'samples': 11970240, 'steps': 62344, 'loss/train': 1.425860047340393} 08/31/2021 00:32:17 - INFO - __main__ - Step 62346: {'lr': 0.0003214531697513183, 'samples': 11970432, 'steps': 62345, 'loss/train': 1.2485907077789307} 08/31/2021 00:32:17 - INFO - __main__ - Step 62347: {'lr': 0.00032144808435902454, 'samples': 11970624, 'steps': 62346, 'loss/train': 1.1319574117660522} 08/31/2021 00:32:17 - INFO - __main__ - Step 62348: {'lr': 0.00032144299893453743, 'samples': 11970816, 'steps': 62347, 'loss/train': 0.9037505388259888} 08/31/2021 00:32:18 - INFO - __main__ - Step 62349: {'lr': 0.0003214379134778592, 'samples': 11971008, 'steps': 62348, 'loss/train': 1.1735849380493164} 08/31/2021 00:32:19 - INFO - __main__ - Step 62350: {'lr': 0.0003214328279889922, 'samples': 11971200, 'steps': 62349, 'loss/train': 0.30713051557540894} 08/31/2021 00:32:20 - INFO - __main__ - Step 62351: {'lr': 0.0003214277424679386, 'samples': 11971392, 'steps': 62350, 'loss/train': 0.21161401271820068} 08/31/2021 00:32:20 - INFO - __main__ - Step 62352: {'lr': 0.00032142265691470083, 'samples': 11971584, 'steps': 62351, 'loss/train': 1.2769067287445068} 08/31/2021 00:32:20 - INFO - __main__ - Step 62353: {'lr': 0.00032141757132928114, 'samples': 11971776, 'steps': 62352, 'loss/train': 1.4506089687347412} 08/31/2021 00:32:21 - INFO - __main__ - Step 62354: {'lr': 0.0003214124857116817, 'samples': 11971968, 'steps': 62353, 'loss/train': 0.6066582202911377} 08/31/2021 00:32:22 - INFO - __main__ - Step 62355: {'lr': 0.00032140740006190494, 'samples': 11972160, 'steps': 62354, 'loss/train': 1.6166421175003052} 08/31/2021 00:32:22 - INFO - __main__ - Step 62356: {'lr': 0.00032140231437995304, 'samples': 11972352, 'steps': 62355, 'loss/train': 1.6407510042190552} 08/31/2021 00:32:23 - INFO - __main__ - Step 62357: {'lr': 0.0003213972286658284, 'samples': 11972544, 'steps': 62356, 'loss/train': 1.1812710762023926} 08/31/2021 00:32:23 - INFO - __main__ - Step 62358: {'lr': 0.0003213921429195334, 'samples': 11972736, 'steps': 62357, 'loss/train': 1.6104660034179688} 08/31/2021 00:32:24 - INFO - __main__ - Step 62359: {'lr': 0.0003213870571410701, 'samples': 11972928, 'steps': 62358, 'loss/train': 1.262515664100647} 08/31/2021 00:32:24 - INFO - __main__ - Step 62360: {'lr': 0.00032138197133044086, 'samples': 11973120, 'steps': 62359, 'loss/train': 0.9501708745956421} 08/31/2021 00:32:26 - INFO - __main__ - Step 62361: {'lr': 0.000321376885487648, 'samples': 11973312, 'steps': 62360, 'loss/train': 1.0267564058303833} 08/31/2021 00:32:26 - INFO - __main__ - Step 62362: {'lr': 0.00032137179961269386, 'samples': 11973504, 'steps': 62361, 'loss/train': 0.9003808498382568} 08/31/2021 00:32:27 - INFO - __main__ - Step 62363: {'lr': 0.0003213667137055807, 'samples': 11973696, 'steps': 62362, 'loss/train': 0.5014355182647705} 08/31/2021 00:32:27 - INFO - __main__ - Step 62364: {'lr': 0.0003213616277663107, 'samples': 11973888, 'steps': 62363, 'loss/train': 1.2728511095046997} 08/31/2021 00:32:27 - INFO - __main__ - Step 62365: {'lr': 0.00032135654179488637, 'samples': 11974080, 'steps': 62364, 'loss/train': 1.5755860805511475} 08/31/2021 00:32:29 - INFO - __main__ - Step 62366: {'lr': 0.00032135145579130985, 'samples': 11974272, 'steps': 62365, 'loss/train': 1.2684135437011719} 08/31/2021 00:32:29 - INFO - __main__ - Step 62367: {'lr': 0.00032134636975558343, 'samples': 11974464, 'steps': 62366, 'loss/train': 1.1783032417297363} 08/31/2021 00:32:30 - INFO - __main__ - Step 62368: {'lr': 0.0003213412836877095, 'samples': 11974656, 'steps': 62367, 'loss/train': 0.844720184803009} 08/31/2021 00:32:30 - INFO - __main__ - Step 62369: {'lr': 0.0003213361975876902, 'samples': 11974848, 'steps': 62368, 'loss/train': 1.8296536207199097} 08/31/2021 00:32:30 - INFO - __main__ - Step 62370: {'lr': 0.00032133111145552797, 'samples': 11975040, 'steps': 62369, 'loss/train': 0.880347728729248} 08/31/2021 00:32:31 - INFO - __main__ - Step 62371: {'lr': 0.000321326025291225, 'samples': 11975232, 'steps': 62370, 'loss/train': 1.4718278646469116} 08/31/2021 00:32:32 - INFO - __main__ - Step 62372: {'lr': 0.0003213209390947837, 'samples': 11975424, 'steps': 62371, 'loss/train': 1.6133702993392944} 08/31/2021 00:32:33 - INFO - __main__ - Step 62373: {'lr': 0.00032131585286620623, 'samples': 11975616, 'steps': 62372, 'loss/train': 1.3820029497146606} 08/31/2021 00:32:33 - INFO - __main__ - Step 62374: {'lr': 0.00032131076660549496, 'samples': 11975808, 'steps': 62373, 'loss/train': 2.264085292816162} 08/31/2021 00:32:33 - INFO - __main__ - Step 62375: {'lr': 0.00032130568031265216, 'samples': 11976000, 'steps': 62374, 'loss/train': 1.032321572303772} 08/31/2021 00:32:34 - INFO - __main__ - Step 62376: {'lr': 0.00032130059398768006, 'samples': 11976192, 'steps': 62375, 'loss/train': 1.3473870754241943} 08/31/2021 00:32:35 - INFO - __main__ - Step 62377: {'lr': 0.00032129550763058105, 'samples': 11976384, 'steps': 62376, 'loss/train': 1.5936411619186401} 08/31/2021 00:32:36 - INFO - __main__ - Step 62378: {'lr': 0.00032129042124135745, 'samples': 11976576, 'steps': 62377, 'loss/train': 1.025199055671692} 08/31/2021 00:32:36 - INFO - __main__ - Step 62379: {'lr': 0.00032128533482001144, 'samples': 11976768, 'steps': 62378, 'loss/train': 1.5237939357757568} 08/31/2021 00:32:36 - INFO - __main__ - Step 62380: {'lr': 0.00032128024836654533, 'samples': 11976960, 'steps': 62379, 'loss/train': 1.0672471523284912} 08/31/2021 00:32:37 - INFO - __main__ - Step 62381: {'lr': 0.00032127516188096153, 'samples': 11977152, 'steps': 62380, 'loss/train': 2.0366461277008057} 08/31/2021 00:32:38 - INFO - __main__ - Step 62382: {'lr': 0.00032127007536326215, 'samples': 11977344, 'steps': 62381, 'loss/train': 1.060616374015808} 08/31/2021 00:32:39 - INFO - __main__ - Step 62383: {'lr': 0.00032126498881344956, 'samples': 11977536, 'steps': 62382, 'loss/train': 1.5345704555511475} 08/31/2021 00:32:39 - INFO - __main__ - Step 62384: {'lr': 0.0003212599022315261, 'samples': 11977728, 'steps': 62383, 'loss/train': 1.8863898515701294} 08/31/2021 00:32:39 - INFO - __main__ - Step 62385: {'lr': 0.00032125481561749405, 'samples': 11977920, 'steps': 62384, 'loss/train': 1.8229122161865234} 08/31/2021 00:32:40 - INFO - __main__ - Step 62386: {'lr': 0.0003212497289713556, 'samples': 11978112, 'steps': 62385, 'loss/train': 0.8158073425292969} 08/31/2021 00:32:41 - INFO - __main__ - Step 62387: {'lr': 0.0003212446422931132, 'samples': 11978304, 'steps': 62386, 'loss/train': 1.153435230255127} 08/31/2021 00:32:41 - INFO - __main__ - Step 62388: {'lr': 0.00032123955558276905, 'samples': 11978496, 'steps': 62387, 'loss/train': 1.2832715511322021} 08/31/2021 00:32:42 - INFO - __main__ - Step 62389: {'lr': 0.0003212344688403255, 'samples': 11978688, 'steps': 62388, 'loss/train': 0.9654755592346191} 08/31/2021 00:32:42 - INFO - __main__ - Step 62390: {'lr': 0.0003212293820657848, 'samples': 11978880, 'steps': 62389, 'loss/train': 1.3745149374008179} 08/31/2021 00:32:43 - INFO - __main__ - Step 62391: {'lr': 0.0003212242952591491, 'samples': 11979072, 'steps': 62390, 'loss/train': 1.383437156677246} 08/31/2021 00:32:45 - INFO - __main__ - Step 62392: {'lr': 0.000321219208420421, 'samples': 11979264, 'steps': 62391, 'loss/train': 1.2201119661331177} 08/31/2021 00:32:45 - INFO - __main__ - Step 62393: {'lr': 0.0003212141215496025, 'samples': 11979456, 'steps': 62392, 'loss/train': 0.9932960867881775} 08/31/2021 00:32:45 - INFO - __main__ - Step 62394: {'lr': 0.00032120903464669603, 'samples': 11979648, 'steps': 62393, 'loss/train': 1.4471087455749512} 08/31/2021 00:32:46 - INFO - __main__ - Step 62395: {'lr': 0.0003212039477117039, 'samples': 11979840, 'steps': 62394, 'loss/train': 1.2384730577468872} 08/31/2021 00:32:46 - INFO - __main__ - Step 62396: {'lr': 0.0003211988607446284, 'samples': 11980032, 'steps': 62395, 'loss/train': 1.4967626333236694} 08/31/2021 00:32:46 - INFO - __main__ - Step 62397: {'lr': 0.0003211937737454718, 'samples': 11980224, 'steps': 62396, 'loss/train': 1.469065546989441} 08/31/2021 00:32:48 - INFO - __main__ - Step 62398: {'lr': 0.0003211886867142363, 'samples': 11980416, 'steps': 62397, 'loss/train': 3.458975076675415} 08/31/2021 00:32:48 - INFO - __main__ - Step 62399: {'lr': 0.00032118359965092424, 'samples': 11980608, 'steps': 62398, 'loss/train': 1.3853633403778076} 08/31/2021 00:32:49 - INFO - __main__ - Step 62400: {'lr': 0.00032117851255553803, 'samples': 11980800, 'steps': 62399, 'loss/train': 1.1326847076416016} 08/31/2021 00:32:49 - INFO - __main__ - Step 62401: {'lr': 0.0003211734254280799, 'samples': 11980992, 'steps': 62400, 'loss/train': 0.942065417766571} 08/31/2021 00:32:49 - INFO - __main__ - Step 62402: {'lr': 0.00032116833826855215, 'samples': 11981184, 'steps': 62401, 'loss/train': 0.8016186952590942} 08/31/2021 00:32:51 - INFO - __main__ - Step 62403: {'lr': 0.000321163251076957, 'samples': 11981376, 'steps': 62402, 'loss/train': 1.391784906387329} 08/31/2021 00:32:51 - INFO - __main__ - Step 62404: {'lr': 0.00032115816385329675, 'samples': 11981568, 'steps': 62403, 'loss/train': 1.2102012634277344} 08/31/2021 00:32:52 - INFO - __main__ - Step 62405: {'lr': 0.00032115307659757374, 'samples': 11981760, 'steps': 62404, 'loss/train': 1.3298333883285522} 08/31/2021 00:32:52 - INFO - __main__ - Step 62406: {'lr': 0.0003211479893097903, 'samples': 11981952, 'steps': 62405, 'loss/train': 1.629575252532959} 08/31/2021 00:32:52 - INFO - __main__ - Step 62407: {'lr': 0.00032114290198994867, 'samples': 11982144, 'steps': 62406, 'loss/train': 1.2186905145645142} 08/31/2021 00:32:54 - INFO - __main__ - Step 62408: {'lr': 0.0003211378146380511, 'samples': 11982336, 'steps': 62407, 'loss/train': 1.3272461891174316} 08/31/2021 00:32:54 - INFO - __main__ - Step 62409: {'lr': 0.0003211327272541, 'samples': 11982528, 'steps': 62408, 'loss/train': 1.987450122833252} 08/31/2021 00:32:55 - INFO - __main__ - Step 62410: {'lr': 0.00032112763983809753, 'samples': 11982720, 'steps': 62409, 'loss/train': 1.3876640796661377} 08/31/2021 00:32:55 - INFO - __main__ - Step 62411: {'lr': 0.000321122552390046, 'samples': 11982912, 'steps': 62410, 'loss/train': 1.6095356941223145} 08/31/2021 00:32:55 - INFO - __main__ - Step 62412: {'lr': 0.0003211174649099479, 'samples': 11983104, 'steps': 62411, 'loss/train': 1.5027339458465576} 08/31/2021 00:32:56 - INFO - __main__ - Step 62413: {'lr': 0.0003211123773978052, 'samples': 11983296, 'steps': 62412, 'loss/train': 0.5556645393371582} 08/31/2021 00:32:58 - INFO - __main__ - Step 62414: {'lr': 0.00032110728985362044, 'samples': 11983488, 'steps': 62413, 'loss/train': 1.5068544149398804} 08/31/2021 00:32:59 - INFO - __main__ - Step 62415: {'lr': 0.0003211022022773958, 'samples': 11983680, 'steps': 62414, 'loss/train': 4.130444526672363} 08/31/2021 00:32:59 - INFO - __main__ - Step 62416: {'lr': 0.0003210971146691336, 'samples': 11983872, 'steps': 62415, 'loss/train': 0.942028820514679} 08/31/2021 00:32:59 - INFO - __main__ - Step 62417: {'lr': 0.0003210920270288362, 'samples': 11984064, 'steps': 62416, 'loss/train': 3.4694039821624756} 08/31/2021 00:33:00 - INFO - __main__ - Step 62418: {'lr': 0.00032108693935650577, 'samples': 11984256, 'steps': 62417, 'loss/train': 1.3769068717956543} 08/31/2021 00:33:00 - INFO - __main__ - Step 62419: {'lr': 0.0003210818516521447, 'samples': 11984448, 'steps': 62418, 'loss/train': 1.0316821336746216} 08/31/2021 00:33:02 - INFO - __main__ - Step 62420: {'lr': 0.00032107676391575525, 'samples': 11984640, 'steps': 62419, 'loss/train': 1.1173372268676758} 08/31/2021 00:33:02 - INFO - __main__ - Step 62421: {'lr': 0.0003210716761473397, 'samples': 11984832, 'steps': 62420, 'loss/train': 1.7497588396072388} 08/31/2021 00:33:02 - INFO - __main__ - Step 62422: {'lr': 0.0003210665883469003, 'samples': 11985024, 'steps': 62421, 'loss/train': 1.5741856098175049} 08/31/2021 00:33:03 - INFO - __main__ - Step 62423: {'lr': 0.0003210615005144394, 'samples': 11985216, 'steps': 62422, 'loss/train': 1.351287841796875} 08/31/2021 00:33:03 - INFO - __main__ - Step 62424: {'lr': 0.00032105641264995935, 'samples': 11985408, 'steps': 62423, 'loss/train': 1.294293999671936} 08/31/2021 00:33:05 - INFO - __main__ - Step 62425: {'lr': 0.00032105132475346233, 'samples': 11985600, 'steps': 62424, 'loss/train': 0.6380172371864319} 08/31/2021 00:33:06 - INFO - __main__ - Step 62426: {'lr': 0.0003210462368249507, 'samples': 11985792, 'steps': 62425, 'loss/train': 1.4184041023254395} 08/31/2021 00:33:06 - INFO - __main__ - Step 62427: {'lr': 0.0003210411488644267, 'samples': 11985984, 'steps': 62426, 'loss/train': 0.10395947843790054} 08/31/2021 00:33:06 - INFO - __main__ - Step 62428: {'lr': 0.00032103606087189267, 'samples': 11986176, 'steps': 62427, 'loss/train': 1.9007951021194458} 08/31/2021 00:33:07 - INFO - __main__ - Step 62429: {'lr': 0.0003210309728473509, 'samples': 11986368, 'steps': 62428, 'loss/train': 0.6135067939758301} 08/31/2021 00:33:07 - INFO - __main__ - Step 62430: {'lr': 0.0003210258847908036, 'samples': 11986560, 'steps': 62429, 'loss/train': 0.3704828917980194} 08/31/2021 00:33:08 - INFO - __main__ - Step 62431: {'lr': 0.00032102079670225325, 'samples': 11986752, 'steps': 62430, 'loss/train': 1.1132739782333374} 08/31/2021 00:33:09 - INFO - __main__ - Step 62432: {'lr': 0.00032101570858170196, 'samples': 11986944, 'steps': 62431, 'loss/train': 0.6501662731170654} 08/31/2021 00:33:09 - INFO - __main__ - Step 62433: {'lr': 0.0003210106204291521, 'samples': 11987136, 'steps': 62432, 'loss/train': 1.415274977684021} 08/31/2021 00:33:10 - INFO - __main__ - Step 62434: {'lr': 0.00032100553224460594, 'samples': 11987328, 'steps': 62433, 'loss/train': 1.5036729574203491} 08/31/2021 00:33:10 - INFO - __main__ - Step 62435: {'lr': 0.00032100044402806583, 'samples': 11987520, 'steps': 62434, 'loss/train': 1.226377248764038} 08/31/2021 00:33:12 - INFO - __main__ - Step 62436: {'lr': 0.00032099535577953395, 'samples': 11987712, 'steps': 62435, 'loss/train': 1.057408094406128} 08/31/2021 00:33:12 - INFO - __main__ - Step 62437: {'lr': 0.0003209902674990127, 'samples': 11987904, 'steps': 62436, 'loss/train': 2.017810821533203} 08/31/2021 00:33:12 - INFO - __main__ - Step 62438: {'lr': 0.00032098517918650426, 'samples': 11988096, 'steps': 62437, 'loss/train': 0.916313648223877} 08/31/2021 00:33:13 - INFO - __main__ - Step 62439: {'lr': 0.0003209800908420111, 'samples': 11988288, 'steps': 62438, 'loss/train': 1.043821096420288} 08/31/2021 00:33:13 - INFO - __main__ - Step 62440: {'lr': 0.00032097500246553535, 'samples': 11988480, 'steps': 62439, 'loss/train': 1.903957724571228} 08/31/2021 00:33:15 - INFO - __main__ - Step 62441: {'lr': 0.00032096991405707937, 'samples': 11988672, 'steps': 62440, 'loss/train': 0.9022694230079651} 08/31/2021 00:33:15 - INFO - __main__ - Step 62442: {'lr': 0.00032096482561664544, 'samples': 11988864, 'steps': 62441, 'loss/train': 1.0240991115570068} 08/31/2021 00:33:15 - INFO - __main__ - Step 62443: {'lr': 0.00032095973714423584, 'samples': 11989056, 'steps': 62442, 'loss/train': 1.525131106376648} 08/31/2021 00:33:16 - INFO - __main__ - Step 62444: {'lr': 0.00032095464863985285, 'samples': 11989248, 'steps': 62443, 'loss/train': 1.703437328338623} 08/31/2021 00:33:16 - INFO - __main__ - Step 62445: {'lr': 0.00032094956010349885, 'samples': 11989440, 'steps': 62444, 'loss/train': 1.6944148540496826} 08/31/2021 00:33:18 - INFO - __main__ - Step 62446: {'lr': 0.00032094447153517607, 'samples': 11989632, 'steps': 62445, 'loss/train': 0.9965673685073853} 08/31/2021 00:33:19 - INFO - __main__ - Step 62447: {'lr': 0.0003209393829348868, 'samples': 11989824, 'steps': 62446, 'loss/train': 1.5218570232391357} 08/31/2021 00:33:19 - INFO - __main__ - Step 62448: {'lr': 0.0003209342943026333, 'samples': 11990016, 'steps': 62447, 'loss/train': 1.1072171926498413} 08/31/2021 00:33:19 - INFO - __main__ - Step 62449: {'lr': 0.00032092920563841793, 'samples': 11990208, 'steps': 62448, 'loss/train': 1.3165018558502197} 08/31/2021 00:33:20 - INFO - __main__ - Step 62450: {'lr': 0.00032092411694224294, 'samples': 11990400, 'steps': 62449, 'loss/train': 0.9899671077728271} 08/31/2021 00:33:21 - INFO - __main__ - Step 62451: {'lr': 0.0003209190282141106, 'samples': 11990592, 'steps': 62450, 'loss/train': 1.3028563261032104} 08/31/2021 00:33:22 - INFO - __main__ - Step 62452: {'lr': 0.0003209139394540233, 'samples': 11990784, 'steps': 62451, 'loss/train': 1.647070050239563} 08/31/2021 00:33:22 - INFO - __main__ - Step 62453: {'lr': 0.00032090885066198336, 'samples': 11990976, 'steps': 62452, 'loss/train': 0.7299593687057495} 08/31/2021 00:33:22 - INFO - __main__ - Step 62454: {'lr': 0.00032090376183799285, 'samples': 11991168, 'steps': 62453, 'loss/train': 1.3813029527664185} 08/31/2021 00:33:23 - INFO - __main__ - Step 62455: {'lr': 0.0003208986729820542, 'samples': 11991360, 'steps': 62454, 'loss/train': 1.4660327434539795} 08/31/2021 00:33:23 - INFO - __main__ - Step 62456: {'lr': 0.0003208935840941697, 'samples': 11991552, 'steps': 62455, 'loss/train': 1.4173839092254639} 08/31/2021 00:33:25 - INFO - __main__ - Step 62457: {'lr': 0.0003208884951743417, 'samples': 11991744, 'steps': 62456, 'loss/train': 2.4223976135253906} 08/31/2021 00:33:25 - INFO - __main__ - Step 62458: {'lr': 0.00032088340622257245, 'samples': 11991936, 'steps': 62457, 'loss/train': 1.126222014427185} 08/31/2021 00:33:26 - INFO - __main__ - Step 62459: {'lr': 0.0003208783172388642, 'samples': 11992128, 'steps': 62458, 'loss/train': 1.5220664739608765} 08/31/2021 00:33:26 - INFO - __main__ - Step 62460: {'lr': 0.0003208732282232193, 'samples': 11992320, 'steps': 62459, 'loss/train': 1.6040441989898682} 08/31/2021 00:33:26 - INFO - __main__ - Step 62461: {'lr': 0.00032086813917563996, 'samples': 11992512, 'steps': 62460, 'loss/train': 0.6255930662155151} 08/31/2021 00:33:28 - INFO - __main__ - Step 62462: {'lr': 0.0003208630500961286, 'samples': 11992704, 'steps': 62461, 'loss/train': 1.7544448375701904} 08/31/2021 00:33:28 - INFO - __main__ - Step 62463: {'lr': 0.0003208579609846874, 'samples': 11992896, 'steps': 62462, 'loss/train': 1.5141531229019165} 08/31/2021 00:33:29 - INFO - __main__ - Step 62464: {'lr': 0.00032085287184131865, 'samples': 11993088, 'steps': 62463, 'loss/train': 1.2912439107894897} 08/31/2021 00:33:29 - INFO - __main__ - Step 62465: {'lr': 0.0003208477826660248, 'samples': 11993280, 'steps': 62464, 'loss/train': 1.3006219863891602} 08/31/2021 00:33:29 - INFO - __main__ - Step 62466: {'lr': 0.000320842693458808, 'samples': 11993472, 'steps': 62465, 'loss/train': 1.9204492568969727} 08/31/2021 00:33:31 - INFO - __main__ - Step 62467: {'lr': 0.00032083760421967053, 'samples': 11993664, 'steps': 62466, 'loss/train': 1.7747702598571777} 08/31/2021 00:33:31 - INFO - __main__ - Step 62468: {'lr': 0.00032083251494861474, 'samples': 11993856, 'steps': 62467, 'loss/train': 1.6982083320617676} 08/31/2021 00:33:32 - INFO - __main__ - Step 62469: {'lr': 0.00032082742564564296, 'samples': 11994048, 'steps': 62468, 'loss/train': 0.5948822498321533} 08/31/2021 00:33:32 - INFO - __main__ - Step 62470: {'lr': 0.0003208223363107573, 'samples': 11994240, 'steps': 62469, 'loss/train': 1.1360349655151367} 08/31/2021 00:33:32 - INFO - __main__ - Step 62471: {'lr': 0.00032081724694396033, 'samples': 11994432, 'steps': 62470, 'loss/train': 1.687681794166565} 08/31/2021 00:33:34 - INFO - __main__ - Step 62472: {'lr': 0.0003208121575452541, 'samples': 11994624, 'steps': 62471, 'loss/train': 1.6547898054122925} 08/31/2021 00:33:35 - INFO - __main__ - Step 62473: {'lr': 0.0003208070681146411, 'samples': 11994816, 'steps': 62472, 'loss/train': 1.0690028667449951} 08/31/2021 00:33:35 - INFO - __main__ - Step 62474: {'lr': 0.00032080197865212354, 'samples': 11995008, 'steps': 62473, 'loss/train': 0.5920546054840088} 08/31/2021 00:33:35 - INFO - __main__ - Step 62475: {'lr': 0.0003207968891577036, 'samples': 11995200, 'steps': 62474, 'loss/train': 1.0440638065338135} 08/31/2021 00:33:36 - INFO - __main__ - Step 62476: {'lr': 0.00032079179963138374, 'samples': 11995392, 'steps': 62475, 'loss/train': 1.184978723526001} 08/31/2021 00:33:36 - INFO - __main__ - Step 62477: {'lr': 0.0003207867100731661, 'samples': 11995584, 'steps': 62476, 'loss/train': 0.03803044185042381} 08/31/2021 00:33:36 - INFO - __main__ - Step 62478: {'lr': 0.00032078162048305314, 'samples': 11995776, 'steps': 62477, 'loss/train': 2.514477014541626} 08/31/2021 00:33:38 - INFO - __main__ - Step 62479: {'lr': 0.0003207765308610471, 'samples': 11995968, 'steps': 62478, 'loss/train': 0.603323757648468} 08/31/2021 00:33:39 - INFO - __main__ - Step 62480: {'lr': 0.00032077144120715026, 'samples': 11996160, 'steps': 62479, 'loss/train': 1.4672003984451294} 08/31/2021 00:33:39 - INFO - __main__ - Step 62481: {'lr': 0.0003207663515213648, 'samples': 11996352, 'steps': 62480, 'loss/train': 1.6976667642593384} 08/31/2021 00:33:40 - INFO - __main__ - Step 62482: {'lr': 0.0003207612618036932, 'samples': 11996544, 'steps': 62481, 'loss/train': 1.6099520921707153} 08/31/2021 00:33:40 - INFO - __main__ - Step 62483: {'lr': 0.0003207561720541376, 'samples': 11996736, 'steps': 62482, 'loss/train': 0.6157894134521484} 08/31/2021 00:33:42 - INFO - __main__ - Step 62484: {'lr': 0.0003207510822727004, 'samples': 11996928, 'steps': 62483, 'loss/train': 0.15832898020744324} 08/31/2021 00:33:42 - INFO - __main__ - Step 62485: {'lr': 0.0003207459924593839, 'samples': 11997120, 'steps': 62484, 'loss/train': 1.6116596460342407} 08/31/2021 00:33:42 - INFO - __main__ - Step 62486: {'lr': 0.0003207409026141903, 'samples': 11997312, 'steps': 62485, 'loss/train': 0.9123030304908752} 08/31/2021 00:33:43 - INFO - __main__ - Step 62487: {'lr': 0.0003207358127371219, 'samples': 11997504, 'steps': 62486, 'loss/train': 1.2929368019104004} 08/31/2021 00:33:43 - INFO - __main__ - Step 62488: {'lr': 0.00032073072282818107, 'samples': 11997696, 'steps': 62487, 'loss/train': 1.4872874021530151} 08/31/2021 00:33:43 - INFO - __main__ - Step 62489: {'lr': 0.00032072563288737006, 'samples': 11997888, 'steps': 62488, 'loss/train': 1.1812913417816162} 08/31/2021 00:33:45 - INFO - __main__ - Step 62490: {'lr': 0.00032072054291469116, 'samples': 11998080, 'steps': 62489, 'loss/train': 1.5985866785049438} 08/31/2021 00:33:45 - INFO - __main__ - Step 62491: {'lr': 0.0003207154529101467, 'samples': 11998272, 'steps': 62490, 'loss/train': 1.2499231100082397} 08/31/2021 00:33:46 - INFO - __main__ - Step 62492: {'lr': 0.0003207103628737389, 'samples': 11998464, 'steps': 62491, 'loss/train': 1.017257571220398} 08/31/2021 00:33:46 - INFO - __main__ - Step 62493: {'lr': 0.00032070527280547023, 'samples': 11998656, 'steps': 62492, 'loss/train': 1.408103108406067} 08/31/2021 00:33:46 - INFO - __main__ - Step 62494: {'lr': 0.00032070018270534276, 'samples': 11998848, 'steps': 62493, 'loss/train': 1.299150824546814} 08/31/2021 00:33:48 - INFO - __main__ - Step 62495: {'lr': 0.0003206950925733589, 'samples': 11999040, 'steps': 62494, 'loss/train': 0.37409114837646484} 08/31/2021 00:33:49 - INFO - __main__ - Step 62496: {'lr': 0.0003206900024095208, 'samples': 11999232, 'steps': 62495, 'loss/train': 0.8581941723823547} 08/31/2021 00:33:49 - INFO - __main__ - Step 62497: {'lr': 0.00032068491221383106, 'samples': 11999424, 'steps': 62496, 'loss/train': 1.3904615640640259} 08/31/2021 00:33:49 - INFO - __main__ - Step 62498: {'lr': 0.0003206798219862917, 'samples': 11999616, 'steps': 62497, 'loss/train': 0.9055432677268982} 08/31/2021 00:33:50 - INFO - __main__ - Step 62499: {'lr': 0.0003206747317269051, 'samples': 11999808, 'steps': 62498, 'loss/train': 1.2075295448303223} 08/31/2021 00:33:51 - INFO - __main__ - Step 62500: {'lr': 0.0003206696414356736, 'samples': 12000000, 'steps': 62499, 'loss/train': 0.04338771104812622} 08/31/2021 00:33:52 - INFO - __main__ - Step 62501: {'lr': 0.0003206645511125995, 'samples': 12000192, 'steps': 62500, 'loss/train': 1.9419785737991333} 08/31/2021 00:33:52 - INFO - __main__ - Step 62502: {'lr': 0.00032065946075768493, 'samples': 12000384, 'steps': 62501, 'loss/train': 1.0014253854751587} 08/31/2021 00:33:52 - INFO - __main__ - Step 62503: {'lr': 0.0003206543703709323, 'samples': 12000576, 'steps': 62502, 'loss/train': 1.0725122690200806} 08/31/2021 00:33:53 - INFO - __main__ - Step 62504: {'lr': 0.00032064927995234397, 'samples': 12000768, 'steps': 62503, 'loss/train': 1.9718879461288452} 08/31/2021 00:33:55 - INFO - __main__ - Step 62505: {'lr': 0.0003206441895019221, 'samples': 12000960, 'steps': 62504, 'loss/train': 1.9160226583480835} 08/31/2021 00:33:55 - INFO - __main__ - Step 62506: {'lr': 0.0003206390990196691, 'samples': 12001152, 'steps': 62505, 'loss/train': 1.1430660486221313} 08/31/2021 00:33:55 - INFO - __main__ - Step 62507: {'lr': 0.0003206340085055872, 'samples': 12001344, 'steps': 62506, 'loss/train': 1.2838515043258667} 08/31/2021 00:33:56 - INFO - __main__ - Step 62508: {'lr': 0.0003206289179596787, 'samples': 12001536, 'steps': 62507, 'loss/train': 0.3246062099933624} 08/31/2021 00:33:56 - INFO - __main__ - Step 62509: {'lr': 0.00032062382738194586, 'samples': 12001728, 'steps': 62508, 'loss/train': 1.5248409509658813} 08/31/2021 00:33:57 - INFO - __main__ - Step 62510: {'lr': 0.0003206187367723911, 'samples': 12001920, 'steps': 62509, 'loss/train': 1.8244946002960205} 08/31/2021 00:33:58 - INFO - __main__ - Step 62511: {'lr': 0.0003206136461310165, 'samples': 12002112, 'steps': 62510, 'loss/train': 2.120310068130493} 08/31/2021 00:33:58 - INFO - __main__ - Step 62512: {'lr': 0.0003206085554578246, 'samples': 12002304, 'steps': 62511, 'loss/train': 1.3803101778030396} 08/31/2021 00:33:59 - INFO - __main__ - Step 62513: {'lr': 0.00032060346475281754, 'samples': 12002496, 'steps': 62512, 'loss/train': 1.62235426902771} 08/31/2021 00:33:59 - INFO - __main__ - Step 62514: {'lr': 0.0003205983740159976, 'samples': 12002688, 'steps': 62513, 'loss/train': 1.267794132232666} 08/31/2021 00:34:00 - INFO - __main__ - Step 62515: {'lr': 0.00032059328324736717, 'samples': 12002880, 'steps': 62514, 'loss/train': 0.7777343392372131} 08/31/2021 00:34:01 - INFO - __main__ - Step 62516: {'lr': 0.00032058819244692847, 'samples': 12003072, 'steps': 62515, 'loss/train': 1.5464674234390259} 08/31/2021 00:34:01 - INFO - __main__ - Step 62517: {'lr': 0.00032058310161468383, 'samples': 12003264, 'steps': 62516, 'loss/train': 0.6582445502281189} 08/31/2021 00:34:02 - INFO - __main__ - Step 62518: {'lr': 0.0003205780107506356, 'samples': 12003456, 'steps': 62517, 'loss/train': 1.5755747556686401} 08/31/2021 00:34:02 - INFO - __main__ - Step 62519: {'lr': 0.00032057291985478596, 'samples': 12003648, 'steps': 62518, 'loss/train': 2.3988945484161377} 08/31/2021 00:34:03 - INFO - __main__ - Step 62520: {'lr': 0.0003205678289271372, 'samples': 12003840, 'steps': 62519, 'loss/train': 0.5072124600410461} 08/31/2021 00:34:04 - INFO - __main__ - Step 62521: {'lr': 0.00032056273796769177, 'samples': 12004032, 'steps': 62520, 'loss/train': 0.06152816489338875} 08/31/2021 00:34:04 - INFO - __main__ - Step 62522: {'lr': 0.00032055764697645176, 'samples': 12004224, 'steps': 62521, 'loss/train': 1.0075045824050903} 08/31/2021 00:34:05 - INFO - __main__ - Step 62523: {'lr': 0.0003205525559534196, 'samples': 12004416, 'steps': 62522, 'loss/train': 0.8002643585205078} 08/31/2021 00:34:05 - INFO - __main__ - Step 62524: {'lr': 0.00032054746489859756, 'samples': 12004608, 'steps': 62523, 'loss/train': 1.33907151222229} 08/31/2021 00:34:05 - INFO - __main__ - Step 62525: {'lr': 0.0003205423738119879, 'samples': 12004800, 'steps': 62524, 'loss/train': 1.4862350225448608} 08/31/2021 00:34:07 - INFO - __main__ - Step 62526: {'lr': 0.00032053728269359295, 'samples': 12004992, 'steps': 62525, 'loss/train': 1.1594805717468262} 08/31/2021 00:34:07 - INFO - __main__ - Step 62527: {'lr': 0.00032053219154341497, 'samples': 12005184, 'steps': 62526, 'loss/train': 0.9267292022705078} 08/31/2021 00:34:08 - INFO - __main__ - Step 62528: {'lr': 0.00032052710036145626, 'samples': 12005376, 'steps': 62527, 'loss/train': 2.5356733798980713} 08/31/2021 00:34:08 - INFO - __main__ - Step 62529: {'lr': 0.0003205220091477191, 'samples': 12005568, 'steps': 62528, 'loss/train': 0.9879505038261414} 08/31/2021 00:34:08 - INFO - __main__ - Step 62530: {'lr': 0.0003205169179022059, 'samples': 12005760, 'steps': 62529, 'loss/train': 0.8701989054679871} 08/31/2021 00:34:10 - INFO - __main__ - Step 62531: {'lr': 0.00032051182662491885, 'samples': 12005952, 'steps': 62530, 'loss/train': 1.1418880224227905} 08/31/2021 00:34:10 - INFO - __main__ - Step 62532: {'lr': 0.00032050673531586025, 'samples': 12006144, 'steps': 62531, 'loss/train': 0.7714837193489075} 08/31/2021 00:34:11 - INFO - __main__ - Step 62533: {'lr': 0.0003205016439750323, 'samples': 12006336, 'steps': 62532, 'loss/train': 0.7260352373123169} 08/31/2021 00:34:11 - INFO - __main__ - Step 62534: {'lr': 0.0003204965526024375, 'samples': 12006528, 'steps': 62533, 'loss/train': 0.9967209100723267} 08/31/2021 00:34:11 - INFO - __main__ - Step 62535: {'lr': 0.00032049146119807816, 'samples': 12006720, 'steps': 62534, 'loss/train': 1.415051817893982} 08/31/2021 00:34:13 - INFO - __main__ - Step 62536: {'lr': 0.0003204863697619563, 'samples': 12006912, 'steps': 62535, 'loss/train': 1.6937724351882935} 08/31/2021 00:34:13 - INFO - __main__ - Step 62537: {'lr': 0.0003204812782940744, 'samples': 12007104, 'steps': 62536, 'loss/train': 0.818937361240387} 08/31/2021 00:34:14 - INFO - __main__ - Step 62538: {'lr': 0.00032047618679443467, 'samples': 12007296, 'steps': 62537, 'loss/train': 0.7607395052909851} 08/31/2021 00:34:14 - INFO - __main__ - Step 62539: {'lr': 0.00032047109526303944, 'samples': 12007488, 'steps': 62538, 'loss/train': 0.8084056973457336} 08/31/2021 00:34:14 - INFO - __main__ - Step 62540: {'lr': 0.0003204660036998911, 'samples': 12007680, 'steps': 62539, 'loss/train': 1.3630644083023071} 08/31/2021 00:34:16 - INFO - __main__ - Step 62541: {'lr': 0.0003204609121049919, 'samples': 12007872, 'steps': 62540, 'loss/train': 1.2600927352905273} 08/31/2021 00:34:16 - INFO - __main__ - Step 62542: {'lr': 0.00032045582047834405, 'samples': 12008064, 'steps': 62541, 'loss/train': 1.3689217567443848} 08/31/2021 00:34:17 - INFO - __main__ - Step 62543: {'lr': 0.00032045072881994993, 'samples': 12008256, 'steps': 62542, 'loss/train': 1.6987597942352295} 08/31/2021 00:34:17 - INFO - __main__ - Step 62544: {'lr': 0.00032044563712981173, 'samples': 12008448, 'steps': 62543, 'loss/train': 1.538292407989502} 08/31/2021 00:34:17 - INFO - __main__ - Step 62545: {'lr': 0.00032044054540793183, 'samples': 12008640, 'steps': 62544, 'loss/train': 1.2919858694076538} 08/31/2021 00:34:18 - INFO - __main__ - Step 62546: {'lr': 0.00032043545365431246, 'samples': 12008832, 'steps': 62545, 'loss/train': 1.2736083269119263} 08/31/2021 00:34:19 - INFO - __main__ - Step 62547: {'lr': 0.00032043036186895615, 'samples': 12009024, 'steps': 62546, 'loss/train': 1.1934738159179688} 08/31/2021 00:34:20 - INFO - __main__ - Step 62548: {'lr': 0.0003204252700518648, 'samples': 12009216, 'steps': 62547, 'loss/train': 0.02829975076019764} 08/31/2021 00:34:20 - INFO - __main__ - Step 62549: {'lr': 0.00032042017820304105, 'samples': 12009408, 'steps': 62548, 'loss/train': 1.6030149459838867} 08/31/2021 00:34:21 - INFO - __main__ - Step 62550: {'lr': 0.000320415086322487, 'samples': 12009600, 'steps': 62549, 'loss/train': 1.1733958721160889} 08/31/2021 00:34:21 - INFO - __main__ - Step 62551: {'lr': 0.00032040999441020497, 'samples': 12009792, 'steps': 62550, 'loss/train': 1.2897717952728271} 08/31/2021 00:34:21 - INFO - __main__ - Step 62552: {'lr': 0.00032040490246619725, 'samples': 12009984, 'steps': 62551, 'loss/train': 0.3849668800830841} 08/31/2021 00:34:23 - INFO - __main__ - Step 62553: {'lr': 0.0003203998104904663, 'samples': 12010176, 'steps': 62552, 'loss/train': 0.8217567205429077} 08/31/2021 00:34:23 - INFO - __main__ - Step 62554: {'lr': 0.0003203947184830142, 'samples': 12010368, 'steps': 62553, 'loss/train': 1.3254585266113281} 08/31/2021 00:34:24 - INFO - __main__ - Step 62555: {'lr': 0.0003203896264438433, 'samples': 12010560, 'steps': 62554, 'loss/train': 1.1755653619766235} 08/31/2021 00:34:24 - INFO - __main__ - Step 62556: {'lr': 0.00032038453437295593, 'samples': 12010752, 'steps': 62555, 'loss/train': 0.9656534194946289} 08/31/2021 00:34:24 - INFO - __main__ - Step 62557: {'lr': 0.00032037944227035443, 'samples': 12010944, 'steps': 62556, 'loss/train': 0.7317005395889282} 08/31/2021 00:34:26 - INFO - __main__ - Step 62558: {'lr': 0.000320374350136041, 'samples': 12011136, 'steps': 62557, 'loss/train': 0.8459063768386841} 08/31/2021 00:34:27 - INFO - __main__ - Step 62559: {'lr': 0.00032036925797001794, 'samples': 12011328, 'steps': 62558, 'loss/train': 1.3803606033325195} 08/31/2021 00:34:27 - INFO - __main__ - Step 62560: {'lr': 0.00032036416577228767, 'samples': 12011520, 'steps': 62559, 'loss/train': 1.3520740270614624} 08/31/2021 00:34:28 - INFO - __main__ - Step 62561: {'lr': 0.0003203590735428523, 'samples': 12011712, 'steps': 62560, 'loss/train': 1.0997049808502197} 08/31/2021 00:34:28 - INFO - __main__ - Step 62562: {'lr': 0.0003203539812817143, 'samples': 12011904, 'steps': 62561, 'loss/train': 1.4708434343338013} 08/31/2021 00:34:29 - INFO - __main__ - Step 62563: {'lr': 0.0003203488889888758, 'samples': 12012096, 'steps': 62562, 'loss/train': 1.0035003423690796} 08/31/2021 00:34:30 - INFO - __main__ - Step 62564: {'lr': 0.0003203437966643392, 'samples': 12012288, 'steps': 62563, 'loss/train': 0.8508998155593872} 08/31/2021 00:34:30 - INFO - __main__ - Step 62565: {'lr': 0.00032033870430810677, 'samples': 12012480, 'steps': 62564, 'loss/train': 0.35720741748809814} 08/31/2021 00:34:31 - INFO - __main__ - Step 62566: {'lr': 0.0003203336119201808, 'samples': 12012672, 'steps': 62565, 'loss/train': 2.228668212890625} 08/31/2021 00:34:31 - INFO - __main__ - Step 62567: {'lr': 0.00032032851950056376, 'samples': 12012864, 'steps': 62566, 'loss/train': 1.440873384475708} 08/31/2021 00:34:31 - INFO - __main__ - Step 62568: {'lr': 0.0003203234270492575, 'samples': 12013056, 'steps': 62567, 'loss/train': 1.1480019092559814} 08/31/2021 00:34:33 - INFO - __main__ - Step 62569: {'lr': 0.0003203183345662648, 'samples': 12013248, 'steps': 62568, 'loss/train': 0.560843825340271} 08/31/2021 00:34:33 - INFO - __main__ - Step 62570: {'lr': 0.0003203132420515876, 'samples': 12013440, 'steps': 62569, 'loss/train': 1.62360417842865} 08/31/2021 00:34:34 - INFO - __main__ - Step 62571: {'lr': 0.0003203081495052284, 'samples': 12013632, 'steps': 62570, 'loss/train': 1.0680067539215088} 08/31/2021 00:34:34 - INFO - __main__ - Step 62572: {'lr': 0.00032030305692718944, 'samples': 12013824, 'steps': 62571, 'loss/train': 0.5545658469200134} 08/31/2021 00:34:34 - INFO - __main__ - Step 62573: {'lr': 0.000320297964317473, 'samples': 12014016, 'steps': 62572, 'loss/train': 1.341873288154602} 08/31/2021 00:34:36 - INFO - __main__ - Step 62574: {'lr': 0.0003202928716760814, 'samples': 12014208, 'steps': 62573, 'loss/train': 1.3625975847244263} 08/31/2021 00:34:36 - INFO - __main__ - Step 62575: {'lr': 0.0003202877790030169, 'samples': 12014400, 'steps': 62574, 'loss/train': 0.9638200402259827} 08/31/2021 00:34:37 - INFO - __main__ - Step 62576: {'lr': 0.00032028268629828184, 'samples': 12014592, 'steps': 62575, 'loss/train': 1.193023920059204} 08/31/2021 00:34:37 - INFO - __main__ - Step 62577: {'lr': 0.0003202775935618784, 'samples': 12014784, 'steps': 62576, 'loss/train': 1.5209935903549194} 08/31/2021 00:34:37 - INFO - __main__ - Step 62578: {'lr': 0.000320272500793809, 'samples': 12014976, 'steps': 62577, 'loss/train': 1.1966955661773682} 08/31/2021 00:34:39 - INFO - __main__ - Step 62579: {'lr': 0.0003202674079940759, 'samples': 12015168, 'steps': 62578, 'loss/train': 1.8025683164596558} 08/31/2021 00:34:39 - INFO - __main__ - Step 62580: {'lr': 0.00032026231516268147, 'samples': 12015360, 'steps': 62579, 'loss/train': 1.439157247543335} 08/31/2021 00:34:39 - INFO - __main__ - Step 62581: {'lr': 0.0003202572222996278, 'samples': 12015552, 'steps': 62580, 'loss/train': 1.405953288078308} 08/31/2021 00:34:40 - INFO - __main__ - Step 62582: {'lr': 0.0003202521294049174, 'samples': 12015744, 'steps': 62581, 'loss/train': 0.8921076059341431} 08/31/2021 00:34:40 - INFO - __main__ - Step 62583: {'lr': 0.0003202470364785524, 'samples': 12015936, 'steps': 62582, 'loss/train': 1.6531615257263184} 08/31/2021 00:34:42 - INFO - __main__ - Step 62584: {'lr': 0.0003202419435205352, 'samples': 12016128, 'steps': 62583, 'loss/train': 1.507846713066101} 08/31/2021 00:34:42 - INFO - __main__ - Step 62585: {'lr': 0.0003202368505308681, 'samples': 12016320, 'steps': 62584, 'loss/train': 1.011644721031189} 08/31/2021 00:34:43 - INFO - __main__ - Step 62586: {'lr': 0.0003202317575095533, 'samples': 12016512, 'steps': 62585, 'loss/train': 1.592368245124817} 08/31/2021 00:34:43 - INFO - __main__ - Step 62587: {'lr': 0.0003202266644565932, 'samples': 12016704, 'steps': 62586, 'loss/train': 1.9229366779327393} 08/31/2021 00:34:43 - INFO - __main__ - Step 62588: {'lr': 0.00032022157137199, 'samples': 12016896, 'steps': 62587, 'loss/train': 1.7107125520706177} 08/31/2021 00:34:45 - INFO - __main__ - Step 62589: {'lr': 0.0003202164782557461, 'samples': 12017088, 'steps': 62588, 'loss/train': 1.551964282989502} 08/31/2021 00:34:46 - INFO - __main__ - Step 62590: {'lr': 0.0003202113851078637, 'samples': 12017280, 'steps': 62589, 'loss/train': 1.4571621417999268} 08/31/2021 00:34:46 - INFO - __main__ - Step 62591: {'lr': 0.0003202062919283452, 'samples': 12017472, 'steps': 62590, 'loss/train': 0.02557920664548874} 08/31/2021 00:34:46 - INFO - __main__ - Step 62592: {'lr': 0.00032020119871719276, 'samples': 12017664, 'steps': 62591, 'loss/train': 1.1237046718597412} 08/31/2021 00:34:47 - INFO - __main__ - Step 62593: {'lr': 0.00032019610547440874, 'samples': 12017856, 'steps': 62592, 'loss/train': 0.7564767003059387} 08/31/2021 00:34:47 - INFO - __main__ - Step 62594: {'lr': 0.0003201910121999955, 'samples': 12018048, 'steps': 62593, 'loss/train': 0.06231416389346123} 08/31/2021 00:34:49 - INFO - __main__ - Step 62595: {'lr': 0.0003201859188939552, 'samples': 12018240, 'steps': 62594, 'loss/train': 1.4566150903701782} 08/31/2021 00:34:49 - INFO - __main__ - Step 62596: {'lr': 0.00032018082555629025, 'samples': 12018432, 'steps': 62595, 'loss/train': 1.2269978523254395} 08/31/2021 00:34:49 - INFO - __main__ - Step 62597: {'lr': 0.0003201757321870029, 'samples': 12018624, 'steps': 62596, 'loss/train': 1.6689963340759277} 08/31/2021 00:34:50 - INFO - __main__ - Step 62598: {'lr': 0.0003201706387860954, 'samples': 12018816, 'steps': 62597, 'loss/train': 1.5077959299087524} 08/31/2021 00:34:50 - INFO - __main__ - Step 62599: {'lr': 0.00032016554535357016, 'samples': 12019008, 'steps': 62598, 'loss/train': 0.8628247380256653} 08/31/2021 00:34:50 - INFO - __main__ - Step 62600: {'lr': 0.00032016045188942946, 'samples': 12019200, 'steps': 62599, 'loss/train': 1.1048557758331299} 08/31/2021 00:34:52 - INFO - __main__ - Step 62601: {'lr': 0.00032015535839367544, 'samples': 12019392, 'steps': 62600, 'loss/train': 1.550207257270813} 08/31/2021 00:34:52 - INFO - __main__ - Step 62602: {'lr': 0.0003201502648663105, 'samples': 12019584, 'steps': 62601, 'loss/train': 0.8444976210594177} 08/31/2021 00:34:53 - INFO - __main__ - Step 62603: {'lr': 0.00032014517130733695, 'samples': 12019776, 'steps': 62602, 'loss/train': 1.2342108488082886} 08/31/2021 00:34:53 - INFO - __main__ - Step 62604: {'lr': 0.0003201400777167571, 'samples': 12019968, 'steps': 62603, 'loss/train': 1.325211524963379} 08/31/2021 00:34:53 - INFO - __main__ - Step 62605: {'lr': 0.00032013498409457316, 'samples': 12020160, 'steps': 62604, 'loss/train': 0.5679945945739746} 08/31/2021 00:34:55 - INFO - __main__ - Step 62606: {'lr': 0.00032012989044078745, 'samples': 12020352, 'steps': 62605, 'loss/train': 1.3868651390075684} 08/31/2021 00:34:55 - INFO - __main__ - Step 62607: {'lr': 0.0003201247967554024, 'samples': 12020544, 'steps': 62606, 'loss/train': 1.60707426071167} 08/31/2021 00:34:56 - INFO - __main__ - Step 62608: {'lr': 0.0003201197030384201, 'samples': 12020736, 'steps': 62607, 'loss/train': 1.2731916904449463} 08/31/2021 00:34:56 - INFO - __main__ - Step 62609: {'lr': 0.00032011460928984306, 'samples': 12020928, 'steps': 62608, 'loss/train': 1.329412579536438} 08/31/2021 00:34:56 - INFO - __main__ - Step 62610: {'lr': 0.00032010951550967337, 'samples': 12021120, 'steps': 62609, 'loss/train': 1.6290414333343506} 08/31/2021 00:34:59 - INFO - __main__ - Step 62611: {'lr': 0.00032010442169791344, 'samples': 12021312, 'steps': 62610, 'loss/train': 0.957778811454773} 08/31/2021 00:34:59 - INFO - __main__ - Step 62612: {'lr': 0.0003200993278545655, 'samples': 12021504, 'steps': 62611, 'loss/train': 0.962286651134491} 08/31/2021 00:35:00 - INFO - __main__ - Step 62613: {'lr': 0.0003200942339796319, 'samples': 12021696, 'steps': 62612, 'loss/train': 0.02106519602239132} 08/31/2021 00:35:00 - INFO - __main__ - Step 62614: {'lr': 0.000320089140073115, 'samples': 12021888, 'steps': 62613, 'loss/train': 1.339984655380249} 08/31/2021 00:35:00 - INFO - __main__ - Step 62615: {'lr': 0.00032008404613501697, 'samples': 12022080, 'steps': 62614, 'loss/train': 1.2713451385498047} 08/31/2021 00:35:01 - INFO - __main__ - Step 62616: {'lr': 0.0003200789521653401, 'samples': 12022272, 'steps': 62615, 'loss/train': 2.040888547897339} 08/31/2021 00:35:02 - INFO - __main__ - Step 62617: {'lr': 0.00032007385816408676, 'samples': 12022464, 'steps': 62616, 'loss/train': 1.1385481357574463} 08/31/2021 00:35:03 - INFO - __main__ - Step 62618: {'lr': 0.00032006876413125926, 'samples': 12022656, 'steps': 62617, 'loss/train': 1.3949686288833618} 08/31/2021 00:35:03 - INFO - __main__ - Step 62619: {'lr': 0.0003200636700668598, 'samples': 12022848, 'steps': 62618, 'loss/train': 0.07499361783266068} 08/31/2021 00:35:04 - INFO - __main__ - Step 62620: {'lr': 0.00032005857597089074, 'samples': 12023040, 'steps': 62619, 'loss/train': 1.4381489753723145} 08/31/2021 00:35:04 - INFO - __main__ - Step 62621: {'lr': 0.00032005348184335443, 'samples': 12023232, 'steps': 62620, 'loss/train': 1.3254919052124023} 08/31/2021 00:35:06 - INFO - __main__ - Step 62622: {'lr': 0.00032004838768425305, 'samples': 12023424, 'steps': 62621, 'loss/train': 1.503236174583435} 08/31/2021 00:35:06 - INFO - __main__ - Step 62623: {'lr': 0.00032004329349358897, 'samples': 12023616, 'steps': 62622, 'loss/train': 1.5493378639221191} 08/31/2021 00:35:06 - INFO - __main__ - Step 62624: {'lr': 0.0003200381992713644, 'samples': 12023808, 'steps': 62623, 'loss/train': 0.8783850073814392} 08/31/2021 00:35:07 - INFO - __main__ - Step 62625: {'lr': 0.00032003310501758177, 'samples': 12024000, 'steps': 62624, 'loss/train': 1.5466567277908325} 08/31/2021 00:35:07 - INFO - __main__ - Step 62626: {'lr': 0.00032002801073224325, 'samples': 12024192, 'steps': 62625, 'loss/train': 0.9997826814651489} 08/31/2021 00:35:08 - INFO - __main__ - Step 62627: {'lr': 0.00032002291641535126, 'samples': 12024384, 'steps': 62626, 'loss/train': 1.7253925800323486} 08/31/2021 00:35:09 - INFO - __main__ - Step 62628: {'lr': 0.000320017822066908, 'samples': 12024576, 'steps': 62627, 'loss/train': 0.6808083653450012} 08/31/2021 00:35:10 - INFO - __main__ - Step 62629: {'lr': 0.00032001272768691577, 'samples': 12024768, 'steps': 62628, 'loss/train': 1.548822045326233} 08/31/2021 00:35:10 - INFO - __main__ - Step 62630: {'lr': 0.00032000763327537683, 'samples': 12024960, 'steps': 62629, 'loss/train': 1.083798885345459} 08/31/2021 00:35:10 - INFO - __main__ - Step 62631: {'lr': 0.00032000253883229357, 'samples': 12025152, 'steps': 62630, 'loss/train': 0.036119237542152405} 08/31/2021 00:35:11 - INFO - __main__ - Step 62632: {'lr': 0.0003199974443576683, 'samples': 12025344, 'steps': 62631, 'loss/train': 1.076228141784668} 08/31/2021 00:35:12 - INFO - __main__ - Step 62633: {'lr': 0.00031999234985150314, 'samples': 12025536, 'steps': 62632, 'loss/train': 1.585218071937561} 08/31/2021 00:35:13 - INFO - __main__ - Step 62634: {'lr': 0.0003199872553138007, 'samples': 12025728, 'steps': 62633, 'loss/train': 1.8292737007141113} 08/31/2021 00:35:13 - INFO - __main__ - Step 62635: {'lr': 0.00031998216074456296, 'samples': 12025920, 'steps': 62634, 'loss/train': 0.8081755638122559} 08/31/2021 00:35:13 - INFO - __main__ - Step 62636: {'lr': 0.00031997706614379236, 'samples': 12026112, 'steps': 62635, 'loss/train': 0.802006721496582} 08/31/2021 00:35:14 - INFO - __main__ - Step 62637: {'lr': 0.00031997197151149116, 'samples': 12026304, 'steps': 62636, 'loss/train': 1.942676305770874} 08/31/2021 00:35:15 - INFO - __main__ - Step 62638: {'lr': 0.0003199668768476617, 'samples': 12026496, 'steps': 62637, 'loss/train': 1.699179768562317} 08/31/2021 00:35:16 - INFO - __main__ - Step 62639: {'lr': 0.0003199617821523062, 'samples': 12026688, 'steps': 62638, 'loss/train': 1.280243158340454} 08/31/2021 00:35:16 - INFO - __main__ - Step 62640: {'lr': 0.000319956687425427, 'samples': 12026880, 'steps': 62639, 'loss/train': 5.91710090637207} 08/31/2021 00:35:17 - INFO - __main__ - Step 62641: {'lr': 0.00031995159266702647, 'samples': 12027072, 'steps': 62640, 'loss/train': 1.5326464176177979} 08/31/2021 00:35:17 - INFO - __main__ - Step 62642: {'lr': 0.0003199464978771067, 'samples': 12027264, 'steps': 62641, 'loss/train': 0.5459507703781128} 08/31/2021 00:35:17 - INFO - __main__ - Step 62643: {'lr': 0.0003199414030556702, 'samples': 12027456, 'steps': 62642, 'loss/train': 0.2092093676328659} 08/31/2021 00:35:19 - INFO - __main__ - Step 62644: {'lr': 0.00031993630820271925, 'samples': 12027648, 'steps': 62643, 'loss/train': 0.7602234482765198} 08/31/2021 00:35:19 - INFO - __main__ - Step 62645: {'lr': 0.000319931213318256, 'samples': 12027840, 'steps': 62644, 'loss/train': 0.8798290491104126} 08/31/2021 00:35:20 - INFO - __main__ - Step 62646: {'lr': 0.0003199261184022828, 'samples': 12028032, 'steps': 62645, 'loss/train': 1.1057913303375244} 08/31/2021 00:35:20 - INFO - __main__ - Step 62647: {'lr': 0.000319921023454802, 'samples': 12028224, 'steps': 62646, 'loss/train': 0.6323972344398499} 08/31/2021 00:35:20 - INFO - __main__ - Step 62648: {'lr': 0.0003199159284758159, 'samples': 12028416, 'steps': 62647, 'loss/train': 0.7204388380050659} 08/31/2021 00:35:22 - INFO - __main__ - Step 62649: {'lr': 0.0003199108334653267, 'samples': 12028608, 'steps': 62648, 'loss/train': 1.5668363571166992} 08/31/2021 00:35:22 - INFO - __main__ - Step 62650: {'lr': 0.0003199057384233368, 'samples': 12028800, 'steps': 62649, 'loss/train': 1.8393142223358154} 08/31/2021 00:35:23 - INFO - __main__ - Step 62651: {'lr': 0.0003199006433498484, 'samples': 12028992, 'steps': 62650, 'loss/train': 1.5853873491287231} 08/31/2021 00:35:23 - INFO - __main__ - Step 62652: {'lr': 0.0003198955482448639, 'samples': 12029184, 'steps': 62651, 'loss/train': 1.308750033378601} 08/31/2021 00:35:23 - INFO - __main__ - Step 62653: {'lr': 0.0003198904531083856, 'samples': 12029376, 'steps': 62652, 'loss/train': 0.138444185256958} 08/31/2021 00:35:25 - INFO - __main__ - Step 62654: {'lr': 0.0003198853579404157, 'samples': 12029568, 'steps': 62653, 'loss/train': 1.2313300371170044} 08/31/2021 00:35:25 - INFO - __main__ - Step 62655: {'lr': 0.0003198802627409565, 'samples': 12029760, 'steps': 62654, 'loss/train': 1.3510966300964355} 08/31/2021 00:35:26 - INFO - __main__ - Step 62656: {'lr': 0.0003198751675100103, 'samples': 12029952, 'steps': 62655, 'loss/train': 0.7087931632995605} 08/31/2021 00:35:26 - INFO - __main__ - Step 62657: {'lr': 0.0003198700722475795, 'samples': 12030144, 'steps': 62656, 'loss/train': 1.417109489440918} 08/31/2021 00:35:26 - INFO - __main__ - Step 62658: {'lr': 0.00031986497695366624, 'samples': 12030336, 'steps': 62657, 'loss/train': 1.3882989883422852} 08/31/2021 00:35:28 - INFO - __main__ - Step 62659: {'lr': 0.000319859881628273, 'samples': 12030528, 'steps': 62658, 'loss/train': 1.219707727432251} 08/31/2021 00:35:28 - INFO - __main__ - Step 62660: {'lr': 0.0003198547862714019, 'samples': 12030720, 'steps': 62659, 'loss/train': 1.7148804664611816} 08/31/2021 00:35:29 - INFO - __main__ - Step 62661: {'lr': 0.0003198496908830554, 'samples': 12030912, 'steps': 62660, 'loss/train': 1.8730792999267578} 08/31/2021 00:35:29 - INFO - __main__ - Step 62662: {'lr': 0.00031984459546323564, 'samples': 12031104, 'steps': 62661, 'loss/train': 1.2514723539352417} 08/31/2021 00:35:29 - INFO - __main__ - Step 62663: {'lr': 0.000319839500011945, 'samples': 12031296, 'steps': 62662, 'loss/train': 1.6510376930236816} 08/31/2021 00:35:31 - INFO - __main__ - Step 62664: {'lr': 0.0003198344045291857, 'samples': 12031488, 'steps': 62663, 'loss/train': 1.3031202554702759} 08/31/2021 00:35:31 - INFO - __main__ - Step 62665: {'lr': 0.00031982930901496015, 'samples': 12031680, 'steps': 62664, 'loss/train': 1.0028048753738403} 08/31/2021 00:35:32 - INFO - __main__ - Step 62666: {'lr': 0.0003198242134692706, 'samples': 12031872, 'steps': 62665, 'loss/train': 1.1802505254745483} 08/31/2021 00:35:32 - INFO - __main__ - Step 62667: {'lr': 0.0003198191178921193, 'samples': 12032064, 'steps': 62666, 'loss/train': 1.3997470140457153} 08/31/2021 00:35:32 - INFO - __main__ - Step 62668: {'lr': 0.00031981402228350867, 'samples': 12032256, 'steps': 62667, 'loss/train': 1.1307822465896606} 08/31/2021 00:35:33 - INFO - __main__ - Step 62669: {'lr': 0.00031980892664344084, 'samples': 12032448, 'steps': 62668, 'loss/train': 0.7833214402198792} 08/31/2021 00:35:35 - INFO - __main__ - Step 62670: {'lr': 0.0003198038309719182, 'samples': 12032640, 'steps': 62669, 'loss/train': 1.4505082368850708} 08/31/2021 00:35:35 - INFO - __main__ - Step 62671: {'lr': 0.000319798735268943, 'samples': 12032832, 'steps': 62670, 'loss/train': 1.0953847169876099} 08/31/2021 00:35:36 - INFO - __main__ - Step 62672: {'lr': 0.00031979363953451765, 'samples': 12033024, 'steps': 62671, 'loss/train': 0.033786021173000336} 08/31/2021 00:35:36 - INFO - __main__ - Step 62673: {'lr': 0.00031978854376864426, 'samples': 12033216, 'steps': 62672, 'loss/train': 1.184295892715454} 08/31/2021 00:35:36 - INFO - __main__ - Step 62674: {'lr': 0.00031978344797132526, 'samples': 12033408, 'steps': 62673, 'loss/train': 1.6585181951522827} 08/31/2021 00:35:39 - INFO - __main__ - Step 62675: {'lr': 0.000319778352142563, 'samples': 12033600, 'steps': 62674, 'loss/train': 1.4312697649002075} 08/31/2021 00:35:39 - INFO - __main__ - Step 62676: {'lr': 0.00031977325628235957, 'samples': 12033792, 'steps': 62675, 'loss/train': 2.6857995986938477} 08/31/2021 00:35:39 - INFO - __main__ - Step 62677: {'lr': 0.0003197681603907174, 'samples': 12033984, 'steps': 62676, 'loss/train': 1.9255179166793823} 08/31/2021 00:35:40 - INFO - __main__ - Step 62678: {'lr': 0.0003197630644676389, 'samples': 12034176, 'steps': 62677, 'loss/train': 1.44828200340271} 08/31/2021 00:35:40 - INFO - __main__ - Step 62679: {'lr': 0.0003197579685131261, 'samples': 12034368, 'steps': 62678, 'loss/train': 1.5227434635162354} 08/31/2021 00:35:40 - INFO - __main__ - Step 62680: {'lr': 0.0003197528725271815, 'samples': 12034560, 'steps': 62679, 'loss/train': 1.3151726722717285} 08/31/2021 00:35:42 - INFO - __main__ - Step 62681: {'lr': 0.00031974777650980735, 'samples': 12034752, 'steps': 62680, 'loss/train': 1.4033313989639282} 08/31/2021 00:35:42 - INFO - __main__ - Step 62682: {'lr': 0.00031974268046100593, 'samples': 12034944, 'steps': 62681, 'loss/train': 1.112673044204712} 08/31/2021 00:35:43 - INFO - __main__ - Step 62683: {'lr': 0.0003197375843807795, 'samples': 12035136, 'steps': 62682, 'loss/train': 1.4536150693893433} 08/31/2021 00:35:43 - INFO - __main__ - Step 62684: {'lr': 0.00031973248826913035, 'samples': 12035328, 'steps': 62683, 'loss/train': 1.1763677597045898} 08/31/2021 00:35:43 - INFO - __main__ - Step 62685: {'lr': 0.0003197273921260609, 'samples': 12035520, 'steps': 62684, 'loss/train': 1.679089069366455} 08/31/2021 00:35:45 - INFO - __main__ - Step 62686: {'lr': 0.0003197222959515733, 'samples': 12035712, 'steps': 62685, 'loss/train': 1.7118972539901733} 08/31/2021 00:35:45 - INFO - __main__ - Step 62687: {'lr': 0.00031971719974566994, 'samples': 12035904, 'steps': 62686, 'loss/train': 1.7860428094863892} 08/31/2021 00:35:46 - INFO - __main__ - Step 62688: {'lr': 0.00031971210350835314, 'samples': 12036096, 'steps': 62687, 'loss/train': 0.922649085521698} 08/31/2021 00:35:46 - INFO - __main__ - Step 62689: {'lr': 0.00031970700723962504, 'samples': 12036288, 'steps': 62688, 'loss/train': 1.3175054788589478} 08/31/2021 00:35:46 - INFO - __main__ - Step 62690: {'lr': 0.0003197019109394881, 'samples': 12036480, 'steps': 62689, 'loss/train': 1.3734437227249146} 08/31/2021 00:35:48 - INFO - __main__ - Step 62691: {'lr': 0.00031969681460794453, 'samples': 12036672, 'steps': 62690, 'loss/train': 1.238411545753479} 08/31/2021 00:35:48 - INFO - __main__ - Step 62692: {'lr': 0.00031969171824499667, 'samples': 12036864, 'steps': 62691, 'loss/train': 1.3479087352752686} 08/31/2021 00:35:49 - INFO - __main__ - Step 62693: {'lr': 0.00031968662185064673, 'samples': 12037056, 'steps': 62692, 'loss/train': 1.339840054512024} 08/31/2021 00:35:49 - INFO - __main__ - Step 62694: {'lr': 0.00031968152542489716, 'samples': 12037248, 'steps': 62693, 'loss/train': 1.2055065631866455} 08/31/2021 00:35:49 - INFO - __main__ - Step 62695: {'lr': 0.0003196764289677502, 'samples': 12037440, 'steps': 62694, 'loss/train': 1.01052725315094} 08/31/2021 00:35:50 - INFO - __main__ - Step 62696: {'lr': 0.000319671332479208, 'samples': 12037632, 'steps': 62695, 'loss/train': 1.695652961730957} 08/31/2021 00:35:51 - INFO - __main__ - Step 62697: {'lr': 0.00031966623595927303, 'samples': 12037824, 'steps': 62696, 'loss/train': 1.1960170269012451} 08/31/2021 00:35:52 - INFO - __main__ - Step 62698: {'lr': 0.0003196611394079475, 'samples': 12038016, 'steps': 62697, 'loss/train': 1.5135751962661743} 08/31/2021 00:35:52 - INFO - __main__ - Step 62699: {'lr': 0.00031965604282523373, 'samples': 12038208, 'steps': 62698, 'loss/train': 1.4526506662368774} 08/31/2021 00:35:52 - INFO - __main__ - Step 62700: {'lr': 0.00031965094621113407, 'samples': 12038400, 'steps': 62699, 'loss/train': 1.2601652145385742} 08/31/2021 00:35:53 - INFO - __main__ - Step 62701: {'lr': 0.0003196458495656508, 'samples': 12038592, 'steps': 62700, 'loss/train': 1.1528955698013306} 08/31/2021 00:35:54 - INFO - __main__ - Step 62702: {'lr': 0.00031964075288878614, 'samples': 12038784, 'steps': 62701, 'loss/train': 1.1835782527923584} 08/31/2021 00:35:55 - INFO - __main__ - Step 62703: {'lr': 0.00031963565618054244, 'samples': 12038976, 'steps': 62702, 'loss/train': 1.3851948976516724} 08/31/2021 00:35:55 - INFO - __main__ - Step 62704: {'lr': 0.0003196305594409219, 'samples': 12039168, 'steps': 62703, 'loss/train': 0.8877078890800476} 08/31/2021 00:35:55 - INFO - __main__ - Step 62705: {'lr': 0.000319625462669927, 'samples': 12039360, 'steps': 62704, 'loss/train': 2.6097967624664307} 08/31/2021 00:35:56 - INFO - __main__ - Step 62706: {'lr': 0.00031962036586755994, 'samples': 12039552, 'steps': 62705, 'loss/train': 1.5554481744766235} 08/31/2021 00:35:58 - INFO - __main__ - Step 62707: {'lr': 0.000319615269033823, 'samples': 12039744, 'steps': 62706, 'loss/train': 1.43854820728302} 08/31/2021 00:35:58 - INFO - __main__ - Step 62708: {'lr': 0.00031961017216871853, 'samples': 12039936, 'steps': 62707, 'loss/train': 1.359556794166565} 08/31/2021 00:35:59 - INFO - __main__ - Step 62709: {'lr': 0.0003196050752722487, 'samples': 12040128, 'steps': 62708, 'loss/train': 0.14251454174518585} 08/31/2021 00:35:59 - INFO - __main__ - Step 62710: {'lr': 0.00031959997834441595, 'samples': 12040320, 'steps': 62709, 'loss/train': 0.1885838508605957} 08/31/2021 00:35:59 - INFO - __main__ - Step 62711: {'lr': 0.00031959488138522254, 'samples': 12040512, 'steps': 62710, 'loss/train': 0.9648082852363586} 08/31/2021 00:36:00 - INFO - __main__ - Step 62712: {'lr': 0.0003195897843946707, 'samples': 12040704, 'steps': 62711, 'loss/train': 1.4262666702270508} 08/31/2021 00:36:01 - INFO - __main__ - Step 62713: {'lr': 0.0003195846873727628, 'samples': 12040896, 'steps': 62712, 'loss/train': 0.9062191843986511} 08/31/2021 00:36:02 - INFO - __main__ - Step 62714: {'lr': 0.00031957959031950114, 'samples': 12041088, 'steps': 62713, 'loss/train': 0.23765285313129425} 08/31/2021 00:36:02 - INFO - __main__ - Step 62715: {'lr': 0.00031957449323488803, 'samples': 12041280, 'steps': 62714, 'loss/train': 0.7571749687194824} 08/31/2021 00:36:02 - INFO - __main__ - Step 62716: {'lr': 0.00031956939611892565, 'samples': 12041472, 'steps': 62715, 'loss/train': 1.214327096939087} 08/31/2021 00:36:03 - INFO - __main__ - Step 62717: {'lr': 0.0003195642989716164, 'samples': 12041664, 'steps': 62716, 'loss/train': 1.504930019378662} 08/31/2021 00:36:04 - INFO - __main__ - Step 62718: {'lr': 0.0003195592017929625, 'samples': 12041856, 'steps': 62717, 'loss/train': 1.4071177244186401} 08/31/2021 00:36:05 - INFO - __main__ - Step 62719: {'lr': 0.00031955410458296636, 'samples': 12042048, 'steps': 62718, 'loss/train': 1.8051644563674927} 08/31/2021 00:36:05 - INFO - __main__ - Step 62720: {'lr': 0.00031954900734163015, 'samples': 12042240, 'steps': 62719, 'loss/train': 1.3657920360565186} 08/31/2021 00:36:05 - INFO - __main__ - Step 62721: {'lr': 0.0003195439100689563, 'samples': 12042432, 'steps': 62720, 'loss/train': 0.22149670124053955} 08/31/2021 00:36:06 - INFO - __main__ - Step 62722: {'lr': 0.00031953881276494705, 'samples': 12042624, 'steps': 62721, 'loss/train': 1.3177224397659302} 08/31/2021 00:36:08 - INFO - __main__ - Step 62723: {'lr': 0.00031953371542960466, 'samples': 12042816, 'steps': 62722, 'loss/train': 1.0201979875564575} 08/31/2021 00:36:08 - INFO - __main__ - Step 62724: {'lr': 0.0003195286180629314, 'samples': 12043008, 'steps': 62723, 'loss/train': 0.6799564361572266} 08/31/2021 00:36:09 - INFO - __main__ - Step 62725: {'lr': 0.0003195235206649297, 'samples': 12043200, 'steps': 62724, 'loss/train': 0.8998138308525085} 08/31/2021 00:36:09 - INFO - __main__ - Step 62726: {'lr': 0.0003195184232356017, 'samples': 12043392, 'steps': 62725, 'loss/train': 1.35517156124115} 08/31/2021 00:36:09 - INFO - __main__ - Step 62727: {'lr': 0.00031951332577494977, 'samples': 12043584, 'steps': 62726, 'loss/train': 1.4548389911651611} 08/31/2021 00:36:11 - INFO - __main__ - Step 62728: {'lr': 0.0003195082282829763, 'samples': 12043776, 'steps': 62727, 'loss/train': 0.8456025719642639} 08/31/2021 00:36:11 - INFO - __main__ - Step 62729: {'lr': 0.0003195031307596834, 'samples': 12043968, 'steps': 62728, 'loss/train': 1.1335943937301636} 08/31/2021 00:36:12 - INFO - __main__ - Step 62730: {'lr': 0.00031949803320507355, 'samples': 12044160, 'steps': 62729, 'loss/train': 1.6051570177078247} 08/31/2021 00:36:12 - INFO - __main__ - Step 62731: {'lr': 0.0003194929356191489, 'samples': 12044352, 'steps': 62730, 'loss/train': 1.1098339557647705} 08/31/2021 00:36:12 - INFO - __main__ - Step 62732: {'lr': 0.00031948783800191176, 'samples': 12044544, 'steps': 62731, 'loss/train': 1.4284979104995728} 08/31/2021 00:36:13 - INFO - __main__ - Step 62733: {'lr': 0.00031948274035336455, 'samples': 12044736, 'steps': 62732, 'loss/train': 1.2427921295166016} 08/31/2021 00:36:14 - INFO - __main__ - Step 62734: {'lr': 0.00031947764267350944, 'samples': 12044928, 'steps': 62733, 'loss/train': 2.177150011062622} 08/31/2021 00:36:15 - INFO - __main__ - Step 62735: {'lr': 0.00031947254496234885, 'samples': 12045120, 'steps': 62734, 'loss/train': 0.7781495451927185} 08/31/2021 00:36:15 - INFO - __main__ - Step 62736: {'lr': 0.00031946744721988497, 'samples': 12045312, 'steps': 62735, 'loss/train': 1.1218606233596802} 08/31/2021 00:36:15 - INFO - __main__ - Step 62737: {'lr': 0.00031946234944612006, 'samples': 12045504, 'steps': 62736, 'loss/train': 1.3110003471374512} 08/31/2021 00:36:16 - INFO - __main__ - Step 62738: {'lr': 0.00031945725164105656, 'samples': 12045696, 'steps': 62737, 'loss/train': 2.0338947772979736} 08/31/2021 00:36:18 - INFO - __main__ - Step 62739: {'lr': 0.00031945215380469664, 'samples': 12045888, 'steps': 62738, 'loss/train': 1.2448290586471558} 08/31/2021 00:36:18 - INFO - __main__ - Step 62740: {'lr': 0.0003194470559370427, 'samples': 12046080, 'steps': 62739, 'loss/train': 0.16804929077625275} 08/31/2021 00:36:18 - INFO - __main__ - Step 62741: {'lr': 0.00031944195803809694, 'samples': 12046272, 'steps': 62740, 'loss/train': 0.37431204319000244} 08/31/2021 00:36:19 - INFO - __main__ - Step 62742: {'lr': 0.00031943686010786176, 'samples': 12046464, 'steps': 62741, 'loss/train': 0.16600260138511658} 08/31/2021 00:36:19 - INFO - __main__ - Step 62743: {'lr': 0.0003194317621463394, 'samples': 12046656, 'steps': 62742, 'loss/train': 0.0524575375020504} 08/31/2021 00:36:19 - INFO - __main__ - Step 62744: {'lr': 0.0003194266641535322, 'samples': 12046848, 'steps': 62743, 'loss/train': 1.1431207656860352} 08/31/2021 00:36:21 - INFO - __main__ - Step 62745: {'lr': 0.0003194215661294423, 'samples': 12047040, 'steps': 62744, 'loss/train': 1.2438815832138062} 08/31/2021 00:36:21 - INFO - __main__ - Step 62746: {'lr': 0.00031941646807407217, 'samples': 12047232, 'steps': 62745, 'loss/train': 1.5179215669631958} 08/31/2021 00:36:22 - INFO - __main__ - Step 62747: {'lr': 0.000319411369987424, 'samples': 12047424, 'steps': 62746, 'loss/train': 1.57768714427948} 08/31/2021 00:36:22 - INFO - __main__ - Step 62748: {'lr': 0.00031940627186950027, 'samples': 12047616, 'steps': 62747, 'loss/train': 1.0390843152999878} 08/31/2021 00:36:22 - INFO - __main__ - Step 62749: {'lr': 0.00031940117372030304, 'samples': 12047808, 'steps': 62748, 'loss/train': 1.2224293947219849} 08/31/2021 00:36:23 - INFO - __main__ - Step 62750: {'lr': 0.00031939607553983475, 'samples': 12048000, 'steps': 62749, 'loss/train': 1.2670832872390747} 08/31/2021 00:36:24 - INFO - __main__ - Step 62751: {'lr': 0.00031939097732809765, 'samples': 12048192, 'steps': 62750, 'loss/train': 1.2228574752807617} 08/31/2021 00:36:25 - INFO - __main__ - Step 62752: {'lr': 0.000319385879085094, 'samples': 12048384, 'steps': 62751, 'loss/train': 0.823636531829834} 08/31/2021 00:36:25 - INFO - __main__ - Step 62753: {'lr': 0.0003193807808108262, 'samples': 12048576, 'steps': 62752, 'loss/train': 1.3215203285217285} 08/31/2021 00:36:25 - INFO - __main__ - Step 62754: {'lr': 0.00031937568250529647, 'samples': 12048768, 'steps': 62753, 'loss/train': 1.8953404426574707} 08/31/2021 00:36:26 - INFO - __main__ - Step 62755: {'lr': 0.00031937058416850716, 'samples': 12048960, 'steps': 62754, 'loss/train': 1.299643635749817} 08/31/2021 00:36:27 - INFO - __main__ - Step 62756: {'lr': 0.00031936548580046046, 'samples': 12049152, 'steps': 62755, 'loss/train': 1.3934985399246216} 08/31/2021 00:36:28 - INFO - __main__ - Step 62757: {'lr': 0.0003193603874011588, 'samples': 12049344, 'steps': 62756, 'loss/train': 0.990595281124115} 08/31/2021 00:36:28 - INFO - __main__ - Step 62758: {'lr': 0.0003193552889706044, 'samples': 12049536, 'steps': 62757, 'loss/train': 1.5447819232940674} 08/31/2021 00:36:29 - INFO - __main__ - Step 62759: {'lr': 0.0003193501905087996, 'samples': 12049728, 'steps': 62758, 'loss/train': 0.5956252217292786} 08/31/2021 00:36:29 - INFO - __main__ - Step 62760: {'lr': 0.0003193450920157467, 'samples': 12049920, 'steps': 62759, 'loss/train': 1.0143345594406128} 08/31/2021 00:36:30 - INFO - __main__ - Step 62761: {'lr': 0.0003193399934914479, 'samples': 12050112, 'steps': 62760, 'loss/train': 0.05643423646688461} 08/31/2021 00:36:31 - INFO - __main__ - Step 62762: {'lr': 0.0003193348949359056, 'samples': 12050304, 'steps': 62761, 'loss/train': 1.4661145210266113} 08/31/2021 00:36:31 - INFO - __main__ - Step 62763: {'lr': 0.0003193297963491221, 'samples': 12050496, 'steps': 62762, 'loss/train': 0.8519482612609863} 08/31/2021 00:36:32 - INFO - __main__ - Step 62764: {'lr': 0.00031932469773109963, 'samples': 12050688, 'steps': 62763, 'loss/train': 1.4555002450942993} 08/31/2021 00:36:32 - INFO - __main__ - Step 62765: {'lr': 0.0003193195990818405, 'samples': 12050880, 'steps': 62764, 'loss/train': 1.4068068265914917} 08/31/2021 00:36:34 - INFO - __main__ - Step 62766: {'lr': 0.00031931450040134705, 'samples': 12051072, 'steps': 62765, 'loss/train': 1.4044280052185059} 08/31/2021 00:36:34 - INFO - __main__ - Step 62767: {'lr': 0.00031930940168962155, 'samples': 12051264, 'steps': 62766, 'loss/train': 1.6647144556045532} 08/31/2021 00:36:35 - INFO - __main__ - Step 62768: {'lr': 0.00031930430294666636, 'samples': 12051456, 'steps': 62767, 'loss/train': 0.058777373284101486} 08/31/2021 00:36:35 - INFO - __main__ - Step 62769: {'lr': 0.00031929920417248366, 'samples': 12051648, 'steps': 62768, 'loss/train': 1.2825514078140259} 08/31/2021 00:36:35 - INFO - __main__ - Step 62770: {'lr': 0.0003192941053670758, 'samples': 12051840, 'steps': 62769, 'loss/train': 0.7021322250366211} 08/31/2021 00:36:36 - INFO - __main__ - Step 62771: {'lr': 0.00031928900653044513, 'samples': 12052032, 'steps': 62770, 'loss/train': 5.337954044342041} 08/31/2021 00:36:37 - INFO - __main__ - Step 62772: {'lr': 0.00031928390766259386, 'samples': 12052224, 'steps': 62771, 'loss/train': 1.1537737846374512} 08/31/2021 00:36:38 - INFO - __main__ - Step 62773: {'lr': 0.00031927880876352435, 'samples': 12052416, 'steps': 62772, 'loss/train': 1.3222887516021729} 08/31/2021 00:36:38 - INFO - __main__ - Step 62774: {'lr': 0.0003192737098332388, 'samples': 12052608, 'steps': 62773, 'loss/train': 1.20563805103302} 08/31/2021 00:36:38 - INFO - __main__ - Step 62775: {'lr': 0.00031926861087173974, 'samples': 12052800, 'steps': 62774, 'loss/train': 0.8797259330749512} 08/31/2021 00:36:39 - INFO - __main__ - Step 62776: {'lr': 0.00031926351187902926, 'samples': 12052992, 'steps': 62775, 'loss/train': 0.5163978934288025} 08/31/2021 00:36:41 - INFO - __main__ - Step 62777: {'lr': 0.00031925841285510964, 'samples': 12053184, 'steps': 62776, 'loss/train': 0.8747900724411011} 08/31/2021 00:36:42 - INFO - __main__ - Step 62778: {'lr': 0.0003192533137999833, 'samples': 12053376, 'steps': 62777, 'loss/train': 1.4019438028335571} 08/31/2021 00:36:42 - INFO - __main__ - Step 62779: {'lr': 0.0003192482147136525, 'samples': 12053568, 'steps': 62778, 'loss/train': 1.2069928646087646} 08/31/2021 00:36:43 - INFO - __main__ - Step 62780: {'lr': 0.00031924311559611946, 'samples': 12053760, 'steps': 62779, 'loss/train': 1.352053165435791} 08/31/2021 00:36:43 - INFO - __main__ - Step 62781: {'lr': 0.0003192380164473866, 'samples': 12053952, 'steps': 62780, 'loss/train': 1.3935160636901855} 08/31/2021 00:36:43 - INFO - __main__ - Step 62782: {'lr': 0.0003192329172674562, 'samples': 12054144, 'steps': 62781, 'loss/train': 0.4326370656490326} 08/31/2021 00:36:44 - INFO - __main__ - Step 62783: {'lr': 0.0003192278180563304, 'samples': 12054336, 'steps': 62782, 'loss/train': 0.46790772676467896} 08/31/2021 00:36:46 - INFO - __main__ - Step 62784: {'lr': 0.00031922271881401165, 'samples': 12054528, 'steps': 62783, 'loss/train': 0.40042707324028015} 08/31/2021 00:36:46 - INFO - __main__ - Step 62785: {'lr': 0.0003192176195405023, 'samples': 12054720, 'steps': 62784, 'loss/train': 0.37298280000686646} 08/31/2021 00:36:46 - INFO - __main__ - Step 62786: {'lr': 0.00031921252023580445, 'samples': 12054912, 'steps': 62785, 'loss/train': 0.22128288447856903} 08/31/2021 00:36:47 - INFO - __main__ - Step 62787: {'lr': 0.00031920742089992056, 'samples': 12055104, 'steps': 62786, 'loss/train': 1.3895823955535889} 08/31/2021 00:36:47 - INFO - __main__ - Step 62788: {'lr': 0.0003192023215328529, 'samples': 12055296, 'steps': 62787, 'loss/train': 1.0939918756484985} 08/31/2021 00:36:49 - INFO - __main__ - Step 62789: {'lr': 0.0003191972221346037, 'samples': 12055488, 'steps': 62788, 'loss/train': 1.0331121683120728} 08/31/2021 00:36:50 - INFO - __main__ - Step 62790: {'lr': 0.0003191921227051753, 'samples': 12055680, 'steps': 62789, 'loss/train': 1.8207085132598877} 08/31/2021 00:36:50 - INFO - __main__ - Step 62791: {'lr': 0.0003191870232445699, 'samples': 12055872, 'steps': 62790, 'loss/train': 1.436144471168518} 08/31/2021 00:36:50 - INFO - __main__ - Step 62792: {'lr': 0.00031918192375279006, 'samples': 12056064, 'steps': 62791, 'loss/train': 1.0741357803344727} 08/31/2021 00:36:51 - INFO - __main__ - Step 62793: {'lr': 0.00031917682422983787, 'samples': 12056256, 'steps': 62792, 'loss/train': 1.4775675535202026} 08/31/2021 00:36:51 - INFO - __main__ - Step 62794: {'lr': 0.00031917172467571563, 'samples': 12056448, 'steps': 62793, 'loss/train': 1.3724267482757568} 08/31/2021 00:36:52 - INFO - __main__ - Step 62795: {'lr': 0.0003191666250904257, 'samples': 12056640, 'steps': 62794, 'loss/train': 0.8917551040649414} 08/31/2021 00:36:53 - INFO - __main__ - Step 62796: {'lr': 0.0003191615254739703, 'samples': 12056832, 'steps': 62795, 'loss/train': 1.6196340322494507} 08/31/2021 00:36:53 - INFO - __main__ - Step 62797: {'lr': 0.00031915642582635185, 'samples': 12057024, 'steps': 62796, 'loss/train': 2.0247418880462646} 08/31/2021 00:36:54 - INFO - __main__ - Step 62798: {'lr': 0.0003191513261475726, 'samples': 12057216, 'steps': 62797, 'loss/train': 1.140218734741211} 08/31/2021 00:36:54 - INFO - __main__ - Step 62799: {'lr': 0.0003191462264376348, 'samples': 12057408, 'steps': 62798, 'loss/train': 1.2685747146606445} 08/31/2021 00:36:55 - INFO - __main__ - Step 62800: {'lr': 0.0003191411266965408, 'samples': 12057600, 'steps': 62799, 'loss/train': 0.2591274380683899} 08/31/2021 00:36:56 - INFO - __main__ - Step 62801: {'lr': 0.0003191360269242928, 'samples': 12057792, 'steps': 62800, 'loss/train': 0.9890345335006714} 08/31/2021 00:36:56 - INFO - __main__ - Step 62802: {'lr': 0.0003191309271208932, 'samples': 12057984, 'steps': 62801, 'loss/train': 1.5029739141464233} 08/31/2021 00:36:57 - INFO - __main__ - Step 62803: {'lr': 0.0003191258272863443, 'samples': 12058176, 'steps': 62802, 'loss/train': 1.3892784118652344} 08/31/2021 00:36:57 - INFO - __main__ - Step 62804: {'lr': 0.0003191207274206484, 'samples': 12058368, 'steps': 62803, 'loss/train': 0.9896650314331055} 08/31/2021 00:36:58 - INFO - __main__ - Step 62805: {'lr': 0.00031911562752380773, 'samples': 12058560, 'steps': 62804, 'loss/train': 1.0513380765914917} 08/31/2021 00:36:59 - INFO - __main__ - Step 62806: {'lr': 0.0003191105275958246, 'samples': 12058752, 'steps': 62805, 'loss/train': 1.1419615745544434} 08/31/2021 00:36:59 - INFO - __main__ - Step 62807: {'lr': 0.00031910542763670136, 'samples': 12058944, 'steps': 62806, 'loss/train': 0.8409192562103271} 08/31/2021 00:37:00 - INFO - __main__ - Step 62808: {'lr': 0.00031910032764644026, 'samples': 12059136, 'steps': 62807, 'loss/train': 1.4609352350234985} 08/31/2021 00:37:00 - INFO - __main__ - Step 62809: {'lr': 0.0003190952276250437, 'samples': 12059328, 'steps': 62808, 'loss/train': 1.8125404119491577} 08/31/2021 00:37:02 - INFO - __main__ - Step 62810: {'lr': 0.00031909012757251376, 'samples': 12059520, 'steps': 62809, 'loss/train': 1.616369366645813} 08/31/2021 00:37:02 - INFO - __main__ - Step 62811: {'lr': 0.000319085027488853, 'samples': 12059712, 'steps': 62810, 'loss/train': 1.299255609512329} 08/31/2021 00:37:03 - INFO - __main__ - Step 62812: {'lr': 0.0003190799273740635, 'samples': 12059904, 'steps': 62811, 'loss/train': 1.1971126794815063} 08/31/2021 00:37:03 - INFO - __main__ - Step 62813: {'lr': 0.00031907482722814766, 'samples': 12060096, 'steps': 62812, 'loss/train': 1.1992071866989136} 08/31/2021 00:37:03 - INFO - __main__ - Step 62814: {'lr': 0.0003190697270511078, 'samples': 12060288, 'steps': 62813, 'loss/train': 0.9504538774490356} 08/31/2021 00:37:05 - INFO - __main__ - Step 62815: {'lr': 0.0003190646268429462, 'samples': 12060480, 'steps': 62814, 'loss/train': 1.6172564029693604} 08/31/2021 00:37:05 - INFO - __main__ - Step 62816: {'lr': 0.00031905952660366514, 'samples': 12060672, 'steps': 62815, 'loss/train': 1.5370166301727295} 08/31/2021 00:37:06 - INFO - __main__ - Step 62817: {'lr': 0.0003190544263332669, 'samples': 12060864, 'steps': 62816, 'loss/train': 0.840502917766571} 08/31/2021 00:37:06 - INFO - __main__ - Step 62818: {'lr': 0.00031904932603175386, 'samples': 12061056, 'steps': 62817, 'loss/train': 2.0394222736358643} 08/31/2021 00:37:07 - INFO - __main__ - Step 62819: {'lr': 0.00031904422569912816, 'samples': 12061248, 'steps': 62818, 'loss/train': 1.3081040382385254} 08/31/2021 00:37:07 - INFO - __main__ - Step 62820: {'lr': 0.00031903912533539226, 'samples': 12061440, 'steps': 62819, 'loss/train': 1.4230154752731323} 08/31/2021 00:37:08 - INFO - __main__ - Step 62821: {'lr': 0.0003190340249405484, 'samples': 12061632, 'steps': 62820, 'loss/train': 1.2342694997787476} 08/31/2021 00:37:09 - INFO - __main__ - Step 62822: {'lr': 0.00031902892451459884, 'samples': 12061824, 'steps': 62821, 'loss/train': 1.2595367431640625} 08/31/2021 00:37:09 - INFO - __main__ - Step 62823: {'lr': 0.000319023824057546, 'samples': 12062016, 'steps': 62822, 'loss/train': 1.179823398590088} 08/31/2021 00:37:10 - INFO - __main__ - Step 62824: {'lr': 0.00031901872356939197, 'samples': 12062208, 'steps': 62823, 'loss/train': 1.6019675731658936} 08/31/2021 00:37:10 - INFO - __main__ - Step 62825: {'lr': 0.00031901362305013925, 'samples': 12062400, 'steps': 62824, 'loss/train': 5.681351661682129} 08/31/2021 00:37:11 - INFO - __main__ - Step 62826: {'lr': 0.00031900852249979004, 'samples': 12062592, 'steps': 62825, 'loss/train': 1.5501731634140015} 08/31/2021 00:37:12 - INFO - __main__ - Step 62827: {'lr': 0.00031900342191834656, 'samples': 12062784, 'steps': 62826, 'loss/train': 0.17992806434631348} 08/31/2021 00:37:12 - INFO - __main__ - Step 62828: {'lr': 0.0003189983213058113, 'samples': 12062976, 'steps': 62827, 'loss/train': 1.5842130184173584} 08/31/2021 00:37:13 - INFO - __main__ - Step 62829: {'lr': 0.0003189932206621865, 'samples': 12063168, 'steps': 62828, 'loss/train': 1.526474118232727} 08/31/2021 00:37:13 - INFO - __main__ - Step 62830: {'lr': 0.00031898811998747436, 'samples': 12063360, 'steps': 62829, 'loss/train': 1.6505844593048096} 08/31/2021 00:37:13 - INFO - __main__ - Step 62831: {'lr': 0.0003189830192816772, 'samples': 12063552, 'steps': 62830, 'loss/train': 1.5202704668045044} 08/31/2021 00:37:15 - INFO - __main__ - Step 62832: {'lr': 0.0003189779185447974, 'samples': 12063744, 'steps': 62831, 'loss/train': 1.402510643005371} 08/31/2021 00:37:15 - INFO - __main__ - Step 62833: {'lr': 0.0003189728177768372, 'samples': 12063936, 'steps': 62832, 'loss/train': 0.6462494730949402} 08/31/2021 00:37:16 - INFO - __main__ - Step 62834: {'lr': 0.00031896771697779893, 'samples': 12064128, 'steps': 62833, 'loss/train': 2.0284106731414795} 08/31/2021 00:37:16 - INFO - __main__ - Step 62835: {'lr': 0.00031896261614768485, 'samples': 12064320, 'steps': 62834, 'loss/train': 0.7173831462860107} 08/31/2021 00:37:16 - INFO - __main__ - Step 62836: {'lr': 0.00031895751528649737, 'samples': 12064512, 'steps': 62835, 'loss/train': 1.1826823949813843} 08/31/2021 00:37:18 - INFO - __main__ - Step 62837: {'lr': 0.0003189524143942386, 'samples': 12064704, 'steps': 62836, 'loss/train': 1.0349229574203491} 08/31/2021 00:37:19 - INFO - __main__ - Step 62838: {'lr': 0.00031894731347091094, 'samples': 12064896, 'steps': 62837, 'loss/train': 1.8895227909088135} 08/31/2021 00:37:19 - INFO - __main__ - Step 62839: {'lr': 0.00031894221251651666, 'samples': 12065088, 'steps': 62838, 'loss/train': 1.0924992561340332} 08/31/2021 00:37:20 - INFO - __main__ - Step 62840: {'lr': 0.00031893711153105814, 'samples': 12065280, 'steps': 62839, 'loss/train': 1.3312385082244873} 08/31/2021 00:37:20 - INFO - __main__ - Step 62841: {'lr': 0.00031893201051453755, 'samples': 12065472, 'steps': 62840, 'loss/train': 0.09295909106731415} 08/31/2021 00:37:22 - INFO - __main__ - Step 62842: {'lr': 0.0003189269094669574, 'samples': 12065664, 'steps': 62841, 'loss/train': 0.9115883708000183} 08/31/2021 00:37:22 - INFO - __main__ - Step 62843: {'lr': 0.0003189218083883197, 'samples': 12065856, 'steps': 62842, 'loss/train': 0.9392722249031067} 08/31/2021 00:37:23 - INFO - __main__ - Step 62844: {'lr': 0.00031891670727862703, 'samples': 12066048, 'steps': 62843, 'loss/train': 1.608138918876648} 08/31/2021 00:37:23 - INFO - __main__ - Step 62845: {'lr': 0.0003189116061378815, 'samples': 12066240, 'steps': 62844, 'loss/train': 1.8264771699905396} 08/31/2021 00:37:23 - INFO - __main__ - Step 62846: {'lr': 0.0003189065049660854, 'samples': 12066432, 'steps': 62845, 'loss/train': 1.493566870689392} 08/31/2021 00:37:24 - INFO - __main__ - Step 62847: {'lr': 0.00031890140376324117, 'samples': 12066624, 'steps': 62846, 'loss/train': 1.1904850006103516} 08/31/2021 00:37:25 - INFO - __main__ - Step 62848: {'lr': 0.00031889630252935095, 'samples': 12066816, 'steps': 62847, 'loss/train': 0.7611990571022034} 08/31/2021 00:37:26 - INFO - __main__ - Step 62849: {'lr': 0.0003188912012644172, 'samples': 12067008, 'steps': 62848, 'loss/train': 1.6407347917556763} 08/31/2021 00:37:26 - INFO - __main__ - Step 62850: {'lr': 0.00031888609996844216, 'samples': 12067200, 'steps': 62849, 'loss/train': 1.2037659883499146} 08/31/2021 00:37:26 - INFO - __main__ - Step 62851: {'lr': 0.0003188809986414281, 'samples': 12067392, 'steps': 62850, 'loss/train': 0.9135605096817017} 08/31/2021 00:37:27 - INFO - __main__ - Step 62852: {'lr': 0.0003188758972833772, 'samples': 12067584, 'steps': 62851, 'loss/train': 0.23704949021339417} 08/31/2021 00:37:28 - INFO - __main__ - Step 62853: {'lr': 0.00031887079589429195, 'samples': 12067776, 'steps': 62852, 'loss/train': 1.4163565635681152} 08/31/2021 00:37:28 - INFO - __main__ - Step 62854: {'lr': 0.00031886569447417456, 'samples': 12067968, 'steps': 62853, 'loss/train': 1.6889792680740356} 08/31/2021 00:37:29 - INFO - __main__ - Step 62855: {'lr': 0.0003188605930230274, 'samples': 12068160, 'steps': 62854, 'loss/train': 1.1666955947875977} 08/31/2021 00:37:29 - INFO - __main__ - Step 62856: {'lr': 0.00031885549154085283, 'samples': 12068352, 'steps': 62855, 'loss/train': 1.1497257947921753} 08/31/2021 00:37:30 - INFO - __main__ - Step 62857: {'lr': 0.0003188503900276529, 'samples': 12068544, 'steps': 62856, 'loss/train': 1.1579440832138062} 08/31/2021 00:37:31 - INFO - __main__ - Step 62858: {'lr': 0.00031884528848342996, 'samples': 12068736, 'steps': 62857, 'loss/train': 0.9788479208946228} 08/31/2021 00:37:31 - INFO - __main__ - Step 62859: {'lr': 0.0003188401869081865, 'samples': 12068928, 'steps': 62858, 'loss/train': 1.0789124965667725} 08/31/2021 00:37:32 - INFO - __main__ - Step 62860: {'lr': 0.0003188350853019247, 'samples': 12069120, 'steps': 62859, 'loss/train': 1.12599778175354} 08/31/2021 00:37:32 - INFO - __main__ - Step 62861: {'lr': 0.0003188299836646469, 'samples': 12069312, 'steps': 62860, 'loss/train': 2.113729238510132} 08/31/2021 00:37:32 - INFO - __main__ - Step 62862: {'lr': 0.00031882488199635534, 'samples': 12069504, 'steps': 62861, 'loss/train': 0.27139216661453247} 08/31/2021 00:37:34 - INFO - __main__ - Step 62863: {'lr': 0.0003188197802970524, 'samples': 12069696, 'steps': 62862, 'loss/train': 0.9471010565757751} 08/31/2021 00:37:35 - INFO - __main__ - Step 62864: {'lr': 0.0003188146785667403, 'samples': 12069888, 'steps': 62863, 'loss/train': 1.35922372341156} 08/31/2021 00:37:35 - INFO - __main__ - Step 62865: {'lr': 0.0003188095768054214, 'samples': 12070080, 'steps': 62864, 'loss/train': 2.375868797302246} 08/31/2021 00:37:35 - INFO - __main__ - Step 62866: {'lr': 0.00031880447501309787, 'samples': 12070272, 'steps': 62865, 'loss/train': 0.9143063426017761} 08/31/2021 00:37:36 - INFO - __main__ - Step 62867: {'lr': 0.00031879937318977214, 'samples': 12070464, 'steps': 62866, 'loss/train': 1.0194108486175537} 08/31/2021 00:37:37 - INFO - __main__ - Step 62868: {'lr': 0.0003187942713354465, 'samples': 12070656, 'steps': 62867, 'loss/train': 0.9666746854782104} 08/31/2021 00:37:37 - INFO - __main__ - Step 62869: {'lr': 0.00031878916945012324, 'samples': 12070848, 'steps': 62868, 'loss/train': 1.601579189300537} 08/31/2021 00:37:38 - INFO - __main__ - Step 62870: {'lr': 0.0003187840675338047, 'samples': 12071040, 'steps': 62869, 'loss/train': 1.1452109813690186} 08/31/2021 00:37:38 - INFO - __main__ - Step 62871: {'lr': 0.000318778965586493, 'samples': 12071232, 'steps': 62870, 'loss/train': 1.1464433670043945} 08/31/2021 00:37:39 - INFO - __main__ - Step 62872: {'lr': 0.0003187738636081906, 'samples': 12071424, 'steps': 62871, 'loss/train': 0.8214479088783264} 08/31/2021 00:37:39 - INFO - __main__ - Step 62873: {'lr': 0.00031876876159889976, 'samples': 12071616, 'steps': 62872, 'loss/train': 0.04233231022953987} 08/31/2021 00:37:40 - INFO - __main__ - Step 62874: {'lr': 0.00031876365955862273, 'samples': 12071808, 'steps': 62873, 'loss/train': 0.6471068859100342} 08/31/2021 00:37:41 - INFO - __main__ - Step 62875: {'lr': 0.0003187585574873619, 'samples': 12072000, 'steps': 62874, 'loss/train': 1.024336814880371} 08/31/2021 00:37:41 - INFO - __main__ - Step 62876: {'lr': 0.00031875345538511955, 'samples': 12072192, 'steps': 62875, 'loss/train': 1.4893290996551514} 08/31/2021 00:37:42 - INFO - __main__ - Step 62877: {'lr': 0.000318748353251898, 'samples': 12072384, 'steps': 62876, 'loss/train': 0.7448544502258301} 08/31/2021 00:37:42 - INFO - __main__ - Step 62878: {'lr': 0.00031874325108769943, 'samples': 12072576, 'steps': 62877, 'loss/train': 1.382733702659607} 08/31/2021 00:37:43 - INFO - __main__ - Step 62879: {'lr': 0.0003187381488925262, 'samples': 12072768, 'steps': 62878, 'loss/train': 1.2611865997314453} 08/31/2021 00:37:44 - INFO - __main__ - Step 62880: {'lr': 0.0003187330466663806, 'samples': 12072960, 'steps': 62879, 'loss/train': 1.1240612268447876} 08/31/2021 00:37:44 - INFO - __main__ - Step 62881: {'lr': 0.000318727944409265, 'samples': 12073152, 'steps': 62880, 'loss/train': 1.4425603151321411} 08/31/2021 00:37:45 - INFO - __main__ - Step 62882: {'lr': 0.0003187228421211816, 'samples': 12073344, 'steps': 62881, 'loss/train': 1.6478677988052368} 08/31/2021 00:37:45 - INFO - __main__ - Step 62883: {'lr': 0.00031871773980213285, 'samples': 12073536, 'steps': 62882, 'loss/train': 1.3771952390670776} 08/31/2021 00:37:46 - INFO - __main__ - Step 62884: {'lr': 0.0003187126374521209, 'samples': 12073728, 'steps': 62883, 'loss/train': 1.4444509744644165} 08/31/2021 00:37:47 - INFO - __main__ - Step 62885: {'lr': 0.00031870753507114803, 'samples': 12073920, 'steps': 62884, 'loss/train': 1.2014223337173462} 08/31/2021 00:37:47 - INFO - __main__ - Step 62886: {'lr': 0.0003187024326592167, 'samples': 12074112, 'steps': 62885, 'loss/train': 1.5059696435928345} 08/31/2021 00:37:48 - INFO - __main__ - Step 62887: {'lr': 0.000318697330216329, 'samples': 12074304, 'steps': 62886, 'loss/train': 1.6727874279022217} 08/31/2021 00:37:48 - INFO - __main__ - Step 62888: {'lr': 0.0003186922277424874, 'samples': 12074496, 'steps': 62887, 'loss/train': 1.3904861211776733} 08/31/2021 00:37:50 - INFO - __main__ - Step 62889: {'lr': 0.00031868712523769425, 'samples': 12074688, 'steps': 62888, 'loss/train': 0.5301766991615295} 08/31/2021 00:37:50 - INFO - __main__ - Step 62890: {'lr': 0.00031868202270195163, 'samples': 12074880, 'steps': 62889, 'loss/train': 0.6931208968162537} 08/31/2021 00:37:50 - INFO - __main__ - Step 62891: {'lr': 0.0003186769201352619, 'samples': 12075072, 'steps': 62890, 'loss/train': 0.7844139933586121} 08/31/2021 00:37:51 - INFO - __main__ - Step 62892: {'lr': 0.0003186718175376275, 'samples': 12075264, 'steps': 62891, 'loss/train': 2.6984925270080566} 08/31/2021 00:37:51 - INFO - __main__ - Step 62893: {'lr': 0.0003186667149090506, 'samples': 12075456, 'steps': 62892, 'loss/train': 1.4286648035049438} 08/31/2021 00:37:53 - INFO - __main__ - Step 62894: {'lr': 0.00031866161224953355, 'samples': 12075648, 'steps': 62893, 'loss/train': 1.9445663690567017} 08/31/2021 00:37:54 - INFO - __main__ - Step 62895: {'lr': 0.0003186565095590786, 'samples': 12075840, 'steps': 62894, 'loss/train': 0.8140825033187866} 08/31/2021 00:37:54 - INFO - __main__ - Step 62896: {'lr': 0.0003186514068376882, 'samples': 12076032, 'steps': 62895, 'loss/train': 1.2778716087341309} 08/31/2021 00:37:54 - INFO - __main__ - Step 62897: {'lr': 0.00031864630408536443, 'samples': 12076224, 'steps': 62896, 'loss/train': 0.8929421305656433} 08/31/2021 00:37:55 - INFO - __main__ - Step 62898: {'lr': 0.00031864120130210973, 'samples': 12076416, 'steps': 62897, 'loss/train': 1.9100003242492676} 08/31/2021 00:37:56 - INFO - __main__ - Step 62899: {'lr': 0.00031863609848792633, 'samples': 12076608, 'steps': 62898, 'loss/train': 1.0555846691131592} 08/31/2021 00:37:57 - INFO - __main__ - Step 62900: {'lr': 0.0003186309956428166, 'samples': 12076800, 'steps': 62899, 'loss/train': 1.9790586233139038} 08/31/2021 00:37:57 - INFO - __main__ - Step 62901: {'lr': 0.00031862589276678276, 'samples': 12076992, 'steps': 62900, 'loss/train': 1.3385553359985352} 08/31/2021 00:37:57 - INFO - __main__ - Step 62902: {'lr': 0.00031862078985982716, 'samples': 12077184, 'steps': 62901, 'loss/train': 0.7022526264190674} 08/31/2021 00:37:58 - INFO - __main__ - Step 62903: {'lr': 0.0003186156869219522, 'samples': 12077376, 'steps': 62902, 'loss/train': 1.5003172159194946} 08/31/2021 00:37:59 - INFO - __main__ - Step 62904: {'lr': 0.00031861058395316, 'samples': 12077568, 'steps': 62903, 'loss/train': 1.150554895401001} 08/31/2021 00:37:59 - INFO - __main__ - Step 62905: {'lr': 0.00031860548095345286, 'samples': 12077760, 'steps': 62904, 'loss/train': 1.1535484790802002} 08/31/2021 00:38:00 - INFO - __main__ - Step 62906: {'lr': 0.0003186003779228332, 'samples': 12077952, 'steps': 62905, 'loss/train': 1.283697485923767} 08/31/2021 00:38:00 - INFO - __main__ - Step 62907: {'lr': 0.0003185952748613033, 'samples': 12078144, 'steps': 62906, 'loss/train': 1.796469807624817} 08/31/2021 00:38:01 - INFO - __main__ - Step 62908: {'lr': 0.0003185901717688654, 'samples': 12078336, 'steps': 62907, 'loss/train': 1.1677168607711792} 08/31/2021 00:38:01 - INFO - __main__ - Step 62909: {'lr': 0.0003185850686455218, 'samples': 12078528, 'steps': 62908, 'loss/train': 1.343098521232605} 08/31/2021 00:38:03 - INFO - __main__ - Step 62910: {'lr': 0.00031857996549127486, 'samples': 12078720, 'steps': 62909, 'loss/train': 1.5188285112380981} 08/31/2021 00:38:03 - INFO - __main__ - Step 62911: {'lr': 0.00031857486230612686, 'samples': 12078912, 'steps': 62910, 'loss/train': 1.759976863861084} 08/31/2021 00:38:04 - INFO - __main__ - Step 62912: {'lr': 0.00031856975909008007, 'samples': 12079104, 'steps': 62911, 'loss/train': 1.2703163623809814} 08/31/2021 00:38:04 - INFO - __main__ - Step 62913: {'lr': 0.00031856465584313676, 'samples': 12079296, 'steps': 62912, 'loss/train': 1.2056124210357666} 08/31/2021 00:38:04 - INFO - __main__ - Step 62914: {'lr': 0.00031855955256529934, 'samples': 12079488, 'steps': 62913, 'loss/train': 0.919179379940033} 08/31/2021 00:38:05 - INFO - __main__ - Step 62915: {'lr': 0.00031855444925656996, 'samples': 12079680, 'steps': 62914, 'loss/train': 0.0315423347055912} 08/31/2021 00:38:06 - INFO - __main__ - Step 62916: {'lr': 0.0003185493459169511, 'samples': 12079872, 'steps': 62915, 'loss/train': 1.1956676244735718} 08/31/2021 00:38:07 - INFO - __main__ - Step 62917: {'lr': 0.00031854424254644493, 'samples': 12080064, 'steps': 62916, 'loss/train': 1.5870387554168701} 08/31/2021 00:38:07 - INFO - __main__ - Step 62918: {'lr': 0.0003185391391450538, 'samples': 12080256, 'steps': 62917, 'loss/train': 0.49478980898857117} 08/31/2021 00:38:07 - INFO - __main__ - Step 62919: {'lr': 0.00031853403571277994, 'samples': 12080448, 'steps': 62918, 'loss/train': 1.3881614208221436} 08/31/2021 00:38:08 - INFO - __main__ - Step 62920: {'lr': 0.0003185289322496257, 'samples': 12080640, 'steps': 62919, 'loss/train': 0.975806713104248} 08/31/2021 00:38:10 - INFO - __main__ - Step 62921: {'lr': 0.0003185238287555934, 'samples': 12080832, 'steps': 62920, 'loss/train': 1.5635299682617188} 08/31/2021 00:38:10 - INFO - __main__ - Step 62922: {'lr': 0.00031851872523068535, 'samples': 12081024, 'steps': 62921, 'loss/train': 1.104038119316101} 08/31/2021 00:38:10 - INFO - __main__ - Step 62923: {'lr': 0.0003185136216749038, 'samples': 12081216, 'steps': 62922, 'loss/train': 1.4624537229537964} 08/31/2021 00:38:11 - INFO - __main__ - Step 62924: {'lr': 0.00031850851808825107, 'samples': 12081408, 'steps': 62923, 'loss/train': 0.5157533884048462} 08/31/2021 00:38:11 - INFO - __main__ - Step 62925: {'lr': 0.0003185034144707294, 'samples': 12081600, 'steps': 62924, 'loss/train': 1.2011182308197021} 08/31/2021 00:38:11 - INFO - __main__ - Step 62926: {'lr': 0.00031849831082234124, 'samples': 12081792, 'steps': 62925, 'loss/train': 1.1958831548690796} 08/31/2021 00:38:13 - INFO - __main__ - Step 62927: {'lr': 0.0003184932071430888, 'samples': 12081984, 'steps': 62926, 'loss/train': 0.9131224751472473} 08/31/2021 00:38:13 - INFO - __main__ - Step 62928: {'lr': 0.00031848810343297433, 'samples': 12082176, 'steps': 62927, 'loss/train': 1.262769103050232} 08/31/2021 00:38:14 - INFO - __main__ - Step 62929: {'lr': 0.0003184829996920002, 'samples': 12082368, 'steps': 62928, 'loss/train': 0.8454135656356812} 08/31/2021 00:38:14 - INFO - __main__ - Step 62930: {'lr': 0.0003184778959201687, 'samples': 12082560, 'steps': 62929, 'loss/train': 1.1529934406280518} 08/31/2021 00:38:14 - INFO - __main__ - Step 62931: {'lr': 0.00031847279211748205, 'samples': 12082752, 'steps': 62930, 'loss/train': 1.0598291158676147} 08/31/2021 00:38:16 - INFO - __main__ - Step 62932: {'lr': 0.00031846768828394266, 'samples': 12082944, 'steps': 62931, 'loss/train': 0.9741289615631104} 08/31/2021 00:38:17 - INFO - __main__ - Step 62933: {'lr': 0.00031846258441955283, 'samples': 12083136, 'steps': 62932, 'loss/train': 1.4293122291564941} 08/31/2021 00:38:17 - INFO - __main__ - Step 62934: {'lr': 0.0003184574805243148, 'samples': 12083328, 'steps': 62933, 'loss/train': 0.4012071192264557} 08/31/2021 00:38:17 - INFO - __main__ - Step 62935: {'lr': 0.0003184523765982308, 'samples': 12083520, 'steps': 62934, 'loss/train': 2.620290517807007} 08/31/2021 00:38:18 - INFO - __main__ - Step 62936: {'lr': 0.0003184472726413032, 'samples': 12083712, 'steps': 62935, 'loss/train': 1.438469409942627} 08/31/2021 00:38:19 - INFO - __main__ - Step 62937: {'lr': 0.00031844216865353444, 'samples': 12083904, 'steps': 62936, 'loss/train': 1.6392807960510254} 08/31/2021 00:38:20 - INFO - __main__ - Step 62938: {'lr': 0.0003184370646349267, 'samples': 12084096, 'steps': 62937, 'loss/train': 1.5687018632888794} 08/31/2021 00:38:20 - INFO - __main__ - Step 62939: {'lr': 0.0003184319605854822, 'samples': 12084288, 'steps': 62938, 'loss/train': 1.1520119905471802} 08/31/2021 00:38:21 - INFO - __main__ - Step 62940: {'lr': 0.0003184268565052033, 'samples': 12084480, 'steps': 62939, 'loss/train': 0.9878177642822266} 08/31/2021 00:38:21 - INFO - __main__ - Step 62941: {'lr': 0.00031842175239409233, 'samples': 12084672, 'steps': 62940, 'loss/train': 1.4293748140335083} 08/31/2021 00:38:22 - INFO - __main__ - Step 62942: {'lr': 0.00031841664825215163, 'samples': 12084864, 'steps': 62941, 'loss/train': 0.6630688905715942} 08/31/2021 00:38:23 - INFO - __main__ - Step 62943: {'lr': 0.0003184115440793834, 'samples': 12085056, 'steps': 62942, 'loss/train': 0.6942741870880127} 08/31/2021 00:38:23 - INFO - __main__ - Step 62944: {'lr': 0.00031840643987579, 'samples': 12085248, 'steps': 62943, 'loss/train': 0.8337026834487915} 08/31/2021 00:38:24 - INFO - __main__ - Step 62945: {'lr': 0.0003184013356413737, 'samples': 12085440, 'steps': 62944, 'loss/train': 0.8776313066482544} 08/31/2021 00:38:24 - INFO - __main__ - Step 62946: {'lr': 0.0003183962313761368, 'samples': 12085632, 'steps': 62945, 'loss/train': 1.1396585702896118} 08/31/2021 00:38:26 - INFO - __main__ - Step 62947: {'lr': 0.0003183911270800816, 'samples': 12085824, 'steps': 62946, 'loss/train': 1.317644715309143} 08/31/2021 00:38:27 - INFO - __main__ - Step 62948: {'lr': 0.00031838602275321043, 'samples': 12086016, 'steps': 62947, 'loss/train': 1.0686110258102417} 08/31/2021 00:38:27 - INFO - __main__ - Step 62949: {'lr': 0.00031838091839552564, 'samples': 12086208, 'steps': 62948, 'loss/train': 1.1367689371109009} 08/31/2021 00:38:27 - INFO - __main__ - Step 62950: {'lr': 0.0003183758140070294, 'samples': 12086400, 'steps': 62949, 'loss/train': 1.4643429517745972} 08/31/2021 00:38:28 - INFO - __main__ - Step 62951: {'lr': 0.0003183707095877241, 'samples': 12086592, 'steps': 62950, 'loss/train': 0.9492879509925842} 08/31/2021 00:38:28 - INFO - __main__ - Step 62952: {'lr': 0.000318365605137612, 'samples': 12086784, 'steps': 62951, 'loss/train': 1.0416635274887085} 08/31/2021 00:38:30 - INFO - __main__ - Step 62953: {'lr': 0.00031836050065669536, 'samples': 12086976, 'steps': 62952, 'loss/train': 1.7356386184692383} 08/31/2021 00:38:30 - INFO - __main__ - Step 62954: {'lr': 0.00031835539614497656, 'samples': 12087168, 'steps': 62953, 'loss/train': 1.6329561471939087} 08/31/2021 00:38:30 - INFO - __main__ - Step 62955: {'lr': 0.00031835029160245785, 'samples': 12087360, 'steps': 62954, 'loss/train': 0.9815516471862793} 08/31/2021 00:38:31 - INFO - __main__ - Step 62956: {'lr': 0.0003183451870291416, 'samples': 12087552, 'steps': 62955, 'loss/train': 0.9800850749015808} 08/31/2021 00:38:31 - INFO - __main__ - Step 62957: {'lr': 0.00031834008242503014, 'samples': 12087744, 'steps': 62956, 'loss/train': 1.6980870962142944} 08/31/2021 00:38:33 - INFO - __main__ - Step 62958: {'lr': 0.0003183349777901256, 'samples': 12087936, 'steps': 62957, 'loss/train': 1.194597601890564} 08/31/2021 00:38:33 - INFO - __main__ - Step 62959: {'lr': 0.0003183298731244304, 'samples': 12088128, 'steps': 62958, 'loss/train': 1.356157660484314} 08/31/2021 00:38:33 - INFO - __main__ - Step 62960: {'lr': 0.0003183247684279468, 'samples': 12088320, 'steps': 62959, 'loss/train': 1.340624451637268} 08/31/2021 00:38:34 - INFO - __main__ - Step 62961: {'lr': 0.0003183196637006771, 'samples': 12088512, 'steps': 62960, 'loss/train': 1.62191903591156} 08/31/2021 00:38:34 - INFO - __main__ - Step 62962: {'lr': 0.0003183145589426236, 'samples': 12088704, 'steps': 62961, 'loss/train': 1.492060661315918} 08/31/2021 00:38:36 - INFO - __main__ - Step 62963: {'lr': 0.0003183094541537887, 'samples': 12088896, 'steps': 62962, 'loss/train': 1.9572557210922241} 08/31/2021 00:38:36 - INFO - __main__ - Step 62964: {'lr': 0.0003183043493341746, 'samples': 12089088, 'steps': 62963, 'loss/train': 1.39463472366333} 08/31/2021 00:38:37 - INFO - __main__ - Step 62965: {'lr': 0.0003182992444837835, 'samples': 12089280, 'steps': 62964, 'loss/train': 0.057413604110479355} 08/31/2021 00:38:37 - INFO - __main__ - Step 62966: {'lr': 0.0003182941396026179, 'samples': 12089472, 'steps': 62965, 'loss/train': 1.6563631296157837} 08/31/2021 00:38:37 - INFO - __main__ - Step 62967: {'lr': 0.00031828903469068, 'samples': 12089664, 'steps': 62966, 'loss/train': 1.1979161500930786} 08/31/2021 00:38:39 - INFO - __main__ - Step 62968: {'lr': 0.0003182839297479721, 'samples': 12089856, 'steps': 62967, 'loss/train': 1.4432965517044067} 08/31/2021 00:38:39 - INFO - __main__ - Step 62969: {'lr': 0.00031827882477449655, 'samples': 12090048, 'steps': 62968, 'loss/train': 1.5669358968734741} 08/31/2021 00:38:40 - INFO - __main__ - Step 62970: {'lr': 0.0003182737197702556, 'samples': 12090240, 'steps': 62969, 'loss/train': 1.0028834342956543} 08/31/2021 00:38:40 - INFO - __main__ - Step 62971: {'lr': 0.00031826861473525155, 'samples': 12090432, 'steps': 62970, 'loss/train': 0.9797742962837219} 08/31/2021 00:38:40 - INFO - __main__ - Step 62972: {'lr': 0.0003182635096694867, 'samples': 12090624, 'steps': 62971, 'loss/train': 0.9241951704025269} 08/31/2021 00:38:42 - INFO - __main__ - Step 62973: {'lr': 0.0003182584045729634, 'samples': 12090816, 'steps': 62972, 'loss/train': 1.3965548276901245} 08/31/2021 00:38:43 - INFO - __main__ - Step 62974: {'lr': 0.0003182532994456839, 'samples': 12091008, 'steps': 62973, 'loss/train': 0.6156963109970093} 08/31/2021 00:38:43 - INFO - __main__ - Step 62975: {'lr': 0.0003182481942876505, 'samples': 12091200, 'steps': 62974, 'loss/train': 1.5372915267944336} 08/31/2021 00:38:43 - INFO - __main__ - Step 62976: {'lr': 0.00031824308909886556, 'samples': 12091392, 'steps': 62975, 'loss/train': 0.8856565952301025} 08/31/2021 00:38:44 - INFO - __main__ - Step 62977: {'lr': 0.00031823798387933133, 'samples': 12091584, 'steps': 62976, 'loss/train': 1.0726079940795898} 08/31/2021 00:38:45 - INFO - __main__ - Step 62978: {'lr': 0.00031823287862905016, 'samples': 12091776, 'steps': 62977, 'loss/train': 0.05189863592386246} 08/31/2021 00:38:46 - INFO - __main__ - Step 62979: {'lr': 0.0003182277733480242, 'samples': 12091968, 'steps': 62978, 'loss/train': 1.3619191646575928} 08/31/2021 00:38:46 - INFO - __main__ - Step 62980: {'lr': 0.0003182226680362559, 'samples': 12092160, 'steps': 62979, 'loss/train': 1.3813800811767578} 08/31/2021 00:38:46 - INFO - __main__ - Step 62981: {'lr': 0.00031821756269374753, 'samples': 12092352, 'steps': 62980, 'loss/train': 0.7306810021400452} 08/31/2021 00:38:47 - INFO - __main__ - Step 62982: {'lr': 0.00031821245732050136, 'samples': 12092544, 'steps': 62981, 'loss/train': 1.6166220903396606} 08/31/2021 00:38:47 - INFO - __main__ - Step 62983: {'lr': 0.0003182073519165197, 'samples': 12092736, 'steps': 62982, 'loss/train': 0.7941630482673645} 08/31/2021 00:38:49 - INFO - __main__ - Step 62984: {'lr': 0.000318202246481805, 'samples': 12092928, 'steps': 62983, 'loss/train': 1.488255262374878} 08/31/2021 00:38:49 - INFO - __main__ - Step 62985: {'lr': 0.0003181971410163593, 'samples': 12093120, 'steps': 62984, 'loss/train': 1.0675220489501953} 08/31/2021 00:38:49 - INFO - __main__ - Step 62986: {'lr': 0.000318192035520185, 'samples': 12093312, 'steps': 62985, 'loss/train': 1.373632550239563} 08/31/2021 00:38:50 - INFO - __main__ - Step 62987: {'lr': 0.0003181869299932844, 'samples': 12093504, 'steps': 62986, 'loss/train': 1.4612897634506226} 08/31/2021 00:38:50 - INFO - __main__ - Step 62988: {'lr': 0.0003181818244356599, 'samples': 12093696, 'steps': 62987, 'loss/train': 1.4288593530654907} 08/31/2021 00:38:52 - INFO - __main__ - Step 62989: {'lr': 0.0003181767188473137, 'samples': 12093888, 'steps': 62988, 'loss/train': 0.8070335984230042} 08/31/2021 00:38:52 - INFO - __main__ - Step 62990: {'lr': 0.00031817161322824814, 'samples': 12094080, 'steps': 62989, 'loss/train': 1.9043244123458862} 08/31/2021 00:38:53 - INFO - __main__ - Step 62991: {'lr': 0.0003181665075784654, 'samples': 12094272, 'steps': 62990, 'loss/train': 1.4030388593673706} 08/31/2021 00:38:53 - INFO - __main__ - Step 62992: {'lr': 0.00031816140189796805, 'samples': 12094464, 'steps': 62991, 'loss/train': 1.0325473546981812} 08/31/2021 00:38:53 - INFO - __main__ - Step 62993: {'lr': 0.0003181562961867581, 'samples': 12094656, 'steps': 62992, 'loss/train': 1.1897872686386108} 08/31/2021 00:38:55 - INFO - __main__ - Step 62994: {'lr': 0.000318151190444838, 'samples': 12094848, 'steps': 62993, 'loss/train': 1.2770894765853882} 08/31/2021 00:38:56 - INFO - __main__ - Step 62995: {'lr': 0.00031814608467221005, 'samples': 12095040, 'steps': 62994, 'loss/train': 0.8532683849334717} 08/31/2021 00:38:56 - INFO - __main__ - Step 62996: {'lr': 0.0003181409788688765, 'samples': 12095232, 'steps': 62995, 'loss/train': 1.0375829935073853} 08/31/2021 00:38:56 - INFO - __main__ - Step 62997: {'lr': 0.0003181358730348397, 'samples': 12095424, 'steps': 62996, 'loss/train': 1.8337432146072388} 08/31/2021 00:38:57 - INFO - __main__ - Step 62998: {'lr': 0.00031813076717010193, 'samples': 12095616, 'steps': 62997, 'loss/train': 1.4218425750732422} 08/31/2021 00:38:57 - INFO - __main__ - Step 62999: {'lr': 0.00031812566127466545, 'samples': 12095808, 'steps': 62998, 'loss/train': 1.3612886667251587} 08/31/2021 00:38:59 - INFO - __main__ - Step 63000: {'lr': 0.00031812055534853265, 'samples': 12096000, 'steps': 62999, 'loss/train': 0.10417603701353073} 08/31/2021 00:39:00 - INFO - __main__ - Step 63001: {'lr': 0.0003181154493917057, 'samples': 12096192, 'steps': 63000, 'loss/train': 0.9927434921264648} 08/31/2021 00:39:00 - INFO - __main__ - Step 63002: {'lr': 0.00031811034340418706, 'samples': 12096384, 'steps': 63001, 'loss/train': 1.197510838508606} 08/31/2021 00:39:00 - INFO - __main__ - Step 63003: {'lr': 0.00031810523738597893, 'samples': 12096576, 'steps': 63002, 'loss/train': 1.3705716133117676} 08/31/2021 00:39:01 - INFO - __main__ - Step 63004: {'lr': 0.0003181001313370836, 'samples': 12096768, 'steps': 63003, 'loss/train': 1.2630765438079834} 08/31/2021 00:39:01 - INFO - __main__ - Step 63005: {'lr': 0.00031809502525750346, 'samples': 12096960, 'steps': 63004, 'loss/train': 1.4596784114837646} 08/31/2021 00:39:02 - INFO - __main__ - Step 63006: {'lr': 0.0003180899191472407, 'samples': 12097152, 'steps': 63005, 'loss/train': 1.556412935256958} 08/31/2021 00:39:03 - INFO - __main__ - Step 63007: {'lr': 0.00031808481300629765, 'samples': 12097344, 'steps': 63006, 'loss/train': 1.2368918657302856} 08/31/2021 00:39:03 - INFO - __main__ - Step 63008: {'lr': 0.0003180797068346767, 'samples': 12097536, 'steps': 63007, 'loss/train': 1.5900626182556152} 08/31/2021 00:39:04 - INFO - __main__ - Step 63009: {'lr': 0.00031807460063238005, 'samples': 12097728, 'steps': 63008, 'loss/train': 1.3460444211959839} 08/31/2021 00:39:04 - INFO - __main__ - Step 63010: {'lr': 0.00031806949439941006, 'samples': 12097920, 'steps': 63009, 'loss/train': 0.9966131448745728} 08/31/2021 00:39:06 - INFO - __main__ - Step 63011: {'lr': 0.000318064388135769, 'samples': 12098112, 'steps': 63010, 'loss/train': 1.3418478965759277} 08/31/2021 00:39:06 - INFO - __main__ - Step 63012: {'lr': 0.00031805928184145917, 'samples': 12098304, 'steps': 63011, 'loss/train': 1.2125086784362793} 08/31/2021 00:39:06 - INFO - __main__ - Step 63013: {'lr': 0.00031805417551648287, 'samples': 12098496, 'steps': 63012, 'loss/train': 1.2044447660446167} 08/31/2021 00:39:07 - INFO - __main__ - Step 63014: {'lr': 0.00031804906916084235, 'samples': 12098688, 'steps': 63013, 'loss/train': 1.5268734693527222} 08/31/2021 00:39:07 - INFO - __main__ - Step 63015: {'lr': 0.00031804396277454005, 'samples': 12098880, 'steps': 63014, 'loss/train': 1.4524513483047485} 08/31/2021 00:39:09 - INFO - __main__ - Step 63016: {'lr': 0.0003180388563575782, 'samples': 12099072, 'steps': 63015, 'loss/train': 1.7991358041763306} 08/31/2021 00:39:09 - INFO - __main__ - Step 63017: {'lr': 0.0003180337499099591, 'samples': 12099264, 'steps': 63016, 'loss/train': 1.2820584774017334} 08/31/2021 00:39:09 - INFO - __main__ - Step 63018: {'lr': 0.000318028643431685, 'samples': 12099456, 'steps': 63017, 'loss/train': 0.1705317348241806} 08/31/2021 00:39:10 - INFO - __main__ - Step 63019: {'lr': 0.0003180235369227582, 'samples': 12099648, 'steps': 63018, 'loss/train': 1.3244625329971313} 08/31/2021 00:39:10 - INFO - __main__ - Step 63020: {'lr': 0.0003180184303831811, 'samples': 12099840, 'steps': 63019, 'loss/train': 0.8981305360794067} 08/31/2021 00:39:12 - INFO - __main__ - Step 63021: {'lr': 0.0003180133238129559, 'samples': 12100032, 'steps': 63020, 'loss/train': 1.0494585037231445} 08/31/2021 00:39:13 - INFO - __main__ - Step 63022: {'lr': 0.000318008217212085, 'samples': 12100224, 'steps': 63021, 'loss/train': 0.4769158959388733} 08/31/2021 00:39:13 - INFO - __main__ - Step 63023: {'lr': 0.00031800311058057066, 'samples': 12100416, 'steps': 63022, 'loss/train': 1.159537434577942} 08/31/2021 00:39:13 - INFO - __main__ - Step 63024: {'lr': 0.0003179980039184152, 'samples': 12100608, 'steps': 63023, 'loss/train': 2.043070077896118} 08/31/2021 00:39:14 - INFO - __main__ - Step 63025: {'lr': 0.00031799289722562075, 'samples': 12100800, 'steps': 63024, 'loss/train': 1.2303053140640259} 08/31/2021 00:39:14 - INFO - __main__ - Step 63026: {'lr': 0.00031798779050218985, 'samples': 12100992, 'steps': 63025, 'loss/train': 0.02499449998140335} 08/31/2021 00:39:16 - INFO - __main__ - Step 63027: {'lr': 0.00031798268374812465, 'samples': 12101184, 'steps': 63026, 'loss/train': 0.9491069912910461} 08/31/2021 00:39:16 - INFO - __main__ - Step 63028: {'lr': 0.00031797757696342755, 'samples': 12101376, 'steps': 63027, 'loss/train': 1.1260814666748047} 08/31/2021 00:39:16 - INFO - __main__ - Step 63029: {'lr': 0.0003179724701481007, 'samples': 12101568, 'steps': 63028, 'loss/train': 0.6883891224861145} 08/31/2021 00:39:17 - INFO - __main__ - Step 63030: {'lr': 0.0003179673633021466, 'samples': 12101760, 'steps': 63029, 'loss/train': 0.05407513305544853} 08/31/2021 00:39:17 - INFO - __main__ - Step 63031: {'lr': 0.00031796225642556755, 'samples': 12101952, 'steps': 63030, 'loss/train': 0.9859893918037415} 08/31/2021 00:39:19 - INFO - __main__ - Step 63032: {'lr': 0.0003179571495183656, 'samples': 12102144, 'steps': 63031, 'loss/train': 1.5856789350509644} 08/31/2021 00:39:19 - INFO - __main__ - Step 63033: {'lr': 0.00031795204258054324, 'samples': 12102336, 'steps': 63032, 'loss/train': 0.9734160304069519} 08/31/2021 00:39:19 - INFO - __main__ - Step 63034: {'lr': 0.00031794693561210276, 'samples': 12102528, 'steps': 63033, 'loss/train': 1.4012688398361206} 08/31/2021 00:39:20 - INFO - __main__ - Step 63035: {'lr': 0.00031794182861304637, 'samples': 12102720, 'steps': 63034, 'loss/train': 1.1835415363311768} 08/31/2021 00:39:20 - INFO - __main__ - Step 63036: {'lr': 0.0003179367215833765, 'samples': 12102912, 'steps': 63035, 'loss/train': 1.5530019998550415} 08/31/2021 00:39:20 - INFO - __main__ - Step 63037: {'lr': 0.00031793161452309547, 'samples': 12103104, 'steps': 63036, 'loss/train': 1.7323505878448486} 08/31/2021 00:39:22 - INFO - __main__ - Step 63038: {'lr': 0.0003179265074322054, 'samples': 12103296, 'steps': 63037, 'loss/train': 1.4878196716308594} 08/31/2021 00:39:22 - INFO - __main__ - Step 63039: {'lr': 0.0003179214003107087, 'samples': 12103488, 'steps': 63038, 'loss/train': 0.944166898727417} 08/31/2021 00:39:23 - INFO - __main__ - Step 63040: {'lr': 0.0003179162931586077, 'samples': 12103680, 'steps': 63039, 'loss/train': 1.7182337045669556} 08/31/2021 00:39:23 - INFO - __main__ - Step 63041: {'lr': 0.00031791118597590464, 'samples': 12103872, 'steps': 63040, 'loss/train': 1.651423692703247} 08/31/2021 00:39:23 - INFO - __main__ - Step 63042: {'lr': 0.00031790607876260187, 'samples': 12104064, 'steps': 63041, 'loss/train': 1.2245123386383057} 08/31/2021 00:39:25 - INFO - __main__ - Step 63043: {'lr': 0.0003179009715187016, 'samples': 12104256, 'steps': 63042, 'loss/train': 1.321390986442566} 08/31/2021 00:39:25 - INFO - __main__ - Step 63044: {'lr': 0.00031789586424420637, 'samples': 12104448, 'steps': 63043, 'loss/train': 1.4393770694732666} 08/31/2021 00:39:26 - INFO - __main__ - Step 63045: {'lr': 0.0003178907569391182, 'samples': 12104640, 'steps': 63044, 'loss/train': 1.7521419525146484} 08/31/2021 00:39:26 - INFO - __main__ - Step 63046: {'lr': 0.00031788564960343946, 'samples': 12104832, 'steps': 63045, 'loss/train': 1.107192873954773} 08/31/2021 00:39:26 - INFO - __main__ - Step 63047: {'lr': 0.0003178805422371725, 'samples': 12105024, 'steps': 63046, 'loss/train': 1.7872743606567383} 08/31/2021 00:39:28 - INFO - __main__ - Step 63048: {'lr': 0.0003178754348403197, 'samples': 12105216, 'steps': 63047, 'loss/train': 1.923681378364563} 08/31/2021 00:39:29 - INFO - __main__ - Step 63049: {'lr': 0.00031787032741288315, 'samples': 12105408, 'steps': 63048, 'loss/train': 0.032367922365665436} 08/31/2021 00:39:29 - INFO - __main__ - Step 63050: {'lr': 0.0003178652199548653, 'samples': 12105600, 'steps': 63049, 'loss/train': 4.582437515258789} 08/31/2021 00:39:29 - INFO - __main__ - Step 63051: {'lr': 0.00031786011246626855, 'samples': 12105792, 'steps': 63050, 'loss/train': 1.433213710784912} 08/31/2021 00:39:30 - INFO - __main__ - Step 63052: {'lr': 0.000317855004947095, 'samples': 12105984, 'steps': 63051, 'loss/train': 1.4464902877807617} 08/31/2021 00:39:32 - INFO - __main__ - Step 63053: {'lr': 0.00031784989739734706, 'samples': 12106176, 'steps': 63052, 'loss/train': 1.1776795387268066} 08/31/2021 00:39:32 - INFO - __main__ - Step 63054: {'lr': 0.000317844789817027, 'samples': 12106368, 'steps': 63053, 'loss/train': 1.7914258241653442} 08/31/2021 00:39:32 - INFO - __main__ - Step 63055: {'lr': 0.0003178396822061371, 'samples': 12106560, 'steps': 63054, 'loss/train': 1.3739598989486694} 08/31/2021 00:39:33 - INFO - __main__ - Step 63056: {'lr': 0.0003178345745646797, 'samples': 12106752, 'steps': 63055, 'loss/train': 1.30812406539917} 08/31/2021 00:39:33 - INFO - __main__ - Step 63057: {'lr': 0.00031782946689265713, 'samples': 12106944, 'steps': 63056, 'loss/train': 1.307167649269104} 08/31/2021 00:39:35 - INFO - __main__ - Step 63058: {'lr': 0.0003178243591900716, 'samples': 12107136, 'steps': 63057, 'loss/train': 1.0261181592941284} 08/31/2021 00:39:35 - INFO - __main__ - Step 63059: {'lr': 0.0003178192514569255, 'samples': 12107328, 'steps': 63058, 'loss/train': 0.8140150904655457} 08/31/2021 00:39:35 - INFO - __main__ - Step 63060: {'lr': 0.000317814143693221, 'samples': 12107520, 'steps': 63059, 'loss/train': 0.15934871137142181} 08/31/2021 00:39:36 - INFO - __main__ - Step 63061: {'lr': 0.00031780903589896057, 'samples': 12107712, 'steps': 63060, 'loss/train': 1.6114236116409302} 08/31/2021 00:39:36 - INFO - __main__ - Step 63062: {'lr': 0.0003178039280741464, 'samples': 12107904, 'steps': 63061, 'loss/train': 1.145565152168274} 08/31/2021 00:39:38 - INFO - __main__ - Step 63063: {'lr': 0.00031779882021878086, 'samples': 12108096, 'steps': 63062, 'loss/train': 0.07455114275217056} 08/31/2021 00:39:38 - INFO - __main__ - Step 63064: {'lr': 0.00031779371233286617, 'samples': 12108288, 'steps': 63063, 'loss/train': 1.3190441131591797} 08/31/2021 00:39:39 - INFO - __main__ - Step 63065: {'lr': 0.00031778860441640473, 'samples': 12108480, 'steps': 63064, 'loss/train': 1.8794481754302979} 08/31/2021 00:39:39 - INFO - __main__ - Step 63066: {'lr': 0.00031778349646939877, 'samples': 12108672, 'steps': 63065, 'loss/train': 1.7126928567886353} 08/31/2021 00:39:39 - INFO - __main__ - Step 63067: {'lr': 0.0003177783884918506, 'samples': 12108864, 'steps': 63066, 'loss/train': 1.6106958389282227} 08/31/2021 00:39:40 - INFO - __main__ - Step 63068: {'lr': 0.0003177732804837626, 'samples': 12109056, 'steps': 63067, 'loss/train': 0.7076658010482788} 08/31/2021 00:39:41 - INFO - __main__ - Step 63069: {'lr': 0.0003177681724451369, 'samples': 12109248, 'steps': 63068, 'loss/train': 1.314157485961914} 08/31/2021 00:39:42 - INFO - __main__ - Step 63070: {'lr': 0.00031776306437597594, 'samples': 12109440, 'steps': 63069, 'loss/train': 1.6956833600997925} 08/31/2021 00:39:42 - INFO - __main__ - Step 63071: {'lr': 0.000317757956276282, 'samples': 12109632, 'steps': 63070, 'loss/train': 0.9436410069465637} 08/31/2021 00:39:42 - INFO - __main__ - Step 63072: {'lr': 0.00031775284814605743, 'samples': 12109824, 'steps': 63071, 'loss/train': 5.90287971496582} 08/31/2021 00:39:43 - INFO - __main__ - Step 63073: {'lr': 0.00031774773998530443, 'samples': 12110016, 'steps': 63072, 'loss/train': 0.977790117263794} 08/31/2021 00:39:44 - INFO - __main__ - Step 63074: {'lr': 0.00031774263179402533, 'samples': 12110208, 'steps': 63073, 'loss/train': 1.7161469459533691} 08/31/2021 00:39:45 - INFO - __main__ - Step 63075: {'lr': 0.0003177375235722225, 'samples': 12110400, 'steps': 63074, 'loss/train': 1.2258538007736206} 08/31/2021 00:39:45 - INFO - __main__ - Step 63076: {'lr': 0.00031773241531989803, 'samples': 12110592, 'steps': 63075, 'loss/train': 1.58267343044281} 08/31/2021 00:39:46 - INFO - __main__ - Step 63077: {'lr': 0.00031772730703705454, 'samples': 12110784, 'steps': 63076, 'loss/train': 1.3920739889144897} 08/31/2021 00:39:46 - INFO - __main__ - Step 63078: {'lr': 0.0003177221987236941, 'samples': 12110976, 'steps': 63077, 'loss/train': 1.3677998781204224} 08/31/2021 00:39:46 - INFO - __main__ - Step 63079: {'lr': 0.0003177170903798191, 'samples': 12111168, 'steps': 63078, 'loss/train': 1.4564796686172485} 08/31/2021 00:39:48 - INFO - __main__ - Step 63080: {'lr': 0.0003177119820054318, 'samples': 12111360, 'steps': 63079, 'loss/train': 1.2047924995422363} 08/31/2021 00:39:48 - INFO - __main__ - Step 63081: {'lr': 0.0003177068736005346, 'samples': 12111552, 'steps': 63080, 'loss/train': 0.8504614233970642} 08/31/2021 00:39:49 - INFO - __main__ - Step 63082: {'lr': 0.00031770176516512965, 'samples': 12111744, 'steps': 63081, 'loss/train': 0.22426463663578033} 08/31/2021 00:39:49 - INFO - __main__ - Step 63083: {'lr': 0.0003176966566992193, 'samples': 12111936, 'steps': 63082, 'loss/train': 1.7633329629898071} 08/31/2021 00:39:49 - INFO - __main__ - Step 63084: {'lr': 0.00031769154820280606, 'samples': 12112128, 'steps': 63083, 'loss/train': 1.4608063697814941} 08/31/2021 00:39:51 - INFO - __main__ - Step 63085: {'lr': 0.0003176864396758919, 'samples': 12112320, 'steps': 63084, 'loss/train': 1.448044776916504} 08/31/2021 00:39:51 - INFO - __main__ - Step 63086: {'lr': 0.0003176813311184793, 'samples': 12112512, 'steps': 63085, 'loss/train': 1.7068331241607666} 08/31/2021 00:39:52 - INFO - __main__ - Step 63087: {'lr': 0.0003176762225305705, 'samples': 12112704, 'steps': 63086, 'loss/train': 1.0338786840438843} 08/31/2021 00:39:52 - INFO - __main__ - Step 63088: {'lr': 0.0003176711139121679, 'samples': 12112896, 'steps': 63087, 'loss/train': 1.4335538148880005} 08/31/2021 00:39:52 - INFO - __main__ - Step 63089: {'lr': 0.00031766600526327373, 'samples': 12113088, 'steps': 63088, 'loss/train': 0.9933000802993774} 08/31/2021 00:39:54 - INFO - __main__ - Step 63090: {'lr': 0.00031766089658389024, 'samples': 12113280, 'steps': 63089, 'loss/train': 0.9718862175941467} 08/31/2021 00:39:54 - INFO - __main__ - Step 63091: {'lr': 0.00031765578787401995, 'samples': 12113472, 'steps': 63090, 'loss/train': 1.038837194442749} 08/31/2021 00:39:55 - INFO - __main__ - Step 63092: {'lr': 0.00031765067913366483, 'samples': 12113664, 'steps': 63091, 'loss/train': 1.3428399562835693} 08/31/2021 00:39:55 - INFO - __main__ - Step 63093: {'lr': 0.0003176455703628274, 'samples': 12113856, 'steps': 63092, 'loss/train': 0.3414855897426605} 08/31/2021 00:39:55 - INFO - __main__ - Step 63094: {'lr': 0.00031764046156151, 'samples': 12114048, 'steps': 63093, 'loss/train': 1.4115997552871704} 08/31/2021 00:39:56 - INFO - __main__ - Step 63095: {'lr': 0.00031763535272971477, 'samples': 12114240, 'steps': 63094, 'loss/train': 0.4223729074001312} 08/31/2021 00:39:57 - INFO - __main__ - Step 63096: {'lr': 0.0003176302438674441, 'samples': 12114432, 'steps': 63095, 'loss/train': 1.3511242866516113} 08/31/2021 00:39:58 - INFO - __main__ - Step 63097: {'lr': 0.00031762513497470034, 'samples': 12114624, 'steps': 63096, 'loss/train': 0.907945990562439} 08/31/2021 00:39:58 - INFO - __main__ - Step 63098: {'lr': 0.00031762002605148574, 'samples': 12114816, 'steps': 63097, 'loss/train': 1.3158848285675049} 08/31/2021 00:39:58 - INFO - __main__ - Step 63099: {'lr': 0.00031761491709780256, 'samples': 12115008, 'steps': 63098, 'loss/train': 1.4728797674179077} 08/31/2021 00:39:59 - INFO - __main__ - Step 63100: {'lr': 0.00031760980811365314, 'samples': 12115200, 'steps': 63099, 'loss/train': 1.3031671047210693} 08/31/2021 00:40:00 - INFO - __main__ - Step 63101: {'lr': 0.00031760469909903976, 'samples': 12115392, 'steps': 63100, 'loss/train': 1.0940608978271484} 08/31/2021 00:40:01 - INFO - __main__ - Step 63102: {'lr': 0.0003175995900539648, 'samples': 12115584, 'steps': 63101, 'loss/train': 1.2090750932693481} 08/31/2021 00:40:01 - INFO - __main__ - Step 63103: {'lr': 0.00031759448097843046, 'samples': 12115776, 'steps': 63102, 'loss/train': 1.8495925664901733} 08/31/2021 00:40:02 - INFO - __main__ - Step 63104: {'lr': 0.00031758937187243916, 'samples': 12115968, 'steps': 63103, 'loss/train': 0.10331092029809952} 08/31/2021 00:40:02 - INFO - __main__ - Step 63105: {'lr': 0.0003175842627359931, 'samples': 12116160, 'steps': 63104, 'loss/train': 1.582945704460144} 08/31/2021 00:40:03 - INFO - __main__ - Step 63106: {'lr': 0.00031757915356909463, 'samples': 12116352, 'steps': 63105, 'loss/train': 1.1520471572875977} 08/31/2021 00:40:04 - INFO - __main__ - Step 63107: {'lr': 0.00031757404437174596, 'samples': 12116544, 'steps': 63106, 'loss/train': 1.806589126586914} 08/31/2021 00:40:04 - INFO - __main__ - Step 63108: {'lr': 0.00031756893514394953, 'samples': 12116736, 'steps': 63107, 'loss/train': 0.9210139513015747} 08/31/2021 00:40:05 - INFO - __main__ - Step 63109: {'lr': 0.0003175638258857075, 'samples': 12116928, 'steps': 63108, 'loss/train': 1.1956868171691895} 08/31/2021 00:40:05 - INFO - __main__ - Step 63110: {'lr': 0.00031755871659702235, 'samples': 12117120, 'steps': 63109, 'loss/train': 1.0390946865081787} 08/31/2021 00:40:07 - INFO - __main__ - Step 63111: {'lr': 0.0003175536072778963, 'samples': 12117312, 'steps': 63110, 'loss/train': 1.1769704818725586} 08/31/2021 00:40:07 - INFO - __main__ - Step 63112: {'lr': 0.0003175484979283316, 'samples': 12117504, 'steps': 63111, 'loss/train': 0.8051005005836487} 08/31/2021 00:40:08 - INFO - __main__ - Step 63113: {'lr': 0.00031754338854833055, 'samples': 12117696, 'steps': 63112, 'loss/train': 1.5408111810684204} 08/31/2021 00:40:08 - INFO - __main__ - Step 63114: {'lr': 0.0003175382791378955, 'samples': 12117888, 'steps': 63113, 'loss/train': 1.242702603340149} 08/31/2021 00:40:08 - INFO - __main__ - Step 63115: {'lr': 0.0003175331696970288, 'samples': 12118080, 'steps': 63114, 'loss/train': 1.088120460510254} 08/31/2021 00:40:10 - INFO - __main__ - Step 63116: {'lr': 0.0003175280602257327, 'samples': 12118272, 'steps': 63115, 'loss/train': 1.9441035985946655} 08/31/2021 00:40:10 - INFO - __main__ - Step 63117: {'lr': 0.0003175229507240094, 'samples': 12118464, 'steps': 63116, 'loss/train': 1.3617537021636963} 08/31/2021 00:40:11 - INFO - __main__ - Step 63118: {'lr': 0.0003175178411918614, 'samples': 12118656, 'steps': 63117, 'loss/train': 0.7511619925498962} 08/31/2021 00:40:11 - INFO - __main__ - Step 63119: {'lr': 0.00031751273162929083, 'samples': 12118848, 'steps': 63118, 'loss/train': 1.2667649984359741} 08/31/2021 00:40:11 - INFO - __main__ - Step 63120: {'lr': 0.00031750762203630015, 'samples': 12119040, 'steps': 63119, 'loss/train': 1.3103642463684082} 08/31/2021 00:40:13 - INFO - __main__ - Step 63121: {'lr': 0.00031750251241289147, 'samples': 12119232, 'steps': 63120, 'loss/train': 0.9572380185127258} 08/31/2021 00:40:14 - INFO - __main__ - Step 63122: {'lr': 0.0003174974027590672, 'samples': 12119424, 'steps': 63121, 'loss/train': 1.4243015050888062} 08/31/2021 00:40:14 - INFO - __main__ - Step 63123: {'lr': 0.00031749229307482976, 'samples': 12119616, 'steps': 63122, 'loss/train': 5.5112833976745605} 08/31/2021 00:40:14 - INFO - __main__ - Step 63124: {'lr': 0.00031748718336018124, 'samples': 12119808, 'steps': 63123, 'loss/train': 5.453982353210449} 08/31/2021 00:40:15 - INFO - __main__ - Step 63125: {'lr': 0.00031748207361512415, 'samples': 12120000, 'steps': 63124, 'loss/train': 2.2082791328430176} 08/31/2021 00:40:15 - INFO - __main__ - Step 63126: {'lr': 0.00031747696383966056, 'samples': 12120192, 'steps': 63125, 'loss/train': 0.8992576003074646} 08/31/2021 00:40:15 - INFO - __main__ - Step 63127: {'lr': 0.0003174718540337929, 'samples': 12120384, 'steps': 63126, 'loss/train': 0.8500070571899414} 08/31/2021 00:40:17 - INFO - __main__ - Step 63128: {'lr': 0.0003174667441975235, 'samples': 12120576, 'steps': 63127, 'loss/train': 1.1992634534835815} 08/31/2021 00:40:17 - INFO - __main__ - Step 63129: {'lr': 0.0003174616343308546, 'samples': 12120768, 'steps': 63128, 'loss/train': 1.139076590538025} 08/31/2021 00:40:18 - INFO - __main__ - Step 63130: {'lr': 0.0003174565244337886, 'samples': 12120960, 'steps': 63129, 'loss/train': 1.4488835334777832} 08/31/2021 00:40:18 - INFO - __main__ - Step 63131: {'lr': 0.0003174514145063277, 'samples': 12121152, 'steps': 63130, 'loss/train': 1.6467238664627075} 08/31/2021 00:40:18 - INFO - __main__ - Step 63132: {'lr': 0.00031744630454847415, 'samples': 12121344, 'steps': 63131, 'loss/train': 0.39889249205589294} 08/31/2021 00:40:20 - INFO - __main__ - Step 63133: {'lr': 0.0003174411945602304, 'samples': 12121536, 'steps': 63132, 'loss/train': 1.2035551071166992} 08/31/2021 00:40:20 - INFO - __main__ - Step 63134: {'lr': 0.00031743608454159864, 'samples': 12121728, 'steps': 63133, 'loss/train': 1.3389517068862915} 08/31/2021 00:40:21 - INFO - __main__ - Step 63135: {'lr': 0.0003174309744925813, 'samples': 12121920, 'steps': 63134, 'loss/train': 1.0536460876464844} 08/31/2021 00:40:21 - INFO - __main__ - Step 63136: {'lr': 0.00031742586441318055, 'samples': 12122112, 'steps': 63135, 'loss/train': 1.5637762546539307} 08/31/2021 00:40:22 - INFO - __main__ - Step 63137: {'lr': 0.0003174207543033988, 'samples': 12122304, 'steps': 63136, 'loss/train': 1.72144615650177} 08/31/2021 00:40:23 - INFO - __main__ - Step 63138: {'lr': 0.0003174156441632383, 'samples': 12122496, 'steps': 63137, 'loss/train': 1.191664695739746} 08/31/2021 00:40:23 - INFO - __main__ - Step 63139: {'lr': 0.0003174105339927013, 'samples': 12122688, 'steps': 63138, 'loss/train': 0.9077399969100952} 08/31/2021 00:40:24 - INFO - __main__ - Step 63140: {'lr': 0.00031740542379179017, 'samples': 12122880, 'steps': 63139, 'loss/train': 1.5284174680709839} 08/31/2021 00:40:24 - INFO - __main__ - Step 63141: {'lr': 0.00031740031356050717, 'samples': 12123072, 'steps': 63140, 'loss/train': 1.2190510034561157} 08/31/2021 00:40:24 - INFO - __main__ - Step 63142: {'lr': 0.00031739520329885463, 'samples': 12123264, 'steps': 63141, 'loss/train': 0.5428723096847534} 08/31/2021 00:40:26 - INFO - __main__ - Step 63143: {'lr': 0.00031739009300683484, 'samples': 12123456, 'steps': 63142, 'loss/train': 1.1110221147537231} 08/31/2021 00:40:26 - INFO - __main__ - Step 63144: {'lr': 0.00031738498268445023, 'samples': 12123648, 'steps': 63143, 'loss/train': 0.9718665480613708} 08/31/2021 00:40:27 - INFO - __main__ - Step 63145: {'lr': 0.0003173798723317029, 'samples': 12123840, 'steps': 63144, 'loss/train': 1.040406346321106} 08/31/2021 00:40:27 - INFO - __main__ - Step 63146: {'lr': 0.00031737476194859524, 'samples': 12124032, 'steps': 63145, 'loss/train': 2.130223035812378} 08/31/2021 00:40:27 - INFO - __main__ - Step 63147: {'lr': 0.0003173696515351295, 'samples': 12124224, 'steps': 63146, 'loss/train': 1.354182243347168} 08/31/2021 00:40:29 - INFO - __main__ - Step 63148: {'lr': 0.00031736454109130815, 'samples': 12124416, 'steps': 63147, 'loss/train': 1.524686574935913} 08/31/2021 00:40:29 - INFO - __main__ - Step 63149: {'lr': 0.0003173594306171333, 'samples': 12124608, 'steps': 63148, 'loss/train': 0.95267254114151} 08/31/2021 00:40:30 - INFO - __main__ - Step 63150: {'lr': 0.0003173543201126073, 'samples': 12124800, 'steps': 63149, 'loss/train': 1.147179365158081} 08/31/2021 00:40:30 - INFO - __main__ - Step 63151: {'lr': 0.0003173492095777326, 'samples': 12124992, 'steps': 63150, 'loss/train': 1.6224397420883179} 08/31/2021 00:40:30 - INFO - __main__ - Step 63152: {'lr': 0.0003173440990125113, 'samples': 12125184, 'steps': 63151, 'loss/train': 1.3801681995391846} 08/31/2021 00:40:31 - INFO - __main__ - Step 63153: {'lr': 0.0003173389884169458, 'samples': 12125376, 'steps': 63152, 'loss/train': 0.9582184553146362} 08/31/2021 00:40:33 - INFO - __main__ - Step 63154: {'lr': 0.0003173338777910384, 'samples': 12125568, 'steps': 63153, 'loss/train': 0.843764066696167} 08/31/2021 00:40:34 - INFO - __main__ - Step 63155: {'lr': 0.0003173287671347914, 'samples': 12125760, 'steps': 63154, 'loss/train': 2.8343892097473145} 08/31/2021 00:40:34 - INFO - __main__ - Step 63156: {'lr': 0.00031732365644820704, 'samples': 12125952, 'steps': 63155, 'loss/train': 3.9675540924072266} 08/31/2021 00:40:34 - INFO - __main__ - Step 63157: {'lr': 0.0003173185457312877, 'samples': 12126144, 'steps': 63156, 'loss/train': 2.1942832469940186} 08/31/2021 00:40:35 - INFO - __main__ - Step 63158: {'lr': 0.00031731343498403577, 'samples': 12126336, 'steps': 63157, 'loss/train': 1.675927996635437} 08/31/2021 00:40:35 - INFO - __main__ - Step 63159: {'lr': 0.0003173083242064534, 'samples': 12126528, 'steps': 63158, 'loss/train': 1.6212207078933716} 08/31/2021 00:40:37 - INFO - __main__ - Step 63160: {'lr': 0.0003173032133985428, 'samples': 12126720, 'steps': 63159, 'loss/train': 1.3295629024505615} 08/31/2021 00:40:37 - INFO - __main__ - Step 63161: {'lr': 0.00031729810256030653, 'samples': 12126912, 'steps': 63160, 'loss/train': 1.1325888633728027} 08/31/2021 00:40:38 - INFO - __main__ - Step 63162: {'lr': 0.00031729299169174673, 'samples': 12127104, 'steps': 63161, 'loss/train': 1.7866268157958984} 08/31/2021 00:40:38 - INFO - __main__ - Step 63163: {'lr': 0.0003172878807928658, 'samples': 12127296, 'steps': 63162, 'loss/train': 1.4685992002487183} 08/31/2021 00:40:38 - INFO - __main__ - Step 63164: {'lr': 0.00031728276986366593, 'samples': 12127488, 'steps': 63163, 'loss/train': 0.8184781670570374} 08/31/2021 00:40:40 - INFO - __main__ - Step 63165: {'lr': 0.0003172776589041496, 'samples': 12127680, 'steps': 63164, 'loss/train': 1.5668963193893433} 08/31/2021 00:40:41 - INFO - __main__ - Step 63166: {'lr': 0.00031727254791431885, 'samples': 12127872, 'steps': 63165, 'loss/train': 0.1272733509540558} 08/31/2021 00:40:41 - INFO - __main__ - Step 63167: {'lr': 0.0003172674368941762, 'samples': 12128064, 'steps': 63166, 'loss/train': 1.3992900848388672} 08/31/2021 00:40:41 - INFO - __main__ - Step 63168: {'lr': 0.0003172623258437238, 'samples': 12128256, 'steps': 63167, 'loss/train': 0.9523813724517822} 08/31/2021 00:40:42 - INFO - __main__ - Step 63169: {'lr': 0.00031725721476296413, 'samples': 12128448, 'steps': 63168, 'loss/train': 1.7060799598693848} 08/31/2021 00:40:43 - INFO - __main__ - Step 63170: {'lr': 0.00031725210365189936, 'samples': 12128640, 'steps': 63169, 'loss/train': 1.2009468078613281} 08/31/2021 00:40:44 - INFO - __main__ - Step 63171: {'lr': 0.00031724699251053185, 'samples': 12128832, 'steps': 63170, 'loss/train': 1.3452955484390259} 08/31/2021 00:40:44 - INFO - __main__ - Step 63172: {'lr': 0.0003172418813388639, 'samples': 12129024, 'steps': 63171, 'loss/train': 1.4259475469589233} 08/31/2021 00:40:44 - INFO - __main__ - Step 63173: {'lr': 0.00031723677013689776, 'samples': 12129216, 'steps': 63172, 'loss/train': 0.9558972716331482} 08/31/2021 00:40:45 - INFO - __main__ - Step 63174: {'lr': 0.0003172316589046358, 'samples': 12129408, 'steps': 63173, 'loss/train': 1.1570717096328735} 08/31/2021 00:40:46 - INFO - __main__ - Step 63175: {'lr': 0.00031722654764208027, 'samples': 12129600, 'steps': 63174, 'loss/train': 1.8307735919952393} 08/31/2021 00:40:47 - INFO - __main__ - Step 63176: {'lr': 0.00031722143634923346, 'samples': 12129792, 'steps': 63175, 'loss/train': 0.5839892029762268} 08/31/2021 00:40:47 - INFO - __main__ - Step 63177: {'lr': 0.0003172163250260977, 'samples': 12129984, 'steps': 63176, 'loss/train': 0.8996771574020386} 08/31/2021 00:40:47 - INFO - __main__ - Step 63178: {'lr': 0.00031721121367267533, 'samples': 12130176, 'steps': 63177, 'loss/train': 0.4762161374092102} 08/31/2021 00:40:48 - INFO - __main__ - Step 63179: {'lr': 0.0003172061022889687, 'samples': 12130368, 'steps': 63178, 'loss/train': 1.226554036140442} 08/31/2021 00:40:49 - INFO - __main__ - Step 63180: {'lr': 0.00031720099087497995, 'samples': 12130560, 'steps': 63179, 'loss/train': 1.2801998853683472} 08/31/2021 00:40:50 - INFO - __main__ - Step 63181: {'lr': 0.0003171958794307115, 'samples': 12130752, 'steps': 63180, 'loss/train': 1.7854140996932983} 08/31/2021 00:40:50 - INFO - __main__ - Step 63182: {'lr': 0.00031719076795616564, 'samples': 12130944, 'steps': 63181, 'loss/train': 1.5663164854049683} 08/31/2021 00:40:50 - INFO - __main__ - Step 63183: {'lr': 0.00031718565645134456, 'samples': 12131136, 'steps': 63182, 'loss/train': 1.2073806524276733} 08/31/2021 00:40:51 - INFO - __main__ - Step 63184: {'lr': 0.00031718054491625076, 'samples': 12131328, 'steps': 63183, 'loss/train': 1.6004589796066284} 08/31/2021 00:40:52 - INFO - __main__ - Step 63185: {'lr': 0.0003171754333508864, 'samples': 12131520, 'steps': 63184, 'loss/train': 1.7383074760437012} 08/31/2021 00:40:53 - INFO - __main__ - Step 63186: {'lr': 0.0003171703217552539, 'samples': 12131712, 'steps': 63185, 'loss/train': 0.7756466865539551} 08/31/2021 00:40:53 - INFO - __main__ - Step 63187: {'lr': 0.0003171652101293554, 'samples': 12131904, 'steps': 63186, 'loss/train': 1.3230786323547363} 08/31/2021 00:40:53 - INFO - __main__ - Step 63188: {'lr': 0.00031716009847319334, 'samples': 12132096, 'steps': 63187, 'loss/train': 1.317207932472229} 08/31/2021 00:40:54 - INFO - __main__ - Step 63189: {'lr': 0.0003171549867867699, 'samples': 12132288, 'steps': 63188, 'loss/train': 1.0936158895492554} 08/31/2021 00:40:54 - INFO - __main__ - Step 63190: {'lr': 0.00031714987507008754, 'samples': 12132480, 'steps': 63189, 'loss/train': 1.075103521347046} 08/31/2021 00:40:56 - INFO - __main__ - Step 63191: {'lr': 0.0003171447633231485, 'samples': 12132672, 'steps': 63190, 'loss/train': 0.8392584323883057} 08/31/2021 00:40:56 - INFO - __main__ - Step 63192: {'lr': 0.000317139651545955, 'samples': 12132864, 'steps': 63191, 'loss/train': 1.3530728816986084} 08/31/2021 00:40:56 - INFO - __main__ - Step 63193: {'lr': 0.0003171345397385095, 'samples': 12133056, 'steps': 63192, 'loss/train': 1.7542105913162231} 08/31/2021 00:40:57 - INFO - __main__ - Step 63194: {'lr': 0.0003171294279008141, 'samples': 12133248, 'steps': 63193, 'loss/train': 1.7605854272842407} 08/31/2021 00:40:57 - INFO - __main__ - Step 63195: {'lr': 0.00031712431603287127, 'samples': 12133440, 'steps': 63194, 'loss/train': 0.6590309739112854} 08/31/2021 00:40:59 - INFO - __main__ - Step 63196: {'lr': 0.0003171192041346833, 'samples': 12133632, 'steps': 63195, 'loss/train': 1.7825978994369507} 08/31/2021 00:40:59 - INFO - __main__ - Step 63197: {'lr': 0.00031711409220625236, 'samples': 12133824, 'steps': 63196, 'loss/train': 1.0565004348754883} 08/31/2021 00:40:59 - INFO - __main__ - Step 63198: {'lr': 0.0003171089802475809, 'samples': 12134016, 'steps': 63197, 'loss/train': 1.3515772819519043} 08/31/2021 00:41:00 - INFO - __main__ - Step 63199: {'lr': 0.0003171038682586712, 'samples': 12134208, 'steps': 63198, 'loss/train': 0.9682039022445679} 08/31/2021 00:41:00 - INFO - __main__ - Step 63200: {'lr': 0.00031709875623952546, 'samples': 12134400, 'steps': 63199, 'loss/train': 1.6411504745483398} 08/31/2021 00:41:02 - INFO - __main__ - Step 63201: {'lr': 0.0003170936441901461, 'samples': 12134592, 'steps': 63200, 'loss/train': 1.9828287363052368} 08/31/2021 00:41:02 - INFO - __main__ - Step 63202: {'lr': 0.0003170885321105354, 'samples': 12134784, 'steps': 63201, 'loss/train': 1.47651207447052} 08/31/2021 00:41:03 - INFO - __main__ - Step 63203: {'lr': 0.0003170834200006956, 'samples': 12134976, 'steps': 63202, 'loss/train': 1.5364704132080078} 08/31/2021 00:41:03 - INFO - __main__ - Step 63204: {'lr': 0.000317078307860629, 'samples': 12135168, 'steps': 63203, 'loss/train': 1.4378939867019653} 08/31/2021 00:41:03 - INFO - __main__ - Step 63205: {'lr': 0.00031707319569033803, 'samples': 12135360, 'steps': 63204, 'loss/train': 1.0013309717178345} 08/31/2021 00:41:06 - INFO - __main__ - Step 63206: {'lr': 0.00031706808348982486, 'samples': 12135552, 'steps': 63205, 'loss/train': 0.7267886400222778} 08/31/2021 00:41:06 - INFO - __main__ - Step 63207: {'lr': 0.00031706297125909193, 'samples': 12135744, 'steps': 63206, 'loss/train': 0.9039614796638489} 08/31/2021 00:41:06 - INFO - __main__ - Step 63208: {'lr': 0.0003170578589981414, 'samples': 12135936, 'steps': 63207, 'loss/train': 1.6518489122390747} 08/31/2021 00:41:07 - INFO - __main__ - Step 63209: {'lr': 0.00031705274670697567, 'samples': 12136128, 'steps': 63208, 'loss/train': 0.05874232202768326} 08/31/2021 00:41:07 - INFO - __main__ - Step 63210: {'lr': 0.00031704763438559694, 'samples': 12136320, 'steps': 63209, 'loss/train': 1.6404658555984497} 08/31/2021 00:41:09 - INFO - __main__ - Step 63211: {'lr': 0.0003170425220340076, 'samples': 12136512, 'steps': 63210, 'loss/train': 1.4377434253692627} 08/31/2021 00:41:09 - INFO - __main__ - Step 63212: {'lr': 0.00031703740965221, 'samples': 12136704, 'steps': 63211, 'loss/train': 1.5004796981811523} 08/31/2021 00:41:09 - INFO - __main__ - Step 63213: {'lr': 0.0003170322972402063, 'samples': 12136896, 'steps': 63212, 'loss/train': 1.5567070245742798} 08/31/2021 00:41:10 - INFO - __main__ - Step 63214: {'lr': 0.0003170271847979989, 'samples': 12137088, 'steps': 63213, 'loss/train': 1.1668742895126343} 08/31/2021 00:41:10 - INFO - __main__ - Step 63215: {'lr': 0.0003170220723255901, 'samples': 12137280, 'steps': 63214, 'loss/train': 1.8381941318511963} 08/31/2021 00:41:10 - INFO - __main__ - Step 63216: {'lr': 0.00031701695982298215, 'samples': 12137472, 'steps': 63215, 'loss/train': 1.3862736225128174} 08/31/2021 00:41:12 - INFO - __main__ - Step 63217: {'lr': 0.00031701184729017744, 'samples': 12137664, 'steps': 63216, 'loss/train': 2.3777530193328857} 08/31/2021 00:41:12 - INFO - __main__ - Step 63218: {'lr': 0.00031700673472717823, 'samples': 12137856, 'steps': 63217, 'loss/train': 1.1624480485916138} 08/31/2021 00:41:13 - INFO - __main__ - Step 63219: {'lr': 0.0003170016221339869, 'samples': 12138048, 'steps': 63218, 'loss/train': 1.223673939704895} 08/31/2021 00:41:13 - INFO - __main__ - Step 63220: {'lr': 0.00031699650951060547, 'samples': 12138240, 'steps': 63219, 'loss/train': 0.8089978694915771} 08/31/2021 00:41:13 - INFO - __main__ - Step 63221: {'lr': 0.0003169913968570366, 'samples': 12138432, 'steps': 63220, 'loss/train': 1.3526047468185425} 08/31/2021 00:41:15 - INFO - __main__ - Step 63222: {'lr': 0.00031698628417328235, 'samples': 12138624, 'steps': 63221, 'loss/train': 0.699476957321167} 08/31/2021 00:41:15 - INFO - __main__ - Step 63223: {'lr': 0.00031698117145934513, 'samples': 12138816, 'steps': 63222, 'loss/train': 1.5428193807601929} 08/31/2021 00:41:16 - INFO - __main__ - Step 63224: {'lr': 0.0003169760587152273, 'samples': 12139008, 'steps': 63223, 'loss/train': 1.5009169578552246} 08/31/2021 00:41:16 - INFO - __main__ - Step 63225: {'lr': 0.000316970945940931, 'samples': 12139200, 'steps': 63224, 'loss/train': 1.0321072340011597} 08/31/2021 00:41:16 - INFO - __main__ - Step 63226: {'lr': 0.0003169658331364587, 'samples': 12139392, 'steps': 63225, 'loss/train': 1.7354533672332764} 08/31/2021 00:41:18 - INFO - __main__ - Step 63227: {'lr': 0.00031696072030181264, 'samples': 12139584, 'steps': 63226, 'loss/train': 1.8786134719848633} 08/31/2021 00:41:18 - INFO - __main__ - Step 63228: {'lr': 0.000316955607436995, 'samples': 12139776, 'steps': 63227, 'loss/train': 1.4089771509170532} 08/31/2021 00:41:19 - INFO - __main__ - Step 63229: {'lr': 0.0003169504945420083, 'samples': 12139968, 'steps': 63228, 'loss/train': 1.110425353050232} 08/31/2021 00:41:19 - INFO - __main__ - Step 63230: {'lr': 0.0003169453816168547, 'samples': 12140160, 'steps': 63229, 'loss/train': 1.1909533739089966} 08/31/2021 00:41:19 - INFO - __main__ - Step 63231: {'lr': 0.0003169402686615365, 'samples': 12140352, 'steps': 63230, 'loss/train': 1.3498494625091553} 08/31/2021 00:41:21 - INFO - __main__ - Step 63232: {'lr': 0.0003169351556760562, 'samples': 12140544, 'steps': 63231, 'loss/train': 1.1206483840942383} 08/31/2021 00:41:21 - INFO - __main__ - Step 63233: {'lr': 0.0003169300426604158, 'samples': 12140736, 'steps': 63232, 'loss/train': 2.845794677734375} 08/31/2021 00:41:22 - INFO - __main__ - Step 63234: {'lr': 0.0003169249296146178, 'samples': 12140928, 'steps': 63233, 'loss/train': 1.4162629842758179} 08/31/2021 00:41:22 - INFO - __main__ - Step 63235: {'lr': 0.00031691981653866446, 'samples': 12141120, 'steps': 63234, 'loss/train': 1.3446255922317505} 08/31/2021 00:41:22 - INFO - __main__ - Step 63236: {'lr': 0.00031691470343255814, 'samples': 12141312, 'steps': 63235, 'loss/train': 1.5017359256744385} 08/31/2021 00:41:23 - INFO - __main__ - Step 63237: {'lr': 0.000316909590296301, 'samples': 12141504, 'steps': 63236, 'loss/train': 0.7140766978263855} 08/31/2021 00:41:24 - INFO - __main__ - Step 63238: {'lr': 0.00031690447712989545, 'samples': 12141696, 'steps': 63237, 'loss/train': 0.07644955068826675} 08/31/2021 00:41:25 - INFO - __main__ - Step 63239: {'lr': 0.00031689936393334385, 'samples': 12141888, 'steps': 63238, 'loss/train': 1.2738008499145508} 08/31/2021 00:41:25 - INFO - __main__ - Step 63240: {'lr': 0.00031689425070664833, 'samples': 12142080, 'steps': 63239, 'loss/train': 1.2311204671859741} 08/31/2021 00:41:25 - INFO - __main__ - Step 63241: {'lr': 0.00031688913744981135, 'samples': 12142272, 'steps': 63240, 'loss/train': 1.4281240701675415} 08/31/2021 00:41:26 - INFO - __main__ - Step 63242: {'lr': 0.0003168840241628351, 'samples': 12142464, 'steps': 63241, 'loss/train': 0.6139264702796936} 08/31/2021 00:41:27 - INFO - __main__ - Step 63243: {'lr': 0.000316878910845722, 'samples': 12142656, 'steps': 63242, 'loss/train': 1.2498475313186646} 08/31/2021 00:41:28 - INFO - __main__ - Step 63244: {'lr': 0.0003168737974984743, 'samples': 12142848, 'steps': 63243, 'loss/train': 1.3884023427963257} 08/31/2021 00:41:28 - INFO - __main__ - Step 63245: {'lr': 0.0003168686841210943, 'samples': 12143040, 'steps': 63244, 'loss/train': 1.2070592641830444} 08/31/2021 00:41:28 - INFO - __main__ - Step 63246: {'lr': 0.0003168635707135842, 'samples': 12143232, 'steps': 63245, 'loss/train': 1.7088154554367065} 08/31/2021 00:41:29 - INFO - __main__ - Step 63247: {'lr': 0.00031685845727594654, 'samples': 12143424, 'steps': 63246, 'loss/train': 1.5133072137832642} 08/31/2021 00:41:30 - INFO - __main__ - Step 63248: {'lr': 0.00031685334380818344, 'samples': 12143616, 'steps': 63247, 'loss/train': 1.6331199407577515} 08/31/2021 00:41:31 - INFO - __main__ - Step 63249: {'lr': 0.0003168482303102972, 'samples': 12143808, 'steps': 63248, 'loss/train': 1.0527093410491943} 08/31/2021 00:41:31 - INFO - __main__ - Step 63250: {'lr': 0.0003168431167822903, 'samples': 12144000, 'steps': 63249, 'loss/train': 1.1009275913238525} 08/31/2021 00:41:31 - INFO - __main__ - Step 63251: {'lr': 0.0003168380032241648, 'samples': 12144192, 'steps': 63250, 'loss/train': 1.3065009117126465} 08/31/2021 00:41:32 - INFO - __main__ - Step 63252: {'lr': 0.0003168328896359232, 'samples': 12144384, 'steps': 63251, 'loss/train': 1.1860682964324951} 08/31/2021 00:41:34 - INFO - __main__ - Step 63253: {'lr': 0.00031682777601756774, 'samples': 12144576, 'steps': 63252, 'loss/train': 1.6533873081207275} 08/31/2021 00:41:35 - INFO - __main__ - Step 63254: {'lr': 0.0003168226623691006, 'samples': 12144768, 'steps': 63253, 'loss/train': 1.0607361793518066} 08/31/2021 00:41:35 - INFO - __main__ - Step 63255: {'lr': 0.00031681754869052433, 'samples': 12144960, 'steps': 63254, 'loss/train': 1.3767935037612915} 08/31/2021 00:41:35 - INFO - __main__ - Step 63256: {'lr': 0.00031681243498184105, 'samples': 12145152, 'steps': 63255, 'loss/train': 1.5584927797317505} 08/31/2021 00:41:36 - INFO - __main__ - Step 63257: {'lr': 0.0003168073212430531, 'samples': 12145344, 'steps': 63256, 'loss/train': 1.0740669965744019} 08/31/2021 00:41:36 - INFO - __main__ - Step 63258: {'lr': 0.00031680220747416283, 'samples': 12145536, 'steps': 63257, 'loss/train': 1.2143843173980713} 08/31/2021 00:41:36 - INFO - __main__ - Step 63259: {'lr': 0.00031679709367517255, 'samples': 12145728, 'steps': 63258, 'loss/train': 0.026841020211577415} 08/31/2021 00:41:38 - INFO - __main__ - Step 63260: {'lr': 0.0003167919798460845, 'samples': 12145920, 'steps': 63259, 'loss/train': 0.024654725566506386} 08/31/2021 00:41:38 - INFO - __main__ - Step 63261: {'lr': 0.000316786865986901, 'samples': 12146112, 'steps': 63260, 'loss/train': 0.5830327272415161} 08/31/2021 00:41:39 - INFO - __main__ - Step 63262: {'lr': 0.0003167817520976244, 'samples': 12146304, 'steps': 63261, 'loss/train': 1.4468116760253906} 08/31/2021 00:41:39 - INFO - __main__ - Step 63263: {'lr': 0.00031677663817825693, 'samples': 12146496, 'steps': 63262, 'loss/train': 5.660685062408447} 08/31/2021 00:41:39 - INFO - __main__ - Step 63264: {'lr': 0.000316771524228801, 'samples': 12146688, 'steps': 63263, 'loss/train': 0.9697508811950684} 08/31/2021 00:41:40 - INFO - __main__ - Step 63265: {'lr': 0.00031676641024925873, 'samples': 12146880, 'steps': 63264, 'loss/train': 1.1949177980422974} 08/31/2021 00:41:42 - INFO - __main__ - Step 63266: {'lr': 0.0003167612962396327, 'samples': 12147072, 'steps': 63265, 'loss/train': 1.6798949241638184} 08/31/2021 00:41:42 - INFO - __main__ - Step 63267: {'lr': 0.000316756182199925, 'samples': 12147264, 'steps': 63266, 'loss/train': 1.5416558980941772} 08/31/2021 00:41:43 - INFO - __main__ - Step 63268: {'lr': 0.0003167510681301379, 'samples': 12147456, 'steps': 63267, 'loss/train': 1.4238370656967163} 08/31/2021 00:41:43 - INFO - __main__ - Step 63269: {'lr': 0.0003167459540302739, 'samples': 12147648, 'steps': 63268, 'loss/train': 2.4863555431365967} 08/31/2021 00:41:43 - INFO - __main__ - Step 63270: {'lr': 0.0003167408399003352, 'samples': 12147840, 'steps': 63269, 'loss/train': 1.17813241481781} 08/31/2021 00:41:45 - INFO - __main__ - Step 63271: {'lr': 0.0003167357257403241, 'samples': 12148032, 'steps': 63270, 'loss/train': 1.2538304328918457} 08/31/2021 00:41:45 - INFO - __main__ - Step 63272: {'lr': 0.00031673061155024283, 'samples': 12148224, 'steps': 63271, 'loss/train': 0.3721311688423157} 08/31/2021 00:41:46 - INFO - __main__ - Step 63273: {'lr': 0.00031672549733009395, 'samples': 12148416, 'steps': 63272, 'loss/train': 0.6800015568733215} 08/31/2021 00:41:46 - INFO - __main__ - Step 63274: {'lr': 0.00031672038307987944, 'samples': 12148608, 'steps': 63273, 'loss/train': 1.298261046409607} 08/31/2021 00:41:46 - INFO - __main__ - Step 63275: {'lr': 0.00031671526879960185, 'samples': 12148800, 'steps': 63274, 'loss/train': 1.7661923170089722} 08/31/2021 00:41:48 - INFO - __main__ - Step 63276: {'lr': 0.00031671015448926334, 'samples': 12148992, 'steps': 63275, 'loss/train': 0.7635094523429871} 08/31/2021 00:41:48 - INFO - __main__ - Step 63277: {'lr': 0.0003167050401488662, 'samples': 12149184, 'steps': 63276, 'loss/train': 1.3925701379776} 08/31/2021 00:41:49 - INFO - __main__ - Step 63278: {'lr': 0.0003166999257784129, 'samples': 12149376, 'steps': 63277, 'loss/train': 0.5411805510520935} 08/31/2021 00:41:49 - INFO - __main__ - Step 63279: {'lr': 0.00031669481137790563, 'samples': 12149568, 'steps': 63278, 'loss/train': 1.8507410287857056} 08/31/2021 00:41:49 - INFO - __main__ - Step 63280: {'lr': 0.00031668969694734667, 'samples': 12149760, 'steps': 63279, 'loss/train': 0.4388197958469391} 08/31/2021 00:41:51 - INFO - __main__ - Step 63281: {'lr': 0.0003166845824867384, 'samples': 12149952, 'steps': 63280, 'loss/train': 1.0986402034759521} 08/31/2021 00:41:51 - INFO - __main__ - Step 63282: {'lr': 0.00031667946799608307, 'samples': 12150144, 'steps': 63281, 'loss/train': 1.1795040369033813} 08/31/2021 00:41:52 - INFO - __main__ - Step 63283: {'lr': 0.00031667435347538294, 'samples': 12150336, 'steps': 63282, 'loss/train': 1.524280071258545} 08/31/2021 00:41:52 - INFO - __main__ - Step 63284: {'lr': 0.0003166692389246404, 'samples': 12150528, 'steps': 63283, 'loss/train': 0.057443782687187195} 08/31/2021 00:41:52 - INFO - __main__ - Step 63285: {'lr': 0.0003166641243438578, 'samples': 12150720, 'steps': 63284, 'loss/train': 0.9853415489196777} 08/31/2021 00:41:54 - INFO - __main__ - Step 63286: {'lr': 0.00031665900973303735, 'samples': 12150912, 'steps': 63285, 'loss/train': 1.3486238718032837} 08/31/2021 00:41:54 - INFO - __main__ - Step 63287: {'lr': 0.00031665389509218133, 'samples': 12151104, 'steps': 63286, 'loss/train': 1.3097885847091675} 08/31/2021 00:41:55 - INFO - __main__ - Step 63288: {'lr': 0.00031664878042129215, 'samples': 12151296, 'steps': 63287, 'loss/train': 0.70932936668396} 08/31/2021 00:41:55 - INFO - __main__ - Step 63289: {'lr': 0.00031664366572037203, 'samples': 12151488, 'steps': 63288, 'loss/train': 1.632688045501709} 08/31/2021 00:41:55 - INFO - __main__ - Step 63290: {'lr': 0.0003166385509894233, 'samples': 12151680, 'steps': 63289, 'loss/train': 1.2798875570297241} 08/31/2021 00:41:56 - INFO - __main__ - Step 63291: {'lr': 0.00031663343622844825, 'samples': 12151872, 'steps': 63290, 'loss/train': 1.585087537765503} 08/31/2021 00:41:57 - INFO - __main__ - Step 63292: {'lr': 0.00031662832143744925, 'samples': 12152064, 'steps': 63291, 'loss/train': 1.0120991468429565} 08/31/2021 00:41:58 - INFO - __main__ - Step 63293: {'lr': 0.00031662320661642854, 'samples': 12152256, 'steps': 63292, 'loss/train': 0.7466258406639099} 08/31/2021 00:41:58 - INFO - __main__ - Step 63294: {'lr': 0.00031661809176538843, 'samples': 12152448, 'steps': 63293, 'loss/train': 0.21221303939819336} 08/31/2021 00:41:58 - INFO - __main__ - Step 63295: {'lr': 0.0003166129768843312, 'samples': 12152640, 'steps': 63294, 'loss/train': 1.5848151445388794} 08/31/2021 00:41:59 - INFO - __main__ - Step 63296: {'lr': 0.00031660786197325926, 'samples': 12152832, 'steps': 63295, 'loss/train': 0.04035428166389465} 08/31/2021 00:42:00 - INFO - __main__ - Step 63297: {'lr': 0.0003166027470321748, 'samples': 12153024, 'steps': 63296, 'loss/train': 1.2292745113372803} 08/31/2021 00:42:01 - INFO - __main__ - Step 63298: {'lr': 0.0003165976320610802, 'samples': 12153216, 'steps': 63297, 'loss/train': 1.2425810098648071} 08/31/2021 00:42:01 - INFO - __main__ - Step 63299: {'lr': 0.00031659251705997766, 'samples': 12153408, 'steps': 63298, 'loss/train': 1.09530770778656} 08/31/2021 00:42:01 - INFO - __main__ - Step 63300: {'lr': 0.0003165874020288697, 'samples': 12153600, 'steps': 63299, 'loss/train': 1.2633148431777954} 08/31/2021 00:42:02 - INFO - __main__ - Step 63301: {'lr': 0.00031658228696775835, 'samples': 12153792, 'steps': 63300, 'loss/train': 1.0093454122543335} 08/31/2021 00:42:03 - INFO - __main__ - Step 63302: {'lr': 0.0003165771718766461, 'samples': 12153984, 'steps': 63301, 'loss/train': 0.382465660572052} 08/31/2021 00:42:04 - INFO - __main__ - Step 63303: {'lr': 0.0003165720567555352, 'samples': 12154176, 'steps': 63302, 'loss/train': 1.8084088563919067} 08/31/2021 00:42:04 - INFO - __main__ - Step 63304: {'lr': 0.00031656694160442795, 'samples': 12154368, 'steps': 63303, 'loss/train': 1.2179042100906372} 08/31/2021 00:42:05 - INFO - __main__ - Step 63305: {'lr': 0.00031656182642332667, 'samples': 12154560, 'steps': 63304, 'loss/train': 1.4921314716339111} 08/31/2021 00:42:05 - INFO - __main__ - Step 63306: {'lr': 0.0003165567112122337, 'samples': 12154752, 'steps': 63305, 'loss/train': 0.8848065137863159} 08/31/2021 00:42:06 - INFO - __main__ - Step 63307: {'lr': 0.0003165515959711513, 'samples': 12154944, 'steps': 63306, 'loss/train': 1.1732115745544434} 08/31/2021 00:42:07 - INFO - __main__ - Step 63308: {'lr': 0.00031654648070008175, 'samples': 12155136, 'steps': 63307, 'loss/train': 1.1792840957641602} 08/31/2021 00:42:07 - INFO - __main__ - Step 63309: {'lr': 0.0003165413653990273, 'samples': 12155328, 'steps': 63308, 'loss/train': 1.032614827156067} 08/31/2021 00:42:08 - INFO - __main__ - Step 63310: {'lr': 0.0003165362500679905, 'samples': 12155520, 'steps': 63309, 'loss/train': 1.6597177982330322} 08/31/2021 00:42:08 - INFO - __main__ - Step 63311: {'lr': 0.0003165311347069734, 'samples': 12155712, 'steps': 63310, 'loss/train': 1.0997729301452637} 08/31/2021 00:42:10 - INFO - __main__ - Step 63312: {'lr': 0.00031652601931597837, 'samples': 12155904, 'steps': 63311, 'loss/train': 1.4029866456985474} 08/31/2021 00:42:10 - INFO - __main__ - Step 63313: {'lr': 0.00031652090389500776, 'samples': 12156096, 'steps': 63312, 'loss/train': 0.8875043392181396} 08/31/2021 00:42:11 - INFO - __main__ - Step 63314: {'lr': 0.0003165157884440639, 'samples': 12156288, 'steps': 63313, 'loss/train': 1.0757819414138794} 08/31/2021 00:42:11 - INFO - __main__ - Step 63315: {'lr': 0.000316510672963149, 'samples': 12156480, 'steps': 63314, 'loss/train': 1.476309895515442} 08/31/2021 00:42:11 - INFO - __main__ - Step 63316: {'lr': 0.00031650555745226547, 'samples': 12156672, 'steps': 63315, 'loss/train': 1.2574416399002075} 08/31/2021 00:42:13 - INFO - __main__ - Step 63317: {'lr': 0.00031650044191141555, 'samples': 12156864, 'steps': 63316, 'loss/train': 0.5954718589782715} 08/31/2021 00:42:13 - INFO - __main__ - Step 63318: {'lr': 0.00031649532634060154, 'samples': 12157056, 'steps': 63317, 'loss/train': 1.237433671951294} 08/31/2021 00:42:14 - INFO - __main__ - Step 63319: {'lr': 0.0003164902107398257, 'samples': 12157248, 'steps': 63318, 'loss/train': 0.959621787071228} 08/31/2021 00:42:14 - INFO - __main__ - Step 63320: {'lr': 0.0003164850951090905, 'samples': 12157440, 'steps': 63319, 'loss/train': 1.2877123355865479} 08/31/2021 00:42:14 - INFO - __main__ - Step 63321: {'lr': 0.00031647997944839814, 'samples': 12157632, 'steps': 63320, 'loss/train': 1.4973138570785522} 08/31/2021 00:42:15 - INFO - __main__ - Step 63322: {'lr': 0.0003164748637577509, 'samples': 12157824, 'steps': 63321, 'loss/train': 1.5201877355575562} 08/31/2021 00:42:17 - INFO - __main__ - Step 63323: {'lr': 0.00031646974803715104, 'samples': 12158016, 'steps': 63322, 'loss/train': 0.09494048357009888} 08/31/2021 00:42:17 - INFO - __main__ - Step 63324: {'lr': 0.000316464632286601, 'samples': 12158208, 'steps': 63323, 'loss/train': 1.3708772659301758} 08/31/2021 00:42:17 - INFO - __main__ - Step 63325: {'lr': 0.000316459516506103, 'samples': 12158400, 'steps': 63324, 'loss/train': 0.10954737663269043} 08/31/2021 00:42:18 - INFO - __main__ - Step 63326: {'lr': 0.00031645440069565946, 'samples': 12158592, 'steps': 63325, 'loss/train': 0.09875571727752686} 08/31/2021 00:42:18 - INFO - __main__ - Step 63327: {'lr': 0.0003164492848552725, 'samples': 12158784, 'steps': 63326, 'loss/train': 1.205311894416809} 08/31/2021 00:42:19 - INFO - __main__ - Step 63328: {'lr': 0.00031644416898494456, 'samples': 12158976, 'steps': 63327, 'loss/train': 1.6226191520690918} 08/31/2021 00:42:21 - INFO - __main__ - Step 63329: {'lr': 0.00031643905308467783, 'samples': 12159168, 'steps': 63328, 'loss/train': 1.4590085744857788} 08/31/2021 00:42:21 - INFO - __main__ - Step 63330: {'lr': 0.0003164339371544748, 'samples': 12159360, 'steps': 63329, 'loss/train': 1.5290634632110596} 08/31/2021 00:42:21 - INFO - __main__ - Step 63331: {'lr': 0.0003164288211943376, 'samples': 12159552, 'steps': 63330, 'loss/train': 1.2219316959381104} 08/31/2021 00:42:22 - INFO - __main__ - Step 63332: {'lr': 0.0003164237052042686, 'samples': 12159744, 'steps': 63331, 'loss/train': 1.6213603019714355} 08/31/2021 00:42:22 - INFO - __main__ - Step 63333: {'lr': 0.00031641858918427006, 'samples': 12159936, 'steps': 63332, 'loss/train': 1.1292411088943481} 08/31/2021 00:42:22 - INFO - __main__ - Step 63334: {'lr': 0.00031641347313434446, 'samples': 12160128, 'steps': 63333, 'loss/train': 1.0052074193954468} 08/31/2021 00:42:24 - INFO - __main__ - Step 63335: {'lr': 0.00031640835705449384, 'samples': 12160320, 'steps': 63334, 'loss/train': 0.6441923379898071} 08/31/2021 00:42:24 - INFO - __main__ - Step 63336: {'lr': 0.0003164032409447207, 'samples': 12160512, 'steps': 63335, 'loss/train': 1.2895604372024536} 08/31/2021 00:42:25 - INFO - __main__ - Step 63337: {'lr': 0.0003163981248050273, 'samples': 12160704, 'steps': 63336, 'loss/train': 1.0761476755142212} 08/31/2021 00:42:25 - INFO - __main__ - Step 63338: {'lr': 0.0003163930086354159, 'samples': 12160896, 'steps': 63337, 'loss/train': 1.3764458894729614} 08/31/2021 00:42:25 - INFO - __main__ - Step 63339: {'lr': 0.00031638789243588876, 'samples': 12161088, 'steps': 63338, 'loss/train': 0.7978149056434631} 08/31/2021 00:42:26 - INFO - __main__ - Step 63340: {'lr': 0.0003163827762064484, 'samples': 12161280, 'steps': 63339, 'loss/train': 1.374582052230835} 08/31/2021 00:42:27 - INFO - __main__ - Step 63341: {'lr': 0.0003163776599470969, 'samples': 12161472, 'steps': 63340, 'loss/train': 1.2055189609527588} 08/31/2021 00:42:28 - INFO - __main__ - Step 63342: {'lr': 0.00031637254365783667, 'samples': 12161664, 'steps': 63341, 'loss/train': 0.6879834532737732} 08/31/2021 00:42:28 - INFO - __main__ - Step 63343: {'lr': 0.00031636742733867, 'samples': 12161856, 'steps': 63342, 'loss/train': 1.288698673248291} 08/31/2021 00:42:29 - INFO - __main__ - Step 63344: {'lr': 0.00031636231098959924, 'samples': 12162048, 'steps': 63343, 'loss/train': 0.9216764569282532} 08/31/2021 00:42:29 - INFO - __main__ - Step 63345: {'lr': 0.0003163571946106265, 'samples': 12162240, 'steps': 63344, 'loss/train': 1.0083556175231934} 08/31/2021 00:42:30 - INFO - __main__ - Step 63346: {'lr': 0.00031635207820175437, 'samples': 12162432, 'steps': 63345, 'loss/train': 2.8177690505981445} 08/31/2021 00:42:31 - INFO - __main__ - Step 63347: {'lr': 0.000316346961762985, 'samples': 12162624, 'steps': 63346, 'loss/train': 1.145334005355835} 08/31/2021 00:42:31 - INFO - __main__ - Step 63348: {'lr': 0.0003163418452943207, 'samples': 12162816, 'steps': 63347, 'loss/train': 0.9613863825798035} 08/31/2021 00:42:32 - INFO - __main__ - Step 63349: {'lr': 0.00031633672879576377, 'samples': 12163008, 'steps': 63348, 'loss/train': 0.5033286809921265} 08/31/2021 00:42:32 - INFO - __main__ - Step 63350: {'lr': 0.00031633161226731654, 'samples': 12163200, 'steps': 63349, 'loss/train': 1.1909977197647095} 08/31/2021 00:42:33 - INFO - __main__ - Step 63351: {'lr': 0.0003163264957089813, 'samples': 12163392, 'steps': 63350, 'loss/train': 1.8957650661468506} 08/31/2021 00:42:34 - INFO - __main__ - Step 63352: {'lr': 0.0003163213791207604, 'samples': 12163584, 'steps': 63351, 'loss/train': 1.3135144710540771} 08/31/2021 00:42:34 - INFO - __main__ - Step 63353: {'lr': 0.0003163162625026561, 'samples': 12163776, 'steps': 63352, 'loss/train': 1.1114729642868042} 08/31/2021 00:42:35 - INFO - __main__ - Step 63354: {'lr': 0.0003163111458546707, 'samples': 12163968, 'steps': 63353, 'loss/train': 1.1310852766036987} 08/31/2021 00:42:35 - INFO - __main__ - Step 63355: {'lr': 0.0003163060291768065, 'samples': 12164160, 'steps': 63354, 'loss/train': 1.5850285291671753} 08/31/2021 00:42:37 - INFO - __main__ - Step 63356: {'lr': 0.00031630091246906585, 'samples': 12164352, 'steps': 63355, 'loss/train': 1.0594276189804077} 08/31/2021 00:42:37 - INFO - __main__ - Step 63357: {'lr': 0.000316295795731451, 'samples': 12164544, 'steps': 63356, 'loss/train': 1.4988042116165161} 08/31/2021 00:42:38 - INFO - __main__ - Step 63358: {'lr': 0.0003162906789639643, 'samples': 12164736, 'steps': 63357, 'loss/train': 1.4038816690444946} 08/31/2021 00:42:38 - INFO - __main__ - Step 63359: {'lr': 0.00031628556216660805, 'samples': 12164928, 'steps': 63358, 'loss/train': 1.4938894510269165} 08/31/2021 00:42:38 - INFO - __main__ - Step 63360: {'lr': 0.0003162804453393846, 'samples': 12165120, 'steps': 63359, 'loss/train': 0.021005185320973396} 08/31/2021 00:42:39 - INFO - __main__ - Step 63361: {'lr': 0.0003162753284822962, 'samples': 12165312, 'steps': 63360, 'loss/train': 1.2558443546295166} 08/31/2021 00:42:40 - INFO - __main__ - Step 63362: {'lr': 0.0003162702115953451, 'samples': 12165504, 'steps': 63361, 'loss/train': 0.3496798574924469} 08/31/2021 00:42:41 - INFO - __main__ - Step 63363: {'lr': 0.00031626509467853366, 'samples': 12165696, 'steps': 63362, 'loss/train': 1.6360706090927124} 08/31/2021 00:42:41 - INFO - __main__ - Step 63364: {'lr': 0.0003162599777318642, 'samples': 12165888, 'steps': 63363, 'loss/train': 1.4633607864379883} 08/31/2021 00:42:41 - INFO - __main__ - Step 63365: {'lr': 0.00031625486075533905, 'samples': 12166080, 'steps': 63364, 'loss/train': 0.13163863122463226} 08/31/2021 00:42:42 - INFO - __main__ - Step 63366: {'lr': 0.0003162497437489604, 'samples': 12166272, 'steps': 63365, 'loss/train': 1.3805770874023438} 08/31/2021 00:42:43 - INFO - __main__ - Step 63367: {'lr': 0.0003162446267127308, 'samples': 12166464, 'steps': 63366, 'loss/train': 0.9736976623535156} 08/31/2021 00:42:44 - INFO - __main__ - Step 63368: {'lr': 0.00031623950964665225, 'samples': 12166656, 'steps': 63367, 'loss/train': 0.536518931388855} 08/31/2021 00:42:44 - INFO - __main__ - Step 63369: {'lr': 0.00031623439255072726, 'samples': 12166848, 'steps': 63368, 'loss/train': 1.3226224184036255} 08/31/2021 00:42:44 - INFO - __main__ - Step 63370: {'lr': 0.000316229275424958, 'samples': 12167040, 'steps': 63369, 'loss/train': 0.06609195470809937} 08/31/2021 00:42:45 - INFO - __main__ - Step 63371: {'lr': 0.00031622415826934694, 'samples': 12167232, 'steps': 63370, 'loss/train': 1.3745795488357544} 08/31/2021 00:42:45 - INFO - __main__ - Step 63372: {'lr': 0.0003162190410838963, 'samples': 12167424, 'steps': 63371, 'loss/train': 1.361777901649475} 08/31/2021 00:42:47 - INFO - __main__ - Step 63373: {'lr': 0.00031621392386860833, 'samples': 12167616, 'steps': 63372, 'loss/train': 0.8415346741676331} 08/31/2021 00:42:48 - INFO - __main__ - Step 63374: {'lr': 0.00031620880662348546, 'samples': 12167808, 'steps': 63373, 'loss/train': 0.03729543462395668} 08/31/2021 00:42:48 - INFO - __main__ - Step 63375: {'lr': 0.00031620368934852985, 'samples': 12168000, 'steps': 63374, 'loss/train': 1.7178246974945068} 08/31/2021 00:42:48 - INFO - __main__ - Step 63376: {'lr': 0.0003161985720437439, 'samples': 12168192, 'steps': 63375, 'loss/train': 0.9963394999504089} 08/31/2021 00:42:49 - INFO - __main__ - Step 63377: {'lr': 0.0003161934547091299, 'samples': 12168384, 'steps': 63376, 'loss/train': 0.8268381953239441} 08/31/2021 00:42:50 - INFO - __main__ - Step 63378: {'lr': 0.0003161883373446901, 'samples': 12168576, 'steps': 63377, 'loss/train': 1.221120834350586} 08/31/2021 00:42:51 - INFO - __main__ - Step 63379: {'lr': 0.0003161832199504269, 'samples': 12168768, 'steps': 63378, 'loss/train': 1.065083384513855} 08/31/2021 00:42:51 - INFO - __main__ - Step 63380: {'lr': 0.0003161781025263426, 'samples': 12168960, 'steps': 63379, 'loss/train': 1.232877492904663} 08/31/2021 00:42:51 - INFO - __main__ - Step 63381: {'lr': 0.0003161729850724394, 'samples': 12169152, 'steps': 63380, 'loss/train': 1.6802672147750854} 08/31/2021 00:42:52 - INFO - __main__ - Step 63382: {'lr': 0.00031616786758871974, 'samples': 12169344, 'steps': 63381, 'loss/train': 0.9204716682434082} 08/31/2021 00:42:53 - INFO - __main__ - Step 63383: {'lr': 0.0003161627500751858, 'samples': 12169536, 'steps': 63382, 'loss/train': 0.537874162197113} 08/31/2021 00:42:54 - INFO - __main__ - Step 63384: {'lr': 0.00031615763253183996, 'samples': 12169728, 'steps': 63383, 'loss/train': 0.9988958239555359} 08/31/2021 00:42:54 - INFO - __main__ - Step 63385: {'lr': 0.0003161525149586845, 'samples': 12169920, 'steps': 63384, 'loss/train': 1.7931241989135742} 08/31/2021 00:42:54 - INFO - __main__ - Step 63386: {'lr': 0.0003161473973557218, 'samples': 12170112, 'steps': 63385, 'loss/train': 1.6002203226089478} 08/31/2021 00:42:55 - INFO - __main__ - Step 63387: {'lr': 0.00031614227972295405, 'samples': 12170304, 'steps': 63386, 'loss/train': 1.0244474411010742} 08/31/2021 00:42:56 - INFO - __main__ - Step 63388: {'lr': 0.0003161371620603837, 'samples': 12170496, 'steps': 63387, 'loss/train': 0.8560093641281128} 08/31/2021 00:42:57 - INFO - __main__ - Step 63389: {'lr': 0.00031613204436801285, 'samples': 12170688, 'steps': 63388, 'loss/train': 1.5621395111083984} 08/31/2021 00:42:57 - INFO - __main__ - Step 63390: {'lr': 0.00031612692664584395, 'samples': 12170880, 'steps': 63389, 'loss/train': 6.089788913726807} 08/31/2021 00:42:57 - INFO - __main__ - Step 63391: {'lr': 0.0003161218088938793, 'samples': 12171072, 'steps': 63390, 'loss/train': 1.204030156135559} 08/31/2021 00:42:58 - INFO - __main__ - Step 63392: {'lr': 0.00031611669111212117, 'samples': 12171264, 'steps': 63391, 'loss/train': 1.9120100736618042} 08/31/2021 00:42:59 - INFO - __main__ - Step 63393: {'lr': 0.00031611157330057183, 'samples': 12171456, 'steps': 63392, 'loss/train': 1.3465684652328491} 08/31/2021 00:42:59 - INFO - __main__ - Step 63394: {'lr': 0.0003161064554592337, 'samples': 12171648, 'steps': 63393, 'loss/train': 0.9864622354507446} 08/31/2021 00:43:00 - INFO - __main__ - Step 63395: {'lr': 0.00031610133758810905, 'samples': 12171840, 'steps': 63394, 'loss/train': 0.8138276934623718} 08/31/2021 00:43:00 - INFO - __main__ - Step 63396: {'lr': 0.0003160962196872001, 'samples': 12172032, 'steps': 63395, 'loss/train': 1.4798619747161865} 08/31/2021 00:43:01 - INFO - __main__ - Step 63397: {'lr': 0.00031609110175650926, 'samples': 12172224, 'steps': 63396, 'loss/train': 1.295654296875} 08/31/2021 00:43:02 - INFO - __main__ - Step 63398: {'lr': 0.0003160859837960387, 'samples': 12172416, 'steps': 63397, 'loss/train': 1.3989876508712769} 08/31/2021 00:43:03 - INFO - __main__ - Step 63399: {'lr': 0.0003160808658057909, 'samples': 12172608, 'steps': 63398, 'loss/train': 0.8899223804473877} 08/31/2021 00:43:03 - INFO - __main__ - Step 63400: {'lr': 0.00031607574778576807, 'samples': 12172800, 'steps': 63399, 'loss/train': 0.9629773497581482} 08/31/2021 00:43:03 - INFO - __main__ - Step 63401: {'lr': 0.0003160706297359725, 'samples': 12172992, 'steps': 63400, 'loss/train': 1.4880006313323975} 08/31/2021 00:43:04 - INFO - __main__ - Step 63402: {'lr': 0.0003160655116564065, 'samples': 12173184, 'steps': 63401, 'loss/train': 0.7588632106781006} 08/31/2021 00:43:04 - INFO - __main__ - Step 63403: {'lr': 0.00031606039354707243, 'samples': 12173376, 'steps': 63402, 'loss/train': 1.4953144788742065} 08/31/2021 00:43:06 - INFO - __main__ - Step 63404: {'lr': 0.00031605527540797256, 'samples': 12173568, 'steps': 63403, 'loss/train': 0.03461470454931259} 08/31/2021 00:43:06 - INFO - __main__ - Step 63405: {'lr': 0.0003160501572391092, 'samples': 12173760, 'steps': 63404, 'loss/train': 1.3127561807632446} 08/31/2021 00:43:07 - INFO - __main__ - Step 63406: {'lr': 0.0003160450390404847, 'samples': 12173952, 'steps': 63405, 'loss/train': 1.581635594367981} 08/31/2021 00:43:07 - INFO - __main__ - Step 63407: {'lr': 0.0003160399208121013, 'samples': 12174144, 'steps': 63406, 'loss/train': 1.9077552556991577} 08/31/2021 00:43:07 - INFO - __main__ - Step 63408: {'lr': 0.0003160348025539613, 'samples': 12174336, 'steps': 63407, 'loss/train': 0.13381296396255493} 08/31/2021 00:43:09 - INFO - __main__ - Step 63409: {'lr': 0.0003160296842660671, 'samples': 12174528, 'steps': 63408, 'loss/train': 1.268142580986023} 08/31/2021 00:43:10 - INFO - __main__ - Step 63410: {'lr': 0.00031602456594842087, 'samples': 12174720, 'steps': 63409, 'loss/train': 1.2510099411010742} 08/31/2021 00:43:10 - INFO - __main__ - Step 63411: {'lr': 0.0003160194476010251, 'samples': 12174912, 'steps': 63410, 'loss/train': 1.5607961416244507} 08/31/2021 00:43:10 - INFO - __main__ - Step 63412: {'lr': 0.00031601432922388187, 'samples': 12175104, 'steps': 63411, 'loss/train': 1.1499388217926025} 08/31/2021 00:43:11 - INFO - __main__ - Step 63413: {'lr': 0.00031600921081699365, 'samples': 12175296, 'steps': 63412, 'loss/train': 1.2354099750518799} 08/31/2021 00:43:12 - INFO - __main__ - Step 63414: {'lr': 0.0003160040923803627, 'samples': 12175488, 'steps': 63413, 'loss/train': 1.4612845182418823} 08/31/2021 00:43:13 - INFO - __main__ - Step 63415: {'lr': 0.00031599897391399134, 'samples': 12175680, 'steps': 63414, 'loss/train': 1.170218586921692} 08/31/2021 00:43:13 - INFO - __main__ - Step 63416: {'lr': 0.00031599385541788186, 'samples': 12175872, 'steps': 63415, 'loss/train': 0.8731545209884644} 08/31/2021 00:43:13 - INFO - __main__ - Step 63417: {'lr': 0.0003159887368920365, 'samples': 12176064, 'steps': 63416, 'loss/train': 0.9108472466468811} 08/31/2021 00:43:14 - INFO - __main__ - Step 63418: {'lr': 0.00031598361833645765, 'samples': 12176256, 'steps': 63417, 'loss/train': 1.1752272844314575} 08/31/2021 00:43:15 - INFO - __main__ - Step 63419: {'lr': 0.0003159784997511476, 'samples': 12176448, 'steps': 63418, 'loss/train': 0.9713296890258789} 08/31/2021 00:43:16 - INFO - __main__ - Step 63420: {'lr': 0.0003159733811361087, 'samples': 12176640, 'steps': 63419, 'loss/train': 1.1288303136825562} 08/31/2021 00:43:16 - INFO - __main__ - Step 63421: {'lr': 0.00031596826249134324, 'samples': 12176832, 'steps': 63420, 'loss/train': 1.534143090248108} 08/31/2021 00:43:16 - INFO - __main__ - Step 63422: {'lr': 0.00031596314381685344, 'samples': 12177024, 'steps': 63421, 'loss/train': 1.412219524383545} 08/31/2021 00:43:17 - INFO - __main__ - Step 63423: {'lr': 0.0003159580251126417, 'samples': 12177216, 'steps': 63422, 'loss/train': 1.2570021152496338} 08/31/2021 00:43:17 - INFO - __main__ - Step 63424: {'lr': 0.00031595290637871024, 'samples': 12177408, 'steps': 63423, 'loss/train': 1.3793009519577026} 08/31/2021 00:43:18 - INFO - __main__ - Step 63425: {'lr': 0.0003159477876150615, 'samples': 12177600, 'steps': 63424, 'loss/train': 0.6071597337722778} 08/31/2021 00:43:19 - INFO - __main__ - Step 63426: {'lr': 0.00031594266882169756, 'samples': 12177792, 'steps': 63425, 'loss/train': 1.138047695159912} 08/31/2021 00:43:19 - INFO - __main__ - Step 63427: {'lr': 0.00031593754999862105, 'samples': 12177984, 'steps': 63426, 'loss/train': 1.7318203449249268} 08/31/2021 00:43:20 - INFO - __main__ - Step 63428: {'lr': 0.00031593243114583404, 'samples': 12178176, 'steps': 63427, 'loss/train': 1.3742812871932983} 08/31/2021 00:43:20 - INFO - __main__ - Step 63429: {'lr': 0.0003159273122633388, 'samples': 12178368, 'steps': 63428, 'loss/train': 0.9731454253196716} 08/31/2021 00:43:22 - INFO - __main__ - Step 63430: {'lr': 0.00031592219335113784, 'samples': 12178560, 'steps': 63429, 'loss/train': 1.6725537776947021} 08/31/2021 00:43:22 - INFO - __main__ - Step 63431: {'lr': 0.0003159170744092333, 'samples': 12178752, 'steps': 63430, 'loss/train': 1.4969732761383057} 08/31/2021 00:43:23 - INFO - __main__ - Step 63432: {'lr': 0.0003159119554376275, 'samples': 12178944, 'steps': 63431, 'loss/train': 1.2306437492370605} 08/31/2021 00:43:23 - INFO - __main__ - Step 63433: {'lr': 0.0003159068364363229, 'samples': 12179136, 'steps': 63432, 'loss/train': 1.1762166023254395} 08/31/2021 00:43:24 - INFO - __main__ - Step 63434: {'lr': 0.0003159017174053217, 'samples': 12179328, 'steps': 63433, 'loss/train': 1.4438422918319702} 08/31/2021 00:43:25 - INFO - __main__ - Step 63435: {'lr': 0.00031589659834462615, 'samples': 12179520, 'steps': 63434, 'loss/train': 1.1773258447647095} 08/31/2021 00:43:26 - INFO - __main__ - Step 63436: {'lr': 0.00031589147925423856, 'samples': 12179712, 'steps': 63435, 'loss/train': 1.1312081813812256} 08/31/2021 00:43:26 - INFO - __main__ - Step 63437: {'lr': 0.00031588636013416135, 'samples': 12179904, 'steps': 63436, 'loss/train': 1.2310906648635864} 08/31/2021 00:43:26 - INFO - __main__ - Step 63438: {'lr': 0.0003158812409843967, 'samples': 12180096, 'steps': 63437, 'loss/train': 1.0282716751098633} 08/31/2021 00:43:27 - INFO - __main__ - Step 63439: {'lr': 0.000315876121804947, 'samples': 12180288, 'steps': 63438, 'loss/train': 6.322365760803223} 08/31/2021 00:43:28 - INFO - __main__ - Step 63440: {'lr': 0.0003158710025958146, 'samples': 12180480, 'steps': 63439, 'loss/train': 1.429933786392212} 08/31/2021 00:43:29 - INFO - __main__ - Step 63441: {'lr': 0.0003158658833570017, 'samples': 12180672, 'steps': 63440, 'loss/train': 1.5781036615371704} 08/31/2021 00:43:29 - INFO - __main__ - Step 63442: {'lr': 0.00031586076408851067, 'samples': 12180864, 'steps': 63441, 'loss/train': 1.2834340333938599} 08/31/2021 00:43:29 - INFO - __main__ - Step 63443: {'lr': 0.00031585564479034376, 'samples': 12181056, 'steps': 63442, 'loss/train': 1.5563881397247314} 08/31/2021 00:43:30 - INFO - __main__ - Step 63444: {'lr': 0.0003158505254625034, 'samples': 12181248, 'steps': 63443, 'loss/train': 1.3643251657485962} 08/31/2021 00:43:30 - INFO - __main__ - Step 63445: {'lr': 0.0003158454061049917, 'samples': 12181440, 'steps': 63444, 'loss/train': 1.4727723598480225} 08/31/2021 00:43:32 - INFO - __main__ - Step 63446: {'lr': 0.00031584028671781107, 'samples': 12181632, 'steps': 63445, 'loss/train': 1.5719338655471802} 08/31/2021 00:43:32 - INFO - __main__ - Step 63447: {'lr': 0.000315835167300964, 'samples': 12181824, 'steps': 63446, 'loss/train': 1.6168831586837769} 08/31/2021 00:43:32 - INFO - __main__ - Step 63448: {'lr': 0.0003158300478544524, 'samples': 12182016, 'steps': 63447, 'loss/train': 1.7002652883529663} 08/31/2021 00:43:33 - INFO - __main__ - Step 63449: {'lr': 0.0003158249283782789, 'samples': 12182208, 'steps': 63448, 'loss/train': 0.6978510618209839} 08/31/2021 00:43:33 - INFO - __main__ - Step 63450: {'lr': 0.00031581980887244565, 'samples': 12182400, 'steps': 63449, 'loss/train': 2.3376033306121826} 08/31/2021 00:43:35 - INFO - __main__ - Step 63451: {'lr': 0.00031581468933695507, 'samples': 12182592, 'steps': 63450, 'loss/train': 1.4945000410079956} 08/31/2021 00:43:36 - INFO - __main__ - Step 63452: {'lr': 0.0003158095697718094, 'samples': 12182784, 'steps': 63451, 'loss/train': 0.6903284192085266} 08/31/2021 00:43:36 - INFO - __main__ - Step 63453: {'lr': 0.00031580445017701094, 'samples': 12182976, 'steps': 63452, 'loss/train': 1.7622568607330322} 08/31/2021 00:43:36 - INFO - __main__ - Step 63454: {'lr': 0.00031579933055256206, 'samples': 12183168, 'steps': 63453, 'loss/train': 1.3744878768920898} 08/31/2021 00:43:37 - INFO - __main__ - Step 63455: {'lr': 0.0003157942108984649, 'samples': 12183360, 'steps': 63454, 'loss/train': 0.9777416586875916} 08/31/2021 00:43:37 - INFO - __main__ - Step 63456: {'lr': 0.000315789091214722, 'samples': 12183552, 'steps': 63455, 'loss/train': 0.04754181578755379} 08/31/2021 00:43:38 - INFO - __main__ - Step 63457: {'lr': 0.00031578397150133547, 'samples': 12183744, 'steps': 63456, 'loss/train': 0.4999885559082031} 08/31/2021 00:43:39 - INFO - __main__ - Step 63458: {'lr': 0.0003157788517583077, 'samples': 12183936, 'steps': 63457, 'loss/train': 0.9499770402908325} 08/31/2021 00:43:39 - INFO - __main__ - Step 63459: {'lr': 0.0003157737319856411, 'samples': 12184128, 'steps': 63458, 'loss/train': 1.7728338241577148} 08/31/2021 00:43:40 - INFO - __main__ - Step 63460: {'lr': 0.00031576861218333773, 'samples': 12184320, 'steps': 63459, 'loss/train': 1.42353093624115} 08/31/2021 00:43:40 - INFO - __main__ - Step 63461: {'lr': 0.0003157634923514001, 'samples': 12184512, 'steps': 63460, 'loss/train': 0.5524860620498657} 08/31/2021 00:43:42 - INFO - __main__ - Step 63462: {'lr': 0.00031575837248983045, 'samples': 12184704, 'steps': 63461, 'loss/train': 1.3176542520523071} 08/31/2021 00:43:42 - INFO - __main__ - Step 63463: {'lr': 0.00031575325259863114, 'samples': 12184896, 'steps': 63462, 'loss/train': 1.1840757131576538} 08/31/2021 00:43:43 - INFO - __main__ - Step 63464: {'lr': 0.0003157481326778043, 'samples': 12185088, 'steps': 63463, 'loss/train': 1.2993731498718262} 08/31/2021 00:43:43 - INFO - __main__ - Step 63465: {'lr': 0.00031574301272735254, 'samples': 12185280, 'steps': 63464, 'loss/train': 1.0506857633590698} 08/31/2021 00:43:44 - INFO - __main__ - Step 63466: {'lr': 0.0003157378927472779, 'samples': 12185472, 'steps': 63465, 'loss/train': 1.0002514123916626} 08/31/2021 00:43:44 - INFO - __main__ - Step 63467: {'lr': 0.00031573277273758284, 'samples': 12185664, 'steps': 63466, 'loss/train': 1.9287787675857544} 08/31/2021 00:43:45 - INFO - __main__ - Step 63468: {'lr': 0.00031572765269826953, 'samples': 12185856, 'steps': 63467, 'loss/train': 1.9364341497421265} 08/31/2021 00:43:46 - INFO - __main__ - Step 63469: {'lr': 0.00031572253262934037, 'samples': 12186048, 'steps': 63468, 'loss/train': 1.9558465480804443} 08/31/2021 00:43:46 - INFO - __main__ - Step 63470: {'lr': 0.0003157174125307977, 'samples': 12186240, 'steps': 63469, 'loss/train': 0.9929943084716797} 08/31/2021 00:43:47 - INFO - __main__ - Step 63471: {'lr': 0.0003157122924026437, 'samples': 12186432, 'steps': 63470, 'loss/train': 1.76425302028656} 08/31/2021 00:43:47 - INFO - __main__ - Step 63472: {'lr': 0.00031570717224488077, 'samples': 12186624, 'steps': 63471, 'loss/train': 1.2895259857177734} 08/31/2021 00:43:48 - INFO - __main__ - Step 63473: {'lr': 0.00031570205205751125, 'samples': 12186816, 'steps': 63472, 'loss/train': 1.9915955066680908} 08/31/2021 00:43:49 - INFO - __main__ - Step 63474: {'lr': 0.00031569693184053737, 'samples': 12187008, 'steps': 63473, 'loss/train': 1.908145546913147} 08/31/2021 00:43:49 - INFO - __main__ - Step 63475: {'lr': 0.0003156918115939614, 'samples': 12187200, 'steps': 63474, 'loss/train': 1.871873378753662} 08/31/2021 00:43:50 - INFO - __main__ - Step 63476: {'lr': 0.00031568669131778587, 'samples': 12187392, 'steps': 63475, 'loss/train': 1.0215046405792236} 08/31/2021 00:43:50 - INFO - __main__ - Step 63477: {'lr': 0.00031568157101201285, 'samples': 12187584, 'steps': 63476, 'loss/train': 1.289180040359497} 08/31/2021 00:43:52 - INFO - __main__ - Step 63478: {'lr': 0.00031567645067664474, 'samples': 12187776, 'steps': 63477, 'loss/train': 1.7082439661026} 08/31/2021 00:43:52 - INFO - __main__ - Step 63479: {'lr': 0.0003156713303116838, 'samples': 12187968, 'steps': 63478, 'loss/train': 1.4908502101898193} 08/31/2021 00:43:53 - INFO - __main__ - Step 63480: {'lr': 0.0003156662099171324, 'samples': 12188160, 'steps': 63479, 'loss/train': 0.7833080291748047} 08/31/2021 00:43:53 - INFO - __main__ - Step 63481: {'lr': 0.00031566108949299284, 'samples': 12188352, 'steps': 63480, 'loss/train': 1.5595544576644897} 08/31/2021 00:43:53 - INFO - __main__ - Step 63482: {'lr': 0.00031565596903926737, 'samples': 12188544, 'steps': 63481, 'loss/train': 1.6511285305023193} 08/31/2021 00:43:55 - INFO - __main__ - Step 63483: {'lr': 0.00031565084855595825, 'samples': 12188736, 'steps': 63482, 'loss/train': 1.628576397895813} 08/31/2021 00:43:56 - INFO - __main__ - Step 63484: {'lr': 0.00031564572804306803, 'samples': 12188928, 'steps': 63483, 'loss/train': 1.0266320705413818} 08/31/2021 00:43:56 - INFO - __main__ - Step 63485: {'lr': 0.00031564060750059877, 'samples': 12189120, 'steps': 63484, 'loss/train': 1.4664963483810425} 08/31/2021 00:43:56 - INFO - __main__ - Step 63486: {'lr': 0.0003156354869285528, 'samples': 12189312, 'steps': 63485, 'loss/train': 0.4361249804496765} 08/31/2021 00:43:57 - INFO - __main__ - Step 63487: {'lr': 0.0003156303663269326, 'samples': 12189504, 'steps': 63486, 'loss/train': 1.646264672279358} 08/31/2021 00:43:57 - INFO - __main__ - Step 63488: {'lr': 0.00031562524569574043, 'samples': 12189696, 'steps': 63487, 'loss/train': 1.5001717805862427} 08/31/2021 00:43:58 - INFO - __main__ - Step 63489: {'lr': 0.0003156201250349784, 'samples': 12189888, 'steps': 63488, 'loss/train': 1.8191304206848145} 08/31/2021 00:43:59 - INFO - __main__ - Step 63490: {'lr': 0.00031561500434464904, 'samples': 12190080, 'steps': 63489, 'loss/train': 1.1371514797210693} 08/31/2021 00:43:59 - INFO - __main__ - Step 63491: {'lr': 0.00031560988362475454, 'samples': 12190272, 'steps': 63490, 'loss/train': 1.3431750535964966} 08/31/2021 00:44:00 - INFO - __main__ - Step 63492: {'lr': 0.00031560476287529715, 'samples': 12190464, 'steps': 63491, 'loss/train': 1.5333442687988281} 08/31/2021 00:44:00 - INFO - __main__ - Step 63493: {'lr': 0.00031559964209627937, 'samples': 12190656, 'steps': 63492, 'loss/train': 1.3733733892440796} 08/31/2021 00:44:01 - INFO - __main__ - Step 63494: {'lr': 0.00031559452128770337, 'samples': 12190848, 'steps': 63493, 'loss/train': 1.2887284755706787} 08/31/2021 00:44:02 - INFO - __main__ - Step 63495: {'lr': 0.0003155894004495716, 'samples': 12191040, 'steps': 63494, 'loss/train': 1.344150185585022} 08/31/2021 00:44:02 - INFO - __main__ - Step 63496: {'lr': 0.0003155842795818861, 'samples': 12191232, 'steps': 63495, 'loss/train': 1.5080816745758057} 08/31/2021 00:44:03 - INFO - __main__ - Step 63497: {'lr': 0.00031557915868464943, 'samples': 12191424, 'steps': 63496, 'loss/train': 1.7475180625915527} 08/31/2021 00:44:03 - INFO - __main__ - Step 63498: {'lr': 0.00031557403775786373, 'samples': 12191616, 'steps': 63497, 'loss/train': 1.4653501510620117} 08/31/2021 00:44:04 - INFO - __main__ - Step 63499: {'lr': 0.00031556891680153146, 'samples': 12191808, 'steps': 63498, 'loss/train': 1.3776987791061401} 08/31/2021 00:44:05 - INFO - __main__ - Step 63500: {'lr': 0.00031556379581565474, 'samples': 12192000, 'steps': 63499, 'loss/train': 0.9864248633384705} 08/31/2021 00:44:05 - INFO - __main__ - Step 63501: {'lr': 0.00031555867480023616, 'samples': 12192192, 'steps': 63500, 'loss/train': 0.5839928984642029} 08/31/2021 00:44:06 - INFO - __main__ - Step 63502: {'lr': 0.00031555355375527774, 'samples': 12192384, 'steps': 63501, 'loss/train': 0.9224342107772827} 08/31/2021 00:44:06 - INFO - __main__ - Step 63503: {'lr': 0.00031554843268078185, 'samples': 12192576, 'steps': 63502, 'loss/train': 1.653887152671814} 08/31/2021 00:44:07 - INFO - __main__ - Step 63504: {'lr': 0.00031554331157675094, 'samples': 12192768, 'steps': 63503, 'loss/train': 1.7588683366775513} 08/31/2021 00:44:08 - INFO - __main__ - Step 63505: {'lr': 0.0003155381904431872, 'samples': 12192960, 'steps': 63504, 'loss/train': 0.9848796725273132} 08/31/2021 00:44:08 - INFO - __main__ - Step 63506: {'lr': 0.0003155330692800929, 'samples': 12193152, 'steps': 63505, 'loss/train': 1.1210452318191528} 08/31/2021 00:44:09 - INFO - __main__ - Step 63507: {'lr': 0.0003155279480874705, 'samples': 12193344, 'steps': 63506, 'loss/train': 1.4904470443725586} 08/31/2021 00:44:09 - INFO - __main__ - Step 63508: {'lr': 0.0003155228268653222, 'samples': 12193536, 'steps': 63507, 'loss/train': 0.9995533227920532} 08/31/2021 00:44:11 - INFO - __main__ - Step 63509: {'lr': 0.00031551770561365027, 'samples': 12193728, 'steps': 63508, 'loss/train': 1.393264651298523} 08/31/2021 00:44:12 - INFO - __main__ - Step 63510: {'lr': 0.0003155125843324571, 'samples': 12193920, 'steps': 63509, 'loss/train': 2.015202045440674} 08/31/2021 00:44:12 - INFO - __main__ - Step 63511: {'lr': 0.000315507463021745, 'samples': 12194112, 'steps': 63510, 'loss/train': 1.6566373109817505} 08/31/2021 00:44:12 - INFO - __main__ - Step 63512: {'lr': 0.0003155023416815162, 'samples': 12194304, 'steps': 63511, 'loss/train': 1.5611387491226196} 08/31/2021 00:44:13 - INFO - __main__ - Step 63513: {'lr': 0.0003154972203117731, 'samples': 12194496, 'steps': 63512, 'loss/train': 1.7243770360946655} 08/31/2021 00:44:13 - INFO - __main__ - Step 63514: {'lr': 0.00031549209891251794, 'samples': 12194688, 'steps': 63513, 'loss/train': 1.347355842590332} 08/31/2021 00:44:14 - INFO - __main__ - Step 63515: {'lr': 0.0003154869774837531, 'samples': 12194880, 'steps': 63514, 'loss/train': 2.1504151821136475} 08/31/2021 00:44:15 - INFO - __main__ - Step 63516: {'lr': 0.0003154818560254808, 'samples': 12195072, 'steps': 63515, 'loss/train': 1.619709849357605} 08/31/2021 00:44:15 - INFO - __main__ - Step 63517: {'lr': 0.00031547673453770337, 'samples': 12195264, 'steps': 63516, 'loss/train': 1.2934805154800415} 08/31/2021 00:44:16 - INFO - __main__ - Step 63518: {'lr': 0.00031547161302042316, 'samples': 12195456, 'steps': 63517, 'loss/train': 1.693841814994812} 08/31/2021 00:44:16 - INFO - __main__ - Step 63519: {'lr': 0.00031546649147364236, 'samples': 12195648, 'steps': 63518, 'loss/train': 1.5288575887680054} 08/31/2021 00:44:18 - INFO - __main__ - Step 63520: {'lr': 0.0003154613698973635, 'samples': 12195840, 'steps': 63519, 'loss/train': 0.8061729669570923} 08/31/2021 00:44:18 - INFO - __main__ - Step 63521: {'lr': 0.0003154562482915887, 'samples': 12196032, 'steps': 63520, 'loss/train': 0.834907054901123} 08/31/2021 00:44:19 - INFO - __main__ - Step 63522: {'lr': 0.00031545112665632037, 'samples': 12196224, 'steps': 63521, 'loss/train': 0.16141319274902344} 08/31/2021 00:44:19 - INFO - __main__ - Step 63523: {'lr': 0.00031544600499156076, 'samples': 12196416, 'steps': 63522, 'loss/train': 1.2503812313079834} 08/31/2021 00:44:19 - INFO - __main__ - Step 63524: {'lr': 0.00031544088329731214, 'samples': 12196608, 'steps': 63523, 'loss/train': 0.47654110193252563} 08/31/2021 00:44:21 - INFO - __main__ - Step 63525: {'lr': 0.00031543576157357686, 'samples': 12196800, 'steps': 63524, 'loss/train': 1.809385895729065} 08/31/2021 00:44:22 - INFO - __main__ - Step 63526: {'lr': 0.00031543063982035724, 'samples': 12196992, 'steps': 63525, 'loss/train': 1.5214743614196777} 08/31/2021 00:44:22 - INFO - __main__ - Step 63527: {'lr': 0.0003154255180376556, 'samples': 12197184, 'steps': 63526, 'loss/train': 1.1978590488433838} 08/31/2021 00:44:22 - INFO - __main__ - Step 63528: {'lr': 0.00031542039622547426, 'samples': 12197376, 'steps': 63527, 'loss/train': 1.4478703737258911} 08/31/2021 00:44:23 - INFO - __main__ - Step 63529: {'lr': 0.0003154152743838155, 'samples': 12197568, 'steps': 63528, 'loss/train': 1.3474507331848145} 08/31/2021 00:44:25 - INFO - __main__ - Step 63530: {'lr': 0.0003154101525126816, 'samples': 12197760, 'steps': 63529, 'loss/train': 1.0028533935546875} 08/31/2021 00:44:25 - INFO - __main__ - Step 63531: {'lr': 0.0003154050306120749, 'samples': 12197952, 'steps': 63530, 'loss/train': 0.4025232195854187} 08/31/2021 00:44:26 - INFO - __main__ - Step 63532: {'lr': 0.0003153999086819977, 'samples': 12198144, 'steps': 63531, 'loss/train': 1.758523941040039} 08/31/2021 00:44:26 - INFO - __main__ - Step 63533: {'lr': 0.00031539478672245225, 'samples': 12198336, 'steps': 63532, 'loss/train': 1.8608888387680054} 08/31/2021 00:44:26 - INFO - __main__ - Step 63534: {'lr': 0.000315389664733441, 'samples': 12198528, 'steps': 63533, 'loss/train': 1.3978314399719238} 08/31/2021 00:44:27 - INFO - __main__ - Step 63535: {'lr': 0.0003153845427149662, 'samples': 12198720, 'steps': 63534, 'loss/train': 1.6758639812469482} 08/31/2021 00:44:28 - INFO - __main__ - Step 63536: {'lr': 0.0003153794206670301, 'samples': 12198912, 'steps': 63535, 'loss/train': 1.0138218402862549} 08/31/2021 00:44:29 - INFO - __main__ - Step 63537: {'lr': 0.000315374298589635, 'samples': 12199104, 'steps': 63536, 'loss/train': 1.3534047603607178} 08/31/2021 00:44:29 - INFO - __main__ - Step 63538: {'lr': 0.00031536917648278327, 'samples': 12199296, 'steps': 63537, 'loss/train': 1.2724394798278809} 08/31/2021 00:44:29 - INFO - __main__ - Step 63539: {'lr': 0.0003153640543464772, 'samples': 12199488, 'steps': 63538, 'loss/train': 0.1369682252407074} 08/31/2021 00:44:30 - INFO - __main__ - Step 63540: {'lr': 0.0003153589321807191, 'samples': 12199680, 'steps': 63539, 'loss/train': 1.2005479335784912} 08/31/2021 00:44:31 - INFO - __main__ - Step 63541: {'lr': 0.00031535380998551127, 'samples': 12199872, 'steps': 63540, 'loss/train': 1.1746673583984375} 08/31/2021 00:44:32 - INFO - __main__ - Step 63542: {'lr': 0.00031534868776085615, 'samples': 12200064, 'steps': 63541, 'loss/train': 1.6152994632720947} 08/31/2021 00:44:32 - INFO - __main__ - Step 63543: {'lr': 0.00031534356550675573, 'samples': 12200256, 'steps': 63542, 'loss/train': 1.492024302482605} 08/31/2021 00:44:33 - INFO - __main__ - Step 63544: {'lr': 0.0003153384432232126, 'samples': 12200448, 'steps': 63543, 'loss/train': 1.5600976943969727} 08/31/2021 00:44:33 - INFO - __main__ - Step 63545: {'lr': 0.00031533332091022894, 'samples': 12200640, 'steps': 63544, 'loss/train': 0.049544233828783035} 08/31/2021 00:44:35 - INFO - __main__ - Step 63546: {'lr': 0.0003153281985678071, 'samples': 12200832, 'steps': 63545, 'loss/train': 0.6165121793746948} 08/31/2021 00:44:35 - INFO - __main__ - Step 63547: {'lr': 0.00031532307619594935, 'samples': 12201024, 'steps': 63546, 'loss/train': 1.3397244215011597} 08/31/2021 00:44:35 - INFO - __main__ - Step 63548: {'lr': 0.0003153179537946581, 'samples': 12201216, 'steps': 63547, 'loss/train': 0.04807659611105919} 08/31/2021 00:44:36 - INFO - __main__ - Step 63549: {'lr': 0.0003153128313639356, 'samples': 12201408, 'steps': 63548, 'loss/train': 1.0502837896347046} 08/31/2021 00:44:36 - INFO - __main__ - Step 63550: {'lr': 0.00031530770890378406, 'samples': 12201600, 'steps': 63549, 'loss/train': 1.0214827060699463} 08/31/2021 00:44:38 - INFO - __main__ - Step 63551: {'lr': 0.00031530258641420593, 'samples': 12201792, 'steps': 63550, 'loss/train': 1.2505528926849365} 08/31/2021 00:44:38 - INFO - __main__ - Step 63552: {'lr': 0.0003152974638952034, 'samples': 12201984, 'steps': 63551, 'loss/train': 1.4635618925094604} 08/31/2021 00:44:38 - INFO - __main__ - Step 63553: {'lr': 0.0003152923413467789, 'samples': 12202176, 'steps': 63552, 'loss/train': 0.9026011824607849} 08/31/2021 00:44:39 - INFO - __main__ - Step 63554: {'lr': 0.0003152872187689347, 'samples': 12202368, 'steps': 63553, 'loss/train': 0.948686420917511} 08/31/2021 00:44:39 - INFO - __main__ - Step 63555: {'lr': 0.0003152820961616731, 'samples': 12202560, 'steps': 63554, 'loss/train': 1.2500348091125488} 08/31/2021 00:44:39 - INFO - __main__ - Step 63556: {'lr': 0.00031527697352499637, 'samples': 12202752, 'steps': 63555, 'loss/train': 1.5774133205413818} 08/31/2021 00:44:41 - INFO - __main__ - Step 63557: {'lr': 0.00031527185085890677, 'samples': 12202944, 'steps': 63556, 'loss/train': 1.2500823736190796} 08/31/2021 00:44:41 - INFO - __main__ - Step 63558: {'lr': 0.0003152667281634067, 'samples': 12203136, 'steps': 63557, 'loss/train': 1.1245977878570557} 08/31/2021 00:44:42 - INFO - __main__ - Step 63559: {'lr': 0.00031526160543849855, 'samples': 12203328, 'steps': 63558, 'loss/train': 1.493415117263794} 08/31/2021 00:44:42 - INFO - __main__ - Step 63560: {'lr': 0.0003152564826841844, 'samples': 12203520, 'steps': 63559, 'loss/train': 1.1828125715255737} 08/31/2021 00:44:42 - INFO - __main__ - Step 63561: {'lr': 0.0003152513599004667, 'samples': 12203712, 'steps': 63560, 'loss/train': 1.2642838954925537} 08/31/2021 00:44:44 - INFO - __main__ - Step 63562: {'lr': 0.0003152462370873479, 'samples': 12203904, 'steps': 63561, 'loss/train': 1.1748827695846558} 08/31/2021 00:44:45 - INFO - __main__ - Step 63563: {'lr': 0.00031524111424483, 'samples': 12204096, 'steps': 63562, 'loss/train': 0.8400883674621582} 08/31/2021 00:44:45 - INFO - __main__ - Step 63564: {'lr': 0.00031523599137291554, 'samples': 12204288, 'steps': 63563, 'loss/train': 1.5909343957901} 08/31/2021 00:44:45 - INFO - __main__ - Step 63565: {'lr': 0.0003152308684716067, 'samples': 12204480, 'steps': 63564, 'loss/train': 1.283403754234314} 08/31/2021 00:44:46 - INFO - __main__ - Step 63566: {'lr': 0.00031522574554090584, 'samples': 12204672, 'steps': 63565, 'loss/train': 1.8346160650253296} 08/31/2021 00:44:47 - INFO - __main__ - Step 63567: {'lr': 0.00031522062258081525, 'samples': 12204864, 'steps': 63566, 'loss/train': 1.6274458169937134} 08/31/2021 00:44:48 - INFO - __main__ - Step 63568: {'lr': 0.0003152154995913373, 'samples': 12205056, 'steps': 63567, 'loss/train': 1.268092155456543} 08/31/2021 00:44:48 - INFO - __main__ - Step 63569: {'lr': 0.0003152103765724743, 'samples': 12205248, 'steps': 63568, 'loss/train': 1.6823102235794067} 08/31/2021 00:44:48 - INFO - __main__ - Step 63570: {'lr': 0.0003152052535242284, 'samples': 12205440, 'steps': 63569, 'loss/train': 1.6236222982406616} 08/31/2021 00:44:49 - INFO - __main__ - Step 63571: {'lr': 0.00031520013044660205, 'samples': 12205632, 'steps': 63570, 'loss/train': 1.6102548837661743} 08/31/2021 00:44:49 - INFO - __main__ - Step 63572: {'lr': 0.0003151950073395975, 'samples': 12205824, 'steps': 63571, 'loss/train': 1.646880865097046} 08/31/2021 00:44:51 - INFO - __main__ - Step 63573: {'lr': 0.00031518988420321716, 'samples': 12206016, 'steps': 63572, 'loss/train': 2.000990629196167} 08/31/2021 00:44:51 - INFO - __main__ - Step 63574: {'lr': 0.0003151847610374632, 'samples': 12206208, 'steps': 63573, 'loss/train': 1.5424220561981201} 08/31/2021 00:44:51 - INFO - __main__ - Step 63575: {'lr': 0.00031517963784233804, 'samples': 12206400, 'steps': 63574, 'loss/train': 1.2665791511535645} 08/31/2021 00:44:52 - INFO - __main__ - Step 63576: {'lr': 0.000315174514617844, 'samples': 12206592, 'steps': 63575, 'loss/train': 1.270397663116455} 08/31/2021 00:44:52 - INFO - __main__ - Step 63577: {'lr': 0.00031516939136398323, 'samples': 12206784, 'steps': 63576, 'loss/train': 1.2408106327056885} 08/31/2021 00:44:54 - INFO - __main__ - Step 63578: {'lr': 0.0003151642680807581, 'samples': 12206976, 'steps': 63577, 'loss/train': 1.2449346780776978} 08/31/2021 00:44:54 - INFO - __main__ - Step 63579: {'lr': 0.00031515914476817105, 'samples': 12207168, 'steps': 63578, 'loss/train': 1.4355778694152832} 08/31/2021 00:44:55 - INFO - __main__ - Step 63580: {'lr': 0.00031515402142622424, 'samples': 12207360, 'steps': 63579, 'loss/train': 0.5260726809501648} 08/31/2021 00:44:55 - INFO - __main__ - Step 63581: {'lr': 0.00031514889805492005, 'samples': 12207552, 'steps': 63580, 'loss/train': 1.4567824602127075} 08/31/2021 00:44:55 - INFO - __main__ - Step 63582: {'lr': 0.0003151437746542608, 'samples': 12207744, 'steps': 63581, 'loss/train': 0.4226226508617401} 08/31/2021 00:44:57 - INFO - __main__ - Step 63583: {'lr': 0.00031513865122424875, 'samples': 12207936, 'steps': 63582, 'loss/train': 1.300722599029541} 08/31/2021 00:44:57 - INFO - __main__ - Step 63584: {'lr': 0.00031513352776488626, 'samples': 12208128, 'steps': 63583, 'loss/train': 1.752397060394287} 08/31/2021 00:44:58 - INFO - __main__ - Step 63585: {'lr': 0.0003151284042761755, 'samples': 12208320, 'steps': 63584, 'loss/train': 0.37659651041030884} 08/31/2021 00:44:58 - INFO - __main__ - Step 63586: {'lr': 0.00031512328075811895, 'samples': 12208512, 'steps': 63585, 'loss/train': 1.9283390045166016} 08/31/2021 00:44:58 - INFO - __main__ - Step 63587: {'lr': 0.0003151181572107189, 'samples': 12208704, 'steps': 63586, 'loss/train': 0.8649500012397766} 08/31/2021 00:45:00 - INFO - __main__ - Step 63588: {'lr': 0.0003151130336339776, 'samples': 12208896, 'steps': 63587, 'loss/train': 1.173439621925354} 08/31/2021 00:45:00 - INFO - __main__ - Step 63589: {'lr': 0.00031510791002789735, 'samples': 12209088, 'steps': 63588, 'loss/train': 1.1513558626174927} 08/31/2021 00:45:01 - INFO - __main__ - Step 63590: {'lr': 0.0003151027863924805, 'samples': 12209280, 'steps': 63589, 'loss/train': 1.3193633556365967} 08/31/2021 00:45:01 - INFO - __main__ - Step 63591: {'lr': 0.00031509766272772927, 'samples': 12209472, 'steps': 63590, 'loss/train': 0.6032484769821167} 08/31/2021 00:45:01 - INFO - __main__ - Step 63592: {'lr': 0.0003150925390336461, 'samples': 12209664, 'steps': 63591, 'loss/train': 1.666886329650879} 08/31/2021 00:45:02 - INFO - __main__ - Step 63593: {'lr': 0.0003150874153102332, 'samples': 12209856, 'steps': 63592, 'loss/train': 1.1846410036087036} 08/31/2021 00:45:04 - INFO - __main__ - Step 63594: {'lr': 0.00031508229155749294, 'samples': 12210048, 'steps': 63593, 'loss/train': 1.0058488845825195} 08/31/2021 00:45:04 - INFO - __main__ - Step 63595: {'lr': 0.0003150771677754276, 'samples': 12210240, 'steps': 63594, 'loss/train': 2.193352460861206} 08/31/2021 00:45:05 - INFO - __main__ - Step 63596: {'lr': 0.00031507204396403956, 'samples': 12210432, 'steps': 63595, 'loss/train': 1.214182734489441} 08/31/2021 00:45:05 - INFO - __main__ - Step 63597: {'lr': 0.00031506692012333096, 'samples': 12210624, 'steps': 63596, 'loss/train': 0.03716440498828888} 08/31/2021 00:45:05 - INFO - __main__ - Step 63598: {'lr': 0.00031506179625330423, 'samples': 12210816, 'steps': 63597, 'loss/train': 1.285956859588623} 08/31/2021 00:45:07 - INFO - __main__ - Step 63599: {'lr': 0.00031505667235396176, 'samples': 12211008, 'steps': 63598, 'loss/train': 1.2846001386642456} 08/31/2021 00:45:08 - INFO - __main__ - Step 63600: {'lr': 0.0003150515484253056, 'samples': 12211200, 'steps': 63599, 'loss/train': 1.8828015327453613} 08/31/2021 00:45:08 - INFO - __main__ - Step 63601: {'lr': 0.00031504642446733826, 'samples': 12211392, 'steps': 63600, 'loss/train': 1.2406747341156006} 08/31/2021 00:45:08 - INFO - __main__ - Step 63602: {'lr': 0.00031504130048006206, 'samples': 12211584, 'steps': 63601, 'loss/train': 1.6854071617126465} 08/31/2021 00:45:09 - INFO - __main__ - Step 63603: {'lr': 0.00031503617646347923, 'samples': 12211776, 'steps': 63602, 'loss/train': 0.5474222898483276} 08/31/2021 00:45:09 - INFO - __main__ - Step 63604: {'lr': 0.00031503105241759204, 'samples': 12211968, 'steps': 63603, 'loss/train': 0.38108956813812256} 08/31/2021 00:45:10 - INFO - __main__ - Step 63605: {'lr': 0.000315025928342403, 'samples': 12212160, 'steps': 63604, 'loss/train': 1.0225454568862915} 08/31/2021 00:45:11 - INFO - __main__ - Step 63606: {'lr': 0.00031502080423791417, 'samples': 12212352, 'steps': 63605, 'loss/train': 1.744140625} 08/31/2021 00:45:11 - INFO - __main__ - Step 63607: {'lr': 0.000315015680104128, 'samples': 12212544, 'steps': 63606, 'loss/train': 1.2886817455291748} 08/31/2021 00:45:12 - INFO - __main__ - Step 63608: {'lr': 0.0003150105559410468, 'samples': 12212736, 'steps': 63607, 'loss/train': 1.5738146305084229} 08/31/2021 00:45:12 - INFO - __main__ - Step 63609: {'lr': 0.00031500543174867277, 'samples': 12212928, 'steps': 63608, 'loss/train': 1.425809383392334} 08/31/2021 00:45:14 - INFO - __main__ - Step 63610: {'lr': 0.0003150003075270084, 'samples': 12213120, 'steps': 63609, 'loss/train': 1.4451093673706055} 08/31/2021 00:45:14 - INFO - __main__ - Step 63611: {'lr': 0.00031499518327605583, 'samples': 12213312, 'steps': 63610, 'loss/train': 0.858025848865509} 08/31/2021 00:45:14 - INFO - __main__ - Step 63612: {'lr': 0.0003149900589958174, 'samples': 12213504, 'steps': 63611, 'loss/train': 1.22562837600708} 08/31/2021 00:45:15 - INFO - __main__ - Step 63613: {'lr': 0.00031498493468629546, 'samples': 12213696, 'steps': 63612, 'loss/train': 1.3446500301361084} 08/31/2021 00:45:15 - INFO - __main__ - Step 63614: {'lr': 0.00031497981034749235, 'samples': 12213888, 'steps': 63613, 'loss/train': 1.6904773712158203} 08/31/2021 00:45:17 - INFO - __main__ - Step 63615: {'lr': 0.0003149746859794103, 'samples': 12214080, 'steps': 63614, 'loss/train': 1.2250962257385254} 08/31/2021 00:45:17 - INFO - __main__ - Step 63616: {'lr': 0.00031496956158205176, 'samples': 12214272, 'steps': 63615, 'loss/train': 0.9825120568275452} 08/31/2021 00:45:17 - INFO - __main__ - Step 63617: {'lr': 0.00031496443715541884, 'samples': 12214464, 'steps': 63616, 'loss/train': 1.218878984451294} 08/31/2021 00:45:18 - INFO - __main__ - Step 63618: {'lr': 0.0003149593126995139, 'samples': 12214656, 'steps': 63617, 'loss/train': 1.2676374912261963} 08/31/2021 00:45:18 - INFO - __main__ - Step 63619: {'lr': 0.0003149541882143394, 'samples': 12214848, 'steps': 63618, 'loss/train': 1.2167763710021973} 08/31/2021 00:45:20 - INFO - __main__ - Step 63620: {'lr': 0.0003149490636998975, 'samples': 12215040, 'steps': 63619, 'loss/train': 0.03918309882283211} 08/31/2021 00:45:20 - INFO - __main__ - Step 63621: {'lr': 0.00031494393915619057, 'samples': 12215232, 'steps': 63620, 'loss/train': 1.4392896890640259} 08/31/2021 00:45:20 - INFO - __main__ - Step 63622: {'lr': 0.000314938814583221, 'samples': 12215424, 'steps': 63621, 'loss/train': 1.2890160083770752} 08/31/2021 00:45:21 - INFO - __main__ - Step 63623: {'lr': 0.00031493368998099084, 'samples': 12215616, 'steps': 63622, 'loss/train': 1.8173956871032715} 08/31/2021 00:45:21 - INFO - __main__ - Step 63624: {'lr': 0.00031492856534950264, 'samples': 12215808, 'steps': 63623, 'loss/train': 1.2359925508499146} 08/31/2021 00:45:23 - INFO - __main__ - Step 63625: {'lr': 0.0003149234406887586, 'samples': 12216000, 'steps': 63624, 'loss/train': 1.1134554147720337} 08/31/2021 00:45:23 - INFO - __main__ - Step 63626: {'lr': 0.0003149183159987611, 'samples': 12216192, 'steps': 63625, 'loss/train': 1.042988896369934} 08/31/2021 00:45:24 - INFO - __main__ - Step 63627: {'lr': 0.00031491319127951236, 'samples': 12216384, 'steps': 63626, 'loss/train': 0.14170262217521667} 08/31/2021 00:45:24 - INFO - __main__ - Step 63628: {'lr': 0.0003149080665310148, 'samples': 12216576, 'steps': 63627, 'loss/train': 0.4668457508087158} 08/31/2021 00:45:24 - INFO - __main__ - Step 63629: {'lr': 0.0003149029417532706, 'samples': 12216768, 'steps': 63628, 'loss/train': 0.6954323649406433} 08/31/2021 00:45:25 - INFO - __main__ - Step 63630: {'lr': 0.0003148978169462822, 'samples': 12216960, 'steps': 63629, 'loss/train': 1.7211318016052246} 08/31/2021 00:45:26 - INFO - __main__ - Step 63631: {'lr': 0.00031489269211005177, 'samples': 12217152, 'steps': 63630, 'loss/train': 1.4046924114227295} 08/31/2021 00:45:27 - INFO - __main__ - Step 63632: {'lr': 0.00031488756724458173, 'samples': 12217344, 'steps': 63631, 'loss/train': 1.36128830909729} 08/31/2021 00:45:27 - INFO - __main__ - Step 63633: {'lr': 0.0003148824423498744, 'samples': 12217536, 'steps': 63632, 'loss/train': 0.3731187582015991} 08/31/2021 00:45:28 - INFO - __main__ - Step 63634: {'lr': 0.000314877317425932, 'samples': 12217728, 'steps': 63633, 'loss/train': 0.6946364045143127} 08/31/2021 00:45:28 - INFO - __main__ - Step 63635: {'lr': 0.0003148721924727568, 'samples': 12217920, 'steps': 63634, 'loss/train': 0.05223281309008598} 08/31/2021 00:45:29 - INFO - __main__ - Step 63636: {'lr': 0.00031486706749035134, 'samples': 12218112, 'steps': 63635, 'loss/train': 5.852504253387451} 08/31/2021 00:45:30 - INFO - __main__ - Step 63637: {'lr': 0.0003148619424787177, 'samples': 12218304, 'steps': 63636, 'loss/train': 0.9207834005355835} 08/31/2021 00:45:30 - INFO - __main__ - Step 63638: {'lr': 0.0003148568174378583, 'samples': 12218496, 'steps': 63637, 'loss/train': 1.3971260786056519} 08/31/2021 00:45:31 - INFO - __main__ - Step 63639: {'lr': 0.0003148516923677754, 'samples': 12218688, 'steps': 63638, 'loss/train': 1.5423744916915894} 08/31/2021 00:45:31 - INFO - __main__ - Step 63640: {'lr': 0.00031484656726847127, 'samples': 12218880, 'steps': 63639, 'loss/train': 0.09506344050168991} 08/31/2021 00:45:31 - INFO - __main__ - Step 63641: {'lr': 0.00031484144213994835, 'samples': 12219072, 'steps': 63640, 'loss/train': 1.107491135597229} 08/31/2021 00:45:33 - INFO - __main__ - Step 63642: {'lr': 0.00031483631698220896, 'samples': 12219264, 'steps': 63641, 'loss/train': 1.1313339471817017} 08/31/2021 00:45:33 - INFO - __main__ - Step 63643: {'lr': 0.0003148311917952552, 'samples': 12219456, 'steps': 63642, 'loss/train': 0.8299199938774109} 08/31/2021 00:45:34 - INFO - __main__ - Step 63644: {'lr': 0.0003148260665790895, 'samples': 12219648, 'steps': 63643, 'loss/train': 0.5080885887145996} 08/31/2021 00:45:34 - INFO - __main__ - Step 63645: {'lr': 0.0003148209413337142, 'samples': 12219840, 'steps': 63644, 'loss/train': 1.4142520427703857} 08/31/2021 00:45:34 - INFO - __main__ - Step 63646: {'lr': 0.00031481581605913154, 'samples': 12220032, 'steps': 63645, 'loss/train': 1.1850855350494385} 08/31/2021 00:45:37 - INFO - __main__ - Step 63647: {'lr': 0.000314810690755344, 'samples': 12220224, 'steps': 63646, 'loss/train': 1.301531195640564} 08/31/2021 00:45:37 - INFO - __main__ - Step 63648: {'lr': 0.00031480556542235366, 'samples': 12220416, 'steps': 63647, 'loss/train': 0.4627496898174286} 08/31/2021 00:45:37 - INFO - __main__ - Step 63649: {'lr': 0.000314800440060163, 'samples': 12220608, 'steps': 63648, 'loss/train': 1.7744669914245605} 08/31/2021 00:45:38 - INFO - __main__ - Step 63650: {'lr': 0.0003147953146687742, 'samples': 12220800, 'steps': 63649, 'loss/train': 0.889118492603302} 08/31/2021 00:45:38 - INFO - __main__ - Step 63651: {'lr': 0.00031479018924818967, 'samples': 12220992, 'steps': 63650, 'loss/train': 0.08763863891363144} 08/31/2021 00:45:40 - INFO - __main__ - Step 63652: {'lr': 0.00031478506379841164, 'samples': 12221184, 'steps': 63651, 'loss/train': 0.6579205393791199} 08/31/2021 00:45:40 - INFO - __main__ - Step 63653: {'lr': 0.0003147799383194425, 'samples': 12221376, 'steps': 63652, 'loss/train': 1.6172277927398682} 08/31/2021 00:45:41 - INFO - __main__ - Step 63654: {'lr': 0.0003147748128112845, 'samples': 12221568, 'steps': 63653, 'loss/train': 1.1946916580200195} 08/31/2021 00:45:41 - INFO - __main__ - Step 63655: {'lr': 0.00031476968727393997, 'samples': 12221760, 'steps': 63654, 'loss/train': 1.2854349613189697} 08/31/2021 00:45:41 - INFO - __main__ - Step 63656: {'lr': 0.00031476456170741125, 'samples': 12221952, 'steps': 63655, 'loss/train': 1.68923819065094} 08/31/2021 00:45:42 - INFO - __main__ - Step 63657: {'lr': 0.0003147594361117006, 'samples': 12222144, 'steps': 63656, 'loss/train': 1.214902400970459} 08/31/2021 00:45:43 - INFO - __main__ - Step 63658: {'lr': 0.0003147543104868103, 'samples': 12222336, 'steps': 63657, 'loss/train': 1.6187775135040283} 08/31/2021 00:45:43 - INFO - __main__ - Step 63659: {'lr': 0.0003147491848327427, 'samples': 12222528, 'steps': 63658, 'loss/train': 1.0065854787826538} 08/31/2021 00:45:44 - INFO - __main__ - Step 63660: {'lr': 0.00031474405914950023, 'samples': 12222720, 'steps': 63659, 'loss/train': 1.0402512550354004} 08/31/2021 00:45:44 - INFO - __main__ - Step 63661: {'lr': 0.00031473893343708496, 'samples': 12222912, 'steps': 63660, 'loss/train': 1.0154080390930176} 08/31/2021 00:45:45 - INFO - __main__ - Step 63662: {'lr': 0.00031473380769549944, 'samples': 12223104, 'steps': 63661, 'loss/train': 0.6477029919624329} 08/31/2021 00:45:46 - INFO - __main__ - Step 63663: {'lr': 0.0003147286819247458, 'samples': 12223296, 'steps': 63662, 'loss/train': 1.8874989748001099} 08/31/2021 00:45:47 - INFO - __main__ - Step 63664: {'lr': 0.00031472355612482646, 'samples': 12223488, 'steps': 63663, 'loss/train': 1.5264928340911865} 08/31/2021 00:45:47 - INFO - __main__ - Step 63665: {'lr': 0.0003147184302957436, 'samples': 12223680, 'steps': 63664, 'loss/train': 1.7833727598190308} 08/31/2021 00:45:48 - INFO - __main__ - Step 63666: {'lr': 0.00031471330443749967, 'samples': 12223872, 'steps': 63665, 'loss/train': 0.02319217659533024} 08/31/2021 00:45:48 - INFO - __main__ - Step 63667: {'lr': 0.00031470817855009693, 'samples': 12224064, 'steps': 63666, 'loss/train': 1.29037344455719} 08/31/2021 00:45:48 - INFO - __main__ - Step 63668: {'lr': 0.0003147030526335376, 'samples': 12224256, 'steps': 63667, 'loss/train': 1.1095267534255981} 08/31/2021 00:45:50 - INFO - __main__ - Step 63669: {'lr': 0.0003146979266878242, 'samples': 12224448, 'steps': 63668, 'loss/train': 1.2522789239883423} 08/31/2021 00:45:50 - INFO - __main__ - Step 63670: {'lr': 0.00031469280071295887, 'samples': 12224640, 'steps': 63669, 'loss/train': 1.253065586090088} 08/31/2021 00:45:51 - INFO - __main__ - Step 63671: {'lr': 0.00031468767470894395, 'samples': 12224832, 'steps': 63670, 'loss/train': 0.9056233167648315} 08/31/2021 00:45:51 - INFO - __main__ - Step 63672: {'lr': 0.0003146825486757817, 'samples': 12225024, 'steps': 63671, 'loss/train': 1.0774885416030884} 08/31/2021 00:45:51 - INFO - __main__ - Step 63673: {'lr': 0.00031467742261347457, 'samples': 12225216, 'steps': 63672, 'loss/train': 2.0717787742614746} 08/31/2021 00:45:53 - INFO - __main__ - Step 63674: {'lr': 0.00031467229652202476, 'samples': 12225408, 'steps': 63673, 'loss/train': 1.6050057411193848} 08/31/2021 00:45:54 - INFO - __main__ - Step 63675: {'lr': 0.00031466717040143464, 'samples': 12225600, 'steps': 63674, 'loss/train': 1.1668956279754639} 08/31/2021 00:45:54 - INFO - __main__ - Step 63676: {'lr': 0.0003146620442517065, 'samples': 12225792, 'steps': 63675, 'loss/train': 5.97847318649292} 08/31/2021 00:45:54 - INFO - __main__ - Step 63677: {'lr': 0.0003146569180728426, 'samples': 12225984, 'steps': 63676, 'loss/train': 1.4074180126190186} 08/31/2021 00:45:55 - INFO - __main__ - Step 63678: {'lr': 0.0003146517918648453, 'samples': 12226176, 'steps': 63677, 'loss/train': 1.661623477935791} 08/31/2021 00:45:55 - INFO - __main__ - Step 63679: {'lr': 0.00031464666562771687, 'samples': 12226368, 'steps': 63678, 'loss/train': 1.5175199508666992} 08/31/2021 00:45:57 - INFO - __main__ - Step 63680: {'lr': 0.0003146415393614597, 'samples': 12226560, 'steps': 63679, 'loss/train': 0.7951781749725342} 08/31/2021 00:45:57 - INFO - __main__ - Step 63681: {'lr': 0.00031463641306607605, 'samples': 12226752, 'steps': 63680, 'loss/train': 1.5113816261291504} 08/31/2021 00:45:57 - INFO - __main__ - Step 63682: {'lr': 0.00031463128674156816, 'samples': 12226944, 'steps': 63681, 'loss/train': 1.0151208639144897} 08/31/2021 00:45:58 - INFO - __main__ - Step 63683: {'lr': 0.00031462616038793853, 'samples': 12227136, 'steps': 63682, 'loss/train': 1.3554210662841797} 08/31/2021 00:45:58 - INFO - __main__ - Step 63684: {'lr': 0.00031462103400518924, 'samples': 12227328, 'steps': 63683, 'loss/train': 0.9572567939758301} 08/31/2021 00:46:00 - INFO - __main__ - Step 63685: {'lr': 0.0003146159075933228, 'samples': 12227520, 'steps': 63684, 'loss/train': 1.3271393775939941} 08/31/2021 00:46:00 - INFO - __main__ - Step 63686: {'lr': 0.0003146107811523413, 'samples': 12227712, 'steps': 63685, 'loss/train': 0.10287193953990936} 08/31/2021 00:46:01 - INFO - __main__ - Step 63687: {'lr': 0.00031460565468224735, 'samples': 12227904, 'steps': 63686, 'loss/train': 1.405027151107788} 08/31/2021 00:46:01 - INFO - __main__ - Step 63688: {'lr': 0.000314600528183043, 'samples': 12228096, 'steps': 63687, 'loss/train': 1.2642616033554077} 08/31/2021 00:46:01 - INFO - __main__ - Step 63689: {'lr': 0.00031459540165473067, 'samples': 12228288, 'steps': 63688, 'loss/train': 1.2779887914657593} 08/31/2021 00:46:02 - INFO - __main__ - Step 63690: {'lr': 0.00031459027509731256, 'samples': 12228480, 'steps': 63689, 'loss/train': 1.9138060808181763} 08/31/2021 00:46:02 - INFO - __main__ - Step 63691: {'lr': 0.0003145851485107911, 'samples': 12228672, 'steps': 63690, 'loss/train': 0.024682695046067238} 08/31/2021 00:46:04 - INFO - __main__ - Step 63692: {'lr': 0.00031458002189516863, 'samples': 12228864, 'steps': 63691, 'loss/train': 1.9892141819000244} 08/31/2021 00:46:04 - INFO - __main__ - Step 63693: {'lr': 0.00031457489525044737, 'samples': 12229056, 'steps': 63692, 'loss/train': 1.1594569683074951} 08/31/2021 00:46:04 - INFO - __main__ - Step 63694: {'lr': 0.00031456976857662964, 'samples': 12229248, 'steps': 63693, 'loss/train': 0.7339290976524353} 08/31/2021 00:46:05 - INFO - __main__ - Step 63695: {'lr': 0.0003145646418737178, 'samples': 12229440, 'steps': 63694, 'loss/train': 0.7319096326828003} 08/31/2021 00:46:05 - INFO - __main__ - Step 63696: {'lr': 0.0003145595151417142, 'samples': 12229632, 'steps': 63695, 'loss/train': 1.9161419868469238} 08/31/2021 00:46:07 - INFO - __main__ - Step 63697: {'lr': 0.00031455438838062094, 'samples': 12229824, 'steps': 63696, 'loss/train': 1.4529675245285034} 08/31/2021 00:46:07 - INFO - __main__ - Step 63698: {'lr': 0.0003145492615904405, 'samples': 12230016, 'steps': 63697, 'loss/train': 1.352220058441162} 08/31/2021 00:46:07 - INFO - __main__ - Step 63699: {'lr': 0.0003145441347711752, 'samples': 12230208, 'steps': 63698, 'loss/train': 1.662047266960144} 08/31/2021 00:46:08 - INFO - __main__ - Step 63700: {'lr': 0.0003145390079228273, 'samples': 12230400, 'steps': 63699, 'loss/train': 1.8421872854232788} 08/31/2021 00:46:08 - INFO - __main__ - Step 63701: {'lr': 0.0003145338810453991, 'samples': 12230592, 'steps': 63700, 'loss/train': 1.4651607275009155} 08/31/2021 00:46:10 - INFO - __main__ - Step 63702: {'lr': 0.00031452875413889294, 'samples': 12230784, 'steps': 63701, 'loss/train': 1.8237990140914917} 08/31/2021 00:46:11 - INFO - __main__ - Step 63703: {'lr': 0.0003145236272033112, 'samples': 12230976, 'steps': 63702, 'loss/train': 1.664595127105713} 08/31/2021 00:46:11 - INFO - __main__ - Step 63704: {'lr': 0.00031451850023865596, 'samples': 12231168, 'steps': 63703, 'loss/train': 1.259240746498108} 08/31/2021 00:46:11 - INFO - __main__ - Step 63705: {'lr': 0.0003145133732449298, 'samples': 12231360, 'steps': 63704, 'loss/train': 1.2167624235153198} 08/31/2021 00:46:12 - INFO - __main__ - Step 63706: {'lr': 0.0003145082462221348, 'samples': 12231552, 'steps': 63705, 'loss/train': 1.3946399688720703} 08/31/2021 00:46:13 - INFO - __main__ - Step 63707: {'lr': 0.00031450311917027347, 'samples': 12231744, 'steps': 63706, 'loss/train': 0.7038837671279907} 08/31/2021 00:46:14 - INFO - __main__ - Step 63708: {'lr': 0.00031449799208934796, 'samples': 12231936, 'steps': 63707, 'loss/train': 1.6685044765472412} 08/31/2021 00:46:14 - INFO - __main__ - Step 63709: {'lr': 0.0003144928649793607, 'samples': 12232128, 'steps': 63708, 'loss/train': 1.1885154247283936} 08/31/2021 00:46:14 - INFO - __main__ - Step 63710: {'lr': 0.000314487737840314, 'samples': 12232320, 'steps': 63709, 'loss/train': 0.8442936539649963} 08/31/2021 00:46:15 - INFO - __main__ - Step 63711: {'lr': 0.00031448261067221, 'samples': 12232512, 'steps': 63710, 'loss/train': 1.438858985900879} 08/31/2021 00:46:16 - INFO - __main__ - Step 63712: {'lr': 0.00031447748347505124, 'samples': 12232704, 'steps': 63711, 'loss/train': 0.7181492447853088} 08/31/2021 00:46:17 - INFO - __main__ - Step 63713: {'lr': 0.00031447235624883983, 'samples': 12232896, 'steps': 63712, 'loss/train': 2.1101882457733154} 08/31/2021 00:46:17 - INFO - __main__ - Step 63714: {'lr': 0.0003144672289935782, 'samples': 12233088, 'steps': 63713, 'loss/train': 1.9599014520645142} 08/31/2021 00:46:17 - INFO - __main__ - Step 63715: {'lr': 0.00031446210170926866, 'samples': 12233280, 'steps': 63714, 'loss/train': 1.2443947792053223} 08/31/2021 00:46:18 - INFO - __main__ - Step 63716: {'lr': 0.00031445697439591347, 'samples': 12233472, 'steps': 63715, 'loss/train': 1.756090760231018} 08/31/2021 00:46:19 - INFO - __main__ - Step 63717: {'lr': 0.000314451847053515, 'samples': 12233664, 'steps': 63716, 'loss/train': 1.0514874458312988} 08/31/2021 00:46:19 - INFO - __main__ - Step 63718: {'lr': 0.00031444671968207545, 'samples': 12233856, 'steps': 63717, 'loss/train': 1.4933186769485474} 08/31/2021 00:46:20 - INFO - __main__ - Step 63719: {'lr': 0.00031444159228159724, 'samples': 12234048, 'steps': 63718, 'loss/train': 1.3933829069137573} 08/31/2021 00:46:20 - INFO - __main__ - Step 63720: {'lr': 0.0003144364648520827, 'samples': 12234240, 'steps': 63719, 'loss/train': 1.4510704278945923} 08/31/2021 00:46:20 - INFO - __main__ - Step 63721: {'lr': 0.00031443133739353395, 'samples': 12234432, 'steps': 63720, 'loss/train': 1.5928927659988403} 08/31/2021 00:46:22 - INFO - __main__ - Step 63722: {'lr': 0.0003144262099059535, 'samples': 12234624, 'steps': 63721, 'loss/train': 1.7035813331604004} 08/31/2021 00:46:22 - INFO - __main__ - Step 63723: {'lr': 0.0003144210823893436, 'samples': 12234816, 'steps': 63722, 'loss/train': 1.461836576461792} 08/31/2021 00:46:23 - INFO - __main__ - Step 63724: {'lr': 0.0003144159548437066, 'samples': 12235008, 'steps': 63723, 'loss/train': 1.704469919204712} 08/31/2021 00:46:23 - INFO - __main__ - Step 63725: {'lr': 0.00031441082726904476, 'samples': 12235200, 'steps': 63724, 'loss/train': 0.16602571308612823} 08/31/2021 00:46:23 - INFO - __main__ - Step 63726: {'lr': 0.0003144056996653603, 'samples': 12235392, 'steps': 63725, 'loss/train': 1.9822883605957031} 08/31/2021 00:46:24 - INFO - __main__ - Step 63727: {'lr': 0.0003144005720326557, 'samples': 12235584, 'steps': 63726, 'loss/train': 1.4048677682876587} 08/31/2021 00:46:25 - INFO - __main__ - Step 63728: {'lr': 0.00031439544437093325, 'samples': 12235776, 'steps': 63727, 'loss/train': 1.225299596786499} 08/31/2021 00:46:26 - INFO - __main__ - Step 63729: {'lr': 0.00031439031668019515, 'samples': 12235968, 'steps': 63728, 'loss/train': 0.8727553486824036} 08/31/2021 00:46:26 - INFO - __main__ - Step 63730: {'lr': 0.00031438518896044373, 'samples': 12236160, 'steps': 63729, 'loss/train': 1.2225850820541382} 08/31/2021 00:46:26 - INFO - __main__ - Step 63731: {'lr': 0.00031438006121168135, 'samples': 12236352, 'steps': 63730, 'loss/train': 1.5643800497055054} 08/31/2021 00:46:27 - INFO - __main__ - Step 63732: {'lr': 0.00031437493343391027, 'samples': 12236544, 'steps': 63731, 'loss/train': 1.0707234144210815} 08/31/2021 00:46:28 - INFO - __main__ - Step 63733: {'lr': 0.00031436980562713293, 'samples': 12236736, 'steps': 63732, 'loss/train': 1.2115468978881836} 08/31/2021 00:46:29 - INFO - __main__ - Step 63734: {'lr': 0.0003143646777913515, 'samples': 12236928, 'steps': 63733, 'loss/train': 0.7397205829620361} 08/31/2021 00:46:29 - INFO - __main__ - Step 63735: {'lr': 0.00031435954992656837, 'samples': 12237120, 'steps': 63734, 'loss/train': 1.605910062789917} 08/31/2021 00:46:29 - INFO - __main__ - Step 63736: {'lr': 0.00031435442203278576, 'samples': 12237312, 'steps': 63735, 'loss/train': 0.6194076538085938} 08/31/2021 00:46:30 - INFO - __main__ - Step 63737: {'lr': 0.00031434929411000605, 'samples': 12237504, 'steps': 63736, 'loss/train': 1.182220697402954} 08/31/2021 00:46:31 - INFO - __main__ - Step 63738: {'lr': 0.0003143441661582316, 'samples': 12237696, 'steps': 63737, 'loss/train': 1.3701897859573364} 08/31/2021 00:46:32 - INFO - __main__ - Step 63739: {'lr': 0.0003143390381774647, 'samples': 12237888, 'steps': 63738, 'loss/train': 0.7092145681381226} 08/31/2021 00:46:32 - INFO - __main__ - Step 63740: {'lr': 0.0003143339101677075, 'samples': 12238080, 'steps': 63739, 'loss/train': 0.6564388871192932} 08/31/2021 00:46:32 - INFO - __main__ - Step 63741: {'lr': 0.0003143287821289625, 'samples': 12238272, 'steps': 63740, 'loss/train': 1.0374531745910645} 08/31/2021 00:46:33 - INFO - __main__ - Step 63742: {'lr': 0.0003143236540612319, 'samples': 12238464, 'steps': 63741, 'loss/train': 1.8190550804138184} 08/31/2021 00:46:33 - INFO - __main__ - Step 63743: {'lr': 0.0003143185259645181, 'samples': 12238656, 'steps': 63742, 'loss/train': 1.4088488817214966} 08/31/2021 00:46:35 - INFO - __main__ - Step 63744: {'lr': 0.0003143133978388234, 'samples': 12238848, 'steps': 63743, 'loss/train': 1.827333688735962} 08/31/2021 00:46:35 - INFO - __main__ - Step 63745: {'lr': 0.00031430826968414997, 'samples': 12239040, 'steps': 63744, 'loss/train': 1.2660144567489624} 08/31/2021 00:46:35 - INFO - __main__ - Step 63746: {'lr': 0.0003143031415005003, 'samples': 12239232, 'steps': 63745, 'loss/train': 0.9933860301971436} 08/31/2021 00:46:36 - INFO - __main__ - Step 63747: {'lr': 0.0003142980132878766, 'samples': 12239424, 'steps': 63746, 'loss/train': 1.551093578338623} 08/31/2021 00:46:36 - INFO - __main__ - Step 63748: {'lr': 0.0003142928850462812, 'samples': 12239616, 'steps': 63747, 'loss/train': 0.6120059490203857} 08/31/2021 00:46:38 - INFO - __main__ - Step 63749: {'lr': 0.00031428775677571643, 'samples': 12239808, 'steps': 63748, 'loss/train': 1.263735294342041} 08/31/2021 00:46:38 - INFO - __main__ - Step 63750: {'lr': 0.0003142826284761846, 'samples': 12240000, 'steps': 63749, 'loss/train': 2.0887086391448975} 08/31/2021 00:46:38 - INFO - __main__ - Step 63751: {'lr': 0.00031427750014768804, 'samples': 12240192, 'steps': 63750, 'loss/train': 1.3544996976852417} 08/31/2021 00:46:39 - INFO - __main__ - Step 63752: {'lr': 0.00031427237179022896, 'samples': 12240384, 'steps': 63751, 'loss/train': 0.8229984641075134} 08/31/2021 00:46:39 - INFO - __main__ - Step 63753: {'lr': 0.00031426724340380977, 'samples': 12240576, 'steps': 63752, 'loss/train': 1.8277246952056885} 08/31/2021 00:46:41 - INFO - __main__ - Step 63754: {'lr': 0.0003142621149884327, 'samples': 12240768, 'steps': 63753, 'loss/train': 2.7897491455078125} 08/31/2021 00:46:42 - INFO - __main__ - Step 63755: {'lr': 0.00031425698654410016, 'samples': 12240960, 'steps': 63754, 'loss/train': 1.2767101526260376} 08/31/2021 00:46:42 - INFO - __main__ - Step 63756: {'lr': 0.0003142518580708144, 'samples': 12241152, 'steps': 63755, 'loss/train': 1.4276173114776611} 08/31/2021 00:46:42 - INFO - __main__ - Step 63757: {'lr': 0.0003142467295685778, 'samples': 12241344, 'steps': 63756, 'loss/train': 1.113625407218933} 08/31/2021 00:46:43 - INFO - __main__ - Step 63758: {'lr': 0.00031424160103739264, 'samples': 12241536, 'steps': 63757, 'loss/train': 1.312881350517273} 08/31/2021 00:46:44 - INFO - __main__ - Step 63759: {'lr': 0.0003142364724772611, 'samples': 12241728, 'steps': 63758, 'loss/train': 1.1165200471878052} 08/31/2021 00:46:45 - INFO - __main__ - Step 63760: {'lr': 0.00031423134388818566, 'samples': 12241920, 'steps': 63759, 'loss/train': 1.3090671300888062} 08/31/2021 00:46:45 - INFO - __main__ - Step 63761: {'lr': 0.00031422621527016847, 'samples': 12242112, 'steps': 63760, 'loss/train': 1.0267759561538696} 08/31/2021 00:46:45 - INFO - __main__ - Step 63762: {'lr': 0.000314221086623212, 'samples': 12242304, 'steps': 63761, 'loss/train': 1.5271841287612915} 08/31/2021 00:46:46 - INFO - __main__ - Step 63763: {'lr': 0.0003142159579473186, 'samples': 12242496, 'steps': 63762, 'loss/train': 1.1536107063293457} 08/31/2021 00:46:47 - INFO - __main__ - Step 63764: {'lr': 0.0003142108292424904, 'samples': 12242688, 'steps': 63763, 'loss/train': 1.4149531126022339} 08/31/2021 00:46:48 - INFO - __main__ - Step 63765: {'lr': 0.00031420570050872976, 'samples': 12242880, 'steps': 63764, 'loss/train': 1.4433735609054565} 08/31/2021 00:46:48 - INFO - __main__ - Step 63766: {'lr': 0.00031420057174603907, 'samples': 12243072, 'steps': 63765, 'loss/train': 0.5084986090660095} 08/31/2021 00:46:48 - INFO - __main__ - Step 63767: {'lr': 0.00031419544295442056, 'samples': 12243264, 'steps': 63766, 'loss/train': 1.607119083404541} 08/31/2021 00:46:49 - INFO - __main__ - Step 63768: {'lr': 0.00031419031413387657, 'samples': 12243456, 'steps': 63767, 'loss/train': 1.5621975660324097} 08/31/2021 00:46:49 - INFO - __main__ - Step 63769: {'lr': 0.0003141851852844094, 'samples': 12243648, 'steps': 63768, 'loss/train': 1.2411539554595947} 08/31/2021 00:46:51 - INFO - __main__ - Step 63770: {'lr': 0.00031418005640602146, 'samples': 12243840, 'steps': 63769, 'loss/train': 2.1718554496765137} 08/31/2021 00:46:51 - INFO - __main__ - Step 63771: {'lr': 0.0003141749274987149, 'samples': 12244032, 'steps': 63770, 'loss/train': 1.2247374057769775} 08/31/2021 00:46:51 - INFO - __main__ - Step 63772: {'lr': 0.00031416979856249217, 'samples': 12244224, 'steps': 63771, 'loss/train': 0.6522596478462219} 08/31/2021 00:46:52 - INFO - __main__ - Step 63773: {'lr': 0.00031416466959735545, 'samples': 12244416, 'steps': 63772, 'loss/train': 1.252790093421936} 08/31/2021 00:46:52 - INFO - __main__ - Step 63774: {'lr': 0.0003141595406033071, 'samples': 12244608, 'steps': 63773, 'loss/train': 1.8619515895843506} 08/31/2021 00:46:54 - INFO - __main__ - Step 63775: {'lr': 0.00031415441158034953, 'samples': 12244800, 'steps': 63774, 'loss/train': 1.7150425910949707} 08/31/2021 00:46:54 - INFO - __main__ - Step 63776: {'lr': 0.00031414928252848493, 'samples': 12244992, 'steps': 63775, 'loss/train': 1.03728449344635} 08/31/2021 00:46:54 - INFO - __main__ - Step 63777: {'lr': 0.0003141441534477157, 'samples': 12245184, 'steps': 63776, 'loss/train': 0.7541941404342651} 08/31/2021 00:46:55 - INFO - __main__ - Step 63778: {'lr': 0.00031413902433804407, 'samples': 12245376, 'steps': 63777, 'loss/train': 0.8602122068405151} 08/31/2021 00:46:55 - INFO - __main__ - Step 63779: {'lr': 0.0003141338951994724, 'samples': 12245568, 'steps': 63778, 'loss/train': 1.4243682622909546} 08/31/2021 00:46:57 - INFO - __main__ - Step 63780: {'lr': 0.00031412876603200297, 'samples': 12245760, 'steps': 63779, 'loss/train': 1.0680497884750366} 08/31/2021 00:46:57 - INFO - __main__ - Step 63781: {'lr': 0.0003141236368356381, 'samples': 12245952, 'steps': 63780, 'loss/train': 1.2992615699768066} 08/31/2021 00:46:57 - INFO - __main__ - Step 63782: {'lr': 0.00031411850761038006, 'samples': 12246144, 'steps': 63781, 'loss/train': 0.8967943787574768} 08/31/2021 00:46:58 - INFO - __main__ - Step 63783: {'lr': 0.0003141133783562313, 'samples': 12246336, 'steps': 63782, 'loss/train': 0.9940569996833801} 08/31/2021 00:46:58 - INFO - __main__ - Step 63784: {'lr': 0.0003141082490731941, 'samples': 12246528, 'steps': 63783, 'loss/train': 1.4814571142196655} 08/31/2021 00:47:00 - INFO - __main__ - Step 63785: {'lr': 0.0003141031197612706, 'samples': 12246720, 'steps': 63784, 'loss/train': 1.4588347673416138} 08/31/2021 00:47:00 - INFO - __main__ - Step 63786: {'lr': 0.0003140979904204632, 'samples': 12246912, 'steps': 63785, 'loss/train': 2.2468807697296143} 08/31/2021 00:47:01 - INFO - __main__ - Step 63787: {'lr': 0.0003140928610507743, 'samples': 12247104, 'steps': 63786, 'loss/train': 0.9480329751968384} 08/31/2021 00:47:01 - INFO - __main__ - Step 63788: {'lr': 0.0003140877316522061, 'samples': 12247296, 'steps': 63787, 'loss/train': 1.3435050249099731} 08/31/2021 00:47:01 - INFO - __main__ - Step 63789: {'lr': 0.000314082602224761, 'samples': 12247488, 'steps': 63788, 'loss/train': 1.8836445808410645} 08/31/2021 00:47:03 - INFO - __main__ - Step 63790: {'lr': 0.00031407747276844127, 'samples': 12247680, 'steps': 63789, 'loss/train': 1.9551347494125366} 08/31/2021 00:47:03 - INFO - __main__ - Step 63791: {'lr': 0.0003140723432832492, 'samples': 12247872, 'steps': 63790, 'loss/train': 1.1621780395507812} 08/31/2021 00:47:04 - INFO - __main__ - Step 63792: {'lr': 0.0003140672137691871, 'samples': 12248064, 'steps': 63791, 'loss/train': 1.5535484552383423} 08/31/2021 00:47:04 - INFO - __main__ - Step 63793: {'lr': 0.0003140620842262573, 'samples': 12248256, 'steps': 63792, 'loss/train': 1.2001597881317139} 08/31/2021 00:47:05 - INFO - __main__ - Step 63794: {'lr': 0.00031405695465446215, 'samples': 12248448, 'steps': 63793, 'loss/train': 1.3780745267868042} 08/31/2021 00:47:06 - INFO - __main__ - Step 63795: {'lr': 0.0003140518250538039, 'samples': 12248640, 'steps': 63794, 'loss/train': 1.0365164279937744} 08/31/2021 00:47:06 - INFO - __main__ - Step 63796: {'lr': 0.0003140466954242849, 'samples': 12248832, 'steps': 63795, 'loss/train': 1.2714771032333374} 08/31/2021 00:47:07 - INFO - __main__ - Step 63797: {'lr': 0.00031404156576590747, 'samples': 12249024, 'steps': 63796, 'loss/train': 1.6875652074813843} 08/31/2021 00:47:07 - INFO - __main__ - Step 63798: {'lr': 0.0003140364360786739, 'samples': 12249216, 'steps': 63797, 'loss/train': 1.1969757080078125} 08/31/2021 00:47:07 - INFO - __main__ - Step 63799: {'lr': 0.0003140313063625865, 'samples': 12249408, 'steps': 63798, 'loss/train': 1.5024245977401733} 08/31/2021 00:47:08 - INFO - __main__ - Step 63800: {'lr': 0.0003140261766176475, 'samples': 12249600, 'steps': 63799, 'loss/train': 1.1818645000457764} 08/31/2021 00:47:09 - INFO - __main__ - Step 63801: {'lr': 0.00031402104684385935, 'samples': 12249792, 'steps': 63800, 'loss/train': 1.2838876247406006} 08/31/2021 00:47:10 - INFO - __main__ - Step 63802: {'lr': 0.00031401591704122427, 'samples': 12249984, 'steps': 63801, 'loss/train': 1.2308005094528198} 08/31/2021 00:47:10 - INFO - __main__ - Step 63803: {'lr': 0.00031401078720974464, 'samples': 12250176, 'steps': 63802, 'loss/train': 1.272182822227478} 08/31/2021 00:47:11 - INFO - __main__ - Step 63804: {'lr': 0.0003140056573494228, 'samples': 12250368, 'steps': 63803, 'loss/train': 1.4661130905151367} 08/31/2021 00:47:11 - INFO - __main__ - Step 63805: {'lr': 0.0003140005274602609, 'samples': 12250560, 'steps': 63804, 'loss/train': 0.08380899578332901} 08/31/2021 00:47:13 - INFO - __main__ - Step 63806: {'lr': 0.0003139953975422614, 'samples': 12250752, 'steps': 63805, 'loss/train': 0.9274905323982239} 08/31/2021 00:47:13 - INFO - __main__ - Step 63807: {'lr': 0.00031399026759542655, 'samples': 12250944, 'steps': 63806, 'loss/train': 1.6040891408920288} 08/31/2021 00:47:14 - INFO - __main__ - Step 63808: {'lr': 0.00031398513761975866, 'samples': 12251136, 'steps': 63807, 'loss/train': 0.5761323571205139} 08/31/2021 00:47:14 - INFO - __main__ - Step 63809: {'lr': 0.00031398000761526004, 'samples': 12251328, 'steps': 63808, 'loss/train': 4.577457904815674} 08/31/2021 00:47:14 - INFO - __main__ - Step 63810: {'lr': 0.0003139748775819331, 'samples': 12251520, 'steps': 63809, 'loss/train': 1.2026909589767456} 08/31/2021 00:47:15 - INFO - __main__ - Step 63811: {'lr': 0.00031396974751977995, 'samples': 12251712, 'steps': 63810, 'loss/train': 0.2182621955871582} 08/31/2021 00:47:17 - INFO - __main__ - Step 63812: {'lr': 0.0003139646174288031, 'samples': 12251904, 'steps': 63811, 'loss/train': 0.13252541422843933} 08/31/2021 00:47:17 - INFO - __main__ - Step 63813: {'lr': 0.0003139594873090047, 'samples': 12252096, 'steps': 63812, 'loss/train': 1.3666812181472778} 08/31/2021 00:47:17 - INFO - __main__ - Step 63814: {'lr': 0.0003139543571603872, 'samples': 12252288, 'steps': 63813, 'loss/train': 1.1218825578689575} 08/31/2021 00:47:18 - INFO - __main__ - Step 63815: {'lr': 0.0003139492269829529, 'samples': 12252480, 'steps': 63814, 'loss/train': 1.2520134449005127} 08/31/2021 00:47:18 - INFO - __main__ - Step 63816: {'lr': 0.000313944096776704, 'samples': 12252672, 'steps': 63815, 'loss/train': 1.7926610708236694} 08/31/2021 00:47:20 - INFO - __main__ - Step 63817: {'lr': 0.0003139389665416429, 'samples': 12252864, 'steps': 63816, 'loss/train': 1.3486257791519165} 08/31/2021 00:47:21 - INFO - __main__ - Step 63818: {'lr': 0.0003139338362777719, 'samples': 12253056, 'steps': 63817, 'loss/train': 1.3989133834838867} 08/31/2021 00:47:21 - INFO - __main__ - Step 63819: {'lr': 0.00031392870598509324, 'samples': 12253248, 'steps': 63818, 'loss/train': 1.4376394748687744} 08/31/2021 00:47:22 - INFO - __main__ - Step 63820: {'lr': 0.00031392357566360936, 'samples': 12253440, 'steps': 63819, 'loss/train': 0.03063294105231762} 08/31/2021 00:47:22 - INFO - __main__ - Step 63821: {'lr': 0.0003139184453133224, 'samples': 12253632, 'steps': 63820, 'loss/train': 0.0872456505894661} 08/31/2021 00:47:22 - INFO - __main__ - Step 63822: {'lr': 0.00031391331493423486, 'samples': 12253824, 'steps': 63821, 'loss/train': 0.621721625328064} 08/31/2021 00:47:24 - INFO - __main__ - Step 63823: {'lr': 0.00031390818452634896, 'samples': 12254016, 'steps': 63822, 'loss/train': 1.7384294271469116} 08/31/2021 00:47:25 - INFO - __main__ - Step 63824: {'lr': 0.0003139030540896671, 'samples': 12254208, 'steps': 63823, 'loss/train': 0.5416995882987976} 08/31/2021 00:47:25 - INFO - __main__ - Step 63825: {'lr': 0.0003138979236241914, 'samples': 12254400, 'steps': 63824, 'loss/train': 1.2870784997940063} 08/31/2021 00:47:25 - INFO - __main__ - Step 63826: {'lr': 0.0003138927931299243, 'samples': 12254592, 'steps': 63825, 'loss/train': 1.3948379755020142} 08/31/2021 00:47:26 - INFO - __main__ - Step 63827: {'lr': 0.0003138876626068681, 'samples': 12254784, 'steps': 63826, 'loss/train': 1.451692819595337} 08/31/2021 00:47:26 - INFO - __main__ - Step 63828: {'lr': 0.000313882532055025, 'samples': 12254976, 'steps': 63827, 'loss/train': 1.0048314332962036} 08/31/2021 00:47:27 - INFO - __main__ - Step 63829: {'lr': 0.00031387740147439757, 'samples': 12255168, 'steps': 63828, 'loss/train': 0.020904673263430595} 08/31/2021 00:47:28 - INFO - __main__ - Step 63830: {'lr': 0.0003138722708649879, 'samples': 12255360, 'steps': 63829, 'loss/train': 1.2569105625152588} 08/31/2021 00:47:28 - INFO - __main__ - Step 63831: {'lr': 0.00031386714022679844, 'samples': 12255552, 'steps': 63830, 'loss/train': 1.2642945051193237} 08/31/2021 00:47:29 - INFO - __main__ - Step 63832: {'lr': 0.0003138620095598314, 'samples': 12255744, 'steps': 63831, 'loss/train': 1.6725207567214966} 08/31/2021 00:47:29 - INFO - __main__ - Step 63833: {'lr': 0.0003138568788640891, 'samples': 12255936, 'steps': 63832, 'loss/train': 1.0206308364868164} 08/31/2021 00:47:29 - INFO - __main__ - Step 63834: {'lr': 0.00031385174813957387, 'samples': 12256128, 'steps': 63833, 'loss/train': 1.2391043901443481} 08/31/2021 00:47:31 - INFO - __main__ - Step 63835: {'lr': 0.00031384661738628804, 'samples': 12256320, 'steps': 63834, 'loss/train': 1.2335671186447144} 08/31/2021 00:47:32 - INFO - __main__ - Step 63836: {'lr': 0.0003138414866042339, 'samples': 12256512, 'steps': 63835, 'loss/train': 1.3402174711227417} 08/31/2021 00:47:32 - INFO - __main__ - Step 63837: {'lr': 0.0003138363557934138, 'samples': 12256704, 'steps': 63836, 'loss/train': 1.438974380493164} 08/31/2021 00:47:32 - INFO - __main__ - Step 63838: {'lr': 0.00031383122495382996, 'samples': 12256896, 'steps': 63837, 'loss/train': 1.668680191040039} 08/31/2021 00:47:33 - INFO - __main__ - Step 63839: {'lr': 0.00031382609408548486, 'samples': 12257088, 'steps': 63838, 'loss/train': 1.1255018711090088} 08/31/2021 00:47:34 - INFO - __main__ - Step 63840: {'lr': 0.0003138209631883806, 'samples': 12257280, 'steps': 63839, 'loss/train': 1.062791347503662} 08/31/2021 00:47:35 - INFO - __main__ - Step 63841: {'lr': 0.00031381583226251965, 'samples': 12257472, 'steps': 63840, 'loss/train': 0.06563165783882141} 08/31/2021 00:47:35 - INFO - __main__ - Step 63842: {'lr': 0.00031381070130790425, 'samples': 12257664, 'steps': 63841, 'loss/train': 1.617329716682434} 08/31/2021 00:47:35 - INFO - __main__ - Step 63843: {'lr': 0.0003138055703245368, 'samples': 12257856, 'steps': 63842, 'loss/train': 1.2608479261398315} 08/31/2021 00:47:36 - INFO - __main__ - Step 63844: {'lr': 0.0003138004393124195, 'samples': 12258048, 'steps': 63843, 'loss/train': 1.4423258304595947} 08/31/2021 00:47:37 - INFO - __main__ - Step 63845: {'lr': 0.00031379530827155467, 'samples': 12258240, 'steps': 63844, 'loss/train': 1.3098337650299072} 08/31/2021 00:47:38 - INFO - __main__ - Step 63846: {'lr': 0.0003137901772019447, 'samples': 12258432, 'steps': 63845, 'loss/train': 1.4476635456085205} 08/31/2021 00:47:38 - INFO - __main__ - Step 63847: {'lr': 0.00031378504610359183, 'samples': 12258624, 'steps': 63846, 'loss/train': 1.2779422998428345} 08/31/2021 00:47:38 - INFO - __main__ - Step 63848: {'lr': 0.0003137799149764984, 'samples': 12258816, 'steps': 63847, 'loss/train': 0.7790808081626892} 08/31/2021 00:47:39 - INFO - __main__ - Step 63849: {'lr': 0.00031377478382066675, 'samples': 12259008, 'steps': 63848, 'loss/train': 2.0377602577209473} 08/31/2021 00:47:40 - INFO - __main__ - Step 63850: {'lr': 0.0003137696526360991, 'samples': 12259200, 'steps': 63849, 'loss/train': 1.572812557220459} 08/31/2021 00:47:40 - INFO - __main__ - Step 63851: {'lr': 0.00031376452142279796, 'samples': 12259392, 'steps': 63850, 'loss/train': 1.3151822090148926} 08/31/2021 00:47:41 - INFO - __main__ - Step 63852: {'lr': 0.0003137593901807655, 'samples': 12259584, 'steps': 63851, 'loss/train': 1.2558236122131348} 08/31/2021 00:47:41 - INFO - __main__ - Step 63853: {'lr': 0.0003137542589100039, 'samples': 12259776, 'steps': 63852, 'loss/train': 1.5933411121368408} 08/31/2021 00:47:41 - INFO - __main__ - Step 63854: {'lr': 0.00031374912761051574, 'samples': 12259968, 'steps': 63853, 'loss/train': 0.8399307727813721} 08/31/2021 00:47:43 - INFO - __main__ - Step 63855: {'lr': 0.00031374399628230314, 'samples': 12260160, 'steps': 63854, 'loss/train': 0.4837762117385864} 08/31/2021 00:47:44 - INFO - __main__ - Step 63856: {'lr': 0.0003137388649253685, 'samples': 12260352, 'steps': 63855, 'loss/train': 1.5619271993637085} 08/31/2021 00:47:44 - INFO - __main__ - Step 63857: {'lr': 0.0003137337335397141, 'samples': 12260544, 'steps': 63856, 'loss/train': 0.1520773470401764} 08/31/2021 00:47:45 - INFO - __main__ - Step 63858: {'lr': 0.0003137286021253423, 'samples': 12260736, 'steps': 63857, 'loss/train': 0.08686301112174988} 08/31/2021 00:47:45 - INFO - __main__ - Step 63859: {'lr': 0.0003137234706822554, 'samples': 12260928, 'steps': 63858, 'loss/train': 1.075947642326355} 08/31/2021 00:47:45 - INFO - __main__ - Step 63860: {'lr': 0.0003137183392104556, 'samples': 12261120, 'steps': 63859, 'loss/train': 1.3206793069839478} 08/31/2021 00:47:47 - INFO - __main__ - Step 63861: {'lr': 0.00031371320770994535, 'samples': 12261312, 'steps': 63860, 'loss/train': 0.9747218489646912} 08/31/2021 00:47:47 - INFO - __main__ - Step 63862: {'lr': 0.00031370807618072693, 'samples': 12261504, 'steps': 63861, 'loss/train': 1.4595867395401} 08/31/2021 00:47:47 - INFO - __main__ - Step 63863: {'lr': 0.00031370294462280257, 'samples': 12261696, 'steps': 63862, 'loss/train': 1.3569902181625366} 08/31/2021 00:47:48 - INFO - __main__ - Step 63864: {'lr': 0.0003136978130361747, 'samples': 12261888, 'steps': 63863, 'loss/train': 1.569252848625183} 08/31/2021 00:47:48 - INFO - __main__ - Step 63865: {'lr': 0.00031369268142084555, 'samples': 12262080, 'steps': 63864, 'loss/train': 1.4300758838653564} 08/31/2021 00:47:50 - INFO - __main__ - Step 63866: {'lr': 0.00031368754977681744, 'samples': 12262272, 'steps': 63865, 'loss/train': 1.252185583114624} 08/31/2021 00:47:51 - INFO - __main__ - Step 63867: {'lr': 0.00031368241810409277, 'samples': 12262464, 'steps': 63866, 'loss/train': 1.2097138166427612} 08/31/2021 00:47:51 - INFO - __main__ - Step 63868: {'lr': 0.00031367728640267377, 'samples': 12262656, 'steps': 63867, 'loss/train': 0.30175939202308655} 08/31/2021 00:47:51 - INFO - __main__ - Step 63869: {'lr': 0.0003136721546725627, 'samples': 12262848, 'steps': 63868, 'loss/train': 1.3907082080841064} 08/31/2021 00:47:52 - INFO - __main__ - Step 63870: {'lr': 0.00031366702291376204, 'samples': 12263040, 'steps': 63869, 'loss/train': 1.377056360244751} 08/31/2021 00:47:52 - INFO - __main__ - Step 63871: {'lr': 0.0003136618911262739, 'samples': 12263232, 'steps': 63870, 'loss/train': 1.558740496635437} 08/31/2021 00:47:54 - INFO - __main__ - Step 63872: {'lr': 0.00031365675931010074, 'samples': 12263424, 'steps': 63871, 'loss/train': 1.1382817029953003} 08/31/2021 00:47:54 - INFO - __main__ - Step 63873: {'lr': 0.0003136516274652449, 'samples': 12263616, 'steps': 63872, 'loss/train': 1.3714760541915894} 08/31/2021 00:47:54 - INFO - __main__ - Step 63874: {'lr': 0.00031364649559170857, 'samples': 12263808, 'steps': 63873, 'loss/train': 1.543533444404602} 08/31/2021 00:47:55 - INFO - __main__ - Step 63875: {'lr': 0.000313641363689494, 'samples': 12264000, 'steps': 63874, 'loss/train': 1.6895102262496948} 08/31/2021 00:47:55 - INFO - __main__ - Step 63876: {'lr': 0.00031363623175860374, 'samples': 12264192, 'steps': 63875, 'loss/train': 0.16917984187602997} 08/31/2021 00:47:57 - INFO - __main__ - Step 63877: {'lr': 0.00031363109979903994, 'samples': 12264384, 'steps': 63876, 'loss/train': 0.6102150678634644} 08/31/2021 00:47:57 - INFO - __main__ - Step 63878: {'lr': 0.00031362596781080496, 'samples': 12264576, 'steps': 63877, 'loss/train': 1.3648712635040283} 08/31/2021 00:47:58 - INFO - __main__ - Step 63879: {'lr': 0.0003136208357939011, 'samples': 12264768, 'steps': 63878, 'loss/train': 0.03947371989488602} 08/31/2021 00:47:58 - INFO - __main__ - Step 63880: {'lr': 0.00031361570374833066, 'samples': 12264960, 'steps': 63879, 'loss/train': 0.10390610992908478} 08/31/2021 00:47:58 - INFO - __main__ - Step 63881: {'lr': 0.00031361057167409595, 'samples': 12265152, 'steps': 63880, 'loss/train': 1.3161741495132446} 08/31/2021 00:47:59 - INFO - __main__ - Step 63882: {'lr': 0.0003136054395711993, 'samples': 12265344, 'steps': 63881, 'loss/train': 0.21375909447669983} 08/31/2021 00:48:00 - INFO - __main__ - Step 63883: {'lr': 0.000313600307439643, 'samples': 12265536, 'steps': 63882, 'loss/train': 0.9536836743354797} 08/31/2021 00:48:01 - INFO - __main__ - Step 63884: {'lr': 0.0003135951752794295, 'samples': 12265728, 'steps': 63883, 'loss/train': 1.2007904052734375} 08/31/2021 00:48:01 - INFO - __main__ - Step 63885: {'lr': 0.0003135900430905609, 'samples': 12265920, 'steps': 63884, 'loss/train': 1.2533957958221436} 08/31/2021 00:48:01 - INFO - __main__ - Step 63886: {'lr': 0.0003135849108730396, 'samples': 12266112, 'steps': 63885, 'loss/train': 1.089656114578247} 08/31/2021 00:48:02 - INFO - __main__ - Step 63887: {'lr': 0.0003135797786268679, 'samples': 12266304, 'steps': 63886, 'loss/train': 0.29064130783081055} 08/31/2021 00:48:03 - INFO - __main__ - Step 63888: {'lr': 0.00031357464635204817, 'samples': 12266496, 'steps': 63887, 'loss/train': 0.8095586895942688} 08/31/2021 00:48:04 - INFO - __main__ - Step 63889: {'lr': 0.0003135695140485827, 'samples': 12266688, 'steps': 63888, 'loss/train': 1.2193946838378906} 08/31/2021 00:48:04 - INFO - __main__ - Step 63890: {'lr': 0.00031356438171647376, 'samples': 12266880, 'steps': 63889, 'loss/train': 0.9084859490394592} 08/31/2021 00:48:05 - INFO - __main__ - Step 63891: {'lr': 0.00031355924935572377, 'samples': 12267072, 'steps': 63890, 'loss/train': 1.741398811340332} 08/31/2021 00:48:05 - INFO - __main__ - Step 63892: {'lr': 0.0003135541169663349, 'samples': 12267264, 'steps': 63891, 'loss/train': 1.321596622467041} 08/31/2021 00:48:06 - INFO - __main__ - Step 63893: {'lr': 0.0003135489845483095, 'samples': 12267456, 'steps': 63892, 'loss/train': 1.3363169431686401} 08/31/2021 00:48:07 - INFO - __main__ - Step 63894: {'lr': 0.00031354385210164993, 'samples': 12267648, 'steps': 63893, 'loss/train': 1.4717912673950195} 08/31/2021 00:48:07 - INFO - __main__ - Step 63895: {'lr': 0.0003135387196263585, 'samples': 12267840, 'steps': 63894, 'loss/train': 1.3311562538146973} 08/31/2021 00:48:08 - INFO - __main__ - Step 63896: {'lr': 0.0003135335871224375, 'samples': 12268032, 'steps': 63895, 'loss/train': 0.828453779220581} 08/31/2021 00:48:08 - INFO - __main__ - Step 63897: {'lr': 0.0003135284545898892, 'samples': 12268224, 'steps': 63896, 'loss/train': 1.2457940578460693} 08/31/2021 00:48:08 - INFO - __main__ - Step 63898: {'lr': 0.00031352332202871604, 'samples': 12268416, 'steps': 63897, 'loss/train': 1.093483805656433} 08/31/2021 00:48:10 - INFO - __main__ - Step 63899: {'lr': 0.00031351818943892016, 'samples': 12268608, 'steps': 63898, 'loss/train': 1.0478293895721436} 08/31/2021 00:48:10 - INFO - __main__ - Step 63900: {'lr': 0.000313513056820504, 'samples': 12268800, 'steps': 63899, 'loss/train': 1.5279252529144287} 08/31/2021 00:48:11 - INFO - __main__ - Step 63901: {'lr': 0.0003135079241734698, 'samples': 12268992, 'steps': 63900, 'loss/train': 1.552388310432434} 08/31/2021 00:48:11 - INFO - __main__ - Step 63902: {'lr': 0.00031350279149782004, 'samples': 12269184, 'steps': 63901, 'loss/train': 1.0692238807678223} 08/31/2021 00:48:11 - INFO - __main__ - Step 63903: {'lr': 0.00031349765879355675, 'samples': 12269376, 'steps': 63902, 'loss/train': 1.2144320011138916} 08/31/2021 00:48:13 - INFO - __main__ - Step 63904: {'lr': 0.00031349252606068244, 'samples': 12269568, 'steps': 63903, 'loss/train': 0.034633979201316833} 08/31/2021 00:48:13 - INFO - __main__ - Step 63905: {'lr': 0.0003134873932991995, 'samples': 12269760, 'steps': 63904, 'loss/train': 0.050124507397413254} 08/31/2021 00:48:14 - INFO - __main__ - Step 63906: {'lr': 0.00031348226050911, 'samples': 12269952, 'steps': 63905, 'loss/train': 0.890463650226593} 08/31/2021 00:48:14 - INFO - __main__ - Step 63907: {'lr': 0.00031347712769041634, 'samples': 12270144, 'steps': 63906, 'loss/train': 1.1072555780410767} 08/31/2021 00:48:14 - INFO - __main__ - Step 63908: {'lr': 0.0003134719948431209, 'samples': 12270336, 'steps': 63907, 'loss/train': 1.5461997985839844} 08/31/2021 00:48:16 - INFO - __main__ - Step 63909: {'lr': 0.00031346686196722604, 'samples': 12270528, 'steps': 63908, 'loss/train': 1.7169437408447266} 08/31/2021 00:48:17 - INFO - __main__ - Step 63910: {'lr': 0.0003134617290627339, 'samples': 12270720, 'steps': 63909, 'loss/train': 1.1340516805648804} 08/31/2021 00:48:17 - INFO - __main__ - Step 63911: {'lr': 0.00031345659612964694, 'samples': 12270912, 'steps': 63910, 'loss/train': 1.6113648414611816} 08/31/2021 00:48:17 - INFO - __main__ - Step 63912: {'lr': 0.0003134514631679674, 'samples': 12271104, 'steps': 63911, 'loss/train': 0.5844710469245911} 08/31/2021 00:48:18 - INFO - __main__ - Step 63913: {'lr': 0.00031344633017769757, 'samples': 12271296, 'steps': 63912, 'loss/train': 1.0981603860855103} 08/31/2021 00:48:19 - INFO - __main__ - Step 63914: {'lr': 0.00031344119715883984, 'samples': 12271488, 'steps': 63913, 'loss/train': 1.218968391418457} 08/31/2021 00:48:20 - INFO - __main__ - Step 63915: {'lr': 0.0003134360641113965, 'samples': 12271680, 'steps': 63914, 'loss/train': 1.314838171005249} 08/31/2021 00:48:20 - INFO - __main__ - Step 63916: {'lr': 0.0003134309310353698, 'samples': 12271872, 'steps': 63915, 'loss/train': 2.0190529823303223} 08/31/2021 00:48:21 - INFO - __main__ - Step 63917: {'lr': 0.0003134257979307621, 'samples': 12272064, 'steps': 63916, 'loss/train': 1.6748346090316772} 08/31/2021 00:48:21 - INFO - __main__ - Step 63918: {'lr': 0.0003134206647975758, 'samples': 12272256, 'steps': 63917, 'loss/train': 1.7560955286026} 08/31/2021 00:48:22 - INFO - __main__ - Step 63919: {'lr': 0.00031341553163581306, 'samples': 12272448, 'steps': 63918, 'loss/train': 1.5536320209503174} 08/31/2021 00:48:23 - INFO - __main__ - Step 63920: {'lr': 0.00031341039844547623, 'samples': 12272640, 'steps': 63919, 'loss/train': 1.114388108253479} 08/31/2021 00:48:23 - INFO - __main__ - Step 63921: {'lr': 0.00031340526522656765, 'samples': 12272832, 'steps': 63920, 'loss/train': 1.259376883506775} 08/31/2021 00:48:24 - INFO - __main__ - Step 63922: {'lr': 0.0003134001319790897, 'samples': 12273024, 'steps': 63921, 'loss/train': 0.8426640629768372} 08/31/2021 00:48:24 - INFO - __main__ - Step 63923: {'lr': 0.0003133949987030446, 'samples': 12273216, 'steps': 63922, 'loss/train': 1.237134575843811} 08/31/2021 00:48:26 - INFO - __main__ - Step 63924: {'lr': 0.0003133898653984347, 'samples': 12273408, 'steps': 63923, 'loss/train': 1.1434271335601807} 08/31/2021 00:48:27 - INFO - __main__ - Step 63925: {'lr': 0.0003133847320652623, 'samples': 12273600, 'steps': 63924, 'loss/train': 0.9297248721122742} 08/31/2021 00:48:27 - INFO - __main__ - Step 63926: {'lr': 0.0003133795987035297, 'samples': 12273792, 'steps': 63925, 'loss/train': 1.5104440450668335} 08/31/2021 00:48:27 - INFO - __main__ - Step 63927: {'lr': 0.0003133744653132393, 'samples': 12273984, 'steps': 63926, 'loss/train': 1.6477733850479126} 08/31/2021 00:48:28 - INFO - __main__ - Step 63928: {'lr': 0.00031336933189439324, 'samples': 12274176, 'steps': 63927, 'loss/train': 1.2755907773971558} 08/31/2021 00:48:28 - INFO - __main__ - Step 63929: {'lr': 0.00031336419844699403, 'samples': 12274368, 'steps': 63928, 'loss/train': 0.48898446559906006} 08/31/2021 00:48:29 - INFO - __main__ - Step 63930: {'lr': 0.0003133590649710438, 'samples': 12274560, 'steps': 63929, 'loss/train': 0.030671339482069016} 08/31/2021 00:48:30 - INFO - __main__ - Step 63931: {'lr': 0.00031335393146654506, 'samples': 12274752, 'steps': 63930, 'loss/train': 1.3688762187957764} 08/31/2021 00:48:30 - INFO - __main__ - Step 63932: {'lr': 0.00031334879793349995, 'samples': 12274944, 'steps': 63931, 'loss/train': 1.1903363466262817} 08/31/2021 00:48:31 - INFO - __main__ - Step 63933: {'lr': 0.00031334366437191084, 'samples': 12275136, 'steps': 63932, 'loss/train': 0.02951567806303501} 08/31/2021 00:48:31 - INFO - __main__ - Step 63934: {'lr': 0.0003133385307817801, 'samples': 12275328, 'steps': 63933, 'loss/train': 1.2328184843063354} 08/31/2021 00:48:33 - INFO - __main__ - Step 63935: {'lr': 0.0003133333971631099, 'samples': 12275520, 'steps': 63934, 'loss/train': 1.6545273065567017} 08/31/2021 00:48:33 - INFO - __main__ - Step 63936: {'lr': 0.00031332826351590276, 'samples': 12275712, 'steps': 63935, 'loss/train': 1.256832242012024} 08/31/2021 00:48:33 - INFO - __main__ - Step 63937: {'lr': 0.0003133231298401608, 'samples': 12275904, 'steps': 63936, 'loss/train': 1.5879240036010742} 08/31/2021 00:48:34 - INFO - __main__ - Step 63938: {'lr': 0.00031331799613588653, 'samples': 12276096, 'steps': 63937, 'loss/train': 0.628510057926178} 08/31/2021 00:48:34 - INFO - __main__ - Step 63939: {'lr': 0.00031331286240308205, 'samples': 12276288, 'steps': 63938, 'loss/train': 1.5535578727722168} 08/31/2021 00:48:35 - INFO - __main__ - Step 63940: {'lr': 0.0003133077286417498, 'samples': 12276480, 'steps': 63939, 'loss/train': 0.7753375768661499} 08/31/2021 00:48:36 - INFO - __main__ - Step 63941: {'lr': 0.00031330259485189203, 'samples': 12276672, 'steps': 63940, 'loss/train': 1.2823940515518188} 08/31/2021 00:48:36 - INFO - __main__ - Step 63942: {'lr': 0.0003132974610335111, 'samples': 12276864, 'steps': 63941, 'loss/train': 1.1278605461120605} 08/31/2021 00:48:37 - INFO - __main__ - Step 63943: {'lr': 0.0003132923271866093, 'samples': 12277056, 'steps': 63942, 'loss/train': 1.365578532218933} 08/31/2021 00:48:37 - INFO - __main__ - Step 63944: {'lr': 0.000313287193311189, 'samples': 12277248, 'steps': 63943, 'loss/train': 1.3309252262115479} 08/31/2021 00:48:39 - INFO - __main__ - Step 63945: {'lr': 0.0003132820594072525, 'samples': 12277440, 'steps': 63944, 'loss/train': 1.2794228792190552} 08/31/2021 00:48:39 - INFO - __main__ - Step 63946: {'lr': 0.000313276925474802, 'samples': 12277632, 'steps': 63945, 'loss/train': 1.3890680074691772} 08/31/2021 00:48:39 - INFO - __main__ - Step 63947: {'lr': 0.0003132717915138399, 'samples': 12277824, 'steps': 63946, 'loss/train': 1.8157659769058228} 08/31/2021 00:48:40 - INFO - __main__ - Step 63948: {'lr': 0.00031326665752436854, 'samples': 12278016, 'steps': 63947, 'loss/train': 0.8992213010787964} 08/31/2021 00:48:40 - INFO - __main__ - Step 63949: {'lr': 0.00031326152350639016, 'samples': 12278208, 'steps': 63948, 'loss/train': 2.700030565261841} 08/31/2021 00:48:41 - INFO - __main__ - Step 63950: {'lr': 0.0003132563894599071, 'samples': 12278400, 'steps': 63949, 'loss/train': 1.3845688104629517} 08/31/2021 00:48:42 - INFO - __main__ - Step 63951: {'lr': 0.0003132512553849218, 'samples': 12278592, 'steps': 63950, 'loss/train': 1.2940402030944824} 08/31/2021 00:48:42 - INFO - __main__ - Step 63952: {'lr': 0.0003132461212814364, 'samples': 12278784, 'steps': 63951, 'loss/train': 1.2459198236465454} 08/31/2021 00:48:43 - INFO - __main__ - Step 63953: {'lr': 0.0003132409871494533, 'samples': 12278976, 'steps': 63952, 'loss/train': 1.0866756439208984} 08/31/2021 00:48:43 - INFO - __main__ - Step 63954: {'lr': 0.00031323585298897473, 'samples': 12279168, 'steps': 63953, 'loss/train': 0.7992063760757446} 08/31/2021 00:48:44 - INFO - __main__ - Step 63955: {'lr': 0.00031323071880000303, 'samples': 12279360, 'steps': 63954, 'loss/train': 0.510710597038269} 08/31/2021 00:48:45 - INFO - __main__ - Step 63956: {'lr': 0.00031322558458254056, 'samples': 12279552, 'steps': 63955, 'loss/train': 0.8208944797515869} 08/31/2021 00:48:45 - INFO - __main__ - Step 63957: {'lr': 0.0003132204503365897, 'samples': 12279744, 'steps': 63956, 'loss/train': 1.3337695598602295} 08/31/2021 00:48:46 - INFO - __main__ - Step 63958: {'lr': 0.0003132153160621526, 'samples': 12279936, 'steps': 63957, 'loss/train': 1.2162737846374512} 08/31/2021 00:48:46 - INFO - __main__ - Step 63959: {'lr': 0.0003132101817592317, 'samples': 12280128, 'steps': 63958, 'loss/train': 2.0965662002563477} 08/31/2021 00:48:46 - INFO - __main__ - Step 63960: {'lr': 0.0003132050474278293, 'samples': 12280320, 'steps': 63959, 'loss/train': 0.6973686218261719} 08/31/2021 00:48:48 - INFO - __main__ - Step 63961: {'lr': 0.0003131999130679476, 'samples': 12280512, 'steps': 63960, 'loss/train': 0.8022066354751587} 08/31/2021 00:48:49 - INFO - __main__ - Step 63962: {'lr': 0.000313194778679589, 'samples': 12280704, 'steps': 63961, 'loss/train': 0.5892042517662048} 08/31/2021 00:48:49 - INFO - __main__ - Step 63963: {'lr': 0.00031318964426275584, 'samples': 12280896, 'steps': 63962, 'loss/train': 0.6015564799308777} 08/31/2021 00:48:49 - INFO - __main__ - Step 63964: {'lr': 0.0003131845098174504, 'samples': 12281088, 'steps': 63963, 'loss/train': 0.43763428926467896} 08/31/2021 00:48:50 - INFO - __main__ - Step 63965: {'lr': 0.000313179375343675, 'samples': 12281280, 'steps': 63964, 'loss/train': 0.7753332853317261} 08/31/2021 00:48:51 - INFO - __main__ - Step 63966: {'lr': 0.00031317424084143197, 'samples': 12281472, 'steps': 63965, 'loss/train': 1.0356831550598145} 08/31/2021 00:48:52 - INFO - __main__ - Step 63967: {'lr': 0.00031316910631072354, 'samples': 12281664, 'steps': 63966, 'loss/train': 0.0436972975730896} 08/31/2021 00:48:52 - INFO - __main__ - Step 63968: {'lr': 0.00031316397175155215, 'samples': 12281856, 'steps': 63967, 'loss/train': 1.02821683883667} 08/31/2021 00:48:53 - INFO - __main__ - Step 63969: {'lr': 0.00031315883716392, 'samples': 12282048, 'steps': 63968, 'loss/train': 1.4147675037384033} 08/31/2021 00:48:53 - INFO - __main__ - Step 63970: {'lr': 0.0003131537025478294, 'samples': 12282240, 'steps': 63969, 'loss/train': 2.2979609966278076} 08/31/2021 00:48:54 - INFO - __main__ - Step 63971: {'lr': 0.00031314856790328285, 'samples': 12282432, 'steps': 63970, 'loss/train': 1.2660794258117676} 08/31/2021 00:48:55 - INFO - __main__ - Step 63972: {'lr': 0.0003131434332302825, 'samples': 12282624, 'steps': 63971, 'loss/train': 1.8413662910461426} 08/31/2021 00:48:55 - INFO - __main__ - Step 63973: {'lr': 0.00031313829852883064, 'samples': 12282816, 'steps': 63972, 'loss/train': 1.0064631700515747} 08/31/2021 00:48:56 - INFO - __main__ - Step 63974: {'lr': 0.00031313316379892966, 'samples': 12283008, 'steps': 63973, 'loss/train': 1.1582531929016113} 08/31/2021 00:48:56 - INFO - __main__ - Step 63975: {'lr': 0.0003131280290405818, 'samples': 12283200, 'steps': 63974, 'loss/train': 1.0639678239822388} 08/31/2021 00:48:58 - INFO - __main__ - Step 63976: {'lr': 0.0003131228942537895, 'samples': 12283392, 'steps': 63975, 'loss/train': 1.3891453742980957} 08/31/2021 00:48:58 - INFO - __main__ - Step 63977: {'lr': 0.0003131177594385549, 'samples': 12283584, 'steps': 63976, 'loss/train': 1.2927284240722656} 08/31/2021 00:48:59 - INFO - __main__ - Step 63978: {'lr': 0.00031311262459488053, 'samples': 12283776, 'steps': 63977, 'loss/train': 1.6461915969848633} 08/31/2021 00:48:59 - INFO - __main__ - Step 63979: {'lr': 0.0003131074897227686, 'samples': 12283968, 'steps': 63978, 'loss/train': 2.070438861846924} 08/31/2021 00:48:59 - INFO - __main__ - Step 63980: {'lr': 0.00031310235482222124, 'samples': 12284160, 'steps': 63979, 'loss/train': 0.5796709060668945} 08/31/2021 00:49:01 - INFO - __main__ - Step 63981: {'lr': 0.00031309721989324107, 'samples': 12284352, 'steps': 63980, 'loss/train': 1.0478434562683105} 08/31/2021 00:49:02 - INFO - __main__ - Step 63982: {'lr': 0.00031309208493583024, 'samples': 12284544, 'steps': 63981, 'loss/train': 1.833215594291687} 08/31/2021 00:49:02 - INFO - __main__ - Step 63983: {'lr': 0.0003130869499499911, 'samples': 12284736, 'steps': 63982, 'loss/train': 1.3272370100021362} 08/31/2021 00:49:02 - INFO - __main__ - Step 63984: {'lr': 0.0003130818149357259, 'samples': 12284928, 'steps': 63983, 'loss/train': 1.3020455837249756} 08/31/2021 00:49:03 - INFO - __main__ - Step 63985: {'lr': 0.00031307667989303713, 'samples': 12285120, 'steps': 63984, 'loss/train': 1.2525047063827515} 08/31/2021 00:49:03 - INFO - __main__ - Step 63986: {'lr': 0.00031307154482192683, 'samples': 12285312, 'steps': 63985, 'loss/train': 0.9039443135261536} 08/31/2021 00:49:05 - INFO - __main__ - Step 63987: {'lr': 0.00031306640972239753, 'samples': 12285504, 'steps': 63986, 'loss/train': 1.662134051322937} 08/31/2021 00:49:05 - INFO - __main__ - Step 63988: {'lr': 0.0003130612745944515, 'samples': 12285696, 'steps': 63987, 'loss/train': 1.681182861328125} 08/31/2021 00:49:05 - INFO - __main__ - Step 63989: {'lr': 0.000313056139438091, 'samples': 12285888, 'steps': 63988, 'loss/train': 1.462325930595398} 08/31/2021 00:49:06 - INFO - __main__ - Step 63990: {'lr': 0.0003130510042533184, 'samples': 12286080, 'steps': 63989, 'loss/train': 1.3671692609786987} 08/31/2021 00:49:06 - INFO - __main__ - Step 63991: {'lr': 0.000313045869040136, 'samples': 12286272, 'steps': 63990, 'loss/train': 1.157274842262268} 08/31/2021 00:49:08 - INFO - __main__ - Step 63992: {'lr': 0.00031304073379854607, 'samples': 12286464, 'steps': 63991, 'loss/train': 1.6030124425888062} 08/31/2021 00:49:08 - INFO - __main__ - Step 63993: {'lr': 0.00031303559852855097, 'samples': 12286656, 'steps': 63992, 'loss/train': 0.7864660620689392} 08/31/2021 00:49:08 - INFO - __main__ - Step 63994: {'lr': 0.00031303046323015297, 'samples': 12286848, 'steps': 63993, 'loss/train': 1.0620758533477783} 08/31/2021 00:49:09 - INFO - __main__ - Step 63995: {'lr': 0.00031302532790335446, 'samples': 12287040, 'steps': 63994, 'loss/train': 1.3992853164672852} 08/31/2021 00:49:09 - INFO - __main__ - Step 63996: {'lr': 0.0003130201925481577, 'samples': 12287232, 'steps': 63995, 'loss/train': 1.545284628868103} 08/31/2021 00:49:11 - INFO - __main__ - Step 63997: {'lr': 0.00031301505716456506, 'samples': 12287424, 'steps': 63996, 'loss/train': 0.9699569344520569} 08/31/2021 00:49:11 - INFO - __main__ - Step 63998: {'lr': 0.0003130099217525788, 'samples': 12287616, 'steps': 63997, 'loss/train': 1.756516456604004} 08/31/2021 00:49:11 - INFO - __main__ - Step 63999: {'lr': 0.00031300478631220114, 'samples': 12287808, 'steps': 63998, 'loss/train': 0.29698777198791504} 08/31/2021 00:49:12 - INFO - __main__ - Step 64000: {'lr': 0.00031299965084343454, 'samples': 12288000, 'steps': 63999, 'loss/train': 1.0142017602920532} 08/31/2021 00:49:12 - INFO - __main__ - Step 64001: {'lr': 0.0003129945153462813, 'samples': 12288192, 'steps': 64000, 'loss/train': 0.8188278675079346} 08/31/2021 00:49:12 - INFO - __main__ - Step 64002: {'lr': 0.0003129893798207437, 'samples': 12288384, 'steps': 64001, 'loss/train': 1.3439022302627563} 08/31/2021 00:49:14 - INFO - __main__ - Step 64003: {'lr': 0.0003129842442668241, 'samples': 12288576, 'steps': 64002, 'loss/train': 1.4170522689819336} 08/31/2021 00:49:14 - INFO - __main__ - Step 64004: {'lr': 0.00031297910868452466, 'samples': 12288768, 'steps': 64003, 'loss/train': 1.3391023874282837} 08/31/2021 00:49:15 - INFO - __main__ - Step 64005: {'lr': 0.00031297397307384787, 'samples': 12288960, 'steps': 64004, 'loss/train': 0.7478479146957397} 08/31/2021 00:49:15 - INFO - __main__ - Step 64006: {'lr': 0.000312968837434796, 'samples': 12289152, 'steps': 64005, 'loss/train': 1.5111829042434692} 08/31/2021 00:49:15 - INFO - __main__ - Step 64007: {'lr': 0.0003129637017673713, 'samples': 12289344, 'steps': 64006, 'loss/train': 0.9787699580192566} 08/31/2021 00:49:17 - INFO - __main__ - Step 64008: {'lr': 0.0003129585660715762, 'samples': 12289536, 'steps': 64007, 'loss/train': 0.9143389463424683} 08/31/2021 00:49:17 - INFO - __main__ - Step 64009: {'lr': 0.00031295343034741285, 'samples': 12289728, 'steps': 64008, 'loss/train': 1.7299370765686035} 08/31/2021 00:49:18 - INFO - __main__ - Step 64010: {'lr': 0.0003129482945948837, 'samples': 12289920, 'steps': 64009, 'loss/train': 1.2354035377502441} 08/31/2021 00:49:18 - INFO - __main__ - Step 64011: {'lr': 0.00031294315881399097, 'samples': 12290112, 'steps': 64010, 'loss/train': 1.181068778038025} 08/31/2021 00:49:18 - INFO - __main__ - Step 64012: {'lr': 0.0003129380230047371, 'samples': 12290304, 'steps': 64011, 'loss/train': 1.611760139465332} 08/31/2021 00:49:20 - INFO - __main__ - Step 64013: {'lr': 0.0003129328871671243, 'samples': 12290496, 'steps': 64012, 'loss/train': 1.2600469589233398} 08/31/2021 00:49:20 - INFO - __main__ - Step 64014: {'lr': 0.0003129277513011549, 'samples': 12290688, 'steps': 64013, 'loss/train': 0.946555495262146} 08/31/2021 00:49:21 - INFO - __main__ - Step 64015: {'lr': 0.00031292261540683127, 'samples': 12290880, 'steps': 64014, 'loss/train': 0.716672956943512} 08/31/2021 00:49:21 - INFO - __main__ - Step 64016: {'lr': 0.0003129174794841556, 'samples': 12291072, 'steps': 64015, 'loss/train': 1.7853597402572632} 08/31/2021 00:49:21 - INFO - __main__ - Step 64017: {'lr': 0.00031291234353313037, 'samples': 12291264, 'steps': 64016, 'loss/train': 1.2270013093948364} 08/31/2021 00:49:23 - INFO - __main__ - Step 64018: {'lr': 0.00031290720755375773, 'samples': 12291456, 'steps': 64017, 'loss/train': 1.433025598526001} 08/31/2021 00:49:23 - INFO - __main__ - Step 64019: {'lr': 0.0003129020715460402, 'samples': 12291648, 'steps': 64018, 'loss/train': 1.1751905679702759} 08/31/2021 00:49:24 - INFO - __main__ - Step 64020: {'lr': 0.0003128969355099798, 'samples': 12291840, 'steps': 64019, 'loss/train': 1.0217769145965576} 08/31/2021 00:49:24 - INFO - __main__ - Step 64021: {'lr': 0.0003128917994455791, 'samples': 12292032, 'steps': 64020, 'loss/train': 1.579779028892517} 08/31/2021 00:49:25 - INFO - __main__ - Step 64022: {'lr': 0.00031288666335284034, 'samples': 12292224, 'steps': 64021, 'loss/train': 1.5092931985855103} 08/31/2021 00:49:26 - INFO - __main__ - Step 64023: {'lr': 0.0003128815272317658, 'samples': 12292416, 'steps': 64022, 'loss/train': 1.1339271068572998} 08/31/2021 00:49:26 - INFO - __main__ - Step 64024: {'lr': 0.00031287639108235776, 'samples': 12292608, 'steps': 64023, 'loss/train': 1.7085473537445068} 08/31/2021 00:49:27 - INFO - __main__ - Step 64025: {'lr': 0.0003128712549046187, 'samples': 12292800, 'steps': 64024, 'loss/train': 0.9188754558563232} 08/31/2021 00:49:27 - INFO - __main__ - Step 64026: {'lr': 0.00031286611869855074, 'samples': 12292992, 'steps': 64025, 'loss/train': 0.08232084661722183} 08/31/2021 00:49:28 - INFO - __main__ - Step 64027: {'lr': 0.0003128609824641563, 'samples': 12293184, 'steps': 64026, 'loss/train': 1.252153754234314} 08/31/2021 00:49:29 - INFO - __main__ - Step 64028: {'lr': 0.00031285584620143766, 'samples': 12293376, 'steps': 64027, 'loss/train': 1.3287549018859863} 08/31/2021 00:49:30 - INFO - __main__ - Step 64029: {'lr': 0.0003128507099103971, 'samples': 12293568, 'steps': 64028, 'loss/train': 1.1528059244155884} 08/31/2021 00:49:30 - INFO - __main__ - Step 64030: {'lr': 0.00031284557359103704, 'samples': 12293760, 'steps': 64029, 'loss/train': 1.8294576406478882} 08/31/2021 00:49:31 - INFO - __main__ - Step 64031: {'lr': 0.00031284043724335973, 'samples': 12293952, 'steps': 64030, 'loss/train': 1.3751142024993896} 08/31/2021 00:49:31 - INFO - __main__ - Step 64032: {'lr': 0.00031283530086736756, 'samples': 12294144, 'steps': 64031, 'loss/train': 0.7705073356628418} 08/31/2021 00:49:32 - INFO - __main__ - Step 64033: {'lr': 0.0003128301644630627, 'samples': 12294336, 'steps': 64032, 'loss/train': 0.9349321126937866} 08/31/2021 00:49:33 - INFO - __main__ - Step 64034: {'lr': 0.0003128250280304475, 'samples': 12294528, 'steps': 64033, 'loss/train': 0.9978719353675842} 08/31/2021 00:49:33 - INFO - __main__ - Step 64035: {'lr': 0.00031281989156952436, 'samples': 12294720, 'steps': 64034, 'loss/train': 1.6149365901947021} 08/31/2021 00:49:34 - INFO - __main__ - Step 64036: {'lr': 0.0003128147550802955, 'samples': 12294912, 'steps': 64035, 'loss/train': 0.5705816745758057} 08/31/2021 00:49:34 - INFO - __main__ - Step 64037: {'lr': 0.0003128096185627633, 'samples': 12295104, 'steps': 64036, 'loss/train': 1.4002525806427002} 08/31/2021 00:49:36 - INFO - __main__ - Step 64038: {'lr': 0.0003128044820169301, 'samples': 12295296, 'steps': 64037, 'loss/train': 1.2755402326583862} 08/31/2021 00:49:36 - INFO - __main__ - Step 64039: {'lr': 0.00031279934544279817, 'samples': 12295488, 'steps': 64038, 'loss/train': 1.2679921388626099} 08/31/2021 00:49:37 - INFO - __main__ - Step 64040: {'lr': 0.0003127942088403698, 'samples': 12295680, 'steps': 64039, 'loss/train': 0.865505576133728} 08/31/2021 00:49:37 - INFO - __main__ - Step 64041: {'lr': 0.0003127890722096473, 'samples': 12295872, 'steps': 64040, 'loss/train': 1.1371299028396606} 08/31/2021 00:49:37 - INFO - __main__ - Step 64042: {'lr': 0.000312783935550633, 'samples': 12296064, 'steps': 64041, 'loss/train': 1.146579623222351} 08/31/2021 00:49:39 - INFO - __main__ - Step 64043: {'lr': 0.00031277879886332927, 'samples': 12296256, 'steps': 64042, 'loss/train': 2.034503936767578} 08/31/2021 00:49:39 - INFO - __main__ - Step 64044: {'lr': 0.0003127736621477384, 'samples': 12296448, 'steps': 64043, 'loss/train': 1.3489660024642944} 08/31/2021 00:49:40 - INFO - __main__ - Step 64045: {'lr': 0.0003127685254038626, 'samples': 12296640, 'steps': 64044, 'loss/train': 1.7920013666152954} 08/31/2021 00:49:40 - INFO - __main__ - Step 64046: {'lr': 0.0003127633886317044, 'samples': 12296832, 'steps': 64045, 'loss/train': 1.3857868909835815} 08/31/2021 00:49:40 - INFO - __main__ - Step 64047: {'lr': 0.0003127582518312659, 'samples': 12297024, 'steps': 64046, 'loss/train': 1.4361634254455566} 08/31/2021 00:49:42 - INFO - __main__ - Step 64048: {'lr': 0.00031275311500254956, 'samples': 12297216, 'steps': 64047, 'loss/train': 1.798432469367981} 08/31/2021 00:49:43 - INFO - __main__ - Step 64049: {'lr': 0.00031274797814555754, 'samples': 12297408, 'steps': 64048, 'loss/train': 1.236446738243103} 08/31/2021 00:49:43 - INFO - __main__ - Step 64050: {'lr': 0.0003127428412602923, 'samples': 12297600, 'steps': 64049, 'loss/train': 1.264224886894226} 08/31/2021 00:49:43 - INFO - __main__ - Step 64051: {'lr': 0.0003127377043467561, 'samples': 12297792, 'steps': 64050, 'loss/train': 1.7078346014022827} 08/31/2021 00:49:44 - INFO - __main__ - Step 64052: {'lr': 0.00031273256740495134, 'samples': 12297984, 'steps': 64051, 'loss/train': 6.006434917449951} 08/31/2021 00:49:44 - INFO - __main__ - Step 64053: {'lr': 0.0003127274304348802, 'samples': 12298176, 'steps': 64052, 'loss/train': 1.1362756490707397} 08/31/2021 00:49:44 - INFO - __main__ - Step 64054: {'lr': 0.00031272229343654495, 'samples': 12298368, 'steps': 64053, 'loss/train': 0.7753580808639526} 08/31/2021 00:49:46 - INFO - __main__ - Step 64055: {'lr': 0.0003127171564099481, 'samples': 12298560, 'steps': 64054, 'loss/train': 1.375970482826233} 08/31/2021 00:49:46 - INFO - __main__ - Step 64056: {'lr': 0.0003127120193550918, 'samples': 12298752, 'steps': 64055, 'loss/train': 1.8227814435958862} 08/31/2021 00:49:47 - INFO - __main__ - Step 64057: {'lr': 0.0003127068822719785, 'samples': 12298944, 'steps': 64056, 'loss/train': 1.311277985572815} 08/31/2021 00:49:47 - INFO - __main__ - Step 64058: {'lr': 0.0003127017451606104, 'samples': 12299136, 'steps': 64057, 'loss/train': 1.9113280773162842} 08/31/2021 00:49:47 - INFO - __main__ - Step 64059: {'lr': 0.00031269660802098995, 'samples': 12299328, 'steps': 64058, 'loss/train': 1.2411161661148071} 08/31/2021 00:49:49 - INFO - __main__ - Step 64060: {'lr': 0.0003126914708531193, 'samples': 12299520, 'steps': 64059, 'loss/train': 2.937511444091797} 08/31/2021 00:49:49 - INFO - __main__ - Step 64061: {'lr': 0.00031268633365700085, 'samples': 12299712, 'steps': 64060, 'loss/train': 1.914599895477295} 08/31/2021 00:49:50 - INFO - __main__ - Step 64062: {'lr': 0.00031268119643263685, 'samples': 12299904, 'steps': 64061, 'loss/train': 1.4306418895721436} 08/31/2021 00:49:50 - INFO - __main__ - Step 64063: {'lr': 0.0003126760591800297, 'samples': 12300096, 'steps': 64062, 'loss/train': 1.0937870740890503} 08/31/2021 00:49:50 - INFO - __main__ - Step 64064: {'lr': 0.0003126709218991818, 'samples': 12300288, 'steps': 64063, 'loss/train': 1.49100661277771} 08/31/2021 00:49:52 - INFO - __main__ - Step 64065: {'lr': 0.0003126657845900952, 'samples': 12300480, 'steps': 64064, 'loss/train': 0.44650566577911377} 08/31/2021 00:49:52 - INFO - __main__ - Step 64066: {'lr': 0.0003126606472527725, 'samples': 12300672, 'steps': 64065, 'loss/train': 1.8953856229782104} 08/31/2021 00:49:53 - INFO - __main__ - Step 64067: {'lr': 0.0003126555098872158, 'samples': 12300864, 'steps': 64066, 'loss/train': 1.138472318649292} 08/31/2021 00:49:53 - INFO - __main__ - Step 64068: {'lr': 0.00031265037249342747, 'samples': 12301056, 'steps': 64067, 'loss/train': 1.8186920881271362} 08/31/2021 00:49:53 - INFO - __main__ - Step 64069: {'lr': 0.00031264523507140983, 'samples': 12301248, 'steps': 64068, 'loss/train': 1.413801908493042} 08/31/2021 00:49:55 - INFO - __main__ - Step 64070: {'lr': 0.0003126400976211653, 'samples': 12301440, 'steps': 64069, 'loss/train': 0.9466199278831482} 08/31/2021 00:49:55 - INFO - __main__ - Step 64071: {'lr': 0.00031263496014269604, 'samples': 12301632, 'steps': 64070, 'loss/train': 1.6724973917007446} 08/31/2021 00:49:56 - INFO - __main__ - Step 64072: {'lr': 0.0003126298226360045, 'samples': 12301824, 'steps': 64071, 'loss/train': 1.3103843927383423} 08/31/2021 00:49:56 - INFO - __main__ - Step 64073: {'lr': 0.0003126246851010929, 'samples': 12302016, 'steps': 64072, 'loss/train': 1.346647024154663} 08/31/2021 00:49:57 - INFO - __main__ - Step 64074: {'lr': 0.0003126195475379636, 'samples': 12302208, 'steps': 64073, 'loss/train': 1.385469675064087} 08/31/2021 00:49:57 - INFO - __main__ - Step 64075: {'lr': 0.0003126144099466188, 'samples': 12302400, 'steps': 64074, 'loss/train': 0.5567613244056702} 08/31/2021 00:49:58 - INFO - __main__ - Step 64076: {'lr': 0.00031260927232706106, 'samples': 12302592, 'steps': 64075, 'loss/train': 1.1861376762390137} 08/31/2021 00:49:59 - INFO - __main__ - Step 64077: {'lr': 0.0003126041346792924, 'samples': 12302784, 'steps': 64076, 'loss/train': 1.7105385065078735} 08/31/2021 00:49:59 - INFO - __main__ - Step 64078: {'lr': 0.0003125989970033154, 'samples': 12302976, 'steps': 64077, 'loss/train': 2.58479905128479} 08/31/2021 00:50:00 - INFO - __main__ - Step 64079: {'lr': 0.00031259385929913224, 'samples': 12303168, 'steps': 64078, 'loss/train': 1.077060580253601} 08/31/2021 00:50:00 - INFO - __main__ - Step 64080: {'lr': 0.00031258872156674525, 'samples': 12303360, 'steps': 64079, 'loss/train': 1.1736823320388794} 08/31/2021 00:50:01 - INFO - __main__ - Step 64081: {'lr': 0.0003125835838061567, 'samples': 12303552, 'steps': 64080, 'loss/train': 1.0312516689300537} 08/31/2021 00:50:02 - INFO - __main__ - Step 64082: {'lr': 0.00031257844601736897, 'samples': 12303744, 'steps': 64081, 'loss/train': 1.2677052021026611} 08/31/2021 00:50:02 - INFO - __main__ - Step 64083: {'lr': 0.00031257330820038434, 'samples': 12303936, 'steps': 64082, 'loss/train': 1.3318485021591187} 08/31/2021 00:50:03 - INFO - __main__ - Step 64084: {'lr': 0.0003125681703552052, 'samples': 12304128, 'steps': 64083, 'loss/train': 0.6275831460952759} 08/31/2021 00:50:03 - INFO - __main__ - Step 64085: {'lr': 0.0003125630324818337, 'samples': 12304320, 'steps': 64084, 'loss/train': 1.6524121761322021} 08/31/2021 00:50:05 - INFO - __main__ - Step 64086: {'lr': 0.0003125578945802724, 'samples': 12304512, 'steps': 64085, 'loss/train': 0.8013032078742981} 08/31/2021 00:50:06 - INFO - __main__ - Step 64087: {'lr': 0.0003125527566505234, 'samples': 12304704, 'steps': 64086, 'loss/train': 1.5287606716156006} 08/31/2021 00:50:06 - INFO - __main__ - Step 64088: {'lr': 0.0003125476186925891, 'samples': 12304896, 'steps': 64087, 'loss/train': 1.5998494625091553} 08/31/2021 00:50:06 - INFO - __main__ - Step 64089: {'lr': 0.0003125424807064718, 'samples': 12305088, 'steps': 64088, 'loss/train': 1.0931293964385986} 08/31/2021 00:50:07 - INFO - __main__ - Step 64090: {'lr': 0.0003125373426921739, 'samples': 12305280, 'steps': 64089, 'loss/train': 1.9681097269058228} 08/31/2021 00:50:07 - INFO - __main__ - Step 64091: {'lr': 0.00031253220464969755, 'samples': 12305472, 'steps': 64090, 'loss/train': 0.6950967311859131} 08/31/2021 00:50:09 - INFO - __main__ - Step 64092: {'lr': 0.00031252706657904517, 'samples': 12305664, 'steps': 64091, 'loss/train': 0.06255407631397247} 08/31/2021 00:50:09 - INFO - __main__ - Step 64093: {'lr': 0.00031252192848021915, 'samples': 12305856, 'steps': 64092, 'loss/train': 0.6356606483459473} 08/31/2021 00:50:09 - INFO - __main__ - Step 64094: {'lr': 0.0003125167903532216, 'samples': 12306048, 'steps': 64093, 'loss/train': 1.710160493850708} 08/31/2021 00:50:10 - INFO - __main__ - Step 64095: {'lr': 0.000312511652198055, 'samples': 12306240, 'steps': 64094, 'loss/train': 1.488448977470398} 08/31/2021 00:50:10 - INFO - __main__ - Step 64096: {'lr': 0.00031250651401472157, 'samples': 12306432, 'steps': 64095, 'loss/train': 0.03731833025813103} 08/31/2021 00:50:12 - INFO - __main__ - Step 64097: {'lr': 0.0003125013758032237, 'samples': 12306624, 'steps': 64096, 'loss/train': 5.896378517150879} 08/31/2021 00:50:12 - INFO - __main__ - Step 64098: {'lr': 0.00031249623756356365, 'samples': 12306816, 'steps': 64097, 'loss/train': 1.080225944519043} 08/31/2021 00:50:12 - INFO - __main__ - Step 64099: {'lr': 0.0003124910992957438, 'samples': 12307008, 'steps': 64098, 'loss/train': 1.215929388999939} 08/31/2021 00:50:13 - INFO - __main__ - Step 64100: {'lr': 0.00031248596099976646, 'samples': 12307200, 'steps': 64099, 'loss/train': 1.157716989517212} 08/31/2021 00:50:13 - INFO - __main__ - Step 64101: {'lr': 0.00031248082267563385, 'samples': 12307392, 'steps': 64100, 'loss/train': 1.4212201833724976} 08/31/2021 00:50:15 - INFO - __main__ - Step 64102: {'lr': 0.0003124756843233483, 'samples': 12307584, 'steps': 64101, 'loss/train': 1.392958402633667} 08/31/2021 00:50:15 - INFO - __main__ - Step 64103: {'lr': 0.00031247054594291226, 'samples': 12307776, 'steps': 64102, 'loss/train': 0.8951438665390015} 08/31/2021 00:50:16 - INFO - __main__ - Step 64104: {'lr': 0.00031246540753432795, 'samples': 12307968, 'steps': 64103, 'loss/train': 0.046601008623838425} 08/31/2021 00:50:16 - INFO - __main__ - Step 64105: {'lr': 0.00031246026909759764, 'samples': 12308160, 'steps': 64104, 'loss/train': 1.560374140739441} 08/31/2021 00:50:16 - INFO - __main__ - Step 64106: {'lr': 0.0003124551306327237, 'samples': 12308352, 'steps': 64105, 'loss/train': 1.1143755912780762} 08/31/2021 00:50:18 - INFO - __main__ - Step 64107: {'lr': 0.00031244999213970846, 'samples': 12308544, 'steps': 64106, 'loss/train': 1.447361707687378} 08/31/2021 00:50:18 - INFO - __main__ - Step 64108: {'lr': 0.00031244485361855425, 'samples': 12308736, 'steps': 64107, 'loss/train': 1.4390956163406372} 08/31/2021 00:50:19 - INFO - __main__ - Step 64109: {'lr': 0.0003124397150692633, 'samples': 12308928, 'steps': 64108, 'loss/train': 0.6195098161697388} 08/31/2021 00:50:19 - INFO - __main__ - Step 64110: {'lr': 0.00031243457649183804, 'samples': 12309120, 'steps': 64109, 'loss/train': 1.584125280380249} 08/31/2021 00:50:20 - INFO - __main__ - Step 64111: {'lr': 0.00031242943788628065, 'samples': 12309312, 'steps': 64110, 'loss/train': 1.0399692058563232} 08/31/2021 00:50:21 - INFO - __main__ - Step 64112: {'lr': 0.0003124242992525935, 'samples': 12309504, 'steps': 64111, 'loss/train': 1.3818116188049316} 08/31/2021 00:50:21 - INFO - __main__ - Step 64113: {'lr': 0.0003124191605907791, 'samples': 12309696, 'steps': 64112, 'loss/train': 1.649562954902649} 08/31/2021 00:50:22 - INFO - __main__ - Step 64114: {'lr': 0.0003124140219008394, 'samples': 12309888, 'steps': 64113, 'loss/train': 1.0646555423736572} 08/31/2021 00:50:22 - INFO - __main__ - Step 64115: {'lr': 0.000312408883182777, 'samples': 12310080, 'steps': 64114, 'loss/train': 1.0771958827972412} 08/31/2021 00:50:22 - INFO - __main__ - Step 64116: {'lr': 0.000312403744436594, 'samples': 12310272, 'steps': 64115, 'loss/train': 0.0752381980419159} 08/31/2021 00:50:23 - INFO - __main__ - Step 64117: {'lr': 0.000312398605662293, 'samples': 12310464, 'steps': 64116, 'loss/train': 1.0962400436401367} 08/31/2021 00:50:24 - INFO - __main__ - Step 64118: {'lr': 0.000312393466859876, 'samples': 12310656, 'steps': 64117, 'loss/train': 1.6412402391433716} 08/31/2021 00:50:25 - INFO - __main__ - Step 64119: {'lr': 0.0003123883280293456, 'samples': 12310848, 'steps': 64118, 'loss/train': 1.0479631423950195} 08/31/2021 00:50:25 - INFO - __main__ - Step 64120: {'lr': 0.00031238318917070396, 'samples': 12311040, 'steps': 64119, 'loss/train': 1.5301388502120972} 08/31/2021 00:50:25 - INFO - __main__ - Step 64121: {'lr': 0.00031237805028395336, 'samples': 12311232, 'steps': 64120, 'loss/train': 0.9009387493133545} 08/31/2021 00:50:26 - INFO - __main__ - Step 64122: {'lr': 0.0003123729113690962, 'samples': 12311424, 'steps': 64121, 'loss/train': 1.5127530097961426} 08/31/2021 00:50:27 - INFO - __main__ - Step 64123: {'lr': 0.00031236777242613475, 'samples': 12311616, 'steps': 64122, 'loss/train': 0.9970970153808594} 08/31/2021 00:50:28 - INFO - __main__ - Step 64124: {'lr': 0.00031236263345507133, 'samples': 12311808, 'steps': 64123, 'loss/train': 1.2909400463104248} 08/31/2021 00:50:28 - INFO - __main__ - Step 64125: {'lr': 0.0003123574944559083, 'samples': 12312000, 'steps': 64124, 'loss/train': 0.5547152161598206} 08/31/2021 00:50:28 - INFO - __main__ - Step 64126: {'lr': 0.000312352355428648, 'samples': 12312192, 'steps': 64125, 'loss/train': 1.2989115715026855} 08/31/2021 00:50:29 - INFO - __main__ - Step 64127: {'lr': 0.0003123472163732926, 'samples': 12312384, 'steps': 64126, 'loss/train': 0.6586781740188599} 08/31/2021 00:50:30 - INFO - __main__ - Step 64128: {'lr': 0.0003123420772898445, 'samples': 12312576, 'steps': 64127, 'loss/train': 1.2294050455093384} 08/31/2021 00:50:31 - INFO - __main__ - Step 64129: {'lr': 0.0003123369381783061, 'samples': 12312768, 'steps': 64128, 'loss/train': 1.2308378219604492} 08/31/2021 00:50:31 - INFO - __main__ - Step 64130: {'lr': 0.00031233179903867957, 'samples': 12312960, 'steps': 64129, 'loss/train': 0.9070194363594055} 08/31/2021 00:50:31 - INFO - __main__ - Step 64131: {'lr': 0.0003123266598709674, 'samples': 12313152, 'steps': 64130, 'loss/train': 1.5365835428237915} 08/31/2021 00:50:32 - INFO - __main__ - Step 64132: {'lr': 0.0003123215206751717, 'samples': 12313344, 'steps': 64131, 'loss/train': 0.5744482278823853} 08/31/2021 00:50:33 - INFO - __main__ - Step 64133: {'lr': 0.0003123163814512949, 'samples': 12313536, 'steps': 64132, 'loss/train': 1.0790835618972778} 08/31/2021 00:50:34 - INFO - __main__ - Step 64134: {'lr': 0.0003123112421993393, 'samples': 12313728, 'steps': 64133, 'loss/train': 0.9790064692497253} 08/31/2021 00:50:34 - INFO - __main__ - Step 64135: {'lr': 0.00031230610291930723, 'samples': 12313920, 'steps': 64134, 'loss/train': 1.345521092414856} 08/31/2021 00:50:34 - INFO - __main__ - Step 64136: {'lr': 0.000312300963611201, 'samples': 12314112, 'steps': 64135, 'loss/train': 1.1798808574676514} 08/31/2021 00:50:35 - INFO - __main__ - Step 64137: {'lr': 0.0003122958242750229, 'samples': 12314304, 'steps': 64136, 'loss/train': 0.5685314536094666} 08/31/2021 00:50:37 - INFO - __main__ - Step 64138: {'lr': 0.0003122906849107753, 'samples': 12314496, 'steps': 64137, 'loss/train': 1.4148070812225342} 08/31/2021 00:50:37 - INFO - __main__ - Step 64139: {'lr': 0.00031228554551846046, 'samples': 12314688, 'steps': 64138, 'loss/train': 1.5229291915893555} 08/31/2021 00:50:37 - INFO - __main__ - Step 64140: {'lr': 0.00031228040609808063, 'samples': 12314880, 'steps': 64139, 'loss/train': 1.51760995388031} 08/31/2021 00:50:38 - INFO - __main__ - Step 64141: {'lr': 0.0003122752666496383, 'samples': 12315072, 'steps': 64140, 'loss/train': 0.6229245066642761} 08/31/2021 00:50:38 - INFO - __main__ - Step 64142: {'lr': 0.0003122701271731357, 'samples': 12315264, 'steps': 64141, 'loss/train': 1.4992125034332275} 08/31/2021 00:50:40 - INFO - __main__ - Step 64143: {'lr': 0.0003122649876685751, 'samples': 12315456, 'steps': 64142, 'loss/train': 1.1589951515197754} 08/31/2021 00:50:40 - INFO - __main__ - Step 64144: {'lr': 0.0003122598481359589, 'samples': 12315648, 'steps': 64143, 'loss/train': 1.2156248092651367} 08/31/2021 00:50:40 - INFO - __main__ - Step 64145: {'lr': 0.0003122547085752893, 'samples': 12315840, 'steps': 64144, 'loss/train': 1.1832987070083618} 08/31/2021 00:50:41 - INFO - __main__ - Step 64146: {'lr': 0.00031224956898656876, 'samples': 12316032, 'steps': 64145, 'loss/train': 1.960123896598816} 08/31/2021 00:50:41 - INFO - __main__ - Step 64147: {'lr': 0.00031224442936979947, 'samples': 12316224, 'steps': 64146, 'loss/train': 1.383860468864441} 08/31/2021 00:50:41 - INFO - __main__ - Step 64148: {'lr': 0.0003122392897249839, 'samples': 12316416, 'steps': 64147, 'loss/train': 1.3171675205230713} 08/31/2021 00:50:43 - INFO - __main__ - Step 64149: {'lr': 0.0003122341500521242, 'samples': 12316608, 'steps': 64148, 'loss/train': 0.5624788999557495} 08/31/2021 00:50:44 - INFO - __main__ - Step 64150: {'lr': 0.0003122290103512227, 'samples': 12316800, 'steps': 64149, 'loss/train': 0.9583098888397217} 08/31/2021 00:50:44 - INFO - __main__ - Step 64151: {'lr': 0.0003122238706222818, 'samples': 12316992, 'steps': 64150, 'loss/train': 0.07504381984472275} 08/31/2021 00:50:44 - INFO - __main__ - Step 64152: {'lr': 0.0003122187308653038, 'samples': 12317184, 'steps': 64151, 'loss/train': 0.9144591093063354} 08/31/2021 00:50:45 - INFO - __main__ - Step 64153: {'lr': 0.00031221359108029104, 'samples': 12317376, 'steps': 64152, 'loss/train': 1.2873417139053345} 08/31/2021 00:50:46 - INFO - __main__ - Step 64154: {'lr': 0.00031220845126724576, 'samples': 12317568, 'steps': 64153, 'loss/train': 1.1486104726791382} 08/31/2021 00:50:47 - INFO - __main__ - Step 64155: {'lr': 0.0003122033114261703, 'samples': 12317760, 'steps': 64154, 'loss/train': 1.24453866481781} 08/31/2021 00:50:47 - INFO - __main__ - Step 64156: {'lr': 0.00031219817155706697, 'samples': 12317952, 'steps': 64155, 'loss/train': 1.8499107360839844} 08/31/2021 00:50:47 - INFO - __main__ - Step 64157: {'lr': 0.0003121930316599381, 'samples': 12318144, 'steps': 64156, 'loss/train': 1.355590581893921} 08/31/2021 00:50:48 - INFO - __main__ - Step 64158: {'lr': 0.00031218789173478607, 'samples': 12318336, 'steps': 64157, 'loss/train': 0.9920222759246826} 08/31/2021 00:50:49 - INFO - __main__ - Step 64159: {'lr': 0.0003121827517816131, 'samples': 12318528, 'steps': 64158, 'loss/train': 0.22200971841812134} 08/31/2021 00:50:50 - INFO - __main__ - Step 64160: {'lr': 0.0003121776118004216, 'samples': 12318720, 'steps': 64159, 'loss/train': 1.2512885332107544} 08/31/2021 00:50:50 - INFO - __main__ - Step 64161: {'lr': 0.0003121724717912138, 'samples': 12318912, 'steps': 64160, 'loss/train': 1.2934645414352417} 08/31/2021 00:50:50 - INFO - __main__ - Step 64162: {'lr': 0.000312167331753992, 'samples': 12319104, 'steps': 64161, 'loss/train': 1.4259852170944214} 08/31/2021 00:50:51 - INFO - __main__ - Step 64163: {'lr': 0.00031216219168875856, 'samples': 12319296, 'steps': 64162, 'loss/train': 1.033271312713623} 08/31/2021 00:50:52 - INFO - __main__ - Step 64164: {'lr': 0.00031215705159551576, 'samples': 12319488, 'steps': 64163, 'loss/train': 1.7125529050827026} 08/31/2021 00:50:53 - INFO - __main__ - Step 64165: {'lr': 0.000312151911474266, 'samples': 12319680, 'steps': 64164, 'loss/train': 0.1905861794948578} 08/31/2021 00:50:53 - INFO - __main__ - Step 64166: {'lr': 0.0003121467713250116, 'samples': 12319872, 'steps': 64165, 'loss/train': 1.2450531721115112} 08/31/2021 00:50:53 - INFO - __main__ - Step 64167: {'lr': 0.00031214163114775477, 'samples': 12320064, 'steps': 64166, 'loss/train': 1.1463446617126465} 08/31/2021 00:50:54 - INFO - __main__ - Step 64168: {'lr': 0.00031213649094249783, 'samples': 12320256, 'steps': 64167, 'loss/train': 0.5957515835762024} 08/31/2021 00:50:55 - INFO - __main__ - Step 64169: {'lr': 0.0003121313507092433, 'samples': 12320448, 'steps': 64168, 'loss/train': 0.9746990203857422} 08/31/2021 00:50:56 - INFO - __main__ - Step 64170: {'lr': 0.00031212621044799315, 'samples': 12320640, 'steps': 64169, 'loss/train': 1.1030126810073853} 08/31/2021 00:50:56 - INFO - __main__ - Step 64171: {'lr': 0.00031212107015875, 'samples': 12320832, 'steps': 64170, 'loss/train': 0.04829961434006691} 08/31/2021 00:50:56 - INFO - __main__ - Step 64172: {'lr': 0.00031211592984151603, 'samples': 12321024, 'steps': 64171, 'loss/train': 1.1287485361099243} 08/31/2021 00:50:57 - INFO - __main__ - Step 64173: {'lr': 0.00031211078949629364, 'samples': 12321216, 'steps': 64172, 'loss/train': 1.8123795986175537} 08/31/2021 00:50:58 - INFO - __main__ - Step 64174: {'lr': 0.00031210564912308506, 'samples': 12321408, 'steps': 64173, 'loss/train': 1.7549808025360107} 08/31/2021 00:50:59 - INFO - __main__ - Step 64175: {'lr': 0.00031210050872189257, 'samples': 12321600, 'steps': 64174, 'loss/train': 0.7262669801712036} 08/31/2021 00:50:59 - INFO - __main__ - Step 64176: {'lr': 0.00031209536829271856, 'samples': 12321792, 'steps': 64175, 'loss/train': 1.3258405923843384} 08/31/2021 00:50:59 - INFO - __main__ - Step 64177: {'lr': 0.00031209022783556536, 'samples': 12321984, 'steps': 64176, 'loss/train': 2.018324851989746} 08/31/2021 00:51:00 - INFO - __main__ - Step 64178: {'lr': 0.0003120850873504353, 'samples': 12322176, 'steps': 64177, 'loss/train': 0.9892061948776245} 08/31/2021 00:51:01 - INFO - __main__ - Step 64179: {'lr': 0.00031207994683733054, 'samples': 12322368, 'steps': 64178, 'loss/train': 0.4570460915565491} 08/31/2021 00:51:02 - INFO - __main__ - Step 64180: {'lr': 0.0003120748062962537, 'samples': 12322560, 'steps': 64179, 'loss/train': 1.3925048112869263} 08/31/2021 00:51:02 - INFO - __main__ - Step 64181: {'lr': 0.00031206966572720676, 'samples': 12322752, 'steps': 64180, 'loss/train': 1.6027557849884033} 08/31/2021 00:51:02 - INFO - __main__ - Step 64182: {'lr': 0.00031206452513019223, 'samples': 12322944, 'steps': 64181, 'loss/train': 1.1206021308898926} 08/31/2021 00:51:03 - INFO - __main__ - Step 64183: {'lr': 0.0003120593845052124, 'samples': 12323136, 'steps': 64182, 'loss/train': 1.6616511344909668} 08/31/2021 00:51:04 - INFO - __main__ - Step 64184: {'lr': 0.0003120542438522695, 'samples': 12323328, 'steps': 64183, 'loss/train': 1.3227694034576416} 08/31/2021 00:51:05 - INFO - __main__ - Step 64185: {'lr': 0.000312049103171366, 'samples': 12323520, 'steps': 64184, 'loss/train': 1.485461711883545} 08/31/2021 00:51:05 - INFO - __main__ - Step 64186: {'lr': 0.00031204396246250403, 'samples': 12323712, 'steps': 64185, 'loss/train': 1.8316982984542847} 08/31/2021 00:51:05 - INFO - __main__ - Step 64187: {'lr': 0.00031203882172568614, 'samples': 12323904, 'steps': 64186, 'loss/train': 1.6549971103668213} 08/31/2021 00:51:06 - INFO - __main__ - Step 64188: {'lr': 0.0003120336809609144, 'samples': 12324096, 'steps': 64187, 'loss/train': 1.1038309335708618} 08/31/2021 00:51:07 - INFO - __main__ - Step 64189: {'lr': 0.0003120285401681913, 'samples': 12324288, 'steps': 64188, 'loss/train': 1.3784093856811523} 08/31/2021 00:51:08 - INFO - __main__ - Step 64190: {'lr': 0.0003120233993475191, 'samples': 12324480, 'steps': 64189, 'loss/train': 0.8671608567237854} 08/31/2021 00:51:08 - INFO - __main__ - Step 64191: {'lr': 0.00031201825849890013, 'samples': 12324672, 'steps': 64190, 'loss/train': 1.3762280941009521} 08/31/2021 00:51:09 - INFO - __main__ - Step 64192: {'lr': 0.00031201311762233666, 'samples': 12324864, 'steps': 64191, 'loss/train': 1.160988450050354} 08/31/2021 00:51:09 - INFO - __main__ - Step 64193: {'lr': 0.000312007976717831, 'samples': 12325056, 'steps': 64192, 'loss/train': 1.8885668516159058} 08/31/2021 00:51:11 - INFO - __main__ - Step 64194: {'lr': 0.0003120028357853856, 'samples': 12325248, 'steps': 64193, 'loss/train': 1.0413371324539185} 08/31/2021 00:51:11 - INFO - __main__ - Step 64195: {'lr': 0.0003119976948250026, 'samples': 12325440, 'steps': 64194, 'loss/train': 1.0470339059829712} 08/31/2021 00:51:12 - INFO - __main__ - Step 64196: {'lr': 0.0003119925538366844, 'samples': 12325632, 'steps': 64195, 'loss/train': 0.670385479927063} 08/31/2021 00:51:12 - INFO - __main__ - Step 64197: {'lr': 0.00031198741282043333, 'samples': 12325824, 'steps': 64196, 'loss/train': 1.214450716972351} 08/31/2021 00:51:12 - INFO - __main__ - Step 64198: {'lr': 0.0003119822717762517, 'samples': 12326016, 'steps': 64197, 'loss/train': 1.9341551065444946} 08/31/2021 00:51:13 - INFO - __main__ - Step 64199: {'lr': 0.0003119771307041418, 'samples': 12326208, 'steps': 64198, 'loss/train': 1.2104687690734863} 08/31/2021 00:51:14 - INFO - __main__ - Step 64200: {'lr': 0.000311971989604106, 'samples': 12326400, 'steps': 64199, 'loss/train': 1.267106294631958} 08/31/2021 00:51:15 - INFO - __main__ - Step 64201: {'lr': 0.00031196684847614655, 'samples': 12326592, 'steps': 64200, 'loss/train': 1.2527793645858765} 08/31/2021 00:51:15 - INFO - __main__ - Step 64202: {'lr': 0.00031196170732026576, 'samples': 12326784, 'steps': 64201, 'loss/train': 1.5968499183654785} 08/31/2021 00:51:15 - INFO - __main__ - Step 64203: {'lr': 0.00031195656613646595, 'samples': 12326976, 'steps': 64202, 'loss/train': 1.020721435546875} 08/31/2021 00:51:16 - INFO - __main__ - Step 64204: {'lr': 0.00031195142492474956, 'samples': 12327168, 'steps': 64203, 'loss/train': 1.667186975479126} 08/31/2021 00:51:17 - INFO - __main__ - Step 64205: {'lr': 0.00031194628368511876, 'samples': 12327360, 'steps': 64204, 'loss/train': 1.1292058229446411} 08/31/2021 00:51:18 - INFO - __main__ - Step 64206: {'lr': 0.00031194114241757593, 'samples': 12327552, 'steps': 64205, 'loss/train': 0.9764935970306396} 08/31/2021 00:51:18 - INFO - __main__ - Step 64207: {'lr': 0.0003119360011221234, 'samples': 12327744, 'steps': 64206, 'loss/train': 1.802575707435608} 08/31/2021 00:51:19 - INFO - __main__ - Step 64208: {'lr': 0.00031193085979876347, 'samples': 12327936, 'steps': 64207, 'loss/train': 1.30955970287323} 08/31/2021 00:51:19 - INFO - __main__ - Step 64209: {'lr': 0.0003119257184474984, 'samples': 12328128, 'steps': 64208, 'loss/train': 0.9428295493125916} 08/31/2021 00:51:19 - INFO - __main__ - Step 64210: {'lr': 0.00031192057706833055, 'samples': 12328320, 'steps': 64209, 'loss/train': 1.4350757598876953} 08/31/2021 00:51:21 - INFO - __main__ - Step 64211: {'lr': 0.0003119154356612623, 'samples': 12328512, 'steps': 64210, 'loss/train': 1.3819315433502197} 08/31/2021 00:51:21 - INFO - __main__ - Step 64212: {'lr': 0.0003119102942262959, 'samples': 12328704, 'steps': 64211, 'loss/train': 1.3821154832839966} 08/31/2021 00:51:22 - INFO - __main__ - Step 64213: {'lr': 0.0003119051527634336, 'samples': 12328896, 'steps': 64212, 'loss/train': 0.8569259643554688} 08/31/2021 00:51:22 - INFO - __main__ - Step 64214: {'lr': 0.00031190001127267793, 'samples': 12329088, 'steps': 64213, 'loss/train': 1.0300993919372559} 08/31/2021 00:51:22 - INFO - __main__ - Step 64215: {'lr': 0.00031189486975403096, 'samples': 12329280, 'steps': 64214, 'loss/train': 1.6036145687103271} 08/31/2021 00:51:24 - INFO - __main__ - Step 64216: {'lr': 0.00031188972820749515, 'samples': 12329472, 'steps': 64215, 'loss/train': 3.7139453887939453} 08/31/2021 00:51:25 - INFO - __main__ - Step 64217: {'lr': 0.0003118845866330728, 'samples': 12329664, 'steps': 64216, 'loss/train': 1.6324293613433838} 08/31/2021 00:51:25 - INFO - __main__ - Step 64218: {'lr': 0.0003118794450307662, 'samples': 12329856, 'steps': 64217, 'loss/train': 1.3492668867111206} 08/31/2021 00:51:25 - INFO - __main__ - Step 64219: {'lr': 0.0003118743034005776, 'samples': 12330048, 'steps': 64218, 'loss/train': 0.7863736152648926} 08/31/2021 00:51:26 - INFO - __main__ - Step 64220: {'lr': 0.0003118691617425095, 'samples': 12330240, 'steps': 64219, 'loss/train': 1.1689592599868774} 08/31/2021 00:51:26 - INFO - __main__ - Step 64221: {'lr': 0.0003118640200565641, 'samples': 12330432, 'steps': 64220, 'loss/train': 1.159845232963562} 08/31/2021 00:51:28 - INFO - __main__ - Step 64222: {'lr': 0.00031185887834274373, 'samples': 12330624, 'steps': 64221, 'loss/train': 1.0507069826126099} 08/31/2021 00:51:28 - INFO - __main__ - Step 64223: {'lr': 0.0003118537366010507, 'samples': 12330816, 'steps': 64222, 'loss/train': 1.2064560651779175} 08/31/2021 00:51:29 - INFO - __main__ - Step 64224: {'lr': 0.00031184859483148733, 'samples': 12331008, 'steps': 64223, 'loss/train': 1.8227331638336182} 08/31/2021 00:51:29 - INFO - __main__ - Step 64225: {'lr': 0.00031184345303405587, 'samples': 12331200, 'steps': 64224, 'loss/train': 1.1871699094772339} 08/31/2021 00:51:30 - INFO - __main__ - Step 64226: {'lr': 0.00031183831120875873, 'samples': 12331392, 'steps': 64225, 'loss/train': 1.1143523454666138} 08/31/2021 00:51:30 - INFO - __main__ - Step 64227: {'lr': 0.0003118331693555983, 'samples': 12331584, 'steps': 64226, 'loss/train': 0.05886506289243698} 08/31/2021 00:51:31 - INFO - __main__ - Step 64228: {'lr': 0.00031182802747457665, 'samples': 12331776, 'steps': 64227, 'loss/train': 0.0301472507417202} 08/31/2021 00:51:32 - INFO - __main__ - Step 64229: {'lr': 0.00031182288556569636, 'samples': 12331968, 'steps': 64228, 'loss/train': 1.2526320219039917} 08/31/2021 00:51:32 - INFO - __main__ - Step 64230: {'lr': 0.0003118177436289596, 'samples': 12332160, 'steps': 64229, 'loss/train': 1.4408401250839233} 08/31/2021 00:51:33 - INFO - __main__ - Step 64231: {'lr': 0.0003118126016643686, 'samples': 12332352, 'steps': 64230, 'loss/train': 1.2518800497055054} 08/31/2021 00:51:33 - INFO - __main__ - Step 64232: {'lr': 0.00031180745967192595, 'samples': 12332544, 'steps': 64231, 'loss/train': 1.5624364614486694} 08/31/2021 00:51:34 - INFO - __main__ - Step 64233: {'lr': 0.00031180231765163375, 'samples': 12332736, 'steps': 64232, 'loss/train': 0.9060717225074768} 08/31/2021 00:51:35 - INFO - __main__ - Step 64234: {'lr': 0.00031179717560349447, 'samples': 12332928, 'steps': 64233, 'loss/train': 1.4034630060195923} 08/31/2021 00:51:35 - INFO - __main__ - Step 64235: {'lr': 0.0003117920335275102, 'samples': 12333120, 'steps': 64234, 'loss/train': 0.6551645994186401} 08/31/2021 00:51:35 - INFO - __main__ - Step 64236: {'lr': 0.0003117868914236835, 'samples': 12333312, 'steps': 64235, 'loss/train': 1.4118750095367432} 08/31/2021 00:51:36 - INFO - __main__ - Step 64237: {'lr': 0.0003117817492920165, 'samples': 12333504, 'steps': 64236, 'loss/train': 1.9821518659591675} 08/31/2021 00:51:37 - INFO - __main__ - Step 64238: {'lr': 0.0003117766071325117, 'samples': 12333696, 'steps': 64237, 'loss/train': 1.6160112619400024} 08/31/2021 00:51:38 - INFO - __main__ - Step 64239: {'lr': 0.00031177146494517114, 'samples': 12333888, 'steps': 64238, 'loss/train': 1.4006712436676025} 08/31/2021 00:51:38 - INFO - __main__ - Step 64240: {'lr': 0.00031176632272999745, 'samples': 12334080, 'steps': 64239, 'loss/train': 0.9841848015785217} 08/31/2021 00:51:39 - INFO - __main__ - Step 64241: {'lr': 0.00031176118048699284, 'samples': 12334272, 'steps': 64240, 'loss/train': 1.613163948059082} 08/31/2021 00:51:39 - INFO - __main__ - Step 64242: {'lr': 0.0003117560382161595, 'samples': 12334464, 'steps': 64241, 'loss/train': 2.0120275020599365} 08/31/2021 00:51:41 - INFO - __main__ - Step 64243: {'lr': 0.0003117508959174998, 'samples': 12334656, 'steps': 64242, 'loss/train': 1.271628737449646} 08/31/2021 00:51:41 - INFO - __main__ - Step 64244: {'lr': 0.0003117457535910162, 'samples': 12334848, 'steps': 64243, 'loss/train': 1.7110226154327393} 08/31/2021 00:51:42 - INFO - __main__ - Step 64245: {'lr': 0.0003117406112367109, 'samples': 12335040, 'steps': 64244, 'loss/train': 1.4632779359817505} 08/31/2021 00:51:42 - INFO - __main__ - Step 64246: {'lr': 0.00031173546885458623, 'samples': 12335232, 'steps': 64245, 'loss/train': 0.981543779373169} 08/31/2021 00:51:42 - INFO - __main__ - Step 64247: {'lr': 0.00031173032644464456, 'samples': 12335424, 'steps': 64246, 'loss/train': 1.4007689952850342} 08/31/2021 00:51:43 - INFO - __main__ - Step 64248: {'lr': 0.000311725184006888, 'samples': 12335616, 'steps': 64247, 'loss/train': 0.6960827708244324} 08/31/2021 00:51:45 - INFO - __main__ - Step 64249: {'lr': 0.0003117200415413192, 'samples': 12335808, 'steps': 64248, 'loss/train': 0.035616833716630936} 08/31/2021 00:51:46 - INFO - __main__ - Step 64250: {'lr': 0.0003117148990479402, 'samples': 12336000, 'steps': 64249, 'loss/train': 1.4911463260650635} 08/31/2021 00:51:46 - INFO - __main__ - Step 64251: {'lr': 0.0003117097565267534, 'samples': 12336192, 'steps': 64250, 'loss/train': 1.9615874290466309} 08/31/2021 00:51:47 - INFO - __main__ - Step 64252: {'lr': 0.00031170461397776115, 'samples': 12336384, 'steps': 64251, 'loss/train': 0.08982541412115097} 08/31/2021 00:51:47 - INFO - __main__ - Step 64253: {'lr': 0.0003116994714009658, 'samples': 12336576, 'steps': 64252, 'loss/train': 1.2592723369598389} 08/31/2021 00:51:47 - INFO - __main__ - Step 64254: {'lr': 0.0003116943287963697, 'samples': 12336768, 'steps': 64253, 'loss/train': 2.901502847671509} 08/31/2021 00:51:49 - INFO - __main__ - Step 64255: {'lr': 0.00031168918616397495, 'samples': 12336960, 'steps': 64254, 'loss/train': 0.1137923151254654} 08/31/2021 00:51:49 - INFO - __main__ - Step 64256: {'lr': 0.000311684043503784, 'samples': 12337152, 'steps': 64255, 'loss/train': 1.7420666217803955} 08/31/2021 00:51:50 - INFO - __main__ - Step 64257: {'lr': 0.00031167890081579925, 'samples': 12337344, 'steps': 64256, 'loss/train': 1.1198477745056152} 08/31/2021 00:51:50 - INFO - __main__ - Step 64258: {'lr': 0.0003116737581000229, 'samples': 12337536, 'steps': 64257, 'loss/train': 1.6105211973190308} 08/31/2021 00:51:50 - INFO - __main__ - Step 64259: {'lr': 0.0003116686153564573, 'samples': 12337728, 'steps': 64258, 'loss/train': 1.2278496026992798} 08/31/2021 00:51:51 - INFO - __main__ - Step 64260: {'lr': 0.0003116634725851048, 'samples': 12337920, 'steps': 64259, 'loss/train': 1.4466543197631836} 08/31/2021 00:51:52 - INFO - __main__ - Step 64261: {'lr': 0.0003116583297859677, 'samples': 12338112, 'steps': 64260, 'loss/train': 1.512083888053894} 08/31/2021 00:51:53 - INFO - __main__ - Step 64262: {'lr': 0.00031165318695904824, 'samples': 12338304, 'steps': 64261, 'loss/train': 1.8980348110198975} 08/31/2021 00:51:53 - INFO - __main__ - Step 64263: {'lr': 0.0003116480441043489, 'samples': 12338496, 'steps': 64262, 'loss/train': 1.5874969959259033} 08/31/2021 00:51:53 - INFO - __main__ - Step 64264: {'lr': 0.0003116429012218718, 'samples': 12338688, 'steps': 64263, 'loss/train': 0.29954448342323303} 08/31/2021 00:51:54 - INFO - __main__ - Step 64265: {'lr': 0.00031163775831161947, 'samples': 12338880, 'steps': 64264, 'loss/train': 0.11218065768480301} 08/31/2021 00:51:55 - INFO - __main__ - Step 64266: {'lr': 0.00031163261537359404, 'samples': 12339072, 'steps': 64265, 'loss/train': 1.509054183959961} 08/31/2021 00:51:56 - INFO - __main__ - Step 64267: {'lr': 0.0003116274724077979, 'samples': 12339264, 'steps': 64266, 'loss/train': 1.5785120725631714} 08/31/2021 00:51:56 - INFO - __main__ - Step 64268: {'lr': 0.0003116223294142334, 'samples': 12339456, 'steps': 64267, 'loss/train': 1.9143500328063965} 08/31/2021 00:51:57 - INFO - __main__ - Step 64269: {'lr': 0.00031161718639290283, 'samples': 12339648, 'steps': 64268, 'loss/train': 3.2849771976470947} 08/31/2021 00:51:57 - INFO - __main__ - Step 64270: {'lr': 0.0003116120433438085, 'samples': 12339840, 'steps': 64269, 'loss/train': 1.2641470432281494} 08/31/2021 00:51:59 - INFO - __main__ - Step 64271: {'lr': 0.00031160690026695275, 'samples': 12340032, 'steps': 64270, 'loss/train': 1.1145833730697632} 08/31/2021 00:51:59 - INFO - __main__ - Step 64272: {'lr': 0.00031160175716233793, 'samples': 12340224, 'steps': 64271, 'loss/train': 0.03322940319776535} 08/31/2021 00:52:00 - INFO - __main__ - Step 64273: {'lr': 0.00031159661402996617, 'samples': 12340416, 'steps': 64272, 'loss/train': 0.690254271030426} 08/31/2021 00:52:00 - INFO - __main__ - Step 64274: {'lr': 0.00031159147086984003, 'samples': 12340608, 'steps': 64273, 'loss/train': 2.0099289417266846} 08/31/2021 00:52:00 - INFO - __main__ - Step 64275: {'lr': 0.0003115863276819617, 'samples': 12340800, 'steps': 64274, 'loss/train': 1.3331416845321655} 08/31/2021 00:52:01 - INFO - __main__ - Step 64276: {'lr': 0.00031158118446633355, 'samples': 12340992, 'steps': 64275, 'loss/train': 1.701292634010315} 08/31/2021 00:52:02 - INFO - __main__ - Step 64277: {'lr': 0.0003115760412229578, 'samples': 12341184, 'steps': 64276, 'loss/train': 1.6765615940093994} 08/31/2021 00:52:03 - INFO - __main__ - Step 64278: {'lr': 0.0003115708979518369, 'samples': 12341376, 'steps': 64277, 'loss/train': 0.9765510559082031} 08/31/2021 00:52:03 - INFO - __main__ - Step 64279: {'lr': 0.00031156575465297306, 'samples': 12341568, 'steps': 64278, 'loss/train': 1.1569929122924805} 08/31/2021 00:52:04 - INFO - __main__ - Step 64280: {'lr': 0.00031156061132636866, 'samples': 12341760, 'steps': 64279, 'loss/train': 1.3496003150939941} 08/31/2021 00:52:04 - INFO - __main__ - Step 64281: {'lr': 0.00031155546797202597, 'samples': 12341952, 'steps': 64280, 'loss/train': 1.1894335746765137} 08/31/2021 00:52:05 - INFO - __main__ - Step 64282: {'lr': 0.0003115503245899474, 'samples': 12342144, 'steps': 64281, 'loss/train': 2.051201105117798} 08/31/2021 00:52:06 - INFO - __main__ - Step 64283: {'lr': 0.0003115451811801351, 'samples': 12342336, 'steps': 64282, 'loss/train': 1.0940444469451904} 08/31/2021 00:52:06 - INFO - __main__ - Step 64284: {'lr': 0.0003115400377425916, 'samples': 12342528, 'steps': 64283, 'loss/train': 1.1227725744247437} 08/31/2021 00:52:07 - INFO - __main__ - Step 64285: {'lr': 0.00031153489427731906, 'samples': 12342720, 'steps': 64284, 'loss/train': 1.3275303840637207} 08/31/2021 00:52:07 - INFO - __main__ - Step 64286: {'lr': 0.0003115297507843198, 'samples': 12342912, 'steps': 64285, 'loss/train': 1.6717911958694458} 08/31/2021 00:52:07 - INFO - __main__ - Step 64287: {'lr': 0.00031152460726359627, 'samples': 12343104, 'steps': 64286, 'loss/train': 1.412594199180603} 08/31/2021 00:52:09 - INFO - __main__ - Step 64288: {'lr': 0.0003115194637151507, 'samples': 12343296, 'steps': 64287, 'loss/train': 0.15093281865119934} 08/31/2021 00:52:09 - INFO - __main__ - Step 64289: {'lr': 0.00031151432013898535, 'samples': 12343488, 'steps': 64288, 'loss/train': 0.8789308071136475} 08/31/2021 00:52:10 - INFO - __main__ - Step 64290: {'lr': 0.00031150917653510263, 'samples': 12343680, 'steps': 64289, 'loss/train': 0.605863094329834} 08/31/2021 00:52:10 - INFO - __main__ - Step 64291: {'lr': 0.00031150403290350484, 'samples': 12343872, 'steps': 64290, 'loss/train': 1.0887303352355957} 08/31/2021 00:52:11 - INFO - __main__ - Step 64292: {'lr': 0.00031149888924419424, 'samples': 12344064, 'steps': 64291, 'loss/train': 1.4003632068634033} 08/31/2021 00:52:12 - INFO - __main__ - Step 64293: {'lr': 0.00031149374555717316, 'samples': 12344256, 'steps': 64292, 'loss/train': 0.9335001111030579} 08/31/2021 00:52:13 - INFO - __main__ - Step 64294: {'lr': 0.00031148860184244406, 'samples': 12344448, 'steps': 64293, 'loss/train': 1.399565577507019} 08/31/2021 00:52:13 - INFO - __main__ - Step 64295: {'lr': 0.00031148345810000903, 'samples': 12344640, 'steps': 64294, 'loss/train': 1.7657095193862915} 08/31/2021 00:52:13 - INFO - __main__ - Step 64296: {'lr': 0.0003114783143298706, 'samples': 12344832, 'steps': 64295, 'loss/train': 1.445308804512024} 08/31/2021 00:52:14 - INFO - __main__ - Step 64297: {'lr': 0.00031147317053203087, 'samples': 12345024, 'steps': 64296, 'loss/train': 1.2329559326171875} 08/31/2021 00:52:15 - INFO - __main__ - Step 64298: {'lr': 0.0003114680267064924, 'samples': 12345216, 'steps': 64297, 'loss/train': 1.4427212476730347} 08/31/2021 00:52:15 - INFO - __main__ - Step 64299: {'lr': 0.0003114628828532573, 'samples': 12345408, 'steps': 64298, 'loss/train': 1.114481806755066} 08/31/2021 00:52:16 - INFO - __main__ - Step 64300: {'lr': 0.000311457738972328, 'samples': 12345600, 'steps': 64299, 'loss/train': 1.1776771545410156} 08/31/2021 00:52:16 - INFO - __main__ - Step 64301: {'lr': 0.00031145259506370685, 'samples': 12345792, 'steps': 64300, 'loss/train': 0.31247463822364807} 08/31/2021 00:52:17 - INFO - __main__ - Step 64302: {'lr': 0.00031144745112739603, 'samples': 12345984, 'steps': 64301, 'loss/train': 1.7641491889953613} 08/31/2021 00:52:18 - INFO - __main__ - Step 64303: {'lr': 0.00031144230716339795, 'samples': 12346176, 'steps': 64302, 'loss/train': 1.0636812448501587} 08/31/2021 00:52:19 - INFO - __main__ - Step 64304: {'lr': 0.00031143716317171493, 'samples': 12346368, 'steps': 64303, 'loss/train': 1.141300082206726} 08/31/2021 00:52:19 - INFO - __main__ - Step 64305: {'lr': 0.00031143201915234924, 'samples': 12346560, 'steps': 64304, 'loss/train': 1.2187222242355347} 08/31/2021 00:52:20 - INFO - __main__ - Step 64306: {'lr': 0.0003114268751053033, 'samples': 12346752, 'steps': 64305, 'loss/train': 1.4263237714767456} 08/31/2021 00:52:20 - INFO - __main__ - Step 64307: {'lr': 0.0003114217310305793, 'samples': 12346944, 'steps': 64306, 'loss/train': 1.2374298572540283} 08/31/2021 00:52:20 - INFO - __main__ - Step 64308: {'lr': 0.00031141658692817963, 'samples': 12347136, 'steps': 64307, 'loss/train': 1.230875849723816} 08/31/2021 00:52:22 - INFO - __main__ - Step 64309: {'lr': 0.0003114114427981066, 'samples': 12347328, 'steps': 64308, 'loss/train': 1.384247899055481} 08/31/2021 00:52:22 - INFO - __main__ - Step 64310: {'lr': 0.0003114062986403625, 'samples': 12347520, 'steps': 64309, 'loss/train': 1.3064405918121338} 08/31/2021 00:52:23 - INFO - __main__ - Step 64311: {'lr': 0.0003114011544549497, 'samples': 12347712, 'steps': 64310, 'loss/train': 1.1341102123260498} 08/31/2021 00:52:23 - INFO - __main__ - Step 64312: {'lr': 0.0003113960102418705, 'samples': 12347904, 'steps': 64311, 'loss/train': 1.2469216585159302} 08/31/2021 00:52:23 - INFO - __main__ - Step 64313: {'lr': 0.00031139086600112713, 'samples': 12348096, 'steps': 64312, 'loss/train': 1.6973850727081299} 08/31/2021 00:52:25 - INFO - __main__ - Step 64314: {'lr': 0.00031138572173272205, 'samples': 12348288, 'steps': 64313, 'loss/train': 1.5589790344238281} 08/31/2021 00:52:25 - INFO - __main__ - Step 64315: {'lr': 0.00031138057743665756, 'samples': 12348480, 'steps': 64314, 'loss/train': 1.267185926437378} 08/31/2021 00:52:26 - INFO - __main__ - Step 64316: {'lr': 0.0003113754331129359, 'samples': 12348672, 'steps': 64315, 'loss/train': 1.6633188724517822} 08/31/2021 00:52:26 - INFO - __main__ - Step 64317: {'lr': 0.0003113702887615593, 'samples': 12348864, 'steps': 64316, 'loss/train': 0.30427056550979614} 08/31/2021 00:52:26 - INFO - __main__ - Step 64318: {'lr': 0.00031136514438253026, 'samples': 12349056, 'steps': 64317, 'loss/train': 0.8114305734634399} 08/31/2021 00:52:28 - INFO - __main__ - Step 64319: {'lr': 0.0003113599999758511, 'samples': 12349248, 'steps': 64318, 'loss/train': 1.2477232217788696} 08/31/2021 00:52:28 - INFO - __main__ - Step 64320: {'lr': 0.000311354855541524, 'samples': 12349440, 'steps': 64319, 'loss/train': 1.3580585718154907} 08/31/2021 00:52:28 - INFO - __main__ - Step 64321: {'lr': 0.0003113497110795514, 'samples': 12349632, 'steps': 64320, 'loss/train': 1.6661816835403442} 08/31/2021 00:52:29 - INFO - __main__ - Step 64322: {'lr': 0.0003113445665899355, 'samples': 12349824, 'steps': 64321, 'loss/train': 1.413511872291565} 08/31/2021 00:52:29 - INFO - __main__ - Step 64323: {'lr': 0.0003113394220726787, 'samples': 12350016, 'steps': 64322, 'loss/train': 0.9739340543746948} 08/31/2021 00:52:31 - INFO - __main__ - Step 64324: {'lr': 0.0003113342775277834, 'samples': 12350208, 'steps': 64323, 'loss/train': 0.4981843829154968} 08/31/2021 00:52:31 - INFO - __main__ - Step 64325: {'lr': 0.0003113291329552517, 'samples': 12350400, 'steps': 64324, 'loss/train': 1.6921849250793457} 08/31/2021 00:52:31 - INFO - __main__ - Step 64326: {'lr': 0.00031132398835508605, 'samples': 12350592, 'steps': 64325, 'loss/train': 1.3427785634994507} 08/31/2021 00:52:32 - INFO - __main__ - Step 64327: {'lr': 0.0003113188437272888, 'samples': 12350784, 'steps': 64326, 'loss/train': 1.2221927642822266} 08/31/2021 00:52:32 - INFO - __main__ - Step 64328: {'lr': 0.00031131369907186227, 'samples': 12350976, 'steps': 64327, 'loss/train': 1.1614477634429932} 08/31/2021 00:52:34 - INFO - __main__ - Step 64329: {'lr': 0.00031130855438880867, 'samples': 12351168, 'steps': 64328, 'loss/train': 1.7844197750091553} 08/31/2021 00:52:34 - INFO - __main__ - Step 64330: {'lr': 0.00031130340967813037, 'samples': 12351360, 'steps': 64329, 'loss/train': 1.2556015253067017} 08/31/2021 00:52:35 - INFO - __main__ - Step 64331: {'lr': 0.00031129826493982973, 'samples': 12351552, 'steps': 64330, 'loss/train': 1.4446145296096802} 08/31/2021 00:52:35 - INFO - __main__ - Step 64332: {'lr': 0.000311293120173909, 'samples': 12351744, 'steps': 64331, 'loss/train': 1.6638087034225464} 08/31/2021 00:52:35 - INFO - __main__ - Step 64333: {'lr': 0.0003112879753803706, 'samples': 12351936, 'steps': 64332, 'loss/train': 1.5919402837753296} 08/31/2021 00:52:37 - INFO - __main__ - Step 64334: {'lr': 0.0003112828305592167, 'samples': 12352128, 'steps': 64333, 'loss/train': 1.5899487733840942} 08/31/2021 00:52:37 - INFO - __main__ - Step 64335: {'lr': 0.0003112776857104498, 'samples': 12352320, 'steps': 64334, 'loss/train': 0.7548910975456238} 08/31/2021 00:52:37 - INFO - __main__ - Step 64336: {'lr': 0.0003112725408340721, 'samples': 12352512, 'steps': 64335, 'loss/train': 1.7062654495239258} 08/31/2021 00:52:38 - INFO - __main__ - Step 64337: {'lr': 0.00031126739593008586, 'samples': 12352704, 'steps': 64336, 'loss/train': 0.8547391295433044} 08/31/2021 00:52:38 - INFO - __main__ - Step 64338: {'lr': 0.00031126225099849356, 'samples': 12352896, 'steps': 64337, 'loss/train': 1.2791417837142944} 08/31/2021 00:52:40 - INFO - __main__ - Step 64339: {'lr': 0.00031125710603929736, 'samples': 12353088, 'steps': 64338, 'loss/train': 1.0063766241073608} 08/31/2021 00:52:40 - INFO - __main__ - Step 64340: {'lr': 0.0003112519610524997, 'samples': 12353280, 'steps': 64339, 'loss/train': 1.3608454465866089} 08/31/2021 00:52:40 - INFO - __main__ - Step 64341: {'lr': 0.00031124681603810286, 'samples': 12353472, 'steps': 64340, 'loss/train': 1.133014440536499} 08/31/2021 00:52:41 - INFO - __main__ - Step 64342: {'lr': 0.0003112416709961092, 'samples': 12353664, 'steps': 64341, 'loss/train': 1.1978564262390137} 08/31/2021 00:52:41 - INFO - __main__ - Step 64343: {'lr': 0.00031123652592652087, 'samples': 12353856, 'steps': 64342, 'loss/train': 1.1534173488616943} 08/31/2021 00:52:42 - INFO - __main__ - Step 64344: {'lr': 0.0003112313808293403, 'samples': 12354048, 'steps': 64343, 'loss/train': 1.5648785829544067} 08/31/2021 00:52:43 - INFO - __main__ - Step 64345: {'lr': 0.0003112262357045699, 'samples': 12354240, 'steps': 64344, 'loss/train': 1.1626980304718018} 08/31/2021 00:52:43 - INFO - __main__ - Step 64346: {'lr': 0.00031122109055221187, 'samples': 12354432, 'steps': 64345, 'loss/train': 1.4973117113113403} 08/31/2021 00:52:44 - INFO - __main__ - Step 64347: {'lr': 0.0003112159453722686, 'samples': 12354624, 'steps': 64346, 'loss/train': 1.6399517059326172} 08/31/2021 00:52:44 - INFO - __main__ - Step 64348: {'lr': 0.0003112108001647423, 'samples': 12354816, 'steps': 64347, 'loss/train': 0.8514527082443237} 08/31/2021 00:52:44 - INFO - __main__ - Step 64349: {'lr': 0.0003112056549296354, 'samples': 12355008, 'steps': 64348, 'loss/train': 1.470271348953247} 08/31/2021 00:52:46 - INFO - __main__ - Step 64350: {'lr': 0.0003112005096669502, 'samples': 12355200, 'steps': 64349, 'loss/train': 1.1317318677902222} 08/31/2021 00:52:46 - INFO - __main__ - Step 64351: {'lr': 0.000311195364376689, 'samples': 12355392, 'steps': 64350, 'loss/train': 0.911060631275177} 08/31/2021 00:52:47 - INFO - __main__ - Step 64352: {'lr': 0.00031119021905885404, 'samples': 12355584, 'steps': 64351, 'loss/train': 1.0902596712112427} 08/31/2021 00:52:47 - INFO - __main__ - Step 64353: {'lr': 0.00031118507371344774, 'samples': 12355776, 'steps': 64352, 'loss/train': 1.1717926263809204} 08/31/2021 00:52:47 - INFO - __main__ - Step 64354: {'lr': 0.00031117992834047244, 'samples': 12355968, 'steps': 64353, 'loss/train': 0.9178889393806458} 08/31/2021 00:52:49 - INFO - __main__ - Step 64355: {'lr': 0.0003111747829399304, 'samples': 12356160, 'steps': 64354, 'loss/train': 1.6254686117172241} 08/31/2021 00:52:49 - INFO - __main__ - Step 64356: {'lr': 0.0003111696375118239, 'samples': 12356352, 'steps': 64355, 'loss/train': 1.332759141921997} 08/31/2021 00:52:50 - INFO - __main__ - Step 64357: {'lr': 0.0003111644920561553, 'samples': 12356544, 'steps': 64356, 'loss/train': 0.1097482293844223} 08/31/2021 00:52:50 - INFO - __main__ - Step 64358: {'lr': 0.0003111593465729269, 'samples': 12356736, 'steps': 64357, 'loss/train': 0.7775449156761169} 08/31/2021 00:52:50 - INFO - __main__ - Step 64359: {'lr': 0.0003111542010621411, 'samples': 12356928, 'steps': 64358, 'loss/train': 1.3839489221572876} 08/31/2021 00:52:52 - INFO - __main__ - Step 64360: {'lr': 0.00031114905552380017, 'samples': 12357120, 'steps': 64359, 'loss/train': 1.679286241531372} 08/31/2021 00:52:53 - INFO - __main__ - Step 64361: {'lr': 0.0003111439099579064, 'samples': 12357312, 'steps': 64360, 'loss/train': 0.1530126929283142} 08/31/2021 00:52:53 - INFO - __main__ - Step 64362: {'lr': 0.00031113876436446216, 'samples': 12357504, 'steps': 64361, 'loss/train': 1.0033071041107178} 08/31/2021 00:52:53 - INFO - __main__ - Step 64363: {'lr': 0.00031113361874346966, 'samples': 12357696, 'steps': 64362, 'loss/train': 1.0005766153335571} 08/31/2021 00:52:54 - INFO - __main__ - Step 64364: {'lr': 0.0003111284730949314, 'samples': 12357888, 'steps': 64363, 'loss/train': 1.2684156894683838} 08/31/2021 00:52:55 - INFO - __main__ - Step 64365: {'lr': 0.0003111233274188495, 'samples': 12358080, 'steps': 64364, 'loss/train': 1.045289158821106} 08/31/2021 00:52:56 - INFO - __main__ - Step 64366: {'lr': 0.0003111181817152264, 'samples': 12358272, 'steps': 64365, 'loss/train': 1.6826990842819214} 08/31/2021 00:52:56 - INFO - __main__ - Step 64367: {'lr': 0.0003111130359840644, 'samples': 12358464, 'steps': 64366, 'loss/train': 0.8894611597061157} 08/31/2021 00:52:56 - INFO - __main__ - Step 64368: {'lr': 0.0003111078902253658, 'samples': 12358656, 'steps': 64367, 'loss/train': 1.2879279851913452} 08/31/2021 00:52:57 - INFO - __main__ - Step 64369: {'lr': 0.00031110274443913295, 'samples': 12358848, 'steps': 64368, 'loss/train': 1.250032901763916} 08/31/2021 00:52:58 - INFO - __main__ - Step 64370: {'lr': 0.0003110975986253681, 'samples': 12359040, 'steps': 64369, 'loss/train': 0.9117981195449829} 08/31/2021 00:52:59 - INFO - __main__ - Step 64371: {'lr': 0.0003110924527840736, 'samples': 12359232, 'steps': 64370, 'loss/train': 1.6192163228988647} 08/31/2021 00:52:59 - INFO - __main__ - Step 64372: {'lr': 0.0003110873069152518, 'samples': 12359424, 'steps': 64371, 'loss/train': 1.5611847639083862} 08/31/2021 00:53:00 - INFO - __main__ - Step 64373: {'lr': 0.0003110821610189051, 'samples': 12359616, 'steps': 64372, 'loss/train': 0.9285088181495667} 08/31/2021 00:53:00 - INFO - __main__ - Step 64374: {'lr': 0.0003110770150950356, 'samples': 12359808, 'steps': 64373, 'loss/train': 0.916355550289154} 08/31/2021 00:53:00 - INFO - __main__ - Step 64375: {'lr': 0.00031107186914364584, 'samples': 12360000, 'steps': 64374, 'loss/train': 1.3335349559783936} 08/31/2021 00:53:02 - INFO - __main__ - Step 64376: {'lr': 0.000311066723164738, 'samples': 12360192, 'steps': 64375, 'loss/train': 1.4482388496398926} 08/31/2021 00:53:02 - INFO - __main__ - Step 64377: {'lr': 0.0003110615771583144, 'samples': 12360384, 'steps': 64376, 'loss/train': 0.6691508889198303} 08/31/2021 00:53:03 - INFO - __main__ - Step 64378: {'lr': 0.00031105643112437745, 'samples': 12360576, 'steps': 64377, 'loss/train': 1.3960468769073486} 08/31/2021 00:53:03 - INFO - __main__ - Step 64379: {'lr': 0.00031105128506292933, 'samples': 12360768, 'steps': 64378, 'loss/train': 1.484409213066101} 08/31/2021 00:53:03 - INFO - __main__ - Step 64380: {'lr': 0.0003110461389739725, 'samples': 12360960, 'steps': 64379, 'loss/train': 0.8951881527900696} 08/31/2021 00:53:05 - INFO - __main__ - Step 64381: {'lr': 0.0003110409928575092, 'samples': 12361152, 'steps': 64380, 'loss/train': 2.0616815090179443} 08/31/2021 00:53:06 - INFO - __main__ - Step 64382: {'lr': 0.0003110358467135418, 'samples': 12361344, 'steps': 64381, 'loss/train': 1.2812042236328125} 08/31/2021 00:53:06 - INFO - __main__ - Step 64383: {'lr': 0.0003110307005420726, 'samples': 12361536, 'steps': 64382, 'loss/train': 1.2061688899993896} 08/31/2021 00:53:07 - INFO - __main__ - Step 64384: {'lr': 0.00031102555434310385, 'samples': 12361728, 'steps': 64383, 'loss/train': 1.6864597797393799} 08/31/2021 00:53:07 - INFO - __main__ - Step 64385: {'lr': 0.00031102040811663794, 'samples': 12361920, 'steps': 64384, 'loss/train': 1.230747938156128} 08/31/2021 00:53:07 - INFO - __main__ - Step 64386: {'lr': 0.0003110152618626772, 'samples': 12362112, 'steps': 64385, 'loss/train': 0.7954106330871582} 08/31/2021 00:53:09 - INFO - __main__ - Step 64387: {'lr': 0.0003110101155812239, 'samples': 12362304, 'steps': 64386, 'loss/train': 1.2508032321929932} 08/31/2021 00:53:09 - INFO - __main__ - Step 64388: {'lr': 0.00031100496927228047, 'samples': 12362496, 'steps': 64387, 'loss/train': 1.9185311794281006} 08/31/2021 00:53:10 - INFO - __main__ - Step 64389: {'lr': 0.00031099982293584903, 'samples': 12362688, 'steps': 64388, 'loss/train': 1.4245555400848389} 08/31/2021 00:53:10 - INFO - __main__ - Step 64390: {'lr': 0.0003109946765719321, 'samples': 12362880, 'steps': 64389, 'loss/train': 1.2787381410598755} 08/31/2021 00:53:10 - INFO - __main__ - Step 64391: {'lr': 0.00031098953018053187, 'samples': 12363072, 'steps': 64390, 'loss/train': 1.4095525741577148} 08/31/2021 00:53:12 - INFO - __main__ - Step 64392: {'lr': 0.00031098438376165065, 'samples': 12363264, 'steps': 64391, 'loss/train': 1.2832757234573364} 08/31/2021 00:53:12 - INFO - __main__ - Step 64393: {'lr': 0.00031097923731529086, 'samples': 12363456, 'steps': 64392, 'loss/train': 2.3036868572235107} 08/31/2021 00:53:13 - INFO - __main__ - Step 64394: {'lr': 0.0003109740908414548, 'samples': 12363648, 'steps': 64393, 'loss/train': 1.3640021085739136} 08/31/2021 00:53:13 - INFO - __main__ - Step 64395: {'lr': 0.0003109689443401447, 'samples': 12363840, 'steps': 64394, 'loss/train': 0.058469660580158234} 08/31/2021 00:53:13 - INFO - __main__ - Step 64396: {'lr': 0.00031096379781136296, 'samples': 12364032, 'steps': 64395, 'loss/train': 0.994904637336731} 08/31/2021 00:53:15 - INFO - __main__ - Step 64397: {'lr': 0.00031095865125511186, 'samples': 12364224, 'steps': 64396, 'loss/train': 1.204929232597351} 08/31/2021 00:53:16 - INFO - __main__ - Step 64398: {'lr': 0.0003109535046713937, 'samples': 12364416, 'steps': 64397, 'loss/train': 1.4004254341125488} 08/31/2021 00:53:16 - INFO - __main__ - Step 64399: {'lr': 0.0003109483580602109, 'samples': 12364608, 'steps': 64398, 'loss/train': 0.6855939626693726} 08/31/2021 00:53:16 - INFO - __main__ - Step 64400: {'lr': 0.00031094321142156574, 'samples': 12364800, 'steps': 64399, 'loss/train': 1.1830424070358276} 08/31/2021 00:53:17 - INFO - __main__ - Step 64401: {'lr': 0.00031093806475546046, 'samples': 12364992, 'steps': 64400, 'loss/train': 1.0950363874435425} 08/31/2021 00:53:18 - INFO - __main__ - Step 64402: {'lr': 0.0003109329180618974, 'samples': 12365184, 'steps': 64401, 'loss/train': 1.1684226989746094} 08/31/2021 00:53:19 - INFO - __main__ - Step 64403: {'lr': 0.00031092777134087893, 'samples': 12365376, 'steps': 64402, 'loss/train': 0.33734604716300964} 08/31/2021 00:53:19 - INFO - __main__ - Step 64404: {'lr': 0.0003109226245924073, 'samples': 12365568, 'steps': 64403, 'loss/train': 1.2967945337295532} 08/31/2021 00:53:20 - INFO - __main__ - Step 64405: {'lr': 0.00031091747781648496, 'samples': 12365760, 'steps': 64404, 'loss/train': 1.196881890296936} 08/31/2021 00:53:20 - INFO - __main__ - Step 64406: {'lr': 0.00031091233101311405, 'samples': 12365952, 'steps': 64405, 'loss/train': 0.9121683239936829} 08/31/2021 00:53:20 - INFO - __main__ - Step 64407: {'lr': 0.0003109071841822971, 'samples': 12366144, 'steps': 64406, 'loss/train': 0.06044892221689224} 08/31/2021 00:53:22 - INFO - __main__ - Step 64408: {'lr': 0.0003109020373240362, 'samples': 12366336, 'steps': 64407, 'loss/train': 1.135819911956787} 08/31/2021 00:53:23 - INFO - __main__ - Step 64409: {'lr': 0.0003108968904383338, 'samples': 12366528, 'steps': 64408, 'loss/train': 1.6106634140014648} 08/31/2021 00:53:23 - INFO - __main__ - Step 64410: {'lr': 0.00031089174352519225, 'samples': 12366720, 'steps': 64409, 'loss/train': 1.3851321935653687} 08/31/2021 00:53:24 - INFO - __main__ - Step 64411: {'lr': 0.0003108865965846138, 'samples': 12366912, 'steps': 64410, 'loss/train': 1.0528379678726196} 08/31/2021 00:53:24 - INFO - __main__ - Step 64412: {'lr': 0.00031088144961660083, 'samples': 12367104, 'steps': 64411, 'loss/train': 1.7474493980407715} 08/31/2021 00:53:26 - INFO - __main__ - Step 64413: {'lr': 0.00031087630262115553, 'samples': 12367296, 'steps': 64412, 'loss/train': 1.323412537574768} 08/31/2021 00:53:26 - INFO - __main__ - Step 64414: {'lr': 0.0003108711555982804, 'samples': 12367488, 'steps': 64413, 'loss/train': 0.7545371651649475} 08/31/2021 00:53:26 - INFO - __main__ - Step 64415: {'lr': 0.00031086600854797757, 'samples': 12367680, 'steps': 64414, 'loss/train': 1.43510901927948} 08/31/2021 00:53:27 - INFO - __main__ - Step 64416: {'lr': 0.00031086086147024956, 'samples': 12367872, 'steps': 64415, 'loss/train': 1.3941618204116821} 08/31/2021 00:53:27 - INFO - __main__ - Step 64417: {'lr': 0.0003108557143650985, 'samples': 12368064, 'steps': 64416, 'loss/train': 1.3352223634719849} 08/31/2021 00:53:29 - INFO - __main__ - Step 64418: {'lr': 0.00031085056723252684, 'samples': 12368256, 'steps': 64417, 'loss/train': 1.1170685291290283} 08/31/2021 00:53:29 - INFO - __main__ - Step 64419: {'lr': 0.0003108454200725368, 'samples': 12368448, 'steps': 64418, 'loss/train': 1.1178709268569946} 08/31/2021 00:53:29 - INFO - __main__ - Step 64420: {'lr': 0.00031084027288513083, 'samples': 12368640, 'steps': 64419, 'loss/train': 1.3199374675750732} 08/31/2021 00:53:30 - INFO - __main__ - Step 64421: {'lr': 0.0003108351256703111, 'samples': 12368832, 'steps': 64420, 'loss/train': 1.0380382537841797} 08/31/2021 00:53:30 - INFO - __main__ - Step 64422: {'lr': 0.0003108299784280801, 'samples': 12369024, 'steps': 64421, 'loss/train': 1.431196928024292} 08/31/2021 00:53:31 - INFO - __main__ - Step 64423: {'lr': 0.00031082483115843994, 'samples': 12369216, 'steps': 64422, 'loss/train': 0.10302615165710449} 08/31/2021 00:53:32 - INFO - __main__ - Step 64424: {'lr': 0.00031081968386139307, 'samples': 12369408, 'steps': 64423, 'loss/train': 1.3002821207046509} 08/31/2021 00:53:33 - INFO - __main__ - Step 64425: {'lr': 0.00031081453653694185, 'samples': 12369600, 'steps': 64424, 'loss/train': 1.8296788930892944} 08/31/2021 00:53:33 - INFO - __main__ - Step 64426: {'lr': 0.0003108093891850885, 'samples': 12369792, 'steps': 64425, 'loss/train': 1.6775665283203125} 08/31/2021 00:53:33 - INFO - __main__ - Step 64427: {'lr': 0.0003108042418058353, 'samples': 12369984, 'steps': 64426, 'loss/train': 1.4417933225631714} 08/31/2021 00:53:34 - INFO - __main__ - Step 64428: {'lr': 0.00031079909439918476, 'samples': 12370176, 'steps': 64427, 'loss/train': 1.1143354177474976} 08/31/2021 00:53:35 - INFO - __main__ - Step 64429: {'lr': 0.00031079394696513913, 'samples': 12370368, 'steps': 64428, 'loss/train': 1.17087721824646} 08/31/2021 00:53:36 - INFO - __main__ - Step 64430: {'lr': 0.0003107887995037006, 'samples': 12370560, 'steps': 64429, 'loss/train': 0.9099040627479553} 08/31/2021 00:53:36 - INFO - __main__ - Step 64431: {'lr': 0.0003107836520148716, 'samples': 12370752, 'steps': 64430, 'loss/train': 1.7362757921218872} 08/31/2021 00:53:37 - INFO - __main__ - Step 64432: {'lr': 0.00031077850449865433, 'samples': 12370944, 'steps': 64431, 'loss/train': 1.8134654760360718} 08/31/2021 00:53:37 - INFO - __main__ - Step 64433: {'lr': 0.00031077335695505127, 'samples': 12371136, 'steps': 64432, 'loss/train': 1.8111536502838135} 08/31/2021 00:53:37 - INFO - __main__ - Step 64434: {'lr': 0.00031076820938406467, 'samples': 12371328, 'steps': 64433, 'loss/train': 0.6133899688720703} 08/31/2021 00:53:39 - INFO - __main__ - Step 64435: {'lr': 0.0003107630617856969, 'samples': 12371520, 'steps': 64434, 'loss/train': 1.0774977207183838} 08/31/2021 00:53:40 - INFO - __main__ - Step 64436: {'lr': 0.00031075791415995026, 'samples': 12371712, 'steps': 64435, 'loss/train': 0.05568802356719971} 08/31/2021 00:53:40 - INFO - __main__ - Step 64437: {'lr': 0.00031075276650682695, 'samples': 12371904, 'steps': 64436, 'loss/train': 0.1885749250650406} 08/31/2021 00:53:40 - INFO - __main__ - Step 64438: {'lr': 0.0003107476188263294, 'samples': 12372096, 'steps': 64437, 'loss/train': 0.05256209895014763} 08/31/2021 00:53:41 - INFO - __main__ - Step 64439: {'lr': 0.0003107424711184599, 'samples': 12372288, 'steps': 64438, 'loss/train': 1.2889409065246582} 08/31/2021 00:53:41 - INFO - __main__ - Step 64440: {'lr': 0.0003107373233832208, 'samples': 12372480, 'steps': 64439, 'loss/train': 0.05799126252532005} 08/31/2021 00:53:42 - INFO - __main__ - Step 64441: {'lr': 0.0003107321756206144, 'samples': 12372672, 'steps': 64440, 'loss/train': 1.4615787267684937} 08/31/2021 00:53:43 - INFO - __main__ - Step 64442: {'lr': 0.00031072702783064307, 'samples': 12372864, 'steps': 64441, 'loss/train': 1.2516515254974365} 08/31/2021 00:53:43 - INFO - __main__ - Step 64443: {'lr': 0.00031072188001330905, 'samples': 12373056, 'steps': 64442, 'loss/train': 1.4269360303878784} 08/31/2021 00:53:44 - INFO - __main__ - Step 64444: {'lr': 0.00031071673216861463, 'samples': 12373248, 'steps': 64443, 'loss/train': 1.3184442520141602} 08/31/2021 00:53:44 - INFO - __main__ - Step 64445: {'lr': 0.0003107115842965622, 'samples': 12373440, 'steps': 64444, 'loss/train': 1.8624615669250488} 08/31/2021 00:53:46 - INFO - __main__ - Step 64446: {'lr': 0.0003107064363971541, 'samples': 12373632, 'steps': 64445, 'loss/train': 2.0653886795043945} 08/31/2021 00:53:46 - INFO - __main__ - Step 64447: {'lr': 0.00031070128847039257, 'samples': 12373824, 'steps': 64446, 'loss/train': 1.305437684059143} 08/31/2021 00:53:46 - INFO - __main__ - Step 64448: {'lr': 0.00031069614051628004, 'samples': 12374016, 'steps': 64447, 'loss/train': 0.7212966680526733} 08/31/2021 00:53:47 - INFO - __main__ - Step 64449: {'lr': 0.00031069099253481873, 'samples': 12374208, 'steps': 64448, 'loss/train': 1.9985276460647583} 08/31/2021 00:53:47 - INFO - __main__ - Step 64450: {'lr': 0.000310685844526011, 'samples': 12374400, 'steps': 64449, 'loss/train': 1.4188988208770752} 08/31/2021 00:53:49 - INFO - __main__ - Step 64451: {'lr': 0.0003106806964898592, 'samples': 12374592, 'steps': 64450, 'loss/train': 1.0166627168655396} 08/31/2021 00:53:49 - INFO - __main__ - Step 64452: {'lr': 0.0003106755484263656, 'samples': 12374784, 'steps': 64451, 'loss/train': 1.0643173456192017} 08/31/2021 00:53:50 - INFO - __main__ - Step 64453: {'lr': 0.00031067040033553244, 'samples': 12374976, 'steps': 64452, 'loss/train': 1.5893126726150513} 08/31/2021 00:53:50 - INFO - __main__ - Step 64454: {'lr': 0.00031066525221736224, 'samples': 12375168, 'steps': 64453, 'loss/train': 1.2776306867599487} 08/31/2021 00:53:50 - INFO - __main__ - Step 64455: {'lr': 0.0003106601040718572, 'samples': 12375360, 'steps': 64454, 'loss/train': 1.4418466091156006} 08/31/2021 00:53:52 - INFO - __main__ - Step 64456: {'lr': 0.00031065495589901966, 'samples': 12375552, 'steps': 64455, 'loss/train': 0.049532052129507065} 08/31/2021 00:53:52 - INFO - __main__ - Step 64457: {'lr': 0.0003106498076988519, 'samples': 12375744, 'steps': 64456, 'loss/train': 1.4377537965774536} 08/31/2021 00:53:53 - INFO - __main__ - Step 64458: {'lr': 0.00031064465947135627, 'samples': 12375936, 'steps': 64457, 'loss/train': 1.6965818405151367} 08/31/2021 00:53:53 - INFO - __main__ - Step 64459: {'lr': 0.0003106395112165351, 'samples': 12376128, 'steps': 64458, 'loss/train': 0.8231273293495178} 08/31/2021 00:53:53 - INFO - __main__ - Step 64460: {'lr': 0.00031063436293439066, 'samples': 12376320, 'steps': 64459, 'loss/train': 1.7458568811416626} 08/31/2021 00:53:55 - INFO - __main__ - Step 64461: {'lr': 0.0003106292146249254, 'samples': 12376512, 'steps': 64460, 'loss/train': 1.6806423664093018} 08/31/2021 00:53:56 - INFO - __main__ - Step 64462: {'lr': 0.0003106240662881415, 'samples': 12376704, 'steps': 64461, 'loss/train': 1.3150551319122314} 08/31/2021 00:53:56 - INFO - __main__ - Step 64463: {'lr': 0.0003106189179240414, 'samples': 12376896, 'steps': 64462, 'loss/train': 1.2801313400268555} 08/31/2021 00:53:56 - INFO - __main__ - Step 64464: {'lr': 0.0003106137695326273, 'samples': 12377088, 'steps': 64463, 'loss/train': 0.7330235242843628} 08/31/2021 00:53:57 - INFO - __main__ - Step 64465: {'lr': 0.00031060862111390155, 'samples': 12377280, 'steps': 64464, 'loss/train': 1.5689622163772583} 08/31/2021 00:54:00 - INFO - __main__ - Step 64466: {'lr': 0.0003106034726678665, 'samples': 12377472, 'steps': 64465, 'loss/train': 0.05913103371858597} 08/31/2021 00:54:01 - INFO - __main__ - Step 64467: {'lr': 0.00031059832419452445, 'samples': 12377664, 'steps': 64466, 'loss/train': 0.9583345055580139} 08/31/2021 00:54:01 - INFO - __main__ - Step 64468: {'lr': 0.0003105931756938777, 'samples': 12377856, 'steps': 64467, 'loss/train': 1.9259109497070312} 08/31/2021 00:54:01 - INFO - __main__ - Step 64469: {'lr': 0.00031058802716592873, 'samples': 12378048, 'steps': 64468, 'loss/train': 1.8677736520767212} 08/31/2021 00:54:02 - INFO - __main__ - Step 64470: {'lr': 0.0003105828786106796, 'samples': 12378240, 'steps': 64469, 'loss/train': 1.9026243686676025} 08/31/2021 00:54:02 - INFO - __main__ - Step 64471: {'lr': 0.00031057773002813276, 'samples': 12378432, 'steps': 64470, 'loss/train': 1.6142969131469727} 08/31/2021 00:54:02 - INFO - __main__ - Step 64472: {'lr': 0.0003105725814182906, 'samples': 12378624, 'steps': 64471, 'loss/train': 1.411934733390808} 08/31/2021 00:54:03 - INFO - __main__ - Step 64473: {'lr': 0.00031056743278115535, 'samples': 12378816, 'steps': 64472, 'loss/train': 1.7905465364456177} 08/31/2021 00:54:05 - INFO - __main__ - Step 64474: {'lr': 0.00031056228411672934, 'samples': 12379008, 'steps': 64473, 'loss/train': 1.1847975254058838} 08/31/2021 00:54:05 - INFO - __main__ - Step 64475: {'lr': 0.00031055713542501483, 'samples': 12379200, 'steps': 64474, 'loss/train': 0.07623011618852615} 08/31/2021 00:54:05 - INFO - __main__ - Step 64476: {'lr': 0.00031055198670601437, 'samples': 12379392, 'steps': 64475, 'loss/train': 1.4295566082000732} 08/31/2021 00:54:06 - INFO - __main__ - Step 64477: {'lr': 0.00031054683795973007, 'samples': 12379584, 'steps': 64476, 'loss/train': 1.6741598844528198} 08/31/2021 00:54:06 - INFO - __main__ - Step 64478: {'lr': 0.0003105416891861642, 'samples': 12379776, 'steps': 64477, 'loss/train': 0.9821784496307373} 08/31/2021 00:54:07 - INFO - __main__ - Step 64479: {'lr': 0.00031053654038531927, 'samples': 12379968, 'steps': 64478, 'loss/train': 1.1796574592590332} 08/31/2021 00:54:08 - INFO - __main__ - Step 64480: {'lr': 0.00031053139155719743, 'samples': 12380160, 'steps': 64479, 'loss/train': 1.0236232280731201} 08/31/2021 00:54:08 - INFO - __main__ - Step 64481: {'lr': 0.00031052624270180114, 'samples': 12380352, 'steps': 64480, 'loss/train': 1.0439622402191162} 08/31/2021 00:54:09 - INFO - __main__ - Step 64482: {'lr': 0.0003105210938191326, 'samples': 12380544, 'steps': 64481, 'loss/train': 1.470099687576294} 08/31/2021 00:54:09 - INFO - __main__ - Step 64483: {'lr': 0.0003105159449091943, 'samples': 12380736, 'steps': 64482, 'loss/train': 1.317150354385376} 08/31/2021 00:54:11 - INFO - __main__ - Step 64484: {'lr': 0.0003105107959719884, 'samples': 12380928, 'steps': 64483, 'loss/train': 1.366068720817566} 08/31/2021 00:54:11 - INFO - __main__ - Step 64485: {'lr': 0.0003105056470075172, 'samples': 12381120, 'steps': 64484, 'loss/train': 1.4233516454696655} 08/31/2021 00:54:12 - INFO - __main__ - Step 64486: {'lr': 0.0003105004980157832, 'samples': 12381312, 'steps': 64485, 'loss/train': 1.580556869506836} 08/31/2021 00:54:12 - INFO - __main__ - Step 64487: {'lr': 0.0003104953489967885, 'samples': 12381504, 'steps': 64486, 'loss/train': 1.3119980096817017} 08/31/2021 00:54:12 - INFO - __main__ - Step 64488: {'lr': 0.0003104901999505356, 'samples': 12381696, 'steps': 64487, 'loss/train': 0.5089579820632935} 08/31/2021 00:54:13 - INFO - __main__ - Step 64489: {'lr': 0.0003104850508770267, 'samples': 12381888, 'steps': 64488, 'loss/train': 1.0178343057632446} 08/31/2021 00:54:13 - INFO - __main__ - Step 64490: {'lr': 0.00031047990177626424, 'samples': 12382080, 'steps': 64489, 'loss/train': 5.917715549468994} 08/31/2021 00:54:15 - INFO - __main__ - Step 64491: {'lr': 0.0003104747526482504, 'samples': 12382272, 'steps': 64490, 'loss/train': 5.86290979385376} 08/31/2021 00:54:15 - INFO - __main__ - Step 64492: {'lr': 0.0003104696034929876, 'samples': 12382464, 'steps': 64491, 'loss/train': 1.2156449556350708} 08/31/2021 00:54:16 - INFO - __main__ - Step 64493: {'lr': 0.0003104644543104781, 'samples': 12382656, 'steps': 64492, 'loss/train': 1.5836365222930908} 08/31/2021 00:54:16 - INFO - __main__ - Step 64494: {'lr': 0.00031045930510072427, 'samples': 12382848, 'steps': 64493, 'loss/train': 1.2121903896331787} 08/31/2021 00:54:16 - INFO - __main__ - Step 64495: {'lr': 0.00031045415586372844, 'samples': 12383040, 'steps': 64494, 'loss/train': 1.581682801246643} 08/31/2021 00:54:17 - INFO - __main__ - Step 64496: {'lr': 0.00031044900659949295, 'samples': 12383232, 'steps': 64495, 'loss/train': 1.576036810874939} 08/31/2021 00:54:18 - INFO - __main__ - Step 64497: {'lr': 0.0003104438573080199, 'samples': 12383424, 'steps': 64496, 'loss/train': 0.130338653922081} 08/31/2021 00:54:19 - INFO - __main__ - Step 64498: {'lr': 0.00031043870798931194, 'samples': 12383616, 'steps': 64497, 'loss/train': 1.6494438648223877} 08/31/2021 00:54:19 - INFO - __main__ - Step 64499: {'lr': 0.00031043355864337113, 'samples': 12383808, 'steps': 64498, 'loss/train': 1.7051554918289185} 08/31/2021 00:54:19 - INFO - __main__ - Step 64500: {'lr': 0.00031042840927019994, 'samples': 12384000, 'steps': 64499, 'loss/train': 0.08969369530677795} 08/31/2021 00:54:20 - INFO - __main__ - Step 64501: {'lr': 0.00031042325986980064, 'samples': 12384192, 'steps': 64500, 'loss/train': 1.6674662828445435} 08/31/2021 00:54:21 - INFO - __main__ - Step 64502: {'lr': 0.0003104181104421755, 'samples': 12384384, 'steps': 64501, 'loss/train': 1.8093011379241943} 08/31/2021 00:54:22 - INFO - __main__ - Step 64503: {'lr': 0.000310412960987327, 'samples': 12384576, 'steps': 64502, 'loss/train': 0.9323804974555969} 08/31/2021 00:54:22 - INFO - __main__ - Step 64504: {'lr': 0.00031040781150525726, 'samples': 12384768, 'steps': 64503, 'loss/train': 1.4834715127944946} 08/31/2021 00:54:22 - INFO - __main__ - Step 64505: {'lr': 0.0003104026619959687, 'samples': 12384960, 'steps': 64504, 'loss/train': 0.5259380340576172} 08/31/2021 00:54:23 - INFO - __main__ - Step 64506: {'lr': 0.00031039751245946366, 'samples': 12385152, 'steps': 64505, 'loss/train': 1.3170998096466064} 08/31/2021 00:54:24 - INFO - __main__ - Step 64507: {'lr': 0.0003103923628957444, 'samples': 12385344, 'steps': 64506, 'loss/train': 1.3272414207458496} 08/31/2021 00:54:25 - INFO - __main__ - Step 64508: {'lr': 0.00031038721330481334, 'samples': 12385536, 'steps': 64507, 'loss/train': 1.339540719985962} 08/31/2021 00:54:25 - INFO - __main__ - Step 64509: {'lr': 0.00031038206368667263, 'samples': 12385728, 'steps': 64508, 'loss/train': 1.0884876251220703} 08/31/2021 00:54:25 - INFO - __main__ - Step 64510: {'lr': 0.00031037691404132484, 'samples': 12385920, 'steps': 64509, 'loss/train': 1.0458595752716064} 08/31/2021 00:54:26 - INFO - __main__ - Step 64511: {'lr': 0.0003103717643687721, 'samples': 12386112, 'steps': 64510, 'loss/train': 1.0479857921600342} 08/31/2021 00:54:27 - INFO - __main__ - Step 64512: {'lr': 0.00031036661466901666, 'samples': 12386304, 'steps': 64511, 'loss/train': 1.310874342918396} 08/31/2021 00:54:28 - INFO - __main__ - Step 64513: {'lr': 0.000310361464942061, 'samples': 12386496, 'steps': 64512, 'loss/train': 1.5953747034072876} 08/31/2021 00:54:28 - INFO - __main__ - Step 64514: {'lr': 0.0003103563151879075, 'samples': 12386688, 'steps': 64513, 'loss/train': 1.5166575908660889} 08/31/2021 00:54:28 - INFO - __main__ - Step 64515: {'lr': 0.00031035116540655824, 'samples': 12386880, 'steps': 64514, 'loss/train': 1.575373649597168} 08/31/2021 00:54:29 - INFO - __main__ - Step 64516: {'lr': 0.0003103460155980158, 'samples': 12387072, 'steps': 64515, 'loss/train': 1.3259754180908203} 08/31/2021 00:54:30 - INFO - __main__ - Step 64517: {'lr': 0.00031034086576228227, 'samples': 12387264, 'steps': 64516, 'loss/train': 1.3975870609283447} 08/31/2021 00:54:31 - INFO - __main__ - Step 64518: {'lr': 0.00031033571589936015, 'samples': 12387456, 'steps': 64517, 'loss/train': 1.815749168395996} 08/31/2021 00:54:31 - INFO - __main__ - Step 64519: {'lr': 0.0003103305660092516, 'samples': 12387648, 'steps': 64518, 'loss/train': 0.3445468842983246} 08/31/2021 00:54:31 - INFO - __main__ - Step 64520: {'lr': 0.0003103254160919591, 'samples': 12387840, 'steps': 64519, 'loss/train': 1.2631624937057495} 08/31/2021 00:54:32 - INFO - __main__ - Step 64521: {'lr': 0.00031032026614748485, 'samples': 12388032, 'steps': 64520, 'loss/train': 1.3830910921096802} 08/31/2021 00:54:33 - INFO - __main__ - Step 64522: {'lr': 0.0003103151161758313, 'samples': 12388224, 'steps': 64521, 'loss/train': 0.95362389087677} 08/31/2021 00:54:34 - INFO - __main__ - Step 64523: {'lr': 0.0003103099661770007, 'samples': 12388416, 'steps': 64522, 'loss/train': 1.115196704864502} 08/31/2021 00:54:34 - INFO - __main__ - Step 64524: {'lr': 0.00031030481615099527, 'samples': 12388608, 'steps': 64523, 'loss/train': 1.3563969135284424} 08/31/2021 00:54:34 - INFO - __main__ - Step 64525: {'lr': 0.00031029966609781747, 'samples': 12388800, 'steps': 64524, 'loss/train': 1.1814733743667603} 08/31/2021 00:54:35 - INFO - __main__ - Step 64526: {'lr': 0.0003102945160174695, 'samples': 12388992, 'steps': 64525, 'loss/train': 1.2870752811431885} 08/31/2021 00:54:37 - INFO - __main__ - Step 64527: {'lr': 0.0003102893659099538, 'samples': 12389184, 'steps': 64526, 'loss/train': 0.8987717032432556} 08/31/2021 00:54:38 - INFO - __main__ - Step 64528: {'lr': 0.0003102842157752727, 'samples': 12389376, 'steps': 64527, 'loss/train': 1.8998942375183105} 08/31/2021 00:54:38 - INFO - __main__ - Step 64529: {'lr': 0.0003102790656134284, 'samples': 12389568, 'steps': 64528, 'loss/train': 1.5297333002090454} 08/31/2021 00:54:38 - INFO - __main__ - Step 64530: {'lr': 0.0003102739154244233, 'samples': 12389760, 'steps': 64529, 'loss/train': 0.9589240550994873} 08/31/2021 00:54:39 - INFO - __main__ - Step 64531: {'lr': 0.0003102687652082597, 'samples': 12389952, 'steps': 64530, 'loss/train': 1.482527256011963} 08/31/2021 00:54:39 - INFO - __main__ - Step 64532: {'lr': 0.0003102636149649399, 'samples': 12390144, 'steps': 64531, 'loss/train': 0.6109333038330078} 08/31/2021 00:54:41 - INFO - __main__ - Step 64533: {'lr': 0.0003102584646944662, 'samples': 12390336, 'steps': 64532, 'loss/train': 0.037687741219997406} 08/31/2021 00:54:41 - INFO - __main__ - Step 64534: {'lr': 0.0003102533143968411, 'samples': 12390528, 'steps': 64533, 'loss/train': 1.1743121147155762} 08/31/2021 00:54:42 - INFO - __main__ - Step 64535: {'lr': 0.00031024816407206675, 'samples': 12390720, 'steps': 64534, 'loss/train': 1.6491576433181763} 08/31/2021 00:54:42 - INFO - __main__ - Step 64536: {'lr': 0.00031024301372014544, 'samples': 12390912, 'steps': 64535, 'loss/train': 1.3132150173187256} 08/31/2021 00:54:42 - INFO - __main__ - Step 64537: {'lr': 0.0003102378633410796, 'samples': 12391104, 'steps': 64536, 'loss/train': 1.0995649099349976} 08/31/2021 00:54:43 - INFO - __main__ - Step 64538: {'lr': 0.0003102327129348715, 'samples': 12391296, 'steps': 64537, 'loss/train': 1.0395365953445435} 08/31/2021 00:54:45 - INFO - __main__ - Step 64539: {'lr': 0.00031022756250152344, 'samples': 12391488, 'steps': 64538, 'loss/train': 0.9451919198036194} 08/31/2021 00:54:45 - INFO - __main__ - Step 64540: {'lr': 0.00031022241204103787, 'samples': 12391680, 'steps': 64539, 'loss/train': 0.26620060205459595} 08/31/2021 00:54:45 - INFO - __main__ - Step 64541: {'lr': 0.0003102172615534169, 'samples': 12391872, 'steps': 64540, 'loss/train': 0.9771392941474915} 08/31/2021 00:54:46 - INFO - __main__ - Step 64542: {'lr': 0.000310212111038663, 'samples': 12392064, 'steps': 64541, 'loss/train': 1.317870020866394} 08/31/2021 00:54:46 - INFO - __main__ - Step 64543: {'lr': 0.00031020696049677846, 'samples': 12392256, 'steps': 64542, 'loss/train': 1.1667386293411255} 08/31/2021 00:54:48 - INFO - __main__ - Step 64544: {'lr': 0.0003102018099277656, 'samples': 12392448, 'steps': 64543, 'loss/train': 0.0920182541012764} 08/31/2021 00:54:48 - INFO - __main__ - Step 64545: {'lr': 0.0003101966593316267, 'samples': 12392640, 'steps': 64544, 'loss/train': 1.1428658962249756} 08/31/2021 00:54:49 - INFO - __main__ - Step 64546: {'lr': 0.00031019150870836414, 'samples': 12392832, 'steps': 64545, 'loss/train': 1.7496490478515625} 08/31/2021 00:54:49 - INFO - __main__ - Step 64547: {'lr': 0.00031018635805798024, 'samples': 12393024, 'steps': 64546, 'loss/train': 1.1966978311538696} 08/31/2021 00:54:49 - INFO - __main__ - Step 64548: {'lr': 0.00031018120738047724, 'samples': 12393216, 'steps': 64547, 'loss/train': 0.9308652281761169} 08/31/2021 00:54:50 - INFO - __main__ - Step 64549: {'lr': 0.00031017605667585754, 'samples': 12393408, 'steps': 64548, 'loss/train': 1.0463491678237915} 08/31/2021 00:54:51 - INFO - __main__ - Step 64550: {'lr': 0.0003101709059441234, 'samples': 12393600, 'steps': 64549, 'loss/train': 1.0267295837402344} 08/31/2021 00:54:51 - INFO - __main__ - Step 64551: {'lr': 0.00031016575518527726, 'samples': 12393792, 'steps': 64550, 'loss/train': 0.9791166186332703} 08/31/2021 00:54:52 - INFO - __main__ - Step 64552: {'lr': 0.0003101606043993213, 'samples': 12393984, 'steps': 64551, 'loss/train': 1.3954187631607056} 08/31/2021 00:54:52 - INFO - __main__ - Step 64553: {'lr': 0.0003101554535862579, 'samples': 12394176, 'steps': 64552, 'loss/train': 1.430877447128296} 08/31/2021 00:54:54 - INFO - __main__ - Step 64554: {'lr': 0.0003101503027460894, 'samples': 12394368, 'steps': 64553, 'loss/train': 1.996307373046875} 08/31/2021 00:54:54 - INFO - __main__ - Step 64555: {'lr': 0.00031014515187881807, 'samples': 12394560, 'steps': 64554, 'loss/train': 0.9077143669128418} 08/31/2021 00:54:54 - INFO - __main__ - Step 64556: {'lr': 0.00031014000098444634, 'samples': 12394752, 'steps': 64555, 'loss/train': 1.3532606363296509} 08/31/2021 00:54:55 - INFO - __main__ - Step 64557: {'lr': 0.00031013485006297644, 'samples': 12394944, 'steps': 64556, 'loss/train': 0.23549744486808777} 08/31/2021 00:54:55 - INFO - __main__ - Step 64558: {'lr': 0.00031012969911441065, 'samples': 12395136, 'steps': 64557, 'loss/train': 1.7970234155654907} 08/31/2021 00:54:55 - INFO - __main__ - Step 64559: {'lr': 0.00031012454813875135, 'samples': 12395328, 'steps': 64558, 'loss/train': 1.7277584075927734} 08/31/2021 00:54:57 - INFO - __main__ - Step 64560: {'lr': 0.0003101193971360009, 'samples': 12395520, 'steps': 64559, 'loss/train': 0.9416779279708862} 08/31/2021 00:54:58 - INFO - __main__ - Step 64561: {'lr': 0.0003101142461061615, 'samples': 12395712, 'steps': 64560, 'loss/train': 1.484253168106079} 08/31/2021 00:54:58 - INFO - __main__ - Step 64562: {'lr': 0.00031010909504923555, 'samples': 12395904, 'steps': 64561, 'loss/train': 1.3639568090438843} 08/31/2021 00:54:59 - INFO - __main__ - Step 64563: {'lr': 0.00031010394396522553, 'samples': 12396096, 'steps': 64562, 'loss/train': 0.6996088624000549} 08/31/2021 00:54:59 - INFO - __main__ - Step 64564: {'lr': 0.00031009879285413345, 'samples': 12396288, 'steps': 64563, 'loss/train': 1.3268821239471436} 08/31/2021 00:55:01 - INFO - __main__ - Step 64565: {'lr': 0.00031009364171596184, 'samples': 12396480, 'steps': 64564, 'loss/train': 1.1292461156845093} 08/31/2021 00:55:01 - INFO - __main__ - Step 64566: {'lr': 0.00031008849055071293, 'samples': 12396672, 'steps': 64565, 'loss/train': 1.411237359046936} 08/31/2021 00:55:02 - INFO - __main__ - Step 64567: {'lr': 0.00031008333935838905, 'samples': 12396864, 'steps': 64566, 'loss/train': 0.4927048683166504} 08/31/2021 00:55:02 - INFO - __main__ - Step 64568: {'lr': 0.0003100781881389926, 'samples': 12397056, 'steps': 64567, 'loss/train': 1.3491095304489136} 08/31/2021 00:55:02 - INFO - __main__ - Step 64569: {'lr': 0.00031007303689252583, 'samples': 12397248, 'steps': 64568, 'loss/train': 1.291314959526062} 08/31/2021 00:55:03 - INFO - __main__ - Step 64570: {'lr': 0.0003100678856189911, 'samples': 12397440, 'steps': 64569, 'loss/train': 2.550189971923828} 08/31/2021 00:55:04 - INFO - __main__ - Step 64571: {'lr': 0.00031006273431839065, 'samples': 12397632, 'steps': 64570, 'loss/train': 1.4419914484024048} 08/31/2021 00:55:05 - INFO - __main__ - Step 64572: {'lr': 0.00031005758299072685, 'samples': 12397824, 'steps': 64571, 'loss/train': 1.3371129035949707} 08/31/2021 00:55:05 - INFO - __main__ - Step 64573: {'lr': 0.00031005243163600207, 'samples': 12398016, 'steps': 64572, 'loss/train': 1.0359523296356201} 08/31/2021 00:55:05 - INFO - __main__ - Step 64574: {'lr': 0.0003100472802542186, 'samples': 12398208, 'steps': 64573, 'loss/train': 1.8950424194335938} 08/31/2021 00:55:06 - INFO - __main__ - Step 64575: {'lr': 0.0003100421288453787, 'samples': 12398400, 'steps': 64574, 'loss/train': 1.4455828666687012} 08/31/2021 00:55:07 - INFO - __main__ - Step 64576: {'lr': 0.00031003697740948475, 'samples': 12398592, 'steps': 64575, 'loss/train': 1.3827803134918213} 08/31/2021 00:55:08 - INFO - __main__ - Step 64577: {'lr': 0.0003100318259465392, 'samples': 12398784, 'steps': 64576, 'loss/train': 1.3719120025634766} 08/31/2021 00:55:08 - INFO - __main__ - Step 64578: {'lr': 0.0003100266744565441, 'samples': 12398976, 'steps': 64577, 'loss/train': 1.3935248851776123} 08/31/2021 00:55:08 - INFO - __main__ - Step 64579: {'lr': 0.00031002152293950193, 'samples': 12399168, 'steps': 64578, 'loss/train': 1.3285269737243652} 08/31/2021 00:55:09 - INFO - __main__ - Step 64580: {'lr': 0.000310016371395415, 'samples': 12399360, 'steps': 64579, 'loss/train': 3.2184622287750244} 08/31/2021 00:55:09 - INFO - __main__ - Step 64581: {'lr': 0.0003100112198242856, 'samples': 12399552, 'steps': 64580, 'loss/train': 0.9703230857849121} 08/31/2021 00:55:11 - INFO - __main__ - Step 64582: {'lr': 0.0003100060682261161, 'samples': 12399744, 'steps': 64581, 'loss/train': 1.3040978908538818} 08/31/2021 00:55:12 - INFO - __main__ - Step 64583: {'lr': 0.0003100009166009087, 'samples': 12399936, 'steps': 64582, 'loss/train': 1.3358967304229736} 08/31/2021 00:55:12 - INFO - __main__ - Step 64584: {'lr': 0.000309995764948666, 'samples': 12400128, 'steps': 64583, 'loss/train': 1.056354284286499} 08/31/2021 00:55:12 - INFO - __main__ - Step 64585: {'lr': 0.00030999061326939, 'samples': 12400320, 'steps': 64584, 'loss/train': 1.383017897605896} 08/31/2021 00:55:13 - INFO - __main__ - Step 64586: {'lr': 0.00030998546156308314, 'samples': 12400512, 'steps': 64585, 'loss/train': 1.2955293655395508} 08/31/2021 00:55:14 - INFO - __main__ - Step 64587: {'lr': 0.00030998030982974786, 'samples': 12400704, 'steps': 64586, 'loss/train': 1.7498838901519775} 08/31/2021 00:55:15 - INFO - __main__ - Step 64588: {'lr': 0.00030997515806938623, 'samples': 12400896, 'steps': 64587, 'loss/train': 0.6269993185997009} 08/31/2021 00:55:15 - INFO - __main__ - Step 64589: {'lr': 0.0003099700062820008, 'samples': 12401088, 'steps': 64588, 'loss/train': 1.7951363325119019} 08/31/2021 00:55:15 - INFO - __main__ - Step 64590: {'lr': 0.0003099648544675939, 'samples': 12401280, 'steps': 64589, 'loss/train': 0.7290248870849609} 08/31/2021 00:55:16 - INFO - __main__ - Step 64591: {'lr': 0.0003099597026261677, 'samples': 12401472, 'steps': 64590, 'loss/train': 1.6160348653793335} 08/31/2021 00:55:17 - INFO - __main__ - Step 64592: {'lr': 0.0003099545507577245, 'samples': 12401664, 'steps': 64591, 'loss/train': 0.8099387884140015} 08/31/2021 00:55:18 - INFO - __main__ - Step 64593: {'lr': 0.00030994939886226674, 'samples': 12401856, 'steps': 64592, 'loss/train': 0.9705431461334229} 08/31/2021 00:55:18 - INFO - __main__ - Step 64594: {'lr': 0.0003099442469397967, 'samples': 12402048, 'steps': 64593, 'loss/train': 1.1504185199737549} 08/31/2021 00:55:18 - INFO - __main__ - Step 64595: {'lr': 0.0003099390949903168, 'samples': 12402240, 'steps': 64594, 'loss/train': 0.7325393557548523} 08/31/2021 00:55:19 - INFO - __main__ - Step 64596: {'lr': 0.00030993394301382916, 'samples': 12402432, 'steps': 64595, 'loss/train': 1.5594658851623535} 08/31/2021 00:55:19 - INFO - __main__ - Step 64597: {'lr': 0.00030992879101033634, 'samples': 12402624, 'steps': 64596, 'loss/train': 1.5249460935592651} 08/31/2021 00:55:21 - INFO - __main__ - Step 64598: {'lr': 0.00030992363897984043, 'samples': 12402816, 'steps': 64597, 'loss/train': 1.3126766681671143} 08/31/2021 00:55:21 - INFO - __main__ - Step 64599: {'lr': 0.00030991848692234387, 'samples': 12403008, 'steps': 64598, 'loss/train': 1.5883969068527222} 08/31/2021 00:55:21 - INFO - __main__ - Step 64600: {'lr': 0.00030991333483784895, 'samples': 12403200, 'steps': 64599, 'loss/train': 0.9785354137420654} 08/31/2021 00:55:22 - INFO - __main__ - Step 64601: {'lr': 0.000309908182726358, 'samples': 12403392, 'steps': 64600, 'loss/train': 1.2645704746246338} 08/31/2021 00:55:22 - INFO - __main__ - Step 64602: {'lr': 0.0003099030305878733, 'samples': 12403584, 'steps': 64601, 'loss/train': 0.12150870263576508} 08/31/2021 00:55:24 - INFO - __main__ - Step 64603: {'lr': 0.0003098978784223974, 'samples': 12403776, 'steps': 64602, 'loss/train': 1.480318546295166} 08/31/2021 00:55:24 - INFO - __main__ - Step 64604: {'lr': 0.0003098927262299323, 'samples': 12403968, 'steps': 64603, 'loss/train': 1.0565274953842163} 08/31/2021 00:55:25 - INFO - __main__ - Step 64605: {'lr': 0.0003098875740104805, 'samples': 12404160, 'steps': 64604, 'loss/train': 0.9954235553741455} 08/31/2021 00:55:25 - INFO - __main__ - Step 64606: {'lr': 0.00030988242176404425, 'samples': 12404352, 'steps': 64605, 'loss/train': 1.0210758447647095} 08/31/2021 00:55:25 - INFO - __main__ - Step 64607: {'lr': 0.00030987726949062596, 'samples': 12404544, 'steps': 64606, 'loss/train': 2.1519289016723633} 08/31/2021 00:55:27 - INFO - __main__ - Step 64608: {'lr': 0.00030987211719022784, 'samples': 12404736, 'steps': 64607, 'loss/train': 0.6160921454429626} 08/31/2021 00:55:28 - INFO - __main__ - Step 64609: {'lr': 0.00030986696486285227, 'samples': 12404928, 'steps': 64608, 'loss/train': 1.9773837327957153} 08/31/2021 00:55:28 - INFO - __main__ - Step 64610: {'lr': 0.00030986181250850165, 'samples': 12405120, 'steps': 64609, 'loss/train': 0.8199756145477295} 08/31/2021 00:55:28 - INFO - __main__ - Step 64611: {'lr': 0.00030985666012717814, 'samples': 12405312, 'steps': 64610, 'loss/train': 1.334643006324768} 08/31/2021 00:55:29 - INFO - __main__ - Step 64612: {'lr': 0.00030985150771888417, 'samples': 12405504, 'steps': 64611, 'loss/train': 0.9402002692222595} 08/31/2021 00:55:29 - INFO - __main__ - Step 64613: {'lr': 0.000309846355283622, 'samples': 12405696, 'steps': 64612, 'loss/train': 1.9788098335266113} 08/31/2021 00:55:30 - INFO - __main__ - Step 64614: {'lr': 0.000309841202821394, 'samples': 12405888, 'steps': 64613, 'loss/train': 1.0911953449249268} 08/31/2021 00:55:31 - INFO - __main__ - Step 64615: {'lr': 0.00030983605033220246, 'samples': 12406080, 'steps': 64614, 'loss/train': 0.7299412488937378} 08/31/2021 00:55:31 - INFO - __main__ - Step 64616: {'lr': 0.0003098308978160498, 'samples': 12406272, 'steps': 64615, 'loss/train': 1.2998801469802856} 08/31/2021 00:55:32 - INFO - __main__ - Step 64617: {'lr': 0.0003098257452729382, 'samples': 12406464, 'steps': 64616, 'loss/train': 1.488476276397705} 08/31/2021 00:55:32 - INFO - __main__ - Step 64618: {'lr': 0.00030982059270287006, 'samples': 12406656, 'steps': 64617, 'loss/train': 1.1463167667388916} 08/31/2021 00:55:34 - INFO - __main__ - Step 64619: {'lr': 0.00030981544010584767, 'samples': 12406848, 'steps': 64618, 'loss/train': 1.0032390356063843} 08/31/2021 00:55:34 - INFO - __main__ - Step 64620: {'lr': 0.0003098102874818734, 'samples': 12407040, 'steps': 64619, 'loss/train': 0.11232057958841324} 08/31/2021 00:55:34 - INFO - __main__ - Step 64621: {'lr': 0.0003098051348309495, 'samples': 12407232, 'steps': 64620, 'loss/train': 0.8659380078315735} 08/31/2021 00:55:35 - INFO - __main__ - Step 64622: {'lr': 0.0003097999821530783, 'samples': 12407424, 'steps': 64621, 'loss/train': 0.7311063408851624} 08/31/2021 00:55:35 - INFO - __main__ - Step 64623: {'lr': 0.0003097948294482622, 'samples': 12407616, 'steps': 64622, 'loss/train': 1.29613196849823} 08/31/2021 00:55:37 - INFO - __main__ - Step 64624: {'lr': 0.0003097896767165035, 'samples': 12407808, 'steps': 64623, 'loss/train': 1.484330654144287} 08/31/2021 00:55:37 - INFO - __main__ - Step 64625: {'lr': 0.00030978452395780446, 'samples': 12408000, 'steps': 64624, 'loss/train': 1.4064972400665283} 08/31/2021 00:55:37 - INFO - __main__ - Step 64626: {'lr': 0.0003097793711721674, 'samples': 12408192, 'steps': 64625, 'loss/train': 1.2482802867889404} 08/31/2021 00:55:38 - INFO - __main__ - Step 64627: {'lr': 0.00030977421835959475, 'samples': 12408384, 'steps': 64626, 'loss/train': 1.1569627523422241} 08/31/2021 00:55:38 - INFO - __main__ - Step 64628: {'lr': 0.0003097690655200887, 'samples': 12408576, 'steps': 64627, 'loss/train': 0.5503897070884705} 08/31/2021 00:55:38 - INFO - __main__ - Step 64629: {'lr': 0.0003097639126536516, 'samples': 12408768, 'steps': 64628, 'loss/train': 1.8702480792999268} 08/31/2021 00:55:40 - INFO - __main__ - Step 64630: {'lr': 0.00030975875976028586, 'samples': 12408960, 'steps': 64629, 'loss/train': 1.419197678565979} 08/31/2021 00:55:40 - INFO - __main__ - Step 64631: {'lr': 0.0003097536068399938, 'samples': 12409152, 'steps': 64630, 'loss/train': 1.135067343711853} 08/31/2021 00:55:41 - INFO - __main__ - Step 64632: {'lr': 0.00030974845389277763, 'samples': 12409344, 'steps': 64631, 'loss/train': 1.398289680480957} 08/31/2021 00:55:41 - INFO - __main__ - Step 64633: {'lr': 0.00030974330091863974, 'samples': 12409536, 'steps': 64632, 'loss/train': 0.722467303276062} 08/31/2021 00:55:41 - INFO - __main__ - Step 64634: {'lr': 0.00030973814791758237, 'samples': 12409728, 'steps': 64633, 'loss/train': 0.7149382829666138} 08/31/2021 00:55:43 - INFO - __main__ - Step 64635: {'lr': 0.000309732994889608, 'samples': 12409920, 'steps': 64634, 'loss/train': 1.4111140966415405} 08/31/2021 00:55:44 - INFO - __main__ - Step 64636: {'lr': 0.0003097278418347188, 'samples': 12410112, 'steps': 64635, 'loss/train': 1.5003210306167603} 08/31/2021 00:55:44 - INFO - __main__ - Step 64637: {'lr': 0.00030972268875291723, 'samples': 12410304, 'steps': 64636, 'loss/train': 1.3465009927749634} 08/31/2021 00:55:44 - INFO - __main__ - Step 64638: {'lr': 0.0003097175356442055, 'samples': 12410496, 'steps': 64637, 'loss/train': 0.10666371136903763} 08/31/2021 00:55:45 - INFO - __main__ - Step 64639: {'lr': 0.00030971238250858597, 'samples': 12410688, 'steps': 64638, 'loss/train': 1.1338441371917725} 08/31/2021 00:55:46 - INFO - __main__ - Step 64640: {'lr': 0.00030970722934606096, 'samples': 12410880, 'steps': 64639, 'loss/train': 1.2101497650146484} 08/31/2021 00:55:47 - INFO - __main__ - Step 64641: {'lr': 0.0003097020761566328, 'samples': 12411072, 'steps': 64640, 'loss/train': 1.3698139190673828} 08/31/2021 00:55:47 - INFO - __main__ - Step 64642: {'lr': 0.00030969692294030376, 'samples': 12411264, 'steps': 64641, 'loss/train': 0.9908256530761719} 08/31/2021 00:55:48 - INFO - __main__ - Step 64643: {'lr': 0.0003096917696970762, 'samples': 12411456, 'steps': 64642, 'loss/train': 2.0012362003326416} 08/31/2021 00:55:48 - INFO - __main__ - Step 64644: {'lr': 0.00030968661642695255, 'samples': 12411648, 'steps': 64643, 'loss/train': 1.8722976446151733} 08/31/2021 00:55:49 - INFO - __main__ - Step 64645: {'lr': 0.00030968146312993503, 'samples': 12411840, 'steps': 64644, 'loss/train': 0.075713150203228} 08/31/2021 00:55:50 - INFO - __main__ - Step 64646: {'lr': 0.0003096763098060259, 'samples': 12412032, 'steps': 64645, 'loss/train': 2.0559134483337402} 08/31/2021 00:55:50 - INFO - __main__ - Step 64647: {'lr': 0.00030967115645522754, 'samples': 12412224, 'steps': 64646, 'loss/train': 1.3385833501815796} 08/31/2021 00:55:50 - INFO - __main__ - Step 64648: {'lr': 0.0003096660030775423, 'samples': 12412416, 'steps': 64647, 'loss/train': 1.0666379928588867} 08/31/2021 00:55:51 - INFO - __main__ - Step 64649: {'lr': 0.0003096608496729724, 'samples': 12412608, 'steps': 64648, 'loss/train': 0.9926508069038391} 08/31/2021 00:55:53 - INFO - __main__ - Step 64650: {'lr': 0.00030965569624152037, 'samples': 12412800, 'steps': 64649, 'loss/train': 1.2494927644729614} 08/31/2021 00:55:53 - INFO - __main__ - Step 64651: {'lr': 0.00030965054278318837, 'samples': 12412992, 'steps': 64650, 'loss/train': 1.1506439447402954} 08/31/2021 00:55:53 - INFO - __main__ - Step 64652: {'lr': 0.0003096453892979787, 'samples': 12413184, 'steps': 64651, 'loss/train': 1.0644644498825073} 08/31/2021 00:55:54 - INFO - __main__ - Step 64653: {'lr': 0.00030964023578589376, 'samples': 12413376, 'steps': 64652, 'loss/train': 1.4961421489715576} 08/31/2021 00:55:54 - INFO - __main__ - Step 64654: {'lr': 0.0003096350822469359, 'samples': 12413568, 'steps': 64653, 'loss/train': 1.1123497486114502} 08/31/2021 00:55:55 - INFO - __main__ - Step 64655: {'lr': 0.00030962992868110734, 'samples': 12413760, 'steps': 64654, 'loss/train': 1.3321354389190674} 08/31/2021 00:55:56 - INFO - __main__ - Step 64656: {'lr': 0.0003096247750884105, 'samples': 12413952, 'steps': 64655, 'loss/train': 1.6951227188110352} 08/31/2021 00:55:57 - INFO - __main__ - Step 64657: {'lr': 0.00030961962146884765, 'samples': 12414144, 'steps': 64656, 'loss/train': 1.820543646812439} 08/31/2021 00:55:57 - INFO - __main__ - Step 64658: {'lr': 0.0003096144678224211, 'samples': 12414336, 'steps': 64657, 'loss/train': 1.1564112901687622} 08/31/2021 00:55:57 - INFO - __main__ - Step 64659: {'lr': 0.0003096093141491331, 'samples': 12414528, 'steps': 64658, 'loss/train': 1.2534104585647583} 08/31/2021 00:55:58 - INFO - __main__ - Step 64660: {'lr': 0.0003096041604489862, 'samples': 12414720, 'steps': 64659, 'loss/train': 0.8058088421821594} 08/31/2021 00:55:59 - INFO - __main__ - Step 64661: {'lr': 0.0003095990067219825, 'samples': 12414912, 'steps': 64660, 'loss/train': 1.3092690706253052} 08/31/2021 00:56:00 - INFO - __main__ - Step 64662: {'lr': 0.0003095938529681244, 'samples': 12415104, 'steps': 64661, 'loss/train': 1.8218446969985962} 08/31/2021 00:56:00 - INFO - __main__ - Step 64663: {'lr': 0.0003095886991874143, 'samples': 12415296, 'steps': 64662, 'loss/train': 1.3012704849243164} 08/31/2021 00:56:00 - INFO - __main__ - Step 64664: {'lr': 0.00030958354537985444, 'samples': 12415488, 'steps': 64663, 'loss/train': 1.000012993812561} 08/31/2021 00:56:01 - INFO - __main__ - Step 64665: {'lr': 0.00030957839154544713, 'samples': 12415680, 'steps': 64664, 'loss/train': 1.1830642223358154} 08/31/2021 00:56:02 - INFO - __main__ - Step 64666: {'lr': 0.00030957323768419475, 'samples': 12415872, 'steps': 64665, 'loss/train': 1.4859908819198608} 08/31/2021 00:56:03 - INFO - __main__ - Step 64667: {'lr': 0.0003095680837960996, 'samples': 12416064, 'steps': 64666, 'loss/train': 1.3863321542739868} 08/31/2021 00:56:03 - INFO - __main__ - Step 64668: {'lr': 0.0003095629298811639, 'samples': 12416256, 'steps': 64667, 'loss/train': 0.9152458310127258} 08/31/2021 00:56:04 - INFO - __main__ - Step 64669: {'lr': 0.0003095577759393902, 'samples': 12416448, 'steps': 64668, 'loss/train': 0.6073722243309021} 08/31/2021 00:56:04 - INFO - __main__ - Step 64670: {'lr': 0.00030955262197078054, 'samples': 12416640, 'steps': 64669, 'loss/train': 1.3489807844161987} 08/31/2021 00:56:05 - INFO - __main__ - Step 64671: {'lr': 0.00030954746797533743, 'samples': 12416832, 'steps': 64670, 'loss/train': 1.2157129049301147} 08/31/2021 00:56:06 - INFO - __main__ - Step 64672: {'lr': 0.00030954231395306314, 'samples': 12417024, 'steps': 64671, 'loss/train': 1.2375338077545166} 08/31/2021 00:56:06 - INFO - __main__ - Step 64673: {'lr': 0.00030953715990396006, 'samples': 12417216, 'steps': 64672, 'loss/train': 1.5156971216201782} 08/31/2021 00:56:06 - INFO - __main__ - Step 64674: {'lr': 0.0003095320058280305, 'samples': 12417408, 'steps': 64673, 'loss/train': 0.5117428302764893} 08/31/2021 00:56:07 - INFO - __main__ - Step 64675: {'lr': 0.0003095268517252766, 'samples': 12417600, 'steps': 64674, 'loss/train': 0.08948330581188202} 08/31/2021 00:56:07 - INFO - __main__ - Step 64676: {'lr': 0.00030952169759570087, 'samples': 12417792, 'steps': 64675, 'loss/train': 1.105003833770752} 08/31/2021 00:56:09 - INFO - __main__ - Step 64677: {'lr': 0.00030951654343930557, 'samples': 12417984, 'steps': 64676, 'loss/train': 0.7397109270095825} 08/31/2021 00:56:09 - INFO - __main__ - Step 64678: {'lr': 0.00030951138925609307, 'samples': 12418176, 'steps': 64677, 'loss/train': 1.2161322832107544} 08/31/2021 00:56:09 - INFO - __main__ - Step 64679: {'lr': 0.00030950623504606565, 'samples': 12418368, 'steps': 64678, 'loss/train': 1.4959901571273804} 08/31/2021 00:56:10 - INFO - __main__ - Step 64680: {'lr': 0.0003095010808092257, 'samples': 12418560, 'steps': 64679, 'loss/train': 1.6069408655166626} 08/31/2021 00:56:10 - INFO - __main__ - Step 64681: {'lr': 0.00030949592654557536, 'samples': 12418752, 'steps': 64680, 'loss/train': 1.50986647605896} 08/31/2021 00:56:12 - INFO - __main__ - Step 64682: {'lr': 0.0003094907722551171, 'samples': 12418944, 'steps': 64681, 'loss/train': 1.2080161571502686} 08/31/2021 00:56:13 - INFO - __main__ - Step 64683: {'lr': 0.00030948561793785325, 'samples': 12419136, 'steps': 64682, 'loss/train': 1.0860681533813477} 08/31/2021 00:56:13 - INFO - __main__ - Step 64684: {'lr': 0.0003094804635937861, 'samples': 12419328, 'steps': 64683, 'loss/train': 1.318843960762024} 08/31/2021 00:56:13 - INFO - __main__ - Step 64685: {'lr': 0.000309475309222918, 'samples': 12419520, 'steps': 64684, 'loss/train': 0.9966768622398376} 08/31/2021 00:56:14 - INFO - __main__ - Step 64686: {'lr': 0.0003094701548252512, 'samples': 12419712, 'steps': 64685, 'loss/train': 1.2256457805633545} 08/31/2021 00:56:15 - INFO - __main__ - Step 64687: {'lr': 0.00030946500040078805, 'samples': 12419904, 'steps': 64686, 'loss/train': 1.2499831914901733} 08/31/2021 00:56:16 - INFO - __main__ - Step 64688: {'lr': 0.0003094598459495309, 'samples': 12420096, 'steps': 64687, 'loss/train': 1.5746866464614868} 08/31/2021 00:56:16 - INFO - __main__ - Step 64689: {'lr': 0.0003094546914714821, 'samples': 12420288, 'steps': 64688, 'loss/train': 1.1834462881088257} 08/31/2021 00:56:16 - INFO - __main__ - Step 64690: {'lr': 0.00030944953696664384, 'samples': 12420480, 'steps': 64689, 'loss/train': 1.4714661836624146} 08/31/2021 00:56:17 - INFO - __main__ - Step 64691: {'lr': 0.00030944438243501863, 'samples': 12420672, 'steps': 64690, 'loss/train': 0.3767198920249939} 08/31/2021 00:56:18 - INFO - __main__ - Step 64692: {'lr': 0.00030943922787660864, 'samples': 12420864, 'steps': 64691, 'loss/train': 1.3354377746582031} 08/31/2021 00:56:19 - INFO - __main__ - Step 64693: {'lr': 0.0003094340732914163, 'samples': 12421056, 'steps': 64692, 'loss/train': 1.070396065711975} 08/31/2021 00:56:19 - INFO - __main__ - Step 64694: {'lr': 0.00030942891867944387, 'samples': 12421248, 'steps': 64693, 'loss/train': 1.0267984867095947} 08/31/2021 00:56:19 - INFO - __main__ - Step 64695: {'lr': 0.0003094237640406937, 'samples': 12421440, 'steps': 64694, 'loss/train': 1.4602872133255005} 08/31/2021 00:56:20 - INFO - __main__ - Step 64696: {'lr': 0.000309418609375168, 'samples': 12421632, 'steps': 64695, 'loss/train': 2.3715853691101074} 08/31/2021 00:56:21 - INFO - __main__ - Step 64697: {'lr': 0.0003094134546828693, 'samples': 12421824, 'steps': 64696, 'loss/train': 1.1176685094833374} 08/31/2021 00:56:22 - INFO - __main__ - Step 64698: {'lr': 0.00030940829996379984, 'samples': 12422016, 'steps': 64697, 'loss/train': 1.6143925189971924} 08/31/2021 00:56:22 - INFO - __main__ - Step 64699: {'lr': 0.0003094031452179618, 'samples': 12422208, 'steps': 64698, 'loss/train': 1.066049337387085} 08/31/2021 00:56:23 - INFO - __main__ - Step 64700: {'lr': 0.0003093979904453577, 'samples': 12422400, 'steps': 64699, 'loss/train': 1.2598042488098145} 08/31/2021 00:56:23 - INFO - __main__ - Step 64701: {'lr': 0.00030939283564598976, 'samples': 12422592, 'steps': 64700, 'loss/train': 0.7982909083366394} 08/31/2021 00:56:24 - INFO - __main__ - Step 64702: {'lr': 0.0003093876808198603, 'samples': 12422784, 'steps': 64701, 'loss/train': 1.0501041412353516} 08/31/2021 00:56:25 - INFO - __main__ - Step 64703: {'lr': 0.0003093825259669717, 'samples': 12422976, 'steps': 64702, 'loss/train': 1.5863170623779297} 08/31/2021 00:56:25 - INFO - __main__ - Step 64704: {'lr': 0.00030937737108732623, 'samples': 12423168, 'steps': 64703, 'loss/train': 1.5644973516464233} 08/31/2021 00:56:26 - INFO - __main__ - Step 64705: {'lr': 0.00030937221618092633, 'samples': 12423360, 'steps': 64704, 'loss/train': 0.22477178275585175} 08/31/2021 00:56:26 - INFO - __main__ - Step 64706: {'lr': 0.00030936706124777406, 'samples': 12423552, 'steps': 64705, 'loss/train': 0.9505504369735718} 08/31/2021 00:56:26 - INFO - __main__ - Step 64707: {'lr': 0.00030936190628787203, 'samples': 12423744, 'steps': 64706, 'loss/train': 1.2307536602020264} 08/31/2021 00:56:28 - INFO - __main__ - Step 64708: {'lr': 0.00030935675130122235, 'samples': 12423936, 'steps': 64707, 'loss/train': 1.3777722120285034} 08/31/2021 00:56:28 - INFO - __main__ - Step 64709: {'lr': 0.0003093515962878275, 'samples': 12424128, 'steps': 64708, 'loss/train': 0.9896668791770935} 08/31/2021 00:56:29 - INFO - __main__ - Step 64710: {'lr': 0.00030934644124768976, 'samples': 12424320, 'steps': 64709, 'loss/train': 1.4052488803863525} 08/31/2021 00:56:29 - INFO - __main__ - Step 64711: {'lr': 0.00030934128618081134, 'samples': 12424512, 'steps': 64710, 'loss/train': 0.46571022272109985} 08/31/2021 00:56:29 - INFO - __main__ - Step 64712: {'lr': 0.00030933613108719476, 'samples': 12424704, 'steps': 64711, 'loss/train': 0.49999111890792847} 08/31/2021 00:56:30 - INFO - __main__ - Step 64713: {'lr': 0.0003093309759668422, 'samples': 12424896, 'steps': 64712, 'loss/train': 0.7311645746231079} 08/31/2021 00:56:31 - INFO - __main__ - Step 64714: {'lr': 0.00030932582081975597, 'samples': 12425088, 'steps': 64713, 'loss/train': 1.3566551208496094} 08/31/2021 00:56:32 - INFO - __main__ - Step 64715: {'lr': 0.0003093206656459384, 'samples': 12425280, 'steps': 64714, 'loss/train': 0.1722615510225296} 08/31/2021 00:56:32 - INFO - __main__ - Step 64716: {'lr': 0.00030931551044539196, 'samples': 12425472, 'steps': 64715, 'loss/train': 1.5312259197235107} 08/31/2021 00:56:32 - INFO - __main__ - Step 64717: {'lr': 0.0003093103552181188, 'samples': 12425664, 'steps': 64716, 'loss/train': 1.2580488920211792} 08/31/2021 00:56:33 - INFO - __main__ - Step 64718: {'lr': 0.0003093051999641214, 'samples': 12425856, 'steps': 64717, 'loss/train': 1.554714560508728} 08/31/2021 00:56:34 - INFO - __main__ - Step 64719: {'lr': 0.00030930004468340187, 'samples': 12426048, 'steps': 64718, 'loss/train': 1.2368419170379639} 08/31/2021 00:56:35 - INFO - __main__ - Step 64720: {'lr': 0.00030929488937596274, 'samples': 12426240, 'steps': 64719, 'loss/train': 0.7770316004753113} 08/31/2021 00:56:35 - INFO - __main__ - Step 64721: {'lr': 0.0003092897340418062, 'samples': 12426432, 'steps': 64720, 'loss/train': 1.2477612495422363} 08/31/2021 00:56:35 - INFO - __main__ - Step 64722: {'lr': 0.0003092845786809346, 'samples': 12426624, 'steps': 64721, 'loss/train': 1.1395825147628784} 08/31/2021 00:56:36 - INFO - __main__ - Step 64723: {'lr': 0.0003092794232933503, 'samples': 12426816, 'steps': 64722, 'loss/train': 0.8604778051376343} 08/31/2021 00:56:37 - INFO - __main__ - Step 64724: {'lr': 0.00030927426787905564, 'samples': 12427008, 'steps': 64723, 'loss/train': 1.2383874654769897} 08/31/2021 00:56:38 - INFO - __main__ - Step 64725: {'lr': 0.000309269112438053, 'samples': 12427200, 'steps': 64724, 'loss/train': 1.241275429725647} 08/31/2021 00:56:38 - INFO - __main__ - Step 64726: {'lr': 0.0003092639569703445, 'samples': 12427392, 'steps': 64725, 'loss/train': 1.4745546579360962} 08/31/2021 00:56:38 - INFO - __main__ - Step 64727: {'lr': 0.0003092588014759325, 'samples': 12427584, 'steps': 64726, 'loss/train': 1.245841383934021} 08/31/2021 00:56:39 - INFO - __main__ - Step 64728: {'lr': 0.00030925364595481953, 'samples': 12427776, 'steps': 64727, 'loss/train': 1.5313794612884521} 08/31/2021 00:56:40 - INFO - __main__ - Step 64729: {'lr': 0.00030924849040700773, 'samples': 12427968, 'steps': 64728, 'loss/train': 1.928740382194519} 08/31/2021 00:56:41 - INFO - __main__ - Step 64730: {'lr': 0.0003092433348324995, 'samples': 12428160, 'steps': 64729, 'loss/train': 0.06377626210451126} 08/31/2021 00:56:41 - INFO - __main__ - Step 64731: {'lr': 0.00030923817923129716, 'samples': 12428352, 'steps': 64730, 'loss/train': 1.6406008005142212} 08/31/2021 00:56:41 - INFO - __main__ - Step 64732: {'lr': 0.00030923302360340294, 'samples': 12428544, 'steps': 64731, 'loss/train': 1.2481693029403687} 08/31/2021 00:56:42 - INFO - __main__ - Step 64733: {'lr': 0.0003092278679488193, 'samples': 12428736, 'steps': 64732, 'loss/train': 2.202874183654785} 08/31/2021 00:56:44 - INFO - __main__ - Step 64734: {'lr': 0.0003092227122675484, 'samples': 12428928, 'steps': 64733, 'loss/train': 1.0506470203399658} 08/31/2021 00:56:45 - INFO - __main__ - Step 64735: {'lr': 0.0003092175565595927, 'samples': 12429120, 'steps': 64734, 'loss/train': 1.281020164489746} 08/31/2021 00:56:45 - INFO - __main__ - Step 64736: {'lr': 0.0003092124008249545, 'samples': 12429312, 'steps': 64735, 'loss/train': 0.904500424861908} 08/31/2021 00:56:45 - INFO - __main__ - Step 64737: {'lr': 0.00030920724506363614, 'samples': 12429504, 'steps': 64736, 'loss/train': 1.300517201423645} 08/31/2021 00:56:46 - INFO - __main__ - Step 64738: {'lr': 0.0003092020892756399, 'samples': 12429696, 'steps': 64737, 'loss/train': 1.2675033807754517} 08/31/2021 00:56:46 - INFO - __main__ - Step 64739: {'lr': 0.0003091969334609681, 'samples': 12429888, 'steps': 64738, 'loss/train': 1.0779526233673096} 08/31/2021 00:56:46 - INFO - __main__ - Step 64740: {'lr': 0.00030919177761962305, 'samples': 12430080, 'steps': 64739, 'loss/train': 0.028981395065784454} 08/31/2021 00:56:48 - INFO - __main__ - Step 64741: {'lr': 0.0003091866217516071, 'samples': 12430272, 'steps': 64740, 'loss/train': 0.38206127285957336} 08/31/2021 00:56:48 - INFO - __main__ - Step 64742: {'lr': 0.0003091814658569226, 'samples': 12430464, 'steps': 64741, 'loss/train': 1.7239089012145996} 08/31/2021 00:56:49 - INFO - __main__ - Step 64743: {'lr': 0.00030917630993557176, 'samples': 12430656, 'steps': 64742, 'loss/train': 0.8435982465744019} 08/31/2021 00:56:49 - INFO - __main__ - Step 64744: {'lr': 0.0003091711539875571, 'samples': 12430848, 'steps': 64743, 'loss/train': 1.3569341897964478} 08/31/2021 00:56:49 - INFO - __main__ - Step 64745: {'lr': 0.0003091659980128808, 'samples': 12431040, 'steps': 64744, 'loss/train': 1.1624677181243896} 08/31/2021 00:56:51 - INFO - __main__ - Step 64746: {'lr': 0.00030916084201154523, 'samples': 12431232, 'steps': 64745, 'loss/train': 1.1463518142700195} 08/31/2021 00:56:51 - INFO - __main__ - Step 64747: {'lr': 0.00030915568598355265, 'samples': 12431424, 'steps': 64746, 'loss/train': 1.3291568756103516} 08/31/2021 00:56:52 - INFO - __main__ - Step 64748: {'lr': 0.00030915052992890545, 'samples': 12431616, 'steps': 64747, 'loss/train': 1.159906029701233} 08/31/2021 00:56:52 - INFO - __main__ - Step 64749: {'lr': 0.00030914537384760596, 'samples': 12431808, 'steps': 64748, 'loss/train': 1.6067662239074707} 08/31/2021 00:56:52 - INFO - __main__ - Step 64750: {'lr': 0.0003091402177396564, 'samples': 12432000, 'steps': 64749, 'loss/train': 1.1436150074005127} 08/31/2021 00:56:54 - INFO - __main__ - Step 64751: {'lr': 0.0003091350616050592, 'samples': 12432192, 'steps': 64750, 'loss/train': 0.3128182291984558} 08/31/2021 00:56:55 - INFO - __main__ - Step 64752: {'lr': 0.00030912990544381677, 'samples': 12432384, 'steps': 64751, 'loss/train': 0.7258626222610474} 08/31/2021 00:56:55 - INFO - __main__ - Step 64753: {'lr': 0.0003091247492559312, 'samples': 12432576, 'steps': 64752, 'loss/train': 0.8845932483673096} 08/31/2021 00:56:55 - INFO - __main__ - Step 64754: {'lr': 0.0003091195930414049, 'samples': 12432768, 'steps': 64753, 'loss/train': 1.5305131673812866} 08/31/2021 00:56:56 - INFO - __main__ - Step 64755: {'lr': 0.00030911443680024033, 'samples': 12432960, 'steps': 64754, 'loss/train': 1.0635175704956055} 08/31/2021 00:56:57 - INFO - __main__ - Step 64756: {'lr': 0.00030910928053243963, 'samples': 12433152, 'steps': 64755, 'loss/train': 1.6347124576568604} 08/31/2021 00:56:58 - INFO - __main__ - Step 64757: {'lr': 0.00030910412423800523, 'samples': 12433344, 'steps': 64756, 'loss/train': 1.3706263303756714} 08/31/2021 00:56:58 - INFO - __main__ - Step 64758: {'lr': 0.00030909896791693947, 'samples': 12433536, 'steps': 64757, 'loss/train': 1.538267970085144} 08/31/2021 00:56:58 - INFO - __main__ - Step 64759: {'lr': 0.00030909381156924456, 'samples': 12433728, 'steps': 64758, 'loss/train': 1.239672303199768} 08/31/2021 00:56:59 - INFO - __main__ - Step 64760: {'lr': 0.0003090886551949229, 'samples': 12433920, 'steps': 64759, 'loss/train': 1.0235875844955444} 08/31/2021 00:57:00 - INFO - __main__ - Step 64761: {'lr': 0.0003090834987939768, 'samples': 12434112, 'steps': 64760, 'loss/train': 0.9938375949859619} 08/31/2021 00:57:01 - INFO - __main__ - Step 64762: {'lr': 0.00030907834236640856, 'samples': 12434304, 'steps': 64761, 'loss/train': 0.9411245584487915} 08/31/2021 00:57:01 - INFO - __main__ - Step 64763: {'lr': 0.00030907318591222056, 'samples': 12434496, 'steps': 64762, 'loss/train': 1.154252529144287} 08/31/2021 00:57:01 - INFO - __main__ - Step 64764: {'lr': 0.0003090680294314151, 'samples': 12434688, 'steps': 64763, 'loss/train': 0.9552150964736938} 08/31/2021 00:57:02 - INFO - __main__ - Step 64765: {'lr': 0.00030906287292399457, 'samples': 12434880, 'steps': 64764, 'loss/train': 1.1638356447219849} 08/31/2021 00:57:02 - INFO - __main__ - Step 64766: {'lr': 0.0003090577163899611, 'samples': 12435072, 'steps': 64765, 'loss/train': 1.0832401514053345} 08/31/2021 00:57:04 - INFO - __main__ - Step 64767: {'lr': 0.00030905255982931716, 'samples': 12435264, 'steps': 64766, 'loss/train': 0.03273583948612213} 08/31/2021 00:57:04 - INFO - __main__ - Step 64768: {'lr': 0.0003090474032420651, 'samples': 12435456, 'steps': 64767, 'loss/train': 1.4795669317245483} 08/31/2021 00:57:05 - INFO - __main__ - Step 64769: {'lr': 0.00030904224662820716, 'samples': 12435648, 'steps': 64768, 'loss/train': 1.512805461883545} 08/31/2021 00:57:05 - INFO - __main__ - Step 64770: {'lr': 0.00030903708998774573, 'samples': 12435840, 'steps': 64769, 'loss/train': 1.426193356513977} 08/31/2021 00:57:05 - INFO - __main__ - Step 64771: {'lr': 0.00030903193332068303, 'samples': 12436032, 'steps': 64770, 'loss/train': 1.1004005670547485} 08/31/2021 00:57:07 - INFO - __main__ - Step 64772: {'lr': 0.0003090267766270215, 'samples': 12436224, 'steps': 64771, 'loss/train': 0.04058600217103958} 08/31/2021 00:57:07 - INFO - __main__ - Step 64773: {'lr': 0.00030902161990676344, 'samples': 12436416, 'steps': 64772, 'loss/train': 1.1129416227340698} 08/31/2021 00:57:08 - INFO - __main__ - Step 64774: {'lr': 0.00030901646315991104, 'samples': 12436608, 'steps': 64773, 'loss/train': 1.2103345394134521} 08/31/2021 00:57:08 - INFO - __main__ - Step 64775: {'lr': 0.00030901130638646686, 'samples': 12436800, 'steps': 64774, 'loss/train': 1.3397797346115112} 08/31/2021 00:57:08 - INFO - __main__ - Step 64776: {'lr': 0.00030900614958643305, 'samples': 12436992, 'steps': 64775, 'loss/train': 1.4227060079574585} 08/31/2021 00:57:10 - INFO - __main__ - Step 64777: {'lr': 0.00030900099275981194, 'samples': 12437184, 'steps': 64776, 'loss/train': 0.49914121627807617} 08/31/2021 00:57:11 - INFO - __main__ - Step 64778: {'lr': 0.000308995835906606, 'samples': 12437376, 'steps': 64777, 'loss/train': 0.7293642163276672} 08/31/2021 00:57:11 - INFO - __main__ - Step 64779: {'lr': 0.00030899067902681734, 'samples': 12437568, 'steps': 64778, 'loss/train': 0.020897358655929565} 08/31/2021 00:57:11 - INFO - __main__ - Step 64780: {'lr': 0.0003089855221204484, 'samples': 12437760, 'steps': 64779, 'loss/train': 1.0851130485534668} 08/31/2021 00:57:12 - INFO - __main__ - Step 64781: {'lr': 0.0003089803651875015, 'samples': 12437952, 'steps': 64780, 'loss/train': 1.1419596672058105} 08/31/2021 00:57:12 - INFO - __main__ - Step 64782: {'lr': 0.000308975208227979, 'samples': 12438144, 'steps': 64781, 'loss/train': 0.7156907916069031} 08/31/2021 00:57:12 - INFO - __main__ - Step 64783: {'lr': 0.0003089700512418831, 'samples': 12438336, 'steps': 64782, 'loss/train': 1.03411865234375} 08/31/2021 00:57:14 - INFO - __main__ - Step 64784: {'lr': 0.00030896489422921623, 'samples': 12438528, 'steps': 64783, 'loss/train': 1.2324186563491821} 08/31/2021 00:57:14 - INFO - __main__ - Step 64785: {'lr': 0.00030895973718998075, 'samples': 12438720, 'steps': 64784, 'loss/train': 0.7365874648094177} 08/31/2021 00:57:15 - INFO - __main__ - Step 64786: {'lr': 0.00030895458012417896, 'samples': 12438912, 'steps': 64785, 'loss/train': 1.0455360412597656} 08/31/2021 00:57:15 - INFO - __main__ - Step 64787: {'lr': 0.000308949423031813, 'samples': 12439104, 'steps': 64786, 'loss/train': 2.129873275756836} 08/31/2021 00:57:15 - INFO - __main__ - Step 64788: {'lr': 0.0003089442659128854, 'samples': 12439296, 'steps': 64787, 'loss/train': 1.5427321195602417} 08/31/2021 00:57:18 - INFO - __main__ - Step 64789: {'lr': 0.00030893910876739845, 'samples': 12439488, 'steps': 64788, 'loss/train': 3.5220224857330322} 08/31/2021 00:57:18 - INFO - __main__ - Step 64790: {'lr': 0.00030893395159535444, 'samples': 12439680, 'steps': 64789, 'loss/train': 0.921168327331543} 08/31/2021 00:57:18 - INFO - __main__ - Step 64791: {'lr': 0.0003089287943967557, 'samples': 12439872, 'steps': 64790, 'loss/train': 1.4034857749938965} 08/31/2021 00:57:19 - INFO - __main__ - Step 64792: {'lr': 0.00030892363717160455, 'samples': 12440064, 'steps': 64791, 'loss/train': 1.4999855756759644} 08/31/2021 00:57:19 - INFO - __main__ - Step 64793: {'lr': 0.00030891847991990334, 'samples': 12440256, 'steps': 64792, 'loss/train': 1.1757062673568726} 08/31/2021 00:57:20 - INFO - __main__ - Step 64794: {'lr': 0.00030891332264165435, 'samples': 12440448, 'steps': 64793, 'loss/train': 0.6723887920379639} 08/31/2021 00:57:21 - INFO - __main__ - Step 64795: {'lr': 0.0003089081653368599, 'samples': 12440640, 'steps': 64794, 'loss/train': 0.9212010502815247} 08/31/2021 00:57:21 - INFO - __main__ - Step 64796: {'lr': 0.00030890300800552237, 'samples': 12440832, 'steps': 64795, 'loss/train': 2.197715997695923} 08/31/2021 00:57:22 - INFO - __main__ - Step 64797: {'lr': 0.00030889785064764405, 'samples': 12441024, 'steps': 64796, 'loss/train': 1.724780559539795} 08/31/2021 00:57:22 - INFO - __main__ - Step 64798: {'lr': 0.00030889269326322727, 'samples': 12441216, 'steps': 64797, 'loss/train': 1.486958622932434} 08/31/2021 00:57:22 - INFO - __main__ - Step 64799: {'lr': 0.0003088875358522744, 'samples': 12441408, 'steps': 64798, 'loss/train': 0.8690364956855774} 08/31/2021 00:57:24 - INFO - __main__ - Step 64800: {'lr': 0.00030888237841478764, 'samples': 12441600, 'steps': 64799, 'loss/train': 1.622388482093811} 08/31/2021 00:57:25 - INFO - __main__ - Step 64801: {'lr': 0.0003088772209507694, 'samples': 12441792, 'steps': 64800, 'loss/train': 1.6668375730514526} 08/31/2021 00:57:25 - INFO - __main__ - Step 64802: {'lr': 0.000308872063460222, 'samples': 12441984, 'steps': 64801, 'loss/train': 1.3714725971221924} 08/31/2021 00:57:25 - INFO - __main__ - Step 64803: {'lr': 0.0003088669059431478, 'samples': 12442176, 'steps': 64802, 'loss/train': 1.1890090703964233} 08/31/2021 00:57:26 - INFO - __main__ - Step 64804: {'lr': 0.000308861748399549, 'samples': 12442368, 'steps': 64803, 'loss/train': 1.019775152206421} 08/31/2021 00:57:27 - INFO - __main__ - Step 64805: {'lr': 0.00030885659082942806, 'samples': 12442560, 'steps': 64804, 'loss/train': 1.3989399671554565} 08/31/2021 00:57:27 - INFO - __main__ - Step 64806: {'lr': 0.00030885143323278717, 'samples': 12442752, 'steps': 64805, 'loss/train': 1.8930106163024902} 08/31/2021 00:57:28 - INFO - __main__ - Step 64807: {'lr': 0.00030884627560962886, 'samples': 12442944, 'steps': 64806, 'loss/train': 1.0389580726623535} 08/31/2021 00:57:28 - INFO - __main__ - Step 64808: {'lr': 0.00030884111795995525, 'samples': 12443136, 'steps': 64807, 'loss/train': 1.3389493227005005} 08/31/2021 00:57:29 - INFO - __main__ - Step 64809: {'lr': 0.0003088359602837688, 'samples': 12443328, 'steps': 64808, 'loss/train': 1.4509284496307373} 08/31/2021 00:57:30 - INFO - __main__ - Step 64810: {'lr': 0.0003088308025810717, 'samples': 12443520, 'steps': 64809, 'loss/train': 1.4586925506591797} 08/31/2021 00:57:30 - INFO - __main__ - Step 64811: {'lr': 0.0003088256448518664, 'samples': 12443712, 'steps': 64810, 'loss/train': 1.1518925428390503} 08/31/2021 00:57:31 - INFO - __main__ - Step 64812: {'lr': 0.00030882048709615515, 'samples': 12443904, 'steps': 64811, 'loss/train': 0.6242234706878662} 08/31/2021 00:57:31 - INFO - __main__ - Step 64813: {'lr': 0.00030881532931394026, 'samples': 12444096, 'steps': 64812, 'loss/train': 0.9438557028770447} 08/31/2021 00:57:32 - INFO - __main__ - Step 64814: {'lr': 0.00030881017150522416, 'samples': 12444288, 'steps': 64813, 'loss/train': 0.9675384163856506} 08/31/2021 00:57:33 - INFO - __main__ - Step 64815: {'lr': 0.0003088050136700091, 'samples': 12444480, 'steps': 64814, 'loss/train': 0.8253622055053711} 08/31/2021 00:57:34 - INFO - __main__ - Step 64816: {'lr': 0.00030879985580829734, 'samples': 12444672, 'steps': 64815, 'loss/train': 1.3524582386016846} 08/31/2021 00:57:34 - INFO - __main__ - Step 64817: {'lr': 0.0003087946979200913, 'samples': 12444864, 'steps': 64816, 'loss/train': 0.6528863906860352} 08/31/2021 00:57:34 - INFO - __main__ - Step 64818: {'lr': 0.0003087895400053933, 'samples': 12445056, 'steps': 64817, 'loss/train': 1.4846203327178955} 08/31/2021 00:57:35 - INFO - __main__ - Step 64819: {'lr': 0.0003087843820642057, 'samples': 12445248, 'steps': 64818, 'loss/train': 2.1463167667388916} 08/31/2021 00:57:36 - INFO - __main__ - Step 64820: {'lr': 0.00030877922409653063, 'samples': 12445440, 'steps': 64819, 'loss/train': 1.1949539184570312} 08/31/2021 00:57:37 - INFO - __main__ - Step 64821: {'lr': 0.0003087740661023706, 'samples': 12445632, 'steps': 64820, 'loss/train': 0.9958912134170532} 08/31/2021 00:57:37 - INFO - __main__ - Step 64822: {'lr': 0.0003087689080817279, 'samples': 12445824, 'steps': 64821, 'loss/train': 1.1968326568603516} 08/31/2021 00:57:38 - INFO - __main__ - Step 64823: {'lr': 0.0003087637500346048, 'samples': 12446016, 'steps': 64822, 'loss/train': 1.1108790636062622} 08/31/2021 00:57:38 - INFO - __main__ - Step 64824: {'lr': 0.0003087585919610037, 'samples': 12446208, 'steps': 64823, 'loss/train': 0.10323929786682129} 08/31/2021 00:57:38 - INFO - __main__ - Step 64825: {'lr': 0.0003087534338609269, 'samples': 12446400, 'steps': 64824, 'loss/train': 1.1725164651870728} 08/31/2021 00:57:40 - INFO - __main__ - Step 64826: {'lr': 0.0003087482757343767, 'samples': 12446592, 'steps': 64825, 'loss/train': 1.577147364616394} 08/31/2021 00:57:40 - INFO - __main__ - Step 64827: {'lr': 0.00030874311758135535, 'samples': 12446784, 'steps': 64826, 'loss/train': 1.1892585754394531} 08/31/2021 00:57:40 - INFO - __main__ - Step 64828: {'lr': 0.0003087379594018653, 'samples': 12446976, 'steps': 64827, 'loss/train': 1.108670949935913} 08/31/2021 00:57:41 - INFO - __main__ - Step 64829: {'lr': 0.0003087328011959089, 'samples': 12447168, 'steps': 64828, 'loss/train': 1.6729233264923096} 08/31/2021 00:57:41 - INFO - __main__ - Step 64830: {'lr': 0.0003087276429634884, 'samples': 12447360, 'steps': 64829, 'loss/train': 1.0220612287521362} 08/31/2021 00:57:43 - INFO - __main__ - Step 64831: {'lr': 0.0003087224847046061, 'samples': 12447552, 'steps': 64830, 'loss/train': 1.7252289056777954} 08/31/2021 00:57:43 - INFO - __main__ - Step 64832: {'lr': 0.0003087173264192643, 'samples': 12447744, 'steps': 64831, 'loss/train': 0.10856522619724274} 08/31/2021 00:57:43 - INFO - __main__ - Step 64833: {'lr': 0.00030871216810746544, 'samples': 12447936, 'steps': 64832, 'loss/train': 0.9146488904953003} 08/31/2021 00:57:44 - INFO - __main__ - Step 64834: {'lr': 0.0003087070097692118, 'samples': 12448128, 'steps': 64833, 'loss/train': 1.1296987533569336} 08/31/2021 00:57:44 - INFO - __main__ - Step 64835: {'lr': 0.00030870185140450564, 'samples': 12448320, 'steps': 64834, 'loss/train': 1.676706314086914} 08/31/2021 00:57:46 - INFO - __main__ - Step 64836: {'lr': 0.00030869669301334936, 'samples': 12448512, 'steps': 64835, 'loss/train': 0.35564327239990234} 08/31/2021 00:57:47 - INFO - __main__ - Step 64837: {'lr': 0.0003086915345957452, 'samples': 12448704, 'steps': 64836, 'loss/train': 1.3305153846740723} 08/31/2021 00:57:47 - INFO - __main__ - Step 64838: {'lr': 0.0003086863761516956, 'samples': 12448896, 'steps': 64837, 'loss/train': 0.026679271832108498} 08/31/2021 00:57:47 - INFO - __main__ - Step 64839: {'lr': 0.0003086812176812028, 'samples': 12449088, 'steps': 64838, 'loss/train': 1.8961358070373535} 08/31/2021 00:57:48 - INFO - __main__ - Step 64840: {'lr': 0.00030867605918426916, 'samples': 12449280, 'steps': 64839, 'loss/train': 1.2597265243530273} 08/31/2021 00:57:48 - INFO - __main__ - Step 64841: {'lr': 0.000308670900660897, 'samples': 12449472, 'steps': 64840, 'loss/train': 1.1355482339859009} 08/31/2021 00:57:50 - INFO - __main__ - Step 64842: {'lr': 0.00030866574211108863, 'samples': 12449664, 'steps': 64841, 'loss/train': 0.7605482935905457} 08/31/2021 00:57:51 - INFO - __main__ - Step 64843: {'lr': 0.0003086605835348464, 'samples': 12449856, 'steps': 64842, 'loss/train': 1.8842616081237793} 08/31/2021 00:57:51 - INFO - __main__ - Step 64844: {'lr': 0.0003086554249321726, 'samples': 12450048, 'steps': 64843, 'loss/train': 1.0175801515579224} 08/31/2021 00:57:52 - INFO - __main__ - Step 64845: {'lr': 0.00030865026630306954, 'samples': 12450240, 'steps': 64844, 'loss/train': 1.524855375289917} 08/31/2021 00:57:52 - INFO - __main__ - Step 64846: {'lr': 0.0003086451076475396, 'samples': 12450432, 'steps': 64845, 'loss/train': 0.8589615225791931} 08/31/2021 00:57:52 - INFO - __main__ - Step 64847: {'lr': 0.00030863994896558513, 'samples': 12450624, 'steps': 64846, 'loss/train': 1.2992236614227295} 08/31/2021 00:57:54 - INFO - __main__ - Step 64848: {'lr': 0.0003086347902572083, 'samples': 12450816, 'steps': 64847, 'loss/train': 1.6388241052627563} 08/31/2021 00:57:54 - INFO - __main__ - Step 64849: {'lr': 0.0003086296315224116, 'samples': 12451008, 'steps': 64848, 'loss/train': 1.480554223060608} 08/31/2021 00:57:54 - INFO - __main__ - Step 64850: {'lr': 0.00030862447276119734, 'samples': 12451200, 'steps': 64849, 'loss/train': 1.1787104606628418} 08/31/2021 00:57:55 - INFO - __main__ - Step 64851: {'lr': 0.0003086193139735677, 'samples': 12451392, 'steps': 64850, 'loss/train': 1.5321199893951416} 08/31/2021 00:57:55 - INFO - __main__ - Step 64852: {'lr': 0.00030861415515952517, 'samples': 12451584, 'steps': 64851, 'loss/train': 2.110417366027832} 08/31/2021 00:57:57 - INFO - __main__ - Step 64853: {'lr': 0.000308608996319072, 'samples': 12451776, 'steps': 64852, 'loss/train': 0.9863107800483704} 08/31/2021 00:57:57 - INFO - __main__ - Step 64854: {'lr': 0.0003086038374522105, 'samples': 12451968, 'steps': 64853, 'loss/train': 0.7349036931991577} 08/31/2021 00:57:58 - INFO - __main__ - Step 64855: {'lr': 0.00030859867855894296, 'samples': 12452160, 'steps': 64854, 'loss/train': 0.9009580612182617} 08/31/2021 00:57:58 - INFO - __main__ - Step 64856: {'lr': 0.00030859351963927184, 'samples': 12452352, 'steps': 64855, 'loss/train': 0.7824165225028992} 08/31/2021 00:57:58 - INFO - __main__ - Step 64857: {'lr': 0.00030858836069319937, 'samples': 12452544, 'steps': 64856, 'loss/train': 1.406494379043579} 08/31/2021 00:58:00 - INFO - __main__ - Step 64858: {'lr': 0.00030858320172072787, 'samples': 12452736, 'steps': 64857, 'loss/train': 1.4573338031768799} 08/31/2021 00:58:01 - INFO - __main__ - Step 64859: {'lr': 0.00030857804272185974, 'samples': 12452928, 'steps': 64858, 'loss/train': 0.9519951343536377} 08/31/2021 00:58:01 - INFO - __main__ - Step 64860: {'lr': 0.0003085728836965972, 'samples': 12453120, 'steps': 64859, 'loss/train': 1.2283339500427246} 08/31/2021 00:58:01 - INFO - __main__ - Step 64861: {'lr': 0.0003085677246449426, 'samples': 12453312, 'steps': 64860, 'loss/train': 0.029279261827468872} 08/31/2021 00:58:02 - INFO - __main__ - Step 64862: {'lr': 0.00030856256556689835, 'samples': 12453504, 'steps': 64861, 'loss/train': 0.10648781061172485} 08/31/2021 00:58:02 - INFO - __main__ - Step 64863: {'lr': 0.0003085574064624666, 'samples': 12453696, 'steps': 64862, 'loss/train': 0.9724735021591187} 08/31/2021 00:58:04 - INFO - __main__ - Step 64864: {'lr': 0.00030855224733164987, 'samples': 12453888, 'steps': 64863, 'loss/train': 1.4249351024627686} 08/31/2021 00:58:04 - INFO - __main__ - Step 64865: {'lr': 0.0003085470881744504, 'samples': 12454080, 'steps': 64864, 'loss/train': 1.2841360569000244} 08/31/2021 00:58:05 - INFO - __main__ - Step 64866: {'lr': 0.0003085419289908705, 'samples': 12454272, 'steps': 64865, 'loss/train': 0.9939422011375427} 08/31/2021 00:58:05 - INFO - __main__ - Step 64867: {'lr': 0.00030853676978091256, 'samples': 12454464, 'steps': 64866, 'loss/train': 1.2381532192230225} 08/31/2021 00:58:05 - INFO - __main__ - Step 64868: {'lr': 0.0003085316105445788, 'samples': 12454656, 'steps': 64867, 'loss/train': 0.022575512528419495} 08/31/2021 00:58:06 - INFO - __main__ - Step 64869: {'lr': 0.00030852645128187157, 'samples': 12454848, 'steps': 64868, 'loss/train': 0.13251350820064545} 08/31/2021 00:58:08 - INFO - __main__ - Step 64870: {'lr': 0.00030852129199279325, 'samples': 12455040, 'steps': 64869, 'loss/train': 1.4519857168197632} 08/31/2021 00:58:08 - INFO - __main__ - Step 64871: {'lr': 0.0003085161326773461, 'samples': 12455232, 'steps': 64870, 'loss/train': 1.0221550464630127} 08/31/2021 00:58:09 - INFO - __main__ - Step 64872: {'lr': 0.0003085109733355326, 'samples': 12455424, 'steps': 64871, 'loss/train': 1.5350313186645508} 08/31/2021 00:58:09 - INFO - __main__ - Step 64873: {'lr': 0.00030850581396735493, 'samples': 12455616, 'steps': 64872, 'loss/train': 1.279771327972412} 08/31/2021 00:58:09 - INFO - __main__ - Step 64874: {'lr': 0.0003085006545728154, 'samples': 12455808, 'steps': 64873, 'loss/train': 1.3906196355819702} 08/31/2021 00:58:10 - INFO - __main__ - Step 64875: {'lr': 0.00030849549515191637, 'samples': 12456000, 'steps': 64874, 'loss/train': 1.5871912240982056} 08/31/2021 00:58:11 - INFO - __main__ - Step 64876: {'lr': 0.00030849033570466017, 'samples': 12456192, 'steps': 64875, 'loss/train': 1.3300929069519043} 08/31/2021 00:58:12 - INFO - __main__ - Step 64877: {'lr': 0.0003084851762310492, 'samples': 12456384, 'steps': 64876, 'loss/train': 1.2610117197036743} 08/31/2021 00:58:12 - INFO - __main__ - Step 64878: {'lr': 0.0003084800167310856, 'samples': 12456576, 'steps': 64877, 'loss/train': 1.739802360534668} 08/31/2021 00:58:13 - INFO - __main__ - Step 64879: {'lr': 0.00030847485720477194, 'samples': 12456768, 'steps': 64878, 'loss/train': 1.3658299446105957} 08/31/2021 00:58:13 - INFO - __main__ - Step 64880: {'lr': 0.0003084696976521103, 'samples': 12456960, 'steps': 64879, 'loss/train': 1.556289792060852} 08/31/2021 00:58:13 - INFO - __main__ - Step 64881: {'lr': 0.00030846453807310316, 'samples': 12457152, 'steps': 64880, 'loss/train': 0.2924835979938507} 08/31/2021 00:58:15 - INFO - __main__ - Step 64882: {'lr': 0.0003084593784677527, 'samples': 12457344, 'steps': 64881, 'loss/train': 1.1888346672058105} 08/31/2021 00:58:15 - INFO - __main__ - Step 64883: {'lr': 0.0003084542188360615, 'samples': 12457536, 'steps': 64882, 'loss/train': 1.2761176824569702} 08/31/2021 00:58:16 - INFO - __main__ - Step 64884: {'lr': 0.0003084490591780317, 'samples': 12457728, 'steps': 64883, 'loss/train': 1.3103601932525635} 08/31/2021 00:58:16 - INFO - __main__ - Step 64885: {'lr': 0.0003084438994936656, 'samples': 12457920, 'steps': 64884, 'loss/train': 1.6931712627410889} 08/31/2021 00:58:16 - INFO - __main__ - Step 64886: {'lr': 0.00030843873978296564, 'samples': 12458112, 'steps': 64885, 'loss/train': 0.7093930840492249} 08/31/2021 00:58:19 - INFO - __main__ - Step 64887: {'lr': 0.000308433580045934, 'samples': 12458304, 'steps': 64886, 'loss/train': 1.1935299634933472} 08/31/2021 00:58:19 - INFO - __main__ - Step 64888: {'lr': 0.0003084284202825732, 'samples': 12458496, 'steps': 64887, 'loss/train': 1.2779301404953003} 08/31/2021 00:58:19 - INFO - __main__ - Step 64889: {'lr': 0.0003084232604928854, 'samples': 12458688, 'steps': 64888, 'loss/train': 0.2342061996459961} 08/31/2021 00:58:20 - INFO - __main__ - Step 64890: {'lr': 0.0003084181006768729, 'samples': 12458880, 'steps': 64889, 'loss/train': 0.5603322982788086} 08/31/2021 00:58:20 - INFO - __main__ - Step 64891: {'lr': 0.0003084129408345382, 'samples': 12459072, 'steps': 64890, 'loss/train': 1.253447413444519} 08/31/2021 00:58:21 - INFO - __main__ - Step 64892: {'lr': 0.0003084077809658835, 'samples': 12459264, 'steps': 64891, 'loss/train': 0.48431047797203064} 08/31/2021 00:58:22 - INFO - __main__ - Step 64893: {'lr': 0.0003084026210709112, 'samples': 12459456, 'steps': 64892, 'loss/train': 1.133331060409546} 08/31/2021 00:58:22 - INFO - __main__ - Step 64894: {'lr': 0.00030839746114962356, 'samples': 12459648, 'steps': 64893, 'loss/train': 1.2975109815597534} 08/31/2021 00:58:23 - INFO - __main__ - Step 64895: {'lr': 0.00030839230120202296, 'samples': 12459840, 'steps': 64894, 'loss/train': 1.50920832157135} 08/31/2021 00:58:23 - INFO - __main__ - Step 64896: {'lr': 0.00030838714122811164, 'samples': 12460032, 'steps': 64895, 'loss/train': 1.3947980403900146} 08/31/2021 00:58:24 - INFO - __main__ - Step 64897: {'lr': 0.00030838198122789195, 'samples': 12460224, 'steps': 64896, 'loss/train': 1.4735513925552368} 08/31/2021 00:58:25 - INFO - __main__ - Step 64898: {'lr': 0.00030837682120136626, 'samples': 12460416, 'steps': 64897, 'loss/train': 1.4938985109329224} 08/31/2021 00:58:25 - INFO - __main__ - Step 64899: {'lr': 0.00030837166114853695, 'samples': 12460608, 'steps': 64898, 'loss/train': 2.099113702774048} 08/31/2021 00:58:26 - INFO - __main__ - Step 64900: {'lr': 0.00030836650106940615, 'samples': 12460800, 'steps': 64899, 'loss/train': 1.3383136987686157} 08/31/2021 00:58:26 - INFO - __main__ - Step 64901: {'lr': 0.0003083613409639764, 'samples': 12460992, 'steps': 64900, 'loss/train': 1.053199052810669} 08/31/2021 00:58:28 - INFO - __main__ - Step 64902: {'lr': 0.00030835618083224986, 'samples': 12461184, 'steps': 64901, 'loss/train': 1.5918221473693848} 08/31/2021 00:58:29 - INFO - __main__ - Step 64903: {'lr': 0.00030835102067422893, 'samples': 12461376, 'steps': 64902, 'loss/train': 0.983816385269165} 08/31/2021 00:58:29 - INFO - __main__ - Step 64904: {'lr': 0.000308345860489916, 'samples': 12461568, 'steps': 64903, 'loss/train': 1.290775179862976} 08/31/2021 00:58:29 - INFO - __main__ - Step 64905: {'lr': 0.00030834070027931326, 'samples': 12461760, 'steps': 64904, 'loss/train': 0.9349378347396851} 08/31/2021 00:58:30 - INFO - __main__ - Step 64906: {'lr': 0.00030833554004242313, 'samples': 12461952, 'steps': 64905, 'loss/train': 1.4281402826309204} 08/31/2021 00:58:31 - INFO - __main__ - Step 64907: {'lr': 0.0003083303797792479, 'samples': 12462144, 'steps': 64906, 'loss/train': 1.3589333295822144} 08/31/2021 00:58:32 - INFO - __main__ - Step 64908: {'lr': 0.0003083252194897899, 'samples': 12462336, 'steps': 64907, 'loss/train': 0.299359530210495} 08/31/2021 00:58:32 - INFO - __main__ - Step 64909: {'lr': 0.00030832005917405146, 'samples': 12462528, 'steps': 64908, 'loss/train': 1.1789755821228027} 08/31/2021 00:58:32 - INFO - __main__ - Step 64910: {'lr': 0.0003083148988320349, 'samples': 12462720, 'steps': 64909, 'loss/train': 1.2521158456802368} 08/31/2021 00:58:33 - INFO - __main__ - Step 64911: {'lr': 0.00030830973846374257, 'samples': 12462912, 'steps': 64910, 'loss/train': 1.4161477088928223} 08/31/2021 00:58:34 - INFO - __main__ - Step 64912: {'lr': 0.00030830457806917664, 'samples': 12463104, 'steps': 64911, 'loss/train': 1.4622178077697754} 08/31/2021 00:58:35 - INFO - __main__ - Step 64913: {'lr': 0.0003082994176483398, 'samples': 12463296, 'steps': 64912, 'loss/train': 1.411734700202942} 08/31/2021 00:58:35 - INFO - __main__ - Step 64914: {'lr': 0.00030829425720123397, 'samples': 12463488, 'steps': 64913, 'loss/train': 1.0695973634719849} 08/31/2021 00:58:35 - INFO - __main__ - Step 64915: {'lr': 0.0003082890967278617, 'samples': 12463680, 'steps': 64914, 'loss/train': 1.3614699840545654} 08/31/2021 00:58:36 - INFO - __main__ - Step 64916: {'lr': 0.0003082839362282253, 'samples': 12463872, 'steps': 64915, 'loss/train': 1.6109020709991455} 08/31/2021 00:58:37 - INFO - __main__ - Step 64917: {'lr': 0.0003082787757023269, 'samples': 12464064, 'steps': 64916, 'loss/train': 1.0214217901229858} 08/31/2021 00:58:38 - INFO - __main__ - Step 64918: {'lr': 0.0003082736151501691, 'samples': 12464256, 'steps': 64917, 'loss/train': 0.8537688255310059} 08/31/2021 00:58:38 - INFO - __main__ - Step 64919: {'lr': 0.0003082684545717541, 'samples': 12464448, 'steps': 64918, 'loss/train': 0.09329164028167725} 08/31/2021 00:58:39 - INFO - __main__ - Step 64920: {'lr': 0.0003082632939670843, 'samples': 12464640, 'steps': 64919, 'loss/train': 1.4768273830413818} 08/31/2021 00:58:39 - INFO - __main__ - Step 64921: {'lr': 0.0003082581333361619, 'samples': 12464832, 'steps': 64920, 'loss/train': 0.0321832001209259} 08/31/2021 00:58:39 - INFO - __main__ - Step 64922: {'lr': 0.0003082529726789893, 'samples': 12465024, 'steps': 64921, 'loss/train': 0.6213216781616211} 08/31/2021 00:58:41 - INFO - __main__ - Step 64923: {'lr': 0.0003082478119955687, 'samples': 12465216, 'steps': 64922, 'loss/train': 1.3190581798553467} 08/31/2021 00:58:42 - INFO - __main__ - Step 64924: {'lr': 0.00030824265128590267, 'samples': 12465408, 'steps': 64923, 'loss/train': 1.381280541419983} 08/31/2021 00:58:42 - INFO - __main__ - Step 64925: {'lr': 0.00030823749054999336, 'samples': 12465600, 'steps': 64924, 'loss/train': 1.2448657751083374} 08/31/2021 00:58:42 - INFO - __main__ - Step 64926: {'lr': 0.00030823232978784317, 'samples': 12465792, 'steps': 64925, 'loss/train': 0.9187562465667725} 08/31/2021 00:58:43 - INFO - __main__ - Step 64927: {'lr': 0.00030822716899945435, 'samples': 12465984, 'steps': 64926, 'loss/train': 0.041790883988142014} 08/31/2021 00:58:44 - INFO - __main__ - Step 64928: {'lr': 0.00030822200818482926, 'samples': 12466176, 'steps': 64927, 'loss/train': 1.7324942350387573} 08/31/2021 00:58:45 - INFO - __main__ - Step 64929: {'lr': 0.0003082168473439702, 'samples': 12466368, 'steps': 64928, 'loss/train': 1.4691295623779297} 08/31/2021 00:58:45 - INFO - __main__ - Step 64930: {'lr': 0.0003082116864768796, 'samples': 12466560, 'steps': 64929, 'loss/train': 0.926102876663208} 08/31/2021 00:58:45 - INFO - __main__ - Step 64931: {'lr': 0.00030820652558355963, 'samples': 12466752, 'steps': 64930, 'loss/train': 1.9054216146469116} 08/31/2021 00:58:46 - INFO - __main__ - Step 64932: {'lr': 0.00030820136466401277, 'samples': 12466944, 'steps': 64931, 'loss/train': 1.1337522268295288} 08/31/2021 00:58:47 - INFO - __main__ - Step 64933: {'lr': 0.0003081962037182413, 'samples': 12467136, 'steps': 64932, 'loss/train': 1.5095829963684082} 08/31/2021 00:58:48 - INFO - __main__ - Step 64934: {'lr': 0.00030819104274624744, 'samples': 12467328, 'steps': 64933, 'loss/train': 1.8218368291854858} 08/31/2021 00:58:48 - INFO - __main__ - Step 64935: {'lr': 0.0003081858817480336, 'samples': 12467520, 'steps': 64934, 'loss/train': 1.669721245765686} 08/31/2021 00:58:48 - INFO - __main__ - Step 64936: {'lr': 0.0003081807207236021, 'samples': 12467712, 'steps': 64935, 'loss/train': 1.0399378538131714} 08/31/2021 00:58:49 - INFO - __main__ - Step 64937: {'lr': 0.00030817555967295533, 'samples': 12467904, 'steps': 64936, 'loss/train': 1.0518404245376587} 08/31/2021 00:58:49 - INFO - __main__ - Step 64938: {'lr': 0.0003081703985960955, 'samples': 12468096, 'steps': 64937, 'loss/train': 1.1786777973175049} 08/31/2021 00:58:50 - INFO - __main__ - Step 64939: {'lr': 0.000308165237493025, 'samples': 12468288, 'steps': 64938, 'loss/train': 1.0878039598464966} 08/31/2021 00:58:51 - INFO - __main__ - Step 64940: {'lr': 0.0003081600763637461, 'samples': 12468480, 'steps': 64939, 'loss/train': 1.4129570722579956} 08/31/2021 00:58:51 - INFO - __main__ - Step 64941: {'lr': 0.0003081549152082612, 'samples': 12468672, 'steps': 64940, 'loss/train': 1.5191045999526978} 08/31/2021 00:58:52 - INFO - __main__ - Step 64942: {'lr': 0.0003081497540265726, 'samples': 12468864, 'steps': 64941, 'loss/train': 1.2825582027435303} 08/31/2021 00:58:52 - INFO - __main__ - Step 64943: {'lr': 0.0003081445928186827, 'samples': 12469056, 'steps': 64942, 'loss/train': 1.4433789253234863} 08/31/2021 00:58:53 - INFO - __main__ - Step 64944: {'lr': 0.0003081394315845936, 'samples': 12469248, 'steps': 64943, 'loss/train': 1.6938477754592896} 08/31/2021 00:58:54 - INFO - __main__ - Step 64945: {'lr': 0.0003081342703243078, 'samples': 12469440, 'steps': 64944, 'loss/train': 1.0518877506256104} 08/31/2021 00:58:54 - INFO - __main__ - Step 64946: {'lr': 0.0003081291090378276, 'samples': 12469632, 'steps': 64945, 'loss/train': 1.361849308013916} 08/31/2021 00:58:54 - INFO - __main__ - Step 64947: {'lr': 0.00030812394772515534, 'samples': 12469824, 'steps': 64946, 'loss/train': 1.2726980447769165} 08/31/2021 00:58:55 - INFO - __main__ - Step 64948: {'lr': 0.0003081187863862934, 'samples': 12470016, 'steps': 64947, 'loss/train': 1.551000952720642} 08/31/2021 00:58:56 - INFO - __main__ - Step 64949: {'lr': 0.00030811362502124396, 'samples': 12470208, 'steps': 64948, 'loss/train': 1.4381647109985352} 08/31/2021 00:58:57 - INFO - __main__ - Step 64950: {'lr': 0.0003081084636300094, 'samples': 12470400, 'steps': 64949, 'loss/train': 1.5460752248764038} 08/31/2021 00:58:57 - INFO - __main__ - Step 64951: {'lr': 0.0003081033022125921, 'samples': 12470592, 'steps': 64950, 'loss/train': 0.6648134589195251} 08/31/2021 00:58:58 - INFO - __main__ - Step 64952: {'lr': 0.0003080981407689943, 'samples': 12470784, 'steps': 64951, 'loss/train': 1.2585463523864746} 08/31/2021 00:58:58 - INFO - __main__ - Step 64953: {'lr': 0.00030809297929921837, 'samples': 12470976, 'steps': 64952, 'loss/train': 1.0065048933029175} 08/31/2021 00:59:00 - INFO - __main__ - Step 64954: {'lr': 0.00030808781780326675, 'samples': 12471168, 'steps': 64953, 'loss/train': 0.09775831550359726} 08/31/2021 00:59:00 - INFO - __main__ - Step 64955: {'lr': 0.0003080826562811415, 'samples': 12471360, 'steps': 64954, 'loss/train': 1.8003623485565186} 08/31/2021 00:59:00 - INFO - __main__ - Step 64956: {'lr': 0.0003080774947328452, 'samples': 12471552, 'steps': 64955, 'loss/train': 1.576063632965088} 08/31/2021 00:59:01 - INFO - __main__ - Step 64957: {'lr': 0.00030807233315838006, 'samples': 12471744, 'steps': 64956, 'loss/train': 1.1665078401565552} 08/31/2021 00:59:01 - INFO - __main__ - Step 64958: {'lr': 0.0003080671715577484, 'samples': 12471936, 'steps': 64957, 'loss/train': 1.5644288063049316} 08/31/2021 00:59:01 - INFO - __main__ - Step 64959: {'lr': 0.00030806200993095255, 'samples': 12472128, 'steps': 64958, 'loss/train': 1.362369179725647} 08/31/2021 00:59:03 - INFO - __main__ - Step 64960: {'lr': 0.00030805684827799496, 'samples': 12472320, 'steps': 64959, 'loss/train': 1.11087965965271} 08/31/2021 00:59:04 - INFO - __main__ - Step 64961: {'lr': 0.0003080516865988778, 'samples': 12472512, 'steps': 64960, 'loss/train': 0.8220141530036926} 08/31/2021 00:59:04 - INFO - __main__ - Step 64962: {'lr': 0.00030804652489360343, 'samples': 12472704, 'steps': 64961, 'loss/train': 1.209451675415039} 08/31/2021 00:59:05 - INFO - __main__ - Step 64963: {'lr': 0.0003080413631621741, 'samples': 12472896, 'steps': 64962, 'loss/train': 0.9170351624488831} 08/31/2021 00:59:05 - INFO - __main__ - Step 64964: {'lr': 0.0003080362014045923, 'samples': 12473088, 'steps': 64963, 'loss/train': 1.4717118740081787} 08/31/2021 00:59:07 - INFO - __main__ - Step 64965: {'lr': 0.0003080310396208603, 'samples': 12473280, 'steps': 64964, 'loss/train': 1.5329012870788574} 08/31/2021 00:59:07 - INFO - __main__ - Step 64966: {'lr': 0.00030802587781098045, 'samples': 12473472, 'steps': 64965, 'loss/train': 0.7613576650619507} 08/31/2021 00:59:08 - INFO - __main__ - Step 64967: {'lr': 0.000308020715974955, 'samples': 12473664, 'steps': 64966, 'loss/train': 1.2622435092926025} 08/31/2021 00:59:08 - INFO - __main__ - Step 64968: {'lr': 0.00030801555411278633, 'samples': 12473856, 'steps': 64967, 'loss/train': 1.6166108846664429} 08/31/2021 00:59:08 - INFO - __main__ - Step 64969: {'lr': 0.0003080103922244767, 'samples': 12474048, 'steps': 64968, 'loss/train': 0.9845263957977295} 08/31/2021 00:59:09 - INFO - __main__ - Step 64970: {'lr': 0.00030800523031002846, 'samples': 12474240, 'steps': 64969, 'loss/train': 1.6117808818817139} 08/31/2021 00:59:11 - INFO - __main__ - Step 64971: {'lr': 0.00030800006836944406, 'samples': 12474432, 'steps': 64970, 'loss/train': 0.037779923528432846} 08/31/2021 00:59:11 - INFO - __main__ - Step 64972: {'lr': 0.00030799490640272563, 'samples': 12474624, 'steps': 64971, 'loss/train': 0.6186236143112183} 08/31/2021 00:59:12 - INFO - __main__ - Step 64973: {'lr': 0.00030798974440987564, 'samples': 12474816, 'steps': 64972, 'loss/train': 1.1751840114593506} 08/31/2021 00:59:12 - INFO - __main__ - Step 64974: {'lr': 0.0003079845823908964, 'samples': 12475008, 'steps': 64973, 'loss/train': 1.614610195159912} 08/31/2021 00:59:12 - INFO - __main__ - Step 64975: {'lr': 0.00030797942034579013, 'samples': 12475200, 'steps': 64974, 'loss/train': 0.9453771710395813} 08/31/2021 00:59:13 - INFO - __main__ - Step 64976: {'lr': 0.0003079742582745592, 'samples': 12475392, 'steps': 64975, 'loss/train': 1.6504135131835938} 08/31/2021 00:59:14 - INFO - __main__ - Step 64977: {'lr': 0.000307969096177206, 'samples': 12475584, 'steps': 64976, 'loss/train': 0.031831756234169006} 08/31/2021 00:59:15 - INFO - __main__ - Step 64978: {'lr': 0.00030796393405373287, 'samples': 12475776, 'steps': 64977, 'loss/train': 1.6114189624786377} 08/31/2021 00:59:15 - INFO - __main__ - Step 64979: {'lr': 0.000307958771904142, 'samples': 12475968, 'steps': 64978, 'loss/train': 1.3165919780731201} 08/31/2021 00:59:15 - INFO - __main__ - Step 64980: {'lr': 0.00030795360972843595, 'samples': 12476160, 'steps': 64979, 'loss/train': 1.2386914491653442} 08/31/2021 00:59:16 - INFO - __main__ - Step 64981: {'lr': 0.0003079484475266168, 'samples': 12476352, 'steps': 64980, 'loss/train': 0.40732434391975403} 08/31/2021 00:59:17 - INFO - __main__ - Step 64982: {'lr': 0.00030794328529868694, 'samples': 12476544, 'steps': 64981, 'loss/train': 0.7652513384819031} 08/31/2021 00:59:18 - INFO - __main__ - Step 64983: {'lr': 0.00030793812304464875, 'samples': 12476736, 'steps': 64982, 'loss/train': 1.6119834184646606} 08/31/2021 00:59:18 - INFO - __main__ - Step 64984: {'lr': 0.00030793296076450454, 'samples': 12476928, 'steps': 64983, 'loss/train': 1.1898595094680786} 08/31/2021 00:59:18 - INFO - __main__ - Step 64985: {'lr': 0.00030792779845825665, 'samples': 12477120, 'steps': 64984, 'loss/train': 1.3661922216415405} 08/31/2021 00:59:19 - INFO - __main__ - Step 64986: {'lr': 0.00030792263612590734, 'samples': 12477312, 'steps': 64985, 'loss/train': 1.3582223653793335} 08/31/2021 00:59:20 - INFO - __main__ - Step 64987: {'lr': 0.0003079174737674591, 'samples': 12477504, 'steps': 64986, 'loss/train': 0.6706880331039429} 08/31/2021 00:59:21 - INFO - __main__ - Step 64988: {'lr': 0.00030791231138291406, 'samples': 12477696, 'steps': 64987, 'loss/train': 1.7530555725097656} 08/31/2021 00:59:21 - INFO - __main__ - Step 64989: {'lr': 0.00030790714897227457, 'samples': 12477888, 'steps': 64988, 'loss/train': 0.873991847038269} 08/31/2021 00:59:21 - INFO - __main__ - Step 64990: {'lr': 0.00030790198653554305, 'samples': 12478080, 'steps': 64989, 'loss/train': 0.8472580313682556} 08/31/2021 00:59:22 - INFO - __main__ - Step 64991: {'lr': 0.00030789682407272184, 'samples': 12478272, 'steps': 64990, 'loss/train': 0.22143006324768066} 08/31/2021 00:59:23 - INFO - __main__ - Step 64992: {'lr': 0.00030789166158381315, 'samples': 12478464, 'steps': 64991, 'loss/train': 1.1227071285247803} 08/31/2021 00:59:24 - INFO - __main__ - Step 64993: {'lr': 0.0003078864990688194, 'samples': 12478656, 'steps': 64992, 'loss/train': 0.7488687038421631} 08/31/2021 00:59:24 - INFO - __main__ - Step 64994: {'lr': 0.000307881336527743, 'samples': 12478848, 'steps': 64993, 'loss/train': 1.507637619972229} 08/31/2021 00:59:24 - INFO - __main__ - Step 64995: {'lr': 0.00030787617396058596, 'samples': 12479040, 'steps': 64994, 'loss/train': 1.3994296789169312} 08/31/2021 00:59:25 - INFO - __main__ - Step 64996: {'lr': 0.00030787101136735094, 'samples': 12479232, 'steps': 64995, 'loss/train': 5.336319446563721} 08/31/2021 00:59:25 - INFO - __main__ - Step 64997: {'lr': 0.00030786584874804005, 'samples': 12479424, 'steps': 64996, 'loss/train': 1.1988325119018555} 08/31/2021 00:59:27 - INFO - __main__ - Step 64998: {'lr': 0.0003078606861026558, 'samples': 12479616, 'steps': 64997, 'loss/train': 1.6411651372909546} 08/31/2021 00:59:27 - INFO - __main__ - Step 64999: {'lr': 0.00030785552343120035, 'samples': 12479808, 'steps': 64998, 'loss/train': 0.674951434135437} 08/31/2021 00:59:28 - INFO - __main__ - Step 65000: {'lr': 0.00030785036073367614, 'samples': 12480000, 'steps': 64999, 'loss/train': 1.522672176361084} 08/31/2021 00:59:28 - INFO - __main__ - Step 65001: {'lr': 0.00030784519801008544, 'samples': 12480192, 'steps': 65000, 'loss/train': 0.8584864735603333} 08/31/2021 00:59:28 - INFO - __main__ - Step 65002: {'lr': 0.0003078400352604305, 'samples': 12480384, 'steps': 65001, 'loss/train': 2.056735038757324} 08/31/2021 00:59:30 - INFO - __main__ - Step 65003: {'lr': 0.0003078348724847138, 'samples': 12480576, 'steps': 65002, 'loss/train': 0.9875257611274719} 08/31/2021 00:59:30 - INFO - __main__ - Step 65004: {'lr': 0.0003078297096829376, 'samples': 12480768, 'steps': 65003, 'loss/train': 1.737903118133545} 08/31/2021 00:59:30 - INFO - __main__ - Step 65005: {'lr': 0.0003078245468551042, 'samples': 12480960, 'steps': 65004, 'loss/train': 1.1894233226776123} 08/31/2021 00:59:31 - INFO - __main__ - Step 65006: {'lr': 0.000307819384001216, 'samples': 12481152, 'steps': 65005, 'loss/train': 0.8268977999687195} 08/31/2021 00:59:31 - INFO - __main__ - Step 65007: {'lr': 0.0003078142211212753, 'samples': 12481344, 'steps': 65006, 'loss/train': 1.0868626832962036} 08/31/2021 00:59:33 - INFO - __main__ - Step 65008: {'lr': 0.00030780905821528435, 'samples': 12481536, 'steps': 65007, 'loss/train': 0.6231642365455627} 08/31/2021 00:59:33 - INFO - __main__ - Step 65009: {'lr': 0.00030780389528324554, 'samples': 12481728, 'steps': 65008, 'loss/train': 1.259151816368103} 08/31/2021 00:59:33 - INFO - __main__ - Step 65010: {'lr': 0.00030779873232516115, 'samples': 12481920, 'steps': 65009, 'loss/train': 1.247302532196045} 08/31/2021 00:59:34 - INFO - __main__ - Step 65011: {'lr': 0.00030779356934103357, 'samples': 12482112, 'steps': 65010, 'loss/train': 1.0323984622955322} 08/31/2021 00:59:34 - INFO - __main__ - Step 65012: {'lr': 0.00030778840633086514, 'samples': 12482304, 'steps': 65011, 'loss/train': 1.3258116245269775} 08/31/2021 00:59:36 - INFO - __main__ - Step 65013: {'lr': 0.0003077832432946581, 'samples': 12482496, 'steps': 65012, 'loss/train': 1.189038872718811} 08/31/2021 00:59:37 - INFO - __main__ - Step 65014: {'lr': 0.0003077780802324149, 'samples': 12482688, 'steps': 65013, 'loss/train': 0.6602399945259094} 08/31/2021 00:59:37 - INFO - __main__ - Step 65015: {'lr': 0.0003077729171441377, 'samples': 12482880, 'steps': 65014, 'loss/train': 0.15293064713478088} 08/31/2021 00:59:37 - INFO - __main__ - Step 65016: {'lr': 0.00030776775402982894, 'samples': 12483072, 'steps': 65015, 'loss/train': 1.5097856521606445} 08/31/2021 00:59:38 - INFO - __main__ - Step 65017: {'lr': 0.00030776259088949087, 'samples': 12483264, 'steps': 65016, 'loss/train': 1.0368448495864868} 08/31/2021 00:59:39 - INFO - __main__ - Step 65018: {'lr': 0.00030775742772312593, 'samples': 12483456, 'steps': 65017, 'loss/train': 1.9865773916244507} 08/31/2021 00:59:40 - INFO - __main__ - Step 65019: {'lr': 0.00030775226453073635, 'samples': 12483648, 'steps': 65018, 'loss/train': 1.6535013914108276} 08/31/2021 00:59:40 - INFO - __main__ - Step 65020: {'lr': 0.0003077471013123246, 'samples': 12483840, 'steps': 65019, 'loss/train': 1.1148086786270142} 08/31/2021 00:59:40 - INFO - __main__ - Step 65021: {'lr': 0.0003077419380678927, 'samples': 12484032, 'steps': 65020, 'loss/train': 1.3112014532089233} 08/31/2021 00:59:41 - INFO - __main__ - Step 65022: {'lr': 0.00030773677479744335, 'samples': 12484224, 'steps': 65021, 'loss/train': 1.5397809743881226} 08/31/2021 00:59:43 - INFO - __main__ - Step 65023: {'lr': 0.0003077316115009786, 'samples': 12484416, 'steps': 65022, 'loss/train': 1.4282519817352295} 08/31/2021 00:59:43 - INFO - __main__ - Step 65024: {'lr': 0.0003077264481785009, 'samples': 12484608, 'steps': 65023, 'loss/train': 0.7894071936607361} 08/31/2021 00:59:43 - INFO - __main__ - Step 65025: {'lr': 0.0003077212848300126, 'samples': 12484800, 'steps': 65024, 'loss/train': 0.7634131908416748} 08/31/2021 00:59:44 - INFO - __main__ - Step 65026: {'lr': 0.0003077161214555159, 'samples': 12484992, 'steps': 65025, 'loss/train': 1.763093113899231} 08/31/2021 00:59:44 - INFO - __main__ - Step 65027: {'lr': 0.0003077109580550133, 'samples': 12485184, 'steps': 65026, 'loss/train': 1.4517779350280762} 08/31/2021 00:59:44 - INFO - __main__ - Step 65028: {'lr': 0.000307705794628507, 'samples': 12485376, 'steps': 65027, 'loss/train': 0.6299188733100891} 08/31/2021 00:59:46 - INFO - __main__ - Step 65029: {'lr': 0.0003077006311759993, 'samples': 12485568, 'steps': 65028, 'loss/train': 0.027544163167476654} 08/31/2021 00:59:46 - INFO - __main__ - Step 65030: {'lr': 0.00030769546769749263, 'samples': 12485760, 'steps': 65029, 'loss/train': 1.3801034688949585} 08/31/2021 00:59:47 - INFO - __main__ - Step 65031: {'lr': 0.00030769030419298927, 'samples': 12485952, 'steps': 65030, 'loss/train': 1.1577725410461426} 08/31/2021 00:59:47 - INFO - __main__ - Step 65032: {'lr': 0.00030768514066249156, 'samples': 12486144, 'steps': 65031, 'loss/train': 1.721334457397461} 08/31/2021 00:59:48 - INFO - __main__ - Step 65033: {'lr': 0.0003076799771060018, 'samples': 12486336, 'steps': 65032, 'loss/train': 0.9798344969749451} 08/31/2021 00:59:49 - INFO - __main__ - Step 65034: {'lr': 0.0003076748135235224, 'samples': 12486528, 'steps': 65033, 'loss/train': 1.270301342010498} 08/31/2021 00:59:49 - INFO - __main__ - Step 65035: {'lr': 0.00030766964991505553, 'samples': 12486720, 'steps': 65034, 'loss/train': 1.382791519165039} 08/31/2021 00:59:50 - INFO - __main__ - Step 65036: {'lr': 0.0003076644862806036, 'samples': 12486912, 'steps': 65035, 'loss/train': 1.495176076889038} 08/31/2021 00:59:50 - INFO - __main__ - Step 65037: {'lr': 0.00030765932262016897, 'samples': 12487104, 'steps': 65036, 'loss/train': 1.2961077690124512} 08/31/2021 00:59:51 - INFO - __main__ - Step 65038: {'lr': 0.00030765415893375394, 'samples': 12487296, 'steps': 65037, 'loss/train': 1.581131100654602} 08/31/2021 00:59:52 - INFO - __main__ - Step 65039: {'lr': 0.0003076489952213609, 'samples': 12487488, 'steps': 65038, 'loss/train': 1.511063575744629} 08/31/2021 00:59:53 - INFO - __main__ - Step 65040: {'lr': 0.00030764383148299196, 'samples': 12487680, 'steps': 65039, 'loss/train': 0.9396119713783264} 08/31/2021 00:59:53 - INFO - __main__ - Step 65041: {'lr': 0.0003076386677186498, 'samples': 12487872, 'steps': 65040, 'loss/train': 1.0151525735855103} 08/31/2021 00:59:53 - INFO - __main__ - Step 65042: {'lr': 0.00030763350392833637, 'samples': 12488064, 'steps': 65041, 'loss/train': 0.6980643272399902} 08/31/2021 00:59:54 - INFO - __main__ - Step 65043: {'lr': 0.00030762834011205425, 'samples': 12488256, 'steps': 65042, 'loss/train': 1.3884057998657227} 08/31/2021 00:59:54 - INFO - __main__ - Step 65044: {'lr': 0.0003076231762698057, 'samples': 12488448, 'steps': 65043, 'loss/train': 1.51949143409729} 08/31/2021 00:59:55 - INFO - __main__ - Step 65045: {'lr': 0.000307618012401593, 'samples': 12488640, 'steps': 65044, 'loss/train': 0.836931586265564} 08/31/2021 00:59:56 - INFO - __main__ - Step 65046: {'lr': 0.0003076128485074185, 'samples': 12488832, 'steps': 65045, 'loss/train': 1.2962034940719604} 08/31/2021 00:59:56 - INFO - __main__ - Step 65047: {'lr': 0.0003076076845872846, 'samples': 12489024, 'steps': 65046, 'loss/train': 1.2615342140197754} 08/31/2021 00:59:57 - INFO - __main__ - Step 65048: {'lr': 0.00030760252064119354, 'samples': 12489216, 'steps': 65047, 'loss/train': 1.0437852144241333} 08/31/2021 00:59:57 - INFO - __main__ - Step 65049: {'lr': 0.00030759735666914767, 'samples': 12489408, 'steps': 65048, 'loss/train': 1.044826865196228} 08/31/2021 00:59:58 - INFO - __main__ - Step 65050: {'lr': 0.0003075921926711493, 'samples': 12489600, 'steps': 65049, 'loss/train': 0.9258054494857788} 08/31/2021 00:59:59 - INFO - __main__ - Step 65051: {'lr': 0.0003075870286472008, 'samples': 12489792, 'steps': 65050, 'loss/train': 1.5876134634017944} 08/31/2021 00:59:59 - INFO - __main__ - Step 65052: {'lr': 0.0003075818645973044, 'samples': 12489984, 'steps': 65051, 'loss/train': 1.0637234449386597} 08/31/2021 00:59:59 - INFO - __main__ - Step 65053: {'lr': 0.00030757670052146256, 'samples': 12490176, 'steps': 65052, 'loss/train': 0.5152906179428101} 08/31/2021 01:00:00 - INFO - __main__ - Step 65054: {'lr': 0.0003075715364196776, 'samples': 12490368, 'steps': 65053, 'loss/train': 0.3404980003833771} 08/31/2021 01:00:01 - INFO - __main__ - Step 65055: {'lr': 0.00030756637229195177, 'samples': 12490560, 'steps': 65054, 'loss/train': 1.4890110492706299} 08/31/2021 01:00:02 - INFO - __main__ - Step 65056: {'lr': 0.0003075612081382874, 'samples': 12490752, 'steps': 65055, 'loss/train': 1.2333905696868896} 08/31/2021 01:00:02 - INFO - __main__ - Step 65057: {'lr': 0.00030755604395868685, 'samples': 12490944, 'steps': 65056, 'loss/train': 1.4340049028396606} 08/31/2021 01:00:02 - INFO - __main__ - Step 65058: {'lr': 0.0003075508797531524, 'samples': 12491136, 'steps': 65057, 'loss/train': 1.4402674436569214} 08/31/2021 01:00:03 - INFO - __main__ - Step 65059: {'lr': 0.00030754571552168644, 'samples': 12491328, 'steps': 65058, 'loss/train': 0.7304226160049438} 08/31/2021 01:00:04 - INFO - __main__ - Step 65060: {'lr': 0.00030754055126429124, 'samples': 12491520, 'steps': 65059, 'loss/train': 1.5010141134262085} 08/31/2021 01:00:05 - INFO - __main__ - Step 65061: {'lr': 0.00030753538698096924, 'samples': 12491712, 'steps': 65060, 'loss/train': 0.8917636871337891} 08/31/2021 01:00:05 - INFO - __main__ - Step 65062: {'lr': 0.0003075302226717226, 'samples': 12491904, 'steps': 65061, 'loss/train': 1.5092113018035889} 08/31/2021 01:00:06 - INFO - __main__ - Step 65063: {'lr': 0.00030752505833655375, 'samples': 12492096, 'steps': 65062, 'loss/train': 0.670124351978302} 08/31/2021 01:00:06 - INFO - __main__ - Step 65064: {'lr': 0.00030751989397546497, 'samples': 12492288, 'steps': 65063, 'loss/train': 1.2616349458694458} 08/31/2021 01:00:08 - INFO - __main__ - Step 65065: {'lr': 0.0003075147295884586, 'samples': 12492480, 'steps': 65064, 'loss/train': 0.9894877076148987} 08/31/2021 01:00:09 - INFO - __main__ - Step 65066: {'lr': 0.0003075095651755371, 'samples': 12492672, 'steps': 65065, 'loss/train': 0.7499938011169434} 08/31/2021 01:00:09 - INFO - __main__ - Step 65067: {'lr': 0.0003075044007367026, 'samples': 12492864, 'steps': 65066, 'loss/train': 1.8168549537658691} 08/31/2021 01:00:09 - INFO - __main__ - Step 65068: {'lr': 0.0003074992362719575, 'samples': 12493056, 'steps': 65067, 'loss/train': 1.6175986528396606} 08/31/2021 01:00:10 - INFO - __main__ - Step 65069: {'lr': 0.0003074940717813041, 'samples': 12493248, 'steps': 65068, 'loss/train': 1.2409189939498901} 08/31/2021 01:00:10 - INFO - __main__ - Step 65070: {'lr': 0.00030748890726474474, 'samples': 12493440, 'steps': 65069, 'loss/train': 0.9397032260894775} 08/31/2021 01:00:12 - INFO - __main__ - Step 65071: {'lr': 0.00030748374272228184, 'samples': 12493632, 'steps': 65070, 'loss/train': 1.0971022844314575} 08/31/2021 01:00:12 - INFO - __main__ - Step 65072: {'lr': 0.00030747857815391767, 'samples': 12493824, 'steps': 65071, 'loss/train': 1.2792898416519165} 08/31/2021 01:00:12 - INFO - __main__ - Step 65073: {'lr': 0.0003074734135596545, 'samples': 12494016, 'steps': 65072, 'loss/train': 1.5297460556030273} 08/31/2021 01:00:13 - INFO - __main__ - Step 65074: {'lr': 0.0003074682489394947, 'samples': 12494208, 'steps': 65073, 'loss/train': 0.9794919490814209} 08/31/2021 01:00:13 - INFO - __main__ - Step 65075: {'lr': 0.00030746308429344056, 'samples': 12494400, 'steps': 65074, 'loss/train': 1.0414743423461914} 08/31/2021 01:00:15 - INFO - __main__ - Step 65076: {'lr': 0.0003074579196214945, 'samples': 12494592, 'steps': 65075, 'loss/train': 0.8322542905807495} 08/31/2021 01:00:15 - INFO - __main__ - Step 65077: {'lr': 0.00030745275492365874, 'samples': 12494784, 'steps': 65076, 'loss/train': 2.0445823669433594} 08/31/2021 01:00:15 - INFO - __main__ - Step 65078: {'lr': 0.0003074475901999357, 'samples': 12494976, 'steps': 65077, 'loss/train': 1.4380910396575928} 08/31/2021 01:00:16 - INFO - __main__ - Step 65079: {'lr': 0.00030744242545032764, 'samples': 12495168, 'steps': 65078, 'loss/train': 1.2705656290054321} 08/31/2021 01:00:16 - INFO - __main__ - Step 65080: {'lr': 0.0003074372606748369, 'samples': 12495360, 'steps': 65079, 'loss/train': 1.5640840530395508} 08/31/2021 01:00:18 - INFO - __main__ - Step 65081: {'lr': 0.0003074320958734658, 'samples': 12495552, 'steps': 65080, 'loss/train': 0.48318102955818176} 08/31/2021 01:00:18 - INFO - __main__ - Step 65082: {'lr': 0.0003074269310462167, 'samples': 12495744, 'steps': 65081, 'loss/train': 2.0487399101257324} 08/31/2021 01:00:18 - INFO - __main__ - Step 65083: {'lr': 0.000307421766193092, 'samples': 12495936, 'steps': 65082, 'loss/train': 1.3704466819763184} 08/31/2021 01:00:19 - INFO - __main__ - Step 65084: {'lr': 0.0003074166013140938, 'samples': 12496128, 'steps': 65083, 'loss/train': 1.7007452249526978} 08/31/2021 01:00:19 - INFO - __main__ - Step 65085: {'lr': 0.0003074114364092246, 'samples': 12496320, 'steps': 65084, 'loss/train': 0.8184317946434021} 08/31/2021 01:00:21 - INFO - __main__ - Step 65086: {'lr': 0.0003074062714784867, 'samples': 12496512, 'steps': 65085, 'loss/train': 0.9584785103797913} 08/31/2021 01:00:21 - INFO - __main__ - Step 65087: {'lr': 0.00030740110652188247, 'samples': 12496704, 'steps': 65086, 'loss/train': 0.5080150961875916} 08/31/2021 01:00:22 - INFO - __main__ - Step 65088: {'lr': 0.0003073959415394142, 'samples': 12496896, 'steps': 65087, 'loss/train': 1.3956408500671387} 08/31/2021 01:00:22 - INFO - __main__ - Step 65089: {'lr': 0.0003073907765310841, 'samples': 12497088, 'steps': 65088, 'loss/train': 0.7632496953010559} 08/31/2021 01:00:22 - INFO - __main__ - Step 65090: {'lr': 0.0003073856114968947, 'samples': 12497280, 'steps': 65089, 'loss/train': 0.041352055966854095} 08/31/2021 01:00:24 - INFO - __main__ - Step 65091: {'lr': 0.00030738044643684816, 'samples': 12497472, 'steps': 65090, 'loss/train': 1.0176873207092285} 08/31/2021 01:00:24 - INFO - __main__ - Step 65092: {'lr': 0.0003073752813509469, 'samples': 12497664, 'steps': 65091, 'loss/train': 2.151690721511841} 08/31/2021 01:00:25 - INFO - __main__ - Step 65093: {'lr': 0.0003073701162391932, 'samples': 12497856, 'steps': 65092, 'loss/train': 1.4041998386383057} 08/31/2021 01:00:25 - INFO - __main__ - Step 65094: {'lr': 0.0003073649511015895, 'samples': 12498048, 'steps': 65093, 'loss/train': 0.9704016447067261} 08/31/2021 01:00:25 - INFO - __main__ - Step 65095: {'lr': 0.00030735978593813797, 'samples': 12498240, 'steps': 65094, 'loss/train': 1.4318653345108032} 08/31/2021 01:00:26 - INFO - __main__ - Step 65096: {'lr': 0.00030735462074884097, 'samples': 12498432, 'steps': 65095, 'loss/train': 1.3913668394088745} 08/31/2021 01:00:27 - INFO - __main__ - Step 65097: {'lr': 0.00030734945553370093, 'samples': 12498624, 'steps': 65096, 'loss/train': 1.3195608854293823} 08/31/2021 01:00:28 - INFO - __main__ - Step 65098: {'lr': 0.00030734429029272, 'samples': 12498816, 'steps': 65097, 'loss/train': 1.6119941473007202} 08/31/2021 01:00:28 - INFO - __main__ - Step 65099: {'lr': 0.0003073391250259007, 'samples': 12499008, 'steps': 65098, 'loss/train': 1.059809923171997} 08/31/2021 01:00:29 - INFO - __main__ - Step 65100: {'lr': 0.0003073339597332453, 'samples': 12499200, 'steps': 65099, 'loss/train': 1.1960350275039673} 08/31/2021 01:00:29 - INFO - __main__ - Step 65101: {'lr': 0.00030732879441475614, 'samples': 12499392, 'steps': 65100, 'loss/train': 1.0385174751281738} 08/31/2021 01:00:30 - INFO - __main__ - Step 65102: {'lr': 0.0003073236290704354, 'samples': 12499584, 'steps': 65101, 'loss/train': 1.386845350265503} 08/31/2021 01:00:31 - INFO - __main__ - Step 65103: {'lr': 0.0003073184637002856, 'samples': 12499776, 'steps': 65102, 'loss/train': 1.0485399961471558} 08/31/2021 01:00:31 - INFO - __main__ - Step 65104: {'lr': 0.0003073132983043089, 'samples': 12499968, 'steps': 65103, 'loss/train': 1.8511412143707275} 08/31/2021 01:00:31 - INFO - __main__ - Step 65105: {'lr': 0.0003073081328825078, 'samples': 12500160, 'steps': 65104, 'loss/train': 1.6660820245742798} 08/31/2021 01:00:32 - INFO - __main__ - Step 65106: {'lr': 0.0003073029674348845, 'samples': 12500352, 'steps': 65105, 'loss/train': 1.0584518909454346} 08/31/2021 01:00:33 - INFO - __main__ - Step 65107: {'lr': 0.00030729780196144137, 'samples': 12500544, 'steps': 65106, 'loss/train': 1.4732412099838257} 08/31/2021 01:00:34 - INFO - __main__ - Step 65108: {'lr': 0.0003072926364621807, 'samples': 12500736, 'steps': 65107, 'loss/train': 1.0585936307907104} 08/31/2021 01:00:34 - INFO - __main__ - Step 65109: {'lr': 0.0003072874709371049, 'samples': 12500928, 'steps': 65108, 'loss/train': 1.3688554763793945} 08/31/2021 01:00:35 - INFO - __main__ - Step 65110: {'lr': 0.0003072823053862163, 'samples': 12501120, 'steps': 65109, 'loss/train': 1.266575574874878} 08/31/2021 01:00:35 - INFO - __main__ - Step 65111: {'lr': 0.00030727713980951705, 'samples': 12501312, 'steps': 65110, 'loss/train': 1.2229974269866943} 08/31/2021 01:00:37 - INFO - __main__ - Step 65112: {'lr': 0.0003072719742070097, 'samples': 12501504, 'steps': 65111, 'loss/train': 1.1649516820907593} 08/31/2021 01:00:38 - INFO - __main__ - Step 65113: {'lr': 0.0003072668085786964, 'samples': 12501696, 'steps': 65112, 'loss/train': 0.784217894077301} 08/31/2021 01:00:38 - INFO - __main__ - Step 65114: {'lr': 0.0003072616429245796, 'samples': 12501888, 'steps': 65113, 'loss/train': 1.1837005615234375} 08/31/2021 01:00:38 - INFO - __main__ - Step 65115: {'lr': 0.00030725647724466165, 'samples': 12502080, 'steps': 65114, 'loss/train': 2.2880494594573975} 08/31/2021 01:00:39 - INFO - __main__ - Step 65116: {'lr': 0.00030725131153894474, 'samples': 12502272, 'steps': 65115, 'loss/train': 1.795592188835144} 08/31/2021 01:00:39 - INFO - __main__ - Step 65117: {'lr': 0.00030724614580743135, 'samples': 12502464, 'steps': 65116, 'loss/train': 1.2838151454925537} 08/31/2021 01:00:41 - INFO - __main__ - Step 65118: {'lr': 0.00030724098005012365, 'samples': 12502656, 'steps': 65117, 'loss/train': 0.9568909406661987} 08/31/2021 01:00:41 - INFO - __main__ - Step 65119: {'lr': 0.00030723581426702403, 'samples': 12502848, 'steps': 65118, 'loss/train': 1.3564015626907349} 08/31/2021 01:00:42 - INFO - __main__ - Step 65120: {'lr': 0.00030723064845813487, 'samples': 12503040, 'steps': 65119, 'loss/train': 1.381718635559082} 08/31/2021 01:00:42 - INFO - __main__ - Step 65121: {'lr': 0.0003072254826234585, 'samples': 12503232, 'steps': 65120, 'loss/train': 1.2300846576690674} 08/31/2021 01:00:43 - INFO - __main__ - Step 65122: {'lr': 0.00030722031676299716, 'samples': 12503424, 'steps': 65121, 'loss/train': 1.2268662452697754} 08/31/2021 01:00:44 - INFO - __main__ - Step 65123: {'lr': 0.00030721515087675326, 'samples': 12503616, 'steps': 65122, 'loss/train': 0.785710871219635} 08/31/2021 01:00:45 - INFO - __main__ - Step 65124: {'lr': 0.00030720998496472905, 'samples': 12503808, 'steps': 65123, 'loss/train': 0.1571958363056183} 08/31/2021 01:00:45 - INFO - __main__ - Step 65125: {'lr': 0.000307204819026927, 'samples': 12504000, 'steps': 65124, 'loss/train': 1.083516001701355} 08/31/2021 01:00:45 - INFO - __main__ - Step 65126: {'lr': 0.00030719965306334925, 'samples': 12504192, 'steps': 65125, 'loss/train': 1.3975321054458618} 08/31/2021 01:00:46 - INFO - __main__ - Step 65127: {'lr': 0.0003071944870739982, 'samples': 12504384, 'steps': 65126, 'loss/train': 1.1734404563903809} 08/31/2021 01:00:47 - INFO - __main__ - Step 65128: {'lr': 0.0003071893210588763, 'samples': 12504576, 'steps': 65127, 'loss/train': 1.2664484977722168} 08/31/2021 01:00:48 - INFO - __main__ - Step 65129: {'lr': 0.00030718415501798576, 'samples': 12504768, 'steps': 65128, 'loss/train': 1.1186857223510742} 08/31/2021 01:00:48 - INFO - __main__ - Step 65130: {'lr': 0.00030717898895132883, 'samples': 12504960, 'steps': 65129, 'loss/train': 1.779291033744812} 08/31/2021 01:00:48 - INFO - __main__ - Step 65131: {'lr': 0.000307173822858908, 'samples': 12505152, 'steps': 65130, 'loss/train': 1.5159132480621338} 08/31/2021 01:00:49 - INFO - __main__ - Step 65132: {'lr': 0.00030716865674072547, 'samples': 12505344, 'steps': 65131, 'loss/train': 1.4244366884231567} 08/31/2021 01:00:50 - INFO - __main__ - Step 65133: {'lr': 0.0003071634905967837, 'samples': 12505536, 'steps': 65132, 'loss/train': 0.8225919604301453} 08/31/2021 01:00:51 - INFO - __main__ - Step 65134: {'lr': 0.00030715832442708484, 'samples': 12505728, 'steps': 65133, 'loss/train': 1.6880662441253662} 08/31/2021 01:00:51 - INFO - __main__ - Step 65135: {'lr': 0.00030715315823163147, 'samples': 12505920, 'steps': 65134, 'loss/train': 1.6297920942306519} 08/31/2021 01:00:52 - INFO - __main__ - Step 65136: {'lr': 0.00030714799201042565, 'samples': 12506112, 'steps': 65135, 'loss/train': 0.629072368144989} 08/31/2021 01:00:52 - INFO - __main__ - Step 65137: {'lr': 0.00030714282576346986, 'samples': 12506304, 'steps': 65136, 'loss/train': 5.852924346923828} 08/31/2021 01:00:52 - INFO - __main__ - Step 65138: {'lr': 0.0003071376594907664, 'samples': 12506496, 'steps': 65137, 'loss/train': 1.1109976768493652} 08/31/2021 01:00:54 - INFO - __main__ - Step 65139: {'lr': 0.00030713249319231755, 'samples': 12506688, 'steps': 65138, 'loss/train': 1.3649274110794067} 08/31/2021 01:00:54 - INFO - __main__ - Step 65140: {'lr': 0.00030712732686812575, 'samples': 12506880, 'steps': 65139, 'loss/train': 0.9489412903785706} 08/31/2021 01:00:54 - INFO - __main__ - Step 65141: {'lr': 0.0003071221605181933, 'samples': 12507072, 'steps': 65140, 'loss/train': 1.0197573900222778} 08/31/2021 01:00:55 - INFO - __main__ - Step 65142: {'lr': 0.0003071169941425224, 'samples': 12507264, 'steps': 65141, 'loss/train': 0.21193522214889526} 08/31/2021 01:00:55 - INFO - __main__ - Step 65143: {'lr': 0.00030711182774111544, 'samples': 12507456, 'steps': 65142, 'loss/train': 0.7720224261283875} 08/31/2021 01:00:57 - INFO - __main__ - Step 65144: {'lr': 0.0003071066613139748, 'samples': 12507648, 'steps': 65143, 'loss/train': 1.4284998178482056} 08/31/2021 01:00:58 - INFO - __main__ - Step 65145: {'lr': 0.0003071014948611028, 'samples': 12507840, 'steps': 65144, 'loss/train': 1.1615760326385498} 08/31/2021 01:00:58 - INFO - __main__ - Step 65146: {'lr': 0.0003070963283825017, 'samples': 12508032, 'steps': 65145, 'loss/train': 0.9842082858085632} 08/31/2021 01:00:58 - INFO - __main__ - Step 65147: {'lr': 0.00030709116187817396, 'samples': 12508224, 'steps': 65146, 'loss/train': 2.0813581943511963} 08/31/2021 01:00:59 - INFO - __main__ - Step 65148: {'lr': 0.0003070859953481218, 'samples': 12508416, 'steps': 65147, 'loss/train': 1.7886137962341309} 08/31/2021 01:01:00 - INFO - __main__ - Step 65149: {'lr': 0.00030708082879234757, 'samples': 12508608, 'steps': 65148, 'loss/train': 1.4071087837219238} 08/31/2021 01:01:01 - INFO - __main__ - Step 65150: {'lr': 0.00030707566221085356, 'samples': 12508800, 'steps': 65149, 'loss/train': 1.0740325450897217} 08/31/2021 01:01:01 - INFO - __main__ - Step 65151: {'lr': 0.00030707049560364216, 'samples': 12508992, 'steps': 65150, 'loss/train': 1.5767239332199097} 08/31/2021 01:01:01 - INFO - __main__ - Step 65152: {'lr': 0.0003070653289707156, 'samples': 12509184, 'steps': 65151, 'loss/train': 1.2635289430618286} 08/31/2021 01:01:02 - INFO - __main__ - Step 65153: {'lr': 0.00030706016231207633, 'samples': 12509376, 'steps': 65152, 'loss/train': 0.8170627951622009} 08/31/2021 01:01:02 - INFO - __main__ - Step 65154: {'lr': 0.00030705499562772666, 'samples': 12509568, 'steps': 65153, 'loss/train': 0.4586712718009949} 08/31/2021 01:01:03 - INFO - __main__ - Step 65155: {'lr': 0.000307049828917669, 'samples': 12509760, 'steps': 65154, 'loss/train': 1.1482584476470947} 08/31/2021 01:01:04 - INFO - __main__ - Step 65156: {'lr': 0.0003070446621819054, 'samples': 12509952, 'steps': 65155, 'loss/train': 1.999744176864624} 08/31/2021 01:01:04 - INFO - __main__ - Step 65157: {'lr': 0.0003070394954204384, 'samples': 12510144, 'steps': 65156, 'loss/train': 0.6824196577072144} 08/31/2021 01:01:05 - INFO - __main__ - Step 65158: {'lr': 0.0003070343286332703, 'samples': 12510336, 'steps': 65157, 'loss/train': 1.0588102340698242} 08/31/2021 01:01:05 - INFO - __main__ - Step 65159: {'lr': 0.0003070291618204034, 'samples': 12510528, 'steps': 65158, 'loss/train': 0.9084184169769287} 08/31/2021 01:01:06 - INFO - __main__ - Step 65160: {'lr': 0.00030702399498184005, 'samples': 12510720, 'steps': 65159, 'loss/train': 0.8751407265663147} 08/31/2021 01:01:07 - INFO - __main__ - Step 65161: {'lr': 0.00030701882811758253, 'samples': 12510912, 'steps': 65160, 'loss/train': 1.496291160583496} 08/31/2021 01:01:07 - INFO - __main__ - Step 65162: {'lr': 0.00030701366122763327, 'samples': 12511104, 'steps': 65161, 'loss/train': 1.0534378290176392} 08/31/2021 01:01:08 - INFO - __main__ - Step 65163: {'lr': 0.00030700849431199444, 'samples': 12511296, 'steps': 65162, 'loss/train': 1.8274379968643188} 08/31/2021 01:01:08 - INFO - __main__ - Step 65164: {'lr': 0.0003070033273706685, 'samples': 12511488, 'steps': 65163, 'loss/train': 1.0940262079238892} 08/31/2021 01:01:10 - INFO - __main__ - Step 65165: {'lr': 0.0003069981604036578, 'samples': 12511680, 'steps': 65164, 'loss/train': 1.4117966890335083} 08/31/2021 01:01:10 - INFO - __main__ - Step 65166: {'lr': 0.00030699299341096456, 'samples': 12511872, 'steps': 65165, 'loss/train': 1.2424603700637817} 08/31/2021 01:01:10 - INFO - __main__ - Step 65167: {'lr': 0.0003069878263925912, 'samples': 12512064, 'steps': 65166, 'loss/train': 1.1086781024932861} 08/31/2021 01:01:11 - INFO - __main__ - Step 65168: {'lr': 0.00030698265934854, 'samples': 12512256, 'steps': 65167, 'loss/train': 0.9969587922096252} 08/31/2021 01:01:11 - INFO - __main__ - Step 65169: {'lr': 0.0003069774922788132, 'samples': 12512448, 'steps': 65168, 'loss/train': 1.5773847103118896} 08/31/2021 01:01:13 - INFO - __main__ - Step 65170: {'lr': 0.0003069723251834133, 'samples': 12512640, 'steps': 65169, 'loss/train': 1.2083224058151245} 08/31/2021 01:01:13 - INFO - __main__ - Step 65171: {'lr': 0.00030696715806234257, 'samples': 12512832, 'steps': 65170, 'loss/train': 1.8458186388015747} 08/31/2021 01:01:13 - INFO - __main__ - Step 65172: {'lr': 0.0003069619909156032, 'samples': 12513024, 'steps': 65171, 'loss/train': 0.7963100075721741} 08/31/2021 01:01:14 - INFO - __main__ - Step 65173: {'lr': 0.0003069568237431978, 'samples': 12513216, 'steps': 65172, 'loss/train': 1.2952070236206055} 08/31/2021 01:01:14 - INFO - __main__ - Step 65174: {'lr': 0.0003069516565451284, 'samples': 12513408, 'steps': 65173, 'loss/train': 1.5574190616607666} 08/31/2021 01:01:16 - INFO - __main__ - Step 65175: {'lr': 0.0003069464893213976, 'samples': 12513600, 'steps': 65174, 'loss/train': 1.4276204109191895} 08/31/2021 01:01:17 - INFO - __main__ - Step 65176: {'lr': 0.0003069413220720075, 'samples': 12513792, 'steps': 65175, 'loss/train': 1.0042895078659058} 08/31/2021 01:01:17 - INFO - __main__ - Step 65177: {'lr': 0.00030693615479696046, 'samples': 12513984, 'steps': 65176, 'loss/train': 0.8516061902046204} 08/31/2021 01:01:18 - INFO - __main__ - Step 65178: {'lr': 0.00030693098749625894, 'samples': 12514176, 'steps': 65177, 'loss/train': 1.6055657863616943} 08/31/2021 01:01:18 - INFO - __main__ - Step 65179: {'lr': 0.0003069258201699052, 'samples': 12514368, 'steps': 65178, 'loss/train': 1.107107162475586} 08/31/2021 01:01:18 - INFO - __main__ - Step 65180: {'lr': 0.00030692065281790154, 'samples': 12514560, 'steps': 65179, 'loss/train': 0.2681787610054016} 08/31/2021 01:01:20 - INFO - __main__ - Step 65181: {'lr': 0.0003069154854402503, 'samples': 12514752, 'steps': 65180, 'loss/train': 0.847260594367981} 08/31/2021 01:01:20 - INFO - __main__ - Step 65182: {'lr': 0.0003069103180369539, 'samples': 12514944, 'steps': 65181, 'loss/train': 0.9012032151222229} 08/31/2021 01:01:21 - INFO - __main__ - Step 65183: {'lr': 0.0003069051506080145, 'samples': 12515136, 'steps': 65182, 'loss/train': 0.7889128923416138} 08/31/2021 01:01:21 - INFO - __main__ - Step 65184: {'lr': 0.0003068999831534346, 'samples': 12515328, 'steps': 65183, 'loss/train': 1.1552120447158813} 08/31/2021 01:01:22 - INFO - __main__ - Step 65185: {'lr': 0.00030689481567321635, 'samples': 12515520, 'steps': 65184, 'loss/train': 0.6649223566055298} 08/31/2021 01:01:23 - INFO - __main__ - Step 65186: {'lr': 0.0003068896481673622, 'samples': 12515712, 'steps': 65185, 'loss/train': 0.9333828091621399} 08/31/2021 01:01:24 - INFO - __main__ - Step 65187: {'lr': 0.00030688448063587447, 'samples': 12515904, 'steps': 65186, 'loss/train': 1.175155520439148} 08/31/2021 01:01:24 - INFO - __main__ - Step 65188: {'lr': 0.0003068793130787555, 'samples': 12516096, 'steps': 65187, 'loss/train': 5.873299598693848} 08/31/2021 01:01:24 - INFO - __main__ - Step 65189: {'lr': 0.00030687414549600755, 'samples': 12516288, 'steps': 65188, 'loss/train': 1.0852007865905762} 08/31/2021 01:01:25 - INFO - __main__ - Step 65190: {'lr': 0.00030686897788763303, 'samples': 12516480, 'steps': 65189, 'loss/train': 1.230493426322937} 08/31/2021 01:01:25 - INFO - __main__ - Step 65191: {'lr': 0.0003068638102536342, 'samples': 12516672, 'steps': 65190, 'loss/train': 1.069223403930664} 08/31/2021 01:01:27 - INFO - __main__ - Step 65192: {'lr': 0.00030685864259401334, 'samples': 12516864, 'steps': 65191, 'loss/train': 1.2784191370010376} 08/31/2021 01:01:27 - INFO - __main__ - Step 65193: {'lr': 0.00030685347490877295, 'samples': 12517056, 'steps': 65192, 'loss/train': 0.9832997918128967} 08/31/2021 01:01:27 - INFO - __main__ - Step 65194: {'lr': 0.00030684830719791525, 'samples': 12517248, 'steps': 65193, 'loss/train': 0.5396224856376648} 08/31/2021 01:01:28 - INFO - __main__ - Step 65195: {'lr': 0.0003068431394614426, 'samples': 12517440, 'steps': 65194, 'loss/train': 1.0273853540420532} 08/31/2021 01:01:28 - INFO - __main__ - Step 65196: {'lr': 0.0003068379716993573, 'samples': 12517632, 'steps': 65195, 'loss/train': 1.5560740232467651} 08/31/2021 01:01:30 - INFO - __main__ - Step 65197: {'lr': 0.0003068328039116616, 'samples': 12517824, 'steps': 65196, 'loss/train': 1.5893405675888062} 08/31/2021 01:01:30 - INFO - __main__ - Step 65198: {'lr': 0.00030682763609835793, 'samples': 12518016, 'steps': 65197, 'loss/train': 0.2451174259185791} 08/31/2021 01:01:30 - INFO - __main__ - Step 65199: {'lr': 0.0003068224682594487, 'samples': 12518208, 'steps': 65198, 'loss/train': 0.9068466424942017} 08/31/2021 01:01:31 - INFO - __main__ - Step 65200: {'lr': 0.0003068173003949361, 'samples': 12518400, 'steps': 65199, 'loss/train': 1.2204580307006836} 08/31/2021 01:01:31 - INFO - __main__ - Step 65201: {'lr': 0.00030681213250482255, 'samples': 12518592, 'steps': 65200, 'loss/train': 0.9093047380447388} 08/31/2021 01:01:32 - INFO - __main__ - Step 65202: {'lr': 0.0003068069645891102, 'samples': 12518784, 'steps': 65201, 'loss/train': 1.299746036529541} 08/31/2021 01:01:33 - INFO - __main__ - Step 65203: {'lr': 0.0003068017966478016, 'samples': 12518976, 'steps': 65202, 'loss/train': 1.619137167930603} 08/31/2021 01:01:33 - INFO - __main__ - Step 65204: {'lr': 0.000306796628680899, 'samples': 12519168, 'steps': 65203, 'loss/train': 0.6598619222640991} 08/31/2021 01:01:34 - INFO - __main__ - Step 65205: {'lr': 0.00030679146068840463, 'samples': 12519360, 'steps': 65204, 'loss/train': 1.6399508714675903} 08/31/2021 01:01:34 - INFO - __main__ - Step 65206: {'lr': 0.00030678629267032106, 'samples': 12519552, 'steps': 65205, 'loss/train': 1.4511638879776} 08/31/2021 01:01:36 - INFO - __main__ - Step 65207: {'lr': 0.0003067811246266503, 'samples': 12519744, 'steps': 65206, 'loss/train': 1.314669132232666} 08/31/2021 01:01:36 - INFO - __main__ - Step 65208: {'lr': 0.00030677595655739494, 'samples': 12519936, 'steps': 65207, 'loss/train': 1.834500789642334} 08/31/2021 01:01:36 - INFO - __main__ - Step 65209: {'lr': 0.0003067707884625571, 'samples': 12520128, 'steps': 65208, 'loss/train': 1.0248457193374634} 08/31/2021 01:01:37 - INFO - __main__ - Step 65210: {'lr': 0.00030676562034213933, 'samples': 12520320, 'steps': 65209, 'loss/train': 1.342811942100525} 08/31/2021 01:01:37 - INFO - __main__ - Step 65211: {'lr': 0.0003067604521961438, 'samples': 12520512, 'steps': 65210, 'loss/train': 1.2149255275726318} 08/31/2021 01:01:38 - INFO - __main__ - Step 65212: {'lr': 0.00030675528402457293, 'samples': 12520704, 'steps': 65211, 'loss/train': 0.8595535159111023} 08/31/2021 01:01:39 - INFO - __main__ - Step 65213: {'lr': 0.000306750115827429, 'samples': 12520896, 'steps': 65212, 'loss/train': 1.539555549621582} 08/31/2021 01:01:39 - INFO - __main__ - Step 65214: {'lr': 0.0003067449476047143, 'samples': 12521088, 'steps': 65213, 'loss/train': 2.168956995010376} 08/31/2021 01:01:40 - INFO - __main__ - Step 65215: {'lr': 0.00030673977935643116, 'samples': 12521280, 'steps': 65214, 'loss/train': 1.4388759136199951} 08/31/2021 01:01:40 - INFO - __main__ - Step 65216: {'lr': 0.00030673461108258207, 'samples': 12521472, 'steps': 65215, 'loss/train': 1.7073516845703125} 08/31/2021 01:01:42 - INFO - __main__ - Step 65217: {'lr': 0.0003067294427831692, 'samples': 12521664, 'steps': 65216, 'loss/train': 1.2788313627243042} 08/31/2021 01:01:42 - INFO - __main__ - Step 65218: {'lr': 0.00030672427445819486, 'samples': 12521856, 'steps': 65217, 'loss/train': 1.3405581712722778} 08/31/2021 01:01:43 - INFO - __main__ - Step 65219: {'lr': 0.00030671910610766145, 'samples': 12522048, 'steps': 65218, 'loss/train': 1.3540922403335571} 08/31/2021 01:01:43 - INFO - __main__ - Step 65220: {'lr': 0.0003067139377315713, 'samples': 12522240, 'steps': 65219, 'loss/train': 2.161436080932617} 08/31/2021 01:01:43 - INFO - __main__ - Step 65221: {'lr': 0.00030670876932992674, 'samples': 12522432, 'steps': 65220, 'loss/train': 1.1055917739868164} 08/31/2021 01:01:44 - INFO - __main__ - Step 65222: {'lr': 0.0003067036009027301, 'samples': 12522624, 'steps': 65221, 'loss/train': 0.21600133180618286} 08/31/2021 01:01:46 - INFO - __main__ - Step 65223: {'lr': 0.0003066984324499837, 'samples': 12522816, 'steps': 65222, 'loss/train': 1.2278404235839844} 08/31/2021 01:01:46 - INFO - __main__ - Step 65224: {'lr': 0.0003066932639716898, 'samples': 12523008, 'steps': 65223, 'loss/train': 1.5523344278335571} 08/31/2021 01:01:46 - INFO - __main__ - Step 65225: {'lr': 0.0003066880954678508, 'samples': 12523200, 'steps': 65224, 'loss/train': 0.8929287195205688} 08/31/2021 01:01:47 - INFO - __main__ - Step 65226: {'lr': 0.00030668292693846903, 'samples': 12523392, 'steps': 65225, 'loss/train': 1.3701552152633667} 08/31/2021 01:01:47 - INFO - __main__ - Step 65227: {'lr': 0.0003066777583835468, 'samples': 12523584, 'steps': 65226, 'loss/train': 0.03697395697236061} 08/31/2021 01:01:48 - INFO - __main__ - Step 65228: {'lr': 0.0003066725898030865, 'samples': 12523776, 'steps': 65227, 'loss/train': 0.03202393278479576} 08/31/2021 01:01:50 - INFO - __main__ - Step 65229: {'lr': 0.0003066674211970904, 'samples': 12523968, 'steps': 65228, 'loss/train': 1.3447917699813843} 08/31/2021 01:01:50 - INFO - __main__ - Step 65230: {'lr': 0.0003066622525655608, 'samples': 12524160, 'steps': 65229, 'loss/train': 1.6941652297973633} 08/31/2021 01:01:51 - INFO - __main__ - Step 65231: {'lr': 0.00030665708390850005, 'samples': 12524352, 'steps': 65230, 'loss/train': 1.0924547910690308} 08/31/2021 01:01:51 - INFO - __main__ - Step 65232: {'lr': 0.00030665191522591054, 'samples': 12524544, 'steps': 65231, 'loss/train': 1.196901559829712} 08/31/2021 01:01:51 - INFO - __main__ - Step 65233: {'lr': 0.0003066467465177945, 'samples': 12524736, 'steps': 65232, 'loss/train': 2.198559522628784} 08/31/2021 01:01:52 - INFO - __main__ - Step 65234: {'lr': 0.0003066415777841543, 'samples': 12524928, 'steps': 65233, 'loss/train': 1.749685287475586} 08/31/2021 01:01:53 - INFO - __main__ - Step 65235: {'lr': 0.0003066364090249923, 'samples': 12525120, 'steps': 65234, 'loss/train': 1.1848537921905518} 08/31/2021 01:01:54 - INFO - __main__ - Step 65236: {'lr': 0.00030663124024031085, 'samples': 12525312, 'steps': 65235, 'loss/train': 1.2967458963394165} 08/31/2021 01:01:54 - INFO - __main__ - Step 65237: {'lr': 0.0003066260714301122, 'samples': 12525504, 'steps': 65236, 'loss/train': 1.7289050817489624} 08/31/2021 01:01:54 - INFO - __main__ - Step 65238: {'lr': 0.0003066209025943987, 'samples': 12525696, 'steps': 65237, 'loss/train': 0.89073246717453} 08/31/2021 01:01:55 - INFO - __main__ - Step 65239: {'lr': 0.00030661573373317273, 'samples': 12525888, 'steps': 65238, 'loss/train': 2.2445068359375} 08/31/2021 01:01:56 - INFO - __main__ - Step 65240: {'lr': 0.00030661056484643657, 'samples': 12526080, 'steps': 65239, 'loss/train': 0.779342770576477} 08/31/2021 01:01:57 - INFO - __main__ - Step 65241: {'lr': 0.00030660539593419255, 'samples': 12526272, 'steps': 65240, 'loss/train': 1.3655064105987549} 08/31/2021 01:01:57 - INFO - __main__ - Step 65242: {'lr': 0.0003066002269964431, 'samples': 12526464, 'steps': 65241, 'loss/train': 1.4496300220489502} 08/31/2021 01:01:57 - INFO - __main__ - Step 65243: {'lr': 0.0003065950580331904, 'samples': 12526656, 'steps': 65242, 'loss/train': 1.308357834815979} 08/31/2021 01:01:58 - INFO - __main__ - Step 65244: {'lr': 0.00030658988904443677, 'samples': 12526848, 'steps': 65243, 'loss/train': 0.7352167963981628} 08/31/2021 01:01:59 - INFO - __main__ - Step 65245: {'lr': 0.00030658472003018466, 'samples': 12527040, 'steps': 65244, 'loss/train': 1.403586983680725} 08/31/2021 01:02:00 - INFO - __main__ - Step 65246: {'lr': 0.00030657955099043635, 'samples': 12527232, 'steps': 65245, 'loss/train': 1.6381748914718628} 08/31/2021 01:02:00 - INFO - __main__ - Step 65247: {'lr': 0.00030657438192519416, 'samples': 12527424, 'steps': 65246, 'loss/train': 1.820156455039978} 08/31/2021 01:02:00 - INFO - __main__ - Step 65248: {'lr': 0.0003065692128344604, 'samples': 12527616, 'steps': 65247, 'loss/train': 1.135299563407898} 08/31/2021 01:02:01 - INFO - __main__ - Step 65249: {'lr': 0.00030656404371823753, 'samples': 12527808, 'steps': 65248, 'loss/train': 1.41089928150177} 08/31/2021 01:02:02 - INFO - __main__ - Step 65250: {'lr': 0.0003065588745765277, 'samples': 12528000, 'steps': 65249, 'loss/train': 1.3189048767089844} 08/31/2021 01:02:03 - INFO - __main__ - Step 65251: {'lr': 0.0003065537054093333, 'samples': 12528192, 'steps': 65250, 'loss/train': 2.320298433303833} 08/31/2021 01:02:03 - INFO - __main__ - Step 65252: {'lr': 0.00030654853621665665, 'samples': 12528384, 'steps': 65251, 'loss/train': 1.6081297397613525} 08/31/2021 01:02:03 - INFO - __main__ - Step 65253: {'lr': 0.0003065433669985002, 'samples': 12528576, 'steps': 65252, 'loss/train': 1.1435214281082153} 08/31/2021 01:02:04 - INFO - __main__ - Step 65254: {'lr': 0.0003065381977548661, 'samples': 12528768, 'steps': 65253, 'loss/train': 1.833910584449768} 08/31/2021 01:02:05 - INFO - __main__ - Step 65255: {'lr': 0.00030653302848575683, 'samples': 12528960, 'steps': 65254, 'loss/train': 1.1593632698059082} 08/31/2021 01:02:06 - INFO - __main__ - Step 65256: {'lr': 0.00030652785919117466, 'samples': 12529152, 'steps': 65255, 'loss/train': 0.7426586151123047} 08/31/2021 01:02:06 - INFO - __main__ - Step 65257: {'lr': 0.0003065226898711218, 'samples': 12529344, 'steps': 65256, 'loss/train': 1.1590896844863892} 08/31/2021 01:02:06 - INFO - __main__ - Step 65258: {'lr': 0.0003065175205256008, 'samples': 12529536, 'steps': 65257, 'loss/train': 1.0784540176391602} 08/31/2021 01:02:07 - INFO - __main__ - Step 65259: {'lr': 0.0003065123511546138, 'samples': 12529728, 'steps': 65258, 'loss/train': 1.4275503158569336} 08/31/2021 01:02:08 - INFO - __main__ - Step 65260: {'lr': 0.0003065071817581632, 'samples': 12529920, 'steps': 65259, 'loss/train': 2.0469226837158203} 08/31/2021 01:02:09 - INFO - __main__ - Step 65261: {'lr': 0.0003065020123362514, 'samples': 12530112, 'steps': 65260, 'loss/train': 1.5659664869308472} 08/31/2021 01:02:09 - INFO - __main__ - Step 65262: {'lr': 0.0003064968428888806, 'samples': 12530304, 'steps': 65261, 'loss/train': 0.24862436950206757} 08/31/2021 01:02:09 - INFO - __main__ - Step 65263: {'lr': 0.0003064916734160532, 'samples': 12530496, 'steps': 65262, 'loss/train': 1.0003474950790405} 08/31/2021 01:02:10 - INFO - __main__ - Step 65264: {'lr': 0.0003064865039177716, 'samples': 12530688, 'steps': 65263, 'loss/train': 0.7393397688865662} 08/31/2021 01:02:12 - INFO - __main__ - Step 65265: {'lr': 0.00030648133439403795, 'samples': 12530880, 'steps': 65264, 'loss/train': 1.2532850503921509} 08/31/2021 01:02:12 - INFO - __main__ - Step 65266: {'lr': 0.00030647616484485475, 'samples': 12531072, 'steps': 65265, 'loss/train': 1.523661732673645} 08/31/2021 01:02:13 - INFO - __main__ - Step 65267: {'lr': 0.00030647099527022424, 'samples': 12531264, 'steps': 65266, 'loss/train': 0.590590238571167} 08/31/2021 01:02:13 - INFO - __main__ - Step 65268: {'lr': 0.0003064658256701488, 'samples': 12531456, 'steps': 65267, 'loss/train': 1.3952745199203491} 08/31/2021 01:02:13 - INFO - __main__ - Step 65269: {'lr': 0.0003064606560446308, 'samples': 12531648, 'steps': 65268, 'loss/train': 0.8797617554664612} 08/31/2021 01:02:14 - INFO - __main__ - Step 65270: {'lr': 0.0003064554863936723, 'samples': 12531840, 'steps': 65269, 'loss/train': 0.9369128942489624} 08/31/2021 01:02:15 - INFO - __main__ - Step 65271: {'lr': 0.000306450316717276, 'samples': 12532032, 'steps': 65270, 'loss/train': 0.05356859043240547} 08/31/2021 01:02:16 - INFO - __main__ - Step 65272: {'lr': 0.00030644514701544395, 'samples': 12532224, 'steps': 65271, 'loss/train': 1.4829695224761963} 08/31/2021 01:02:16 - INFO - __main__ - Step 65273: {'lr': 0.00030643997728817864, 'samples': 12532416, 'steps': 65272, 'loss/train': 0.7589545249938965} 08/31/2021 01:02:16 - INFO - __main__ - Step 65274: {'lr': 0.0003064348075354823, 'samples': 12532608, 'steps': 65273, 'loss/train': 1.245417833328247} 08/31/2021 01:02:17 - INFO - __main__ - Step 65275: {'lr': 0.00030642963775735733, 'samples': 12532800, 'steps': 65274, 'loss/train': 1.5071918964385986} 08/31/2021 01:02:17 - INFO - __main__ - Step 65276: {'lr': 0.00030642446795380615, 'samples': 12532992, 'steps': 65275, 'loss/train': 1.2894372940063477} 08/31/2021 01:02:18 - INFO - __main__ - Step 65277: {'lr': 0.0003064192981248308, 'samples': 12533184, 'steps': 65276, 'loss/train': 1.5430562496185303} 08/31/2021 01:02:19 - INFO - __main__ - Step 65278: {'lr': 0.0003064141282704339, 'samples': 12533376, 'steps': 65277, 'loss/train': 0.7801702618598938} 08/31/2021 01:02:19 - INFO - __main__ - Step 65279: {'lr': 0.0003064089583906176, 'samples': 12533568, 'steps': 65278, 'loss/train': 0.913831889629364} 08/31/2021 01:02:20 - INFO - __main__ - Step 65280: {'lr': 0.0003064037884853843, 'samples': 12533760, 'steps': 65279, 'loss/train': 1.5912412405014038} 08/31/2021 01:02:20 - INFO - __main__ - Step 65281: {'lr': 0.00030639861855473634, 'samples': 12533952, 'steps': 65280, 'loss/train': 0.646050214767456} 08/31/2021 01:02:22 - INFO - __main__ - Step 65282: {'lr': 0.000306393448598676, 'samples': 12534144, 'steps': 65281, 'loss/train': 1.122941255569458} 08/31/2021 01:02:22 - INFO - __main__ - Step 65283: {'lr': 0.00030638827861720574, 'samples': 12534336, 'steps': 65282, 'loss/train': 1.092604398727417} 08/31/2021 01:02:23 - INFO - __main__ - Step 65284: {'lr': 0.00030638310861032773, 'samples': 12534528, 'steps': 65283, 'loss/train': 1.7483227252960205} 08/31/2021 01:02:23 - INFO - __main__ - Step 65285: {'lr': 0.00030637793857804437, 'samples': 12534720, 'steps': 65284, 'loss/train': 0.4135191738605499} 08/31/2021 01:02:23 - INFO - __main__ - Step 65286: {'lr': 0.00030637276852035793, 'samples': 12534912, 'steps': 65285, 'loss/train': 2.1518776416778564} 08/31/2021 01:02:25 - INFO - __main__ - Step 65287: {'lr': 0.00030636759843727086, 'samples': 12535104, 'steps': 65286, 'loss/train': 1.1349259614944458} 08/31/2021 01:02:26 - INFO - __main__ - Step 65288: {'lr': 0.0003063624283287854, 'samples': 12535296, 'steps': 65287, 'loss/train': 0.932526171207428} 08/31/2021 01:02:26 - INFO - __main__ - Step 65289: {'lr': 0.0003063572581949039, 'samples': 12535488, 'steps': 65288, 'loss/train': 1.5245333909988403} 08/31/2021 01:02:27 - INFO - __main__ - Step 65290: {'lr': 0.00030635208803562867, 'samples': 12535680, 'steps': 65289, 'loss/train': 0.7644720077514648} 08/31/2021 01:02:27 - INFO - __main__ - Step 65291: {'lr': 0.0003063469178509621, 'samples': 12535872, 'steps': 65290, 'loss/train': 1.6293435096740723} 08/31/2021 01:02:27 - INFO - __main__ - Step 65292: {'lr': 0.00030634174764090645, 'samples': 12536064, 'steps': 65291, 'loss/train': 1.4052040576934814} 08/31/2021 01:02:29 - INFO - __main__ - Step 65293: {'lr': 0.00030633657740546403, 'samples': 12536256, 'steps': 65292, 'loss/train': 1.225758671760559} 08/31/2021 01:02:29 - INFO - __main__ - Step 65294: {'lr': 0.00030633140714463725, 'samples': 12536448, 'steps': 65293, 'loss/train': 0.7700873613357544} 08/31/2021 01:02:30 - INFO - __main__ - Step 65295: {'lr': 0.0003063262368584284, 'samples': 12536640, 'steps': 65294, 'loss/train': 0.9255138039588928} 08/31/2021 01:02:30 - INFO - __main__ - Step 65296: {'lr': 0.0003063210665468399, 'samples': 12536832, 'steps': 65295, 'loss/train': 1.1014186143875122} 08/31/2021 01:02:31 - INFO - __main__ - Step 65297: {'lr': 0.00030631589620987393, 'samples': 12537024, 'steps': 65296, 'loss/train': 0.4793717861175537} 08/31/2021 01:02:32 - INFO - __main__ - Step 65298: {'lr': 0.0003063107258475329, 'samples': 12537216, 'steps': 65297, 'loss/train': 0.4943670928478241} 08/31/2021 01:02:32 - INFO - __main__ - Step 65299: {'lr': 0.0003063055554598191, 'samples': 12537408, 'steps': 65298, 'loss/train': 1.13809335231781} 08/31/2021 01:02:33 - INFO - __main__ - Step 65300: {'lr': 0.0003063003850467349, 'samples': 12537600, 'steps': 65299, 'loss/train': 1.2476929426193237} 08/31/2021 01:02:33 - INFO - __main__ - Step 65301: {'lr': 0.0003062952146082826, 'samples': 12537792, 'steps': 65300, 'loss/train': 1.1723254919052124} 08/31/2021 01:02:33 - INFO - __main__ - Step 65302: {'lr': 0.00030629004414446453, 'samples': 12537984, 'steps': 65301, 'loss/train': 0.7291707992553711} 08/31/2021 01:02:35 - INFO - __main__ - Step 65303: {'lr': 0.00030628487365528314, 'samples': 12538176, 'steps': 65302, 'loss/train': 0.7751654982566833} 08/31/2021 01:02:35 - INFO - __main__ - Step 65304: {'lr': 0.0003062797031407406, 'samples': 12538368, 'steps': 65303, 'loss/train': 0.986967921257019} 08/31/2021 01:02:36 - INFO - __main__ - Step 65305: {'lr': 0.0003062745326008393, 'samples': 12538560, 'steps': 65304, 'loss/train': 0.8790035247802734} 08/31/2021 01:02:36 - INFO - __main__ - Step 65306: {'lr': 0.0003062693620355815, 'samples': 12538752, 'steps': 65305, 'loss/train': 1.5665104389190674} 08/31/2021 01:02:36 - INFO - __main__ - Step 65307: {'lr': 0.00030626419144496957, 'samples': 12538944, 'steps': 65306, 'loss/train': 1.4642003774642944} 08/31/2021 01:02:38 - INFO - __main__ - Step 65308: {'lr': 0.0003062590208290059, 'samples': 12539136, 'steps': 65307, 'loss/train': 0.928884744644165} 08/31/2021 01:02:38 - INFO - __main__ - Step 65309: {'lr': 0.00030625385018769285, 'samples': 12539328, 'steps': 65308, 'loss/train': 1.9493886232376099} 08/31/2021 01:02:39 - INFO - __main__ - Step 65310: {'lr': 0.0003062486795210327, 'samples': 12539520, 'steps': 65309, 'loss/train': 1.3687663078308105} 08/31/2021 01:02:39 - INFO - __main__ - Step 65311: {'lr': 0.0003062435088290277, 'samples': 12539712, 'steps': 65310, 'loss/train': 0.08828943222761154} 08/31/2021 01:02:39 - INFO - __main__ - Step 65312: {'lr': 0.0003062383381116802, 'samples': 12539904, 'steps': 65311, 'loss/train': 1.2767094373703003} 08/31/2021 01:02:40 - INFO - __main__ - Step 65313: {'lr': 0.00030623316736899263, 'samples': 12540096, 'steps': 65312, 'loss/train': 0.7039202451705933} 08/31/2021 01:02:41 - INFO - __main__ - Step 65314: {'lr': 0.00030622799660096723, 'samples': 12540288, 'steps': 65313, 'loss/train': 1.584833025932312} 08/31/2021 01:02:42 - INFO - __main__ - Step 65315: {'lr': 0.0003062228258076064, 'samples': 12540480, 'steps': 65314, 'loss/train': 1.1392016410827637} 08/31/2021 01:02:42 - INFO - __main__ - Step 65316: {'lr': 0.00030621765498891246, 'samples': 12540672, 'steps': 65315, 'loss/train': 1.134868860244751} 08/31/2021 01:02:42 - INFO - __main__ - Step 65317: {'lr': 0.0003062124841448877, 'samples': 12540864, 'steps': 65316, 'loss/train': 1.3588521480560303} 08/31/2021 01:02:43 - INFO - __main__ - Step 65318: {'lr': 0.00030620731327553444, 'samples': 12541056, 'steps': 65317, 'loss/train': 1.6490507125854492} 08/31/2021 01:02:44 - INFO - __main__ - Step 65319: {'lr': 0.000306202142380855, 'samples': 12541248, 'steps': 65318, 'loss/train': 0.9353638887405396} 08/31/2021 01:02:45 - INFO - __main__ - Step 65320: {'lr': 0.0003061969714608517, 'samples': 12541440, 'steps': 65319, 'loss/train': 1.107518196105957} 08/31/2021 01:02:45 - INFO - __main__ - Step 65321: {'lr': 0.00030619180051552695, 'samples': 12541632, 'steps': 65320, 'loss/train': 1.0536773204803467} 08/31/2021 01:02:45 - INFO - __main__ - Step 65322: {'lr': 0.00030618662954488314, 'samples': 12541824, 'steps': 65321, 'loss/train': 0.7140889763832092} 08/31/2021 01:02:46 - INFO - __main__ - Step 65323: {'lr': 0.00030618145854892245, 'samples': 12542016, 'steps': 65322, 'loss/train': 2.0609688758850098} 08/31/2021 01:02:47 - INFO - __main__ - Step 65324: {'lr': 0.00030617628752764727, 'samples': 12542208, 'steps': 65323, 'loss/train': 1.2198058366775513} 08/31/2021 01:02:48 - INFO - __main__ - Step 65325: {'lr': 0.0003061711164810598, 'samples': 12542400, 'steps': 65324, 'loss/train': 1.339455246925354} 08/31/2021 01:02:48 - INFO - __main__ - Step 65326: {'lr': 0.00030616594540916264, 'samples': 12542592, 'steps': 65325, 'loss/train': 1.645803451538086} 08/31/2021 01:02:48 - INFO - __main__ - Step 65327: {'lr': 0.0003061607743119579, 'samples': 12542784, 'steps': 65326, 'loss/train': 1.2720084190368652} 08/31/2021 01:02:49 - INFO - __main__ - Step 65328: {'lr': 0.000306155603189448, 'samples': 12542976, 'steps': 65327, 'loss/train': 1.61607027053833} 08/31/2021 01:02:50 - INFO - __main__ - Step 65329: {'lr': 0.0003061504320416352, 'samples': 12543168, 'steps': 65328, 'loss/train': 1.4218889474868774} 08/31/2021 01:02:51 - INFO - __main__ - Step 65330: {'lr': 0.000306145260868522, 'samples': 12543360, 'steps': 65329, 'loss/train': 1.728495478630066} 08/31/2021 01:02:51 - INFO - __main__ - Step 65331: {'lr': 0.0003061400896701105, 'samples': 12543552, 'steps': 65330, 'loss/train': 1.6888155937194824} 08/31/2021 01:02:52 - INFO - __main__ - Step 65332: {'lr': 0.00030613491844640325, 'samples': 12543744, 'steps': 65331, 'loss/train': 1.5354582071304321} 08/31/2021 01:02:52 - INFO - __main__ - Step 65333: {'lr': 0.0003061297471974024, 'samples': 12543936, 'steps': 65332, 'loss/train': 1.4867109060287476} 08/31/2021 01:02:52 - INFO - __main__ - Step 65334: {'lr': 0.0003061245759231103, 'samples': 12544128, 'steps': 65333, 'loss/train': 0.2137824445962906} 08/31/2021 01:02:54 - INFO - __main__ - Step 65335: {'lr': 0.0003061194046235295, 'samples': 12544320, 'steps': 65334, 'loss/train': 0.028480736538767815} 08/31/2021 01:02:54 - INFO - __main__ - Step 65336: {'lr': 0.00030611423329866204, 'samples': 12544512, 'steps': 65335, 'loss/train': 1.5702605247497559} 08/31/2021 01:02:55 - INFO - __main__ - Step 65337: {'lr': 0.0003061090619485104, 'samples': 12544704, 'steps': 65336, 'loss/train': 1.6134980916976929} 08/31/2021 01:02:55 - INFO - __main__ - Step 65338: {'lr': 0.0003061038905730769, 'samples': 12544896, 'steps': 65337, 'loss/train': 0.8564213514328003} 08/31/2021 01:02:55 - INFO - __main__ - Step 65339: {'lr': 0.00030609871917236373, 'samples': 12545088, 'steps': 65338, 'loss/train': 1.1316055059432983} 08/31/2021 01:02:57 - INFO - __main__ - Step 65340: {'lr': 0.00030609354774637344, 'samples': 12545280, 'steps': 65339, 'loss/train': 1.6460126638412476} 08/31/2021 01:02:58 - INFO - __main__ - Step 65341: {'lr': 0.00030608837629510834, 'samples': 12545472, 'steps': 65340, 'loss/train': 1.0187140703201294} 08/31/2021 01:02:58 - INFO - __main__ - Step 65342: {'lr': 0.00030608320481857054, 'samples': 12545664, 'steps': 65341, 'loss/train': 2.2399191856384277} 08/31/2021 01:02:59 - INFO - __main__ - Step 65343: {'lr': 0.0003060780333167626, 'samples': 12545856, 'steps': 65342, 'loss/train': 1.606986403465271} 08/31/2021 01:02:59 - INFO - __main__ - Step 65344: {'lr': 0.00030607286178968677, 'samples': 12546048, 'steps': 65343, 'loss/train': 1.323708415031433} 08/31/2021 01:03:00 - INFO - __main__ - Step 65345: {'lr': 0.00030606769023734534, 'samples': 12546240, 'steps': 65344, 'loss/train': 0.33518466353416443} 08/31/2021 01:03:01 - INFO - __main__ - Step 65346: {'lr': 0.00030606251865974066, 'samples': 12546432, 'steps': 65345, 'loss/train': 0.7586167454719543} 08/31/2021 01:03:01 - INFO - __main__ - Step 65347: {'lr': 0.0003060573470568751, 'samples': 12546624, 'steps': 65346, 'loss/train': 1.0322881937026978} 08/31/2021 01:03:02 - INFO - __main__ - Step 65348: {'lr': 0.00030605217542875097, 'samples': 12546816, 'steps': 65347, 'loss/train': 1.8462631702423096} 08/31/2021 01:03:02 - INFO - __main__ - Step 65349: {'lr': 0.0003060470037753705, 'samples': 12547008, 'steps': 65348, 'loss/train': 0.717022716999054} 08/31/2021 01:03:03 - INFO - __main__ - Step 65350: {'lr': 0.00030604183209673625, 'samples': 12547200, 'steps': 65349, 'loss/train': 0.26397910714149475} 08/31/2021 01:03:04 - INFO - __main__ - Step 65351: {'lr': 0.0003060366603928504, 'samples': 12547392, 'steps': 65350, 'loss/train': 1.3524682521820068} 08/31/2021 01:03:04 - INFO - __main__ - Step 65352: {'lr': 0.00030603148866371524, 'samples': 12547584, 'steps': 65351, 'loss/train': 0.8862168788909912} 08/31/2021 01:03:05 - INFO - __main__ - Step 65353: {'lr': 0.0003060263169093332, 'samples': 12547776, 'steps': 65352, 'loss/train': 1.6093941926956177} 08/31/2021 01:03:05 - INFO - __main__ - Step 65354: {'lr': 0.0003060211451297065, 'samples': 12547968, 'steps': 65353, 'loss/train': 1.3892207145690918} 08/31/2021 01:03:06 - INFO - __main__ - Step 65355: {'lr': 0.00030601597332483753, 'samples': 12548160, 'steps': 65354, 'loss/train': 1.9119935035705566} 08/31/2021 01:03:07 - INFO - __main__ - Step 65356: {'lr': 0.0003060108014947287, 'samples': 12548352, 'steps': 65355, 'loss/train': 1.5612053871154785} 08/31/2021 01:03:07 - INFO - __main__ - Step 65357: {'lr': 0.0003060056296393823, 'samples': 12548544, 'steps': 65356, 'loss/train': 1.4192818403244019} 08/31/2021 01:03:08 - INFO - __main__ - Step 65358: {'lr': 0.00030600045775880055, 'samples': 12548736, 'steps': 65357, 'loss/train': 1.6976889371871948} 08/31/2021 01:03:08 - INFO - __main__ - Step 65359: {'lr': 0.00030599528585298585, 'samples': 12548928, 'steps': 65358, 'loss/train': 1.1929247379302979} 08/31/2021 01:03:08 - INFO - __main__ - Step 65360: {'lr': 0.00030599011392194053, 'samples': 12549120, 'steps': 65359, 'loss/train': 1.8115984201431274} 08/31/2021 01:03:10 - INFO - __main__ - Step 65361: {'lr': 0.000305984941965667, 'samples': 12549312, 'steps': 65360, 'loss/train': 1.291661024093628} 08/31/2021 01:03:10 - INFO - __main__ - Step 65362: {'lr': 0.0003059797699841674, 'samples': 12549504, 'steps': 65361, 'loss/train': 0.03530087694525719} 08/31/2021 01:03:11 - INFO - __main__ - Step 65363: {'lr': 0.00030597459797744434, 'samples': 12549696, 'steps': 65362, 'loss/train': 1.5015692710876465} 08/31/2021 01:03:11 - INFO - __main__ - Step 65364: {'lr': 0.0003059694259454999, 'samples': 12549888, 'steps': 65363, 'loss/train': 0.42019134759902954} 08/31/2021 01:03:11 - INFO - __main__ - Step 65365: {'lr': 0.00030596425388833656, 'samples': 12550080, 'steps': 65364, 'loss/train': 0.04514908790588379} 08/31/2021 01:03:13 - INFO - __main__ - Step 65366: {'lr': 0.0003059590818059565, 'samples': 12550272, 'steps': 65365, 'loss/train': 1.5094143152236938} 08/31/2021 01:03:13 - INFO - __main__ - Step 65367: {'lr': 0.0003059539096983622, 'samples': 12550464, 'steps': 65366, 'loss/train': 1.5701478719711304} 08/31/2021 01:03:14 - INFO - __main__ - Step 65368: {'lr': 0.00030594873756555584, 'samples': 12550656, 'steps': 65367, 'loss/train': 1.5590153932571411} 08/31/2021 01:03:14 - INFO - __main__ - Step 65369: {'lr': 0.00030594356540753994, 'samples': 12550848, 'steps': 65368, 'loss/train': 1.869443416595459} 08/31/2021 01:03:14 - INFO - __main__ - Step 65370: {'lr': 0.0003059383932243168, 'samples': 12551040, 'steps': 65369, 'loss/train': 1.1415507793426514} 08/31/2021 01:03:16 - INFO - __main__ - Step 65371: {'lr': 0.0003059332210158886, 'samples': 12551232, 'steps': 65370, 'loss/train': 1.2487038373947144} 08/31/2021 01:03:16 - INFO - __main__ - Step 65372: {'lr': 0.00030592804878225765, 'samples': 12551424, 'steps': 65371, 'loss/train': 1.111667513847351} 08/31/2021 01:03:17 - INFO - __main__ - Step 65373: {'lr': 0.00030592287652342646, 'samples': 12551616, 'steps': 65372, 'loss/train': 0.7935970425605774} 08/31/2021 01:03:17 - INFO - __main__ - Step 65374: {'lr': 0.0003059177042393974, 'samples': 12551808, 'steps': 65373, 'loss/train': 1.3558342456817627} 08/31/2021 01:03:17 - INFO - __main__ - Step 65375: {'lr': 0.0003059125319301725, 'samples': 12552000, 'steps': 65374, 'loss/train': 1.7394251823425293} 08/31/2021 01:03:19 - INFO - __main__ - Step 65376: {'lr': 0.0003059073595957544, 'samples': 12552192, 'steps': 65375, 'loss/train': 1.0173066854476929} 08/31/2021 01:03:19 - INFO - __main__ - Step 65377: {'lr': 0.00030590218723614525, 'samples': 12552384, 'steps': 65376, 'loss/train': 1.3585991859436035} 08/31/2021 01:03:20 - INFO - __main__ - Step 65378: {'lr': 0.0003058970148513475, 'samples': 12552576, 'steps': 65377, 'loss/train': 1.4440702199935913} 08/31/2021 01:03:20 - INFO - __main__ - Step 65379: {'lr': 0.0003058918424413634, 'samples': 12552768, 'steps': 65378, 'loss/train': 1.450331687927246} 08/31/2021 01:03:20 - INFO - __main__ - Step 65380: {'lr': 0.0003058866700061952, 'samples': 12552960, 'steps': 65379, 'loss/train': 1.3511501550674438} 08/31/2021 01:03:21 - INFO - __main__ - Step 65381: {'lr': 0.00030588149754584543, 'samples': 12553152, 'steps': 65380, 'loss/train': 0.9993184804916382} 08/31/2021 01:03:22 - INFO - __main__ - Step 65382: {'lr': 0.00030587632506031624, 'samples': 12553344, 'steps': 65381, 'loss/train': 1.486837387084961} 08/31/2021 01:03:23 - INFO - __main__ - Step 65383: {'lr': 0.0003058711525496102, 'samples': 12553536, 'steps': 65382, 'loss/train': 1.2671277523040771} 08/31/2021 01:03:23 - INFO - __main__ - Step 65384: {'lr': 0.00030586598001372935, 'samples': 12553728, 'steps': 65383, 'loss/train': 1.638203501701355} 08/31/2021 01:03:24 - INFO - __main__ - Step 65385: {'lr': 0.0003058608074526762, 'samples': 12553920, 'steps': 65384, 'loss/train': 1.1194007396697998} 08/31/2021 01:03:24 - INFO - __main__ - Step 65386: {'lr': 0.000305855634866453, 'samples': 12554112, 'steps': 65385, 'loss/train': 1.464186191558838} 08/31/2021 01:03:25 - INFO - __main__ - Step 65387: {'lr': 0.00030585046225506206, 'samples': 12554304, 'steps': 65386, 'loss/train': 1.3238593339920044} 08/31/2021 01:03:26 - INFO - __main__ - Step 65388: {'lr': 0.00030584528961850584, 'samples': 12554496, 'steps': 65387, 'loss/train': 1.0601996183395386} 08/31/2021 01:03:26 - INFO - __main__ - Step 65389: {'lr': 0.0003058401169567865, 'samples': 12554688, 'steps': 65388, 'loss/train': 1.0835189819335938} 08/31/2021 01:03:26 - INFO - __main__ - Step 65390: {'lr': 0.0003058349442699067, 'samples': 12554880, 'steps': 65389, 'loss/train': 1.386785626411438} 08/31/2021 01:03:27 - INFO - __main__ - Step 65391: {'lr': 0.00030582977155786835, 'samples': 12555072, 'steps': 65390, 'loss/train': 1.0749680995941162} 08/31/2021 01:03:29 - INFO - __main__ - Step 65392: {'lr': 0.000305824598820674, 'samples': 12555264, 'steps': 65391, 'loss/train': 0.3079562783241272} 08/31/2021 01:03:29 - INFO - __main__ - Step 65393: {'lr': 0.0003058194260583259, 'samples': 12555456, 'steps': 65392, 'loss/train': 0.8178128004074097} 08/31/2021 01:03:30 - INFO - __main__ - Step 65394: {'lr': 0.00030581425327082647, 'samples': 12555648, 'steps': 65393, 'loss/train': 1.7896173000335693} 08/31/2021 01:03:30 - INFO - __main__ - Step 65395: {'lr': 0.000305809080458178, 'samples': 12555840, 'steps': 65394, 'loss/train': 1.4996016025543213} 08/31/2021 01:03:30 - INFO - __main__ - Step 65396: {'lr': 0.00030580390762038277, 'samples': 12556032, 'steps': 65395, 'loss/train': 1.025526523590088} 08/31/2021 01:03:32 - INFO - __main__ - Step 65397: {'lr': 0.0003057987347574433, 'samples': 12556224, 'steps': 65396, 'loss/train': 1.5527220964431763} 08/31/2021 01:03:32 - INFO - __main__ - Step 65398: {'lr': 0.00030579356186936164, 'samples': 12556416, 'steps': 65397, 'loss/train': 0.6506005525588989} 08/31/2021 01:03:33 - INFO - __main__ - Step 65399: {'lr': 0.00030578838895614033, 'samples': 12556608, 'steps': 65398, 'loss/train': 1.7162628173828125} 08/31/2021 01:03:33 - INFO - __main__ - Step 65400: {'lr': 0.0003057832160177816, 'samples': 12556800, 'steps': 65399, 'loss/train': 0.13975289463996887} 08/31/2021 01:03:33 - INFO - __main__ - Step 65401: {'lr': 0.0003057780430542878, 'samples': 12556992, 'steps': 65400, 'loss/train': 0.9734500646591187} 08/31/2021 01:03:35 - INFO - __main__ - Step 65402: {'lr': 0.00030577287006566134, 'samples': 12557184, 'steps': 65401, 'loss/train': 1.857311725616455} 08/31/2021 01:03:35 - INFO - __main__ - Step 65403: {'lr': 0.00030576769705190445, 'samples': 12557376, 'steps': 65402, 'loss/train': 1.5781463384628296} 08/31/2021 01:03:36 - INFO - __main__ - Step 65404: {'lr': 0.0003057625240130195, 'samples': 12557568, 'steps': 65403, 'loss/train': 1.2986353635787964} 08/31/2021 01:03:36 - INFO - __main__ - Step 65405: {'lr': 0.0003057573509490088, 'samples': 12557760, 'steps': 65404, 'loss/train': 1.1898669004440308} 08/31/2021 01:03:36 - INFO - __main__ - Step 65406: {'lr': 0.00030575217785987473, 'samples': 12557952, 'steps': 65405, 'loss/train': 1.471035361289978} 08/31/2021 01:03:38 - INFO - __main__ - Step 65407: {'lr': 0.00030574700474561957, 'samples': 12558144, 'steps': 65406, 'loss/train': 1.7986111640930176} 08/31/2021 01:03:38 - INFO - __main__ - Step 65408: {'lr': 0.0003057418316062456, 'samples': 12558336, 'steps': 65407, 'loss/train': 0.9701345562934875} 08/31/2021 01:03:39 - INFO - __main__ - Step 65409: {'lr': 0.0003057366584417553, 'samples': 12558528, 'steps': 65408, 'loss/train': 1.710814356803894} 08/31/2021 01:03:39 - INFO - __main__ - Step 65410: {'lr': 0.000305731485252151, 'samples': 12558720, 'steps': 65409, 'loss/train': 0.3088211119174957} 08/31/2021 01:03:39 - INFO - __main__ - Step 65411: {'lr': 0.0003057263120374348, 'samples': 12558912, 'steps': 65410, 'loss/train': 1.588350772857666} 08/31/2021 01:03:41 - INFO - __main__ - Step 65412: {'lr': 0.00030572113879760927, 'samples': 12559104, 'steps': 65411, 'loss/train': 1.4046602249145508} 08/31/2021 01:03:41 - INFO - __main__ - Step 65413: {'lr': 0.0003057159655326766, 'samples': 12559296, 'steps': 65412, 'loss/train': 1.4372975826263428} 08/31/2021 01:03:42 - INFO - __main__ - Step 65414: {'lr': 0.0003057107922426392, 'samples': 12559488, 'steps': 65413, 'loss/train': 0.6909124255180359} 08/31/2021 01:03:42 - INFO - __main__ - Step 65415: {'lr': 0.00030570561892749945, 'samples': 12559680, 'steps': 65414, 'loss/train': 0.6323590874671936} 08/31/2021 01:03:42 - INFO - __main__ - Step 65416: {'lr': 0.00030570044558725953, 'samples': 12559872, 'steps': 65415, 'loss/train': 1.3942949771881104} 08/31/2021 01:03:43 - INFO - __main__ - Step 65417: {'lr': 0.00030569527222192185, 'samples': 12560064, 'steps': 65416, 'loss/train': 1.350322961807251} 08/31/2021 01:03:44 - INFO - __main__ - Step 65418: {'lr': 0.00030569009883148874, 'samples': 12560256, 'steps': 65417, 'loss/train': 0.9602599143981934} 08/31/2021 01:03:45 - INFO - __main__ - Step 65419: {'lr': 0.0003056849254159625, 'samples': 12560448, 'steps': 65418, 'loss/train': 0.9342049360275269} 08/31/2021 01:03:45 - INFO - __main__ - Step 65420: {'lr': 0.0003056797519753456, 'samples': 12560640, 'steps': 65419, 'loss/train': 1.1393790245056152} 08/31/2021 01:03:45 - INFO - __main__ - Step 65421: {'lr': 0.0003056745785096402, 'samples': 12560832, 'steps': 65420, 'loss/train': 1.3824578523635864} 08/31/2021 01:03:46 - INFO - __main__ - Step 65422: {'lr': 0.00030566940501884865, 'samples': 12561024, 'steps': 65421, 'loss/train': 1.2435543537139893} 08/31/2021 01:03:47 - INFO - __main__ - Step 65423: {'lr': 0.00030566423150297335, 'samples': 12561216, 'steps': 65422, 'loss/train': 1.6534020900726318} 08/31/2021 01:03:48 - INFO - __main__ - Step 65424: {'lr': 0.00030565905796201665, 'samples': 12561408, 'steps': 65423, 'loss/train': 0.5402517914772034} 08/31/2021 01:03:48 - INFO - __main__ - Step 65425: {'lr': 0.00030565388439598084, 'samples': 12561600, 'steps': 65424, 'loss/train': 1.4072133302688599} 08/31/2021 01:03:48 - INFO - __main__ - Step 65426: {'lr': 0.00030564871080486825, 'samples': 12561792, 'steps': 65425, 'loss/train': 0.9062454700469971} 08/31/2021 01:03:49 - INFO - __main__ - Step 65427: {'lr': 0.0003056435371886811, 'samples': 12561984, 'steps': 65426, 'loss/train': 0.7725446224212646} 08/31/2021 01:03:50 - INFO - __main__ - Step 65428: {'lr': 0.00030563836354742193, 'samples': 12562176, 'steps': 65427, 'loss/train': 1.5714434385299683} 08/31/2021 01:03:51 - INFO - __main__ - Step 65429: {'lr': 0.000305633189881093, 'samples': 12562368, 'steps': 65428, 'loss/train': 1.1407411098480225} 08/31/2021 01:03:51 - INFO - __main__ - Step 65430: {'lr': 0.0003056280161896965, 'samples': 12562560, 'steps': 65429, 'loss/train': 1.3342559337615967} 08/31/2021 01:03:52 - INFO - __main__ - Step 65431: {'lr': 0.00030562284247323497, 'samples': 12562752, 'steps': 65430, 'loss/train': 0.053595565259456635} 08/31/2021 01:03:52 - INFO - __main__ - Step 65432: {'lr': 0.0003056176687317106, 'samples': 12562944, 'steps': 65431, 'loss/train': 0.7255933880805969} 08/31/2021 01:03:53 - INFO - __main__ - Step 65433: {'lr': 0.00030561249496512577, 'samples': 12563136, 'steps': 65432, 'loss/train': 1.2721627950668335} 08/31/2021 01:03:54 - INFO - __main__ - Step 65434: {'lr': 0.00030560732117348283, 'samples': 12563328, 'steps': 65433, 'loss/train': 1.4163888692855835} 08/31/2021 01:03:54 - INFO - __main__ - Step 65435: {'lr': 0.00030560214735678403, 'samples': 12563520, 'steps': 65434, 'loss/train': 1.5344668626785278} 08/31/2021 01:03:55 - INFO - __main__ - Step 65436: {'lr': 0.00030559697351503187, 'samples': 12563712, 'steps': 65435, 'loss/train': 1.4815545082092285} 08/31/2021 01:03:55 - INFO - __main__ - Step 65437: {'lr': 0.0003055917996482285, 'samples': 12563904, 'steps': 65436, 'loss/train': 1.0166478157043457} 08/31/2021 01:03:57 - INFO - __main__ - Step 65438: {'lr': 0.00030558662575637635, 'samples': 12564096, 'steps': 65437, 'loss/train': 1.1588822603225708} 08/31/2021 01:03:57 - INFO - __main__ - Step 65439: {'lr': 0.0003055814518394777, 'samples': 12564288, 'steps': 65438, 'loss/train': 1.5594710111618042} 08/31/2021 01:03:57 - INFO - __main__ - Step 65440: {'lr': 0.0003055762778975349, 'samples': 12564480, 'steps': 65439, 'loss/train': 1.0479875802993774} 08/31/2021 01:03:58 - INFO - __main__ - Step 65441: {'lr': 0.0003055711039305503, 'samples': 12564672, 'steps': 65440, 'loss/train': 1.5295466184616089} 08/31/2021 01:03:58 - INFO - __main__ - Step 65442: {'lr': 0.0003055659299385262, 'samples': 12564864, 'steps': 65441, 'loss/train': 0.9162209630012512} 08/31/2021 01:03:58 - INFO - __main__ - Step 65443: {'lr': 0.00030556075592146493, 'samples': 12565056, 'steps': 65442, 'loss/train': 1.3160309791564941} 08/31/2021 01:04:00 - INFO - __main__ - Step 65444: {'lr': 0.00030555558187936896, 'samples': 12565248, 'steps': 65443, 'loss/train': 1.2982314825057983} 08/31/2021 01:04:00 - INFO - __main__ - Step 65445: {'lr': 0.00030555040781224044, 'samples': 12565440, 'steps': 65444, 'loss/train': 1.5482531785964966} 08/31/2021 01:04:01 - INFO - __main__ - Step 65446: {'lr': 0.0003055452337200817, 'samples': 12565632, 'steps': 65445, 'loss/train': 1.1800979375839233} 08/31/2021 01:04:01 - INFO - __main__ - Step 65447: {'lr': 0.00030554005960289513, 'samples': 12565824, 'steps': 65446, 'loss/train': 0.038209468126297} 08/31/2021 01:04:02 - INFO - __main__ - Step 65448: {'lr': 0.0003055348854606831, 'samples': 12566016, 'steps': 65447, 'loss/train': 1.299225926399231} 08/31/2021 01:04:04 - INFO - __main__ - Step 65449: {'lr': 0.000305529711293448, 'samples': 12566208, 'steps': 65448, 'loss/train': 2.5857608318328857} 08/31/2021 01:04:04 - INFO - __main__ - Step 65450: {'lr': 0.0003055245371011919, 'samples': 12566400, 'steps': 65449, 'loss/train': 1.6825381517410278} 08/31/2021 01:04:04 - INFO - __main__ - Step 65451: {'lr': 0.00030551936288391744, 'samples': 12566592, 'steps': 65450, 'loss/train': 1.5013864040374756} 08/31/2021 01:04:05 - INFO - __main__ - Step 65452: {'lr': 0.0003055141886416268, 'samples': 12566784, 'steps': 65451, 'loss/train': 1.0155662298202515} 08/31/2021 01:04:05 - INFO - __main__ - Step 65453: {'lr': 0.0003055090143743223, 'samples': 12566976, 'steps': 65452, 'loss/train': 1.2221181392669678} 08/31/2021 01:04:07 - INFO - __main__ - Step 65454: {'lr': 0.00030550384008200623, 'samples': 12567168, 'steps': 65453, 'loss/train': 0.06850052624940872} 08/31/2021 01:04:07 - INFO - __main__ - Step 65455: {'lr': 0.00030549866576468104, 'samples': 12567360, 'steps': 65454, 'loss/train': 1.3900820016860962} 08/31/2021 01:04:07 - INFO - __main__ - Step 65456: {'lr': 0.000305493491422349, 'samples': 12567552, 'steps': 65455, 'loss/train': 0.9984094500541687} 08/31/2021 01:04:08 - INFO - __main__ - Step 65457: {'lr': 0.0003054883170550125, 'samples': 12567744, 'steps': 65456, 'loss/train': 1.3410265445709229} 08/31/2021 01:04:08 - INFO - __main__ - Step 65458: {'lr': 0.0003054831426626737, 'samples': 12567936, 'steps': 65457, 'loss/train': 1.1324186325073242} 08/31/2021 01:04:10 - INFO - __main__ - Step 65459: {'lr': 0.00030547796824533516, 'samples': 12568128, 'steps': 65458, 'loss/train': 1.8552407026290894} 08/31/2021 01:04:11 - INFO - __main__ - Step 65460: {'lr': 0.0003054727938029991, 'samples': 12568320, 'steps': 65459, 'loss/train': 1.3655139207839966} 08/31/2021 01:04:11 - INFO - __main__ - Step 65461: {'lr': 0.0003054676193356678, 'samples': 12568512, 'steps': 65460, 'loss/train': 1.3080756664276123} 08/31/2021 01:04:11 - INFO - __main__ - Step 65462: {'lr': 0.00030546244484334364, 'samples': 12568704, 'steps': 65461, 'loss/train': 1.3975461721420288} 08/31/2021 01:04:12 - INFO - __main__ - Step 65463: {'lr': 0.000305457270326029, 'samples': 12568896, 'steps': 65462, 'loss/train': 0.1180807426571846} 08/31/2021 01:04:12 - INFO - __main__ - Step 65464: {'lr': 0.00030545209578372617, 'samples': 12569088, 'steps': 65463, 'loss/train': 0.09238910675048828} 08/31/2021 01:04:12 - INFO - __main__ - Step 65465: {'lr': 0.00030544692121643746, 'samples': 12569280, 'steps': 65464, 'loss/train': 0.08684872090816498} 08/31/2021 01:04:14 - INFO - __main__ - Step 65466: {'lr': 0.00030544174662416526, 'samples': 12569472, 'steps': 65465, 'loss/train': 0.025238599628210068} 08/31/2021 01:04:14 - INFO - __main__ - Step 65467: {'lr': 0.0003054365720069118, 'samples': 12569664, 'steps': 65466, 'loss/train': 1.5372382402420044} 08/31/2021 01:04:15 - INFO - __main__ - Step 65468: {'lr': 0.0003054313973646795, 'samples': 12569856, 'steps': 65467, 'loss/train': 1.118472933769226} 08/31/2021 01:04:15 - INFO - __main__ - Step 65469: {'lr': 0.0003054262226974708, 'samples': 12570048, 'steps': 65468, 'loss/train': 0.8707084059715271} 08/31/2021 01:04:15 - INFO - __main__ - Step 65470: {'lr': 0.0003054210480052877, 'samples': 12570240, 'steps': 65469, 'loss/train': 1.2123708724975586} 08/31/2021 01:04:17 - INFO - __main__ - Step 65471: {'lr': 0.0003054158732881328, 'samples': 12570432, 'steps': 65470, 'loss/train': 0.7128463983535767} 08/31/2021 01:04:18 - INFO - __main__ - Step 65472: {'lr': 0.0003054106985460084, 'samples': 12570624, 'steps': 65471, 'loss/train': 0.3604664206504822} 08/31/2021 01:04:18 - INFO - __main__ - Step 65473: {'lr': 0.00030540552377891674, 'samples': 12570816, 'steps': 65472, 'loss/train': 1.4155164957046509} 08/31/2021 01:04:18 - INFO - __main__ - Step 65474: {'lr': 0.00030540034898686024, 'samples': 12571008, 'steps': 65473, 'loss/train': 0.930700421333313} 08/31/2021 01:04:19 - INFO - __main__ - Step 65475: {'lr': 0.00030539517416984123, 'samples': 12571200, 'steps': 65474, 'loss/train': 1.4424867630004883} 08/31/2021 01:04:20 - INFO - __main__ - Step 65476: {'lr': 0.000305389999327862, 'samples': 12571392, 'steps': 65475, 'loss/train': 1.3000661134719849} 08/31/2021 01:04:21 - INFO - __main__ - Step 65477: {'lr': 0.0003053848244609248, 'samples': 12571584, 'steps': 65476, 'loss/train': 1.1761702299118042} 08/31/2021 01:04:21 - INFO - __main__ - Step 65478: {'lr': 0.0003053796495690321, 'samples': 12571776, 'steps': 65477, 'loss/train': 0.2412552535533905} 08/31/2021 01:04:21 - INFO - __main__ - Step 65479: {'lr': 0.00030537447465218623, 'samples': 12571968, 'steps': 65478, 'loss/train': 1.2745057344436646} 08/31/2021 01:04:22 - INFO - __main__ - Step 65480: {'lr': 0.00030536929971038953, 'samples': 12572160, 'steps': 65479, 'loss/train': 0.6010195016860962} 08/31/2021 01:04:22 - INFO - __main__ - Step 65481: {'lr': 0.00030536412474364415, 'samples': 12572352, 'steps': 65480, 'loss/train': 1.3028984069824219} 08/31/2021 01:04:23 - INFO - __main__ - Step 65482: {'lr': 0.0003053589497519526, 'samples': 12572544, 'steps': 65481, 'loss/train': 2.1467528343200684} 08/31/2021 01:04:24 - INFO - __main__ - Step 65483: {'lr': 0.0003053537747353171, 'samples': 12572736, 'steps': 65482, 'loss/train': 1.0863821506500244} 08/31/2021 01:04:24 - INFO - __main__ - Step 65484: {'lr': 0.00030534859969374013, 'samples': 12572928, 'steps': 65483, 'loss/train': 0.7901158332824707} 08/31/2021 01:04:25 - INFO - __main__ - Step 65485: {'lr': 0.00030534342462722387, 'samples': 12573120, 'steps': 65484, 'loss/train': 1.3181108236312866} 08/31/2021 01:04:25 - INFO - __main__ - Step 65486: {'lr': 0.00030533824953577084, 'samples': 12573312, 'steps': 65485, 'loss/train': 1.416019082069397} 08/31/2021 01:04:26 - INFO - __main__ - Step 65487: {'lr': 0.0003053330744193831, 'samples': 12573504, 'steps': 65486, 'loss/train': 1.1219581365585327} 08/31/2021 01:04:27 - INFO - __main__ - Step 65488: {'lr': 0.0003053278992780632, 'samples': 12573696, 'steps': 65487, 'loss/train': 1.1792430877685547} 08/31/2021 01:04:27 - INFO - __main__ - Step 65489: {'lr': 0.0003053227241118134, 'samples': 12573888, 'steps': 65488, 'loss/train': 1.2285432815551758} 08/31/2021 01:04:28 - INFO - __main__ - Step 65490: {'lr': 0.000305317548920636, 'samples': 12574080, 'steps': 65489, 'loss/train': 0.6102317571640015} 08/31/2021 01:04:28 - INFO - __main__ - Step 65491: {'lr': 0.0003053123737045335, 'samples': 12574272, 'steps': 65490, 'loss/train': 0.9824184775352478} 08/31/2021 01:04:30 - INFO - __main__ - Step 65492: {'lr': 0.0003053071984635079, 'samples': 12574464, 'steps': 65491, 'loss/train': 1.2301666736602783} 08/31/2021 01:04:30 - INFO - __main__ - Step 65493: {'lr': 0.00030530202319756184, 'samples': 12574656, 'steps': 65492, 'loss/train': 1.5633533000946045} 08/31/2021 01:04:31 - INFO - __main__ - Step 65494: {'lr': 0.0003052968479066975, 'samples': 12574848, 'steps': 65493, 'loss/train': 1.2178678512573242} 08/31/2021 01:04:31 - INFO - __main__ - Step 65495: {'lr': 0.0003052916725909173, 'samples': 12575040, 'steps': 65494, 'loss/train': 1.0237693786621094} 08/31/2021 01:04:31 - INFO - __main__ - Step 65496: {'lr': 0.00030528649725022346, 'samples': 12575232, 'steps': 65495, 'loss/train': 0.13464678823947906} 08/31/2021 01:04:32 - INFO - __main__ - Step 65497: {'lr': 0.0003052813218846184, 'samples': 12575424, 'steps': 65496, 'loss/train': 0.16016772389411926} 08/31/2021 01:04:33 - INFO - __main__ - Step 65498: {'lr': 0.0003052761464941045, 'samples': 12575616, 'steps': 65497, 'loss/train': 1.1956838369369507} 08/31/2021 01:04:34 - INFO - __main__ - Step 65499: {'lr': 0.00030527097107868395, 'samples': 12575808, 'steps': 65498, 'loss/train': 1.101978063583374} 08/31/2021 01:04:34 - INFO - __main__ - Step 65500: {'lr': 0.00030526579563835916, 'samples': 12576000, 'steps': 65499, 'loss/train': 1.1840393543243408} 08/31/2021 01:04:34 - INFO - __main__ - Step 65501: {'lr': 0.0003052606201731325, 'samples': 12576192, 'steps': 65500, 'loss/train': 1.160020351409912} 08/31/2021 01:04:35 - INFO - __main__ - Step 65502: {'lr': 0.0003052554446830062, 'samples': 12576384, 'steps': 65501, 'loss/train': 1.1487290859222412} 08/31/2021 01:04:37 - INFO - __main__ - Step 65503: {'lr': 0.00030525026916798263, 'samples': 12576576, 'steps': 65502, 'loss/train': 1.042948842048645} 08/31/2021 01:04:37 - INFO - __main__ - Step 65504: {'lr': 0.00030524509362806423, 'samples': 12576768, 'steps': 65503, 'loss/train': 1.2275941371917725} 08/31/2021 01:04:38 - INFO - __main__ - Step 65505: {'lr': 0.00030523991806325325, 'samples': 12576960, 'steps': 65504, 'loss/train': 0.06754051893949509} 08/31/2021 01:04:38 - INFO - __main__ - Step 65506: {'lr': 0.0003052347424735519, 'samples': 12577152, 'steps': 65505, 'loss/train': 1.301141381263733} 08/31/2021 01:04:38 - INFO - __main__ - Step 65507: {'lr': 0.00030522956685896267, 'samples': 12577344, 'steps': 65506, 'loss/train': 0.07068648934364319} 08/31/2021 01:04:39 - INFO - __main__ - Step 65508: {'lr': 0.0003052243912194879, 'samples': 12577536, 'steps': 65507, 'loss/train': 1.4461653232574463} 08/31/2021 01:04:41 - INFO - __main__ - Step 65509: {'lr': 0.0003052192155551298, 'samples': 12577728, 'steps': 65508, 'loss/train': 1.1686768531799316} 08/31/2021 01:04:41 - INFO - __main__ - Step 65510: {'lr': 0.00030521403986589086, 'samples': 12577920, 'steps': 65509, 'loss/train': 1.406132698059082} 08/31/2021 01:04:41 - INFO - __main__ - Step 65511: {'lr': 0.0003052088641517733, 'samples': 12578112, 'steps': 65510, 'loss/train': 0.3219676911830902} 08/31/2021 01:04:42 - INFO - __main__ - Step 65512: {'lr': 0.00030520368841277946, 'samples': 12578304, 'steps': 65511, 'loss/train': 1.770419716835022} 08/31/2021 01:04:42 - INFO - __main__ - Step 65513: {'lr': 0.00030519851264891167, 'samples': 12578496, 'steps': 65512, 'loss/train': 1.9473719596862793} 08/31/2021 01:04:43 - INFO - __main__ - Step 65514: {'lr': 0.0003051933368601723, 'samples': 12578688, 'steps': 65513, 'loss/train': 0.3327634334564209} 08/31/2021 01:04:44 - INFO - __main__ - Step 65515: {'lr': 0.00030518816104656364, 'samples': 12578880, 'steps': 65514, 'loss/train': 1.639843463897705} 08/31/2021 01:04:45 - INFO - __main__ - Step 65516: {'lr': 0.00030518298520808805, 'samples': 12579072, 'steps': 65515, 'loss/train': 0.09634692966938019} 08/31/2021 01:04:45 - INFO - __main__ - Step 65517: {'lr': 0.0003051778093447479, 'samples': 12579264, 'steps': 65516, 'loss/train': 1.6036688089370728} 08/31/2021 01:04:46 - INFO - __main__ - Step 65518: {'lr': 0.0003051726334565455, 'samples': 12579456, 'steps': 65517, 'loss/train': 1.1505919694900513} 08/31/2021 01:04:46 - INFO - __main__ - Step 65519: {'lr': 0.00030516745754348315, 'samples': 12579648, 'steps': 65518, 'loss/train': 1.5212005376815796} 08/31/2021 01:04:47 - INFO - __main__ - Step 65520: {'lr': 0.00030516228160556313, 'samples': 12579840, 'steps': 65519, 'loss/train': 0.872897744178772} 08/31/2021 01:04:48 - INFO - __main__ - Step 65521: {'lr': 0.0003051571056427879, 'samples': 12580032, 'steps': 65520, 'loss/train': 1.7957966327667236} 08/31/2021 01:04:48 - INFO - __main__ - Step 65522: {'lr': 0.0003051519296551597, 'samples': 12580224, 'steps': 65521, 'loss/train': 1.8613463640213013} 08/31/2021 01:04:49 - INFO - __main__ - Step 65523: {'lr': 0.0003051467536426809, 'samples': 12580416, 'steps': 65522, 'loss/train': 1.7184118032455444} 08/31/2021 01:04:49 - INFO - __main__ - Step 65524: {'lr': 0.0003051415776053538, 'samples': 12580608, 'steps': 65523, 'loss/train': 1.5138543844223022} 08/31/2021 01:04:51 - INFO - __main__ - Step 65525: {'lr': 0.00030513640154318077, 'samples': 12580800, 'steps': 65524, 'loss/train': 1.3826284408569336} 08/31/2021 01:04:51 - INFO - __main__ - Step 65526: {'lr': 0.00030513122545616414, 'samples': 12580992, 'steps': 65525, 'loss/train': 1.363770604133606} 08/31/2021 01:04:51 - INFO - __main__ - Step 65527: {'lr': 0.0003051260493443062, 'samples': 12581184, 'steps': 65526, 'loss/train': 1.6781185865402222} 08/31/2021 01:04:52 - INFO - __main__ - Step 65528: {'lr': 0.00030512087320760933, 'samples': 12581376, 'steps': 65527, 'loss/train': 1.2611083984375} 08/31/2021 01:04:52 - INFO - __main__ - Step 65529: {'lr': 0.00030511569704607587, 'samples': 12581568, 'steps': 65528, 'loss/train': 1.1740074157714844} 08/31/2021 01:04:54 - INFO - __main__ - Step 65530: {'lr': 0.0003051105208597081, 'samples': 12581760, 'steps': 65529, 'loss/train': 1.6582772731781006} 08/31/2021 01:04:54 - INFO - __main__ - Step 65531: {'lr': 0.0003051053446485084, 'samples': 12581952, 'steps': 65530, 'loss/train': 1.1281095743179321} 08/31/2021 01:04:54 - INFO - __main__ - Step 65532: {'lr': 0.0003051001684124791, 'samples': 12582144, 'steps': 65531, 'loss/train': 1.5246357917785645} 08/31/2021 01:04:55 - INFO - __main__ - Step 65533: {'lr': 0.00030509499215162247, 'samples': 12582336, 'steps': 65532, 'loss/train': 1.3084328174591064} 08/31/2021 01:04:55 - INFO - __main__ - Step 65534: {'lr': 0.0003050898158659409, 'samples': 12582528, 'steps': 65533, 'loss/train': 1.3747323751449585} 08/31/2021 01:04:55 - INFO - __main__ - Step 65535: {'lr': 0.00030508463955543667, 'samples': 12582720, 'steps': 65534, 'loss/train': 1.1627228260040283} 08/31/2021 01:04:57 - INFO - __main__ - Step 65536: {'lr': 0.0003050794632201122, 'samples': 12582912, 'steps': 65535, 'loss/train': 1.1082838773727417} 08/31/2021 01:04:58 - INFO - __main__ - Step 65537: {'lr': 0.0003050742868599698, 'samples': 12583104, 'steps': 65536, 'loss/train': 1.3850253820419312} 08/31/2021 01:04:58 - INFO - __main__ - Step 65538: {'lr': 0.0003050691104750117, 'samples': 12583296, 'steps': 65537, 'loss/train': 1.648293375968933} 08/31/2021 01:04:58 - INFO - __main__ - Step 65539: {'lr': 0.0003050639340652404, 'samples': 12583488, 'steps': 65538, 'loss/train': 1.3609986305236816} 08/31/2021 01:04:59 - INFO - __main__ - Step 65540: {'lr': 0.0003050587576306581, 'samples': 12583680, 'steps': 65539, 'loss/train': 1.2524360418319702} 08/31/2021 01:05:00 - INFO - __main__ - Step 65541: {'lr': 0.00030505358117126715, 'samples': 12583872, 'steps': 65540, 'loss/train': 1.5203332901000977} 08/31/2021 01:05:01 - INFO - __main__ - Step 65542: {'lr': 0.0003050484046870699, 'samples': 12584064, 'steps': 65541, 'loss/train': 1.148880124092102} 08/31/2021 01:05:01 - INFO - __main__ - Step 65543: {'lr': 0.00030504322817806874, 'samples': 12584256, 'steps': 65542, 'loss/train': 1.1090930700302124} 08/31/2021 01:05:01 - INFO - __main__ - Step 65544: {'lr': 0.0003050380516442659, 'samples': 12584448, 'steps': 65543, 'loss/train': 1.268911600112915} 08/31/2021 01:05:02 - INFO - __main__ - Step 65545: {'lr': 0.0003050328750856638, 'samples': 12584640, 'steps': 65544, 'loss/train': 0.3544308543205261} 08/31/2021 01:05:03 - INFO - __main__ - Step 65546: {'lr': 0.00030502769850226474, 'samples': 12584832, 'steps': 65545, 'loss/train': 1.5572277307510376} 08/31/2021 01:05:04 - INFO - __main__ - Step 65547: {'lr': 0.000305022521894071, 'samples': 12585024, 'steps': 65546, 'loss/train': 0.03900055214762688} 08/31/2021 01:05:04 - INFO - __main__ - Step 65548: {'lr': 0.000305017345261085, 'samples': 12585216, 'steps': 65547, 'loss/train': 1.5241512060165405} 08/31/2021 01:05:04 - INFO - __main__ - Step 65549: {'lr': 0.000305012168603309, 'samples': 12585408, 'steps': 65548, 'loss/train': 1.536971092224121} 08/31/2021 01:05:05 - INFO - __main__ - Step 65550: {'lr': 0.0003050069919207454, 'samples': 12585600, 'steps': 65549, 'loss/train': 1.1472582817077637} 08/31/2021 01:05:07 - INFO - __main__ - Step 65551: {'lr': 0.00030500181521339646, 'samples': 12585792, 'steps': 65550, 'loss/train': 0.7221522331237793} 08/31/2021 01:05:07 - INFO - __main__ - Step 65552: {'lr': 0.00030499663848126464, 'samples': 12585984, 'steps': 65551, 'loss/train': 1.5984482765197754} 08/31/2021 01:05:08 - INFO - __main__ - Step 65553: {'lr': 0.0003049914617243521, 'samples': 12586176, 'steps': 65552, 'loss/train': 1.4192724227905273} 08/31/2021 01:05:08 - INFO - __main__ - Step 65554: {'lr': 0.0003049862849426613, 'samples': 12586368, 'steps': 65553, 'loss/train': 1.1038672924041748} 08/31/2021 01:05:08 - INFO - __main__ - Step 65555: {'lr': 0.00030498110813619446, 'samples': 12586560, 'steps': 65554, 'loss/train': 1.074635624885559} 08/31/2021 01:05:09 - INFO - __main__ - Step 65556: {'lr': 0.000304975931304954, 'samples': 12586752, 'steps': 65555, 'loss/train': 1.5704437494277954} 08/31/2021 01:05:09 - INFO - __main__ - Step 65557: {'lr': 0.0003049707544489423, 'samples': 12586944, 'steps': 65556, 'loss/train': 0.03686600178480148} 08/31/2021 01:05:11 - INFO - __main__ - Step 65558: {'lr': 0.0003049655775681616, 'samples': 12587136, 'steps': 65557, 'loss/train': 1.6779683828353882} 08/31/2021 01:05:11 - INFO - __main__ - Step 65559: {'lr': 0.0003049604006626142, 'samples': 12587328, 'steps': 65558, 'loss/train': 1.0385903120040894} 08/31/2021 01:05:12 - INFO - __main__ - Step 65560: {'lr': 0.0003049552237323026, 'samples': 12587520, 'steps': 65559, 'loss/train': 0.955756425857544} 08/31/2021 01:05:12 - INFO - __main__ - Step 65561: {'lr': 0.0003049500467772289, 'samples': 12587712, 'steps': 65560, 'loss/train': 1.8698246479034424} 08/31/2021 01:05:12 - INFO - __main__ - Step 65562: {'lr': 0.0003049448697973956, 'samples': 12587904, 'steps': 65561, 'loss/train': 1.5860635042190552} 08/31/2021 01:05:14 - INFO - __main__ - Step 65563: {'lr': 0.00030493969279280506, 'samples': 12588096, 'steps': 65562, 'loss/train': 1.6989681720733643} 08/31/2021 01:05:15 - INFO - __main__ - Step 65564: {'lr': 0.0003049345157634594, 'samples': 12588288, 'steps': 65563, 'loss/train': 1.0945967435836792} 08/31/2021 01:05:15 - INFO - __main__ - Step 65565: {'lr': 0.0003049293387093613, 'samples': 12588480, 'steps': 65564, 'loss/train': 1.7983009815216064} 08/31/2021 01:05:15 - INFO - __main__ - Step 65566: {'lr': 0.0003049241616305127, 'samples': 12588672, 'steps': 65565, 'loss/train': 1.2110165357589722} 08/31/2021 01:05:16 - INFO - __main__ - Step 65567: {'lr': 0.00030491898452691626, 'samples': 12588864, 'steps': 65566, 'loss/train': 1.1529186964035034} 08/31/2021 01:05:17 - INFO - __main__ - Step 65568: {'lr': 0.000304913807398574, 'samples': 12589056, 'steps': 65567, 'loss/train': 1.3519152402877808} 08/31/2021 01:05:17 - INFO - __main__ - Step 65569: {'lr': 0.0003049086302454886, 'samples': 12589248, 'steps': 65568, 'loss/train': 1.5600913763046265} 08/31/2021 01:05:18 - INFO - __main__ - Step 65570: {'lr': 0.0003049034530676621, 'samples': 12589440, 'steps': 65569, 'loss/train': 1.5932154655456543} 08/31/2021 01:05:18 - INFO - __main__ - Step 65571: {'lr': 0.000304898275865097, 'samples': 12589632, 'steps': 65570, 'loss/train': 1.4467531442642212} 08/31/2021 01:05:18 - INFO - __main__ - Step 65572: {'lr': 0.0003048930986377956, 'samples': 12589824, 'steps': 65571, 'loss/train': 1.3988691568374634} 08/31/2021 01:05:20 - INFO - __main__ - Step 65573: {'lr': 0.0003048879213857602, 'samples': 12590016, 'steps': 65572, 'loss/train': 1.345668077468872} 08/31/2021 01:05:20 - INFO - __main__ - Step 65574: {'lr': 0.0003048827441089932, 'samples': 12590208, 'steps': 65573, 'loss/train': 1.2760107517242432} 08/31/2021 01:05:21 - INFO - __main__ - Step 65575: {'lr': 0.0003048775668074968, 'samples': 12590400, 'steps': 65574, 'loss/train': 0.7072003483772278} 08/31/2021 01:05:21 - INFO - __main__ - Step 65576: {'lr': 0.00030487238948127344, 'samples': 12590592, 'steps': 65575, 'loss/train': 1.5038321018218994} 08/31/2021 01:05:21 - INFO - __main__ - Step 65577: {'lr': 0.0003048672121303254, 'samples': 12590784, 'steps': 65576, 'loss/train': 1.5642590522766113} 08/31/2021 01:05:23 - INFO - __main__ - Step 65578: {'lr': 0.00030486203475465514, 'samples': 12590976, 'steps': 65577, 'loss/train': 1.6476410627365112} 08/31/2021 01:05:24 - INFO - __main__ - Step 65579: {'lr': 0.00030485685735426484, 'samples': 12591168, 'steps': 65578, 'loss/train': 0.22722014784812927} 08/31/2021 01:05:24 - INFO - __main__ - Step 65580: {'lr': 0.00030485167992915684, 'samples': 12591360, 'steps': 65579, 'loss/train': 0.14522886276245117} 08/31/2021 01:05:24 - INFO - __main__ - Step 65581: {'lr': 0.00030484650247933353, 'samples': 12591552, 'steps': 65580, 'loss/train': 1.514438271522522} 08/31/2021 01:05:25 - INFO - __main__ - Step 65582: {'lr': 0.0003048413250047973, 'samples': 12591744, 'steps': 65581, 'loss/train': 1.532418966293335} 08/31/2021 01:05:26 - INFO - __main__ - Step 65583: {'lr': 0.0003048361475055503, 'samples': 12591936, 'steps': 65582, 'loss/train': 1.343340516090393} 08/31/2021 01:05:26 - INFO - __main__ - Step 65584: {'lr': 0.0003048309699815951, 'samples': 12592128, 'steps': 65583, 'loss/train': 1.7715470790863037} 08/31/2021 01:05:27 - INFO - __main__ - Step 65585: {'lr': 0.0003048257924329339, 'samples': 12592320, 'steps': 65584, 'loss/train': 0.7833008170127869} 08/31/2021 01:05:27 - INFO - __main__ - Step 65586: {'lr': 0.00030482061485956905, 'samples': 12592512, 'steps': 65585, 'loss/train': 1.4438294172286987} 08/31/2021 01:05:28 - INFO - __main__ - Step 65587: {'lr': 0.0003048154372615028, 'samples': 12592704, 'steps': 65586, 'loss/train': 1.3713933229446411} 08/31/2021 01:05:29 - INFO - __main__ - Step 65588: {'lr': 0.0003048102596387375, 'samples': 12592896, 'steps': 65587, 'loss/train': 0.7076399922370911} 08/31/2021 01:05:30 - INFO - __main__ - Step 65589: {'lr': 0.0003048050819912757, 'samples': 12593088, 'steps': 65588, 'loss/train': 0.9226212501525879} 08/31/2021 01:05:30 - INFO - __main__ - Step 65590: {'lr': 0.0003047999043191195, 'samples': 12593280, 'steps': 65589, 'loss/train': 1.0069657564163208} 08/31/2021 01:05:30 - INFO - __main__ - Step 65591: {'lr': 0.0003047947266222713, 'samples': 12593472, 'steps': 65590, 'loss/train': 1.8062045574188232} 08/31/2021 01:05:31 - INFO - __main__ - Step 65592: {'lr': 0.00030478954890073354, 'samples': 12593664, 'steps': 65591, 'loss/train': 1.038064956665039} 08/31/2021 01:05:32 - INFO - __main__ - Step 65593: {'lr': 0.00030478437115450833, 'samples': 12593856, 'steps': 65592, 'loss/train': 1.3835132122039795} 08/31/2021 01:05:33 - INFO - __main__ - Step 65594: {'lr': 0.0003047791933835982, 'samples': 12594048, 'steps': 65593, 'loss/train': 1.3088860511779785} 08/31/2021 01:05:33 - INFO - __main__ - Step 65595: {'lr': 0.0003047740155880054, 'samples': 12594240, 'steps': 65594, 'loss/train': 1.485385775566101} 08/31/2021 01:05:33 - INFO - __main__ - Step 65596: {'lr': 0.0003047688377677322, 'samples': 12594432, 'steps': 65595, 'loss/train': 1.1186926364898682} 08/31/2021 01:05:34 - INFO - __main__ - Step 65597: {'lr': 0.0003047636599227811, 'samples': 12594624, 'steps': 65596, 'loss/train': 1.1243784427642822} 08/31/2021 01:05:35 - INFO - __main__ - Step 65598: {'lr': 0.0003047584820531543, 'samples': 12594816, 'steps': 65597, 'loss/train': 0.5864096879959106} 08/31/2021 01:05:36 - INFO - __main__ - Step 65599: {'lr': 0.0003047533041588542, 'samples': 12595008, 'steps': 65598, 'loss/train': 1.353763222694397} 08/31/2021 01:05:36 - INFO - __main__ - Step 65600: {'lr': 0.00030474812623988305, 'samples': 12595200, 'steps': 65599, 'loss/train': 1.471656322479248} 08/31/2021 01:05:36 - INFO - __main__ - Step 65601: {'lr': 0.0003047429482962433, 'samples': 12595392, 'steps': 65600, 'loss/train': 1.0457476377487183} 08/31/2021 01:05:37 - INFO - __main__ - Step 65602: {'lr': 0.0003047377703279372, 'samples': 12595584, 'steps': 65601, 'loss/train': 0.627854585647583} 08/31/2021 01:05:39 - INFO - __main__ - Step 65603: {'lr': 0.0003047325923349671, 'samples': 12595776, 'steps': 65602, 'loss/train': 1.7588140964508057} 08/31/2021 01:05:39 - INFO - __main__ - Step 65604: {'lr': 0.00030472741431733535, 'samples': 12595968, 'steps': 65603, 'loss/train': 0.08042265474796295} 08/31/2021 01:05:39 - INFO - __main__ - Step 65605: {'lr': 0.00030472223627504424, 'samples': 12596160, 'steps': 65604, 'loss/train': 1.7280620336532593} 08/31/2021 01:05:40 - INFO - __main__ - Step 65606: {'lr': 0.0003047170582080962, 'samples': 12596352, 'steps': 65605, 'loss/train': 0.14389686286449432} 08/31/2021 01:05:40 - INFO - __main__ - Step 65607: {'lr': 0.0003047118801164934, 'samples': 12596544, 'steps': 65606, 'loss/train': 0.04037637263536453} 08/31/2021 01:05:40 - INFO - __main__ - Step 65608: {'lr': 0.00030470670200023834, 'samples': 12596736, 'steps': 65607, 'loss/train': 1.2405771017074585} 08/31/2021 01:05:42 - INFO - __main__ - Step 65609: {'lr': 0.0003047015238593333, 'samples': 12596928, 'steps': 65608, 'loss/train': 0.08492952585220337} 08/31/2021 01:05:42 - INFO - __main__ - Step 65610: {'lr': 0.0003046963456937806, 'samples': 12597120, 'steps': 65609, 'loss/train': 1.2709823846817017} 08/31/2021 01:05:43 - INFO - __main__ - Step 65611: {'lr': 0.0003046911675035825, 'samples': 12597312, 'steps': 65610, 'loss/train': 1.2408356666564941} 08/31/2021 01:05:43 - INFO - __main__ - Step 65612: {'lr': 0.0003046859892887415, 'samples': 12597504, 'steps': 65611, 'loss/train': 1.3600733280181885} 08/31/2021 01:05:43 - INFO - __main__ - Step 65613: {'lr': 0.0003046808110492597, 'samples': 12597696, 'steps': 65612, 'loss/train': 0.21674691140651703} 08/31/2021 01:05:45 - INFO - __main__ - Step 65614: {'lr': 0.0003046756327851397, 'samples': 12597888, 'steps': 65613, 'loss/train': 1.541252851486206} 08/31/2021 01:05:46 - INFO - __main__ - Step 65615: {'lr': 0.00030467045449638367, 'samples': 12598080, 'steps': 65614, 'loss/train': 1.2974989414215088} 08/31/2021 01:05:46 - INFO - __main__ - Step 65616: {'lr': 0.0003046652761829939, 'samples': 12598272, 'steps': 65615, 'loss/train': 0.9779419898986816} 08/31/2021 01:05:47 - INFO - __main__ - Step 65617: {'lr': 0.0003046600978449729, 'samples': 12598464, 'steps': 65616, 'loss/train': 0.9942209720611572} 08/31/2021 01:05:47 - INFO - __main__ - Step 65618: {'lr': 0.0003046549194823228, 'samples': 12598656, 'steps': 65617, 'loss/train': 1.5766369104385376} 08/31/2021 01:05:49 - INFO - __main__ - Step 65619: {'lr': 0.0003046497410950461, 'samples': 12598848, 'steps': 65618, 'loss/train': 1.477533221244812} 08/31/2021 01:05:49 - INFO - __main__ - Step 65620: {'lr': 0.00030464456268314516, 'samples': 12599040, 'steps': 65619, 'loss/train': 0.8222578167915344} 08/31/2021 01:05:49 - INFO - __main__ - Step 65621: {'lr': 0.00030463938424662215, 'samples': 12599232, 'steps': 65620, 'loss/train': 1.3584755659103394} 08/31/2021 01:05:50 - INFO - __main__ - Step 65622: {'lr': 0.0003046342057854794, 'samples': 12599424, 'steps': 65621, 'loss/train': 1.3603103160858154} 08/31/2021 01:05:50 - INFO - __main__ - Step 65623: {'lr': 0.0003046290272997194, 'samples': 12599616, 'steps': 65622, 'loss/train': 1.6252825260162354} 08/31/2021 01:05:52 - INFO - __main__ - Step 65624: {'lr': 0.0003046238487893443, 'samples': 12599808, 'steps': 65623, 'loss/train': 1.5058934688568115} 08/31/2021 01:05:52 - INFO - __main__ - Step 65625: {'lr': 0.00030461867025435667, 'samples': 12600000, 'steps': 65624, 'loss/train': 1.6021329164505005} 08/31/2021 01:05:53 - INFO - __main__ - Step 65626: {'lr': 0.0003046134916947587, 'samples': 12600192, 'steps': 65625, 'loss/train': 1.0611512660980225} 08/31/2021 01:05:53 - INFO - __main__ - Step 65627: {'lr': 0.0003046083131105527, 'samples': 12600384, 'steps': 65626, 'loss/train': 1.5266166925430298} 08/31/2021 01:05:53 - INFO - __main__ - Step 65628: {'lr': 0.00030460313450174104, 'samples': 12600576, 'steps': 65627, 'loss/train': 1.3987737894058228} 08/31/2021 01:05:54 - INFO - __main__ - Step 65629: {'lr': 0.000304597955868326, 'samples': 12600768, 'steps': 65628, 'loss/train': 1.594549298286438} 08/31/2021 01:05:55 - INFO - __main__ - Step 65630: {'lr': 0.00030459277721031, 'samples': 12600960, 'steps': 65629, 'loss/train': 1.478549838066101} 08/31/2021 01:05:55 - INFO - __main__ - Step 65631: {'lr': 0.00030458759852769533, 'samples': 12601152, 'steps': 65630, 'loss/train': 1.3377227783203125} 08/31/2021 01:05:56 - INFO - __main__ - Step 65632: {'lr': 0.0003045824198204844, 'samples': 12601344, 'steps': 65631, 'loss/train': 1.7493841648101807} 08/31/2021 01:05:56 - INFO - __main__ - Step 65633: {'lr': 0.0003045772410886794, 'samples': 12601536, 'steps': 65632, 'loss/train': 1.368530511856079} 08/31/2021 01:05:56 - INFO - __main__ - Step 65634: {'lr': 0.00030457206233228275, 'samples': 12601728, 'steps': 65633, 'loss/train': 1.5062402486801147} 08/31/2021 01:05:58 - INFO - __main__ - Step 65635: {'lr': 0.0003045668835512967, 'samples': 12601920, 'steps': 65634, 'loss/train': 1.3132561445236206} 08/31/2021 01:05:59 - INFO - __main__ - Step 65636: {'lr': 0.0003045617047457238, 'samples': 12602112, 'steps': 65635, 'loss/train': 0.9524532556533813} 08/31/2021 01:05:59 - INFO - __main__ - Step 65637: {'lr': 0.00030455652591556613, 'samples': 12602304, 'steps': 65636, 'loss/train': 0.9317214488983154} 08/31/2021 01:05:59 - INFO - __main__ - Step 65638: {'lr': 0.00030455134706082617, 'samples': 12602496, 'steps': 65637, 'loss/train': 1.563252568244934} 08/31/2021 01:06:00 - INFO - __main__ - Step 65639: {'lr': 0.00030454616818150626, 'samples': 12602688, 'steps': 65638, 'loss/train': 1.1605559587478638} 08/31/2021 01:06:01 - INFO - __main__ - Step 65640: {'lr': 0.0003045409892776086, 'samples': 12602880, 'steps': 65639, 'loss/train': 0.790834903717041} 08/31/2021 01:06:01 - INFO - __main__ - Step 65641: {'lr': 0.0003045358103491357, 'samples': 12603072, 'steps': 65640, 'loss/train': 0.7105901837348938} 08/31/2021 01:06:02 - INFO - __main__ - Step 65642: {'lr': 0.0003045306313960897, 'samples': 12603264, 'steps': 65641, 'loss/train': 1.2170301675796509} 08/31/2021 01:06:02 - INFO - __main__ - Step 65643: {'lr': 0.0003045254524184731, 'samples': 12603456, 'steps': 65642, 'loss/train': 1.3542912006378174} 08/31/2021 01:06:03 - INFO - __main__ - Step 65644: {'lr': 0.00030452027341628816, 'samples': 12603648, 'steps': 65643, 'loss/train': 1.5068169832229614} 08/31/2021 01:06:04 - INFO - __main__ - Step 65645: {'lr': 0.00030451509438953725, 'samples': 12603840, 'steps': 65644, 'loss/train': 1.3855295181274414} 08/31/2021 01:06:05 - INFO - __main__ - Step 65646: {'lr': 0.0003045099153382227, 'samples': 12604032, 'steps': 65645, 'loss/train': 0.8555009961128235} 08/31/2021 01:06:05 - INFO - __main__ - Step 65647: {'lr': 0.00030450473626234675, 'samples': 12604224, 'steps': 65646, 'loss/train': 1.4673259258270264} 08/31/2021 01:06:05 - INFO - __main__ - Step 65648: {'lr': 0.00030449955716191184, 'samples': 12604416, 'steps': 65647, 'loss/train': 1.0852632522583008} 08/31/2021 01:06:06 - INFO - __main__ - Step 65649: {'lr': 0.00030449437803692033, 'samples': 12604608, 'steps': 65648, 'loss/train': 1.017540454864502} 08/31/2021 01:06:07 - INFO - __main__ - Step 65650: {'lr': 0.0003044891988873744, 'samples': 12604800, 'steps': 65649, 'loss/train': 1.0352526903152466} 08/31/2021 01:06:08 - INFO - __main__ - Step 65651: {'lr': 0.00030448401971327647, 'samples': 12604992, 'steps': 65650, 'loss/train': 1.3276678323745728} 08/31/2021 01:06:08 - INFO - __main__ - Step 65652: {'lr': 0.000304478840514629, 'samples': 12605184, 'steps': 65651, 'loss/train': 1.3731125593185425} 08/31/2021 01:06:08 - INFO - __main__ - Step 65653: {'lr': 0.00030447366129143414, 'samples': 12605376, 'steps': 65652, 'loss/train': 0.6256946921348572} 08/31/2021 01:06:09 - INFO - __main__ - Step 65654: {'lr': 0.00030446848204369425, 'samples': 12605568, 'steps': 65653, 'loss/train': 1.4039373397827148} 08/31/2021 01:06:09 - INFO - __main__ - Step 65655: {'lr': 0.00030446330277141177, 'samples': 12605760, 'steps': 65654, 'loss/train': 1.146743893623352} 08/31/2021 01:06:10 - INFO - __main__ - Step 65656: {'lr': 0.0003044581234745889, 'samples': 12605952, 'steps': 65655, 'loss/train': 1.3375041484832764} 08/31/2021 01:06:11 - INFO - __main__ - Step 65657: {'lr': 0.00030445294415322807, 'samples': 12606144, 'steps': 65656, 'loss/train': 1.5493111610412598} 08/31/2021 01:06:11 - INFO - __main__ - Step 65658: {'lr': 0.00030444776480733157, 'samples': 12606336, 'steps': 65657, 'loss/train': 1.4256242513656616} 08/31/2021 01:06:12 - INFO - __main__ - Step 65659: {'lr': 0.0003044425854369018, 'samples': 12606528, 'steps': 65658, 'loss/train': 1.3781471252441406} 08/31/2021 01:06:12 - INFO - __main__ - Step 65660: {'lr': 0.00030443740604194097, 'samples': 12606720, 'steps': 65659, 'loss/train': 1.0716898441314697} 08/31/2021 01:06:13 - INFO - __main__ - Step 65661: {'lr': 0.00030443222662245153, 'samples': 12606912, 'steps': 65660, 'loss/train': 1.1720976829528809} 08/31/2021 01:06:14 - INFO - __main__ - Step 65662: {'lr': 0.00030442704717843576, 'samples': 12607104, 'steps': 65661, 'loss/train': 1.3393474817276} 08/31/2021 01:06:14 - INFO - __main__ - Step 65663: {'lr': 0.000304421867709896, 'samples': 12607296, 'steps': 65662, 'loss/train': 1.0453345775604248} 08/31/2021 01:06:15 - INFO - __main__ - Step 65664: {'lr': 0.00030441668821683455, 'samples': 12607488, 'steps': 65663, 'loss/train': 1.1285711526870728} 08/31/2021 01:06:15 - INFO - __main__ - Step 65665: {'lr': 0.0003044115086992538, 'samples': 12607680, 'steps': 65664, 'loss/train': 1.6157113313674927} 08/31/2021 01:06:17 - INFO - __main__ - Step 65666: {'lr': 0.00030440632915715613, 'samples': 12607872, 'steps': 65665, 'loss/train': 1.182793378829956} 08/31/2021 01:06:18 - INFO - __main__ - Step 65667: {'lr': 0.00030440114959054377, 'samples': 12608064, 'steps': 65666, 'loss/train': 1.2624728679656982} 08/31/2021 01:06:18 - INFO - __main__ - Step 65668: {'lr': 0.00030439596999941906, 'samples': 12608256, 'steps': 65667, 'loss/train': 1.1697227954864502} 08/31/2021 01:06:19 - INFO - __main__ - Step 65669: {'lr': 0.0003043907903837844, 'samples': 12608448, 'steps': 65668, 'loss/train': 0.5169389247894287} 08/31/2021 01:06:19 - INFO - __main__ - Step 65670: {'lr': 0.00030438561074364203, 'samples': 12608640, 'steps': 65669, 'loss/train': 1.1597702503204346} 08/31/2021 01:06:21 - INFO - __main__ - Step 65671: {'lr': 0.00030438043107899437, 'samples': 12608832, 'steps': 65670, 'loss/train': 0.11286672949790955} 08/31/2021 01:06:21 - INFO - __main__ - Step 65672: {'lr': 0.00030437525138984374, 'samples': 12609024, 'steps': 65671, 'loss/train': 0.9507306814193726} 08/31/2021 01:06:21 - INFO - __main__ - Step 65673: {'lr': 0.00030437007167619253, 'samples': 12609216, 'steps': 65672, 'loss/train': 0.8446483016014099} 08/31/2021 01:06:22 - INFO - __main__ - Step 65674: {'lr': 0.00030436489193804296, 'samples': 12609408, 'steps': 65673, 'loss/train': 1.4591350555419922} 08/31/2021 01:06:22 - INFO - __main__ - Step 65675: {'lr': 0.00030435971217539735, 'samples': 12609600, 'steps': 65674, 'loss/train': 1.1098353862762451} 08/31/2021 01:06:23 - INFO - __main__ - Step 65676: {'lr': 0.0003043545323882581, 'samples': 12609792, 'steps': 65675, 'loss/train': 1.2715929746627808} 08/31/2021 01:06:24 - INFO - __main__ - Step 65677: {'lr': 0.00030434935257662754, 'samples': 12609984, 'steps': 65676, 'loss/train': 0.7431046366691589} 08/31/2021 01:06:24 - INFO - __main__ - Step 65678: {'lr': 0.00030434417274050805, 'samples': 12610176, 'steps': 65677, 'loss/train': 1.3851513862609863} 08/31/2021 01:06:25 - INFO - __main__ - Step 65679: {'lr': 0.00030433899287990197, 'samples': 12610368, 'steps': 65678, 'loss/train': 1.3608399629592896} 08/31/2021 01:06:25 - INFO - __main__ - Step 65680: {'lr': 0.00030433381299481145, 'samples': 12610560, 'steps': 65679, 'loss/train': 1.5880674123764038} 08/31/2021 01:06:25 - INFO - __main__ - Step 65681: {'lr': 0.000304328633085239, 'samples': 12610752, 'steps': 65680, 'loss/train': 0.815694272518158} 08/31/2021 01:06:27 - INFO - __main__ - Step 65682: {'lr': 0.00030432345315118694, 'samples': 12610944, 'steps': 65681, 'loss/train': 0.8361729979515076} 08/31/2021 01:06:27 - INFO - __main__ - Step 65683: {'lr': 0.0003043182731926575, 'samples': 12611136, 'steps': 65682, 'loss/train': 1.3148976564407349} 08/31/2021 01:06:28 - INFO - __main__ - Step 65684: {'lr': 0.0003043130932096531, 'samples': 12611328, 'steps': 65683, 'loss/train': 1.7413169145584106} 08/31/2021 01:06:28 - INFO - __main__ - Step 65685: {'lr': 0.0003043079132021761, 'samples': 12611520, 'steps': 65684, 'loss/train': 1.5297836065292358} 08/31/2021 01:06:28 - INFO - __main__ - Step 65686: {'lr': 0.0003043027331702288, 'samples': 12611712, 'steps': 65685, 'loss/train': 0.6354113221168518} 08/31/2021 01:06:30 - INFO - __main__ - Step 65687: {'lr': 0.00030429755311381346, 'samples': 12611904, 'steps': 65686, 'loss/train': 0.8478710651397705} 08/31/2021 01:06:31 - INFO - __main__ - Step 65688: {'lr': 0.00030429237303293257, 'samples': 12612096, 'steps': 65687, 'loss/train': 1.8329905271530151} 08/31/2021 01:06:31 - INFO - __main__ - Step 65689: {'lr': 0.0003042871929275883, 'samples': 12612288, 'steps': 65688, 'loss/train': 2.531397819519043} 08/31/2021 01:06:31 - INFO - __main__ - Step 65690: {'lr': 0.0003042820127977831, 'samples': 12612480, 'steps': 65689, 'loss/train': 0.05460086464881897} 08/31/2021 01:06:32 - INFO - __main__ - Step 65691: {'lr': 0.0003042768326435192, 'samples': 12612672, 'steps': 65690, 'loss/train': 0.9574427008628845} 08/31/2021 01:06:32 - INFO - __main__ - Step 65692: {'lr': 0.00030427165246479904, 'samples': 12612864, 'steps': 65691, 'loss/train': 1.2121062278747559} 08/31/2021 01:06:33 - INFO - __main__ - Step 65693: {'lr': 0.00030426647226162497, 'samples': 12613056, 'steps': 65692, 'loss/train': 1.3398723602294922} 08/31/2021 01:06:34 - INFO - __main__ - Step 65694: {'lr': 0.00030426129203399915, 'samples': 12613248, 'steps': 65693, 'loss/train': 1.4196290969848633} 08/31/2021 01:06:34 - INFO - __main__ - Step 65695: {'lr': 0.0003042561117819241, 'samples': 12613440, 'steps': 65694, 'loss/train': 1.3432259559631348} 08/31/2021 01:06:35 - INFO - __main__ - Step 65696: {'lr': 0.00030425093150540205, 'samples': 12613632, 'steps': 65695, 'loss/train': 1.3809902667999268} 08/31/2021 01:06:35 - INFO - __main__ - Step 65697: {'lr': 0.0003042457512044354, 'samples': 12613824, 'steps': 65696, 'loss/train': 1.4782880544662476} 08/31/2021 01:06:37 - INFO - __main__ - Step 65698: {'lr': 0.0003042405708790264, 'samples': 12614016, 'steps': 65697, 'loss/train': 1.9256722927093506} 08/31/2021 01:06:37 - INFO - __main__ - Step 65699: {'lr': 0.00030423539052917755, 'samples': 12614208, 'steps': 65698, 'loss/train': 1.3516201972961426} 08/31/2021 01:06:38 - INFO - __main__ - Step 65700: {'lr': 0.00030423021015489095, 'samples': 12614400, 'steps': 65699, 'loss/train': 1.3756670951843262} 08/31/2021 01:06:38 - INFO - __main__ - Step 65701: {'lr': 0.00030422502975616914, 'samples': 12614592, 'steps': 65700, 'loss/train': 1.8415358066558838} 08/31/2021 01:06:38 - INFO - __main__ - Step 65702: {'lr': 0.0003042198493330143, 'samples': 12614784, 'steps': 65701, 'loss/train': 1.0998808145523071} 08/31/2021 01:06:40 - INFO - __main__ - Step 65703: {'lr': 0.0003042146688854288, 'samples': 12614976, 'steps': 65702, 'loss/train': 2.13792085647583} 08/31/2021 01:06:41 - INFO - __main__ - Step 65704: {'lr': 0.0003042094884134151, 'samples': 12615168, 'steps': 65703, 'loss/train': 1.369227647781372} 08/31/2021 01:06:41 - INFO - __main__ - Step 65705: {'lr': 0.0003042043079169754, 'samples': 12615360, 'steps': 65704, 'loss/train': 1.392295241355896} 08/31/2021 01:06:41 - INFO - __main__ - Step 65706: {'lr': 0.0003041991273961121, 'samples': 12615552, 'steps': 65705, 'loss/train': 1.4619916677474976} 08/31/2021 01:06:42 - INFO - __main__ - Step 65707: {'lr': 0.0003041939468508275, 'samples': 12615744, 'steps': 65706, 'loss/train': 5.771909713745117} 08/31/2021 01:06:42 - INFO - __main__ - Step 65708: {'lr': 0.0003041887662811239, 'samples': 12615936, 'steps': 65707, 'loss/train': 5.807562351226807} 08/31/2021 01:06:44 - INFO - __main__ - Step 65709: {'lr': 0.00030418358568700375, 'samples': 12616128, 'steps': 65708, 'loss/train': 0.5157005190849304} 08/31/2021 01:06:44 - INFO - __main__ - Step 65710: {'lr': 0.0003041784050684693, 'samples': 12616320, 'steps': 65709, 'loss/train': 1.2984416484832764} 08/31/2021 01:06:45 - INFO - __main__ - Step 65711: {'lr': 0.0003041732244255228, 'samples': 12616512, 'steps': 65710, 'loss/train': 1.3406691551208496} 08/31/2021 01:06:45 - INFO - __main__ - Step 65712: {'lr': 0.00030416804375816675, 'samples': 12616704, 'steps': 65711, 'loss/train': 0.9369736313819885} 08/31/2021 01:06:45 - INFO - __main__ - Step 65713: {'lr': 0.0003041628630664035, 'samples': 12616896, 'steps': 65712, 'loss/train': 1.9948670864105225} 08/31/2021 01:06:46 - INFO - __main__ - Step 65714: {'lr': 0.00030415768235023523, 'samples': 12617088, 'steps': 65713, 'loss/train': 0.9613785147666931} 08/31/2021 01:06:47 - INFO - __main__ - Step 65715: {'lr': 0.0003041525016096643, 'samples': 12617280, 'steps': 65714, 'loss/train': 1.1854872703552246} 08/31/2021 01:06:48 - INFO - __main__ - Step 65716: {'lr': 0.0003041473208446931, 'samples': 12617472, 'steps': 65715, 'loss/train': 1.042839527130127} 08/31/2021 01:06:48 - INFO - __main__ - Step 65717: {'lr': 0.000304142140055324, 'samples': 12617664, 'steps': 65716, 'loss/train': 1.1337006092071533} 08/31/2021 01:06:48 - INFO - __main__ - Step 65718: {'lr': 0.0003041369592415592, 'samples': 12617856, 'steps': 65717, 'loss/train': 1.8512425422668457} 08/31/2021 01:06:49 - INFO - __main__ - Step 65719: {'lr': 0.0003041317784034012, 'samples': 12618048, 'steps': 65718, 'loss/train': 1.2683120965957642} 08/31/2021 01:06:50 - INFO - __main__ - Step 65720: {'lr': 0.00030412659754085224, 'samples': 12618240, 'steps': 65719, 'loss/train': 1.3660284280776978} 08/31/2021 01:06:51 - INFO - __main__ - Step 65721: {'lr': 0.0003041214166539147, 'samples': 12618432, 'steps': 65720, 'loss/train': 1.1938979625701904} 08/31/2021 01:06:51 - INFO - __main__ - Step 65722: {'lr': 0.00030411623574259087, 'samples': 12618624, 'steps': 65721, 'loss/train': 1.2607556581497192} 08/31/2021 01:06:51 - INFO - __main__ - Step 65723: {'lr': 0.0003041110548068831, 'samples': 12618816, 'steps': 65722, 'loss/train': 1.4443755149841309} 08/31/2021 01:06:52 - INFO - __main__ - Step 65724: {'lr': 0.0003041058738467937, 'samples': 12619008, 'steps': 65723, 'loss/train': 1.3362150192260742} 08/31/2021 01:06:54 - INFO - __main__ - Step 65725: {'lr': 0.000304100692862325, 'samples': 12619200, 'steps': 65724, 'loss/train': 1.6278599500656128} 08/31/2021 01:06:54 - INFO - __main__ - Step 65726: {'lr': 0.00030409551185347946, 'samples': 12619392, 'steps': 65725, 'loss/train': 0.994918167591095} 08/31/2021 01:06:55 - INFO - __main__ - Step 65727: {'lr': 0.00030409033082025923, 'samples': 12619584, 'steps': 65726, 'loss/train': 1.4790382385253906} 08/31/2021 01:06:55 - INFO - __main__ - Step 65728: {'lr': 0.00030408514976266673, 'samples': 12619776, 'steps': 65727, 'loss/train': 1.417972207069397} 08/31/2021 01:06:55 - INFO - __main__ - Step 65729: {'lr': 0.0003040799686807043, 'samples': 12619968, 'steps': 65728, 'loss/train': 0.771467924118042} 08/31/2021 01:06:57 - INFO - __main__ - Step 65730: {'lr': 0.0003040747875743743, 'samples': 12620160, 'steps': 65729, 'loss/train': 1.1443029642105103} 08/31/2021 01:06:57 - INFO - __main__ - Step 65731: {'lr': 0.00030406960644367904, 'samples': 12620352, 'steps': 65730, 'loss/train': 1.377034306526184} 08/31/2021 01:06:58 - INFO - __main__ - Step 65732: {'lr': 0.00030406442528862083, 'samples': 12620544, 'steps': 65731, 'loss/train': 1.3753222227096558} 08/31/2021 01:06:58 - INFO - __main__ - Step 65733: {'lr': 0.00030405924410920206, 'samples': 12620736, 'steps': 65732, 'loss/train': 0.6283468008041382} 08/31/2021 01:06:58 - INFO - __main__ - Step 65734: {'lr': 0.00030405406290542496, 'samples': 12620928, 'steps': 65733, 'loss/train': 1.1610513925552368} 08/31/2021 01:07:00 - INFO - __main__ - Step 65735: {'lr': 0.000304048881677292, 'samples': 12621120, 'steps': 65734, 'loss/train': 0.37409356236457825} 08/31/2021 01:07:00 - INFO - __main__ - Step 65736: {'lr': 0.0003040437004248054, 'samples': 12621312, 'steps': 65735, 'loss/train': 1.442511796951294} 08/31/2021 01:07:00 - INFO - __main__ - Step 65737: {'lr': 0.0003040385191479675, 'samples': 12621504, 'steps': 65736, 'loss/train': 1.5717774629592896} 08/31/2021 01:07:01 - INFO - __main__ - Step 65738: {'lr': 0.0003040333378467808, 'samples': 12621696, 'steps': 65737, 'loss/train': 0.8143641352653503} 08/31/2021 01:07:01 - INFO - __main__ - Step 65739: {'lr': 0.0003040281565212475, 'samples': 12621888, 'steps': 65738, 'loss/train': 1.0893356800079346} 08/31/2021 01:07:03 - INFO - __main__ - Step 65740: {'lr': 0.0003040229751713699, 'samples': 12622080, 'steps': 65739, 'loss/train': 1.1096841096878052} 08/31/2021 01:07:03 - INFO - __main__ - Step 65741: {'lr': 0.00030401779379715037, 'samples': 12622272, 'steps': 65740, 'loss/train': 1.528191089630127} 08/31/2021 01:07:04 - INFO - __main__ - Step 65742: {'lr': 0.00030401261239859124, 'samples': 12622464, 'steps': 65741, 'loss/train': 1.487464427947998} 08/31/2021 01:07:04 - INFO - __main__ - Step 65743: {'lr': 0.0003040074309756949, 'samples': 12622656, 'steps': 65742, 'loss/train': 1.7137879133224487} 08/31/2021 01:07:04 - INFO - __main__ - Step 65744: {'lr': 0.0003040022495284637, 'samples': 12622848, 'steps': 65743, 'loss/train': 1.4899556636810303} 08/31/2021 01:07:06 - INFO - __main__ - Step 65745: {'lr': 0.0003039970680568998, 'samples': 12623040, 'steps': 65744, 'loss/train': 0.33670490980148315} 08/31/2021 01:07:06 - INFO - __main__ - Step 65746: {'lr': 0.00030399188656100574, 'samples': 12623232, 'steps': 65745, 'loss/train': 0.500127375125885} 08/31/2021 01:07:07 - INFO - __main__ - Step 65747: {'lr': 0.0003039867050407837, 'samples': 12623424, 'steps': 65746, 'loss/train': 0.40187951922416687} 08/31/2021 01:07:07 - INFO - __main__ - Step 65748: {'lr': 0.0003039815234962361, 'samples': 12623616, 'steps': 65747, 'loss/train': 1.0641663074493408} 08/31/2021 01:07:07 - INFO - __main__ - Step 65749: {'lr': 0.00030397634192736535, 'samples': 12623808, 'steps': 65748, 'loss/train': 1.2282426357269287} 08/31/2021 01:07:09 - INFO - __main__ - Step 65750: {'lr': 0.0003039711603341736, 'samples': 12624000, 'steps': 65749, 'loss/train': 1.1908291578292847} 08/31/2021 01:07:09 - INFO - __main__ - Step 65751: {'lr': 0.00030396597871666333, 'samples': 12624192, 'steps': 65750, 'loss/train': 5.927736759185791} 08/31/2021 01:07:10 - INFO - __main__ - Step 65752: {'lr': 0.0003039607970748368, 'samples': 12624384, 'steps': 65751, 'loss/train': 1.5543220043182373} 08/31/2021 01:07:10 - INFO - __main__ - Step 65753: {'lr': 0.0003039556154086963, 'samples': 12624576, 'steps': 65752, 'loss/train': 1.118242859840393} 08/31/2021 01:07:11 - INFO - __main__ - Step 65754: {'lr': 0.00030395043371824425, 'samples': 12624768, 'steps': 65753, 'loss/train': 1.282416582107544} 08/31/2021 01:07:11 - INFO - __main__ - Step 65755: {'lr': 0.0003039452520034831, 'samples': 12624960, 'steps': 65754, 'loss/train': 1.53329336643219} 08/31/2021 01:07:12 - INFO - __main__ - Step 65756: {'lr': 0.00030394007026441494, 'samples': 12625152, 'steps': 65755, 'loss/train': 1.979080319404602} 08/31/2021 01:07:13 - INFO - __main__ - Step 65757: {'lr': 0.0003039348885010422, 'samples': 12625344, 'steps': 65756, 'loss/train': 1.2377064228057861} 08/31/2021 01:07:13 - INFO - __main__ - Step 65758: {'lr': 0.0003039297067133673, 'samples': 12625536, 'steps': 65757, 'loss/train': 0.9163308143615723} 08/31/2021 01:07:13 - INFO - __main__ - Step 65759: {'lr': 0.00030392452490139244, 'samples': 12625728, 'steps': 65758, 'loss/train': 1.055426836013794} 08/31/2021 01:07:14 - INFO - __main__ - Step 65760: {'lr': 0.0003039193430651201, 'samples': 12625920, 'steps': 65759, 'loss/train': 1.0309340953826904} 08/31/2021 01:07:16 - INFO - __main__ - Step 65761: {'lr': 0.0003039141612045525, 'samples': 12626112, 'steps': 65760, 'loss/train': 1.536370873451233} 08/31/2021 01:07:16 - INFO - __main__ - Step 65762: {'lr': 0.000303908979319692, 'samples': 12626304, 'steps': 65761, 'loss/train': 1.7228598594665527} 08/31/2021 01:07:16 - INFO - __main__ - Step 65763: {'lr': 0.0003039037974105409, 'samples': 12626496, 'steps': 65762, 'loss/train': 1.4869513511657715} 08/31/2021 01:07:17 - INFO - __main__ - Step 65764: {'lr': 0.0003038986154771016, 'samples': 12626688, 'steps': 65763, 'loss/train': 1.2177176475524902} 08/31/2021 01:07:17 - INFO - __main__ - Step 65765: {'lr': 0.0003038934335193765, 'samples': 12626880, 'steps': 65764, 'loss/train': 1.566712737083435} 08/31/2021 01:07:18 - INFO - __main__ - Step 65766: {'lr': 0.00030388825153736775, 'samples': 12627072, 'steps': 65765, 'loss/train': 0.8238131403923035} 08/31/2021 01:07:19 - INFO - __main__ - Step 65767: {'lr': 0.0003038830695310779, 'samples': 12627264, 'steps': 65766, 'loss/train': 2.921921491622925} 08/31/2021 01:07:20 - INFO - __main__ - Step 65768: {'lr': 0.0003038778875005091, 'samples': 12627456, 'steps': 65767, 'loss/train': 1.9126842021942139} 08/31/2021 01:07:20 - INFO - __main__ - Step 65769: {'lr': 0.00030387270544566375, 'samples': 12627648, 'steps': 65768, 'loss/train': 1.2456804513931274} 08/31/2021 01:07:20 - INFO - __main__ - Step 65770: {'lr': 0.00030386752336654415, 'samples': 12627840, 'steps': 65769, 'loss/train': 1.2494781017303467} 08/31/2021 01:07:21 - INFO - __main__ - Step 65771: {'lr': 0.00030386234126315273, 'samples': 12628032, 'steps': 65770, 'loss/train': 1.4556268453598022} 08/31/2021 01:07:22 - INFO - __main__ - Step 65772: {'lr': 0.00030385715913549177, 'samples': 12628224, 'steps': 65771, 'loss/train': 1.453789234161377} 08/31/2021 01:07:23 - INFO - __main__ - Step 65773: {'lr': 0.00030385197698356366, 'samples': 12628416, 'steps': 65772, 'loss/train': 1.3813209533691406} 08/31/2021 01:07:23 - INFO - __main__ - Step 65774: {'lr': 0.0003038467948073706, 'samples': 12628608, 'steps': 65773, 'loss/train': 0.9250257015228271} 08/31/2021 01:07:23 - INFO - __main__ - Step 65775: {'lr': 0.000303841612606915, 'samples': 12628800, 'steps': 65774, 'loss/train': 0.8400217294692993} 08/31/2021 01:07:24 - INFO - __main__ - Step 65776: {'lr': 0.0003038364303821992, 'samples': 12628992, 'steps': 65775, 'loss/train': 0.7937390208244324} 08/31/2021 01:07:26 - INFO - __main__ - Step 65777: {'lr': 0.00030383124813322557, 'samples': 12629184, 'steps': 65776, 'loss/train': 1.30526864528656} 08/31/2021 01:07:26 - INFO - __main__ - Step 65778: {'lr': 0.00030382606585999637, 'samples': 12629376, 'steps': 65777, 'loss/train': 1.4073336124420166} 08/31/2021 01:07:26 - INFO - __main__ - Step 65779: {'lr': 0.000303820883562514, 'samples': 12629568, 'steps': 65778, 'loss/train': 1.6214057207107544} 08/31/2021 01:07:27 - INFO - __main__ - Step 65780: {'lr': 0.00030381570124078086, 'samples': 12629760, 'steps': 65779, 'loss/train': 1.4024131298065186} 08/31/2021 01:07:27 - INFO - __main__ - Step 65781: {'lr': 0.00030381051889479904, 'samples': 12629952, 'steps': 65780, 'loss/train': 1.307908058166504} 08/31/2021 01:07:29 - INFO - __main__ - Step 65782: {'lr': 0.0003038053365245711, 'samples': 12630144, 'steps': 65781, 'loss/train': 0.9476237893104553} 08/31/2021 01:07:29 - INFO - __main__ - Step 65783: {'lr': 0.0003038001541300993, 'samples': 12630336, 'steps': 65782, 'loss/train': 1.1082634925842285} 08/31/2021 01:07:29 - INFO - __main__ - Step 65784: {'lr': 0.00030379497171138597, 'samples': 12630528, 'steps': 65783, 'loss/train': 1.2881497144699097} 08/31/2021 01:07:30 - INFO - __main__ - Step 65785: {'lr': 0.0003037897892684335, 'samples': 12630720, 'steps': 65784, 'loss/train': 0.37675154209136963} 08/31/2021 01:07:30 - INFO - __main__ - Step 65786: {'lr': 0.00030378460680124416, 'samples': 12630912, 'steps': 65785, 'loss/train': 1.2897045612335205} 08/31/2021 01:07:30 - INFO - __main__ - Step 65787: {'lr': 0.0003037794243098203, 'samples': 12631104, 'steps': 65786, 'loss/train': 0.626921534538269} 08/31/2021 01:07:32 - INFO - __main__ - Step 65788: {'lr': 0.00030377424179416426, 'samples': 12631296, 'steps': 65787, 'loss/train': 0.576586902141571} 08/31/2021 01:07:33 - INFO - __main__ - Step 65789: {'lr': 0.0003037690592542784, 'samples': 12631488, 'steps': 65788, 'loss/train': 1.4083505868911743} 08/31/2021 01:07:33 - INFO - __main__ - Step 65790: {'lr': 0.000303763876690165, 'samples': 12631680, 'steps': 65789, 'loss/train': 0.06405092030763626} 08/31/2021 01:07:33 - INFO - __main__ - Step 65791: {'lr': 0.00030375869410182636, 'samples': 12631872, 'steps': 65790, 'loss/train': 0.03785305842757225} 08/31/2021 01:07:34 - INFO - __main__ - Step 65792: {'lr': 0.000303753511489265, 'samples': 12632064, 'steps': 65791, 'loss/train': 0.9010270237922668} 08/31/2021 01:07:36 - INFO - __main__ - Step 65793: {'lr': 0.0003037483288524831, 'samples': 12632256, 'steps': 65792, 'loss/train': 1.2627743482589722} 08/31/2021 01:07:36 - INFO - __main__ - Step 65794: {'lr': 0.00030374314619148305, 'samples': 12632448, 'steps': 65793, 'loss/train': 0.3847729563713074} 08/31/2021 01:07:36 - INFO - __main__ - Step 65795: {'lr': 0.00030373796350626717, 'samples': 12632640, 'steps': 65794, 'loss/train': 1.4146790504455566} 08/31/2021 01:07:37 - INFO - __main__ - Step 65796: {'lr': 0.00030373278079683775, 'samples': 12632832, 'steps': 65795, 'loss/train': 2.1232573986053467} 08/31/2021 01:07:37 - INFO - __main__ - Step 65797: {'lr': 0.00030372759806319717, 'samples': 12633024, 'steps': 65796, 'loss/train': 0.9742507338523865} 08/31/2021 01:07:37 - INFO - __main__ - Step 65798: {'lr': 0.00030372241530534776, 'samples': 12633216, 'steps': 65797, 'loss/train': 1.4070311784744263} 08/31/2021 01:07:39 - INFO - __main__ - Step 65799: {'lr': 0.00030371723252329186, 'samples': 12633408, 'steps': 65798, 'loss/train': 0.7044625878334045} 08/31/2021 01:07:39 - INFO - __main__ - Step 65800: {'lr': 0.00030371204971703185, 'samples': 12633600, 'steps': 65799, 'loss/train': 1.6504533290863037} 08/31/2021 01:07:40 - INFO - __main__ - Step 65801: {'lr': 0.00030370686688657, 'samples': 12633792, 'steps': 65800, 'loss/train': 1.2236274480819702} 08/31/2021 01:07:40 - INFO - __main__ - Step 65802: {'lr': 0.00030370168403190867, 'samples': 12633984, 'steps': 65801, 'loss/train': 1.2071605920791626} 08/31/2021 01:07:40 - INFO - __main__ - Step 65803: {'lr': 0.00030369650115305016, 'samples': 12634176, 'steps': 65802, 'loss/train': 1.0775954723358154} 08/31/2021 01:07:42 - INFO - __main__ - Step 65804: {'lr': 0.00030369131824999686, 'samples': 12634368, 'steps': 65803, 'loss/train': 0.9874613285064697} 08/31/2021 01:07:42 - INFO - __main__ - Step 65805: {'lr': 0.000303686135322751, 'samples': 12634560, 'steps': 65804, 'loss/train': 2.001483201980591} 08/31/2021 01:07:43 - INFO - __main__ - Step 65806: {'lr': 0.0003036809523713151, 'samples': 12634752, 'steps': 65805, 'loss/train': 1.1047208309173584} 08/31/2021 01:07:43 - INFO - __main__ - Step 65807: {'lr': 0.0003036757693956914, 'samples': 12634944, 'steps': 65806, 'loss/train': 1.0678659677505493} 08/31/2021 01:07:43 - INFO - __main__ - Step 65808: {'lr': 0.0003036705863958822, 'samples': 12635136, 'steps': 65807, 'loss/train': 1.3861057758331299} 08/31/2021 01:07:45 - INFO - __main__ - Step 65809: {'lr': 0.0003036654033718898, 'samples': 12635328, 'steps': 65808, 'loss/train': 1.6354106664657593} 08/31/2021 01:07:46 - INFO - __main__ - Step 65810: {'lr': 0.00030366022032371666, 'samples': 12635520, 'steps': 65809, 'loss/train': 1.0971996784210205} 08/31/2021 01:07:46 - INFO - __main__ - Step 65811: {'lr': 0.00030365503725136503, 'samples': 12635712, 'steps': 65810, 'loss/train': 1.1421266794204712} 08/31/2021 01:07:46 - INFO - __main__ - Step 65812: {'lr': 0.00030364985415483727, 'samples': 12635904, 'steps': 65811, 'loss/train': 0.018593359738588333} 08/31/2021 01:07:47 - INFO - __main__ - Step 65813: {'lr': 0.0003036446710341357, 'samples': 12636096, 'steps': 65812, 'loss/train': 1.338747501373291} 08/31/2021 01:07:47 - INFO - __main__ - Step 65814: {'lr': 0.0003036394878892627, 'samples': 12636288, 'steps': 65813, 'loss/train': 1.7386434078216553} 08/31/2021 01:07:48 - INFO - __main__ - Step 65815: {'lr': 0.0003036343047202206, 'samples': 12636480, 'steps': 65814, 'loss/train': 1.3169050216674805} 08/31/2021 01:07:49 - INFO - __main__ - Step 65816: {'lr': 0.00030362912152701163, 'samples': 12636672, 'steps': 65815, 'loss/train': 0.7996598482131958} 08/31/2021 01:07:49 - INFO - __main__ - Step 65817: {'lr': 0.00030362393830963826, 'samples': 12636864, 'steps': 65816, 'loss/train': 1.0812872648239136} 08/31/2021 01:07:50 - INFO - __main__ - Step 65818: {'lr': 0.00030361875506810273, 'samples': 12637056, 'steps': 65817, 'loss/train': 1.4997085332870483} 08/31/2021 01:07:50 - INFO - __main__ - Step 65819: {'lr': 0.00030361357180240745, 'samples': 12637248, 'steps': 65818, 'loss/train': 1.1740524768829346} 08/31/2021 01:07:52 - INFO - __main__ - Step 65820: {'lr': 0.0003036083885125547, 'samples': 12637440, 'steps': 65819, 'loss/train': 0.7947989702224731} 08/31/2021 01:07:52 - INFO - __main__ - Step 65821: {'lr': 0.0003036032051985469, 'samples': 12637632, 'steps': 65820, 'loss/train': 0.05270244553685188} 08/31/2021 01:07:52 - INFO - __main__ - Step 65822: {'lr': 0.00030359802186038625, 'samples': 12637824, 'steps': 65821, 'loss/train': 0.7701067328453064} 08/31/2021 01:07:53 - INFO - __main__ - Step 65823: {'lr': 0.00030359283849807516, 'samples': 12638016, 'steps': 65822, 'loss/train': 1.0110740661621094} 08/31/2021 01:07:53 - INFO - __main__ - Step 65824: {'lr': 0.000303587655111616, 'samples': 12638208, 'steps': 65823, 'loss/train': 0.09060265868902206} 08/31/2021 01:07:55 - INFO - __main__ - Step 65825: {'lr': 0.00030358247170101104, 'samples': 12638400, 'steps': 65824, 'loss/train': 1.247219443321228} 08/31/2021 01:07:55 - INFO - __main__ - Step 65826: {'lr': 0.00030357728826626266, 'samples': 12638592, 'steps': 65825, 'loss/train': 0.06866944581270218} 08/31/2021 01:07:56 - INFO - __main__ - Step 65827: {'lr': 0.00030357210480737323, 'samples': 12638784, 'steps': 65826, 'loss/train': 1.2087512016296387} 08/31/2021 01:07:56 - INFO - __main__ - Step 65828: {'lr': 0.000303566921324345, 'samples': 12638976, 'steps': 65827, 'loss/train': 1.6270509958267212} 08/31/2021 01:07:56 - INFO - __main__ - Step 65829: {'lr': 0.00030356173781718033, 'samples': 12639168, 'steps': 65828, 'loss/train': 0.07372482866048813} 08/31/2021 01:07:58 - INFO - __main__ - Step 65830: {'lr': 0.0003035565542858816, 'samples': 12639360, 'steps': 65829, 'loss/train': 1.6874191761016846} 08/31/2021 01:07:59 - INFO - __main__ - Step 65831: {'lr': 0.00030355137073045105, 'samples': 12639552, 'steps': 65830, 'loss/train': 1.5783295631408691} 08/31/2021 01:07:59 - INFO - __main__ - Step 65832: {'lr': 0.0003035461871508911, 'samples': 12639744, 'steps': 65831, 'loss/train': 0.7489145398139954} 08/31/2021 01:08:00 - INFO - __main__ - Step 65833: {'lr': 0.00030354100354720403, 'samples': 12639936, 'steps': 65832, 'loss/train': 1.6703813076019287} 08/31/2021 01:08:00 - INFO - __main__ - Step 65834: {'lr': 0.0003035358199193923, 'samples': 12640128, 'steps': 65833, 'loss/train': 1.0327829122543335} 08/31/2021 01:08:01 - INFO - __main__ - Step 65835: {'lr': 0.00030353063626745814, 'samples': 12640320, 'steps': 65834, 'loss/train': 1.2123132944107056} 08/31/2021 01:08:02 - INFO - __main__ - Step 65836: {'lr': 0.0003035254525914038, 'samples': 12640512, 'steps': 65835, 'loss/train': 1.2800759077072144} 08/31/2021 01:08:02 - INFO - __main__ - Step 65837: {'lr': 0.00030352026889123187, 'samples': 12640704, 'steps': 65836, 'loss/train': 1.8243138790130615} 08/31/2021 01:08:02 - INFO - __main__ - Step 65838: {'lr': 0.00030351508516694443, 'samples': 12640896, 'steps': 65837, 'loss/train': 1.3478175401687622} 08/31/2021 01:08:03 - INFO - __main__ - Step 65839: {'lr': 0.0003035099014185439, 'samples': 12641088, 'steps': 65838, 'loss/train': 1.4443506002426147} 08/31/2021 01:08:04 - INFO - __main__ - Step 65840: {'lr': 0.0003035047176460327, 'samples': 12641280, 'steps': 65839, 'loss/train': 1.312974214553833} 08/31/2021 01:08:05 - INFO - __main__ - Step 65841: {'lr': 0.00030349953384941307, 'samples': 12641472, 'steps': 65840, 'loss/train': 1.2631193399429321} 08/31/2021 01:08:05 - INFO - __main__ - Step 65842: {'lr': 0.0003034943500286874, 'samples': 12641664, 'steps': 65841, 'loss/train': 1.0239132642745972} 08/31/2021 01:08:06 - INFO - __main__ - Step 65843: {'lr': 0.00030348916618385796, 'samples': 12641856, 'steps': 65842, 'loss/train': 0.2349710315465927} 08/31/2021 01:08:06 - INFO - __main__ - Step 65844: {'lr': 0.0003034839823149271, 'samples': 12642048, 'steps': 65843, 'loss/train': 0.8245071172714233} 08/31/2021 01:08:06 - INFO - __main__ - Step 65845: {'lr': 0.0003034787984218973, 'samples': 12642240, 'steps': 65844, 'loss/train': 1.3762048482894897} 08/31/2021 01:08:08 - INFO - __main__ - Step 65846: {'lr': 0.0003034736145047707, 'samples': 12642432, 'steps': 65845, 'loss/train': 1.3618677854537964} 08/31/2021 01:08:08 - INFO - __main__ - Step 65847: {'lr': 0.0003034684305635497, 'samples': 12642624, 'steps': 65846, 'loss/train': 1.0759583711624146} 08/31/2021 01:08:09 - INFO - __main__ - Step 65848: {'lr': 0.0003034632465982367, 'samples': 12642816, 'steps': 65847, 'loss/train': 1.720124363899231} 08/31/2021 01:08:09 - INFO - __main__ - Step 65849: {'lr': 0.00030345806260883396, 'samples': 12643008, 'steps': 65848, 'loss/train': 1.2611768245697021} 08/31/2021 01:08:09 - INFO - __main__ - Step 65850: {'lr': 0.00030345287859534384, 'samples': 12643200, 'steps': 65849, 'loss/train': 0.6493425965309143} 08/31/2021 01:08:11 - INFO - __main__ - Step 65851: {'lr': 0.00030344769455776865, 'samples': 12643392, 'steps': 65850, 'loss/train': 1.423813819885254} 08/31/2021 01:08:11 - INFO - __main__ - Step 65852: {'lr': 0.00030344251049611084, 'samples': 12643584, 'steps': 65851, 'loss/train': 1.77849280834198} 08/31/2021 01:08:12 - INFO - __main__ - Step 65853: {'lr': 0.0003034373264103725, 'samples': 12643776, 'steps': 65852, 'loss/train': 1.1963828802108765} 08/31/2021 01:08:12 - INFO - __main__ - Step 65854: {'lr': 0.00030343214230055634, 'samples': 12643968, 'steps': 65853, 'loss/train': 1.1193403005599976} 08/31/2021 01:08:12 - INFO - __main__ - Step 65855: {'lr': 0.0003034269581666643, 'samples': 12644160, 'steps': 65854, 'loss/train': 1.3066281080245972} 08/31/2021 01:08:14 - INFO - __main__ - Step 65856: {'lr': 0.00030342177400869905, 'samples': 12644352, 'steps': 65855, 'loss/train': 1.1654835939407349} 08/31/2021 01:08:14 - INFO - __main__ - Step 65857: {'lr': 0.00030341658982666265, 'samples': 12644544, 'steps': 65856, 'loss/train': 1.153998613357544} 08/31/2021 01:08:15 - INFO - __main__ - Step 65858: {'lr': 0.00030341140562055755, 'samples': 12644736, 'steps': 65857, 'loss/train': 1.9430736303329468} 08/31/2021 01:08:15 - INFO - __main__ - Step 65859: {'lr': 0.00030340622139038616, 'samples': 12644928, 'steps': 65858, 'loss/train': 0.8455159664154053} 08/31/2021 01:08:15 - INFO - __main__ - Step 65860: {'lr': 0.0003034010371361507, 'samples': 12645120, 'steps': 65859, 'loss/train': 1.1531219482421875} 08/31/2021 01:08:17 - INFO - __main__ - Step 65861: {'lr': 0.00030339585285785365, 'samples': 12645312, 'steps': 65860, 'loss/train': 0.8698910474777222} 08/31/2021 01:08:17 - INFO - __main__ - Step 65862: {'lr': 0.0003033906685554972, 'samples': 12645504, 'steps': 65861, 'loss/train': 1.1135250329971313} 08/31/2021 01:08:17 - INFO - __main__ - Step 65863: {'lr': 0.00030338548422908373, 'samples': 12645696, 'steps': 65862, 'loss/train': 1.2021974325180054} 08/31/2021 01:08:18 - INFO - __main__ - Step 65864: {'lr': 0.0003033802998786156, 'samples': 12645888, 'steps': 65863, 'loss/train': 1.090243935585022} 08/31/2021 01:08:18 - INFO - __main__ - Step 65865: {'lr': 0.0003033751155040951, 'samples': 12646080, 'steps': 65864, 'loss/train': 1.0777881145477295} 08/31/2021 01:08:20 - INFO - __main__ - Step 65866: {'lr': 0.00030336993110552455, 'samples': 12646272, 'steps': 65865, 'loss/train': 2.1781797409057617} 08/31/2021 01:08:20 - INFO - __main__ - Step 65867: {'lr': 0.00030336474668290645, 'samples': 12646464, 'steps': 65866, 'loss/train': 1.9447112083435059} 08/31/2021 01:08:21 - INFO - __main__ - Step 65868: {'lr': 0.00030335956223624303, 'samples': 12646656, 'steps': 65867, 'loss/train': 2.159682273864746} 08/31/2021 01:08:21 - INFO - __main__ - Step 65869: {'lr': 0.0003033543777655365, 'samples': 12646848, 'steps': 65868, 'loss/train': 0.10666154325008392} 08/31/2021 01:08:22 - INFO - __main__ - Step 65870: {'lr': 0.00030334919327078936, 'samples': 12647040, 'steps': 65869, 'loss/train': 1.2484843730926514} 08/31/2021 01:08:22 - INFO - __main__ - Step 65871: {'lr': 0.0003033440087520039, 'samples': 12647232, 'steps': 65870, 'loss/train': 1.2730315923690796} 08/31/2021 01:08:23 - INFO - __main__ - Step 65872: {'lr': 0.0003033388242091824, 'samples': 12647424, 'steps': 65871, 'loss/train': 1.1233868598937988} 08/31/2021 01:08:24 - INFO - __main__ - Step 65873: {'lr': 0.00030333363964232736, 'samples': 12647616, 'steps': 65872, 'loss/train': 0.8288429379463196} 08/31/2021 01:08:24 - INFO - __main__ - Step 65874: {'lr': 0.000303328455051441, 'samples': 12647808, 'steps': 65873, 'loss/train': 2.341963768005371} 08/31/2021 01:08:24 - INFO - __main__ - Step 65875: {'lr': 0.00030332327043652553, 'samples': 12648000, 'steps': 65874, 'loss/train': 1.1291850805282593} 08/31/2021 01:08:25 - INFO - __main__ - Step 65876: {'lr': 0.0003033180857975835, 'samples': 12648192, 'steps': 65875, 'loss/train': 0.9952127933502197} 08/31/2021 01:08:26 - INFO - __main__ - Step 65877: {'lr': 0.00030331290113461715, 'samples': 12648384, 'steps': 65876, 'loss/train': 1.31715726852417} 08/31/2021 01:08:27 - INFO - __main__ - Step 65878: {'lr': 0.00030330771644762887, 'samples': 12648576, 'steps': 65877, 'loss/train': 1.2778785228729248} 08/31/2021 01:08:27 - INFO - __main__ - Step 65879: {'lr': 0.0003033025317366209, 'samples': 12648768, 'steps': 65878, 'loss/train': 1.5605806112289429} 08/31/2021 01:08:27 - INFO - __main__ - Step 65880: {'lr': 0.00030329734700159565, 'samples': 12648960, 'steps': 65879, 'loss/train': 1.2306151390075684} 08/31/2021 01:08:28 - INFO - __main__ - Step 65881: {'lr': 0.00030329216224255547, 'samples': 12649152, 'steps': 65880, 'loss/train': 4.2898430824279785} 08/31/2021 01:08:28 - INFO - __main__ - Step 65882: {'lr': 0.0003032869774595026, 'samples': 12649344, 'steps': 65881, 'loss/train': 1.0282505750656128} 08/31/2021 01:08:30 - INFO - __main__ - Step 65883: {'lr': 0.0003032817926524395, 'samples': 12649536, 'steps': 65882, 'loss/train': 1.4457778930664062} 08/31/2021 01:08:31 - INFO - __main__ - Step 65884: {'lr': 0.00030327660782136843, 'samples': 12649728, 'steps': 65883, 'loss/train': 0.9965853691101074} 08/31/2021 01:08:31 - INFO - __main__ - Step 65885: {'lr': 0.00030327142296629174, 'samples': 12649920, 'steps': 65884, 'loss/train': 1.2670036554336548} 08/31/2021 01:08:32 - INFO - __main__ - Step 65886: {'lr': 0.0003032662380872118, 'samples': 12650112, 'steps': 65885, 'loss/train': 0.12240852415561676} 08/31/2021 01:08:32 - INFO - __main__ - Step 65887: {'lr': 0.00030326105318413086, 'samples': 12650304, 'steps': 65886, 'loss/train': 1.4445197582244873} 08/31/2021 01:08:34 - INFO - __main__ - Step 65888: {'lr': 0.00030325586825705127, 'samples': 12650496, 'steps': 65887, 'loss/train': 0.9331350326538086} 08/31/2021 01:08:34 - INFO - __main__ - Step 65889: {'lr': 0.0003032506833059755, 'samples': 12650688, 'steps': 65888, 'loss/train': 0.382219135761261} 08/31/2021 01:08:35 - INFO - __main__ - Step 65890: {'lr': 0.00030324549833090573, 'samples': 12650880, 'steps': 65889, 'loss/train': 1.5543391704559326} 08/31/2021 01:08:35 - INFO - __main__ - Step 65891: {'lr': 0.00030324031333184444, 'samples': 12651072, 'steps': 65890, 'loss/train': 1.5006940364837646} 08/31/2021 01:08:35 - INFO - __main__ - Step 65892: {'lr': 0.00030323512830879377, 'samples': 12651264, 'steps': 65891, 'loss/train': 0.09221365302801132} 08/31/2021 01:08:37 - INFO - __main__ - Step 65893: {'lr': 0.00030322994326175627, 'samples': 12651456, 'steps': 65892, 'loss/train': 1.2121707201004028} 08/31/2021 01:08:38 - INFO - __main__ - Step 65894: {'lr': 0.0003032247581907342, 'samples': 12651648, 'steps': 65893, 'loss/train': 0.8326782584190369} 08/31/2021 01:08:38 - INFO - __main__ - Step 65895: {'lr': 0.0003032195730957298, 'samples': 12651840, 'steps': 65894, 'loss/train': 1.1058540344238281} 08/31/2021 01:08:38 - INFO - __main__ - Step 65896: {'lr': 0.0003032143879767455, 'samples': 12652032, 'steps': 65895, 'loss/train': 1.101645827293396} 08/31/2021 01:08:39 - INFO - __main__ - Step 65897: {'lr': 0.0003032092028337836, 'samples': 12652224, 'steps': 65896, 'loss/train': 1.685446858406067} 08/31/2021 01:08:40 - INFO - __main__ - Step 65898: {'lr': 0.00030320401766684645, 'samples': 12652416, 'steps': 65897, 'loss/train': 1.7968113422393799} 08/31/2021 01:08:41 - INFO - __main__ - Step 65899: {'lr': 0.00030319883247593646, 'samples': 12652608, 'steps': 65898, 'loss/train': 1.8053383827209473} 08/31/2021 01:08:41 - INFO - __main__ - Step 65900: {'lr': 0.00030319364726105584, 'samples': 12652800, 'steps': 65899, 'loss/train': 1.3248956203460693} 08/31/2021 01:08:41 - INFO - __main__ - Step 65901: {'lr': 0.0003031884620222071, 'samples': 12652992, 'steps': 65900, 'loss/train': 1.6386667490005493} 08/31/2021 01:08:42 - INFO - __main__ - Step 65902: {'lr': 0.00030318327675939226, 'samples': 12653184, 'steps': 65901, 'loss/train': 2.0547080039978027} 08/31/2021 01:08:43 - INFO - __main__ - Step 65903: {'lr': 0.000303178091472614, 'samples': 12653376, 'steps': 65902, 'loss/train': 1.637991189956665} 08/31/2021 01:08:44 - INFO - __main__ - Step 65904: {'lr': 0.0003031729061618744, 'samples': 12653568, 'steps': 65903, 'loss/train': 1.2782520055770874} 08/31/2021 01:08:44 - INFO - __main__ - Step 65905: {'lr': 0.000303167720827176, 'samples': 12653760, 'steps': 65904, 'loss/train': 1.156000018119812} 08/31/2021 01:08:44 - INFO - __main__ - Step 65906: {'lr': 0.000303162535468521, 'samples': 12653952, 'steps': 65905, 'loss/train': 1.7092310190200806} 08/31/2021 01:08:45 - INFO - __main__ - Step 65907: {'lr': 0.00030315735008591184, 'samples': 12654144, 'steps': 65906, 'loss/train': 0.8868407011032104} 08/31/2021 01:08:45 - INFO - __main__ - Step 65908: {'lr': 0.00030315216467935083, 'samples': 12654336, 'steps': 65907, 'loss/train': 1.5162544250488281} 08/31/2021 01:08:47 - INFO - __main__ - Step 65909: {'lr': 0.0003031469792488402, 'samples': 12654528, 'steps': 65908, 'loss/train': 1.1699973344802856} 08/31/2021 01:08:47 - INFO - __main__ - Step 65910: {'lr': 0.00030314179379438227, 'samples': 12654720, 'steps': 65909, 'loss/train': 1.318607211112976} 08/31/2021 01:08:48 - INFO - __main__ - Step 65911: {'lr': 0.0003031366083159796, 'samples': 12654912, 'steps': 65910, 'loss/train': 0.3048091232776642} 08/31/2021 01:08:48 - INFO - __main__ - Step 65912: {'lr': 0.00030313142281363436, 'samples': 12655104, 'steps': 65911, 'loss/train': 0.9739013910293579} 08/31/2021 01:08:48 - INFO - __main__ - Step 65913: {'lr': 0.0003031262372873489, 'samples': 12655296, 'steps': 65912, 'loss/train': 0.05206552892923355} 08/31/2021 01:08:50 - INFO - __main__ - Step 65914: {'lr': 0.00030312105173712554, 'samples': 12655488, 'steps': 65913, 'loss/train': 0.9683367609977722} 08/31/2021 01:08:50 - INFO - __main__ - Step 65915: {'lr': 0.00030311586616296683, 'samples': 12655680, 'steps': 65914, 'loss/train': 1.6245954036712646} 08/31/2021 01:08:51 - INFO - __main__ - Step 65916: {'lr': 0.0003031106805648748, 'samples': 12655872, 'steps': 65915, 'loss/train': 0.800868570804596} 08/31/2021 01:08:51 - INFO - __main__ - Step 65917: {'lr': 0.0003031054949428519, 'samples': 12656064, 'steps': 65916, 'loss/train': 1.4601258039474487} 08/31/2021 01:08:51 - INFO - __main__ - Step 65918: {'lr': 0.0003031003092969005, 'samples': 12656256, 'steps': 65917, 'loss/train': 1.4202390909194946} 08/31/2021 01:08:53 - INFO - __main__ - Step 65919: {'lr': 0.0003030951236270229, 'samples': 12656448, 'steps': 65918, 'loss/train': 1.3149826526641846} 08/31/2021 01:08:53 - INFO - __main__ - Step 65920: {'lr': 0.00030308993793322147, 'samples': 12656640, 'steps': 65919, 'loss/train': 1.3933838605880737} 08/31/2021 01:08:54 - INFO - __main__ - Step 65921: {'lr': 0.0003030847522154986, 'samples': 12656832, 'steps': 65920, 'loss/train': 1.134491205215454} 08/31/2021 01:08:54 - INFO - __main__ - Step 65922: {'lr': 0.00030307956647385653, 'samples': 12657024, 'steps': 65921, 'loss/train': 0.8888758420944214} 08/31/2021 01:08:54 - INFO - __main__ - Step 65923: {'lr': 0.00030307438070829764, 'samples': 12657216, 'steps': 65922, 'loss/train': 1.0645960569381714} 08/31/2021 01:08:56 - INFO - __main__ - Step 65924: {'lr': 0.0003030691949188242, 'samples': 12657408, 'steps': 65923, 'loss/train': 2.006544589996338} 08/31/2021 01:08:57 - INFO - __main__ - Step 65925: {'lr': 0.0003030640091054386, 'samples': 12657600, 'steps': 65924, 'loss/train': 0.05754195898771286} 08/31/2021 01:08:57 - INFO - __main__ - Step 65926: {'lr': 0.00030305882326814315, 'samples': 12657792, 'steps': 65925, 'loss/train': 1.3018587827682495} 08/31/2021 01:08:57 - INFO - __main__ - Step 65927: {'lr': 0.00030305363740694023, 'samples': 12657984, 'steps': 65926, 'loss/train': 1.6821051836013794} 08/31/2021 01:08:58 - INFO - __main__ - Step 65928: {'lr': 0.0003030484515218323, 'samples': 12658176, 'steps': 65927, 'loss/train': 0.023766731843352318} 08/31/2021 01:08:58 - INFO - __main__ - Step 65929: {'lr': 0.0003030432656128214, 'samples': 12658368, 'steps': 65928, 'loss/train': 0.021355103701353073} 08/31/2021 01:09:00 - INFO - __main__ - Step 65930: {'lr': 0.00030303807967991007, 'samples': 12658560, 'steps': 65929, 'loss/train': 1.4763789176940918} 08/31/2021 01:09:00 - INFO - __main__ - Step 65931: {'lr': 0.00030303289372310063, 'samples': 12658752, 'steps': 65930, 'loss/train': 1.349745750427246} 08/31/2021 01:09:01 - INFO - __main__ - Step 65932: {'lr': 0.00030302770774239527, 'samples': 12658944, 'steps': 65931, 'loss/train': 1.3322137594223022} 08/31/2021 01:09:01 - INFO - __main__ - Step 65933: {'lr': 0.00030302252173779653, 'samples': 12659136, 'steps': 65932, 'loss/train': 2.148031234741211} 08/31/2021 01:09:02 - INFO - __main__ - Step 65934: {'lr': 0.0003030173357093067, 'samples': 12659328, 'steps': 65933, 'loss/train': 0.019344013184309006} 08/31/2021 01:09:02 - INFO - __main__ - Step 65935: {'lr': 0.0003030121496569281, 'samples': 12659520, 'steps': 65934, 'loss/train': 1.559005856513977} 08/31/2021 01:09:03 - INFO - __main__ - Step 65936: {'lr': 0.00030300696358066294, 'samples': 12659712, 'steps': 65935, 'loss/train': 1.0203615427017212} 08/31/2021 01:09:04 - INFO - __main__ - Step 65937: {'lr': 0.00030300177748051373, 'samples': 12659904, 'steps': 65936, 'loss/train': 1.0646593570709229} 08/31/2021 01:09:04 - INFO - __main__ - Step 65938: {'lr': 0.00030299659135648265, 'samples': 12660096, 'steps': 65937, 'loss/train': 0.7878075242042542} 08/31/2021 01:09:05 - INFO - __main__ - Step 65939: {'lr': 0.00030299140520857217, 'samples': 12660288, 'steps': 65938, 'loss/train': 1.0797593593597412} 08/31/2021 01:09:05 - INFO - __main__ - Step 65940: {'lr': 0.0003029862190367846, 'samples': 12660480, 'steps': 65939, 'loss/train': 0.08780722320079803} 08/31/2021 01:09:05 - INFO - __main__ - Step 65941: {'lr': 0.00030298103284112226, 'samples': 12660672, 'steps': 65940, 'loss/train': 1.3972340822219849} 08/31/2021 01:09:07 - INFO - __main__ - Step 65942: {'lr': 0.0003029758466215875, 'samples': 12660864, 'steps': 65941, 'loss/train': 1.152197003364563} 08/31/2021 01:09:08 - INFO - __main__ - Step 65943: {'lr': 0.0003029706603781826, 'samples': 12661056, 'steps': 65942, 'loss/train': 1.1505191326141357} 08/31/2021 01:09:08 - INFO - __main__ - Step 65944: {'lr': 0.0003029654741109099, 'samples': 12661248, 'steps': 65943, 'loss/train': 1.7697044610977173} 08/31/2021 01:09:08 - INFO - __main__ - Step 65945: {'lr': 0.0003029602878197719, 'samples': 12661440, 'steps': 65944, 'loss/train': 1.1464521884918213} 08/31/2021 01:09:09 - INFO - __main__ - Step 65946: {'lr': 0.00030295510150477067, 'samples': 12661632, 'steps': 65945, 'loss/train': 0.9246228933334351} 08/31/2021 01:09:10 - INFO - __main__ - Step 65947: {'lr': 0.00030294991516590877, 'samples': 12661824, 'steps': 65946, 'loss/train': 0.9936612248420715} 08/31/2021 01:09:11 - INFO - __main__ - Step 65948: {'lr': 0.00030294472880318846, 'samples': 12662016, 'steps': 65947, 'loss/train': 1.36318838596344} 08/31/2021 01:09:11 - INFO - __main__ - Step 65949: {'lr': 0.000302939542416612, 'samples': 12662208, 'steps': 65948, 'loss/train': 0.8315436244010925} 08/31/2021 01:09:12 - INFO - __main__ - Step 65950: {'lr': 0.00030293435600618193, 'samples': 12662400, 'steps': 65949, 'loss/train': 1.4340078830718994} 08/31/2021 01:09:12 - INFO - __main__ - Step 65951: {'lr': 0.0003029291695719003, 'samples': 12662592, 'steps': 65950, 'loss/train': 0.07883232831954956} 08/31/2021 01:09:14 - INFO - __main__ - Step 65952: {'lr': 0.0003029239831137697, 'samples': 12662784, 'steps': 65951, 'loss/train': 0.18378718197345734} 08/31/2021 01:09:14 - INFO - __main__ - Step 65953: {'lr': 0.00030291879663179233, 'samples': 12662976, 'steps': 65952, 'loss/train': 1.4610933065414429} 08/31/2021 01:09:14 - INFO - __main__ - Step 65954: {'lr': 0.00030291361012597056, 'samples': 12663168, 'steps': 65953, 'loss/train': 1.306896448135376} 08/31/2021 01:09:15 - INFO - __main__ - Step 65955: {'lr': 0.0003029084235963068, 'samples': 12663360, 'steps': 65954, 'loss/train': 3.052548885345459} 08/31/2021 01:09:15 - INFO - __main__ - Step 65956: {'lr': 0.00030290323704280334, 'samples': 12663552, 'steps': 65955, 'loss/train': 0.7414348125457764} 08/31/2021 01:09:17 - INFO - __main__ - Step 65957: {'lr': 0.0003028980504654624, 'samples': 12663744, 'steps': 65956, 'loss/train': 1.3095656633377075} 08/31/2021 01:09:17 - INFO - __main__ - Step 65958: {'lr': 0.00030289286386428645, 'samples': 12663936, 'steps': 65957, 'loss/train': 1.262945294380188} 08/31/2021 01:09:17 - INFO - __main__ - Step 65959: {'lr': 0.0003028876772392778, 'samples': 12664128, 'steps': 65958, 'loss/train': 0.18180279433727264} 08/31/2021 01:09:18 - INFO - __main__ - Step 65960: {'lr': 0.00030288249059043875, 'samples': 12664320, 'steps': 65959, 'loss/train': 1.2817773818969727} 08/31/2021 01:09:18 - INFO - __main__ - Step 65961: {'lr': 0.0003028773039177717, 'samples': 12664512, 'steps': 65960, 'loss/train': 0.9384646415710449} 08/31/2021 01:09:20 - INFO - __main__ - Step 65962: {'lr': 0.00030287211722127894, 'samples': 12664704, 'steps': 65961, 'loss/train': 1.497781753540039} 08/31/2021 01:09:20 - INFO - __main__ - Step 65963: {'lr': 0.0003028669305009628, 'samples': 12664896, 'steps': 65962, 'loss/train': 1.3185358047485352} 08/31/2021 01:09:20 - INFO - __main__ - Step 65964: {'lr': 0.0003028617437568257, 'samples': 12665088, 'steps': 65963, 'loss/train': 1.1864171028137207} 08/31/2021 01:09:21 - INFO - __main__ - Step 65965: {'lr': 0.0003028565569888699, 'samples': 12665280, 'steps': 65964, 'loss/train': 1.2991809844970703} 08/31/2021 01:09:21 - INFO - __main__ - Step 65966: {'lr': 0.00030285137019709767, 'samples': 12665472, 'steps': 65965, 'loss/train': 1.0306307077407837} 08/31/2021 01:09:23 - INFO - __main__ - Step 65967: {'lr': 0.0003028461833815115, 'samples': 12665664, 'steps': 65966, 'loss/train': 1.481786847114563} 08/31/2021 01:09:24 - INFO - __main__ - Step 65968: {'lr': 0.00030284099654211366, 'samples': 12665856, 'steps': 65967, 'loss/train': 1.5292929410934448} 08/31/2021 01:09:24 - INFO - __main__ - Step 65969: {'lr': 0.00030283580967890644, 'samples': 12666048, 'steps': 65968, 'loss/train': 0.04558928310871124} 08/31/2021 01:09:24 - INFO - __main__ - Step 65970: {'lr': 0.0003028306227918922, 'samples': 12666240, 'steps': 65969, 'loss/train': 1.741346001625061} 08/31/2021 01:09:25 - INFO - __main__ - Step 65971: {'lr': 0.00030282543588107337, 'samples': 12666432, 'steps': 65970, 'loss/train': 2.0394437313079834} 08/31/2021 01:09:25 - INFO - __main__ - Step 65972: {'lr': 0.00030282024894645213, 'samples': 12666624, 'steps': 65971, 'loss/train': 1.3586783409118652} 08/31/2021 01:09:26 - INFO - __main__ - Step 65973: {'lr': 0.000302815061988031, 'samples': 12666816, 'steps': 65972, 'loss/train': 1.0497355461120605} 08/31/2021 01:09:27 - INFO - __main__ - Step 65974: {'lr': 0.00030280987500581213, 'samples': 12667008, 'steps': 65973, 'loss/train': 1.4774341583251953} 08/31/2021 01:09:27 - INFO - __main__ - Step 65975: {'lr': 0.000302804687999798, 'samples': 12667200, 'steps': 65974, 'loss/train': 1.0417388677597046} 08/31/2021 01:09:28 - INFO - __main__ - Step 65976: {'lr': 0.00030279950096999094, 'samples': 12667392, 'steps': 65975, 'loss/train': 1.2771494388580322} 08/31/2021 01:09:28 - INFO - __main__ - Step 65977: {'lr': 0.0003027943139163931, 'samples': 12667584, 'steps': 65976, 'loss/train': 0.6606126427650452} 08/31/2021 01:09:29 - INFO - __main__ - Step 65978: {'lr': 0.00030278912683900705, 'samples': 12667776, 'steps': 65977, 'loss/train': 1.4271670579910278} 08/31/2021 01:09:30 - INFO - __main__ - Step 65979: {'lr': 0.000302783939737835, 'samples': 12667968, 'steps': 65978, 'loss/train': 1.8155410289764404} 08/31/2021 01:09:30 - INFO - __main__ - Step 65980: {'lr': 0.0003027787526128794, 'samples': 12668160, 'steps': 65979, 'loss/train': 1.084389328956604} 08/31/2021 01:09:31 - INFO - __main__ - Step 65981: {'lr': 0.0003027735654641424, 'samples': 12668352, 'steps': 65980, 'loss/train': 1.2520512342453003} 08/31/2021 01:09:31 - INFO - __main__ - Step 65982: {'lr': 0.0003027683782916265, 'samples': 12668544, 'steps': 65981, 'loss/train': 1.174633502960205} 08/31/2021 01:09:33 - INFO - __main__ - Step 65983: {'lr': 0.000302763191095334, 'samples': 12668736, 'steps': 65982, 'loss/train': 1.3936184644699097} 08/31/2021 01:09:33 - INFO - __main__ - Step 65984: {'lr': 0.0003027580038752672, 'samples': 12668928, 'steps': 65983, 'loss/train': 1.9840712547302246} 08/31/2021 01:09:34 - INFO - __main__ - Step 65985: {'lr': 0.00030275281663142843, 'samples': 12669120, 'steps': 65984, 'loss/train': 1.9453052282333374} 08/31/2021 01:09:34 - INFO - __main__ - Step 65986: {'lr': 0.00030274762936382003, 'samples': 12669312, 'steps': 65985, 'loss/train': 1.9196542501449585} 08/31/2021 01:09:34 - INFO - __main__ - Step 65987: {'lr': 0.00030274244207244446, 'samples': 12669504, 'steps': 65986, 'loss/train': 0.020443035289645195} 08/31/2021 01:09:35 - INFO - __main__ - Step 65988: {'lr': 0.00030273725475730393, 'samples': 12669696, 'steps': 65987, 'loss/train': 1.357226848602295} 08/31/2021 01:09:36 - INFO - __main__ - Step 65989: {'lr': 0.00030273206741840083, 'samples': 12669888, 'steps': 65988, 'loss/train': 1.0094387531280518} 08/31/2021 01:09:36 - INFO - __main__ - Step 65990: {'lr': 0.0003027268800557374, 'samples': 12670080, 'steps': 65989, 'loss/train': 1.013974905014038} 08/31/2021 01:09:37 - INFO - __main__ - Step 65991: {'lr': 0.00030272169266931605, 'samples': 12670272, 'steps': 65990, 'loss/train': 1.2535074949264526} 08/31/2021 01:09:37 - INFO - __main__ - Step 65992: {'lr': 0.0003027165052591391, 'samples': 12670464, 'steps': 65991, 'loss/train': 1.2962270975112915} 08/31/2021 01:09:38 - INFO - __main__ - Step 65993: {'lr': 0.000302711317825209, 'samples': 12670656, 'steps': 65992, 'loss/train': 1.4793527126312256} 08/31/2021 01:09:40 - INFO - __main__ - Step 65994: {'lr': 0.00030270613036752794, 'samples': 12670848, 'steps': 65993, 'loss/train': 1.105223298072815} 08/31/2021 01:09:40 - INFO - __main__ - Step 65995: {'lr': 0.0003027009428860984, 'samples': 12671040, 'steps': 65994, 'loss/train': 1.689761996269226} 08/31/2021 01:09:40 - INFO - __main__ - Step 65996: {'lr': 0.00030269575538092254, 'samples': 12671232, 'steps': 65995, 'loss/train': 1.4291160106658936} 08/31/2021 01:09:41 - INFO - __main__ - Step 65997: {'lr': 0.00030269056785200277, 'samples': 12671424, 'steps': 65996, 'loss/train': 1.035862922668457} 08/31/2021 01:09:41 - INFO - __main__ - Step 65998: {'lr': 0.00030268538029934146, 'samples': 12671616, 'steps': 65997, 'loss/train': 0.7810248136520386} 08/31/2021 01:09:43 - INFO - __main__ - Step 65999: {'lr': 0.0003026801927229409, 'samples': 12671808, 'steps': 65998, 'loss/train': 1.6495434045791626} 08/31/2021 01:09:44 - INFO - __main__ - Step 66000: {'lr': 0.0003026750051228035, 'samples': 12672000, 'steps': 65999, 'loss/train': 1.02850341796875} 08/31/2021 01:09:44 - INFO - __main__ - Step 66001: {'lr': 0.0003026698174989316, 'samples': 12672192, 'steps': 66000, 'loss/train': 0.020564567297697067} 08/31/2021 01:09:44 - INFO - __main__ - Step 66002: {'lr': 0.0003026646298513274, 'samples': 12672384, 'steps': 66001, 'loss/train': 1.0645530223846436} 08/31/2021 01:09:45 - INFO - __main__ - Step 66003: {'lr': 0.0003026594421799934, 'samples': 12672576, 'steps': 66002, 'loss/train': 2.025251626968384} 08/31/2021 01:09:45 - INFO - __main__ - Step 66004: {'lr': 0.00030265425448493185, 'samples': 12672768, 'steps': 66003, 'loss/train': 1.4274324178695679} 08/31/2021 01:09:46 - INFO - __main__ - Step 66005: {'lr': 0.0003026490667661451, 'samples': 12672960, 'steps': 66004, 'loss/train': 0.5314050316810608} 08/31/2021 01:09:47 - INFO - __main__ - Step 66006: {'lr': 0.0003026438790236355, 'samples': 12673152, 'steps': 66005, 'loss/train': 1.3462532758712769} 08/31/2021 01:09:47 - INFO - __main__ - Step 66007: {'lr': 0.0003026386912574054, 'samples': 12673344, 'steps': 66006, 'loss/train': 0.23902970552444458} 08/31/2021 01:09:48 - INFO - __main__ - Step 66008: {'lr': 0.0003026335034674571, 'samples': 12673536, 'steps': 66007, 'loss/train': 1.612241506576538} 08/31/2021 01:09:48 - INFO - __main__ - Step 66009: {'lr': 0.0003026283156537929, 'samples': 12673728, 'steps': 66008, 'loss/train': 0.6342671513557434} 08/31/2021 01:09:49 - INFO - __main__ - Step 66010: {'lr': 0.00030262312781641524, 'samples': 12673920, 'steps': 66009, 'loss/train': 1.148796796798706} 08/31/2021 01:09:50 - INFO - __main__ - Step 66011: {'lr': 0.0003026179399553264, 'samples': 12674112, 'steps': 66010, 'loss/train': 1.7654675245285034} 08/31/2021 01:09:50 - INFO - __main__ - Step 66012: {'lr': 0.0003026127520705288, 'samples': 12674304, 'steps': 66011, 'loss/train': 0.9871665239334106} 08/31/2021 01:09:51 - INFO - __main__ - Step 66013: {'lr': 0.00030260756416202464, 'samples': 12674496, 'steps': 66012, 'loss/train': 0.16525939106941223} 08/31/2021 01:09:51 - INFO - __main__ - Step 66014: {'lr': 0.0003026023762298163, 'samples': 12674688, 'steps': 66013, 'loss/train': 1.5363733768463135} 08/31/2021 01:09:52 - INFO - __main__ - Step 66015: {'lr': 0.00030259718827390617, 'samples': 12674880, 'steps': 66014, 'loss/train': 1.1539626121520996} 08/31/2021 01:09:53 - INFO - __main__ - Step 66016: {'lr': 0.00030259200029429656, 'samples': 12675072, 'steps': 66015, 'loss/train': 0.7272818088531494} 08/31/2021 01:09:53 - INFO - __main__ - Step 66017: {'lr': 0.00030258681229098977, 'samples': 12675264, 'steps': 66016, 'loss/train': 1.2061820030212402} 08/31/2021 01:09:54 - INFO - __main__ - Step 66018: {'lr': 0.0003025816242639883, 'samples': 12675456, 'steps': 66017, 'loss/train': 0.8383573293685913} 08/31/2021 01:09:54 - INFO - __main__ - Step 66019: {'lr': 0.0003025764362132942, 'samples': 12675648, 'steps': 66018, 'loss/train': 0.33657994866371155} 08/31/2021 01:09:56 - INFO - __main__ - Step 66020: {'lr': 0.0003025712481389101, 'samples': 12675840, 'steps': 66019, 'loss/train': 0.8999456167221069} 08/31/2021 01:09:56 - INFO - __main__ - Step 66021: {'lr': 0.00030256606004083807, 'samples': 12676032, 'steps': 66020, 'loss/train': 0.8856205344200134} 08/31/2021 01:09:56 - INFO - __main__ - Step 66022: {'lr': 0.00030256087191908067, 'samples': 12676224, 'steps': 66021, 'loss/train': 1.2754194736480713} 08/31/2021 01:09:57 - INFO - __main__ - Step 66023: {'lr': 0.00030255568377364017, 'samples': 12676416, 'steps': 66022, 'loss/train': 0.32570910453796387} 08/31/2021 01:09:57 - INFO - __main__ - Step 66024: {'lr': 0.00030255049560451886, 'samples': 12676608, 'steps': 66023, 'loss/train': 1.3047727346420288} 08/31/2021 01:09:59 - INFO - __main__ - Step 66025: {'lr': 0.00030254530741171917, 'samples': 12676800, 'steps': 66024, 'loss/train': 1.361109733581543} 08/31/2021 01:09:59 - INFO - __main__ - Step 66026: {'lr': 0.00030254011919524326, 'samples': 12676992, 'steps': 66025, 'loss/train': 1.4654417037963867} 08/31/2021 01:09:59 - INFO - __main__ - Step 66027: {'lr': 0.00030253493095509364, 'samples': 12677184, 'steps': 66026, 'loss/train': 1.4810339212417603} 08/31/2021 01:10:00 - INFO - __main__ - Step 66028: {'lr': 0.0003025297426912726, 'samples': 12677376, 'steps': 66027, 'loss/train': 1.2857400178909302} 08/31/2021 01:10:00 - INFO - __main__ - Step 66029: {'lr': 0.00030252455440378246, 'samples': 12677568, 'steps': 66028, 'loss/train': 1.5010154247283936} 08/31/2021 01:10:00 - INFO - __main__ - Step 66030: {'lr': 0.0003025193660926255, 'samples': 12677760, 'steps': 66029, 'loss/train': 0.033327843993902206} 08/31/2021 01:10:02 - INFO - __main__ - Step 66031: {'lr': 0.0003025141777578043, 'samples': 12677952, 'steps': 66030, 'loss/train': 0.2552381753921509} 08/31/2021 01:10:02 - INFO - __main__ - Step 66032: {'lr': 0.0003025089893993209, 'samples': 12678144, 'steps': 66031, 'loss/train': 1.7138158082962036} 08/31/2021 01:10:03 - INFO - __main__ - Step 66033: {'lr': 0.00030250380101717775, 'samples': 12678336, 'steps': 66032, 'loss/train': 1.635338544845581} 08/31/2021 01:10:03 - INFO - __main__ - Step 66034: {'lr': 0.00030249861261137716, 'samples': 12678528, 'steps': 66033, 'loss/train': 1.964723825454712} 08/31/2021 01:10:04 - INFO - __main__ - Step 66035: {'lr': 0.00030249342418192155, 'samples': 12678720, 'steps': 66034, 'loss/train': 0.9431825280189514} 08/31/2021 01:10:05 - INFO - __main__ - Step 66036: {'lr': 0.00030248823572881327, 'samples': 12678912, 'steps': 66035, 'loss/train': 0.08830235153436661} 08/31/2021 01:10:06 - INFO - __main__ - Step 66037: {'lr': 0.0003024830472520546, 'samples': 12679104, 'steps': 66036, 'loss/train': 1.395084023475647} 08/31/2021 01:10:06 - INFO - __main__ - Step 66038: {'lr': 0.0003024778587516478, 'samples': 12679296, 'steps': 66037, 'loss/train': 1.52084481716156} 08/31/2021 01:10:06 - INFO - __main__ - Step 66039: {'lr': 0.0003024726702275953, 'samples': 12679488, 'steps': 66038, 'loss/train': 0.8955772519111633} 08/31/2021 01:10:07 - INFO - __main__ - Step 66040: {'lr': 0.0003024674816798995, 'samples': 12679680, 'steps': 66039, 'loss/train': 5.645725727081299} 08/31/2021 01:10:08 - INFO - __main__ - Step 66041: {'lr': 0.0003024622931085626, 'samples': 12679872, 'steps': 66040, 'loss/train': 1.0171451568603516} 08/31/2021 01:10:09 - INFO - __main__ - Step 66042: {'lr': 0.000302457104513587, 'samples': 12680064, 'steps': 66041, 'loss/train': 0.8080103397369385} 08/31/2021 01:10:09 - INFO - __main__ - Step 66043: {'lr': 0.000302451915894975, 'samples': 12680256, 'steps': 66042, 'loss/train': 0.8974658846855164} 08/31/2021 01:10:09 - INFO - __main__ - Step 66044: {'lr': 0.00030244672725272906, 'samples': 12680448, 'steps': 66043, 'loss/train': 1.4546220302581787} 08/31/2021 01:10:10 - INFO - __main__ - Step 66045: {'lr': 0.00030244153858685136, 'samples': 12680640, 'steps': 66044, 'loss/train': 1.3175065517425537} 08/31/2021 01:10:12 - INFO - __main__ - Step 66046: {'lr': 0.0003024363498973444, 'samples': 12680832, 'steps': 66045, 'loss/train': 2.6128597259521484} 08/31/2021 01:10:12 - INFO - __main__ - Step 66047: {'lr': 0.0003024311611842103, 'samples': 12681024, 'steps': 66046, 'loss/train': 1.5000090599060059} 08/31/2021 01:10:12 - INFO - __main__ - Step 66048: {'lr': 0.0003024259724474516, 'samples': 12681216, 'steps': 66047, 'loss/train': 1.4402213096618652} 08/31/2021 01:10:13 - INFO - __main__ - Step 66049: {'lr': 0.0003024207836870706, 'samples': 12681408, 'steps': 66048, 'loss/train': 1.2400944232940674} 08/31/2021 01:10:13 - INFO - __main__ - Step 66050: {'lr': 0.00030241559490306957, 'samples': 12681600, 'steps': 66049, 'loss/train': 1.421663522720337} 08/31/2021 01:10:14 - INFO - __main__ - Step 66051: {'lr': 0.0003024104060954509, 'samples': 12681792, 'steps': 66050, 'loss/train': 1.8244187831878662} 08/31/2021 01:10:15 - INFO - __main__ - Step 66052: {'lr': 0.0003024052172642169, 'samples': 12681984, 'steps': 66051, 'loss/train': 1.5441679954528809} 08/31/2021 01:10:15 - INFO - __main__ - Step 66053: {'lr': 0.00030240002840936994, 'samples': 12682176, 'steps': 66052, 'loss/train': 1.4516924619674683} 08/31/2021 01:10:16 - INFO - __main__ - Step 66054: {'lr': 0.0003023948395309123, 'samples': 12682368, 'steps': 66053, 'loss/train': 1.5355536937713623} 08/31/2021 01:10:16 - INFO - __main__ - Step 66055: {'lr': 0.00030238965062884634, 'samples': 12682560, 'steps': 66054, 'loss/train': 1.5977903604507446} 08/31/2021 01:10:17 - INFO - __main__ - Step 66056: {'lr': 0.00030238446170317444, 'samples': 12682752, 'steps': 66055, 'loss/train': 1.2352265119552612} 08/31/2021 01:10:18 - INFO - __main__ - Step 66057: {'lr': 0.0003023792727538989, 'samples': 12682944, 'steps': 66056, 'loss/train': 1.1677289009094238} 08/31/2021 01:10:19 - INFO - __main__ - Step 66058: {'lr': 0.0003023740837810221, 'samples': 12683136, 'steps': 66057, 'loss/train': 1.4555187225341797} 08/31/2021 01:10:19 - INFO - __main__ - Step 66059: {'lr': 0.00030236889478454633, 'samples': 12683328, 'steps': 66058, 'loss/train': 1.7881406545639038} 08/31/2021 01:10:20 - INFO - __main__ - Step 66060: {'lr': 0.0003023637057644739, 'samples': 12683520, 'steps': 66059, 'loss/train': 0.37494590878486633} 08/31/2021 01:10:20 - INFO - __main__ - Step 66061: {'lr': 0.0003023585167208072, 'samples': 12683712, 'steps': 66060, 'loss/train': 0.05098218843340874} 08/31/2021 01:10:23 - INFO - __main__ - Step 66062: {'lr': 0.0003023533276535486, 'samples': 12683904, 'steps': 66061, 'loss/train': 1.6670334339141846} 08/31/2021 01:10:23 - INFO - __main__ - Step 66063: {'lr': 0.00030234813856270046, 'samples': 12684096, 'steps': 66062, 'loss/train': 1.444349765777588} 08/31/2021 01:10:24 - INFO - __main__ - Step 66064: {'lr': 0.0003023429494482649, 'samples': 12684288, 'steps': 66063, 'loss/train': 1.4012346267700195} 08/31/2021 01:10:24 - INFO - __main__ - Step 66065: {'lr': 0.0003023377603102445, 'samples': 12684480, 'steps': 66064, 'loss/train': 1.3510769605636597} 08/31/2021 01:10:24 - INFO - __main__ - Step 66066: {'lr': 0.00030233257114864156, 'samples': 12684672, 'steps': 66065, 'loss/train': 1.3957021236419678} 08/31/2021 01:10:25 - INFO - __main__ - Step 66067: {'lr': 0.0003023273819634583, 'samples': 12684864, 'steps': 66066, 'loss/train': 0.9905305504798889} 08/31/2021 01:10:25 - INFO - __main__ - Step 66068: {'lr': 0.00030232219275469713, 'samples': 12685056, 'steps': 66067, 'loss/train': 2.7726380825042725} 08/31/2021 01:10:25 - INFO - __main__ - Step 66069: {'lr': 0.00030231700352236044, 'samples': 12685248, 'steps': 66068, 'loss/train': 2.6378750801086426} 08/31/2021 01:10:27 - INFO - __main__ - Step 66070: {'lr': 0.0003023118142664505, 'samples': 12685440, 'steps': 66069, 'loss/train': 2.816310167312622} 08/31/2021 01:10:27 - INFO - __main__ - Step 66071: {'lr': 0.0003023066249869696, 'samples': 12685632, 'steps': 66070, 'loss/train': 1.422318696975708} 08/31/2021 01:10:28 - INFO - __main__ - Step 66072: {'lr': 0.0003023014356839202, 'samples': 12685824, 'steps': 66071, 'loss/train': 0.46967846155166626} 08/31/2021 01:10:28 - INFO - __main__ - Step 66073: {'lr': 0.0003022962463573046, 'samples': 12686016, 'steps': 66072, 'loss/train': 1.3832213878631592} 08/31/2021 01:10:28 - INFO - __main__ - Step 66074: {'lr': 0.000302291057007125, 'samples': 12686208, 'steps': 66073, 'loss/train': 1.5720726251602173} 08/31/2021 01:10:30 - INFO - __main__ - Step 66075: {'lr': 0.00030228586763338393, 'samples': 12686400, 'steps': 66074, 'loss/train': 1.665828824043274} 08/31/2021 01:10:30 - INFO - __main__ - Step 66076: {'lr': 0.00030228067823608376, 'samples': 12686592, 'steps': 66075, 'loss/train': 1.7706561088562012} 08/31/2021 01:10:31 - INFO - __main__ - Step 66077: {'lr': 0.0003022754888152266, 'samples': 12686784, 'steps': 66076, 'loss/train': 1.2173024415969849} 08/31/2021 01:10:31 - INFO - __main__ - Step 66078: {'lr': 0.00030227029937081497, 'samples': 12686976, 'steps': 66077, 'loss/train': 0.5167948603630066} 08/31/2021 01:10:31 - INFO - __main__ - Step 66079: {'lr': 0.00030226510990285105, 'samples': 12687168, 'steps': 66078, 'loss/train': 0.8278330564498901} 08/31/2021 01:10:32 - INFO - __main__ - Step 66080: {'lr': 0.00030225992041133735, 'samples': 12687360, 'steps': 66079, 'loss/train': 1.181849718093872} 08/31/2021 01:10:33 - INFO - __main__ - Step 66081: {'lr': 0.00030225473089627613, 'samples': 12687552, 'steps': 66080, 'loss/train': 1.1168715953826904} 08/31/2021 01:10:34 - INFO - __main__ - Step 66082: {'lr': 0.0003022495413576697, 'samples': 12687744, 'steps': 66081, 'loss/train': 1.417359709739685} 08/31/2021 01:10:34 - INFO - __main__ - Step 66083: {'lr': 0.00030224435179552057, 'samples': 12687936, 'steps': 66082, 'loss/train': 0.7643819451332092} 08/31/2021 01:10:34 - INFO - __main__ - Step 66084: {'lr': 0.00030223916220983084, 'samples': 12688128, 'steps': 66083, 'loss/train': 0.9993094801902771} 08/31/2021 01:10:35 - INFO - __main__ - Step 66085: {'lr': 0.0003022339726006029, 'samples': 12688320, 'steps': 66084, 'loss/train': 1.7294390201568604} 08/31/2021 01:10:37 - INFO - __main__ - Step 66086: {'lr': 0.00030222878296783925, 'samples': 12688512, 'steps': 66085, 'loss/train': 1.0122522115707397} 08/31/2021 01:10:37 - INFO - __main__ - Step 66087: {'lr': 0.00030222359331154205, 'samples': 12688704, 'steps': 66086, 'loss/train': 1.311166524887085} 08/31/2021 01:10:37 - INFO - __main__ - Step 66088: {'lr': 0.0003022184036317137, 'samples': 12688896, 'steps': 66087, 'loss/train': 0.7432406544685364} 08/31/2021 01:10:38 - INFO - __main__ - Step 66089: {'lr': 0.0003022132139283566, 'samples': 12689088, 'steps': 66088, 'loss/train': 1.378537654876709} 08/31/2021 01:10:38 - INFO - __main__ - Step 66090: {'lr': 0.00030220802420147296, 'samples': 12689280, 'steps': 66089, 'loss/train': 1.2470773458480835} 08/31/2021 01:10:40 - INFO - __main__ - Step 66091: {'lr': 0.0003022028344510652, 'samples': 12689472, 'steps': 66090, 'loss/train': 1.4538100957870483} 08/31/2021 01:10:40 - INFO - __main__ - Step 66092: {'lr': 0.00030219764467713566, 'samples': 12689664, 'steps': 66091, 'loss/train': 1.1943458318710327} 08/31/2021 01:10:41 - INFO - __main__ - Step 66093: {'lr': 0.00030219245487968666, 'samples': 12689856, 'steps': 66092, 'loss/train': 1.163406491279602} 08/31/2021 01:10:41 - INFO - __main__ - Step 66094: {'lr': 0.00030218726505872056, 'samples': 12690048, 'steps': 66093, 'loss/train': 1.9015536308288574} 08/31/2021 01:10:41 - INFO - __main__ - Step 66095: {'lr': 0.0003021820752142397, 'samples': 12690240, 'steps': 66094, 'loss/train': 1.188024878501892} 08/31/2021 01:10:43 - INFO - __main__ - Step 66096: {'lr': 0.00030217688534624643, 'samples': 12690432, 'steps': 66095, 'loss/train': 1.3065025806427002} 08/31/2021 01:10:43 - INFO - __main__ - Step 66097: {'lr': 0.000302171695454743, 'samples': 12690624, 'steps': 66096, 'loss/train': 1.3263020515441895} 08/31/2021 01:10:44 - INFO - __main__ - Step 66098: {'lr': 0.0003021665055397318, 'samples': 12690816, 'steps': 66097, 'loss/train': 1.016243577003479} 08/31/2021 01:10:44 - INFO - __main__ - Step 66099: {'lr': 0.0003021613156012152, 'samples': 12691008, 'steps': 66098, 'loss/train': 1.2605936527252197} 08/31/2021 01:10:44 - INFO - __main__ - Step 66100: {'lr': 0.00030215612563919554, 'samples': 12691200, 'steps': 66099, 'loss/train': 1.4379863739013672} 08/31/2021 01:10:45 - INFO - __main__ - Step 66101: {'lr': 0.0003021509356536751, 'samples': 12691392, 'steps': 66100, 'loss/train': 4.254034042358398} 08/31/2021 01:10:46 - INFO - __main__ - Step 66102: {'lr': 0.00030214574564465624, 'samples': 12691584, 'steps': 66101, 'loss/train': 0.7094317078590393} 08/31/2021 01:10:47 - INFO - __main__ - Step 66103: {'lr': 0.00030214055561214137, 'samples': 12691776, 'steps': 66102, 'loss/train': 5.89802360534668} 08/31/2021 01:10:47 - INFO - __main__ - Step 66104: {'lr': 0.00030213536555613276, 'samples': 12691968, 'steps': 66103, 'loss/train': 5.830848693847656} 08/31/2021 01:10:48 - INFO - __main__ - Step 66105: {'lr': 0.0003021301754766327, 'samples': 12692160, 'steps': 66104, 'loss/train': 0.6521362662315369} 08/31/2021 01:10:48 - INFO - __main__ - Step 66106: {'lr': 0.00030212498537364365, 'samples': 12692352, 'steps': 66105, 'loss/train': 1.2350260019302368} 08/31/2021 01:10:48 - INFO - __main__ - Step 66107: {'lr': 0.0003021197952471678, 'samples': 12692544, 'steps': 66106, 'loss/train': 1.717641830444336} 08/31/2021 01:10:50 - INFO - __main__ - Step 66108: {'lr': 0.00030211460509720767, 'samples': 12692736, 'steps': 66107, 'loss/train': 0.05370006710290909} 08/31/2021 01:10:51 - INFO - __main__ - Step 66109: {'lr': 0.00030210941492376543, 'samples': 12692928, 'steps': 66108, 'loss/train': 1.3199681043624878} 08/31/2021 01:10:51 - INFO - __main__ - Step 66110: {'lr': 0.00030210422472684356, 'samples': 12693120, 'steps': 66109, 'loss/train': 0.6202741861343384} 08/31/2021 01:10:52 - INFO - __main__ - Step 66111: {'lr': 0.0003020990345064443, 'samples': 12693312, 'steps': 66110, 'loss/train': 1.3871079683303833} 08/31/2021 01:10:52 - INFO - __main__ - Step 66112: {'lr': 0.00030209384426257003, 'samples': 12693504, 'steps': 66111, 'loss/train': 1.9306694269180298} 08/31/2021 01:10:53 - INFO - __main__ - Step 66113: {'lr': 0.00030208865399522305, 'samples': 12693696, 'steps': 66112, 'loss/train': 1.1573891639709473} 08/31/2021 01:10:54 - INFO - __main__ - Step 66114: {'lr': 0.0003020834637044057, 'samples': 12693888, 'steps': 66113, 'loss/train': 0.9767410755157471} 08/31/2021 01:10:54 - INFO - __main__ - Step 66115: {'lr': 0.0003020782733901204, 'samples': 12694080, 'steps': 66114, 'loss/train': 1.547727346420288} 08/31/2021 01:10:55 - INFO - __main__ - Step 66116: {'lr': 0.0003020730830523695, 'samples': 12694272, 'steps': 66115, 'loss/train': 1.418609619140625} 08/31/2021 01:10:55 - INFO - __main__ - Step 66117: {'lr': 0.00030206789269115515, 'samples': 12694464, 'steps': 66116, 'loss/train': 1.3780627250671387} 08/31/2021 01:10:55 - INFO - __main__ - Step 66118: {'lr': 0.00030206270230647987, 'samples': 12694656, 'steps': 66117, 'loss/train': 2.143683671951294} 08/31/2021 01:10:57 - INFO - __main__ - Step 66119: {'lr': 0.0003020575118983459, 'samples': 12694848, 'steps': 66118, 'loss/train': 0.9876827001571655} 08/31/2021 01:10:57 - INFO - __main__ - Step 66120: {'lr': 0.00030205232146675564, 'samples': 12695040, 'steps': 66119, 'loss/train': 1.1913319826126099} 08/31/2021 01:10:58 - INFO - __main__ - Step 66121: {'lr': 0.0003020471310117114, 'samples': 12695232, 'steps': 66120, 'loss/train': 1.5533381700515747} 08/31/2021 01:10:58 - INFO - __main__ - Step 66122: {'lr': 0.00030204194053321556, 'samples': 12695424, 'steps': 66121, 'loss/train': 1.8916206359863281} 08/31/2021 01:10:58 - INFO - __main__ - Step 66123: {'lr': 0.00030203675003127043, 'samples': 12695616, 'steps': 66122, 'loss/train': 1.2002266645431519} 08/31/2021 01:11:00 - INFO - __main__ - Step 66124: {'lr': 0.0003020315595058783, 'samples': 12695808, 'steps': 66123, 'loss/train': 1.2728787660598755} 08/31/2021 01:11:00 - INFO - __main__ - Step 66125: {'lr': 0.00030202636895704157, 'samples': 12696000, 'steps': 66124, 'loss/train': 1.9307547807693481} 08/31/2021 01:11:01 - INFO - __main__ - Step 66126: {'lr': 0.0003020211783847625, 'samples': 12696192, 'steps': 66125, 'loss/train': 0.9360848069190979} 08/31/2021 01:11:01 - INFO - __main__ - Step 66127: {'lr': 0.00030201598778904353, 'samples': 12696384, 'steps': 66126, 'loss/train': 0.45807212591171265} 08/31/2021 01:11:01 - INFO - __main__ - Step 66128: {'lr': 0.000302010797169887, 'samples': 12696576, 'steps': 66127, 'loss/train': 1.3443076610565186} 08/31/2021 01:11:03 - INFO - __main__ - Step 66129: {'lr': 0.0003020056065272951, 'samples': 12696768, 'steps': 66128, 'loss/train': 1.428950548171997} 08/31/2021 01:11:03 - INFO - __main__ - Step 66130: {'lr': 0.00030200041586127046, 'samples': 12696960, 'steps': 66129, 'loss/train': 1.2275792360305786} 08/31/2021 01:11:04 - INFO - __main__ - Step 66131: {'lr': 0.0003019952251718151, 'samples': 12697152, 'steps': 66130, 'loss/train': 1.0265305042266846} 08/31/2021 01:11:04 - INFO - __main__ - Step 66132: {'lr': 0.0003019900344589315, 'samples': 12697344, 'steps': 66131, 'loss/train': 1.1949602365493774} 08/31/2021 01:11:04 - INFO - __main__ - Step 66133: {'lr': 0.0003019848437226221, 'samples': 12697536, 'steps': 66132, 'loss/train': 1.3149751424789429} 08/31/2021 01:11:06 - INFO - __main__ - Step 66134: {'lr': 0.00030197965296288896, 'samples': 12697728, 'steps': 66133, 'loss/train': 1.6684849262237549} 08/31/2021 01:11:06 - INFO - __main__ - Step 66135: {'lr': 0.00030197446217973474, 'samples': 12697920, 'steps': 66134, 'loss/train': 0.6331090331077576} 08/31/2021 01:11:07 - INFO - __main__ - Step 66136: {'lr': 0.0003019692713731616, 'samples': 12698112, 'steps': 66135, 'loss/train': 1.104103922843933} 08/31/2021 01:11:07 - INFO - __main__ - Step 66137: {'lr': 0.00030196408054317185, 'samples': 12698304, 'steps': 66136, 'loss/train': 0.9608568549156189} 08/31/2021 01:11:08 - INFO - __main__ - Step 66138: {'lr': 0.00030195888968976794, 'samples': 12698496, 'steps': 66137, 'loss/train': 1.415120005607605} 08/31/2021 01:11:09 - INFO - __main__ - Step 66139: {'lr': 0.0003019536988129521, 'samples': 12698688, 'steps': 66138, 'loss/train': 0.059041932225227356} 08/31/2021 01:11:10 - INFO - __main__ - Step 66140: {'lr': 0.00030194850791272676, 'samples': 12698880, 'steps': 66139, 'loss/train': 0.7970123887062073} 08/31/2021 01:11:10 - INFO - __main__ - Step 66141: {'lr': 0.00030194331698909425, 'samples': 12699072, 'steps': 66140, 'loss/train': 0.5090571641921997} 08/31/2021 01:11:10 - INFO - __main__ - Step 66142: {'lr': 0.00030193812604205686, 'samples': 12699264, 'steps': 66141, 'loss/train': 1.1570976972579956} 08/31/2021 01:11:11 - INFO - __main__ - Step 66143: {'lr': 0.00030193293507161696, 'samples': 12699456, 'steps': 66142, 'loss/train': 1.1927858591079712} 08/31/2021 01:11:11 - INFO - __main__ - Step 66144: {'lr': 0.00030192774407777683, 'samples': 12699648, 'steps': 66143, 'loss/train': 1.0357877016067505} 08/31/2021 01:11:13 - INFO - __main__ - Step 66145: {'lr': 0.0003019225530605389, 'samples': 12699840, 'steps': 66144, 'loss/train': 1.2140473127365112} 08/31/2021 01:11:14 - INFO - __main__ - Step 66146: {'lr': 0.00030191736201990544, 'samples': 12700032, 'steps': 66145, 'loss/train': 0.6921444535255432} 08/31/2021 01:11:14 - INFO - __main__ - Step 66147: {'lr': 0.0003019121709558789, 'samples': 12700224, 'steps': 66146, 'loss/train': 1.5134912729263306} 08/31/2021 01:11:14 - INFO - __main__ - Step 66148: {'lr': 0.0003019069798684615, 'samples': 12700416, 'steps': 66147, 'loss/train': 1.5071394443511963} 08/31/2021 01:11:15 - INFO - __main__ - Step 66149: {'lr': 0.0003019017887576556, 'samples': 12700608, 'steps': 66148, 'loss/train': 1.2239997386932373} 08/31/2021 01:11:17 - INFO - __main__ - Step 66150: {'lr': 0.0003018965976234635, 'samples': 12700800, 'steps': 66149, 'loss/train': 0.6006621718406677} 08/31/2021 01:11:17 - INFO - __main__ - Step 66151: {'lr': 0.00030189140646588763, 'samples': 12700992, 'steps': 66150, 'loss/train': 1.2305288314819336} 08/31/2021 01:11:17 - INFO - __main__ - Step 66152: {'lr': 0.00030188621528493036, 'samples': 12701184, 'steps': 66151, 'loss/train': 0.021271314471960068} 08/31/2021 01:11:18 - INFO - __main__ - Step 66153: {'lr': 0.0003018810240805939, 'samples': 12701376, 'steps': 66152, 'loss/train': 1.8742759227752686} 08/31/2021 01:11:18 - INFO - __main__ - Step 66154: {'lr': 0.0003018758328528807, 'samples': 12701568, 'steps': 66153, 'loss/train': 0.6934241056442261} 08/31/2021 01:11:18 - INFO - __main__ - Step 66155: {'lr': 0.00030187064160179294, 'samples': 12701760, 'steps': 66154, 'loss/train': 0.8654941916465759} 08/31/2021 01:11:20 - INFO - __main__ - Step 66156: {'lr': 0.00030186545032733316, 'samples': 12701952, 'steps': 66155, 'loss/train': 1.1086262464523315} 08/31/2021 01:11:20 - INFO - __main__ - Step 66157: {'lr': 0.0003018602590295036, 'samples': 12702144, 'steps': 66156, 'loss/train': 1.0255937576293945} 08/31/2021 01:11:21 - INFO - __main__ - Step 66158: {'lr': 0.00030185506770830664, 'samples': 12702336, 'steps': 66157, 'loss/train': 0.9764173030853271} 08/31/2021 01:11:21 - INFO - __main__ - Step 66159: {'lr': 0.0003018498763637445, 'samples': 12702528, 'steps': 66158, 'loss/train': 1.3195828199386597} 08/31/2021 01:11:21 - INFO - __main__ - Step 66160: {'lr': 0.0003018446849958196, 'samples': 12702720, 'steps': 66159, 'loss/train': 1.7576332092285156} 08/31/2021 01:11:23 - INFO - __main__ - Step 66161: {'lr': 0.0003018394936045344, 'samples': 12702912, 'steps': 66160, 'loss/train': 0.7265757918357849} 08/31/2021 01:11:23 - INFO - __main__ - Step 66162: {'lr': 0.00030183430218989107, 'samples': 12703104, 'steps': 66161, 'loss/train': 1.235973596572876} 08/31/2021 01:11:24 - INFO - __main__ - Step 66163: {'lr': 0.000301829110751892, 'samples': 12703296, 'steps': 66162, 'loss/train': 1.3523199558258057} 08/31/2021 01:11:24 - INFO - __main__ - Step 66164: {'lr': 0.0003018239192905395, 'samples': 12703488, 'steps': 66163, 'loss/train': 1.0917869806289673} 08/31/2021 01:11:25 - INFO - __main__ - Step 66165: {'lr': 0.000301818727805836, 'samples': 12703680, 'steps': 66164, 'loss/train': 1.3273104429244995} 08/31/2021 01:11:26 - INFO - __main__ - Step 66166: {'lr': 0.0003018135362977837, 'samples': 12703872, 'steps': 66165, 'loss/train': 1.278826355934143} 08/31/2021 01:11:27 - INFO - __main__ - Step 66167: {'lr': 0.00030180834476638507, 'samples': 12704064, 'steps': 66166, 'loss/train': 1.2177469730377197} 08/31/2021 01:11:27 - INFO - __main__ - Step 66168: {'lr': 0.0003018031532116424, 'samples': 12704256, 'steps': 66167, 'loss/train': 1.1386572122573853} 08/31/2021 01:11:27 - INFO - __main__ - Step 66169: {'lr': 0.000301797961633558, 'samples': 12704448, 'steps': 66168, 'loss/train': 1.5464329719543457} 08/31/2021 01:11:28 - INFO - __main__ - Step 66170: {'lr': 0.0003017927700321343, 'samples': 12704640, 'steps': 66169, 'loss/train': 0.633595883846283} 08/31/2021 01:11:29 - INFO - __main__ - Step 66171: {'lr': 0.0003017875784073735, 'samples': 12704832, 'steps': 66170, 'loss/train': 0.6006934642791748} 08/31/2021 01:11:30 - INFO - __main__ - Step 66172: {'lr': 0.0003017823867592781, 'samples': 12705024, 'steps': 66171, 'loss/train': 1.1668667793273926} 08/31/2021 01:11:30 - INFO - __main__ - Step 66173: {'lr': 0.00030177719508785026, 'samples': 12705216, 'steps': 66172, 'loss/train': 1.5097099542617798} 08/31/2021 01:11:30 - INFO - __main__ - Step 66174: {'lr': 0.0003017720033930925, 'samples': 12705408, 'steps': 66173, 'loss/train': 0.8498116731643677} 08/31/2021 01:11:31 - INFO - __main__ - Step 66175: {'lr': 0.000301766811675007, 'samples': 12705600, 'steps': 66174, 'loss/train': 1.1972379684448242} 08/31/2021 01:11:31 - INFO - __main__ - Step 66176: {'lr': 0.00030176161993359626, 'samples': 12705792, 'steps': 66175, 'loss/train': 1.2062350511550903} 08/31/2021 01:11:33 - INFO - __main__ - Step 66177: {'lr': 0.0003017564281688625, 'samples': 12705984, 'steps': 66176, 'loss/train': 1.412508249282837} 08/31/2021 01:11:33 - INFO - __main__ - Step 66178: {'lr': 0.0003017512363808081, 'samples': 12706176, 'steps': 66177, 'loss/train': 1.2515400648117065} 08/31/2021 01:11:33 - INFO - __main__ - Step 66179: {'lr': 0.0003017460445694353, 'samples': 12706368, 'steps': 66178, 'loss/train': 1.35331130027771} 08/31/2021 01:11:34 - INFO - __main__ - Step 66180: {'lr': 0.00030174085273474663, 'samples': 12706560, 'steps': 66179, 'loss/train': 1.2336350679397583} 08/31/2021 01:11:34 - INFO - __main__ - Step 66181: {'lr': 0.0003017356608767443, 'samples': 12706752, 'steps': 66180, 'loss/train': 1.0955660343170166} 08/31/2021 01:11:35 - INFO - __main__ - Step 66182: {'lr': 0.00030173046899543065, 'samples': 12706944, 'steps': 66181, 'loss/train': 1.7764631509780884} 08/31/2021 01:11:36 - INFO - __main__ - Step 66183: {'lr': 0.0003017252770908081, 'samples': 12707136, 'steps': 66182, 'loss/train': 1.180425763130188} 08/31/2021 01:11:36 - INFO - __main__ - Step 66184: {'lr': 0.000301720085162879, 'samples': 12707328, 'steps': 66183, 'loss/train': 0.7004525661468506} 08/31/2021 01:11:37 - INFO - __main__ - Step 66185: {'lr': 0.00030171489321164545, 'samples': 12707520, 'steps': 66184, 'loss/train': 0.9172206521034241} 08/31/2021 01:11:37 - INFO - __main__ - Step 66186: {'lr': 0.00030170970123711004, 'samples': 12707712, 'steps': 66185, 'loss/train': 1.4602490663528442} 08/31/2021 01:11:38 - INFO - __main__ - Step 66187: {'lr': 0.0003017045092392751, 'samples': 12707904, 'steps': 66186, 'loss/train': 0.8695699572563171} 08/31/2021 01:11:39 - INFO - __main__ - Step 66188: {'lr': 0.00030169931721814287, 'samples': 12708096, 'steps': 66187, 'loss/train': 1.7009611129760742} 08/31/2021 01:11:39 - INFO - __main__ - Step 66189: {'lr': 0.0003016941251737157, 'samples': 12708288, 'steps': 66188, 'loss/train': 1.2282015085220337} 08/31/2021 01:11:40 - INFO - __main__ - Step 66190: {'lr': 0.000301688933105996, 'samples': 12708480, 'steps': 66189, 'loss/train': 0.5743079781532288} 08/31/2021 01:11:40 - INFO - __main__ - Step 66191: {'lr': 0.00030168374101498604, 'samples': 12708672, 'steps': 66190, 'loss/train': 1.2798901796340942} 08/31/2021 01:11:41 - INFO - __main__ - Step 66192: {'lr': 0.0003016785489006882, 'samples': 12708864, 'steps': 66191, 'loss/train': 1.3811618089675903} 08/31/2021 01:11:42 - INFO - __main__ - Step 66193: {'lr': 0.00030167335676310476, 'samples': 12709056, 'steps': 66192, 'loss/train': 1.6444865465164185} 08/31/2021 01:11:42 - INFO - __main__ - Step 66194: {'lr': 0.0003016681646022381, 'samples': 12709248, 'steps': 66193, 'loss/train': 0.9462544322013855} 08/31/2021 01:11:43 - INFO - __main__ - Step 66195: {'lr': 0.0003016629724180906, 'samples': 12709440, 'steps': 66194, 'loss/train': 1.0749833583831787} 08/31/2021 01:11:43 - INFO - __main__ - Step 66196: {'lr': 0.0003016577802106645, 'samples': 12709632, 'steps': 66195, 'loss/train': 0.6138770580291748} 08/31/2021 01:11:44 - INFO - __main__ - Step 66197: {'lr': 0.00030165258797996237, 'samples': 12709824, 'steps': 66196, 'loss/train': 1.5984948873519897} 08/31/2021 01:11:45 - INFO - __main__ - Step 66198: {'lr': 0.00030164739572598626, 'samples': 12710016, 'steps': 66197, 'loss/train': 1.5046939849853516} 08/31/2021 01:11:45 - INFO - __main__ - Step 66199: {'lr': 0.0003016422034487386, 'samples': 12710208, 'steps': 66198, 'loss/train': 0.6115707159042358} 08/31/2021 01:11:46 - INFO - __main__ - Step 66200: {'lr': 0.0003016370111482218, 'samples': 12710400, 'steps': 66199, 'loss/train': 0.9794584512710571} 08/31/2021 01:11:46 - INFO - __main__ - Step 66201: {'lr': 0.0003016318188244381, 'samples': 12710592, 'steps': 66200, 'loss/train': 1.6124595403671265} 08/31/2021 01:11:46 - INFO - __main__ - Step 66202: {'lr': 0.00030162662647738997, 'samples': 12710784, 'steps': 66201, 'loss/train': 1.6391416788101196} 08/31/2021 01:11:49 - INFO - __main__ - Step 66203: {'lr': 0.0003016214341070797, 'samples': 12710976, 'steps': 66202, 'loss/train': 1.2352232933044434} 08/31/2021 01:11:49 - INFO - __main__ - Step 66204: {'lr': 0.0003016162417135096, 'samples': 12711168, 'steps': 66203, 'loss/train': 1.647311806678772} 08/31/2021 01:11:50 - INFO - __main__ - Step 66205: {'lr': 0.000301611049296682, 'samples': 12711360, 'steps': 66204, 'loss/train': 0.8942677974700928} 08/31/2021 01:11:50 - INFO - __main__ - Step 66206: {'lr': 0.0003016058568565993, 'samples': 12711552, 'steps': 66205, 'loss/train': 0.8759243488311768} 08/31/2021 01:11:50 - INFO - __main__ - Step 66207: {'lr': 0.00030160066439326367, 'samples': 12711744, 'steps': 66206, 'loss/train': 1.2349439859390259} 08/31/2021 01:11:51 - INFO - __main__ - Step 66208: {'lr': 0.0003015954719066776, 'samples': 12711936, 'steps': 66207, 'loss/train': 0.15018564462661743} 08/31/2021 01:11:52 - INFO - __main__ - Step 66209: {'lr': 0.00030159027939684346, 'samples': 12712128, 'steps': 66208, 'loss/train': 1.6783733367919922} 08/31/2021 01:11:53 - INFO - __main__ - Step 66210: {'lr': 0.0003015850868637636, 'samples': 12712320, 'steps': 66209, 'loss/train': 1.4897782802581787} 08/31/2021 01:11:53 - INFO - __main__ - Step 66211: {'lr': 0.00030157989430744023, 'samples': 12712512, 'steps': 66210, 'loss/train': 0.67148756980896} 08/31/2021 01:11:53 - INFO - __main__ - Step 66212: {'lr': 0.0003015747017278757, 'samples': 12712704, 'steps': 66211, 'loss/train': 0.49577224254608154} 08/31/2021 01:11:54 - INFO - __main__ - Step 66213: {'lr': 0.00030156950912507246, 'samples': 12712896, 'steps': 66212, 'loss/train': 1.7290034294128418} 08/31/2021 01:11:56 - INFO - __main__ - Step 66214: {'lr': 0.0003015643164990328, 'samples': 12713088, 'steps': 66213, 'loss/train': 1.2380144596099854} 08/31/2021 01:11:56 - INFO - __main__ - Step 66215: {'lr': 0.0003015591238497591, 'samples': 12713280, 'steps': 66214, 'loss/train': 1.513075351715088} 08/31/2021 01:11:56 - INFO - __main__ - Step 66216: {'lr': 0.00030155393117725355, 'samples': 12713472, 'steps': 66215, 'loss/train': 1.4332433938980103} 08/31/2021 01:11:57 - INFO - __main__ - Step 66217: {'lr': 0.00030154873848151873, 'samples': 12713664, 'steps': 66216, 'loss/train': 1.5498522520065308} 08/31/2021 01:11:57 - INFO - __main__ - Step 66218: {'lr': 0.0003015435457625567, 'samples': 12713856, 'steps': 66217, 'loss/train': 0.04204827919602394} 08/31/2021 01:11:58 - INFO - __main__ - Step 66219: {'lr': 0.00030153835302037, 'samples': 12714048, 'steps': 66218, 'loss/train': 0.02341647632420063} 08/31/2021 01:11:59 - INFO - __main__ - Step 66220: {'lr': 0.00030153316025496093, 'samples': 12714240, 'steps': 66219, 'loss/train': 0.2741487920284271} 08/31/2021 01:11:59 - INFO - __main__ - Step 66221: {'lr': 0.0003015279674663318, 'samples': 12714432, 'steps': 66220, 'loss/train': 1.0527722835540771} 08/31/2021 01:12:00 - INFO - __main__ - Step 66222: {'lr': 0.00030152277465448496, 'samples': 12714624, 'steps': 66221, 'loss/train': 0.8961308002471924} 08/31/2021 01:12:00 - INFO - __main__ - Step 66223: {'lr': 0.0003015175818194227, 'samples': 12714816, 'steps': 66222, 'loss/train': 1.452254056930542} 08/31/2021 01:12:00 - INFO - __main__ - Step 66224: {'lr': 0.00030151238896114756, 'samples': 12715008, 'steps': 66223, 'loss/train': 0.777122974395752} 08/31/2021 01:12:01 - INFO - __main__ - Step 66225: {'lr': 0.00030150719607966163, 'samples': 12715200, 'steps': 66224, 'loss/train': 1.517582893371582} 08/31/2021 01:12:03 - INFO - __main__ - Step 66226: {'lr': 0.0003015020031749674, 'samples': 12715392, 'steps': 66225, 'loss/train': 0.8865670561790466} 08/31/2021 01:12:04 - INFO - __main__ - Step 66227: {'lr': 0.0003014968102470671, 'samples': 12715584, 'steps': 66226, 'loss/train': 1.8849705457687378} 08/31/2021 01:12:04 - INFO - __main__ - Step 66228: {'lr': 0.00030149161729596313, 'samples': 12715776, 'steps': 66227, 'loss/train': 1.7018564939498901} 08/31/2021 01:12:04 - INFO - __main__ - Step 66229: {'lr': 0.00030148642432165784, 'samples': 12715968, 'steps': 66228, 'loss/train': 1.3624086380004883} 08/31/2021 01:12:05 - INFO - __main__ - Step 66230: {'lr': 0.0003014812313241536, 'samples': 12716160, 'steps': 66229, 'loss/train': 0.45854854583740234} 08/31/2021 01:12:05 - INFO - __main__ - Step 66231: {'lr': 0.00030147603830345276, 'samples': 12716352, 'steps': 66230, 'loss/train': 0.3959277272224426} 08/31/2021 01:12:07 - INFO - __main__ - Step 66232: {'lr': 0.0003014708452595575, 'samples': 12716544, 'steps': 66231, 'loss/train': 0.31907063722610474} 08/31/2021 01:12:07 - INFO - __main__ - Step 66233: {'lr': 0.00030146565219247033, 'samples': 12716736, 'steps': 66232, 'loss/train': 1.4287464618682861} 08/31/2021 01:12:07 - INFO - __main__ - Step 66234: {'lr': 0.0003014604591021936, 'samples': 12716928, 'steps': 66233, 'loss/train': 1.765332579612732} 08/31/2021 01:12:08 - INFO - __main__ - Step 66235: {'lr': 0.0003014552659887294, 'samples': 12717120, 'steps': 66234, 'loss/train': 0.6637787222862244} 08/31/2021 01:12:08 - INFO - __main__ - Step 66236: {'lr': 0.00030145007285208036, 'samples': 12717312, 'steps': 66235, 'loss/train': 1.0399236679077148} 08/31/2021 01:12:10 - INFO - __main__ - Step 66237: {'lr': 0.0003014448796922488, 'samples': 12717504, 'steps': 66236, 'loss/train': 0.3696272075176239} 08/31/2021 01:12:10 - INFO - __main__ - Step 66238: {'lr': 0.0003014396865092368, 'samples': 12717696, 'steps': 66237, 'loss/train': 1.3608425855636597} 08/31/2021 01:12:11 - INFO - __main__ - Step 66239: {'lr': 0.00030143449330304696, 'samples': 12717888, 'steps': 66238, 'loss/train': 0.026029501110315323} 08/31/2021 01:12:11 - INFO - __main__ - Step 66240: {'lr': 0.00030142930007368154, 'samples': 12718080, 'steps': 66239, 'loss/train': 1.1622552871704102} 08/31/2021 01:12:12 - INFO - __main__ - Step 66241: {'lr': 0.0003014241068211428, 'samples': 12718272, 'steps': 66240, 'loss/train': 0.9132991433143616} 08/31/2021 01:12:12 - INFO - __main__ - Step 66242: {'lr': 0.0003014189135454332, 'samples': 12718464, 'steps': 66241, 'loss/train': 1.6550019979476929} 08/31/2021 01:12:13 - INFO - __main__ - Step 66243: {'lr': 0.000301413720246555, 'samples': 12718656, 'steps': 66242, 'loss/train': 1.2946698665618896} 08/31/2021 01:12:14 - INFO - __main__ - Step 66244: {'lr': 0.00030140852692451067, 'samples': 12718848, 'steps': 66243, 'loss/train': 1.7775214910507202} 08/31/2021 01:12:14 - INFO - __main__ - Step 66245: {'lr': 0.00030140333357930237, 'samples': 12719040, 'steps': 66244, 'loss/train': 0.9749186635017395} 08/31/2021 01:12:15 - INFO - __main__ - Step 66246: {'lr': 0.0003013981402109325, 'samples': 12719232, 'steps': 66245, 'loss/train': 1.2170358896255493} 08/31/2021 01:12:15 - INFO - __main__ - Step 66247: {'lr': 0.00030139294681940347, 'samples': 12719424, 'steps': 66246, 'loss/train': 1.309685468673706} 08/31/2021 01:12:16 - INFO - __main__ - Step 66248: {'lr': 0.00030138775340471754, 'samples': 12719616, 'steps': 66247, 'loss/train': 1.3572505712509155} 08/31/2021 01:12:17 - INFO - __main__ - Step 66249: {'lr': 0.00030138255996687706, 'samples': 12719808, 'steps': 66248, 'loss/train': 1.3516802787780762} 08/31/2021 01:12:17 - INFO - __main__ - Step 66250: {'lr': 0.0003013773665058844, 'samples': 12720000, 'steps': 66249, 'loss/train': 0.8233041763305664} 08/31/2021 01:12:18 - INFO - __main__ - Step 66251: {'lr': 0.000301372173021742, 'samples': 12720192, 'steps': 66250, 'loss/train': 0.8687008023262024} 08/31/2021 01:12:18 - INFO - __main__ - Step 66252: {'lr': 0.00030136697951445204, 'samples': 12720384, 'steps': 66251, 'loss/train': 0.7094151377677917} 08/31/2021 01:12:18 - INFO - __main__ - Step 66253: {'lr': 0.00030136178598401685, 'samples': 12720576, 'steps': 66252, 'loss/train': 1.8775416612625122} 08/31/2021 01:12:20 - INFO - __main__ - Step 66254: {'lr': 0.0003013565924304388, 'samples': 12720768, 'steps': 66253, 'loss/train': 1.5194509029388428} 08/31/2021 01:12:20 - INFO - __main__ - Step 66255: {'lr': 0.0003013513988537204, 'samples': 12720960, 'steps': 66254, 'loss/train': 1.2756584882736206} 08/31/2021 01:12:21 - INFO - __main__ - Step 66256: {'lr': 0.00030134620525386373, 'samples': 12721152, 'steps': 66255, 'loss/train': 0.5369020104408264} 08/31/2021 01:12:21 - INFO - __main__ - Step 66257: {'lr': 0.00030134101163087134, 'samples': 12721344, 'steps': 66256, 'loss/train': 1.1045364141464233} 08/31/2021 01:12:21 - INFO - __main__ - Step 66258: {'lr': 0.0003013358179847455, 'samples': 12721536, 'steps': 66257, 'loss/train': 0.08595399558544159} 08/31/2021 01:12:24 - INFO - __main__ - Step 66259: {'lr': 0.0003013306243154884, 'samples': 12721728, 'steps': 66258, 'loss/train': 1.2540596723556519} 08/31/2021 01:12:25 - INFO - __main__ - Step 66260: {'lr': 0.00030132543062310257, 'samples': 12721920, 'steps': 66259, 'loss/train': 1.3286588191986084} 08/31/2021 01:12:25 - INFO - __main__ - Step 66261: {'lr': 0.0003013202369075904, 'samples': 12722112, 'steps': 66260, 'loss/train': 1.2755935192108154} 08/31/2021 01:12:25 - INFO - __main__ - Step 66262: {'lr': 0.00030131504316895395, 'samples': 12722304, 'steps': 66261, 'loss/train': 1.2406541109085083} 08/31/2021 01:12:26 - INFO - __main__ - Step 66263: {'lr': 0.0003013098494071958, 'samples': 12722496, 'steps': 66262, 'loss/train': 4.247156143188477} 08/31/2021 01:12:26 - INFO - __main__ - Step 66264: {'lr': 0.0003013046556223183, 'samples': 12722688, 'steps': 66263, 'loss/train': 5.257234573364258} 08/31/2021 01:12:27 - INFO - __main__ - Step 66265: {'lr': 0.00030129946181432364, 'samples': 12722880, 'steps': 66264, 'loss/train': 0.31734055280685425} 08/31/2021 01:12:28 - INFO - __main__ - Step 66266: {'lr': 0.00030129426798321425, 'samples': 12723072, 'steps': 66265, 'loss/train': 0.6321618556976318} 08/31/2021 01:12:28 - INFO - __main__ - Step 66267: {'lr': 0.00030128907412899244, 'samples': 12723264, 'steps': 66266, 'loss/train': 1.2824673652648926} 08/31/2021 01:12:29 - INFO - __main__ - Step 66268: {'lr': 0.0003012838802516606, 'samples': 12723456, 'steps': 66267, 'loss/train': 0.26952728629112244} 08/31/2021 01:12:29 - INFO - __main__ - Step 66269: {'lr': 0.00030127868635122096, 'samples': 12723648, 'steps': 66268, 'loss/train': 1.4389690160751343} 08/31/2021 01:12:31 - INFO - __main__ - Step 66270: {'lr': 0.00030127349242767607, 'samples': 12723840, 'steps': 66269, 'loss/train': 0.9132270812988281} 08/31/2021 01:12:31 - INFO - __main__ - Step 66271: {'lr': 0.000301268298481028, 'samples': 12724032, 'steps': 66270, 'loss/train': 1.0380363464355469} 08/31/2021 01:12:31 - INFO - __main__ - Step 66272: {'lr': 0.0003012631045112793, 'samples': 12724224, 'steps': 66271, 'loss/train': 1.6378422975540161} 08/31/2021 01:12:32 - INFO - __main__ - Step 66273: {'lr': 0.0003012579105184322, 'samples': 12724416, 'steps': 66272, 'loss/train': 1.818402647972107} 08/31/2021 01:12:32 - INFO - __main__ - Step 66274: {'lr': 0.0003012527165024891, 'samples': 12724608, 'steps': 66273, 'loss/train': 1.466766595840454} 08/31/2021 01:12:33 - INFO - __main__ - Step 66275: {'lr': 0.0003012475224634523, 'samples': 12724800, 'steps': 66274, 'loss/train': 0.5925455689430237} 08/31/2021 01:12:34 - INFO - __main__ - Step 66276: {'lr': 0.0003012423284013242, 'samples': 12724992, 'steps': 66275, 'loss/train': 1.1414216756820679} 08/31/2021 01:12:34 - INFO - __main__ - Step 66277: {'lr': 0.00030123713431610705, 'samples': 12725184, 'steps': 66276, 'loss/train': 0.19354623556137085} 08/31/2021 01:12:35 - INFO - __main__ - Step 66278: {'lr': 0.00030123194020780327, 'samples': 12725376, 'steps': 66277, 'loss/train': 0.8708623647689819} 08/31/2021 01:12:35 - INFO - __main__ - Step 66279: {'lr': 0.00030122674607641514, 'samples': 12725568, 'steps': 66278, 'loss/train': 2.046186685562134} 08/31/2021 01:12:37 - INFO - __main__ - Step 66280: {'lr': 0.000301221551921945, 'samples': 12725760, 'steps': 66279, 'loss/train': 1.0461252927780151} 08/31/2021 01:12:37 - INFO - __main__ - Step 66281: {'lr': 0.00030121635774439534, 'samples': 12725952, 'steps': 66280, 'loss/train': 1.2001185417175293} 08/31/2021 01:12:37 - INFO - __main__ - Step 66282: {'lr': 0.0003012111635437683, 'samples': 12726144, 'steps': 66281, 'loss/train': 1.0659611225128174} 08/31/2021 01:12:38 - INFO - __main__ - Step 66283: {'lr': 0.0003012059693200663, 'samples': 12726336, 'steps': 66282, 'loss/train': 0.9292659759521484} 08/31/2021 01:12:38 - INFO - __main__ - Step 66284: {'lr': 0.00030120077507329163, 'samples': 12726528, 'steps': 66283, 'loss/train': 1.4151498079299927} 08/31/2021 01:12:38 - INFO - __main__ - Step 66285: {'lr': 0.0003011955808034467, 'samples': 12726720, 'steps': 66284, 'loss/train': 1.51018226146698} 08/31/2021 01:12:40 - INFO - __main__ - Step 66286: {'lr': 0.0003011903865105339, 'samples': 12726912, 'steps': 66285, 'loss/train': 1.294831395149231} 08/31/2021 01:12:40 - INFO - __main__ - Step 66287: {'lr': 0.0003011851921945555, 'samples': 12727104, 'steps': 66286, 'loss/train': 0.8981680870056152} 08/31/2021 01:12:41 - INFO - __main__ - Step 66288: {'lr': 0.00030117999785551376, 'samples': 12727296, 'steps': 66287, 'loss/train': 1.0411955118179321} 08/31/2021 01:12:41 - INFO - __main__ - Step 66289: {'lr': 0.00030117480349341116, 'samples': 12727488, 'steps': 66288, 'loss/train': 1.927188515663147} 08/31/2021 01:12:41 - INFO - __main__ - Step 66290: {'lr': 0.00030116960910824995, 'samples': 12727680, 'steps': 66289, 'loss/train': 1.3672033548355103} 08/31/2021 01:12:43 - INFO - __main__ - Step 66291: {'lr': 0.00030116441470003254, 'samples': 12727872, 'steps': 66290, 'loss/train': 3.0824713706970215} 08/31/2021 01:12:43 - INFO - __main__ - Step 66292: {'lr': 0.00030115922026876125, 'samples': 12728064, 'steps': 66291, 'loss/train': 1.3332139253616333} 08/31/2021 01:12:44 - INFO - __main__ - Step 66293: {'lr': 0.00030115402581443835, 'samples': 12728256, 'steps': 66292, 'loss/train': 1.5268608331680298} 08/31/2021 01:12:44 - INFO - __main__ - Step 66294: {'lr': 0.0003011488313370663, 'samples': 12728448, 'steps': 66293, 'loss/train': 1.631563663482666} 08/31/2021 01:12:44 - INFO - __main__ - Step 66295: {'lr': 0.0003011436368366473, 'samples': 12728640, 'steps': 66294, 'loss/train': 0.8398197889328003} 08/31/2021 01:12:46 - INFO - __main__ - Step 66296: {'lr': 0.00030113844231318375, 'samples': 12728832, 'steps': 66295, 'loss/train': 1.7733460664749146} 08/31/2021 01:12:46 - INFO - __main__ - Step 66297: {'lr': 0.00030113324776667803, 'samples': 12729024, 'steps': 66296, 'loss/train': 0.5823764801025391} 08/31/2021 01:12:47 - INFO - __main__ - Step 66298: {'lr': 0.0003011280531971326, 'samples': 12729216, 'steps': 66297, 'loss/train': 1.3295763731002808} 08/31/2021 01:12:47 - INFO - __main__ - Step 66299: {'lr': 0.0003011228586045495, 'samples': 12729408, 'steps': 66298, 'loss/train': 0.9957047700881958} 08/31/2021 01:12:47 - INFO - __main__ - Step 66300: {'lr': 0.00030111766398893127, 'samples': 12729600, 'steps': 66299, 'loss/train': 0.7222984433174133} 08/31/2021 01:12:49 - INFO - __main__ - Step 66301: {'lr': 0.0003011124693502802, 'samples': 12729792, 'steps': 66300, 'loss/train': 0.12251999974250793} 08/31/2021 01:12:50 - INFO - __main__ - Step 66302: {'lr': 0.00030110727468859864, 'samples': 12729984, 'steps': 66301, 'loss/train': 0.9677755832672119} 08/31/2021 01:12:50 - INFO - __main__ - Step 66303: {'lr': 0.00030110208000388896, 'samples': 12730176, 'steps': 66302, 'loss/train': 1.4186018705368042} 08/31/2021 01:12:50 - INFO - __main__ - Step 66304: {'lr': 0.0003010968852961535, 'samples': 12730368, 'steps': 66303, 'loss/train': 0.7743035554885864} 08/31/2021 01:12:51 - INFO - __main__ - Step 66305: {'lr': 0.0003010916905653945, 'samples': 12730560, 'steps': 66304, 'loss/train': 0.9439331889152527} 08/31/2021 01:12:52 - INFO - __main__ - Step 66306: {'lr': 0.0003010864958116144, 'samples': 12730752, 'steps': 66305, 'loss/train': 1.7499064207077026} 08/31/2021 01:12:52 - INFO - __main__ - Step 66307: {'lr': 0.00030108130103481554, 'samples': 12730944, 'steps': 66306, 'loss/train': 1.1106477975845337} 08/31/2021 01:12:53 - INFO - __main__ - Step 66308: {'lr': 0.00030107610623500013, 'samples': 12731136, 'steps': 66307, 'loss/train': 1.1482702493667603} 08/31/2021 01:12:53 - INFO - __main__ - Step 66309: {'lr': 0.0003010709114121707, 'samples': 12731328, 'steps': 66308, 'loss/train': 1.4943978786468506} 08/31/2021 01:12:54 - INFO - __main__ - Step 66310: {'lr': 0.0003010657165663295, 'samples': 12731520, 'steps': 66309, 'loss/train': 1.2082287073135376} 08/31/2021 01:12:56 - INFO - __main__ - Step 66311: {'lr': 0.00030106052169747886, 'samples': 12731712, 'steps': 66310, 'loss/train': 1.5045912265777588} 08/31/2021 01:12:56 - INFO - __main__ - Step 66312: {'lr': 0.0003010553268056212, 'samples': 12731904, 'steps': 66311, 'loss/train': 0.11629776656627655} 08/31/2021 01:12:57 - INFO - __main__ - Step 66313: {'lr': 0.0003010501318907587, 'samples': 12732096, 'steps': 66312, 'loss/train': 1.520919919013977} 08/31/2021 01:12:57 - INFO - __main__ - Step 66314: {'lr': 0.0003010449369528939, 'samples': 12732288, 'steps': 66313, 'loss/train': 1.091184139251709} 08/31/2021 01:12:57 - INFO - __main__ - Step 66315: {'lr': 0.0003010397419920289, 'samples': 12732480, 'steps': 66314, 'loss/train': 0.0632890835404396} 08/31/2021 01:12:59 - INFO - __main__ - Step 66316: {'lr': 0.0003010345470081663, 'samples': 12732672, 'steps': 66315, 'loss/train': 1.442683219909668} 08/31/2021 01:12:59 - INFO - __main__ - Step 66317: {'lr': 0.0003010293520013083, 'samples': 12732864, 'steps': 66316, 'loss/train': 1.253663182258606} 08/31/2021 01:13:00 - INFO - __main__ - Step 66318: {'lr': 0.00030102415697145726, 'samples': 12733056, 'steps': 66317, 'loss/train': 1.163952112197876} 08/31/2021 01:13:00 - INFO - __main__ - Step 66319: {'lr': 0.0003010189619186155, 'samples': 12733248, 'steps': 66318, 'loss/train': 1.7566289901733398} 08/31/2021 01:13:00 - INFO - __main__ - Step 66320: {'lr': 0.0003010137668427854, 'samples': 12733440, 'steps': 66319, 'loss/train': 0.7359146475791931} 08/31/2021 01:13:02 - INFO - __main__ - Step 66321: {'lr': 0.00030100857174396924, 'samples': 12733632, 'steps': 66320, 'loss/train': 2.0672214031219482} 08/31/2021 01:13:03 - INFO - __main__ - Step 66322: {'lr': 0.0003010033766221694, 'samples': 12733824, 'steps': 66321, 'loss/train': 1.104321837425232} 08/31/2021 01:13:03 - INFO - __main__ - Step 66323: {'lr': 0.00030099818147738826, 'samples': 12734016, 'steps': 66322, 'loss/train': 0.056265026330947876} 08/31/2021 01:13:03 - INFO - __main__ - Step 66324: {'lr': 0.00030099298630962813, 'samples': 12734208, 'steps': 66323, 'loss/train': 0.9365917444229126} 08/31/2021 01:13:04 - INFO - __main__ - Step 66325: {'lr': 0.0003009877911188914, 'samples': 12734400, 'steps': 66324, 'loss/train': 1.5493844747543335} 08/31/2021 01:13:04 - INFO - __main__ - Step 66326: {'lr': 0.0003009825959051803, 'samples': 12734592, 'steps': 66325, 'loss/train': 1.1687474250793457} 08/31/2021 01:13:06 - INFO - __main__ - Step 66327: {'lr': 0.0003009774006684972, 'samples': 12734784, 'steps': 66326, 'loss/train': 0.033782199025154114} 08/31/2021 01:13:06 - INFO - __main__ - Step 66328: {'lr': 0.0003009722054088445, 'samples': 12734976, 'steps': 66327, 'loss/train': 1.4734464883804321} 08/31/2021 01:13:06 - INFO - __main__ - Step 66329: {'lr': 0.00030096701012622453, 'samples': 12735168, 'steps': 66328, 'loss/train': 5.458911895751953} 08/31/2021 01:13:07 - INFO - __main__ - Step 66330: {'lr': 0.0003009618148206396, 'samples': 12735360, 'steps': 66329, 'loss/train': 1.430238962173462} 08/31/2021 01:13:07 - INFO - __main__ - Step 66331: {'lr': 0.0003009566194920921, 'samples': 12735552, 'steps': 66330, 'loss/train': 1.5601907968521118} 08/31/2021 01:13:07 - INFO - __main__ - Step 66332: {'lr': 0.0003009514241405843, 'samples': 12735744, 'steps': 66331, 'loss/train': 0.9773998260498047} 08/31/2021 01:13:09 - INFO - __main__ - Step 66333: {'lr': 0.00030094622876611853, 'samples': 12735936, 'steps': 66332, 'loss/train': 1.3806602954864502} 08/31/2021 01:13:09 - INFO - __main__ - Step 66334: {'lr': 0.00030094103336869723, 'samples': 12736128, 'steps': 66333, 'loss/train': 1.7981231212615967} 08/31/2021 01:13:10 - INFO - __main__ - Step 66335: {'lr': 0.0003009358379483227, 'samples': 12736320, 'steps': 66334, 'loss/train': 0.8696849346160889} 08/31/2021 01:13:10 - INFO - __main__ - Step 66336: {'lr': 0.0003009306425049972, 'samples': 12736512, 'steps': 66335, 'loss/train': 1.4209431409835815} 08/31/2021 01:13:10 - INFO - __main__ - Step 66337: {'lr': 0.00030092544703872316, 'samples': 12736704, 'steps': 66336, 'loss/train': 1.5103458166122437} 08/31/2021 01:13:12 - INFO - __main__ - Step 66338: {'lr': 0.000300920251549503, 'samples': 12736896, 'steps': 66337, 'loss/train': 0.9508179426193237} 08/31/2021 01:13:13 - INFO - __main__ - Step 66339: {'lr': 0.0003009150560373388, 'samples': 12737088, 'steps': 66338, 'loss/train': 1.3476523160934448} 08/31/2021 01:13:13 - INFO - __main__ - Step 66340: {'lr': 0.00030090986050223314, 'samples': 12737280, 'steps': 66339, 'loss/train': 1.2408537864685059} 08/31/2021 01:13:13 - INFO - __main__ - Step 66341: {'lr': 0.00030090466494418826, 'samples': 12737472, 'steps': 66340, 'loss/train': 1.3317121267318726} 08/31/2021 01:13:14 - INFO - __main__ - Step 66342: {'lr': 0.00030089946936320654, 'samples': 12737664, 'steps': 66341, 'loss/train': 1.1010162830352783} 08/31/2021 01:13:15 - INFO - __main__ - Step 66343: {'lr': 0.0003008942737592903, 'samples': 12737856, 'steps': 66342, 'loss/train': 1.260528326034546} 08/31/2021 01:13:16 - INFO - __main__ - Step 66344: {'lr': 0.0003008890781324419, 'samples': 12738048, 'steps': 66343, 'loss/train': 0.5980089902877808} 08/31/2021 01:13:16 - INFO - __main__ - Step 66345: {'lr': 0.00030088388248266366, 'samples': 12738240, 'steps': 66344, 'loss/train': 0.2205207496881485} 08/31/2021 01:13:17 - INFO - __main__ - Step 66346: {'lr': 0.00030087868680995795, 'samples': 12738432, 'steps': 66345, 'loss/train': 1.1083862781524658} 08/31/2021 01:13:17 - INFO - __main__ - Step 66347: {'lr': 0.00030087349111432705, 'samples': 12738624, 'steps': 66346, 'loss/train': 0.7370054125785828} 08/31/2021 01:13:18 - INFO - __main__ - Step 66348: {'lr': 0.00030086829539577336, 'samples': 12738816, 'steps': 66347, 'loss/train': 1.0241729021072388} 08/31/2021 01:13:19 - INFO - __main__ - Step 66349: {'lr': 0.0003008630996542992, 'samples': 12739008, 'steps': 66348, 'loss/train': 1.3216239213943481} 08/31/2021 01:13:19 - INFO - __main__ - Step 66350: {'lr': 0.0003008579038899069, 'samples': 12739200, 'steps': 66349, 'loss/train': 1.7386630773544312} 08/31/2021 01:13:19 - INFO - __main__ - Step 66351: {'lr': 0.0003008527081025988, 'samples': 12739392, 'steps': 66350, 'loss/train': 0.9527299404144287} 08/31/2021 01:13:20 - INFO - __main__ - Step 66352: {'lr': 0.00030084751229237733, 'samples': 12739584, 'steps': 66351, 'loss/train': 1.5144838094711304} 08/31/2021 01:13:22 - INFO - __main__ - Step 66353: {'lr': 0.0003008423164592447, 'samples': 12739776, 'steps': 66352, 'loss/train': 1.3079394102096558} 08/31/2021 01:13:23 - INFO - __main__ - Step 66354: {'lr': 0.0003008371206032033, 'samples': 12739968, 'steps': 66353, 'loss/train': 1.6426916122436523} 08/31/2021 01:13:23 - INFO - __main__ - Step 66355: {'lr': 0.00030083192472425544, 'samples': 12740160, 'steps': 66354, 'loss/train': 1.3522270917892456} 08/31/2021 01:13:23 - INFO - __main__ - Step 66356: {'lr': 0.0003008267288224036, 'samples': 12740352, 'steps': 66355, 'loss/train': 1.702168583869934} 08/31/2021 01:13:24 - INFO - __main__ - Step 66357: {'lr': 0.0003008215328976499, 'samples': 12740544, 'steps': 66356, 'loss/train': 0.6116412878036499} 08/31/2021 01:13:24 - INFO - __main__ - Step 66358: {'lr': 0.00030081633694999696, 'samples': 12740736, 'steps': 66357, 'loss/train': 0.4963441491127014} 08/31/2021 01:13:24 - INFO - __main__ - Step 66359: {'lr': 0.0003008111409794468, 'samples': 12740928, 'steps': 66358, 'loss/train': 1.3008747100830078} 08/31/2021 01:13:26 - INFO - __main__ - Step 66360: {'lr': 0.00030080594498600206, 'samples': 12741120, 'steps': 66359, 'loss/train': 0.052252598106861115} 08/31/2021 01:13:26 - INFO - __main__ - Step 66361: {'lr': 0.00030080074896966487, 'samples': 12741312, 'steps': 66360, 'loss/train': 1.2224633693695068} 08/31/2021 01:13:27 - INFO - __main__ - Step 66362: {'lr': 0.0003007955529304376, 'samples': 12741504, 'steps': 66361, 'loss/train': 1.153740406036377} 08/31/2021 01:13:27 - INFO - __main__ - Step 66363: {'lr': 0.00030079035686832276, 'samples': 12741696, 'steps': 66362, 'loss/train': 1.1917974948883057} 08/31/2021 01:13:27 - INFO - __main__ - Step 66364: {'lr': 0.00030078516078332245, 'samples': 12741888, 'steps': 66363, 'loss/train': 2.0509488582611084} 08/31/2021 01:13:29 - INFO - __main__ - Step 66365: {'lr': 0.00030077996467543924, 'samples': 12742080, 'steps': 66364, 'loss/train': 1.492065668106079} 08/31/2021 01:13:30 - INFO - __main__ - Step 66366: {'lr': 0.0003007747685446753, 'samples': 12742272, 'steps': 66365, 'loss/train': 1.7069917917251587} 08/31/2021 01:13:30 - INFO - __main__ - Step 66367: {'lr': 0.00030076957239103306, 'samples': 12742464, 'steps': 66366, 'loss/train': 1.138412594795227} 08/31/2021 01:13:31 - INFO - __main__ - Step 66368: {'lr': 0.00030076437621451475, 'samples': 12742656, 'steps': 66367, 'loss/train': 0.8459151983261108} 08/31/2021 01:13:31 - INFO - __main__ - Step 66369: {'lr': 0.00030075918001512287, 'samples': 12742848, 'steps': 66368, 'loss/train': 1.2081328630447388} 08/31/2021 01:13:33 - INFO - __main__ - Step 66370: {'lr': 0.0003007539837928597, 'samples': 12743040, 'steps': 66369, 'loss/train': 1.7632384300231934} 08/31/2021 01:13:33 - INFO - __main__ - Step 66371: {'lr': 0.0003007487875477275, 'samples': 12743232, 'steps': 66370, 'loss/train': 1.3297895193099976} 08/31/2021 01:13:33 - INFO - __main__ - Step 66372: {'lr': 0.00030074359127972876, 'samples': 12743424, 'steps': 66371, 'loss/train': 0.07648979127407074} 08/31/2021 01:13:34 - INFO - __main__ - Step 66373: {'lr': 0.00030073839498886566, 'samples': 12743616, 'steps': 66372, 'loss/train': 2.1366617679595947} 08/31/2021 01:13:34 - INFO - __main__ - Step 66374: {'lr': 0.0003007331986751407, 'samples': 12743808, 'steps': 66373, 'loss/train': 1.3016115427017212} 08/31/2021 01:13:36 - INFO - __main__ - Step 66375: {'lr': 0.00030072800233855605, 'samples': 12744000, 'steps': 66374, 'loss/train': 0.10701411217451096} 08/31/2021 01:13:36 - INFO - __main__ - Step 66376: {'lr': 0.00030072280597911424, 'samples': 12744192, 'steps': 66375, 'loss/train': 0.7687753438949585} 08/31/2021 01:13:37 - INFO - __main__ - Step 66377: {'lr': 0.0003007176095968175, 'samples': 12744384, 'steps': 66376, 'loss/train': 1.3770768642425537} 08/31/2021 01:13:37 - INFO - __main__ - Step 66378: {'lr': 0.0003007124131916682, 'samples': 12744576, 'steps': 66377, 'loss/train': 0.7176153063774109} 08/31/2021 01:13:38 - INFO - __main__ - Step 66379: {'lr': 0.0003007072167636686, 'samples': 12744768, 'steps': 66378, 'loss/train': 0.1115768626332283} 08/31/2021 01:13:38 - INFO - __main__ - Step 66380: {'lr': 0.0003007020203128211, 'samples': 12744960, 'steps': 66379, 'loss/train': 0.22591623663902283} 08/31/2021 01:13:39 - INFO - __main__ - Step 66381: {'lr': 0.0003006968238391281, 'samples': 12745152, 'steps': 66380, 'loss/train': 0.440812885761261} 08/31/2021 01:13:40 - INFO - __main__ - Step 66382: {'lr': 0.00030069162734259195, 'samples': 12745344, 'steps': 66381, 'loss/train': 1.0504668951034546} 08/31/2021 01:13:40 - INFO - __main__ - Step 66383: {'lr': 0.0003006864308232148, 'samples': 12745536, 'steps': 66382, 'loss/train': 1.0158405303955078} 08/31/2021 01:13:41 - INFO - __main__ - Step 66384: {'lr': 0.00030068123428099924, 'samples': 12745728, 'steps': 66383, 'loss/train': 1.0992988348007202} 08/31/2021 01:13:41 - INFO - __main__ - Step 66385: {'lr': 0.0003006760377159475, 'samples': 12745920, 'steps': 66384, 'loss/train': 1.5597180128097534} 08/31/2021 01:13:42 - INFO - __main__ - Step 66386: {'lr': 0.00030067084112806185, 'samples': 12746112, 'steps': 66385, 'loss/train': 1.645325779914856} 08/31/2021 01:13:43 - INFO - __main__ - Step 66387: {'lr': 0.00030066564451734475, 'samples': 12746304, 'steps': 66386, 'loss/train': 1.138221025466919} 08/31/2021 01:13:43 - INFO - __main__ - Step 66388: {'lr': 0.0003006604478837984, 'samples': 12746496, 'steps': 66387, 'loss/train': 1.979127049446106} 08/31/2021 01:13:44 - INFO - __main__ - Step 66389: {'lr': 0.00030065525122742535, 'samples': 12746688, 'steps': 66388, 'loss/train': 1.1483659744262695} 08/31/2021 01:13:44 - INFO - __main__ - Step 66390: {'lr': 0.0003006500545482278, 'samples': 12746880, 'steps': 66389, 'loss/train': 1.1244680881500244} 08/31/2021 01:13:45 - INFO - __main__ - Step 66391: {'lr': 0.0003006448578462081, 'samples': 12747072, 'steps': 66390, 'loss/train': 1.3565233945846558} 08/31/2021 01:13:46 - INFO - __main__ - Step 66392: {'lr': 0.00030063966112136865, 'samples': 12747264, 'steps': 66391, 'loss/train': 0.9013239145278931} 08/31/2021 01:13:46 - INFO - __main__ - Step 66393: {'lr': 0.00030063446437371167, 'samples': 12747456, 'steps': 66392, 'loss/train': 1.2719471454620361} 08/31/2021 01:13:47 - INFO - __main__ - Step 66394: {'lr': 0.0003006292676032396, 'samples': 12747648, 'steps': 66393, 'loss/train': 0.21903246641159058} 08/31/2021 01:13:47 - INFO - __main__ - Step 66395: {'lr': 0.0003006240708099548, 'samples': 12747840, 'steps': 66394, 'loss/train': 1.2614506483078003} 08/31/2021 01:13:49 - INFO - __main__ - Step 66396: {'lr': 0.00030061887399385954, 'samples': 12748032, 'steps': 66395, 'loss/train': 0.6843661665916443} 08/31/2021 01:13:49 - INFO - __main__ - Step 66397: {'lr': 0.00030061367715495627, 'samples': 12748224, 'steps': 66396, 'loss/train': 1.0805606842041016} 08/31/2021 01:13:49 - INFO - __main__ - Step 66398: {'lr': 0.0003006084802932472, 'samples': 12748416, 'steps': 66397, 'loss/train': 0.808167576789856} 08/31/2021 01:13:50 - INFO - __main__ - Step 66399: {'lr': 0.0003006032834087347, 'samples': 12748608, 'steps': 66398, 'loss/train': 1.531572937965393} 08/31/2021 01:13:50 - INFO - __main__ - Step 66400: {'lr': 0.00030059808650142116, 'samples': 12748800, 'steps': 66399, 'loss/train': 1.1363321542739868} 08/31/2021 01:13:52 - INFO - __main__ - Step 66401: {'lr': 0.00030059288957130895, 'samples': 12748992, 'steps': 66400, 'loss/train': 1.172533631324768} 08/31/2021 01:13:52 - INFO - __main__ - Step 66402: {'lr': 0.0003005876926184003, 'samples': 12749184, 'steps': 66401, 'loss/train': 1.2081408500671387} 08/31/2021 01:13:53 - INFO - __main__ - Step 66403: {'lr': 0.00030058249564269765, 'samples': 12749376, 'steps': 66402, 'loss/train': 1.131523847579956} 08/31/2021 01:13:53 - INFO - __main__ - Step 66404: {'lr': 0.0003005772986442033, 'samples': 12749568, 'steps': 66403, 'loss/train': 1.7191752195358276} 08/31/2021 01:13:53 - INFO - __main__ - Step 66405: {'lr': 0.00030057210162291964, 'samples': 12749760, 'steps': 66404, 'loss/train': 0.9269458651542664} 08/31/2021 01:13:54 - INFO - __main__ - Step 66406: {'lr': 0.00030056690457884894, 'samples': 12749952, 'steps': 66405, 'loss/train': 1.502486228942871} 08/31/2021 01:13:55 - INFO - __main__ - Step 66407: {'lr': 0.00030056170751199357, 'samples': 12750144, 'steps': 66406, 'loss/train': 0.05340186506509781} 08/31/2021 01:13:56 - INFO - __main__ - Step 66408: {'lr': 0.00030055651042235586, 'samples': 12750336, 'steps': 66407, 'loss/train': 0.9016268253326416} 08/31/2021 01:13:56 - INFO - __main__ - Step 66409: {'lr': 0.0003005513133099382, 'samples': 12750528, 'steps': 66408, 'loss/train': 1.4830379486083984} 08/31/2021 01:13:56 - INFO - __main__ - Step 66410: {'lr': 0.0003005461161747429, 'samples': 12750720, 'steps': 66409, 'loss/train': 1.613773226737976} 08/31/2021 01:13:57 - INFO - __main__ - Step 66411: {'lr': 0.00030054091901677226, 'samples': 12750912, 'steps': 66410, 'loss/train': 1.2237249612808228} 08/31/2021 01:13:58 - INFO - __main__ - Step 66412: {'lr': 0.00030053572183602866, 'samples': 12751104, 'steps': 66411, 'loss/train': 0.766167163848877} 08/31/2021 01:13:59 - INFO - __main__ - Step 66413: {'lr': 0.00030053052463251443, 'samples': 12751296, 'steps': 66412, 'loss/train': 1.5242937803268433} 08/31/2021 01:13:59 - INFO - __main__ - Step 66414: {'lr': 0.000300525327406232, 'samples': 12751488, 'steps': 66413, 'loss/train': 1.032677412033081} 08/31/2021 01:13:59 - INFO - __main__ - Step 66415: {'lr': 0.0003005201301571836, 'samples': 12751680, 'steps': 66414, 'loss/train': 0.0724327340722084} 08/31/2021 01:14:00 - INFO - __main__ - Step 66416: {'lr': 0.00030051493288537164, 'samples': 12751872, 'steps': 66415, 'loss/train': 1.108871579170227} 08/31/2021 01:14:01 - INFO - __main__ - Step 66417: {'lr': 0.0003005097355907984, 'samples': 12752064, 'steps': 66416, 'loss/train': 1.390562653541565} 08/31/2021 01:14:02 - INFO - __main__ - Step 66418: {'lr': 0.00030050453827346627, 'samples': 12752256, 'steps': 66417, 'loss/train': 1.338270664215088} 08/31/2021 01:14:02 - INFO - __main__ - Step 66419: {'lr': 0.0003004993409333775, 'samples': 12752448, 'steps': 66418, 'loss/train': 1.70110023021698} 08/31/2021 01:14:03 - INFO - __main__ - Step 66420: {'lr': 0.0003004941435705346, 'samples': 12752640, 'steps': 66419, 'loss/train': 0.620741605758667} 08/31/2021 01:14:03 - INFO - __main__ - Step 66421: {'lr': 0.00030048894618493977, 'samples': 12752832, 'steps': 66420, 'loss/train': 1.0229856967926025} 08/31/2021 01:14:05 - INFO - __main__ - Step 66422: {'lr': 0.0003004837487765954, 'samples': 12753024, 'steps': 66421, 'loss/train': 1.7186158895492554} 08/31/2021 01:14:05 - INFO - __main__ - Step 66423: {'lr': 0.00030047855134550383, 'samples': 12753216, 'steps': 66422, 'loss/train': 1.3650039434432983} 08/31/2021 01:14:06 - INFO - __main__ - Step 66424: {'lr': 0.00030047335389166743, 'samples': 12753408, 'steps': 66423, 'loss/train': 1.8444702625274658} 08/31/2021 01:14:06 - INFO - __main__ - Step 66425: {'lr': 0.00030046815641508853, 'samples': 12753600, 'steps': 66424, 'loss/train': 1.179566502571106} 08/31/2021 01:14:06 - INFO - __main__ - Step 66426: {'lr': 0.0003004629589157694, 'samples': 12753792, 'steps': 66425, 'loss/train': 1.2975965738296509} 08/31/2021 01:14:07 - INFO - __main__ - Step 66427: {'lr': 0.0003004577613937125, 'samples': 12753984, 'steps': 66426, 'loss/train': 0.5947790145874023} 08/31/2021 01:14:08 - INFO - __main__ - Step 66428: {'lr': 0.00030045256384892007, 'samples': 12754176, 'steps': 66427, 'loss/train': 1.4437586069107056} 08/31/2021 01:14:09 - INFO - __main__ - Step 66429: {'lr': 0.00030044736628139445, 'samples': 12754368, 'steps': 66428, 'loss/train': 0.9880276322364807} 08/31/2021 01:14:09 - INFO - __main__ - Step 66430: {'lr': 0.0003004421686911381, 'samples': 12754560, 'steps': 66429, 'loss/train': 1.1240370273590088} 08/31/2021 01:14:10 - INFO - __main__ - Step 66431: {'lr': 0.0003004369710781533, 'samples': 12754752, 'steps': 66430, 'loss/train': 1.432469367980957} 08/31/2021 01:14:10 - INFO - __main__ - Step 66432: {'lr': 0.00030043177344244235, 'samples': 12754944, 'steps': 66431, 'loss/train': 0.04439309239387512} 08/31/2021 01:14:12 - INFO - __main__ - Step 66433: {'lr': 0.0003004265757840076, 'samples': 12755136, 'steps': 66432, 'loss/train': 1.0174185037612915} 08/31/2021 01:14:12 - INFO - __main__ - Step 66434: {'lr': 0.0003004213781028514, 'samples': 12755328, 'steps': 66433, 'loss/train': 1.7597239017486572} 08/31/2021 01:14:13 - INFO - __main__ - Step 66435: {'lr': 0.00030041618039897616, 'samples': 12755520, 'steps': 66434, 'loss/train': 1.1137728691101074} 08/31/2021 01:14:13 - INFO - __main__ - Step 66436: {'lr': 0.0003004109826723841, 'samples': 12755712, 'steps': 66435, 'loss/train': 0.03229179233312607} 08/31/2021 01:14:13 - INFO - __main__ - Step 66437: {'lr': 0.00030040578492307766, 'samples': 12755904, 'steps': 66436, 'loss/train': 1.5945078134536743} 08/31/2021 01:14:14 - INFO - __main__ - Step 66438: {'lr': 0.00030040058715105915, 'samples': 12756096, 'steps': 66437, 'loss/train': 1.0081977844238281} 08/31/2021 01:14:15 - INFO - __main__ - Step 66439: {'lr': 0.000300395389356331, 'samples': 12756288, 'steps': 66438, 'loss/train': 1.0514984130859375} 08/31/2021 01:14:16 - INFO - __main__ - Step 66440: {'lr': 0.00030039019153889536, 'samples': 12756480, 'steps': 66439, 'loss/train': 1.070542335510254} 08/31/2021 01:14:16 - INFO - __main__ - Step 66441: {'lr': 0.00030038499369875474, 'samples': 12756672, 'steps': 66440, 'loss/train': 0.4992007911205292} 08/31/2021 01:14:17 - INFO - __main__ - Step 66442: {'lr': 0.00030037979583591136, 'samples': 12756864, 'steps': 66441, 'loss/train': 1.0400627851486206} 08/31/2021 01:14:17 - INFO - __main__ - Step 66443: {'lr': 0.0003003745979503676, 'samples': 12757056, 'steps': 66442, 'loss/train': 1.623121976852417} 08/31/2021 01:14:18 - INFO - __main__ - Step 66444: {'lr': 0.0003003694000421259, 'samples': 12757248, 'steps': 66443, 'loss/train': 0.03841857984662056} 08/31/2021 01:14:19 - INFO - __main__ - Step 66445: {'lr': 0.0003003642021111885, 'samples': 12757440, 'steps': 66444, 'loss/train': 0.8075260519981384} 08/31/2021 01:14:19 - INFO - __main__ - Step 66446: {'lr': 0.0003003590041575578, 'samples': 12757632, 'steps': 66445, 'loss/train': 0.8986574411392212} 08/31/2021 01:14:20 - INFO - __main__ - Step 66447: {'lr': 0.00030035380618123603, 'samples': 12757824, 'steps': 66446, 'loss/train': 1.8350696563720703} 08/31/2021 01:14:20 - INFO - __main__ - Step 66448: {'lr': 0.00030034860818222564, 'samples': 12758016, 'steps': 66447, 'loss/train': 0.7929929494857788} 08/31/2021 01:14:21 - INFO - __main__ - Step 66449: {'lr': 0.000300343410160529, 'samples': 12758208, 'steps': 66448, 'loss/train': 1.042650580406189} 08/31/2021 01:14:22 - INFO - __main__ - Step 66450: {'lr': 0.0003003382121161483, 'samples': 12758400, 'steps': 66449, 'loss/train': 1.3681522607803345} 08/31/2021 01:14:22 - INFO - __main__ - Step 66451: {'lr': 0.000300333014049086, 'samples': 12758592, 'steps': 66450, 'loss/train': 1.178039312362671} 08/31/2021 01:14:23 - INFO - __main__ - Step 66452: {'lr': 0.00030032781595934455, 'samples': 12758784, 'steps': 66451, 'loss/train': 1.398542881011963} 08/31/2021 01:14:23 - INFO - __main__ - Step 66453: {'lr': 0.0003003226178469261, 'samples': 12758976, 'steps': 66452, 'loss/train': 1.5518157482147217} 08/31/2021 01:14:24 - INFO - __main__ - Step 66454: {'lr': 0.000300317419711833, 'samples': 12759168, 'steps': 66453, 'loss/train': 0.9115895628929138} 08/31/2021 01:14:25 - INFO - __main__ - Step 66455: {'lr': 0.00030031222155406763, 'samples': 12759360, 'steps': 66454, 'loss/train': 0.6560949683189392} 08/31/2021 01:14:25 - INFO - __main__ - Step 66456: {'lr': 0.0003003070233736324, 'samples': 12759552, 'steps': 66455, 'loss/train': 1.2272297143936157} 08/31/2021 01:14:26 - INFO - __main__ - Step 66457: {'lr': 0.00030030182517052956, 'samples': 12759744, 'steps': 66456, 'loss/train': 1.4391615390777588} 08/31/2021 01:14:26 - INFO - __main__ - Step 66458: {'lr': 0.0003002966269447615, 'samples': 12759936, 'steps': 66457, 'loss/train': 1.644375205039978} 08/31/2021 01:14:27 - INFO - __main__ - Step 66459: {'lr': 0.00030029142869633066, 'samples': 12760128, 'steps': 66458, 'loss/train': 1.7592140436172485} 08/31/2021 01:14:28 - INFO - __main__ - Step 66460: {'lr': 0.0003002862304252392, 'samples': 12760320, 'steps': 66459, 'loss/train': 1.3071209192276} 08/31/2021 01:14:28 - INFO - __main__ - Step 66461: {'lr': 0.0003002810321314895, 'samples': 12760512, 'steps': 66460, 'loss/train': 1.5338735580444336} 08/31/2021 01:14:29 - INFO - __main__ - Step 66462: {'lr': 0.00030027583381508395, 'samples': 12760704, 'steps': 66461, 'loss/train': 0.7121207118034363} 08/31/2021 01:14:29 - INFO - __main__ - Step 66463: {'lr': 0.0003002706354760249, 'samples': 12760896, 'steps': 66462, 'loss/train': 0.9216613173484802} 08/31/2021 01:14:29 - INFO - __main__ - Step 66464: {'lr': 0.0003002654371143147, 'samples': 12761088, 'steps': 66463, 'loss/train': 1.3124037981033325} 08/31/2021 01:14:31 - INFO - __main__ - Step 66465: {'lr': 0.0003002602387299557, 'samples': 12761280, 'steps': 66464, 'loss/train': 1.0798547267913818} 08/31/2021 01:14:32 - INFO - __main__ - Step 66466: {'lr': 0.00030025504032295014, 'samples': 12761472, 'steps': 66465, 'loss/train': 1.581080436706543} 08/31/2021 01:14:32 - INFO - __main__ - Step 66467: {'lr': 0.0003002498418933005, 'samples': 12761664, 'steps': 66466, 'loss/train': 1.3403946161270142} 08/31/2021 01:14:32 - INFO - __main__ - Step 66468: {'lr': 0.000300244643441009, 'samples': 12761856, 'steps': 66467, 'loss/train': 0.2268802672624588} 08/31/2021 01:14:33 - INFO - __main__ - Step 66469: {'lr': 0.0003002394449660781, 'samples': 12762048, 'steps': 66468, 'loss/train': 1.0203367471694946} 08/31/2021 01:14:33 - INFO - __main__ - Step 66470: {'lr': 0.00030023424646851, 'samples': 12762240, 'steps': 66469, 'loss/train': 0.05781470239162445} 08/31/2021 01:14:35 - INFO - __main__ - Step 66471: {'lr': 0.00030022904794830716, 'samples': 12762432, 'steps': 66470, 'loss/train': 1.112509846687317} 08/31/2021 01:14:35 - INFO - __main__ - Step 66472: {'lr': 0.00030022384940547186, 'samples': 12762624, 'steps': 66471, 'loss/train': 1.4240211248397827} 08/31/2021 01:14:35 - INFO - __main__ - Step 66473: {'lr': 0.0003002186508400066, 'samples': 12762816, 'steps': 66472, 'loss/train': 1.2957916259765625} 08/31/2021 01:14:36 - INFO - __main__ - Step 66474: {'lr': 0.0003002134522519135, 'samples': 12763008, 'steps': 66473, 'loss/train': 1.8551292419433594} 08/31/2021 01:14:36 - INFO - __main__ - Step 66475: {'lr': 0.00030020825364119496, 'samples': 12763200, 'steps': 66474, 'loss/train': 1.345435619354248} 08/31/2021 01:14:38 - INFO - __main__ - Step 66476: {'lr': 0.0003002030550078534, 'samples': 12763392, 'steps': 66475, 'loss/train': 1.0607115030288696} 08/31/2021 01:14:39 - INFO - __main__ - Step 66477: {'lr': 0.0003001978563518911, 'samples': 12763584, 'steps': 66476, 'loss/train': 1.4347478151321411} 08/31/2021 01:14:39 - INFO - __main__ - Step 66478: {'lr': 0.0003001926576733104, 'samples': 12763776, 'steps': 66477, 'loss/train': 1.4001829624176025} 08/31/2021 01:14:40 - INFO - __main__ - Step 66479: {'lr': 0.00030018745897211367, 'samples': 12763968, 'steps': 66478, 'loss/train': 1.2926408052444458} 08/31/2021 01:14:40 - INFO - __main__ - Step 66480: {'lr': 0.0003001822602483033, 'samples': 12764160, 'steps': 66479, 'loss/train': 1.7003318071365356} 08/31/2021 01:14:40 - INFO - __main__ - Step 66481: {'lr': 0.0003001770615018815, 'samples': 12764352, 'steps': 66480, 'loss/train': 1.7341364622116089} 08/31/2021 01:14:42 - INFO - __main__ - Step 66482: {'lr': 0.0003001718627328507, 'samples': 12764544, 'steps': 66481, 'loss/train': 1.4408880472183228} 08/31/2021 01:14:43 - INFO - __main__ - Step 66483: {'lr': 0.0003001666639412133, 'samples': 12764736, 'steps': 66482, 'loss/train': 1.238145351409912} 08/31/2021 01:14:43 - INFO - __main__ - Step 66484: {'lr': 0.0003001614651269715, 'samples': 12764928, 'steps': 66483, 'loss/train': 1.557083249092102} 08/31/2021 01:14:43 - INFO - __main__ - Step 66485: {'lr': 0.00030015626629012774, 'samples': 12765120, 'steps': 66484, 'loss/train': 1.4320902824401855} 08/31/2021 01:14:44 - INFO - __main__ - Step 66486: {'lr': 0.00030015106743068443, 'samples': 12765312, 'steps': 66485, 'loss/train': 0.30935078859329224} 08/31/2021 01:14:45 - INFO - __main__ - Step 66487: {'lr': 0.00030014586854864374, 'samples': 12765504, 'steps': 66486, 'loss/train': 1.1121342182159424} 08/31/2021 01:14:46 - INFO - __main__ - Step 66488: {'lr': 0.0003001406696440081, 'samples': 12765696, 'steps': 66487, 'loss/train': 1.6348049640655518} 08/31/2021 01:14:46 - INFO - __main__ - Step 66489: {'lr': 0.00030013547071677983, 'samples': 12765888, 'steps': 66488, 'loss/train': 1.1826287508010864} 08/31/2021 01:14:46 - INFO - __main__ - Step 66490: {'lr': 0.0003001302717669613, 'samples': 12766080, 'steps': 66489, 'loss/train': 1.0245252847671509} 08/31/2021 01:14:47 - INFO - __main__ - Step 66491: {'lr': 0.0003001250727945549, 'samples': 12766272, 'steps': 66490, 'loss/train': 1.499831199645996} 08/31/2021 01:14:48 - INFO - __main__ - Step 66492: {'lr': 0.0003001198737995628, 'samples': 12766464, 'steps': 66491, 'loss/train': 0.6957758665084839} 08/31/2021 01:14:49 - INFO - __main__ - Step 66493: {'lr': 0.00030011467478198764, 'samples': 12766656, 'steps': 66492, 'loss/train': 1.4842870235443115} 08/31/2021 01:14:49 - INFO - __main__ - Step 66494: {'lr': 0.00030010947574183146, 'samples': 12766848, 'steps': 66493, 'loss/train': 0.6068068146705627} 08/31/2021 01:14:49 - INFO - __main__ - Step 66495: {'lr': 0.00030010427667909666, 'samples': 12767040, 'steps': 66494, 'loss/train': 1.2824535369873047} 08/31/2021 01:14:50 - INFO - __main__ - Step 66496: {'lr': 0.00030009907759378574, 'samples': 12767232, 'steps': 66495, 'loss/train': 1.1934356689453125} 08/31/2021 01:14:50 - INFO - __main__ - Step 66497: {'lr': 0.0003000938784859009, 'samples': 12767424, 'steps': 66496, 'loss/train': 0.6017325520515442} 08/31/2021 01:14:52 - INFO - __main__ - Step 66498: {'lr': 0.00030008867935544457, 'samples': 12767616, 'steps': 66497, 'loss/train': 0.956586480140686} 08/31/2021 01:14:52 - INFO - __main__ - Step 66499: {'lr': 0.0003000834802024191, 'samples': 12767808, 'steps': 66498, 'loss/train': 1.347489833831787} 08/31/2021 01:14:53 - INFO - __main__ - Step 66500: {'lr': 0.0003000782810268267, 'samples': 12768000, 'steps': 66499, 'loss/train': 1.2194404602050781} 08/31/2021 01:14:53 - INFO - __main__ - Step 66501: {'lr': 0.0003000730818286698, 'samples': 12768192, 'steps': 66500, 'loss/train': 1.1891096830368042} 08/31/2021 01:14:53 - INFO - __main__ - Step 66502: {'lr': 0.0003000678826079508, 'samples': 12768384, 'steps': 66501, 'loss/train': 1.6522839069366455} 08/31/2021 01:14:55 - INFO - __main__ - Step 66503: {'lr': 0.00030006268336467195, 'samples': 12768576, 'steps': 66502, 'loss/train': 1.3624308109283447} 08/31/2021 01:14:55 - INFO - __main__ - Step 66504: {'lr': 0.0003000574840988357, 'samples': 12768768, 'steps': 66503, 'loss/train': 1.5744835138320923} 08/31/2021 01:14:56 - INFO - __main__ - Step 66505: {'lr': 0.00030005228481044414, 'samples': 12768960, 'steps': 66504, 'loss/train': 1.826978325843811} 08/31/2021 01:14:56 - INFO - __main__ - Step 66506: {'lr': 0.0003000470854995, 'samples': 12769152, 'steps': 66505, 'loss/train': 1.2708399295806885} 08/31/2021 01:14:56 - INFO - __main__ - Step 66507: {'lr': 0.0003000418861660053, 'samples': 12769344, 'steps': 66506, 'loss/train': 1.4890323877334595} 08/31/2021 01:14:58 - INFO - __main__ - Step 66508: {'lr': 0.0003000366868099625, 'samples': 12769536, 'steps': 66507, 'loss/train': 1.0406877994537354} 08/31/2021 01:14:58 - INFO - __main__ - Step 66509: {'lr': 0.000300031487431374, 'samples': 12769728, 'steps': 66508, 'loss/train': 1.5714147090911865} 08/31/2021 01:14:59 - INFO - __main__ - Step 66510: {'lr': 0.000300026288030242, 'samples': 12769920, 'steps': 66509, 'loss/train': 0.9017835259437561} 08/31/2021 01:14:59 - INFO - __main__ - Step 66511: {'lr': 0.00030002108860656895, 'samples': 12770112, 'steps': 66510, 'loss/train': 0.754727840423584} 08/31/2021 01:14:59 - INFO - __main__ - Step 66512: {'lr': 0.0003000158891603572, 'samples': 12770304, 'steps': 66511, 'loss/train': 1.0507131814956665} 08/31/2021 01:15:01 - INFO - __main__ - Step 66513: {'lr': 0.00030001068969160913, 'samples': 12770496, 'steps': 66512, 'loss/train': 1.152030110359192} 08/31/2021 01:15:01 - INFO - __main__ - Step 66514: {'lr': 0.0003000054902003269, 'samples': 12770688, 'steps': 66513, 'loss/train': 1.0442732572555542} 08/31/2021 01:15:02 - INFO - __main__ - Step 66515: {'lr': 0.00030000029068651303, 'samples': 12770880, 'steps': 66514, 'loss/train': 1.5815967321395874} 08/31/2021 01:15:02 - INFO - __main__ - Step 66516: {'lr': 0.00029999509115016977, 'samples': 12771072, 'steps': 66515, 'loss/train': 0.6941567063331604} 08/31/2021 01:15:02 - INFO - __main__ - Step 66517: {'lr': 0.00029998989159129945, 'samples': 12771264, 'steps': 66516, 'loss/train': 0.6340495944023132} 08/31/2021 01:15:03 - INFO - __main__ - Step 66518: {'lr': 0.0002999846920099045, 'samples': 12771456, 'steps': 66517, 'loss/train': 1.2154134511947632} 08/31/2021 01:15:04 - INFO - __main__ - Step 66519: {'lr': 0.0002999794924059872, 'samples': 12771648, 'steps': 66518, 'loss/train': 0.9845523238182068} 08/31/2021 01:15:05 - INFO - __main__ - Step 66520: {'lr': 0.00029997429277955, 'samples': 12771840, 'steps': 66519, 'loss/train': 1.0266910791397095} 08/31/2021 01:15:05 - INFO - __main__ - Step 66521: {'lr': 0.0002999690931305951, 'samples': 12772032, 'steps': 66520, 'loss/train': 1.6924242973327637} 08/31/2021 01:15:06 - INFO - __main__ - Step 66522: {'lr': 0.00029996389345912487, 'samples': 12772224, 'steps': 66521, 'loss/train': 0.5261301398277283} 08/31/2021 01:15:06 - INFO - __main__ - Step 66523: {'lr': 0.0002999586937651417, 'samples': 12772416, 'steps': 66522, 'loss/train': 1.4776389598846436} 08/31/2021 01:15:08 - INFO - __main__ - Step 66524: {'lr': 0.0002999534940486479, 'samples': 12772608, 'steps': 66523, 'loss/train': 2.38578462600708} 08/31/2021 01:15:08 - INFO - __main__ - Step 66525: {'lr': 0.00029994829430964585, 'samples': 12772800, 'steps': 66524, 'loss/train': 1.542242169380188} 08/31/2021 01:15:08 - INFO - __main__ - Step 66526: {'lr': 0.00029994309454813787, 'samples': 12772992, 'steps': 66525, 'loss/train': 2.9587457180023193} 08/31/2021 01:15:09 - INFO - __main__ - Step 66527: {'lr': 0.0002999378947641263, 'samples': 12773184, 'steps': 66526, 'loss/train': 1.1152361631393433} 08/31/2021 01:15:09 - INFO - __main__ - Step 66528: {'lr': 0.00029993269495761347, 'samples': 12773376, 'steps': 66527, 'loss/train': 1.6514194011688232} 08/31/2021 01:15:11 - INFO - __main__ - Step 66529: {'lr': 0.0002999274951286017, 'samples': 12773568, 'steps': 66528, 'loss/train': 1.2198529243469238} 08/31/2021 01:15:11 - INFO - __main__ - Step 66530: {'lr': 0.00029992229527709346, 'samples': 12773760, 'steps': 66529, 'loss/train': 1.1510934829711914} 08/31/2021 01:15:12 - INFO - __main__ - Step 66531: {'lr': 0.000299917095403091, 'samples': 12773952, 'steps': 66530, 'loss/train': 1.2177245616912842} 08/31/2021 01:15:12 - INFO - __main__ - Step 66532: {'lr': 0.0002999118955065966, 'samples': 12774144, 'steps': 66531, 'loss/train': 0.6474673748016357} 08/31/2021 01:15:12 - INFO - __main__ - Step 66533: {'lr': 0.00029990669558761275, 'samples': 12774336, 'steps': 66532, 'loss/train': 1.2041007280349731} 08/31/2021 01:15:13 - INFO - __main__ - Step 66534: {'lr': 0.00029990149564614163, 'samples': 12774528, 'steps': 66533, 'loss/train': 0.5882863998413086} 08/31/2021 01:15:15 - INFO - __main__ - Step 66535: {'lr': 0.0002998962956821857, 'samples': 12774720, 'steps': 66534, 'loss/train': 0.3385232090950012} 08/31/2021 01:15:15 - INFO - __main__ - Step 66536: {'lr': 0.0002998910956957472, 'samples': 12774912, 'steps': 66535, 'loss/train': 1.7201387882232666} 08/31/2021 01:15:16 - INFO - __main__ - Step 66537: {'lr': 0.0002998858956868287, 'samples': 12775104, 'steps': 66536, 'loss/train': 1.1489557027816772} 08/31/2021 01:15:16 - INFO - __main__ - Step 66538: {'lr': 0.0002998806956554322, 'samples': 12775296, 'steps': 66537, 'loss/train': 0.6216567754745483} 08/31/2021 01:15:16 - INFO - __main__ - Step 66539: {'lr': 0.0002998754956015604, 'samples': 12775488, 'steps': 66538, 'loss/train': 1.537582516670227} 08/31/2021 01:15:18 - INFO - __main__ - Step 66540: {'lr': 0.0002998702955252154, 'samples': 12775680, 'steps': 66539, 'loss/train': 1.322252869606018} 08/31/2021 01:15:18 - INFO - __main__ - Step 66541: {'lr': 0.00029986509542639955, 'samples': 12775872, 'steps': 66540, 'loss/train': 1.0358753204345703} 08/31/2021 01:15:19 - INFO - __main__ - Step 66542: {'lr': 0.00029985989530511534, 'samples': 12776064, 'steps': 66541, 'loss/train': 1.3270435333251953} 08/31/2021 01:15:19 - INFO - __main__ - Step 66543: {'lr': 0.000299854695161365, 'samples': 12776256, 'steps': 66542, 'loss/train': 0.992167592048645} 08/31/2021 01:15:19 - INFO - __main__ - Step 66544: {'lr': 0.00029984949499515097, 'samples': 12776448, 'steps': 66543, 'loss/train': 1.438037395477295} 08/31/2021 01:15:21 - INFO - __main__ - Step 66545: {'lr': 0.00029984429480647547, 'samples': 12776640, 'steps': 66544, 'loss/train': 0.9986074566841125} 08/31/2021 01:15:21 - INFO - __main__ - Step 66546: {'lr': 0.0002998390945953409, 'samples': 12776832, 'steps': 66545, 'loss/train': 1.5698997974395752} 08/31/2021 01:15:22 - INFO - __main__ - Step 66547: {'lr': 0.0002998338943617496, 'samples': 12777024, 'steps': 66546, 'loss/train': 1.8473981618881226} 08/31/2021 01:15:22 - INFO - __main__ - Step 66548: {'lr': 0.0002998286941057038, 'samples': 12777216, 'steps': 66547, 'loss/train': 1.2348382472991943} 08/31/2021 01:15:22 - INFO - __main__ - Step 66549: {'lr': 0.00029982349382720613, 'samples': 12777408, 'steps': 66548, 'loss/train': 1.0449459552764893} 08/31/2021 01:15:24 - INFO - __main__ - Step 66550: {'lr': 0.00029981829352625873, 'samples': 12777600, 'steps': 66549, 'loss/train': 1.1977999210357666} 08/31/2021 01:15:24 - INFO - __main__ - Step 66551: {'lr': 0.000299813093202864, 'samples': 12777792, 'steps': 66550, 'loss/train': 0.7934580445289612} 08/31/2021 01:15:25 - INFO - __main__ - Step 66552: {'lr': 0.0002998078928570241, 'samples': 12777984, 'steps': 66551, 'loss/train': 1.2448347806930542} 08/31/2021 01:15:25 - INFO - __main__ - Step 66553: {'lr': 0.0002998026924887417, 'samples': 12778176, 'steps': 66552, 'loss/train': 1.4912844896316528} 08/31/2021 01:15:25 - INFO - __main__ - Step 66554: {'lr': 0.00029979749209801894, 'samples': 12778368, 'steps': 66553, 'loss/train': 1.3719546794891357} 08/31/2021 01:15:27 - INFO - __main__ - Step 66555: {'lr': 0.00029979229168485824, 'samples': 12778560, 'steps': 66554, 'loss/train': 0.3432719111442566} 08/31/2021 01:15:28 - INFO - __main__ - Step 66556: {'lr': 0.00029978709124926176, 'samples': 12778752, 'steps': 66555, 'loss/train': 1.1924985647201538} 08/31/2021 01:15:28 - INFO - __main__ - Step 66557: {'lr': 0.00029978189079123206, 'samples': 12778944, 'steps': 66556, 'loss/train': 1.7947378158569336} 08/31/2021 01:15:28 - INFO - __main__ - Step 66558: {'lr': 0.0002997766903107714, 'samples': 12779136, 'steps': 66557, 'loss/train': 1.0313650369644165} 08/31/2021 01:15:29 - INFO - __main__ - Step 66559: {'lr': 0.00029977148980788213, 'samples': 12779328, 'steps': 66558, 'loss/train': 1.044758915901184} 08/31/2021 01:15:29 - INFO - __main__ - Step 66560: {'lr': 0.0002997662892825666, 'samples': 12779520, 'steps': 66559, 'loss/train': 1.476853370666504} 08/31/2021 01:15:31 - INFO - __main__ - Step 66561: {'lr': 0.0002997610887348272, 'samples': 12779712, 'steps': 66560, 'loss/train': 0.7958889007568359} 08/31/2021 01:15:31 - INFO - __main__ - Step 66562: {'lr': 0.0002997558881646662, 'samples': 12779904, 'steps': 66561, 'loss/train': 1.150795578956604} 08/31/2021 01:15:31 - INFO - __main__ - Step 66563: {'lr': 0.00029975068757208596, 'samples': 12780096, 'steps': 66562, 'loss/train': 1.3932702541351318} 08/31/2021 01:15:32 - INFO - __main__ - Step 66564: {'lr': 0.00029974548695708877, 'samples': 12780288, 'steps': 66563, 'loss/train': 0.9868043065071106} 08/31/2021 01:15:32 - INFO - __main__ - Step 66565: {'lr': 0.0002997402863196771, 'samples': 12780480, 'steps': 66564, 'loss/train': 0.7184203267097473} 08/31/2021 01:15:34 - INFO - __main__ - Step 66566: {'lr': 0.00029973508565985316, 'samples': 12780672, 'steps': 66565, 'loss/train': 1.6391639709472656} 08/31/2021 01:15:34 - INFO - __main__ - Step 66567: {'lr': 0.00029972988497761944, 'samples': 12780864, 'steps': 66566, 'loss/train': 1.4871892929077148} 08/31/2021 01:15:34 - INFO - __main__ - Step 66568: {'lr': 0.00029972468427297814, 'samples': 12781056, 'steps': 66567, 'loss/train': 1.3746296167373657} 08/31/2021 01:15:35 - INFO - __main__ - Step 66569: {'lr': 0.0002997194835459317, 'samples': 12781248, 'steps': 66568, 'loss/train': 1.494836688041687} 08/31/2021 01:15:35 - INFO - __main__ - Step 66570: {'lr': 0.0002997142827964824, 'samples': 12781440, 'steps': 66569, 'loss/train': 1.2491081953048706} 08/31/2021 01:15:37 - INFO - __main__ - Step 66571: {'lr': 0.0002997090820246326, 'samples': 12781632, 'steps': 66570, 'loss/train': 1.1714414358139038} 08/31/2021 01:15:37 - INFO - __main__ - Step 66572: {'lr': 0.0002997038812303847, 'samples': 12781824, 'steps': 66571, 'loss/train': 1.418691873550415} 08/31/2021 01:15:37 - INFO - __main__ - Step 66573: {'lr': 0.00029969868041374096, 'samples': 12782016, 'steps': 66572, 'loss/train': 1.0282680988311768} 08/31/2021 01:15:38 - INFO - __main__ - Step 66574: {'lr': 0.00029969347957470375, 'samples': 12782208, 'steps': 66573, 'loss/train': 5.80886173248291} 08/31/2021 01:15:38 - INFO - __main__ - Step 66575: {'lr': 0.0002996882787132755, 'samples': 12782400, 'steps': 66574, 'loss/train': 1.4069651365280151} 08/31/2021 01:15:39 - INFO - __main__ - Step 66576: {'lr': 0.00029968307782945834, 'samples': 12782592, 'steps': 66575, 'loss/train': 1.8397490978240967} 08/31/2021 01:15:40 - INFO - __main__ - Step 66577: {'lr': 0.00029967787692325486, 'samples': 12782784, 'steps': 66576, 'loss/train': 1.7873835563659668} 08/31/2021 01:15:41 - INFO - __main__ - Step 66578: {'lr': 0.0002996726759946673, 'samples': 12782976, 'steps': 66577, 'loss/train': 1.253786325454712} 08/31/2021 01:15:41 - INFO - __main__ - Step 66579: {'lr': 0.00029966747504369794, 'samples': 12783168, 'steps': 66578, 'loss/train': 1.3769854307174683} 08/31/2021 01:15:41 - INFO - __main__ - Step 66580: {'lr': 0.0002996622740703492, 'samples': 12783360, 'steps': 66579, 'loss/train': 0.5426275730133057} 08/31/2021 01:15:42 - INFO - __main__ - Step 66581: {'lr': 0.0002996570730746235, 'samples': 12783552, 'steps': 66580, 'loss/train': 1.6425106525421143} 08/31/2021 01:15:43 - INFO - __main__ - Step 66582: {'lr': 0.000299651872056523, 'samples': 12783744, 'steps': 66581, 'loss/train': 0.9070307016372681} 08/31/2021 01:15:44 - INFO - __main__ - Step 66583: {'lr': 0.0002996466710160501, 'samples': 12783936, 'steps': 66582, 'loss/train': 1.3906959295272827} 08/31/2021 01:15:44 - INFO - __main__ - Step 66584: {'lr': 0.0002996414699532072, 'samples': 12784128, 'steps': 66583, 'loss/train': 1.7404391765594482} 08/31/2021 01:15:44 - INFO - __main__ - Step 66585: {'lr': 0.00029963626886799665, 'samples': 12784320, 'steps': 66584, 'loss/train': 1.3556116819381714} 08/31/2021 01:15:45 - INFO - __main__ - Step 66586: {'lr': 0.0002996310677604208, 'samples': 12784512, 'steps': 66585, 'loss/train': 1.1038249731063843} 08/31/2021 01:15:47 - INFO - __main__ - Step 66587: {'lr': 0.00029962586663048193, 'samples': 12784704, 'steps': 66586, 'loss/train': 1.4168556928634644} 08/31/2021 01:15:47 - INFO - __main__ - Step 66588: {'lr': 0.00029962066547818233, 'samples': 12784896, 'steps': 66587, 'loss/train': 1.4734995365142822} 08/31/2021 01:15:48 - INFO - __main__ - Step 66589: {'lr': 0.0002996154643035245, 'samples': 12785088, 'steps': 66588, 'loss/train': 1.449047565460205} 08/31/2021 01:15:48 - INFO - __main__ - Step 66590: {'lr': 0.00029961026310651066, 'samples': 12785280, 'steps': 66589, 'loss/train': 1.6542316675186157} 08/31/2021 01:15:48 - INFO - __main__ - Step 66591: {'lr': 0.0002996050618871432, 'samples': 12785472, 'steps': 66590, 'loss/train': 1.1786723136901855} 08/31/2021 01:15:50 - INFO - __main__ - Step 66592: {'lr': 0.0002995998606454245, 'samples': 12785664, 'steps': 66591, 'loss/train': 1.7711762189865112} 08/31/2021 01:15:51 - INFO - __main__ - Step 66593: {'lr': 0.0002995946593813569, 'samples': 12785856, 'steps': 66592, 'loss/train': 0.5556048154830933} 08/31/2021 01:15:51 - INFO - __main__ - Step 66594: {'lr': 0.0002995894580949427, 'samples': 12786048, 'steps': 66593, 'loss/train': 0.21622800827026367} 08/31/2021 01:15:51 - INFO - __main__ - Step 66595: {'lr': 0.0002995842567861842, 'samples': 12786240, 'steps': 66594, 'loss/train': 1.3063949346542358} 08/31/2021 01:15:52 - INFO - __main__ - Step 66596: {'lr': 0.00029957905545508384, 'samples': 12786432, 'steps': 66595, 'loss/train': 1.0697543621063232} 08/31/2021 01:15:52 - INFO - __main__ - Step 66597: {'lr': 0.0002995738541016439, 'samples': 12786624, 'steps': 66596, 'loss/train': 0.02375691942870617} 08/31/2021 01:15:53 - INFO - __main__ - Step 66598: {'lr': 0.00029956865272586674, 'samples': 12786816, 'steps': 66597, 'loss/train': 0.1468989998102188} 08/31/2021 01:15:54 - INFO - __main__ - Step 66599: {'lr': 0.0002995634513277547, 'samples': 12787008, 'steps': 66598, 'loss/train': 1.879630446434021} 08/31/2021 01:15:54 - INFO - __main__ - Step 66600: {'lr': 0.00029955824990731024, 'samples': 12787200, 'steps': 66599, 'loss/train': 1.4784363508224487} 08/31/2021 01:15:55 - INFO - __main__ - Step 66601: {'lr': 0.00029955304846453554, 'samples': 12787392, 'steps': 66600, 'loss/train': 1.5949933528900146} 08/31/2021 01:15:55 - INFO - __main__ - Step 66602: {'lr': 0.00029954784699943294, 'samples': 12787584, 'steps': 66601, 'loss/train': 1.3020598888397217} 08/31/2021 01:15:55 - INFO - __main__ - Step 66603: {'lr': 0.0002995426455120049, 'samples': 12787776, 'steps': 66602, 'loss/train': 1.161914587020874} 08/31/2021 01:15:57 - INFO - __main__ - Step 66604: {'lr': 0.00029953744400225364, 'samples': 12787968, 'steps': 66603, 'loss/train': 1.6978298425674438} 08/31/2021 01:15:57 - INFO - __main__ - Step 66605: {'lr': 0.0002995322424701816, 'samples': 12788160, 'steps': 66604, 'loss/train': 0.8381934762001038} 08/31/2021 01:15:58 - INFO - __main__ - Step 66606: {'lr': 0.00029952704091579116, 'samples': 12788352, 'steps': 66605, 'loss/train': 1.5363584756851196} 08/31/2021 01:15:58 - INFO - __main__ - Step 66607: {'lr': 0.00029952183933908464, 'samples': 12788544, 'steps': 66606, 'loss/train': 0.9005187153816223} 08/31/2021 01:15:58 - INFO - __main__ - Step 66608: {'lr': 0.0002995166377400642, 'samples': 12788736, 'steps': 66607, 'loss/train': 1.4625617265701294} 08/31/2021 01:16:00 - INFO - __main__ - Step 66609: {'lr': 0.0002995114361187324, 'samples': 12788928, 'steps': 66608, 'loss/train': 0.8700261116027832} 08/31/2021 01:16:00 - INFO - __main__ - Step 66610: {'lr': 0.00029950623447509147, 'samples': 12789120, 'steps': 66609, 'loss/train': 1.1949946880340576} 08/31/2021 01:16:01 - INFO - __main__ - Step 66611: {'lr': 0.00029950103280914383, 'samples': 12789312, 'steps': 66610, 'loss/train': 1.5915995836257935} 08/31/2021 01:16:01 - INFO - __main__ - Step 66612: {'lr': 0.00029949583112089177, 'samples': 12789504, 'steps': 66611, 'loss/train': 0.8689237833023071} 08/31/2021 01:16:01 - INFO - __main__ - Step 66613: {'lr': 0.00029949062941033767, 'samples': 12789696, 'steps': 66612, 'loss/train': 1.4915305376052856} 08/31/2021 01:16:03 - INFO - __main__ - Step 66614: {'lr': 0.00029948542767748386, 'samples': 12789888, 'steps': 66613, 'loss/train': 1.0551185607910156} 08/31/2021 01:16:04 - INFO - __main__ - Step 66615: {'lr': 0.0002994802259223327, 'samples': 12790080, 'steps': 66614, 'loss/train': 2.381103277206421} 08/31/2021 01:16:04 - INFO - __main__ - Step 66616: {'lr': 0.00029947502414488645, 'samples': 12790272, 'steps': 66615, 'loss/train': 1.0634897947311401} 08/31/2021 01:16:04 - INFO - __main__ - Step 66617: {'lr': 0.00029946982234514756, 'samples': 12790464, 'steps': 66616, 'loss/train': 0.7031606435775757} 08/31/2021 01:16:05 - INFO - __main__ - Step 66618: {'lr': 0.00029946462052311834, 'samples': 12790656, 'steps': 66617, 'loss/train': 1.5418651103973389} 08/31/2021 01:16:06 - INFO - __main__ - Step 66619: {'lr': 0.0002994594186788011, 'samples': 12790848, 'steps': 66618, 'loss/train': 0.20129728317260742} 08/31/2021 01:16:07 - INFO - __main__ - Step 66620: {'lr': 0.00029945421681219824, 'samples': 12791040, 'steps': 66619, 'loss/train': 1.232826590538025} 08/31/2021 01:16:07 - INFO - __main__ - Step 66621: {'lr': 0.00029944901492331207, 'samples': 12791232, 'steps': 66620, 'loss/train': 1.0813194513320923} 08/31/2021 01:16:07 - INFO - __main__ - Step 66622: {'lr': 0.0002994438130121449, 'samples': 12791424, 'steps': 66621, 'loss/train': 1.5874284505844116} 08/31/2021 01:16:08 - INFO - __main__ - Step 66623: {'lr': 0.0002994386110786991, 'samples': 12791616, 'steps': 66622, 'loss/train': 0.25188493728637695} 08/31/2021 01:16:08 - INFO - __main__ - Step 66624: {'lr': 0.0002994334091229771, 'samples': 12791808, 'steps': 66623, 'loss/train': 1.081129550933838} 08/31/2021 01:16:10 - INFO - __main__ - Step 66625: {'lr': 0.0002994282071449811, 'samples': 12792000, 'steps': 66624, 'loss/train': 1.120578646659851} 08/31/2021 01:16:10 - INFO - __main__ - Step 66626: {'lr': 0.00029942300514471354, 'samples': 12792192, 'steps': 66625, 'loss/train': 1.2666631937026978} 08/31/2021 01:16:11 - INFO - __main__ - Step 66627: {'lr': 0.00029941780312217674, 'samples': 12792384, 'steps': 66626, 'loss/train': 1.6700056791305542} 08/31/2021 01:16:11 - INFO - __main__ - Step 66628: {'lr': 0.0002994126010773731, 'samples': 12792576, 'steps': 66627, 'loss/train': 0.8342205882072449} 08/31/2021 01:16:11 - INFO - __main__ - Step 66629: {'lr': 0.0002994073990103048, 'samples': 12792768, 'steps': 66628, 'loss/train': 0.8626260161399841} 08/31/2021 01:16:13 - INFO - __main__ - Step 66630: {'lr': 0.0002994021969209743, 'samples': 12792960, 'steps': 66629, 'loss/train': 0.834702730178833} 08/31/2021 01:16:13 - INFO - __main__ - Step 66631: {'lr': 0.0002993969948093839, 'samples': 12793152, 'steps': 66630, 'loss/train': 1.284346580505371} 08/31/2021 01:16:14 - INFO - __main__ - Step 66632: {'lr': 0.0002993917926755361, 'samples': 12793344, 'steps': 66631, 'loss/train': 1.2170320749282837} 08/31/2021 01:16:14 - INFO - __main__ - Step 66633: {'lr': 0.000299386590519433, 'samples': 12793536, 'steps': 66632, 'loss/train': 1.3368921279907227} 08/31/2021 01:16:14 - INFO - __main__ - Step 66634: {'lr': 0.0002993813883410772, 'samples': 12793728, 'steps': 66633, 'loss/train': 1.2975174188613892} 08/31/2021 01:16:15 - INFO - __main__ - Step 66635: {'lr': 0.0002993761861404708, 'samples': 12793920, 'steps': 66634, 'loss/train': 0.6192722916603088} 08/31/2021 01:16:16 - INFO - __main__ - Step 66636: {'lr': 0.0002993709839176163, 'samples': 12794112, 'steps': 66635, 'loss/train': 1.3333109617233276} 08/31/2021 01:16:17 - INFO - __main__ - Step 66637: {'lr': 0.00029936578167251594, 'samples': 12794304, 'steps': 66636, 'loss/train': 1.6913611888885498} 08/31/2021 01:16:17 - INFO - __main__ - Step 66638: {'lr': 0.00029936057940517215, 'samples': 12794496, 'steps': 66637, 'loss/train': 1.327253818511963} 08/31/2021 01:16:17 - INFO - __main__ - Step 66639: {'lr': 0.00029935537711558725, 'samples': 12794688, 'steps': 66638, 'loss/train': 1.2137717008590698} 08/31/2021 01:16:18 - INFO - __main__ - Step 66640: {'lr': 0.00029935017480376357, 'samples': 12794880, 'steps': 66639, 'loss/train': 0.9855504631996155} 08/31/2021 01:16:19 - INFO - __main__ - Step 66641: {'lr': 0.00029934497246970356, 'samples': 12795072, 'steps': 66640, 'loss/train': 1.2263870239257812} 08/31/2021 01:16:20 - INFO - __main__ - Step 66642: {'lr': 0.0002993397701134093, 'samples': 12795264, 'steps': 66641, 'loss/train': 1.643341064453125} 08/31/2021 01:16:20 - INFO - __main__ - Step 66643: {'lr': 0.0002993345677348834, 'samples': 12795456, 'steps': 66642, 'loss/train': 1.197921633720398} 08/31/2021 01:16:20 - INFO - __main__ - Step 66644: {'lr': 0.00029932936533412806, 'samples': 12795648, 'steps': 66643, 'loss/train': 1.7516601085662842} 08/31/2021 01:16:21 - INFO - __main__ - Step 66645: {'lr': 0.00029932416291114574, 'samples': 12795840, 'steps': 66644, 'loss/train': 1.3573087453842163} 08/31/2021 01:16:23 - INFO - __main__ - Step 66646: {'lr': 0.00029931896046593863, 'samples': 12796032, 'steps': 66645, 'loss/train': 1.49173104763031} 08/31/2021 01:16:24 - INFO - __main__ - Step 66647: {'lr': 0.00029931375799850923, 'samples': 12796224, 'steps': 66646, 'loss/train': 1.1248565912246704} 08/31/2021 01:16:24 - INFO - __main__ - Step 66648: {'lr': 0.0002993085555088598, 'samples': 12796416, 'steps': 66647, 'loss/train': 0.49542292952537537} 08/31/2021 01:16:24 - INFO - __main__ - Step 66649: {'lr': 0.0002993033529969927, 'samples': 12796608, 'steps': 66648, 'loss/train': 0.9794304370880127} 08/31/2021 01:16:25 - INFO - __main__ - Step 66650: {'lr': 0.0002992981504629102, 'samples': 12796800, 'steps': 66649, 'loss/train': 0.80614173412323} 08/31/2021 01:16:26 - INFO - __main__ - Step 66651: {'lr': 0.00029929294790661474, 'samples': 12796992, 'steps': 66650, 'loss/train': 0.372713565826416} 08/31/2021 01:16:27 - INFO - __main__ - Step 66652: {'lr': 0.00029928774532810866, 'samples': 12797184, 'steps': 66651, 'loss/train': 1.3536577224731445} 08/31/2021 01:16:27 - INFO - __main__ - Step 66653: {'lr': 0.00029928254272739433, 'samples': 12797376, 'steps': 66652, 'loss/train': 1.4034385681152344} 08/31/2021 01:16:27 - INFO - __main__ - Step 66654: {'lr': 0.000299277340104474, 'samples': 12797568, 'steps': 66653, 'loss/train': 1.2619315385818481} 08/31/2021 01:16:28 - INFO - __main__ - Step 66655: {'lr': 0.00029927213745935, 'samples': 12797760, 'steps': 66654, 'loss/train': 0.24160926043987274} 08/31/2021 01:16:28 - INFO - __main__ - Step 66656: {'lr': 0.00029926693479202484, 'samples': 12797952, 'steps': 66655, 'loss/train': 1.4200044870376587} 08/31/2021 01:16:29 - INFO - __main__ - Step 66657: {'lr': 0.0002992617321025007, 'samples': 12798144, 'steps': 66656, 'loss/train': 1.3601938486099243} 08/31/2021 01:16:30 - INFO - __main__ - Step 66658: {'lr': 0.00029925652939078, 'samples': 12798336, 'steps': 66657, 'loss/train': 0.8859828114509583} 08/31/2021 01:16:30 - INFO - __main__ - Step 66659: {'lr': 0.0002992513266568651, 'samples': 12798528, 'steps': 66658, 'loss/train': 1.4019842147827148} 08/31/2021 01:16:31 - INFO - __main__ - Step 66660: {'lr': 0.00029924612390075817, 'samples': 12798720, 'steps': 66659, 'loss/train': 1.1978262662887573} 08/31/2021 01:16:31 - INFO - __main__ - Step 66661: {'lr': 0.0002992409211224619, 'samples': 12798912, 'steps': 66660, 'loss/train': 0.21389222145080566} 08/31/2021 01:16:32 - INFO - __main__ - Step 66662: {'lr': 0.00029923571832197825, 'samples': 12799104, 'steps': 66661, 'loss/train': 1.4978324174880981} 08/31/2021 01:16:33 - INFO - __main__ - Step 66663: {'lr': 0.00029923051549930984, 'samples': 12799296, 'steps': 66662, 'loss/train': 0.8216031789779663} 08/31/2021 01:16:33 - INFO - __main__ - Step 66664: {'lr': 0.0002992253126544589, 'samples': 12799488, 'steps': 66663, 'loss/train': 0.990667998790741} 08/31/2021 01:16:34 - INFO - __main__ - Step 66665: {'lr': 0.0002992201097874278, 'samples': 12799680, 'steps': 66664, 'loss/train': 1.317095398902893} 08/31/2021 01:16:34 - INFO - __main__ - Step 66666: {'lr': 0.0002992149068982189, 'samples': 12799872, 'steps': 66665, 'loss/train': 0.7245876789093018} 08/31/2021 01:16:35 - INFO - __main__ - Step 66667: {'lr': 0.0002992097039868346, 'samples': 12800064, 'steps': 66666, 'loss/train': 1.280407428741455} 08/31/2021 01:16:36 - INFO - __main__ - Step 66668: {'lr': 0.000299204501053277, 'samples': 12800256, 'steps': 66667, 'loss/train': 1.2407413721084595} 08/31/2021 01:16:36 - INFO - __main__ - Step 66669: {'lr': 0.00029919929809754865, 'samples': 12800448, 'steps': 66668, 'loss/train': 1.1615363359451294} 08/31/2021 01:16:37 - INFO - __main__ - Step 66670: {'lr': 0.0002991940951196519, 'samples': 12800640, 'steps': 66669, 'loss/train': 1.2591402530670166} 08/31/2021 01:16:37 - INFO - __main__ - Step 66671: {'lr': 0.000299188892119589, 'samples': 12800832, 'steps': 66670, 'loss/train': 0.574702799320221} 08/31/2021 01:16:38 - INFO - __main__ - Step 66672: {'lr': 0.00029918368909736235, 'samples': 12801024, 'steps': 66671, 'loss/train': 1.521361231803894} 08/31/2021 01:16:39 - INFO - __main__ - Step 66673: {'lr': 0.0002991784860529744, 'samples': 12801216, 'steps': 66672, 'loss/train': 1.7676143646240234} 08/31/2021 01:16:39 - INFO - __main__ - Step 66674: {'lr': 0.00029917328298642733, 'samples': 12801408, 'steps': 66673, 'loss/train': 1.8350005149841309} 08/31/2021 01:16:40 - INFO - __main__ - Step 66675: {'lr': 0.0002991680798977234, 'samples': 12801600, 'steps': 66674, 'loss/train': 1.3866899013519287} 08/31/2021 01:16:40 - INFO - __main__ - Step 66676: {'lr': 0.0002991628767868653, 'samples': 12801792, 'steps': 66675, 'loss/train': 0.0731678232550621} 08/31/2021 01:16:41 - INFO - __main__ - Step 66677: {'lr': 0.000299157673653855, 'samples': 12801984, 'steps': 66676, 'loss/train': 1.2085895538330078} 08/31/2021 01:16:42 - INFO - __main__ - Step 66678: {'lr': 0.0002991524704986951, 'samples': 12802176, 'steps': 66677, 'loss/train': 1.5846161842346191} 08/31/2021 01:16:42 - INFO - __main__ - Step 66679: {'lr': 0.0002991472673213879, 'samples': 12802368, 'steps': 66678, 'loss/train': 1.2082282304763794} 08/31/2021 01:16:43 - INFO - __main__ - Step 66680: {'lr': 0.0002991420641219356, 'samples': 12802560, 'steps': 66679, 'loss/train': 1.8006643056869507} 08/31/2021 01:16:43 - INFO - __main__ - Step 66681: {'lr': 0.00029913686090034063, 'samples': 12802752, 'steps': 66680, 'loss/train': 1.6363009214401245} 08/31/2021 01:16:43 - INFO - __main__ - Step 66682: {'lr': 0.0002991316576566054, 'samples': 12802944, 'steps': 66681, 'loss/train': 0.946659505367279} 08/31/2021 01:16:45 - INFO - __main__ - Step 66683: {'lr': 0.0002991264543907322, 'samples': 12803136, 'steps': 66682, 'loss/train': 0.8713789582252502} 08/31/2021 01:16:45 - INFO - __main__ - Step 66684: {'lr': 0.0002991212511027234, 'samples': 12803328, 'steps': 66683, 'loss/train': 1.2702867984771729} 08/31/2021 01:16:45 - INFO - __main__ - Step 66685: {'lr': 0.0002991160477925813, 'samples': 12803520, 'steps': 66684, 'loss/train': 1.3647561073303223} 08/31/2021 01:16:46 - INFO - __main__ - Step 66686: {'lr': 0.00029911084446030827, 'samples': 12803712, 'steps': 66685, 'loss/train': 1.3533357381820679} 08/31/2021 01:16:46 - INFO - __main__ - Step 66687: {'lr': 0.0002991056411059067, 'samples': 12803904, 'steps': 66686, 'loss/train': 0.4909053146839142} 08/31/2021 01:16:48 - INFO - __main__ - Step 66688: {'lr': 0.0002991004377293788, 'samples': 12804096, 'steps': 66687, 'loss/train': 1.6754751205444336} 08/31/2021 01:16:48 - INFO - __main__ - Step 66689: {'lr': 0.000299095234330727, 'samples': 12804288, 'steps': 66688, 'loss/train': 1.1658737659454346} 08/31/2021 01:16:49 - INFO - __main__ - Step 66690: {'lr': 0.0002990900309099537, 'samples': 12804480, 'steps': 66689, 'loss/train': 1.5174106359481812} 08/31/2021 01:16:49 - INFO - __main__ - Step 66691: {'lr': 0.00029908482746706115, 'samples': 12804672, 'steps': 66690, 'loss/train': 1.6086114645004272} 08/31/2021 01:16:49 - INFO - __main__ - Step 66692: {'lr': 0.00029907962400205175, 'samples': 12804864, 'steps': 66691, 'loss/train': 2.1206419467926025} 08/31/2021 01:16:51 - INFO - __main__ - Step 66693: {'lr': 0.0002990744205149278, 'samples': 12805056, 'steps': 66692, 'loss/train': 0.9303330779075623} 08/31/2021 01:16:51 - INFO - __main__ - Step 66694: {'lr': 0.00029906921700569174, 'samples': 12805248, 'steps': 66693, 'loss/train': 0.2996772825717926} 08/31/2021 01:16:52 - INFO - __main__ - Step 66695: {'lr': 0.00029906401347434586, 'samples': 12805440, 'steps': 66694, 'loss/train': 1.463254690170288} 08/31/2021 01:16:52 - INFO - __main__ - Step 66696: {'lr': 0.0002990588099208924, 'samples': 12805632, 'steps': 66695, 'loss/train': 1.1905536651611328} 08/31/2021 01:16:52 - INFO - __main__ - Step 66697: {'lr': 0.00029905360634533383, 'samples': 12805824, 'steps': 66696, 'loss/train': 0.8470683097839355} 08/31/2021 01:16:54 - INFO - __main__ - Step 66698: {'lr': 0.00029904840274767245, 'samples': 12806016, 'steps': 66697, 'loss/train': 0.9781017303466797} 08/31/2021 01:16:55 - INFO - __main__ - Step 66699: {'lr': 0.0002990431991279107, 'samples': 12806208, 'steps': 66698, 'loss/train': 1.9014285802841187} 08/31/2021 01:16:55 - INFO - __main__ - Step 66700: {'lr': 0.00029903799548605073, 'samples': 12806400, 'steps': 66699, 'loss/train': 1.1884220838546753} 08/31/2021 01:16:55 - INFO - __main__ - Step 66701: {'lr': 0.0002990327918220951, 'samples': 12806592, 'steps': 66700, 'loss/train': 1.4539381265640259} 08/31/2021 01:16:56 - INFO - __main__ - Step 66702: {'lr': 0.000299027588136046, 'samples': 12806784, 'steps': 66701, 'loss/train': 1.2705975770950317} 08/31/2021 01:16:57 - INFO - __main__ - Step 66703: {'lr': 0.0002990223844279058, 'samples': 12806976, 'steps': 66702, 'loss/train': 0.03024780936539173} 08/31/2021 01:16:58 - INFO - __main__ - Step 66704: {'lr': 0.00029901718069767693, 'samples': 12807168, 'steps': 66703, 'loss/train': 1.1295967102050781} 08/31/2021 01:16:58 - INFO - __main__ - Step 66705: {'lr': 0.0002990119769453616, 'samples': 12807360, 'steps': 66704, 'loss/train': 0.633186936378479} 08/31/2021 01:16:58 - INFO - __main__ - Step 66706: {'lr': 0.00029900677317096225, 'samples': 12807552, 'steps': 66705, 'loss/train': 1.1704033613204956} 08/31/2021 01:16:59 - INFO - __main__ - Step 66707: {'lr': 0.0002990015693744812, 'samples': 12807744, 'steps': 66706, 'loss/train': 1.108583927154541} 08/31/2021 01:17:01 - INFO - __main__ - Step 66708: {'lr': 0.00029899636555592087, 'samples': 12807936, 'steps': 66707, 'loss/train': 0.5644575953483582} 08/31/2021 01:17:01 - INFO - __main__ - Step 66709: {'lr': 0.0002989911617152835, 'samples': 12808128, 'steps': 66708, 'loss/train': 1.4954010248184204} 08/31/2021 01:17:01 - INFO - __main__ - Step 66710: {'lr': 0.00029898595785257144, 'samples': 12808320, 'steps': 66709, 'loss/train': 1.665158748626709} 08/31/2021 01:17:02 - INFO - __main__ - Step 66711: {'lr': 0.0002989807539677871, 'samples': 12808512, 'steps': 66710, 'loss/train': 1.799777626991272} 08/31/2021 01:17:02 - INFO - __main__ - Step 66712: {'lr': 0.00029897555006093266, 'samples': 12808704, 'steps': 66711, 'loss/train': 0.05549148842692375} 08/31/2021 01:17:04 - INFO - __main__ - Step 66713: {'lr': 0.0002989703461320107, 'samples': 12808896, 'steps': 66712, 'loss/train': 1.3670520782470703} 08/31/2021 01:17:04 - INFO - __main__ - Step 66714: {'lr': 0.0002989651421810235, 'samples': 12809088, 'steps': 66713, 'loss/train': 0.5061144828796387} 08/31/2021 01:17:04 - INFO - __main__ - Step 66715: {'lr': 0.00029895993820797334, 'samples': 12809280, 'steps': 66714, 'loss/train': 1.3379106521606445} 08/31/2021 01:17:05 - INFO - __main__ - Step 66716: {'lr': 0.0002989547342128626, 'samples': 12809472, 'steps': 66715, 'loss/train': 0.8019230961799622} 08/31/2021 01:17:05 - INFO - __main__ - Step 66717: {'lr': 0.0002989495301956935, 'samples': 12809664, 'steps': 66716, 'loss/train': 1.3347843885421753} 08/31/2021 01:17:07 - INFO - __main__ - Step 66718: {'lr': 0.00029894432615646863, 'samples': 12809856, 'steps': 66717, 'loss/train': 2.027360200881958} 08/31/2021 01:17:07 - INFO - __main__ - Step 66719: {'lr': 0.0002989391220951901, 'samples': 12810048, 'steps': 66718, 'loss/train': 1.3291161060333252} 08/31/2021 01:17:07 - INFO - __main__ - Step 66720: {'lr': 0.0002989339180118604, 'samples': 12810240, 'steps': 66719, 'loss/train': 1.2006460428237915} 08/31/2021 01:17:08 - INFO - __main__ - Step 66721: {'lr': 0.0002989287139064819, 'samples': 12810432, 'steps': 66720, 'loss/train': 1.8004224300384521} 08/31/2021 01:17:08 - INFO - __main__ - Step 66722: {'lr': 0.0002989235097790568, 'samples': 12810624, 'steps': 66721, 'loss/train': 1.5721464157104492} 08/31/2021 01:17:09 - INFO - __main__ - Step 66723: {'lr': 0.0002989183056295875, 'samples': 12810816, 'steps': 66722, 'loss/train': 1.4433501958847046} 08/31/2021 01:17:10 - INFO - __main__ - Step 66724: {'lr': 0.00029891310145807636, 'samples': 12811008, 'steps': 66723, 'loss/train': 0.19048067927360535} 08/31/2021 01:17:10 - INFO - __main__ - Step 66725: {'lr': 0.00029890789726452576, 'samples': 12811200, 'steps': 66724, 'loss/train': 1.2670272588729858} 08/31/2021 01:17:11 - INFO - __main__ - Step 66726: {'lr': 0.00029890269304893804, 'samples': 12811392, 'steps': 66725, 'loss/train': 1.839468002319336} 08/31/2021 01:17:11 - INFO - __main__ - Step 66727: {'lr': 0.0002988974888113155, 'samples': 12811584, 'steps': 66726, 'loss/train': 1.8483203649520874} 08/31/2021 01:17:11 - INFO - __main__ - Step 66728: {'lr': 0.00029889228455166054, 'samples': 12811776, 'steps': 66727, 'loss/train': 0.9351038336753845} 08/31/2021 01:17:13 - INFO - __main__ - Step 66729: {'lr': 0.00029888708026997547, 'samples': 12811968, 'steps': 66728, 'loss/train': 1.5633805990219116} 08/31/2021 01:17:13 - INFO - __main__ - Step 66730: {'lr': 0.0002988818759662626, 'samples': 12812160, 'steps': 66729, 'loss/train': 1.2824108600616455} 08/31/2021 01:17:14 - INFO - __main__ - Step 66731: {'lr': 0.0002988766716405243, 'samples': 12812352, 'steps': 66730, 'loss/train': 1.3100558519363403} 08/31/2021 01:17:14 - INFO - __main__ - Step 66732: {'lr': 0.00029887146729276295, 'samples': 12812544, 'steps': 66731, 'loss/train': 1.3638330698013306} 08/31/2021 01:17:15 - INFO - __main__ - Step 66733: {'lr': 0.00029886626292298087, 'samples': 12812736, 'steps': 66732, 'loss/train': 0.6909828782081604} 08/31/2021 01:17:16 - INFO - __main__ - Step 66734: {'lr': 0.0002988610585311804, 'samples': 12812928, 'steps': 66733, 'loss/train': 1.2919949293136597} 08/31/2021 01:17:16 - INFO - __main__ - Step 66735: {'lr': 0.0002988558541173639, 'samples': 12813120, 'steps': 66734, 'loss/train': 1.1824523210525513} 08/31/2021 01:17:17 - INFO - __main__ - Step 66736: {'lr': 0.0002988506496815337, 'samples': 12813312, 'steps': 66735, 'loss/train': 1.7155864238739014} 08/31/2021 01:17:17 - INFO - __main__ - Step 66737: {'lr': 0.00029884544522369217, 'samples': 12813504, 'steps': 66736, 'loss/train': 0.22088900208473206} 08/31/2021 01:17:17 - INFO - __main__ - Step 66738: {'lr': 0.00029884024074384156, 'samples': 12813696, 'steps': 66737, 'loss/train': 1.3626419305801392} 08/31/2021 01:17:19 - INFO - __main__ - Step 66739: {'lr': 0.00029883503624198436, 'samples': 12813888, 'steps': 66738, 'loss/train': 1.166611671447754} 08/31/2021 01:17:20 - INFO - __main__ - Step 66740: {'lr': 0.00029882983171812283, 'samples': 12814080, 'steps': 66739, 'loss/train': 0.918258011341095} 08/31/2021 01:17:20 - INFO - __main__ - Step 66741: {'lr': 0.0002988246271722594, 'samples': 12814272, 'steps': 66740, 'loss/train': 1.8517708778381348} 08/31/2021 01:17:20 - INFO - __main__ - Step 66742: {'lr': 0.0002988194226043963, 'samples': 12814464, 'steps': 66741, 'loss/train': 0.5473620295524597} 08/31/2021 01:17:21 - INFO - __main__ - Step 66743: {'lr': 0.0002988142180145359, 'samples': 12814656, 'steps': 66742, 'loss/train': 1.3578598499298096} 08/31/2021 01:17:22 - INFO - __main__ - Step 66744: {'lr': 0.00029880901340268053, 'samples': 12814848, 'steps': 66743, 'loss/train': 1.292415738105774} 08/31/2021 01:17:23 - INFO - __main__ - Step 66745: {'lr': 0.0002988038087688326, 'samples': 12815040, 'steps': 66744, 'loss/train': 1.393042802810669} 08/31/2021 01:17:23 - INFO - __main__ - Step 66746: {'lr': 0.0002987986041129944, 'samples': 12815232, 'steps': 66745, 'loss/train': 1.4876257181167603} 08/31/2021 01:17:23 - INFO - __main__ - Step 66747: {'lr': 0.00029879339943516837, 'samples': 12815424, 'steps': 66746, 'loss/train': 1.3231587409973145} 08/31/2021 01:17:24 - INFO - __main__ - Step 66748: {'lr': 0.00029878819473535677, 'samples': 12815616, 'steps': 66747, 'loss/train': 1.5077682733535767} 08/31/2021 01:17:26 - INFO - __main__ - Step 66749: {'lr': 0.00029878299001356195, 'samples': 12815808, 'steps': 66748, 'loss/train': 1.4857052564620972} 08/31/2021 01:17:26 - INFO - __main__ - Step 66750: {'lr': 0.0002987777852697863, 'samples': 12816000, 'steps': 66749, 'loss/train': 1.3803631067276} 08/31/2021 01:17:26 - INFO - __main__ - Step 66751: {'lr': 0.0002987725805040321, 'samples': 12816192, 'steps': 66750, 'loss/train': 1.2580007314682007} 08/31/2021 01:17:27 - INFO - __main__ - Step 66752: {'lr': 0.0002987673757163017, 'samples': 12816384, 'steps': 66751, 'loss/train': 0.9460901021957397} 08/31/2021 01:17:27 - INFO - __main__ - Step 66753: {'lr': 0.0002987621709065975, 'samples': 12816576, 'steps': 66752, 'loss/train': 1.3101465702056885} 08/31/2021 01:17:29 - INFO - __main__ - Step 66754: {'lr': 0.0002987569660749218, 'samples': 12816768, 'steps': 66753, 'loss/train': 0.8937992453575134} 08/31/2021 01:17:29 - INFO - __main__ - Step 66755: {'lr': 0.0002987517612212771, 'samples': 12816960, 'steps': 66754, 'loss/train': 0.042572274804115295} 08/31/2021 01:17:30 - INFO - __main__ - Step 66756: {'lr': 0.00029874655634566546, 'samples': 12817152, 'steps': 66755, 'loss/train': 0.671847403049469} 08/31/2021 01:17:30 - INFO - __main__ - Step 66757: {'lr': 0.0002987413514480893, 'samples': 12817344, 'steps': 66756, 'loss/train': 1.1997441053390503} 08/31/2021 01:17:30 - INFO - __main__ - Step 66758: {'lr': 0.0002987361465285512, 'samples': 12817536, 'steps': 66757, 'loss/train': 0.5504373908042908} 08/31/2021 01:17:32 - INFO - __main__ - Step 66759: {'lr': 0.00029873094158705326, 'samples': 12817728, 'steps': 66758, 'loss/train': 1.5788230895996094} 08/31/2021 01:17:33 - INFO - __main__ - Step 66760: {'lr': 0.00029872573662359796, 'samples': 12817920, 'steps': 66759, 'loss/train': 0.9937694668769836} 08/31/2021 01:17:33 - INFO - __main__ - Step 66761: {'lr': 0.00029872053163818756, 'samples': 12818112, 'steps': 66760, 'loss/train': 1.9276877641677856} 08/31/2021 01:17:33 - INFO - __main__ - Step 66762: {'lr': 0.0002987153266308245, 'samples': 12818304, 'steps': 66761, 'loss/train': 1.232514500617981} 08/31/2021 01:17:34 - INFO - __main__ - Step 66763: {'lr': 0.000298710121601511, 'samples': 12818496, 'steps': 66762, 'loss/train': 1.5548673868179321} 08/31/2021 01:17:35 - INFO - __main__ - Step 66764: {'lr': 0.0002987049165502495, 'samples': 12818688, 'steps': 66763, 'loss/train': 1.5231047868728638} 08/31/2021 01:17:36 - INFO - __main__ - Step 66765: {'lr': 0.0002986997114770423, 'samples': 12818880, 'steps': 66764, 'loss/train': 1.2149670124053955} 08/31/2021 01:17:36 - INFO - __main__ - Step 66766: {'lr': 0.0002986945063818918, 'samples': 12819072, 'steps': 66765, 'loss/train': 0.8809140920639038} 08/31/2021 01:17:36 - INFO - __main__ - Step 66767: {'lr': 0.0002986893012648002, 'samples': 12819264, 'steps': 66766, 'loss/train': 0.9550579190254211} 08/31/2021 01:17:37 - INFO - __main__ - Step 66768: {'lr': 0.00029868409612577007, 'samples': 12819456, 'steps': 66767, 'loss/train': 1.351239800453186} 08/31/2021 01:17:38 - INFO - __main__ - Step 66769: {'lr': 0.0002986788909648036, 'samples': 12819648, 'steps': 66768, 'loss/train': 1.6131253242492676} 08/31/2021 01:17:38 - INFO - __main__ - Step 66770: {'lr': 0.00029867368578190317, 'samples': 12819840, 'steps': 66769, 'loss/train': 0.9798727631568909} 08/31/2021 01:17:39 - INFO - __main__ - Step 66771: {'lr': 0.0002986684805770711, 'samples': 12820032, 'steps': 66770, 'loss/train': 1.5431162118911743} 08/31/2021 01:17:39 - INFO - __main__ - Step 66772: {'lr': 0.0002986632753503098, 'samples': 12820224, 'steps': 66771, 'loss/train': 0.7042244672775269} 08/31/2021 01:17:40 - INFO - __main__ - Step 66773: {'lr': 0.00029865807010162154, 'samples': 12820416, 'steps': 66772, 'loss/train': 1.4888657331466675} 08/31/2021 01:17:41 - INFO - __main__ - Step 66774: {'lr': 0.0002986528648310087, 'samples': 12820608, 'steps': 66773, 'loss/train': 1.3808069229125977} 08/31/2021 01:17:41 - INFO - __main__ - Step 66775: {'lr': 0.0002986476595384738, 'samples': 12820800, 'steps': 66774, 'loss/train': 1.3251856565475464} 08/31/2021 01:17:42 - INFO - __main__ - Step 66776: {'lr': 0.0002986424542240188, 'samples': 12820992, 'steps': 66775, 'loss/train': 0.14978352189064026} 08/31/2021 01:17:42 - INFO - __main__ - Step 66777: {'lr': 0.00029863724888764637, 'samples': 12821184, 'steps': 66776, 'loss/train': 0.6504873037338257} 08/31/2021 01:17:43 - INFO - __main__ - Step 66778: {'lr': 0.0002986320435293587, 'samples': 12821376, 'steps': 66777, 'loss/train': 1.4862473011016846} 08/31/2021 01:17:44 - INFO - __main__ - Step 66779: {'lr': 0.0002986268381491582, 'samples': 12821568, 'steps': 66778, 'loss/train': 1.5813493728637695} 08/31/2021 01:17:45 - INFO - __main__ - Step 66780: {'lr': 0.0002986216327470472, 'samples': 12821760, 'steps': 66779, 'loss/train': 1.0315605401992798} 08/31/2021 01:17:45 - INFO - __main__ - Step 66781: {'lr': 0.000298616427323028, 'samples': 12821952, 'steps': 66780, 'loss/train': 0.21358458697795868} 08/31/2021 01:17:45 - INFO - __main__ - Step 66782: {'lr': 0.0002986112218771031, 'samples': 12822144, 'steps': 66781, 'loss/train': 1.9447767734527588} 08/31/2021 01:17:46 - INFO - __main__ - Step 66783: {'lr': 0.00029860601640927464, 'samples': 12822336, 'steps': 66782, 'loss/train': 0.7501627802848816} 08/31/2021 01:17:46 - INFO - __main__ - Step 66784: {'lr': 0.00029860081091954505, 'samples': 12822528, 'steps': 66783, 'loss/train': 1.1003984212875366} 08/31/2021 01:17:48 - INFO - __main__ - Step 66785: {'lr': 0.0002985956054079167, 'samples': 12822720, 'steps': 66784, 'loss/train': 0.9507541656494141} 08/31/2021 01:17:48 - INFO - __main__ - Step 66786: {'lr': 0.00029859039987439195, 'samples': 12822912, 'steps': 66785, 'loss/train': 0.9319968819618225} 08/31/2021 01:17:48 - INFO - __main__ - Step 66787: {'lr': 0.00029858519431897305, 'samples': 12823104, 'steps': 66786, 'loss/train': 0.6615083813667297} 08/31/2021 01:17:49 - INFO - __main__ - Step 66788: {'lr': 0.00029857998874166253, 'samples': 12823296, 'steps': 66787, 'loss/train': 1.6010165214538574} 08/31/2021 01:17:49 - INFO - __main__ - Step 66789: {'lr': 0.00029857478314246257, 'samples': 12823488, 'steps': 66788, 'loss/train': 1.5961567163467407} 08/31/2021 01:17:51 - INFO - __main__ - Step 66790: {'lr': 0.0002985695775213755, 'samples': 12823680, 'steps': 66789, 'loss/train': 0.8538408875465393} 08/31/2021 01:17:51 - INFO - __main__ - Step 66791: {'lr': 0.00029856437187840375, 'samples': 12823872, 'steps': 66790, 'loss/train': 1.0830730199813843} 08/31/2021 01:17:51 - INFO - __main__ - Step 66792: {'lr': 0.00029855916621354965, 'samples': 12824064, 'steps': 66791, 'loss/train': 0.7635622024536133} 08/31/2021 01:17:52 - INFO - __main__ - Step 66793: {'lr': 0.00029855396052681554, 'samples': 12824256, 'steps': 66792, 'loss/train': 1.0281744003295898} 08/31/2021 01:17:52 - INFO - __main__ - Step 66794: {'lr': 0.00029854875481820375, 'samples': 12824448, 'steps': 66793, 'loss/train': 0.8538246154785156} 08/31/2021 01:17:53 - INFO - __main__ - Step 66795: {'lr': 0.0002985435490877168, 'samples': 12824640, 'steps': 66794, 'loss/train': 1.4429211616516113} 08/31/2021 01:17:54 - INFO - __main__ - Step 66796: {'lr': 0.00029853834333535667, 'samples': 12824832, 'steps': 66795, 'loss/train': 1.5254387855529785} 08/31/2021 01:17:54 - INFO - __main__ - Step 66797: {'lr': 0.000298533137561126, 'samples': 12825024, 'steps': 66796, 'loss/train': 0.8941939473152161} 08/31/2021 01:17:55 - INFO - __main__ - Step 66798: {'lr': 0.00029852793176502704, 'samples': 12825216, 'steps': 66797, 'loss/train': 0.9137363433837891} 08/31/2021 01:17:55 - INFO - __main__ - Step 66799: {'lr': 0.0002985227259470621, 'samples': 12825408, 'steps': 66798, 'loss/train': 1.118599772453308} 08/31/2021 01:17:57 - INFO - __main__ - Step 66800: {'lr': 0.00029851752010723353, 'samples': 12825600, 'steps': 66799, 'loss/train': 1.282005786895752} 08/31/2021 01:17:57 - INFO - __main__ - Step 66801: {'lr': 0.00029851231424554383, 'samples': 12825792, 'steps': 66800, 'loss/train': 0.7836785912513733} 08/31/2021 01:17:57 - INFO - __main__ - Step 66802: {'lr': 0.00029850710836199526, 'samples': 12825984, 'steps': 66801, 'loss/train': 1.1296055316925049} 08/31/2021 01:17:58 - INFO - __main__ - Step 66803: {'lr': 0.00029850190245659, 'samples': 12826176, 'steps': 66802, 'loss/train': 1.3223121166229248} 08/31/2021 01:17:58 - INFO - __main__ - Step 66804: {'lr': 0.0002984966965293306, 'samples': 12826368, 'steps': 66803, 'loss/train': 1.2607578039169312} 08/31/2021 01:17:59 - INFO - __main__ - Step 66805: {'lr': 0.0002984914905802193, 'samples': 12826560, 'steps': 66804, 'loss/train': 1.5547442436218262} 08/31/2021 01:18:00 - INFO - __main__ - Step 66806: {'lr': 0.0002984862846092585, 'samples': 12826752, 'steps': 66805, 'loss/train': 0.9328221082687378} 08/31/2021 01:18:00 - INFO - __main__ - Step 66807: {'lr': 0.0002984810786164505, 'samples': 12826944, 'steps': 66806, 'loss/train': 1.555440068244934} 08/31/2021 01:18:01 - INFO - __main__ - Step 66808: {'lr': 0.00029847587260179776, 'samples': 12827136, 'steps': 66807, 'loss/train': 1.2397770881652832} 08/31/2021 01:18:01 - INFO - __main__ - Step 66809: {'lr': 0.0002984706665653025, 'samples': 12827328, 'steps': 66808, 'loss/train': 0.9761009216308594} 08/31/2021 01:18:03 - INFO - __main__ - Step 66810: {'lr': 0.0002984654605069671, 'samples': 12827520, 'steps': 66809, 'loss/train': 1.2348487377166748} 08/31/2021 01:18:04 - INFO - __main__ - Step 66811: {'lr': 0.00029846025442679394, 'samples': 12827712, 'steps': 66810, 'loss/train': 1.8199223279953003} 08/31/2021 01:18:04 - INFO - __main__ - Step 66812: {'lr': 0.00029845504832478524, 'samples': 12827904, 'steps': 66811, 'loss/train': 1.2564620971679688} 08/31/2021 01:18:04 - INFO - __main__ - Step 66813: {'lr': 0.0002984498422009436, 'samples': 12828096, 'steps': 66812, 'loss/train': 1.4352198839187622} 08/31/2021 01:18:05 - INFO - __main__ - Step 66814: {'lr': 0.00029844463605527104, 'samples': 12828288, 'steps': 66813, 'loss/train': 1.4326952695846558} 08/31/2021 01:18:06 - INFO - __main__ - Step 66815: {'lr': 0.0002984394298877702, 'samples': 12828480, 'steps': 66814, 'loss/train': 0.5583600997924805} 08/31/2021 01:18:07 - INFO - __main__ - Step 66816: {'lr': 0.0002984342236984432, 'samples': 12828672, 'steps': 66815, 'loss/train': 1.1357769966125488} 08/31/2021 01:18:07 - INFO - __main__ - Step 66817: {'lr': 0.00029842901748729255, 'samples': 12828864, 'steps': 66816, 'loss/train': 1.244722604751587} 08/31/2021 01:18:07 - INFO - __main__ - Step 66818: {'lr': 0.0002984238112543205, 'samples': 12829056, 'steps': 66817, 'loss/train': 1.6334446668624878} 08/31/2021 01:18:08 - INFO - __main__ - Step 66819: {'lr': 0.0002984186049995295, 'samples': 12829248, 'steps': 66818, 'loss/train': 0.9254969954490662} 08/31/2021 01:18:08 - INFO - __main__ - Step 66820: {'lr': 0.0002984133987229218, 'samples': 12829440, 'steps': 66819, 'loss/train': 0.9549763202667236} 08/31/2021 01:18:10 - INFO - __main__ - Step 66821: {'lr': 0.0002984081924244997, 'samples': 12829632, 'steps': 66820, 'loss/train': 1.4259655475616455} 08/31/2021 01:18:10 - INFO - __main__ - Step 66822: {'lr': 0.00029840298610426565, 'samples': 12829824, 'steps': 66821, 'loss/train': 1.8141850233078003} 08/31/2021 01:18:10 - INFO - __main__ - Step 66823: {'lr': 0.00029839777976222196, 'samples': 12830016, 'steps': 66822, 'loss/train': 0.7448185682296753} 08/31/2021 01:18:11 - INFO - __main__ - Step 66824: {'lr': 0.0002983925733983711, 'samples': 12830208, 'steps': 66823, 'loss/train': 1.2846322059631348} 08/31/2021 01:18:11 - INFO - __main__ - Step 66825: {'lr': 0.00029838736701271514, 'samples': 12830400, 'steps': 66824, 'loss/train': 1.657800316810608} 08/31/2021 01:18:13 - INFO - __main__ - Step 66826: {'lr': 0.00029838216060525656, 'samples': 12830592, 'steps': 66825, 'loss/train': 1.5548515319824219} 08/31/2021 01:18:13 - INFO - __main__ - Step 66827: {'lr': 0.0002983769541759978, 'samples': 12830784, 'steps': 66826, 'loss/train': 0.7413408160209656} 08/31/2021 01:18:14 - INFO - __main__ - Step 66828: {'lr': 0.00029837174772494107, 'samples': 12830976, 'steps': 66827, 'loss/train': 1.9610315561294556} 08/31/2021 01:18:14 - INFO - __main__ - Step 66829: {'lr': 0.0002983665412520888, 'samples': 12831168, 'steps': 66828, 'loss/train': 0.9007928371429443} 08/31/2021 01:18:14 - INFO - __main__ - Step 66830: {'lr': 0.0002983613347574434, 'samples': 12831360, 'steps': 66829, 'loss/train': 1.5353553295135498} 08/31/2021 01:18:16 - INFO - __main__ - Step 66831: {'lr': 0.00029835612824100706, 'samples': 12831552, 'steps': 66830, 'loss/train': 1.384204626083374} 08/31/2021 01:18:16 - INFO - __main__ - Step 66832: {'lr': 0.0002983509217027822, 'samples': 12831744, 'steps': 66831, 'loss/train': 1.4799957275390625} 08/31/2021 01:18:17 - INFO - __main__ - Step 66833: {'lr': 0.00029834571514277116, 'samples': 12831936, 'steps': 66832, 'loss/train': 1.2683178186416626} 08/31/2021 01:18:17 - INFO - __main__ - Step 66834: {'lr': 0.0002983405085609763, 'samples': 12832128, 'steps': 66833, 'loss/train': 1.753151774406433} 08/31/2021 01:18:17 - INFO - __main__ - Step 66835: {'lr': 0.0002983353019573999, 'samples': 12832320, 'steps': 66834, 'loss/train': 0.7125412225723267} 08/31/2021 01:18:19 - INFO - __main__ - Step 66836: {'lr': 0.0002983300953320445, 'samples': 12832512, 'steps': 66835, 'loss/train': 0.8784317374229431} 08/31/2021 01:18:19 - INFO - __main__ - Step 66837: {'lr': 0.00029832488868491216, 'samples': 12832704, 'steps': 66836, 'loss/train': 0.918865442276001} 08/31/2021 01:18:20 - INFO - __main__ - Step 66838: {'lr': 0.0002983196820160054, 'samples': 12832896, 'steps': 66837, 'loss/train': 0.8013406991958618} 08/31/2021 01:18:20 - INFO - __main__ - Step 66839: {'lr': 0.0002983144753253265, 'samples': 12833088, 'steps': 66838, 'loss/train': 1.0291317701339722} 08/31/2021 01:18:20 - INFO - __main__ - Step 66840: {'lr': 0.0002983092686128779, 'samples': 12833280, 'steps': 66839, 'loss/train': 0.9856081008911133} 08/31/2021 01:18:22 - INFO - __main__ - Step 66841: {'lr': 0.00029830406187866186, 'samples': 12833472, 'steps': 66840, 'loss/train': 1.172946572303772} 08/31/2021 01:18:22 - INFO - __main__ - Step 66842: {'lr': 0.00029829885512268084, 'samples': 12833664, 'steps': 66841, 'loss/train': 0.9351199269294739} 08/31/2021 01:18:23 - INFO - __main__ - Step 66843: {'lr': 0.000298293648344937, 'samples': 12833856, 'steps': 66842, 'loss/train': 1.5846223831176758} 08/31/2021 01:18:23 - INFO - __main__ - Step 66844: {'lr': 0.0002982884415454328, 'samples': 12834048, 'steps': 66843, 'loss/train': 1.218687653541565} 08/31/2021 01:18:23 - INFO - __main__ - Step 66845: {'lr': 0.00029828323472417065, 'samples': 12834240, 'steps': 66844, 'loss/train': 1.4752322435379028} 08/31/2021 01:18:25 - INFO - __main__ - Step 66846: {'lr': 0.00029827802788115276, 'samples': 12834432, 'steps': 66845, 'loss/train': 0.09260542690753937} 08/31/2021 01:18:26 - INFO - __main__ - Step 66847: {'lr': 0.00029827282101638154, 'samples': 12834624, 'steps': 66846, 'loss/train': 1.1105436086654663} 08/31/2021 01:18:26 - INFO - __main__ - Step 66848: {'lr': 0.00029826761412985933, 'samples': 12834816, 'steps': 66847, 'loss/train': 1.3852894306182861} 08/31/2021 01:18:26 - INFO - __main__ - Step 66849: {'lr': 0.00029826240722158847, 'samples': 12835008, 'steps': 66848, 'loss/train': 0.9132786989212036} 08/31/2021 01:18:27 - INFO - __main__ - Step 66850: {'lr': 0.0002982572002915713, 'samples': 12835200, 'steps': 66849, 'loss/train': 1.3430602550506592} 08/31/2021 01:18:27 - INFO - __main__ - Step 66851: {'lr': 0.00029825199333981023, 'samples': 12835392, 'steps': 66850, 'loss/train': 1.0233311653137207} 08/31/2021 01:18:28 - INFO - __main__ - Step 66852: {'lr': 0.0002982467863663075, 'samples': 12835584, 'steps': 66851, 'loss/train': 0.6597539186477661} 08/31/2021 01:18:29 - INFO - __main__ - Step 66853: {'lr': 0.00029824157937106553, 'samples': 12835776, 'steps': 66852, 'loss/train': 1.5347833633422852} 08/31/2021 01:18:29 - INFO - __main__ - Step 66854: {'lr': 0.0002982363723540867, 'samples': 12835968, 'steps': 66853, 'loss/train': 1.2718546390533447} 08/31/2021 01:18:30 - INFO - __main__ - Step 66855: {'lr': 0.00029823116531537325, 'samples': 12836160, 'steps': 66854, 'loss/train': 1.5051580667495728} 08/31/2021 01:18:30 - INFO - __main__ - Step 66856: {'lr': 0.00029822595825492766, 'samples': 12836352, 'steps': 66855, 'loss/train': 1.1154175996780396} 08/31/2021 01:18:32 - INFO - __main__ - Step 66857: {'lr': 0.0002982207511727522, 'samples': 12836544, 'steps': 66856, 'loss/train': 0.30748021602630615} 08/31/2021 01:18:33 - INFO - __main__ - Step 66858: {'lr': 0.0002982155440688491, 'samples': 12836736, 'steps': 66857, 'loss/train': 1.4344037771224976} 08/31/2021 01:18:33 - INFO - __main__ - Step 66859: {'lr': 0.00029821033694322086, 'samples': 12836928, 'steps': 66858, 'loss/train': 0.8698562383651733} 08/31/2021 01:18:33 - INFO - __main__ - Step 66860: {'lr': 0.00029820512979586975, 'samples': 12837120, 'steps': 66859, 'loss/train': 1.1522618532180786} 08/31/2021 01:18:34 - INFO - __main__ - Step 66861: {'lr': 0.00029819992262679817, 'samples': 12837312, 'steps': 66860, 'loss/train': 1.1389583349227905} 08/31/2021 01:18:35 - INFO - __main__ - Step 66862: {'lr': 0.00029819471543600856, 'samples': 12837504, 'steps': 66861, 'loss/train': 1.1656979322433472} 08/31/2021 01:18:36 - INFO - __main__ - Step 66863: {'lr': 0.000298189508223503, 'samples': 12837696, 'steps': 66862, 'loss/train': 0.9584106802940369} 08/31/2021 01:18:36 - INFO - __main__ - Step 66864: {'lr': 0.0002981843009892841, 'samples': 12837888, 'steps': 66863, 'loss/train': 0.3829325735569} 08/31/2021 01:18:36 - INFO - __main__ - Step 66865: {'lr': 0.00029817909373335407, 'samples': 12838080, 'steps': 66864, 'loss/train': 0.03614123538136482} 08/31/2021 01:18:37 - INFO - __main__ - Step 66866: {'lr': 0.0002981738864557153, 'samples': 12838272, 'steps': 66865, 'loss/train': 1.9796062707901} 08/31/2021 01:18:38 - INFO - __main__ - Step 66867: {'lr': 0.0002981686791563701, 'samples': 12838464, 'steps': 66866, 'loss/train': 0.8041342496871948} 08/31/2021 01:18:39 - INFO - __main__ - Step 66868: {'lr': 0.00029816347183532076, 'samples': 12838656, 'steps': 66867, 'loss/train': 1.1151974201202393} 08/31/2021 01:18:39 - INFO - __main__ - Step 66869: {'lr': 0.00029815826449256985, 'samples': 12838848, 'steps': 66868, 'loss/train': 1.2256717681884766} 08/31/2021 01:18:40 - INFO - __main__ - Step 66870: {'lr': 0.00029815305712811946, 'samples': 12839040, 'steps': 66869, 'loss/train': 1.4676800966262817} 08/31/2021 01:18:40 - INFO - __main__ - Step 66871: {'lr': 0.0002981478497419721, 'samples': 12839232, 'steps': 66870, 'loss/train': 2.0075292587280273} 08/31/2021 01:18:41 - INFO - __main__ - Step 66872: {'lr': 0.00029814264233413, 'samples': 12839424, 'steps': 66871, 'loss/train': 0.8467180132865906} 08/31/2021 01:18:42 - INFO - __main__ - Step 66873: {'lr': 0.00029813743490459565, 'samples': 12839616, 'steps': 66872, 'loss/train': 1.3976972103118896} 08/31/2021 01:18:42 - INFO - __main__ - Step 66874: {'lr': 0.00029813222745337124, 'samples': 12839808, 'steps': 66873, 'loss/train': 0.8895623087882996} 08/31/2021 01:18:43 - INFO - __main__ - Step 66875: {'lr': 0.0002981270199804592, 'samples': 12840000, 'steps': 66874, 'loss/train': 1.1763345003128052} 08/31/2021 01:18:43 - INFO - __main__ - Step 66876: {'lr': 0.00029812181248586194, 'samples': 12840192, 'steps': 66875, 'loss/train': 1.102329134941101} 08/31/2021 01:18:44 - INFO - __main__ - Step 66877: {'lr': 0.0002981166049695817, 'samples': 12840384, 'steps': 66876, 'loss/train': 0.7732347846031189} 08/31/2021 01:18:45 - INFO - __main__ - Step 66878: {'lr': 0.00029811139743162086, 'samples': 12840576, 'steps': 66877, 'loss/train': 1.0742268562316895} 08/31/2021 01:18:45 - INFO - __main__ - Step 66879: {'lr': 0.0002981061898719817, 'samples': 12840768, 'steps': 66878, 'loss/train': 1.3667839765548706} 08/31/2021 01:18:46 - INFO - __main__ - Step 66880: {'lr': 0.00029810098229066676, 'samples': 12840960, 'steps': 66879, 'loss/train': 1.3175114393234253} 08/31/2021 01:18:46 - INFO - __main__ - Step 66881: {'lr': 0.0002980957746876781, 'samples': 12841152, 'steps': 66880, 'loss/train': 1.6963398456573486} 08/31/2021 01:18:46 - INFO - __main__ - Step 66882: {'lr': 0.00029809056706301833, 'samples': 12841344, 'steps': 66881, 'loss/train': 1.2980982065200806} 08/31/2021 01:18:48 - INFO - __main__ - Step 66883: {'lr': 0.00029808535941668973, 'samples': 12841536, 'steps': 66882, 'loss/train': 1.1808865070343018} 08/31/2021 01:18:48 - INFO - __main__ - Step 66884: {'lr': 0.0002980801517486945, 'samples': 12841728, 'steps': 66883, 'loss/train': 1.864681363105774} 08/31/2021 01:18:49 - INFO - __main__ - Step 66885: {'lr': 0.00029807494405903516, 'samples': 12841920, 'steps': 66884, 'loss/train': 1.4782522916793823} 08/31/2021 01:18:49 - INFO - __main__ - Step 66886: {'lr': 0.000298069736347714, 'samples': 12842112, 'steps': 66885, 'loss/train': 1.240394949913025} 08/31/2021 01:18:49 - INFO - __main__ - Step 66887: {'lr': 0.0002980645286147333, 'samples': 12842304, 'steps': 66886, 'loss/train': 1.5596376657485962} 08/31/2021 01:18:51 - INFO - __main__ - Step 66888: {'lr': 0.00029805932086009553, 'samples': 12842496, 'steps': 66887, 'loss/train': 0.1188664510846138} 08/31/2021 01:18:51 - INFO - __main__ - Step 66889: {'lr': 0.00029805411308380297, 'samples': 12842688, 'steps': 66888, 'loss/train': 1.454859733581543} 08/31/2021 01:18:52 - INFO - __main__ - Step 66890: {'lr': 0.0002980489052858579, 'samples': 12842880, 'steps': 66889, 'loss/train': 1.020492672920227} 08/31/2021 01:18:52 - INFO - __main__ - Step 66891: {'lr': 0.0002980436974662628, 'samples': 12843072, 'steps': 66890, 'loss/train': 1.5038830041885376} 08/31/2021 01:18:52 - INFO - __main__ - Step 66892: {'lr': 0.0002980384896250199, 'samples': 12843264, 'steps': 66891, 'loss/train': 1.522275447845459} 08/31/2021 01:18:54 - INFO - __main__ - Step 66893: {'lr': 0.0002980332817621317, 'samples': 12843456, 'steps': 66892, 'loss/train': 1.3033643960952759} 08/31/2021 01:18:54 - INFO - __main__ - Step 66894: {'lr': 0.0002980280738776003, 'samples': 12843648, 'steps': 66893, 'loss/train': 1.3281683921813965} 08/31/2021 01:18:55 - INFO - __main__ - Step 66895: {'lr': 0.0002980228659714283, 'samples': 12843840, 'steps': 66894, 'loss/train': 1.4909989833831787} 08/31/2021 01:18:55 - INFO - __main__ - Step 66896: {'lr': 0.00029801765804361794, 'samples': 12844032, 'steps': 66895, 'loss/train': 1.5445282459259033} 08/31/2021 01:18:55 - INFO - __main__ - Step 66897: {'lr': 0.0002980124500941716, 'samples': 12844224, 'steps': 66896, 'loss/train': 1.2830215692520142} 08/31/2021 01:18:57 - INFO - __main__ - Step 66898: {'lr': 0.0002980072421230914, 'samples': 12844416, 'steps': 66897, 'loss/train': 0.8689067363739014} 08/31/2021 01:18:58 - INFO - __main__ - Step 66899: {'lr': 0.00029800203413038, 'samples': 12844608, 'steps': 66898, 'loss/train': 0.8154518604278564} 08/31/2021 01:18:58 - INFO - __main__ - Step 66900: {'lr': 0.00029799682611603964, 'samples': 12844800, 'steps': 66899, 'loss/train': 1.1743546724319458} 08/31/2021 01:18:58 - INFO - __main__ - Step 66901: {'lr': 0.00029799161808007264, 'samples': 12844992, 'steps': 66900, 'loss/train': 0.20885689556598663} 08/31/2021 01:18:59 - INFO - __main__ - Step 66902: {'lr': 0.0002979864100224813, 'samples': 12845184, 'steps': 66901, 'loss/train': 1.0077096223831177} 08/31/2021 01:18:59 - INFO - __main__ - Step 66903: {'lr': 0.0002979812019432681, 'samples': 12845376, 'steps': 66902, 'loss/train': 1.025418758392334} 08/31/2021 01:19:00 - INFO - __main__ - Step 66904: {'lr': 0.0002979759938424353, 'samples': 12845568, 'steps': 66903, 'loss/train': 0.021742895245552063} 08/31/2021 01:19:01 - INFO - __main__ - Step 66905: {'lr': 0.00029797078571998527, 'samples': 12845760, 'steps': 66904, 'loss/train': 1.7234159708023071} 08/31/2021 01:19:01 - INFO - __main__ - Step 66906: {'lr': 0.0002979655775759202, 'samples': 12845952, 'steps': 66905, 'loss/train': 0.9386310577392578} 08/31/2021 01:19:02 - INFO - __main__ - Step 66907: {'lr': 0.00029796036941024274, 'samples': 12846144, 'steps': 66906, 'loss/train': 1.7891029119491577} 08/31/2021 01:19:02 - INFO - __main__ - Step 66908: {'lr': 0.000297955161222955, 'samples': 12846336, 'steps': 66907, 'loss/train': 0.9810433983802795} 08/31/2021 01:19:02 - INFO - __main__ - Step 66909: {'lr': 0.00029794995301405953, 'samples': 12846528, 'steps': 66908, 'loss/train': 1.3418229818344116} 08/31/2021 01:19:04 - INFO - __main__ - Step 66910: {'lr': 0.0002979447447835584, 'samples': 12846720, 'steps': 66909, 'loss/train': 1.2938421964645386} 08/31/2021 01:19:04 - INFO - __main__ - Step 66911: {'lr': 0.00029793953653145424, 'samples': 12846912, 'steps': 66910, 'loss/train': 1.3185867071151733} 08/31/2021 01:19:05 - INFO - __main__ - Step 66912: {'lr': 0.00029793432825774913, 'samples': 12847104, 'steps': 66911, 'loss/train': 0.9243249297142029} 08/31/2021 01:19:05 - INFO - __main__ - Step 66913: {'lr': 0.0002979291199624456, 'samples': 12847296, 'steps': 66912, 'loss/train': 0.4896719455718994} 08/31/2021 01:19:05 - INFO - __main__ - Step 66914: {'lr': 0.000297923911645546, 'samples': 12847488, 'steps': 66913, 'loss/train': 1.2935611009597778} 08/31/2021 01:19:08 - INFO - __main__ - Step 66915: {'lr': 0.00029791870330705256, 'samples': 12847680, 'steps': 66914, 'loss/train': 1.9248849153518677} 08/31/2021 01:19:08 - INFO - __main__ - Step 66916: {'lr': 0.0002979134949469677, 'samples': 12847872, 'steps': 66915, 'loss/train': 1.1208335161209106} 08/31/2021 01:19:08 - INFO - __main__ - Step 66917: {'lr': 0.00029790828656529384, 'samples': 12848064, 'steps': 66916, 'loss/train': 1.1424239873886108} 08/31/2021 01:19:09 - INFO - __main__ - Step 66918: {'lr': 0.0002979030781620332, 'samples': 12848256, 'steps': 66917, 'loss/train': 1.1392258405685425} 08/31/2021 01:19:09 - INFO - __main__ - Step 66919: {'lr': 0.00029789786973718807, 'samples': 12848448, 'steps': 66918, 'loss/train': 0.24282416701316833} 08/31/2021 01:19:11 - INFO - __main__ - Step 66920: {'lr': 0.000297892661290761, 'samples': 12848640, 'steps': 66919, 'loss/train': 1.8477740287780762} 08/31/2021 01:19:11 - INFO - __main__ - Step 66921: {'lr': 0.0002978874528227542, 'samples': 12848832, 'steps': 66920, 'loss/train': 0.9438933730125427} 08/31/2021 01:19:12 - INFO - __main__ - Step 66922: {'lr': 0.0002978822443331701, 'samples': 12849024, 'steps': 66921, 'loss/train': 1.0634092092514038} 08/31/2021 01:19:12 - INFO - __main__ - Step 66923: {'lr': 0.000297877035822011, 'samples': 12849216, 'steps': 66922, 'loss/train': 2.4748291969299316} 08/31/2021 01:19:13 - INFO - __main__ - Step 66924: {'lr': 0.0002978718272892792, 'samples': 12849408, 'steps': 66923, 'loss/train': 1.5229867696762085} 08/31/2021 01:19:13 - INFO - __main__ - Step 66925: {'lr': 0.00029786661873497714, 'samples': 12849600, 'steps': 66924, 'loss/train': 1.186870813369751} 08/31/2021 01:19:14 - INFO - __main__ - Step 66926: {'lr': 0.00029786141015910705, 'samples': 12849792, 'steps': 66925, 'loss/train': 2.1753625869750977} 08/31/2021 01:19:15 - INFO - __main__ - Step 66927: {'lr': 0.00029785620156167137, 'samples': 12849984, 'steps': 66926, 'loss/train': 1.3050265312194824} 08/31/2021 01:19:15 - INFO - __main__ - Step 66928: {'lr': 0.0002978509929426724, 'samples': 12850176, 'steps': 66927, 'loss/train': 0.5931389331817627} 08/31/2021 01:19:16 - INFO - __main__ - Step 66929: {'lr': 0.00029784578430211255, 'samples': 12850368, 'steps': 66928, 'loss/train': 0.82071852684021} 08/31/2021 01:19:16 - INFO - __main__ - Step 66930: {'lr': 0.0002978405756399942, 'samples': 12850560, 'steps': 66929, 'loss/train': 1.2574752569198608} 08/31/2021 01:19:17 - INFO - __main__ - Step 66931: {'lr': 0.00029783536695631954, 'samples': 12850752, 'steps': 66930, 'loss/train': 1.510852575302124} 08/31/2021 01:19:18 - INFO - __main__ - Step 66932: {'lr': 0.000297830158251091, 'samples': 12850944, 'steps': 66931, 'loss/train': 1.030163288116455} 08/31/2021 01:19:18 - INFO - __main__ - Step 66933: {'lr': 0.00029782494952431093, 'samples': 12851136, 'steps': 66932, 'loss/train': 3.0584919452667236} 08/31/2021 01:19:19 - INFO - __main__ - Step 66934: {'lr': 0.00029781974077598174, 'samples': 12851328, 'steps': 66933, 'loss/train': 1.2814842462539673} 08/31/2021 01:19:19 - INFO - __main__ - Step 66935: {'lr': 0.00029781453200610565, 'samples': 12851520, 'steps': 66934, 'loss/train': 1.4723799228668213} 08/31/2021 01:19:20 - INFO - __main__ - Step 66936: {'lr': 0.0002978093232146851, 'samples': 12851712, 'steps': 66935, 'loss/train': 1.4092057943344116} 08/31/2021 01:19:21 - INFO - __main__ - Step 66937: {'lr': 0.0002978041144017224, 'samples': 12851904, 'steps': 66936, 'loss/train': 1.2618420124053955} 08/31/2021 01:19:21 - INFO - __main__ - Step 66938: {'lr': 0.0002977989055672199, 'samples': 12852096, 'steps': 66937, 'loss/train': 1.448586106300354} 08/31/2021 01:19:22 - INFO - __main__ - Step 66939: {'lr': 0.0002977936967111799, 'samples': 12852288, 'steps': 66938, 'loss/train': 1.2611346244812012} 08/31/2021 01:19:22 - INFO - __main__ - Step 66940: {'lr': 0.00029778848783360484, 'samples': 12852480, 'steps': 66939, 'loss/train': 1.0379679203033447} 08/31/2021 01:19:23 - INFO - __main__ - Step 66941: {'lr': 0.000297783278934497, 'samples': 12852672, 'steps': 66940, 'loss/train': 1.8807241916656494} 08/31/2021 01:19:24 - INFO - __main__ - Step 66942: {'lr': 0.0002977780700138588, 'samples': 12852864, 'steps': 66941, 'loss/train': 1.4803217649459839} 08/31/2021 01:19:24 - INFO - __main__ - Step 66943: {'lr': 0.00029777286107169254, 'samples': 12853056, 'steps': 66942, 'loss/train': 1.7687623500823975} 08/31/2021 01:19:25 - INFO - __main__ - Step 66944: {'lr': 0.00029776765210800057, 'samples': 12853248, 'steps': 66943, 'loss/train': 1.5736079216003418} 08/31/2021 01:19:25 - INFO - __main__ - Step 66945: {'lr': 0.0002977624431227852, 'samples': 12853440, 'steps': 66944, 'loss/train': 1.2501235008239746} 08/31/2021 01:19:25 - INFO - __main__ - Step 66946: {'lr': 0.00029775723411604876, 'samples': 12853632, 'steps': 66945, 'loss/train': 0.360105037689209} 08/31/2021 01:19:27 - INFO - __main__ - Step 66947: {'lr': 0.0002977520250877937, 'samples': 12853824, 'steps': 66946, 'loss/train': 0.7575933337211609} 08/31/2021 01:19:27 - INFO - __main__ - Step 66948: {'lr': 0.0002977468160380224, 'samples': 12854016, 'steps': 66947, 'loss/train': 1.2348713874816895} 08/31/2021 01:19:28 - INFO - __main__ - Step 66949: {'lr': 0.00029774160696673704, 'samples': 12854208, 'steps': 66948, 'loss/train': 1.3413946628570557} 08/31/2021 01:19:28 - INFO - __main__ - Step 66950: {'lr': 0.00029773639787394, 'samples': 12854400, 'steps': 66949, 'loss/train': 1.4753596782684326} 08/31/2021 01:19:28 - INFO - __main__ - Step 66951: {'lr': 0.0002977311887596337, 'samples': 12854592, 'steps': 66950, 'loss/train': 0.9712883830070496} 08/31/2021 01:19:30 - INFO - __main__ - Step 66952: {'lr': 0.0002977259796238205, 'samples': 12854784, 'steps': 66951, 'loss/train': 1.3430200815200806} 08/31/2021 01:19:31 - INFO - __main__ - Step 66953: {'lr': 0.00029772077046650273, 'samples': 12854976, 'steps': 66952, 'loss/train': 1.3880642652511597} 08/31/2021 01:19:31 - INFO - __main__ - Step 66954: {'lr': 0.00029771556128768266, 'samples': 12855168, 'steps': 66953, 'loss/train': 1.1368135213851929} 08/31/2021 01:19:32 - INFO - __main__ - Step 66955: {'lr': 0.00029771035208736276, 'samples': 12855360, 'steps': 66954, 'loss/train': 0.9716967344284058} 08/31/2021 01:19:32 - INFO - __main__ - Step 66956: {'lr': 0.00029770514286554524, 'samples': 12855552, 'steps': 66955, 'loss/train': 0.11081194877624512} 08/31/2021 01:19:32 - INFO - __main__ - Step 66957: {'lr': 0.0002976999336222326, 'samples': 12855744, 'steps': 66956, 'loss/train': 0.11166037619113922} 08/31/2021 01:19:34 - INFO - __main__ - Step 66958: {'lr': 0.000297694724357427, 'samples': 12855936, 'steps': 66957, 'loss/train': 1.5337371826171875} 08/31/2021 01:19:34 - INFO - __main__ - Step 66959: {'lr': 0.000297689515071131, 'samples': 12856128, 'steps': 66958, 'loss/train': 1.1040167808532715} 08/31/2021 01:19:35 - INFO - __main__ - Step 66960: {'lr': 0.00029768430576334676, 'samples': 12856320, 'steps': 66959, 'loss/train': 1.955173373222351} 08/31/2021 01:19:35 - INFO - __main__ - Step 66961: {'lr': 0.0002976790964340768, 'samples': 12856512, 'steps': 66960, 'loss/train': 1.180368423461914} 08/31/2021 01:19:35 - INFO - __main__ - Step 66962: {'lr': 0.00029767388708332323, 'samples': 12856704, 'steps': 66961, 'loss/train': 1.3541319370269775} 08/31/2021 01:19:37 - INFO - __main__ - Step 66963: {'lr': 0.00029766867771108865, 'samples': 12856896, 'steps': 66962, 'loss/train': 0.611372172832489} 08/31/2021 01:19:37 - INFO - __main__ - Step 66964: {'lr': 0.00029766346831737526, 'samples': 12857088, 'steps': 66963, 'loss/train': 1.6876871585845947} 08/31/2021 01:19:38 - INFO - __main__ - Step 66965: {'lr': 0.0002976582589021855, 'samples': 12857280, 'steps': 66964, 'loss/train': 1.6059099435806274} 08/31/2021 01:19:38 - INFO - __main__ - Step 66966: {'lr': 0.0002976530494655216, 'samples': 12857472, 'steps': 66965, 'loss/train': 1.3068475723266602} 08/31/2021 01:19:38 - INFO - __main__ - Step 66967: {'lr': 0.000297647840007386, 'samples': 12857664, 'steps': 66966, 'loss/train': 0.4375608265399933} 08/31/2021 01:19:40 - INFO - __main__ - Step 66968: {'lr': 0.000297642630527781, 'samples': 12857856, 'steps': 66967, 'loss/train': 1.5038422346115112} 08/31/2021 01:19:41 - INFO - __main__ - Step 66969: {'lr': 0.000297637421026709, 'samples': 12858048, 'steps': 66968, 'loss/train': 1.0588759183883667} 08/31/2021 01:19:41 - INFO - __main__ - Step 66970: {'lr': 0.0002976322115041723, 'samples': 12858240, 'steps': 66969, 'loss/train': 1.0717089176177979} 08/31/2021 01:19:42 - INFO - __main__ - Step 66971: {'lr': 0.00029762700196017325, 'samples': 12858432, 'steps': 66970, 'loss/train': 1.1834946870803833} 08/31/2021 01:19:42 - INFO - __main__ - Step 66972: {'lr': 0.0002976217923947142, 'samples': 12858624, 'steps': 66971, 'loss/train': 1.7217684984207153} 08/31/2021 01:19:43 - INFO - __main__ - Step 66973: {'lr': 0.0002976165828077975, 'samples': 12858816, 'steps': 66972, 'loss/train': 1.1152746677398682} 08/31/2021 01:19:44 - INFO - __main__ - Step 66974: {'lr': 0.0002976113731994255, 'samples': 12859008, 'steps': 66973, 'loss/train': 0.9818087816238403} 08/31/2021 01:19:44 - INFO - __main__ - Step 66975: {'lr': 0.0002976061635696006, 'samples': 12859200, 'steps': 66974, 'loss/train': 1.286996603012085} 08/31/2021 01:19:45 - INFO - __main__ - Step 66976: {'lr': 0.00029760095391832505, 'samples': 12859392, 'steps': 66975, 'loss/train': 0.6949533820152283} 08/31/2021 01:19:45 - INFO - __main__ - Step 66977: {'lr': 0.00029759574424560134, 'samples': 12859584, 'steps': 66976, 'loss/train': 1.9749059677124023} 08/31/2021 01:19:45 - INFO - __main__ - Step 66978: {'lr': 0.0002975905345514316, 'samples': 12859776, 'steps': 66977, 'loss/train': 0.1618361920118332} 08/31/2021 01:19:47 - INFO - __main__ - Step 66979: {'lr': 0.00029758532483581835, 'samples': 12859968, 'steps': 66978, 'loss/train': 1.24375319480896} 08/31/2021 01:19:47 - INFO - __main__ - Step 66980: {'lr': 0.00029758011509876383, 'samples': 12860160, 'steps': 66979, 'loss/train': 1.6563459634780884} 08/31/2021 01:19:48 - INFO - __main__ - Step 66981: {'lr': 0.00029757490534027046, 'samples': 12860352, 'steps': 66980, 'loss/train': 1.08072829246521} 08/31/2021 01:19:48 - INFO - __main__ - Step 66982: {'lr': 0.00029756969556034063, 'samples': 12860544, 'steps': 66981, 'loss/train': 1.112642765045166} 08/31/2021 01:19:49 - INFO - __main__ - Step 66983: {'lr': 0.00029756448575897666, 'samples': 12860736, 'steps': 66982, 'loss/train': 1.1083557605743408} 08/31/2021 01:19:50 - INFO - __main__ - Step 66984: {'lr': 0.00029755927593618083, 'samples': 12860928, 'steps': 66983, 'loss/train': 0.7727072834968567} 08/31/2021 01:19:51 - INFO - __main__ - Step 66985: {'lr': 0.0002975540660919555, 'samples': 12861120, 'steps': 66984, 'loss/train': 1.0062907934188843} 08/31/2021 01:19:51 - INFO - __main__ - Step 66986: {'lr': 0.000297548856226303, 'samples': 12861312, 'steps': 66985, 'loss/train': 1.5398635864257812} 08/31/2021 01:19:51 - INFO - __main__ - Step 66987: {'lr': 0.0002975436463392258, 'samples': 12861504, 'steps': 66986, 'loss/train': 1.086190104484558} 08/31/2021 01:19:52 - INFO - __main__ - Step 66988: {'lr': 0.0002975384364307261, 'samples': 12861696, 'steps': 66987, 'loss/train': 0.4397985637187958} 08/31/2021 01:19:53 - INFO - __main__ - Step 66989: {'lr': 0.00029753322650080634, 'samples': 12861888, 'steps': 66988, 'loss/train': 1.1122337579727173} 08/31/2021 01:19:54 - INFO - __main__ - Step 66990: {'lr': 0.00029752801654946886, 'samples': 12862080, 'steps': 66989, 'loss/train': 0.054766811430454254} 08/31/2021 01:19:54 - INFO - __main__ - Step 66991: {'lr': 0.000297522806576716, 'samples': 12862272, 'steps': 66990, 'loss/train': 1.643615961074829} 08/31/2021 01:19:55 - INFO - __main__ - Step 66992: {'lr': 0.0002975175965825501, 'samples': 12862464, 'steps': 66991, 'loss/train': 1.285048246383667} 08/31/2021 01:19:55 - INFO - __main__ - Step 66993: {'lr': 0.0002975123865669734, 'samples': 12862656, 'steps': 66992, 'loss/train': 1.4134382009506226} 08/31/2021 01:19:56 - INFO - __main__ - Step 66994: {'lr': 0.00029750717652998846, 'samples': 12862848, 'steps': 66993, 'loss/train': 1.6476378440856934} 08/31/2021 01:19:57 - INFO - __main__ - Step 66995: {'lr': 0.00029750196647159745, 'samples': 12863040, 'steps': 66994, 'loss/train': 0.5705776214599609} 08/31/2021 01:19:57 - INFO - __main__ - Step 66996: {'lr': 0.00029749675639180283, 'samples': 12863232, 'steps': 66995, 'loss/train': 0.5513965487480164} 08/31/2021 01:19:57 - INFO - __main__ - Step 66997: {'lr': 0.0002974915462906069, 'samples': 12863424, 'steps': 66996, 'loss/train': 1.8614526987075806} 08/31/2021 01:19:58 - INFO - __main__ - Step 66998: {'lr': 0.00029748633616801206, 'samples': 12863616, 'steps': 66997, 'loss/train': 1.289076328277588} 08/31/2021 01:19:59 - INFO - __main__ - Step 66999: {'lr': 0.00029748112602402053, 'samples': 12863808, 'steps': 66998, 'loss/train': 0.7560307383537292} 08/31/2021 01:20:00 - INFO - __main__ - Step 67000: {'lr': 0.00029747591585863476, 'samples': 12864000, 'steps': 66999, 'loss/train': 2.114107847213745} 08/31/2021 01:20:00 - INFO - __main__ - Step 67001: {'lr': 0.0002974707056718571, 'samples': 12864192, 'steps': 67000, 'loss/train': 1.24894380569458} 08/31/2021 01:20:00 - INFO - __main__ - Step 67002: {'lr': 0.00029746549546368984, 'samples': 12864384, 'steps': 67001, 'loss/train': 0.6127899289131165} 08/31/2021 01:20:01 - INFO - __main__ - Step 67003: {'lr': 0.0002974602852341354, 'samples': 12864576, 'steps': 67002, 'loss/train': 1.1805307865142822} 08/31/2021 01:20:03 - INFO - __main__ - Step 67004: {'lr': 0.00029745507498319605, 'samples': 12864768, 'steps': 67003, 'loss/train': 1.6920961141586304} 08/31/2021 01:20:03 - INFO - __main__ - Step 67005: {'lr': 0.0002974498647108742, 'samples': 12864960, 'steps': 67004, 'loss/train': 1.1887695789337158} 08/31/2021 01:20:03 - INFO - __main__ - Step 67006: {'lr': 0.00029744465441717215, 'samples': 12865152, 'steps': 67005, 'loss/train': 0.1399640142917633} 08/31/2021 01:20:04 - INFO - __main__ - Step 67007: {'lr': 0.00029743944410209227, 'samples': 12865344, 'steps': 67006, 'loss/train': 1.4024311304092407} 08/31/2021 01:20:04 - INFO - __main__ - Step 67008: {'lr': 0.00029743423376563696, 'samples': 12865536, 'steps': 67007, 'loss/train': 0.8827478289604187} 08/31/2021 01:20:05 - INFO - __main__ - Step 67009: {'lr': 0.00029742902340780845, 'samples': 12865728, 'steps': 67008, 'loss/train': 1.2762292623519897} 08/31/2021 01:20:06 - INFO - __main__ - Step 67010: {'lr': 0.00029742381302860923, 'samples': 12865920, 'steps': 67009, 'loss/train': 1.3688523769378662} 08/31/2021 01:20:07 - INFO - __main__ - Step 67011: {'lr': 0.0002974186026280415, 'samples': 12866112, 'steps': 67010, 'loss/train': 0.9956218004226685} 08/31/2021 01:20:07 - INFO - __main__ - Step 67012: {'lr': 0.0002974133922061077, 'samples': 12866304, 'steps': 67011, 'loss/train': 0.9253025054931641} 08/31/2021 01:20:07 - INFO - __main__ - Step 67013: {'lr': 0.00029740818176281013, 'samples': 12866496, 'steps': 67012, 'loss/train': 1.555445671081543} 08/31/2021 01:20:08 - INFO - __main__ - Step 67014: {'lr': 0.0002974029712981512, 'samples': 12866688, 'steps': 67013, 'loss/train': 0.7399852871894836} 08/31/2021 01:20:09 - INFO - __main__ - Step 67015: {'lr': 0.0002973977608121332, 'samples': 12866880, 'steps': 67014, 'loss/train': 0.048610761761665344} 08/31/2021 01:20:10 - INFO - __main__ - Step 67016: {'lr': 0.0002973925503047585, 'samples': 12867072, 'steps': 67015, 'loss/train': 1.2430057525634766} 08/31/2021 01:20:10 - INFO - __main__ - Step 67017: {'lr': 0.00029738733977602955, 'samples': 12867264, 'steps': 67016, 'loss/train': 1.3832236528396606} 08/31/2021 01:20:10 - INFO - __main__ - Step 67018: {'lr': 0.0002973821292259485, 'samples': 12867456, 'steps': 67017, 'loss/train': 1.525444746017456} 08/31/2021 01:20:11 - INFO - __main__ - Step 67019: {'lr': 0.0002973769186545178, 'samples': 12867648, 'steps': 67018, 'loss/train': 0.6412503719329834} 08/31/2021 01:20:12 - INFO - __main__ - Step 67020: {'lr': 0.0002973717080617398, 'samples': 12867840, 'steps': 67019, 'loss/train': 1.094258189201355} 08/31/2021 01:20:13 - INFO - __main__ - Step 67021: {'lr': 0.00029736649744761687, 'samples': 12868032, 'steps': 67020, 'loss/train': 1.6158090829849243} 08/31/2021 01:20:13 - INFO - __main__ - Step 67022: {'lr': 0.00029736128681215123, 'samples': 12868224, 'steps': 67021, 'loss/train': 0.03755970299243927} 08/31/2021 01:20:13 - INFO - __main__ - Step 67023: {'lr': 0.00029735607615534535, 'samples': 12868416, 'steps': 67022, 'loss/train': 1.2244937419891357} 08/31/2021 01:20:14 - INFO - __main__ - Step 67024: {'lr': 0.00029735086547720167, 'samples': 12868608, 'steps': 67023, 'loss/train': 1.0821040868759155} 08/31/2021 01:20:16 - INFO - __main__ - Step 67025: {'lr': 0.00029734565477772235, 'samples': 12868800, 'steps': 67024, 'loss/train': 1.2710294723510742} 08/31/2021 01:20:16 - INFO - __main__ - Step 67026: {'lr': 0.0002973404440569098, 'samples': 12868992, 'steps': 67025, 'loss/train': 1.4979480504989624} 08/31/2021 01:20:17 - INFO - __main__ - Step 67027: {'lr': 0.00029733523331476635, 'samples': 12869184, 'steps': 67026, 'loss/train': 0.1029643788933754} 08/31/2021 01:20:17 - INFO - __main__ - Step 67028: {'lr': 0.00029733002255129444, 'samples': 12869376, 'steps': 67027, 'loss/train': 1.5740405321121216} 08/31/2021 01:20:17 - INFO - __main__ - Step 67029: {'lr': 0.00029732481176649627, 'samples': 12869568, 'steps': 67028, 'loss/train': 1.1500892639160156} 08/31/2021 01:20:19 - INFO - __main__ - Step 67030: {'lr': 0.00029731960096037434, 'samples': 12869760, 'steps': 67029, 'loss/train': 1.0586161613464355} 08/31/2021 01:20:19 - INFO - __main__ - Step 67031: {'lr': 0.0002973143901329309, 'samples': 12869952, 'steps': 67030, 'loss/train': 1.2469881772994995} 08/31/2021 01:20:20 - INFO - __main__ - Step 67032: {'lr': 0.00029730917928416834, 'samples': 12870144, 'steps': 67031, 'loss/train': 0.9209446310997009} 08/31/2021 01:20:20 - INFO - __main__ - Step 67033: {'lr': 0.00029730396841408895, 'samples': 12870336, 'steps': 67032, 'loss/train': 0.8209173083305359} 08/31/2021 01:20:20 - INFO - __main__ - Step 67034: {'lr': 0.0002972987575226952, 'samples': 12870528, 'steps': 67033, 'loss/train': 1.4850705862045288} 08/31/2021 01:20:22 - INFO - __main__ - Step 67035: {'lr': 0.00029729354660998933, 'samples': 12870720, 'steps': 67034, 'loss/train': 0.9378286004066467} 08/31/2021 01:20:22 - INFO - __main__ - Step 67036: {'lr': 0.0002972883356759736, 'samples': 12870912, 'steps': 67035, 'loss/train': 1.1645989418029785} 08/31/2021 01:20:23 - INFO - __main__ - Step 67037: {'lr': 0.00029728312472065066, 'samples': 12871104, 'steps': 67036, 'loss/train': 1.6403316259384155} 08/31/2021 01:20:23 - INFO - __main__ - Step 67038: {'lr': 0.0002972779137440226, 'samples': 12871296, 'steps': 67037, 'loss/train': 1.3138209581375122} 08/31/2021 01:20:23 - INFO - __main__ - Step 67039: {'lr': 0.0002972727027460918, 'samples': 12871488, 'steps': 67038, 'loss/train': 2.217129945755005} 08/31/2021 01:20:25 - INFO - __main__ - Step 67040: {'lr': 0.00029726749172686066, 'samples': 12871680, 'steps': 67039, 'loss/train': 0.6684144735336304} 08/31/2021 01:20:25 - INFO - __main__ - Step 67041: {'lr': 0.00029726228068633156, 'samples': 12871872, 'steps': 67040, 'loss/train': 0.5806643962860107} 08/31/2021 01:20:26 - INFO - __main__ - Step 67042: {'lr': 0.0002972570696245068, 'samples': 12872064, 'steps': 67041, 'loss/train': 1.037682294845581} 08/31/2021 01:20:26 - INFO - __main__ - Step 67043: {'lr': 0.0002972518585413887, 'samples': 12872256, 'steps': 67042, 'loss/train': 1.3713310956954956} 08/31/2021 01:20:26 - INFO - __main__ - Step 67044: {'lr': 0.0002972466474369797, 'samples': 12872448, 'steps': 67043, 'loss/train': 1.3022724390029907} 08/31/2021 01:20:27 - INFO - __main__ - Step 67045: {'lr': 0.00029724143631128203, 'samples': 12872640, 'steps': 67044, 'loss/train': 1.4938738346099854} 08/31/2021 01:20:28 - INFO - __main__ - Step 67046: {'lr': 0.0002972362251642981, 'samples': 12872832, 'steps': 67045, 'loss/train': 1.9854189157485962} 08/31/2021 01:20:29 - INFO - __main__ - Step 67047: {'lr': 0.0002972310139960303, 'samples': 12873024, 'steps': 67046, 'loss/train': 1.3464194536209106} 08/31/2021 01:20:29 - INFO - __main__ - Step 67048: {'lr': 0.0002972258028064809, 'samples': 12873216, 'steps': 67047, 'loss/train': 1.4101618528366089} 08/31/2021 01:20:29 - INFO - __main__ - Step 67049: {'lr': 0.0002972205915956523, 'samples': 12873408, 'steps': 67048, 'loss/train': 0.9585720896720886} 08/31/2021 01:20:30 - INFO - __main__ - Step 67050: {'lr': 0.0002972153803635468, 'samples': 12873600, 'steps': 67049, 'loss/train': 0.6798101663589478} 08/31/2021 01:20:31 - INFO - __main__ - Step 67051: {'lr': 0.00029721016911016685, 'samples': 12873792, 'steps': 67050, 'loss/train': 1.4037163257598877} 08/31/2021 01:20:32 - INFO - __main__ - Step 67052: {'lr': 0.00029720495783551465, 'samples': 12873984, 'steps': 67051, 'loss/train': 1.4620639085769653} 08/31/2021 01:20:32 - INFO - __main__ - Step 67053: {'lr': 0.0002971997465395926, 'samples': 12874176, 'steps': 67052, 'loss/train': 1.2347787618637085} 08/31/2021 01:20:32 - INFO - __main__ - Step 67054: {'lr': 0.00029719453522240316, 'samples': 12874368, 'steps': 67053, 'loss/train': 1.5888503789901733} 08/31/2021 01:20:33 - INFO - __main__ - Step 67055: {'lr': 0.00029718932388394853, 'samples': 12874560, 'steps': 67054, 'loss/train': 1.2724056243896484} 08/31/2021 01:20:34 - INFO - __main__ - Step 67056: {'lr': 0.0002971841125242312, 'samples': 12874752, 'steps': 67055, 'loss/train': 0.7765518426895142} 08/31/2021 01:20:35 - INFO - __main__ - Step 67057: {'lr': 0.0002971789011432534, 'samples': 12874944, 'steps': 67056, 'loss/train': 1.3155969381332397} 08/31/2021 01:20:35 - INFO - __main__ - Step 67058: {'lr': 0.0002971736897410174, 'samples': 12875136, 'steps': 67057, 'loss/train': 0.7036265730857849} 08/31/2021 01:20:36 - INFO - __main__ - Step 67059: {'lr': 0.0002971684783175258, 'samples': 12875328, 'steps': 67058, 'loss/train': 1.2751851081848145} 08/31/2021 01:20:36 - INFO - __main__ - Step 67060: {'lr': 0.0002971632668727808, 'samples': 12875520, 'steps': 67059, 'loss/train': 0.4763600826263428} 08/31/2021 01:20:38 - INFO - __main__ - Step 67061: {'lr': 0.0002971580554067847, 'samples': 12875712, 'steps': 67060, 'loss/train': 0.10931190848350525} 08/31/2021 01:20:38 - INFO - __main__ - Step 67062: {'lr': 0.0002971528439195399, 'samples': 12875904, 'steps': 67061, 'loss/train': 1.3713198900222778} 08/31/2021 01:20:38 - INFO - __main__ - Step 67063: {'lr': 0.0002971476324110488, 'samples': 12876096, 'steps': 67062, 'loss/train': 0.723401665687561} 08/31/2021 01:20:39 - INFO - __main__ - Step 67064: {'lr': 0.0002971424208813137, 'samples': 12876288, 'steps': 67063, 'loss/train': 1.411474585533142} 08/31/2021 01:20:39 - INFO - __main__ - Step 67065: {'lr': 0.00029713720933033697, 'samples': 12876480, 'steps': 67064, 'loss/train': 1.1257280111312866} 08/31/2021 01:20:39 - INFO - __main__ - Step 67066: {'lr': 0.00029713199775812093, 'samples': 12876672, 'steps': 67065, 'loss/train': 0.03626011312007904} 08/31/2021 01:20:41 - INFO - __main__ - Step 67067: {'lr': 0.0002971267861646679, 'samples': 12876864, 'steps': 67066, 'loss/train': 1.6475043296813965} 08/31/2021 01:20:41 - INFO - __main__ - Step 67068: {'lr': 0.0002971215745499803, 'samples': 12877056, 'steps': 67067, 'loss/train': 0.33451738953590393} 08/31/2021 01:20:42 - INFO - __main__ - Step 67069: {'lr': 0.0002971163629140604, 'samples': 12877248, 'steps': 67068, 'loss/train': 1.5003925561904907} 08/31/2021 01:20:42 - INFO - __main__ - Step 67070: {'lr': 0.00029711115125691066, 'samples': 12877440, 'steps': 67069, 'loss/train': 1.589120626449585} 08/31/2021 01:20:42 - INFO - __main__ - Step 67071: {'lr': 0.0002971059395785334, 'samples': 12877632, 'steps': 67070, 'loss/train': 1.7128506898880005} 08/31/2021 01:20:44 - INFO - __main__ - Step 67072: {'lr': 0.0002971007278789308, 'samples': 12877824, 'steps': 67071, 'loss/train': 1.0157474279403687} 08/31/2021 01:20:44 - INFO - __main__ - Step 67073: {'lr': 0.00029709551615810545, 'samples': 12878016, 'steps': 67072, 'loss/train': 0.26563286781311035} 08/31/2021 01:20:45 - INFO - __main__ - Step 67074: {'lr': 0.00029709030441605954, 'samples': 12878208, 'steps': 67073, 'loss/train': 1.2315056324005127} 08/31/2021 01:20:45 - INFO - __main__ - Step 67075: {'lr': 0.0002970850926527954, 'samples': 12878400, 'steps': 67074, 'loss/train': 1.0132856369018555} 08/31/2021 01:20:45 - INFO - __main__ - Step 67076: {'lr': 0.0002970798808683156, 'samples': 12878592, 'steps': 67075, 'loss/train': 1.1228145360946655} 08/31/2021 01:20:47 - INFO - __main__ - Step 67077: {'lr': 0.00029707466906262224, 'samples': 12878784, 'steps': 67076, 'loss/train': 0.9170123934745789} 08/31/2021 01:20:48 - INFO - __main__ - Step 67078: {'lr': 0.0002970694572357178, 'samples': 12878976, 'steps': 67077, 'loss/train': 0.8674792051315308} 08/31/2021 01:20:48 - INFO - __main__ - Step 67079: {'lr': 0.00029706424538760454, 'samples': 12879168, 'steps': 67078, 'loss/train': 1.3322120904922485} 08/31/2021 01:20:49 - INFO - __main__ - Step 67080: {'lr': 0.00029705903351828484, 'samples': 12879360, 'steps': 67079, 'loss/train': 0.7783786058425903} 08/31/2021 01:20:49 - INFO - __main__ - Step 67081: {'lr': 0.0002970538216277611, 'samples': 12879552, 'steps': 67080, 'loss/train': 1.6893784999847412} 08/31/2021 01:20:51 - INFO - __main__ - Step 67082: {'lr': 0.00029704860971603564, 'samples': 12879744, 'steps': 67081, 'loss/train': 1.0893957614898682} 08/31/2021 01:20:51 - INFO - __main__ - Step 67083: {'lr': 0.0002970433977831108, 'samples': 12879936, 'steps': 67082, 'loss/train': 1.323053002357483} 08/31/2021 01:20:51 - INFO - __main__ - Step 67084: {'lr': 0.0002970381858289889, 'samples': 12880128, 'steps': 67083, 'loss/train': 1.4866057634353638} 08/31/2021 01:20:52 - INFO - __main__ - Step 67085: {'lr': 0.0002970329738536723, 'samples': 12880320, 'steps': 67084, 'loss/train': 1.0056614875793457} 08/31/2021 01:20:52 - INFO - __main__ - Step 67086: {'lr': 0.00029702776185716346, 'samples': 12880512, 'steps': 67085, 'loss/train': 0.08844929188489914} 08/31/2021 01:20:53 - INFO - __main__ - Step 67087: {'lr': 0.0002970225498394646, 'samples': 12880704, 'steps': 67086, 'loss/train': 1.0192879438400269} 08/31/2021 01:20:55 - INFO - __main__ - Step 67088: {'lr': 0.00029701733780057815, 'samples': 12880896, 'steps': 67087, 'loss/train': 1.6145986318588257} 08/31/2021 01:20:55 - INFO - __main__ - Step 67089: {'lr': 0.00029701212574050637, 'samples': 12881088, 'steps': 67088, 'loss/train': 1.3170959949493408} 08/31/2021 01:20:55 - INFO - __main__ - Step 67090: {'lr': 0.0002970069136592516, 'samples': 12881280, 'steps': 67089, 'loss/train': 1.1686134338378906} 08/31/2021 01:20:56 - INFO - __main__ - Step 67091: {'lr': 0.00029700170155681625, 'samples': 12881472, 'steps': 67090, 'loss/train': 1.1470987796783447} 08/31/2021 01:20:56 - INFO - __main__ - Step 67092: {'lr': 0.0002969964894332027, 'samples': 12881664, 'steps': 67091, 'loss/train': 1.0545759201049805} 08/31/2021 01:20:57 - INFO - __main__ - Step 67093: {'lr': 0.0002969912772884133, 'samples': 12881856, 'steps': 67092, 'loss/train': 0.759925127029419} 08/31/2021 01:20:58 - INFO - __main__ - Step 67094: {'lr': 0.0002969860651224503, 'samples': 12882048, 'steps': 67093, 'loss/train': 1.213994026184082} 08/31/2021 01:20:58 - INFO - __main__ - Step 67095: {'lr': 0.0002969808529353161, 'samples': 12882240, 'steps': 67094, 'loss/train': 0.920197606086731} 08/31/2021 01:20:59 - INFO - __main__ - Step 67096: {'lr': 0.000296975640727013, 'samples': 12882432, 'steps': 67095, 'loss/train': 0.8949924111366272} 08/31/2021 01:20:59 - INFO - __main__ - Step 67097: {'lr': 0.00029697042849754346, 'samples': 12882624, 'steps': 67096, 'loss/train': 1.5670857429504395} 08/31/2021 01:21:01 - INFO - __main__ - Step 67098: {'lr': 0.0002969652162469098, 'samples': 12882816, 'steps': 67097, 'loss/train': 0.9668014645576477} 08/31/2021 01:21:01 - INFO - __main__ - Step 67099: {'lr': 0.0002969600039751143, 'samples': 12883008, 'steps': 67098, 'loss/train': 1.5061118602752686} 08/31/2021 01:21:01 - INFO - __main__ - Step 67100: {'lr': 0.0002969547916821593, 'samples': 12883200, 'steps': 67099, 'loss/train': 1.4360418319702148} 08/31/2021 01:21:02 - INFO - __main__ - Step 67101: {'lr': 0.00029694957936804726, 'samples': 12883392, 'steps': 67100, 'loss/train': 1.1947853565216064} 08/31/2021 01:21:02 - INFO - __main__ - Step 67102: {'lr': 0.0002969443670327805, 'samples': 12883584, 'steps': 67101, 'loss/train': 1.5724467039108276} 08/31/2021 01:21:02 - INFO - __main__ - Step 67103: {'lr': 0.0002969391546763612, 'samples': 12883776, 'steps': 67102, 'loss/train': 1.1097766160964966} 08/31/2021 01:21:04 - INFO - __main__ - Step 67104: {'lr': 0.000296933942298792, 'samples': 12883968, 'steps': 67103, 'loss/train': 1.3276187181472778} 08/31/2021 01:21:04 - INFO - __main__ - Step 67105: {'lr': 0.000296928729900075, 'samples': 12884160, 'steps': 67104, 'loss/train': 1.778512954711914} 08/31/2021 01:21:05 - INFO - __main__ - Step 67106: {'lr': 0.0002969235174802127, 'samples': 12884352, 'steps': 67105, 'loss/train': 1.1825752258300781} 08/31/2021 01:21:05 - INFO - __main__ - Step 67107: {'lr': 0.0002969183050392073, 'samples': 12884544, 'steps': 67106, 'loss/train': 1.4804391860961914} 08/31/2021 01:21:05 - INFO - __main__ - Step 67108: {'lr': 0.0002969130925770613, 'samples': 12884736, 'steps': 67107, 'loss/train': 1.4835723638534546} 08/31/2021 01:21:07 - INFO - __main__ - Step 67109: {'lr': 0.00029690788009377694, 'samples': 12884928, 'steps': 67108, 'loss/train': 0.9987737536430359} 08/31/2021 01:21:07 - INFO - __main__ - Step 67110: {'lr': 0.0002969026675893566, 'samples': 12885120, 'steps': 67109, 'loss/train': 1.2363098859786987} 08/31/2021 01:21:07 - INFO - __main__ - Step 67111: {'lr': 0.00029689745506380273, 'samples': 12885312, 'steps': 67110, 'loss/train': 0.5830304026603699} 08/31/2021 01:21:08 - INFO - __main__ - Step 67112: {'lr': 0.00029689224251711754, 'samples': 12885504, 'steps': 67111, 'loss/train': 1.4072409868240356} 08/31/2021 01:21:08 - INFO - __main__ - Step 67113: {'lr': 0.0002968870299493034, 'samples': 12885696, 'steps': 67112, 'loss/train': 1.2606875896453857} 08/31/2021 01:21:10 - INFO - __main__ - Step 67114: {'lr': 0.00029688181736036275, 'samples': 12885888, 'steps': 67113, 'loss/train': 0.958053469657898} 08/31/2021 01:21:10 - INFO - __main__ - Step 67115: {'lr': 0.0002968766047502978, 'samples': 12886080, 'steps': 67114, 'loss/train': 1.4018117189407349} 08/31/2021 01:21:10 - INFO - __main__ - Step 67116: {'lr': 0.00029687139211911104, 'samples': 12886272, 'steps': 67115, 'loss/train': 1.2760132551193237} 08/31/2021 01:21:11 - INFO - __main__ - Step 67117: {'lr': 0.0002968661794668047, 'samples': 12886464, 'steps': 67116, 'loss/train': 0.9158856272697449} 08/31/2021 01:21:11 - INFO - __main__ - Step 67118: {'lr': 0.0002968609667933813, 'samples': 12886656, 'steps': 67117, 'loss/train': 1.2488019466400146} 08/31/2021 01:21:13 - INFO - __main__ - Step 67119: {'lr': 0.0002968557540988429, 'samples': 12886848, 'steps': 67118, 'loss/train': 0.87434983253479} 08/31/2021 01:21:13 - INFO - __main__ - Step 67120: {'lr': 0.0002968505413831921, 'samples': 12887040, 'steps': 67119, 'loss/train': 1.610935926437378} 08/31/2021 01:21:13 - INFO - __main__ - Step 67121: {'lr': 0.0002968453286464312, 'samples': 12887232, 'steps': 67120, 'loss/train': 0.7276598811149597} 08/31/2021 01:21:14 - INFO - __main__ - Step 67122: {'lr': 0.00029684011588856246, 'samples': 12887424, 'steps': 67121, 'loss/train': 0.5146053433418274} 08/31/2021 01:21:14 - INFO - __main__ - Step 67123: {'lr': 0.0002968349031095883, 'samples': 12887616, 'steps': 67122, 'loss/train': 1.1072075366973877} 08/31/2021 01:21:16 - INFO - __main__ - Step 67124: {'lr': 0.0002968296903095111, 'samples': 12887808, 'steps': 67123, 'loss/train': 1.2438184022903442} 08/31/2021 01:21:16 - INFO - __main__ - Step 67125: {'lr': 0.00029682447748833316, 'samples': 12888000, 'steps': 67124, 'loss/train': 0.9545401334762573} 08/31/2021 01:21:16 - INFO - __main__ - Step 67126: {'lr': 0.0002968192646460568, 'samples': 12888192, 'steps': 67125, 'loss/train': 0.590844988822937} 08/31/2021 01:21:17 - INFO - __main__ - Step 67127: {'lr': 0.0002968140517826844, 'samples': 12888384, 'steps': 67126, 'loss/train': 1.6578930616378784} 08/31/2021 01:21:17 - INFO - __main__ - Step 67128: {'lr': 0.00029680883889821833, 'samples': 12888576, 'steps': 67127, 'loss/train': 1.647874116897583} 08/31/2021 01:21:19 - INFO - __main__ - Step 67129: {'lr': 0.0002968036259926609, 'samples': 12888768, 'steps': 67128, 'loss/train': 0.915919840335846} 08/31/2021 01:21:19 - INFO - __main__ - Step 67130: {'lr': 0.00029679841306601447, 'samples': 12888960, 'steps': 67129, 'loss/train': 1.0962798595428467} 08/31/2021 01:21:20 - INFO - __main__ - Step 67131: {'lr': 0.0002967932001182815, 'samples': 12889152, 'steps': 67130, 'loss/train': 1.2301462888717651} 08/31/2021 01:21:20 - INFO - __main__ - Step 67132: {'lr': 0.0002967879871494641, 'samples': 12889344, 'steps': 67131, 'loss/train': 1.2720783948898315} 08/31/2021 01:21:20 - INFO - __main__ - Step 67133: {'lr': 0.00029678277415956484, 'samples': 12889536, 'steps': 67132, 'loss/train': 0.9503430128097534} 08/31/2021 01:21:21 - INFO - __main__ - Step 67134: {'lr': 0.0002967775611485859, 'samples': 12889728, 'steps': 67133, 'loss/train': 0.8263628482818604} 08/31/2021 01:21:23 - INFO - __main__ - Step 67135: {'lr': 0.00029677234811652974, 'samples': 12889920, 'steps': 67134, 'loss/train': 1.5656658411026} 08/31/2021 01:21:23 - INFO - __main__ - Step 67136: {'lr': 0.00029676713506339875, 'samples': 12890112, 'steps': 67135, 'loss/train': 1.699737548828125} 08/31/2021 01:21:24 - INFO - __main__ - Step 67137: {'lr': 0.00029676192198919516, 'samples': 12890304, 'steps': 67136, 'loss/train': 1.0007259845733643} 08/31/2021 01:21:24 - INFO - __main__ - Step 67138: {'lr': 0.00029675670889392144, 'samples': 12890496, 'steps': 67137, 'loss/train': 0.10293139517307281} 08/31/2021 01:21:25 - INFO - __main__ - Step 67139: {'lr': 0.00029675149577757973, 'samples': 12890688, 'steps': 67138, 'loss/train': 0.0905950739979744} 08/31/2021 01:21:25 - INFO - __main__ - Step 67140: {'lr': 0.0002967462826401726, 'samples': 12890880, 'steps': 67139, 'loss/train': 1.2025915384292603} 08/31/2021 01:21:26 - INFO - __main__ - Step 67141: {'lr': 0.00029674106948170234, 'samples': 12891072, 'steps': 67140, 'loss/train': 1.287833333015442} 08/31/2021 01:21:27 - INFO - __main__ - Step 67142: {'lr': 0.0002967358563021712, 'samples': 12891264, 'steps': 67141, 'loss/train': 1.2068164348602295} 08/31/2021 01:21:27 - INFO - __main__ - Step 67143: {'lr': 0.00029673064310158163, 'samples': 12891456, 'steps': 67142, 'loss/train': 0.9326778650283813} 08/31/2021 01:21:28 - INFO - __main__ - Step 67144: {'lr': 0.000296725429879936, 'samples': 12891648, 'steps': 67143, 'loss/train': 0.9108598232269287} 08/31/2021 01:21:28 - INFO - __main__ - Step 67145: {'lr': 0.0002967202166372366, 'samples': 12891840, 'steps': 67144, 'loss/train': 0.6190603375434875} 08/31/2021 01:21:29 - INFO - __main__ - Step 67146: {'lr': 0.00029671500337348576, 'samples': 12892032, 'steps': 67145, 'loss/train': 1.2858823537826538} 08/31/2021 01:21:30 - INFO - __main__ - Step 67147: {'lr': 0.00029670979008868586, 'samples': 12892224, 'steps': 67146, 'loss/train': 0.7372404336929321} 08/31/2021 01:21:30 - INFO - __main__ - Step 67148: {'lr': 0.0002967045767828393, 'samples': 12892416, 'steps': 67147, 'loss/train': 0.6942642331123352} 08/31/2021 01:21:31 - INFO - __main__ - Step 67149: {'lr': 0.0002966993634559483, 'samples': 12892608, 'steps': 67148, 'loss/train': 1.1529484987258911} 08/31/2021 01:21:31 - INFO - __main__ - Step 67150: {'lr': 0.0002966941501080154, 'samples': 12892800, 'steps': 67149, 'loss/train': 2.468722343444824} 08/31/2021 01:21:33 - INFO - __main__ - Step 67151: {'lr': 0.00029668893673904275, 'samples': 12892992, 'steps': 67150, 'loss/train': 1.2849832773208618} 08/31/2021 01:21:33 - INFO - __main__ - Step 67152: {'lr': 0.0002966837233490328, 'samples': 12893184, 'steps': 67151, 'loss/train': 1.1034064292907715} 08/31/2021 01:21:33 - INFO - __main__ - Step 67153: {'lr': 0.0002966785099379879, 'samples': 12893376, 'steps': 67152, 'loss/train': 1.0601178407669067} 08/31/2021 01:21:34 - INFO - __main__ - Step 67154: {'lr': 0.00029667329650591033, 'samples': 12893568, 'steps': 67153, 'loss/train': 1.4249582290649414} 08/31/2021 01:21:34 - INFO - __main__ - Step 67155: {'lr': 0.0002966680830528026, 'samples': 12893760, 'steps': 67154, 'loss/train': 1.6124616861343384} 08/31/2021 01:21:35 - INFO - __main__ - Step 67156: {'lr': 0.00029666286957866683, 'samples': 12893952, 'steps': 67155, 'loss/train': 1.1594054698944092} 08/31/2021 01:21:36 - INFO - __main__ - Step 67157: {'lr': 0.00029665765608350553, 'samples': 12894144, 'steps': 67156, 'loss/train': 0.7472809553146362} 08/31/2021 01:21:36 - INFO - __main__ - Step 67158: {'lr': 0.00029665244256732107, 'samples': 12894336, 'steps': 67157, 'loss/train': 1.2743346691131592} 08/31/2021 01:21:37 - INFO - __main__ - Step 67159: {'lr': 0.0002966472290301157, 'samples': 12894528, 'steps': 67158, 'loss/train': 1.3589049577713013} 08/31/2021 01:21:37 - INFO - __main__ - Step 67160: {'lr': 0.0002966420154718918, 'samples': 12894720, 'steps': 67159, 'loss/train': 1.4947272539138794} 08/31/2021 01:21:37 - INFO - __main__ - Step 67161: {'lr': 0.00029663680189265175, 'samples': 12894912, 'steps': 67160, 'loss/train': 1.4066373109817505} 08/31/2021 01:21:39 - INFO - __main__ - Step 67162: {'lr': 0.0002966315882923978, 'samples': 12895104, 'steps': 67161, 'loss/train': 1.0824980735778809} 08/31/2021 01:21:39 - INFO - __main__ - Step 67163: {'lr': 0.0002966263746711325, 'samples': 12895296, 'steps': 67162, 'loss/train': 0.9582497477531433} 08/31/2021 01:21:40 - INFO - __main__ - Step 67164: {'lr': 0.00029662116102885795, 'samples': 12895488, 'steps': 67163, 'loss/train': 1.3986989259719849} 08/31/2021 01:21:40 - INFO - __main__ - Step 67165: {'lr': 0.00029661594736557674, 'samples': 12895680, 'steps': 67164, 'loss/train': 1.2620986700057983} 08/31/2021 01:21:40 - INFO - __main__ - Step 67166: {'lr': 0.00029661073368129106, 'samples': 12895872, 'steps': 67165, 'loss/train': 1.2804806232452393} 08/31/2021 01:21:42 - INFO - __main__ - Step 67167: {'lr': 0.00029660551997600325, 'samples': 12896064, 'steps': 67166, 'loss/train': 1.2569401264190674} 08/31/2021 01:21:42 - INFO - __main__ - Step 67168: {'lr': 0.00029660030624971574, 'samples': 12896256, 'steps': 67167, 'loss/train': 0.7140110731124878} 08/31/2021 01:21:43 - INFO - __main__ - Step 67169: {'lr': 0.0002965950925024308, 'samples': 12896448, 'steps': 67168, 'loss/train': 0.4449387192726135} 08/31/2021 01:21:43 - INFO - __main__ - Step 67170: {'lr': 0.0002965898787341509, 'samples': 12896640, 'steps': 67169, 'loss/train': 2.0375466346740723} 08/31/2021 01:21:44 - INFO - __main__ - Step 67171: {'lr': 0.00029658466494487837, 'samples': 12896832, 'steps': 67170, 'loss/train': 1.4174525737762451} 08/31/2021 01:21:45 - INFO - __main__ - Step 67172: {'lr': 0.0002965794511346155, 'samples': 12897024, 'steps': 67171, 'loss/train': 1.8305997848510742} 08/31/2021 01:21:45 - INFO - __main__ - Step 67173: {'lr': 0.0002965742373033646, 'samples': 12897216, 'steps': 67172, 'loss/train': 1.3863637447357178} 08/31/2021 01:21:46 - INFO - __main__ - Step 67174: {'lr': 0.00029656902345112803, 'samples': 12897408, 'steps': 67173, 'loss/train': 1.6721675395965576} 08/31/2021 01:21:46 - INFO - __main__ - Step 67175: {'lr': 0.0002965638095779082, 'samples': 12897600, 'steps': 67174, 'loss/train': 1.1092529296875} 08/31/2021 01:21:47 - INFO - __main__ - Step 67176: {'lr': 0.0002965585956837075, 'samples': 12897792, 'steps': 67175, 'loss/train': 1.6385749578475952} 08/31/2021 01:21:48 - INFO - __main__ - Step 67177: {'lr': 0.0002965533817685281, 'samples': 12897984, 'steps': 67176, 'loss/train': 1.5538489818572998} 08/31/2021 01:21:49 - INFO - __main__ - Step 67178: {'lr': 0.0002965481678323726, 'samples': 12898176, 'steps': 67177, 'loss/train': 0.03536885231733322} 08/31/2021 01:21:49 - INFO - __main__ - Step 67179: {'lr': 0.0002965429538752431, 'samples': 12898368, 'steps': 67178, 'loss/train': 1.3754252195358276} 08/31/2021 01:21:50 - INFO - __main__ - Step 67180: {'lr': 0.00029653773989714213, 'samples': 12898560, 'steps': 67179, 'loss/train': 1.5311359167099} 08/31/2021 01:21:50 - INFO - __main__ - Step 67181: {'lr': 0.0002965325258980719, 'samples': 12898752, 'steps': 67180, 'loss/train': 1.3413571119308472} 08/31/2021 01:21:51 - INFO - __main__ - Step 67182: {'lr': 0.0002965273118780349, 'samples': 12898944, 'steps': 67181, 'loss/train': 1.1429039239883423} 08/31/2021 01:21:52 - INFO - __main__ - Step 67183: {'lr': 0.00029652209783703336, 'samples': 12899136, 'steps': 67182, 'loss/train': 1.8375798463821411} 08/31/2021 01:21:52 - INFO - __main__ - Step 67184: {'lr': 0.00029651688377506976, 'samples': 12899328, 'steps': 67183, 'loss/train': 1.054050087928772} 08/31/2021 01:21:53 - INFO - __main__ - Step 67185: {'lr': 0.0002965116696921463, 'samples': 12899520, 'steps': 67184, 'loss/train': 0.30840247869491577} 08/31/2021 01:21:53 - INFO - __main__ - Step 67186: {'lr': 0.00029650645558826545, 'samples': 12899712, 'steps': 67185, 'loss/train': 1.5117073059082031} 08/31/2021 01:21:53 - INFO - __main__ - Step 67187: {'lr': 0.0002965012414634295, 'samples': 12899904, 'steps': 67186, 'loss/train': 0.8783172369003296} 08/31/2021 01:21:55 - INFO - __main__ - Step 67188: {'lr': 0.00029649602731764076, 'samples': 12900096, 'steps': 67187, 'loss/train': 2.7876787185668945} 08/31/2021 01:21:56 - INFO - __main__ - Step 67189: {'lr': 0.00029649081315090165, 'samples': 12900288, 'steps': 67188, 'loss/train': 0.4860400855541229} 08/31/2021 01:21:56 - INFO - __main__ - Step 67190: {'lr': 0.00029648559896321445, 'samples': 12900480, 'steps': 67189, 'loss/train': 1.099668025970459} 08/31/2021 01:21:57 - INFO - __main__ - Step 67191: {'lr': 0.0002964803847545816, 'samples': 12900672, 'steps': 67190, 'loss/train': 0.8498167395591736} 08/31/2021 01:21:57 - INFO - __main__ - Step 67192: {'lr': 0.0002964751705250055, 'samples': 12900864, 'steps': 67191, 'loss/train': 1.140614628791809} 08/31/2021 01:21:58 - INFO - __main__ - Step 67193: {'lr': 0.0002964699562744883, 'samples': 12901056, 'steps': 67192, 'loss/train': 1.42580246925354} 08/31/2021 01:21:59 - INFO - __main__ - Step 67194: {'lr': 0.00029646474200303245, 'samples': 12901248, 'steps': 67193, 'loss/train': 1.68765389919281} 08/31/2021 01:21:59 - INFO - __main__ - Step 67195: {'lr': 0.0002964595277106403, 'samples': 12901440, 'steps': 67194, 'loss/train': 0.9404320120811462} 08/31/2021 01:22:00 - INFO - __main__ - Step 67196: {'lr': 0.00029645431339731426, 'samples': 12901632, 'steps': 67195, 'loss/train': 1.4045435190200806} 08/31/2021 01:22:00 - INFO - __main__ - Step 67197: {'lr': 0.0002964490990630566, 'samples': 12901824, 'steps': 67196, 'loss/train': 1.5160537958145142} 08/31/2021 01:22:02 - INFO - __main__ - Step 67198: {'lr': 0.0002964438847078697, 'samples': 12902016, 'steps': 67197, 'loss/train': 2.2124369144439697} 08/31/2021 01:22:02 - INFO - __main__ - Step 67199: {'lr': 0.0002964386703317559, 'samples': 12902208, 'steps': 67198, 'loss/train': 1.0822741985321045} 08/31/2021 01:22:03 - INFO - __main__ - Step 67200: {'lr': 0.0002964334559347175, 'samples': 12902400, 'steps': 67199, 'loss/train': 1.6287016868591309} 08/31/2021 01:22:03 - INFO - __main__ - Step 67201: {'lr': 0.000296428241516757, 'samples': 12902592, 'steps': 67200, 'loss/train': 0.02224789559841156} 08/31/2021 01:22:03 - INFO - __main__ - Step 67202: {'lr': 0.0002964230270778766, 'samples': 12902784, 'steps': 67201, 'loss/train': 0.6218258142471313} 08/31/2021 01:22:04 - INFO - __main__ - Step 67203: {'lr': 0.00029641781261807867, 'samples': 12902976, 'steps': 67202, 'loss/train': 0.6027570366859436} 08/31/2021 01:22:05 - INFO - __main__ - Step 67204: {'lr': 0.0002964125981373656, 'samples': 12903168, 'steps': 67203, 'loss/train': 1.272787094116211} 08/31/2021 01:22:06 - INFO - __main__ - Step 67205: {'lr': 0.0002964073836357398, 'samples': 12903360, 'steps': 67204, 'loss/train': 0.8167366981506348} 08/31/2021 01:22:06 - INFO - __main__ - Step 67206: {'lr': 0.0002964021691132035, 'samples': 12903552, 'steps': 67205, 'loss/train': 1.463064193725586} 08/31/2021 01:22:06 - INFO - __main__ - Step 67207: {'lr': 0.00029639695456975905, 'samples': 12903744, 'steps': 67206, 'loss/train': 0.828780472278595} 08/31/2021 01:22:07 - INFO - __main__ - Step 67208: {'lr': 0.0002963917400054089, 'samples': 12903936, 'steps': 67207, 'loss/train': 1.4022791385650635} 08/31/2021 01:22:08 - INFO - __main__ - Step 67209: {'lr': 0.0002963865254201553, 'samples': 12904128, 'steps': 67208, 'loss/train': 0.8185678720474243} 08/31/2021 01:22:09 - INFO - __main__ - Step 67210: {'lr': 0.0002963813108140007, 'samples': 12904320, 'steps': 67209, 'loss/train': 1.5716546773910522} 08/31/2021 01:22:09 - INFO - __main__ - Step 67211: {'lr': 0.00029637609618694745, 'samples': 12904512, 'steps': 67210, 'loss/train': 0.08120473474264145} 08/31/2021 01:22:10 - INFO - __main__ - Step 67212: {'lr': 0.0002963708815389978, 'samples': 12904704, 'steps': 67211, 'loss/train': 1.0801887512207031} 08/31/2021 01:22:10 - INFO - __main__ - Step 67213: {'lr': 0.0002963656668701541, 'samples': 12904896, 'steps': 67212, 'loss/train': 1.4482944011688232} 08/31/2021 01:22:12 - INFO - __main__ - Step 67214: {'lr': 0.0002963604521804187, 'samples': 12905088, 'steps': 67213, 'loss/train': 1.3612366914749146} 08/31/2021 01:22:12 - INFO - __main__ - Step 67215: {'lr': 0.0002963552374697941, 'samples': 12905280, 'steps': 67214, 'loss/train': 0.4368901550769806} 08/31/2021 01:22:12 - INFO - __main__ - Step 67216: {'lr': 0.0002963500227382826, 'samples': 12905472, 'steps': 67215, 'loss/train': 0.6943337917327881} 08/31/2021 01:22:13 - INFO - __main__ - Step 67217: {'lr': 0.00029634480798588635, 'samples': 12905664, 'steps': 67216, 'loss/train': 1.1590162515640259} 08/31/2021 01:22:13 - INFO - __main__ - Step 67218: {'lr': 0.00029633959321260795, 'samples': 12905856, 'steps': 67217, 'loss/train': 1.0560611486434937} 08/31/2021 01:22:14 - INFO - __main__ - Step 67219: {'lr': 0.00029633437841844956, 'samples': 12906048, 'steps': 67218, 'loss/train': 0.8615282773971558} 08/31/2021 01:22:15 - INFO - __main__ - Step 67220: {'lr': 0.00029632916360341366, 'samples': 12906240, 'steps': 67219, 'loss/train': 0.9128265380859375} 08/31/2021 01:22:15 - INFO - __main__ - Step 67221: {'lr': 0.0002963239487675025, 'samples': 12906432, 'steps': 67220, 'loss/train': 0.5170688033103943} 08/31/2021 01:22:16 - INFO - __main__ - Step 67222: {'lr': 0.0002963187339107186, 'samples': 12906624, 'steps': 67221, 'loss/train': 0.22411656379699707} 08/31/2021 01:22:16 - INFO - __main__ - Step 67223: {'lr': 0.0002963135190330641, 'samples': 12906816, 'steps': 67222, 'loss/train': 1.036946177482605} 08/31/2021 01:22:17 - INFO - __main__ - Step 67224: {'lr': 0.00029630830413454145, 'samples': 12907008, 'steps': 67223, 'loss/train': 0.928666889667511} 08/31/2021 01:22:18 - INFO - __main__ - Step 67225: {'lr': 0.00029630308921515305, 'samples': 12907200, 'steps': 67224, 'loss/train': 1.3290016651153564} 08/31/2021 01:22:18 - INFO - __main__ - Step 67226: {'lr': 0.0002962978742749011, 'samples': 12907392, 'steps': 67225, 'loss/train': 0.4273613691329956} 08/31/2021 01:22:19 - INFO - __main__ - Step 67227: {'lr': 0.00029629265931378816, 'samples': 12907584, 'steps': 67226, 'loss/train': 0.7186167240142822} 08/31/2021 01:22:19 - INFO - __main__ - Step 67228: {'lr': 0.00029628744433181635, 'samples': 12907776, 'steps': 67227, 'loss/train': 0.8256433606147766} 08/31/2021 01:22:20 - INFO - __main__ - Step 67229: {'lr': 0.0002962822293289882, 'samples': 12907968, 'steps': 67228, 'loss/train': 0.21732503175735474} 08/31/2021 01:22:21 - INFO - __main__ - Step 67230: {'lr': 0.00029627701430530597, 'samples': 12908160, 'steps': 67229, 'loss/train': 1.1622576713562012} 08/31/2021 01:22:21 - INFO - __main__ - Step 67231: {'lr': 0.000296271799260772, 'samples': 12908352, 'steps': 67230, 'loss/train': 0.44571995735168457} 08/31/2021 01:22:22 - INFO - __main__ - Step 67232: {'lr': 0.00029626658419538873, 'samples': 12908544, 'steps': 67231, 'loss/train': 0.9916109442710876} 08/31/2021 01:22:22 - INFO - __main__ - Step 67233: {'lr': 0.00029626136910915847, 'samples': 12908736, 'steps': 67232, 'loss/train': 1.2002506256103516} 08/31/2021 01:22:23 - INFO - __main__ - Step 67234: {'lr': 0.0002962561540020835, 'samples': 12908928, 'steps': 67233, 'loss/train': 1.3030495643615723} 08/31/2021 01:22:24 - INFO - __main__ - Step 67235: {'lr': 0.0002962509388741662, 'samples': 12909120, 'steps': 67234, 'loss/train': 1.5468883514404297} 08/31/2021 01:22:24 - INFO - __main__ - Step 67236: {'lr': 0.0002962457237254089, 'samples': 12909312, 'steps': 67235, 'loss/train': 1.9066689014434814} 08/31/2021 01:22:25 - INFO - __main__ - Step 67237: {'lr': 0.0002962405085558141, 'samples': 12909504, 'steps': 67236, 'loss/train': 1.0529307126998901} 08/31/2021 01:22:25 - INFO - __main__ - Step 67238: {'lr': 0.00029623529336538396, 'samples': 12909696, 'steps': 67237, 'loss/train': 1.2192548513412476} 08/31/2021 01:22:25 - INFO - __main__ - Step 67239: {'lr': 0.000296230078154121, 'samples': 12909888, 'steps': 67238, 'loss/train': 1.5046194791793823} 08/31/2021 01:22:27 - INFO - __main__ - Step 67240: {'lr': 0.00029622486292202744, 'samples': 12910080, 'steps': 67239, 'loss/train': 1.228639841079712} 08/31/2021 01:22:28 - INFO - __main__ - Step 67241: {'lr': 0.00029621964766910565, 'samples': 12910272, 'steps': 67240, 'loss/train': 2.4678924083709717} 08/31/2021 01:22:28 - INFO - __main__ - Step 67242: {'lr': 0.000296214432395358, 'samples': 12910464, 'steps': 67241, 'loss/train': 0.8232345581054688} 08/31/2021 01:22:28 - INFO - __main__ - Step 67243: {'lr': 0.00029620921710078686, 'samples': 12910656, 'steps': 67242, 'loss/train': 1.0302306413650513} 08/31/2021 01:22:29 - INFO - __main__ - Step 67244: {'lr': 0.00029620400178539453, 'samples': 12910848, 'steps': 67243, 'loss/train': 1.727097749710083} 08/31/2021 01:22:30 - INFO - __main__ - Step 67245: {'lr': 0.00029619878644918335, 'samples': 12911040, 'steps': 67244, 'loss/train': 1.2299987077713013} 08/31/2021 01:22:31 - INFO - __main__ - Step 67246: {'lr': 0.0002961935710921558, 'samples': 12911232, 'steps': 67245, 'loss/train': 1.2454516887664795} 08/31/2021 01:22:31 - INFO - __main__ - Step 67247: {'lr': 0.00029618835571431414, 'samples': 12911424, 'steps': 67246, 'loss/train': 0.4846718907356262} 08/31/2021 01:22:31 - INFO - __main__ - Step 67248: {'lr': 0.00029618314031566067, 'samples': 12911616, 'steps': 67247, 'loss/train': 1.154470443725586} 08/31/2021 01:22:32 - INFO - __main__ - Step 67249: {'lr': 0.0002961779248961978, 'samples': 12911808, 'steps': 67248, 'loss/train': 0.6490768194198608} 08/31/2021 01:22:34 - INFO - __main__ - Step 67250: {'lr': 0.0002961727094559279, 'samples': 12912000, 'steps': 67249, 'loss/train': 1.2662487030029297} 08/31/2021 01:22:34 - INFO - __main__ - Step 67251: {'lr': 0.00029616749399485323, 'samples': 12912192, 'steps': 67250, 'loss/train': 0.8597075343132019} 08/31/2021 01:22:35 - INFO - __main__ - Step 67252: {'lr': 0.0002961622785129763, 'samples': 12912384, 'steps': 67251, 'loss/train': 1.40156888961792} 08/31/2021 01:22:35 - INFO - __main__ - Step 67253: {'lr': 0.00029615706301029925, 'samples': 12912576, 'steps': 67252, 'loss/train': 0.9322826862335205} 08/31/2021 01:22:35 - INFO - __main__ - Step 67254: {'lr': 0.00029615184748682456, 'samples': 12912768, 'steps': 67253, 'loss/train': 1.1522917747497559} 08/31/2021 01:22:36 - INFO - __main__ - Step 67255: {'lr': 0.0002961466319425546, 'samples': 12912960, 'steps': 67254, 'loss/train': 0.42903006076812744} 08/31/2021 01:22:37 - INFO - __main__ - Step 67256: {'lr': 0.00029614141637749166, 'samples': 12913152, 'steps': 67255, 'loss/train': 2.3557419776916504} 08/31/2021 01:22:38 - INFO - __main__ - Step 67257: {'lr': 0.00029613620079163805, 'samples': 12913344, 'steps': 67256, 'loss/train': 0.2445560246706009} 08/31/2021 01:22:38 - INFO - __main__ - Step 67258: {'lr': 0.00029613098518499627, 'samples': 12913536, 'steps': 67257, 'loss/train': 1.2856018543243408} 08/31/2021 01:22:38 - INFO - __main__ - Step 67259: {'lr': 0.0002961257695575686, 'samples': 12913728, 'steps': 67258, 'loss/train': 0.11023828387260437} 08/31/2021 01:22:39 - INFO - __main__ - Step 67260: {'lr': 0.0002961205539093573, 'samples': 12913920, 'steps': 67259, 'loss/train': 1.306622862815857} 08/31/2021 01:22:40 - INFO - __main__ - Step 67261: {'lr': 0.0002961153382403648, 'samples': 12914112, 'steps': 67260, 'loss/train': 1.5416741371154785} 08/31/2021 01:22:41 - INFO - __main__ - Step 67262: {'lr': 0.00029611012255059346, 'samples': 12914304, 'steps': 67261, 'loss/train': 1.120469093322754} 08/31/2021 01:22:41 - INFO - __main__ - Step 67263: {'lr': 0.0002961049068400456, 'samples': 12914496, 'steps': 67262, 'loss/train': 1.4403598308563232} 08/31/2021 01:22:41 - INFO - __main__ - Step 67264: {'lr': 0.0002960996911087236, 'samples': 12914688, 'steps': 67263, 'loss/train': 0.9313377141952515} 08/31/2021 01:22:42 - INFO - __main__ - Step 67265: {'lr': 0.0002960944753566297, 'samples': 12914880, 'steps': 67264, 'loss/train': 1.181982398033142} 08/31/2021 01:22:43 - INFO - __main__ - Step 67266: {'lr': 0.00029608925958376646, 'samples': 12915072, 'steps': 67265, 'loss/train': 1.2282320261001587} 08/31/2021 01:22:44 - INFO - __main__ - Step 67267: {'lr': 0.0002960840437901361, 'samples': 12915264, 'steps': 67266, 'loss/train': 0.8366397023200989} 08/31/2021 01:22:44 - INFO - __main__ - Step 67268: {'lr': 0.00029607882797574094, 'samples': 12915456, 'steps': 67267, 'loss/train': 1.1666364669799805} 08/31/2021 01:22:44 - INFO - __main__ - Step 67269: {'lr': 0.0002960736121405834, 'samples': 12915648, 'steps': 67268, 'loss/train': 1.3035130500793457} 08/31/2021 01:22:45 - INFO - __main__ - Step 67270: {'lr': 0.0002960683962846657, 'samples': 12915840, 'steps': 67269, 'loss/train': 0.1442573517560959} 08/31/2021 01:22:46 - INFO - __main__ - Step 67271: {'lr': 0.0002960631804079904, 'samples': 12916032, 'steps': 67270, 'loss/train': 0.9961205720901489} 08/31/2021 01:22:47 - INFO - __main__ - Step 67272: {'lr': 0.0002960579645105597, 'samples': 12916224, 'steps': 67271, 'loss/train': 0.9388519525527954} 08/31/2021 01:22:47 - INFO - __main__ - Step 67273: {'lr': 0.000296052748592376, 'samples': 12916416, 'steps': 67272, 'loss/train': 1.5497591495513916} 08/31/2021 01:22:47 - INFO - __main__ - Step 67274: {'lr': 0.00029604753265344166, 'samples': 12916608, 'steps': 67273, 'loss/train': 1.86030912399292} 08/31/2021 01:22:48 - INFO - __main__ - Step 67275: {'lr': 0.00029604231669375905, 'samples': 12916800, 'steps': 67274, 'loss/train': 2.0556800365448} 08/31/2021 01:22:48 - INFO - __main__ - Step 67276: {'lr': 0.00029603710071333033, 'samples': 12916992, 'steps': 67275, 'loss/train': 1.4944922924041748} 08/31/2021 01:22:50 - INFO - __main__ - Step 67277: {'lr': 0.0002960318847121581, 'samples': 12917184, 'steps': 67276, 'loss/train': 1.3660640716552734} 08/31/2021 01:22:50 - INFO - __main__ - Step 67278: {'lr': 0.00029602666869024463, 'samples': 12917376, 'steps': 67277, 'loss/train': 1.1638180017471313} 08/31/2021 01:22:51 - INFO - __main__ - Step 67279: {'lr': 0.0002960214526475923, 'samples': 12917568, 'steps': 67278, 'loss/train': 0.9460097551345825} 08/31/2021 01:22:51 - INFO - __main__ - Step 67280: {'lr': 0.00029601623658420337, 'samples': 12917760, 'steps': 67279, 'loss/train': 1.0874183177947998} 08/31/2021 01:22:51 - INFO - __main__ - Step 67281: {'lr': 0.00029601102050008014, 'samples': 12917952, 'steps': 67280, 'loss/train': 1.2384308576583862} 08/31/2021 01:22:53 - INFO - __main__ - Step 67282: {'lr': 0.0002960058043952252, 'samples': 12918144, 'steps': 67281, 'loss/train': 0.5077690482139587} 08/31/2021 01:22:53 - INFO - __main__ - Step 67283: {'lr': 0.00029600058826964067, 'samples': 12918336, 'steps': 67282, 'loss/train': 0.6857076287269592} 08/31/2021 01:22:54 - INFO - __main__ - Step 67284: {'lr': 0.00029599537212332896, 'samples': 12918528, 'steps': 67283, 'loss/train': 0.5984632968902588} 08/31/2021 01:22:54 - INFO - __main__ - Step 67285: {'lr': 0.00029599015595629247, 'samples': 12918720, 'steps': 67284, 'loss/train': 0.8798766136169434} 08/31/2021 01:22:54 - INFO - __main__ - Step 67286: {'lr': 0.00029598493976853356, 'samples': 12918912, 'steps': 67285, 'loss/train': 2.0867857933044434} 08/31/2021 01:22:56 - INFO - __main__ - Step 67287: {'lr': 0.0002959797235600545, 'samples': 12919104, 'steps': 67286, 'loss/train': 1.9592050313949585} 08/31/2021 01:22:56 - INFO - __main__ - Step 67288: {'lr': 0.0002959745073308577, 'samples': 12919296, 'steps': 67287, 'loss/train': 1.8575867414474487} 08/31/2021 01:22:57 - INFO - __main__ - Step 67289: {'lr': 0.0002959692910809456, 'samples': 12919488, 'steps': 67288, 'loss/train': 1.005267858505249} 08/31/2021 01:22:57 - INFO - __main__ - Step 67290: {'lr': 0.0002959640748103203, 'samples': 12919680, 'steps': 67289, 'loss/train': 1.953130841255188} 08/31/2021 01:22:57 - INFO - __main__ - Step 67291: {'lr': 0.00029595885851898434, 'samples': 12919872, 'steps': 67290, 'loss/train': 1.3073337078094482} 08/31/2021 01:22:58 - INFO - __main__ - Step 67292: {'lr': 0.00029595364220694003, 'samples': 12920064, 'steps': 67291, 'loss/train': 1.4957650899887085} 08/31/2021 01:22:59 - INFO - __main__ - Step 67293: {'lr': 0.0002959484258741898, 'samples': 12920256, 'steps': 67292, 'loss/train': 1.229253888130188} 08/31/2021 01:23:00 - INFO - __main__ - Step 67294: {'lr': 0.00029594320952073584, 'samples': 12920448, 'steps': 67293, 'loss/train': 0.5470949411392212} 08/31/2021 01:23:00 - INFO - __main__ - Step 67295: {'lr': 0.00029593799314658057, 'samples': 12920640, 'steps': 67294, 'loss/train': 1.479648232460022} 08/31/2021 01:23:00 - INFO - __main__ - Step 67296: {'lr': 0.00029593277675172636, 'samples': 12920832, 'steps': 67295, 'loss/train': 1.784189224243164} 08/31/2021 01:23:01 - INFO - __main__ - Step 67297: {'lr': 0.0002959275603361755, 'samples': 12921024, 'steps': 67296, 'loss/train': 1.4899342060089111} 08/31/2021 01:23:03 - INFO - __main__ - Step 67298: {'lr': 0.00029592234389993045, 'samples': 12921216, 'steps': 67297, 'loss/train': 1.537702202796936} 08/31/2021 01:23:03 - INFO - __main__ - Step 67299: {'lr': 0.0002959171274429936, 'samples': 12921408, 'steps': 67298, 'loss/train': 1.4438914060592651} 08/31/2021 01:23:03 - INFO - __main__ - Step 67300: {'lr': 0.00029591191096536704, 'samples': 12921600, 'steps': 67299, 'loss/train': 0.3313632905483246} 08/31/2021 01:23:04 - INFO - __main__ - Step 67301: {'lr': 0.00029590669446705333, 'samples': 12921792, 'steps': 67300, 'loss/train': 1.4691389799118042} 08/31/2021 01:23:04 - INFO - __main__ - Step 67302: {'lr': 0.0002959014779480548, 'samples': 12921984, 'steps': 67301, 'loss/train': 1.822137713432312} 08/31/2021 01:23:06 - INFO - __main__ - Step 67303: {'lr': 0.0002958962614083737, 'samples': 12922176, 'steps': 67302, 'loss/train': 0.5065180659294128} 08/31/2021 01:23:06 - INFO - __main__ - Step 67304: {'lr': 0.00029589104484801257, 'samples': 12922368, 'steps': 67303, 'loss/train': 0.9618237018585205} 08/31/2021 01:23:06 - INFO - __main__ - Step 67305: {'lr': 0.0002958858282669735, 'samples': 12922560, 'steps': 67304, 'loss/train': 0.5398802161216736} 08/31/2021 01:23:07 - INFO - __main__ - Step 67306: {'lr': 0.0002958806116652591, 'samples': 12922752, 'steps': 67305, 'loss/train': 1.1349689960479736} 08/31/2021 01:23:07 - INFO - __main__ - Step 67307: {'lr': 0.0002958753950428716, 'samples': 12922944, 'steps': 67306, 'loss/train': 1.5453988313674927} 08/31/2021 01:23:08 - INFO - __main__ - Step 67308: {'lr': 0.00029587017839981326, 'samples': 12923136, 'steps': 67307, 'loss/train': 1.4983649253845215} 08/31/2021 01:23:09 - INFO - __main__ - Step 67309: {'lr': 0.0002958649617360866, 'samples': 12923328, 'steps': 67308, 'loss/train': 1.3653947114944458} 08/31/2021 01:23:09 - INFO - __main__ - Step 67310: {'lr': 0.0002958597450516939, 'samples': 12923520, 'steps': 67309, 'loss/train': 0.8583663105964661} 08/31/2021 01:23:10 - INFO - __main__ - Step 67311: {'lr': 0.00029585452834663745, 'samples': 12923712, 'steps': 67310, 'loss/train': 1.1497200727462769} 08/31/2021 01:23:10 - INFO - __main__ - Step 67312: {'lr': 0.0002958493116209197, 'samples': 12923904, 'steps': 67311, 'loss/train': 0.9940330982208252} 08/31/2021 01:23:12 - INFO - __main__ - Step 67313: {'lr': 0.000295844094874543, 'samples': 12924096, 'steps': 67312, 'loss/train': 1.4647021293640137} 08/31/2021 01:23:12 - INFO - __main__ - Step 67314: {'lr': 0.0002958388781075096, 'samples': 12924288, 'steps': 67313, 'loss/train': 0.7532001733779907} 08/31/2021 01:23:12 - INFO - __main__ - Step 67315: {'lr': 0.00029583366131982194, 'samples': 12924480, 'steps': 67314, 'loss/train': 0.8213338255882263} 08/31/2021 01:23:13 - INFO - __main__ - Step 67316: {'lr': 0.0002958284445114823, 'samples': 12924672, 'steps': 67315, 'loss/train': 0.7621904015541077} 08/31/2021 01:23:13 - INFO - __main__ - Step 67317: {'lr': 0.0002958232276824931, 'samples': 12924864, 'steps': 67316, 'loss/train': 1.4554259777069092} 08/31/2021 01:23:14 - INFO - __main__ - Step 67318: {'lr': 0.00029581801083285663, 'samples': 12925056, 'steps': 67317, 'loss/train': 1.4327729940414429} 08/31/2021 01:23:15 - INFO - __main__ - Step 67319: {'lr': 0.00029581279396257527, 'samples': 12925248, 'steps': 67318, 'loss/train': 1.5596407651901245} 08/31/2021 01:23:15 - INFO - __main__ - Step 67320: {'lr': 0.00029580757707165146, 'samples': 12925440, 'steps': 67319, 'loss/train': 1.5236468315124512} 08/31/2021 01:23:16 - INFO - __main__ - Step 67321: {'lr': 0.00029580236016008737, 'samples': 12925632, 'steps': 67320, 'loss/train': 0.7073302268981934} 08/31/2021 01:23:16 - INFO - __main__ - Step 67322: {'lr': 0.0002957971432278855, 'samples': 12925824, 'steps': 67321, 'loss/train': 1.3943994045257568} 08/31/2021 01:23:17 - INFO - __main__ - Step 67323: {'lr': 0.0002957919262750481, 'samples': 12926016, 'steps': 67322, 'loss/train': 1.120500087738037} 08/31/2021 01:23:18 - INFO - __main__ - Step 67324: {'lr': 0.0002957867093015775, 'samples': 12926208, 'steps': 67323, 'loss/train': 0.5555053353309631} 08/31/2021 01:23:18 - INFO - __main__ - Step 67325: {'lr': 0.0002957814923074762, 'samples': 12926400, 'steps': 67324, 'loss/train': 1.434370517730713} 08/31/2021 01:23:19 - INFO - __main__ - Step 67326: {'lr': 0.00029577627529274653, 'samples': 12926592, 'steps': 67325, 'loss/train': 1.6512407064437866} 08/31/2021 01:23:19 - INFO - __main__ - Step 67327: {'lr': 0.0002957710582573907, 'samples': 12926784, 'steps': 67326, 'loss/train': 2.107652187347412} 08/31/2021 01:23:20 - INFO - __main__ - Step 67328: {'lr': 0.0002957658412014111, 'samples': 12926976, 'steps': 67327, 'loss/train': 1.1523739099502563} 08/31/2021 01:23:21 - INFO - __main__ - Step 67329: {'lr': 0.0002957606241248102, 'samples': 12927168, 'steps': 67328, 'loss/train': 1.6415226459503174} 08/31/2021 01:23:21 - INFO - __main__ - Step 67330: {'lr': 0.0002957554070275902, 'samples': 12927360, 'steps': 67329, 'loss/train': 1.9429186582565308} 08/31/2021 01:23:21 - INFO - __main__ - Step 67331: {'lr': 0.00029575018990975356, 'samples': 12927552, 'steps': 67330, 'loss/train': 1.0913474559783936} 08/31/2021 01:23:22 - INFO - __main__ - Step 67332: {'lr': 0.0002957449727713026, 'samples': 12927744, 'steps': 67331, 'loss/train': 1.5038528442382812} 08/31/2021 01:23:24 - INFO - __main__ - Step 67333: {'lr': 0.00029573975561223966, 'samples': 12927936, 'steps': 67332, 'loss/train': 1.5670125484466553} 08/31/2021 01:23:25 - INFO - __main__ - Step 67334: {'lr': 0.00029573453843256706, 'samples': 12928128, 'steps': 67333, 'loss/train': 2.2626571655273438} 08/31/2021 01:23:25 - INFO - __main__ - Step 67335: {'lr': 0.0002957293212322872, 'samples': 12928320, 'steps': 67334, 'loss/train': 1.1662787199020386} 08/31/2021 01:23:25 - INFO - __main__ - Step 67336: {'lr': 0.0002957241040114024, 'samples': 12928512, 'steps': 67335, 'loss/train': 1.4891979694366455} 08/31/2021 01:23:26 - INFO - __main__ - Step 67337: {'lr': 0.000295718886769915, 'samples': 12928704, 'steps': 67336, 'loss/train': 1.681563138961792} 08/31/2021 01:23:26 - INFO - __main__ - Step 67338: {'lr': 0.0002957136695078274, 'samples': 12928896, 'steps': 67337, 'loss/train': 1.2860952615737915} 08/31/2021 01:23:26 - INFO - __main__ - Step 67339: {'lr': 0.00029570845222514193, 'samples': 12929088, 'steps': 67338, 'loss/train': 0.16539733111858368} 08/31/2021 01:23:28 - INFO - __main__ - Step 67340: {'lr': 0.000295703234921861, 'samples': 12929280, 'steps': 67339, 'loss/train': 0.13234315812587738} 08/31/2021 01:23:28 - INFO - __main__ - Step 67341: {'lr': 0.0002956980175979868, 'samples': 12929472, 'steps': 67340, 'loss/train': 1.1545521020889282} 08/31/2021 01:23:29 - INFO - __main__ - Step 67342: {'lr': 0.00029569280025352183, 'samples': 12929664, 'steps': 67341, 'loss/train': 1.4692260026931763} 08/31/2021 01:23:29 - INFO - __main__ - Step 67343: {'lr': 0.0002956875828884684, 'samples': 12929856, 'steps': 67342, 'loss/train': 1.373400092124939} 08/31/2021 01:23:29 - INFO - __main__ - Step 67344: {'lr': 0.00029568236550282876, 'samples': 12930048, 'steps': 67343, 'loss/train': 1.7306725978851318} 08/31/2021 01:23:31 - INFO - __main__ - Step 67345: {'lr': 0.0002956771480966055, 'samples': 12930240, 'steps': 67344, 'loss/train': 1.4070326089859009} 08/31/2021 01:23:31 - INFO - __main__ - Step 67346: {'lr': 0.00029567193066980073, 'samples': 12930432, 'steps': 67345, 'loss/train': 1.9116497039794922} 08/31/2021 01:23:32 - INFO - __main__ - Step 67347: {'lr': 0.0002956667132224169, 'samples': 12930624, 'steps': 67346, 'loss/train': 1.2092394828796387} 08/31/2021 01:23:32 - INFO - __main__ - Step 67348: {'lr': 0.0002956614957544563, 'samples': 12930816, 'steps': 67347, 'loss/train': 0.9740875959396362} 08/31/2021 01:23:32 - INFO - __main__ - Step 67349: {'lr': 0.00029565627826592147, 'samples': 12931008, 'steps': 67348, 'loss/train': 1.0259815454483032} 08/31/2021 01:23:35 - INFO - __main__ - Step 67350: {'lr': 0.00029565106075681453, 'samples': 12931200, 'steps': 67349, 'loss/train': 1.1873886585235596} 08/31/2021 01:23:35 - INFO - __main__ - Step 67351: {'lr': 0.00029564584322713794, 'samples': 12931392, 'steps': 67350, 'loss/train': 0.10530173033475876} 08/31/2021 01:23:35 - INFO - __main__ - Step 67352: {'lr': 0.00029564062567689404, 'samples': 12931584, 'steps': 67351, 'loss/train': 1.7025476694107056} 08/31/2021 01:23:36 - INFO - __main__ - Step 67353: {'lr': 0.0002956354081060852, 'samples': 12931776, 'steps': 67352, 'loss/train': 0.7352439165115356} 08/31/2021 01:23:36 - INFO - __main__ - Step 67354: {'lr': 0.0002956301905147137, 'samples': 12931968, 'steps': 67353, 'loss/train': 0.03476248309016228} 08/31/2021 01:23:38 - INFO - __main__ - Step 67355: {'lr': 0.00029562497290278197, 'samples': 12932160, 'steps': 67354, 'loss/train': 1.6767550706863403} 08/31/2021 01:23:38 - INFO - __main__ - Step 67356: {'lr': 0.0002956197552702924, 'samples': 12932352, 'steps': 67355, 'loss/train': 1.0600203275680542} 08/31/2021 01:23:39 - INFO - __main__ - Step 67357: {'lr': 0.00029561453761724714, 'samples': 12932544, 'steps': 67356, 'loss/train': 0.17869305610656738} 08/31/2021 01:23:39 - INFO - __main__ - Step 67358: {'lr': 0.00029560931994364873, 'samples': 12932736, 'steps': 67357, 'loss/train': 1.6082078218460083} 08/31/2021 01:23:39 - INFO - __main__ - Step 67359: {'lr': 0.00029560410224949954, 'samples': 12932928, 'steps': 67358, 'loss/train': 1.2444177865982056} 08/31/2021 01:23:41 - INFO - __main__ - Step 67360: {'lr': 0.00029559888453480174, 'samples': 12933120, 'steps': 67359, 'loss/train': 1.1669715642929077} 08/31/2021 01:23:41 - INFO - __main__ - Step 67361: {'lr': 0.0002955936667995578, 'samples': 12933312, 'steps': 67360, 'loss/train': 1.8192592859268188} 08/31/2021 01:23:42 - INFO - __main__ - Step 67362: {'lr': 0.00029558844904377016, 'samples': 12933504, 'steps': 67361, 'loss/train': 0.8208832144737244} 08/31/2021 01:23:42 - INFO - __main__ - Step 67363: {'lr': 0.0002955832312674409, 'samples': 12933696, 'steps': 67362, 'loss/train': 0.8838455677032471} 08/31/2021 01:23:42 - INFO - __main__ - Step 67364: {'lr': 0.00029557801347057265, 'samples': 12933888, 'steps': 67363, 'loss/train': 1.701340675354004} 08/31/2021 01:23:43 - INFO - __main__ - Step 67365: {'lr': 0.0002955727956531676, 'samples': 12934080, 'steps': 67364, 'loss/train': 1.322880744934082} 08/31/2021 01:23:44 - INFO - __main__ - Step 67366: {'lr': 0.00029556757781522817, 'samples': 12934272, 'steps': 67365, 'loss/train': 1.150952935218811} 08/31/2021 01:23:45 - INFO - __main__ - Step 67367: {'lr': 0.0002955623599567568, 'samples': 12934464, 'steps': 67366, 'loss/train': 1.252413034439087} 08/31/2021 01:23:45 - INFO - __main__ - Step 67368: {'lr': 0.0002955571420777556, 'samples': 12934656, 'steps': 67367, 'loss/train': 0.7361128330230713} 08/31/2021 01:23:45 - INFO - __main__ - Step 67369: {'lr': 0.0002955519241782271, 'samples': 12934848, 'steps': 67368, 'loss/train': 1.5557529926300049} 08/31/2021 01:23:46 - INFO - __main__ - Step 67370: {'lr': 0.00029554670625817357, 'samples': 12935040, 'steps': 67369, 'loss/train': 1.3172117471694946} 08/31/2021 01:23:47 - INFO - __main__ - Step 67371: {'lr': 0.0002955414883175974, 'samples': 12935232, 'steps': 67370, 'loss/train': 1.297950029373169} 08/31/2021 01:23:48 - INFO - __main__ - Step 67372: {'lr': 0.00029553627035650096, 'samples': 12935424, 'steps': 67371, 'loss/train': 1.2782132625579834} 08/31/2021 01:23:48 - INFO - __main__ - Step 67373: {'lr': 0.00029553105237488663, 'samples': 12935616, 'steps': 67372, 'loss/train': 1.2572295665740967} 08/31/2021 01:23:48 - INFO - __main__ - Step 67374: {'lr': 0.00029552583437275664, 'samples': 12935808, 'steps': 67373, 'loss/train': 0.7247860431671143} 08/31/2021 01:23:49 - INFO - __main__ - Step 67375: {'lr': 0.0002955206163501134, 'samples': 12936000, 'steps': 67374, 'loss/train': 1.5507349967956543} 08/31/2021 01:23:50 - INFO - __main__ - Step 67376: {'lr': 0.00029551539830695935, 'samples': 12936192, 'steps': 67375, 'loss/train': 0.4934374690055847} 08/31/2021 01:23:50 - INFO - __main__ - Step 67377: {'lr': 0.00029551018024329666, 'samples': 12936384, 'steps': 67376, 'loss/train': 0.9581613540649414} 08/31/2021 01:23:51 - INFO - __main__ - Step 67378: {'lr': 0.00029550496215912785, 'samples': 12936576, 'steps': 67377, 'loss/train': 1.2177382707595825} 08/31/2021 01:23:51 - INFO - __main__ - Step 67379: {'lr': 0.0002954997440544552, 'samples': 12936768, 'steps': 67378, 'loss/train': 1.1096482276916504} 08/31/2021 01:23:52 - INFO - __main__ - Step 67380: {'lr': 0.0002954945259292811, 'samples': 12936960, 'steps': 67379, 'loss/train': 1.2363710403442383} 08/31/2021 01:23:53 - INFO - __main__ - Step 67381: {'lr': 0.0002954893077836078, 'samples': 12937152, 'steps': 67380, 'loss/train': 1.2126071453094482} 08/31/2021 01:23:53 - INFO - __main__ - Step 67382: {'lr': 0.00029548408961743776, 'samples': 12937344, 'steps': 67381, 'loss/train': 0.7059365510940552} 08/31/2021 01:23:54 - INFO - __main__ - Step 67383: {'lr': 0.0002954788714307733, 'samples': 12937536, 'steps': 67382, 'loss/train': 1.278326153755188} 08/31/2021 01:23:54 - INFO - __main__ - Step 67384: {'lr': 0.0002954736532236167, 'samples': 12937728, 'steps': 67383, 'loss/train': 1.6807000637054443} 08/31/2021 01:23:55 - INFO - __main__ - Step 67385: {'lr': 0.00029546843499597046, 'samples': 12937920, 'steps': 67384, 'loss/train': 1.4463062286376953} 08/31/2021 01:23:56 - INFO - __main__ - Step 67386: {'lr': 0.00029546321674783684, 'samples': 12938112, 'steps': 67385, 'loss/train': 0.6857553124427795} 08/31/2021 01:23:56 - INFO - __main__ - Step 67387: {'lr': 0.0002954579984792182, 'samples': 12938304, 'steps': 67386, 'loss/train': 1.1282284259796143} 08/31/2021 01:23:57 - INFO - __main__ - Step 67388: {'lr': 0.0002954527801901168, 'samples': 12938496, 'steps': 67387, 'loss/train': 1.6343621015548706} 08/31/2021 01:23:57 - INFO - __main__ - Step 67389: {'lr': 0.0002954475618805351, 'samples': 12938688, 'steps': 67388, 'loss/train': 1.476297378540039} 08/31/2021 01:23:57 - INFO - __main__ - Step 67390: {'lr': 0.0002954423435504755, 'samples': 12938880, 'steps': 67389, 'loss/train': 1.3380370140075684} 08/31/2021 01:23:58 - INFO - __main__ - Step 67391: {'lr': 0.0002954371251999402, 'samples': 12939072, 'steps': 67390, 'loss/train': 0.1595357209444046} 08/31/2021 01:24:00 - INFO - __main__ - Step 67392: {'lr': 0.0002954319068289317, 'samples': 12939264, 'steps': 67391, 'loss/train': 1.034340262413025} 08/31/2021 01:24:00 - INFO - __main__ - Step 67393: {'lr': 0.0002954266884374523, 'samples': 12939456, 'steps': 67392, 'loss/train': 1.1113537549972534} 08/31/2021 01:24:01 - INFO - __main__ - Step 67394: {'lr': 0.0002954214700255043, 'samples': 12939648, 'steps': 67393, 'loss/train': 1.161213994026184} 08/31/2021 01:24:01 - INFO - __main__ - Step 67395: {'lr': 0.00029541625159309006, 'samples': 12939840, 'steps': 67394, 'loss/train': 0.4729783833026886} 08/31/2021 01:24:01 - INFO - __main__ - Step 67396: {'lr': 0.00029541103314021196, 'samples': 12940032, 'steps': 67395, 'loss/train': 0.02116595394909382} 08/31/2021 01:24:02 - INFO - __main__ - Step 67397: {'lr': 0.0002954058146668723, 'samples': 12940224, 'steps': 67396, 'loss/train': 0.49097710847854614} 08/31/2021 01:24:03 - INFO - __main__ - Step 67398: {'lr': 0.00029540059617307355, 'samples': 12940416, 'steps': 67397, 'loss/train': 1.4839897155761719} 08/31/2021 01:24:03 - INFO - __main__ - Step 67399: {'lr': 0.000295395377658818, 'samples': 12940608, 'steps': 67398, 'loss/train': 1.2509636878967285} 08/31/2021 01:24:04 - INFO - __main__ - Step 67400: {'lr': 0.00029539015912410807, 'samples': 12940800, 'steps': 67399, 'loss/train': 1.2580912113189697} 08/31/2021 01:24:04 - INFO - __main__ - Step 67401: {'lr': 0.00029538494056894596, 'samples': 12940992, 'steps': 67400, 'loss/train': 1.6706064939498901} 08/31/2021 01:24:04 - INFO - __main__ - Step 67402: {'lr': 0.000295379721993334, 'samples': 12941184, 'steps': 67401, 'loss/train': 0.9120582938194275} 08/31/2021 01:24:06 - INFO - __main__ - Step 67403: {'lr': 0.0002953745033972747, 'samples': 12941376, 'steps': 67402, 'loss/train': 1.4652910232543945} 08/31/2021 01:24:06 - INFO - __main__ - Step 67404: {'lr': 0.0002953692847807704, 'samples': 12941568, 'steps': 67403, 'loss/train': 1.4509997367858887} 08/31/2021 01:24:07 - INFO - __main__ - Step 67405: {'lr': 0.0002953640661438234, 'samples': 12941760, 'steps': 67404, 'loss/train': 1.1233372688293457} 08/31/2021 01:24:07 - INFO - __main__ - Step 67406: {'lr': 0.00029535884748643597, 'samples': 12941952, 'steps': 67405, 'loss/train': 0.7107851505279541} 08/31/2021 01:24:07 - INFO - __main__ - Step 67407: {'lr': 0.00029535362880861064, 'samples': 12942144, 'steps': 67406, 'loss/train': 0.9783292412757874} 08/31/2021 01:24:09 - INFO - __main__ - Step 67408: {'lr': 0.0002953484101103496, 'samples': 12942336, 'steps': 67407, 'loss/train': 0.7400608062744141} 08/31/2021 01:24:10 - INFO - __main__ - Step 67409: {'lr': 0.0002953431913916553, 'samples': 12942528, 'steps': 67408, 'loss/train': 1.3893479108810425} 08/31/2021 01:24:10 - INFO - __main__ - Step 67410: {'lr': 0.00029533797265253003, 'samples': 12942720, 'steps': 67409, 'loss/train': 1.5558645725250244} 08/31/2021 01:24:11 - INFO - __main__ - Step 67411: {'lr': 0.00029533275389297613, 'samples': 12942912, 'steps': 67410, 'loss/train': 1.423771858215332} 08/31/2021 01:24:11 - INFO - __main__ - Step 67412: {'lr': 0.0002953275351129961, 'samples': 12943104, 'steps': 67411, 'loss/train': 1.3812248706817627} 08/31/2021 01:24:12 - INFO - __main__ - Step 67413: {'lr': 0.0002953223163125921, 'samples': 12943296, 'steps': 67412, 'loss/train': 1.1578524112701416} 08/31/2021 01:24:13 - INFO - __main__ - Step 67414: {'lr': 0.00029531709749176663, 'samples': 12943488, 'steps': 67413, 'loss/train': 0.730228841304779} 08/31/2021 01:24:13 - INFO - __main__ - Step 67415: {'lr': 0.0002953118786505219, 'samples': 12943680, 'steps': 67414, 'loss/train': 1.493813157081604} 08/31/2021 01:24:14 - INFO - __main__ - Step 67416: {'lr': 0.0002953066597888604, 'samples': 12943872, 'steps': 67415, 'loss/train': 1.4018288850784302} 08/31/2021 01:24:14 - INFO - __main__ - Step 67417: {'lr': 0.0002953014409067844, 'samples': 12944064, 'steps': 67416, 'loss/train': 1.24613356590271} 08/31/2021 01:24:15 - INFO - __main__ - Step 67418: {'lr': 0.0002952962220042962, 'samples': 12944256, 'steps': 67417, 'loss/train': 1.3306128978729248} 08/31/2021 01:24:16 - INFO - __main__ - Step 67419: {'lr': 0.0002952910030813983, 'samples': 12944448, 'steps': 67418, 'loss/train': 0.04153592139482498} 08/31/2021 01:24:16 - INFO - __main__ - Step 67420: {'lr': 0.000295285784138093, 'samples': 12944640, 'steps': 67419, 'loss/train': 1.583031415939331} 08/31/2021 01:24:17 - INFO - __main__ - Step 67421: {'lr': 0.0002952805651743826, 'samples': 12944832, 'steps': 67420, 'loss/train': 1.3468540906906128} 08/31/2021 01:24:17 - INFO - __main__ - Step 67422: {'lr': 0.0002952753461902694, 'samples': 12945024, 'steps': 67421, 'loss/train': 1.521012783050537} 08/31/2021 01:24:19 - INFO - __main__ - Step 67423: {'lr': 0.00029527012718575583, 'samples': 12945216, 'steps': 67422, 'loss/train': 1.5916223526000977} 08/31/2021 01:24:19 - INFO - __main__ - Step 67424: {'lr': 0.00029526490816084427, 'samples': 12945408, 'steps': 67423, 'loss/train': 0.16509023308753967} 08/31/2021 01:24:19 - INFO - __main__ - Step 67425: {'lr': 0.00029525968911553707, 'samples': 12945600, 'steps': 67424, 'loss/train': 0.38010174036026} 08/31/2021 01:24:20 - INFO - __main__ - Step 67426: {'lr': 0.00029525447004983657, 'samples': 12945792, 'steps': 67425, 'loss/train': 0.8333727717399597} 08/31/2021 01:24:20 - INFO - __main__ - Step 67427: {'lr': 0.0002952492509637451, 'samples': 12945984, 'steps': 67426, 'loss/train': 1.302741527557373} 08/31/2021 01:24:22 - INFO - __main__ - Step 67428: {'lr': 0.000295244031857265, 'samples': 12946176, 'steps': 67427, 'loss/train': 1.3761940002441406} 08/31/2021 01:24:22 - INFO - __main__ - Step 67429: {'lr': 0.0002952388127303986, 'samples': 12946368, 'steps': 67428, 'loss/train': 0.9408570528030396} 08/31/2021 01:24:22 - INFO - __main__ - Step 67430: {'lr': 0.00029523359358314834, 'samples': 12946560, 'steps': 67429, 'loss/train': 1.5776751041412354} 08/31/2021 01:24:23 - INFO - __main__ - Step 67431: {'lr': 0.00029522837441551647, 'samples': 12946752, 'steps': 67430, 'loss/train': 2.912656784057617} 08/31/2021 01:24:23 - INFO - __main__ - Step 67432: {'lr': 0.00029522315522750544, 'samples': 12946944, 'steps': 67431, 'loss/train': 1.0118530988693237} 08/31/2021 01:24:23 - INFO - __main__ - Step 67433: {'lr': 0.0002952179360191175, 'samples': 12947136, 'steps': 67432, 'loss/train': 1.0948232412338257} 08/31/2021 01:24:25 - INFO - __main__ - Step 67434: {'lr': 0.00029521271679035514, 'samples': 12947328, 'steps': 67433, 'loss/train': 1.0634952783584595} 08/31/2021 01:24:26 - INFO - __main__ - Step 67435: {'lr': 0.00029520749754122054, 'samples': 12947520, 'steps': 67434, 'loss/train': 1.708784580230713} 08/31/2021 01:24:26 - INFO - __main__ - Step 67436: {'lr': 0.0002952022782717162, 'samples': 12947712, 'steps': 67435, 'loss/train': 1.2963018417358398} 08/31/2021 01:24:27 - INFO - __main__ - Step 67437: {'lr': 0.0002951970589818444, 'samples': 12947904, 'steps': 67436, 'loss/train': 0.6883227229118347} 08/31/2021 01:24:27 - INFO - __main__ - Step 67438: {'lr': 0.00029519183967160746, 'samples': 12948096, 'steps': 67437, 'loss/train': 1.2726694345474243} 08/31/2021 01:24:27 - INFO - __main__ - Step 67439: {'lr': 0.0002951866203410078, 'samples': 12948288, 'steps': 67438, 'loss/train': 5.778228282928467} 08/31/2021 01:24:29 - INFO - __main__ - Step 67440: {'lr': 0.00029518140099004774, 'samples': 12948480, 'steps': 67439, 'loss/train': 5.732555389404297} 08/31/2021 01:24:29 - INFO - __main__ - Step 67441: {'lr': 0.00029517618161872973, 'samples': 12948672, 'steps': 67440, 'loss/train': 5.7111711502075195} 08/31/2021 01:24:30 - INFO - __main__ - Step 67442: {'lr': 0.00029517096222705594, 'samples': 12948864, 'steps': 67441, 'loss/train': 1.4009931087493896} 08/31/2021 01:24:30 - INFO - __main__ - Step 67443: {'lr': 0.00029516574281502884, 'samples': 12949056, 'steps': 67442, 'loss/train': 1.1888713836669922} 08/31/2021 01:24:30 - INFO - __main__ - Step 67444: {'lr': 0.0002951605233826507, 'samples': 12949248, 'steps': 67443, 'loss/train': 1.184219479560852} 08/31/2021 01:24:32 - INFO - __main__ - Step 67445: {'lr': 0.00029515530392992394, 'samples': 12949440, 'steps': 67444, 'loss/train': 1.9230027198791504} 08/31/2021 01:24:32 - INFO - __main__ - Step 67446: {'lr': 0.00029515008445685096, 'samples': 12949632, 'steps': 67445, 'loss/train': 1.265867829322815} 08/31/2021 01:24:33 - INFO - __main__ - Step 67447: {'lr': 0.000295144864963434, 'samples': 12949824, 'steps': 67446, 'loss/train': 1.006935954093933} 08/31/2021 01:24:33 - INFO - __main__ - Step 67448: {'lr': 0.00029513964544967546, 'samples': 12950016, 'steps': 67447, 'loss/train': 1.0791599750518799} 08/31/2021 01:24:33 - INFO - __main__ - Step 67449: {'lr': 0.0002951344259155777, 'samples': 12950208, 'steps': 67448, 'loss/train': 1.3744630813598633} 08/31/2021 01:24:34 - INFO - __main__ - Step 67450: {'lr': 0.00029512920636114306, 'samples': 12950400, 'steps': 67449, 'loss/train': 1.2599045038223267} 08/31/2021 01:24:35 - INFO - __main__ - Step 67451: {'lr': 0.00029512398678637386, 'samples': 12950592, 'steps': 67450, 'loss/train': 0.6653138399124146} 08/31/2021 01:24:36 - INFO - __main__ - Step 67452: {'lr': 0.0002951187671912725, 'samples': 12950784, 'steps': 67451, 'loss/train': 1.4849673509597778} 08/31/2021 01:24:36 - INFO - __main__ - Step 67453: {'lr': 0.00029511354757584134, 'samples': 12950976, 'steps': 67452, 'loss/train': 1.2742420434951782} 08/31/2021 01:24:36 - INFO - __main__ - Step 67454: {'lr': 0.0002951083279400828, 'samples': 12951168, 'steps': 67453, 'loss/train': 0.22765424847602844} 08/31/2021 01:24:37 - INFO - __main__ - Step 67455: {'lr': 0.0002951031082839991, 'samples': 12951360, 'steps': 67454, 'loss/train': 1.2416462898254395} 08/31/2021 01:24:38 - INFO - __main__ - Step 67456: {'lr': 0.0002950978886075926, 'samples': 12951552, 'steps': 67455, 'loss/train': 1.2238677740097046} 08/31/2021 01:24:39 - INFO - __main__ - Step 67457: {'lr': 0.0002950926689108656, 'samples': 12951744, 'steps': 67456, 'loss/train': 0.8689148426055908} 08/31/2021 01:24:39 - INFO - __main__ - Step 67458: {'lr': 0.0002950874491938206, 'samples': 12951936, 'steps': 67457, 'loss/train': 1.053402066230774} 08/31/2021 01:24:39 - INFO - __main__ - Step 67459: {'lr': 0.00029508222945645997, 'samples': 12952128, 'steps': 67458, 'loss/train': 0.17238979041576385} 08/31/2021 01:24:40 - INFO - __main__ - Step 67460: {'lr': 0.00029507700969878586, 'samples': 12952320, 'steps': 67459, 'loss/train': 1.3985472917556763} 08/31/2021 01:24:42 - INFO - __main__ - Step 67461: {'lr': 0.00029507178992080086, 'samples': 12952512, 'steps': 67460, 'loss/train': 1.3489418029785156} 08/31/2021 01:24:43 - INFO - __main__ - Step 67462: {'lr': 0.00029506657012250717, 'samples': 12952704, 'steps': 67461, 'loss/train': 1.2790946960449219} 08/31/2021 01:24:43 - INFO - __main__ - Step 67463: {'lr': 0.0002950613503039072, 'samples': 12952896, 'steps': 67462, 'loss/train': 1.2824333906173706} 08/31/2021 01:24:44 - INFO - __main__ - Step 67464: {'lr': 0.00029505613046500325, 'samples': 12953088, 'steps': 67463, 'loss/train': 1.082503318786621} 08/31/2021 01:24:44 - INFO - __main__ - Step 67465: {'lr': 0.0002950509106057976, 'samples': 12953280, 'steps': 67464, 'loss/train': 0.4730348289012909} 08/31/2021 01:24:45 - INFO - __main__ - Step 67466: {'lr': 0.00029504569072629286, 'samples': 12953472, 'steps': 67465, 'loss/train': 0.12996917963027954} 08/31/2021 01:24:46 - INFO - __main__ - Step 67467: {'lr': 0.00029504047082649123, 'samples': 12953664, 'steps': 67466, 'loss/train': 1.7722407579421997} 08/31/2021 01:24:46 - INFO - __main__ - Step 67468: {'lr': 0.00029503525090639497, 'samples': 12953856, 'steps': 67467, 'loss/train': 1.7071295976638794} 08/31/2021 01:24:47 - INFO - __main__ - Step 67469: {'lr': 0.00029503003096600656, 'samples': 12954048, 'steps': 67468, 'loss/train': 1.4237823486328125} 08/31/2021 01:24:47 - INFO - __main__ - Step 67470: {'lr': 0.0002950248110053283, 'samples': 12954240, 'steps': 67469, 'loss/train': 0.9144507646560669} 08/31/2021 01:24:47 - INFO - __main__ - Step 67471: {'lr': 0.0002950195910243625, 'samples': 12954432, 'steps': 67470, 'loss/train': 0.832586407661438} 08/31/2021 01:24:50 - INFO - __main__ - Step 67472: {'lr': 0.00029501437102311167, 'samples': 12954624, 'steps': 67471, 'loss/train': 0.9960911870002747} 08/31/2021 01:24:50 - INFO - __main__ - Step 67473: {'lr': 0.000295009151001578, 'samples': 12954816, 'steps': 67472, 'loss/train': 1.449034333229065} 08/31/2021 01:24:51 - INFO - __main__ - Step 67474: {'lr': 0.000295003930959764, 'samples': 12955008, 'steps': 67473, 'loss/train': 1.8237203359603882} 08/31/2021 01:24:51 - INFO - __main__ - Step 67475: {'lr': 0.0002949987108976718, 'samples': 12955200, 'steps': 67474, 'loss/train': 0.054173603653907776} 08/31/2021 01:24:51 - INFO - __main__ - Step 67476: {'lr': 0.0002949934908153039, 'samples': 12955392, 'steps': 67475, 'loss/train': 0.4013930857181549} 08/31/2021 01:24:52 - INFO - __main__ - Step 67477: {'lr': 0.00029498827071266267, 'samples': 12955584, 'steps': 67476, 'loss/train': 0.35756543278694153} 08/31/2021 01:24:53 - INFO - __main__ - Step 67478: {'lr': 0.0002949830505897504, 'samples': 12955776, 'steps': 67477, 'loss/train': 1.3971511125564575} 08/31/2021 01:24:53 - INFO - __main__ - Step 67479: {'lr': 0.0002949778304465694, 'samples': 12955968, 'steps': 67478, 'loss/train': 1.0165722370147705} 08/31/2021 01:24:54 - INFO - __main__ - Step 67480: {'lr': 0.00029497261028312217, 'samples': 12956160, 'steps': 67479, 'loss/train': 0.6077296733856201} 08/31/2021 01:24:54 - INFO - __main__ - Step 67481: {'lr': 0.000294967390099411, 'samples': 12956352, 'steps': 67480, 'loss/train': 1.1521515846252441} 08/31/2021 01:24:54 - INFO - __main__ - Step 67482: {'lr': 0.0002949621698954381, 'samples': 12956544, 'steps': 67481, 'loss/train': 1.1490596532821655} 08/31/2021 01:24:56 - INFO - __main__ - Step 67483: {'lr': 0.000294956949671206, 'samples': 12956736, 'steps': 67482, 'loss/train': 1.487499475479126} 08/31/2021 01:24:57 - INFO - __main__ - Step 67484: {'lr': 0.000294951729426717, 'samples': 12956928, 'steps': 67483, 'loss/train': 1.2843458652496338} 08/31/2021 01:24:57 - INFO - __main__ - Step 67485: {'lr': 0.00029494650916197347, 'samples': 12957120, 'steps': 67484, 'loss/train': 1.2697501182556152} 08/31/2021 01:24:57 - INFO - __main__ - Step 67486: {'lr': 0.0002949412888769777, 'samples': 12957312, 'steps': 67485, 'loss/train': 0.3404081463813782} 08/31/2021 01:24:58 - INFO - __main__ - Step 67487: {'lr': 0.0002949360685717321, 'samples': 12957504, 'steps': 67486, 'loss/train': 1.2349153757095337} 08/31/2021 01:24:58 - INFO - __main__ - Step 67488: {'lr': 0.0002949308482462389, 'samples': 12957696, 'steps': 67487, 'loss/train': 1.048222303390503} 08/31/2021 01:24:59 - INFO - __main__ - Step 67489: {'lr': 0.0002949256279005007, 'samples': 12957888, 'steps': 67488, 'loss/train': 1.2878544330596924} 08/31/2021 01:25:00 - INFO - __main__ - Step 67490: {'lr': 0.00029492040753451964, 'samples': 12958080, 'steps': 67489, 'loss/train': 1.280605673789978} 08/31/2021 01:25:00 - INFO - __main__ - Step 67491: {'lr': 0.0002949151871482982, 'samples': 12958272, 'steps': 67490, 'loss/train': 0.8489207029342651} 08/31/2021 01:25:01 - INFO - __main__ - Step 67492: {'lr': 0.0002949099667418386, 'samples': 12958464, 'steps': 67491, 'loss/train': 1.50380277633667} 08/31/2021 01:25:01 - INFO - __main__ - Step 67493: {'lr': 0.0002949047463151432, 'samples': 12958656, 'steps': 67492, 'loss/train': 1.0486774444580078} 08/31/2021 01:25:02 - INFO - __main__ - Step 67494: {'lr': 0.0002948995258682145, 'samples': 12958848, 'steps': 67493, 'loss/train': 1.331679105758667} 08/31/2021 01:25:03 - INFO - __main__ - Step 67495: {'lr': 0.0002948943054010548, 'samples': 12959040, 'steps': 67494, 'loss/train': 0.9906023740768433} 08/31/2021 01:25:03 - INFO - __main__ - Step 67496: {'lr': 0.0002948890849136664, 'samples': 12959232, 'steps': 67495, 'loss/train': 1.5816479921340942} 08/31/2021 01:25:04 - INFO - __main__ - Step 67497: {'lr': 0.00029488386440605164, 'samples': 12959424, 'steps': 67496, 'loss/train': 1.5642073154449463} 08/31/2021 01:25:04 - INFO - __main__ - Step 67498: {'lr': 0.0002948786438782129, 'samples': 12959616, 'steps': 67497, 'loss/train': 1.1807430982589722} 08/31/2021 01:25:06 - INFO - __main__ - Step 67499: {'lr': 0.00029487342333015253, 'samples': 12959808, 'steps': 67498, 'loss/train': 1.4790843725204468} 08/31/2021 01:25:06 - INFO - __main__ - Step 67500: {'lr': 0.0002948682027618729, 'samples': 12960000, 'steps': 67499, 'loss/train': 0.5809208154678345} 08/31/2021 01:25:06 - INFO - __main__ - Step 67501: {'lr': 0.0002948629821733764, 'samples': 12960192, 'steps': 67500, 'loss/train': 1.2198457717895508} 08/31/2021 01:25:07 - INFO - __main__ - Step 67502: {'lr': 0.00029485776156466527, 'samples': 12960384, 'steps': 67501, 'loss/train': 1.4482365846633911} 08/31/2021 01:25:07 - INFO - __main__ - Step 67503: {'lr': 0.0002948525409357419, 'samples': 12960576, 'steps': 67502, 'loss/train': 0.6510043740272522} 08/31/2021 01:25:09 - INFO - __main__ - Step 67504: {'lr': 0.0002948473202866087, 'samples': 12960768, 'steps': 67503, 'loss/train': 1.2182202339172363} 08/31/2021 01:25:09 - INFO - __main__ - Step 67505: {'lr': 0.000294842099617268, 'samples': 12960960, 'steps': 67504, 'loss/train': 2.339989185333252} 08/31/2021 01:25:10 - INFO - __main__ - Step 67506: {'lr': 0.00029483687892772214, 'samples': 12961152, 'steps': 67505, 'loss/train': 1.2019106149673462} 08/31/2021 01:25:10 - INFO - __main__ - Step 67507: {'lr': 0.0002948316582179734, 'samples': 12961344, 'steps': 67506, 'loss/train': 1.0574510097503662} 08/31/2021 01:25:10 - INFO - __main__ - Step 67508: {'lr': 0.00029482643748802436, 'samples': 12961536, 'steps': 67507, 'loss/train': 0.9048876166343689} 08/31/2021 01:25:12 - INFO - __main__ - Step 67509: {'lr': 0.00029482121673787717, 'samples': 12961728, 'steps': 67508, 'loss/train': 1.5761804580688477} 08/31/2021 01:25:12 - INFO - __main__ - Step 67510: {'lr': 0.00029481599596753417, 'samples': 12961920, 'steps': 67509, 'loss/train': 1.4274176359176636} 08/31/2021 01:25:13 - INFO - __main__ - Step 67511: {'lr': 0.0002948107751769978, 'samples': 12962112, 'steps': 67510, 'loss/train': 0.28467699885368347} 08/31/2021 01:25:13 - INFO - __main__ - Step 67512: {'lr': 0.00029480555436627037, 'samples': 12962304, 'steps': 67511, 'loss/train': 0.9065371751785278} 08/31/2021 01:25:13 - INFO - __main__ - Step 67513: {'lr': 0.00029480033353535424, 'samples': 12962496, 'steps': 67512, 'loss/train': 0.7665656208992004} 08/31/2021 01:25:15 - INFO - __main__ - Step 67514: {'lr': 0.00029479511268425183, 'samples': 12962688, 'steps': 67513, 'loss/train': 1.478581190109253} 08/31/2021 01:25:16 - INFO - __main__ - Step 67515: {'lr': 0.0002947898918129654, 'samples': 12962880, 'steps': 67514, 'loss/train': 1.6228762865066528} 08/31/2021 01:25:16 - INFO - __main__ - Step 67516: {'lr': 0.00029478467092149737, 'samples': 12963072, 'steps': 67515, 'loss/train': 0.5968645811080933} 08/31/2021 01:25:17 - INFO - __main__ - Step 67517: {'lr': 0.00029477945000984997, 'samples': 12963264, 'steps': 67516, 'loss/train': 1.3465945720672607} 08/31/2021 01:25:17 - INFO - __main__ - Step 67518: {'lr': 0.0002947742290780257, 'samples': 12963456, 'steps': 67517, 'loss/train': 1.1241309642791748} 08/31/2021 01:25:17 - INFO - __main__ - Step 67519: {'lr': 0.0002947690081260269, 'samples': 12963648, 'steps': 67518, 'loss/train': 1.3193233013153076} 08/31/2021 01:25:19 - INFO - __main__ - Step 67520: {'lr': 0.0002947637871538558, 'samples': 12963840, 'steps': 67519, 'loss/train': 1.1454368829727173} 08/31/2021 01:25:19 - INFO - __main__ - Step 67521: {'lr': 0.00029475856616151486, 'samples': 12964032, 'steps': 67520, 'loss/train': 1.115240216255188} 08/31/2021 01:25:20 - INFO - __main__ - Step 67522: {'lr': 0.00029475334514900636, 'samples': 12964224, 'steps': 67521, 'loss/train': 1.251710057258606} 08/31/2021 01:25:20 - INFO - __main__ - Step 67523: {'lr': 0.0002947481241163327, 'samples': 12964416, 'steps': 67522, 'loss/train': 0.957309365272522} 08/31/2021 01:25:20 - INFO - __main__ - Step 67524: {'lr': 0.0002947429030634963, 'samples': 12964608, 'steps': 67523, 'loss/train': 1.319569706916809} 08/31/2021 01:25:22 - INFO - __main__ - Step 67525: {'lr': 0.0002947376819904994, 'samples': 12964800, 'steps': 67524, 'loss/train': 1.3572741746902466} 08/31/2021 01:25:23 - INFO - __main__ - Step 67526: {'lr': 0.00029473246089734435, 'samples': 12964992, 'steps': 67525, 'loss/train': 1.2257887125015259} 08/31/2021 01:25:23 - INFO - __main__ - Step 67527: {'lr': 0.00029472723978403356, 'samples': 12965184, 'steps': 67526, 'loss/train': 0.6159338355064392} 08/31/2021 01:25:24 - INFO - __main__ - Step 67528: {'lr': 0.0002947220186505694, 'samples': 12965376, 'steps': 67527, 'loss/train': 0.027352485805749893} 08/31/2021 01:25:24 - INFO - __main__ - Step 67529: {'lr': 0.0002947167974969542, 'samples': 12965568, 'steps': 67528, 'loss/train': 0.18472923338413239} 08/31/2021 01:25:24 - INFO - __main__ - Step 67530: {'lr': 0.00029471157632319025, 'samples': 12965760, 'steps': 67529, 'loss/train': 0.19179576635360718} 08/31/2021 01:25:26 - INFO - __main__ - Step 67531: {'lr': 0.00029470635512928, 'samples': 12965952, 'steps': 67530, 'loss/train': 0.032553426921367645} 08/31/2021 01:25:26 - INFO - __main__ - Step 67532: {'lr': 0.00029470113391522567, 'samples': 12966144, 'steps': 67531, 'loss/train': 1.3554996252059937} 08/31/2021 01:25:27 - INFO - __main__ - Step 67533: {'lr': 0.0002946959126810298, 'samples': 12966336, 'steps': 67532, 'loss/train': 1.0145596265792847} 08/31/2021 01:25:27 - INFO - __main__ - Step 67534: {'lr': 0.00029469069142669456, 'samples': 12966528, 'steps': 67533, 'loss/train': 1.0344198942184448} 08/31/2021 01:25:27 - INFO - __main__ - Step 67535: {'lr': 0.0002946854701522225, 'samples': 12966720, 'steps': 67534, 'loss/train': 1.8306282758712769} 08/31/2021 01:25:30 - INFO - __main__ - Step 67536: {'lr': 0.00029468024885761574, 'samples': 12966912, 'steps': 67535, 'loss/train': 1.1045925617218018} 08/31/2021 01:25:30 - INFO - __main__ - Step 67537: {'lr': 0.00029467502754287677, 'samples': 12967104, 'steps': 67536, 'loss/train': 0.6841279864311218} 08/31/2021 01:25:31 - INFO - __main__ - Step 67538: {'lr': 0.00029466980620800797, 'samples': 12967296, 'steps': 67537, 'loss/train': 1.211939811706543} 08/31/2021 01:25:31 - INFO - __main__ - Step 67539: {'lr': 0.0002946645848530116, 'samples': 12967488, 'steps': 67538, 'loss/train': 1.581418514251709} 08/31/2021 01:25:31 - INFO - __main__ - Step 67540: {'lr': 0.00029465936347789005, 'samples': 12967680, 'steps': 67539, 'loss/train': 0.36600154638290405} 08/31/2021 01:25:32 - INFO - __main__ - Step 67541: {'lr': 0.00029465414208264577, 'samples': 12967872, 'steps': 67540, 'loss/train': 0.3008045554161072} 08/31/2021 01:25:32 - INFO - __main__ - Step 67542: {'lr': 0.0002946489206672809, 'samples': 12968064, 'steps': 67541, 'loss/train': 0.3125803768634796} 08/31/2021 01:25:33 - INFO - __main__ - Step 67543: {'lr': 0.00029464369923179804, 'samples': 12968256, 'steps': 67542, 'loss/train': 0.05140071362257004} 08/31/2021 01:25:34 - INFO - __main__ - Step 67544: {'lr': 0.00029463847777619936, 'samples': 12968448, 'steps': 67543, 'loss/train': 1.3441611528396606} 08/31/2021 01:25:34 - INFO - __main__ - Step 67545: {'lr': 0.0002946332563004872, 'samples': 12968640, 'steps': 67544, 'loss/train': 1.475769281387329} 08/31/2021 01:25:35 - INFO - __main__ - Step 67546: {'lr': 0.00029462803480466405, 'samples': 12968832, 'steps': 67545, 'loss/train': 1.5134835243225098} 08/31/2021 01:25:35 - INFO - __main__ - Step 67547: {'lr': 0.0002946228132887322, 'samples': 12969024, 'steps': 67546, 'loss/train': 1.5749351978302002} 08/31/2021 01:25:37 - INFO - __main__ - Step 67548: {'lr': 0.00029461759175269405, 'samples': 12969216, 'steps': 67547, 'loss/train': 1.2563568353652954} 08/31/2021 01:25:37 - INFO - __main__ - Step 67549: {'lr': 0.0002946123701965518, 'samples': 12969408, 'steps': 67548, 'loss/train': 1.3792693614959717} 08/31/2021 01:25:38 - INFO - __main__ - Step 67550: {'lr': 0.0002946071486203079, 'samples': 12969600, 'steps': 67549, 'loss/train': 1.550318956375122} 08/31/2021 01:25:38 - INFO - __main__ - Step 67551: {'lr': 0.0002946019270239648, 'samples': 12969792, 'steps': 67550, 'loss/train': 0.5708853602409363} 08/31/2021 01:25:38 - INFO - __main__ - Step 67552: {'lr': 0.0002945967054075247, 'samples': 12969984, 'steps': 67551, 'loss/train': 1.0339009761810303} 08/31/2021 01:25:39 - INFO - __main__ - Step 67553: {'lr': 0.00029459148377099, 'samples': 12970176, 'steps': 67552, 'loss/train': 1.3088515996932983} 08/31/2021 01:25:40 - INFO - __main__ - Step 67554: {'lr': 0.0002945862621143631, 'samples': 12970368, 'steps': 67553, 'loss/train': 0.027694443240761757} 08/31/2021 01:25:41 - INFO - __main__ - Step 67555: {'lr': 0.0002945810404376463, 'samples': 12970560, 'steps': 67554, 'loss/train': 0.7318239808082581} 08/31/2021 01:25:41 - INFO - __main__ - Step 67556: {'lr': 0.000294575818740842, 'samples': 12970752, 'steps': 67555, 'loss/train': 1.2023646831512451} 08/31/2021 01:25:41 - INFO - __main__ - Step 67557: {'lr': 0.0002945705970239525, 'samples': 12970944, 'steps': 67556, 'loss/train': 1.4832589626312256} 08/31/2021 01:25:42 - INFO - __main__ - Step 67558: {'lr': 0.0002945653752869802, 'samples': 12971136, 'steps': 67557, 'loss/train': 2.309269428253174} 08/31/2021 01:25:42 - INFO - __main__ - Step 67559: {'lr': 0.0002945601535299274, 'samples': 12971328, 'steps': 67558, 'loss/train': 1.3034013509750366} 08/31/2021 01:25:44 - INFO - __main__ - Step 67560: {'lr': 0.0002945549317527965, 'samples': 12971520, 'steps': 67559, 'loss/train': 1.3933744430541992} 08/31/2021 01:25:44 - INFO - __main__ - Step 67561: {'lr': 0.0002945497099555898, 'samples': 12971712, 'steps': 67560, 'loss/train': 1.8231050968170166} 08/31/2021 01:25:45 - INFO - __main__ - Step 67562: {'lr': 0.00029454448813830977, 'samples': 12971904, 'steps': 67561, 'loss/train': 1.231293797492981} 08/31/2021 01:25:45 - INFO - __main__ - Step 67563: {'lr': 0.0002945392663009586, 'samples': 12972096, 'steps': 67562, 'loss/train': 1.5082104206085205} 08/31/2021 01:25:45 - INFO - __main__ - Step 67564: {'lr': 0.00029453404444353874, 'samples': 12972288, 'steps': 67563, 'loss/train': 1.40010404586792} 08/31/2021 01:25:47 - INFO - __main__ - Step 67565: {'lr': 0.0002945288225660525, 'samples': 12972480, 'steps': 67564, 'loss/train': 0.15225431323051453} 08/31/2021 01:25:47 - INFO - __main__ - Step 67566: {'lr': 0.00029452360066850234, 'samples': 12972672, 'steps': 67565, 'loss/train': 5.05982780456543} 08/31/2021 01:25:47 - INFO - __main__ - Step 67567: {'lr': 0.0002945183787508905, 'samples': 12972864, 'steps': 67566, 'loss/train': 1.6740440130233765} 08/31/2021 01:25:48 - INFO - __main__ - Step 67568: {'lr': 0.0002945131568132194, 'samples': 12973056, 'steps': 67567, 'loss/train': 1.0191590785980225} 08/31/2021 01:25:48 - INFO - __main__ - Step 67569: {'lr': 0.00029450793485549125, 'samples': 12973248, 'steps': 67568, 'loss/train': 0.9287869930267334} 08/31/2021 01:25:50 - INFO - __main__ - Step 67570: {'lr': 0.00029450271287770856, 'samples': 12973440, 'steps': 67569, 'loss/train': 1.3281569480895996} 08/31/2021 01:25:50 - INFO - __main__ - Step 67571: {'lr': 0.0002944974908798737, 'samples': 12973632, 'steps': 67570, 'loss/train': 1.0224125385284424} 08/31/2021 01:25:51 - INFO - __main__ - Step 67572: {'lr': 0.00029449226886198886, 'samples': 12973824, 'steps': 67571, 'loss/train': 0.5426316261291504} 08/31/2021 01:25:51 - INFO - __main__ - Step 67573: {'lr': 0.0002944870468240566, 'samples': 12974016, 'steps': 67572, 'loss/train': 1.027237057685852} 08/31/2021 01:25:51 - INFO - __main__ - Step 67574: {'lr': 0.00029448182476607903, 'samples': 12974208, 'steps': 67573, 'loss/train': 0.43833068013191223} 08/31/2021 01:25:53 - INFO - __main__ - Step 67575: {'lr': 0.00029447660268805875, 'samples': 12974400, 'steps': 67574, 'loss/train': 1.873935580253601} 08/31/2021 01:25:54 - INFO - __main__ - Step 67576: {'lr': 0.000294471380589998, 'samples': 12974592, 'steps': 67575, 'loss/train': 1.5200519561767578} 08/31/2021 01:25:54 - INFO - __main__ - Step 67577: {'lr': 0.0002944661584718991, 'samples': 12974784, 'steps': 67576, 'loss/train': 0.17684932053089142} 08/31/2021 01:25:54 - INFO - __main__ - Step 67578: {'lr': 0.00029446093633376434, 'samples': 12974976, 'steps': 67577, 'loss/train': 1.6804553270339966} 08/31/2021 01:25:55 - INFO - __main__ - Step 67579: {'lr': 0.00029445571417559626, 'samples': 12975168, 'steps': 67578, 'loss/train': 1.537541151046753} 08/31/2021 01:25:56 - INFO - __main__ - Step 67580: {'lr': 0.0002944504919973971, 'samples': 12975360, 'steps': 67579, 'loss/train': 1.0340267419815063} 08/31/2021 01:25:57 - INFO - __main__ - Step 67581: {'lr': 0.00029444526979916923, 'samples': 12975552, 'steps': 67580, 'loss/train': 1.2682172060012817} 08/31/2021 01:25:57 - INFO - __main__ - Step 67582: {'lr': 0.0002944400475809151, 'samples': 12975744, 'steps': 67581, 'loss/train': 0.9088749885559082} 08/31/2021 01:25:57 - INFO - __main__ - Step 67583: {'lr': 0.0002944348253426369, 'samples': 12975936, 'steps': 67582, 'loss/train': 0.8514489531517029} 08/31/2021 01:25:58 - INFO - __main__ - Step 67584: {'lr': 0.00029442960308433705, 'samples': 12976128, 'steps': 67583, 'loss/train': 0.7605417966842651} 08/31/2021 01:25:58 - INFO - __main__ - Step 67585: {'lr': 0.00029442438080601785, 'samples': 12976320, 'steps': 67584, 'loss/train': 0.7546161413192749} 08/31/2021 01:26:00 - INFO - __main__ - Step 67586: {'lr': 0.0002944191585076817, 'samples': 12976512, 'steps': 67585, 'loss/train': 0.7804756760597229} 08/31/2021 01:26:00 - INFO - __main__ - Step 67587: {'lr': 0.0002944139361893311, 'samples': 12976704, 'steps': 67586, 'loss/train': 1.52971351146698} 08/31/2021 01:26:00 - INFO - __main__ - Step 67588: {'lr': 0.0002944087138509682, 'samples': 12976896, 'steps': 67587, 'loss/train': 2.074720621109009} 08/31/2021 01:26:01 - INFO - __main__ - Step 67589: {'lr': 0.0002944034914925954, 'samples': 12977088, 'steps': 67588, 'loss/train': 0.8770108819007874} 08/31/2021 01:26:01 - INFO - __main__ - Step 67590: {'lr': 0.0002943982691142151, 'samples': 12977280, 'steps': 67589, 'loss/train': 1.226244568824768} 08/31/2021 01:26:03 - INFO - __main__ - Step 67591: {'lr': 0.0002943930467158296, 'samples': 12977472, 'steps': 67590, 'loss/train': 1.2671470642089844} 08/31/2021 01:26:03 - INFO - __main__ - Step 67592: {'lr': 0.00029438782429744124, 'samples': 12977664, 'steps': 67591, 'loss/train': 1.538426399230957} 08/31/2021 01:26:03 - INFO - __main__ - Step 67593: {'lr': 0.00029438260185905255, 'samples': 12977856, 'steps': 67592, 'loss/train': 1.075835943222046} 08/31/2021 01:26:04 - INFO - __main__ - Step 67594: {'lr': 0.00029437737940066563, 'samples': 12978048, 'steps': 67593, 'loss/train': 1.0521397590637207} 08/31/2021 01:26:04 - INFO - __main__ - Step 67595: {'lr': 0.000294372156922283, 'samples': 12978240, 'steps': 67594, 'loss/train': 0.9949709177017212} 08/31/2021 01:26:06 - INFO - __main__ - Step 67596: {'lr': 0.0002943669344239069, 'samples': 12978432, 'steps': 67595, 'loss/train': 1.3948193788528442} 08/31/2021 01:26:06 - INFO - __main__ - Step 67597: {'lr': 0.00029436171190553976, 'samples': 12978624, 'steps': 67596, 'loss/train': 1.2240782976150513} 08/31/2021 01:26:06 - INFO - __main__ - Step 67598: {'lr': 0.00029435648936718394, 'samples': 12978816, 'steps': 67597, 'loss/train': 0.8198760151863098} 08/31/2021 01:26:07 - INFO - __main__ - Step 67599: {'lr': 0.0002943512668088417, 'samples': 12979008, 'steps': 67598, 'loss/train': 1.3189784288406372} 08/31/2021 01:26:07 - INFO - __main__ - Step 67600: {'lr': 0.0002943460442305156, 'samples': 12979200, 'steps': 67599, 'loss/train': 0.605216920375824} 08/31/2021 01:26:09 - INFO - __main__ - Step 67601: {'lr': 0.0002943408216322077, 'samples': 12979392, 'steps': 67600, 'loss/train': 0.6598116159439087} 08/31/2021 01:26:09 - INFO - __main__ - Step 67602: {'lr': 0.00029433559901392067, 'samples': 12979584, 'steps': 67601, 'loss/train': 1.2130626440048218} 08/31/2021 01:26:09 - INFO - __main__ - Step 67603: {'lr': 0.00029433037637565664, 'samples': 12979776, 'steps': 67602, 'loss/train': 0.6383997201919556} 08/31/2021 01:26:10 - INFO - __main__ - Step 67604: {'lr': 0.000294325153717418, 'samples': 12979968, 'steps': 67603, 'loss/train': 1.302760124206543} 08/31/2021 01:26:10 - INFO - __main__ - Step 67605: {'lr': 0.00029431993103920713, 'samples': 12980160, 'steps': 67604, 'loss/train': 0.039868611842393875} 08/31/2021 01:26:12 - INFO - __main__ - Step 67606: {'lr': 0.00029431470834102635, 'samples': 12980352, 'steps': 67605, 'loss/train': 1.3586688041687012} 08/31/2021 01:26:12 - INFO - __main__ - Step 67607: {'lr': 0.00029430948562287815, 'samples': 12980544, 'steps': 67606, 'loss/train': 1.6338838338851929} 08/31/2021 01:26:12 - INFO - __main__ - Step 67608: {'lr': 0.00029430426288476464, 'samples': 12980736, 'steps': 67607, 'loss/train': 1.1228686571121216} 08/31/2021 01:26:13 - INFO - __main__ - Step 67609: {'lr': 0.00029429904012668847, 'samples': 12980928, 'steps': 67608, 'loss/train': 1.5154340267181396} 08/31/2021 01:26:13 - INFO - __main__ - Step 67610: {'lr': 0.00029429381734865176, 'samples': 12981120, 'steps': 67609, 'loss/train': 1.1369274854660034} 08/31/2021 01:26:15 - INFO - __main__ - Step 67611: {'lr': 0.00029428859455065694, 'samples': 12981312, 'steps': 67610, 'loss/train': 0.775677502155304} 08/31/2021 01:26:15 - INFO - __main__ - Step 67612: {'lr': 0.00029428337173270636, 'samples': 12981504, 'steps': 67611, 'loss/train': 1.2640856504440308} 08/31/2021 01:26:16 - INFO - __main__ - Step 67613: {'lr': 0.0002942781488948024, 'samples': 12981696, 'steps': 67612, 'loss/train': 1.32713782787323} 08/31/2021 01:26:16 - INFO - __main__ - Step 67614: {'lr': 0.0002942729260369473, 'samples': 12981888, 'steps': 67613, 'loss/train': 1.2284284830093384} 08/31/2021 01:26:16 - INFO - __main__ - Step 67615: {'lr': 0.0002942677031591436, 'samples': 12982080, 'steps': 67614, 'loss/train': 1.3896325826644897} 08/31/2021 01:26:17 - INFO - __main__ - Step 67616: {'lr': 0.00029426248026139353, 'samples': 12982272, 'steps': 67615, 'loss/train': 0.5761620402336121} 08/31/2021 01:26:18 - INFO - __main__ - Step 67617: {'lr': 0.00029425725734369944, 'samples': 12982464, 'steps': 67616, 'loss/train': 0.6355273723602295} 08/31/2021 01:26:19 - INFO - __main__ - Step 67618: {'lr': 0.0002942520344060637, 'samples': 12982656, 'steps': 67617, 'loss/train': 1.2448889017105103} 08/31/2021 01:26:19 - INFO - __main__ - Step 67619: {'lr': 0.0002942468114484888, 'samples': 12982848, 'steps': 67618, 'loss/train': 1.1575102806091309} 08/31/2021 01:26:19 - INFO - __main__ - Step 67620: {'lr': 0.00029424158847097685, 'samples': 12983040, 'steps': 67619, 'loss/train': 1.6303410530090332} 08/31/2021 01:26:20 - INFO - __main__ - Step 67621: {'lr': 0.00029423636547353037, 'samples': 12983232, 'steps': 67620, 'loss/train': 1.1523674726486206} 08/31/2021 01:26:22 - INFO - __main__ - Step 67622: {'lr': 0.0002942311424561517, 'samples': 12983424, 'steps': 67621, 'loss/train': 1.1182472705841064} 08/31/2021 01:26:23 - INFO - __main__ - Step 67623: {'lr': 0.0002942259194188431, 'samples': 12983616, 'steps': 67622, 'loss/train': 0.9650672674179077} 08/31/2021 01:26:23 - INFO - __main__ - Step 67624: {'lr': 0.000294220696361607, 'samples': 12983808, 'steps': 67623, 'loss/train': 1.5158580541610718} 08/31/2021 01:26:23 - INFO - __main__ - Step 67625: {'lr': 0.0002942154732844458, 'samples': 12984000, 'steps': 67624, 'loss/train': 1.7997028827667236} 08/31/2021 01:26:24 - INFO - __main__ - Step 67626: {'lr': 0.00029421025018736165, 'samples': 12984192, 'steps': 67625, 'loss/train': 1.476909875869751} 08/31/2021 01:26:26 - INFO - __main__ - Step 67627: {'lr': 0.0002942050270703571, 'samples': 12984384, 'steps': 67626, 'loss/train': 0.08484278619289398} 08/31/2021 01:26:26 - INFO - __main__ - Step 67628: {'lr': 0.0002941998039334345, 'samples': 12984576, 'steps': 67627, 'loss/train': 0.9266104102134705} 08/31/2021 01:26:26 - INFO - __main__ - Step 67629: {'lr': 0.00029419458077659604, 'samples': 12984768, 'steps': 67628, 'loss/train': 1.6690266132354736} 08/31/2021 01:26:27 - INFO - __main__ - Step 67630: {'lr': 0.0002941893575998443, 'samples': 12984960, 'steps': 67629, 'loss/train': 0.8716647624969482} 08/31/2021 01:26:27 - INFO - __main__ - Step 67631: {'lr': 0.00029418413440318147, 'samples': 12985152, 'steps': 67630, 'loss/train': 1.4257428646087646} 08/31/2021 01:26:27 - INFO - __main__ - Step 67632: {'lr': 0.00029417891118661, 'samples': 12985344, 'steps': 67631, 'loss/train': 1.3895775079727173} 08/31/2021 01:26:29 - INFO - __main__ - Step 67633: {'lr': 0.0002941736879501321, 'samples': 12985536, 'steps': 67632, 'loss/train': 0.9006094932556152} 08/31/2021 01:26:29 - INFO - __main__ - Step 67634: {'lr': 0.00029416846469375026, 'samples': 12985728, 'steps': 67633, 'loss/train': 0.8364992737770081} 08/31/2021 01:26:30 - INFO - __main__ - Step 67635: {'lr': 0.0002941632414174668, 'samples': 12985920, 'steps': 67634, 'loss/train': 2.1838459968566895} 08/31/2021 01:26:30 - INFO - __main__ - Step 67636: {'lr': 0.00029415801812128413, 'samples': 12986112, 'steps': 67635, 'loss/train': 1.2810273170471191} 08/31/2021 01:26:30 - INFO - __main__ - Step 67637: {'lr': 0.00029415279480520445, 'samples': 12986304, 'steps': 67636, 'loss/train': 1.1099156141281128} 08/31/2021 01:26:32 - INFO - __main__ - Step 67638: {'lr': 0.0002941475714692302, 'samples': 12986496, 'steps': 67637, 'loss/train': 0.7762098908424377} 08/31/2021 01:26:32 - INFO - __main__ - Step 67639: {'lr': 0.00029414234811336377, 'samples': 12986688, 'steps': 67638, 'loss/train': 0.8204135894775391} 08/31/2021 01:26:33 - INFO - __main__ - Step 67640: {'lr': 0.00029413712473760743, 'samples': 12986880, 'steps': 67639, 'loss/train': 1.0015863180160522} 08/31/2021 01:26:33 - INFO - __main__ - Step 67641: {'lr': 0.0002941319013419637, 'samples': 12987072, 'steps': 67640, 'loss/train': 1.3725167512893677} 08/31/2021 01:26:34 - INFO - __main__ - Step 67642: {'lr': 0.00029412667792643474, 'samples': 12987264, 'steps': 67641, 'loss/train': 1.3615374565124512} 08/31/2021 01:26:35 - INFO - __main__ - Step 67643: {'lr': 0.00029412145449102294, 'samples': 12987456, 'steps': 67642, 'loss/train': 1.3450583219528198} 08/31/2021 01:26:35 - INFO - __main__ - Step 67644: {'lr': 0.0002941162310357307, 'samples': 12987648, 'steps': 67643, 'loss/train': 1.6693906784057617} 08/31/2021 01:26:36 - INFO - __main__ - Step 67645: {'lr': 0.0002941110075605604, 'samples': 12987840, 'steps': 67644, 'loss/train': 0.8538834452629089} 08/31/2021 01:26:36 - INFO - __main__ - Step 67646: {'lr': 0.00029410578406551435, 'samples': 12988032, 'steps': 67645, 'loss/train': 1.2981783151626587} 08/31/2021 01:26:36 - INFO - __main__ - Step 67647: {'lr': 0.0002941005605505949, 'samples': 12988224, 'steps': 67646, 'loss/train': 1.263508677482605} 08/31/2021 01:26:38 - INFO - __main__ - Step 67648: {'lr': 0.0002940953370158045, 'samples': 12988416, 'steps': 67647, 'loss/train': 0.5747990608215332} 08/31/2021 01:26:39 - INFO - __main__ - Step 67649: {'lr': 0.00029409011346114537, 'samples': 12988608, 'steps': 67648, 'loss/train': 1.3437682390213013} 08/31/2021 01:26:39 - INFO - __main__ - Step 67650: {'lr': 0.0002940848898866199, 'samples': 12988800, 'steps': 67649, 'loss/train': 1.1183520555496216} 08/31/2021 01:26:39 - INFO - __main__ - Step 67651: {'lr': 0.00029407966629223047, 'samples': 12988992, 'steps': 67650, 'loss/train': 1.140228271484375} 08/31/2021 01:26:40 - INFO - __main__ - Step 67652: {'lr': 0.0002940744426779794, 'samples': 12989184, 'steps': 67651, 'loss/train': 1.366222858428955} 08/31/2021 01:26:41 - INFO - __main__ - Step 67653: {'lr': 0.0002940692190438691, 'samples': 12989376, 'steps': 67652, 'loss/train': 0.910083532333374} 08/31/2021 01:26:41 - INFO - __main__ - Step 67654: {'lr': 0.00029406399538990186, 'samples': 12989568, 'steps': 67653, 'loss/train': 1.3089193105697632} 08/31/2021 01:26:42 - INFO - __main__ - Step 67655: {'lr': 0.00029405877171608007, 'samples': 12989760, 'steps': 67654, 'loss/train': 1.1004831790924072} 08/31/2021 01:26:42 - INFO - __main__ - Step 67656: {'lr': 0.0002940535480224061, 'samples': 12989952, 'steps': 67655, 'loss/train': 1.4602506160736084} 08/31/2021 01:26:43 - INFO - __main__ - Step 67657: {'lr': 0.0002940483243088823, 'samples': 12990144, 'steps': 67656, 'loss/train': 1.502648115158081} 08/31/2021 01:26:44 - INFO - __main__ - Step 67658: {'lr': 0.00029404310057551094, 'samples': 12990336, 'steps': 67657, 'loss/train': 1.1525663137435913} 08/31/2021 01:26:44 - INFO - __main__ - Step 67659: {'lr': 0.00029403787682229444, 'samples': 12990528, 'steps': 67658, 'loss/train': 0.9391362071037292} 08/31/2021 01:26:45 - INFO - __main__ - Step 67660: {'lr': 0.0002940326530492352, 'samples': 12990720, 'steps': 67659, 'loss/train': 0.8489968180656433} 08/31/2021 01:26:45 - INFO - __main__ - Step 67661: {'lr': 0.00029402742925633554, 'samples': 12990912, 'steps': 67660, 'loss/train': 1.2628432512283325} 08/31/2021 01:26:45 - INFO - __main__ - Step 67662: {'lr': 0.00029402220544359775, 'samples': 12991104, 'steps': 67661, 'loss/train': 0.645639181137085} 08/31/2021 01:26:47 - INFO - __main__ - Step 67663: {'lr': 0.00029401698161102426, 'samples': 12991296, 'steps': 67662, 'loss/train': 1.317683458328247} 08/31/2021 01:26:47 - INFO - __main__ - Step 67664: {'lr': 0.00029401175775861736, 'samples': 12991488, 'steps': 67663, 'loss/train': 1.3180159330368042} 08/31/2021 01:26:48 - INFO - __main__ - Step 67665: {'lr': 0.00029400653388637947, 'samples': 12991680, 'steps': 67664, 'loss/train': 1.4643876552581787} 08/31/2021 01:26:48 - INFO - __main__ - Step 67666: {'lr': 0.00029400130999431294, 'samples': 12991872, 'steps': 67665, 'loss/train': 1.206943392753601} 08/31/2021 01:26:48 - INFO - __main__ - Step 67667: {'lr': 0.0002939960860824201, 'samples': 12992064, 'steps': 67666, 'loss/train': 1.0702707767486572} 08/31/2021 01:26:50 - INFO - __main__ - Step 67668: {'lr': 0.00029399086215070326, 'samples': 12992256, 'steps': 67667, 'loss/train': 1.4917488098144531} 08/31/2021 01:26:50 - INFO - __main__ - Step 67669: {'lr': 0.0002939856381991649, 'samples': 12992448, 'steps': 67668, 'loss/train': 1.0763754844665527} 08/31/2021 01:26:51 - INFO - __main__ - Step 67670: {'lr': 0.00029398041422780717, 'samples': 12992640, 'steps': 67669, 'loss/train': 1.1433665752410889} 08/31/2021 01:26:51 - INFO - __main__ - Step 67671: {'lr': 0.0002939751902366326, 'samples': 12992832, 'steps': 67670, 'loss/train': 1.1712336540222168} 08/31/2021 01:26:51 - INFO - __main__ - Step 67672: {'lr': 0.00029396996622564343, 'samples': 12993024, 'steps': 67671, 'loss/train': 1.0535351037979126} 08/31/2021 01:26:53 - INFO - __main__ - Step 67673: {'lr': 0.00029396474219484217, 'samples': 12993216, 'steps': 67672, 'loss/train': 1.5168027877807617} 08/31/2021 01:26:54 - INFO - __main__ - Step 67674: {'lr': 0.000293959518144231, 'samples': 12993408, 'steps': 67673, 'loss/train': 1.7700157165527344} 08/31/2021 01:26:54 - INFO - __main__ - Step 67675: {'lr': 0.00029395429407381236, 'samples': 12993600, 'steps': 67674, 'loss/train': 1.5775692462921143} 08/31/2021 01:26:54 - INFO - __main__ - Step 67676: {'lr': 0.0002939490699835887, 'samples': 12993792, 'steps': 67675, 'loss/train': 1.150404453277588} 08/31/2021 01:26:55 - INFO - __main__ - Step 67677: {'lr': 0.0002939438458735622, 'samples': 12993984, 'steps': 67676, 'loss/train': 1.7574855089187622} 08/31/2021 01:26:56 - INFO - __main__ - Step 67678: {'lr': 0.0002939386217437352, 'samples': 12994176, 'steps': 67677, 'loss/train': 1.3206948041915894} 08/31/2021 01:26:57 - INFO - __main__ - Step 67679: {'lr': 0.0002939333975941102, 'samples': 12994368, 'steps': 67678, 'loss/train': 1.4929358959197998} 08/31/2021 01:26:57 - INFO - __main__ - Step 67680: {'lr': 0.0002939281734246895, 'samples': 12994560, 'steps': 67679, 'loss/train': 1.2412688732147217} 08/31/2021 01:26:57 - INFO - __main__ - Step 67681: {'lr': 0.0002939229492354754, 'samples': 12994752, 'steps': 67680, 'loss/train': 1.506327748298645} 08/31/2021 01:26:58 - INFO - __main__ - Step 67682: {'lr': 0.00029391772502647027, 'samples': 12994944, 'steps': 67681, 'loss/train': 1.5312684774398804} 08/31/2021 01:26:59 - INFO - __main__ - Step 67683: {'lr': 0.0002939125007976766, 'samples': 12995136, 'steps': 67682, 'loss/train': 1.6676218509674072} 08/31/2021 01:27:00 - INFO - __main__ - Step 67684: {'lr': 0.0002939072765490966, 'samples': 12995328, 'steps': 67683, 'loss/train': 1.2224570512771606} 08/31/2021 01:27:00 - INFO - __main__ - Step 67685: {'lr': 0.00029390205228073266, 'samples': 12995520, 'steps': 67684, 'loss/train': 0.20221272110939026} 08/31/2021 01:27:00 - INFO - __main__ - Step 67686: {'lr': 0.0002938968279925871, 'samples': 12995712, 'steps': 67685, 'loss/train': 1.3263001441955566} 08/31/2021 01:27:01 - INFO - __main__ - Step 67687: {'lr': 0.00029389160368466227, 'samples': 12995904, 'steps': 67686, 'loss/train': 1.045846700668335} 08/31/2021 01:27:01 - INFO - __main__ - Step 67688: {'lr': 0.0002938863793569606, 'samples': 12996096, 'steps': 67687, 'loss/train': 1.0698065757751465} 08/31/2021 01:27:03 - INFO - __main__ - Step 67689: {'lr': 0.0002938811550094845, 'samples': 12996288, 'steps': 67688, 'loss/train': 1.2167071104049683} 08/31/2021 01:27:03 - INFO - __main__ - Step 67690: {'lr': 0.00029387593064223615, 'samples': 12996480, 'steps': 67689, 'loss/train': 1.2290935516357422} 08/31/2021 01:27:03 - INFO - __main__ - Step 67691: {'lr': 0.00029387070625521794, 'samples': 12996672, 'steps': 67690, 'loss/train': 0.9320974946022034} 08/31/2021 01:27:04 - INFO - __main__ - Step 67692: {'lr': 0.00029386548184843234, 'samples': 12996864, 'steps': 67691, 'loss/train': 1.0502053499221802} 08/31/2021 01:27:04 - INFO - __main__ - Step 67693: {'lr': 0.00029386025742188156, 'samples': 12997056, 'steps': 67692, 'loss/train': 1.209747552871704} 08/31/2021 01:27:05 - INFO - __main__ - Step 67694: {'lr': 0.00029385503297556806, 'samples': 12997248, 'steps': 67693, 'loss/train': 0.8616365194320679} 08/31/2021 01:27:06 - INFO - __main__ - Step 67695: {'lr': 0.00029384980850949416, 'samples': 12997440, 'steps': 67694, 'loss/train': 1.2265609502792358} 08/31/2021 01:27:06 - INFO - __main__ - Step 67696: {'lr': 0.0002938445840236622, 'samples': 12997632, 'steps': 67695, 'loss/train': 1.6409012079238892} 08/31/2021 01:27:07 - INFO - __main__ - Step 67697: {'lr': 0.0002938393595180746, 'samples': 12997824, 'steps': 67696, 'loss/train': 1.208688497543335} 08/31/2021 01:27:07 - INFO - __main__ - Step 67698: {'lr': 0.0002938341349927336, 'samples': 12998016, 'steps': 67697, 'loss/train': 0.5845790505409241} 08/31/2021 01:27:09 - INFO - __main__ - Step 67699: {'lr': 0.00029382891044764164, 'samples': 12998208, 'steps': 67698, 'loss/train': 1.2500959634780884} 08/31/2021 01:27:09 - INFO - __main__ - Step 67700: {'lr': 0.000293823685882801, 'samples': 12998400, 'steps': 67699, 'loss/train': 0.858209490776062} 08/31/2021 01:27:09 - INFO - __main__ - Step 67701: {'lr': 0.00029381846129821414, 'samples': 12998592, 'steps': 67700, 'loss/train': 3.7993946075439453} 08/31/2021 01:27:10 - INFO - __main__ - Step 67702: {'lr': 0.0002938132366938833, 'samples': 12998784, 'steps': 67701, 'loss/train': 1.1374431848526} 08/31/2021 01:27:10 - INFO - __main__ - Step 67703: {'lr': 0.00029380801206981103, 'samples': 12998976, 'steps': 67702, 'loss/train': 1.332762360572815} 08/31/2021 01:27:11 - INFO - __main__ - Step 67704: {'lr': 0.0002938027874259994, 'samples': 12999168, 'steps': 67703, 'loss/train': 1.1688268184661865} 08/31/2021 01:27:12 - INFO - __main__ - Step 67705: {'lr': 0.000293797562762451, 'samples': 12999360, 'steps': 67704, 'loss/train': 1.3029675483703613} 08/31/2021 01:27:12 - INFO - __main__ - Step 67706: {'lr': 0.00029379233807916804, 'samples': 12999552, 'steps': 67705, 'loss/train': 1.6076828241348267} 08/31/2021 01:27:13 - INFO - __main__ - Step 67707: {'lr': 0.0002937871133761529, 'samples': 12999744, 'steps': 67706, 'loss/train': 1.6269893646240234} 08/31/2021 01:27:13 - INFO - __main__ - Step 67708: {'lr': 0.00029378188865340803, 'samples': 12999936, 'steps': 67707, 'loss/train': 1.5229400396347046} 08/31/2021 01:27:14 - INFO - __main__ - Step 67709: {'lr': 0.0002937766639109357, 'samples': 13000128, 'steps': 67708, 'loss/train': 1.5997381210327148} 08/31/2021 01:27:15 - INFO - __main__ - Step 67710: {'lr': 0.00029377143914873833, 'samples': 13000320, 'steps': 67709, 'loss/train': 0.750806987285614} 08/31/2021 01:27:15 - INFO - __main__ - Step 67711: {'lr': 0.0002937662143668182, 'samples': 13000512, 'steps': 67710, 'loss/train': 0.6204168796539307} 08/31/2021 01:27:16 - INFO - __main__ - Step 67712: {'lr': 0.0002937609895651776, 'samples': 13000704, 'steps': 67711, 'loss/train': 0.9506745934486389} 08/31/2021 01:27:16 - INFO - __main__ - Step 67713: {'lr': 0.00029375576474381903, 'samples': 13000896, 'steps': 67712, 'loss/train': 0.7126471996307373} 08/31/2021 01:27:17 - INFO - __main__ - Step 67714: {'lr': 0.00029375053990274476, 'samples': 13001088, 'steps': 67713, 'loss/train': 1.5883266925811768} 08/31/2021 01:27:18 - INFO - __main__ - Step 67715: {'lr': 0.00029374531504195724, 'samples': 13001280, 'steps': 67714, 'loss/train': 1.214419960975647} 08/31/2021 01:27:18 - INFO - __main__ - Step 67716: {'lr': 0.0002937400901614588, 'samples': 13001472, 'steps': 67715, 'loss/train': 1.440848469734192} 08/31/2021 01:27:19 - INFO - __main__ - Step 67717: {'lr': 0.00029373486526125157, 'samples': 13001664, 'steps': 67716, 'loss/train': 1.781884789466858} 08/31/2021 01:27:19 - INFO - __main__ - Step 67718: {'lr': 0.0002937296403413382, 'samples': 13001856, 'steps': 67717, 'loss/train': 1.6651355028152466} 08/31/2021 01:27:19 - INFO - __main__ - Step 67719: {'lr': 0.0002937244154017209, 'samples': 13002048, 'steps': 67718, 'loss/train': 1.194791555404663} 08/31/2021 01:27:21 - INFO - __main__ - Step 67720: {'lr': 0.00029371919044240204, 'samples': 13002240, 'steps': 67719, 'loss/train': 0.19807156920433044} 08/31/2021 01:27:21 - INFO - __main__ - Step 67721: {'lr': 0.000293713965463384, 'samples': 13002432, 'steps': 67720, 'loss/train': 0.19977091252803802} 08/31/2021 01:27:22 - INFO - __main__ - Step 67722: {'lr': 0.00029370874046466913, 'samples': 13002624, 'steps': 67721, 'loss/train': 1.1623387336730957} 08/31/2021 01:27:22 - INFO - __main__ - Step 67723: {'lr': 0.0002937035154462598, 'samples': 13002816, 'steps': 67722, 'loss/train': 2.5569345951080322} 08/31/2021 01:27:22 - INFO - __main__ - Step 67724: {'lr': 0.0002936982904081583, 'samples': 13003008, 'steps': 67723, 'loss/train': 0.1575649380683899} 08/31/2021 01:27:24 - INFO - __main__ - Step 67725: {'lr': 0.0002936930653503671, 'samples': 13003200, 'steps': 67724, 'loss/train': 1.6640188694000244} 08/31/2021 01:27:25 - INFO - __main__ - Step 67726: {'lr': 0.00029368784027288843, 'samples': 13003392, 'steps': 67725, 'loss/train': 1.454827904701233} 08/31/2021 01:27:25 - INFO - __main__ - Step 67727: {'lr': 0.0002936826151757246, 'samples': 13003584, 'steps': 67726, 'loss/train': 1.443440556526184} 08/31/2021 01:27:26 - INFO - __main__ - Step 67728: {'lr': 0.00029367739005887816, 'samples': 13003776, 'steps': 67727, 'loss/train': 1.1221339702606201} 08/31/2021 01:27:26 - INFO - __main__ - Step 67729: {'lr': 0.00029367216492235136, 'samples': 13003968, 'steps': 67728, 'loss/train': 1.2911723852157593} 08/31/2021 01:27:28 - INFO - __main__ - Step 67730: {'lr': 0.00029366693976614656, 'samples': 13004160, 'steps': 67729, 'loss/train': 1.1682153940200806} 08/31/2021 01:27:28 - INFO - __main__ - Step 67731: {'lr': 0.00029366171459026616, 'samples': 13004352, 'steps': 67730, 'loss/train': 1.823222279548645} 08/31/2021 01:27:29 - INFO - __main__ - Step 67732: {'lr': 0.00029365648939471236, 'samples': 13004544, 'steps': 67731, 'loss/train': 1.1395870447158813} 08/31/2021 01:27:29 - INFO - __main__ - Step 67733: {'lr': 0.0002936512641794876, 'samples': 13004736, 'steps': 67732, 'loss/train': 0.8194634318351746} 08/31/2021 01:27:29 - INFO - __main__ - Step 67734: {'lr': 0.00029364603894459435, 'samples': 13004928, 'steps': 67733, 'loss/train': 0.02316165156662464} 08/31/2021 01:27:30 - INFO - __main__ - Step 67735: {'lr': 0.0002936408136900348, 'samples': 13005120, 'steps': 67734, 'loss/train': 1.3779635429382324} 08/31/2021 01:27:31 - INFO - __main__ - Step 67736: {'lr': 0.00029363558841581145, 'samples': 13005312, 'steps': 67735, 'loss/train': 1.7655869722366333} 08/31/2021 01:27:32 - INFO - __main__ - Step 67737: {'lr': 0.00029363036312192654, 'samples': 13005504, 'steps': 67736, 'loss/train': 1.3618533611297607} 08/31/2021 01:27:32 - INFO - __main__ - Step 67738: {'lr': 0.0002936251378083824, 'samples': 13005696, 'steps': 67737, 'loss/train': 1.1401805877685547} 08/31/2021 01:27:32 - INFO - __main__ - Step 67739: {'lr': 0.00029361991247518147, 'samples': 13005888, 'steps': 67738, 'loss/train': 1.5209671258926392} 08/31/2021 01:27:33 - INFO - __main__ - Step 67740: {'lr': 0.00029361468712232614, 'samples': 13006080, 'steps': 67739, 'loss/train': 1.108688235282898} 08/31/2021 01:27:34 - INFO - __main__ - Step 67741: {'lr': 0.0002936094617498187, 'samples': 13006272, 'steps': 67740, 'loss/train': 1.2196228504180908} 08/31/2021 01:27:35 - INFO - __main__ - Step 67742: {'lr': 0.0002936042363576614, 'samples': 13006464, 'steps': 67741, 'loss/train': 1.5712743997573853} 08/31/2021 01:27:35 - INFO - __main__ - Step 67743: {'lr': 0.00029359901094585687, 'samples': 13006656, 'steps': 67742, 'loss/train': 1.140502691268921} 08/31/2021 01:27:35 - INFO - __main__ - Step 67744: {'lr': 0.00029359378551440724, 'samples': 13006848, 'steps': 67743, 'loss/train': 1.7112559080123901} 08/31/2021 01:27:36 - INFO - __main__ - Step 67745: {'lr': 0.00029358856006331485, 'samples': 13007040, 'steps': 67744, 'loss/train': 1.1642491817474365} 08/31/2021 01:27:37 - INFO - __main__ - Step 67746: {'lr': 0.0002935833345925822, 'samples': 13007232, 'steps': 67745, 'loss/train': 0.557751476764679} 08/31/2021 01:27:38 - INFO - __main__ - Step 67747: {'lr': 0.00029357810910221155, 'samples': 13007424, 'steps': 67746, 'loss/train': 1.4865726232528687} 08/31/2021 01:27:38 - INFO - __main__ - Step 67748: {'lr': 0.0002935728835922053, 'samples': 13007616, 'steps': 67747, 'loss/train': 1.6170045137405396} 08/31/2021 01:27:38 - INFO - __main__ - Step 67749: {'lr': 0.00029356765806256576, 'samples': 13007808, 'steps': 67748, 'loss/train': 1.003379225730896} 08/31/2021 01:27:39 - INFO - __main__ - Step 67750: {'lr': 0.0002935624325132953, 'samples': 13008000, 'steps': 67749, 'loss/train': 1.3694719076156616} 08/31/2021 01:27:40 - INFO - __main__ - Step 67751: {'lr': 0.00029355720694439625, 'samples': 13008192, 'steps': 67750, 'loss/train': 1.1237156391143799} 08/31/2021 01:27:41 - INFO - __main__ - Step 67752: {'lr': 0.00029355198135587105, 'samples': 13008384, 'steps': 67751, 'loss/train': 1.8917272090911865} 08/31/2021 01:27:41 - INFO - __main__ - Step 67753: {'lr': 0.00029354675574772194, 'samples': 13008576, 'steps': 67752, 'loss/train': 0.7052973508834839} 08/31/2021 01:27:42 - INFO - __main__ - Step 67754: {'lr': 0.00029354153011995144, 'samples': 13008768, 'steps': 67753, 'loss/train': 0.9476897120475769} 08/31/2021 01:27:42 - INFO - __main__ - Step 67755: {'lr': 0.0002935363044725617, 'samples': 13008960, 'steps': 67754, 'loss/train': 1.478770136833191} 08/31/2021 01:27:43 - INFO - __main__ - Step 67756: {'lr': 0.00029353107880555516, 'samples': 13009152, 'steps': 67755, 'loss/train': 1.295505166053772} 08/31/2021 01:27:44 - INFO - __main__ - Step 67757: {'lr': 0.00029352585311893427, 'samples': 13009344, 'steps': 67756, 'loss/train': 1.538504958152771} 08/31/2021 01:27:44 - INFO - __main__ - Step 67758: {'lr': 0.00029352062741270124, 'samples': 13009536, 'steps': 67757, 'loss/train': 1.3233448266983032} 08/31/2021 01:27:45 - INFO - __main__ - Step 67759: {'lr': 0.0002935154016868585, 'samples': 13009728, 'steps': 67758, 'loss/train': 1.2219573259353638} 08/31/2021 01:27:45 - INFO - __main__ - Step 67760: {'lr': 0.00029351017594140844, 'samples': 13009920, 'steps': 67759, 'loss/train': 1.1147633790969849} 08/31/2021 01:27:45 - INFO - __main__ - Step 67761: {'lr': 0.00029350495017635333, 'samples': 13010112, 'steps': 67760, 'loss/train': 1.1172040700912476} 08/31/2021 01:27:47 - INFO - __main__ - Step 67762: {'lr': 0.0002934997243916955, 'samples': 13010304, 'steps': 67761, 'loss/train': 1.3613258600234985} 08/31/2021 01:27:47 - INFO - __main__ - Step 67763: {'lr': 0.00029349449858743744, 'samples': 13010496, 'steps': 67762, 'loss/train': 1.7507621049880981} 08/31/2021 01:27:48 - INFO - __main__ - Step 67764: {'lr': 0.0002934892727635814, 'samples': 13010688, 'steps': 67763, 'loss/train': 0.8134829998016357} 08/31/2021 01:27:48 - INFO - __main__ - Step 67765: {'lr': 0.00029348404692012983, 'samples': 13010880, 'steps': 67764, 'loss/train': 2.14795184135437} 08/31/2021 01:27:48 - INFO - __main__ - Step 67766: {'lr': 0.00029347882105708496, 'samples': 13011072, 'steps': 67765, 'loss/train': 1.1795177459716797} 08/31/2021 01:27:50 - INFO - __main__ - Step 67767: {'lr': 0.00029347359517444915, 'samples': 13011264, 'steps': 67766, 'loss/train': 1.0529487133026123} 08/31/2021 01:27:50 - INFO - __main__ - Step 67768: {'lr': 0.0002934683692722249, 'samples': 13011456, 'steps': 67767, 'loss/train': 1.436017632484436} 08/31/2021 01:27:50 - INFO - __main__ - Step 67769: {'lr': 0.0002934631433504145, 'samples': 13011648, 'steps': 67768, 'loss/train': 0.9785046577453613} 08/31/2021 01:27:51 - INFO - __main__ - Step 67770: {'lr': 0.0002934579174090202, 'samples': 13011840, 'steps': 67769, 'loss/train': 1.2661105394363403} 08/31/2021 01:27:51 - INFO - __main__ - Step 67771: {'lr': 0.0002934526914480444, 'samples': 13012032, 'steps': 67770, 'loss/train': 1.304181694984436} 08/31/2021 01:27:53 - INFO - __main__ - Step 67772: {'lr': 0.0002934474654674896, 'samples': 13012224, 'steps': 67771, 'loss/train': 0.202386736869812} 08/31/2021 01:27:53 - INFO - __main__ - Step 67773: {'lr': 0.00029344223946735793, 'samples': 13012416, 'steps': 67772, 'loss/train': 0.9503214955329895} 08/31/2021 01:27:53 - INFO - __main__ - Step 67774: {'lr': 0.00029343701344765197, 'samples': 13012608, 'steps': 67773, 'loss/train': 1.3504685163497925} 08/31/2021 01:27:54 - INFO - __main__ - Step 67775: {'lr': 0.00029343178740837383, 'samples': 13012800, 'steps': 67774, 'loss/train': 1.2671312093734741} 08/31/2021 01:27:54 - INFO - __main__ - Step 67776: {'lr': 0.00029342656134952606, 'samples': 13012992, 'steps': 67775, 'loss/train': 1.2872108221054077} 08/31/2021 01:27:56 - INFO - __main__ - Step 67777: {'lr': 0.00029342133527111104, 'samples': 13013184, 'steps': 67776, 'loss/train': 1.705499529838562} 08/31/2021 01:27:56 - INFO - __main__ - Step 67778: {'lr': 0.00029341610917313094, 'samples': 13013376, 'steps': 67777, 'loss/train': 1.6610145568847656} 08/31/2021 01:27:56 - INFO - __main__ - Step 67779: {'lr': 0.0002934108830555882, 'samples': 13013568, 'steps': 67778, 'loss/train': 1.4618042707443237} 08/31/2021 01:27:57 - INFO - __main__ - Step 67780: {'lr': 0.0002934056569184852, 'samples': 13013760, 'steps': 67779, 'loss/train': 1.6170578002929688} 08/31/2021 01:27:57 - INFO - __main__ - Step 67781: {'lr': 0.0002934004307618243, 'samples': 13013952, 'steps': 67780, 'loss/train': 1.0044476985931396} 08/31/2021 01:27:59 - INFO - __main__ - Step 67782: {'lr': 0.0002933952045856078, 'samples': 13014144, 'steps': 67781, 'loss/train': 0.9746813178062439} 08/31/2021 01:28:00 - INFO - __main__ - Step 67783: {'lr': 0.00029338997838983824, 'samples': 13014336, 'steps': 67782, 'loss/train': 1.037432312965393} 08/31/2021 01:28:00 - INFO - __main__ - Step 67784: {'lr': 0.00029338475217451765, 'samples': 13014528, 'steps': 67783, 'loss/train': 1.4095760583877563} 08/31/2021 01:28:00 - INFO - __main__ - Step 67785: {'lr': 0.00029337952593964863, 'samples': 13014720, 'steps': 67784, 'loss/train': 1.1553125381469727} 08/31/2021 01:28:01 - INFO - __main__ - Step 67786: {'lr': 0.00029337429968523344, 'samples': 13014912, 'steps': 67785, 'loss/train': 3.4595673084259033} 08/31/2021 01:28:02 - INFO - __main__ - Step 67787: {'lr': 0.00029336907341127443, 'samples': 13015104, 'steps': 67786, 'loss/train': 0.9514287710189819} 08/31/2021 01:28:03 - INFO - __main__ - Step 67788: {'lr': 0.00029336384711777403, 'samples': 13015296, 'steps': 67787, 'loss/train': 0.36007747054100037} 08/31/2021 01:28:03 - INFO - __main__ - Step 67789: {'lr': 0.0002933586208047345, 'samples': 13015488, 'steps': 67788, 'loss/train': 1.3276890516281128} 08/31/2021 01:28:03 - INFO - __main__ - Step 67790: {'lr': 0.0002933533944721584, 'samples': 13015680, 'steps': 67789, 'loss/train': 1.2317603826522827} 08/31/2021 01:28:04 - INFO - __main__ - Step 67791: {'lr': 0.0002933481681200478, 'samples': 13015872, 'steps': 67790, 'loss/train': 1.3801147937774658} 08/31/2021 01:28:05 - INFO - __main__ - Step 67792: {'lr': 0.0002933429417484052, 'samples': 13016064, 'steps': 67791, 'loss/train': 4.078406810760498} 08/31/2021 01:28:06 - INFO - __main__ - Step 67793: {'lr': 0.00029333771535723294, 'samples': 13016256, 'steps': 67792, 'loss/train': 1.3747847080230713} 08/31/2021 01:28:06 - INFO - __main__ - Step 67794: {'lr': 0.00029333248894653337, 'samples': 13016448, 'steps': 67793, 'loss/train': 0.0653805211186409} 08/31/2021 01:28:07 - INFO - __main__ - Step 67795: {'lr': 0.0002933272625163088, 'samples': 13016640, 'steps': 67794, 'loss/train': 0.708601176738739} 08/31/2021 01:28:07 - INFO - __main__ - Step 67796: {'lr': 0.00029332203606656173, 'samples': 13016832, 'steps': 67795, 'loss/train': 1.356740117073059} 08/31/2021 01:28:09 - INFO - __main__ - Step 67797: {'lr': 0.0002933168095972944, 'samples': 13017024, 'steps': 67796, 'loss/train': 1.4471186399459839} 08/31/2021 01:28:09 - INFO - __main__ - Step 67798: {'lr': 0.00029331158310850916, 'samples': 13017216, 'steps': 67797, 'loss/train': 1.6261558532714844} 08/31/2021 01:28:09 - INFO - __main__ - Step 67799: {'lr': 0.00029330635660020836, 'samples': 13017408, 'steps': 67798, 'loss/train': 1.3138643503189087} 08/31/2021 01:28:10 - INFO - __main__ - Step 67800: {'lr': 0.00029330113007239447, 'samples': 13017600, 'steps': 67799, 'loss/train': 2.3387339115142822} 08/31/2021 01:28:10 - INFO - __main__ - Step 67801: {'lr': 0.0002932959035250697, 'samples': 13017792, 'steps': 67800, 'loss/train': 1.4281854629516602} 08/31/2021 01:28:10 - INFO - __main__ - Step 67802: {'lr': 0.0002932906769582364, 'samples': 13017984, 'steps': 67801, 'loss/train': 1.3780803680419922} 08/31/2021 01:28:12 - INFO - __main__ - Step 67803: {'lr': 0.00029328545037189707, 'samples': 13018176, 'steps': 67802, 'loss/train': 1.4125933647155762} 08/31/2021 01:28:12 - INFO - __main__ - Step 67804: {'lr': 0.000293280223766054, 'samples': 13018368, 'steps': 67803, 'loss/train': 1.472554087638855} 08/31/2021 01:28:13 - INFO - __main__ - Step 67805: {'lr': 0.0002932749971407095, 'samples': 13018560, 'steps': 67804, 'loss/train': 1.0547653436660767} 08/31/2021 01:28:13 - INFO - __main__ - Step 67806: {'lr': 0.000293269770495866, 'samples': 13018752, 'steps': 67805, 'loss/train': 0.2848556637763977} 08/31/2021 01:28:13 - INFO - __main__ - Step 67807: {'lr': 0.0002932645438315257, 'samples': 13018944, 'steps': 67806, 'loss/train': 1.2572823762893677} 08/31/2021 01:28:15 - INFO - __main__ - Step 67808: {'lr': 0.00029325931714769117, 'samples': 13019136, 'steps': 67807, 'loss/train': 1.1319494247436523} 08/31/2021 01:28:15 - INFO - __main__ - Step 67809: {'lr': 0.00029325409044436457, 'samples': 13019328, 'steps': 67808, 'loss/train': 1.1553261280059814} 08/31/2021 01:28:16 - INFO - __main__ - Step 67810: {'lr': 0.00029324886372154846, 'samples': 13019520, 'steps': 67809, 'loss/train': 1.4062318801879883} 08/31/2021 01:28:16 - INFO - __main__ - Step 67811: {'lr': 0.000293243636979245, 'samples': 13019712, 'steps': 67810, 'loss/train': 1.2439489364624023} 08/31/2021 01:28:16 - INFO - __main__ - Step 67812: {'lr': 0.0002932384102174566, 'samples': 13019904, 'steps': 67811, 'loss/train': 0.8763661980628967} 08/31/2021 01:28:18 - INFO - __main__ - Step 67813: {'lr': 0.00029323318343618573, 'samples': 13020096, 'steps': 67812, 'loss/train': 1.1972851753234863} 08/31/2021 01:28:18 - INFO - __main__ - Step 67814: {'lr': 0.00029322795663543457, 'samples': 13020288, 'steps': 67813, 'loss/train': 0.526793360710144} 08/31/2021 01:28:19 - INFO - __main__ - Step 67815: {'lr': 0.0002932227298152056, 'samples': 13020480, 'steps': 67814, 'loss/train': 1.164121389389038} 08/31/2021 01:28:19 - INFO - __main__ - Step 67816: {'lr': 0.0002932175029755011, 'samples': 13020672, 'steps': 67815, 'loss/train': 1.7077429294586182} 08/31/2021 01:28:20 - INFO - __main__ - Step 67817: {'lr': 0.0002932122761163235, 'samples': 13020864, 'steps': 67816, 'loss/train': 0.7477916479110718} 08/31/2021 01:28:21 - INFO - __main__ - Step 67818: {'lr': 0.0002932070492376751, 'samples': 13021056, 'steps': 67817, 'loss/train': 1.6902118921279907} 08/31/2021 01:28:22 - INFO - __main__ - Step 67819: {'lr': 0.00029320182233955825, 'samples': 13021248, 'steps': 67818, 'loss/train': 1.8069305419921875} 08/31/2021 01:28:22 - INFO - __main__ - Step 67820: {'lr': 0.00029319659542197536, 'samples': 13021440, 'steps': 67819, 'loss/train': 0.5530529618263245} 08/31/2021 01:28:22 - INFO - __main__ - Step 67821: {'lr': 0.0002931913684849287, 'samples': 13021632, 'steps': 67820, 'loss/train': 1.4641697406768799} 08/31/2021 01:28:23 - INFO - __main__ - Step 67822: {'lr': 0.00029318614152842073, 'samples': 13021824, 'steps': 67821, 'loss/train': 1.1220003366470337} 08/31/2021 01:28:24 - INFO - __main__ - Step 67823: {'lr': 0.0002931809145524537, 'samples': 13022016, 'steps': 67822, 'loss/train': 1.7820667028427124} 08/31/2021 01:28:24 - INFO - __main__ - Step 67824: {'lr': 0.0002931756875570301, 'samples': 13022208, 'steps': 67823, 'loss/train': 1.2005202770233154} 08/31/2021 01:28:25 - INFO - __main__ - Step 67825: {'lr': 0.0002931704605421522, 'samples': 13022400, 'steps': 67824, 'loss/train': 1.3338478803634644} 08/31/2021 01:28:25 - INFO - __main__ - Step 67826: {'lr': 0.00029316523350782225, 'samples': 13022592, 'steps': 67825, 'loss/train': 1.3109687566757202} 08/31/2021 01:28:26 - INFO - __main__ - Step 67827: {'lr': 0.0002931600064540428, 'samples': 13022784, 'steps': 67826, 'loss/train': 1.184797763824463} 08/31/2021 01:28:27 - INFO - __main__ - Step 67828: {'lr': 0.0002931547793808161, 'samples': 13022976, 'steps': 67827, 'loss/train': 1.2667001485824585} 08/31/2021 01:28:28 - INFO - __main__ - Step 67829: {'lr': 0.0002931495522881445, 'samples': 13023168, 'steps': 67828, 'loss/train': 1.0324605703353882} 08/31/2021 01:28:28 - INFO - __main__ - Step 67830: {'lr': 0.00029314432517603043, 'samples': 13023360, 'steps': 67829, 'loss/train': 1.204369068145752} 08/31/2021 01:28:28 - INFO - __main__ - Step 67831: {'lr': 0.0002931390980444761, 'samples': 13023552, 'steps': 67830, 'loss/train': 0.8425908088684082} 08/31/2021 01:28:29 - INFO - __main__ - Step 67832: {'lr': 0.000293133870893484, 'samples': 13023744, 'steps': 67831, 'loss/train': 1.7275841236114502} 08/31/2021 01:28:29 - INFO - __main__ - Step 67833: {'lr': 0.0002931286437230565, 'samples': 13023936, 'steps': 67832, 'loss/train': 1.2768758535385132} 08/31/2021 01:28:29 - INFO - __main__ - Step 67834: {'lr': 0.0002931234165331958, 'samples': 13024128, 'steps': 67833, 'loss/train': 1.5382429361343384} 08/31/2021 01:28:32 - INFO - __main__ - Step 67835: {'lr': 0.0002931181893239044, 'samples': 13024320, 'steps': 67834, 'loss/train': 0.586150586605072} 08/31/2021 01:28:32 - INFO - __main__ - Step 67836: {'lr': 0.0002931129620951846, 'samples': 13024512, 'steps': 67835, 'loss/train': 0.938522458076477} 08/31/2021 01:28:32 - INFO - __main__ - Step 67837: {'lr': 0.0002931077348470388, 'samples': 13024704, 'steps': 67836, 'loss/train': 1.4998631477355957} 08/31/2021 01:28:33 - INFO - __main__ - Step 67838: {'lr': 0.00029310250757946934, 'samples': 13024896, 'steps': 67837, 'loss/train': 0.8181996941566467} 08/31/2021 01:28:33 - INFO - __main__ - Step 67839: {'lr': 0.0002930972802924785, 'samples': 13025088, 'steps': 67838, 'loss/train': 0.5255703926086426} 08/31/2021 01:28:35 - INFO - __main__ - Step 67840: {'lr': 0.00029309205298606866, 'samples': 13025280, 'steps': 67839, 'loss/train': 1.2995777130126953} 08/31/2021 01:28:35 - INFO - __main__ - Step 67841: {'lr': 0.00029308682566024224, 'samples': 13025472, 'steps': 67840, 'loss/train': 1.6298691034317017} 08/31/2021 01:28:35 - INFO - __main__ - Step 67842: {'lr': 0.0002930815983150016, 'samples': 13025664, 'steps': 67841, 'loss/train': 1.2745720148086548} 08/31/2021 01:28:36 - INFO - __main__ - Step 67843: {'lr': 0.000293076370950349, 'samples': 13025856, 'steps': 67842, 'loss/train': 1.7493703365325928} 08/31/2021 01:28:36 - INFO - __main__ - Step 67844: {'lr': 0.00029307114356628695, 'samples': 13026048, 'steps': 67843, 'loss/train': 1.0781060457229614} 08/31/2021 01:28:38 - INFO - __main__ - Step 67845: {'lr': 0.0002930659161628176, 'samples': 13026240, 'steps': 67844, 'loss/train': 1.3015398979187012} 08/31/2021 01:28:38 - INFO - __main__ - Step 67846: {'lr': 0.0002930606887399435, 'samples': 13026432, 'steps': 67845, 'loss/train': 1.4417784214019775} 08/31/2021 01:28:39 - INFO - __main__ - Step 67847: {'lr': 0.0002930554612976668, 'samples': 13026624, 'steps': 67846, 'loss/train': 0.22774933278560638} 08/31/2021 01:28:39 - INFO - __main__ - Step 67848: {'lr': 0.00029305023383599006, 'samples': 13026816, 'steps': 67847, 'loss/train': 0.04829039424657822} 08/31/2021 01:28:39 - INFO - __main__ - Step 67849: {'lr': 0.0002930450063549155, 'samples': 13027008, 'steps': 67848, 'loss/train': 2.908182382583618} 08/31/2021 01:28:41 - INFO - __main__ - Step 67850: {'lr': 0.00029303977885444555, 'samples': 13027200, 'steps': 67849, 'loss/train': 1.146323323249817} 08/31/2021 01:28:41 - INFO - __main__ - Step 67851: {'lr': 0.00029303455133458255, 'samples': 13027392, 'steps': 67850, 'loss/train': 1.4898430109024048} 08/31/2021 01:28:42 - INFO - __main__ - Step 67852: {'lr': 0.00029302932379532886, 'samples': 13027584, 'steps': 67851, 'loss/train': 1.312170147895813} 08/31/2021 01:28:42 - INFO - __main__ - Step 67853: {'lr': 0.0002930240962366868, 'samples': 13027776, 'steps': 67852, 'loss/train': 1.0711716413497925} 08/31/2021 01:28:43 - INFO - __main__ - Step 67854: {'lr': 0.0002930188686586587, 'samples': 13027968, 'steps': 67853, 'loss/train': 1.512625813484192} 08/31/2021 01:28:43 - INFO - __main__ - Step 67855: {'lr': 0.00029301364106124706, 'samples': 13028160, 'steps': 67854, 'loss/train': 0.2582547962665558} 08/31/2021 01:28:44 - INFO - __main__ - Step 67856: {'lr': 0.00029300841344445406, 'samples': 13028352, 'steps': 67855, 'loss/train': 2.2727444171905518} 08/31/2021 01:28:45 - INFO - __main__ - Step 67857: {'lr': 0.0002930031858082822, 'samples': 13028544, 'steps': 67856, 'loss/train': 1.4771186113357544} 08/31/2021 01:28:45 - INFO - __main__ - Step 67858: {'lr': 0.0002929979581527337, 'samples': 13028736, 'steps': 67857, 'loss/train': 0.47544094920158386} 08/31/2021 01:28:46 - INFO - __main__ - Step 67859: {'lr': 0.000292992730477811, 'samples': 13028928, 'steps': 67858, 'loss/train': 1.479772686958313} 08/31/2021 01:28:46 - INFO - __main__ - Step 67860: {'lr': 0.00029298750278351646, 'samples': 13029120, 'steps': 67859, 'loss/train': 0.9874066710472107} 08/31/2021 01:28:47 - INFO - __main__ - Step 67861: {'lr': 0.0002929822750698524, 'samples': 13029312, 'steps': 67860, 'loss/train': 0.07181134819984436} 08/31/2021 01:28:48 - INFO - __main__ - Step 67862: {'lr': 0.0002929770473368212, 'samples': 13029504, 'steps': 67861, 'loss/train': 0.3695666193962097} 08/31/2021 01:28:48 - INFO - __main__ - Step 67863: {'lr': 0.00029297181958442517, 'samples': 13029696, 'steps': 67862, 'loss/train': 0.8859261274337769} 08/31/2021 01:28:49 - INFO - __main__ - Step 67864: {'lr': 0.00029296659181266677, 'samples': 13029888, 'steps': 67863, 'loss/train': 1.1853867769241333} 08/31/2021 01:28:49 - INFO - __main__ - Step 67865: {'lr': 0.0002929613640215482, 'samples': 13030080, 'steps': 67864, 'loss/train': 1.1201280355453491} 08/31/2021 01:28:50 - INFO - __main__ - Step 67866: {'lr': 0.00029295613621107197, 'samples': 13030272, 'steps': 67865, 'loss/train': 1.5780447721481323} 08/31/2021 01:28:51 - INFO - __main__ - Step 67867: {'lr': 0.00029295090838124034, 'samples': 13030464, 'steps': 67866, 'loss/train': 0.7025597095489502} 08/31/2021 01:28:51 - INFO - __main__ - Step 67868: {'lr': 0.00029294568053205564, 'samples': 13030656, 'steps': 67867, 'loss/train': 1.4070324897766113} 08/31/2021 01:28:52 - INFO - __main__ - Step 67869: {'lr': 0.0002929404526635204, 'samples': 13030848, 'steps': 67868, 'loss/train': 1.4567179679870605} 08/31/2021 01:28:52 - INFO - __main__ - Step 67870: {'lr': 0.00029293522477563677, 'samples': 13031040, 'steps': 67869, 'loss/train': 1.1625449657440186} 08/31/2021 01:28:54 - INFO - __main__ - Step 67871: {'lr': 0.00029292999686840725, 'samples': 13031232, 'steps': 67870, 'loss/train': 0.3391913175582886} 08/31/2021 01:28:54 - INFO - __main__ - Step 67872: {'lr': 0.0002929247689418341, 'samples': 13031424, 'steps': 67871, 'loss/train': 1.6637778282165527} 08/31/2021 01:28:54 - INFO - __main__ - Step 67873: {'lr': 0.0002929195409959197, 'samples': 13031616, 'steps': 67872, 'loss/train': 0.8943034410476685} 08/31/2021 01:28:55 - INFO - __main__ - Step 67874: {'lr': 0.0002929143130306664, 'samples': 13031808, 'steps': 67873, 'loss/train': 1.4173948764801025} 08/31/2021 01:28:55 - INFO - __main__ - Step 67875: {'lr': 0.0002929090850460766, 'samples': 13032000, 'steps': 67874, 'loss/train': 0.7249215245246887} 08/31/2021 01:28:55 - INFO - __main__ - Step 67876: {'lr': 0.0002929038570421526, 'samples': 13032192, 'steps': 67875, 'loss/train': 1.540314793586731} 08/31/2021 01:28:57 - INFO - __main__ - Step 67877: {'lr': 0.0002928986290188969, 'samples': 13032384, 'steps': 67876, 'loss/train': 0.9265669584274292} 08/31/2021 01:28:57 - INFO - __main__ - Step 67878: {'lr': 0.00029289340097631163, 'samples': 13032576, 'steps': 67877, 'loss/train': 1.4588295221328735} 08/31/2021 01:28:58 - INFO - __main__ - Step 67879: {'lr': 0.00029288817291439926, 'samples': 13032768, 'steps': 67878, 'loss/train': 1.3932958841323853} 08/31/2021 01:28:58 - INFO - __main__ - Step 67880: {'lr': 0.0002928829448331622, 'samples': 13032960, 'steps': 67879, 'loss/train': 1.1856240034103394} 08/31/2021 01:28:58 - INFO - __main__ - Step 67881: {'lr': 0.00029287771673260267, 'samples': 13033152, 'steps': 67880, 'loss/train': 1.1226571798324585} 08/31/2021 01:29:00 - INFO - __main__ - Step 67882: {'lr': 0.00029287248861272316, 'samples': 13033344, 'steps': 67881, 'loss/train': 1.224923014640808} 08/31/2021 01:29:00 - INFO - __main__ - Step 67883: {'lr': 0.000292867260473526, 'samples': 13033536, 'steps': 67882, 'loss/train': 0.1088305190205574} 08/31/2021 01:29:01 - INFO - __main__ - Step 67884: {'lr': 0.0002928620323150134, 'samples': 13033728, 'steps': 67883, 'loss/train': 0.8336793184280396} 08/31/2021 01:29:01 - INFO - __main__ - Step 67885: {'lr': 0.0002928568041371879, 'samples': 13033920, 'steps': 67884, 'loss/train': 1.3519313335418701} 08/31/2021 01:29:01 - INFO - __main__ - Step 67886: {'lr': 0.00029285157594005173, 'samples': 13034112, 'steps': 67885, 'loss/train': 0.7414048314094543} 08/31/2021 01:29:03 - INFO - __main__ - Step 67887: {'lr': 0.00029284634772360743, 'samples': 13034304, 'steps': 67886, 'loss/train': 1.148362636566162} 08/31/2021 01:29:04 - INFO - __main__ - Step 67888: {'lr': 0.0002928411194878571, 'samples': 13034496, 'steps': 67887, 'loss/train': 1.4836450815200806} 08/31/2021 01:29:04 - INFO - __main__ - Step 67889: {'lr': 0.0002928358912328033, 'samples': 13034688, 'steps': 67888, 'loss/train': 0.8339913487434387} 08/31/2021 01:29:04 - INFO - __main__ - Step 67890: {'lr': 0.0002928306629584483, 'samples': 13034880, 'steps': 67889, 'loss/train': 0.7456128001213074} 08/31/2021 01:29:05 - INFO - __main__ - Step 67891: {'lr': 0.00029282543466479437, 'samples': 13035072, 'steps': 67890, 'loss/train': 1.5870834589004517} 08/31/2021 01:29:06 - INFO - __main__ - Step 67892: {'lr': 0.00029282020635184404, 'samples': 13035264, 'steps': 67891, 'loss/train': 1.1924604177474976} 08/31/2021 01:29:07 - INFO - __main__ - Step 67893: {'lr': 0.00029281497801959957, 'samples': 13035456, 'steps': 67892, 'loss/train': 1.3423759937286377} 08/31/2021 01:29:07 - INFO - __main__ - Step 67894: {'lr': 0.0002928097496680634, 'samples': 13035648, 'steps': 67893, 'loss/train': 0.743363082408905} 08/31/2021 01:29:07 - INFO - __main__ - Step 67895: {'lr': 0.0002928045212972377, 'samples': 13035840, 'steps': 67894, 'loss/train': 1.9052306413650513} 08/31/2021 01:29:08 - INFO - __main__ - Step 67896: {'lr': 0.00029279929290712504, 'samples': 13036032, 'steps': 67895, 'loss/train': 1.561437964439392} 08/31/2021 01:29:09 - INFO - __main__ - Step 67897: {'lr': 0.0002927940644977276, 'samples': 13036224, 'steps': 67896, 'loss/train': 1.3459665775299072} 08/31/2021 01:29:10 - INFO - __main__ - Step 67898: {'lr': 0.0002927888360690478, 'samples': 13036416, 'steps': 67897, 'loss/train': 1.2206895351409912} 08/31/2021 01:29:10 - INFO - __main__ - Step 67899: {'lr': 0.0002927836076210881, 'samples': 13036608, 'steps': 67898, 'loss/train': 1.4109137058258057} 08/31/2021 01:29:10 - INFO - __main__ - Step 67900: {'lr': 0.0002927783791538508, 'samples': 13036800, 'steps': 67899, 'loss/train': 1.5856026411056519} 08/31/2021 01:29:11 - INFO - __main__ - Step 67901: {'lr': 0.0002927731506673381, 'samples': 13036992, 'steps': 67900, 'loss/train': 0.3593411445617676} 08/31/2021 01:29:11 - INFO - __main__ - Step 67902: {'lr': 0.00029276792216155256, 'samples': 13037184, 'steps': 67901, 'loss/train': 1.0337295532226562} 08/31/2021 01:29:13 - INFO - __main__ - Step 67903: {'lr': 0.0002927626936364964, 'samples': 13037376, 'steps': 67902, 'loss/train': 1.2400776147842407} 08/31/2021 01:29:14 - INFO - __main__ - Step 67904: {'lr': 0.00029275746509217207, 'samples': 13037568, 'steps': 67903, 'loss/train': 1.56035578250885} 08/31/2021 01:29:14 - INFO - __main__ - Step 67905: {'lr': 0.0002927522365285819, 'samples': 13037760, 'steps': 67904, 'loss/train': 0.6178262233734131} 08/31/2021 01:29:15 - INFO - __main__ - Step 67906: {'lr': 0.00029274700794572816, 'samples': 13037952, 'steps': 67905, 'loss/train': 1.348024606704712} 08/31/2021 01:29:15 - INFO - __main__ - Step 67907: {'lr': 0.00029274177934361336, 'samples': 13038144, 'steps': 67906, 'loss/train': 2.1751956939697266} 08/31/2021 01:29:15 - INFO - __main__ - Step 67908: {'lr': 0.0002927365507222397, 'samples': 13038336, 'steps': 67907, 'loss/train': 1.3690881729125977} 08/31/2021 01:29:16 - INFO - __main__ - Step 67909: {'lr': 0.0002927313220816096, 'samples': 13038528, 'steps': 67908, 'loss/train': 0.36655643582344055} 08/31/2021 01:29:17 - INFO - __main__ - Step 67910: {'lr': 0.00029272609342172553, 'samples': 13038720, 'steps': 67909, 'loss/train': 0.3698165714740753} 08/31/2021 01:29:18 - INFO - __main__ - Step 67911: {'lr': 0.0002927208647425897, 'samples': 13038912, 'steps': 67910, 'loss/train': 0.8300804495811462} 08/31/2021 01:29:18 - INFO - __main__ - Step 67912: {'lr': 0.0002927156360442045, 'samples': 13039104, 'steps': 67911, 'loss/train': 1.7853436470031738} 08/31/2021 01:29:18 - INFO - __main__ - Step 67913: {'lr': 0.0002927104073265722, 'samples': 13039296, 'steps': 67912, 'loss/train': 1.3986791372299194} 08/31/2021 01:29:19 - INFO - __main__ - Step 67914: {'lr': 0.00029270517858969537, 'samples': 13039488, 'steps': 67913, 'loss/train': 1.1653175354003906} 08/31/2021 01:29:21 - INFO - __main__ - Step 67915: {'lr': 0.00029269994983357616, 'samples': 13039680, 'steps': 67914, 'loss/train': 1.844679594039917} 08/31/2021 01:29:22 - INFO - __main__ - Step 67916: {'lr': 0.00029269472105821707, 'samples': 13039872, 'steps': 67915, 'loss/train': 1.0312339067459106} 08/31/2021 01:29:22 - INFO - __main__ - Step 67917: {'lr': 0.0002926894922636204, 'samples': 13040064, 'steps': 67916, 'loss/train': 0.04994107037782669} 08/31/2021 01:29:22 - INFO - __main__ - Step 67918: {'lr': 0.00029268426344978855, 'samples': 13040256, 'steps': 67917, 'loss/train': 1.3392900228500366} 08/31/2021 01:29:23 - INFO - __main__ - Step 67919: {'lr': 0.0002926790346167237, 'samples': 13040448, 'steps': 67918, 'loss/train': 1.8146761655807495} 08/31/2021 01:29:23 - INFO - __main__ - Step 67920: {'lr': 0.0002926738057644284, 'samples': 13040640, 'steps': 67919, 'loss/train': 0.9709327220916748} 08/31/2021 01:29:23 - INFO - __main__ - Step 67921: {'lr': 0.00029266857689290497, 'samples': 13040832, 'steps': 67920, 'loss/train': 0.3856511414051056} 08/31/2021 01:29:25 - INFO - __main__ - Step 67922: {'lr': 0.0002926633480021557, 'samples': 13041024, 'steps': 67921, 'loss/train': 0.3855969309806824} 08/31/2021 01:29:26 - INFO - __main__ - Step 67923: {'lr': 0.000292658119092183, 'samples': 13041216, 'steps': 67922, 'loss/train': 1.0495264530181885} 08/31/2021 01:29:26 - INFO - __main__ - Step 67924: {'lr': 0.0002926528901629892, 'samples': 13041408, 'steps': 67923, 'loss/train': 1.2048511505126953} 08/31/2021 01:29:26 - INFO - __main__ - Step 67925: {'lr': 0.0002926476612145767, 'samples': 13041600, 'steps': 67924, 'loss/train': 0.6300525069236755} 08/31/2021 01:29:27 - INFO - __main__ - Step 67926: {'lr': 0.0002926424322469478, 'samples': 13041792, 'steps': 67925, 'loss/train': 0.5391020178794861} 08/31/2021 01:29:27 - INFO - __main__ - Step 67927: {'lr': 0.00029263720326010487, 'samples': 13041984, 'steps': 67926, 'loss/train': 0.9276099801063538} 08/31/2021 01:29:28 - INFO - __main__ - Step 67928: {'lr': 0.0002926319742540503, 'samples': 13042176, 'steps': 67927, 'loss/train': 0.5557413697242737} 08/31/2021 01:29:29 - INFO - __main__ - Step 67929: {'lr': 0.00029262674522878633, 'samples': 13042368, 'steps': 67928, 'loss/train': 1.5431759357452393} 08/31/2021 01:29:29 - INFO - __main__ - Step 67930: {'lr': 0.00029262151618431547, 'samples': 13042560, 'steps': 67929, 'loss/train': 0.49037638306617737} 08/31/2021 01:29:30 - INFO - __main__ - Step 67931: {'lr': 0.0002926162871206401, 'samples': 13042752, 'steps': 67930, 'loss/train': 1.2104835510253906} 08/31/2021 01:29:30 - INFO - __main__ - Step 67932: {'lr': 0.0002926110580377624, 'samples': 13042944, 'steps': 67931, 'loss/train': 1.2502434253692627} 08/31/2021 01:29:31 - INFO - __main__ - Step 67933: {'lr': 0.0002926058289356848, 'samples': 13043136, 'steps': 67932, 'loss/train': 1.0687909126281738} 08/31/2021 01:29:32 - INFO - __main__ - Step 67934: {'lr': 0.0002926005998144097, 'samples': 13043328, 'steps': 67933, 'loss/train': 1.330787181854248} 08/31/2021 01:29:32 - INFO - __main__ - Step 67935: {'lr': 0.0002925953706739394, 'samples': 13043520, 'steps': 67934, 'loss/train': 1.191935420036316} 08/31/2021 01:29:32 - INFO - __main__ - Step 67936: {'lr': 0.0002925901415142763, 'samples': 13043712, 'steps': 67935, 'loss/train': 1.489275336265564} 08/31/2021 01:29:33 - INFO - __main__ - Step 67937: {'lr': 0.00029258491233542273, 'samples': 13043904, 'steps': 67936, 'loss/train': 1.5848336219787598} 08/31/2021 01:29:34 - INFO - __main__ - Step 67938: {'lr': 0.0002925796831373811, 'samples': 13044096, 'steps': 67937, 'loss/train': 1.2117817401885986} 08/31/2021 01:29:35 - INFO - __main__ - Step 67939: {'lr': 0.00029257445392015367, 'samples': 13044288, 'steps': 67938, 'loss/train': 0.9598543643951416} 08/31/2021 01:29:35 - INFO - __main__ - Step 67940: {'lr': 0.00029256922468374287, 'samples': 13044480, 'steps': 67939, 'loss/train': 0.9938111901283264} 08/31/2021 01:29:36 - INFO - __main__ - Step 67941: {'lr': 0.000292563995428151, 'samples': 13044672, 'steps': 67940, 'loss/train': 1.0671086311340332} 08/31/2021 01:29:36 - INFO - __main__ - Step 67942: {'lr': 0.00029255876615338043, 'samples': 13044864, 'steps': 67941, 'loss/train': 1.2390116453170776} 08/31/2021 01:29:38 - INFO - __main__ - Step 67943: {'lr': 0.0002925535368594336, 'samples': 13045056, 'steps': 67942, 'loss/train': 0.9282611608505249} 08/31/2021 01:29:38 - INFO - __main__ - Step 67944: {'lr': 0.0002925483075463128, 'samples': 13045248, 'steps': 67943, 'loss/train': 1.061629295349121} 08/31/2021 01:29:38 - INFO - __main__ - Step 67945: {'lr': 0.0002925430782140204, 'samples': 13045440, 'steps': 67944, 'loss/train': 1.3701940774917603} 08/31/2021 01:29:39 - INFO - __main__ - Step 67946: {'lr': 0.00029253784886255874, 'samples': 13045632, 'steps': 67945, 'loss/train': 1.2745327949523926} 08/31/2021 01:29:39 - INFO - __main__ - Step 67947: {'lr': 0.00029253261949193016, 'samples': 13045824, 'steps': 67946, 'loss/train': 2.1080875396728516} 08/31/2021 01:29:39 - INFO - __main__ - Step 67948: {'lr': 0.000292527390102137, 'samples': 13046016, 'steps': 67947, 'loss/train': 0.888938307762146} 08/31/2021 01:29:41 - INFO - __main__ - Step 67949: {'lr': 0.0002925221606931817, 'samples': 13046208, 'steps': 67948, 'loss/train': 2.2097249031066895} 08/31/2021 01:29:42 - INFO - __main__ - Step 67950: {'lr': 0.0002925169312650666, 'samples': 13046400, 'steps': 67949, 'loss/train': 1.260026454925537} 08/31/2021 01:29:42 - INFO - __main__ - Step 67951: {'lr': 0.000292511701817794, 'samples': 13046592, 'steps': 67950, 'loss/train': 1.7252388000488281} 08/31/2021 01:29:43 - INFO - __main__ - Step 67952: {'lr': 0.0002925064723513663, 'samples': 13046784, 'steps': 67951, 'loss/train': 1.1619789600372314} 08/31/2021 01:29:43 - INFO - __main__ - Step 67953: {'lr': 0.00029250124286578583, 'samples': 13046976, 'steps': 67952, 'loss/train': 1.3374921083450317} 08/31/2021 01:29:44 - INFO - __main__ - Step 67954: {'lr': 0.00029249601336105494, 'samples': 13047168, 'steps': 67953, 'loss/train': 1.3742895126342773} 08/31/2021 01:29:45 - INFO - __main__ - Step 67955: {'lr': 0.00029249078383717595, 'samples': 13047360, 'steps': 67954, 'loss/train': 1.3983196020126343} 08/31/2021 01:29:45 - INFO - __main__ - Step 67956: {'lr': 0.00029248555429415137, 'samples': 13047552, 'steps': 67955, 'loss/train': 0.43771690130233765} 08/31/2021 01:29:46 - INFO - __main__ - Step 67957: {'lr': 0.0002924803247319834, 'samples': 13047744, 'steps': 67956, 'loss/train': 1.367340087890625} 08/31/2021 01:29:46 - INFO - __main__ - Step 67958: {'lr': 0.0002924750951506745, 'samples': 13047936, 'steps': 67957, 'loss/train': 1.0406945943832397} 08/31/2021 01:29:48 - INFO - __main__ - Step 67959: {'lr': 0.00029246986555022693, 'samples': 13048128, 'steps': 67958, 'loss/train': 0.7907241582870483} 08/31/2021 01:29:48 - INFO - __main__ - Step 67960: {'lr': 0.0002924646359306431, 'samples': 13048320, 'steps': 67959, 'loss/train': 1.5010285377502441} 08/31/2021 01:29:48 - INFO - __main__ - Step 67961: {'lr': 0.00029245940629192536, 'samples': 13048512, 'steps': 67960, 'loss/train': 1.5909510850906372} 08/31/2021 01:29:49 - INFO - __main__ - Step 67962: {'lr': 0.000292454176634076, 'samples': 13048704, 'steps': 67961, 'loss/train': 1.1300361156463623} 08/31/2021 01:29:49 - INFO - __main__ - Step 67963: {'lr': 0.00029244894695709754, 'samples': 13048896, 'steps': 67962, 'loss/train': 1.613627314567566} 08/31/2021 01:29:50 - INFO - __main__ - Step 67964: {'lr': 0.0002924437172609922, 'samples': 13049088, 'steps': 67963, 'loss/train': 1.1110750436782837} 08/31/2021 01:29:51 - INFO - __main__ - Step 67965: {'lr': 0.0002924384875457624, 'samples': 13049280, 'steps': 67964, 'loss/train': 1.5071920156478882} 08/31/2021 01:29:51 - INFO - __main__ - Step 67966: {'lr': 0.0002924332578114105, 'samples': 13049472, 'steps': 67965, 'loss/train': 1.4184000492095947} 08/31/2021 01:29:52 - INFO - __main__ - Step 67967: {'lr': 0.0002924280280579388, 'samples': 13049664, 'steps': 67966, 'loss/train': 1.079538345336914} 08/31/2021 01:29:52 - INFO - __main__ - Step 67968: {'lr': 0.00029242279828534963, 'samples': 13049856, 'steps': 67967, 'loss/train': 1.1180609464645386} 08/31/2021 01:29:54 - INFO - __main__ - Step 67969: {'lr': 0.00029241756849364544, 'samples': 13050048, 'steps': 67968, 'loss/train': 1.3479028940200806} 08/31/2021 01:29:54 - INFO - __main__ - Step 67970: {'lr': 0.00029241233868282856, 'samples': 13050240, 'steps': 67969, 'loss/train': 1.181639313697815} 08/31/2021 01:29:54 - INFO - __main__ - Step 67971: {'lr': 0.00029240710885290136, 'samples': 13050432, 'steps': 67970, 'loss/train': 1.498465657234192} 08/31/2021 01:29:55 - INFO - __main__ - Step 67972: {'lr': 0.0002924018790038662, 'samples': 13050624, 'steps': 67971, 'loss/train': 1.7600650787353516} 08/31/2021 01:29:55 - INFO - __main__ - Step 67973: {'lr': 0.00029239664913572526, 'samples': 13050816, 'steps': 67972, 'loss/train': 1.1531527042388916} 08/31/2021 01:29:56 - INFO - __main__ - Step 67974: {'lr': 0.0002923914192484811, 'samples': 13051008, 'steps': 67973, 'loss/train': 0.7583751082420349} 08/31/2021 01:29:57 - INFO - __main__ - Step 67975: {'lr': 0.00029238618934213605, 'samples': 13051200, 'steps': 67974, 'loss/train': 1.422121286392212} 08/31/2021 01:29:57 - INFO - __main__ - Step 67976: {'lr': 0.0002923809594166925, 'samples': 13051392, 'steps': 67975, 'loss/train': 1.3579862117767334} 08/31/2021 01:29:58 - INFO - __main__ - Step 67977: {'lr': 0.00029237572947215265, 'samples': 13051584, 'steps': 67976, 'loss/train': 1.4415180683135986} 08/31/2021 01:29:58 - INFO - __main__ - Step 67978: {'lr': 0.00029237049950851904, 'samples': 13051776, 'steps': 67977, 'loss/train': 1.7565608024597168} 08/31/2021 01:29:58 - INFO - __main__ - Step 67979: {'lr': 0.0002923652695257938, 'samples': 13051968, 'steps': 67978, 'loss/train': 1.705335021018982} 08/31/2021 01:30:00 - INFO - __main__ - Step 67980: {'lr': 0.00029236003952397955, 'samples': 13052160, 'steps': 67979, 'loss/train': 0.9007473587989807} 08/31/2021 01:30:00 - INFO - __main__ - Step 67981: {'lr': 0.0002923548095030785, 'samples': 13052352, 'steps': 67980, 'loss/train': 1.717358946800232} 08/31/2021 01:30:01 - INFO - __main__ - Step 67982: {'lr': 0.0002923495794630929, 'samples': 13052544, 'steps': 67981, 'loss/train': 1.8239063024520874} 08/31/2021 01:30:01 - INFO - __main__ - Step 67983: {'lr': 0.0002923443494040254, 'samples': 13052736, 'steps': 67982, 'loss/train': 1.6812416315078735} 08/31/2021 01:30:01 - INFO - __main__ - Step 67984: {'lr': 0.0002923391193258781, 'samples': 13052928, 'steps': 67983, 'loss/train': 1.978598952293396} 08/31/2021 01:30:03 - INFO - __main__ - Step 67985: {'lr': 0.00029233388922865353, 'samples': 13053120, 'steps': 67984, 'loss/train': 0.8307998776435852} 08/31/2021 01:30:03 - INFO - __main__ - Step 67986: {'lr': 0.00029232865911235384, 'samples': 13053312, 'steps': 67985, 'loss/train': 1.203877568244934} 08/31/2021 01:30:04 - INFO - __main__ - Step 67987: {'lr': 0.00029232342897698164, 'samples': 13053504, 'steps': 67986, 'loss/train': 0.8185569643974304} 08/31/2021 01:30:04 - INFO - __main__ - Step 67988: {'lr': 0.000292318198822539, 'samples': 13053696, 'steps': 67987, 'loss/train': 2.4741673469543457} 08/31/2021 01:30:05 - INFO - __main__ - Step 67989: {'lr': 0.0002923129686490286, 'samples': 13053888, 'steps': 67988, 'loss/train': 0.9318029284477234} 08/31/2021 01:30:06 - INFO - __main__ - Step 67990: {'lr': 0.00029230773845645246, 'samples': 13054080, 'steps': 67989, 'loss/train': 1.3752623796463013} 08/31/2021 01:30:06 - INFO - __main__ - Step 67991: {'lr': 0.0002923025082448132, 'samples': 13054272, 'steps': 67990, 'loss/train': 1.7143465280532837} 08/31/2021 01:30:07 - INFO - __main__ - Step 67992: {'lr': 0.00029229727801411315, 'samples': 13054464, 'steps': 67991, 'loss/train': 1.4266024827957153} 08/31/2021 01:30:07 - INFO - __main__ - Step 67993: {'lr': 0.00029229204776435447, 'samples': 13054656, 'steps': 67992, 'loss/train': 1.6137473583221436} 08/31/2021 01:30:07 - INFO - __main__ - Step 67994: {'lr': 0.0002922868174955397, 'samples': 13054848, 'steps': 67993, 'loss/train': 1.2165700197219849} 08/31/2021 01:30:09 - INFO - __main__ - Step 67995: {'lr': 0.0002922815872076712, 'samples': 13055040, 'steps': 67994, 'loss/train': 1.5779281854629517} 08/31/2021 01:30:10 - INFO - __main__ - Step 67996: {'lr': 0.00029227635690075115, 'samples': 13055232, 'steps': 67995, 'loss/train': 0.49462181329727173} 08/31/2021 01:30:10 - INFO - __main__ - Step 67997: {'lr': 0.0002922711265747821, 'samples': 13055424, 'steps': 67996, 'loss/train': 0.3037017583847046} 08/31/2021 01:30:10 - INFO - __main__ - Step 67998: {'lr': 0.0002922658962297663, 'samples': 13055616, 'steps': 67997, 'loss/train': 1.0852890014648438} 08/31/2021 01:30:11 - INFO - __main__ - Step 67999: {'lr': 0.0002922606658657062, 'samples': 13055808, 'steps': 67998, 'loss/train': 1.5537317991256714} 08/31/2021 01:30:11 - INFO - __main__ - Step 68000: {'lr': 0.0002922554354826041, 'samples': 13056000, 'steps': 67999, 'loss/train': 1.3716009855270386} 08/31/2021 01:30:13 - INFO - __main__ - Step 68001: {'lr': 0.0002922502050804623, 'samples': 13056192, 'steps': 68000, 'loss/train': 0.367465078830719} 08/31/2021 01:30:13 - INFO - __main__ - Step 68002: {'lr': 0.0002922449746592832, 'samples': 13056384, 'steps': 68001, 'loss/train': 0.21712873876094818} 08/31/2021 01:30:14 - INFO - __main__ - Step 68003: {'lr': 0.0002922397442190692, 'samples': 13056576, 'steps': 68002, 'loss/train': 1.5088969469070435} 08/31/2021 01:30:14 - INFO - __main__ - Step 68004: {'lr': 0.00029223451375982255, 'samples': 13056768, 'steps': 68003, 'loss/train': 1.1935968399047852} 08/31/2021 01:30:14 - INFO - __main__ - Step 68005: {'lr': 0.0002922292832815458, 'samples': 13056960, 'steps': 68004, 'loss/train': 1.1991946697235107} 08/31/2021 01:30:16 - INFO - __main__ - Step 68006: {'lr': 0.0002922240527842411, 'samples': 13057152, 'steps': 68005, 'loss/train': 0.1306265890598297} 08/31/2021 01:30:17 - INFO - __main__ - Step 68007: {'lr': 0.0002922188222679109, 'samples': 13057344, 'steps': 68006, 'loss/train': 1.41517972946167} 08/31/2021 01:30:17 - INFO - __main__ - Step 68008: {'lr': 0.0002922135917325576, 'samples': 13057536, 'steps': 68007, 'loss/train': 1.1543755531311035} 08/31/2021 01:30:18 - INFO - __main__ - Step 68009: {'lr': 0.00029220836117818346, 'samples': 13057728, 'steps': 68008, 'loss/train': 1.4313795566558838} 08/31/2021 01:30:18 - INFO - __main__ - Step 68010: {'lr': 0.00029220313060479087, 'samples': 13057920, 'steps': 68009, 'loss/train': 1.5024737119674683} 08/31/2021 01:30:20 - INFO - __main__ - Step 68011: {'lr': 0.00029219790001238223, 'samples': 13058112, 'steps': 68010, 'loss/train': 0.10210105776786804} 08/31/2021 01:30:20 - INFO - __main__ - Step 68012: {'lr': 0.0002921926694009599, 'samples': 13058304, 'steps': 68011, 'loss/train': 1.1570004224777222} 08/31/2021 01:30:20 - INFO - __main__ - Step 68013: {'lr': 0.00029218743877052616, 'samples': 13058496, 'steps': 68012, 'loss/train': 1.1810107231140137} 08/31/2021 01:30:21 - INFO - __main__ - Step 68014: {'lr': 0.00029218220812108345, 'samples': 13058688, 'steps': 68013, 'loss/train': 1.1940646171569824} 08/31/2021 01:30:21 - INFO - __main__ - Step 68015: {'lr': 0.000292176977452634, 'samples': 13058880, 'steps': 68014, 'loss/train': 1.1354836225509644} 08/31/2021 01:30:23 - INFO - __main__ - Step 68016: {'lr': 0.0002921717467651804, 'samples': 13059072, 'steps': 68015, 'loss/train': 1.4915817975997925} 08/31/2021 01:30:23 - INFO - __main__ - Step 68017: {'lr': 0.0002921665160587248, 'samples': 13059264, 'steps': 68016, 'loss/train': 1.270913004875183} 08/31/2021 01:30:24 - INFO - __main__ - Step 68018: {'lr': 0.0002921612853332696, 'samples': 13059456, 'steps': 68017, 'loss/train': 0.09143267571926117} 08/31/2021 01:30:24 - INFO - __main__ - Step 68019: {'lr': 0.0002921560545888171, 'samples': 13059648, 'steps': 68018, 'loss/train': 0.5442556142807007} 08/31/2021 01:30:25 - INFO - __main__ - Step 68020: {'lr': 0.0002921508238253698, 'samples': 13059840, 'steps': 68019, 'loss/train': 1.6161534786224365} 08/31/2021 01:30:25 - INFO - __main__ - Step 68021: {'lr': 0.00029214559304293003, 'samples': 13060032, 'steps': 68020, 'loss/train': 1.3836476802825928} 08/31/2021 01:30:26 - INFO - __main__ - Step 68022: {'lr': 0.0002921403622415, 'samples': 13060224, 'steps': 68021, 'loss/train': 0.7736821174621582} 08/31/2021 01:30:27 - INFO - __main__ - Step 68023: {'lr': 0.00029213513142108236, 'samples': 13060416, 'steps': 68022, 'loss/train': 0.8232761025428772} 08/31/2021 01:30:27 - INFO - __main__ - Step 68024: {'lr': 0.00029212990058167913, 'samples': 13060608, 'steps': 68023, 'loss/train': 1.5115957260131836} 08/31/2021 01:30:27 - INFO - __main__ - Step 68025: {'lr': 0.0002921246697232928, 'samples': 13060800, 'steps': 68024, 'loss/train': 1.036458969116211} 08/31/2021 01:30:28 - INFO - __main__ - Step 68026: {'lr': 0.0002921194388459258, 'samples': 13060992, 'steps': 68025, 'loss/train': 1.7585945129394531} 08/31/2021 01:30:29 - INFO - __main__ - Step 68027: {'lr': 0.0002921142079495804, 'samples': 13061184, 'steps': 68026, 'loss/train': 0.4013836681842804} 08/31/2021 01:30:30 - INFO - __main__ - Step 68028: {'lr': 0.00029210897703425907, 'samples': 13061376, 'steps': 68027, 'loss/train': 2.014219045639038} 08/31/2021 01:30:30 - INFO - __main__ - Step 68029: {'lr': 0.00029210374609996403, 'samples': 13061568, 'steps': 68028, 'loss/train': 1.283689260482788} 08/31/2021 01:30:31 - INFO - __main__ - Step 68030: {'lr': 0.00029209851514669773, 'samples': 13061760, 'steps': 68029, 'loss/train': 1.5401618480682373} 08/31/2021 01:30:31 - INFO - __main__ - Step 68031: {'lr': 0.0002920932841744624, 'samples': 13061952, 'steps': 68030, 'loss/train': 1.574012041091919} 08/31/2021 01:30:32 - INFO - __main__ - Step 68032: {'lr': 0.00029208805318326056, 'samples': 13062144, 'steps': 68031, 'loss/train': 1.5333223342895508} 08/31/2021 01:30:33 - INFO - __main__ - Step 68033: {'lr': 0.00029208282217309446, 'samples': 13062336, 'steps': 68032, 'loss/train': 1.6356842517852783} 08/31/2021 01:30:33 - INFO - __main__ - Step 68034: {'lr': 0.00029207759114396653, 'samples': 13062528, 'steps': 68033, 'loss/train': 0.9452357292175293} 08/31/2021 01:30:34 - INFO - __main__ - Step 68035: {'lr': 0.000292072360095879, 'samples': 13062720, 'steps': 68034, 'loss/train': 1.2077596187591553} 08/31/2021 01:30:34 - INFO - __main__ - Step 68036: {'lr': 0.00029206712902883435, 'samples': 13062912, 'steps': 68035, 'loss/train': 2.0786826610565186} 08/31/2021 01:30:35 - INFO - __main__ - Step 68037: {'lr': 0.0002920618979428349, 'samples': 13063104, 'steps': 68036, 'loss/train': 1.102617621421814} 08/31/2021 01:30:36 - INFO - __main__ - Step 68038: {'lr': 0.00029205666683788305, 'samples': 13063296, 'steps': 68037, 'loss/train': 1.45933198928833} 08/31/2021 01:30:36 - INFO - __main__ - Step 68039: {'lr': 0.0002920514357139811, 'samples': 13063488, 'steps': 68038, 'loss/train': 0.9637492895126343} 08/31/2021 01:30:37 - INFO - __main__ - Step 68040: {'lr': 0.0002920462045711315, 'samples': 13063680, 'steps': 68039, 'loss/train': 1.334786057472229} 08/31/2021 01:30:37 - INFO - __main__ - Step 68041: {'lr': 0.0002920409734093364, 'samples': 13063872, 'steps': 68040, 'loss/train': 1.3040587902069092} 08/31/2021 01:30:39 - INFO - __main__ - Step 68042: {'lr': 0.0002920357422285983, 'samples': 13064064, 'steps': 68041, 'loss/train': 1.971181035041809} 08/31/2021 01:30:39 - INFO - __main__ - Step 68043: {'lr': 0.0002920305110289195, 'samples': 13064256, 'steps': 68042, 'loss/train': 0.8796241283416748} 08/31/2021 01:30:39 - INFO - __main__ - Step 68044: {'lr': 0.00029202527981030254, 'samples': 13064448, 'steps': 68043, 'loss/train': 1.3064640760421753} 08/31/2021 01:30:40 - INFO - __main__ - Step 68045: {'lr': 0.00029202004857274954, 'samples': 13064640, 'steps': 68044, 'loss/train': 1.5612410306930542} 08/31/2021 01:30:40 - INFO - __main__ - Step 68046: {'lr': 0.000292014817316263, 'samples': 13064832, 'steps': 68045, 'loss/train': 1.2145329713821411} 08/31/2021 01:30:42 - INFO - __main__ - Step 68047: {'lr': 0.0002920095860408452, 'samples': 13065024, 'steps': 68046, 'loss/train': 1.6382856369018555} 08/31/2021 01:30:42 - INFO - __main__ - Step 68048: {'lr': 0.00029200435474649857, 'samples': 13065216, 'steps': 68047, 'loss/train': 5.349654674530029} 08/31/2021 01:30:42 - INFO - __main__ - Step 68049: {'lr': 0.00029199912343322537, 'samples': 13065408, 'steps': 68048, 'loss/train': 0.9542976021766663} 08/31/2021 01:30:43 - INFO - __main__ - Step 68050: {'lr': 0.0002919938921010281, 'samples': 13065600, 'steps': 68049, 'loss/train': 0.989949643611908} 08/31/2021 01:30:43 - INFO - __main__ - Step 68051: {'lr': 0.0002919886607499089, 'samples': 13065792, 'steps': 68050, 'loss/train': 0.8820651173591614} 08/31/2021 01:30:45 - INFO - __main__ - Step 68052: {'lr': 0.00029198342937987036, 'samples': 13065984, 'steps': 68051, 'loss/train': 0.7892338633537292} 08/31/2021 01:30:46 - INFO - __main__ - Step 68053: {'lr': 0.00029197819799091476, 'samples': 13066176, 'steps': 68052, 'loss/train': 1.129402995109558} 08/31/2021 01:30:46 - INFO - __main__ - Step 68054: {'lr': 0.00029197296658304433, 'samples': 13066368, 'steps': 68053, 'loss/train': 0.839544951915741} 08/31/2021 01:30:46 - INFO - __main__ - Step 68055: {'lr': 0.00029196773515626157, 'samples': 13066560, 'steps': 68054, 'loss/train': 0.9052118062973022} 08/31/2021 01:30:47 - INFO - __main__ - Step 68056: {'lr': 0.00029196250371056875, 'samples': 13066752, 'steps': 68055, 'loss/train': 1.859175205230713} 08/31/2021 01:30:48 - INFO - __main__ - Step 68057: {'lr': 0.00029195727224596836, 'samples': 13066944, 'steps': 68056, 'loss/train': 1.090475082397461} 08/31/2021 01:30:49 - INFO - __main__ - Step 68058: {'lr': 0.00029195204076246263, 'samples': 13067136, 'steps': 68057, 'loss/train': 0.7629402279853821} 08/31/2021 01:30:49 - INFO - __main__ - Step 68059: {'lr': 0.000291946809260054, 'samples': 13067328, 'steps': 68058, 'loss/train': 1.0024158954620361} 08/31/2021 01:30:49 - INFO - __main__ - Step 68060: {'lr': 0.00029194157773874475, 'samples': 13067520, 'steps': 68059, 'loss/train': 1.2940878868103027} 08/31/2021 01:30:50 - INFO - __main__ - Step 68061: {'lr': 0.00029193634619853725, 'samples': 13067712, 'steps': 68060, 'loss/train': 1.033224105834961} 08/31/2021 01:30:50 - INFO - __main__ - Step 68062: {'lr': 0.0002919311146394339, 'samples': 13067904, 'steps': 68061, 'loss/train': 0.10024940222501755} 08/31/2021 01:30:52 - INFO - __main__ - Step 68063: {'lr': 0.000291925883061437, 'samples': 13068096, 'steps': 68062, 'loss/train': 1.506155014038086} 08/31/2021 01:30:52 - INFO - __main__ - Step 68064: {'lr': 0.000291920651464549, 'samples': 13068288, 'steps': 68063, 'loss/train': 1.1909465789794922} 08/31/2021 01:30:52 - INFO - __main__ - Step 68065: {'lr': 0.0002919154198487722, 'samples': 13068480, 'steps': 68064, 'loss/train': 1.4616740942001343} 08/31/2021 01:30:53 - INFO - __main__ - Step 68066: {'lr': 0.0002919101882141089, 'samples': 13068672, 'steps': 68065, 'loss/train': 0.9613765478134155} 08/31/2021 01:30:53 - INFO - __main__ - Step 68067: {'lr': 0.0002919049565605616, 'samples': 13068864, 'steps': 68066, 'loss/train': 1.606062650680542} 08/31/2021 01:30:54 - INFO - __main__ - Step 68068: {'lr': 0.0002918997248881325, 'samples': 13069056, 'steps': 68067, 'loss/train': 1.01076340675354} 08/31/2021 01:30:55 - INFO - __main__ - Step 68069: {'lr': 0.00029189449319682405, 'samples': 13069248, 'steps': 68068, 'loss/train': 1.563477873802185} 08/31/2021 01:30:55 - INFO - __main__ - Step 68070: {'lr': 0.0002918892614866386, 'samples': 13069440, 'steps': 68069, 'loss/train': 1.5914194583892822} 08/31/2021 01:30:56 - INFO - __main__ - Step 68071: {'lr': 0.0002918840297575785, 'samples': 13069632, 'steps': 68070, 'loss/train': 0.898252546787262} 08/31/2021 01:30:56 - INFO - __main__ - Step 68072: {'lr': 0.00029187879800964613, 'samples': 13069824, 'steps': 68071, 'loss/train': 1.165825605392456} 08/31/2021 01:30:57 - INFO - __main__ - Step 68073: {'lr': 0.0002918735662428438, 'samples': 13070016, 'steps': 68072, 'loss/train': 1.1969189643859863} 08/31/2021 01:30:58 - INFO - __main__ - Step 68074: {'lr': 0.0002918683344571738, 'samples': 13070208, 'steps': 68073, 'loss/train': 0.8681507706642151} 08/31/2021 01:30:58 - INFO - __main__ - Step 68075: {'lr': 0.0002918631026526387, 'samples': 13070400, 'steps': 68074, 'loss/train': 1.3867977857589722} 08/31/2021 01:30:59 - INFO - __main__ - Step 68076: {'lr': 0.00029185787082924066, 'samples': 13070592, 'steps': 68075, 'loss/train': 1.1649138927459717} 08/31/2021 01:30:59 - INFO - __main__ - Step 68077: {'lr': 0.0002918526389869821, 'samples': 13070784, 'steps': 68076, 'loss/train': 1.3856849670410156} 08/31/2021 01:31:01 - INFO - __main__ - Step 68078: {'lr': 0.0002918474071258654, 'samples': 13070976, 'steps': 68077, 'loss/train': 1.7111510038375854} 08/31/2021 01:31:01 - INFO - __main__ - Step 68079: {'lr': 0.00029184217524589294, 'samples': 13071168, 'steps': 68078, 'loss/train': 1.199415683746338} 08/31/2021 01:31:01 - INFO - __main__ - Step 68080: {'lr': 0.0002918369433470671, 'samples': 13071360, 'steps': 68079, 'loss/train': 1.5036638975143433} 08/31/2021 01:31:02 - INFO - __main__ - Step 68081: {'lr': 0.00029183171142939, 'samples': 13071552, 'steps': 68080, 'loss/train': 0.6963161826133728} 08/31/2021 01:31:02 - INFO - __main__ - Step 68082: {'lr': 0.00029182647949286427, 'samples': 13071744, 'steps': 68081, 'loss/train': 1.6968803405761719} 08/31/2021 01:31:04 - INFO - __main__ - Step 68083: {'lr': 0.0002918212475374922, 'samples': 13071936, 'steps': 68082, 'loss/train': 1.4984312057495117} 08/31/2021 01:31:04 - INFO - __main__ - Step 68084: {'lr': 0.00029181601556327606, 'samples': 13072128, 'steps': 68083, 'loss/train': 0.8727709054946899} 08/31/2021 01:31:05 - INFO - __main__ - Step 68085: {'lr': 0.00029181078357021835, 'samples': 13072320, 'steps': 68084, 'loss/train': 1.1269859075546265} 08/31/2021 01:31:05 - INFO - __main__ - Step 68086: {'lr': 0.00029180555155832133, 'samples': 13072512, 'steps': 68085, 'loss/train': 1.1120550632476807} 08/31/2021 01:31:05 - INFO - __main__ - Step 68087: {'lr': 0.0002918003195275873, 'samples': 13072704, 'steps': 68086, 'loss/train': 1.764296531677246} 08/31/2021 01:31:06 - INFO - __main__ - Step 68088: {'lr': 0.0002917950874780188, 'samples': 13072896, 'steps': 68087, 'loss/train': 1.4342936277389526} 08/31/2021 01:31:07 - INFO - __main__ - Step 68089: {'lr': 0.000291789855409618, 'samples': 13073088, 'steps': 68088, 'loss/train': 1.2671704292297363} 08/31/2021 01:31:08 - INFO - __main__ - Step 68090: {'lr': 0.0002917846233223873, 'samples': 13073280, 'steps': 68089, 'loss/train': 1.1658514738082886} 08/31/2021 01:31:08 - INFO - __main__ - Step 68091: {'lr': 0.0002917793912163292, 'samples': 13073472, 'steps': 68090, 'loss/train': 1.2106965780258179} 08/31/2021 01:31:09 - INFO - __main__ - Step 68092: {'lr': 0.0002917741590914458, 'samples': 13073664, 'steps': 68091, 'loss/train': 1.4621119499206543} 08/31/2021 01:31:09 - INFO - __main__ - Step 68093: {'lr': 0.00029176892694773984, 'samples': 13073856, 'steps': 68092, 'loss/train': 1.1233769655227661} 08/31/2021 01:31:10 - INFO - __main__ - Step 68094: {'lr': 0.00029176369478521325, 'samples': 13074048, 'steps': 68093, 'loss/train': 1.6692144870758057} 08/31/2021 01:31:11 - INFO - __main__ - Step 68095: {'lr': 0.00029175846260386866, 'samples': 13074240, 'steps': 68094, 'loss/train': 1.6293370723724365} 08/31/2021 01:31:11 - INFO - __main__ - Step 68096: {'lr': 0.00029175323040370833, 'samples': 13074432, 'steps': 68095, 'loss/train': 1.2103732824325562} 08/31/2021 01:31:11 - INFO - __main__ - Step 68097: {'lr': 0.00029174799818473465, 'samples': 13074624, 'steps': 68096, 'loss/train': 1.4834802150726318} 08/31/2021 01:31:12 - INFO - __main__ - Step 68098: {'lr': 0.0002917427659469499, 'samples': 13074816, 'steps': 68097, 'loss/train': 0.7900363802909851} 08/31/2021 01:31:13 - INFO - __main__ - Step 68099: {'lr': 0.00029173753369035664, 'samples': 13075008, 'steps': 68098, 'loss/train': 1.249145746231079} 08/31/2021 01:31:14 - INFO - __main__ - Step 68100: {'lr': 0.00029173230141495707, 'samples': 13075200, 'steps': 68099, 'loss/train': 1.7258718013763428} 08/31/2021 01:31:14 - INFO - __main__ - Step 68101: {'lr': 0.0002917270691207535, 'samples': 13075392, 'steps': 68100, 'loss/train': 0.6761499643325806} 08/31/2021 01:31:14 - INFO - __main__ - Step 68102: {'lr': 0.0002917218368077483, 'samples': 13075584, 'steps': 68101, 'loss/train': 1.4543671607971191} 08/31/2021 01:31:15 - INFO - __main__ - Step 68103: {'lr': 0.00029171660447594393, 'samples': 13075776, 'steps': 68102, 'loss/train': 1.1667933464050293} 08/31/2021 01:31:16 - INFO - __main__ - Step 68104: {'lr': 0.00029171137212534275, 'samples': 13075968, 'steps': 68103, 'loss/train': 1.1337130069732666} 08/31/2021 01:31:17 - INFO - __main__ - Step 68105: {'lr': 0.0002917061397559471, 'samples': 13076160, 'steps': 68104, 'loss/train': 1.3632763624191284} 08/31/2021 01:31:17 - INFO - __main__ - Step 68106: {'lr': 0.00029170090736775926, 'samples': 13076352, 'steps': 68105, 'loss/train': 0.9865971803665161} 08/31/2021 01:31:17 - INFO - __main__ - Step 68107: {'lr': 0.0002916956749607816, 'samples': 13076544, 'steps': 68106, 'loss/train': 0.9967426657676697} 08/31/2021 01:31:18 - INFO - __main__ - Step 68108: {'lr': 0.00029169044253501655, 'samples': 13076736, 'steps': 68107, 'loss/train': 1.5468337535858154} 08/31/2021 01:31:20 - INFO - __main__ - Step 68109: {'lr': 0.0002916852100904664, 'samples': 13076928, 'steps': 68108, 'loss/train': 0.9237077832221985} 08/31/2021 01:31:20 - INFO - __main__ - Step 68110: {'lr': 0.00029167997762713353, 'samples': 13077120, 'steps': 68109, 'loss/train': 1.5520068407058716} 08/31/2021 01:31:20 - INFO - __main__ - Step 68111: {'lr': 0.00029167474514502035, 'samples': 13077312, 'steps': 68110, 'loss/train': 1.495011568069458} 08/31/2021 01:31:21 - INFO - __main__ - Step 68112: {'lr': 0.0002916695126441292, 'samples': 13077504, 'steps': 68111, 'loss/train': 1.5740665197372437} 08/31/2021 01:31:21 - INFO - __main__ - Step 68113: {'lr': 0.0002916642801244624, 'samples': 13077696, 'steps': 68112, 'loss/train': 0.07595464587211609} 08/31/2021 01:31:23 - INFO - __main__ - Step 68114: {'lr': 0.00029165904758602225, 'samples': 13077888, 'steps': 68113, 'loss/train': 1.1476788520812988} 08/31/2021 01:31:23 - INFO - __main__ - Step 68115: {'lr': 0.0002916538150288112, 'samples': 13078080, 'steps': 68114, 'loss/train': 2.5071041584014893} 08/31/2021 01:31:24 - INFO - __main__ - Step 68116: {'lr': 0.0002916485824528316, 'samples': 13078272, 'steps': 68115, 'loss/train': 1.2555081844329834} 08/31/2021 01:31:24 - INFO - __main__ - Step 68117: {'lr': 0.00029164334985808577, 'samples': 13078464, 'steps': 68116, 'loss/train': 0.9435556530952454} 08/31/2021 01:31:24 - INFO - __main__ - Step 68118: {'lr': 0.0002916381172445761, 'samples': 13078656, 'steps': 68117, 'loss/train': 1.4397836923599243} 08/31/2021 01:31:26 - INFO - __main__ - Step 68119: {'lr': 0.00029163288461230496, 'samples': 13078848, 'steps': 68118, 'loss/train': 1.2211731672286987} 08/31/2021 01:31:26 - INFO - __main__ - Step 68120: {'lr': 0.0002916276519612747, 'samples': 13079040, 'steps': 68119, 'loss/train': 1.5060194730758667} 08/31/2021 01:31:27 - INFO - __main__ - Step 68121: {'lr': 0.00029162241929148766, 'samples': 13079232, 'steps': 68120, 'loss/train': 1.4685587882995605} 08/31/2021 01:31:27 - INFO - __main__ - Step 68122: {'lr': 0.00029161718660294613, 'samples': 13079424, 'steps': 68121, 'loss/train': 1.160433292388916} 08/31/2021 01:31:27 - INFO - __main__ - Step 68123: {'lr': 0.00029161195389565257, 'samples': 13079616, 'steps': 68122, 'loss/train': 1.2344541549682617} 08/31/2021 01:31:28 - INFO - __main__ - Step 68124: {'lr': 0.0002916067211696093, 'samples': 13079808, 'steps': 68123, 'loss/train': 1.3274705410003662} 08/31/2021 01:31:30 - INFO - __main__ - Step 68125: {'lr': 0.0002916014884248187, 'samples': 13080000, 'steps': 68124, 'loss/train': 1.449119210243225} 08/31/2021 01:31:30 - INFO - __main__ - Step 68126: {'lr': 0.0002915962556612832, 'samples': 13080192, 'steps': 68125, 'loss/train': 1.1229729652404785} 08/31/2021 01:31:31 - INFO - __main__ - Step 68127: {'lr': 0.0002915910228790049, 'samples': 13080384, 'steps': 68126, 'loss/train': 1.27510666847229} 08/31/2021 01:31:31 - INFO - __main__ - Step 68128: {'lr': 0.0002915857900779864, 'samples': 13080576, 'steps': 68127, 'loss/train': 1.7692437171936035} 08/31/2021 01:31:31 - INFO - __main__ - Step 68129: {'lr': 0.00029158055725823, 'samples': 13080768, 'steps': 68128, 'loss/train': 1.0472885370254517} 08/31/2021 01:31:32 - INFO - __main__ - Step 68130: {'lr': 0.000291575324419738, 'samples': 13080960, 'steps': 68129, 'loss/train': 1.9226628541946411} 08/31/2021 01:31:33 - INFO - __main__ - Step 68131: {'lr': 0.00029157009156251284, 'samples': 13081152, 'steps': 68130, 'loss/train': 1.570175051689148} 08/31/2021 01:31:34 - INFO - __main__ - Step 68132: {'lr': 0.0002915648586865569, 'samples': 13081344, 'steps': 68131, 'loss/train': 1.008933186531067} 08/31/2021 01:31:34 - INFO - __main__ - Step 68133: {'lr': 0.0002915596257918724, 'samples': 13081536, 'steps': 68132, 'loss/train': 1.530382752418518} 08/31/2021 01:31:34 - INFO - __main__ - Step 68134: {'lr': 0.00029155439287846177, 'samples': 13081728, 'steps': 68133, 'loss/train': 0.7604279518127441} 08/31/2021 01:31:35 - INFO - __main__ - Step 68135: {'lr': 0.00029154915994632734, 'samples': 13081920, 'steps': 68134, 'loss/train': 0.837898313999176} 08/31/2021 01:31:36 - INFO - __main__ - Step 68136: {'lr': 0.00029154392699547155, 'samples': 13082112, 'steps': 68135, 'loss/train': 1.5412472486495972} 08/31/2021 01:31:37 - INFO - __main__ - Step 68137: {'lr': 0.00029153869402589674, 'samples': 13082304, 'steps': 68136, 'loss/train': 1.3313263654708862} 08/31/2021 01:31:37 - INFO - __main__ - Step 68138: {'lr': 0.00029153346103760514, 'samples': 13082496, 'steps': 68137, 'loss/train': 1.4363598823547363} 08/31/2021 01:31:37 - INFO - __main__ - Step 68139: {'lr': 0.0002915282280305993, 'samples': 13082688, 'steps': 68138, 'loss/train': 1.22421395778656} 08/31/2021 01:31:38 - INFO - __main__ - Step 68140: {'lr': 0.00029152299500488144, 'samples': 13082880, 'steps': 68139, 'loss/train': 1.4367412328720093} 08/31/2021 01:31:39 - INFO - __main__ - Step 68141: {'lr': 0.00029151776196045397, 'samples': 13083072, 'steps': 68140, 'loss/train': 0.7460671067237854} 08/31/2021 01:31:40 - INFO - __main__ - Step 68142: {'lr': 0.00029151252889731923, 'samples': 13083264, 'steps': 68141, 'loss/train': 1.8455352783203125} 08/31/2021 01:31:40 - INFO - __main__ - Step 68143: {'lr': 0.0002915072958154795, 'samples': 13083456, 'steps': 68142, 'loss/train': 0.07851774245500565} 08/31/2021 01:31:40 - INFO - __main__ - Step 68144: {'lr': 0.0002915020627149373, 'samples': 13083648, 'steps': 68143, 'loss/train': 0.7795334458351135} 08/31/2021 01:31:41 - INFO - __main__ - Step 68145: {'lr': 0.00029149682959569496, 'samples': 13083840, 'steps': 68144, 'loss/train': 0.7704107761383057} 08/31/2021 01:31:42 - INFO - __main__ - Step 68146: {'lr': 0.00029149159645775483, 'samples': 13084032, 'steps': 68145, 'loss/train': 1.0161093473434448} 08/31/2021 01:31:43 - INFO - __main__ - Step 68147: {'lr': 0.0002914863633011191, 'samples': 13084224, 'steps': 68146, 'loss/train': 0.18601104617118835} 08/31/2021 01:31:43 - INFO - __main__ - Step 68148: {'lr': 0.00029148113012579025, 'samples': 13084416, 'steps': 68147, 'loss/train': 1.5163207054138184} 08/31/2021 01:31:43 - INFO - __main__ - Step 68149: {'lr': 0.0002914758969317707, 'samples': 13084608, 'steps': 68148, 'loss/train': 1.2360576391220093} 08/31/2021 01:31:44 - INFO - __main__ - Step 68150: {'lr': 0.00029147066371906273, 'samples': 13084800, 'steps': 68149, 'loss/train': 1.14661705493927} 08/31/2021 01:31:44 - INFO - __main__ - Step 68151: {'lr': 0.0002914654304876687, 'samples': 13084992, 'steps': 68150, 'loss/train': 0.7040440440177917} 08/31/2021 01:31:46 - INFO - __main__ - Step 68152: {'lr': 0.0002914601972375911, 'samples': 13085184, 'steps': 68151, 'loss/train': 1.5059255361557007} 08/31/2021 01:31:46 - INFO - __main__ - Step 68153: {'lr': 0.0002914549639688321, 'samples': 13085376, 'steps': 68152, 'loss/train': 1.00648832321167} 08/31/2021 01:31:46 - INFO - __main__ - Step 68154: {'lr': 0.0002914497306813941, 'samples': 13085568, 'steps': 68153, 'loss/train': 1.998332142829895} 08/31/2021 01:31:47 - INFO - __main__ - Step 68155: {'lr': 0.0002914444973752795, 'samples': 13085760, 'steps': 68154, 'loss/train': 1.4017000198364258} 08/31/2021 01:31:47 - INFO - __main__ - Step 68156: {'lr': 0.0002914392640504907, 'samples': 13085952, 'steps': 68155, 'loss/train': 0.5260002613067627} 08/31/2021 01:31:49 - INFO - __main__ - Step 68157: {'lr': 0.00029143403070702994, 'samples': 13086144, 'steps': 68156, 'loss/train': 1.0483803749084473} 08/31/2021 01:31:49 - INFO - __main__ - Step 68158: {'lr': 0.0002914287973448997, 'samples': 13086336, 'steps': 68157, 'loss/train': 1.257274866104126} 08/31/2021 01:31:49 - INFO - __main__ - Step 68159: {'lr': 0.00029142356396410227, 'samples': 13086528, 'steps': 68158, 'loss/train': 1.3984980583190918} 08/31/2021 01:31:50 - INFO - __main__ - Step 68160: {'lr': 0.00029141833056463995, 'samples': 13086720, 'steps': 68159, 'loss/train': 1.285122275352478} 08/31/2021 01:31:50 - INFO - __main__ - Step 68161: {'lr': 0.00029141309714651525, 'samples': 13086912, 'steps': 68160, 'loss/train': 1.2959176301956177} 08/31/2021 01:31:52 - INFO - __main__ - Step 68162: {'lr': 0.0002914078637097305, 'samples': 13087104, 'steps': 68161, 'loss/train': 1.4740757942199707} 08/31/2021 01:31:53 - INFO - __main__ - Step 68163: {'lr': 0.00029140263025428785, 'samples': 13087296, 'steps': 68162, 'loss/train': 1.2510318756103516} 08/31/2021 01:31:53 - INFO - __main__ - Step 68164: {'lr': 0.00029139739678018996, 'samples': 13087488, 'steps': 68163, 'loss/train': 1.338843584060669} 08/31/2021 01:31:53 - INFO - __main__ - Step 68165: {'lr': 0.0002913921632874389, 'samples': 13087680, 'steps': 68164, 'loss/train': 1.4558651447296143} 08/31/2021 01:31:54 - INFO - __main__ - Step 68166: {'lr': 0.00029138692977603734, 'samples': 13087872, 'steps': 68165, 'loss/train': 1.890730381011963} 08/31/2021 01:31:55 - INFO - __main__ - Step 68167: {'lr': 0.0002913816962459873, 'samples': 13088064, 'steps': 68166, 'loss/train': 1.6539490222930908} 08/31/2021 01:31:56 - INFO - __main__ - Step 68168: {'lr': 0.00029137646269729143, 'samples': 13088256, 'steps': 68167, 'loss/train': 1.2691904306411743} 08/31/2021 01:31:56 - INFO - __main__ - Step 68169: {'lr': 0.0002913712291299519, 'samples': 13088448, 'steps': 68168, 'loss/train': 1.2410469055175781} 08/31/2021 01:31:56 - INFO - __main__ - Step 68170: {'lr': 0.0002913659955439711, 'samples': 13088640, 'steps': 68169, 'loss/train': 1.1446846723556519} 08/31/2021 01:31:57 - INFO - __main__ - Step 68171: {'lr': 0.0002913607619393515, 'samples': 13088832, 'steps': 68170, 'loss/train': 1.2803078889846802} 08/31/2021 01:31:58 - INFO - __main__ - Step 68172: {'lr': 0.00029135552831609533, 'samples': 13089024, 'steps': 68171, 'loss/train': 1.4866667985916138} 08/31/2021 01:31:59 - INFO - __main__ - Step 68173: {'lr': 0.0002913502946742051, 'samples': 13089216, 'steps': 68172, 'loss/train': 2.0220680236816406} 08/31/2021 01:31:59 - INFO - __main__ - Step 68174: {'lr': 0.00029134506101368297, 'samples': 13089408, 'steps': 68173, 'loss/train': 1.2810126543045044} 08/31/2021 01:31:59 - INFO - __main__ - Step 68175: {'lr': 0.0002913398273345314, 'samples': 13089600, 'steps': 68174, 'loss/train': 1.0082900524139404} 08/31/2021 01:32:00 - INFO - __main__ - Step 68176: {'lr': 0.00029133459363675274, 'samples': 13089792, 'steps': 68175, 'loss/train': 0.8816171884536743} 08/31/2021 01:32:00 - INFO - __main__ - Step 68177: {'lr': 0.0002913293599203494, 'samples': 13089984, 'steps': 68176, 'loss/train': 0.9563390016555786} 08/31/2021 01:32:02 - INFO - __main__ - Step 68178: {'lr': 0.00029132412618532356, 'samples': 13090176, 'steps': 68177, 'loss/train': 3.6922876834869385} 08/31/2021 01:32:02 - INFO - __main__ - Step 68179: {'lr': 0.0002913188924316778, 'samples': 13090368, 'steps': 68178, 'loss/train': 1.2226438522338867} 08/31/2021 01:32:02 - INFO - __main__ - Step 68180: {'lr': 0.0002913136586594144, 'samples': 13090560, 'steps': 68179, 'loss/train': 2.1852035522460938} 08/31/2021 01:32:03 - INFO - __main__ - Step 68181: {'lr': 0.0002913084248685357, 'samples': 13090752, 'steps': 68180, 'loss/train': 1.1740124225616455} 08/31/2021 01:32:03 - INFO - __main__ - Step 68182: {'lr': 0.000291303191059044, 'samples': 13090944, 'steps': 68181, 'loss/train': 1.25513756275177} 08/31/2021 01:32:04 - INFO - __main__ - Step 68183: {'lr': 0.00029129795723094174, 'samples': 13091136, 'steps': 68182, 'loss/train': 1.5092518329620361} 08/31/2021 01:32:05 - INFO - __main__ - Step 68184: {'lr': 0.0002912927233842313, 'samples': 13091328, 'steps': 68183, 'loss/train': 1.3213435411453247} 08/31/2021 01:32:05 - INFO - __main__ - Step 68185: {'lr': 0.000291287489518915, 'samples': 13091520, 'steps': 68184, 'loss/train': 1.6030715703964233} 08/31/2021 01:32:06 - INFO - __main__ - Step 68186: {'lr': 0.0002912822556349951, 'samples': 13091712, 'steps': 68185, 'loss/train': 1.3912101984024048} 08/31/2021 01:32:06 - INFO - __main__ - Step 68187: {'lr': 0.00029127702173247416, 'samples': 13091904, 'steps': 68186, 'loss/train': 1.4697203636169434} 08/31/2021 01:32:08 - INFO - __main__ - Step 68188: {'lr': 0.0002912717878113544, 'samples': 13092096, 'steps': 68187, 'loss/train': 1.7523428201675415} 08/31/2021 01:32:08 - INFO - __main__ - Step 68189: {'lr': 0.0002912665538716382, 'samples': 13092288, 'steps': 68188, 'loss/train': 0.6082072257995605} 08/31/2021 01:32:09 - INFO - __main__ - Step 68190: {'lr': 0.00029126131991332794, 'samples': 13092480, 'steps': 68189, 'loss/train': 1.3147159814834595} 08/31/2021 01:32:09 - INFO - __main__ - Step 68191: {'lr': 0.00029125608593642594, 'samples': 13092672, 'steps': 68190, 'loss/train': 1.1826220750808716} 08/31/2021 01:32:09 - INFO - __main__ - Step 68192: {'lr': 0.0002912508519409346, 'samples': 13092864, 'steps': 68191, 'loss/train': 1.1446528434753418} 08/31/2021 01:32:10 - INFO - __main__ - Step 68193: {'lr': 0.00029124561792685626, 'samples': 13093056, 'steps': 68192, 'loss/train': 1.269321322441101} 08/31/2021 01:32:11 - INFO - __main__ - Step 68194: {'lr': 0.00029124038389419325, 'samples': 13093248, 'steps': 68193, 'loss/train': 0.8568294048309326} 08/31/2021 01:32:12 - INFO - __main__ - Step 68195: {'lr': 0.00029123514984294804, 'samples': 13093440, 'steps': 68194, 'loss/train': 1.5922636985778809} 08/31/2021 01:32:12 - INFO - __main__ - Step 68196: {'lr': 0.00029122991577312286, 'samples': 13093632, 'steps': 68195, 'loss/train': 1.6113656759262085} 08/31/2021 01:32:13 - INFO - __main__ - Step 68197: {'lr': 0.0002912246816847201, 'samples': 13093824, 'steps': 68196, 'loss/train': 0.18990935385227203} 08/31/2021 01:32:13 - INFO - __main__ - Step 68198: {'lr': 0.0002912194475777422, 'samples': 13094016, 'steps': 68197, 'loss/train': 1.2927453517913818} 08/31/2021 01:32:14 - INFO - __main__ - Step 68199: {'lr': 0.00029121421345219134, 'samples': 13094208, 'steps': 68198, 'loss/train': 0.8649305105209351} 08/31/2021 01:32:15 - INFO - __main__ - Step 68200: {'lr': 0.0002912089793080701, 'samples': 13094400, 'steps': 68199, 'loss/train': 1.0639899969100952} 08/31/2021 01:32:15 - INFO - __main__ - Step 68201: {'lr': 0.0002912037451453807, 'samples': 13094592, 'steps': 68200, 'loss/train': 0.9559394121170044} 08/31/2021 01:32:16 - INFO - __main__ - Step 68202: {'lr': 0.00029119851096412545, 'samples': 13094784, 'steps': 68201, 'loss/train': 1.1974632740020752} 08/31/2021 01:32:16 - INFO - __main__ - Step 68203: {'lr': 0.00029119327676430687, 'samples': 13094976, 'steps': 68202, 'loss/train': 1.1155285835266113} 08/31/2021 01:32:17 - INFO - __main__ - Step 68204: {'lr': 0.0002911880425459272, 'samples': 13095168, 'steps': 68203, 'loss/train': 1.411320686340332} 08/31/2021 01:32:18 - INFO - __main__ - Step 68205: {'lr': 0.0002911828083089889, 'samples': 13095360, 'steps': 68204, 'loss/train': 1.4522972106933594} 08/31/2021 01:32:18 - INFO - __main__ - Step 68206: {'lr': 0.00029117757405349413, 'samples': 13095552, 'steps': 68205, 'loss/train': 0.973151445388794} 08/31/2021 01:32:19 - INFO - __main__ - Step 68207: {'lr': 0.00029117233977944554, 'samples': 13095744, 'steps': 68206, 'loss/train': 1.6091856956481934} 08/31/2021 01:32:19 - INFO - __main__ - Step 68208: {'lr': 0.0002911671054868452, 'samples': 13095936, 'steps': 68207, 'loss/train': 1.1424247026443481} 08/31/2021 01:32:21 - INFO - __main__ - Step 68209: {'lr': 0.00029116187117569567, 'samples': 13096128, 'steps': 68208, 'loss/train': 1.2149156332015991} 08/31/2021 01:32:21 - INFO - __main__ - Step 68210: {'lr': 0.0002911566368459992, 'samples': 13096320, 'steps': 68209, 'loss/train': 1.0054470300674438} 08/31/2021 01:32:21 - INFO - __main__ - Step 68211: {'lr': 0.0002911514024977582, 'samples': 13096512, 'steps': 68210, 'loss/train': 0.6728118658065796} 08/31/2021 01:32:22 - INFO - __main__ - Step 68212: {'lr': 0.000291146168130975, 'samples': 13096704, 'steps': 68211, 'loss/train': 1.8570133447647095} 08/31/2021 01:32:22 - INFO - __main__ - Step 68213: {'lr': 0.000291140933745652, 'samples': 13096896, 'steps': 68212, 'loss/train': 0.9649721384048462} 08/31/2021 01:32:22 - INFO - __main__ - Step 68214: {'lr': 0.0002911356993417915, 'samples': 13097088, 'steps': 68213, 'loss/train': 1.1075611114501953} 08/31/2021 01:32:24 - INFO - __main__ - Step 68215: {'lr': 0.00029113046491939585, 'samples': 13097280, 'steps': 68214, 'loss/train': 0.4509407877922058} 08/31/2021 01:32:25 - INFO - __main__ - Step 68216: {'lr': 0.00029112523047846757, 'samples': 13097472, 'steps': 68215, 'loss/train': 2.43389630317688} 08/31/2021 01:32:25 - INFO - __main__ - Step 68217: {'lr': 0.0002911199960190088, 'samples': 13097664, 'steps': 68216, 'loss/train': 0.9972076416015625} 08/31/2021 01:32:26 - INFO - __main__ - Step 68218: {'lr': 0.000291114761541022, 'samples': 13097856, 'steps': 68217, 'loss/train': 1.361508846282959} 08/31/2021 01:32:26 - INFO - __main__ - Step 68219: {'lr': 0.00029110952704450955, 'samples': 13098048, 'steps': 68218, 'loss/train': 0.07756655663251877} 08/31/2021 01:32:28 - INFO - __main__ - Step 68220: {'lr': 0.00029110429252947377, 'samples': 13098240, 'steps': 68219, 'loss/train': 2.2008631229400635} 08/31/2021 01:32:28 - INFO - __main__ - Step 68221: {'lr': 0.00029109905799591706, 'samples': 13098432, 'steps': 68220, 'loss/train': 1.6899158954620361} 08/31/2021 01:32:29 - INFO - __main__ - Step 68222: {'lr': 0.00029109382344384173, 'samples': 13098624, 'steps': 68221, 'loss/train': 1.3089725971221924} 08/31/2021 01:32:29 - INFO - __main__ - Step 68223: {'lr': 0.00029108858887325013, 'samples': 13098816, 'steps': 68222, 'loss/train': 1.5303027629852295} 08/31/2021 01:32:29 - INFO - __main__ - Step 68224: {'lr': 0.00029108335428414464, 'samples': 13099008, 'steps': 68223, 'loss/train': 0.49880149960517883} 08/31/2021 01:32:31 - INFO - __main__ - Step 68225: {'lr': 0.00029107811967652765, 'samples': 13099200, 'steps': 68224, 'loss/train': 1.119649887084961} 08/31/2021 01:32:31 - INFO - __main__ - Step 68226: {'lr': 0.0002910728850504015, 'samples': 13099392, 'steps': 68225, 'loss/train': 1.2007708549499512} 08/31/2021 01:32:32 - INFO - __main__ - Step 68227: {'lr': 0.0002910676504057686, 'samples': 13099584, 'steps': 68226, 'loss/train': 1.7505699396133423} 08/31/2021 01:32:32 - INFO - __main__ - Step 68228: {'lr': 0.00029106241574263116, 'samples': 13099776, 'steps': 68227, 'loss/train': 0.9658808708190918} 08/31/2021 01:32:32 - INFO - __main__ - Step 68229: {'lr': 0.0002910571810609916, 'samples': 13099968, 'steps': 68228, 'loss/train': 1.0086928606033325} 08/31/2021 01:32:34 - INFO - __main__ - Step 68230: {'lr': 0.0002910519463608524, 'samples': 13100160, 'steps': 68229, 'loss/train': 1.2013778686523438} 08/31/2021 01:32:35 - INFO - __main__ - Step 68231: {'lr': 0.00029104671164221574, 'samples': 13100352, 'steps': 68230, 'loss/train': 1.0396431684494019} 08/31/2021 01:32:35 - INFO - __main__ - Step 68232: {'lr': 0.0002910414769050841, 'samples': 13100544, 'steps': 68231, 'loss/train': 1.4804521799087524} 08/31/2021 01:32:35 - INFO - __main__ - Step 68233: {'lr': 0.0002910362421494598, 'samples': 13100736, 'steps': 68232, 'loss/train': 1.202102541923523} 08/31/2021 01:32:36 - INFO - __main__ - Step 68234: {'lr': 0.00029103100737534526, 'samples': 13100928, 'steps': 68233, 'loss/train': 1.109757423400879} 08/31/2021 01:32:37 - INFO - __main__ - Step 68235: {'lr': 0.0002910257725827428, 'samples': 13101120, 'steps': 68234, 'loss/train': 0.689448356628418} 08/31/2021 01:32:38 - INFO - __main__ - Step 68236: {'lr': 0.00029102053777165464, 'samples': 13101312, 'steps': 68235, 'loss/train': 1.0013620853424072} 08/31/2021 01:32:38 - INFO - __main__ - Step 68237: {'lr': 0.00029101530294208336, 'samples': 13101504, 'steps': 68236, 'loss/train': 0.9682286977767944} 08/31/2021 01:32:38 - INFO - __main__ - Step 68238: {'lr': 0.00029101006809403114, 'samples': 13101696, 'steps': 68237, 'loss/train': 1.0167193412780762} 08/31/2021 01:32:39 - INFO - __main__ - Step 68239: {'lr': 0.00029100483322750043, 'samples': 13101888, 'steps': 68238, 'loss/train': 0.3510865867137909} 08/31/2021 01:32:39 - INFO - __main__ - Step 68240: {'lr': 0.00029099959834249356, 'samples': 13102080, 'steps': 68239, 'loss/train': 1.6852891445159912} 08/31/2021 01:32:40 - INFO - __main__ - Step 68241: {'lr': 0.00029099436343901303, 'samples': 13102272, 'steps': 68240, 'loss/train': 1.2663004398345947} 08/31/2021 01:32:41 - INFO - __main__ - Step 68242: {'lr': 0.00029098912851706094, 'samples': 13102464, 'steps': 68241, 'loss/train': 0.48887011408805847} 08/31/2021 01:32:41 - INFO - __main__ - Step 68243: {'lr': 0.00029098389357663985, 'samples': 13102656, 'steps': 68242, 'loss/train': 1.4586509466171265} 08/31/2021 01:32:42 - INFO - __main__ - Step 68244: {'lr': 0.000290978658617752, 'samples': 13102848, 'steps': 68243, 'loss/train': 1.0050959587097168} 08/31/2021 01:32:42 - INFO - __main__ - Step 68245: {'lr': 0.0002909734236403998, 'samples': 13103040, 'steps': 68244, 'loss/train': 1.0626496076583862} 08/31/2021 01:32:44 - INFO - __main__ - Step 68246: {'lr': 0.00029096818864458564, 'samples': 13103232, 'steps': 68245, 'loss/train': 1.5251855850219727} 08/31/2021 01:32:44 - INFO - __main__ - Step 68247: {'lr': 0.0002909629536303119, 'samples': 13103424, 'steps': 68246, 'loss/train': 2.4116978645324707} 08/31/2021 01:32:45 - INFO - __main__ - Step 68248: {'lr': 0.0002909577185975808, 'samples': 13103616, 'steps': 68247, 'loss/train': 1.958675742149353} 08/31/2021 01:32:45 - INFO - __main__ - Step 68249: {'lr': 0.0002909524835463948, 'samples': 13103808, 'steps': 68248, 'loss/train': 0.05548269301652908} 08/31/2021 01:32:45 - INFO - __main__ - Step 68250: {'lr': 0.00029094724847675627, 'samples': 13104000, 'steps': 68249, 'loss/train': 0.9983542561531067} 08/31/2021 01:32:47 - INFO - __main__ - Step 68251: {'lr': 0.0002909420133886675, 'samples': 13104192, 'steps': 68250, 'loss/train': 1.732792615890503} 08/31/2021 01:32:47 - INFO - __main__ - Step 68252: {'lr': 0.0002909367782821309, 'samples': 13104384, 'steps': 68251, 'loss/train': 0.0315539613366127} 08/31/2021 01:32:48 - INFO - __main__ - Step 68253: {'lr': 0.00029093154315714884, 'samples': 13104576, 'steps': 68252, 'loss/train': 0.8909804224967957} 08/31/2021 01:32:48 - INFO - __main__ - Step 68254: {'lr': 0.0002909263080137237, 'samples': 13104768, 'steps': 68253, 'loss/train': 0.7391616106033325} 08/31/2021 01:32:48 - INFO - __main__ - Step 68255: {'lr': 0.0002909210728518577, 'samples': 13104960, 'steps': 68254, 'loss/train': 1.02452552318573} 08/31/2021 01:32:50 - INFO - __main__ - Step 68256: {'lr': 0.0002909158376715533, 'samples': 13105152, 'steps': 68255, 'loss/train': 0.47335150837898254} 08/31/2021 01:32:50 - INFO - __main__ - Step 68257: {'lr': 0.0002909106024728129, 'samples': 13105344, 'steps': 68256, 'loss/train': 1.3404724597930908} 08/31/2021 01:32:51 - INFO - __main__ - Step 68258: {'lr': 0.0002909053672556388, 'samples': 13105536, 'steps': 68257, 'loss/train': 0.7072112560272217} 08/31/2021 01:32:51 - INFO - __main__ - Step 68259: {'lr': 0.0002909001320200334, 'samples': 13105728, 'steps': 68258, 'loss/train': 0.6487130522727966} 08/31/2021 01:32:51 - INFO - __main__ - Step 68260: {'lr': 0.000290894896765999, 'samples': 13105920, 'steps': 68259, 'loss/train': 1.1788722276687622} 08/31/2021 01:32:53 - INFO - __main__ - Step 68261: {'lr': 0.00029088966149353807, 'samples': 13106112, 'steps': 68260, 'loss/train': 0.8305516839027405} 08/31/2021 01:32:53 - INFO - __main__ - Step 68262: {'lr': 0.0002908844262026528, 'samples': 13106304, 'steps': 68261, 'loss/train': 1.0852059125900269} 08/31/2021 01:32:54 - INFO - __main__ - Step 68263: {'lr': 0.00029087919089334564, 'samples': 13106496, 'steps': 68262, 'loss/train': 0.651207447052002} 08/31/2021 01:32:54 - INFO - __main__ - Step 68264: {'lr': 0.00029087395556561896, 'samples': 13106688, 'steps': 68263, 'loss/train': 0.9260433912277222} 08/31/2021 01:32:54 - INFO - __main__ - Step 68265: {'lr': 0.00029086872021947516, 'samples': 13106880, 'steps': 68264, 'loss/train': 0.31244969367980957} 08/31/2021 01:32:56 - INFO - __main__ - Step 68266: {'lr': 0.0002908634848549165, 'samples': 13107072, 'steps': 68265, 'loss/train': 1.3421013355255127} 08/31/2021 01:32:56 - INFO - __main__ - Step 68267: {'lr': 0.0002908582494719454, 'samples': 13107264, 'steps': 68266, 'loss/train': 1.7212965488433838} 08/31/2021 01:32:57 - INFO - __main__ - Step 68268: {'lr': 0.0002908530140705642, 'samples': 13107456, 'steps': 68267, 'loss/train': 1.163435459136963} 08/31/2021 01:32:57 - INFO - __main__ - Step 68269: {'lr': 0.0002908477786507752, 'samples': 13107648, 'steps': 68268, 'loss/train': 1.4085341691970825} 08/31/2021 01:32:57 - INFO - __main__ - Step 68270: {'lr': 0.00029084254321258085, 'samples': 13107840, 'steps': 68269, 'loss/train': 0.9648072123527527} 08/31/2021 01:32:59 - INFO - __main__ - Step 68271: {'lr': 0.0002908373077559836, 'samples': 13108032, 'steps': 68270, 'loss/train': 1.644148826599121} 08/31/2021 01:33:00 - INFO - __main__ - Step 68272: {'lr': 0.00029083207228098554, 'samples': 13108224, 'steps': 68271, 'loss/train': 0.7896692156791687} 08/31/2021 01:33:00 - INFO - __main__ - Step 68273: {'lr': 0.0002908268367875892, 'samples': 13108416, 'steps': 68272, 'loss/train': 1.3934568166732788} 08/31/2021 01:33:01 - INFO - __main__ - Step 68274: {'lr': 0.000290821601275797, 'samples': 13108608, 'steps': 68273, 'loss/train': 1.2787977457046509} 08/31/2021 01:33:01 - INFO - __main__ - Step 68275: {'lr': 0.00029081636574561115, 'samples': 13108800, 'steps': 68274, 'loss/train': 1.2241207361221313} 08/31/2021 01:33:03 - INFO - __main__ - Step 68276: {'lr': 0.00029081113019703407, 'samples': 13108992, 'steps': 68275, 'loss/train': 0.9655299782752991} 08/31/2021 01:33:03 - INFO - __main__ - Step 68277: {'lr': 0.0002908058946300681, 'samples': 13109184, 'steps': 68276, 'loss/train': 1.1219016313552856} 08/31/2021 01:33:04 - INFO - __main__ - Step 68278: {'lr': 0.0002908006590447157, 'samples': 13109376, 'steps': 68277, 'loss/train': 0.9366458058357239} 08/31/2021 01:33:04 - INFO - __main__ - Step 68279: {'lr': 0.00029079542344097916, 'samples': 13109568, 'steps': 68278, 'loss/train': 1.2553186416625977} 08/31/2021 01:33:04 - INFO - __main__ - Step 68280: {'lr': 0.0002907901878188608, 'samples': 13109760, 'steps': 68279, 'loss/train': 0.022391030564904213} 08/31/2021 01:33:05 - INFO - __main__ - Step 68281: {'lr': 0.000290784952178363, 'samples': 13109952, 'steps': 68280, 'loss/train': 1.3752951622009277} 08/31/2021 01:33:06 - INFO - __main__ - Step 68282: {'lr': 0.0002907797165194881, 'samples': 13110144, 'steps': 68281, 'loss/train': 0.27132272720336914} 08/31/2021 01:33:06 - INFO - __main__ - Step 68283: {'lr': 0.0002907744808422386, 'samples': 13110336, 'steps': 68282, 'loss/train': 0.9387616515159607} 08/31/2021 01:33:07 - INFO - __main__ - Step 68284: {'lr': 0.0002907692451466166, 'samples': 13110528, 'steps': 68283, 'loss/train': 1.582855224609375} 08/31/2021 01:33:07 - INFO - __main__ - Step 68285: {'lr': 0.00029076400943262465, 'samples': 13110720, 'steps': 68284, 'loss/train': 1.5211553573608398} 08/31/2021 01:33:08 - INFO - __main__ - Step 68286: {'lr': 0.00029075877370026516, 'samples': 13110912, 'steps': 68285, 'loss/train': 0.8592393398284912} 08/31/2021 01:33:09 - INFO - __main__ - Step 68287: {'lr': 0.00029075353794954037, 'samples': 13111104, 'steps': 68286, 'loss/train': 0.6157307624816895} 08/31/2021 01:33:10 - INFO - __main__ - Step 68288: {'lr': 0.00029074830218045255, 'samples': 13111296, 'steps': 68287, 'loss/train': 1.4782217741012573} 08/31/2021 01:33:10 - INFO - __main__ - Step 68289: {'lr': 0.00029074306639300426, 'samples': 13111488, 'steps': 68288, 'loss/train': 1.095231533050537} 08/31/2021 01:33:10 - INFO - __main__ - Step 68290: {'lr': 0.00029073783058719777, 'samples': 13111680, 'steps': 68289, 'loss/train': 1.3776792287826538} 08/31/2021 01:33:11 - INFO - __main__ - Step 68291: {'lr': 0.00029073259476303546, 'samples': 13111872, 'steps': 68290, 'loss/train': 1.0549005270004272} 08/31/2021 01:33:12 - INFO - __main__ - Step 68292: {'lr': 0.00029072735892051967, 'samples': 13112064, 'steps': 68291, 'loss/train': 1.255000352859497} 08/31/2021 01:33:13 - INFO - __main__ - Step 68293: {'lr': 0.0002907221230596527, 'samples': 13112256, 'steps': 68292, 'loss/train': 1.2774090766906738} 08/31/2021 01:33:13 - INFO - __main__ - Step 68294: {'lr': 0.00029071688718043697, 'samples': 13112448, 'steps': 68293, 'loss/train': 1.6506061553955078} 08/31/2021 01:33:13 - INFO - __main__ - Step 68295: {'lr': 0.00029071165128287494, 'samples': 13112640, 'steps': 68294, 'loss/train': 1.221009612083435} 08/31/2021 01:33:14 - INFO - __main__ - Step 68296: {'lr': 0.00029070641536696874, 'samples': 13112832, 'steps': 68295, 'loss/train': 1.6281782388687134} 08/31/2021 01:33:14 - INFO - __main__ - Step 68297: {'lr': 0.00029070117943272094, 'samples': 13113024, 'steps': 68296, 'loss/train': 1.325685977935791} 08/31/2021 01:33:15 - INFO - __main__ - Step 68298: {'lr': 0.00029069594348013386, 'samples': 13113216, 'steps': 68297, 'loss/train': 1.142771601676941} 08/31/2021 01:33:16 - INFO - __main__ - Step 68299: {'lr': 0.00029069070750920966, 'samples': 13113408, 'steps': 68298, 'loss/train': 0.2843590974807739} 08/31/2021 01:33:16 - INFO - __main__ - Step 68300: {'lr': 0.000290685471519951, 'samples': 13113600, 'steps': 68299, 'loss/train': 1.071016550064087} 08/31/2021 01:33:17 - INFO - __main__ - Step 68301: {'lr': 0.00029068023551236, 'samples': 13113792, 'steps': 68300, 'loss/train': 1.8013430833816528} 08/31/2021 01:33:17 - INFO - __main__ - Step 68302: {'lr': 0.00029067499948643924, 'samples': 13113984, 'steps': 68301, 'loss/train': 1.428745985031128} 08/31/2021 01:33:19 - INFO - __main__ - Step 68303: {'lr': 0.00029066976344219083, 'samples': 13114176, 'steps': 68302, 'loss/train': 1.0904937982559204} 08/31/2021 01:33:19 - INFO - __main__ - Step 68304: {'lr': 0.0002906645273796173, 'samples': 13114368, 'steps': 68303, 'loss/train': 1.326312780380249} 08/31/2021 01:33:19 - INFO - __main__ - Step 68305: {'lr': 0.00029065929129872095, 'samples': 13114560, 'steps': 68304, 'loss/train': 0.7342612147331238} 08/31/2021 01:33:20 - INFO - __main__ - Step 68306: {'lr': 0.0002906540551995041, 'samples': 13114752, 'steps': 68305, 'loss/train': 0.6534122228622437} 08/31/2021 01:33:20 - INFO - __main__ - Step 68307: {'lr': 0.0002906488190819692, 'samples': 13114944, 'steps': 68306, 'loss/train': 1.1291056871414185} 08/31/2021 01:33:20 - INFO - __main__ - Step 68308: {'lr': 0.00029064358294611867, 'samples': 13115136, 'steps': 68307, 'loss/train': 1.0658934116363525} 08/31/2021 01:33:22 - INFO - __main__ - Step 68309: {'lr': 0.00029063834679195465, 'samples': 13115328, 'steps': 68308, 'loss/train': 1.245192050933838} 08/31/2021 01:33:22 - INFO - __main__ - Step 68310: {'lr': 0.00029063311061947966, 'samples': 13115520, 'steps': 68309, 'loss/train': 1.311521053314209} 08/31/2021 01:33:23 - INFO - __main__ - Step 68311: {'lr': 0.00029062787442869596, 'samples': 13115712, 'steps': 68310, 'loss/train': 1.1826874017715454} 08/31/2021 01:33:23 - INFO - __main__ - Step 68312: {'lr': 0.00029062263821960605, 'samples': 13115904, 'steps': 68311, 'loss/train': 1.4529142379760742} 08/31/2021 01:33:23 - INFO - __main__ - Step 68313: {'lr': 0.00029061740199221215, 'samples': 13116096, 'steps': 68312, 'loss/train': 1.0491831302642822} 08/31/2021 01:33:25 - INFO - __main__ - Step 68314: {'lr': 0.0002906121657465167, 'samples': 13116288, 'steps': 68313, 'loss/train': 1.2611268758773804} 08/31/2021 01:33:25 - INFO - __main__ - Step 68315: {'lr': 0.00029060692948252204, 'samples': 13116480, 'steps': 68314, 'loss/train': 0.6872463226318359} 08/31/2021 01:33:26 - INFO - __main__ - Step 68316: {'lr': 0.0002906016932002305, 'samples': 13116672, 'steps': 68315, 'loss/train': 1.31606924533844} 08/31/2021 01:33:26 - INFO - __main__ - Step 68317: {'lr': 0.0002905964568996445, 'samples': 13116864, 'steps': 68316, 'loss/train': 1.3691829442977905} 08/31/2021 01:33:26 - INFO - __main__ - Step 68318: {'lr': 0.0002905912205807663, 'samples': 13117056, 'steps': 68317, 'loss/train': 1.294265627861023} 08/31/2021 01:33:28 - INFO - __main__ - Step 68319: {'lr': 0.0002905859842435984, 'samples': 13117248, 'steps': 68318, 'loss/train': 1.259339451789856} 08/31/2021 01:33:28 - INFO - __main__ - Step 68320: {'lr': 0.00029058074788814304, 'samples': 13117440, 'steps': 68319, 'loss/train': 1.9347575902938843} 08/31/2021 01:33:29 - INFO - __main__ - Step 68321: {'lr': 0.00029057551151440267, 'samples': 13117632, 'steps': 68320, 'loss/train': 1.6844044923782349} 08/31/2021 01:33:29 - INFO - __main__ - Step 68322: {'lr': 0.00029057027512237955, 'samples': 13117824, 'steps': 68321, 'loss/train': 1.3334020376205444} 08/31/2021 01:33:29 - INFO - __main__ - Step 68323: {'lr': 0.0002905650387120761, 'samples': 13118016, 'steps': 68322, 'loss/train': 1.1153171062469482} 08/31/2021 01:33:31 - INFO - __main__ - Step 68324: {'lr': 0.0002905598022834946, 'samples': 13118208, 'steps': 68323, 'loss/train': 1.711625099182129} 08/31/2021 01:33:31 - INFO - __main__ - Step 68325: {'lr': 0.0002905545658366375, 'samples': 13118400, 'steps': 68324, 'loss/train': 0.7157991528511047} 08/31/2021 01:33:32 - INFO - __main__ - Step 68326: {'lr': 0.00029054932937150725, 'samples': 13118592, 'steps': 68325, 'loss/train': 2.0600316524505615} 08/31/2021 01:33:32 - INFO - __main__ - Step 68327: {'lr': 0.000290544092888106, 'samples': 13118784, 'steps': 68326, 'loss/train': 1.4289733171463013} 08/31/2021 01:33:32 - INFO - __main__ - Step 68328: {'lr': 0.0002905388563864363, 'samples': 13118976, 'steps': 68327, 'loss/train': 1.3581582307815552} 08/31/2021 01:33:34 - INFO - __main__ - Step 68329: {'lr': 0.00029053361986650035, 'samples': 13119168, 'steps': 68328, 'loss/train': 1.455905556678772} 08/31/2021 01:33:35 - INFO - __main__ - Step 68330: {'lr': 0.00029052838332830055, 'samples': 13119360, 'steps': 68329, 'loss/train': 1.623052716255188} 08/31/2021 01:33:35 - INFO - __main__ - Step 68331: {'lr': 0.0002905231467718393, 'samples': 13119552, 'steps': 68330, 'loss/train': 1.2838512659072876} 08/31/2021 01:33:35 - INFO - __main__ - Step 68332: {'lr': 0.00029051791019711897, 'samples': 13119744, 'steps': 68331, 'loss/train': 1.3751112222671509} 08/31/2021 01:33:36 - INFO - __main__ - Step 68333: {'lr': 0.00029051267360414185, 'samples': 13119936, 'steps': 68332, 'loss/train': 1.7148526906967163} 08/31/2021 01:33:37 - INFO - __main__ - Step 68334: {'lr': 0.00029050743699291035, 'samples': 13120128, 'steps': 68333, 'loss/train': 1.2770839929580688} 08/31/2021 01:33:38 - INFO - __main__ - Step 68335: {'lr': 0.00029050220036342696, 'samples': 13120320, 'steps': 68334, 'loss/train': 0.39435625076293945} 08/31/2021 01:33:38 - INFO - __main__ - Step 68336: {'lr': 0.0002904969637156938, 'samples': 13120512, 'steps': 68335, 'loss/train': 0.9040395021438599} 08/31/2021 01:33:39 - INFO - __main__ - Step 68337: {'lr': 0.00029049172704971333, 'samples': 13120704, 'steps': 68336, 'loss/train': 1.0512423515319824} 08/31/2021 01:33:39 - INFO - __main__ - Step 68338: {'lr': 0.0002904864903654879, 'samples': 13120896, 'steps': 68337, 'loss/train': 0.9200107455253601} 08/31/2021 01:33:41 - INFO - __main__ - Step 68339: {'lr': 0.0002904812536630199, 'samples': 13121088, 'steps': 68338, 'loss/train': 0.6985852122306824} 08/31/2021 01:33:41 - INFO - __main__ - Step 68340: {'lr': 0.0002904760169423116, 'samples': 13121280, 'steps': 68339, 'loss/train': 1.3674851655960083} 08/31/2021 01:33:41 - INFO - __main__ - Step 68341: {'lr': 0.0002904707802033656, 'samples': 13121472, 'steps': 68340, 'loss/train': 1.461983561515808} 08/31/2021 01:33:42 - INFO - __main__ - Step 68342: {'lr': 0.000290465543446184, 'samples': 13121664, 'steps': 68341, 'loss/train': 5.66592264175415} 08/31/2021 01:33:42 - INFO - __main__ - Step 68343: {'lr': 0.00029046030667076916, 'samples': 13121856, 'steps': 68342, 'loss/train': 5.590814113616943} 08/31/2021 01:33:42 - INFO - __main__ - Step 68344: {'lr': 0.0002904550698771237, 'samples': 13122048, 'steps': 68343, 'loss/train': 0.4457715153694153} 08/31/2021 01:33:44 - INFO - __main__ - Step 68345: {'lr': 0.0002904498330652496, 'samples': 13122240, 'steps': 68344, 'loss/train': 1.5812406539916992} 08/31/2021 01:33:44 - INFO - __main__ - Step 68346: {'lr': 0.0002904445962351496, 'samples': 13122432, 'steps': 68345, 'loss/train': 1.4648075103759766} 08/31/2021 01:33:45 - INFO - __main__ - Step 68347: {'lr': 0.00029043935938682583, 'samples': 13122624, 'steps': 68346, 'loss/train': 1.8229347467422485} 08/31/2021 01:33:45 - INFO - __main__ - Step 68348: {'lr': 0.00029043412252028076, 'samples': 13122816, 'steps': 68347, 'loss/train': 0.12367294728755951} 08/31/2021 01:33:45 - INFO - __main__ - Step 68349: {'lr': 0.00029042888563551666, 'samples': 13123008, 'steps': 68348, 'loss/train': 1.912804126739502} 08/31/2021 01:33:46 - INFO - __main__ - Step 68350: {'lr': 0.0002904236487325359, 'samples': 13123200, 'steps': 68349, 'loss/train': 1.2780665159225464} 08/31/2021 01:33:47 - INFO - __main__ - Step 68351: {'lr': 0.00029041841181134086, 'samples': 13123392, 'steps': 68350, 'loss/train': 0.7516918778419495} 08/31/2021 01:33:48 - INFO - __main__ - Step 68352: {'lr': 0.000290413174871934, 'samples': 13123584, 'steps': 68351, 'loss/train': 0.7866028547286987} 08/31/2021 01:33:48 - INFO - __main__ - Step 68353: {'lr': 0.00029040793791431746, 'samples': 13123776, 'steps': 68352, 'loss/train': 1.1524262428283691} 08/31/2021 01:33:48 - INFO - __main__ - Step 68354: {'lr': 0.0002904027009384938, 'samples': 13123968, 'steps': 68353, 'loss/train': 0.08721006661653519} 08/31/2021 01:33:49 - INFO - __main__ - Step 68355: {'lr': 0.0002903974639444654, 'samples': 13124160, 'steps': 68354, 'loss/train': 0.8584244251251221} 08/31/2021 01:33:50 - INFO - __main__ - Step 68356: {'lr': 0.0002903922269322344, 'samples': 13124352, 'steps': 68355, 'loss/train': 0.7792115211486816} 08/31/2021 01:33:51 - INFO - __main__ - Step 68357: {'lr': 0.0002903869899018033, 'samples': 13124544, 'steps': 68356, 'loss/train': 1.4157836437225342} 08/31/2021 01:33:51 - INFO - __main__ - Step 68358: {'lr': 0.0002903817528531744, 'samples': 13124736, 'steps': 68357, 'loss/train': 1.129551887512207} 08/31/2021 01:33:51 - INFO - __main__ - Step 68359: {'lr': 0.00029037651578635017, 'samples': 13124928, 'steps': 68358, 'loss/train': 1.4244186878204346} 08/31/2021 01:33:52 - INFO - __main__ - Step 68360: {'lr': 0.0002903712787013329, 'samples': 13125120, 'steps': 68359, 'loss/train': 1.5115058422088623} 08/31/2021 01:33:53 - INFO - __main__ - Step 68361: {'lr': 0.000290366041598125, 'samples': 13125312, 'steps': 68360, 'loss/train': 0.8729142546653748} 08/31/2021 01:33:54 - INFO - __main__ - Step 68362: {'lr': 0.00029036080447672875, 'samples': 13125504, 'steps': 68361, 'loss/train': 1.5964806079864502} 08/31/2021 01:33:54 - INFO - __main__ - Step 68363: {'lr': 0.0002903555673371465, 'samples': 13125696, 'steps': 68362, 'loss/train': 1.0941388607025146} 08/31/2021 01:33:54 - INFO - __main__ - Step 68364: {'lr': 0.00029035033017938067, 'samples': 13125888, 'steps': 68363, 'loss/train': 0.754223644733429} 08/31/2021 01:33:55 - INFO - __main__ - Step 68365: {'lr': 0.0002903450930034336, 'samples': 13126080, 'steps': 68364, 'loss/train': 1.031327247619629} 08/31/2021 01:33:57 - INFO - __main__ - Step 68366: {'lr': 0.00029033985580930767, 'samples': 13126272, 'steps': 68365, 'loss/train': 1.2902047634124756} 08/31/2021 01:33:57 - INFO - __main__ - Step 68367: {'lr': 0.0002903346185970052, 'samples': 13126464, 'steps': 68366, 'loss/train': 0.9101170897483826} 08/31/2021 01:33:58 - INFO - __main__ - Step 68368: {'lr': 0.0002903293813665287, 'samples': 13126656, 'steps': 68367, 'loss/train': 0.773718535900116} 08/31/2021 01:33:58 - INFO - __main__ - Step 68369: {'lr': 0.0002903241441178803, 'samples': 13126848, 'steps': 68368, 'loss/train': 0.020782189443707466} 08/31/2021 01:33:58 - INFO - __main__ - Step 68370: {'lr': 0.0002903189068510624, 'samples': 13127040, 'steps': 68369, 'loss/train': 0.9187906384468079} 08/31/2021 01:33:59 - INFO - __main__ - Step 68371: {'lr': 0.00029031366956607755, 'samples': 13127232, 'steps': 68370, 'loss/train': 1.4562162160873413} 08/31/2021 01:34:00 - INFO - __main__ - Step 68372: {'lr': 0.00029030843226292784, 'samples': 13127424, 'steps': 68371, 'loss/train': 1.703060269355774} 08/31/2021 01:34:00 - INFO - __main__ - Step 68373: {'lr': 0.0002903031949416159, 'samples': 13127616, 'steps': 68372, 'loss/train': 1.259192705154419} 08/31/2021 01:34:01 - INFO - __main__ - Step 68374: {'lr': 0.0002902979576021439, 'samples': 13127808, 'steps': 68373, 'loss/train': 1.2060261964797974} 08/31/2021 01:34:01 - INFO - __main__ - Step 68375: {'lr': 0.0002902927202445143, 'samples': 13128000, 'steps': 68374, 'loss/train': 1.2474443912506104} 08/31/2021 01:34:02 - INFO - __main__ - Step 68376: {'lr': 0.0002902874828687294, 'samples': 13128192, 'steps': 68375, 'loss/train': 0.8682750463485718} 08/31/2021 01:34:03 - INFO - __main__ - Step 68377: {'lr': 0.0002902822454747916, 'samples': 13128384, 'steps': 68376, 'loss/train': 0.6740553975105286} 08/31/2021 01:34:03 - INFO - __main__ - Step 68378: {'lr': 0.0002902770080627032, 'samples': 13128576, 'steps': 68377, 'loss/train': 1.1543081998825073} 08/31/2021 01:34:04 - INFO - __main__ - Step 68379: {'lr': 0.0002902717706324666, 'samples': 13128768, 'steps': 68378, 'loss/train': 1.5385091304779053} 08/31/2021 01:34:04 - INFO - __main__ - Step 68380: {'lr': 0.0002902665331840842, 'samples': 13128960, 'steps': 68379, 'loss/train': 0.48120471835136414} 08/31/2021 01:34:05 - INFO - __main__ - Step 68381: {'lr': 0.0002902612957175583, 'samples': 13129152, 'steps': 68380, 'loss/train': 1.3266798257827759} 08/31/2021 01:34:07 - INFO - __main__ - Step 68382: {'lr': 0.0002902560582328913, 'samples': 13129344, 'steps': 68381, 'loss/train': 1.8603378534317017} 08/31/2021 01:34:07 - INFO - __main__ - Step 68383: {'lr': 0.0002902508207300856, 'samples': 13129536, 'steps': 68382, 'loss/train': 0.632861316204071} 08/31/2021 01:34:07 - INFO - __main__ - Step 68384: {'lr': 0.00029024558320914337, 'samples': 13129728, 'steps': 68383, 'loss/train': 1.1651573181152344} 08/31/2021 01:34:08 - INFO - __main__ - Step 68385: {'lr': 0.0002902403456700672, 'samples': 13129920, 'steps': 68384, 'loss/train': 0.5149828791618347} 08/31/2021 01:34:08 - INFO - __main__ - Step 68386: {'lr': 0.00029023510811285923, 'samples': 13130112, 'steps': 68385, 'loss/train': 2.0208399295806885} 08/31/2021 01:34:08 - INFO - __main__ - Step 68387: {'lr': 0.00029022987053752204, 'samples': 13130304, 'steps': 68386, 'loss/train': 1.200089931488037} 08/31/2021 01:34:10 - INFO - __main__ - Step 68388: {'lr': 0.00029022463294405796, 'samples': 13130496, 'steps': 68387, 'loss/train': 1.365473985671997} 08/31/2021 01:34:10 - INFO - __main__ - Step 68389: {'lr': 0.00029021939533246916, 'samples': 13130688, 'steps': 68388, 'loss/train': 1.6131004095077515} 08/31/2021 01:34:11 - INFO - __main__ - Step 68390: {'lr': 0.00029021415770275814, 'samples': 13130880, 'steps': 68389, 'loss/train': 1.3724850416183472} 08/31/2021 01:34:11 - INFO - __main__ - Step 68391: {'lr': 0.0002902089200549273, 'samples': 13131072, 'steps': 68390, 'loss/train': 1.0164248943328857} 08/31/2021 01:34:11 - INFO - __main__ - Step 68392: {'lr': 0.0002902036823889789, 'samples': 13131264, 'steps': 68391, 'loss/train': 5.913998126983643} 08/31/2021 01:34:13 - INFO - __main__ - Step 68393: {'lr': 0.0002901984447049153, 'samples': 13131456, 'steps': 68392, 'loss/train': 1.1419810056686401} 08/31/2021 01:34:13 - INFO - __main__ - Step 68394: {'lr': 0.00029019320700273896, 'samples': 13131648, 'steps': 68393, 'loss/train': 1.2309643030166626} 08/31/2021 01:34:14 - INFO - __main__ - Step 68395: {'lr': 0.00029018796928245217, 'samples': 13131840, 'steps': 68394, 'loss/train': 1.0875496864318848} 08/31/2021 01:34:14 - INFO - __main__ - Step 68396: {'lr': 0.00029018273154405726, 'samples': 13132032, 'steps': 68395, 'loss/train': 1.629975438117981} 08/31/2021 01:34:14 - INFO - __main__ - Step 68397: {'lr': 0.0002901774937875567, 'samples': 13132224, 'steps': 68396, 'loss/train': 0.8070445656776428} 08/31/2021 01:34:16 - INFO - __main__ - Step 68398: {'lr': 0.0002901722560129527, 'samples': 13132416, 'steps': 68397, 'loss/train': 0.9590449333190918} 08/31/2021 01:34:16 - INFO - __main__ - Step 68399: {'lr': 0.00029016701822024777, 'samples': 13132608, 'steps': 68398, 'loss/train': 1.2848174571990967} 08/31/2021 01:34:17 - INFO - __main__ - Step 68400: {'lr': 0.0002901617804094442, 'samples': 13132800, 'steps': 68399, 'loss/train': 0.6735925078392029} 08/31/2021 01:34:17 - INFO - __main__ - Step 68401: {'lr': 0.0002901565425805443, 'samples': 13132992, 'steps': 68400, 'loss/train': 1.1481958627700806} 08/31/2021 01:34:17 - INFO - __main__ - Step 68402: {'lr': 0.00029015130473355056, 'samples': 13133184, 'steps': 68401, 'loss/train': 1.2226781845092773} 08/31/2021 01:34:19 - INFO - __main__ - Step 68403: {'lr': 0.0002901460668684652, 'samples': 13133376, 'steps': 68402, 'loss/train': 1.0846539735794067} 08/31/2021 01:34:19 - INFO - __main__ - Step 68404: {'lr': 0.00029014082898529066, 'samples': 13133568, 'steps': 68403, 'loss/train': 0.9618962407112122} 08/31/2021 01:34:20 - INFO - __main__ - Step 68405: {'lr': 0.0002901355910840293, 'samples': 13133760, 'steps': 68404, 'loss/train': 0.24806909263134003} 08/31/2021 01:34:20 - INFO - __main__ - Step 68406: {'lr': 0.0002901303531646834, 'samples': 13133952, 'steps': 68405, 'loss/train': 1.3503397703170776} 08/31/2021 01:34:20 - INFO - __main__ - Step 68407: {'lr': 0.00029012511522725544, 'samples': 13134144, 'steps': 68406, 'loss/train': 1.6775612831115723} 08/31/2021 01:34:21 - INFO - __main__ - Step 68408: {'lr': 0.00029011987727174774, 'samples': 13134336, 'steps': 68407, 'loss/train': 3.310159921646118} 08/31/2021 01:34:22 - INFO - __main__ - Step 68409: {'lr': 0.0002901146392981626, 'samples': 13134528, 'steps': 68408, 'loss/train': 1.2924717664718628} 08/31/2021 01:34:23 - INFO - __main__ - Step 68410: {'lr': 0.00029010940130650244, 'samples': 13134720, 'steps': 68409, 'loss/train': 1.454147219657898} 08/31/2021 01:34:23 - INFO - __main__ - Step 68411: {'lr': 0.00029010416329676957, 'samples': 13134912, 'steps': 68410, 'loss/train': 0.8730812668800354} 08/31/2021 01:34:23 - INFO - __main__ - Step 68412: {'lr': 0.0002900989252689664, 'samples': 13135104, 'steps': 68411, 'loss/train': 0.9830076694488525} 08/31/2021 01:34:24 - INFO - __main__ - Step 68413: {'lr': 0.0002900936872230953, 'samples': 13135296, 'steps': 68412, 'loss/train': 1.4735957384109497} 08/31/2021 01:34:25 - INFO - __main__ - Step 68414: {'lr': 0.0002900884491591586, 'samples': 13135488, 'steps': 68413, 'loss/train': 1.1715646982192993} 08/31/2021 01:34:25 - INFO - __main__ - Step 68415: {'lr': 0.00029008321107715863, 'samples': 13135680, 'steps': 68414, 'loss/train': 0.15835781395435333} 08/31/2021 01:34:26 - INFO - __main__ - Step 68416: {'lr': 0.00029007797297709784, 'samples': 13135872, 'steps': 68415, 'loss/train': 1.5644997358322144} 08/31/2021 01:34:26 - INFO - __main__ - Step 68417: {'lr': 0.00029007273485897846, 'samples': 13136064, 'steps': 68416, 'loss/train': 1.0897552967071533} 08/31/2021 01:34:27 - INFO - __main__ - Step 68418: {'lr': 0.0002900674967228029, 'samples': 13136256, 'steps': 68417, 'loss/train': 1.4531021118164062} 08/31/2021 01:34:28 - INFO - __main__ - Step 68419: {'lr': 0.0002900622585685736, 'samples': 13136448, 'steps': 68418, 'loss/train': 0.6941252946853638} 08/31/2021 01:34:29 - INFO - __main__ - Step 68420: {'lr': 0.0002900570203962929, 'samples': 13136640, 'steps': 68419, 'loss/train': 1.202345609664917} 08/31/2021 01:34:29 - INFO - __main__ - Step 68421: {'lr': 0.00029005178220596313, 'samples': 13136832, 'steps': 68420, 'loss/train': 0.9776018857955933} 08/31/2021 01:34:29 - INFO - __main__ - Step 68422: {'lr': 0.0002900465439975866, 'samples': 13137024, 'steps': 68421, 'loss/train': 2.100146532058716} 08/31/2021 01:34:30 - INFO - __main__ - Step 68423: {'lr': 0.0002900413057711657, 'samples': 13137216, 'steps': 68422, 'loss/train': 1.3226743936538696} 08/31/2021 01:34:31 - INFO - __main__ - Step 68424: {'lr': 0.0002900360675267028, 'samples': 13137408, 'steps': 68423, 'loss/train': 1.0883064270019531} 08/31/2021 01:34:32 - INFO - __main__ - Step 68425: {'lr': 0.0002900308292642003, 'samples': 13137600, 'steps': 68424, 'loss/train': 1.4257744550704956} 08/31/2021 01:34:32 - INFO - __main__ - Step 68426: {'lr': 0.00029002559098366057, 'samples': 13137792, 'steps': 68425, 'loss/train': 1.6951450109481812} 08/31/2021 01:34:32 - INFO - __main__ - Step 68427: {'lr': 0.0002900203526850859, 'samples': 13137984, 'steps': 68426, 'loss/train': 0.9853631258010864} 08/31/2021 01:34:33 - INFO - __main__ - Step 68428: {'lr': 0.00029001511436847863, 'samples': 13138176, 'steps': 68427, 'loss/train': 1.1668212413787842} 08/31/2021 01:34:34 - INFO - __main__ - Step 68429: {'lr': 0.00029000987603384115, 'samples': 13138368, 'steps': 68428, 'loss/train': 1.0820118188858032} 08/31/2021 01:34:35 - INFO - __main__ - Step 68430: {'lr': 0.0002900046376811759, 'samples': 13138560, 'steps': 68429, 'loss/train': 1.1970747709274292} 08/31/2021 01:34:35 - INFO - __main__ - Step 68431: {'lr': 0.0002899993993104852, 'samples': 13138752, 'steps': 68430, 'loss/train': 0.8202576041221619} 08/31/2021 01:34:35 - INFO - __main__ - Step 68432: {'lr': 0.0002899941609217713, 'samples': 13138944, 'steps': 68431, 'loss/train': 0.8493996262550354} 08/31/2021 01:34:36 - INFO - __main__ - Step 68433: {'lr': 0.0002899889225150367, 'samples': 13139136, 'steps': 68432, 'loss/train': 1.321224331855774} 08/31/2021 01:34:36 - INFO - __main__ - Step 68434: {'lr': 0.0002899836840902837, 'samples': 13139328, 'steps': 68433, 'loss/train': 1.3762327432632446} 08/31/2021 01:34:38 - INFO - __main__ - Step 68435: {'lr': 0.00028997844564751464, 'samples': 13139520, 'steps': 68434, 'loss/train': 1.039636492729187} 08/31/2021 01:34:39 - INFO - __main__ - Step 68436: {'lr': 0.0002899732071867319, 'samples': 13139712, 'steps': 68435, 'loss/train': 0.5574381351470947} 08/31/2021 01:34:39 - INFO - __main__ - Step 68437: {'lr': 0.00028996796870793795, 'samples': 13139904, 'steps': 68436, 'loss/train': 1.7521443367004395} 08/31/2021 01:34:39 - INFO - __main__ - Step 68438: {'lr': 0.000289962730211135, 'samples': 13140096, 'steps': 68437, 'loss/train': 1.2688448429107666} 08/31/2021 01:34:40 - INFO - __main__ - Step 68439: {'lr': 0.00028995749169632545, 'samples': 13140288, 'steps': 68438, 'loss/train': 0.7019142508506775} 08/31/2021 01:34:41 - INFO - __main__ - Step 68440: {'lr': 0.00028995225316351164, 'samples': 13140480, 'steps': 68439, 'loss/train': 0.40624991059303284} 08/31/2021 01:34:42 - INFO - __main__ - Step 68441: {'lr': 0.00028994701461269596, 'samples': 13140672, 'steps': 68440, 'loss/train': 0.8434987664222717} 08/31/2021 01:34:42 - INFO - __main__ - Step 68442: {'lr': 0.00028994177604388084, 'samples': 13140864, 'steps': 68441, 'loss/train': 0.8279221653938293} 08/31/2021 01:34:43 - INFO - __main__ - Step 68443: {'lr': 0.00028993653745706857, 'samples': 13141056, 'steps': 68442, 'loss/train': 1.489992380142212} 08/31/2021 01:34:43 - INFO - __main__ - Step 68444: {'lr': 0.00028993129885226146, 'samples': 13141248, 'steps': 68443, 'loss/train': 1.6129447221755981} 08/31/2021 01:34:44 - INFO - __main__ - Step 68445: {'lr': 0.0002899260602294619, 'samples': 13141440, 'steps': 68444, 'loss/train': 1.3355801105499268} 08/31/2021 01:34:45 - INFO - __main__ - Step 68446: {'lr': 0.00028992082158867236, 'samples': 13141632, 'steps': 68445, 'loss/train': 0.8152126669883728} 08/31/2021 01:34:45 - INFO - __main__ - Step 68447: {'lr': 0.000289915582929895, 'samples': 13141824, 'steps': 68446, 'loss/train': 1.5379836559295654} 08/31/2021 01:34:45 - INFO - __main__ - Step 68448: {'lr': 0.00028991034425313234, 'samples': 13142016, 'steps': 68447, 'loss/train': 1.095365047454834} 08/31/2021 01:34:46 - INFO - __main__ - Step 68449: {'lr': 0.00028990510555838676, 'samples': 13142208, 'steps': 68448, 'loss/train': 1.4822686910629272} 08/31/2021 01:34:47 - INFO - __main__ - Step 68450: {'lr': 0.0002898998668456605, 'samples': 13142400, 'steps': 68449, 'loss/train': 1.3391358852386475} 08/31/2021 01:34:48 - INFO - __main__ - Step 68451: {'lr': 0.000289894628114956, 'samples': 13142592, 'steps': 68450, 'loss/train': 1.2521768808364868} 08/31/2021 01:34:48 - INFO - __main__ - Step 68452: {'lr': 0.0002898893893662756, 'samples': 13142784, 'steps': 68451, 'loss/train': 1.6058480739593506} 08/31/2021 01:34:49 - INFO - __main__ - Step 68453: {'lr': 0.0002898841505996216, 'samples': 13142976, 'steps': 68452, 'loss/train': 0.5015112161636353} 08/31/2021 01:34:49 - INFO - __main__ - Step 68454: {'lr': 0.0002898789118149964, 'samples': 13143168, 'steps': 68453, 'loss/train': 1.0090773105621338} 08/31/2021 01:34:51 - INFO - __main__ - Step 68455: {'lr': 0.0002898736730124025, 'samples': 13143360, 'steps': 68454, 'loss/train': 0.2773524224758148} 08/31/2021 01:34:51 - INFO - __main__ - Step 68456: {'lr': 0.00028986843419184213, 'samples': 13143552, 'steps': 68455, 'loss/train': 1.3218152523040771} 08/31/2021 01:34:51 - INFO - __main__ - Step 68457: {'lr': 0.0002898631953533176, 'samples': 13143744, 'steps': 68456, 'loss/train': 0.05975029245018959} 08/31/2021 01:34:52 - INFO - __main__ - Step 68458: {'lr': 0.00028985795649683126, 'samples': 13143936, 'steps': 68457, 'loss/train': 0.5654512643814087} 08/31/2021 01:34:52 - INFO - __main__ - Step 68459: {'lr': 0.0002898527176223856, 'samples': 13144128, 'steps': 68458, 'loss/train': 2.535764217376709} 08/31/2021 01:34:53 - INFO - __main__ - Step 68460: {'lr': 0.00028984747872998293, 'samples': 13144320, 'steps': 68459, 'loss/train': 1.6192790269851685} 08/31/2021 01:34:54 - INFO - __main__ - Step 68461: {'lr': 0.0002898422398196256, 'samples': 13144512, 'steps': 68460, 'loss/train': 1.309002161026001} 08/31/2021 01:34:54 - INFO - __main__ - Step 68462: {'lr': 0.00028983700089131603, 'samples': 13144704, 'steps': 68461, 'loss/train': 1.3734573125839233} 08/31/2021 01:34:55 - INFO - __main__ - Step 68463: {'lr': 0.00028983176194505647, 'samples': 13144896, 'steps': 68462, 'loss/train': 1.5607126951217651} 08/31/2021 01:34:55 - INFO - __main__ - Step 68464: {'lr': 0.00028982652298084925, 'samples': 13145088, 'steps': 68463, 'loss/train': 0.8695279359817505} 08/31/2021 01:34:55 - INFO - __main__ - Step 68465: {'lr': 0.0002898212839986969, 'samples': 13145280, 'steps': 68464, 'loss/train': 1.4448851346969604} 08/31/2021 01:34:57 - INFO - __main__ - Step 68466: {'lr': 0.0002898160449986017, 'samples': 13145472, 'steps': 68465, 'loss/train': 1.383121371269226} 08/31/2021 01:34:57 - INFO - __main__ - Step 68467: {'lr': 0.00028981080598056597, 'samples': 13145664, 'steps': 68466, 'loss/train': 1.7642841339111328} 08/31/2021 01:34:58 - INFO - __main__ - Step 68468: {'lr': 0.00028980556694459215, 'samples': 13145856, 'steps': 68467, 'loss/train': 1.2575007677078247} 08/31/2021 01:34:58 - INFO - __main__ - Step 68469: {'lr': 0.00028980032789068254, 'samples': 13146048, 'steps': 68468, 'loss/train': 0.48376020789146423} 08/31/2021 01:34:58 - INFO - __main__ - Step 68470: {'lr': 0.00028979508881883946, 'samples': 13146240, 'steps': 68469, 'loss/train': 1.3816509246826172} 08/31/2021 01:34:59 - INFO - __main__ - Step 68471: {'lr': 0.0002897898497290654, 'samples': 13146432, 'steps': 68470, 'loss/train': 0.9914101958274841} 08/31/2021 01:35:00 - INFO - __main__ - Step 68472: {'lr': 0.0002897846106213626, 'samples': 13146624, 'steps': 68471, 'loss/train': 1.093134880065918} 08/31/2021 01:35:01 - INFO - __main__ - Step 68473: {'lr': 0.0002897793714957335, 'samples': 13146816, 'steps': 68472, 'loss/train': 1.324904441833496} 08/31/2021 01:35:01 - INFO - __main__ - Step 68474: {'lr': 0.0002897741323521804, 'samples': 13147008, 'steps': 68473, 'loss/train': 1.4695725440979004} 08/31/2021 01:35:01 - INFO - __main__ - Step 68475: {'lr': 0.00028976889319070573, 'samples': 13147200, 'steps': 68474, 'loss/train': 0.8261727690696716} 08/31/2021 01:35:02 - INFO - __main__ - Step 68476: {'lr': 0.0002897636540113118, 'samples': 13147392, 'steps': 68475, 'loss/train': 0.9590627551078796} 08/31/2021 01:35:03 - INFO - __main__ - Step 68477: {'lr': 0.00028975841481400095, 'samples': 13147584, 'steps': 68476, 'loss/train': 0.8801388740539551} 08/31/2021 01:35:04 - INFO - __main__ - Step 68478: {'lr': 0.0002897531755987756, 'samples': 13147776, 'steps': 68477, 'loss/train': 0.1102176085114479} 08/31/2021 01:35:04 - INFO - __main__ - Step 68479: {'lr': 0.00028974793636563805, 'samples': 13147968, 'steps': 68478, 'loss/train': 1.276466727256775} 08/31/2021 01:35:05 - INFO - __main__ - Step 68480: {'lr': 0.0002897426971145907, 'samples': 13148160, 'steps': 68479, 'loss/train': 0.6480053663253784} 08/31/2021 01:35:05 - INFO - __main__ - Step 68481: {'lr': 0.00028973745784563595, 'samples': 13148352, 'steps': 68480, 'loss/train': 1.2208694219589233} 08/31/2021 01:35:07 - INFO - __main__ - Step 68482: {'lr': 0.00028973221855877607, 'samples': 13148544, 'steps': 68481, 'loss/train': 0.9801681041717529} 08/31/2021 01:35:07 - INFO - __main__ - Step 68483: {'lr': 0.0002897269792540135, 'samples': 13148736, 'steps': 68482, 'loss/train': 1.370408296585083} 08/31/2021 01:35:07 - INFO - __main__ - Step 68484: {'lr': 0.0002897217399313505, 'samples': 13148928, 'steps': 68483, 'loss/train': 1.1680653095245361} 08/31/2021 01:35:08 - INFO - __main__ - Step 68485: {'lr': 0.00028971650059078955, 'samples': 13149120, 'steps': 68484, 'loss/train': 1.3901081085205078} 08/31/2021 01:35:08 - INFO - __main__ - Step 68486: {'lr': 0.00028971126123233297, 'samples': 13149312, 'steps': 68485, 'loss/train': 1.4677979946136475} 08/31/2021 01:35:10 - INFO - __main__ - Step 68487: {'lr': 0.0002897060218559831, 'samples': 13149504, 'steps': 68486, 'loss/train': 0.9391050338745117} 08/31/2021 01:35:10 - INFO - __main__ - Step 68488: {'lr': 0.0002897007824617423, 'samples': 13149696, 'steps': 68487, 'loss/train': 1.2993024587631226} 08/31/2021 01:35:11 - INFO - __main__ - Step 68489: {'lr': 0.000289695543049613, 'samples': 13149888, 'steps': 68488, 'loss/train': 1.016849398612976} 08/31/2021 01:35:11 - INFO - __main__ - Step 68490: {'lr': 0.0002896903036195974, 'samples': 13150080, 'steps': 68489, 'loss/train': 1.0236549377441406} 08/31/2021 01:35:11 - INFO - __main__ - Step 68491: {'lr': 0.000289685064171698, 'samples': 13150272, 'steps': 68490, 'loss/train': 1.1139311790466309} 08/31/2021 01:35:13 - INFO - __main__ - Step 68492: {'lr': 0.00028967982470591715, 'samples': 13150464, 'steps': 68491, 'loss/train': 1.1132665872573853} 08/31/2021 01:35:14 - INFO - __main__ - Step 68493: {'lr': 0.00028967458522225707, 'samples': 13150656, 'steps': 68492, 'loss/train': 1.3483343124389648} 08/31/2021 01:35:14 - INFO - __main__ - Step 68494: {'lr': 0.00028966934572072033, 'samples': 13150848, 'steps': 68493, 'loss/train': 1.4864599704742432} 08/31/2021 01:35:14 - INFO - __main__ - Step 68495: {'lr': 0.0002896641062013092, 'samples': 13151040, 'steps': 68494, 'loss/train': 1.705461859703064} 08/31/2021 01:35:15 - INFO - __main__ - Step 68496: {'lr': 0.00028965886666402606, 'samples': 13151232, 'steps': 68495, 'loss/train': 0.9830974340438843} 08/31/2021 01:35:16 - INFO - __main__ - Step 68497: {'lr': 0.0002896536271088732, 'samples': 13151424, 'steps': 68496, 'loss/train': 1.3174374103546143} 08/31/2021 01:35:17 - INFO - __main__ - Step 68498: {'lr': 0.00028964838753585306, 'samples': 13151616, 'steps': 68497, 'loss/train': 1.11794912815094} 08/31/2021 01:35:17 - INFO - __main__ - Step 68499: {'lr': 0.0002896431479449679, 'samples': 13151808, 'steps': 68498, 'loss/train': 1.0166951417922974} 08/31/2021 01:35:17 - INFO - __main__ - Step 68500: {'lr': 0.00028963790833622024, 'samples': 13152000, 'steps': 68499, 'loss/train': 1.746373176574707} 08/31/2021 01:35:18 - INFO - __main__ - Step 68501: {'lr': 0.00028963266870961227, 'samples': 13152192, 'steps': 68500, 'loss/train': 1.3806904554367065} 08/31/2021 01:35:19 - INFO - __main__ - Step 68502: {'lr': 0.00028962742906514646, 'samples': 13152384, 'steps': 68501, 'loss/train': 1.061415672302246} 08/31/2021 01:35:20 - INFO - __main__ - Step 68503: {'lr': 0.0002896221894028252, 'samples': 13152576, 'steps': 68502, 'loss/train': 1.1097540855407715} 08/31/2021 01:35:20 - INFO - __main__ - Step 68504: {'lr': 0.00028961694972265076, 'samples': 13152768, 'steps': 68503, 'loss/train': 0.6438301205635071} 08/31/2021 01:35:20 - INFO - __main__ - Step 68505: {'lr': 0.0002896117100246254, 'samples': 13152960, 'steps': 68504, 'loss/train': 1.0259705781936646} 08/31/2021 01:35:21 - INFO - __main__ - Step 68506: {'lr': 0.0002896064703087518, 'samples': 13153152, 'steps': 68505, 'loss/train': 1.097128987312317} 08/31/2021 01:35:22 - INFO - __main__ - Step 68507: {'lr': 0.000289601230575032, 'samples': 13153344, 'steps': 68506, 'loss/train': 0.5633179545402527} 08/31/2021 01:35:23 - INFO - __main__ - Step 68508: {'lr': 0.0002895959908234686, 'samples': 13153536, 'steps': 68507, 'loss/train': 0.23640340566635132} 08/31/2021 01:35:23 - INFO - __main__ - Step 68509: {'lr': 0.00028959075105406383, 'samples': 13153728, 'steps': 68508, 'loss/train': 1.2242792844772339} 08/31/2021 01:35:24 - INFO - __main__ - Step 68510: {'lr': 0.0002895855112668201, 'samples': 13153920, 'steps': 68509, 'loss/train': 1.159428596496582} 08/31/2021 01:35:24 - INFO - __main__ - Step 68511: {'lr': 0.0002895802714617397, 'samples': 13154112, 'steps': 68510, 'loss/train': 1.3752576112747192} 08/31/2021 01:35:25 - INFO - __main__ - Step 68512: {'lr': 0.00028957503163882506, 'samples': 13154304, 'steps': 68511, 'loss/train': 0.0755804032087326} 08/31/2021 01:35:26 - INFO - __main__ - Step 68513: {'lr': 0.0002895697917980785, 'samples': 13154496, 'steps': 68512, 'loss/train': 1.544188380241394} 08/31/2021 01:35:26 - INFO - __main__ - Step 68514: {'lr': 0.00028956455193950237, 'samples': 13154688, 'steps': 68513, 'loss/train': 1.6761786937713623} 08/31/2021 01:35:27 - INFO - __main__ - Step 68515: {'lr': 0.00028955931206309915, 'samples': 13154880, 'steps': 68514, 'loss/train': 1.3591787815093994} 08/31/2021 01:35:27 - INFO - __main__ - Step 68516: {'lr': 0.0002895540721688711, 'samples': 13155072, 'steps': 68515, 'loss/train': 0.5180548429489136} 08/31/2021 01:35:29 - INFO - __main__ - Step 68517: {'lr': 0.0002895488322568206, 'samples': 13155264, 'steps': 68516, 'loss/train': 1.268838882446289} 08/31/2021 01:35:29 - INFO - __main__ - Step 68518: {'lr': 0.00028954359232694993, 'samples': 13155456, 'steps': 68517, 'loss/train': 1.5834989547729492} 08/31/2021 01:35:29 - INFO - __main__ - Step 68519: {'lr': 0.00028953835237926156, 'samples': 13155648, 'steps': 68518, 'loss/train': 0.6453801393508911} 08/31/2021 01:35:30 - INFO - __main__ - Step 68520: {'lr': 0.00028953311241375785, 'samples': 13155840, 'steps': 68519, 'loss/train': 5.9328765869140625} 08/31/2021 01:35:30 - INFO - __main__ - Step 68521: {'lr': 0.0002895278724304411, 'samples': 13156032, 'steps': 68520, 'loss/train': 0.4870724678039551} 08/31/2021 01:35:30 - INFO - __main__ - Step 68522: {'lr': 0.0002895226324293137, 'samples': 13156224, 'steps': 68521, 'loss/train': 0.6047220230102539} 08/31/2021 01:35:32 - INFO - __main__ - Step 68523: {'lr': 0.0002895173924103781, 'samples': 13156416, 'steps': 68522, 'loss/train': 1.7404968738555908} 08/31/2021 01:35:32 - INFO - __main__ - Step 68524: {'lr': 0.0002895121523736365, 'samples': 13156608, 'steps': 68523, 'loss/train': 1.6585663557052612} 08/31/2021 01:35:33 - INFO - __main__ - Step 68525: {'lr': 0.00028950691231909134, 'samples': 13156800, 'steps': 68524, 'loss/train': 1.8640176057815552} 08/31/2021 01:35:33 - INFO - __main__ - Step 68526: {'lr': 0.00028950167224674493, 'samples': 13156992, 'steps': 68525, 'loss/train': 0.22669239342212677} 08/31/2021 01:35:34 - INFO - __main__ - Step 68527: {'lr': 0.0002894964321565997, 'samples': 13157184, 'steps': 68526, 'loss/train': 1.0038762092590332} 08/31/2021 01:35:34 - INFO - __main__ - Step 68528: {'lr': 0.00028949119204865797, 'samples': 13157376, 'steps': 68527, 'loss/train': 0.7953502535820007} 08/31/2021 01:35:35 - INFO - __main__ - Step 68529: {'lr': 0.00028948595192292213, 'samples': 13157568, 'steps': 68528, 'loss/train': 0.04808768257498741} 08/31/2021 01:35:36 - INFO - __main__ - Step 68530: {'lr': 0.0002894807117793946, 'samples': 13157760, 'steps': 68529, 'loss/train': 0.4691236913204193} 08/31/2021 01:35:36 - INFO - __main__ - Step 68531: {'lr': 0.00028947547161807763, 'samples': 13157952, 'steps': 68530, 'loss/train': 1.4777295589447021} 08/31/2021 01:35:37 - INFO - __main__ - Step 68532: {'lr': 0.0002894702314389736, 'samples': 13158144, 'steps': 68531, 'loss/train': 1.3817908763885498} 08/31/2021 01:35:37 - INFO - __main__ - Step 68533: {'lr': 0.0002894649912420849, 'samples': 13158336, 'steps': 68532, 'loss/train': 1.7192902565002441} 08/31/2021 01:35:39 - INFO - __main__ - Step 68534: {'lr': 0.0002894597510274139, 'samples': 13158528, 'steps': 68533, 'loss/train': 1.6250965595245361} 08/31/2021 01:35:39 - INFO - __main__ - Step 68535: {'lr': 0.00028945451079496294, 'samples': 13158720, 'steps': 68534, 'loss/train': 1.4777607917785645} 08/31/2021 01:35:39 - INFO - __main__ - Step 68536: {'lr': 0.0002894492705447344, 'samples': 13158912, 'steps': 68535, 'loss/train': 1.9049792289733887} 08/31/2021 01:35:40 - INFO - __main__ - Step 68537: {'lr': 0.0002894440302767306, 'samples': 13159104, 'steps': 68536, 'loss/train': 1.0905787944793701} 08/31/2021 01:35:40 - INFO - __main__ - Step 68538: {'lr': 0.000289438789990954, 'samples': 13159296, 'steps': 68537, 'loss/train': 0.905354917049408} 08/31/2021 01:35:42 - INFO - __main__ - Step 68539: {'lr': 0.0002894335496874068, 'samples': 13159488, 'steps': 68538, 'loss/train': 1.2867125272750854} 08/31/2021 01:35:42 - INFO - __main__ - Step 68540: {'lr': 0.00028942830936609144, 'samples': 13159680, 'steps': 68539, 'loss/train': 0.7027406692504883} 08/31/2021 01:35:42 - INFO - __main__ - Step 68541: {'lr': 0.0002894230690270103, 'samples': 13159872, 'steps': 68540, 'loss/train': 1.299781322479248} 08/31/2021 01:35:43 - INFO - __main__ - Step 68542: {'lr': 0.00028941782867016573, 'samples': 13160064, 'steps': 68541, 'loss/train': 1.3292739391326904} 08/31/2021 01:35:43 - INFO - __main__ - Step 68543: {'lr': 0.00028941258829556023, 'samples': 13160256, 'steps': 68542, 'loss/train': 1.8579784631729126} 08/31/2021 01:35:43 - INFO - __main__ - Step 68544: {'lr': 0.0002894073479031959, 'samples': 13160448, 'steps': 68543, 'loss/train': 1.7294000387191772} 08/31/2021 01:35:46 - INFO - __main__ - Step 68545: {'lr': 0.0002894021074930752, 'samples': 13160640, 'steps': 68544, 'loss/train': 1.1945985555648804} 08/31/2021 01:35:46 - INFO - __main__ - Step 68546: {'lr': 0.0002893968670652006, 'samples': 13160832, 'steps': 68545, 'loss/train': 1.0549018383026123} 08/31/2021 01:35:46 - INFO - __main__ - Step 68547: {'lr': 0.0002893916266195744, 'samples': 13161024, 'steps': 68546, 'loss/train': 0.9479683637619019} 08/31/2021 01:35:47 - INFO - __main__ - Step 68548: {'lr': 0.00028938638615619885, 'samples': 13161216, 'steps': 68547, 'loss/train': 1.6512593030929565} 08/31/2021 01:35:47 - INFO - __main__ - Step 68549: {'lr': 0.00028938114567507645, 'samples': 13161408, 'steps': 68548, 'loss/train': 0.03724685311317444} 08/31/2021 01:35:49 - INFO - __main__ - Step 68550: {'lr': 0.0002893759051762095, 'samples': 13161600, 'steps': 68549, 'loss/train': 1.1183110475540161} 08/31/2021 01:35:49 - INFO - __main__ - Step 68551: {'lr': 0.00028937066465960036, 'samples': 13161792, 'steps': 68550, 'loss/train': 1.0744577646255493} 08/31/2021 01:35:50 - INFO - __main__ - Step 68552: {'lr': 0.00028936542412525144, 'samples': 13161984, 'steps': 68551, 'loss/train': 1.3711692094802856} 08/31/2021 01:35:50 - INFO - __main__ - Step 68553: {'lr': 0.0002893601835731651, 'samples': 13162176, 'steps': 68552, 'loss/train': 1.7328236103057861} 08/31/2021 01:35:50 - INFO - __main__ - Step 68554: {'lr': 0.0002893549430033435, 'samples': 13162368, 'steps': 68553, 'loss/train': 0.4491300582885742} 08/31/2021 01:35:52 - INFO - __main__ - Step 68555: {'lr': 0.0002893497024157894, 'samples': 13162560, 'steps': 68554, 'loss/train': 1.7429341077804565} 08/31/2021 01:35:52 - INFO - __main__ - Step 68556: {'lr': 0.0002893444618105048, 'samples': 13162752, 'steps': 68555, 'loss/train': 1.098934531211853} 08/31/2021 01:35:52 - INFO - __main__ - Step 68557: {'lr': 0.0002893392211874922, 'samples': 13162944, 'steps': 68556, 'loss/train': 1.8352575302124023} 08/31/2021 01:35:53 - INFO - __main__ - Step 68558: {'lr': 0.000289333980546754, 'samples': 13163136, 'steps': 68557, 'loss/train': 1.519819974899292} 08/31/2021 01:35:53 - INFO - __main__ - Step 68559: {'lr': 0.00028932873988829244, 'samples': 13163328, 'steps': 68558, 'loss/train': 0.810289740562439} 08/31/2021 01:35:55 - INFO - __main__ - Step 68560: {'lr': 0.00028932349921211004, 'samples': 13163520, 'steps': 68559, 'loss/train': 1.1496750116348267} 08/31/2021 01:35:55 - INFO - __main__ - Step 68561: {'lr': 0.000289318258518209, 'samples': 13163712, 'steps': 68560, 'loss/train': 0.6700031757354736} 08/31/2021 01:35:55 - INFO - __main__ - Step 68562: {'lr': 0.00028931301780659184, 'samples': 13163904, 'steps': 68561, 'loss/train': 0.7835355401039124} 08/31/2021 01:35:56 - INFO - __main__ - Step 68563: {'lr': 0.0002893077770772608, 'samples': 13164096, 'steps': 68562, 'loss/train': 1.2777351140975952} 08/31/2021 01:35:56 - INFO - __main__ - Step 68564: {'lr': 0.00028930253633021826, 'samples': 13164288, 'steps': 68563, 'loss/train': 1.608851671218872} 08/31/2021 01:35:58 - INFO - __main__ - Step 68565: {'lr': 0.0002892972955654666, 'samples': 13164480, 'steps': 68564, 'loss/train': 1.2146228551864624} 08/31/2021 01:35:58 - INFO - __main__ - Step 68566: {'lr': 0.0002892920547830083, 'samples': 13164672, 'steps': 68565, 'loss/train': 1.2768175601959229} 08/31/2021 01:35:58 - INFO - __main__ - Step 68567: {'lr': 0.0002892868139828455, 'samples': 13164864, 'steps': 68566, 'loss/train': 1.2686069011688232} 08/31/2021 01:35:59 - INFO - __main__ - Step 68568: {'lr': 0.00028928157316498066, 'samples': 13165056, 'steps': 68567, 'loss/train': 1.283945918083191} 08/31/2021 01:35:59 - INFO - __main__ - Step 68569: {'lr': 0.0002892763323294162, 'samples': 13165248, 'steps': 68568, 'loss/train': 1.3713957071304321} 08/31/2021 01:36:01 - INFO - __main__ - Step 68570: {'lr': 0.00028927109147615436, 'samples': 13165440, 'steps': 68569, 'loss/train': 1.4678629636764526} 08/31/2021 01:36:01 - INFO - __main__ - Step 68571: {'lr': 0.0002892658506051977, 'samples': 13165632, 'steps': 68570, 'loss/train': 1.23796546459198} 08/31/2021 01:36:02 - INFO - __main__ - Step 68572: {'lr': 0.0002892606097165483, 'samples': 13165824, 'steps': 68571, 'loss/train': 1.3515568971633911} 08/31/2021 01:36:02 - INFO - __main__ - Step 68573: {'lr': 0.00028925536881020875, 'samples': 13166016, 'steps': 68572, 'loss/train': 1.4123724699020386} 08/31/2021 01:36:02 - INFO - __main__ - Step 68574: {'lr': 0.0002892501278861813, 'samples': 13166208, 'steps': 68573, 'loss/train': 1.1851919889450073} 08/31/2021 01:36:03 - INFO - __main__ - Step 68575: {'lr': 0.0002892448869444684, 'samples': 13166400, 'steps': 68574, 'loss/train': 0.6014587879180908} 08/31/2021 01:36:04 - INFO - __main__ - Step 68576: {'lr': 0.00028923964598507235, 'samples': 13166592, 'steps': 68575, 'loss/train': 0.6939263343811035} 08/31/2021 01:36:05 - INFO - __main__ - Step 68577: {'lr': 0.0002892344050079956, 'samples': 13166784, 'steps': 68576, 'loss/train': 1.670469045639038} 08/31/2021 01:36:05 - INFO - __main__ - Step 68578: {'lr': 0.0002892291640132403, 'samples': 13166976, 'steps': 68577, 'loss/train': 0.8150118589401245} 08/31/2021 01:36:05 - INFO - __main__ - Step 68579: {'lr': 0.00028922392300080894, 'samples': 13167168, 'steps': 68578, 'loss/train': 1.9959425926208496} 08/31/2021 01:36:06 - INFO - __main__ - Step 68580: {'lr': 0.00028921868197070397, 'samples': 13167360, 'steps': 68579, 'loss/train': 0.6616799831390381} 08/31/2021 01:36:07 - INFO - __main__ - Step 68581: {'lr': 0.00028921344092292764, 'samples': 13167552, 'steps': 68580, 'loss/train': 1.6362931728363037} 08/31/2021 01:36:07 - INFO - __main__ - Step 68582: {'lr': 0.0002892081998574823, 'samples': 13167744, 'steps': 68581, 'loss/train': 1.6161694526672363} 08/31/2021 01:36:08 - INFO - __main__ - Step 68583: {'lr': 0.0002892029587743704, 'samples': 13167936, 'steps': 68582, 'loss/train': 0.875567615032196} 08/31/2021 01:36:08 - INFO - __main__ - Step 68584: {'lr': 0.00028919771767359426, 'samples': 13168128, 'steps': 68583, 'loss/train': 2.9078264236450195} 08/31/2021 01:36:09 - INFO - __main__ - Step 68585: {'lr': 0.0002891924765551562, 'samples': 13168320, 'steps': 68584, 'loss/train': 0.3222227394580841} 08/31/2021 01:36:10 - INFO - __main__ - Step 68586: {'lr': 0.0002891872354190586, 'samples': 13168512, 'steps': 68585, 'loss/train': 1.208561658859253} 08/31/2021 01:36:10 - INFO - __main__ - Step 68587: {'lr': 0.00028918199426530383, 'samples': 13168704, 'steps': 68586, 'loss/train': 1.5555137395858765} 08/31/2021 01:36:11 - INFO - __main__ - Step 68588: {'lr': 0.0002891767530938943, 'samples': 13168896, 'steps': 68587, 'loss/train': 0.7514135241508484} 08/31/2021 01:36:11 - INFO - __main__ - Step 68589: {'lr': 0.0002891715119048323, 'samples': 13169088, 'steps': 68588, 'loss/train': 0.20536218583583832} 08/31/2021 01:36:11 - INFO - __main__ - Step 68590: {'lr': 0.00028916627069812027, 'samples': 13169280, 'steps': 68589, 'loss/train': 1.232387900352478} 08/31/2021 01:36:13 - INFO - __main__ - Step 68591: {'lr': 0.0002891610294737605, 'samples': 13169472, 'steps': 68590, 'loss/train': 1.362808346748352} 08/31/2021 01:36:14 - INFO - __main__ - Step 68592: {'lr': 0.0002891557882317553, 'samples': 13169664, 'steps': 68591, 'loss/train': 1.2701321840286255} 08/31/2021 01:36:14 - INFO - __main__ - Step 68593: {'lr': 0.0002891505469721072, 'samples': 13169856, 'steps': 68592, 'loss/train': 1.4231359958648682} 08/31/2021 01:36:14 - INFO - __main__ - Step 68594: {'lr': 0.00028914530569481845, 'samples': 13170048, 'steps': 68593, 'loss/train': 1.6203311681747437} 08/31/2021 01:36:15 - INFO - __main__ - Step 68595: {'lr': 0.00028914006439989136, 'samples': 13170240, 'steps': 68594, 'loss/train': 1.2981337308883667} 08/31/2021 01:36:17 - INFO - __main__ - Step 68596: {'lr': 0.0002891348230873284, 'samples': 13170432, 'steps': 68595, 'loss/train': 0.9267703294754028} 08/31/2021 01:36:17 - INFO - __main__ - Step 68597: {'lr': 0.000289129581757132, 'samples': 13170624, 'steps': 68596, 'loss/train': 0.6053143739700317} 08/31/2021 01:36:18 - INFO - __main__ - Step 68598: {'lr': 0.0002891243404093043, 'samples': 13170816, 'steps': 68597, 'loss/train': 1.2357749938964844} 08/31/2021 01:36:18 - INFO - __main__ - Step 68599: {'lr': 0.0002891190990438478, 'samples': 13171008, 'steps': 68598, 'loss/train': 0.9517439007759094} 08/31/2021 01:36:18 - INFO - __main__ - Step 68600: {'lr': 0.0002891138576607648, 'samples': 13171200, 'steps': 68599, 'loss/train': 1.6830321550369263} 08/31/2021 01:36:20 - INFO - __main__ - Step 68601: {'lr': 0.00028910861626005774, 'samples': 13171392, 'steps': 68600, 'loss/train': 1.7122559547424316} 08/31/2021 01:36:20 - INFO - __main__ - Step 68602: {'lr': 0.0002891033748417289, 'samples': 13171584, 'steps': 68601, 'loss/train': 1.0764527320861816} 08/31/2021 01:36:21 - INFO - __main__ - Step 68603: {'lr': 0.00028909813340578073, 'samples': 13171776, 'steps': 68602, 'loss/train': 1.6102768182754517} 08/31/2021 01:36:21 - INFO - __main__ - Step 68604: {'lr': 0.0002890928919522156, 'samples': 13171968, 'steps': 68603, 'loss/train': 1.493375301361084} 08/31/2021 01:36:21 - INFO - __main__ - Step 68605: {'lr': 0.0002890876504810357, 'samples': 13172160, 'steps': 68604, 'loss/train': 1.3229812383651733} 08/31/2021 01:36:22 - INFO - __main__ - Step 68606: {'lr': 0.0002890824089922436, 'samples': 13172352, 'steps': 68605, 'loss/train': 0.3858312964439392} 08/31/2021 01:36:23 - INFO - __main__ - Step 68607: {'lr': 0.0002890771674858415, 'samples': 13172544, 'steps': 68606, 'loss/train': 1.3201992511749268} 08/31/2021 01:36:24 - INFO - __main__ - Step 68608: {'lr': 0.00028907192596183185, 'samples': 13172736, 'steps': 68607, 'loss/train': 1.701823115348816} 08/31/2021 01:36:24 - INFO - __main__ - Step 68609: {'lr': 0.000289066684420217, 'samples': 13172928, 'steps': 68608, 'loss/train': 1.1608041524887085} 08/31/2021 01:36:24 - INFO - __main__ - Step 68610: {'lr': 0.00028906144286099935, 'samples': 13173120, 'steps': 68609, 'loss/train': 1.6116472482681274} 08/31/2021 01:36:25 - INFO - __main__ - Step 68611: {'lr': 0.00028905620128418115, 'samples': 13173312, 'steps': 68610, 'loss/train': 0.9433948397636414} 08/31/2021 01:36:27 - INFO - __main__ - Step 68612: {'lr': 0.00028905095968976484, 'samples': 13173504, 'steps': 68611, 'loss/train': 0.8499065637588501} 08/31/2021 01:36:27 - INFO - __main__ - Step 68613: {'lr': 0.0002890457180777528, 'samples': 13173696, 'steps': 68612, 'loss/train': 0.6608076691627502} 08/31/2021 01:36:27 - INFO - __main__ - Step 68614: {'lr': 0.0002890404764481473, 'samples': 13173888, 'steps': 68613, 'loss/train': 1.1729224920272827} 08/31/2021 01:36:28 - INFO - __main__ - Step 68615: {'lr': 0.00028903523480095086, 'samples': 13174080, 'steps': 68614, 'loss/train': 1.19910728931427} 08/31/2021 01:36:28 - INFO - __main__ - Step 68616: {'lr': 0.00028902999313616565, 'samples': 13174272, 'steps': 68615, 'loss/train': 1.0465219020843506} 08/31/2021 01:36:30 - INFO - __main__ - Step 68617: {'lr': 0.0002890247514537942, 'samples': 13174464, 'steps': 68616, 'loss/train': 1.4126956462860107} 08/31/2021 01:36:30 - INFO - __main__ - Step 68618: {'lr': 0.0002890195097538388, 'samples': 13174656, 'steps': 68617, 'loss/train': 1.101697564125061} 08/31/2021 01:36:30 - INFO - __main__ - Step 68619: {'lr': 0.0002890142680363017, 'samples': 13174848, 'steps': 68618, 'loss/train': 1.4561245441436768} 08/31/2021 01:36:31 - INFO - __main__ - Step 68620: {'lr': 0.00028900902630118547, 'samples': 13175040, 'steps': 68619, 'loss/train': 0.9180858731269836} 08/31/2021 01:36:31 - INFO - __main__ - Step 68621: {'lr': 0.00028900378454849233, 'samples': 13175232, 'steps': 68620, 'loss/train': 0.9119496941566467} 08/31/2021 01:36:31 - INFO - __main__ - Step 68622: {'lr': 0.00028899854277822476, 'samples': 13175424, 'steps': 68621, 'loss/train': 1.0998440980911255} 08/31/2021 01:36:33 - INFO - __main__ - Step 68623: {'lr': 0.00028899330099038494, 'samples': 13175616, 'steps': 68622, 'loss/train': 1.1582527160644531} 08/31/2021 01:36:33 - INFO - __main__ - Step 68624: {'lr': 0.0002889880591849755, 'samples': 13175808, 'steps': 68623, 'loss/train': 0.9914218187332153} 08/31/2021 01:36:34 - INFO - __main__ - Step 68625: {'lr': 0.00028898281736199847, 'samples': 13176000, 'steps': 68624, 'loss/train': 0.932897686958313} 08/31/2021 01:36:34 - INFO - __main__ - Step 68626: {'lr': 0.0002889775755214565, 'samples': 13176192, 'steps': 68625, 'loss/train': 0.8917565941810608} 08/31/2021 01:36:34 - INFO - __main__ - Step 68627: {'lr': 0.0002889723336633518, 'samples': 13176384, 'steps': 68626, 'loss/train': 1.2156856060028076} 08/31/2021 01:36:36 - INFO - __main__ - Step 68628: {'lr': 0.00028896709178768677, 'samples': 13176576, 'steps': 68627, 'loss/train': 1.019052505493164} 08/31/2021 01:36:36 - INFO - __main__ - Step 68629: {'lr': 0.00028896184989446374, 'samples': 13176768, 'steps': 68628, 'loss/train': 1.2827280759811401} 08/31/2021 01:36:37 - INFO - __main__ - Step 68630: {'lr': 0.0002889566079836852, 'samples': 13176960, 'steps': 68629, 'loss/train': 1.3103746175765991} 08/31/2021 01:36:37 - INFO - __main__ - Step 68631: {'lr': 0.00028895136605535326, 'samples': 13177152, 'steps': 68630, 'loss/train': 1.3029487133026123} 08/31/2021 01:36:38 - INFO - __main__ - Step 68632: {'lr': 0.0002889461241094705, 'samples': 13177344, 'steps': 68631, 'loss/train': 1.3916280269622803} 08/31/2021 01:36:39 - INFO - __main__ - Step 68633: {'lr': 0.0002889408821460393, 'samples': 13177536, 'steps': 68632, 'loss/train': 1.7174017429351807} 08/31/2021 01:36:40 - INFO - __main__ - Step 68634: {'lr': 0.0002889356401650618, 'samples': 13177728, 'steps': 68633, 'loss/train': 1.4392975568771362} 08/31/2021 01:36:40 - INFO - __main__ - Step 68635: {'lr': 0.0002889303981665406, 'samples': 13177920, 'steps': 68634, 'loss/train': 1.4520752429962158} 08/31/2021 01:36:40 - INFO - __main__ - Step 68636: {'lr': 0.0002889251561504779, 'samples': 13178112, 'steps': 68635, 'loss/train': 0.8220979571342468} 08/31/2021 01:36:41 - INFO - __main__ - Step 68637: {'lr': 0.0002889199141168762, 'samples': 13178304, 'steps': 68636, 'loss/train': 1.0571506023406982} 08/31/2021 01:36:42 - INFO - __main__ - Step 68638: {'lr': 0.00028891467206573773, 'samples': 13178496, 'steps': 68637, 'loss/train': 0.9349420666694641} 08/31/2021 01:36:43 - INFO - __main__ - Step 68639: {'lr': 0.0002889094299970649, 'samples': 13178688, 'steps': 68638, 'loss/train': 1.5438815355300903} 08/31/2021 01:36:43 - INFO - __main__ - Step 68640: {'lr': 0.00028890418791086014, 'samples': 13178880, 'steps': 68639, 'loss/train': 1.0664368867874146} 08/31/2021 01:36:43 - INFO - __main__ - Step 68641: {'lr': 0.0002888989458071257, 'samples': 13179072, 'steps': 68640, 'loss/train': 1.3353466987609863} 08/31/2021 01:36:44 - INFO - __main__ - Step 68642: {'lr': 0.000288893703685864, 'samples': 13179264, 'steps': 68641, 'loss/train': 1.6071381568908691} 08/31/2021 01:36:45 - INFO - __main__ - Step 68643: {'lr': 0.0002888884615470774, 'samples': 13179456, 'steps': 68642, 'loss/train': 0.9557133913040161} 08/31/2021 01:36:46 - INFO - __main__ - Step 68644: {'lr': 0.00028888321939076833, 'samples': 13179648, 'steps': 68643, 'loss/train': 0.9600305557250977} 08/31/2021 01:36:46 - INFO - __main__ - Step 68645: {'lr': 0.00028887797721693903, 'samples': 13179840, 'steps': 68644, 'loss/train': 1.4337778091430664} 08/31/2021 01:36:46 - INFO - __main__ - Step 68646: {'lr': 0.0002888727350255919, 'samples': 13180032, 'steps': 68645, 'loss/train': 0.41455134749412537} 08/31/2021 01:36:47 - INFO - __main__ - Step 68647: {'lr': 0.0002888674928167293, 'samples': 13180224, 'steps': 68646, 'loss/train': 0.9495470523834229} 08/31/2021 01:36:48 - INFO - __main__ - Step 68648: {'lr': 0.00028886225059035367, 'samples': 13180416, 'steps': 68647, 'loss/train': 0.7081342935562134} 08/31/2021 01:36:49 - INFO - __main__ - Step 68649: {'lr': 0.00028885700834646724, 'samples': 13180608, 'steps': 68648, 'loss/train': 1.1558631658554077} 08/31/2021 01:36:49 - INFO - __main__ - Step 68650: {'lr': 0.00028885176608507246, 'samples': 13180800, 'steps': 68649, 'loss/train': 1.6523295640945435} 08/31/2021 01:36:49 - INFO - __main__ - Step 68651: {'lr': 0.0002888465238061717, 'samples': 13180992, 'steps': 68650, 'loss/train': 1.0796550512313843} 08/31/2021 01:36:50 - INFO - __main__ - Step 68652: {'lr': 0.0002888412815097673, 'samples': 13181184, 'steps': 68651, 'loss/train': 1.2942936420440674} 08/31/2021 01:36:52 - INFO - __main__ - Step 68653: {'lr': 0.0002888360391958616, 'samples': 13181376, 'steps': 68652, 'loss/train': 1.2514047622680664} 08/31/2021 01:36:52 - INFO - __main__ - Step 68654: {'lr': 0.00028883079686445697, 'samples': 13181568, 'steps': 68653, 'loss/train': 1.2569414377212524} 08/31/2021 01:36:53 - INFO - __main__ - Step 68655: {'lr': 0.00028882555451555575, 'samples': 13181760, 'steps': 68654, 'loss/train': 1.496193528175354} 08/31/2021 01:36:53 - INFO - __main__ - Step 68656: {'lr': 0.0002888203121491604, 'samples': 13181952, 'steps': 68655, 'loss/train': 0.5768393278121948} 08/31/2021 01:36:53 - INFO - __main__ - Step 68657: {'lr': 0.0002888150697652732, 'samples': 13182144, 'steps': 68656, 'loss/train': 1.6650456190109253} 08/31/2021 01:36:54 - INFO - __main__ - Step 68658: {'lr': 0.00028880982736389653, 'samples': 13182336, 'steps': 68657, 'loss/train': 1.7334729433059692} 08/31/2021 01:36:55 - INFO - __main__ - Step 68659: {'lr': 0.00028880458494503277, 'samples': 13182528, 'steps': 68658, 'loss/train': 0.8054826855659485} 08/31/2021 01:36:56 - INFO - __main__ - Step 68660: {'lr': 0.0002887993425086842, 'samples': 13182720, 'steps': 68659, 'loss/train': 0.45647215843200684} 08/31/2021 01:36:56 - INFO - __main__ - Step 68661: {'lr': 0.0002887941000548533, 'samples': 13182912, 'steps': 68660, 'loss/train': 1.3899916410446167} 08/31/2021 01:36:56 - INFO - __main__ - Step 68662: {'lr': 0.0002887888575835423, 'samples': 13183104, 'steps': 68661, 'loss/train': 1.2508162260055542} 08/31/2021 01:36:57 - INFO - __main__ - Step 68663: {'lr': 0.0002887836150947537, 'samples': 13183296, 'steps': 68662, 'loss/train': 1.4959378242492676} 08/31/2021 01:36:58 - INFO - __main__ - Step 68664: {'lr': 0.0002887783725884898, 'samples': 13183488, 'steps': 68663, 'loss/train': 1.2988098859786987} 08/31/2021 01:36:58 - INFO - __main__ - Step 68665: {'lr': 0.000288773130064753, 'samples': 13183680, 'steps': 68664, 'loss/train': 1.606726884841919} 08/31/2021 01:36:59 - INFO - __main__ - Step 68666: {'lr': 0.00028876788752354554, 'samples': 13183872, 'steps': 68665, 'loss/train': 1.2830442190170288} 08/31/2021 01:36:59 - INFO - __main__ - Step 68667: {'lr': 0.00028876264496486995, 'samples': 13184064, 'steps': 68666, 'loss/train': 0.7760048508644104} 08/31/2021 01:37:00 - INFO - __main__ - Step 68668: {'lr': 0.00028875740238872846, 'samples': 13184256, 'steps': 68667, 'loss/train': 1.3503775596618652} 08/31/2021 01:37:01 - INFO - __main__ - Step 68669: {'lr': 0.0002887521597951235, 'samples': 13184448, 'steps': 68668, 'loss/train': 1.4039565324783325} 08/31/2021 01:37:01 - INFO - __main__ - Step 68670: {'lr': 0.00028874691718405737, 'samples': 13184640, 'steps': 68669, 'loss/train': 0.9518436193466187} 08/31/2021 01:37:02 - INFO - __main__ - Step 68671: {'lr': 0.0002887416745555326, 'samples': 13184832, 'steps': 68670, 'loss/train': 0.9806452989578247} 08/31/2021 01:37:02 - INFO - __main__ - Step 68672: {'lr': 0.00028873643190955136, 'samples': 13185024, 'steps': 68671, 'loss/train': 1.0292503833770752} 08/31/2021 01:37:02 - INFO - __main__ - Step 68673: {'lr': 0.00028873118924611604, 'samples': 13185216, 'steps': 68672, 'loss/train': 1.130771517753601} 08/31/2021 01:37:04 - INFO - __main__ - Step 68674: {'lr': 0.00028872594656522907, 'samples': 13185408, 'steps': 68673, 'loss/train': 1.036687970161438} 08/31/2021 01:37:04 - INFO - __main__ - Step 68675: {'lr': 0.00028872070386689274, 'samples': 13185600, 'steps': 68674, 'loss/train': 1.2849476337432861} 08/31/2021 01:37:05 - INFO - __main__ - Step 68676: {'lr': 0.00028871546115110953, 'samples': 13185792, 'steps': 68675, 'loss/train': 1.5107734203338623} 08/31/2021 01:37:05 - INFO - __main__ - Step 68677: {'lr': 0.00028871021841788173, 'samples': 13185984, 'steps': 68676, 'loss/train': 1.796207308769226} 08/31/2021 01:37:05 - INFO - __main__ - Step 68678: {'lr': 0.0002887049756672117, 'samples': 13186176, 'steps': 68677, 'loss/train': 1.9434820413589478} 08/31/2021 01:37:06 - INFO - __main__ - Step 68679: {'lr': 0.00028869973289910177, 'samples': 13186368, 'steps': 68678, 'loss/train': 1.4167503118515015} 08/31/2021 01:37:07 - INFO - __main__ - Step 68680: {'lr': 0.0002886944901135544, 'samples': 13186560, 'steps': 68679, 'loss/train': 1.6509312391281128} 08/31/2021 01:37:08 - INFO - __main__ - Step 68681: {'lr': 0.0002886892473105718, 'samples': 13186752, 'steps': 68680, 'loss/train': 3.0879175662994385} 08/31/2021 01:37:08 - INFO - __main__ - Step 68682: {'lr': 0.0002886840044901564, 'samples': 13186944, 'steps': 68681, 'loss/train': 1.4527822732925415} 08/31/2021 01:37:08 - INFO - __main__ - Step 68683: {'lr': 0.00028867876165231067, 'samples': 13187136, 'steps': 68682, 'loss/train': 1.1277109384536743} 08/31/2021 01:37:09 - INFO - __main__ - Step 68684: {'lr': 0.00028867351879703694, 'samples': 13187328, 'steps': 68683, 'loss/train': 1.381513237953186} 08/31/2021 01:37:10 - INFO - __main__ - Step 68685: {'lr': 0.0002886682759243374, 'samples': 13187520, 'steps': 68684, 'loss/train': 1.071233868598938} 08/31/2021 01:37:11 - INFO - __main__ - Step 68686: {'lr': 0.0002886630330342146, 'samples': 13187712, 'steps': 68685, 'loss/train': 0.6625286340713501} 08/31/2021 01:37:11 - INFO - __main__ - Step 68687: {'lr': 0.0002886577901266708, 'samples': 13187904, 'steps': 68686, 'loss/train': 1.4043540954589844} 08/31/2021 01:37:12 - INFO - __main__ - Step 68688: {'lr': 0.0002886525472017084, 'samples': 13188096, 'steps': 68687, 'loss/train': 1.2916172742843628} 08/31/2021 01:37:12 - INFO - __main__ - Step 68689: {'lr': 0.0002886473042593298, 'samples': 13188288, 'steps': 68688, 'loss/train': 1.0117497444152832} 08/31/2021 01:37:13 - INFO - __main__ - Step 68690: {'lr': 0.0002886420612995373, 'samples': 13188480, 'steps': 68689, 'loss/train': 1.2443944215774536} 08/31/2021 01:37:14 - INFO - __main__ - Step 68691: {'lr': 0.00028863681832233323, 'samples': 13188672, 'steps': 68690, 'loss/train': 1.8036632537841797} 08/31/2021 01:37:14 - INFO - __main__ - Step 68692: {'lr': 0.00028863157532772006, 'samples': 13188864, 'steps': 68691, 'loss/train': 1.417612075805664} 08/31/2021 01:37:15 - INFO - __main__ - Step 68693: {'lr': 0.00028862633231570013, 'samples': 13189056, 'steps': 68692, 'loss/train': 0.47602060437202454} 08/31/2021 01:37:15 - INFO - __main__ - Step 68694: {'lr': 0.0002886210892862757, 'samples': 13189248, 'steps': 68693, 'loss/train': 1.6627651453018188} 08/31/2021 01:37:15 - INFO - __main__ - Step 68695: {'lr': 0.00028861584623944927, 'samples': 13189440, 'steps': 68694, 'loss/train': 1.4780831336975098} 08/31/2021 01:37:17 - INFO - __main__ - Step 68696: {'lr': 0.0002886106031752231, 'samples': 13189632, 'steps': 68695, 'loss/train': 1.432620882987976} 08/31/2021 01:37:17 - INFO - __main__ - Step 68697: {'lr': 0.00028860536009359957, 'samples': 13189824, 'steps': 68696, 'loss/train': 1.1195505857467651} 08/31/2021 01:37:18 - INFO - __main__ - Step 68698: {'lr': 0.00028860011699458104, 'samples': 13190016, 'steps': 68697, 'loss/train': 0.6138575673103333} 08/31/2021 01:37:18 - INFO - __main__ - Step 68699: {'lr': 0.0002885948738781699, 'samples': 13190208, 'steps': 68698, 'loss/train': 1.5212353467941284} 08/31/2021 01:37:18 - INFO - __main__ - Step 68700: {'lr': 0.00028858963074436864, 'samples': 13190400, 'steps': 68699, 'loss/train': 1.421234130859375} 08/31/2021 01:37:20 - INFO - __main__ - Step 68701: {'lr': 0.0002885843875931793, 'samples': 13190592, 'steps': 68700, 'loss/train': 1.6859781742095947} 08/31/2021 01:37:20 - INFO - __main__ - Step 68702: {'lr': 0.0002885791444246045, 'samples': 13190784, 'steps': 68701, 'loss/train': 1.2929565906524658} 08/31/2021 01:37:21 - INFO - __main__ - Step 68703: {'lr': 0.00028857390123864657, 'samples': 13190976, 'steps': 68702, 'loss/train': 1.0797613859176636} 08/31/2021 01:37:21 - INFO - __main__ - Step 68704: {'lr': 0.0002885686580353078, 'samples': 13191168, 'steps': 68703, 'loss/train': 0.9142427444458008} 08/31/2021 01:37:21 - INFO - __main__ - Step 68705: {'lr': 0.00028856341481459064, 'samples': 13191360, 'steps': 68704, 'loss/train': 1.4602301120758057} 08/31/2021 01:37:24 - INFO - __main__ - Step 68706: {'lr': 0.0002885581715764973, 'samples': 13191552, 'steps': 68705, 'loss/train': 1.148637294769287} 08/31/2021 01:37:24 - INFO - __main__ - Step 68707: {'lr': 0.00028855292832103037, 'samples': 13191744, 'steps': 68706, 'loss/train': 1.4986891746520996} 08/31/2021 01:37:24 - INFO - __main__ - Step 68708: {'lr': 0.00028854768504819195, 'samples': 13191936, 'steps': 68707, 'loss/train': 0.05904309079051018} 08/31/2021 01:37:25 - INFO - __main__ - Step 68709: {'lr': 0.0002885424417579846, 'samples': 13192128, 'steps': 68708, 'loss/train': 0.9312520027160645} 08/31/2021 01:37:25 - INFO - __main__ - Step 68710: {'lr': 0.0002885371984504107, 'samples': 13192320, 'steps': 68709, 'loss/train': 1.4101148843765259} 08/31/2021 01:37:26 - INFO - __main__ - Step 68711: {'lr': 0.0002885319551254725, 'samples': 13192512, 'steps': 68710, 'loss/train': 1.1761395931243896} 08/31/2021 01:37:27 - INFO - __main__ - Step 68712: {'lr': 0.00028852671178317233, 'samples': 13192704, 'steps': 68711, 'loss/train': 0.830775797367096} 08/31/2021 01:37:27 - INFO - __main__ - Step 68713: {'lr': 0.00028852146842351257, 'samples': 13192896, 'steps': 68712, 'loss/train': 1.4087084531784058} 08/31/2021 01:37:28 - INFO - __main__ - Step 68714: {'lr': 0.0002885162250464957, 'samples': 13193088, 'steps': 68713, 'loss/train': 1.4181432723999023} 08/31/2021 01:37:28 - INFO - __main__ - Step 68715: {'lr': 0.000288510981652124, 'samples': 13193280, 'steps': 68714, 'loss/train': 1.2033060789108276} 08/31/2021 01:37:28 - INFO - __main__ - Step 68716: {'lr': 0.0002885057382403999, 'samples': 13193472, 'steps': 68715, 'loss/train': 0.4494099020957947} 08/31/2021 01:37:30 - INFO - __main__ - Step 68717: {'lr': 0.0002885004948113256, 'samples': 13193664, 'steps': 68716, 'loss/train': 1.1140363216400146} 08/31/2021 01:37:30 - INFO - __main__ - Step 68718: {'lr': 0.0002884952513649037, 'samples': 13193856, 'steps': 68717, 'loss/train': 1.15998113155365} 08/31/2021 01:37:31 - INFO - __main__ - Step 68719: {'lr': 0.00028849000790113637, 'samples': 13194048, 'steps': 68718, 'loss/train': 1.2568553686141968} 08/31/2021 01:37:31 - INFO - __main__ - Step 68720: {'lr': 0.000288484764420026, 'samples': 13194240, 'steps': 68719, 'loss/train': 1.3725802898406982} 08/31/2021 01:37:31 - INFO - __main__ - Step 68721: {'lr': 0.0002884795209215751, 'samples': 13194432, 'steps': 68720, 'loss/train': 0.9090165495872498} 08/31/2021 01:37:33 - INFO - __main__ - Step 68722: {'lr': 0.0002884742774057858, 'samples': 13194624, 'steps': 68721, 'loss/train': 1.6173397302627563} 08/31/2021 01:37:34 - INFO - __main__ - Step 68723: {'lr': 0.00028846903387266066, 'samples': 13194816, 'steps': 68722, 'loss/train': 1.0238624811172485} 08/31/2021 01:37:34 - INFO - __main__ - Step 68724: {'lr': 0.0002884637903222019, 'samples': 13195008, 'steps': 68723, 'loss/train': 0.8503173589706421} 08/31/2021 01:37:34 - INFO - __main__ - Step 68725: {'lr': 0.0002884585467544121, 'samples': 13195200, 'steps': 68724, 'loss/train': 1.1104426383972168} 08/31/2021 01:37:35 - INFO - __main__ - Step 68726: {'lr': 0.0002884533031692933, 'samples': 13195392, 'steps': 68725, 'loss/train': 0.291232168674469} 08/31/2021 01:37:35 - INFO - __main__ - Step 68727: {'lr': 0.0002884480595668481, 'samples': 13195584, 'steps': 68726, 'loss/train': 0.5064166784286499} 08/31/2021 01:37:37 - INFO - __main__ - Step 68728: {'lr': 0.00028844281594707876, 'samples': 13195776, 'steps': 68727, 'loss/train': 0.9244897365570068} 08/31/2021 01:37:37 - INFO - __main__ - Step 68729: {'lr': 0.00028843757230998776, 'samples': 13195968, 'steps': 68728, 'loss/train': 1.1848481893539429} 08/31/2021 01:37:38 - INFO - __main__ - Step 68730: {'lr': 0.00028843232865557734, 'samples': 13196160, 'steps': 68729, 'loss/train': 1.7168124914169312} 08/31/2021 01:37:38 - INFO - __main__ - Step 68731: {'lr': 0.00028842708498384994, 'samples': 13196352, 'steps': 68730, 'loss/train': 0.8599862456321716} 08/31/2021 01:37:38 - INFO - __main__ - Step 68732: {'lr': 0.0002884218412948078, 'samples': 13196544, 'steps': 68731, 'loss/train': 1.1718705892562866} 08/31/2021 01:37:40 - INFO - __main__ - Step 68733: {'lr': 0.00028841659758845344, 'samples': 13196736, 'steps': 68732, 'loss/train': 0.8571202158927917} 08/31/2021 01:37:40 - INFO - __main__ - Step 68734: {'lr': 0.0002884113538647891, 'samples': 13196928, 'steps': 68733, 'loss/train': 0.8002461194992065} 08/31/2021 01:37:41 - INFO - __main__ - Step 68735: {'lr': 0.0002884061101238173, 'samples': 13197120, 'steps': 68734, 'loss/train': 0.5506974458694458} 08/31/2021 01:37:41 - INFO - __main__ - Step 68736: {'lr': 0.0002884008663655402, 'samples': 13197312, 'steps': 68735, 'loss/train': 0.6199313998222351} 08/31/2021 01:37:41 - INFO - __main__ - Step 68737: {'lr': 0.00028839562258996026, 'samples': 13197504, 'steps': 68736, 'loss/train': 1.2758994102478027} 08/31/2021 01:37:43 - INFO - __main__ - Step 68738: {'lr': 0.00028839037879708, 'samples': 13197696, 'steps': 68737, 'loss/train': 1.643169641494751} 08/31/2021 01:37:43 - INFO - __main__ - Step 68739: {'lr': 0.00028838513498690143, 'samples': 13197888, 'steps': 68738, 'loss/train': 0.76316237449646} 08/31/2021 01:37:44 - INFO - __main__ - Step 68740: {'lr': 0.0002883798911594272, 'samples': 13198080, 'steps': 68739, 'loss/train': 0.924549400806427} 08/31/2021 01:37:44 - INFO - __main__ - Step 68741: {'lr': 0.00028837464731465954, 'samples': 13198272, 'steps': 68740, 'loss/train': 1.440084457397461} 08/31/2021 01:37:44 - INFO - __main__ - Step 68742: {'lr': 0.00028836940345260093, 'samples': 13198464, 'steps': 68741, 'loss/train': 0.5912492275238037} 08/31/2021 01:37:46 - INFO - __main__ - Step 68743: {'lr': 0.0002883641595732536, 'samples': 13198656, 'steps': 68742, 'loss/train': 1.8157130479812622} 08/31/2021 01:37:46 - INFO - __main__ - Step 68744: {'lr': 0.00028835891567662, 'samples': 13198848, 'steps': 68743, 'loss/train': 1.2156683206558228} 08/31/2021 01:37:47 - INFO - __main__ - Step 68745: {'lr': 0.0002883536717627025, 'samples': 13199040, 'steps': 68744, 'loss/train': 5.304928779602051} 08/31/2021 01:37:47 - INFO - __main__ - Step 68746: {'lr': 0.0002883484278315033, 'samples': 13199232, 'steps': 68745, 'loss/train': 1.8640223741531372} 08/31/2021 01:37:47 - INFO - __main__ - Step 68747: {'lr': 0.00028834318388302506, 'samples': 13199424, 'steps': 68746, 'loss/train': 0.3711581826210022} 08/31/2021 01:37:48 - INFO - __main__ - Step 68748: {'lr': 0.0002883379399172699, 'samples': 13199616, 'steps': 68747, 'loss/train': 0.91090989112854} 08/31/2021 01:37:49 - INFO - __main__ - Step 68749: {'lr': 0.00028833269593424017, 'samples': 13199808, 'steps': 68748, 'loss/train': 0.4196515679359436} 08/31/2021 01:37:50 - INFO - __main__ - Step 68750: {'lr': 0.0002883274519339384, 'samples': 13200000, 'steps': 68749, 'loss/train': 1.0838546752929688} 08/31/2021 01:37:50 - INFO - __main__ - Step 68751: {'lr': 0.0002883222079163669, 'samples': 13200192, 'steps': 68750, 'loss/train': 1.1927999258041382} 08/31/2021 01:37:51 - INFO - __main__ - Step 68752: {'lr': 0.000288316963881528, 'samples': 13200384, 'steps': 68751, 'loss/train': 0.6974478960037231} 08/31/2021 01:37:51 - INFO - __main__ - Step 68753: {'lr': 0.00028831171982942396, 'samples': 13200576, 'steps': 68752, 'loss/train': 1.6174393892288208} 08/31/2021 01:37:52 - INFO - __main__ - Step 68754: {'lr': 0.00028830647576005733, 'samples': 13200768, 'steps': 68753, 'loss/train': 1.45135498046875} 08/31/2021 01:37:53 - INFO - __main__ - Step 68755: {'lr': 0.00028830123167343036, 'samples': 13200960, 'steps': 68754, 'loss/train': 0.9841320514678955} 08/31/2021 01:37:53 - INFO - __main__ - Step 68756: {'lr': 0.0002882959875695455, 'samples': 13201152, 'steps': 68755, 'loss/train': 1.1728956699371338} 08/31/2021 01:37:54 - INFO - __main__ - Step 68757: {'lr': 0.000288290743448405, 'samples': 13201344, 'steps': 68756, 'loss/train': 1.0963284969329834} 08/31/2021 01:37:54 - INFO - __main__ - Step 68758: {'lr': 0.00028828549931001136, 'samples': 13201536, 'steps': 68757, 'loss/train': 1.5994616746902466} 08/31/2021 01:37:54 - INFO - __main__ - Step 68759: {'lr': 0.00028828025515436684, 'samples': 13201728, 'steps': 68758, 'loss/train': 2.668271064758301} 08/31/2021 01:37:57 - INFO - __main__ - Step 68760: {'lr': 0.0002882750109814738, 'samples': 13201920, 'steps': 68759, 'loss/train': 1.0402567386627197} 08/31/2021 01:37:57 - INFO - __main__ - Step 68761: {'lr': 0.0002882697667913346, 'samples': 13202112, 'steps': 68760, 'loss/train': 0.9250509142875671} 08/31/2021 01:37:58 - INFO - __main__ - Step 68762: {'lr': 0.0002882645225839517, 'samples': 13202304, 'steps': 68761, 'loss/train': 1.4248698949813843} 08/31/2021 01:37:58 - INFO - __main__ - Step 68763: {'lr': 0.0002882592783593273, 'samples': 13202496, 'steps': 68762, 'loss/train': 0.9712652564048767} 08/31/2021 01:37:58 - INFO - __main__ - Step 68764: {'lr': 0.00028825403411746395, 'samples': 13202688, 'steps': 68763, 'loss/train': 1.2832317352294922} 08/31/2021 01:38:00 - INFO - __main__ - Step 68765: {'lr': 0.00028824878985836394, 'samples': 13202880, 'steps': 68764, 'loss/train': 0.12151867896318436} 08/31/2021 01:38:00 - INFO - __main__ - Step 68766: {'lr': 0.00028824354558202957, 'samples': 13203072, 'steps': 68765, 'loss/train': 0.939643144607544} 08/31/2021 01:38:00 - INFO - __main__ - Step 68767: {'lr': 0.0002882383012884632, 'samples': 13203264, 'steps': 68766, 'loss/train': 1.7424982786178589} 08/31/2021 01:38:01 - INFO - __main__ - Step 68768: {'lr': 0.0002882330569776673, 'samples': 13203456, 'steps': 68767, 'loss/train': 0.6698072552680969} 08/31/2021 01:38:01 - INFO - __main__ - Step 68769: {'lr': 0.0002882278126496442, 'samples': 13203648, 'steps': 68768, 'loss/train': 1.631431221961975} 08/31/2021 01:38:03 - INFO - __main__ - Step 68770: {'lr': 0.0002882225683043962, 'samples': 13203840, 'steps': 68769, 'loss/train': 0.8772340416908264} 08/31/2021 01:38:03 - INFO - __main__ - Step 68771: {'lr': 0.0002882173239419257, 'samples': 13204032, 'steps': 68770, 'loss/train': 0.3423311114311218} 08/31/2021 01:38:04 - INFO - __main__ - Step 68772: {'lr': 0.0002882120795622351, 'samples': 13204224, 'steps': 68771, 'loss/train': 1.648494005203247} 08/31/2021 01:38:04 - INFO - __main__ - Step 68773: {'lr': 0.0002882068351653267, 'samples': 13204416, 'steps': 68772, 'loss/train': 1.2143453359603882} 08/31/2021 01:38:04 - INFO - __main__ - Step 68774: {'lr': 0.00028820159075120287, 'samples': 13204608, 'steps': 68773, 'loss/train': 1.6674102544784546} 08/31/2021 01:38:06 - INFO - __main__ - Step 68775: {'lr': 0.000288196346319866, 'samples': 13204800, 'steps': 68774, 'loss/train': 1.2278931140899658} 08/31/2021 01:38:06 - INFO - __main__ - Step 68776: {'lr': 0.0002881911018713185, 'samples': 13204992, 'steps': 68775, 'loss/train': 1.574691653251648} 08/31/2021 01:38:07 - INFO - __main__ - Step 68777: {'lr': 0.00028818585740556256, 'samples': 13205184, 'steps': 68776, 'loss/train': 1.675447940826416} 08/31/2021 01:38:07 - INFO - __main__ - Step 68778: {'lr': 0.00028818061292260077, 'samples': 13205376, 'steps': 68777, 'loss/train': 1.0672099590301514} 08/31/2021 01:38:07 - INFO - __main__ - Step 68779: {'lr': 0.00028817536842243535, 'samples': 13205568, 'steps': 68778, 'loss/train': 5.281649112701416} 08/31/2021 01:38:08 - INFO - __main__ - Step 68780: {'lr': 0.0002881701239050687, 'samples': 13205760, 'steps': 68779, 'loss/train': 1.3022233247756958} 08/31/2021 01:38:09 - INFO - __main__ - Step 68781: {'lr': 0.00028816487937050316, 'samples': 13205952, 'steps': 68780, 'loss/train': 0.06064751744270325} 08/31/2021 01:38:10 - INFO - __main__ - Step 68782: {'lr': 0.0002881596348187412, 'samples': 13206144, 'steps': 68781, 'loss/train': 0.8910722136497498} 08/31/2021 01:38:10 - INFO - __main__ - Step 68783: {'lr': 0.00028815439024978495, 'samples': 13206336, 'steps': 68782, 'loss/train': 1.031821370124817} 08/31/2021 01:38:11 - INFO - __main__ - Step 68784: {'lr': 0.00028814914566363704, 'samples': 13206528, 'steps': 68783, 'loss/train': 1.1056632995605469} 08/31/2021 01:38:11 - INFO - __main__ - Step 68785: {'lr': 0.0002881439010602997, 'samples': 13206720, 'steps': 68784, 'loss/train': 0.25180771946907043} 08/31/2021 01:38:12 - INFO - __main__ - Step 68786: {'lr': 0.00028813865643977527, 'samples': 13206912, 'steps': 68785, 'loss/train': 0.08268294483423233} 08/31/2021 01:38:13 - INFO - __main__ - Step 68787: {'lr': 0.00028813341180206623, 'samples': 13207104, 'steps': 68786, 'loss/train': 2.136183738708496} 08/31/2021 01:38:13 - INFO - __main__ - Step 68788: {'lr': 0.0002881281671471747, 'samples': 13207296, 'steps': 68787, 'loss/train': 0.6108173131942749} 08/31/2021 01:38:14 - INFO - __main__ - Step 68789: {'lr': 0.0002881229224751033, 'samples': 13207488, 'steps': 68788, 'loss/train': 1.843660593032837} 08/31/2021 01:38:14 - INFO - __main__ - Step 68790: {'lr': 0.0002881176777858543, 'samples': 13207680, 'steps': 68789, 'loss/train': 0.40146639943122864} 08/31/2021 01:38:15 - INFO - __main__ - Step 68791: {'lr': 0.0002881124330794301, 'samples': 13207872, 'steps': 68790, 'loss/train': 1.5795307159423828} 08/31/2021 01:38:16 - INFO - __main__ - Step 68792: {'lr': 0.000288107188355833, 'samples': 13208064, 'steps': 68791, 'loss/train': 0.8440595269203186} 08/31/2021 01:38:16 - INFO - __main__ - Step 68793: {'lr': 0.00028810194361506534, 'samples': 13208256, 'steps': 68792, 'loss/train': 0.7870237231254578} 08/31/2021 01:38:17 - INFO - __main__ - Step 68794: {'lr': 0.0002880966988571296, 'samples': 13208448, 'steps': 68793, 'loss/train': 1.247857689857483} 08/31/2021 01:38:17 - INFO - __main__ - Step 68795: {'lr': 0.00028809145408202803, 'samples': 13208640, 'steps': 68794, 'loss/train': 0.71714186668396} 08/31/2021 01:38:19 - INFO - __main__ - Step 68796: {'lr': 0.00028808620928976304, 'samples': 13208832, 'steps': 68795, 'loss/train': 0.6604792475700378} 08/31/2021 01:38:19 - INFO - __main__ - Step 68797: {'lr': 0.00028808096448033703, 'samples': 13209024, 'steps': 68796, 'loss/train': 1.5354552268981934} 08/31/2021 01:38:19 - INFO - __main__ - Step 68798: {'lr': 0.00028807571965375233, 'samples': 13209216, 'steps': 68797, 'loss/train': 0.07897432893514633} 08/31/2021 01:38:20 - INFO - __main__ - Step 68799: {'lr': 0.00028807047481001127, 'samples': 13209408, 'steps': 68798, 'loss/train': 1.273423671722412} 08/31/2021 01:38:20 - INFO - __main__ - Step 68800: {'lr': 0.0002880652299491162, 'samples': 13209600, 'steps': 68799, 'loss/train': 1.081102728843689} 08/31/2021 01:38:22 - INFO - __main__ - Step 68801: {'lr': 0.00028805998507106954, 'samples': 13209792, 'steps': 68800, 'loss/train': 1.0047880411148071} 08/31/2021 01:38:22 - INFO - __main__ - Step 68802: {'lr': 0.00028805474017587376, 'samples': 13209984, 'steps': 68801, 'loss/train': 1.0754189491271973} 08/31/2021 01:38:23 - INFO - __main__ - Step 68803: {'lr': 0.00028804949526353094, 'samples': 13210176, 'steps': 68802, 'loss/train': 1.4172779321670532} 08/31/2021 01:38:23 - INFO - __main__ - Step 68804: {'lr': 0.0002880442503340437, 'samples': 13210368, 'steps': 68803, 'loss/train': 1.2441520690917969} 08/31/2021 01:38:23 - INFO - __main__ - Step 68805: {'lr': 0.0002880390053874143, 'samples': 13210560, 'steps': 68804, 'loss/train': 1.5253491401672363} 08/31/2021 01:38:25 - INFO - __main__ - Step 68806: {'lr': 0.0002880337604236451, 'samples': 13210752, 'steps': 68805, 'loss/train': 1.2526661157608032} 08/31/2021 01:38:25 - INFO - __main__ - Step 68807: {'lr': 0.0002880285154427385, 'samples': 13210944, 'steps': 68806, 'loss/train': 1.4844954013824463} 08/31/2021 01:38:26 - INFO - __main__ - Step 68808: {'lr': 0.00028802327044469674, 'samples': 13211136, 'steps': 68807, 'loss/train': 1.3723387718200684} 08/31/2021 01:38:26 - INFO - __main__ - Step 68809: {'lr': 0.00028801802542952233, 'samples': 13211328, 'steps': 68808, 'loss/train': 0.4679250121116638} 08/31/2021 01:38:26 - INFO - __main__ - Step 68810: {'lr': 0.0002880127803972176, 'samples': 13211520, 'steps': 68809, 'loss/train': 1.2996424436569214} 08/31/2021 01:38:27 - INFO - __main__ - Step 68811: {'lr': 0.00028800753534778483, 'samples': 13211712, 'steps': 68810, 'loss/train': 0.9715739488601685} 08/31/2021 01:38:29 - INFO - __main__ - Step 68812: {'lr': 0.0002880022902812266, 'samples': 13211904, 'steps': 68811, 'loss/train': 1.3443851470947266} 08/31/2021 01:38:29 - INFO - __main__ - Step 68813: {'lr': 0.00028799704519754505, 'samples': 13212096, 'steps': 68812, 'loss/train': 1.3296256065368652} 08/31/2021 01:38:30 - INFO - __main__ - Step 68814: {'lr': 0.0002879918000967426, 'samples': 13212288, 'steps': 68813, 'loss/train': 0.7022924423217773} 08/31/2021 01:38:30 - INFO - __main__ - Step 68815: {'lr': 0.0002879865549788216, 'samples': 13212480, 'steps': 68814, 'loss/train': 1.7976123094558716} 08/31/2021 01:38:30 - INFO - __main__ - Step 68816: {'lr': 0.0002879813098437845, 'samples': 13212672, 'steps': 68815, 'loss/train': 0.3908464014530182} 08/31/2021 01:38:32 - INFO - __main__ - Step 68817: {'lr': 0.00028797606469163357, 'samples': 13212864, 'steps': 68816, 'loss/train': 0.6894538402557373} 08/31/2021 01:38:33 - INFO - __main__ - Step 68818: {'lr': 0.00028797081952237127, 'samples': 13213056, 'steps': 68817, 'loss/train': 1.0617246627807617} 08/31/2021 01:38:33 - INFO - __main__ - Step 68819: {'lr': 0.0002879655743359999, 'samples': 13213248, 'steps': 68818, 'loss/train': 1.2623767852783203} 08/31/2021 01:38:34 - INFO - __main__ - Step 68820: {'lr': 0.0002879603291325217, 'samples': 13213440, 'steps': 68819, 'loss/train': 1.7007477283477783} 08/31/2021 01:38:34 - INFO - __main__ - Step 68821: {'lr': 0.0002879550839119393, 'samples': 13213632, 'steps': 68820, 'loss/train': 1.063895583152771} 08/31/2021 01:38:35 - INFO - __main__ - Step 68822: {'lr': 0.0002879498386742549, 'samples': 13213824, 'steps': 68821, 'loss/train': 1.1720741987228394} 08/31/2021 01:38:36 - INFO - __main__ - Step 68823: {'lr': 0.0002879445934194709, 'samples': 13214016, 'steps': 68822, 'loss/train': 0.6889025568962097} 08/31/2021 01:38:36 - INFO - __main__ - Step 68824: {'lr': 0.0002879393481475896, 'samples': 13214208, 'steps': 68823, 'loss/train': 1.0751873254776} 08/31/2021 01:38:37 - INFO - __main__ - Step 68825: {'lr': 0.00028793410285861344, 'samples': 13214400, 'steps': 68824, 'loss/train': 0.9896445870399475} 08/31/2021 01:38:37 - INFO - __main__ - Step 68826: {'lr': 0.0002879288575525447, 'samples': 13214592, 'steps': 68825, 'loss/train': 1.2029712200164795} 08/31/2021 01:38:39 - INFO - __main__ - Step 68827: {'lr': 0.0002879236122293859, 'samples': 13214784, 'steps': 68826, 'loss/train': 1.4356642961502075} 08/31/2021 01:38:39 - INFO - __main__ - Step 68828: {'lr': 0.00028791836688913926, 'samples': 13214976, 'steps': 68827, 'loss/train': 1.1937891244888306} 08/31/2021 01:38:39 - INFO - __main__ - Step 68829: {'lr': 0.00028791312153180723, 'samples': 13215168, 'steps': 68828, 'loss/train': 1.866499662399292} 08/31/2021 01:38:40 - INFO - __main__ - Step 68830: {'lr': 0.0002879078761573921, 'samples': 13215360, 'steps': 68829, 'loss/train': 1.0349392890930176} 08/31/2021 01:38:40 - INFO - __main__ - Step 68831: {'lr': 0.00028790263076589626, 'samples': 13215552, 'steps': 68830, 'loss/train': 1.323405146598816} 08/31/2021 01:38:40 - INFO - __main__ - Step 68832: {'lr': 0.0002878973853573221, 'samples': 13215744, 'steps': 68831, 'loss/train': 1.0455776453018188} 08/31/2021 01:38:42 - INFO - __main__ - Step 68833: {'lr': 0.0002878921399316719, 'samples': 13215936, 'steps': 68832, 'loss/train': 2.3163394927978516} 08/31/2021 01:38:42 - INFO - __main__ - Step 68834: {'lr': 0.0002878868944889482, 'samples': 13216128, 'steps': 68833, 'loss/train': 0.8598027229309082} 08/31/2021 01:38:43 - INFO - __main__ - Step 68835: {'lr': 0.00028788164902915315, 'samples': 13216320, 'steps': 68834, 'loss/train': 1.411163330078125} 08/31/2021 01:38:43 - INFO - __main__ - Step 68836: {'lr': 0.00028787640355228925, 'samples': 13216512, 'steps': 68835, 'loss/train': 1.5241444110870361} 08/31/2021 01:38:44 - INFO - __main__ - Step 68837: {'lr': 0.0002878711580583588, 'samples': 13216704, 'steps': 68836, 'loss/train': 1.3180828094482422} 08/31/2021 01:38:45 - INFO - __main__ - Step 68838: {'lr': 0.00028786591254736417, 'samples': 13216896, 'steps': 68837, 'loss/train': 0.7797693014144897} 08/31/2021 01:38:46 - INFO - __main__ - Step 68839: {'lr': 0.0002878606670193078, 'samples': 13217088, 'steps': 68838, 'loss/train': 1.1064118146896362} 08/31/2021 01:38:46 - INFO - __main__ - Step 68840: {'lr': 0.00028785542147419203, 'samples': 13217280, 'steps': 68839, 'loss/train': 1.24722158908844} 08/31/2021 01:38:46 - INFO - __main__ - Step 68841: {'lr': 0.00028785017591201914, 'samples': 13217472, 'steps': 68840, 'loss/train': 1.2572994232177734} 08/31/2021 01:38:47 - INFO - __main__ - Step 68842: {'lr': 0.00028784493033279153, 'samples': 13217664, 'steps': 68841, 'loss/train': 1.467419147491455} 08/31/2021 01:38:48 - INFO - __main__ - Step 68843: {'lr': 0.00028783968473651154, 'samples': 13217856, 'steps': 68842, 'loss/train': 1.3730716705322266} 08/31/2021 01:38:48 - INFO - __main__ - Step 68844: {'lr': 0.0002878344391231817, 'samples': 13218048, 'steps': 68843, 'loss/train': 1.8637851476669312} 08/31/2021 01:38:49 - INFO - __main__ - Step 68845: {'lr': 0.0002878291934928041, 'samples': 13218240, 'steps': 68844, 'loss/train': 0.8764941692352295} 08/31/2021 01:38:49 - INFO - __main__ - Step 68846: {'lr': 0.00028782394784538143, 'samples': 13218432, 'steps': 68845, 'loss/train': 1.4687438011169434} 08/31/2021 01:38:50 - INFO - __main__ - Step 68847: {'lr': 0.0002878187021809157, 'samples': 13218624, 'steps': 68846, 'loss/train': 1.5601105690002441} 08/31/2021 01:38:51 - INFO - __main__ - Step 68848: {'lr': 0.00028781345649940955, 'samples': 13218816, 'steps': 68847, 'loss/train': 1.1209638118743896} 08/31/2021 01:38:52 - INFO - __main__ - Step 68849: {'lr': 0.0002878082108008652, 'samples': 13219008, 'steps': 68848, 'loss/train': 1.3531118631362915} 08/31/2021 01:38:52 - INFO - __main__ - Step 68850: {'lr': 0.00028780296508528505, 'samples': 13219200, 'steps': 68849, 'loss/train': 1.083047866821289} 08/31/2021 01:38:52 - INFO - __main__ - Step 68851: {'lr': 0.00028779771935267146, 'samples': 13219392, 'steps': 68850, 'loss/train': 0.5736199617385864} 08/31/2021 01:38:53 - INFO - __main__ - Step 68852: {'lr': 0.00028779247360302684, 'samples': 13219584, 'steps': 68851, 'loss/train': 1.3872631788253784} 08/31/2021 01:38:53 - INFO - __main__ - Step 68853: {'lr': 0.0002877872278363535, 'samples': 13219776, 'steps': 68852, 'loss/train': 1.7934151887893677} 08/31/2021 01:38:55 - INFO - __main__ - Step 68854: {'lr': 0.00028778198205265374, 'samples': 13219968, 'steps': 68853, 'loss/train': 0.7787632346153259} 08/31/2021 01:38:55 - INFO - __main__ - Step 68855: {'lr': 0.00028777673625193014, 'samples': 13220160, 'steps': 68854, 'loss/train': 1.5957863330841064} 08/31/2021 01:38:56 - INFO - __main__ - Step 68856: {'lr': 0.00028777149043418483, 'samples': 13220352, 'steps': 68855, 'loss/train': 1.2843279838562012} 08/31/2021 01:38:56 - INFO - __main__ - Step 68857: {'lr': 0.00028776624459942026, 'samples': 13220544, 'steps': 68856, 'loss/train': 1.273947834968567} 08/31/2021 01:38:56 - INFO - __main__ - Step 68858: {'lr': 0.0002877609987476388, 'samples': 13220736, 'steps': 68857, 'loss/train': 0.6033949851989746} 08/31/2021 01:38:58 - INFO - __main__ - Step 68859: {'lr': 0.0002877557528788429, 'samples': 13220928, 'steps': 68858, 'loss/train': 1.3945859670639038} 08/31/2021 01:38:59 - INFO - __main__ - Step 68860: {'lr': 0.0002877505069930348, 'samples': 13221120, 'steps': 68859, 'loss/train': 1.3145517110824585} 08/31/2021 01:38:59 - INFO - __main__ - Step 68861: {'lr': 0.00028774526109021694, 'samples': 13221312, 'steps': 68860, 'loss/train': 1.0185878276824951} 08/31/2021 01:38:59 - INFO - __main__ - Step 68862: {'lr': 0.00028774001517039156, 'samples': 13221504, 'steps': 68861, 'loss/train': 0.08339644968509674} 08/31/2021 01:39:00 - INFO - __main__ - Step 68863: {'lr': 0.0002877347692335612, 'samples': 13221696, 'steps': 68862, 'loss/train': 1.8392186164855957} 08/31/2021 01:39:01 - INFO - __main__ - Step 68864: {'lr': 0.00028772952327972806, 'samples': 13221888, 'steps': 68863, 'loss/train': 0.03189130127429962} 08/31/2021 01:39:02 - INFO - __main__ - Step 68865: {'lr': 0.0002877242773088946, 'samples': 13222080, 'steps': 68864, 'loss/train': 1.123862862586975} 08/31/2021 01:39:02 - INFO - __main__ - Step 68866: {'lr': 0.0002877190313210632, 'samples': 13222272, 'steps': 68865, 'loss/train': 0.536413311958313} 08/31/2021 01:39:03 - INFO - __main__ - Step 68867: {'lr': 0.00028771378531623613, 'samples': 13222464, 'steps': 68866, 'loss/train': 1.5437359809875488} 08/31/2021 01:39:03 - INFO - __main__ - Step 68868: {'lr': 0.0002877085392944159, 'samples': 13222656, 'steps': 68867, 'loss/train': 0.2895238697528839} 08/31/2021 01:39:05 - INFO - __main__ - Step 68869: {'lr': 0.0002877032932556047, 'samples': 13222848, 'steps': 68868, 'loss/train': 0.4816166162490845} 08/31/2021 01:39:05 - INFO - __main__ - Step 68870: {'lr': 0.00028769804719980496, 'samples': 13223040, 'steps': 68869, 'loss/train': 0.8895971179008484} 08/31/2021 01:39:06 - INFO - __main__ - Step 68871: {'lr': 0.00028769280112701914, 'samples': 13223232, 'steps': 68870, 'loss/train': 1.085952877998352} 08/31/2021 01:39:06 - INFO - __main__ - Step 68872: {'lr': 0.0002876875550372495, 'samples': 13223424, 'steps': 68871, 'loss/train': 1.0927118062973022} 08/31/2021 01:39:06 - INFO - __main__ - Step 68873: {'lr': 0.0002876823089304984, 'samples': 13223616, 'steps': 68872, 'loss/train': 1.216980218887329} 08/31/2021 01:39:07 - INFO - __main__ - Step 68874: {'lr': 0.00028767706280676827, 'samples': 13223808, 'steps': 68873, 'loss/train': 0.9259707927703857} 08/31/2021 01:39:08 - INFO - __main__ - Step 68875: {'lr': 0.0002876718166660614, 'samples': 13224000, 'steps': 68874, 'loss/train': 1.7057223320007324} 08/31/2021 01:39:09 - INFO - __main__ - Step 68876: {'lr': 0.0002876665705083802, 'samples': 13224192, 'steps': 68875, 'loss/train': 1.1939208507537842} 08/31/2021 01:39:09 - INFO - __main__ - Step 68877: {'lr': 0.00028766132433372707, 'samples': 13224384, 'steps': 68876, 'loss/train': 1.4083508253097534} 08/31/2021 01:39:09 - INFO - __main__ - Step 68878: {'lr': 0.00028765607814210424, 'samples': 13224576, 'steps': 68877, 'loss/train': 1.9833792448043823} 08/31/2021 01:39:10 - INFO - __main__ - Step 68879: {'lr': 0.0002876508319335143, 'samples': 13224768, 'steps': 68878, 'loss/train': 0.10178351402282715} 08/31/2021 01:39:11 - INFO - __main__ - Step 68880: {'lr': 0.00028764558570795935, 'samples': 13224960, 'steps': 68879, 'loss/train': 1.1375421285629272} 08/31/2021 01:39:12 - INFO - __main__ - Step 68881: {'lr': 0.00028764033946544195, 'samples': 13225152, 'steps': 68880, 'loss/train': 1.3344398736953735} 08/31/2021 01:39:12 - INFO - __main__ - Step 68882: {'lr': 0.00028763509320596433, 'samples': 13225344, 'steps': 68881, 'loss/train': 0.5605395436286926} 08/31/2021 01:39:13 - INFO - __main__ - Step 68883: {'lr': 0.0002876298469295289, 'samples': 13225536, 'steps': 68882, 'loss/train': 1.1881775856018066} 08/31/2021 01:39:13 - INFO - __main__ - Step 68884: {'lr': 0.00028762460063613815, 'samples': 13225728, 'steps': 68883, 'loss/train': 1.7789674997329712} 08/31/2021 01:39:14 - INFO - __main__ - Step 68885: {'lr': 0.0002876193543257942, 'samples': 13225920, 'steps': 68884, 'loss/train': 1.9599943161010742} 08/31/2021 01:39:15 - INFO - __main__ - Step 68886: {'lr': 0.00028761410799849974, 'samples': 13226112, 'steps': 68885, 'loss/train': 1.1457759141921997} 08/31/2021 01:39:15 - INFO - __main__ - Step 68887: {'lr': 0.0002876088616542568, 'samples': 13226304, 'steps': 68886, 'loss/train': 0.8571404814720154} 08/31/2021 01:39:16 - INFO - __main__ - Step 68888: {'lr': 0.00028760361529306795, 'samples': 13226496, 'steps': 68887, 'loss/train': 0.2212282121181488} 08/31/2021 01:39:16 - INFO - __main__ - Step 68889: {'lr': 0.0002875983689149354, 'samples': 13226688, 'steps': 68888, 'loss/train': 1.9750397205352783} 08/31/2021 01:39:18 - INFO - __main__ - Step 68890: {'lr': 0.0002875931225198617, 'samples': 13226880, 'steps': 68889, 'loss/train': 0.8803195357322693} 08/31/2021 01:39:18 - INFO - __main__ - Step 68891: {'lr': 0.0002875878761078491, 'samples': 13227072, 'steps': 68890, 'loss/train': 0.4268910586833954} 08/31/2021 01:39:18 - INFO - __main__ - Step 68892: {'lr': 0.00028758262967889994, 'samples': 13227264, 'steps': 68891, 'loss/train': 0.643622100353241} 08/31/2021 01:39:19 - INFO - __main__ - Step 68893: {'lr': 0.0002875773832330167, 'samples': 13227456, 'steps': 68892, 'loss/train': 1.2952911853790283} 08/31/2021 01:39:19 - INFO - __main__ - Step 68894: {'lr': 0.0002875721367702016, 'samples': 13227648, 'steps': 68893, 'loss/train': 0.38672876358032227} 08/31/2021 01:39:21 - INFO - __main__ - Step 68895: {'lr': 0.00028756689029045714, 'samples': 13227840, 'steps': 68894, 'loss/train': 0.7388125658035278} 08/31/2021 01:39:21 - INFO - __main__ - Step 68896: {'lr': 0.0002875616437937855, 'samples': 13228032, 'steps': 68895, 'loss/train': 1.5653778314590454} 08/31/2021 01:39:21 - INFO - __main__ - Step 68897: {'lr': 0.0002875563972801893, 'samples': 13228224, 'steps': 68896, 'loss/train': 0.6914176344871521} 08/31/2021 01:39:22 - INFO - __main__ - Step 68898: {'lr': 0.00028755115074967065, 'samples': 13228416, 'steps': 68897, 'loss/train': 0.7520762085914612} 08/31/2021 01:39:22 - INFO - __main__ - Step 68899: {'lr': 0.00028754590420223213, 'samples': 13228608, 'steps': 68898, 'loss/train': 0.8215921521186829} 08/31/2021 01:39:23 - INFO - __main__ - Step 68900: {'lr': 0.000287540657637876, 'samples': 13228800, 'steps': 68899, 'loss/train': 0.5735486745834351} 08/31/2021 01:39:24 - INFO - __main__ - Step 68901: {'lr': 0.00028753541105660456, 'samples': 13228992, 'steps': 68900, 'loss/train': 1.8644840717315674} 08/31/2021 01:39:24 - INFO - __main__ - Step 68902: {'lr': 0.0002875301644584203, 'samples': 13229184, 'steps': 68901, 'loss/train': 1.5565061569213867} 08/31/2021 01:39:25 - INFO - __main__ - Step 68903: {'lr': 0.0002875249178433255, 'samples': 13229376, 'steps': 68902, 'loss/train': 1.4141186475753784} 08/31/2021 01:39:25 - INFO - __main__ - Step 68904: {'lr': 0.00028751967121132255, 'samples': 13229568, 'steps': 68903, 'loss/train': 0.8404693603515625} 08/31/2021 01:39:25 - INFO - __main__ - Step 68905: {'lr': 0.00028751442456241376, 'samples': 13229760, 'steps': 68904, 'loss/train': 1.0515716075897217} 08/31/2021 01:39:27 - INFO - __main__ - Step 68906: {'lr': 0.00028750917789660167, 'samples': 13229952, 'steps': 68905, 'loss/train': 1.149599552154541} 08/31/2021 01:39:27 - INFO - __main__ - Step 68907: {'lr': 0.0002875039312138885, 'samples': 13230144, 'steps': 68906, 'loss/train': 1.0521680116653442} 08/31/2021 01:39:28 - INFO - __main__ - Step 68908: {'lr': 0.00028749868451427655, 'samples': 13230336, 'steps': 68907, 'loss/train': 1.6415379047393799} 08/31/2021 01:39:28 - INFO - __main__ - Step 68909: {'lr': 0.0002874934377977683, 'samples': 13230528, 'steps': 68908, 'loss/train': 1.8838082551956177} 08/31/2021 01:39:28 - INFO - __main__ - Step 68910: {'lr': 0.0002874881910643661, 'samples': 13230720, 'steps': 68909, 'loss/train': 1.6626617908477783} 08/31/2021 01:39:30 - INFO - __main__ - Step 68911: {'lr': 0.00028748294431407234, 'samples': 13230912, 'steps': 68910, 'loss/train': 1.2704225778579712} 08/31/2021 01:39:31 - INFO - __main__ - Step 68912: {'lr': 0.0002874776975468893, 'samples': 13231104, 'steps': 68911, 'loss/train': 0.4528994858264923} 08/31/2021 01:39:31 - INFO - __main__ - Step 68913: {'lr': 0.0002874724507628195, 'samples': 13231296, 'steps': 68912, 'loss/train': 1.2125685214996338} 08/31/2021 01:39:31 - INFO - __main__ - Step 68914: {'lr': 0.00028746720396186505, 'samples': 13231488, 'steps': 68913, 'loss/train': 1.3664100170135498} 08/31/2021 01:39:32 - INFO - __main__ - Step 68915: {'lr': 0.00028746195714402845, 'samples': 13231680, 'steps': 68914, 'loss/train': 1.614943504333496} 08/31/2021 01:39:33 - INFO - __main__ - Step 68916: {'lr': 0.00028745671030931214, 'samples': 13231872, 'steps': 68915, 'loss/train': 0.04105352237820625} 08/31/2021 01:39:34 - INFO - __main__ - Step 68917: {'lr': 0.00028745146345771837, 'samples': 13232064, 'steps': 68916, 'loss/train': 1.1305079460144043} 08/31/2021 01:39:34 - INFO - __main__ - Step 68918: {'lr': 0.0002874462165892496, 'samples': 13232256, 'steps': 68917, 'loss/train': 1.2315748929977417} 08/31/2021 01:39:35 - INFO - __main__ - Step 68919: {'lr': 0.00028744096970390807, 'samples': 13232448, 'steps': 68918, 'loss/train': 1.2714122533798218} 08/31/2021 01:39:35 - INFO - __main__ - Step 68920: {'lr': 0.00028743572280169626, 'samples': 13232640, 'steps': 68919, 'loss/train': 1.1320942640304565} 08/31/2021 01:39:37 - INFO - __main__ - Step 68921: {'lr': 0.0002874304758826165, 'samples': 13232832, 'steps': 68920, 'loss/train': 0.9587633609771729} 08/31/2021 01:39:37 - INFO - __main__ - Step 68922: {'lr': 0.00028742522894667114, 'samples': 13233024, 'steps': 68921, 'loss/train': 1.099491000175476} 08/31/2021 01:39:38 - INFO - __main__ - Step 68923: {'lr': 0.00028741998199386255, 'samples': 13233216, 'steps': 68922, 'loss/train': 1.8310481309890747} 08/31/2021 01:39:38 - INFO - __main__ - Step 68924: {'lr': 0.0002874147350241931, 'samples': 13233408, 'steps': 68923, 'loss/train': 1.210988998413086} 08/31/2021 01:39:39 - INFO - __main__ - Step 68925: {'lr': 0.0002874094880376651, 'samples': 13233600, 'steps': 68924, 'loss/train': 0.9021779894828796} 08/31/2021 01:39:39 - INFO - __main__ - Step 68926: {'lr': 0.000287404241034281, 'samples': 13233792, 'steps': 68925, 'loss/train': 1.3668006658554077} 08/31/2021 01:39:41 - INFO - __main__ - Step 68927: {'lr': 0.0002873989940140432, 'samples': 13233984, 'steps': 68926, 'loss/train': 1.5352381467819214} 08/31/2021 01:39:41 - INFO - __main__ - Step 68928: {'lr': 0.00028739374697695386, 'samples': 13234176, 'steps': 68927, 'loss/train': 1.0522006750106812} 08/31/2021 01:39:41 - INFO - __main__ - Step 68929: {'lr': 0.00028738849992301555, 'samples': 13234368, 'steps': 68928, 'loss/train': 0.5640026926994324} 08/31/2021 01:39:42 - INFO - __main__ - Step 68930: {'lr': 0.0002873832528522305, 'samples': 13234560, 'steps': 68929, 'loss/train': 1.330747365951538} 08/31/2021 01:39:42 - INFO - __main__ - Step 68931: {'lr': 0.00028737800576460117, 'samples': 13234752, 'steps': 68930, 'loss/train': 1.116958737373352} 08/31/2021 01:39:44 - INFO - __main__ - Step 68932: {'lr': 0.00028737275866012993, 'samples': 13234944, 'steps': 68931, 'loss/train': 1.2757619619369507} 08/31/2021 01:39:44 - INFO - __main__ - Step 68933: {'lr': 0.0002873675115388191, 'samples': 13235136, 'steps': 68932, 'loss/train': 1.6001396179199219} 08/31/2021 01:39:45 - INFO - __main__ - Step 68934: {'lr': 0.000287362264400671, 'samples': 13235328, 'steps': 68933, 'loss/train': 0.909116268157959} 08/31/2021 01:39:45 - INFO - __main__ - Step 68935: {'lr': 0.000287357017245688, 'samples': 13235520, 'steps': 68934, 'loss/train': 0.04615689069032669} 08/31/2021 01:39:45 - INFO - __main__ - Step 68936: {'lr': 0.00028735177007387254, 'samples': 13235712, 'steps': 68935, 'loss/train': 0.2746168076992035} 08/31/2021 01:39:47 - INFO - __main__ - Step 68937: {'lr': 0.00028734652288522693, 'samples': 13235904, 'steps': 68936, 'loss/train': 1.388205885887146} 08/31/2021 01:39:47 - INFO - __main__ - Step 68938: {'lr': 0.0002873412756797536, 'samples': 13236096, 'steps': 68937, 'loss/train': 1.432328462600708} 08/31/2021 01:39:47 - INFO - __main__ - Step 68939: {'lr': 0.0002873360284574549, 'samples': 13236288, 'steps': 68938, 'loss/train': 0.7348791360855103} 08/31/2021 01:39:48 - INFO - __main__ - Step 68940: {'lr': 0.0002873307812183331, 'samples': 13236480, 'steps': 68939, 'loss/train': 1.6820719242095947} 08/31/2021 01:39:48 - INFO - __main__ - Step 68941: {'lr': 0.00028732553396239064, 'samples': 13236672, 'steps': 68940, 'loss/train': 1.1107057332992554} 08/31/2021 01:39:50 - INFO - __main__ - Step 68942: {'lr': 0.00028732028668962986, 'samples': 13236864, 'steps': 68941, 'loss/train': 1.5313400030136108} 08/31/2021 01:39:50 - INFO - __main__ - Step 68943: {'lr': 0.0002873150394000531, 'samples': 13237056, 'steps': 68942, 'loss/train': 1.4115183353424072} 08/31/2021 01:39:50 - INFO - __main__ - Step 68944: {'lr': 0.0002873097920936628, 'samples': 13237248, 'steps': 68943, 'loss/train': 1.511657953262329} 08/31/2021 01:39:51 - INFO - __main__ - Step 68945: {'lr': 0.0002873045447704613, 'samples': 13237440, 'steps': 68944, 'loss/train': 1.330142617225647} 08/31/2021 01:39:51 - INFO - __main__ - Step 68946: {'lr': 0.00028729929743045096, 'samples': 13237632, 'steps': 68945, 'loss/train': 0.224909245967865} 08/31/2021 01:39:53 - INFO - __main__ - Step 68947: {'lr': 0.00028729405007363415, 'samples': 13237824, 'steps': 68946, 'loss/train': 1.3545008897781372} 08/31/2021 01:39:53 - INFO - __main__ - Step 68948: {'lr': 0.00028728880270001314, 'samples': 13238016, 'steps': 68947, 'loss/train': 1.4703636169433594} 08/31/2021 01:39:53 - INFO - __main__ - Step 68949: {'lr': 0.0002872835553095904, 'samples': 13238208, 'steps': 68948, 'loss/train': 0.22587184607982635} 08/31/2021 01:39:54 - INFO - __main__ - Step 68950: {'lr': 0.00028727830790236823, 'samples': 13238400, 'steps': 68949, 'loss/train': 0.6479589343070984} 08/31/2021 01:39:54 - INFO - __main__ - Step 68951: {'lr': 0.00028727306047834905, 'samples': 13238592, 'steps': 68950, 'loss/train': 1.3593617677688599} 08/31/2021 01:39:56 - INFO - __main__ - Step 68952: {'lr': 0.0002872678130375353, 'samples': 13238784, 'steps': 68951, 'loss/train': 0.6340569257736206} 08/31/2021 01:39:56 - INFO - __main__ - Step 68953: {'lr': 0.0002872625655799291, 'samples': 13238976, 'steps': 68952, 'loss/train': 1.0441796779632568} 08/31/2021 01:39:56 - INFO - __main__ - Step 68954: {'lr': 0.0002872573181055331, 'samples': 13239168, 'steps': 68953, 'loss/train': 1.4081811904907227} 08/31/2021 01:39:57 - INFO - __main__ - Step 68955: {'lr': 0.00028725207061434943, 'samples': 13239360, 'steps': 68954, 'loss/train': 1.1621432304382324} 08/31/2021 01:39:57 - INFO - __main__ - Step 68956: {'lr': 0.0002872468231063806, 'samples': 13239552, 'steps': 68955, 'loss/train': 0.7615321278572083} 08/31/2021 01:39:58 - INFO - __main__ - Step 68957: {'lr': 0.0002872415755816289, 'samples': 13239744, 'steps': 68956, 'loss/train': 0.9269390106201172} 08/31/2021 01:40:00 - INFO - __main__ - Step 68958: {'lr': 0.0002872363280400967, 'samples': 13239936, 'steps': 68957, 'loss/train': 1.1794129610061646} 08/31/2021 01:40:01 - INFO - __main__ - Step 68959: {'lr': 0.0002872310804817865, 'samples': 13240128, 'steps': 68958, 'loss/train': 0.780022919178009} 08/31/2021 01:40:01 - INFO - __main__ - Step 68960: {'lr': 0.0002872258329067005, 'samples': 13240320, 'steps': 68959, 'loss/train': 1.027729868888855} 08/31/2021 01:40:01 - INFO - __main__ - Step 68961: {'lr': 0.000287220585314841, 'samples': 13240512, 'steps': 68960, 'loss/train': 1.7611830234527588} 08/31/2021 01:40:02 - INFO - __main__ - Step 68962: {'lr': 0.00028721533770621055, 'samples': 13240704, 'steps': 68961, 'loss/train': 1.754428744316101} 08/31/2021 01:40:02 - INFO - __main__ - Step 68963: {'lr': 0.0002872100900808115, 'samples': 13240896, 'steps': 68962, 'loss/train': 1.7940118312835693} 08/31/2021 01:40:02 - INFO - __main__ - Step 68964: {'lr': 0.0002872048424386461, 'samples': 13241088, 'steps': 68963, 'loss/train': 1.182040810585022} 08/31/2021 01:40:04 - INFO - __main__ - Step 68965: {'lr': 0.00028719959477971677, 'samples': 13241280, 'steps': 68964, 'loss/train': 0.5730526447296143} 08/31/2021 01:40:05 - INFO - __main__ - Step 68966: {'lr': 0.00028719434710402586, 'samples': 13241472, 'steps': 68965, 'loss/train': 1.288251519203186} 08/31/2021 01:40:05 - INFO - __main__ - Step 68967: {'lr': 0.0002871890994115758, 'samples': 13241664, 'steps': 68966, 'loss/train': 1.7241792678833008} 08/31/2021 01:40:05 - INFO - __main__ - Step 68968: {'lr': 0.0002871838517023689, 'samples': 13241856, 'steps': 68967, 'loss/train': 1.6088041067123413} 08/31/2021 01:40:06 - INFO - __main__ - Step 68969: {'lr': 0.0002871786039764075, 'samples': 13242048, 'steps': 68968, 'loss/train': 0.40174615383148193} 08/31/2021 01:40:06 - INFO - __main__ - Step 68970: {'lr': 0.000287173356233694, 'samples': 13242240, 'steps': 68969, 'loss/train': 1.7157742977142334} 08/31/2021 01:40:08 - INFO - __main__ - Step 68971: {'lr': 0.0002871681084742308, 'samples': 13242432, 'steps': 68970, 'loss/train': 1.3769363164901733} 08/31/2021 01:40:08 - INFO - __main__ - Step 68972: {'lr': 0.00028716286069802017, 'samples': 13242624, 'steps': 68971, 'loss/train': 0.5374529957771301} 08/31/2021 01:40:09 - INFO - __main__ - Step 68973: {'lr': 0.00028715761290506455, 'samples': 13242816, 'steps': 68972, 'loss/train': 1.1328951120376587} 08/31/2021 01:40:09 - INFO - __main__ - Step 68974: {'lr': 0.0002871523650953663, 'samples': 13243008, 'steps': 68973, 'loss/train': 1.510274052619934} 08/31/2021 01:40:09 - INFO - __main__ - Step 68975: {'lr': 0.0002871471172689277, 'samples': 13243200, 'steps': 68974, 'loss/train': 1.5531785488128662} 08/31/2021 01:40:10 - INFO - __main__ - Step 68976: {'lr': 0.00028714186942575126, 'samples': 13243392, 'steps': 68975, 'loss/train': 1.1157747507095337} 08/31/2021 01:40:12 - INFO - __main__ - Step 68977: {'lr': 0.00028713662156583923, 'samples': 13243584, 'steps': 68976, 'loss/train': 1.6584888696670532} 08/31/2021 01:40:12 - INFO - __main__ - Step 68978: {'lr': 0.00028713137368919405, 'samples': 13243776, 'steps': 68977, 'loss/train': 1.1212425231933594} 08/31/2021 01:40:12 - INFO - __main__ - Step 68979: {'lr': 0.000287126125795818, 'samples': 13243968, 'steps': 68978, 'loss/train': 1.2958472967147827} 08/31/2021 01:40:13 - INFO - __main__ - Step 68980: {'lr': 0.00028712087788571353, 'samples': 13244160, 'steps': 68979, 'loss/train': 1.1313772201538086} 08/31/2021 01:40:13 - INFO - __main__ - Step 68981: {'lr': 0.00028711562995888297, 'samples': 13244352, 'steps': 68980, 'loss/train': 1.5937427282333374} 08/31/2021 01:40:15 - INFO - __main__ - Step 68982: {'lr': 0.00028711038201532864, 'samples': 13244544, 'steps': 68981, 'loss/train': 0.9898165464401245} 08/31/2021 01:40:15 - INFO - __main__ - Step 68983: {'lr': 0.00028710513405505293, 'samples': 13244736, 'steps': 68982, 'loss/train': 0.6384257078170776} 08/31/2021 01:40:15 - INFO - __main__ - Step 68984: {'lr': 0.0002870998860780583, 'samples': 13244928, 'steps': 68983, 'loss/train': 0.6648547649383545} 08/31/2021 01:40:16 - INFO - __main__ - Step 68985: {'lr': 0.0002870946380843469, 'samples': 13245120, 'steps': 68984, 'loss/train': 1.5099819898605347} 08/31/2021 01:40:16 - INFO - __main__ - Step 68986: {'lr': 0.0002870893900739213, 'samples': 13245312, 'steps': 68985, 'loss/train': 0.3791624903678894} 08/31/2021 01:40:17 - INFO - __main__ - Step 68987: {'lr': 0.00028708414204678385, 'samples': 13245504, 'steps': 68986, 'loss/train': 1.20378577709198} 08/31/2021 01:40:18 - INFO - __main__ - Step 68988: {'lr': 0.0002870788940029368, 'samples': 13245696, 'steps': 68987, 'loss/train': 1.406821608543396} 08/31/2021 01:40:18 - INFO - __main__ - Step 68989: {'lr': 0.0002870736459423826, 'samples': 13245888, 'steps': 68988, 'loss/train': 0.7658434510231018} 08/31/2021 01:40:19 - INFO - __main__ - Step 68990: {'lr': 0.0002870683978651236, 'samples': 13246080, 'steps': 68989, 'loss/train': 1.1887303590774536} 08/31/2021 01:40:19 - INFO - __main__ - Step 68991: {'lr': 0.00028706314977116205, 'samples': 13246272, 'steps': 68990, 'loss/train': 1.3713746070861816} 08/31/2021 01:40:21 - INFO - __main__ - Step 68992: {'lr': 0.0002870579016605005, 'samples': 13246464, 'steps': 68991, 'loss/train': 0.788730800151825} 08/31/2021 01:40:21 - INFO - __main__ - Step 68993: {'lr': 0.0002870526535331413, 'samples': 13246656, 'steps': 68992, 'loss/train': 1.4553481340408325} 08/31/2021 01:40:21 - INFO - __main__ - Step 68994: {'lr': 0.00028704740538908663, 'samples': 13246848, 'steps': 68993, 'loss/train': 1.3480738401412964} 08/31/2021 01:40:22 - INFO - __main__ - Step 68995: {'lr': 0.000287042157228339, 'samples': 13247040, 'steps': 68994, 'loss/train': 1.065873384475708} 08/31/2021 01:40:22 - INFO - __main__ - Step 68996: {'lr': 0.00028703690905090075, 'samples': 13247232, 'steps': 68995, 'loss/train': 4.59540319442749} 08/31/2021 01:40:22 - INFO - __main__ - Step 68997: {'lr': 0.00028703166085677423, 'samples': 13247424, 'steps': 68996, 'loss/train': 1.7354880571365356} 08/31/2021 01:40:24 - INFO - __main__ - Step 68998: {'lr': 0.0002870264126459618, 'samples': 13247616, 'steps': 68997, 'loss/train': 1.6087145805358887} 08/31/2021 01:40:24 - INFO - __main__ - Step 68999: {'lr': 0.00028702116441846586, 'samples': 13247808, 'steps': 68998, 'loss/train': 1.1857655048370361} 08/31/2021 01:40:25 - INFO - __main__ - Step 69000: {'lr': 0.0002870159161742888, 'samples': 13248000, 'steps': 68999, 'loss/train': 1.232528567314148} 08/31/2021 01:40:25 - INFO - __main__ - Step 69001: {'lr': 0.00028701066791343287, 'samples': 13248192, 'steps': 69000, 'loss/train': 1.4541674852371216} 08/31/2021 01:40:25 - INFO - __main__ - Step 69002: {'lr': 0.0002870054196359005, 'samples': 13248384, 'steps': 69001, 'loss/train': 1.6077214479446411} 08/31/2021 01:40:27 - INFO - __main__ - Step 69003: {'lr': 0.0002870001713416941, 'samples': 13248576, 'steps': 69002, 'loss/train': 1.473773717880249} 08/31/2021 01:40:27 - INFO - __main__ - Step 69004: {'lr': 0.00028699492303081606, 'samples': 13248768, 'steps': 69003, 'loss/train': 1.6160311698913574} 08/31/2021 01:40:28 - INFO - __main__ - Step 69005: {'lr': 0.00028698967470326854, 'samples': 13248960, 'steps': 69004, 'loss/train': 2.3832812309265137} 08/31/2021 01:40:28 - INFO - __main__ - Step 69006: {'lr': 0.00028698442635905413, 'samples': 13249152, 'steps': 69005, 'loss/train': 1.4647513628005981} 08/31/2021 01:40:28 - INFO - __main__ - Step 69007: {'lr': 0.00028697917799817515, 'samples': 13249344, 'steps': 69006, 'loss/train': 1.4891091585159302} 08/31/2021 01:40:30 - INFO - __main__ - Step 69008: {'lr': 0.0002869739296206338, 'samples': 13249536, 'steps': 69007, 'loss/train': 0.8924762010574341} 08/31/2021 01:40:30 - INFO - __main__ - Step 69009: {'lr': 0.00028696868122643265, 'samples': 13249728, 'steps': 69008, 'loss/train': 1.3429028987884521} 08/31/2021 01:40:31 - INFO - __main__ - Step 69010: {'lr': 0.00028696343281557396, 'samples': 13249920, 'steps': 69009, 'loss/train': 0.8488872051239014} 08/31/2021 01:40:31 - INFO - __main__ - Step 69011: {'lr': 0.0002869581843880601, 'samples': 13250112, 'steps': 69010, 'loss/train': 1.0422565937042236} 08/31/2021 01:40:31 - INFO - __main__ - Step 69012: {'lr': 0.0002869529359438935, 'samples': 13250304, 'steps': 69011, 'loss/train': 2.4392828941345215} 08/31/2021 01:40:33 - INFO - __main__ - Step 69013: {'lr': 0.00028694768748307645, 'samples': 13250496, 'steps': 69012, 'loss/train': 1.299049735069275} 08/31/2021 01:40:33 - INFO - __main__ - Step 69014: {'lr': 0.00028694243900561137, 'samples': 13250688, 'steps': 69013, 'loss/train': 1.5124661922454834} 08/31/2021 01:40:34 - INFO - __main__ - Step 69015: {'lr': 0.00028693719051150053, 'samples': 13250880, 'steps': 69014, 'loss/train': 1.361217975616455} 08/31/2021 01:40:34 - INFO - __main__ - Step 69016: {'lr': 0.00028693194200074643, 'samples': 13251072, 'steps': 69015, 'loss/train': 1.595812439918518} 08/31/2021 01:40:34 - INFO - __main__ - Step 69017: {'lr': 0.00028692669347335134, 'samples': 13251264, 'steps': 69016, 'loss/train': 1.27761709690094} 08/31/2021 01:40:36 - INFO - __main__ - Step 69018: {'lr': 0.0002869214449293176, 'samples': 13251456, 'steps': 69017, 'loss/train': 1.8909939527511597} 08/31/2021 01:40:36 - INFO - __main__ - Step 69019: {'lr': 0.0002869161963686477, 'samples': 13251648, 'steps': 69018, 'loss/train': 1.7595840692520142} 08/31/2021 01:40:37 - INFO - __main__ - Step 69020: {'lr': 0.0002869109477913439, 'samples': 13251840, 'steps': 69019, 'loss/train': 1.5144175291061401} 08/31/2021 01:40:37 - INFO - __main__ - Step 69021: {'lr': 0.00028690569919740864, 'samples': 13252032, 'steps': 69020, 'loss/train': 1.2824270725250244} 08/31/2021 01:40:37 - INFO - __main__ - Step 69022: {'lr': 0.0002869004505868442, 'samples': 13252224, 'steps': 69021, 'loss/train': 1.562415361404419} 08/31/2021 01:40:39 - INFO - __main__ - Step 69023: {'lr': 0.00028689520195965295, 'samples': 13252416, 'steps': 69022, 'loss/train': 0.9769020080566406} 08/31/2021 01:40:39 - INFO - __main__ - Step 69024: {'lr': 0.0002868899533158373, 'samples': 13252608, 'steps': 69023, 'loss/train': 1.0283417701721191} 08/31/2021 01:40:40 - INFO - __main__ - Step 69025: {'lr': 0.0002868847046553997, 'samples': 13252800, 'steps': 69024, 'loss/train': 1.566767692565918} 08/31/2021 01:40:40 - INFO - __main__ - Step 69026: {'lr': 0.0002868794559783423, 'samples': 13252992, 'steps': 69025, 'loss/train': 1.655280590057373} 08/31/2021 01:40:40 - INFO - __main__ - Step 69027: {'lr': 0.0002868742072846677, 'samples': 13253184, 'steps': 69026, 'loss/train': 0.9845290184020996} 08/31/2021 01:40:42 - INFO - __main__ - Step 69028: {'lr': 0.0002868689585743781, 'samples': 13253376, 'steps': 69027, 'loss/train': 1.0049760341644287} 08/31/2021 01:40:43 - INFO - __main__ - Step 69029: {'lr': 0.0002868637098474759, 'samples': 13253568, 'steps': 69028, 'loss/train': 1.5677649974822998} 08/31/2021 01:40:43 - INFO - __main__ - Step 69030: {'lr': 0.00028685846110396347, 'samples': 13253760, 'steps': 69029, 'loss/train': 1.4571105241775513} 08/31/2021 01:40:43 - INFO - __main__ - Step 69031: {'lr': 0.0002868532123438432, 'samples': 13253952, 'steps': 69030, 'loss/train': 1.2089600563049316} 08/31/2021 01:40:44 - INFO - __main__ - Step 69032: {'lr': 0.00028684796356711744, 'samples': 13254144, 'steps': 69031, 'loss/train': 1.8041448593139648} 08/31/2021 01:40:44 - INFO - __main__ - Step 69033: {'lr': 0.0002868427147737886, 'samples': 13254336, 'steps': 69032, 'loss/train': 1.4183655977249146} 08/31/2021 01:40:46 - INFO - __main__ - Step 69034: {'lr': 0.000286837465963859, 'samples': 13254528, 'steps': 69033, 'loss/train': 1.5891839265823364} 08/31/2021 01:40:46 - INFO - __main__ - Step 69035: {'lr': 0.000286832217137331, 'samples': 13254720, 'steps': 69034, 'loss/train': 0.8479142189025879} 08/31/2021 01:40:47 - INFO - __main__ - Step 69036: {'lr': 0.0002868269682942069, 'samples': 13254912, 'steps': 69035, 'loss/train': 0.18017151951789856} 08/31/2021 01:40:47 - INFO - __main__ - Step 69037: {'lr': 0.0002868217194344891, 'samples': 13255104, 'steps': 69036, 'loss/train': 2.1328835487365723} 08/31/2021 01:40:47 - INFO - __main__ - Step 69038: {'lr': 0.00028681647055818016, 'samples': 13255296, 'steps': 69037, 'loss/train': 0.9261119365692139} 08/31/2021 01:40:49 - INFO - __main__ - Step 69039: {'lr': 0.00028681122166528215, 'samples': 13255488, 'steps': 69038, 'loss/train': 1.3289324045181274} 08/31/2021 01:40:49 - INFO - __main__ - Step 69040: {'lr': 0.00028680597275579774, 'samples': 13255680, 'steps': 69039, 'loss/train': 0.7784653306007385} 08/31/2021 01:40:50 - INFO - __main__ - Step 69041: {'lr': 0.000286800723829729, 'samples': 13255872, 'steps': 69040, 'loss/train': 0.9558103084564209} 08/31/2021 01:40:50 - INFO - __main__ - Step 69042: {'lr': 0.0002867954748870784, 'samples': 13256064, 'steps': 69041, 'loss/train': 3.1978511810302734} 08/31/2021 01:40:50 - INFO - __main__ - Step 69043: {'lr': 0.00028679022592784835, 'samples': 13256256, 'steps': 69042, 'loss/train': 1.1156527996063232} 08/31/2021 01:40:52 - INFO - __main__ - Step 69044: {'lr': 0.00028678497695204123, 'samples': 13256448, 'steps': 69043, 'loss/train': 1.2488584518432617} 08/31/2021 01:40:52 - INFO - __main__ - Step 69045: {'lr': 0.0002867797279596593, 'samples': 13256640, 'steps': 69044, 'loss/train': 0.34099242091178894} 08/31/2021 01:40:53 - INFO - __main__ - Step 69046: {'lr': 0.00028677447895070505, 'samples': 13256832, 'steps': 69045, 'loss/train': 1.5604047775268555} 08/31/2021 01:40:53 - INFO - __main__ - Step 69047: {'lr': 0.0002867692299251808, 'samples': 13257024, 'steps': 69046, 'loss/train': 0.9836782217025757} 08/31/2021 01:40:53 - INFO - __main__ - Step 69048: {'lr': 0.00028676398088308894, 'samples': 13257216, 'steps': 69047, 'loss/train': 1.149145483970642} 08/31/2021 01:40:55 - INFO - __main__ - Step 69049: {'lr': 0.0002867587318244317, 'samples': 13257408, 'steps': 69048, 'loss/train': 1.2414212226867676} 08/31/2021 01:40:56 - INFO - __main__ - Step 69050: {'lr': 0.0002867534827492116, 'samples': 13257600, 'steps': 69049, 'loss/train': 1.7505587339401245} 08/31/2021 01:40:56 - INFO - __main__ - Step 69051: {'lr': 0.0002867482336574309, 'samples': 13257792, 'steps': 69050, 'loss/train': 2.0151445865631104} 08/31/2021 01:40:56 - INFO - __main__ - Step 69052: {'lr': 0.00028674298454909203, 'samples': 13257984, 'steps': 69051, 'loss/train': 1.4375168085098267} 08/31/2021 01:40:57 - INFO - __main__ - Step 69053: {'lr': 0.00028673773542419736, 'samples': 13258176, 'steps': 69052, 'loss/train': 1.252759337425232} 08/31/2021 01:40:58 - INFO - __main__ - Step 69054: {'lr': 0.00028673248628274925, 'samples': 13258368, 'steps': 69053, 'loss/train': 1.2232991456985474} 08/31/2021 01:40:58 - INFO - __main__ - Step 69055: {'lr': 0.00028672723712475003, 'samples': 13258560, 'steps': 69054, 'loss/train': 1.0600857734680176} 08/31/2021 01:40:59 - INFO - __main__ - Step 69056: {'lr': 0.00028672198795020204, 'samples': 13258752, 'steps': 69055, 'loss/train': 1.3904129266738892} 08/31/2021 01:40:59 - INFO - __main__ - Step 69057: {'lr': 0.0002867167387591077, 'samples': 13258944, 'steps': 69056, 'loss/train': 1.6141654253005981} 08/31/2021 01:41:00 - INFO - __main__ - Step 69058: {'lr': 0.00028671148955146944, 'samples': 13259136, 'steps': 69057, 'loss/train': 0.4753783047199249} 08/31/2021 01:41:00 - INFO - __main__ - Step 69059: {'lr': 0.00028670624032728944, 'samples': 13259328, 'steps': 69058, 'loss/train': 0.5037471652030945} 08/31/2021 01:41:01 - INFO - __main__ - Step 69060: {'lr': 0.0002867009910865702, 'samples': 13259520, 'steps': 69059, 'loss/train': 1.235815167427063} 08/31/2021 01:41:02 - INFO - __main__ - Step 69061: {'lr': 0.00028669574182931413, 'samples': 13259712, 'steps': 69060, 'loss/train': 1.3846851587295532} 08/31/2021 01:41:02 - INFO - __main__ - Step 69062: {'lr': 0.0002866904925555235, 'samples': 13259904, 'steps': 69061, 'loss/train': 1.316233515739441} 08/31/2021 01:41:03 - INFO - __main__ - Step 69063: {'lr': 0.0002866852432652007, 'samples': 13260096, 'steps': 69062, 'loss/train': 1.4330065250396729} 08/31/2021 01:41:03 - INFO - __main__ - Step 69064: {'lr': 0.00028667999395834805, 'samples': 13260288, 'steps': 69063, 'loss/train': 1.0987696647644043} 08/31/2021 01:41:04 - INFO - __main__ - Step 69065: {'lr': 0.000286674744634968, 'samples': 13260480, 'steps': 69064, 'loss/train': 1.1687451601028442} 08/31/2021 01:41:05 - INFO - __main__ - Step 69066: {'lr': 0.00028666949529506286, 'samples': 13260672, 'steps': 69065, 'loss/train': 1.5355556011199951} 08/31/2021 01:41:05 - INFO - __main__ - Step 69067: {'lr': 0.000286664245938635, 'samples': 13260864, 'steps': 69066, 'loss/train': 0.9375945925712585} 08/31/2021 01:41:05 - INFO - __main__ - Step 69068: {'lr': 0.0002866589965656868, 'samples': 13261056, 'steps': 69067, 'loss/train': 1.1461424827575684} 08/31/2021 01:41:06 - INFO - __main__ - Step 69069: {'lr': 0.0002866537471762207, 'samples': 13261248, 'steps': 69068, 'loss/train': 1.285535216331482} 08/31/2021 01:41:08 - INFO - __main__ - Step 69070: {'lr': 0.0002866484977702389, 'samples': 13261440, 'steps': 69069, 'loss/train': 0.8535446524620056} 08/31/2021 01:41:08 - INFO - __main__ - Step 69071: {'lr': 0.00028664324834774385, 'samples': 13261632, 'steps': 69070, 'loss/train': 1.1759169101715088} 08/31/2021 01:41:09 - INFO - __main__ - Step 69072: {'lr': 0.00028663799890873797, 'samples': 13261824, 'steps': 69071, 'loss/train': 1.286060094833374} 08/31/2021 01:41:09 - INFO - __main__ - Step 69073: {'lr': 0.00028663274945322354, 'samples': 13262016, 'steps': 69072, 'loss/train': 1.0966018438339233} 08/31/2021 01:41:09 - INFO - __main__ - Step 69074: {'lr': 0.00028662749998120294, 'samples': 13262208, 'steps': 69073, 'loss/train': 1.3999803066253662} 08/31/2021 01:41:11 - INFO - __main__ - Step 69075: {'lr': 0.0002866222504926786, 'samples': 13262400, 'steps': 69074, 'loss/train': 0.8905598521232605} 08/31/2021 01:41:11 - INFO - __main__ - Step 69076: {'lr': 0.00028661700098765285, 'samples': 13262592, 'steps': 69075, 'loss/train': 1.0552626848220825} 08/31/2021 01:41:12 - INFO - __main__ - Step 69077: {'lr': 0.000286611751466128, 'samples': 13262784, 'steps': 69076, 'loss/train': 0.5012195706367493} 08/31/2021 01:41:12 - INFO - __main__ - Step 69078: {'lr': 0.00028660650192810646, 'samples': 13262976, 'steps': 69077, 'loss/train': 1.3075703382492065} 08/31/2021 01:41:12 - INFO - __main__ - Step 69079: {'lr': 0.0002866012523735906, 'samples': 13263168, 'steps': 69078, 'loss/train': 1.2875133752822876} 08/31/2021 01:41:14 - INFO - __main__ - Step 69080: {'lr': 0.0002865960028025828, 'samples': 13263360, 'steps': 69079, 'loss/train': 1.0623348951339722} 08/31/2021 01:41:14 - INFO - __main__ - Step 69081: {'lr': 0.00028659075321508544, 'samples': 13263552, 'steps': 69080, 'loss/train': 1.5271142721176147} 08/31/2021 01:41:14 - INFO - __main__ - Step 69082: {'lr': 0.00028658550361110075, 'samples': 13263744, 'steps': 69081, 'loss/train': 0.5145108103752136} 08/31/2021 01:41:15 - INFO - __main__ - Step 69083: {'lr': 0.00028658025399063125, 'samples': 13263936, 'steps': 69082, 'loss/train': 1.2222208976745605} 08/31/2021 01:41:15 - INFO - __main__ - Step 69084: {'lr': 0.00028657500435367927, 'samples': 13264128, 'steps': 69083, 'loss/train': 1.2406381368637085} 08/31/2021 01:41:17 - INFO - __main__ - Step 69085: {'lr': 0.0002865697547002471, 'samples': 13264320, 'steps': 69084, 'loss/train': 1.1959604024887085} 08/31/2021 01:41:17 - INFO - __main__ - Step 69086: {'lr': 0.0002865645050303372, 'samples': 13264512, 'steps': 69085, 'loss/train': 2.0077085494995117} 08/31/2021 01:41:17 - INFO - __main__ - Step 69087: {'lr': 0.000286559255343952, 'samples': 13264704, 'steps': 69086, 'loss/train': 2.7713382244110107} 08/31/2021 01:41:18 - INFO - __main__ - Step 69088: {'lr': 0.0002865540056410936, 'samples': 13264896, 'steps': 69087, 'loss/train': 1.1249195337295532} 08/31/2021 01:41:18 - INFO - __main__ - Step 69089: {'lr': 0.0002865487559217646, 'samples': 13265088, 'steps': 69088, 'loss/train': 1.4579346179962158} 08/31/2021 01:41:18 - INFO - __main__ - Step 69090: {'lr': 0.0002865435061859673, 'samples': 13265280, 'steps': 69089, 'loss/train': 0.7124353051185608} 08/31/2021 01:41:20 - INFO - __main__ - Step 69091: {'lr': 0.000286538256433704, 'samples': 13265472, 'steps': 69090, 'loss/train': 0.9838092923164368} 08/31/2021 01:41:20 - INFO - __main__ - Step 69092: {'lr': 0.0002865330066649773, 'samples': 13265664, 'steps': 69091, 'loss/train': 1.3585478067398071} 08/31/2021 01:41:21 - INFO - __main__ - Step 69093: {'lr': 0.0002865277568797892, 'samples': 13265856, 'steps': 69092, 'loss/train': 1.1229366064071655} 08/31/2021 01:41:21 - INFO - __main__ - Step 69094: {'lr': 0.0002865225070781423, 'samples': 13266048, 'steps': 69093, 'loss/train': 1.7074530124664307} 08/31/2021 01:41:21 - INFO - __main__ - Step 69095: {'lr': 0.000286517257260039, 'samples': 13266240, 'steps': 69094, 'loss/train': 1.369594693183899} 08/31/2021 01:41:23 - INFO - __main__ - Step 69096: {'lr': 0.0002865120074254815, 'samples': 13266432, 'steps': 69095, 'loss/train': 1.1628352403640747} 08/31/2021 01:41:23 - INFO - __main__ - Step 69097: {'lr': 0.00028650675757447224, 'samples': 13266624, 'steps': 69096, 'loss/train': 1.7909623384475708} 08/31/2021 01:41:24 - INFO - __main__ - Step 69098: {'lr': 0.00028650150770701373, 'samples': 13266816, 'steps': 69097, 'loss/train': 1.2931052446365356} 08/31/2021 01:41:24 - INFO - __main__ - Step 69099: {'lr': 0.00028649625782310804, 'samples': 13267008, 'steps': 69098, 'loss/train': 0.9287781715393066} 08/31/2021 01:41:24 - INFO - __main__ - Step 69100: {'lr': 0.0002864910079227578, 'samples': 13267200, 'steps': 69099, 'loss/train': 1.3811174631118774} 08/31/2021 01:41:26 - INFO - __main__ - Step 69101: {'lr': 0.0002864857580059653, 'samples': 13267392, 'steps': 69100, 'loss/train': 0.9640502333641052} 08/31/2021 01:41:27 - INFO - __main__ - Step 69102: {'lr': 0.0002864805080727328, 'samples': 13267584, 'steps': 69101, 'loss/train': 1.4676097631454468} 08/31/2021 01:41:27 - INFO - __main__ - Step 69103: {'lr': 0.0002864752581230628, 'samples': 13267776, 'steps': 69102, 'loss/train': 0.6048466563224792} 08/31/2021 01:41:27 - INFO - __main__ - Step 69104: {'lr': 0.00028647000815695757, 'samples': 13267968, 'steps': 69103, 'loss/train': 1.496862530708313} 08/31/2021 01:41:28 - INFO - __main__ - Step 69105: {'lr': 0.0002864647581744195, 'samples': 13268160, 'steps': 69104, 'loss/train': 1.001657247543335} 08/31/2021 01:41:29 - INFO - __main__ - Step 69106: {'lr': 0.0002864595081754511, 'samples': 13268352, 'steps': 69105, 'loss/train': 0.8567373156547546} 08/31/2021 01:41:29 - INFO - __main__ - Step 69107: {'lr': 0.00028645425816005443, 'samples': 13268544, 'steps': 69106, 'loss/train': 0.8215797543525696} 08/31/2021 01:41:30 - INFO - __main__ - Step 69108: {'lr': 0.0002864490081282322, 'samples': 13268736, 'steps': 69107, 'loss/train': 1.1781553030014038} 08/31/2021 01:41:30 - INFO - __main__ - Step 69109: {'lr': 0.00028644375807998653, 'samples': 13268928, 'steps': 69108, 'loss/train': 1.423060655593872} 08/31/2021 01:41:31 - INFO - __main__ - Step 69110: {'lr': 0.00028643850801531983, 'samples': 13269120, 'steps': 69109, 'loss/train': 1.0750645399093628} 08/31/2021 01:41:32 - INFO - __main__ - Step 69111: {'lr': 0.0002864332579342345, 'samples': 13269312, 'steps': 69110, 'loss/train': 0.9825314283370972} 08/31/2021 01:41:33 - INFO - __main__ - Step 69112: {'lr': 0.000286428007836733, 'samples': 13269504, 'steps': 69111, 'loss/train': 1.6913001537322998} 08/31/2021 01:41:33 - INFO - __main__ - Step 69113: {'lr': 0.00028642275772281753, 'samples': 13269696, 'steps': 69112, 'loss/train': 1.1343404054641724} 08/31/2021 01:41:33 - INFO - __main__ - Step 69114: {'lr': 0.0002864175075924906, 'samples': 13269888, 'steps': 69113, 'loss/train': 1.1020777225494385} 08/31/2021 01:41:34 - INFO - __main__ - Step 69115: {'lr': 0.0002864122574457544, 'samples': 13270080, 'steps': 69114, 'loss/train': 1.4585444927215576} 08/31/2021 01:41:35 - INFO - __main__ - Step 69116: {'lr': 0.00028640700728261144, 'samples': 13270272, 'steps': 69115, 'loss/train': 1.0123146772384644} 08/31/2021 01:41:36 - INFO - __main__ - Step 69117: {'lr': 0.00028640175710306404, 'samples': 13270464, 'steps': 69116, 'loss/train': 1.1787267923355103} 08/31/2021 01:41:36 - INFO - __main__ - Step 69118: {'lr': 0.00028639650690711455, 'samples': 13270656, 'steps': 69117, 'loss/train': 1.4283549785614014} 08/31/2021 01:41:36 - INFO - __main__ - Step 69119: {'lr': 0.0002863912566947654, 'samples': 13270848, 'steps': 69118, 'loss/train': 1.2492384910583496} 08/31/2021 01:41:37 - INFO - __main__ - Step 69120: {'lr': 0.0002863860064660189, 'samples': 13271040, 'steps': 69119, 'loss/train': 1.5809459686279297} 08/31/2021 01:41:39 - INFO - __main__ - Step 69121: {'lr': 0.00028638075622087745, 'samples': 13271232, 'steps': 69120, 'loss/train': 1.181994080543518} 08/31/2021 01:41:39 - INFO - __main__ - Step 69122: {'lr': 0.0002863755059593434, 'samples': 13271424, 'steps': 69121, 'loss/train': 1.7780849933624268} 08/31/2021 01:41:39 - INFO - __main__ - Step 69123: {'lr': 0.000286370255681419, 'samples': 13271616, 'steps': 69122, 'loss/train': 0.9840190410614014} 08/31/2021 01:41:40 - INFO - __main__ - Step 69124: {'lr': 0.0002863650053871068, 'samples': 13271808, 'steps': 69123, 'loss/train': 1.4925061464309692} 08/31/2021 01:41:40 - INFO - __main__ - Step 69125: {'lr': 0.0002863597550764091, 'samples': 13272000, 'steps': 69124, 'loss/train': 1.432785987854004} 08/31/2021 01:41:40 - INFO - __main__ - Step 69126: {'lr': 0.0002863545047493282, 'samples': 13272192, 'steps': 69125, 'loss/train': 1.3322514295578003} 08/31/2021 01:41:42 - INFO - __main__ - Step 69127: {'lr': 0.0002863492544058666, 'samples': 13272384, 'steps': 69126, 'loss/train': 1.2974870204925537} 08/31/2021 01:41:43 - INFO - __main__ - Step 69128: {'lr': 0.00028634400404602654, 'samples': 13272576, 'steps': 69127, 'loss/train': 0.647570013999939} 08/31/2021 01:41:43 - INFO - __main__ - Step 69129: {'lr': 0.00028633875366981045, 'samples': 13272768, 'steps': 69128, 'loss/train': 1.591734766960144} 08/31/2021 01:41:44 - INFO - __main__ - Step 69130: {'lr': 0.0002863335032772207, 'samples': 13272960, 'steps': 69129, 'loss/train': 0.05937333032488823} 08/31/2021 01:41:44 - INFO - __main__ - Step 69131: {'lr': 0.00028632825286825956, 'samples': 13273152, 'steps': 69130, 'loss/train': 1.5721701383590698} 08/31/2021 01:41:46 - INFO - __main__ - Step 69132: {'lr': 0.00028632300244292954, 'samples': 13273344, 'steps': 69131, 'loss/train': 1.1303585767745972} 08/31/2021 01:41:46 - INFO - __main__ - Step 69133: {'lr': 0.0002863177520012329, 'samples': 13273536, 'steps': 69132, 'loss/train': 0.42194870114326477} 08/31/2021 01:41:46 - INFO - __main__ - Step 69134: {'lr': 0.000286312501543172, 'samples': 13273728, 'steps': 69133, 'loss/train': 2.0735154151916504} 08/31/2021 01:41:47 - INFO - __main__ - Step 69135: {'lr': 0.0002863072510687493, 'samples': 13273920, 'steps': 69134, 'loss/train': 1.7445998191833496} 08/31/2021 01:41:47 - INFO - __main__ - Step 69136: {'lr': 0.0002863020005779672, 'samples': 13274112, 'steps': 69135, 'loss/train': 1.3637323379516602} 08/31/2021 01:41:49 - INFO - __main__ - Step 69137: {'lr': 0.00028629675007082783, 'samples': 13274304, 'steps': 69136, 'loss/train': 1.1223872900009155} 08/31/2021 01:41:49 - INFO - __main__ - Step 69138: {'lr': 0.00028629149954733377, 'samples': 13274496, 'steps': 69137, 'loss/train': 0.9906426072120667} 08/31/2021 01:41:49 - INFO - __main__ - Step 69139: {'lr': 0.0002862862490074873, 'samples': 13274688, 'steps': 69138, 'loss/train': 0.544013500213623} 08/31/2021 01:41:50 - INFO - __main__ - Step 69140: {'lr': 0.0002862809984512908, 'samples': 13274880, 'steps': 69139, 'loss/train': 1.5619895458221436} 08/31/2021 01:41:50 - INFO - __main__ - Step 69141: {'lr': 0.00028627574787874673, 'samples': 13275072, 'steps': 69140, 'loss/train': 0.7195444107055664} 08/31/2021 01:41:50 - INFO - __main__ - Step 69142: {'lr': 0.0002862704972898573, 'samples': 13275264, 'steps': 69141, 'loss/train': 1.1981141567230225} 08/31/2021 01:41:52 - INFO - __main__ - Step 69143: {'lr': 0.00028626524668462494, 'samples': 13275456, 'steps': 69142, 'loss/train': 1.0799496173858643} 08/31/2021 01:41:53 - INFO - __main__ - Step 69144: {'lr': 0.000286259996063052, 'samples': 13275648, 'steps': 69143, 'loss/train': 0.9672683477401733} 08/31/2021 01:41:53 - INFO - __main__ - Step 69145: {'lr': 0.00028625474542514083, 'samples': 13275840, 'steps': 69144, 'loss/train': 1.5316084623336792} 08/31/2021 01:41:53 - INFO - __main__ - Step 69146: {'lr': 0.0002862494947708939, 'samples': 13276032, 'steps': 69145, 'loss/train': 1.479302167892456} 08/31/2021 01:41:54 - INFO - __main__ - Step 69147: {'lr': 0.00028624424410031354, 'samples': 13276224, 'steps': 69146, 'loss/train': 1.5036413669586182} 08/31/2021 01:41:55 - INFO - __main__ - Step 69148: {'lr': 0.00028623899341340207, 'samples': 13276416, 'steps': 69147, 'loss/train': 1.465988278388977} 08/31/2021 01:41:56 - INFO - __main__ - Step 69149: {'lr': 0.0002862337427101618, 'samples': 13276608, 'steps': 69148, 'loss/train': 0.4204690158367157} 08/31/2021 01:41:56 - INFO - __main__ - Step 69150: {'lr': 0.0002862284919905952, 'samples': 13276800, 'steps': 69149, 'loss/train': 1.2259953022003174} 08/31/2021 01:41:56 - INFO - __main__ - Step 69151: {'lr': 0.00028622324125470464, 'samples': 13276992, 'steps': 69150, 'loss/train': 2.1923227310180664} 08/31/2021 01:41:57 - INFO - __main__ - Step 69152: {'lr': 0.0002862179905024924, 'samples': 13277184, 'steps': 69151, 'loss/train': 1.2576440572738647} 08/31/2021 01:41:58 - INFO - __main__ - Step 69153: {'lr': 0.00028621273973396087, 'samples': 13277376, 'steps': 69152, 'loss/train': 1.3029941320419312} 08/31/2021 01:41:59 - INFO - __main__ - Step 69154: {'lr': 0.00028620748894911245, 'samples': 13277568, 'steps': 69153, 'loss/train': 0.0969022810459137} 08/31/2021 01:41:59 - INFO - __main__ - Step 69155: {'lr': 0.00028620223814794954, 'samples': 13277760, 'steps': 69154, 'loss/train': 1.1859437227249146} 08/31/2021 01:41:59 - INFO - __main__ - Step 69156: {'lr': 0.00028619698733047444, 'samples': 13277952, 'steps': 69155, 'loss/train': 0.9191822409629822} 08/31/2021 01:42:00 - INFO - __main__ - Step 69157: {'lr': 0.0002861917364966896, 'samples': 13278144, 'steps': 69156, 'loss/train': 0.6315219402313232} 08/31/2021 01:42:01 - INFO - __main__ - Step 69158: {'lr': 0.0002861864856465972, 'samples': 13278336, 'steps': 69157, 'loss/train': 0.9961555600166321} 08/31/2021 01:42:02 - INFO - __main__ - Step 69159: {'lr': 0.0002861812347801998, 'samples': 13278528, 'steps': 69158, 'loss/train': 1.2329764366149902} 08/31/2021 01:42:02 - INFO - __main__ - Step 69160: {'lr': 0.00028617598389749966, 'samples': 13278720, 'steps': 69159, 'loss/train': 1.404584527015686} 08/31/2021 01:42:03 - INFO - __main__ - Step 69161: {'lr': 0.0002861707329984992, 'samples': 13278912, 'steps': 69160, 'loss/train': 1.4295979738235474} 08/31/2021 01:42:03 - INFO - __main__ - Step 69162: {'lr': 0.00028616548208320073, 'samples': 13279104, 'steps': 69161, 'loss/train': 1.2363359928131104} 08/31/2021 01:42:03 - INFO - __main__ - Step 69163: {'lr': 0.00028616023115160674, 'samples': 13279296, 'steps': 69162, 'loss/train': 0.5240989327430725} 08/31/2021 01:42:05 - INFO - __main__ - Step 69164: {'lr': 0.00028615498020371946, 'samples': 13279488, 'steps': 69163, 'loss/train': 0.04744187742471695} 08/31/2021 01:42:05 - INFO - __main__ - Step 69165: {'lr': 0.00028614972923954123, 'samples': 13279680, 'steps': 69164, 'loss/train': 0.3823872208595276} 08/31/2021 01:42:05 - INFO - __main__ - Step 69166: {'lr': 0.00028614447825907455, 'samples': 13279872, 'steps': 69165, 'loss/train': 0.741399884223938} 08/31/2021 01:42:06 - INFO - __main__ - Step 69167: {'lr': 0.00028613922726232173, 'samples': 13280064, 'steps': 69166, 'loss/train': 1.2867902517318726} 08/31/2021 01:42:06 - INFO - __main__ - Step 69168: {'lr': 0.0002861339762492852, 'samples': 13280256, 'steps': 69167, 'loss/train': 1.2279313802719116} 08/31/2021 01:42:08 - INFO - __main__ - Step 69169: {'lr': 0.0002861287252199671, 'samples': 13280448, 'steps': 69168, 'loss/train': 1.2405366897583008} 08/31/2021 01:42:09 - INFO - __main__ - Step 69170: {'lr': 0.00028612347417437007, 'samples': 13280640, 'steps': 69169, 'loss/train': 1.5034812688827515} 08/31/2021 01:42:09 - INFO - __main__ - Step 69171: {'lr': 0.00028611822311249633, 'samples': 13280832, 'steps': 69170, 'loss/train': 0.48732322454452515} 08/31/2021 01:42:10 - INFO - __main__ - Step 69172: {'lr': 0.0002861129720343483, 'samples': 13281024, 'steps': 69171, 'loss/train': 1.3177059888839722} 08/31/2021 01:42:10 - INFO - __main__ - Step 69173: {'lr': 0.00028610772093992827, 'samples': 13281216, 'steps': 69172, 'loss/train': 0.06229985132813454} 08/31/2021 01:42:10 - INFO - __main__ - Step 69174: {'lr': 0.0002861024698292387, 'samples': 13281408, 'steps': 69173, 'loss/train': 1.087061882019043} 08/31/2021 01:42:12 - INFO - __main__ - Step 69175: {'lr': 0.00028609721870228195, 'samples': 13281600, 'steps': 69174, 'loss/train': 1.0002788305282593} 08/31/2021 01:42:13 - INFO - __main__ - Step 69176: {'lr': 0.0002860919675590603, 'samples': 13281792, 'steps': 69175, 'loss/train': 1.0491517782211304} 08/31/2021 01:42:13 - INFO - __main__ - Step 69177: {'lr': 0.0002860867163995762, 'samples': 13281984, 'steps': 69176, 'loss/train': 1.4301068782806396} 08/31/2021 01:42:14 - INFO - __main__ - Step 69178: {'lr': 0.0002860814652238319, 'samples': 13282176, 'steps': 69177, 'loss/train': 1.0008540153503418} 08/31/2021 01:42:14 - INFO - __main__ - Step 69179: {'lr': 0.0002860762140318299, 'samples': 13282368, 'steps': 69178, 'loss/train': 1.5668154954910278} 08/31/2021 01:42:15 - INFO - __main__ - Step 69180: {'lr': 0.0002860709628235725, 'samples': 13282560, 'steps': 69179, 'loss/train': 0.060261961072683334} 08/31/2021 01:42:16 - INFO - __main__ - Step 69181: {'lr': 0.00028606571159906207, 'samples': 13282752, 'steps': 69180, 'loss/train': 1.084168553352356} 08/31/2021 01:42:16 - INFO - __main__ - Step 69182: {'lr': 0.0002860604603583011, 'samples': 13282944, 'steps': 69181, 'loss/train': 0.5540854334831238} 08/31/2021 01:42:17 - INFO - __main__ - Step 69183: {'lr': 0.00028605520910129174, 'samples': 13283136, 'steps': 69182, 'loss/train': 1.3696943521499634} 08/31/2021 01:42:17 - INFO - __main__ - Step 69184: {'lr': 0.0002860499578280364, 'samples': 13283328, 'steps': 69183, 'loss/train': 0.0728173553943634} 08/31/2021 01:42:18 - INFO - __main__ - Step 69185: {'lr': 0.00028604470653853764, 'samples': 13283520, 'steps': 69184, 'loss/train': 1.9422788619995117} 08/31/2021 01:42:19 - INFO - __main__ - Step 69186: {'lr': 0.0002860394552327976, 'samples': 13283712, 'steps': 69185, 'loss/train': 1.2595152854919434} 08/31/2021 01:42:19 - INFO - __main__ - Step 69187: {'lr': 0.0002860342039108188, 'samples': 13283904, 'steps': 69186, 'loss/train': 1.1562530994415283} 08/31/2021 01:42:20 - INFO - __main__ - Step 69188: {'lr': 0.00028602895257260355, 'samples': 13284096, 'steps': 69187, 'loss/train': 0.34550735354423523} 08/31/2021 01:42:20 - INFO - __main__ - Step 69189: {'lr': 0.0002860237012181541, 'samples': 13284288, 'steps': 69188, 'loss/train': 1.027223825454712} 08/31/2021 01:42:22 - INFO - __main__ - Step 69190: {'lr': 0.00028601844984747304, 'samples': 13284480, 'steps': 69189, 'loss/train': 0.5430083870887756} 08/31/2021 01:42:22 - INFO - __main__ - Step 69191: {'lr': 0.00028601319846056255, 'samples': 13284672, 'steps': 69190, 'loss/train': 0.04721713811159134} 08/31/2021 01:42:22 - INFO - __main__ - Step 69192: {'lr': 0.0002860079470574251, 'samples': 13284864, 'steps': 69191, 'loss/train': 1.0872070789337158} 08/31/2021 01:42:23 - INFO - __main__ - Step 69193: {'lr': 0.00028600269563806304, 'samples': 13285056, 'steps': 69192, 'loss/train': 1.6307061910629272} 08/31/2021 01:42:23 - INFO - __main__ - Step 69194: {'lr': 0.0002859974442024787, 'samples': 13285248, 'steps': 69193, 'loss/train': 1.8372392654418945} 08/31/2021 01:42:23 - INFO - __main__ - Step 69195: {'lr': 0.0002859921927506745, 'samples': 13285440, 'steps': 69194, 'loss/train': 1.0242353677749634} 08/31/2021 01:42:25 - INFO - __main__ - Step 69196: {'lr': 0.00028598694128265274, 'samples': 13285632, 'steps': 69195, 'loss/train': 1.2779674530029297} 08/31/2021 01:42:25 - INFO - __main__ - Step 69197: {'lr': 0.0002859816897984158, 'samples': 13285824, 'steps': 69196, 'loss/train': 1.6353520154953003} 08/31/2021 01:42:26 - INFO - __main__ - Step 69198: {'lr': 0.0002859764382979661, 'samples': 13286016, 'steps': 69197, 'loss/train': 0.38717591762542725} 08/31/2021 01:42:26 - INFO - __main__ - Step 69199: {'lr': 0.00028597118678130596, 'samples': 13286208, 'steps': 69198, 'loss/train': 1.7381988763809204} 08/31/2021 01:42:27 - INFO - __main__ - Step 69200: {'lr': 0.0002859659352484378, 'samples': 13286400, 'steps': 69199, 'loss/train': 2.0281295776367188} 08/31/2021 01:42:28 - INFO - __main__ - Step 69201: {'lr': 0.00028596068369936387, 'samples': 13286592, 'steps': 69200, 'loss/train': 0.9709375500679016} 08/31/2021 01:42:28 - INFO - __main__ - Step 69202: {'lr': 0.0002859554321340867, 'samples': 13286784, 'steps': 69201, 'loss/train': 1.0929887294769287} 08/31/2021 01:42:29 - INFO - __main__ - Step 69203: {'lr': 0.0002859501805526085, 'samples': 13286976, 'steps': 69202, 'loss/train': 1.1598114967346191} 08/31/2021 01:42:29 - INFO - __main__ - Step 69204: {'lr': 0.0002859449289549317, 'samples': 13287168, 'steps': 69203, 'loss/train': 0.5541812181472778} 08/31/2021 01:42:30 - INFO - __main__ - Step 69205: {'lr': 0.0002859396773410587, 'samples': 13287360, 'steps': 69204, 'loss/train': 0.716668963432312} 08/31/2021 01:42:31 - INFO - __main__ - Step 69206: {'lr': 0.0002859344257109918, 'samples': 13287552, 'steps': 69205, 'loss/train': 0.5892334580421448} 08/31/2021 01:42:31 - INFO - __main__ - Step 69207: {'lr': 0.0002859291740647334, 'samples': 13287744, 'steps': 69206, 'loss/train': 1.2392159700393677} 08/31/2021 01:42:32 - INFO - __main__ - Step 69208: {'lr': 0.00028592392240228595, 'samples': 13287936, 'steps': 69207, 'loss/train': 1.2263298034667969} 08/31/2021 01:42:32 - INFO - __main__ - Step 69209: {'lr': 0.00028591867072365166, 'samples': 13288128, 'steps': 69208, 'loss/train': 0.6481131911277771} 08/31/2021 01:42:32 - INFO - __main__ - Step 69210: {'lr': 0.000285913419028833, 'samples': 13288320, 'steps': 69209, 'loss/train': 1.7341796159744263} 08/31/2021 01:42:34 - INFO - __main__ - Step 69211: {'lr': 0.0002859081673178323, 'samples': 13288512, 'steps': 69210, 'loss/train': 0.9820091724395752} 08/31/2021 01:42:34 - INFO - __main__ - Step 69212: {'lr': 0.0002859029155906519, 'samples': 13288704, 'steps': 69211, 'loss/train': 0.8558233976364136} 08/31/2021 01:42:35 - INFO - __main__ - Step 69213: {'lr': 0.00028589766384729426, 'samples': 13288896, 'steps': 69212, 'loss/train': 1.663884162902832} 08/31/2021 01:42:35 - INFO - __main__ - Step 69214: {'lr': 0.00028589241208776164, 'samples': 13289088, 'steps': 69213, 'loss/train': 1.4321736097335815} 08/31/2021 01:42:36 - INFO - __main__ - Step 69215: {'lr': 0.0002858871603120565, 'samples': 13289280, 'steps': 69214, 'loss/train': 1.2621766328811646} 08/31/2021 01:42:37 - INFO - __main__ - Step 69216: {'lr': 0.00028588190852018116, 'samples': 13289472, 'steps': 69215, 'loss/train': 1.6269437074661255} 08/31/2021 01:42:37 - INFO - __main__ - Step 69217: {'lr': 0.0002858766567121379, 'samples': 13289664, 'steps': 69216, 'loss/train': 0.18103525042533875} 08/31/2021 01:42:38 - INFO - __main__ - Step 69218: {'lr': 0.0002858714048879292, 'samples': 13289856, 'steps': 69217, 'loss/train': 1.400937557220459} 08/31/2021 01:42:38 - INFO - __main__ - Step 69219: {'lr': 0.0002858661530475575, 'samples': 13290048, 'steps': 69218, 'loss/train': 1.4177753925323486} 08/31/2021 01:42:39 - INFO - __main__ - Step 69220: {'lr': 0.000285860901191025, 'samples': 13290240, 'steps': 69219, 'loss/train': 0.9003981947898865} 08/31/2021 01:42:39 - INFO - __main__ - Step 69221: {'lr': 0.00028585564931833413, 'samples': 13290432, 'steps': 69220, 'loss/train': 1.1543956995010376} 08/31/2021 01:42:41 - INFO - __main__ - Step 69222: {'lr': 0.00028585039742948725, 'samples': 13290624, 'steps': 69221, 'loss/train': 1.57218337059021} 08/31/2021 01:42:41 - INFO - __main__ - Step 69223: {'lr': 0.0002858451455244867, 'samples': 13290816, 'steps': 69222, 'loss/train': 1.880743384361267} 08/31/2021 01:42:41 - INFO - __main__ - Step 69224: {'lr': 0.00028583989360333496, 'samples': 13291008, 'steps': 69223, 'loss/train': 0.048990439623594284} 08/31/2021 01:42:42 - INFO - __main__ - Step 69225: {'lr': 0.0002858346416660342, 'samples': 13291200, 'steps': 69224, 'loss/train': 0.5841689109802246} 08/31/2021 01:42:42 - INFO - __main__ - Step 69226: {'lr': 0.000285829389712587, 'samples': 13291392, 'steps': 69225, 'loss/train': 1.4602285623550415} 08/31/2021 01:42:44 - INFO - __main__ - Step 69227: {'lr': 0.00028582413774299567, 'samples': 13291584, 'steps': 69226, 'loss/train': 1.4360982179641724} 08/31/2021 01:42:44 - INFO - __main__ - Step 69228: {'lr': 0.0002858188857572624, 'samples': 13291776, 'steps': 69227, 'loss/train': 1.1035380363464355} 08/31/2021 01:42:45 - INFO - __main__ - Step 69229: {'lr': 0.0002858136337553898, 'samples': 13291968, 'steps': 69228, 'loss/train': 1.0871245861053467} 08/31/2021 01:42:45 - INFO - __main__ - Step 69230: {'lr': 0.0002858083817373801, 'samples': 13292160, 'steps': 69229, 'loss/train': 0.026279520243406296} 08/31/2021 01:42:45 - INFO - __main__ - Step 69231: {'lr': 0.0002858031297032357, 'samples': 13292352, 'steps': 69230, 'loss/train': 0.9407035708427429} 08/31/2021 01:42:46 - INFO - __main__ - Step 69232: {'lr': 0.00028579787765295895, 'samples': 13292544, 'steps': 69231, 'loss/train': 1.6903537511825562} 08/31/2021 01:42:49 - INFO - __main__ - Step 69233: {'lr': 0.0002857926255865523, 'samples': 13292736, 'steps': 69232, 'loss/train': 0.8091885447502136} 08/31/2021 01:42:49 - INFO - __main__ - Step 69234: {'lr': 0.0002857873735040179, 'samples': 13292928, 'steps': 69233, 'loss/train': 0.6797033548355103} 08/31/2021 01:42:49 - INFO - __main__ - Step 69235: {'lr': 0.00028578212140535836, 'samples': 13293120, 'steps': 69234, 'loss/train': 1.7984566688537598} 08/31/2021 01:42:50 - INFO - __main__ - Step 69236: {'lr': 0.0002857768692905759, 'samples': 13293312, 'steps': 69235, 'loss/train': 1.0541329383850098} 08/31/2021 01:42:50 - INFO - __main__ - Step 69237: {'lr': 0.000285771617159673, 'samples': 13293504, 'steps': 69236, 'loss/train': 1.162770390510559} 08/31/2021 01:42:50 - INFO - __main__ - Step 69238: {'lr': 0.00028576636501265195, 'samples': 13293696, 'steps': 69237, 'loss/train': 0.024716956540942192} 08/31/2021 01:42:51 - INFO - __main__ - Step 69239: {'lr': 0.00028576111284951504, 'samples': 13293888, 'steps': 69238, 'loss/train': 0.023094289004802704} 08/31/2021 01:42:52 - INFO - __main__ - Step 69240: {'lr': 0.0002857558606702648, 'samples': 13294080, 'steps': 69239, 'loss/train': 1.3978697061538696} 08/31/2021 01:42:53 - INFO - __main__ - Step 69241: {'lr': 0.0002857506084749035, 'samples': 13294272, 'steps': 69240, 'loss/train': 1.0614886283874512} 08/31/2021 01:42:53 - INFO - __main__ - Step 69242: {'lr': 0.0002857453562634336, 'samples': 13294464, 'steps': 69241, 'loss/train': 1.1451126337051392} 08/31/2021 01:42:53 - INFO - __main__ - Step 69243: {'lr': 0.00028574010403585733, 'samples': 13294656, 'steps': 69242, 'loss/train': 2.1977622509002686} 08/31/2021 01:42:54 - INFO - __main__ - Step 69244: {'lr': 0.0002857348517921771, 'samples': 13294848, 'steps': 69243, 'loss/train': 0.5467246770858765} 08/31/2021 01:42:55 - INFO - __main__ - Step 69245: {'lr': 0.0002857295995323953, 'samples': 13295040, 'steps': 69244, 'loss/train': 1.6179664134979248} 08/31/2021 01:42:56 - INFO - __main__ - Step 69246: {'lr': 0.0002857243472565143, 'samples': 13295232, 'steps': 69245, 'loss/train': 0.7987332940101624} 08/31/2021 01:42:56 - INFO - __main__ - Step 69247: {'lr': 0.0002857190949645365, 'samples': 13295424, 'steps': 69246, 'loss/train': 1.0000512599945068} 08/31/2021 01:42:57 - INFO - __main__ - Step 69248: {'lr': 0.0002857138426564642, 'samples': 13295616, 'steps': 69247, 'loss/train': 1.0633726119995117} 08/31/2021 01:42:57 - INFO - __main__ - Step 69249: {'lr': 0.0002857085903322998, 'samples': 13295808, 'steps': 69248, 'loss/train': 1.35701584815979} 08/31/2021 01:42:58 - INFO - __main__ - Step 69250: {'lr': 0.00028570333799204565, 'samples': 13296000, 'steps': 69249, 'loss/train': 1.3298888206481934} 08/31/2021 01:42:59 - INFO - __main__ - Step 69251: {'lr': 0.0002856980856357041, 'samples': 13296192, 'steps': 69250, 'loss/train': 1.3059083223342896} 08/31/2021 01:42:59 - INFO - __main__ - Step 69252: {'lr': 0.00028569283326327754, 'samples': 13296384, 'steps': 69251, 'loss/train': 1.6847862005233765} 08/31/2021 01:43:00 - INFO - __main__ - Step 69253: {'lr': 0.0002856875808747684, 'samples': 13296576, 'steps': 69252, 'loss/train': 1.0872013568878174} 08/31/2021 01:43:00 - INFO - __main__ - Step 69254: {'lr': 0.00028568232847017895, 'samples': 13296768, 'steps': 69253, 'loss/train': 1.9332196712493896} 08/31/2021 01:43:00 - INFO - __main__ - Step 69255: {'lr': 0.0002856770760495116, 'samples': 13296960, 'steps': 69254, 'loss/train': 0.9832795858383179} 08/31/2021 01:43:02 - INFO - __main__ - Step 69256: {'lr': 0.00028567182361276873, 'samples': 13297152, 'steps': 69255, 'loss/train': 1.1123636960983276} 08/31/2021 01:43:03 - INFO - __main__ - Step 69257: {'lr': 0.0002856665711599526, 'samples': 13297344, 'steps': 69256, 'loss/train': 1.4919461011886597} 08/31/2021 01:43:03 - INFO - __main__ - Step 69258: {'lr': 0.0002856613186910658, 'samples': 13297536, 'steps': 69257, 'loss/train': 0.8623973727226257} 08/31/2021 01:43:03 - INFO - __main__ - Step 69259: {'lr': 0.0002856560662061105, 'samples': 13297728, 'steps': 69258, 'loss/train': 1.3434020280838013} 08/31/2021 01:43:04 - INFO - __main__ - Step 69260: {'lr': 0.0002856508137050891, 'samples': 13297920, 'steps': 69259, 'loss/train': 0.08443035185337067} 08/31/2021 01:43:05 - INFO - __main__ - Step 69261: {'lr': 0.000285645561188004, 'samples': 13298112, 'steps': 69260, 'loss/train': 1.5482412576675415} 08/31/2021 01:43:06 - INFO - __main__ - Step 69262: {'lr': 0.0002856403086548576, 'samples': 13298304, 'steps': 69261, 'loss/train': 1.3870086669921875} 08/31/2021 01:43:06 - INFO - __main__ - Step 69263: {'lr': 0.0002856350561056522, 'samples': 13298496, 'steps': 69262, 'loss/train': 1.0981676578521729} 08/31/2021 01:43:07 - INFO - __main__ - Step 69264: {'lr': 0.0002856298035403902, 'samples': 13298688, 'steps': 69263, 'loss/train': 0.03839516267180443} 08/31/2021 01:43:07 - INFO - __main__ - Step 69265: {'lr': 0.00028562455095907394, 'samples': 13298880, 'steps': 69264, 'loss/train': 1.241572618484497} 08/31/2021 01:43:08 - INFO - __main__ - Step 69266: {'lr': 0.0002856192983617058, 'samples': 13299072, 'steps': 69265, 'loss/train': 1.6829500198364258} 08/31/2021 01:43:09 - INFO - __main__ - Step 69267: {'lr': 0.0002856140457482882, 'samples': 13299264, 'steps': 69266, 'loss/train': 1.0138384103775024} 08/31/2021 01:43:09 - INFO - __main__ - Step 69268: {'lr': 0.00028560879311882335, 'samples': 13299456, 'steps': 69267, 'loss/train': 1.3905998468399048} 08/31/2021 01:43:10 - INFO - __main__ - Step 69269: {'lr': 0.0002856035404733139, 'samples': 13299648, 'steps': 69268, 'loss/train': 1.399985671043396} 08/31/2021 01:43:10 - INFO - __main__ - Step 69270: {'lr': 0.00028559828781176197, 'samples': 13299840, 'steps': 69269, 'loss/train': 0.8746113181114197} 08/31/2021 01:43:11 - INFO - __main__ - Step 69271: {'lr': 0.00028559303513416993, 'samples': 13300032, 'steps': 69270, 'loss/train': 2.1724250316619873} 08/31/2021 01:43:12 - INFO - __main__ - Step 69272: {'lr': 0.00028558778244054027, 'samples': 13300224, 'steps': 69271, 'loss/train': 1.006085991859436} 08/31/2021 01:43:12 - INFO - __main__ - Step 69273: {'lr': 0.00028558252973087537, 'samples': 13300416, 'steps': 69272, 'loss/train': 0.9256826043128967} 08/31/2021 01:43:13 - INFO - __main__ - Step 69274: {'lr': 0.00028557727700517744, 'samples': 13300608, 'steps': 69273, 'loss/train': 1.3252973556518555} 08/31/2021 01:43:13 - INFO - __main__ - Step 69275: {'lr': 0.00028557202426344894, 'samples': 13300800, 'steps': 69274, 'loss/train': 1.5559202432632446} 08/31/2021 01:43:14 - INFO - __main__ - Step 69276: {'lr': 0.00028556677150569235, 'samples': 13300992, 'steps': 69275, 'loss/train': 1.0640015602111816} 08/31/2021 01:43:15 - INFO - __main__ - Step 69277: {'lr': 0.0002855615187319098, 'samples': 13301184, 'steps': 69276, 'loss/train': 1.1030808687210083} 08/31/2021 01:43:15 - INFO - __main__ - Step 69278: {'lr': 0.00028555626594210375, 'samples': 13301376, 'steps': 69277, 'loss/train': 1.2212833166122437} 08/31/2021 01:43:15 - INFO - __main__ - Step 69279: {'lr': 0.00028555101313627667, 'samples': 13301568, 'steps': 69278, 'loss/train': 1.1970258951187134} 08/31/2021 01:43:16 - INFO - __main__ - Step 69280: {'lr': 0.0002855457603144309, 'samples': 13301760, 'steps': 69279, 'loss/train': 1.3850483894348145} 08/31/2021 01:43:17 - INFO - __main__ - Step 69281: {'lr': 0.0002855405074765686, 'samples': 13301952, 'steps': 69280, 'loss/train': 1.417009949684143} 08/31/2021 01:43:18 - INFO - __main__ - Step 69282: {'lr': 0.00028553525462269246, 'samples': 13302144, 'steps': 69281, 'loss/train': 1.794687032699585} 08/31/2021 01:43:18 - INFO - __main__ - Step 69283: {'lr': 0.00028553000175280465, 'samples': 13302336, 'steps': 69282, 'loss/train': 0.5450864434242249} 08/31/2021 01:43:18 - INFO - __main__ - Step 69284: {'lr': 0.0002855247488669075, 'samples': 13302528, 'steps': 69283, 'loss/train': 1.4071056842803955} 08/31/2021 01:43:19 - INFO - __main__ - Step 69285: {'lr': 0.00028551949596500347, 'samples': 13302720, 'steps': 69284, 'loss/train': 0.9443320631980896} 08/31/2021 01:43:21 - INFO - __main__ - Step 69286: {'lr': 0.00028551424304709493, 'samples': 13302912, 'steps': 69285, 'loss/train': 0.9934136867523193} 08/31/2021 01:43:21 - INFO - __main__ - Step 69287: {'lr': 0.0002855089901131842, 'samples': 13303104, 'steps': 69286, 'loss/train': 1.2062464952468872} 08/31/2021 01:43:22 - INFO - __main__ - Step 69288: {'lr': 0.00028550373716327367, 'samples': 13303296, 'steps': 69287, 'loss/train': 0.7785606384277344} 08/31/2021 01:43:22 - INFO - __main__ - Step 69289: {'lr': 0.0002854984841973657, 'samples': 13303488, 'steps': 69288, 'loss/train': 1.2534589767456055} 08/31/2021 01:43:22 - INFO - __main__ - Step 69290: {'lr': 0.0002854932312154627, 'samples': 13303680, 'steps': 69289, 'loss/train': 1.1560221910476685} 08/31/2021 01:43:23 - INFO - __main__ - Step 69291: {'lr': 0.00028548797821756697, 'samples': 13303872, 'steps': 69290, 'loss/train': 1.2113797664642334} 08/31/2021 01:43:24 - INFO - __main__ - Step 69292: {'lr': 0.00028548272520368084, 'samples': 13304064, 'steps': 69291, 'loss/train': 0.6671143174171448} 08/31/2021 01:43:25 - INFO - __main__ - Step 69293: {'lr': 0.0002854774721738068, 'samples': 13304256, 'steps': 69292, 'loss/train': 1.0656770467758179} 08/31/2021 01:43:25 - INFO - __main__ - Step 69294: {'lr': 0.00028547221912794717, 'samples': 13304448, 'steps': 69293, 'loss/train': 1.8065582513809204} 08/31/2021 01:43:26 - INFO - __main__ - Step 69295: {'lr': 0.0002854669660661043, 'samples': 13304640, 'steps': 69294, 'loss/train': 0.6460257172584534} 08/31/2021 01:43:26 - INFO - __main__ - Step 69296: {'lr': 0.0002854617129882806, 'samples': 13304832, 'steps': 69295, 'loss/train': 0.9615085124969482} 08/31/2021 01:43:27 - INFO - __main__ - Step 69297: {'lr': 0.0002854564598944783, 'samples': 13305024, 'steps': 69296, 'loss/train': 1.0073589086532593} 08/31/2021 01:43:28 - INFO - __main__ - Step 69298: {'lr': 0.0002854512067846999, 'samples': 13305216, 'steps': 69297, 'loss/train': 1.7168242931365967} 08/31/2021 01:43:28 - INFO - __main__ - Step 69299: {'lr': 0.0002854459536589478, 'samples': 13305408, 'steps': 69298, 'loss/train': 0.8370617628097534} 08/31/2021 01:43:29 - INFO - __main__ - Step 69300: {'lr': 0.0002854407005172243, 'samples': 13305600, 'steps': 69299, 'loss/train': 1.0063207149505615} 08/31/2021 01:43:29 - INFO - __main__ - Step 69301: {'lr': 0.0002854354473595317, 'samples': 13305792, 'steps': 69300, 'loss/train': 1.393725037574768} 08/31/2021 01:43:31 - INFO - __main__ - Step 69302: {'lr': 0.0002854301941858724, 'samples': 13305984, 'steps': 69301, 'loss/train': 1.7713078260421753} 08/31/2021 01:43:31 - INFO - __main__ - Step 69303: {'lr': 0.00028542494099624896, 'samples': 13306176, 'steps': 69302, 'loss/train': 1.0608466863632202} 08/31/2021 01:43:31 - INFO - __main__ - Step 69304: {'lr': 0.0002854196877906635, 'samples': 13306368, 'steps': 69303, 'loss/train': 1.0067853927612305} 08/31/2021 01:43:32 - INFO - __main__ - Step 69305: {'lr': 0.00028541443456911843, 'samples': 13306560, 'steps': 69304, 'loss/train': 1.2961978912353516} 08/31/2021 01:43:32 - INFO - __main__ - Step 69306: {'lr': 0.0002854091813316162, 'samples': 13306752, 'steps': 69305, 'loss/train': 1.0665541887283325} 08/31/2021 01:43:33 - INFO - __main__ - Step 69307: {'lr': 0.0002854039280781591, 'samples': 13306944, 'steps': 69306, 'loss/train': 0.08399892598390579} 08/31/2021 01:43:34 - INFO - __main__ - Step 69308: {'lr': 0.00028539867480874954, 'samples': 13307136, 'steps': 69307, 'loss/train': 1.6583815813064575} 08/31/2021 01:43:34 - INFO - __main__ - Step 69309: {'lr': 0.00028539342152339, 'samples': 13307328, 'steps': 69308, 'loss/train': 1.8351348638534546} 08/31/2021 01:43:35 - INFO - __main__ - Step 69310: {'lr': 0.0002853881682220826, 'samples': 13307520, 'steps': 69309, 'loss/train': 1.4858763217926025} 08/31/2021 01:43:35 - INFO - __main__ - Step 69311: {'lr': 0.0002853829149048299, 'samples': 13307712, 'steps': 69310, 'loss/train': 2.7569079399108887} 08/31/2021 01:43:35 - INFO - __main__ - Step 69312: {'lr': 0.00028537766157163413, 'samples': 13307904, 'steps': 69311, 'loss/train': 0.8095908164978027} 08/31/2021 01:43:37 - INFO - __main__ - Step 69313: {'lr': 0.00028537240822249784, 'samples': 13308096, 'steps': 69312, 'loss/train': 0.8469929695129395} 08/31/2021 01:43:37 - INFO - __main__ - Step 69314: {'lr': 0.0002853671548574232, 'samples': 13308288, 'steps': 69313, 'loss/train': 0.6789662837982178} 08/31/2021 01:43:38 - INFO - __main__ - Step 69315: {'lr': 0.0002853619014764127, 'samples': 13308480, 'steps': 69314, 'loss/train': 0.2751725912094116} 08/31/2021 01:43:38 - INFO - __main__ - Step 69316: {'lr': 0.0002853566480794687, 'samples': 13308672, 'steps': 69315, 'loss/train': 1.6727489233016968} 08/31/2021 01:43:38 - INFO - __main__ - Step 69317: {'lr': 0.00028535139466659355, 'samples': 13308864, 'steps': 69316, 'loss/train': 1.2304143905639648} 08/31/2021 01:43:40 - INFO - __main__ - Step 69318: {'lr': 0.00028534614123778955, 'samples': 13309056, 'steps': 69317, 'loss/train': 1.6052933931350708} 08/31/2021 01:43:40 - INFO - __main__ - Step 69319: {'lr': 0.0002853408877930591, 'samples': 13309248, 'steps': 69318, 'loss/train': 0.9328069090843201} 08/31/2021 01:43:41 - INFO - __main__ - Step 69320: {'lr': 0.0002853356343324047, 'samples': 13309440, 'steps': 69319, 'loss/train': 1.3505868911743164} 08/31/2021 01:43:41 - INFO - __main__ - Step 69321: {'lr': 0.0002853303808558285, 'samples': 13309632, 'steps': 69320, 'loss/train': 1.3700711727142334} 08/31/2021 01:43:42 - INFO - __main__ - Step 69322: {'lr': 0.00028532512736333305, 'samples': 13309824, 'steps': 69321, 'loss/train': 0.038974251598119736} 08/31/2021 01:43:43 - INFO - __main__ - Step 69323: {'lr': 0.00028531987385492063, 'samples': 13310016, 'steps': 69322, 'loss/train': 1.1151282787322998} 08/31/2021 01:43:43 - INFO - __main__ - Step 69324: {'lr': 0.0002853146203305936, 'samples': 13310208, 'steps': 69323, 'loss/train': 1.8012120723724365} 08/31/2021 01:43:44 - INFO - __main__ - Step 69325: {'lr': 0.00028530936679035436, 'samples': 13310400, 'steps': 69324, 'loss/train': 1.6028425693511963} 08/31/2021 01:43:44 - INFO - __main__ - Step 69326: {'lr': 0.0002853041132342052, 'samples': 13310592, 'steps': 69325, 'loss/train': 1.9514063596725464} 08/31/2021 01:43:44 - INFO - __main__ - Step 69327: {'lr': 0.0002852988596621486, 'samples': 13310784, 'steps': 69326, 'loss/train': 1.1627850532531738} 08/31/2021 01:43:46 - INFO - __main__ - Step 69328: {'lr': 0.0002852936060741869, 'samples': 13310976, 'steps': 69327, 'loss/train': 1.0792596340179443} 08/31/2021 01:43:47 - INFO - __main__ - Step 69329: {'lr': 0.00028528835247032243, 'samples': 13311168, 'steps': 69328, 'loss/train': 2.158806324005127} 08/31/2021 01:43:47 - INFO - __main__ - Step 69330: {'lr': 0.0002852830988505576, 'samples': 13311360, 'steps': 69329, 'loss/train': 0.04473259299993515} 08/31/2021 01:43:47 - INFO - __main__ - Step 69331: {'lr': 0.0002852778452148947, 'samples': 13311552, 'steps': 69330, 'loss/train': 1.3013873100280762} 08/31/2021 01:43:48 - INFO - __main__ - Step 69332: {'lr': 0.0002852725915633362, 'samples': 13311744, 'steps': 69331, 'loss/train': 1.2971376180648804} 08/31/2021 01:43:49 - INFO - __main__ - Step 69333: {'lr': 0.00028526733789588436, 'samples': 13311936, 'steps': 69332, 'loss/train': 0.08029208332300186} 08/31/2021 01:43:50 - INFO - __main__ - Step 69334: {'lr': 0.0002852620842125416, 'samples': 13312128, 'steps': 69333, 'loss/train': 0.9651135802268982} 08/31/2021 01:43:50 - INFO - __main__ - Step 69335: {'lr': 0.00028525683051331037, 'samples': 13312320, 'steps': 69334, 'loss/train': 1.082176685333252} 08/31/2021 01:43:50 - INFO - __main__ - Step 69336: {'lr': 0.0002852515767981929, 'samples': 13312512, 'steps': 69335, 'loss/train': 0.9689358472824097} 08/31/2021 01:43:51 - INFO - __main__ - Step 69337: {'lr': 0.0002852463230671916, 'samples': 13312704, 'steps': 69336, 'loss/train': 1.398164987564087} 08/31/2021 01:43:51 - INFO - __main__ - Step 69338: {'lr': 0.0002852410693203089, 'samples': 13312896, 'steps': 69337, 'loss/train': 1.4321768283843994} 08/31/2021 01:43:53 - INFO - __main__ - Step 69339: {'lr': 0.00028523581555754706, 'samples': 13313088, 'steps': 69338, 'loss/train': 0.9747936725616455} 08/31/2021 01:43:53 - INFO - __main__ - Step 69340: {'lr': 0.0002852305617789085, 'samples': 13313280, 'steps': 69339, 'loss/train': 3.0141234397888184} 08/31/2021 01:43:53 - INFO - __main__ - Step 69341: {'lr': 0.00028522530798439564, 'samples': 13313472, 'steps': 69340, 'loss/train': 1.8214223384857178} 08/31/2021 01:43:54 - INFO - __main__ - Step 69342: {'lr': 0.00028522005417401075, 'samples': 13313664, 'steps': 69341, 'loss/train': 1.0572112798690796} 08/31/2021 01:43:54 - INFO - __main__ - Step 69343: {'lr': 0.0002852148003477564, 'samples': 13313856, 'steps': 69342, 'loss/train': 0.8154531717300415} 08/31/2021 01:43:56 - INFO - __main__ - Step 69344: {'lr': 0.0002852095465056346, 'samples': 13314048, 'steps': 69343, 'loss/train': 1.4261271953582764} 08/31/2021 01:43:57 - INFO - __main__ - Step 69345: {'lr': 0.00028520429264764803, 'samples': 13314240, 'steps': 69344, 'loss/train': 3.46885085105896} 08/31/2021 01:43:57 - INFO - __main__ - Step 69346: {'lr': 0.00028519903877379893, 'samples': 13314432, 'steps': 69345, 'loss/train': 0.825255274772644} 08/31/2021 01:43:58 - INFO - __main__ - Step 69347: {'lr': 0.0002851937848840896, 'samples': 13314624, 'steps': 69346, 'loss/train': 0.864661693572998} 08/31/2021 01:43:58 - INFO - __main__ - Step 69348: {'lr': 0.0002851885309785227, 'samples': 13314816, 'steps': 69347, 'loss/train': 1.4608840942382812} 08/31/2021 01:43:58 - INFO - __main__ - Step 69349: {'lr': 0.0002851832770571002, 'samples': 13315008, 'steps': 69348, 'loss/train': 1.0230993032455444} 08/31/2021 01:44:00 - INFO - __main__ - Step 69350: {'lr': 0.00028517802311982477, 'samples': 13315200, 'steps': 69349, 'loss/train': 1.8471380472183228} 08/31/2021 01:44:00 - INFO - __main__ - Step 69351: {'lr': 0.0002851727691666986, 'samples': 13315392, 'steps': 69350, 'loss/train': 1.3599085807800293} 08/31/2021 01:44:01 - INFO - __main__ - Step 69352: {'lr': 0.0002851675151977242, 'samples': 13315584, 'steps': 69351, 'loss/train': 1.282123327255249} 08/31/2021 01:44:01 - INFO - __main__ - Step 69353: {'lr': 0.00028516226121290373, 'samples': 13315776, 'steps': 69352, 'loss/train': 0.8091922998428345} 08/31/2021 01:44:01 - INFO - __main__ - Step 69354: {'lr': 0.0002851570072122397, 'samples': 13315968, 'steps': 69353, 'loss/train': 1.35909104347229} 08/31/2021 01:44:03 - INFO - __main__ - Step 69355: {'lr': 0.0002851517531957346, 'samples': 13316160, 'steps': 69354, 'loss/train': 1.3038926124572754} 08/31/2021 01:44:03 - INFO - __main__ - Step 69356: {'lr': 0.00028514649916339065, 'samples': 13316352, 'steps': 69355, 'loss/train': 1.6898090839385986} 08/31/2021 01:44:04 - INFO - __main__ - Step 69357: {'lr': 0.0002851412451152101, 'samples': 13316544, 'steps': 69356, 'loss/train': 1.9967865943908691} 08/31/2021 01:44:04 - INFO - __main__ - Step 69358: {'lr': 0.00028513599105119554, 'samples': 13316736, 'steps': 69357, 'loss/train': 1.7059977054595947} 08/31/2021 01:44:05 - INFO - __main__ - Step 69359: {'lr': 0.0002851307369713492, 'samples': 13316928, 'steps': 69358, 'loss/train': 0.5676969289779663} 08/31/2021 01:44:05 - INFO - __main__ - Step 69360: {'lr': 0.00028512548287567353, 'samples': 13317120, 'steps': 69359, 'loss/train': 1.3591058254241943} 08/31/2021 01:44:06 - INFO - __main__ - Step 69361: {'lr': 0.0002851202287641709, 'samples': 13317312, 'steps': 69360, 'loss/train': 1.4742509126663208} 08/31/2021 01:44:07 - INFO - __main__ - Step 69362: {'lr': 0.00028511497463684356, 'samples': 13317504, 'steps': 69361, 'loss/train': 1.9103044271469116} 08/31/2021 01:44:07 - INFO - __main__ - Step 69363: {'lr': 0.0002851097204936939, 'samples': 13317696, 'steps': 69362, 'loss/train': 1.2954787015914917} 08/31/2021 01:44:08 - INFO - __main__ - Step 69364: {'lr': 0.0002851044663347244, 'samples': 13317888, 'steps': 69363, 'loss/train': 1.5962992906570435} 08/31/2021 01:44:08 - INFO - __main__ - Step 69365: {'lr': 0.0002850992121599374, 'samples': 13318080, 'steps': 69364, 'loss/train': 1.416143536567688} 08/31/2021 01:44:09 - INFO - __main__ - Step 69366: {'lr': 0.0002850939579693353, 'samples': 13318272, 'steps': 69365, 'loss/train': 1.905125617980957} 08/31/2021 01:44:10 - INFO - __main__ - Step 69367: {'lr': 0.0002850887037629203, 'samples': 13318464, 'steps': 69366, 'loss/train': 1.2876008749008179} 08/31/2021 01:44:10 - INFO - __main__ - Step 69368: {'lr': 0.00028508344954069487, 'samples': 13318656, 'steps': 69367, 'loss/train': 1.387712001800537} 08/31/2021 01:44:11 - INFO - __main__ - Step 69369: {'lr': 0.00028507819530266144, 'samples': 13318848, 'steps': 69368, 'loss/train': 1.3755148649215698} 08/31/2021 01:44:11 - INFO - __main__ - Step 69370: {'lr': 0.00028507294104882224, 'samples': 13319040, 'steps': 69369, 'loss/train': 0.1602877527475357} 08/31/2021 01:44:13 - INFO - __main__ - Step 69371: {'lr': 0.00028506768677917976, 'samples': 13319232, 'steps': 69370, 'loss/train': 0.07451887428760529} 08/31/2021 01:44:13 - INFO - __main__ - Step 69372: {'lr': 0.00028506243249373634, 'samples': 13319424, 'steps': 69371, 'loss/train': 1.7823102474212646} 08/31/2021 01:44:14 - INFO - __main__ - Step 69373: {'lr': 0.0002850571781924943, 'samples': 13319616, 'steps': 69372, 'loss/train': 1.7030304670333862} 08/31/2021 01:44:14 - INFO - __main__ - Step 69374: {'lr': 0.00028505192387545604, 'samples': 13319808, 'steps': 69373, 'loss/train': 1.694132924079895} 08/31/2021 01:44:14 - INFO - __main__ - Step 69375: {'lr': 0.00028504666954262393, 'samples': 13320000, 'steps': 69374, 'loss/train': 1.9395103454589844} 08/31/2021 01:44:16 - INFO - __main__ - Step 69376: {'lr': 0.00028504141519400037, 'samples': 13320192, 'steps': 69375, 'loss/train': 1.34749174118042} 08/31/2021 01:44:16 - INFO - __main__ - Step 69377: {'lr': 0.00028503616082958767, 'samples': 13320384, 'steps': 69376, 'loss/train': 1.6566383838653564} 08/31/2021 01:44:17 - INFO - __main__ - Step 69378: {'lr': 0.0002850309064493882, 'samples': 13320576, 'steps': 69377, 'loss/train': 0.6402542591094971} 08/31/2021 01:44:17 - INFO - __main__ - Step 69379: {'lr': 0.00028502565205340433, 'samples': 13320768, 'steps': 69378, 'loss/train': 0.15804998576641083} 08/31/2021 01:44:17 - INFO - __main__ - Step 69380: {'lr': 0.0002850203976416384, 'samples': 13320960, 'steps': 69379, 'loss/train': 1.2291784286499023} 08/31/2021 01:44:19 - INFO - __main__ - Step 69381: {'lr': 0.00028501514321409283, 'samples': 13321152, 'steps': 69380, 'loss/train': 1.298554539680481} 08/31/2021 01:44:19 - INFO - __main__ - Step 69382: {'lr': 0.00028500988877077006, 'samples': 13321344, 'steps': 69381, 'loss/train': 1.0581679344177246} 08/31/2021 01:44:20 - INFO - __main__ - Step 69383: {'lr': 0.00028500463431167236, 'samples': 13321536, 'steps': 69382, 'loss/train': 1.69014573097229} 08/31/2021 01:44:20 - INFO - __main__ - Step 69384: {'lr': 0.00028499937983680207, 'samples': 13321728, 'steps': 69383, 'loss/train': 1.2611677646636963} 08/31/2021 01:44:20 - INFO - __main__ - Step 69385: {'lr': 0.00028499412534616157, 'samples': 13321920, 'steps': 69384, 'loss/train': 1.3542821407318115} 08/31/2021 01:44:22 - INFO - __main__ - Step 69386: {'lr': 0.00028498887083975335, 'samples': 13322112, 'steps': 69385, 'loss/train': 1.264596939086914} 08/31/2021 01:44:22 - INFO - __main__ - Step 69387: {'lr': 0.0002849836163175796, 'samples': 13322304, 'steps': 69386, 'loss/train': 0.852975070476532} 08/31/2021 01:44:23 - INFO - __main__ - Step 69388: {'lr': 0.0002849783617796428, 'samples': 13322496, 'steps': 69387, 'loss/train': 0.8571876883506775} 08/31/2021 01:44:23 - INFO - __main__ - Step 69389: {'lr': 0.0002849731072259453, 'samples': 13322688, 'steps': 69388, 'loss/train': 1.4557143449783325} 08/31/2021 01:44:23 - INFO - __main__ - Step 69390: {'lr': 0.0002849678526564895, 'samples': 13322880, 'steps': 69389, 'loss/train': 1.2765929698944092} 08/31/2021 01:44:25 - INFO - __main__ - Step 69391: {'lr': 0.00028496259807127766, 'samples': 13323072, 'steps': 69390, 'loss/train': 1.9725313186645508} 08/31/2021 01:44:26 - INFO - __main__ - Step 69392: {'lr': 0.0002849573434703122, 'samples': 13323264, 'steps': 69391, 'loss/train': 1.7555108070373535} 08/31/2021 01:44:26 - INFO - __main__ - Step 69393: {'lr': 0.00028495208885359553, 'samples': 13323456, 'steps': 69392, 'loss/train': 1.2201685905456543} 08/31/2021 01:44:26 - INFO - __main__ - Step 69394: {'lr': 0.00028494683422113, 'samples': 13323648, 'steps': 69393, 'loss/train': 1.3562055826187134} 08/31/2021 01:44:27 - INFO - __main__ - Step 69395: {'lr': 0.00028494157957291796, 'samples': 13323840, 'steps': 69394, 'loss/train': 1.3144451379776} 08/31/2021 01:44:29 - INFO - __main__ - Step 69396: {'lr': 0.0002849363249089617, 'samples': 13324032, 'steps': 69395, 'loss/train': 1.0813472270965576} 08/31/2021 01:44:29 - INFO - __main__ - Step 69397: {'lr': 0.00028493107022926385, 'samples': 13324224, 'steps': 69396, 'loss/train': 1.5332697629928589} 08/31/2021 01:44:29 - INFO - __main__ - Step 69398: {'lr': 0.00028492581553382645, 'samples': 13324416, 'steps': 69397, 'loss/train': 1.5490108728408813} 08/31/2021 01:44:30 - INFO - __main__ - Step 69399: {'lr': 0.0002849205608226521, 'samples': 13324608, 'steps': 69398, 'loss/train': 1.2791932821273804} 08/31/2021 01:44:30 - INFO - __main__ - Step 69400: {'lr': 0.000284915306095743, 'samples': 13324800, 'steps': 69399, 'loss/train': 0.829836905002594} 08/31/2021 01:44:31 - INFO - __main__ - Step 69401: {'lr': 0.00028491005135310166, 'samples': 13324992, 'steps': 69400, 'loss/train': 1.3709455728530884} 08/31/2021 01:44:32 - INFO - __main__ - Step 69402: {'lr': 0.00028490479659473033, 'samples': 13325184, 'steps': 69401, 'loss/train': 1.6687490940093994} 08/31/2021 01:44:32 - INFO - __main__ - Step 69403: {'lr': 0.0002848995418206316, 'samples': 13325376, 'steps': 69402, 'loss/train': 1.514037847518921} 08/31/2021 01:44:33 - INFO - __main__ - Step 69404: {'lr': 0.00028489428703080754, 'samples': 13325568, 'steps': 69403, 'loss/train': 0.9105343818664551} 08/31/2021 01:44:33 - INFO - __main__ - Step 69405: {'lr': 0.00028488903222526063, 'samples': 13325760, 'steps': 69404, 'loss/train': 1.2580446004867554} 08/31/2021 01:44:35 - INFO - __main__ - Step 69406: {'lr': 0.0002848837774039933, 'samples': 13325952, 'steps': 69405, 'loss/train': 1.3190574645996094} 08/31/2021 01:44:35 - INFO - __main__ - Step 69407: {'lr': 0.0002848785225670079, 'samples': 13326144, 'steps': 69406, 'loss/train': 1.7456177473068237} 08/31/2021 01:44:35 - INFO - __main__ - Step 69408: {'lr': 0.00028487326771430677, 'samples': 13326336, 'steps': 69407, 'loss/train': 1.571697473526001} 08/31/2021 01:44:36 - INFO - __main__ - Step 69409: {'lr': 0.00028486801284589223, 'samples': 13326528, 'steps': 69408, 'loss/train': 1.3362518548965454} 08/31/2021 01:44:36 - INFO - __main__ - Step 69410: {'lr': 0.0002848627579617668, 'samples': 13326720, 'steps': 69409, 'loss/train': 1.6830639839172363} 08/31/2021 01:44:36 - INFO - __main__ - Step 69411: {'lr': 0.0002848575030619327, 'samples': 13326912, 'steps': 69410, 'loss/train': 1.3567049503326416} 08/31/2021 01:44:38 - INFO - __main__ - Step 69412: {'lr': 0.0002848522481463923, 'samples': 13327104, 'steps': 69411, 'loss/train': 1.3910223245620728} 08/31/2021 01:44:38 - INFO - __main__ - Step 69413: {'lr': 0.00028484699321514804, 'samples': 13327296, 'steps': 69412, 'loss/train': 5.788909912109375} 08/31/2021 01:44:39 - INFO - __main__ - Step 69414: {'lr': 0.0002848417382682023, 'samples': 13327488, 'steps': 69413, 'loss/train': 1.1058343648910522} 08/31/2021 01:44:39 - INFO - __main__ - Step 69415: {'lr': 0.00028483648330555737, 'samples': 13327680, 'steps': 69414, 'loss/train': 1.7830638885498047} 08/31/2021 01:44:40 - INFO - __main__ - Step 69416: {'lr': 0.0002848312283272157, 'samples': 13327872, 'steps': 69415, 'loss/train': 1.4624545574188232} 08/31/2021 01:44:41 - INFO - __main__ - Step 69417: {'lr': 0.0002848259733331796, 'samples': 13328064, 'steps': 69416, 'loss/train': 1.4255298376083374} 08/31/2021 01:44:41 - INFO - __main__ - Step 69418: {'lr': 0.0002848207183234515, 'samples': 13328256, 'steps': 69417, 'loss/train': 1.172734022140503} 08/31/2021 01:44:42 - INFO - __main__ - Step 69419: {'lr': 0.0002848154632980337, 'samples': 13328448, 'steps': 69418, 'loss/train': 1.2558326721191406} 08/31/2021 01:44:42 - INFO - __main__ - Step 69420: {'lr': 0.0002848102082569285, 'samples': 13328640, 'steps': 69419, 'loss/train': 0.9832043051719666} 08/31/2021 01:44:43 - INFO - __main__ - Step 69421: {'lr': 0.0002848049532001384, 'samples': 13328832, 'steps': 69420, 'loss/train': 0.4071460962295532} 08/31/2021 01:44:44 - INFO - __main__ - Step 69422: {'lr': 0.0002847996981276657, 'samples': 13329024, 'steps': 69421, 'loss/train': 1.3087859153747559} 08/31/2021 01:44:44 - INFO - __main__ - Step 69423: {'lr': 0.00028479444303951284, 'samples': 13329216, 'steps': 69422, 'loss/train': 1.058510184288025} 08/31/2021 01:44:45 - INFO - __main__ - Step 69424: {'lr': 0.0002847891879356822, 'samples': 13329408, 'steps': 69423, 'loss/train': 0.08935584872961044} 08/31/2021 01:44:45 - INFO - __main__ - Step 69425: {'lr': 0.00028478393281617596, 'samples': 13329600, 'steps': 69424, 'loss/train': 1.9103760719299316} 08/31/2021 01:44:45 - INFO - __main__ - Step 69426: {'lr': 0.0002847786776809967, 'samples': 13329792, 'steps': 69425, 'loss/train': 0.6891043782234192} 08/31/2021 01:44:47 - INFO - __main__ - Step 69427: {'lr': 0.0002847734225301467, 'samples': 13329984, 'steps': 69426, 'loss/train': 0.9857739806175232} 08/31/2021 01:44:48 - INFO - __main__ - Step 69428: {'lr': 0.0002847681673636283, 'samples': 13330176, 'steps': 69427, 'loss/train': 1.2318992614746094} 08/31/2021 01:44:48 - INFO - __main__ - Step 69429: {'lr': 0.0002847629121814439, 'samples': 13330368, 'steps': 69428, 'loss/train': 1.2522871494293213} 08/31/2021 01:44:48 - INFO - __main__ - Step 69430: {'lr': 0.0002847576569835959, 'samples': 13330560, 'steps': 69429, 'loss/train': 1.0440443754196167} 08/31/2021 01:44:49 - INFO - __main__ - Step 69431: {'lr': 0.00028475240177008664, 'samples': 13330752, 'steps': 69430, 'loss/train': 1.48428475856781} 08/31/2021 01:44:49 - INFO - __main__ - Step 69432: {'lr': 0.0002847471465409184, 'samples': 13330944, 'steps': 69431, 'loss/train': 1.493818759918213} 08/31/2021 01:44:51 - INFO - __main__ - Step 69433: {'lr': 0.0002847418912960937, 'samples': 13331136, 'steps': 69432, 'loss/train': 1.66157066822052} 08/31/2021 01:44:51 - INFO - __main__ - Step 69434: {'lr': 0.0002847366360356149, 'samples': 13331328, 'steps': 69433, 'loss/train': 1.1199147701263428} 08/31/2021 01:44:52 - INFO - __main__ - Step 69435: {'lr': 0.00028473138075948425, 'samples': 13331520, 'steps': 69434, 'loss/train': 1.4235910177230835} 08/31/2021 01:44:52 - INFO - __main__ - Step 69436: {'lr': 0.0002847261254677041, 'samples': 13331712, 'steps': 69435, 'loss/train': 1.4849953651428223} 08/31/2021 01:44:52 - INFO - __main__ - Step 69437: {'lr': 0.00028472087016027703, 'samples': 13331904, 'steps': 69436, 'loss/train': 1.5646201372146606} 08/31/2021 01:44:53 - INFO - __main__ - Step 69438: {'lr': 0.0002847156148372052, 'samples': 13332096, 'steps': 69437, 'loss/train': 0.05882516875863075} 08/31/2021 01:44:54 - INFO - __main__ - Step 69439: {'lr': 0.00028471035949849106, 'samples': 13332288, 'steps': 69438, 'loss/train': 0.10772015899419785} 08/31/2021 01:44:55 - INFO - __main__ - Step 69440: {'lr': 0.00028470510414413695, 'samples': 13332480, 'steps': 69439, 'loss/train': 1.0560981035232544} 08/31/2021 01:44:55 - INFO - __main__ - Step 69441: {'lr': 0.0002846998487741452, 'samples': 13332672, 'steps': 69440, 'loss/train': 1.5897676944732666} 08/31/2021 01:44:55 - INFO - __main__ - Step 69442: {'lr': 0.00028469459338851833, 'samples': 13332864, 'steps': 69441, 'loss/train': 1.3907026052474976} 08/31/2021 01:44:56 - INFO - __main__ - Step 69443: {'lr': 0.0002846893379872586, 'samples': 13333056, 'steps': 69442, 'loss/train': 1.6242297887802124} 08/31/2021 01:44:57 - INFO - __main__ - Step 69444: {'lr': 0.0002846840825703684, 'samples': 13333248, 'steps': 69443, 'loss/train': 1.0983421802520752} 08/31/2021 01:44:58 - INFO - __main__ - Step 69445: {'lr': 0.0002846788271378501, 'samples': 13333440, 'steps': 69444, 'loss/train': 0.030025796964764595} 08/31/2021 01:44:58 - INFO - __main__ - Step 69446: {'lr': 0.000284673571689706, 'samples': 13333632, 'steps': 69445, 'loss/train': 1.9182260036468506} 08/31/2021 01:44:58 - INFO - __main__ - Step 69447: {'lr': 0.0002846683162259385, 'samples': 13333824, 'steps': 69446, 'loss/train': 1.3504124879837036} 08/31/2021 01:44:59 - INFO - __main__ - Step 69448: {'lr': 0.00028466306074655004, 'samples': 13334016, 'steps': 69447, 'loss/train': 1.8476784229278564} 08/31/2021 01:45:01 - INFO - __main__ - Step 69449: {'lr': 0.00028465780525154297, 'samples': 13334208, 'steps': 69448, 'loss/train': 0.8284099698066711} 08/31/2021 01:45:02 - INFO - __main__ - Step 69450: {'lr': 0.00028465254974091955, 'samples': 13334400, 'steps': 69449, 'loss/train': 1.594618797302246} 08/31/2021 01:45:02 - INFO - __main__ - Step 69451: {'lr': 0.00028464729421468225, 'samples': 13334592, 'steps': 69450, 'loss/train': 1.591100811958313} 08/31/2021 01:45:02 - INFO - __main__ - Step 69452: {'lr': 0.0002846420386728334, 'samples': 13334784, 'steps': 69451, 'loss/train': 0.596708357334137} 08/31/2021 01:45:03 - INFO - __main__ - Step 69453: {'lr': 0.00028463678311537545, 'samples': 13334976, 'steps': 69452, 'loss/train': 0.029572345316410065} 08/31/2021 01:45:03 - INFO - __main__ - Step 69454: {'lr': 0.00028463152754231065, 'samples': 13335168, 'steps': 69453, 'loss/train': 1.4137178659439087} 08/31/2021 01:45:04 - INFO - __main__ - Step 69455: {'lr': 0.0002846262719536414, 'samples': 13335360, 'steps': 69454, 'loss/train': 1.7967488765716553} 08/31/2021 01:45:05 - INFO - __main__ - Step 69456: {'lr': 0.00028462101634937014, 'samples': 13335552, 'steps': 69455, 'loss/train': 1.2380905151367188} 08/31/2021 01:45:05 - INFO - __main__ - Step 69457: {'lr': 0.00028461576072949925, 'samples': 13335744, 'steps': 69456, 'loss/train': 1.3570889234542847} 08/31/2021 01:45:06 - INFO - __main__ - Step 69458: {'lr': 0.0002846105050940309, 'samples': 13335936, 'steps': 69457, 'loss/train': 0.7565982937812805} 08/31/2021 01:45:06 - INFO - __main__ - Step 69459: {'lr': 0.00028460524944296764, 'samples': 13336128, 'steps': 69458, 'loss/train': 0.9613208770751953} 08/31/2021 01:45:07 - INFO - __main__ - Step 69460: {'lr': 0.00028459999377631175, 'samples': 13336320, 'steps': 69459, 'loss/train': 1.5025734901428223} 08/31/2021 01:45:08 - INFO - __main__ - Step 69461: {'lr': 0.0002845947380940657, 'samples': 13336512, 'steps': 69460, 'loss/train': 0.459683358669281} 08/31/2021 01:45:08 - INFO - __main__ - Step 69462: {'lr': 0.0002845894823962317, 'samples': 13336704, 'steps': 69461, 'loss/train': 0.9982460141181946} 08/31/2021 01:45:09 - INFO - __main__ - Step 69463: {'lr': 0.0002845842266828123, 'samples': 13336896, 'steps': 69462, 'loss/train': 0.8161441087722778} 08/31/2021 01:45:09 - INFO - __main__ - Step 69464: {'lr': 0.0002845789709538098, 'samples': 13337088, 'steps': 69463, 'loss/train': 1.316896915435791} 08/31/2021 01:45:11 - INFO - __main__ - Step 69465: {'lr': 0.00028457371520922647, 'samples': 13337280, 'steps': 69464, 'loss/train': 1.1255022287368774} 08/31/2021 01:45:11 - INFO - __main__ - Step 69466: {'lr': 0.0002845684594490648, 'samples': 13337472, 'steps': 69465, 'loss/train': 1.1322436332702637} 08/31/2021 01:45:11 - INFO - __main__ - Step 69467: {'lr': 0.0002845632036733271, 'samples': 13337664, 'steps': 69466, 'loss/train': 0.6896535754203796} 08/31/2021 01:45:12 - INFO - __main__ - Step 69468: {'lr': 0.0002845579478820158, 'samples': 13337856, 'steps': 69467, 'loss/train': 1.387115716934204} 08/31/2021 01:45:12 - INFO - __main__ - Step 69469: {'lr': 0.00028455269207513313, 'samples': 13338048, 'steps': 69468, 'loss/train': 1.9962124824523926} 08/31/2021 01:45:14 - INFO - __main__ - Step 69470: {'lr': 0.0002845474362526816, 'samples': 13338240, 'steps': 69469, 'loss/train': 1.1042336225509644} 08/31/2021 01:45:14 - INFO - __main__ - Step 69471: {'lr': 0.00028454218041466356, 'samples': 13338432, 'steps': 69470, 'loss/train': 2.6564366817474365} 08/31/2021 01:45:14 - INFO - __main__ - Step 69472: {'lr': 0.00028453692456108134, 'samples': 13338624, 'steps': 69471, 'loss/train': 1.1589421033859253} 08/31/2021 01:45:15 - INFO - __main__ - Step 69473: {'lr': 0.00028453166869193725, 'samples': 13338816, 'steps': 69472, 'loss/train': 1.802948236465454} 08/31/2021 01:45:15 - INFO - __main__ - Step 69474: {'lr': 0.00028452641280723377, 'samples': 13339008, 'steps': 69473, 'loss/train': 1.4703713655471802} 08/31/2021 01:45:16 - INFO - __main__ - Step 69475: {'lr': 0.00028452115690697324, 'samples': 13339200, 'steps': 69474, 'loss/train': 1.1374497413635254} 08/31/2021 01:45:17 - INFO - __main__ - Step 69476: {'lr': 0.000284515900991158, 'samples': 13339392, 'steps': 69475, 'loss/train': 1.1902101039886475} 08/31/2021 01:45:18 - INFO - __main__ - Step 69477: {'lr': 0.0002845106450597904, 'samples': 13339584, 'steps': 69476, 'loss/train': 2.042433738708496} 08/31/2021 01:45:18 - INFO - __main__ - Step 69478: {'lr': 0.0002845053891128729, 'samples': 13339776, 'steps': 69477, 'loss/train': 1.3421809673309326} 08/31/2021 01:45:18 - INFO - __main__ - Step 69479: {'lr': 0.0002845001331504077, 'samples': 13339968, 'steps': 69478, 'loss/train': 1.1859867572784424} 08/31/2021 01:45:19 - INFO - __main__ - Step 69480: {'lr': 0.00028449487717239737, 'samples': 13340160, 'steps': 69479, 'loss/train': 0.9196860790252686} 08/31/2021 01:45:20 - INFO - __main__ - Step 69481: {'lr': 0.00028448962117884406, 'samples': 13340352, 'steps': 69480, 'loss/train': 1.475538730621338} 08/31/2021 01:45:21 - INFO - __main__ - Step 69482: {'lr': 0.00028448436516975034, 'samples': 13340544, 'steps': 69481, 'loss/train': 0.1529434621334076} 08/31/2021 01:45:21 - INFO - __main__ - Step 69483: {'lr': 0.00028447910914511853, 'samples': 13340736, 'steps': 69482, 'loss/train': 0.5635127425193787} 08/31/2021 01:45:21 - INFO - __main__ - Step 69484: {'lr': 0.0002844738531049509, 'samples': 13340928, 'steps': 69483, 'loss/train': 1.2468631267547607} 08/31/2021 01:45:22 - INFO - __main__ - Step 69485: {'lr': 0.00028446859704925, 'samples': 13341120, 'steps': 69484, 'loss/train': 2.3066065311431885} 08/31/2021 01:45:23 - INFO - __main__ - Step 69486: {'lr': 0.00028446334097801795, 'samples': 13341312, 'steps': 69485, 'loss/train': 0.935088038444519} 08/31/2021 01:45:24 - INFO - __main__ - Step 69487: {'lr': 0.0002844580848912573, 'samples': 13341504, 'steps': 69486, 'loss/train': 1.4775009155273438} 08/31/2021 01:45:24 - INFO - __main__ - Step 69488: {'lr': 0.0002844528287889703, 'samples': 13341696, 'steps': 69487, 'loss/train': 0.9599565863609314} 08/31/2021 01:45:24 - INFO - __main__ - Step 69489: {'lr': 0.0002844475726711595, 'samples': 13341888, 'steps': 69488, 'loss/train': 1.1090301275253296} 08/31/2021 01:45:25 - INFO - __main__ - Step 69490: {'lr': 0.00028444231653782713, 'samples': 13342080, 'steps': 69489, 'loss/train': 1.9364253282546997} 08/31/2021 01:45:25 - INFO - __main__ - Step 69491: {'lr': 0.0002844370603889755, 'samples': 13342272, 'steps': 69490, 'loss/train': 1.222141146659851} 08/31/2021 01:45:27 - INFO - __main__ - Step 69492: {'lr': 0.0002844318042246072, 'samples': 13342464, 'steps': 69491, 'loss/train': 1.812094807624817} 08/31/2021 01:45:27 - INFO - __main__ - Step 69493: {'lr': 0.00028442654804472435, 'samples': 13342656, 'steps': 69492, 'loss/train': 0.9841757416725159} 08/31/2021 01:45:27 - INFO - __main__ - Step 69494: {'lr': 0.00028442129184932946, 'samples': 13342848, 'steps': 69493, 'loss/train': 1.3795899152755737} 08/31/2021 01:45:28 - INFO - __main__ - Step 69495: {'lr': 0.00028441603563842495, 'samples': 13343040, 'steps': 69494, 'loss/train': 1.0671154260635376} 08/31/2021 01:45:28 - INFO - __main__ - Step 69496: {'lr': 0.000284410779412013, 'samples': 13343232, 'steps': 69495, 'loss/train': 1.473993182182312} 08/31/2021 01:45:30 - INFO - __main__ - Step 69497: {'lr': 0.0002844055231700961, 'samples': 13343424, 'steps': 69496, 'loss/train': 0.7377057075500488} 08/31/2021 01:45:30 - INFO - __main__ - Step 69498: {'lr': 0.0002844002669126766, 'samples': 13343616, 'steps': 69497, 'loss/train': 1.1664108037948608} 08/31/2021 01:45:31 - INFO - __main__ - Step 69499: {'lr': 0.0002843950106397569, 'samples': 13343808, 'steps': 69498, 'loss/train': 1.1864080429077148} 08/31/2021 01:45:31 - INFO - __main__ - Step 69500: {'lr': 0.0002843897543513393, 'samples': 13344000, 'steps': 69499, 'loss/train': 0.04452569782733917} 08/31/2021 01:45:31 - INFO - __main__ - Step 69501: {'lr': 0.00028438449804742626, 'samples': 13344192, 'steps': 69500, 'loss/train': 1.3681141138076782} 08/31/2021 01:45:33 - INFO - __main__ - Step 69502: {'lr': 0.00028437924172802006, 'samples': 13344384, 'steps': 69501, 'loss/train': 1.1992443799972534} 08/31/2021 01:45:33 - INFO - __main__ - Step 69503: {'lr': 0.0002843739853931231, 'samples': 13344576, 'steps': 69502, 'loss/train': 0.607943594455719} 08/31/2021 01:45:34 - INFO - __main__ - Step 69504: {'lr': 0.00028436872904273776, 'samples': 13344768, 'steps': 69503, 'loss/train': 0.4701595902442932} 08/31/2021 01:45:34 - INFO - __main__ - Step 69505: {'lr': 0.00028436347267686633, 'samples': 13344960, 'steps': 69504, 'loss/train': 1.1750714778900146} 08/31/2021 01:45:34 - INFO - __main__ - Step 69506: {'lr': 0.0002843582162955114, 'samples': 13345152, 'steps': 69505, 'loss/train': 1.0794918537139893} 08/31/2021 01:45:36 - INFO - __main__ - Step 69507: {'lr': 0.0002843529598986751, 'samples': 13345344, 'steps': 69506, 'loss/train': 1.4897661209106445} 08/31/2021 01:45:37 - INFO - __main__ - Step 69508: {'lr': 0.0002843477034863599, 'samples': 13345536, 'steps': 69507, 'loss/train': 0.34374427795410156} 08/31/2021 01:45:37 - INFO - __main__ - Step 69509: {'lr': 0.00028434244705856815, 'samples': 13345728, 'steps': 69508, 'loss/train': 1.3872355222702026} 08/31/2021 01:45:38 - INFO - __main__ - Step 69510: {'lr': 0.00028433719061530215, 'samples': 13345920, 'steps': 69509, 'loss/train': 1.0508240461349487} 08/31/2021 01:45:38 - INFO - __main__ - Step 69511: {'lr': 0.00028433193415656447, 'samples': 13346112, 'steps': 69510, 'loss/train': 1.2692757844924927} 08/31/2021 01:45:39 - INFO - __main__ - Step 69512: {'lr': 0.00028432667768235734, 'samples': 13346304, 'steps': 69511, 'loss/train': 1.4977682828903198} 08/31/2021 01:45:40 - INFO - __main__ - Step 69513: {'lr': 0.0002843214211926831, 'samples': 13346496, 'steps': 69512, 'loss/train': 0.7937774062156677} 08/31/2021 01:45:40 - INFO - __main__ - Step 69514: {'lr': 0.0002843161646875441, 'samples': 13346688, 'steps': 69513, 'loss/train': 1.3471779823303223} 08/31/2021 01:45:41 - INFO - __main__ - Step 69515: {'lr': 0.0002843109081669428, 'samples': 13346880, 'steps': 69514, 'loss/train': 1.253235936164856} 08/31/2021 01:45:41 - INFO - __main__ - Step 69516: {'lr': 0.0002843056516308816, 'samples': 13347072, 'steps': 69515, 'loss/train': 2.3026347160339355} 08/31/2021 01:45:43 - INFO - __main__ - Step 69517: {'lr': 0.00028430039507936275, 'samples': 13347264, 'steps': 69516, 'loss/train': 0.8623945713043213} 08/31/2021 01:45:43 - INFO - __main__ - Step 69518: {'lr': 0.0002842951385123887, 'samples': 13347456, 'steps': 69517, 'loss/train': 1.047446846961975} 08/31/2021 01:45:44 - INFO - __main__ - Step 69519: {'lr': 0.00028428988192996175, 'samples': 13347648, 'steps': 69518, 'loss/train': 1.524829626083374} 08/31/2021 01:45:44 - INFO - __main__ - Step 69520: {'lr': 0.00028428462533208434, 'samples': 13347840, 'steps': 69519, 'loss/train': 1.6327279806137085} 08/31/2021 01:45:44 - INFO - __main__ - Step 69521: {'lr': 0.0002842793687187588, 'samples': 13348032, 'steps': 69520, 'loss/train': 0.023410305380821228} 08/31/2021 01:45:45 - INFO - __main__ - Step 69522: {'lr': 0.00028427411208998746, 'samples': 13348224, 'steps': 69521, 'loss/train': 1.041872501373291} 08/31/2021 01:45:45 - INFO - __main__ - Step 69523: {'lr': 0.00028426885544577277, 'samples': 13348416, 'steps': 69522, 'loss/train': 0.5013735890388489} 08/31/2021 01:45:46 - INFO - __main__ - Step 69524: {'lr': 0.0002842635987861171, 'samples': 13348608, 'steps': 69523, 'loss/train': 1.2131990194320679} 08/31/2021 01:45:47 - INFO - __main__ - Step 69525: {'lr': 0.0002842583421110227, 'samples': 13348800, 'steps': 69524, 'loss/train': 0.7522966861724854} 08/31/2021 01:45:47 - INFO - __main__ - Step 69526: {'lr': 0.00028425308542049207, 'samples': 13348992, 'steps': 69525, 'loss/train': 1.571132779121399} 08/31/2021 01:45:48 - INFO - __main__ - Step 69527: {'lr': 0.00028424782871452745, 'samples': 13349184, 'steps': 69526, 'loss/train': 1.0010429620742798} 08/31/2021 01:45:48 - INFO - __main__ - Step 69528: {'lr': 0.00028424257199313144, 'samples': 13349376, 'steps': 69527, 'loss/train': 0.9631580114364624} 08/31/2021 01:45:50 - INFO - __main__ - Step 69529: {'lr': 0.00028423731525630615, 'samples': 13349568, 'steps': 69528, 'loss/train': 1.428274393081665} 08/31/2021 01:45:50 - INFO - __main__ - Step 69530: {'lr': 0.000284232058504054, 'samples': 13349760, 'steps': 69529, 'loss/train': 0.9525402784347534} 08/31/2021 01:45:51 - INFO - __main__ - Step 69531: {'lr': 0.0002842268017363776, 'samples': 13349952, 'steps': 69530, 'loss/train': 1.0092289447784424} 08/31/2021 01:45:51 - INFO - __main__ - Step 69532: {'lr': 0.000284221544953279, 'samples': 13350144, 'steps': 69531, 'loss/train': 1.2605100870132446} 08/31/2021 01:45:51 - INFO - __main__ - Step 69533: {'lr': 0.0002842162881547607, 'samples': 13350336, 'steps': 69532, 'loss/train': 0.7460618615150452} 08/31/2021 01:45:53 - INFO - __main__ - Step 69534: {'lr': 0.0002842110313408251, 'samples': 13350528, 'steps': 69533, 'loss/train': 0.8800016641616821} 08/31/2021 01:45:53 - INFO - __main__ - Step 69535: {'lr': 0.0002842057745114745, 'samples': 13350720, 'steps': 69534, 'loss/train': 0.5745030045509338} 08/31/2021 01:45:54 - INFO - __main__ - Step 69536: {'lr': 0.00028420051766671133, 'samples': 13350912, 'steps': 69535, 'loss/train': 1.314862608909607} 08/31/2021 01:45:54 - INFO - __main__ - Step 69537: {'lr': 0.0002841952608065379, 'samples': 13351104, 'steps': 69536, 'loss/train': 1.3892590999603271} 08/31/2021 01:45:54 - INFO - __main__ - Step 69538: {'lr': 0.0002841900039309567, 'samples': 13351296, 'steps': 69537, 'loss/train': 1.2714895009994507} 08/31/2021 01:45:56 - INFO - __main__ - Step 69539: {'lr': 0.00028418474703997, 'samples': 13351488, 'steps': 69538, 'loss/train': 1.252899408340454} 08/31/2021 01:45:56 - INFO - __main__ - Step 69540: {'lr': 0.0002841794901335801, 'samples': 13351680, 'steps': 69539, 'loss/train': 0.8150569200515747} 08/31/2021 01:45:56 - INFO - __main__ - Step 69541: {'lr': 0.0002841742332117895, 'samples': 13351872, 'steps': 69540, 'loss/train': 1.5204877853393555} 08/31/2021 01:45:57 - INFO - __main__ - Step 69542: {'lr': 0.0002841689762746005, 'samples': 13352064, 'steps': 69541, 'loss/train': 1.2232568264007568} 08/31/2021 01:45:57 - INFO - __main__ - Step 69543: {'lr': 0.00028416371932201546, 'samples': 13352256, 'steps': 69542, 'loss/train': 1.6832823753356934} 08/31/2021 01:45:59 - INFO - __main__ - Step 69544: {'lr': 0.0002841584623540368, 'samples': 13352448, 'steps': 69543, 'loss/train': 0.2788940370082855} 08/31/2021 01:46:00 - INFO - __main__ - Step 69545: {'lr': 0.00028415320537066697, 'samples': 13352640, 'steps': 69544, 'loss/train': 0.315967857837677} 08/31/2021 01:46:00 - INFO - __main__ - Step 69546: {'lr': 0.0002841479483719081, 'samples': 13352832, 'steps': 69545, 'loss/train': 0.9699750542640686} 08/31/2021 01:46:00 - INFO - __main__ - Step 69547: {'lr': 0.00028414269135776274, 'samples': 13353024, 'steps': 69546, 'loss/train': 0.42834171652793884} 08/31/2021 01:46:01 - INFO - __main__ - Step 69548: {'lr': 0.0002841374343282332, 'samples': 13353216, 'steps': 69547, 'loss/train': 1.0511127710342407} 08/31/2021 01:46:01 - INFO - __main__ - Step 69549: {'lr': 0.00028413217728332185, 'samples': 13353408, 'steps': 69548, 'loss/train': 1.437811017036438} 08/31/2021 01:46:01 - INFO - __main__ - Step 69550: {'lr': 0.0002841269202230311, 'samples': 13353600, 'steps': 69549, 'loss/train': 0.025402437895536423} 08/31/2021 01:46:03 - INFO - __main__ - Step 69551: {'lr': 0.0002841216631473633, 'samples': 13353792, 'steps': 69550, 'loss/train': 0.023910807445645332} 08/31/2021 01:46:03 - INFO - __main__ - Step 69552: {'lr': 0.00028411640605632073, 'samples': 13353984, 'steps': 69551, 'loss/train': 1.5131672620773315} 08/31/2021 01:46:04 - INFO - __main__ - Step 69553: {'lr': 0.0002841111489499059, 'samples': 13354176, 'steps': 69552, 'loss/train': 0.9786812663078308} 08/31/2021 01:46:04 - INFO - __main__ - Step 69554: {'lr': 0.000284105891828121, 'samples': 13354368, 'steps': 69553, 'loss/train': 0.8639963269233704} 08/31/2021 01:46:04 - INFO - __main__ - Step 69555: {'lr': 0.0002841006346909686, 'samples': 13354560, 'steps': 69554, 'loss/train': 0.9060031771659851} 08/31/2021 01:46:06 - INFO - __main__ - Step 69556: {'lr': 0.000284095377538451, 'samples': 13354752, 'steps': 69555, 'loss/train': 0.9863250255584717} 08/31/2021 01:46:06 - INFO - __main__ - Step 69557: {'lr': 0.00028409012037057047, 'samples': 13354944, 'steps': 69556, 'loss/train': 1.3013861179351807} 08/31/2021 01:46:07 - INFO - __main__ - Step 69558: {'lr': 0.00028408486318732954, 'samples': 13355136, 'steps': 69557, 'loss/train': 0.9444453120231628} 08/31/2021 01:46:07 - INFO - __main__ - Step 69559: {'lr': 0.0002840796059887305, 'samples': 13355328, 'steps': 69558, 'loss/train': 1.5242891311645508} 08/31/2021 01:46:07 - INFO - __main__ - Step 69560: {'lr': 0.00028407434877477565, 'samples': 13355520, 'steps': 69559, 'loss/train': 1.5946177244186401} 08/31/2021 01:46:09 - INFO - __main__ - Step 69561: {'lr': 0.00028406909154546746, 'samples': 13355712, 'steps': 69560, 'loss/train': 1.2130438089370728} 08/31/2021 01:46:10 - INFO - __main__ - Step 69562: {'lr': 0.00028406383430080827, 'samples': 13355904, 'steps': 69561, 'loss/train': 1.572830080986023} 08/31/2021 01:46:10 - INFO - __main__ - Step 69563: {'lr': 0.0002840585770408004, 'samples': 13356096, 'steps': 69562, 'loss/train': 1.303949236869812} 08/31/2021 01:46:11 - INFO - __main__ - Step 69564: {'lr': 0.0002840533197654463, 'samples': 13356288, 'steps': 69563, 'loss/train': 1.28591787815094} 08/31/2021 01:46:11 - INFO - __main__ - Step 69565: {'lr': 0.00028404806247474837, 'samples': 13356480, 'steps': 69564, 'loss/train': 0.961539626121521} 08/31/2021 01:46:12 - INFO - __main__ - Step 69566: {'lr': 0.00028404280516870886, 'samples': 13356672, 'steps': 69565, 'loss/train': 0.8421489596366882} 08/31/2021 01:46:13 - INFO - __main__ - Step 69567: {'lr': 0.0002840375478473301, 'samples': 13356864, 'steps': 69566, 'loss/train': 1.1046104431152344} 08/31/2021 01:46:13 - INFO - __main__ - Step 69568: {'lr': 0.00028403229051061457, 'samples': 13357056, 'steps': 69567, 'loss/train': 1.2236926555633545} 08/31/2021 01:46:14 - INFO - __main__ - Step 69569: {'lr': 0.00028402703315856466, 'samples': 13357248, 'steps': 69568, 'loss/train': 1.284297227859497} 08/31/2021 01:46:14 - INFO - __main__ - Step 69570: {'lr': 0.00028402177579118273, 'samples': 13357440, 'steps': 69569, 'loss/train': 1.21291184425354} 08/31/2021 01:46:14 - INFO - __main__ - Step 69571: {'lr': 0.00028401651840847104, 'samples': 13357632, 'steps': 69570, 'loss/train': 1.2691904306411743} 08/31/2021 01:46:16 - INFO - __main__ - Step 69572: {'lr': 0.00028401126101043205, 'samples': 13357824, 'steps': 69571, 'loss/train': 1.1120929718017578} 08/31/2021 01:46:16 - INFO - __main__ - Step 69573: {'lr': 0.0002840060035970681, 'samples': 13358016, 'steps': 69572, 'loss/train': 1.2773369550704956} 08/31/2021 01:46:17 - INFO - __main__ - Step 69574: {'lr': 0.0002840007461683816, 'samples': 13358208, 'steps': 69573, 'loss/train': 1.25348961353302} 08/31/2021 01:46:17 - INFO - __main__ - Step 69575: {'lr': 0.00028399548872437493, 'samples': 13358400, 'steps': 69574, 'loss/train': 1.1658539772033691} 08/31/2021 01:46:18 - INFO - __main__ - Step 69576: {'lr': 0.0002839902312650503, 'samples': 13358592, 'steps': 69575, 'loss/train': 1.1509146690368652} 08/31/2021 01:46:19 - INFO - __main__ - Step 69577: {'lr': 0.00028398497379041027, 'samples': 13358784, 'steps': 69576, 'loss/train': 1.1172102689743042} 08/31/2021 01:46:19 - INFO - __main__ - Step 69578: {'lr': 0.00028397971630045717, 'samples': 13358976, 'steps': 69577, 'loss/train': 1.4314799308776855} 08/31/2021 01:46:20 - INFO - __main__ - Step 69579: {'lr': 0.0002839744587951933, 'samples': 13359168, 'steps': 69578, 'loss/train': 1.1574441194534302} 08/31/2021 01:46:20 - INFO - __main__ - Step 69580: {'lr': 0.00028396920127462107, 'samples': 13359360, 'steps': 69579, 'loss/train': 0.8888075947761536} 08/31/2021 01:46:20 - INFO - __main__ - Step 69581: {'lr': 0.0002839639437387428, 'samples': 13359552, 'steps': 69580, 'loss/train': 1.3405870199203491} 08/31/2021 01:46:22 - INFO - __main__ - Step 69582: {'lr': 0.00028395868618756094, 'samples': 13359744, 'steps': 69581, 'loss/train': 0.9394187331199646} 08/31/2021 01:46:22 - INFO - __main__ - Step 69583: {'lr': 0.00028395342862107774, 'samples': 13359936, 'steps': 69582, 'loss/train': 1.2230069637298584} 08/31/2021 01:46:23 - INFO - __main__ - Step 69584: {'lr': 0.0002839481710392957, 'samples': 13360128, 'steps': 69583, 'loss/train': 0.4510710537433624} 08/31/2021 01:46:23 - INFO - __main__ - Step 69585: {'lr': 0.00028394291344221724, 'samples': 13360320, 'steps': 69584, 'loss/train': 1.2831138372421265} 08/31/2021 01:46:23 - INFO - __main__ - Step 69586: {'lr': 0.00028393765582984454, 'samples': 13360512, 'steps': 69585, 'loss/train': 1.3788264989852905} 08/31/2021 01:46:25 - INFO - __main__ - Step 69587: {'lr': 0.00028393239820218003, 'samples': 13360704, 'steps': 69586, 'loss/train': 1.078654408454895} 08/31/2021 01:46:25 - INFO - __main__ - Step 69588: {'lr': 0.00028392714055922616, 'samples': 13360896, 'steps': 69587, 'loss/train': 0.7337486147880554} 08/31/2021 01:46:26 - INFO - __main__ - Step 69589: {'lr': 0.0002839218829009852, 'samples': 13361088, 'steps': 69588, 'loss/train': 0.8949423432350159} 08/31/2021 01:46:26 - INFO - __main__ - Step 69590: {'lr': 0.00028391662522745954, 'samples': 13361280, 'steps': 69589, 'loss/train': 1.381469964981079} 08/31/2021 01:46:26 - INFO - __main__ - Step 69591: {'lr': 0.0002839113675386516, 'samples': 13361472, 'steps': 69590, 'loss/train': 0.9314327836036682} 08/31/2021 01:46:28 - INFO - __main__ - Step 69592: {'lr': 0.00028390610983456376, 'samples': 13361664, 'steps': 69591, 'loss/train': 0.7535827159881592} 08/31/2021 01:46:28 - INFO - __main__ - Step 69593: {'lr': 0.00028390085211519835, 'samples': 13361856, 'steps': 69592, 'loss/train': 1.4790221452713013} 08/31/2021 01:46:29 - INFO - __main__ - Step 69594: {'lr': 0.0002838955943805577, 'samples': 13362048, 'steps': 69593, 'loss/train': 1.1172807216644287} 08/31/2021 01:46:29 - INFO - __main__ - Step 69595: {'lr': 0.0002838903366306442, 'samples': 13362240, 'steps': 69594, 'loss/train': 2.021979808807373} 08/31/2021 01:46:29 - INFO - __main__ - Step 69596: {'lr': 0.0002838850788654603, 'samples': 13362432, 'steps': 69595, 'loss/train': 0.7007434368133545} 08/31/2021 01:46:31 - INFO - __main__ - Step 69597: {'lr': 0.00028387982108500826, 'samples': 13362624, 'steps': 69596, 'loss/train': 1.3809401988983154} 08/31/2021 01:46:31 - INFO - __main__ - Step 69598: {'lr': 0.0002838745632892905, 'samples': 13362816, 'steps': 69597, 'loss/train': 1.1984645128250122} 08/31/2021 01:46:32 - INFO - __main__ - Step 69599: {'lr': 0.00028386930547830944, 'samples': 13363008, 'steps': 69598, 'loss/train': 1.3144100904464722} 08/31/2021 01:46:32 - INFO - __main__ - Step 69600: {'lr': 0.0002838640476520673, 'samples': 13363200, 'steps': 69599, 'loss/train': 1.616392970085144} 08/31/2021 01:46:32 - INFO - __main__ - Step 69601: {'lr': 0.0002838587898105666, 'samples': 13363392, 'steps': 69600, 'loss/train': 1.3015635013580322} 08/31/2021 01:46:34 - INFO - __main__ - Step 69602: {'lr': 0.00028385353195380965, 'samples': 13363584, 'steps': 69601, 'loss/train': 1.3360275030136108} 08/31/2021 01:46:34 - INFO - __main__ - Step 69603: {'lr': 0.0002838482740817988, 'samples': 13363776, 'steps': 69602, 'loss/train': 0.7834016680717468} 08/31/2021 01:46:35 - INFO - __main__ - Step 69604: {'lr': 0.0002838430161945365, 'samples': 13363968, 'steps': 69603, 'loss/train': 0.8339465260505676} 08/31/2021 01:46:35 - INFO - __main__ - Step 69605: {'lr': 0.000283837758292025, 'samples': 13364160, 'steps': 69604, 'loss/train': 1.296127438545227} 08/31/2021 01:46:36 - INFO - __main__ - Step 69606: {'lr': 0.00028383250037426674, 'samples': 13364352, 'steps': 69605, 'loss/train': 0.6821190714836121} 08/31/2021 01:46:36 - INFO - __main__ - Step 69607: {'lr': 0.00028382724244126406, 'samples': 13364544, 'steps': 69606, 'loss/train': 1.0603361129760742} 08/31/2021 01:46:38 - INFO - __main__ - Step 69608: {'lr': 0.0002838219844930193, 'samples': 13364736, 'steps': 69607, 'loss/train': 1.3085548877716064} 08/31/2021 01:46:38 - INFO - __main__ - Step 69609: {'lr': 0.000283816726529535, 'samples': 13364928, 'steps': 69608, 'loss/train': 1.2892749309539795} 08/31/2021 01:46:38 - INFO - __main__ - Step 69610: {'lr': 0.0002838114685508133, 'samples': 13365120, 'steps': 69609, 'loss/train': 0.604664146900177} 08/31/2021 01:46:39 - INFO - __main__ - Step 69611: {'lr': 0.0002838062105568567, 'samples': 13365312, 'steps': 69610, 'loss/train': 1.367133378982544} 08/31/2021 01:46:39 - INFO - __main__ - Step 69612: {'lr': 0.00028380095254766766, 'samples': 13365504, 'steps': 69611, 'loss/train': 0.8614541292190552} 08/31/2021 01:46:41 - INFO - __main__ - Step 69613: {'lr': 0.00028379569452324825, 'samples': 13365696, 'steps': 69612, 'loss/train': 1.1678545475006104} 08/31/2021 01:46:42 - INFO - __main__ - Step 69614: {'lr': 0.0002837904364836011, 'samples': 13365888, 'steps': 69613, 'loss/train': 1.0347919464111328} 08/31/2021 01:46:42 - INFO - __main__ - Step 69615: {'lr': 0.00028378517842872855, 'samples': 13366080, 'steps': 69614, 'loss/train': 0.6348645091056824} 08/31/2021 01:46:42 - INFO - __main__ - Step 69616: {'lr': 0.00028377992035863285, 'samples': 13366272, 'steps': 69615, 'loss/train': 0.8040921688079834} 08/31/2021 01:46:43 - INFO - __main__ - Step 69617: {'lr': 0.0002837746622733165, 'samples': 13366464, 'steps': 69616, 'loss/train': 1.2846747636795044} 08/31/2021 01:46:44 - INFO - __main__ - Step 69618: {'lr': 0.00028376940417278174, 'samples': 13366656, 'steps': 69617, 'loss/train': 1.0538815259933472} 08/31/2021 01:46:45 - INFO - __main__ - Step 69619: {'lr': 0.0002837641460570311, 'samples': 13366848, 'steps': 69618, 'loss/train': 0.7765041589736938} 08/31/2021 01:46:45 - INFO - __main__ - Step 69620: {'lr': 0.00028375888792606677, 'samples': 13367040, 'steps': 69619, 'loss/train': 1.4145474433898926} 08/31/2021 01:46:45 - INFO - __main__ - Step 69621: {'lr': 0.00028375362977989125, 'samples': 13367232, 'steps': 69620, 'loss/train': 1.4493296146392822} 08/31/2021 01:46:46 - INFO - __main__ - Step 69622: {'lr': 0.0002837483716185068, 'samples': 13367424, 'steps': 69621, 'loss/train': 1.56495201587677} 08/31/2021 01:46:46 - INFO - __main__ - Step 69623: {'lr': 0.0002837431134419159, 'samples': 13367616, 'steps': 69622, 'loss/train': 1.3839521408081055} 08/31/2021 01:46:48 - INFO - __main__ - Step 69624: {'lr': 0.00028373785525012094, 'samples': 13367808, 'steps': 69623, 'loss/train': 1.1640714406967163} 08/31/2021 01:46:49 - INFO - __main__ - Step 69625: {'lr': 0.00028373259704312417, 'samples': 13368000, 'steps': 69624, 'loss/train': 1.0206693410873413} 08/31/2021 01:46:49 - INFO - __main__ - Step 69626: {'lr': 0.00028372733882092797, 'samples': 13368192, 'steps': 69625, 'loss/train': 0.9727171063423157} 08/31/2021 01:46:50 - INFO - __main__ - Step 69627: {'lr': 0.0002837220805835348, 'samples': 13368384, 'steps': 69626, 'loss/train': 0.06220328062772751} 08/31/2021 01:46:50 - INFO - __main__ - Step 69628: {'lr': 0.0002837168223309469, 'samples': 13368576, 'steps': 69627, 'loss/train': 1.0458099842071533} 08/31/2021 01:46:50 - INFO - __main__ - Step 69629: {'lr': 0.0002837115640631668, 'samples': 13368768, 'steps': 69628, 'loss/train': 2.6226003170013428} 08/31/2021 01:46:52 - INFO - __main__ - Step 69630: {'lr': 0.00028370630578019684, 'samples': 13368960, 'steps': 69629, 'loss/train': 1.75681734085083} 08/31/2021 01:46:52 - INFO - __main__ - Step 69631: {'lr': 0.00028370104748203927, 'samples': 13369152, 'steps': 69630, 'loss/train': 0.7429976463317871} 08/31/2021 01:46:53 - INFO - __main__ - Step 69632: {'lr': 0.0002836957891686965, 'samples': 13369344, 'steps': 69631, 'loss/train': 1.2372249364852905} 08/31/2021 01:46:53 - INFO - __main__ - Step 69633: {'lr': 0.00028369053084017094, 'samples': 13369536, 'steps': 69632, 'loss/train': 1.6489187479019165} 08/31/2021 01:46:53 - INFO - __main__ - Step 69634: {'lr': 0.000283685272496465, 'samples': 13369728, 'steps': 69633, 'loss/train': 1.114445686340332} 08/31/2021 01:46:56 - INFO - __main__ - Step 69635: {'lr': 0.000283680014137581, 'samples': 13369920, 'steps': 69634, 'loss/train': 0.6864233016967773} 08/31/2021 01:46:56 - INFO - __main__ - Step 69636: {'lr': 0.00028367475576352125, 'samples': 13370112, 'steps': 69635, 'loss/train': 0.9296894669532776} 08/31/2021 01:46:57 - INFO - __main__ - Step 69637: {'lr': 0.00028366949737428814, 'samples': 13370304, 'steps': 69636, 'loss/train': 1.9283976554870605} 08/31/2021 01:46:57 - INFO - __main__ - Step 69638: {'lr': 0.0002836642389698841, 'samples': 13370496, 'steps': 69637, 'loss/train': 1.3352001905441284} 08/31/2021 01:46:57 - INFO - __main__ - Step 69639: {'lr': 0.0002836589805503115, 'samples': 13370688, 'steps': 69638, 'loss/train': 1.6488617658615112} 08/31/2021 01:46:58 - INFO - __main__ - Step 69640: {'lr': 0.0002836537221155727, 'samples': 13370880, 'steps': 69639, 'loss/train': 0.9390825629234314} 08/31/2021 01:46:58 - INFO - __main__ - Step 69641: {'lr': 0.0002836484636656701, 'samples': 13371072, 'steps': 69640, 'loss/train': 1.5714030265808105} 08/31/2021 01:46:58 - INFO - __main__ - Step 69642: {'lr': 0.00028364320520060595, 'samples': 13371264, 'steps': 69641, 'loss/train': 1.6571271419525146} 08/31/2021 01:47:00 - INFO - __main__ - Step 69643: {'lr': 0.0002836379467203827, 'samples': 13371456, 'steps': 69642, 'loss/train': 0.052237775176763535} 08/31/2021 01:47:00 - INFO - __main__ - Step 69644: {'lr': 0.0002836326882250027, 'samples': 13371648, 'steps': 69643, 'loss/train': 1.445986270904541} 08/31/2021 01:47:01 - INFO - __main__ - Step 69645: {'lr': 0.00028362742971446833, 'samples': 13371840, 'steps': 69644, 'loss/train': 1.9974658489227295} 08/31/2021 01:47:01 - INFO - __main__ - Step 69646: {'lr': 0.000283622171188782, 'samples': 13372032, 'steps': 69645, 'loss/train': 1.4548399448394775} 08/31/2021 01:47:01 - INFO - __main__ - Step 69647: {'lr': 0.000283616912647946, 'samples': 13372224, 'steps': 69646, 'loss/train': 1.5436747074127197} 08/31/2021 01:47:03 - INFO - __main__ - Step 69648: {'lr': 0.0002836116540919627, 'samples': 13372416, 'steps': 69647, 'loss/train': 2.354663610458374} 08/31/2021 01:47:04 - INFO - __main__ - Step 69649: {'lr': 0.00028360639552083456, 'samples': 13372608, 'steps': 69648, 'loss/train': 0.28397616744041443} 08/31/2021 01:47:04 - INFO - __main__ - Step 69650: {'lr': 0.0002836011369345639, 'samples': 13372800, 'steps': 69649, 'loss/train': 1.7007668018341064} 08/31/2021 01:47:05 - INFO - __main__ - Step 69651: {'lr': 0.00028359587833315305, 'samples': 13372992, 'steps': 69650, 'loss/train': 1.884022831916809} 08/31/2021 01:47:05 - INFO - __main__ - Step 69652: {'lr': 0.0002835906197166045, 'samples': 13373184, 'steps': 69651, 'loss/train': 1.054390549659729} 08/31/2021 01:47:05 - INFO - __main__ - Step 69653: {'lr': 0.00028358536108492047, 'samples': 13373376, 'steps': 69652, 'loss/train': 1.2250654697418213} 08/31/2021 01:47:07 - INFO - __main__ - Step 69654: {'lr': 0.0002835801024381033, 'samples': 13373568, 'steps': 69653, 'loss/train': 0.04220056161284447} 08/31/2021 01:47:08 - INFO - __main__ - Step 69655: {'lr': 0.0002835748437761556, 'samples': 13373760, 'steps': 69654, 'loss/train': 2.102851152420044} 08/31/2021 01:47:08 - INFO - __main__ - Step 69656: {'lr': 0.00028356958509907955, 'samples': 13373952, 'steps': 69655, 'loss/train': 1.8109815120697021} 08/31/2021 01:47:08 - INFO - __main__ - Step 69657: {'lr': 0.0002835643264068776, 'samples': 13374144, 'steps': 69656, 'loss/train': 2.9603335857391357} 08/31/2021 01:47:09 - INFO - __main__ - Step 69658: {'lr': 0.000283559067699552, 'samples': 13374336, 'steps': 69657, 'loss/train': 1.4111101627349854} 08/31/2021 01:47:10 - INFO - __main__ - Step 69659: {'lr': 0.0002835538089771053, 'samples': 13374528, 'steps': 69658, 'loss/train': 1.547420859336853} 08/31/2021 01:47:11 - INFO - __main__ - Step 69660: {'lr': 0.0002835485502395397, 'samples': 13374720, 'steps': 69659, 'loss/train': 1.0657514333724976} 08/31/2021 01:47:11 - INFO - __main__ - Step 69661: {'lr': 0.0002835432914868576, 'samples': 13374912, 'steps': 69660, 'loss/train': 1.5255966186523438} 08/31/2021 01:47:11 - INFO - __main__ - Step 69662: {'lr': 0.00028353803271906146, 'samples': 13375104, 'steps': 69661, 'loss/train': 1.6592975854873657} 08/31/2021 01:47:12 - INFO - __main__ - Step 69663: {'lr': 0.00028353277393615363, 'samples': 13375296, 'steps': 69662, 'loss/train': 1.5409661531448364} 08/31/2021 01:47:12 - INFO - __main__ - Step 69664: {'lr': 0.0002835275151381364, 'samples': 13375488, 'steps': 69663, 'loss/train': 1.0381324291229248} 08/31/2021 01:47:14 - INFO - __main__ - Step 69665: {'lr': 0.00028352225632501224, 'samples': 13375680, 'steps': 69664, 'loss/train': 1.0388398170471191} 08/31/2021 01:47:15 - INFO - __main__ - Step 69666: {'lr': 0.00028351699749678346, 'samples': 13375872, 'steps': 69665, 'loss/train': 1.388078212738037} 08/31/2021 01:47:15 - INFO - __main__ - Step 69667: {'lr': 0.0002835117386534524, 'samples': 13376064, 'steps': 69666, 'loss/train': 1.5084714889526367} 08/31/2021 01:47:15 - INFO - __main__ - Step 69668: {'lr': 0.00028350647979502147, 'samples': 13376256, 'steps': 69667, 'loss/train': 1.6159604787826538} 08/31/2021 01:47:16 - INFO - __main__ - Step 69669: {'lr': 0.00028350122092149304, 'samples': 13376448, 'steps': 69668, 'loss/train': 1.6961772441864014} 08/31/2021 01:47:16 - INFO - __main__ - Step 69670: {'lr': 0.0002834959620328695, 'samples': 13376640, 'steps': 69669, 'loss/train': 1.2638847827911377} 08/31/2021 01:47:17 - INFO - __main__ - Step 69671: {'lr': 0.00028349070312915317, 'samples': 13376832, 'steps': 69670, 'loss/train': 0.05067965015769005} 08/31/2021 01:47:19 - INFO - __main__ - Step 69672: {'lr': 0.0002834854442103465, 'samples': 13377024, 'steps': 69671, 'loss/train': 1.4999934434890747} 08/31/2021 01:47:19 - INFO - __main__ - Step 69673: {'lr': 0.0002834801852764518, 'samples': 13377216, 'steps': 69672, 'loss/train': 1.6064125299453735} 08/31/2021 01:47:19 - INFO - __main__ - Step 69674: {'lr': 0.0002834749263274714, 'samples': 13377408, 'steps': 69673, 'loss/train': 1.2311100959777832} 08/31/2021 01:47:20 - INFO - __main__ - Step 69675: {'lr': 0.00028346966736340776, 'samples': 13377600, 'steps': 69674, 'loss/train': 1.097520351409912} 08/31/2021 01:47:20 - INFO - __main__ - Step 69676: {'lr': 0.00028346440838426313, 'samples': 13377792, 'steps': 69675, 'loss/train': 1.4373302459716797} 08/31/2021 01:47:22 - INFO - __main__ - Step 69677: {'lr': 0.00028345914939003995, 'samples': 13377984, 'steps': 69676, 'loss/train': 1.1741313934326172} 08/31/2021 01:47:22 - INFO - __main__ - Step 69678: {'lr': 0.0002834538903807407, 'samples': 13378176, 'steps': 69677, 'loss/train': 1.5002976655960083} 08/31/2021 01:47:23 - INFO - __main__ - Step 69679: {'lr': 0.0002834486313563676, 'samples': 13378368, 'steps': 69678, 'loss/train': 1.8416054248809814} 08/31/2021 01:47:23 - INFO - __main__ - Step 69680: {'lr': 0.00028344337231692304, 'samples': 13378560, 'steps': 69679, 'loss/train': 1.3468254804611206} 08/31/2021 01:47:23 - INFO - __main__ - Step 69681: {'lr': 0.00028343811326240944, 'samples': 13378752, 'steps': 69680, 'loss/train': 1.6093686819076538} 08/31/2021 01:47:25 - INFO - __main__ - Step 69682: {'lr': 0.00028343285419282907, 'samples': 13378944, 'steps': 69681, 'loss/train': 1.041601300239563} 08/31/2021 01:47:25 - INFO - __main__ - Step 69683: {'lr': 0.0002834275951081844, 'samples': 13379136, 'steps': 69682, 'loss/train': 0.27289924025535583} 08/31/2021 01:47:26 - INFO - __main__ - Step 69684: {'lr': 0.0002834223360084778, 'samples': 13379328, 'steps': 69683, 'loss/train': 1.095299243927002} 08/31/2021 01:47:26 - INFO - __main__ - Step 69685: {'lr': 0.0002834170768937116, 'samples': 13379520, 'steps': 69684, 'loss/train': 1.6300550699234009} 08/31/2021 01:47:26 - INFO - __main__ - Step 69686: {'lr': 0.00028341181776388825, 'samples': 13379712, 'steps': 69685, 'loss/train': 0.7680323719978333} 08/31/2021 01:47:27 - INFO - __main__ - Step 69687: {'lr': 0.00028340655861901, 'samples': 13379904, 'steps': 69686, 'loss/train': 1.3654334545135498} 08/31/2021 01:47:28 - INFO - __main__ - Step 69688: {'lr': 0.00028340129945907924, 'samples': 13380096, 'steps': 69687, 'loss/train': 1.6654475927352905} 08/31/2021 01:47:29 - INFO - __main__ - Step 69689: {'lr': 0.00028339604028409837, 'samples': 13380288, 'steps': 69688, 'loss/train': 0.8655904531478882} 08/31/2021 01:47:29 - INFO - __main__ - Step 69690: {'lr': 0.00028339078109406975, 'samples': 13380480, 'steps': 69689, 'loss/train': 1.1241015195846558} 08/31/2021 01:47:30 - INFO - __main__ - Step 69691: {'lr': 0.0002833855218889958, 'samples': 13380672, 'steps': 69690, 'loss/train': 4.347714900970459} 08/31/2021 01:47:30 - INFO - __main__ - Step 69692: {'lr': 0.00028338026266887885, 'samples': 13380864, 'steps': 69691, 'loss/train': 2.075701951980591} 08/31/2021 01:47:30 - INFO - __main__ - Step 69693: {'lr': 0.00028337500343372123, 'samples': 13381056, 'steps': 69692, 'loss/train': 1.0615193843841553} 08/31/2021 01:47:32 - INFO - __main__ - Step 69694: {'lr': 0.0002833697441835254, 'samples': 13381248, 'steps': 69693, 'loss/train': 0.462064266204834} 08/31/2021 01:47:32 - INFO - __main__ - Step 69695: {'lr': 0.00028336448491829365, 'samples': 13381440, 'steps': 69694, 'loss/train': 0.8442476391792297} 08/31/2021 01:47:33 - INFO - __main__ - Step 69696: {'lr': 0.00028335922563802834, 'samples': 13381632, 'steps': 69695, 'loss/train': 0.9184074997901917} 08/31/2021 01:47:33 - INFO - __main__ - Step 69697: {'lr': 0.00028335396634273193, 'samples': 13381824, 'steps': 69696, 'loss/train': 1.2603998184204102} 08/31/2021 01:47:33 - INFO - __main__ - Step 69698: {'lr': 0.00028334870703240674, 'samples': 13382016, 'steps': 69697, 'loss/train': 0.5606609582901001} 08/31/2021 01:47:35 - INFO - __main__ - Step 69699: {'lr': 0.00028334344770705516, 'samples': 13382208, 'steps': 69698, 'loss/train': 0.5881161093711853} 08/31/2021 01:47:35 - INFO - __main__ - Step 69700: {'lr': 0.00028333818836667946, 'samples': 13382400, 'steps': 69699, 'loss/train': 1.5385377407073975} 08/31/2021 01:47:36 - INFO - __main__ - Step 69701: {'lr': 0.00028333292901128215, 'samples': 13382592, 'steps': 69700, 'loss/train': 1.009387493133545} 08/31/2021 01:47:36 - INFO - __main__ - Step 69702: {'lr': 0.0002833276696408655, 'samples': 13382784, 'steps': 69701, 'loss/train': 0.32517874240875244} 08/31/2021 01:47:36 - INFO - __main__ - Step 69703: {'lr': 0.0002833224102554319, 'samples': 13382976, 'steps': 69702, 'loss/train': 1.4104253053665161} 08/31/2021 01:47:39 - INFO - __main__ - Step 69704: {'lr': 0.0002833171508549838, 'samples': 13383168, 'steps': 69703, 'loss/train': 0.5309178233146667} 08/31/2021 01:47:39 - INFO - __main__ - Step 69705: {'lr': 0.0002833118914395234, 'samples': 13383360, 'steps': 69704, 'loss/train': 1.631123661994934} 08/31/2021 01:47:39 - INFO - __main__ - Step 69706: {'lr': 0.0002833066320090533, 'samples': 13383552, 'steps': 69705, 'loss/train': 1.8928292989730835} 08/31/2021 01:47:40 - INFO - __main__ - Step 69707: {'lr': 0.0002833013725635757, 'samples': 13383744, 'steps': 69706, 'loss/train': 0.031238364055752754} 08/31/2021 01:47:40 - INFO - __main__ - Step 69708: {'lr': 0.000283296113103093, 'samples': 13383936, 'steps': 69707, 'loss/train': 0.031041545793414116} 08/31/2021 01:47:40 - INFO - __main__ - Step 69709: {'lr': 0.00028329085362760757, 'samples': 13384128, 'steps': 69708, 'loss/train': 1.0048075914382935} 08/31/2021 01:47:42 - INFO - __main__ - Step 69710: {'lr': 0.00028328559413712186, 'samples': 13384320, 'steps': 69709, 'loss/train': 0.9570635557174683} 08/31/2021 01:47:42 - INFO - __main__ - Step 69711: {'lr': 0.0002832803346316381, 'samples': 13384512, 'steps': 69710, 'loss/train': 0.6065398454666138} 08/31/2021 01:47:43 - INFO - __main__ - Step 69712: {'lr': 0.00028327507511115876, 'samples': 13384704, 'steps': 69711, 'loss/train': 1.1303175687789917} 08/31/2021 01:47:43 - INFO - __main__ - Step 69713: {'lr': 0.0002832698155756862, 'samples': 13384896, 'steps': 69712, 'loss/train': 1.2641279697418213} 08/31/2021 01:47:43 - INFO - __main__ - Step 69714: {'lr': 0.00028326455602522275, 'samples': 13385088, 'steps': 69713, 'loss/train': 1.280601143836975} 08/31/2021 01:47:44 - INFO - __main__ - Step 69715: {'lr': 0.00028325929645977086, 'samples': 13385280, 'steps': 69714, 'loss/train': 1.0184273719787598} 08/31/2021 01:47:45 - INFO - __main__ - Step 69716: {'lr': 0.00028325403687933274, 'samples': 13385472, 'steps': 69715, 'loss/train': 1.4111765623092651} 08/31/2021 01:47:46 - INFO - __main__ - Step 69717: {'lr': 0.00028324877728391095, 'samples': 13385664, 'steps': 69716, 'loss/train': 0.8192737102508545} 08/31/2021 01:47:46 - INFO - __main__ - Step 69718: {'lr': 0.00028324351767350776, 'samples': 13385856, 'steps': 69717, 'loss/train': 1.289730429649353} 08/31/2021 01:47:46 - INFO - __main__ - Step 69719: {'lr': 0.00028323825804812557, 'samples': 13386048, 'steps': 69718, 'loss/train': 1.4836180210113525} 08/31/2021 01:47:47 - INFO - __main__ - Step 69720: {'lr': 0.00028323299840776674, 'samples': 13386240, 'steps': 69719, 'loss/train': 1.2126266956329346} 08/31/2021 01:47:48 - INFO - __main__ - Step 69721: {'lr': 0.00028322773875243357, 'samples': 13386432, 'steps': 69720, 'loss/train': 1.595438838005066} 08/31/2021 01:47:49 - INFO - __main__ - Step 69722: {'lr': 0.0002832224790821285, 'samples': 13386624, 'steps': 69721, 'loss/train': 1.2320125102996826} 08/31/2021 01:47:49 - INFO - __main__ - Step 69723: {'lr': 0.000283217219396854, 'samples': 13386816, 'steps': 69722, 'loss/train': 1.9501938819885254} 08/31/2021 01:47:49 - INFO - __main__ - Step 69724: {'lr': 0.0002832119596966122, 'samples': 13387008, 'steps': 69723, 'loss/train': 1.1469734907150269} 08/31/2021 01:47:50 - INFO - __main__ - Step 69725: {'lr': 0.0002832066999814056, 'samples': 13387200, 'steps': 69724, 'loss/train': 1.7654814720153809} 08/31/2021 01:47:51 - INFO - __main__ - Step 69726: {'lr': 0.00028320144025123674, 'samples': 13387392, 'steps': 69725, 'loss/train': 1.153764009475708} 08/31/2021 01:47:52 - INFO - __main__ - Step 69727: {'lr': 0.00028319618050610766, 'samples': 13387584, 'steps': 69726, 'loss/train': 1.456260085105896} 08/31/2021 01:47:52 - INFO - __main__ - Step 69728: {'lr': 0.000283190920746021, 'samples': 13387776, 'steps': 69727, 'loss/train': 0.6809636354446411} 08/31/2021 01:47:53 - INFO - __main__ - Step 69729: {'lr': 0.00028318566097097894, 'samples': 13387968, 'steps': 69728, 'loss/train': 0.9763906598091125} 08/31/2021 01:47:53 - INFO - __main__ - Step 69730: {'lr': 0.00028318040118098395, 'samples': 13388160, 'steps': 69729, 'loss/train': 1.8336700201034546} 08/31/2021 01:47:53 - INFO - __main__ - Step 69731: {'lr': 0.0002831751413760384, 'samples': 13388352, 'steps': 69730, 'loss/train': 1.9282602071762085} 08/31/2021 01:47:55 - INFO - __main__ - Step 69732: {'lr': 0.0002831698815561446, 'samples': 13388544, 'steps': 69731, 'loss/train': 1.1561418771743774} 08/31/2021 01:47:56 - INFO - __main__ - Step 69733: {'lr': 0.0002831646217213051, 'samples': 13388736, 'steps': 69732, 'loss/train': 1.0552860498428345} 08/31/2021 01:47:56 - INFO - __main__ - Step 69734: {'lr': 0.000283159361871522, 'samples': 13388928, 'steps': 69733, 'loss/train': 0.6355657577514648} 08/31/2021 01:47:56 - INFO - __main__ - Step 69735: {'lr': 0.0002831541020067978, 'samples': 13389120, 'steps': 69734, 'loss/train': 1.7334027290344238} 08/31/2021 01:47:57 - INFO - __main__ - Step 69736: {'lr': 0.00028314884212713495, 'samples': 13389312, 'steps': 69735, 'loss/train': 1.0987434387207031} 08/31/2021 01:47:59 - INFO - __main__ - Step 69737: {'lr': 0.00028314358223253564, 'samples': 13389504, 'steps': 69736, 'loss/train': 1.5398774147033691} 08/31/2021 01:47:59 - INFO - __main__ - Step 69738: {'lr': 0.0002831383223230025, 'samples': 13389696, 'steps': 69737, 'loss/train': 1.5904115438461304} 08/31/2021 01:47:59 - INFO - __main__ - Step 69739: {'lr': 0.0002831330623985376, 'samples': 13389888, 'steps': 69738, 'loss/train': 0.02454308792948723} 08/31/2021 01:48:00 - INFO - __main__ - Step 69740: {'lr': 0.00028312780245914356, 'samples': 13390080, 'steps': 69739, 'loss/train': 1.394909143447876} 08/31/2021 01:48:00 - INFO - __main__ - Step 69741: {'lr': 0.00028312254250482255, 'samples': 13390272, 'steps': 69740, 'loss/train': 0.1392328292131424} 08/31/2021 01:48:00 - INFO - __main__ - Step 69742: {'lr': 0.0002831172825355771, 'samples': 13390464, 'steps': 69741, 'loss/train': 1.3450160026550293} 08/31/2021 01:48:02 - INFO - __main__ - Step 69743: {'lr': 0.00028311202255140944, 'samples': 13390656, 'steps': 69742, 'loss/train': 1.1770236492156982} 08/31/2021 01:48:02 - INFO - __main__ - Step 69744: {'lr': 0.0002831067625523221, 'samples': 13390848, 'steps': 69743, 'loss/train': 1.4411650896072388} 08/31/2021 01:48:03 - INFO - __main__ - Step 69745: {'lr': 0.0002831015025383173, 'samples': 13391040, 'steps': 69744, 'loss/train': 1.0476359128952026} 08/31/2021 01:48:03 - INFO - __main__ - Step 69746: {'lr': 0.00028309624250939753, 'samples': 13391232, 'steps': 69745, 'loss/train': 0.05612229183316231} 08/31/2021 01:48:04 - INFO - __main__ - Step 69747: {'lr': 0.00028309098246556507, 'samples': 13391424, 'steps': 69746, 'loss/train': 1.5203816890716553} 08/31/2021 01:48:05 - INFO - __main__ - Step 69748: {'lr': 0.00028308572240682233, 'samples': 13391616, 'steps': 69747, 'loss/train': 1.6471965312957764} 08/31/2021 01:48:06 - INFO - __main__ - Step 69749: {'lr': 0.00028308046233317165, 'samples': 13391808, 'steps': 69748, 'loss/train': 1.321824073791504} 08/31/2021 01:48:06 - INFO - __main__ - Step 69750: {'lr': 0.00028307520224461546, 'samples': 13392000, 'steps': 69749, 'loss/train': 0.02227659896016121} 08/31/2021 01:48:07 - INFO - __main__ - Step 69751: {'lr': 0.00028306994214115605, 'samples': 13392192, 'steps': 69750, 'loss/train': 0.832294225692749} 08/31/2021 01:48:07 - INFO - __main__ - Step 69752: {'lr': 0.00028306468202279585, 'samples': 13392384, 'steps': 69751, 'loss/train': 1.1339857578277588} 08/31/2021 01:48:07 - INFO - __main__ - Step 69753: {'lr': 0.00028305942188953725, 'samples': 13392576, 'steps': 69752, 'loss/train': 2.053158760070801} 08/31/2021 01:48:09 - INFO - __main__ - Step 69754: {'lr': 0.0002830541617413826, 'samples': 13392768, 'steps': 69753, 'loss/train': 0.43057170510292053} 08/31/2021 01:48:09 - INFO - __main__ - Step 69755: {'lr': 0.00028304890157833417, 'samples': 13392960, 'steps': 69754, 'loss/train': 0.5982902646064758} 08/31/2021 01:48:10 - INFO - __main__ - Step 69756: {'lr': 0.0002830436414003945, 'samples': 13393152, 'steps': 69755, 'loss/train': 1.606635332107544} 08/31/2021 01:48:10 - INFO - __main__ - Step 69757: {'lr': 0.00028303838120756584, 'samples': 13393344, 'steps': 69756, 'loss/train': 0.054562460631132126} 08/31/2021 01:48:10 - INFO - __main__ - Step 69758: {'lr': 0.0002830331209998506, 'samples': 13393536, 'steps': 69757, 'loss/train': 1.1662625074386597} 08/31/2021 01:48:12 - INFO - __main__ - Step 69759: {'lr': 0.0002830278607772511, 'samples': 13393728, 'steps': 69758, 'loss/train': 1.4929865598678589} 08/31/2021 01:48:12 - INFO - __main__ - Step 69760: {'lr': 0.0002830226005397698, 'samples': 13393920, 'steps': 69759, 'loss/train': 1.7908740043640137} 08/31/2021 01:48:13 - INFO - __main__ - Step 69761: {'lr': 0.00028301734028740903, 'samples': 13394112, 'steps': 69760, 'loss/train': 1.3657430410385132} 08/31/2021 01:48:13 - INFO - __main__ - Step 69762: {'lr': 0.0002830120800201712, 'samples': 13394304, 'steps': 69761, 'loss/train': 1.532315969467163} 08/31/2021 01:48:13 - INFO - __main__ - Step 69763: {'lr': 0.00028300681973805855, 'samples': 13394496, 'steps': 69762, 'loss/train': 1.2795346975326538} 08/31/2021 01:48:14 - INFO - __main__ - Step 69764: {'lr': 0.0002830015594410736, 'samples': 13394688, 'steps': 69763, 'loss/train': 1.3074108362197876} 08/31/2021 01:48:15 - INFO - __main__ - Step 69765: {'lr': 0.0002829962991292186, 'samples': 13394880, 'steps': 69764, 'loss/train': 1.38532292842865} 08/31/2021 01:48:15 - INFO - __main__ - Step 69766: {'lr': 0.000282991038802496, 'samples': 13395072, 'steps': 69765, 'loss/train': 1.2354906797409058} 08/31/2021 01:48:16 - INFO - __main__ - Step 69767: {'lr': 0.0002829857784609081, 'samples': 13395264, 'steps': 69766, 'loss/train': 1.391526460647583} 08/31/2021 01:48:16 - INFO - __main__ - Step 69768: {'lr': 0.0002829805181044574, 'samples': 13395456, 'steps': 69767, 'loss/train': 1.0761816501617432} 08/31/2021 01:48:16 - INFO - __main__ - Step 69769: {'lr': 0.0002829752577331462, 'samples': 13395648, 'steps': 69768, 'loss/train': 1.68583083152771} 08/31/2021 01:48:18 - INFO - __main__ - Step 69770: {'lr': 0.0002829699973469768, 'samples': 13395840, 'steps': 69769, 'loss/train': 1.5143522024154663} 08/31/2021 01:48:18 - INFO - __main__ - Step 69771: {'lr': 0.0002829647369459516, 'samples': 13396032, 'steps': 69770, 'loss/train': 0.8750485181808472} 08/31/2021 01:48:19 - INFO - __main__ - Step 69772: {'lr': 0.00028295947653007305, 'samples': 13396224, 'steps': 69771, 'loss/train': 0.8684315085411072} 08/31/2021 01:48:19 - INFO - __main__ - Step 69773: {'lr': 0.00028295421609934347, 'samples': 13396416, 'steps': 69772, 'loss/train': 1.2105704545974731} 08/31/2021 01:48:19 - INFO - __main__ - Step 69774: {'lr': 0.00028294895565376515, 'samples': 13396608, 'steps': 69773, 'loss/train': 1.0751595497131348} 08/31/2021 01:48:21 - INFO - __main__ - Step 69775: {'lr': 0.0002829436951933407, 'samples': 13396800, 'steps': 69774, 'loss/train': 0.5806208848953247} 08/31/2021 01:48:21 - INFO - __main__ - Step 69776: {'lr': 0.00028293843471807224, 'samples': 13396992, 'steps': 69775, 'loss/train': 1.3370461463928223} 08/31/2021 01:48:22 - INFO - __main__ - Step 69777: {'lr': 0.00028293317422796216, 'samples': 13397184, 'steps': 69776, 'loss/train': 1.3255767822265625} 08/31/2021 01:48:22 - INFO - __main__ - Step 69778: {'lr': 0.000282927913723013, 'samples': 13397376, 'steps': 69777, 'loss/train': 0.9352535009384155} 08/31/2021 01:48:22 - INFO - __main__ - Step 69779: {'lr': 0.000282922653203227, 'samples': 13397568, 'steps': 69778, 'loss/train': 1.068210482597351} 08/31/2021 01:48:24 - INFO - __main__ - Step 69780: {'lr': 0.00028291739266860655, 'samples': 13397760, 'steps': 69779, 'loss/train': 0.9876019954681396} 08/31/2021 01:48:25 - INFO - __main__ - Step 69781: {'lr': 0.000282912132119154, 'samples': 13397952, 'steps': 69780, 'loss/train': 1.1832557916641235} 08/31/2021 01:48:25 - INFO - __main__ - Step 69782: {'lr': 0.0002829068715548718, 'samples': 13398144, 'steps': 69781, 'loss/train': 1.1516841650009155} 08/31/2021 01:48:25 - INFO - __main__ - Step 69783: {'lr': 0.0002829016109757623, 'samples': 13398336, 'steps': 69782, 'loss/train': 1.0370389223098755} 08/31/2021 01:48:26 - INFO - __main__ - Step 69784: {'lr': 0.00028289635038182776, 'samples': 13398528, 'steps': 69783, 'loss/train': 1.2119576930999756} 08/31/2021 01:48:28 - INFO - __main__ - Step 69785: {'lr': 0.00028289108977307066, 'samples': 13398720, 'steps': 69784, 'loss/train': 1.2317302227020264} 08/31/2021 01:48:28 - INFO - __main__ - Step 69786: {'lr': 0.00028288582914949334, 'samples': 13398912, 'steps': 69785, 'loss/train': 1.2644926309585571} 08/31/2021 01:48:29 - INFO - __main__ - Step 69787: {'lr': 0.0002828805685110982, 'samples': 13399104, 'steps': 69786, 'loss/train': 1.44906485080719} 08/31/2021 01:48:29 - INFO - __main__ - Step 69788: {'lr': 0.00028287530785788754, 'samples': 13399296, 'steps': 69787, 'loss/train': 1.3680627346038818} 08/31/2021 01:48:29 - INFO - __main__ - Step 69789: {'lr': 0.00028287004718986384, 'samples': 13399488, 'steps': 69788, 'loss/train': 0.3544588088989258} 08/31/2021 01:48:31 - INFO - __main__ - Step 69790: {'lr': 0.00028286478650702934, 'samples': 13399680, 'steps': 69789, 'loss/train': 0.6757148504257202} 08/31/2021 01:48:31 - INFO - __main__ - Step 69791: {'lr': 0.00028285952580938653, 'samples': 13399872, 'steps': 69790, 'loss/train': 0.920371413230896} 08/31/2021 01:48:32 - INFO - __main__ - Step 69792: {'lr': 0.0002828542650969377, 'samples': 13400064, 'steps': 69791, 'loss/train': 0.8770109415054321} 08/31/2021 01:48:32 - INFO - __main__ - Step 69793: {'lr': 0.0002828490043696852, 'samples': 13400256, 'steps': 69792, 'loss/train': 1.3033086061477661} 08/31/2021 01:48:32 - INFO - __main__ - Step 69794: {'lr': 0.00028284374362763155, 'samples': 13400448, 'steps': 69793, 'loss/train': 1.36796236038208} 08/31/2021 01:48:34 - INFO - __main__ - Step 69795: {'lr': 0.0002828384828707789, 'samples': 13400640, 'steps': 69794, 'loss/train': 1.0729777812957764} 08/31/2021 01:48:34 - INFO - __main__ - Step 69796: {'lr': 0.0002828332220991298, 'samples': 13400832, 'steps': 69795, 'loss/train': 0.8810123801231384} 08/31/2021 01:48:35 - INFO - __main__ - Step 69797: {'lr': 0.0002828279613126865, 'samples': 13401024, 'steps': 69796, 'loss/train': 1.2918390035629272} 08/31/2021 01:48:35 - INFO - __main__ - Step 69798: {'lr': 0.0002828227005114515, 'samples': 13401216, 'steps': 69797, 'loss/train': 1.0391879081726074} 08/31/2021 01:48:35 - INFO - __main__ - Step 69799: {'lr': 0.0002828174396954271, 'samples': 13401408, 'steps': 69798, 'loss/train': 1.3554251194000244} 08/31/2021 01:48:37 - INFO - __main__ - Step 69800: {'lr': 0.0002828121788646156, 'samples': 13401600, 'steps': 69799, 'loss/train': 0.4507986903190613} 08/31/2021 01:48:37 - INFO - __main__ - Step 69801: {'lr': 0.00028280691801901956, 'samples': 13401792, 'steps': 69800, 'loss/train': 1.4850292205810547} 08/31/2021 01:48:38 - INFO - __main__ - Step 69802: {'lr': 0.0002828016571586411, 'samples': 13401984, 'steps': 69801, 'loss/train': 1.553157925605774} 08/31/2021 01:48:38 - INFO - __main__ - Step 69803: {'lr': 0.00028279639628348273, 'samples': 13402176, 'steps': 69802, 'loss/train': 1.2780382633209229} 08/31/2021 01:48:38 - INFO - __main__ - Step 69804: {'lr': 0.00028279113539354686, 'samples': 13402368, 'steps': 69803, 'loss/train': 1.281442403793335} 08/31/2021 01:48:40 - INFO - __main__ - Step 69805: {'lr': 0.00028278587448883575, 'samples': 13402560, 'steps': 69804, 'loss/train': 0.13937699794769287} 08/31/2021 01:48:41 - INFO - __main__ - Step 69806: {'lr': 0.0002827806135693519, 'samples': 13402752, 'steps': 69805, 'loss/train': 1.2649438381195068} 08/31/2021 01:48:41 - INFO - __main__ - Step 69807: {'lr': 0.00028277535263509764, 'samples': 13402944, 'steps': 69806, 'loss/train': 1.0948519706726074} 08/31/2021 01:48:41 - INFO - __main__ - Step 69808: {'lr': 0.00028277009168607524, 'samples': 13403136, 'steps': 69807, 'loss/train': 1.961183786392212} 08/31/2021 01:48:42 - INFO - __main__ - Step 69809: {'lr': 0.00028276483072228715, 'samples': 13403328, 'steps': 69808, 'loss/train': 1.2630131244659424} 08/31/2021 01:48:42 - INFO - __main__ - Step 69810: {'lr': 0.00028275956974373575, 'samples': 13403520, 'steps': 69809, 'loss/train': 0.9640730619430542} 08/31/2021 01:48:44 - INFO - __main__ - Step 69811: {'lr': 0.00028275430875042336, 'samples': 13403712, 'steps': 69810, 'loss/train': 1.63835608959198} 08/31/2021 01:48:44 - INFO - __main__ - Step 69812: {'lr': 0.00028274904774235244, 'samples': 13403904, 'steps': 69811, 'loss/train': 1.3567767143249512} 08/31/2021 01:48:44 - INFO - __main__ - Step 69813: {'lr': 0.0002827437867195252, 'samples': 13404096, 'steps': 69812, 'loss/train': 0.443865031003952} 08/31/2021 01:48:45 - INFO - __main__ - Step 69814: {'lr': 0.00028273852568194425, 'samples': 13404288, 'steps': 69813, 'loss/train': 1.0212112665176392} 08/31/2021 01:48:45 - INFO - __main__ - Step 69815: {'lr': 0.0002827332646296118, 'samples': 13404480, 'steps': 69814, 'loss/train': 1.189047932624817} 08/31/2021 01:48:46 - INFO - __main__ - Step 69816: {'lr': 0.0002827280035625302, 'samples': 13404672, 'steps': 69815, 'loss/train': 1.6591180562973022} 08/31/2021 01:48:47 - INFO - __main__ - Step 69817: {'lr': 0.0002827227424807018, 'samples': 13404864, 'steps': 69816, 'loss/train': 1.0803898572921753} 08/31/2021 01:48:47 - INFO - __main__ - Step 69818: {'lr': 0.00028271748138412916, 'samples': 13405056, 'steps': 69817, 'loss/train': 1.5001270771026611} 08/31/2021 01:48:48 - INFO - __main__ - Step 69819: {'lr': 0.0002827122202728145, 'samples': 13405248, 'steps': 69818, 'loss/train': 0.7470311522483826} 08/31/2021 01:48:48 - INFO - __main__ - Step 69820: {'lr': 0.00028270695914676025, 'samples': 13405440, 'steps': 69819, 'loss/train': 0.9707133173942566} 08/31/2021 01:48:50 - INFO - __main__ - Step 69821: {'lr': 0.0002827016980059687, 'samples': 13405632, 'steps': 69820, 'loss/train': 1.643568515777588} 08/31/2021 01:48:50 - INFO - __main__ - Step 69822: {'lr': 0.0002826964368504422, 'samples': 13405824, 'steps': 69821, 'loss/train': 1.69668710231781} 08/31/2021 01:48:51 - INFO - __main__ - Step 69823: {'lr': 0.0002826911756801833, 'samples': 13406016, 'steps': 69822, 'loss/train': 1.2915064096450806} 08/31/2021 01:48:51 - INFO - __main__ - Step 69824: {'lr': 0.0002826859144951942, 'samples': 13406208, 'steps': 69823, 'loss/train': 0.5385603308677673} 08/31/2021 01:48:51 - INFO - __main__ - Step 69825: {'lr': 0.00028268065329547734, 'samples': 13406400, 'steps': 69824, 'loss/train': 0.6689823269844055} 08/31/2021 01:48:53 - INFO - __main__ - Step 69826: {'lr': 0.0002826753920810351, 'samples': 13406592, 'steps': 69825, 'loss/train': 0.13067622482776642} 08/31/2021 01:48:54 - INFO - __main__ - Step 69827: {'lr': 0.00028267013085186987, 'samples': 13406784, 'steps': 69826, 'loss/train': 0.04598454013466835} 08/31/2021 01:48:54 - INFO - __main__ - Step 69828: {'lr': 0.00028266486960798395, 'samples': 13406976, 'steps': 69827, 'loss/train': 0.18507379293441772} 08/31/2021 01:48:55 - INFO - __main__ - Step 69829: {'lr': 0.0002826596083493797, 'samples': 13407168, 'steps': 69828, 'loss/train': 1.5732089281082153} 08/31/2021 01:48:55 - INFO - __main__ - Step 69830: {'lr': 0.0002826543470760596, 'samples': 13407360, 'steps': 69829, 'loss/train': 1.0365164279937744} 08/31/2021 01:48:55 - INFO - __main__ - Step 69831: {'lr': 0.0002826490857880259, 'samples': 13407552, 'steps': 69830, 'loss/train': 0.305986225605011} 08/31/2021 01:48:57 - INFO - __main__ - Step 69832: {'lr': 0.00028264382448528106, 'samples': 13407744, 'steps': 69831, 'loss/train': 1.2288053035736084} 08/31/2021 01:48:57 - INFO - __main__ - Step 69833: {'lr': 0.00028263856316782735, 'samples': 13407936, 'steps': 69832, 'loss/train': 0.232666015625} 08/31/2021 01:48:58 - INFO - __main__ - Step 69834: {'lr': 0.0002826333018356673, 'samples': 13408128, 'steps': 69833, 'loss/train': 0.4472677707672119} 08/31/2021 01:48:58 - INFO - __main__ - Step 69835: {'lr': 0.00028262804048880317, 'samples': 13408320, 'steps': 69834, 'loss/train': 0.8547523021697998} 08/31/2021 01:48:58 - INFO - __main__ - Step 69836: {'lr': 0.00028262277912723734, 'samples': 13408512, 'steps': 69835, 'loss/train': 1.1576695442199707} 08/31/2021 01:49:01 - INFO - __main__ - Step 69837: {'lr': 0.0002826175177509722, 'samples': 13408704, 'steps': 69836, 'loss/train': 0.5686327219009399} 08/31/2021 01:49:01 - INFO - __main__ - Step 69838: {'lr': 0.00028261225636001005, 'samples': 13408896, 'steps': 69837, 'loss/train': 1.5274096727371216} 08/31/2021 01:49:01 - INFO - __main__ - Step 69839: {'lr': 0.0002826069949543533, 'samples': 13409088, 'steps': 69838, 'loss/train': 1.0310157537460327} 08/31/2021 01:49:02 - INFO - __main__ - Step 69840: {'lr': 0.0002826017335340045, 'samples': 13409280, 'steps': 69839, 'loss/train': 1.7817225456237793} 08/31/2021 01:49:02 - INFO - __main__ - Step 69841: {'lr': 0.00028259647209896574, 'samples': 13409472, 'steps': 69840, 'loss/train': 0.9145523905754089} 08/31/2021 01:49:03 - INFO - __main__ - Step 69842: {'lr': 0.00028259121064923954, 'samples': 13409664, 'steps': 69841, 'loss/train': 1.2261416912078857} 08/31/2021 01:49:04 - INFO - __main__ - Step 69843: {'lr': 0.0002825859491848282, 'samples': 13409856, 'steps': 69842, 'loss/train': 1.228484034538269} 08/31/2021 01:49:04 - INFO - __main__ - Step 69844: {'lr': 0.00028258068770573415, 'samples': 13410048, 'steps': 69843, 'loss/train': 1.021642804145813} 08/31/2021 01:49:05 - INFO - __main__ - Step 69845: {'lr': 0.00028257542621195974, 'samples': 13410240, 'steps': 69844, 'loss/train': 0.9934737682342529} 08/31/2021 01:49:05 - INFO - __main__ - Step 69846: {'lr': 0.0002825701647035074, 'samples': 13410432, 'steps': 69845, 'loss/train': 0.28352877497673035} 08/31/2021 01:49:07 - INFO - __main__ - Step 69847: {'lr': 0.00028256490318037946, 'samples': 13410624, 'steps': 69846, 'loss/train': 1.4651224613189697} 08/31/2021 01:49:07 - INFO - __main__ - Step 69848: {'lr': 0.00028255964164257825, 'samples': 13410816, 'steps': 69847, 'loss/train': 1.6709891557693481} 08/31/2021 01:49:08 - INFO - __main__ - Step 69849: {'lr': 0.00028255438009010616, 'samples': 13411008, 'steps': 69848, 'loss/train': 1.1285247802734375} 08/31/2021 01:49:08 - INFO - __main__ - Step 69850: {'lr': 0.0002825491185229655, 'samples': 13411200, 'steps': 69849, 'loss/train': 0.19367101788520813} 08/31/2021 01:49:08 - INFO - __main__ - Step 69851: {'lr': 0.00028254385694115883, 'samples': 13411392, 'steps': 69850, 'loss/train': 1.2044187784194946} 08/31/2021 01:49:10 - INFO - __main__ - Step 69852: {'lr': 0.0002825385953446883, 'samples': 13411584, 'steps': 69851, 'loss/train': 0.056067001074552536} 08/31/2021 01:49:10 - INFO - __main__ - Step 69853: {'lr': 0.0002825333337335564, 'samples': 13411776, 'steps': 69852, 'loss/train': 1.0703247785568237} 08/31/2021 01:49:11 - INFO - __main__ - Step 69854: {'lr': 0.00028252807210776555, 'samples': 13411968, 'steps': 69853, 'loss/train': 1.298195242881775} 08/31/2021 01:49:11 - INFO - __main__ - Step 69855: {'lr': 0.000282522810467318, 'samples': 13412160, 'steps': 69854, 'loss/train': 1.468064785003662} 08/31/2021 01:49:11 - INFO - __main__ - Step 69856: {'lr': 0.0002825175488122162, 'samples': 13412352, 'steps': 69855, 'loss/train': 1.237064242362976} 08/31/2021 01:49:13 - INFO - __main__ - Step 69857: {'lr': 0.0002825122871424625, 'samples': 13412544, 'steps': 69856, 'loss/train': 1.3591880798339844} 08/31/2021 01:49:13 - INFO - __main__ - Step 69858: {'lr': 0.0002825070254580592, 'samples': 13412736, 'steps': 69857, 'loss/train': 0.9036276936531067} 08/31/2021 01:49:14 - INFO - __main__ - Step 69859: {'lr': 0.0002825017637590088, 'samples': 13412928, 'steps': 69858, 'loss/train': 1.1108087301254272} 08/31/2021 01:49:14 - INFO - __main__ - Step 69860: {'lr': 0.0002824965020453135, 'samples': 13413120, 'steps': 69859, 'loss/train': 1.1831413507461548} 08/31/2021 01:49:14 - INFO - __main__ - Step 69861: {'lr': 0.0002824912403169759, 'samples': 13413312, 'steps': 69860, 'loss/train': 1.1802555322647095} 08/31/2021 01:49:15 - INFO - __main__ - Step 69862: {'lr': 0.0002824859785739982, 'samples': 13413504, 'steps': 69861, 'loss/train': 1.3539531230926514} 08/31/2021 01:49:16 - INFO - __main__ - Step 69863: {'lr': 0.0002824807168163829, 'samples': 13413696, 'steps': 69862, 'loss/train': 1.2143912315368652} 08/31/2021 01:49:17 - INFO - __main__ - Step 69864: {'lr': 0.00028247545504413217, 'samples': 13413888, 'steps': 69863, 'loss/train': 0.9143357276916504} 08/31/2021 01:49:17 - INFO - __main__ - Step 69865: {'lr': 0.0002824701932572485, 'samples': 13414080, 'steps': 69864, 'loss/train': 1.3215347528457642} 08/31/2021 01:49:17 - INFO - __main__ - Step 69866: {'lr': 0.00028246493145573433, 'samples': 13414272, 'steps': 69865, 'loss/train': 0.5114234685897827} 08/31/2021 01:49:18 - INFO - __main__ - Step 69867: {'lr': 0.00028245966963959203, 'samples': 13414464, 'steps': 69866, 'loss/train': 1.3352437019348145} 08/31/2021 01:49:19 - INFO - __main__ - Step 69868: {'lr': 0.00028245440780882373, 'samples': 13414656, 'steps': 69867, 'loss/train': 1.1631633043289185} 08/31/2021 01:49:20 - INFO - __main__ - Step 69869: {'lr': 0.0002824491459634321, 'samples': 13414848, 'steps': 69868, 'loss/train': 1.3513199090957642} 08/31/2021 01:49:20 - INFO - __main__ - Step 69870: {'lr': 0.0002824438841034194, 'samples': 13415040, 'steps': 69869, 'loss/train': 0.9103039503097534} 08/31/2021 01:49:20 - INFO - __main__ - Step 69871: {'lr': 0.00028243862222878784, 'samples': 13415232, 'steps': 69870, 'loss/train': 2.134162187576294} 08/31/2021 01:49:21 - INFO - __main__ - Step 69872: {'lr': 0.00028243336033954, 'samples': 13415424, 'steps': 69871, 'loss/train': 1.1002206802368164} 08/31/2021 01:49:23 - INFO - __main__ - Step 69873: {'lr': 0.00028242809843567827, 'samples': 13415616, 'steps': 69872, 'loss/train': 2.0837786197662354} 08/31/2021 01:49:23 - INFO - __main__ - Step 69874: {'lr': 0.0002824228365172049, 'samples': 13415808, 'steps': 69873, 'loss/train': 1.1760015487670898} 08/31/2021 01:49:23 - INFO - __main__ - Step 69875: {'lr': 0.00028241757458412234, 'samples': 13416000, 'steps': 69874, 'loss/train': 2.570422887802124} 08/31/2021 01:49:24 - INFO - __main__ - Step 69876: {'lr': 0.00028241231263643286, 'samples': 13416192, 'steps': 69875, 'loss/train': 1.163046956062317} 08/31/2021 01:49:24 - INFO - __main__ - Step 69877: {'lr': 0.00028240705067413886, 'samples': 13416384, 'steps': 69876, 'loss/train': 1.1912784576416016} 08/31/2021 01:49:24 - INFO - __main__ - Step 69878: {'lr': 0.0002824017886972428, 'samples': 13416576, 'steps': 69877, 'loss/train': 1.1717849969863892} 08/31/2021 01:49:26 - INFO - __main__ - Step 69879: {'lr': 0.00028239652670574697, 'samples': 13416768, 'steps': 69878, 'loss/train': 1.3407623767852783} 08/31/2021 01:49:27 - INFO - __main__ - Step 69880: {'lr': 0.00028239126469965374, 'samples': 13416960, 'steps': 69879, 'loss/train': 1.5813010931015015} 08/31/2021 01:49:27 - INFO - __main__ - Step 69881: {'lr': 0.00028238600267896564, 'samples': 13417152, 'steps': 69880, 'loss/train': 1.1898938417434692} 08/31/2021 01:49:27 - INFO - __main__ - Step 69882: {'lr': 0.00028238074064368477, 'samples': 13417344, 'steps': 69881, 'loss/train': 1.3113657236099243} 08/31/2021 01:49:28 - INFO - __main__ - Step 69883: {'lr': 0.0002823754785938137, 'samples': 13417536, 'steps': 69882, 'loss/train': 0.7087445259094238} 08/31/2021 01:49:29 - INFO - __main__ - Step 69884: {'lr': 0.00028237021652935466, 'samples': 13417728, 'steps': 69883, 'loss/train': 0.8225330710411072} 08/31/2021 01:49:30 - INFO - __main__ - Step 69885: {'lr': 0.0002823649544503102, 'samples': 13417920, 'steps': 69884, 'loss/train': 1.3779419660568237} 08/31/2021 01:49:30 - INFO - __main__ - Step 69886: {'lr': 0.0002823596923566825, 'samples': 13418112, 'steps': 69885, 'loss/train': 0.06960663944482803} 08/31/2021 01:49:31 - INFO - __main__ - Step 69887: {'lr': 0.0002823544302484741, 'samples': 13418304, 'steps': 69886, 'loss/train': 0.160548597574234} 08/31/2021 01:49:31 - INFO - __main__ - Step 69888: {'lr': 0.0002823491681256873, 'samples': 13418496, 'steps': 69887, 'loss/train': 1.2476224899291992} 08/31/2021 01:49:31 - INFO - __main__ - Step 69889: {'lr': 0.0002823439059883244, 'samples': 13418688, 'steps': 69888, 'loss/train': 0.6734285950660706} 08/31/2021 01:49:33 - INFO - __main__ - Step 69890: {'lr': 0.00028233864383638783, 'samples': 13418880, 'steps': 69889, 'loss/train': 1.4686331748962402} 08/31/2021 01:49:33 - INFO - __main__ - Step 69891: {'lr': 0.00028233338166988, 'samples': 13419072, 'steps': 69890, 'loss/train': 1.4530161619186401} 08/31/2021 01:49:34 - INFO - __main__ - Step 69892: {'lr': 0.0002823281194888032, 'samples': 13419264, 'steps': 69891, 'loss/train': 1.8000918626785278} 08/31/2021 01:49:34 - INFO - __main__ - Step 69893: {'lr': 0.00028232285729315996, 'samples': 13419456, 'steps': 69892, 'loss/train': 1.2210156917572021} 08/31/2021 01:49:34 - INFO - __main__ - Step 69894: {'lr': 0.00028231759508295245, 'samples': 13419648, 'steps': 69893, 'loss/train': 1.3602274656295776} 08/31/2021 01:49:35 - INFO - __main__ - Step 69895: {'lr': 0.00028231233285818313, 'samples': 13419840, 'steps': 69894, 'loss/train': 0.2909322679042816} 08/31/2021 01:49:37 - INFO - __main__ - Step 69896: {'lr': 0.0002823070706188544, 'samples': 13420032, 'steps': 69895, 'loss/train': 1.9300113916397095} 08/31/2021 01:49:37 - INFO - __main__ - Step 69897: {'lr': 0.0002823018083649686, 'samples': 13420224, 'steps': 69896, 'loss/train': 0.9809861183166504} 08/31/2021 01:49:38 - INFO - __main__ - Step 69898: {'lr': 0.00028229654609652816, 'samples': 13420416, 'steps': 69897, 'loss/train': 0.5199548602104187} 08/31/2021 01:49:38 - INFO - __main__ - Step 69899: {'lr': 0.0002822912838135353, 'samples': 13420608, 'steps': 69898, 'loss/train': 1.1921409368515015} 08/31/2021 01:49:38 - INFO - __main__ - Step 69900: {'lr': 0.0002822860215159925, 'samples': 13420800, 'steps': 69899, 'loss/train': 0.7738382816314697} 08/31/2021 01:49:40 - INFO - __main__ - Step 69901: {'lr': 0.00028228075920390215, 'samples': 13420992, 'steps': 69900, 'loss/train': 1.0736325979232788} 08/31/2021 01:49:40 - INFO - __main__ - Step 69902: {'lr': 0.00028227549687726656, 'samples': 13421184, 'steps': 69901, 'loss/train': 0.5848528146743774} 08/31/2021 01:49:41 - INFO - __main__ - Step 69903: {'lr': 0.00028227023453608813, 'samples': 13421376, 'steps': 69902, 'loss/train': 1.4622505903244019} 08/31/2021 01:49:41 - INFO - __main__ - Step 69904: {'lr': 0.0002822649721803693, 'samples': 13421568, 'steps': 69903, 'loss/train': 1.3547868728637695} 08/31/2021 01:49:41 - INFO - __main__ - Step 69905: {'lr': 0.00028225970981011236, 'samples': 13421760, 'steps': 69904, 'loss/train': 1.0147168636322021} 08/31/2021 01:49:43 - INFO - __main__ - Step 69906: {'lr': 0.00028225444742531957, 'samples': 13421952, 'steps': 69905, 'loss/train': 1.7476085424423218} 08/31/2021 01:49:43 - INFO - __main__ - Step 69907: {'lr': 0.0002822491850259935, 'samples': 13422144, 'steps': 69906, 'loss/train': 1.0804262161254883} 08/31/2021 01:49:44 - INFO - __main__ - Step 69908: {'lr': 0.00028224392261213643, 'samples': 13422336, 'steps': 69907, 'loss/train': 1.3140108585357666} 08/31/2021 01:49:44 - INFO - __main__ - Step 69909: {'lr': 0.00028223866018375085, 'samples': 13422528, 'steps': 69908, 'loss/train': 1.085764765739441} 08/31/2021 01:49:45 - INFO - __main__ - Step 69910: {'lr': 0.0002822333977408389, 'samples': 13422720, 'steps': 69909, 'loss/train': 1.3997652530670166} 08/31/2021 01:49:46 - INFO - __main__ - Step 69911: {'lr': 0.0002822281352834031, 'samples': 13422912, 'steps': 69910, 'loss/train': 0.06760300695896149} 08/31/2021 01:49:46 - INFO - __main__ - Step 69912: {'lr': 0.00028222287281144584, 'samples': 13423104, 'steps': 69911, 'loss/train': 1.2049989700317383} 08/31/2021 01:49:47 - INFO - __main__ - Step 69913: {'lr': 0.0002822176103249694, 'samples': 13423296, 'steps': 69912, 'loss/train': 1.2819615602493286} 08/31/2021 01:49:47 - INFO - __main__ - Step 69914: {'lr': 0.0002822123478239763, 'samples': 13423488, 'steps': 69913, 'loss/train': 1.5549455881118774} 08/31/2021 01:49:47 - INFO - __main__ - Step 69915: {'lr': 0.0002822070853084687, 'samples': 13423680, 'steps': 69914, 'loss/train': 1.437334656715393} 08/31/2021 01:49:49 - INFO - __main__ - Step 69916: {'lr': 0.00028220182277844915, 'samples': 13423872, 'steps': 69915, 'loss/train': 1.1907155513763428} 08/31/2021 01:49:49 - INFO - __main__ - Step 69917: {'lr': 0.00028219656023391993, 'samples': 13424064, 'steps': 69916, 'loss/train': 1.2589221000671387} 08/31/2021 01:49:50 - INFO - __main__ - Step 69918: {'lr': 0.00028219129767488344, 'samples': 13424256, 'steps': 69917, 'loss/train': 1.3504480123519897} 08/31/2021 01:49:50 - INFO - __main__ - Step 69919: {'lr': 0.000282186035101342, 'samples': 13424448, 'steps': 69918, 'loss/train': 1.2251936197280884} 08/31/2021 01:49:51 - INFO - __main__ - Step 69920: {'lr': 0.0002821807725132981, 'samples': 13424640, 'steps': 69919, 'loss/train': 1.4153854846954346} 08/31/2021 01:49:52 - INFO - __main__ - Step 69921: {'lr': 0.0002821755099107541, 'samples': 13424832, 'steps': 69920, 'loss/train': 0.7783285975456238} 08/31/2021 01:49:52 - INFO - __main__ - Step 69922: {'lr': 0.0002821702472937122, 'samples': 13425024, 'steps': 69921, 'loss/train': 0.8597663044929504} 08/31/2021 01:49:53 - INFO - __main__ - Step 69923: {'lr': 0.0002821649846621749, 'samples': 13425216, 'steps': 69922, 'loss/train': 1.5017529726028442} 08/31/2021 01:49:53 - INFO - __main__ - Step 69924: {'lr': 0.00028215972201614455, 'samples': 13425408, 'steps': 69923, 'loss/train': 1.6013818979263306} 08/31/2021 01:49:53 - INFO - __main__ - Step 69925: {'lr': 0.0002821544593556235, 'samples': 13425600, 'steps': 69924, 'loss/train': 0.7032907009124756} 08/31/2021 01:49:55 - INFO - __main__ - Step 69926: {'lr': 0.0002821491966806142, 'samples': 13425792, 'steps': 69925, 'loss/train': 0.2661946713924408} 08/31/2021 01:49:55 - INFO - __main__ - Step 69927: {'lr': 0.00028214393399111893, 'samples': 13425984, 'steps': 69926, 'loss/train': 1.1052894592285156} 08/31/2021 01:49:56 - INFO - __main__ - Step 69928: {'lr': 0.0002821386712871402, 'samples': 13426176, 'steps': 69927, 'loss/train': 1.1950733661651611} 08/31/2021 01:49:56 - INFO - __main__ - Step 69929: {'lr': 0.0002821334085686802, 'samples': 13426368, 'steps': 69928, 'loss/train': 1.3849912881851196} 08/31/2021 01:49:56 - INFO - __main__ - Step 69930: {'lr': 0.00028212814583574136, 'samples': 13426560, 'steps': 69929, 'loss/train': 1.2573732137680054} 08/31/2021 01:49:57 - INFO - __main__ - Step 69931: {'lr': 0.00028212288308832615, 'samples': 13426752, 'steps': 69930, 'loss/train': 2.890404462814331} 08/31/2021 01:49:58 - INFO - __main__ - Step 69932: {'lr': 0.0002821176203264368, 'samples': 13426944, 'steps': 69931, 'loss/train': 1.4360142946243286} 08/31/2021 01:49:59 - INFO - __main__ - Step 69933: {'lr': 0.00028211235755007575, 'samples': 13427136, 'steps': 69932, 'loss/train': 0.9427715539932251} 08/31/2021 01:49:59 - INFO - __main__ - Step 69934: {'lr': 0.00028210709475924535, 'samples': 13427328, 'steps': 69933, 'loss/train': 0.11944568157196045} 08/31/2021 01:50:00 - INFO - __main__ - Step 69935: {'lr': 0.00028210183195394805, 'samples': 13427520, 'steps': 69934, 'loss/train': 1.463945984840393} 08/31/2021 01:50:00 - INFO - __main__ - Step 69936: {'lr': 0.00028209656913418614, 'samples': 13427712, 'steps': 69935, 'loss/train': 1.0769977569580078} 08/31/2021 01:50:01 - INFO - __main__ - Step 69937: {'lr': 0.000282091306299962, 'samples': 13427904, 'steps': 69936, 'loss/train': 1.178403377532959} 08/31/2021 01:50:02 - INFO - __main__ - Step 69938: {'lr': 0.00028208604345127797, 'samples': 13428096, 'steps': 69937, 'loss/train': 0.758830726146698} 08/31/2021 01:50:02 - INFO - __main__ - Step 69939: {'lr': 0.00028208078058813654, 'samples': 13428288, 'steps': 69938, 'loss/train': 1.083876609802246} 08/31/2021 01:50:02 - INFO - __main__ - Step 69940: {'lr': 0.00028207551771054, 'samples': 13428480, 'steps': 69939, 'loss/train': 1.0156500339508057} 08/31/2021 01:50:03 - INFO - __main__ - Step 69941: {'lr': 0.0002820702548184907, 'samples': 13428672, 'steps': 69940, 'loss/train': 1.6233930587768555} 08/31/2021 01:50:04 - INFO - __main__ - Step 69942: {'lr': 0.000282064991911991, 'samples': 13428864, 'steps': 69941, 'loss/train': 1.5985472202301025} 08/31/2021 01:50:05 - INFO - __main__ - Step 69943: {'lr': 0.0002820597289910434, 'samples': 13429056, 'steps': 69942, 'loss/train': 0.8860101699829102} 08/31/2021 01:50:05 - INFO - __main__ - Step 69944: {'lr': 0.00028205446605565, 'samples': 13429248, 'steps': 69943, 'loss/train': 0.8535700440406799} 08/31/2021 01:50:05 - INFO - __main__ - Step 69945: {'lr': 0.00028204920310581356, 'samples': 13429440, 'steps': 69944, 'loss/train': 1.8448069095611572} 08/31/2021 01:50:06 - INFO - __main__ - Step 69946: {'lr': 0.0002820439401415361, 'samples': 13429632, 'steps': 69945, 'loss/train': 1.3758702278137207} 08/31/2021 01:50:08 - INFO - __main__ - Step 69947: {'lr': 0.0002820386771628202, 'samples': 13429824, 'steps': 69946, 'loss/train': 0.8191783428192139} 08/31/2021 01:50:08 - INFO - __main__ - Step 69948: {'lr': 0.00028203341416966824, 'samples': 13430016, 'steps': 69947, 'loss/train': 1.1772680282592773} 08/31/2021 01:50:09 - INFO - __main__ - Step 69949: {'lr': 0.0002820281511620824, 'samples': 13430208, 'steps': 69948, 'loss/train': 0.7814431190490723} 08/31/2021 01:50:09 - INFO - __main__ - Step 69950: {'lr': 0.0002820228881400652, 'samples': 13430400, 'steps': 69949, 'loss/train': 0.7370638847351074} 08/31/2021 01:50:09 - INFO - __main__ - Step 69951: {'lr': 0.000282017625103619, 'samples': 13430592, 'steps': 69950, 'loss/train': 0.7600519061088562} 08/31/2021 01:50:11 - INFO - __main__ - Step 69952: {'lr': 0.0002820123620527462, 'samples': 13430784, 'steps': 69951, 'loss/train': 1.1368738412857056} 08/31/2021 01:50:11 - INFO - __main__ - Step 69953: {'lr': 0.000282007098987449, 'samples': 13430976, 'steps': 69952, 'loss/train': 0.20924066007137299} 08/31/2021 01:50:12 - INFO - __main__ - Step 69954: {'lr': 0.00028200183590773, 'samples': 13431168, 'steps': 69953, 'loss/train': 1.3699896335601807} 08/31/2021 01:50:12 - INFO - __main__ - Step 69955: {'lr': 0.00028199657281359144, 'samples': 13431360, 'steps': 69954, 'loss/train': 1.2368541955947876} 08/31/2021 01:50:12 - INFO - __main__ - Step 69956: {'lr': 0.00028199130970503575, 'samples': 13431552, 'steps': 69955, 'loss/train': 1.6198917627334595} 08/31/2021 01:50:14 - INFO - __main__ - Step 69957: {'lr': 0.00028198604658206516, 'samples': 13431744, 'steps': 69956, 'loss/train': 1.0832558870315552} 08/31/2021 01:50:14 - INFO - __main__ - Step 69958: {'lr': 0.0002819807834446822, 'samples': 13431936, 'steps': 69957, 'loss/train': 1.3526763916015625} 08/31/2021 01:50:15 - INFO - __main__ - Step 69959: {'lr': 0.0002819755202928892, 'samples': 13432128, 'steps': 69958, 'loss/train': 1.1549866199493408} 08/31/2021 01:50:15 - INFO - __main__ - Step 69960: {'lr': 0.0002819702571266886, 'samples': 13432320, 'steps': 69959, 'loss/train': 1.8190538883209229} 08/31/2021 01:50:16 - INFO - __main__ - Step 69961: {'lr': 0.0002819649939460826, 'samples': 13432512, 'steps': 69960, 'loss/train': 1.0135098695755005} 08/31/2021 01:50:16 - INFO - __main__ - Step 69962: {'lr': 0.0002819597307510737, 'samples': 13432704, 'steps': 69961, 'loss/train': 1.3431476354599} 08/31/2021 01:50:17 - INFO - __main__ - Step 69963: {'lr': 0.0002819544675416642, 'samples': 13432896, 'steps': 69962, 'loss/train': 0.06741678714752197} 08/31/2021 01:50:18 - INFO - __main__ - Step 69964: {'lr': 0.0002819492043178566, 'samples': 13433088, 'steps': 69963, 'loss/train': 0.6653690934181213} 08/31/2021 01:50:18 - INFO - __main__ - Step 69965: {'lr': 0.0002819439410796531, 'samples': 13433280, 'steps': 69964, 'loss/train': 1.2024301290512085} 08/31/2021 01:50:19 - INFO - __main__ - Step 69966: {'lr': 0.00028193867782705617, 'samples': 13433472, 'steps': 69965, 'loss/train': 1.398436427116394} 08/31/2021 01:50:19 - INFO - __main__ - Step 69967: {'lr': 0.0002819334145600682, 'samples': 13433664, 'steps': 69966, 'loss/train': 1.5649759769439697} 08/31/2021 01:50:20 - INFO - __main__ - Step 69968: {'lr': 0.0002819281512786915, 'samples': 13433856, 'steps': 69967, 'loss/train': 1.3945374488830566} 08/31/2021 01:50:21 - INFO - __main__ - Step 69969: {'lr': 0.0002819228879829285, 'samples': 13434048, 'steps': 69968, 'loss/train': 1.309427261352539} 08/31/2021 01:50:21 - INFO - __main__ - Step 69970: {'lr': 0.00028191762467278146, 'samples': 13434240, 'steps': 69969, 'loss/train': 0.8705837726593018} 08/31/2021 01:50:22 - INFO - __main__ - Step 69971: {'lr': 0.00028191236134825285, 'samples': 13434432, 'steps': 69970, 'loss/train': 1.59339439868927} 08/31/2021 01:50:22 - INFO - __main__ - Step 69972: {'lr': 0.0002819070980093451, 'samples': 13434624, 'steps': 69971, 'loss/train': 1.0815258026123047} 08/31/2021 01:50:23 - INFO - __main__ - Step 69973: {'lr': 0.0002819018346560604, 'samples': 13434816, 'steps': 69972, 'loss/train': 1.334007978439331} 08/31/2021 01:50:24 - INFO - __main__ - Step 69974: {'lr': 0.0002818965712884013, 'samples': 13435008, 'steps': 69973, 'loss/train': 1.637495994567871} 08/31/2021 01:50:24 - INFO - __main__ - Step 69975: {'lr': 0.0002818913079063701, 'samples': 13435200, 'steps': 69974, 'loss/train': 1.2492438554763794} 08/31/2021 01:50:25 - INFO - __main__ - Step 69976: {'lr': 0.00028188604450996913, 'samples': 13435392, 'steps': 69975, 'loss/train': 1.2267491817474365} 08/31/2021 01:50:25 - INFO - __main__ - Step 69977: {'lr': 0.00028188078109920087, 'samples': 13435584, 'steps': 69976, 'loss/train': 1.3591428995132446} 08/31/2021 01:50:26 - INFO - __main__ - Step 69978: {'lr': 0.0002818755176740675, 'samples': 13435776, 'steps': 69977, 'loss/train': 1.9204021692276} 08/31/2021 01:50:27 - INFO - __main__ - Step 69979: {'lr': 0.0002818702542345716, 'samples': 13435968, 'steps': 69978, 'loss/train': 1.177259087562561} 08/31/2021 01:50:27 - INFO - __main__ - Step 69980: {'lr': 0.00028186499078071544, 'samples': 13436160, 'steps': 69979, 'loss/train': 0.5898385047912598} 08/31/2021 01:50:27 - INFO - __main__ - Step 69981: {'lr': 0.0002818597273125014, 'samples': 13436352, 'steps': 69980, 'loss/train': 1.0233213901519775} 08/31/2021 01:50:28 - INFO - __main__ - Step 69982: {'lr': 0.00028185446382993193, 'samples': 13436544, 'steps': 69981, 'loss/train': 1.386724829673767} 08/31/2021 01:50:29 - INFO - __main__ - Step 69983: {'lr': 0.0002818492003330092, 'samples': 13436736, 'steps': 69982, 'loss/train': 1.359192967414856} 08/31/2021 01:50:30 - INFO - __main__ - Step 69984: {'lr': 0.00028184393682173574, 'samples': 13436928, 'steps': 69983, 'loss/train': 1.2401185035705566} 08/31/2021 01:50:30 - INFO - __main__ - Step 69985: {'lr': 0.000281838673296114, 'samples': 13437120, 'steps': 69984, 'loss/train': 0.07004343718290329} 08/31/2021 01:50:31 - INFO - __main__ - Step 69986: {'lr': 0.0002818334097561461, 'samples': 13437312, 'steps': 69985, 'loss/train': 0.7641000747680664} 08/31/2021 01:50:31 - INFO - __main__ - Step 69987: {'lr': 0.00028182814620183463, 'samples': 13437504, 'steps': 69986, 'loss/train': 1.364078164100647} 08/31/2021 01:50:32 - INFO - __main__ - Step 69988: {'lr': 0.00028182288263318197, 'samples': 13437696, 'steps': 69987, 'loss/train': 1.240027904510498} 08/31/2021 01:50:33 - INFO - __main__ - Step 69989: {'lr': 0.0002818176190501903, 'samples': 13437888, 'steps': 69988, 'loss/train': 0.9661622047424316} 08/31/2021 01:50:33 - INFO - __main__ - Step 69990: {'lr': 0.0002818123554528621, 'samples': 13438080, 'steps': 69989, 'loss/train': 0.3014635145664215} 08/31/2021 01:50:34 - INFO - __main__ - Step 69991: {'lr': 0.0002818070918411998, 'samples': 13438272, 'steps': 69990, 'loss/train': 1.7611429691314697} 08/31/2021 01:50:34 - INFO - __main__ - Step 69992: {'lr': 0.00028180182821520565, 'samples': 13438464, 'steps': 69991, 'loss/train': 1.300383448600769} 08/31/2021 01:50:36 - INFO - __main__ - Step 69993: {'lr': 0.00028179656457488214, 'samples': 13438656, 'steps': 69992, 'loss/train': 1.6170333623886108} 08/31/2021 01:50:36 - INFO - __main__ - Step 69994: {'lr': 0.00028179130092023154, 'samples': 13438848, 'steps': 69993, 'loss/train': 1.3407676219940186} 08/31/2021 01:50:36 - INFO - __main__ - Step 69995: {'lr': 0.0002817860372512564, 'samples': 13439040, 'steps': 69994, 'loss/train': 1.5283721685409546} 08/31/2021 01:50:37 - INFO - __main__ - Step 69996: {'lr': 0.00028178077356795885, 'samples': 13439232, 'steps': 69995, 'loss/train': 1.9190783500671387} 08/31/2021 01:50:37 - INFO - __main__ - Step 69997: {'lr': 0.0002817755098703413, 'samples': 13439424, 'steps': 69996, 'loss/train': 1.0990285873413086} 08/31/2021 01:50:37 - INFO - __main__ - Step 69998: {'lr': 0.00028177024615840636, 'samples': 13439616, 'steps': 69997, 'loss/train': 1.1088006496429443} 08/31/2021 01:50:39 - INFO - __main__ - Step 69999: {'lr': 0.00028176498243215613, 'samples': 13439808, 'steps': 69998, 'loss/train': 1.210331916809082} 08/31/2021 01:50:39 - INFO - __main__ - Step 70000: {'lr': 0.00028175971869159313, 'samples': 13440000, 'steps': 69999, 'loss/train': 0.9798736572265625} 08/31/2021 01:50:40 - INFO - __main__ - Step 70001: {'lr': 0.0002817544549367197, 'samples': 13440192, 'steps': 70000, 'loss/train': 0.07748722285032272} 08/31/2021 01:50:40 - INFO - __main__ - Step 70002: {'lr': 0.0002817491911675382, 'samples': 13440384, 'steps': 70001, 'loss/train': 1.0023819208145142} 08/31/2021 01:50:41 - INFO - __main__ - Step 70003: {'lr': 0.00028174392738405094, 'samples': 13440576, 'steps': 70002, 'loss/train': 1.3486731052398682} 08/31/2021 01:50:43 - INFO - __main__ - Step 70004: {'lr': 0.00028173866358626045, 'samples': 13440768, 'steps': 70003, 'loss/train': 1.6337532997131348} 08/31/2021 01:50:43 - INFO - __main__ - Step 70005: {'lr': 0.00028173339977416895, 'samples': 13440960, 'steps': 70004, 'loss/train': 1.7786133289337158} 08/31/2021 01:50:43 - INFO - __main__ - Step 70006: {'lr': 0.0002817281359477789, 'samples': 13441152, 'steps': 70005, 'loss/train': 1.0866810083389282} 08/31/2021 01:50:44 - INFO - __main__ - Step 70007: {'lr': 0.0002817228721070926, 'samples': 13441344, 'steps': 70006, 'loss/train': 1.2504619359970093} 08/31/2021 01:50:44 - INFO - __main__ - Step 70008: {'lr': 0.00028171760825211254, 'samples': 13441536, 'steps': 70007, 'loss/train': 1.7838438749313354} 08/31/2021 01:50:46 - INFO - __main__ - Step 70009: {'lr': 0.0002817123443828409, 'samples': 13441728, 'steps': 70008, 'loss/train': 0.7600383162498474} 08/31/2021 01:50:46 - INFO - __main__ - Step 70010: {'lr': 0.0002817070804992803, 'samples': 13441920, 'steps': 70009, 'loss/train': 1.1657835245132446} 08/31/2021 01:50:46 - INFO - __main__ - Step 70011: {'lr': 0.0002817018166014329, 'samples': 13442112, 'steps': 70010, 'loss/train': 1.4070391654968262} 08/31/2021 01:50:47 - INFO - __main__ - Step 70012: {'lr': 0.0002816965526893011, 'samples': 13442304, 'steps': 70011, 'loss/train': 1.758155345916748} 08/31/2021 01:50:47 - INFO - __main__ - Step 70013: {'lr': 0.0002816912887628874, 'samples': 13442496, 'steps': 70012, 'loss/train': 1.560766577720642} 08/31/2021 01:50:48 - INFO - __main__ - Step 70014: {'lr': 0.00028168602482219406, 'samples': 13442688, 'steps': 70013, 'loss/train': 1.6634547710418701} 08/31/2021 01:50:49 - INFO - __main__ - Step 70015: {'lr': 0.00028168076086722353, 'samples': 13442880, 'steps': 70014, 'loss/train': 1.3923193216323853} 08/31/2021 01:50:49 - INFO - __main__ - Step 70016: {'lr': 0.0002816754968979781, 'samples': 13443072, 'steps': 70015, 'loss/train': 1.203087568283081} 08/31/2021 01:50:50 - INFO - __main__ - Step 70017: {'lr': 0.0002816702329144602, 'samples': 13443264, 'steps': 70016, 'loss/train': 1.1917014122009277} 08/31/2021 01:50:50 - INFO - __main__ - Step 70018: {'lr': 0.0002816649689166722, 'samples': 13443456, 'steps': 70017, 'loss/train': 1.0064131021499634} 08/31/2021 01:50:52 - INFO - __main__ - Step 70019: {'lr': 0.0002816597049046164, 'samples': 13443648, 'steps': 70018, 'loss/train': 1.2321900129318237} 08/31/2021 01:50:52 - INFO - __main__ - Step 70020: {'lr': 0.00028165444087829524, 'samples': 13443840, 'steps': 70019, 'loss/train': 1.6238816976547241} 08/31/2021 01:50:53 - INFO - __main__ - Step 70021: {'lr': 0.00028164917683771106, 'samples': 13444032, 'steps': 70020, 'loss/train': 1.394282579421997} 08/31/2021 01:50:53 - INFO - __main__ - Step 70022: {'lr': 0.00028164391278286637, 'samples': 13444224, 'steps': 70021, 'loss/train': 1.02409827709198} 08/31/2021 01:50:53 - INFO - __main__ - Step 70023: {'lr': 0.00028163864871376333, 'samples': 13444416, 'steps': 70022, 'loss/train': 0.9146462678909302} 08/31/2021 01:50:54 - INFO - __main__ - Step 70024: {'lr': 0.0002816333846304044, 'samples': 13444608, 'steps': 70023, 'loss/train': 0.018053444102406502} 08/31/2021 01:50:55 - INFO - __main__ - Step 70025: {'lr': 0.0002816281205327919, 'samples': 13444800, 'steps': 70024, 'loss/train': 1.0057176351547241} 08/31/2021 01:50:56 - INFO - __main__ - Step 70026: {'lr': 0.00028162285642092835, 'samples': 13444992, 'steps': 70025, 'loss/train': 1.218501091003418} 08/31/2021 01:50:56 - INFO - __main__ - Step 70027: {'lr': 0.000281617592294816, 'samples': 13445184, 'steps': 70026, 'loss/train': 0.744834303855896} 08/31/2021 01:50:56 - INFO - __main__ - Step 70028: {'lr': 0.00028161232815445726, 'samples': 13445376, 'steps': 70027, 'loss/train': 2.004805088043213} 08/31/2021 01:50:57 - INFO - __main__ - Step 70029: {'lr': 0.0002816070639998545, 'samples': 13445568, 'steps': 70028, 'loss/train': 0.6087831854820251} 08/31/2021 01:50:59 - INFO - __main__ - Step 70030: {'lr': 0.00028160179983101005, 'samples': 13445760, 'steps': 70029, 'loss/train': 0.23718592524528503} 08/31/2021 01:50:59 - INFO - __main__ - Step 70031: {'lr': 0.0002815965356479263, 'samples': 13445952, 'steps': 70030, 'loss/train': 0.9886587262153625} 08/31/2021 01:50:59 - INFO - __main__ - Step 70032: {'lr': 0.0002815912714506056, 'samples': 13446144, 'steps': 70031, 'loss/train': 1.3914875984191895} 08/31/2021 01:51:00 - INFO - __main__ - Step 70033: {'lr': 0.0002815860072390505, 'samples': 13446336, 'steps': 70032, 'loss/train': 0.9718757271766663} 08/31/2021 01:51:00 - INFO - __main__ - Step 70034: {'lr': 0.0002815807430132632, 'samples': 13446528, 'steps': 70033, 'loss/train': 1.3938969373703003} 08/31/2021 01:51:00 - INFO - __main__ - Step 70035: {'lr': 0.0002815754787732461, 'samples': 13446720, 'steps': 70034, 'loss/train': 1.2961283922195435} 08/31/2021 01:51:02 - INFO - __main__ - Step 70036: {'lr': 0.0002815702145190015, 'samples': 13446912, 'steps': 70035, 'loss/train': 3.167123317718506} 08/31/2021 01:51:02 - INFO - __main__ - Step 70037: {'lr': 0.00028156495025053184, 'samples': 13447104, 'steps': 70036, 'loss/train': 1.2879401445388794} 08/31/2021 01:51:03 - INFO - __main__ - Step 70038: {'lr': 0.0002815596859678396, 'samples': 13447296, 'steps': 70037, 'loss/train': 0.9793619513511658} 08/31/2021 01:51:03 - INFO - __main__ - Step 70039: {'lr': 0.00028155442167092707, 'samples': 13447488, 'steps': 70038, 'loss/train': 2.1401519775390625} 08/31/2021 01:51:03 - INFO - __main__ - Step 70040: {'lr': 0.0002815491573597965, 'samples': 13447680, 'steps': 70039, 'loss/train': 1.6057968139648438} 08/31/2021 01:51:05 - INFO - __main__ - Step 70041: {'lr': 0.0002815438930344504, 'samples': 13447872, 'steps': 70040, 'loss/train': 1.3015563488006592} 08/31/2021 01:51:05 - INFO - __main__ - Step 70042: {'lr': 0.0002815386286948911, 'samples': 13448064, 'steps': 70041, 'loss/train': 1.2117587327957153} 08/31/2021 01:51:06 - INFO - __main__ - Step 70043: {'lr': 0.00028153336434112096, 'samples': 13448256, 'steps': 70042, 'loss/train': 1.0847102403640747} 08/31/2021 01:51:06 - INFO - __main__ - Step 70044: {'lr': 0.0002815280999731424, 'samples': 13448448, 'steps': 70043, 'loss/train': 1.311454176902771} 08/31/2021 01:51:06 - INFO - __main__ - Step 70045: {'lr': 0.00028152283559095784, 'samples': 13448640, 'steps': 70044, 'loss/train': 1.210163950920105} 08/31/2021 01:51:08 - INFO - __main__ - Step 70046: {'lr': 0.0002815175711945695, 'samples': 13448832, 'steps': 70045, 'loss/train': 1.1724815368652344} 08/31/2021 01:51:08 - INFO - __main__ - Step 70047: {'lr': 0.0002815123067839798, 'samples': 13449024, 'steps': 70046, 'loss/train': 1.2330876588821411} 08/31/2021 01:51:09 - INFO - __main__ - Step 70048: {'lr': 0.00028150704235919115, 'samples': 13449216, 'steps': 70047, 'loss/train': 1.1103414297103882} 08/31/2021 01:51:09 - INFO - __main__ - Step 70049: {'lr': 0.00028150177792020604, 'samples': 13449408, 'steps': 70048, 'loss/train': 1.5293697118759155} 08/31/2021 01:51:09 - INFO - __main__ - Step 70050: {'lr': 0.0002814965134670266, 'samples': 13449600, 'steps': 70049, 'loss/train': 0.8542646765708923} 08/31/2021 01:51:11 - INFO - __main__ - Step 70051: {'lr': 0.0002814912489996553, 'samples': 13449792, 'steps': 70050, 'loss/train': 1.3889625072479248} 08/31/2021 01:51:11 - INFO - __main__ - Step 70052: {'lr': 0.00028148598451809454, 'samples': 13449984, 'steps': 70051, 'loss/train': 0.0436360202729702} 08/31/2021 01:51:12 - INFO - __main__ - Step 70053: {'lr': 0.0002814807200223467, 'samples': 13450176, 'steps': 70052, 'loss/train': 1.4558041095733643} 08/31/2021 01:51:12 - INFO - __main__ - Step 70054: {'lr': 0.00028147545551241414, 'samples': 13450368, 'steps': 70053, 'loss/train': 2.1451752185821533} 08/31/2021 01:51:12 - INFO - __main__ - Step 70055: {'lr': 0.00028147019098829926, 'samples': 13450560, 'steps': 70054, 'loss/train': 1.4362012147903442} 08/31/2021 01:51:14 - INFO - __main__ - Step 70056: {'lr': 0.0002814649264500044, 'samples': 13450752, 'steps': 70055, 'loss/train': 1.150458812713623} 08/31/2021 01:51:15 - INFO - __main__ - Step 70057: {'lr': 0.00028145966189753186, 'samples': 13450944, 'steps': 70056, 'loss/train': 1.0447638034820557} 08/31/2021 01:51:15 - INFO - __main__ - Step 70058: {'lr': 0.00028145439733088406, 'samples': 13451136, 'steps': 70057, 'loss/train': 1.117089033126831} 08/31/2021 01:51:15 - INFO - __main__ - Step 70059: {'lr': 0.00028144913275006346, 'samples': 13451328, 'steps': 70058, 'loss/train': 1.3331921100616455} 08/31/2021 01:51:16 - INFO - __main__ - Step 70060: {'lr': 0.00028144386815507234, 'samples': 13451520, 'steps': 70059, 'loss/train': 1.1677396297454834} 08/31/2021 01:51:16 - INFO - __main__ - Step 70061: {'lr': 0.00028143860354591313, 'samples': 13451712, 'steps': 70060, 'loss/train': 0.5795976519584656} 08/31/2021 01:51:18 - INFO - __main__ - Step 70062: {'lr': 0.00028143333892258817, 'samples': 13451904, 'steps': 70061, 'loss/train': 1.0676982402801514} 08/31/2021 01:51:18 - INFO - __main__ - Step 70063: {'lr': 0.0002814280742850998, 'samples': 13452096, 'steps': 70062, 'loss/train': 1.7770428657531738} 08/31/2021 01:51:18 - INFO - __main__ - Step 70064: {'lr': 0.0002814228096334505, 'samples': 13452288, 'steps': 70063, 'loss/train': 0.7405876517295837} 08/31/2021 01:51:19 - INFO - __main__ - Step 70065: {'lr': 0.0002814175449676424, 'samples': 13452480, 'steps': 70064, 'loss/train': 1.5627448558807373} 08/31/2021 01:51:19 - INFO - __main__ - Step 70066: {'lr': 0.0002814122802876782, 'samples': 13452672, 'steps': 70065, 'loss/train': 1.4466181993484497} 08/31/2021 01:51:21 - INFO - __main__ - Step 70067: {'lr': 0.00028140701559356004, 'samples': 13452864, 'steps': 70066, 'loss/train': 1.3295313119888306} 08/31/2021 01:51:21 - INFO - __main__ - Step 70068: {'lr': 0.00028140175088529033, 'samples': 13453056, 'steps': 70067, 'loss/train': 0.935444176197052} 08/31/2021 01:51:21 - INFO - __main__ - Step 70069: {'lr': 0.00028139648616287157, 'samples': 13453248, 'steps': 70068, 'loss/train': 0.9551671147346497} 08/31/2021 01:51:22 - INFO - __main__ - Step 70070: {'lr': 0.000281391221426306, 'samples': 13453440, 'steps': 70069, 'loss/train': 1.3337481021881104} 08/31/2021 01:51:22 - INFO - __main__ - Step 70071: {'lr': 0.00028138595667559605, 'samples': 13453632, 'steps': 70070, 'loss/train': 1.2113919258117676} 08/31/2021 01:51:24 - INFO - __main__ - Step 70072: {'lr': 0.000281380691910744, 'samples': 13453824, 'steps': 70071, 'loss/train': 1.7818251848220825} 08/31/2021 01:51:24 - INFO - __main__ - Step 70073: {'lr': 0.00028137542713175227, 'samples': 13454016, 'steps': 70072, 'loss/train': 1.7538167238235474} 08/31/2021 01:51:25 - INFO - __main__ - Step 70074: {'lr': 0.00028137016233862336, 'samples': 13454208, 'steps': 70073, 'loss/train': 0.8341115117073059} 08/31/2021 01:51:25 - INFO - __main__ - Step 70075: {'lr': 0.0002813648975313595, 'samples': 13454400, 'steps': 70074, 'loss/train': 1.1931811571121216} 08/31/2021 01:51:25 - INFO - __main__ - Step 70076: {'lr': 0.0002813596327099631, 'samples': 13454592, 'steps': 70075, 'loss/train': 1.1931639909744263} 08/31/2021 01:51:27 - INFO - __main__ - Step 70077: {'lr': 0.0002813543678744366, 'samples': 13454784, 'steps': 70076, 'loss/train': 1.6192437410354614} 08/31/2021 01:51:27 - INFO - __main__ - Step 70078: {'lr': 0.00028134910302478225, 'samples': 13454976, 'steps': 70077, 'loss/train': 1.4320955276489258} 08/31/2021 01:51:28 - INFO - __main__ - Step 70079: {'lr': 0.0002813438381610024, 'samples': 13455168, 'steps': 70078, 'loss/train': 1.4927942752838135} 08/31/2021 01:51:28 - INFO - __main__ - Step 70080: {'lr': 0.0002813385732830996, 'samples': 13455360, 'steps': 70079, 'loss/train': 1.4494678974151611} 08/31/2021 01:51:28 - INFO - __main__ - Step 70081: {'lr': 0.00028133330839107606, 'samples': 13455552, 'steps': 70080, 'loss/train': 1.5554128885269165} 08/31/2021 01:51:30 - INFO - __main__ - Step 70082: {'lr': 0.0002813280434849343, 'samples': 13455744, 'steps': 70081, 'loss/train': 1.1809097528457642} 08/31/2021 01:51:30 - INFO - __main__ - Step 70083: {'lr': 0.0002813227785646765, 'samples': 13455936, 'steps': 70082, 'loss/train': 0.5977910757064819} 08/31/2021 01:51:31 - INFO - __main__ - Step 70084: {'lr': 0.00028131751363030523, 'samples': 13456128, 'steps': 70083, 'loss/train': 1.3088772296905518} 08/31/2021 01:51:31 - INFO - __main__ - Step 70085: {'lr': 0.0002813122486818228, 'samples': 13456320, 'steps': 70084, 'loss/train': 0.5449234843254089} 08/31/2021 01:51:31 - INFO - __main__ - Step 70086: {'lr': 0.0002813069837192314, 'samples': 13456512, 'steps': 70085, 'loss/train': 1.174635410308838} 08/31/2021 01:51:32 - INFO - __main__ - Step 70087: {'lr': 0.0002813017187425336, 'samples': 13456704, 'steps': 70086, 'loss/train': 1.0218307971954346} 08/31/2021 01:51:33 - INFO - __main__ - Step 70088: {'lr': 0.0002812964537517318, 'samples': 13456896, 'steps': 70087, 'loss/train': 0.8709760308265686} 08/31/2021 01:51:34 - INFO - __main__ - Step 70089: {'lr': 0.00028129118874682836, 'samples': 13457088, 'steps': 70088, 'loss/train': 1.035385012626648} 08/31/2021 01:51:34 - INFO - __main__ - Step 70090: {'lr': 0.00028128592372782545, 'samples': 13457280, 'steps': 70089, 'loss/train': 1.246169090270996} 08/31/2021 01:51:34 - INFO - __main__ - Step 70091: {'lr': 0.0002812806586947257, 'samples': 13457472, 'steps': 70090, 'loss/train': 1.3665039539337158} 08/31/2021 01:51:35 - INFO - __main__ - Step 70092: {'lr': 0.0002812753936475313, 'samples': 13457664, 'steps': 70091, 'loss/train': 1.1837584972381592} 08/31/2021 01:51:36 - INFO - __main__ - Step 70093: {'lr': 0.0002812701285862447, 'samples': 13457856, 'steps': 70092, 'loss/train': 1.1918572187423706} 08/31/2021 01:51:37 - INFO - __main__ - Step 70094: {'lr': 0.0002812648635108682, 'samples': 13458048, 'steps': 70093, 'loss/train': 0.5781963467597961} 08/31/2021 01:51:37 - INFO - __main__ - Step 70095: {'lr': 0.0002812595984214043, 'samples': 13458240, 'steps': 70094, 'loss/train': 1.283780813217163} 08/31/2021 01:51:37 - INFO - __main__ - Step 70096: {'lr': 0.0002812543333178554, 'samples': 13458432, 'steps': 70095, 'loss/train': 0.9058168530464172} 08/31/2021 01:51:38 - INFO - __main__ - Step 70097: {'lr': 0.00028124906820022364, 'samples': 13458624, 'steps': 70096, 'loss/train': 0.8937811851501465} 08/31/2021 01:51:40 - INFO - __main__ - Step 70098: {'lr': 0.0002812438030685116, 'samples': 13458816, 'steps': 70097, 'loss/train': 1.6712735891342163} 08/31/2021 01:51:40 - INFO - __main__ - Step 70099: {'lr': 0.0002812385379227215, 'samples': 13459008, 'steps': 70098, 'loss/train': 1.1200417280197144} 08/31/2021 01:51:41 - INFO - __main__ - Step 70100: {'lr': 0.00028123327276285585, 'samples': 13459200, 'steps': 70099, 'loss/train': 1.189531683921814} 08/31/2021 01:51:41 - INFO - __main__ - Step 70101: {'lr': 0.00028122800758891703, 'samples': 13459392, 'steps': 70100, 'loss/train': 1.2020862102508545} 08/31/2021 01:51:41 - INFO - __main__ - Step 70102: {'lr': 0.00028122274240090727, 'samples': 13459584, 'steps': 70101, 'loss/train': 1.1459156274795532} 08/31/2021 01:51:42 - INFO - __main__ - Step 70103: {'lr': 0.0002812174771988291, 'samples': 13459776, 'steps': 70102, 'loss/train': 1.0225306749343872} 08/31/2021 01:51:43 - INFO - __main__ - Step 70104: {'lr': 0.00028121221198268475, 'samples': 13459968, 'steps': 70103, 'loss/train': 1.2637375593185425} 08/31/2021 01:51:44 - INFO - __main__ - Step 70105: {'lr': 0.0002812069467524767, 'samples': 13460160, 'steps': 70104, 'loss/train': 0.08769458532333374} 08/31/2021 01:51:44 - INFO - __main__ - Step 70106: {'lr': 0.00028120168150820726, 'samples': 13460352, 'steps': 70105, 'loss/train': 0.9607364535331726} 08/31/2021 01:51:45 - INFO - __main__ - Step 70107: {'lr': 0.0002811964162498788, 'samples': 13460544, 'steps': 70106, 'loss/train': 1.3968615531921387} 08/31/2021 01:51:45 - INFO - __main__ - Step 70108: {'lr': 0.00028119115097749377, 'samples': 13460736, 'steps': 70107, 'loss/train': 1.7395421266555786} 08/31/2021 01:51:47 - INFO - __main__ - Step 70109: {'lr': 0.00028118588569105445, 'samples': 13460928, 'steps': 70108, 'loss/train': 1.266114592552185} 08/31/2021 01:51:47 - INFO - __main__ - Step 70110: {'lr': 0.0002811806203905633, 'samples': 13461120, 'steps': 70109, 'loss/train': 1.0520166158676147} 08/31/2021 01:51:48 - INFO - __main__ - Step 70111: {'lr': 0.0002811753550760226, 'samples': 13461312, 'steps': 70110, 'loss/train': 0.411303848028183} 08/31/2021 01:51:48 - INFO - __main__ - Step 70112: {'lr': 0.00028117008974743476, 'samples': 13461504, 'steps': 70111, 'loss/train': 0.8644882440567017} 08/31/2021 01:51:49 - INFO - __main__ - Step 70113: {'lr': 0.00028116482440480216, 'samples': 13461696, 'steps': 70112, 'loss/train': 0.527738094329834} 08/31/2021 01:51:50 - INFO - __main__ - Step 70114: {'lr': 0.0002811595590481272, 'samples': 13461888, 'steps': 70113, 'loss/train': 1.7766822576522827} 08/31/2021 01:51:50 - INFO - __main__ - Step 70115: {'lr': 0.0002811542936774122, 'samples': 13462080, 'steps': 70114, 'loss/train': 1.6294082403182983} 08/31/2021 01:51:51 - INFO - __main__ - Step 70116: {'lr': 0.00028114902829265957, 'samples': 13462272, 'steps': 70115, 'loss/train': 1.4197245836257935} 08/31/2021 01:51:51 - INFO - __main__ - Step 70117: {'lr': 0.0002811437628938717, 'samples': 13462464, 'steps': 70116, 'loss/train': 0.8328443169593811} 08/31/2021 01:51:51 - INFO - __main__ - Step 70118: {'lr': 0.0002811384974810508, 'samples': 13462656, 'steps': 70117, 'loss/train': 1.0642271041870117} 08/31/2021 01:51:53 - INFO - __main__ - Step 70119: {'lr': 0.0002811332320541995, 'samples': 13462848, 'steps': 70118, 'loss/train': 1.4571481943130493} 08/31/2021 01:51:53 - INFO - __main__ - Step 70120: {'lr': 0.00028112796661332, 'samples': 13463040, 'steps': 70119, 'loss/train': 1.2891360521316528} 08/31/2021 01:51:54 - INFO - __main__ - Step 70121: {'lr': 0.0002811227011584147, 'samples': 13463232, 'steps': 70120, 'loss/train': 1.0749752521514893} 08/31/2021 01:51:54 - INFO - __main__ - Step 70122: {'lr': 0.000281117435689486, 'samples': 13463424, 'steps': 70121, 'loss/train': 1.5988564491271973} 08/31/2021 01:51:54 - INFO - __main__ - Step 70123: {'lr': 0.00028111217020653634, 'samples': 13463616, 'steps': 70122, 'loss/train': 1.5845390558242798} 08/31/2021 01:51:56 - INFO - __main__ - Step 70124: {'lr': 0.00028110690470956794, 'samples': 13463808, 'steps': 70123, 'loss/train': 1.5227530002593994} 08/31/2021 01:51:56 - INFO - __main__ - Step 70125: {'lr': 0.0002811016391985833, 'samples': 13464000, 'steps': 70124, 'loss/train': 1.5560096502304077} 08/31/2021 01:51:57 - INFO - __main__ - Step 70126: {'lr': 0.0002810963736735847, 'samples': 13464192, 'steps': 70125, 'loss/train': 1.1038260459899902} 08/31/2021 01:51:57 - INFO - __main__ - Step 70127: {'lr': 0.00028109110813457456, 'samples': 13464384, 'steps': 70126, 'loss/train': 0.5177904367446899} 08/31/2021 01:51:57 - INFO - __main__ - Step 70128: {'lr': 0.00028108584258155524, 'samples': 13464576, 'steps': 70127, 'loss/train': 0.831106424331665} 08/31/2021 01:51:59 - INFO - __main__ - Step 70129: {'lr': 0.00028108057701452916, 'samples': 13464768, 'steps': 70128, 'loss/train': 1.5865371227264404} 08/31/2021 01:51:59 - INFO - __main__ - Step 70130: {'lr': 0.0002810753114334986, 'samples': 13464960, 'steps': 70129, 'loss/train': 0.22448082268238068} 08/31/2021 01:52:00 - INFO - __main__ - Step 70131: {'lr': 0.000281070045838466, 'samples': 13465152, 'steps': 70130, 'loss/train': 1.051500916481018} 08/31/2021 01:52:00 - INFO - __main__ - Step 70132: {'lr': 0.0002810647802294337, 'samples': 13465344, 'steps': 70131, 'loss/train': 1.102248191833496} 08/31/2021 01:52:00 - INFO - __main__ - Step 70133: {'lr': 0.0002810595146064041, 'samples': 13465536, 'steps': 70132, 'loss/train': 1.0437461137771606} 08/31/2021 01:52:01 - INFO - __main__ - Step 70134: {'lr': 0.0002810542489693796, 'samples': 13465728, 'steps': 70133, 'loss/train': 0.7129206657409668} 08/31/2021 01:52:02 - INFO - __main__ - Step 70135: {'lr': 0.0002810489833183625, 'samples': 13465920, 'steps': 70134, 'loss/train': 0.43116793036460876} 08/31/2021 01:52:03 - INFO - __main__ - Step 70136: {'lr': 0.0002810437176533552, 'samples': 13466112, 'steps': 70135, 'loss/train': 0.5195745825767517} 08/31/2021 01:52:03 - INFO - __main__ - Step 70137: {'lr': 0.0002810384519743601, 'samples': 13466304, 'steps': 70136, 'loss/train': 1.1757826805114746} 08/31/2021 01:52:03 - INFO - __main__ - Step 70138: {'lr': 0.00028103318628137957, 'samples': 13466496, 'steps': 70137, 'loss/train': 1.0613958835601807} 08/31/2021 01:52:04 - INFO - __main__ - Step 70139: {'lr': 0.00028102792057441595, 'samples': 13466688, 'steps': 70138, 'loss/train': 1.6548959016799927} 08/31/2021 01:52:06 - INFO - __main__ - Step 70140: {'lr': 0.0002810226548534716, 'samples': 13466880, 'steps': 70139, 'loss/train': 1.3868346214294434} 08/31/2021 01:52:06 - INFO - __main__ - Step 70141: {'lr': 0.0002810173891185489, 'samples': 13467072, 'steps': 70140, 'loss/train': 0.03684203326702118} 08/31/2021 01:52:06 - INFO - __main__ - Step 70142: {'lr': 0.0002810121233696503, 'samples': 13467264, 'steps': 70141, 'loss/train': 1.249014973640442} 08/31/2021 01:52:07 - INFO - __main__ - Step 70143: {'lr': 0.0002810068576067781, 'samples': 13467456, 'steps': 70142, 'loss/train': 0.8612250089645386} 08/31/2021 01:52:07 - INFO - __main__ - Step 70144: {'lr': 0.00028100159182993474, 'samples': 13467648, 'steps': 70143, 'loss/train': 1.8941484689712524} 08/31/2021 01:52:09 - INFO - __main__ - Step 70145: {'lr': 0.00028099632603912245, 'samples': 13467840, 'steps': 70144, 'loss/train': 1.0312237739562988} 08/31/2021 01:52:09 - INFO - __main__ - Step 70146: {'lr': 0.00028099106023434374, 'samples': 13468032, 'steps': 70145, 'loss/train': 1.1412643194198608} 08/31/2021 01:52:09 - INFO - __main__ - Step 70147: {'lr': 0.0002809857944156009, 'samples': 13468224, 'steps': 70146, 'loss/train': 1.636690378189087} 08/31/2021 01:52:10 - INFO - __main__ - Step 70148: {'lr': 0.00028098052858289643, 'samples': 13468416, 'steps': 70147, 'loss/train': 0.17772841453552246} 08/31/2021 01:52:10 - INFO - __main__ - Step 70149: {'lr': 0.00028097526273623255, 'samples': 13468608, 'steps': 70148, 'loss/train': 1.7023975849151611} 08/31/2021 01:52:12 - INFO - __main__ - Step 70150: {'lr': 0.0002809699968756117, 'samples': 13468800, 'steps': 70149, 'loss/train': 1.8248159885406494} 08/31/2021 01:52:12 - INFO - __main__ - Step 70151: {'lr': 0.0002809647310010362, 'samples': 13468992, 'steps': 70150, 'loss/train': 1.234182357788086} 08/31/2021 01:52:12 - INFO - __main__ - Step 70152: {'lr': 0.0002809594651125085, 'samples': 13469184, 'steps': 70151, 'loss/train': 1.0743293762207031} 08/31/2021 01:52:13 - INFO - __main__ - Step 70153: {'lr': 0.00028095419921003094, 'samples': 13469376, 'steps': 70152, 'loss/train': 0.4297057092189789} 08/31/2021 01:52:13 - INFO - __main__ - Step 70154: {'lr': 0.0002809489332936059, 'samples': 13469568, 'steps': 70153, 'loss/train': 1.3671101331710815} 08/31/2021 01:52:15 - INFO - __main__ - Step 70155: {'lr': 0.00028094366736323577, 'samples': 13469760, 'steps': 70154, 'loss/train': 0.5396690964698792} 08/31/2021 01:52:15 - INFO - __main__ - Step 70156: {'lr': 0.00028093840141892295, 'samples': 13469952, 'steps': 70155, 'loss/train': 0.7373369336128235} 08/31/2021 01:52:15 - INFO - __main__ - Step 70157: {'lr': 0.0002809331354606697, 'samples': 13470144, 'steps': 70156, 'loss/train': 0.9887990355491638} 08/31/2021 01:52:16 - INFO - __main__ - Step 70158: {'lr': 0.00028092786948847844, 'samples': 13470336, 'steps': 70157, 'loss/train': 0.48165878653526306} 08/31/2021 01:52:16 - INFO - __main__ - Step 70159: {'lr': 0.0002809226035023516, 'samples': 13470528, 'steps': 70158, 'loss/train': 0.5418733954429626} 08/31/2021 01:52:18 - INFO - __main__ - Step 70160: {'lr': 0.00028091733750229146, 'samples': 13470720, 'steps': 70159, 'loss/train': 1.6422876119613647} 08/31/2021 01:52:18 - INFO - __main__ - Step 70161: {'lr': 0.00028091207148830044, 'samples': 13470912, 'steps': 70160, 'loss/train': 1.5440987348556519} 08/31/2021 01:52:19 - INFO - __main__ - Step 70162: {'lr': 0.00028090680546038105, 'samples': 13471104, 'steps': 70161, 'loss/train': 1.2421669960021973} 08/31/2021 01:52:19 - INFO - __main__ - Step 70163: {'lr': 0.0002809015394185354, 'samples': 13471296, 'steps': 70162, 'loss/train': 0.6724638938903809} 08/31/2021 01:52:19 - INFO - __main__ - Step 70164: {'lr': 0.000280896273362766, 'samples': 13471488, 'steps': 70163, 'loss/train': 0.9566552042961121} 08/31/2021 01:52:21 - INFO - __main__ - Step 70165: {'lr': 0.0002808910072930753, 'samples': 13471680, 'steps': 70164, 'loss/train': 1.533249855041504} 08/31/2021 01:52:22 - INFO - __main__ - Step 70166: {'lr': 0.0002808857412094655, 'samples': 13471872, 'steps': 70165, 'loss/train': 1.0640121698379517} 08/31/2021 01:52:22 - INFO - __main__ - Step 70167: {'lr': 0.00028088047511193917, 'samples': 13472064, 'steps': 70166, 'loss/train': 1.3206655979156494} 08/31/2021 01:52:22 - INFO - __main__ - Step 70168: {'lr': 0.0002808752090004985, 'samples': 13472256, 'steps': 70167, 'loss/train': 1.0120843648910522} 08/31/2021 01:52:23 - INFO - __main__ - Step 70169: {'lr': 0.0002808699428751459, 'samples': 13472448, 'steps': 70168, 'loss/train': 0.9690564274787903} 08/31/2021 01:52:23 - INFO - __main__ - Step 70170: {'lr': 0.0002808646767358838, 'samples': 13472640, 'steps': 70169, 'loss/train': 1.2588626146316528} 08/31/2021 01:52:25 - INFO - __main__ - Step 70171: {'lr': 0.00028085941058271453, 'samples': 13472832, 'steps': 70170, 'loss/train': 0.9654351472854614} 08/31/2021 01:52:25 - INFO - __main__ - Step 70172: {'lr': 0.0002808541444156405, 'samples': 13473024, 'steps': 70171, 'loss/train': 1.548242211341858} 08/31/2021 01:52:26 - INFO - __main__ - Step 70173: {'lr': 0.00028084887823466413, 'samples': 13473216, 'steps': 70172, 'loss/train': 1.8780385255813599} 08/31/2021 01:52:26 - INFO - __main__ - Step 70174: {'lr': 0.0002808436120397877, 'samples': 13473408, 'steps': 70173, 'loss/train': 0.7067037224769592} 08/31/2021 01:52:26 - INFO - __main__ - Step 70175: {'lr': 0.0002808383458310136, 'samples': 13473600, 'steps': 70174, 'loss/train': 0.7179852724075317} 08/31/2021 01:52:28 - INFO - __main__ - Step 70176: {'lr': 0.00028083307960834425, 'samples': 13473792, 'steps': 70175, 'loss/train': 1.6897730827331543} 08/31/2021 01:52:29 - INFO - __main__ - Step 70177: {'lr': 0.0002808278133717819, 'samples': 13473984, 'steps': 70176, 'loss/train': 1.4279332160949707} 08/31/2021 01:52:29 - INFO - __main__ - Step 70178: {'lr': 0.00028082254712132916, 'samples': 13474176, 'steps': 70177, 'loss/train': 0.524531364440918} 08/31/2021 01:52:29 - INFO - __main__ - Step 70179: {'lr': 0.00028081728085698816, 'samples': 13474368, 'steps': 70178, 'loss/train': 1.2032558917999268} 08/31/2021 01:52:30 - INFO - __main__ - Step 70180: {'lr': 0.0002808120145787614, 'samples': 13474560, 'steps': 70179, 'loss/train': 1.1623841524124146} 08/31/2021 01:52:31 - INFO - __main__ - Step 70181: {'lr': 0.0002808067482866512, 'samples': 13474752, 'steps': 70180, 'loss/train': 0.525478720664978} 08/31/2021 01:52:32 - INFO - __main__ - Step 70182: {'lr': 0.00028080148198065993, 'samples': 13474944, 'steps': 70181, 'loss/train': 1.027868390083313} 08/31/2021 01:52:32 - INFO - __main__ - Step 70183: {'lr': 0.00028079621566079005, 'samples': 13475136, 'steps': 70182, 'loss/train': 1.7739189863204956} 08/31/2021 01:52:32 - INFO - __main__ - Step 70184: {'lr': 0.00028079094932704384, 'samples': 13475328, 'steps': 70183, 'loss/train': 0.6365178823471069} 08/31/2021 01:52:33 - INFO - __main__ - Step 70185: {'lr': 0.0002807856829794237, 'samples': 13475520, 'steps': 70184, 'loss/train': 0.4240153431892395} 08/31/2021 01:52:33 - INFO - __main__ - Step 70186: {'lr': 0.000280780416617932, 'samples': 13475712, 'steps': 70185, 'loss/train': 1.465751051902771} 08/31/2021 01:52:34 - INFO - __main__ - Step 70187: {'lr': 0.00028077515024257113, 'samples': 13475904, 'steps': 70186, 'loss/train': 1.2161931991577148} 08/31/2021 01:52:35 - INFO - __main__ - Step 70188: {'lr': 0.0002807698838533435, 'samples': 13476096, 'steps': 70187, 'loss/train': 1.231316328048706} 08/31/2021 01:52:35 - INFO - __main__ - Step 70189: {'lr': 0.00028076461745025127, 'samples': 13476288, 'steps': 70188, 'loss/train': 0.9316453337669373} 08/31/2021 01:52:36 - INFO - __main__ - Step 70190: {'lr': 0.0002807593510332972, 'samples': 13476480, 'steps': 70189, 'loss/train': 1.4705941677093506} 08/31/2021 01:52:36 - INFO - __main__ - Step 70191: {'lr': 0.0002807540846024833, 'samples': 13476672, 'steps': 70190, 'loss/train': 1.667647361755371} 08/31/2021 01:52:38 - INFO - __main__ - Step 70192: {'lr': 0.0002807488181578121, 'samples': 13476864, 'steps': 70191, 'loss/train': 1.3752021789550781} 08/31/2021 01:52:38 - INFO - __main__ - Step 70193: {'lr': 0.000280743551699286, 'samples': 13477056, 'steps': 70192, 'loss/train': 0.8786906599998474} 08/31/2021 01:52:38 - INFO - __main__ - Step 70194: {'lr': 0.00028073828522690725, 'samples': 13477248, 'steps': 70193, 'loss/train': 0.6857443451881409} 08/31/2021 01:52:39 - INFO - __main__ - Step 70195: {'lr': 0.00028073301874067836, 'samples': 13477440, 'steps': 70194, 'loss/train': 0.37627530097961426} 08/31/2021 01:52:39 - INFO - __main__ - Step 70196: {'lr': 0.00028072775224060166, 'samples': 13477632, 'steps': 70195, 'loss/train': 0.03191041201353073} 08/31/2021 01:52:41 - INFO - __main__ - Step 70197: {'lr': 0.00028072248572667954, 'samples': 13477824, 'steps': 70196, 'loss/train': 1.599334478378296} 08/31/2021 01:52:41 - INFO - __main__ - Step 70198: {'lr': 0.00028071721919891427, 'samples': 13478016, 'steps': 70197, 'loss/train': 1.4035134315490723} 08/31/2021 01:52:41 - INFO - __main__ - Step 70199: {'lr': 0.0002807119526573083, 'samples': 13478208, 'steps': 70198, 'loss/train': 1.2885136604309082} 08/31/2021 01:52:42 - INFO - __main__ - Step 70200: {'lr': 0.000280706686101864, 'samples': 13478400, 'steps': 70199, 'loss/train': 1.7005162239074707} 08/31/2021 01:52:42 - INFO - __main__ - Step 70201: {'lr': 0.00028070141953258376, 'samples': 13478592, 'steps': 70200, 'loss/train': 1.1952691078186035} 08/31/2021 01:52:44 - INFO - __main__ - Step 70202: {'lr': 0.0002806961529494699, 'samples': 13478784, 'steps': 70201, 'loss/train': 1.320373296737671} 08/31/2021 01:52:44 - INFO - __main__ - Step 70203: {'lr': 0.00028069088635252496, 'samples': 13478976, 'steps': 70202, 'loss/train': 0.9743397831916809} 08/31/2021 01:52:45 - INFO - __main__ - Step 70204: {'lr': 0.00028068561974175106, 'samples': 13479168, 'steps': 70203, 'loss/train': 1.9622036218643188} 08/31/2021 01:52:45 - INFO - __main__ - Step 70205: {'lr': 0.0002806803531171507, 'samples': 13479360, 'steps': 70204, 'loss/train': 0.7488285899162292} 08/31/2021 01:52:45 - INFO - __main__ - Step 70206: {'lr': 0.00028067508647872623, 'samples': 13479552, 'steps': 70205, 'loss/train': 1.5087240934371948} 08/31/2021 01:52:46 - INFO - __main__ - Step 70207: {'lr': 0.0002806698198264801, 'samples': 13479744, 'steps': 70206, 'loss/train': 1.9689538478851318} 08/31/2021 01:52:47 - INFO - __main__ - Step 70208: {'lr': 0.0002806645531604146, 'samples': 13479936, 'steps': 70207, 'loss/train': 7.369941711425781} 08/31/2021 01:52:48 - INFO - __main__ - Step 70209: {'lr': 0.00028065928648053206, 'samples': 13480128, 'steps': 70208, 'loss/train': 0.10310561209917068} 08/31/2021 01:52:48 - INFO - __main__ - Step 70210: {'lr': 0.000280654019786835, 'samples': 13480320, 'steps': 70209, 'loss/train': 1.430384874343872} 08/31/2021 01:52:48 - INFO - __main__ - Step 70211: {'lr': 0.00028064875307932567, 'samples': 13480512, 'steps': 70210, 'loss/train': 1.6067181825637817} 08/31/2021 01:52:49 - INFO - __main__ - Step 70212: {'lr': 0.0002806434863580065, 'samples': 13480704, 'steps': 70211, 'loss/train': 1.1834876537322998} 08/31/2021 01:52:50 - INFO - __main__ - Step 70213: {'lr': 0.0002806382196228799, 'samples': 13480896, 'steps': 70212, 'loss/train': 0.9354625344276428} 08/31/2021 01:52:51 - INFO - __main__ - Step 70214: {'lr': 0.00028063295287394815, 'samples': 13481088, 'steps': 70213, 'loss/train': 1.0810325145721436} 08/31/2021 01:52:51 - INFO - __main__ - Step 70215: {'lr': 0.00028062768611121356, 'samples': 13481280, 'steps': 70214, 'loss/train': 1.4218266010284424} 08/31/2021 01:52:51 - INFO - __main__ - Step 70216: {'lr': 0.00028062241933467875, 'samples': 13481472, 'steps': 70215, 'loss/train': 0.920202910900116} 08/31/2021 01:52:52 - INFO - __main__ - Step 70217: {'lr': 0.00028061715254434596, 'samples': 13481664, 'steps': 70216, 'loss/train': 2.0325522422790527} 08/31/2021 01:52:52 - INFO - __main__ - Step 70218: {'lr': 0.00028061188574021745, 'samples': 13481856, 'steps': 70217, 'loss/train': 1.128911018371582} 08/31/2021 01:52:54 - INFO - __main__ - Step 70219: {'lr': 0.00028060661892229577, 'samples': 13482048, 'steps': 70218, 'loss/train': 1.5979290008544922} 08/31/2021 01:52:55 - INFO - __main__ - Step 70220: {'lr': 0.0002806013520905832, 'samples': 13482240, 'steps': 70219, 'loss/train': 0.4299798607826233} 08/31/2021 01:52:55 - INFO - __main__ - Step 70221: {'lr': 0.0002805960852450821, 'samples': 13482432, 'steps': 70220, 'loss/train': 1.684497594833374} 08/31/2021 01:52:55 - INFO - __main__ - Step 70222: {'lr': 0.0002805908183857949, 'samples': 13482624, 'steps': 70221, 'loss/train': 0.9770234227180481} 08/31/2021 01:52:56 - INFO - __main__ - Step 70223: {'lr': 0.0002805855515127239, 'samples': 13482816, 'steps': 70222, 'loss/train': 1.748419165611267} 08/31/2021 01:52:57 - INFO - __main__ - Step 70224: {'lr': 0.00028058028462587165, 'samples': 13483008, 'steps': 70223, 'loss/train': 1.4211071729660034} 08/31/2021 01:52:58 - INFO - __main__ - Step 70225: {'lr': 0.0002805750177252403, 'samples': 13483200, 'steps': 70224, 'loss/train': 1.2042654752731323} 08/31/2021 01:52:58 - INFO - __main__ - Step 70226: {'lr': 0.0002805697508108323, 'samples': 13483392, 'steps': 70225, 'loss/train': 0.637896716594696} 08/31/2021 01:52:58 - INFO - __main__ - Step 70227: {'lr': 0.0002805644838826501, 'samples': 13483584, 'steps': 70226, 'loss/train': 1.9242697954177856} 08/31/2021 01:52:59 - INFO - __main__ - Step 70228: {'lr': 0.000280559216940696, 'samples': 13483776, 'steps': 70227, 'loss/train': 1.2161859273910522} 08/31/2021 01:53:00 - INFO - __main__ - Step 70229: {'lr': 0.00028055394998497237, 'samples': 13483968, 'steps': 70228, 'loss/train': 1.2172298431396484} 08/31/2021 01:53:01 - INFO - __main__ - Step 70230: {'lr': 0.00028054868301548167, 'samples': 13484160, 'steps': 70229, 'loss/train': 1.3294330835342407} 08/31/2021 01:53:01 - INFO - __main__ - Step 70231: {'lr': 0.0002805434160322261, 'samples': 13484352, 'steps': 70230, 'loss/train': 0.23957069218158722} 08/31/2021 01:53:01 - INFO - __main__ - Step 70232: {'lr': 0.0002805381490352082, 'samples': 13484544, 'steps': 70231, 'loss/train': 1.1858346462249756} 08/31/2021 01:53:02 - INFO - __main__ - Step 70233: {'lr': 0.0002805328820244303, 'samples': 13484736, 'steps': 70232, 'loss/train': 1.1237568855285645} 08/31/2021 01:53:03 - INFO - __main__ - Step 70234: {'lr': 0.00028052761499989463, 'samples': 13484928, 'steps': 70233, 'loss/train': 0.7938069105148315} 08/31/2021 01:53:04 - INFO - __main__ - Step 70235: {'lr': 0.0002805223479616038, 'samples': 13485120, 'steps': 70234, 'loss/train': 0.6531755328178406} 08/31/2021 01:53:04 - INFO - __main__ - Step 70236: {'lr': 0.00028051708090956007, 'samples': 13485312, 'steps': 70235, 'loss/train': 1.7630494832992554} 08/31/2021 01:53:04 - INFO - __main__ - Step 70237: {'lr': 0.0002805118138437658, 'samples': 13485504, 'steps': 70236, 'loss/train': 0.40897679328918457} 08/31/2021 01:53:05 - INFO - __main__ - Step 70238: {'lr': 0.0002805065467642234, 'samples': 13485696, 'steps': 70237, 'loss/train': 1.2349920272827148} 08/31/2021 01:53:06 - INFO - __main__ - Step 70239: {'lr': 0.0002805012796709352, 'samples': 13485888, 'steps': 70238, 'loss/train': 0.6471957564353943} 08/31/2021 01:53:07 - INFO - __main__ - Step 70240: {'lr': 0.00028049601256390356, 'samples': 13486080, 'steps': 70239, 'loss/train': 1.6336919069290161} 08/31/2021 01:53:07 - INFO - __main__ - Step 70241: {'lr': 0.00028049074544313094, 'samples': 13486272, 'steps': 70240, 'loss/train': 0.9799959063529968} 08/31/2021 01:53:07 - INFO - __main__ - Step 70242: {'lr': 0.00028048547830861957, 'samples': 13486464, 'steps': 70241, 'loss/train': 1.4944406747817993} 08/31/2021 01:53:08 - INFO - __main__ - Step 70243: {'lr': 0.000280480211160372, 'samples': 13486656, 'steps': 70242, 'loss/train': 1.1688964366912842} 08/31/2021 01:53:08 - INFO - __main__ - Step 70244: {'lr': 0.0002804749439983906, 'samples': 13486848, 'steps': 70243, 'loss/train': 1.3213233947753906} 08/31/2021 01:53:09 - INFO - __main__ - Step 70245: {'lr': 0.0002804696768226775, 'samples': 13487040, 'steps': 70244, 'loss/train': 2.0692718029022217} 08/31/2021 01:53:10 - INFO - __main__ - Step 70246: {'lr': 0.0002804644096332353, 'samples': 13487232, 'steps': 70245, 'loss/train': 1.783473253250122} 08/31/2021 01:53:10 - INFO - __main__ - Step 70247: {'lr': 0.00028045914243006627, 'samples': 13487424, 'steps': 70246, 'loss/train': 1.0366765260696411} 08/31/2021 01:53:11 - INFO - __main__ - Step 70248: {'lr': 0.00028045387521317283, 'samples': 13487616, 'steps': 70247, 'loss/train': 1.8179081678390503} 08/31/2021 01:53:11 - INFO - __main__ - Step 70249: {'lr': 0.0002804486079825574, 'samples': 13487808, 'steps': 70248, 'loss/train': 0.6092125773429871} 08/31/2021 01:53:13 - INFO - __main__ - Step 70250: {'lr': 0.00028044334073822226, 'samples': 13488000, 'steps': 70249, 'loss/train': 1.040944218635559} 08/31/2021 01:53:13 - INFO - __main__ - Step 70251: {'lr': 0.00028043807348016985, 'samples': 13488192, 'steps': 70250, 'loss/train': 1.6184688806533813} 08/31/2021 01:53:13 - INFO - __main__ - Step 70252: {'lr': 0.00028043280620840245, 'samples': 13488384, 'steps': 70251, 'loss/train': 1.5665972232818604} 08/31/2021 01:53:14 - INFO - __main__ - Step 70253: {'lr': 0.00028042753892292254, 'samples': 13488576, 'steps': 70252, 'loss/train': 1.598190188407898} 08/31/2021 01:53:14 - INFO - __main__ - Step 70254: {'lr': 0.00028042227162373246, 'samples': 13488768, 'steps': 70253, 'loss/train': 1.1888147592544556} 08/31/2021 01:53:16 - INFO - __main__ - Step 70255: {'lr': 0.0002804170043108345, 'samples': 13488960, 'steps': 70254, 'loss/train': 1.4797903299331665} 08/31/2021 01:53:16 - INFO - __main__ - Step 70256: {'lr': 0.0002804117369842312, 'samples': 13489152, 'steps': 70255, 'loss/train': 1.29198157787323} 08/31/2021 01:53:17 - INFO - __main__ - Step 70257: {'lr': 0.0002804064696439248, 'samples': 13489344, 'steps': 70256, 'loss/train': 1.0369863510131836} 08/31/2021 01:53:17 - INFO - __main__ - Step 70258: {'lr': 0.00028040120228991773, 'samples': 13489536, 'steps': 70257, 'loss/train': 1.3293639421463013} 08/31/2021 01:53:17 - INFO - __main__ - Step 70259: {'lr': 0.0002803959349222123, 'samples': 13489728, 'steps': 70258, 'loss/train': 0.5745102763175964} 08/31/2021 01:53:19 - INFO - __main__ - Step 70260: {'lr': 0.000280390667540811, 'samples': 13489920, 'steps': 70259, 'loss/train': 0.993419885635376} 08/31/2021 01:53:19 - INFO - __main__ - Step 70261: {'lr': 0.00028038540014571606, 'samples': 13490112, 'steps': 70260, 'loss/train': 1.1290069818496704} 08/31/2021 01:53:20 - INFO - __main__ - Step 70262: {'lr': 0.00028038013273692995, 'samples': 13490304, 'steps': 70261, 'loss/train': 0.9466513991355896} 08/31/2021 01:53:20 - INFO - __main__ - Step 70263: {'lr': 0.00028037486531445503, 'samples': 13490496, 'steps': 70262, 'loss/train': 1.711404800415039} 08/31/2021 01:53:20 - INFO - __main__ - Step 70264: {'lr': 0.00028036959787829373, 'samples': 13490688, 'steps': 70263, 'loss/train': 1.3084255456924438} 08/31/2021 01:53:22 - INFO - __main__ - Step 70265: {'lr': 0.00028036433042844834, 'samples': 13490880, 'steps': 70264, 'loss/train': 0.7387650609016418} 08/31/2021 01:53:22 - INFO - __main__ - Step 70266: {'lr': 0.0002803590629649212, 'samples': 13491072, 'steps': 70265, 'loss/train': 1.7037098407745361} 08/31/2021 01:53:23 - INFO - __main__ - Step 70267: {'lr': 0.0002803537954877147, 'samples': 13491264, 'steps': 70266, 'loss/train': 1.539976716041565} 08/31/2021 01:53:23 - INFO - __main__ - Step 70268: {'lr': 0.0002803485279968313, 'samples': 13491456, 'steps': 70267, 'loss/train': 0.6475107073783875} 08/31/2021 01:53:23 - INFO - __main__ - Step 70269: {'lr': 0.0002803432604922733, 'samples': 13491648, 'steps': 70268, 'loss/train': 1.6484812498092651} 08/31/2021 01:53:25 - INFO - __main__ - Step 70270: {'lr': 0.00028033799297404313, 'samples': 13491840, 'steps': 70269, 'loss/train': 1.3438785076141357} 08/31/2021 01:53:26 - INFO - __main__ - Step 70271: {'lr': 0.00028033272544214315, 'samples': 13492032, 'steps': 70270, 'loss/train': 0.4497615694999695} 08/31/2021 01:53:26 - INFO - __main__ - Step 70272: {'lr': 0.00028032745789657567, 'samples': 13492224, 'steps': 70271, 'loss/train': 1.4408503770828247} 08/31/2021 01:53:27 - INFO - __main__ - Step 70273: {'lr': 0.00028032219033734306, 'samples': 13492416, 'steps': 70272, 'loss/train': 1.2139077186584473} 08/31/2021 01:53:27 - INFO - __main__ - Step 70274: {'lr': 0.0002803169227644478, 'samples': 13492608, 'steps': 70273, 'loss/train': 1.2388452291488647} 08/31/2021 01:53:29 - INFO - __main__ - Step 70275: {'lr': 0.0002803116551778922, 'samples': 13492800, 'steps': 70274, 'loss/train': 1.0569217205047607} 08/31/2021 01:53:29 - INFO - __main__ - Step 70276: {'lr': 0.00028030638757767863, 'samples': 13492992, 'steps': 70275, 'loss/train': 1.1417911052703857} 08/31/2021 01:53:30 - INFO - __main__ - Step 70277: {'lr': 0.00028030111996380945, 'samples': 13493184, 'steps': 70276, 'loss/train': 1.3525669574737549} 08/31/2021 01:53:30 - INFO - __main__ - Step 70278: {'lr': 0.00028029585233628707, 'samples': 13493376, 'steps': 70277, 'loss/train': 1.132816195487976} 08/31/2021 01:53:30 - INFO - __main__ - Step 70279: {'lr': 0.0002802905846951139, 'samples': 13493568, 'steps': 70278, 'loss/train': 1.6202019453048706} 08/31/2021 01:53:31 - INFO - __main__ - Step 70280: {'lr': 0.00028028531704029215, 'samples': 13493760, 'steps': 70279, 'loss/train': 1.4847402572631836} 08/31/2021 01:53:33 - INFO - __main__ - Step 70281: {'lr': 0.0002802800493718244, 'samples': 13493952, 'steps': 70280, 'loss/train': 0.04713856428861618} 08/31/2021 01:53:33 - INFO - __main__ - Step 70282: {'lr': 0.0002802747816897128, 'samples': 13494144, 'steps': 70281, 'loss/train': 2.9029388427734375} 08/31/2021 01:53:34 - INFO - __main__ - Step 70283: {'lr': 0.00028026951399395995, 'samples': 13494336, 'steps': 70282, 'loss/train': 2.6625375747680664} 08/31/2021 01:53:34 - INFO - __main__ - Step 70284: {'lr': 0.00028026424628456816, 'samples': 13494528, 'steps': 70283, 'loss/train': 2.7207846641540527} 08/31/2021 01:53:34 - INFO - __main__ - Step 70285: {'lr': 0.0002802589785615397, 'samples': 13494720, 'steps': 70284, 'loss/train': 1.1555901765823364} 08/31/2021 01:53:35 - INFO - __main__ - Step 70286: {'lr': 0.00028025371082487704, 'samples': 13494912, 'steps': 70285, 'loss/train': 1.5302386283874512} 08/31/2021 01:53:36 - INFO - __main__ - Step 70287: {'lr': 0.00028024844307458253, 'samples': 13495104, 'steps': 70286, 'loss/train': 1.3156484365463257} 08/31/2021 01:53:37 - INFO - __main__ - Step 70288: {'lr': 0.00028024317531065847, 'samples': 13495296, 'steps': 70287, 'loss/train': 2.0465025901794434} 08/31/2021 01:53:37 - INFO - __main__ - Step 70289: {'lr': 0.00028023790753310733, 'samples': 13495488, 'steps': 70288, 'loss/train': 0.9210759401321411} 08/31/2021 01:53:37 - INFO - __main__ - Step 70290: {'lr': 0.00028023263974193146, 'samples': 13495680, 'steps': 70289, 'loss/train': 2.4526665210723877} 08/31/2021 01:53:38 - INFO - __main__ - Step 70291: {'lr': 0.0002802273719371333, 'samples': 13495872, 'steps': 70290, 'loss/train': 1.105119228363037} 08/31/2021 01:53:38 - INFO - __main__ - Step 70292: {'lr': 0.0002802221041187151, 'samples': 13496064, 'steps': 70291, 'loss/train': 1.256088376045227} 08/31/2021 01:53:40 - INFO - __main__ - Step 70293: {'lr': 0.0002802168362866793, 'samples': 13496256, 'steps': 70292, 'loss/train': 0.6202293634414673} 08/31/2021 01:53:40 - INFO - __main__ - Step 70294: {'lr': 0.00028021156844102823, 'samples': 13496448, 'steps': 70293, 'loss/train': 1.4798182249069214} 08/31/2021 01:53:40 - INFO - __main__ - Step 70295: {'lr': 0.0002802063005817643, 'samples': 13496640, 'steps': 70294, 'loss/train': 1.7105330228805542} 08/31/2021 01:53:41 - INFO - __main__ - Step 70296: {'lr': 0.00028020103270888995, 'samples': 13496832, 'steps': 70295, 'loss/train': 1.4809635877609253} 08/31/2021 01:53:41 - INFO - __main__ - Step 70297: {'lr': 0.0002801957648224074, 'samples': 13497024, 'steps': 70296, 'loss/train': 1.288055658340454} 08/31/2021 01:53:42 - INFO - __main__ - Step 70298: {'lr': 0.00028019049692231914, 'samples': 13497216, 'steps': 70297, 'loss/train': 1.197645902633667} 08/31/2021 01:53:43 - INFO - __main__ - Step 70299: {'lr': 0.00028018522900862745, 'samples': 13497408, 'steps': 70298, 'loss/train': 1.350925326347351} 08/31/2021 01:53:43 - INFO - __main__ - Step 70300: {'lr': 0.0002801799610813348, 'samples': 13497600, 'steps': 70299, 'loss/train': 1.3433811664581299} 08/31/2021 01:53:44 - INFO - __main__ - Step 70301: {'lr': 0.00028017469314044354, 'samples': 13497792, 'steps': 70300, 'loss/train': 1.3706953525543213} 08/31/2021 01:53:44 - INFO - __main__ - Step 70302: {'lr': 0.0002801694251859561, 'samples': 13497984, 'steps': 70301, 'loss/train': 1.245164394378662} 08/31/2021 01:53:45 - INFO - __main__ - Step 70303: {'lr': 0.00028016415721787463, 'samples': 13498176, 'steps': 70302, 'loss/train': 1.5401341915130615} 08/31/2021 01:53:46 - INFO - __main__ - Step 70304: {'lr': 0.0002801588892362017, 'samples': 13498368, 'steps': 70303, 'loss/train': 1.3623119592666626} 08/31/2021 01:53:46 - INFO - __main__ - Step 70305: {'lr': 0.00028015362124093966, 'samples': 13498560, 'steps': 70304, 'loss/train': 1.3438841104507446} 08/31/2021 01:53:47 - INFO - __main__ - Step 70306: {'lr': 0.00028014835323209085, 'samples': 13498752, 'steps': 70305, 'loss/train': 1.83485746383667} 08/31/2021 01:53:47 - INFO - __main__ - Step 70307: {'lr': 0.00028014308520965775, 'samples': 13498944, 'steps': 70306, 'loss/train': 0.0712674930691719} 08/31/2021 01:53:49 - INFO - __main__ - Step 70308: {'lr': 0.0002801378171736426, 'samples': 13499136, 'steps': 70307, 'loss/train': 1.3835835456848145} 08/31/2021 01:53:49 - INFO - __main__ - Step 70309: {'lr': 0.0002801325491240477, 'samples': 13499328, 'steps': 70308, 'loss/train': 1.2830222845077515} 08/31/2021 01:53:49 - INFO - __main__ - Step 70310: {'lr': 0.00028012728106087566, 'samples': 13499520, 'steps': 70309, 'loss/train': 1.4104796648025513} 08/31/2021 01:53:50 - INFO - __main__ - Step 70311: {'lr': 0.00028012201298412864, 'samples': 13499712, 'steps': 70310, 'loss/train': 0.9270650148391724} 08/31/2021 01:53:50 - INFO - __main__ - Step 70312: {'lr': 0.00028011674489380925, 'samples': 13499904, 'steps': 70311, 'loss/train': 1.4975996017456055} 08/31/2021 01:53:52 - INFO - __main__ - Step 70313: {'lr': 0.00028011147678991955, 'samples': 13500096, 'steps': 70312, 'loss/train': 1.2775923013687134} 08/31/2021 01:53:52 - INFO - __main__ - Step 70314: {'lr': 0.0002801062086724622, 'samples': 13500288, 'steps': 70313, 'loss/train': 1.3094425201416016} 08/31/2021 01:53:53 - INFO - __main__ - Step 70315: {'lr': 0.00028010094054143936, 'samples': 13500480, 'steps': 70314, 'loss/train': 0.9326856136322021} 08/31/2021 01:53:53 - INFO - __main__ - Step 70316: {'lr': 0.0002800956723968536, 'samples': 13500672, 'steps': 70315, 'loss/train': 1.8435858488082886} 08/31/2021 01:53:53 - INFO - __main__ - Step 70317: {'lr': 0.0002800904042387071, 'samples': 13500864, 'steps': 70316, 'loss/train': 1.506442904472351} 08/31/2021 01:53:54 - INFO - __main__ - Step 70318: {'lr': 0.0002800851360670024, 'samples': 13501056, 'steps': 70317, 'loss/train': 1.7978216409683228} 08/31/2021 01:53:55 - INFO - __main__ - Step 70319: {'lr': 0.0002800798678817418, 'samples': 13501248, 'steps': 70318, 'loss/train': 1.6105164289474487} 08/31/2021 01:53:55 - INFO - __main__ - Step 70320: {'lr': 0.00028007459968292767, 'samples': 13501440, 'steps': 70319, 'loss/train': 1.1211949586868286} 08/31/2021 01:53:56 - INFO - __main__ - Step 70321: {'lr': 0.00028006933147056235, 'samples': 13501632, 'steps': 70320, 'loss/train': 1.0103999376296997} 08/31/2021 01:53:56 - INFO - __main__ - Step 70322: {'lr': 0.0002800640632446483, 'samples': 13501824, 'steps': 70321, 'loss/train': 1.063185214996338} 08/31/2021 01:53:57 - INFO - __main__ - Step 70323: {'lr': 0.00028005879500518784, 'samples': 13502016, 'steps': 70322, 'loss/train': 0.9041999578475952} 08/31/2021 01:53:58 - INFO - __main__ - Step 70324: {'lr': 0.00028005352675218337, 'samples': 13502208, 'steps': 70323, 'loss/train': 1.45386803150177} 08/31/2021 01:53:58 - INFO - __main__ - Step 70325: {'lr': 0.0002800482584856372, 'samples': 13502400, 'steps': 70324, 'loss/train': 0.807045042514801} 08/31/2021 01:53:59 - INFO - __main__ - Step 70326: {'lr': 0.00028004299020555176, 'samples': 13502592, 'steps': 70325, 'loss/train': 1.3802552223205566} 08/31/2021 01:53:59 - INFO - __main__ - Step 70327: {'lr': 0.0002800377219119294, 'samples': 13502784, 'steps': 70326, 'loss/train': 1.401489019393921} 08/31/2021 01:54:00 - INFO - __main__ - Step 70328: {'lr': 0.0002800324536047725, 'samples': 13502976, 'steps': 70327, 'loss/train': 0.9510210752487183} 08/31/2021 01:54:01 - INFO - __main__ - Step 70329: {'lr': 0.00028002718528408345, 'samples': 13503168, 'steps': 70328, 'loss/train': 0.9320211410522461} 08/31/2021 01:54:02 - INFO - __main__ - Step 70330: {'lr': 0.0002800219169498646, 'samples': 13503360, 'steps': 70329, 'loss/train': 1.6898252964019775} 08/31/2021 01:54:02 - INFO - __main__ - Step 70331: {'lr': 0.0002800166486021184, 'samples': 13503552, 'steps': 70330, 'loss/train': 1.0162551403045654} 08/31/2021 01:54:03 - INFO - __main__ - Step 70332: {'lr': 0.0002800113802408471, 'samples': 13503744, 'steps': 70331, 'loss/train': 0.686618447303772} 08/31/2021 01:54:03 - INFO - __main__ - Step 70333: {'lr': 0.00028000611186605317, 'samples': 13503936, 'steps': 70332, 'loss/train': 1.1813278198242188} 08/31/2021 01:54:05 - INFO - __main__ - Step 70334: {'lr': 0.0002800008434777389, 'samples': 13504128, 'steps': 70333, 'loss/train': 2.3011722564697266} 08/31/2021 01:54:05 - INFO - __main__ - Step 70335: {'lr': 0.00027999557507590677, 'samples': 13504320, 'steps': 70334, 'loss/train': 0.7575650215148926} 08/31/2021 01:54:06 - INFO - __main__ - Step 70336: {'lr': 0.00027999030666055907, 'samples': 13504512, 'steps': 70335, 'loss/train': 1.1126677989959717} 08/31/2021 01:54:06 - INFO - __main__ - Step 70337: {'lr': 0.0002799850382316982, 'samples': 13504704, 'steps': 70336, 'loss/train': 1.183193325996399} 08/31/2021 01:54:06 - INFO - __main__ - Step 70338: {'lr': 0.0002799797697893266, 'samples': 13504896, 'steps': 70337, 'loss/train': 0.8601084351539612} 08/31/2021 01:54:08 - INFO - __main__ - Step 70339: {'lr': 0.0002799745013334465, 'samples': 13505088, 'steps': 70338, 'loss/train': 1.919942021369934} 08/31/2021 01:54:08 - INFO - __main__ - Step 70340: {'lr': 0.00027996923286406037, 'samples': 13505280, 'steps': 70339, 'loss/train': 1.2693376541137695} 08/31/2021 01:54:09 - INFO - __main__ - Step 70341: {'lr': 0.00027996396438117056, 'samples': 13505472, 'steps': 70340, 'loss/train': 0.7172886729240417} 08/31/2021 01:54:09 - INFO - __main__ - Step 70342: {'lr': 0.0002799586958847794, 'samples': 13505664, 'steps': 70341, 'loss/train': 0.7451295852661133} 08/31/2021 01:54:09 - INFO - __main__ - Step 70343: {'lr': 0.0002799534273748894, 'samples': 13505856, 'steps': 70342, 'loss/train': 0.9313872456550598} 08/31/2021 01:54:11 - INFO - __main__ - Step 70344: {'lr': 0.00027994815885150283, 'samples': 13506048, 'steps': 70343, 'loss/train': 0.7545625567436218} 08/31/2021 01:54:12 - INFO - __main__ - Step 70345: {'lr': 0.00027994289031462203, 'samples': 13506240, 'steps': 70344, 'loss/train': 1.5368871688842773} 08/31/2021 01:54:12 - INFO - __main__ - Step 70346: {'lr': 0.00027993762176424953, 'samples': 13506432, 'steps': 70345, 'loss/train': 1.8490583896636963} 08/31/2021 01:54:12 - INFO - __main__ - Step 70347: {'lr': 0.0002799323532003875, 'samples': 13506624, 'steps': 70346, 'loss/train': 1.2322828769683838} 08/31/2021 01:54:13 - INFO - __main__ - Step 70348: {'lr': 0.00027992708462303847, 'samples': 13506816, 'steps': 70347, 'loss/train': 5.489258766174316} 08/31/2021 01:54:13 - INFO - __main__ - Step 70349: {'lr': 0.0002799218160322047, 'samples': 13507008, 'steps': 70348, 'loss/train': 5.5131683349609375} 08/31/2021 01:54:13 - INFO - __main__ - Step 70350: {'lr': 0.0002799165474278886, 'samples': 13507200, 'steps': 70349, 'loss/train': 1.3213013410568237} 08/31/2021 01:54:15 - INFO - __main__ - Step 70351: {'lr': 0.0002799112788100927, 'samples': 13507392, 'steps': 70350, 'loss/train': 1.0230776071548462} 08/31/2021 01:54:15 - INFO - __main__ - Step 70352: {'lr': 0.00027990601017881917, 'samples': 13507584, 'steps': 70351, 'loss/train': 0.5223931670188904} 08/31/2021 01:54:16 - INFO - __main__ - Step 70353: {'lr': 0.00027990074153407045, 'samples': 13507776, 'steps': 70352, 'loss/train': 0.42044520378112793} 08/31/2021 01:54:16 - INFO - __main__ - Step 70354: {'lr': 0.0002798954728758489, 'samples': 13507968, 'steps': 70353, 'loss/train': 1.1714147329330444} 08/31/2021 01:54:16 - INFO - __main__ - Step 70355: {'lr': 0.00027989020420415687, 'samples': 13508160, 'steps': 70354, 'loss/train': 1.339963436126709} 08/31/2021 01:54:18 - INFO - __main__ - Step 70356: {'lr': 0.00027988493551899684, 'samples': 13508352, 'steps': 70355, 'loss/train': 1.3464165925979614} 08/31/2021 01:54:18 - INFO - __main__ - Step 70357: {'lr': 0.00027987966682037113, 'samples': 13508544, 'steps': 70356, 'loss/train': 1.0198200941085815} 08/31/2021 01:54:19 - INFO - __main__ - Step 70358: {'lr': 0.0002798743981082821, 'samples': 13508736, 'steps': 70357, 'loss/train': 1.5426558256149292} 08/31/2021 01:54:19 - INFO - __main__ - Step 70359: {'lr': 0.00027986912938273215, 'samples': 13508928, 'steps': 70358, 'loss/train': 1.776350975036621} 08/31/2021 01:54:19 - INFO - __main__ - Step 70360: {'lr': 0.00027986386064372354, 'samples': 13509120, 'steps': 70359, 'loss/train': 1.1354817152023315} 08/31/2021 01:54:21 - INFO - __main__ - Step 70361: {'lr': 0.0002798585918912588, 'samples': 13509312, 'steps': 70360, 'loss/train': 1.6648564338684082} 08/31/2021 01:54:22 - INFO - __main__ - Step 70362: {'lr': 0.0002798533231253402, 'samples': 13509504, 'steps': 70361, 'loss/train': 1.018193006515503} 08/31/2021 01:54:22 - INFO - __main__ - Step 70363: {'lr': 0.0002798480543459702, 'samples': 13509696, 'steps': 70362, 'loss/train': 0.9078865051269531} 08/31/2021 01:54:22 - INFO - __main__ - Step 70364: {'lr': 0.00027984278555315105, 'samples': 13509888, 'steps': 70363, 'loss/train': 0.12435978651046753} 08/31/2021 01:54:23 - INFO - __main__ - Step 70365: {'lr': 0.00027983751674688536, 'samples': 13510080, 'steps': 70364, 'loss/train': 0.8341184854507446} 08/31/2021 01:54:24 - INFO - __main__ - Step 70366: {'lr': 0.0002798322479271752, 'samples': 13510272, 'steps': 70365, 'loss/train': 0.8561352491378784} 08/31/2021 01:54:25 - INFO - __main__ - Step 70367: {'lr': 0.0002798269790940231, 'samples': 13510464, 'steps': 70366, 'loss/train': 1.1050279140472412} 08/31/2021 01:54:25 - INFO - __main__ - Step 70368: {'lr': 0.0002798217102474315, 'samples': 13510656, 'steps': 70367, 'loss/train': 1.3848527669906616} 08/31/2021 01:54:25 - INFO - __main__ - Step 70369: {'lr': 0.00027981644138740265, 'samples': 13510848, 'steps': 70368, 'loss/train': 0.9900150299072266} 08/31/2021 01:54:26 - INFO - __main__ - Step 70370: {'lr': 0.00027981117251393893, 'samples': 13511040, 'steps': 70369, 'loss/train': 0.5113475322723389} 08/31/2021 01:54:27 - INFO - __main__ - Step 70371: {'lr': 0.00027980590362704276, 'samples': 13511232, 'steps': 70370, 'loss/train': 0.9797846674919128} 08/31/2021 01:54:28 - INFO - __main__ - Step 70372: {'lr': 0.00027980063472671663, 'samples': 13511424, 'steps': 70371, 'loss/train': 1.158218264579773} 08/31/2021 01:54:28 - INFO - __main__ - Step 70373: {'lr': 0.0002797953658129627, 'samples': 13511616, 'steps': 70372, 'loss/train': 1.7092257738113403} 08/31/2021 01:54:28 - INFO - __main__ - Step 70374: {'lr': 0.00027979009688578344, 'samples': 13511808, 'steps': 70373, 'loss/train': 1.0736117362976074} 08/31/2021 01:54:29 - INFO - __main__ - Step 70375: {'lr': 0.0002797848279451812, 'samples': 13512000, 'steps': 70374, 'loss/train': 0.9576318860054016} 08/31/2021 01:54:29 - INFO - __main__ - Step 70376: {'lr': 0.00027977955899115845, 'samples': 13512192, 'steps': 70375, 'loss/train': 2.0923125743865967} 08/31/2021 01:54:31 - INFO - __main__ - Step 70377: {'lr': 0.00027977429002371744, 'samples': 13512384, 'steps': 70376, 'loss/train': 1.1855437755584717} 08/31/2021 01:54:31 - INFO - __main__ - Step 70378: {'lr': 0.0002797690210428606, 'samples': 13512576, 'steps': 70377, 'loss/train': 0.8585538864135742} 08/31/2021 01:54:31 - INFO - __main__ - Step 70379: {'lr': 0.0002797637520485903, 'samples': 13512768, 'steps': 70378, 'loss/train': 1.4141157865524292} 08/31/2021 01:54:32 - INFO - __main__ - Step 70380: {'lr': 0.00027975848304090894, 'samples': 13512960, 'steps': 70379, 'loss/train': 0.36146804690361023} 08/31/2021 01:54:32 - INFO - __main__ - Step 70381: {'lr': 0.00027975321401981884, 'samples': 13513152, 'steps': 70380, 'loss/train': 1.1543498039245605} 08/31/2021 01:54:34 - INFO - __main__ - Step 70382: {'lr': 0.0002797479449853224, 'samples': 13513344, 'steps': 70381, 'loss/train': 1.3487613201141357} 08/31/2021 01:54:35 - INFO - __main__ - Step 70383: {'lr': 0.00027974267593742195, 'samples': 13513536, 'steps': 70382, 'loss/train': 1.1391358375549316} 08/31/2021 01:54:35 - INFO - __main__ - Step 70384: {'lr': 0.00027973740687612, 'samples': 13513728, 'steps': 70383, 'loss/train': 0.22317929565906525} 08/31/2021 01:54:35 - INFO - __main__ - Step 70385: {'lr': 0.0002797321378014188, 'samples': 13513920, 'steps': 70384, 'loss/train': 1.362997055053711} 08/31/2021 01:54:36 - INFO - __main__ - Step 70386: {'lr': 0.00027972686871332073, 'samples': 13514112, 'steps': 70385, 'loss/train': 0.6582409143447876} 08/31/2021 01:54:37 - INFO - __main__ - Step 70387: {'lr': 0.00027972159961182826, 'samples': 13514304, 'steps': 70386, 'loss/train': 1.5551472902297974} 08/31/2021 01:54:38 - INFO - __main__ - Step 70388: {'lr': 0.0002797163304969436, 'samples': 13514496, 'steps': 70387, 'loss/train': 1.1520987749099731} 08/31/2021 01:54:38 - INFO - __main__ - Step 70389: {'lr': 0.00027971106136866924, 'samples': 13514688, 'steps': 70388, 'loss/train': 1.1611814498901367} 08/31/2021 01:54:38 - INFO - __main__ - Step 70390: {'lr': 0.00027970579222700757, 'samples': 13514880, 'steps': 70389, 'loss/train': 1.1324541568756104} 08/31/2021 01:54:39 - INFO - __main__ - Step 70391: {'lr': 0.00027970052307196093, 'samples': 13515072, 'steps': 70390, 'loss/train': 1.0291671752929688} 08/31/2021 01:54:39 - INFO - __main__ - Step 70392: {'lr': 0.0002796952539035317, 'samples': 13515264, 'steps': 70391, 'loss/train': 0.7792238593101501} 08/31/2021 01:54:41 - INFO - __main__ - Step 70393: {'lr': 0.00027968998472172225, 'samples': 13515456, 'steps': 70392, 'loss/train': 1.4933282136917114} 08/31/2021 01:54:41 - INFO - __main__ - Step 70394: {'lr': 0.00027968471552653493, 'samples': 13515648, 'steps': 70393, 'loss/train': 1.4072577953338623} 08/31/2021 01:54:42 - INFO - __main__ - Step 70395: {'lr': 0.00027967944631797207, 'samples': 13515840, 'steps': 70394, 'loss/train': 0.8622848987579346} 08/31/2021 01:54:42 - INFO - __main__ - Step 70396: {'lr': 0.00027967417709603623, 'samples': 13516032, 'steps': 70395, 'loss/train': 1.7142813205718994} 08/31/2021 01:54:42 - INFO - __main__ - Step 70397: {'lr': 0.0002796689078607296, 'samples': 13516224, 'steps': 70396, 'loss/train': 0.25015366077423096} 08/31/2021 01:54:44 - INFO - __main__ - Step 70398: {'lr': 0.0002796636386120546, 'samples': 13516416, 'steps': 70397, 'loss/train': 0.03597555682063103} 08/31/2021 01:54:44 - INFO - __main__ - Step 70399: {'lr': 0.00027965836935001364, 'samples': 13516608, 'steps': 70398, 'loss/train': 1.0839262008666992} 08/31/2021 01:54:45 - INFO - __main__ - Step 70400: {'lr': 0.00027965310007460907, 'samples': 13516800, 'steps': 70399, 'loss/train': 1.4189112186431885} 08/31/2021 01:54:45 - INFO - __main__ - Step 70401: {'lr': 0.00027964783078584333, 'samples': 13516992, 'steps': 70400, 'loss/train': 1.3952547311782837} 08/31/2021 01:54:45 - INFO - __main__ - Step 70402: {'lr': 0.00027964256148371865, 'samples': 13517184, 'steps': 70401, 'loss/train': 1.4083560705184937} 08/31/2021 01:54:47 - INFO - __main__ - Step 70403: {'lr': 0.0002796372921682375, 'samples': 13517376, 'steps': 70402, 'loss/train': 1.1695261001586914} 08/31/2021 01:54:48 - INFO - __main__ - Step 70404: {'lr': 0.00027963202283940233, 'samples': 13517568, 'steps': 70403, 'loss/train': 0.80649733543396} 08/31/2021 01:54:48 - INFO - __main__ - Step 70405: {'lr': 0.0002796267534972154, 'samples': 13517760, 'steps': 70404, 'loss/train': 1.3849937915802002} 08/31/2021 01:54:49 - INFO - __main__ - Step 70406: {'lr': 0.00027962148414167903, 'samples': 13517952, 'steps': 70405, 'loss/train': 0.04729945585131645} 08/31/2021 01:54:49 - INFO - __main__ - Step 70407: {'lr': 0.00027961621477279574, 'samples': 13518144, 'steps': 70406, 'loss/train': 0.7204081416130066} 08/31/2021 01:54:49 - INFO - __main__ - Step 70408: {'lr': 0.0002796109453905678, 'samples': 13518336, 'steps': 70407, 'loss/train': 0.3425706923007965} 08/31/2021 01:54:51 - INFO - __main__ - Step 70409: {'lr': 0.00027960567599499765, 'samples': 13518528, 'steps': 70408, 'loss/train': 0.9689747095108032} 08/31/2021 01:54:51 - INFO - __main__ - Step 70410: {'lr': 0.0002796004065860876, 'samples': 13518720, 'steps': 70409, 'loss/train': 0.45361435413360596} 08/31/2021 01:54:52 - INFO - __main__ - Step 70411: {'lr': 0.0002795951371638402, 'samples': 13518912, 'steps': 70410, 'loss/train': 1.269345998764038} 08/31/2021 01:54:52 - INFO - __main__ - Step 70412: {'lr': 0.0002795898677282576, 'samples': 13519104, 'steps': 70411, 'loss/train': 1.149872899055481} 08/31/2021 01:54:52 - INFO - __main__ - Step 70413: {'lr': 0.00027958459827934223, 'samples': 13519296, 'steps': 70412, 'loss/train': 1.168600082397461} 08/31/2021 01:54:53 - INFO - __main__ - Step 70414: {'lr': 0.0002795793288170965, 'samples': 13519488, 'steps': 70413, 'loss/train': 1.2627732753753662} 08/31/2021 01:54:54 - INFO - __main__ - Step 70415: {'lr': 0.0002795740593415228, 'samples': 13519680, 'steps': 70414, 'loss/train': 1.4818274974822998} 08/31/2021 01:54:55 - INFO - __main__ - Step 70416: {'lr': 0.0002795687898526235, 'samples': 13519872, 'steps': 70415, 'loss/train': 1.2751295566558838} 08/31/2021 01:54:55 - INFO - __main__ - Step 70417: {'lr': 0.00027956352035040093, 'samples': 13520064, 'steps': 70416, 'loss/train': 1.1872057914733887} 08/31/2021 01:54:55 - INFO - __main__ - Step 70418: {'lr': 0.0002795582508348575, 'samples': 13520256, 'steps': 70417, 'loss/train': 1.352078914642334} 08/31/2021 01:54:56 - INFO - __main__ - Step 70419: {'lr': 0.00027955298130599563, 'samples': 13520448, 'steps': 70418, 'loss/train': 1.475023627281189} 08/31/2021 01:54:57 - INFO - __main__ - Step 70420: {'lr': 0.0002795477117638176, 'samples': 13520640, 'steps': 70419, 'loss/train': 1.4875996112823486} 08/31/2021 01:54:58 - INFO - __main__ - Step 70421: {'lr': 0.0002795424422083258, 'samples': 13520832, 'steps': 70420, 'loss/train': 0.9462617635726929} 08/31/2021 01:54:58 - INFO - __main__ - Step 70422: {'lr': 0.0002795371726395227, 'samples': 13521024, 'steps': 70421, 'loss/train': 1.1001595258712769} 08/31/2021 01:54:58 - INFO - __main__ - Step 70423: {'lr': 0.00027953190305741055, 'samples': 13521216, 'steps': 70422, 'loss/train': 1.158836007118225} 08/31/2021 01:54:59 - INFO - __main__ - Step 70424: {'lr': 0.0002795266334619918, 'samples': 13521408, 'steps': 70423, 'loss/train': 1.5533382892608643} 08/31/2021 01:55:00 - INFO - __main__ - Step 70425: {'lr': 0.0002795213638532688, 'samples': 13521600, 'steps': 70424, 'loss/train': 1.3929457664489746} 08/31/2021 01:55:01 - INFO - __main__ - Step 70426: {'lr': 0.00027951609423124395, 'samples': 13521792, 'steps': 70425, 'loss/train': 0.9857532978057861} 08/31/2021 01:55:01 - INFO - __main__ - Step 70427: {'lr': 0.0002795108245959196, 'samples': 13521984, 'steps': 70426, 'loss/train': 1.2087030410766602} 08/31/2021 01:55:01 - INFO - __main__ - Step 70428: {'lr': 0.00027950555494729806, 'samples': 13522176, 'steps': 70427, 'loss/train': 1.9049476385116577} 08/31/2021 01:55:02 - INFO - __main__ - Step 70429: {'lr': 0.00027950028528538187, 'samples': 13522368, 'steps': 70428, 'loss/train': 1.5571625232696533} 08/31/2021 01:55:03 - INFO - __main__ - Step 70430: {'lr': 0.00027949501561017325, 'samples': 13522560, 'steps': 70429, 'loss/train': 1.943880558013916} 08/31/2021 01:55:04 - INFO - __main__ - Step 70431: {'lr': 0.00027948974592167464, 'samples': 13522752, 'steps': 70430, 'loss/train': 1.0513206720352173} 08/31/2021 01:55:04 - INFO - __main__ - Step 70432: {'lr': 0.00027948447621988843, 'samples': 13522944, 'steps': 70431, 'loss/train': 1.2124677896499634} 08/31/2021 01:55:04 - INFO - __main__ - Step 70433: {'lr': 0.00027947920650481695, 'samples': 13523136, 'steps': 70432, 'loss/train': 0.8630989193916321} 08/31/2021 01:55:05 - INFO - __main__ - Step 70434: {'lr': 0.0002794739367764626, 'samples': 13523328, 'steps': 70433, 'loss/train': 0.7203189134597778} 08/31/2021 01:55:06 - INFO - __main__ - Step 70435: {'lr': 0.0002794686670348277, 'samples': 13523520, 'steps': 70434, 'loss/train': 1.376103401184082} 08/31/2021 01:55:07 - INFO - __main__ - Step 70436: {'lr': 0.0002794633972799148, 'samples': 13523712, 'steps': 70435, 'loss/train': 1.0725336074829102} 08/31/2021 01:55:07 - INFO - __main__ - Step 70437: {'lr': 0.000279458127511726, 'samples': 13523904, 'steps': 70436, 'loss/train': 1.0243624448776245} 08/31/2021 01:55:07 - INFO - __main__ - Step 70438: {'lr': 0.0002794528577302639, 'samples': 13524096, 'steps': 70437, 'loss/train': 1.390401005744934} 08/31/2021 01:55:08 - INFO - __main__ - Step 70439: {'lr': 0.00027944758793553077, 'samples': 13524288, 'steps': 70438, 'loss/train': 1.3748056888580322} 08/31/2021 01:55:10 - INFO - __main__ - Step 70440: {'lr': 0.000279442318127529, 'samples': 13524480, 'steps': 70439, 'loss/train': 0.6917523145675659} 08/31/2021 01:55:11 - INFO - __main__ - Step 70441: {'lr': 0.00027943704830626107, 'samples': 13524672, 'steps': 70440, 'loss/train': 1.4209142923355103} 08/31/2021 01:55:11 - INFO - __main__ - Step 70442: {'lr': 0.0002794317784717292, 'samples': 13524864, 'steps': 70441, 'loss/train': 1.7882955074310303} 08/31/2021 01:55:11 - INFO - __main__ - Step 70443: {'lr': 0.00027942650862393577, 'samples': 13525056, 'steps': 70442, 'loss/train': 1.7692604064941406} 08/31/2021 01:55:12 - INFO - __main__ - Step 70444: {'lr': 0.0002794212387628833, 'samples': 13525248, 'steps': 70443, 'loss/train': 0.775000274181366} 08/31/2021 01:55:12 - INFO - __main__ - Step 70445: {'lr': 0.00027941596888857395, 'samples': 13525440, 'steps': 70444, 'loss/train': 1.6796400547027588} 08/31/2021 01:55:12 - INFO - __main__ - Step 70446: {'lr': 0.0002794106990010103, 'samples': 13525632, 'steps': 70445, 'loss/train': 1.2482272386550903} 08/31/2021 01:55:14 - INFO - __main__ - Step 70447: {'lr': 0.00027940542910019465, 'samples': 13525824, 'steps': 70446, 'loss/train': 1.3690063953399658} 08/31/2021 01:55:14 - INFO - __main__ - Step 70448: {'lr': 0.00027940015918612935, 'samples': 13526016, 'steps': 70447, 'loss/train': 1.841338872909546} 08/31/2021 01:55:15 - INFO - __main__ - Step 70449: {'lr': 0.00027939488925881684, 'samples': 13526208, 'steps': 70448, 'loss/train': 1.102094054222107} 08/31/2021 01:55:15 - INFO - __main__ - Step 70450: {'lr': 0.0002793896193182594, 'samples': 13526400, 'steps': 70449, 'loss/train': 0.6847687363624573} 08/31/2021 01:55:15 - INFO - __main__ - Step 70451: {'lr': 0.00027938434936445943, 'samples': 13526592, 'steps': 70450, 'loss/train': 1.084831953048706} 08/31/2021 01:55:17 - INFO - __main__ - Step 70452: {'lr': 0.0002793790793974194, 'samples': 13526784, 'steps': 70451, 'loss/train': 1.6045886278152466} 08/31/2021 01:55:17 - INFO - __main__ - Step 70453: {'lr': 0.0002793738094171415, 'samples': 13526976, 'steps': 70452, 'loss/train': 1.2596670389175415} 08/31/2021 01:55:18 - INFO - __main__ - Step 70454: {'lr': 0.0002793685394236283, 'samples': 13527168, 'steps': 70453, 'loss/train': 1.4766429662704468} 08/31/2021 01:55:18 - INFO - __main__ - Step 70455: {'lr': 0.00027936326941688206, 'samples': 13527360, 'steps': 70454, 'loss/train': 1.3011964559555054} 08/31/2021 01:55:18 - INFO - __main__ - Step 70456: {'lr': 0.00027935799939690523, 'samples': 13527552, 'steps': 70455, 'loss/train': 1.3516404628753662} 08/31/2021 01:55:20 - INFO - __main__ - Step 70457: {'lr': 0.00027935272936370004, 'samples': 13527744, 'steps': 70456, 'loss/train': 0.9692673683166504} 08/31/2021 01:55:20 - INFO - __main__ - Step 70458: {'lr': 0.000279347459317269, 'samples': 13527936, 'steps': 70457, 'loss/train': 1.0288522243499756} 08/31/2021 01:55:21 - INFO - __main__ - Step 70459: {'lr': 0.00027934218925761454, 'samples': 13528128, 'steps': 70458, 'loss/train': 1.2698116302490234} 08/31/2021 01:55:21 - INFO - __main__ - Step 70460: {'lr': 0.00027933691918473883, 'samples': 13528320, 'steps': 70459, 'loss/train': 1.171878695487976} 08/31/2021 01:55:21 - INFO - __main__ - Step 70461: {'lr': 0.0002793316490986444, 'samples': 13528512, 'steps': 70460, 'loss/train': 1.5317991971969604} 08/31/2021 01:55:23 - INFO - __main__ - Step 70462: {'lr': 0.0002793263789993336, 'samples': 13528704, 'steps': 70461, 'loss/train': 1.8173236846923828} 08/31/2021 01:55:23 - INFO - __main__ - Step 70463: {'lr': 0.0002793211088868087, 'samples': 13528896, 'steps': 70462, 'loss/train': 1.8012100458145142} 08/31/2021 01:55:24 - INFO - __main__ - Step 70464: {'lr': 0.00027931583876107224, 'samples': 13529088, 'steps': 70463, 'loss/train': 1.2171550989151} 08/31/2021 01:55:24 - INFO - __main__ - Step 70465: {'lr': 0.0002793105686221265, 'samples': 13529280, 'steps': 70464, 'loss/train': 1.6860555410385132} 08/31/2021 01:55:24 - INFO - __main__ - Step 70466: {'lr': 0.0002793052984699739, 'samples': 13529472, 'steps': 70465, 'loss/train': 0.8608500361442566} 08/31/2021 01:55:25 - INFO - __main__ - Step 70467: {'lr': 0.00027930002830461675, 'samples': 13529664, 'steps': 70466, 'loss/train': 5.782919406890869} 08/31/2021 01:55:26 - INFO - __main__ - Step 70468: {'lr': 0.00027929475812605746, 'samples': 13529856, 'steps': 70467, 'loss/train': 1.0551233291625977} 08/31/2021 01:55:27 - INFO - __main__ - Step 70469: {'lr': 0.00027928948793429844, 'samples': 13530048, 'steps': 70468, 'loss/train': 0.4405287206172943} 08/31/2021 01:55:27 - INFO - __main__ - Step 70470: {'lr': 0.00027928421772934197, 'samples': 13530240, 'steps': 70469, 'loss/train': 0.1515074074268341} 08/31/2021 01:55:27 - INFO - __main__ - Step 70471: {'lr': 0.00027927894751119054, 'samples': 13530432, 'steps': 70470, 'loss/train': 1.5770612955093384} 08/31/2021 01:55:28 - INFO - __main__ - Step 70472: {'lr': 0.0002792736772798465, 'samples': 13530624, 'steps': 70471, 'loss/train': 1.09837007522583} 08/31/2021 01:55:29 - INFO - __main__ - Step 70473: {'lr': 0.0002792684070353121, 'samples': 13530816, 'steps': 70472, 'loss/train': 0.8764258623123169} 08/31/2021 01:55:30 - INFO - __main__ - Step 70474: {'lr': 0.0002792631367775898, 'samples': 13531008, 'steps': 70473, 'loss/train': 1.6429085731506348} 08/31/2021 01:55:30 - INFO - __main__ - Step 70475: {'lr': 0.00027925786650668204, 'samples': 13531200, 'steps': 70474, 'loss/train': 0.8115407824516296} 08/31/2021 01:55:31 - INFO - __main__ - Step 70476: {'lr': 0.00027925259622259106, 'samples': 13531392, 'steps': 70475, 'loss/train': 1.3691980838775635} 08/31/2021 01:55:31 - INFO - __main__ - Step 70477: {'lr': 0.00027924732592531944, 'samples': 13531584, 'steps': 70476, 'loss/train': 1.1711854934692383} 08/31/2021 01:55:32 - INFO - __main__ - Step 70478: {'lr': 0.00027924205561486934, 'samples': 13531776, 'steps': 70477, 'loss/train': 0.0506996214389801} 08/31/2021 01:55:33 - INFO - __main__ - Step 70479: {'lr': 0.00027923678529124325, 'samples': 13531968, 'steps': 70478, 'loss/train': 1.0082277059555054} 08/31/2021 01:55:33 - INFO - __main__ - Step 70480: {'lr': 0.00027923151495444346, 'samples': 13532160, 'steps': 70479, 'loss/train': 1.1512678861618042} 08/31/2021 01:55:34 - INFO - __main__ - Step 70481: {'lr': 0.0002792262446044725, 'samples': 13532352, 'steps': 70480, 'loss/train': 0.2253803163766861} 08/31/2021 01:55:34 - INFO - __main__ - Step 70482: {'lr': 0.0002792209742413325, 'samples': 13532544, 'steps': 70481, 'loss/train': 1.3881423473358154} 08/31/2021 01:55:35 - INFO - __main__ - Step 70483: {'lr': 0.0002792157038650261, 'samples': 13532736, 'steps': 70482, 'loss/train': 0.9418765306472778} 08/31/2021 01:55:36 - INFO - __main__ - Step 70484: {'lr': 0.00027921043347555553, 'samples': 13532928, 'steps': 70483, 'loss/train': 0.7543420791625977} 08/31/2021 01:55:36 - INFO - __main__ - Step 70485: {'lr': 0.00027920516307292315, 'samples': 13533120, 'steps': 70484, 'loss/train': 1.4322948455810547} 08/31/2021 01:55:37 - INFO - __main__ - Step 70486: {'lr': 0.0002791998926571315, 'samples': 13533312, 'steps': 70485, 'loss/train': 0.881753146648407} 08/31/2021 01:55:37 - INFO - __main__ - Step 70487: {'lr': 0.0002791946222281827, 'samples': 13533504, 'steps': 70486, 'loss/train': 1.0707556009292603} 08/31/2021 01:55:38 - INFO - __main__ - Step 70488: {'lr': 0.00027918935178607927, 'samples': 13533696, 'steps': 70487, 'loss/train': 1.4764000177383423} 08/31/2021 01:55:39 - INFO - __main__ - Step 70489: {'lr': 0.00027918408133082356, 'samples': 13533888, 'steps': 70488, 'loss/train': 1.4273649454116821} 08/31/2021 01:55:39 - INFO - __main__ - Step 70490: {'lr': 0.00027917881086241805, 'samples': 13534080, 'steps': 70489, 'loss/train': 1.241124153137207} 08/31/2021 01:55:40 - INFO - __main__ - Step 70491: {'lr': 0.0002791735403808649, 'samples': 13534272, 'steps': 70490, 'loss/train': 1.5405547618865967} 08/31/2021 01:55:40 - INFO - __main__ - Step 70492: {'lr': 0.00027916826988616663, 'samples': 13534464, 'steps': 70491, 'loss/train': 1.4464739561080933} 08/31/2021 01:55:42 - INFO - __main__ - Step 70493: {'lr': 0.00027916299937832565, 'samples': 13534656, 'steps': 70492, 'loss/train': 1.0003329515457153} 08/31/2021 01:55:42 - INFO - __main__ - Step 70494: {'lr': 0.00027915772885734425, 'samples': 13534848, 'steps': 70493, 'loss/train': 1.5370903015136719} 08/31/2021 01:55:43 - INFO - __main__ - Step 70495: {'lr': 0.00027915245832322476, 'samples': 13535040, 'steps': 70494, 'loss/train': 1.6786941289901733} 08/31/2021 01:55:43 - INFO - __main__ - Step 70496: {'lr': 0.0002791471877759697, 'samples': 13535232, 'steps': 70495, 'loss/train': 1.4836736917495728} 08/31/2021 01:55:43 - INFO - __main__ - Step 70497: {'lr': 0.0002791419172155814, 'samples': 13535424, 'steps': 70496, 'loss/train': 1.6099721193313599} 08/31/2021 01:55:44 - INFO - __main__ - Step 70498: {'lr': 0.0002791366466420621, 'samples': 13535616, 'steps': 70497, 'loss/train': 0.5409693121910095} 08/31/2021 01:55:45 - INFO - __main__ - Step 70499: {'lr': 0.00027913137605541436, 'samples': 13535808, 'steps': 70498, 'loss/train': 1.4572439193725586} 08/31/2021 01:55:46 - INFO - __main__ - Step 70500: {'lr': 0.00027912610545564035, 'samples': 13536000, 'steps': 70499, 'loss/train': 1.242647647857666} 08/31/2021 01:55:46 - INFO - __main__ - Step 70501: {'lr': 0.0002791208348427426, 'samples': 13536192, 'steps': 70500, 'loss/train': 1.58432137966156} 08/31/2021 01:55:46 - INFO - __main__ - Step 70502: {'lr': 0.00027911556421672355, 'samples': 13536384, 'steps': 70501, 'loss/train': 1.8367799520492554} 08/31/2021 01:55:47 - INFO - __main__ - Step 70503: {'lr': 0.0002791102935775854, 'samples': 13536576, 'steps': 70502, 'loss/train': 1.142133355140686} 08/31/2021 01:55:48 - INFO - __main__ - Step 70504: {'lr': 0.0002791050229253306, 'samples': 13536768, 'steps': 70503, 'loss/train': 0.944118857383728} 08/31/2021 01:55:49 - INFO - __main__ - Step 70505: {'lr': 0.0002790997522599616, 'samples': 13536960, 'steps': 70504, 'loss/train': 1.1873970031738281} 08/31/2021 01:55:49 - INFO - __main__ - Step 70506: {'lr': 0.00027909448158148066, 'samples': 13537152, 'steps': 70505, 'loss/train': 0.04330621287226677} 08/31/2021 01:55:49 - INFO - __main__ - Step 70507: {'lr': 0.0002790892108898902, 'samples': 13537344, 'steps': 70506, 'loss/train': 0.03285203501582146} 08/31/2021 01:55:50 - INFO - __main__ - Step 70508: {'lr': 0.00027908394018519257, 'samples': 13537536, 'steps': 70507, 'loss/train': 1.5823265314102173} 08/31/2021 01:55:51 - INFO - __main__ - Step 70509: {'lr': 0.00027907866946739015, 'samples': 13537728, 'steps': 70508, 'loss/train': 0.9548134803771973} 08/31/2021 01:55:52 - INFO - __main__ - Step 70510: {'lr': 0.00027907339873648536, 'samples': 13537920, 'steps': 70509, 'loss/train': 0.05148770287632942} 08/31/2021 01:55:52 - INFO - __main__ - Step 70511: {'lr': 0.0002790681279924805, 'samples': 13538112, 'steps': 70510, 'loss/train': 1.5171784162521362} 08/31/2021 01:55:53 - INFO - __main__ - Step 70512: {'lr': 0.00027906285723537807, 'samples': 13538304, 'steps': 70511, 'loss/train': 1.2495225667953491} 08/31/2021 01:55:53 - INFO - __main__ - Step 70513: {'lr': 0.00027905758646518033, 'samples': 13538496, 'steps': 70512, 'loss/train': 1.0988335609436035} 08/31/2021 01:55:55 - INFO - __main__ - Step 70514: {'lr': 0.00027905231568188966, 'samples': 13538688, 'steps': 70513, 'loss/train': 0.16328199207782745} 08/31/2021 01:55:55 - INFO - __main__ - Step 70515: {'lr': 0.0002790470448855085, 'samples': 13538880, 'steps': 70514, 'loss/train': 1.0518739223480225} 08/31/2021 01:55:56 - INFO - __main__ - Step 70516: {'lr': 0.00027904177407603916, 'samples': 13539072, 'steps': 70515, 'loss/train': 1.9702928066253662} 08/31/2021 01:55:56 - INFO - __main__ - Step 70517: {'lr': 0.00027903650325348405, 'samples': 13539264, 'steps': 70516, 'loss/train': 1.7611050605773926} 08/31/2021 01:55:56 - INFO - __main__ - Step 70518: {'lr': 0.00027903123241784555, 'samples': 13539456, 'steps': 70517, 'loss/train': 1.3710432052612305} 08/31/2021 01:55:58 - INFO - __main__ - Step 70519: {'lr': 0.0002790259615691261, 'samples': 13539648, 'steps': 70518, 'loss/train': 1.269344687461853} 08/31/2021 01:55:59 - INFO - __main__ - Step 70520: {'lr': 0.00027902069070732786, 'samples': 13539840, 'steps': 70519, 'loss/train': 1.4597011804580688} 08/31/2021 01:55:59 - INFO - __main__ - Step 70521: {'lr': 0.00027901541983245344, 'samples': 13540032, 'steps': 70520, 'loss/train': 0.7185147404670715} 08/31/2021 01:55:59 - INFO - __main__ - Step 70522: {'lr': 0.00027901014894450506, 'samples': 13540224, 'steps': 70521, 'loss/train': 1.3170393705368042} 08/31/2021 01:56:00 - INFO - __main__ - Step 70523: {'lr': 0.00027900487804348516, 'samples': 13540416, 'steps': 70522, 'loss/train': 0.26991692185401917} 08/31/2021 01:56:00 - INFO - __main__ - Step 70524: {'lr': 0.00027899960712939617, 'samples': 13540608, 'steps': 70523, 'loss/train': 0.9690997004508972} 08/31/2021 01:56:02 - INFO - __main__ - Step 70525: {'lr': 0.00027899433620224033, 'samples': 13540800, 'steps': 70524, 'loss/train': 1.7935272455215454} 08/31/2021 01:56:02 - INFO - __main__ - Step 70526: {'lr': 0.0002789890652620202, 'samples': 13540992, 'steps': 70525, 'loss/train': 1.2571882009506226} 08/31/2021 01:56:02 - INFO - __main__ - Step 70527: {'lr': 0.00027898379430873793, 'samples': 13541184, 'steps': 70526, 'loss/train': 1.5787975788116455} 08/31/2021 01:56:03 - INFO - __main__ - Step 70528: {'lr': 0.00027897852334239604, 'samples': 13541376, 'steps': 70527, 'loss/train': 1.9805537462234497} 08/31/2021 01:56:03 - INFO - __main__ - Step 70529: {'lr': 0.0002789732523629969, 'samples': 13541568, 'steps': 70528, 'loss/train': 1.0378254652023315} 08/31/2021 01:56:05 - INFO - __main__ - Step 70530: {'lr': 0.0002789679813705428, 'samples': 13541760, 'steps': 70529, 'loss/train': 1.4031906127929688} 08/31/2021 01:56:05 - INFO - __main__ - Step 70531: {'lr': 0.0002789627103650362, 'samples': 13541952, 'steps': 70530, 'loss/train': 1.3669883012771606} 08/31/2021 01:56:06 - INFO - __main__ - Step 70532: {'lr': 0.0002789574393464795, 'samples': 13542144, 'steps': 70531, 'loss/train': 1.1487184762954712} 08/31/2021 01:56:06 - INFO - __main__ - Step 70533: {'lr': 0.000278952168314875, 'samples': 13542336, 'steps': 70532, 'loss/train': 0.9704070091247559} 08/31/2021 01:56:06 - INFO - __main__ - Step 70534: {'lr': 0.00027894689727022516, 'samples': 13542528, 'steps': 70533, 'loss/train': 1.3345316648483276} 08/31/2021 01:56:08 - INFO - __main__ - Step 70535: {'lr': 0.0002789416262125322, 'samples': 13542720, 'steps': 70534, 'loss/train': 0.6464299559593201} 08/31/2021 01:56:08 - INFO - __main__ - Step 70536: {'lr': 0.0002789363551417986, 'samples': 13542912, 'steps': 70535, 'loss/train': 0.7810966372489929} 08/31/2021 01:56:08 - INFO - __main__ - Step 70537: {'lr': 0.00027893108405802676, 'samples': 13543104, 'steps': 70536, 'loss/train': 0.8780048489570618} 08/31/2021 01:56:09 - INFO - __main__ - Step 70538: {'lr': 0.0002789258129612189, 'samples': 13543296, 'steps': 70537, 'loss/train': 0.7121970057487488} 08/31/2021 01:56:09 - INFO - __main__ - Step 70539: {'lr': 0.00027892054185137767, 'samples': 13543488, 'steps': 70538, 'loss/train': 0.7321433424949646} 08/31/2021 01:56:11 - INFO - __main__ - Step 70540: {'lr': 0.00027891527072850534, 'samples': 13543680, 'steps': 70539, 'loss/train': 1.7413369417190552} 08/31/2021 01:56:11 - INFO - __main__ - Step 70541: {'lr': 0.0002789099995926041, 'samples': 13543872, 'steps': 70540, 'loss/train': 1.4577778577804565} 08/31/2021 01:56:11 - INFO - __main__ - Step 70542: {'lr': 0.0002789047284436765, 'samples': 13544064, 'steps': 70541, 'loss/train': 1.5256216526031494} 08/31/2021 01:56:12 - INFO - __main__ - Step 70543: {'lr': 0.00027889945728172484, 'samples': 13544256, 'steps': 70542, 'loss/train': 1.0906602144241333} 08/31/2021 01:56:12 - INFO - __main__ - Step 70544: {'lr': 0.00027889418610675155, 'samples': 13544448, 'steps': 70543, 'loss/train': 1.2775565385818481} 08/31/2021 01:56:12 - INFO - __main__ - Step 70545: {'lr': 0.00027888891491875895, 'samples': 13544640, 'steps': 70544, 'loss/train': 0.8905907273292542} 08/31/2021 01:56:14 - INFO - __main__ - Step 70546: {'lr': 0.0002788836437177495, 'samples': 13544832, 'steps': 70545, 'loss/train': 0.5865033864974976} 08/31/2021 01:56:14 - INFO - __main__ - Step 70547: {'lr': 0.00027887837250372555, 'samples': 13545024, 'steps': 70546, 'loss/train': 1.096804141998291} 08/31/2021 01:56:15 - INFO - __main__ - Step 70548: {'lr': 0.0002788731012766894, 'samples': 13545216, 'steps': 70547, 'loss/train': 0.7290067076683044} 08/31/2021 01:56:15 - INFO - __main__ - Step 70549: {'lr': 0.0002788678300366435, 'samples': 13545408, 'steps': 70548, 'loss/train': 1.7052265405654907} 08/31/2021 01:56:15 - INFO - __main__ - Step 70550: {'lr': 0.00027886255878359025, 'samples': 13545600, 'steps': 70549, 'loss/train': 1.2051894664764404} 08/31/2021 01:56:17 - INFO - __main__ - Step 70551: {'lr': 0.00027885728751753184, 'samples': 13545792, 'steps': 70550, 'loss/train': 1.222141146659851} 08/31/2021 01:56:17 - INFO - __main__ - Step 70552: {'lr': 0.0002788520162384709, 'samples': 13545984, 'steps': 70551, 'loss/train': 0.868234395980835} 08/31/2021 01:56:18 - INFO - __main__ - Step 70553: {'lr': 0.0002788467449464097, 'samples': 13546176, 'steps': 70552, 'loss/train': 1.3596910238265991} 08/31/2021 01:56:18 - INFO - __main__ - Step 70554: {'lr': 0.00027884147364135053, 'samples': 13546368, 'steps': 70553, 'loss/train': 0.4287896454334259} 08/31/2021 01:56:18 - INFO - __main__ - Step 70555: {'lr': 0.0002788362023232959, 'samples': 13546560, 'steps': 70554, 'loss/train': 0.9036746025085449} 08/31/2021 01:56:20 - INFO - __main__ - Step 70556: {'lr': 0.00027883093099224807, 'samples': 13546752, 'steps': 70555, 'loss/train': 1.0453580617904663} 08/31/2021 01:56:20 - INFO - __main__ - Step 70557: {'lr': 0.0002788256596482095, 'samples': 13546944, 'steps': 70556, 'loss/train': 0.6507572531700134} 08/31/2021 01:56:21 - INFO - __main__ - Step 70558: {'lr': 0.0002788203882911825, 'samples': 13547136, 'steps': 70557, 'loss/train': 0.9976885914802551} 08/31/2021 01:56:21 - INFO - __main__ - Step 70559: {'lr': 0.0002788151169211695, 'samples': 13547328, 'steps': 70558, 'loss/train': 1.3766905069351196} 08/31/2021 01:56:21 - INFO - __main__ - Step 70560: {'lr': 0.0002788098455381728, 'samples': 13547520, 'steps': 70559, 'loss/train': 0.2867048978805542} 08/31/2021 01:56:22 - INFO - __main__ - Step 70561: {'lr': 0.0002788045741421949, 'samples': 13547712, 'steps': 70560, 'loss/train': 0.0668225958943367} 08/31/2021 01:56:23 - INFO - __main__ - Step 70562: {'lr': 0.0002787993027332381, 'samples': 13547904, 'steps': 70561, 'loss/train': 1.3925834894180298} 08/31/2021 01:56:24 - INFO - __main__ - Step 70563: {'lr': 0.00027879403131130475, 'samples': 13548096, 'steps': 70562, 'loss/train': 1.189207673072815} 08/31/2021 01:56:24 - INFO - __main__ - Step 70564: {'lr': 0.00027878875987639724, 'samples': 13548288, 'steps': 70563, 'loss/train': 0.7326452732086182} 08/31/2021 01:56:25 - INFO - __main__ - Step 70565: {'lr': 0.000278783488428518, 'samples': 13548480, 'steps': 70564, 'loss/train': 1.9564570188522339} 08/31/2021 01:56:25 - INFO - __main__ - Step 70566: {'lr': 0.00027877821696766934, 'samples': 13548672, 'steps': 70565, 'loss/train': 1.4714034795761108} 08/31/2021 01:56:27 - INFO - __main__ - Step 70567: {'lr': 0.00027877294549385367, 'samples': 13548864, 'steps': 70566, 'loss/train': 1.3014987707138062} 08/31/2021 01:56:28 - INFO - __main__ - Step 70568: {'lr': 0.0002787676740070734, 'samples': 13549056, 'steps': 70567, 'loss/train': 1.4727085828781128} 08/31/2021 01:56:28 - INFO - __main__ - Step 70569: {'lr': 0.00027876240250733074, 'samples': 13549248, 'steps': 70568, 'loss/train': 1.589491605758667} 08/31/2021 01:56:28 - INFO - __main__ - Step 70570: {'lr': 0.0002787571309946283, 'samples': 13549440, 'steps': 70569, 'loss/train': 1.507200002670288} 08/31/2021 01:56:29 - INFO - __main__ - Step 70571: {'lr': 0.0002787518594689683, 'samples': 13549632, 'steps': 70570, 'loss/train': 1.370974063873291} 08/31/2021 01:56:29 - INFO - __main__ - Step 70572: {'lr': 0.00027874658793035313, 'samples': 13549824, 'steps': 70571, 'loss/train': 1.9129983186721802} 08/31/2021 01:56:31 - INFO - __main__ - Step 70573: {'lr': 0.0002787413163787852, 'samples': 13550016, 'steps': 70572, 'loss/train': 0.02863510325551033} 08/31/2021 01:56:31 - INFO - __main__ - Step 70574: {'lr': 0.0002787360448142669, 'samples': 13550208, 'steps': 70573, 'loss/train': 0.6953412890434265} 08/31/2021 01:56:31 - INFO - __main__ - Step 70575: {'lr': 0.0002787307732368006, 'samples': 13550400, 'steps': 70574, 'loss/train': 1.2158162593841553} 08/31/2021 01:56:32 - INFO - __main__ - Step 70576: {'lr': 0.0002787255016463886, 'samples': 13550592, 'steps': 70575, 'loss/train': 1.573107123374939} 08/31/2021 01:56:32 - INFO - __main__ - Step 70577: {'lr': 0.0002787202300430334, 'samples': 13550784, 'steps': 70576, 'loss/train': 1.356996774673462} 08/31/2021 01:56:34 - INFO - __main__ - Step 70578: {'lr': 0.00027871495842673723, 'samples': 13550976, 'steps': 70577, 'loss/train': 1.224387764930725} 08/31/2021 01:56:34 - INFO - __main__ - Step 70579: {'lr': 0.0002787096867975026, 'samples': 13551168, 'steps': 70578, 'loss/train': 1.148444652557373} 08/31/2021 01:56:34 - INFO - __main__ - Step 70580: {'lr': 0.0002787044151553317, 'samples': 13551360, 'steps': 70579, 'loss/train': 1.4991483688354492} 08/31/2021 01:56:35 - INFO - __main__ - Step 70581: {'lr': 0.00027869914350022725, 'samples': 13551552, 'steps': 70580, 'loss/train': 1.871139407157898} 08/31/2021 01:56:35 - INFO - __main__ - Step 70582: {'lr': 0.0002786938718321913, 'samples': 13551744, 'steps': 70581, 'loss/train': 1.5400385856628418} 08/31/2021 01:56:37 - INFO - __main__ - Step 70583: {'lr': 0.0002786886001512263, 'samples': 13551936, 'steps': 70582, 'loss/train': 1.139467477798462} 08/31/2021 01:56:38 - INFO - __main__ - Step 70584: {'lr': 0.0002786833284573347, 'samples': 13552128, 'steps': 70583, 'loss/train': 3.1125216484069824} 08/31/2021 01:56:38 - INFO - __main__ - Step 70585: {'lr': 0.0002786780567505188, 'samples': 13552320, 'steps': 70584, 'loss/train': 0.8662192821502686} 08/31/2021 01:56:38 - INFO - __main__ - Step 70586: {'lr': 0.00027867278503078104, 'samples': 13552512, 'steps': 70585, 'loss/train': 1.7711676359176636} 08/31/2021 01:56:39 - INFO - __main__ - Step 70587: {'lr': 0.0002786675132981238, 'samples': 13552704, 'steps': 70586, 'loss/train': 0.19190536439418793} 08/31/2021 01:56:40 - INFO - __main__ - Step 70588: {'lr': 0.0002786622415525494, 'samples': 13552896, 'steps': 70587, 'loss/train': 0.2513004541397095} 08/31/2021 01:56:41 - INFO - __main__ - Step 70589: {'lr': 0.00027865696979406017, 'samples': 13553088, 'steps': 70588, 'loss/train': 1.3345214128494263} 08/31/2021 01:56:41 - INFO - __main__ - Step 70590: {'lr': 0.0002786516980226586, 'samples': 13553280, 'steps': 70589, 'loss/train': 1.4002940654754639} 08/31/2021 01:56:42 - INFO - __main__ - Step 70591: {'lr': 0.00027864642623834704, 'samples': 13553472, 'steps': 70590, 'loss/train': 0.9122004508972168} 08/31/2021 01:56:42 - INFO - __main__ - Step 70592: {'lr': 0.0002786411544411278, 'samples': 13553664, 'steps': 70591, 'loss/train': 0.9871839880943298} 08/31/2021 01:56:42 - INFO - __main__ - Step 70593: {'lr': 0.0002786358826310034, 'samples': 13553856, 'steps': 70592, 'loss/train': 0.0964854434132576} 08/31/2021 01:56:44 - INFO - __main__ - Step 70594: {'lr': 0.000278630610807976, 'samples': 13554048, 'steps': 70593, 'loss/train': 1.1924264430999756} 08/31/2021 01:56:44 - INFO - __main__ - Step 70595: {'lr': 0.00027862533897204814, 'samples': 13554240, 'steps': 70594, 'loss/train': 3.475478172302246} 08/31/2021 01:56:45 - INFO - __main__ - Step 70596: {'lr': 0.00027862006712322206, 'samples': 13554432, 'steps': 70595, 'loss/train': 1.6420029401779175} 08/31/2021 01:56:45 - INFO - __main__ - Step 70597: {'lr': 0.0002786147952615003, 'samples': 13554624, 'steps': 70596, 'loss/train': 1.5750226974487305} 08/31/2021 01:56:45 - INFO - __main__ - Step 70598: {'lr': 0.00027860952338688513, 'samples': 13554816, 'steps': 70597, 'loss/train': 1.5486946105957031} 08/31/2021 01:56:47 - INFO - __main__ - Step 70599: {'lr': 0.00027860425149937894, 'samples': 13555008, 'steps': 70598, 'loss/train': 1.1230300664901733} 08/31/2021 01:56:47 - INFO - __main__ - Step 70600: {'lr': 0.0002785989795989842, 'samples': 13555200, 'steps': 70599, 'loss/train': 1.08226478099823} 08/31/2021 01:56:48 - INFO - __main__ - Step 70601: {'lr': 0.0002785937076857031, 'samples': 13555392, 'steps': 70600, 'loss/train': 1.4545626640319824} 08/31/2021 01:56:48 - INFO - __main__ - Step 70602: {'lr': 0.0002785884357595382, 'samples': 13555584, 'steps': 70601, 'loss/train': 0.9717907309532166} 08/31/2021 01:56:48 - INFO - __main__ - Step 70603: {'lr': 0.0002785831638204917, 'samples': 13555776, 'steps': 70602, 'loss/train': 1.5690046548843384} 08/31/2021 01:56:50 - INFO - __main__ - Step 70604: {'lr': 0.0002785778918685661, 'samples': 13555968, 'steps': 70603, 'loss/train': 1.5176877975463867} 08/31/2021 01:56:50 - INFO - __main__ - Step 70605: {'lr': 0.0002785726199037638, 'samples': 13556160, 'steps': 70604, 'loss/train': 1.6276695728302002} 08/31/2021 01:56:51 - INFO - __main__ - Step 70606: {'lr': 0.000278567347926087, 'samples': 13556352, 'steps': 70605, 'loss/train': 1.1351810693740845} 08/31/2021 01:56:51 - INFO - __main__ - Step 70607: {'lr': 0.00027856207593553834, 'samples': 13556544, 'steps': 70606, 'loss/train': 1.2768250703811646} 08/31/2021 01:56:51 - INFO - __main__ - Step 70608: {'lr': 0.00027855680393211994, 'samples': 13556736, 'steps': 70607, 'loss/train': 1.4781981706619263} 08/31/2021 01:56:53 - INFO - __main__ - Step 70609: {'lr': 0.00027855153191583433, 'samples': 13556928, 'steps': 70608, 'loss/train': 1.4952384233474731} 08/31/2021 01:56:53 - INFO - __main__ - Step 70610: {'lr': 0.0002785462598866838, 'samples': 13557120, 'steps': 70609, 'loss/train': 0.9996678829193115} 08/31/2021 01:56:54 - INFO - __main__ - Step 70611: {'lr': 0.0002785409878446708, 'samples': 13557312, 'steps': 70610, 'loss/train': 1.2136625051498413} 08/31/2021 01:56:54 - INFO - __main__ - Step 70612: {'lr': 0.00027853571578979766, 'samples': 13557504, 'steps': 70611, 'loss/train': 1.5800856351852417} 08/31/2021 01:56:54 - INFO - __main__ - Step 70613: {'lr': 0.00027853044372206677, 'samples': 13557696, 'steps': 70612, 'loss/train': 1.198608160018921} 08/31/2021 01:56:56 - INFO - __main__ - Step 70614: {'lr': 0.00027852517164148055, 'samples': 13557888, 'steps': 70613, 'loss/train': 0.7242297530174255} 08/31/2021 01:56:56 - INFO - __main__ - Step 70615: {'lr': 0.0002785198995480413, 'samples': 13558080, 'steps': 70614, 'loss/train': 0.8618609309196472} 08/31/2021 01:56:57 - INFO - __main__ - Step 70616: {'lr': 0.0002785146274417514, 'samples': 13558272, 'steps': 70615, 'loss/train': 1.0857064723968506} 08/31/2021 01:56:57 - INFO - __main__ - Step 70617: {'lr': 0.0002785093553226132, 'samples': 13558464, 'steps': 70616, 'loss/train': 1.773146390914917} 08/31/2021 01:56:57 - INFO - __main__ - Step 70618: {'lr': 0.0002785040831906292, 'samples': 13558656, 'steps': 70617, 'loss/train': 0.24485981464385986} 08/31/2021 01:57:00 - INFO - __main__ - Step 70619: {'lr': 0.00027849881104580166, 'samples': 13558848, 'steps': 70618, 'loss/train': 1.2069381475448608} 08/31/2021 01:57:01 - INFO - __main__ - Step 70620: {'lr': 0.00027849353888813306, 'samples': 13559040, 'steps': 70619, 'loss/train': 1.3685325384140015} 08/31/2021 01:57:01 - INFO - __main__ - Step 70621: {'lr': 0.00027848826671762565, 'samples': 13559232, 'steps': 70620, 'loss/train': 1.1784485578536987} 08/31/2021 01:57:01 - INFO - __main__ - Step 70622: {'lr': 0.0002784829945342819, 'samples': 13559424, 'steps': 70621, 'loss/train': 1.1420499086380005} 08/31/2021 01:57:02 - INFO - __main__ - Step 70623: {'lr': 0.00027847772233810416, 'samples': 13559616, 'steps': 70622, 'loss/train': 0.9066617488861084} 08/31/2021 01:57:03 - INFO - __main__ - Step 70624: {'lr': 0.00027847245012909474, 'samples': 13559808, 'steps': 70623, 'loss/train': 0.09545610100030899} 08/31/2021 01:57:04 - INFO - __main__ - Step 70625: {'lr': 0.0002784671779072561, 'samples': 13560000, 'steps': 70624, 'loss/train': 1.0940366983413696} 08/31/2021 01:57:04 - INFO - __main__ - Step 70626: {'lr': 0.0002784619056725906, 'samples': 13560192, 'steps': 70625, 'loss/train': 1.494202733039856} 08/31/2021 01:57:04 - INFO - __main__ - Step 70627: {'lr': 0.0002784566334251006, 'samples': 13560384, 'steps': 70626, 'loss/train': 1.5033438205718994} 08/31/2021 01:57:05 - INFO - __main__ - Step 70628: {'lr': 0.00027845136116478854, 'samples': 13560576, 'steps': 70627, 'loss/train': 1.375194787979126} 08/31/2021 01:57:06 - INFO - __main__ - Step 70629: {'lr': 0.00027844608889165663, 'samples': 13560768, 'steps': 70628, 'loss/train': 1.1748180389404297} 08/31/2021 01:57:07 - INFO - __main__ - Step 70630: {'lr': 0.0002784408166057074, 'samples': 13560960, 'steps': 70629, 'loss/train': 1.461989164352417} 08/31/2021 01:57:07 - INFO - __main__ - Step 70631: {'lr': 0.00027843554430694316, 'samples': 13561152, 'steps': 70630, 'loss/train': 1.064985752105713} 08/31/2021 01:57:07 - INFO - __main__ - Step 70632: {'lr': 0.0002784302719953663, 'samples': 13561344, 'steps': 70631, 'loss/train': 1.7296503782272339} 08/31/2021 01:57:08 - INFO - __main__ - Step 70633: {'lr': 0.00027842499967097923, 'samples': 13561536, 'steps': 70632, 'loss/train': 1.0591145753860474} 08/31/2021 01:57:09 - INFO - __main__ - Step 70634: {'lr': 0.00027841972733378437, 'samples': 13561728, 'steps': 70633, 'loss/train': 1.7987715005874634} 08/31/2021 01:57:10 - INFO - __main__ - Step 70635: {'lr': 0.0002784144549837839, 'samples': 13561920, 'steps': 70634, 'loss/train': 0.45148468017578125} 08/31/2021 01:57:10 - INFO - __main__ - Step 70636: {'lr': 0.0002784091826209803, 'samples': 13562112, 'steps': 70635, 'loss/train': 2.188277006149292} 08/31/2021 01:57:10 - INFO - __main__ - Step 70637: {'lr': 0.000278403910245376, 'samples': 13562304, 'steps': 70636, 'loss/train': 1.5927459001541138} 08/31/2021 01:57:11 - INFO - __main__ - Step 70638: {'lr': 0.00027839863785697336, 'samples': 13562496, 'steps': 70637, 'loss/train': 1.5247735977172852} 08/31/2021 01:57:11 - INFO - __main__ - Step 70639: {'lr': 0.0002783933654557747, 'samples': 13562688, 'steps': 70638, 'loss/train': 1.4221246242523193} 08/31/2021 01:57:13 - INFO - __main__ - Step 70640: {'lr': 0.00027838809304178247, 'samples': 13562880, 'steps': 70639, 'loss/train': 1.1667336225509644} 08/31/2021 01:57:13 - INFO - __main__ - Step 70641: {'lr': 0.000278382820614999, 'samples': 13563072, 'steps': 70640, 'loss/train': 1.3805521726608276} 08/31/2021 01:57:14 - INFO - __main__ - Step 70642: {'lr': 0.0002783775481754266, 'samples': 13563264, 'steps': 70641, 'loss/train': 0.45445874333381653} 08/31/2021 01:57:14 - INFO - __main__ - Step 70643: {'lr': 0.0002783722757230678, 'samples': 13563456, 'steps': 70642, 'loss/train': 2.005504846572876} 08/31/2021 01:57:14 - INFO - __main__ - Step 70644: {'lr': 0.0002783670032579248, 'samples': 13563648, 'steps': 70643, 'loss/train': 1.0167920589447021} 08/31/2021 01:57:16 - INFO - __main__ - Step 70645: {'lr': 0.0002783617307800001, 'samples': 13563840, 'steps': 70644, 'loss/train': 1.6675262451171875} 08/31/2021 01:57:16 - INFO - __main__ - Step 70646: {'lr': 0.00027835645828929606, 'samples': 13564032, 'steps': 70645, 'loss/train': 0.884722888469696} 08/31/2021 01:57:17 - INFO - __main__ - Step 70647: {'lr': 0.0002783511857858151, 'samples': 13564224, 'steps': 70646, 'loss/train': 1.286026954650879} 08/31/2021 01:57:17 - INFO - __main__ - Step 70648: {'lr': 0.0002783459132695594, 'samples': 13564416, 'steps': 70647, 'loss/train': 1.3433020114898682} 08/31/2021 01:57:17 - INFO - __main__ - Step 70649: {'lr': 0.00027834064074053156, 'samples': 13564608, 'steps': 70648, 'loss/train': 1.4609119892120361} 08/31/2021 01:57:19 - INFO - __main__ - Step 70650: {'lr': 0.0002783353681987338, 'samples': 13564800, 'steps': 70649, 'loss/train': 1.1998854875564575} 08/31/2021 01:57:19 - INFO - __main__ - Step 70651: {'lr': 0.0002783300956441686, 'samples': 13564992, 'steps': 70650, 'loss/train': 1.3942315578460693} 08/31/2021 01:57:20 - INFO - __main__ - Step 70652: {'lr': 0.00027832482307683833, 'samples': 13565184, 'steps': 70651, 'loss/train': 1.2294560670852661} 08/31/2021 01:57:20 - INFO - __main__ - Step 70653: {'lr': 0.00027831955049674526, 'samples': 13565376, 'steps': 70652, 'loss/train': 1.326339840888977} 08/31/2021 01:57:20 - INFO - __main__ - Step 70654: {'lr': 0.0002783142779038919, 'samples': 13565568, 'steps': 70653, 'loss/train': 0.03485352173447609} 08/31/2021 01:57:22 - INFO - __main__ - Step 70655: {'lr': 0.00027830900529828055, 'samples': 13565760, 'steps': 70654, 'loss/train': 0.9284096956253052} 08/31/2021 01:57:23 - INFO - __main__ - Step 70656: {'lr': 0.0002783037326799136, 'samples': 13565952, 'steps': 70655, 'loss/train': 1.2885135412216187} 08/31/2021 01:57:23 - INFO - __main__ - Step 70657: {'lr': 0.0002782984600487934, 'samples': 13566144, 'steps': 70656, 'loss/train': 1.419732689857483} 08/31/2021 01:57:23 - INFO - __main__ - Step 70658: {'lr': 0.00027829318740492235, 'samples': 13566336, 'steps': 70657, 'loss/train': 1.3792660236358643} 08/31/2021 01:57:24 - INFO - __main__ - Step 70659: {'lr': 0.0002782879147483028, 'samples': 13566528, 'steps': 70658, 'loss/train': 1.562635898590088} 08/31/2021 01:57:25 - INFO - __main__ - Step 70660: {'lr': 0.0002782826420789372, 'samples': 13566720, 'steps': 70659, 'loss/train': 1.301884651184082} 08/31/2021 01:57:26 - INFO - __main__ - Step 70661: {'lr': 0.00027827736939682796, 'samples': 13566912, 'steps': 70660, 'loss/train': 1.3562254905700684} 08/31/2021 01:57:26 - INFO - __main__ - Step 70662: {'lr': 0.00027827209670197724, 'samples': 13567104, 'steps': 70661, 'loss/train': 1.0438541173934937} 08/31/2021 01:57:26 - INFO - __main__ - Step 70663: {'lr': 0.0002782668239943876, 'samples': 13567296, 'steps': 70662, 'loss/train': 0.1241978332400322} 08/31/2021 01:57:27 - INFO - __main__ - Step 70664: {'lr': 0.0002782615512740613, 'samples': 13567488, 'steps': 70663, 'loss/train': 1.3682509660720825} 08/31/2021 01:57:28 - INFO - __main__ - Step 70665: {'lr': 0.00027825627854100087, 'samples': 13567680, 'steps': 70664, 'loss/train': 1.361811637878418} 08/31/2021 01:57:29 - INFO - __main__ - Step 70666: {'lr': 0.0002782510057952086, 'samples': 13567872, 'steps': 70665, 'loss/train': 1.2012649774551392} 08/31/2021 01:57:29 - INFO - __main__ - Step 70667: {'lr': 0.00027824573303668684, 'samples': 13568064, 'steps': 70666, 'loss/train': 2.020102024078369} 08/31/2021 01:57:29 - INFO - __main__ - Step 70668: {'lr': 0.000278240460265438, 'samples': 13568256, 'steps': 70667, 'loss/train': 1.8257582187652588} 08/31/2021 01:57:30 - INFO - __main__ - Step 70669: {'lr': 0.0002782351874814644, 'samples': 13568448, 'steps': 70668, 'loss/train': 1.6203875541687012} 08/31/2021 01:57:32 - INFO - __main__ - Step 70670: {'lr': 0.0002782299146847684, 'samples': 13568640, 'steps': 70669, 'loss/train': 1.0315765142440796} 08/31/2021 01:57:32 - INFO - __main__ - Step 70671: {'lr': 0.00027822464187535255, 'samples': 13568832, 'steps': 70670, 'loss/train': 1.5483009815216064} 08/31/2021 01:57:32 - INFO - __main__ - Step 70672: {'lr': 0.0002782193690532191, 'samples': 13569024, 'steps': 70671, 'loss/train': 1.4387046098709106} 08/31/2021 01:57:33 - INFO - __main__ - Step 70673: {'lr': 0.0002782140962183704, 'samples': 13569216, 'steps': 70672, 'loss/train': 0.02497638203203678} 08/31/2021 01:57:33 - INFO - __main__ - Step 70674: {'lr': 0.00027820882337080893, 'samples': 13569408, 'steps': 70673, 'loss/train': 0.9590194821357727} 08/31/2021 01:57:34 - INFO - __main__ - Step 70675: {'lr': 0.00027820355051053693, 'samples': 13569600, 'steps': 70674, 'loss/train': 0.917914628982544} 08/31/2021 01:57:35 - INFO - __main__ - Step 70676: {'lr': 0.0002781982776375569, 'samples': 13569792, 'steps': 70675, 'loss/train': 1.0606017112731934} 08/31/2021 01:57:36 - INFO - __main__ - Step 70677: {'lr': 0.0002781930047518711, 'samples': 13569984, 'steps': 70676, 'loss/train': 0.8415396809577942} 08/31/2021 01:57:36 - INFO - __main__ - Step 70678: {'lr': 0.000278187731853482, 'samples': 13570176, 'steps': 70677, 'loss/train': 1.4477561712265015} 08/31/2021 01:57:37 - INFO - __main__ - Step 70679: {'lr': 0.00027818245894239193, 'samples': 13570368, 'steps': 70678, 'loss/train': 1.1311057806015015} 08/31/2021 01:57:37 - INFO - __main__ - Step 70680: {'lr': 0.00027817718601860325, 'samples': 13570560, 'steps': 70679, 'loss/train': 0.997433066368103} 08/31/2021 01:57:37 - INFO - __main__ - Step 70681: {'lr': 0.0002781719130821185, 'samples': 13570752, 'steps': 70680, 'loss/train': 1.3982106447219849} 08/31/2021 01:57:39 - INFO - __main__ - Step 70682: {'lr': 0.0002781666401329398, 'samples': 13570944, 'steps': 70681, 'loss/train': 0.9632187485694885} 08/31/2021 01:57:40 - INFO - __main__ - Step 70683: {'lr': 0.00027816136717106967, 'samples': 13571136, 'steps': 70682, 'loss/train': 1.2995375394821167} 08/31/2021 01:57:40 - INFO - __main__ - Step 70684: {'lr': 0.0002781560941965104, 'samples': 13571328, 'steps': 70683, 'loss/train': 1.314422369003296} 08/31/2021 01:57:40 - INFO - __main__ - Step 70685: {'lr': 0.0002781508212092645, 'samples': 13571520, 'steps': 70684, 'loss/train': 1.2935843467712402} 08/31/2021 01:57:41 - INFO - __main__ - Step 70686: {'lr': 0.00027814554820933425, 'samples': 13571712, 'steps': 70685, 'loss/train': 1.1790803670883179} 08/31/2021 01:57:42 - INFO - __main__ - Step 70687: {'lr': 0.00027814027519672214, 'samples': 13571904, 'steps': 70686, 'loss/train': 0.9954887628555298} 08/31/2021 01:57:42 - INFO - __main__ - Step 70688: {'lr': 0.00027813500217143035, 'samples': 13572096, 'steps': 70687, 'loss/train': 1.12734854221344} 08/31/2021 01:57:43 - INFO - __main__ - Step 70689: {'lr': 0.0002781297291334614, 'samples': 13572288, 'steps': 70688, 'loss/train': 1.6981024742126465} 08/31/2021 01:57:43 - INFO - __main__ - Step 70690: {'lr': 0.0002781244560828176, 'samples': 13572480, 'steps': 70689, 'loss/train': 1.1728605031967163} 08/31/2021 01:57:44 - INFO - __main__ - Step 70691: {'lr': 0.00027811918301950137, 'samples': 13572672, 'steps': 70690, 'loss/train': 1.7457143068313599} 08/31/2021 01:57:45 - INFO - __main__ - Step 70692: {'lr': 0.00027811390994351504, 'samples': 13572864, 'steps': 70691, 'loss/train': 1.3760325908660889} 08/31/2021 01:57:46 - INFO - __main__ - Step 70693: {'lr': 0.00027810863685486106, 'samples': 13573056, 'steps': 70692, 'loss/train': 1.4776068925857544} 08/31/2021 01:57:46 - INFO - __main__ - Step 70694: {'lr': 0.0002781033637535418, 'samples': 13573248, 'steps': 70693, 'loss/train': 1.3994354009628296} 08/31/2021 01:57:46 - INFO - __main__ - Step 70695: {'lr': 0.00027809809063955956, 'samples': 13573440, 'steps': 70694, 'loss/train': 1.2565577030181885} 08/31/2021 01:57:47 - INFO - __main__ - Step 70696: {'lr': 0.0002780928175129167, 'samples': 13573632, 'steps': 70695, 'loss/train': 1.1460736989974976} 08/31/2021 01:57:47 - INFO - __main__ - Step 70697: {'lr': 0.00027808754437361573, 'samples': 13573824, 'steps': 70696, 'loss/train': 0.5828344821929932} 08/31/2021 01:57:49 - INFO - __main__ - Step 70698: {'lr': 0.00027808227122165887, 'samples': 13574016, 'steps': 70697, 'loss/train': 1.5482158660888672} 08/31/2021 01:57:49 - INFO - __main__ - Step 70699: {'lr': 0.00027807699805704867, 'samples': 13574208, 'steps': 70698, 'loss/train': 1.403328537940979} 08/31/2021 01:57:49 - INFO - __main__ - Step 70700: {'lr': 0.00027807172487978734, 'samples': 13574400, 'steps': 70699, 'loss/train': 1.0481547117233276} 08/31/2021 01:57:50 - INFO - __main__ - Step 70701: {'lr': 0.00027806645168987733, 'samples': 13574592, 'steps': 70700, 'loss/train': 0.917931854724884} 08/31/2021 01:57:50 - INFO - __main__ - Step 70702: {'lr': 0.00027806117848732097, 'samples': 13574784, 'steps': 70701, 'loss/train': 1.4085981845855713} 08/31/2021 01:57:51 - INFO - __main__ - Step 70703: {'lr': 0.00027805590527212075, 'samples': 13574976, 'steps': 70702, 'loss/train': 1.108858585357666} 08/31/2021 01:57:52 - INFO - __main__ - Step 70704: {'lr': 0.00027805063204427896, 'samples': 13575168, 'steps': 70703, 'loss/train': 1.0782889127731323} 08/31/2021 01:57:52 - INFO - __main__ - Step 70705: {'lr': 0.000278045358803798, 'samples': 13575360, 'steps': 70704, 'loss/train': 1.237143874168396} 08/31/2021 01:57:53 - INFO - __main__ - Step 70706: {'lr': 0.00027804008555068016, 'samples': 13575552, 'steps': 70705, 'loss/train': 1.5511298179626465} 08/31/2021 01:57:53 - INFO - __main__ - Step 70707: {'lr': 0.00027803481228492793, 'samples': 13575744, 'steps': 70706, 'loss/train': 1.9540396928787231} 08/31/2021 01:57:55 - INFO - __main__ - Step 70708: {'lr': 0.00027802953900654367, 'samples': 13575936, 'steps': 70707, 'loss/train': 0.9831619262695312} 08/31/2021 01:57:55 - INFO - __main__ - Step 70709: {'lr': 0.0002780242657155297, 'samples': 13576128, 'steps': 70708, 'loss/train': 0.8121544122695923} 08/31/2021 01:57:55 - INFO - __main__ - Step 70710: {'lr': 0.0002780189924118885, 'samples': 13576320, 'steps': 70709, 'loss/train': 1.2294052839279175} 08/31/2021 01:57:56 - INFO - __main__ - Step 70711: {'lr': 0.00027801371909562226, 'samples': 13576512, 'steps': 70710, 'loss/train': 0.8936618566513062} 08/31/2021 01:57:56 - INFO - __main__ - Step 70712: {'lr': 0.0002780084457667336, 'samples': 13576704, 'steps': 70711, 'loss/train': 1.2214363813400269} 08/31/2021 01:57:57 - INFO - __main__ - Step 70713: {'lr': 0.0002780031724252247, 'samples': 13576896, 'steps': 70712, 'loss/train': 1.301012635231018} 08/31/2021 01:57:58 - INFO - __main__ - Step 70714: {'lr': 0.0002779978990710979, 'samples': 13577088, 'steps': 70713, 'loss/train': 0.838665783405304} 08/31/2021 01:57:58 - INFO - __main__ - Step 70715: {'lr': 0.0002779926257043558, 'samples': 13577280, 'steps': 70714, 'loss/train': 1.0573019981384277} 08/31/2021 01:57:59 - INFO - __main__ - Step 70716: {'lr': 0.00027798735232500066, 'samples': 13577472, 'steps': 70715, 'loss/train': 1.3007457256317139} 08/31/2021 01:57:59 - INFO - __main__ - Step 70717: {'lr': 0.00027798207893303483, 'samples': 13577664, 'steps': 70716, 'loss/train': 0.9040173292160034} 08/31/2021 01:58:01 - INFO - __main__ - Step 70718: {'lr': 0.00027797680552846065, 'samples': 13577856, 'steps': 70717, 'loss/train': 1.7065870761871338} 08/31/2021 01:58:01 - INFO - __main__ - Step 70719: {'lr': 0.0002779715321112806, 'samples': 13578048, 'steps': 70718, 'loss/train': 1.42002534866333} 08/31/2021 01:58:01 - INFO - __main__ - Step 70720: {'lr': 0.000277966258681497, 'samples': 13578240, 'steps': 70719, 'loss/train': 1.4589290618896484} 08/31/2021 01:58:02 - INFO - __main__ - Step 70721: {'lr': 0.0002779609852391123, 'samples': 13578432, 'steps': 70720, 'loss/train': 0.05051476135849953} 08/31/2021 01:58:02 - INFO - __main__ - Step 70722: {'lr': 0.00027795571178412874, 'samples': 13578624, 'steps': 70721, 'loss/train': 1.6058292388916016} 08/31/2021 01:58:04 - INFO - __main__ - Step 70723: {'lr': 0.0002779504383165488, 'samples': 13578816, 'steps': 70722, 'loss/train': 0.9521028399467468} 08/31/2021 01:58:04 - INFO - __main__ - Step 70724: {'lr': 0.0002779451648363748, 'samples': 13579008, 'steps': 70723, 'loss/train': 1.0830029249191284} 08/31/2021 01:58:05 - INFO - __main__ - Step 70725: {'lr': 0.00027793989134360916, 'samples': 13579200, 'steps': 70724, 'loss/train': 1.0942821502685547} 08/31/2021 01:58:05 - INFO - __main__ - Step 70726: {'lr': 0.00027793461783825416, 'samples': 13579392, 'steps': 70725, 'loss/train': 1.2793257236480713} 08/31/2021 01:58:05 - INFO - __main__ - Step 70727: {'lr': 0.00027792934432031234, 'samples': 13579584, 'steps': 70726, 'loss/train': 0.7384063005447388} 08/31/2021 01:58:07 - INFO - __main__ - Step 70728: {'lr': 0.000277924070789786, 'samples': 13579776, 'steps': 70727, 'loss/train': 1.4569892883300781} 08/31/2021 01:58:08 - INFO - __main__ - Step 70729: {'lr': 0.00027791879724667747, 'samples': 13579968, 'steps': 70728, 'loss/train': 1.5769845247268677} 08/31/2021 01:58:08 - INFO - __main__ - Step 70730: {'lr': 0.00027791352369098914, 'samples': 13580160, 'steps': 70729, 'loss/train': 0.9413447380065918} 08/31/2021 01:58:08 - INFO - __main__ - Step 70731: {'lr': 0.0002779082501227234, 'samples': 13580352, 'steps': 70730, 'loss/train': 0.6855733394622803} 08/31/2021 01:58:09 - INFO - __main__ - Step 70732: {'lr': 0.0002779029765418827, 'samples': 13580544, 'steps': 70731, 'loss/train': 1.1501109600067139} 08/31/2021 01:58:10 - INFO - __main__ - Step 70733: {'lr': 0.0002778977029484693, 'samples': 13580736, 'steps': 70732, 'loss/train': 1.20713210105896} 08/31/2021 01:58:11 - INFO - __main__ - Step 70734: {'lr': 0.0002778924293424856, 'samples': 13580928, 'steps': 70733, 'loss/train': 1.7139856815338135} 08/31/2021 01:58:11 - INFO - __main__ - Step 70735: {'lr': 0.00027788715572393406, 'samples': 13581120, 'steps': 70734, 'loss/train': 1.1082736253738403} 08/31/2021 01:58:11 - INFO - __main__ - Step 70736: {'lr': 0.000277881882092817, 'samples': 13581312, 'steps': 70735, 'loss/train': 1.1403237581253052} 08/31/2021 01:58:12 - INFO - __main__ - Step 70737: {'lr': 0.00027787660844913676, 'samples': 13581504, 'steps': 70736, 'loss/train': 1.1401184797286987} 08/31/2021 01:58:13 - INFO - __main__ - Step 70738: {'lr': 0.00027787133479289573, 'samples': 13581696, 'steps': 70737, 'loss/train': 0.6748707890510559} 08/31/2021 01:58:14 - INFO - __main__ - Step 70739: {'lr': 0.00027786606112409633, 'samples': 13581888, 'steps': 70738, 'loss/train': 1.6704905033111572} 08/31/2021 01:58:14 - INFO - __main__ - Step 70740: {'lr': 0.0002778607874427409, 'samples': 13582080, 'steps': 70739, 'loss/train': 0.9663398861885071} 08/31/2021 01:58:15 - INFO - __main__ - Step 70741: {'lr': 0.00027785551374883197, 'samples': 13582272, 'steps': 70740, 'loss/train': 1.42598295211792} 08/31/2021 01:58:15 - INFO - __main__ - Step 70742: {'lr': 0.00027785024004237156, 'samples': 13582464, 'steps': 70741, 'loss/train': 1.4227544069290161} 08/31/2021 01:58:15 - INFO - __main__ - Step 70743: {'lr': 0.0002778449663233624, 'samples': 13582656, 'steps': 70742, 'loss/train': 1.2229844331741333} 08/31/2021 01:58:17 - INFO - __main__ - Step 70744: {'lr': 0.00027783969259180665, 'samples': 13582848, 'steps': 70743, 'loss/train': 1.7625072002410889} 08/31/2021 01:58:17 - INFO - __main__ - Step 70745: {'lr': 0.00027783441884770676, 'samples': 13583040, 'steps': 70744, 'loss/train': 0.4439752995967865} 08/31/2021 01:58:17 - INFO - __main__ - Step 70746: {'lr': 0.00027782914509106514, 'samples': 13583232, 'steps': 70745, 'loss/train': 1.591770887374878} 08/31/2021 01:58:18 - INFO - __main__ - Step 70747: {'lr': 0.0002778238713218842, 'samples': 13583424, 'steps': 70746, 'loss/train': 1.574633002281189} 08/31/2021 01:58:18 - INFO - __main__ - Step 70748: {'lr': 0.0002778185975401662, 'samples': 13583616, 'steps': 70747, 'loss/train': 1.6589548587799072} 08/31/2021 01:58:20 - INFO - __main__ - Step 70749: {'lr': 0.00027781332374591356, 'samples': 13583808, 'steps': 70748, 'loss/train': 1.0610597133636475} 08/31/2021 01:58:21 - INFO - __main__ - Step 70750: {'lr': 0.00027780804993912867, 'samples': 13584000, 'steps': 70749, 'loss/train': 0.9801697134971619} 08/31/2021 01:58:21 - INFO - __main__ - Step 70751: {'lr': 0.00027780277611981393, 'samples': 13584192, 'steps': 70750, 'loss/train': 1.013377070426941} 08/31/2021 01:58:21 - INFO - __main__ - Step 70752: {'lr': 0.0002777975022879716, 'samples': 13584384, 'steps': 70751, 'loss/train': 0.041789304465055466} 08/31/2021 01:58:22 - INFO - __main__ - Step 70753: {'lr': 0.00027779222844360427, 'samples': 13584576, 'steps': 70752, 'loss/train': 1.1558655500411987} 08/31/2021 01:58:24 - INFO - __main__ - Step 70754: {'lr': 0.00027778695458671406, 'samples': 13584768, 'steps': 70753, 'loss/train': 1.1760227680206299} 08/31/2021 01:58:24 - INFO - __main__ - Step 70755: {'lr': 0.0002777816807173036, 'samples': 13584960, 'steps': 70754, 'loss/train': 1.4882875680923462} 08/31/2021 01:58:24 - INFO - __main__ - Step 70756: {'lr': 0.0002777764068353751, 'samples': 13585152, 'steps': 70755, 'loss/train': 1.036024808883667} 08/31/2021 01:58:25 - INFO - __main__ - Step 70757: {'lr': 0.00027777113294093095, 'samples': 13585344, 'steps': 70756, 'loss/train': 1.3151365518569946} 08/31/2021 01:58:25 - INFO - __main__ - Step 70758: {'lr': 0.00027776585903397353, 'samples': 13585536, 'steps': 70757, 'loss/train': 0.11180184036493301} 08/31/2021 01:58:27 - INFO - __main__ - Step 70759: {'lr': 0.0002777605851145053, 'samples': 13585728, 'steps': 70758, 'loss/train': 0.193918377161026} 08/31/2021 01:58:27 - INFO - __main__ - Step 70760: {'lr': 0.00027775531118252856, 'samples': 13585920, 'steps': 70759, 'loss/train': 1.537237286567688} 08/31/2021 01:58:27 - INFO - __main__ - Step 70761: {'lr': 0.00027775003723804577, 'samples': 13586112, 'steps': 70760, 'loss/train': 1.3135579824447632} 08/31/2021 01:58:28 - INFO - __main__ - Step 70762: {'lr': 0.00027774476328105914, 'samples': 13586304, 'steps': 70761, 'loss/train': 1.1145881414413452} 08/31/2021 01:58:28 - INFO - __main__ - Step 70763: {'lr': 0.0002777394893115712, 'samples': 13586496, 'steps': 70762, 'loss/train': 1.1825907230377197} 08/31/2021 01:58:30 - INFO - __main__ - Step 70764: {'lr': 0.00027773421532958426, 'samples': 13586688, 'steps': 70763, 'loss/train': 1.935309648513794} 08/31/2021 01:58:30 - INFO - __main__ - Step 70765: {'lr': 0.00027772894133510067, 'samples': 13586880, 'steps': 70764, 'loss/train': 0.8935701847076416} 08/31/2021 01:58:30 - INFO - __main__ - Step 70766: {'lr': 0.00027772366732812295, 'samples': 13587072, 'steps': 70765, 'loss/train': 1.5245801210403442} 08/31/2021 01:58:31 - INFO - __main__ - Step 70767: {'lr': 0.0002777183933086532, 'samples': 13587264, 'steps': 70766, 'loss/train': 1.3104478120803833} 08/31/2021 01:58:31 - INFO - __main__ - Step 70768: {'lr': 0.00027771311927669417, 'samples': 13587456, 'steps': 70767, 'loss/train': 1.1340240240097046} 08/31/2021 01:58:31 - INFO - __main__ - Step 70769: {'lr': 0.00027770784523224794, 'samples': 13587648, 'steps': 70768, 'loss/train': 0.29850831627845764} 08/31/2021 01:58:33 - INFO - __main__ - Step 70770: {'lr': 0.000277702571175317, 'samples': 13587840, 'steps': 70769, 'loss/train': 1.3275398015975952} 08/31/2021 01:58:33 - INFO - __main__ - Step 70771: {'lr': 0.0002776972971059037, 'samples': 13588032, 'steps': 70770, 'loss/train': 1.6545017957687378} 08/31/2021 01:58:34 - INFO - __main__ - Step 70772: {'lr': 0.00027769202302401044, 'samples': 13588224, 'steps': 70771, 'loss/train': 1.4350751638412476} 08/31/2021 01:58:34 - INFO - __main__ - Step 70773: {'lr': 0.0002776867489296395, 'samples': 13588416, 'steps': 70772, 'loss/train': 1.3047261238098145} 08/31/2021 01:58:34 - INFO - __main__ - Step 70774: {'lr': 0.00027768147482279344, 'samples': 13588608, 'steps': 70773, 'loss/train': 0.3078049421310425} 08/31/2021 01:58:36 - INFO - __main__ - Step 70775: {'lr': 0.00027767620070347454, 'samples': 13588800, 'steps': 70774, 'loss/train': 1.210696816444397} 08/31/2021 01:58:36 - INFO - __main__ - Step 70776: {'lr': 0.00027767092657168514, 'samples': 13588992, 'steps': 70775, 'loss/train': 1.5465527772903442} 08/31/2021 01:58:37 - INFO - __main__ - Step 70777: {'lr': 0.0002776656524274276, 'samples': 13589184, 'steps': 70776, 'loss/train': 1.4505258798599243} 08/31/2021 01:58:37 - INFO - __main__ - Step 70778: {'lr': 0.0002776603782707044, 'samples': 13589376, 'steps': 70777, 'loss/train': 1.0160603523254395} 08/31/2021 01:58:38 - INFO - __main__ - Step 70779: {'lr': 0.0002776551041015178, 'samples': 13589568, 'steps': 70778, 'loss/train': 1.3776483535766602} 08/31/2021 01:58:39 - INFO - __main__ - Step 70780: {'lr': 0.00027764982991987033, 'samples': 13589760, 'steps': 70779, 'loss/train': 1.2452961206436157} 08/31/2021 01:58:40 - INFO - __main__ - Step 70781: {'lr': 0.0002776445557257642, 'samples': 13589952, 'steps': 70780, 'loss/train': 1.838399052619934} 08/31/2021 01:58:40 - INFO - __main__ - Step 70782: {'lr': 0.00027763928151920193, 'samples': 13590144, 'steps': 70781, 'loss/train': 0.8113296627998352} 08/31/2021 01:58:40 - INFO - __main__ - Step 70783: {'lr': 0.00027763400730018576, 'samples': 13590336, 'steps': 70782, 'loss/train': 1.1195697784423828} 08/31/2021 01:58:41 - INFO - __main__ - Step 70784: {'lr': 0.0002776287330687181, 'samples': 13590528, 'steps': 70783, 'loss/train': 1.297395944595337} 08/31/2021 01:58:43 - INFO - __main__ - Step 70785: {'lr': 0.00027762345882480146, 'samples': 13590720, 'steps': 70784, 'loss/train': 1.2816126346588135} 08/31/2021 01:58:43 - INFO - __main__ - Step 70786: {'lr': 0.000277618184568438, 'samples': 13590912, 'steps': 70785, 'loss/train': 1.5543060302734375} 08/31/2021 01:58:43 - INFO - __main__ - Step 70787: {'lr': 0.0002776129102996303, 'samples': 13591104, 'steps': 70786, 'loss/train': 1.4929540157318115} 08/31/2021 01:58:44 - INFO - __main__ - Step 70788: {'lr': 0.0002776076360183807, 'samples': 13591296, 'steps': 70787, 'loss/train': 1.03612220287323} 08/31/2021 01:58:44 - INFO - __main__ - Step 70789: {'lr': 0.0002776023617246914, 'samples': 13591488, 'steps': 70788, 'loss/train': 1.602980613708496} 08/31/2021 01:58:46 - INFO - __main__ - Step 70790: {'lr': 0.00027759708741856493, 'samples': 13591680, 'steps': 70789, 'loss/train': 0.7620939016342163} 08/31/2021 01:58:46 - INFO - __main__ - Step 70791: {'lr': 0.0002775918131000037, 'samples': 13591872, 'steps': 70790, 'loss/train': 1.6002670526504517} 08/31/2021 01:58:46 - INFO - __main__ - Step 70792: {'lr': 0.00027758653876900995, 'samples': 13592064, 'steps': 70791, 'loss/train': 1.2157922983169556} 08/31/2021 01:58:47 - INFO - __main__ - Step 70793: {'lr': 0.0002775812644255862, 'samples': 13592256, 'steps': 70792, 'loss/train': 1.8222134113311768} 08/31/2021 01:58:47 - INFO - __main__ - Step 70794: {'lr': 0.00027757599006973465, 'samples': 13592448, 'steps': 70793, 'loss/train': 1.4138479232788086} 08/31/2021 01:58:47 - INFO - __main__ - Step 70795: {'lr': 0.00027757071570145794, 'samples': 13592640, 'steps': 70794, 'loss/train': 1.3752152919769287} 08/31/2021 01:58:49 - INFO - __main__ - Step 70796: {'lr': 0.0002775654413207582, 'samples': 13592832, 'steps': 70795, 'loss/train': 0.9981752634048462} 08/31/2021 01:58:49 - INFO - __main__ - Step 70797: {'lr': 0.00027756016692763794, 'samples': 13593024, 'steps': 70796, 'loss/train': 1.2181105613708496} 08/31/2021 01:58:50 - INFO - __main__ - Step 70798: {'lr': 0.0002775548925220994, 'samples': 13593216, 'steps': 70797, 'loss/train': 0.8081824779510498} 08/31/2021 01:58:50 - INFO - __main__ - Step 70799: {'lr': 0.00027754961810414516, 'samples': 13593408, 'steps': 70798, 'loss/train': 1.1431210041046143} 08/31/2021 01:58:50 - INFO - __main__ - Step 70800: {'lr': 0.0002775443436737774, 'samples': 13593600, 'steps': 70799, 'loss/train': 1.4727851152420044} 08/31/2021 01:58:53 - INFO - __main__ - Step 70801: {'lr': 0.00027753906923099863, 'samples': 13593792, 'steps': 70800, 'loss/train': 1.49917471408844} 08/31/2021 01:58:53 - INFO - __main__ - Step 70802: {'lr': 0.0002775337947758112, 'samples': 13593984, 'steps': 70801, 'loss/train': 1.6416800022125244} 08/31/2021 01:58:53 - INFO - __main__ - Step 70803: {'lr': 0.00027752852030821744, 'samples': 13594176, 'steps': 70802, 'loss/train': 1.2758240699768066} 08/31/2021 01:58:54 - INFO - __main__ - Step 70804: {'lr': 0.00027752324582821977, 'samples': 13594368, 'steps': 70803, 'loss/train': 0.07251603156328201} 08/31/2021 01:58:54 - INFO - __main__ - Step 70805: {'lr': 0.0002775179713358205, 'samples': 13594560, 'steps': 70804, 'loss/train': 0.08482061326503754} 08/31/2021 01:58:54 - INFO - __main__ - Step 70806: {'lr': 0.0002775126968310221, 'samples': 13594752, 'steps': 70805, 'loss/train': 0.022785887122154236} 08/31/2021 01:58:56 - INFO - __main__ - Step 70807: {'lr': 0.00027750742231382684, 'samples': 13594944, 'steps': 70806, 'loss/train': 1.146510362625122} 08/31/2021 01:58:56 - INFO - __main__ - Step 70808: {'lr': 0.0002775021477842373, 'samples': 13595136, 'steps': 70807, 'loss/train': 0.334042489528656} 08/31/2021 01:58:57 - INFO - __main__ - Step 70809: {'lr': 0.00027749687324225565, 'samples': 13595328, 'steps': 70808, 'loss/train': 5.666934013366699} 08/31/2021 01:58:57 - INFO - __main__ - Step 70810: {'lr': 0.0002774915986878843, 'samples': 13595520, 'steps': 70809, 'loss/train': 1.157764196395874} 08/31/2021 01:58:58 - INFO - __main__ - Step 70811: {'lr': 0.0002774863241211257, 'samples': 13595712, 'steps': 70810, 'loss/train': 1.2403347492218018} 08/31/2021 01:58:58 - INFO - __main__ - Step 70812: {'lr': 0.0002774810495419821, 'samples': 13595904, 'steps': 70811, 'loss/train': 2.21632719039917} 08/31/2021 01:59:00 - INFO - __main__ - Step 70813: {'lr': 0.00027747577495045603, 'samples': 13596096, 'steps': 70812, 'loss/train': 1.7167216539382935} 08/31/2021 01:59:00 - INFO - __main__ - Step 70814: {'lr': 0.0002774705003465498, 'samples': 13596288, 'steps': 70813, 'loss/train': 0.6486212611198425} 08/31/2021 01:59:00 - INFO - __main__ - Step 70815: {'lr': 0.0002774652257302658, 'samples': 13596480, 'steps': 70814, 'loss/train': 1.156921625137329} 08/31/2021 01:59:01 - INFO - __main__ - Step 70816: {'lr': 0.00027745995110160635, 'samples': 13596672, 'steps': 70815, 'loss/train': 1.7204911708831787} 08/31/2021 01:59:01 - INFO - __main__ - Step 70817: {'lr': 0.0002774546764605739, 'samples': 13596864, 'steps': 70816, 'loss/train': 1.1446226835250854} 08/31/2021 01:59:03 - INFO - __main__ - Step 70818: {'lr': 0.0002774494018071708, 'samples': 13597056, 'steps': 70817, 'loss/train': 1.3494925498962402} 08/31/2021 01:59:03 - INFO - __main__ - Step 70819: {'lr': 0.00027744412714139936, 'samples': 13597248, 'steps': 70818, 'loss/train': 1.214959979057312} 08/31/2021 01:59:03 - INFO - __main__ - Step 70820: {'lr': 0.0002774388524632621, 'samples': 13597440, 'steps': 70819, 'loss/train': 0.8486010432243347} 08/31/2021 01:59:04 - INFO - __main__ - Step 70821: {'lr': 0.0002774335777727613, 'samples': 13597632, 'steps': 70820, 'loss/train': 0.8182990550994873} 08/31/2021 01:59:04 - INFO - __main__ - Step 70822: {'lr': 0.0002774283030698994, 'samples': 13597824, 'steps': 70821, 'loss/train': 1.2506074905395508} 08/31/2021 01:59:06 - INFO - __main__ - Step 70823: {'lr': 0.00027742302835467863, 'samples': 13598016, 'steps': 70822, 'loss/train': 1.4299638271331787} 08/31/2021 01:59:06 - INFO - __main__ - Step 70824: {'lr': 0.00027741775362710155, 'samples': 13598208, 'steps': 70823, 'loss/train': 1.6397533416748047} 08/31/2021 01:59:07 - INFO - __main__ - Step 70825: {'lr': 0.00027741247888717036, 'samples': 13598400, 'steps': 70824, 'loss/train': 1.4938405752182007} 08/31/2021 01:59:07 - INFO - __main__ - Step 70826: {'lr': 0.00027740720413488756, 'samples': 13598592, 'steps': 70825, 'loss/train': 0.09053795784711838} 08/31/2021 01:59:07 - INFO - __main__ - Step 70827: {'lr': 0.00027740192937025554, 'samples': 13598784, 'steps': 70826, 'loss/train': 0.13665920495986938} 08/31/2021 01:59:09 - INFO - __main__ - Step 70828: {'lr': 0.0002773966545932767, 'samples': 13598976, 'steps': 70827, 'loss/train': 1.0387465953826904} 08/31/2021 01:59:09 - INFO - __main__ - Step 70829: {'lr': 0.00027739137980395325, 'samples': 13599168, 'steps': 70828, 'loss/train': 1.3873406648635864} 08/31/2021 01:59:10 - INFO - __main__ - Step 70830: {'lr': 0.0002773861050022876, 'samples': 13599360, 'steps': 70829, 'loss/train': 1.387803554534912} 08/31/2021 01:59:10 - INFO - __main__ - Step 70831: {'lr': 0.0002773808301882823, 'samples': 13599552, 'steps': 70830, 'loss/train': 1.4273505210876465} 08/31/2021 01:59:10 - INFO - __main__ - Step 70832: {'lr': 0.0002773755553619396, 'samples': 13599744, 'steps': 70831, 'loss/train': 1.0267419815063477} 08/31/2021 01:59:12 - INFO - __main__ - Step 70833: {'lr': 0.00027737028052326183, 'samples': 13599936, 'steps': 70832, 'loss/train': 0.06221706420183182} 08/31/2021 01:59:12 - INFO - __main__ - Step 70834: {'lr': 0.0002773650056722516, 'samples': 13600128, 'steps': 70833, 'loss/train': 1.4242963790893555} 08/31/2021 01:59:13 - INFO - __main__ - Step 70835: {'lr': 0.00027735973080891097, 'samples': 13600320, 'steps': 70834, 'loss/train': 1.3066567182540894} 08/31/2021 01:59:13 - INFO - __main__ - Step 70836: {'lr': 0.00027735445593324255, 'samples': 13600512, 'steps': 70835, 'loss/train': 1.259000301361084} 08/31/2021 01:59:13 - INFO - __main__ - Step 70837: {'lr': 0.0002773491810452486, 'samples': 13600704, 'steps': 70836, 'loss/train': 0.6392010450363159} 08/31/2021 01:59:14 - INFO - __main__ - Step 70838: {'lr': 0.0002773439061449315, 'samples': 13600896, 'steps': 70837, 'loss/train': 1.5021995306015015} 08/31/2021 01:59:16 - INFO - __main__ - Step 70839: {'lr': 0.0002773386312322937, 'samples': 13601088, 'steps': 70838, 'loss/train': 1.55643630027771} 08/31/2021 01:59:16 - INFO - __main__ - Step 70840: {'lr': 0.0002773333563073375, 'samples': 13601280, 'steps': 70839, 'loss/train': 1.2293998003005981} 08/31/2021 01:59:16 - INFO - __main__ - Step 70841: {'lr': 0.0002773280813700654, 'samples': 13601472, 'steps': 70840, 'loss/train': 1.1084860563278198} 08/31/2021 01:59:17 - INFO - __main__ - Step 70842: {'lr': 0.0002773228064204796, 'samples': 13601664, 'steps': 70841, 'loss/train': 0.8307563066482544} 08/31/2021 01:59:17 - INFO - __main__ - Step 70843: {'lr': 0.00027731753145858256, 'samples': 13601856, 'steps': 70842, 'loss/train': 1.154921054840088} 08/31/2021 01:59:19 - INFO - __main__ - Step 70844: {'lr': 0.00027731225648437675, 'samples': 13602048, 'steps': 70843, 'loss/train': 1.4845200777053833} 08/31/2021 01:59:20 - INFO - __main__ - Step 70845: {'lr': 0.0002773069814978644, 'samples': 13602240, 'steps': 70844, 'loss/train': 0.7670890688896179} 08/31/2021 01:59:20 - INFO - __main__ - Step 70846: {'lr': 0.0002773017064990479, 'samples': 13602432, 'steps': 70845, 'loss/train': 1.0900715589523315} 08/31/2021 01:59:20 - INFO - __main__ - Step 70847: {'lr': 0.0002772964314879297, 'samples': 13602624, 'steps': 70846, 'loss/train': 0.12234720587730408} 08/31/2021 01:59:21 - INFO - __main__ - Step 70848: {'lr': 0.0002772911564645122, 'samples': 13602816, 'steps': 70847, 'loss/train': 1.0471826791763306} 08/31/2021 01:59:22 - INFO - __main__ - Step 70849: {'lr': 0.0002772858814287976, 'samples': 13603008, 'steps': 70848, 'loss/train': 1.1091302633285522} 08/31/2021 01:59:23 - INFO - __main__ - Step 70850: {'lr': 0.0002772806063807886, 'samples': 13603200, 'steps': 70849, 'loss/train': 1.3517860174179077} 08/31/2021 01:59:23 - INFO - __main__ - Step 70851: {'lr': 0.00027727533132048727, 'samples': 13603392, 'steps': 70850, 'loss/train': 1.3407161235809326} 08/31/2021 01:59:24 - INFO - __main__ - Step 70852: {'lr': 0.0002772700562478961, 'samples': 13603584, 'steps': 70851, 'loss/train': 1.380319356918335} 08/31/2021 01:59:24 - INFO - __main__ - Step 70853: {'lr': 0.00027726478116301746, 'samples': 13603776, 'steps': 70852, 'loss/train': 1.395501732826233} 08/31/2021 01:59:25 - INFO - __main__ - Step 70854: {'lr': 0.0002772595060658537, 'samples': 13603968, 'steps': 70853, 'loss/train': 1.4789544343948364} 08/31/2021 01:59:26 - INFO - __main__ - Step 70855: {'lr': 0.0002772542309564072, 'samples': 13604160, 'steps': 70854, 'loss/train': 1.6174919605255127} 08/31/2021 01:59:26 - INFO - __main__ - Step 70856: {'lr': 0.0002772489558346805, 'samples': 13604352, 'steps': 70855, 'loss/train': 1.1474571228027344} 08/31/2021 01:59:27 - INFO - __main__ - Step 70857: {'lr': 0.00027724368070067577, 'samples': 13604544, 'steps': 70856, 'loss/train': 1.3340363502502441} 08/31/2021 01:59:27 - INFO - __main__ - Step 70858: {'lr': 0.0002772384055543954, 'samples': 13604736, 'steps': 70857, 'loss/train': 1.128651738166809} 08/31/2021 01:59:27 - INFO - __main__ - Step 70859: {'lr': 0.0002772331303958419, 'samples': 13604928, 'steps': 70858, 'loss/train': 1.5630762577056885} 08/31/2021 01:59:29 - INFO - __main__ - Step 70860: {'lr': 0.0002772278552250176, 'samples': 13605120, 'steps': 70859, 'loss/train': 0.4015461504459381} 08/31/2021 01:59:29 - INFO - __main__ - Step 70861: {'lr': 0.00027722258004192474, 'samples': 13605312, 'steps': 70860, 'loss/train': 2.0906851291656494} 08/31/2021 01:59:30 - INFO - __main__ - Step 70862: {'lr': 0.0002772173048465659, 'samples': 13605504, 'steps': 70861, 'loss/train': 1.79374361038208} 08/31/2021 01:59:30 - INFO - __main__ - Step 70863: {'lr': 0.0002772120296389433, 'samples': 13605696, 'steps': 70862, 'loss/train': 0.8162899613380432} 08/31/2021 01:59:30 - INFO - __main__ - Step 70864: {'lr': 0.00027720675441905945, 'samples': 13605888, 'steps': 70863, 'loss/train': 0.9251577258110046} 08/31/2021 01:59:32 - INFO - __main__ - Step 70865: {'lr': 0.0002772014791869166, 'samples': 13606080, 'steps': 70864, 'loss/train': 1.757735013961792} 08/31/2021 01:59:33 - INFO - __main__ - Step 70866: {'lr': 0.0002771962039425172, 'samples': 13606272, 'steps': 70865, 'loss/train': 1.212862253189087} 08/31/2021 01:59:33 - INFO - __main__ - Step 70867: {'lr': 0.0002771909286858636, 'samples': 13606464, 'steps': 70866, 'loss/train': 1.3525118827819824} 08/31/2021 01:59:33 - INFO - __main__ - Step 70868: {'lr': 0.0002771856534169582, 'samples': 13606656, 'steps': 70867, 'loss/train': 0.7583963871002197} 08/31/2021 01:59:34 - INFO - __main__ - Step 70869: {'lr': 0.0002771803781358034, 'samples': 13606848, 'steps': 70868, 'loss/train': 1.5536314249038696} 08/31/2021 01:59:34 - INFO - __main__ - Step 70870: {'lr': 0.0002771751028424014, 'samples': 13607040, 'steps': 70869, 'loss/train': 1.2631455659866333} 08/31/2021 01:59:36 - INFO - __main__ - Step 70871: {'lr': 0.00027716982753675485, 'samples': 13607232, 'steps': 70870, 'loss/train': 1.4127936363220215} 08/31/2021 01:59:36 - INFO - __main__ - Step 70872: {'lr': 0.00027716455221886595, 'samples': 13607424, 'steps': 70871, 'loss/train': 1.108192801475525} 08/31/2021 01:59:36 - INFO - __main__ - Step 70873: {'lr': 0.00027715927688873717, 'samples': 13607616, 'steps': 70872, 'loss/train': 1.1890170574188232} 08/31/2021 01:59:37 - INFO - __main__ - Step 70874: {'lr': 0.0002771540015463708, 'samples': 13607808, 'steps': 70873, 'loss/train': 1.6610676050186157} 08/31/2021 01:59:37 - INFO - __main__ - Step 70875: {'lr': 0.0002771487261917692, 'samples': 13608000, 'steps': 70874, 'loss/train': 0.6455259919166565} 08/31/2021 01:59:39 - INFO - __main__ - Step 70876: {'lr': 0.00027714345082493493, 'samples': 13608192, 'steps': 70875, 'loss/train': 1.0609291791915894} 08/31/2021 01:59:39 - INFO - __main__ - Step 70877: {'lr': 0.00027713817544587014, 'samples': 13608384, 'steps': 70876, 'loss/train': 1.2250745296478271} 08/31/2021 01:59:40 - INFO - __main__ - Step 70878: {'lr': 0.00027713290005457734, 'samples': 13608576, 'steps': 70877, 'loss/train': 0.066319040954113} 08/31/2021 01:59:40 - INFO - __main__ - Step 70879: {'lr': 0.00027712762465105886, 'samples': 13608768, 'steps': 70878, 'loss/train': 1.5456197261810303} 08/31/2021 01:59:40 - INFO - __main__ - Step 70880: {'lr': 0.0002771223492353171, 'samples': 13608960, 'steps': 70879, 'loss/train': 1.4455211162567139} 08/31/2021 01:59:42 - INFO - __main__ - Step 70881: {'lr': 0.0002771170738073544, 'samples': 13609152, 'steps': 70880, 'loss/train': 0.9542911052703857} 08/31/2021 01:59:42 - INFO - __main__ - Step 70882: {'lr': 0.0002771117983671733, 'samples': 13609344, 'steps': 70881, 'loss/train': 0.8098540902137756} 08/31/2021 01:59:42 - INFO - __main__ - Step 70883: {'lr': 0.0002771065229147759, 'samples': 13609536, 'steps': 70882, 'loss/train': 1.170528531074524} 08/31/2021 01:59:43 - INFO - __main__ - Step 70884: {'lr': 0.0002771012474501647, 'samples': 13609728, 'steps': 70883, 'loss/train': 1.2828874588012695} 08/31/2021 01:59:43 - INFO - __main__ - Step 70885: {'lr': 0.0002770959719733422, 'samples': 13609920, 'steps': 70884, 'loss/train': 0.9665020108222961} 08/31/2021 01:59:45 - INFO - __main__ - Step 70886: {'lr': 0.00027709069648431056, 'samples': 13610112, 'steps': 70885, 'loss/train': 1.5284641981124878} 08/31/2021 01:59:45 - INFO - __main__ - Step 70887: {'lr': 0.0002770854209830724, 'samples': 13610304, 'steps': 70886, 'loss/train': 0.08084061741828918} 08/31/2021 01:59:45 - INFO - __main__ - Step 70888: {'lr': 0.00027708014546962986, 'samples': 13610496, 'steps': 70887, 'loss/train': 0.7521278858184814} 08/31/2021 01:59:46 - INFO - __main__ - Step 70889: {'lr': 0.0002770748699439855, 'samples': 13610688, 'steps': 70888, 'loss/train': 1.258407711982727} 08/31/2021 01:59:46 - INFO - __main__ - Step 70890: {'lr': 0.0002770695944061416, 'samples': 13610880, 'steps': 70889, 'loss/train': 1.3876216411590576} 08/31/2021 01:59:48 - INFO - __main__ - Step 70891: {'lr': 0.00027706431885610053, 'samples': 13611072, 'steps': 70890, 'loss/train': 1.4551655054092407} 08/31/2021 01:59:49 - INFO - __main__ - Step 70892: {'lr': 0.0002770590432938647, 'samples': 13611264, 'steps': 70891, 'loss/train': 1.0194017887115479} 08/31/2021 01:59:49 - INFO - __main__ - Step 70893: {'lr': 0.00027705376771943645, 'samples': 13611456, 'steps': 70892, 'loss/train': 0.7488135695457458} 08/31/2021 01:59:49 - INFO - __main__ - Step 70894: {'lr': 0.00027704849213281823, 'samples': 13611648, 'steps': 70893, 'loss/train': 1.5493336915969849} 08/31/2021 01:59:50 - INFO - __main__ - Step 70895: {'lr': 0.00027704321653401244, 'samples': 13611840, 'steps': 70894, 'loss/train': 1.3397955894470215} 08/31/2021 01:59:51 - INFO - __main__ - Step 70896: {'lr': 0.00027703794092302135, 'samples': 13612032, 'steps': 70895, 'loss/train': 1.2285044193267822} 08/31/2021 01:59:52 - INFO - __main__ - Step 70897: {'lr': 0.0002770326652998473, 'samples': 13612224, 'steps': 70896, 'loss/train': 1.441120982170105} 08/31/2021 01:59:52 - INFO - __main__ - Step 70898: {'lr': 0.0002770273896644929, 'samples': 13612416, 'steps': 70897, 'loss/train': 1.5895835161209106} 08/31/2021 01:59:52 - INFO - __main__ - Step 70899: {'lr': 0.00027702211401696024, 'samples': 13612608, 'steps': 70898, 'loss/train': 1.3481429815292358} 08/31/2021 01:59:53 - INFO - __main__ - Step 70900: {'lr': 0.0002770168383572519, 'samples': 13612800, 'steps': 70899, 'loss/train': 1.36026930809021} 08/31/2021 01:59:54 - INFO - __main__ - Step 70901: {'lr': 0.00027701156268537016, 'samples': 13612992, 'steps': 70900, 'loss/train': 1.406764268875122} 08/31/2021 01:59:55 - INFO - __main__ - Step 70902: {'lr': 0.0002770062870013174, 'samples': 13613184, 'steps': 70901, 'loss/train': 0.8945376873016357} 08/31/2021 01:59:55 - INFO - __main__ - Step 70903: {'lr': 0.00027700101130509615, 'samples': 13613376, 'steps': 70902, 'loss/train': 1.3494728803634644} 08/31/2021 01:59:56 - INFO - __main__ - Step 70904: {'lr': 0.00027699573559670853, 'samples': 13613568, 'steps': 70903, 'loss/train': 0.5781910419464111} 08/31/2021 01:59:56 - INFO - __main__ - Step 70905: {'lr': 0.0002769904598761571, 'samples': 13613760, 'steps': 70904, 'loss/train': 0.9341793060302734} 08/31/2021 01:59:56 - INFO - __main__ - Step 70906: {'lr': 0.00027698518414344414, 'samples': 13613952, 'steps': 70905, 'loss/train': 0.5741398334503174} 08/31/2021 01:59:58 - INFO - __main__ - Step 70907: {'lr': 0.00027697990839857214, 'samples': 13614144, 'steps': 70906, 'loss/train': 0.15583543479442596} 08/31/2021 01:59:58 - INFO - __main__ - Step 70908: {'lr': 0.0002769746326415433, 'samples': 13614336, 'steps': 70907, 'loss/train': 1.085799217224121} 08/31/2021 01:59:59 - INFO - __main__ - Step 70909: {'lr': 0.0002769693568723603, 'samples': 13614528, 'steps': 70908, 'loss/train': 0.8898462653160095} 08/31/2021 01:59:59 - INFO - __main__ - Step 70910: {'lr': 0.00027696408109102516, 'samples': 13614720, 'steps': 70909, 'loss/train': 1.2776685953140259} 08/31/2021 01:59:59 - INFO - __main__ - Step 70911: {'lr': 0.00027695880529754046, 'samples': 13614912, 'steps': 70910, 'loss/train': 0.06326914578676224} 08/31/2021 02:00:01 - INFO - __main__ - Step 70912: {'lr': 0.0002769535294919086, 'samples': 13615104, 'steps': 70911, 'loss/train': 1.206645131111145} 08/31/2021 02:00:01 - INFO - __main__ - Step 70913: {'lr': 0.0002769482536741318, 'samples': 13615296, 'steps': 70912, 'loss/train': 1.4326192140579224} 08/31/2021 02:00:02 - INFO - __main__ - Step 70914: {'lr': 0.0002769429778442126, 'samples': 13615488, 'steps': 70913, 'loss/train': 1.1480848789215088} 08/31/2021 02:00:02 - INFO - __main__ - Step 70915: {'lr': 0.00027693770200215323, 'samples': 13615680, 'steps': 70914, 'loss/train': 1.116368293762207} 08/31/2021 02:00:02 - INFO - __main__ - Step 70916: {'lr': 0.00027693242614795625, 'samples': 13615872, 'steps': 70915, 'loss/train': 0.40851789712905884} 08/31/2021 02:00:04 - INFO - __main__ - Step 70917: {'lr': 0.0002769271502816239, 'samples': 13616064, 'steps': 70916, 'loss/train': 0.8099366426467896} 08/31/2021 02:00:04 - INFO - __main__ - Step 70918: {'lr': 0.00027692187440315856, 'samples': 13616256, 'steps': 70917, 'loss/train': 1.4407343864440918} 08/31/2021 02:00:05 - INFO - __main__ - Step 70919: {'lr': 0.0002769165985125627, 'samples': 13616448, 'steps': 70918, 'loss/train': 0.41420289874076843} 08/31/2021 02:00:05 - INFO - __main__ - Step 70920: {'lr': 0.00027691132260983855, 'samples': 13616640, 'steps': 70919, 'loss/train': 1.4911998510360718} 08/31/2021 02:00:05 - INFO - __main__ - Step 70921: {'lr': 0.0002769060466949886, 'samples': 13616832, 'steps': 70920, 'loss/train': 1.9299145936965942} 08/31/2021 02:00:07 - INFO - __main__ - Step 70922: {'lr': 0.00027690077076801523, 'samples': 13617024, 'steps': 70921, 'loss/train': 0.7125928401947021} 08/31/2021 02:00:07 - INFO - __main__ - Step 70923: {'lr': 0.00027689549482892077, 'samples': 13617216, 'steps': 70922, 'loss/train': 0.6615471243858337} 08/31/2021 02:00:08 - INFO - __main__ - Step 70924: {'lr': 0.00027689021887770764, 'samples': 13617408, 'steps': 70923, 'loss/train': 1.1014584302902222} 08/31/2021 02:00:08 - INFO - __main__ - Step 70925: {'lr': 0.00027688494291437817, 'samples': 13617600, 'steps': 70924, 'loss/train': 1.1047930717468262} 08/31/2021 02:00:08 - INFO - __main__ - Step 70926: {'lr': 0.00027687966693893475, 'samples': 13617792, 'steps': 70925, 'loss/train': 1.4068434238433838} 08/31/2021 02:00:10 - INFO - __main__ - Step 70927: {'lr': 0.0002768743909513798, 'samples': 13617984, 'steps': 70926, 'loss/train': 1.3722939491271973} 08/31/2021 02:00:11 - INFO - __main__ - Step 70928: {'lr': 0.00027686911495171564, 'samples': 13618176, 'steps': 70927, 'loss/train': 1.6528218984603882} 08/31/2021 02:00:11 - INFO - __main__ - Step 70929: {'lr': 0.0002768638389399447, 'samples': 13618368, 'steps': 70928, 'loss/train': 0.9773498773574829} 08/31/2021 02:00:11 - INFO - __main__ - Step 70930: {'lr': 0.00027685856291606933, 'samples': 13618560, 'steps': 70929, 'loss/train': 1.1212787628173828} 08/31/2021 02:00:12 - INFO - __main__ - Step 70931: {'lr': 0.00027685328688009187, 'samples': 13618752, 'steps': 70930, 'loss/train': 1.854131817817688} 08/31/2021 02:00:13 - INFO - __main__ - Step 70932: {'lr': 0.0002768480108320147, 'samples': 13618944, 'steps': 70931, 'loss/train': 1.2695517539978027} 08/31/2021 02:00:14 - INFO - __main__ - Step 70933: {'lr': 0.0002768427347718403, 'samples': 13619136, 'steps': 70932, 'loss/train': 1.323284387588501} 08/31/2021 02:00:14 - INFO - __main__ - Step 70934: {'lr': 0.00027683745869957094, 'samples': 13619328, 'steps': 70933, 'loss/train': 0.9788365960121155} 08/31/2021 02:00:14 - INFO - __main__ - Step 70935: {'lr': 0.00027683218261520906, 'samples': 13619520, 'steps': 70934, 'loss/train': 0.46051692962646484} 08/31/2021 02:00:15 - INFO - __main__ - Step 70936: {'lr': 0.000276826906518757, 'samples': 13619712, 'steps': 70935, 'loss/train': 0.8745854496955872} 08/31/2021 02:00:16 - INFO - __main__ - Step 70937: {'lr': 0.00027682163041021715, 'samples': 13619904, 'steps': 70936, 'loss/train': 1.6823947429656982} 08/31/2021 02:00:17 - INFO - __main__ - Step 70938: {'lr': 0.0002768163542895919, 'samples': 13620096, 'steps': 70937, 'loss/train': 1.3462790250778198} 08/31/2021 02:00:17 - INFO - __main__ - Step 70939: {'lr': 0.00027681107815688354, 'samples': 13620288, 'steps': 70938, 'loss/train': 0.7701421976089478} 08/31/2021 02:00:18 - INFO - __main__ - Step 70940: {'lr': 0.0002768058020120946, 'samples': 13620480, 'steps': 70939, 'loss/train': 0.050203077495098114} 08/31/2021 02:00:18 - INFO - __main__ - Step 70941: {'lr': 0.00027680052585522737, 'samples': 13620672, 'steps': 70940, 'loss/train': 1.2158541679382324} 08/31/2021 02:00:18 - INFO - __main__ - Step 70942: {'lr': 0.0002767952496862842, 'samples': 13620864, 'steps': 70941, 'loss/train': 5.75856876373291} 08/31/2021 02:00:20 - INFO - __main__ - Step 70943: {'lr': 0.0002767899735052676, 'samples': 13621056, 'steps': 70942, 'loss/train': 1.787402868270874} 08/31/2021 02:00:20 - INFO - __main__ - Step 70944: {'lr': 0.00027678469731217976, 'samples': 13621248, 'steps': 70943, 'loss/train': 0.5172969698905945} 08/31/2021 02:00:20 - INFO - __main__ - Step 70945: {'lr': 0.0002767794211070232, 'samples': 13621440, 'steps': 70944, 'loss/train': 1.7259279489517212} 08/31/2021 02:00:21 - INFO - __main__ - Step 70946: {'lr': 0.00027677414488980017, 'samples': 13621632, 'steps': 70945, 'loss/train': 1.2712653875350952} 08/31/2021 02:00:21 - INFO - __main__ - Step 70947: {'lr': 0.0002767688686605132, 'samples': 13621824, 'steps': 70946, 'loss/train': 1.120287299156189} 08/31/2021 02:00:23 - INFO - __main__ - Step 70948: {'lr': 0.0002767635924191645, 'samples': 13622016, 'steps': 70947, 'loss/train': 1.3822990655899048} 08/31/2021 02:00:24 - INFO - __main__ - Step 70949: {'lr': 0.00027675831616575666, 'samples': 13622208, 'steps': 70948, 'loss/train': 0.07125447690486908} 08/31/2021 02:00:24 - INFO - __main__ - Step 70950: {'lr': 0.00027675303990029186, 'samples': 13622400, 'steps': 70949, 'loss/train': 0.8894773125648499} 08/31/2021 02:00:24 - INFO - __main__ - Step 70951: {'lr': 0.0002767477636227726, 'samples': 13622592, 'steps': 70950, 'loss/train': 0.9449966549873352} 08/31/2021 02:00:25 - INFO - __main__ - Step 70952: {'lr': 0.00027674248733320115, 'samples': 13622784, 'steps': 70951, 'loss/train': 1.2031606435775757} 08/31/2021 02:00:26 - INFO - __main__ - Step 70953: {'lr': 0.00027673721103158, 'samples': 13622976, 'steps': 70952, 'loss/train': 0.9498867392539978} 08/31/2021 02:00:27 - INFO - __main__ - Step 70954: {'lr': 0.0002767319347179115, 'samples': 13623168, 'steps': 70953, 'loss/train': 1.400974154472351} 08/31/2021 02:00:27 - INFO - __main__ - Step 70955: {'lr': 0.0002767266583921979, 'samples': 13623360, 'steps': 70954, 'loss/train': 1.6825981140136719} 08/31/2021 02:00:27 - INFO - __main__ - Step 70956: {'lr': 0.00027672138205444175, 'samples': 13623552, 'steps': 70955, 'loss/train': 1.8054683208465576} 08/31/2021 02:00:28 - INFO - __main__ - Step 70957: {'lr': 0.0002767161057046453, 'samples': 13623744, 'steps': 70956, 'loss/train': 0.9248736500740051} 08/31/2021 02:00:28 - INFO - __main__ - Step 70958: {'lr': 0.0002767108293428111, 'samples': 13623936, 'steps': 70957, 'loss/train': 1.4837546348571777} 08/31/2021 02:00:30 - INFO - __main__ - Step 70959: {'lr': 0.00027670555296894134, 'samples': 13624128, 'steps': 70958, 'loss/train': 1.11895751953125} 08/31/2021 02:00:30 - INFO - __main__ - Step 70960: {'lr': 0.00027670027658303843, 'samples': 13624320, 'steps': 70959, 'loss/train': 0.47081100940704346} 08/31/2021 02:00:30 - INFO - __main__ - Step 70961: {'lr': 0.00027669500018510484, 'samples': 13624512, 'steps': 70960, 'loss/train': 1.214030385017395} 08/31/2021 02:00:31 - INFO - __main__ - Step 70962: {'lr': 0.00027668972377514295, 'samples': 13624704, 'steps': 70961, 'loss/train': 0.8361070156097412} 08/31/2021 02:00:31 - INFO - __main__ - Step 70963: {'lr': 0.00027668444735315503, 'samples': 13624896, 'steps': 70962, 'loss/train': 1.2012555599212646} 08/31/2021 02:00:33 - INFO - __main__ - Step 70964: {'lr': 0.0002766791709191435, 'samples': 13625088, 'steps': 70963, 'loss/train': 1.3099870681762695} 08/31/2021 02:00:33 - INFO - __main__ - Step 70965: {'lr': 0.0002766738944731107, 'samples': 13625280, 'steps': 70964, 'loss/train': 1.0944982767105103} 08/31/2021 02:00:33 - INFO - __main__ - Step 70966: {'lr': 0.00027666861801505904, 'samples': 13625472, 'steps': 70965, 'loss/train': 1.6444346904754639} 08/31/2021 02:00:34 - INFO - __main__ - Step 70967: {'lr': 0.000276663341544991, 'samples': 13625664, 'steps': 70966, 'loss/train': 1.5825961828231812} 08/31/2021 02:00:34 - INFO - __main__ - Step 70968: {'lr': 0.0002766580650629089, 'samples': 13625856, 'steps': 70967, 'loss/train': 1.2333956956863403} 08/31/2021 02:00:36 - INFO - __main__ - Step 70969: {'lr': 0.00027665278856881496, 'samples': 13626048, 'steps': 70968, 'loss/train': 0.8483140468597412} 08/31/2021 02:00:36 - INFO - __main__ - Step 70970: {'lr': 0.00027664751206271177, 'samples': 13626240, 'steps': 70969, 'loss/train': 1.2344416379928589} 08/31/2021 02:00:36 - INFO - __main__ - Step 70971: {'lr': 0.00027664223554460163, 'samples': 13626432, 'steps': 70970, 'loss/train': 2.318326711654663} 08/31/2021 02:00:37 - INFO - __main__ - Step 70972: {'lr': 0.0002766369590144869, 'samples': 13626624, 'steps': 70971, 'loss/train': 1.4842514991760254} 08/31/2021 02:00:37 - INFO - __main__ - Step 70973: {'lr': 0.00027663168247236996, 'samples': 13626816, 'steps': 70972, 'loss/train': 3.8655922412872314} 08/31/2021 02:00:39 - INFO - __main__ - Step 70974: {'lr': 0.00027662640591825314, 'samples': 13627008, 'steps': 70973, 'loss/train': 1.902207374572754} 08/31/2021 02:00:39 - INFO - __main__ - Step 70975: {'lr': 0.000276621129352139, 'samples': 13627200, 'steps': 70974, 'loss/train': 1.8512729406356812} 08/31/2021 02:00:39 - INFO - __main__ - Step 70976: {'lr': 0.0002766158527740297, 'samples': 13627392, 'steps': 70975, 'loss/train': 1.3686286211013794} 08/31/2021 02:00:40 - INFO - __main__ - Step 70977: {'lr': 0.00027661057618392766, 'samples': 13627584, 'steps': 70976, 'loss/train': 4.053260326385498} 08/31/2021 02:00:40 - INFO - __main__ - Step 70978: {'lr': 0.00027660529958183533, 'samples': 13627776, 'steps': 70977, 'loss/train': 1.0426968336105347} 08/31/2021 02:00:40 - INFO - __main__ - Step 70979: {'lr': 0.00027660002296775514, 'samples': 13627968, 'steps': 70978, 'loss/train': 1.38494074344635} 08/31/2021 02:00:42 - INFO - __main__ - Step 70980: {'lr': 0.00027659474634168937, 'samples': 13628160, 'steps': 70979, 'loss/train': 1.3989641666412354} 08/31/2021 02:00:43 - INFO - __main__ - Step 70981: {'lr': 0.00027658946970364034, 'samples': 13628352, 'steps': 70980, 'loss/train': 1.1567530632019043} 08/31/2021 02:00:43 - INFO - __main__ - Step 70982: {'lr': 0.0002765841930536106, 'samples': 13628544, 'steps': 70981, 'loss/train': 0.07208515703678131} 08/31/2021 02:00:43 - INFO - __main__ - Step 70983: {'lr': 0.0002765789163916024, 'samples': 13628736, 'steps': 70982, 'loss/train': 1.5155185461044312} 08/31/2021 02:00:44 - INFO - __main__ - Step 70984: {'lr': 0.0002765736397176182, 'samples': 13628928, 'steps': 70983, 'loss/train': 1.6239458322525024} 08/31/2021 02:00:45 - INFO - __main__ - Step 70985: {'lr': 0.0002765683630316602, 'samples': 13629120, 'steps': 70984, 'loss/train': 1.2672384977340698} 08/31/2021 02:00:46 - INFO - __main__ - Step 70986: {'lr': 0.000276563086333731, 'samples': 13629312, 'steps': 70985, 'loss/train': 0.3055866062641144} 08/31/2021 02:00:46 - INFO - __main__ - Step 70987: {'lr': 0.0002765578096238328, 'samples': 13629504, 'steps': 70986, 'loss/train': 1.4123523235321045} 08/31/2021 02:00:46 - INFO - __main__ - Step 70988: {'lr': 0.0002765525329019681, 'samples': 13629696, 'steps': 70987, 'loss/train': 0.710658609867096} 08/31/2021 02:00:47 - INFO - __main__ - Step 70989: {'lr': 0.0002765472561681393, 'samples': 13629888, 'steps': 70988, 'loss/train': 1.3539502620697021} 08/31/2021 02:00:48 - INFO - __main__ - Step 70990: {'lr': 0.0002765419794223487, 'samples': 13630080, 'steps': 70989, 'loss/train': 1.313214659690857} 08/31/2021 02:00:49 - INFO - __main__ - Step 70991: {'lr': 0.0002765367026645987, 'samples': 13630272, 'steps': 70990, 'loss/train': 1.3658385276794434} 08/31/2021 02:00:49 - INFO - __main__ - Step 70992: {'lr': 0.0002765314258948916, 'samples': 13630464, 'steps': 70991, 'loss/train': 1.220522403717041} 08/31/2021 02:00:49 - INFO - __main__ - Step 70993: {'lr': 0.0002765261491132299, 'samples': 13630656, 'steps': 70992, 'loss/train': 1.2400041818618774} 08/31/2021 02:00:50 - INFO - __main__ - Step 70994: {'lr': 0.0002765208723196159, 'samples': 13630848, 'steps': 70993, 'loss/train': 0.9986876249313354} 08/31/2021 02:00:51 - INFO - __main__ - Step 70995: {'lr': 0.000276515595514052, 'samples': 13631040, 'steps': 70994, 'loss/train': 1.4180858135223389} 08/31/2021 02:00:52 - INFO - __main__ - Step 70996: {'lr': 0.00027651031869654056, 'samples': 13631232, 'steps': 70995, 'loss/train': 1.1480562686920166} 08/31/2021 02:00:52 - INFO - __main__ - Step 70997: {'lr': 0.0002765050418670841, 'samples': 13631424, 'steps': 70996, 'loss/train': 0.32586273550987244} 08/31/2021 02:00:52 - INFO - __main__ - Step 70998: {'lr': 0.00027649976502568477, 'samples': 13631616, 'steps': 70997, 'loss/train': 1.4961711168289185} 08/31/2021 02:00:53 - INFO - __main__ - Step 70999: {'lr': 0.00027649448817234506, 'samples': 13631808, 'steps': 70998, 'loss/train': 1.4981622695922852} 08/31/2021 02:00:55 - INFO - __main__ - Step 71000: {'lr': 0.00027648921130706737, 'samples': 13632000, 'steps': 70999, 'loss/train': 1.2395495176315308} 08/31/2021 02:00:55 - INFO - __main__ - Step 71001: {'lr': 0.000276483934429854, 'samples': 13632192, 'steps': 71000, 'loss/train': 1.4329633712768555} 08/31/2021 02:00:55 - INFO - __main__ - Step 71002: {'lr': 0.00027647865754070746, 'samples': 13632384, 'steps': 71001, 'loss/train': 1.0584570169448853} 08/31/2021 02:00:56 - INFO - __main__ - Step 71003: {'lr': 0.00027647338063963, 'samples': 13632576, 'steps': 71002, 'loss/train': 1.3539928197860718} 08/31/2021 02:00:56 - INFO - __main__ - Step 71004: {'lr': 0.00027646810372662406, 'samples': 13632768, 'steps': 71003, 'loss/train': 1.3562623262405396} 08/31/2021 02:00:58 - INFO - __main__ - Step 71005: {'lr': 0.000276462826801692, 'samples': 13632960, 'steps': 71004, 'loss/train': 0.6596177220344543} 08/31/2021 02:00:58 - INFO - __main__ - Step 71006: {'lr': 0.0002764575498648362, 'samples': 13633152, 'steps': 71005, 'loss/train': 1.392074704170227} 08/31/2021 02:00:58 - INFO - __main__ - Step 71007: {'lr': 0.000276452272916059, 'samples': 13633344, 'steps': 71006, 'loss/train': 1.293148398399353} 08/31/2021 02:00:59 - INFO - __main__ - Step 71008: {'lr': 0.00027644699595536285, 'samples': 13633536, 'steps': 71007, 'loss/train': 1.5725394487380981} 08/31/2021 02:00:59 - INFO - __main__ - Step 71009: {'lr': 0.00027644171898275006, 'samples': 13633728, 'steps': 71008, 'loss/train': 0.7555349469184875} 08/31/2021 02:01:01 - INFO - __main__ - Step 71010: {'lr': 0.0002764364419982231, 'samples': 13633920, 'steps': 71009, 'loss/train': 1.404726266860962} 08/31/2021 02:01:01 - INFO - __main__ - Step 71011: {'lr': 0.0002764311650017842, 'samples': 13634112, 'steps': 71010, 'loss/train': 1.011318325996399} 08/31/2021 02:01:01 - INFO - __main__ - Step 71012: {'lr': 0.0002764258879934359, 'samples': 13634304, 'steps': 71011, 'loss/train': 1.202316164970398} 08/31/2021 02:01:02 - INFO - __main__ - Step 71013: {'lr': 0.0002764206109731805, 'samples': 13634496, 'steps': 71012, 'loss/train': 1.4375057220458984} 08/31/2021 02:01:02 - INFO - __main__ - Step 71014: {'lr': 0.0002764153339410203, 'samples': 13634688, 'steps': 71013, 'loss/train': 1.2059153318405151} 08/31/2021 02:01:04 - INFO - __main__ - Step 71015: {'lr': 0.0002764100568969578, 'samples': 13634880, 'steps': 71014, 'loss/train': 1.4581209421157837} 08/31/2021 02:01:04 - INFO - __main__ - Step 71016: {'lr': 0.0002764047798409954, 'samples': 13635072, 'steps': 71015, 'loss/train': 1.1895476579666138} 08/31/2021 02:01:04 - INFO - __main__ - Step 71017: {'lr': 0.00027639950277313533, 'samples': 13635264, 'steps': 71016, 'loss/train': 1.8145338296890259} 08/31/2021 02:01:05 - INFO - __main__ - Step 71018: {'lr': 0.0002763942256933801, 'samples': 13635456, 'steps': 71017, 'loss/train': 1.5784939527511597} 08/31/2021 02:01:05 - INFO - __main__ - Step 71019: {'lr': 0.000276388948601732, 'samples': 13635648, 'steps': 71018, 'loss/train': 1.172195553779602} 08/31/2021 02:01:05 - INFO - __main__ - Step 71020: {'lr': 0.0002763836714981935, 'samples': 13635840, 'steps': 71019, 'loss/train': 1.3490757942199707} 08/31/2021 02:01:07 - INFO - __main__ - Step 71021: {'lr': 0.0002763783943827669, 'samples': 13636032, 'steps': 71020, 'loss/train': 1.42054283618927} 08/31/2021 02:01:07 - INFO - __main__ - Step 71022: {'lr': 0.00027637311725545454, 'samples': 13636224, 'steps': 71021, 'loss/train': 1.900201439857483} 08/31/2021 02:01:08 - INFO - __main__ - Step 71023: {'lr': 0.0002763678401162589, 'samples': 13636416, 'steps': 71022, 'loss/train': 1.3807629346847534} 08/31/2021 02:01:08 - INFO - __main__ - Step 71024: {'lr': 0.00027636256296518244, 'samples': 13636608, 'steps': 71023, 'loss/train': 1.5624444484710693} 08/31/2021 02:01:09 - INFO - __main__ - Step 71025: {'lr': 0.0002763572858022273, 'samples': 13636800, 'steps': 71024, 'loss/train': 1.5336430072784424} 08/31/2021 02:01:10 - INFO - __main__ - Step 71026: {'lr': 0.00027635200862739594, 'samples': 13636992, 'steps': 71025, 'loss/train': 0.6866983771324158} 08/31/2021 02:01:11 - INFO - __main__ - Step 71027: {'lr': 0.00027634673144069085, 'samples': 13637184, 'steps': 71026, 'loss/train': 0.684396505355835} 08/31/2021 02:01:11 - INFO - __main__ - Step 71028: {'lr': 0.0002763414542421143, 'samples': 13637376, 'steps': 71027, 'loss/train': 1.1624029874801636} 08/31/2021 02:01:12 - INFO - __main__ - Step 71029: {'lr': 0.0002763361770316687, 'samples': 13637568, 'steps': 71028, 'loss/train': 1.176120400428772} 08/31/2021 02:01:12 - INFO - __main__ - Step 71030: {'lr': 0.00027633089980935645, 'samples': 13637760, 'steps': 71029, 'loss/train': 0.6529610753059387} 08/31/2021 02:01:12 - INFO - __main__ - Step 71031: {'lr': 0.00027632562257517984, 'samples': 13637952, 'steps': 71030, 'loss/train': 1.0891963243484497} 08/31/2021 02:01:14 - INFO - __main__ - Step 71032: {'lr': 0.00027632034532914135, 'samples': 13638144, 'steps': 71031, 'loss/train': 1.1984237432479858} 08/31/2021 02:01:14 - INFO - __main__ - Step 71033: {'lr': 0.0002763150680712433, 'samples': 13638336, 'steps': 71032, 'loss/train': 1.1440807580947876} 08/31/2021 02:01:15 - INFO - __main__ - Step 71034: {'lr': 0.0002763097908014881, 'samples': 13638528, 'steps': 71033, 'loss/train': 0.8027364611625671} 08/31/2021 02:01:15 - INFO - __main__ - Step 71035: {'lr': 0.00027630451351987804, 'samples': 13638720, 'steps': 71034, 'loss/train': 0.858132004737854} 08/31/2021 02:01:15 - INFO - __main__ - Step 71036: {'lr': 0.0002762992362264157, 'samples': 13638912, 'steps': 71035, 'loss/train': 1.0578614473342896} 08/31/2021 02:01:17 - INFO - __main__ - Step 71037: {'lr': 0.0002762939589211033, 'samples': 13639104, 'steps': 71036, 'loss/train': 0.9577045440673828} 08/31/2021 02:01:18 - INFO - __main__ - Step 71038: {'lr': 0.00027628868160394323, 'samples': 13639296, 'steps': 71037, 'loss/train': 1.8706949949264526} 08/31/2021 02:01:18 - INFO - __main__ - Step 71039: {'lr': 0.00027628340427493785, 'samples': 13639488, 'steps': 71038, 'loss/train': 1.0540598630905151} 08/31/2021 02:01:18 - INFO - __main__ - Step 71040: {'lr': 0.0002762781269340896, 'samples': 13639680, 'steps': 71039, 'loss/train': 1.6275895833969116} 08/31/2021 02:01:19 - INFO - __main__ - Step 71041: {'lr': 0.0002762728495814008, 'samples': 13639872, 'steps': 71040, 'loss/train': 0.8405128717422485} 08/31/2021 02:01:20 - INFO - __main__ - Step 71042: {'lr': 0.00027626757221687394, 'samples': 13640064, 'steps': 71041, 'loss/train': 0.9770914316177368} 08/31/2021 02:01:21 - INFO - __main__ - Step 71043: {'lr': 0.00027626229484051126, 'samples': 13640256, 'steps': 71042, 'loss/train': 1.223240852355957} 08/31/2021 02:01:21 - INFO - __main__ - Step 71044: {'lr': 0.0002762570174523152, 'samples': 13640448, 'steps': 71043, 'loss/train': 1.1706781387329102} 08/31/2021 02:01:21 - INFO - __main__ - Step 71045: {'lr': 0.00027625174005228815, 'samples': 13640640, 'steps': 71044, 'loss/train': 0.9624653458595276} 08/31/2021 02:01:22 - INFO - __main__ - Step 71046: {'lr': 0.0002762464626404325, 'samples': 13640832, 'steps': 71045, 'loss/train': 0.7802889347076416} 08/31/2021 02:01:23 - INFO - __main__ - Step 71047: {'lr': 0.0002762411852167505, 'samples': 13641024, 'steps': 71046, 'loss/train': 1.1574225425720215} 08/31/2021 02:01:24 - INFO - __main__ - Step 71048: {'lr': 0.0002762359077812447, 'samples': 13641216, 'steps': 71047, 'loss/train': 0.9540354609489441} 08/31/2021 02:01:24 - INFO - __main__ - Step 71049: {'lr': 0.00027623063033391736, 'samples': 13641408, 'steps': 71048, 'loss/train': 0.7003363370895386} 08/31/2021 02:01:24 - INFO - __main__ - Step 71050: {'lr': 0.00027622535287477097, 'samples': 13641600, 'steps': 71049, 'loss/train': 0.8949952125549316} 08/31/2021 02:01:25 - INFO - __main__ - Step 71051: {'lr': 0.0002762200754038078, 'samples': 13641792, 'steps': 71050, 'loss/train': 0.8763378858566284} 08/31/2021 02:01:27 - INFO - __main__ - Step 71052: {'lr': 0.0002762147979210303, 'samples': 13641984, 'steps': 71051, 'loss/train': 1.164725422859192} 08/31/2021 02:01:28 - INFO - __main__ - Step 71053: {'lr': 0.00027620952042644074, 'samples': 13642176, 'steps': 71052, 'loss/train': 1.1106468439102173} 08/31/2021 02:01:28 - INFO - __main__ - Step 71054: {'lr': 0.00027620424292004167, 'samples': 13642368, 'steps': 71053, 'loss/train': 0.11692754924297333} 08/31/2021 02:01:28 - INFO - __main__ - Step 71055: {'lr': 0.00027619896540183526, 'samples': 13642560, 'steps': 71054, 'loss/train': 0.7546526193618774} 08/31/2021 02:01:29 - INFO - __main__ - Step 71056: {'lr': 0.0002761936878718241, 'samples': 13642752, 'steps': 71055, 'loss/train': 0.7891828417778015} 08/31/2021 02:01:29 - INFO - __main__ - Step 71057: {'lr': 0.00027618841033001044, 'samples': 13642944, 'steps': 71056, 'loss/train': 0.8854241967201233} 08/31/2021 02:01:30 - INFO - __main__ - Step 71058: {'lr': 0.0002761831327763967, 'samples': 13643136, 'steps': 71057, 'loss/train': 1.0649985074996948} 08/31/2021 02:01:31 - INFO - __main__ - Step 71059: {'lr': 0.0002761778552109852, 'samples': 13643328, 'steps': 71058, 'loss/train': 0.9191047549247742} 08/31/2021 02:01:31 - INFO - __main__ - Step 71060: {'lr': 0.00027617257763377836, 'samples': 13643520, 'steps': 71059, 'loss/train': 0.05951275676488876} 08/31/2021 02:01:32 - INFO - __main__ - Step 71061: {'lr': 0.0002761673000447786, 'samples': 13643712, 'steps': 71060, 'loss/train': 1.6890524625778198} 08/31/2021 02:01:32 - INFO - __main__ - Step 71062: {'lr': 0.0002761620224439882, 'samples': 13643904, 'steps': 71061, 'loss/train': 0.5602583289146423} 08/31/2021 02:01:33 - INFO - __main__ - Step 71063: {'lr': 0.00027615674483140966, 'samples': 13644096, 'steps': 71062, 'loss/train': 1.2052258253097534} 08/31/2021 02:01:34 - INFO - __main__ - Step 71064: {'lr': 0.00027615146720704533, 'samples': 13644288, 'steps': 71063, 'loss/train': 1.3831461668014526} 08/31/2021 02:01:34 - INFO - __main__ - Step 71065: {'lr': 0.0002761461895708975, 'samples': 13644480, 'steps': 71064, 'loss/train': 1.1174005270004272} 08/31/2021 02:01:35 - INFO - __main__ - Step 71066: {'lr': 0.0002761409119229686, 'samples': 13644672, 'steps': 71065, 'loss/train': 0.8877728581428528} 08/31/2021 02:01:35 - INFO - __main__ - Step 71067: {'lr': 0.000276135634263261, 'samples': 13644864, 'steps': 71066, 'loss/train': 1.0967085361480713} 08/31/2021 02:01:36 - INFO - __main__ - Step 71068: {'lr': 0.000276130356591777, 'samples': 13645056, 'steps': 71067, 'loss/train': 1.3454636335372925} 08/31/2021 02:01:37 - INFO - __main__ - Step 71069: {'lr': 0.0002761250789085192, 'samples': 13645248, 'steps': 71068, 'loss/train': 1.4635757207870483} 08/31/2021 02:01:37 - INFO - __main__ - Step 71070: {'lr': 0.0002761198012134898, 'samples': 13645440, 'steps': 71069, 'loss/train': 2.0366506576538086} 08/31/2021 02:01:38 - INFO - __main__ - Step 71071: {'lr': 0.00027611452350669133, 'samples': 13645632, 'steps': 71070, 'loss/train': 1.5139676332473755} 08/31/2021 02:01:38 - INFO - __main__ - Step 71072: {'lr': 0.00027610924578812593, 'samples': 13645824, 'steps': 71071, 'loss/train': 1.8426631689071655} 08/31/2021 02:01:40 - INFO - __main__ - Step 71073: {'lr': 0.00027610396805779607, 'samples': 13646016, 'steps': 71072, 'loss/train': 1.2086459398269653} 08/31/2021 02:01:40 - INFO - __main__ - Step 71074: {'lr': 0.00027609869031570424, 'samples': 13646208, 'steps': 71073, 'loss/train': 0.8356479406356812} 08/31/2021 02:01:40 - INFO - __main__ - Step 71075: {'lr': 0.0002760934125618527, 'samples': 13646400, 'steps': 71074, 'loss/train': 1.3758190870285034} 08/31/2021 02:01:41 - INFO - __main__ - Step 71076: {'lr': 0.0002760881347962439, 'samples': 13646592, 'steps': 71075, 'loss/train': 1.3756502866744995} 08/31/2021 02:01:41 - INFO - __main__ - Step 71077: {'lr': 0.00027608285701888026, 'samples': 13646784, 'steps': 71076, 'loss/train': 0.8872230052947998} 08/31/2021 02:01:41 - INFO - __main__ - Step 71078: {'lr': 0.00027607757922976393, 'samples': 13646976, 'steps': 71077, 'loss/train': 1.5237109661102295} 08/31/2021 02:01:43 - INFO - __main__ - Step 71079: {'lr': 0.00027607230142889756, 'samples': 13647168, 'steps': 71078, 'loss/train': 1.4694887399673462} 08/31/2021 02:01:43 - INFO - __main__ - Step 71080: {'lr': 0.00027606702361628337, 'samples': 13647360, 'steps': 71079, 'loss/train': 0.8905508518218994} 08/31/2021 02:01:44 - INFO - __main__ - Step 71081: {'lr': 0.0002760617457919238, 'samples': 13647552, 'steps': 71080, 'loss/train': 0.10690788179636002} 08/31/2021 02:01:44 - INFO - __main__ - Step 71082: {'lr': 0.0002760564679558212, 'samples': 13647744, 'steps': 71081, 'loss/train': 1.373399019241333} 08/31/2021 02:01:44 - INFO - __main__ - Step 71083: {'lr': 0.0002760511901079779, 'samples': 13647936, 'steps': 71082, 'loss/train': 0.713557243347168} 08/31/2021 02:01:46 - INFO - __main__ - Step 71084: {'lr': 0.0002760459122483965, 'samples': 13648128, 'steps': 71083, 'loss/train': 0.9340013861656189} 08/31/2021 02:01:46 - INFO - __main__ - Step 71085: {'lr': 0.00027604063437707905, 'samples': 13648320, 'steps': 71084, 'loss/train': 1.2645206451416016} 08/31/2021 02:01:47 - INFO - __main__ - Step 71086: {'lr': 0.00027603535649402814, 'samples': 13648512, 'steps': 71085, 'loss/train': 1.1228586435317993} 08/31/2021 02:01:47 - INFO - __main__ - Step 71087: {'lr': 0.0002760300785992461, 'samples': 13648704, 'steps': 71086, 'loss/train': 1.072285532951355} 08/31/2021 02:01:47 - INFO - __main__ - Step 71088: {'lr': 0.00027602480069273535, 'samples': 13648896, 'steps': 71087, 'loss/train': 1.1428272724151611} 08/31/2021 02:01:49 - INFO - __main__ - Step 71089: {'lr': 0.00027601952277449813, 'samples': 13649088, 'steps': 71088, 'loss/train': 1.9186824560165405} 08/31/2021 02:01:49 - INFO - __main__ - Step 71090: {'lr': 0.000276014244844537, 'samples': 13649280, 'steps': 71089, 'loss/train': 1.9145903587341309} 08/31/2021 02:01:50 - INFO - __main__ - Step 71091: {'lr': 0.00027600896690285434, 'samples': 13649472, 'steps': 71090, 'loss/train': 0.8706647157669067} 08/31/2021 02:01:50 - INFO - __main__ - Step 71092: {'lr': 0.00027600368894945226, 'samples': 13649664, 'steps': 71091, 'loss/train': 1.5280574560165405} 08/31/2021 02:01:50 - INFO - __main__ - Step 71093: {'lr': 0.00027599841098433343, 'samples': 13649856, 'steps': 71092, 'loss/train': 1.3434580564498901} 08/31/2021 02:01:52 - INFO - __main__ - Step 71094: {'lr': 0.00027599313300750007, 'samples': 13650048, 'steps': 71093, 'loss/train': 1.4168684482574463} 08/31/2021 02:01:52 - INFO - __main__ - Step 71095: {'lr': 0.00027598785501895456, 'samples': 13650240, 'steps': 71094, 'loss/train': 1.5014420747756958} 08/31/2021 02:01:53 - INFO - __main__ - Step 71096: {'lr': 0.0002759825770186994, 'samples': 13650432, 'steps': 71095, 'loss/train': 1.7810722589492798} 08/31/2021 02:01:53 - INFO - __main__ - Step 71097: {'lr': 0.0002759772990067369, 'samples': 13650624, 'steps': 71096, 'loss/train': 1.9817922115325928} 08/31/2021 02:01:54 - INFO - __main__ - Step 71098: {'lr': 0.0002759720209830694, 'samples': 13650816, 'steps': 71097, 'loss/train': 0.989887535572052} 08/31/2021 02:01:54 - INFO - __main__ - Step 71099: {'lr': 0.0002759667429476993, 'samples': 13651008, 'steps': 71098, 'loss/train': 1.0433509349822998} 08/31/2021 02:01:56 - INFO - __main__ - Step 71100: {'lr': 0.00027596146490062903, 'samples': 13651200, 'steps': 71099, 'loss/train': 0.8990168571472168} 08/31/2021 02:01:56 - INFO - __main__ - Step 71101: {'lr': 0.0002759561868418609, 'samples': 13651392, 'steps': 71100, 'loss/train': 1.1493699550628662} 08/31/2021 02:01:56 - INFO - __main__ - Step 71102: {'lr': 0.0002759509087713973, 'samples': 13651584, 'steps': 71101, 'loss/train': 0.8535706996917725} 08/31/2021 02:01:57 - INFO - __main__ - Step 71103: {'lr': 0.0002759456306892406, 'samples': 13651776, 'steps': 71102, 'loss/train': 0.28402236104011536} 08/31/2021 02:01:57 - INFO - __main__ - Step 71104: {'lr': 0.0002759403525953932, 'samples': 13651968, 'steps': 71103, 'loss/train': 1.015536904335022} 08/31/2021 02:01:59 - INFO - __main__ - Step 71105: {'lr': 0.00027593507448985747, 'samples': 13652160, 'steps': 71104, 'loss/train': 0.04961179569363594} 08/31/2021 02:01:59 - INFO - __main__ - Step 71106: {'lr': 0.00027592979637263587, 'samples': 13652352, 'steps': 71105, 'loss/train': 1.0342603921890259} 08/31/2021 02:02:00 - INFO - __main__ - Step 71107: {'lr': 0.0002759245182437307, 'samples': 13652544, 'steps': 71106, 'loss/train': 1.8702043294906616} 08/31/2021 02:02:00 - INFO - __main__ - Step 71108: {'lr': 0.0002759192401031443, 'samples': 13652736, 'steps': 71107, 'loss/train': 2.215421676635742} 08/31/2021 02:02:00 - INFO - __main__ - Step 71109: {'lr': 0.0002759139619508791, 'samples': 13652928, 'steps': 71108, 'loss/train': 1.1473333835601807} 08/31/2021 02:02:02 - INFO - __main__ - Step 71110: {'lr': 0.00027590868378693745, 'samples': 13653120, 'steps': 71109, 'loss/train': 1.3715685606002808} 08/31/2021 02:02:03 - INFO - __main__ - Step 71111: {'lr': 0.0002759034056113217, 'samples': 13653312, 'steps': 71110, 'loss/train': 1.722002387046814} 08/31/2021 02:02:03 - INFO - __main__ - Step 71112: {'lr': 0.0002758981274240344, 'samples': 13653504, 'steps': 71111, 'loss/train': 1.6125293970108032} 08/31/2021 02:02:03 - INFO - __main__ - Step 71113: {'lr': 0.00027589284922507776, 'samples': 13653696, 'steps': 71112, 'loss/train': 1.32521653175354} 08/31/2021 02:02:04 - INFO - __main__ - Step 71114: {'lr': 0.00027588757101445414, 'samples': 13653888, 'steps': 71113, 'loss/train': 2.063831090927124} 08/31/2021 02:02:04 - INFO - __main__ - Step 71115: {'lr': 0.000275882292792166, 'samples': 13654080, 'steps': 71114, 'loss/train': 2.0489187240600586} 08/31/2021 02:02:06 - INFO - __main__ - Step 71116: {'lr': 0.00027587701455821575, 'samples': 13654272, 'steps': 71115, 'loss/train': 0.3018127381801605} 08/31/2021 02:02:06 - INFO - __main__ - Step 71117: {'lr': 0.00027587173631260563, 'samples': 13654464, 'steps': 71116, 'loss/train': 1.6725894212722778} 08/31/2021 02:02:06 - INFO - __main__ - Step 71118: {'lr': 0.00027586645805533817, 'samples': 13654656, 'steps': 71117, 'loss/train': 0.7490366697311401} 08/31/2021 02:02:07 - INFO - __main__ - Step 71119: {'lr': 0.0002758611797864157, 'samples': 13654848, 'steps': 71118, 'loss/train': 1.2600059509277344} 08/31/2021 02:02:07 - INFO - __main__ - Step 71120: {'lr': 0.00027585590150584055, 'samples': 13655040, 'steps': 71119, 'loss/train': 0.7361146807670593} 08/31/2021 02:02:09 - INFO - __main__ - Step 71121: {'lr': 0.00027585062321361516, 'samples': 13655232, 'steps': 71120, 'loss/train': 1.1052513122558594} 08/31/2021 02:02:09 - INFO - __main__ - Step 71122: {'lr': 0.0002758453449097418, 'samples': 13655424, 'steps': 71121, 'loss/train': 1.7522114515304565} 08/31/2021 02:02:09 - INFO - __main__ - Step 71123: {'lr': 0.000275840066594223, 'samples': 13655616, 'steps': 71122, 'loss/train': 1.0164557695388794} 08/31/2021 02:02:10 - INFO - __main__ - Step 71124: {'lr': 0.0002758347882670611, 'samples': 13655808, 'steps': 71123, 'loss/train': 0.20804286003112793} 08/31/2021 02:02:10 - INFO - __main__ - Step 71125: {'lr': 0.0002758295099282583, 'samples': 13656000, 'steps': 71124, 'loss/train': 0.5771844983100891} 08/31/2021 02:02:12 - INFO - __main__ - Step 71126: {'lr': 0.00027582423157781723, 'samples': 13656192, 'steps': 71125, 'loss/train': 0.8938525319099426} 08/31/2021 02:02:12 - INFO - __main__ - Step 71127: {'lr': 0.0002758189532157401, 'samples': 13656384, 'steps': 71126, 'loss/train': 0.7837660908699036} 08/31/2021 02:02:12 - INFO - __main__ - Step 71128: {'lr': 0.0002758136748420294, 'samples': 13656576, 'steps': 71127, 'loss/train': 1.3474308252334595} 08/31/2021 02:02:13 - INFO - __main__ - Step 71129: {'lr': 0.0002758083964566874, 'samples': 13656768, 'steps': 71128, 'loss/train': 1.2605230808258057} 08/31/2021 02:02:13 - INFO - __main__ - Step 71130: {'lr': 0.0002758031180597166, 'samples': 13656960, 'steps': 71129, 'loss/train': 0.9122046828269958} 08/31/2021 02:02:15 - INFO - __main__ - Step 71131: {'lr': 0.0002757978396511194, 'samples': 13657152, 'steps': 71130, 'loss/train': 0.8481096625328064} 08/31/2021 02:02:15 - INFO - __main__ - Step 71132: {'lr': 0.00027579256123089793, 'samples': 13657344, 'steps': 71131, 'loss/train': 1.2996028661727905} 08/31/2021 02:02:15 - INFO - __main__ - Step 71133: {'lr': 0.00027578728279905473, 'samples': 13657536, 'steps': 71132, 'loss/train': 0.9080079793930054} 08/31/2021 02:02:16 - INFO - __main__ - Step 71134: {'lr': 0.00027578200435559225, 'samples': 13657728, 'steps': 71133, 'loss/train': 0.8219980001449585} 08/31/2021 02:02:16 - INFO - __main__ - Step 71135: {'lr': 0.0002757767259005128, 'samples': 13657920, 'steps': 71134, 'loss/train': 1.1899911165237427} 08/31/2021 02:02:16 - INFO - __main__ - Step 71136: {'lr': 0.00027577144743381863, 'samples': 13658112, 'steps': 71135, 'loss/train': 0.7054104208946228} 08/31/2021 02:02:18 - INFO - __main__ - Step 71137: {'lr': 0.0002757661689555124, 'samples': 13658304, 'steps': 71136, 'loss/train': 1.4845805168151855} 08/31/2021 02:02:18 - INFO - __main__ - Step 71138: {'lr': 0.00027576089046559634, 'samples': 13658496, 'steps': 71137, 'loss/train': 1.255760669708252} 08/31/2021 02:02:19 - INFO - __main__ - Step 71139: {'lr': 0.0002757556119640727, 'samples': 13658688, 'steps': 71138, 'loss/train': 1.2813010215759277} 08/31/2021 02:02:19 - INFO - __main__ - Step 71140: {'lr': 0.000275750333450944, 'samples': 13658880, 'steps': 71139, 'loss/train': 1.1623284816741943} 08/31/2021 02:02:19 - INFO - __main__ - Step 71141: {'lr': 0.00027574505492621265, 'samples': 13659072, 'steps': 71140, 'loss/train': 1.156997561454773} 08/31/2021 02:02:21 - INFO - __main__ - Step 71142: {'lr': 0.000275739776389881, 'samples': 13659264, 'steps': 71141, 'loss/train': 1.1778669357299805} 08/31/2021 02:02:21 - INFO - __main__ - Step 71143: {'lr': 0.00027573449784195134, 'samples': 13659456, 'steps': 71142, 'loss/train': 0.6832206845283508} 08/31/2021 02:02:22 - INFO - __main__ - Step 71144: {'lr': 0.0002757292192824261, 'samples': 13659648, 'steps': 71143, 'loss/train': 1.2760614156723022} 08/31/2021 02:02:22 - INFO - __main__ - Step 71145: {'lr': 0.00027572394071130775, 'samples': 13659840, 'steps': 71144, 'loss/train': 1.1411348581314087} 08/31/2021 02:02:22 - INFO - __main__ - Step 71146: {'lr': 0.0002757186621285985, 'samples': 13660032, 'steps': 71145, 'loss/train': 1.6590617895126343} 08/31/2021 02:02:24 - INFO - __main__ - Step 71147: {'lr': 0.00027571338353430086, 'samples': 13660224, 'steps': 71146, 'loss/train': 1.205040454864502} 08/31/2021 02:02:24 - INFO - __main__ - Step 71148: {'lr': 0.0002757081049284172, 'samples': 13660416, 'steps': 71147, 'loss/train': 1.2348414659500122} 08/31/2021 02:02:25 - INFO - __main__ - Step 71149: {'lr': 0.0002757028263109498, 'samples': 13660608, 'steps': 71148, 'loss/train': 1.3387329578399658} 08/31/2021 02:02:25 - INFO - __main__ - Step 71150: {'lr': 0.0002756975476819011, 'samples': 13660800, 'steps': 71149, 'loss/train': 0.24797503650188446} 08/31/2021 02:02:25 - INFO - __main__ - Step 71151: {'lr': 0.0002756922690412736, 'samples': 13660992, 'steps': 71150, 'loss/train': 1.1569478511810303} 08/31/2021 02:02:27 - INFO - __main__ - Step 71152: {'lr': 0.00027568699038906945, 'samples': 13661184, 'steps': 71151, 'loss/train': 1.222655177116394} 08/31/2021 02:02:27 - INFO - __main__ - Step 71153: {'lr': 0.0002756817117252912, 'samples': 13661376, 'steps': 71152, 'loss/train': 1.3403377532958984} 08/31/2021 02:02:27 - INFO - __main__ - Step 71154: {'lr': 0.0002756764330499411, 'samples': 13661568, 'steps': 71153, 'loss/train': 1.4718798398971558} 08/31/2021 02:02:28 - INFO - __main__ - Step 71155: {'lr': 0.0002756711543630216, 'samples': 13661760, 'steps': 71154, 'loss/train': 1.693915605545044} 08/31/2021 02:02:28 - INFO - __main__ - Step 71156: {'lr': 0.0002756658756645351, 'samples': 13661952, 'steps': 71155, 'loss/train': 1.1381994485855103} 08/31/2021 02:02:30 - INFO - __main__ - Step 71157: {'lr': 0.00027566059695448395, 'samples': 13662144, 'steps': 71156, 'loss/train': 0.5107965469360352} 08/31/2021 02:02:30 - INFO - __main__ - Step 71158: {'lr': 0.0002756553182328706, 'samples': 13662336, 'steps': 71157, 'loss/train': 1.349172830581665} 08/31/2021 02:02:31 - INFO - __main__ - Step 71159: {'lr': 0.00027565003949969725, 'samples': 13662528, 'steps': 71158, 'loss/train': 1.0273865461349487} 08/31/2021 02:02:31 - INFO - __main__ - Step 71160: {'lr': 0.0002756447607549664, 'samples': 13662720, 'steps': 71159, 'loss/train': 0.6025280356407166} 08/31/2021 02:02:31 - INFO - __main__ - Step 71161: {'lr': 0.0002756394819986805, 'samples': 13662912, 'steps': 71160, 'loss/train': 1.0147219896316528} 08/31/2021 02:02:32 - INFO - __main__ - Step 71162: {'lr': 0.00027563420323084174, 'samples': 13663104, 'steps': 71161, 'loss/train': 1.61845064163208} 08/31/2021 02:02:34 - INFO - __main__ - Step 71163: {'lr': 0.00027562892445145266, 'samples': 13663296, 'steps': 71162, 'loss/train': 1.1650346517562866} 08/31/2021 02:02:34 - INFO - __main__ - Step 71164: {'lr': 0.00027562364566051557, 'samples': 13663488, 'steps': 71163, 'loss/train': 2.1103157997131348} 08/31/2021 02:02:34 - INFO - __main__ - Step 71165: {'lr': 0.00027561836685803293, 'samples': 13663680, 'steps': 71164, 'loss/train': 1.4147448539733887} 08/31/2021 02:02:35 - INFO - __main__ - Step 71166: {'lr': 0.000275613088044007, 'samples': 13663872, 'steps': 71165, 'loss/train': 1.2333877086639404} 08/31/2021 02:02:35 - INFO - __main__ - Step 71167: {'lr': 0.0002756078092184401, 'samples': 13664064, 'steps': 71166, 'loss/train': 1.3756237030029297} 08/31/2021 02:02:37 - INFO - __main__ - Step 71168: {'lr': 0.0002756025303813349, 'samples': 13664256, 'steps': 71167, 'loss/train': 1.3016599416732788} 08/31/2021 02:02:37 - INFO - __main__ - Step 71169: {'lr': 0.0002755972515326934, 'samples': 13664448, 'steps': 71168, 'loss/train': 1.4977514743804932} 08/31/2021 02:02:37 - INFO - __main__ - Step 71170: {'lr': 0.0002755919726725183, 'samples': 13664640, 'steps': 71169, 'loss/train': 0.9187539219856262} 08/31/2021 02:02:38 - INFO - __main__ - Step 71171: {'lr': 0.0002755866938008119, 'samples': 13664832, 'steps': 71170, 'loss/train': 1.7029471397399902} 08/31/2021 02:02:38 - INFO - __main__ - Step 71172: {'lr': 0.0002755814149175765, 'samples': 13665024, 'steps': 71171, 'loss/train': 0.9126016497612} 08/31/2021 02:02:40 - INFO - __main__ - Step 71173: {'lr': 0.00027557613602281446, 'samples': 13665216, 'steps': 71172, 'loss/train': 1.500624179840088} 08/31/2021 02:02:40 - INFO - __main__ - Step 71174: {'lr': 0.0002755708571165282, 'samples': 13665408, 'steps': 71173, 'loss/train': 1.585999846458435} 08/31/2021 02:02:40 - INFO - __main__ - Step 71175: {'lr': 0.0002755655781987201, 'samples': 13665600, 'steps': 71174, 'loss/train': 0.828350841999054} 08/31/2021 02:02:41 - INFO - __main__ - Step 71176: {'lr': 0.0002755602992693926, 'samples': 13665792, 'steps': 71175, 'loss/train': 0.9986202716827393} 08/31/2021 02:02:41 - INFO - __main__ - Step 71177: {'lr': 0.00027555502032854795, 'samples': 13665984, 'steps': 71176, 'loss/train': 1.2742012739181519} 08/31/2021 02:02:43 - INFO - __main__ - Step 71178: {'lr': 0.0002755497413761887, 'samples': 13666176, 'steps': 71177, 'loss/train': 1.479053258895874} 08/31/2021 02:02:43 - INFO - __main__ - Step 71179: {'lr': 0.00027554446241231706, 'samples': 13666368, 'steps': 71178, 'loss/train': 0.9659569263458252} 08/31/2021 02:02:43 - INFO - __main__ - Step 71180: {'lr': 0.0002755391834369355, 'samples': 13666560, 'steps': 71179, 'loss/train': 0.8962542414665222} 08/31/2021 02:02:44 - INFO - __main__ - Step 71181: {'lr': 0.0002755339044500464, 'samples': 13666752, 'steps': 71180, 'loss/train': 0.20854924619197845} 08/31/2021 02:02:44 - INFO - __main__ - Step 71182: {'lr': 0.0002755286254516521, 'samples': 13666944, 'steps': 71181, 'loss/train': 1.7864797115325928} 08/31/2021 02:02:46 - INFO - __main__ - Step 71183: {'lr': 0.0002755233464417549, 'samples': 13667136, 'steps': 71182, 'loss/train': 1.0063762664794922} 08/31/2021 02:02:46 - INFO - __main__ - Step 71184: {'lr': 0.0002755180674203574, 'samples': 13667328, 'steps': 71183, 'loss/train': 1.1761698722839355} 08/31/2021 02:02:46 - INFO - __main__ - Step 71185: {'lr': 0.00027551278838746187, 'samples': 13667520, 'steps': 71184, 'loss/train': 0.9569677114486694} 08/31/2021 02:02:47 - INFO - __main__ - Step 71186: {'lr': 0.00027550750934307057, 'samples': 13667712, 'steps': 71185, 'loss/train': 1.8797359466552734} 08/31/2021 02:02:47 - INFO - __main__ - Step 71187: {'lr': 0.00027550223028718603, 'samples': 13667904, 'steps': 71186, 'loss/train': 1.240380883216858} 08/31/2021 02:02:49 - INFO - __main__ - Step 71188: {'lr': 0.00027549695121981057, 'samples': 13668096, 'steps': 71187, 'loss/train': 1.0601247549057007} 08/31/2021 02:02:49 - INFO - __main__ - Step 71189: {'lr': 0.0002754916721409466, 'samples': 13668288, 'steps': 71188, 'loss/train': 1.1809173822402954} 08/31/2021 02:02:50 - INFO - __main__ - Step 71190: {'lr': 0.00027548639305059644, 'samples': 13668480, 'steps': 71189, 'loss/train': 1.265048861503601} 08/31/2021 02:02:50 - INFO - __main__ - Step 71191: {'lr': 0.00027548111394876254, 'samples': 13668672, 'steps': 71190, 'loss/train': 1.1013342142105103} 08/31/2021 02:02:50 - INFO - __main__ - Step 71192: {'lr': 0.00027547583483544726, 'samples': 13668864, 'steps': 71191, 'loss/train': 1.4123222827911377} 08/31/2021 02:02:52 - INFO - __main__ - Step 71193: {'lr': 0.0002754705557106529, 'samples': 13669056, 'steps': 71192, 'loss/train': 0.8850478529930115} 08/31/2021 02:02:52 - INFO - __main__ - Step 71194: {'lr': 0.0002754652765743819, 'samples': 13669248, 'steps': 71193, 'loss/train': 1.4028937816619873} 08/31/2021 02:02:53 - INFO - __main__ - Step 71195: {'lr': 0.0002754599974266367, 'samples': 13669440, 'steps': 71194, 'loss/train': 0.8767645359039307} 08/31/2021 02:02:53 - INFO - __main__ - Step 71196: {'lr': 0.0002754547182674195, 'samples': 13669632, 'steps': 71195, 'loss/train': 1.2083566188812256} 08/31/2021 02:02:54 - INFO - __main__ - Step 71197: {'lr': 0.0002754494390967329, 'samples': 13669824, 'steps': 71196, 'loss/train': 1.2994389533996582} 08/31/2021 02:02:54 - INFO - __main__ - Step 71198: {'lr': 0.0002754441599145792, 'samples': 13670016, 'steps': 71197, 'loss/train': 1.1376210451126099} 08/31/2021 02:02:55 - INFO - __main__ - Step 71199: {'lr': 0.00027543888072096076, 'samples': 13670208, 'steps': 71198, 'loss/train': 1.139302134513855} 08/31/2021 02:02:56 - INFO - __main__ - Step 71200: {'lr': 0.00027543360151587986, 'samples': 13670400, 'steps': 71199, 'loss/train': 0.836692750453949} 08/31/2021 02:02:56 - INFO - __main__ - Step 71201: {'lr': 0.000275428322299339, 'samples': 13670592, 'steps': 71200, 'loss/train': 1.2414872646331787} 08/31/2021 02:02:56 - INFO - __main__ - Step 71202: {'lr': 0.0002754230430713405, 'samples': 13670784, 'steps': 71201, 'loss/train': 1.5125421285629272} 08/31/2021 02:02:57 - INFO - __main__ - Step 71203: {'lr': 0.00027541776383188687, 'samples': 13670976, 'steps': 71202, 'loss/train': 0.9852046370506287} 08/31/2021 02:02:58 - INFO - __main__ - Step 71204: {'lr': 0.00027541248458098027, 'samples': 13671168, 'steps': 71203, 'loss/train': 1.2081490755081177} 08/31/2021 02:02:59 - INFO - __main__ - Step 71205: {'lr': 0.00027540720531862335, 'samples': 13671360, 'steps': 71204, 'loss/train': 1.2805417776107788} 08/31/2021 02:02:59 - INFO - __main__ - Step 71206: {'lr': 0.00027540192604481824, 'samples': 13671552, 'steps': 71205, 'loss/train': 0.555843710899353} 08/31/2021 02:03:00 - INFO - __main__ - Step 71207: {'lr': 0.00027539664675956736, 'samples': 13671744, 'steps': 71206, 'loss/train': 1.1892603635787964} 08/31/2021 02:03:00 - INFO - __main__ - Step 71208: {'lr': 0.0002753913674628732, 'samples': 13671936, 'steps': 71207, 'loss/train': 0.3917340040206909} 08/31/2021 02:03:01 - INFO - __main__ - Step 71209: {'lr': 0.0002753860881547381, 'samples': 13672128, 'steps': 71208, 'loss/train': 0.4727100729942322} 08/31/2021 02:03:02 - INFO - __main__ - Step 71210: {'lr': 0.0002753808088351644, 'samples': 13672320, 'steps': 71209, 'loss/train': 1.0108399391174316} 08/31/2021 02:03:02 - INFO - __main__ - Step 71211: {'lr': 0.0002753755295041545, 'samples': 13672512, 'steps': 71210, 'loss/train': 0.5571727156639099} 08/31/2021 02:03:02 - INFO - __main__ - Step 71212: {'lr': 0.0002753702501617108, 'samples': 13672704, 'steps': 71211, 'loss/train': 1.3246185779571533} 08/31/2021 02:03:03 - INFO - __main__ - Step 71213: {'lr': 0.0002753649708078357, 'samples': 13672896, 'steps': 71212, 'loss/train': 1.4469082355499268} 08/31/2021 02:03:04 - INFO - __main__ - Step 71214: {'lr': 0.0002753596914425314, 'samples': 13673088, 'steps': 71213, 'loss/train': 0.6962994337081909} 08/31/2021 02:03:05 - INFO - __main__ - Step 71215: {'lr': 0.0002753544120658005, 'samples': 13673280, 'steps': 71214, 'loss/train': 1.219153881072998} 08/31/2021 02:03:05 - INFO - __main__ - Step 71216: {'lr': 0.0002753491326776453, 'samples': 13673472, 'steps': 71215, 'loss/train': 0.030435891821980476} 08/31/2021 02:03:06 - INFO - __main__ - Step 71217: {'lr': 0.0002753438532780681, 'samples': 13673664, 'steps': 71216, 'loss/train': 1.642555832862854} 08/31/2021 02:03:06 - INFO - __main__ - Step 71218: {'lr': 0.0002753385738670714, 'samples': 13673856, 'steps': 71217, 'loss/train': 1.1024565696716309} 08/31/2021 02:03:08 - INFO - __main__ - Step 71219: {'lr': 0.0002753332944446576, 'samples': 13674048, 'steps': 71218, 'loss/train': 0.9650189280509949} 08/31/2021 02:03:08 - INFO - __main__ - Step 71220: {'lr': 0.00027532801501082893, 'samples': 13674240, 'steps': 71219, 'loss/train': 0.9492564797401428} 08/31/2021 02:03:09 - INFO - __main__ - Step 71221: {'lr': 0.00027532273556558787, 'samples': 13674432, 'steps': 71220, 'loss/train': 1.4985029697418213} 08/31/2021 02:03:09 - INFO - __main__ - Step 71222: {'lr': 0.0002753174561089367, 'samples': 13674624, 'steps': 71221, 'loss/train': 1.6663846969604492} 08/31/2021 02:03:09 - INFO - __main__ - Step 71223: {'lr': 0.000275312176640878, 'samples': 13674816, 'steps': 71222, 'loss/train': 0.41934120655059814} 08/31/2021 02:03:11 - INFO - __main__ - Step 71224: {'lr': 0.00027530689716141396, 'samples': 13675008, 'steps': 71223, 'loss/train': 1.1156296730041504} 08/31/2021 02:03:11 - INFO - __main__ - Step 71225: {'lr': 0.0002753016176705471, 'samples': 13675200, 'steps': 71224, 'loss/train': 1.575100064277649} 08/31/2021 02:03:12 - INFO - __main__ - Step 71226: {'lr': 0.0002752963381682796, 'samples': 13675392, 'steps': 71225, 'loss/train': 1.450239658355713} 08/31/2021 02:03:12 - INFO - __main__ - Step 71227: {'lr': 0.000275291058654614, 'samples': 13675584, 'steps': 71226, 'loss/train': 0.5467860102653503} 08/31/2021 02:03:12 - INFO - __main__ - Step 71228: {'lr': 0.0002752857791295526, 'samples': 13675776, 'steps': 71227, 'loss/train': 1.058375597000122} 08/31/2021 02:03:14 - INFO - __main__ - Step 71229: {'lr': 0.0002752804995930979, 'samples': 13675968, 'steps': 71228, 'loss/train': 0.7713623642921448} 08/31/2021 02:03:15 - INFO - __main__ - Step 71230: {'lr': 0.0002752752200452521, 'samples': 13676160, 'steps': 71229, 'loss/train': 1.290664792060852} 08/31/2021 02:03:15 - INFO - __main__ - Step 71231: {'lr': 0.0002752699404860178, 'samples': 13676352, 'steps': 71230, 'loss/train': 1.2366315126419067} 08/31/2021 02:03:15 - INFO - __main__ - Step 71232: {'lr': 0.0002752646609153972, 'samples': 13676544, 'steps': 71231, 'loss/train': 0.78892982006073} 08/31/2021 02:03:16 - INFO - __main__ - Step 71233: {'lr': 0.00027525938133339273, 'samples': 13676736, 'steps': 71232, 'loss/train': 1.2695811986923218} 08/31/2021 02:03:16 - INFO - __main__ - Step 71234: {'lr': 0.0002752541017400068, 'samples': 13676928, 'steps': 71233, 'loss/train': 0.9350317716598511} 08/31/2021 02:03:17 - INFO - __main__ - Step 71235: {'lr': 0.0002752488221352417, 'samples': 13677120, 'steps': 71234, 'loss/train': 0.022421035915613174} 08/31/2021 02:03:18 - INFO - __main__ - Step 71236: {'lr': 0.0002752435425190999, 'samples': 13677312, 'steps': 71235, 'loss/train': 0.4152746796607971} 08/31/2021 02:03:19 - INFO - __main__ - Step 71237: {'lr': 0.00027523826289158374, 'samples': 13677504, 'steps': 71236, 'loss/train': 1.2999714612960815} 08/31/2021 02:03:19 - INFO - __main__ - Step 71238: {'lr': 0.0002752329832526956, 'samples': 13677696, 'steps': 71237, 'loss/train': 1.190003514289856} 08/31/2021 02:03:19 - INFO - __main__ - Step 71239: {'lr': 0.00027522770360243794, 'samples': 13677888, 'steps': 71238, 'loss/train': 0.23723502457141876} 08/31/2021 02:03:20 - INFO - __main__ - Step 71240: {'lr': 0.000275222423940813, 'samples': 13678080, 'steps': 71239, 'loss/train': 0.03218080475926399} 08/31/2021 02:03:21 - INFO - __main__ - Step 71241: {'lr': 0.0002752171442678232, 'samples': 13678272, 'steps': 71240, 'loss/train': 1.1842730045318604} 08/31/2021 02:03:22 - INFO - __main__ - Step 71242: {'lr': 0.00027521186458347104, 'samples': 13678464, 'steps': 71241, 'loss/train': 1.628151774406433} 08/31/2021 02:03:22 - INFO - __main__ - Step 71243: {'lr': 0.00027520658488775873, 'samples': 13678656, 'steps': 71242, 'loss/train': 1.052701711654663} 08/31/2021 02:03:23 - INFO - __main__ - Step 71244: {'lr': 0.00027520130518068875, 'samples': 13678848, 'steps': 71243, 'loss/train': 0.019209707155823708} 08/31/2021 02:03:23 - INFO - __main__ - Step 71245: {'lr': 0.0002751960254622634, 'samples': 13679040, 'steps': 71244, 'loss/train': 1.396060824394226} 08/31/2021 02:03:24 - INFO - __main__ - Step 71246: {'lr': 0.0002751907457324851, 'samples': 13679232, 'steps': 71245, 'loss/train': 0.9163379073143005} 08/31/2021 02:03:25 - INFO - __main__ - Step 71247: {'lr': 0.0002751854659913563, 'samples': 13679424, 'steps': 71246, 'loss/train': 1.2079797983169556} 08/31/2021 02:03:25 - INFO - __main__ - Step 71248: {'lr': 0.0002751801862388794, 'samples': 13679616, 'steps': 71247, 'loss/train': 0.9380229115486145} 08/31/2021 02:03:26 - INFO - __main__ - Step 71249: {'lr': 0.0002751749064750566, 'samples': 13679808, 'steps': 71248, 'loss/train': 0.5931749939918518} 08/31/2021 02:03:26 - INFO - __main__ - Step 71250: {'lr': 0.0002751696266998903, 'samples': 13680000, 'steps': 71249, 'loss/train': 1.3293756246566772} 08/31/2021 02:03:27 - INFO - __main__ - Step 71251: {'lr': 0.00027516434691338305, 'samples': 13680192, 'steps': 71250, 'loss/train': 1.4109370708465576} 08/31/2021 02:03:28 - INFO - __main__ - Step 71252: {'lr': 0.0002751590671155371, 'samples': 13680384, 'steps': 71251, 'loss/train': 1.3839190006256104} 08/31/2021 02:03:28 - INFO - __main__ - Step 71253: {'lr': 0.0002751537873063549, 'samples': 13680576, 'steps': 71252, 'loss/train': 1.5417935848236084} 08/31/2021 02:03:29 - INFO - __main__ - Step 71254: {'lr': 0.0002751485074858388, 'samples': 13680768, 'steps': 71253, 'loss/train': 1.098914623260498} 08/31/2021 02:03:29 - INFO - __main__ - Step 71255: {'lr': 0.00027514322765399114, 'samples': 13680960, 'steps': 71254, 'loss/train': 0.6363546252250671} 08/31/2021 02:03:30 - INFO - __main__ - Step 71256: {'lr': 0.0002751379478108143, 'samples': 13681152, 'steps': 71255, 'loss/train': 0.8163884282112122} 08/31/2021 02:03:31 - INFO - __main__ - Step 71257: {'lr': 0.0002751326679563107, 'samples': 13681344, 'steps': 71256, 'loss/train': 1.289880394935608} 08/31/2021 02:03:31 - INFO - __main__ - Step 71258: {'lr': 0.0002751273880904827, 'samples': 13681536, 'steps': 71257, 'loss/train': 1.4745597839355469} 08/31/2021 02:03:32 - INFO - __main__ - Step 71259: {'lr': 0.00027512210821333276, 'samples': 13681728, 'steps': 71258, 'loss/train': 0.7592875957489014} 08/31/2021 02:03:32 - INFO - __main__ - Step 71260: {'lr': 0.00027511682832486313, 'samples': 13681920, 'steps': 71259, 'loss/train': 1.260082721710205} 08/31/2021 02:03:33 - INFO - __main__ - Step 71261: {'lr': 0.0002751115484250762, 'samples': 13682112, 'steps': 71260, 'loss/train': 1.7346831560134888} 08/31/2021 02:03:34 - INFO - __main__ - Step 71262: {'lr': 0.00027510626851397446, 'samples': 13682304, 'steps': 71261, 'loss/train': 0.8756316304206848} 08/31/2021 02:03:34 - INFO - __main__ - Step 71263: {'lr': 0.00027510098859156025, 'samples': 13682496, 'steps': 71262, 'loss/train': 1.286426305770874} 08/31/2021 02:03:35 - INFO - __main__ - Step 71264: {'lr': 0.00027509570865783586, 'samples': 13682688, 'steps': 71263, 'loss/train': 1.0008821487426758} 08/31/2021 02:03:35 - INFO - __main__ - Step 71265: {'lr': 0.0002750904287128037, 'samples': 13682880, 'steps': 71264, 'loss/train': 1.5622787475585938} 08/31/2021 02:03:36 - INFO - __main__ - Step 71266: {'lr': 0.0002750851487564663, 'samples': 13683072, 'steps': 71265, 'loss/train': 0.7103875875473022} 08/31/2021 02:03:37 - INFO - __main__ - Step 71267: {'lr': 0.00027507986878882583, 'samples': 13683264, 'steps': 71266, 'loss/train': 1.2881453037261963} 08/31/2021 02:03:37 - INFO - __main__ - Step 71268: {'lr': 0.0002750745888098848, 'samples': 13683456, 'steps': 71267, 'loss/train': 1.7854961156845093} 08/31/2021 02:03:38 - INFO - __main__ - Step 71269: {'lr': 0.0002750693088196455, 'samples': 13683648, 'steps': 71268, 'loss/train': 0.7827132344245911} 08/31/2021 02:03:38 - INFO - __main__ - Step 71270: {'lr': 0.0002750640288181104, 'samples': 13683840, 'steps': 71269, 'loss/train': 1.7772570848464966} 08/31/2021 02:03:38 - INFO - __main__ - Step 71271: {'lr': 0.0002750587488052818, 'samples': 13684032, 'steps': 71270, 'loss/train': 1.343318223953247} 08/31/2021 02:03:41 - INFO - __main__ - Step 71272: {'lr': 0.00027505346878116215, 'samples': 13684224, 'steps': 71271, 'loss/train': 0.23248028755187988} 08/31/2021 02:03:41 - INFO - __main__ - Step 71273: {'lr': 0.0002750481887457538, 'samples': 13684416, 'steps': 71272, 'loss/train': 1.4982012510299683} 08/31/2021 02:03:42 - INFO - __main__ - Step 71274: {'lr': 0.00027504290869905906, 'samples': 13684608, 'steps': 71273, 'loss/train': 1.3068078756332397} 08/31/2021 02:03:42 - INFO - __main__ - Step 71275: {'lr': 0.0002750376286410804, 'samples': 13684800, 'steps': 71274, 'loss/train': 0.7909181118011475} 08/31/2021 02:03:42 - INFO - __main__ - Step 71276: {'lr': 0.0002750323485718202, 'samples': 13684992, 'steps': 71275, 'loss/train': 1.5113613605499268} 08/31/2021 02:03:43 - INFO - __main__ - Step 71277: {'lr': 0.0002750270684912808, 'samples': 13685184, 'steps': 71276, 'loss/train': 0.06081250309944153} 08/31/2021 02:03:44 - INFO - __main__ - Step 71278: {'lr': 0.0002750217883994645, 'samples': 13685376, 'steps': 71277, 'loss/train': 1.2258638143539429} 08/31/2021 02:03:45 - INFO - __main__ - Step 71279: {'lr': 0.0002750165082963739, 'samples': 13685568, 'steps': 71278, 'loss/train': 1.6265960931777954} 08/31/2021 02:03:45 - INFO - __main__ - Step 71280: {'lr': 0.0002750112281820112, 'samples': 13685760, 'steps': 71279, 'loss/train': 1.6372826099395752} 08/31/2021 02:03:45 - INFO - __main__ - Step 71281: {'lr': 0.0002750059480563788, 'samples': 13685952, 'steps': 71280, 'loss/train': 1.5316331386566162} 08/31/2021 02:03:46 - INFO - __main__ - Step 71282: {'lr': 0.00027500066791947913, 'samples': 13686144, 'steps': 71281, 'loss/train': 1.487363576889038} 08/31/2021 02:03:47 - INFO - __main__ - Step 71283: {'lr': 0.00027499538777131456, 'samples': 13686336, 'steps': 71282, 'loss/train': 1.0895085334777832} 08/31/2021 02:03:48 - INFO - __main__ - Step 71284: {'lr': 0.0002749901076118874, 'samples': 13686528, 'steps': 71283, 'loss/train': 1.0630162954330444} 08/31/2021 02:03:48 - INFO - __main__ - Step 71285: {'lr': 0.0002749848274412001, 'samples': 13686720, 'steps': 71284, 'loss/train': 0.5644595623016357} 08/31/2021 02:03:49 - INFO - __main__ - Step 71286: {'lr': 0.0002749795472592551, 'samples': 13686912, 'steps': 71285, 'loss/train': 1.1850799322128296} 08/31/2021 02:03:49 - INFO - __main__ - Step 71287: {'lr': 0.00027497426706605464, 'samples': 13687104, 'steps': 71286, 'loss/train': 1.3488434553146362} 08/31/2021 02:03:50 - INFO - __main__ - Step 71288: {'lr': 0.0002749689868616012, 'samples': 13687296, 'steps': 71287, 'loss/train': 1.1341371536254883} 08/31/2021 02:03:51 - INFO - __main__ - Step 71289: {'lr': 0.00027496370664589705, 'samples': 13687488, 'steps': 71288, 'loss/train': 1.2035090923309326} 08/31/2021 02:03:51 - INFO - __main__ - Step 71290: {'lr': 0.00027495842641894465, 'samples': 13687680, 'steps': 71289, 'loss/train': 1.3878123760223389} 08/31/2021 02:03:52 - INFO - __main__ - Step 71291: {'lr': 0.0002749531461807464, 'samples': 13687872, 'steps': 71290, 'loss/train': 1.2726813554763794} 08/31/2021 02:03:52 - INFO - __main__ - Step 71292: {'lr': 0.0002749478659313047, 'samples': 13688064, 'steps': 71291, 'loss/train': 1.2981725931167603} 08/31/2021 02:03:53 - INFO - __main__ - Step 71293: {'lr': 0.0002749425856706217, 'samples': 13688256, 'steps': 71292, 'loss/train': 0.9959590435028076} 08/31/2021 02:03:54 - INFO - __main__ - Step 71294: {'lr': 0.00027493730539870014, 'samples': 13688448, 'steps': 71293, 'loss/train': 1.343357801437378} 08/31/2021 02:03:54 - INFO - __main__ - Step 71295: {'lr': 0.0002749320251155421, 'samples': 13688640, 'steps': 71294, 'loss/train': 1.1441959142684937} 08/31/2021 02:03:55 - INFO - __main__ - Step 71296: {'lr': 0.00027492674482115017, 'samples': 13688832, 'steps': 71295, 'loss/train': 1.3863511085510254} 08/31/2021 02:03:55 - INFO - __main__ - Step 71297: {'lr': 0.00027492146451552654, 'samples': 13689024, 'steps': 71296, 'loss/train': 1.2397500276565552} 08/31/2021 02:03:57 - INFO - __main__ - Step 71298: {'lr': 0.0002749161841986737, 'samples': 13689216, 'steps': 71297, 'loss/train': 1.2951945066452026} 08/31/2021 02:03:57 - INFO - __main__ - Step 71299: {'lr': 0.0002749109038705941, 'samples': 13689408, 'steps': 71298, 'loss/train': 1.2835824489593506} 08/31/2021 02:03:57 - INFO - __main__ - Step 71300: {'lr': 0.00027490562353128995, 'samples': 13689600, 'steps': 71299, 'loss/train': 1.5014173984527588} 08/31/2021 02:03:58 - INFO - __main__ - Step 71301: {'lr': 0.0002749003431807637, 'samples': 13689792, 'steps': 71300, 'loss/train': 1.5398632287979126} 08/31/2021 02:03:58 - INFO - __main__ - Step 71302: {'lr': 0.00027489506281901777, 'samples': 13689984, 'steps': 71301, 'loss/train': 0.6989170908927917} 08/31/2021 02:03:58 - INFO - __main__ - Step 71303: {'lr': 0.0002748897824460545, 'samples': 13690176, 'steps': 71302, 'loss/train': 1.211078405380249} 08/31/2021 02:04:00 - INFO - __main__ - Step 71304: {'lr': 0.0002748845020618763, 'samples': 13690368, 'steps': 71303, 'loss/train': 0.7465998530387878} 08/31/2021 02:04:00 - INFO - __main__ - Step 71305: {'lr': 0.00027487922166648547, 'samples': 13690560, 'steps': 71304, 'loss/train': 1.3191297054290771} 08/31/2021 02:04:01 - INFO - __main__ - Step 71306: {'lr': 0.00027487394125988456, 'samples': 13690752, 'steps': 71305, 'loss/train': 1.4420474767684937} 08/31/2021 02:04:01 - INFO - __main__ - Step 71307: {'lr': 0.0002748686608420757, 'samples': 13690944, 'steps': 71306, 'loss/train': 1.2698527574539185} 08/31/2021 02:04:01 - INFO - __main__ - Step 71308: {'lr': 0.00027486338041306154, 'samples': 13691136, 'steps': 71307, 'loss/train': 1.7229130268096924} 08/31/2021 02:04:03 - INFO - __main__ - Step 71309: {'lr': 0.00027485809997284424, 'samples': 13691328, 'steps': 71308, 'loss/train': 1.2094610929489136} 08/31/2021 02:04:04 - INFO - __main__ - Step 71310: {'lr': 0.00027485281952142627, 'samples': 13691520, 'steps': 71309, 'loss/train': 0.8554244637489319} 08/31/2021 02:04:04 - INFO - __main__ - Step 71311: {'lr': 0.00027484753905881, 'samples': 13691712, 'steps': 71310, 'loss/train': 1.3887568712234497} 08/31/2021 02:04:04 - INFO - __main__ - Step 71312: {'lr': 0.0002748422585849978, 'samples': 13691904, 'steps': 71311, 'loss/train': 1.4032130241394043} 08/31/2021 02:04:05 - INFO - __main__ - Step 71313: {'lr': 0.00027483697809999215, 'samples': 13692096, 'steps': 71312, 'loss/train': 1.454835295677185} 08/31/2021 02:04:06 - INFO - __main__ - Step 71314: {'lr': 0.0002748316976037952, 'samples': 13692288, 'steps': 71313, 'loss/train': 1.3676944971084595} 08/31/2021 02:04:07 - INFO - __main__ - Step 71315: {'lr': 0.0002748264170964096, 'samples': 13692480, 'steps': 71314, 'loss/train': 0.5675011873245239} 08/31/2021 02:04:07 - INFO - __main__ - Step 71316: {'lr': 0.00027482113657783754, 'samples': 13692672, 'steps': 71315, 'loss/train': 1.2804923057556152} 08/31/2021 02:04:07 - INFO - __main__ - Step 71317: {'lr': 0.00027481585604808146, 'samples': 13692864, 'steps': 71316, 'loss/train': 1.7428674697875977} 08/31/2021 02:04:08 - INFO - __main__ - Step 71318: {'lr': 0.00027481057550714374, 'samples': 13693056, 'steps': 71317, 'loss/train': 0.8196892142295837} 08/31/2021 02:04:09 - INFO - __main__ - Step 71319: {'lr': 0.00027480529495502675, 'samples': 13693248, 'steps': 71318, 'loss/train': 0.08410114794969559} 08/31/2021 02:04:10 - INFO - __main__ - Step 71320: {'lr': 0.00027480001439173293, 'samples': 13693440, 'steps': 71319, 'loss/train': 1.3122555017471313} 08/31/2021 02:04:10 - INFO - __main__ - Step 71321: {'lr': 0.0002747947338172646, 'samples': 13693632, 'steps': 71320, 'loss/train': 0.9613444805145264} 08/31/2021 02:04:10 - INFO - __main__ - Step 71322: {'lr': 0.000274789453231624, 'samples': 13693824, 'steps': 71321, 'loss/train': 1.8284142017364502} 08/31/2021 02:04:11 - INFO - __main__ - Step 71323: {'lr': 0.0002747841726348138, 'samples': 13694016, 'steps': 71322, 'loss/train': 0.8633977770805359} 08/31/2021 02:04:13 - INFO - __main__ - Step 71324: {'lr': 0.0002747788920268362, 'samples': 13694208, 'steps': 71323, 'loss/train': 1.227269172668457} 08/31/2021 02:04:13 - INFO - __main__ - Step 71325: {'lr': 0.0002747736114076936, 'samples': 13694400, 'steps': 71324, 'loss/train': 0.7682477235794067} 08/31/2021 02:04:13 - INFO - __main__ - Step 71326: {'lr': 0.00027476833077738844, 'samples': 13694592, 'steps': 71325, 'loss/train': 1.4922696352005005} 08/31/2021 02:04:14 - INFO - __main__ - Step 71327: {'lr': 0.000274763050135923, 'samples': 13694784, 'steps': 71326, 'loss/train': 0.8266589641571045} 08/31/2021 02:04:14 - INFO - __main__ - Step 71328: {'lr': 0.0002747577694832997, 'samples': 13694976, 'steps': 71327, 'loss/train': 1.5382457971572876} 08/31/2021 02:04:15 - INFO - __main__ - Step 71329: {'lr': 0.00027475248881952095, 'samples': 13695168, 'steps': 71328, 'loss/train': 1.3325828313827515} 08/31/2021 02:04:16 - INFO - __main__ - Step 71330: {'lr': 0.0002747472081445891, 'samples': 13695360, 'steps': 71329, 'loss/train': 1.408787488937378} 08/31/2021 02:04:17 - INFO - __main__ - Step 71331: {'lr': 0.0002747419274585066, 'samples': 13695552, 'steps': 71330, 'loss/train': 1.5989052057266235} 08/31/2021 02:04:17 - INFO - __main__ - Step 71332: {'lr': 0.00027473664676127575, 'samples': 13695744, 'steps': 71331, 'loss/train': 1.8515229225158691} 08/31/2021 02:04:17 - INFO - __main__ - Step 71333: {'lr': 0.00027473136605289894, 'samples': 13695936, 'steps': 71332, 'loss/train': 0.9980238080024719} 08/31/2021 02:04:18 - INFO - __main__ - Step 71334: {'lr': 0.0002747260853333786, 'samples': 13696128, 'steps': 71333, 'loss/train': 1.6187174320220947} 08/31/2021 02:04:19 - INFO - __main__ - Step 71335: {'lr': 0.0002747208046027169, 'samples': 13696320, 'steps': 71334, 'loss/train': 1.0102418661117554} 08/31/2021 02:04:20 - INFO - __main__ - Step 71336: {'lr': 0.00027471552386091653, 'samples': 13696512, 'steps': 71335, 'loss/train': 1.2125322818756104} 08/31/2021 02:04:20 - INFO - __main__ - Step 71337: {'lr': 0.0002747102431079797, 'samples': 13696704, 'steps': 71336, 'loss/train': 0.8294684290885925} 08/31/2021 02:04:21 - INFO - __main__ - Step 71338: {'lr': 0.0002747049623439088, 'samples': 13696896, 'steps': 71337, 'loss/train': 1.2642401456832886} 08/31/2021 02:04:21 - INFO - __main__ - Step 71339: {'lr': 0.00027469968156870625, 'samples': 13697088, 'steps': 71338, 'loss/train': 1.2497882843017578} 08/31/2021 02:04:23 - INFO - __main__ - Step 71340: {'lr': 0.0002746944007823744, 'samples': 13697280, 'steps': 71339, 'loss/train': 1.3063544034957886} 08/31/2021 02:04:23 - INFO - __main__ - Step 71341: {'lr': 0.0002746891199849156, 'samples': 13697472, 'steps': 71340, 'loss/train': 2.7532737255096436} 08/31/2021 02:04:23 - INFO - __main__ - Step 71342: {'lr': 0.00027468383917633233, 'samples': 13697664, 'steps': 71341, 'loss/train': 2.697873115539551} 08/31/2021 02:04:24 - INFO - __main__ - Step 71343: {'lr': 0.00027467855835662687, 'samples': 13697856, 'steps': 71342, 'loss/train': 1.2762736082077026} 08/31/2021 02:04:24 - INFO - __main__ - Step 71344: {'lr': 0.00027467327752580157, 'samples': 13698048, 'steps': 71343, 'loss/train': 1.328735113143921} 08/31/2021 02:04:25 - INFO - __main__ - Step 71345: {'lr': 0.00027466799668385896, 'samples': 13698240, 'steps': 71344, 'loss/train': 1.478084921836853} 08/31/2021 02:04:26 - INFO - __main__ - Step 71346: {'lr': 0.0002746627158308013, 'samples': 13698432, 'steps': 71345, 'loss/train': 0.752569317817688} 08/31/2021 02:04:26 - INFO - __main__ - Step 71347: {'lr': 0.00027465743496663106, 'samples': 13698624, 'steps': 71346, 'loss/train': 0.8946017026901245} 08/31/2021 02:04:27 - INFO - __main__ - Step 71348: {'lr': 0.0002746521540913505, 'samples': 13698816, 'steps': 71347, 'loss/train': 1.555199384689331} 08/31/2021 02:04:27 - INFO - __main__ - Step 71349: {'lr': 0.00027464687320496203, 'samples': 13699008, 'steps': 71348, 'loss/train': 0.2255793958902359} 08/31/2021 02:04:27 - INFO - __main__ - Step 71350: {'lr': 0.00027464159230746805, 'samples': 13699200, 'steps': 71349, 'loss/train': 1.3136703968048096} 08/31/2021 02:04:29 - INFO - __main__ - Step 71351: {'lr': 0.00027463631139887097, 'samples': 13699392, 'steps': 71350, 'loss/train': 1.6980414390563965} 08/31/2021 02:04:30 - INFO - __main__ - Step 71352: {'lr': 0.0002746310304791732, 'samples': 13699584, 'steps': 71351, 'loss/train': 1.7192065715789795} 08/31/2021 02:04:30 - INFO - __main__ - Step 71353: {'lr': 0.00027462574954837705, 'samples': 13699776, 'steps': 71352, 'loss/train': 1.1625348329544067} 08/31/2021 02:04:30 - INFO - __main__ - Step 71354: {'lr': 0.0002746204686064849, 'samples': 13699968, 'steps': 71353, 'loss/train': 0.03365860879421234} 08/31/2021 02:04:31 - INFO - __main__ - Step 71355: {'lr': 0.00027461518765349916, 'samples': 13700160, 'steps': 71354, 'loss/train': 1.1643826961517334} 08/31/2021 02:04:31 - INFO - __main__ - Step 71356: {'lr': 0.00027460990668942215, 'samples': 13700352, 'steps': 71355, 'loss/train': 0.07590105384588242} 08/31/2021 02:04:33 - INFO - __main__ - Step 71357: {'lr': 0.0002746046257142563, 'samples': 13700544, 'steps': 71356, 'loss/train': 0.06289833039045334} 08/31/2021 02:04:33 - INFO - __main__ - Step 71358: {'lr': 0.000274599344728004, 'samples': 13700736, 'steps': 71357, 'loss/train': 1.2327234745025635} 08/31/2021 02:04:34 - INFO - __main__ - Step 71359: {'lr': 0.00027459406373066763, 'samples': 13700928, 'steps': 71358, 'loss/train': 1.2503716945648193} 08/31/2021 02:04:34 - INFO - __main__ - Step 71360: {'lr': 0.0002745887827222496, 'samples': 13701120, 'steps': 71359, 'loss/train': 0.01885250024497509} 08/31/2021 02:04:34 - INFO - __main__ - Step 71361: {'lr': 0.0002745835017027522, 'samples': 13701312, 'steps': 71360, 'loss/train': 2.4829416275024414} 08/31/2021 02:04:35 - INFO - __main__ - Step 71362: {'lr': 0.00027457822067217784, 'samples': 13701504, 'steps': 71361, 'loss/train': 2.110239267349243} 08/31/2021 02:04:36 - INFO - __main__ - Step 71363: {'lr': 0.00027457293963052893, 'samples': 13701696, 'steps': 71362, 'loss/train': 1.2786006927490234} 08/31/2021 02:04:37 - INFO - __main__ - Step 71364: {'lr': 0.0002745676585778078, 'samples': 13701888, 'steps': 71363, 'loss/train': 1.2389260530471802} 08/31/2021 02:04:37 - INFO - __main__ - Step 71365: {'lr': 0.0002745623775140169, 'samples': 13702080, 'steps': 71364, 'loss/train': 1.1993248462677002} 08/31/2021 02:04:37 - INFO - __main__ - Step 71366: {'lr': 0.0002745570964391586, 'samples': 13702272, 'steps': 71365, 'loss/train': 1.3288058042526245} 08/31/2021 02:04:38 - INFO - __main__ - Step 71367: {'lr': 0.0002745518153532352, 'samples': 13702464, 'steps': 71366, 'loss/train': 0.7740391492843628} 08/31/2021 02:04:39 - INFO - __main__ - Step 71368: {'lr': 0.00027454653425624913, 'samples': 13702656, 'steps': 71367, 'loss/train': 0.45063403248786926} 08/31/2021 02:04:40 - INFO - __main__ - Step 71369: {'lr': 0.00027454125314820276, 'samples': 13702848, 'steps': 71368, 'loss/train': 1.8936848640441895} 08/31/2021 02:04:40 - INFO - __main__ - Step 71370: {'lr': 0.0002745359720290985, 'samples': 13703040, 'steps': 71369, 'loss/train': 1.2132736444473267} 08/31/2021 02:04:40 - INFO - __main__ - Step 71371: {'lr': 0.0002745306908989388, 'samples': 13703232, 'steps': 71370, 'loss/train': 1.2388719320297241} 08/31/2021 02:04:41 - INFO - __main__ - Step 71372: {'lr': 0.0002745254097577258, 'samples': 13703424, 'steps': 71371, 'loss/train': 0.1873541623353958} 08/31/2021 02:04:42 - INFO - __main__ - Step 71373: {'lr': 0.0002745201286054621, 'samples': 13703616, 'steps': 71372, 'loss/train': 0.7341599464416504} 08/31/2021 02:04:43 - INFO - __main__ - Step 71374: {'lr': 0.00027451484744215, 'samples': 13703808, 'steps': 71373, 'loss/train': 0.9143781065940857} 08/31/2021 02:04:43 - INFO - __main__ - Step 71375: {'lr': 0.00027450956626779186, 'samples': 13704000, 'steps': 71374, 'loss/train': 0.9596929550170898} 08/31/2021 02:04:43 - INFO - __main__ - Step 71376: {'lr': 0.0002745042850823902, 'samples': 13704192, 'steps': 71375, 'loss/train': 1.0468292236328125} 08/31/2021 02:04:44 - INFO - __main__ - Step 71377: {'lr': 0.00027449900388594716, 'samples': 13704384, 'steps': 71376, 'loss/train': 1.4832135438919067} 08/31/2021 02:04:46 - INFO - __main__ - Step 71378: {'lr': 0.0002744937226784653, 'samples': 13704576, 'steps': 71377, 'loss/train': 1.155765175819397} 08/31/2021 02:04:46 - INFO - __main__ - Step 71379: {'lr': 0.00027448844145994697, 'samples': 13704768, 'steps': 71378, 'loss/train': 1.2048338651657104} 08/31/2021 02:04:47 - INFO - __main__ - Step 71380: {'lr': 0.00027448316023039444, 'samples': 13704960, 'steps': 71379, 'loss/train': 1.1042448282241821} 08/31/2021 02:04:47 - INFO - __main__ - Step 71381: {'lr': 0.00027447787898981027, 'samples': 13705152, 'steps': 71380, 'loss/train': 1.3323969841003418} 08/31/2021 02:04:47 - INFO - __main__ - Step 71382: {'lr': 0.0002744725977381967, 'samples': 13705344, 'steps': 71381, 'loss/train': 0.7224748730659485} 08/31/2021 02:04:49 - INFO - __main__ - Step 71383: {'lr': 0.0002744673164755562, 'samples': 13705536, 'steps': 71382, 'loss/train': 1.1112512350082397} 08/31/2021 02:04:49 - INFO - __main__ - Step 71384: {'lr': 0.000274462035201891, 'samples': 13705728, 'steps': 71383, 'loss/train': 1.925275206565857} 08/31/2021 02:04:50 - INFO - __main__ - Step 71385: {'lr': 0.00027445675391720364, 'samples': 13705920, 'steps': 71384, 'loss/train': 1.3499269485473633} 08/31/2021 02:04:50 - INFO - __main__ - Step 71386: {'lr': 0.00027445147262149646, 'samples': 13706112, 'steps': 71385, 'loss/train': 1.3618861436843872} 08/31/2021 02:04:50 - INFO - __main__ - Step 71387: {'lr': 0.0002744461913147719, 'samples': 13706304, 'steps': 71386, 'loss/train': 0.7477204203605652} 08/31/2021 02:04:52 - INFO - __main__ - Step 71388: {'lr': 0.00027444090999703214, 'samples': 13706496, 'steps': 71387, 'loss/train': 1.485256314277649} 08/31/2021 02:04:53 - INFO - __main__ - Step 71389: {'lr': 0.0002744356286682797, 'samples': 13706688, 'steps': 71388, 'loss/train': 1.891670823097229} 08/31/2021 02:04:53 - INFO - __main__ - Step 71390: {'lr': 0.00027443034732851695, 'samples': 13706880, 'steps': 71389, 'loss/train': 0.9877370595932007} 08/31/2021 02:04:53 - INFO - __main__ - Step 71391: {'lr': 0.0002744250659777463, 'samples': 13707072, 'steps': 71390, 'loss/train': 1.4351338148117065} 08/31/2021 02:04:54 - INFO - __main__ - Step 71392: {'lr': 0.00027441978461597004, 'samples': 13707264, 'steps': 71391, 'loss/train': 0.9575364589691162} 08/31/2021 02:04:54 - INFO - __main__ - Step 71393: {'lr': 0.00027441450324319067, 'samples': 13707456, 'steps': 71392, 'loss/train': 0.033652547746896744} 08/31/2021 02:04:56 - INFO - __main__ - Step 71394: {'lr': 0.0002744092218594105, 'samples': 13707648, 'steps': 71393, 'loss/train': 1.3762760162353516} 08/31/2021 02:04:56 - INFO - __main__ - Step 71395: {'lr': 0.00027440394046463184, 'samples': 13707840, 'steps': 71394, 'loss/train': 0.7853575944900513} 08/31/2021 02:04:56 - INFO - __main__ - Step 71396: {'lr': 0.0002743986590588572, 'samples': 13708032, 'steps': 71395, 'loss/train': 0.9991810917854309} 08/31/2021 02:04:57 - INFO - __main__ - Step 71397: {'lr': 0.0002743933776420888, 'samples': 13708224, 'steps': 71396, 'loss/train': 0.033535435795784} 08/31/2021 02:04:57 - INFO - __main__ - Step 71398: {'lr': 0.0002743880962143292, 'samples': 13708416, 'steps': 71397, 'loss/train': 1.198683500289917} 08/31/2021 02:04:59 - INFO - __main__ - Step 71399: {'lr': 0.0002743828147755807, 'samples': 13708608, 'steps': 71398, 'loss/train': 1.2336318492889404} 08/31/2021 02:04:59 - INFO - __main__ - Step 71400: {'lr': 0.00027437753332584575, 'samples': 13708800, 'steps': 71399, 'loss/train': 1.2583543062210083} 08/31/2021 02:04:59 - INFO - __main__ - Step 71401: {'lr': 0.00027437225186512657, 'samples': 13708992, 'steps': 71400, 'loss/train': 1.0367099046707153} 08/31/2021 02:05:00 - INFO - __main__ - Step 71402: {'lr': 0.0002743669703934256, 'samples': 13709184, 'steps': 71401, 'loss/train': 0.9279152750968933} 08/31/2021 02:05:00 - INFO - __main__ - Step 71403: {'lr': 0.00027436168891074533, 'samples': 13709376, 'steps': 71402, 'loss/train': 0.9943650960922241} 08/31/2021 02:05:02 - INFO - __main__ - Step 71404: {'lr': 0.000274356407417088, 'samples': 13709568, 'steps': 71403, 'loss/train': 1.5436815023422241} 08/31/2021 02:05:02 - INFO - __main__ - Step 71405: {'lr': 0.00027435112591245607, 'samples': 13709760, 'steps': 71404, 'loss/train': 0.10259843617677689} 08/31/2021 02:05:03 - INFO - __main__ - Step 71406: {'lr': 0.0002743458443968519, 'samples': 13709952, 'steps': 71405, 'loss/train': 0.9843782782554626} 08/31/2021 02:05:03 - INFO - __main__ - Step 71407: {'lr': 0.0002743405628702779, 'samples': 13710144, 'steps': 71406, 'loss/train': 1.299628734588623} 08/31/2021 02:05:04 - INFO - __main__ - Step 71408: {'lr': 0.0002743352813327364, 'samples': 13710336, 'steps': 71407, 'loss/train': 1.4014222621917725} 08/31/2021 02:05:05 - INFO - __main__ - Step 71409: {'lr': 0.0002743299997842297, 'samples': 13710528, 'steps': 71408, 'loss/train': 1.142305612564087} 08/31/2021 02:05:06 - INFO - __main__ - Step 71410: {'lr': 0.0002743247182247604, 'samples': 13710720, 'steps': 71409, 'loss/train': 1.2390716075897217} 08/31/2021 02:05:06 - INFO - __main__ - Step 71411: {'lr': 0.0002743194366543307, 'samples': 13710912, 'steps': 71410, 'loss/train': 0.05881567299365997} 08/31/2021 02:05:06 - INFO - __main__ - Step 71412: {'lr': 0.00027431415507294304, 'samples': 13711104, 'steps': 71411, 'loss/train': 1.2028745412826538} 08/31/2021 02:05:07 - INFO - __main__ - Step 71413: {'lr': 0.00027430887348059993, 'samples': 13711296, 'steps': 71412, 'loss/train': 0.6886596083641052} 08/31/2021 02:05:08 - INFO - __main__ - Step 71414: {'lr': 0.00027430359187730345, 'samples': 13711488, 'steps': 71413, 'loss/train': 1.443223237991333} 08/31/2021 02:05:09 - INFO - __main__ - Step 71415: {'lr': 0.0002742983102630562, 'samples': 13711680, 'steps': 71414, 'loss/train': 1.2431139945983887} 08/31/2021 02:05:09 - INFO - __main__ - Step 71416: {'lr': 0.00027429302863786047, 'samples': 13711872, 'steps': 71415, 'loss/train': 1.4677510261535645} 08/31/2021 02:05:09 - INFO - __main__ - Step 71417: {'lr': 0.0002742877470017187, 'samples': 13712064, 'steps': 71416, 'loss/train': 1.349745512008667} 08/31/2021 02:05:10 - INFO - __main__ - Step 71418: {'lr': 0.00027428246535463323, 'samples': 13712256, 'steps': 71417, 'loss/train': 1.131018877029419} 08/31/2021 02:05:11 - INFO - __main__ - Step 71419: {'lr': 0.0002742771836966065, 'samples': 13712448, 'steps': 71418, 'loss/train': 1.4990323781967163} 08/31/2021 02:05:12 - INFO - __main__ - Step 71420: {'lr': 0.0002742719020276409, 'samples': 13712640, 'steps': 71419, 'loss/train': 0.8638190031051636} 08/31/2021 02:05:12 - INFO - __main__ - Step 71421: {'lr': 0.0002742666203477386, 'samples': 13712832, 'steps': 71420, 'loss/train': 1.0522704124450684} 08/31/2021 02:05:12 - INFO - __main__ - Step 71422: {'lr': 0.0002742613386569023, 'samples': 13713024, 'steps': 71421, 'loss/train': 1.2913569211959839} 08/31/2021 02:05:13 - INFO - __main__ - Step 71423: {'lr': 0.0002742560569551341, 'samples': 13713216, 'steps': 71422, 'loss/train': 0.9629345536231995} 08/31/2021 02:05:13 - INFO - __main__ - Step 71424: {'lr': 0.0002742507752424365, 'samples': 13713408, 'steps': 71423, 'loss/train': 1.1290560960769653} 08/31/2021 02:05:15 - INFO - __main__ - Step 71425: {'lr': 0.0002742454935188119, 'samples': 13713600, 'steps': 71424, 'loss/train': 0.8525129556655884} 08/31/2021 02:05:15 - INFO - __main__ - Step 71426: {'lr': 0.0002742402117842627, 'samples': 13713792, 'steps': 71425, 'loss/train': 1.4590694904327393} 08/31/2021 02:05:16 - INFO - __main__ - Step 71427: {'lr': 0.0002742349300387912, 'samples': 13713984, 'steps': 71426, 'loss/train': 1.0115710496902466} 08/31/2021 02:05:16 - INFO - __main__ - Step 71428: {'lr': 0.0002742296482823998, 'samples': 13714176, 'steps': 71427, 'loss/train': 0.5082507729530334} 08/31/2021 02:05:16 - INFO - __main__ - Step 71429: {'lr': 0.00027422436651509084, 'samples': 13714368, 'steps': 71428, 'loss/train': 0.9848098754882812} 08/31/2021 02:05:18 - INFO - __main__ - Step 71430: {'lr': 0.00027421908473686685, 'samples': 13714560, 'steps': 71429, 'loss/train': 1.6593788862228394} 08/31/2021 02:05:18 - INFO - __main__ - Step 71431: {'lr': 0.0002742138029477301, 'samples': 13714752, 'steps': 71430, 'loss/train': 1.6462033987045288} 08/31/2021 02:05:18 - INFO - __main__ - Step 71432: {'lr': 0.0002742085211476829, 'samples': 13714944, 'steps': 71431, 'loss/train': 1.1517928838729858} 08/31/2021 02:05:19 - INFO - __main__ - Step 71433: {'lr': 0.0002742032393367278, 'samples': 13715136, 'steps': 71432, 'loss/train': 2.0373902320861816} 08/31/2021 02:05:19 - INFO - __main__ - Step 71434: {'lr': 0.0002741979575148671, 'samples': 13715328, 'steps': 71433, 'loss/train': 1.1880371570587158} 08/31/2021 02:05:21 - INFO - __main__ - Step 71435: {'lr': 0.00027419267568210313, 'samples': 13715520, 'steps': 71434, 'loss/train': 1.1678245067596436} 08/31/2021 02:05:22 - INFO - __main__ - Step 71436: {'lr': 0.0002741873938384383, 'samples': 13715712, 'steps': 71435, 'loss/train': 0.6763049364089966} 08/31/2021 02:05:22 - INFO - __main__ - Step 71437: {'lr': 0.00027418211198387507, 'samples': 13715904, 'steps': 71436, 'loss/train': 0.6837509274482727} 08/31/2021 02:05:22 - INFO - __main__ - Step 71438: {'lr': 0.0002741768301184157, 'samples': 13716096, 'steps': 71437, 'loss/train': 0.9608787894248962} 08/31/2021 02:05:23 - INFO - __main__ - Step 71439: {'lr': 0.0002741715482420626, 'samples': 13716288, 'steps': 71438, 'loss/train': 1.2114763259887695} 08/31/2021 02:05:24 - INFO - __main__ - Step 71440: {'lr': 0.0002741662663548183, 'samples': 13716480, 'steps': 71439, 'loss/train': 0.9201328158378601} 08/31/2021 02:05:25 - INFO - __main__ - Step 71441: {'lr': 0.00027416098445668497, 'samples': 13716672, 'steps': 71440, 'loss/train': 1.493192195892334} 08/31/2021 02:05:25 - INFO - __main__ - Step 71442: {'lr': 0.00027415570254766506, 'samples': 13716864, 'steps': 71441, 'loss/train': 1.7233526706695557} 08/31/2021 02:05:25 - INFO - __main__ - Step 71443: {'lr': 0.00027415042062776094, 'samples': 13717056, 'steps': 71442, 'loss/train': 1.0793567895889282} 08/31/2021 02:05:26 - INFO - __main__ - Step 71444: {'lr': 0.0002741451386969751, 'samples': 13717248, 'steps': 71443, 'loss/train': 1.5568268299102783} 08/31/2021 02:05:26 - INFO - __main__ - Step 71445: {'lr': 0.0002741398567553097, 'samples': 13717440, 'steps': 71444, 'loss/train': 1.096541404724121} 08/31/2021 02:05:27 - INFO - __main__ - Step 71446: {'lr': 0.00027413457480276733, 'samples': 13717632, 'steps': 71445, 'loss/train': 1.151078701019287} 08/31/2021 02:05:28 - INFO - __main__ - Step 71447: {'lr': 0.00027412929283935033, 'samples': 13717824, 'steps': 71446, 'loss/train': 0.94045490026474} 08/31/2021 02:05:28 - INFO - __main__ - Step 71448: {'lr': 0.000274124010865061, 'samples': 13718016, 'steps': 71447, 'loss/train': 1.3311129808425903} 08/31/2021 02:05:29 - INFO - __main__ - Step 71449: {'lr': 0.00027411872887990175, 'samples': 13718208, 'steps': 71448, 'loss/train': 1.3599791526794434} 08/31/2021 02:05:29 - INFO - __main__ - Step 71450: {'lr': 0.000274113446883875, 'samples': 13718400, 'steps': 71449, 'loss/train': 1.1383450031280518} 08/31/2021 02:05:30 - INFO - __main__ - Step 71451: {'lr': 0.00027410816487698306, 'samples': 13718592, 'steps': 71450, 'loss/train': 1.2889773845672607} 08/31/2021 02:05:31 - INFO - __main__ - Step 71452: {'lr': 0.0002741028828592284, 'samples': 13718784, 'steps': 71451, 'loss/train': 1.6923975944519043} 08/31/2021 02:05:31 - INFO - __main__ - Step 71453: {'lr': 0.00027409760083061335, 'samples': 13718976, 'steps': 71452, 'loss/train': 1.7232407331466675} 08/31/2021 02:05:32 - INFO - __main__ - Step 71454: {'lr': 0.0002740923187911403, 'samples': 13719168, 'steps': 71453, 'loss/train': 1.0711112022399902} 08/31/2021 02:05:32 - INFO - __main__ - Step 71455: {'lr': 0.0002740870367408116, 'samples': 13719360, 'steps': 71454, 'loss/train': 0.4645802676677704} 08/31/2021 02:05:34 - INFO - __main__ - Step 71456: {'lr': 0.0002740817546796297, 'samples': 13719552, 'steps': 71455, 'loss/train': 1.118329644203186} 08/31/2021 02:05:34 - INFO - __main__ - Step 71457: {'lr': 0.0002740764726075969, 'samples': 13719744, 'steps': 71456, 'loss/train': 1.0861127376556396} 08/31/2021 02:05:34 - INFO - __main__ - Step 71458: {'lr': 0.00027407119052471555, 'samples': 13719936, 'steps': 71457, 'loss/train': 1.2502366304397583} 08/31/2021 02:05:35 - INFO - __main__ - Step 71459: {'lr': 0.0002740659084309882, 'samples': 13720128, 'steps': 71458, 'loss/train': 0.20913033187389374} 08/31/2021 02:05:35 - INFO - __main__ - Step 71460: {'lr': 0.000274060626326417, 'samples': 13720320, 'steps': 71459, 'loss/train': 0.9519754648208618} 08/31/2021 02:05:36 - INFO - __main__ - Step 71461: {'lr': 0.0002740553442110046, 'samples': 13720512, 'steps': 71460, 'loss/train': 1.1773812770843506} 08/31/2021 02:05:37 - INFO - __main__ - Step 71462: {'lr': 0.00027405006208475316, 'samples': 13720704, 'steps': 71461, 'loss/train': 1.7407199144363403} 08/31/2021 02:05:37 - INFO - __main__ - Step 71463: {'lr': 0.00027404477994766514, 'samples': 13720896, 'steps': 71462, 'loss/train': 1.3654472827911377} 08/31/2021 02:05:38 - INFO - __main__ - Step 71464: {'lr': 0.00027403949779974284, 'samples': 13721088, 'steps': 71463, 'loss/train': 1.08944833278656} 08/31/2021 02:05:38 - INFO - __main__ - Step 71465: {'lr': 0.0002740342156409888, 'samples': 13721280, 'steps': 71464, 'loss/train': 1.3043466806411743} 08/31/2021 02:05:39 - INFO - __main__ - Step 71466: {'lr': 0.00027402893347140526, 'samples': 13721472, 'steps': 71465, 'loss/train': 1.8644343614578247} 08/31/2021 02:05:40 - INFO - __main__ - Step 71467: {'lr': 0.00027402365129099474, 'samples': 13721664, 'steps': 71466, 'loss/train': 1.1665596961975098} 08/31/2021 02:05:40 - INFO - __main__ - Step 71468: {'lr': 0.00027401836909975944, 'samples': 13721856, 'steps': 71467, 'loss/train': 0.8865026235580444} 08/31/2021 02:05:41 - INFO - __main__ - Step 71469: {'lr': 0.0002740130868977019, 'samples': 13722048, 'steps': 71468, 'loss/train': 1.1883984804153442} 08/31/2021 02:05:41 - INFO - __main__ - Step 71470: {'lr': 0.0002740078046848244, 'samples': 13722240, 'steps': 71469, 'loss/train': 1.1620814800262451} 08/31/2021 02:05:41 - INFO - __main__ - Step 71471: {'lr': 0.00027400252246112934, 'samples': 13722432, 'steps': 71470, 'loss/train': 1.4015049934387207} 08/31/2021 02:05:43 - INFO - __main__ - Step 71472: {'lr': 0.00027399724022661914, 'samples': 13722624, 'steps': 71471, 'loss/train': 0.859138548374176} 08/31/2021 02:05:43 - INFO - __main__ - Step 71473: {'lr': 0.00027399195798129614, 'samples': 13722816, 'steps': 71472, 'loss/train': 1.0582280158996582} 08/31/2021 02:05:44 - INFO - __main__ - Step 71474: {'lr': 0.00027398667572516277, 'samples': 13723008, 'steps': 71473, 'loss/train': 1.4873403310775757} 08/31/2021 02:05:44 - INFO - __main__ - Step 71475: {'lr': 0.00027398139345822137, 'samples': 13723200, 'steps': 71474, 'loss/train': 1.3067702054977417} 08/31/2021 02:05:44 - INFO - __main__ - Step 71476: {'lr': 0.00027397611118047427, 'samples': 13723392, 'steps': 71475, 'loss/train': 1.0162415504455566} 08/31/2021 02:05:46 - INFO - __main__ - Step 71477: {'lr': 0.0002739708288919239, 'samples': 13723584, 'steps': 71476, 'loss/train': 1.2591897249221802} 08/31/2021 02:05:46 - INFO - __main__ - Step 71478: {'lr': 0.00027396554659257273, 'samples': 13723776, 'steps': 71477, 'loss/train': 1.2907984256744385} 08/31/2021 02:05:47 - INFO - __main__ - Step 71479: {'lr': 0.000273960264282423, 'samples': 13723968, 'steps': 71478, 'loss/train': 1.135048270225525} 08/31/2021 02:05:47 - INFO - __main__ - Step 71480: {'lr': 0.0002739549819614771, 'samples': 13724160, 'steps': 71479, 'loss/train': 1.10059654712677} 08/31/2021 02:05:47 - INFO - __main__ - Step 71481: {'lr': 0.00027394969962973756, 'samples': 13724352, 'steps': 71480, 'loss/train': 1.1939184665679932} 08/31/2021 02:05:49 - INFO - __main__ - Step 71482: {'lr': 0.0002739444172872066, 'samples': 13724544, 'steps': 71481, 'loss/train': 1.381699562072754} 08/31/2021 02:05:50 - INFO - __main__ - Step 71483: {'lr': 0.0002739391349338866, 'samples': 13724736, 'steps': 71482, 'loss/train': 0.7397862076759338} 08/31/2021 02:05:50 - INFO - __main__ - Step 71484: {'lr': 0.00027393385256978004, 'samples': 13724928, 'steps': 71483, 'loss/train': 0.492292195558548} 08/31/2021 02:05:50 - INFO - __main__ - Step 71485: {'lr': 0.00027392857019488924, 'samples': 13725120, 'steps': 71484, 'loss/train': 1.263408899307251} 08/31/2021 02:05:51 - INFO - __main__ - Step 71486: {'lr': 0.00027392328780921664, 'samples': 13725312, 'steps': 71485, 'loss/train': 1.0111191272735596} 08/31/2021 02:05:52 - INFO - __main__ - Step 71487: {'lr': 0.00027391800541276464, 'samples': 13725504, 'steps': 71486, 'loss/train': 1.2809364795684814} 08/31/2021 02:05:53 - INFO - __main__ - Step 71488: {'lr': 0.00027391272300553545, 'samples': 13725696, 'steps': 71487, 'loss/train': 1.0661636590957642} 08/31/2021 02:05:53 - INFO - __main__ - Step 71489: {'lr': 0.0002739074405875315, 'samples': 13725888, 'steps': 71488, 'loss/train': 1.022660732269287} 08/31/2021 02:05:53 - INFO - __main__ - Step 71490: {'lr': 0.0002739021581587554, 'samples': 13726080, 'steps': 71489, 'loss/train': 1.5881353616714478} 08/31/2021 02:05:54 - INFO - __main__ - Step 71491: {'lr': 0.0002738968757192092, 'samples': 13726272, 'steps': 71490, 'loss/train': 1.290055274963379} 08/31/2021 02:05:54 - INFO - __main__ - Step 71492: {'lr': 0.00027389159326889545, 'samples': 13726464, 'steps': 71491, 'loss/train': 1.0843350887298584} 08/31/2021 02:05:56 - INFO - __main__ - Step 71493: {'lr': 0.0002738863108078166, 'samples': 13726656, 'steps': 71492, 'loss/train': 0.6819525957107544} 08/31/2021 02:05:57 - INFO - __main__ - Step 71494: {'lr': 0.00027388102833597497, 'samples': 13726848, 'steps': 71493, 'loss/train': 0.9637612104415894} 08/31/2021 02:05:57 - INFO - __main__ - Step 71495: {'lr': 0.0002738757458533728, 'samples': 13727040, 'steps': 71494, 'loss/train': 1.7740579843521118} 08/31/2021 02:05:57 - INFO - __main__ - Step 71496: {'lr': 0.00027387046336001264, 'samples': 13727232, 'steps': 71495, 'loss/train': 0.5467250347137451} 08/31/2021 02:05:58 - INFO - __main__ - Step 71497: {'lr': 0.0002738651808558968, 'samples': 13727424, 'steps': 71496, 'loss/train': 1.0181775093078613} 08/31/2021 02:05:59 - INFO - __main__ - Step 71498: {'lr': 0.0002738598983410277, 'samples': 13727616, 'steps': 71497, 'loss/train': 0.906245768070221} 08/31/2021 02:06:00 - INFO - __main__ - Step 71499: {'lr': 0.0002738546158154077, 'samples': 13727808, 'steps': 71498, 'loss/train': 0.9270720481872559} 08/31/2021 02:06:00 - INFO - __main__ - Step 71500: {'lr': 0.00027384933327903924, 'samples': 13728000, 'steps': 71499, 'loss/train': 2.040423631668091} 08/31/2021 02:06:00 - INFO - __main__ - Step 71501: {'lr': 0.00027384405073192455, 'samples': 13728192, 'steps': 71500, 'loss/train': 1.5319768190383911} 08/31/2021 02:06:01 - INFO - __main__ - Step 71502: {'lr': 0.0002738387681740661, 'samples': 13728384, 'steps': 71501, 'loss/train': 1.0634374618530273} 08/31/2021 02:06:02 - INFO - __main__ - Step 71503: {'lr': 0.0002738334856054663, 'samples': 13728576, 'steps': 71502, 'loss/train': 0.8422096371650696} 08/31/2021 02:06:03 - INFO - __main__ - Step 71504: {'lr': 0.0002738282030261274, 'samples': 13728768, 'steps': 71503, 'loss/train': 0.8748875260353088} 08/31/2021 02:06:03 - INFO - __main__ - Step 71505: {'lr': 0.00027382292043605204, 'samples': 13728960, 'steps': 71504, 'loss/train': 0.9283928275108337} 08/31/2021 02:06:03 - INFO - __main__ - Step 71506: {'lr': 0.0002738176378352424, 'samples': 13729152, 'steps': 71505, 'loss/train': 1.2416964769363403} 08/31/2021 02:06:04 - INFO - __main__ - Step 71507: {'lr': 0.00027381235522370084, 'samples': 13729344, 'steps': 71506, 'loss/train': 1.0504368543624878} 08/31/2021 02:06:05 - INFO - __main__ - Step 71508: {'lr': 0.00027380707260142985, 'samples': 13729536, 'steps': 71507, 'loss/train': 1.3039777278900146} 08/31/2021 02:06:06 - INFO - __main__ - Step 71509: {'lr': 0.0002738017899684317, 'samples': 13729728, 'steps': 71508, 'loss/train': 1.5764961242675781} 08/31/2021 02:06:06 - INFO - __main__ - Step 71510: {'lr': 0.0002737965073247089, 'samples': 13729920, 'steps': 71509, 'loss/train': 1.557783603668213} 08/31/2021 02:06:06 - INFO - __main__ - Step 71511: {'lr': 0.00027379122467026374, 'samples': 13730112, 'steps': 71510, 'loss/train': 0.4392232596874237} 08/31/2021 02:06:07 - INFO - __main__ - Step 71512: {'lr': 0.0002737859420050986, 'samples': 13730304, 'steps': 71511, 'loss/train': 1.5224027633666992} 08/31/2021 02:06:07 - INFO - __main__ - Step 71513: {'lr': 0.0002737806593292159, 'samples': 13730496, 'steps': 71512, 'loss/train': 1.3972855806350708} 08/31/2021 02:06:08 - INFO - __main__ - Step 71514: {'lr': 0.000273775376642618, 'samples': 13730688, 'steps': 71513, 'loss/train': 1.6018072366714478} 08/31/2021 02:06:09 - INFO - __main__ - Step 71515: {'lr': 0.00027377009394530727, 'samples': 13730880, 'steps': 71514, 'loss/train': 1.2405736446380615} 08/31/2021 02:06:09 - INFO - __main__ - Step 71516: {'lr': 0.00027376481123728613, 'samples': 13731072, 'steps': 71515, 'loss/train': 1.6109519004821777} 08/31/2021 02:06:10 - INFO - __main__ - Step 71517: {'lr': 0.0002737595285185569, 'samples': 13731264, 'steps': 71516, 'loss/train': 1.6594083309173584} 08/31/2021 02:06:10 - INFO - __main__ - Step 71518: {'lr': 0.000273754245789122, 'samples': 13731456, 'steps': 71517, 'loss/train': 1.36829674243927} 08/31/2021 02:06:11 - INFO - __main__ - Step 71519: {'lr': 0.00027374896304898386, 'samples': 13731648, 'steps': 71518, 'loss/train': 1.3712750673294067} 08/31/2021 02:06:12 - INFO - __main__ - Step 71520: {'lr': 0.0002737436802981447, 'samples': 13731840, 'steps': 71519, 'loss/train': 0.49189525842666626} 08/31/2021 02:06:12 - INFO - __main__ - Step 71521: {'lr': 0.0002737383975366071, 'samples': 13732032, 'steps': 71520, 'loss/train': 1.327000617980957} 08/31/2021 02:06:13 - INFO - __main__ - Step 71522: {'lr': 0.0002737331147643733, 'samples': 13732224, 'steps': 71521, 'loss/train': 2.3455288410186768} 08/31/2021 02:06:13 - INFO - __main__ - Step 71523: {'lr': 0.00027372783198144574, 'samples': 13732416, 'steps': 71522, 'loss/train': 1.4627846479415894} 08/31/2021 02:06:14 - INFO - __main__ - Step 71524: {'lr': 0.00027372254918782673, 'samples': 13732608, 'steps': 71523, 'loss/train': 1.380168080329895} 08/31/2021 02:06:15 - INFO - __main__ - Step 71525: {'lr': 0.00027371726638351874, 'samples': 13732800, 'steps': 71524, 'loss/train': 1.393275260925293} 08/31/2021 02:06:15 - INFO - __main__ - Step 71526: {'lr': 0.0002737119835685241, 'samples': 13732992, 'steps': 71525, 'loss/train': 1.0741087198257446} 08/31/2021 02:06:16 - INFO - __main__ - Step 71527: {'lr': 0.0002737067007428453, 'samples': 13733184, 'steps': 71526, 'loss/train': 1.3643101453781128} 08/31/2021 02:06:16 - INFO - __main__ - Step 71528: {'lr': 0.00027370141790648454, 'samples': 13733376, 'steps': 71527, 'loss/train': 0.8823736310005188} 08/31/2021 02:06:18 - INFO - __main__ - Step 71529: {'lr': 0.0002736961350594443, 'samples': 13733568, 'steps': 71528, 'loss/train': 1.1621448993682861} 08/31/2021 02:06:18 - INFO - __main__ - Step 71530: {'lr': 0.000273690852201727, 'samples': 13733760, 'steps': 71529, 'loss/train': 1.1729425191879272} 08/31/2021 02:06:18 - INFO - __main__ - Step 71531: {'lr': 0.00027368556933333484, 'samples': 13733952, 'steps': 71530, 'loss/train': 1.0362670421600342} 08/31/2021 02:06:19 - INFO - __main__ - Step 71532: {'lr': 0.0002736802864542704, 'samples': 13734144, 'steps': 71531, 'loss/train': 0.8946256637573242} 08/31/2021 02:06:19 - INFO - __main__ - Step 71533: {'lr': 0.000273675003564536, 'samples': 13734336, 'steps': 71532, 'loss/train': 1.0004569292068481} 08/31/2021 02:06:20 - INFO - __main__ - Step 71534: {'lr': 0.00027366972066413404, 'samples': 13734528, 'steps': 71533, 'loss/train': 1.767060399055481} 08/31/2021 02:06:21 - INFO - __main__ - Step 71535: {'lr': 0.00027366443775306683, 'samples': 13734720, 'steps': 71534, 'loss/train': 0.7849962115287781} 08/31/2021 02:06:21 - INFO - __main__ - Step 71536: {'lr': 0.00027365915483133676, 'samples': 13734912, 'steps': 71535, 'loss/train': 1.4331728219985962} 08/31/2021 02:06:22 - INFO - __main__ - Step 71537: {'lr': 0.0002736538718989463, 'samples': 13735104, 'steps': 71536, 'loss/train': 1.4786572456359863} 08/31/2021 02:06:22 - INFO - __main__ - Step 71538: {'lr': 0.0002736485889558977, 'samples': 13735296, 'steps': 71537, 'loss/train': 1.769282579421997} 08/31/2021 02:06:23 - INFO - __main__ - Step 71539: {'lr': 0.00027364330600219343, 'samples': 13735488, 'steps': 71538, 'loss/train': 1.3507916927337646} 08/31/2021 02:06:24 - INFO - __main__ - Step 71540: {'lr': 0.00027363802303783584, 'samples': 13735680, 'steps': 71539, 'loss/train': 0.9869716763496399} 08/31/2021 02:06:24 - INFO - __main__ - Step 71541: {'lr': 0.0002736327400628275, 'samples': 13735872, 'steps': 71540, 'loss/train': 1.369935154914856} 08/31/2021 02:06:25 - INFO - __main__ - Step 71542: {'lr': 0.0002736274570771704, 'samples': 13736064, 'steps': 71541, 'loss/train': 0.8686544299125671} 08/31/2021 02:06:25 - INFO - __main__ - Step 71543: {'lr': 0.0002736221740808672, 'samples': 13736256, 'steps': 71542, 'loss/train': 0.5502705574035645} 08/31/2021 02:06:27 - INFO - __main__ - Step 71544: {'lr': 0.0002736168910739202, 'samples': 13736448, 'steps': 71543, 'loss/train': 1.1443015336990356} 08/31/2021 02:06:28 - INFO - __main__ - Step 71545: {'lr': 0.0002736116080563318, 'samples': 13736640, 'steps': 71544, 'loss/train': 1.1103004217147827} 08/31/2021 02:06:28 - INFO - __main__ - Step 71546: {'lr': 0.00027360632502810433, 'samples': 13736832, 'steps': 71545, 'loss/train': 1.0323938131332397} 08/31/2021 02:06:28 - INFO - __main__ - Step 71547: {'lr': 0.0002736010419892403, 'samples': 13737024, 'steps': 71546, 'loss/train': 1.786076307296753} 08/31/2021 02:06:29 - INFO - __main__ - Step 71548: {'lr': 0.00027359575893974196, 'samples': 13737216, 'steps': 71547, 'loss/train': 1.5207171440124512} 08/31/2021 02:06:29 - INFO - __main__ - Step 71549: {'lr': 0.0002735904758796118, 'samples': 13737408, 'steps': 71548, 'loss/train': 0.28276509046554565} 08/31/2021 02:06:30 - INFO - __main__ - Step 71550: {'lr': 0.000273585192808852, 'samples': 13737600, 'steps': 71549, 'loss/train': 1.024096965789795} 08/31/2021 02:06:31 - INFO - __main__ - Step 71551: {'lr': 0.00027357990972746516, 'samples': 13737792, 'steps': 71550, 'loss/train': 1.1518696546554565} 08/31/2021 02:06:31 - INFO - __main__ - Step 71552: {'lr': 0.00027357462663545355, 'samples': 13737984, 'steps': 71551, 'loss/train': 0.8197980523109436} 08/31/2021 02:06:32 - INFO - __main__ - Step 71553: {'lr': 0.0002735693435328196, 'samples': 13738176, 'steps': 71552, 'loss/train': 1.0914732217788696} 08/31/2021 02:06:32 - INFO - __main__ - Step 71554: {'lr': 0.0002735640604195657, 'samples': 13738368, 'steps': 71553, 'loss/train': 0.791104257106781} 08/31/2021 02:06:33 - INFO - __main__ - Step 71555: {'lr': 0.0002735587772956942, 'samples': 13738560, 'steps': 71554, 'loss/train': 0.974867045879364} 08/31/2021 02:06:34 - INFO - __main__ - Step 71556: {'lr': 0.0002735534941612074, 'samples': 13738752, 'steps': 71555, 'loss/train': 0.9770546555519104} 08/31/2021 02:06:34 - INFO - __main__ - Step 71557: {'lr': 0.00027354821101610783, 'samples': 13738944, 'steps': 71556, 'loss/train': 1.2796157598495483} 08/31/2021 02:06:34 - INFO - __main__ - Step 71558: {'lr': 0.00027354292786039777, 'samples': 13739136, 'steps': 71557, 'loss/train': 1.3353071212768555} 08/31/2021 02:06:35 - INFO - __main__ - Step 71559: {'lr': 0.0002735376446940796, 'samples': 13739328, 'steps': 71558, 'loss/train': 2.659097194671631} 08/31/2021 02:06:36 - INFO - __main__ - Step 71560: {'lr': 0.0002735323615171558, 'samples': 13739520, 'steps': 71559, 'loss/train': 1.175235390663147} 08/31/2021 02:06:37 - INFO - __main__ - Step 71561: {'lr': 0.0002735270783296286, 'samples': 13739712, 'steps': 71560, 'loss/train': 0.7801572680473328} 08/31/2021 02:06:37 - INFO - __main__ - Step 71562: {'lr': 0.00027352179513150056, 'samples': 13739904, 'steps': 71561, 'loss/train': 1.080388069152832} 08/31/2021 02:06:37 - INFO - __main__ - Step 71563: {'lr': 0.0002735165119227739, 'samples': 13740096, 'steps': 71562, 'loss/train': 1.6050775051116943} 08/31/2021 02:06:38 - INFO - __main__ - Step 71564: {'lr': 0.000273511228703451, 'samples': 13740288, 'steps': 71563, 'loss/train': 0.9947289824485779} 08/31/2021 02:06:39 - INFO - __main__ - Step 71565: {'lr': 0.0002735059454735344, 'samples': 13740480, 'steps': 71564, 'loss/train': 1.7696110010147095} 08/31/2021 02:06:40 - INFO - __main__ - Step 71566: {'lr': 0.0002735006622330263, 'samples': 13740672, 'steps': 71565, 'loss/train': 0.9118590950965881} 08/31/2021 02:06:40 - INFO - __main__ - Step 71567: {'lr': 0.00027349537898192924, 'samples': 13740864, 'steps': 71566, 'loss/train': 1.2718948125839233} 08/31/2021 02:06:41 - INFO - __main__ - Step 71568: {'lr': 0.0002734900957202455, 'samples': 13741056, 'steps': 71567, 'loss/train': 0.913885235786438} 08/31/2021 02:06:41 - INFO - __main__ - Step 71569: {'lr': 0.0002734848124479775, 'samples': 13741248, 'steps': 71568, 'loss/train': 0.08457870781421661} 08/31/2021 02:06:43 - INFO - __main__ - Step 71570: {'lr': 0.00027347952916512765, 'samples': 13741440, 'steps': 71569, 'loss/train': 0.9443016648292542} 08/31/2021 02:06:43 - INFO - __main__ - Step 71571: {'lr': 0.00027347424587169817, 'samples': 13741632, 'steps': 71570, 'loss/train': 1.9110770225524902} 08/31/2021 02:06:43 - INFO - __main__ - Step 71572: {'lr': 0.0002734689625676916, 'samples': 13741824, 'steps': 71571, 'loss/train': 0.0376625619828701} 08/31/2021 02:06:44 - INFO - __main__ - Step 71573: {'lr': 0.00027346367925311035, 'samples': 13742016, 'steps': 71572, 'loss/train': 1.0279048681259155} 08/31/2021 02:06:44 - INFO - __main__ - Step 71574: {'lr': 0.0002734583959279566, 'samples': 13742208, 'steps': 71573, 'loss/train': 1.6312177181243896} 08/31/2021 02:06:46 - INFO - __main__ - Step 71575: {'lr': 0.000273453112592233, 'samples': 13742400, 'steps': 71574, 'loss/train': 1.6439521312713623} 08/31/2021 02:06:46 - INFO - __main__ - Step 71576: {'lr': 0.00027344782924594173, 'samples': 13742592, 'steps': 71575, 'loss/train': 1.1304773092269897} 08/31/2021 02:06:47 - INFO - __main__ - Step 71577: {'lr': 0.0002734425458890852, 'samples': 13742784, 'steps': 71576, 'loss/train': 1.1564013957977295} 08/31/2021 02:06:47 - INFO - __main__ - Step 71578: {'lr': 0.00027343726252166583, 'samples': 13742976, 'steps': 71577, 'loss/train': 1.0915452241897583} 08/31/2021 02:06:47 - INFO - __main__ - Step 71579: {'lr': 0.00027343197914368603, 'samples': 13743168, 'steps': 71578, 'loss/train': 0.9319290518760681} 08/31/2021 02:06:49 - INFO - __main__ - Step 71580: {'lr': 0.0002734266957551481, 'samples': 13743360, 'steps': 71579, 'loss/train': 1.2626301050186157} 08/31/2021 02:06:49 - INFO - __main__ - Step 71581: {'lr': 0.00027342141235605445, 'samples': 13743552, 'steps': 71580, 'loss/train': 1.1845872402191162} 08/31/2021 02:06:50 - INFO - __main__ - Step 71582: {'lr': 0.00027341612894640755, 'samples': 13743744, 'steps': 71581, 'loss/train': 1.6974315643310547} 08/31/2021 02:06:50 - INFO - __main__ - Step 71583: {'lr': 0.0002734108455262097, 'samples': 13743936, 'steps': 71582, 'loss/train': 1.032554030418396} 08/31/2021 02:06:50 - INFO - __main__ - Step 71584: {'lr': 0.00027340556209546317, 'samples': 13744128, 'steps': 71583, 'loss/train': 0.43971511721611023} 08/31/2021 02:06:51 - INFO - __main__ - Step 71585: {'lr': 0.00027340027865417057, 'samples': 13744320, 'steps': 71584, 'loss/train': 0.8974747061729431} 08/31/2021 02:06:52 - INFO - __main__ - Step 71586: {'lr': 0.00027339499520233405, 'samples': 13744512, 'steps': 71585, 'loss/train': 1.5983854532241821} 08/31/2021 02:06:52 - INFO - __main__ - Step 71587: {'lr': 0.0002733897117399562, 'samples': 13744704, 'steps': 71586, 'loss/train': 0.9374179840087891} 08/31/2021 02:06:53 - INFO - __main__ - Step 71588: {'lr': 0.0002733844282670393, 'samples': 13744896, 'steps': 71587, 'loss/train': 1.4808452129364014} 08/31/2021 02:06:53 - INFO - __main__ - Step 71589: {'lr': 0.0002733791447835857, 'samples': 13745088, 'steps': 71588, 'loss/train': 1.4876911640167236} 08/31/2021 02:06:53 - INFO - __main__ - Step 71590: {'lr': 0.00027337386128959784, 'samples': 13745280, 'steps': 71589, 'loss/train': 0.7875997424125671} 08/31/2021 02:06:55 - INFO - __main__ - Step 71591: {'lr': 0.00027336857778507804, 'samples': 13745472, 'steps': 71590, 'loss/train': 1.386608600616455} 08/31/2021 02:06:56 - INFO - __main__ - Step 71592: {'lr': 0.0002733632942700288, 'samples': 13745664, 'steps': 71591, 'loss/train': 0.5891455411911011} 08/31/2021 02:06:56 - INFO - __main__ - Step 71593: {'lr': 0.0002733580107444524, 'samples': 13745856, 'steps': 71592, 'loss/train': 1.3561838865280151} 08/31/2021 02:06:56 - INFO - __main__ - Step 71594: {'lr': 0.0002733527272083512, 'samples': 13746048, 'steps': 71593, 'loss/train': 1.2231656312942505} 08/31/2021 02:06:57 - INFO - __main__ - Step 71595: {'lr': 0.00027334744366172765, 'samples': 13746240, 'steps': 71594, 'loss/train': 0.9214104413986206} 08/31/2021 02:06:59 - INFO - __main__ - Step 71596: {'lr': 0.0002733421601045841, 'samples': 13746432, 'steps': 71595, 'loss/train': 1.3172928094863892} 08/31/2021 02:06:59 - INFO - __main__ - Step 71597: {'lr': 0.0002733368765369229, 'samples': 13746624, 'steps': 71596, 'loss/train': 1.3632469177246094} 08/31/2021 02:07:00 - INFO - __main__ - Step 71598: {'lr': 0.0002733315929587465, 'samples': 13746816, 'steps': 71597, 'loss/train': 1.4681153297424316} 08/31/2021 02:07:00 - INFO - __main__ - Step 71599: {'lr': 0.0002733263093700572, 'samples': 13747008, 'steps': 71598, 'loss/train': 1.5010051727294922} 08/31/2021 02:07:01 - INFO - __main__ - Step 71600: {'lr': 0.00027332102577085743, 'samples': 13747200, 'steps': 71599, 'loss/train': 3.9327447414398193} 08/31/2021 02:07:02 - INFO - __main__ - Step 71601: {'lr': 0.00027331574216114964, 'samples': 13747392, 'steps': 71600, 'loss/train': 1.1037664413452148} 08/31/2021 02:07:02 - INFO - __main__ - Step 71602: {'lr': 0.0002733104585409361, 'samples': 13747584, 'steps': 71601, 'loss/train': 1.1040797233581543} 08/31/2021 02:07:03 - INFO - __main__ - Step 71603: {'lr': 0.00027330517491021923, 'samples': 13747776, 'steps': 71602, 'loss/train': 1.413150429725647} 08/31/2021 02:07:03 - INFO - __main__ - Step 71604: {'lr': 0.0002732998912690013, 'samples': 13747968, 'steps': 71603, 'loss/train': 1.8389469385147095} 08/31/2021 02:07:04 - INFO - __main__ - Step 71605: {'lr': 0.0002732946076172849, 'samples': 13748160, 'steps': 71604, 'loss/train': 0.9485300779342651} 08/31/2021 02:07:05 - INFO - __main__ - Step 71606: {'lr': 0.0002732893239550723, 'samples': 13748352, 'steps': 71605, 'loss/train': 1.0066224336624146} 08/31/2021 02:07:05 - INFO - __main__ - Step 71607: {'lr': 0.0002732840402823659, 'samples': 13748544, 'steps': 71606, 'loss/train': 1.1949267387390137} 08/31/2021 02:07:06 - INFO - __main__ - Step 71608: {'lr': 0.00027327875659916815, 'samples': 13748736, 'steps': 71607, 'loss/train': 1.731885552406311} 08/31/2021 02:07:06 - INFO - __main__ - Step 71609: {'lr': 0.0002732734729054812, 'samples': 13748928, 'steps': 71608, 'loss/train': 0.8447232246398926} 08/31/2021 02:07:07 - INFO - __main__ - Step 71610: {'lr': 0.0002732681892013077, 'samples': 13749120, 'steps': 71609, 'loss/train': 1.100447177886963} 08/31/2021 02:07:07 - INFO - __main__ - Step 71611: {'lr': 0.0002732629054866498, 'samples': 13749312, 'steps': 71610, 'loss/train': 1.4167412519454956} 08/31/2021 02:07:08 - INFO - __main__ - Step 71612: {'lr': 0.00027325762176151, 'samples': 13749504, 'steps': 71611, 'loss/train': 0.5717031359672546} 08/31/2021 02:07:09 - INFO - __main__ - Step 71613: {'lr': 0.0002732523380258908, 'samples': 13749696, 'steps': 71612, 'loss/train': 0.5144609808921814} 08/31/2021 02:07:09 - INFO - __main__ - Step 71614: {'lr': 0.00027324705427979437, 'samples': 13749888, 'steps': 71613, 'loss/train': 1.0936554670333862} 08/31/2021 02:07:09 - INFO - __main__ - Step 71615: {'lr': 0.00027324177052322326, 'samples': 13750080, 'steps': 71614, 'loss/train': 1.506079077720642} 08/31/2021 02:07:10 - INFO - __main__ - Step 71616: {'lr': 0.00027323648675617963, 'samples': 13750272, 'steps': 71615, 'loss/train': 1.3992105722427368} 08/31/2021 02:07:12 - INFO - __main__ - Step 71617: {'lr': 0.0002732312029786661, 'samples': 13750464, 'steps': 71616, 'loss/train': 1.4183125495910645} 08/31/2021 02:07:12 - INFO - __main__ - Step 71618: {'lr': 0.00027322591919068487, 'samples': 13750656, 'steps': 71617, 'loss/train': 1.343821406364441} 08/31/2021 02:07:12 - INFO - __main__ - Step 71619: {'lr': 0.00027322063539223846, 'samples': 13750848, 'steps': 71618, 'loss/train': 0.10677781701087952} 08/31/2021 02:07:13 - INFO - __main__ - Step 71620: {'lr': 0.0002732153515833291, 'samples': 13751040, 'steps': 71619, 'loss/train': 0.8967961072921753} 08/31/2021 02:07:13 - INFO - __main__ - Step 71621: {'lr': 0.00027321006776395934, 'samples': 13751232, 'steps': 71620, 'loss/train': 1.3999484777450562} 08/31/2021 02:07:15 - INFO - __main__ - Step 71622: {'lr': 0.00027320478393413157, 'samples': 13751424, 'steps': 71621, 'loss/train': 2.055812358856201} 08/31/2021 02:07:15 - INFO - __main__ - Step 71623: {'lr': 0.0002731995000938479, 'samples': 13751616, 'steps': 71622, 'loss/train': 1.7927119731903076} 08/31/2021 02:07:15 - INFO - __main__ - Step 71624: {'lr': 0.000273194216243111, 'samples': 13751808, 'steps': 71623, 'loss/train': 1.5663338899612427} 08/31/2021 02:07:16 - INFO - __main__ - Step 71625: {'lr': 0.0002731889323819231, 'samples': 13752000, 'steps': 71624, 'loss/train': 1.1714236736297607} 08/31/2021 02:07:16 - INFO - __main__ - Step 71626: {'lr': 0.0002731836485102866, 'samples': 13752192, 'steps': 71625, 'loss/train': 1.3395466804504395} 08/31/2021 02:07:18 - INFO - __main__ - Step 71627: {'lr': 0.000273178364628204, 'samples': 13752384, 'steps': 71626, 'loss/train': 1.0270107984542847} 08/31/2021 02:07:18 - INFO - __main__ - Step 71628: {'lr': 0.0002731730807356775, 'samples': 13752576, 'steps': 71627, 'loss/train': 1.5382986068725586} 08/31/2021 02:07:18 - INFO - __main__ - Step 71629: {'lr': 0.00027316779683270973, 'samples': 13752768, 'steps': 71628, 'loss/train': 1.0659950971603394} 08/31/2021 02:07:19 - INFO - __main__ - Step 71630: {'lr': 0.0002731625129193027, 'samples': 13752960, 'steps': 71629, 'loss/train': 1.469657301902771} 08/31/2021 02:07:19 - INFO - __main__ - Step 71631: {'lr': 0.00027315722899545915, 'samples': 13753152, 'steps': 71630, 'loss/train': 0.851248025894165} 08/31/2021 02:07:21 - INFO - __main__ - Step 71632: {'lr': 0.0002731519450611812, 'samples': 13753344, 'steps': 71631, 'loss/train': 0.9107213020324707} 08/31/2021 02:07:21 - INFO - __main__ - Step 71633: {'lr': 0.0002731466611164714, 'samples': 13753536, 'steps': 71632, 'loss/train': 1.0017844438552856} 08/31/2021 02:07:21 - INFO - __main__ - Step 71634: {'lr': 0.0002731413771613321, 'samples': 13753728, 'steps': 71633, 'loss/train': 1.6843100786209106} 08/31/2021 02:07:22 - INFO - __main__ - Step 71635: {'lr': 0.0002731360931957656, 'samples': 13753920, 'steps': 71634, 'loss/train': 1.2661815881729126} 08/31/2021 02:07:22 - INFO - __main__ - Step 71636: {'lr': 0.00027313080921977437, 'samples': 13754112, 'steps': 71635, 'loss/train': 1.5231822729110718} 08/31/2021 02:07:24 - INFO - __main__ - Step 71637: {'lr': 0.00027312552523336064, 'samples': 13754304, 'steps': 71636, 'loss/train': 1.5175220966339111} 08/31/2021 02:07:24 - INFO - __main__ - Step 71638: {'lr': 0.000273120241236527, 'samples': 13754496, 'steps': 71637, 'loss/train': 1.1207592487335205} 08/31/2021 02:07:25 - INFO - __main__ - Step 71639: {'lr': 0.0002731149572292757, 'samples': 13754688, 'steps': 71638, 'loss/train': 1.240148901939392} 08/31/2021 02:07:25 - INFO - __main__ - Step 71640: {'lr': 0.0002731096732116093, 'samples': 13754880, 'steps': 71639, 'loss/train': 0.7485765218734741} 08/31/2021 02:07:25 - INFO - __main__ - Step 71641: {'lr': 0.0002731043891835299, 'samples': 13755072, 'steps': 71640, 'loss/train': 1.6550277471542358} 08/31/2021 02:07:26 - INFO - __main__ - Step 71642: {'lr': 0.00027309910514504, 'samples': 13755264, 'steps': 71641, 'loss/train': 0.508671224117279} 08/31/2021 02:07:27 - INFO - __main__ - Step 71643: {'lr': 0.00027309382109614206, 'samples': 13755456, 'steps': 71642, 'loss/train': 0.9960625767707825} 08/31/2021 02:07:28 - INFO - __main__ - Step 71644: {'lr': 0.00027308853703683834, 'samples': 13755648, 'steps': 71643, 'loss/train': 2.3481998443603516} 08/31/2021 02:07:28 - INFO - __main__ - Step 71645: {'lr': 0.0002730832529671314, 'samples': 13755840, 'steps': 71644, 'loss/train': 1.3443505764007568} 08/31/2021 02:07:29 - INFO - __main__ - Step 71646: {'lr': 0.0002730779688870234, 'samples': 13756032, 'steps': 71645, 'loss/train': 1.3004306554794312} 08/31/2021 02:07:29 - INFO - __main__ - Step 71647: {'lr': 0.00027307268479651687, 'samples': 13756224, 'steps': 71646, 'loss/train': 0.8702322244644165} 08/31/2021 02:07:29 - INFO - __main__ - Step 71648: {'lr': 0.0002730674006956141, 'samples': 13756416, 'steps': 71647, 'loss/train': 0.020478591322898865} 08/31/2021 02:07:32 - INFO - __main__ - Step 71649: {'lr': 0.0002730621165843175, 'samples': 13756608, 'steps': 71648, 'loss/train': 1.4505451917648315} 08/31/2021 02:07:32 - INFO - __main__ - Step 71650: {'lr': 0.0002730568324626295, 'samples': 13756800, 'steps': 71649, 'loss/train': 0.979577362537384} 08/31/2021 02:07:33 - INFO - __main__ - Step 71651: {'lr': 0.0002730515483305525, 'samples': 13756992, 'steps': 71650, 'loss/train': 0.7105475664138794} 08/31/2021 02:07:33 - INFO - __main__ - Step 71652: {'lr': 0.0002730462641880888, 'samples': 13757184, 'steps': 71651, 'loss/train': 1.315426230430603} 08/31/2021 02:07:33 - INFO - __main__ - Step 71653: {'lr': 0.00027304098003524073, 'samples': 13757376, 'steps': 71652, 'loss/train': 0.8702681660652161} 08/31/2021 02:07:34 - INFO - __main__ - Step 71654: {'lr': 0.0002730356958720108, 'samples': 13757568, 'steps': 71653, 'loss/train': 0.01745438203215599} 08/31/2021 02:07:35 - INFO - __main__ - Step 71655: {'lr': 0.0002730304116984014, 'samples': 13757760, 'steps': 71654, 'loss/train': 1.795942783355713} 08/31/2021 02:07:36 - INFO - __main__ - Step 71656: {'lr': 0.0002730251275144148, 'samples': 13757952, 'steps': 71655, 'loss/train': 1.5173219442367554} 08/31/2021 02:07:36 - INFO - __main__ - Step 71657: {'lr': 0.0002730198433200535, 'samples': 13758144, 'steps': 71656, 'loss/train': 1.1281017065048218} 08/31/2021 02:07:36 - INFO - __main__ - Step 71658: {'lr': 0.0002730145591153197, 'samples': 13758336, 'steps': 71657, 'loss/train': 1.3943544626235962} 08/31/2021 02:07:37 - INFO - __main__ - Step 71659: {'lr': 0.00027300927490021593, 'samples': 13758528, 'steps': 71658, 'loss/train': 1.3832721710205078} 08/31/2021 02:07:38 - INFO - __main__ - Step 71660: {'lr': 0.0002730039906747445, 'samples': 13758720, 'steps': 71659, 'loss/train': 1.9679970741271973} 08/31/2021 02:07:39 - INFO - __main__ - Step 71661: {'lr': 0.0002729987064389079, 'samples': 13758912, 'steps': 71660, 'loss/train': 1.374800205230713} 08/31/2021 02:07:39 - INFO - __main__ - Step 71662: {'lr': 0.00027299342219270844, 'samples': 13759104, 'steps': 71661, 'loss/train': 0.9698425531387329} 08/31/2021 02:07:39 - INFO - __main__ - Step 71663: {'lr': 0.0002729881379361485, 'samples': 13759296, 'steps': 71662, 'loss/train': 0.9200813174247742} 08/31/2021 02:07:40 - INFO - __main__ - Step 71664: {'lr': 0.0002729828536692304, 'samples': 13759488, 'steps': 71663, 'loss/train': 1.4195915460586548} 08/31/2021 02:07:41 - INFO - __main__ - Step 71665: {'lr': 0.00027297756939195664, 'samples': 13759680, 'steps': 71664, 'loss/train': 0.710800290107727} 08/31/2021 02:07:42 - INFO - __main__ - Step 71666: {'lr': 0.0002729722851043295, 'samples': 13759872, 'steps': 71665, 'loss/train': 1.3052873611450195} 08/31/2021 02:07:42 - INFO - __main__ - Step 71667: {'lr': 0.0002729670008063514, 'samples': 13760064, 'steps': 71666, 'loss/train': 1.015886664390564} 08/31/2021 02:07:42 - INFO - __main__ - Step 71668: {'lr': 0.0002729617164980247, 'samples': 13760256, 'steps': 71667, 'loss/train': 0.8362871408462524} 08/31/2021 02:07:43 - INFO - __main__ - Step 71669: {'lr': 0.0002729564321793519, 'samples': 13760448, 'steps': 71668, 'loss/train': 1.6861099004745483} 08/31/2021 02:07:44 - INFO - __main__ - Step 71670: {'lr': 0.0002729511478503353, 'samples': 13760640, 'steps': 71669, 'loss/train': 2.0778048038482666} 08/31/2021 02:07:45 - INFO - __main__ - Step 71671: {'lr': 0.0002729458635109771, 'samples': 13760832, 'steps': 71670, 'loss/train': 1.1251716613769531} 08/31/2021 02:07:45 - INFO - __main__ - Step 71672: {'lr': 0.00027294057916127997, 'samples': 13761024, 'steps': 71671, 'loss/train': 1.2687556743621826} 08/31/2021 02:07:45 - INFO - __main__ - Step 71673: {'lr': 0.0002729352948012461, 'samples': 13761216, 'steps': 71672, 'loss/train': 1.3064305782318115} 08/31/2021 02:07:46 - INFO - __main__ - Step 71674: {'lr': 0.000272930010430878, 'samples': 13761408, 'steps': 71673, 'loss/train': 0.5051161050796509} 08/31/2021 02:07:48 - INFO - __main__ - Step 71675: {'lr': 0.000272924726050178, 'samples': 13761600, 'steps': 71674, 'loss/train': 1.0426051616668701} 08/31/2021 02:07:48 - INFO - __main__ - Step 71676: {'lr': 0.0002729194416591485, 'samples': 13761792, 'steps': 71675, 'loss/train': 0.08880388736724854} 08/31/2021 02:07:48 - INFO - __main__ - Step 71677: {'lr': 0.00027291415725779177, 'samples': 13761984, 'steps': 71676, 'loss/train': 1.535243272781372} 08/31/2021 02:07:49 - INFO - __main__ - Step 71678: {'lr': 0.0002729088728461103, 'samples': 13762176, 'steps': 71677, 'loss/train': 1.3455761671066284} 08/31/2021 02:07:49 - INFO - __main__ - Step 71679: {'lr': 0.00027290358842410644, 'samples': 13762368, 'steps': 71678, 'loss/train': 1.7335540056228638} 08/31/2021 02:07:51 - INFO - __main__ - Step 71680: {'lr': 0.00027289830399178264, 'samples': 13762560, 'steps': 71679, 'loss/train': 0.9854430556297302} 08/31/2021 02:07:51 - INFO - __main__ - Step 71681: {'lr': 0.0002728930195491411, 'samples': 13762752, 'steps': 71680, 'loss/train': 1.7011522054672241} 08/31/2021 02:07:51 - INFO - __main__ - Step 71682: {'lr': 0.0002728877350961844, 'samples': 13762944, 'steps': 71681, 'loss/train': 1.424498200416565} 08/31/2021 02:07:52 - INFO - __main__ - Step 71683: {'lr': 0.00027288245063291483, 'samples': 13763136, 'steps': 71682, 'loss/train': 1.5046659708023071} 08/31/2021 02:07:52 - INFO - __main__ - Step 71684: {'lr': 0.00027287716615933476, 'samples': 13763328, 'steps': 71683, 'loss/train': 1.3174265623092651} 08/31/2021 02:07:53 - INFO - __main__ - Step 71685: {'lr': 0.0002728718816754466, 'samples': 13763520, 'steps': 71684, 'loss/train': 1.1983602046966553} 08/31/2021 02:07:54 - INFO - __main__ - Step 71686: {'lr': 0.0002728665971812527, 'samples': 13763712, 'steps': 71685, 'loss/train': 1.0949385166168213} 08/31/2021 02:07:54 - INFO - __main__ - Step 71687: {'lr': 0.0002728613126767556, 'samples': 13763904, 'steps': 71686, 'loss/train': 1.4161978960037231} 08/31/2021 02:07:55 - INFO - __main__ - Step 71688: {'lr': 0.0002728560281619574, 'samples': 13764096, 'steps': 71687, 'loss/train': 0.9788653254508972} 08/31/2021 02:07:55 - INFO - __main__ - Step 71689: {'lr': 0.0002728507436368607, 'samples': 13764288, 'steps': 71688, 'loss/train': 0.8851578235626221} 08/31/2021 02:07:56 - INFO - __main__ - Step 71690: {'lr': 0.00027284545910146775, 'samples': 13764480, 'steps': 71689, 'loss/train': 1.109228253364563} 08/31/2021 02:07:57 - INFO - __main__ - Step 71691: {'lr': 0.000272840174555781, 'samples': 13764672, 'steps': 71690, 'loss/train': 0.20024874806404114} 08/31/2021 02:07:57 - INFO - __main__ - Step 71692: {'lr': 0.0002728348899998028, 'samples': 13764864, 'steps': 71691, 'loss/train': 0.9764578938484192} 08/31/2021 02:07:58 - INFO - __main__ - Step 71693: {'lr': 0.00027282960543353565, 'samples': 13765056, 'steps': 71692, 'loss/train': 1.8569953441619873} 08/31/2021 02:07:58 - INFO - __main__ - Step 71694: {'lr': 0.00027282432085698173, 'samples': 13765248, 'steps': 71693, 'loss/train': 1.067812442779541} 08/31/2021 02:08:00 - INFO - __main__ - Step 71695: {'lr': 0.00027281903627014356, 'samples': 13765440, 'steps': 71694, 'loss/train': 1.3102929592132568} 08/31/2021 02:08:00 - INFO - __main__ - Step 71696: {'lr': 0.0002728137516730235, 'samples': 13765632, 'steps': 71695, 'loss/train': 1.6357355117797852} 08/31/2021 02:08:01 - INFO - __main__ - Step 71697: {'lr': 0.0002728084670656239, 'samples': 13765824, 'steps': 71696, 'loss/train': 0.3461426794528961} 08/31/2021 02:08:01 - INFO - __main__ - Step 71698: {'lr': 0.00027280318244794717, 'samples': 13766016, 'steps': 71697, 'loss/train': 0.7018738389015198} 08/31/2021 02:08:01 - INFO - __main__ - Step 71699: {'lr': 0.0002727978978199956, 'samples': 13766208, 'steps': 71698, 'loss/train': 0.06014474108815193} 08/31/2021 02:08:02 - INFO - __main__ - Step 71700: {'lr': 0.00027279261318177174, 'samples': 13766400, 'steps': 71699, 'loss/train': 0.019275330007076263} 08/31/2021 02:08:04 - INFO - __main__ - Step 71701: {'lr': 0.0002727873285332778, 'samples': 13766592, 'steps': 71700, 'loss/train': 0.5112018585205078} 08/31/2021 02:08:04 - INFO - __main__ - Step 71702: {'lr': 0.00027278204387451633, 'samples': 13766784, 'steps': 71701, 'loss/train': 0.8698492646217346} 08/31/2021 02:08:04 - INFO - __main__ - Step 71703: {'lr': 0.0002727767592054896, 'samples': 13766976, 'steps': 71702, 'loss/train': 1.0740588903427124} 08/31/2021 02:08:05 - INFO - __main__ - Step 71704: {'lr': 0.0002727714745262, 'samples': 13767168, 'steps': 71703, 'loss/train': 1.2821900844573975} 08/31/2021 02:08:05 - INFO - __main__ - Step 71705: {'lr': 0.0002727661898366499, 'samples': 13767360, 'steps': 71704, 'loss/train': 1.2952518463134766} 08/31/2021 02:08:05 - INFO - __main__ - Step 71706: {'lr': 0.00027276090513684176, 'samples': 13767552, 'steps': 71705, 'loss/train': 0.6305691599845886} 08/31/2021 02:08:08 - INFO - __main__ - Step 71707: {'lr': 0.0002727556204267779, 'samples': 13767744, 'steps': 71706, 'loss/train': 1.7624191045761108} 08/31/2021 02:08:08 - INFO - __main__ - Step 71708: {'lr': 0.0002727503357064606, 'samples': 13767936, 'steps': 71707, 'loss/train': 1.3695639371871948} 08/31/2021 02:08:09 - INFO - __main__ - Step 71709: {'lr': 0.0002727450509758925, 'samples': 13768128, 'steps': 71708, 'loss/train': 1.3451288938522339} 08/31/2021 02:08:09 - INFO - __main__ - Step 71710: {'lr': 0.0002727397662350758, 'samples': 13768320, 'steps': 71709, 'loss/train': 0.016922084614634514} 08/31/2021 02:08:09 - INFO - __main__ - Step 71711: {'lr': 0.0002727344814840129, 'samples': 13768512, 'steps': 71710, 'loss/train': 0.45692306756973267} 08/31/2021 02:08:10 - INFO - __main__ - Step 71712: {'lr': 0.00027272919672270614, 'samples': 13768704, 'steps': 71711, 'loss/train': 1.5734871625900269} 08/31/2021 02:08:12 - INFO - __main__ - Step 71713: {'lr': 0.000272723911951158, 'samples': 13768896, 'steps': 71712, 'loss/train': 0.9437532424926758} 08/31/2021 02:08:12 - INFO - __main__ - Step 71714: {'lr': 0.0002727186271693707, 'samples': 13769088, 'steps': 71713, 'loss/train': 1.1498538255691528} 08/31/2021 02:08:13 - INFO - __main__ - Step 71715: {'lr': 0.0002727133423773469, 'samples': 13769280, 'steps': 71714, 'loss/train': 0.9020752906799316} 08/31/2021 02:08:13 - INFO - __main__ - Step 71716: {'lr': 0.0002727080575750888, 'samples': 13769472, 'steps': 71715, 'loss/train': 1.013679027557373} 08/31/2021 02:08:13 - INFO - __main__ - Step 71717: {'lr': 0.00027270277276259875, 'samples': 13769664, 'steps': 71716, 'loss/train': 1.144629716873169} 08/31/2021 02:08:14 - INFO - __main__ - Step 71718: {'lr': 0.00027269748793987917, 'samples': 13769856, 'steps': 71717, 'loss/train': 1.3810434341430664} 08/31/2021 02:08:15 - INFO - __main__ - Step 71719: {'lr': 0.0002726922031069325, 'samples': 13770048, 'steps': 71718, 'loss/train': 0.6113247871398926} 08/31/2021 02:08:16 - INFO - __main__ - Step 71720: {'lr': 0.000272686918263761, 'samples': 13770240, 'steps': 71719, 'loss/train': 1.208774447441101} 08/31/2021 02:08:16 - INFO - __main__ - Step 71721: {'lr': 0.00027268163341036717, 'samples': 13770432, 'steps': 71720, 'loss/train': 1.5397899150848389} 08/31/2021 02:08:17 - INFO - __main__ - Step 71722: {'lr': 0.0002726763485467533, 'samples': 13770624, 'steps': 71721, 'loss/train': 0.01616523042321205} 08/31/2021 02:08:17 - INFO - __main__ - Step 71723: {'lr': 0.00027267106367292196, 'samples': 13770816, 'steps': 71722, 'loss/train': 0.01591184362769127} 08/31/2021 02:08:17 - INFO - __main__ - Step 71724: {'lr': 0.0002726657787888753, 'samples': 13771008, 'steps': 71723, 'loss/train': 1.7955650091171265} 08/31/2021 02:08:19 - INFO - __main__ - Step 71725: {'lr': 0.0002726604938946158, 'samples': 13771200, 'steps': 71724, 'loss/train': 1.3053503036499023} 08/31/2021 02:08:19 - INFO - __main__ - Step 71726: {'lr': 0.00027265520899014573, 'samples': 13771392, 'steps': 71725, 'loss/train': 1.5568430423736572} 08/31/2021 02:08:20 - INFO - __main__ - Step 71727: {'lr': 0.0002726499240754677, 'samples': 13771584, 'steps': 71726, 'loss/train': 1.3267309665679932} 08/31/2021 02:08:20 - INFO - __main__ - Step 71728: {'lr': 0.0002726446391505839, 'samples': 13771776, 'steps': 71727, 'loss/train': 1.3530330657958984} 08/31/2021 02:08:20 - INFO - __main__ - Step 71729: {'lr': 0.00027263935421549686, 'samples': 13771968, 'steps': 71728, 'loss/train': 0.9528221487998962} 08/31/2021 02:08:22 - INFO - __main__ - Step 71730: {'lr': 0.00027263406927020877, 'samples': 13772160, 'steps': 71729, 'loss/train': 1.069585919380188} 08/31/2021 02:08:22 - INFO - __main__ - Step 71731: {'lr': 0.00027262878431472213, 'samples': 13772352, 'steps': 71730, 'loss/train': 1.4378180503845215} 08/31/2021 02:08:23 - INFO - __main__ - Step 71732: {'lr': 0.0002726234993490393, 'samples': 13772544, 'steps': 71731, 'loss/train': 1.6253403425216675} 08/31/2021 02:08:23 - INFO - __main__ - Step 71733: {'lr': 0.00027261821437316275, 'samples': 13772736, 'steps': 71732, 'loss/train': 2.3164455890655518} 08/31/2021 02:08:23 - INFO - __main__ - Step 71734: {'lr': 0.0002726129293870948, 'samples': 13772928, 'steps': 71733, 'loss/train': 0.17366835474967957} 08/31/2021 02:08:25 - INFO - __main__ - Step 71735: {'lr': 0.0002726076443908377, 'samples': 13773120, 'steps': 71734, 'loss/train': 1.4579639434814453} 08/31/2021 02:08:25 - INFO - __main__ - Step 71736: {'lr': 0.00027260235938439403, 'samples': 13773312, 'steps': 71735, 'loss/train': 1.7784819602966309} 08/31/2021 02:08:26 - INFO - __main__ - Step 71737: {'lr': 0.00027259707436776603, 'samples': 13773504, 'steps': 71736, 'loss/train': 1.5078129768371582} 08/31/2021 02:08:26 - INFO - __main__ - Step 71738: {'lr': 0.00027259178934095613, 'samples': 13773696, 'steps': 71737, 'loss/train': 1.2522634267807007} 08/31/2021 02:08:26 - INFO - __main__ - Step 71739: {'lr': 0.00027258650430396676, 'samples': 13773888, 'steps': 71738, 'loss/train': 1.8538726568222046} 08/31/2021 02:08:28 - INFO - __main__ - Step 71740: {'lr': 0.00027258121925680025, 'samples': 13774080, 'steps': 71739, 'loss/train': 0.7686343193054199} 08/31/2021 02:08:28 - INFO - __main__ - Step 71741: {'lr': 0.000272575934199459, 'samples': 13774272, 'steps': 71740, 'loss/train': 1.2403273582458496} 08/31/2021 02:08:29 - INFO - __main__ - Step 71742: {'lr': 0.0002725706491319453, 'samples': 13774464, 'steps': 71741, 'loss/train': 0.9853551983833313} 08/31/2021 02:08:29 - INFO - __main__ - Step 71743: {'lr': 0.00027256536405426173, 'samples': 13774656, 'steps': 71742, 'loss/train': 0.8578416705131531} 08/31/2021 02:08:29 - INFO - __main__ - Step 71744: {'lr': 0.00027256007896641054, 'samples': 13774848, 'steps': 71743, 'loss/train': 0.3816549479961395} 08/31/2021 02:08:31 - INFO - __main__ - Step 71745: {'lr': 0.0002725547938683941, 'samples': 13775040, 'steps': 71744, 'loss/train': 1.9963775873184204} 08/31/2021 02:08:31 - INFO - __main__ - Step 71746: {'lr': 0.0002725495087602148, 'samples': 13775232, 'steps': 71745, 'loss/train': 1.5862057209014893} 08/31/2021 02:08:32 - INFO - __main__ - Step 71747: {'lr': 0.00027254422364187504, 'samples': 13775424, 'steps': 71746, 'loss/train': 1.2465087175369263} 08/31/2021 02:08:32 - INFO - __main__ - Step 71748: {'lr': 0.0002725389385133772, 'samples': 13775616, 'steps': 71747, 'loss/train': 1.8165216445922852} 08/31/2021 02:08:32 - INFO - __main__ - Step 71749: {'lr': 0.00027253365337472367, 'samples': 13775808, 'steps': 71748, 'loss/train': 0.789237916469574} 08/31/2021 02:08:33 - INFO - __main__ - Step 71750: {'lr': 0.00027252836822591684, 'samples': 13776000, 'steps': 71749, 'loss/train': 1.2203015089035034} 08/31/2021 02:08:34 - INFO - __main__ - Step 71751: {'lr': 0.0002725230830669591, 'samples': 13776192, 'steps': 71750, 'loss/train': 1.1641241312026978} 08/31/2021 02:08:35 - INFO - __main__ - Step 71752: {'lr': 0.0002725177978978527, 'samples': 13776384, 'steps': 71751, 'loss/train': 1.851900577545166} 08/31/2021 02:08:35 - INFO - __main__ - Step 71753: {'lr': 0.00027251251271860025, 'samples': 13776576, 'steps': 71752, 'loss/train': 1.1997767686843872} 08/31/2021 02:08:35 - INFO - __main__ - Step 71754: {'lr': 0.00027250722752920393, 'samples': 13776768, 'steps': 71753, 'loss/train': 3.09153413772583} 08/31/2021 02:08:36 - INFO - __main__ - Step 71755: {'lr': 0.00027250194232966626, 'samples': 13776960, 'steps': 71754, 'loss/train': 1.2197706699371338} 08/31/2021 02:08:37 - INFO - __main__ - Step 71756: {'lr': 0.00027249665711998955, 'samples': 13777152, 'steps': 71755, 'loss/train': 1.3517003059387207} 08/31/2021 02:08:38 - INFO - __main__ - Step 71757: {'lr': 0.00027249137190017616, 'samples': 13777344, 'steps': 71756, 'loss/train': 1.398971438407898} 08/31/2021 02:08:38 - INFO - __main__ - Step 71758: {'lr': 0.0002724860866702285, 'samples': 13777536, 'steps': 71757, 'loss/train': 1.5528390407562256} 08/31/2021 02:08:38 - INFO - __main__ - Step 71759: {'lr': 0.000272480801430149, 'samples': 13777728, 'steps': 71758, 'loss/train': 0.21326148509979248} 08/31/2021 02:08:39 - INFO - __main__ - Step 71760: {'lr': 0.00027247551617993993, 'samples': 13777920, 'steps': 71759, 'loss/train': 1.3945330381393433} 08/31/2021 02:08:41 - INFO - __main__ - Step 71761: {'lr': 0.0002724702309196038, 'samples': 13778112, 'steps': 71760, 'loss/train': 1.1453474760055542} 08/31/2021 02:08:42 - INFO - __main__ - Step 71762: {'lr': 0.0002724649456491429, 'samples': 13778304, 'steps': 71761, 'loss/train': 1.1333286762237549} 08/31/2021 02:08:42 - INFO - __main__ - Step 71763: {'lr': 0.00027245966036855965, 'samples': 13778496, 'steps': 71762, 'loss/train': 0.8596428632736206} 08/31/2021 02:08:42 - INFO - __main__ - Step 71764: {'lr': 0.00027245437507785646, 'samples': 13778688, 'steps': 71763, 'loss/train': 0.8237727284431458} 08/31/2021 02:08:43 - INFO - __main__ - Step 71765: {'lr': 0.00027244908977703565, 'samples': 13778880, 'steps': 71764, 'loss/train': 0.06685718894004822} 08/31/2021 02:08:44 - INFO - __main__ - Step 71766: {'lr': 0.0002724438044660996, 'samples': 13779072, 'steps': 71765, 'loss/train': 1.634225845336914} 08/31/2021 02:08:44 - INFO - __main__ - Step 71767: {'lr': 0.00027243851914505074, 'samples': 13779264, 'steps': 71766, 'loss/train': 1.1004072427749634} 08/31/2021 02:08:45 - INFO - __main__ - Step 71768: {'lr': 0.0002724332338138914, 'samples': 13779456, 'steps': 71767, 'loss/train': 0.9386444687843323} 08/31/2021 02:08:45 - INFO - __main__ - Step 71769: {'lr': 0.00027242794847262406, 'samples': 13779648, 'steps': 71768, 'loss/train': 1.2253471612930298} 08/31/2021 02:08:46 - INFO - __main__ - Step 71770: {'lr': 0.000272422663121251, 'samples': 13779840, 'steps': 71769, 'loss/train': 1.1340742111206055} 08/31/2021 02:08:47 - INFO - __main__ - Step 71771: {'lr': 0.0002724173777597746, 'samples': 13780032, 'steps': 71770, 'loss/train': 1.6603312492370605} 08/31/2021 02:08:48 - INFO - __main__ - Step 71772: {'lr': 0.00027241209238819733, 'samples': 13780224, 'steps': 71771, 'loss/train': 0.7378440499305725} 08/31/2021 02:08:48 - INFO - __main__ - Step 71773: {'lr': 0.0002724068070065215, 'samples': 13780416, 'steps': 71772, 'loss/train': 0.9530391693115234} 08/31/2021 02:08:48 - INFO - __main__ - Step 71774: {'lr': 0.0002724015216147495, 'samples': 13780608, 'steps': 71773, 'loss/train': 0.14303044974803925} 08/31/2021 02:08:49 - INFO - __main__ - Step 71775: {'lr': 0.0002723962362128837, 'samples': 13780800, 'steps': 71774, 'loss/train': 2.206939220428467} 08/31/2021 02:08:50 - INFO - __main__ - Step 71776: {'lr': 0.0002723909508009265, 'samples': 13780992, 'steps': 71775, 'loss/train': 1.2498908042907715} 08/31/2021 02:08:51 - INFO - __main__ - Step 71777: {'lr': 0.00027238566537888035, 'samples': 13781184, 'steps': 71776, 'loss/train': 0.8863233327865601} 08/31/2021 02:08:51 - INFO - __main__ - Step 71778: {'lr': 0.0002723803799467475, 'samples': 13781376, 'steps': 71777, 'loss/train': 2.043297529220581} 08/31/2021 02:08:51 - INFO - __main__ - Step 71779: {'lr': 0.0002723750945045304, 'samples': 13781568, 'steps': 71778, 'loss/train': 1.5111397504806519} 08/31/2021 02:08:52 - INFO - __main__ - Step 71780: {'lr': 0.00027236980905223147, 'samples': 13781760, 'steps': 71779, 'loss/train': 1.4046707153320312} 08/31/2021 02:08:54 - INFO - __main__ - Step 71781: {'lr': 0.00027236452358985304, 'samples': 13781952, 'steps': 71780, 'loss/train': 1.0233914852142334} 08/31/2021 02:08:54 - INFO - __main__ - Step 71782: {'lr': 0.00027235923811739745, 'samples': 13782144, 'steps': 71781, 'loss/train': 0.21773214638233185} 08/31/2021 02:08:54 - INFO - __main__ - Step 71783: {'lr': 0.0002723539526348671, 'samples': 13782336, 'steps': 71782, 'loss/train': 1.3017206192016602} 08/31/2021 02:08:55 - INFO - __main__ - Step 71784: {'lr': 0.0002723486671422645, 'samples': 13782528, 'steps': 71783, 'loss/train': 1.6972883939743042} 08/31/2021 02:08:55 - INFO - __main__ - Step 71785: {'lr': 0.0002723433816395919, 'samples': 13782720, 'steps': 71784, 'loss/train': 1.133371114730835} 08/31/2021 02:08:57 - INFO - __main__ - Step 71786: {'lr': 0.00027233809612685177, 'samples': 13782912, 'steps': 71785, 'loss/train': 1.6089400053024292} 08/31/2021 02:08:57 - INFO - __main__ - Step 71787: {'lr': 0.00027233281060404636, 'samples': 13783104, 'steps': 71786, 'loss/train': 1.575496792793274} 08/31/2021 02:08:57 - INFO - __main__ - Step 71788: {'lr': 0.00027232752507117816, 'samples': 13783296, 'steps': 71787, 'loss/train': 1.4457038640975952} 08/31/2021 02:08:58 - INFO - __main__ - Step 71789: {'lr': 0.00027232223952824953, 'samples': 13783488, 'steps': 71788, 'loss/train': 1.1541671752929688} 08/31/2021 02:08:58 - INFO - __main__ - Step 71790: {'lr': 0.0002723169539752628, 'samples': 13783680, 'steps': 71789, 'loss/train': 0.18693362176418304} 08/31/2021 02:08:58 - INFO - __main__ - Step 71791: {'lr': 0.0002723116684122205, 'samples': 13783872, 'steps': 71790, 'loss/train': 1.0650616884231567} 08/31/2021 02:09:00 - INFO - __main__ - Step 71792: {'lr': 0.0002723063828391248, 'samples': 13784064, 'steps': 71791, 'loss/train': 0.6598535776138306} 08/31/2021 02:09:01 - INFO - __main__ - Step 71793: {'lr': 0.00027230109725597825, 'samples': 13784256, 'steps': 71792, 'loss/train': 1.5486494302749634} 08/31/2021 02:09:01 - INFO - __main__ - Step 71794: {'lr': 0.00027229581166278313, 'samples': 13784448, 'steps': 71793, 'loss/train': 2.352980375289917} 08/31/2021 02:09:01 - INFO - __main__ - Step 71795: {'lr': 0.00027229052605954186, 'samples': 13784640, 'steps': 71794, 'loss/train': 1.4779479503631592} 08/31/2021 02:09:02 - INFO - __main__ - Step 71796: {'lr': 0.0002722852404462568, 'samples': 13784832, 'steps': 71795, 'loss/train': 0.8203113079071045} 08/31/2021 02:09:03 - INFO - __main__ - Step 71797: {'lr': 0.00027227995482293046, 'samples': 13785024, 'steps': 71796, 'loss/train': 0.37125325202941895} 08/31/2021 02:09:04 - INFO - __main__ - Step 71798: {'lr': 0.000272274669189565, 'samples': 13785216, 'steps': 71797, 'loss/train': 0.7688640356063843} 08/31/2021 02:09:04 - INFO - __main__ - Step 71799: {'lr': 0.000272269383546163, 'samples': 13785408, 'steps': 71798, 'loss/train': 1.5322670936584473} 08/31/2021 02:09:04 - INFO - __main__ - Step 71800: {'lr': 0.0002722640978927267, 'samples': 13785600, 'steps': 71799, 'loss/train': 1.9150255918502808} 08/31/2021 02:09:05 - INFO - __main__ - Step 71801: {'lr': 0.0002722588122292585, 'samples': 13785792, 'steps': 71800, 'loss/train': 1.2476016283035278} 08/31/2021 02:09:06 - INFO - __main__ - Step 71802: {'lr': 0.00027225352655576093, 'samples': 13785984, 'steps': 71801, 'loss/train': 1.5951107740402222} 08/31/2021 02:09:07 - INFO - __main__ - Step 71803: {'lr': 0.0002722482408722363, 'samples': 13786176, 'steps': 71802, 'loss/train': 0.9490998983383179} 08/31/2021 02:09:07 - INFO - __main__ - Step 71804: {'lr': 0.0002722429551786868, 'samples': 13786368, 'steps': 71803, 'loss/train': 1.4838277101516724} 08/31/2021 02:09:07 - INFO - __main__ - Step 71805: {'lr': 0.0002722376694751151, 'samples': 13786560, 'steps': 71804, 'loss/train': 1.1185781955718994} 08/31/2021 02:09:08 - INFO - __main__ - Step 71806: {'lr': 0.0002722323837615234, 'samples': 13786752, 'steps': 71805, 'loss/train': 1.0753403902053833} 08/31/2021 02:09:09 - INFO - __main__ - Step 71807: {'lr': 0.00027222709803791404, 'samples': 13786944, 'steps': 71806, 'loss/train': 1.1032284498214722} 08/31/2021 02:09:10 - INFO - __main__ - Step 71808: {'lr': 0.0002722218123042896, 'samples': 13787136, 'steps': 71807, 'loss/train': 1.5455331802368164} 08/31/2021 02:09:10 - INFO - __main__ - Step 71809: {'lr': 0.0002722165265606523, 'samples': 13787328, 'steps': 71808, 'loss/train': 1.9509400129318237} 08/31/2021 02:09:10 - INFO - __main__ - Step 71810: {'lr': 0.00027221124080700467, 'samples': 13787520, 'steps': 71809, 'loss/train': 1.1802167892456055} 08/31/2021 02:09:11 - INFO - __main__ - Step 71811: {'lr': 0.00027220595504334896, 'samples': 13787712, 'steps': 71810, 'loss/train': 1.7279623746871948} 08/31/2021 02:09:13 - INFO - __main__ - Step 71812: {'lr': 0.0002722006692696875, 'samples': 13787904, 'steps': 71811, 'loss/train': 0.3353756368160248} 08/31/2021 02:09:13 - INFO - __main__ - Step 71813: {'lr': 0.00027219538348602286, 'samples': 13788096, 'steps': 71812, 'loss/train': 1.3684765100479126} 08/31/2021 02:09:13 - INFO - __main__ - Step 71814: {'lr': 0.00027219009769235725, 'samples': 13788288, 'steps': 71813, 'loss/train': 0.03623883053660393} 08/31/2021 02:09:14 - INFO - __main__ - Step 71815: {'lr': 0.0002721848118886931, 'samples': 13788480, 'steps': 71814, 'loss/train': 0.9971165060997009} 08/31/2021 02:09:14 - INFO - __main__ - Step 71816: {'lr': 0.0002721795260750329, 'samples': 13788672, 'steps': 71815, 'loss/train': 0.5264564752578735} 08/31/2021 02:09:16 - INFO - __main__ - Step 71817: {'lr': 0.000272174240251379, 'samples': 13788864, 'steps': 71816, 'loss/train': 1.7824957370758057} 08/31/2021 02:09:17 - INFO - __main__ - Step 71818: {'lr': 0.00027216895441773363, 'samples': 13789056, 'steps': 71817, 'loss/train': 1.2448334693908691} 08/31/2021 02:09:17 - INFO - __main__ - Step 71819: {'lr': 0.0002721636685740993, 'samples': 13789248, 'steps': 71818, 'loss/train': 1.3212934732437134} 08/31/2021 02:09:17 - INFO - __main__ - Step 71820: {'lr': 0.0002721583827204784, 'samples': 13789440, 'steps': 71819, 'loss/train': 0.7498018145561218} 08/31/2021 02:09:18 - INFO - __main__ - Step 71821: {'lr': 0.00027215309685687324, 'samples': 13789632, 'steps': 71820, 'loss/train': 1.3428144454956055} 08/31/2021 02:09:20 - INFO - __main__ - Step 71822: {'lr': 0.00027214781098328615, 'samples': 13789824, 'steps': 71821, 'loss/train': 1.626422643661499} 08/31/2021 02:09:20 - INFO - __main__ - Step 71823: {'lr': 0.0002721425250997197, 'samples': 13790016, 'steps': 71822, 'loss/train': 1.1016721725463867} 08/31/2021 02:09:21 - INFO - __main__ - Step 71824: {'lr': 0.00027213723920617623, 'samples': 13790208, 'steps': 71823, 'loss/train': 0.031574640423059464} 08/31/2021 02:09:21 - INFO - __main__ - Step 71825: {'lr': 0.00027213195330265795, 'samples': 13790400, 'steps': 71824, 'loss/train': 1.5541096925735474} 08/31/2021 02:09:21 - INFO - __main__ - Step 71826: {'lr': 0.00027212666738916734, 'samples': 13790592, 'steps': 71825, 'loss/train': 0.04841599240899086} 08/31/2021 02:09:22 - INFO - __main__ - Step 71827: {'lr': 0.00027212138146570685, 'samples': 13790784, 'steps': 71826, 'loss/train': 0.7800121903419495} 08/31/2021 02:09:23 - INFO - __main__ - Step 71828: {'lr': 0.0002721160955322788, 'samples': 13790976, 'steps': 71827, 'loss/train': 1.1219667196273804} 08/31/2021 02:09:24 - INFO - __main__ - Step 71829: {'lr': 0.00027211080958888556, 'samples': 13791168, 'steps': 71828, 'loss/train': 1.0483545064926147} 08/31/2021 02:09:24 - INFO - __main__ - Step 71830: {'lr': 0.0002721055236355296, 'samples': 13791360, 'steps': 71829, 'loss/train': 1.3974030017852783} 08/31/2021 02:09:24 - INFO - __main__ - Step 71831: {'lr': 0.00027210023767221313, 'samples': 13791552, 'steps': 71830, 'loss/train': 0.7880610227584839} 08/31/2021 02:09:25 - INFO - __main__ - Step 71832: {'lr': 0.00027209495169893875, 'samples': 13791744, 'steps': 71831, 'loss/train': 0.7188607454299927} 08/31/2021 02:09:26 - INFO - __main__ - Step 71833: {'lr': 0.00027208966571570857, 'samples': 13791936, 'steps': 71832, 'loss/train': 1.1963181495666504} 08/31/2021 02:09:26 - INFO - __main__ - Step 71834: {'lr': 0.00027208437972252525, 'samples': 13792128, 'steps': 71833, 'loss/train': 1.4966095685958862} 08/31/2021 02:09:27 - INFO - __main__ - Step 71835: {'lr': 0.00027207909371939097, 'samples': 13792320, 'steps': 71834, 'loss/train': 0.7905936241149902} 08/31/2021 02:09:27 - INFO - __main__ - Step 71836: {'lr': 0.00027207380770630826, 'samples': 13792512, 'steps': 71835, 'loss/train': 0.926896333694458} 08/31/2021 02:09:27 - INFO - __main__ - Step 71837: {'lr': 0.00027206852168327946, 'samples': 13792704, 'steps': 71836, 'loss/train': 0.8145347237586975} 08/31/2021 02:09:29 - INFO - __main__ - Step 71838: {'lr': 0.0002720632356503069, 'samples': 13792896, 'steps': 71837, 'loss/train': 1.4145678281784058} 08/31/2021 02:09:30 - INFO - __main__ - Step 71839: {'lr': 0.00027205794960739296, 'samples': 13793088, 'steps': 71838, 'loss/train': 0.6460774540901184} 08/31/2021 02:09:30 - INFO - __main__ - Step 71840: {'lr': 0.00027205266355454, 'samples': 13793280, 'steps': 71839, 'loss/train': 1.3290339708328247} 08/31/2021 02:09:30 - INFO - __main__ - Step 71841: {'lr': 0.00027204737749175046, 'samples': 13793472, 'steps': 71840, 'loss/train': 0.8300988078117371} 08/31/2021 02:09:31 - INFO - __main__ - Step 71842: {'lr': 0.00027204209141902676, 'samples': 13793664, 'steps': 71841, 'loss/train': 1.169360876083374} 08/31/2021 02:09:32 - INFO - __main__ - Step 71843: {'lr': 0.0002720368053363712, 'samples': 13793856, 'steps': 71842, 'loss/train': 0.11396960914134979} 08/31/2021 02:09:33 - INFO - __main__ - Step 71844: {'lr': 0.00027203151924378626, 'samples': 13794048, 'steps': 71843, 'loss/train': 1.4842778444290161} 08/31/2021 02:09:33 - INFO - __main__ - Step 71845: {'lr': 0.0002720262331412742, 'samples': 13794240, 'steps': 71844, 'loss/train': 1.6009315252304077} 08/31/2021 02:09:33 - INFO - __main__ - Step 71846: {'lr': 0.0002720209470288375, 'samples': 13794432, 'steps': 71845, 'loss/train': 0.16520129144191742} 08/31/2021 02:09:34 - INFO - __main__ - Step 71847: {'lr': 0.00027201566090647843, 'samples': 13794624, 'steps': 71846, 'loss/train': 0.41732698678970337} 08/31/2021 02:09:35 - INFO - __main__ - Step 71848: {'lr': 0.00027201037477419957, 'samples': 13794816, 'steps': 71847, 'loss/train': 1.0788354873657227} 08/31/2021 02:09:36 - INFO - __main__ - Step 71849: {'lr': 0.000272005088632003, 'samples': 13795008, 'steps': 71848, 'loss/train': 0.8886075019836426} 08/31/2021 02:09:36 - INFO - __main__ - Step 71850: {'lr': 0.0002719998024798915, 'samples': 13795200, 'steps': 71849, 'loss/train': 1.1929460763931274} 08/31/2021 02:09:36 - INFO - __main__ - Step 71851: {'lr': 0.00027199451631786705, 'samples': 13795392, 'steps': 71850, 'loss/train': 0.6693491339683533} 08/31/2021 02:09:37 - INFO - __main__ - Step 71852: {'lr': 0.00027198923014593225, 'samples': 13795584, 'steps': 71851, 'loss/train': 1.514860987663269} 08/31/2021 02:09:37 - INFO - __main__ - Step 71853: {'lr': 0.0002719839439640894, 'samples': 13795776, 'steps': 71852, 'loss/train': 1.0255705118179321} 08/31/2021 02:09:39 - INFO - __main__ - Step 71854: {'lr': 0.00027197865777234097, 'samples': 13795968, 'steps': 71853, 'loss/train': 1.4749382734298706} 08/31/2021 02:09:39 - INFO - __main__ - Step 71855: {'lr': 0.00027197337157068937, 'samples': 13796160, 'steps': 71854, 'loss/train': 0.1670232117176056} 08/31/2021 02:09:39 - INFO - __main__ - Step 71856: {'lr': 0.0002719680853591368, 'samples': 13796352, 'steps': 71855, 'loss/train': 1.066933512687683} 08/31/2021 02:09:40 - INFO - __main__ - Step 71857: {'lr': 0.00027196279913768587, 'samples': 13796544, 'steps': 71856, 'loss/train': 1.617854118347168} 08/31/2021 02:09:40 - INFO - __main__ - Step 71858: {'lr': 0.00027195751290633874, 'samples': 13796736, 'steps': 71857, 'loss/train': 1.1576604843139648} 08/31/2021 02:09:42 - INFO - __main__ - Step 71859: {'lr': 0.0002719522266650979, 'samples': 13796928, 'steps': 71858, 'loss/train': 1.6109875440597534} 08/31/2021 02:09:42 - INFO - __main__ - Step 71860: {'lr': 0.00027194694041396574, 'samples': 13797120, 'steps': 71859, 'loss/train': 0.7469168305397034} 08/31/2021 02:09:42 - INFO - __main__ - Step 71861: {'lr': 0.0002719416541529446, 'samples': 13797312, 'steps': 71860, 'loss/train': 1.3880442380905151} 08/31/2021 02:09:43 - INFO - __main__ - Step 71862: {'lr': 0.0002719363678820369, 'samples': 13797504, 'steps': 71861, 'loss/train': 1.3394416570663452} 08/31/2021 02:09:43 - INFO - __main__ - Step 71863: {'lr': 0.000271931081601245, 'samples': 13797696, 'steps': 71862, 'loss/train': 1.2015798091888428} 08/31/2021 02:09:45 - INFO - __main__ - Step 71864: {'lr': 0.00027192579531057137, 'samples': 13797888, 'steps': 71863, 'loss/train': 1.2618608474731445} 08/31/2021 02:09:45 - INFO - __main__ - Step 71865: {'lr': 0.0002719205090100183, 'samples': 13798080, 'steps': 71864, 'loss/train': 1.5206608772277832} 08/31/2021 02:09:45 - INFO - __main__ - Step 71866: {'lr': 0.0002719152226995881, 'samples': 13798272, 'steps': 71865, 'loss/train': 1.453237771987915} 08/31/2021 02:09:46 - INFO - __main__ - Step 71867: {'lr': 0.0002719099363792833, 'samples': 13798464, 'steps': 71866, 'loss/train': 0.8926674723625183} 08/31/2021 02:09:46 - INFO - __main__ - Step 71868: {'lr': 0.0002719046500491062, 'samples': 13798656, 'steps': 71867, 'loss/train': 1.5233970880508423} 08/31/2021 02:09:48 - INFO - __main__ - Step 71869: {'lr': 0.0002718993637090592, 'samples': 13798848, 'steps': 71868, 'loss/train': 1.435213565826416} 08/31/2021 02:09:49 - INFO - __main__ - Step 71870: {'lr': 0.0002718940773591447, 'samples': 13799040, 'steps': 71869, 'loss/train': 0.18652428686618805} 08/31/2021 02:09:49 - INFO - __main__ - Step 71871: {'lr': 0.00027188879099936515, 'samples': 13799232, 'steps': 71870, 'loss/train': 1.088565468788147} 08/31/2021 02:09:49 - INFO - __main__ - Step 71872: {'lr': 0.0002718835046297227, 'samples': 13799424, 'steps': 71871, 'loss/train': 1.2797343730926514} 08/31/2021 02:09:50 - INFO - __main__ - Step 71873: {'lr': 0.00027187821825021995, 'samples': 13799616, 'steps': 71872, 'loss/train': 1.255205512046814} 08/31/2021 02:09:50 - INFO - __main__ - Step 71874: {'lr': 0.0002718729318608592, 'samples': 13799808, 'steps': 71873, 'loss/train': 1.2216391563415527} 08/31/2021 02:09:52 - INFO - __main__ - Step 71875: {'lr': 0.0002718676454616428, 'samples': 13800000, 'steps': 71874, 'loss/train': 1.0651239156723022} 08/31/2021 02:09:52 - INFO - __main__ - Step 71876: {'lr': 0.00027186235905257326, 'samples': 13800192, 'steps': 71875, 'loss/train': 1.1758140325546265} 08/31/2021 02:09:52 - INFO - __main__ - Step 71877: {'lr': 0.0002718570726336529, 'samples': 13800384, 'steps': 71876, 'loss/train': 1.3456740379333496} 08/31/2021 02:09:53 - INFO - __main__ - Step 71878: {'lr': 0.00027185178620488406, 'samples': 13800576, 'steps': 71877, 'loss/train': 1.367003083229065} 08/31/2021 02:09:53 - INFO - __main__ - Step 71879: {'lr': 0.00027184649976626907, 'samples': 13800768, 'steps': 71878, 'loss/train': 0.8910170793533325} 08/31/2021 02:09:55 - INFO - __main__ - Step 71880: {'lr': 0.0002718412133178104, 'samples': 13800960, 'steps': 71879, 'loss/train': 1.0664637088775635} 08/31/2021 02:09:55 - INFO - __main__ - Step 71881: {'lr': 0.0002718359268595105, 'samples': 13801152, 'steps': 71880, 'loss/train': 0.9118184447288513} 08/31/2021 02:09:55 - INFO - __main__ - Step 71882: {'lr': 0.0002718306403913716, 'samples': 13801344, 'steps': 71881, 'loss/train': 1.2467832565307617} 08/31/2021 02:09:56 - INFO - __main__ - Step 71883: {'lr': 0.0002718253539133961, 'samples': 13801536, 'steps': 71882, 'loss/train': 1.2186129093170166} 08/31/2021 02:09:56 - INFO - __main__ - Step 71884: {'lr': 0.0002718200674255865, 'samples': 13801728, 'steps': 71883, 'loss/train': 1.663096308708191} 08/31/2021 02:09:58 - INFO - __main__ - Step 71885: {'lr': 0.00027181478092794514, 'samples': 13801920, 'steps': 71884, 'loss/train': 0.9407398700714111} 08/31/2021 02:09:58 - INFO - __main__ - Step 71886: {'lr': 0.0002718094944204743, 'samples': 13802112, 'steps': 71885, 'loss/train': 2.150406837463379} 08/31/2021 02:09:59 - INFO - __main__ - Step 71887: {'lr': 0.0002718042079031765, 'samples': 13802304, 'steps': 71886, 'loss/train': 1.59259033203125} 08/31/2021 02:09:59 - INFO - __main__ - Step 71888: {'lr': 0.00027179892137605403, 'samples': 13802496, 'steps': 71887, 'loss/train': 1.391556978225708} 08/31/2021 02:09:59 - INFO - __main__ - Step 71889: {'lr': 0.0002717936348391093, 'samples': 13802688, 'steps': 71888, 'loss/train': 1.0704445838928223} 08/31/2021 02:10:01 - INFO - __main__ - Step 71890: {'lr': 0.00027178834829234475, 'samples': 13802880, 'steps': 71889, 'loss/train': 1.042679786682129} 08/31/2021 02:10:01 - INFO - __main__ - Step 71891: {'lr': 0.00027178306173576266, 'samples': 13803072, 'steps': 71890, 'loss/train': 1.209949254989624} 08/31/2021 02:10:01 - INFO - __main__ - Step 71892: {'lr': 0.00027177777516936545, 'samples': 13803264, 'steps': 71891, 'loss/train': 0.8254095315933228} 08/31/2021 02:10:02 - INFO - __main__ - Step 71893: {'lr': 0.0002717724885931555, 'samples': 13803456, 'steps': 71892, 'loss/train': 1.0430561304092407} 08/31/2021 02:10:02 - INFO - __main__ - Step 71894: {'lr': 0.0002717672020071352, 'samples': 13803648, 'steps': 71893, 'loss/train': 1.215504765510559} 08/31/2021 02:10:04 - INFO - __main__ - Step 71895: {'lr': 0.000271761915411307, 'samples': 13803840, 'steps': 71894, 'loss/train': 1.8220446109771729} 08/31/2021 02:10:04 - INFO - __main__ - Step 71896: {'lr': 0.00027175662880567317, 'samples': 13804032, 'steps': 71895, 'loss/train': 1.5866509675979614} 08/31/2021 02:10:04 - INFO - __main__ - Step 71897: {'lr': 0.0002717513421902362, 'samples': 13804224, 'steps': 71896, 'loss/train': 0.1443040668964386} 08/31/2021 02:10:05 - INFO - __main__ - Step 71898: {'lr': 0.0002717460555649983, 'samples': 13804416, 'steps': 71897, 'loss/train': 0.8531907200813293} 08/31/2021 02:10:05 - INFO - __main__ - Step 71899: {'lr': 0.00027174076892996204, 'samples': 13804608, 'steps': 71898, 'loss/train': 1.317726969718933} 08/31/2021 02:10:07 - INFO - __main__ - Step 71900: {'lr': 0.0002717354822851297, 'samples': 13804800, 'steps': 71899, 'loss/train': 1.2646633386611938} 08/31/2021 02:10:07 - INFO - __main__ - Step 71901: {'lr': 0.0002717301956305037, 'samples': 13804992, 'steps': 71900, 'loss/train': 1.0536948442459106} 08/31/2021 02:10:08 - INFO - __main__ - Step 71902: {'lr': 0.00027172490896608636, 'samples': 13805184, 'steps': 71901, 'loss/train': 1.365206003189087} 08/31/2021 02:10:08 - INFO - __main__ - Step 71903: {'lr': 0.00027171962229188026, 'samples': 13805376, 'steps': 71902, 'loss/train': 1.8418794870376587} 08/31/2021 02:10:08 - INFO - __main__ - Step 71904: {'lr': 0.0002717143356078875, 'samples': 13805568, 'steps': 71903, 'loss/train': 1.777762532234192} 08/31/2021 02:10:09 - INFO - __main__ - Step 71905: {'lr': 0.0002717090489141106, 'samples': 13805760, 'steps': 71904, 'loss/train': 1.3134312629699707} 08/31/2021 02:10:10 - INFO - __main__ - Step 71906: {'lr': 0.00027170376221055193, 'samples': 13805952, 'steps': 71905, 'loss/train': 1.6213696002960205} 08/31/2021 02:10:11 - INFO - __main__ - Step 71907: {'lr': 0.0002716984754972139, 'samples': 13806144, 'steps': 71906, 'loss/train': 0.6308441162109375} 08/31/2021 02:10:11 - INFO - __main__ - Step 71908: {'lr': 0.0002716931887740989, 'samples': 13806336, 'steps': 71907, 'loss/train': 0.7587864995002747} 08/31/2021 02:10:11 - INFO - __main__ - Step 71909: {'lr': 0.0002716879020412093, 'samples': 13806528, 'steps': 71908, 'loss/train': 1.91879141330719} 08/31/2021 02:10:12 - INFO - __main__ - Step 71910: {'lr': 0.00027168261529854744, 'samples': 13806720, 'steps': 71909, 'loss/train': 0.4860613942146301} 08/31/2021 02:10:13 - INFO - __main__ - Step 71911: {'lr': 0.00027167732854611567, 'samples': 13806912, 'steps': 71910, 'loss/train': 0.9167730808258057} 08/31/2021 02:10:14 - INFO - __main__ - Step 71912: {'lr': 0.0002716720417839165, 'samples': 13807104, 'steps': 71911, 'loss/train': 1.3088304996490479} 08/31/2021 02:10:14 - INFO - __main__ - Step 71913: {'lr': 0.0002716667550119522, 'samples': 13807296, 'steps': 71912, 'loss/train': 1.4194934368133545} 08/31/2021 02:10:14 - INFO - __main__ - Step 71914: {'lr': 0.00027166146823022524, 'samples': 13807488, 'steps': 71913, 'loss/train': 1.3507927656173706} 08/31/2021 02:10:15 - INFO - __main__ - Step 71915: {'lr': 0.00027165618143873795, 'samples': 13807680, 'steps': 71914, 'loss/train': 0.7111819386482239} 08/31/2021 02:10:16 - INFO - __main__ - Step 71916: {'lr': 0.0002716508946374927, 'samples': 13807872, 'steps': 71915, 'loss/train': 1.7977361679077148} 08/31/2021 02:10:16 - INFO - __main__ - Step 71917: {'lr': 0.0002716456078264918, 'samples': 13808064, 'steps': 71916, 'loss/train': 0.9843373894691467} 08/31/2021 02:10:17 - INFO - __main__ - Step 71918: {'lr': 0.00027164032100573785, 'samples': 13808256, 'steps': 71917, 'loss/train': 0.4353739023208618} 08/31/2021 02:10:17 - INFO - __main__ - Step 71919: {'lr': 0.0002716350341752331, 'samples': 13808448, 'steps': 71918, 'loss/train': 1.1569195985794067} 08/31/2021 02:10:17 - INFO - __main__ - Step 71920: {'lr': 0.00027162974733497994, 'samples': 13808640, 'steps': 71919, 'loss/train': 1.5274311304092407} 08/31/2021 02:10:19 - INFO - __main__ - Step 71921: {'lr': 0.0002716244604849807, 'samples': 13808832, 'steps': 71920, 'loss/train': 1.5517988204956055} 08/31/2021 02:10:19 - INFO - __main__ - Step 71922: {'lr': 0.0002716191736252378, 'samples': 13809024, 'steps': 71921, 'loss/train': 1.4516217708587646} 08/31/2021 02:10:20 - INFO - __main__ - Step 71923: {'lr': 0.00027161388675575365, 'samples': 13809216, 'steps': 71922, 'loss/train': 1.291532039642334} 08/31/2021 02:10:20 - INFO - __main__ - Step 71924: {'lr': 0.0002716085998765306, 'samples': 13809408, 'steps': 71923, 'loss/train': 1.3154784440994263} 08/31/2021 02:10:20 - INFO - __main__ - Step 71925: {'lr': 0.00027160331298757117, 'samples': 13809600, 'steps': 71924, 'loss/train': 1.2804261445999146} 08/31/2021 02:10:22 - INFO - __main__ - Step 71926: {'lr': 0.0002715980260888775, 'samples': 13809792, 'steps': 71925, 'loss/train': 1.0660544633865356} 08/31/2021 02:10:23 - INFO - __main__ - Step 71927: {'lr': 0.0002715927391804521, 'samples': 13809984, 'steps': 71926, 'loss/train': 1.4897725582122803} 08/31/2021 02:10:23 - INFO - __main__ - Step 71928: {'lr': 0.00027158745226229744, 'samples': 13810176, 'steps': 71927, 'loss/train': 0.7033146619796753} 08/31/2021 02:10:23 - INFO - __main__ - Step 71929: {'lr': 0.0002715821653344157, 'samples': 13810368, 'steps': 71928, 'loss/train': 1.0730615854263306} 08/31/2021 02:10:24 - INFO - __main__ - Step 71930: {'lr': 0.0002715768783968094, 'samples': 13810560, 'steps': 71929, 'loss/train': 0.1897783726453781} 08/31/2021 02:10:25 - INFO - __main__ - Step 71931: {'lr': 0.0002715715914494809, 'samples': 13810752, 'steps': 71930, 'loss/train': 0.9465924501419067} 08/31/2021 02:10:26 - INFO - __main__ - Step 71932: {'lr': 0.00027156630449243256, 'samples': 13810944, 'steps': 71931, 'loss/train': 1.1401950120925903} 08/31/2021 02:10:26 - INFO - __main__ - Step 71933: {'lr': 0.00027156101752566676, 'samples': 13811136, 'steps': 71932, 'loss/train': 1.6202417612075806} 08/31/2021 02:10:26 - INFO - __main__ - Step 71934: {'lr': 0.0002715557305491859, 'samples': 13811328, 'steps': 71933, 'loss/train': 1.122138261795044} 08/31/2021 02:10:27 - INFO - __main__ - Step 71935: {'lr': 0.0002715504435629924, 'samples': 13811520, 'steps': 71934, 'loss/train': 0.9035658836364746} 08/31/2021 02:10:27 - INFO - __main__ - Step 71936: {'lr': 0.00027154515656708855, 'samples': 13811712, 'steps': 71935, 'loss/train': 1.3073073625564575} 08/31/2021 02:10:29 - INFO - __main__ - Step 71937: {'lr': 0.00027153986956147686, 'samples': 13811904, 'steps': 71936, 'loss/train': 1.2274471521377563} 08/31/2021 02:10:29 - INFO - __main__ - Step 71938: {'lr': 0.0002715345825461597, 'samples': 13812096, 'steps': 71937, 'loss/train': 1.1972758769989014} 08/31/2021 02:10:29 - INFO - __main__ - Step 71939: {'lr': 0.0002715292955211392, 'samples': 13812288, 'steps': 71938, 'loss/train': 1.0990734100341797} 08/31/2021 02:10:30 - INFO - __main__ - Step 71940: {'lr': 0.000271524008486418, 'samples': 13812480, 'steps': 71939, 'loss/train': 0.8881654739379883} 08/31/2021 02:10:30 - INFO - __main__ - Step 71941: {'lr': 0.0002715187214419985, 'samples': 13812672, 'steps': 71940, 'loss/train': 1.1712855100631714} 08/31/2021 02:10:32 - INFO - __main__ - Step 71942: {'lr': 0.00027151343438788284, 'samples': 13812864, 'steps': 71941, 'loss/train': 1.445496916770935} 08/31/2021 02:10:32 - INFO - __main__ - Step 71943: {'lr': 0.0002715081473240736, 'samples': 13813056, 'steps': 71942, 'loss/train': 1.2958215475082397} 08/31/2021 02:10:33 - INFO - __main__ - Step 71944: {'lr': 0.0002715028602505732, 'samples': 13813248, 'steps': 71943, 'loss/train': 1.0915355682373047} 08/31/2021 02:10:33 - INFO - __main__ - Step 71945: {'lr': 0.000271497573167384, 'samples': 13813440, 'steps': 71944, 'loss/train': 1.4653412103652954} 08/31/2021 02:10:33 - INFO - __main__ - Step 71946: {'lr': 0.00027149228607450823, 'samples': 13813632, 'steps': 71945, 'loss/train': 1.581407904624939} 08/31/2021 02:10:34 - INFO - __main__ - Step 71947: {'lr': 0.00027148699897194833, 'samples': 13813824, 'steps': 71946, 'loss/train': 0.4549999535083771} 08/31/2021 02:10:35 - INFO - __main__ - Step 71948: {'lr': 0.00027148171185970677, 'samples': 13814016, 'steps': 71947, 'loss/train': 1.7717126607894897} 08/31/2021 02:10:36 - INFO - __main__ - Step 71949: {'lr': 0.00027147642473778584, 'samples': 13814208, 'steps': 71948, 'loss/train': 0.14619968831539154} 08/31/2021 02:10:36 - INFO - __main__ - Step 71950: {'lr': 0.000271471137606188, 'samples': 13814400, 'steps': 71949, 'loss/train': 1.738751769065857} 08/31/2021 02:10:36 - INFO - __main__ - Step 71951: {'lr': 0.00027146585046491564, 'samples': 13814592, 'steps': 71950, 'loss/train': 1.5013618469238281} 08/31/2021 02:10:37 - INFO - __main__ - Step 71952: {'lr': 0.00027146056331397105, 'samples': 13814784, 'steps': 71951, 'loss/train': 1.2778161764144897} 08/31/2021 02:10:38 - INFO - __main__ - Step 71953: {'lr': 0.0002714552761533566, 'samples': 13814976, 'steps': 71952, 'loss/train': 1.572054147720337} 08/31/2021 02:10:39 - INFO - __main__ - Step 71954: {'lr': 0.00027144998898307485, 'samples': 13815168, 'steps': 71953, 'loss/train': 1.5151296854019165} 08/31/2021 02:10:39 - INFO - __main__ - Step 71955: {'lr': 0.000271444701803128, 'samples': 13815360, 'steps': 71954, 'loss/train': 1.1486774682998657} 08/31/2021 02:10:39 - INFO - __main__ - Step 71956: {'lr': 0.0002714394146135185, 'samples': 13815552, 'steps': 71955, 'loss/train': 1.0118156671524048} 08/31/2021 02:10:40 - INFO - __main__ - Step 71957: {'lr': 0.0002714341274142488, 'samples': 13815744, 'steps': 71956, 'loss/train': 1.0609763860702515} 08/31/2021 02:10:41 - INFO - __main__ - Step 71958: {'lr': 0.00027142884020532116, 'samples': 13815936, 'steps': 71957, 'loss/train': 1.169831395149231} 08/31/2021 02:10:42 - INFO - __main__ - Step 71959: {'lr': 0.00027142355298673796, 'samples': 13816128, 'steps': 71958, 'loss/train': 1.6477346420288086} 08/31/2021 02:10:42 - INFO - __main__ - Step 71960: {'lr': 0.0002714182657585017, 'samples': 13816320, 'steps': 71959, 'loss/train': 0.6323637366294861} 08/31/2021 02:10:42 - INFO - __main__ - Step 71961: {'lr': 0.0002714129785206147, 'samples': 13816512, 'steps': 71960, 'loss/train': 1.380145788192749} 08/31/2021 02:10:43 - INFO - __main__ - Step 71962: {'lr': 0.00027140769127307935, 'samples': 13816704, 'steps': 71961, 'loss/train': 1.4470113515853882} 08/31/2021 02:10:43 - INFO - __main__ - Step 71963: {'lr': 0.000271402404015898, 'samples': 13816896, 'steps': 71962, 'loss/train': 1.4563477039337158} 08/31/2021 02:10:45 - INFO - __main__ - Step 71964: {'lr': 0.000271397116749073, 'samples': 13817088, 'steps': 71963, 'loss/train': 0.7580975890159607} 08/31/2021 02:10:46 - INFO - __main__ - Step 71965: {'lr': 0.0002713918294726069, 'samples': 13817280, 'steps': 71964, 'loss/train': 2.000556707382202} 08/31/2021 02:10:46 - INFO - __main__ - Step 71966: {'lr': 0.00027138654218650195, 'samples': 13817472, 'steps': 71965, 'loss/train': 1.7264808416366577} 08/31/2021 02:10:46 - INFO - __main__ - Step 71967: {'lr': 0.0002713812548907605, 'samples': 13817664, 'steps': 71966, 'loss/train': 1.4046133756637573} 08/31/2021 02:10:47 - INFO - __main__ - Step 71968: {'lr': 0.000271375967585385, 'samples': 13817856, 'steps': 71967, 'loss/train': 1.3069590330123901} 08/31/2021 02:10:48 - INFO - __main__ - Step 71969: {'lr': 0.00027137068027037784, 'samples': 13818048, 'steps': 71968, 'loss/train': 1.4908533096313477} 08/31/2021 02:10:49 - INFO - __main__ - Step 71970: {'lr': 0.00027136539294574135, 'samples': 13818240, 'steps': 71969, 'loss/train': 2.078841209411621} 08/31/2021 02:10:49 - INFO - __main__ - Step 71971: {'lr': 0.00027136010561147806, 'samples': 13818432, 'steps': 71970, 'loss/train': 1.5993973016738892} 08/31/2021 02:10:49 - INFO - __main__ - Step 71972: {'lr': 0.0002713548182675901, 'samples': 13818624, 'steps': 71971, 'loss/train': 1.082198977470398} 08/31/2021 02:10:50 - INFO - __main__ - Step 71973: {'lr': 0.00027134953091408005, 'samples': 13818816, 'steps': 71972, 'loss/train': 1.2532931566238403} 08/31/2021 02:10:51 - INFO - __main__ - Step 71974: {'lr': 0.0002713442435509502, 'samples': 13819008, 'steps': 71973, 'loss/train': 1.501170039176941} 08/31/2021 02:10:52 - INFO - __main__ - Step 71975: {'lr': 0.000271338956178203, 'samples': 13819200, 'steps': 71974, 'loss/train': 1.530116081237793} 08/31/2021 02:10:52 - INFO - __main__ - Step 71976: {'lr': 0.00027133366879584077, 'samples': 13819392, 'steps': 71975, 'loss/train': 1.4197934865951538} 08/31/2021 02:10:52 - INFO - __main__ - Step 71977: {'lr': 0.0002713283814038659, 'samples': 13819584, 'steps': 71976, 'loss/train': 1.939423680305481} 08/31/2021 02:10:53 - INFO - __main__ - Step 71978: {'lr': 0.00027132309400228086, 'samples': 13819776, 'steps': 71977, 'loss/train': 1.4892264604568481} 08/31/2021 02:10:54 - INFO - __main__ - Step 71979: {'lr': 0.0002713178065910879, 'samples': 13819968, 'steps': 71978, 'loss/train': 1.29826819896698} 08/31/2021 02:10:55 - INFO - __main__ - Step 71980: {'lr': 0.0002713125191702895, 'samples': 13820160, 'steps': 71979, 'loss/train': 1.1571437120437622} 08/31/2021 02:10:55 - INFO - __main__ - Step 71981: {'lr': 0.0002713072317398879, 'samples': 13820352, 'steps': 71980, 'loss/train': 1.0996073484420776} 08/31/2021 02:10:55 - INFO - __main__ - Step 71982: {'lr': 0.0002713019442998857, 'samples': 13820544, 'steps': 71981, 'loss/train': 0.027310166507959366} 08/31/2021 02:10:56 - INFO - __main__ - Step 71983: {'lr': 0.00027129665685028513, 'samples': 13820736, 'steps': 71982, 'loss/train': 1.1806666851043701} 08/31/2021 02:10:57 - INFO - __main__ - Step 71984: {'lr': 0.0002712913693910887, 'samples': 13820928, 'steps': 71983, 'loss/train': 1.5284677743911743} 08/31/2021 02:10:58 - INFO - __main__ - Step 71985: {'lr': 0.0002712860819222986, 'samples': 13821120, 'steps': 71984, 'loss/train': 1.4542551040649414} 08/31/2021 02:10:58 - INFO - __main__ - Step 71986: {'lr': 0.0002712807944439174, 'samples': 13821312, 'steps': 71985, 'loss/train': 1.4725511074066162} 08/31/2021 02:10:58 - INFO - __main__ - Step 71987: {'lr': 0.0002712755069559474, 'samples': 13821504, 'steps': 71986, 'loss/train': 1.8445281982421875} 08/31/2021 02:10:59 - INFO - __main__ - Step 71988: {'lr': 0.0002712702194583909, 'samples': 13821696, 'steps': 71987, 'loss/train': 0.43735894560813904} 08/31/2021 02:10:59 - INFO - __main__ - Step 71989: {'lr': 0.0002712649319512504, 'samples': 13821888, 'steps': 71988, 'loss/train': 1.1974599361419678} 08/31/2021 02:11:01 - INFO - __main__ - Step 71990: {'lr': 0.0002712596444345283, 'samples': 13822080, 'steps': 71989, 'loss/train': 1.1666879653930664} 08/31/2021 02:11:01 - INFO - __main__ - Step 71991: {'lr': 0.00027125435690822684, 'samples': 13822272, 'steps': 71990, 'loss/train': 1.6443849802017212} 08/31/2021 02:11:02 - INFO - __main__ - Step 71992: {'lr': 0.0002712490693723486, 'samples': 13822464, 'steps': 71991, 'loss/train': 1.3230786323547363} 08/31/2021 02:11:02 - INFO - __main__ - Step 71993: {'lr': 0.0002712437818268958, 'samples': 13822656, 'steps': 71992, 'loss/train': 2.008877754211426} 08/31/2021 02:11:02 - INFO - __main__ - Step 71994: {'lr': 0.0002712384942718709, 'samples': 13822848, 'steps': 71993, 'loss/train': 0.9854332804679871} 08/31/2021 02:11:04 - INFO - __main__ - Step 71995: {'lr': 0.00027123320670727625, 'samples': 13823040, 'steps': 71994, 'loss/train': 1.349066972732544} 08/31/2021 02:11:04 - INFO - __main__ - Step 71996: {'lr': 0.0002712279191331142, 'samples': 13823232, 'steps': 71995, 'loss/train': 1.3517123460769653} 08/31/2021 02:11:05 - INFO - __main__ - Step 71997: {'lr': 0.0002712226315493873, 'samples': 13823424, 'steps': 71996, 'loss/train': 1.0534732341766357} 08/31/2021 02:11:05 - INFO - __main__ - Step 71998: {'lr': 0.00027121734395609774, 'samples': 13823616, 'steps': 71997, 'loss/train': 1.362243890762329} 08/31/2021 02:11:05 - INFO - __main__ - Step 71999: {'lr': 0.000271212056353248, 'samples': 13823808, 'steps': 71998, 'loss/train': 1.683861494064331} 08/31/2021 02:11:07 - INFO - __main__ - Step 72000: {'lr': 0.00027120676874084037, 'samples': 13824000, 'steps': 71999, 'loss/train': 1.2242833375930786} 08/31/2021 02:11:07 - INFO - __main__ - Step 72001: {'lr': 0.0002712014811188773, 'samples': 13824192, 'steps': 72000, 'loss/train': 0.8397529721260071} 08/31/2021 02:11:08 - INFO - __main__ - Step 72002: {'lr': 0.0002711961934873612, 'samples': 13824384, 'steps': 72001, 'loss/train': 1.241045594215393} 08/31/2021 02:11:08 - INFO - __main__ - Step 72003: {'lr': 0.0002711909058462944, 'samples': 13824576, 'steps': 72002, 'loss/train': 1.103126883506775} 08/31/2021 02:11:08 - INFO - __main__ - Step 72004: {'lr': 0.00027118561819567934, 'samples': 13824768, 'steps': 72003, 'loss/train': 1.2148770093917847} 08/31/2021 02:11:10 - INFO - __main__ - Step 72005: {'lr': 0.0002711803305355184, 'samples': 13824960, 'steps': 72004, 'loss/train': 1.6202831268310547} 08/31/2021 02:11:10 - INFO - __main__ - Step 72006: {'lr': 0.00027117504286581384, 'samples': 13825152, 'steps': 72005, 'loss/train': 1.735373854637146} 08/31/2021 02:11:11 - INFO - __main__ - Step 72007: {'lr': 0.0002711697551865682, 'samples': 13825344, 'steps': 72006, 'loss/train': 1.834244966506958} 08/31/2021 02:11:11 - INFO - __main__ - Step 72008: {'lr': 0.00027116446749778377, 'samples': 13825536, 'steps': 72007, 'loss/train': 1.192871332168579} 08/31/2021 02:11:11 - INFO - __main__ - Step 72009: {'lr': 0.0002711591797994629, 'samples': 13825728, 'steps': 72008, 'loss/train': 1.6327286958694458} 08/31/2021 02:11:12 - INFO - __main__ - Step 72010: {'lr': 0.0002711538920916081, 'samples': 13825920, 'steps': 72009, 'loss/train': 0.7069824934005737} 08/31/2021 02:11:13 - INFO - __main__ - Step 72011: {'lr': 0.00027114860437422165, 'samples': 13826112, 'steps': 72010, 'loss/train': 0.996897280216217} 08/31/2021 02:11:14 - INFO - __main__ - Step 72012: {'lr': 0.0002711433166473061, 'samples': 13826304, 'steps': 72011, 'loss/train': 0.8047179579734802} 08/31/2021 02:11:14 - INFO - __main__ - Step 72013: {'lr': 0.00027113802891086354, 'samples': 13826496, 'steps': 72012, 'loss/train': 0.7439761161804199} 08/31/2021 02:11:15 - INFO - __main__ - Step 72014: {'lr': 0.00027113274116489654, 'samples': 13826688, 'steps': 72013, 'loss/train': 1.262413740158081} 08/31/2021 02:11:15 - INFO - __main__ - Step 72015: {'lr': 0.0002711274534094075, 'samples': 13826880, 'steps': 72014, 'loss/train': 1.6576792001724243} 08/31/2021 02:11:17 - INFO - __main__ - Step 72016: {'lr': 0.0002711221656443987, 'samples': 13827072, 'steps': 72015, 'loss/train': 1.2282614707946777} 08/31/2021 02:11:18 - INFO - __main__ - Step 72017: {'lr': 0.0002711168778698726, 'samples': 13827264, 'steps': 72016, 'loss/train': 0.6973865628242493} 08/31/2021 02:11:18 - INFO - __main__ - Step 72018: {'lr': 0.0002711115900858316, 'samples': 13827456, 'steps': 72017, 'loss/train': 0.7066344618797302} 08/31/2021 02:11:18 - INFO - __main__ - Step 72019: {'lr': 0.00027110630229227803, 'samples': 13827648, 'steps': 72018, 'loss/train': 1.0691620111465454} 08/31/2021 02:11:19 - INFO - __main__ - Step 72020: {'lr': 0.0002711010144892142, 'samples': 13827840, 'steps': 72019, 'loss/train': 1.6009246110916138} 08/31/2021 02:11:20 - INFO - __main__ - Step 72021: {'lr': 0.00027109572667664264, 'samples': 13828032, 'steps': 72020, 'loss/train': 1.17514169216156} 08/31/2021 02:11:21 - INFO - __main__ - Step 72022: {'lr': 0.0002710904388545656, 'samples': 13828224, 'steps': 72021, 'loss/train': 1.4484015703201294} 08/31/2021 02:11:21 - INFO - __main__ - Step 72023: {'lr': 0.00027108515102298563, 'samples': 13828416, 'steps': 72022, 'loss/train': 0.8014837503433228} 08/31/2021 02:11:21 - INFO - __main__ - Step 72024: {'lr': 0.00027107986318190505, 'samples': 13828608, 'steps': 72023, 'loss/train': 1.4023680686950684} 08/31/2021 02:11:22 - INFO - __main__ - Step 72025: {'lr': 0.0002710745753313262, 'samples': 13828800, 'steps': 72024, 'loss/train': 1.3083512783050537} 08/31/2021 02:11:23 - INFO - __main__ - Step 72026: {'lr': 0.00027106928747125137, 'samples': 13828992, 'steps': 72025, 'loss/train': 0.526358962059021} 08/31/2021 02:11:24 - INFO - __main__ - Step 72027: {'lr': 0.0002710639996016831, 'samples': 13829184, 'steps': 72026, 'loss/train': 0.05984005331993103} 08/31/2021 02:11:24 - INFO - __main__ - Step 72028: {'lr': 0.00027105871172262367, 'samples': 13829376, 'steps': 72027, 'loss/train': 1.3060894012451172} 08/31/2021 02:11:24 - INFO - __main__ - Step 72029: {'lr': 0.0002710534238340756, 'samples': 13829568, 'steps': 72028, 'loss/train': 0.6613709330558777} 08/31/2021 02:11:25 - INFO - __main__ - Step 72030: {'lr': 0.0002710481359360411, 'samples': 13829760, 'steps': 72029, 'loss/train': 0.7740705013275146} 08/31/2021 02:11:27 - INFO - __main__ - Step 72031: {'lr': 0.00027104284802852266, 'samples': 13829952, 'steps': 72030, 'loss/train': 1.3969019651412964} 08/31/2021 02:11:27 - INFO - __main__ - Step 72032: {'lr': 0.0002710375601115227, 'samples': 13830144, 'steps': 72031, 'loss/train': 0.7463847994804382} 08/31/2021 02:11:27 - INFO - __main__ - Step 72033: {'lr': 0.00027103227218504343, 'samples': 13830336, 'steps': 72032, 'loss/train': 0.973653256893158} 08/31/2021 02:11:28 - INFO - __main__ - Step 72034: {'lr': 0.00027102698424908745, 'samples': 13830528, 'steps': 72033, 'loss/train': 1.4789975881576538} 08/31/2021 02:11:28 - INFO - __main__ - Step 72035: {'lr': 0.00027102169630365696, 'samples': 13830720, 'steps': 72034, 'loss/train': 1.0886093378067017} 08/31/2021 02:11:29 - INFO - __main__ - Step 72036: {'lr': 0.0002710164083487544, 'samples': 13830912, 'steps': 72035, 'loss/train': 1.2479852437973022} 08/31/2021 02:11:30 - INFO - __main__ - Step 72037: {'lr': 0.0002710111203843823, 'samples': 13831104, 'steps': 72036, 'loss/train': 1.0589535236358643} 08/31/2021 02:11:30 - INFO - __main__ - Step 72038: {'lr': 0.0002710058324105428, 'samples': 13831296, 'steps': 72037, 'loss/train': 0.7370551228523254} 08/31/2021 02:11:31 - INFO - __main__ - Step 72039: {'lr': 0.00027100054442723845, 'samples': 13831488, 'steps': 72038, 'loss/train': 1.0679881572723389} 08/31/2021 02:11:31 - INFO - __main__ - Step 72040: {'lr': 0.00027099525643447153, 'samples': 13831680, 'steps': 72039, 'loss/train': 0.9817774295806885} 08/31/2021 02:11:31 - INFO - __main__ - Step 72041: {'lr': 0.00027098996843224446, 'samples': 13831872, 'steps': 72040, 'loss/train': 1.2833592891693115} 08/31/2021 02:11:33 - INFO - __main__ - Step 72042: {'lr': 0.0002709846804205597, 'samples': 13832064, 'steps': 72041, 'loss/train': 0.8005906343460083} 08/31/2021 02:11:33 - INFO - __main__ - Step 72043: {'lr': 0.00027097939239941957, 'samples': 13832256, 'steps': 72042, 'loss/train': 1.0511001348495483} 08/31/2021 02:11:34 - INFO - __main__ - Step 72044: {'lr': 0.00027097410436882635, 'samples': 13832448, 'steps': 72043, 'loss/train': 0.8602052927017212} 08/31/2021 02:11:34 - INFO - __main__ - Step 72045: {'lr': 0.00027096881632878263, 'samples': 13832640, 'steps': 72044, 'loss/train': 0.06304959207773209} 08/31/2021 02:11:34 - INFO - __main__ - Step 72046: {'lr': 0.0002709635282792906, 'samples': 13832832, 'steps': 72045, 'loss/train': 0.9824002385139465} 08/31/2021 02:11:36 - INFO - __main__ - Step 72047: {'lr': 0.00027095824022035274, 'samples': 13833024, 'steps': 72046, 'loss/train': 0.919491171836853} 08/31/2021 02:11:37 - INFO - __main__ - Step 72048: {'lr': 0.0002709529521519715, 'samples': 13833216, 'steps': 72047, 'loss/train': 0.8733831644058228} 08/31/2021 02:11:37 - INFO - __main__ - Step 72049: {'lr': 0.0002709476640741492, 'samples': 13833408, 'steps': 72048, 'loss/train': 0.5809602737426758} 08/31/2021 02:11:37 - INFO - __main__ - Step 72050: {'lr': 0.0002709423759868881, 'samples': 13833600, 'steps': 72049, 'loss/train': 0.7885367274284363} 08/31/2021 02:11:38 - INFO - __main__ - Step 72051: {'lr': 0.0002709370878901907, 'samples': 13833792, 'steps': 72050, 'loss/train': 5.764814376831055} 08/31/2021 02:11:39 - INFO - __main__ - Step 72052: {'lr': 0.00027093179978405937, 'samples': 13833984, 'steps': 72051, 'loss/train': 1.475883960723877} 08/31/2021 02:11:40 - INFO - __main__ - Step 72053: {'lr': 0.00027092651166849653, 'samples': 13834176, 'steps': 72052, 'loss/train': 1.349105954170227} 08/31/2021 02:11:40 - INFO - __main__ - Step 72054: {'lr': 0.0002709212235435046, 'samples': 13834368, 'steps': 72053, 'loss/train': 0.9303628206253052} 08/31/2021 02:11:40 - INFO - __main__ - Step 72055: {'lr': 0.0002709159354090858, 'samples': 13834560, 'steps': 72054, 'loss/train': 1.414660096168518} 08/31/2021 02:11:41 - INFO - __main__ - Step 72056: {'lr': 0.00027091064726524256, 'samples': 13834752, 'steps': 72055, 'loss/train': 1.2292464971542358} 08/31/2021 02:11:41 - INFO - __main__ - Step 72057: {'lr': 0.00027090535911197735, 'samples': 13834944, 'steps': 72056, 'loss/train': 0.9855533242225647} 08/31/2021 02:11:42 - INFO - __main__ - Step 72058: {'lr': 0.0002709000709492925, 'samples': 13835136, 'steps': 72057, 'loss/train': 1.5539004802703857} 08/31/2021 02:11:43 - INFO - __main__ - Step 72059: {'lr': 0.00027089478277719044, 'samples': 13835328, 'steps': 72058, 'loss/train': 1.29099440574646} 08/31/2021 02:11:43 - INFO - __main__ - Step 72060: {'lr': 0.00027088949459567346, 'samples': 13835520, 'steps': 72059, 'loss/train': 0.9535779356956482} 08/31/2021 02:11:43 - INFO - __main__ - Step 72061: {'lr': 0.00027088420640474404, 'samples': 13835712, 'steps': 72060, 'loss/train': 1.2085964679718018} 08/31/2021 02:11:44 - INFO - __main__ - Step 72062: {'lr': 0.00027087891820440455, 'samples': 13835904, 'steps': 72061, 'loss/train': 1.0702252388000488} 08/31/2021 02:11:46 - INFO - __main__ - Step 72063: {'lr': 0.0002708736299946573, 'samples': 13836096, 'steps': 72062, 'loss/train': 1.3630472421646118} 08/31/2021 02:11:47 - INFO - __main__ - Step 72064: {'lr': 0.0002708683417755046, 'samples': 13836288, 'steps': 72063, 'loss/train': 0.3961092531681061} 08/31/2021 02:11:47 - INFO - __main__ - Step 72065: {'lr': 0.0002708630535469491, 'samples': 13836480, 'steps': 72064, 'loss/train': 0.8488057851791382} 08/31/2021 02:11:47 - INFO - __main__ - Step 72066: {'lr': 0.00027085776530899304, 'samples': 13836672, 'steps': 72065, 'loss/train': 0.049852918833494186} 08/31/2021 02:11:48 - INFO - __main__ - Step 72067: {'lr': 0.0002708524770616387, 'samples': 13836864, 'steps': 72066, 'loss/train': 3.7977747917175293} 08/31/2021 02:11:48 - INFO - __main__ - Step 72068: {'lr': 0.00027084718880488856, 'samples': 13837056, 'steps': 72067, 'loss/train': 1.196556806564331} 08/31/2021 02:11:49 - INFO - __main__ - Step 72069: {'lr': 0.00027084190053874505, 'samples': 13837248, 'steps': 72068, 'loss/train': 0.8692418932914734} 08/31/2021 02:11:50 - INFO - __main__ - Step 72070: {'lr': 0.0002708366122632105, 'samples': 13837440, 'steps': 72069, 'loss/train': 1.4230170249938965} 08/31/2021 02:11:50 - INFO - __main__ - Step 72071: {'lr': 0.00027083132397828725, 'samples': 13837632, 'steps': 72070, 'loss/train': 0.602416455745697} 08/31/2021 02:11:51 - INFO - __main__ - Step 72072: {'lr': 0.0002708260356839778, 'samples': 13837824, 'steps': 72071, 'loss/train': 1.4890471696853638} 08/31/2021 02:11:51 - INFO - __main__ - Step 72073: {'lr': 0.0002708207473802844, 'samples': 13838016, 'steps': 72072, 'loss/train': 0.5009086728096008} 08/31/2021 02:11:53 - INFO - __main__ - Step 72074: {'lr': 0.00027081545906720953, 'samples': 13838208, 'steps': 72073, 'loss/train': 1.3195151090621948} 08/31/2021 02:11:54 - INFO - __main__ - Step 72075: {'lr': 0.00027081017074475543, 'samples': 13838400, 'steps': 72074, 'loss/train': 1.3731615543365479} 08/31/2021 02:11:54 - INFO - __main__ - Step 72076: {'lr': 0.00027080488241292466, 'samples': 13838592, 'steps': 72075, 'loss/train': 0.9621325731277466} 08/31/2021 02:11:54 - INFO - __main__ - Step 72077: {'lr': 0.00027079959407171956, 'samples': 13838784, 'steps': 72076, 'loss/train': 1.2942606210708618} 08/31/2021 02:11:55 - INFO - __main__ - Step 72078: {'lr': 0.00027079430572114245, 'samples': 13838976, 'steps': 72077, 'loss/train': 1.1365571022033691} 08/31/2021 02:11:56 - INFO - __main__ - Step 72079: {'lr': 0.0002707890173611958, 'samples': 13839168, 'steps': 72078, 'loss/train': 1.48257315158844} 08/31/2021 02:11:57 - INFO - __main__ - Step 72080: {'lr': 0.0002707837289918819, 'samples': 13839360, 'steps': 72079, 'loss/train': 1.372639536857605} 08/31/2021 02:11:57 - INFO - __main__ - Step 72081: {'lr': 0.00027077844061320315, 'samples': 13839552, 'steps': 72080, 'loss/train': 1.2305853366851807} 08/31/2021 02:11:58 - INFO - __main__ - Step 72082: {'lr': 0.000270773152225162, 'samples': 13839744, 'steps': 72081, 'loss/train': 0.11175371706485748} 08/31/2021 02:11:58 - INFO - __main__ - Step 72083: {'lr': 0.0002707678638277608, 'samples': 13839936, 'steps': 72082, 'loss/train': 1.35683274269104} 08/31/2021 02:11:59 - INFO - __main__ - Step 72084: {'lr': 0.0002707625754210018, 'samples': 13840128, 'steps': 72083, 'loss/train': 1.3245865106582642} 08/31/2021 02:12:00 - INFO - __main__ - Step 72085: {'lr': 0.0002707572870048876, 'samples': 13840320, 'steps': 72084, 'loss/train': 0.8205268979072571} 08/31/2021 02:12:00 - INFO - __main__ - Step 72086: {'lr': 0.0002707519985794205, 'samples': 13840512, 'steps': 72085, 'loss/train': 1.0794743299484253} 08/31/2021 02:12:01 - INFO - __main__ - Step 72087: {'lr': 0.0002707467101446029, 'samples': 13840704, 'steps': 72086, 'loss/train': 1.4406050443649292} 08/31/2021 02:12:01 - INFO - __main__ - Step 72088: {'lr': 0.00027074142170043706, 'samples': 13840896, 'steps': 72087, 'loss/train': 1.403921365737915} 08/31/2021 02:12:02 - INFO - __main__ - Step 72089: {'lr': 0.0002707361332469255, 'samples': 13841088, 'steps': 72088, 'loss/train': 0.8681383728981018} 08/31/2021 02:12:03 - INFO - __main__ - Step 72090: {'lr': 0.0002707308447840705, 'samples': 13841280, 'steps': 72089, 'loss/train': 1.1682885885238647} 08/31/2021 02:12:03 - INFO - __main__ - Step 72091: {'lr': 0.0002707255563118746, 'samples': 13841472, 'steps': 72090, 'loss/train': 1.1491316556930542} 08/31/2021 02:12:03 - INFO - __main__ - Step 72092: {'lr': 0.0002707202678303401, 'samples': 13841664, 'steps': 72091, 'loss/train': 1.0571141242980957} 08/31/2021 02:12:04 - INFO - __main__ - Step 72093: {'lr': 0.00027071497933946924, 'samples': 13841856, 'steps': 72092, 'loss/train': 1.1868637800216675} 08/31/2021 02:12:05 - INFO - __main__ - Step 72094: {'lr': 0.0002707096908392646, 'samples': 13842048, 'steps': 72093, 'loss/train': 1.289687156677246} 08/31/2021 02:12:06 - INFO - __main__ - Step 72095: {'lr': 0.0002707044023297285, 'samples': 13842240, 'steps': 72094, 'loss/train': 1.1795477867126465} 08/31/2021 02:12:06 - INFO - __main__ - Step 72096: {'lr': 0.0002706991138108633, 'samples': 13842432, 'steps': 72095, 'loss/train': 1.7242456674575806} 08/31/2021 02:12:07 - INFO - __main__ - Step 72097: {'lr': 0.0002706938252826714, 'samples': 13842624, 'steps': 72096, 'loss/train': 1.2373415231704712} 08/31/2021 02:12:07 - INFO - __main__ - Step 72098: {'lr': 0.00027068853674515515, 'samples': 13842816, 'steps': 72097, 'loss/train': 1.4801573753356934} 08/31/2021 02:12:09 - INFO - __main__ - Step 72099: {'lr': 0.00027068324819831707, 'samples': 13843008, 'steps': 72098, 'loss/train': 1.2786763906478882} 08/31/2021 02:12:09 - INFO - __main__ - Step 72100: {'lr': 0.00027067795964215934, 'samples': 13843200, 'steps': 72099, 'loss/train': 1.668737530708313} 08/31/2021 02:12:09 - INFO - __main__ - Step 72101: {'lr': 0.00027067267107668447, 'samples': 13843392, 'steps': 72100, 'loss/train': 1.1998169422149658} 08/31/2021 02:12:10 - INFO - __main__ - Step 72102: {'lr': 0.00027066738250189484, 'samples': 13843584, 'steps': 72101, 'loss/train': 1.2268129587173462} 08/31/2021 02:12:10 - INFO - __main__ - Step 72103: {'lr': 0.0002706620939177927, 'samples': 13843776, 'steps': 72102, 'loss/train': 1.003921389579773} 08/31/2021 02:12:11 - INFO - __main__ - Step 72104: {'lr': 0.0002706568053243806, 'samples': 13843968, 'steps': 72103, 'loss/train': 0.6824901700019836} 08/31/2021 02:12:12 - INFO - __main__ - Step 72105: {'lr': 0.0002706515167216609, 'samples': 13844160, 'steps': 72104, 'loss/train': 1.1261849403381348} 08/31/2021 02:12:12 - INFO - __main__ - Step 72106: {'lr': 0.000270646228109636, 'samples': 13844352, 'steps': 72105, 'loss/train': 1.292431116104126} 08/31/2021 02:12:13 - INFO - __main__ - Step 72107: {'lr': 0.00027064093948830816, 'samples': 13844544, 'steps': 72106, 'loss/train': 0.631554901599884} 08/31/2021 02:12:13 - INFO - __main__ - Step 72108: {'lr': 0.0002706356508576798, 'samples': 13844736, 'steps': 72107, 'loss/train': 1.777997612953186} 08/31/2021 02:12:13 - INFO - __main__ - Step 72109: {'lr': 0.00027063036221775335, 'samples': 13844928, 'steps': 72108, 'loss/train': 0.22424930334091187} 08/31/2021 02:12:15 - INFO - __main__ - Step 72110: {'lr': 0.0002706250735685312, 'samples': 13845120, 'steps': 72109, 'loss/train': 0.9958212375640869} 08/31/2021 02:12:16 - INFO - __main__ - Step 72111: {'lr': 0.00027061978491001566, 'samples': 13845312, 'steps': 72110, 'loss/train': 1.5320671796798706} 08/31/2021 02:12:16 - INFO - __main__ - Step 72112: {'lr': 0.0002706144962422092, 'samples': 13845504, 'steps': 72111, 'loss/train': 1.3888977766036987} 08/31/2021 02:12:16 - INFO - __main__ - Step 72113: {'lr': 0.0002706092075651142, 'samples': 13845696, 'steps': 72112, 'loss/train': 1.4068028926849365} 08/31/2021 02:12:17 - INFO - __main__ - Step 72114: {'lr': 0.00027060391887873293, 'samples': 13845888, 'steps': 72113, 'loss/train': 1.0073245763778687} 08/31/2021 02:12:18 - INFO - __main__ - Step 72115: {'lr': 0.00027059863018306793, 'samples': 13846080, 'steps': 72114, 'loss/train': 1.190913438796997} 08/31/2021 02:12:19 - INFO - __main__ - Step 72116: {'lr': 0.0002705933414781214, 'samples': 13846272, 'steps': 72115, 'loss/train': 1.3037550449371338} 08/31/2021 02:12:19 - INFO - __main__ - Step 72117: {'lr': 0.00027058805276389595, 'samples': 13846464, 'steps': 72116, 'loss/train': 1.384641170501709} 08/31/2021 02:12:19 - INFO - __main__ - Step 72118: {'lr': 0.0002705827640403938, 'samples': 13846656, 'steps': 72117, 'loss/train': 0.0856870636343956} 08/31/2021 02:12:20 - INFO - __main__ - Step 72119: {'lr': 0.0002705774753076174, 'samples': 13846848, 'steps': 72118, 'loss/train': 1.0351265668869019} 08/31/2021 02:12:21 - INFO - __main__ - Step 72120: {'lr': 0.00027057218656556905, 'samples': 13847040, 'steps': 72119, 'loss/train': 0.804035484790802} 08/31/2021 02:12:22 - INFO - __main__ - Step 72121: {'lr': 0.0002705668978142512, 'samples': 13847232, 'steps': 72120, 'loss/train': 1.3275268077850342} 08/31/2021 02:12:22 - INFO - __main__ - Step 72122: {'lr': 0.0002705616090536662, 'samples': 13847424, 'steps': 72121, 'loss/train': 1.6969298124313354} 08/31/2021 02:12:22 - INFO - __main__ - Step 72123: {'lr': 0.0002705563202838165, 'samples': 13847616, 'steps': 72122, 'loss/train': 0.8371493220329285} 08/31/2021 02:12:23 - INFO - __main__ - Step 72124: {'lr': 0.0002705510315047044, 'samples': 13847808, 'steps': 72123, 'loss/train': 1.6161319017410278} 08/31/2021 02:12:25 - INFO - __main__ - Step 72125: {'lr': 0.00027054574271633236, 'samples': 13848000, 'steps': 72124, 'loss/train': 1.402915596961975} 08/31/2021 02:12:26 - INFO - __main__ - Step 72126: {'lr': 0.00027054045391870275, 'samples': 13848192, 'steps': 72125, 'loss/train': 1.3274896144866943} 08/31/2021 02:12:26 - INFO - __main__ - Step 72127: {'lr': 0.0002705351651118179, 'samples': 13848384, 'steps': 72126, 'loss/train': 1.053769826889038} 08/31/2021 02:12:26 - INFO - __main__ - Step 72128: {'lr': 0.0002705298762956802, 'samples': 13848576, 'steps': 72127, 'loss/train': 0.02158389240503311} 08/31/2021 02:12:27 - INFO - __main__ - Step 72129: {'lr': 0.00027052458747029204, 'samples': 13848768, 'steps': 72128, 'loss/train': 1.6153024435043335} 08/31/2021 02:12:27 - INFO - __main__ - Step 72130: {'lr': 0.0002705192986356559, 'samples': 13848960, 'steps': 72129, 'loss/train': 0.8258509039878845} 08/31/2021 02:12:27 - INFO - __main__ - Step 72131: {'lr': 0.00027051400979177396, 'samples': 13849152, 'steps': 72130, 'loss/train': 3.645742654800415} 08/31/2021 02:12:29 - INFO - __main__ - Step 72132: {'lr': 0.0002705087209386488, 'samples': 13849344, 'steps': 72131, 'loss/train': 1.4620691537857056} 08/31/2021 02:12:30 - INFO - __main__ - Step 72133: {'lr': 0.0002705034320762828, 'samples': 13849536, 'steps': 72132, 'loss/train': 0.9218935370445251} 08/31/2021 02:12:30 - INFO - __main__ - Step 72134: {'lr': 0.0002704981432046782, 'samples': 13849728, 'steps': 72133, 'loss/train': 1.3838883638381958} 08/31/2021 02:12:30 - INFO - __main__ - Step 72135: {'lr': 0.0002704928543238374, 'samples': 13849920, 'steps': 72134, 'loss/train': 1.5561814308166504} 08/31/2021 02:12:31 - INFO - __main__ - Step 72136: {'lr': 0.0002704875654337629, 'samples': 13850112, 'steps': 72135, 'loss/train': 1.2136379480361938} 08/31/2021 02:12:32 - INFO - __main__ - Step 72137: {'lr': 0.00027048227653445696, 'samples': 13850304, 'steps': 72136, 'loss/train': 0.7077997922897339} 08/31/2021 02:12:33 - INFO - __main__ - Step 72138: {'lr': 0.00027047698762592203, 'samples': 13850496, 'steps': 72137, 'loss/train': 1.6797447204589844} 08/31/2021 02:12:33 - INFO - __main__ - Step 72139: {'lr': 0.00027047169870816055, 'samples': 13850688, 'steps': 72138, 'loss/train': 1.2875269651412964} 08/31/2021 02:12:33 - INFO - __main__ - Step 72140: {'lr': 0.0002704664097811749, 'samples': 13850880, 'steps': 72139, 'loss/train': 1.4703963994979858} 08/31/2021 02:12:34 - INFO - __main__ - Step 72141: {'lr': 0.0002704611208449673, 'samples': 13851072, 'steps': 72140, 'loss/train': 0.3236922323703766} 08/31/2021 02:12:35 - INFO - __main__ - Step 72142: {'lr': 0.00027045583189954015, 'samples': 13851264, 'steps': 72141, 'loss/train': 1.6465325355529785} 08/31/2021 02:12:36 - INFO - __main__ - Step 72143: {'lr': 0.000270450542944896, 'samples': 13851456, 'steps': 72142, 'loss/train': 1.3059812784194946} 08/31/2021 02:12:36 - INFO - __main__ - Step 72144: {'lr': 0.0002704452539810372, 'samples': 13851648, 'steps': 72143, 'loss/train': 1.7072635889053345} 08/31/2021 02:12:36 - INFO - __main__ - Step 72145: {'lr': 0.00027043996500796604, 'samples': 13851840, 'steps': 72144, 'loss/train': 0.05559687316417694} 08/31/2021 02:12:37 - INFO - __main__ - Step 72146: {'lr': 0.00027043467602568493, 'samples': 13852032, 'steps': 72145, 'loss/train': 1.2567451000213623} 08/31/2021 02:12:38 - INFO - __main__ - Step 72147: {'lr': 0.00027042938703419634, 'samples': 13852224, 'steps': 72146, 'loss/train': 1.0730596780776978} 08/31/2021 02:12:39 - INFO - __main__ - Step 72148: {'lr': 0.00027042409803350255, 'samples': 13852416, 'steps': 72147, 'loss/train': 1.3298438787460327} 08/31/2021 02:12:39 - INFO - __main__ - Step 72149: {'lr': 0.00027041880902360595, 'samples': 13852608, 'steps': 72148, 'loss/train': 0.8417419195175171} 08/31/2021 02:12:39 - INFO - __main__ - Step 72150: {'lr': 0.0002704135200045089, 'samples': 13852800, 'steps': 72149, 'loss/train': 1.3635448217391968} 08/31/2021 02:12:40 - INFO - __main__ - Step 72151: {'lr': 0.00027040823097621393, 'samples': 13852992, 'steps': 72150, 'loss/train': 1.3842568397521973} 08/31/2021 02:12:40 - INFO - __main__ - Step 72152: {'lr': 0.0002704029419387233, 'samples': 13853184, 'steps': 72151, 'loss/train': 1.6138312816619873} 08/31/2021 02:12:41 - INFO - __main__ - Step 72153: {'lr': 0.00027039765289203944, 'samples': 13853376, 'steps': 72152, 'loss/train': 1.5085906982421875} 08/31/2021 02:12:42 - INFO - __main__ - Step 72154: {'lr': 0.00027039236383616464, 'samples': 13853568, 'steps': 72153, 'loss/train': 0.8128953576087952} 08/31/2021 02:12:42 - INFO - __main__ - Step 72155: {'lr': 0.0002703870747711014, 'samples': 13853760, 'steps': 72154, 'loss/train': 2.367262363433838} 08/31/2021 02:12:43 - INFO - __main__ - Step 72156: {'lr': 0.0002703817856968521, 'samples': 13853952, 'steps': 72155, 'loss/train': 1.439103603363037} 08/31/2021 02:12:43 - INFO - __main__ - Step 72157: {'lr': 0.00027037649661341897, 'samples': 13854144, 'steps': 72156, 'loss/train': 0.9675666093826294} 08/31/2021 02:12:44 - INFO - __main__ - Step 72158: {'lr': 0.00027037120752080457, 'samples': 13854336, 'steps': 72157, 'loss/train': 1.4611836671829224} 08/31/2021 02:12:45 - INFO - __main__ - Step 72159: {'lr': 0.0002703659184190112, 'samples': 13854528, 'steps': 72158, 'loss/train': 1.2010693550109863} 08/31/2021 02:12:45 - INFO - __main__ - Step 72160: {'lr': 0.0002703606293080413, 'samples': 13854720, 'steps': 72159, 'loss/train': 1.7751024961471558} 08/31/2021 02:12:46 - INFO - __main__ - Step 72161: {'lr': 0.00027035534018789723, 'samples': 13854912, 'steps': 72160, 'loss/train': 1.0594003200531006} 08/31/2021 02:12:46 - INFO - __main__ - Step 72162: {'lr': 0.0002703500510585813, 'samples': 13855104, 'steps': 72161, 'loss/train': 1.6987884044647217} 08/31/2021 02:12:47 - INFO - __main__ - Step 72163: {'lr': 0.00027034476192009597, 'samples': 13855296, 'steps': 72162, 'loss/train': 1.1441826820373535} 08/31/2021 02:12:48 - INFO - __main__ - Step 72164: {'lr': 0.0002703394727724436, 'samples': 13855488, 'steps': 72163, 'loss/train': 0.8365353941917419} 08/31/2021 02:12:48 - INFO - __main__ - Step 72165: {'lr': 0.0002703341836156266, 'samples': 13855680, 'steps': 72164, 'loss/train': 0.1104123517870903} 08/31/2021 02:12:49 - INFO - __main__ - Step 72166: {'lr': 0.00027032889444964734, 'samples': 13855872, 'steps': 72165, 'loss/train': 0.915063738822937} 08/31/2021 02:12:49 - INFO - __main__ - Step 72167: {'lr': 0.0002703236052745082, 'samples': 13856064, 'steps': 72166, 'loss/train': 1.2292263507843018} 08/31/2021 02:12:51 - INFO - __main__ - Step 72168: {'lr': 0.00027031831609021154, 'samples': 13856256, 'steps': 72167, 'loss/train': 1.3079272508621216} 08/31/2021 02:12:51 - INFO - __main__ - Step 72169: {'lr': 0.00027031302689675967, 'samples': 13856448, 'steps': 72168, 'loss/train': 1.0256322622299194} 08/31/2021 02:12:51 - INFO - __main__ - Step 72170: {'lr': 0.0002703077376941552, 'samples': 13856640, 'steps': 72169, 'loss/train': 1.0534428358078003} 08/31/2021 02:12:52 - INFO - __main__ - Step 72171: {'lr': 0.00027030244848240024, 'samples': 13856832, 'steps': 72170, 'loss/train': 1.1236858367919922} 08/31/2021 02:12:52 - INFO - __main__ - Step 72172: {'lr': 0.0002702971592614975, 'samples': 13857024, 'steps': 72171, 'loss/train': 0.9681483507156372} 08/31/2021 02:12:54 - INFO - __main__ - Step 72173: {'lr': 0.00027029187003144904, 'samples': 13857216, 'steps': 72172, 'loss/train': 1.6839979887008667} 08/31/2021 02:12:54 - INFO - __main__ - Step 72174: {'lr': 0.0002702865807922574, 'samples': 13857408, 'steps': 72173, 'loss/train': 1.0935349464416504} 08/31/2021 02:12:54 - INFO - __main__ - Step 72175: {'lr': 0.0002702812915439249, 'samples': 13857600, 'steps': 72174, 'loss/train': 1.3880244493484497} 08/31/2021 02:12:55 - INFO - __main__ - Step 72176: {'lr': 0.00027027600228645397, 'samples': 13857792, 'steps': 72175, 'loss/train': 1.4834109544754028} 08/31/2021 02:12:55 - INFO - __main__ - Step 72177: {'lr': 0.00027027071301984713, 'samples': 13857984, 'steps': 72176, 'loss/train': 1.2205692529678345} 08/31/2021 02:12:58 - INFO - __main__ - Step 72178: {'lr': 0.00027026542374410643, 'samples': 13858176, 'steps': 72177, 'loss/train': 0.594086766242981} 08/31/2021 02:12:58 - INFO - __main__ - Step 72179: {'lr': 0.0002702601344592346, 'samples': 13858368, 'steps': 72178, 'loss/train': 1.4179701805114746} 08/31/2021 02:12:59 - INFO - __main__ - Step 72180: {'lr': 0.00027025484516523374, 'samples': 13858560, 'steps': 72179, 'loss/train': 1.9558968544006348} 08/31/2021 02:12:59 - INFO - __main__ - Step 72181: {'lr': 0.0002702495558621064, 'samples': 13858752, 'steps': 72180, 'loss/train': 0.3171112537384033} 08/31/2021 02:12:59 - INFO - __main__ - Step 72182: {'lr': 0.0002702442665498549, 'samples': 13858944, 'steps': 72181, 'loss/train': 1.1402262449264526} 08/31/2021 02:13:00 - INFO - __main__ - Step 72183: {'lr': 0.00027023897722848174, 'samples': 13859136, 'steps': 72182, 'loss/train': 0.8366397023200989} 08/31/2021 02:13:01 - INFO - __main__ - Step 72184: {'lr': 0.00027023368789798915, 'samples': 13859328, 'steps': 72183, 'loss/train': 1.2874605655670166} 08/31/2021 02:13:02 - INFO - __main__ - Step 72185: {'lr': 0.00027022839855837957, 'samples': 13859520, 'steps': 72184, 'loss/train': 1.0688823461532593} 08/31/2021 02:13:02 - INFO - __main__ - Step 72186: {'lr': 0.00027022310920965536, 'samples': 13859712, 'steps': 72185, 'loss/train': 1.6763817071914673} 08/31/2021 02:13:03 - INFO - __main__ - Step 72187: {'lr': 0.0002702178198518189, 'samples': 13859904, 'steps': 72186, 'loss/train': 1.5651111602783203} 08/31/2021 02:13:03 - INFO - __main__ - Step 72188: {'lr': 0.0002702125304848727, 'samples': 13860096, 'steps': 72187, 'loss/train': 0.029041828587651253} 08/31/2021 02:13:04 - INFO - __main__ - Step 72189: {'lr': 0.000270207241108819, 'samples': 13860288, 'steps': 72188, 'loss/train': 0.7137012481689453} 08/31/2021 02:13:05 - INFO - __main__ - Step 72190: {'lr': 0.00027020195172366025, 'samples': 13860480, 'steps': 72189, 'loss/train': 1.2171568870544434} 08/31/2021 02:13:05 - INFO - __main__ - Step 72191: {'lr': 0.0002701966623293988, 'samples': 13860672, 'steps': 72190, 'loss/train': 1.4159492254257202} 08/31/2021 02:13:06 - INFO - __main__ - Step 72192: {'lr': 0.00027019137292603703, 'samples': 13860864, 'steps': 72191, 'loss/train': 1.4449901580810547} 08/31/2021 02:13:06 - INFO - __main__ - Step 72193: {'lr': 0.0002701860835135773, 'samples': 13861056, 'steps': 72192, 'loss/train': 1.0927919149398804} 08/31/2021 02:13:08 - INFO - __main__ - Step 72194: {'lr': 0.00027018079409202214, 'samples': 13861248, 'steps': 72193, 'loss/train': 0.48695793747901917} 08/31/2021 02:13:08 - INFO - __main__ - Step 72195: {'lr': 0.0002701755046613738, 'samples': 13861440, 'steps': 72194, 'loss/train': 1.0577619075775146} 08/31/2021 02:13:08 - INFO - __main__ - Step 72196: {'lr': 0.0002701702152216346, 'samples': 13861632, 'steps': 72195, 'loss/train': 1.2898343801498413} 08/31/2021 02:13:09 - INFO - __main__ - Step 72197: {'lr': 0.00027016492577280703, 'samples': 13861824, 'steps': 72196, 'loss/train': 1.099484920501709} 08/31/2021 02:13:09 - INFO - __main__ - Step 72198: {'lr': 0.0002701596363148935, 'samples': 13862016, 'steps': 72197, 'loss/train': 1.0237904787063599} 08/31/2021 02:13:11 - INFO - __main__ - Step 72199: {'lr': 0.0002701543468478963, 'samples': 13862208, 'steps': 72198, 'loss/train': 0.2580766975879669} 08/31/2021 02:13:11 - INFO - __main__ - Step 72200: {'lr': 0.000270149057371818, 'samples': 13862400, 'steps': 72199, 'loss/train': 2.1793651580810547} 08/31/2021 02:13:11 - INFO - __main__ - Step 72201: {'lr': 0.0002701437678866607, 'samples': 13862592, 'steps': 72200, 'loss/train': 0.9312063455581665} 08/31/2021 02:13:12 - INFO - __main__ - Step 72202: {'lr': 0.000270138478392427, 'samples': 13862784, 'steps': 72201, 'loss/train': 1.1657358407974243} 08/31/2021 02:13:12 - INFO - __main__ - Step 72203: {'lr': 0.0002701331888891191, 'samples': 13862976, 'steps': 72202, 'loss/train': 1.2601163387298584} 08/31/2021 02:13:12 - INFO - __main__ - Step 72204: {'lr': 0.00027012789937673964, 'samples': 13863168, 'steps': 72203, 'loss/train': 1.51908278465271} 08/31/2021 02:13:14 - INFO - __main__ - Step 72205: {'lr': 0.0002701226098552908, 'samples': 13863360, 'steps': 72204, 'loss/train': 1.3159502744674683} 08/31/2021 02:13:14 - INFO - __main__ - Step 72206: {'lr': 0.000270117320324775, 'samples': 13863552, 'steps': 72205, 'loss/train': 1.0837246179580688} 08/31/2021 02:13:15 - INFO - __main__ - Step 72207: {'lr': 0.00027011203078519474, 'samples': 13863744, 'steps': 72206, 'loss/train': 1.4597898721694946} 08/31/2021 02:13:15 - INFO - __main__ - Step 72208: {'lr': 0.0002701067412365522, 'samples': 13863936, 'steps': 72207, 'loss/train': 1.4587990045547485} 08/31/2021 02:13:16 - INFO - __main__ - Step 72209: {'lr': 0.00027010145167884994, 'samples': 13864128, 'steps': 72208, 'loss/train': 0.30149129033088684} 08/31/2021 02:13:17 - INFO - __main__ - Step 72210: {'lr': 0.0002700961621120902, 'samples': 13864320, 'steps': 72209, 'loss/train': 1.3983551263809204} 08/31/2021 02:13:18 - INFO - __main__ - Step 72211: {'lr': 0.0002700908725362755, 'samples': 13864512, 'steps': 72210, 'loss/train': 1.8790663480758667} 08/31/2021 02:13:18 - INFO - __main__ - Step 72212: {'lr': 0.00027008558295140816, 'samples': 13864704, 'steps': 72211, 'loss/train': 1.2378250360488892} 08/31/2021 02:13:18 - INFO - __main__ - Step 72213: {'lr': 0.00027008029335749055, 'samples': 13864896, 'steps': 72212, 'loss/train': 1.0457851886749268} 08/31/2021 02:13:19 - INFO - __main__ - Step 72214: {'lr': 0.0002700750037545251, 'samples': 13865088, 'steps': 72213, 'loss/train': 1.5430934429168701} 08/31/2021 02:13:21 - INFO - __main__ - Step 72215: {'lr': 0.0002700697141425141, 'samples': 13865280, 'steps': 72214, 'loss/train': 0.2597264051437378} 08/31/2021 02:13:21 - INFO - __main__ - Step 72216: {'lr': 0.00027006442452146007, 'samples': 13865472, 'steps': 72215, 'loss/train': 0.6935952305793762} 08/31/2021 02:13:21 - INFO - __main__ - Step 72217: {'lr': 0.0002700591348913653, 'samples': 13865664, 'steps': 72216, 'loss/train': 1.2429345846176147} 08/31/2021 02:13:22 - INFO - __main__ - Step 72218: {'lr': 0.00027005384525223216, 'samples': 13865856, 'steps': 72217, 'loss/train': 0.5495886206626892} 08/31/2021 02:13:22 - INFO - __main__ - Step 72219: {'lr': 0.00027004855560406303, 'samples': 13866048, 'steps': 72218, 'loss/train': 1.5898422002792358} 08/31/2021 02:13:23 - INFO - __main__ - Step 72220: {'lr': 0.0002700432659468605, 'samples': 13866240, 'steps': 72219, 'loss/train': 2.342695474624634} 08/31/2021 02:13:24 - INFO - __main__ - Step 72221: {'lr': 0.00027003797628062664, 'samples': 13866432, 'steps': 72220, 'loss/train': 1.2592804431915283} 08/31/2021 02:13:25 - INFO - __main__ - Step 72222: {'lr': 0.000270032686605364, 'samples': 13866624, 'steps': 72221, 'loss/train': 1.4799772500991821} 08/31/2021 02:13:25 - INFO - __main__ - Step 72223: {'lr': 0.00027002739692107494, 'samples': 13866816, 'steps': 72222, 'loss/train': 0.045244280248880386} 08/31/2021 02:13:25 - INFO - __main__ - Step 72224: {'lr': 0.00027002210722776185, 'samples': 13867008, 'steps': 72223, 'loss/train': 1.8105766773223877} 08/31/2021 02:13:26 - INFO - __main__ - Step 72225: {'lr': 0.0002700168175254271, 'samples': 13867200, 'steps': 72224, 'loss/train': 1.8140789270401} 08/31/2021 02:13:27 - INFO - __main__ - Step 72226: {'lr': 0.00027001152781407306, 'samples': 13867392, 'steps': 72225, 'loss/train': 1.184653401374817} 08/31/2021 02:13:28 - INFO - __main__ - Step 72227: {'lr': 0.00027000623809370224, 'samples': 13867584, 'steps': 72226, 'loss/train': 1.4569004774093628} 08/31/2021 02:13:28 - INFO - __main__ - Step 72228: {'lr': 0.0002700009483643168, 'samples': 13867776, 'steps': 72227, 'loss/train': 0.7020648121833801} 08/31/2021 02:13:28 - INFO - __main__ - Step 72229: {'lr': 0.0002699956586259193, 'samples': 13867968, 'steps': 72228, 'loss/train': 1.4901916980743408} 08/31/2021 02:13:29 - INFO - __main__ - Step 72230: {'lr': 0.000269990368878512, 'samples': 13868160, 'steps': 72229, 'loss/train': 1.2751822471618652} 08/31/2021 02:13:29 - INFO - __main__ - Step 72231: {'lr': 0.0002699850791220974, 'samples': 13868352, 'steps': 72230, 'loss/train': 1.357049584388733} 08/31/2021 02:13:31 - INFO - __main__ - Step 72232: {'lr': 0.00026997978935667784, 'samples': 13868544, 'steps': 72231, 'loss/train': 1.7835865020751953} 08/31/2021 02:13:31 - INFO - __main__ - Step 72233: {'lr': 0.0002699744995822557, 'samples': 13868736, 'steps': 72232, 'loss/train': 1.856255054473877} 08/31/2021 02:13:32 - INFO - __main__ - Step 72234: {'lr': 0.00026996920979883337, 'samples': 13868928, 'steps': 72233, 'loss/train': 0.6797049045562744} 08/31/2021 02:13:32 - INFO - __main__ - Step 72235: {'lr': 0.0002699639200064132, 'samples': 13869120, 'steps': 72234, 'loss/train': 0.6835712194442749} 08/31/2021 02:13:32 - INFO - __main__ - Step 72236: {'lr': 0.00026995863020499755, 'samples': 13869312, 'steps': 72235, 'loss/train': 0.03863028064370155} 08/31/2021 02:13:33 - INFO - __main__ - Step 72237: {'lr': 0.0002699533403945889, 'samples': 13869504, 'steps': 72236, 'loss/train': 2.9714131355285645} 08/31/2021 02:13:35 - INFO - __main__ - Step 72238: {'lr': 0.00026994805057518954, 'samples': 13869696, 'steps': 72237, 'loss/train': 0.9826887845993042} 08/31/2021 02:13:35 - INFO - __main__ - Step 72239: {'lr': 0.00026994276074680194, 'samples': 13869888, 'steps': 72238, 'loss/train': 1.3997336626052856} 08/31/2021 02:13:36 - INFO - __main__ - Step 72240: {'lr': 0.0002699374709094285, 'samples': 13870080, 'steps': 72239, 'loss/train': 0.6080203056335449} 08/31/2021 02:13:36 - INFO - __main__ - Step 72241: {'lr': 0.00026993218106307145, 'samples': 13870272, 'steps': 72240, 'loss/train': 1.51102876663208} 08/31/2021 02:13:36 - INFO - __main__ - Step 72242: {'lr': 0.0002699268912077333, 'samples': 13870464, 'steps': 72241, 'loss/train': 2.2751548290252686} 08/31/2021 02:13:38 - INFO - __main__ - Step 72243: {'lr': 0.00026992160134341637, 'samples': 13870656, 'steps': 72242, 'loss/train': 1.6170847415924072} 08/31/2021 02:13:38 - INFO - __main__ - Step 72244: {'lr': 0.00026991631147012306, 'samples': 13870848, 'steps': 72243, 'loss/train': 1.387176513671875} 08/31/2021 02:13:39 - INFO - __main__ - Step 72245: {'lr': 0.0002699110215878558, 'samples': 13871040, 'steps': 72244, 'loss/train': 1.6522314548492432} 08/31/2021 02:13:39 - INFO - __main__ - Step 72246: {'lr': 0.00026990573169661695, 'samples': 13871232, 'steps': 72245, 'loss/train': 1.4337600469589233} 08/31/2021 02:13:39 - INFO - __main__ - Step 72247: {'lr': 0.0002699004417964089, 'samples': 13871424, 'steps': 72246, 'loss/train': 1.533881664276123} 08/31/2021 02:13:40 - INFO - __main__ - Step 72248: {'lr': 0.000269895151887234, 'samples': 13871616, 'steps': 72247, 'loss/train': 1.2226965427398682} 08/31/2021 02:13:41 - INFO - __main__ - Step 72249: {'lr': 0.00026988986196909467, 'samples': 13871808, 'steps': 72248, 'loss/train': 1.594757080078125} 08/31/2021 02:13:42 - INFO - __main__ - Step 72250: {'lr': 0.0002698845720419932, 'samples': 13872000, 'steps': 72249, 'loss/train': 0.5669077634811401} 08/31/2021 02:13:42 - INFO - __main__ - Step 72251: {'lr': 0.0002698792821059321, 'samples': 13872192, 'steps': 72250, 'loss/train': 1.5827810764312744} 08/31/2021 02:13:42 - INFO - __main__ - Step 72252: {'lr': 0.00026987399216091366, 'samples': 13872384, 'steps': 72251, 'loss/train': 0.44361111521720886} 08/31/2021 02:13:43 - INFO - __main__ - Step 72253: {'lr': 0.00026986870220694037, 'samples': 13872576, 'steps': 72252, 'loss/train': 1.347524642944336} 08/31/2021 02:13:44 - INFO - __main__ - Step 72254: {'lr': 0.00026986341224401455, 'samples': 13872768, 'steps': 72253, 'loss/train': 1.639551043510437} 08/31/2021 02:13:45 - INFO - __main__ - Step 72255: {'lr': 0.0002698581222721386, 'samples': 13872960, 'steps': 72254, 'loss/train': 1.7764548063278198} 08/31/2021 02:13:45 - INFO - __main__ - Step 72256: {'lr': 0.0002698528322913148, 'samples': 13873152, 'steps': 72255, 'loss/train': 0.6658207774162292} 08/31/2021 02:13:45 - INFO - __main__ - Step 72257: {'lr': 0.00026984754230154566, 'samples': 13873344, 'steps': 72256, 'loss/train': 1.1202751398086548} 08/31/2021 02:13:46 - INFO - __main__ - Step 72258: {'lr': 0.00026984225230283353, 'samples': 13873536, 'steps': 72257, 'loss/train': 1.5853327512741089} 08/31/2021 02:13:47 - INFO - __main__ - Step 72259: {'lr': 0.0002698369622951808, 'samples': 13873728, 'steps': 72258, 'loss/train': 2.1750524044036865} 08/31/2021 02:13:48 - INFO - __main__ - Step 72260: {'lr': 0.00026983167227858984, 'samples': 13873920, 'steps': 72259, 'loss/train': 0.06348233669996262} 08/31/2021 02:13:48 - INFO - __main__ - Step 72261: {'lr': 0.00026982638225306305, 'samples': 13874112, 'steps': 72260, 'loss/train': 0.6912716627120972} 08/31/2021 02:13:49 - INFO - __main__ - Step 72262: {'lr': 0.0002698210922186027, 'samples': 13874304, 'steps': 72261, 'loss/train': 1.1424466371536255} 08/31/2021 02:13:49 - INFO - __main__ - Step 72263: {'lr': 0.0002698158021752114, 'samples': 13874496, 'steps': 72262, 'loss/train': 1.7089914083480835} 08/31/2021 02:13:51 - INFO - __main__ - Step 72264: {'lr': 0.00026981051212289134, 'samples': 13874688, 'steps': 72263, 'loss/train': 2.1300954818725586} 08/31/2021 02:13:51 - INFO - __main__ - Step 72265: {'lr': 0.0002698052220616449, 'samples': 13874880, 'steps': 72264, 'loss/train': 0.20581738650798798} 08/31/2021 02:13:51 - INFO - __main__ - Step 72266: {'lr': 0.0002697999319914747, 'samples': 13875072, 'steps': 72265, 'loss/train': 0.7920008301734924} 08/31/2021 02:13:52 - INFO - __main__ - Step 72267: {'lr': 0.0002697946419123829, 'samples': 13875264, 'steps': 72266, 'loss/train': 1.5287761688232422} 08/31/2021 02:13:52 - INFO - __main__ - Step 72268: {'lr': 0.00026978935182437187, 'samples': 13875456, 'steps': 72267, 'loss/train': 0.5916830897331238} 08/31/2021 02:13:52 - INFO - __main__ - Step 72269: {'lr': 0.0002697840617274441, 'samples': 13875648, 'steps': 72268, 'loss/train': 1.0348137617111206} 08/31/2021 02:13:54 - INFO - __main__ - Step 72270: {'lr': 0.00026977877162160193, 'samples': 13875840, 'steps': 72269, 'loss/train': 0.686562180519104} 08/31/2021 02:13:55 - INFO - __main__ - Step 72271: {'lr': 0.0002697734815068477, 'samples': 13876032, 'steps': 72270, 'loss/train': 0.029449203982949257} 08/31/2021 02:13:55 - INFO - __main__ - Step 72272: {'lr': 0.0002697681913831839, 'samples': 13876224, 'steps': 72271, 'loss/train': 1.3351728916168213} 08/31/2021 02:13:55 - INFO - __main__ - Step 72273: {'lr': 0.00026976290125061287, 'samples': 13876416, 'steps': 72272, 'loss/train': 1.6630642414093018} 08/31/2021 02:13:56 - INFO - __main__ - Step 72274: {'lr': 0.00026975761110913706, 'samples': 13876608, 'steps': 72273, 'loss/train': 1.8959908485412598} 08/31/2021 02:13:56 - INFO - __main__ - Step 72275: {'lr': 0.00026975232095875865, 'samples': 13876800, 'steps': 72274, 'loss/train': 0.09858129173517227} 08/31/2021 02:13:58 - INFO - __main__ - Step 72276: {'lr': 0.00026974703079948013, 'samples': 13876992, 'steps': 72275, 'loss/train': 1.0610910654067993} 08/31/2021 02:13:58 - INFO - __main__ - Step 72277: {'lr': 0.00026974174063130394, 'samples': 13877184, 'steps': 72276, 'loss/train': 1.457619309425354} 08/31/2021 02:13:58 - INFO - __main__ - Step 72278: {'lr': 0.00026973645045423253, 'samples': 13877376, 'steps': 72277, 'loss/train': 0.27487438917160034} 08/31/2021 02:13:59 - INFO - __main__ - Step 72279: {'lr': 0.00026973116026826805, 'samples': 13877568, 'steps': 72278, 'loss/train': 1.0326627492904663} 08/31/2021 02:13:59 - INFO - __main__ - Step 72280: {'lr': 0.000269725870073413, 'samples': 13877760, 'steps': 72279, 'loss/train': 0.28327685594558716} 08/31/2021 02:14:01 - INFO - __main__ - Step 72281: {'lr': 0.0002697205798696699, 'samples': 13877952, 'steps': 72280, 'loss/train': 1.1201720237731934} 08/31/2021 02:14:01 - INFO - __main__ - Step 72282: {'lr': 0.00026971528965704094, 'samples': 13878144, 'steps': 72281, 'loss/train': 1.4462852478027344} 08/31/2021 02:14:01 - INFO - __main__ - Step 72283: {'lr': 0.0002697099994355286, 'samples': 13878336, 'steps': 72282, 'loss/train': 1.3675183057785034} 08/31/2021 02:14:02 - INFO - __main__ - Step 72284: {'lr': 0.00026970470920513516, 'samples': 13878528, 'steps': 72283, 'loss/train': 1.4017993211746216} 08/31/2021 02:14:02 - INFO - __main__ - Step 72285: {'lr': 0.0002696994189658632, 'samples': 13878720, 'steps': 72284, 'loss/train': 1.2345499992370605} 08/31/2021 02:14:04 - INFO - __main__ - Step 72286: {'lr': 0.0002696941287177149, 'samples': 13878912, 'steps': 72285, 'loss/train': 1.502232551574707} 08/31/2021 02:14:04 - INFO - __main__ - Step 72287: {'lr': 0.0002696888384606928, 'samples': 13879104, 'steps': 72286, 'loss/train': 1.3250337839126587} 08/31/2021 02:14:04 - INFO - __main__ - Step 72288: {'lr': 0.0002696835481947992, 'samples': 13879296, 'steps': 72287, 'loss/train': 1.097527265548706} 08/31/2021 02:14:05 - INFO - __main__ - Step 72289: {'lr': 0.00026967825792003643, 'samples': 13879488, 'steps': 72288, 'loss/train': 0.03558628633618355} 08/31/2021 02:14:05 - INFO - __main__ - Step 72290: {'lr': 0.00026967296763640697, 'samples': 13879680, 'steps': 72289, 'loss/train': 0.5886280536651611} 08/31/2021 02:14:05 - INFO - __main__ - Step 72291: {'lr': 0.0002696676773439132, 'samples': 13879872, 'steps': 72290, 'loss/train': 1.3696142435073853} 08/31/2021 02:14:07 - INFO - __main__ - Step 72292: {'lr': 0.0002696623870425574, 'samples': 13880064, 'steps': 72291, 'loss/train': 2.0396249294281006} 08/31/2021 02:14:08 - INFO - __main__ - Step 72293: {'lr': 0.00026965709673234205, 'samples': 13880256, 'steps': 72292, 'loss/train': 1.5744905471801758} 08/31/2021 02:14:08 - INFO - __main__ - Step 72294: {'lr': 0.00026965180641326964, 'samples': 13880448, 'steps': 72293, 'loss/train': 1.3328702449798584} 08/31/2021 02:14:09 - INFO - __main__ - Step 72295: {'lr': 0.00026964651608534233, 'samples': 13880640, 'steps': 72294, 'loss/train': 0.9113600850105286} 08/31/2021 02:14:09 - INFO - __main__ - Step 72296: {'lr': 0.00026964122574856263, 'samples': 13880832, 'steps': 72295, 'loss/train': 1.6998814344406128} 08/31/2021 02:14:11 - INFO - __main__ - Step 72297: {'lr': 0.00026963593540293285, 'samples': 13881024, 'steps': 72296, 'loss/train': 1.2136600017547607} 08/31/2021 02:14:11 - INFO - __main__ - Step 72298: {'lr': 0.0002696306450484555, 'samples': 13881216, 'steps': 72297, 'loss/train': 0.8231152296066284} 08/31/2021 02:14:11 - INFO - __main__ - Step 72299: {'lr': 0.0002696253546851328, 'samples': 13881408, 'steps': 72298, 'loss/train': 0.7015904784202576} 08/31/2021 02:14:12 - INFO - __main__ - Step 72300: {'lr': 0.00026962006431296726, 'samples': 13881600, 'steps': 72299, 'loss/train': 1.3553979396820068} 08/31/2021 02:14:12 - INFO - __main__ - Step 72301: {'lr': 0.00026961477393196127, 'samples': 13881792, 'steps': 72300, 'loss/train': 0.7003491520881653} 08/31/2021 02:14:14 - INFO - __main__ - Step 72302: {'lr': 0.0002696094835421171, 'samples': 13881984, 'steps': 72301, 'loss/train': 1.0287044048309326} 08/31/2021 02:14:14 - INFO - __main__ - Step 72303: {'lr': 0.00026960419314343723, 'samples': 13882176, 'steps': 72302, 'loss/train': 1.1072815656661987} 08/31/2021 02:14:14 - INFO - __main__ - Step 72304: {'lr': 0.00026959890273592395, 'samples': 13882368, 'steps': 72303, 'loss/train': 0.8704538345336914} 08/31/2021 02:14:15 - INFO - __main__ - Step 72305: {'lr': 0.00026959361231957974, 'samples': 13882560, 'steps': 72304, 'loss/train': 0.6909866333007812} 08/31/2021 02:14:15 - INFO - __main__ - Step 72306: {'lr': 0.00026958832189440704, 'samples': 13882752, 'steps': 72305, 'loss/train': 1.6689372062683105} 08/31/2021 02:14:15 - INFO - __main__ - Step 72307: {'lr': 0.00026958303146040806, 'samples': 13882944, 'steps': 72306, 'loss/train': 0.8323312401771545} 08/31/2021 02:14:17 - INFO - __main__ - Step 72308: {'lr': 0.00026957774101758525, 'samples': 13883136, 'steps': 72307, 'loss/train': 0.7821879982948303} 08/31/2021 02:14:18 - INFO - __main__ - Step 72309: {'lr': 0.00026957245056594104, 'samples': 13883328, 'steps': 72308, 'loss/train': 1.407978892326355} 08/31/2021 02:14:18 - INFO - __main__ - Step 72310: {'lr': 0.0002695671601054778, 'samples': 13883520, 'steps': 72309, 'loss/train': 0.3236265778541565} 08/31/2021 02:14:19 - INFO - __main__ - Step 72311: {'lr': 0.0002695618696361979, 'samples': 13883712, 'steps': 72310, 'loss/train': 0.798716127872467} 08/31/2021 02:14:19 - INFO - __main__ - Step 72312: {'lr': 0.0002695565791581037, 'samples': 13883904, 'steps': 72311, 'loss/train': 1.0410178899765015} 08/31/2021 02:14:19 - INFO - __main__ - Step 72313: {'lr': 0.0002695512886711976, 'samples': 13884096, 'steps': 72312, 'loss/train': 0.2653714418411255} 08/31/2021 02:14:21 - INFO - __main__ - Step 72314: {'lr': 0.00026954599817548204, 'samples': 13884288, 'steps': 72313, 'loss/train': 0.9483033418655396} 08/31/2021 02:14:21 - INFO - __main__ - Step 72315: {'lr': 0.0002695407076709593, 'samples': 13884480, 'steps': 72314, 'loss/train': 1.7426594495773315} 08/31/2021 02:14:22 - INFO - __main__ - Step 72316: {'lr': 0.00026953541715763184, 'samples': 13884672, 'steps': 72315, 'loss/train': 1.1281040906906128} 08/31/2021 02:14:22 - INFO - __main__ - Step 72317: {'lr': 0.0002695301266355021, 'samples': 13884864, 'steps': 72316, 'loss/train': 1.5274832248687744} 08/31/2021 02:14:22 - INFO - __main__ - Step 72318: {'lr': 0.00026952483610457223, 'samples': 13885056, 'steps': 72317, 'loss/train': 1.1282832622528076} 08/31/2021 02:14:24 - INFO - __main__ - Step 72319: {'lr': 0.0002695195455648449, 'samples': 13885248, 'steps': 72318, 'loss/train': 1.5959864854812622} 08/31/2021 02:14:24 - INFO - __main__ - Step 72320: {'lr': 0.00026951425501632224, 'samples': 13885440, 'steps': 72319, 'loss/train': 1.5840513706207275} 08/31/2021 02:14:25 - INFO - __main__ - Step 72321: {'lr': 0.00026950896445900686, 'samples': 13885632, 'steps': 72320, 'loss/train': 1.4408738613128662} 08/31/2021 02:14:25 - INFO - __main__ - Step 72322: {'lr': 0.000269503673892901, 'samples': 13885824, 'steps': 72321, 'loss/train': 1.249897837638855} 08/31/2021 02:14:25 - INFO - __main__ - Step 72323: {'lr': 0.0002694983833180071, 'samples': 13886016, 'steps': 72322, 'loss/train': 1.3714118003845215} 08/31/2021 02:14:27 - INFO - __main__ - Step 72324: {'lr': 0.0002694930927343276, 'samples': 13886208, 'steps': 72323, 'loss/train': 1.2818543910980225} 08/31/2021 02:14:27 - INFO - __main__ - Step 72325: {'lr': 0.0002694878021418647, 'samples': 13886400, 'steps': 72324, 'loss/train': 1.2567174434661865} 08/31/2021 02:14:28 - INFO - __main__ - Step 72326: {'lr': 0.00026948251154062093, 'samples': 13886592, 'steps': 72325, 'loss/train': 1.0857877731323242} 08/31/2021 02:14:28 - INFO - __main__ - Step 72327: {'lr': 0.0002694772209305987, 'samples': 13886784, 'steps': 72326, 'loss/train': 0.8577544689178467} 08/31/2021 02:14:29 - INFO - __main__ - Step 72328: {'lr': 0.0002694719303118003, 'samples': 13886976, 'steps': 72327, 'loss/train': 0.9204802513122559} 08/31/2021 02:14:29 - INFO - __main__ - Step 72329: {'lr': 0.0002694666396842281, 'samples': 13887168, 'steps': 72328, 'loss/train': 0.7246614098548889} 08/31/2021 02:14:30 - INFO - __main__ - Step 72330: {'lr': 0.00026946134904788454, 'samples': 13887360, 'steps': 72329, 'loss/train': 1.8314744234085083} 08/31/2021 02:14:31 - INFO - __main__ - Step 72331: {'lr': 0.00026945605840277204, 'samples': 13887552, 'steps': 72330, 'loss/train': 1.300889015197754} 08/31/2021 02:14:31 - INFO - __main__ - Step 72332: {'lr': 0.0002694507677488929, 'samples': 13887744, 'steps': 72331, 'loss/train': 0.1082649752497673} 08/31/2021 02:14:32 - INFO - __main__ - Step 72333: {'lr': 0.00026944547708624957, 'samples': 13887936, 'steps': 72332, 'loss/train': 1.1299291849136353} 08/31/2021 02:14:32 - INFO - __main__ - Step 72334: {'lr': 0.00026944018641484447, 'samples': 13888128, 'steps': 72333, 'loss/train': 1.273540735244751} 08/31/2021 02:14:33 - INFO - __main__ - Step 72335: {'lr': 0.0002694348957346798, 'samples': 13888320, 'steps': 72334, 'loss/train': 1.5388572216033936} 08/31/2021 02:14:34 - INFO - __main__ - Step 72336: {'lr': 0.00026942960504575814, 'samples': 13888512, 'steps': 72335, 'loss/train': 0.2650742828845978} 08/31/2021 02:14:34 - INFO - __main__ - Step 72337: {'lr': 0.0002694243143480818, 'samples': 13888704, 'steps': 72336, 'loss/train': 0.988481879234314} 08/31/2021 02:14:35 - INFO - __main__ - Step 72338: {'lr': 0.0002694190236416531, 'samples': 13888896, 'steps': 72337, 'loss/train': 0.7506185173988342} 08/31/2021 02:14:35 - INFO - __main__ - Step 72339: {'lr': 0.00026941373292647453, 'samples': 13889088, 'steps': 72338, 'loss/train': 1.2069367170333862} 08/31/2021 02:14:36 - INFO - __main__ - Step 72340: {'lr': 0.00026940844220254846, 'samples': 13889280, 'steps': 72339, 'loss/train': 1.1526286602020264} 08/31/2021 02:14:37 - INFO - __main__ - Step 72341: {'lr': 0.00026940315146987726, 'samples': 13889472, 'steps': 72340, 'loss/train': 1.7882158756256104} 08/31/2021 02:14:37 - INFO - __main__ - Step 72342: {'lr': 0.0002693978607284632, 'samples': 13889664, 'steps': 72341, 'loss/train': 1.2919681072235107} 08/31/2021 02:14:38 - INFO - __main__ - Step 72343: {'lr': 0.0002693925699783089, 'samples': 13889856, 'steps': 72342, 'loss/train': 1.7219548225402832} 08/31/2021 02:14:38 - INFO - __main__ - Step 72344: {'lr': 0.00026938727921941647, 'samples': 13890048, 'steps': 72343, 'loss/train': 1.2948112487792969} 08/31/2021 02:14:38 - INFO - __main__ - Step 72345: {'lr': 0.0002693819884517885, 'samples': 13890240, 'steps': 72344, 'loss/train': 0.5518013834953308} 08/31/2021 02:14:40 - INFO - __main__ - Step 72346: {'lr': 0.0002693766976754273, 'samples': 13890432, 'steps': 72345, 'loss/train': 2.0110909938812256} 08/31/2021 02:14:41 - INFO - __main__ - Step 72347: {'lr': 0.00026937140689033525, 'samples': 13890624, 'steps': 72346, 'loss/train': 1.0362706184387207} 08/31/2021 02:14:41 - INFO - __main__ - Step 72348: {'lr': 0.0002693661160965147, 'samples': 13890816, 'steps': 72347, 'loss/train': 1.1826986074447632} 08/31/2021 02:14:42 - INFO - __main__ - Step 72349: {'lr': 0.00026936082529396816, 'samples': 13891008, 'steps': 72348, 'loss/train': 1.2530858516693115} 08/31/2021 02:14:42 - INFO - __main__ - Step 72350: {'lr': 0.0002693555344826979, 'samples': 13891200, 'steps': 72349, 'loss/train': 1.1553319692611694} 08/31/2021 02:14:43 - INFO - __main__ - Step 72351: {'lr': 0.00026935024366270635, 'samples': 13891392, 'steps': 72350, 'loss/train': 1.3692138195037842} 08/31/2021 02:14:44 - INFO - __main__ - Step 72352: {'lr': 0.00026934495283399587, 'samples': 13891584, 'steps': 72351, 'loss/train': 1.4967557191848755} 08/31/2021 02:14:44 - INFO - __main__ - Step 72353: {'lr': 0.0002693396619965688, 'samples': 13891776, 'steps': 72352, 'loss/train': 1.0041913986206055} 08/31/2021 02:14:45 - INFO - __main__ - Step 72354: {'lr': 0.0002693343711504276, 'samples': 13891968, 'steps': 72353, 'loss/train': 1.1842751502990723} 08/31/2021 02:14:45 - INFO - __main__ - Step 72355: {'lr': 0.00026932908029557467, 'samples': 13892160, 'steps': 72354, 'loss/train': 0.5270581841468811} 08/31/2021 02:14:46 - INFO - __main__ - Step 72356: {'lr': 0.00026932378943201235, 'samples': 13892352, 'steps': 72355, 'loss/train': 0.4460236132144928} 08/31/2021 02:14:47 - INFO - __main__ - Step 72357: {'lr': 0.000269318498559743, 'samples': 13892544, 'steps': 72356, 'loss/train': 0.9342917203903198} 08/31/2021 02:14:47 - INFO - __main__ - Step 72358: {'lr': 0.00026931320767876907, 'samples': 13892736, 'steps': 72357, 'loss/train': 1.5137261152267456} 08/31/2021 02:14:48 - INFO - __main__ - Step 72359: {'lr': 0.0002693079167890928, 'samples': 13892928, 'steps': 72358, 'loss/train': 1.482995629310608} 08/31/2021 02:14:48 - INFO - __main__ - Step 72360: {'lr': 0.0002693026258907168, 'samples': 13893120, 'steps': 72359, 'loss/train': 1.5314587354660034} 08/31/2021 02:14:50 - INFO - __main__ - Step 72361: {'lr': 0.00026929733498364336, 'samples': 13893312, 'steps': 72360, 'loss/train': 1.001082181930542} 08/31/2021 02:14:50 - INFO - __main__ - Step 72362: {'lr': 0.00026929204406787475, 'samples': 13893504, 'steps': 72361, 'loss/train': 0.404805451631546} 08/31/2021 02:14:50 - INFO - __main__ - Step 72363: {'lr': 0.0002692867531434135, 'samples': 13893696, 'steps': 72362, 'loss/train': 1.4692044258117676} 08/31/2021 02:14:51 - INFO - __main__ - Step 72364: {'lr': 0.0002692814622102619, 'samples': 13893888, 'steps': 72363, 'loss/train': 1.4651743173599243} 08/31/2021 02:14:51 - INFO - __main__ - Step 72365: {'lr': 0.00026927617126842234, 'samples': 13894080, 'steps': 72364, 'loss/train': 1.401835322380066} 08/31/2021 02:14:51 - INFO - __main__ - Step 72366: {'lr': 0.00026927088031789725, 'samples': 13894272, 'steps': 72365, 'loss/train': 0.9096024036407471} 08/31/2021 02:14:53 - INFO - __main__ - Step 72367: {'lr': 0.00026926558935868905, 'samples': 13894464, 'steps': 72366, 'loss/train': 0.055733270943164825} 08/31/2021 02:14:53 - INFO - __main__ - Step 72368: {'lr': 0.0002692602983908001, 'samples': 13894656, 'steps': 72367, 'loss/train': 1.8703336715698242} 08/31/2021 02:14:54 - INFO - __main__ - Step 72369: {'lr': 0.0002692550074142326, 'samples': 13894848, 'steps': 72368, 'loss/train': 1.4848804473876953} 08/31/2021 02:14:54 - INFO - __main__ - Step 72370: {'lr': 0.0002692497164289892, 'samples': 13895040, 'steps': 72369, 'loss/train': 1.3495419025421143} 08/31/2021 02:14:54 - INFO - __main__ - Step 72371: {'lr': 0.00026924442543507223, 'samples': 13895232, 'steps': 72370, 'loss/train': 1.3501745462417603} 08/31/2021 02:14:56 - INFO - __main__ - Step 72372: {'lr': 0.0002692391344324839, 'samples': 13895424, 'steps': 72371, 'loss/train': 0.183204784989357} 08/31/2021 02:14:56 - INFO - __main__ - Step 72373: {'lr': 0.00026923384342122676, 'samples': 13895616, 'steps': 72372, 'loss/train': 1.4158012866973877} 08/31/2021 02:14:57 - INFO - __main__ - Step 72374: {'lr': 0.0002692285524013032, 'samples': 13895808, 'steps': 72373, 'loss/train': 0.04021468386054039} 08/31/2021 02:14:57 - INFO - __main__ - Step 72375: {'lr': 0.00026922326137271554, 'samples': 13896000, 'steps': 72374, 'loss/train': 1.3543171882629395} 08/31/2021 02:14:57 - INFO - __main__ - Step 72376: {'lr': 0.0002692179703354661, 'samples': 13896192, 'steps': 72375, 'loss/train': 1.1566057205200195} 08/31/2021 02:14:59 - INFO - __main__ - Step 72377: {'lr': 0.0002692126792895574, 'samples': 13896384, 'steps': 72376, 'loss/train': 1.4566344022750854} 08/31/2021 02:14:59 - INFO - __main__ - Step 72378: {'lr': 0.00026920738823499167, 'samples': 13896576, 'steps': 72377, 'loss/train': 1.2625174522399902} 08/31/2021 02:15:00 - INFO - __main__ - Step 72379: {'lr': 0.00026920209717177146, 'samples': 13896768, 'steps': 72378, 'loss/train': 1.165475606918335} 08/31/2021 02:15:00 - INFO - __main__ - Step 72380: {'lr': 0.0002691968060998991, 'samples': 13896960, 'steps': 72379, 'loss/train': 1.3752671480178833} 08/31/2021 02:15:00 - INFO - __main__ - Step 72381: {'lr': 0.000269191515019377, 'samples': 13897152, 'steps': 72380, 'loss/train': 1.6267260313034058} 08/31/2021 02:15:02 - INFO - __main__ - Step 72382: {'lr': 0.0002691862239302074, 'samples': 13897344, 'steps': 72381, 'loss/train': 1.142656922340393} 08/31/2021 02:15:02 - INFO - __main__ - Step 72383: {'lr': 0.0002691809328323928, 'samples': 13897536, 'steps': 72382, 'loss/train': 1.5490769147872925} 08/31/2021 02:15:03 - INFO - __main__ - Step 72384: {'lr': 0.0002691756417259356, 'samples': 13897728, 'steps': 72383, 'loss/train': 1.0942339897155762} 08/31/2021 02:15:03 - INFO - __main__ - Step 72385: {'lr': 0.0002691703506108381, 'samples': 13897920, 'steps': 72384, 'loss/train': 0.02243773080408573} 08/31/2021 02:15:03 - INFO - __main__ - Step 72386: {'lr': 0.0002691650594871028, 'samples': 13898112, 'steps': 72385, 'loss/train': 1.0192737579345703} 08/31/2021 02:15:05 - INFO - __main__ - Step 72387: {'lr': 0.000269159768354732, 'samples': 13898304, 'steps': 72386, 'loss/train': 1.4139734506607056} 08/31/2021 02:15:05 - INFO - __main__ - Step 72388: {'lr': 0.0002691544772137281, 'samples': 13898496, 'steps': 72387, 'loss/train': 1.273564338684082} 08/31/2021 02:15:06 - INFO - __main__ - Step 72389: {'lr': 0.0002691491860640935, 'samples': 13898688, 'steps': 72388, 'loss/train': 0.7780843377113342} 08/31/2021 02:15:06 - INFO - __main__ - Step 72390: {'lr': 0.0002691438949058306, 'samples': 13898880, 'steps': 72389, 'loss/train': 1.5849196910858154} 08/31/2021 02:15:06 - INFO - __main__ - Step 72391: {'lr': 0.0002691386037389417, 'samples': 13899072, 'steps': 72390, 'loss/train': 0.7984572052955627} 08/31/2021 02:15:08 - INFO - __main__ - Step 72392: {'lr': 0.0002691333125634292, 'samples': 13899264, 'steps': 72391, 'loss/train': 1.909445881843567} 08/31/2021 02:15:09 - INFO - __main__ - Step 72393: {'lr': 0.0002691280213792956, 'samples': 13899456, 'steps': 72392, 'loss/train': 1.2436870336532593} 08/31/2021 02:15:09 - INFO - __main__ - Step 72394: {'lr': 0.0002691227301865432, 'samples': 13899648, 'steps': 72393, 'loss/train': 1.3836069107055664} 08/31/2021 02:15:09 - INFO - __main__ - Step 72395: {'lr': 0.00026911743898517436, 'samples': 13899840, 'steps': 72394, 'loss/train': 0.6191542148590088} 08/31/2021 02:15:10 - INFO - __main__ - Step 72396: {'lr': 0.00026911214777519156, 'samples': 13900032, 'steps': 72395, 'loss/train': 1.3562309741973877} 08/31/2021 02:15:10 - INFO - __main__ - Step 72397: {'lr': 0.00026910685655659705, 'samples': 13900224, 'steps': 72396, 'loss/train': 0.45928341150283813} 08/31/2021 02:15:12 - INFO - __main__ - Step 72398: {'lr': 0.00026910156532939327, 'samples': 13900416, 'steps': 72397, 'loss/train': 1.1622862815856934} 08/31/2021 02:15:12 - INFO - __main__ - Step 72399: {'lr': 0.00026909627409358266, 'samples': 13900608, 'steps': 72398, 'loss/train': 1.3383678197860718} 08/31/2021 02:15:12 - INFO - __main__ - Step 72400: {'lr': 0.0002690909828491676, 'samples': 13900800, 'steps': 72399, 'loss/train': 0.04197324067354202} 08/31/2021 02:15:13 - INFO - __main__ - Step 72401: {'lr': 0.0002690856915961504, 'samples': 13900992, 'steps': 72400, 'loss/train': 0.06526970863342285} 08/31/2021 02:15:13 - INFO - __main__ - Step 72402: {'lr': 0.00026908040033453353, 'samples': 13901184, 'steps': 72401, 'loss/train': 0.03348439931869507} 08/31/2021 02:15:15 - INFO - __main__ - Step 72403: {'lr': 0.0002690751090643193, 'samples': 13901376, 'steps': 72402, 'loss/train': 2.0166356563568115} 08/31/2021 02:15:16 - INFO - __main__ - Step 72404: {'lr': 0.00026906981778551, 'samples': 13901568, 'steps': 72403, 'loss/train': 1.4998897314071655} 08/31/2021 02:15:16 - INFO - __main__ - Step 72405: {'lr': 0.0002690645264981083, 'samples': 13901760, 'steps': 72404, 'loss/train': 1.689485788345337} 08/31/2021 02:15:16 - INFO - __main__ - Step 72406: {'lr': 0.00026905923520211634, 'samples': 13901952, 'steps': 72405, 'loss/train': 1.4039822816848755} 08/31/2021 02:15:17 - INFO - __main__ - Step 72407: {'lr': 0.0002690539438975366, 'samples': 13902144, 'steps': 72406, 'loss/train': 1.5668138265609741} 08/31/2021 02:15:18 - INFO - __main__ - Step 72408: {'lr': 0.0002690486525843715, 'samples': 13902336, 'steps': 72407, 'loss/train': 0.8498299717903137} 08/31/2021 02:15:19 - INFO - __main__ - Step 72409: {'lr': 0.0002690433612626233, 'samples': 13902528, 'steps': 72408, 'loss/train': 1.402642011642456} 08/31/2021 02:15:19 - INFO - __main__ - Step 72410: {'lr': 0.0002690380699322945, 'samples': 13902720, 'steps': 72409, 'loss/train': 1.7499408721923828} 08/31/2021 02:15:19 - INFO - __main__ - Step 72411: {'lr': 0.00026903277859338735, 'samples': 13902912, 'steps': 72410, 'loss/train': 1.300295352935791} 08/31/2021 02:15:20 - INFO - __main__ - Step 72412: {'lr': 0.00026902748724590435, 'samples': 13903104, 'steps': 72411, 'loss/train': 0.9999207854270935} 08/31/2021 02:15:21 - INFO - __main__ - Step 72413: {'lr': 0.00026902219588984796, 'samples': 13903296, 'steps': 72412, 'loss/train': 0.5019004344940186} 08/31/2021 02:15:22 - INFO - __main__ - Step 72414: {'lr': 0.00026901690452522036, 'samples': 13903488, 'steps': 72413, 'loss/train': 1.386711597442627} 08/31/2021 02:15:22 - INFO - __main__ - Step 72415: {'lr': 0.0002690116131520241, 'samples': 13903680, 'steps': 72414, 'loss/train': 1.0412094593048096} 08/31/2021 02:15:22 - INFO - __main__ - Step 72416: {'lr': 0.00026900632177026144, 'samples': 13903872, 'steps': 72415, 'loss/train': 1.1082264184951782} 08/31/2021 02:15:23 - INFO - __main__ - Step 72417: {'lr': 0.0002690010303799349, 'samples': 13904064, 'steps': 72416, 'loss/train': 1.264628291130066} 08/31/2021 02:15:23 - INFO - __main__ - Step 72418: {'lr': 0.0002689957389810467, 'samples': 13904256, 'steps': 72417, 'loss/train': 1.5921573638916016} 08/31/2021 02:15:24 - INFO - __main__ - Step 72419: {'lr': 0.00026899044757359937, 'samples': 13904448, 'steps': 72418, 'loss/train': 1.2879875898361206} 08/31/2021 02:15:25 - INFO - __main__ - Step 72420: {'lr': 0.0002689851561575952, 'samples': 13904640, 'steps': 72419, 'loss/train': 1.7204641103744507} 08/31/2021 02:15:25 - INFO - __main__ - Step 72421: {'lr': 0.00026897986473303667, 'samples': 13904832, 'steps': 72420, 'loss/train': 0.32122573256492615} 08/31/2021 02:15:26 - INFO - __main__ - Step 72422: {'lr': 0.0002689745732999261, 'samples': 13905024, 'steps': 72421, 'loss/train': 1.5823911428451538} 08/31/2021 02:15:26 - INFO - __main__ - Step 72423: {'lr': 0.00026896928185826587, 'samples': 13905216, 'steps': 72422, 'loss/train': 1.1259770393371582} 08/31/2021 02:15:27 - INFO - __main__ - Step 72424: {'lr': 0.00026896399040805835, 'samples': 13905408, 'steps': 72423, 'loss/train': 1.0089484453201294} 08/31/2021 02:15:28 - INFO - __main__ - Step 72425: {'lr': 0.0002689586989493059, 'samples': 13905600, 'steps': 72424, 'loss/train': 0.8861715793609619} 08/31/2021 02:15:28 - INFO - __main__ - Step 72426: {'lr': 0.000268953407482011, 'samples': 13905792, 'steps': 72425, 'loss/train': 1.4804952144622803} 08/31/2021 02:15:29 - INFO - __main__ - Step 72427: {'lr': 0.00026894811600617605, 'samples': 13905984, 'steps': 72426, 'loss/train': 1.661532998085022} 08/31/2021 02:15:29 - INFO - __main__ - Step 72428: {'lr': 0.0002689428245218033, 'samples': 13906176, 'steps': 72427, 'loss/train': 1.5344483852386475} 08/31/2021 02:15:31 - INFO - __main__ - Step 72429: {'lr': 0.00026893753302889524, 'samples': 13906368, 'steps': 72428, 'loss/train': 1.675782561302185} 08/31/2021 02:15:31 - INFO - __main__ - Step 72430: {'lr': 0.0002689322415274542, 'samples': 13906560, 'steps': 72429, 'loss/train': 0.8665429949760437} 08/31/2021 02:15:31 - INFO - __main__ - Step 72431: {'lr': 0.00026892695001748255, 'samples': 13906752, 'steps': 72430, 'loss/train': 0.048122793436050415} 08/31/2021 02:15:32 - INFO - __main__ - Step 72432: {'lr': 0.00026892165849898275, 'samples': 13906944, 'steps': 72431, 'loss/train': 0.8753800988197327} 08/31/2021 02:15:32 - INFO - __main__ - Step 72433: {'lr': 0.0002689163669719572, 'samples': 13907136, 'steps': 72432, 'loss/train': 1.2689521312713623} 08/31/2021 02:15:34 - INFO - __main__ - Step 72434: {'lr': 0.00026891107543640814, 'samples': 13907328, 'steps': 72433, 'loss/train': 0.17975430190563202} 08/31/2021 02:15:34 - INFO - __main__ - Step 72435: {'lr': 0.0002689057838923381, 'samples': 13907520, 'steps': 72434, 'loss/train': 1.4780186414718628} 08/31/2021 02:15:35 - INFO - __main__ - Step 72436: {'lr': 0.00026890049233974935, 'samples': 13907712, 'steps': 72435, 'loss/train': 0.6976523995399475} 08/31/2021 02:15:35 - INFO - __main__ - Step 72437: {'lr': 0.0002688952007786443, 'samples': 13907904, 'steps': 72436, 'loss/train': 1.0744777917861938} 08/31/2021 02:15:35 - INFO - __main__ - Step 72438: {'lr': 0.00026888990920902547, 'samples': 13908096, 'steps': 72437, 'loss/train': 1.4858417510986328} 08/31/2021 02:15:37 - INFO - __main__ - Step 72439: {'lr': 0.00026888461763089505, 'samples': 13908288, 'steps': 72438, 'loss/train': 1.0540874004364014} 08/31/2021 02:15:37 - INFO - __main__ - Step 72440: {'lr': 0.00026887932604425553, 'samples': 13908480, 'steps': 72439, 'loss/train': 0.8486223816871643} 08/31/2021 02:15:38 - INFO - __main__ - Step 72441: {'lr': 0.00026887403444910936, 'samples': 13908672, 'steps': 72440, 'loss/train': 1.0290594100952148} 08/31/2021 02:15:38 - INFO - __main__ - Step 72442: {'lr': 0.00026886874284545877, 'samples': 13908864, 'steps': 72441, 'loss/train': 0.4727453589439392} 08/31/2021 02:15:38 - INFO - __main__ - Step 72443: {'lr': 0.0002688634512333062, 'samples': 13909056, 'steps': 72442, 'loss/train': 1.1521961688995361} 08/31/2021 02:15:40 - INFO - __main__ - Step 72444: {'lr': 0.00026885815961265406, 'samples': 13909248, 'steps': 72443, 'loss/train': 1.4038711786270142} 08/31/2021 02:15:40 - INFO - __main__ - Step 72445: {'lr': 0.0002688528679835047, 'samples': 13909440, 'steps': 72444, 'loss/train': 0.7171943783760071} 08/31/2021 02:15:41 - INFO - __main__ - Step 72446: {'lr': 0.00026884757634586064, 'samples': 13909632, 'steps': 72445, 'loss/train': 0.9970467686653137} 08/31/2021 02:15:41 - INFO - __main__ - Step 72447: {'lr': 0.0002688422846997241, 'samples': 13909824, 'steps': 72446, 'loss/train': 1.19137442111969} 08/31/2021 02:15:42 - INFO - __main__ - Step 72448: {'lr': 0.00026883699304509743, 'samples': 13910016, 'steps': 72447, 'loss/train': 3.5729267597198486} 08/31/2021 02:15:42 - INFO - __main__ - Step 72449: {'lr': 0.00026883170138198323, 'samples': 13910208, 'steps': 72448, 'loss/train': 0.41064438223838806} 08/31/2021 02:15:43 - INFO - __main__ - Step 72450: {'lr': 0.0002688264097103836, 'samples': 13910400, 'steps': 72449, 'loss/train': 1.4305108785629272} 08/31/2021 02:15:44 - INFO - __main__ - Step 72451: {'lr': 0.0002688211180303013, 'samples': 13910592, 'steps': 72450, 'loss/train': 1.1406127214431763} 08/31/2021 02:15:44 - INFO - __main__ - Step 72452: {'lr': 0.00026881582634173836, 'samples': 13910784, 'steps': 72451, 'loss/train': 0.7754366993904114} 08/31/2021 02:15:45 - INFO - __main__ - Step 72453: {'lr': 0.0002688105346446973, 'samples': 13910976, 'steps': 72452, 'loss/train': 1.586470365524292} 08/31/2021 02:15:45 - INFO - __main__ - Step 72454: {'lr': 0.00026880524293918044, 'samples': 13911168, 'steps': 72453, 'loss/train': 1.4239588975906372} 08/31/2021 02:15:47 - INFO - __main__ - Step 72455: {'lr': 0.0002687999512251903, 'samples': 13911360, 'steps': 72454, 'loss/train': 1.7786555290222168} 08/31/2021 02:15:47 - INFO - __main__ - Step 72456: {'lr': 0.00026879465950272916, 'samples': 13911552, 'steps': 72455, 'loss/train': 2.087712049484253} 08/31/2021 02:15:48 - INFO - __main__ - Step 72457: {'lr': 0.0002687893677717995, 'samples': 13911744, 'steps': 72456, 'loss/train': 1.3254801034927368} 08/31/2021 02:15:48 - INFO - __main__ - Step 72458: {'lr': 0.0002687840760324036, 'samples': 13911936, 'steps': 72457, 'loss/train': 1.2096048593521118} 08/31/2021 02:15:48 - INFO - __main__ - Step 72459: {'lr': 0.00026877878428454395, 'samples': 13912128, 'steps': 72458, 'loss/train': 1.6170114278793335} 08/31/2021 02:15:50 - INFO - __main__ - Step 72460: {'lr': 0.00026877349252822283, 'samples': 13912320, 'steps': 72459, 'loss/train': 1.4037290811538696} 08/31/2021 02:15:50 - INFO - __main__ - Step 72461: {'lr': 0.0002687682007634426, 'samples': 13912512, 'steps': 72460, 'loss/train': 1.1301743984222412} 08/31/2021 02:15:51 - INFO - __main__ - Step 72462: {'lr': 0.0002687629089902058, 'samples': 13912704, 'steps': 72461, 'loss/train': 1.492825984954834} 08/31/2021 02:15:51 - INFO - __main__ - Step 72463: {'lr': 0.00026875761720851466, 'samples': 13912896, 'steps': 72462, 'loss/train': 1.2263529300689697} 08/31/2021 02:15:51 - INFO - __main__ - Step 72464: {'lr': 0.00026875232541837164, 'samples': 13913088, 'steps': 72463, 'loss/train': 1.4493370056152344} 08/31/2021 02:15:53 - INFO - __main__ - Step 72465: {'lr': 0.0002687470336197791, 'samples': 13913280, 'steps': 72464, 'loss/train': 1.2424585819244385} 08/31/2021 02:15:54 - INFO - __main__ - Step 72466: {'lr': 0.0002687417418127394, 'samples': 13913472, 'steps': 72465, 'loss/train': 1.1514497995376587} 08/31/2021 02:15:54 - INFO - __main__ - Step 72467: {'lr': 0.00026873644999725506, 'samples': 13913664, 'steps': 72466, 'loss/train': 0.7047415375709534} 08/31/2021 02:15:55 - INFO - __main__ - Step 72468: {'lr': 0.00026873115817332825, 'samples': 13913856, 'steps': 72467, 'loss/train': 1.6200963258743286} 08/31/2021 02:15:55 - INFO - __main__ - Step 72469: {'lr': 0.00026872586634096163, 'samples': 13914048, 'steps': 72468, 'loss/train': 1.5966286659240723} 08/31/2021 02:15:55 - INFO - __main__ - Step 72470: {'lr': 0.0002687205745001573, 'samples': 13914240, 'steps': 72469, 'loss/train': 0.06624601781368256} 08/31/2021 02:15:57 - INFO - __main__ - Step 72471: {'lr': 0.0002687152826509178, 'samples': 13914432, 'steps': 72470, 'loss/train': 0.11346552520990372} 08/31/2021 02:15:57 - INFO - __main__ - Step 72472: {'lr': 0.00026870999079324547, 'samples': 13914624, 'steps': 72471, 'loss/train': 1.5444658994674683} 08/31/2021 02:15:58 - INFO - __main__ - Step 72473: {'lr': 0.0002687046989271427, 'samples': 13914816, 'steps': 72472, 'loss/train': 1.0157538652420044} 08/31/2021 02:15:58 - INFO - __main__ - Step 72474: {'lr': 0.0002686994070526119, 'samples': 13915008, 'steps': 72473, 'loss/train': 1.4552819728851318} 08/31/2021 02:15:59 - INFO - __main__ - Step 72475: {'lr': 0.00026869411516965543, 'samples': 13915200, 'steps': 72474, 'loss/train': 1.8472670316696167} 08/31/2021 02:16:00 - INFO - __main__ - Step 72476: {'lr': 0.0002686888232782757, 'samples': 13915392, 'steps': 72475, 'loss/train': 1.4321173429489136} 08/31/2021 02:16:00 - INFO - __main__ - Step 72477: {'lr': 0.00026868353137847505, 'samples': 13915584, 'steps': 72476, 'loss/train': 1.0835342407226562} 08/31/2021 02:16:01 - INFO - __main__ - Step 72478: {'lr': 0.0002686782394702559, 'samples': 13915776, 'steps': 72477, 'loss/train': 1.4825308322906494} 08/31/2021 02:16:01 - INFO - __main__ - Step 72479: {'lr': 0.0002686729475536206, 'samples': 13915968, 'steps': 72478, 'loss/train': 0.9102644920349121} 08/31/2021 02:16:01 - INFO - __main__ - Step 72480: {'lr': 0.0002686676556285716, 'samples': 13916160, 'steps': 72479, 'loss/train': 1.6609597206115723} 08/31/2021 02:16:03 - INFO - __main__ - Step 72481: {'lr': 0.0002686623636951112, 'samples': 13916352, 'steps': 72480, 'loss/train': 1.0874245166778564} 08/31/2021 02:16:03 - INFO - __main__ - Step 72482: {'lr': 0.0002686570717532419, 'samples': 13916544, 'steps': 72481, 'loss/train': 1.2056349515914917} 08/31/2021 02:16:04 - INFO - __main__ - Step 72483: {'lr': 0.000268651779802966, 'samples': 13916736, 'steps': 72482, 'loss/train': 1.2354564666748047} 08/31/2021 02:16:04 - INFO - __main__ - Step 72484: {'lr': 0.0002686464878442858, 'samples': 13916928, 'steps': 72483, 'loss/train': 1.735910177230835} 08/31/2021 02:16:04 - INFO - __main__ - Step 72485: {'lr': 0.0002686411958772038, 'samples': 13917120, 'steps': 72484, 'loss/train': 0.9441967010498047} 08/31/2021 02:16:06 - INFO - __main__ - Step 72486: {'lr': 0.00026863590390172244, 'samples': 13917312, 'steps': 72485, 'loss/train': 0.9856163859367371} 08/31/2021 02:16:06 - INFO - __main__ - Step 72487: {'lr': 0.00026863061191784393, 'samples': 13917504, 'steps': 72486, 'loss/train': 0.8320234417915344} 08/31/2021 02:16:07 - INFO - __main__ - Step 72488: {'lr': 0.00026862531992557083, 'samples': 13917696, 'steps': 72487, 'loss/train': 0.9092441201210022} 08/31/2021 02:16:07 - INFO - __main__ - Step 72489: {'lr': 0.00026862002792490546, 'samples': 13917888, 'steps': 72488, 'loss/train': 1.0499509572982788} 08/31/2021 02:16:07 - INFO - __main__ - Step 72490: {'lr': 0.00026861473591585015, 'samples': 13918080, 'steps': 72489, 'loss/train': 1.4039710760116577} 08/31/2021 02:16:09 - INFO - __main__ - Step 72491: {'lr': 0.00026860944389840735, 'samples': 13918272, 'steps': 72490, 'loss/train': 1.163573145866394} 08/31/2021 02:16:10 - INFO - __main__ - Step 72492: {'lr': 0.00026860415187257943, 'samples': 13918464, 'steps': 72491, 'loss/train': 1.0213398933410645} 08/31/2021 02:16:10 - INFO - __main__ - Step 72493: {'lr': 0.00026859885983836874, 'samples': 13918656, 'steps': 72492, 'loss/train': 0.6494866013526917} 08/31/2021 02:16:10 - INFO - __main__ - Step 72494: {'lr': 0.00026859356779577765, 'samples': 13918848, 'steps': 72493, 'loss/train': 1.142940878868103} 08/31/2021 02:16:11 - INFO - __main__ - Step 72495: {'lr': 0.00026858827574480866, 'samples': 13919040, 'steps': 72494, 'loss/train': 1.1988614797592163} 08/31/2021 02:16:11 - INFO - __main__ - Step 72496: {'lr': 0.0002685829836854641, 'samples': 13919232, 'steps': 72495, 'loss/train': 1.3545743227005005} 08/31/2021 02:16:12 - INFO - __main__ - Step 72497: {'lr': 0.00026857769161774624, 'samples': 13919424, 'steps': 72496, 'loss/train': 1.2237046957015991} 08/31/2021 02:16:13 - INFO - __main__ - Step 72498: {'lr': 0.00026857239954165764, 'samples': 13919616, 'steps': 72497, 'loss/train': 1.8826913833618164} 08/31/2021 02:16:13 - INFO - __main__ - Step 72499: {'lr': 0.0002685671074572005, 'samples': 13919808, 'steps': 72498, 'loss/train': 1.2300653457641602} 08/31/2021 02:16:14 - INFO - __main__ - Step 72500: {'lr': 0.0002685618153643774, 'samples': 13920000, 'steps': 72499, 'loss/train': 1.3102253675460815} 08/31/2021 02:16:14 - INFO - __main__ - Step 72501: {'lr': 0.0002685565232631906, 'samples': 13920192, 'steps': 72500, 'loss/train': 1.0193508863449097} 08/31/2021 02:16:15 - INFO - __main__ - Step 72502: {'lr': 0.0002685512311536426, 'samples': 13920384, 'steps': 72501, 'loss/train': 1.5315489768981934} 08/31/2021 02:16:16 - INFO - __main__ - Step 72503: {'lr': 0.00026854593903573564, 'samples': 13920576, 'steps': 72502, 'loss/train': 1.309600591659546} 08/31/2021 02:16:16 - INFO - __main__ - Step 72504: {'lr': 0.00026854064690947217, 'samples': 13920768, 'steps': 72503, 'loss/train': 0.7757824659347534} 08/31/2021 02:16:17 - INFO - __main__ - Step 72505: {'lr': 0.00026853535477485454, 'samples': 13920960, 'steps': 72504, 'loss/train': 1.5952482223510742} 08/31/2021 02:16:17 - INFO - __main__ - Step 72506: {'lr': 0.0002685300626318852, 'samples': 13921152, 'steps': 72505, 'loss/train': 1.6621125936508179} 08/31/2021 02:16:19 - INFO - __main__ - Step 72507: {'lr': 0.00026852477048056647, 'samples': 13921344, 'steps': 72506, 'loss/train': 1.2519413232803345} 08/31/2021 02:16:19 - INFO - __main__ - Step 72508: {'lr': 0.00026851947832090073, 'samples': 13921536, 'steps': 72507, 'loss/train': 1.2833975553512573} 08/31/2021 02:16:20 - INFO - __main__ - Step 72509: {'lr': 0.0002685141861528905, 'samples': 13921728, 'steps': 72508, 'loss/train': 1.2184709310531616} 08/31/2021 02:16:20 - INFO - __main__ - Step 72510: {'lr': 0.000268508893976538, 'samples': 13921920, 'steps': 72509, 'loss/train': 1.1591953039169312} 08/31/2021 02:16:20 - INFO - __main__ - Step 72511: {'lr': 0.0002685036017918457, 'samples': 13922112, 'steps': 72510, 'loss/train': 1.0586416721343994} 08/31/2021 02:16:22 - INFO - __main__ - Step 72512: {'lr': 0.00026849830959881587, 'samples': 13922304, 'steps': 72511, 'loss/train': 1.1799975633621216} 08/31/2021 02:16:23 - INFO - __main__ - Step 72513: {'lr': 0.00026849301739745107, 'samples': 13922496, 'steps': 72512, 'loss/train': 1.6718589067459106} 08/31/2021 02:16:23 - INFO - __main__ - Step 72514: {'lr': 0.00026848772518775363, 'samples': 13922688, 'steps': 72513, 'loss/train': 1.2403583526611328} 08/31/2021 02:16:23 - INFO - __main__ - Step 72515: {'lr': 0.00026848243296972584, 'samples': 13922880, 'steps': 72514, 'loss/train': 1.6283683776855469} 08/31/2021 02:16:24 - INFO - __main__ - Step 72516: {'lr': 0.0002684771407433703, 'samples': 13923072, 'steps': 72515, 'loss/train': 1.2532650232315063} 08/31/2021 02:16:25 - INFO - __main__ - Step 72517: {'lr': 0.00026847184850868904, 'samples': 13923264, 'steps': 72516, 'loss/train': 1.7043848037719727} 08/31/2021 02:16:25 - INFO - __main__ - Step 72518: {'lr': 0.00026846655626568475, 'samples': 13923456, 'steps': 72517, 'loss/train': 1.3040016889572144} 08/31/2021 02:16:26 - INFO - __main__ - Step 72519: {'lr': 0.0002684612640143597, 'samples': 13923648, 'steps': 72518, 'loss/train': 1.0803614854812622} 08/31/2021 02:16:26 - INFO - __main__ - Step 72520: {'lr': 0.00026845597175471626, 'samples': 13923840, 'steps': 72519, 'loss/train': 1.4002666473388672} 08/31/2021 02:16:27 - INFO - __main__ - Step 72521: {'lr': 0.0002684506794867569, 'samples': 13924032, 'steps': 72520, 'loss/train': 1.2156678438186646} 08/31/2021 02:16:27 - INFO - __main__ - Step 72522: {'lr': 0.0002684453872104839, 'samples': 13924224, 'steps': 72521, 'loss/train': 0.7178241014480591} 08/31/2021 02:16:29 - INFO - __main__ - Step 72523: {'lr': 0.00026844009492589977, 'samples': 13924416, 'steps': 72522, 'loss/train': 1.8491171598434448} 08/31/2021 02:16:29 - INFO - __main__ - Step 72524: {'lr': 0.0002684348026330068, 'samples': 13924608, 'steps': 72523, 'loss/train': 2.163201093673706} 08/31/2021 02:16:30 - INFO - __main__ - Step 72525: {'lr': 0.00026842951033180735, 'samples': 13924800, 'steps': 72524, 'loss/train': 1.6336538791656494} 08/31/2021 02:16:30 - INFO - __main__ - Step 72526: {'lr': 0.00026842421802230384, 'samples': 13924992, 'steps': 72525, 'loss/train': 1.4241600036621094} 08/31/2021 02:16:30 - INFO - __main__ - Step 72527: {'lr': 0.00026841892570449866, 'samples': 13925184, 'steps': 72526, 'loss/train': 1.0242516994476318} 08/31/2021 02:16:32 - INFO - __main__ - Step 72528: {'lr': 0.00026841363337839417, 'samples': 13925376, 'steps': 72527, 'loss/train': 1.5715187788009644} 08/31/2021 02:16:33 - INFO - __main__ - Step 72529: {'lr': 0.00026840834104399294, 'samples': 13925568, 'steps': 72528, 'loss/train': 0.5641014575958252} 08/31/2021 02:16:33 - INFO - __main__ - Step 72530: {'lr': 0.0002684030487012971, 'samples': 13925760, 'steps': 72529, 'loss/train': 1.1975831985473633} 08/31/2021 02:16:33 - INFO - __main__ - Step 72531: {'lr': 0.00026839775635030907, 'samples': 13925952, 'steps': 72530, 'loss/train': 1.1931484937667847} 08/31/2021 02:16:34 - INFO - __main__ - Step 72532: {'lr': 0.0002683924639910313, 'samples': 13926144, 'steps': 72531, 'loss/train': 1.4869775772094727} 08/31/2021 02:16:34 - INFO - __main__ - Step 72533: {'lr': 0.00026838717162346623, 'samples': 13926336, 'steps': 72532, 'loss/train': 0.052785035222768784} 08/31/2021 02:16:36 - INFO - __main__ - Step 72534: {'lr': 0.00026838187924761617, 'samples': 13926528, 'steps': 72533, 'loss/train': 0.024734655395150185} 08/31/2021 02:16:36 - INFO - __main__ - Step 72535: {'lr': 0.00026837658686348345, 'samples': 13926720, 'steps': 72534, 'loss/train': 1.2585445642471313} 08/31/2021 02:16:36 - INFO - __main__ - Step 72536: {'lr': 0.0002683712944710706, 'samples': 13926912, 'steps': 72535, 'loss/train': 1.1307404041290283} 08/31/2021 02:16:37 - INFO - __main__ - Step 72537: {'lr': 0.0002683660020703799, 'samples': 13927104, 'steps': 72536, 'loss/train': 0.752778172492981} 08/31/2021 02:16:37 - INFO - __main__ - Step 72538: {'lr': 0.0002683607096614138, 'samples': 13927296, 'steps': 72537, 'loss/train': 1.1310068368911743} 08/31/2021 02:16:37 - INFO - __main__ - Step 72539: {'lr': 0.0002683554172441746, 'samples': 13927488, 'steps': 72538, 'loss/train': 1.3738861083984375} 08/31/2021 02:16:39 - INFO - __main__ - Step 72540: {'lr': 0.0002683501248186648, 'samples': 13927680, 'steps': 72539, 'loss/train': 0.2748982310295105} 08/31/2021 02:16:39 - INFO - __main__ - Step 72541: {'lr': 0.0002683448323848866, 'samples': 13927872, 'steps': 72540, 'loss/train': 1.269315242767334} 08/31/2021 02:16:40 - INFO - __main__ - Step 72542: {'lr': 0.0002683395399428426, 'samples': 13928064, 'steps': 72541, 'loss/train': 1.6915017366409302} 08/31/2021 02:16:40 - INFO - __main__ - Step 72543: {'lr': 0.0002683342474925351, 'samples': 13928256, 'steps': 72542, 'loss/train': 0.8825339674949646} 08/31/2021 02:16:40 - INFO - __main__ - Step 72544: {'lr': 0.00026832895503396643, 'samples': 13928448, 'steps': 72543, 'loss/train': 0.7457846403121948} 08/31/2021 02:16:42 - INFO - __main__ - Step 72545: {'lr': 0.00026832366256713896, 'samples': 13928640, 'steps': 72544, 'loss/train': 1.368367075920105} 08/31/2021 02:16:42 - INFO - __main__ - Step 72546: {'lr': 0.00026831837009205523, 'samples': 13928832, 'steps': 72545, 'loss/train': 1.1935617923736572} 08/31/2021 02:16:43 - INFO - __main__ - Step 72547: {'lr': 0.0002683130776087174, 'samples': 13929024, 'steps': 72546, 'loss/train': 0.9245227575302124} 08/31/2021 02:16:43 - INFO - __main__ - Step 72548: {'lr': 0.0002683077851171281, 'samples': 13929216, 'steps': 72547, 'loss/train': 1.1207990646362305} 08/31/2021 02:16:43 - INFO - __main__ - Step 72549: {'lr': 0.00026830249261728956, 'samples': 13929408, 'steps': 72548, 'loss/train': 1.3626755475997925} 08/31/2021 02:16:45 - INFO - __main__ - Step 72550: {'lr': 0.00026829720010920424, 'samples': 13929600, 'steps': 72549, 'loss/train': 1.340133786201477} 08/31/2021 02:16:45 - INFO - __main__ - Step 72551: {'lr': 0.00026829190759287443, 'samples': 13929792, 'steps': 72550, 'loss/train': 0.6631032228469849} 08/31/2021 02:16:46 - INFO - __main__ - Step 72552: {'lr': 0.00026828661506830256, 'samples': 13929984, 'steps': 72551, 'loss/train': 0.9996430277824402} 08/31/2021 02:16:46 - INFO - __main__ - Step 72553: {'lr': 0.00026828132253549103, 'samples': 13930176, 'steps': 72552, 'loss/train': 1.758979320526123} 08/31/2021 02:16:46 - INFO - __main__ - Step 72554: {'lr': 0.0002682760299944422, 'samples': 13930368, 'steps': 72553, 'loss/train': 1.3076356649398804} 08/31/2021 02:16:48 - INFO - __main__ - Step 72555: {'lr': 0.0002682707374451585, 'samples': 13930560, 'steps': 72554, 'loss/train': 1.56959068775177} 08/31/2021 02:16:48 - INFO - __main__ - Step 72556: {'lr': 0.00026826544488764236, 'samples': 13930752, 'steps': 72555, 'loss/train': 0.9473382830619812} 08/31/2021 02:16:49 - INFO - __main__ - Step 72557: {'lr': 0.00026826015232189596, 'samples': 13930944, 'steps': 72556, 'loss/train': 0.9540873765945435} 08/31/2021 02:16:49 - INFO - __main__ - Step 72558: {'lr': 0.0002682548597479219, 'samples': 13931136, 'steps': 72557, 'loss/train': 1.878682255744934} 08/31/2021 02:16:49 - INFO - __main__ - Step 72559: {'lr': 0.00026824956716572245, 'samples': 13931328, 'steps': 72558, 'loss/train': 1.1730936765670776} 08/31/2021 02:16:51 - INFO - __main__ - Step 72560: {'lr': 0.00026824427457530005, 'samples': 13931520, 'steps': 72559, 'loss/train': 1.657087802886963} 08/31/2021 02:16:52 - INFO - __main__ - Step 72561: {'lr': 0.000268238981976657, 'samples': 13931712, 'steps': 72560, 'loss/train': 1.4620158672332764} 08/31/2021 02:16:52 - INFO - __main__ - Step 72562: {'lr': 0.00026823368936979583, 'samples': 13931904, 'steps': 72561, 'loss/train': 0.9346069693565369} 08/31/2021 02:16:53 - INFO - __main__ - Step 72563: {'lr': 0.00026822839675471884, 'samples': 13932096, 'steps': 72562, 'loss/train': 0.703696072101593} 08/31/2021 02:16:53 - INFO - __main__ - Step 72564: {'lr': 0.00026822310413142836, 'samples': 13932288, 'steps': 72563, 'loss/train': 0.9063234925270081} 08/31/2021 02:16:55 - INFO - __main__ - Step 72565: {'lr': 0.00026821781149992684, 'samples': 13932480, 'steps': 72564, 'loss/train': 1.0874696969985962} 08/31/2021 02:16:55 - INFO - __main__ - Step 72566: {'lr': 0.0002682125188602167, 'samples': 13932672, 'steps': 72565, 'loss/train': 1.1966135501861572} 08/31/2021 02:16:55 - INFO - __main__ - Step 72567: {'lr': 0.0002682072262123002, 'samples': 13932864, 'steps': 72566, 'loss/train': 1.930899739265442} 08/31/2021 02:16:56 - INFO - __main__ - Step 72568: {'lr': 0.0002682019335561799, 'samples': 13933056, 'steps': 72567, 'loss/train': 1.3115696907043457} 08/31/2021 02:16:56 - INFO - __main__ - Step 72569: {'lr': 0.00026819664089185803, 'samples': 13933248, 'steps': 72568, 'loss/train': 0.8319618105888367} 08/31/2021 02:16:58 - INFO - __main__ - Step 72570: {'lr': 0.000268191348219337, 'samples': 13933440, 'steps': 72569, 'loss/train': 1.399375557899475} 08/31/2021 02:16:58 - INFO - __main__ - Step 72571: {'lr': 0.00026818605553861934, 'samples': 13933632, 'steps': 72570, 'loss/train': 0.8677547574043274} 08/31/2021 02:16:59 - INFO - __main__ - Step 72572: {'lr': 0.0002681807628497072, 'samples': 13933824, 'steps': 72571, 'loss/train': 1.1849168539047241} 08/31/2021 02:16:59 - INFO - __main__ - Step 72573: {'lr': 0.0002681754701526032, 'samples': 13934016, 'steps': 72572, 'loss/train': 1.0944201946258545} 08/31/2021 02:16:59 - INFO - __main__ - Step 72574: {'lr': 0.00026817017744730953, 'samples': 13934208, 'steps': 72573, 'loss/train': 1.4413748979568481} 08/31/2021 02:17:00 - INFO - __main__ - Step 72575: {'lr': 0.0002681648847338287, 'samples': 13934400, 'steps': 72574, 'loss/train': 1.4454609155654907} 08/31/2021 02:17:02 - INFO - __main__ - Step 72576: {'lr': 0.00026815959201216305, 'samples': 13934592, 'steps': 72575, 'loss/train': 1.3492318391799927} 08/31/2021 02:17:02 - INFO - __main__ - Step 72577: {'lr': 0.000268154299282315, 'samples': 13934784, 'steps': 72576, 'loss/train': 1.8421434164047241} 08/31/2021 02:17:03 - INFO - __main__ - Step 72578: {'lr': 0.00026814900654428684, 'samples': 13934976, 'steps': 72577, 'loss/train': 0.4851692318916321} 08/31/2021 02:17:03 - INFO - __main__ - Step 72579: {'lr': 0.000268143713798081, 'samples': 13935168, 'steps': 72578, 'loss/train': 0.40751445293426514} 08/31/2021 02:17:04 - INFO - __main__ - Step 72580: {'lr': 0.00026813842104370003, 'samples': 13935360, 'steps': 72579, 'loss/train': 0.35362786054611206} 08/31/2021 02:17:04 - INFO - __main__ - Step 72581: {'lr': 0.000268133128281146, 'samples': 13935552, 'steps': 72580, 'loss/train': 0.9788015484809875} 08/31/2021 02:17:05 - INFO - __main__ - Step 72582: {'lr': 0.00026812783551042154, 'samples': 13935744, 'steps': 72581, 'loss/train': 1.7521367073059082} 08/31/2021 02:17:06 - INFO - __main__ - Step 72583: {'lr': 0.0002681225427315289, 'samples': 13935936, 'steps': 72582, 'loss/train': 1.5492053031921387} 08/31/2021 02:17:06 - INFO - __main__ - Step 72584: {'lr': 0.00026811724994447056, 'samples': 13936128, 'steps': 72583, 'loss/train': 1.2722738981246948} 08/31/2021 02:17:07 - INFO - __main__ - Step 72585: {'lr': 0.00026811195714924893, 'samples': 13936320, 'steps': 72584, 'loss/train': 0.9422040581703186} 08/31/2021 02:17:07 - INFO - __main__ - Step 72586: {'lr': 0.0002681066643458663, 'samples': 13936512, 'steps': 72585, 'loss/train': 1.2749050855636597} 08/31/2021 02:17:08 - INFO - __main__ - Step 72587: {'lr': 0.00026810137153432503, 'samples': 13936704, 'steps': 72586, 'loss/train': 1.626928448677063} 08/31/2021 02:17:09 - INFO - __main__ - Step 72588: {'lr': 0.0002680960787146276, 'samples': 13936896, 'steps': 72587, 'loss/train': 1.4380656480789185} 08/31/2021 02:17:09 - INFO - __main__ - Step 72589: {'lr': 0.0002680907858867763, 'samples': 13937088, 'steps': 72588, 'loss/train': 1.2618260383605957} 08/31/2021 02:17:09 - INFO - __main__ - Step 72590: {'lr': 0.0002680854930507736, 'samples': 13937280, 'steps': 72589, 'loss/train': 1.2581515312194824} 08/31/2021 02:17:10 - INFO - __main__ - Step 72591: {'lr': 0.0002680802002066219, 'samples': 13937472, 'steps': 72590, 'loss/train': 1.5839159488677979} 08/31/2021 02:17:11 - INFO - __main__ - Step 72592: {'lr': 0.00026807490735432355, 'samples': 13937664, 'steps': 72591, 'loss/train': 0.5290898680686951} 08/31/2021 02:17:12 - INFO - __main__ - Step 72593: {'lr': 0.0002680696144938809, 'samples': 13937856, 'steps': 72592, 'loss/train': 1.303620457649231} 08/31/2021 02:17:12 - INFO - __main__ - Step 72594: {'lr': 0.0002680643216252963, 'samples': 13938048, 'steps': 72593, 'loss/train': 0.47253021597862244} 08/31/2021 02:17:12 - INFO - __main__ - Step 72595: {'lr': 0.0002680590287485722, 'samples': 13938240, 'steps': 72594, 'loss/train': 1.241157054901123} 08/31/2021 02:17:13 - INFO - __main__ - Step 72596: {'lr': 0.0002680537358637111, 'samples': 13938432, 'steps': 72595, 'loss/train': 0.5604168176651001} 08/31/2021 02:17:13 - INFO - __main__ - Step 72597: {'lr': 0.00026804844297071524, 'samples': 13938624, 'steps': 72596, 'loss/train': 1.4152311086654663} 08/31/2021 02:17:15 - INFO - __main__ - Step 72598: {'lr': 0.00026804315006958695, 'samples': 13938816, 'steps': 72597, 'loss/train': 1.3341805934906006} 08/31/2021 02:17:15 - INFO - __main__ - Step 72599: {'lr': 0.0002680378571603287, 'samples': 13939008, 'steps': 72598, 'loss/train': 1.1847715377807617} 08/31/2021 02:17:15 - INFO - __main__ - Step 72600: {'lr': 0.0002680325642429429, 'samples': 13939200, 'steps': 72599, 'loss/train': 1.9268519878387451} 08/31/2021 02:17:16 - INFO - __main__ - Step 72601: {'lr': 0.0002680272713174319, 'samples': 13939392, 'steps': 72600, 'loss/train': 2.2026526927948} 08/31/2021 02:17:17 - INFO - __main__ - Step 72602: {'lr': 0.00026802197838379804, 'samples': 13939584, 'steps': 72601, 'loss/train': 1.3014439344406128} 08/31/2021 02:17:18 - INFO - __main__ - Step 72603: {'lr': 0.0002680166854420439, 'samples': 13939776, 'steps': 72602, 'loss/train': 1.4226658344268799} 08/31/2021 02:17:18 - INFO - __main__ - Step 72604: {'lr': 0.0002680113924921716, 'samples': 13939968, 'steps': 72603, 'loss/train': 1.5599489212036133} 08/31/2021 02:17:18 - INFO - __main__ - Step 72605: {'lr': 0.0002680060995341836, 'samples': 13940160, 'steps': 72604, 'loss/train': 1.1729140281677246} 08/31/2021 02:17:19 - INFO - __main__ - Step 72606: {'lr': 0.00026800080656808246, 'samples': 13940352, 'steps': 72605, 'loss/train': 1.228993535041809} 08/31/2021 02:17:19 - INFO - __main__ - Step 72607: {'lr': 0.0002679955135938704, 'samples': 13940544, 'steps': 72606, 'loss/train': 0.21462196111679077} 08/31/2021 02:17:21 - INFO - __main__ - Step 72608: {'lr': 0.00026799022061154977, 'samples': 13940736, 'steps': 72607, 'loss/train': 1.5236605405807495} 08/31/2021 02:17:21 - INFO - __main__ - Step 72609: {'lr': 0.000267984927621123, 'samples': 13940928, 'steps': 72608, 'loss/train': 1.4814642667770386} 08/31/2021 02:17:21 - INFO - __main__ - Step 72610: {'lr': 0.00026797963462259265, 'samples': 13941120, 'steps': 72609, 'loss/train': 1.6837146282196045} 08/31/2021 02:17:22 - INFO - __main__ - Step 72611: {'lr': 0.00026797434161596087, 'samples': 13941312, 'steps': 72610, 'loss/train': 0.8390631079673767} 08/31/2021 02:17:22 - INFO - __main__ - Step 72612: {'lr': 0.0002679690486012301, 'samples': 13941504, 'steps': 72611, 'loss/train': 1.1200037002563477} 08/31/2021 02:17:24 - INFO - __main__ - Step 72613: {'lr': 0.0002679637555784028, 'samples': 13941696, 'steps': 72612, 'loss/train': 1.5056297779083252} 08/31/2021 02:17:24 - INFO - __main__ - Step 72614: {'lr': 0.00026795846254748127, 'samples': 13941888, 'steps': 72613, 'loss/train': 1.0958046913146973} 08/31/2021 02:17:24 - INFO - __main__ - Step 72615: {'lr': 0.00026795316950846795, 'samples': 13942080, 'steps': 72614, 'loss/train': 2.6628775596618652} 08/31/2021 02:17:25 - INFO - __main__ - Step 72616: {'lr': 0.0002679478764613652, 'samples': 13942272, 'steps': 72615, 'loss/train': 0.04593045637011528} 08/31/2021 02:17:25 - INFO - __main__ - Step 72617: {'lr': 0.0002679425834061755, 'samples': 13942464, 'steps': 72616, 'loss/train': 2.4251654148101807} 08/31/2021 02:17:27 - INFO - __main__ - Step 72618: {'lr': 0.00026793729034290103, 'samples': 13942656, 'steps': 72617, 'loss/train': 0.6612880825996399} 08/31/2021 02:17:28 - INFO - __main__ - Step 72619: {'lr': 0.0002679319972715443, 'samples': 13942848, 'steps': 72618, 'loss/train': 1.306248664855957} 08/31/2021 02:17:28 - INFO - __main__ - Step 72620: {'lr': 0.00026792670419210777, 'samples': 13943040, 'steps': 72619, 'loss/train': 1.4352929592132568} 08/31/2021 02:17:28 - INFO - __main__ - Step 72621: {'lr': 0.0002679214111045937, 'samples': 13943232, 'steps': 72620, 'loss/train': 1.1258635520935059} 08/31/2021 02:17:29 - INFO - __main__ - Step 72622: {'lr': 0.0002679161180090045, 'samples': 13943424, 'steps': 72621, 'loss/train': 1.3838136196136475} 08/31/2021 02:17:30 - INFO - __main__ - Step 72623: {'lr': 0.0002679108249053426, 'samples': 13943616, 'steps': 72622, 'loss/train': 1.6733767986297607} 08/31/2021 02:17:31 - INFO - __main__ - Step 72624: {'lr': 0.00026790553179361037, 'samples': 13943808, 'steps': 72623, 'loss/train': 1.4868971109390259} 08/31/2021 02:17:31 - INFO - __main__ - Step 72625: {'lr': 0.0002679002386738102, 'samples': 13944000, 'steps': 72624, 'loss/train': 1.1472309827804565} 08/31/2021 02:17:31 - INFO - __main__ - Step 72626: {'lr': 0.0002678949455459444, 'samples': 13944192, 'steps': 72625, 'loss/train': 0.6033019423484802} 08/31/2021 02:17:32 - INFO - __main__ - Step 72627: {'lr': 0.00026788965241001544, 'samples': 13944384, 'steps': 72626, 'loss/train': 1.0598773956298828} 08/31/2021 02:17:33 - INFO - __main__ - Step 72628: {'lr': 0.00026788435926602565, 'samples': 13944576, 'steps': 72627, 'loss/train': 1.3472315073013306} 08/31/2021 02:17:34 - INFO - __main__ - Step 72629: {'lr': 0.0002678790661139775, 'samples': 13944768, 'steps': 72628, 'loss/train': 1.5252656936645508} 08/31/2021 02:17:34 - INFO - __main__ - Step 72630: {'lr': 0.00026787377295387334, 'samples': 13944960, 'steps': 72629, 'loss/train': 0.3370198905467987} 08/31/2021 02:17:35 - INFO - __main__ - Step 72631: {'lr': 0.00026786847978571543, 'samples': 13945152, 'steps': 72630, 'loss/train': 1.1537632942199707} 08/31/2021 02:17:35 - INFO - __main__ - Step 72632: {'lr': 0.0002678631866095063, 'samples': 13945344, 'steps': 72631, 'loss/train': 1.0623284578323364} 08/31/2021 02:17:36 - INFO - __main__ - Step 72633: {'lr': 0.0002678578934252483, 'samples': 13945536, 'steps': 72632, 'loss/train': 0.5610310435295105} 08/31/2021 02:17:37 - INFO - __main__ - Step 72634: {'lr': 0.0002678526002329438, 'samples': 13945728, 'steps': 72633, 'loss/train': 0.9688615202903748} 08/31/2021 02:17:37 - INFO - __main__ - Step 72635: {'lr': 0.00026784730703259524, 'samples': 13945920, 'steps': 72634, 'loss/train': 1.5678184032440186} 08/31/2021 02:17:38 - INFO - __main__ - Step 72636: {'lr': 0.0002678420138242049, 'samples': 13946112, 'steps': 72635, 'loss/train': 0.8365487456321716} 08/31/2021 02:17:38 - INFO - __main__ - Step 72637: {'lr': 0.0002678367206077753, 'samples': 13946304, 'steps': 72636, 'loss/train': 0.9165943264961243} 08/31/2021 02:17:38 - INFO - __main__ - Step 72638: {'lr': 0.00026783142738330865, 'samples': 13946496, 'steps': 72637, 'loss/train': 0.9638664722442627} 08/31/2021 02:17:40 - INFO - __main__ - Step 72639: {'lr': 0.0002678261341508075, 'samples': 13946688, 'steps': 72638, 'loss/train': 1.379464030265808} 08/31/2021 02:17:41 - INFO - __main__ - Step 72640: {'lr': 0.0002678208409102742, 'samples': 13946880, 'steps': 72639, 'loss/train': 1.9421802759170532} 08/31/2021 02:17:41 - INFO - __main__ - Step 72641: {'lr': 0.00026781554766171104, 'samples': 13947072, 'steps': 72640, 'loss/train': 0.8523021340370178} 08/31/2021 02:17:42 - INFO - __main__ - Step 72642: {'lr': 0.00026781025440512045, 'samples': 13947264, 'steps': 72641, 'loss/train': 1.1648839712142944} 08/31/2021 02:17:42 - INFO - __main__ - Step 72643: {'lr': 0.0002678049611405049, 'samples': 13947456, 'steps': 72642, 'loss/train': 1.3840078115463257} 08/31/2021 02:17:42 - INFO - __main__ - Step 72644: {'lr': 0.0002677996678678667, 'samples': 13947648, 'steps': 72643, 'loss/train': 1.0474252700805664} 08/31/2021 02:17:44 - INFO - __main__ - Step 72645: {'lr': 0.0002677943745872082, 'samples': 13947840, 'steps': 72644, 'loss/train': 0.958203136920929} 08/31/2021 02:17:44 - INFO - __main__ - Step 72646: {'lr': 0.00026778908129853187, 'samples': 13948032, 'steps': 72645, 'loss/train': 0.09695811569690704} 08/31/2021 02:17:45 - INFO - __main__ - Step 72647: {'lr': 0.00026778378800184, 'samples': 13948224, 'steps': 72646, 'loss/train': 1.7631818056106567} 08/31/2021 02:17:45 - INFO - __main__ - Step 72648: {'lr': 0.00026777849469713513, 'samples': 13948416, 'steps': 72647, 'loss/train': 1.6355243921279907} 08/31/2021 02:17:45 - INFO - __main__ - Step 72649: {'lr': 0.0002677732013844194, 'samples': 13948608, 'steps': 72648, 'loss/train': 1.6804397106170654} 08/31/2021 02:17:47 - INFO - __main__ - Step 72650: {'lr': 0.0002677679080636955, 'samples': 13948800, 'steps': 72649, 'loss/train': 1.7406766414642334} 08/31/2021 02:17:47 - INFO - __main__ - Step 72651: {'lr': 0.00026776261473496557, 'samples': 13948992, 'steps': 72650, 'loss/train': 0.9583122730255127} 08/31/2021 02:17:48 - INFO - __main__ - Step 72652: {'lr': 0.00026775732139823206, 'samples': 13949184, 'steps': 72651, 'loss/train': 0.9831607937812805} 08/31/2021 02:17:48 - INFO - __main__ - Step 72653: {'lr': 0.0002677520280534974, 'samples': 13949376, 'steps': 72652, 'loss/train': 1.63720703125} 08/31/2021 02:17:48 - INFO - __main__ - Step 72654: {'lr': 0.00026774673470076395, 'samples': 13949568, 'steps': 72653, 'loss/train': 0.40848496556282043} 08/31/2021 02:17:49 - INFO - __main__ - Step 72655: {'lr': 0.00026774144134003407, 'samples': 13949760, 'steps': 72654, 'loss/train': 0.9667925238609314} 08/31/2021 02:17:50 - INFO - __main__ - Step 72656: {'lr': 0.00026773614797131025, 'samples': 13949952, 'steps': 72655, 'loss/train': 1.4918394088745117} 08/31/2021 02:17:51 - INFO - __main__ - Step 72657: {'lr': 0.0002677308545945948, 'samples': 13950144, 'steps': 72656, 'loss/train': 1.7425403594970703} 08/31/2021 02:17:51 - INFO - __main__ - Step 72658: {'lr': 0.00026772556120989, 'samples': 13950336, 'steps': 72657, 'loss/train': 1.6110506057739258} 08/31/2021 02:17:52 - INFO - __main__ - Step 72659: {'lr': 0.00026772026781719837, 'samples': 13950528, 'steps': 72658, 'loss/train': 1.5487130880355835} 08/31/2021 02:17:52 - INFO - __main__ - Step 72660: {'lr': 0.00026771497441652225, 'samples': 13950720, 'steps': 72659, 'loss/train': 1.172010064125061} 08/31/2021 02:17:53 - INFO - __main__ - Step 72661: {'lr': 0.00026770968100786407, 'samples': 13950912, 'steps': 72660, 'loss/train': 1.6014950275421143} 08/31/2021 02:17:54 - INFO - __main__ - Step 72662: {'lr': 0.00026770438759122616, 'samples': 13951104, 'steps': 72661, 'loss/train': 1.3496054410934448} 08/31/2021 02:17:54 - INFO - __main__ - Step 72663: {'lr': 0.0002676990941666109, 'samples': 13951296, 'steps': 72662, 'loss/train': 1.5449917316436768} 08/31/2021 02:17:55 - INFO - __main__ - Step 72664: {'lr': 0.00026769380073402076, 'samples': 13951488, 'steps': 72663, 'loss/train': 1.261541485786438} 08/31/2021 02:17:55 - INFO - __main__ - Step 72665: {'lr': 0.0002676885072934581, 'samples': 13951680, 'steps': 72664, 'loss/train': 1.1515530347824097} 08/31/2021 02:17:56 - INFO - __main__ - Step 72666: {'lr': 0.00026768321384492517, 'samples': 13951872, 'steps': 72665, 'loss/train': 2.1222479343414307} 08/31/2021 02:17:57 - INFO - __main__ - Step 72667: {'lr': 0.00026767792038842446, 'samples': 13952064, 'steps': 72666, 'loss/train': 1.231149435043335} 08/31/2021 02:17:57 - INFO - __main__ - Step 72668: {'lr': 0.00026767262692395843, 'samples': 13952256, 'steps': 72667, 'loss/train': 0.5374219417572021} 08/31/2021 02:17:57 - INFO - __main__ - Step 72669: {'lr': 0.0002676673334515293, 'samples': 13952448, 'steps': 72668, 'loss/train': 1.9413540363311768} 08/31/2021 02:17:58 - INFO - __main__ - Step 72670: {'lr': 0.00026766203997113957, 'samples': 13952640, 'steps': 72669, 'loss/train': 1.1304140090942383} 08/31/2021 02:18:00 - INFO - __main__ - Step 72671: {'lr': 0.0002676567464827917, 'samples': 13952832, 'steps': 72670, 'loss/train': 1.8231074810028076} 08/31/2021 02:18:00 - INFO - __main__ - Step 72672: {'lr': 0.00026765145298648794, 'samples': 13953024, 'steps': 72671, 'loss/train': 1.254810094833374} 08/31/2021 02:18:01 - INFO - __main__ - Step 72673: {'lr': 0.0002676461594822306, 'samples': 13953216, 'steps': 72672, 'loss/train': 0.9281531572341919} 08/31/2021 02:18:01 - INFO - __main__ - Step 72674: {'lr': 0.00026764086597002223, 'samples': 13953408, 'steps': 72673, 'loss/train': 1.4499300718307495} 08/31/2021 02:18:01 - INFO - __main__ - Step 72675: {'lr': 0.00026763557244986513, 'samples': 13953600, 'steps': 72674, 'loss/train': 1.235424280166626} 08/31/2021 02:18:02 - INFO - __main__ - Step 72676: {'lr': 0.0002676302789217617, 'samples': 13953792, 'steps': 72675, 'loss/train': 0.3643442988395691} 08/31/2021 02:18:03 - INFO - __main__ - Step 72677: {'lr': 0.00026762498538571443, 'samples': 13953984, 'steps': 72676, 'loss/train': 1.4690757989883423} 08/31/2021 02:18:04 - INFO - __main__ - Step 72678: {'lr': 0.0002676196918417256, 'samples': 13954176, 'steps': 72677, 'loss/train': 1.7314800024032593} 08/31/2021 02:18:04 - INFO - __main__ - Step 72679: {'lr': 0.0002676143982897976, 'samples': 13954368, 'steps': 72678, 'loss/train': 1.7252506017684937} 08/31/2021 02:18:04 - INFO - __main__ - Step 72680: {'lr': 0.0002676091047299327, 'samples': 13954560, 'steps': 72679, 'loss/train': 1.0300512313842773} 08/31/2021 02:18:05 - INFO - __main__ - Step 72681: {'lr': 0.00026760381116213355, 'samples': 13954752, 'steps': 72680, 'loss/train': 1.1234447956085205} 08/31/2021 02:18:07 - INFO - __main__ - Step 72682: {'lr': 0.00026759851758640236, 'samples': 13954944, 'steps': 72681, 'loss/train': 0.9408932328224182} 08/31/2021 02:18:07 - INFO - __main__ - Step 72683: {'lr': 0.0002675932240027415, 'samples': 13955136, 'steps': 72682, 'loss/train': 0.8595715761184692} 08/31/2021 02:18:07 - INFO - __main__ - Step 72684: {'lr': 0.00026758793041115346, 'samples': 13955328, 'steps': 72683, 'loss/train': 1.3420493602752686} 08/31/2021 02:18:08 - INFO - __main__ - Step 72685: {'lr': 0.00026758263681164057, 'samples': 13955520, 'steps': 72684, 'loss/train': 1.1141947507858276} 08/31/2021 02:18:08 - INFO - __main__ - Step 72686: {'lr': 0.0002675773432042052, 'samples': 13955712, 'steps': 72685, 'loss/train': 0.9098474383354187} 08/31/2021 02:18:08 - INFO - __main__ - Step 72687: {'lr': 0.00026757204958884973, 'samples': 13955904, 'steps': 72686, 'loss/train': 1.2916085720062256} 08/31/2021 02:18:10 - INFO - __main__ - Step 72688: {'lr': 0.0002675667559655766, 'samples': 13956096, 'steps': 72687, 'loss/train': 0.5376352667808533} 08/31/2021 02:18:10 - INFO - __main__ - Step 72689: {'lr': 0.00026756146233438815, 'samples': 13956288, 'steps': 72688, 'loss/train': 1.1984341144561768} 08/31/2021 02:18:11 - INFO - __main__ - Step 72690: {'lr': 0.00026755616869528675, 'samples': 13956480, 'steps': 72689, 'loss/train': 1.2150715589523315} 08/31/2021 02:18:11 - INFO - __main__ - Step 72691: {'lr': 0.00026755087504827486, 'samples': 13956672, 'steps': 72690, 'loss/train': 0.8520966172218323} 08/31/2021 02:18:11 - INFO - __main__ - Step 72692: {'lr': 0.0002675455813933548, 'samples': 13956864, 'steps': 72691, 'loss/train': 1.6009548902511597} 08/31/2021 02:18:13 - INFO - __main__ - Step 72693: {'lr': 0.00026754028773052894, 'samples': 13957056, 'steps': 72692, 'loss/train': 1.3968857526779175} 08/31/2021 02:18:13 - INFO - __main__ - Step 72694: {'lr': 0.00026753499405979974, 'samples': 13957248, 'steps': 72693, 'loss/train': 1.0002222061157227} 08/31/2021 02:18:14 - INFO - __main__ - Step 72695: {'lr': 0.0002675297003811695, 'samples': 13957440, 'steps': 72694, 'loss/train': 1.4080429077148438} 08/31/2021 02:18:14 - INFO - __main__ - Step 72696: {'lr': 0.0002675244066946407, 'samples': 13957632, 'steps': 72695, 'loss/train': 1.3976143598556519} 08/31/2021 02:18:14 - INFO - __main__ - Step 72697: {'lr': 0.00026751911300021565, 'samples': 13957824, 'steps': 72696, 'loss/train': 0.966826856136322} 08/31/2021 02:18:16 - INFO - __main__ - Step 72698: {'lr': 0.00026751381929789676, 'samples': 13958016, 'steps': 72697, 'loss/train': 1.7557929754257202} 08/31/2021 02:18:16 - INFO - __main__ - Step 72699: {'lr': 0.00026750852558768634, 'samples': 13958208, 'steps': 72698, 'loss/train': 1.6581112146377563} 08/31/2021 02:18:17 - INFO - __main__ - Step 72700: {'lr': 0.00026750323186958694, 'samples': 13958400, 'steps': 72699, 'loss/train': 1.7667542695999146} 08/31/2021 02:18:17 - INFO - __main__ - Step 72701: {'lr': 0.0002674979381436008, 'samples': 13958592, 'steps': 72700, 'loss/train': 0.7495783567428589} 08/31/2021 02:18:17 - INFO - __main__ - Step 72702: {'lr': 0.00026749264440973036, 'samples': 13958784, 'steps': 72701, 'loss/train': 0.895966112613678} 08/31/2021 02:18:19 - INFO - __main__ - Step 72703: {'lr': 0.000267487350667978, 'samples': 13958976, 'steps': 72702, 'loss/train': 1.2169859409332275} 08/31/2021 02:18:19 - INFO - __main__ - Step 72704: {'lr': 0.00026748205691834627, 'samples': 13959168, 'steps': 72703, 'loss/train': 1.1504194736480713} 08/31/2021 02:18:19 - INFO - __main__ - Step 72705: {'lr': 0.00026747676316083726, 'samples': 13959360, 'steps': 72704, 'loss/train': 1.3197715282440186} 08/31/2021 02:18:20 - INFO - __main__ - Step 72706: {'lr': 0.0002674714693954534, 'samples': 13959552, 'steps': 72705, 'loss/train': 1.287400484085083} 08/31/2021 02:18:20 - INFO - __main__ - Step 72707: {'lr': 0.0002674661756221973, 'samples': 13959744, 'steps': 72706, 'loss/train': 1.161880612373352} 08/31/2021 02:18:22 - INFO - __main__ - Step 72708: {'lr': 0.00026746088184107116, 'samples': 13959936, 'steps': 72707, 'loss/train': 1.3389004468917847} 08/31/2021 02:18:22 - INFO - __main__ - Step 72709: {'lr': 0.00026745558805207746, 'samples': 13960128, 'steps': 72708, 'loss/train': 1.1018028259277344} 08/31/2021 02:18:23 - INFO - __main__ - Step 72710: {'lr': 0.0002674502942552185, 'samples': 13960320, 'steps': 72709, 'loss/train': 1.4559744596481323} 08/31/2021 02:18:23 - INFO - __main__ - Step 72711: {'lr': 0.0002674450004504967, 'samples': 13960512, 'steps': 72710, 'loss/train': 0.7310948967933655} 08/31/2021 02:18:23 - INFO - __main__ - Step 72712: {'lr': 0.00026743970663791443, 'samples': 13960704, 'steps': 72711, 'loss/train': 1.5347261428833008} 08/31/2021 02:18:24 - INFO - __main__ - Step 72713: {'lr': 0.00026743441281747415, 'samples': 13960896, 'steps': 72712, 'loss/train': 1.6226773262023926} 08/31/2021 02:18:25 - INFO - __main__ - Step 72714: {'lr': 0.00026742911898917823, 'samples': 13961088, 'steps': 72713, 'loss/train': 1.2340542078018188} 08/31/2021 02:18:25 - INFO - __main__ - Step 72715: {'lr': 0.000267423825153029, 'samples': 13961280, 'steps': 72714, 'loss/train': 1.3412314653396606} 08/31/2021 02:18:26 - INFO - __main__ - Step 72716: {'lr': 0.0002674185313090288, 'samples': 13961472, 'steps': 72715, 'loss/train': 1.384194254875183} 08/31/2021 02:18:26 - INFO - __main__ - Step 72717: {'lr': 0.0002674132374571801, 'samples': 13961664, 'steps': 72716, 'loss/train': 1.5378811359405518} 08/31/2021 02:18:27 - INFO - __main__ - Step 72718: {'lr': 0.0002674079435974852, 'samples': 13961856, 'steps': 72717, 'loss/train': 1.572944164276123} 08/31/2021 02:18:28 - INFO - __main__ - Step 72719: {'lr': 0.0002674026497299467, 'samples': 13962048, 'steps': 72718, 'loss/train': 0.6797504425048828} 08/31/2021 02:18:28 - INFO - __main__ - Step 72720: {'lr': 0.00026739735585456674, 'samples': 13962240, 'steps': 72719, 'loss/train': 1.893574595451355} 08/31/2021 02:18:29 - INFO - __main__ - Step 72721: {'lr': 0.0002673920619713478, 'samples': 13962432, 'steps': 72720, 'loss/train': 1.4758646488189697} 08/31/2021 02:18:29 - INFO - __main__ - Step 72722: {'lr': 0.0002673867680802923, 'samples': 13962624, 'steps': 72721, 'loss/train': 1.129052996635437} 08/31/2021 02:18:29 - INFO - __main__ - Step 72723: {'lr': 0.00026738147418140255, 'samples': 13962816, 'steps': 72722, 'loss/train': 1.4619925022125244} 08/31/2021 02:18:31 - INFO - __main__ - Step 72724: {'lr': 0.000267376180274681, 'samples': 13963008, 'steps': 72723, 'loss/train': 1.8882017135620117} 08/31/2021 02:18:32 - INFO - __main__ - Step 72725: {'lr': 0.00026737088636012994, 'samples': 13963200, 'steps': 72724, 'loss/train': 1.2352142333984375} 08/31/2021 02:18:32 - INFO - __main__ - Step 72726: {'lr': 0.000267365592437752, 'samples': 13963392, 'steps': 72725, 'loss/train': 0.9696081876754761} 08/31/2021 02:18:32 - INFO - __main__ - Step 72727: {'lr': 0.00026736029850754926, 'samples': 13963584, 'steps': 72726, 'loss/train': 1.5297046899795532} 08/31/2021 02:18:33 - INFO - __main__ - Step 72728: {'lr': 0.0002673550045695243, 'samples': 13963776, 'steps': 72727, 'loss/train': 1.2490558624267578} 08/31/2021 02:18:35 - INFO - __main__ - Step 72729: {'lr': 0.00026734971062367937, 'samples': 13963968, 'steps': 72728, 'loss/train': 1.0693943500518799} 08/31/2021 02:18:35 - INFO - __main__ - Step 72730: {'lr': 0.0002673444166700169, 'samples': 13964160, 'steps': 72729, 'loss/train': 1.0447368621826172} 08/31/2021 02:18:36 - INFO - __main__ - Step 72731: {'lr': 0.00026733912270853947, 'samples': 13964352, 'steps': 72730, 'loss/train': 0.9892253279685974} 08/31/2021 02:18:36 - INFO - __main__ - Step 72732: {'lr': 0.0002673338287392492, 'samples': 13964544, 'steps': 72731, 'loss/train': 1.0674991607666016} 08/31/2021 02:18:36 - INFO - __main__ - Step 72733: {'lr': 0.0002673285347621485, 'samples': 13964736, 'steps': 72732, 'loss/train': 1.9137259721755981} 08/31/2021 02:18:38 - INFO - __main__ - Step 72734: {'lr': 0.0002673232407772399, 'samples': 13964928, 'steps': 72733, 'loss/train': 1.810681939125061} 08/31/2021 02:18:38 - INFO - __main__ - Step 72735: {'lr': 0.0002673179467845257, 'samples': 13965120, 'steps': 72734, 'loss/train': 1.0409454107284546} 08/31/2021 02:18:39 - INFO - __main__ - Step 72736: {'lr': 0.00026731265278400834, 'samples': 13965312, 'steps': 72735, 'loss/train': 1.1410378217697144} 08/31/2021 02:18:39 - INFO - __main__ - Step 72737: {'lr': 0.00026730735877569014, 'samples': 13965504, 'steps': 72736, 'loss/train': 0.9620932936668396} 08/31/2021 02:18:39 - INFO - __main__ - Step 72738: {'lr': 0.00026730206475957354, 'samples': 13965696, 'steps': 72737, 'loss/train': 0.042134273797273636} 08/31/2021 02:18:40 - INFO - __main__ - Step 72739: {'lr': 0.0002672967707356608, 'samples': 13965888, 'steps': 72738, 'loss/train': 1.3665851354599} 08/31/2021 02:18:41 - INFO - __main__ - Step 72740: {'lr': 0.00026729147670395454, 'samples': 13966080, 'steps': 72739, 'loss/train': 1.1448233127593994} 08/31/2021 02:18:42 - INFO - __main__ - Step 72741: {'lr': 0.0002672861826644569, 'samples': 13966272, 'steps': 72740, 'loss/train': 1.4237136840820312} 08/31/2021 02:18:42 - INFO - __main__ - Step 72742: {'lr': 0.0002672808886171704, 'samples': 13966464, 'steps': 72741, 'loss/train': 1.8781406879425049} 08/31/2021 02:18:43 - INFO - __main__ - Step 72743: {'lr': 0.00026727559456209745, 'samples': 13966656, 'steps': 72742, 'loss/train': 1.9956514835357666} 08/31/2021 02:18:43 - INFO - __main__ - Step 72744: {'lr': 0.0002672703004992403, 'samples': 13966848, 'steps': 72743, 'loss/train': 1.1334357261657715} 08/31/2021 02:18:45 - INFO - __main__ - Step 72745: {'lr': 0.0002672650064286015, 'samples': 13967040, 'steps': 72744, 'loss/train': 1.0480647087097168} 08/31/2021 02:18:45 - INFO - __main__ - Step 72746: {'lr': 0.00026725971235018334, 'samples': 13967232, 'steps': 72745, 'loss/train': 0.5225749611854553} 08/31/2021 02:18:45 - INFO - __main__ - Step 72747: {'lr': 0.00026725441826398814, 'samples': 13967424, 'steps': 72746, 'loss/train': 1.3422428369522095} 08/31/2021 02:18:46 - INFO - __main__ - Step 72748: {'lr': 0.00026724912417001845, 'samples': 13967616, 'steps': 72747, 'loss/train': 1.1470197439193726} 08/31/2021 02:18:46 - INFO - __main__ - Step 72749: {'lr': 0.0002672438300682765, 'samples': 13967808, 'steps': 72748, 'loss/train': 1.00807785987854} 08/31/2021 02:18:48 - INFO - __main__ - Step 72750: {'lr': 0.0002672385359587648, 'samples': 13968000, 'steps': 72749, 'loss/train': 0.05625222995877266} 08/31/2021 02:18:48 - INFO - __main__ - Step 72751: {'lr': 0.0002672332418414857, 'samples': 13968192, 'steps': 72750, 'loss/train': 1.353161096572876} 08/31/2021 02:18:48 - INFO - __main__ - Step 72752: {'lr': 0.00026722794771644155, 'samples': 13968384, 'steps': 72751, 'loss/train': 1.3333898782730103} 08/31/2021 02:18:49 - INFO - __main__ - Step 72753: {'lr': 0.00026722265358363476, 'samples': 13968576, 'steps': 72752, 'loss/train': 0.9744367599487305} 08/31/2021 02:18:49 - INFO - __main__ - Step 72754: {'lr': 0.00026721735944306764, 'samples': 13968768, 'steps': 72753, 'loss/train': 1.0257675647735596} 08/31/2021 02:18:51 - INFO - __main__ - Step 72755: {'lr': 0.00026721206529474266, 'samples': 13968960, 'steps': 72754, 'loss/train': 2.0465011596679688} 08/31/2021 02:18:51 - INFO - __main__ - Step 72756: {'lr': 0.0002672067711386623, 'samples': 13969152, 'steps': 72755, 'loss/train': 1.0886919498443604} 08/31/2021 02:18:52 - INFO - __main__ - Step 72757: {'lr': 0.00026720147697482867, 'samples': 13969344, 'steps': 72756, 'loss/train': 1.1333454847335815} 08/31/2021 02:18:52 - INFO - __main__ - Step 72758: {'lr': 0.0002671961828032445, 'samples': 13969536, 'steps': 72757, 'loss/train': 0.045433081686496735} 08/31/2021 02:18:52 - INFO - __main__ - Step 72759: {'lr': 0.00026719088862391186, 'samples': 13969728, 'steps': 72758, 'loss/train': 1.2303473949432373} 08/31/2021 02:18:53 - INFO - __main__ - Step 72760: {'lr': 0.00026718559443683333, 'samples': 13969920, 'steps': 72759, 'loss/train': 1.355100154876709} 08/31/2021 02:18:54 - INFO - __main__ - Step 72761: {'lr': 0.00026718030024201116, 'samples': 13970112, 'steps': 72760, 'loss/train': 1.3279857635498047} 08/31/2021 02:18:55 - INFO - __main__ - Step 72762: {'lr': 0.0002671750060394479, 'samples': 13970304, 'steps': 72761, 'loss/train': 1.5972579717636108} 08/31/2021 02:18:55 - INFO - __main__ - Step 72763: {'lr': 0.0002671697118291458, 'samples': 13970496, 'steps': 72762, 'loss/train': 1.7269532680511475} 08/31/2021 02:18:55 - INFO - __main__ - Step 72764: {'lr': 0.00026716441761110734, 'samples': 13970688, 'steps': 72763, 'loss/train': 1.3175108432769775} 08/31/2021 02:18:56 - INFO - __main__ - Step 72765: {'lr': 0.0002671591233853348, 'samples': 13970880, 'steps': 72764, 'loss/train': 0.701194167137146} 08/31/2021 02:18:57 - INFO - __main__ - Step 72766: {'lr': 0.0002671538291518307, 'samples': 13971072, 'steps': 72765, 'loss/train': 1.329774260520935} 08/31/2021 02:18:58 - INFO - __main__ - Step 72767: {'lr': 0.00026714853491059725, 'samples': 13971264, 'steps': 72766, 'loss/train': 0.9126999378204346} 08/31/2021 02:18:58 - INFO - __main__ - Step 72768: {'lr': 0.00026714324066163695, 'samples': 13971456, 'steps': 72767, 'loss/train': 0.996527373790741} 08/31/2021 02:18:59 - INFO - __main__ - Step 72769: {'lr': 0.00026713794640495226, 'samples': 13971648, 'steps': 72768, 'loss/train': 1.045885443687439} 08/31/2021 02:18:59 - INFO - __main__ - Step 72770: {'lr': 0.0002671326521405454, 'samples': 13971840, 'steps': 72769, 'loss/train': 1.582472801208496} 08/31/2021 02:19:01 - INFO - __main__ - Step 72771: {'lr': 0.0002671273578684189, 'samples': 13972032, 'steps': 72770, 'loss/train': 0.8677223920822144} 08/31/2021 02:19:01 - INFO - __main__ - Step 72772: {'lr': 0.000267122063588575, 'samples': 13972224, 'steps': 72771, 'loss/train': 2.0632128715515137} 08/31/2021 02:19:01 - INFO - __main__ - Step 72773: {'lr': 0.0002671167693010162, 'samples': 13972416, 'steps': 72772, 'loss/train': 2.0139169692993164} 08/31/2021 02:19:02 - INFO - __main__ - Step 72774: {'lr': 0.00026711147500574486, 'samples': 13972608, 'steps': 72773, 'loss/train': 1.8441040515899658} 08/31/2021 02:19:02 - INFO - __main__ - Step 72775: {'lr': 0.00026710618070276327, 'samples': 13972800, 'steps': 72774, 'loss/train': 0.9415711760520935} 08/31/2021 02:19:04 - INFO - __main__ - Step 72776: {'lr': 0.000267100886392074, 'samples': 13972992, 'steps': 72775, 'loss/train': 1.0438145399093628} 08/31/2021 02:19:04 - INFO - __main__ - Step 72777: {'lr': 0.00026709559207367927, 'samples': 13973184, 'steps': 72776, 'loss/train': 0.9929928779602051} 08/31/2021 02:19:05 - INFO - __main__ - Step 72778: {'lr': 0.0002670902977475816, 'samples': 13973376, 'steps': 72777, 'loss/train': 0.06380926072597504} 08/31/2021 02:19:05 - INFO - __main__ - Step 72779: {'lr': 0.0002670850034137833, 'samples': 13973568, 'steps': 72778, 'loss/train': 1.6100307703018188} 08/31/2021 02:19:05 - INFO - __main__ - Step 72780: {'lr': 0.00026707970907228665, 'samples': 13973760, 'steps': 72779, 'loss/train': 1.711074948310852} 08/31/2021 02:19:07 - INFO - __main__ - Step 72781: {'lr': 0.00026707441472309426, 'samples': 13973952, 'steps': 72780, 'loss/train': 1.2558599710464478} 08/31/2021 02:19:08 - INFO - __main__ - Step 72782: {'lr': 0.00026706912036620836, 'samples': 13974144, 'steps': 72781, 'loss/train': 1.3074274063110352} 08/31/2021 02:19:08 - INFO - __main__ - Step 72783: {'lr': 0.0002670638260016313, 'samples': 13974336, 'steps': 72782, 'loss/train': 0.7905417680740356} 08/31/2021 02:19:09 - INFO - __main__ - Step 72784: {'lr': 0.00026705853162936567, 'samples': 13974528, 'steps': 72783, 'loss/train': 0.8686649799346924} 08/31/2021 02:19:09 - INFO - __main__ - Step 72785: {'lr': 0.0002670532372494137, 'samples': 13974720, 'steps': 72784, 'loss/train': 0.2826768159866333} 08/31/2021 02:19:09 - INFO - __main__ - Step 72786: {'lr': 0.0002670479428617778, 'samples': 13974912, 'steps': 72785, 'loss/train': 0.9803704023361206} 08/31/2021 02:19:11 - INFO - __main__ - Step 72787: {'lr': 0.0002670426484664603, 'samples': 13975104, 'steps': 72786, 'loss/train': 0.24366915225982666} 08/31/2021 02:19:11 - INFO - __main__ - Step 72788: {'lr': 0.00026703735406346374, 'samples': 13975296, 'steps': 72787, 'loss/train': 0.03262738138437271} 08/31/2021 02:19:11 - INFO - __main__ - Step 72789: {'lr': 0.0002670320596527903, 'samples': 13975488, 'steps': 72788, 'loss/train': 1.2974258661270142} 08/31/2021 02:19:12 - INFO - __main__ - Step 72790: {'lr': 0.00026702676523444256, 'samples': 13975680, 'steps': 72789, 'loss/train': 1.3405705690383911} 08/31/2021 02:19:12 - INFO - __main__ - Step 72791: {'lr': 0.00026702147080842284, 'samples': 13975872, 'steps': 72790, 'loss/train': 1.5282139778137207} 08/31/2021 02:19:14 - INFO - __main__ - Step 72792: {'lr': 0.00026701617637473347, 'samples': 13976064, 'steps': 72791, 'loss/train': 1.38700532913208} 08/31/2021 02:19:14 - INFO - __main__ - Step 72793: {'lr': 0.00026701088193337684, 'samples': 13976256, 'steps': 72792, 'loss/train': 1.9150489568710327} 08/31/2021 02:19:15 - INFO - __main__ - Step 72794: {'lr': 0.00026700558748435544, 'samples': 13976448, 'steps': 72793, 'loss/train': 1.3320943117141724} 08/31/2021 02:19:15 - INFO - __main__ - Step 72795: {'lr': 0.00026700029302767156, 'samples': 13976640, 'steps': 72794, 'loss/train': 1.671610951423645} 08/31/2021 02:19:15 - INFO - __main__ - Step 72796: {'lr': 0.00026699499856332756, 'samples': 13976832, 'steps': 72795, 'loss/train': 1.4133503437042236} 08/31/2021 02:19:17 - INFO - __main__ - Step 72797: {'lr': 0.0002669897040913259, 'samples': 13977024, 'steps': 72796, 'loss/train': 1.1226106882095337} 08/31/2021 02:19:17 - INFO - __main__ - Step 72798: {'lr': 0.000266984409611669, 'samples': 13977216, 'steps': 72797, 'loss/train': 0.9436579346656799} 08/31/2021 02:19:18 - INFO - __main__ - Step 72799: {'lr': 0.00026697911512435914, 'samples': 13977408, 'steps': 72798, 'loss/train': 1.3456608057022095} 08/31/2021 02:19:18 - INFO - __main__ - Step 72800: {'lr': 0.00026697382062939874, 'samples': 13977600, 'steps': 72799, 'loss/train': 1.244107961654663} 08/31/2021 02:19:18 - INFO - __main__ - Step 72801: {'lr': 0.0002669685261267902, 'samples': 13977792, 'steps': 72800, 'loss/train': 0.8376646041870117} 08/31/2021 02:19:20 - INFO - __main__ - Step 72802: {'lr': 0.0002669632316165359, 'samples': 13977984, 'steps': 72801, 'loss/train': 1.3697540760040283} 08/31/2021 02:19:20 - INFO - __main__ - Step 72803: {'lr': 0.00026695793709863823, 'samples': 13978176, 'steps': 72802, 'loss/train': 1.2894965410232544} 08/31/2021 02:19:21 - INFO - __main__ - Step 72804: {'lr': 0.0002669526425730996, 'samples': 13978368, 'steps': 72803, 'loss/train': 1.9754743576049805} 08/31/2021 02:19:21 - INFO - __main__ - Step 72805: {'lr': 0.0002669473480399224, 'samples': 13978560, 'steps': 72804, 'loss/train': 0.6249001026153564} 08/31/2021 02:19:21 - INFO - __main__ - Step 72806: {'lr': 0.00026694205349910894, 'samples': 13978752, 'steps': 72805, 'loss/train': 1.6080111265182495} 08/31/2021 02:19:23 - INFO - __main__ - Step 72807: {'lr': 0.00026693675895066166, 'samples': 13978944, 'steps': 72806, 'loss/train': 1.2361856698989868} 08/31/2021 02:19:23 - INFO - __main__ - Step 72808: {'lr': 0.00026693146439458294, 'samples': 13979136, 'steps': 72807, 'loss/train': 0.6861307621002197} 08/31/2021 02:19:24 - INFO - __main__ - Step 72809: {'lr': 0.0002669261698308751, 'samples': 13979328, 'steps': 72808, 'loss/train': 1.2046877145767212} 08/31/2021 02:19:24 - INFO - __main__ - Step 72810: {'lr': 0.0002669208752595407, 'samples': 13979520, 'steps': 72809, 'loss/train': 0.9367088079452515} 08/31/2021 02:19:24 - INFO - __main__ - Step 72811: {'lr': 0.00026691558068058196, 'samples': 13979712, 'steps': 72810, 'loss/train': 0.6553855538368225} 08/31/2021 02:19:26 - INFO - __main__ - Step 72812: {'lr': 0.0002669102860940014, 'samples': 13979904, 'steps': 72811, 'loss/train': 1.2430384159088135} 08/31/2021 02:19:26 - INFO - __main__ - Step 72813: {'lr': 0.00026690499149980125, 'samples': 13980096, 'steps': 72812, 'loss/train': 0.9024077653884888} 08/31/2021 02:19:27 - INFO - __main__ - Step 72814: {'lr': 0.00026689969689798395, 'samples': 13980288, 'steps': 72813, 'loss/train': 1.2854177951812744} 08/31/2021 02:19:27 - INFO - __main__ - Step 72815: {'lr': 0.00026689440228855197, 'samples': 13980480, 'steps': 72814, 'loss/train': 1.176350712776184} 08/31/2021 02:19:27 - INFO - __main__ - Step 72816: {'lr': 0.00026688910767150753, 'samples': 13980672, 'steps': 72815, 'loss/train': 0.18183325231075287} 08/31/2021 02:19:30 - INFO - __main__ - Step 72817: {'lr': 0.0002668838130468532, 'samples': 13980864, 'steps': 72816, 'loss/train': 0.12846814095973969} 08/31/2021 02:19:30 - INFO - __main__ - Step 72818: {'lr': 0.0002668785184145913, 'samples': 13981056, 'steps': 72817, 'loss/train': 1.9627690315246582} 08/31/2021 02:19:31 - INFO - __main__ - Step 72819: {'lr': 0.00026687322377472416, 'samples': 13981248, 'steps': 72818, 'loss/train': 0.6112474799156189} 08/31/2021 02:19:31 - INFO - __main__ - Step 72820: {'lr': 0.0002668679291272542, 'samples': 13981440, 'steps': 72819, 'loss/train': 0.4922015368938446} 08/31/2021 02:19:31 - INFO - __main__ - Step 72821: {'lr': 0.00026686263447218386, 'samples': 13981632, 'steps': 72820, 'loss/train': 1.4067155122756958} 08/31/2021 02:19:32 - INFO - __main__ - Step 72822: {'lr': 0.0002668573398095154, 'samples': 13981824, 'steps': 72821, 'loss/train': 1.1130541563034058} 08/31/2021 02:19:33 - INFO - __main__ - Step 72823: {'lr': 0.0002668520451392513, 'samples': 13982016, 'steps': 72822, 'loss/train': 1.2853636741638184} 08/31/2021 02:19:34 - INFO - __main__ - Step 72824: {'lr': 0.00026684675046139393, 'samples': 13982208, 'steps': 72823, 'loss/train': 1.4810234308242798} 08/31/2021 02:19:34 - INFO - __main__ - Step 72825: {'lr': 0.00026684145577594577, 'samples': 13982400, 'steps': 72824, 'loss/train': 1.5768887996673584} 08/31/2021 02:19:34 - INFO - __main__ - Step 72826: {'lr': 0.00026683616108290906, 'samples': 13982592, 'steps': 72825, 'loss/train': 1.1562122106552124} 08/31/2021 02:19:35 - INFO - __main__ - Step 72827: {'lr': 0.00026683086638228614, 'samples': 13982784, 'steps': 72826, 'loss/train': 1.334577202796936} 08/31/2021 02:19:36 - INFO - __main__ - Step 72828: {'lr': 0.0002668255716740796, 'samples': 13982976, 'steps': 72827, 'loss/train': 1.171078085899353} 08/31/2021 02:19:37 - INFO - __main__ - Step 72829: {'lr': 0.00026682027695829167, 'samples': 13983168, 'steps': 72828, 'loss/train': 1.8776720762252808} 08/31/2021 02:19:37 - INFO - __main__ - Step 72830: {'lr': 0.0002668149822349248, 'samples': 13983360, 'steps': 72829, 'loss/train': 0.202748641371727} 08/31/2021 02:19:37 - INFO - __main__ - Step 72831: {'lr': 0.00026680968750398133, 'samples': 13983552, 'steps': 72830, 'loss/train': 0.9719099998474121} 08/31/2021 02:19:38 - INFO - __main__ - Step 72832: {'lr': 0.00026680439276546375, 'samples': 13983744, 'steps': 72831, 'loss/train': 1.1464070081710815} 08/31/2021 02:19:39 - INFO - __main__ - Step 72833: {'lr': 0.0002667990980193743, 'samples': 13983936, 'steps': 72832, 'loss/train': 1.5375258922576904} 08/31/2021 02:19:40 - INFO - __main__ - Step 72834: {'lr': 0.0002667938032657155, 'samples': 13984128, 'steps': 72833, 'loss/train': 1.3523387908935547} 08/31/2021 02:19:40 - INFO - __main__ - Step 72835: {'lr': 0.00026678850850448955, 'samples': 13984320, 'steps': 72834, 'loss/train': 1.2189726829528809} 08/31/2021 02:19:40 - INFO - __main__ - Step 72836: {'lr': 0.00026678321373569904, 'samples': 13984512, 'steps': 72835, 'loss/train': 1.2749654054641724} 08/31/2021 02:19:41 - INFO - __main__ - Step 72837: {'lr': 0.0002667779189593463, 'samples': 13984704, 'steps': 72836, 'loss/train': 1.5714616775512695} 08/31/2021 02:19:41 - INFO - __main__ - Step 72838: {'lr': 0.00026677262417543364, 'samples': 13984896, 'steps': 72837, 'loss/train': 1.4129780530929565} 08/31/2021 02:19:43 - INFO - __main__ - Step 72839: {'lr': 0.0002667673293839635, 'samples': 13985088, 'steps': 72838, 'loss/train': 1.0879156589508057} 08/31/2021 02:19:44 - INFO - __main__ - Step 72840: {'lr': 0.00026676203458493824, 'samples': 13985280, 'steps': 72839, 'loss/train': 1.1775070428848267} 08/31/2021 02:19:44 - INFO - __main__ - Step 72841: {'lr': 0.00026675673977836036, 'samples': 13985472, 'steps': 72840, 'loss/train': 1.307835340499878} 08/31/2021 02:19:44 - INFO - __main__ - Step 72842: {'lr': 0.00026675144496423204, 'samples': 13985664, 'steps': 72841, 'loss/train': 1.3537975549697876} 08/31/2021 02:19:45 - INFO - __main__ - Step 72843: {'lr': 0.00026674615014255583, 'samples': 13985856, 'steps': 72842, 'loss/train': 1.5071101188659668} 08/31/2021 02:19:46 - INFO - __main__ - Step 72844: {'lr': 0.0002667408553133341, 'samples': 13986048, 'steps': 72843, 'loss/train': 1.4303812980651855} 08/31/2021 02:19:47 - INFO - __main__ - Step 72845: {'lr': 0.0002667355604765691, 'samples': 13986240, 'steps': 72844, 'loss/train': 1.4734160900115967} 08/31/2021 02:19:47 - INFO - __main__ - Step 72846: {'lr': 0.0002667302656322634, 'samples': 13986432, 'steps': 72845, 'loss/train': 1.19130539894104} 08/31/2021 02:19:47 - INFO - __main__ - Step 72847: {'lr': 0.00026672497078041924, 'samples': 13986624, 'steps': 72846, 'loss/train': 1.4162144660949707} 08/31/2021 02:19:48 - INFO - __main__ - Step 72848: {'lr': 0.0002667196759210391, 'samples': 13986816, 'steps': 72847, 'loss/train': 1.054840326309204} 08/31/2021 02:19:49 - INFO - __main__ - Step 72849: {'lr': 0.00026671438105412535, 'samples': 13987008, 'steps': 72848, 'loss/train': 0.9816423654556274} 08/31/2021 02:19:50 - INFO - __main__ - Step 72850: {'lr': 0.0002667090861796804, 'samples': 13987200, 'steps': 72849, 'loss/train': 0.8229645490646362} 08/31/2021 02:19:50 - INFO - __main__ - Step 72851: {'lr': 0.0002667037912977065, 'samples': 13987392, 'steps': 72850, 'loss/train': 0.41922664642333984} 08/31/2021 02:19:50 - INFO - __main__ - Step 72852: {'lr': 0.0002666984964082061, 'samples': 13987584, 'steps': 72851, 'loss/train': 1.046634316444397} 08/31/2021 02:19:51 - INFO - __main__ - Step 72853: {'lr': 0.0002666932015111817, 'samples': 13987776, 'steps': 72852, 'loss/train': 1.4584455490112305} 08/31/2021 02:19:52 - INFO - __main__ - Step 72854: {'lr': 0.00026668790660663557, 'samples': 13987968, 'steps': 72853, 'loss/train': 1.5105983018875122} 08/31/2021 02:19:52 - INFO - __main__ - Step 72855: {'lr': 0.0002666826116945701, 'samples': 13988160, 'steps': 72854, 'loss/train': 0.8323543071746826} 08/31/2021 02:19:53 - INFO - __main__ - Step 72856: {'lr': 0.0002666773167749878, 'samples': 13988352, 'steps': 72855, 'loss/train': 0.470624178647995} 08/31/2021 02:19:53 - INFO - __main__ - Step 72857: {'lr': 0.00026667202184789087, 'samples': 13988544, 'steps': 72856, 'loss/train': 1.663237452507019} 08/31/2021 02:19:54 - INFO - __main__ - Step 72858: {'lr': 0.00026666672691328183, 'samples': 13988736, 'steps': 72857, 'loss/train': 1.5731251239776611} 08/31/2021 02:19:55 - INFO - __main__ - Step 72859: {'lr': 0.00026666143197116296, 'samples': 13988928, 'steps': 72858, 'loss/train': 1.6236591339111328} 08/31/2021 02:19:56 - INFO - __main__ - Step 72860: {'lr': 0.0002666561370215368, 'samples': 13989120, 'steps': 72859, 'loss/train': 0.20703862607479095} 08/31/2021 02:19:56 - INFO - __main__ - Step 72861: {'lr': 0.0002666508420644056, 'samples': 13989312, 'steps': 72860, 'loss/train': 1.4210501909255981} 08/31/2021 02:19:57 - INFO - __main__ - Step 72862: {'lr': 0.0002666455470997717, 'samples': 13989504, 'steps': 72861, 'loss/train': 1.3668875694274902} 08/31/2021 02:19:57 - INFO - __main__ - Step 72863: {'lr': 0.0002666402521276376, 'samples': 13989696, 'steps': 72862, 'loss/train': 1.05892014503479} 08/31/2021 02:19:57 - INFO - __main__ - Step 72864: {'lr': 0.0002666349571480058, 'samples': 13989888, 'steps': 72863, 'loss/train': 1.1429150104522705} 08/31/2021 02:19:59 - INFO - __main__ - Step 72865: {'lr': 0.0002666296621608784, 'samples': 13990080, 'steps': 72864, 'loss/train': 0.8101662993431091} 08/31/2021 02:19:59 - INFO - __main__ - Step 72866: {'lr': 0.00026662436716625804, 'samples': 13990272, 'steps': 72865, 'loss/train': 1.8082029819488525} 08/31/2021 02:19:59 - INFO - __main__ - Step 72867: {'lr': 0.00026661907216414695, 'samples': 13990464, 'steps': 72866, 'loss/train': 1.1864099502563477} 08/31/2021 02:20:00 - INFO - __main__ - Step 72868: {'lr': 0.0002666137771545475, 'samples': 13990656, 'steps': 72867, 'loss/train': 1.6351673603057861} 08/31/2021 02:20:00 - INFO - __main__ - Step 72869: {'lr': 0.0002666084821374622, 'samples': 13990848, 'steps': 72868, 'loss/train': 1.1408318281173706} 08/31/2021 02:20:02 - INFO - __main__ - Step 72870: {'lr': 0.00026660318711289334, 'samples': 13991040, 'steps': 72869, 'loss/train': 1.351172685623169} 08/31/2021 02:20:02 - INFO - __main__ - Step 72871: {'lr': 0.0002665978920808433, 'samples': 13991232, 'steps': 72870, 'loss/train': 0.1786050796508789} 08/31/2021 02:20:02 - INFO - __main__ - Step 72872: {'lr': 0.0002665925970413147, 'samples': 13991424, 'steps': 72871, 'loss/train': 1.3096596002578735} 08/31/2021 02:20:03 - INFO - __main__ - Step 72873: {'lr': 0.0002665873019943096, 'samples': 13991616, 'steps': 72872, 'loss/train': 1.4251983165740967} 08/31/2021 02:20:03 - INFO - __main__ - Step 72874: {'lr': 0.00026658200693983045, 'samples': 13991808, 'steps': 72873, 'loss/train': 1.1129820346832275} 08/31/2021 02:20:05 - INFO - __main__ - Step 72875: {'lr': 0.0002665767118778798, 'samples': 13992000, 'steps': 72874, 'loss/train': 1.15596604347229} 08/31/2021 02:20:05 - INFO - __main__ - Step 72876: {'lr': 0.00026657141680845993, 'samples': 13992192, 'steps': 72875, 'loss/train': 1.2980773448944092} 08/31/2021 02:20:06 - INFO - __main__ - Step 72877: {'lr': 0.0002665661217315732, 'samples': 13992384, 'steps': 72876, 'loss/train': 1.3888710737228394} 08/31/2021 02:20:06 - INFO - __main__ - Step 72878: {'lr': 0.000266560826647222, 'samples': 13992576, 'steps': 72877, 'loss/train': 1.2063629627227783} 08/31/2021 02:20:06 - INFO - __main__ - Step 72879: {'lr': 0.00026655553155540887, 'samples': 13992768, 'steps': 72878, 'loss/train': 1.1382100582122803} 08/31/2021 02:20:08 - INFO - __main__ - Step 72880: {'lr': 0.000266550236456136, 'samples': 13992960, 'steps': 72879, 'loss/train': 1.9041907787322998} 08/31/2021 02:20:08 - INFO - __main__ - Step 72881: {'lr': 0.00026654494134940583, 'samples': 13993152, 'steps': 72880, 'loss/train': 1.1536972522735596} 08/31/2021 02:20:09 - INFO - __main__ - Step 72882: {'lr': 0.00026653964623522076, 'samples': 13993344, 'steps': 72881, 'loss/train': 0.8748160600662231} 08/31/2021 02:20:09 - INFO - __main__ - Step 72883: {'lr': 0.0002665343511135832, 'samples': 13993536, 'steps': 72882, 'loss/train': 0.37451377511024475} 08/31/2021 02:20:09 - INFO - __main__ - Step 72884: {'lr': 0.0002665290559844955, 'samples': 13993728, 'steps': 72883, 'loss/train': 1.8446059226989746} 08/31/2021 02:20:12 - INFO - __main__ - Step 72885: {'lr': 0.00026652376084796006, 'samples': 13993920, 'steps': 72884, 'loss/train': 1.0633848905563354} 08/31/2021 02:20:12 - INFO - __main__ - Step 72886: {'lr': 0.0002665184657039794, 'samples': 13994112, 'steps': 72885, 'loss/train': 1.3214201927185059} 08/31/2021 02:20:12 - INFO - __main__ - Step 72887: {'lr': 0.0002665131705525556, 'samples': 13994304, 'steps': 72886, 'loss/train': 0.5099840760231018} 08/31/2021 02:20:13 - INFO - __main__ - Step 72888: {'lr': 0.00026650787539369127, 'samples': 13994496, 'steps': 72887, 'loss/train': 0.9975236654281616} 08/31/2021 02:20:13 - INFO - __main__ - Step 72889: {'lr': 0.00026650258022738876, 'samples': 13994688, 'steps': 72888, 'loss/train': 0.881157636642456} 08/31/2021 02:20:13 - INFO - __main__ - Step 72890: {'lr': 0.0002664972850536505, 'samples': 13994880, 'steps': 72889, 'loss/train': 0.9152589440345764} 08/31/2021 02:20:14 - INFO - __main__ - Step 72891: {'lr': 0.0002664919898724787, 'samples': 13995072, 'steps': 72890, 'loss/train': 1.305307149887085} 08/31/2021 02:20:16 - INFO - __main__ - Step 72892: {'lr': 0.00026648669468387593, 'samples': 13995264, 'steps': 72891, 'loss/train': 1.4882034063339233} 08/31/2021 02:20:17 - INFO - __main__ - Step 72893: {'lr': 0.0002664813994878445, 'samples': 13995456, 'steps': 72892, 'loss/train': 1.3916053771972656} 08/31/2021 02:20:17 - INFO - __main__ - Step 72894: {'lr': 0.00026647610428438676, 'samples': 13995648, 'steps': 72893, 'loss/train': 1.3168418407440186} 08/31/2021 02:20:17 - INFO - __main__ - Step 72895: {'lr': 0.00026647080907350523, 'samples': 13995840, 'steps': 72894, 'loss/train': 1.1401963233947754} 08/31/2021 02:20:18 - INFO - __main__ - Step 72896: {'lr': 0.00026646551385520217, 'samples': 13996032, 'steps': 72895, 'loss/train': 0.6779321432113647} 08/31/2021 02:20:19 - INFO - __main__ - Step 72897: {'lr': 0.00026646021862948, 'samples': 13996224, 'steps': 72896, 'loss/train': 0.49530649185180664} 08/31/2021 02:20:20 - INFO - __main__ - Step 72898: {'lr': 0.00026645492339634106, 'samples': 13996416, 'steps': 72897, 'loss/train': 1.4187906980514526} 08/31/2021 02:20:20 - INFO - __main__ - Step 72899: {'lr': 0.00026644962815578795, 'samples': 13996608, 'steps': 72898, 'loss/train': 1.9355591535568237} 08/31/2021 02:20:20 - INFO - __main__ - Step 72900: {'lr': 0.00026644433290782274, 'samples': 13996800, 'steps': 72899, 'loss/train': 1.4126168489456177} 08/31/2021 02:20:21 - INFO - __main__ - Step 72901: {'lr': 0.000266439037652448, 'samples': 13996992, 'steps': 72900, 'loss/train': 0.9645009636878967} 08/31/2021 02:20:21 - INFO - __main__ - Step 72902: {'lr': 0.0002664337423896661, 'samples': 13997184, 'steps': 72901, 'loss/train': 1.5092504024505615} 08/31/2021 02:20:23 - INFO - __main__ - Step 72903: {'lr': 0.00026642844711947933, 'samples': 13997376, 'steps': 72902, 'loss/train': 1.4461356401443481} 08/31/2021 02:20:23 - INFO - __main__ - Step 72904: {'lr': 0.00026642315184189025, 'samples': 13997568, 'steps': 72903, 'loss/train': 1.1831586360931396} 08/31/2021 02:20:24 - INFO - __main__ - Step 72905: {'lr': 0.0002664178565569011, 'samples': 13997760, 'steps': 72904, 'loss/train': 1.4753559827804565} 08/31/2021 02:20:24 - INFO - __main__ - Step 72906: {'lr': 0.0002664125612645144, 'samples': 13997952, 'steps': 72905, 'loss/train': 0.9250298142433167} 08/31/2021 02:20:25 - INFO - __main__ - Step 72907: {'lr': 0.00026640726596473236, 'samples': 13998144, 'steps': 72906, 'loss/train': 1.2013673782348633} 08/31/2021 02:20:26 - INFO - __main__ - Step 72908: {'lr': 0.0002664019706575575, 'samples': 13998336, 'steps': 72907, 'loss/train': 1.5781514644622803} 08/31/2021 02:20:26 - INFO - __main__ - Step 72909: {'lr': 0.00026639667534299216, 'samples': 13998528, 'steps': 72908, 'loss/train': 0.770169734954834} 08/31/2021 02:20:27 - INFO - __main__ - Step 72910: {'lr': 0.0002663913800210387, 'samples': 13998720, 'steps': 72909, 'loss/train': 1.5412993431091309} 08/31/2021 02:20:27 - INFO - __main__ - Step 72911: {'lr': 0.0002663860846916996, 'samples': 13998912, 'steps': 72910, 'loss/train': 1.604941964149475} 08/31/2021 02:20:27 - INFO - __main__ - Step 72912: {'lr': 0.00026638078935497714, 'samples': 13999104, 'steps': 72911, 'loss/train': 1.2834280729293823} 08/31/2021 02:20:29 - INFO - __main__ - Step 72913: {'lr': 0.0002663754940108738, 'samples': 13999296, 'steps': 72912, 'loss/train': 1.054474115371704} 08/31/2021 02:20:30 - INFO - __main__ - Step 72914: {'lr': 0.0002663701986593918, 'samples': 13999488, 'steps': 72913, 'loss/train': 1.3722171783447266} 08/31/2021 02:20:30 - INFO - __main__ - Step 72915: {'lr': 0.00026636490330053376, 'samples': 13999680, 'steps': 72914, 'loss/train': 1.4748883247375488} 08/31/2021 02:20:30 - INFO - __main__ - Step 72916: {'lr': 0.00026635960793430194, 'samples': 13999872, 'steps': 72915, 'loss/train': 0.7870684862136841} 08/31/2021 02:20:31 - INFO - __main__ - Step 72917: {'lr': 0.00026635431256069863, 'samples': 14000064, 'steps': 72916, 'loss/train': 1.2845674753189087} 08/31/2021 02:20:31 - INFO - __main__ - Step 72918: {'lr': 0.00026634901717972637, 'samples': 14000256, 'steps': 72917, 'loss/train': 1.4188379049301147} 08/31/2021 02:20:32 - INFO - __main__ - Step 72919: {'lr': 0.00026634372179138756, 'samples': 14000448, 'steps': 72918, 'loss/train': 1.3157551288604736} 08/31/2021 02:20:33 - INFO - __main__ - Step 72920: {'lr': 0.00026633842639568446, 'samples': 14000640, 'steps': 72919, 'loss/train': 1.0334621667861938} 08/31/2021 02:20:33 - INFO - __main__ - Step 72921: {'lr': 0.00026633313099261953, 'samples': 14000832, 'steps': 72920, 'loss/train': 1.2756264209747314} 08/31/2021 02:20:34 - INFO - __main__ - Step 72922: {'lr': 0.00026632783558219514, 'samples': 14001024, 'steps': 72921, 'loss/train': 1.3568079471588135} 08/31/2021 02:20:34 - INFO - __main__ - Step 72923: {'lr': 0.0002663225401644137, 'samples': 14001216, 'steps': 72922, 'loss/train': 1.4710036516189575} 08/31/2021 02:20:35 - INFO - __main__ - Step 72924: {'lr': 0.00026631724473927753, 'samples': 14001408, 'steps': 72923, 'loss/train': 1.2027812004089355} 08/31/2021 02:20:36 - INFO - __main__ - Step 72925: {'lr': 0.0002663119493067891, 'samples': 14001600, 'steps': 72924, 'loss/train': 0.9540876150131226} 08/31/2021 02:20:36 - INFO - __main__ - Step 72926: {'lr': 0.0002663066538669507, 'samples': 14001792, 'steps': 72925, 'loss/train': 1.2998840808868408} 08/31/2021 02:20:36 - INFO - __main__ - Step 72927: {'lr': 0.0002663013584197649, 'samples': 14001984, 'steps': 72926, 'loss/train': 0.6998586654663086} 08/31/2021 02:20:37 - INFO - __main__ - Step 72928: {'lr': 0.00026629606296523384, 'samples': 14002176, 'steps': 72927, 'loss/train': 2.284456968307495} 08/31/2021 02:20:38 - INFO - __main__ - Step 72929: {'lr': 0.00026629076750336005, 'samples': 14002368, 'steps': 72928, 'loss/train': 1.345656394958496} 08/31/2021 02:20:39 - INFO - __main__ - Step 72930: {'lr': 0.0002662854720341459, 'samples': 14002560, 'steps': 72929, 'loss/train': 1.1476861238479614} 08/31/2021 02:20:39 - INFO - __main__ - Step 72931: {'lr': 0.0002662801765575937, 'samples': 14002752, 'steps': 72930, 'loss/train': 1.3388339281082153} 08/31/2021 02:20:39 - INFO - __main__ - Step 72932: {'lr': 0.000266274881073706, 'samples': 14002944, 'steps': 72931, 'loss/train': 0.3744190037250519} 08/31/2021 02:20:40 - INFO - __main__ - Step 72933: {'lr': 0.00026626958558248514, 'samples': 14003136, 'steps': 72932, 'loss/train': 1.3008694648742676} 08/31/2021 02:20:41 - INFO - __main__ - Step 72934: {'lr': 0.0002662642900839334, 'samples': 14003328, 'steps': 72933, 'loss/train': 1.4222804307937622} 08/31/2021 02:20:42 - INFO - __main__ - Step 72935: {'lr': 0.0002662589945780531, 'samples': 14003520, 'steps': 72934, 'loss/train': 1.5208791494369507} 08/31/2021 02:20:42 - INFO - __main__ - Step 72936: {'lr': 0.0002662536990648469, 'samples': 14003712, 'steps': 72935, 'loss/train': 1.5553244352340698} 08/31/2021 02:20:42 - INFO - __main__ - Step 72937: {'lr': 0.000266248403544317, 'samples': 14003904, 'steps': 72936, 'loss/train': 1.366594672203064} 08/31/2021 02:20:43 - INFO - __main__ - Step 72938: {'lr': 0.00026624310801646577, 'samples': 14004096, 'steps': 72937, 'loss/train': 1.5886926651000977} 08/31/2021 02:20:44 - INFO - __main__ - Step 72939: {'lr': 0.00026623781248129574, 'samples': 14004288, 'steps': 72938, 'loss/train': 0.9726188778877258} 08/31/2021 02:20:45 - INFO - __main__ - Step 72940: {'lr': 0.0002662325169388091, 'samples': 14004480, 'steps': 72939, 'loss/train': 1.5384238958358765} 08/31/2021 02:20:45 - INFO - __main__ - Step 72941: {'lr': 0.0002662272213890084, 'samples': 14004672, 'steps': 72940, 'loss/train': 0.9923635721206665} 08/31/2021 02:20:46 - INFO - __main__ - Step 72942: {'lr': 0.000266221925831896, 'samples': 14004864, 'steps': 72941, 'loss/train': 1.0734798908233643} 08/31/2021 02:20:46 - INFO - __main__ - Step 72943: {'lr': 0.0002662166302674741, 'samples': 14005056, 'steps': 72942, 'loss/train': 1.3608920574188232} 08/31/2021 02:20:48 - INFO - __main__ - Step 72944: {'lr': 0.0002662113346957454, 'samples': 14005248, 'steps': 72943, 'loss/train': 1.437751054763794} 08/31/2021 02:20:49 - INFO - __main__ - Step 72945: {'lr': 0.000266206039116712, 'samples': 14005440, 'steps': 72944, 'loss/train': 1.5417602062225342} 08/31/2021 02:20:49 - INFO - __main__ - Step 72946: {'lr': 0.00026620074353037656, 'samples': 14005632, 'steps': 72945, 'loss/train': 1.7655349969863892} 08/31/2021 02:20:49 - INFO - __main__ - Step 72947: {'lr': 0.0002661954479367412, 'samples': 14005824, 'steps': 72946, 'loss/train': 1.1133201122283936} 08/31/2021 02:20:50 - INFO - __main__ - Step 72948: {'lr': 0.0002661901523358084, 'samples': 14006016, 'steps': 72947, 'loss/train': 1.2248210906982422} 08/31/2021 02:20:50 - INFO - __main__ - Step 72949: {'lr': 0.00026618485672758057, 'samples': 14006208, 'steps': 72948, 'loss/train': 0.8695427775382996} 08/31/2021 02:20:50 - INFO - __main__ - Step 72950: {'lr': 0.00026617956111206015, 'samples': 14006400, 'steps': 72949, 'loss/train': 1.4336313009262085} 08/31/2021 02:20:52 - INFO - __main__ - Step 72951: {'lr': 0.00026617426548924944, 'samples': 14006592, 'steps': 72950, 'loss/train': 1.0753157138824463} 08/31/2021 02:20:52 - INFO - __main__ - Step 72952: {'lr': 0.00026616896985915084, 'samples': 14006784, 'steps': 72951, 'loss/train': 0.9249626994132996} 08/31/2021 02:20:53 - INFO - __main__ - Step 72953: {'lr': 0.00026616367422176683, 'samples': 14006976, 'steps': 72952, 'loss/train': 1.0444837808609009} 08/31/2021 02:20:53 - INFO - __main__ - Step 72954: {'lr': 0.0002661583785770997, 'samples': 14007168, 'steps': 72953, 'loss/train': 0.876063883304596} 08/31/2021 02:20:53 - INFO - __main__ - Step 72955: {'lr': 0.00026615308292515176, 'samples': 14007360, 'steps': 72954, 'loss/train': 1.33126699924469} 08/31/2021 02:20:55 - INFO - __main__ - Step 72956: {'lr': 0.00026614778726592557, 'samples': 14007552, 'steps': 72955, 'loss/train': 1.1240441799163818} 08/31/2021 02:20:55 - INFO - __main__ - Step 72957: {'lr': 0.00026614249159942336, 'samples': 14007744, 'steps': 72956, 'loss/train': 1.9369544982910156} 08/31/2021 02:20:56 - INFO - __main__ - Step 72958: {'lr': 0.00026613719592564767, 'samples': 14007936, 'steps': 72957, 'loss/train': 1.5818445682525635} 08/31/2021 02:20:56 - INFO - __main__ - Step 72959: {'lr': 0.00026613190024460083, 'samples': 14008128, 'steps': 72958, 'loss/train': 1.1503489017486572} 08/31/2021 02:20:56 - INFO - __main__ - Step 72960: {'lr': 0.0002661266045562852, 'samples': 14008320, 'steps': 72959, 'loss/train': 0.9076793789863586} 08/31/2021 02:20:58 - INFO - __main__ - Step 72961: {'lr': 0.00026612130886070315, 'samples': 14008512, 'steps': 72960, 'loss/train': 1.2519912719726562} 08/31/2021 02:20:58 - INFO - __main__ - Step 72962: {'lr': 0.000266116013157857, 'samples': 14008704, 'steps': 72961, 'loss/train': 1.760165810585022} 08/31/2021 02:20:59 - INFO - __main__ - Step 72963: {'lr': 0.0002661107174477493, 'samples': 14008896, 'steps': 72962, 'loss/train': 2.937497854232788} 08/31/2021 02:20:59 - INFO - __main__ - Step 72964: {'lr': 0.0002661054217303823, 'samples': 14009088, 'steps': 72963, 'loss/train': 1.5380892753601074} 08/31/2021 02:20:59 - INFO - __main__ - Step 72965: {'lr': 0.0002661001260057586, 'samples': 14009280, 'steps': 72964, 'loss/train': 0.4345747232437134} 08/31/2021 02:21:01 - INFO - __main__ - Step 72966: {'lr': 0.00026609483027388033, 'samples': 14009472, 'steps': 72965, 'loss/train': 1.4392951726913452} 08/31/2021 02:21:02 - INFO - __main__ - Step 72967: {'lr': 0.0002660895345347499, 'samples': 14009664, 'steps': 72966, 'loss/train': 1.187406063079834} 08/31/2021 02:21:02 - INFO - __main__ - Step 72968: {'lr': 0.0002660842387883699, 'samples': 14009856, 'steps': 72967, 'loss/train': 0.04559677839279175} 08/31/2021 02:21:02 - INFO - __main__ - Step 72969: {'lr': 0.0002660789430347425, 'samples': 14010048, 'steps': 72968, 'loss/train': 1.5642722845077515} 08/31/2021 02:21:03 - INFO - __main__ - Step 72970: {'lr': 0.0002660736472738702, 'samples': 14010240, 'steps': 72969, 'loss/train': 1.2828258275985718} 08/31/2021 02:21:04 - INFO - __main__ - Step 72971: {'lr': 0.00026606835150575544, 'samples': 14010432, 'steps': 72970, 'loss/train': 0.7748688459396362} 08/31/2021 02:21:05 - INFO - __main__ - Step 72972: {'lr': 0.0002660630557304004, 'samples': 14010624, 'steps': 72971, 'loss/train': 0.8016748428344727} 08/31/2021 02:21:05 - INFO - __main__ - Step 72973: {'lr': 0.00026605775994780774, 'samples': 14010816, 'steps': 72972, 'loss/train': 1.7586156129837036} 08/31/2021 02:21:05 - INFO - __main__ - Step 72974: {'lr': 0.00026605246415797965, 'samples': 14011008, 'steps': 72973, 'loss/train': 1.4211291074752808} 08/31/2021 02:21:06 - INFO - __main__ - Step 72975: {'lr': 0.0002660471683609185, 'samples': 14011200, 'steps': 72974, 'loss/train': 1.469901442527771} 08/31/2021 02:21:06 - INFO - __main__ - Step 72976: {'lr': 0.0002660418725566268, 'samples': 14011392, 'steps': 72975, 'loss/train': 1.3412444591522217} 08/31/2021 02:21:08 - INFO - __main__ - Step 72977: {'lr': 0.00026603657674510684, 'samples': 14011584, 'steps': 72976, 'loss/train': 1.5744940042495728} 08/31/2021 02:21:08 - INFO - __main__ - Step 72978: {'lr': 0.0002660312809263611, 'samples': 14011776, 'steps': 72977, 'loss/train': 0.1689653992652893} 08/31/2021 02:21:08 - INFO - __main__ - Step 72979: {'lr': 0.0002660259851003919, 'samples': 14011968, 'steps': 72978, 'loss/train': 1.367154836654663} 08/31/2021 02:21:09 - INFO - __main__ - Step 72980: {'lr': 0.0002660206892672016, 'samples': 14012160, 'steps': 72979, 'loss/train': 1.5091148614883423} 08/31/2021 02:21:09 - INFO - __main__ - Step 72981: {'lr': 0.00026601539342679264, 'samples': 14012352, 'steps': 72980, 'loss/train': 0.80643230676651} 08/31/2021 02:21:11 - INFO - __main__ - Step 72982: {'lr': 0.0002660100975791674, 'samples': 14012544, 'steps': 72981, 'loss/train': 1.1689586639404297} 08/31/2021 02:21:11 - INFO - __main__ - Step 72983: {'lr': 0.0002660048017243282, 'samples': 14012736, 'steps': 72982, 'loss/train': 1.476087212562561} 08/31/2021 02:21:12 - INFO - __main__ - Step 72984: {'lr': 0.00026599950586227763, 'samples': 14012928, 'steps': 72983, 'loss/train': 0.5887980461120605} 08/31/2021 02:21:12 - INFO - __main__ - Step 72985: {'lr': 0.0002659942099930178, 'samples': 14013120, 'steps': 72984, 'loss/train': 1.3141367435455322} 08/31/2021 02:21:12 - INFO - __main__ - Step 72986: {'lr': 0.00026598891411655127, 'samples': 14013312, 'steps': 72985, 'loss/train': 1.459875464439392} 08/31/2021 02:21:14 - INFO - __main__ - Step 72987: {'lr': 0.0002659836182328804, 'samples': 14013504, 'steps': 72986, 'loss/train': 1.5716150999069214} 08/31/2021 02:21:14 - INFO - __main__ - Step 72988: {'lr': 0.00026597832234200746, 'samples': 14013696, 'steps': 72987, 'loss/train': 1.4846521615982056} 08/31/2021 02:21:15 - INFO - __main__ - Step 72989: {'lr': 0.0002659730264439351, 'samples': 14013888, 'steps': 72988, 'loss/train': 0.9725610017776489} 08/31/2021 02:21:15 - INFO - __main__ - Step 72990: {'lr': 0.0002659677305386654, 'samples': 14014080, 'steps': 72989, 'loss/train': 0.8895366191864014} 08/31/2021 02:21:15 - INFO - __main__ - Step 72991: {'lr': 0.000265962434626201, 'samples': 14014272, 'steps': 72990, 'loss/train': 1.0408705472946167} 08/31/2021 02:21:17 - INFO - __main__ - Step 72992: {'lr': 0.00026595713870654407, 'samples': 14014464, 'steps': 72991, 'loss/train': 1.0810538530349731} 08/31/2021 02:21:17 - INFO - __main__ - Step 72993: {'lr': 0.00026595184277969716, 'samples': 14014656, 'steps': 72992, 'loss/train': 5.789781093597412} 08/31/2021 02:21:18 - INFO - __main__ - Step 72994: {'lr': 0.0002659465468456626, 'samples': 14014848, 'steps': 72993, 'loss/train': 1.269100546836853} 08/31/2021 02:21:18 - INFO - __main__ - Step 72995: {'lr': 0.00026594125090444274, 'samples': 14015040, 'steps': 72994, 'loss/train': 1.1171435117721558} 08/31/2021 02:21:18 - INFO - __main__ - Step 72996: {'lr': 0.00026593595495604, 'samples': 14015232, 'steps': 72995, 'loss/train': 1.3462622165679932} 08/31/2021 02:21:19 - INFO - __main__ - Step 72997: {'lr': 0.00026593065900045674, 'samples': 14015424, 'steps': 72996, 'loss/train': 1.0879185199737549} 08/31/2021 02:21:20 - INFO - __main__ - Step 72998: {'lr': 0.00026592536303769536, 'samples': 14015616, 'steps': 72997, 'loss/train': 1.4680525064468384} 08/31/2021 02:21:21 - INFO - __main__ - Step 72999: {'lr': 0.00026592006706775836, 'samples': 14015808, 'steps': 72998, 'loss/train': 1.1318998336791992} 08/31/2021 02:21:21 - INFO - __main__ - Step 73000: {'lr': 0.000265914771090648, 'samples': 14016000, 'steps': 72999, 'loss/train': 1.1033365726470947} 08/31/2021 02:21:21 - INFO - __main__ - Step 73001: {'lr': 0.0002659094751063666, 'samples': 14016192, 'steps': 73000, 'loss/train': 1.7594276666641235} 08/31/2021 02:21:22 - INFO - __main__ - Step 73002: {'lr': 0.0002659041791149167, 'samples': 14016384, 'steps': 73001, 'loss/train': 1.9706135988235474} 08/31/2021 02:21:24 - INFO - __main__ - Step 73003: {'lr': 0.0002658988831163006, 'samples': 14016576, 'steps': 73002, 'loss/train': 0.9890288710594177} 08/31/2021 02:21:24 - INFO - __main__ - Step 73004: {'lr': 0.0002658935871105207, 'samples': 14016768, 'steps': 73003, 'loss/train': 1.0145792961120605} 08/31/2021 02:21:25 - INFO - __main__ - Step 73005: {'lr': 0.0002658882910975794, 'samples': 14016960, 'steps': 73004, 'loss/train': 0.5209456086158752} 08/31/2021 02:21:25 - INFO - __main__ - Step 73006: {'lr': 0.0002658829950774791, 'samples': 14017152, 'steps': 73005, 'loss/train': 1.3733041286468506} 08/31/2021 02:21:25 - INFO - __main__ - Step 73007: {'lr': 0.0002658776990502222, 'samples': 14017344, 'steps': 73006, 'loss/train': 1.546535849571228} 08/31/2021 02:21:27 - INFO - __main__ - Step 73008: {'lr': 0.000265872403015811, 'samples': 14017536, 'steps': 73007, 'loss/train': 1.7438734769821167} 08/31/2021 02:21:27 - INFO - __main__ - Step 73009: {'lr': 0.00026586710697424796, 'samples': 14017728, 'steps': 73008, 'loss/train': 1.4866008758544922} 08/31/2021 02:21:28 - INFO - __main__ - Step 73010: {'lr': 0.00026586181092553543, 'samples': 14017920, 'steps': 73009, 'loss/train': 0.13700726628303528} 08/31/2021 02:21:28 - INFO - __main__ - Step 73011: {'lr': 0.00026585651486967584, 'samples': 14018112, 'steps': 73010, 'loss/train': 1.1763054132461548} 08/31/2021 02:21:28 - INFO - __main__ - Step 73012: {'lr': 0.0002658512188066715, 'samples': 14018304, 'steps': 73011, 'loss/train': 1.2303133010864258} 08/31/2021 02:21:29 - INFO - __main__ - Step 73013: {'lr': 0.0002658459227365249, 'samples': 14018496, 'steps': 73012, 'loss/train': 0.7416631579399109} 08/31/2021 02:21:30 - INFO - __main__ - Step 73014: {'lr': 0.0002658406266592384, 'samples': 14018688, 'steps': 73013, 'loss/train': 1.0967355966567993} 08/31/2021 02:21:31 - INFO - __main__ - Step 73015: {'lr': 0.0002658353305748143, 'samples': 14018880, 'steps': 73014, 'loss/train': 1.3079719543457031} 08/31/2021 02:21:31 - INFO - __main__ - Step 73016: {'lr': 0.00026583003448325506, 'samples': 14019072, 'steps': 73015, 'loss/train': 1.2797702550888062} 08/31/2021 02:21:31 - INFO - __main__ - Step 73017: {'lr': 0.00026582473838456303, 'samples': 14019264, 'steps': 73016, 'loss/train': 1.3092806339263916} 08/31/2021 02:21:32 - INFO - __main__ - Step 73018: {'lr': 0.00026581944227874063, 'samples': 14019456, 'steps': 73017, 'loss/train': 1.9770692586898804} 08/31/2021 02:21:33 - INFO - __main__ - Step 73019: {'lr': 0.0002658141461657902, 'samples': 14019648, 'steps': 73018, 'loss/train': 1.5962421894073486} 08/31/2021 02:21:34 - INFO - __main__ - Step 73020: {'lr': 0.0002658088500457142, 'samples': 14019840, 'steps': 73019, 'loss/train': 0.5112539529800415} 08/31/2021 02:21:34 - INFO - __main__ - Step 73021: {'lr': 0.00026580355391851495, 'samples': 14020032, 'steps': 73020, 'loss/train': 1.4080957174301147} 08/31/2021 02:21:34 - INFO - __main__ - Step 73022: {'lr': 0.0002657982577841949, 'samples': 14020224, 'steps': 73021, 'loss/train': 0.8737781047821045} 08/31/2021 02:21:35 - INFO - __main__ - Step 73023: {'lr': 0.0002657929616427564, 'samples': 14020416, 'steps': 73022, 'loss/train': 1.702631950378418} 08/31/2021 02:21:36 - INFO - __main__ - Step 73024: {'lr': 0.0002657876654942018, 'samples': 14020608, 'steps': 73023, 'loss/train': 1.331117868423462} 08/31/2021 02:21:37 - INFO - __main__ - Step 73025: {'lr': 0.0002657823693385335, 'samples': 14020800, 'steps': 73024, 'loss/train': 1.4716187715530396} 08/31/2021 02:21:37 - INFO - __main__ - Step 73026: {'lr': 0.00026577707317575395, 'samples': 14020992, 'steps': 73025, 'loss/train': 1.3134716749191284} 08/31/2021 02:21:37 - INFO - __main__ - Step 73027: {'lr': 0.0002657717770058655, 'samples': 14021184, 'steps': 73026, 'loss/train': 1.002944827079773} 08/31/2021 02:21:38 - INFO - __main__ - Step 73028: {'lr': 0.00026576648082887055, 'samples': 14021376, 'steps': 73027, 'loss/train': 1.3375859260559082} 08/31/2021 02:21:39 - INFO - __main__ - Step 73029: {'lr': 0.00026576118464477147, 'samples': 14021568, 'steps': 73028, 'loss/train': 1.6759591102600098} 08/31/2021 02:21:40 - INFO - __main__ - Step 73030: {'lr': 0.0002657558884535706, 'samples': 14021760, 'steps': 73029, 'loss/train': 0.7573211789131165} 08/31/2021 02:21:40 - INFO - __main__ - Step 73031: {'lr': 0.00026575059225527036, 'samples': 14021952, 'steps': 73030, 'loss/train': 1.250441551208496} 08/31/2021 02:21:40 - INFO - __main__ - Step 73032: {'lr': 0.0002657452960498731, 'samples': 14022144, 'steps': 73031, 'loss/train': 1.4415512084960938} 08/31/2021 02:21:41 - INFO - __main__ - Step 73033: {'lr': 0.0002657399998373813, 'samples': 14022336, 'steps': 73032, 'loss/train': 1.1970099210739136} 08/31/2021 02:21:42 - INFO - __main__ - Step 73034: {'lr': 0.00026573470361779744, 'samples': 14022528, 'steps': 73033, 'loss/train': 0.9237213134765625} 08/31/2021 02:21:42 - INFO - __main__ - Step 73035: {'lr': 0.00026572940739112363, 'samples': 14022720, 'steps': 73034, 'loss/train': 1.0604419708251953} 08/31/2021 02:21:43 - INFO - __main__ - Step 73036: {'lr': 0.0002657241111573624, 'samples': 14022912, 'steps': 73035, 'loss/train': 1.1363441944122314} 08/31/2021 02:21:43 - INFO - __main__ - Step 73037: {'lr': 0.0002657188149165161, 'samples': 14023104, 'steps': 73036, 'loss/train': 0.9213749170303345} 08/31/2021 02:21:43 - INFO - __main__ - Step 73038: {'lr': 0.0002657135186685872, 'samples': 14023296, 'steps': 73037, 'loss/train': 0.12948012351989746} 08/31/2021 02:21:46 - INFO - __main__ - Step 73039: {'lr': 0.00026570822241357803, 'samples': 14023488, 'steps': 73038, 'loss/train': 1.2989953756332397} 08/31/2021 02:21:46 - INFO - __main__ - Step 73040: {'lr': 0.00026570292615149093, 'samples': 14023680, 'steps': 73039, 'loss/train': 1.3735284805297852} 08/31/2021 02:21:46 - INFO - __main__ - Step 73041: {'lr': 0.0002656976298823284, 'samples': 14023872, 'steps': 73040, 'loss/train': 0.7839721441268921} 08/31/2021 02:21:47 - INFO - __main__ - Step 73042: {'lr': 0.00026569233360609266, 'samples': 14024064, 'steps': 73041, 'loss/train': 0.7973423004150391} 08/31/2021 02:21:47 - INFO - __main__ - Step 73043: {'lr': 0.0002656870373227863, 'samples': 14024256, 'steps': 73042, 'loss/train': 1.7996137142181396} 08/31/2021 02:21:47 - INFO - __main__ - Step 73044: {'lr': 0.0002656817410324116, 'samples': 14024448, 'steps': 73043, 'loss/train': 0.3877585232257843} 08/31/2021 02:21:48 - INFO - __main__ - Step 73045: {'lr': 0.0002656764447349708, 'samples': 14024640, 'steps': 73044, 'loss/train': 0.9113698601722717} 08/31/2021 02:21:49 - INFO - __main__ - Step 73046: {'lr': 0.0002656711484304666, 'samples': 14024832, 'steps': 73045, 'loss/train': 1.4779794216156006} 08/31/2021 02:21:50 - INFO - __main__ - Step 73047: {'lr': 0.0002656658521189012, 'samples': 14025024, 'steps': 73046, 'loss/train': 2.313729763031006} 08/31/2021 02:21:50 - INFO - __main__ - Step 73048: {'lr': 0.000265660555800277, 'samples': 14025216, 'steps': 73047, 'loss/train': 0.8346641063690186} 08/31/2021 02:21:50 - INFO - __main__ - Step 73049: {'lr': 0.0002656552594745963, 'samples': 14025408, 'steps': 73048, 'loss/train': 1.081662654876709} 08/31/2021 02:21:51 - INFO - __main__ - Step 73050: {'lr': 0.0002656499631418617, 'samples': 14025600, 'steps': 73049, 'loss/train': 1.184011697769165} 08/31/2021 02:21:53 - INFO - __main__ - Step 73051: {'lr': 0.0002656446668020754, 'samples': 14025792, 'steps': 73050, 'loss/train': 0.6866941452026367} 08/31/2021 02:21:53 - INFO - __main__ - Step 73052: {'lr': 0.00026563937045523986, 'samples': 14025984, 'steps': 73051, 'loss/train': 0.1634615808725357} 08/31/2021 02:21:54 - INFO - __main__ - Step 73053: {'lr': 0.0002656340741013575, 'samples': 14026176, 'steps': 73052, 'loss/train': 1.3359400033950806} 08/31/2021 02:21:54 - INFO - __main__ - Step 73054: {'lr': 0.00026562877774043066, 'samples': 14026368, 'steps': 73053, 'loss/train': 1.4278738498687744} 08/31/2021 02:21:54 - INFO - __main__ - Step 73055: {'lr': 0.00026562348137246174, 'samples': 14026560, 'steps': 73054, 'loss/train': 1.3703423738479614} 08/31/2021 02:21:56 - INFO - __main__ - Step 73056: {'lr': 0.00026561818499745303, 'samples': 14026752, 'steps': 73055, 'loss/train': 0.07163830101490021} 08/31/2021 02:21:57 - INFO - __main__ - Step 73057: {'lr': 0.0002656128886154071, 'samples': 14026944, 'steps': 73056, 'loss/train': 1.2103140354156494} 08/31/2021 02:21:57 - INFO - __main__ - Step 73058: {'lr': 0.0002656075922263262, 'samples': 14027136, 'steps': 73057, 'loss/train': 1.1814136505126953} 08/31/2021 02:21:58 - INFO - __main__ - Step 73059: {'lr': 0.0002656022958302128, 'samples': 14027328, 'steps': 73058, 'loss/train': 1.4020029306411743} 08/31/2021 02:21:58 - INFO - __main__ - Step 73060: {'lr': 0.00026559699942706926, 'samples': 14027520, 'steps': 73059, 'loss/train': 1.0373163223266602} 08/31/2021 02:21:59 - INFO - __main__ - Step 73061: {'lr': 0.00026559170301689787, 'samples': 14027712, 'steps': 73060, 'loss/train': 0.0598764531314373} 08/31/2021 02:22:00 - INFO - __main__ - Step 73062: {'lr': 0.0002655864065997012, 'samples': 14027904, 'steps': 73061, 'loss/train': 1.6769126653671265} 08/31/2021 02:22:00 - INFO - __main__ - Step 73063: {'lr': 0.00026558111017548145, 'samples': 14028096, 'steps': 73062, 'loss/train': 1.223038911819458} 08/31/2021 02:22:00 - INFO - __main__ - Step 73064: {'lr': 0.0002655758137442411, 'samples': 14028288, 'steps': 73063, 'loss/train': 1.5555061101913452} 08/31/2021 02:22:01 - INFO - __main__ - Step 73065: {'lr': 0.0002655705173059826, 'samples': 14028480, 'steps': 73064, 'loss/train': 1.2273811101913452} 08/31/2021 02:22:02 - INFO - __main__ - Step 73066: {'lr': 0.0002655652208607082, 'samples': 14028672, 'steps': 73065, 'loss/train': 1.006769061088562} 08/31/2021 02:22:03 - INFO - __main__ - Step 73067: {'lr': 0.0002655599244084204, 'samples': 14028864, 'steps': 73066, 'loss/train': 1.594373345375061} 08/31/2021 02:22:03 - INFO - __main__ - Step 73068: {'lr': 0.0002655546279491215, 'samples': 14029056, 'steps': 73067, 'loss/train': 1.134746789932251} 08/31/2021 02:22:03 - INFO - __main__ - Step 73069: {'lr': 0.0002655493314828139, 'samples': 14029248, 'steps': 73068, 'loss/train': 1.215878963470459} 08/31/2021 02:22:04 - INFO - __main__ - Step 73070: {'lr': 0.00026554403500950006, 'samples': 14029440, 'steps': 73069, 'loss/train': 1.4169223308563232} 08/31/2021 02:22:05 - INFO - __main__ - Step 73071: {'lr': 0.0002655387385291823, 'samples': 14029632, 'steps': 73070, 'loss/train': 1.248420000076294} 08/31/2021 02:22:06 - INFO - __main__ - Step 73072: {'lr': 0.000265533442041863, 'samples': 14029824, 'steps': 73071, 'loss/train': 0.8522987365722656} 08/31/2021 02:22:06 - INFO - __main__ - Step 73073: {'lr': 0.0002655281455475446, 'samples': 14030016, 'steps': 73072, 'loss/train': 0.9572522640228271} 08/31/2021 02:22:06 - INFO - __main__ - Step 73074: {'lr': 0.0002655228490462295, 'samples': 14030208, 'steps': 73073, 'loss/train': 1.0976446866989136} 08/31/2021 02:22:07 - INFO - __main__ - Step 73075: {'lr': 0.00026551755253792, 'samples': 14030400, 'steps': 73074, 'loss/train': 0.5588639974594116} 08/31/2021 02:22:07 - INFO - __main__ - Step 73076: {'lr': 0.0002655122560226185, 'samples': 14030592, 'steps': 73075, 'loss/train': 1.0446282625198364} 08/31/2021 02:22:09 - INFO - __main__ - Step 73077: {'lr': 0.00026550695950032743, 'samples': 14030784, 'steps': 73076, 'loss/train': 1.1420894861221313} 08/31/2021 02:22:09 - INFO - __main__ - Step 73078: {'lr': 0.0002655016629710492, 'samples': 14030976, 'steps': 73077, 'loss/train': 1.2855775356292725} 08/31/2021 02:22:10 - INFO - __main__ - Step 73079: {'lr': 0.00026549636643478615, 'samples': 14031168, 'steps': 73078, 'loss/train': 0.14886820316314697} 08/31/2021 02:22:10 - INFO - __main__ - Step 73080: {'lr': 0.00026549106989154066, 'samples': 14031360, 'steps': 73079, 'loss/train': 1.1463534832000732} 08/31/2021 02:22:10 - INFO - __main__ - Step 73081: {'lr': 0.0002654857733413152, 'samples': 14031552, 'steps': 73080, 'loss/train': 1.478468894958496} 08/31/2021 02:22:12 - INFO - __main__ - Step 73082: {'lr': 0.000265480476784112, 'samples': 14031744, 'steps': 73081, 'loss/train': 0.7648167014122009} 08/31/2021 02:22:12 - INFO - __main__ - Step 73083: {'lr': 0.00026547518021993353, 'samples': 14031936, 'steps': 73082, 'loss/train': 1.9097483158111572} 08/31/2021 02:22:13 - INFO - __main__ - Step 73084: {'lr': 0.00026546988364878224, 'samples': 14032128, 'steps': 73083, 'loss/train': 1.0021528005599976} 08/31/2021 02:22:13 - INFO - __main__ - Step 73085: {'lr': 0.0002654645870706604, 'samples': 14032320, 'steps': 73084, 'loss/train': 1.4584599733352661} 08/31/2021 02:22:13 - INFO - __main__ - Step 73086: {'lr': 0.0002654592904855705, 'samples': 14032512, 'steps': 73085, 'loss/train': 0.8490316867828369} 08/31/2021 02:22:15 - INFO - __main__ - Step 73087: {'lr': 0.00026545399389351493, 'samples': 14032704, 'steps': 73086, 'loss/train': 2.305785894393921} 08/31/2021 02:22:15 - INFO - __main__ - Step 73088: {'lr': 0.00026544869729449596, 'samples': 14032896, 'steps': 73087, 'loss/train': 1.3578436374664307} 08/31/2021 02:22:16 - INFO - __main__ - Step 73089: {'lr': 0.00026544340068851603, 'samples': 14033088, 'steps': 73088, 'loss/train': 1.1619352102279663} 08/31/2021 02:22:16 - INFO - __main__ - Step 73090: {'lr': 0.00026543810407557753, 'samples': 14033280, 'steps': 73089, 'loss/train': 1.399930715560913} 08/31/2021 02:22:16 - INFO - __main__ - Step 73091: {'lr': 0.00026543280745568295, 'samples': 14033472, 'steps': 73090, 'loss/train': 1.135161280632019} 08/31/2021 02:22:18 - INFO - __main__ - Step 73092: {'lr': 0.00026542751082883446, 'samples': 14033664, 'steps': 73091, 'loss/train': 1.4470274448394775} 08/31/2021 02:22:19 - INFO - __main__ - Step 73093: {'lr': 0.00026542221419503467, 'samples': 14033856, 'steps': 73092, 'loss/train': 0.07359208166599274} 08/31/2021 02:22:19 - INFO - __main__ - Step 73094: {'lr': 0.0002654169175542859, 'samples': 14034048, 'steps': 73093, 'loss/train': 0.8994735479354858} 08/31/2021 02:22:19 - INFO - __main__ - Step 73095: {'lr': 0.0002654116209065904, 'samples': 14034240, 'steps': 73094, 'loss/train': 0.9855991005897522} 08/31/2021 02:22:20 - INFO - __main__ - Step 73096: {'lr': 0.0002654063242519507, 'samples': 14034432, 'steps': 73095, 'loss/train': 1.447925090789795} 08/31/2021 02:22:20 - INFO - __main__ - Step 73097: {'lr': 0.00026540102759036924, 'samples': 14034624, 'steps': 73096, 'loss/train': 1.2965556383132935} 08/31/2021 02:22:21 - INFO - __main__ - Step 73098: {'lr': 0.00026539573092184814, 'samples': 14034816, 'steps': 73097, 'loss/train': 1.2037569284439087} 08/31/2021 02:22:22 - INFO - __main__ - Step 73099: {'lr': 0.0002653904342463901, 'samples': 14035008, 'steps': 73098, 'loss/train': 1.0003396272659302} 08/31/2021 02:22:22 - INFO - __main__ - Step 73100: {'lr': 0.0002653851375639973, 'samples': 14035200, 'steps': 73099, 'loss/train': 2.001826047897339} 08/31/2021 02:22:23 - INFO - __main__ - Step 73101: {'lr': 0.00026537984087467224, 'samples': 14035392, 'steps': 73100, 'loss/train': 0.31254515051841736} 08/31/2021 02:22:23 - INFO - __main__ - Step 73102: {'lr': 0.0002653745441784172, 'samples': 14035584, 'steps': 73101, 'loss/train': 0.7089697122573853} 08/31/2021 02:22:24 - INFO - __main__ - Step 73103: {'lr': 0.0002653692474752347, 'samples': 14035776, 'steps': 73102, 'loss/train': 1.2378675937652588} 08/31/2021 02:22:25 - INFO - __main__ - Step 73104: {'lr': 0.00026536395076512696, 'samples': 14035968, 'steps': 73103, 'loss/train': 1.0890083312988281} 08/31/2021 02:22:25 - INFO - __main__ - Step 73105: {'lr': 0.00026535865404809654, 'samples': 14036160, 'steps': 73104, 'loss/train': 1.3376625776290894} 08/31/2021 02:22:26 - INFO - __main__ - Step 73106: {'lr': 0.0002653533573241457, 'samples': 14036352, 'steps': 73105, 'loss/train': 1.1134765148162842} 08/31/2021 02:22:26 - INFO - __main__ - Step 73107: {'lr': 0.00026534806059327697, 'samples': 14036544, 'steps': 73106, 'loss/train': 1.2213020324707031} 08/31/2021 02:22:28 - INFO - __main__ - Step 73108: {'lr': 0.0002653427638554926, 'samples': 14036736, 'steps': 73107, 'loss/train': 1.2176525592803955} 08/31/2021 02:22:28 - INFO - __main__ - Step 73109: {'lr': 0.00026533746711079496, 'samples': 14036928, 'steps': 73108, 'loss/train': 1.3770568370819092} 08/31/2021 02:22:29 - INFO - __main__ - Step 73110: {'lr': 0.0002653321703591865, 'samples': 14037120, 'steps': 73109, 'loss/train': 1.3218778371810913} 08/31/2021 02:22:29 - INFO - __main__ - Step 73111: {'lr': 0.00026532687360066964, 'samples': 14037312, 'steps': 73110, 'loss/train': 1.5917996168136597} 08/31/2021 02:22:29 - INFO - __main__ - Step 73112: {'lr': 0.0002653215768352468, 'samples': 14037504, 'steps': 73111, 'loss/train': 1.1990139484405518} 08/31/2021 02:22:31 - INFO - __main__ - Step 73113: {'lr': 0.00026531628006292015, 'samples': 14037696, 'steps': 73112, 'loss/train': 1.3273948431015015} 08/31/2021 02:22:32 - INFO - __main__ - Step 73114: {'lr': 0.00026531098328369225, 'samples': 14037888, 'steps': 73113, 'loss/train': 1.1475906372070312} 08/31/2021 02:22:32 - INFO - __main__ - Step 73115: {'lr': 0.00026530568649756547, 'samples': 14038080, 'steps': 73114, 'loss/train': 0.9254710674285889} 08/31/2021 02:22:32 - INFO - __main__ - Step 73116: {'lr': 0.00026530038970454223, 'samples': 14038272, 'steps': 73115, 'loss/train': 1.4343845844268799} 08/31/2021 02:22:33 - INFO - __main__ - Step 73117: {'lr': 0.00026529509290462483, 'samples': 14038464, 'steps': 73116, 'loss/train': 1.2572330236434937} 08/31/2021 02:22:33 - INFO - __main__ - Step 73118: {'lr': 0.00026528979609781575, 'samples': 14038656, 'steps': 73117, 'loss/train': 1.4960881471633911} 08/31/2021 02:22:34 - INFO - __main__ - Step 73119: {'lr': 0.00026528449928411727, 'samples': 14038848, 'steps': 73118, 'loss/train': 0.09197686612606049} 08/31/2021 02:22:35 - INFO - __main__ - Step 73120: {'lr': 0.0002652792024635318, 'samples': 14039040, 'steps': 73119, 'loss/train': 1.0738270282745361} 08/31/2021 02:22:35 - INFO - __main__ - Step 73121: {'lr': 0.0002652739056360618, 'samples': 14039232, 'steps': 73120, 'loss/train': 1.1419733762741089} 08/31/2021 02:22:36 - INFO - __main__ - Step 73122: {'lr': 0.0002652686088017096, 'samples': 14039424, 'steps': 73121, 'loss/train': 1.2305264472961426} 08/31/2021 02:22:36 - INFO - __main__ - Step 73123: {'lr': 0.00026526331196047764, 'samples': 14039616, 'steps': 73122, 'loss/train': 0.9767038822174072} 08/31/2021 02:22:38 - INFO - __main__ - Step 73124: {'lr': 0.00026525801511236827, 'samples': 14039808, 'steps': 73123, 'loss/train': 1.522409200668335} 08/31/2021 02:22:38 - INFO - __main__ - Step 73125: {'lr': 0.0002652527182573838, 'samples': 14040000, 'steps': 73124, 'loss/train': 0.6983116865158081} 08/31/2021 02:22:38 - INFO - __main__ - Step 73126: {'lr': 0.0002652474213955267, 'samples': 14040192, 'steps': 73125, 'loss/train': 0.705600917339325} 08/31/2021 02:22:39 - INFO - __main__ - Step 73127: {'lr': 0.0002652421245267994, 'samples': 14040384, 'steps': 73126, 'loss/train': 1.5444194078445435} 08/31/2021 02:22:39 - INFO - __main__ - Step 73128: {'lr': 0.0002652368276512042, 'samples': 14040576, 'steps': 73127, 'loss/train': 1.0466694831848145} 08/31/2021 02:22:41 - INFO - __main__ - Step 73129: {'lr': 0.00026523153076874357, 'samples': 14040768, 'steps': 73128, 'loss/train': 1.3083550930023193} 08/31/2021 02:22:41 - INFO - __main__ - Step 73130: {'lr': 0.0002652262338794198, 'samples': 14040960, 'steps': 73129, 'loss/train': 1.7036712169647217} 08/31/2021 02:22:42 - INFO - __main__ - Step 73131: {'lr': 0.00026522093698323534, 'samples': 14041152, 'steps': 73130, 'loss/train': 1.1166342496871948} 08/31/2021 02:22:42 - INFO - __main__ - Step 73132: {'lr': 0.00026521564008019253, 'samples': 14041344, 'steps': 73131, 'loss/train': 0.0558927059173584} 08/31/2021 02:22:42 - INFO - __main__ - Step 73133: {'lr': 0.0002652103431702938, 'samples': 14041536, 'steps': 73132, 'loss/train': 1.405735731124878} 08/31/2021 02:22:44 - INFO - __main__ - Step 73134: {'lr': 0.0002652050462535416, 'samples': 14041728, 'steps': 73133, 'loss/train': 1.4358172416687012} 08/31/2021 02:22:45 - INFO - __main__ - Step 73135: {'lr': 0.0002651997493299382, 'samples': 14041920, 'steps': 73134, 'loss/train': 0.5607736110687256} 08/31/2021 02:22:45 - INFO - __main__ - Step 73136: {'lr': 0.000265194452399486, 'samples': 14042112, 'steps': 73135, 'loss/train': 1.3803410530090332} 08/31/2021 02:22:45 - INFO - __main__ - Step 73137: {'lr': 0.0002651891554621874, 'samples': 14042304, 'steps': 73136, 'loss/train': 1.7329699993133545} 08/31/2021 02:22:46 - INFO - __main__ - Step 73138: {'lr': 0.0002651838585180448, 'samples': 14042496, 'steps': 73137, 'loss/train': 0.626850962638855} 08/31/2021 02:22:47 - INFO - __main__ - Step 73139: {'lr': 0.0002651785615670606, 'samples': 14042688, 'steps': 73138, 'loss/train': 0.13998164236545563} 08/31/2021 02:22:48 - INFO - __main__ - Step 73140: {'lr': 0.0002651732646092372, 'samples': 14042880, 'steps': 73139, 'loss/train': 1.2297887802124023} 08/31/2021 02:22:48 - INFO - __main__ - Step 73141: {'lr': 0.00026516796764457695, 'samples': 14043072, 'steps': 73140, 'loss/train': 0.17812156677246094} 08/31/2021 02:22:49 - INFO - __main__ - Step 73142: {'lr': 0.0002651626706730823, 'samples': 14043264, 'steps': 73141, 'loss/train': 0.1705489158630371} 08/31/2021 02:22:49 - INFO - __main__ - Step 73143: {'lr': 0.00026515737369475545, 'samples': 14043456, 'steps': 73142, 'loss/train': 1.2295348644256592} 08/31/2021 02:22:50 - INFO - __main__ - Step 73144: {'lr': 0.000265152076709599, 'samples': 14043648, 'steps': 73143, 'loss/train': 0.868702232837677} 08/31/2021 02:22:51 - INFO - __main__ - Step 73145: {'lr': 0.00026514677971761525, 'samples': 14043840, 'steps': 73144, 'loss/train': 1.4219295978546143} 08/31/2021 02:22:51 - INFO - __main__ - Step 73146: {'lr': 0.0002651414827188066, 'samples': 14044032, 'steps': 73145, 'loss/train': 1.4454364776611328} 08/31/2021 02:22:51 - INFO - __main__ - Step 73147: {'lr': 0.00026513618571317543, 'samples': 14044224, 'steps': 73146, 'loss/train': 1.818782091140747} 08/31/2021 02:22:52 - INFO - __main__ - Step 73148: {'lr': 0.00026513088870072415, 'samples': 14044416, 'steps': 73147, 'loss/train': 1.3231077194213867} 08/31/2021 02:22:53 - INFO - __main__ - Step 73149: {'lr': 0.00026512559168145514, 'samples': 14044608, 'steps': 73148, 'loss/train': 1.2112711668014526} 08/31/2021 02:22:54 - INFO - __main__ - Step 73150: {'lr': 0.00026512029465537067, 'samples': 14044800, 'steps': 73149, 'loss/train': 1.267490029335022} 08/31/2021 02:22:54 - INFO - __main__ - Step 73151: {'lr': 0.00026511499762247334, 'samples': 14044992, 'steps': 73150, 'loss/train': 1.2850029468536377} 08/31/2021 02:22:54 - INFO - __main__ - Step 73152: {'lr': 0.00026510970058276533, 'samples': 14045184, 'steps': 73151, 'loss/train': 0.8455951809883118} 08/31/2021 02:22:55 - INFO - __main__ - Step 73153: {'lr': 0.0002651044035362492, 'samples': 14045376, 'steps': 73152, 'loss/train': 1.2810708284378052} 08/31/2021 02:22:56 - INFO - __main__ - Step 73154: {'lr': 0.00026509910648292716, 'samples': 14045568, 'steps': 73153, 'loss/train': 1.353956937789917} 08/31/2021 02:22:57 - INFO - __main__ - Step 73155: {'lr': 0.0002650938094228019, 'samples': 14045760, 'steps': 73154, 'loss/train': 1.3038299083709717} 08/31/2021 02:22:57 - INFO - __main__ - Step 73156: {'lr': 0.0002650885123558754, 'samples': 14045952, 'steps': 73155, 'loss/train': 1.3638074398040771} 08/31/2021 02:22:57 - INFO - __main__ - Step 73157: {'lr': 0.00026508321528215034, 'samples': 14046144, 'steps': 73156, 'loss/train': 0.8844515085220337} 08/31/2021 02:22:58 - INFO - __main__ - Step 73158: {'lr': 0.00026507791820162894, 'samples': 14046336, 'steps': 73157, 'loss/train': 0.7829955220222473} 08/31/2021 02:22:58 - INFO - __main__ - Step 73159: {'lr': 0.0002650726211143137, 'samples': 14046528, 'steps': 73158, 'loss/train': 1.5982015132904053} 08/31/2021 02:23:00 - INFO - __main__ - Step 73160: {'lr': 0.000265067324020207, 'samples': 14046720, 'steps': 73159, 'loss/train': 1.3365600109100342} 08/31/2021 02:23:01 - INFO - __main__ - Step 73161: {'lr': 0.0002650620269193112, 'samples': 14046912, 'steps': 73160, 'loss/train': 1.0765149593353271} 08/31/2021 02:23:01 - INFO - __main__ - Step 73162: {'lr': 0.0002650567298116287, 'samples': 14047104, 'steps': 73161, 'loss/train': 1.1449239253997803} 08/31/2021 02:23:01 - INFO - __main__ - Step 73163: {'lr': 0.0002650514326971618, 'samples': 14047296, 'steps': 73162, 'loss/train': 1.3646115064620972} 08/31/2021 02:23:02 - INFO - __main__ - Step 73164: {'lr': 0.00026504613557591303, 'samples': 14047488, 'steps': 73163, 'loss/train': 1.1091307401657104} 08/31/2021 02:23:02 - INFO - __main__ - Step 73165: {'lr': 0.0002650408384478846, 'samples': 14047680, 'steps': 73164, 'loss/train': 1.3164966106414795} 08/31/2021 02:23:04 - INFO - __main__ - Step 73166: {'lr': 0.0002650355413130791, 'samples': 14047872, 'steps': 73165, 'loss/train': 0.5973919630050659} 08/31/2021 02:23:05 - INFO - __main__ - Step 73167: {'lr': 0.0002650302441714988, 'samples': 14048064, 'steps': 73166, 'loss/train': 1.505922555923462} 08/31/2021 02:23:05 - INFO - __main__ - Step 73168: {'lr': 0.0002650249470231461, 'samples': 14048256, 'steps': 73167, 'loss/train': 1.443696141242981} 08/31/2021 02:23:05 - INFO - __main__ - Step 73169: {'lr': 0.0002650196498680234, 'samples': 14048448, 'steps': 73168, 'loss/train': 1.279679775238037} 08/31/2021 02:23:06 - INFO - __main__ - Step 73170: {'lr': 0.00026501435270613307, 'samples': 14048640, 'steps': 73169, 'loss/train': 0.870452880859375} 08/31/2021 02:23:07 - INFO - __main__ - Step 73171: {'lr': 0.00026500905553747747, 'samples': 14048832, 'steps': 73170, 'loss/train': 1.229486346244812} 08/31/2021 02:23:08 - INFO - __main__ - Step 73172: {'lr': 0.00026500375836205895, 'samples': 14049024, 'steps': 73171, 'loss/train': 0.18498925864696503} 08/31/2021 02:23:08 - INFO - __main__ - Step 73173: {'lr': 0.0002649984611798801, 'samples': 14049216, 'steps': 73172, 'loss/train': 1.4328806400299072} 08/31/2021 02:23:08 - INFO - __main__ - Step 73174: {'lr': 0.00026499316399094316, 'samples': 14049408, 'steps': 73173, 'loss/train': 0.8677010536193848} 08/31/2021 02:23:09 - INFO - __main__ - Step 73175: {'lr': 0.0002649878667952505, 'samples': 14049600, 'steps': 73174, 'loss/train': 1.4555052518844604} 08/31/2021 02:23:10 - INFO - __main__ - Step 73176: {'lr': 0.00026498256959280454, 'samples': 14049792, 'steps': 73175, 'loss/train': 2.772996187210083} 08/31/2021 02:23:11 - INFO - __main__ - Step 73177: {'lr': 0.0002649772723836077, 'samples': 14049984, 'steps': 73176, 'loss/train': 1.927402377128601} 08/31/2021 02:23:11 - INFO - __main__ - Step 73178: {'lr': 0.00026497197516766225, 'samples': 14050176, 'steps': 73177, 'loss/train': 1.533288836479187} 08/31/2021 02:23:11 - INFO - __main__ - Step 73179: {'lr': 0.0002649666779449707, 'samples': 14050368, 'steps': 73178, 'loss/train': 1.2843053340911865} 08/31/2021 02:23:12 - INFO - __main__ - Step 73180: {'lr': 0.00026496138071553546, 'samples': 14050560, 'steps': 73179, 'loss/train': 1.7660819292068481} 08/31/2021 02:23:13 - INFO - __main__ - Step 73181: {'lr': 0.0002649560834793588, 'samples': 14050752, 'steps': 73180, 'loss/train': 1.2816359996795654} 08/31/2021 02:23:14 - INFO - __main__ - Step 73182: {'lr': 0.00026495078623644315, 'samples': 14050944, 'steps': 73181, 'loss/train': 1.3929070234298706} 08/31/2021 02:23:14 - INFO - __main__ - Step 73183: {'lr': 0.00026494548898679094, 'samples': 14051136, 'steps': 73182, 'loss/train': 1.2328500747680664} 08/31/2021 02:23:14 - INFO - __main__ - Step 73184: {'lr': 0.00026494019173040447, 'samples': 14051328, 'steps': 73183, 'loss/train': 1.1262447834014893} 08/31/2021 02:23:15 - INFO - __main__ - Step 73185: {'lr': 0.0002649348944672862, 'samples': 14051520, 'steps': 73184, 'loss/train': 1.4434667825698853} 08/31/2021 02:23:15 - INFO - __main__ - Step 73186: {'lr': 0.0002649295971974385, 'samples': 14051712, 'steps': 73185, 'loss/train': 1.666518211364746} 08/31/2021 02:23:16 - INFO - __main__ - Step 73187: {'lr': 0.00026492429992086374, 'samples': 14051904, 'steps': 73186, 'loss/train': 0.93953537940979} 08/31/2021 02:23:17 - INFO - __main__ - Step 73188: {'lr': 0.0002649190026375644, 'samples': 14052096, 'steps': 73187, 'loss/train': 1.4598276615142822} 08/31/2021 02:23:17 - INFO - __main__ - Step 73189: {'lr': 0.0002649137053475427, 'samples': 14052288, 'steps': 73188, 'loss/train': 0.9979143142700195} 08/31/2021 02:23:18 - INFO - __main__ - Step 73190: {'lr': 0.0002649084080508011, 'samples': 14052480, 'steps': 73189, 'loss/train': 1.2561802864074707} 08/31/2021 02:23:18 - INFO - __main__ - Step 73191: {'lr': 0.0002649031107473421, 'samples': 14052672, 'steps': 73190, 'loss/train': 1.4062790870666504} 08/31/2021 02:23:20 - INFO - __main__ - Step 73192: {'lr': 0.0002648978134371679, 'samples': 14052864, 'steps': 73191, 'loss/train': 1.1579084396362305} 08/31/2021 02:23:20 - INFO - __main__ - Step 73193: {'lr': 0.000264892516120281, 'samples': 14053056, 'steps': 73192, 'loss/train': 1.569324016571045} 08/31/2021 02:23:20 - INFO - __main__ - Step 73194: {'lr': 0.00026488721879668373, 'samples': 14053248, 'steps': 73193, 'loss/train': 0.9964125752449036} 08/31/2021 02:23:21 - INFO - __main__ - Step 73195: {'lr': 0.00026488192146637864, 'samples': 14053440, 'steps': 73194, 'loss/train': 1.6624447107315063} 08/31/2021 02:23:21 - INFO - __main__ - Step 73196: {'lr': 0.00026487662412936786, 'samples': 14053632, 'steps': 73195, 'loss/train': 0.8394228219985962} 08/31/2021 02:23:23 - INFO - __main__ - Step 73197: {'lr': 0.00026487132678565395, 'samples': 14053824, 'steps': 73196, 'loss/train': 0.96117103099823} 08/31/2021 02:23:23 - INFO - __main__ - Step 73198: {'lr': 0.00026486602943523923, 'samples': 14054016, 'steps': 73197, 'loss/train': 1.597739577293396} 08/31/2021 02:23:23 - INFO - __main__ - Step 73199: {'lr': 0.0002648607320781261, 'samples': 14054208, 'steps': 73198, 'loss/train': 1.1898099184036255} 08/31/2021 02:23:24 - INFO - __main__ - Step 73200: {'lr': 0.00026485543471431694, 'samples': 14054400, 'steps': 73199, 'loss/train': 1.4003334045410156} 08/31/2021 02:23:24 - INFO - __main__ - Step 73201: {'lr': 0.0002648501373438142, 'samples': 14054592, 'steps': 73200, 'loss/train': 0.8712138533592224} 08/31/2021 02:23:25 - INFO - __main__ - Step 73202: {'lr': 0.0002648448399666202, 'samples': 14054784, 'steps': 73201, 'loss/train': 1.2812037467956543} 08/31/2021 02:23:26 - INFO - __main__ - Step 73203: {'lr': 0.00026483954258273737, 'samples': 14054976, 'steps': 73202, 'loss/train': 1.1658910512924194} 08/31/2021 02:23:26 - INFO - __main__ - Step 73204: {'lr': 0.00026483424519216803, 'samples': 14055168, 'steps': 73203, 'loss/train': 1.2504795789718628} 08/31/2021 02:23:27 - INFO - __main__ - Step 73205: {'lr': 0.00026482894779491465, 'samples': 14055360, 'steps': 73204, 'loss/train': 0.9223400354385376} 08/31/2021 02:23:27 - INFO - __main__ - Step 73206: {'lr': 0.0002648236503909795, 'samples': 14055552, 'steps': 73205, 'loss/train': 1.377537488937378} 08/31/2021 02:23:29 - INFO - __main__ - Step 73207: {'lr': 0.00026481835298036504, 'samples': 14055744, 'steps': 73206, 'loss/train': 1.1200778484344482} 08/31/2021 02:23:29 - INFO - __main__ - Step 73208: {'lr': 0.00026481305556307376, 'samples': 14055936, 'steps': 73207, 'loss/train': 1.4326722621917725} 08/31/2021 02:23:29 - INFO - __main__ - Step 73209: {'lr': 0.0002648077581391079, 'samples': 14056128, 'steps': 73208, 'loss/train': 0.909936785697937} 08/31/2021 02:23:30 - INFO - __main__ - Step 73210: {'lr': 0.00026480246070846987, 'samples': 14056320, 'steps': 73209, 'loss/train': 0.03791166469454765} 08/31/2021 02:23:30 - INFO - __main__ - Step 73211: {'lr': 0.00026479716327116204, 'samples': 14056512, 'steps': 73210, 'loss/train': 1.0220212936401367} 08/31/2021 02:23:32 - INFO - __main__ - Step 73212: {'lr': 0.0002647918658271869, 'samples': 14056704, 'steps': 73211, 'loss/train': 1.4745094776153564} 08/31/2021 02:23:32 - INFO - __main__ - Step 73213: {'lr': 0.00026478656837654676, 'samples': 14056896, 'steps': 73212, 'loss/train': 0.8579018115997314} 08/31/2021 02:23:32 - INFO - __main__ - Step 73214: {'lr': 0.00026478127091924403, 'samples': 14057088, 'steps': 73213, 'loss/train': 1.0864070653915405} 08/31/2021 02:23:33 - INFO - __main__ - Step 73215: {'lr': 0.0002647759734552811, 'samples': 14057280, 'steps': 73214, 'loss/train': 1.362866759300232} 08/31/2021 02:23:33 - INFO - __main__ - Step 73216: {'lr': 0.00026477067598466034, 'samples': 14057472, 'steps': 73215, 'loss/train': 1.0031142234802246} 08/31/2021 02:23:35 - INFO - __main__ - Step 73217: {'lr': 0.0002647653785073841, 'samples': 14057664, 'steps': 73216, 'loss/train': 0.9887429475784302} 08/31/2021 02:23:36 - INFO - __main__ - Step 73218: {'lr': 0.0002647600810234548, 'samples': 14057856, 'steps': 73217, 'loss/train': 0.8024775981903076} 08/31/2021 02:23:36 - INFO - __main__ - Step 73219: {'lr': 0.0002647547835328749, 'samples': 14058048, 'steps': 73218, 'loss/train': 0.7827826738357544} 08/31/2021 02:23:36 - INFO - __main__ - Step 73220: {'lr': 0.0002647494860356467, 'samples': 14058240, 'steps': 73219, 'loss/train': 0.22210781276226044} 08/31/2021 02:23:37 - INFO - __main__ - Step 73221: {'lr': 0.0002647441885317726, 'samples': 14058432, 'steps': 73220, 'loss/train': 1.44319486618042} 08/31/2021 02:23:37 - INFO - __main__ - Step 73222: {'lr': 0.000264738891021255, 'samples': 14058624, 'steps': 73221, 'loss/train': 1.2846037149429321} 08/31/2021 02:23:39 - INFO - __main__ - Step 73223: {'lr': 0.00026473359350409625, 'samples': 14058816, 'steps': 73222, 'loss/train': 1.3532112836837769} 08/31/2021 02:23:39 - INFO - __main__ - Step 73224: {'lr': 0.0002647282959802988, 'samples': 14059008, 'steps': 73223, 'loss/train': 1.599331259727478} 08/31/2021 02:23:39 - INFO - __main__ - Step 73225: {'lr': 0.00026472299844986505, 'samples': 14059200, 'steps': 73224, 'loss/train': 1.1512500047683716} 08/31/2021 02:23:40 - INFO - __main__ - Step 73226: {'lr': 0.00026471770091279724, 'samples': 14059392, 'steps': 73225, 'loss/train': 1.9713343381881714} 08/31/2021 02:23:40 - INFO - __main__ - Step 73227: {'lr': 0.0002647124033690979, 'samples': 14059584, 'steps': 73226, 'loss/train': 1.278969645500183} 08/31/2021 02:23:42 - INFO - __main__ - Step 73228: {'lr': 0.00026470710581876937, 'samples': 14059776, 'steps': 73227, 'loss/train': 0.8238174319267273} 08/31/2021 02:23:42 - INFO - __main__ - Step 73229: {'lr': 0.0002647018082618142, 'samples': 14059968, 'steps': 73228, 'loss/train': 0.8561329245567322} 08/31/2021 02:23:43 - INFO - __main__ - Step 73230: {'lr': 0.0002646965106982345, 'samples': 14060160, 'steps': 73229, 'loss/train': 0.09290239214897156} 08/31/2021 02:23:43 - INFO - __main__ - Step 73231: {'lr': 0.00026469121312803275, 'samples': 14060352, 'steps': 73230, 'loss/train': 0.029803646728396416} 08/31/2021 02:23:43 - INFO - __main__ - Step 73232: {'lr': 0.00026468591555121136, 'samples': 14060544, 'steps': 73231, 'loss/train': 0.473631888628006} 08/31/2021 02:23:44 - INFO - __main__ - Step 73233: {'lr': 0.00026468061796777276, 'samples': 14060736, 'steps': 73232, 'loss/train': 1.5473536252975464} 08/31/2021 02:23:45 - INFO - __main__ - Step 73234: {'lr': 0.0002646753203777192, 'samples': 14060928, 'steps': 73233, 'loss/train': 0.32497841119766235} 08/31/2021 02:23:46 - INFO - __main__ - Step 73235: {'lr': 0.0002646700227810534, 'samples': 14061120, 'steps': 73234, 'loss/train': 1.0305366516113281} 08/31/2021 02:23:46 - INFO - __main__ - Step 73236: {'lr': 0.0002646647251777773, 'samples': 14061312, 'steps': 73235, 'loss/train': 0.9344678521156311} 08/31/2021 02:23:46 - INFO - __main__ - Step 73237: {'lr': 0.0002646594275678936, 'samples': 14061504, 'steps': 73236, 'loss/train': 1.7021180391311646} 08/31/2021 02:23:47 - INFO - __main__ - Step 73238: {'lr': 0.0002646541299514046, 'samples': 14061696, 'steps': 73237, 'loss/train': 1.1991691589355469} 08/31/2021 02:23:48 - INFO - __main__ - Step 73239: {'lr': 0.0002646488323283126, 'samples': 14061888, 'steps': 73238, 'loss/train': 1.3267229795455933} 08/31/2021 02:23:49 - INFO - __main__ - Step 73240: {'lr': 0.0002646435346986201, 'samples': 14062080, 'steps': 73239, 'loss/train': 1.9971455335617065} 08/31/2021 02:23:49 - INFO - __main__ - Step 73241: {'lr': 0.0002646382370623295, 'samples': 14062272, 'steps': 73240, 'loss/train': 0.04428431764245033} 08/31/2021 02:23:50 - INFO - __main__ - Step 73242: {'lr': 0.00026463293941944306, 'samples': 14062464, 'steps': 73241, 'loss/train': 1.4025952816009521} 08/31/2021 02:23:50 - INFO - __main__ - Step 73243: {'lr': 0.0002646276417699633, 'samples': 14062656, 'steps': 73242, 'loss/train': 1.2470293045043945} 08/31/2021 02:23:50 - INFO - __main__ - Step 73244: {'lr': 0.00026462234411389244, 'samples': 14062848, 'steps': 73243, 'loss/train': 1.390744924545288} 08/31/2021 02:23:52 - INFO - __main__ - Step 73245: {'lr': 0.0002646170464512331, 'samples': 14063040, 'steps': 73244, 'loss/train': 1.27907133102417} 08/31/2021 02:23:53 - INFO - __main__ - Step 73246: {'lr': 0.0002646117487819875, 'samples': 14063232, 'steps': 73245, 'loss/train': 1.375020146369934} 08/31/2021 02:23:53 - INFO - __main__ - Step 73247: {'lr': 0.0002646064511061581, 'samples': 14063424, 'steps': 73246, 'loss/train': 1.3245381116867065} 08/31/2021 02:23:53 - INFO - __main__ - Step 73248: {'lr': 0.00026460115342374723, 'samples': 14063616, 'steps': 73247, 'loss/train': 1.0786559581756592} 08/31/2021 02:23:54 - INFO - __main__ - Step 73249: {'lr': 0.0002645958557347573, 'samples': 14063808, 'steps': 73248, 'loss/train': 0.10681106895208359} 08/31/2021 02:23:55 - INFO - __main__ - Step 73250: {'lr': 0.00026459055803919074, 'samples': 14064000, 'steps': 73249, 'loss/train': 1.2306303977966309} 08/31/2021 02:23:56 - INFO - __main__ - Step 73251: {'lr': 0.00026458526033704984, 'samples': 14064192, 'steps': 73250, 'loss/train': 1.5276073217391968} 08/31/2021 02:23:56 - INFO - __main__ - Step 73252: {'lr': 0.0002645799626283371, 'samples': 14064384, 'steps': 73251, 'loss/train': 1.2185710668563843} 08/31/2021 02:23:56 - INFO - __main__ - Step 73253: {'lr': 0.00026457466491305485, 'samples': 14064576, 'steps': 73252, 'loss/train': 1.5884020328521729} 08/31/2021 02:23:57 - INFO - __main__ - Step 73254: {'lr': 0.00026456936719120543, 'samples': 14064768, 'steps': 73253, 'loss/train': 1.6288573741912842} 08/31/2021 02:23:58 - INFO - __main__ - Step 73255: {'lr': 0.0002645640694627913, 'samples': 14064960, 'steps': 73254, 'loss/train': 1.3765184879302979} 08/31/2021 02:23:59 - INFO - __main__ - Step 73256: {'lr': 0.0002645587717278148, 'samples': 14065152, 'steps': 73255, 'loss/train': 1.6053593158721924} 08/31/2021 02:23:59 - INFO - __main__ - Step 73257: {'lr': 0.00026455347398627845, 'samples': 14065344, 'steps': 73256, 'loss/train': 1.2271672487258911} 08/31/2021 02:23:59 - INFO - __main__ - Step 73258: {'lr': 0.0002645481762381845, 'samples': 14065536, 'steps': 73257, 'loss/train': 0.5368940830230713} 08/31/2021 02:24:00 - INFO - __main__ - Step 73259: {'lr': 0.0002645428784835353, 'samples': 14065728, 'steps': 73258, 'loss/train': 1.282732605934143} 08/31/2021 02:24:01 - INFO - __main__ - Step 73260: {'lr': 0.0002645375807223333, 'samples': 14065920, 'steps': 73259, 'loss/train': 1.8421562910079956} 08/31/2021 02:24:02 - INFO - __main__ - Step 73261: {'lr': 0.00026453228295458093, 'samples': 14066112, 'steps': 73260, 'loss/train': 0.05133262649178505} 08/31/2021 02:24:02 - INFO - __main__ - Step 73262: {'lr': 0.0002645269851802805, 'samples': 14066304, 'steps': 73261, 'loss/train': 1.0901168584823608} 08/31/2021 02:24:03 - INFO - __main__ - Step 73263: {'lr': 0.0002645216873994345, 'samples': 14066496, 'steps': 73262, 'loss/train': 1.424126148223877} 08/31/2021 02:24:03 - INFO - __main__ - Step 73264: {'lr': 0.0002645163896120452, 'samples': 14066688, 'steps': 73263, 'loss/train': 1.4914157390594482} 08/31/2021 02:24:04 - INFO - __main__ - Step 73265: {'lr': 0.00026451109181811506, 'samples': 14066880, 'steps': 73264, 'loss/train': 0.9530246257781982} 08/31/2021 02:24:05 - INFO - __main__ - Step 73266: {'lr': 0.0002645057940176464, 'samples': 14067072, 'steps': 73265, 'loss/train': 1.076644778251648} 08/31/2021 02:24:05 - INFO - __main__ - Step 73267: {'lr': 0.00026450049621064173, 'samples': 14067264, 'steps': 73266, 'loss/train': 1.3117979764938354} 08/31/2021 02:24:06 - INFO - __main__ - Step 73268: {'lr': 0.0002644951983971033, 'samples': 14067456, 'steps': 73267, 'loss/train': 1.455521583557129} 08/31/2021 02:24:06 - INFO - __main__ - Step 73269: {'lr': 0.0002644899005770336, 'samples': 14067648, 'steps': 73268, 'loss/train': 0.8408186435699463} 08/31/2021 02:24:07 - INFO - __main__ - Step 73270: {'lr': 0.00026448460275043496, 'samples': 14067840, 'steps': 73269, 'loss/train': 0.8994410037994385} 08/31/2021 02:24:08 - INFO - __main__ - Step 73271: {'lr': 0.00026447930491730974, 'samples': 14068032, 'steps': 73270, 'loss/train': 0.9202208518981934} 08/31/2021 02:24:08 - INFO - __main__ - Step 73272: {'lr': 0.0002644740070776604, 'samples': 14068224, 'steps': 73271, 'loss/train': 1.7299647331237793} 08/31/2021 02:24:09 - INFO - __main__ - Step 73273: {'lr': 0.0002644687092314893, 'samples': 14068416, 'steps': 73272, 'loss/train': 2.329860210418701} 08/31/2021 02:24:09 - INFO - __main__ - Step 73274: {'lr': 0.0002644634113787988, 'samples': 14068608, 'steps': 73273, 'loss/train': 1.0601245164871216} 08/31/2021 02:24:09 - INFO - __main__ - Step 73275: {'lr': 0.0002644581135195913, 'samples': 14068800, 'steps': 73274, 'loss/train': 0.9185693860054016} 08/31/2021 02:24:11 - INFO - __main__ - Step 73276: {'lr': 0.0002644528156538693, 'samples': 14068992, 'steps': 73275, 'loss/train': 0.6965778470039368} 08/31/2021 02:24:12 - INFO - __main__ - Step 73277: {'lr': 0.000264447517781635, 'samples': 14069184, 'steps': 73276, 'loss/train': 0.9787795543670654} 08/31/2021 02:24:12 - INFO - __main__ - Step 73278: {'lr': 0.00026444221990289086, 'samples': 14069376, 'steps': 73277, 'loss/train': 1.7070099115371704} 08/31/2021 02:24:12 - INFO - __main__ - Step 73279: {'lr': 0.0002644369220176393, 'samples': 14069568, 'steps': 73278, 'loss/train': 1.251724123954773} 08/31/2021 02:24:13 - INFO - __main__ - Step 73280: {'lr': 0.0002644316241258827, 'samples': 14069760, 'steps': 73279, 'loss/train': 1.10393488407135} 08/31/2021 02:24:14 - INFO - __main__ - Step 73281: {'lr': 0.0002644263262276234, 'samples': 14069952, 'steps': 73280, 'loss/train': 1.1284202337265015} 08/31/2021 02:24:15 - INFO - __main__ - Step 73282: {'lr': 0.0002644210283228639, 'samples': 14070144, 'steps': 73281, 'loss/train': 1.692011833190918} 08/31/2021 02:24:15 - INFO - __main__ - Step 73283: {'lr': 0.0002644157304116064, 'samples': 14070336, 'steps': 73282, 'loss/train': 1.9592326879501343} 08/31/2021 02:24:15 - INFO - __main__ - Step 73284: {'lr': 0.0002644104324938534, 'samples': 14070528, 'steps': 73283, 'loss/train': 1.3172950744628906} 08/31/2021 02:24:16 - INFO - __main__ - Step 73285: {'lr': 0.00026440513456960736, 'samples': 14070720, 'steps': 73284, 'loss/train': 1.6673959493637085} 08/31/2021 02:24:17 - INFO - __main__ - Step 73286: {'lr': 0.00026439983663887056, 'samples': 14070912, 'steps': 73285, 'loss/train': 1.2677229642868042} 08/31/2021 02:24:18 - INFO - __main__ - Step 73287: {'lr': 0.0002643945387016454, 'samples': 14071104, 'steps': 73286, 'loss/train': 1.299888014793396} 08/31/2021 02:24:18 - INFO - __main__ - Step 73288: {'lr': 0.0002643892407579343, 'samples': 14071296, 'steps': 73287, 'loss/train': 1.107555866241455} 08/31/2021 02:24:18 - INFO - __main__ - Step 73289: {'lr': 0.00026438394280773963, 'samples': 14071488, 'steps': 73288, 'loss/train': 1.3467990159988403} 08/31/2021 02:24:19 - INFO - __main__ - Step 73290: {'lr': 0.0002643786448510638, 'samples': 14071680, 'steps': 73289, 'loss/train': 1.0875306129455566} 08/31/2021 02:24:20 - INFO - __main__ - Step 73291: {'lr': 0.0002643733468879091, 'samples': 14071872, 'steps': 73290, 'loss/train': 0.0389912985265255} 08/31/2021 02:24:21 - INFO - __main__ - Step 73292: {'lr': 0.000264368048918278, 'samples': 14072064, 'steps': 73291, 'loss/train': 1.40816330909729} 08/31/2021 02:24:21 - INFO - __main__ - Step 73293: {'lr': 0.00026436275094217295, 'samples': 14072256, 'steps': 73292, 'loss/train': 0.178851917386055} 08/31/2021 02:24:21 - INFO - __main__ - Step 73294: {'lr': 0.0002643574529595962, 'samples': 14072448, 'steps': 73293, 'loss/train': 0.9631555080413818} 08/31/2021 02:24:22 - INFO - __main__ - Step 73295: {'lr': 0.0002643521549705502, 'samples': 14072640, 'steps': 73294, 'loss/train': 0.556743323802948} 08/31/2021 02:24:23 - INFO - __main__ - Step 73296: {'lr': 0.0002643468569750375, 'samples': 14072832, 'steps': 73295, 'loss/train': 0.7212334275245667} 08/31/2021 02:24:24 - INFO - __main__ - Step 73297: {'lr': 0.0002643415589730602, 'samples': 14073024, 'steps': 73296, 'loss/train': 3.4481654167175293} 08/31/2021 02:24:24 - INFO - __main__ - Step 73298: {'lr': 0.0002643362609646208, 'samples': 14073216, 'steps': 73297, 'loss/train': 0.5133734941482544} 08/31/2021 02:24:24 - INFO - __main__ - Step 73299: {'lr': 0.00026433096294972166, 'samples': 14073408, 'steps': 73298, 'loss/train': 1.8308025598526} 08/31/2021 02:24:25 - INFO - __main__ - Step 73300: {'lr': 0.00026432566492836523, 'samples': 14073600, 'steps': 73299, 'loss/train': 1.629417896270752} 08/31/2021 02:24:26 - INFO - __main__ - Step 73301: {'lr': 0.00026432036690055396, 'samples': 14073792, 'steps': 73300, 'loss/train': 1.7021222114562988} 08/31/2021 02:24:27 - INFO - __main__ - Step 73302: {'lr': 0.00026431506886629016, 'samples': 14073984, 'steps': 73301, 'loss/train': 1.3780876398086548} 08/31/2021 02:24:27 - INFO - __main__ - Step 73303: {'lr': 0.0002643097708255761, 'samples': 14074176, 'steps': 73302, 'loss/train': 1.1002068519592285} 08/31/2021 02:24:27 - INFO - __main__ - Step 73304: {'lr': 0.00026430447277841433, 'samples': 14074368, 'steps': 73303, 'loss/train': 1.1068761348724365} 08/31/2021 02:24:28 - INFO - __main__ - Step 73305: {'lr': 0.00026429917472480717, 'samples': 14074560, 'steps': 73304, 'loss/train': 1.143089771270752} 08/31/2021 02:24:29 - INFO - __main__ - Step 73306: {'lr': 0.0002642938766647571, 'samples': 14074752, 'steps': 73305, 'loss/train': 0.8216519951820374} 08/31/2021 02:24:30 - INFO - __main__ - Step 73307: {'lr': 0.0002642885785982663, 'samples': 14074944, 'steps': 73306, 'loss/train': 1.392944097518921} 08/31/2021 02:24:30 - INFO - __main__ - Step 73308: {'lr': 0.0002642832805253374, 'samples': 14075136, 'steps': 73307, 'loss/train': 1.2048336267471313} 08/31/2021 02:24:30 - INFO - __main__ - Step 73309: {'lr': 0.00026427798244597266, 'samples': 14075328, 'steps': 73308, 'loss/train': 0.9713424444198608} 08/31/2021 02:24:31 - INFO - __main__ - Step 73310: {'lr': 0.00026427268436017445, 'samples': 14075520, 'steps': 73309, 'loss/train': 1.4601454734802246} 08/31/2021 02:24:31 - INFO - __main__ - Step 73311: {'lr': 0.00026426738626794514, 'samples': 14075712, 'steps': 73310, 'loss/train': 1.170870065689087} 08/31/2021 02:24:33 - INFO - __main__ - Step 73312: {'lr': 0.00026426208816928727, 'samples': 14075904, 'steps': 73311, 'loss/train': 0.5816428065299988} 08/31/2021 02:24:34 - INFO - __main__ - Step 73313: {'lr': 0.00026425679006420306, 'samples': 14076096, 'steps': 73312, 'loss/train': 1.468279242515564} 08/31/2021 02:24:34 - INFO - __main__ - Step 73314: {'lr': 0.00026425149195269496, 'samples': 14076288, 'steps': 73313, 'loss/train': 2.267108917236328} 08/31/2021 02:24:35 - INFO - __main__ - Step 73315: {'lr': 0.00026424619383476534, 'samples': 14076480, 'steps': 73314, 'loss/train': 1.0037941932678223} 08/31/2021 02:24:35 - INFO - __main__ - Step 73316: {'lr': 0.0002642408957104167, 'samples': 14076672, 'steps': 73315, 'loss/train': 0.9892922043800354} 08/31/2021 02:24:35 - INFO - __main__ - Step 73317: {'lr': 0.00026423559757965127, 'samples': 14076864, 'steps': 73316, 'loss/train': 0.3533060550689697} 08/31/2021 02:24:37 - INFO - __main__ - Step 73318: {'lr': 0.0002642302994424715, 'samples': 14077056, 'steps': 73317, 'loss/train': 0.34175848960876465} 08/31/2021 02:24:37 - INFO - __main__ - Step 73319: {'lr': 0.0002642250012988797, 'samples': 14077248, 'steps': 73318, 'loss/train': 1.546321988105774} 08/31/2021 02:24:38 - INFO - __main__ - Step 73320: {'lr': 0.0002642197031488784, 'samples': 14077440, 'steps': 73319, 'loss/train': 0.6363245248794556} 08/31/2021 02:24:38 - INFO - __main__ - Step 73321: {'lr': 0.00026421440499247, 'samples': 14077632, 'steps': 73320, 'loss/train': 1.1718320846557617} 08/31/2021 02:24:38 - INFO - __main__ - Step 73322: {'lr': 0.0002642091068296567, 'samples': 14077824, 'steps': 73321, 'loss/train': 1.0786099433898926} 08/31/2021 02:24:40 - INFO - __main__ - Step 73323: {'lr': 0.0002642038086604411, 'samples': 14078016, 'steps': 73322, 'loss/train': 0.854138195514679} 08/31/2021 02:24:40 - INFO - __main__ - Step 73324: {'lr': 0.00026419851048482536, 'samples': 14078208, 'steps': 73323, 'loss/train': 1.9407857656478882} 08/31/2021 02:24:41 - INFO - __main__ - Step 73325: {'lr': 0.00026419321230281207, 'samples': 14078400, 'steps': 73324, 'loss/train': 0.8876842260360718} 08/31/2021 02:24:41 - INFO - __main__ - Step 73326: {'lr': 0.0002641879141144035, 'samples': 14078592, 'steps': 73325, 'loss/train': 0.8748255968093872} 08/31/2021 02:24:41 - INFO - __main__ - Step 73327: {'lr': 0.00026418261591960206, 'samples': 14078784, 'steps': 73326, 'loss/train': 1.9097650051116943} 08/31/2021 02:24:42 - INFO - __main__ - Step 73328: {'lr': 0.0002641773177184102, 'samples': 14078976, 'steps': 73327, 'loss/train': 0.62630695104599} 08/31/2021 02:24:44 - INFO - __main__ - Step 73329: {'lr': 0.00026417201951083025, 'samples': 14079168, 'steps': 73328, 'loss/train': 0.757448136806488} 08/31/2021 02:24:45 - INFO - __main__ - Step 73330: {'lr': 0.0002641667212968646, 'samples': 14079360, 'steps': 73329, 'loss/train': 0.8940508365631104} 08/31/2021 02:24:45 - INFO - __main__ - Step 73331: {'lr': 0.0002641614230765156, 'samples': 14079552, 'steps': 73330, 'loss/train': 1.4360854625701904} 08/31/2021 02:24:45 - INFO - __main__ - Step 73332: {'lr': 0.00026415612484978577, 'samples': 14079744, 'steps': 73331, 'loss/train': 0.04165249690413475} 08/31/2021 02:24:46 - INFO - __main__ - Step 73333: {'lr': 0.00026415082661667734, 'samples': 14079936, 'steps': 73332, 'loss/train': 0.02723035030066967} 08/31/2021 02:24:46 - INFO - __main__ - Step 73334: {'lr': 0.0002641455283771928, 'samples': 14080128, 'steps': 73333, 'loss/train': 0.32836803793907166} 08/31/2021 02:24:47 - INFO - __main__ - Step 73335: {'lr': 0.00026414023013133446, 'samples': 14080320, 'steps': 73334, 'loss/train': 0.38782092928886414} 08/31/2021 02:24:48 - INFO - __main__ - Step 73336: {'lr': 0.0002641349318791048, 'samples': 14080512, 'steps': 73335, 'loss/train': 1.660362958908081} 08/31/2021 02:24:48 - INFO - __main__ - Step 73337: {'lr': 0.0002641296336205062, 'samples': 14080704, 'steps': 73336, 'loss/train': 1.134482741355896} 08/31/2021 02:24:49 - INFO - __main__ - Step 73338: {'lr': 0.00026412433535554094, 'samples': 14080896, 'steps': 73337, 'loss/train': 1.4728022813796997} 08/31/2021 02:24:49 - INFO - __main__ - Step 73339: {'lr': 0.0002641190370842114, 'samples': 14081088, 'steps': 73338, 'loss/train': 1.3022239208221436} 08/31/2021 02:24:50 - INFO - __main__ - Step 73340: {'lr': 0.0002641137388065201, 'samples': 14081280, 'steps': 73339, 'loss/train': 1.0960946083068848} 08/31/2021 02:24:51 - INFO - __main__ - Step 73341: {'lr': 0.0002641084405224694, 'samples': 14081472, 'steps': 73340, 'loss/train': 0.8196993470191956} 08/31/2021 02:24:51 - INFO - __main__ - Step 73342: {'lr': 0.0002641031422320616, 'samples': 14081664, 'steps': 73341, 'loss/train': 0.31488028168678284} 08/31/2021 02:24:52 - INFO - __main__ - Step 73343: {'lr': 0.0002640978439352993, 'samples': 14081856, 'steps': 73342, 'loss/train': 1.3167577981948853} 08/31/2021 02:24:52 - INFO - __main__ - Step 73344: {'lr': 0.00026409254563218457, 'samples': 14082048, 'steps': 73343, 'loss/train': 1.4454493522644043} 08/31/2021 02:24:53 - INFO - __main__ - Step 73345: {'lr': 0.00026408724732272, 'samples': 14082240, 'steps': 73344, 'loss/train': 1.473252773284912} 08/31/2021 02:24:54 - INFO - __main__ - Step 73346: {'lr': 0.0002640819490069079, 'samples': 14082432, 'steps': 73345, 'loss/train': 1.7128833532333374} 08/31/2021 02:24:54 - INFO - __main__ - Step 73347: {'lr': 0.00026407665068475073, 'samples': 14082624, 'steps': 73346, 'loss/train': 1.0198898315429688} 08/31/2021 02:24:55 - INFO - __main__ - Step 73348: {'lr': 0.0002640713523562508, 'samples': 14082816, 'steps': 73347, 'loss/train': 1.1278678178787231} 08/31/2021 02:24:55 - INFO - __main__ - Step 73349: {'lr': 0.00026406605402141053, 'samples': 14083008, 'steps': 73348, 'loss/train': 1.1012632846832275} 08/31/2021 02:24:56 - INFO - __main__ - Step 73350: {'lr': 0.0002640607556802324, 'samples': 14083200, 'steps': 73349, 'loss/train': 0.9500187039375305} 08/31/2021 02:24:57 - INFO - __main__ - Step 73351: {'lr': 0.0002640554573327187, 'samples': 14083392, 'steps': 73350, 'loss/train': 1.2478691339492798} 08/31/2021 02:24:57 - INFO - __main__ - Step 73352: {'lr': 0.00026405015897887173, 'samples': 14083584, 'steps': 73351, 'loss/train': 1.3886700868606567} 08/31/2021 02:24:58 - INFO - __main__ - Step 73353: {'lr': 0.00026404486061869405, 'samples': 14083776, 'steps': 73352, 'loss/train': 1.45456862449646} 08/31/2021 02:24:58 - INFO - __main__ - Step 73354: {'lr': 0.00026403956225218793, 'samples': 14083968, 'steps': 73353, 'loss/train': 1.0668904781341553} 08/31/2021 02:25:00 - INFO - __main__ - Step 73355: {'lr': 0.0002640342638793558, 'samples': 14084160, 'steps': 73354, 'loss/train': 1.3490267992019653} 08/31/2021 02:25:00 - INFO - __main__ - Step 73356: {'lr': 0.0002640289655002001, 'samples': 14084352, 'steps': 73355, 'loss/train': 1.033103108406067} 08/31/2021 02:25:00 - INFO - __main__ - Step 73357: {'lr': 0.00026402366711472317, 'samples': 14084544, 'steps': 73356, 'loss/train': 1.0786635875701904} 08/31/2021 02:25:01 - INFO - __main__ - Step 73358: {'lr': 0.00026401836872292733, 'samples': 14084736, 'steps': 73357, 'loss/train': 1.369263768196106} 08/31/2021 02:25:01 - INFO - __main__ - Step 73359: {'lr': 0.00026401307032481504, 'samples': 14084928, 'steps': 73358, 'loss/train': 1.3751288652420044} 08/31/2021 02:25:03 - INFO - __main__ - Step 73360: {'lr': 0.00026400777192038874, 'samples': 14085120, 'steps': 73359, 'loss/train': 1.3708455562591553} 08/31/2021 02:25:03 - INFO - __main__ - Step 73361: {'lr': 0.00026400247350965065, 'samples': 14085312, 'steps': 73360, 'loss/train': 1.161970615386963} 08/31/2021 02:25:03 - INFO - __main__ - Step 73362: {'lr': 0.0002639971750926033, 'samples': 14085504, 'steps': 73361, 'loss/train': 1.2283179759979248} 08/31/2021 02:25:04 - INFO - __main__ - Step 73363: {'lr': 0.0002639918766692491, 'samples': 14085696, 'steps': 73362, 'loss/train': 1.4615907669067383} 08/31/2021 02:25:04 - INFO - __main__ - Step 73364: {'lr': 0.00026398657823959034, 'samples': 14085888, 'steps': 73363, 'loss/train': 1.533347725868225} 08/31/2021 02:25:06 - INFO - __main__ - Step 73365: {'lr': 0.0002639812798036294, 'samples': 14086080, 'steps': 73364, 'loss/train': 0.3506014943122864} 08/31/2021 02:25:06 - INFO - __main__ - Step 73366: {'lr': 0.00026397598136136875, 'samples': 14086272, 'steps': 73365, 'loss/train': 1.0300663709640503} 08/31/2021 02:25:06 - INFO - __main__ - Step 73367: {'lr': 0.00026397068291281076, 'samples': 14086464, 'steps': 73366, 'loss/train': 1.4747086763381958} 08/31/2021 02:25:07 - INFO - __main__ - Step 73368: {'lr': 0.0002639653844579578, 'samples': 14086656, 'steps': 73367, 'loss/train': 0.6908305287361145} 08/31/2021 02:25:07 - INFO - __main__ - Step 73369: {'lr': 0.00026396008599681214, 'samples': 14086848, 'steps': 73368, 'loss/train': 0.19190587103366852} 08/31/2021 02:25:07 - INFO - __main__ - Step 73370: {'lr': 0.00026395478752937646, 'samples': 14087040, 'steps': 73369, 'loss/train': 1.5247046947479248} 08/31/2021 02:25:09 - INFO - __main__ - Step 73371: {'lr': 0.0002639494890556529, 'samples': 14087232, 'steps': 73370, 'loss/train': 1.0377223491668701} 08/31/2021 02:25:09 - INFO - __main__ - Step 73372: {'lr': 0.0002639441905756438, 'samples': 14087424, 'steps': 73371, 'loss/train': 1.5411795377731323} 08/31/2021 02:25:10 - INFO - __main__ - Step 73373: {'lr': 0.0002639388920893518, 'samples': 14087616, 'steps': 73372, 'loss/train': 1.497235894203186} 08/31/2021 02:25:10 - INFO - __main__ - Step 73374: {'lr': 0.00026393359359677904, 'samples': 14087808, 'steps': 73373, 'loss/train': 1.1253942251205444} 08/31/2021 02:25:10 - INFO - __main__ - Step 73375: {'lr': 0.0002639282950979281, 'samples': 14088000, 'steps': 73374, 'loss/train': 0.5167967677116394} 08/31/2021 02:25:12 - INFO - __main__ - Step 73376: {'lr': 0.0002639229965928013, 'samples': 14088192, 'steps': 73375, 'loss/train': 1.1784367561340332} 08/31/2021 02:25:12 - INFO - __main__ - Step 73377: {'lr': 0.00026391769808140097, 'samples': 14088384, 'steps': 73376, 'loss/train': 1.5552738904953003} 08/31/2021 02:25:13 - INFO - __main__ - Step 73378: {'lr': 0.00026391239956372953, 'samples': 14088576, 'steps': 73377, 'loss/train': 1.4120337963104248} 08/31/2021 02:25:13 - INFO - __main__ - Step 73379: {'lr': 0.00026390710103978946, 'samples': 14088768, 'steps': 73378, 'loss/train': 1.3735785484313965} 08/31/2021 02:25:13 - INFO - __main__ - Step 73380: {'lr': 0.00026390180250958296, 'samples': 14088960, 'steps': 73379, 'loss/train': 0.71113121509552} 08/31/2021 02:25:15 - INFO - __main__ - Step 73381: {'lr': 0.0002638965039731126, 'samples': 14089152, 'steps': 73380, 'loss/train': 1.2531903982162476} 08/31/2021 02:25:15 - INFO - __main__ - Step 73382: {'lr': 0.00026389120543038064, 'samples': 14089344, 'steps': 73381, 'loss/train': 1.2083911895751953} 08/31/2021 02:25:16 - INFO - __main__ - Step 73383: {'lr': 0.00026388590688138954, 'samples': 14089536, 'steps': 73382, 'loss/train': 1.1184022426605225} 08/31/2021 02:25:16 - INFO - __main__ - Step 73384: {'lr': 0.00026388060832614166, 'samples': 14089728, 'steps': 73383, 'loss/train': 0.7641670107841492} 08/31/2021 02:25:16 - INFO - __main__ - Step 73385: {'lr': 0.00026387530976463934, 'samples': 14089920, 'steps': 73384, 'loss/train': 0.30286070704460144} 08/31/2021 02:25:18 - INFO - __main__ - Step 73386: {'lr': 0.0002638700111968851, 'samples': 14090112, 'steps': 73385, 'loss/train': 1.4308818578720093} 08/31/2021 02:25:19 - INFO - __main__ - Step 73387: {'lr': 0.00026386471262288127, 'samples': 14090304, 'steps': 73386, 'loss/train': 1.5030591487884521} 08/31/2021 02:25:19 - INFO - __main__ - Step 73388: {'lr': 0.00026385941404263007, 'samples': 14090496, 'steps': 73387, 'loss/train': 0.7017491459846497} 08/31/2021 02:25:19 - INFO - __main__ - Step 73389: {'lr': 0.0002638541154561341, 'samples': 14090688, 'steps': 73388, 'loss/train': 0.9429415464401245} 08/31/2021 02:25:20 - INFO - __main__ - Step 73390: {'lr': 0.00026384881686339573, 'samples': 14090880, 'steps': 73389, 'loss/train': 1.5346410274505615} 08/31/2021 02:25:21 - INFO - __main__ - Step 73391: {'lr': 0.00026384351826441726, 'samples': 14091072, 'steps': 73390, 'loss/train': 1.2102346420288086} 08/31/2021 02:25:22 - INFO - __main__ - Step 73392: {'lr': 0.00026383821965920116, 'samples': 14091264, 'steps': 73391, 'loss/train': 1.19760262966156} 08/31/2021 02:25:22 - INFO - __main__ - Step 73393: {'lr': 0.00026383292104774976, 'samples': 14091456, 'steps': 73392, 'loss/train': 0.9134278297424316} 08/31/2021 02:25:22 - INFO - __main__ - Step 73394: {'lr': 0.0002638276224300654, 'samples': 14091648, 'steps': 73393, 'loss/train': 0.9118844270706177} 08/31/2021 02:25:23 - INFO - __main__ - Step 73395: {'lr': 0.00026382232380615055, 'samples': 14091840, 'steps': 73394, 'loss/train': 1.0176132917404175} 08/31/2021 02:25:24 - INFO - __main__ - Step 73396: {'lr': 0.0002638170251760076, 'samples': 14092032, 'steps': 73395, 'loss/train': 0.2012166678905487} 08/31/2021 02:25:25 - INFO - __main__ - Step 73397: {'lr': 0.00026381172653963886, 'samples': 14092224, 'steps': 73396, 'loss/train': 0.6669048070907593} 08/31/2021 02:25:25 - INFO - __main__ - Step 73398: {'lr': 0.00026380642789704684, 'samples': 14092416, 'steps': 73397, 'loss/train': 1.0505832433700562} 08/31/2021 02:25:25 - INFO - __main__ - Step 73399: {'lr': 0.0002638011292482338, 'samples': 14092608, 'steps': 73398, 'loss/train': 1.274923324584961} 08/31/2021 02:25:26 - INFO - __main__ - Step 73400: {'lr': 0.0002637958305932022, 'samples': 14092800, 'steps': 73399, 'loss/train': 1.3819936513900757} 08/31/2021 02:25:27 - INFO - __main__ - Step 73401: {'lr': 0.0002637905319319544, 'samples': 14092992, 'steps': 73400, 'loss/train': 0.7748899459838867} 08/31/2021 02:25:28 - INFO - __main__ - Step 73402: {'lr': 0.00026378523326449284, 'samples': 14093184, 'steps': 73401, 'loss/train': 1.4036107063293457} 08/31/2021 02:25:28 - INFO - __main__ - Step 73403: {'lr': 0.0002637799345908199, 'samples': 14093376, 'steps': 73402, 'loss/train': 1.1485015153884888} 08/31/2021 02:25:28 - INFO - __main__ - Step 73404: {'lr': 0.0002637746359109379, 'samples': 14093568, 'steps': 73403, 'loss/train': 1.1989911794662476} 08/31/2021 02:25:29 - INFO - __main__ - Step 73405: {'lr': 0.0002637693372248492, 'samples': 14093760, 'steps': 73404, 'loss/train': 0.8764984011650085} 08/31/2021 02:25:29 - INFO - __main__ - Step 73406: {'lr': 0.00026376403853255626, 'samples': 14093952, 'steps': 73405, 'loss/train': 1.3600032329559326} 08/31/2021 02:25:31 - INFO - __main__ - Step 73407: {'lr': 0.0002637587398340615, 'samples': 14094144, 'steps': 73406, 'loss/train': 0.5986205339431763} 08/31/2021 02:25:31 - INFO - __main__ - Step 73408: {'lr': 0.0002637534411293672, 'samples': 14094336, 'steps': 73407, 'loss/train': 1.6586226224899292} 08/31/2021 02:25:31 - INFO - __main__ - Step 73409: {'lr': 0.00026374814241847584, 'samples': 14094528, 'steps': 73408, 'loss/train': 1.2219655513763428} 08/31/2021 02:25:32 - INFO - __main__ - Step 73410: {'lr': 0.00026374284370138986, 'samples': 14094720, 'steps': 73409, 'loss/train': 1.1499155759811401} 08/31/2021 02:25:32 - INFO - __main__ - Step 73411: {'lr': 0.00026373754497811147, 'samples': 14094912, 'steps': 73410, 'loss/train': 1.2573100328445435} 08/31/2021 02:25:33 - INFO - __main__ - Step 73412: {'lr': 0.00026373224624864325, 'samples': 14095104, 'steps': 73411, 'loss/train': 1.067215085029602} 08/31/2021 02:25:34 - INFO - __main__ - Step 73413: {'lr': 0.0002637269475129874, 'samples': 14095296, 'steps': 73412, 'loss/train': 1.1540052890777588} 08/31/2021 02:25:34 - INFO - __main__ - Step 73414: {'lr': 0.0002637216487711464, 'samples': 14095488, 'steps': 73413, 'loss/train': 0.9943435788154602} 08/31/2021 02:25:35 - INFO - __main__ - Step 73415: {'lr': 0.0002637163500231227, 'samples': 14095680, 'steps': 73414, 'loss/train': 1.568928837776184} 08/31/2021 02:25:35 - INFO - __main__ - Step 73416: {'lr': 0.00026371105126891855, 'samples': 14095872, 'steps': 73415, 'loss/train': 1.2181862592697144} 08/31/2021 02:25:35 - INFO - __main__ - Step 73417: {'lr': 0.0002637057525085365, 'samples': 14096064, 'steps': 73416, 'loss/train': 1.305564284324646} 08/31/2021 02:25:37 - INFO - __main__ - Step 73418: {'lr': 0.0002637004537419788, 'samples': 14096256, 'steps': 73417, 'loss/train': 1.361501693725586} 08/31/2021 02:25:37 - INFO - __main__ - Step 73419: {'lr': 0.0002636951549692478, 'samples': 14096448, 'steps': 73418, 'loss/train': 1.267722487449646} 08/31/2021 02:25:38 - INFO - __main__ - Step 73420: {'lr': 0.0002636898561903461, 'samples': 14096640, 'steps': 73419, 'loss/train': 1.3192031383514404} 08/31/2021 02:25:38 - INFO - __main__ - Step 73421: {'lr': 0.00026368455740527594, 'samples': 14096832, 'steps': 73420, 'loss/train': 0.8027979135513306} 08/31/2021 02:25:38 - INFO - __main__ - Step 73422: {'lr': 0.0002636792586140397, 'samples': 14097024, 'steps': 73421, 'loss/train': 1.3808879852294922} 08/31/2021 02:25:40 - INFO - __main__ - Step 73423: {'lr': 0.0002636739598166398, 'samples': 14097216, 'steps': 73422, 'loss/train': 1.3915002346038818} 08/31/2021 02:25:40 - INFO - __main__ - Step 73424: {'lr': 0.0002636686610130787, 'samples': 14097408, 'steps': 73423, 'loss/train': 0.4217318594455719} 08/31/2021 02:25:41 - INFO - __main__ - Step 73425: {'lr': 0.00026366336220335864, 'samples': 14097600, 'steps': 73424, 'loss/train': 0.5031238794326782} 08/31/2021 02:25:41 - INFO - __main__ - Step 73426: {'lr': 0.00026365806338748206, 'samples': 14097792, 'steps': 73425, 'loss/train': 3.316880464553833} 08/31/2021 02:25:41 - INFO - __main__ - Step 73427: {'lr': 0.0002636527645654514, 'samples': 14097984, 'steps': 73426, 'loss/train': 1.8214441537857056} 08/31/2021 02:25:43 - INFO - __main__ - Step 73428: {'lr': 0.000263647465737269, 'samples': 14098176, 'steps': 73427, 'loss/train': 0.7303040623664856} 08/31/2021 02:25:44 - INFO - __main__ - Step 73429: {'lr': 0.00026364216690293724, 'samples': 14098368, 'steps': 73428, 'loss/train': 0.9422740936279297} 08/31/2021 02:25:44 - INFO - __main__ - Step 73430: {'lr': 0.00026363686806245865, 'samples': 14098560, 'steps': 73429, 'loss/train': 1.1376138925552368} 08/31/2021 02:25:44 - INFO - __main__ - Step 73431: {'lr': 0.00026363156921583534, 'samples': 14098752, 'steps': 73430, 'loss/train': 0.21512529253959656} 08/31/2021 02:25:45 - INFO - __main__ - Step 73432: {'lr': 0.00026362627036306997, 'samples': 14098944, 'steps': 73431, 'loss/train': 1.0126888751983643} 08/31/2021 02:25:47 - INFO - __main__ - Step 73433: {'lr': 0.00026362097150416477, 'samples': 14099136, 'steps': 73432, 'loss/train': 1.642899513244629} 08/31/2021 02:25:47 - INFO - __main__ - Step 73434: {'lr': 0.0002636156726391221, 'samples': 14099328, 'steps': 73433, 'loss/train': 1.3691391944885254} 08/31/2021 02:25:47 - INFO - __main__ - Step 73435: {'lr': 0.0002636103737679445, 'samples': 14099520, 'steps': 73434, 'loss/train': 1.5518875122070312} 08/31/2021 02:25:48 - INFO - __main__ - Step 73436: {'lr': 0.0002636050748906343, 'samples': 14099712, 'steps': 73435, 'loss/train': 0.31569337844848633} 08/31/2021 02:25:48 - INFO - __main__ - Step 73437: {'lr': 0.0002635997760071939, 'samples': 14099904, 'steps': 73436, 'loss/train': 0.5351471900939941} 08/31/2021 02:25:50 - INFO - __main__ - Step 73438: {'lr': 0.00026359447711762554, 'samples': 14100096, 'steps': 73437, 'loss/train': 0.3128379285335541} 08/31/2021 02:25:50 - INFO - __main__ - Step 73439: {'lr': 0.00026358917822193173, 'samples': 14100288, 'steps': 73438, 'loss/train': 1.9205846786499023} 08/31/2021 02:25:50 - INFO - __main__ - Step 73440: {'lr': 0.00026358387932011484, 'samples': 14100480, 'steps': 73439, 'loss/train': 1.2926678657531738} 08/31/2021 02:25:51 - INFO - __main__ - Step 73441: {'lr': 0.0002635785804121773, 'samples': 14100672, 'steps': 73440, 'loss/train': 0.44003593921661377} 08/31/2021 02:25:51 - INFO - __main__ - Step 73442: {'lr': 0.00026357328149812144, 'samples': 14100864, 'steps': 73441, 'loss/train': 1.2816749811172485} 08/31/2021 02:25:53 - INFO - __main__ - Step 73443: {'lr': 0.00026356798257794965, 'samples': 14101056, 'steps': 73442, 'loss/train': 0.4003889262676239} 08/31/2021 02:25:53 - INFO - __main__ - Step 73444: {'lr': 0.0002635626836516645, 'samples': 14101248, 'steps': 73443, 'loss/train': 1.4494496583938599} 08/31/2021 02:25:53 - INFO - __main__ - Step 73445: {'lr': 0.00026355738471926804, 'samples': 14101440, 'steps': 73444, 'loss/train': 1.0190227031707764} 08/31/2021 02:25:54 - INFO - __main__ - Step 73446: {'lr': 0.0002635520857807629, 'samples': 14101632, 'steps': 73445, 'loss/train': 1.1231260299682617} 08/31/2021 02:25:54 - INFO - __main__ - Step 73447: {'lr': 0.00026354678683615133, 'samples': 14101824, 'steps': 73446, 'loss/train': 0.2719864845275879} 08/31/2021 02:25:54 - INFO - __main__ - Step 73448: {'lr': 0.0002635414878854359, 'samples': 14102016, 'steps': 73447, 'loss/train': 0.8794539570808411} 08/31/2021 02:25:56 - INFO - __main__ - Step 73449: {'lr': 0.00026353618892861877, 'samples': 14102208, 'steps': 73448, 'loss/train': 1.2205009460449219} 08/31/2021 02:25:56 - INFO - __main__ - Step 73450: {'lr': 0.0002635308899657025, 'samples': 14102400, 'steps': 73449, 'loss/train': 0.6610302329063416} 08/31/2021 02:25:57 - INFO - __main__ - Step 73451: {'lr': 0.00026352559099668943, 'samples': 14102592, 'steps': 73450, 'loss/train': 1.5913612842559814} 08/31/2021 02:25:57 - INFO - __main__ - Step 73452: {'lr': 0.0002635202920215819, 'samples': 14102784, 'steps': 73451, 'loss/train': 0.44389837980270386} 08/31/2021 02:25:57 - INFO - __main__ - Step 73453: {'lr': 0.00026351499304038236, 'samples': 14102976, 'steps': 73452, 'loss/train': 1.1372498273849487} 08/31/2021 02:25:59 - INFO - __main__ - Step 73454: {'lr': 0.00026350969405309314, 'samples': 14103168, 'steps': 73453, 'loss/train': 1.8064391613006592} 08/31/2021 02:26:00 - INFO - __main__ - Step 73455: {'lr': 0.0002635043950597167, 'samples': 14103360, 'steps': 73454, 'loss/train': 0.919752836227417} 08/31/2021 02:26:00 - INFO - __main__ - Step 73456: {'lr': 0.00026349909606025534, 'samples': 14103552, 'steps': 73455, 'loss/train': 1.2665629386901855} 08/31/2021 02:26:01 - INFO - __main__ - Step 73457: {'lr': 0.00026349379705471157, 'samples': 14103744, 'steps': 73456, 'loss/train': 1.4908881187438965} 08/31/2021 02:26:01 - INFO - __main__ - Step 73458: {'lr': 0.00026348849804308766, 'samples': 14103936, 'steps': 73457, 'loss/train': 0.7464187145233154} 08/31/2021 02:26:02 - INFO - __main__ - Step 73459: {'lr': 0.000263483199025386, 'samples': 14104128, 'steps': 73458, 'loss/train': 1.7496116161346436} 08/31/2021 02:26:03 - INFO - __main__ - Step 73460: {'lr': 0.00026347790000160907, 'samples': 14104320, 'steps': 73459, 'loss/train': 1.5235003232955933} 08/31/2021 02:26:03 - INFO - __main__ - Step 73461: {'lr': 0.00026347260097175923, 'samples': 14104512, 'steps': 73460, 'loss/train': 0.353551983833313} 08/31/2021 02:26:03 - INFO - __main__ - Step 73462: {'lr': 0.0002634673019358388, 'samples': 14104704, 'steps': 73461, 'loss/train': 1.755239486694336} 08/31/2021 02:26:04 - INFO - __main__ - Step 73463: {'lr': 0.0002634620028938502, 'samples': 14104896, 'steps': 73462, 'loss/train': 1.611023187637329} 08/31/2021 02:26:05 - INFO - __main__ - Step 73464: {'lr': 0.0002634567038457959, 'samples': 14105088, 'steps': 73463, 'loss/train': 1.4054266214370728} 08/31/2021 02:26:06 - INFO - __main__ - Step 73465: {'lr': 0.0002634514047916782, 'samples': 14105280, 'steps': 73464, 'loss/train': 0.4619384706020355} 08/31/2021 02:26:06 - INFO - __main__ - Step 73466: {'lr': 0.00026344610573149943, 'samples': 14105472, 'steps': 73465, 'loss/train': 1.4911084175109863} 08/31/2021 02:26:06 - INFO - __main__ - Step 73467: {'lr': 0.0002634408066652621, 'samples': 14105664, 'steps': 73466, 'loss/train': 0.7755881547927856} 08/31/2021 02:26:07 - INFO - __main__ - Step 73468: {'lr': 0.00026343550759296854, 'samples': 14105856, 'steps': 73467, 'loss/train': 1.6736187934875488} 08/31/2021 02:26:09 - INFO - __main__ - Step 73469: {'lr': 0.00026343020851462114, 'samples': 14106048, 'steps': 73468, 'loss/train': 1.1565442085266113} 08/31/2021 02:26:09 - INFO - __main__ - Step 73470: {'lr': 0.00026342490943022227, 'samples': 14106240, 'steps': 73469, 'loss/train': 0.4080396890640259} 08/31/2021 02:26:09 - INFO - __main__ - Step 73471: {'lr': 0.00026341961033977447, 'samples': 14106432, 'steps': 73470, 'loss/train': 1.0482758283615112} 08/31/2021 02:26:10 - INFO - __main__ - Step 73472: {'lr': 0.00026341431124327986, 'samples': 14106624, 'steps': 73471, 'loss/train': 1.5583854913711548} 08/31/2021 02:26:10 - INFO - __main__ - Step 73473: {'lr': 0.00026340901214074103, 'samples': 14106816, 'steps': 73472, 'loss/train': 1.3318493366241455} 08/31/2021 02:26:10 - INFO - __main__ - Step 73474: {'lr': 0.00026340371303216033, 'samples': 14107008, 'steps': 73473, 'loss/train': 1.374106764793396} 08/31/2021 02:26:12 - INFO - __main__ - Step 73475: {'lr': 0.00026339841391754003, 'samples': 14107200, 'steps': 73474, 'loss/train': 0.6536082625389099} 08/31/2021 02:26:12 - INFO - __main__ - Step 73476: {'lr': 0.00026339311479688267, 'samples': 14107392, 'steps': 73475, 'loss/train': 1.49380624294281} 08/31/2021 02:26:13 - INFO - __main__ - Step 73477: {'lr': 0.00026338781567019064, 'samples': 14107584, 'steps': 73476, 'loss/train': 1.3597519397735596} 08/31/2021 02:26:13 - INFO - __main__ - Step 73478: {'lr': 0.0002633825165374662, 'samples': 14107776, 'steps': 73477, 'loss/train': 1.3322688341140747} 08/31/2021 02:26:13 - INFO - __main__ - Step 73479: {'lr': 0.0002633772173987118, 'samples': 14107968, 'steps': 73478, 'loss/train': 1.3566901683807373} 08/31/2021 02:26:15 - INFO - __main__ - Step 73480: {'lr': 0.00026337191825392985, 'samples': 14108160, 'steps': 73479, 'loss/train': 0.995567262172699} 08/31/2021 02:26:15 - INFO - __main__ - Step 73481: {'lr': 0.00026336661910312273, 'samples': 14108352, 'steps': 73480, 'loss/train': 1.276207685470581} 08/31/2021 02:26:16 - INFO - __main__ - Step 73482: {'lr': 0.00026336131994629275, 'samples': 14108544, 'steps': 73481, 'loss/train': 1.6013933420181274} 08/31/2021 02:26:16 - INFO - __main__ - Step 73483: {'lr': 0.0002633560207834425, 'samples': 14108736, 'steps': 73482, 'loss/train': 1.4392961263656616} 08/31/2021 02:26:17 - INFO - __main__ - Step 73484: {'lr': 0.0002633507216145741, 'samples': 14108928, 'steps': 73483, 'loss/train': 1.3724370002746582} 08/31/2021 02:26:19 - INFO - __main__ - Step 73485: {'lr': 0.0002633454224396901, 'samples': 14109120, 'steps': 73484, 'loss/train': 1.6147741079330444} 08/31/2021 02:26:19 - INFO - __main__ - Step 73486: {'lr': 0.0002633401232587929, 'samples': 14109312, 'steps': 73485, 'loss/train': 0.5101938247680664} 08/31/2021 02:26:19 - INFO - __main__ - Step 73487: {'lr': 0.0002633348240718848, 'samples': 14109504, 'steps': 73486, 'loss/train': 1.780120849609375} 08/31/2021 02:26:20 - INFO - __main__ - Step 73488: {'lr': 0.0002633295248789683, 'samples': 14109696, 'steps': 73487, 'loss/train': 1.9691569805145264} 08/31/2021 02:26:20 - INFO - __main__ - Step 73489: {'lr': 0.00026332422568004567, 'samples': 14109888, 'steps': 73488, 'loss/train': 1.31107497215271} 08/31/2021 02:26:22 - INFO - __main__ - Step 73490: {'lr': 0.00026331892647511935, 'samples': 14110080, 'steps': 73489, 'loss/train': 0.6688054800033569} 08/31/2021 02:26:22 - INFO - __main__ - Step 73491: {'lr': 0.0002633136272641918, 'samples': 14110272, 'steps': 73490, 'loss/train': 0.8630155324935913} 08/31/2021 02:26:23 - INFO - __main__ - Step 73492: {'lr': 0.0002633083280472652, 'samples': 14110464, 'steps': 73491, 'loss/train': 1.1947380304336548} 08/31/2021 02:26:23 - INFO - __main__ - Step 73493: {'lr': 0.0002633030288243422, 'samples': 14110656, 'steps': 73492, 'loss/train': 1.3690658807754517} 08/31/2021 02:26:23 - INFO - __main__ - Step 73494: {'lr': 0.000263297729595425, 'samples': 14110848, 'steps': 73493, 'loss/train': 1.1099666357040405} 08/31/2021 02:26:25 - INFO - __main__ - Step 73495: {'lr': 0.00026329243036051604, 'samples': 14111040, 'steps': 73494, 'loss/train': 1.3083430528640747} 08/31/2021 02:26:25 - INFO - __main__ - Step 73496: {'lr': 0.00026328713111961773, 'samples': 14111232, 'steps': 73495, 'loss/train': 1.360857605934143} 08/31/2021 02:26:26 - INFO - __main__ - Step 73497: {'lr': 0.00026328183187273246, 'samples': 14111424, 'steps': 73496, 'loss/train': 1.633591651916504} 08/31/2021 02:26:26 - INFO - __main__ - Step 73498: {'lr': 0.0002632765326198626, 'samples': 14111616, 'steps': 73497, 'loss/train': 0.41256070137023926} 08/31/2021 02:26:26 - INFO - __main__ - Step 73499: {'lr': 0.0002632712333610105, 'samples': 14111808, 'steps': 73498, 'loss/train': 1.644883394241333} 08/31/2021 02:26:27 - INFO - __main__ - Step 73500: {'lr': 0.0002632659340961786, 'samples': 14112000, 'steps': 73499, 'loss/train': 2.3035824298858643} 08/31/2021 02:26:28 - INFO - __main__ - Step 73501: {'lr': 0.0002632606348253693, 'samples': 14112192, 'steps': 73500, 'loss/train': 1.3000130653381348} 08/31/2021 02:26:29 - INFO - __main__ - Step 73502: {'lr': 0.00026325533554858496, 'samples': 14112384, 'steps': 73501, 'loss/train': 1.106302261352539} 08/31/2021 02:26:29 - INFO - __main__ - Step 73503: {'lr': 0.00026325003626582793, 'samples': 14112576, 'steps': 73502, 'loss/train': 1.1352754831314087} 08/31/2021 02:26:29 - INFO - __main__ - Step 73504: {'lr': 0.0002632447369771007, 'samples': 14112768, 'steps': 73503, 'loss/train': 1.1652313470840454} 08/31/2021 02:26:30 - INFO - __main__ - Step 73505: {'lr': 0.0002632394376824056, 'samples': 14112960, 'steps': 73504, 'loss/train': 0.8345621228218079} 08/31/2021 02:26:31 - INFO - __main__ - Step 73506: {'lr': 0.00026323413838174497, 'samples': 14113152, 'steps': 73505, 'loss/train': 1.5771461725234985} 08/31/2021 02:26:32 - INFO - __main__ - Step 73507: {'lr': 0.00026322883907512124, 'samples': 14113344, 'steps': 73506, 'loss/train': 0.7566940188407898} 08/31/2021 02:26:32 - INFO - __main__ - Step 73508: {'lr': 0.0002632235397625368, 'samples': 14113536, 'steps': 73507, 'loss/train': 1.807887315750122} 08/31/2021 02:26:32 - INFO - __main__ - Step 73509: {'lr': 0.000263218240443994, 'samples': 14113728, 'steps': 73508, 'loss/train': 1.0752559900283813} 08/31/2021 02:26:33 - INFO - __main__ - Step 73510: {'lr': 0.0002632129411194954, 'samples': 14113920, 'steps': 73509, 'loss/train': 0.7581214904785156} 08/31/2021 02:26:35 - INFO - __main__ - Step 73511: {'lr': 0.00026320764178904314, 'samples': 14114112, 'steps': 73510, 'loss/train': 1.1626895666122437} 08/31/2021 02:26:35 - INFO - __main__ - Step 73512: {'lr': 0.00026320234245263974, 'samples': 14114304, 'steps': 73511, 'loss/train': 0.10315600037574768} 08/31/2021 02:26:35 - INFO - __main__ - Step 73513: {'lr': 0.0002631970431102876, 'samples': 14114496, 'steps': 73512, 'loss/train': 1.3214677572250366} 08/31/2021 02:26:36 - INFO - __main__ - Step 73514: {'lr': 0.00026319174376198903, 'samples': 14114688, 'steps': 73513, 'loss/train': 1.3690252304077148} 08/31/2021 02:26:36 - INFO - __main__ - Step 73515: {'lr': 0.0002631864444077465, 'samples': 14114880, 'steps': 73514, 'loss/train': 1.1032052040100098} 08/31/2021 02:26:36 - INFO - __main__ - Step 73516: {'lr': 0.00026318114504756237, 'samples': 14115072, 'steps': 73515, 'loss/train': 1.3283029794692993} 08/31/2021 02:26:38 - INFO - __main__ - Step 73517: {'lr': 0.000263175845681439, 'samples': 14115264, 'steps': 73516, 'loss/train': 0.3529563844203949} 08/31/2021 02:26:39 - INFO - __main__ - Step 73518: {'lr': 0.0002631705463093788, 'samples': 14115456, 'steps': 73517, 'loss/train': 0.05112418904900551} 08/31/2021 02:26:39 - INFO - __main__ - Step 73519: {'lr': 0.00026316524693138413, 'samples': 14115648, 'steps': 73518, 'loss/train': 1.4392062425613403} 08/31/2021 02:26:39 - INFO - __main__ - Step 73520: {'lr': 0.0002631599475474574, 'samples': 14115840, 'steps': 73519, 'loss/train': 0.8213036060333252} 08/31/2021 02:26:40 - INFO - __main__ - Step 73521: {'lr': 0.00026315464815760103, 'samples': 14116032, 'steps': 73520, 'loss/train': 1.382561445236206} 08/31/2021 02:26:41 - INFO - __main__ - Step 73522: {'lr': 0.00026314934876181734, 'samples': 14116224, 'steps': 73521, 'loss/train': 1.0551763772964478} 08/31/2021 02:26:42 - INFO - __main__ - Step 73523: {'lr': 0.0002631440493601088, 'samples': 14116416, 'steps': 73522, 'loss/train': 1.2140121459960938} 08/31/2021 02:26:42 - INFO - __main__ - Step 73524: {'lr': 0.0002631387499524777, 'samples': 14116608, 'steps': 73523, 'loss/train': 1.0616514682769775} 08/31/2021 02:26:42 - INFO - __main__ - Step 73525: {'lr': 0.00026313345053892656, 'samples': 14116800, 'steps': 73524, 'loss/train': 0.6345576643943787} 08/31/2021 02:26:43 - INFO - __main__ - Step 73526: {'lr': 0.0002631281511194577, 'samples': 14116992, 'steps': 73525, 'loss/train': 0.031612884253263474} 08/31/2021 02:26:44 - INFO - __main__ - Step 73527: {'lr': 0.0002631228516940734, 'samples': 14117184, 'steps': 73526, 'loss/train': 1.2019963264465332} 08/31/2021 02:26:45 - INFO - __main__ - Step 73528: {'lr': 0.00026311755226277625, 'samples': 14117376, 'steps': 73527, 'loss/train': 1.0024129152297974} 08/31/2021 02:26:45 - INFO - __main__ - Step 73529: {'lr': 0.00026311225282556845, 'samples': 14117568, 'steps': 73528, 'loss/train': 1.320746898651123} 08/31/2021 02:26:45 - INFO - __main__ - Step 73530: {'lr': 0.0002631069533824525, 'samples': 14117760, 'steps': 73529, 'loss/train': 0.7088653445243835} 08/31/2021 02:26:46 - INFO - __main__ - Step 73531: {'lr': 0.0002631016539334307, 'samples': 14117952, 'steps': 73530, 'loss/train': 1.1035231351852417} 08/31/2021 02:26:48 - INFO - __main__ - Step 73532: {'lr': 0.0002630963544785056, 'samples': 14118144, 'steps': 73531, 'loss/train': 0.03166589140892029} 08/31/2021 02:26:48 - INFO - __main__ - Step 73533: {'lr': 0.00026309105501767945, 'samples': 14118336, 'steps': 73532, 'loss/train': 1.2715892791748047} 08/31/2021 02:26:49 - INFO - __main__ - Step 73534: {'lr': 0.0002630857555509547, 'samples': 14118528, 'steps': 73533, 'loss/train': 1.154145359992981} 08/31/2021 02:26:49 - INFO - __main__ - Step 73535: {'lr': 0.00026308045607833364, 'samples': 14118720, 'steps': 73534, 'loss/train': 0.038371119648218155} 08/31/2021 02:26:49 - INFO - __main__ - Step 73536: {'lr': 0.0002630751565998187, 'samples': 14118912, 'steps': 73535, 'loss/train': 0.8903789520263672} 08/31/2021 02:26:51 - INFO - __main__ - Step 73537: {'lr': 0.0002630698571154124, 'samples': 14119104, 'steps': 73536, 'loss/train': 1.6945170164108276} 08/31/2021 02:26:51 - INFO - __main__ - Step 73538: {'lr': 0.000263064557625117, 'samples': 14119296, 'steps': 73537, 'loss/train': 1.5025036334991455} 08/31/2021 02:26:52 - INFO - __main__ - Step 73539: {'lr': 0.0002630592581289349, 'samples': 14119488, 'steps': 73538, 'loss/train': 1.0286720991134644} 08/31/2021 02:26:52 - INFO - __main__ - Step 73540: {'lr': 0.0002630539586268685, 'samples': 14119680, 'steps': 73539, 'loss/train': 0.2688200771808624} 08/31/2021 02:26:52 - INFO - __main__ - Step 73541: {'lr': 0.0002630486591189202, 'samples': 14119872, 'steps': 73540, 'loss/train': 1.4310444593429565} 08/31/2021 02:26:54 - INFO - __main__ - Step 73542: {'lr': 0.0002630433596050923, 'samples': 14120064, 'steps': 73541, 'loss/train': 1.5911056995391846} 08/31/2021 02:26:55 - INFO - __main__ - Step 73543: {'lr': 0.00026303806008538735, 'samples': 14120256, 'steps': 73542, 'loss/train': 1.0799458026885986} 08/31/2021 02:26:55 - INFO - __main__ - Step 73544: {'lr': 0.00026303276055980764, 'samples': 14120448, 'steps': 73543, 'loss/train': 0.5566464066505432} 08/31/2021 02:26:55 - INFO - __main__ - Step 73545: {'lr': 0.0002630274610283555, 'samples': 14120640, 'steps': 73544, 'loss/train': 1.645729899406433} 08/31/2021 02:26:56 - INFO - __main__ - Step 73546: {'lr': 0.00026302216149103345, 'samples': 14120832, 'steps': 73545, 'loss/train': 1.4278504848480225} 08/31/2021 02:26:57 - INFO - __main__ - Step 73547: {'lr': 0.0002630168619478438, 'samples': 14121024, 'steps': 73546, 'loss/train': 0.03422365337610245} 08/31/2021 02:26:58 - INFO - __main__ - Step 73548: {'lr': 0.00026301156239878895, 'samples': 14121216, 'steps': 73547, 'loss/train': 1.3103209733963013} 08/31/2021 02:26:58 - INFO - __main__ - Step 73549: {'lr': 0.0002630062628438713, 'samples': 14121408, 'steps': 73548, 'loss/train': 1.391187310218811} 08/31/2021 02:26:58 - INFO - __main__ - Step 73550: {'lr': 0.0002630009632830932, 'samples': 14121600, 'steps': 73549, 'loss/train': 1.2125892639160156} 08/31/2021 02:26:59 - INFO - __main__ - Step 73551: {'lr': 0.00026299566371645715, 'samples': 14121792, 'steps': 73550, 'loss/train': 0.9818572998046875} 08/31/2021 02:27:00 - INFO - __main__ - Step 73552: {'lr': 0.00026299036414396536, 'samples': 14121984, 'steps': 73551, 'loss/train': 1.433953046798706} 08/31/2021 02:27:01 - INFO - __main__ - Step 73553: {'lr': 0.0002629850645656204, 'samples': 14122176, 'steps': 73552, 'loss/train': 1.312009572982788} 08/31/2021 02:27:01 - INFO - __main__ - Step 73554: {'lr': 0.00026297976498142444, 'samples': 14122368, 'steps': 73553, 'loss/train': 1.258933424949646} 08/31/2021 02:27:01 - INFO - __main__ - Step 73555: {'lr': 0.0002629744653913801, 'samples': 14122560, 'steps': 73554, 'loss/train': 0.8108022212982178} 08/31/2021 02:27:02 - INFO - __main__ - Step 73556: {'lr': 0.00026296916579548964, 'samples': 14122752, 'steps': 73555, 'loss/train': 0.19537924230098724} 08/31/2021 02:27:03 - INFO - __main__ - Step 73557: {'lr': 0.00026296386619375546, 'samples': 14122944, 'steps': 73556, 'loss/train': 1.1180758476257324} 08/31/2021 02:27:04 - INFO - __main__ - Step 73558: {'lr': 0.00026295856658618003, 'samples': 14123136, 'steps': 73557, 'loss/train': 1.5075801610946655} 08/31/2021 02:27:04 - INFO - __main__ - Step 73559: {'lr': 0.00026295326697276563, 'samples': 14123328, 'steps': 73558, 'loss/train': 0.8640294075012207} 08/31/2021 02:27:04 - INFO - __main__ - Step 73560: {'lr': 0.0002629479673535146, 'samples': 14123520, 'steps': 73559, 'loss/train': 1.8127115964889526} 08/31/2021 02:27:05 - INFO - __main__ - Step 73561: {'lr': 0.0002629426677284295, 'samples': 14123712, 'steps': 73560, 'loss/train': 0.2818000018596649} 08/31/2021 02:27:05 - INFO - __main__ - Step 73562: {'lr': 0.00026293736809751263, 'samples': 14123904, 'steps': 73561, 'loss/train': 0.6351548433303833} 08/31/2021 02:27:07 - INFO - __main__ - Step 73563: {'lr': 0.0002629320684607664, 'samples': 14124096, 'steps': 73562, 'loss/train': 0.6617889404296875} 08/31/2021 02:27:07 - INFO - __main__ - Step 73564: {'lr': 0.0002629267688181931, 'samples': 14124288, 'steps': 73563, 'loss/train': 0.5415332317352295} 08/31/2021 02:27:07 - INFO - __main__ - Step 73565: {'lr': 0.0002629214691697953, 'samples': 14124480, 'steps': 73564, 'loss/train': 0.8723465800285339} 08/31/2021 02:27:08 - INFO - __main__ - Step 73566: {'lr': 0.00026291616951557527, 'samples': 14124672, 'steps': 73565, 'loss/train': 0.7595688104629517} 08/31/2021 02:27:08 - INFO - __main__ - Step 73567: {'lr': 0.00026291086985553535, 'samples': 14124864, 'steps': 73566, 'loss/train': 1.4480324983596802} 08/31/2021 02:27:10 - INFO - __main__ - Step 73568: {'lr': 0.00026290557018967804, 'samples': 14125056, 'steps': 73567, 'loss/train': 1.6876541376113892} 08/31/2021 02:27:10 - INFO - __main__ - Step 73569: {'lr': 0.0002629002705180056, 'samples': 14125248, 'steps': 73568, 'loss/train': 1.2290958166122437} 08/31/2021 02:27:10 - INFO - __main__ - Step 73570: {'lr': 0.0002628949708405206, 'samples': 14125440, 'steps': 73569, 'loss/train': 1.3278965950012207} 08/31/2021 02:27:11 - INFO - __main__ - Step 73571: {'lr': 0.0002628896711572253, 'samples': 14125632, 'steps': 73570, 'loss/train': 1.1151130199432373} 08/31/2021 02:27:11 - INFO - __main__ - Step 73572: {'lr': 0.0002628843714681221, 'samples': 14125824, 'steps': 73571, 'loss/train': 2.0167317390441895} 08/31/2021 02:27:13 - INFO - __main__ - Step 73573: {'lr': 0.0002628790717732134, 'samples': 14126016, 'steps': 73572, 'loss/train': 1.0570204257965088} 08/31/2021 02:27:13 - INFO - __main__ - Step 73574: {'lr': 0.0002628737720725016, 'samples': 14126208, 'steps': 73573, 'loss/train': 1.4448162317276} 08/31/2021 02:27:14 - INFO - __main__ - Step 73575: {'lr': 0.000262868472365989, 'samples': 14126400, 'steps': 73574, 'loss/train': 1.5862630605697632} 08/31/2021 02:27:14 - INFO - __main__ - Step 73576: {'lr': 0.00026286317265367815, 'samples': 14126592, 'steps': 73575, 'loss/train': 1.2472608089447021} 08/31/2021 02:27:14 - INFO - __main__ - Step 73577: {'lr': 0.00026285787293557134, 'samples': 14126784, 'steps': 73576, 'loss/train': 0.027092408388853073} 08/31/2021 02:27:16 - INFO - __main__ - Step 73578: {'lr': 0.000262852573211671, 'samples': 14126976, 'steps': 73577, 'loss/train': 1.018761396408081} 08/31/2021 02:27:16 - INFO - __main__ - Step 73579: {'lr': 0.00026284727348197944, 'samples': 14127168, 'steps': 73578, 'loss/train': 1.3339849710464478} 08/31/2021 02:27:17 - INFO - __main__ - Step 73580: {'lr': 0.0002628419737464991, 'samples': 14127360, 'steps': 73579, 'loss/train': 1.8857765197753906} 08/31/2021 02:27:17 - INFO - __main__ - Step 73581: {'lr': 0.0002628366740052324, 'samples': 14127552, 'steps': 73580, 'loss/train': 0.8858127593994141} 08/31/2021 02:27:17 - INFO - __main__ - Step 73582: {'lr': 0.0002628313742581817, 'samples': 14127744, 'steps': 73581, 'loss/train': 1.1755086183547974} 08/31/2021 02:27:19 - INFO - __main__ - Step 73583: {'lr': 0.0002628260745053493, 'samples': 14127936, 'steps': 73582, 'loss/train': 0.8250306248664856} 08/31/2021 02:27:19 - INFO - __main__ - Step 73584: {'lr': 0.0002628207747467377, 'samples': 14128128, 'steps': 73583, 'loss/train': 1.0304136276245117} 08/31/2021 02:27:20 - INFO - __main__ - Step 73585: {'lr': 0.0002628154749823493, 'samples': 14128320, 'steps': 73584, 'loss/train': 1.4088866710662842} 08/31/2021 02:27:20 - INFO - __main__ - Step 73586: {'lr': 0.00026281017521218643, 'samples': 14128512, 'steps': 73585, 'loss/train': 0.772152304649353} 08/31/2021 02:27:20 - INFO - __main__ - Step 73587: {'lr': 0.0002628048754362515, 'samples': 14128704, 'steps': 73586, 'loss/train': 2.148592472076416} 08/31/2021 02:27:21 - INFO - __main__ - Step 73588: {'lr': 0.0002627995756545468, 'samples': 14128896, 'steps': 73587, 'loss/train': 1.094679832458496} 08/31/2021 02:27:23 - INFO - __main__ - Step 73589: {'lr': 0.0002627942758670749, 'samples': 14129088, 'steps': 73588, 'loss/train': 1.3048815727233887} 08/31/2021 02:27:23 - INFO - __main__ - Step 73590: {'lr': 0.00026278897607383804, 'samples': 14129280, 'steps': 73589, 'loss/train': 1.119025468826294} 08/31/2021 02:27:24 - INFO - __main__ - Step 73591: {'lr': 0.00026278367627483875, 'samples': 14129472, 'steps': 73590, 'loss/train': 1.1124330759048462} 08/31/2021 02:27:24 - INFO - __main__ - Step 73592: {'lr': 0.0002627783764700793, 'samples': 14129664, 'steps': 73591, 'loss/train': 2.4055845737457275} 08/31/2021 02:27:24 - INFO - __main__ - Step 73593: {'lr': 0.00026277307665956205, 'samples': 14129856, 'steps': 73592, 'loss/train': 1.3863544464111328} 08/31/2021 02:27:26 - INFO - __main__ - Step 73594: {'lr': 0.0002627677768432896, 'samples': 14130048, 'steps': 73593, 'loss/train': 0.7292086482048035} 08/31/2021 02:27:26 - INFO - __main__ - Step 73595: {'lr': 0.000262762477021264, 'samples': 14130240, 'steps': 73594, 'loss/train': 1.3374629020690918} 08/31/2021 02:27:26 - INFO - __main__ - Step 73596: {'lr': 0.00026275717719348793, 'samples': 14130432, 'steps': 73595, 'loss/train': 1.0208041667938232} 08/31/2021 02:27:27 - INFO - __main__ - Step 73597: {'lr': 0.00026275187735996363, 'samples': 14130624, 'steps': 73596, 'loss/train': 1.257259488105774} 08/31/2021 02:27:27 - INFO - __main__ - Step 73598: {'lr': 0.0002627465775206936, 'samples': 14130816, 'steps': 73597, 'loss/train': 1.7098233699798584} 08/31/2021 02:27:29 - INFO - __main__ - Step 73599: {'lr': 0.00026274127767568007, 'samples': 14131008, 'steps': 73598, 'loss/train': 1.009979248046875} 08/31/2021 02:27:29 - INFO - __main__ - Step 73600: {'lr': 0.0002627359778249255, 'samples': 14131200, 'steps': 73599, 'loss/train': 1.7785309553146362} 08/31/2021 02:27:30 - INFO - __main__ - Step 73601: {'lr': 0.0002627306779684324, 'samples': 14131392, 'steps': 73600, 'loss/train': 1.6569409370422363} 08/31/2021 02:27:30 - INFO - __main__ - Step 73602: {'lr': 0.000262725378106203, 'samples': 14131584, 'steps': 73601, 'loss/train': 1.0218466520309448} 08/31/2021 02:27:30 - INFO - __main__ - Step 73603: {'lr': 0.00026272007823823976, 'samples': 14131776, 'steps': 73602, 'loss/train': 1.1383906602859497} 08/31/2021 02:27:32 - INFO - __main__ - Step 73604: {'lr': 0.000262714778364545, 'samples': 14131968, 'steps': 73603, 'loss/train': 1.3389651775360107} 08/31/2021 02:27:32 - INFO - __main__ - Step 73605: {'lr': 0.00026270947848512123, 'samples': 14132160, 'steps': 73604, 'loss/train': 0.9499202370643616} 08/31/2021 02:27:33 - INFO - __main__ - Step 73606: {'lr': 0.0002627041785999707, 'samples': 14132352, 'steps': 73605, 'loss/train': 1.745639681816101} 08/31/2021 02:27:33 - INFO - __main__ - Step 73607: {'lr': 0.00026269887870909595, 'samples': 14132544, 'steps': 73606, 'loss/train': 1.6424843072891235} 08/31/2021 02:27:33 - INFO - __main__ - Step 73608: {'lr': 0.00026269357881249916, 'samples': 14132736, 'steps': 73607, 'loss/train': 1.5010578632354736} 08/31/2021 02:27:34 - INFO - __main__ - Step 73609: {'lr': 0.0002626882789101829, 'samples': 14132928, 'steps': 73608, 'loss/train': 1.336864709854126} 08/31/2021 02:27:35 - INFO - __main__ - Step 73610: {'lr': 0.0002626829790021495, 'samples': 14133120, 'steps': 73609, 'loss/train': 0.8882965445518494} 08/31/2021 02:27:36 - INFO - __main__ - Step 73611: {'lr': 0.0002626776790884013, 'samples': 14133312, 'steps': 73610, 'loss/train': 0.8927057385444641} 08/31/2021 02:27:36 - INFO - __main__ - Step 73612: {'lr': 0.0002626723791689408, 'samples': 14133504, 'steps': 73611, 'loss/train': 1.582324743270874} 08/31/2021 02:27:37 - INFO - __main__ - Step 73613: {'lr': 0.0002626670792437703, 'samples': 14133696, 'steps': 73612, 'loss/train': 1.6786301136016846} 08/31/2021 02:27:37 - INFO - __main__ - Step 73614: {'lr': 0.0002626617793128922, 'samples': 14133888, 'steps': 73613, 'loss/train': 1.6884485483169556} 08/31/2021 02:27:39 - INFO - __main__ - Step 73615: {'lr': 0.00026265647937630894, 'samples': 14134080, 'steps': 73614, 'loss/train': 1.2843412160873413} 08/31/2021 02:27:39 - INFO - __main__ - Step 73616: {'lr': 0.0002626511794340228, 'samples': 14134272, 'steps': 73615, 'loss/train': 1.3192521333694458} 08/31/2021 02:27:40 - INFO - __main__ - Step 73617: {'lr': 0.00026264587948603623, 'samples': 14134464, 'steps': 73616, 'loss/train': 1.0670050382614136} 08/31/2021 02:27:40 - INFO - __main__ - Step 73618: {'lr': 0.0002626405795323517, 'samples': 14134656, 'steps': 73617, 'loss/train': 0.035311970859766006} 08/31/2021 02:27:40 - INFO - __main__ - Step 73619: {'lr': 0.0002626352795729715, 'samples': 14134848, 'steps': 73618, 'loss/train': 1.193218469619751} 08/31/2021 02:27:41 - INFO - __main__ - Step 73620: {'lr': 0.00026262997960789796, 'samples': 14135040, 'steps': 73619, 'loss/train': 1.3012170791625977} 08/31/2021 02:27:42 - INFO - __main__ - Step 73621: {'lr': 0.0002626246796371336, 'samples': 14135232, 'steps': 73620, 'loss/train': 1.1909105777740479} 08/31/2021 02:27:43 - INFO - __main__ - Step 73622: {'lr': 0.0002626193796606808, 'samples': 14135424, 'steps': 73621, 'loss/train': 0.8716668486595154} 08/31/2021 02:27:43 - INFO - __main__ - Step 73623: {'lr': 0.00026261407967854186, 'samples': 14135616, 'steps': 73622, 'loss/train': 1.6989634037017822} 08/31/2021 02:27:43 - INFO - __main__ - Step 73624: {'lr': 0.00026260877969071916, 'samples': 14135808, 'steps': 73623, 'loss/train': 1.28793466091156} 08/31/2021 02:27:44 - INFO - __main__ - Step 73625: {'lr': 0.0002626034796972152, 'samples': 14136000, 'steps': 73624, 'loss/train': 0.9727147221565247} 08/31/2021 02:27:45 - INFO - __main__ - Step 73626: {'lr': 0.0002625981796980323, 'samples': 14136192, 'steps': 73625, 'loss/train': 1.1370004415512085} 08/31/2021 02:27:46 - INFO - __main__ - Step 73627: {'lr': 0.0002625928796931729, 'samples': 14136384, 'steps': 73626, 'loss/train': 1.5553643703460693} 08/31/2021 02:27:46 - INFO - __main__ - Step 73628: {'lr': 0.00026258757968263924, 'samples': 14136576, 'steps': 73627, 'loss/train': 0.6965472102165222} 08/31/2021 02:27:46 - INFO - __main__ - Step 73629: {'lr': 0.0002625822796664338, 'samples': 14136768, 'steps': 73628, 'loss/train': 1.6144064664840698} 08/31/2021 02:27:47 - INFO - __main__ - Step 73630: {'lr': 0.0002625769796445591, 'samples': 14136960, 'steps': 73629, 'loss/train': 1.1903076171875} 08/31/2021 02:27:48 - INFO - __main__ - Step 73631: {'lr': 0.0002625716796170173, 'samples': 14137152, 'steps': 73630, 'loss/train': 2.5298566818237305} 08/31/2021 02:27:49 - INFO - __main__ - Step 73632: {'lr': 0.000262566379583811, 'samples': 14137344, 'steps': 73631, 'loss/train': 1.3522546291351318} 08/31/2021 02:27:49 - INFO - __main__ - Step 73633: {'lr': 0.0002625610795449424, 'samples': 14137536, 'steps': 73632, 'loss/train': 0.7834699153900146} 08/31/2021 02:27:49 - INFO - __main__ - Step 73634: {'lr': 0.00026255577950041396, 'samples': 14137728, 'steps': 73633, 'loss/train': 0.9038732647895813} 08/31/2021 02:27:50 - INFO - __main__ - Step 73635: {'lr': 0.0002625504794502281, 'samples': 14137920, 'steps': 73634, 'loss/train': 1.2835975885391235} 08/31/2021 02:27:51 - INFO - __main__ - Step 73636: {'lr': 0.0002625451793943872, 'samples': 14138112, 'steps': 73635, 'loss/train': 1.5865411758422852} 08/31/2021 02:27:52 - INFO - __main__ - Step 73637: {'lr': 0.00026253987933289366, 'samples': 14138304, 'steps': 73636, 'loss/train': 0.6301918625831604} 08/31/2021 02:27:52 - INFO - __main__ - Step 73638: {'lr': 0.0002625345792657498, 'samples': 14138496, 'steps': 73637, 'loss/train': 1.5382981300354004} 08/31/2021 02:27:52 - INFO - __main__ - Step 73639: {'lr': 0.00026252927919295815, 'samples': 14138688, 'steps': 73638, 'loss/train': 0.6547728180885315} 08/31/2021 02:27:53 - INFO - __main__ - Step 73640: {'lr': 0.0002625239791145209, 'samples': 14138880, 'steps': 73639, 'loss/train': 0.7807331085205078} 08/31/2021 02:27:54 - INFO - __main__ - Step 73641: {'lr': 0.0002625186790304406, 'samples': 14139072, 'steps': 73640, 'loss/train': 1.3696625232696533} 08/31/2021 02:27:55 - INFO - __main__ - Step 73642: {'lr': 0.0002625133789407195, 'samples': 14139264, 'steps': 73641, 'loss/train': 1.4177711009979248} 08/31/2021 02:27:55 - INFO - __main__ - Step 73643: {'lr': 0.0002625080788453601, 'samples': 14139456, 'steps': 73642, 'loss/train': 2.018542528152466} 08/31/2021 02:27:55 - INFO - __main__ - Step 73644: {'lr': 0.00026250277874436474, 'samples': 14139648, 'steps': 73643, 'loss/train': 2.1299309730529785} 08/31/2021 02:27:56 - INFO - __main__ - Step 73645: {'lr': 0.0002624974786377359, 'samples': 14139840, 'steps': 73644, 'loss/train': 1.3912655115127563} 08/31/2021 02:27:58 - INFO - __main__ - Step 73646: {'lr': 0.0002624921785254758, 'samples': 14140032, 'steps': 73645, 'loss/train': 1.2407333850860596} 08/31/2021 02:27:58 - INFO - __main__ - Step 73647: {'lr': 0.0002624868784075869, 'samples': 14140224, 'steps': 73646, 'loss/train': 1.5569591522216797} 08/31/2021 02:27:58 - INFO - __main__ - Step 73648: {'lr': 0.0002624815782840717, 'samples': 14140416, 'steps': 73647, 'loss/train': 1.6723124980926514} 08/31/2021 02:27:59 - INFO - __main__ - Step 73649: {'lr': 0.0002624762781549324, 'samples': 14140608, 'steps': 73648, 'loss/train': 1.2639434337615967} 08/31/2021 02:27:59 - INFO - __main__ - Step 73650: {'lr': 0.0002624709780201716, 'samples': 14140800, 'steps': 73649, 'loss/train': 1.2298202514648438} 08/31/2021 02:27:59 - INFO - __main__ - Step 73651: {'lr': 0.00026246567787979145, 'samples': 14140992, 'steps': 73650, 'loss/train': 1.0311959981918335} 08/31/2021 02:28:01 - INFO - __main__ - Step 73652: {'lr': 0.0002624603777337945, 'samples': 14141184, 'steps': 73651, 'loss/train': 1.4436193704605103} 08/31/2021 02:28:02 - INFO - __main__ - Step 73653: {'lr': 0.00026245507758218306, 'samples': 14141376, 'steps': 73652, 'loss/train': 1.6945947408676147} 08/31/2021 02:28:02 - INFO - __main__ - Step 73654: {'lr': 0.00026244977742495963, 'samples': 14141568, 'steps': 73653, 'loss/train': 1.425593376159668} 08/31/2021 02:28:03 - INFO - __main__ - Step 73655: {'lr': 0.0002624444772621265, 'samples': 14141760, 'steps': 73654, 'loss/train': 0.39111053943634033} 08/31/2021 02:28:03 - INFO - __main__ - Step 73656: {'lr': 0.000262439177093686, 'samples': 14141952, 'steps': 73655, 'loss/train': 1.0718882083892822} 08/31/2021 02:28:05 - INFO - __main__ - Step 73657: {'lr': 0.0002624338769196407, 'samples': 14142144, 'steps': 73656, 'loss/train': 0.12231644988059998} 08/31/2021 02:28:05 - INFO - __main__ - Step 73658: {'lr': 0.0002624285767399929, 'samples': 14142336, 'steps': 73657, 'loss/train': 1.193769931793213} 08/31/2021 02:28:05 - INFO - __main__ - Step 73659: {'lr': 0.00026242327655474483, 'samples': 14142528, 'steps': 73658, 'loss/train': 1.644660234451294} 08/31/2021 02:28:06 - INFO - __main__ - Step 73660: {'lr': 0.00026241797636389916, 'samples': 14142720, 'steps': 73659, 'loss/train': 1.3472470045089722} 08/31/2021 02:28:06 - INFO - __main__ - Step 73661: {'lr': 0.00026241267616745813, 'samples': 14142912, 'steps': 73660, 'loss/train': 0.6725630164146423} 08/31/2021 02:28:08 - INFO - __main__ - Step 73662: {'lr': 0.0002624073759654241, 'samples': 14143104, 'steps': 73661, 'loss/train': 2.3179783821105957} 08/31/2021 02:28:08 - INFO - __main__ - Step 73663: {'lr': 0.0002624020757577995, 'samples': 14143296, 'steps': 73662, 'loss/train': 1.134676456451416} 08/31/2021 02:28:08 - INFO - __main__ - Step 73664: {'lr': 0.00026239677554458675, 'samples': 14143488, 'steps': 73663, 'loss/train': 1.7879329919815063} 08/31/2021 02:28:09 - INFO - __main__ - Step 73665: {'lr': 0.0002623914753257881, 'samples': 14143680, 'steps': 73664, 'loss/train': 1.5659407377243042} 08/31/2021 02:28:09 - INFO - __main__ - Step 73666: {'lr': 0.0002623861751014062, 'samples': 14143872, 'steps': 73665, 'loss/train': 1.4962915182113647} 08/31/2021 02:28:09 - INFO - __main__ - Step 73667: {'lr': 0.0002623808748714432, 'samples': 14144064, 'steps': 73666, 'loss/train': 0.9363408088684082} 08/31/2021 02:28:11 - INFO - __main__ - Step 73668: {'lr': 0.00026237557463590155, 'samples': 14144256, 'steps': 73667, 'loss/train': 1.7875421047210693} 08/31/2021 02:28:12 - INFO - __main__ - Step 73669: {'lr': 0.0002623702743947837, 'samples': 14144448, 'steps': 73668, 'loss/train': 1.5582737922668457} 08/31/2021 02:28:12 - INFO - __main__ - Step 73670: {'lr': 0.0002623649741480919, 'samples': 14144640, 'steps': 73669, 'loss/train': 0.7961894869804382} 08/31/2021 02:28:12 - INFO - __main__ - Step 73671: {'lr': 0.0002623596738958287, 'samples': 14144832, 'steps': 73670, 'loss/train': 0.9586278200149536} 08/31/2021 02:28:13 - INFO - __main__ - Step 73672: {'lr': 0.00026235437363799654, 'samples': 14145024, 'steps': 73671, 'loss/train': 1.3671728372573853} 08/31/2021 02:28:14 - INFO - __main__ - Step 73673: {'lr': 0.0002623490733745975, 'samples': 14145216, 'steps': 73672, 'loss/train': 1.3318722248077393} 08/31/2021 02:28:15 - INFO - __main__ - Step 73674: {'lr': 0.00026234377310563426, 'samples': 14145408, 'steps': 73673, 'loss/train': 1.6517409086227417} 08/31/2021 02:28:15 - INFO - __main__ - Step 73675: {'lr': 0.00026233847283110905, 'samples': 14145600, 'steps': 73674, 'loss/train': 0.8410689830780029} 08/31/2021 02:28:15 - INFO - __main__ - Step 73676: {'lr': 0.00026233317255102437, 'samples': 14145792, 'steps': 73675, 'loss/train': 1.2765501737594604} 08/31/2021 02:28:16 - INFO - __main__ - Step 73677: {'lr': 0.0002623278722653825, 'samples': 14145984, 'steps': 73676, 'loss/train': 1.896872639656067} 08/31/2021 02:28:17 - INFO - __main__ - Step 73678: {'lr': 0.0002623225719741859, 'samples': 14146176, 'steps': 73677, 'loss/train': 0.9314259886741638} 08/31/2021 02:28:18 - INFO - __main__ - Step 73679: {'lr': 0.00026231727167743703, 'samples': 14146368, 'steps': 73678, 'loss/train': 1.365376591682434} 08/31/2021 02:28:18 - INFO - __main__ - Step 73680: {'lr': 0.0002623119713751381, 'samples': 14146560, 'steps': 73679, 'loss/train': 1.422025203704834} 08/31/2021 02:28:18 - INFO - __main__ - Step 73681: {'lr': 0.00026230667106729154, 'samples': 14146752, 'steps': 73680, 'loss/train': 1.569852590560913} 08/31/2021 02:28:19 - INFO - __main__ - Step 73682: {'lr': 0.0002623013707538998, 'samples': 14146944, 'steps': 73681, 'loss/train': 0.49778860807418823} 08/31/2021 02:28:20 - INFO - __main__ - Step 73683: {'lr': 0.00026229607043496534, 'samples': 14147136, 'steps': 73682, 'loss/train': 1.2312899827957153} 08/31/2021 02:28:21 - INFO - __main__ - Step 73684: {'lr': 0.00026229077011049034, 'samples': 14147328, 'steps': 73683, 'loss/train': 1.4277313947677612} 08/31/2021 02:28:21 - INFO - __main__ - Step 73685: {'lr': 0.0002622854697804774, 'samples': 14147520, 'steps': 73684, 'loss/train': 1.2185190916061401} 08/31/2021 02:28:21 - INFO - __main__ - Step 73686: {'lr': 0.00026228016944492883, 'samples': 14147712, 'steps': 73685, 'loss/train': 1.3921468257904053} 08/31/2021 02:28:22 - INFO - __main__ - Step 73687: {'lr': 0.00026227486910384694, 'samples': 14147904, 'steps': 73686, 'loss/train': 1.3057266473770142} 08/31/2021 02:28:23 - INFO - __main__ - Step 73688: {'lr': 0.0002622695687572342, 'samples': 14148096, 'steps': 73687, 'loss/train': 1.5757036209106445} 08/31/2021 02:28:24 - INFO - __main__ - Step 73689: {'lr': 0.00026226426840509303, 'samples': 14148288, 'steps': 73688, 'loss/train': 1.3612390756607056} 08/31/2021 02:28:24 - INFO - __main__ - Step 73690: {'lr': 0.0002622589680474257, 'samples': 14148480, 'steps': 73689, 'loss/train': 1.0741504430770874} 08/31/2021 02:28:24 - INFO - __main__ - Step 73691: {'lr': 0.0002622536676842347, 'samples': 14148672, 'steps': 73690, 'loss/train': 1.2421809434890747} 08/31/2021 02:28:25 - INFO - __main__ - Step 73692: {'lr': 0.0002622483673155224, 'samples': 14148864, 'steps': 73691, 'loss/train': 1.9243687391281128} 08/31/2021 02:28:26 - INFO - __main__ - Step 73693: {'lr': 0.00026224306694129116, 'samples': 14149056, 'steps': 73692, 'loss/train': 1.0269250869750977} 08/31/2021 02:28:27 - INFO - __main__ - Step 73694: {'lr': 0.0002622377665615434, 'samples': 14149248, 'steps': 73693, 'loss/train': 0.7064356803894043} 08/31/2021 02:28:27 - INFO - __main__ - Step 73695: {'lr': 0.0002622324661762815, 'samples': 14149440, 'steps': 73694, 'loss/train': 1.1331212520599365} 08/31/2021 02:28:27 - INFO - __main__ - Step 73696: {'lr': 0.0002622271657855078, 'samples': 14149632, 'steps': 73695, 'loss/train': 1.389017939567566} 08/31/2021 02:28:28 - INFO - __main__ - Step 73697: {'lr': 0.0002622218653892247, 'samples': 14149824, 'steps': 73696, 'loss/train': 1.2894026041030884} 08/31/2021 02:28:30 - INFO - __main__ - Step 73698: {'lr': 0.00026221656498743467, 'samples': 14150016, 'steps': 73697, 'loss/train': 0.22668862342834473} 08/31/2021 02:28:30 - INFO - __main__ - Step 73699: {'lr': 0.0002622112645801401, 'samples': 14150208, 'steps': 73698, 'loss/train': 0.9098275303840637} 08/31/2021 02:28:31 - INFO - __main__ - Step 73700: {'lr': 0.0002622059641673432, 'samples': 14150400, 'steps': 73699, 'loss/train': 1.4351356029510498} 08/31/2021 02:28:31 - INFO - __main__ - Step 73701: {'lr': 0.00026220066374904653, 'samples': 14150592, 'steps': 73700, 'loss/train': 0.8830181956291199} 08/31/2021 02:28:31 - INFO - __main__ - Step 73702: {'lr': 0.00026219536332525243, 'samples': 14150784, 'steps': 73701, 'loss/train': 0.9621348977088928} 08/31/2021 02:28:33 - INFO - __main__ - Step 73703: {'lr': 0.0002621900628959633, 'samples': 14150976, 'steps': 73702, 'loss/train': 0.9826291799545288} 08/31/2021 02:28:33 - INFO - __main__ - Step 73704: {'lr': 0.0002621847624611815, 'samples': 14151168, 'steps': 73703, 'loss/train': 0.9792874455451965} 08/31/2021 02:28:34 - INFO - __main__ - Step 73705: {'lr': 0.00026217946202090946, 'samples': 14151360, 'steps': 73704, 'loss/train': 1.3325741291046143} 08/31/2021 02:28:34 - INFO - __main__ - Step 73706: {'lr': 0.0002621741615751496, 'samples': 14151552, 'steps': 73705, 'loss/train': 1.6728547811508179} 08/31/2021 02:28:34 - INFO - __main__ - Step 73707: {'lr': 0.00026216886112390413, 'samples': 14151744, 'steps': 73706, 'loss/train': 0.9773305058479309} 08/31/2021 02:28:35 - INFO - __main__ - Step 73708: {'lr': 0.0002621635606671756, 'samples': 14151936, 'steps': 73707, 'loss/train': 0.5706927180290222} 08/31/2021 02:28:36 - INFO - __main__ - Step 73709: {'lr': 0.00026215826020496637, 'samples': 14152128, 'steps': 73708, 'loss/train': 1.5168293714523315} 08/31/2021 02:28:37 - INFO - __main__ - Step 73710: {'lr': 0.00026215295973727883, 'samples': 14152320, 'steps': 73709, 'loss/train': 1.3705171346664429} 08/31/2021 02:28:37 - INFO - __main__ - Step 73711: {'lr': 0.00026214765926411526, 'samples': 14152512, 'steps': 73710, 'loss/train': 1.3415809869766235} 08/31/2021 02:28:37 - INFO - __main__ - Step 73712: {'lr': 0.00026214235878547825, 'samples': 14152704, 'steps': 73711, 'loss/train': 1.404384732246399} 08/31/2021 02:28:38 - INFO - __main__ - Step 73713: {'lr': 0.0002621370583013701, 'samples': 14152896, 'steps': 73712, 'loss/train': 1.5384130477905273} 08/31/2021 02:28:39 - INFO - __main__ - Step 73714: {'lr': 0.0002621317578117931, 'samples': 14153088, 'steps': 73713, 'loss/train': 1.120052695274353} 08/31/2021 02:28:40 - INFO - __main__ - Step 73715: {'lr': 0.00026212645731674974, 'samples': 14153280, 'steps': 73714, 'loss/train': 1.2266565561294556} 08/31/2021 02:28:40 - INFO - __main__ - Step 73716: {'lr': 0.00026212115681624237, 'samples': 14153472, 'steps': 73715, 'loss/train': 1.0292751789093018} 08/31/2021 02:28:40 - INFO - __main__ - Step 73717: {'lr': 0.0002621158563102734, 'samples': 14153664, 'steps': 73716, 'loss/train': 1.8446571826934814} 08/31/2021 02:28:41 - INFO - __main__ - Step 73718: {'lr': 0.00026211055579884523, 'samples': 14153856, 'steps': 73717, 'loss/train': 1.177682638168335} 08/31/2021 02:28:42 - INFO - __main__ - Step 73719: {'lr': 0.0002621052552819603, 'samples': 14154048, 'steps': 73718, 'loss/train': 1.2416598796844482} 08/31/2021 02:28:43 - INFO - __main__ - Step 73720: {'lr': 0.00026209995475962077, 'samples': 14154240, 'steps': 73719, 'loss/train': 1.6163688898086548} 08/31/2021 02:28:43 - INFO - __main__ - Step 73721: {'lr': 0.00026209465423182934, 'samples': 14154432, 'steps': 73720, 'loss/train': 0.9564164280891418} 08/31/2021 02:28:43 - INFO - __main__ - Step 73722: {'lr': 0.0002620893536985881, 'samples': 14154624, 'steps': 73721, 'loss/train': 1.5815908908843994} 08/31/2021 02:28:44 - INFO - __main__ - Step 73723: {'lr': 0.0002620840531598997, 'samples': 14154816, 'steps': 73722, 'loss/train': 0.22766801714897156} 08/31/2021 02:28:45 - INFO - __main__ - Step 73724: {'lr': 0.0002620787526157664, 'samples': 14155008, 'steps': 73723, 'loss/train': 1.0547047853469849} 08/31/2021 02:28:46 - INFO - __main__ - Step 73725: {'lr': 0.0002620734520661905, 'samples': 14155200, 'steps': 73724, 'loss/train': 0.04666225612163544} 08/31/2021 02:28:46 - INFO - __main__ - Step 73726: {'lr': 0.0002620681515111746, 'samples': 14155392, 'steps': 73725, 'loss/train': 1.5892831087112427} 08/31/2021 02:28:46 - INFO - __main__ - Step 73727: {'lr': 0.0002620628509507209, 'samples': 14155584, 'steps': 73726, 'loss/train': 1.5041683912277222} 08/31/2021 02:28:47 - INFO - __main__ - Step 73728: {'lr': 0.0002620575503848319, 'samples': 14155776, 'steps': 73727, 'loss/train': 1.6904425621032715} 08/31/2021 02:28:48 - INFO - __main__ - Step 73729: {'lr': 0.00026205224981350997, 'samples': 14155968, 'steps': 73728, 'loss/train': 1.6215367317199707} 08/31/2021 02:28:49 - INFO - __main__ - Step 73730: {'lr': 0.0002620469492367575, 'samples': 14156160, 'steps': 73729, 'loss/train': 1.308518409729004} 08/31/2021 02:28:49 - INFO - __main__ - Step 73731: {'lr': 0.0002620416486545768, 'samples': 14156352, 'steps': 73730, 'loss/train': 0.45506420731544495} 08/31/2021 02:28:50 - INFO - __main__ - Step 73732: {'lr': 0.0002620363480669703, 'samples': 14156544, 'steps': 73731, 'loss/train': 1.559410572052002} 08/31/2021 02:28:50 - INFO - __main__ - Step 73733: {'lr': 0.0002620310474739405, 'samples': 14156736, 'steps': 73732, 'loss/train': 0.09785237163305283} 08/31/2021 02:28:52 - INFO - __main__ - Step 73734: {'lr': 0.0002620257468754897, 'samples': 14156928, 'steps': 73733, 'loss/train': 1.2381919622421265} 08/31/2021 02:28:52 - INFO - __main__ - Step 73735: {'lr': 0.0002620204462716202, 'samples': 14157120, 'steps': 73734, 'loss/train': 1.6132622957229614} 08/31/2021 02:28:52 - INFO - __main__ - Step 73736: {'lr': 0.00026201514566233445, 'samples': 14157312, 'steps': 73735, 'loss/train': 1.9848109483718872} 08/31/2021 02:28:53 - INFO - __main__ - Step 73737: {'lr': 0.00026200984504763495, 'samples': 14157504, 'steps': 73736, 'loss/train': 0.6208850145339966} 08/31/2021 02:28:53 - INFO - __main__ - Step 73738: {'lr': 0.000262004544427524, 'samples': 14157696, 'steps': 73737, 'loss/train': 1.1685651540756226} 08/31/2021 02:28:55 - INFO - __main__ - Step 73739: {'lr': 0.000261999243802004, 'samples': 14157888, 'steps': 73738, 'loss/train': 1.5249336957931519} 08/31/2021 02:28:55 - INFO - __main__ - Step 73740: {'lr': 0.00026199394317107723, 'samples': 14158080, 'steps': 73739, 'loss/train': 1.1961325407028198} 08/31/2021 02:28:56 - INFO - __main__ - Step 73741: {'lr': 0.0002619886425347462, 'samples': 14158272, 'steps': 73740, 'loss/train': 1.928039312362671} 08/31/2021 02:28:56 - INFO - __main__ - Step 73742: {'lr': 0.00026198334189301333, 'samples': 14158464, 'steps': 73741, 'loss/train': 1.160095453262329} 08/31/2021 02:28:56 - INFO - __main__ - Step 73743: {'lr': 0.00026197804124588085, 'samples': 14158656, 'steps': 73742, 'loss/train': 1.161638855934143} 08/31/2021 02:28:57 - INFO - __main__ - Step 73744: {'lr': 0.00026197274059335137, 'samples': 14158848, 'steps': 73743, 'loss/train': 1.5204180479049683} 08/31/2021 02:28:58 - INFO - __main__ - Step 73745: {'lr': 0.0002619674399354271, 'samples': 14159040, 'steps': 73744, 'loss/train': 1.0743166208267212} 08/31/2021 02:28:58 - INFO - __main__ - Step 73746: {'lr': 0.0002619621392721105, 'samples': 14159232, 'steps': 73745, 'loss/train': 1.1292206048965454} 08/31/2021 02:28:59 - INFO - __main__ - Step 73747: {'lr': 0.000261956838603404, 'samples': 14159424, 'steps': 73746, 'loss/train': 1.3338428735733032} 08/31/2021 02:28:59 - INFO - __main__ - Step 73748: {'lr': 0.00026195153792930983, 'samples': 14159616, 'steps': 73747, 'loss/train': 1.6996904611587524} 08/31/2021 02:28:59 - INFO - __main__ - Step 73749: {'lr': 0.0002619462372498305, 'samples': 14159808, 'steps': 73748, 'loss/train': 1.137351632118225} 08/31/2021 02:29:01 - INFO - __main__ - Step 73750: {'lr': 0.0002619409365649684, 'samples': 14160000, 'steps': 73749, 'loss/train': 0.9919248223304749} 08/31/2021 02:29:02 - INFO - __main__ - Step 73751: {'lr': 0.0002619356358747259, 'samples': 14160192, 'steps': 73750, 'loss/train': 0.8025957942008972} 08/31/2021 02:29:02 - INFO - __main__ - Step 73752: {'lr': 0.00026193033517910534, 'samples': 14160384, 'steps': 73751, 'loss/train': 1.8581957817077637} 08/31/2021 02:29:03 - INFO - __main__ - Step 73753: {'lr': 0.00026192503447810926, 'samples': 14160576, 'steps': 73752, 'loss/train': 1.2753022909164429} 08/31/2021 02:29:03 - INFO - __main__ - Step 73754: {'lr': 0.00026191973377173987, 'samples': 14160768, 'steps': 73753, 'loss/train': 1.645385980606079} 08/31/2021 02:29:05 - INFO - __main__ - Step 73755: {'lr': 0.0002619144330599996, 'samples': 14160960, 'steps': 73754, 'loss/train': 1.3754183053970337} 08/31/2021 02:29:05 - INFO - __main__ - Step 73756: {'lr': 0.00026190913234289093, 'samples': 14161152, 'steps': 73755, 'loss/train': 0.8962876200675964} 08/31/2021 02:29:05 - INFO - __main__ - Step 73757: {'lr': 0.0002619038316204162, 'samples': 14161344, 'steps': 73756, 'loss/train': 1.4058477878570557} 08/31/2021 02:29:06 - INFO - __main__ - Step 73758: {'lr': 0.0002618985308925778, 'samples': 14161536, 'steps': 73757, 'loss/train': 1.03179132938385} 08/31/2021 02:29:06 - INFO - __main__ - Step 73759: {'lr': 0.000261893230159378, 'samples': 14161728, 'steps': 73758, 'loss/train': 1.338594675064087} 08/31/2021 02:29:08 - INFO - __main__ - Step 73760: {'lr': 0.0002618879294208194, 'samples': 14161920, 'steps': 73759, 'loss/train': 1.439196228981018} 08/31/2021 02:29:08 - INFO - __main__ - Step 73761: {'lr': 0.0002618826286769043, 'samples': 14162112, 'steps': 73760, 'loss/train': 1.4933499097824097} 08/31/2021 02:29:08 - INFO - __main__ - Step 73762: {'lr': 0.00026187732792763496, 'samples': 14162304, 'steps': 73761, 'loss/train': 1.2684627771377563} 08/31/2021 02:29:09 - INFO - __main__ - Step 73763: {'lr': 0.00026187202717301396, 'samples': 14162496, 'steps': 73762, 'loss/train': 1.4554517269134521} 08/31/2021 02:29:09 - INFO - __main__ - Step 73764: {'lr': 0.0002618667264130435, 'samples': 14162688, 'steps': 73763, 'loss/train': 1.3655606508255005} 08/31/2021 02:29:11 - INFO - __main__ - Step 73765: {'lr': 0.0002618614256477262, 'samples': 14162880, 'steps': 73764, 'loss/train': 1.51304292678833} 08/31/2021 02:29:11 - INFO - __main__ - Step 73766: {'lr': 0.00026185612487706435, 'samples': 14163072, 'steps': 73765, 'loss/train': 1.4681761264801025} 08/31/2021 02:29:11 - INFO - __main__ - Step 73767: {'lr': 0.00026185082410106023, 'samples': 14163264, 'steps': 73766, 'loss/train': 1.1623344421386719} 08/31/2021 02:29:12 - INFO - __main__ - Step 73768: {'lr': 0.0002618455233197163, 'samples': 14163456, 'steps': 73767, 'loss/train': 0.9710837602615356} 08/31/2021 02:29:12 - INFO - __main__ - Step 73769: {'lr': 0.00026184022253303497, 'samples': 14163648, 'steps': 73768, 'loss/train': 1.1191638708114624} 08/31/2021 02:29:14 - INFO - __main__ - Step 73770: {'lr': 0.00026183492174101865, 'samples': 14163840, 'steps': 73769, 'loss/train': 1.5186951160430908} 08/31/2021 02:29:14 - INFO - __main__ - Step 73771: {'lr': 0.0002618296209436697, 'samples': 14164032, 'steps': 73770, 'loss/train': 0.6923171877861023} 08/31/2021 02:29:15 - INFO - __main__ - Step 73772: {'lr': 0.00026182432014099045, 'samples': 14164224, 'steps': 73771, 'loss/train': 0.9102209210395813} 08/31/2021 02:29:15 - INFO - __main__ - Step 73773: {'lr': 0.0002618190193329834, 'samples': 14164416, 'steps': 73772, 'loss/train': 1.4809564352035522} 08/31/2021 02:29:15 - INFO - __main__ - Step 73774: {'lr': 0.0002618137185196509, 'samples': 14164608, 'steps': 73773, 'loss/train': 0.7919502854347229} 08/31/2021 02:29:17 - INFO - __main__ - Step 73775: {'lr': 0.0002618084177009953, 'samples': 14164800, 'steps': 73774, 'loss/train': 0.09312083572149277} 08/31/2021 02:29:17 - INFO - __main__ - Step 73776: {'lr': 0.000261803116877019, 'samples': 14164992, 'steps': 73775, 'loss/train': 1.6160887479782104} 08/31/2021 02:29:18 - INFO - __main__ - Step 73777: {'lr': 0.0002617978160477243, 'samples': 14165184, 'steps': 73776, 'loss/train': 1.4269099235534668} 08/31/2021 02:29:18 - INFO - __main__ - Step 73778: {'lr': 0.0002617925152131138, 'samples': 14165376, 'steps': 73777, 'loss/train': 0.8548377752304077} 08/31/2021 02:29:18 - INFO - __main__ - Step 73779: {'lr': 0.0002617872143731898, 'samples': 14165568, 'steps': 73778, 'loss/train': 1.8001437187194824} 08/31/2021 02:29:19 - INFO - __main__ - Step 73780: {'lr': 0.0002617819135279546, 'samples': 14165760, 'steps': 73779, 'loss/train': 1.4610933065414429} 08/31/2021 02:29:20 - INFO - __main__ - Step 73781: {'lr': 0.00026177661267741067, 'samples': 14165952, 'steps': 73780, 'loss/train': 1.1961926221847534} 08/31/2021 02:29:21 - INFO - __main__ - Step 73782: {'lr': 0.0002617713118215604, 'samples': 14166144, 'steps': 73781, 'loss/train': 1.5453569889068604} 08/31/2021 02:29:21 - INFO - __main__ - Step 73783: {'lr': 0.0002617660109604061, 'samples': 14166336, 'steps': 73782, 'loss/train': 1.3461533784866333} 08/31/2021 02:29:21 - INFO - __main__ - Step 73784: {'lr': 0.0002617607100939503, 'samples': 14166528, 'steps': 73783, 'loss/train': 1.2008225917816162} 08/31/2021 02:29:22 - INFO - __main__ - Step 73785: {'lr': 0.00026175540922219526, 'samples': 14166720, 'steps': 73784, 'loss/train': 0.6829270124435425} 08/31/2021 02:29:23 - INFO - __main__ - Step 73786: {'lr': 0.0002617501083451434, 'samples': 14166912, 'steps': 73785, 'loss/train': 1.2620478868484497} 08/31/2021 02:29:24 - INFO - __main__ - Step 73787: {'lr': 0.0002617448074627971, 'samples': 14167104, 'steps': 73786, 'loss/train': 0.18901002407073975} 08/31/2021 02:29:24 - INFO - __main__ - Step 73788: {'lr': 0.0002617395065751588, 'samples': 14167296, 'steps': 73787, 'loss/train': 1.8826930522918701} 08/31/2021 02:29:24 - INFO - __main__ - Step 73789: {'lr': 0.00026173420568223086, 'samples': 14167488, 'steps': 73788, 'loss/train': 1.784773826599121} 08/31/2021 02:29:25 - INFO - __main__ - Step 73790: {'lr': 0.00026172890478401575, 'samples': 14167680, 'steps': 73789, 'loss/train': 1.388883352279663} 08/31/2021 02:29:26 - INFO - __main__ - Step 73791: {'lr': 0.0002617236038805157, 'samples': 14167872, 'steps': 73790, 'loss/train': 0.16555579006671906} 08/31/2021 02:29:27 - INFO - __main__ - Step 73792: {'lr': 0.0002617183029717332, 'samples': 14168064, 'steps': 73791, 'loss/train': 2.11197829246521} 08/31/2021 02:29:27 - INFO - __main__ - Step 73793: {'lr': 0.0002617130020576705, 'samples': 14168256, 'steps': 73792, 'loss/train': 1.3511031866073608} 08/31/2021 02:29:27 - INFO - __main__ - Step 73794: {'lr': 0.0002617077011383302, 'samples': 14168448, 'steps': 73793, 'loss/train': 0.7877046465873718} 08/31/2021 02:29:28 - INFO - __main__ - Step 73795: {'lr': 0.00026170240021371465, 'samples': 14168640, 'steps': 73794, 'loss/train': 1.604653239250183} 08/31/2021 02:29:29 - INFO - __main__ - Step 73796: {'lr': 0.00026169709928382614, 'samples': 14168832, 'steps': 73795, 'loss/train': 1.37043297290802} 08/31/2021 02:29:30 - INFO - __main__ - Step 73797: {'lr': 0.000261691798348667, 'samples': 14169024, 'steps': 73796, 'loss/train': 1.7283650636672974} 08/31/2021 02:29:30 - INFO - __main__ - Step 73798: {'lr': 0.0002616864974082398, 'samples': 14169216, 'steps': 73797, 'loss/train': 1.2980177402496338} 08/31/2021 02:29:30 - INFO - __main__ - Step 73799: {'lr': 0.0002616811964625468, 'samples': 14169408, 'steps': 73798, 'loss/train': 1.6521003246307373} 08/31/2021 02:29:31 - INFO - __main__ - Step 73800: {'lr': 0.0002616758955115905, 'samples': 14169600, 'steps': 73799, 'loss/train': 1.1861872673034668} 08/31/2021 02:29:32 - INFO - __main__ - Step 73801: {'lr': 0.0002616705945553732, 'samples': 14169792, 'steps': 73800, 'loss/train': 0.9784031510353088} 08/31/2021 02:29:33 - INFO - __main__ - Step 73802: {'lr': 0.0002616652935938973, 'samples': 14169984, 'steps': 73801, 'loss/train': 1.277580738067627} 08/31/2021 02:29:33 - INFO - __main__ - Step 73803: {'lr': 0.00026165999262716517, 'samples': 14170176, 'steps': 73802, 'loss/train': 1.9786510467529297} 08/31/2021 02:29:33 - INFO - __main__ - Step 73804: {'lr': 0.00026165469165517926, 'samples': 14170368, 'steps': 73803, 'loss/train': 1.0352262258529663} 08/31/2021 02:29:34 - INFO - __main__ - Step 73805: {'lr': 0.0002616493906779419, 'samples': 14170560, 'steps': 73804, 'loss/train': 0.4702782928943634} 08/31/2021 02:29:36 - INFO - __main__ - Step 73806: {'lr': 0.0002616440896954555, 'samples': 14170752, 'steps': 73805, 'loss/train': 1.2044671773910522} 08/31/2021 02:29:36 - INFO - __main__ - Step 73807: {'lr': 0.0002616387887077225, 'samples': 14170944, 'steps': 73806, 'loss/train': 1.7375907897949219} 08/31/2021 02:29:37 - INFO - __main__ - Step 73808: {'lr': 0.0002616334877147452, 'samples': 14171136, 'steps': 73807, 'loss/train': 1.7061854600906372} 08/31/2021 02:29:37 - INFO - __main__ - Step 73809: {'lr': 0.00026162818671652605, 'samples': 14171328, 'steps': 73808, 'loss/train': 1.5577641725540161} 08/31/2021 02:29:37 - INFO - __main__ - Step 73810: {'lr': 0.00026162288571306743, 'samples': 14171520, 'steps': 73809, 'loss/train': 0.20529255270957947} 08/31/2021 02:29:39 - INFO - __main__ - Step 73811: {'lr': 0.0002616175847043717, 'samples': 14171712, 'steps': 73810, 'loss/train': 1.133884072303772} 08/31/2021 02:29:40 - INFO - __main__ - Step 73812: {'lr': 0.0002616122836904412, 'samples': 14171904, 'steps': 73811, 'loss/train': 0.49002835154533386} 08/31/2021 02:29:40 - INFO - __main__ - Step 73813: {'lr': 0.00026160698267127855, 'samples': 14172096, 'steps': 73812, 'loss/train': 1.1900092363357544} 08/31/2021 02:29:40 - INFO - __main__ - Step 73814: {'lr': 0.00026160168164688583, 'samples': 14172288, 'steps': 73813, 'loss/train': 1.3685253858566284} 08/31/2021 02:29:41 - INFO - __main__ - Step 73815: {'lr': 0.0002615963806172656, 'samples': 14172480, 'steps': 73814, 'loss/train': 0.8190751075744629} 08/31/2021 02:29:41 - INFO - __main__ - Step 73816: {'lr': 0.0002615910795824202, 'samples': 14172672, 'steps': 73815, 'loss/train': 1.4313569068908691} 08/31/2021 02:29:42 - INFO - __main__ - Step 73817: {'lr': 0.0002615857785423521, 'samples': 14172864, 'steps': 73816, 'loss/train': 1.1611067056655884} 08/31/2021 02:29:43 - INFO - __main__ - Step 73818: {'lr': 0.0002615804774970636, 'samples': 14173056, 'steps': 73817, 'loss/train': 1.5956298112869263} 08/31/2021 02:29:43 - INFO - __main__ - Step 73819: {'lr': 0.0002615751764465571, 'samples': 14173248, 'steps': 73818, 'loss/train': 1.1503931283950806} 08/31/2021 02:29:43 - INFO - __main__ - Step 73820: {'lr': 0.00026156987539083503, 'samples': 14173440, 'steps': 73819, 'loss/train': 2.032027006149292} 08/31/2021 02:29:44 - INFO - __main__ - Step 73821: {'lr': 0.00026156457432989976, 'samples': 14173632, 'steps': 73820, 'loss/train': 1.1515074968338013} 08/31/2021 02:29:45 - INFO - __main__ - Step 73822: {'lr': 0.00026155927326375366, 'samples': 14173824, 'steps': 73821, 'loss/train': 2.725783109664917} 08/31/2021 02:29:46 - INFO - __main__ - Step 73823: {'lr': 0.0002615539721923991, 'samples': 14174016, 'steps': 73822, 'loss/train': 1.5660572052001953} 08/31/2021 02:29:46 - INFO - __main__ - Step 73824: {'lr': 0.00026154867111583853, 'samples': 14174208, 'steps': 73823, 'loss/train': 1.2334684133529663} 08/31/2021 02:29:47 - INFO - __main__ - Step 73825: {'lr': 0.0002615433700340743, 'samples': 14174400, 'steps': 73824, 'loss/train': 1.148677945137024} 08/31/2021 02:29:47 - INFO - __main__ - Step 73826: {'lr': 0.0002615380689471088, 'samples': 14174592, 'steps': 73825, 'loss/train': 1.292038083076477} 08/31/2021 02:29:49 - INFO - __main__ - Step 73827: {'lr': 0.0002615327678549445, 'samples': 14174784, 'steps': 73826, 'loss/train': 1.4168267250061035} 08/31/2021 02:29:49 - INFO - __main__ - Step 73828: {'lr': 0.0002615274667575836, 'samples': 14174976, 'steps': 73827, 'loss/train': 1.1404573917388916} 08/31/2021 02:29:49 - INFO - __main__ - Step 73829: {'lr': 0.00026152216565502863, 'samples': 14175168, 'steps': 73828, 'loss/train': 1.2019908428192139} 08/31/2021 02:29:50 - INFO - __main__ - Step 73830: {'lr': 0.00026151686454728196, 'samples': 14175360, 'steps': 73829, 'loss/train': 1.323311686515808} 08/31/2021 02:29:50 - INFO - __main__ - Step 73831: {'lr': 0.00026151156343434597, 'samples': 14175552, 'steps': 73830, 'loss/train': 1.011031150817871} 08/31/2021 02:29:52 - INFO - __main__ - Step 73832: {'lr': 0.000261506262316223, 'samples': 14175744, 'steps': 73831, 'loss/train': 1.8533097505569458} 08/31/2021 02:29:52 - INFO - __main__ - Step 73833: {'lr': 0.00026150096119291553, 'samples': 14175936, 'steps': 73832, 'loss/train': 1.077238917350769} 08/31/2021 02:29:53 - INFO - __main__ - Step 73834: {'lr': 0.00026149566006442596, 'samples': 14176128, 'steps': 73833, 'loss/train': 1.3821015357971191} 08/31/2021 02:29:53 - INFO - __main__ - Step 73835: {'lr': 0.00026149035893075655, 'samples': 14176320, 'steps': 73834, 'loss/train': 5.9289093017578125} 08/31/2021 02:29:54 - INFO - __main__ - Step 73836: {'lr': 0.00026148505779190976, 'samples': 14176512, 'steps': 73835, 'loss/train': 5.831814765930176} 08/31/2021 02:29:54 - INFO - __main__ - Step 73837: {'lr': 0.000261479756647888, 'samples': 14176704, 'steps': 73836, 'loss/train': 1.6832892894744873} 08/31/2021 02:29:54 - INFO - __main__ - Step 73838: {'lr': 0.00026147445549869365, 'samples': 14176896, 'steps': 73837, 'loss/train': 1.4737049341201782} 08/31/2021 02:29:56 - INFO - __main__ - Step 73839: {'lr': 0.00026146915434432905, 'samples': 14177088, 'steps': 73838, 'loss/train': 1.3945406675338745} 08/31/2021 02:29:56 - INFO - __main__ - Step 73840: {'lr': 0.0002614638531847967, 'samples': 14177280, 'steps': 73839, 'loss/train': 1.4646472930908203} 08/31/2021 02:29:56 - INFO - __main__ - Step 73841: {'lr': 0.0002614585520200989, 'samples': 14177472, 'steps': 73840, 'loss/train': 2.1116576194763184} 08/31/2021 02:29:57 - INFO - __main__ - Step 73842: {'lr': 0.00026145325085023797, 'samples': 14177664, 'steps': 73841, 'loss/train': 1.4613268375396729} 08/31/2021 02:29:57 - INFO - __main__ - Step 73843: {'lr': 0.00026144794967521644, 'samples': 14177856, 'steps': 73842, 'loss/train': 1.1738717555999756} 08/31/2021 02:29:59 - INFO - __main__ - Step 73844: {'lr': 0.0002614426484950366, 'samples': 14178048, 'steps': 73843, 'loss/train': 0.8902122378349304} 08/31/2021 02:29:59 - INFO - __main__ - Step 73845: {'lr': 0.0002614373473097009, 'samples': 14178240, 'steps': 73844, 'loss/train': 1.1666680574417114} 08/31/2021 02:30:00 - INFO - __main__ - Step 73846: {'lr': 0.0002614320461192117, 'samples': 14178432, 'steps': 73845, 'loss/train': 1.4232051372528076} 08/31/2021 02:30:00 - INFO - __main__ - Step 73847: {'lr': 0.0002614267449235715, 'samples': 14178624, 'steps': 73846, 'loss/train': 0.5855374932289124} 08/31/2021 02:30:00 - INFO - __main__ - Step 73848: {'lr': 0.00026142144372278255, 'samples': 14178816, 'steps': 73847, 'loss/train': 0.045180659741163254} 08/31/2021 02:30:02 - INFO - __main__ - Step 73849: {'lr': 0.0002614161425168472, 'samples': 14179008, 'steps': 73848, 'loss/train': 1.486304521560669} 08/31/2021 02:30:02 - INFO - __main__ - Step 73850: {'lr': 0.0002614108413057679, 'samples': 14179200, 'steps': 73849, 'loss/train': 1.740419864654541} 08/31/2021 02:30:02 - INFO - __main__ - Step 73851: {'lr': 0.00026140554008954707, 'samples': 14179392, 'steps': 73850, 'loss/train': 1.3689627647399902} 08/31/2021 02:30:03 - INFO - __main__ - Step 73852: {'lr': 0.00026140023886818707, 'samples': 14179584, 'steps': 73851, 'loss/train': 0.8620059490203857} 08/31/2021 02:30:03 - INFO - __main__ - Step 73853: {'lr': 0.0002613949376416904, 'samples': 14179776, 'steps': 73852, 'loss/train': 1.904212236404419} 08/31/2021 02:30:05 - INFO - __main__ - Step 73854: {'lr': 0.0002613896364100593, 'samples': 14179968, 'steps': 73853, 'loss/train': 1.2030514478683472} 08/31/2021 02:30:05 - INFO - __main__ - Step 73855: {'lr': 0.00026138433517329616, 'samples': 14180160, 'steps': 73854, 'loss/train': 1.289250373840332} 08/31/2021 02:30:05 - INFO - __main__ - Step 73856: {'lr': 0.00026137903393140343, 'samples': 14180352, 'steps': 73855, 'loss/train': 1.2093861103057861} 08/31/2021 02:30:06 - INFO - __main__ - Step 73857: {'lr': 0.00026137373268438345, 'samples': 14180544, 'steps': 73856, 'loss/train': 1.3708702325820923} 08/31/2021 02:30:06 - INFO - __main__ - Step 73858: {'lr': 0.0002613684314322387, 'samples': 14180736, 'steps': 73857, 'loss/train': 0.0716538280248642} 08/31/2021 02:30:09 - INFO - __main__ - Step 73859: {'lr': 0.00026136313017497147, 'samples': 14180928, 'steps': 73858, 'loss/train': 1.1288244724273682} 08/31/2021 02:30:09 - INFO - __main__ - Step 73860: {'lr': 0.00026135782891258423, 'samples': 14181120, 'steps': 73859, 'loss/train': 0.8251278400421143} 08/31/2021 02:30:09 - INFO - __main__ - Step 73861: {'lr': 0.00026135252764507934, 'samples': 14181312, 'steps': 73860, 'loss/train': 0.8456598520278931} 08/31/2021 02:30:10 - INFO - __main__ - Step 73862: {'lr': 0.0002613472263724591, 'samples': 14181504, 'steps': 73861, 'loss/train': 1.2823604345321655} 08/31/2021 02:30:10 - INFO - __main__ - Step 73863: {'lr': 0.00026134192509472603, 'samples': 14181696, 'steps': 73862, 'loss/train': 0.024358998984098434} 08/31/2021 02:30:10 - INFO - __main__ - Step 73864: {'lr': 0.00026133662381188245, 'samples': 14181888, 'steps': 73863, 'loss/train': 0.9260059595108032} 08/31/2021 02:30:12 - INFO - __main__ - Step 73865: {'lr': 0.00026133132252393075, 'samples': 14182080, 'steps': 73864, 'loss/train': 0.7063610553741455} 08/31/2021 02:30:13 - INFO - __main__ - Step 73866: {'lr': 0.0002613260212308733, 'samples': 14182272, 'steps': 73865, 'loss/train': 1.403633713722229} 08/31/2021 02:30:13 - INFO - __main__ - Step 73867: {'lr': 0.0002613207199327127, 'samples': 14182464, 'steps': 73866, 'loss/train': 1.4835249185562134} 08/31/2021 02:30:13 - INFO - __main__ - Step 73868: {'lr': 0.00026131541862945096, 'samples': 14182656, 'steps': 73867, 'loss/train': 1.101198434829712} 08/31/2021 02:30:14 - INFO - __main__ - Step 73869: {'lr': 0.0002613101173210907, 'samples': 14182848, 'steps': 73868, 'loss/train': 1.4433468580245972} 08/31/2021 02:30:15 - INFO - __main__ - Step 73870: {'lr': 0.00026130481600763437, 'samples': 14183040, 'steps': 73869, 'loss/train': 1.2971603870391846} 08/31/2021 02:30:16 - INFO - __main__ - Step 73871: {'lr': 0.00026129951468908415, 'samples': 14183232, 'steps': 73870, 'loss/train': 1.1570231914520264} 08/31/2021 02:30:16 - INFO - __main__ - Step 73872: {'lr': 0.0002612942133654426, 'samples': 14183424, 'steps': 73871, 'loss/train': 0.8168889880180359} 08/31/2021 02:30:16 - INFO - __main__ - Step 73873: {'lr': 0.00026128891203671203, 'samples': 14183616, 'steps': 73872, 'loss/train': 1.1657640933990479} 08/31/2021 02:30:17 - INFO - __main__ - Step 73874: {'lr': 0.00026128361070289484, 'samples': 14183808, 'steps': 73873, 'loss/train': 1.095201015472412} 08/31/2021 02:30:18 - INFO - __main__ - Step 73875: {'lr': 0.0002612783093639935, 'samples': 14184000, 'steps': 73874, 'loss/train': 0.9360285401344299} 08/31/2021 02:30:19 - INFO - __main__ - Step 73876: {'lr': 0.00026127300802001024, 'samples': 14184192, 'steps': 73875, 'loss/train': 1.1223633289337158} 08/31/2021 02:30:19 - INFO - __main__ - Step 73877: {'lr': 0.0002612677066709476, 'samples': 14184384, 'steps': 73876, 'loss/train': 0.7445254325866699} 08/31/2021 02:30:19 - INFO - __main__ - Step 73878: {'lr': 0.00026126240531680785, 'samples': 14184576, 'steps': 73877, 'loss/train': 1.0213710069656372} 08/31/2021 02:30:20 - INFO - __main__ - Step 73879: {'lr': 0.00026125710395759344, 'samples': 14184768, 'steps': 73878, 'loss/train': 1.1233543157577515} 08/31/2021 02:30:20 - INFO - __main__ - Step 73880: {'lr': 0.00026125180259330675, 'samples': 14184960, 'steps': 73879, 'loss/train': 0.8172473907470703} 08/31/2021 02:30:21 - INFO - __main__ - Step 73881: {'lr': 0.0002612465012239503, 'samples': 14185152, 'steps': 73880, 'loss/train': 1.306695818901062} 08/31/2021 02:30:22 - INFO - __main__ - Step 73882: {'lr': 0.0002612411998495262, 'samples': 14185344, 'steps': 73881, 'loss/train': 1.373853325843811} 08/31/2021 02:30:22 - INFO - __main__ - Step 73883: {'lr': 0.0002612358984700371, 'samples': 14185536, 'steps': 73882, 'loss/train': 1.3747271299362183} 08/31/2021 02:30:23 - INFO - __main__ - Step 73884: {'lr': 0.0002612305970854852, 'samples': 14185728, 'steps': 73883, 'loss/train': 0.05761390179395676} 08/31/2021 02:30:23 - INFO - __main__ - Step 73885: {'lr': 0.0002612252956958729, 'samples': 14185920, 'steps': 73884, 'loss/train': 1.4216020107269287} 08/31/2021 02:30:25 - INFO - __main__ - Step 73886: {'lr': 0.0002612199943012028, 'samples': 14186112, 'steps': 73885, 'loss/train': 1.3910605907440186} 08/31/2021 02:30:25 - INFO - __main__ - Step 73887: {'lr': 0.0002612146929014771, 'samples': 14186304, 'steps': 73886, 'loss/train': 1.417158603668213} 08/31/2021 02:30:26 - INFO - __main__ - Step 73888: {'lr': 0.0002612093914966982, 'samples': 14186496, 'steps': 73887, 'loss/train': 1.0179719924926758} 08/31/2021 02:30:26 - INFO - __main__ - Step 73889: {'lr': 0.00026120409008686854, 'samples': 14186688, 'steps': 73888, 'loss/train': 0.9636437892913818} 08/31/2021 02:30:26 - INFO - __main__ - Step 73890: {'lr': 0.0002611987886719905, 'samples': 14186880, 'steps': 73889, 'loss/train': 1.1145851612091064} 08/31/2021 02:30:28 - INFO - __main__ - Step 73891: {'lr': 0.00026119348725206644, 'samples': 14187072, 'steps': 73890, 'loss/train': 4.590820789337158} 08/31/2021 02:30:28 - INFO - __main__ - Step 73892: {'lr': 0.00026118818582709875, 'samples': 14187264, 'steps': 73891, 'loss/train': 2.024787187576294} 08/31/2021 02:30:29 - INFO - __main__ - Step 73893: {'lr': 0.0002611828843970898, 'samples': 14187456, 'steps': 73892, 'loss/train': 1.871503233909607} 08/31/2021 02:30:29 - INFO - __main__ - Step 73894: {'lr': 0.00026117758296204216, 'samples': 14187648, 'steps': 73893, 'loss/train': 1.2066466808319092} 08/31/2021 02:30:29 - INFO - __main__ - Step 73895: {'lr': 0.000261172281521958, 'samples': 14187840, 'steps': 73894, 'loss/train': 0.830182671546936} 08/31/2021 02:30:30 - INFO - __main__ - Step 73896: {'lr': 0.00026116698007683974, 'samples': 14188032, 'steps': 73895, 'loss/train': 0.5352442860603333} 08/31/2021 02:30:31 - INFO - __main__ - Step 73897: {'lr': 0.0002611616786266898, 'samples': 14188224, 'steps': 73896, 'loss/train': 1.7775663137435913} 08/31/2021 02:30:31 - INFO - __main__ - Step 73898: {'lr': 0.0002611563771715106, 'samples': 14188416, 'steps': 73897, 'loss/train': 0.8964123129844666} 08/31/2021 02:30:32 - INFO - __main__ - Step 73899: {'lr': 0.0002611510757113045, 'samples': 14188608, 'steps': 73898, 'loss/train': 1.6776198148727417} 08/31/2021 02:30:32 - INFO - __main__ - Step 73900: {'lr': 0.000261145774246074, 'samples': 14188800, 'steps': 73899, 'loss/train': 1.4394989013671875} 08/31/2021 02:30:32 - INFO - __main__ - Step 73901: {'lr': 0.0002611404727758213, 'samples': 14188992, 'steps': 73900, 'loss/train': 1.169190526008606} 08/31/2021 02:30:34 - INFO - __main__ - Step 73902: {'lr': 0.0002611351713005489, 'samples': 14189184, 'steps': 73901, 'loss/train': 1.2821696996688843} 08/31/2021 02:30:34 - INFO - __main__ - Step 73903: {'lr': 0.00026112986982025914, 'samples': 14189376, 'steps': 73902, 'loss/train': 1.399035096168518} 08/31/2021 02:30:35 - INFO - __main__ - Step 73904: {'lr': 0.00026112456833495446, 'samples': 14189568, 'steps': 73903, 'loss/train': 1.2174960374832153} 08/31/2021 02:30:35 - INFO - __main__ - Step 73905: {'lr': 0.0002611192668446372, 'samples': 14189760, 'steps': 73904, 'loss/train': 1.7139909267425537} 08/31/2021 02:30:35 - INFO - __main__ - Step 73906: {'lr': 0.00026111396534930976, 'samples': 14189952, 'steps': 73905, 'loss/train': 0.9418984055519104} 08/31/2021 02:30:37 - INFO - __main__ - Step 73907: {'lr': 0.00026110866384897457, 'samples': 14190144, 'steps': 73906, 'loss/train': 1.4088343381881714} 08/31/2021 02:30:37 - INFO - __main__ - Step 73908: {'lr': 0.000261103362343634, 'samples': 14190336, 'steps': 73907, 'loss/train': 1.4929753541946411} 08/31/2021 02:30:38 - INFO - __main__ - Step 73909: {'lr': 0.00026109806083329036, 'samples': 14190528, 'steps': 73908, 'loss/train': 1.3448928594589233} 08/31/2021 02:30:38 - INFO - __main__ - Step 73910: {'lr': 0.0002610927593179461, 'samples': 14190720, 'steps': 73909, 'loss/train': 0.9630615711212158} 08/31/2021 02:30:38 - INFO - __main__ - Step 73911: {'lr': 0.00026108745779760366, 'samples': 14190912, 'steps': 73910, 'loss/train': 1.5219454765319824} 08/31/2021 02:30:40 - INFO - __main__ - Step 73912: {'lr': 0.0002610821562722654, 'samples': 14191104, 'steps': 73911, 'loss/train': 2.6952075958251953} 08/31/2021 02:30:40 - INFO - __main__ - Step 73913: {'lr': 0.0002610768547419337, 'samples': 14191296, 'steps': 73912, 'loss/train': 1.728877067565918} 08/31/2021 02:30:41 - INFO - __main__ - Step 73914: {'lr': 0.0002610715532066109, 'samples': 14191488, 'steps': 73913, 'loss/train': 1.026764988899231} 08/31/2021 02:30:41 - INFO - __main__ - Step 73915: {'lr': 0.0002610662516662994, 'samples': 14191680, 'steps': 73914, 'loss/train': 1.1898515224456787} 08/31/2021 02:30:41 - INFO - __main__ - Step 73916: {'lr': 0.00026106095012100165, 'samples': 14191872, 'steps': 73915, 'loss/train': 1.181313395500183} 08/31/2021 02:30:43 - INFO - __main__ - Step 73917: {'lr': 0.0002610556485707201, 'samples': 14192064, 'steps': 73916, 'loss/train': 1.6391315460205078} 08/31/2021 02:30:44 - INFO - __main__ - Step 73918: {'lr': 0.00026105034701545687, 'samples': 14192256, 'steps': 73917, 'loss/train': 1.5900299549102783} 08/31/2021 02:30:44 - INFO - __main__ - Step 73919: {'lr': 0.0002610450454552147, 'samples': 14192448, 'steps': 73918, 'loss/train': 1.178785800933838} 08/31/2021 02:30:45 - INFO - __main__ - Step 73920: {'lr': 0.0002610397438899957, 'samples': 14192640, 'steps': 73919, 'loss/train': 1.3505150079727173} 08/31/2021 02:30:45 - INFO - __main__ - Step 73921: {'lr': 0.0002610344423198023, 'samples': 14192832, 'steps': 73920, 'loss/train': 0.21900467574596405} 08/31/2021 02:30:46 - INFO - __main__ - Step 73922: {'lr': 0.00026102914074463705, 'samples': 14193024, 'steps': 73921, 'loss/train': 1.850195288658142} 08/31/2021 02:30:47 - INFO - __main__ - Step 73923: {'lr': 0.00026102383916450225, 'samples': 14193216, 'steps': 73922, 'loss/train': 1.5462607145309448} 08/31/2021 02:30:47 - INFO - __main__ - Step 73924: {'lr': 0.0002610185375794002, 'samples': 14193408, 'steps': 73923, 'loss/train': 0.8502938151359558} 08/31/2021 02:30:47 - INFO - __main__ - Step 73925: {'lr': 0.0002610132359893335, 'samples': 14193600, 'steps': 73924, 'loss/train': 2.1641135215759277} 08/31/2021 02:30:48 - INFO - __main__ - Step 73926: {'lr': 0.0002610079343943043, 'samples': 14193792, 'steps': 73925, 'loss/train': 0.752824068069458} 08/31/2021 02:30:48 - INFO - __main__ - Step 73927: {'lr': 0.0002610026327943151, 'samples': 14193984, 'steps': 73926, 'loss/train': 0.7637747526168823} 08/31/2021 02:30:50 - INFO - __main__ - Step 73928: {'lr': 0.00026099733118936826, 'samples': 14194176, 'steps': 73927, 'loss/train': 1.119149088859558} 08/31/2021 02:30:50 - INFO - __main__ - Step 73929: {'lr': 0.0002609920295794662, 'samples': 14194368, 'steps': 73928, 'loss/train': 1.233834981918335} 08/31/2021 02:30:50 - INFO - __main__ - Step 73930: {'lr': 0.00026098672796461144, 'samples': 14194560, 'steps': 73929, 'loss/train': 1.261284589767456} 08/31/2021 02:30:51 - INFO - __main__ - Step 73931: {'lr': 0.0002609814263448061, 'samples': 14194752, 'steps': 73930, 'loss/train': 1.161221981048584} 08/31/2021 02:30:51 - INFO - __main__ - Step 73932: {'lr': 0.00026097612472005265, 'samples': 14194944, 'steps': 73931, 'loss/train': 0.11707206070423126} 08/31/2021 02:30:53 - INFO - __main__ - Step 73933: {'lr': 0.00026097082309035365, 'samples': 14195136, 'steps': 73932, 'loss/train': 0.999501645565033} 08/31/2021 02:30:53 - INFO - __main__ - Step 73934: {'lr': 0.0002609655214557113, 'samples': 14195328, 'steps': 73933, 'loss/train': 0.6262899041175842} 08/31/2021 02:30:53 - INFO - __main__ - Step 73935: {'lr': 0.0002609602198161281, 'samples': 14195520, 'steps': 73934, 'loss/train': 1.065865159034729} 08/31/2021 02:30:54 - INFO - __main__ - Step 73936: {'lr': 0.00026095491817160633, 'samples': 14195712, 'steps': 73935, 'loss/train': 1.6258260011672974} 08/31/2021 02:30:54 - INFO - __main__ - Step 73937: {'lr': 0.0002609496165221485, 'samples': 14195904, 'steps': 73936, 'loss/train': 0.9063222408294678} 08/31/2021 02:30:56 - INFO - __main__ - Step 73938: {'lr': 0.0002609443148677569, 'samples': 14196096, 'steps': 73937, 'loss/train': 1.342504858970642} 08/31/2021 02:30:56 - INFO - __main__ - Step 73939: {'lr': 0.00026093901320843393, 'samples': 14196288, 'steps': 73938, 'loss/train': 1.181039810180664} 08/31/2021 02:30:56 - INFO - __main__ - Step 73940: {'lr': 0.00026093371154418206, 'samples': 14196480, 'steps': 73939, 'loss/train': 0.7562289834022522} 08/31/2021 02:30:57 - INFO - __main__ - Step 73941: {'lr': 0.0002609284098750037, 'samples': 14196672, 'steps': 73940, 'loss/train': 1.1657058000564575} 08/31/2021 02:30:57 - INFO - __main__ - Step 73942: {'lr': 0.000260923108200901, 'samples': 14196864, 'steps': 73941, 'loss/train': 1.4818100929260254} 08/31/2021 02:30:59 - INFO - __main__ - Step 73943: {'lr': 0.0002609178065218766, 'samples': 14197056, 'steps': 73942, 'loss/train': 0.8296200633049011} 08/31/2021 02:30:59 - INFO - __main__ - Step 73944: {'lr': 0.0002609125048379329, 'samples': 14197248, 'steps': 73943, 'loss/train': 1.0184749364852905} 08/31/2021 02:31:00 - INFO - __main__ - Step 73945: {'lr': 0.00026090720314907206, 'samples': 14197440, 'steps': 73944, 'loss/train': 1.2780860662460327} 08/31/2021 02:31:00 - INFO - __main__ - Step 73946: {'lr': 0.00026090190145529665, 'samples': 14197632, 'steps': 73945, 'loss/train': 1.7436784505844116} 08/31/2021 02:31:00 - INFO - __main__ - Step 73947: {'lr': 0.000260896599756609, 'samples': 14197824, 'steps': 73946, 'loss/train': 0.5255002379417419} 08/31/2021 02:31:02 - INFO - __main__ - Step 73948: {'lr': 0.00026089129805301155, 'samples': 14198016, 'steps': 73947, 'loss/train': 1.0919413566589355} 08/31/2021 02:31:02 - INFO - __main__ - Step 73949: {'lr': 0.0002608859963445066, 'samples': 14198208, 'steps': 73948, 'loss/train': 1.3433032035827637} 08/31/2021 02:31:03 - INFO - __main__ - Step 73950: {'lr': 0.0002608806946310966, 'samples': 14198400, 'steps': 73949, 'loss/train': 1.6750919818878174} 08/31/2021 02:31:03 - INFO - __main__ - Step 73951: {'lr': 0.00026087539291278395, 'samples': 14198592, 'steps': 73950, 'loss/train': 1.5064936876296997} 08/31/2021 02:31:03 - INFO - __main__ - Step 73952: {'lr': 0.000260870091189571, 'samples': 14198784, 'steps': 73951, 'loss/train': 1.5701252222061157} 08/31/2021 02:31:05 - INFO - __main__ - Step 73953: {'lr': 0.00026086478946146015, 'samples': 14198976, 'steps': 73952, 'loss/train': 1.1929501295089722} 08/31/2021 02:31:05 - INFO - __main__ - Step 73954: {'lr': 0.00026085948772845377, 'samples': 14199168, 'steps': 73953, 'loss/train': 0.9577845931053162} 08/31/2021 02:31:05 - INFO - __main__ - Step 73955: {'lr': 0.0002608541859905543, 'samples': 14199360, 'steps': 73954, 'loss/train': 1.4301364421844482} 08/31/2021 02:31:06 - INFO - __main__ - Step 73956: {'lr': 0.00026084888424776414, 'samples': 14199552, 'steps': 73955, 'loss/train': 0.49926912784576416} 08/31/2021 02:31:06 - INFO - __main__ - Step 73957: {'lr': 0.0002608435825000856, 'samples': 14199744, 'steps': 73956, 'loss/train': 0.7171154618263245} 08/31/2021 02:31:08 - INFO - __main__ - Step 73958: {'lr': 0.0002608382807475211, 'samples': 14199936, 'steps': 73957, 'loss/train': 0.6856456995010376} 08/31/2021 02:31:08 - INFO - __main__ - Step 73959: {'lr': 0.00026083297899007305, 'samples': 14200128, 'steps': 73958, 'loss/train': 1.0891913175582886} 08/31/2021 02:31:09 - INFO - __main__ - Step 73960: {'lr': 0.0002608276772277438, 'samples': 14200320, 'steps': 73959, 'loss/train': 0.2640734314918518} 08/31/2021 02:31:09 - INFO - __main__ - Step 73961: {'lr': 0.00026082237546053584, 'samples': 14200512, 'steps': 73960, 'loss/train': 0.9626652002334595} 08/31/2021 02:31:09 - INFO - __main__ - Step 73962: {'lr': 0.00026081707368845144, 'samples': 14200704, 'steps': 73961, 'loss/train': 1.1123833656311035} 08/31/2021 02:31:10 - INFO - __main__ - Step 73963: {'lr': 0.000260811771911493, 'samples': 14200896, 'steps': 73962, 'loss/train': 1.3118594884872437} 08/31/2021 02:31:11 - INFO - __main__ - Step 73964: {'lr': 0.00026080647012966294, 'samples': 14201088, 'steps': 73963, 'loss/train': 0.048953570425510406} 08/31/2021 02:31:12 - INFO - __main__ - Step 73965: {'lr': 0.0002608011683429637, 'samples': 14201280, 'steps': 73964, 'loss/train': 0.49654385447502136} 08/31/2021 02:31:12 - INFO - __main__ - Step 73966: {'lr': 0.0002607958665513976, 'samples': 14201472, 'steps': 73965, 'loss/train': 1.5309562683105469} 08/31/2021 02:31:12 - INFO - __main__ - Step 73967: {'lr': 0.000260790564754967, 'samples': 14201664, 'steps': 73966, 'loss/train': 1.1891064643859863} 08/31/2021 02:31:13 - INFO - __main__ - Step 73968: {'lr': 0.0002607852629536745, 'samples': 14201856, 'steps': 73967, 'loss/train': 0.8165427446365356} 08/31/2021 02:31:15 - INFO - __main__ - Step 73969: {'lr': 0.0002607799611475222, 'samples': 14202048, 'steps': 73968, 'loss/train': 0.8836376070976257} 08/31/2021 02:31:15 - INFO - __main__ - Step 73970: {'lr': 0.0002607746593365126, 'samples': 14202240, 'steps': 73969, 'loss/train': 6.3906378746032715} 08/31/2021 02:31:16 - INFO - __main__ - Step 73971: {'lr': 0.0002607693575206481, 'samples': 14202432, 'steps': 73970, 'loss/train': 1.6186350584030151} 08/31/2021 02:31:16 - INFO - __main__ - Step 73972: {'lr': 0.0002607640556999312, 'samples': 14202624, 'steps': 73971, 'loss/train': 1.5782177448272705} 08/31/2021 02:31:16 - INFO - __main__ - Step 73973: {'lr': 0.00026075875387436407, 'samples': 14202816, 'steps': 73972, 'loss/train': 1.235352873802185} 08/31/2021 02:31:18 - INFO - __main__ - Step 73974: {'lr': 0.0002607534520439492, 'samples': 14203008, 'steps': 73973, 'loss/train': 1.2223906517028809} 08/31/2021 02:31:18 - INFO - __main__ - Step 73975: {'lr': 0.0002607481502086891, 'samples': 14203200, 'steps': 73974, 'loss/train': 0.7911155223846436} 08/31/2021 02:31:19 - INFO - __main__ - Step 73976: {'lr': 0.00026074284836858605, 'samples': 14203392, 'steps': 73975, 'loss/train': 1.7591416835784912} 08/31/2021 02:31:19 - INFO - __main__ - Step 73977: {'lr': 0.00026073754652364235, 'samples': 14203584, 'steps': 73976, 'loss/train': 1.6659607887268066} 08/31/2021 02:31:19 - INFO - __main__ - Step 73978: {'lr': 0.00026073224467386056, 'samples': 14203776, 'steps': 73977, 'loss/train': 1.4790618419647217} 08/31/2021 02:31:21 - INFO - __main__ - Step 73979: {'lr': 0.00026072694281924284, 'samples': 14203968, 'steps': 73978, 'loss/train': 0.9175165891647339} 08/31/2021 02:31:21 - INFO - __main__ - Step 73980: {'lr': 0.00026072164095979186, 'samples': 14204160, 'steps': 73979, 'loss/train': 1.6569547653198242} 08/31/2021 02:31:21 - INFO - __main__ - Step 73981: {'lr': 0.00026071633909550984, 'samples': 14204352, 'steps': 73980, 'loss/train': 1.1709442138671875} 08/31/2021 02:31:22 - INFO - __main__ - Step 73982: {'lr': 0.0002607110372263992, 'samples': 14204544, 'steps': 73981, 'loss/train': 1.225095272064209} 08/31/2021 02:31:22 - INFO - __main__ - Step 73983: {'lr': 0.0002607057353524623, 'samples': 14204736, 'steps': 73982, 'loss/train': 1.5249500274658203} 08/31/2021 02:31:22 - INFO - __main__ - Step 73984: {'lr': 0.00026070043347370164, 'samples': 14204928, 'steps': 73983, 'loss/train': 1.4460567235946655} 08/31/2021 02:31:24 - INFO - __main__ - Step 73985: {'lr': 0.00026069513159011947, 'samples': 14205120, 'steps': 73984, 'loss/train': 0.7060475945472717} 08/31/2021 02:31:24 - INFO - __main__ - Step 73986: {'lr': 0.00026068982970171823, 'samples': 14205312, 'steps': 73985, 'loss/train': 0.7789646983146667} 08/31/2021 02:31:25 - INFO - __main__ - Step 73987: {'lr': 0.0002606845278085003, 'samples': 14205504, 'steps': 73986, 'loss/train': 1.729158878326416} 08/31/2021 02:31:25 - INFO - __main__ - Step 73988: {'lr': 0.0002606792259104682, 'samples': 14205696, 'steps': 73987, 'loss/train': 1.0413521528244019} 08/31/2021 02:31:25 - INFO - __main__ - Step 73989: {'lr': 0.0002606739240076241, 'samples': 14205888, 'steps': 73988, 'loss/train': 1.2550451755523682} 08/31/2021 02:31:27 - INFO - __main__ - Step 73990: {'lr': 0.00026066862209997053, 'samples': 14206080, 'steps': 73989, 'loss/train': 1.2193834781646729} 08/31/2021 02:31:27 - INFO - __main__ - Step 73991: {'lr': 0.0002606633201875098, 'samples': 14206272, 'steps': 73990, 'loss/train': 0.6498138308525085} 08/31/2021 02:31:28 - INFO - __main__ - Step 73992: {'lr': 0.00026065801827024446, 'samples': 14206464, 'steps': 73991, 'loss/train': 1.2237482070922852} 08/31/2021 02:31:28 - INFO - __main__ - Step 73993: {'lr': 0.0002606527163481767, 'samples': 14206656, 'steps': 73992, 'loss/train': 0.4508155286312103} 08/31/2021 02:31:28 - INFO - __main__ - Step 73994: {'lr': 0.000260647414421309, 'samples': 14206848, 'steps': 73993, 'loss/train': 1.2881873846054077} 08/31/2021 02:31:30 - INFO - __main__ - Step 73995: {'lr': 0.0002606421124896437, 'samples': 14207040, 'steps': 73994, 'loss/train': 1.2763397693634033} 08/31/2021 02:31:31 - INFO - __main__ - Step 73996: {'lr': 0.0002606368105531833, 'samples': 14207232, 'steps': 73995, 'loss/train': 1.1651827096939087} 08/31/2021 02:31:31 - INFO - __main__ - Step 73997: {'lr': 0.00026063150861193, 'samples': 14207424, 'steps': 73996, 'loss/train': 0.6725418567657471} 08/31/2021 02:31:31 - INFO - __main__ - Step 73998: {'lr': 0.0002606262066658864, 'samples': 14207616, 'steps': 73997, 'loss/train': 1.057037115097046} 08/31/2021 02:31:32 - INFO - __main__ - Step 73999: {'lr': 0.0002606209047150548, 'samples': 14207808, 'steps': 73998, 'loss/train': 1.481551170349121} 08/31/2021 02:31:32 - INFO - __main__ - Step 74000: {'lr': 0.00026061560275943753, 'samples': 14208000, 'steps': 73999, 'loss/train': 0.7740755677223206} 08/31/2021 02:31:34 - INFO - __main__ - Step 74001: {'lr': 0.0002606103007990371, 'samples': 14208192, 'steps': 74000, 'loss/train': 1.7094199657440186} 08/31/2021 02:31:34 - INFO - __main__ - Step 74002: {'lr': 0.0002606049988338558, 'samples': 14208384, 'steps': 74001, 'loss/train': 1.5051710605621338} 08/31/2021 02:31:34 - INFO - __main__ - Step 74003: {'lr': 0.00026059969686389605, 'samples': 14208576, 'steps': 74002, 'loss/train': 1.1953773498535156} 08/31/2021 02:31:35 - INFO - __main__ - Step 74004: {'lr': 0.0002605943948891603, 'samples': 14208768, 'steps': 74003, 'loss/train': 0.6325957775115967} 08/31/2021 02:31:35 - INFO - __main__ - Step 74005: {'lr': 0.00026058909290965077, 'samples': 14208960, 'steps': 74004, 'loss/train': 1.2574266195297241} 08/31/2021 02:31:37 - INFO - __main__ - Step 74006: {'lr': 0.00026058379092537, 'samples': 14209152, 'steps': 74005, 'loss/train': 0.22851593792438507} 08/31/2021 02:31:37 - INFO - __main__ - Step 74007: {'lr': 0.0002605784889363203, 'samples': 14209344, 'steps': 74006, 'loss/train': 1.0402852296829224} 08/31/2021 02:31:38 - INFO - __main__ - Step 74008: {'lr': 0.00026057318694250423, 'samples': 14209536, 'steps': 74007, 'loss/train': 1.3524913787841797} 08/31/2021 02:31:38 - INFO - __main__ - Step 74009: {'lr': 0.0002605678849439239, 'samples': 14209728, 'steps': 74008, 'loss/train': 0.7258417010307312} 08/31/2021 02:31:38 - INFO - __main__ - Step 74010: {'lr': 0.00026056258294058186, 'samples': 14209920, 'steps': 74009, 'loss/train': 1.9828816652297974} 08/31/2021 02:31:40 - INFO - __main__ - Step 74011: {'lr': 0.00026055728093248053, 'samples': 14210112, 'steps': 74010, 'loss/train': 1.1043078899383545} 08/31/2021 02:31:40 - INFO - __main__ - Step 74012: {'lr': 0.0002605519789196223, 'samples': 14210304, 'steps': 74011, 'loss/train': 0.8496440649032593} 08/31/2021 02:31:41 - INFO - __main__ - Step 74013: {'lr': 0.0002605466769020094, 'samples': 14210496, 'steps': 74012, 'loss/train': 1.2981594800949097} 08/31/2021 02:31:41 - INFO - __main__ - Step 74014: {'lr': 0.0002605413748796444, 'samples': 14210688, 'steps': 74013, 'loss/train': 1.2458906173706055} 08/31/2021 02:31:41 - INFO - __main__ - Step 74015: {'lr': 0.0002605360728525297, 'samples': 14210880, 'steps': 74014, 'loss/train': 1.0526009798049927} 08/31/2021 02:31:43 - INFO - __main__ - Step 74016: {'lr': 0.00026053077082066747, 'samples': 14211072, 'steps': 74015, 'loss/train': 1.1824458837509155} 08/31/2021 02:31:43 - INFO - __main__ - Step 74017: {'lr': 0.00026052546878406024, 'samples': 14211264, 'steps': 74016, 'loss/train': 1.3683913946151733} 08/31/2021 02:31:44 - INFO - __main__ - Step 74018: {'lr': 0.00026052016674271044, 'samples': 14211456, 'steps': 74017, 'loss/train': 1.3052107095718384} 08/31/2021 02:31:44 - INFO - __main__ - Step 74019: {'lr': 0.0002605148646966204, 'samples': 14211648, 'steps': 74018, 'loss/train': 0.5575474500656128} 08/31/2021 02:31:45 - INFO - __main__ - Step 74020: {'lr': 0.00026050956264579256, 'samples': 14211840, 'steps': 74019, 'loss/train': 1.1713911294937134} 08/31/2021 02:31:45 - INFO - __main__ - Step 74021: {'lr': 0.00026050426059022924, 'samples': 14212032, 'steps': 74020, 'loss/train': 1.2566475868225098} 08/31/2021 02:31:47 - INFO - __main__ - Step 74022: {'lr': 0.0002604989585299329, 'samples': 14212224, 'steps': 74021, 'loss/train': 0.825547456741333} 08/31/2021 02:31:47 - INFO - __main__ - Step 74023: {'lr': 0.00026049365646490586, 'samples': 14212416, 'steps': 74022, 'loss/train': 1.1268993616104126} 08/31/2021 02:31:48 - INFO - __main__ - Step 74024: {'lr': 0.0002604883543951505, 'samples': 14212608, 'steps': 74023, 'loss/train': 0.7658182382583618} 08/31/2021 02:31:48 - INFO - __main__ - Step 74025: {'lr': 0.00026048305232066933, 'samples': 14212800, 'steps': 74024, 'loss/train': 1.2816181182861328} 08/31/2021 02:31:48 - INFO - __main__ - Step 74026: {'lr': 0.0002604777502414646, 'samples': 14212992, 'steps': 74025, 'loss/train': 0.9278843998908997} 08/31/2021 02:31:50 - INFO - __main__ - Step 74027: {'lr': 0.0002604724481575388, 'samples': 14213184, 'steps': 74026, 'loss/train': 1.4079536199569702} 08/31/2021 02:31:51 - INFO - __main__ - Step 74028: {'lr': 0.00026046714606889424, 'samples': 14213376, 'steps': 74027, 'loss/train': 1.2861645221710205} 08/31/2021 02:31:51 - INFO - __main__ - Step 74029: {'lr': 0.0002604618439755334, 'samples': 14213568, 'steps': 74028, 'loss/train': 1.2306700944900513} 08/31/2021 02:31:51 - INFO - __main__ - Step 74030: {'lr': 0.00026045654187745854, 'samples': 14213760, 'steps': 74029, 'loss/train': 1.5019687414169312} 08/31/2021 02:31:52 - INFO - __main__ - Step 74031: {'lr': 0.00026045123977467215, 'samples': 14213952, 'steps': 74030, 'loss/train': 0.14596952497959137} 08/31/2021 02:31:53 - INFO - __main__ - Step 74032: {'lr': 0.0002604459376671766, 'samples': 14214144, 'steps': 74031, 'loss/train': 1.257666826248169} 08/31/2021 02:31:54 - INFO - __main__ - Step 74033: {'lr': 0.0002604406355549743, 'samples': 14214336, 'steps': 74032, 'loss/train': 1.4222900867462158} 08/31/2021 02:31:54 - INFO - __main__ - Step 74034: {'lr': 0.0002604353334380675, 'samples': 14214528, 'steps': 74033, 'loss/train': 1.3001012802124023} 08/31/2021 02:31:54 - INFO - __main__ - Step 74035: {'lr': 0.0002604300313164589, 'samples': 14214720, 'steps': 74034, 'loss/train': 0.03893143683671951} 08/31/2021 02:31:55 - INFO - __main__ - Step 74036: {'lr': 0.0002604247291901505, 'samples': 14214912, 'steps': 74035, 'loss/train': 0.8447965383529663} 08/31/2021 02:31:56 - INFO - __main__ - Step 74037: {'lr': 0.000260419427059145, 'samples': 14215104, 'steps': 74036, 'loss/train': 1.1808736324310303} 08/31/2021 02:31:57 - INFO - __main__ - Step 74038: {'lr': 0.00026041412492344457, 'samples': 14215296, 'steps': 74037, 'loss/train': 0.8264582753181458} 08/31/2021 02:31:57 - INFO - __main__ - Step 74039: {'lr': 0.00026040882278305176, 'samples': 14215488, 'steps': 74038, 'loss/train': 1.4115175008773804} 08/31/2021 02:31:57 - INFO - __main__ - Step 74040: {'lr': 0.00026040352063796886, 'samples': 14215680, 'steps': 74039, 'loss/train': 1.1111233234405518} 08/31/2021 02:31:58 - INFO - __main__ - Step 74041: {'lr': 0.00026039821848819835, 'samples': 14215872, 'steps': 74040, 'loss/train': 0.030801093205809593} 08/31/2021 02:31:59 - INFO - __main__ - Step 74042: {'lr': 0.0002603929163337425, 'samples': 14216064, 'steps': 74041, 'loss/train': 1.3927736282348633} 08/31/2021 02:32:00 - INFO - __main__ - Step 74043: {'lr': 0.0002603876141746038, 'samples': 14216256, 'steps': 74042, 'loss/train': 1.789008378982544} 08/31/2021 02:32:00 - INFO - __main__ - Step 74044: {'lr': 0.0002603823120107846, 'samples': 14216448, 'steps': 74043, 'loss/train': 0.801303505897522} 08/31/2021 02:32:01 - INFO - __main__ - Step 74045: {'lr': 0.00026037700984228725, 'samples': 14216640, 'steps': 74044, 'loss/train': 1.21528959274292} 08/31/2021 02:32:01 - INFO - __main__ - Step 74046: {'lr': 0.00026037170766911424, 'samples': 14216832, 'steps': 74045, 'loss/train': 1.0768513679504395} 08/31/2021 02:32:02 - INFO - __main__ - Step 74047: {'lr': 0.00026036640549126784, 'samples': 14217024, 'steps': 74046, 'loss/train': 0.9648885130882263} 08/31/2021 02:32:03 - INFO - __main__ - Step 74048: {'lr': 0.0002603611033087506, 'samples': 14217216, 'steps': 74047, 'loss/train': 1.3445439338684082} 08/31/2021 02:32:03 - INFO - __main__ - Step 74049: {'lr': 0.0002603558011215647, 'samples': 14217408, 'steps': 74048, 'loss/train': 1.1111326217651367} 08/31/2021 02:32:04 - INFO - __main__ - Step 74050: {'lr': 0.0002603504989297126, 'samples': 14217600, 'steps': 74049, 'loss/train': 0.8405225276947021} 08/31/2021 02:32:04 - INFO - __main__ - Step 74051: {'lr': 0.00026034519673319683, 'samples': 14217792, 'steps': 74050, 'loss/train': 1.1282851696014404} 08/31/2021 02:32:06 - INFO - __main__ - Step 74052: {'lr': 0.00026033989453201964, 'samples': 14217984, 'steps': 74051, 'loss/train': 1.4279917478561401} 08/31/2021 02:32:06 - INFO - __main__ - Step 74053: {'lr': 0.0002603345923261835, 'samples': 14218176, 'steps': 74052, 'loss/train': 0.9985830187797546} 08/31/2021 02:32:06 - INFO - __main__ - Step 74054: {'lr': 0.0002603292901156907, 'samples': 14218368, 'steps': 74053, 'loss/train': 1.6589767932891846} 08/31/2021 02:32:07 - INFO - __main__ - Step 74055: {'lr': 0.00026032398790054367, 'samples': 14218560, 'steps': 74054, 'loss/train': 1.1453149318695068} 08/31/2021 02:32:07 - INFO - __main__ - Step 74056: {'lr': 0.0002603186856807448, 'samples': 14218752, 'steps': 74055, 'loss/train': 1.7727367877960205} 08/31/2021 02:32:08 - INFO - __main__ - Step 74057: {'lr': 0.00026031338345629653, 'samples': 14218944, 'steps': 74056, 'loss/train': 1.7840040922164917} 08/31/2021 02:32:09 - INFO - __main__ - Step 74058: {'lr': 0.0002603080812272012, 'samples': 14219136, 'steps': 74057, 'loss/train': 1.731192946434021} 08/31/2021 02:32:10 - INFO - __main__ - Step 74059: {'lr': 0.0002603027789934612, 'samples': 14219328, 'steps': 74058, 'loss/train': 1.79788339138031} 08/31/2021 02:32:10 - INFO - __main__ - Step 74060: {'lr': 0.00026029747675507893, 'samples': 14219520, 'steps': 74059, 'loss/train': 1.3937917947769165} 08/31/2021 02:32:10 - INFO - __main__ - Step 74061: {'lr': 0.0002602921745120568, 'samples': 14219712, 'steps': 74060, 'loss/train': 1.027349591255188} 08/31/2021 02:32:11 - INFO - __main__ - Step 74062: {'lr': 0.00026028687226439714, 'samples': 14219904, 'steps': 74061, 'loss/train': 1.5054720640182495} 08/31/2021 02:32:12 - INFO - __main__ - Step 74063: {'lr': 0.00026028157001210236, 'samples': 14220096, 'steps': 74062, 'loss/train': 1.018439769744873} 08/31/2021 02:32:13 - INFO - __main__ - Step 74064: {'lr': 0.00026027626775517495, 'samples': 14220288, 'steps': 74063, 'loss/train': 0.9524691700935364} 08/31/2021 02:32:13 - INFO - __main__ - Step 74065: {'lr': 0.00026027096549361713, 'samples': 14220480, 'steps': 74064, 'loss/train': 1.379232406616211} 08/31/2021 02:32:13 - INFO - __main__ - Step 74066: {'lr': 0.00026026566322743134, 'samples': 14220672, 'steps': 74065, 'loss/train': 0.9875381588935852} 08/31/2021 02:32:14 - INFO - __main__ - Step 74067: {'lr': 0.00026026036095662, 'samples': 14220864, 'steps': 74066, 'loss/train': 1.4372684955596924} 08/31/2021 02:32:16 - INFO - __main__ - Step 74068: {'lr': 0.0002602550586811856, 'samples': 14221056, 'steps': 74067, 'loss/train': 4.758537769317627} 08/31/2021 02:32:16 - INFO - __main__ - Step 74069: {'lr': 0.0002602497564011304, 'samples': 14221248, 'steps': 74068, 'loss/train': 0.050818827003240585} 08/31/2021 02:32:16 - INFO - __main__ - Step 74070: {'lr': 0.0002602444541164568, 'samples': 14221440, 'steps': 74069, 'loss/train': 1.023223638534546} 08/31/2021 02:32:17 - INFO - __main__ - Step 74071: {'lr': 0.00026023915182716716, 'samples': 14221632, 'steps': 74070, 'loss/train': 1.1741620302200317} 08/31/2021 02:32:17 - INFO - __main__ - Step 74072: {'lr': 0.00026023384953326395, 'samples': 14221824, 'steps': 74071, 'loss/train': 1.6580885648727417} 08/31/2021 02:32:18 - INFO - __main__ - Step 74073: {'lr': 0.00026022854723474953, 'samples': 14222016, 'steps': 74072, 'loss/train': 2.3323428630828857} 08/31/2021 02:32:20 - INFO - __main__ - Step 74074: {'lr': 0.0002602232449316263, 'samples': 14222208, 'steps': 74073, 'loss/train': 0.10248526930809021} 08/31/2021 02:32:20 - INFO - __main__ - Step 74075: {'lr': 0.00026021794262389667, 'samples': 14222400, 'steps': 74074, 'loss/train': 0.18308740854263306} 08/31/2021 02:32:20 - INFO - __main__ - Step 74076: {'lr': 0.00026021264031156295, 'samples': 14222592, 'steps': 74075, 'loss/train': 1.74949049949646} 08/31/2021 02:32:21 - INFO - __main__ - Step 74077: {'lr': 0.00026020733799462755, 'samples': 14222784, 'steps': 74076, 'loss/train': 1.3150867223739624} 08/31/2021 02:32:21 - INFO - __main__ - Step 74078: {'lr': 0.00026020203567309286, 'samples': 14222976, 'steps': 74077, 'loss/train': 1.2127355337142944} 08/31/2021 02:32:21 - INFO - __main__ - Step 74079: {'lr': 0.00026019673334696136, 'samples': 14223168, 'steps': 74078, 'loss/train': 1.4852873086929321} 08/31/2021 02:32:23 - INFO - __main__ - Step 74080: {'lr': 0.00026019143101623535, 'samples': 14223360, 'steps': 74079, 'loss/train': 1.205962061882019} 08/31/2021 02:32:24 - INFO - __main__ - Step 74081: {'lr': 0.0002601861286809172, 'samples': 14223552, 'steps': 74080, 'loss/train': 1.2590335607528687} 08/31/2021 02:32:24 - INFO - __main__ - Step 74082: {'lr': 0.0002601808263410094, 'samples': 14223744, 'steps': 74081, 'loss/train': 0.853243887424469} 08/31/2021 02:32:24 - INFO - __main__ - Step 74083: {'lr': 0.0002601755239965142, 'samples': 14223936, 'steps': 74082, 'loss/train': 1.7435228824615479} 08/31/2021 02:32:25 - INFO - __main__ - Step 74084: {'lr': 0.00026017022164743413, 'samples': 14224128, 'steps': 74083, 'loss/train': 1.2725259065628052} 08/31/2021 02:32:26 - INFO - __main__ - Step 74085: {'lr': 0.00026016491929377143, 'samples': 14224320, 'steps': 74084, 'loss/train': 1.7240835428237915} 08/31/2021 02:32:27 - INFO - __main__ - Step 74086: {'lr': 0.0002601596169355287, 'samples': 14224512, 'steps': 74085, 'loss/train': 0.39149123430252075} 08/31/2021 02:32:27 - INFO - __main__ - Step 74087: {'lr': 0.0002601543145727081, 'samples': 14224704, 'steps': 74086, 'loss/train': 1.3566420078277588} 08/31/2021 02:32:27 - INFO - __main__ - Step 74088: {'lr': 0.00026014901220531217, 'samples': 14224896, 'steps': 74087, 'loss/train': 1.56852388381958} 08/31/2021 02:32:28 - INFO - __main__ - Step 74089: {'lr': 0.0002601437098333433, 'samples': 14225088, 'steps': 74088, 'loss/train': 1.3156481981277466} 08/31/2021 02:32:28 - INFO - __main__ - Step 74090: {'lr': 0.00026013840745680374, 'samples': 14225280, 'steps': 74089, 'loss/train': 0.19342586398124695} 08/31/2021 02:32:30 - INFO - __main__ - Step 74091: {'lr': 0.000260133105075696, 'samples': 14225472, 'steps': 74090, 'loss/train': 4.1192626953125} 08/31/2021 02:32:30 - INFO - __main__ - Step 74092: {'lr': 0.00026012780269002244, 'samples': 14225664, 'steps': 74091, 'loss/train': 0.24126794934272766} 08/31/2021 02:32:30 - INFO - __main__ - Step 74093: {'lr': 0.00026012250029978543, 'samples': 14225856, 'steps': 74092, 'loss/train': 1.3163243532180786} 08/31/2021 02:32:31 - INFO - __main__ - Step 74094: {'lr': 0.0002601171979049874, 'samples': 14226048, 'steps': 74093, 'loss/train': 0.984122097492218} 08/31/2021 02:32:31 - INFO - __main__ - Step 74095: {'lr': 0.0002601118955056307, 'samples': 14226240, 'steps': 74094, 'loss/train': 1.5844494104385376} 08/31/2021 02:32:33 - INFO - __main__ - Step 74096: {'lr': 0.0002601065931017178, 'samples': 14226432, 'steps': 74095, 'loss/train': 1.3268409967422485} 08/31/2021 02:32:33 - INFO - __main__ - Step 74097: {'lr': 0.00026010129069325093, 'samples': 14226624, 'steps': 74096, 'loss/train': 1.6687685251235962} 08/31/2021 02:32:33 - INFO - __main__ - Step 74098: {'lr': 0.0002600959882802326, 'samples': 14226816, 'steps': 74097, 'loss/train': 1.298669457435608} 08/31/2021 02:32:34 - INFO - __main__ - Step 74099: {'lr': 0.0002600906858626652, 'samples': 14227008, 'steps': 74098, 'loss/train': 1.0275583267211914} 08/31/2021 02:32:34 - INFO - __main__ - Step 74100: {'lr': 0.0002600853834405511, 'samples': 14227200, 'steps': 74099, 'loss/train': 0.9429939389228821} 08/31/2021 02:32:36 - INFO - __main__ - Step 74101: {'lr': 0.0002600800810138927, 'samples': 14227392, 'steps': 74100, 'loss/train': 1.0719387531280518} 08/31/2021 02:32:36 - INFO - __main__ - Step 74102: {'lr': 0.00026007477858269235, 'samples': 14227584, 'steps': 74101, 'loss/train': 0.8654521703720093} 08/31/2021 02:32:36 - INFO - __main__ - Step 74103: {'lr': 0.0002600694761469524, 'samples': 14227776, 'steps': 74102, 'loss/train': 0.6734660267829895} 08/31/2021 02:32:37 - INFO - __main__ - Step 74104: {'lr': 0.0002600641737066754, 'samples': 14227968, 'steps': 74103, 'loss/train': 1.150901436805725} 08/31/2021 02:32:37 - INFO - __main__ - Step 74105: {'lr': 0.00026005887126186357, 'samples': 14228160, 'steps': 74104, 'loss/train': 0.22138789296150208} 08/31/2021 02:32:37 - INFO - __main__ - Step 74106: {'lr': 0.0002600535688125194, 'samples': 14228352, 'steps': 74105, 'loss/train': 0.29245495796203613} 08/31/2021 02:32:39 - INFO - __main__ - Step 74107: {'lr': 0.0002600482663586452, 'samples': 14228544, 'steps': 74106, 'loss/train': 1.164528727531433} 08/31/2021 02:32:40 - INFO - __main__ - Step 74108: {'lr': 0.00026004296390024346, 'samples': 14228736, 'steps': 74107, 'loss/train': 1.392675757408142} 08/31/2021 02:32:40 - INFO - __main__ - Step 74109: {'lr': 0.0002600376614373165, 'samples': 14228928, 'steps': 74108, 'loss/train': 0.366092324256897} 08/31/2021 02:32:40 - INFO - __main__ - Step 74110: {'lr': 0.00026003235896986674, 'samples': 14229120, 'steps': 74109, 'loss/train': 1.1302520036697388} 08/31/2021 02:32:41 - INFO - __main__ - Step 74111: {'lr': 0.0002600270564978965, 'samples': 14229312, 'steps': 74110, 'loss/train': 2.0866804122924805} 08/31/2021 02:32:42 - INFO - __main__ - Step 74112: {'lr': 0.0002600217540214083, 'samples': 14229504, 'steps': 74111, 'loss/train': 1.0451539754867554} 08/31/2021 02:32:43 - INFO - __main__ - Step 74113: {'lr': 0.00026001645154040436, 'samples': 14229696, 'steps': 74112, 'loss/train': 1.396050214767456} 08/31/2021 02:32:43 - INFO - __main__ - Step 74114: {'lr': 0.0002600111490548872, 'samples': 14229888, 'steps': 74113, 'loss/train': 1.3358922004699707} 08/31/2021 02:32:43 - INFO - __main__ - Step 74115: {'lr': 0.0002600058465648591, 'samples': 14230080, 'steps': 74114, 'loss/train': 0.8427857160568237} 08/31/2021 02:32:44 - INFO - __main__ - Step 74116: {'lr': 0.0002600005440703227, 'samples': 14230272, 'steps': 74115, 'loss/train': 1.2656283378601074} 08/31/2021 02:32:45 - INFO - __main__ - Step 74117: {'lr': 0.00025999524157128013, 'samples': 14230464, 'steps': 74116, 'loss/train': 0.9526849985122681} 08/31/2021 02:32:46 - INFO - __main__ - Step 74118: {'lr': 0.0002599899390677338, 'samples': 14230656, 'steps': 74117, 'loss/train': 0.8696883320808411} 08/31/2021 02:32:46 - INFO - __main__ - Step 74119: {'lr': 0.0002599846365596862, 'samples': 14230848, 'steps': 74118, 'loss/train': 0.954900860786438} 08/31/2021 02:32:46 - INFO - __main__ - Step 74120: {'lr': 0.0002599793340471397, 'samples': 14231040, 'steps': 74119, 'loss/train': 0.5472553968429565} 08/31/2021 02:32:47 - INFO - __main__ - Step 74121: {'lr': 0.00025997403153009657, 'samples': 14231232, 'steps': 74120, 'loss/train': 1.768509030342102} 08/31/2021 02:32:48 - INFO - __main__ - Step 74122: {'lr': 0.00025996872900855937, 'samples': 14231424, 'steps': 74121, 'loss/train': 1.244236946105957} 08/31/2021 02:32:49 - INFO - __main__ - Step 74123: {'lr': 0.0002599634264825305, 'samples': 14231616, 'steps': 74122, 'loss/train': 1.3816405534744263} 08/31/2021 02:32:49 - INFO - __main__ - Step 74124: {'lr': 0.00025995812395201214, 'samples': 14231808, 'steps': 74123, 'loss/train': 1.5805401802062988} 08/31/2021 02:32:49 - INFO - __main__ - Step 74125: {'lr': 0.0002599528214170068, 'samples': 14232000, 'steps': 74124, 'loss/train': 1.5367149114608765} 08/31/2021 02:32:50 - INFO - __main__ - Step 74126: {'lr': 0.0002599475188775169, 'samples': 14232192, 'steps': 74125, 'loss/train': 1.2444974184036255} 08/31/2021 02:32:51 - INFO - __main__ - Step 74127: {'lr': 0.0002599422163335448, 'samples': 14232384, 'steps': 74126, 'loss/train': 1.8327139616012573} 08/31/2021 02:32:52 - INFO - __main__ - Step 74128: {'lr': 0.00025993691378509295, 'samples': 14232576, 'steps': 74127, 'loss/train': 0.7155473828315735} 08/31/2021 02:32:52 - INFO - __main__ - Step 74129: {'lr': 0.00025993161123216365, 'samples': 14232768, 'steps': 74128, 'loss/train': 1.603977918624878} 08/31/2021 02:32:53 - INFO - __main__ - Step 74130: {'lr': 0.0002599263086747593, 'samples': 14232960, 'steps': 74129, 'loss/train': 1.0049327611923218} 08/31/2021 02:32:53 - INFO - __main__ - Step 74131: {'lr': 0.00025992100611288226, 'samples': 14233152, 'steps': 74130, 'loss/train': 0.04268684610724449} 08/31/2021 02:32:55 - INFO - __main__ - Step 74132: {'lr': 0.00025991570354653504, 'samples': 14233344, 'steps': 74131, 'loss/train': 1.434774398803711} 08/31/2021 02:32:56 - INFO - __main__ - Step 74133: {'lr': 0.0002599104009757199, 'samples': 14233536, 'steps': 74132, 'loss/train': 0.5331514477729797} 08/31/2021 02:32:56 - INFO - __main__ - Step 74134: {'lr': 0.0002599050984004393, 'samples': 14233728, 'steps': 74133, 'loss/train': 1.2795324325561523} 08/31/2021 02:32:56 - INFO - __main__ - Step 74135: {'lr': 0.00025989979582069565, 'samples': 14233920, 'steps': 74134, 'loss/train': 0.19210103154182434} 08/31/2021 02:32:57 - INFO - __main__ - Step 74136: {'lr': 0.00025989449323649135, 'samples': 14234112, 'steps': 74135, 'loss/train': 0.7325699925422668} 08/31/2021 02:32:57 - INFO - __main__ - Step 74137: {'lr': 0.00025988919064782865, 'samples': 14234304, 'steps': 74136, 'loss/train': 1.3610260486602783} 08/31/2021 02:32:59 - INFO - __main__ - Step 74138: {'lr': 0.0002598838880547101, 'samples': 14234496, 'steps': 74137, 'loss/train': 1.4693129062652588} 08/31/2021 02:32:59 - INFO - __main__ - Step 74139: {'lr': 0.00025987858545713796, 'samples': 14234688, 'steps': 74138, 'loss/train': 1.854383945465088} 08/31/2021 02:32:59 - INFO - __main__ - Step 74140: {'lr': 0.0002598732828551147, 'samples': 14234880, 'steps': 74139, 'loss/train': 1.0471163988113403} 08/31/2021 02:33:00 - INFO - __main__ - Step 74141: {'lr': 0.00025986798024864267, 'samples': 14235072, 'steps': 74140, 'loss/train': 1.049447774887085} 08/31/2021 02:33:00 - INFO - __main__ - Step 74142: {'lr': 0.00025986267763772433, 'samples': 14235264, 'steps': 74141, 'loss/train': 1.1388987302780151} 08/31/2021 02:33:02 - INFO - __main__ - Step 74143: {'lr': 0.000259857375022362, 'samples': 14235456, 'steps': 74142, 'loss/train': 1.018293857574463} 08/31/2021 02:33:02 - INFO - __main__ - Step 74144: {'lr': 0.0002598520724025581, 'samples': 14235648, 'steps': 74143, 'loss/train': 0.09718480706214905} 08/31/2021 02:33:02 - INFO - __main__ - Step 74145: {'lr': 0.00025984676977831503, 'samples': 14235840, 'steps': 74144, 'loss/train': 1.3795647621154785} 08/31/2021 02:33:03 - INFO - __main__ - Step 74146: {'lr': 0.0002598414671496351, 'samples': 14236032, 'steps': 74145, 'loss/train': 1.1948232650756836} 08/31/2021 02:33:03 - INFO - __main__ - Step 74147: {'lr': 0.00025983616451652074, 'samples': 14236224, 'steps': 74146, 'loss/train': 1.3595659732818604} 08/31/2021 02:33:05 - INFO - __main__ - Step 74148: {'lr': 0.0002598308618789744, 'samples': 14236416, 'steps': 74147, 'loss/train': 1.3463307619094849} 08/31/2021 02:33:05 - INFO - __main__ - Step 74149: {'lr': 0.00025982555923699844, 'samples': 14236608, 'steps': 74148, 'loss/train': 1.0073076486587524} 08/31/2021 02:33:06 - INFO - __main__ - Step 74150: {'lr': 0.00025982025659059525, 'samples': 14236800, 'steps': 74149, 'loss/train': 0.6661739349365234} 08/31/2021 02:33:06 - INFO - __main__ - Step 74151: {'lr': 0.00025981495393976716, 'samples': 14236992, 'steps': 74150, 'loss/train': 1.2043811082839966} 08/31/2021 02:33:06 - INFO - __main__ - Step 74152: {'lr': 0.0002598096512845166, 'samples': 14237184, 'steps': 74151, 'loss/train': 1.7425943613052368} 08/31/2021 02:33:08 - INFO - __main__ - Step 74153: {'lr': 0.000259804348624846, 'samples': 14237376, 'steps': 74152, 'loss/train': 1.6476999521255493} 08/31/2021 02:33:08 - INFO - __main__ - Step 74154: {'lr': 0.00025979904596075767, 'samples': 14237568, 'steps': 74153, 'loss/train': 1.0570236444473267} 08/31/2021 02:33:09 - INFO - __main__ - Step 74155: {'lr': 0.0002597937432922541, 'samples': 14237760, 'steps': 74154, 'loss/train': 0.7995379567146301} 08/31/2021 02:33:09 - INFO - __main__ - Step 74156: {'lr': 0.0002597884406193376, 'samples': 14237952, 'steps': 74155, 'loss/train': 0.9488495588302612} 08/31/2021 02:33:09 - INFO - __main__ - Step 74157: {'lr': 0.00025978313794201055, 'samples': 14238144, 'steps': 74156, 'loss/train': 1.3648383617401123} 08/31/2021 02:33:11 - INFO - __main__ - Step 74158: {'lr': 0.0002597778352602754, 'samples': 14238336, 'steps': 74157, 'loss/train': 0.20270894467830658} 08/31/2021 02:33:11 - INFO - __main__ - Step 74159: {'lr': 0.00025977253257413444, 'samples': 14238528, 'steps': 74158, 'loss/train': 1.5216047763824463} 08/31/2021 02:33:12 - INFO - __main__ - Step 74160: {'lr': 0.00025976722988359013, 'samples': 14238720, 'steps': 74159, 'loss/train': 1.5168548822402954} 08/31/2021 02:33:12 - INFO - __main__ - Step 74161: {'lr': 0.00025976192718864493, 'samples': 14238912, 'steps': 74160, 'loss/train': 1.3964554071426392} 08/31/2021 02:33:12 - INFO - __main__ - Step 74162: {'lr': 0.00025975662448930113, 'samples': 14239104, 'steps': 74161, 'loss/train': 0.38393598794937134} 08/31/2021 02:33:13 - INFO - __main__ - Step 74163: {'lr': 0.0002597513217855612, 'samples': 14239296, 'steps': 74162, 'loss/train': 1.412476897239685} 08/31/2021 02:33:15 - INFO - __main__ - Step 74164: {'lr': 0.0002597460190774274, 'samples': 14239488, 'steps': 74163, 'loss/train': 1.4728151559829712} 08/31/2021 02:33:15 - INFO - __main__ - Step 74165: {'lr': 0.0002597407163649022, 'samples': 14239680, 'steps': 74164, 'loss/train': 1.7887942790985107} 08/31/2021 02:33:15 - INFO - __main__ - Step 74166: {'lr': 0.00025973541364798797, 'samples': 14239872, 'steps': 74165, 'loss/train': 0.9589278101921082} 08/31/2021 02:33:16 - INFO - __main__ - Step 74167: {'lr': 0.0002597301109266871, 'samples': 14240064, 'steps': 74166, 'loss/train': 0.02947915717959404} 08/31/2021 02:33:16 - INFO - __main__ - Step 74168: {'lr': 0.0002597248082010021, 'samples': 14240256, 'steps': 74167, 'loss/train': 0.028736064210534096} 08/31/2021 02:33:17 - INFO - __main__ - Step 74169: {'lr': 0.0002597195054709351, 'samples': 14240448, 'steps': 74168, 'loss/train': 0.4515496492385864} 08/31/2021 02:33:18 - INFO - __main__ - Step 74170: {'lr': 0.0002597142027364888, 'samples': 14240640, 'steps': 74169, 'loss/train': 1.2789407968521118} 08/31/2021 02:33:18 - INFO - __main__ - Step 74171: {'lr': 0.0002597088999976654, 'samples': 14240832, 'steps': 74170, 'loss/train': 0.9227067232131958} 08/31/2021 02:33:19 - INFO - __main__ - Step 74172: {'lr': 0.00025970359725446725, 'samples': 14241024, 'steps': 74171, 'loss/train': 1.3746575117111206} 08/31/2021 02:33:19 - INFO - __main__ - Step 74173: {'lr': 0.0002596982945068968, 'samples': 14241216, 'steps': 74172, 'loss/train': 0.9814186692237854} 08/31/2021 02:33:19 - INFO - __main__ - Step 74174: {'lr': 0.0002596929917549565, 'samples': 14241408, 'steps': 74173, 'loss/train': 1.2879406213760376} 08/31/2021 02:33:21 - INFO - __main__ - Step 74175: {'lr': 0.00025968768899864864, 'samples': 14241600, 'steps': 74174, 'loss/train': 1.6998735666275024} 08/31/2021 02:33:22 - INFO - __main__ - Step 74176: {'lr': 0.00025968238623797575, 'samples': 14241792, 'steps': 74175, 'loss/train': 1.3764557838439941} 08/31/2021 02:33:22 - INFO - __main__ - Step 74177: {'lr': 0.0002596770834729401, 'samples': 14241984, 'steps': 74176, 'loss/train': 1.2603111267089844} 08/31/2021 02:33:22 - INFO - __main__ - Step 74178: {'lr': 0.000259671780703544, 'samples': 14242176, 'steps': 74177, 'loss/train': 0.7914605736732483} 08/31/2021 02:33:23 - INFO - __main__ - Step 74179: {'lr': 0.00025966647792979, 'samples': 14242368, 'steps': 74178, 'loss/train': 0.657827615737915} 08/31/2021 02:33:23 - INFO - __main__ - Step 74180: {'lr': 0.0002596611751516805, 'samples': 14242560, 'steps': 74179, 'loss/train': 0.020162757486104965} 08/31/2021 02:33:25 - INFO - __main__ - Step 74181: {'lr': 0.00025965587236921774, 'samples': 14242752, 'steps': 74180, 'loss/train': 0.8038930892944336} 08/31/2021 02:33:25 - INFO - __main__ - Step 74182: {'lr': 0.00025965056958240424, 'samples': 14242944, 'steps': 74181, 'loss/train': 1.474578619003296} 08/31/2021 02:33:25 - INFO - __main__ - Step 74183: {'lr': 0.00025964526679124234, 'samples': 14243136, 'steps': 74182, 'loss/train': 1.3637462854385376} 08/31/2021 02:33:26 - INFO - __main__ - Step 74184: {'lr': 0.00025963996399573435, 'samples': 14243328, 'steps': 74183, 'loss/train': 1.9082032442092896} 08/31/2021 02:33:26 - INFO - __main__ - Step 74185: {'lr': 0.00025963466119588284, 'samples': 14243520, 'steps': 74184, 'loss/train': 1.1553866863250732} 08/31/2021 02:33:28 - INFO - __main__ - Step 74186: {'lr': 0.00025962935839169007, 'samples': 14243712, 'steps': 74185, 'loss/train': 1.1197541952133179} 08/31/2021 02:33:29 - INFO - __main__ - Step 74187: {'lr': 0.0002596240555831585, 'samples': 14243904, 'steps': 74186, 'loss/train': 1.902187466621399} 08/31/2021 02:33:29 - INFO - __main__ - Step 74188: {'lr': 0.0002596187527702904, 'samples': 14244096, 'steps': 74187, 'loss/train': 1.0896133184432983} 08/31/2021 02:33:30 - INFO - __main__ - Step 74189: {'lr': 0.00025961344995308825, 'samples': 14244288, 'steps': 74188, 'loss/train': 1.206966757774353} 08/31/2021 02:33:30 - INFO - __main__ - Step 74190: {'lr': 0.0002596081471315545, 'samples': 14244480, 'steps': 74189, 'loss/train': 1.457242727279663} 08/31/2021 02:33:31 - INFO - __main__ - Step 74191: {'lr': 0.0002596028443056914, 'samples': 14244672, 'steps': 74190, 'loss/train': 1.4783742427825928} 08/31/2021 02:33:32 - INFO - __main__ - Step 74192: {'lr': 0.0002595975414755014, 'samples': 14244864, 'steps': 74191, 'loss/train': 1.853065013885498} 08/31/2021 02:33:32 - INFO - __main__ - Step 74193: {'lr': 0.00025959223864098697, 'samples': 14245056, 'steps': 74192, 'loss/train': 1.2595272064208984} 08/31/2021 02:33:32 - INFO - __main__ - Step 74194: {'lr': 0.00025958693580215036, 'samples': 14245248, 'steps': 74193, 'loss/train': 0.735456645488739} 08/31/2021 02:33:33 - INFO - __main__ - Step 74195: {'lr': 0.0002595816329589941, 'samples': 14245440, 'steps': 74194, 'loss/train': 1.0847103595733643} 08/31/2021 02:33:34 - INFO - __main__ - Step 74196: {'lr': 0.0002595763301115204, 'samples': 14245632, 'steps': 74195, 'loss/train': 1.2611808776855469} 08/31/2021 02:33:35 - INFO - __main__ - Step 74197: {'lr': 0.0002595710272597318, 'samples': 14245824, 'steps': 74196, 'loss/train': 1.1516714096069336} 08/31/2021 02:33:35 - INFO - __main__ - Step 74198: {'lr': 0.0002595657244036307, 'samples': 14246016, 'steps': 74197, 'loss/train': 0.683303952217102} 08/31/2021 02:33:35 - INFO - __main__ - Step 74199: {'lr': 0.0002595604215432194, 'samples': 14246208, 'steps': 74198, 'loss/train': 1.5554085969924927} 08/31/2021 02:33:36 - INFO - __main__ - Step 74200: {'lr': 0.00025955511867850026, 'samples': 14246400, 'steps': 74199, 'loss/train': 1.6020334959030151} 08/31/2021 02:33:36 - INFO - __main__ - Step 74201: {'lr': 0.0002595498158094757, 'samples': 14246592, 'steps': 74200, 'loss/train': 0.6300523281097412} 08/31/2021 02:33:38 - INFO - __main__ - Step 74202: {'lr': 0.0002595445129361482, 'samples': 14246784, 'steps': 74201, 'loss/train': 0.9799588322639465} 08/31/2021 02:33:38 - INFO - __main__ - Step 74203: {'lr': 0.0002595392100585201, 'samples': 14246976, 'steps': 74202, 'loss/train': 1.1437816619873047} 08/31/2021 02:33:39 - INFO - __main__ - Step 74204: {'lr': 0.0002595339071765939, 'samples': 14247168, 'steps': 74203, 'loss/train': 1.3532088994979858} 08/31/2021 02:33:39 - INFO - __main__ - Step 74205: {'lr': 0.0002595286042903717, 'samples': 14247360, 'steps': 74204, 'loss/train': 0.8904999494552612} 08/31/2021 02:33:39 - INFO - __main__ - Step 74206: {'lr': 0.0002595233013998561, 'samples': 14247552, 'steps': 74205, 'loss/train': 0.15768523514270782} 08/31/2021 02:33:41 - INFO - __main__ - Step 74207: {'lr': 0.00025951799850504944, 'samples': 14247744, 'steps': 74206, 'loss/train': 0.7966058850288391} 08/31/2021 02:33:41 - INFO - __main__ - Step 74208: {'lr': 0.00025951269560595407, 'samples': 14247936, 'steps': 74207, 'loss/train': 0.8924757242202759} 08/31/2021 02:33:41 - INFO - __main__ - Step 74209: {'lr': 0.0002595073927025725, 'samples': 14248128, 'steps': 74208, 'loss/train': 1.134222388267517} 08/31/2021 02:33:42 - INFO - __main__ - Step 74210: {'lr': 0.0002595020897949071, 'samples': 14248320, 'steps': 74209, 'loss/train': 0.8151630163192749} 08/31/2021 02:33:42 - INFO - __main__ - Step 74211: {'lr': 0.0002594967868829601, 'samples': 14248512, 'steps': 74210, 'loss/train': 0.9713186025619507} 08/31/2021 02:33:44 - INFO - __main__ - Step 74212: {'lr': 0.0002594914839667341, 'samples': 14248704, 'steps': 74211, 'loss/train': 0.6970579028129578} 08/31/2021 02:33:44 - INFO - __main__ - Step 74213: {'lr': 0.00025948618104623125, 'samples': 14248896, 'steps': 74212, 'loss/train': 1.2177448272705078} 08/31/2021 02:33:44 - INFO - __main__ - Step 74214: {'lr': 0.0002594808781214541, 'samples': 14249088, 'steps': 74213, 'loss/train': 1.0746787786483765} 08/31/2021 02:33:45 - INFO - __main__ - Step 74215: {'lr': 0.00025947557519240505, 'samples': 14249280, 'steps': 74214, 'loss/train': 0.962391197681427} 08/31/2021 02:33:45 - INFO - __main__ - Step 74216: {'lr': 0.0002594702722590864, 'samples': 14249472, 'steps': 74215, 'loss/train': 1.7329771518707275} 08/31/2021 02:33:47 - INFO - __main__ - Step 74217: {'lr': 0.0002594649693215007, 'samples': 14249664, 'steps': 74216, 'loss/train': 0.5209887027740479} 08/31/2021 02:33:47 - INFO - __main__ - Step 74218: {'lr': 0.00025945966637965016, 'samples': 14249856, 'steps': 74217, 'loss/train': 1.1249033212661743} 08/31/2021 02:33:47 - INFO - __main__ - Step 74219: {'lr': 0.0002594543634335373, 'samples': 14250048, 'steps': 74218, 'loss/train': 1.1176612377166748} 08/31/2021 02:33:48 - INFO - __main__ - Step 74220: {'lr': 0.00025944906048316435, 'samples': 14250240, 'steps': 74219, 'loss/train': 0.4047768712043762} 08/31/2021 02:33:48 - INFO - __main__ - Step 74221: {'lr': 0.00025944375752853387, 'samples': 14250432, 'steps': 74220, 'loss/train': 0.5538629293441772} 08/31/2021 02:33:50 - INFO - __main__ - Step 74222: {'lr': 0.00025943845456964816, 'samples': 14250624, 'steps': 74221, 'loss/train': 0.8082265257835388} 08/31/2021 02:33:50 - INFO - __main__ - Step 74223: {'lr': 0.0002594331516065097, 'samples': 14250816, 'steps': 74222, 'loss/train': 1.2782429456710815} 08/31/2021 02:33:51 - INFO - __main__ - Step 74224: {'lr': 0.00025942784863912074, 'samples': 14251008, 'steps': 74223, 'loss/train': 1.5640238523483276} 08/31/2021 02:33:51 - INFO - __main__ - Step 74225: {'lr': 0.0002594225456674837, 'samples': 14251200, 'steps': 74224, 'loss/train': 2.0590884685516357} 08/31/2021 02:33:51 - INFO - __main__ - Step 74226: {'lr': 0.000259417242691601, 'samples': 14251392, 'steps': 74225, 'loss/train': 1.7556716203689575} 08/31/2021 02:33:53 - INFO - __main__ - Step 74227: {'lr': 0.0002594119397114751, 'samples': 14251584, 'steps': 74226, 'loss/train': 0.3775859773159027} 08/31/2021 02:33:53 - INFO - __main__ - Step 74228: {'lr': 0.00025940663672710827, 'samples': 14251776, 'steps': 74227, 'loss/train': 0.8606963157653809} 08/31/2021 02:33:53 - INFO - __main__ - Step 74229: {'lr': 0.000259401333738503, 'samples': 14251968, 'steps': 74228, 'loss/train': 1.23453688621521} 08/31/2021 02:33:54 - INFO - __main__ - Step 74230: {'lr': 0.00025939603074566167, 'samples': 14252160, 'steps': 74229, 'loss/train': 0.8172366619110107} 08/31/2021 02:33:54 - INFO - __main__ - Step 74231: {'lr': 0.0002593907277485865, 'samples': 14252352, 'steps': 74230, 'loss/train': 1.2107876539230347} 08/31/2021 02:33:55 - INFO - __main__ - Step 74232: {'lr': 0.0002593854247472801, 'samples': 14252544, 'steps': 74231, 'loss/train': 0.688720166683197} 08/31/2021 02:33:56 - INFO - __main__ - Step 74233: {'lr': 0.0002593801217417448, 'samples': 14252736, 'steps': 74232, 'loss/train': 1.2341604232788086} 08/31/2021 02:33:57 - INFO - __main__ - Step 74234: {'lr': 0.0002593748187319829, 'samples': 14252928, 'steps': 74233, 'loss/train': 1.0547000169754028} 08/31/2021 02:33:57 - INFO - __main__ - Step 74235: {'lr': 0.00025936951571799686, 'samples': 14253120, 'steps': 74234, 'loss/train': 1.4086813926696777} 08/31/2021 02:33:57 - INFO - __main__ - Step 74236: {'lr': 0.0002593642126997891, 'samples': 14253312, 'steps': 74235, 'loss/train': 0.019972600042819977} 08/31/2021 02:33:58 - INFO - __main__ - Step 74237: {'lr': 0.000259358909677362, 'samples': 14253504, 'steps': 74236, 'loss/train': 1.4634488821029663} 08/31/2021 02:33:58 - INFO - __main__ - Step 74238: {'lr': 0.00025935360665071787, 'samples': 14253696, 'steps': 74237, 'loss/train': 0.7571510076522827} 08/31/2021 02:34:00 - INFO - __main__ - Step 74239: {'lr': 0.00025934830361985914, 'samples': 14253888, 'steps': 74238, 'loss/train': 1.393378734588623} 08/31/2021 02:34:01 - INFO - __main__ - Step 74240: {'lr': 0.0002593430005847882, 'samples': 14254080, 'steps': 74239, 'loss/train': 0.6896852254867554} 08/31/2021 02:34:01 - INFO - __main__ - Step 74241: {'lr': 0.00025933769754550747, 'samples': 14254272, 'steps': 74240, 'loss/train': 0.22647519409656525} 08/31/2021 02:34:01 - INFO - __main__ - Step 74242: {'lr': 0.0002593323945020193, 'samples': 14254464, 'steps': 74241, 'loss/train': 0.6957089900970459} 08/31/2021 02:34:02 - INFO - __main__ - Step 74243: {'lr': 0.0002593270914543261, 'samples': 14254656, 'steps': 74242, 'loss/train': 1.7307548522949219} 08/31/2021 02:34:03 - INFO - __main__ - Step 74244: {'lr': 0.00025932178840243033, 'samples': 14254848, 'steps': 74243, 'loss/train': 1.427903652191162} 08/31/2021 02:34:04 - INFO - __main__ - Step 74245: {'lr': 0.00025931648534633424, 'samples': 14255040, 'steps': 74244, 'loss/train': 1.2391762733459473} 08/31/2021 02:34:04 - INFO - __main__ - Step 74246: {'lr': 0.0002593111822860403, 'samples': 14255232, 'steps': 74245, 'loss/train': 0.6527667045593262} 08/31/2021 02:34:04 - INFO - __main__ - Step 74247: {'lr': 0.00025930587922155086, 'samples': 14255424, 'steps': 74246, 'loss/train': 1.0868470668792725} 08/31/2021 02:34:05 - INFO - __main__ - Step 74248: {'lr': 0.0002593005761528683, 'samples': 14255616, 'steps': 74247, 'loss/train': 1.0076801776885986} 08/31/2021 02:34:06 - INFO - __main__ - Step 74249: {'lr': 0.00025929527307999513, 'samples': 14255808, 'steps': 74248, 'loss/train': 1.080017328262329} 08/31/2021 02:34:07 - INFO - __main__ - Step 74250: {'lr': 0.00025928997000293367, 'samples': 14256000, 'steps': 74249, 'loss/train': 1.2820453643798828} 08/31/2021 02:34:07 - INFO - __main__ - Step 74251: {'lr': 0.00025928466692168615, 'samples': 14256192, 'steps': 74250, 'loss/train': 1.1425877809524536} 08/31/2021 02:34:07 - INFO - __main__ - Step 74252: {'lr': 0.00025927936383625524, 'samples': 14256384, 'steps': 74251, 'loss/train': 0.8354565501213074} 08/31/2021 02:34:08 - INFO - __main__ - Step 74253: {'lr': 0.0002592740607466431, 'samples': 14256576, 'steps': 74252, 'loss/train': 1.424378752708435} 08/31/2021 02:34:09 - INFO - __main__ - Step 74254: {'lr': 0.0002592687576528523, 'samples': 14256768, 'steps': 74253, 'loss/train': 1.3989108800888062} 08/31/2021 02:34:10 - INFO - __main__ - Step 74255: {'lr': 0.0002592634545548851, 'samples': 14256960, 'steps': 74254, 'loss/train': 0.4581138491630554} 08/31/2021 02:34:10 - INFO - __main__ - Step 74256: {'lr': 0.0002592581514527439, 'samples': 14257152, 'steps': 74255, 'loss/train': 0.6365799903869629} 08/31/2021 02:34:10 - INFO - __main__ - Step 74257: {'lr': 0.0002592528483464312, 'samples': 14257344, 'steps': 74256, 'loss/train': 1.7907081842422485} 08/31/2021 02:34:11 - INFO - __main__ - Step 74258: {'lr': 0.0002592475452359492, 'samples': 14257536, 'steps': 74257, 'loss/train': 1.60166597366333} 08/31/2021 02:34:12 - INFO - __main__ - Step 74259: {'lr': 0.00025924224212130046, 'samples': 14257728, 'steps': 74258, 'loss/train': 0.07402370125055313} 08/31/2021 02:34:13 - INFO - __main__ - Step 74260: {'lr': 0.0002592369390024873, 'samples': 14257920, 'steps': 74259, 'loss/train': 1.5396780967712402} 08/31/2021 02:34:13 - INFO - __main__ - Step 74261: {'lr': 0.0002592316358795121, 'samples': 14258112, 'steps': 74260, 'loss/train': 0.808897852897644} 08/31/2021 02:34:14 - INFO - __main__ - Step 74262: {'lr': 0.0002592263327523773, 'samples': 14258304, 'steps': 74261, 'loss/train': 1.0954437255859375} 08/31/2021 02:34:14 - INFO - __main__ - Step 74263: {'lr': 0.0002592210296210852, 'samples': 14258496, 'steps': 74262, 'loss/train': 1.008307695388794} 08/31/2021 02:34:14 - INFO - __main__ - Step 74264: {'lr': 0.00025921572648563833, 'samples': 14258688, 'steps': 74263, 'loss/train': 1.3644545078277588} 08/31/2021 02:34:16 - INFO - __main__ - Step 74265: {'lr': 0.000259210423346039, 'samples': 14258880, 'steps': 74264, 'loss/train': 1.16538667678833} 08/31/2021 02:34:16 - INFO - __main__ - Step 74266: {'lr': 0.0002592051202022895, 'samples': 14259072, 'steps': 74265, 'loss/train': 0.9092150926589966} 08/31/2021 02:34:17 - INFO - __main__ - Step 74267: {'lr': 0.0002591998170543924, 'samples': 14259264, 'steps': 74266, 'loss/train': 1.1479383707046509} 08/31/2021 02:34:17 - INFO - __main__ - Step 74268: {'lr': 0.00025919451390234995, 'samples': 14259456, 'steps': 74267, 'loss/train': 1.3026164770126343} 08/31/2021 02:34:17 - INFO - __main__ - Step 74269: {'lr': 0.00025918921074616466, 'samples': 14259648, 'steps': 74268, 'loss/train': 1.525829553604126} 08/31/2021 02:34:19 - INFO - __main__ - Step 74270: {'lr': 0.0002591839075858388, 'samples': 14259840, 'steps': 74269, 'loss/train': 0.7899249792098999} 08/31/2021 02:34:19 - INFO - __main__ - Step 74271: {'lr': 0.0002591786044213748, 'samples': 14260032, 'steps': 74270, 'loss/train': 1.2795742750167847} 08/31/2021 02:34:20 - INFO - __main__ - Step 74272: {'lr': 0.00025917330125277513, 'samples': 14260224, 'steps': 74271, 'loss/train': 1.2977747917175293} 08/31/2021 02:34:20 - INFO - __main__ - Step 74273: {'lr': 0.00025916799808004204, 'samples': 14260416, 'steps': 74272, 'loss/train': 1.3687548637390137} 08/31/2021 02:34:20 - INFO - __main__ - Step 74274: {'lr': 0.00025916269490317803, 'samples': 14260608, 'steps': 74273, 'loss/train': 1.414303183555603} 08/31/2021 02:34:22 - INFO - __main__ - Step 74275: {'lr': 0.0002591573917221854, 'samples': 14260800, 'steps': 74274, 'loss/train': 0.9284401535987854} 08/31/2021 02:34:22 - INFO - __main__ - Step 74276: {'lr': 0.00025915208853706664, 'samples': 14260992, 'steps': 74275, 'loss/train': 1.2283811569213867} 08/31/2021 02:34:22 - INFO - __main__ - Step 74277: {'lr': 0.0002591467853478241, 'samples': 14261184, 'steps': 74276, 'loss/train': 0.05905720964074135} 08/31/2021 02:34:23 - INFO - __main__ - Step 74278: {'lr': 0.00025914148215446013, 'samples': 14261376, 'steps': 74277, 'loss/train': 1.4409343004226685} 08/31/2021 02:34:23 - INFO - __main__ - Step 74279: {'lr': 0.00025913617895697715, 'samples': 14261568, 'steps': 74278, 'loss/train': 1.7499734163284302} 08/31/2021 02:34:23 - INFO - __main__ - Step 74280: {'lr': 0.00025913087575537755, 'samples': 14261760, 'steps': 74279, 'loss/train': 0.918796956539154} 08/31/2021 02:34:25 - INFO - __main__ - Step 74281: {'lr': 0.00025912557254966374, 'samples': 14261952, 'steps': 74280, 'loss/train': 1.055101990699768} 08/31/2021 02:34:25 - INFO - __main__ - Step 74282: {'lr': 0.0002591202693398381, 'samples': 14262144, 'steps': 74281, 'loss/train': 1.3369183540344238} 08/31/2021 02:34:26 - INFO - __main__ - Step 74283: {'lr': 0.0002591149661259029, 'samples': 14262336, 'steps': 74282, 'loss/train': 1.300946831703186} 08/31/2021 02:34:26 - INFO - __main__ - Step 74284: {'lr': 0.0002591096629078608, 'samples': 14262528, 'steps': 74283, 'loss/train': 0.8945990800857544} 08/31/2021 02:34:27 - INFO - __main__ - Step 74285: {'lr': 0.00025910435968571396, 'samples': 14262720, 'steps': 74284, 'loss/train': 1.2304134368896484} 08/31/2021 02:34:28 - INFO - __main__ - Step 74286: {'lr': 0.0002590990564594648, 'samples': 14262912, 'steps': 74285, 'loss/train': 1.8981341123580933} 08/31/2021 02:34:28 - INFO - __main__ - Step 74287: {'lr': 0.0002590937532291157, 'samples': 14263104, 'steps': 74286, 'loss/train': 0.9695380330085754} 08/31/2021 02:34:29 - INFO - __main__ - Step 74288: {'lr': 0.00025908844999466917, 'samples': 14263296, 'steps': 74287, 'loss/train': 0.695277988910675} 08/31/2021 02:34:29 - INFO - __main__ - Step 74289: {'lr': 0.00025908314675612755, 'samples': 14263488, 'steps': 74288, 'loss/train': 1.2397127151489258} 08/31/2021 02:34:30 - INFO - __main__ - Step 74290: {'lr': 0.00025907784351349313, 'samples': 14263680, 'steps': 74289, 'loss/train': 1.1129103899002075} 08/31/2021 02:34:31 - INFO - __main__ - Step 74291: {'lr': 0.00025907254026676845, 'samples': 14263872, 'steps': 74290, 'loss/train': 1.2192317247390747} 08/31/2021 02:34:31 - INFO - __main__ - Step 74292: {'lr': 0.0002590672370159558, 'samples': 14264064, 'steps': 74291, 'loss/train': 1.0273804664611816} 08/31/2021 02:34:32 - INFO - __main__ - Step 74293: {'lr': 0.00025906193376105756, 'samples': 14264256, 'steps': 74292, 'loss/train': 1.9361212253570557} 08/31/2021 02:34:32 - INFO - __main__ - Step 74294: {'lr': 0.0002590566305020762, 'samples': 14264448, 'steps': 74293, 'loss/train': 0.4829122722148895} 08/31/2021 02:34:32 - INFO - __main__ - Step 74295: {'lr': 0.000259051327239014, 'samples': 14264640, 'steps': 74294, 'loss/train': 1.3473167419433594} 08/31/2021 02:34:34 - INFO - __main__ - Step 74296: {'lr': 0.00025904602397187345, 'samples': 14264832, 'steps': 74295, 'loss/train': 1.0345511436462402} 08/31/2021 02:34:35 - INFO - __main__ - Step 74297: {'lr': 0.0002590407207006569, 'samples': 14265024, 'steps': 74296, 'loss/train': 1.113724946975708} 08/31/2021 02:34:35 - INFO - __main__ - Step 74298: {'lr': 0.00025903541742536675, 'samples': 14265216, 'steps': 74297, 'loss/train': 0.6144183278083801} 08/31/2021 02:34:36 - INFO - __main__ - Step 74299: {'lr': 0.00025903011414600536, 'samples': 14265408, 'steps': 74298, 'loss/train': 0.8786898851394653} 08/31/2021 02:34:36 - INFO - __main__ - Step 74300: {'lr': 0.0002590248108625751, 'samples': 14265600, 'steps': 74299, 'loss/train': 1.2671669721603394} 08/31/2021 02:34:37 - INFO - __main__ - Step 74301: {'lr': 0.00025901950757507847, 'samples': 14265792, 'steps': 74300, 'loss/train': 0.920833945274353} 08/31/2021 02:34:38 - INFO - __main__ - Step 74302: {'lr': 0.0002590142042835178, 'samples': 14265984, 'steps': 74301, 'loss/train': 0.890676736831665} 08/31/2021 02:34:38 - INFO - __main__ - Step 74303: {'lr': 0.00025900890098789543, 'samples': 14266176, 'steps': 74302, 'loss/train': 1.395511269569397} 08/31/2021 02:34:39 - INFO - __main__ - Step 74304: {'lr': 0.0002590035976882138, 'samples': 14266368, 'steps': 74303, 'loss/train': 1.495290756225586} 08/31/2021 02:34:39 - INFO - __main__ - Step 74305: {'lr': 0.0002589982943844753, 'samples': 14266560, 'steps': 74304, 'loss/train': 1.174095630645752} 08/31/2021 02:34:40 - INFO - __main__ - Step 74306: {'lr': 0.0002589929910766823, 'samples': 14266752, 'steps': 74305, 'loss/train': 0.7219915986061096} 08/31/2021 02:34:41 - INFO - __main__ - Step 74307: {'lr': 0.0002589876877648372, 'samples': 14266944, 'steps': 74306, 'loss/train': 1.656805157661438} 08/31/2021 02:34:41 - INFO - __main__ - Step 74308: {'lr': 0.0002589823844489423, 'samples': 14267136, 'steps': 74307, 'loss/train': 0.3666863739490509} 08/31/2021 02:34:41 - INFO - __main__ - Step 74309: {'lr': 0.00025897708112900014, 'samples': 14267328, 'steps': 74308, 'loss/train': 1.1800607442855835} 08/31/2021 02:34:42 - INFO - __main__ - Step 74310: {'lr': 0.0002589717778050131, 'samples': 14267520, 'steps': 74309, 'loss/train': 1.1394227743148804} 08/31/2021 02:34:43 - INFO - __main__ - Step 74311: {'lr': 0.00025896647447698343, 'samples': 14267712, 'steps': 74310, 'loss/train': 0.4331999719142914} 08/31/2021 02:34:44 - INFO - __main__ - Step 74312: {'lr': 0.0002589611711449137, 'samples': 14267904, 'steps': 74311, 'loss/train': 0.9396628141403198} 08/31/2021 02:34:44 - INFO - __main__ - Step 74313: {'lr': 0.0002589558678088061, 'samples': 14268096, 'steps': 74312, 'loss/train': 0.9168160557746887} 08/31/2021 02:34:45 - INFO - __main__ - Step 74314: {'lr': 0.00025895056446866314, 'samples': 14268288, 'steps': 74313, 'loss/train': 1.0886718034744263} 08/31/2021 02:34:45 - INFO - __main__ - Step 74315: {'lr': 0.0002589452611244872, 'samples': 14268480, 'steps': 74314, 'loss/train': 1.1992274522781372} 08/31/2021 02:34:46 - INFO - __main__ - Step 74316: {'lr': 0.00025893995777628083, 'samples': 14268672, 'steps': 74315, 'loss/train': 1.7442153692245483} 08/31/2021 02:34:47 - INFO - __main__ - Step 74317: {'lr': 0.0002589346544240461, 'samples': 14268864, 'steps': 74316, 'loss/train': 1.4884847402572632} 08/31/2021 02:34:47 - INFO - __main__ - Step 74318: {'lr': 0.00025892935106778555, 'samples': 14269056, 'steps': 74317, 'loss/train': 0.5752079486846924} 08/31/2021 02:34:48 - INFO - __main__ - Step 74319: {'lr': 0.0002589240477075015, 'samples': 14269248, 'steps': 74318, 'loss/train': 1.4356213808059692} 08/31/2021 02:34:48 - INFO - __main__ - Step 74320: {'lr': 0.0002589187443431966, 'samples': 14269440, 'steps': 74319, 'loss/train': 1.367120623588562} 08/31/2021 02:34:49 - INFO - __main__ - Step 74321: {'lr': 0.00025891344097487293, 'samples': 14269632, 'steps': 74320, 'loss/train': 0.6902837157249451} 08/31/2021 02:34:50 - INFO - __main__ - Step 74322: {'lr': 0.000258908137602533, 'samples': 14269824, 'steps': 74321, 'loss/train': 1.1536027193069458} 08/31/2021 02:34:50 - INFO - __main__ - Step 74323: {'lr': 0.0002589028342261793, 'samples': 14270016, 'steps': 74322, 'loss/train': 1.1278836727142334} 08/31/2021 02:34:51 - INFO - __main__ - Step 74324: {'lr': 0.000258897530845814, 'samples': 14270208, 'steps': 74323, 'loss/train': 0.8953182697296143} 08/31/2021 02:34:51 - INFO - __main__ - Step 74325: {'lr': 0.00025889222746143964, 'samples': 14270400, 'steps': 74324, 'loss/train': 1.5609681606292725} 08/31/2021 02:34:51 - INFO - __main__ - Step 74326: {'lr': 0.0002588869240730586, 'samples': 14270592, 'steps': 74325, 'loss/train': 0.7876879572868347} 08/31/2021 02:34:53 - INFO - __main__ - Step 74327: {'lr': 0.0002588816206806733, 'samples': 14270784, 'steps': 74326, 'loss/train': 1.6924725770950317} 08/31/2021 02:34:53 - INFO - __main__ - Step 74328: {'lr': 0.000258876317284286, 'samples': 14270976, 'steps': 74327, 'loss/train': 1.21024489402771} 08/31/2021 02:34:54 - INFO - __main__ - Step 74329: {'lr': 0.00025887101388389917, 'samples': 14271168, 'steps': 74328, 'loss/train': 0.07404961436986923} 08/31/2021 02:34:54 - INFO - __main__ - Step 74330: {'lr': 0.00025886571047951517, 'samples': 14271360, 'steps': 74329, 'loss/train': 1.1054123640060425} 08/31/2021 02:34:54 - INFO - __main__ - Step 74331: {'lr': 0.0002588604070711365, 'samples': 14271552, 'steps': 74330, 'loss/train': 1.075192928314209} 08/31/2021 02:34:56 - INFO - __main__ - Step 74332: {'lr': 0.00025885510365876544, 'samples': 14271744, 'steps': 74331, 'loss/train': 0.05402268096804619} 08/31/2021 02:34:56 - INFO - __main__ - Step 74333: {'lr': 0.0002588498002424044, 'samples': 14271936, 'steps': 74332, 'loss/train': 1.40254545211792} 08/31/2021 02:34:57 - INFO - __main__ - Step 74334: {'lr': 0.0002588444968220558, 'samples': 14272128, 'steps': 74333, 'loss/train': 0.7126697897911072} 08/31/2021 02:34:57 - INFO - __main__ - Step 74335: {'lr': 0.00025883919339772196, 'samples': 14272320, 'steps': 74334, 'loss/train': 0.9266878366470337} 08/31/2021 02:34:57 - INFO - __main__ - Step 74336: {'lr': 0.00025883388996940533, 'samples': 14272512, 'steps': 74335, 'loss/train': 0.7214785814285278} 08/31/2021 02:35:00 - INFO - __main__ - Step 74337: {'lr': 0.0002588285865371083, 'samples': 14272704, 'steps': 74336, 'loss/train': 0.7301530838012695} 08/31/2021 02:35:00 - INFO - __main__ - Step 74338: {'lr': 0.00025882328310083323, 'samples': 14272896, 'steps': 74337, 'loss/train': 0.7339147925376892} 08/31/2021 02:35:01 - INFO - __main__ - Step 74339: {'lr': 0.0002588179796605826, 'samples': 14273088, 'steps': 74338, 'loss/train': 0.8204435110092163} 08/31/2021 02:35:01 - INFO - __main__ - Step 74340: {'lr': 0.0002588126762163586, 'samples': 14273280, 'steps': 74339, 'loss/train': 1.8064764738082886} 08/31/2021 02:35:01 - INFO - __main__ - Step 74341: {'lr': 0.0002588073727681638, 'samples': 14273472, 'steps': 74340, 'loss/train': 0.9000580906867981} 08/31/2021 02:35:02 - INFO - __main__ - Step 74342: {'lr': 0.0002588020693160005, 'samples': 14273664, 'steps': 74341, 'loss/train': 0.7520741820335388} 08/31/2021 02:35:03 - INFO - __main__ - Step 74343: {'lr': 0.0002587967658598712, 'samples': 14273856, 'steps': 74342, 'loss/train': 1.5911692380905151} 08/31/2021 02:35:04 - INFO - __main__ - Step 74344: {'lr': 0.0002587914623997782, 'samples': 14274048, 'steps': 74343, 'loss/train': 1.792311191558838} 08/31/2021 02:35:04 - INFO - __main__ - Step 74345: {'lr': 0.0002587861589357239, 'samples': 14274240, 'steps': 74344, 'loss/train': 0.7687051892280579} 08/31/2021 02:35:05 - INFO - __main__ - Step 74346: {'lr': 0.0002587808554677106, 'samples': 14274432, 'steps': 74345, 'loss/train': 1.9158873558044434} 08/31/2021 02:35:05 - INFO - __main__ - Step 74347: {'lr': 0.0002587755519957409, 'samples': 14274624, 'steps': 74346, 'loss/train': 1.368952989578247} 08/31/2021 02:35:07 - INFO - __main__ - Step 74348: {'lr': 0.00025877024851981694, 'samples': 14274816, 'steps': 74347, 'loss/train': 1.055505633354187} 08/31/2021 02:35:07 - INFO - __main__ - Step 74349: {'lr': 0.00025876494503994135, 'samples': 14275008, 'steps': 74348, 'loss/train': 1.2922903299331665} 08/31/2021 02:35:08 - INFO - __main__ - Step 74350: {'lr': 0.00025875964155611634, 'samples': 14275200, 'steps': 74349, 'loss/train': 1.393334984779358} 08/31/2021 02:35:08 - INFO - __main__ - Step 74351: {'lr': 0.00025875433806834446, 'samples': 14275392, 'steps': 74350, 'loss/train': 0.6933605670928955} 08/31/2021 02:35:08 - INFO - __main__ - Step 74352: {'lr': 0.00025874903457662803, 'samples': 14275584, 'steps': 74351, 'loss/train': 1.1336798667907715} 08/31/2021 02:35:10 - INFO - __main__ - Step 74353: {'lr': 0.00025874373108096934, 'samples': 14275776, 'steps': 74352, 'loss/train': 0.10843151807785034} 08/31/2021 02:35:11 - INFO - __main__ - Step 74354: {'lr': 0.00025873842758137087, 'samples': 14275968, 'steps': 74353, 'loss/train': 0.770236611366272} 08/31/2021 02:35:11 - INFO - __main__ - Step 74355: {'lr': 0.00025873312407783495, 'samples': 14276160, 'steps': 74354, 'loss/train': 1.5992051362991333} 08/31/2021 02:35:11 - INFO - __main__ - Step 74356: {'lr': 0.0002587278205703641, 'samples': 14276352, 'steps': 74355, 'loss/train': 1.3020687103271484} 08/31/2021 02:35:12 - INFO - __main__ - Step 74357: {'lr': 0.00025872251705896056, 'samples': 14276544, 'steps': 74356, 'loss/train': 1.4427181482315063} 08/31/2021 02:35:13 - INFO - __main__ - Step 74358: {'lr': 0.0002587172135436269, 'samples': 14276736, 'steps': 74357, 'loss/train': 1.4800242185592651} 08/31/2021 02:35:14 - INFO - __main__ - Step 74359: {'lr': 0.0002587119100243653, 'samples': 14276928, 'steps': 74358, 'loss/train': 1.733041524887085} 08/31/2021 02:35:14 - INFO - __main__ - Step 74360: {'lr': 0.00025870660650117826, 'samples': 14277120, 'steps': 74359, 'loss/train': 1.4963709115982056} 08/31/2021 02:35:14 - INFO - __main__ - Step 74361: {'lr': 0.0002587013029740682, 'samples': 14277312, 'steps': 74360, 'loss/train': 1.2554441690444946} 08/31/2021 02:35:15 - INFO - __main__ - Step 74362: {'lr': 0.0002586959994430374, 'samples': 14277504, 'steps': 74361, 'loss/train': 1.3641350269317627} 08/31/2021 02:35:15 - INFO - __main__ - Step 74363: {'lr': 0.0002586906959080884, 'samples': 14277696, 'steps': 74362, 'loss/train': 1.0793553590774536} 08/31/2021 02:35:16 - INFO - __main__ - Step 74364: {'lr': 0.0002586853923692234, 'samples': 14277888, 'steps': 74363, 'loss/train': 1.533365249633789} 08/31/2021 02:35:17 - INFO - __main__ - Step 74365: {'lr': 0.000258680088826445, 'samples': 14278080, 'steps': 74364, 'loss/train': 1.2086774110794067} 08/31/2021 02:35:17 - INFO - __main__ - Step 74366: {'lr': 0.00025867478527975547, 'samples': 14278272, 'steps': 74365, 'loss/train': 1.402422308921814} 08/31/2021 02:35:18 - INFO - __main__ - Step 74367: {'lr': 0.00025866948172915716, 'samples': 14278464, 'steps': 74366, 'loss/train': 1.3986009359359741} 08/31/2021 02:35:18 - INFO - __main__ - Step 74368: {'lr': 0.0002586641781746525, 'samples': 14278656, 'steps': 74367, 'loss/train': 1.9966706037521362} 08/31/2021 02:35:20 - INFO - __main__ - Step 74369: {'lr': 0.000258658874616244, 'samples': 14278848, 'steps': 74368, 'loss/train': 0.663760781288147} 08/31/2021 02:35:20 - INFO - __main__ - Step 74370: {'lr': 0.0002586535710539338, 'samples': 14279040, 'steps': 74369, 'loss/train': 0.7204717993736267} 08/31/2021 02:35:20 - INFO - __main__ - Step 74371: {'lr': 0.0002586482674877246, 'samples': 14279232, 'steps': 74370, 'loss/train': 0.8693673610687256} 08/31/2021 02:35:21 - INFO - __main__ - Step 74372: {'lr': 0.00025864296391761853, 'samples': 14279424, 'steps': 74371, 'loss/train': 0.15485818684101105} 08/31/2021 02:35:21 - INFO - __main__ - Step 74373: {'lr': 0.00025863766034361815, 'samples': 14279616, 'steps': 74372, 'loss/train': 1.471200942993164} 08/31/2021 02:35:23 - INFO - __main__ - Step 74374: {'lr': 0.00025863235676572565, 'samples': 14279808, 'steps': 74373, 'loss/train': 0.7602594494819641} 08/31/2021 02:35:23 - INFO - __main__ - Step 74375: {'lr': 0.00025862705318394357, 'samples': 14280000, 'steps': 74374, 'loss/train': 1.529714822769165} 08/31/2021 02:35:23 - INFO - __main__ - Step 74376: {'lr': 0.00025862174959827435, 'samples': 14280192, 'steps': 74375, 'loss/train': 0.2555845379829407} 08/31/2021 02:35:24 - INFO - __main__ - Step 74377: {'lr': 0.0002586164460087203, 'samples': 14280384, 'steps': 74376, 'loss/train': 1.1914265155792236} 08/31/2021 02:35:24 - INFO - __main__ - Step 74378: {'lr': 0.0002586111424152838, 'samples': 14280576, 'steps': 74377, 'loss/train': 1.425399899482727} 08/31/2021 02:35:26 - INFO - __main__ - Step 74379: {'lr': 0.0002586058388179672, 'samples': 14280768, 'steps': 74378, 'loss/train': 0.6143218874931335} 08/31/2021 02:35:26 - INFO - __main__ - Step 74380: {'lr': 0.00025860053521677297, 'samples': 14280960, 'steps': 74379, 'loss/train': 0.6179105043411255} 08/31/2021 02:35:27 - INFO - __main__ - Step 74381: {'lr': 0.0002585952316117034, 'samples': 14281152, 'steps': 74380, 'loss/train': 0.482343465089798} 08/31/2021 02:35:27 - INFO - __main__ - Step 74382: {'lr': 0.00025858992800276105, 'samples': 14281344, 'steps': 74381, 'loss/train': 1.4569370746612549} 08/31/2021 02:35:28 - INFO - __main__ - Step 74383: {'lr': 0.0002585846243899482, 'samples': 14281536, 'steps': 74382, 'loss/train': 0.627951979637146} 08/31/2021 02:35:28 - INFO - __main__ - Step 74384: {'lr': 0.00025857932077326715, 'samples': 14281728, 'steps': 74383, 'loss/train': 1.4350420236587524} 08/31/2021 02:35:29 - INFO - __main__ - Step 74385: {'lr': 0.00025857401715272056, 'samples': 14281920, 'steps': 74384, 'loss/train': 1.1980897188186646} 08/31/2021 02:35:30 - INFO - __main__ - Step 74386: {'lr': 0.0002585687135283106, 'samples': 14282112, 'steps': 74385, 'loss/train': 0.911659300327301} 08/31/2021 02:35:30 - INFO - __main__ - Step 74387: {'lr': 0.00025856340990003965, 'samples': 14282304, 'steps': 74386, 'loss/train': 1.2421551942825317} 08/31/2021 02:35:31 - INFO - __main__ - Step 74388: {'lr': 0.00025855810626791015, 'samples': 14282496, 'steps': 74387, 'loss/train': 1.3643938302993774} 08/31/2021 02:35:31 - INFO - __main__ - Step 74389: {'lr': 0.00025855280263192447, 'samples': 14282688, 'steps': 74388, 'loss/train': 1.568123698234558} 08/31/2021 02:35:32 - INFO - __main__ - Step 74390: {'lr': 0.00025854749899208515, 'samples': 14282880, 'steps': 74389, 'loss/train': 0.9539188146591187} 08/31/2021 02:35:33 - INFO - __main__ - Step 74391: {'lr': 0.0002585421953483944, 'samples': 14283072, 'steps': 74390, 'loss/train': 1.2203551530838013} 08/31/2021 02:35:33 - INFO - __main__ - Step 74392: {'lr': 0.00025853689170085467, 'samples': 14283264, 'steps': 74391, 'loss/train': 0.6575886011123657} 08/31/2021 02:35:33 - INFO - __main__ - Step 74393: {'lr': 0.0002585315880494684, 'samples': 14283456, 'steps': 74392, 'loss/train': 1.0170729160308838} 08/31/2021 02:35:34 - INFO - __main__ - Step 74394: {'lr': 0.0002585262843942378, 'samples': 14283648, 'steps': 74393, 'loss/train': 1.2863327264785767} 08/31/2021 02:35:35 - INFO - __main__ - Step 74395: {'lr': 0.0002585209807351654, 'samples': 14283840, 'steps': 74394, 'loss/train': 1.6080724000930786} 08/31/2021 02:35:36 - INFO - __main__ - Step 74396: {'lr': 0.0002585156770722537, 'samples': 14284032, 'steps': 74395, 'loss/train': 1.3983722925186157} 08/31/2021 02:35:36 - INFO - __main__ - Step 74397: {'lr': 0.00025851037340550486, 'samples': 14284224, 'steps': 74396, 'loss/train': 1.1968430280685425} 08/31/2021 02:35:36 - INFO - __main__ - Step 74398: {'lr': 0.00025850506973492147, 'samples': 14284416, 'steps': 74397, 'loss/train': 1.459964394569397} 08/31/2021 02:35:37 - INFO - __main__ - Step 74399: {'lr': 0.0002584997660605058, 'samples': 14284608, 'steps': 74398, 'loss/train': 0.7649711966514587} 08/31/2021 02:35:38 - INFO - __main__ - Step 74400: {'lr': 0.00025849446238226026, 'samples': 14284800, 'steps': 74399, 'loss/train': 1.5849062204360962} 08/31/2021 02:35:39 - INFO - __main__ - Step 74401: {'lr': 0.0002584891587001872, 'samples': 14284992, 'steps': 74400, 'loss/train': 1.1128712892532349} 08/31/2021 02:35:39 - INFO - __main__ - Step 74402: {'lr': 0.00025848385501428913, 'samples': 14285184, 'steps': 74401, 'loss/train': 0.7961801290512085} 08/31/2021 02:35:40 - INFO - __main__ - Step 74403: {'lr': 0.0002584785513245683, 'samples': 14285376, 'steps': 74402, 'loss/train': 0.9713432788848877} 08/31/2021 02:35:40 - INFO - __main__ - Step 74404: {'lr': 0.0002584732476310271, 'samples': 14285568, 'steps': 74403, 'loss/train': 0.6929603219032288} 08/31/2021 02:35:42 - INFO - __main__ - Step 74405: {'lr': 0.00025846794393366817, 'samples': 14285760, 'steps': 74404, 'loss/train': 1.1478196382522583} 08/31/2021 02:35:43 - INFO - __main__ - Step 74406: {'lr': 0.0002584626402324936, 'samples': 14285952, 'steps': 74405, 'loss/train': 1.394416093826294} 08/31/2021 02:35:43 - INFO - __main__ - Step 74407: {'lr': 0.0002584573365275059, 'samples': 14286144, 'steps': 74406, 'loss/train': 0.829887866973877} 08/31/2021 02:35:43 - INFO - __main__ - Step 74408: {'lr': 0.0002584520328187075, 'samples': 14286336, 'steps': 74407, 'loss/train': 0.8966425061225891} 08/31/2021 02:35:44 - INFO - __main__ - Step 74409: {'lr': 0.00025844672910610076, 'samples': 14286528, 'steps': 74408, 'loss/train': 1.6378780603408813} 08/31/2021 02:35:45 - INFO - __main__ - Step 74410: {'lr': 0.000258441425389688, 'samples': 14286720, 'steps': 74409, 'loss/train': 1.5692346096038818} 08/31/2021 02:35:46 - INFO - __main__ - Step 74411: {'lr': 0.0002584361216694716, 'samples': 14286912, 'steps': 74410, 'loss/train': 0.9675005078315735} 08/31/2021 02:35:46 - INFO - __main__ - Step 74412: {'lr': 0.00025843081794545413, 'samples': 14287104, 'steps': 74411, 'loss/train': 0.9202162623405457} 08/31/2021 02:35:46 - INFO - __main__ - Step 74413: {'lr': 0.0002584255142176378, 'samples': 14287296, 'steps': 74412, 'loss/train': 1.770005702972412} 08/31/2021 02:35:47 - INFO - __main__ - Step 74414: {'lr': 0.0002584202104860251, 'samples': 14287488, 'steps': 74413, 'loss/train': 1.322332501411438} 08/31/2021 02:35:47 - INFO - __main__ - Step 74415: {'lr': 0.0002584149067506183, 'samples': 14287680, 'steps': 74414, 'loss/train': 0.9169453978538513} 08/31/2021 02:35:49 - INFO - __main__ - Step 74416: {'lr': 0.00025840960301142, 'samples': 14287872, 'steps': 74415, 'loss/train': 1.9251108169555664} 08/31/2021 02:35:49 - INFO - __main__ - Step 74417: {'lr': 0.0002584042992684324, 'samples': 14288064, 'steps': 74416, 'loss/train': 0.26239213347435} 08/31/2021 02:35:49 - INFO - __main__ - Step 74418: {'lr': 0.000258398995521658, 'samples': 14288256, 'steps': 74417, 'loss/train': 1.5615224838256836} 08/31/2021 02:35:50 - INFO - __main__ - Step 74419: {'lr': 0.00025839369177109905, 'samples': 14288448, 'steps': 74418, 'loss/train': 0.9055259823799133} 08/31/2021 02:35:50 - INFO - __main__ - Step 74420: {'lr': 0.0002583883880167581, 'samples': 14288640, 'steps': 74419, 'loss/train': 1.5142158269882202} 08/31/2021 02:35:52 - INFO - __main__ - Step 74421: {'lr': 0.00025838308425863744, 'samples': 14288832, 'steps': 74420, 'loss/train': 1.4421206712722778} 08/31/2021 02:35:52 - INFO - __main__ - Step 74422: {'lr': 0.0002583777804967395, 'samples': 14289024, 'steps': 74421, 'loss/train': 1.1347122192382812} 08/31/2021 02:35:52 - INFO - __main__ - Step 74423: {'lr': 0.00025837247673106666, 'samples': 14289216, 'steps': 74422, 'loss/train': 0.745577335357666} 08/31/2021 02:35:53 - INFO - __main__ - Step 74424: {'lr': 0.00025836717296162133, 'samples': 14289408, 'steps': 74423, 'loss/train': 1.423754334449768} 08/31/2021 02:35:53 - INFO - __main__ - Step 74425: {'lr': 0.00025836186918840585, 'samples': 14289600, 'steps': 74424, 'loss/train': 1.3243144750595093} 08/31/2021 02:35:55 - INFO - __main__ - Step 74426: {'lr': 0.0002583565654114227, 'samples': 14289792, 'steps': 74425, 'loss/train': 1.5433332920074463} 08/31/2021 02:35:55 - INFO - __main__ - Step 74427: {'lr': 0.00025835126163067414, 'samples': 14289984, 'steps': 74426, 'loss/train': 0.5429815053939819} 08/31/2021 02:35:56 - INFO - __main__ - Step 74428: {'lr': 0.0002583459578461627, 'samples': 14290176, 'steps': 74427, 'loss/train': 1.1639913320541382} 08/31/2021 02:35:56 - INFO - __main__ - Step 74429: {'lr': 0.0002583406540578906, 'samples': 14290368, 'steps': 74428, 'loss/train': 1.3568751811981201} 08/31/2021 02:35:56 - INFO - __main__ - Step 74430: {'lr': 0.0002583353502658604, 'samples': 14290560, 'steps': 74429, 'loss/train': 1.6112301349639893} 08/31/2021 02:35:58 - INFO - __main__ - Step 74431: {'lr': 0.0002583300464700744, 'samples': 14290752, 'steps': 74430, 'loss/train': 0.3143899142742157} 08/31/2021 02:35:58 - INFO - __main__ - Step 74432: {'lr': 0.0002583247426705351, 'samples': 14290944, 'steps': 74431, 'loss/train': 0.15426687896251678} 08/31/2021 02:35:59 - INFO - __main__ - Step 74433: {'lr': 0.0002583194388672447, 'samples': 14291136, 'steps': 74432, 'loss/train': 1.1333158016204834} 08/31/2021 02:35:59 - INFO - __main__ - Step 74434: {'lr': 0.0002583141350602057, 'samples': 14291328, 'steps': 74433, 'loss/train': 1.2955243587493896} 08/31/2021 02:35:59 - INFO - __main__ - Step 74435: {'lr': 0.00025830883124942043, 'samples': 14291520, 'steps': 74434, 'loss/train': 2.085097551345825} 08/31/2021 02:36:00 - INFO - __main__ - Step 74436: {'lr': 0.00025830352743489137, 'samples': 14291712, 'steps': 74435, 'loss/train': 1.4108262062072754} 08/31/2021 02:36:01 - INFO - __main__ - Step 74437: {'lr': 0.0002582982236166209, 'samples': 14291904, 'steps': 74436, 'loss/train': 0.6045325994491577} 08/31/2021 02:36:02 - INFO - __main__ - Step 74438: {'lr': 0.0002582929197946113, 'samples': 14292096, 'steps': 74437, 'loss/train': 1.1069196462631226} 08/31/2021 02:36:02 - INFO - __main__ - Step 74439: {'lr': 0.00025828761596886516, 'samples': 14292288, 'steps': 74438, 'loss/train': 1.5634500980377197} 08/31/2021 02:36:03 - INFO - __main__ - Step 74440: {'lr': 0.0002582823121393847, 'samples': 14292480, 'steps': 74439, 'loss/train': 0.8308555483818054} 08/31/2021 02:36:03 - INFO - __main__ - Step 74441: {'lr': 0.0002582770083061723, 'samples': 14292672, 'steps': 74440, 'loss/train': 1.224547266960144} 08/31/2021 02:36:03 - INFO - __main__ - Step 74442: {'lr': 0.0002582717044692305, 'samples': 14292864, 'steps': 74441, 'loss/train': 6.869625568389893} 08/31/2021 02:36:05 - INFO - __main__ - Step 74443: {'lr': 0.00025826640062856157, 'samples': 14293056, 'steps': 74442, 'loss/train': 6.381706237792969} 08/31/2021 02:36:05 - INFO - __main__ - Step 74444: {'lr': 0.0002582610967841679, 'samples': 14293248, 'steps': 74443, 'loss/train': 1.351515769958496} 08/31/2021 02:36:06 - INFO - __main__ - Step 74445: {'lr': 0.00025825579293605193, 'samples': 14293440, 'steps': 74444, 'loss/train': 1.3911889791488647} 08/31/2021 02:36:06 - INFO - __main__ - Step 74446: {'lr': 0.000258250489084216, 'samples': 14293632, 'steps': 74445, 'loss/train': 1.1784145832061768} 08/31/2021 02:36:06 - INFO - __main__ - Step 74447: {'lr': 0.00025824518522866253, 'samples': 14293824, 'steps': 74446, 'loss/train': 1.5809239149093628} 08/31/2021 02:36:08 - INFO - __main__ - Step 74448: {'lr': 0.0002582398813693939, 'samples': 14294016, 'steps': 74447, 'loss/train': 0.7831807136535645} 08/31/2021 02:36:08 - INFO - __main__ - Step 74449: {'lr': 0.00025823457750641257, 'samples': 14294208, 'steps': 74448, 'loss/train': 1.0719236135482788} 08/31/2021 02:36:09 - INFO - __main__ - Step 74450: {'lr': 0.00025822927363972076, 'samples': 14294400, 'steps': 74449, 'loss/train': 1.6371486186981201} 08/31/2021 02:36:09 - INFO - __main__ - Step 74451: {'lr': 0.00025822396976932113, 'samples': 14294592, 'steps': 74450, 'loss/train': 2.0443778038024902} 08/31/2021 02:36:09 - INFO - __main__ - Step 74452: {'lr': 0.00025821866589521576, 'samples': 14294784, 'steps': 74451, 'loss/train': 0.9747274518013} 08/31/2021 02:36:11 - INFO - __main__ - Step 74453: {'lr': 0.0002582133620174072, 'samples': 14294976, 'steps': 74452, 'loss/train': 1.5400289297103882} 08/31/2021 02:36:11 - INFO - __main__ - Step 74454: {'lr': 0.00025820805813589785, 'samples': 14295168, 'steps': 74453, 'loss/train': 1.1734814643859863} 08/31/2021 02:36:12 - INFO - __main__ - Step 74455: {'lr': 0.0002582027542506901, 'samples': 14295360, 'steps': 74454, 'loss/train': 1.454685926437378} 08/31/2021 02:36:12 - INFO - __main__ - Step 74456: {'lr': 0.0002581974503617863, 'samples': 14295552, 'steps': 74455, 'loss/train': 0.8694735169410706} 08/31/2021 02:36:12 - INFO - __main__ - Step 74457: {'lr': 0.00025819214646918885, 'samples': 14295744, 'steps': 74456, 'loss/train': 0.23965254426002502} 08/31/2021 02:36:13 - INFO - __main__ - Step 74458: {'lr': 0.00025818684257290016, 'samples': 14295936, 'steps': 74457, 'loss/train': 1.6999057531356812} 08/31/2021 02:36:15 - INFO - __main__ - Step 74459: {'lr': 0.0002581815386729226, 'samples': 14296128, 'steps': 74458, 'loss/train': 1.1098448038101196} 08/31/2021 02:36:15 - INFO - __main__ - Step 74460: {'lr': 0.0002581762347692585, 'samples': 14296320, 'steps': 74459, 'loss/train': 1.476335883140564} 08/31/2021 02:36:15 - INFO - __main__ - Step 74461: {'lr': 0.0002581709308619104, 'samples': 14296512, 'steps': 74460, 'loss/train': 1.3838998079299927} 08/31/2021 02:36:16 - INFO - __main__ - Step 74462: {'lr': 0.00025816562695088057, 'samples': 14296704, 'steps': 74461, 'loss/train': 1.7689718008041382} 08/31/2021 02:36:16 - INFO - __main__ - Step 74463: {'lr': 0.0002581603230361715, 'samples': 14296896, 'steps': 74462, 'loss/train': 0.6998897790908813} 08/31/2021 02:36:18 - INFO - __main__ - Step 74464: {'lr': 0.00025815501911778546, 'samples': 14297088, 'steps': 74463, 'loss/train': 0.7647417783737183} 08/31/2021 02:36:18 - INFO - __main__ - Step 74465: {'lr': 0.00025814971519572485, 'samples': 14297280, 'steps': 74464, 'loss/train': 1.5117007493972778} 08/31/2021 02:36:19 - INFO - __main__ - Step 74466: {'lr': 0.0002581444112699921, 'samples': 14297472, 'steps': 74465, 'loss/train': 1.344641923904419} 08/31/2021 02:36:19 - INFO - __main__ - Step 74467: {'lr': 0.0002581391073405897, 'samples': 14297664, 'steps': 74466, 'loss/train': 1.956156849861145} 08/31/2021 02:36:19 - INFO - __main__ - Step 74468: {'lr': 0.0002581338034075199, 'samples': 14297856, 'steps': 74467, 'loss/train': 1.632014274597168} 08/31/2021 02:36:21 - INFO - __main__ - Step 74469: {'lr': 0.0002581284994707851, 'samples': 14298048, 'steps': 74468, 'loss/train': 1.3848518133163452} 08/31/2021 02:36:21 - INFO - __main__ - Step 74470: {'lr': 0.00025812319553038775, 'samples': 14298240, 'steps': 74469, 'loss/train': 1.5774784088134766} 08/31/2021 02:36:22 - INFO - __main__ - Step 74471: {'lr': 0.0002581178915863302, 'samples': 14298432, 'steps': 74470, 'loss/train': 0.8832056522369385} 08/31/2021 02:36:22 - INFO - __main__ - Step 74472: {'lr': 0.00025811258763861486, 'samples': 14298624, 'steps': 74471, 'loss/train': 1.4172884225845337} 08/31/2021 02:36:22 - INFO - __main__ - Step 74473: {'lr': 0.0002581072836872442, 'samples': 14298816, 'steps': 74472, 'loss/train': 0.04336697980761528} 08/31/2021 02:36:24 - INFO - __main__ - Step 74474: {'lr': 0.0002581019797322204, 'samples': 14299008, 'steps': 74473, 'loss/train': 1.5699857473373413} 08/31/2021 02:36:24 - INFO - __main__ - Step 74475: {'lr': 0.000258096675773546, 'samples': 14299200, 'steps': 74474, 'loss/train': 2.254112482070923} 08/31/2021 02:36:25 - INFO - __main__ - Step 74476: {'lr': 0.00025809137181122336, 'samples': 14299392, 'steps': 74475, 'loss/train': 1.3660073280334473} 08/31/2021 02:36:25 - INFO - __main__ - Step 74477: {'lr': 0.0002580860678452549, 'samples': 14299584, 'steps': 74476, 'loss/train': 1.1736165285110474} 08/31/2021 02:36:25 - INFO - __main__ - Step 74478: {'lr': 0.00025808076387564297, 'samples': 14299776, 'steps': 74477, 'loss/train': 1.067107915878296} 08/31/2021 02:36:27 - INFO - __main__ - Step 74479: {'lr': 0.00025807545990239, 'samples': 14299968, 'steps': 74478, 'loss/train': 0.7906565070152283} 08/31/2021 02:36:28 - INFO - __main__ - Step 74480: {'lr': 0.0002580701559254983, 'samples': 14300160, 'steps': 74479, 'loss/train': 1.859724998474121} 08/31/2021 02:36:28 - INFO - __main__ - Step 74481: {'lr': 0.00025806485194497037, 'samples': 14300352, 'steps': 74480, 'loss/train': 0.06243950501084328} 08/31/2021 02:36:28 - INFO - __main__ - Step 74482: {'lr': 0.0002580595479608085, 'samples': 14300544, 'steps': 74481, 'loss/train': 1.472823143005371} 08/31/2021 02:36:29 - INFO - __main__ - Step 74483: {'lr': 0.00025805424397301515, 'samples': 14300736, 'steps': 74482, 'loss/train': 0.055072613060474396} 08/31/2021 02:36:29 - INFO - __main__ - Step 74484: {'lr': 0.0002580489399815926, 'samples': 14300928, 'steps': 74483, 'loss/train': 1.5229222774505615} 08/31/2021 02:36:30 - INFO - __main__ - Step 74485: {'lr': 0.0002580436359865434, 'samples': 14301120, 'steps': 74484, 'loss/train': 1.0739091634750366} 08/31/2021 02:36:31 - INFO - __main__ - Step 74486: {'lr': 0.0002580383319878699, 'samples': 14301312, 'steps': 74485, 'loss/train': 1.8419253826141357} 08/31/2021 02:36:31 - INFO - __main__ - Step 74487: {'lr': 0.0002580330279855744, 'samples': 14301504, 'steps': 74486, 'loss/train': 1.4474729299545288} 08/31/2021 02:36:32 - INFO - __main__ - Step 74488: {'lr': 0.0002580277239796593, 'samples': 14301696, 'steps': 74487, 'loss/train': 1.4319040775299072} 08/31/2021 02:36:32 - INFO - __main__ - Step 74489: {'lr': 0.0002580224199701271, 'samples': 14301888, 'steps': 74488, 'loss/train': 0.8116939663887024} 08/31/2021 02:36:33 - INFO - __main__ - Step 74490: {'lr': 0.00025801711595698005, 'samples': 14302080, 'steps': 74489, 'loss/train': 1.2675411701202393} 08/31/2021 02:36:34 - INFO - __main__ - Step 74491: {'lr': 0.00025801181194022067, 'samples': 14302272, 'steps': 74490, 'loss/train': 0.7347664833068848} 08/31/2021 02:36:34 - INFO - __main__ - Step 74492: {'lr': 0.00025800650791985133, 'samples': 14302464, 'steps': 74491, 'loss/train': 1.5106018781661987} 08/31/2021 02:36:35 - INFO - __main__ - Step 74493: {'lr': 0.0002580012038958743, 'samples': 14302656, 'steps': 74492, 'loss/train': 1.2081751823425293} 08/31/2021 02:36:35 - INFO - __main__ - Step 74494: {'lr': 0.0002579958998682921, 'samples': 14302848, 'steps': 74493, 'loss/train': 0.03205345943570137} 08/31/2021 02:36:36 - INFO - __main__ - Step 74495: {'lr': 0.000257990595837107, 'samples': 14303040, 'steps': 74494, 'loss/train': 1.614316463470459} 08/31/2021 02:36:37 - INFO - __main__ - Step 74496: {'lr': 0.0002579852918023215, 'samples': 14303232, 'steps': 74495, 'loss/train': 1.7589807510375977} 08/31/2021 02:36:37 - INFO - __main__ - Step 74497: {'lr': 0.000257979987763938, 'samples': 14303424, 'steps': 74496, 'loss/train': 1.7547260522842407} 08/31/2021 02:36:38 - INFO - __main__ - Step 74498: {'lr': 0.0002579746837219588, 'samples': 14303616, 'steps': 74497, 'loss/train': 1.2003250122070312} 08/31/2021 02:36:38 - INFO - __main__ - Step 74499: {'lr': 0.00025796937967638634, 'samples': 14303808, 'steps': 74498, 'loss/train': 1.1179310083389282} 08/31/2021 02:36:39 - INFO - __main__ - Step 74500: {'lr': 0.00025796407562722303, 'samples': 14304000, 'steps': 74499, 'loss/train': 1.1028282642364502} 08/31/2021 02:36:40 - INFO - __main__ - Step 74501: {'lr': 0.00025795877157447117, 'samples': 14304192, 'steps': 74500, 'loss/train': 0.2599307596683502} 08/31/2021 02:36:40 - INFO - __main__ - Step 74502: {'lr': 0.0002579534675181332, 'samples': 14304384, 'steps': 74501, 'loss/train': 1.2402182817459106} 08/31/2021 02:36:40 - INFO - __main__ - Step 74503: {'lr': 0.0002579481634582115, 'samples': 14304576, 'steps': 74502, 'loss/train': 1.0647069215774536} 08/31/2021 02:36:41 - INFO - __main__ - Step 74504: {'lr': 0.0002579428593947086, 'samples': 14304768, 'steps': 74503, 'loss/train': 1.140574336051941} 08/31/2021 02:36:42 - INFO - __main__ - Step 74505: {'lr': 0.0002579375553276267, 'samples': 14304960, 'steps': 74504, 'loss/train': 1.2417799234390259} 08/31/2021 02:36:43 - INFO - __main__ - Step 74506: {'lr': 0.0002579322512569683, 'samples': 14305152, 'steps': 74505, 'loss/train': 2.0508010387420654} 08/31/2021 02:36:43 - INFO - __main__ - Step 74507: {'lr': 0.0002579269471827357, 'samples': 14305344, 'steps': 74506, 'loss/train': 0.8004079461097717} 08/31/2021 02:36:43 - INFO - __main__ - Step 74508: {'lr': 0.00025792164310493133, 'samples': 14305536, 'steps': 74507, 'loss/train': 1.1843006610870361} 08/31/2021 02:36:44 - INFO - __main__ - Step 74509: {'lr': 0.0002579163390235576, 'samples': 14305728, 'steps': 74508, 'loss/train': 0.519808292388916} 08/31/2021 02:36:46 - INFO - __main__ - Step 74510: {'lr': 0.0002579110349386169, 'samples': 14305920, 'steps': 74509, 'loss/train': 1.230278491973877} 08/31/2021 02:36:46 - INFO - __main__ - Step 74511: {'lr': 0.0002579057308501116, 'samples': 14306112, 'steps': 74510, 'loss/train': 1.565902590751648} 08/31/2021 02:36:47 - INFO - __main__ - Step 74512: {'lr': 0.00025790042675804414, 'samples': 14306304, 'steps': 74511, 'loss/train': 1.6457242965698242} 08/31/2021 02:36:47 - INFO - __main__ - Step 74513: {'lr': 0.00025789512266241685, 'samples': 14306496, 'steps': 74512, 'loss/train': 1.2397527694702148} 08/31/2021 02:36:47 - INFO - __main__ - Step 74514: {'lr': 0.00025788981856323214, 'samples': 14306688, 'steps': 74513, 'loss/train': 1.592482089996338} 08/31/2021 02:36:49 - INFO - __main__ - Step 74515: {'lr': 0.0002578845144604924, 'samples': 14306880, 'steps': 74514, 'loss/train': 1.0190237760543823} 08/31/2021 02:36:49 - INFO - __main__ - Step 74516: {'lr': 0.00025787921035419996, 'samples': 14307072, 'steps': 74515, 'loss/train': 1.230097770690918} 08/31/2021 02:36:50 - INFO - __main__ - Step 74517: {'lr': 0.0002578739062443574, 'samples': 14307264, 'steps': 74516, 'loss/train': 1.4789581298828125} 08/31/2021 02:36:50 - INFO - __main__ - Step 74518: {'lr': 0.00025786860213096685, 'samples': 14307456, 'steps': 74517, 'loss/train': 1.126114845275879} 08/31/2021 02:36:50 - INFO - __main__ - Step 74519: {'lr': 0.00025786329801403093, 'samples': 14307648, 'steps': 74518, 'loss/train': 1.4933680295944214} 08/31/2021 02:36:51 - INFO - __main__ - Step 74520: {'lr': 0.00025785799389355183, 'samples': 14307840, 'steps': 74519, 'loss/train': 1.2653377056121826} 08/31/2021 02:36:52 - INFO - __main__ - Step 74521: {'lr': 0.00025785268976953206, 'samples': 14308032, 'steps': 74520, 'loss/train': 1.252185583114624} 08/31/2021 02:36:53 - INFO - __main__ - Step 74522: {'lr': 0.0002578473856419741, 'samples': 14308224, 'steps': 74521, 'loss/train': 1.5669416189193726} 08/31/2021 02:36:53 - INFO - __main__ - Step 74523: {'lr': 0.00025784208151088007, 'samples': 14308416, 'steps': 74522, 'loss/train': 0.8888974785804749} 08/31/2021 02:36:53 - INFO - __main__ - Step 74524: {'lr': 0.0002578367773762526, 'samples': 14308608, 'steps': 74523, 'loss/train': 0.906305193901062} 08/31/2021 02:36:54 - INFO - __main__ - Step 74525: {'lr': 0.000257831473238094, 'samples': 14308800, 'steps': 74524, 'loss/train': 1.9122916460037231} 08/31/2021 02:36:55 - INFO - __main__ - Step 74526: {'lr': 0.0002578261690964067, 'samples': 14308992, 'steps': 74525, 'loss/train': 0.9697586894035339} 08/31/2021 02:36:56 - INFO - __main__ - Step 74527: {'lr': 0.000257820864951193, 'samples': 14309184, 'steps': 74526, 'loss/train': 1.3821486234664917} 08/31/2021 02:36:56 - INFO - __main__ - Step 74528: {'lr': 0.0002578155608024553, 'samples': 14309376, 'steps': 74527, 'loss/train': 1.6440646648406982} 08/31/2021 02:36:56 - INFO - __main__ - Step 74529: {'lr': 0.0002578102566501961, 'samples': 14309568, 'steps': 74528, 'loss/train': 0.4005886912345886} 08/31/2021 02:36:57 - INFO - __main__ - Step 74530: {'lr': 0.00025780495249441764, 'samples': 14309760, 'steps': 74529, 'loss/train': 1.4193229675292969} 08/31/2021 02:36:58 - INFO - __main__ - Step 74531: {'lr': 0.0002577996483351225, 'samples': 14309952, 'steps': 74530, 'loss/train': 0.8393095135688782} 08/31/2021 02:36:59 - INFO - __main__ - Step 74532: {'lr': 0.0002577943441723128, 'samples': 14310144, 'steps': 74531, 'loss/train': 1.5027529001235962} 08/31/2021 02:36:59 - INFO - __main__ - Step 74533: {'lr': 0.00025778904000599127, 'samples': 14310336, 'steps': 74532, 'loss/train': 1.314251184463501} 08/31/2021 02:37:00 - INFO - __main__ - Step 74534: {'lr': 0.00025778373583616005, 'samples': 14310528, 'steps': 74533, 'loss/train': 1.5456843376159668} 08/31/2021 02:37:00 - INFO - __main__ - Step 74535: {'lr': 0.00025777843166282155, 'samples': 14310720, 'steps': 74534, 'loss/train': 0.06128116697072983} 08/31/2021 02:37:01 - INFO - __main__ - Step 74536: {'lr': 0.00025777312748597825, 'samples': 14310912, 'steps': 74535, 'loss/train': 1.0616837739944458} 08/31/2021 02:37:02 - INFO - __main__ - Step 74537: {'lr': 0.0002577678233056325, 'samples': 14311104, 'steps': 74536, 'loss/train': 1.2470543384552002} 08/31/2021 02:37:02 - INFO - __main__ - Step 74538: {'lr': 0.00025776251912178666, 'samples': 14311296, 'steps': 74537, 'loss/train': 1.3326419591903687} 08/31/2021 02:37:03 - INFO - __main__ - Step 74539: {'lr': 0.0002577572149344432, 'samples': 14311488, 'steps': 74538, 'loss/train': 0.15270225703716278} 08/31/2021 02:37:03 - INFO - __main__ - Step 74540: {'lr': 0.0002577519107436044, 'samples': 14311680, 'steps': 74539, 'loss/train': 1.3426393270492554} 08/31/2021 02:37:05 - INFO - __main__ - Step 74541: {'lr': 0.0002577466065492727, 'samples': 14311872, 'steps': 74540, 'loss/train': 1.956488847732544} 08/31/2021 02:37:05 - INFO - __main__ - Step 74542: {'lr': 0.00025774130235145054, 'samples': 14312064, 'steps': 74541, 'loss/train': 0.86993008852005} 08/31/2021 02:37:05 - INFO - __main__ - Step 74543: {'lr': 0.00025773599815014027, 'samples': 14312256, 'steps': 74542, 'loss/train': 1.3764652013778687} 08/31/2021 02:37:06 - INFO - __main__ - Step 74544: {'lr': 0.0002577306939453443, 'samples': 14312448, 'steps': 74543, 'loss/train': 1.2191798686981201} 08/31/2021 02:37:06 - INFO - __main__ - Step 74545: {'lr': 0.00025772538973706493, 'samples': 14312640, 'steps': 74544, 'loss/train': 1.4068962335586548} 08/31/2021 02:37:06 - INFO - __main__ - Step 74546: {'lr': 0.00025772008552530474, 'samples': 14312832, 'steps': 74545, 'loss/train': 1.2133363485336304} 08/31/2021 02:37:08 - INFO - __main__ - Step 74547: {'lr': 0.0002577147813100659, 'samples': 14313024, 'steps': 74546, 'loss/train': 1.5610371828079224} 08/31/2021 02:37:08 - INFO - __main__ - Step 74548: {'lr': 0.0002577094770913509, 'samples': 14313216, 'steps': 74547, 'loss/train': 1.2431707382202148} 08/31/2021 02:37:09 - INFO - __main__ - Step 74549: {'lr': 0.00025770417286916217, 'samples': 14313408, 'steps': 74548, 'loss/train': 1.7197996377944946} 08/31/2021 02:37:09 - INFO - __main__ - Step 74550: {'lr': 0.000257698868643502, 'samples': 14313600, 'steps': 74549, 'loss/train': 1.1930601596832275} 08/31/2021 02:37:09 - INFO - __main__ - Step 74551: {'lr': 0.00025769356441437285, 'samples': 14313792, 'steps': 74550, 'loss/train': 1.0875781774520874} 08/31/2021 02:37:11 - INFO - __main__ - Step 74552: {'lr': 0.0002576882601817771, 'samples': 14313984, 'steps': 74551, 'loss/train': 1.3441274166107178} 08/31/2021 02:37:11 - INFO - __main__ - Step 74553: {'lr': 0.00025768295594571724, 'samples': 14314176, 'steps': 74552, 'loss/train': 0.9781581163406372} 08/31/2021 02:37:12 - INFO - __main__ - Step 74554: {'lr': 0.00025767765170619546, 'samples': 14314368, 'steps': 74553, 'loss/train': 1.3572914600372314} 08/31/2021 02:37:12 - INFO - __main__ - Step 74555: {'lr': 0.0002576723474632142, 'samples': 14314560, 'steps': 74554, 'loss/train': 1.7579375505447388} 08/31/2021 02:37:12 - INFO - __main__ - Step 74556: {'lr': 0.00025766704321677597, 'samples': 14314752, 'steps': 74555, 'loss/train': 0.8433244824409485} 08/31/2021 02:37:14 - INFO - __main__ - Step 74557: {'lr': 0.0002576617389668831, 'samples': 14314944, 'steps': 74556, 'loss/train': 1.6148121356964111} 08/31/2021 02:37:14 - INFO - __main__ - Step 74558: {'lr': 0.00025765643471353794, 'samples': 14315136, 'steps': 74557, 'loss/train': 1.746972918510437} 08/31/2021 02:37:15 - INFO - __main__ - Step 74559: {'lr': 0.0002576511304567429, 'samples': 14315328, 'steps': 74558, 'loss/train': 1.56871497631073} 08/31/2021 02:37:15 - INFO - __main__ - Step 74560: {'lr': 0.00025764582619650046, 'samples': 14315520, 'steps': 74559, 'loss/train': 1.3230823278427124} 08/31/2021 02:37:15 - INFO - __main__ - Step 74561: {'lr': 0.00025764052193281284, 'samples': 14315712, 'steps': 74560, 'loss/train': 0.910186231136322} 08/31/2021 02:37:17 - INFO - __main__ - Step 74562: {'lr': 0.00025763521766568255, 'samples': 14315904, 'steps': 74561, 'loss/train': 1.8123935461044312} 08/31/2021 02:37:18 - INFO - __main__ - Step 74563: {'lr': 0.00025762991339511193, 'samples': 14316096, 'steps': 74562, 'loss/train': 1.2659566402435303} 08/31/2021 02:37:18 - INFO - __main__ - Step 74564: {'lr': 0.0002576246091211034, 'samples': 14316288, 'steps': 74563, 'loss/train': 1.2960171699523926} 08/31/2021 02:37:18 - INFO - __main__ - Step 74565: {'lr': 0.0002576193048436594, 'samples': 14316480, 'steps': 74564, 'loss/train': 1.2776566743850708} 08/31/2021 02:37:19 - INFO - __main__ - Step 74566: {'lr': 0.00025761400056278217, 'samples': 14316672, 'steps': 74565, 'loss/train': 1.2078914642333984} 08/31/2021 02:37:19 - INFO - __main__ - Step 74567: {'lr': 0.0002576086962784742, 'samples': 14316864, 'steps': 74566, 'loss/train': 1.7736587524414062} 08/31/2021 02:37:21 - INFO - __main__ - Step 74568: {'lr': 0.0002576033919907379, 'samples': 14317056, 'steps': 74567, 'loss/train': 0.7566959857940674} 08/31/2021 02:37:21 - INFO - __main__ - Step 74569: {'lr': 0.0002575980876995756, 'samples': 14317248, 'steps': 74568, 'loss/train': 1.0616123676300049} 08/31/2021 02:37:22 - INFO - __main__ - Step 74570: {'lr': 0.00025759278340498976, 'samples': 14317440, 'steps': 74569, 'loss/train': 2.188539981842041} 08/31/2021 02:37:22 - INFO - __main__ - Step 74571: {'lr': 0.0002575874791069827, 'samples': 14317632, 'steps': 74570, 'loss/train': 1.462920904159546} 08/31/2021 02:37:23 - INFO - __main__ - Step 74572: {'lr': 0.00025758217480555687, 'samples': 14317824, 'steps': 74571, 'loss/train': 1.390277624130249} 08/31/2021 02:37:24 - INFO - __main__ - Step 74573: {'lr': 0.0002575768705007146, 'samples': 14318016, 'steps': 74572, 'loss/train': 1.525329828262329} 08/31/2021 02:37:25 - INFO - __main__ - Step 74574: {'lr': 0.0002575715661924583, 'samples': 14318208, 'steps': 74573, 'loss/train': 0.8317526578903198} 08/31/2021 02:37:25 - INFO - __main__ - Step 74575: {'lr': 0.0002575662618807904, 'samples': 14318400, 'steps': 74574, 'loss/train': 1.4729310274124146} 08/31/2021 02:37:25 - INFO - __main__ - Step 74576: {'lr': 0.00025756095756571324, 'samples': 14318592, 'steps': 74575, 'loss/train': 1.250020980834961} 08/31/2021 02:37:26 - INFO - __main__ - Step 74577: {'lr': 0.0002575556532472292, 'samples': 14318784, 'steps': 74576, 'loss/train': 0.6246165037155151} 08/31/2021 02:37:27 - INFO - __main__ - Step 74578: {'lr': 0.0002575503489253407, 'samples': 14318976, 'steps': 74577, 'loss/train': 0.9685624241828918} 08/31/2021 02:37:27 - INFO - __main__ - Step 74579: {'lr': 0.0002575450446000502, 'samples': 14319168, 'steps': 74578, 'loss/train': 1.4391250610351562} 08/31/2021 02:37:28 - INFO - __main__ - Step 74580: {'lr': 0.00025753974027136, 'samples': 14319360, 'steps': 74579, 'loss/train': 1.7080230712890625} 08/31/2021 02:37:28 - INFO - __main__ - Step 74581: {'lr': 0.0002575344359392725, 'samples': 14319552, 'steps': 74580, 'loss/train': 1.3387622833251953} 08/31/2021 02:37:29 - INFO - __main__ - Step 74582: {'lr': 0.00025752913160379003, 'samples': 14319744, 'steps': 74581, 'loss/train': 1.1602039337158203} 08/31/2021 02:37:29 - INFO - __main__ - Step 74583: {'lr': 0.0002575238272649151, 'samples': 14319936, 'steps': 74582, 'loss/train': 1.2411426305770874} 08/31/2021 02:37:30 - INFO - __main__ - Step 74584: {'lr': 0.0002575185229226501, 'samples': 14320128, 'steps': 74583, 'loss/train': 0.5723379254341125} 08/31/2021 02:37:31 - INFO - __main__ - Step 74585: {'lr': 0.00025751321857699733, 'samples': 14320320, 'steps': 74584, 'loss/train': 1.2264320850372314} 08/31/2021 02:37:31 - INFO - __main__ - Step 74586: {'lr': 0.0002575079142279592, 'samples': 14320512, 'steps': 74585, 'loss/train': 1.6096646785736084} 08/31/2021 02:37:32 - INFO - __main__ - Step 74587: {'lr': 0.00025750260987553815, 'samples': 14320704, 'steps': 74586, 'loss/train': 1.592512845993042} 08/31/2021 02:37:32 - INFO - __main__ - Step 74588: {'lr': 0.00025749730551973655, 'samples': 14320896, 'steps': 74587, 'loss/train': 1.862013339996338} 08/31/2021 02:37:34 - INFO - __main__ - Step 74589: {'lr': 0.0002574920011605567, 'samples': 14321088, 'steps': 74588, 'loss/train': 0.2284705638885498} 08/31/2021 02:37:35 - INFO - __main__ - Step 74590: {'lr': 0.00025748669679800116, 'samples': 14321280, 'steps': 74589, 'loss/train': 1.5417972803115845} 08/31/2021 02:37:35 - INFO - __main__ - Step 74591: {'lr': 0.0002574813924320722, 'samples': 14321472, 'steps': 74590, 'loss/train': 1.739687204360962} 08/31/2021 02:37:35 - INFO - __main__ - Step 74592: {'lr': 0.0002574760880627722, 'samples': 14321664, 'steps': 74591, 'loss/train': 0.6003680229187012} 08/31/2021 02:37:36 - INFO - __main__ - Step 74593: {'lr': 0.0002574707836901037, 'samples': 14321856, 'steps': 74592, 'loss/train': 0.8339866995811462} 08/31/2021 02:37:36 - INFO - __main__ - Step 74594: {'lr': 0.0002574654793140688, 'samples': 14322048, 'steps': 74593, 'loss/train': 1.4927586317062378} 08/31/2021 02:37:38 - INFO - __main__ - Step 74595: {'lr': 0.0002574601749346702, 'samples': 14322240, 'steps': 74594, 'loss/train': 4.963280200958252} 08/31/2021 02:37:38 - INFO - __main__ - Step 74596: {'lr': 0.0002574548705519102, 'samples': 14322432, 'steps': 74595, 'loss/train': 1.451048731803894} 08/31/2021 02:37:38 - INFO - __main__ - Step 74597: {'lr': 0.0002574495661657911, 'samples': 14322624, 'steps': 74596, 'loss/train': 1.4809141159057617} 08/31/2021 02:37:39 - INFO - __main__ - Step 74598: {'lr': 0.0002574442617763153, 'samples': 14322816, 'steps': 74597, 'loss/train': 2.002108097076416} 08/31/2021 02:37:39 - INFO - __main__ - Step 74599: {'lr': 0.0002574389573834853, 'samples': 14323008, 'steps': 74598, 'loss/train': 0.5056803822517395} 08/31/2021 02:37:41 - INFO - __main__ - Step 74600: {'lr': 0.00025743365298730333, 'samples': 14323200, 'steps': 74599, 'loss/train': 1.081205129623413} 08/31/2021 02:37:41 - INFO - __main__ - Step 74601: {'lr': 0.00025742834858777196, 'samples': 14323392, 'steps': 74600, 'loss/train': 0.906459629535675} 08/31/2021 02:37:42 - INFO - __main__ - Step 74602: {'lr': 0.00025742304418489343, 'samples': 14323584, 'steps': 74601, 'loss/train': 1.4509599208831787} 08/31/2021 02:37:42 - INFO - __main__ - Step 74603: {'lr': 0.0002574177397786702, 'samples': 14323776, 'steps': 74602, 'loss/train': 1.059210181236267} 08/31/2021 02:37:42 - INFO - __main__ - Step 74604: {'lr': 0.00025741243536910464, 'samples': 14323968, 'steps': 74603, 'loss/train': 0.4781053066253662} 08/31/2021 02:37:44 - INFO - __main__ - Step 74605: {'lr': 0.00025740713095619914, 'samples': 14324160, 'steps': 74604, 'loss/train': 1.3882977962493896} 08/31/2021 02:37:45 - INFO - __main__ - Step 74606: {'lr': 0.00025740182653995615, 'samples': 14324352, 'steps': 74605, 'loss/train': 1.1649800539016724} 08/31/2021 02:37:45 - INFO - __main__ - Step 74607: {'lr': 0.0002573965221203781, 'samples': 14324544, 'steps': 74606, 'loss/train': 1.3383499383926392} 08/31/2021 02:37:45 - INFO - __main__ - Step 74608: {'lr': 0.00025739121769746714, 'samples': 14324736, 'steps': 74607, 'loss/train': 1.4540655612945557} 08/31/2021 02:37:46 - INFO - __main__ - Step 74609: {'lr': 0.00025738591327122585, 'samples': 14324928, 'steps': 74608, 'loss/train': 1.6419599056243896} 08/31/2021 02:37:46 - INFO - __main__ - Step 74610: {'lr': 0.0002573806088416566, 'samples': 14325120, 'steps': 74609, 'loss/train': 0.04617210105061531} 08/31/2021 02:37:46 - INFO - __main__ - Step 74611: {'lr': 0.0002573753044087617, 'samples': 14325312, 'steps': 74610, 'loss/train': 0.06817445904016495} 08/31/2021 02:37:48 - INFO - __main__ - Step 74612: {'lr': 0.0002573699999725437, 'samples': 14325504, 'steps': 74611, 'loss/train': 0.031303923577070236} 08/31/2021 02:37:48 - INFO - __main__ - Step 74613: {'lr': 0.00025736469553300483, 'samples': 14325696, 'steps': 74612, 'loss/train': 1.416534185409546} 08/31/2021 02:37:49 - INFO - __main__ - Step 74614: {'lr': 0.00025735939109014754, 'samples': 14325888, 'steps': 74613, 'loss/train': 1.0746650695800781} 08/31/2021 02:37:49 - INFO - __main__ - Step 74615: {'lr': 0.0002573540866439742, 'samples': 14326080, 'steps': 74614, 'loss/train': 1.6282896995544434} 08/31/2021 02:37:49 - INFO - __main__ - Step 74616: {'lr': 0.0002573487821944873, 'samples': 14326272, 'steps': 74615, 'loss/train': 0.4439986050128937} 08/31/2021 02:37:51 - INFO - __main__ - Step 74617: {'lr': 0.0002573434777416891, 'samples': 14326464, 'steps': 74616, 'loss/train': 0.2664920687675476} 08/31/2021 02:37:51 - INFO - __main__ - Step 74618: {'lr': 0.0002573381732855821, 'samples': 14326656, 'steps': 74617, 'loss/train': 1.2877299785614014} 08/31/2021 02:37:52 - INFO - __main__ - Step 74619: {'lr': 0.00025733286882616854, 'samples': 14326848, 'steps': 74618, 'loss/train': 1.4611581563949585} 08/31/2021 02:37:52 - INFO - __main__ - Step 74620: {'lr': 0.00025732756436345095, 'samples': 14327040, 'steps': 74619, 'loss/train': 1.1728105545043945} 08/31/2021 02:37:52 - INFO - __main__ - Step 74621: {'lr': 0.0002573222598974317, 'samples': 14327232, 'steps': 74620, 'loss/train': 1.5253996849060059} 08/31/2021 02:37:55 - INFO - __main__ - Step 74622: {'lr': 0.00025731695542811315, 'samples': 14327424, 'steps': 74621, 'loss/train': 1.22536301612854} 08/31/2021 02:37:55 - INFO - __main__ - Step 74623: {'lr': 0.00025731165095549765, 'samples': 14327616, 'steps': 74622, 'loss/train': 5.649447917938232} 08/31/2021 02:37:56 - INFO - __main__ - Step 74624: {'lr': 0.0002573063464795876, 'samples': 14327808, 'steps': 74623, 'loss/train': 5.622010707855225} 08/31/2021 02:37:56 - INFO - __main__ - Step 74625: {'lr': 0.00025730104200038546, 'samples': 14328000, 'steps': 74624, 'loss/train': 0.9714295864105225} 08/31/2021 02:37:56 - INFO - __main__ - Step 74626: {'lr': 0.0002572957375178936, 'samples': 14328192, 'steps': 74625, 'loss/train': 1.2593743801116943} 08/31/2021 02:37:57 - INFO - __main__ - Step 74627: {'lr': 0.0002572904330321144, 'samples': 14328384, 'steps': 74626, 'loss/train': 1.1705673933029175} 08/31/2021 02:37:58 - INFO - __main__ - Step 74628: {'lr': 0.00025728512854305023, 'samples': 14328576, 'steps': 74627, 'loss/train': 0.9003356695175171} 08/31/2021 02:37:59 - INFO - __main__ - Step 74629: {'lr': 0.0002572798240507035, 'samples': 14328768, 'steps': 74628, 'loss/train': 0.933340311050415} 08/31/2021 02:37:59 - INFO - __main__ - Step 74630: {'lr': 0.0002572745195550766, 'samples': 14328960, 'steps': 74629, 'loss/train': 0.8866857290267944} 08/31/2021 02:37:59 - INFO - __main__ - Step 74631: {'lr': 0.0002572692150561719, 'samples': 14329152, 'steps': 74630, 'loss/train': 0.04216171056032181} 08/31/2021 02:38:00 - INFO - __main__ - Step 74632: {'lr': 0.0002572639105539918, 'samples': 14329344, 'steps': 74631, 'loss/train': 1.1430978775024414} 08/31/2021 02:38:00 - INFO - __main__ - Step 74633: {'lr': 0.00025725860604853873, 'samples': 14329536, 'steps': 74632, 'loss/train': 1.5792502164840698} 08/31/2021 02:38:02 - INFO - __main__ - Step 74634: {'lr': 0.000257253301539815, 'samples': 14329728, 'steps': 74633, 'loss/train': 1.0994670391082764} 08/31/2021 02:38:02 - INFO - __main__ - Step 74635: {'lr': 0.00025724799702782304, 'samples': 14329920, 'steps': 74634, 'loss/train': 0.10335011780261993} 08/31/2021 02:38:03 - INFO - __main__ - Step 74636: {'lr': 0.0002572426925125653, 'samples': 14330112, 'steps': 74635, 'loss/train': 1.3651809692382812} 08/31/2021 02:38:03 - INFO - __main__ - Step 74637: {'lr': 0.00025723738799404407, 'samples': 14330304, 'steps': 74636, 'loss/train': 0.9779158234596252} 08/31/2021 02:38:03 - INFO - __main__ - Step 74638: {'lr': 0.00025723208347226174, 'samples': 14330496, 'steps': 74637, 'loss/train': 1.3239877223968506} 08/31/2021 02:38:05 - INFO - __main__ - Step 74639: {'lr': 0.0002572267789472208, 'samples': 14330688, 'steps': 74638, 'loss/train': 0.815737247467041} 08/31/2021 02:38:05 - INFO - __main__ - Step 74640: {'lr': 0.0002572214744189236, 'samples': 14330880, 'steps': 74639, 'loss/train': 1.3685601949691772} 08/31/2021 02:38:06 - INFO - __main__ - Step 74641: {'lr': 0.0002572161698873725, 'samples': 14331072, 'steps': 74640, 'loss/train': 0.7284939885139465} 08/31/2021 02:38:06 - INFO - __main__ - Step 74642: {'lr': 0.00025721086535256994, 'samples': 14331264, 'steps': 74641, 'loss/train': 0.6821136474609375} 08/31/2021 02:38:07 - INFO - __main__ - Step 74643: {'lr': 0.0002572055608145182, 'samples': 14331456, 'steps': 74642, 'loss/train': 1.2949122190475464} 08/31/2021 02:38:08 - INFO - __main__ - Step 74644: {'lr': 0.00025720025627321973, 'samples': 14331648, 'steps': 74643, 'loss/train': 1.6336853504180908} 08/31/2021 02:38:08 - INFO - __main__ - Step 74645: {'lr': 0.000257194951728677, 'samples': 14331840, 'steps': 74644, 'loss/train': 0.904301106929779} 08/31/2021 02:38:09 - INFO - __main__ - Step 74646: {'lr': 0.0002571896471808923, 'samples': 14332032, 'steps': 74645, 'loss/train': 1.6525561809539795} 08/31/2021 02:38:09 - INFO - __main__ - Step 74647: {'lr': 0.0002571843426298682, 'samples': 14332224, 'steps': 74646, 'loss/train': 1.2131742238998413} 08/31/2021 02:38:10 - INFO - __main__ - Step 74648: {'lr': 0.00025717903807560675, 'samples': 14332416, 'steps': 74647, 'loss/train': 1.2768871784210205} 08/31/2021 02:38:11 - INFO - __main__ - Step 74649: {'lr': 0.00025717373351811064, 'samples': 14332608, 'steps': 74648, 'loss/train': 1.142392873764038} 08/31/2021 02:38:12 - INFO - __main__ - Step 74650: {'lr': 0.00025716842895738215, 'samples': 14332800, 'steps': 74649, 'loss/train': 1.2674973011016846} 08/31/2021 02:38:12 - INFO - __main__ - Step 74651: {'lr': 0.0002571631243934236, 'samples': 14332992, 'steps': 74650, 'loss/train': 1.8064042329788208} 08/31/2021 02:38:12 - INFO - __main__ - Step 74652: {'lr': 0.00025715781982623754, 'samples': 14333184, 'steps': 74651, 'loss/train': 1.36148202419281} 08/31/2021 02:38:13 - INFO - __main__ - Step 74653: {'lr': 0.0002571525152558262, 'samples': 14333376, 'steps': 74652, 'loss/train': 1.588287591934204} 08/31/2021 02:38:14 - INFO - __main__ - Step 74654: {'lr': 0.0002571472106821922, 'samples': 14333568, 'steps': 74653, 'loss/train': 1.1806457042694092} 08/31/2021 02:38:15 - INFO - __main__ - Step 74655: {'lr': 0.0002571419061053376, 'samples': 14333760, 'steps': 74654, 'loss/train': 1.1966540813446045} 08/31/2021 02:38:15 - INFO - __main__ - Step 74656: {'lr': 0.0002571366015252651, 'samples': 14333952, 'steps': 74655, 'loss/train': 1.4820202589035034} 08/31/2021 02:38:16 - INFO - __main__ - Step 74657: {'lr': 0.00025713129694197683, 'samples': 14334144, 'steps': 74656, 'loss/train': 0.044851794838905334} 08/31/2021 02:38:16 - INFO - __main__ - Step 74658: {'lr': 0.0002571259923554754, 'samples': 14334336, 'steps': 74657, 'loss/train': 0.39169958233833313} 08/31/2021 02:38:16 - INFO - __main__ - Step 74659: {'lr': 0.0002571206877657631, 'samples': 14334528, 'steps': 74658, 'loss/train': 0.08714783936738968} 08/31/2021 02:38:18 - INFO - __main__ - Step 74660: {'lr': 0.00025711538317284234, 'samples': 14334720, 'steps': 74659, 'loss/train': 1.4566209316253662} 08/31/2021 02:38:19 - INFO - __main__ - Step 74661: {'lr': 0.0002571100785767154, 'samples': 14334912, 'steps': 74660, 'loss/train': 0.9090837240219116} 08/31/2021 02:38:19 - INFO - __main__ - Step 74662: {'lr': 0.00025710477397738486, 'samples': 14335104, 'steps': 74661, 'loss/train': 1.7963659763336182} 08/31/2021 02:38:19 - INFO - __main__ - Step 74663: {'lr': 0.000257099469374853, 'samples': 14335296, 'steps': 74662, 'loss/train': 1.785243272781372} 08/31/2021 02:38:20 - INFO - __main__ - Step 74664: {'lr': 0.0002570941647691222, 'samples': 14335488, 'steps': 74663, 'loss/train': 1.139148235321045} 08/31/2021 02:38:20 - INFO - __main__ - Step 74665: {'lr': 0.0002570888601601949, 'samples': 14335680, 'steps': 74664, 'loss/train': 1.195846438407898} 08/31/2021 02:38:21 - INFO - __main__ - Step 74666: {'lr': 0.0002570835555480735, 'samples': 14335872, 'steps': 74665, 'loss/train': 0.6754500865936279} 08/31/2021 02:38:22 - INFO - __main__ - Step 74667: {'lr': 0.00025707825093276035, 'samples': 14336064, 'steps': 74666, 'loss/train': 1.168605923652649} 08/31/2021 02:38:22 - INFO - __main__ - Step 74668: {'lr': 0.0002570729463142578, 'samples': 14336256, 'steps': 74667, 'loss/train': 1.3189911842346191} 08/31/2021 02:38:23 - INFO - __main__ - Step 74669: {'lr': 0.00025706764169256837, 'samples': 14336448, 'steps': 74668, 'loss/train': 1.0786221027374268} 08/31/2021 02:38:23 - INFO - __main__ - Step 74670: {'lr': 0.0002570623370676943, 'samples': 14336640, 'steps': 74669, 'loss/train': 1.9376729726791382} 08/31/2021 02:38:24 - INFO - __main__ - Step 74671: {'lr': 0.00025705703243963804, 'samples': 14336832, 'steps': 74670, 'loss/train': 1.2726584672927856} 08/31/2021 02:38:25 - INFO - __main__ - Step 74672: {'lr': 0.00025705172780840204, 'samples': 14337024, 'steps': 74671, 'loss/train': 1.440333604812622} 08/31/2021 02:38:25 - INFO - __main__ - Step 74673: {'lr': 0.00025704642317398856, 'samples': 14337216, 'steps': 74672, 'loss/train': 1.8509666919708252} 08/31/2021 02:38:26 - INFO - __main__ - Step 74674: {'lr': 0.0002570411185364002, 'samples': 14337408, 'steps': 74673, 'loss/train': 1.1018632650375366} 08/31/2021 02:38:26 - INFO - __main__ - Step 74675: {'lr': 0.0002570358138956391, 'samples': 14337600, 'steps': 74674, 'loss/train': 1.1918878555297852} 08/31/2021 02:38:28 - INFO - __main__ - Step 74676: {'lr': 0.00025703050925170786, 'samples': 14337792, 'steps': 74675, 'loss/train': 1.3233321905136108} 08/31/2021 02:38:29 - INFO - __main__ - Step 74677: {'lr': 0.0002570252046046088, 'samples': 14337984, 'steps': 74676, 'loss/train': 1.407859444618225} 08/31/2021 02:38:29 - INFO - __main__ - Step 74678: {'lr': 0.00025701989995434416, 'samples': 14338176, 'steps': 74677, 'loss/train': 1.4378128051757812} 08/31/2021 02:38:30 - INFO - __main__ - Step 74679: {'lr': 0.00025701459530091654, 'samples': 14338368, 'steps': 74678, 'loss/train': 0.10468751192092896} 08/31/2021 02:38:30 - INFO - __main__ - Step 74680: {'lr': 0.0002570092906443282, 'samples': 14338560, 'steps': 74679, 'loss/train': 1.1295335292816162} 08/31/2021 02:38:31 - INFO - __main__ - Step 74681: {'lr': 0.0002570039859845817, 'samples': 14338752, 'steps': 74680, 'loss/train': 1.2122834920883179} 08/31/2021 02:38:32 - INFO - __main__ - Step 74682: {'lr': 0.00025699868132167923, 'samples': 14338944, 'steps': 74681, 'loss/train': 1.2651958465576172} 08/31/2021 02:38:32 - INFO - __main__ - Step 74683: {'lr': 0.00025699337665562326, 'samples': 14339136, 'steps': 74682, 'loss/train': 0.9876343607902527} 08/31/2021 02:38:33 - INFO - __main__ - Step 74684: {'lr': 0.0002569880719864162, 'samples': 14339328, 'steps': 74683, 'loss/train': 1.3768571615219116} 08/31/2021 02:38:33 - INFO - __main__ - Step 74685: {'lr': 0.0002569827673140604, 'samples': 14339520, 'steps': 74684, 'loss/train': 0.3729386329650879} 08/31/2021 02:38:33 - INFO - __main__ - Step 74686: {'lr': 0.0002569774626385583, 'samples': 14339712, 'steps': 74685, 'loss/train': 0.8992018103599548} 08/31/2021 02:38:35 - INFO - __main__ - Step 74687: {'lr': 0.0002569721579599123, 'samples': 14339904, 'steps': 74686, 'loss/train': 1.2304717302322388} 08/31/2021 02:38:35 - INFO - __main__ - Step 74688: {'lr': 0.00025696685327812466, 'samples': 14340096, 'steps': 74687, 'loss/train': 1.574223518371582} 08/31/2021 02:38:36 - INFO - __main__ - Step 74689: {'lr': 0.00025696154859319794, 'samples': 14340288, 'steps': 74688, 'loss/train': 1.5479822158813477} 08/31/2021 02:38:36 - INFO - __main__ - Step 74690: {'lr': 0.00025695624390513445, 'samples': 14340480, 'steps': 74689, 'loss/train': 1.7164971828460693} 08/31/2021 02:38:36 - INFO - __main__ - Step 74691: {'lr': 0.00025695093921393653, 'samples': 14340672, 'steps': 74690, 'loss/train': 1.2392704486846924} 08/31/2021 02:38:38 - INFO - __main__ - Step 74692: {'lr': 0.00025694563451960663, 'samples': 14340864, 'steps': 74691, 'loss/train': 1.88941490650177} 08/31/2021 02:38:38 - INFO - __main__ - Step 74693: {'lr': 0.0002569403298221472, 'samples': 14341056, 'steps': 74692, 'loss/train': 1.3385095596313477} 08/31/2021 02:38:39 - INFO - __main__ - Step 74694: {'lr': 0.0002569350251215605, 'samples': 14341248, 'steps': 74693, 'loss/train': 0.2612850069999695} 08/31/2021 02:38:39 - INFO - __main__ - Step 74695: {'lr': 0.000256929720417849, 'samples': 14341440, 'steps': 74694, 'loss/train': 2.242401361465454} 08/31/2021 02:38:39 - INFO - __main__ - Step 74696: {'lr': 0.0002569244157110151, 'samples': 14341632, 'steps': 74695, 'loss/train': 0.7763971090316772} 08/31/2021 02:38:41 - INFO - __main__ - Step 74697: {'lr': 0.00025691911100106114, 'samples': 14341824, 'steps': 74696, 'loss/train': 1.4728249311447144} 08/31/2021 02:38:42 - INFO - __main__ - Step 74698: {'lr': 0.00025691380628798955, 'samples': 14342016, 'steps': 74697, 'loss/train': 1.1859655380249023} 08/31/2021 02:38:42 - INFO - __main__ - Step 74699: {'lr': 0.0002569085015718027, 'samples': 14342208, 'steps': 74698, 'loss/train': 1.5012120008468628} 08/31/2021 02:38:42 - INFO - __main__ - Step 74700: {'lr': 0.00025690319685250294, 'samples': 14342400, 'steps': 74699, 'loss/train': 1.031686544418335} 08/31/2021 02:38:43 - INFO - __main__ - Step 74701: {'lr': 0.0002568978921300928, 'samples': 14342592, 'steps': 74700, 'loss/train': 1.6545559167861938} 08/31/2021 02:38:44 - INFO - __main__ - Step 74702: {'lr': 0.0002568925874045745, 'samples': 14342784, 'steps': 74701, 'loss/train': 1.5145905017852783} 08/31/2021 02:38:45 - INFO - __main__ - Step 74703: {'lr': 0.00025688728267595054, 'samples': 14342976, 'steps': 74702, 'loss/train': 1.562331199645996} 08/31/2021 02:38:45 - INFO - __main__ - Step 74704: {'lr': 0.00025688197794422325, 'samples': 14343168, 'steps': 74703, 'loss/train': 1.1486610174179077} 08/31/2021 02:38:45 - INFO - __main__ - Step 74705: {'lr': 0.0002568766732093951, 'samples': 14343360, 'steps': 74704, 'loss/train': 1.5112545490264893} 08/31/2021 02:38:46 - INFO - __main__ - Step 74706: {'lr': 0.0002568713684714684, 'samples': 14343552, 'steps': 74705, 'loss/train': 0.6893680095672607} 08/31/2021 02:38:46 - INFO - __main__ - Step 74707: {'lr': 0.0002568660637304456, 'samples': 14343744, 'steps': 74706, 'loss/train': 1.190888524055481} 08/31/2021 02:38:48 - INFO - __main__ - Step 74708: {'lr': 0.00025686075898632895, 'samples': 14343936, 'steps': 74707, 'loss/train': 1.1155767440795898} 08/31/2021 02:38:48 - INFO - __main__ - Step 74709: {'lr': 0.00025685545423912104, 'samples': 14344128, 'steps': 74708, 'loss/train': 1.4523266553878784} 08/31/2021 02:38:49 - INFO - __main__ - Step 74710: {'lr': 0.00025685014948882413, 'samples': 14344320, 'steps': 74709, 'loss/train': 1.3803378343582153} 08/31/2021 02:38:49 - INFO - __main__ - Step 74711: {'lr': 0.0002568448447354406, 'samples': 14344512, 'steps': 74710, 'loss/train': 1.6487010717391968} 08/31/2021 02:38:49 - INFO - __main__ - Step 74712: {'lr': 0.00025683953997897297, 'samples': 14344704, 'steps': 74711, 'loss/train': 1.0196771621704102} 08/31/2021 02:38:51 - INFO - __main__ - Step 74713: {'lr': 0.00025683423521942353, 'samples': 14344896, 'steps': 74712, 'loss/train': 1.083280324935913} 08/31/2021 02:38:51 - INFO - __main__ - Step 74714: {'lr': 0.00025682893045679474, 'samples': 14345088, 'steps': 74713, 'loss/train': 2.383718490600586} 08/31/2021 02:38:52 - INFO - __main__ - Step 74715: {'lr': 0.0002568236256910889, 'samples': 14345280, 'steps': 74714, 'loss/train': 0.9546159505844116} 08/31/2021 02:38:52 - INFO - __main__ - Step 74716: {'lr': 0.0002568183209223084, 'samples': 14345472, 'steps': 74715, 'loss/train': 1.073370099067688} 08/31/2021 02:38:52 - INFO - __main__ - Step 74717: {'lr': 0.00025681301615045564, 'samples': 14345664, 'steps': 74716, 'loss/train': 1.3801416158676147} 08/31/2021 02:38:54 - INFO - __main__ - Step 74718: {'lr': 0.00025680771137553314, 'samples': 14345856, 'steps': 74717, 'loss/train': 1.0696762800216675} 08/31/2021 02:38:54 - INFO - __main__ - Step 74719: {'lr': 0.00025680240659754316, 'samples': 14346048, 'steps': 74718, 'loss/train': 1.4727227687835693} 08/31/2021 02:38:55 - INFO - __main__ - Step 74720: {'lr': 0.00025679710181648814, 'samples': 14346240, 'steps': 74719, 'loss/train': 1.1034064292907715} 08/31/2021 02:38:55 - INFO - __main__ - Step 74721: {'lr': 0.00025679179703237036, 'samples': 14346432, 'steps': 74720, 'loss/train': 1.9245142936706543} 08/31/2021 02:38:55 - INFO - __main__ - Step 74722: {'lr': 0.0002567864922451924, 'samples': 14346624, 'steps': 74721, 'loss/train': 1.6208760738372803} 08/31/2021 02:38:57 - INFO - __main__ - Step 74723: {'lr': 0.0002567811874549565, 'samples': 14346816, 'steps': 74722, 'loss/train': 1.7327808141708374} 08/31/2021 02:38:58 - INFO - __main__ - Step 74724: {'lr': 0.00025677588266166505, 'samples': 14347008, 'steps': 74723, 'loss/train': 1.31336510181427} 08/31/2021 02:38:58 - INFO - __main__ - Step 74725: {'lr': 0.00025677057786532067, 'samples': 14347200, 'steps': 74724, 'loss/train': 0.6042991876602173} 08/31/2021 02:38:58 - INFO - __main__ - Step 74726: {'lr': 0.00025676527306592545, 'samples': 14347392, 'steps': 74725, 'loss/train': 1.2361372709274292} 08/31/2021 02:38:59 - INFO - __main__ - Step 74727: {'lr': 0.0002567599682634819, 'samples': 14347584, 'steps': 74726, 'loss/train': 0.7707201242446899} 08/31/2021 02:39:00 - INFO - __main__ - Step 74728: {'lr': 0.00025675466345799236, 'samples': 14347776, 'steps': 74727, 'loss/train': 1.0922044515609741} 08/31/2021 02:39:00 - INFO - __main__ - Step 74729: {'lr': 0.0002567493586494594, 'samples': 14347968, 'steps': 74728, 'loss/train': 1.0464894771575928} 08/31/2021 02:39:01 - INFO - __main__ - Step 74730: {'lr': 0.00025674405383788526, 'samples': 14348160, 'steps': 74729, 'loss/train': 1.2157316207885742} 08/31/2021 02:39:01 - INFO - __main__ - Step 74731: {'lr': 0.0002567387490232723, 'samples': 14348352, 'steps': 74730, 'loss/train': 1.1724077463150024} 08/31/2021 02:39:01 - INFO - __main__ - Step 74732: {'lr': 0.00025673344420562295, 'samples': 14348544, 'steps': 74731, 'loss/train': 0.567979633808136} 08/31/2021 02:39:04 - INFO - __main__ - Step 74733: {'lr': 0.0002567281393849396, 'samples': 14348736, 'steps': 74732, 'loss/train': 0.788312554359436} 08/31/2021 02:39:04 - INFO - __main__ - Step 74734: {'lr': 0.0002567228345612247, 'samples': 14348928, 'steps': 74733, 'loss/train': 1.0675177574157715} 08/31/2021 02:39:04 - INFO - __main__ - Step 74735: {'lr': 0.00025671752973448057, 'samples': 14349120, 'steps': 74734, 'loss/train': 1.198209285736084} 08/31/2021 02:39:05 - INFO - __main__ - Step 74736: {'lr': 0.0002567122249047097, 'samples': 14349312, 'steps': 74735, 'loss/train': 1.4260059595108032} 08/31/2021 02:39:05 - INFO - __main__ - Step 74737: {'lr': 0.0002567069200719143, 'samples': 14349504, 'steps': 74736, 'loss/train': 0.8651806116104126} 08/31/2021 02:39:07 - INFO - __main__ - Step 74738: {'lr': 0.0002567016152360969, 'samples': 14349696, 'steps': 74737, 'loss/train': 1.5280325412750244} 08/31/2021 02:39:07 - INFO - __main__ - Step 74739: {'lr': 0.00025669631039725987, 'samples': 14349888, 'steps': 74738, 'loss/train': 0.8936000466346741} 08/31/2021 02:39:07 - INFO - __main__ - Step 74740: {'lr': 0.0002566910055554056, 'samples': 14350080, 'steps': 74739, 'loss/train': 2.2901530265808105} 08/31/2021 02:39:08 - INFO - __main__ - Step 74741: {'lr': 0.0002566857007105365, 'samples': 14350272, 'steps': 74740, 'loss/train': 0.6630066633224487} 08/31/2021 02:39:08 - INFO - __main__ - Step 74742: {'lr': 0.00025668039586265485, 'samples': 14350464, 'steps': 74741, 'loss/train': 1.4555906057357788} 08/31/2021 02:39:09 - INFO - __main__ - Step 74743: {'lr': 0.00025667509101176317, 'samples': 14350656, 'steps': 74742, 'loss/train': 1.2855465412139893} 08/31/2021 02:39:10 - INFO - __main__ - Step 74744: {'lr': 0.00025666978615786375, 'samples': 14350848, 'steps': 74743, 'loss/train': 1.13911771774292} 08/31/2021 02:39:11 - INFO - __main__ - Step 74745: {'lr': 0.00025666448130095903, 'samples': 14351040, 'steps': 74744, 'loss/train': 0.08474069088697433} 08/31/2021 02:39:11 - INFO - __main__ - Step 74746: {'lr': 0.0002566591764410514, 'samples': 14351232, 'steps': 74745, 'loss/train': 1.153204321861267} 08/31/2021 02:39:12 - INFO - __main__ - Step 74747: {'lr': 0.00025665387157814323, 'samples': 14351424, 'steps': 74746, 'loss/train': 0.05560923367738724} 08/31/2021 02:39:12 - INFO - __main__ - Step 74748: {'lr': 0.00025664856671223703, 'samples': 14351616, 'steps': 74747, 'loss/train': 0.9849945902824402} 08/31/2021 02:39:13 - INFO - __main__ - Step 74749: {'lr': 0.000256643261843335, 'samples': 14351808, 'steps': 74748, 'loss/train': 1.6066944599151611} 08/31/2021 02:39:14 - INFO - __main__ - Step 74750: {'lr': 0.00025663795697143964, 'samples': 14352000, 'steps': 74749, 'loss/train': 1.1640045642852783} 08/31/2021 02:39:14 - INFO - __main__ - Step 74751: {'lr': 0.00025663265209655337, 'samples': 14352192, 'steps': 74750, 'loss/train': 1.5420522689819336} 08/31/2021 02:39:15 - INFO - __main__ - Step 74752: {'lr': 0.00025662734721867845, 'samples': 14352384, 'steps': 74751, 'loss/train': 1.5120553970336914} 08/31/2021 02:39:15 - INFO - __main__ - Step 74753: {'lr': 0.0002566220423378173, 'samples': 14352576, 'steps': 74752, 'loss/train': 1.4187180995941162} 08/31/2021 02:39:17 - INFO - __main__ - Step 74754: {'lr': 0.0002566167374539725, 'samples': 14352768, 'steps': 74753, 'loss/train': 0.9540307521820068} 08/31/2021 02:39:17 - INFO - __main__ - Step 74755: {'lr': 0.00025661143256714623, 'samples': 14352960, 'steps': 74754, 'loss/train': 0.6608849167823792} 08/31/2021 02:39:17 - INFO - __main__ - Step 74756: {'lr': 0.00025660612767734097, 'samples': 14353152, 'steps': 74755, 'loss/train': 1.1654136180877686} 08/31/2021 02:39:18 - INFO - __main__ - Step 74757: {'lr': 0.000256600822784559, 'samples': 14353344, 'steps': 74756, 'loss/train': 0.6925610899925232} 08/31/2021 02:39:18 - INFO - __main__ - Step 74758: {'lr': 0.00025659551788880295, 'samples': 14353536, 'steps': 74757, 'loss/train': 1.8875480890274048} 08/31/2021 02:39:20 - INFO - __main__ - Step 74759: {'lr': 0.00025659021299007497, 'samples': 14353728, 'steps': 74758, 'loss/train': 0.09046899527311325} 08/31/2021 02:39:20 - INFO - __main__ - Step 74760: {'lr': 0.0002565849080883775, 'samples': 14353920, 'steps': 74759, 'loss/train': 0.760810911655426} 08/31/2021 02:39:21 - INFO - __main__ - Step 74761: {'lr': 0.00025657960318371315, 'samples': 14354112, 'steps': 74760, 'loss/train': 1.279234766960144} 08/31/2021 02:39:21 - INFO - __main__ - Step 74762: {'lr': 0.000256574298276084, 'samples': 14354304, 'steps': 74761, 'loss/train': 0.8569238781929016} 08/31/2021 02:39:21 - INFO - __main__ - Step 74763: {'lr': 0.00025656899336549255, 'samples': 14354496, 'steps': 74762, 'loss/train': 1.3443613052368164} 08/31/2021 02:39:23 - INFO - __main__ - Step 74764: {'lr': 0.0002565636884519413, 'samples': 14354688, 'steps': 74763, 'loss/train': 0.04954631254076958} 08/31/2021 02:39:23 - INFO - __main__ - Step 74765: {'lr': 0.00025655838353543246, 'samples': 14354880, 'steps': 74764, 'loss/train': 1.4250742197036743} 08/31/2021 02:39:24 - INFO - __main__ - Step 74766: {'lr': 0.0002565530786159686, 'samples': 14355072, 'steps': 74765, 'loss/train': 0.6392054557800293} 08/31/2021 02:39:24 - INFO - __main__ - Step 74767: {'lr': 0.0002565477736935519, 'samples': 14355264, 'steps': 74766, 'loss/train': 2.017202615737915} 08/31/2021 02:39:24 - INFO - __main__ - Step 74768: {'lr': 0.00025654246876818503, 'samples': 14355456, 'steps': 74767, 'loss/train': 0.33150020241737366} 08/31/2021 02:39:26 - INFO - __main__ - Step 74769: {'lr': 0.00025653716383987015, 'samples': 14355648, 'steps': 74768, 'loss/train': 0.05464886873960495} 08/31/2021 02:39:26 - INFO - __main__ - Step 74770: {'lr': 0.0002565318589086097, 'samples': 14355840, 'steps': 74769, 'loss/train': 1.106634259223938} 08/31/2021 02:39:27 - INFO - __main__ - Step 74771: {'lr': 0.0002565265539744061, 'samples': 14356032, 'steps': 74770, 'loss/train': 0.5481734871864319} 08/31/2021 02:39:27 - INFO - __main__ - Step 74772: {'lr': 0.00025652124903726174, 'samples': 14356224, 'steps': 74771, 'loss/train': 1.0539813041687012} 08/31/2021 02:39:27 - INFO - __main__ - Step 74773: {'lr': 0.00025651594409717903, 'samples': 14356416, 'steps': 74772, 'loss/train': 1.315967082977295} 08/31/2021 02:39:28 - INFO - __main__ - Step 74774: {'lr': 0.00025651063915416037, 'samples': 14356608, 'steps': 74773, 'loss/train': 0.71394944190979} 08/31/2021 02:39:29 - INFO - __main__ - Step 74775: {'lr': 0.0002565053342082081, 'samples': 14356800, 'steps': 74774, 'loss/train': 0.6552649736404419} 08/31/2021 02:39:30 - INFO - __main__ - Step 74776: {'lr': 0.00025650002925932456, 'samples': 14356992, 'steps': 74775, 'loss/train': 1.4507519006729126} 08/31/2021 02:39:30 - INFO - __main__ - Step 74777: {'lr': 0.00025649472430751226, 'samples': 14357184, 'steps': 74776, 'loss/train': 1.2702319622039795} 08/31/2021 02:39:31 - INFO - __main__ - Step 74778: {'lr': 0.0002564894193527735, 'samples': 14357376, 'steps': 74777, 'loss/train': 1.5710452795028687} 08/31/2021 02:39:31 - INFO - __main__ - Step 74779: {'lr': 0.00025648411439511075, 'samples': 14357568, 'steps': 74778, 'loss/train': 1.4578312635421753} 08/31/2021 02:39:33 - INFO - __main__ - Step 74780: {'lr': 0.00025647880943452633, 'samples': 14357760, 'steps': 74779, 'loss/train': 1.034852385520935} 08/31/2021 02:39:34 - INFO - __main__ - Step 74781: {'lr': 0.00025647350447102274, 'samples': 14357952, 'steps': 74780, 'loss/train': 1.0847193002700806} 08/31/2021 02:39:34 - INFO - __main__ - Step 74782: {'lr': 0.0002564681995046022, 'samples': 14358144, 'steps': 74781, 'loss/train': 0.8999574184417725} 08/31/2021 02:39:34 - INFO - __main__ - Step 74783: {'lr': 0.00025646289453526715, 'samples': 14358336, 'steps': 74782, 'loss/train': 1.093953013420105} 08/31/2021 02:39:35 - INFO - __main__ - Step 74784: {'lr': 0.0002564575895630201, 'samples': 14358528, 'steps': 74783, 'loss/train': 1.1048887968063354} 08/31/2021 02:39:35 - INFO - __main__ - Step 74785: {'lr': 0.00025645228458786337, 'samples': 14358720, 'steps': 74784, 'loss/train': 1.4297425746917725} 08/31/2021 02:39:37 - INFO - __main__ - Step 74786: {'lr': 0.0002564469796097993, 'samples': 14358912, 'steps': 74785, 'loss/train': 0.04848223924636841} 08/31/2021 02:39:38 - INFO - __main__ - Step 74787: {'lr': 0.0002564416746288303, 'samples': 14359104, 'steps': 74786, 'loss/train': 1.1796835660934448} 08/31/2021 02:39:38 - INFO - __main__ - Step 74788: {'lr': 0.00025643636964495887, 'samples': 14359296, 'steps': 74787, 'loss/train': 0.8021712899208069} 08/31/2021 02:39:38 - INFO - __main__ - Step 74789: {'lr': 0.0002564310646581872, 'samples': 14359488, 'steps': 74788, 'loss/train': 1.128443956375122} 08/31/2021 02:39:39 - INFO - __main__ - Step 74790: {'lr': 0.00025642575966851783, 'samples': 14359680, 'steps': 74789, 'loss/train': 1.0808871984481812} 08/31/2021 02:39:40 - INFO - __main__ - Step 74791: {'lr': 0.0002564204546759531, 'samples': 14359872, 'steps': 74790, 'loss/train': 1.1598615646362305} 08/31/2021 02:39:41 - INFO - __main__ - Step 74792: {'lr': 0.00025641514968049545, 'samples': 14360064, 'steps': 74791, 'loss/train': 1.4143825769424438} 08/31/2021 02:39:41 - INFO - __main__ - Step 74793: {'lr': 0.00025640984468214723, 'samples': 14360256, 'steps': 74792, 'loss/train': 1.2991195917129517} 08/31/2021 02:39:41 - INFO - __main__ - Step 74794: {'lr': 0.0002564045396809108, 'samples': 14360448, 'steps': 74793, 'loss/train': 1.0456310510635376} 08/31/2021 02:39:42 - INFO - __main__ - Step 74795: {'lr': 0.00025639923467678867, 'samples': 14360640, 'steps': 74794, 'loss/train': 3.292480945587158} 08/31/2021 02:39:42 - INFO - __main__ - Step 74796: {'lr': 0.00025639392966978305, 'samples': 14360832, 'steps': 74795, 'loss/train': 1.7421576976776123} 08/31/2021 02:39:44 - INFO - __main__ - Step 74797: {'lr': 0.0002563886246598964, 'samples': 14361024, 'steps': 74796, 'loss/train': 1.1986790895462036} 08/31/2021 02:39:44 - INFO - __main__ - Step 74798: {'lr': 0.00025638331964713125, 'samples': 14361216, 'steps': 74797, 'loss/train': 0.5901054739952087} 08/31/2021 02:39:45 - INFO - __main__ - Step 74799: {'lr': 0.0002563780146314898, 'samples': 14361408, 'steps': 74798, 'loss/train': 1.1965755224227905} 08/31/2021 02:39:45 - INFO - __main__ - Step 74800: {'lr': 0.0002563727096129745, 'samples': 14361600, 'steps': 74799, 'loss/train': 1.384899377822876} 08/31/2021 02:39:45 - INFO - __main__ - Step 74801: {'lr': 0.00025636740459158774, 'samples': 14361792, 'steps': 74800, 'loss/train': 0.9437565207481384} 08/31/2021 02:39:47 - INFO - __main__ - Step 74802: {'lr': 0.000256362099567332, 'samples': 14361984, 'steps': 74801, 'loss/train': 1.3792637586593628} 08/31/2021 02:39:47 - INFO - __main__ - Step 74803: {'lr': 0.0002563567945402096, 'samples': 14362176, 'steps': 74802, 'loss/train': 1.490693211555481} 08/31/2021 02:39:48 - INFO - __main__ - Step 74804: {'lr': 0.0002563514895102229, 'samples': 14362368, 'steps': 74803, 'loss/train': 1.3884663581848145} 08/31/2021 02:39:48 - INFO - __main__ - Step 74805: {'lr': 0.0002563461844773743, 'samples': 14362560, 'steps': 74804, 'loss/train': 1.402698278427124} 08/31/2021 02:39:48 - INFO - __main__ - Step 74806: {'lr': 0.00025634087944166617, 'samples': 14362752, 'steps': 74805, 'loss/train': 1.164042592048645} 08/31/2021 02:39:50 - INFO - __main__ - Step 74807: {'lr': 0.000256335574403101, 'samples': 14362944, 'steps': 74806, 'loss/train': 0.3094871938228607} 08/31/2021 02:39:50 - INFO - __main__ - Step 74808: {'lr': 0.00025633026936168116, 'samples': 14363136, 'steps': 74807, 'loss/train': 1.506894826889038} 08/31/2021 02:39:51 - INFO - __main__ - Step 74809: {'lr': 0.0002563249643174089, 'samples': 14363328, 'steps': 74808, 'loss/train': 0.578403890132904} 08/31/2021 02:39:51 - INFO - __main__ - Step 74810: {'lr': 0.00025631965927028677, 'samples': 14363520, 'steps': 74809, 'loss/train': 1.069451093673706} 08/31/2021 02:39:51 - INFO - __main__ - Step 74811: {'lr': 0.0002563143542203171, 'samples': 14363712, 'steps': 74810, 'loss/train': 0.5738568902015686} 08/31/2021 02:39:53 - INFO - __main__ - Step 74812: {'lr': 0.0002563090491675022, 'samples': 14363904, 'steps': 74811, 'loss/train': 1.076644778251648} 08/31/2021 02:39:53 - INFO - __main__ - Step 74813: {'lr': 0.0002563037441118446, 'samples': 14364096, 'steps': 74812, 'loss/train': 1.1455881595611572} 08/31/2021 02:39:54 - INFO - __main__ - Step 74814: {'lr': 0.0002562984390533466, 'samples': 14364288, 'steps': 74813, 'loss/train': 1.1895058155059814} 08/31/2021 02:39:54 - INFO - __main__ - Step 74815: {'lr': 0.00025629313399201073, 'samples': 14364480, 'steps': 74814, 'loss/train': 1.0079935789108276} 08/31/2021 02:39:54 - INFO - __main__ - Step 74816: {'lr': 0.00025628782892783914, 'samples': 14364672, 'steps': 74815, 'loss/train': 1.1648732423782349} 08/31/2021 02:39:55 - INFO - __main__ - Step 74817: {'lr': 0.0002562825238608344, 'samples': 14364864, 'steps': 74816, 'loss/train': 1.5479427576065063} 08/31/2021 02:39:56 - INFO - __main__ - Step 74818: {'lr': 0.00025627721879099884, 'samples': 14365056, 'steps': 74817, 'loss/train': 1.417162537574768} 08/31/2021 02:39:57 - INFO - __main__ - Step 74819: {'lr': 0.00025627191371833485, 'samples': 14365248, 'steps': 74818, 'loss/train': 1.2715173959732056} 08/31/2021 02:39:57 - INFO - __main__ - Step 74820: {'lr': 0.00025626660864284484, 'samples': 14365440, 'steps': 74819, 'loss/train': 0.9102470278739929} 08/31/2021 02:39:57 - INFO - __main__ - Step 74821: {'lr': 0.0002562613035645312, 'samples': 14365632, 'steps': 74820, 'loss/train': 1.391611933708191} 08/31/2021 02:39:58 - INFO - __main__ - Step 74822: {'lr': 0.0002562559984833964, 'samples': 14365824, 'steps': 74821, 'loss/train': 0.8878122568130493} 08/31/2021 02:40:00 - INFO - __main__ - Step 74823: {'lr': 0.00025625069339944265, 'samples': 14366016, 'steps': 74822, 'loss/train': 1.1036534309387207} 08/31/2021 02:40:00 - INFO - __main__ - Step 74824: {'lr': 0.00025624538831267243, 'samples': 14366208, 'steps': 74823, 'loss/train': 1.5622450113296509} 08/31/2021 02:40:00 - INFO - __main__ - Step 74825: {'lr': 0.0002562400832230881, 'samples': 14366400, 'steps': 74824, 'loss/train': 0.9755282402038574} 08/31/2021 02:40:01 - INFO - __main__ - Step 74826: {'lr': 0.0002562347781306922, 'samples': 14366592, 'steps': 74825, 'loss/train': 1.5701227188110352} 08/31/2021 02:40:01 - INFO - __main__ - Step 74827: {'lr': 0.0002562294730354869, 'samples': 14366784, 'steps': 74826, 'loss/train': 1.2928237915039062} 08/31/2021 02:40:03 - INFO - __main__ - Step 74828: {'lr': 0.0002562241679374748, 'samples': 14366976, 'steps': 74827, 'loss/train': 1.7081665992736816} 08/31/2021 02:40:04 - INFO - __main__ - Step 74829: {'lr': 0.0002562188628366581, 'samples': 14367168, 'steps': 74828, 'loss/train': 1.2256335020065308} 08/31/2021 02:40:04 - INFO - __main__ - Step 74830: {'lr': 0.00025621355773303926, 'samples': 14367360, 'steps': 74829, 'loss/train': 1.3257981538772583} 08/31/2021 02:40:04 - INFO - __main__ - Step 74831: {'lr': 0.00025620825262662075, 'samples': 14367552, 'steps': 74830, 'loss/train': 0.9260838031768799} 08/31/2021 02:40:05 - INFO - __main__ - Step 74832: {'lr': 0.00025620294751740484, 'samples': 14367744, 'steps': 74831, 'loss/train': 0.9570564031600952} 08/31/2021 02:40:05 - INFO - __main__ - Step 74833: {'lr': 0.000256197642405394, 'samples': 14367936, 'steps': 74832, 'loss/train': 0.8585691452026367} 08/31/2021 02:40:06 - INFO - __main__ - Step 74834: {'lr': 0.0002561923372905906, 'samples': 14368128, 'steps': 74833, 'loss/train': 1.0666221380233765} 08/31/2021 02:40:07 - INFO - __main__ - Step 74835: {'lr': 0.00025618703217299713, 'samples': 14368320, 'steps': 74834, 'loss/train': 0.7489994168281555} 08/31/2021 02:40:07 - INFO - __main__ - Step 74836: {'lr': 0.0002561817270526158, 'samples': 14368512, 'steps': 74835, 'loss/train': 2.039583444595337} 08/31/2021 02:40:08 - INFO - __main__ - Step 74837: {'lr': 0.000256176421929449, 'samples': 14368704, 'steps': 74836, 'loss/train': 1.7273834943771362} 08/31/2021 02:40:08 - INFO - __main__ - Step 74838: {'lr': 0.00025617111680349924, 'samples': 14368896, 'steps': 74837, 'loss/train': 1.5640935897827148} 08/31/2021 02:40:08 - INFO - __main__ - Step 74839: {'lr': 0.00025616581167476894, 'samples': 14369088, 'steps': 74838, 'loss/train': 1.1625932455062866} 08/31/2021 02:40:10 - INFO - __main__ - Step 74840: {'lr': 0.00025616050654326037, 'samples': 14369280, 'steps': 74839, 'loss/train': 1.1804571151733398} 08/31/2021 02:40:10 - INFO - __main__ - Step 74841: {'lr': 0.00025615520140897597, 'samples': 14369472, 'steps': 74840, 'loss/train': 0.9704157114028931} 08/31/2021 02:40:11 - INFO - __main__ - Step 74842: {'lr': 0.0002561498962719181, 'samples': 14369664, 'steps': 74841, 'loss/train': 1.053851842880249} 08/31/2021 02:40:11 - INFO - __main__ - Step 74843: {'lr': 0.0002561445911320893, 'samples': 14369856, 'steps': 74842, 'loss/train': 0.9269737005233765} 08/31/2021 02:40:11 - INFO - __main__ - Step 74844: {'lr': 0.0002561392859894917, 'samples': 14370048, 'steps': 74843, 'loss/train': 1.7170782089233398} 08/31/2021 02:40:13 - INFO - __main__ - Step 74845: {'lr': 0.00025613398084412795, 'samples': 14370240, 'steps': 74844, 'loss/train': 0.30610227584838867} 08/31/2021 02:40:13 - INFO - __main__ - Step 74846: {'lr': 0.00025612867569600023, 'samples': 14370432, 'steps': 74845, 'loss/train': 0.3502427637577057} 08/31/2021 02:40:14 - INFO - __main__ - Step 74847: {'lr': 0.000256123370545111, 'samples': 14370624, 'steps': 74846, 'loss/train': 0.518635094165802} 08/31/2021 02:40:14 - INFO - __main__ - Step 74848: {'lr': 0.0002561180653914628, 'samples': 14370816, 'steps': 74847, 'loss/train': 1.741651177406311} 08/31/2021 02:40:14 - INFO - __main__ - Step 74849: {'lr': 0.00025611276023505787, 'samples': 14371008, 'steps': 74848, 'loss/train': 1.2459365129470825} 08/31/2021 02:40:16 - INFO - __main__ - Step 74850: {'lr': 0.00025610745507589856, 'samples': 14371200, 'steps': 74849, 'loss/train': 0.6301921010017395} 08/31/2021 02:40:17 - INFO - __main__ - Step 74851: {'lr': 0.00025610214991398733, 'samples': 14371392, 'steps': 74850, 'loss/train': 0.08949711918830872} 08/31/2021 02:40:17 - INFO - __main__ - Step 74852: {'lr': 0.00025609684474932657, 'samples': 14371584, 'steps': 74851, 'loss/train': 1.0261272192001343} 08/31/2021 02:40:17 - INFO - __main__ - Step 74853: {'lr': 0.00025609153958191865, 'samples': 14371776, 'steps': 74852, 'loss/train': 1.0879582166671753} 08/31/2021 02:40:18 - INFO - __main__ - Step 74854: {'lr': 0.0002560862344117661, 'samples': 14371968, 'steps': 74853, 'loss/train': 1.240535020828247} 08/31/2021 02:40:19 - INFO - __main__ - Step 74855: {'lr': 0.00025608092923887107, 'samples': 14372160, 'steps': 74854, 'loss/train': 1.0636796951293945} 08/31/2021 02:40:20 - INFO - __main__ - Step 74856: {'lr': 0.00025607562406323607, 'samples': 14372352, 'steps': 74855, 'loss/train': 0.3212813138961792} 08/31/2021 02:40:20 - INFO - __main__ - Step 74857: {'lr': 0.0002560703188848635, 'samples': 14372544, 'steps': 74856, 'loss/train': 0.3255368173122406} 08/31/2021 02:40:20 - INFO - __main__ - Step 74858: {'lr': 0.0002560650137037557, 'samples': 14372736, 'steps': 74857, 'loss/train': 1.141413927078247} 08/31/2021 02:40:21 - INFO - __main__ - Step 74859: {'lr': 0.0002560597085199152, 'samples': 14372928, 'steps': 74858, 'loss/train': 0.7652764320373535} 08/31/2021 02:40:22 - INFO - __main__ - Step 74860: {'lr': 0.00025605440333334423, 'samples': 14373120, 'steps': 74859, 'loss/train': 0.8207625150680542} 08/31/2021 02:40:23 - INFO - __main__ - Step 74861: {'lr': 0.00025604909814404525, 'samples': 14373312, 'steps': 74860, 'loss/train': 1.330777883529663} 08/31/2021 02:40:23 - INFO - __main__ - Step 74862: {'lr': 0.00025604379295202063, 'samples': 14373504, 'steps': 74861, 'loss/train': 0.1706676036119461} 08/31/2021 02:40:23 - INFO - __main__ - Step 74863: {'lr': 0.0002560384877572727, 'samples': 14373696, 'steps': 74862, 'loss/train': 1.4504140615463257} 08/31/2021 02:40:24 - INFO - __main__ - Step 74864: {'lr': 0.000256033182559804, 'samples': 14373888, 'steps': 74863, 'loss/train': 1.673542857170105} 08/31/2021 02:40:25 - INFO - __main__ - Step 74865: {'lr': 0.0002560278773596169, 'samples': 14374080, 'steps': 74864, 'loss/train': 1.3253788948059082} 08/31/2021 02:40:26 - INFO - __main__ - Step 74866: {'lr': 0.00025602257215671367, 'samples': 14374272, 'steps': 74865, 'loss/train': 0.8473280072212219} 08/31/2021 02:40:26 - INFO - __main__ - Step 74867: {'lr': 0.00025601726695109674, 'samples': 14374464, 'steps': 74866, 'loss/train': 2.1004552841186523} 08/31/2021 02:40:26 - INFO - __main__ - Step 74868: {'lr': 0.00025601196174276854, 'samples': 14374656, 'steps': 74867, 'loss/train': 1.0816571712493896} 08/31/2021 02:40:27 - INFO - __main__ - Step 74869: {'lr': 0.00025600665653173146, 'samples': 14374848, 'steps': 74868, 'loss/train': 1.375726580619812} 08/31/2021 02:40:29 - INFO - __main__ - Step 74870: {'lr': 0.00025600135131798783, 'samples': 14375040, 'steps': 74869, 'loss/train': 0.22730781137943268} 08/31/2021 02:40:29 - INFO - __main__ - Step 74871: {'lr': 0.00025599604610154015, 'samples': 14375232, 'steps': 74870, 'loss/train': 1.3766146898269653} 08/31/2021 02:40:30 - INFO - __main__ - Step 74872: {'lr': 0.00025599074088239064, 'samples': 14375424, 'steps': 74871, 'loss/train': 1.372460126876831} 08/31/2021 02:40:30 - INFO - __main__ - Step 74873: {'lr': 0.0002559854356605419, 'samples': 14375616, 'steps': 74872, 'loss/train': 0.11907536536455154} 08/31/2021 02:40:30 - INFO - __main__ - Step 74874: {'lr': 0.00025598013043599615, 'samples': 14375808, 'steps': 74873, 'loss/train': 1.7033352851867676} 08/31/2021 02:40:31 - INFO - __main__ - Step 74875: {'lr': 0.0002559748252087559, 'samples': 14376000, 'steps': 74874, 'loss/train': 0.9502257108688354} 08/31/2021 02:40:32 - INFO - __main__ - Step 74876: {'lr': 0.00025596951997882344, 'samples': 14376192, 'steps': 74875, 'loss/train': 2.3171427249908447} 08/31/2021 02:40:33 - INFO - __main__ - Step 74877: {'lr': 0.00025596421474620125, 'samples': 14376384, 'steps': 74876, 'loss/train': 3.9296882152557373} 08/31/2021 02:40:33 - INFO - __main__ - Step 74878: {'lr': 0.0002559589095108916, 'samples': 14376576, 'steps': 74877, 'loss/train': 1.0012842416763306} 08/31/2021 02:40:34 - INFO - __main__ - Step 74879: {'lr': 0.000255953604272897, 'samples': 14376768, 'steps': 74878, 'loss/train': 1.3301252126693726} 08/31/2021 02:40:34 - INFO - __main__ - Step 74880: {'lr': 0.0002559482990322198, 'samples': 14376960, 'steps': 74879, 'loss/train': 0.8375659584999084} 08/31/2021 02:40:36 - INFO - __main__ - Step 74881: {'lr': 0.0002559429937888624, 'samples': 14377152, 'steps': 74880, 'loss/train': 1.7847907543182373} 08/31/2021 02:40:36 - INFO - __main__ - Step 74882: {'lr': 0.0002559376885428272, 'samples': 14377344, 'steps': 74881, 'loss/train': 1.1466411352157593} 08/31/2021 02:40:36 - INFO - __main__ - Step 74883: {'lr': 0.00025593238329411655, 'samples': 14377536, 'steps': 74882, 'loss/train': 1.0072886943817139} 08/31/2021 02:40:37 - INFO - __main__ - Step 74884: {'lr': 0.00025592707804273284, 'samples': 14377728, 'steps': 74883, 'loss/train': 0.5843454599380493} 08/31/2021 02:40:37 - INFO - __main__ - Step 74885: {'lr': 0.00025592177278867847, 'samples': 14377920, 'steps': 74884, 'loss/train': 1.5140656232833862} 08/31/2021 02:40:37 - INFO - __main__ - Step 74886: {'lr': 0.0002559164675319559, 'samples': 14378112, 'steps': 74885, 'loss/train': 0.0828278437256813} 08/31/2021 02:40:39 - INFO - __main__ - Step 74887: {'lr': 0.0002559111622725674, 'samples': 14378304, 'steps': 74886, 'loss/train': 1.6604418754577637} 08/31/2021 02:40:39 - INFO - __main__ - Step 74888: {'lr': 0.0002559058570105154, 'samples': 14378496, 'steps': 74887, 'loss/train': 1.0260953903198242} 08/31/2021 02:40:40 - INFO - __main__ - Step 74889: {'lr': 0.0002559005517458024, 'samples': 14378688, 'steps': 74888, 'loss/train': 1.906926155090332} 08/31/2021 02:40:40 - INFO - __main__ - Step 74890: {'lr': 0.00025589524647843067, 'samples': 14378880, 'steps': 74889, 'loss/train': 0.880640983581543} 08/31/2021 02:40:40 - INFO - __main__ - Step 74891: {'lr': 0.0002558899412084026, 'samples': 14379072, 'steps': 74890, 'loss/train': 1.0329668521881104} 08/31/2021 02:40:42 - INFO - __main__ - Step 74892: {'lr': 0.0002558846359357206, 'samples': 14379264, 'steps': 74891, 'loss/train': 1.47071373462677} 08/31/2021 02:40:43 - INFO - __main__ - Step 74893: {'lr': 0.00025587933066038707, 'samples': 14379456, 'steps': 74892, 'loss/train': 0.8369423151016235} 08/31/2021 02:40:43 - INFO - __main__ - Step 74894: {'lr': 0.00025587402538240447, 'samples': 14379648, 'steps': 74893, 'loss/train': 1.3960707187652588} 08/31/2021 02:40:43 - INFO - __main__ - Step 74895: {'lr': 0.0002558687201017751, 'samples': 14379840, 'steps': 74894, 'loss/train': 0.0717979371547699} 08/31/2021 02:40:44 - INFO - __main__ - Step 74896: {'lr': 0.0002558634148185014, 'samples': 14380032, 'steps': 74895, 'loss/train': 0.9806078672409058} 08/31/2021 02:40:45 - INFO - __main__ - Step 74897: {'lr': 0.0002558581095325857, 'samples': 14380224, 'steps': 74896, 'loss/train': 1.1636872291564941} 08/31/2021 02:40:46 - INFO - __main__ - Step 74898: {'lr': 0.0002558528042440304, 'samples': 14380416, 'steps': 74897, 'loss/train': 1.6326043605804443} 08/31/2021 02:40:46 - INFO - __main__ - Step 74899: {'lr': 0.00025584749895283794, 'samples': 14380608, 'steps': 74898, 'loss/train': 1.3479992151260376} 08/31/2021 02:40:46 - INFO - __main__ - Step 74900: {'lr': 0.0002558421936590107, 'samples': 14380800, 'steps': 74899, 'loss/train': 1.3986423015594482} 08/31/2021 02:40:47 - INFO - __main__ - Step 74901: {'lr': 0.000255836888362551, 'samples': 14380992, 'steps': 74900, 'loss/train': 0.7920138239860535} 08/31/2021 02:40:48 - INFO - __main__ - Step 74902: {'lr': 0.00025583158306346143, 'samples': 14381184, 'steps': 74901, 'loss/train': 1.7809818983078003} 08/31/2021 02:40:49 - INFO - __main__ - Step 74903: {'lr': 0.0002558262777617442, 'samples': 14381376, 'steps': 74902, 'loss/train': 1.0741312503814697} 08/31/2021 02:40:49 - INFO - __main__ - Step 74904: {'lr': 0.0002558209724574016, 'samples': 14381568, 'steps': 74903, 'loss/train': 0.7883332371711731} 08/31/2021 02:40:50 - INFO - __main__ - Step 74905: {'lr': 0.00025581566715043624, 'samples': 14381760, 'steps': 74904, 'loss/train': 1.5493282079696655} 08/31/2021 02:40:50 - INFO - __main__ - Step 74906: {'lr': 0.00025581036184085045, 'samples': 14381952, 'steps': 74905, 'loss/train': 0.06510284543037415} 08/31/2021 02:40:52 - INFO - __main__ - Step 74907: {'lr': 0.0002558050565286466, 'samples': 14382144, 'steps': 74906, 'loss/train': 1.0087652206420898} 08/31/2021 02:40:52 - INFO - __main__ - Step 74908: {'lr': 0.00025579975121382706, 'samples': 14382336, 'steps': 74907, 'loss/train': 1.5112428665161133} 08/31/2021 02:40:52 - INFO - __main__ - Step 74909: {'lr': 0.0002557944458963943, 'samples': 14382528, 'steps': 74908, 'loss/train': 1.1100566387176514} 08/31/2021 02:40:53 - INFO - __main__ - Step 74910: {'lr': 0.0002557891405763506, 'samples': 14382720, 'steps': 74909, 'loss/train': 1.1927729845046997} 08/31/2021 02:40:53 - INFO - __main__ - Step 74911: {'lr': 0.0002557838352536984, 'samples': 14382912, 'steps': 74910, 'loss/train': 1.275374174118042} 08/31/2021 02:40:55 - INFO - __main__ - Step 74912: {'lr': 0.00025577852992844007, 'samples': 14383104, 'steps': 74911, 'loss/train': 1.6435855627059937} 08/31/2021 02:40:55 - INFO - __main__ - Step 74913: {'lr': 0.00025577322460057804, 'samples': 14383296, 'steps': 74912, 'loss/train': 1.4391789436340332} 08/31/2021 02:40:55 - INFO - __main__ - Step 74914: {'lr': 0.00025576791927011473, 'samples': 14383488, 'steps': 74913, 'loss/train': 0.989947497844696} 08/31/2021 02:40:56 - INFO - __main__ - Step 74915: {'lr': 0.00025576261393705244, 'samples': 14383680, 'steps': 74914, 'loss/train': 1.0963897705078125} 08/31/2021 02:40:56 - INFO - __main__ - Step 74916: {'lr': 0.00025575730860139364, 'samples': 14383872, 'steps': 74915, 'loss/train': 1.763017177581787} 08/31/2021 02:40:57 - INFO - __main__ - Step 74917: {'lr': 0.0002557520032631406, 'samples': 14384064, 'steps': 74916, 'loss/train': 1.345076084136963} 08/31/2021 02:40:58 - INFO - __main__ - Step 74918: {'lr': 0.00025574669792229586, 'samples': 14384256, 'steps': 74917, 'loss/train': 0.06362662464380264} 08/31/2021 02:40:59 - INFO - __main__ - Step 74919: {'lr': 0.0002557413925788618, 'samples': 14384448, 'steps': 74918, 'loss/train': 0.905857503414154} 08/31/2021 02:40:59 - INFO - __main__ - Step 74920: {'lr': 0.0002557360872328407, 'samples': 14384640, 'steps': 74919, 'loss/train': 1.168685793876648} 08/31/2021 02:40:59 - INFO - __main__ - Step 74921: {'lr': 0.000255730781884235, 'samples': 14384832, 'steps': 74920, 'loss/train': 1.238973617553711} 08/31/2021 02:41:00 - INFO - __main__ - Step 74922: {'lr': 0.00025572547653304707, 'samples': 14385024, 'steps': 74921, 'loss/train': 0.04512011632323265} 08/31/2021 02:41:02 - INFO - __main__ - Step 74923: {'lr': 0.00025572017117927944, 'samples': 14385216, 'steps': 74922, 'loss/train': 1.5053362846374512} 08/31/2021 02:41:02 - INFO - __main__ - Step 74924: {'lr': 0.0002557148658229343, 'samples': 14385408, 'steps': 74923, 'loss/train': 1.1575076580047607} 08/31/2021 02:41:03 - INFO - __main__ - Step 74925: {'lr': 0.00025570956046401413, 'samples': 14385600, 'steps': 74924, 'loss/train': 1.7220473289489746} 08/31/2021 02:41:03 - INFO - __main__ - Step 74926: {'lr': 0.00025570425510252135, 'samples': 14385792, 'steps': 74925, 'loss/train': 1.6104127168655396} 08/31/2021 02:41:03 - INFO - __main__ - Step 74927: {'lr': 0.00025569894973845824, 'samples': 14385984, 'steps': 74926, 'loss/train': 0.08701974898576736} 08/31/2021 02:41:04 - INFO - __main__ - Step 74928: {'lr': 0.00025569364437182736, 'samples': 14386176, 'steps': 74927, 'loss/train': 1.6073839664459229} 08/31/2021 02:41:05 - INFO - __main__ - Step 74929: {'lr': 0.00025568833900263104, 'samples': 14386368, 'steps': 74928, 'loss/train': 1.4121427536010742} 08/31/2021 02:41:06 - INFO - __main__ - Step 74930: {'lr': 0.00025568303363087156, 'samples': 14386560, 'steps': 74929, 'loss/train': 1.0033349990844727} 08/31/2021 02:41:06 - INFO - __main__ - Step 74931: {'lr': 0.00025567772825655147, 'samples': 14386752, 'steps': 74930, 'loss/train': 1.0234546661376953} 08/31/2021 02:41:06 - INFO - __main__ - Step 74932: {'lr': 0.00025567242287967304, 'samples': 14386944, 'steps': 74931, 'loss/train': 1.346171259880066} 08/31/2021 02:41:07 - INFO - __main__ - Step 74933: {'lr': 0.00025566711750023865, 'samples': 14387136, 'steps': 74932, 'loss/train': 1.180854082107544} 08/31/2021 02:41:08 - INFO - __main__ - Step 74934: {'lr': 0.0002556618121182508, 'samples': 14387328, 'steps': 74933, 'loss/train': 1.0656051635742188} 08/31/2021 02:41:09 - INFO - __main__ - Step 74935: {'lr': 0.00025565650673371184, 'samples': 14387520, 'steps': 74934, 'loss/train': 2.436638355255127} 08/31/2021 02:41:09 - INFO - __main__ - Step 74936: {'lr': 0.00025565120134662413, 'samples': 14387712, 'steps': 74935, 'loss/train': 0.5235907435417175} 08/31/2021 02:41:09 - INFO - __main__ - Step 74937: {'lr': 0.00025564589595699006, 'samples': 14387904, 'steps': 74936, 'loss/train': 0.9675179123878479} 08/31/2021 02:41:10 - INFO - __main__ - Step 74938: {'lr': 0.000255640590564812, 'samples': 14388096, 'steps': 74937, 'loss/train': 1.3103147745132446} 08/31/2021 02:41:11 - INFO - __main__ - Step 74939: {'lr': 0.0002556352851700925, 'samples': 14388288, 'steps': 74938, 'loss/train': 1.3825825452804565} 08/31/2021 02:41:12 - INFO - __main__ - Step 74940: {'lr': 0.0002556299797728337, 'samples': 14388480, 'steps': 74939, 'loss/train': 1.5057300329208374} 08/31/2021 02:41:12 - INFO - __main__ - Step 74941: {'lr': 0.0002556246743730382, 'samples': 14388672, 'steps': 74940, 'loss/train': 1.2873327732086182} 08/31/2021 02:41:13 - INFO - __main__ - Step 74942: {'lr': 0.00025561936897070827, 'samples': 14388864, 'steps': 74941, 'loss/train': 0.7437264323234558} 08/31/2021 02:41:13 - INFO - __main__ - Step 74943: {'lr': 0.00025561406356584636, 'samples': 14389056, 'steps': 74942, 'loss/train': 1.237999439239502} 08/31/2021 02:41:14 - INFO - __main__ - Step 74944: {'lr': 0.00025560875815845485, 'samples': 14389248, 'steps': 74943, 'loss/train': 0.6687834858894348} 08/31/2021 02:41:15 - INFO - __main__ - Step 74945: {'lr': 0.00025560345274853606, 'samples': 14389440, 'steps': 74944, 'loss/train': 1.0436264276504517} 08/31/2021 02:41:15 - INFO - __main__ - Step 74946: {'lr': 0.0002555981473360925, 'samples': 14389632, 'steps': 74945, 'loss/train': 0.8544621467590332} 08/31/2021 02:41:16 - INFO - __main__ - Step 74947: {'lr': 0.00025559284192112647, 'samples': 14389824, 'steps': 74946, 'loss/train': 1.4611537456512451} 08/31/2021 02:41:16 - INFO - __main__ - Step 74948: {'lr': 0.0002555875365036404, 'samples': 14390016, 'steps': 74947, 'loss/train': 0.549538254737854} 08/31/2021 02:41:16 - INFO - __main__ - Step 74949: {'lr': 0.00025558223108363673, 'samples': 14390208, 'steps': 74948, 'loss/train': 0.6973435282707214} 08/31/2021 02:41:18 - INFO - __main__ - Step 74950: {'lr': 0.00025557692566111767, 'samples': 14390400, 'steps': 74949, 'loss/train': 0.8347441554069519} 08/31/2021 02:41:18 - INFO - __main__ - Step 74951: {'lr': 0.0002555716202360858, 'samples': 14390592, 'steps': 74950, 'loss/train': 1.0891199111938477} 08/31/2021 02:41:19 - INFO - __main__ - Step 74952: {'lr': 0.0002555663148085435, 'samples': 14390784, 'steps': 74951, 'loss/train': 1.3507052659988403} 08/31/2021 02:41:19 - INFO - __main__ - Step 74953: {'lr': 0.00025556100937849295, 'samples': 14390976, 'steps': 74952, 'loss/train': 0.7958877086639404} 08/31/2021 02:41:19 - INFO - __main__ - Step 74954: {'lr': 0.0002555557039459368, 'samples': 14391168, 'steps': 74953, 'loss/train': 1.513616681098938} 08/31/2021 02:41:21 - INFO - __main__ - Step 74955: {'lr': 0.00025555039851087735, 'samples': 14391360, 'steps': 74954, 'loss/train': 0.761959969997406} 08/31/2021 02:41:21 - INFO - __main__ - Step 74956: {'lr': 0.00025554509307331705, 'samples': 14391552, 'steps': 74955, 'loss/train': 1.5591531991958618} 08/31/2021 02:41:22 - INFO - __main__ - Step 74957: {'lr': 0.0002555397876332581, 'samples': 14391744, 'steps': 74956, 'loss/train': 1.375494360923767} 08/31/2021 02:41:22 - INFO - __main__ - Step 74958: {'lr': 0.00025553448219070297, 'samples': 14391936, 'steps': 74957, 'loss/train': 1.539903998374939} 08/31/2021 02:41:22 - INFO - __main__ - Step 74959: {'lr': 0.00025552917674565414, 'samples': 14392128, 'steps': 74958, 'loss/train': 1.273618459701538} 08/31/2021 02:41:24 - INFO - __main__ - Step 74960: {'lr': 0.00025552387129811397, 'samples': 14392320, 'steps': 74959, 'loss/train': 1.4077534675598145} 08/31/2021 02:41:24 - INFO - __main__ - Step 74961: {'lr': 0.0002555185658480848, 'samples': 14392512, 'steps': 74960, 'loss/train': 1.1467105150222778} 08/31/2021 02:41:25 - INFO - __main__ - Step 74962: {'lr': 0.00025551326039556906, 'samples': 14392704, 'steps': 74961, 'loss/train': 1.2807971239089966} 08/31/2021 02:41:25 - INFO - __main__ - Step 74963: {'lr': 0.00025550795494056914, 'samples': 14392896, 'steps': 74962, 'loss/train': 0.03416157141327858} 08/31/2021 02:41:25 - INFO - __main__ - Step 74964: {'lr': 0.00025550264948308744, 'samples': 14393088, 'steps': 74963, 'loss/train': 1.6998952627182007} 08/31/2021 02:41:27 - INFO - __main__ - Step 74965: {'lr': 0.0002554973440231263, 'samples': 14393280, 'steps': 74964, 'loss/train': 1.2244422435760498} 08/31/2021 02:41:28 - INFO - __main__ - Step 74966: {'lr': 0.00025549203856068813, 'samples': 14393472, 'steps': 74965, 'loss/train': 0.051251672208309174} 08/31/2021 02:41:28 - INFO - __main__ - Step 74967: {'lr': 0.00025548673309577536, 'samples': 14393664, 'steps': 74966, 'loss/train': 0.12922897934913635} 08/31/2021 02:41:28 - INFO - __main__ - Step 74968: {'lr': 0.00025548142762839033, 'samples': 14393856, 'steps': 74967, 'loss/train': 0.19428721070289612} 08/31/2021 02:41:29 - INFO - __main__ - Step 74969: {'lr': 0.00025547612215853544, 'samples': 14394048, 'steps': 74968, 'loss/train': 1.541616678237915} 08/31/2021 02:41:29 - INFO - __main__ - Step 74970: {'lr': 0.0002554708166862131, 'samples': 14394240, 'steps': 74969, 'loss/train': 1.8681145906448364} 08/31/2021 02:41:31 - INFO - __main__ - Step 74971: {'lr': 0.00025546551121142575, 'samples': 14394432, 'steps': 74970, 'loss/train': 0.6214266419410706} 08/31/2021 02:41:31 - INFO - __main__ - Step 74972: {'lr': 0.00025546020573417573, 'samples': 14394624, 'steps': 74971, 'loss/train': 1.0717648267745972} 08/31/2021 02:41:31 - INFO - __main__ - Step 74973: {'lr': 0.00025545490025446533, 'samples': 14394816, 'steps': 74972, 'loss/train': 1.2162166833877563} 08/31/2021 02:41:32 - INFO - __main__ - Step 74974: {'lr': 0.00025544959477229705, 'samples': 14395008, 'steps': 74973, 'loss/train': 1.3548469543457031} 08/31/2021 02:41:32 - INFO - __main__ - Step 74975: {'lr': 0.0002554442892876733, 'samples': 14395200, 'steps': 74974, 'loss/train': 1.2429494857788086} 08/31/2021 02:41:34 - INFO - __main__ - Step 74976: {'lr': 0.0002554389838005966, 'samples': 14395392, 'steps': 74975, 'loss/train': 0.952497124671936} 08/31/2021 02:41:35 - INFO - __main__ - Step 74977: {'lr': 0.00025543367831106894, 'samples': 14395584, 'steps': 74976, 'loss/train': 0.6303207874298096} 08/31/2021 02:41:35 - INFO - __main__ - Step 74978: {'lr': 0.000255428372819093, 'samples': 14395776, 'steps': 74977, 'loss/train': 1.17829430103302} 08/31/2021 02:41:35 - INFO - __main__ - Step 74979: {'lr': 0.0002554230673246712, 'samples': 14395968, 'steps': 74978, 'loss/train': 1.358996868133545} 08/31/2021 02:41:36 - INFO - __main__ - Step 74980: {'lr': 0.0002554177618278057, 'samples': 14396160, 'steps': 74979, 'loss/train': 1.4532705545425415} 08/31/2021 02:41:37 - INFO - __main__ - Step 74981: {'lr': 0.0002554124563284992, 'samples': 14396352, 'steps': 74980, 'loss/train': 1.3775603771209717} 08/31/2021 02:41:38 - INFO - __main__ - Step 74982: {'lr': 0.00025540715082675384, 'samples': 14396544, 'steps': 74981, 'loss/train': 1.664934515953064} 08/31/2021 02:41:38 - INFO - __main__ - Step 74983: {'lr': 0.0002554018453225722, 'samples': 14396736, 'steps': 74982, 'loss/train': 1.6029502153396606} 08/31/2021 02:41:38 - INFO - __main__ - Step 74984: {'lr': 0.00025539653981595644, 'samples': 14396928, 'steps': 74983, 'loss/train': 0.8195392489433289} 08/31/2021 02:41:39 - INFO - __main__ - Step 74985: {'lr': 0.0002553912343069092, 'samples': 14397120, 'steps': 74984, 'loss/train': 0.96502685546875} 08/31/2021 02:41:39 - INFO - __main__ - Step 74986: {'lr': 0.00025538592879543266, 'samples': 14397312, 'steps': 74985, 'loss/train': 1.2572399377822876} 08/31/2021 02:41:41 - INFO - __main__ - Step 74987: {'lr': 0.00025538062328152935, 'samples': 14397504, 'steps': 74986, 'loss/train': 1.695077657699585} 08/31/2021 02:41:41 - INFO - __main__ - Step 74988: {'lr': 0.00025537531776520164, 'samples': 14397696, 'steps': 74987, 'loss/train': 0.7704429626464844} 08/31/2021 02:41:41 - INFO - __main__ - Step 74989: {'lr': 0.00025537001224645183, 'samples': 14397888, 'steps': 74988, 'loss/train': 1.7076141834259033} 08/31/2021 02:41:42 - INFO - __main__ - Step 74990: {'lr': 0.0002553647067252824, 'samples': 14398080, 'steps': 74989, 'loss/train': 1.4675666093826294} 08/31/2021 02:41:42 - INFO - __main__ - Step 74991: {'lr': 0.0002553594012016957, 'samples': 14398272, 'steps': 74990, 'loss/train': 0.45606154203414917} 08/31/2021 02:41:44 - INFO - __main__ - Step 74992: {'lr': 0.00025535409567569416, 'samples': 14398464, 'steps': 74991, 'loss/train': 0.6531842947006226} 08/31/2021 02:41:44 - INFO - __main__ - Step 74993: {'lr': 0.00025534879014728015, 'samples': 14398656, 'steps': 74992, 'loss/train': 1.2798092365264893} 08/31/2021 02:41:44 - INFO - __main__ - Step 74994: {'lr': 0.0002553434846164561, 'samples': 14398848, 'steps': 74993, 'loss/train': 1.3041874170303345} 08/31/2021 02:41:45 - INFO - __main__ - Step 74995: {'lr': 0.0002553381790832243, 'samples': 14399040, 'steps': 74994, 'loss/train': 1.4234421253204346} 08/31/2021 02:41:45 - INFO - __main__ - Step 74996: {'lr': 0.0002553328735475872, 'samples': 14399232, 'steps': 74995, 'loss/train': 1.1885381937026978} 08/31/2021 02:41:47 - INFO - __main__ - Step 74997: {'lr': 0.0002553275680095472, 'samples': 14399424, 'steps': 74996, 'loss/train': 1.2689462900161743} 08/31/2021 02:41:47 - INFO - __main__ - Step 74998: {'lr': 0.00025532226246910666, 'samples': 14399616, 'steps': 74997, 'loss/train': 1.4146244525909424} 08/31/2021 02:41:47 - INFO - __main__ - Step 74999: {'lr': 0.00025531695692626805, 'samples': 14399808, 'steps': 74998, 'loss/train': 1.4525163173675537} 08/31/2021 02:41:48 - INFO - __main__ - Step 75000: {'lr': 0.0002553116513810337, 'samples': 14400000, 'steps': 74999, 'loss/train': 1.5982519388198853} 08/31/2021 02:41:48 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 02:50:28 - INFO - __main__ - Step 75000: {'loss/eval': 1.139208436012268, 'perplexity': 3.1242942810058594} 08/31/2021 02:50:28 - INFO - __main__ - Saving model checkpoint 08/31/2021 02:50:41 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['log/debug_0.log', 'wandb/run-20210830_131354-2654p8r7/files/output.log']. This may take a bit of time if the files are large. 08/31/2021 02:51:31 - INFO - __main__ - Step 75001: {'lr': 0.00025530634583340587, 'samples': 14400192, 'steps': 75000, 'loss/train': 1.2259427309036255} 08/31/2021 02:51:33 - INFO - __main__ - Step 75002: {'lr': 0.0002553010402833872, 'samples': 14400384, 'steps': 75001, 'loss/train': 5.946112632751465} 08/31/2021 02:51:34 - INFO - __main__ - Step 75003: {'lr': 0.00025529573473097994, 'samples': 14400576, 'steps': 75002, 'loss/train': 1.718904972076416} 08/31/2021 02:51:34 - INFO - __main__ - Step 75004: {'lr': 0.0002552904291761865, 'samples': 14400768, 'steps': 75003, 'loss/train': 0.5617595314979553} 08/31/2021 02:51:35 - INFO - __main__ - Step 75005: {'lr': 0.0002552851236190093, 'samples': 14400960, 'steps': 75004, 'loss/train': 1.3609336614608765} 08/31/2021 02:51:35 - INFO - __main__ - Step 75006: {'lr': 0.0002552798180594507, 'samples': 14401152, 'steps': 75005, 'loss/train': 1.4098682403564453} 08/31/2021 02:51:35 - INFO - __main__ - Step 75007: {'lr': 0.00025527451249751306, 'samples': 14401344, 'steps': 75006, 'loss/train': 0.03430351987481117} 08/31/2021 02:51:37 - INFO - __main__ - Step 75008: {'lr': 0.00025526920693319885, 'samples': 14401536, 'steps': 75007, 'loss/train': 0.026948530226945877} 08/31/2021 02:51:37 - INFO - __main__ - Step 75009: {'lr': 0.00025526390136651033, 'samples': 14401728, 'steps': 75008, 'loss/train': 1.0280604362487793} 08/31/2021 02:51:38 - INFO - __main__ - Step 75010: {'lr': 0.0002552585957974501, 'samples': 14401920, 'steps': 75009, 'loss/train': 1.7829108238220215} 08/31/2021 02:51:38 - INFO - __main__ - Step 75011: {'lr': 0.00025525329022602034, 'samples': 14402112, 'steps': 75010, 'loss/train': 0.8506579995155334} 08/31/2021 02:51:38 - INFO - __main__ - Step 75012: {'lr': 0.00025524798465222353, 'samples': 14402304, 'steps': 75011, 'loss/train': 0.6313310861587524} 08/31/2021 02:51:40 - INFO - __main__ - Step 75013: {'lr': 0.00025524267907606207, 'samples': 14402496, 'steps': 75012, 'loss/train': 1.0686086416244507} 08/31/2021 02:51:40 - INFO - __main__ - Step 75014: {'lr': 0.0002552373734975384, 'samples': 14402688, 'steps': 75013, 'loss/train': 1.1555296182632446} 08/31/2021 02:51:41 - INFO - __main__ - Step 75015: {'lr': 0.00025523206791665476, 'samples': 14402880, 'steps': 75014, 'loss/train': 1.4956631660461426} 08/31/2021 02:51:41 - INFO - __main__ - Step 75016: {'lr': 0.0002552267623334137, 'samples': 14403072, 'steps': 75015, 'loss/train': 0.7454053163528442} 08/31/2021 02:51:41 - INFO - __main__ - Step 75017: {'lr': 0.00025522145674781755, 'samples': 14403264, 'steps': 75016, 'loss/train': 1.4082878828048706} 08/31/2021 02:51:43 - INFO - __main__ - Step 75018: {'lr': 0.00025521615115986864, 'samples': 14403456, 'steps': 75017, 'loss/train': 1.241457223892212} 08/31/2021 02:51:43 - INFO - __main__ - Step 75019: {'lr': 0.0002552108455695694, 'samples': 14403648, 'steps': 75018, 'loss/train': 1.2261570692062378} 08/31/2021 02:51:44 - INFO - __main__ - Step 75020: {'lr': 0.0002552055399769223, 'samples': 14403840, 'steps': 75019, 'loss/train': 1.3119792938232422} 08/31/2021 02:51:44 - INFO - __main__ - Step 75021: {'lr': 0.0002552002343819296, 'samples': 14404032, 'steps': 75020, 'loss/train': 1.216381549835205} 08/31/2021 02:51:44 - INFO - __main__ - Step 75022: {'lr': 0.00025519492878459376, 'samples': 14404224, 'steps': 75021, 'loss/train': 1.4662489891052246} 08/31/2021 02:51:45 - INFO - __main__ - Step 75023: {'lr': 0.00025518962318491726, 'samples': 14404416, 'steps': 75022, 'loss/train': 1.757567286491394} 08/31/2021 02:51:46 - INFO - __main__ - Step 75024: {'lr': 0.0002551843175829023, 'samples': 14404608, 'steps': 75023, 'loss/train': 1.5770273208618164} 08/31/2021 02:51:47 - INFO - __main__ - Step 75025: {'lr': 0.00025517901197855136, 'samples': 14404800, 'steps': 75024, 'loss/train': 0.7316528558731079} 08/31/2021 02:51:47 - INFO - __main__ - Step 75026: {'lr': 0.0002551737063718669, 'samples': 14404992, 'steps': 75025, 'loss/train': 1.562834620475769} 08/31/2021 02:51:47 - INFO - __main__ - Step 75027: {'lr': 0.0002551684007628512, 'samples': 14405184, 'steps': 75026, 'loss/train': 1.7233790159225464} 08/31/2021 02:51:48 - INFO - __main__ - Step 75028: {'lr': 0.0002551630951515067, 'samples': 14405376, 'steps': 75027, 'loss/train': 1.128270149230957} 08/31/2021 02:51:50 - INFO - __main__ - Step 75029: {'lr': 0.00025515778953783577, 'samples': 14405568, 'steps': 75028, 'loss/train': 0.17061761021614075} 08/31/2021 02:51:50 - INFO - __main__ - Step 75030: {'lr': 0.00025515248392184094, 'samples': 14405760, 'steps': 75029, 'loss/train': 0.814765214920044} 08/31/2021 02:51:50 - INFO - __main__ - Step 75031: {'lr': 0.00025514717830352435, 'samples': 14405952, 'steps': 75030, 'loss/train': 1.1327362060546875} 08/31/2021 02:51:51 - INFO - __main__ - Step 75032: {'lr': 0.0002551418726828886, 'samples': 14406144, 'steps': 75031, 'loss/train': 1.7848137617111206} 08/31/2021 02:51:51 - INFO - __main__ - Step 75033: {'lr': 0.00025513656705993595, 'samples': 14406336, 'steps': 75032, 'loss/train': 0.02780049480497837} 08/31/2021 02:51:51 - INFO - __main__ - Step 75034: {'lr': 0.0002551312614346688, 'samples': 14406528, 'steps': 75033, 'loss/train': 0.10410826653242111} 08/31/2021 02:51:54 - INFO - __main__ - Step 75035: {'lr': 0.00025512595580708965, 'samples': 14406720, 'steps': 75034, 'loss/train': 0.8782897591590881} 08/31/2021 02:51:54 - INFO - __main__ - Step 75036: {'lr': 0.00025512065017720077, 'samples': 14406912, 'steps': 75035, 'loss/train': 3.3165743350982666} 08/31/2021 02:51:55 - INFO - __main__ - Step 75037: {'lr': 0.0002551153445450047, 'samples': 14407104, 'steps': 75036, 'loss/train': 0.9996334910392761} 08/31/2021 02:51:55 - INFO - __main__ - Step 75038: {'lr': 0.0002551100389105037, 'samples': 14407296, 'steps': 75037, 'loss/train': 0.6898874640464783} 08/31/2021 02:51:55 - INFO - __main__ - Step 75039: {'lr': 0.00025510473327370014, 'samples': 14407488, 'steps': 75038, 'loss/train': 1.2983372211456299} 08/31/2021 02:51:56 - INFO - __main__ - Step 75040: {'lr': 0.00025509942763459647, 'samples': 14407680, 'steps': 75039, 'loss/train': 1.1747699975967407} 08/31/2021 02:51:56 - INFO - __main__ - Step 75041: {'lr': 0.00025509412199319515, 'samples': 14407872, 'steps': 75040, 'loss/train': 0.07574766874313354} 08/31/2021 02:51:58 - INFO - __main__ - Step 75042: {'lr': 0.0002550888163494984, 'samples': 14408064, 'steps': 75041, 'loss/train': 0.029576534405350685} 08/31/2021 02:51:58 - INFO - __main__ - Step 75043: {'lr': 0.00025508351070350875, 'samples': 14408256, 'steps': 75042, 'loss/train': 1.0055469274520874} 08/31/2021 02:51:58 - INFO - __main__ - Step 75044: {'lr': 0.00025507820505522866, 'samples': 14408448, 'steps': 75043, 'loss/train': 1.84634268283844} 08/31/2021 02:51:59 - INFO - __main__ - Step 75045: {'lr': 0.0002550728994046603, 'samples': 14408640, 'steps': 75044, 'loss/train': 1.7448081970214844} 08/31/2021 02:51:59 - INFO - __main__ - Step 75046: {'lr': 0.0002550675937518062, 'samples': 14408832, 'steps': 75045, 'loss/train': 1.181408405303955} 08/31/2021 02:52:00 - INFO - __main__ - Step 75047: {'lr': 0.00025506228809666866, 'samples': 14409024, 'steps': 75046, 'loss/train': 1.1081984043121338} 08/31/2021 02:52:01 - INFO - __main__ - Step 75048: {'lr': 0.0002550569824392502, 'samples': 14409216, 'steps': 75047, 'loss/train': 1.6005512475967407} 08/31/2021 02:52:01 - INFO - __main__ - Step 75049: {'lr': 0.00025505167677955303, 'samples': 14409408, 'steps': 75048, 'loss/train': 0.8842373490333557} 08/31/2021 02:52:02 - INFO - __main__ - Step 75050: {'lr': 0.00025504637111757985, 'samples': 14409600, 'steps': 75049, 'loss/train': 0.9381831288337708} 08/31/2021 02:52:02 - INFO - __main__ - Step 75051: {'lr': 0.0002550410654533327, 'samples': 14409792, 'steps': 75050, 'loss/train': 1.4434939622879028} 08/31/2021 02:52:04 - INFO - __main__ - Step 75052: {'lr': 0.00025503575978681417, 'samples': 14409984, 'steps': 75051, 'loss/train': 1.447698712348938} 08/31/2021 02:52:04 - INFO - __main__ - Step 75053: {'lr': 0.00025503045411802655, 'samples': 14410176, 'steps': 75052, 'loss/train': 0.9964850544929504} 08/31/2021 02:52:04 - INFO - __main__ - Step 75054: {'lr': 0.00025502514844697236, 'samples': 14410368, 'steps': 75053, 'loss/train': 1.948672890663147} 08/31/2021 02:52:05 - INFO - __main__ - Step 75055: {'lr': 0.00025501984277365386, 'samples': 14410560, 'steps': 75054, 'loss/train': 1.194271445274353} 08/31/2021 02:52:05 - INFO - __main__ - Step 75056: {'lr': 0.00025501453709807356, 'samples': 14410752, 'steps': 75055, 'loss/train': 0.036900412291288376} 08/31/2021 02:52:07 - INFO - __main__ - Step 75057: {'lr': 0.0002550092314202337, 'samples': 14410944, 'steps': 75056, 'loss/train': 2.194547653198242} 08/31/2021 02:52:07 - INFO - __main__ - Step 75058: {'lr': 0.00025500392574013685, 'samples': 14411136, 'steps': 75057, 'loss/train': 1.3241511583328247} 08/31/2021 02:52:07 - INFO - __main__ - Step 75059: {'lr': 0.00025499862005778527, 'samples': 14411328, 'steps': 75058, 'loss/train': 0.9397519826889038} 08/31/2021 02:52:08 - INFO - __main__ - Step 75060: {'lr': 0.0002549933143731814, 'samples': 14411520, 'steps': 75059, 'loss/train': 1.2059135437011719} 08/31/2021 02:52:08 - INFO - __main__ - Step 75061: {'lr': 0.0002549880086863276, 'samples': 14411712, 'steps': 75060, 'loss/train': 1.1453269720077515} 08/31/2021 02:52:10 - INFO - __main__ - Step 75062: {'lr': 0.00025498270299722625, 'samples': 14411904, 'steps': 75061, 'loss/train': 1.8759700059890747} 08/31/2021 02:52:10 - INFO - __main__ - Step 75063: {'lr': 0.0002549773973058798, 'samples': 14412096, 'steps': 75062, 'loss/train': 1.0240957736968994} 08/31/2021 02:52:11 - INFO - __main__ - Step 75064: {'lr': 0.0002549720916122907, 'samples': 14412288, 'steps': 75063, 'loss/train': 0.7467330098152161} 08/31/2021 02:52:11 - INFO - __main__ - Step 75065: {'lr': 0.00025496678591646117, 'samples': 14412480, 'steps': 75064, 'loss/train': 1.2114856243133545} 08/31/2021 02:52:11 - INFO - __main__ - Step 75066: {'lr': 0.00025496148021839364, 'samples': 14412672, 'steps': 75065, 'loss/train': 0.2940925061702728} 08/31/2021 02:52:13 - INFO - __main__ - Step 75067: {'lr': 0.0002549561745180906, 'samples': 14412864, 'steps': 75066, 'loss/train': 1.1444505453109741} 08/31/2021 02:52:14 - INFO - __main__ - Step 75068: {'lr': 0.0002549508688155544, 'samples': 14413056, 'steps': 75067, 'loss/train': 1.5056134462356567} 08/31/2021 02:52:14 - INFO - __main__ - Step 75069: {'lr': 0.0002549455631107873, 'samples': 14413248, 'steps': 75068, 'loss/train': 0.040721818804740906} 08/31/2021 02:52:14 - INFO - __main__ - Step 75070: {'lr': 0.00025494025740379196, 'samples': 14413440, 'steps': 75069, 'loss/train': 1.2061891555786133} 08/31/2021 02:52:15 - INFO - __main__ - Step 75071: {'lr': 0.00025493495169457054, 'samples': 14413632, 'steps': 75070, 'loss/train': 0.1436704397201538} 08/31/2021 02:52:15 - INFO - __main__ - Step 75072: {'lr': 0.00025492964598312554, 'samples': 14413824, 'steps': 75071, 'loss/train': 0.041327450424432755} 08/31/2021 02:52:17 - INFO - __main__ - Step 75073: {'lr': 0.00025492434026945927, 'samples': 14414016, 'steps': 75072, 'loss/train': 0.9918743968009949} 08/31/2021 02:52:17 - INFO - __main__ - Step 75074: {'lr': 0.0002549190345535742, 'samples': 14414208, 'steps': 75073, 'loss/train': 1.52540123462677} 08/31/2021 02:52:18 - INFO - __main__ - Step 75075: {'lr': 0.00025491372883547266, 'samples': 14414400, 'steps': 75074, 'loss/train': 0.027844786643981934} 08/31/2021 02:52:18 - INFO - __main__ - Step 75076: {'lr': 0.00025490842311515704, 'samples': 14414592, 'steps': 75075, 'loss/train': 1.0305720567703247} 08/31/2021 02:52:18 - INFO - __main__ - Step 75077: {'lr': 0.0002549031173926299, 'samples': 14414784, 'steps': 75076, 'loss/train': 1.2526459693908691} 08/31/2021 02:52:19 - INFO - __main__ - Step 75078: {'lr': 0.0002548978116678934, 'samples': 14414976, 'steps': 75077, 'loss/train': 0.39343300461769104} 08/31/2021 02:52:20 - INFO - __main__ - Step 75079: {'lr': 0.00025489250594095, 'samples': 14415168, 'steps': 75078, 'loss/train': 0.30718183517456055} 08/31/2021 02:52:21 - INFO - __main__ - Step 75080: {'lr': 0.00025488720021180213, 'samples': 14415360, 'steps': 75079, 'loss/train': 0.951718807220459} 08/31/2021 02:52:21 - INFO - __main__ - Step 75081: {'lr': 0.00025488189448045215, 'samples': 14415552, 'steps': 75080, 'loss/train': 1.2960344552993774} 08/31/2021 02:52:21 - INFO - __main__ - Step 75082: {'lr': 0.00025487658874690243, 'samples': 14415744, 'steps': 75081, 'loss/train': 0.9800154566764832} 08/31/2021 02:52:22 - INFO - __main__ - Step 75083: {'lr': 0.00025487128301115547, 'samples': 14415936, 'steps': 75082, 'loss/train': 1.5335701704025269} 08/31/2021 02:52:23 - INFO - __main__ - Step 75084: {'lr': 0.00025486597727321364, 'samples': 14416128, 'steps': 75083, 'loss/train': 1.4151179790496826} 08/31/2021 02:52:24 - INFO - __main__ - Step 75085: {'lr': 0.0002548606715330792, 'samples': 14416320, 'steps': 75084, 'loss/train': 1.0972087383270264} 08/31/2021 02:52:24 - INFO - __main__ - Step 75086: {'lr': 0.0002548553657907546, 'samples': 14416512, 'steps': 75085, 'loss/train': 1.3432469367980957} 08/31/2021 02:52:24 - INFO - __main__ - Step 75087: {'lr': 0.0002548500600462422, 'samples': 14416704, 'steps': 75086, 'loss/train': 1.6963645219802856} 08/31/2021 02:52:25 - INFO - __main__ - Step 75088: {'lr': 0.00025484475429954454, 'samples': 14416896, 'steps': 75087, 'loss/train': 5.769352436065674} 08/31/2021 02:52:25 - INFO - __main__ - Step 75089: {'lr': 0.0002548394485506638, 'samples': 14417088, 'steps': 75088, 'loss/train': 0.8280194401741028} 08/31/2021 02:52:27 - INFO - __main__ - Step 75090: {'lr': 0.0002548341427996026, 'samples': 14417280, 'steps': 75089, 'loss/train': 1.931693434715271} 08/31/2021 02:52:28 - INFO - __main__ - Step 75091: {'lr': 0.0002548288370463632, 'samples': 14417472, 'steps': 75090, 'loss/train': 1.1405375003814697} 08/31/2021 02:52:28 - INFO - __main__ - Step 75092: {'lr': 0.0002548235312909479, 'samples': 14417664, 'steps': 75091, 'loss/train': 0.04352688789367676} 08/31/2021 02:52:28 - INFO - __main__ - Step 75093: {'lr': 0.00025481822553335927, 'samples': 14417856, 'steps': 75092, 'loss/train': 1.738323450088501} 08/31/2021 02:52:29 - INFO - __main__ - Step 75094: {'lr': 0.0002548129197735996, 'samples': 14418048, 'steps': 75093, 'loss/train': 1.8267548084259033} 08/31/2021 02:52:30 - INFO - __main__ - Step 75095: {'lr': 0.0002548076140116713, 'samples': 14418240, 'steps': 75094, 'loss/train': 1.0858341455459595} 08/31/2021 02:52:31 - INFO - __main__ - Step 75096: {'lr': 0.0002548023082475767, 'samples': 14418432, 'steps': 75095, 'loss/train': 0.5130172967910767} 08/31/2021 02:52:31 - INFO - __main__ - Step 75097: {'lr': 0.00025479700248131845, 'samples': 14418624, 'steps': 75096, 'loss/train': 0.5936155319213867} 08/31/2021 02:52:31 - INFO - __main__ - Step 75098: {'lr': 0.0002547916967128985, 'samples': 14418816, 'steps': 75097, 'loss/train': 0.8339299559593201} 08/31/2021 02:52:32 - INFO - __main__ - Step 75099: {'lr': 0.00025478639094231965, 'samples': 14419008, 'steps': 75098, 'loss/train': 1.3570762872695923} 08/31/2021 02:52:33 - INFO - __main__ - Step 75100: {'lr': 0.0002547810851695841, 'samples': 14419200, 'steps': 75099, 'loss/train': 1.4133836030960083} 08/31/2021 02:52:34 - INFO - __main__ - Step 75101: {'lr': 0.0002547757793946942, 'samples': 14419392, 'steps': 75100, 'loss/train': 1.3948783874511719} 08/31/2021 02:52:34 - INFO - __main__ - Step 75102: {'lr': 0.00025477047361765245, 'samples': 14419584, 'steps': 75101, 'loss/train': 0.865175724029541} 08/31/2021 02:52:34 - INFO - __main__ - Step 75103: {'lr': 0.00025476516783846123, 'samples': 14419776, 'steps': 75102, 'loss/train': 1.4679653644561768} 08/31/2021 02:52:35 - INFO - __main__ - Step 75104: {'lr': 0.00025475986205712286, 'samples': 14419968, 'steps': 75103, 'loss/train': 1.2472755908966064} 08/31/2021 02:52:37 - INFO - __main__ - Step 75105: {'lr': 0.0002547545562736397, 'samples': 14420160, 'steps': 75104, 'loss/train': 1.9089181423187256} 08/31/2021 02:52:37 - INFO - __main__ - Step 75106: {'lr': 0.00025474925048801436, 'samples': 14420352, 'steps': 75105, 'loss/train': 1.5632469654083252} 08/31/2021 02:52:38 - INFO - __main__ - Step 75107: {'lr': 0.000254743944700249, 'samples': 14420544, 'steps': 75106, 'loss/train': 0.8034831881523132} 08/31/2021 02:52:38 - INFO - __main__ - Step 75108: {'lr': 0.0002547386389103461, 'samples': 14420736, 'steps': 75107, 'loss/train': 0.8795294761657715} 08/31/2021 02:52:38 - INFO - __main__ - Step 75109: {'lr': 0.00025473333311830805, 'samples': 14420928, 'steps': 75108, 'loss/train': 1.2324591875076294} 08/31/2021 02:52:39 - INFO - __main__ - Step 75110: {'lr': 0.00025472802732413717, 'samples': 14421120, 'steps': 75109, 'loss/train': 0.7866925597190857} 08/31/2021 02:52:40 - INFO - __main__ - Step 75111: {'lr': 0.00025472272152783605, 'samples': 14421312, 'steps': 75110, 'loss/train': 0.1285575032234192} 08/31/2021 02:52:40 - INFO - __main__ - Step 75112: {'lr': 0.0002547174157294068, 'samples': 14421504, 'steps': 75111, 'loss/train': 0.9422279000282288} 08/31/2021 02:52:41 - INFO - __main__ - Step 75113: {'lr': 0.0002547121099288521, 'samples': 14421696, 'steps': 75112, 'loss/train': 0.5768993496894836} 08/31/2021 02:52:41 - INFO - __main__ - Step 75114: {'lr': 0.000254706804126174, 'samples': 14421888, 'steps': 75113, 'loss/train': 0.5258089303970337} 08/31/2021 02:52:42 - INFO - __main__ - Step 75115: {'lr': 0.00025470149832137524, 'samples': 14422080, 'steps': 75114, 'loss/train': 0.9920636415481567} 08/31/2021 02:52:43 - INFO - __main__ - Step 75116: {'lr': 0.00025469619251445804, 'samples': 14422272, 'steps': 75115, 'loss/train': 0.5981653332710266} 08/31/2021 02:52:44 - INFO - __main__ - Step 75117: {'lr': 0.0002546908867054248, 'samples': 14422464, 'steps': 75116, 'loss/train': 1.2305546998977661} 08/31/2021 02:52:44 - INFO - __main__ - Step 75118: {'lr': 0.0002546855808942779, 'samples': 14422656, 'steps': 75117, 'loss/train': 0.32277750968933105} 08/31/2021 02:52:44 - INFO - __main__ - Step 75119: {'lr': 0.0002546802750810198, 'samples': 14422848, 'steps': 75118, 'loss/train': 0.41392743587493896} 08/31/2021 02:52:45 - INFO - __main__ - Step 75120: {'lr': 0.00025467496926565275, 'samples': 14423040, 'steps': 75119, 'loss/train': 1.385967493057251} 08/31/2021 02:52:45 - INFO - __main__ - Step 75121: {'lr': 0.00025466966344817927, 'samples': 14423232, 'steps': 75120, 'loss/train': 0.874121367931366} 08/31/2021 02:52:46 - INFO - __main__ - Step 75122: {'lr': 0.0002546643576286017, 'samples': 14423424, 'steps': 75121, 'loss/train': 1.2723997831344604} 08/31/2021 02:52:47 - INFO - __main__ - Step 75123: {'lr': 0.0002546590518069225, 'samples': 14423616, 'steps': 75122, 'loss/train': 1.0319112539291382} 08/31/2021 02:52:47 - INFO - __main__ - Step 75124: {'lr': 0.00025465374598314394, 'samples': 14423808, 'steps': 75123, 'loss/train': 0.9062697887420654} 08/31/2021 02:52:48 - INFO - __main__ - Step 75125: {'lr': 0.0002546484401572685, 'samples': 14424000, 'steps': 75124, 'loss/train': 1.2263429164886475} 08/31/2021 02:52:48 - INFO - __main__ - Step 75126: {'lr': 0.00025464313432929853, 'samples': 14424192, 'steps': 75125, 'loss/train': 0.9935835599899292} 08/31/2021 02:52:49 - INFO - __main__ - Step 75127: {'lr': 0.00025463782849923644, 'samples': 14424384, 'steps': 75126, 'loss/train': 0.5223522782325745} 08/31/2021 02:52:50 - INFO - __main__ - Step 75128: {'lr': 0.0002546325226670847, 'samples': 14424576, 'steps': 75127, 'loss/train': 1.092206358909607} 08/31/2021 02:52:50 - INFO - __main__ - Step 75129: {'lr': 0.0002546272168328455, 'samples': 14424768, 'steps': 75128, 'loss/train': 1.179013967514038} 08/31/2021 02:52:51 - INFO - __main__ - Step 75130: {'lr': 0.00025462191099652145, 'samples': 14424960, 'steps': 75129, 'loss/train': 1.290937900543213} 08/31/2021 02:52:51 - INFO - __main__ - Step 75131: {'lr': 0.00025461660515811474, 'samples': 14425152, 'steps': 75130, 'loss/train': 1.6807861328125} 08/31/2021 02:52:53 - INFO - __main__ - Step 75132: {'lr': 0.0002546112993176279, 'samples': 14425344, 'steps': 75131, 'loss/train': 1.203350305557251} 08/31/2021 02:52:53 - INFO - __main__ - Step 75133: {'lr': 0.00025460599347506326, 'samples': 14425536, 'steps': 75132, 'loss/train': 1.2051302194595337} 08/31/2021 02:52:53 - INFO - __main__ - Step 75134: {'lr': 0.00025460068763042326, 'samples': 14425728, 'steps': 75133, 'loss/train': 1.0504631996154785} 08/31/2021 02:52:54 - INFO - __main__ - Step 75135: {'lr': 0.0002545953817837102, 'samples': 14425920, 'steps': 75134, 'loss/train': 1.2058377265930176} 08/31/2021 02:52:54 - INFO - __main__ - Step 75136: {'lr': 0.0002545900759349266, 'samples': 14426112, 'steps': 75135, 'loss/train': 1.3129006624221802} 08/31/2021 02:52:55 - INFO - __main__ - Step 75137: {'lr': 0.00025458477008407477, 'samples': 14426304, 'steps': 75136, 'loss/train': 1.4823559522628784} 08/31/2021 02:52:56 - INFO - __main__ - Step 75138: {'lr': 0.0002545794642311571, 'samples': 14426496, 'steps': 75137, 'loss/train': 1.4096237421035767} 08/31/2021 02:52:56 - INFO - __main__ - Step 75139: {'lr': 0.00025457415837617603, 'samples': 14426688, 'steps': 75138, 'loss/train': 1.3864376544952393} 08/31/2021 02:52:57 - INFO - __main__ - Step 75140: {'lr': 0.00025456885251913384, 'samples': 14426880, 'steps': 75139, 'loss/train': 1.8386027812957764} 08/31/2021 02:52:57 - INFO - __main__ - Step 75141: {'lr': 0.00025456354666003307, 'samples': 14427072, 'steps': 75140, 'loss/train': 1.1156615018844604} 08/31/2021 02:52:59 - INFO - __main__ - Step 75142: {'lr': 0.000254558240798876, 'samples': 14427264, 'steps': 75141, 'loss/train': 1.1285336017608643} 08/31/2021 02:53:00 - INFO - __main__ - Step 75143: {'lr': 0.0002545529349356651, 'samples': 14427456, 'steps': 75142, 'loss/train': 1.7283525466918945} 08/31/2021 02:53:00 - INFO - __main__ - Step 75144: {'lr': 0.0002545476290704027, 'samples': 14427648, 'steps': 75143, 'loss/train': 1.4640893936157227} 08/31/2021 02:53:00 - INFO - __main__ - Step 75145: {'lr': 0.00025454232320309115, 'samples': 14427840, 'steps': 75144, 'loss/train': 0.696985125541687} 08/31/2021 02:53:01 - INFO - __main__ - Step 75146: {'lr': 0.00025453701733373297, 'samples': 14428032, 'steps': 75145, 'loss/train': 1.0171517133712769} 08/31/2021 02:53:02 - INFO - __main__ - Step 75147: {'lr': 0.0002545317114623304, 'samples': 14428224, 'steps': 75146, 'loss/train': 0.9775373339653015} 08/31/2021 02:53:03 - INFO - __main__ - Step 75148: {'lr': 0.00025452640558888597, 'samples': 14428416, 'steps': 75147, 'loss/train': 0.8304611444473267} 08/31/2021 02:53:03 - INFO - __main__ - Step 75149: {'lr': 0.000254521099713402, 'samples': 14428608, 'steps': 75148, 'loss/train': 1.45724618434906} 08/31/2021 02:53:04 - INFO - __main__ - Step 75150: {'lr': 0.00025451579383588084, 'samples': 14428800, 'steps': 75149, 'loss/train': 1.0411783456802368} 08/31/2021 02:53:04 - INFO - __main__ - Step 75151: {'lr': 0.0002545104879563251, 'samples': 14428992, 'steps': 75150, 'loss/train': 1.5882368087768555} 08/31/2021 02:53:05 - INFO - __main__ - Step 75152: {'lr': 0.00025450518207473683, 'samples': 14429184, 'steps': 75151, 'loss/train': 1.0853835344314575} 08/31/2021 02:53:06 - INFO - __main__ - Step 75153: {'lr': 0.0002544998761911186, 'samples': 14429376, 'steps': 75152, 'loss/train': 1.0433019399642944} 08/31/2021 02:53:06 - INFO - __main__ - Step 75154: {'lr': 0.0002544945703054729, 'samples': 14429568, 'steps': 75153, 'loss/train': 1.6634981632232666} 08/31/2021 02:53:07 - INFO - __main__ - Step 75155: {'lr': 0.00025448926441780194, 'samples': 14429760, 'steps': 75154, 'loss/train': 1.2015812397003174} 08/31/2021 02:53:07 - INFO - __main__ - Step 75156: {'lr': 0.00025448395852810824, 'samples': 14429952, 'steps': 75155, 'loss/train': 1.9484307765960693} 08/31/2021 02:53:07 - INFO - __main__ - Step 75157: {'lr': 0.0002544786526363941, 'samples': 14430144, 'steps': 75156, 'loss/train': 1.3063305616378784} 08/31/2021 02:53:09 - INFO - __main__ - Step 75158: {'lr': 0.000254473346742662, 'samples': 14430336, 'steps': 75157, 'loss/train': 1.2344030141830444} 08/31/2021 02:53:09 - INFO - __main__ - Step 75159: {'lr': 0.0002544680408469142, 'samples': 14430528, 'steps': 75158, 'loss/train': 0.052809394896030426} 08/31/2021 02:53:10 - INFO - __main__ - Step 75160: {'lr': 0.00025446273494915324, 'samples': 14430720, 'steps': 75159, 'loss/train': 1.1766043901443481} 08/31/2021 02:53:10 - INFO - __main__ - Step 75161: {'lr': 0.00025445742904938134, 'samples': 14430912, 'steps': 75160, 'loss/train': 0.8654624223709106} 08/31/2021 02:53:10 - INFO - __main__ - Step 75162: {'lr': 0.00025445212314760107, 'samples': 14431104, 'steps': 75161, 'loss/train': 0.05177266523241997} 08/31/2021 02:53:12 - INFO - __main__ - Step 75163: {'lr': 0.00025444681724381475, 'samples': 14431296, 'steps': 75162, 'loss/train': 1.0014371871948242} 08/31/2021 02:53:12 - INFO - __main__ - Step 75164: {'lr': 0.0002544415113380247, 'samples': 14431488, 'steps': 75163, 'loss/train': 1.0585867166519165} 08/31/2021 02:53:13 - INFO - __main__ - Step 75165: {'lr': 0.0002544362054302335, 'samples': 14431680, 'steps': 75164, 'loss/train': 1.4837287664413452} 08/31/2021 02:53:13 - INFO - __main__ - Step 75166: {'lr': 0.0002544308995204433, 'samples': 14431872, 'steps': 75165, 'loss/train': 1.123409628868103} 08/31/2021 02:53:13 - INFO - __main__ - Step 75167: {'lr': 0.00025442559360865666, 'samples': 14432064, 'steps': 75166, 'loss/train': 1.2415249347686768} 08/31/2021 02:53:15 - INFO - __main__ - Step 75168: {'lr': 0.00025442028769487584, 'samples': 14432256, 'steps': 75167, 'loss/train': 1.1578625440597534} 08/31/2021 02:53:15 - INFO - __main__ - Step 75169: {'lr': 0.0002544149817791034, 'samples': 14432448, 'steps': 75168, 'loss/train': 1.2624564170837402} 08/31/2021 02:53:16 - INFO - __main__ - Step 75170: {'lr': 0.00025440967586134154, 'samples': 14432640, 'steps': 75169, 'loss/train': 1.231152057647705} 08/31/2021 02:53:16 - INFO - __main__ - Step 75171: {'lr': 0.00025440436994159283, 'samples': 14432832, 'steps': 75170, 'loss/train': 1.2237498760223389} 08/31/2021 02:53:16 - INFO - __main__ - Step 75172: {'lr': 0.00025439906401985955, 'samples': 14433024, 'steps': 75171, 'loss/train': 1.566405177116394} 08/31/2021 02:53:18 - INFO - __main__ - Step 75173: {'lr': 0.00025439375809614413, 'samples': 14433216, 'steps': 75172, 'loss/train': 2.31282377243042} 08/31/2021 02:53:18 - INFO - __main__ - Step 75174: {'lr': 0.0002543884521704489, 'samples': 14433408, 'steps': 75173, 'loss/train': 1.1121058464050293} 08/31/2021 02:53:19 - INFO - __main__ - Step 75175: {'lr': 0.00025438314624277636, 'samples': 14433600, 'steps': 75174, 'loss/train': 1.223976492881775} 08/31/2021 02:53:19 - INFO - __main__ - Step 75176: {'lr': 0.00025437784031312883, 'samples': 14433792, 'steps': 75175, 'loss/train': 1.2149420976638794} 08/31/2021 02:53:19 - INFO - __main__ - Step 75177: {'lr': 0.0002543725343815087, 'samples': 14433984, 'steps': 75176, 'loss/train': 1.354541540145874} 08/31/2021 02:53:21 - INFO - __main__ - Step 75178: {'lr': 0.00025436722844791843, 'samples': 14434176, 'steps': 75177, 'loss/train': 1.1277368068695068} 08/31/2021 02:53:21 - INFO - __main__ - Step 75179: {'lr': 0.00025436192251236027, 'samples': 14434368, 'steps': 75178, 'loss/train': 1.2618122100830078} 08/31/2021 02:53:22 - INFO - __main__ - Step 75180: {'lr': 0.0002543566165748367, 'samples': 14434560, 'steps': 75179, 'loss/train': 1.3809990882873535} 08/31/2021 02:53:22 - INFO - __main__ - Step 75181: {'lr': 0.00025435131063535017, 'samples': 14434752, 'steps': 75180, 'loss/train': 1.1504031419754028} 08/31/2021 02:53:22 - INFO - __main__ - Step 75182: {'lr': 0.00025434600469390295, 'samples': 14434944, 'steps': 75181, 'loss/train': 1.2371699810028076} 08/31/2021 02:53:24 - INFO - __main__ - Step 75183: {'lr': 0.00025434069875049755, 'samples': 14435136, 'steps': 75182, 'loss/train': 1.0888235569000244} 08/31/2021 02:53:24 - INFO - __main__ - Step 75184: {'lr': 0.00025433539280513625, 'samples': 14435328, 'steps': 75183, 'loss/train': 2.0645711421966553} 08/31/2021 02:53:25 - INFO - __main__ - Step 75185: {'lr': 0.0002543300868578215, 'samples': 14435520, 'steps': 75184, 'loss/train': 1.5037646293640137} 08/31/2021 02:53:25 - INFO - __main__ - Step 75186: {'lr': 0.0002543247809085557, 'samples': 14435712, 'steps': 75185, 'loss/train': 1.3969711065292358} 08/31/2021 02:53:26 - INFO - __main__ - Step 75187: {'lr': 0.00025431947495734117, 'samples': 14435904, 'steps': 75186, 'loss/train': 1.447620153427124} 08/31/2021 02:53:26 - INFO - __main__ - Step 75188: {'lr': 0.00025431416900418034, 'samples': 14436096, 'steps': 75187, 'loss/train': 0.9013260006904602} 08/31/2021 02:53:27 - INFO - __main__ - Step 75189: {'lr': 0.0002543088630490757, 'samples': 14436288, 'steps': 75188, 'loss/train': 1.3251813650131226} 08/31/2021 02:53:28 - INFO - __main__ - Step 75190: {'lr': 0.00025430355709202946, 'samples': 14436480, 'steps': 75189, 'loss/train': 1.418080449104309} 08/31/2021 02:53:28 - INFO - __main__ - Step 75191: {'lr': 0.00025429825113304423, 'samples': 14436672, 'steps': 75190, 'loss/train': 0.20107504725456238} 08/31/2021 02:53:29 - INFO - __main__ - Step 75192: {'lr': 0.00025429294517212214, 'samples': 14436864, 'steps': 75191, 'loss/train': 0.9083806872367859} 08/31/2021 02:53:29 - INFO - __main__ - Step 75193: {'lr': 0.00025428763920926577, 'samples': 14437056, 'steps': 75192, 'loss/train': 1.4765511751174927} 08/31/2021 02:53:31 - INFO - __main__ - Step 75194: {'lr': 0.00025428233324447747, 'samples': 14437248, 'steps': 75193, 'loss/train': 1.2180497646331787} 08/31/2021 02:53:31 - INFO - __main__ - Step 75195: {'lr': 0.0002542770272777596, 'samples': 14437440, 'steps': 75194, 'loss/train': 0.7217928171157837} 08/31/2021 02:53:31 - INFO - __main__ - Step 75196: {'lr': 0.0002542717213091145, 'samples': 14437632, 'steps': 75195, 'loss/train': 1.608072280883789} 08/31/2021 02:53:32 - INFO - __main__ - Step 75197: {'lr': 0.0002542664153385447, 'samples': 14437824, 'steps': 75196, 'loss/train': 0.9882802963256836} 08/31/2021 02:53:32 - INFO - __main__ - Step 75198: {'lr': 0.00025426110936605255, 'samples': 14438016, 'steps': 75197, 'loss/train': 1.7708946466445923} 08/31/2021 02:53:34 - INFO - __main__ - Step 75199: {'lr': 0.0002542558033916404, 'samples': 14438208, 'steps': 75198, 'loss/train': 1.4489152431488037} 08/31/2021 02:53:34 - INFO - __main__ - Step 75200: {'lr': 0.0002542504974153106, 'samples': 14438400, 'steps': 75199, 'loss/train': 1.4125721454620361} 08/31/2021 02:53:35 - INFO - __main__ - Step 75201: {'lr': 0.0002542451914370656, 'samples': 14438592, 'steps': 75200, 'loss/train': 0.8788732290267944} 08/31/2021 02:53:35 - INFO - __main__ - Step 75202: {'lr': 0.0002542398854569078, 'samples': 14438784, 'steps': 75201, 'loss/train': 1.6559253931045532} 08/31/2021 02:53:36 - INFO - __main__ - Step 75203: {'lr': 0.0002542345794748396, 'samples': 14438976, 'steps': 75202, 'loss/train': 0.7613362669944763} 08/31/2021 02:53:37 - INFO - __main__ - Step 75204: {'lr': 0.0002542292734908633, 'samples': 14439168, 'steps': 75203, 'loss/train': 1.8057911396026611} 08/31/2021 02:53:38 - INFO - __main__ - Step 75205: {'lr': 0.00025422396750498144, 'samples': 14439360, 'steps': 75204, 'loss/train': 1.2924551963806152} 08/31/2021 02:53:38 - INFO - __main__ - Step 75206: {'lr': 0.00025421866151719623, 'samples': 14439552, 'steps': 75205, 'loss/train': 1.2284411191940308} 08/31/2021 02:53:38 - INFO - __main__ - Step 75207: {'lr': 0.00025421335552751025, 'samples': 14439744, 'steps': 75206, 'loss/train': 1.5770151615142822} 08/31/2021 02:53:39 - INFO - __main__ - Step 75208: {'lr': 0.00025420804953592567, 'samples': 14439936, 'steps': 75207, 'loss/train': 2.1319782733917236} 08/31/2021 02:53:41 - INFO - __main__ - Step 75209: {'lr': 0.0002542027435424451, 'samples': 14440128, 'steps': 75208, 'loss/train': 0.3925148546695709} 08/31/2021 02:53:41 - INFO - __main__ - Step 75210: {'lr': 0.00025419743754707085, 'samples': 14440320, 'steps': 75209, 'loss/train': 0.7203658223152161} 08/31/2021 02:53:42 - INFO - __main__ - Step 75211: {'lr': 0.00025419213154980526, 'samples': 14440512, 'steps': 75210, 'loss/train': 1.0319517850875854} 08/31/2021 02:53:42 - INFO - __main__ - Step 75212: {'lr': 0.00025418682555065084, 'samples': 14440704, 'steps': 75211, 'loss/train': 1.4934104681015015} 08/31/2021 02:53:42 - INFO - __main__ - Step 75213: {'lr': 0.00025418151954960985, 'samples': 14440896, 'steps': 75212, 'loss/train': 1.2269572019577026} 08/31/2021 02:53:43 - INFO - __main__ - Step 75214: {'lr': 0.0002541762135466847, 'samples': 14441088, 'steps': 75213, 'loss/train': 1.0506742000579834} 08/31/2021 02:53:43 - INFO - __main__ - Step 75215: {'lr': 0.00025417090754187776, 'samples': 14441280, 'steps': 75214, 'loss/train': 0.09472623467445374} 08/31/2021 02:53:45 - INFO - __main__ - Step 75216: {'lr': 0.0002541656015351916, 'samples': 14441472, 'steps': 75215, 'loss/train': 0.07588637620210648} 08/31/2021 02:53:45 - INFO - __main__ - Step 75217: {'lr': 0.0002541602955266284, 'samples': 14441664, 'steps': 75216, 'loss/train': 0.5368208885192871} 08/31/2021 02:53:46 - INFO - __main__ - Step 75218: {'lr': 0.0002541549895161907, 'samples': 14441856, 'steps': 75217, 'loss/train': 1.2436412572860718} 08/31/2021 02:53:46 - INFO - __main__ - Step 75219: {'lr': 0.0002541496835038808, 'samples': 14442048, 'steps': 75218, 'loss/train': 0.06100202351808548} 08/31/2021 02:53:46 - INFO - __main__ - Step 75220: {'lr': 0.00025414437748970105, 'samples': 14442240, 'steps': 75219, 'loss/train': 1.7784334421157837} 08/31/2021 02:53:48 - INFO - __main__ - Step 75221: {'lr': 0.00025413907147365394, 'samples': 14442432, 'steps': 75220, 'loss/train': 2.0230188369750977} 08/31/2021 02:53:49 - INFO - __main__ - Step 75222: {'lr': 0.00025413376545574184, 'samples': 14442624, 'steps': 75221, 'loss/train': 0.08194079995155334} 08/31/2021 02:53:49 - INFO - __main__ - Step 75223: {'lr': 0.0002541284594359672, 'samples': 14442816, 'steps': 75222, 'loss/train': 1.4181935787200928} 08/31/2021 02:53:49 - INFO - __main__ - Step 75224: {'lr': 0.0002541231534143322, 'samples': 14443008, 'steps': 75223, 'loss/train': 0.9946227669715881} 08/31/2021 02:53:50 - INFO - __main__ - Step 75225: {'lr': 0.00025411784739083957, 'samples': 14443200, 'steps': 75224, 'loss/train': 1.519130825996399} 08/31/2021 02:53:51 - INFO - __main__ - Step 75226: {'lr': 0.00025411254136549136, 'samples': 14443392, 'steps': 75225, 'loss/train': 2.009187698364258} 08/31/2021 02:53:52 - INFO - __main__ - Step 75227: {'lr': 0.0002541072353382901, 'samples': 14443584, 'steps': 75226, 'loss/train': 0.6702519059181213} 08/31/2021 02:53:52 - INFO - __main__ - Step 75228: {'lr': 0.0002541019293092382, 'samples': 14443776, 'steps': 75227, 'loss/train': 1.677671194076538} 08/31/2021 02:53:53 - INFO - __main__ - Step 75229: {'lr': 0.00025409662327833805, 'samples': 14443968, 'steps': 75228, 'loss/train': 0.19417548179626465} 08/31/2021 02:53:53 - INFO - __main__ - Step 75230: {'lr': 0.00025409131724559196, 'samples': 14444160, 'steps': 75229, 'loss/train': 0.5882528424263} 08/31/2021 02:53:54 - INFO - __main__ - Step 75231: {'lr': 0.00025408601121100244, 'samples': 14444352, 'steps': 75230, 'loss/train': 1.4453530311584473} 08/31/2021 02:53:55 - INFO - __main__ - Step 75232: {'lr': 0.0002540807051745719, 'samples': 14444544, 'steps': 75231, 'loss/train': 1.1535265445709229} 08/31/2021 02:53:55 - INFO - __main__ - Step 75233: {'lr': 0.00025407539913630255, 'samples': 14444736, 'steps': 75232, 'loss/train': 0.15540537238121033} 08/31/2021 02:53:56 - INFO - __main__ - Step 75234: {'lr': 0.00025407009309619694, 'samples': 14444928, 'steps': 75233, 'loss/train': 1.365565299987793} 08/31/2021 02:53:56 - INFO - __main__ - Step 75235: {'lr': 0.0002540647870542574, 'samples': 14445120, 'steps': 75234, 'loss/train': 0.9124082326889038} 08/31/2021 02:53:56 - INFO - __main__ - Step 75236: {'lr': 0.0002540594810104863, 'samples': 14445312, 'steps': 75235, 'loss/train': 1.2839083671569824} 08/31/2021 02:53:58 - INFO - __main__ - Step 75237: {'lr': 0.0002540541749648861, 'samples': 14445504, 'steps': 75236, 'loss/train': 1.494030237197876} 08/31/2021 02:53:59 - INFO - __main__ - Step 75238: {'lr': 0.0002540488689174591, 'samples': 14445696, 'steps': 75237, 'loss/train': 1.3494067192077637} 08/31/2021 02:53:59 - INFO - __main__ - Step 75239: {'lr': 0.0002540435628682078, 'samples': 14445888, 'steps': 75238, 'loss/train': 1.7412989139556885} 08/31/2021 02:53:59 - INFO - __main__ - Step 75240: {'lr': 0.0002540382568171345, 'samples': 14446080, 'steps': 75239, 'loss/train': 1.4309108257293701} 08/31/2021 02:54:00 - INFO - __main__ - Step 75241: {'lr': 0.00025403295076424165, 'samples': 14446272, 'steps': 75240, 'loss/train': 1.6779028177261353} 08/31/2021 02:54:01 - INFO - __main__ - Step 75242: {'lr': 0.0002540276447095316, 'samples': 14446464, 'steps': 75241, 'loss/train': 0.3429912030696869} 08/31/2021 02:54:02 - INFO - __main__ - Step 75243: {'lr': 0.00025402233865300675, 'samples': 14446656, 'steps': 75242, 'loss/train': 0.5613527297973633} 08/31/2021 02:54:02 - INFO - __main__ - Step 75244: {'lr': 0.00025401703259466947, 'samples': 14446848, 'steps': 75243, 'loss/train': 1.655098795890808} 08/31/2021 02:54:02 - INFO - __main__ - Step 75245: {'lr': 0.0002540117265345223, 'samples': 14447040, 'steps': 75244, 'loss/train': 1.158214807510376} 08/31/2021 02:54:03 - INFO - __main__ - Step 75246: {'lr': 0.00025400642047256733, 'samples': 14447232, 'steps': 75245, 'loss/train': 1.7399770021438599} 08/31/2021 02:54:04 - INFO - __main__ - Step 75247: {'lr': 0.00025400111440880725, 'samples': 14447424, 'steps': 75246, 'loss/train': 0.9032354354858398} 08/31/2021 02:54:05 - INFO - __main__ - Step 75248: {'lr': 0.00025399580834324425, 'samples': 14447616, 'steps': 75247, 'loss/train': 1.0440022945404053} 08/31/2021 02:54:05 - INFO - __main__ - Step 75249: {'lr': 0.0002539905022758808, 'samples': 14447808, 'steps': 75248, 'loss/train': 1.7345727682113647} 08/31/2021 02:54:05 - INFO - __main__ - Step 75250: {'lr': 0.0002539851962067194, 'samples': 14448000, 'steps': 75249, 'loss/train': 0.7311576008796692} 08/31/2021 02:54:06 - INFO - __main__ - Step 75251: {'lr': 0.00025397989013576223, 'samples': 14448192, 'steps': 75250, 'loss/train': 1.1423200368881226} 08/31/2021 02:54:08 - INFO - __main__ - Step 75252: {'lr': 0.0002539745840630119, 'samples': 14448384, 'steps': 75251, 'loss/train': 0.49220865964889526} 08/31/2021 02:54:09 - INFO - __main__ - Step 75253: {'lr': 0.00025396927798847056, 'samples': 14448576, 'steps': 75252, 'loss/train': 1.4505157470703125} 08/31/2021 02:54:09 - INFO - __main__ - Step 75254: {'lr': 0.0002539639719121408, 'samples': 14448768, 'steps': 75253, 'loss/train': 1.5494719743728638} 08/31/2021 02:54:09 - INFO - __main__ - Step 75255: {'lr': 0.00025395866583402483, 'samples': 14448960, 'steps': 75254, 'loss/train': 2.294767141342163} 08/31/2021 02:54:10 - INFO - __main__ - Step 75256: {'lr': 0.00025395335975412527, 'samples': 14449152, 'steps': 75255, 'loss/train': 0.5356206893920898} 08/31/2021 02:54:10 - INFO - __main__ - Step 75257: {'lr': 0.00025394805367244435, 'samples': 14449344, 'steps': 75256, 'loss/train': 1.3001457452774048} 08/31/2021 02:54:12 - INFO - __main__ - Step 75258: {'lr': 0.0002539427475889845, 'samples': 14449536, 'steps': 75257, 'loss/train': 1.427817702293396} 08/31/2021 02:54:12 - INFO - __main__ - Step 75259: {'lr': 0.00025393744150374804, 'samples': 14449728, 'steps': 75258, 'loss/train': 1.4268401861190796} 08/31/2021 02:54:13 - INFO - __main__ - Step 75260: {'lr': 0.0002539321354167375, 'samples': 14449920, 'steps': 75259, 'loss/train': 0.10698438435792923} 08/31/2021 02:54:13 - INFO - __main__ - Step 75261: {'lr': 0.0002539268293279552, 'samples': 14450112, 'steps': 75260, 'loss/train': 1.40985906124115} 08/31/2021 02:54:13 - INFO - __main__ - Step 75262: {'lr': 0.00025392152323740354, 'samples': 14450304, 'steps': 75261, 'loss/train': 0.47916683554649353} 08/31/2021 02:54:14 - INFO - __main__ - Step 75263: {'lr': 0.0002539162171450848, 'samples': 14450496, 'steps': 75262, 'loss/train': 1.1719202995300293} 08/31/2021 02:54:15 - INFO - __main__ - Step 75264: {'lr': 0.0002539109110510016, 'samples': 14450688, 'steps': 75263, 'loss/train': 1.326780080795288} 08/31/2021 02:54:16 - INFO - __main__ - Step 75265: {'lr': 0.00025390560495515614, 'samples': 14450880, 'steps': 75264, 'loss/train': 0.3467259109020233} 08/31/2021 02:54:16 - INFO - __main__ - Step 75266: {'lr': 0.0002539002988575509, 'samples': 14451072, 'steps': 75265, 'loss/train': 0.04769762605428696} 08/31/2021 02:54:16 - INFO - __main__ - Step 75267: {'lr': 0.0002538949927581882, 'samples': 14451264, 'steps': 75266, 'loss/train': 1.126755714416504} 08/31/2021 02:54:17 - INFO - __main__ - Step 75268: {'lr': 0.0002538896866570706, 'samples': 14451456, 'steps': 75267, 'loss/train': 1.462185025215149} 08/31/2021 02:54:18 - INFO - __main__ - Step 75269: {'lr': 0.0002538843805542002, 'samples': 14451648, 'steps': 75268, 'loss/train': 1.1213605403900146} 08/31/2021 02:54:19 - INFO - __main__ - Step 75270: {'lr': 0.0002538790744495796, 'samples': 14451840, 'steps': 75269, 'loss/train': 1.21845281124115} 08/31/2021 02:54:19 - INFO - __main__ - Step 75271: {'lr': 0.00025387376834321127, 'samples': 14452032, 'steps': 75270, 'loss/train': 0.4745613932609558} 08/31/2021 02:54:19 - INFO - __main__ - Step 75272: {'lr': 0.00025386846223509734, 'samples': 14452224, 'steps': 75271, 'loss/train': 0.40925678610801697} 08/31/2021 02:54:20 - INFO - __main__ - Step 75273: {'lr': 0.00025386315612524045, 'samples': 14452416, 'steps': 75272, 'loss/train': 0.9813075065612793} 08/31/2021 02:54:22 - INFO - __main__ - Step 75274: {'lr': 0.0002538578500136428, 'samples': 14452608, 'steps': 75273, 'loss/train': 1.326324224472046} 08/31/2021 02:54:22 - INFO - __main__ - Step 75275: {'lr': 0.0002538525439003069, 'samples': 14452800, 'steps': 75274, 'loss/train': 1.5428589582443237} 08/31/2021 02:54:22 - INFO - __main__ - Step 75276: {'lr': 0.0002538472377852351, 'samples': 14452992, 'steps': 75275, 'loss/train': 1.4166162014007568} 08/31/2021 02:54:23 - INFO - __main__ - Step 75277: {'lr': 0.0002538419316684298, 'samples': 14453184, 'steps': 75276, 'loss/train': 0.0979713723063469} 08/31/2021 02:54:23 - INFO - __main__ - Step 75278: {'lr': 0.00025383662554989337, 'samples': 14453376, 'steps': 75277, 'loss/train': 1.3196909427642822} 08/31/2021 02:54:25 - INFO - __main__ - Step 75279: {'lr': 0.00025383131942962825, 'samples': 14453568, 'steps': 75278, 'loss/train': 1.2201898097991943} 08/31/2021 02:54:25 - INFO - __main__ - Step 75280: {'lr': 0.0002538260133076367, 'samples': 14453760, 'steps': 75279, 'loss/train': 1.6147788763046265} 08/31/2021 02:54:25 - INFO - __main__ - Step 75281: {'lr': 0.0002538207071839213, 'samples': 14453952, 'steps': 75280, 'loss/train': 0.2513779401779175} 08/31/2021 02:54:26 - INFO - __main__ - Step 75282: {'lr': 0.0002538154010584843, 'samples': 14454144, 'steps': 75281, 'loss/train': 1.1900382041931152} 08/31/2021 02:54:26 - INFO - __main__ - Step 75283: {'lr': 0.00025381009493132814, 'samples': 14454336, 'steps': 75282, 'loss/train': 0.5335661768913269} 08/31/2021 02:54:28 - INFO - __main__ - Step 75284: {'lr': 0.0002538047888024552, 'samples': 14454528, 'steps': 75283, 'loss/train': 1.8300609588623047} 08/31/2021 02:54:28 - INFO - __main__ - Step 75285: {'lr': 0.00025379948267186794, 'samples': 14454720, 'steps': 75284, 'loss/train': 1.1083372831344604} 08/31/2021 02:54:28 - INFO - __main__ - Step 75286: {'lr': 0.0002537941765395687, 'samples': 14454912, 'steps': 75285, 'loss/train': 1.1044589281082153} 08/31/2021 02:54:29 - INFO - __main__ - Step 75287: {'lr': 0.0002537888704055598, 'samples': 14455104, 'steps': 75286, 'loss/train': 1.3145346641540527} 08/31/2021 02:54:29 - INFO - __main__ - Step 75288: {'lr': 0.00025378356426984373, 'samples': 14455296, 'steps': 75287, 'loss/train': 1.5901323556900024} 08/31/2021 02:54:31 - INFO - __main__ - Step 75289: {'lr': 0.0002537782581324228, 'samples': 14455488, 'steps': 75288, 'loss/train': 1.0248284339904785} 08/31/2021 02:54:31 - INFO - __main__ - Step 75290: {'lr': 0.0002537729519932995, 'samples': 14455680, 'steps': 75289, 'loss/train': 1.0050554275512695} 08/31/2021 02:54:31 - INFO - __main__ - Step 75291: {'lr': 0.00025376764585247606, 'samples': 14455872, 'steps': 75290, 'loss/train': 1.5077028274536133} 08/31/2021 02:54:32 - INFO - __main__ - Step 75292: {'lr': 0.00025376233970995514, 'samples': 14456064, 'steps': 75291, 'loss/train': 1.2774631977081299} 08/31/2021 02:54:32 - INFO - __main__ - Step 75293: {'lr': 0.00025375703356573886, 'samples': 14456256, 'steps': 75292, 'loss/train': 1.060726284980774} 08/31/2021 02:54:32 - INFO - __main__ - Step 75294: {'lr': 0.00025375172741982975, 'samples': 14456448, 'steps': 75293, 'loss/train': 1.2151408195495605} 08/31/2021 02:54:34 - INFO - __main__ - Step 75295: {'lr': 0.0002537464212722302, 'samples': 14456640, 'steps': 75294, 'loss/train': 1.3865807056427002} 08/31/2021 02:54:34 - INFO - __main__ - Step 75296: {'lr': 0.0002537411151229425, 'samples': 14456832, 'steps': 75295, 'loss/train': 1.1089028120040894} 08/31/2021 02:54:35 - INFO - __main__ - Step 75297: {'lr': 0.0002537358089719691, 'samples': 14457024, 'steps': 75296, 'loss/train': 1.0700287818908691} 08/31/2021 02:54:35 - INFO - __main__ - Step 75298: {'lr': 0.00025373050281931247, 'samples': 14457216, 'steps': 75297, 'loss/train': 1.221130609512329} 08/31/2021 02:54:35 - INFO - __main__ - Step 75299: {'lr': 0.00025372519666497494, 'samples': 14457408, 'steps': 75298, 'loss/train': 1.1593760251998901} 08/31/2021 02:54:37 - INFO - __main__ - Step 75300: {'lr': 0.0002537198905089589, 'samples': 14457600, 'steps': 75299, 'loss/train': 0.5037676095962524} 08/31/2021 02:54:37 - INFO - __main__ - Step 75301: {'lr': 0.00025371458435126664, 'samples': 14457792, 'steps': 75300, 'loss/train': 0.5399014949798584} 08/31/2021 02:54:38 - INFO - __main__ - Step 75302: {'lr': 0.0002537092781919007, 'samples': 14457984, 'steps': 75301, 'loss/train': 1.1197816133499146} 08/31/2021 02:54:38 - INFO - __main__ - Step 75303: {'lr': 0.00025370397203086344, 'samples': 14458176, 'steps': 75302, 'loss/train': 1.8617522716522217} 08/31/2021 02:54:38 - INFO - __main__ - Step 75304: {'lr': 0.0002536986658681572, 'samples': 14458368, 'steps': 75303, 'loss/train': 0.9948375821113586} 08/31/2021 02:54:40 - INFO - __main__ - Step 75305: {'lr': 0.0002536933597037844, 'samples': 14458560, 'steps': 75304, 'loss/train': 1.571800708770752} 08/31/2021 02:54:40 - INFO - __main__ - Step 75306: {'lr': 0.0002536880535377475, 'samples': 14458752, 'steps': 75305, 'loss/train': 1.444849967956543} 08/31/2021 02:54:41 - INFO - __main__ - Step 75307: {'lr': 0.0002536827473700487, 'samples': 14458944, 'steps': 75306, 'loss/train': 1.7032846212387085} 08/31/2021 02:54:41 - INFO - __main__ - Step 75308: {'lr': 0.00025367744120069057, 'samples': 14459136, 'steps': 75307, 'loss/train': 1.844343900680542} 08/31/2021 02:54:41 - INFO - __main__ - Step 75309: {'lr': 0.00025367213502967546, 'samples': 14459328, 'steps': 75308, 'loss/train': 0.6692790389060974} 08/31/2021 02:54:44 - INFO - __main__ - Step 75310: {'lr': 0.0002536668288570057, 'samples': 14459520, 'steps': 75309, 'loss/train': 1.0168708562850952} 08/31/2021 02:54:44 - INFO - __main__ - Step 75311: {'lr': 0.0002536615226826837, 'samples': 14459712, 'steps': 75310, 'loss/train': 1.834870457649231} 08/31/2021 02:54:44 - INFO - __main__ - Step 75312: {'lr': 0.000253656216506712, 'samples': 14459904, 'steps': 75311, 'loss/train': 1.0316715240478516} 08/31/2021 02:54:45 - INFO - __main__ - Step 75313: {'lr': 0.00025365091032909277, 'samples': 14460096, 'steps': 75312, 'loss/train': 1.9026029109954834} 08/31/2021 02:54:45 - INFO - __main__ - Step 75314: {'lr': 0.0002536456041498285, 'samples': 14460288, 'steps': 75313, 'loss/train': 3.5419037342071533} 08/31/2021 02:54:47 - INFO - __main__ - Step 75315: {'lr': 0.0002536402979689216, 'samples': 14460480, 'steps': 75314, 'loss/train': 1.592149019241333} 08/31/2021 02:54:47 - INFO - __main__ - Step 75316: {'lr': 0.0002536349917863744, 'samples': 14460672, 'steps': 75315, 'loss/train': 1.3174138069152832} 08/31/2021 02:54:47 - INFO - __main__ - Step 75317: {'lr': 0.00025362968560218934, 'samples': 14460864, 'steps': 75316, 'loss/train': 1.497838020324707} 08/31/2021 02:54:48 - INFO - __main__ - Step 75318: {'lr': 0.00025362437941636886, 'samples': 14461056, 'steps': 75317, 'loss/train': 1.0438263416290283} 08/31/2021 02:54:48 - INFO - __main__ - Step 75319: {'lr': 0.00025361907322891524, 'samples': 14461248, 'steps': 75318, 'loss/train': 1.5286650657653809} 08/31/2021 02:54:50 - INFO - __main__ - Step 75320: {'lr': 0.000253613767039831, 'samples': 14461440, 'steps': 75319, 'loss/train': 0.671324610710144} 08/31/2021 02:54:50 - INFO - __main__ - Step 75321: {'lr': 0.0002536084608491183, 'samples': 14461632, 'steps': 75320, 'loss/train': 1.2295244932174683} 08/31/2021 02:54:50 - INFO - __main__ - Step 75322: {'lr': 0.00025360315465677976, 'samples': 14461824, 'steps': 75321, 'loss/train': 1.7429317235946655} 08/31/2021 02:54:51 - INFO - __main__ - Step 75323: {'lr': 0.0002535978484628177, 'samples': 14462016, 'steps': 75322, 'loss/train': 0.9460595846176147} 08/31/2021 02:54:51 - INFO - __main__ - Step 75324: {'lr': 0.0002535925422672345, 'samples': 14462208, 'steps': 75323, 'loss/train': 1.6195790767669678} 08/31/2021 02:54:51 - INFO - __main__ - Step 75325: {'lr': 0.00025358723607003255, 'samples': 14462400, 'steps': 75324, 'loss/train': 1.9777754545211792} 08/31/2021 02:54:53 - INFO - __main__ - Step 75326: {'lr': 0.0002535819298712143, 'samples': 14462592, 'steps': 75325, 'loss/train': 0.9445948600769043} 08/31/2021 02:54:53 - INFO - __main__ - Step 75327: {'lr': 0.00025357662367078205, 'samples': 14462784, 'steps': 75326, 'loss/train': 1.4777534008026123} 08/31/2021 02:54:54 - INFO - __main__ - Step 75328: {'lr': 0.00025357131746873816, 'samples': 14462976, 'steps': 75327, 'loss/train': 1.537955641746521} 08/31/2021 02:54:54 - INFO - __main__ - Step 75329: {'lr': 0.00025356601126508516, 'samples': 14463168, 'steps': 75328, 'loss/train': 0.9305527806282043} 08/31/2021 02:54:54 - INFO - __main__ - Step 75330: {'lr': 0.00025356070505982536, 'samples': 14463360, 'steps': 75329, 'loss/train': 1.4285731315612793} 08/31/2021 02:54:56 - INFO - __main__ - Step 75331: {'lr': 0.00025355539885296116, 'samples': 14463552, 'steps': 75330, 'loss/train': 1.3932284116744995} 08/31/2021 02:54:56 - INFO - __main__ - Step 75332: {'lr': 0.0002535500926444949, 'samples': 14463744, 'steps': 75331, 'loss/train': 1.140783667564392} 08/31/2021 02:54:57 - INFO - __main__ - Step 75333: {'lr': 0.0002535447864344291, 'samples': 14463936, 'steps': 75332, 'loss/train': 1.5857325792312622} 08/31/2021 02:54:57 - INFO - __main__ - Step 75334: {'lr': 0.00025353948022276607, 'samples': 14464128, 'steps': 75333, 'loss/train': 1.2761627435684204} 08/31/2021 02:54:57 - INFO - __main__ - Step 75335: {'lr': 0.0002535341740095082, 'samples': 14464320, 'steps': 75334, 'loss/train': 1.8666255474090576} 08/31/2021 02:54:59 - INFO - __main__ - Step 75336: {'lr': 0.0002535288677946579, 'samples': 14464512, 'steps': 75335, 'loss/train': 1.7984150648117065} 08/31/2021 02:54:59 - INFO - __main__ - Step 75337: {'lr': 0.0002535235615782175, 'samples': 14464704, 'steps': 75336, 'loss/train': 1.2553293704986572} 08/31/2021 02:55:00 - INFO - __main__ - Step 75338: {'lr': 0.0002535182553601894, 'samples': 14464896, 'steps': 75337, 'loss/train': 1.7652982473373413} 08/31/2021 02:55:00 - INFO - __main__ - Step 75339: {'lr': 0.00025351294914057615, 'samples': 14465088, 'steps': 75338, 'loss/train': 0.45975741744041443} 08/31/2021 02:55:00 - INFO - __main__ - Step 75340: {'lr': 0.00025350764291937994, 'samples': 14465280, 'steps': 75339, 'loss/train': 0.6697790026664734} 08/31/2021 02:55:02 - INFO - __main__ - Step 75341: {'lr': 0.0002535023366966033, 'samples': 14465472, 'steps': 75340, 'loss/train': 1.4848339557647705} 08/31/2021 02:55:03 - INFO - __main__ - Step 75342: {'lr': 0.00025349703047224847, 'samples': 14465664, 'steps': 75341, 'loss/train': 0.3872889280319214} 08/31/2021 02:55:03 - INFO - __main__ - Step 75343: {'lr': 0.0002534917242463179, 'samples': 14465856, 'steps': 75342, 'loss/train': 0.09052351862192154} 08/31/2021 02:55:03 - INFO - __main__ - Step 75344: {'lr': 0.0002534864180188141, 'samples': 14466048, 'steps': 75343, 'loss/train': 0.26117727160453796} 08/31/2021 02:55:04 - INFO - __main__ - Step 75345: {'lr': 0.00025348111178973937, 'samples': 14466240, 'steps': 75344, 'loss/train': 0.28392770886421204} 08/31/2021 02:55:04 - INFO - __main__ - Step 75346: {'lr': 0.0002534758055590962, 'samples': 14466432, 'steps': 75345, 'loss/train': 0.4602649509906769} 08/31/2021 02:55:06 - INFO - __main__ - Step 75347: {'lr': 0.00025347049932688675, 'samples': 14466624, 'steps': 75346, 'loss/train': 1.6145411729812622} 08/31/2021 02:55:06 - INFO - __main__ - Step 75348: {'lr': 0.0002534651930931136, 'samples': 14466816, 'steps': 75347, 'loss/train': 1.3919848203659058} 08/31/2021 02:55:06 - INFO - __main__ - Step 75349: {'lr': 0.00025345988685777904, 'samples': 14467008, 'steps': 75348, 'loss/train': 1.8846428394317627} 08/31/2021 02:55:07 - INFO - __main__ - Step 75350: {'lr': 0.0002534545806208855, 'samples': 14467200, 'steps': 75349, 'loss/train': 1.9490127563476562} 08/31/2021 02:55:07 - INFO - __main__ - Step 75351: {'lr': 0.00025344927438243544, 'samples': 14467392, 'steps': 75350, 'loss/train': 1.3745771646499634} 08/31/2021 02:55:09 - INFO - __main__ - Step 75352: {'lr': 0.00025344396814243114, 'samples': 14467584, 'steps': 75351, 'loss/train': 1.6119352579116821} 08/31/2021 02:55:09 - INFO - __main__ - Step 75353: {'lr': 0.00025343866190087513, 'samples': 14467776, 'steps': 75352, 'loss/train': 1.198676586151123} 08/31/2021 02:55:09 - INFO - __main__ - Step 75354: {'lr': 0.0002534333556577696, 'samples': 14467968, 'steps': 75353, 'loss/train': 0.6845552921295166} 08/31/2021 02:55:10 - INFO - __main__ - Step 75355: {'lr': 0.0002534280494131171, 'samples': 14468160, 'steps': 75354, 'loss/train': 0.6164214015007019} 08/31/2021 02:55:10 - INFO - __main__ - Step 75356: {'lr': 0.00025342274316692, 'samples': 14468352, 'steps': 75355, 'loss/train': 0.9713616371154785} 08/31/2021 02:55:12 - INFO - __main__ - Step 75357: {'lr': 0.0002534174369191806, 'samples': 14468544, 'steps': 75356, 'loss/train': 1.2549742460250854} 08/31/2021 02:55:12 - INFO - __main__ - Step 75358: {'lr': 0.0002534121306699014, 'samples': 14468736, 'steps': 75357, 'loss/train': 1.2674453258514404} 08/31/2021 02:55:13 - INFO - __main__ - Step 75359: {'lr': 0.0002534068244190847, 'samples': 14468928, 'steps': 75358, 'loss/train': 1.5516678094863892} 08/31/2021 02:55:13 - INFO - __main__ - Step 75360: {'lr': 0.0002534015181667331, 'samples': 14469120, 'steps': 75359, 'loss/train': 1.429195761680603} 08/31/2021 02:55:13 - INFO - __main__ - Step 75361: {'lr': 0.0002533962119128487, 'samples': 14469312, 'steps': 75360, 'loss/train': 0.9544488191604614} 08/31/2021 02:55:15 - INFO - __main__ - Step 75362: {'lr': 0.000253390905657434, 'samples': 14469504, 'steps': 75361, 'loss/train': 1.0222877264022827} 08/31/2021 02:55:16 - INFO - __main__ - Step 75363: {'lr': 0.0002533855994004914, 'samples': 14469696, 'steps': 75362, 'loss/train': 0.9620041847229004} 08/31/2021 02:55:16 - INFO - __main__ - Step 75364: {'lr': 0.00025338029314202334, 'samples': 14469888, 'steps': 75363, 'loss/train': 1.129572868347168} 08/31/2021 02:55:17 - INFO - __main__ - Step 75365: {'lr': 0.00025337498688203215, 'samples': 14470080, 'steps': 75364, 'loss/train': 1.8542102575302124} 08/31/2021 02:55:17 - INFO - __main__ - Step 75366: {'lr': 0.0002533696806205203, 'samples': 14470272, 'steps': 75365, 'loss/train': 1.0250047445297241} 08/31/2021 02:55:17 - INFO - __main__ - Step 75367: {'lr': 0.0002533643743574901, 'samples': 14470464, 'steps': 75366, 'loss/train': 1.25789475440979} 08/31/2021 02:55:19 - INFO - __main__ - Step 75368: {'lr': 0.000253359068092944, 'samples': 14470656, 'steps': 75367, 'loss/train': 1.139193058013916} 08/31/2021 02:55:19 - INFO - __main__ - Step 75369: {'lr': 0.00025335376182688424, 'samples': 14470848, 'steps': 75368, 'loss/train': 1.1753052473068237} 08/31/2021 02:55:20 - INFO - __main__ - Step 75370: {'lr': 0.0002533484555593134, 'samples': 14471040, 'steps': 75369, 'loss/train': 1.3952986001968384} 08/31/2021 02:55:20 - INFO - __main__ - Step 75371: {'lr': 0.00025334314929023377, 'samples': 14471232, 'steps': 75370, 'loss/train': 1.7966651916503906} 08/31/2021 02:55:20 - INFO - __main__ - Step 75372: {'lr': 0.0002533378430196478, 'samples': 14471424, 'steps': 75371, 'loss/train': 1.6125705242156982} 08/31/2021 02:55:23 - INFO - __main__ - Step 75373: {'lr': 0.00025333253674755785, 'samples': 14471616, 'steps': 75372, 'loss/train': 1.1125125885009766} 08/31/2021 02:55:23 - INFO - __main__ - Step 75374: {'lr': 0.0002533272304739663, 'samples': 14471808, 'steps': 75373, 'loss/train': 0.5511462688446045} 08/31/2021 02:55:24 - INFO - __main__ - Step 75375: {'lr': 0.00025332192419887556, 'samples': 14472000, 'steps': 75374, 'loss/train': 0.449563205242157} 08/31/2021 02:55:24 - INFO - __main__ - Step 75376: {'lr': 0.000253316617922288, 'samples': 14472192, 'steps': 75375, 'loss/train': 0.3663491904735565} 08/31/2021 02:55:24 - INFO - __main__ - Step 75377: {'lr': 0.00025331131164420603, 'samples': 14472384, 'steps': 75376, 'loss/train': 1.0758415460586548} 08/31/2021 02:55:25 - INFO - __main__ - Step 75378: {'lr': 0.000253306005364632, 'samples': 14472576, 'steps': 75377, 'loss/train': 0.9459220767021179} 08/31/2021 02:55:26 - INFO - __main__ - Step 75379: {'lr': 0.00025330069908356835, 'samples': 14472768, 'steps': 75378, 'loss/train': 0.9965904355049133} 08/31/2021 02:55:27 - INFO - __main__ - Step 75380: {'lr': 0.0002532953928010175, 'samples': 14472960, 'steps': 75379, 'loss/train': 1.041954755783081} 08/31/2021 02:55:27 - INFO - __main__ - Step 75381: {'lr': 0.0002532900865169818, 'samples': 14473152, 'steps': 75380, 'loss/train': 1.1788148880004883} 08/31/2021 02:55:28 - INFO - __main__ - Step 75382: {'lr': 0.00025328478023146363, 'samples': 14473344, 'steps': 75381, 'loss/train': 1.3258641958236694} 08/31/2021 02:55:28 - INFO - __main__ - Step 75383: {'lr': 0.0002532794739444653, 'samples': 14473536, 'steps': 75382, 'loss/train': 0.32237955927848816} 08/31/2021 02:55:30 - INFO - __main__ - Step 75384: {'lr': 0.00025327416765598935, 'samples': 14473728, 'steps': 75383, 'loss/train': 1.4304817914962769} 08/31/2021 02:55:30 - INFO - __main__ - Step 75385: {'lr': 0.0002532688613660381, 'samples': 14473920, 'steps': 75384, 'loss/train': 1.2431868314743042} 08/31/2021 02:55:30 - INFO - __main__ - Step 75386: {'lr': 0.0002532635550746141, 'samples': 14474112, 'steps': 75385, 'loss/train': 1.5515958070755005} 08/31/2021 02:55:31 - INFO - __main__ - Step 75387: {'lr': 0.00025325824878171937, 'samples': 14474304, 'steps': 75386, 'loss/train': 0.9053732752799988} 08/31/2021 02:55:31 - INFO - __main__ - Step 75388: {'lr': 0.00025325294248735664, 'samples': 14474496, 'steps': 75387, 'loss/train': 1.0244989395141602} 08/31/2021 02:55:33 - INFO - __main__ - Step 75389: {'lr': 0.0002532476361915281, 'samples': 14474688, 'steps': 75388, 'loss/train': 0.8342292904853821} 08/31/2021 02:55:33 - INFO - __main__ - Step 75390: {'lr': 0.00025324232989423626, 'samples': 14474880, 'steps': 75389, 'loss/train': 1.614606261253357} 08/31/2021 02:55:34 - INFO - __main__ - Step 75391: {'lr': 0.0002532370235954836, 'samples': 14475072, 'steps': 75390, 'loss/train': 1.3052823543548584} 08/31/2021 02:55:34 - INFO - __main__ - Step 75392: {'lr': 0.00025323171729527225, 'samples': 14475264, 'steps': 75391, 'loss/train': 1.1763960123062134} 08/31/2021 02:55:34 - INFO - __main__ - Step 75393: {'lr': 0.00025322641099360477, 'samples': 14475456, 'steps': 75392, 'loss/train': 1.1358219385147095} 08/31/2021 02:55:35 - INFO - __main__ - Step 75394: {'lr': 0.00025322110469048353, 'samples': 14475648, 'steps': 75393, 'loss/train': 1.352681279182434} 08/31/2021 02:55:35 - INFO - __main__ - Step 75395: {'lr': 0.0002532157983859109, 'samples': 14475840, 'steps': 75394, 'loss/train': 0.051810745149850845} 08/31/2021 02:55:37 - INFO - __main__ - Step 75396: {'lr': 0.0002532104920798893, 'samples': 14476032, 'steps': 75395, 'loss/train': 0.787544846534729} 08/31/2021 02:55:37 - INFO - __main__ - Step 75397: {'lr': 0.00025320518577242115, 'samples': 14476224, 'steps': 75396, 'loss/train': 0.08150927722454071} 08/31/2021 02:55:38 - INFO - __main__ - Step 75398: {'lr': 0.0002531998794635087, 'samples': 14476416, 'steps': 75397, 'loss/train': 0.7722798585891724} 08/31/2021 02:55:38 - INFO - __main__ - Step 75399: {'lr': 0.00025319457315315443, 'samples': 14476608, 'steps': 75398, 'loss/train': 1.1850682497024536} 08/31/2021 02:55:39 - INFO - __main__ - Step 75400: {'lr': 0.00025318926684136077, 'samples': 14476800, 'steps': 75399, 'loss/train': 1.1530864238739014} 08/31/2021 02:55:40 - INFO - __main__ - Step 75401: {'lr': 0.0002531839605281301, 'samples': 14476992, 'steps': 75400, 'loss/train': 1.5613160133361816} 08/31/2021 02:55:40 - INFO - __main__ - Step 75402: {'lr': 0.00025317865421346477, 'samples': 14477184, 'steps': 75401, 'loss/train': 1.2004742622375488} 08/31/2021 02:55:41 - INFO - __main__ - Step 75403: {'lr': 0.0002531733478973672, 'samples': 14477376, 'steps': 75402, 'loss/train': 1.3784561157226562} 08/31/2021 02:55:41 - INFO - __main__ - Step 75404: {'lr': 0.0002531680415798397, 'samples': 14477568, 'steps': 75403, 'loss/train': 1.0189054012298584} 08/31/2021 02:55:42 - INFO - __main__ - Step 75405: {'lr': 0.0002531627352608848, 'samples': 14477760, 'steps': 75404, 'loss/train': 0.8310841917991638} 08/31/2021 02:55:43 - INFO - __main__ - Step 75406: {'lr': 0.00025315742894050475, 'samples': 14477952, 'steps': 75405, 'loss/train': 1.8274199962615967} 08/31/2021 02:55:44 - INFO - __main__ - Step 75407: {'lr': 0.00025315212261870206, 'samples': 14478144, 'steps': 75406, 'loss/train': 1.7726939916610718} 08/31/2021 02:55:44 - INFO - __main__ - Step 75408: {'lr': 0.00025314681629547907, 'samples': 14478336, 'steps': 75407, 'loss/train': 1.5078085660934448} 08/31/2021 02:55:45 - INFO - __main__ - Step 75409: {'lr': 0.0002531415099708382, 'samples': 14478528, 'steps': 75408, 'loss/train': 1.8451526165008545} 08/31/2021 02:55:45 - INFO - __main__ - Step 75410: {'lr': 0.0002531362036447818, 'samples': 14478720, 'steps': 75409, 'loss/train': 0.6375092267990112} 08/31/2021 02:55:47 - INFO - __main__ - Step 75411: {'lr': 0.0002531308973173122, 'samples': 14478912, 'steps': 75410, 'loss/train': 1.8047149181365967} 08/31/2021 02:55:48 - INFO - __main__ - Step 75412: {'lr': 0.00025312559098843195, 'samples': 14479104, 'steps': 75411, 'loss/train': 1.4570558071136475} 08/31/2021 02:55:48 - INFO - __main__ - Step 75413: {'lr': 0.00025312028465814337, 'samples': 14479296, 'steps': 75412, 'loss/train': 1.4086912870407104} 08/31/2021 02:55:49 - INFO - __main__ - Step 75414: {'lr': 0.0002531149783264488, 'samples': 14479488, 'steps': 75413, 'loss/train': 1.2016944885253906} 08/31/2021 02:55:49 - INFO - __main__ - Step 75415: {'lr': 0.0002531096719933507, 'samples': 14479680, 'steps': 75414, 'loss/train': 1.746329665184021} 08/31/2021 02:55:49 - INFO - __main__ - Step 75416: {'lr': 0.0002531043656588514, 'samples': 14479872, 'steps': 75415, 'loss/train': 1.0228562355041504} 08/31/2021 02:55:50 - INFO - __main__ - Step 75417: {'lr': 0.00025309905932295324, 'samples': 14480064, 'steps': 75416, 'loss/train': 0.9523840546607971} 08/31/2021 02:55:52 - INFO - __main__ - Step 75418: {'lr': 0.00025309375298565877, 'samples': 14480256, 'steps': 75417, 'loss/train': 1.1554557085037231} 08/31/2021 02:55:52 - INFO - __main__ - Step 75419: {'lr': 0.00025308844664697033, 'samples': 14480448, 'steps': 75418, 'loss/train': 1.3090519905090332} 08/31/2021 02:55:53 - INFO - __main__ - Step 75420: {'lr': 0.00025308314030689027, 'samples': 14480640, 'steps': 75419, 'loss/train': 0.6379532217979431} 08/31/2021 02:55:53 - INFO - __main__ - Step 75421: {'lr': 0.000253077833965421, 'samples': 14480832, 'steps': 75420, 'loss/train': 0.9146919250488281} 08/31/2021 02:55:53 - INFO - __main__ - Step 75422: {'lr': 0.0002530725276225649, 'samples': 14481024, 'steps': 75421, 'loss/train': 1.6375998258590698} 08/31/2021 02:55:55 - INFO - __main__ - Step 75423: {'lr': 0.0002530672212783243, 'samples': 14481216, 'steps': 75422, 'loss/train': 1.6421741247177124} 08/31/2021 02:55:55 - INFO - __main__ - Step 75424: {'lr': 0.0002530619149327017, 'samples': 14481408, 'steps': 75423, 'loss/train': 0.607656717300415} 08/31/2021 02:55:55 - INFO - __main__ - Step 75425: {'lr': 0.00025305660858569945, 'samples': 14481600, 'steps': 75424, 'loss/train': 1.1289632320404053} 08/31/2021 02:55:56 - INFO - __main__ - Step 75426: {'lr': 0.00025305130223732, 'samples': 14481792, 'steps': 75425, 'loss/train': 1.6200463771820068} 08/31/2021 02:55:56 - INFO - __main__ - Step 75427: {'lr': 0.00025304599588756564, 'samples': 14481984, 'steps': 75426, 'loss/train': 0.8890091776847839} 08/31/2021 02:55:58 - INFO - __main__ - Step 75428: {'lr': 0.00025304068953643875, 'samples': 14482176, 'steps': 75427, 'loss/train': 1.4924073219299316} 08/31/2021 02:55:59 - INFO - __main__ - Step 75429: {'lr': 0.00025303538318394186, 'samples': 14482368, 'steps': 75428, 'loss/train': 1.0268913507461548} 08/31/2021 02:55:59 - INFO - __main__ - Step 75430: {'lr': 0.00025303007683007725, 'samples': 14482560, 'steps': 75429, 'loss/train': 1.2870116233825684} 08/31/2021 02:55:59 - INFO - __main__ - Step 75431: {'lr': 0.00025302477047484725, 'samples': 14482752, 'steps': 75430, 'loss/train': 1.1330407857894897} 08/31/2021 02:56:00 - INFO - __main__ - Step 75432: {'lr': 0.0002530194641182544, 'samples': 14482944, 'steps': 75431, 'loss/train': 1.8539986610412598} 08/31/2021 02:56:01 - INFO - __main__ - Step 75433: {'lr': 0.00025301415776030105, 'samples': 14483136, 'steps': 75432, 'loss/train': 0.11652675271034241} 08/31/2021 02:56:01 - INFO - __main__ - Step 75434: {'lr': 0.0002530088514009896, 'samples': 14483328, 'steps': 75433, 'loss/train': 0.4625113308429718} 08/31/2021 02:56:02 - INFO - __main__ - Step 75435: {'lr': 0.0002530035450403223, 'samples': 14483520, 'steps': 75434, 'loss/train': 1.2194904088974} 08/31/2021 02:56:02 - INFO - __main__ - Step 75436: {'lr': 0.00025299823867830167, 'samples': 14483712, 'steps': 75435, 'loss/train': 0.9952524304389954} 08/31/2021 02:56:03 - INFO - __main__ - Step 75437: {'lr': 0.00025299293231493007, 'samples': 14483904, 'steps': 75436, 'loss/train': 1.0440640449523926} 08/31/2021 02:56:04 - INFO - __main__ - Step 75438: {'lr': 0.00025298762595020994, 'samples': 14484096, 'steps': 75437, 'loss/train': 1.7588376998901367} 08/31/2021 02:56:05 - INFO - __main__ - Step 75439: {'lr': 0.00025298231958414367, 'samples': 14484288, 'steps': 75438, 'loss/train': 1.2755217552185059} 08/31/2021 02:56:05 - INFO - __main__ - Step 75440: {'lr': 0.00025297701321673363, 'samples': 14484480, 'steps': 75439, 'loss/train': 0.037881188094615936} 08/31/2021 02:56:06 - INFO - __main__ - Step 75441: {'lr': 0.0002529717068479821, 'samples': 14484672, 'steps': 75440, 'loss/train': 0.31785187125205994} 08/31/2021 02:56:06 - INFO - __main__ - Step 75442: {'lr': 0.0002529664004778916, 'samples': 14484864, 'steps': 75441, 'loss/train': 1.1218136548995972} 08/31/2021 02:56:06 - INFO - __main__ - Step 75443: {'lr': 0.00025296109410646443, 'samples': 14485056, 'steps': 75442, 'loss/train': 1.3569759130477905} 08/31/2021 02:56:08 - INFO - __main__ - Step 75444: {'lr': 0.0002529557877337031, 'samples': 14485248, 'steps': 75443, 'loss/train': 1.1336982250213623} 08/31/2021 02:56:08 - INFO - __main__ - Step 75445: {'lr': 0.0002529504813596099, 'samples': 14485440, 'steps': 75444, 'loss/train': 1.4293559789657593} 08/31/2021 02:56:09 - INFO - __main__ - Step 75446: {'lr': 0.00025294517498418727, 'samples': 14485632, 'steps': 75445, 'loss/train': 0.8155045509338379} 08/31/2021 02:56:09 - INFO - __main__ - Step 75447: {'lr': 0.0002529398686074377, 'samples': 14485824, 'steps': 75446, 'loss/train': 0.9238346219062805} 08/31/2021 02:56:09 - INFO - __main__ - Step 75448: {'lr': 0.00025293456222936334, 'samples': 14486016, 'steps': 75447, 'loss/train': 1.4554271697998047} 08/31/2021 02:56:10 - INFO - __main__ - Step 75449: {'lr': 0.0002529292558499668, 'samples': 14486208, 'steps': 75448, 'loss/train': 1.164899230003357} 08/31/2021 02:56:11 - INFO - __main__ - Step 75450: {'lr': 0.0002529239494692503, 'samples': 14486400, 'steps': 75449, 'loss/train': 1.3710087537765503} 08/31/2021 02:56:12 - INFO - __main__ - Step 75451: {'lr': 0.0002529186430872163, 'samples': 14486592, 'steps': 75450, 'loss/train': 1.419642686843872} 08/31/2021 02:56:12 - INFO - __main__ - Step 75452: {'lr': 0.00025291333670386727, 'samples': 14486784, 'steps': 75451, 'loss/train': 1.4293352365493774} 08/31/2021 02:56:13 - INFO - __main__ - Step 75453: {'lr': 0.0002529080303192055, 'samples': 14486976, 'steps': 75452, 'loss/train': 1.3187475204467773} 08/31/2021 02:56:13 - INFO - __main__ - Step 75454: {'lr': 0.0002529027239332335, 'samples': 14487168, 'steps': 75453, 'loss/train': 1.9169442653656006} 08/31/2021 02:56:14 - INFO - __main__ - Step 75455: {'lr': 0.0002528974175459535, 'samples': 14487360, 'steps': 75454, 'loss/train': 1.329147219657898} 08/31/2021 02:56:15 - INFO - __main__ - Step 75456: {'lr': 0.000252892111157368, 'samples': 14487552, 'steps': 75455, 'loss/train': 0.8219429850578308} 08/31/2021 02:56:15 - INFO - __main__ - Step 75457: {'lr': 0.0002528868047674793, 'samples': 14487744, 'steps': 75456, 'loss/train': 1.684824824333191} 08/31/2021 02:56:16 - INFO - __main__ - Step 75458: {'lr': 0.0002528814983762899, 'samples': 14487936, 'steps': 75457, 'loss/train': 1.4601101875305176} 08/31/2021 02:56:16 - INFO - __main__ - Step 75459: {'lr': 0.0002528761919838021, 'samples': 14488128, 'steps': 75458, 'loss/train': 1.3117260932922363} 08/31/2021 02:56:16 - INFO - __main__ - Step 75460: {'lr': 0.0002528708855900184, 'samples': 14488320, 'steps': 75459, 'loss/train': 1.1906118392944336} 08/31/2021 02:56:18 - INFO - __main__ - Step 75461: {'lr': 0.0002528655791949411, 'samples': 14488512, 'steps': 75460, 'loss/train': 1.4097344875335693} 08/31/2021 02:56:18 - INFO - __main__ - Step 75462: {'lr': 0.0002528602727985726, 'samples': 14488704, 'steps': 75461, 'loss/train': 1.3136606216430664} 08/31/2021 02:56:19 - INFO - __main__ - Step 75463: {'lr': 0.00025285496640091524, 'samples': 14488896, 'steps': 75462, 'loss/train': 1.0606794357299805} 08/31/2021 02:56:19 - INFO - __main__ - Step 75464: {'lr': 0.00025284966000197156, 'samples': 14489088, 'steps': 75463, 'loss/train': 1.4022210836410522} 08/31/2021 02:56:19 - INFO - __main__ - Step 75465: {'lr': 0.00025284435360174387, 'samples': 14489280, 'steps': 75464, 'loss/train': 1.0950443744659424} 08/31/2021 02:56:21 - INFO - __main__ - Step 75466: {'lr': 0.0002528390472002345, 'samples': 14489472, 'steps': 75465, 'loss/train': 1.9720600843429565} 08/31/2021 02:56:22 - INFO - __main__ - Step 75467: {'lr': 0.00025283374079744595, 'samples': 14489664, 'steps': 75466, 'loss/train': 1.344670295715332} 08/31/2021 02:56:22 - INFO - __main__ - Step 75468: {'lr': 0.00025282843439338056, 'samples': 14489856, 'steps': 75467, 'loss/train': 1.5960248708724976} 08/31/2021 02:56:22 - INFO - __main__ - Step 75469: {'lr': 0.0002528231279880407, 'samples': 14490048, 'steps': 75468, 'loss/train': 1.2515414953231812} 08/31/2021 02:56:23 - INFO - __main__ - Step 75470: {'lr': 0.0002528178215814288, 'samples': 14490240, 'steps': 75469, 'loss/train': 1.3239128589630127} 08/31/2021 02:56:23 - INFO - __main__ - Step 75471: {'lr': 0.0002528125151735472, 'samples': 14490432, 'steps': 75470, 'loss/train': 0.973098635673523} 08/31/2021 02:56:25 - INFO - __main__ - Step 75472: {'lr': 0.0002528072087643983, 'samples': 14490624, 'steps': 75471, 'loss/train': 0.7244437336921692} 08/31/2021 02:56:25 - INFO - __main__ - Step 75473: {'lr': 0.0002528019023539846, 'samples': 14490816, 'steps': 75472, 'loss/train': 1.2201491594314575} 08/31/2021 02:56:26 - INFO - __main__ - Step 75474: {'lr': 0.0002527965959423084, 'samples': 14491008, 'steps': 75473, 'loss/train': 1.3068203926086426} 08/31/2021 02:56:26 - INFO - __main__ - Step 75475: {'lr': 0.0002527912895293721, 'samples': 14491200, 'steps': 75474, 'loss/train': 1.5774104595184326} 08/31/2021 02:56:26 - INFO - __main__ - Step 75476: {'lr': 0.000252785983115178, 'samples': 14491392, 'steps': 75475, 'loss/train': 1.8944660425186157} 08/31/2021 02:56:28 - INFO - __main__ - Step 75477: {'lr': 0.00025278067669972867, 'samples': 14491584, 'steps': 75476, 'loss/train': 1.2583426237106323} 08/31/2021 02:56:29 - INFO - __main__ - Step 75478: {'lr': 0.0002527753702830263, 'samples': 14491776, 'steps': 75477, 'loss/train': 0.06760642677545547} 08/31/2021 02:56:29 - INFO - __main__ - Step 75479: {'lr': 0.0002527700638650735, 'samples': 14491968, 'steps': 75478, 'loss/train': 1.1239306926727295} 08/31/2021 02:56:29 - INFO - __main__ - Step 75480: {'lr': 0.00025276475744587246, 'samples': 14492160, 'steps': 75479, 'loss/train': 0.832754373550415} 08/31/2021 02:56:30 - INFO - __main__ - Step 75481: {'lr': 0.0002527594510254258, 'samples': 14492352, 'steps': 75480, 'loss/train': 0.028164366260170937} 08/31/2021 02:56:31 - INFO - __main__ - Step 75482: {'lr': 0.00025275414460373567, 'samples': 14492544, 'steps': 75481, 'loss/train': 1.0335421562194824} 08/31/2021 02:56:32 - INFO - __main__ - Step 75483: {'lr': 0.00025274883818080456, 'samples': 14492736, 'steps': 75482, 'loss/train': 1.2049161195755005} 08/31/2021 02:56:32 - INFO - __main__ - Step 75484: {'lr': 0.0002527435317566349, 'samples': 14492928, 'steps': 75483, 'loss/train': 1.4779554605484009} 08/31/2021 02:56:32 - INFO - __main__ - Step 75485: {'lr': 0.000252738225331229, 'samples': 14493120, 'steps': 75484, 'loss/train': 1.531872034072876} 08/31/2021 02:56:33 - INFO - __main__ - Step 75486: {'lr': 0.00025273291890458933, 'samples': 14493312, 'steps': 75485, 'loss/train': 0.9868484735488892} 08/31/2021 02:56:34 - INFO - __main__ - Step 75487: {'lr': 0.00025272761247671833, 'samples': 14493504, 'steps': 75486, 'loss/train': 1.3812679052352905} 08/31/2021 02:56:35 - INFO - __main__ - Step 75488: {'lr': 0.0002527223060476182, 'samples': 14493696, 'steps': 75487, 'loss/train': 0.0443466491997242} 08/31/2021 02:56:35 - INFO - __main__ - Step 75489: {'lr': 0.0002527169996172915, 'samples': 14493888, 'steps': 75488, 'loss/train': 0.7916406393051147} 08/31/2021 02:56:35 - INFO - __main__ - Step 75490: {'lr': 0.0002527116931857405, 'samples': 14494080, 'steps': 75489, 'loss/train': 1.6894943714141846} 08/31/2021 02:56:36 - INFO - __main__ - Step 75491: {'lr': 0.0002527063867529677, 'samples': 14494272, 'steps': 75490, 'loss/train': 1.4837770462036133} 08/31/2021 02:56:37 - INFO - __main__ - Step 75492: {'lr': 0.0002527010803189754, 'samples': 14494464, 'steps': 75491, 'loss/train': 1.6676030158996582} 08/31/2021 02:56:38 - INFO - __main__ - Step 75493: {'lr': 0.0002526957738837661, 'samples': 14494656, 'steps': 75492, 'loss/train': 0.4041358232498169} 08/31/2021 02:56:38 - INFO - __main__ - Step 75494: {'lr': 0.00025269046744734214, 'samples': 14494848, 'steps': 75493, 'loss/train': 1.1864904165267944} 08/31/2021 02:56:38 - INFO - __main__ - Step 75495: {'lr': 0.00025268516100970584, 'samples': 14495040, 'steps': 75494, 'loss/train': 0.5887913107872009} 08/31/2021 02:56:39 - INFO - __main__ - Step 75496: {'lr': 0.0002526798545708596, 'samples': 14495232, 'steps': 75495, 'loss/train': 1.1055622100830078} 08/31/2021 02:56:40 - INFO - __main__ - Step 75497: {'lr': 0.000252674548130806, 'samples': 14495424, 'steps': 75496, 'loss/train': 0.9616855382919312} 08/31/2021 02:56:41 - INFO - __main__ - Step 75498: {'lr': 0.00025266924168954714, 'samples': 14495616, 'steps': 75497, 'loss/train': 0.6089503765106201} 08/31/2021 02:56:41 - INFO - __main__ - Step 75499: {'lr': 0.00025266393524708564, 'samples': 14495808, 'steps': 75498, 'loss/train': 0.34499362111091614} 08/31/2021 02:56:41 - INFO - __main__ - Step 75500: {'lr': 0.0002526586288034238, 'samples': 14496000, 'steps': 75499, 'loss/train': 1.6511790752410889} 08/31/2021 02:56:42 - INFO - __main__ - Step 75501: {'lr': 0.0002526533223585641, 'samples': 14496192, 'steps': 75500, 'loss/train': 0.5789750218391418} 08/31/2021 02:56:44 - INFO - __main__ - Step 75502: {'lr': 0.00025264801591250873, 'samples': 14496384, 'steps': 75501, 'loss/train': 1.165460228919983} 08/31/2021 02:56:44 - INFO - __main__ - Step 75503: {'lr': 0.0002526427094652602, 'samples': 14496576, 'steps': 75502, 'loss/train': 0.42938026785850525} 08/31/2021 02:56:45 - INFO - __main__ - Step 75504: {'lr': 0.00025263740301682103, 'samples': 14496768, 'steps': 75503, 'loss/train': 0.051292482763528824} 08/31/2021 02:56:45 - INFO - __main__ - Step 75505: {'lr': 0.0002526320965671934, 'samples': 14496960, 'steps': 75504, 'loss/train': 1.3647794723510742} 08/31/2021 02:56:45 - INFO - __main__ - Step 75506: {'lr': 0.0002526267901163798, 'samples': 14497152, 'steps': 75505, 'loss/train': 1.2075724601745605} 08/31/2021 02:56:46 - INFO - __main__ - Step 75507: {'lr': 0.00025262148366438265, 'samples': 14497344, 'steps': 75506, 'loss/train': 0.7280755639076233} 08/31/2021 02:56:47 - INFO - __main__ - Step 75508: {'lr': 0.0002526161772112042, 'samples': 14497536, 'steps': 75507, 'loss/train': 1.5336610078811646} 08/31/2021 02:56:48 - INFO - __main__ - Step 75509: {'lr': 0.000252610870756847, 'samples': 14497728, 'steps': 75508, 'loss/train': 1.5385831594467163} 08/31/2021 02:56:48 - INFO - __main__ - Step 75510: {'lr': 0.00025260556430131345, 'samples': 14497920, 'steps': 75509, 'loss/train': 1.0742876529693604} 08/31/2021 02:56:48 - INFO - __main__ - Step 75511: {'lr': 0.00025260025784460576, 'samples': 14498112, 'steps': 75510, 'loss/train': 1.3983434438705444} 08/31/2021 02:56:49 - INFO - __main__ - Step 75512: {'lr': 0.0002525949513867265, 'samples': 14498304, 'steps': 75511, 'loss/train': 1.6667835712432861} 08/31/2021 02:56:50 - INFO - __main__ - Step 75513: {'lr': 0.00025258964492767794, 'samples': 14498496, 'steps': 75512, 'loss/train': 1.2831156253814697} 08/31/2021 02:56:51 - INFO - __main__ - Step 75514: {'lr': 0.00025258433846746264, 'samples': 14498688, 'steps': 75513, 'loss/train': 1.3299815654754639} 08/31/2021 02:56:51 - INFO - __main__ - Step 75515: {'lr': 0.0002525790320060828, 'samples': 14498880, 'steps': 75514, 'loss/train': 0.8241341710090637} 08/31/2021 02:56:51 - INFO - __main__ - Step 75516: {'lr': 0.00025257372554354085, 'samples': 14499072, 'steps': 75515, 'loss/train': 0.9896805286407471} 08/31/2021 02:56:52 - INFO - __main__ - Step 75517: {'lr': 0.00025256841907983924, 'samples': 14499264, 'steps': 75516, 'loss/train': 1.3871583938598633} 08/31/2021 02:56:53 - INFO - __main__ - Step 75518: {'lr': 0.00025256311261498036, 'samples': 14499456, 'steps': 75517, 'loss/train': 0.09232461452484131} 08/31/2021 02:56:54 - INFO - __main__ - Step 75519: {'lr': 0.0002525578061489666, 'samples': 14499648, 'steps': 75518, 'loss/train': 1.4548341035842896} 08/31/2021 02:56:54 - INFO - __main__ - Step 75520: {'lr': 0.00025255249968180035, 'samples': 14499840, 'steps': 75519, 'loss/train': 1.0767465829849243} 08/31/2021 02:56:54 - INFO - __main__ - Step 75521: {'lr': 0.0002525471932134839, 'samples': 14500032, 'steps': 75520, 'loss/train': 1.4425578117370605} 08/31/2021 02:56:55 - INFO - __main__ - Step 75522: {'lr': 0.0002525418867440198, 'samples': 14500224, 'steps': 75521, 'loss/train': 1.5345110893249512} 08/31/2021 02:56:56 - INFO - __main__ - Step 75523: {'lr': 0.0002525365802734103, 'samples': 14500416, 'steps': 75522, 'loss/train': 1.3358302116394043} 08/31/2021 02:56:57 - INFO - __main__ - Step 75524: {'lr': 0.00025253127380165784, 'samples': 14500608, 'steps': 75523, 'loss/train': 0.7378090620040894} 08/31/2021 02:56:57 - INFO - __main__ - Step 75525: {'lr': 0.0002525259673287649, 'samples': 14500800, 'steps': 75524, 'loss/train': 1.869117021560669} 08/31/2021 02:56:58 - INFO - __main__ - Step 75526: {'lr': 0.00025252066085473384, 'samples': 14500992, 'steps': 75525, 'loss/train': 1.2293870449066162} 08/31/2021 02:56:58 - INFO - __main__ - Step 75527: {'lr': 0.0002525153543795669, 'samples': 14501184, 'steps': 75526, 'loss/train': 1.062119722366333} 08/31/2021 02:56:58 - INFO - __main__ - Step 75528: {'lr': 0.00025251004790326665, 'samples': 14501376, 'steps': 75527, 'loss/train': 2.082688808441162} 08/31/2021 02:57:00 - INFO - __main__ - Step 75529: {'lr': 0.00025250474142583535, 'samples': 14501568, 'steps': 75528, 'loss/train': 1.3372890949249268} 08/31/2021 02:57:01 - INFO - __main__ - Step 75530: {'lr': 0.0002524994349472755, 'samples': 14501760, 'steps': 75529, 'loss/train': 0.9772977828979492} 08/31/2021 02:57:01 - INFO - __main__ - Step 75531: {'lr': 0.00025249412846758946, 'samples': 14501952, 'steps': 75530, 'loss/train': 1.0461293458938599} 08/31/2021 02:57:01 - INFO - __main__ - Step 75532: {'lr': 0.00025248882198677957, 'samples': 14502144, 'steps': 75531, 'loss/train': 1.6450845003128052} 08/31/2021 02:57:02 - INFO - __main__ - Step 75533: {'lr': 0.0002524835155048483, 'samples': 14502336, 'steps': 75532, 'loss/train': 1.406976580619812} 08/31/2021 02:57:03 - INFO - __main__ - Step 75534: {'lr': 0.0002524782090217979, 'samples': 14502528, 'steps': 75533, 'loss/train': 1.0838971138000488} 08/31/2021 02:57:04 - INFO - __main__ - Step 75535: {'lr': 0.0002524729025376309, 'samples': 14502720, 'steps': 75534, 'loss/train': 1.5255675315856934} 08/31/2021 02:57:04 - INFO - __main__ - Step 75536: {'lr': 0.00025246759605234966, 'samples': 14502912, 'steps': 75535, 'loss/train': 1.623169183731079} 08/31/2021 02:57:04 - INFO - __main__ - Step 75537: {'lr': 0.0002524622895659566, 'samples': 14503104, 'steps': 75536, 'loss/train': 0.8629474639892578} 08/31/2021 02:57:05 - INFO - __main__ - Step 75538: {'lr': 0.00025245698307845406, 'samples': 14503296, 'steps': 75537, 'loss/train': 1.4245057106018066} 08/31/2021 02:57:06 - INFO - __main__ - Step 75539: {'lr': 0.00025245167658984437, 'samples': 14503488, 'steps': 75538, 'loss/train': 1.3908854722976685} 08/31/2021 02:57:07 - INFO - __main__ - Step 75540: {'lr': 0.00025244637010013004, 'samples': 14503680, 'steps': 75539, 'loss/train': 1.583115816116333} 08/31/2021 02:57:07 - INFO - __main__ - Step 75541: {'lr': 0.0002524410636093134, 'samples': 14503872, 'steps': 75540, 'loss/train': 1.1402699947357178} 08/31/2021 02:57:07 - INFO - __main__ - Step 75542: {'lr': 0.0002524357571173969, 'samples': 14504064, 'steps': 75541, 'loss/train': 0.31265369057655334} 08/31/2021 02:57:08 - INFO - __main__ - Step 75543: {'lr': 0.00025243045062438285, 'samples': 14504256, 'steps': 75542, 'loss/train': 1.190527319908142} 08/31/2021 02:57:09 - INFO - __main__ - Step 75544: {'lr': 0.00025242514413027366, 'samples': 14504448, 'steps': 75543, 'loss/train': 1.0247904062271118} 08/31/2021 02:57:10 - INFO - __main__ - Step 75545: {'lr': 0.00025241983763507175, 'samples': 14504640, 'steps': 75544, 'loss/train': 1.3113043308258057} 08/31/2021 02:57:10 - INFO - __main__ - Step 75546: {'lr': 0.0002524145311387795, 'samples': 14504832, 'steps': 75545, 'loss/train': 1.1537443399429321} 08/31/2021 02:57:10 - INFO - __main__ - Step 75547: {'lr': 0.0002524092246413993, 'samples': 14505024, 'steps': 75546, 'loss/train': 1.2511202096939087} 08/31/2021 02:57:11 - INFO - __main__ - Step 75548: {'lr': 0.00025240391814293354, 'samples': 14505216, 'steps': 75547, 'loss/train': 1.338088870048523} 08/31/2021 02:57:11 - INFO - __main__ - Step 75549: {'lr': 0.0002523986116433846, 'samples': 14505408, 'steps': 75548, 'loss/train': 1.1507529020309448} 08/31/2021 02:57:13 - INFO - __main__ - Step 75550: {'lr': 0.0002523933051427549, 'samples': 14505600, 'steps': 75549, 'loss/train': 0.8757404685020447} 08/31/2021 02:57:13 - INFO - __main__ - Step 75551: {'lr': 0.0002523879986410468, 'samples': 14505792, 'steps': 75550, 'loss/train': 1.3277881145477295} 08/31/2021 02:57:13 - INFO - __main__ - Step 75552: {'lr': 0.0002523826921382627, 'samples': 14505984, 'steps': 75551, 'loss/train': 1.774636149406433} 08/31/2021 02:57:14 - INFO - __main__ - Step 75553: {'lr': 0.00025237738563440497, 'samples': 14506176, 'steps': 75552, 'loss/train': 0.7861302495002747} 08/31/2021 02:57:14 - INFO - __main__ - Step 75554: {'lr': 0.00025237207912947614, 'samples': 14506368, 'steps': 75553, 'loss/train': 1.1609200239181519} 08/31/2021 02:57:16 - INFO - __main__ - Step 75555: {'lr': 0.0002523667726234784, 'samples': 14506560, 'steps': 75554, 'loss/train': 1.2330944538116455} 08/31/2021 02:57:16 - INFO - __main__ - Step 75556: {'lr': 0.00025236146611641423, 'samples': 14506752, 'steps': 75555, 'loss/train': 0.5910906195640564} 08/31/2021 02:57:17 - INFO - __main__ - Step 75557: {'lr': 0.0002523561596082861, 'samples': 14506944, 'steps': 75556, 'loss/train': 1.0558464527130127} 08/31/2021 02:57:17 - INFO - __main__ - Step 75558: {'lr': 0.0002523508530990962, 'samples': 14507136, 'steps': 75557, 'loss/train': 1.4336618185043335} 08/31/2021 02:57:17 - INFO - __main__ - Step 75559: {'lr': 0.00025234554658884706, 'samples': 14507328, 'steps': 75558, 'loss/train': 1.0900758504867554} 08/31/2021 02:57:19 - INFO - __main__ - Step 75560: {'lr': 0.00025234024007754106, 'samples': 14507520, 'steps': 75559, 'loss/train': 1.4774688482284546} 08/31/2021 02:57:19 - INFO - __main__ - Step 75561: {'lr': 0.0002523349335651807, 'samples': 14507712, 'steps': 75560, 'loss/train': 1.1146647930145264} 08/31/2021 02:57:20 - INFO - __main__ - Step 75562: {'lr': 0.0002523296270517682, 'samples': 14507904, 'steps': 75561, 'loss/train': 1.4274437427520752} 08/31/2021 02:57:20 - INFO - __main__ - Step 75563: {'lr': 0.0002523243205373059, 'samples': 14508096, 'steps': 75562, 'loss/train': 0.7930645942687988} 08/31/2021 02:57:20 - INFO - __main__ - Step 75564: {'lr': 0.00025231901402179635, 'samples': 14508288, 'steps': 75563, 'loss/train': 1.0671244859695435} 08/31/2021 02:57:22 - INFO - __main__ - Step 75565: {'lr': 0.0002523137075052419, 'samples': 14508480, 'steps': 75564, 'loss/train': 0.26723968982696533} 08/31/2021 02:57:22 - INFO - __main__ - Step 75566: {'lr': 0.00025230840098764497, 'samples': 14508672, 'steps': 75565, 'loss/train': 1.2995799779891968} 08/31/2021 02:57:23 - INFO - __main__ - Step 75567: {'lr': 0.00025230309446900787, 'samples': 14508864, 'steps': 75566, 'loss/train': 1.3125742673873901} 08/31/2021 02:57:23 - INFO - __main__ - Step 75568: {'lr': 0.0002522977879493331, 'samples': 14509056, 'steps': 75567, 'loss/train': 1.408579707145691} 08/31/2021 02:57:23 - INFO - __main__ - Step 75569: {'lr': 0.00025229248142862287, 'samples': 14509248, 'steps': 75568, 'loss/train': 1.3709421157836914} 08/31/2021 02:57:25 - INFO - __main__ - Step 75570: {'lr': 0.00025228717490687974, 'samples': 14509440, 'steps': 75569, 'loss/train': 0.992441713809967} 08/31/2021 02:57:25 - INFO - __main__ - Step 75571: {'lr': 0.000252281868384106, 'samples': 14509632, 'steps': 75570, 'loss/train': 1.7727453708648682} 08/31/2021 02:57:26 - INFO - __main__ - Step 75572: {'lr': 0.0002522765618603041, 'samples': 14509824, 'steps': 75571, 'loss/train': 1.5837562084197998} 08/31/2021 02:57:26 - INFO - __main__ - Step 75573: {'lr': 0.00025227125533547643, 'samples': 14510016, 'steps': 75572, 'loss/train': 1.6693394184112549} 08/31/2021 02:57:26 - INFO - __main__ - Step 75574: {'lr': 0.0002522659488096254, 'samples': 14510208, 'steps': 75573, 'loss/train': 0.03939279913902283} 08/31/2021 02:57:27 - INFO - __main__ - Step 75575: {'lr': 0.0002522606422827534, 'samples': 14510400, 'steps': 75574, 'loss/train': 0.8668308854103088} 08/31/2021 02:57:28 - INFO - __main__ - Step 75576: {'lr': 0.0002522553357548627, 'samples': 14510592, 'steps': 75575, 'loss/train': 1.7681597471237183} 08/31/2021 02:57:29 - INFO - __main__ - Step 75577: {'lr': 0.0002522500292259558, 'samples': 14510784, 'steps': 75576, 'loss/train': 1.0354269742965698} 08/31/2021 02:57:29 - INFO - __main__ - Step 75578: {'lr': 0.0002522447226960351, 'samples': 14510976, 'steps': 75577, 'loss/train': 1.7712455987930298} 08/31/2021 02:57:29 - INFO - __main__ - Step 75579: {'lr': 0.00025223941616510294, 'samples': 14511168, 'steps': 75578, 'loss/train': 2.036703109741211} 08/31/2021 02:57:30 - INFO - __main__ - Step 75580: {'lr': 0.00025223410963316176, 'samples': 14511360, 'steps': 75579, 'loss/train': 1.5213702917099} 08/31/2021 02:57:31 - INFO - __main__ - Step 75581: {'lr': 0.0002522288031002139, 'samples': 14511552, 'steps': 75580, 'loss/train': 0.1437140852212906} 08/31/2021 02:57:32 - INFO - __main__ - Step 75582: {'lr': 0.00025222349656626184, 'samples': 14511744, 'steps': 75581, 'loss/train': 0.8007624745368958} 08/31/2021 02:57:32 - INFO - __main__ - Step 75583: {'lr': 0.0002522181900313078, 'samples': 14511936, 'steps': 75582, 'loss/train': 0.876829981803894} 08/31/2021 02:57:32 - INFO - __main__ - Step 75584: {'lr': 0.0002522128834953543, 'samples': 14512128, 'steps': 75583, 'loss/train': 1.4058910608291626} 08/31/2021 02:57:33 - INFO - __main__ - Step 75585: {'lr': 0.00025220757695840375, 'samples': 14512320, 'steps': 75584, 'loss/train': 1.1054025888442993} 08/31/2021 02:57:35 - INFO - __main__ - Step 75586: {'lr': 0.00025220227042045847, 'samples': 14512512, 'steps': 75585, 'loss/train': 0.7929758429527283} 08/31/2021 02:57:36 - INFO - __main__ - Step 75587: {'lr': 0.00025219696388152093, 'samples': 14512704, 'steps': 75586, 'loss/train': 0.7295993566513062} 08/31/2021 02:57:36 - INFO - __main__ - Step 75588: {'lr': 0.00025219165734159345, 'samples': 14512896, 'steps': 75587, 'loss/train': 0.6099095940589905} 08/31/2021 02:57:36 - INFO - __main__ - Step 75589: {'lr': 0.00025218635080067844, 'samples': 14513088, 'steps': 75588, 'loss/train': 0.5325550436973572} 08/31/2021 02:57:37 - INFO - __main__ - Step 75590: {'lr': 0.00025218104425877826, 'samples': 14513280, 'steps': 75589, 'loss/train': 1.1648074388504028} 08/31/2021 02:57:38 - INFO - __main__ - Step 75591: {'lr': 0.00025217573771589536, 'samples': 14513472, 'steps': 75590, 'loss/train': 1.3158104419708252} 08/31/2021 02:57:38 - INFO - __main__ - Step 75592: {'lr': 0.00025217043117203207, 'samples': 14513664, 'steps': 75591, 'loss/train': 0.37850287556648254} 08/31/2021 02:57:39 - INFO - __main__ - Step 75593: {'lr': 0.0002521651246271909, 'samples': 14513856, 'steps': 75592, 'loss/train': 0.1823401153087616} 08/31/2021 02:57:39 - INFO - __main__ - Step 75594: {'lr': 0.0002521598180813741, 'samples': 14514048, 'steps': 75593, 'loss/train': 0.8425978422164917} 08/31/2021 02:57:40 - INFO - __main__ - Step 75595: {'lr': 0.00025215451153458415, 'samples': 14514240, 'steps': 75594, 'loss/train': 1.5010370016098022} 08/31/2021 02:57:41 - INFO - __main__ - Step 75596: {'lr': 0.0002521492049868234, 'samples': 14514432, 'steps': 75595, 'loss/train': 1.1465399265289307} 08/31/2021 02:57:41 - INFO - __main__ - Step 75597: {'lr': 0.0002521438984380942, 'samples': 14514624, 'steps': 75596, 'loss/train': 1.1596013307571411} 08/31/2021 02:57:42 - INFO - __main__ - Step 75598: {'lr': 0.00025213859188839903, 'samples': 14514816, 'steps': 75597, 'loss/train': 0.19690567255020142} 08/31/2021 02:57:42 - INFO - __main__ - Step 75599: {'lr': 0.0002521332853377403, 'samples': 14515008, 'steps': 75598, 'loss/train': 1.092085599899292} 08/31/2021 02:57:42 - INFO - __main__ - Step 75600: {'lr': 0.00025212797878612024, 'samples': 14515200, 'steps': 75599, 'loss/train': 0.2808372676372528} 08/31/2021 02:57:44 - INFO - __main__ - Step 75601: {'lr': 0.0002521226722335414, 'samples': 14515392, 'steps': 75600, 'loss/train': 1.4907203912734985} 08/31/2021 02:57:44 - INFO - __main__ - Step 75602: {'lr': 0.00025211736568000613, 'samples': 14515584, 'steps': 75601, 'loss/train': 1.341914415359497} 08/31/2021 02:57:45 - INFO - __main__ - Step 75603: {'lr': 0.00025211205912551685, 'samples': 14515776, 'steps': 75602, 'loss/train': 1.5076297521591187} 08/31/2021 02:57:45 - INFO - __main__ - Step 75604: {'lr': 0.0002521067525700758, 'samples': 14515968, 'steps': 75603, 'loss/train': 1.0855066776275635} 08/31/2021 02:57:45 - INFO - __main__ - Step 75605: {'lr': 0.00025210144601368553, 'samples': 14516160, 'steps': 75604, 'loss/train': 0.9977853894233704} 08/31/2021 02:57:46 - INFO - __main__ - Step 75606: {'lr': 0.00025209613945634837, 'samples': 14516352, 'steps': 75605, 'loss/train': 0.6374680995941162} 08/31/2021 02:57:48 - INFO - __main__ - Step 75607: {'lr': 0.0002520908328980667, 'samples': 14516544, 'steps': 75606, 'loss/train': 1.286719799041748} 08/31/2021 02:57:48 - INFO - __main__ - Step 75608: {'lr': 0.0002520855263388431, 'samples': 14516736, 'steps': 75607, 'loss/train': 0.7495183944702148} 08/31/2021 02:57:49 - INFO - __main__ - Step 75609: {'lr': 0.00025208021977867964, 'samples': 14516928, 'steps': 75608, 'loss/train': 1.3578312397003174} 08/31/2021 02:57:49 - INFO - __main__ - Step 75610: {'lr': 0.00025207491321757884, 'samples': 14517120, 'steps': 75609, 'loss/train': 1.6958248615264893} 08/31/2021 02:57:49 - INFO - __main__ - Step 75611: {'lr': 0.0002520696066555432, 'samples': 14517312, 'steps': 75610, 'loss/train': 0.945141077041626} 08/31/2021 02:57:51 - INFO - __main__ - Step 75612: {'lr': 0.0002520643000925749, 'samples': 14517504, 'steps': 75611, 'loss/train': 0.7832516431808472} 08/31/2021 02:57:52 - INFO - __main__ - Step 75613: {'lr': 0.0002520589935286766, 'samples': 14517696, 'steps': 75612, 'loss/train': 1.217359185218811} 08/31/2021 02:57:52 - INFO - __main__ - Step 75614: {'lr': 0.00025205368696385046, 'samples': 14517888, 'steps': 75613, 'loss/train': 0.09254781156778336} 08/31/2021 02:57:53 - INFO - __main__ - Step 75615: {'lr': 0.0002520483803980991, 'samples': 14518080, 'steps': 75614, 'loss/train': 5.934779167175293} 08/31/2021 02:57:53 - INFO - __main__ - Step 75616: {'lr': 0.0002520430738314246, 'samples': 14518272, 'steps': 75615, 'loss/train': 0.8820176124572754} 08/31/2021 02:57:53 - INFO - __main__ - Step 75617: {'lr': 0.0002520377672638296, 'samples': 14518464, 'steps': 75616, 'loss/train': 0.31806397438049316} 08/31/2021 02:57:55 - INFO - __main__ - Step 75618: {'lr': 0.0002520324606953164, 'samples': 14518656, 'steps': 75617, 'loss/train': 1.766912579536438} 08/31/2021 02:57:55 - INFO - __main__ - Step 75619: {'lr': 0.0002520271541258874, 'samples': 14518848, 'steps': 75618, 'loss/train': 0.1524791419506073} 08/31/2021 02:57:56 - INFO - __main__ - Step 75620: {'lr': 0.000252021847555545, 'samples': 14519040, 'steps': 75619, 'loss/train': 0.9401299357414246} 08/31/2021 02:57:56 - INFO - __main__ - Step 75621: {'lr': 0.00025201654098429163, 'samples': 14519232, 'steps': 75620, 'loss/train': 1.0889581441879272} 08/31/2021 02:57:56 - INFO - __main__ - Step 75622: {'lr': 0.0002520112344121296, 'samples': 14519424, 'steps': 75621, 'loss/train': 0.6149852871894836} 08/31/2021 02:57:58 - INFO - __main__ - Step 75623: {'lr': 0.00025200592783906136, 'samples': 14519616, 'steps': 75622, 'loss/train': 1.6944489479064941} 08/31/2021 02:57:58 - INFO - __main__ - Step 75624: {'lr': 0.00025200062126508923, 'samples': 14519808, 'steps': 75623, 'loss/train': 1.4725767374038696} 08/31/2021 02:57:59 - INFO - __main__ - Step 75625: {'lr': 0.0002519953146902157, 'samples': 14520000, 'steps': 75624, 'loss/train': 1.0411628484725952} 08/31/2021 02:57:59 - INFO - __main__ - Step 75626: {'lr': 0.00025199000811444304, 'samples': 14520192, 'steps': 75625, 'loss/train': 1.5837795734405518} 08/31/2021 02:57:59 - INFO - __main__ - Step 75627: {'lr': 0.00025198470153777375, 'samples': 14520384, 'steps': 75626, 'loss/train': 0.32971739768981934} 08/31/2021 02:58:01 - INFO - __main__ - Step 75628: {'lr': 0.00025197939496021026, 'samples': 14520576, 'steps': 75627, 'loss/train': 1.2305585145950317} 08/31/2021 02:58:01 - INFO - __main__ - Step 75629: {'lr': 0.00025197408838175485, 'samples': 14520768, 'steps': 75628, 'loss/train': 0.9359213709831238} 08/31/2021 02:58:02 - INFO - __main__ - Step 75630: {'lr': 0.0002519687818024099, 'samples': 14520960, 'steps': 75629, 'loss/train': 1.2763323783874512} 08/31/2021 02:58:02 - INFO - __main__ - Step 75631: {'lr': 0.0002519634752221778, 'samples': 14521152, 'steps': 75630, 'loss/train': 1.129970669746399} 08/31/2021 02:58:02 - INFO - __main__ - Step 75632: {'lr': 0.00025195816864106107, 'samples': 14521344, 'steps': 75631, 'loss/train': 1.069182276725769} 08/31/2021 02:58:04 - INFO - __main__ - Step 75633: {'lr': 0.00025195286205906205, 'samples': 14521536, 'steps': 75632, 'loss/train': 1.579905390739441} 08/31/2021 02:58:04 - INFO - __main__ - Step 75634: {'lr': 0.00025194755547618304, 'samples': 14521728, 'steps': 75633, 'loss/train': 0.6601301431655884} 08/31/2021 02:58:05 - INFO - __main__ - Step 75635: {'lr': 0.00025194224889242653, 'samples': 14521920, 'steps': 75634, 'loss/train': 1.2424213886260986} 08/31/2021 02:58:05 - INFO - __main__ - Step 75636: {'lr': 0.00025193694230779486, 'samples': 14522112, 'steps': 75635, 'loss/train': 1.2697927951812744} 08/31/2021 02:58:05 - INFO - __main__ - Step 75637: {'lr': 0.0002519316357222904, 'samples': 14522304, 'steps': 75636, 'loss/train': 1.2872189283370972} 08/31/2021 02:58:07 - INFO - __main__ - Step 75638: {'lr': 0.00025192632913591554, 'samples': 14522496, 'steps': 75637, 'loss/train': 1.7149218320846558} 08/31/2021 02:58:08 - INFO - __main__ - Step 75639: {'lr': 0.00025192102254867284, 'samples': 14522688, 'steps': 75638, 'loss/train': 1.4415770769119263} 08/31/2021 02:58:08 - INFO - __main__ - Step 75640: {'lr': 0.00025191571596056445, 'samples': 14522880, 'steps': 75639, 'loss/train': 1.246580719947815} 08/31/2021 02:58:08 - INFO - __main__ - Step 75641: {'lr': 0.0002519104093715929, 'samples': 14523072, 'steps': 75640, 'loss/train': 0.9323390126228333} 08/31/2021 02:58:09 - INFO - __main__ - Step 75642: {'lr': 0.0002519051027817606, 'samples': 14523264, 'steps': 75641, 'loss/train': 1.2116155624389648} 08/31/2021 02:58:09 - INFO - __main__ - Step 75643: {'lr': 0.00025189979619106976, 'samples': 14523456, 'steps': 75642, 'loss/train': 2.0366249084472656} 08/31/2021 02:58:11 - INFO - __main__ - Step 75644: {'lr': 0.00025189448959952304, 'samples': 14523648, 'steps': 75643, 'loss/train': 1.3583189249038696} 08/31/2021 02:58:11 - INFO - __main__ - Step 75645: {'lr': 0.0002518891830071226, 'samples': 14523840, 'steps': 75644, 'loss/train': 0.09810593724250793} 08/31/2021 02:58:12 - INFO - __main__ - Step 75646: {'lr': 0.00025188387641387095, 'samples': 14524032, 'steps': 75645, 'loss/train': 1.3698327541351318} 08/31/2021 02:58:12 - INFO - __main__ - Step 75647: {'lr': 0.0002518785698197705, 'samples': 14524224, 'steps': 75646, 'loss/train': 1.3552770614624023} 08/31/2021 02:58:12 - INFO - __main__ - Step 75648: {'lr': 0.0002518732632248235, 'samples': 14524416, 'steps': 75647, 'loss/train': 1.3735625743865967} 08/31/2021 02:58:14 - INFO - __main__ - Step 75649: {'lr': 0.0002518679566290326, 'samples': 14524608, 'steps': 75648, 'loss/train': 1.0332412719726562} 08/31/2021 02:58:14 - INFO - __main__ - Step 75650: {'lr': 0.0002518626500323998, 'samples': 14524800, 'steps': 75649, 'loss/train': 1.264232873916626} 08/31/2021 02:58:15 - INFO - __main__ - Step 75651: {'lr': 0.0002518573434349279, 'samples': 14524992, 'steps': 75650, 'loss/train': 1.187659502029419} 08/31/2021 02:58:15 - INFO - __main__ - Step 75652: {'lr': 0.000251852036836619, 'samples': 14525184, 'steps': 75651, 'loss/train': 1.6762666702270508} 08/31/2021 02:58:15 - INFO - __main__ - Step 75653: {'lr': 0.0002518467302374757, 'samples': 14525376, 'steps': 75652, 'loss/train': 0.9619335532188416} 08/31/2021 02:58:17 - INFO - __main__ - Step 75654: {'lr': 0.0002518414236375002, 'samples': 14525568, 'steps': 75653, 'loss/train': 1.4682302474975586} 08/31/2021 02:58:18 - INFO - __main__ - Step 75655: {'lr': 0.0002518361170366951, 'samples': 14525760, 'steps': 75654, 'loss/train': 0.8745130896568298} 08/31/2021 02:58:18 - INFO - __main__ - Step 75656: {'lr': 0.00025183081043506257, 'samples': 14525952, 'steps': 75655, 'loss/train': 1.0621976852416992} 08/31/2021 02:58:19 - INFO - __main__ - Step 75657: {'lr': 0.0002518255038326051, 'samples': 14526144, 'steps': 75656, 'loss/train': 0.5212317109107971} 08/31/2021 02:58:19 - INFO - __main__ - Step 75658: {'lr': 0.0002518201972293251, 'samples': 14526336, 'steps': 75657, 'loss/train': 1.6112663745880127} 08/31/2021 02:58:19 - INFO - __main__ - Step 75659: {'lr': 0.00025181489062522494, 'samples': 14526528, 'steps': 75658, 'loss/train': 1.231552004814148} 08/31/2021 02:58:21 - INFO - __main__ - Step 75660: {'lr': 0.00025180958402030713, 'samples': 14526720, 'steps': 75659, 'loss/train': 1.3596036434173584} 08/31/2021 02:58:21 - INFO - __main__ - Step 75661: {'lr': 0.00025180427741457385, 'samples': 14526912, 'steps': 75660, 'loss/train': 1.2960501909255981} 08/31/2021 02:58:22 - INFO - __main__ - Step 75662: {'lr': 0.0002517989708080276, 'samples': 14527104, 'steps': 75661, 'loss/train': 0.6880070567131042} 08/31/2021 02:58:22 - INFO - __main__ - Step 75663: {'lr': 0.00025179366420067075, 'samples': 14527296, 'steps': 75662, 'loss/train': 1.7851754426956177} 08/31/2021 02:58:22 - INFO - __main__ - Step 75664: {'lr': 0.00025178835759250576, 'samples': 14527488, 'steps': 75663, 'loss/train': 1.4866867065429688} 08/31/2021 02:58:24 - INFO - __main__ - Step 75665: {'lr': 0.0002517830509835349, 'samples': 14527680, 'steps': 75664, 'loss/train': 0.18798133730888367} 08/31/2021 02:58:25 - INFO - __main__ - Step 75666: {'lr': 0.00025177774437376067, 'samples': 14527872, 'steps': 75665, 'loss/train': 0.955909252166748} 08/31/2021 02:58:25 - INFO - __main__ - Step 75667: {'lr': 0.0002517724377631854, 'samples': 14528064, 'steps': 75666, 'loss/train': 0.9254905581474304} 08/31/2021 02:58:25 - INFO - __main__ - Step 75668: {'lr': 0.00025176713115181143, 'samples': 14528256, 'steps': 75667, 'loss/train': 1.2450237274169922} 08/31/2021 02:58:26 - INFO - __main__ - Step 75669: {'lr': 0.0002517618245396413, 'samples': 14528448, 'steps': 75668, 'loss/train': 1.4137554168701172} 08/31/2021 02:58:26 - INFO - __main__ - Step 75670: {'lr': 0.00025175651792667725, 'samples': 14528640, 'steps': 75669, 'loss/train': 0.025114011019468307} 08/31/2021 02:58:28 - INFO - __main__ - Step 75671: {'lr': 0.00025175121131292184, 'samples': 14528832, 'steps': 75670, 'loss/train': 1.3507201671600342} 08/31/2021 02:58:28 - INFO - __main__ - Step 75672: {'lr': 0.00025174590469837735, 'samples': 14529024, 'steps': 75671, 'loss/train': 0.9863811135292053} 08/31/2021 02:58:28 - INFO - __main__ - Step 75673: {'lr': 0.0002517405980830461, 'samples': 14529216, 'steps': 75672, 'loss/train': 1.6147769689559937} 08/31/2021 02:58:29 - INFO - __main__ - Step 75674: {'lr': 0.00025173529146693056, 'samples': 14529408, 'steps': 75673, 'loss/train': 1.3590792417526245} 08/31/2021 02:58:29 - INFO - __main__ - Step 75675: {'lr': 0.0002517299848500332, 'samples': 14529600, 'steps': 75674, 'loss/train': 1.351578712463379} 08/31/2021 02:58:31 - INFO - __main__ - Step 75676: {'lr': 0.00025172467823235634, 'samples': 14529792, 'steps': 75675, 'loss/train': 2.1084306240081787} 08/31/2021 02:58:31 - INFO - __main__ - Step 75677: {'lr': 0.0002517193716139023, 'samples': 14529984, 'steps': 75676, 'loss/train': 1.1355820894241333} 08/31/2021 02:58:32 - INFO - __main__ - Step 75678: {'lr': 0.0002517140649946736, 'samples': 14530176, 'steps': 75677, 'loss/train': 0.19560691714286804} 08/31/2021 02:58:32 - INFO - __main__ - Step 75679: {'lr': 0.0002517087583746725, 'samples': 14530368, 'steps': 75678, 'loss/train': 1.2274333238601685} 08/31/2021 02:58:32 - INFO - __main__ - Step 75680: {'lr': 0.00025170345175390147, 'samples': 14530560, 'steps': 75679, 'loss/train': 1.805202841758728} 08/31/2021 02:58:33 - INFO - __main__ - Step 75681: {'lr': 0.00025169814513236296, 'samples': 14530752, 'steps': 75680, 'loss/train': 0.9685713052749634} 08/31/2021 02:58:34 - INFO - __main__ - Step 75682: {'lr': 0.00025169283851005927, 'samples': 14530944, 'steps': 75681, 'loss/train': 1.1438034772872925} 08/31/2021 02:58:35 - INFO - __main__ - Step 75683: {'lr': 0.0002516875318869928, 'samples': 14531136, 'steps': 75682, 'loss/train': 0.8600901365280151} 08/31/2021 02:58:35 - INFO - __main__ - Step 75684: {'lr': 0.0002516822252631659, 'samples': 14531328, 'steps': 75683, 'loss/train': 1.1137412786483765} 08/31/2021 02:58:36 - INFO - __main__ - Step 75685: {'lr': 0.00025167691863858105, 'samples': 14531520, 'steps': 75684, 'loss/train': 1.372216820716858} 08/31/2021 02:58:36 - INFO - __main__ - Step 75686: {'lr': 0.0002516716120132406, 'samples': 14531712, 'steps': 75685, 'loss/train': 1.1191647052764893} 08/31/2021 02:58:37 - INFO - __main__ - Step 75687: {'lr': 0.00025166630538714694, 'samples': 14531904, 'steps': 75686, 'loss/train': 1.0305416584014893} 08/31/2021 02:58:38 - INFO - __main__ - Step 75688: {'lr': 0.0002516609987603025, 'samples': 14532096, 'steps': 75687, 'loss/train': 1.6848742961883545} 08/31/2021 02:58:38 - INFO - __main__ - Step 75689: {'lr': 0.00025165569213270975, 'samples': 14532288, 'steps': 75688, 'loss/train': 1.2863916158676147} 08/31/2021 02:58:38 - INFO - __main__ - Step 75690: {'lr': 0.0002516503855043708, 'samples': 14532480, 'steps': 75689, 'loss/train': 1.1177656650543213} 08/31/2021 02:58:39 - INFO - __main__ - Step 75691: {'lr': 0.00025164507887528824, 'samples': 14532672, 'steps': 75690, 'loss/train': 2.0359363555908203} 08/31/2021 02:58:41 - INFO - __main__ - Step 75692: {'lr': 0.00025163977224546447, 'samples': 14532864, 'steps': 75691, 'loss/train': 1.505253791809082} 08/31/2021 02:58:41 - INFO - __main__ - Step 75693: {'lr': 0.0002516344656149018, 'samples': 14533056, 'steps': 75692, 'loss/train': 1.0675352811813354} 08/31/2021 02:58:41 - INFO - __main__ - Step 75694: {'lr': 0.0002516291589836027, 'samples': 14533248, 'steps': 75693, 'loss/train': 1.3794424533843994} 08/31/2021 02:58:42 - INFO - __main__ - Step 75695: {'lr': 0.00025162385235156956, 'samples': 14533440, 'steps': 75694, 'loss/train': 1.046895980834961} 08/31/2021 02:58:42 - INFO - __main__ - Step 75696: {'lr': 0.00025161854571880473, 'samples': 14533632, 'steps': 75695, 'loss/train': 1.6166058778762817} 08/31/2021 02:58:44 - INFO - __main__ - Step 75697: {'lr': 0.0002516132390853106, 'samples': 14533824, 'steps': 75696, 'loss/train': 1.466314435005188} 08/31/2021 02:58:44 - INFO - __main__ - Step 75698: {'lr': 0.0002516079324510895, 'samples': 14534016, 'steps': 75697, 'loss/train': 1.0822203159332275} 08/31/2021 02:58:44 - INFO - __main__ - Step 75699: {'lr': 0.00025160262581614394, 'samples': 14534208, 'steps': 75698, 'loss/train': 0.9582127332687378} 08/31/2021 02:58:45 - INFO - __main__ - Step 75700: {'lr': 0.00025159731918047626, 'samples': 14534400, 'steps': 75699, 'loss/train': 1.270399808883667} 08/31/2021 02:58:45 - INFO - __main__ - Step 75701: {'lr': 0.0002515920125440888, 'samples': 14534592, 'steps': 75700, 'loss/train': 0.5701960921287537} 08/31/2021 02:58:47 - INFO - __main__ - Step 75702: {'lr': 0.0002515867059069841, 'samples': 14534784, 'steps': 75701, 'loss/train': 1.100197434425354} 08/31/2021 02:58:47 - INFO - __main__ - Step 75703: {'lr': 0.00025158139926916446, 'samples': 14534976, 'steps': 75702, 'loss/train': 1.1103910207748413} 08/31/2021 02:58:48 - INFO - __main__ - Step 75704: {'lr': 0.0002515760926306322, 'samples': 14535168, 'steps': 75703, 'loss/train': 1.8411526679992676} 08/31/2021 02:58:48 - INFO - __main__ - Step 75705: {'lr': 0.00025157078599138976, 'samples': 14535360, 'steps': 75704, 'loss/train': 1.0838611125946045} 08/31/2021 02:58:48 - INFO - __main__ - Step 75706: {'lr': 0.0002515654793514396, 'samples': 14535552, 'steps': 75705, 'loss/train': 1.7088725566864014} 08/31/2021 02:58:49 - INFO - __main__ - Step 75707: {'lr': 0.000251560172710784, 'samples': 14535744, 'steps': 75706, 'loss/train': 1.31050705909729} 08/31/2021 02:58:50 - INFO - __main__ - Step 75708: {'lr': 0.00025155486606942546, 'samples': 14535936, 'steps': 75707, 'loss/train': 0.6450015306472778} 08/31/2021 02:58:50 - INFO - __main__ - Step 75709: {'lr': 0.00025154955942736636, 'samples': 14536128, 'steps': 75708, 'loss/train': 1.2650880813598633} 08/31/2021 02:58:51 - INFO - __main__ - Step 75710: {'lr': 0.00025154425278460903, 'samples': 14536320, 'steps': 75709, 'loss/train': 1.6625430583953857} 08/31/2021 02:58:51 - INFO - __main__ - Step 75711: {'lr': 0.0002515389461411558, 'samples': 14536512, 'steps': 75710, 'loss/train': 1.4877630472183228} 08/31/2021 02:58:52 - INFO - __main__ - Step 75712: {'lr': 0.0002515336394970092, 'samples': 14536704, 'steps': 75711, 'loss/train': 1.4739395380020142} 08/31/2021 02:58:53 - INFO - __main__ - Step 75713: {'lr': 0.0002515283328521716, 'samples': 14536896, 'steps': 75712, 'loss/train': 1.3946082592010498} 08/31/2021 02:58:54 - INFO - __main__ - Step 75714: {'lr': 0.0002515230262066453, 'samples': 14537088, 'steps': 75713, 'loss/train': 1.1256849765777588} 08/31/2021 02:58:54 - INFO - __main__ - Step 75715: {'lr': 0.00025151771956043276, 'samples': 14537280, 'steps': 75714, 'loss/train': 0.4909224510192871} 08/31/2021 02:58:54 - INFO - __main__ - Step 75716: {'lr': 0.00025151241291353644, 'samples': 14537472, 'steps': 75715, 'loss/train': 0.34064340591430664} 08/31/2021 02:58:55 - INFO - __main__ - Step 75717: {'lr': 0.0002515071062659586, 'samples': 14537664, 'steps': 75716, 'loss/train': 1.3989629745483398} 08/31/2021 02:58:56 - INFO - __main__ - Step 75718: {'lr': 0.0002515017996177016, 'samples': 14537856, 'steps': 75717, 'loss/train': 1.0014996528625488} 08/31/2021 02:58:57 - INFO - __main__ - Step 75719: {'lr': 0.000251496492968768, 'samples': 14538048, 'steps': 75718, 'loss/train': 1.2237744331359863} 08/31/2021 02:58:57 - INFO - __main__ - Step 75720: {'lr': 0.0002514911863191601, 'samples': 14538240, 'steps': 75719, 'loss/train': 0.7975091934204102} 08/31/2021 02:58:57 - INFO - __main__ - Step 75721: {'lr': 0.0002514858796688802, 'samples': 14538432, 'steps': 75720, 'loss/train': 1.0703743696212769} 08/31/2021 02:58:58 - INFO - __main__ - Step 75722: {'lr': 0.00025148057301793085, 'samples': 14538624, 'steps': 75721, 'loss/train': 0.3354842960834503} 08/31/2021 02:58:59 - INFO - __main__ - Step 75723: {'lr': 0.00025147526636631445, 'samples': 14538816, 'steps': 75722, 'loss/train': 1.3858147859573364} 08/31/2021 02:59:00 - INFO - __main__ - Step 75724: {'lr': 0.0002514699597140332, 'samples': 14539008, 'steps': 75723, 'loss/train': 1.3342605829238892} 08/31/2021 02:59:00 - INFO - __main__ - Step 75725: {'lr': 0.00025146465306108965, 'samples': 14539200, 'steps': 75724, 'loss/train': 1.0906972885131836} 08/31/2021 02:59:00 - INFO - __main__ - Step 75726: {'lr': 0.0002514593464074862, 'samples': 14539392, 'steps': 75725, 'loss/train': 1.3920806646347046} 08/31/2021 02:59:01 - INFO - __main__ - Step 75727: {'lr': 0.00025145403975322515, 'samples': 14539584, 'steps': 75726, 'loss/train': 1.2926065921783447} 08/31/2021 02:59:02 - INFO - __main__ - Step 75728: {'lr': 0.000251448733098309, 'samples': 14539776, 'steps': 75727, 'loss/train': 0.9876756072044373} 08/31/2021 02:59:03 - INFO - __main__ - Step 75729: {'lr': 0.00025144342644273996, 'samples': 14539968, 'steps': 75728, 'loss/train': 0.8659155368804932} 08/31/2021 02:59:03 - INFO - __main__ - Step 75730: {'lr': 0.0002514381197865206, 'samples': 14540160, 'steps': 75729, 'loss/train': 0.7332167625427246} 08/31/2021 02:59:03 - INFO - __main__ - Step 75731: {'lr': 0.00025143281312965324, 'samples': 14540352, 'steps': 75730, 'loss/train': 1.5072646141052246} 08/31/2021 02:59:04 - INFO - __main__ - Step 75732: {'lr': 0.00025142750647214025, 'samples': 14540544, 'steps': 75731, 'loss/train': 1.2655971050262451} 08/31/2021 02:59:05 - INFO - __main__ - Step 75733: {'lr': 0.00025142219981398405, 'samples': 14540736, 'steps': 75732, 'loss/train': 1.4422972202301025} 08/31/2021 02:59:06 - INFO - __main__ - Step 75734: {'lr': 0.00025141689315518704, 'samples': 14540928, 'steps': 75733, 'loss/train': 1.5034759044647217} 08/31/2021 02:59:06 - INFO - __main__ - Step 75735: {'lr': 0.0002514115864957516, 'samples': 14541120, 'steps': 75734, 'loss/train': 1.197568416595459} 08/31/2021 02:59:07 - INFO - __main__ - Step 75736: {'lr': 0.00025140627983568015, 'samples': 14541312, 'steps': 75735, 'loss/train': 0.45381367206573486} 08/31/2021 02:59:07 - INFO - __main__ - Step 75737: {'lr': 0.000251400973174975, 'samples': 14541504, 'steps': 75736, 'loss/train': 1.0681072473526} 08/31/2021 02:59:07 - INFO - __main__ - Step 75738: {'lr': 0.0002513956665136387, 'samples': 14541696, 'steps': 75737, 'loss/train': 1.5615744590759277} 08/31/2021 02:59:09 - INFO - __main__ - Step 75739: {'lr': 0.00025139035985167335, 'samples': 14541888, 'steps': 75738, 'loss/train': 1.5769213438034058} 08/31/2021 02:59:09 - INFO - __main__ - Step 75740: {'lr': 0.00025138505318908163, 'samples': 14542080, 'steps': 75739, 'loss/train': 1.3391720056533813} 08/31/2021 02:59:10 - INFO - __main__ - Step 75741: {'lr': 0.0002513797465258658, 'samples': 14542272, 'steps': 75740, 'loss/train': 1.1606457233428955} 08/31/2021 02:59:10 - INFO - __main__ - Step 75742: {'lr': 0.00025137443986202827, 'samples': 14542464, 'steps': 75741, 'loss/train': 0.949670135974884} 08/31/2021 02:59:11 - INFO - __main__ - Step 75743: {'lr': 0.00025136913319757156, 'samples': 14542656, 'steps': 75742, 'loss/train': 0.2669329345226288} 08/31/2021 02:59:12 - INFO - __main__ - Step 75744: {'lr': 0.0002513638265324978, 'samples': 14542848, 'steps': 75743, 'loss/train': 1.043901801109314} 08/31/2021 02:59:12 - INFO - __main__ - Step 75745: {'lr': 0.0002513585198668096, 'samples': 14543040, 'steps': 75744, 'loss/train': 1.041359782218933} 08/31/2021 02:59:13 - INFO - __main__ - Step 75746: {'lr': 0.0002513532132005092, 'samples': 14543232, 'steps': 75745, 'loss/train': 0.8768002986907959} 08/31/2021 02:59:13 - INFO - __main__ - Step 75747: {'lr': 0.00025134790653359913, 'samples': 14543424, 'steps': 75746, 'loss/train': 1.4685618877410889} 08/31/2021 02:59:14 - INFO - __main__ - Step 75748: {'lr': 0.0002513425998660817, 'samples': 14543616, 'steps': 75747, 'loss/train': 1.540024757385254} 08/31/2021 02:59:15 - INFO - __main__ - Step 75749: {'lr': 0.0002513372931979593, 'samples': 14543808, 'steps': 75748, 'loss/train': 1.6047940254211426} 08/31/2021 02:59:16 - INFO - __main__ - Step 75750: {'lr': 0.00025133198652923437, 'samples': 14544000, 'steps': 75749, 'loss/train': 1.936698317527771} 08/31/2021 02:59:16 - INFO - __main__ - Step 75751: {'lr': 0.00025132667985990927, 'samples': 14544192, 'steps': 75750, 'loss/train': 1.1191328763961792} 08/31/2021 02:59:17 - INFO - __main__ - Step 75752: {'lr': 0.00025132137318998633, 'samples': 14544384, 'steps': 75751, 'loss/train': 1.588986873626709} 08/31/2021 02:59:17 - INFO - __main__ - Step 75753: {'lr': 0.00025131606651946796, 'samples': 14544576, 'steps': 75752, 'loss/train': 1.6410109996795654} 08/31/2021 02:59:19 - INFO - __main__ - Step 75754: {'lr': 0.00025131075984835674, 'samples': 14544768, 'steps': 75753, 'loss/train': 0.8227803111076355} 08/31/2021 02:59:19 - INFO - __main__ - Step 75755: {'lr': 0.00025130545317665474, 'samples': 14544960, 'steps': 75754, 'loss/train': 0.9083148241043091} 08/31/2021 02:59:20 - INFO - __main__ - Step 75756: {'lr': 0.00025130014650436467, 'samples': 14545152, 'steps': 75755, 'loss/train': 1.4091801643371582} 08/31/2021 02:59:20 - INFO - __main__ - Step 75757: {'lr': 0.0002512948398314887, 'samples': 14545344, 'steps': 75756, 'loss/train': 1.0386512279510498} 08/31/2021 02:59:20 - INFO - __main__ - Step 75758: {'lr': 0.0002512895331580293, 'samples': 14545536, 'steps': 75757, 'loss/train': 1.0826654434204102} 08/31/2021 02:59:21 - INFO - __main__ - Step 75759: {'lr': 0.0002512842264839889, 'samples': 14545728, 'steps': 75758, 'loss/train': 1.3481868505477905} 08/31/2021 02:59:22 - INFO - __main__ - Step 75760: {'lr': 0.0002512789198093698, 'samples': 14545920, 'steps': 75759, 'loss/train': 0.6854262948036194} 08/31/2021 02:59:23 - INFO - __main__ - Step 75761: {'lr': 0.00025127361313417445, 'samples': 14546112, 'steps': 75760, 'loss/train': 1.478756070137024} 08/31/2021 02:59:23 - INFO - __main__ - Step 75762: {'lr': 0.0002512683064584052, 'samples': 14546304, 'steps': 75761, 'loss/train': 2.013754367828369} 08/31/2021 02:59:23 - INFO - __main__ - Step 75763: {'lr': 0.00025126299978206457, 'samples': 14546496, 'steps': 75762, 'loss/train': 0.9797298908233643} 08/31/2021 02:59:24 - INFO - __main__ - Step 75764: {'lr': 0.00025125769310515477, 'samples': 14546688, 'steps': 75763, 'loss/train': 1.402586579322815} 08/31/2021 02:59:25 - INFO - __main__ - Step 75765: {'lr': 0.0002512523864276783, 'samples': 14546880, 'steps': 75764, 'loss/train': 1.0155138969421387} 08/31/2021 02:59:25 - INFO - __main__ - Step 75766: {'lr': 0.0002512470797496375, 'samples': 14547072, 'steps': 75765, 'loss/train': 1.412282943725586} 08/31/2021 02:59:26 - INFO - __main__ - Step 75767: {'lr': 0.0002512417730710348, 'samples': 14547264, 'steps': 75766, 'loss/train': 0.6303002834320068} 08/31/2021 02:59:26 - INFO - __main__ - Step 75768: {'lr': 0.00025123646639187256, 'samples': 14547456, 'steps': 75767, 'loss/train': 1.415141224861145} 08/31/2021 02:59:26 - INFO - __main__ - Step 75769: {'lr': 0.00025123115971215315, 'samples': 14547648, 'steps': 75768, 'loss/train': 0.6951045393943787} 08/31/2021 02:59:28 - INFO - __main__ - Step 75770: {'lr': 0.0002512258530318791, 'samples': 14547840, 'steps': 75769, 'loss/train': 1.1855370998382568} 08/31/2021 02:59:29 - INFO - __main__ - Step 75771: {'lr': 0.0002512205463510527, 'samples': 14548032, 'steps': 75770, 'loss/train': 2.0117669105529785} 08/31/2021 02:59:29 - INFO - __main__ - Step 75772: {'lr': 0.00025121523966967625, 'samples': 14548224, 'steps': 75771, 'loss/train': 2.235297918319702} 08/31/2021 02:59:30 - INFO - __main__ - Step 75773: {'lr': 0.00025120993298775223, 'samples': 14548416, 'steps': 75772, 'loss/train': 1.4802517890930176} 08/31/2021 02:59:30 - INFO - __main__ - Step 75774: {'lr': 0.00025120462630528307, 'samples': 14548608, 'steps': 75773, 'loss/train': 1.3349800109863281} 08/31/2021 02:59:30 - INFO - __main__ - Step 75775: {'lr': 0.00025119931962227116, 'samples': 14548800, 'steps': 75774, 'loss/train': 1.7870490550994873} 08/31/2021 02:59:32 - INFO - __main__ - Step 75776: {'lr': 0.00025119401293871883, 'samples': 14548992, 'steps': 75775, 'loss/train': 0.7353508472442627} 08/31/2021 02:59:32 - INFO - __main__ - Step 75777: {'lr': 0.0002511887062546285, 'samples': 14549184, 'steps': 75776, 'loss/train': 1.442308783531189} 08/31/2021 02:59:33 - INFO - __main__ - Step 75778: {'lr': 0.0002511833995700025, 'samples': 14549376, 'steps': 75777, 'loss/train': 1.1633236408233643} 08/31/2021 02:59:33 - INFO - __main__ - Step 75779: {'lr': 0.00025117809288484333, 'samples': 14549568, 'steps': 75778, 'loss/train': 1.0785852670669556} 08/31/2021 02:59:33 - INFO - __main__ - Step 75780: {'lr': 0.00025117278619915333, 'samples': 14549760, 'steps': 75779, 'loss/train': 1.9291809797286987} 08/31/2021 02:59:34 - INFO - __main__ - Step 75781: {'lr': 0.0002511674795129349, 'samples': 14549952, 'steps': 75780, 'loss/train': 1.3616167306900024} 08/31/2021 02:59:35 - INFO - __main__ - Step 75782: {'lr': 0.0002511621728261904, 'samples': 14550144, 'steps': 75781, 'loss/train': 1.2773560285568237} 08/31/2021 02:59:36 - INFO - __main__ - Step 75783: {'lr': 0.0002511568661389223, 'samples': 14550336, 'steps': 75782, 'loss/train': 0.14211948215961456} 08/31/2021 02:59:36 - INFO - __main__ - Step 75784: {'lr': 0.0002511515594511329, 'samples': 14550528, 'steps': 75783, 'loss/train': 1.4064534902572632} 08/31/2021 02:59:37 - INFO - __main__ - Step 75785: {'lr': 0.00025114625276282456, 'samples': 14550720, 'steps': 75784, 'loss/train': 1.1871411800384521} 08/31/2021 02:59:37 - INFO - __main__ - Step 75786: {'lr': 0.0002511409460739998, 'samples': 14550912, 'steps': 75785, 'loss/train': 0.8107979893684387} 08/31/2021 02:59:38 - INFO - __main__ - Step 75787: {'lr': 0.00025113563938466087, 'samples': 14551104, 'steps': 75786, 'loss/train': 1.4822850227355957} 08/31/2021 02:59:39 - INFO - __main__ - Step 75788: {'lr': 0.00025113033269481036, 'samples': 14551296, 'steps': 75787, 'loss/train': 0.5998745560646057} 08/31/2021 02:59:39 - INFO - __main__ - Step 75789: {'lr': 0.0002511250260044505, 'samples': 14551488, 'steps': 75788, 'loss/train': 1.4035804271697998} 08/31/2021 02:59:40 - INFO - __main__ - Step 75790: {'lr': 0.0002511197193135837, 'samples': 14551680, 'steps': 75789, 'loss/train': 2.0595712661743164} 08/31/2021 02:59:40 - INFO - __main__ - Step 75791: {'lr': 0.00025111441262221237, 'samples': 14551872, 'steps': 75790, 'loss/train': 1.3210574388504028} 08/31/2021 02:59:42 - INFO - __main__ - Step 75792: {'lr': 0.00025110910593033884, 'samples': 14552064, 'steps': 75791, 'loss/train': 0.7263615727424622} 08/31/2021 02:59:42 - INFO - __main__ - Step 75793: {'lr': 0.00025110379923796566, 'samples': 14552256, 'steps': 75792, 'loss/train': 1.4539167881011963} 08/31/2021 02:59:42 - INFO - __main__ - Step 75794: {'lr': 0.00025109849254509515, 'samples': 14552448, 'steps': 75793, 'loss/train': 0.30354586243629456} 08/31/2021 02:59:43 - INFO - __main__ - Step 75795: {'lr': 0.0002510931858517296, 'samples': 14552640, 'steps': 75794, 'loss/train': 0.057563815265893936} 08/31/2021 02:59:43 - INFO - __main__ - Step 75796: {'lr': 0.0002510878791578715, 'samples': 14552832, 'steps': 75795, 'loss/train': 1.7471867799758911} 08/31/2021 02:59:45 - INFO - __main__ - Step 75797: {'lr': 0.0002510825724635232, 'samples': 14553024, 'steps': 75796, 'loss/train': 1.9568039178848267} 08/31/2021 02:59:45 - INFO - __main__ - Step 75798: {'lr': 0.0002510772657686871, 'samples': 14553216, 'steps': 75797, 'loss/train': 1.4895384311676025} 08/31/2021 02:59:46 - INFO - __main__ - Step 75799: {'lr': 0.00025107195907336566, 'samples': 14553408, 'steps': 75798, 'loss/train': 1.336673617362976} 08/31/2021 02:59:46 - INFO - __main__ - Step 75800: {'lr': 0.0002510666523775612, 'samples': 14553600, 'steps': 75799, 'loss/train': 1.2377222776412964} 08/31/2021 02:59:46 - INFO - __main__ - Step 75801: {'lr': 0.0002510613456812761, 'samples': 14553792, 'steps': 75800, 'loss/train': 1.55010187625885} 08/31/2021 02:59:47 - INFO - __main__ - Step 75802: {'lr': 0.00025105603898451276, 'samples': 14553984, 'steps': 75801, 'loss/train': 1.4298404455184937} 08/31/2021 02:59:49 - INFO - __main__ - Step 75803: {'lr': 0.0002510507322872736, 'samples': 14554176, 'steps': 75802, 'loss/train': 1.061355710029602} 08/31/2021 02:59:49 - INFO - __main__ - Step 75804: {'lr': 0.000251045425589561, 'samples': 14554368, 'steps': 75803, 'loss/train': 1.4604665040969849} 08/31/2021 02:59:50 - INFO - __main__ - Step 75805: {'lr': 0.0002510401188913774, 'samples': 14554560, 'steps': 75804, 'loss/train': 1.2440433502197266} 08/31/2021 02:59:50 - INFO - __main__ - Step 75806: {'lr': 0.00025103481219272504, 'samples': 14554752, 'steps': 75805, 'loss/train': 1.3851139545440674} 08/31/2021 02:59:50 - INFO - __main__ - Step 75807: {'lr': 0.0002510295054936065, 'samples': 14554944, 'steps': 75806, 'loss/train': 1.7241730690002441} 08/31/2021 02:59:52 - INFO - __main__ - Step 75808: {'lr': 0.00025102419879402397, 'samples': 14555136, 'steps': 75807, 'loss/train': 1.2056970596313477} 08/31/2021 02:59:53 - INFO - __main__ - Step 75809: {'lr': 0.00025101889209398006, 'samples': 14555328, 'steps': 75808, 'loss/train': 1.4226605892181396} 08/31/2021 02:59:53 - INFO - __main__ - Step 75810: {'lr': 0.000251013585393477, 'samples': 14555520, 'steps': 75809, 'loss/train': 1.2417186498641968} 08/31/2021 02:59:53 - INFO - __main__ - Step 75811: {'lr': 0.00025100827869251724, 'samples': 14555712, 'steps': 75810, 'loss/train': 0.8419809341430664} 08/31/2021 02:59:54 - INFO - __main__ - Step 75812: {'lr': 0.00025100297199110317, 'samples': 14555904, 'steps': 75811, 'loss/train': 1.3252685070037842} 08/31/2021 02:59:54 - INFO - __main__ - Step 75813: {'lr': 0.0002509976652892372, 'samples': 14556096, 'steps': 75812, 'loss/train': 1.3871605396270752} 08/31/2021 02:59:55 - INFO - __main__ - Step 75814: {'lr': 0.0002509923585869216, 'samples': 14556288, 'steps': 75813, 'loss/train': 1.2917182445526123} 08/31/2021 02:59:56 - INFO - __main__ - Step 75815: {'lr': 0.00025098705188415896, 'samples': 14556480, 'steps': 75814, 'loss/train': 0.09032848477363586} 08/31/2021 02:59:56 - INFO - __main__ - Step 75816: {'lr': 0.0002509817451809515, 'samples': 14556672, 'steps': 75815, 'loss/train': 1.7117772102355957} 08/31/2021 02:59:57 - INFO - __main__ - Step 75817: {'lr': 0.0002509764384773018, 'samples': 14556864, 'steps': 75816, 'loss/train': 0.7510830163955688} 08/31/2021 02:59:57 - INFO - __main__ - Step 75818: {'lr': 0.00025097113177321203, 'samples': 14557056, 'steps': 75817, 'loss/train': 1.4840973615646362} 08/31/2021 02:59:58 - INFO - __main__ - Step 75819: {'lr': 0.0002509658250686847, 'samples': 14557248, 'steps': 75818, 'loss/train': 1.4043999910354614} 08/31/2021 02:59:59 - INFO - __main__ - Step 75820: {'lr': 0.00025096051836372217, 'samples': 14557440, 'steps': 75819, 'loss/train': 1.2666138410568237} 08/31/2021 02:59:59 - INFO - __main__ - Step 75821: {'lr': 0.00025095521165832685, 'samples': 14557632, 'steps': 75820, 'loss/train': 0.8681547045707703} 08/31/2021 03:00:00 - INFO - __main__ - Step 75822: {'lr': 0.00025094990495250116, 'samples': 14557824, 'steps': 75821, 'loss/train': 0.8772540092468262} 08/31/2021 03:00:00 - INFO - __main__ - Step 75823: {'lr': 0.0002509445982462475, 'samples': 14558016, 'steps': 75822, 'loss/train': 1.0124125480651855} 08/31/2021 03:00:01 - INFO - __main__ - Step 75824: {'lr': 0.00025093929153956814, 'samples': 14558208, 'steps': 75823, 'loss/train': 1.253002405166626} 08/31/2021 03:00:02 - INFO - __main__ - Step 75825: {'lr': 0.00025093398483246553, 'samples': 14558400, 'steps': 75824, 'loss/train': 1.3024781942367554} 08/31/2021 03:00:02 - INFO - __main__ - Step 75826: {'lr': 0.00025092867812494214, 'samples': 14558592, 'steps': 75825, 'loss/train': 1.5117583274841309} 08/31/2021 03:00:02 - INFO - __main__ - Step 75827: {'lr': 0.00025092337141700025, 'samples': 14558784, 'steps': 75826, 'loss/train': 1.289764165878296} 08/31/2021 03:00:03 - INFO - __main__ - Step 75828: {'lr': 0.0002509180647086423, 'samples': 14558976, 'steps': 75827, 'loss/train': 1.0282286405563354} 08/31/2021 03:00:04 - INFO - __main__ - Step 75829: {'lr': 0.0002509127579998707, 'samples': 14559168, 'steps': 75828, 'loss/train': 1.579141616821289} 08/31/2021 03:00:05 - INFO - __main__ - Step 75830: {'lr': 0.00025090745129068795, 'samples': 14559360, 'steps': 75829, 'loss/train': 1.3165240287780762} 08/31/2021 03:00:05 - INFO - __main__ - Step 75831: {'lr': 0.0002509021445810962, 'samples': 14559552, 'steps': 75830, 'loss/train': 1.0664622783660889} 08/31/2021 03:00:05 - INFO - __main__ - Step 75832: {'lr': 0.0002508968378710979, 'samples': 14559744, 'steps': 75831, 'loss/train': 1.5927691459655762} 08/31/2021 03:00:06 - INFO - __main__ - Step 75833: {'lr': 0.00025089153116069555, 'samples': 14559936, 'steps': 75832, 'loss/train': 0.6603018045425415} 08/31/2021 03:00:07 - INFO - __main__ - Step 75834: {'lr': 0.00025088622444989153, 'samples': 14560128, 'steps': 75833, 'loss/train': 1.372585654258728} 08/31/2021 03:00:08 - INFO - __main__ - Step 75835: {'lr': 0.00025088091773868814, 'samples': 14560320, 'steps': 75834, 'loss/train': 1.203762173652649} 08/31/2021 03:00:08 - INFO - __main__ - Step 75836: {'lr': 0.0002508756110270878, 'samples': 14560512, 'steps': 75835, 'loss/train': 1.2516173124313354} 08/31/2021 03:00:08 - INFO - __main__ - Step 75837: {'lr': 0.0002508703043150931, 'samples': 14560704, 'steps': 75836, 'loss/train': 1.3394901752471924} 08/31/2021 03:00:09 - INFO - __main__ - Step 75838: {'lr': 0.00025086499760270607, 'samples': 14560896, 'steps': 75837, 'loss/train': 1.5205535888671875} 08/31/2021 03:00:10 - INFO - __main__ - Step 75839: {'lr': 0.00025085969088992934, 'samples': 14561088, 'steps': 75838, 'loss/train': 1.0591930150985718} 08/31/2021 03:00:11 - INFO - __main__ - Step 75840: {'lr': 0.0002508543841767653, 'samples': 14561280, 'steps': 75839, 'loss/train': 0.9622746706008911} 08/31/2021 03:00:11 - INFO - __main__ - Step 75841: {'lr': 0.00025084907746321616, 'samples': 14561472, 'steps': 75840, 'loss/train': 1.4378982782363892} 08/31/2021 03:00:11 - INFO - __main__ - Step 75842: {'lr': 0.0002508437707492845, 'samples': 14561664, 'steps': 75841, 'loss/train': 1.0707364082336426} 08/31/2021 03:00:12 - INFO - __main__ - Step 75843: {'lr': 0.0002508384640349727, 'samples': 14561856, 'steps': 75842, 'loss/train': 1.347192645072937} 08/31/2021 03:00:13 - INFO - __main__ - Step 75844: {'lr': 0.00025083315732028305, 'samples': 14562048, 'steps': 75843, 'loss/train': 1.8152223825454712} 08/31/2021 03:00:14 - INFO - __main__ - Step 75845: {'lr': 0.000250827850605218, 'samples': 14562240, 'steps': 75844, 'loss/train': 1.4448946714401245} 08/31/2021 03:00:14 - INFO - __main__ - Step 75846: {'lr': 0.00025082254388977994, 'samples': 14562432, 'steps': 75845, 'loss/train': 1.2549272775650024} 08/31/2021 03:00:14 - INFO - __main__ - Step 75847: {'lr': 0.00025081723717397124, 'samples': 14562624, 'steps': 75846, 'loss/train': 1.1160913705825806} 08/31/2021 03:00:15 - INFO - __main__ - Step 75848: {'lr': 0.00025081193045779434, 'samples': 14562816, 'steps': 75847, 'loss/train': 1.557185173034668} 08/31/2021 03:00:15 - INFO - __main__ - Step 75849: {'lr': 0.0002508066237412516, 'samples': 14563008, 'steps': 75848, 'loss/train': 1.268998146057129} 08/31/2021 03:00:16 - INFO - __main__ - Step 75850: {'lr': 0.0002508013170243454, 'samples': 14563200, 'steps': 75849, 'loss/train': 1.4777578115463257} 08/31/2021 03:00:17 - INFO - __main__ - Step 75851: {'lr': 0.0002507960103070781, 'samples': 14563392, 'steps': 75850, 'loss/train': 1.6470609903335571} 08/31/2021 03:00:17 - INFO - __main__ - Step 75852: {'lr': 0.00025079070358945214, 'samples': 14563584, 'steps': 75851, 'loss/train': 1.272840142250061} 08/31/2021 03:00:18 - INFO - __main__ - Step 75853: {'lr': 0.0002507853968714699, 'samples': 14563776, 'steps': 75852, 'loss/train': 1.419264793395996} 08/31/2021 03:00:18 - INFO - __main__ - Step 75854: {'lr': 0.0002507800901531338, 'samples': 14563968, 'steps': 75853, 'loss/train': 1.7938487529754639} 08/31/2021 03:00:20 - INFO - __main__ - Step 75855: {'lr': 0.00025077478343444616, 'samples': 14564160, 'steps': 75854, 'loss/train': 1.3830983638763428} 08/31/2021 03:00:20 - INFO - __main__ - Step 75856: {'lr': 0.00025076947671540947, 'samples': 14564352, 'steps': 75855, 'loss/train': 1.122881293296814} 08/31/2021 03:00:21 - INFO - __main__ - Step 75857: {'lr': 0.0002507641699960261, 'samples': 14564544, 'steps': 75856, 'loss/train': 1.4220210313796997} 08/31/2021 03:00:21 - INFO - __main__ - Step 75858: {'lr': 0.00025075886327629833, 'samples': 14564736, 'steps': 75857, 'loss/train': 1.084840178489685} 08/31/2021 03:00:21 - INFO - __main__ - Step 75859: {'lr': 0.0002507535565562286, 'samples': 14564928, 'steps': 75858, 'loss/train': 1.8591535091400146} 08/31/2021 03:00:23 - INFO - __main__ - Step 75860: {'lr': 0.0002507482498358194, 'samples': 14565120, 'steps': 75859, 'loss/train': 1.7147691249847412} 08/31/2021 03:00:23 - INFO - __main__ - Step 75861: {'lr': 0.000250742943115073, 'samples': 14565312, 'steps': 75860, 'loss/train': 0.869170606136322} 08/31/2021 03:00:24 - INFO - __main__ - Step 75862: {'lr': 0.0002507376363939918, 'samples': 14565504, 'steps': 75861, 'loss/train': 1.3528828620910645} 08/31/2021 03:00:24 - INFO - __main__ - Step 75863: {'lr': 0.00025073232967257834, 'samples': 14565696, 'steps': 75862, 'loss/train': 0.7948334813117981} 08/31/2021 03:00:24 - INFO - __main__ - Step 75864: {'lr': 0.00025072702295083493, 'samples': 14565888, 'steps': 75863, 'loss/train': 1.4271481037139893} 08/31/2021 03:00:26 - INFO - __main__ - Step 75865: {'lr': 0.0002507217162287638, 'samples': 14566080, 'steps': 75864, 'loss/train': 0.921919047832489} 08/31/2021 03:00:27 - INFO - __main__ - Step 75866: {'lr': 0.00025071640950636757, 'samples': 14566272, 'steps': 75865, 'loss/train': 1.8082077503204346} 08/31/2021 03:00:27 - INFO - __main__ - Step 75867: {'lr': 0.0002507111027836485, 'samples': 14566464, 'steps': 75866, 'loss/train': 1.7038010358810425} 08/31/2021 03:00:27 - INFO - __main__ - Step 75868: {'lr': 0.000250705796060609, 'samples': 14566656, 'steps': 75867, 'loss/train': 0.692109227180481} 08/31/2021 03:00:28 - INFO - __main__ - Step 75869: {'lr': 0.0002507004893372515, 'samples': 14566848, 'steps': 75868, 'loss/train': 1.170361042022705} 08/31/2021 03:00:28 - INFO - __main__ - Step 75870: {'lr': 0.00025069518261357844, 'samples': 14567040, 'steps': 75869, 'loss/train': 1.3074791431427002} 08/31/2021 03:00:29 - INFO - __main__ - Step 75871: {'lr': 0.0002506898758895921, 'samples': 14567232, 'steps': 75870, 'loss/train': 1.3525515794754028} 08/31/2021 03:00:30 - INFO - __main__ - Step 75872: {'lr': 0.00025068456916529485, 'samples': 14567424, 'steps': 75871, 'loss/train': 1.1702443361282349} 08/31/2021 03:00:30 - INFO - __main__ - Step 75873: {'lr': 0.00025067926244068915, 'samples': 14567616, 'steps': 75872, 'loss/train': 1.0939478874206543} 08/31/2021 03:00:31 - INFO - __main__ - Step 75874: {'lr': 0.00025067395571577744, 'samples': 14567808, 'steps': 75873, 'loss/train': 1.562560796737671} 08/31/2021 03:00:31 - INFO - __main__ - Step 75875: {'lr': 0.00025066864899056204, 'samples': 14568000, 'steps': 75874, 'loss/train': 0.9119924306869507} 08/31/2021 03:00:33 - INFO - __main__ - Step 75876: {'lr': 0.00025066334226504533, 'samples': 14568192, 'steps': 75875, 'loss/train': 1.007000207901001} 08/31/2021 03:00:33 - INFO - __main__ - Step 75877: {'lr': 0.0002506580355392298, 'samples': 14568384, 'steps': 75876, 'loss/train': 0.40407758951187134} 08/31/2021 03:00:33 - INFO - __main__ - Step 75878: {'lr': 0.0002506527288131177, 'samples': 14568576, 'steps': 75877, 'loss/train': 1.4800444841384888} 08/31/2021 03:00:34 - INFO - __main__ - Step 75879: {'lr': 0.0002506474220867115, 'samples': 14568768, 'steps': 75878, 'loss/train': 1.5883835554122925} 08/31/2021 03:00:34 - INFO - __main__ - Step 75880: {'lr': 0.00025064211536001356, 'samples': 14568960, 'steps': 75879, 'loss/train': 0.9291226863861084} 08/31/2021 03:00:36 - INFO - __main__ - Step 75881: {'lr': 0.00025063680863302636, 'samples': 14569152, 'steps': 75880, 'loss/train': 2.1818816661834717} 08/31/2021 03:00:36 - INFO - __main__ - Step 75882: {'lr': 0.00025063150190575217, 'samples': 14569344, 'steps': 75881, 'loss/train': 1.3646162748336792} 08/31/2021 03:00:37 - INFO - __main__ - Step 75883: {'lr': 0.0002506261951781935, 'samples': 14569536, 'steps': 75882, 'loss/train': 1.771425724029541} 08/31/2021 03:00:37 - INFO - __main__ - Step 75884: {'lr': 0.00025062088845035263, 'samples': 14569728, 'steps': 75883, 'loss/train': 0.7759379148483276} 08/31/2021 03:00:38 - INFO - __main__ - Step 75885: {'lr': 0.000250615581722232, 'samples': 14569920, 'steps': 75884, 'loss/train': 0.08033515512943268} 08/31/2021 03:00:40 - INFO - __main__ - Step 75886: {'lr': 0.000250610274993834, 'samples': 14570112, 'steps': 75885, 'loss/train': 1.2912876605987549} 08/31/2021 03:00:40 - INFO - __main__ - Step 75887: {'lr': 0.000250604968265161, 'samples': 14570304, 'steps': 75886, 'loss/train': 4.253546714782715} 08/31/2021 03:00:40 - INFO - __main__ - Step 75888: {'lr': 0.0002505996615362154, 'samples': 14570496, 'steps': 75887, 'loss/train': 1.0092885494232178} 08/31/2021 03:00:41 - INFO - __main__ - Step 75889: {'lr': 0.0002505943548069996, 'samples': 14570688, 'steps': 75888, 'loss/train': 0.05251547694206238} 08/31/2021 03:00:41 - INFO - __main__ - Step 75890: {'lr': 0.00025058904807751604, 'samples': 14570880, 'steps': 75889, 'loss/train': 1.50080406665802} 08/31/2021 03:00:41 - INFO - __main__ - Step 75891: {'lr': 0.00025058374134776705, 'samples': 14571072, 'steps': 75890, 'loss/train': 1.3320187330245972} 08/31/2021 03:00:42 - INFO - __main__ - Step 75892: {'lr': 0.00025057843461775503, 'samples': 14571264, 'steps': 75891, 'loss/train': 0.09447329491376877} 08/31/2021 03:00:44 - INFO - __main__ - Step 75893: {'lr': 0.00025057312788748237, 'samples': 14571456, 'steps': 75892, 'loss/train': 0.12614786624908447} 08/31/2021 03:00:44 - INFO - __main__ - Step 75894: {'lr': 0.0002505678211569515, 'samples': 14571648, 'steps': 75893, 'loss/train': 0.04032263532280922} 08/31/2021 03:00:45 - INFO - __main__ - Step 75895: {'lr': 0.0002505625144261647, 'samples': 14571840, 'steps': 75894, 'loss/train': 0.9627196192741394} 08/31/2021 03:00:45 - INFO - __main__ - Step 75896: {'lr': 0.0002505572076951245, 'samples': 14572032, 'steps': 75895, 'loss/train': 0.037912048399448395} 08/31/2021 03:00:45 - INFO - __main__ - Step 75897: {'lr': 0.0002505519009638332, 'samples': 14572224, 'steps': 75896, 'loss/train': 1.2917068004608154} 08/31/2021 03:00:47 - INFO - __main__ - Step 75898: {'lr': 0.0002505465942322933, 'samples': 14572416, 'steps': 75897, 'loss/train': 1.594099760055542} 08/31/2021 03:00:47 - INFO - __main__ - Step 75899: {'lr': 0.00025054128750050703, 'samples': 14572608, 'steps': 75898, 'loss/train': 0.36263757944107056} 08/31/2021 03:00:48 - INFO - __main__ - Step 75900: {'lr': 0.0002505359807684769, 'samples': 14572800, 'steps': 75899, 'loss/train': 0.08425389975309372} 08/31/2021 03:00:48 - INFO - __main__ - Step 75901: {'lr': 0.0002505306740362052, 'samples': 14572992, 'steps': 75900, 'loss/train': 1.0330514907836914} 08/31/2021 03:00:49 - INFO - __main__ - Step 75902: {'lr': 0.00025052536730369444, 'samples': 14573184, 'steps': 75901, 'loss/train': 1.9334172010421753} 08/31/2021 03:00:49 - INFO - __main__ - Step 75903: {'lr': 0.00025052006057094703, 'samples': 14573376, 'steps': 75902, 'loss/train': 1.3767691850662231} 08/31/2021 03:00:50 - INFO - __main__ - Step 75904: {'lr': 0.0002505147538379652, 'samples': 14573568, 'steps': 75903, 'loss/train': 0.38717567920684814} 08/31/2021 03:00:51 - INFO - __main__ - Step 75905: {'lr': 0.0002505094471047515, 'samples': 14573760, 'steps': 75904, 'loss/train': 0.7120769619941711} 08/31/2021 03:00:51 - INFO - __main__ - Step 75906: {'lr': 0.00025050414037130814, 'samples': 14573952, 'steps': 75905, 'loss/train': 1.2021766901016235} 08/31/2021 03:00:51 - INFO - __main__ - Step 75907: {'lr': 0.0002504988336376377, 'samples': 14574144, 'steps': 75906, 'loss/train': 1.3907437324523926} 08/31/2021 03:00:52 - INFO - __main__ - Step 75908: {'lr': 0.00025049352690374244, 'samples': 14574336, 'steps': 75907, 'loss/train': 1.3873800039291382} 08/31/2021 03:00:53 - INFO - __main__ - Step 75909: {'lr': 0.00025048822016962487, 'samples': 14574528, 'steps': 75908, 'loss/train': 1.103470802307129} 08/31/2021 03:00:54 - INFO - __main__ - Step 75910: {'lr': 0.0002504829134352872, 'samples': 14574720, 'steps': 75909, 'loss/train': 1.3539698123931885} 08/31/2021 03:00:54 - INFO - __main__ - Step 75911: {'lr': 0.0002504776067007321, 'samples': 14574912, 'steps': 75910, 'loss/train': 0.9081496596336365} 08/31/2021 03:00:54 - INFO - __main__ - Step 75912: {'lr': 0.0002504722999659617, 'samples': 14575104, 'steps': 75911, 'loss/train': 0.9098060131072998} 08/31/2021 03:00:55 - INFO - __main__ - Step 75913: {'lr': 0.00025046699323097855, 'samples': 14575296, 'steps': 75912, 'loss/train': 1.348695158958435} 08/31/2021 03:00:57 - INFO - __main__ - Step 75914: {'lr': 0.0002504616864957849, 'samples': 14575488, 'steps': 75913, 'loss/train': 0.5518211722373962} 08/31/2021 03:00:58 - INFO - __main__ - Step 75915: {'lr': 0.00025045637976038327, 'samples': 14575680, 'steps': 75914, 'loss/train': 0.897678017616272} 08/31/2021 03:00:58 - INFO - __main__ - Step 75916: {'lr': 0.000250451073024776, 'samples': 14575872, 'steps': 75915, 'loss/train': 0.9874606728553772} 08/31/2021 03:00:58 - INFO - __main__ - Step 75917: {'lr': 0.00025044576628896546, 'samples': 14576064, 'steps': 75916, 'loss/train': 1.448007345199585} 08/31/2021 03:00:59 - INFO - __main__ - Step 75918: {'lr': 0.0002504404595529541, 'samples': 14576256, 'steps': 75917, 'loss/train': 1.5368832349777222} 08/31/2021 03:01:00 - INFO - __main__ - Step 75919: {'lr': 0.0002504351528167443, 'samples': 14576448, 'steps': 75918, 'loss/train': 1.3465778827667236} 08/31/2021 03:01:00 - INFO - __main__ - Step 75920: {'lr': 0.0002504298460803383, 'samples': 14576640, 'steps': 75919, 'loss/train': 1.2524324655532837} 08/31/2021 03:01:01 - INFO - __main__ - Step 75921: {'lr': 0.00025042453934373874, 'samples': 14576832, 'steps': 75920, 'loss/train': 1.0645151138305664} 08/31/2021 03:01:01 - INFO - __main__ - Step 75922: {'lr': 0.0002504192326069478, 'samples': 14577024, 'steps': 75921, 'loss/train': 1.5135300159454346} 08/31/2021 03:01:01 - INFO - __main__ - Step 75923: {'lr': 0.0002504139258699681, 'samples': 14577216, 'steps': 75922, 'loss/train': 0.6843339800834656} 08/31/2021 03:01:03 - INFO - __main__ - Step 75924: {'lr': 0.00025040861913280175, 'samples': 14577408, 'steps': 75923, 'loss/train': 0.6948888301849365} 08/31/2021 03:01:03 - INFO - __main__ - Step 75925: {'lr': 0.0002504033123954513, 'samples': 14577600, 'steps': 75924, 'loss/train': 1.6244845390319824} 08/31/2021 03:01:04 - INFO - __main__ - Step 75926: {'lr': 0.0002503980056579192, 'samples': 14577792, 'steps': 75925, 'loss/train': 1.4745160341262817} 08/31/2021 03:01:04 - INFO - __main__ - Step 75927: {'lr': 0.00025039269892020773, 'samples': 14577984, 'steps': 75926, 'loss/train': 1.0820456743240356} 08/31/2021 03:01:04 - INFO - __main__ - Step 75928: {'lr': 0.00025038739218231925, 'samples': 14578176, 'steps': 75927, 'loss/train': 0.8788448572158813} 08/31/2021 03:01:06 - INFO - __main__ - Step 75929: {'lr': 0.00025038208544425633, 'samples': 14578368, 'steps': 75928, 'loss/train': 1.3586047887802124} 08/31/2021 03:01:06 - INFO - __main__ - Step 75930: {'lr': 0.00025037677870602123, 'samples': 14578560, 'steps': 75929, 'loss/train': 0.5201501250267029} 08/31/2021 03:01:07 - INFO - __main__ - Step 75931: {'lr': 0.0002503714719676163, 'samples': 14578752, 'steps': 75930, 'loss/train': 1.2288802862167358} 08/31/2021 03:01:07 - INFO - __main__ - Step 75932: {'lr': 0.000250366165229044, 'samples': 14578944, 'steps': 75931, 'loss/train': 0.8866162896156311} 08/31/2021 03:01:07 - INFO - __main__ - Step 75933: {'lr': 0.0002503608584903067, 'samples': 14579136, 'steps': 75932, 'loss/train': 1.3835930824279785} 08/31/2021 03:01:09 - INFO - __main__ - Step 75934: {'lr': 0.0002503555517514069, 'samples': 14579328, 'steps': 75933, 'loss/train': 1.603975772857666} 08/31/2021 03:01:09 - INFO - __main__ - Step 75935: {'lr': 0.0002503502450123468, 'samples': 14579520, 'steps': 75934, 'loss/train': 1.5480504035949707} 08/31/2021 03:01:10 - INFO - __main__ - Step 75936: {'lr': 0.00025034493827312895, 'samples': 14579712, 'steps': 75935, 'loss/train': 1.11873459815979} 08/31/2021 03:01:10 - INFO - __main__ - Step 75937: {'lr': 0.00025033963153375555, 'samples': 14579904, 'steps': 75936, 'loss/train': 0.045341748744249344} 08/31/2021 03:01:10 - INFO - __main__ - Step 75938: {'lr': 0.0002503343247942292, 'samples': 14580096, 'steps': 75937, 'loss/train': 1.16111159324646} 08/31/2021 03:01:11 - INFO - __main__ - Step 75939: {'lr': 0.0002503290180545522, 'samples': 14580288, 'steps': 75938, 'loss/train': 0.7966912984848022} 08/31/2021 03:01:12 - INFO - __main__ - Step 75940: {'lr': 0.00025032371131472706, 'samples': 14580480, 'steps': 75939, 'loss/train': 0.7305633425712585} 08/31/2021 03:01:13 - INFO - __main__ - Step 75941: {'lr': 0.0002503184045747559, 'samples': 14580672, 'steps': 75940, 'loss/train': 0.9578276872634888} 08/31/2021 03:01:13 - INFO - __main__ - Step 75942: {'lr': 0.0002503130978346413, 'samples': 14580864, 'steps': 75941, 'loss/train': 1.1602567434310913} 08/31/2021 03:01:14 - INFO - __main__ - Step 75943: {'lr': 0.00025030779109438565, 'samples': 14581056, 'steps': 75942, 'loss/train': 0.4934826195240021} 08/31/2021 03:01:14 - INFO - __main__ - Step 75944: {'lr': 0.0002503024843539913, 'samples': 14581248, 'steps': 75943, 'loss/train': 1.3874866962432861} 08/31/2021 03:01:15 - INFO - __main__ - Step 75945: {'lr': 0.00025029717761346074, 'samples': 14581440, 'steps': 75944, 'loss/train': 1.525143027305603} 08/31/2021 03:01:16 - INFO - __main__ - Step 75946: {'lr': 0.0002502918708727962, 'samples': 14581632, 'steps': 75945, 'loss/train': 0.2808074653148651} 08/31/2021 03:01:16 - INFO - __main__ - Step 75947: {'lr': 0.0002502865641320002, 'samples': 14581824, 'steps': 75946, 'loss/train': 0.849748969078064} 08/31/2021 03:01:16 - INFO - __main__ - Step 75948: {'lr': 0.00025028125739107496, 'samples': 14582016, 'steps': 75947, 'loss/train': 0.9701616168022156} 08/31/2021 03:01:17 - INFO - __main__ - Step 75949: {'lr': 0.00025027595065002306, 'samples': 14582208, 'steps': 75948, 'loss/train': 1.2476249933242798} 08/31/2021 03:01:19 - INFO - __main__ - Step 75950: {'lr': 0.00025027064390884684, 'samples': 14582400, 'steps': 75949, 'loss/train': 1.256209373474121} 08/31/2021 03:01:19 - INFO - __main__ - Step 75951: {'lr': 0.0002502653371675487, 'samples': 14582592, 'steps': 75950, 'loss/train': 1.327075481414795} 08/31/2021 03:01:19 - INFO - __main__ - Step 75952: {'lr': 0.000250260030426131, 'samples': 14582784, 'steps': 75951, 'loss/train': 0.05561938136816025} 08/31/2021 03:01:20 - INFO - __main__ - Step 75953: {'lr': 0.0002502547236845961, 'samples': 14582976, 'steps': 75952, 'loss/train': 0.6782205104827881} 08/31/2021 03:01:20 - INFO - __main__ - Step 75954: {'lr': 0.00025024941694294634, 'samples': 14583168, 'steps': 75953, 'loss/train': 1.5158993005752563} 08/31/2021 03:01:22 - INFO - __main__ - Step 75955: {'lr': 0.00025024411020118433, 'samples': 14583360, 'steps': 75954, 'loss/train': 1.6508184671401978} 08/31/2021 03:01:22 - INFO - __main__ - Step 75956: {'lr': 0.0002502388034593122, 'samples': 14583552, 'steps': 75955, 'loss/train': 0.9318785667419434} 08/31/2021 03:01:22 - INFO - __main__ - Step 75957: {'lr': 0.00025023349671733256, 'samples': 14583744, 'steps': 75956, 'loss/train': 1.3750827312469482} 08/31/2021 03:01:23 - INFO - __main__ - Step 75958: {'lr': 0.0002502281899752478, 'samples': 14583936, 'steps': 75957, 'loss/train': 1.0974700450897217} 08/31/2021 03:01:23 - INFO - __main__ - Step 75959: {'lr': 0.00025022288323306, 'samples': 14584128, 'steps': 75958, 'loss/train': 1.380969524383545} 08/31/2021 03:01:25 - INFO - __main__ - Step 75960: {'lr': 0.0002502175764907719, 'samples': 14584320, 'steps': 75959, 'loss/train': 1.3868284225463867} 08/31/2021 03:01:25 - INFO - __main__ - Step 75961: {'lr': 0.0002502122697483858, 'samples': 14584512, 'steps': 75960, 'loss/train': 0.656322181224823} 08/31/2021 03:01:25 - INFO - __main__ - Step 75962: {'lr': 0.00025020696300590397, 'samples': 14584704, 'steps': 75961, 'loss/train': 1.142273187637329} 08/31/2021 03:01:26 - INFO - __main__ - Step 75963: {'lr': 0.0002502016562633289, 'samples': 14584896, 'steps': 75962, 'loss/train': 0.7585622668266296} 08/31/2021 03:01:26 - INFO - __main__ - Step 75964: {'lr': 0.000250196349520663, 'samples': 14585088, 'steps': 75963, 'loss/train': 1.274369239807129} 08/31/2021 03:01:28 - INFO - __main__ - Step 75965: {'lr': 0.0002501910427779087, 'samples': 14585280, 'steps': 75964, 'loss/train': 0.06582143157720566} 08/31/2021 03:01:29 - INFO - __main__ - Step 75966: {'lr': 0.00025018573603506817, 'samples': 14585472, 'steps': 75965, 'loss/train': 0.9547935724258423} 08/31/2021 03:01:29 - INFO - __main__ - Step 75967: {'lr': 0.000250180429292144, 'samples': 14585664, 'steps': 75966, 'loss/train': 1.784651756286621} 08/31/2021 03:01:29 - INFO - __main__ - Step 75968: {'lr': 0.00025017512254913853, 'samples': 14585856, 'steps': 75967, 'loss/train': 0.8861294984817505} 08/31/2021 03:01:30 - INFO - __main__ - Step 75969: {'lr': 0.0002501698158060542, 'samples': 14586048, 'steps': 75968, 'loss/train': 1.1738227605819702} 08/31/2021 03:01:30 - INFO - __main__ - Step 75970: {'lr': 0.0002501645090628933, 'samples': 14586240, 'steps': 75969, 'loss/train': 1.206190824508667} 08/31/2021 03:01:31 - INFO - __main__ - Step 75971: {'lr': 0.00025015920231965833, 'samples': 14586432, 'steps': 75970, 'loss/train': 0.727915346622467} 08/31/2021 03:01:32 - INFO - __main__ - Step 75972: {'lr': 0.0002501538955763516, 'samples': 14586624, 'steps': 75971, 'loss/train': 0.8090962171554565} 08/31/2021 03:01:32 - INFO - __main__ - Step 75973: {'lr': 0.00025014858883297555, 'samples': 14586816, 'steps': 75972, 'loss/train': 1.1204919815063477} 08/31/2021 03:01:32 - INFO - __main__ - Step 75974: {'lr': 0.0002501432820895325, 'samples': 14587008, 'steps': 75973, 'loss/train': 1.1482207775115967} 08/31/2021 03:01:33 - INFO - __main__ - Step 75975: {'lr': 0.0002501379753460249, 'samples': 14587200, 'steps': 75974, 'loss/train': 0.9951162934303284} 08/31/2021 03:01:34 - INFO - __main__ - Step 75976: {'lr': 0.0002501326686024551, 'samples': 14587392, 'steps': 75975, 'loss/train': 1.093135118484497} 08/31/2021 03:01:35 - INFO - __main__ - Step 75977: {'lr': 0.00025012736185882556, 'samples': 14587584, 'steps': 75976, 'loss/train': 0.656887412071228} 08/31/2021 03:01:35 - INFO - __main__ - Step 75978: {'lr': 0.00025012205511513866, 'samples': 14587776, 'steps': 75977, 'loss/train': 1.0889291763305664} 08/31/2021 03:01:35 - INFO - __main__ - Step 75979: {'lr': 0.00025011674837139674, 'samples': 14587968, 'steps': 75978, 'loss/train': 1.1730409860610962} 08/31/2021 03:01:36 - INFO - __main__ - Step 75980: {'lr': 0.0002501114416276022, 'samples': 14588160, 'steps': 75979, 'loss/train': 0.8905990719795227} 08/31/2021 03:01:37 - INFO - __main__ - Step 75981: {'lr': 0.0002501061348837574, 'samples': 14588352, 'steps': 75980, 'loss/train': 0.9678863883018494} 08/31/2021 03:01:38 - INFO - __main__ - Step 75982: {'lr': 0.00025010082813986485, 'samples': 14588544, 'steps': 75981, 'loss/train': 0.11656512320041656} 08/31/2021 03:01:38 - INFO - __main__ - Step 75983: {'lr': 0.00025009552139592685, 'samples': 14588736, 'steps': 75982, 'loss/train': 1.1390963792800903} 08/31/2021 03:01:39 - INFO - __main__ - Step 75984: {'lr': 0.0002500902146519458, 'samples': 14588928, 'steps': 75983, 'loss/train': 1.3056349754333496} 08/31/2021 03:01:39 - INFO - __main__ - Step 75985: {'lr': 0.00025008490790792416, 'samples': 14589120, 'steps': 75984, 'loss/train': 1.3564766645431519} 08/31/2021 03:01:40 - INFO - __main__ - Step 75986: {'lr': 0.00025007960116386424, 'samples': 14589312, 'steps': 75985, 'loss/train': 0.46140268445014954} 08/31/2021 03:01:41 - INFO - __main__ - Step 75987: {'lr': 0.00025007429441976844, 'samples': 14589504, 'steps': 75986, 'loss/train': 1.2623414993286133} 08/31/2021 03:01:41 - INFO - __main__ - Step 75988: {'lr': 0.00025006898767563913, 'samples': 14589696, 'steps': 75987, 'loss/train': 1.4763997793197632} 08/31/2021 03:01:42 - INFO - __main__ - Step 75989: {'lr': 0.00025006368093147876, 'samples': 14589888, 'steps': 75988, 'loss/train': 1.1877684593200684} 08/31/2021 03:01:42 - INFO - __main__ - Step 75990: {'lr': 0.00025005837418728966, 'samples': 14590080, 'steps': 75989, 'loss/train': 0.948982298374176} 08/31/2021 03:01:43 - INFO - __main__ - Step 75991: {'lr': 0.0002500530674430743, 'samples': 14590272, 'steps': 75990, 'loss/train': 1.18455970287323} 08/31/2021 03:01:44 - INFO - __main__ - Step 75992: {'lr': 0.00025004776069883507, 'samples': 14590464, 'steps': 75991, 'loss/train': 1.4526796340942383} 08/31/2021 03:01:44 - INFO - __main__ - Step 75993: {'lr': 0.00025004245395457425, 'samples': 14590656, 'steps': 75992, 'loss/train': 1.5540072917938232} 08/31/2021 03:01:45 - INFO - __main__ - Step 75994: {'lr': 0.0002500371472102943, 'samples': 14590848, 'steps': 75993, 'loss/train': 1.2808300256729126} 08/31/2021 03:01:45 - INFO - __main__ - Step 75995: {'lr': 0.00025003184046599764, 'samples': 14591040, 'steps': 75994, 'loss/train': 0.566076397895813} 08/31/2021 03:01:46 - INFO - __main__ - Step 75996: {'lr': 0.0002500265337216866, 'samples': 14591232, 'steps': 75995, 'loss/train': 1.323386549949646} 08/31/2021 03:01:47 - INFO - __main__ - Step 75997: {'lr': 0.0002500212269773636, 'samples': 14591424, 'steps': 75996, 'loss/train': 1.1713502407073975} 08/31/2021 03:01:47 - INFO - __main__ - Step 75998: {'lr': 0.0002500159202330311, 'samples': 14591616, 'steps': 75997, 'loss/train': 1.4423636198043823} 08/31/2021 03:01:48 - INFO - __main__ - Step 75999: {'lr': 0.00025001061348869143, 'samples': 14591808, 'steps': 75998, 'loss/train': 1.1718428134918213} 08/31/2021 03:01:48 - INFO - __main__ - Step 76000: {'lr': 0.0002500053067443469, 'samples': 14592000, 'steps': 75999, 'loss/train': 1.3132559061050415} 08/31/2021 03:01:49 - INFO - __main__ - Step 76001: {'lr': 0.00025, 'samples': 14592192, 'steps': 76000, 'loss/train': 1.0183806419372559} 08/31/2021 03:01:50 - INFO - __main__ - Step 76002: {'lr': 0.00024999469325565315, 'samples': 14592384, 'steps': 76001, 'loss/train': 1.0948970317840576} 08/31/2021 03:01:50 - INFO - __main__ - Step 76003: {'lr': 0.00024998938651130863, 'samples': 14592576, 'steps': 76002, 'loss/train': 1.088343620300293} 08/31/2021 03:01:50 - INFO - __main__ - Step 76004: {'lr': 0.00024998407976696893, 'samples': 14592768, 'steps': 76003, 'loss/train': 1.1991753578186035} 08/31/2021 03:01:51 - INFO - __main__ - Step 76005: {'lr': 0.00024997877302263634, 'samples': 14592960, 'steps': 76004, 'loss/train': 0.7881013751029968} 08/31/2021 03:01:51 - INFO - __main__ - Step 76006: {'lr': 0.0002499734662783134, 'samples': 14593152, 'steps': 76005, 'loss/train': 0.36814841628074646} 08/31/2021 03:01:53 - INFO - __main__ - Step 76007: {'lr': 0.00024996815953400237, 'samples': 14593344, 'steps': 76006, 'loss/train': 1.700767159461975} 08/31/2021 03:01:53 - INFO - __main__ - Step 76008: {'lr': 0.00024996285278970577, 'samples': 14593536, 'steps': 76007, 'loss/train': 1.0480092763900757} 08/31/2021 03:01:54 - INFO - __main__ - Step 76009: {'lr': 0.00024995754604542587, 'samples': 14593728, 'steps': 76008, 'loss/train': 1.1620908975601196} 08/31/2021 03:01:54 - INFO - __main__ - Step 76010: {'lr': 0.00024995223930116505, 'samples': 14593920, 'steps': 76009, 'loss/train': 1.1803436279296875} 08/31/2021 03:01:54 - INFO - __main__ - Step 76011: {'lr': 0.00024994693255692575, 'samples': 14594112, 'steps': 76010, 'loss/train': 1.3535716533660889} 08/31/2021 03:01:56 - INFO - __main__ - Step 76012: {'lr': 0.00024994162581271035, 'samples': 14594304, 'steps': 76011, 'loss/train': 0.13280804455280304} 08/31/2021 03:01:56 - INFO - __main__ - Step 76013: {'lr': 0.0002499363190685213, 'samples': 14594496, 'steps': 76012, 'loss/train': 1.3494961261749268} 08/31/2021 03:01:56 - INFO - __main__ - Step 76014: {'lr': 0.00024993101232436094, 'samples': 14594688, 'steps': 76013, 'loss/train': 1.2974095344543457} 08/31/2021 03:01:57 - INFO - __main__ - Step 76015: {'lr': 0.00024992570558023163, 'samples': 14594880, 'steps': 76014, 'loss/train': 0.9611928462982178} 08/31/2021 03:01:57 - INFO - __main__ - Step 76016: {'lr': 0.0002499203988361358, 'samples': 14595072, 'steps': 76015, 'loss/train': 1.6644442081451416} 08/31/2021 03:01:59 - INFO - __main__ - Step 76017: {'lr': 0.00024991509209207585, 'samples': 14595264, 'steps': 76016, 'loss/train': 0.9217259883880615} 08/31/2021 03:01:59 - INFO - __main__ - Step 76018: {'lr': 0.00024990978534805415, 'samples': 14595456, 'steps': 76017, 'loss/train': 1.4514870643615723} 08/31/2021 03:01:59 - INFO - __main__ - Step 76019: {'lr': 0.0002499044786040731, 'samples': 14595648, 'steps': 76018, 'loss/train': 1.180228352546692} 08/31/2021 03:02:00 - INFO - __main__ - Step 76020: {'lr': 0.0002498991718601351, 'samples': 14595840, 'steps': 76019, 'loss/train': 1.5839978456497192} 08/31/2021 03:02:00 - INFO - __main__ - Step 76021: {'lr': 0.00024989386511624253, 'samples': 14596032, 'steps': 76020, 'loss/train': 1.3776108026504517} 08/31/2021 03:02:02 - INFO - __main__ - Step 76022: {'lr': 0.0002498885583723979, 'samples': 14596224, 'steps': 76021, 'loss/train': 1.4398752450942993} 08/31/2021 03:02:03 - INFO - __main__ - Step 76023: {'lr': 0.0002498832516286034, 'samples': 14596416, 'steps': 76022, 'loss/train': 0.7742119431495667} 08/31/2021 03:02:03 - INFO - __main__ - Step 76024: {'lr': 0.00024987794488486145, 'samples': 14596608, 'steps': 76023, 'loss/train': 1.7051836252212524} 08/31/2021 03:02:03 - INFO - __main__ - Step 76025: {'lr': 0.0002498726381411745, 'samples': 14596800, 'steps': 76024, 'loss/train': 0.9624290466308594} 08/31/2021 03:02:04 - INFO - __main__ - Step 76026: {'lr': 0.00024986733139754496, 'samples': 14596992, 'steps': 76025, 'loss/train': 1.575364112854004} 08/31/2021 03:02:05 - INFO - __main__ - Step 76027: {'lr': 0.00024986202465397515, 'samples': 14597184, 'steps': 76026, 'loss/train': 0.033689118921756744} 08/31/2021 03:02:06 - INFO - __main__ - Step 76028: {'lr': 0.0002498567179104676, 'samples': 14597376, 'steps': 76027, 'loss/train': 1.300978183746338} 08/31/2021 03:02:06 - INFO - __main__ - Step 76029: {'lr': 0.0002498514111670245, 'samples': 14597568, 'steps': 76028, 'loss/train': 1.6676234006881714} 08/31/2021 03:02:06 - INFO - __main__ - Step 76030: {'lr': 0.00024984610442364846, 'samples': 14597760, 'steps': 76029, 'loss/train': 1.2466503381729126} 08/31/2021 03:02:07 - INFO - __main__ - Step 76031: {'lr': 0.0002498407976803417, 'samples': 14597952, 'steps': 76030, 'loss/train': 0.7792497277259827} 08/31/2021 03:02:09 - INFO - __main__ - Step 76032: {'lr': 0.0002498354909371067, 'samples': 14598144, 'steps': 76031, 'loss/train': 1.2262033224105835} 08/31/2021 03:02:09 - INFO - __main__ - Step 76033: {'lr': 0.0002498301841939458, 'samples': 14598336, 'steps': 76032, 'loss/train': 0.5482776165008545} 08/31/2021 03:02:09 - INFO - __main__ - Step 76034: {'lr': 0.0002498248774508614, 'samples': 14598528, 'steps': 76033, 'loss/train': 3.18530535697937} 08/31/2021 03:02:10 - INFO - __main__ - Step 76035: {'lr': 0.00024981957070785606, 'samples': 14598720, 'steps': 76034, 'loss/train': 1.0483176708221436} 08/31/2021 03:02:10 - INFO - __main__ - Step 76036: {'lr': 0.00024981426396493195, 'samples': 14598912, 'steps': 76035, 'loss/train': 0.7014828324317932} 08/31/2021 03:02:10 - INFO - __main__ - Step 76037: {'lr': 0.00024980895722209143, 'samples': 14599104, 'steps': 76036, 'loss/train': 0.03475377708673477} 08/31/2021 03:02:11 - INFO - __main__ - Step 76038: {'lr': 0.00024980365047933705, 'samples': 14599296, 'steps': 76037, 'loss/train': 1.6804219484329224} 08/31/2021 03:02:12 - INFO - __main__ - Step 76039: {'lr': 0.00024979834373667115, 'samples': 14599488, 'steps': 76038, 'loss/train': 2.159128189086914} 08/31/2021 03:02:13 - INFO - __main__ - Step 76040: {'lr': 0.00024979303699409604, 'samples': 14599680, 'steps': 76039, 'loss/train': 1.3052738904953003} 08/31/2021 03:02:13 - INFO - __main__ - Step 76041: {'lr': 0.0002497877302516143, 'samples': 14599872, 'steps': 76040, 'loss/train': 1.229746699333191} 08/31/2021 03:02:13 - INFO - __main__ - Step 76042: {'lr': 0.0002497824235092281, 'samples': 14600064, 'steps': 76041, 'loss/train': 0.8298074007034302} 08/31/2021 03:02:14 - INFO - __main__ - Step 76043: {'lr': 0.00024977711676694, 'samples': 14600256, 'steps': 76042, 'loss/train': 1.7608630657196045} 08/31/2021 03:02:15 - INFO - __main__ - Step 76044: {'lr': 0.0002497718100247523, 'samples': 14600448, 'steps': 76043, 'loss/train': 1.858614444732666} 08/31/2021 03:02:16 - INFO - __main__ - Step 76045: {'lr': 0.00024976650328266745, 'samples': 14600640, 'steps': 76044, 'loss/train': 1.107060432434082} 08/31/2021 03:02:16 - INFO - __main__ - Step 76046: {'lr': 0.00024976119654068773, 'samples': 14600832, 'steps': 76045, 'loss/train': 1.192851185798645} 08/31/2021 03:02:17 - INFO - __main__ - Step 76047: {'lr': 0.00024975588979881573, 'samples': 14601024, 'steps': 76046, 'loss/train': 0.9008498191833496} 08/31/2021 03:02:17 - INFO - __main__ - Step 76048: {'lr': 0.0002497505830570537, 'samples': 14601216, 'steps': 76047, 'loss/train': 0.7915131449699402} 08/31/2021 03:02:19 - INFO - __main__ - Step 76049: {'lr': 0.00024974527631540404, 'samples': 14601408, 'steps': 76048, 'loss/train': 0.0448029451072216} 08/31/2021 03:02:19 - INFO - __main__ - Step 76050: {'lr': 0.0002497399695738691, 'samples': 14601600, 'steps': 76049, 'loss/train': 0.9136148691177368} 08/31/2021 03:02:19 - INFO - __main__ - Step 76051: {'lr': 0.0002497346628324514, 'samples': 14601792, 'steps': 76050, 'loss/train': 1.679762601852417} 08/31/2021 03:02:20 - INFO - __main__ - Step 76052: {'lr': 0.00024972935609115317, 'samples': 14601984, 'steps': 76051, 'loss/train': 1.618465542793274} 08/31/2021 03:02:20 - INFO - __main__ - Step 76053: {'lr': 0.00024972404934997695, 'samples': 14602176, 'steps': 76052, 'loss/train': 1.3087188005447388} 08/31/2021 03:02:22 - INFO - __main__ - Step 76054: {'lr': 0.00024971874260892505, 'samples': 14602368, 'steps': 76053, 'loss/train': 0.2567789554595947} 08/31/2021 03:02:22 - INFO - __main__ - Step 76055: {'lr': 0.0002497134358679999, 'samples': 14602560, 'steps': 76054, 'loss/train': 1.1799472570419312} 08/31/2021 03:02:23 - INFO - __main__ - Step 76056: {'lr': 0.0002497081291272038, 'samples': 14602752, 'steps': 76055, 'loss/train': 1.7441550493240356} 08/31/2021 03:02:23 - INFO - __main__ - Step 76057: {'lr': 0.00024970282238653927, 'samples': 14602944, 'steps': 76056, 'loss/train': 0.8351420760154724} 08/31/2021 03:02:23 - INFO - __main__ - Step 76058: {'lr': 0.0002496975156460087, 'samples': 14603136, 'steps': 76057, 'loss/train': 0.597756564617157} 08/31/2021 03:02:25 - INFO - __main__ - Step 76059: {'lr': 0.00024969220890561436, 'samples': 14603328, 'steps': 76058, 'loss/train': 1.3794742822647095} 08/31/2021 03:02:25 - INFO - __main__ - Step 76060: {'lr': 0.0002496869021653587, 'samples': 14603520, 'steps': 76059, 'loss/train': 1.427046537399292} 08/31/2021 03:02:26 - INFO - __main__ - Step 76061: {'lr': 0.00024968159542524413, 'samples': 14603712, 'steps': 76060, 'loss/train': 1.3404332399368286} 08/31/2021 03:02:26 - INFO - __main__ - Step 76062: {'lr': 0.00024967628868527306, 'samples': 14603904, 'steps': 76061, 'loss/train': 0.9159040451049805} 08/31/2021 03:02:26 - INFO - __main__ - Step 76063: {'lr': 0.0002496709819454478, 'samples': 14604096, 'steps': 76062, 'loss/train': 1.449683427810669} 08/31/2021 03:02:28 - INFO - __main__ - Step 76064: {'lr': 0.00024966567520577084, 'samples': 14604288, 'steps': 76063, 'loss/train': 0.6364129185676575} 08/31/2021 03:02:28 - INFO - __main__ - Step 76065: {'lr': 0.00024966036846624446, 'samples': 14604480, 'steps': 76064, 'loss/train': 1.5357818603515625} 08/31/2021 03:02:29 - INFO - __main__ - Step 76066: {'lr': 0.0002496550617268711, 'samples': 14604672, 'steps': 76065, 'loss/train': 1.2133734226226807} 08/31/2021 03:02:29 - INFO - __main__ - Step 76067: {'lr': 0.00024964975498765324, 'samples': 14604864, 'steps': 76066, 'loss/train': 2.2170002460479736} 08/31/2021 03:02:29 - INFO - __main__ - Step 76068: {'lr': 0.0002496444482485931, 'samples': 14605056, 'steps': 76067, 'loss/train': 1.2268010377883911} 08/31/2021 03:02:31 - INFO - __main__ - Step 76069: {'lr': 0.00024963914150969335, 'samples': 14605248, 'steps': 76068, 'loss/train': 1.8618990182876587} 08/31/2021 03:02:31 - INFO - __main__ - Step 76070: {'lr': 0.000249633834770956, 'samples': 14605440, 'steps': 76069, 'loss/train': 1.756541132926941} 08/31/2021 03:02:32 - INFO - __main__ - Step 76071: {'lr': 0.00024962852803238377, 'samples': 14605632, 'steps': 76070, 'loss/train': 1.2372820377349854} 08/31/2021 03:02:32 - INFO - __main__ - Step 76072: {'lr': 0.00024962322129397883, 'samples': 14605824, 'steps': 76071, 'loss/train': 0.9310241341590881} 08/31/2021 03:02:32 - INFO - __main__ - Step 76073: {'lr': 0.0002496179145557437, 'samples': 14606016, 'steps': 76072, 'loss/train': 1.2378056049346924} 08/31/2021 03:02:33 - INFO - __main__ - Step 76074: {'lr': 0.0002496126078176807, 'samples': 14606208, 'steps': 76073, 'loss/train': 0.9621381759643555} 08/31/2021 03:02:35 - INFO - __main__ - Step 76075: {'lr': 0.00024960730107979233, 'samples': 14606400, 'steps': 76074, 'loss/train': 1.4461009502410889} 08/31/2021 03:02:35 - INFO - __main__ - Step 76076: {'lr': 0.00024960199434208085, 'samples': 14606592, 'steps': 76075, 'loss/train': 1.063333511352539} 08/31/2021 03:02:36 - INFO - __main__ - Step 76077: {'lr': 0.0002495966876045487, 'samples': 14606784, 'steps': 76076, 'loss/train': 0.7787593007087708} 08/31/2021 03:02:36 - INFO - __main__ - Step 76078: {'lr': 0.00024959138086719826, 'samples': 14606976, 'steps': 76077, 'loss/train': 0.9504784345626831} 08/31/2021 03:02:36 - INFO - __main__ - Step 76079: {'lr': 0.00024958607413003197, 'samples': 14607168, 'steps': 76078, 'loss/train': 0.6752511262893677} 08/31/2021 03:02:38 - INFO - __main__ - Step 76080: {'lr': 0.0002495807673930522, 'samples': 14607360, 'steps': 76079, 'loss/train': 0.7305728197097778} 08/31/2021 03:02:38 - INFO - __main__ - Step 76081: {'lr': 0.00024957546065626133, 'samples': 14607552, 'steps': 76080, 'loss/train': 1.2270112037658691} 08/31/2021 03:02:39 - INFO - __main__ - Step 76082: {'lr': 0.0002495701539196617, 'samples': 14607744, 'steps': 76081, 'loss/train': 0.9201236367225647} 08/31/2021 03:02:39 - INFO - __main__ - Step 76083: {'lr': 0.0002495648471832558, 'samples': 14607936, 'steps': 76082, 'loss/train': 1.4883463382720947} 08/31/2021 03:02:39 - INFO - __main__ - Step 76084: {'lr': 0.00024955954044704595, 'samples': 14608128, 'steps': 76083, 'loss/train': 1.2297794818878174} 08/31/2021 03:02:41 - INFO - __main__ - Step 76085: {'lr': 0.00024955423371103455, 'samples': 14608320, 'steps': 76084, 'loss/train': 0.8518332839012146} 08/31/2021 03:02:42 - INFO - __main__ - Step 76086: {'lr': 0.000249548926975224, 'samples': 14608512, 'steps': 76085, 'loss/train': 1.3206501007080078} 08/31/2021 03:02:42 - INFO - __main__ - Step 76087: {'lr': 0.00024954362023961674, 'samples': 14608704, 'steps': 76086, 'loss/train': 0.5554872751235962} 08/31/2021 03:02:42 - INFO - __main__ - Step 76088: {'lr': 0.0002495383135042151, 'samples': 14608896, 'steps': 76087, 'loss/train': 1.6804293394088745} 08/31/2021 03:02:43 - INFO - __main__ - Step 76089: {'lr': 0.0002495330067690215, 'samples': 14609088, 'steps': 76088, 'loss/train': 0.03260564059019089} 08/31/2021 03:02:43 - INFO - __main__ - Step 76090: {'lr': 0.00024952770003403837, 'samples': 14609280, 'steps': 76089, 'loss/train': 1.3075902462005615} 08/31/2021 03:02:45 - INFO - __main__ - Step 76091: {'lr': 0.000249522393299268, 'samples': 14609472, 'steps': 76090, 'loss/train': 1.1724894046783447} 08/31/2021 03:02:45 - INFO - __main__ - Step 76092: {'lr': 0.0002495170865647128, 'samples': 14609664, 'steps': 76091, 'loss/train': 1.0479896068572998} 08/31/2021 03:02:46 - INFO - __main__ - Step 76093: {'lr': 0.0002495117798303752, 'samples': 14609856, 'steps': 76092, 'loss/train': 0.22243845462799072} 08/31/2021 03:02:46 - INFO - __main__ - Step 76094: {'lr': 0.0002495064730962576, 'samples': 14610048, 'steps': 76093, 'loss/train': 0.8405550718307495} 08/31/2021 03:02:46 - INFO - __main__ - Step 76095: {'lr': 0.00024950116636236237, 'samples': 14610240, 'steps': 76094, 'loss/train': 0.8060351014137268} 08/31/2021 03:02:48 - INFO - __main__ - Step 76096: {'lr': 0.0002494958596286919, 'samples': 14610432, 'steps': 76095, 'loss/train': 1.8436096906661987} 08/31/2021 03:02:48 - INFO - __main__ - Step 76097: {'lr': 0.00024949055289524857, 'samples': 14610624, 'steps': 76096, 'loss/train': 0.9607623815536499} 08/31/2021 03:02:49 - INFO - __main__ - Step 76098: {'lr': 0.00024948524616203485, 'samples': 14610816, 'steps': 76097, 'loss/train': 0.9731927514076233} 08/31/2021 03:02:49 - INFO - __main__ - Step 76099: {'lr': 0.000249479939429053, 'samples': 14611008, 'steps': 76098, 'loss/train': 1.2687116861343384} 08/31/2021 03:02:49 - INFO - __main__ - Step 76100: {'lr': 0.0002494746326963055, 'samples': 14611200, 'steps': 76099, 'loss/train': 1.026465654373169} 08/31/2021 03:02:51 - INFO - __main__ - Step 76101: {'lr': 0.00024946932596379474, 'samples': 14611392, 'steps': 76100, 'loss/train': 1.4339821338653564} 08/31/2021 03:02:51 - INFO - __main__ - Step 76102: {'lr': 0.0002494640192315232, 'samples': 14611584, 'steps': 76101, 'loss/train': 1.8858410120010376} 08/31/2021 03:02:52 - INFO - __main__ - Step 76103: {'lr': 0.00024945871249949304, 'samples': 14611776, 'steps': 76102, 'loss/train': 1.4711202383041382} 08/31/2021 03:02:52 - INFO - __main__ - Step 76104: {'lr': 0.00024945340576770683, 'samples': 14611968, 'steps': 76103, 'loss/train': 1.0596387386322021} 08/31/2021 03:02:52 - INFO - __main__ - Step 76105: {'lr': 0.00024944809903616684, 'samples': 14612160, 'steps': 76104, 'loss/train': 1.7733433246612549} 08/31/2021 03:02:54 - INFO - __main__ - Step 76106: {'lr': 0.0002494427923048755, 'samples': 14612352, 'steps': 76105, 'loss/train': 0.2336418479681015} 08/31/2021 03:02:54 - INFO - __main__ - Step 76107: {'lr': 0.00024943748557383535, 'samples': 14612544, 'steps': 76106, 'loss/train': 1.2179224491119385} 08/31/2021 03:02:55 - INFO - __main__ - Step 76108: {'lr': 0.00024943217884304856, 'samples': 14612736, 'steps': 76107, 'loss/train': 1.1575214862823486} 08/31/2021 03:02:55 - INFO - __main__ - Step 76109: {'lr': 0.00024942687211251764, 'samples': 14612928, 'steps': 76108, 'loss/train': 0.8165356516838074} 08/31/2021 03:02:55 - INFO - __main__ - Step 76110: {'lr': 0.000249421565382245, 'samples': 14613120, 'steps': 76109, 'loss/train': 1.5724787712097168} 08/31/2021 03:02:57 - INFO - __main__ - Step 76111: {'lr': 0.00024941625865223296, 'samples': 14613312, 'steps': 76110, 'loss/train': 1.558717966079712} 08/31/2021 03:02:57 - INFO - __main__ - Step 76112: {'lr': 0.00024941095192248397, 'samples': 14613504, 'steps': 76111, 'loss/train': 0.780930757522583} 08/31/2021 03:02:58 - INFO - __main__ - Step 76113: {'lr': 0.0002494056451930004, 'samples': 14613696, 'steps': 76112, 'loss/train': 0.649164080619812} 08/31/2021 03:02:58 - INFO - __main__ - Step 76114: {'lr': 0.0002494003384637846, 'samples': 14613888, 'steps': 76113, 'loss/train': 1.0440642833709717} 08/31/2021 03:02:58 - INFO - __main__ - Step 76115: {'lr': 0.000249395031734839, 'samples': 14614080, 'steps': 76114, 'loss/train': 1.134547233581543} 08/31/2021 03:02:59 - INFO - __main__ - Step 76116: {'lr': 0.00024938972500616614, 'samples': 14614272, 'steps': 76115, 'loss/train': 1.168295979499817} 08/31/2021 03:03:00 - INFO - __main__ - Step 76117: {'lr': 0.0002493844182777681, 'samples': 14614464, 'steps': 76116, 'loss/train': 1.6324177980422974} 08/31/2021 03:03:01 - INFO - __main__ - Step 76118: {'lr': 0.0002493791115496475, 'samples': 14614656, 'steps': 76117, 'loss/train': 1.5874024629592896} 08/31/2021 03:03:01 - INFO - __main__ - Step 76119: {'lr': 0.0002493738048218066, 'samples': 14614848, 'steps': 76118, 'loss/train': 0.05450655147433281} 08/31/2021 03:03:02 - INFO - __main__ - Step 76120: {'lr': 0.0002493684980942479, 'samples': 14615040, 'steps': 76119, 'loss/train': 1.5510787963867188} 08/31/2021 03:03:02 - INFO - __main__ - Step 76121: {'lr': 0.0002493631913669737, 'samples': 14615232, 'steps': 76120, 'loss/train': 1.5748244524002075} 08/31/2021 03:03:03 - INFO - __main__ - Step 76122: {'lr': 0.00024935788463998645, 'samples': 14615424, 'steps': 76121, 'loss/train': 1.8452898263931274} 08/31/2021 03:03:04 - INFO - __main__ - Step 76123: {'lr': 0.0002493525779132885, 'samples': 14615616, 'steps': 76122, 'loss/train': 0.9340685606002808} 08/31/2021 03:03:04 - INFO - __main__ - Step 76124: {'lr': 0.0002493472711868823, 'samples': 14615808, 'steps': 76123, 'loss/train': 0.7172012329101562} 08/31/2021 03:03:05 - INFO - __main__ - Step 76125: {'lr': 0.00024934196446077024, 'samples': 14616000, 'steps': 76124, 'loss/train': 0.9064702987670898} 08/31/2021 03:03:05 - INFO - __main__ - Step 76126: {'lr': 0.0002493366577349546, 'samples': 14616192, 'steps': 76125, 'loss/train': 1.3504674434661865} 08/31/2021 03:03:06 - INFO - __main__ - Step 76127: {'lr': 0.000249331351009438, 'samples': 14616384, 'steps': 76126, 'loss/train': 1.2782200574874878} 08/31/2021 03:03:07 - INFO - __main__ - Step 76128: {'lr': 0.0002493260442842225, 'samples': 14616576, 'steps': 76127, 'loss/train': 1.484340786933899} 08/31/2021 03:03:07 - INFO - __main__ - Step 76129: {'lr': 0.0002493207375593109, 'samples': 14616768, 'steps': 76128, 'loss/train': 1.2196828126907349} 08/31/2021 03:03:07 - INFO - __main__ - Step 76130: {'lr': 0.0002493154308347052, 'samples': 14616960, 'steps': 76129, 'loss/train': 1.667483925819397} 08/31/2021 03:03:08 - INFO - __main__ - Step 76131: {'lr': 0.000249310124110408, 'samples': 14617152, 'steps': 76130, 'loss/train': 1.3616350889205933} 08/31/2021 03:03:10 - INFO - __main__ - Step 76132: {'lr': 0.0002493048173864217, 'samples': 14617344, 'steps': 76131, 'loss/train': 1.048540472984314} 08/31/2021 03:03:10 - INFO - __main__ - Step 76133: {'lr': 0.00024929951066274855, 'samples': 14617536, 'steps': 76132, 'loss/train': 1.2853491306304932} 08/31/2021 03:03:11 - INFO - __main__ - Step 76134: {'lr': 0.000249294203939391, 'samples': 14617728, 'steps': 76133, 'loss/train': 1.3604224920272827} 08/31/2021 03:03:11 - INFO - __main__ - Step 76135: {'lr': 0.0002492888972163515, 'samples': 14617920, 'steps': 76134, 'loss/train': 0.8828426599502563} 08/31/2021 03:03:11 - INFO - __main__ - Step 76136: {'lr': 0.0002492835904936325, 'samples': 14618112, 'steps': 76135, 'loss/train': 0.6356719732284546} 08/31/2021 03:03:13 - INFO - __main__ - Step 76137: {'lr': 0.0002492782837712362, 'samples': 14618304, 'steps': 76136, 'loss/train': 1.0029102563858032} 08/31/2021 03:03:13 - INFO - __main__ - Step 76138: {'lr': 0.00024927297704916513, 'samples': 14618496, 'steps': 76137, 'loss/train': 1.4318205118179321} 08/31/2021 03:03:14 - INFO - __main__ - Step 76139: {'lr': 0.0002492676703274217, 'samples': 14618688, 'steps': 76138, 'loss/train': 0.7709014415740967} 08/31/2021 03:03:14 - INFO - __main__ - Step 76140: {'lr': 0.00024926236360600814, 'samples': 14618880, 'steps': 76139, 'loss/train': 1.1156730651855469} 08/31/2021 03:03:14 - INFO - __main__ - Step 76141: {'lr': 0.000249257056884927, 'samples': 14619072, 'steps': 76140, 'loss/train': 0.160000279545784} 08/31/2021 03:03:17 - INFO - __main__ - Step 76142: {'lr': 0.0002492517501641806, 'samples': 14619264, 'steps': 76141, 'loss/train': 0.7213853597640991} 08/31/2021 03:03:17 - INFO - __main__ - Step 76143: {'lr': 0.00024924644344377145, 'samples': 14619456, 'steps': 76142, 'loss/train': 1.438902735710144} 08/31/2021 03:03:18 - INFO - __main__ - Step 76144: {'lr': 0.0002492411367237018, 'samples': 14619648, 'steps': 76143, 'loss/train': 0.8339664936065674} 08/31/2021 03:03:18 - INFO - __main__ - Step 76145: {'lr': 0.000249235830003974, 'samples': 14619840, 'steps': 76144, 'loss/train': 1.449841022491455} 08/31/2021 03:03:18 - INFO - __main__ - Step 76146: {'lr': 0.0002492305232845906, 'samples': 14620032, 'steps': 76145, 'loss/train': 1.3360220193862915} 08/31/2021 03:03:19 - INFO - __main__ - Step 76147: {'lr': 0.00024922521656555385, 'samples': 14620224, 'steps': 76146, 'loss/train': 1.7505329847335815} 08/31/2021 03:03:19 - INFO - __main__ - Step 76148: {'lr': 0.00024921990984686626, 'samples': 14620416, 'steps': 76147, 'loss/train': 0.9849547743797302} 08/31/2021 03:03:19 - INFO - __main__ - Step 76149: {'lr': 0.0002492146031285301, 'samples': 14620608, 'steps': 76148, 'loss/train': 0.8609797954559326} 08/31/2021 03:03:21 - INFO - __main__ - Step 76150: {'lr': 0.00024920929641054787, 'samples': 14620800, 'steps': 76149, 'loss/train': 1.3124980926513672} 08/31/2021 03:03:21 - INFO - __main__ - Step 76151: {'lr': 0.00024920398969292194, 'samples': 14620992, 'steps': 76150, 'loss/train': 1.435641884803772} 08/31/2021 03:03:22 - INFO - __main__ - Step 76152: {'lr': 0.00024919868297565466, 'samples': 14621184, 'steps': 76151, 'loss/train': 1.0860795974731445} 08/31/2021 03:03:22 - INFO - __main__ - Step 76153: {'lr': 0.0002491933762587484, 'samples': 14621376, 'steps': 76152, 'loss/train': 5.59473180770874} 08/31/2021 03:03:22 - INFO - __main__ - Step 76154: {'lr': 0.00024918806954220567, 'samples': 14621568, 'steps': 76153, 'loss/train': 1.6437253952026367} 08/31/2021 03:03:24 - INFO - __main__ - Step 76155: {'lr': 0.0002491827628260287, 'samples': 14621760, 'steps': 76154, 'loss/train': 1.3007899522781372} 08/31/2021 03:03:24 - INFO - __main__ - Step 76156: {'lr': 0.0002491774561102201, 'samples': 14621952, 'steps': 76155, 'loss/train': 0.9250556826591492} 08/31/2021 03:03:25 - INFO - __main__ - Step 76157: {'lr': 0.00024917214939478206, 'samples': 14622144, 'steps': 76156, 'loss/train': 0.7423492074012756} 08/31/2021 03:03:25 - INFO - __main__ - Step 76158: {'lr': 0.000249166842679717, 'samples': 14622336, 'steps': 76157, 'loss/train': 1.7550644874572754} 08/31/2021 03:03:26 - INFO - __main__ - Step 76159: {'lr': 0.0002491615359650274, 'samples': 14622528, 'steps': 76158, 'loss/train': 1.256860375404358} 08/31/2021 03:03:27 - INFO - __main__ - Step 76160: {'lr': 0.0002491562292507155, 'samples': 14622720, 'steps': 76159, 'loss/train': 1.3361645936965942} 08/31/2021 03:03:27 - INFO - __main__ - Step 76161: {'lr': 0.00024915092253678385, 'samples': 14622912, 'steps': 76160, 'loss/train': 1.361262559890747} 08/31/2021 03:03:28 - INFO - __main__ - Step 76162: {'lr': 0.0002491456158232348, 'samples': 14623104, 'steps': 76161, 'loss/train': 1.4747624397277832} 08/31/2021 03:03:28 - INFO - __main__ - Step 76163: {'lr': 0.00024914030911007073, 'samples': 14623296, 'steps': 76162, 'loss/train': 1.872819185256958} 08/31/2021 03:03:28 - INFO - __main__ - Step 76164: {'lr': 0.00024913500239729394, 'samples': 14623488, 'steps': 76163, 'loss/train': 1.1440013647079468} 08/31/2021 03:03:30 - INFO - __main__ - Step 76165: {'lr': 0.000249129695684907, 'samples': 14623680, 'steps': 76164, 'loss/train': 1.3216922283172607} 08/31/2021 03:03:31 - INFO - __main__ - Step 76166: {'lr': 0.00024912438897291213, 'samples': 14623872, 'steps': 76165, 'loss/train': 1.2783684730529785} 08/31/2021 03:03:31 - INFO - __main__ - Step 76167: {'lr': 0.0002491190822613118, 'samples': 14624064, 'steps': 76166, 'loss/train': 0.6348004937171936} 08/31/2021 03:03:31 - INFO - __main__ - Step 76168: {'lr': 0.0002491137755501085, 'samples': 14624256, 'steps': 76167, 'loss/train': 1.2899757623672485} 08/31/2021 03:03:32 - INFO - __main__ - Step 76169: {'lr': 0.0002491084688393044, 'samples': 14624448, 'steps': 76168, 'loss/train': 1.6150389909744263} 08/31/2021 03:03:32 - INFO - __main__ - Step 76170: {'lr': 0.0002491031621289022, 'samples': 14624640, 'steps': 76169, 'loss/train': 1.1691752672195435} 08/31/2021 03:03:33 - INFO - __main__ - Step 76171: {'lr': 0.00024909785541890394, 'samples': 14624832, 'steps': 76170, 'loss/train': 1.2545061111450195} 08/31/2021 03:03:34 - INFO - __main__ - Step 76172: {'lr': 0.0002490925487093122, 'samples': 14625024, 'steps': 76171, 'loss/train': 1.1430832147598267} 08/31/2021 03:03:34 - INFO - __main__ - Step 76173: {'lr': 0.0002490872420001293, 'samples': 14625216, 'steps': 76172, 'loss/train': 1.1953468322753906} 08/31/2021 03:03:35 - INFO - __main__ - Step 76174: {'lr': 0.0002490819352913577, 'samples': 14625408, 'steps': 76173, 'loss/train': 2.473571538925171} 08/31/2021 03:03:35 - INFO - __main__ - Step 76175: {'lr': 0.00024907662858299976, 'samples': 14625600, 'steps': 76174, 'loss/train': 1.4688831567764282} 08/31/2021 03:03:36 - INFO - __main__ - Step 76176: {'lr': 0.0002490713218750579, 'samples': 14625792, 'steps': 76175, 'loss/train': 1.2502760887145996} 08/31/2021 03:03:37 - INFO - __main__ - Step 76177: {'lr': 0.00024906601516753454, 'samples': 14625984, 'steps': 76176, 'loss/train': 1.8837562799453735} 08/31/2021 03:03:37 - INFO - __main__ - Step 76178: {'lr': 0.0002490607084604319, 'samples': 14626176, 'steps': 76177, 'loss/train': 1.5544970035552979} 08/31/2021 03:03:38 - INFO - __main__ - Step 76179: {'lr': 0.0002490554017537526, 'samples': 14626368, 'steps': 76178, 'loss/train': 1.0911076068878174} 08/31/2021 03:03:38 - INFO - __main__ - Step 76180: {'lr': 0.00024905009504749885, 'samples': 14626560, 'steps': 76179, 'loss/train': 1.3872979879379272} 08/31/2021 03:03:39 - INFO - __main__ - Step 76181: {'lr': 0.00024904478834167316, 'samples': 14626752, 'steps': 76180, 'loss/train': 0.9786946177482605} 08/31/2021 03:03:40 - INFO - __main__ - Step 76182: {'lr': 0.0002490394816362779, 'samples': 14626944, 'steps': 76181, 'loss/train': 1.949276328086853} 08/31/2021 03:03:40 - INFO - __main__ - Step 76183: {'lr': 0.0002490341749313154, 'samples': 14627136, 'steps': 76182, 'loss/train': 0.9412062764167786} 08/31/2021 03:03:41 - INFO - __main__ - Step 76184: {'lr': 0.0002490288682267881, 'samples': 14627328, 'steps': 76183, 'loss/train': 0.9187430739402771} 08/31/2021 03:03:41 - INFO - __main__ - Step 76185: {'lr': 0.0002490235615226983, 'samples': 14627520, 'steps': 76184, 'loss/train': 1.2711567878723145} 08/31/2021 03:03:41 - INFO - __main__ - Step 76186: {'lr': 0.0002490182548190485, 'samples': 14627712, 'steps': 76185, 'loss/train': 0.9061172008514404} 08/31/2021 03:03:43 - INFO - __main__ - Step 76187: {'lr': 0.0002490129481158411, 'samples': 14627904, 'steps': 76186, 'loss/train': 1.8787047863006592} 08/31/2021 03:03:44 - INFO - __main__ - Step 76188: {'lr': 0.0002490076414130784, 'samples': 14628096, 'steps': 76187, 'loss/train': 1.5121122598648071} 08/31/2021 03:03:44 - INFO - __main__ - Step 76189: {'lr': 0.0002490023347107629, 'samples': 14628288, 'steps': 76188, 'loss/train': 1.5512316226959229} 08/31/2021 03:03:45 - INFO - __main__ - Step 76190: {'lr': 0.0002489970280088969, 'samples': 14628480, 'steps': 76189, 'loss/train': 1.8629801273345947} 08/31/2021 03:03:45 - INFO - __main__ - Step 76191: {'lr': 0.0002489917213074828, 'samples': 14628672, 'steps': 76190, 'loss/train': 1.6632529497146606} 08/31/2021 03:03:47 - INFO - __main__ - Step 76192: {'lr': 0.0002489864146065231, 'samples': 14628864, 'steps': 76191, 'loss/train': 0.8086346387863159} 08/31/2021 03:03:47 - INFO - __main__ - Step 76193: {'lr': 0.00024898110790602, 'samples': 14629056, 'steps': 76192, 'loss/train': 0.2815791666507721} 08/31/2021 03:03:47 - INFO - __main__ - Step 76194: {'lr': 0.0002489758012059761, 'samples': 14629248, 'steps': 76193, 'loss/train': 1.2079421281814575} 08/31/2021 03:03:48 - INFO - __main__ - Step 76195: {'lr': 0.00024897049450639357, 'samples': 14629440, 'steps': 76194, 'loss/train': 1.019531488418579} 08/31/2021 03:03:48 - INFO - __main__ - Step 76196: {'lr': 0.000248965187807275, 'samples': 14629632, 'steps': 76195, 'loss/train': 1.1377893686294556} 08/31/2021 03:03:48 - INFO - __main__ - Step 76197: {'lr': 0.00024895988110862274, 'samples': 14629824, 'steps': 76196, 'loss/train': 1.025015950202942} 08/31/2021 03:03:50 - INFO - __main__ - Step 76198: {'lr': 0.00024895457441043904, 'samples': 14630016, 'steps': 76197, 'loss/train': 0.962000846862793} 08/31/2021 03:03:50 - INFO - __main__ - Step 76199: {'lr': 0.00024894926771272644, 'samples': 14630208, 'steps': 76198, 'loss/train': 1.5435123443603516} 08/31/2021 03:03:51 - INFO - __main__ - Step 76200: {'lr': 0.0002489439610154873, 'samples': 14630400, 'steps': 76199, 'loss/train': 1.3949249982833862} 08/31/2021 03:03:51 - INFO - __main__ - Step 76201: {'lr': 0.00024893865431872397, 'samples': 14630592, 'steps': 76200, 'loss/train': 0.634924054145813} 08/31/2021 03:03:51 - INFO - __main__ - Step 76202: {'lr': 0.0002489333476224388, 'samples': 14630784, 'steps': 76201, 'loss/train': 0.8821326494216919} 08/31/2021 03:03:53 - INFO - __main__ - Step 76203: {'lr': 0.0002489280409266344, 'samples': 14630976, 'steps': 76202, 'loss/train': 1.526873230934143} 08/31/2021 03:03:54 - INFO - __main__ - Step 76204: {'lr': 0.0002489227342313129, 'samples': 14631168, 'steps': 76203, 'loss/train': 1.6969795227050781} 08/31/2021 03:03:54 - INFO - __main__ - Step 76205: {'lr': 0.00024891742753647685, 'samples': 14631360, 'steps': 76204, 'loss/train': 1.9992774724960327} 08/31/2021 03:03:54 - INFO - __main__ - Step 76206: {'lr': 0.00024891212084212857, 'samples': 14631552, 'steps': 76205, 'loss/train': 1.5111989974975586} 08/31/2021 03:03:55 - INFO - __main__ - Step 76207: {'lr': 0.0002489068141482704, 'samples': 14631744, 'steps': 76206, 'loss/train': 0.9841534495353699} 08/31/2021 03:03:56 - INFO - __main__ - Step 76208: {'lr': 0.0002489015074549049, 'samples': 14631936, 'steps': 76207, 'loss/train': 1.120396375656128} 08/31/2021 03:03:57 - INFO - __main__ - Step 76209: {'lr': 0.0002488962007620343, 'samples': 14632128, 'steps': 76208, 'loss/train': 1.6838432550430298} 08/31/2021 03:03:57 - INFO - __main__ - Step 76210: {'lr': 0.00024889089406966117, 'samples': 14632320, 'steps': 76209, 'loss/train': 0.9248865246772766} 08/31/2021 03:03:57 - INFO - __main__ - Step 76211: {'lr': 0.0002488855873777877, 'samples': 14632512, 'steps': 76210, 'loss/train': 1.4970499277114868} 08/31/2021 03:03:58 - INFO - __main__ - Step 76212: {'lr': 0.00024888028068641637, 'samples': 14632704, 'steps': 76211, 'loss/train': 1.0571789741516113} 08/31/2021 03:03:58 - INFO - __main__ - Step 76213: {'lr': 0.0002488749739955495, 'samples': 14632896, 'steps': 76212, 'loss/train': 0.08216383308172226} 08/31/2021 03:03:59 - INFO - __main__ - Step 76214: {'lr': 0.0002488696673051897, 'samples': 14633088, 'steps': 76213, 'loss/train': 0.9915986657142639} 08/31/2021 03:04:00 - INFO - __main__ - Step 76215: {'lr': 0.00024886436061533914, 'samples': 14633280, 'steps': 76214, 'loss/train': 1.2214378118515015} 08/31/2021 03:04:00 - INFO - __main__ - Step 76216: {'lr': 0.00024885905392600026, 'samples': 14633472, 'steps': 76215, 'loss/train': 1.476426124572754} 08/31/2021 03:04:01 - INFO - __main__ - Step 76217: {'lr': 0.00024885374723717545, 'samples': 14633664, 'steps': 76216, 'loss/train': 1.0641149282455444} 08/31/2021 03:04:01 - INFO - __main__ - Step 76218: {'lr': 0.00024884844054886716, 'samples': 14633856, 'steps': 76217, 'loss/train': 1.5787683725357056} 08/31/2021 03:04:02 - INFO - __main__ - Step 76219: {'lr': 0.00024884313386107777, 'samples': 14634048, 'steps': 76218, 'loss/train': 0.8392664790153503} 08/31/2021 03:04:03 - INFO - __main__ - Step 76220: {'lr': 0.0002488378271738096, 'samples': 14634240, 'steps': 76219, 'loss/train': 1.3542559146881104} 08/31/2021 03:04:03 - INFO - __main__ - Step 76221: {'lr': 0.0002488325204870651, 'samples': 14634432, 'steps': 76220, 'loss/train': 0.6835397481918335} 08/31/2021 03:04:04 - INFO - __main__ - Step 76222: {'lr': 0.0002488272138008466, 'samples': 14634624, 'steps': 76221, 'loss/train': 1.379441261291504} 08/31/2021 03:04:04 - INFO - __main__ - Step 76223: {'lr': 0.0002488219071151567, 'samples': 14634816, 'steps': 76222, 'loss/train': 1.2242774963378906} 08/31/2021 03:04:06 - INFO - __main__ - Step 76224: {'lr': 0.0002488166004299975, 'samples': 14635008, 'steps': 76223, 'loss/train': 0.953273355960846} 08/31/2021 03:04:06 - INFO - __main__ - Step 76225: {'lr': 0.0002488112937453716, 'samples': 14635200, 'steps': 76224, 'loss/train': 0.03423207253217697} 08/31/2021 03:04:06 - INFO - __main__ - Step 76226: {'lr': 0.00024880598706128124, 'samples': 14635392, 'steps': 76225, 'loss/train': 1.0334186553955078} 08/31/2021 03:04:07 - INFO - __main__ - Step 76227: {'lr': 0.0002488006803777289, 'samples': 14635584, 'steps': 76226, 'loss/train': 0.8794387578964233} 08/31/2021 03:04:07 - INFO - __main__ - Step 76228: {'lr': 0.00024879537369471694, 'samples': 14635776, 'steps': 76227, 'loss/train': 1.028482437133789} 08/31/2021 03:04:09 - INFO - __main__ - Step 76229: {'lr': 0.0002487900670122478, 'samples': 14635968, 'steps': 76228, 'loss/train': 0.3711059093475342} 08/31/2021 03:04:09 - INFO - __main__ - Step 76230: {'lr': 0.0002487847603303238, 'samples': 14636160, 'steps': 76229, 'loss/train': 1.2520923614501953} 08/31/2021 03:04:10 - INFO - __main__ - Step 76231: {'lr': 0.00024877945364894737, 'samples': 14636352, 'steps': 76230, 'loss/train': 0.9513642191886902} 08/31/2021 03:04:10 - INFO - __main__ - Step 76232: {'lr': 0.00024877414696812094, 'samples': 14636544, 'steps': 76231, 'loss/train': 0.7526183128356934} 08/31/2021 03:04:10 - INFO - __main__ - Step 76233: {'lr': 0.0002487688402878468, 'samples': 14636736, 'steps': 76232, 'loss/train': 1.6894521713256836} 08/31/2021 03:04:11 - INFO - __main__ - Step 76234: {'lr': 0.00024876353360812745, 'samples': 14636928, 'steps': 76233, 'loss/train': 1.299231767654419} 08/31/2021 03:04:12 - INFO - __main__ - Step 76235: {'lr': 0.0002487582269289652, 'samples': 14637120, 'steps': 76234, 'loss/train': 0.24116721749305725} 08/31/2021 03:04:13 - INFO - __main__ - Step 76236: {'lr': 0.0002487529202503625, 'samples': 14637312, 'steps': 76235, 'loss/train': 4.512813568115234} 08/31/2021 03:04:13 - INFO - __main__ - Step 76237: {'lr': 0.0002487476135723218, 'samples': 14637504, 'steps': 76236, 'loss/train': 0.8846369385719299} 08/31/2021 03:04:13 - INFO - __main__ - Step 76238: {'lr': 0.0002487423068948453, 'samples': 14637696, 'steps': 76237, 'loss/train': 0.9663136005401611} 08/31/2021 03:04:14 - INFO - __main__ - Step 76239: {'lr': 0.00024873700021793555, 'samples': 14637888, 'steps': 76238, 'loss/train': 0.6723865270614624} 08/31/2021 03:04:16 - INFO - __main__ - Step 76240: {'lr': 0.00024873169354159484, 'samples': 14638080, 'steps': 76239, 'loss/train': 1.3168166875839233} 08/31/2021 03:04:16 - INFO - __main__ - Step 76241: {'lr': 0.0002487263868658256, 'samples': 14638272, 'steps': 76240, 'loss/train': 1.1547620296478271} 08/31/2021 03:04:17 - INFO - __main__ - Step 76242: {'lr': 0.00024872108019063027, 'samples': 14638464, 'steps': 76241, 'loss/train': 1.8829914331436157} 08/31/2021 03:04:17 - INFO - __main__ - Step 76243: {'lr': 0.00024871577351601116, 'samples': 14638656, 'steps': 76242, 'loss/train': 1.0023925304412842} 08/31/2021 03:04:17 - INFO - __main__ - Step 76244: {'lr': 0.0002487104668419707, 'samples': 14638848, 'steps': 76243, 'loss/train': 1.992418646812439} 08/31/2021 03:04:19 - INFO - __main__ - Step 76245: {'lr': 0.0002487051601685113, 'samples': 14639040, 'steps': 76244, 'loss/train': 1.5092028379440308} 08/31/2021 03:04:20 - INFO - __main__ - Step 76246: {'lr': 0.00024869985349563534, 'samples': 14639232, 'steps': 76245, 'loss/train': 0.03854125365614891} 08/31/2021 03:04:20 - INFO - __main__ - Step 76247: {'lr': 0.0002486945468233452, 'samples': 14639424, 'steps': 76246, 'loss/train': 0.7958913445472717} 08/31/2021 03:04:20 - INFO - __main__ - Step 76248: {'lr': 0.00024868924015164327, 'samples': 14639616, 'steps': 76247, 'loss/train': 1.6336302757263184} 08/31/2021 03:04:21 - INFO - __main__ - Step 76249: {'lr': 0.000248683933480532, 'samples': 14639808, 'steps': 76248, 'loss/train': 1.1813308000564575} 08/31/2021 03:04:22 - INFO - __main__ - Step 76250: {'lr': 0.0002486786268100138, 'samples': 14640000, 'steps': 76249, 'loss/train': 1.7053685188293457} 08/31/2021 03:04:23 - INFO - __main__ - Step 76251: {'lr': 0.00024867332014009085, 'samples': 14640192, 'steps': 76250, 'loss/train': 1.1402475833892822} 08/31/2021 03:04:23 - INFO - __main__ - Step 76252: {'lr': 0.00024866801347076575, 'samples': 14640384, 'steps': 76251, 'loss/train': 1.3268808126449585} 08/31/2021 03:04:23 - INFO - __main__ - Step 76253: {'lr': 0.00024866270680204075, 'samples': 14640576, 'steps': 76252, 'loss/train': 1.1098718643188477} 08/31/2021 03:04:24 - INFO - __main__ - Step 76254: {'lr': 0.00024865740013391835, 'samples': 14640768, 'steps': 76253, 'loss/train': 1.4147361516952515} 08/31/2021 03:04:25 - INFO - __main__ - Step 76255: {'lr': 0.00024865209346640094, 'samples': 14640960, 'steps': 76254, 'loss/train': 1.2423757314682007} 08/31/2021 03:04:26 - INFO - __main__ - Step 76256: {'lr': 0.0002486467867994908, 'samples': 14641152, 'steps': 76255, 'loss/train': 1.3256274461746216} 08/31/2021 03:04:26 - INFO - __main__ - Step 76257: {'lr': 0.00024864148013319044, 'samples': 14641344, 'steps': 76256, 'loss/train': 1.0631788969039917} 08/31/2021 03:04:26 - INFO - __main__ - Step 76258: {'lr': 0.0002486361734675022, 'samples': 14641536, 'steps': 76257, 'loss/train': 1.238140344619751} 08/31/2021 03:04:27 - INFO - __main__ - Step 76259: {'lr': 0.00024863086680242846, 'samples': 14641728, 'steps': 76258, 'loss/train': 0.06480304151773453} 08/31/2021 03:04:28 - INFO - __main__ - Step 76260: {'lr': 0.00024862556013797164, 'samples': 14641920, 'steps': 76259, 'loss/train': 0.5251705050468445} 08/31/2021 03:04:29 - INFO - __main__ - Step 76261: {'lr': 0.00024862025347413417, 'samples': 14642112, 'steps': 76260, 'loss/train': 1.3777233362197876} 08/31/2021 03:04:29 - INFO - __main__ - Step 76262: {'lr': 0.0002486149468109183, 'samples': 14642304, 'steps': 76261, 'loss/train': 0.1745815873146057} 08/31/2021 03:04:30 - INFO - __main__ - Step 76263: {'lr': 0.0002486096401483266, 'samples': 14642496, 'steps': 76262, 'loss/train': 1.3472059965133667} 08/31/2021 03:04:30 - INFO - __main__ - Step 76264: {'lr': 0.00024860433348636144, 'samples': 14642688, 'steps': 76263, 'loss/train': 1.5751681327819824} 08/31/2021 03:04:32 - INFO - __main__ - Step 76265: {'lr': 0.00024859902682502507, 'samples': 14642880, 'steps': 76264, 'loss/train': 0.9913574457168579} 08/31/2021 03:04:32 - INFO - __main__ - Step 76266: {'lr': 0.00024859372016431997, 'samples': 14643072, 'steps': 76265, 'loss/train': 1.3647855520248413} 08/31/2021 03:04:33 - INFO - __main__ - Step 76267: {'lr': 0.0002485884135042485, 'samples': 14643264, 'steps': 76266, 'loss/train': 1.5103096961975098} 08/31/2021 03:04:33 - INFO - __main__ - Step 76268: {'lr': 0.000248583106844813, 'samples': 14643456, 'steps': 76267, 'loss/train': 1.2653712034225464} 08/31/2021 03:04:33 - INFO - __main__ - Step 76269: {'lr': 0.000248577800186016, 'samples': 14643648, 'steps': 76268, 'loss/train': 0.9256041049957275} 08/31/2021 03:04:34 - INFO - __main__ - Step 76270: {'lr': 0.0002485724935278598, 'samples': 14643840, 'steps': 76269, 'loss/train': 1.4173015356063843} 08/31/2021 03:04:35 - INFO - __main__ - Step 76271: {'lr': 0.0002485671868703468, 'samples': 14644032, 'steps': 76270, 'loss/train': 1.3538432121276855} 08/31/2021 03:04:36 - INFO - __main__ - Step 76272: {'lr': 0.0002485618802134794, 'samples': 14644224, 'steps': 76271, 'loss/train': 1.1306942701339722} 08/31/2021 03:04:36 - INFO - __main__ - Step 76273: {'lr': 0.00024855657355726005, 'samples': 14644416, 'steps': 76272, 'loss/train': 1.548762559890747} 08/31/2021 03:04:36 - INFO - __main__ - Step 76274: {'lr': 0.00024855126690169103, 'samples': 14644608, 'steps': 76273, 'loss/train': 1.4192895889282227} 08/31/2021 03:04:37 - INFO - __main__ - Step 76275: {'lr': 0.00024854596024677486, 'samples': 14644800, 'steps': 76274, 'loss/train': 1.3521912097930908} 08/31/2021 03:04:38 - INFO - __main__ - Step 76276: {'lr': 0.00024854065359251377, 'samples': 14644992, 'steps': 76275, 'loss/train': 1.2252684831619263} 08/31/2021 03:04:39 - INFO - __main__ - Step 76277: {'lr': 0.0002485353469389104, 'samples': 14645184, 'steps': 76276, 'loss/train': 0.7214155197143555} 08/31/2021 03:04:39 - INFO - __main__ - Step 76278: {'lr': 0.00024853004028596684, 'samples': 14645376, 'steps': 76277, 'loss/train': 1.237542986869812} 08/31/2021 03:04:39 - INFO - __main__ - Step 76279: {'lr': 0.0002485247336336856, 'samples': 14645568, 'steps': 76278, 'loss/train': 0.058222219347953796} 08/31/2021 03:04:40 - INFO - __main__ - Step 76280: {'lr': 0.00024851942698206916, 'samples': 14645760, 'steps': 76279, 'loss/train': 1.0120309591293335} 08/31/2021 03:04:41 - INFO - __main__ - Step 76281: {'lr': 0.0002485141203311198, 'samples': 14645952, 'steps': 76280, 'loss/train': 1.2993481159210205} 08/31/2021 03:04:42 - INFO - __main__ - Step 76282: {'lr': 0.00024850881368084, 'samples': 14646144, 'steps': 76281, 'loss/train': 1.5477627515792847} 08/31/2021 03:04:42 - INFO - __main__ - Step 76283: {'lr': 0.00024850350703123207, 'samples': 14646336, 'steps': 76282, 'loss/train': 1.3428523540496826} 08/31/2021 03:04:42 - INFO - __main__ - Step 76284: {'lr': 0.0002484982003822984, 'samples': 14646528, 'steps': 76283, 'loss/train': 1.456638216972351} 08/31/2021 03:04:43 - INFO - __main__ - Step 76285: {'lr': 0.0002484928937340415, 'samples': 14646720, 'steps': 76284, 'loss/train': 1.639638066291809} 08/31/2021 03:04:44 - INFO - __main__ - Step 76286: {'lr': 0.0002484875870864636, 'samples': 14646912, 'steps': 76285, 'loss/train': 0.9013887643814087} 08/31/2021 03:04:45 - INFO - __main__ - Step 76287: {'lr': 0.0002484822804395672, 'samples': 14647104, 'steps': 76286, 'loss/train': 1.5554124116897583} 08/31/2021 03:04:45 - INFO - __main__ - Step 76288: {'lr': 0.0002484769737933547, 'samples': 14647296, 'steps': 76287, 'loss/train': 0.2991192042827606} 08/31/2021 03:04:45 - INFO - __main__ - Step 76289: {'lr': 0.0002484716671478284, 'samples': 14647488, 'steps': 76288, 'loss/train': 1.407927393913269} 08/31/2021 03:04:46 - INFO - __main__ - Step 76290: {'lr': 0.00024846636050299077, 'samples': 14647680, 'steps': 76289, 'loss/train': 0.6094433069229126} 08/31/2021 03:04:46 - INFO - __main__ - Step 76291: {'lr': 0.00024846105385884426, 'samples': 14647872, 'steps': 76290, 'loss/train': 1.3083404302597046} 08/31/2021 03:04:47 - INFO - __main__ - Step 76292: {'lr': 0.0002484557472153911, 'samples': 14648064, 'steps': 76291, 'loss/train': 1.8404715061187744} 08/31/2021 03:04:48 - INFO - __main__ - Step 76293: {'lr': 0.00024845044057263376, 'samples': 14648256, 'steps': 76292, 'loss/train': 1.3797192573547363} 08/31/2021 03:04:48 - INFO - __main__ - Step 76294: {'lr': 0.00024844513393057455, 'samples': 14648448, 'steps': 76293, 'loss/train': 0.27170318365097046} 08/31/2021 03:04:48 - INFO - __main__ - Step 76295: {'lr': 0.000248439827289216, 'samples': 14648640, 'steps': 76294, 'loss/train': 1.2841894626617432} 08/31/2021 03:04:49 - INFO - __main__ - Step 76296: {'lr': 0.00024843452064856047, 'samples': 14648832, 'steps': 76295, 'loss/train': 0.8770601749420166} 08/31/2021 03:04:51 - INFO - __main__ - Step 76297: {'lr': 0.00024842921400861025, 'samples': 14649024, 'steps': 76296, 'loss/train': 1.3223800659179688} 08/31/2021 03:04:51 - INFO - __main__ - Step 76298: {'lr': 0.00024842390736936785, 'samples': 14649216, 'steps': 76297, 'loss/train': 1.6719424724578857} 08/31/2021 03:04:52 - INFO - __main__ - Step 76299: {'lr': 0.0002484186007308356, 'samples': 14649408, 'steps': 76298, 'loss/train': 0.8297688364982605} 08/31/2021 03:04:52 - INFO - __main__ - Step 76300: {'lr': 0.0002484132940930159, 'samples': 14649600, 'steps': 76299, 'loss/train': 1.753953218460083} 08/31/2021 03:04:52 - INFO - __main__ - Step 76301: {'lr': 0.00024840798745591117, 'samples': 14649792, 'steps': 76300, 'loss/train': 0.9812555909156799} 08/31/2021 03:04:54 - INFO - __main__ - Step 76302: {'lr': 0.00024840268081952375, 'samples': 14649984, 'steps': 76301, 'loss/train': 0.10186919569969177} 08/31/2021 03:04:54 - INFO - __main__ - Step 76303: {'lr': 0.0002483973741838561, 'samples': 14650176, 'steps': 76302, 'loss/train': 1.0238075256347656} 08/31/2021 03:04:55 - INFO - __main__ - Step 76304: {'lr': 0.0002483920675489106, 'samples': 14650368, 'steps': 76303, 'loss/train': 0.9996776580810547} 08/31/2021 03:04:55 - INFO - __main__ - Step 76305: {'lr': 0.0002483867609146895, 'samples': 14650560, 'steps': 76304, 'loss/train': 0.8887452483177185} 08/31/2021 03:04:55 - INFO - __main__ - Step 76306: {'lr': 0.0002483814542811954, 'samples': 14650752, 'steps': 76305, 'loss/train': 1.4524023532867432} 08/31/2021 03:04:57 - INFO - __main__ - Step 76307: {'lr': 0.0002483761476484305, 'samples': 14650944, 'steps': 76306, 'loss/train': 0.9197561144828796} 08/31/2021 03:04:57 - INFO - __main__ - Step 76308: {'lr': 0.0002483708410163973, 'samples': 14651136, 'steps': 76307, 'loss/train': 1.7358951568603516} 08/31/2021 03:04:58 - INFO - __main__ - Step 76309: {'lr': 0.0002483655343850982, 'samples': 14651328, 'steps': 76308, 'loss/train': 1.483651041984558} 08/31/2021 03:04:58 - INFO - __main__ - Step 76310: {'lr': 0.00024836022775453554, 'samples': 14651520, 'steps': 76309, 'loss/train': 3.5359995365142822} 08/31/2021 03:04:58 - INFO - __main__ - Step 76311: {'lr': 0.00024835492112471177, 'samples': 14651712, 'steps': 76310, 'loss/train': 1.0047588348388672} 08/31/2021 03:05:00 - INFO - __main__ - Step 76312: {'lr': 0.0002483496144956292, 'samples': 14651904, 'steps': 76311, 'loss/train': 1.102111577987671} 08/31/2021 03:05:00 - INFO - __main__ - Step 76313: {'lr': 0.0002483443078672903, 'samples': 14652096, 'steps': 76312, 'loss/train': 1.0766223669052124} 08/31/2021 03:05:01 - INFO - __main__ - Step 76314: {'lr': 0.00024833900123969745, 'samples': 14652288, 'steps': 76313, 'loss/train': 0.9712730050086975} 08/31/2021 03:05:01 - INFO - __main__ - Step 76315: {'lr': 0.00024833369461285296, 'samples': 14652480, 'steps': 76314, 'loss/train': 2.5671145915985107} 08/31/2021 03:05:02 - INFO - __main__ - Step 76316: {'lr': 0.0002483283879867594, 'samples': 14652672, 'steps': 76315, 'loss/train': 1.1850587129592896} 08/31/2021 03:05:03 - INFO - __main__ - Step 76317: {'lr': 0.000248323081361419, 'samples': 14652864, 'steps': 76316, 'loss/train': 0.8182069063186646} 08/31/2021 03:05:04 - INFO - __main__ - Step 76318: {'lr': 0.00024831777473683416, 'samples': 14653056, 'steps': 76317, 'loss/train': 1.102942943572998} 08/31/2021 03:05:04 - INFO - __main__ - Step 76319: {'lr': 0.00024831246811300733, 'samples': 14653248, 'steps': 76318, 'loss/train': 1.2799147367477417} 08/31/2021 03:05:04 - INFO - __main__ - Step 76320: {'lr': 0.0002483071614899408, 'samples': 14653440, 'steps': 76319, 'loss/train': 1.3815971612930298} 08/31/2021 03:05:05 - INFO - __main__ - Step 76321: {'lr': 0.0002483018548676371, 'samples': 14653632, 'steps': 76320, 'loss/train': 1.708480715751648} 08/31/2021 03:05:05 - INFO - __main__ - Step 76322: {'lr': 0.00024829654824609854, 'samples': 14653824, 'steps': 76321, 'loss/train': 2.0813183784484863} 08/31/2021 03:05:07 - INFO - __main__ - Step 76323: {'lr': 0.00024829124162532753, 'samples': 14654016, 'steps': 76322, 'loss/train': 1.5413756370544434} 08/31/2021 03:05:07 - INFO - __main__ - Step 76324: {'lr': 0.00024828593500532647, 'samples': 14654208, 'steps': 76323, 'loss/train': 1.5671939849853516} 08/31/2021 03:05:07 - INFO - __main__ - Step 76325: {'lr': 0.00024828062838609774, 'samples': 14654400, 'steps': 76324, 'loss/train': 1.2910805940628052} 08/31/2021 03:05:08 - INFO - __main__ - Step 76326: {'lr': 0.0002482753217676437, 'samples': 14654592, 'steps': 76325, 'loss/train': 0.7911060452461243} 08/31/2021 03:05:08 - INFO - __main__ - Step 76327: {'lr': 0.00024827001514996687, 'samples': 14654784, 'steps': 76326, 'loss/train': 1.2890572547912598} 08/31/2021 03:05:10 - INFO - __main__ - Step 76328: {'lr': 0.00024826470853306945, 'samples': 14654976, 'steps': 76327, 'loss/train': 1.5823204517364502} 08/31/2021 03:05:10 - INFO - __main__ - Step 76329: {'lr': 0.00024825940191695395, 'samples': 14655168, 'steps': 76328, 'loss/train': 1.4900689125061035} 08/31/2021 03:05:10 - INFO - __main__ - Step 76330: {'lr': 0.0002482540953016227, 'samples': 14655360, 'steps': 76329, 'loss/train': 1.5401012897491455} 08/31/2021 03:05:11 - INFO - __main__ - Step 76331: {'lr': 0.0002482487886870782, 'samples': 14655552, 'steps': 76330, 'loss/train': 1.4023725986480713} 08/31/2021 03:05:11 - INFO - __main__ - Step 76332: {'lr': 0.00024824348207332276, 'samples': 14655744, 'steps': 76331, 'loss/train': 1.136751651763916} 08/31/2021 03:05:13 - INFO - __main__ - Step 76333: {'lr': 0.00024823817546035877, 'samples': 14655936, 'steps': 76332, 'loss/train': 1.3458075523376465} 08/31/2021 03:05:13 - INFO - __main__ - Step 76334: {'lr': 0.0002482328688481886, 'samples': 14656128, 'steps': 76333, 'loss/train': 0.9695250391960144} 08/31/2021 03:05:14 - INFO - __main__ - Step 76335: {'lr': 0.0002482275622368147, 'samples': 14656320, 'steps': 76334, 'loss/train': 1.3610525131225586} 08/31/2021 03:05:14 - INFO - __main__ - Step 76336: {'lr': 0.0002482222556262394, 'samples': 14656512, 'steps': 76335, 'loss/train': 0.8433332443237305} 08/31/2021 03:05:14 - INFO - __main__ - Step 76337: {'lr': 0.0002482169490164652, 'samples': 14656704, 'steps': 76336, 'loss/train': 1.1764384508132935} 08/31/2021 03:05:15 - INFO - __main__ - Step 76338: {'lr': 0.0002482116424074943, 'samples': 14656896, 'steps': 76337, 'loss/train': 0.49437645077705383} 08/31/2021 03:05:16 - INFO - __main__ - Step 76339: {'lr': 0.0002482063357993293, 'samples': 14657088, 'steps': 76338, 'loss/train': 1.1324270963668823} 08/31/2021 03:05:17 - INFO - __main__ - Step 76340: {'lr': 0.00024820102919197244, 'samples': 14657280, 'steps': 76339, 'loss/train': 1.385129690170288} 08/31/2021 03:05:17 - INFO - __main__ - Step 76341: {'lr': 0.0002481957225854262, 'samples': 14657472, 'steps': 76340, 'loss/train': 1.6292915344238281} 08/31/2021 03:05:17 - INFO - __main__ - Step 76342: {'lr': 0.00024819041597969293, 'samples': 14657664, 'steps': 76341, 'loss/train': 1.0634113550186157} 08/31/2021 03:05:18 - INFO - __main__ - Step 76343: {'lr': 0.000248185109374775, 'samples': 14657856, 'steps': 76342, 'loss/train': 1.7279858589172363} 08/31/2021 03:05:19 - INFO - __main__ - Step 76344: {'lr': 0.0002481798027706749, 'samples': 14658048, 'steps': 76343, 'loss/train': 1.2080894708633423} 08/31/2021 03:05:20 - INFO - __main__ - Step 76345: {'lr': 0.0002481744961673949, 'samples': 14658240, 'steps': 76344, 'loss/train': 0.7155590057373047} 08/31/2021 03:05:20 - INFO - __main__ - Step 76346: {'lr': 0.0002481691895649375, 'samples': 14658432, 'steps': 76345, 'loss/train': 0.07149568200111389} 08/31/2021 03:05:21 - INFO - __main__ - Step 76347: {'lr': 0.000248163882963305, 'samples': 14658624, 'steps': 76346, 'loss/train': 1.1278444528579712} 08/31/2021 03:05:21 - INFO - __main__ - Step 76348: {'lr': 0.0002481585763624999, 'samples': 14658816, 'steps': 76347, 'loss/train': 1.226325273513794} 08/31/2021 03:05:23 - INFO - __main__ - Step 76349: {'lr': 0.00024815326976252436, 'samples': 14659008, 'steps': 76348, 'loss/train': 1.5540651082992554} 08/31/2021 03:05:23 - INFO - __main__ - Step 76350: {'lr': 0.000248147963163381, 'samples': 14659200, 'steps': 76349, 'loss/train': 0.043037038296461105} 08/31/2021 03:05:24 - INFO - __main__ - Step 76351: {'lr': 0.00024814265656507214, 'samples': 14659392, 'steps': 76350, 'loss/train': 0.22997534275054932} 08/31/2021 03:05:24 - INFO - __main__ - Step 76352: {'lr': 0.0002481373499676002, 'samples': 14659584, 'steps': 76351, 'loss/train': 1.1770544052124023} 08/31/2021 03:05:25 - INFO - __main__ - Step 76353: {'lr': 0.0002481320433709675, 'samples': 14659776, 'steps': 76352, 'loss/train': 1.3253732919692993} 08/31/2021 03:05:26 - INFO - __main__ - Step 76354: {'lr': 0.0002481267367751765, 'samples': 14659968, 'steps': 76353, 'loss/train': 1.4391199350357056} 08/31/2021 03:05:27 - INFO - __main__ - Step 76355: {'lr': 0.0002481214301802295, 'samples': 14660160, 'steps': 76354, 'loss/train': 1.123695969581604} 08/31/2021 03:05:27 - INFO - __main__ - Step 76356: {'lr': 0.000248116123586129, 'samples': 14660352, 'steps': 76355, 'loss/train': 0.09864883124828339} 08/31/2021 03:05:27 - INFO - __main__ - Step 76357: {'lr': 0.0002481108169928774, 'samples': 14660544, 'steps': 76356, 'loss/train': 1.1437463760375977} 08/31/2021 03:05:28 - INFO - __main__ - Step 76358: {'lr': 0.000248105510400477, 'samples': 14660736, 'steps': 76357, 'loss/train': 0.9267274141311646} 08/31/2021 03:05:29 - INFO - __main__ - Step 76359: {'lr': 0.0002481002038089303, 'samples': 14660928, 'steps': 76358, 'loss/train': 0.584101140499115} 08/31/2021 03:05:30 - INFO - __main__ - Step 76360: {'lr': 0.0002480948972182395, 'samples': 14661120, 'steps': 76359, 'loss/train': 0.8371267914772034} 08/31/2021 03:05:30 - INFO - __main__ - Step 76361: {'lr': 0.0002480895906284072, 'samples': 14661312, 'steps': 76360, 'loss/train': 1.5550601482391357} 08/31/2021 03:05:30 - INFO - __main__ - Step 76362: {'lr': 0.0002480842840394356, 'samples': 14661504, 'steps': 76361, 'loss/train': 0.03020698018372059} 08/31/2021 03:05:31 - INFO - __main__ - Step 76363: {'lr': 0.0002480789774513272, 'samples': 14661696, 'steps': 76362, 'loss/train': 1.460096001625061} 08/31/2021 03:05:32 - INFO - __main__ - Step 76364: {'lr': 0.00024807367086408447, 'samples': 14661888, 'steps': 76363, 'loss/train': 0.9915304183959961} 08/31/2021 03:05:33 - INFO - __main__ - Step 76365: {'lr': 0.00024806836427770967, 'samples': 14662080, 'steps': 76364, 'loss/train': 1.2433981895446777} 08/31/2021 03:05:33 - INFO - __main__ - Step 76366: {'lr': 0.0002480630576922052, 'samples': 14662272, 'steps': 76365, 'loss/train': 0.05591254681348801} 08/31/2021 03:05:34 - INFO - __main__ - Step 76367: {'lr': 0.0002480577511075735, 'samples': 14662464, 'steps': 76366, 'loss/train': 1.642177700996399} 08/31/2021 03:05:34 - INFO - __main__ - Step 76368: {'lr': 0.00024805244452381697, 'samples': 14662656, 'steps': 76367, 'loss/train': 1.5344722270965576} 08/31/2021 03:05:35 - INFO - __main__ - Step 76369: {'lr': 0.00024804713794093796, 'samples': 14662848, 'steps': 76368, 'loss/train': 1.5075792074203491} 08/31/2021 03:05:36 - INFO - __main__ - Step 76370: {'lr': 0.0002480418313589389, 'samples': 14663040, 'steps': 76369, 'loss/train': 0.7667003870010376} 08/31/2021 03:05:36 - INFO - __main__ - Step 76371: {'lr': 0.00024803652477782225, 'samples': 14663232, 'steps': 76370, 'loss/train': 1.1973729133605957} 08/31/2021 03:05:37 - INFO - __main__ - Step 76372: {'lr': 0.0002480312181975902, 'samples': 14663424, 'steps': 76371, 'loss/train': 1.0599005222320557} 08/31/2021 03:05:37 - INFO - __main__ - Step 76373: {'lr': 0.00024802591161824527, 'samples': 14663616, 'steps': 76372, 'loss/train': 1.0276283025741577} 08/31/2021 03:05:37 - INFO - __main__ - Step 76374: {'lr': 0.0002480206050397898, 'samples': 14663808, 'steps': 76373, 'loss/train': 1.7025558948516846} 08/31/2021 03:05:39 - INFO - __main__ - Step 76375: {'lr': 0.00024801529846222626, 'samples': 14664000, 'steps': 76374, 'loss/train': 0.38498032093048096} 08/31/2021 03:05:39 - INFO - __main__ - Step 76376: {'lr': 0.00024800999188555697, 'samples': 14664192, 'steps': 76375, 'loss/train': 1.6036219596862793} 08/31/2021 03:05:40 - INFO - __main__ - Step 76377: {'lr': 0.00024800468530978436, 'samples': 14664384, 'steps': 76376, 'loss/train': 1.1311123371124268} 08/31/2021 03:05:40 - INFO - __main__ - Step 76378: {'lr': 0.00024799937873491083, 'samples': 14664576, 'steps': 76377, 'loss/train': 1.5322530269622803} 08/31/2021 03:05:40 - INFO - __main__ - Step 76379: {'lr': 0.0002479940721609387, 'samples': 14664768, 'steps': 76378, 'loss/train': 0.9037693738937378} 08/31/2021 03:05:42 - INFO - __main__ - Step 76380: {'lr': 0.00024798876558787043, 'samples': 14664960, 'steps': 76379, 'loss/train': 1.2296020984649658} 08/31/2021 03:05:42 - INFO - __main__ - Step 76381: {'lr': 0.0002479834590157084, 'samples': 14665152, 'steps': 76380, 'loss/train': 1.1771544218063354} 08/31/2021 03:05:43 - INFO - __main__ - Step 76382: {'lr': 0.000247978152444455, 'samples': 14665344, 'steps': 76381, 'loss/train': 1.2676912546157837} 08/31/2021 03:05:43 - INFO - __main__ - Step 76383: {'lr': 0.00024797284587411257, 'samples': 14665536, 'steps': 76382, 'loss/train': 0.2435413897037506} 08/31/2021 03:05:43 - INFO - __main__ - Step 76384: {'lr': 0.00024796753930468357, 'samples': 14665728, 'steps': 76383, 'loss/train': 1.20464289188385} 08/31/2021 03:05:45 - INFO - __main__ - Step 76385: {'lr': 0.0002479622327361705, 'samples': 14665920, 'steps': 76384, 'loss/train': 1.1795886754989624} 08/31/2021 03:05:45 - INFO - __main__ - Step 76386: {'lr': 0.0002479569261685755, 'samples': 14666112, 'steps': 76385, 'loss/train': 1.4186995029449463} 08/31/2021 03:05:46 - INFO - __main__ - Step 76387: {'lr': 0.00024795161960190103, 'samples': 14666304, 'steps': 76386, 'loss/train': 1.2319504022598267} 08/31/2021 03:05:46 - INFO - __main__ - Step 76388: {'lr': 0.00024794631303614955, 'samples': 14666496, 'steps': 76387, 'loss/train': 0.9779788255691528} 08/31/2021 03:05:46 - INFO - __main__ - Step 76389: {'lr': 0.0002479410064713234, 'samples': 14666688, 'steps': 76388, 'loss/train': 1.0054048299789429} 08/31/2021 03:05:48 - INFO - __main__ - Step 76390: {'lr': 0.0002479356999074251, 'samples': 14666880, 'steps': 76389, 'loss/train': 1.1691522598266602} 08/31/2021 03:05:48 - INFO - __main__ - Step 76391: {'lr': 0.0002479303933444569, 'samples': 14667072, 'steps': 76390, 'loss/train': 1.2750242948532104} 08/31/2021 03:05:49 - INFO - __main__ - Step 76392: {'lr': 0.0002479250867824212, 'samples': 14667264, 'steps': 76391, 'loss/train': 1.364673376083374} 08/31/2021 03:05:49 - INFO - __main__ - Step 76393: {'lr': 0.0002479197802213204, 'samples': 14667456, 'steps': 76392, 'loss/train': 1.3844443559646606} 08/31/2021 03:05:49 - INFO - __main__ - Step 76394: {'lr': 0.00024791447366115697, 'samples': 14667648, 'steps': 76393, 'loss/train': 1.1238151788711548} 08/31/2021 03:05:51 - INFO - __main__ - Step 76395: {'lr': 0.00024790916710193324, 'samples': 14667840, 'steps': 76394, 'loss/train': 1.0334430932998657} 08/31/2021 03:05:52 - INFO - __main__ - Step 76396: {'lr': 0.0002479038605436516, 'samples': 14668032, 'steps': 76395, 'loss/train': 1.6257529258728027} 08/31/2021 03:05:52 - INFO - __main__ - Step 76397: {'lr': 0.0002478985539863144, 'samples': 14668224, 'steps': 76396, 'loss/train': 0.8915913701057434} 08/31/2021 03:05:52 - INFO - __main__ - Step 76398: {'lr': 0.00024789324742992427, 'samples': 14668416, 'steps': 76397, 'loss/train': 0.8266011476516724} 08/31/2021 03:05:53 - INFO - __main__ - Step 76399: {'lr': 0.00024788794087448327, 'samples': 14668608, 'steps': 76398, 'loss/train': 1.0066885948181152} 08/31/2021 03:05:53 - INFO - __main__ - Step 76400: {'lr': 0.00024788263431999393, 'samples': 14668800, 'steps': 76399, 'loss/train': 1.1811882257461548} 08/31/2021 03:05:55 - INFO - __main__ - Step 76401: {'lr': 0.00024787732776645864, 'samples': 14668992, 'steps': 76400, 'loss/train': 1.287289023399353} 08/31/2021 03:05:56 - INFO - __main__ - Step 76402: {'lr': 0.00024787202121387983, 'samples': 14669184, 'steps': 76401, 'loss/train': 0.03551258519291878} 08/31/2021 03:05:56 - INFO - __main__ - Step 76403: {'lr': 0.0002478667146622598, 'samples': 14669376, 'steps': 76402, 'loss/train': 0.0938284695148468} 08/31/2021 03:05:56 - INFO - __main__ - Step 76404: {'lr': 0.000247861408111601, 'samples': 14669568, 'steps': 76403, 'loss/train': 1.4169787168502808} 08/31/2021 03:05:57 - INFO - __main__ - Step 76405: {'lr': 0.0002478561015619058, 'samples': 14669760, 'steps': 76404, 'loss/train': 1.3555200099945068} 08/31/2021 03:05:57 - INFO - __main__ - Step 76406: {'lr': 0.0002478507950131767, 'samples': 14669952, 'steps': 76405, 'loss/train': 0.5713874101638794} 08/31/2021 03:05:59 - INFO - __main__ - Step 76407: {'lr': 0.00024784548846541586, 'samples': 14670144, 'steps': 76406, 'loss/train': 1.0437828302383423} 08/31/2021 03:06:00 - INFO - __main__ - Step 76408: {'lr': 0.00024784018191862593, 'samples': 14670336, 'steps': 76407, 'loss/train': 1.541190266609192} 08/31/2021 03:06:00 - INFO - __main__ - Step 76409: {'lr': 0.0002478348753728091, 'samples': 14670528, 'steps': 76408, 'loss/train': 1.1952117681503296} 08/31/2021 03:06:00 - INFO - __main__ - Step 76410: {'lr': 0.0002478295688279679, 'samples': 14670720, 'steps': 76409, 'loss/train': 1.0350713729858398} 08/31/2021 03:06:01 - INFO - __main__ - Step 76411: {'lr': 0.00024782426228410465, 'samples': 14670912, 'steps': 76410, 'loss/train': 1.3481011390686035} 08/31/2021 03:06:02 - INFO - __main__ - Step 76412: {'lr': 0.00024781895574122186, 'samples': 14671104, 'steps': 76411, 'loss/train': 1.414416790008545} 08/31/2021 03:06:03 - INFO - __main__ - Step 76413: {'lr': 0.0002478136491993217, 'samples': 14671296, 'steps': 76412, 'loss/train': 1.6621137857437134} 08/31/2021 03:06:03 - INFO - __main__ - Step 76414: {'lr': 0.00024780834265840666, 'samples': 14671488, 'steps': 76413, 'loss/train': 0.47090473771095276} 08/31/2021 03:06:03 - INFO - __main__ - Step 76415: {'lr': 0.00024780303611847914, 'samples': 14671680, 'steps': 76414, 'loss/train': 0.07862811535596848} 08/31/2021 03:06:04 - INFO - __main__ - Step 76416: {'lr': 0.0002477977295795416, 'samples': 14671872, 'steps': 76415, 'loss/train': 1.1256839036941528} 08/31/2021 03:06:04 - INFO - __main__ - Step 76417: {'lr': 0.0002477924230415963, 'samples': 14672064, 'steps': 76416, 'loss/train': 0.43741217255592346} 08/31/2021 03:06:05 - INFO - __main__ - Step 76418: {'lr': 0.00024778711650464574, 'samples': 14672256, 'steps': 76417, 'loss/train': 1.2650911808013916} 08/31/2021 03:06:06 - INFO - __main__ - Step 76419: {'lr': 0.00024778180996869225, 'samples': 14672448, 'steps': 76418, 'loss/train': 0.7172797322273254} 08/31/2021 03:06:06 - INFO - __main__ - Step 76420: {'lr': 0.0002477765034337383, 'samples': 14672640, 'steps': 76419, 'loss/train': 0.983384907245636} 08/31/2021 03:06:07 - INFO - __main__ - Step 76421: {'lr': 0.0002477711968997861, 'samples': 14672832, 'steps': 76420, 'loss/train': 1.6153026819229126} 08/31/2021 03:06:07 - INFO - __main__ - Step 76422: {'lr': 0.00024776589036683825, 'samples': 14673024, 'steps': 76421, 'loss/train': 1.0405062437057495} 08/31/2021 03:06:09 - INFO - __main__ - Step 76423: {'lr': 0.00024776058383489707, 'samples': 14673216, 'steps': 76422, 'loss/train': 0.7502327561378479} 08/31/2021 03:06:09 - INFO - __main__ - Step 76424: {'lr': 0.0002477552773039649, 'samples': 14673408, 'steps': 76423, 'loss/train': 0.9871194958686829} 08/31/2021 03:06:09 - INFO - __main__ - Step 76425: {'lr': 0.0002477499707740443, 'samples': 14673600, 'steps': 76424, 'loss/train': 1.3991602659225464} 08/31/2021 03:06:10 - INFO - __main__ - Step 76426: {'lr': 0.0002477446642451374, 'samples': 14673792, 'steps': 76425, 'loss/train': 1.202734112739563} 08/31/2021 03:06:10 - INFO - __main__ - Step 76427: {'lr': 0.0002477393577172467, 'samples': 14673984, 'steps': 76426, 'loss/train': 1.3404074907302856} 08/31/2021 03:06:12 - INFO - __main__ - Step 76428: {'lr': 0.00024773405119037464, 'samples': 14674176, 'steps': 76427, 'loss/train': 0.877012312412262} 08/31/2021 03:06:12 - INFO - __main__ - Step 76429: {'lr': 0.0002477287446645236, 'samples': 14674368, 'steps': 76428, 'loss/train': 1.2816306352615356} 08/31/2021 03:06:13 - INFO - __main__ - Step 76430: {'lr': 0.0002477234381396959, 'samples': 14674560, 'steps': 76429, 'loss/train': 1.3864473104476929} 08/31/2021 03:06:13 - INFO - __main__ - Step 76431: {'lr': 0.00024771813161589403, 'samples': 14674752, 'steps': 76430, 'loss/train': 0.17674128711223602} 08/31/2021 03:06:14 - INFO - __main__ - Step 76432: {'lr': 0.0002477128250931203, 'samples': 14674944, 'steps': 76431, 'loss/train': 0.24497409164905548} 08/31/2021 03:06:14 - INFO - __main__ - Step 76433: {'lr': 0.00024770751857137714, 'samples': 14675136, 'steps': 76432, 'loss/train': 1.2780389785766602} 08/31/2021 03:06:16 - INFO - __main__ - Step 76434: {'lr': 0.000247702212050667, 'samples': 14675328, 'steps': 76433, 'loss/train': 1.3864811658859253} 08/31/2021 03:06:16 - INFO - __main__ - Step 76435: {'lr': 0.00024769690553099214, 'samples': 14675520, 'steps': 76434, 'loss/train': 1.177164912223816} 08/31/2021 03:06:17 - INFO - __main__ - Step 76436: {'lr': 0.00024769159901235504, 'samples': 14675712, 'steps': 76435, 'loss/train': 1.351674199104309} 08/31/2021 03:06:17 - INFO - __main__ - Step 76437: {'lr': 0.00024768629249475807, 'samples': 14675904, 'steps': 76436, 'loss/train': 1.1977119445800781} 08/31/2021 03:06:17 - INFO - __main__ - Step 76438: {'lr': 0.0002476809859782037, 'samples': 14676096, 'steps': 76437, 'loss/train': 1.1581506729125977} 08/31/2021 03:06:18 - INFO - __main__ - Step 76439: {'lr': 0.00024767567946269416, 'samples': 14676288, 'steps': 76438, 'loss/train': 0.8737398982048035} 08/31/2021 03:06:19 - INFO - __main__ - Step 76440: {'lr': 0.00024767037294823194, 'samples': 14676480, 'steps': 76439, 'loss/train': 0.024990662932395935} 08/31/2021 03:06:20 - INFO - __main__ - Step 76441: {'lr': 0.0002476650664348194, 'samples': 14676672, 'steps': 76440, 'loss/train': 1.4555684328079224} 08/31/2021 03:06:20 - INFO - __main__ - Step 76442: {'lr': 0.00024765975992245895, 'samples': 14676864, 'steps': 76441, 'loss/train': 1.4749850034713745} 08/31/2021 03:06:21 - INFO - __main__ - Step 76443: {'lr': 0.00024765445341115295, 'samples': 14677056, 'steps': 76442, 'loss/train': 1.35152006149292} 08/31/2021 03:06:21 - INFO - __main__ - Step 76444: {'lr': 0.00024764914690090384, 'samples': 14677248, 'steps': 76443, 'loss/train': 1.3573367595672607} 08/31/2021 03:06:21 - INFO - __main__ - Step 76445: {'lr': 0.000247643840391714, 'samples': 14677440, 'steps': 76444, 'loss/train': 0.9348586201667786} 08/31/2021 03:06:23 - INFO - __main__ - Step 76446: {'lr': 0.0002476385338835858, 'samples': 14677632, 'steps': 76445, 'loss/train': 1.278282880783081} 08/31/2021 03:06:23 - INFO - __main__ - Step 76447: {'lr': 0.0002476332273765216, 'samples': 14677824, 'steps': 76446, 'loss/train': 0.9461045861244202} 08/31/2021 03:06:24 - INFO - __main__ - Step 76448: {'lr': 0.00024762792087052387, 'samples': 14678016, 'steps': 76447, 'loss/train': 1.19760000705719} 08/31/2021 03:06:24 - INFO - __main__ - Step 76449: {'lr': 0.000247622614365595, 'samples': 14678208, 'steps': 76448, 'loss/train': 1.7573915719985962} 08/31/2021 03:06:24 - INFO - __main__ - Step 76450: {'lr': 0.00024761730786173735, 'samples': 14678400, 'steps': 76449, 'loss/train': 0.823415994644165} 08/31/2021 03:06:26 - INFO - __main__ - Step 76451: {'lr': 0.00024761200135895323, 'samples': 14678592, 'steps': 76450, 'loss/train': 1.4343572854995728} 08/31/2021 03:06:26 - INFO - __main__ - Step 76452: {'lr': 0.0002476066948572452, 'samples': 14678784, 'steps': 76451, 'loss/train': 1.2211769819259644} 08/31/2021 03:06:27 - INFO - __main__ - Step 76453: {'lr': 0.0002476013883566155, 'samples': 14678976, 'steps': 76452, 'loss/train': 1.399049997329712} 08/31/2021 03:06:27 - INFO - __main__ - Step 76454: {'lr': 0.00024759608185706653, 'samples': 14679168, 'steps': 76453, 'loss/train': 2.4406239986419678} 08/31/2021 03:06:28 - INFO - __main__ - Step 76455: {'lr': 0.0002475907753586008, 'samples': 14679360, 'steps': 76454, 'loss/train': 0.9832277894020081} 08/31/2021 03:06:28 - INFO - __main__ - Step 76456: {'lr': 0.00024758546886122055, 'samples': 14679552, 'steps': 76455, 'loss/train': 1.1811224222183228} 08/31/2021 03:06:30 - INFO - __main__ - Step 76457: {'lr': 0.0002475801623649283, 'samples': 14679744, 'steps': 76456, 'loss/train': 1.0207709074020386} 08/31/2021 03:06:30 - INFO - __main__ - Step 76458: {'lr': 0.0002475748558697264, 'samples': 14679936, 'steps': 76457, 'loss/train': 0.5652148723602295} 08/31/2021 03:06:30 - INFO - __main__ - Step 76459: {'lr': 0.0002475695493756172, 'samples': 14680128, 'steps': 76458, 'loss/train': 0.8171514868736267} 08/31/2021 03:06:31 - INFO - __main__ - Step 76460: {'lr': 0.00024756424288260317, 'samples': 14680320, 'steps': 76459, 'loss/train': 1.4036636352539062} 08/31/2021 03:06:31 - INFO - __main__ - Step 76461: {'lr': 0.00024755893639068666, 'samples': 14680512, 'steps': 76460, 'loss/train': 1.4865745306015015} 08/31/2021 03:06:33 - INFO - __main__ - Step 76462: {'lr': 0.00024755362989987, 'samples': 14680704, 'steps': 76461, 'loss/train': 1.5173336267471313} 08/31/2021 03:06:34 - INFO - __main__ - Step 76463: {'lr': 0.0002475483234101557, 'samples': 14680896, 'steps': 76462, 'loss/train': 1.433248519897461} 08/31/2021 03:06:34 - INFO - __main__ - Step 76464: {'lr': 0.000247543016921546, 'samples': 14681088, 'steps': 76463, 'loss/train': 1.6877468824386597} 08/31/2021 03:06:35 - INFO - __main__ - Step 76465: {'lr': 0.0002475377104340435, 'samples': 14681280, 'steps': 76464, 'loss/train': 1.5034493207931519} 08/31/2021 03:06:35 - INFO - __main__ - Step 76466: {'lr': 0.0002475324039476504, 'samples': 14681472, 'steps': 76465, 'loss/train': 1.8263996839523315} 08/31/2021 03:06:36 - INFO - __main__ - Step 76467: {'lr': 0.0002475270974623691, 'samples': 14681664, 'steps': 76466, 'loss/train': 1.605832576751709} 08/31/2021 03:06:37 - INFO - __main__ - Step 76468: {'lr': 0.0002475217909782021, 'samples': 14681856, 'steps': 76467, 'loss/train': 1.2680091857910156} 08/31/2021 03:06:37 - INFO - __main__ - Step 76469: {'lr': 0.00024751648449515177, 'samples': 14682048, 'steps': 76468, 'loss/train': 1.6202332973480225} 08/31/2021 03:06:37 - INFO - __main__ - Step 76470: {'lr': 0.00024751117801322044, 'samples': 14682240, 'steps': 76469, 'loss/train': 1.2936923503875732} 08/31/2021 03:06:38 - INFO - __main__ - Step 76471: {'lr': 0.0002475058715324106, 'samples': 14682432, 'steps': 76470, 'loss/train': 0.4809529781341553} 08/31/2021 03:06:38 - INFO - __main__ - Step 76472: {'lr': 0.00024750056505272455, 'samples': 14682624, 'steps': 76471, 'loss/train': 1.6549549102783203} 08/31/2021 03:06:40 - INFO - __main__ - Step 76473: {'lr': 0.00024749525857416466, 'samples': 14682816, 'steps': 76472, 'loss/train': 1.4913538694381714} 08/31/2021 03:06:40 - INFO - __main__ - Step 76474: {'lr': 0.00024748995209673336, 'samples': 14683008, 'steps': 76473, 'loss/train': 0.2459385246038437} 08/31/2021 03:06:41 - INFO - __main__ - Step 76475: {'lr': 0.0002474846456204331, 'samples': 14683200, 'steps': 76474, 'loss/train': 1.1593692302703857} 08/31/2021 03:06:41 - INFO - __main__ - Step 76476: {'lr': 0.0002474793391452662, 'samples': 14683392, 'steps': 76475, 'loss/train': 1.3424443006515503} 08/31/2021 03:06:41 - INFO - __main__ - Step 76477: {'lr': 0.0002474740326712351, 'samples': 14683584, 'steps': 76476, 'loss/train': 1.3789336681365967} 08/31/2021 03:06:43 - INFO - __main__ - Step 76478: {'lr': 0.0002474687261983421, 'samples': 14683776, 'steps': 76477, 'loss/train': 1.4301940202713013} 08/31/2021 03:06:43 - INFO - __main__ - Step 76479: {'lr': 0.0002474634197265897, 'samples': 14683968, 'steps': 76478, 'loss/train': 0.8001185655593872} 08/31/2021 03:06:44 - INFO - __main__ - Step 76480: {'lr': 0.00024745811325598027, 'samples': 14684160, 'steps': 76479, 'loss/train': 1.1561623811721802} 08/31/2021 03:06:44 - INFO - __main__ - Step 76481: {'lr': 0.0002474528067865161, 'samples': 14684352, 'steps': 76480, 'loss/train': 1.443322777748108} 08/31/2021 03:06:44 - INFO - __main__ - Step 76482: {'lr': 0.0002474475003181997, 'samples': 14684544, 'steps': 76481, 'loss/train': 0.6724688410758972} 08/31/2021 03:06:46 - INFO - __main__ - Step 76483: {'lr': 0.0002474421938510335, 'samples': 14684736, 'steps': 76482, 'loss/train': 1.4083209037780762} 08/31/2021 03:06:46 - INFO - __main__ - Step 76484: {'lr': 0.0002474368873850197, 'samples': 14684928, 'steps': 76483, 'loss/train': 1.4525507688522339} 08/31/2021 03:06:46 - INFO - __main__ - Step 76485: {'lr': 0.0002474315809201608, 'samples': 14685120, 'steps': 76484, 'loss/train': 1.052875280380249} 08/31/2021 03:06:47 - INFO - __main__ - Step 76486: {'lr': 0.00024742627445645916, 'samples': 14685312, 'steps': 76485, 'loss/train': 0.2639238238334656} 08/31/2021 03:06:47 - INFO - __main__ - Step 76487: {'lr': 0.00024742096799391727, 'samples': 14685504, 'steps': 76486, 'loss/train': 0.8343145847320557} 08/31/2021 03:06:49 - INFO - __main__ - Step 76488: {'lr': 0.0002474156615325374, 'samples': 14685696, 'steps': 76487, 'loss/train': 1.4653515815734863} 08/31/2021 03:06:49 - INFO - __main__ - Step 76489: {'lr': 0.00024741035507232207, 'samples': 14685888, 'steps': 76488, 'loss/train': 0.062474846839904785} 08/31/2021 03:06:50 - INFO - __main__ - Step 76490: {'lr': 0.00024740504861327353, 'samples': 14686080, 'steps': 76489, 'loss/train': 1.2131164073944092} 08/31/2021 03:06:50 - INFO - __main__ - Step 76491: {'lr': 0.0002473997421553942, 'samples': 14686272, 'steps': 76490, 'loss/train': 2.250216484069824} 08/31/2021 03:06:50 - INFO - __main__ - Step 76492: {'lr': 0.0002473944356986866, 'samples': 14686464, 'steps': 76491, 'loss/train': 0.6662151217460632} 08/31/2021 03:06:51 - INFO - __main__ - Step 76493: {'lr': 0.000247389129243153, 'samples': 14686656, 'steps': 76492, 'loss/train': 1.2458807229995728} 08/31/2021 03:06:52 - INFO - __main__ - Step 76494: {'lr': 0.00024738382278879586, 'samples': 14686848, 'steps': 76493, 'loss/train': 1.4920856952667236} 08/31/2021 03:06:53 - INFO - __main__ - Step 76495: {'lr': 0.00024737851633561747, 'samples': 14687040, 'steps': 76494, 'loss/train': 0.966263473033905} 08/31/2021 03:06:53 - INFO - __main__ - Step 76496: {'lr': 0.00024737320988362025, 'samples': 14687232, 'steps': 76495, 'loss/train': 1.1116485595703125} 08/31/2021 03:06:53 - INFO - __main__ - Step 76497: {'lr': 0.00024736790343280667, 'samples': 14687424, 'steps': 76496, 'loss/train': 1.1467413902282715} 08/31/2021 03:06:54 - INFO - __main__ - Step 76498: {'lr': 0.00024736259698317903, 'samples': 14687616, 'steps': 76497, 'loss/train': 1.4482372999191284} 08/31/2021 03:06:55 - INFO - __main__ - Step 76499: {'lr': 0.0002473572905347398, 'samples': 14687808, 'steps': 76498, 'loss/train': 1.2994542121887207} 08/31/2021 03:06:56 - INFO - __main__ - Step 76500: {'lr': 0.0002473519840874913, 'samples': 14688000, 'steps': 76499, 'loss/train': 1.0382075309753418} 08/31/2021 03:06:56 - INFO - __main__ - Step 76501: {'lr': 0.000247346677641436, 'samples': 14688192, 'steps': 76500, 'loss/train': 1.4358181953430176} 08/31/2021 03:06:56 - INFO - __main__ - Step 76502: {'lr': 0.0002473413711965762, 'samples': 14688384, 'steps': 76501, 'loss/train': 1.3450922966003418} 08/31/2021 03:06:57 - INFO - __main__ - Step 76503: {'lr': 0.00024733606475291437, 'samples': 14688576, 'steps': 76502, 'loss/train': 1.619792103767395} 08/31/2021 03:06:58 - INFO - __main__ - Step 76504: {'lr': 0.0002473307583104528, 'samples': 14688768, 'steps': 76503, 'loss/train': 1.0274231433868408} 08/31/2021 03:06:59 - INFO - __main__ - Step 76505: {'lr': 0.00024732545186919403, 'samples': 14688960, 'steps': 76504, 'loss/train': 0.2097604125738144} 08/31/2021 03:06:59 - INFO - __main__ - Step 76506: {'lr': 0.00024732014542914045, 'samples': 14689152, 'steps': 76505, 'loss/train': 1.2372233867645264} 08/31/2021 03:06:59 - INFO - __main__ - Step 76507: {'lr': 0.00024731483899029423, 'samples': 14689344, 'steps': 76506, 'loss/train': 1.1853684186935425} 08/31/2021 03:07:00 - INFO - __main__ - Step 76508: {'lr': 0.0002473095325526579, 'samples': 14689536, 'steps': 76507, 'loss/train': 1.0254285335540771} 08/31/2021 03:07:01 - INFO - __main__ - Step 76509: {'lr': 0.000247304226116234, 'samples': 14689728, 'steps': 76508, 'loss/train': 1.4357091188430786} 08/31/2021 03:07:02 - INFO - __main__ - Step 76510: {'lr': 0.0002472989196810246, 'samples': 14689920, 'steps': 76509, 'loss/train': 5.34974479675293} 08/31/2021 03:07:02 - INFO - __main__ - Step 76511: {'lr': 0.00024729361324703236, 'samples': 14690112, 'steps': 76510, 'loss/train': 1.0505118370056152} 08/31/2021 03:07:02 - INFO - __main__ - Step 76512: {'lr': 0.0002472883068142595, 'samples': 14690304, 'steps': 76511, 'loss/train': 0.7094888091087341} 08/31/2021 03:07:03 - INFO - __main__ - Step 76513: {'lr': 0.00024728300038270856, 'samples': 14690496, 'steps': 76512, 'loss/train': 1.2702674865722656} 08/31/2021 03:07:05 - INFO - __main__ - Step 76514: {'lr': 0.0002472776939523818, 'samples': 14690688, 'steps': 76513, 'loss/train': 1.3864609003067017} 08/31/2021 03:07:05 - INFO - __main__ - Step 76515: {'lr': 0.00024727238752328173, 'samples': 14690880, 'steps': 76514, 'loss/train': 1.7354791164398193} 08/31/2021 03:07:05 - INFO - __main__ - Step 76516: {'lr': 0.0002472670810954106, 'samples': 14691072, 'steps': 76515, 'loss/train': 0.7108293771743774} 08/31/2021 03:07:06 - INFO - __main__ - Step 76517: {'lr': 0.00024726177466877095, 'samples': 14691264, 'steps': 76516, 'loss/train': 1.2655380964279175} 08/31/2021 03:07:06 - INFO - __main__ - Step 76518: {'lr': 0.0002472564682433651, 'samples': 14691456, 'steps': 76517, 'loss/train': 0.9027760028839111} 08/31/2021 03:07:06 - INFO - __main__ - Step 76519: {'lr': 0.0002472511618191955, 'samples': 14691648, 'steps': 76518, 'loss/train': 1.032411813735962} 08/31/2021 03:07:08 - INFO - __main__ - Step 76520: {'lr': 0.00024724585539626445, 'samples': 14691840, 'steps': 76519, 'loss/train': 1.6027535200119019} 08/31/2021 03:07:09 - INFO - __main__ - Step 76521: {'lr': 0.0002472405489745743, 'samples': 14692032, 'steps': 76520, 'loss/train': 1.58228600025177} 08/31/2021 03:07:09 - INFO - __main__ - Step 76522: {'lr': 0.00024723524255412755, 'samples': 14692224, 'steps': 76521, 'loss/train': 1.0072914361953735} 08/31/2021 03:07:09 - INFO - __main__ - Step 76523: {'lr': 0.00024722993613492654, 'samples': 14692416, 'steps': 76522, 'loss/train': 0.04056384414434433} 08/31/2021 03:07:10 - INFO - __main__ - Step 76524: {'lr': 0.0002472246297169737, 'samples': 14692608, 'steps': 76523, 'loss/train': 0.48701244592666626} 08/31/2021 03:07:11 - INFO - __main__ - Step 76525: {'lr': 0.0002472193233002714, 'samples': 14692800, 'steps': 76524, 'loss/train': 1.1847872734069824} 08/31/2021 03:07:12 - INFO - __main__ - Step 76526: {'lr': 0.00024721401688482204, 'samples': 14692992, 'steps': 76525, 'loss/train': 1.6894865036010742} 08/31/2021 03:07:12 - INFO - __main__ - Step 76527: {'lr': 0.000247208710470628, 'samples': 14693184, 'steps': 76526, 'loss/train': 1.2441644668579102} 08/31/2021 03:07:12 - INFO - __main__ - Step 76528: {'lr': 0.00024720340405769164, 'samples': 14693376, 'steps': 76527, 'loss/train': 1.2977865934371948} 08/31/2021 03:07:13 - INFO - __main__ - Step 76529: {'lr': 0.00024719809764601537, 'samples': 14693568, 'steps': 76528, 'loss/train': 1.0632153749465942} 08/31/2021 03:07:14 - INFO - __main__ - Step 76530: {'lr': 0.00024719279123560164, 'samples': 14693760, 'steps': 76529, 'loss/train': 1.2371238470077515} 08/31/2021 03:07:15 - INFO - __main__ - Step 76531: {'lr': 0.0002471874848264528, 'samples': 14693952, 'steps': 76530, 'loss/train': 0.973686695098877} 08/31/2021 03:07:15 - INFO - __main__ - Step 76532: {'lr': 0.0002471821784185712, 'samples': 14694144, 'steps': 76531, 'loss/train': 1.1388996839523315} 08/31/2021 03:07:15 - INFO - __main__ - Step 76533: {'lr': 0.0002471768720119594, 'samples': 14694336, 'steps': 76532, 'loss/train': 0.508251965045929} 08/31/2021 03:07:16 - INFO - __main__ - Step 76534: {'lr': 0.0002471715656066195, 'samples': 14694528, 'steps': 76533, 'loss/train': 1.1483534574508667} 08/31/2021 03:07:17 - INFO - __main__ - Step 76535: {'lr': 0.0002471662592025541, 'samples': 14694720, 'steps': 76534, 'loss/train': 1.4965202808380127} 08/31/2021 03:07:18 - INFO - __main__ - Step 76536: {'lr': 0.00024716095279976553, 'samples': 14694912, 'steps': 76535, 'loss/train': 0.06889445334672928} 08/31/2021 03:07:18 - INFO - __main__ - Step 76537: {'lr': 0.0002471556463982562, 'samples': 14695104, 'steps': 76536, 'loss/train': 1.1823357343673706} 08/31/2021 03:07:19 - INFO - __main__ - Step 76538: {'lr': 0.00024715033999802845, 'samples': 14695296, 'steps': 76537, 'loss/train': 1.5455068349838257} 08/31/2021 03:07:19 - INFO - __main__ - Step 76539: {'lr': 0.00024714503359908477, 'samples': 14695488, 'steps': 76538, 'loss/train': 0.5129196047782898} 08/31/2021 03:07:19 - INFO - __main__ - Step 76540: {'lr': 0.00024713972720142745, 'samples': 14695680, 'steps': 76539, 'loss/train': 2.3190886974334717} 08/31/2021 03:07:21 - INFO - __main__ - Step 76541: {'lr': 0.00024713442080505897, 'samples': 14695872, 'steps': 76540, 'loss/train': 0.9597370624542236} 08/31/2021 03:07:22 - INFO - __main__ - Step 76542: {'lr': 0.00024712911440998166, 'samples': 14696064, 'steps': 76541, 'loss/train': 0.7247560024261475} 08/31/2021 03:07:22 - INFO - __main__ - Step 76543: {'lr': 0.00024712380801619787, 'samples': 14696256, 'steps': 76542, 'loss/train': 1.0477015972137451} 08/31/2021 03:07:23 - INFO - __main__ - Step 76544: {'lr': 0.00024711850162371013, 'samples': 14696448, 'steps': 76543, 'loss/train': 0.9737330675125122} 08/31/2021 03:07:23 - INFO - __main__ - Step 76545: {'lr': 0.00024711319523252066, 'samples': 14696640, 'steps': 76544, 'loss/train': 0.9440644383430481} 08/31/2021 03:07:24 - INFO - __main__ - Step 76546: {'lr': 0.00024710788884263214, 'samples': 14696832, 'steps': 76545, 'loss/train': 0.16545900702476501} 08/31/2021 03:07:25 - INFO - __main__ - Step 76547: {'lr': 0.0002471025824540466, 'samples': 14697024, 'steps': 76546, 'loss/train': 1.5979000329971313} 08/31/2021 03:07:25 - INFO - __main__ - Step 76548: {'lr': 0.0002470972760667666, 'samples': 14697216, 'steps': 76547, 'loss/train': 1.0624396800994873} 08/31/2021 03:07:25 - INFO - __main__ - Step 76549: {'lr': 0.00024709196968079455, 'samples': 14697408, 'steps': 76548, 'loss/train': 1.764328122138977} 08/31/2021 03:07:26 - INFO - __main__ - Step 76550: {'lr': 0.0002470866632961328, 'samples': 14697600, 'steps': 76549, 'loss/train': 1.8893028497695923} 08/31/2021 03:07:27 - INFO - __main__ - Step 76551: {'lr': 0.00024708135691278374, 'samples': 14697792, 'steps': 76550, 'loss/train': 1.1674306392669678} 08/31/2021 03:07:28 - INFO - __main__ - Step 76552: {'lr': 0.00024707605053074977, 'samples': 14697984, 'steps': 76551, 'loss/train': 0.9938403367996216} 08/31/2021 03:07:28 - INFO - __main__ - Step 76553: {'lr': 0.00024707074415003327, 'samples': 14698176, 'steps': 76552, 'loss/train': 1.5758509635925293} 08/31/2021 03:07:28 - INFO - __main__ - Step 76554: {'lr': 0.00024706543777063667, 'samples': 14698368, 'steps': 76553, 'loss/train': 1.3236021995544434} 08/31/2021 03:07:29 - INFO - __main__ - Step 76555: {'lr': 0.0002470601313925623, 'samples': 14698560, 'steps': 76554, 'loss/train': 1.3052812814712524} 08/31/2021 03:07:30 - INFO - __main__ - Step 76556: {'lr': 0.0002470548250158127, 'samples': 14698752, 'steps': 76555, 'loss/train': 1.5867154598236084} 08/31/2021 03:07:31 - INFO - __main__ - Step 76557: {'lr': 0.0002470495186403901, 'samples': 14698944, 'steps': 76556, 'loss/train': 1.278283715248108} 08/31/2021 03:07:31 - INFO - __main__ - Step 76558: {'lr': 0.00024704421226629685, 'samples': 14699136, 'steps': 76557, 'loss/train': 0.6375889778137207} 08/31/2021 03:07:32 - INFO - __main__ - Step 76559: {'lr': 0.00024703890589353563, 'samples': 14699328, 'steps': 76558, 'loss/train': 1.4065861701965332} 08/31/2021 03:07:32 - INFO - __main__ - Step 76560: {'lr': 0.0002470335995221085, 'samples': 14699520, 'steps': 76559, 'loss/train': 1.220959186553955} 08/31/2021 03:07:33 - INFO - __main__ - Step 76561: {'lr': 0.000247028293152018, 'samples': 14699712, 'steps': 76560, 'loss/train': 0.033637501299381256} 08/31/2021 03:07:34 - INFO - __main__ - Step 76562: {'lr': 0.0002470229867832665, 'samples': 14699904, 'steps': 76561, 'loss/train': 1.028831124305725} 08/31/2021 03:07:34 - INFO - __main__ - Step 76563: {'lr': 0.0002470176804158564, 'samples': 14700096, 'steps': 76562, 'loss/train': 0.9784656763076782} 08/31/2021 03:07:35 - INFO - __main__ - Step 76564: {'lr': 0.00024701237404979007, 'samples': 14700288, 'steps': 76563, 'loss/train': 0.9158138036727905} 08/31/2021 03:07:35 - INFO - __main__ - Step 76565: {'lr': 0.00024700706768506994, 'samples': 14700480, 'steps': 76564, 'loss/train': 1.5971304178237915} 08/31/2021 03:07:37 - INFO - __main__ - Step 76566: {'lr': 0.0002470017613216984, 'samples': 14700672, 'steps': 76565, 'loss/train': 1.719960331916809} 08/31/2021 03:07:37 - INFO - __main__ - Step 76567: {'lr': 0.00024699645495967777, 'samples': 14700864, 'steps': 76566, 'loss/train': 1.0574560165405273} 08/31/2021 03:07:37 - INFO - __main__ - Step 76568: {'lr': 0.0002469911485990105, 'samples': 14701056, 'steps': 76567, 'loss/train': 0.7370049953460693} 08/31/2021 03:07:38 - INFO - __main__ - Step 76569: {'lr': 0.00024698584223969896, 'samples': 14701248, 'steps': 76568, 'loss/train': 0.7820421457290649} 08/31/2021 03:07:38 - INFO - __main__ - Step 76570: {'lr': 0.0002469805358817456, 'samples': 14701440, 'steps': 76569, 'loss/train': 1.8513681888580322} 08/31/2021 03:07:40 - INFO - __main__ - Step 76571: {'lr': 0.0002469752295251527, 'samples': 14701632, 'steps': 76570, 'loss/train': 1.020504355430603} 08/31/2021 03:07:41 - INFO - __main__ - Step 76572: {'lr': 0.00024696992316992276, 'samples': 14701824, 'steps': 76571, 'loss/train': 0.9092392921447754} 08/31/2021 03:07:41 - INFO - __main__ - Step 76573: {'lr': 0.00024696461681605826, 'samples': 14702016, 'steps': 76572, 'loss/train': 0.4533708393573761} 08/31/2021 03:07:41 - INFO - __main__ - Step 76574: {'lr': 0.0002469593104635613, 'samples': 14702208, 'steps': 76573, 'loss/train': 0.7353560924530029} 08/31/2021 03:07:42 - INFO - __main__ - Step 76575: {'lr': 0.0002469540041124345, 'samples': 14702400, 'steps': 76574, 'loss/train': 0.657386302947998} 08/31/2021 03:07:42 - INFO - __main__ - Step 76576: {'lr': 0.0002469486977626801, 'samples': 14702592, 'steps': 76575, 'loss/train': 1.265729546546936} 08/31/2021 03:07:43 - INFO - __main__ - Step 76577: {'lr': 0.00024694339141430056, 'samples': 14702784, 'steps': 76576, 'loss/train': 1.2128628492355347} 08/31/2021 03:07:44 - INFO - __main__ - Step 76578: {'lr': 0.0002469380850672983, 'samples': 14702976, 'steps': 76577, 'loss/train': 1.4014512300491333} 08/31/2021 03:07:44 - INFO - __main__ - Step 76579: {'lr': 0.00024693277872167574, 'samples': 14703168, 'steps': 76578, 'loss/train': 1.3886256217956543} 08/31/2021 03:07:45 - INFO - __main__ - Step 76580: {'lr': 0.00024692747237743516, 'samples': 14703360, 'steps': 76579, 'loss/train': 1.1827641725540161} 08/31/2021 03:07:45 - INFO - __main__ - Step 76581: {'lr': 0.00024692216603457905, 'samples': 14703552, 'steps': 76580, 'loss/train': 1.3861440420150757} 08/31/2021 03:07:46 - INFO - __main__ - Step 76582: {'lr': 0.00024691685969310974, 'samples': 14703744, 'steps': 76581, 'loss/train': 0.8682945370674133} 08/31/2021 03:07:47 - INFO - __main__ - Step 76583: {'lr': 0.0002469115533530297, 'samples': 14703936, 'steps': 76582, 'loss/train': 1.477987289428711} 08/31/2021 03:07:47 - INFO - __main__ - Step 76584: {'lr': 0.00024690624701434124, 'samples': 14704128, 'steps': 76583, 'loss/train': 0.7387635707855225} 08/31/2021 03:07:48 - INFO - __main__ - Step 76585: {'lr': 0.00024690094067704677, 'samples': 14704320, 'steps': 76584, 'loss/train': 0.7813519835472107} 08/31/2021 03:07:48 - INFO - __main__ - Step 76586: {'lr': 0.00024689563434114874, 'samples': 14704512, 'steps': 76585, 'loss/train': 0.9542191624641418} 08/31/2021 03:07:50 - INFO - __main__ - Step 76587: {'lr': 0.00024689032800664945, 'samples': 14704704, 'steps': 76586, 'loss/train': 1.2589154243469238} 08/31/2021 03:07:50 - INFO - __main__ - Step 76588: {'lr': 0.00024688502167355126, 'samples': 14704896, 'steps': 76587, 'loss/train': 1.4696481227874756} 08/31/2021 03:07:50 - INFO - __main__ - Step 76589: {'lr': 0.0002468797153418567, 'samples': 14705088, 'steps': 76588, 'loss/train': 1.2024226188659668} 08/31/2021 03:07:51 - INFO - __main__ - Step 76590: {'lr': 0.0002468744090115681, 'samples': 14705280, 'steps': 76589, 'loss/train': 1.0137598514556885} 08/31/2021 03:07:51 - INFO - __main__ - Step 76591: {'lr': 0.0002468691026826878, 'samples': 14705472, 'steps': 76590, 'loss/train': 0.6785452961921692} 08/31/2021 03:07:53 - INFO - __main__ - Step 76592: {'lr': 0.00024686379635521826, 'samples': 14705664, 'steps': 76591, 'loss/train': 1.2689363956451416} 08/31/2021 03:07:53 - INFO - __main__ - Step 76593: {'lr': 0.0002468584900291618, 'samples': 14705856, 'steps': 76592, 'loss/train': 1.1940969228744507} 08/31/2021 03:07:53 - INFO - __main__ - Step 76594: {'lr': 0.00024685318370452094, 'samples': 14706048, 'steps': 76593, 'loss/train': 0.7768265008926392} 08/31/2021 03:07:54 - INFO - __main__ - Step 76595: {'lr': 0.000246847877381298, 'samples': 14706240, 'steps': 76594, 'loss/train': 0.7588772177696228} 08/31/2021 03:07:54 - INFO - __main__ - Step 76596: {'lr': 0.0002468425710594953, 'samples': 14706432, 'steps': 76595, 'loss/train': 0.07245124131441116} 08/31/2021 03:07:56 - INFO - __main__ - Step 76597: {'lr': 0.00024683726473911525, 'samples': 14706624, 'steps': 76596, 'loss/train': 1.182958722114563} 08/31/2021 03:07:56 - INFO - __main__ - Step 76598: {'lr': 0.00024683195842016033, 'samples': 14706816, 'steps': 76597, 'loss/train': 0.6594909429550171} 08/31/2021 03:07:57 - INFO - __main__ - Step 76599: {'lr': 0.00024682665210263286, 'samples': 14707008, 'steps': 76598, 'loss/train': 1.6319406032562256} 08/31/2021 03:07:57 - INFO - __main__ - Step 76600: {'lr': 0.00024682134578653535, 'samples': 14707200, 'steps': 76599, 'loss/train': 0.9337005019187927} 08/31/2021 03:07:57 - INFO - __main__ - Step 76601: {'lr': 0.00024681603947186996, 'samples': 14707392, 'steps': 76600, 'loss/train': 1.6132010221481323} 08/31/2021 03:07:58 - INFO - __main__ - Step 76602: {'lr': 0.0002468107331586393, 'samples': 14707584, 'steps': 76601, 'loss/train': 1.556922197341919} 08/31/2021 03:07:59 - INFO - __main__ - Step 76603: {'lr': 0.0002468054268468456, 'samples': 14707776, 'steps': 76602, 'loss/train': 1.135837435722351} 08/31/2021 03:08:00 - INFO - __main__ - Step 76604: {'lr': 0.00024680012053649136, 'samples': 14707968, 'steps': 76603, 'loss/train': 1.345894694328308} 08/31/2021 03:08:00 - INFO - __main__ - Step 76605: {'lr': 0.0002467948142275789, 'samples': 14708160, 'steps': 76604, 'loss/train': 1.803865909576416} 08/31/2021 03:08:00 - INFO - __main__ - Step 76606: {'lr': 0.0002467895079201108, 'samples': 14708352, 'steps': 76605, 'loss/train': 0.9646623730659485} 08/31/2021 03:08:01 - INFO - __main__ - Step 76607: {'lr': 0.00024678420161408914, 'samples': 14708544, 'steps': 76606, 'loss/train': 1.2970181703567505} 08/31/2021 03:08:02 - INFO - __main__ - Step 76608: {'lr': 0.0002467788953095165, 'samples': 14708736, 'steps': 76607, 'loss/train': 1.4611809253692627} 08/31/2021 03:08:03 - INFO - __main__ - Step 76609: {'lr': 0.00024677358900639524, 'samples': 14708928, 'steps': 76608, 'loss/train': 2.120300531387329} 08/31/2021 03:08:03 - INFO - __main__ - Step 76610: {'lr': 0.00024676828270472776, 'samples': 14709120, 'steps': 76609, 'loss/train': 1.0321186780929565} 08/31/2021 03:08:03 - INFO - __main__ - Step 76611: {'lr': 0.00024676297640451646, 'samples': 14709312, 'steps': 76610, 'loss/train': 1.5974770784378052} 08/31/2021 03:08:04 - INFO - __main__ - Step 76612: {'lr': 0.00024675767010576364, 'samples': 14709504, 'steps': 76611, 'loss/train': 0.0798482894897461} 08/31/2021 03:08:05 - INFO - __main__ - Step 76613: {'lr': 0.0002467523638084719, 'samples': 14709696, 'steps': 76612, 'loss/train': 1.2523305416107178} 08/31/2021 03:08:06 - INFO - __main__ - Step 76614: {'lr': 0.00024674705751264337, 'samples': 14709888, 'steps': 76613, 'loss/train': 1.4150850772857666} 08/31/2021 03:08:06 - INFO - __main__ - Step 76615: {'lr': 0.00024674175121828064, 'samples': 14710080, 'steps': 76614, 'loss/train': 1.3901995420455933} 08/31/2021 03:08:06 - INFO - __main__ - Step 76616: {'lr': 0.000246736444925386, 'samples': 14710272, 'steps': 76615, 'loss/train': 0.9592878818511963} 08/31/2021 03:08:07 - INFO - __main__ - Step 76617: {'lr': 0.00024673113863396193, 'samples': 14710464, 'steps': 76616, 'loss/train': 1.500937581062317} 08/31/2021 03:08:08 - INFO - __main__ - Step 76618: {'lr': 0.00024672583234401066, 'samples': 14710656, 'steps': 76617, 'loss/train': 1.3573050498962402} 08/31/2021 03:08:09 - INFO - __main__ - Step 76619: {'lr': 0.0002467205260555347, 'samples': 14710848, 'steps': 76618, 'loss/train': 1.0225920677185059} 08/31/2021 03:08:09 - INFO - __main__ - Step 76620: {'lr': 0.00024671521976853643, 'samples': 14711040, 'steps': 76619, 'loss/train': 1.487764596939087} 08/31/2021 03:08:09 - INFO - __main__ - Step 76621: {'lr': 0.00024670991348301824, 'samples': 14711232, 'steps': 76620, 'loss/train': 1.5978379249572754} 08/31/2021 03:08:10 - INFO - __main__ - Step 76622: {'lr': 0.0002467046071989825, 'samples': 14711424, 'steps': 76621, 'loss/train': 0.24822872877120972} 08/31/2021 03:08:12 - INFO - __main__ - Step 76623: {'lr': 0.0002466993009164316, 'samples': 14711616, 'steps': 76622, 'loss/train': 0.7137423753738403} 08/31/2021 03:08:12 - INFO - __main__ - Step 76624: {'lr': 0.00024669399463536797, 'samples': 14711808, 'steps': 76623, 'loss/train': 1.1280512809753418} 08/31/2021 03:08:13 - INFO - __main__ - Step 76625: {'lr': 0.000246688688355794, 'samples': 14712000, 'steps': 76624, 'loss/train': 0.8744216561317444} 08/31/2021 03:08:13 - INFO - __main__ - Step 76626: {'lr': 0.000246683382077712, 'samples': 14712192, 'steps': 76625, 'loss/train': 0.6895650625228882} 08/31/2021 03:08:13 - INFO - __main__ - Step 76627: {'lr': 0.00024667807580112445, 'samples': 14712384, 'steps': 76626, 'loss/train': 1.3679852485656738} 08/31/2021 03:08:15 - INFO - __main__ - Step 76628: {'lr': 0.0002466727695260338, 'samples': 14712576, 'steps': 76627, 'loss/train': 1.487102746963501} 08/31/2021 03:08:16 - INFO - __main__ - Step 76629: {'lr': 0.0002466674632524422, 'samples': 14712768, 'steps': 76628, 'loss/train': 1.3295464515686035} 08/31/2021 03:08:16 - INFO - __main__ - Step 76630: {'lr': 0.00024666215698035225, 'samples': 14712960, 'steps': 76629, 'loss/train': 1.140838861465454} 08/31/2021 03:08:16 - INFO - __main__ - Step 76631: {'lr': 0.00024665685070976624, 'samples': 14713152, 'steps': 76630, 'loss/train': 0.05069298297166824} 08/31/2021 03:08:17 - INFO - __main__ - Step 76632: {'lr': 0.0002466515444406867, 'samples': 14713344, 'steps': 76631, 'loss/train': 0.8926272988319397} 08/31/2021 03:08:18 - INFO - __main__ - Step 76633: {'lr': 0.0002466462381731158, 'samples': 14713536, 'steps': 76632, 'loss/train': 0.4441049098968506} 08/31/2021 03:08:18 - INFO - __main__ - Step 76634: {'lr': 0.0002466409319070561, 'samples': 14713728, 'steps': 76633, 'loss/train': 1.2274607419967651} 08/31/2021 03:08:19 - INFO - __main__ - Step 76635: {'lr': 0.00024663562564250995, 'samples': 14713920, 'steps': 76634, 'loss/train': 0.7507412433624268} 08/31/2021 03:08:19 - INFO - __main__ - Step 76636: {'lr': 0.0002466303193794797, 'samples': 14714112, 'steps': 76635, 'loss/train': 1.2068101167678833} 08/31/2021 03:08:20 - INFO - __main__ - Step 76637: {'lr': 0.00024662501311796786, 'samples': 14714304, 'steps': 76636, 'loss/train': 0.7753759622573853} 08/31/2021 03:08:21 - INFO - __main__ - Step 76638: {'lr': 0.00024661970685797667, 'samples': 14714496, 'steps': 76637, 'loss/train': 1.3436367511749268} 08/31/2021 03:08:21 - INFO - __main__ - Step 76639: {'lr': 0.00024661440059950857, 'samples': 14714688, 'steps': 76638, 'loss/train': 1.1885554790496826} 08/31/2021 03:08:22 - INFO - __main__ - Step 76640: {'lr': 0.0002466090943425661, 'samples': 14714880, 'steps': 76639, 'loss/train': 1.7111058235168457} 08/31/2021 03:08:22 - INFO - __main__ - Step 76641: {'lr': 0.00024660378808715144, 'samples': 14715072, 'steps': 76640, 'loss/train': 1.1664057970046997} 08/31/2021 03:08:22 - INFO - __main__ - Step 76642: {'lr': 0.0002465984818332671, 'samples': 14715264, 'steps': 76641, 'loss/train': 1.1451352834701538} 08/31/2021 03:08:24 - INFO - __main__ - Step 76643: {'lr': 0.00024659317558091534, 'samples': 14715456, 'steps': 76642, 'loss/train': 0.9508946537971497} 08/31/2021 03:08:24 - INFO - __main__ - Step 76644: {'lr': 0.0002465878693300986, 'samples': 14715648, 'steps': 76643, 'loss/train': 1.022153377532959} 08/31/2021 03:08:25 - INFO - __main__ - Step 76645: {'lr': 0.00024658256308081946, 'samples': 14715840, 'steps': 76644, 'loss/train': 1.4187142848968506} 08/31/2021 03:08:25 - INFO - __main__ - Step 76646: {'lr': 0.00024657725683308, 'samples': 14716032, 'steps': 76645, 'loss/train': 0.8004674911499023} 08/31/2021 03:08:25 - INFO - __main__ - Step 76647: {'lr': 0.0002465719505868829, 'samples': 14716224, 'steps': 76646, 'loss/train': 1.3745325803756714} 08/31/2021 03:08:27 - INFO - __main__ - Step 76648: {'lr': 0.00024656664434223043, 'samples': 14716416, 'steps': 76647, 'loss/train': 0.6902081370353699} 08/31/2021 03:08:28 - INFO - __main__ - Step 76649: {'lr': 0.00024656133809912494, 'samples': 14716608, 'steps': 76648, 'loss/train': 1.0808017253875732} 08/31/2021 03:08:28 - INFO - __main__ - Step 76650: {'lr': 0.00024655603185756887, 'samples': 14716800, 'steps': 76649, 'loss/train': 1.0147422552108765} 08/31/2021 03:08:28 - INFO - __main__ - Step 76651: {'lr': 0.00024655072561756457, 'samples': 14716992, 'steps': 76650, 'loss/train': 0.762976348400116} 08/31/2021 03:08:29 - INFO - __main__ - Step 76652: {'lr': 0.0002465454193791145, 'samples': 14717184, 'steps': 76651, 'loss/train': 0.6043115854263306} 08/31/2021 03:08:29 - INFO - __main__ - Step 76653: {'lr': 0.00024654011314222097, 'samples': 14717376, 'steps': 76652, 'loss/train': 1.5899056196212769} 08/31/2021 03:08:31 - INFO - __main__ - Step 76654: {'lr': 0.00024653480690688654, 'samples': 14717568, 'steps': 76653, 'loss/train': 1.7249081134796143} 08/31/2021 03:08:31 - INFO - __main__ - Step 76655: {'lr': 0.00024652950067311337, 'samples': 14717760, 'steps': 76654, 'loss/train': 0.705153226852417} 08/31/2021 03:08:31 - INFO - __main__ - Step 76656: {'lr': 0.00024652419444090394, 'samples': 14717952, 'steps': 76655, 'loss/train': 1.5029761791229248} 08/31/2021 03:08:32 - INFO - __main__ - Step 76657: {'lr': 0.00024651888821026064, 'samples': 14718144, 'steps': 76656, 'loss/train': 1.4602957963943481} 08/31/2021 03:08:32 - INFO - __main__ - Step 76658: {'lr': 0.0002465135819811859, 'samples': 14718336, 'steps': 76657, 'loss/train': 1.2200140953063965} 08/31/2021 03:08:34 - INFO - __main__ - Step 76659: {'lr': 0.0002465082757536821, 'samples': 14718528, 'steps': 76658, 'loss/train': 1.2902668714523315} 08/31/2021 03:08:34 - INFO - __main__ - Step 76660: {'lr': 0.0002465029695277516, 'samples': 14718720, 'steps': 76659, 'loss/train': 2.3497211933135986} 08/31/2021 03:08:34 - INFO - __main__ - Step 76661: {'lr': 0.0002464976633033968, 'samples': 14718912, 'steps': 76660, 'loss/train': 1.2474250793457031} 08/31/2021 03:08:35 - INFO - __main__ - Step 76662: {'lr': 0.0002464923570806201, 'samples': 14719104, 'steps': 76661, 'loss/train': 1.4179624319076538} 08/31/2021 03:08:35 - INFO - __main__ - Step 76663: {'lr': 0.00024648705085942386, 'samples': 14719296, 'steps': 76662, 'loss/train': 0.4700077474117279} 08/31/2021 03:08:35 - INFO - __main__ - Step 76664: {'lr': 0.0002464817446398106, 'samples': 14719488, 'steps': 76663, 'loss/train': 1.1045559644699097} 08/31/2021 03:08:37 - INFO - __main__ - Step 76665: {'lr': 0.00024647643842178247, 'samples': 14719680, 'steps': 76664, 'loss/train': 1.1370768547058105} 08/31/2021 03:08:37 - INFO - __main__ - Step 76666: {'lr': 0.0002464711322053421, 'samples': 14719872, 'steps': 76665, 'loss/train': 1.184302568435669} 08/31/2021 03:08:38 - INFO - __main__ - Step 76667: {'lr': 0.0002464658259904919, 'samples': 14720064, 'steps': 76666, 'loss/train': 0.9237724542617798} 08/31/2021 03:08:38 - INFO - __main__ - Step 76668: {'lr': 0.000246460519777234, 'samples': 14720256, 'steps': 76667, 'loss/train': 1.3973802328109741} 08/31/2021 03:08:38 - INFO - __main__ - Step 76669: {'lr': 0.00024645521356557096, 'samples': 14720448, 'steps': 76668, 'loss/train': 1.620729684829712} 08/31/2021 03:08:40 - INFO - __main__ - Step 76670: {'lr': 0.0002464499073555051, 'samples': 14720640, 'steps': 76669, 'loss/train': 1.2306498289108276} 08/31/2021 03:08:40 - INFO - __main__ - Step 76671: {'lr': 0.0002464446011470389, 'samples': 14720832, 'steps': 76670, 'loss/train': 2.0076887607574463} 08/31/2021 03:08:41 - INFO - __main__ - Step 76672: {'lr': 0.0002464392949401747, 'samples': 14721024, 'steps': 76671, 'loss/train': 1.2467758655548096} 08/31/2021 03:08:41 - INFO - __main__ - Step 76673: {'lr': 0.00024643398873491485, 'samples': 14721216, 'steps': 76672, 'loss/train': 1.5111178159713745} 08/31/2021 03:08:41 - INFO - __main__ - Step 76674: {'lr': 0.00024642868253126185, 'samples': 14721408, 'steps': 76673, 'loss/train': 0.9508521556854248} 08/31/2021 03:08:43 - INFO - __main__ - Step 76675: {'lr': 0.000246423376329218, 'samples': 14721600, 'steps': 76674, 'loss/train': 1.3065433502197266} 08/31/2021 03:08:43 - INFO - __main__ - Step 76676: {'lr': 0.00024641807012878574, 'samples': 14721792, 'steps': 76675, 'loss/train': 1.2350250482559204} 08/31/2021 03:08:44 - INFO - __main__ - Step 76677: {'lr': 0.00024641276392996746, 'samples': 14721984, 'steps': 76676, 'loss/train': 1.4769306182861328} 08/31/2021 03:08:44 - INFO - __main__ - Step 76678: {'lr': 0.0002464074577327655, 'samples': 14722176, 'steps': 76677, 'loss/train': 0.9574155807495117} 08/31/2021 03:08:44 - INFO - __main__ - Step 76679: {'lr': 0.0002464021515371823, 'samples': 14722368, 'steps': 76678, 'loss/train': 1.1605160236358643} 08/31/2021 03:08:46 - INFO - __main__ - Step 76680: {'lr': 0.0002463968453432203, 'samples': 14722560, 'steps': 76679, 'loss/train': 1.3969711065292358} 08/31/2021 03:08:47 - INFO - __main__ - Step 76681: {'lr': 0.00024639153915088176, 'samples': 14722752, 'steps': 76680, 'loss/train': 1.4326727390289307} 08/31/2021 03:08:47 - INFO - __main__ - Step 76682: {'lr': 0.00024638623296016914, 'samples': 14722944, 'steps': 76681, 'loss/train': 1.07416570186615} 08/31/2021 03:08:48 - INFO - __main__ - Step 76683: {'lr': 0.0002463809267710848, 'samples': 14723136, 'steps': 76682, 'loss/train': 1.6003954410552979} 08/31/2021 03:08:48 - INFO - __main__ - Step 76684: {'lr': 0.0002463756205836312, 'samples': 14723328, 'steps': 76683, 'loss/train': 0.12767383456230164} 08/31/2021 03:08:48 - INFO - __main__ - Step 76685: {'lr': 0.00024637031439781067, 'samples': 14723520, 'steps': 76684, 'loss/train': 1.7316004037857056} 08/31/2021 03:08:50 - INFO - __main__ - Step 76686: {'lr': 0.0002463650082136256, 'samples': 14723712, 'steps': 76685, 'loss/train': 1.2688008546829224} 08/31/2021 03:08:50 - INFO - __main__ - Step 76687: {'lr': 0.00024635970203107843, 'samples': 14723904, 'steps': 76686, 'loss/train': 1.3355910778045654} 08/31/2021 03:08:51 - INFO - __main__ - Step 76688: {'lr': 0.00024635439585017155, 'samples': 14724096, 'steps': 76687, 'loss/train': 0.8672897815704346} 08/31/2021 03:08:51 - INFO - __main__ - Step 76689: {'lr': 0.00024634908967090724, 'samples': 14724288, 'steps': 76688, 'loss/train': 0.8167523741722107} 08/31/2021 03:08:52 - INFO - __main__ - Step 76690: {'lr': 0.00024634378349328804, 'samples': 14724480, 'steps': 76689, 'loss/train': 1.0722298622131348} 08/31/2021 03:08:53 - INFO - __main__ - Step 76691: {'lr': 0.00024633847731731623, 'samples': 14724672, 'steps': 76690, 'loss/train': 1.1877973079681396} 08/31/2021 03:08:54 - INFO - __main__ - Step 76692: {'lr': 0.00024633317114299425, 'samples': 14724864, 'steps': 76691, 'loss/train': 1.5230424404144287} 08/31/2021 03:08:54 - INFO - __main__ - Step 76693: {'lr': 0.00024632786497032455, 'samples': 14725056, 'steps': 76692, 'loss/train': 1.932791829109192} 08/31/2021 03:08:54 - INFO - __main__ - Step 76694: {'lr': 0.0002463225587993095, 'samples': 14725248, 'steps': 76693, 'loss/train': 0.49835601449012756} 08/31/2021 03:08:55 - INFO - __main__ - Step 76695: {'lr': 0.0002463172526299514, 'samples': 14725440, 'steps': 76694, 'loss/train': 1.4544049501419067} 08/31/2021 03:08:55 - INFO - __main__ - Step 76696: {'lr': 0.0002463119464622526, 'samples': 14725632, 'steps': 76695, 'loss/train': 0.07218638062477112} 08/31/2021 03:08:57 - INFO - __main__ - Step 76697: {'lr': 0.00024630664029621563, 'samples': 14725824, 'steps': 76696, 'loss/train': 0.17950084805488586} 08/31/2021 03:08:58 - INFO - __main__ - Step 76698: {'lr': 0.00024630133413184284, 'samples': 14726016, 'steps': 76697, 'loss/train': 0.2668643891811371} 08/31/2021 03:08:58 - INFO - __main__ - Step 76699: {'lr': 0.0002462960279691366, 'samples': 14726208, 'steps': 76698, 'loss/train': 1.893229365348816} 08/31/2021 03:08:59 - INFO - __main__ - Step 76700: {'lr': 0.0002462907218080993, 'samples': 14726400, 'steps': 76699, 'loss/train': 1.7805088758468628} 08/31/2021 03:08:59 - INFO - __main__ - Step 76701: {'lr': 0.00024628541564873337, 'samples': 14726592, 'steps': 76700, 'loss/train': 1.835086464881897} 08/31/2021 03:08:59 - INFO - __main__ - Step 76702: {'lr': 0.00024628010949104116, 'samples': 14726784, 'steps': 76701, 'loss/train': 1.3076791763305664} 08/31/2021 03:09:01 - INFO - __main__ - Step 76703: {'lr': 0.00024627480333502507, 'samples': 14726976, 'steps': 76702, 'loss/train': 1.3729194402694702} 08/31/2021 03:09:01 - INFO - __main__ - Step 76704: {'lr': 0.0002462694971806875, 'samples': 14727168, 'steps': 76703, 'loss/train': 1.1234050989151} 08/31/2021 03:09:02 - INFO - __main__ - Step 76705: {'lr': 0.00024626419102803085, 'samples': 14727360, 'steps': 76704, 'loss/train': 1.1998084783554077} 08/31/2021 03:09:02 - INFO - __main__ - Step 76706: {'lr': 0.0002462588848770575, 'samples': 14727552, 'steps': 76705, 'loss/train': 1.7037525177001953} 08/31/2021 03:09:02 - INFO - __main__ - Step 76707: {'lr': 0.00024625357872776996, 'samples': 14727744, 'steps': 76706, 'loss/train': 1.3030214309692383} 08/31/2021 03:09:04 - INFO - __main__ - Step 76708: {'lr': 0.0002462482725801703, 'samples': 14727936, 'steps': 76707, 'loss/train': 1.1041412353515625} 08/31/2021 03:09:04 - INFO - __main__ - Step 76709: {'lr': 0.0002462429664342612, 'samples': 14728128, 'steps': 76708, 'loss/train': 1.261474609375} 08/31/2021 03:09:04 - INFO - __main__ - Step 76710: {'lr': 0.000246237660290045, 'samples': 14728320, 'steps': 76709, 'loss/train': 0.552486002445221} 08/31/2021 03:09:05 - INFO - __main__ - Step 76711: {'lr': 0.00024623235414752395, 'samples': 14728512, 'steps': 76710, 'loss/train': 0.9494842886924744} 08/31/2021 03:09:05 - INFO - __main__ - Step 76712: {'lr': 0.00024622704800670057, 'samples': 14728704, 'steps': 76711, 'loss/train': 0.6801669597625732} 08/31/2021 03:09:07 - INFO - __main__ - Step 76713: {'lr': 0.0002462217418675772, 'samples': 14728896, 'steps': 76712, 'loss/train': 0.6205145716667175} 08/31/2021 03:09:07 - INFO - __main__ - Step 76714: {'lr': 0.00024621643573015633, 'samples': 14729088, 'steps': 76713, 'loss/train': 1.1571110486984253} 08/31/2021 03:09:07 - INFO - __main__ - Step 76715: {'lr': 0.00024621112959444025, 'samples': 14729280, 'steps': 76714, 'loss/train': 0.9813156723976135} 08/31/2021 03:09:08 - INFO - __main__ - Step 76716: {'lr': 0.00024620582346043134, 'samples': 14729472, 'steps': 76715, 'loss/train': 1.9125690460205078} 08/31/2021 03:09:08 - INFO - __main__ - Step 76717: {'lr': 0.00024620051732813207, 'samples': 14729664, 'steps': 76716, 'loss/train': 2.1581995487213135} 08/31/2021 03:09:08 - INFO - __main__ - Step 76718: {'lr': 0.00024619521119754475, 'samples': 14729856, 'steps': 76717, 'loss/train': 1.6628438234329224} 08/31/2021 03:09:10 - INFO - __main__ - Step 76719: {'lr': 0.0002461899050686719, 'samples': 14730048, 'steps': 76718, 'loss/train': 1.326878547668457} 08/31/2021 03:09:10 - INFO - __main__ - Step 76720: {'lr': 0.00024618459894151573, 'samples': 14730240, 'steps': 76719, 'loss/train': 1.481653094291687} 08/31/2021 03:09:11 - INFO - __main__ - Step 76721: {'lr': 0.0002461792928160788, 'samples': 14730432, 'steps': 76720, 'loss/train': 1.0803128480911255} 08/31/2021 03:09:11 - INFO - __main__ - Step 76722: {'lr': 0.00024617398669236337, 'samples': 14730624, 'steps': 76721, 'loss/train': 0.77934330701828} 08/31/2021 03:09:11 - INFO - __main__ - Step 76723: {'lr': 0.0002461686805703719, 'samples': 14730816, 'steps': 76722, 'loss/train': 0.8478450179100037} 08/31/2021 03:09:13 - INFO - __main__ - Step 76724: {'lr': 0.0002461633744501067, 'samples': 14731008, 'steps': 76723, 'loss/train': 1.4987653493881226} 08/31/2021 03:09:13 - INFO - __main__ - Step 76725: {'lr': 0.0002461580683315703, 'samples': 14731200, 'steps': 76724, 'loss/train': 1.1862307786941528} 08/31/2021 03:09:14 - INFO - __main__ - Step 76726: {'lr': 0.00024615276221476496, 'samples': 14731392, 'steps': 76725, 'loss/train': 2.1192500591278076} 08/31/2021 03:09:14 - INFO - __main__ - Step 76727: {'lr': 0.0002461474560996931, 'samples': 14731584, 'steps': 76726, 'loss/train': 1.2754606008529663} 08/31/2021 03:09:14 - INFO - __main__ - Step 76728: {'lr': 0.00024614214998635724, 'samples': 14731776, 'steps': 76727, 'loss/train': 0.8764550685882568} 08/31/2021 03:09:16 - INFO - __main__ - Step 76729: {'lr': 0.0002461368438747596, 'samples': 14731968, 'steps': 76728, 'loss/train': 1.2445709705352783} 08/31/2021 03:09:17 - INFO - __main__ - Step 76730: {'lr': 0.00024613153776490267, 'samples': 14732160, 'steps': 76729, 'loss/train': 0.0448739193379879} 08/31/2021 03:09:17 - INFO - __main__ - Step 76731: {'lr': 0.0002461262316567888, 'samples': 14732352, 'steps': 76730, 'loss/train': 0.13454392552375793} 08/31/2021 03:09:17 - INFO - __main__ - Step 76732: {'lr': 0.0002461209255504204, 'samples': 14732544, 'steps': 76731, 'loss/train': 0.8469882011413574} 08/31/2021 03:09:18 - INFO - __main__ - Step 76733: {'lr': 0.0002461156194457998, 'samples': 14732736, 'steps': 76732, 'loss/train': 1.1255238056182861} 08/31/2021 03:09:18 - INFO - __main__ - Step 76734: {'lr': 0.0002461103133429295, 'samples': 14732928, 'steps': 76733, 'loss/train': 1.1264381408691406} 08/31/2021 03:09:20 - INFO - __main__ - Step 76735: {'lr': 0.00024610500724181185, 'samples': 14733120, 'steps': 76734, 'loss/train': 0.5638050436973572} 08/31/2021 03:09:21 - INFO - __main__ - Step 76736: {'lr': 0.00024609970114244917, 'samples': 14733312, 'steps': 76735, 'loss/train': 1.4910026788711548} 08/31/2021 03:09:21 - INFO - __main__ - Step 76737: {'lr': 0.00024609439504484393, 'samples': 14733504, 'steps': 76736, 'loss/train': 0.5732797384262085} 08/31/2021 03:09:21 - INFO - __main__ - Step 76738: {'lr': 0.00024608908894899846, 'samples': 14733696, 'steps': 76737, 'loss/train': 0.42396271228790283} 08/31/2021 03:09:22 - INFO - __main__ - Step 76739: {'lr': 0.0002460837828549152, 'samples': 14733888, 'steps': 76738, 'loss/train': 1.2328110933303833} 08/31/2021 03:09:23 - INFO - __main__ - Step 76740: {'lr': 0.0002460784767625965, 'samples': 14734080, 'steps': 76739, 'loss/train': 0.23237290978431702} 08/31/2021 03:09:24 - INFO - __main__ - Step 76741: {'lr': 0.0002460731706720449, 'samples': 14734272, 'steps': 76740, 'loss/train': 0.7120025753974915} 08/31/2021 03:09:24 - INFO - __main__ - Step 76742: {'lr': 0.00024606786458326255, 'samples': 14734464, 'steps': 76741, 'loss/train': 1.1811494827270508} 08/31/2021 03:09:25 - INFO - __main__ - Step 76743: {'lr': 0.000246062558496252, 'samples': 14734656, 'steps': 76742, 'loss/train': 1.246167778968811} 08/31/2021 03:09:25 - INFO - __main__ - Step 76744: {'lr': 0.0002460572524110156, 'samples': 14734848, 'steps': 76743, 'loss/train': 1.4521104097366333} 08/31/2021 03:09:25 - INFO - __main__ - Step 76745: {'lr': 0.0002460519463275557, 'samples': 14735040, 'steps': 76744, 'loss/train': 0.5998066067695618} 08/31/2021 03:09:27 - INFO - __main__ - Step 76746: {'lr': 0.00024604664024587474, 'samples': 14735232, 'steps': 76745, 'loss/train': 0.4295734763145447} 08/31/2021 03:09:27 - INFO - __main__ - Step 76747: {'lr': 0.0002460413341659751, 'samples': 14735424, 'steps': 76746, 'loss/train': 1.2836796045303345} 08/31/2021 03:09:28 - INFO - __main__ - Step 76748: {'lr': 0.0002460360280878593, 'samples': 14735616, 'steps': 76747, 'loss/train': 1.1632840633392334} 08/31/2021 03:09:28 - INFO - __main__ - Step 76749: {'lr': 0.0002460307220115295, 'samples': 14735808, 'steps': 76748, 'loss/train': 0.6877043843269348} 08/31/2021 03:09:28 - INFO - __main__ - Step 76750: {'lr': 0.00024602541593698817, 'samples': 14736000, 'steps': 76749, 'loss/train': 1.5211678743362427} 08/31/2021 03:09:30 - INFO - __main__ - Step 76751: {'lr': 0.00024602010986423783, 'samples': 14736192, 'steps': 76750, 'loss/train': 1.2044625282287598} 08/31/2021 03:09:30 - INFO - __main__ - Step 76752: {'lr': 0.00024601480379328065, 'samples': 14736384, 'steps': 76751, 'loss/train': 0.5693367123603821} 08/31/2021 03:09:31 - INFO - __main__ - Step 76753: {'lr': 0.0002460094977241192, 'samples': 14736576, 'steps': 76752, 'loss/train': 1.4335428476333618} 08/31/2021 03:09:31 - INFO - __main__ - Step 76754: {'lr': 0.00024600419165675576, 'samples': 14736768, 'steps': 76753, 'loss/train': 0.8833388090133667} 08/31/2021 03:09:31 - INFO - __main__ - Step 76755: {'lr': 0.0002459988855911928, 'samples': 14736960, 'steps': 76754, 'loss/train': 0.22007019817829132} 08/31/2021 03:09:32 - INFO - __main__ - Step 76756: {'lr': 0.0002459935795274327, 'samples': 14737152, 'steps': 76755, 'loss/train': 1.5125712156295776} 08/31/2021 03:09:33 - INFO - __main__ - Step 76757: {'lr': 0.0002459882734654778, 'samples': 14737344, 'steps': 76756, 'loss/train': 0.17745976150035858} 08/31/2021 03:09:34 - INFO - __main__ - Step 76758: {'lr': 0.00024598296740533054, 'samples': 14737536, 'steps': 76757, 'loss/train': 1.3606462478637695} 08/31/2021 03:09:34 - INFO - __main__ - Step 76759: {'lr': 0.00024597766134699326, 'samples': 14737728, 'steps': 76758, 'loss/train': 0.8953026533126831} 08/31/2021 03:09:35 - INFO - __main__ - Step 76760: {'lr': 0.0002459723552904684, 'samples': 14737920, 'steps': 76759, 'loss/train': 1.160839319229126} 08/31/2021 03:09:35 - INFO - __main__ - Step 76761: {'lr': 0.0002459670492357584, 'samples': 14738112, 'steps': 76760, 'loss/train': 4.510353088378906} 08/31/2021 03:09:37 - INFO - __main__ - Step 76762: {'lr': 0.00024596174318286556, 'samples': 14738304, 'steps': 76761, 'loss/train': 2.125217914581299} 08/31/2021 03:09:38 - INFO - __main__ - Step 76763: {'lr': 0.00024595643713179227, 'samples': 14738496, 'steps': 76762, 'loss/train': 0.5314230918884277} 08/31/2021 03:09:38 - INFO - __main__ - Step 76764: {'lr': 0.00024595113108254093, 'samples': 14738688, 'steps': 76763, 'loss/train': 0.4840681850910187} 08/31/2021 03:09:38 - INFO - __main__ - Step 76765: {'lr': 0.000245945825035114, 'samples': 14738880, 'steps': 76764, 'loss/train': 0.028742382302880287} 08/31/2021 03:09:39 - INFO - __main__ - Step 76766: {'lr': 0.00024594051898951374, 'samples': 14739072, 'steps': 76765, 'loss/train': 0.16724665462970734} 08/31/2021 03:09:40 - INFO - __main__ - Step 76767: {'lr': 0.00024593521294574266, 'samples': 14739264, 'steps': 76766, 'loss/train': 0.8185701966285706} 08/31/2021 03:09:41 - INFO - __main__ - Step 76768: {'lr': 0.0002459299069038031, 'samples': 14739456, 'steps': 76767, 'loss/train': 1.2447260618209839} 08/31/2021 03:09:41 - INFO - __main__ - Step 76769: {'lr': 0.00024592460086369746, 'samples': 14739648, 'steps': 76768, 'loss/train': 0.22249244153499603} 08/31/2021 03:09:41 - INFO - __main__ - Step 76770: {'lr': 0.00024591929482542816, 'samples': 14739840, 'steps': 76769, 'loss/train': 1.3481030464172363} 08/31/2021 03:09:42 - INFO - __main__ - Step 76771: {'lr': 0.0002459139887889975, 'samples': 14740032, 'steps': 76770, 'loss/train': 0.763323187828064} 08/31/2021 03:09:43 - INFO - __main__ - Step 76772: {'lr': 0.000245908682754408, 'samples': 14740224, 'steps': 76771, 'loss/train': 0.48036178946495056} 08/31/2021 03:09:44 - INFO - __main__ - Step 76773: {'lr': 0.00024590337672166196, 'samples': 14740416, 'steps': 76772, 'loss/train': 1.4406412839889526} 08/31/2021 03:09:44 - INFO - __main__ - Step 76774: {'lr': 0.00024589807069076177, 'samples': 14740608, 'steps': 76773, 'loss/train': 1.8469895124435425} 08/31/2021 03:09:44 - INFO - __main__ - Step 76775: {'lr': 0.00024589276466171003, 'samples': 14740800, 'steps': 76774, 'loss/train': 0.7788040637969971} 08/31/2021 03:09:45 - INFO - __main__ - Step 76776: {'lr': 0.00024588745863450876, 'samples': 14740992, 'steps': 76775, 'loss/train': 1.4607387781143188} 08/31/2021 03:09:46 - INFO - __main__ - Step 76777: {'lr': 0.00024588215260916055, 'samples': 14741184, 'steps': 76776, 'loss/train': 1.1841262578964233} 08/31/2021 03:09:47 - INFO - __main__ - Step 76778: {'lr': 0.0002458768465856678, 'samples': 14741376, 'steps': 76777, 'loss/train': 1.4250190258026123} 08/31/2021 03:09:47 - INFO - __main__ - Step 76779: {'lr': 0.00024587154056403287, 'samples': 14741568, 'steps': 76778, 'loss/train': 1.3079307079315186} 08/31/2021 03:09:47 - INFO - __main__ - Step 76780: {'lr': 0.00024586623454425817, 'samples': 14741760, 'steps': 76779, 'loss/train': 0.953400194644928} 08/31/2021 03:09:48 - INFO - __main__ - Step 76781: {'lr': 0.00024586092852634607, 'samples': 14741952, 'steps': 76780, 'loss/train': 0.9493175745010376} 08/31/2021 03:09:49 - INFO - __main__ - Step 76782: {'lr': 0.00024585562251029896, 'samples': 14742144, 'steps': 76781, 'loss/train': 2.2719974517822266} 08/31/2021 03:09:50 - INFO - __main__ - Step 76783: {'lr': 0.0002458503164961193, 'samples': 14742336, 'steps': 76782, 'loss/train': 1.5534554719924927} 08/31/2021 03:09:50 - INFO - __main__ - Step 76784: {'lr': 0.00024584501048380937, 'samples': 14742528, 'steps': 76783, 'loss/train': 1.0572041273117065} 08/31/2021 03:09:51 - INFO - __main__ - Step 76785: {'lr': 0.0002458397044733716, 'samples': 14742720, 'steps': 76784, 'loss/train': 0.9918142557144165} 08/31/2021 03:09:51 - INFO - __main__ - Step 76786: {'lr': 0.0002458343984648084, 'samples': 14742912, 'steps': 76785, 'loss/train': 1.2507346868515015} 08/31/2021 03:09:51 - INFO - __main__ - Step 76787: {'lr': 0.0002458290924581222, 'samples': 14743104, 'steps': 76786, 'loss/train': 5.785864353179932} 08/31/2021 03:09:53 - INFO - __main__ - Step 76788: {'lr': 0.00024582378645331544, 'samples': 14743296, 'steps': 76787, 'loss/train': 1.3086544275283813} 08/31/2021 03:09:54 - INFO - __main__ - Step 76789: {'lr': 0.00024581848045039027, 'samples': 14743488, 'steps': 76788, 'loss/train': 0.6911213994026184} 08/31/2021 03:09:54 - INFO - __main__ - Step 76790: {'lr': 0.0002458131744493493, 'samples': 14743680, 'steps': 76789, 'loss/train': 0.16971459984779358} 08/31/2021 03:09:55 - INFO - __main__ - Step 76791: {'lr': 0.0002458078684501948, 'samples': 14743872, 'steps': 76790, 'loss/train': 0.5233926177024841} 08/31/2021 03:09:55 - INFO - __main__ - Step 76792: {'lr': 0.0002458025624529292, 'samples': 14744064, 'steps': 76791, 'loss/train': 0.9864898324012756} 08/31/2021 03:09:57 - INFO - __main__ - Step 76793: {'lr': 0.0002457972564575549, 'samples': 14744256, 'steps': 76792, 'loss/train': 1.1950173377990723} 08/31/2021 03:09:57 - INFO - __main__ - Step 76794: {'lr': 0.00024579195046407434, 'samples': 14744448, 'steps': 76793, 'loss/train': 1.2348978519439697} 08/31/2021 03:09:57 - INFO - __main__ - Step 76795: {'lr': 0.0002457866444724898, 'samples': 14744640, 'steps': 76794, 'loss/train': 1.3375258445739746} 08/31/2021 03:09:58 - INFO - __main__ - Step 76796: {'lr': 0.0002457813384828038, 'samples': 14744832, 'steps': 76795, 'loss/train': 1.0318080186843872} 08/31/2021 03:09:58 - INFO - __main__ - Step 76797: {'lr': 0.0002457760324950186, 'samples': 14745024, 'steps': 76796, 'loss/train': 0.17008520662784576} 08/31/2021 03:10:00 - INFO - __main__ - Step 76798: {'lr': 0.0002457707265091367, 'samples': 14745216, 'steps': 76797, 'loss/train': 1.0431355237960815} 08/31/2021 03:10:00 - INFO - __main__ - Step 76799: {'lr': 0.0002457654205251604, 'samples': 14745408, 'steps': 76798, 'loss/train': 0.4066864848136902} 08/31/2021 03:10:00 - INFO - __main__ - Step 76800: {'lr': 0.00024576011454309217, 'samples': 14745600, 'steps': 76799, 'loss/train': 1.0010658502578735} 08/31/2021 03:10:01 - INFO - __main__ - Step 76801: {'lr': 0.0002457548085629345, 'samples': 14745792, 'steps': 76800, 'loss/train': 1.3051434755325317} 08/31/2021 03:10:01 - INFO - __main__ - Step 76802: {'lr': 0.0002457495025846895, 'samples': 14745984, 'steps': 76801, 'loss/train': 1.6116586923599243} 08/31/2021 03:10:02 - INFO - __main__ - Step 76803: {'lr': 0.0002457441966083597, 'samples': 14746176, 'steps': 76802, 'loss/train': 1.0958187580108643} 08/31/2021 03:10:03 - INFO - __main__ - Step 76804: {'lr': 0.0002457388906339475, 'samples': 14746368, 'steps': 76803, 'loss/train': 1.1623427867889404} 08/31/2021 03:10:04 - INFO - __main__ - Step 76805: {'lr': 0.0002457335846614553, 'samples': 14746560, 'steps': 76804, 'loss/train': 1.2650165557861328} 08/31/2021 03:10:04 - INFO - __main__ - Step 76806: {'lr': 0.0002457282786908855, 'samples': 14746752, 'steps': 76805, 'loss/train': 1.0915415287017822} 08/31/2021 03:10:04 - INFO - __main__ - Step 76807: {'lr': 0.00024572297272224046, 'samples': 14746944, 'steps': 76806, 'loss/train': 0.3857073485851288} 08/31/2021 03:10:05 - INFO - __main__ - Step 76808: {'lr': 0.0002457176667555226, 'samples': 14747136, 'steps': 76807, 'loss/train': 1.1641409397125244} 08/31/2021 03:10:06 - INFO - __main__ - Step 76809: {'lr': 0.0002457123607907343, 'samples': 14747328, 'steps': 76808, 'loss/train': 1.100390076637268} 08/31/2021 03:10:07 - INFO - __main__ - Step 76810: {'lr': 0.00024570705482787787, 'samples': 14747520, 'steps': 76809, 'loss/train': 1.3151136636734009} 08/31/2021 03:10:07 - INFO - __main__ - Step 76811: {'lr': 0.00024570174886695583, 'samples': 14747712, 'steps': 76810, 'loss/train': 1.3627772331237793} 08/31/2021 03:10:07 - INFO - __main__ - Step 76812: {'lr': 0.0002456964429079705, 'samples': 14747904, 'steps': 76811, 'loss/train': 1.5126357078552246} 08/31/2021 03:10:08 - INFO - __main__ - Step 76813: {'lr': 0.0002456911369509243, 'samples': 14748096, 'steps': 76812, 'loss/train': 1.247465968132019} 08/31/2021 03:10:09 - INFO - __main__ - Step 76814: {'lr': 0.0002456858309958196, 'samples': 14748288, 'steps': 76813, 'loss/train': 1.2348369359970093} 08/31/2021 03:10:10 - INFO - __main__ - Step 76815: {'lr': 0.00024568052504265895, 'samples': 14748480, 'steps': 76814, 'loss/train': 1.324292540550232} 08/31/2021 03:10:10 - INFO - __main__ - Step 76816: {'lr': 0.0002456752190914444, 'samples': 14748672, 'steps': 76815, 'loss/train': 1.0120596885681152} 08/31/2021 03:10:10 - INFO - __main__ - Step 76817: {'lr': 0.0002456699131421786, 'samples': 14748864, 'steps': 76816, 'loss/train': 1.1259115934371948} 08/31/2021 03:10:11 - INFO - __main__ - Step 76818: {'lr': 0.0002456646071948638, 'samples': 14749056, 'steps': 76817, 'loss/train': 0.13043048977851868} 08/31/2021 03:10:12 - INFO - __main__ - Step 76819: {'lr': 0.0002456593012495025, 'samples': 14749248, 'steps': 76818, 'loss/train': 1.0165379047393799} 08/31/2021 03:10:13 - INFO - __main__ - Step 76820: {'lr': 0.00024565399530609706, 'samples': 14749440, 'steps': 76819, 'loss/train': 1.665590524673462} 08/31/2021 03:10:13 - INFO - __main__ - Step 76821: {'lr': 0.0002456486893646499, 'samples': 14749632, 'steps': 76820, 'loss/train': 1.2008891105651855} 08/31/2021 03:10:13 - INFO - __main__ - Step 76822: {'lr': 0.0002456433834251633, 'samples': 14749824, 'steps': 76821, 'loss/train': 2.292696952819824} 08/31/2021 03:10:14 - INFO - __main__ - Step 76823: {'lr': 0.00024563807748763974, 'samples': 14750016, 'steps': 76822, 'loss/train': 1.4979264736175537} 08/31/2021 03:10:14 - INFO - __main__ - Step 76824: {'lr': 0.00024563277155208163, 'samples': 14750208, 'steps': 76823, 'loss/train': 1.2596796751022339} 08/31/2021 03:10:16 - INFO - __main__ - Step 76825: {'lr': 0.0002456274656184913, 'samples': 14750400, 'steps': 76824, 'loss/train': 1.5226032733917236} 08/31/2021 03:10:16 - INFO - __main__ - Step 76826: {'lr': 0.0002456221596868712, 'samples': 14750592, 'steps': 76825, 'loss/train': 1.5034079551696777} 08/31/2021 03:10:17 - INFO - __main__ - Step 76827: {'lr': 0.0002456168537572236, 'samples': 14750784, 'steps': 76826, 'loss/train': 1.366033911705017} 08/31/2021 03:10:17 - INFO - __main__ - Step 76828: {'lr': 0.00024561154782955116, 'samples': 14750976, 'steps': 76827, 'loss/train': 0.18663713335990906} 08/31/2021 03:10:17 - INFO - __main__ - Step 76829: {'lr': 0.000245606241903856, 'samples': 14751168, 'steps': 76828, 'loss/train': 0.6228228807449341} 08/31/2021 03:10:19 - INFO - __main__ - Step 76830: {'lr': 0.0002456009359801405, 'samples': 14751360, 'steps': 76829, 'loss/train': 1.4863322973251343} 08/31/2021 03:10:19 - INFO - __main__ - Step 76831: {'lr': 0.00024559563005840723, 'samples': 14751552, 'steps': 76830, 'loss/train': 1.4243292808532715} 08/31/2021 03:10:19 - INFO - __main__ - Step 76832: {'lr': 0.0002455903241386585, 'samples': 14751744, 'steps': 76831, 'loss/train': 1.2461973428726196} 08/31/2021 03:10:20 - INFO - __main__ - Step 76833: {'lr': 0.0002455850182208967, 'samples': 14751936, 'steps': 76832, 'loss/train': 1.2219444513320923} 08/31/2021 03:10:20 - INFO - __main__ - Step 76834: {'lr': 0.0002455797123051242, 'samples': 14752128, 'steps': 76833, 'loss/train': 1.4689369201660156} 08/31/2021 03:10:22 - INFO - __main__ - Step 76835: {'lr': 0.0002455744063913434, 'samples': 14752320, 'steps': 76834, 'loss/train': 1.0131080150604248} 08/31/2021 03:10:22 - INFO - __main__ - Step 76836: {'lr': 0.00024556910047955676, 'samples': 14752512, 'steps': 76835, 'loss/train': 0.05913153663277626} 08/31/2021 03:10:23 - INFO - __main__ - Step 76837: {'lr': 0.00024556379456976656, 'samples': 14752704, 'steps': 76836, 'loss/train': 1.1461564302444458} 08/31/2021 03:10:23 - INFO - __main__ - Step 76838: {'lr': 0.0002455584886619753, 'samples': 14752896, 'steps': 76837, 'loss/train': 1.3227930068969727} 08/31/2021 03:10:23 - INFO - __main__ - Step 76839: {'lr': 0.00024555318275618527, 'samples': 14753088, 'steps': 76838, 'loss/train': 1.3677120208740234} 08/31/2021 03:10:25 - INFO - __main__ - Step 76840: {'lr': 0.0002455478768523989, 'samples': 14753280, 'steps': 76839, 'loss/train': 1.3015778064727783} 08/31/2021 03:10:25 - INFO - __main__ - Step 76841: {'lr': 0.0002455425709506186, 'samples': 14753472, 'steps': 76840, 'loss/train': 0.6917561888694763} 08/31/2021 03:10:26 - INFO - __main__ - Step 76842: {'lr': 0.0002455372650508469, 'samples': 14753664, 'steps': 76841, 'loss/train': 1.2980632781982422} 08/31/2021 03:10:26 - INFO - __main__ - Step 76843: {'lr': 0.0002455319591530859, 'samples': 14753856, 'steps': 76842, 'loss/train': 1.4163198471069336} 08/31/2021 03:10:27 - INFO - __main__ - Step 76844: {'lr': 0.0002455266532573381, 'samples': 14754048, 'steps': 76843, 'loss/train': 0.9255401492118835} 08/31/2021 03:10:29 - INFO - __main__ - Step 76845: {'lr': 0.00024552134736360593, 'samples': 14754240, 'steps': 76844, 'loss/train': 0.48049575090408325} 08/31/2021 03:10:29 - INFO - __main__ - Step 76846: {'lr': 0.0002455160414718918, 'samples': 14754432, 'steps': 76845, 'loss/train': 1.454932689666748} 08/31/2021 03:10:30 - INFO - __main__ - Step 76847: {'lr': 0.00024551073558219807, 'samples': 14754624, 'steps': 76846, 'loss/train': 0.028208985924720764} 08/31/2021 03:10:30 - INFO - __main__ - Step 76848: {'lr': 0.0002455054296945271, 'samples': 14754816, 'steps': 76847, 'loss/train': 1.1965482234954834} 08/31/2021 03:10:30 - INFO - __main__ - Step 76849: {'lr': 0.0002455001238088814, 'samples': 14755008, 'steps': 76848, 'loss/train': 1.2559022903442383} 08/31/2021 03:10:32 - INFO - __main__ - Step 76850: {'lr': 0.0002454948179252632, 'samples': 14755200, 'steps': 76849, 'loss/train': 1.046769380569458} 08/31/2021 03:10:32 - INFO - __main__ - Step 76851: {'lr': 0.000245489512043675, 'samples': 14755392, 'steps': 76850, 'loss/train': 1.5295004844665527} 08/31/2021 03:10:33 - INFO - __main__ - Step 76852: {'lr': 0.0002454842061641191, 'samples': 14755584, 'steps': 76851, 'loss/train': 1.7317196130752563} 08/31/2021 03:10:33 - INFO - __main__ - Step 76853: {'lr': 0.0002454789002865981, 'samples': 14755776, 'steps': 76852, 'loss/train': 1.1272070407867432} 08/31/2021 03:10:33 - INFO - __main__ - Step 76854: {'lr': 0.0002454735944111141, 'samples': 14755968, 'steps': 76853, 'loss/train': 1.1489018201828003} 08/31/2021 03:10:34 - INFO - __main__ - Step 76855: {'lr': 0.00024546828853766966, 'samples': 14756160, 'steps': 76854, 'loss/train': 1.1677696704864502} 08/31/2021 03:10:35 - INFO - __main__ - Step 76856: {'lr': 0.00024546298266626715, 'samples': 14756352, 'steps': 76855, 'loss/train': 0.6962173581123352} 08/31/2021 03:10:36 - INFO - __main__ - Step 76857: {'lr': 0.0002454576767969089, 'samples': 14756544, 'steps': 76856, 'loss/train': 1.6905499696731567} 08/31/2021 03:10:36 - INFO - __main__ - Step 76858: {'lr': 0.00024545237092959743, 'samples': 14756736, 'steps': 76857, 'loss/train': 1.413476586341858} 08/31/2021 03:10:36 - INFO - __main__ - Step 76859: {'lr': 0.000245447065064335, 'samples': 14756928, 'steps': 76858, 'loss/train': 1.1002682447433472} 08/31/2021 03:10:37 - INFO - __main__ - Step 76860: {'lr': 0.000245441759201124, 'samples': 14757120, 'steps': 76859, 'loss/train': 1.3813380002975464} 08/31/2021 03:10:38 - INFO - __main__ - Step 76861: {'lr': 0.00024543645333996694, 'samples': 14757312, 'steps': 76860, 'loss/train': 0.9088582396507263} 08/31/2021 03:10:39 - INFO - __main__ - Step 76862: {'lr': 0.00024543114748086617, 'samples': 14757504, 'steps': 76861, 'loss/train': 1.2510732412338257} 08/31/2021 03:10:39 - INFO - __main__ - Step 76863: {'lr': 0.000245425841623824, 'samples': 14757696, 'steps': 76862, 'loss/train': 1.284186840057373} 08/31/2021 03:10:39 - INFO - __main__ - Step 76864: {'lr': 0.0002454205357688429, 'samples': 14757888, 'steps': 76863, 'loss/train': 1.4757270812988281} 08/31/2021 03:10:40 - INFO - __main__ - Step 76865: {'lr': 0.0002454152299159253, 'samples': 14758080, 'steps': 76864, 'loss/train': 1.1844273805618286} 08/31/2021 03:10:42 - INFO - __main__ - Step 76866: {'lr': 0.0002454099240650734, 'samples': 14758272, 'steps': 76865, 'loss/train': 1.0484673976898193} 08/31/2021 03:10:42 - INFO - __main__ - Step 76867: {'lr': 0.0002454046182162898, 'samples': 14758464, 'steps': 76866, 'loss/train': 1.3843986988067627} 08/31/2021 03:10:42 - INFO - __main__ - Step 76868: {'lr': 0.00024539931236957675, 'samples': 14758656, 'steps': 76867, 'loss/train': 1.5335909128189087} 08/31/2021 03:10:43 - INFO - __main__ - Step 76869: {'lr': 0.0002453940065249368, 'samples': 14758848, 'steps': 76868, 'loss/train': 1.5559569597244263} 08/31/2021 03:10:43 - INFO - __main__ - Step 76870: {'lr': 0.0002453887006823722, 'samples': 14759040, 'steps': 76869, 'loss/train': 3.4014830589294434} 08/31/2021 03:10:44 - INFO - __main__ - Step 76871: {'lr': 0.0002453833948418853, 'samples': 14759232, 'steps': 76870, 'loss/train': 0.8033837676048279} 08/31/2021 03:10:44 - INFO - __main__ - Step 76872: {'lr': 0.0002453780890034786, 'samples': 14759424, 'steps': 76871, 'loss/train': 1.5589423179626465} 08/31/2021 03:10:45 - INFO - __main__ - Step 76873: {'lr': 0.0002453727831671545, 'samples': 14759616, 'steps': 76872, 'loss/train': 1.3875113725662231} 08/31/2021 03:10:46 - INFO - __main__ - Step 76874: {'lr': 0.00024536747733291535, 'samples': 14759808, 'steps': 76873, 'loss/train': 1.4752830266952515} 08/31/2021 03:10:46 - INFO - __main__ - Step 76875: {'lr': 0.00024536217150076357, 'samples': 14760000, 'steps': 76874, 'loss/train': 1.6644572019577026} 08/31/2021 03:10:47 - INFO - __main__ - Step 76876: {'lr': 0.0002453568656707015, 'samples': 14760192, 'steps': 76875, 'loss/train': 1.2541542053222656} 08/31/2021 03:10:47 - INFO - __main__ - Step 76877: {'lr': 0.0002453515598427315, 'samples': 14760384, 'steps': 76876, 'loss/train': 1.475039005279541} 08/31/2021 03:10:49 - INFO - __main__ - Step 76878: {'lr': 0.00024534625401685607, 'samples': 14760576, 'steps': 76877, 'loss/train': 1.402772068977356} 08/31/2021 03:10:50 - INFO - __main__ - Step 76879: {'lr': 0.00024534094819307753, 'samples': 14760768, 'steps': 76878, 'loss/train': 0.38839852809906006} 08/31/2021 03:10:50 - INFO - __main__ - Step 76880: {'lr': 0.00024533564237139827, 'samples': 14760960, 'steps': 76879, 'loss/train': 0.8099064230918884} 08/31/2021 03:10:50 - INFO - __main__ - Step 76881: {'lr': 0.00024533033655182074, 'samples': 14761152, 'steps': 76880, 'loss/train': 1.1151379346847534} 08/31/2021 03:10:51 - INFO - __main__ - Step 76882: {'lr': 0.00024532503073434726, 'samples': 14761344, 'steps': 76881, 'loss/train': 1.4948837757110596} 08/31/2021 03:10:51 - INFO - __main__ - Step 76883: {'lr': 0.0002453197249189803, 'samples': 14761536, 'steps': 76882, 'loss/train': 1.2929178476333618} 08/31/2021 03:10:53 - INFO - __main__ - Step 76884: {'lr': 0.00024531441910572214, 'samples': 14761728, 'steps': 76883, 'loss/train': 1.6121386289596558} 08/31/2021 03:10:53 - INFO - __main__ - Step 76885: {'lr': 0.00024530911329457525, 'samples': 14761920, 'steps': 76884, 'loss/train': 0.8800563812255859} 08/31/2021 03:10:54 - INFO - __main__ - Step 76886: {'lr': 0.000245303807485542, 'samples': 14762112, 'steps': 76885, 'loss/train': 1.1756376028060913} 08/31/2021 03:10:54 - INFO - __main__ - Step 76887: {'lr': 0.0002452985016786248, 'samples': 14762304, 'steps': 76886, 'loss/train': 0.033757533878088} 08/31/2021 03:10:54 - INFO - __main__ - Step 76888: {'lr': 0.000245293195873826, 'samples': 14762496, 'steps': 76887, 'loss/train': 1.4945927858352661} 08/31/2021 03:10:55 - INFO - __main__ - Step 76889: {'lr': 0.000245287890071148, 'samples': 14762688, 'steps': 76888, 'loss/train': 1.6253852844238281} 08/31/2021 03:10:56 - INFO - __main__ - Step 76890: {'lr': 0.0002452825842705932, 'samples': 14762880, 'steps': 76889, 'loss/train': 1.6185234785079956} 08/31/2021 03:10:57 - INFO - __main__ - Step 76891: {'lr': 0.000245277278472164, 'samples': 14763072, 'steps': 76890, 'loss/train': 1.1856902837753296} 08/31/2021 03:10:57 - INFO - __main__ - Step 76892: {'lr': 0.0002452719726758628, 'samples': 14763264, 'steps': 76891, 'loss/train': 1.5300376415252686} 08/31/2021 03:10:58 - INFO - __main__ - Step 76893: {'lr': 0.00024526666688169196, 'samples': 14763456, 'steps': 76892, 'loss/train': 1.6208484172821045} 08/31/2021 03:10:58 - INFO - __main__ - Step 76894: {'lr': 0.00024526136108965393, 'samples': 14763648, 'steps': 76893, 'loss/train': 1.4366892576217651} 08/31/2021 03:10:58 - INFO - __main__ - Step 76895: {'lr': 0.00024525605529975096, 'samples': 14763840, 'steps': 76894, 'loss/train': 0.9302564263343811} 08/31/2021 03:11:00 - INFO - __main__ - Step 76896: {'lr': 0.0002452507495119857, 'samples': 14764032, 'steps': 76895, 'loss/train': 0.8685102462768555} 08/31/2021 03:11:00 - INFO - __main__ - Step 76897: {'lr': 0.00024524544372636034, 'samples': 14764224, 'steps': 76896, 'loss/train': 2.3939337730407715} 08/31/2021 03:11:00 - INFO - __main__ - Step 76898: {'lr': 0.0002452401379428772, 'samples': 14764416, 'steps': 76897, 'loss/train': 1.0072218179702759} 08/31/2021 03:11:01 - INFO - __main__ - Step 76899: {'lr': 0.00024523483216153883, 'samples': 14764608, 'steps': 76898, 'loss/train': 0.9239288568496704} 08/31/2021 03:11:01 - INFO - __main__ - Step 76900: {'lr': 0.0002452295263823476, 'samples': 14764800, 'steps': 76899, 'loss/train': 0.30224451422691345} 08/31/2021 03:11:03 - INFO - __main__ - Step 76901: {'lr': 0.00024522422060530583, 'samples': 14764992, 'steps': 76900, 'loss/train': 1.3251959085464478} 08/31/2021 03:11:04 - INFO - __main__ - Step 76902: {'lr': 0.00024521891483041597, 'samples': 14765184, 'steps': 76901, 'loss/train': 1.443184733390808} 08/31/2021 03:11:04 - INFO - __main__ - Step 76903: {'lr': 0.0002452136090576804, 'samples': 14765376, 'steps': 76902, 'loss/train': 1.9796918630599976} 08/31/2021 03:11:04 - INFO - __main__ - Step 76904: {'lr': 0.0002452083032871015, 'samples': 14765568, 'steps': 76903, 'loss/train': 1.4853463172912598} 08/31/2021 03:11:05 - INFO - __main__ - Step 76905: {'lr': 0.0002452029975186816, 'samples': 14765760, 'steps': 76904, 'loss/train': 0.06751459836959839} 08/31/2021 03:11:06 - INFO - __main__ - Step 76906: {'lr': 0.00024519769175242325, 'samples': 14765952, 'steps': 76905, 'loss/train': 1.8441451787948608} 08/31/2021 03:11:07 - INFO - __main__ - Step 76907: {'lr': 0.00024519238598832874, 'samples': 14766144, 'steps': 76906, 'loss/train': 1.7057538032531738} 08/31/2021 03:11:07 - INFO - __main__ - Step 76908: {'lr': 0.0002451870802264004, 'samples': 14766336, 'steps': 76907, 'loss/train': 1.7480192184448242} 08/31/2021 03:11:08 - INFO - __main__ - Step 76909: {'lr': 0.00024518177446664085, 'samples': 14766528, 'steps': 76908, 'loss/train': 1.1213874816894531} 08/31/2021 03:11:08 - INFO - __main__ - Step 76910: {'lr': 0.00024517646870905215, 'samples': 14766720, 'steps': 76909, 'loss/train': 1.436898112297058} 08/31/2021 03:11:10 - INFO - __main__ - Step 76911: {'lr': 0.00024517116295363694, 'samples': 14766912, 'steps': 76910, 'loss/train': 1.2818529605865479} 08/31/2021 03:11:10 - INFO - __main__ - Step 76912: {'lr': 0.00024516585720039746, 'samples': 14767104, 'steps': 76911, 'loss/train': 1.384817361831665} 08/31/2021 03:11:10 - INFO - __main__ - Step 76913: {'lr': 0.0002451605514493362, 'samples': 14767296, 'steps': 76912, 'loss/train': 0.7647010087966919} 08/31/2021 03:11:11 - INFO - __main__ - Step 76914: {'lr': 0.0002451552457004555, 'samples': 14767488, 'steps': 76913, 'loss/train': 0.9524046778678894} 08/31/2021 03:11:11 - INFO - __main__ - Step 76915: {'lr': 0.0002451499399537578, 'samples': 14767680, 'steps': 76914, 'loss/train': 0.36449408531188965} 08/31/2021 03:11:13 - INFO - __main__ - Step 76916: {'lr': 0.00024514463420924543, 'samples': 14767872, 'steps': 76915, 'loss/train': 1.5591094493865967} 08/31/2021 03:11:13 - INFO - __main__ - Step 76917: {'lr': 0.0002451393284669209, 'samples': 14768064, 'steps': 76916, 'loss/train': 1.0950452089309692} 08/31/2021 03:11:14 - INFO - __main__ - Step 76918: {'lr': 0.0002451340227267864, 'samples': 14768256, 'steps': 76917, 'loss/train': 0.6048716902732849} 08/31/2021 03:11:14 - INFO - __main__ - Step 76919: {'lr': 0.0002451287169888445, 'samples': 14768448, 'steps': 76918, 'loss/train': 1.6759635210037231} 08/31/2021 03:11:14 - INFO - __main__ - Step 76920: {'lr': 0.0002451234112530975, 'samples': 14768640, 'steps': 76919, 'loss/train': 1.212672472000122} 08/31/2021 03:11:15 - INFO - __main__ - Step 76921: {'lr': 0.0002451181055195478, 'samples': 14768832, 'steps': 76920, 'loss/train': 0.0233592726290226} 08/31/2021 03:11:15 - INFO - __main__ - Step 76922: {'lr': 0.000245112799788198, 'samples': 14769024, 'steps': 76921, 'loss/train': 1.6444389820098877} 08/31/2021 03:11:17 - INFO - __main__ - Step 76923: {'lr': 0.0002451074940590501, 'samples': 14769216, 'steps': 76922, 'loss/train': 1.9547252655029297} 08/31/2021 03:11:17 - INFO - __main__ - Step 76924: {'lr': 0.0002451021883321067, 'samples': 14769408, 'steps': 76923, 'loss/train': 1.6014066934585571} 08/31/2021 03:11:17 - INFO - __main__ - Step 76925: {'lr': 0.0002450968826073702, 'samples': 14769600, 'steps': 76924, 'loss/train': 1.2958728075027466} 08/31/2021 03:11:18 - INFO - __main__ - Step 76926: {'lr': 0.00024509157688484297, 'samples': 14769792, 'steps': 76925, 'loss/train': 1.8014440536499023} 08/31/2021 03:11:18 - INFO - __main__ - Step 76927: {'lr': 0.0002450862711645274, 'samples': 14769984, 'steps': 76926, 'loss/train': 1.064582347869873} 08/31/2021 03:11:19 - INFO - __main__ - Step 76928: {'lr': 0.0002450809654464259, 'samples': 14770176, 'steps': 76927, 'loss/train': 1.1852089166641235} 08/31/2021 03:11:20 - INFO - __main__ - Step 76929: {'lr': 0.0002450756597305408, 'samples': 14770368, 'steps': 76928, 'loss/train': 1.4586243629455566} 08/31/2021 03:11:20 - INFO - __main__ - Step 76930: {'lr': 0.00024507035401687453, 'samples': 14770560, 'steps': 76929, 'loss/train': 1.1648991107940674} 08/31/2021 03:11:21 - INFO - __main__ - Step 76931: {'lr': 0.0002450650483054295, 'samples': 14770752, 'steps': 76930, 'loss/train': 1.720155954360962} 08/31/2021 03:11:21 - INFO - __main__ - Step 76932: {'lr': 0.0002450597425962081, 'samples': 14770944, 'steps': 76931, 'loss/train': 1.0710413455963135} 08/31/2021 03:11:23 - INFO - __main__ - Step 76933: {'lr': 0.00024505443688921266, 'samples': 14771136, 'steps': 76932, 'loss/train': 1.0564937591552734} 08/31/2021 03:11:23 - INFO - __main__ - Step 76934: {'lr': 0.00024504913118444564, 'samples': 14771328, 'steps': 76933, 'loss/train': 0.7555227279663086} 08/31/2021 03:11:24 - INFO - __main__ - Step 76935: {'lr': 0.0002450438254819094, 'samples': 14771520, 'steps': 76934, 'loss/train': 1.2038518190383911} 08/31/2021 03:11:24 - INFO - __main__ - Step 76936: {'lr': 0.0002450385197816065, 'samples': 14771712, 'steps': 76935, 'loss/train': 1.9927507638931274} 08/31/2021 03:11:24 - INFO - __main__ - Step 76937: {'lr': 0.00024503321408353895, 'samples': 14771904, 'steps': 76936, 'loss/train': 1.1899809837341309} 08/31/2021 03:11:25 - INFO - __main__ - Step 76938: {'lr': 0.00024502790838770944, 'samples': 14772096, 'steps': 76937, 'loss/train': 1.811884880065918} 08/31/2021 03:11:26 - INFO - __main__ - Step 76939: {'lr': 0.0002450226026941202, 'samples': 14772288, 'steps': 76938, 'loss/train': 1.1465731859207153} 08/31/2021 03:11:27 - INFO - __main__ - Step 76940: {'lr': 0.00024501729700277376, 'samples': 14772480, 'steps': 76939, 'loss/train': 1.4878005981445312} 08/31/2021 03:11:27 - INFO - __main__ - Step 76941: {'lr': 0.0002450119913136725, 'samples': 14772672, 'steps': 76940, 'loss/train': 1.0730775594711304} 08/31/2021 03:11:27 - INFO - __main__ - Step 76942: {'lr': 0.00024500668562681864, 'samples': 14772864, 'steps': 76941, 'loss/train': 0.7644315958023071} 08/31/2021 03:11:28 - INFO - __main__ - Step 76943: {'lr': 0.0002450013799422148, 'samples': 14773056, 'steps': 76942, 'loss/train': 1.367863655090332} 08/31/2021 03:11:29 - INFO - __main__ - Step 76944: {'lr': 0.00024499607425986316, 'samples': 14773248, 'steps': 76943, 'loss/train': 1.2613247632980347} 08/31/2021 03:11:30 - INFO - __main__ - Step 76945: {'lr': 0.0002449907685797663, 'samples': 14773440, 'steps': 76944, 'loss/train': 1.2802307605743408} 08/31/2021 03:11:30 - INFO - __main__ - Step 76946: {'lr': 0.00024498546290192645, 'samples': 14773632, 'steps': 76945, 'loss/train': 1.5555561780929565} 08/31/2021 03:11:30 - INFO - __main__ - Step 76947: {'lr': 0.0002449801572263461, 'samples': 14773824, 'steps': 76946, 'loss/train': 1.1123913526535034} 08/31/2021 03:11:31 - INFO - __main__ - Step 76948: {'lr': 0.0002449748515530276, 'samples': 14774016, 'steps': 76947, 'loss/train': 1.3686025142669678} 08/31/2021 03:11:33 - INFO - __main__ - Step 76949: {'lr': 0.0002449695458819735, 'samples': 14774208, 'steps': 76948, 'loss/train': 0.6868263483047485} 08/31/2021 03:11:34 - INFO - __main__ - Step 76950: {'lr': 0.00024496424021318595, 'samples': 14774400, 'steps': 76949, 'loss/train': 1.1503674983978271} 08/31/2021 03:11:34 - INFO - __main__ - Step 76951: {'lr': 0.0002449589345466674, 'samples': 14774592, 'steps': 76950, 'loss/train': 1.0115209817886353} 08/31/2021 03:11:34 - INFO - __main__ - Step 76952: {'lr': 0.00024495362888242027, 'samples': 14774784, 'steps': 76951, 'loss/train': 1.1788924932479858} 08/31/2021 03:11:35 - INFO - __main__ - Step 76953: {'lr': 0.000244948323220447, 'samples': 14774976, 'steps': 76952, 'loss/train': 1.7244277000427246} 08/31/2021 03:11:35 - INFO - __main__ - Step 76954: {'lr': 0.0002449430175607499, 'samples': 14775168, 'steps': 76953, 'loss/train': 1.784252405166626} 08/31/2021 03:11:35 - INFO - __main__ - Step 76955: {'lr': 0.0002449377119033314, 'samples': 14775360, 'steps': 76954, 'loss/train': 1.415224313735962} 08/31/2021 03:11:37 - INFO - __main__ - Step 76956: {'lr': 0.0002449324062481939, 'samples': 14775552, 'steps': 76955, 'loss/train': 1.4616464376449585} 08/31/2021 03:11:38 - INFO - __main__ - Step 76957: {'lr': 0.00024492710059533976, 'samples': 14775744, 'steps': 76956, 'loss/train': 0.7264333963394165} 08/31/2021 03:11:38 - INFO - __main__ - Step 76958: {'lr': 0.0002449217949447714, 'samples': 14775936, 'steps': 76957, 'loss/train': 1.6160783767700195} 08/31/2021 03:11:39 - INFO - __main__ - Step 76959: {'lr': 0.0002449164892964912, 'samples': 14776128, 'steps': 76958, 'loss/train': 1.5920517444610596} 08/31/2021 03:11:39 - INFO - __main__ - Step 76960: {'lr': 0.00024491118365050154, 'samples': 14776320, 'steps': 76959, 'loss/train': 2.5434458255767822} 08/31/2021 03:11:40 - INFO - __main__ - Step 76961: {'lr': 0.00024490587800680486, 'samples': 14776512, 'steps': 76960, 'loss/train': 1.753704309463501} 08/31/2021 03:11:41 - INFO - __main__ - Step 76962: {'lr': 0.0002449005723654035, 'samples': 14776704, 'steps': 76961, 'loss/train': 1.1369370222091675} 08/31/2021 03:11:41 - INFO - __main__ - Step 76963: {'lr': 0.0002448952667262999, 'samples': 14776896, 'steps': 76962, 'loss/train': 1.0360782146453857} 08/31/2021 03:11:42 - INFO - __main__ - Step 76964: {'lr': 0.0002448899610894964, 'samples': 14777088, 'steps': 76963, 'loss/train': 1.037610411643982} 08/31/2021 03:11:42 - INFO - __main__ - Step 76965: {'lr': 0.0002448846554549954, 'samples': 14777280, 'steps': 76964, 'loss/train': 1.4329400062561035} 08/31/2021 03:11:43 - INFO - __main__ - Step 76966: {'lr': 0.00024487934982279924, 'samples': 14777472, 'steps': 76965, 'loss/train': 1.4198534488677979} 08/31/2021 03:11:44 - INFO - __main__ - Step 76967: {'lr': 0.0002448740441929104, 'samples': 14777664, 'steps': 76966, 'loss/train': 1.2722407579421997} 08/31/2021 03:11:44 - INFO - __main__ - Step 76968: {'lr': 0.0002448687385653312, 'samples': 14777856, 'steps': 76967, 'loss/train': 1.1931524276733398} 08/31/2021 03:11:45 - INFO - __main__ - Step 76969: {'lr': 0.0002448634329400641, 'samples': 14778048, 'steps': 76968, 'loss/train': 1.0858888626098633} 08/31/2021 03:11:45 - INFO - __main__ - Step 76970: {'lr': 0.0002448581273171115, 'samples': 14778240, 'steps': 76969, 'loss/train': 2.5147039890289307} 08/31/2021 03:11:47 - INFO - __main__ - Step 76971: {'lr': 0.00024485282169647567, 'samples': 14778432, 'steps': 76970, 'loss/train': 1.6677273511886597} 08/31/2021 03:11:47 - INFO - __main__ - Step 76972: {'lr': 0.0002448475160781591, 'samples': 14778624, 'steps': 76971, 'loss/train': 1.0694917440414429} 08/31/2021 03:11:48 - INFO - __main__ - Step 76973: {'lr': 0.0002448422104621642, 'samples': 14778816, 'steps': 76972, 'loss/train': 0.05667559802532196} 08/31/2021 03:11:48 - INFO - __main__ - Step 76974: {'lr': 0.0002448369048484933, 'samples': 14779008, 'steps': 76973, 'loss/train': 1.1313443183898926} 08/31/2021 03:11:48 - INFO - __main__ - Step 76975: {'lr': 0.0002448315992371488, 'samples': 14779200, 'steps': 76974, 'loss/train': 0.9805823564529419} 08/31/2021 03:11:49 - INFO - __main__ - Step 76976: {'lr': 0.0002448262936281332, 'samples': 14779392, 'steps': 76975, 'loss/train': 1.5088145732879639} 08/31/2021 03:11:50 - INFO - __main__ - Step 76977: {'lr': 0.0002448209880214487, 'samples': 14779584, 'steps': 76976, 'loss/train': 1.2732422351837158} 08/31/2021 03:11:51 - INFO - __main__ - Step 76978: {'lr': 0.0002448156824170978, 'samples': 14779776, 'steps': 76977, 'loss/train': 0.9674056768417358} 08/31/2021 03:11:51 - INFO - __main__ - Step 76979: {'lr': 0.00024481037681508286, 'samples': 14779968, 'steps': 76978, 'loss/train': 1.499874472618103} 08/31/2021 03:11:51 - INFO - __main__ - Step 76980: {'lr': 0.00024480507121540625, 'samples': 14780160, 'steps': 76979, 'loss/train': 1.3415254354476929} 08/31/2021 03:11:52 - INFO - __main__ - Step 76981: {'lr': 0.00024479976561807043, 'samples': 14780352, 'steps': 76980, 'loss/train': 1.011148452758789} 08/31/2021 03:11:53 - INFO - __main__ - Step 76982: {'lr': 0.00024479446002307774, 'samples': 14780544, 'steps': 76981, 'loss/train': 0.8763231635093689} 08/31/2021 03:11:54 - INFO - __main__ - Step 76983: {'lr': 0.0002447891544304306, 'samples': 14780736, 'steps': 76982, 'loss/train': 1.4974902868270874} 08/31/2021 03:11:54 - INFO - __main__ - Step 76984: {'lr': 0.0002447838488401314, 'samples': 14780928, 'steps': 76983, 'loss/train': 0.7577086091041565} 08/31/2021 03:11:54 - INFO - __main__ - Step 76985: {'lr': 0.00024477854325218246, 'samples': 14781120, 'steps': 76984, 'loss/train': 2.1218276023864746} 08/31/2021 03:11:55 - INFO - __main__ - Step 76986: {'lr': 0.0002447732376665863, 'samples': 14781312, 'steps': 76985, 'loss/train': 1.1590830087661743} 08/31/2021 03:11:55 - INFO - __main__ - Step 76987: {'lr': 0.0002447679320833452, 'samples': 14781504, 'steps': 76986, 'loss/train': 1.3452695608139038} 08/31/2021 03:11:57 - INFO - __main__ - Step 76988: {'lr': 0.00024476262650246166, 'samples': 14781696, 'steps': 76987, 'loss/train': 1.8778454065322876} 08/31/2021 03:11:57 - INFO - __main__ - Step 76989: {'lr': 0.00024475732092393794, 'samples': 14781888, 'steps': 76988, 'loss/train': 1.0769844055175781} 08/31/2021 03:11:57 - INFO - __main__ - Step 76990: {'lr': 0.00024475201534777653, 'samples': 14782080, 'steps': 76989, 'loss/train': 1.717460036277771} 08/31/2021 03:11:58 - INFO - __main__ - Step 76991: {'lr': 0.0002447467097739797, 'samples': 14782272, 'steps': 76990, 'loss/train': 1.0969607830047607} 08/31/2021 03:11:58 - INFO - __main__ - Step 76992: {'lr': 0.00024474140420255, 'samples': 14782464, 'steps': 76991, 'loss/train': 1.2402749061584473} 08/31/2021 03:12:00 - INFO - __main__ - Step 76993: {'lr': 0.0002447360986334897, 'samples': 14782656, 'steps': 76992, 'loss/train': 1.6066532135009766} 08/31/2021 03:12:00 - INFO - __main__ - Step 76994: {'lr': 0.0002447307930668012, 'samples': 14782848, 'steps': 76993, 'loss/train': 1.110012412071228} 08/31/2021 03:12:00 - INFO - __main__ - Step 76995: {'lr': 0.00024472548750248695, 'samples': 14783040, 'steps': 76994, 'loss/train': 1.4370797872543335} 08/31/2021 03:12:01 - INFO - __main__ - Step 76996: {'lr': 0.00024472018194054935, 'samples': 14783232, 'steps': 76995, 'loss/train': 1.73973548412323} 08/31/2021 03:12:01 - INFO - __main__ - Step 76997: {'lr': 0.0002447148763809907, 'samples': 14783424, 'steps': 76996, 'loss/train': 1.6638859510421753} 08/31/2021 03:12:03 - INFO - __main__ - Step 76998: {'lr': 0.00024470957082381353, 'samples': 14783616, 'steps': 76997, 'loss/train': 0.27491408586502075} 08/31/2021 03:12:03 - INFO - __main__ - Step 76999: {'lr': 0.00024470426526902007, 'samples': 14783808, 'steps': 76998, 'loss/train': 1.3123329877853394} 08/31/2021 03:12:03 - INFO - __main__ - Step 77000: {'lr': 0.00024469895971661283, 'samples': 14784000, 'steps': 76999, 'loss/train': 1.9624079465866089} 08/31/2021 03:12:04 - INFO - __main__ - Step 77001: {'lr': 0.00024469365416659414, 'samples': 14784192, 'steps': 77000, 'loss/train': 0.03860728070139885} 08/31/2021 03:12:04 - INFO - __main__ - Step 77002: {'lr': 0.0002446883486189664, 'samples': 14784384, 'steps': 77001, 'loss/train': 1.3297358751296997} 08/31/2021 03:12:06 - INFO - __main__ - Step 77003: {'lr': 0.00024468304307373207, 'samples': 14784576, 'steps': 77002, 'loss/train': 0.04357365891337395} 08/31/2021 03:12:06 - INFO - __main__ - Step 77004: {'lr': 0.00024467773753089335, 'samples': 14784768, 'steps': 77003, 'loss/train': 1.233566403388977} 08/31/2021 03:12:06 - INFO - __main__ - Step 77005: {'lr': 0.0002446724319904529, 'samples': 14784960, 'steps': 77004, 'loss/train': 1.2065540552139282} 08/31/2021 03:12:07 - INFO - __main__ - Step 77006: {'lr': 0.00024466712645241284, 'samples': 14785152, 'steps': 77005, 'loss/train': 2.840714454650879} 08/31/2021 03:12:07 - INFO - __main__ - Step 77007: {'lr': 0.00024466182091677577, 'samples': 14785344, 'steps': 77006, 'loss/train': 0.7287720441818237} 08/31/2021 03:12:09 - INFO - __main__ - Step 77008: {'lr': 0.00024465651538354394, 'samples': 14785536, 'steps': 77007, 'loss/train': 1.2173199653625488} 08/31/2021 03:12:10 - INFO - __main__ - Step 77009: {'lr': 0.00024465120985271986, 'samples': 14785728, 'steps': 77008, 'loss/train': 1.1931581497192383} 08/31/2021 03:12:10 - INFO - __main__ - Step 77010: {'lr': 0.00024464590432430586, 'samples': 14785920, 'steps': 77009, 'loss/train': 1.3772284984588623} 08/31/2021 03:12:10 - INFO - __main__ - Step 77011: {'lr': 0.0002446405987983043, 'samples': 14786112, 'steps': 77010, 'loss/train': 0.34733185172080994} 08/31/2021 03:12:11 - INFO - __main__ - Step 77012: {'lr': 0.0002446352932747176, 'samples': 14786304, 'steps': 77011, 'loss/train': 2.138315200805664} 08/31/2021 03:12:11 - INFO - __main__ - Step 77013: {'lr': 0.0002446299877535482, 'samples': 14786496, 'steps': 77012, 'loss/train': 1.9205434322357178} 08/31/2021 03:12:11 - INFO - __main__ - Step 77014: {'lr': 0.0002446246822347984, 'samples': 14786688, 'steps': 77013, 'loss/train': 0.9589449167251587} 08/31/2021 03:12:13 - INFO - __main__ - Step 77015: {'lr': 0.00024461937671847066, 'samples': 14786880, 'steps': 77014, 'loss/train': 1.3389028310775757} 08/31/2021 03:12:14 - INFO - __main__ - Step 77016: {'lr': 0.00024461407120456735, 'samples': 14787072, 'steps': 77015, 'loss/train': 1.1556708812713623} 08/31/2021 03:12:14 - INFO - __main__ - Step 77017: {'lr': 0.00024460876569309085, 'samples': 14787264, 'steps': 77016, 'loss/train': 0.2979830503463745} 08/31/2021 03:12:15 - INFO - __main__ - Step 77018: {'lr': 0.00024460346018404357, 'samples': 14787456, 'steps': 77017, 'loss/train': 1.3466097116470337} 08/31/2021 03:12:15 - INFO - __main__ - Step 77019: {'lr': 0.0002445981546774278, 'samples': 14787648, 'steps': 77018, 'loss/train': 1.8049713373184204} 08/31/2021 03:12:17 - INFO - __main__ - Step 77020: {'lr': 0.0002445928491732462, 'samples': 14787840, 'steps': 77019, 'loss/train': 1.1992976665496826} 08/31/2021 03:12:17 - INFO - __main__ - Step 77021: {'lr': 0.0002445875436715008, 'samples': 14788032, 'steps': 77020, 'loss/train': 1.1853030920028687} 08/31/2021 03:12:17 - INFO - __main__ - Step 77022: {'lr': 0.0002445822381721943, 'samples': 14788224, 'steps': 77021, 'loss/train': 0.03502202779054642} 08/31/2021 03:12:18 - INFO - __main__ - Step 77023: {'lr': 0.0002445769326753289, 'samples': 14788416, 'steps': 77022, 'loss/train': 1.0522856712341309} 08/31/2021 03:12:18 - INFO - __main__ - Step 77024: {'lr': 0.00024457162718090705, 'samples': 14788608, 'steps': 77023, 'loss/train': 1.4635529518127441} 08/31/2021 03:12:20 - INFO - __main__ - Step 77025: {'lr': 0.0002445663216889311, 'samples': 14788800, 'steps': 77024, 'loss/train': 0.8966521620750427} 08/31/2021 03:12:20 - INFO - __main__ - Step 77026: {'lr': 0.00024456101619940355, 'samples': 14788992, 'steps': 77025, 'loss/train': 1.2505196332931519} 08/31/2021 03:12:21 - INFO - __main__ - Step 77027: {'lr': 0.00024455571071232664, 'samples': 14789184, 'steps': 77026, 'loss/train': 1.5699584484100342} 08/31/2021 03:12:21 - INFO - __main__ - Step 77028: {'lr': 0.0002445504052277029, 'samples': 14789376, 'steps': 77027, 'loss/train': 1.1107299327850342} 08/31/2021 03:12:21 - INFO - __main__ - Step 77029: {'lr': 0.0002445450997455347, 'samples': 14789568, 'steps': 77028, 'loss/train': 0.8189150094985962} 08/31/2021 03:12:22 - INFO - __main__ - Step 77030: {'lr': 0.00024453979426582433, 'samples': 14789760, 'steps': 77029, 'loss/train': 1.0297716856002808} 08/31/2021 03:12:24 - INFO - __main__ - Step 77031: {'lr': 0.00024453448878857437, 'samples': 14789952, 'steps': 77030, 'loss/train': 0.025347406044602394} 08/31/2021 03:12:24 - INFO - __main__ - Step 77032: {'lr': 0.00024452918331378695, 'samples': 14790144, 'steps': 77031, 'loss/train': 1.4118247032165527} 08/31/2021 03:12:25 - INFO - __main__ - Step 77033: {'lr': 0.0002445238778414646, 'samples': 14790336, 'steps': 77032, 'loss/train': 1.4125645160675049} 08/31/2021 03:12:25 - INFO - __main__ - Step 77034: {'lr': 0.00024451857237160974, 'samples': 14790528, 'steps': 77033, 'loss/train': 0.7781972289085388} 08/31/2021 03:12:25 - INFO - __main__ - Step 77035: {'lr': 0.0002445132669042247, 'samples': 14790720, 'steps': 77034, 'loss/train': 0.7542278170585632} 08/31/2021 03:12:26 - INFO - __main__ - Step 77036: {'lr': 0.00024450796143931193, 'samples': 14790912, 'steps': 77035, 'loss/train': 1.0470396280288696} 08/31/2021 03:12:27 - INFO - __main__ - Step 77037: {'lr': 0.00024450265597687374, 'samples': 14791104, 'steps': 77036, 'loss/train': 1.315934658050537} 08/31/2021 03:12:27 - INFO - __main__ - Step 77038: {'lr': 0.00024449735051691263, 'samples': 14791296, 'steps': 77037, 'loss/train': 0.8342568278312683} 08/31/2021 03:12:28 - INFO - __main__ - Step 77039: {'lr': 0.00024449204505943087, 'samples': 14791488, 'steps': 77038, 'loss/train': 1.4011375904083252} 08/31/2021 03:12:28 - INFO - __main__ - Step 77040: {'lr': 0.00024448673960443095, 'samples': 14791680, 'steps': 77039, 'loss/train': 1.2058552503585815} 08/31/2021 03:12:28 - INFO - __main__ - Step 77041: {'lr': 0.0002444814341519152, 'samples': 14791872, 'steps': 77040, 'loss/train': 0.7979873418807983} 08/31/2021 03:12:30 - INFO - __main__ - Step 77042: {'lr': 0.000244476128701886, 'samples': 14792064, 'steps': 77041, 'loss/train': 1.1289105415344238} 08/31/2021 03:12:30 - INFO - __main__ - Step 77043: {'lr': 0.00024447082325434593, 'samples': 14792256, 'steps': 77042, 'loss/train': 0.8149069547653198} 08/31/2021 03:12:31 - INFO - __main__ - Step 77044: {'lr': 0.0002444655178092971, 'samples': 14792448, 'steps': 77043, 'loss/train': 1.3623689413070679} 08/31/2021 03:12:31 - INFO - __main__ - Step 77045: {'lr': 0.00024446021236674203, 'samples': 14792640, 'steps': 77044, 'loss/train': 0.8219023942947388} 08/31/2021 03:12:31 - INFO - __main__ - Step 77046: {'lr': 0.0002444549069266831, 'samples': 14792832, 'steps': 77045, 'loss/train': 0.7266661524772644} 08/31/2021 03:12:33 - INFO - __main__ - Step 77047: {'lr': 0.00024444960148912266, 'samples': 14793024, 'steps': 77046, 'loss/train': 1.1259249448776245} 08/31/2021 03:12:34 - INFO - __main__ - Step 77048: {'lr': 0.00024444429605406323, 'samples': 14793216, 'steps': 77047, 'loss/train': 0.9546825289726257} 08/31/2021 03:12:34 - INFO - __main__ - Step 77049: {'lr': 0.00024443899062150706, 'samples': 14793408, 'steps': 77048, 'loss/train': 0.7428441047668457} 08/31/2021 03:12:34 - INFO - __main__ - Step 77050: {'lr': 0.0002444336851914566, 'samples': 14793600, 'steps': 77049, 'loss/train': 0.08034386485815048} 08/31/2021 03:12:35 - INFO - __main__ - Step 77051: {'lr': 0.0002444283797639142, 'samples': 14793792, 'steps': 77050, 'loss/train': 0.04886656254529953} 08/31/2021 03:12:35 - INFO - __main__ - Step 77052: {'lr': 0.00024442307433888234, 'samples': 14793984, 'steps': 77051, 'loss/train': 0.025113128125667572} 08/31/2021 03:12:37 - INFO - __main__ - Step 77053: {'lr': 0.00024441776891636333, 'samples': 14794176, 'steps': 77052, 'loss/train': 1.0719817876815796} 08/31/2021 03:12:37 - INFO - __main__ - Step 77054: {'lr': 0.0002444124634963596, 'samples': 14794368, 'steps': 77053, 'loss/train': 1.4907634258270264} 08/31/2021 03:12:37 - INFO - __main__ - Step 77055: {'lr': 0.00024440715807887354, 'samples': 14794560, 'steps': 77054, 'loss/train': 1.4288716316223145} 08/31/2021 03:12:38 - INFO - __main__ - Step 77056: {'lr': 0.0002444018526639075, 'samples': 14794752, 'steps': 77055, 'loss/train': 0.583325982093811} 08/31/2021 03:12:38 - INFO - __main__ - Step 77057: {'lr': 0.000244396547251464, 'samples': 14794944, 'steps': 77056, 'loss/train': 1.4546746015548706} 08/31/2021 03:12:40 - INFO - __main__ - Step 77058: {'lr': 0.00024439124184154527, 'samples': 14795136, 'steps': 77057, 'loss/train': 1.5852370262145996} 08/31/2021 03:12:40 - INFO - __main__ - Step 77059: {'lr': 0.0002443859364341537, 'samples': 14795328, 'steps': 77058, 'loss/train': 1.6780301332473755} 08/31/2021 03:12:41 - INFO - __main__ - Step 77060: {'lr': 0.0002443806310292918, 'samples': 14795520, 'steps': 77059, 'loss/train': 0.874431312084198} 08/31/2021 03:12:41 - INFO - __main__ - Step 77061: {'lr': 0.0002443753256269618, 'samples': 14795712, 'steps': 77060, 'loss/train': 1.6500025987625122} 08/31/2021 03:12:41 - INFO - __main__ - Step 77062: {'lr': 0.00024437002022716634, 'samples': 14795904, 'steps': 77061, 'loss/train': 1.0051919221878052} 08/31/2021 03:12:44 - INFO - __main__ - Step 77063: {'lr': 0.00024436471482990757, 'samples': 14796096, 'steps': 77062, 'loss/train': 1.0989048480987549} 08/31/2021 03:12:44 - INFO - __main__ - Step 77064: {'lr': 0.000244359409435188, 'samples': 14796288, 'steps': 77063, 'loss/train': 1.4808580875396729} 08/31/2021 03:12:45 - INFO - __main__ - Step 77065: {'lr': 0.00024435410404301, 'samples': 14796480, 'steps': 77064, 'loss/train': 2.0709645748138428} 08/31/2021 03:12:45 - INFO - __main__ - Step 77066: {'lr': 0.0002443487986533759, 'samples': 14796672, 'steps': 77065, 'loss/train': 1.9172074794769287} 08/31/2021 03:12:45 - INFO - __main__ - Step 77067: {'lr': 0.00024434349326628817, 'samples': 14796864, 'steps': 77066, 'loss/train': 0.8695784211158752} 08/31/2021 03:12:46 - INFO - __main__ - Step 77068: {'lr': 0.0002443381878817492, 'samples': 14797056, 'steps': 77067, 'loss/train': 2.006465435028076} 08/31/2021 03:12:46 - INFO - __main__ - Step 77069: {'lr': 0.0002443328824997613, 'samples': 14797248, 'steps': 77068, 'loss/train': 0.8156983256340027} 08/31/2021 03:12:46 - INFO - __main__ - Step 77070: {'lr': 0.0002443275771203271, 'samples': 14797440, 'steps': 77069, 'loss/train': 1.1860514879226685} 08/31/2021 03:12:48 - INFO - __main__ - Step 77071: {'lr': 0.00024432227174344865, 'samples': 14797632, 'steps': 77070, 'loss/train': 1.6889252662658691} 08/31/2021 03:12:49 - INFO - __main__ - Step 77072: {'lr': 0.0002443169663691285, 'samples': 14797824, 'steps': 77071, 'loss/train': 1.7044637203216553} 08/31/2021 03:12:49 - INFO - __main__ - Step 77073: {'lr': 0.0002443116609973691, 'samples': 14798016, 'steps': 77072, 'loss/train': 1.4007295370101929} 08/31/2021 03:12:49 - INFO - __main__ - Step 77074: {'lr': 0.0002443063556281727, 'samples': 14798208, 'steps': 77073, 'loss/train': 1.416623830795288} 08/31/2021 03:12:50 - INFO - __main__ - Step 77075: {'lr': 0.00024430105026154177, 'samples': 14798400, 'steps': 77074, 'loss/train': 1.3074150085449219} 08/31/2021 03:12:52 - INFO - __main__ - Step 77076: {'lr': 0.0002442957448974787, 'samples': 14798592, 'steps': 77075, 'loss/train': 1.4170011281967163} 08/31/2021 03:12:52 - INFO - __main__ - Step 77077: {'lr': 0.0002442904395359859, 'samples': 14798784, 'steps': 77076, 'loss/train': 0.9154795408248901} 08/31/2021 03:12:52 - INFO - __main__ - Step 77078: {'lr': 0.00024428513417706574, 'samples': 14798976, 'steps': 77077, 'loss/train': 2.061785936355591} 08/31/2021 03:12:53 - INFO - __main__ - Step 77079: {'lr': 0.00024427982882072063, 'samples': 14799168, 'steps': 77078, 'loss/train': 1.043663740158081} 08/31/2021 03:12:53 - INFO - __main__ - Step 77080: {'lr': 0.0002442745234669529, 'samples': 14799360, 'steps': 77079, 'loss/train': 1.1787428855895996} 08/31/2021 03:12:54 - INFO - __main__ - Step 77081: {'lr': 0.000244269218115765, 'samples': 14799552, 'steps': 77080, 'loss/train': 0.14380641281604767} 08/31/2021 03:12:55 - INFO - __main__ - Step 77082: {'lr': 0.0002442639127671593, 'samples': 14799744, 'steps': 77081, 'loss/train': 0.15039896965026855} 08/31/2021 03:12:56 - INFO - __main__ - Step 77083: {'lr': 0.0002442586074211382, 'samples': 14799936, 'steps': 77082, 'loss/train': 1.04977548122406} 08/31/2021 03:12:56 - INFO - __main__ - Step 77084: {'lr': 0.0002442533020777042, 'samples': 14800128, 'steps': 77083, 'loss/train': 0.9631929993629456} 08/31/2021 03:12:56 - INFO - __main__ - Step 77085: {'lr': 0.00024424799673685945, 'samples': 14800320, 'steps': 77084, 'loss/train': 1.0645488500595093} 08/31/2021 03:12:57 - INFO - __main__ - Step 77086: {'lr': 0.00024424269139860643, 'samples': 14800512, 'steps': 77085, 'loss/train': 1.5813673734664917} 08/31/2021 03:12:57 - INFO - __main__ - Step 77087: {'lr': 0.00024423738606294763, 'samples': 14800704, 'steps': 77086, 'loss/train': 1.3328723907470703} 08/31/2021 03:12:58 - INFO - __main__ - Step 77088: {'lr': 0.00024423208072988533, 'samples': 14800896, 'steps': 77087, 'loss/train': 1.3345531225204468} 08/31/2021 03:12:59 - INFO - __main__ - Step 77089: {'lr': 0.000244226775399422, 'samples': 14801088, 'steps': 77088, 'loss/train': 0.29235392808914185} 08/31/2021 03:12:59 - INFO - __main__ - Step 77090: {'lr': 0.00024422147007155994, 'samples': 14801280, 'steps': 77089, 'loss/train': 0.9409058690071106} 08/31/2021 03:12:59 - INFO - __main__ - Step 77091: {'lr': 0.0002442161647463016, 'samples': 14801472, 'steps': 77090, 'loss/train': 1.3993295431137085} 08/31/2021 03:13:00 - INFO - __main__ - Step 77092: {'lr': 0.00024421085942364946, 'samples': 14801664, 'steps': 77091, 'loss/train': 1.4007446765899658} 08/31/2021 03:13:01 - INFO - __main__ - Step 77093: {'lr': 0.00024420555410360577, 'samples': 14801856, 'steps': 77092, 'loss/train': 1.1019999980926514} 08/31/2021 03:13:02 - INFO - __main__ - Step 77094: {'lr': 0.00024420024878617295, 'samples': 14802048, 'steps': 77093, 'loss/train': 0.9684559106826782} 08/31/2021 03:13:02 - INFO - __main__ - Step 77095: {'lr': 0.0002441949434713534, 'samples': 14802240, 'steps': 77094, 'loss/train': 1.7488279342651367} 08/31/2021 03:13:03 - INFO - __main__ - Step 77096: {'lr': 0.0002441896381591495, 'samples': 14802432, 'steps': 77095, 'loss/train': 1.055733323097229} 08/31/2021 03:13:03 - INFO - __main__ - Step 77097: {'lr': 0.0002441843328495638, 'samples': 14802624, 'steps': 77096, 'loss/train': 1.4443118572235107} 08/31/2021 03:13:04 - INFO - __main__ - Step 77098: {'lr': 0.0002441790275425985, 'samples': 14802816, 'steps': 77097, 'loss/train': 2.1982016563415527} 08/31/2021 03:13:05 - INFO - __main__ - Step 77099: {'lr': 0.00024417372223825594, 'samples': 14803008, 'steps': 77098, 'loss/train': 1.2583189010620117} 08/31/2021 03:13:05 - INFO - __main__ - Step 77100: {'lr': 0.00024416841693653864, 'samples': 14803200, 'steps': 77099, 'loss/train': 0.9516972303390503} 08/31/2021 03:13:06 - INFO - __main__ - Step 77101: {'lr': 0.000244163111637449, 'samples': 14803392, 'steps': 77100, 'loss/train': 1.5511189699172974} 08/31/2021 03:13:06 - INFO - __main__ - Step 77102: {'lr': 0.0002441578063409893, 'samples': 14803584, 'steps': 77101, 'loss/train': 1.209271788597107} 08/31/2021 03:13:07 - INFO - __main__ - Step 77103: {'lr': 0.00024415250104716207, 'samples': 14803776, 'steps': 77102, 'loss/train': 0.4307345747947693} 08/31/2021 03:13:08 - INFO - __main__ - Step 77104: {'lr': 0.00024414719575596965, 'samples': 14803968, 'steps': 77103, 'loss/train': 0.2121889889240265} 08/31/2021 03:13:08 - INFO - __main__ - Step 77105: {'lr': 0.00024414189046741434, 'samples': 14804160, 'steps': 77104, 'loss/train': 1.1029309034347534} 08/31/2021 03:13:09 - INFO - __main__ - Step 77106: {'lr': 0.00024413658518149863, 'samples': 14804352, 'steps': 77105, 'loss/train': 0.5992100238800049} 08/31/2021 03:13:09 - INFO - __main__ - Step 77107: {'lr': 0.0002441312798982249, 'samples': 14804544, 'steps': 77106, 'loss/train': 1.2725753784179688} 08/31/2021 03:13:11 - INFO - __main__ - Step 77108: {'lr': 0.00024412597461759554, 'samples': 14804736, 'steps': 77107, 'loss/train': 1.3778878450393677} 08/31/2021 03:13:11 - INFO - __main__ - Step 77109: {'lr': 0.00024412066933961288, 'samples': 14804928, 'steps': 77108, 'loss/train': 1.5826606750488281} 08/31/2021 03:13:11 - INFO - __main__ - Step 77110: {'lr': 0.0002441153640642794, 'samples': 14805120, 'steps': 77109, 'loss/train': 1.5830767154693604} 08/31/2021 03:13:12 - INFO - __main__ - Step 77111: {'lr': 0.0002441100587915975, 'samples': 14805312, 'steps': 77110, 'loss/train': 0.6378541588783264} 08/31/2021 03:13:12 - INFO - __main__ - Step 77112: {'lr': 0.00024410475352156947, 'samples': 14805504, 'steps': 77111, 'loss/train': 0.0783778727054596} 08/31/2021 03:13:12 - INFO - __main__ - Step 77113: {'lr': 0.00024409944825419768, 'samples': 14805696, 'steps': 77112, 'loss/train': 1.088627576828003} 08/31/2021 03:13:14 - INFO - __main__ - Step 77114: {'lr': 0.00024409414298948466, 'samples': 14805888, 'steps': 77113, 'loss/train': 0.45090019702911377} 08/31/2021 03:13:15 - INFO - __main__ - Step 77115: {'lr': 0.00024408883772743267, 'samples': 14806080, 'steps': 77114, 'loss/train': 1.296048879623413} 08/31/2021 03:13:15 - INFO - __main__ - Step 77116: {'lr': 0.00024408353246804419, 'samples': 14806272, 'steps': 77115, 'loss/train': 1.1132357120513916} 08/31/2021 03:13:15 - INFO - __main__ - Step 77117: {'lr': 0.00024407822721132157, 'samples': 14806464, 'steps': 77116, 'loss/train': 0.7748557329177856} 08/31/2021 03:13:16 - INFO - __main__ - Step 77118: {'lr': 0.00024407292195726722, 'samples': 14806656, 'steps': 77117, 'loss/train': 1.4296029806137085} 08/31/2021 03:13:17 - INFO - __main__ - Step 77119: {'lr': 0.0002440676167058835, 'samples': 14806848, 'steps': 77118, 'loss/train': 1.1973440647125244} 08/31/2021 03:13:18 - INFO - __main__ - Step 77120: {'lr': 0.00024406231145717285, 'samples': 14807040, 'steps': 77119, 'loss/train': 1.2501392364501953} 08/31/2021 03:13:18 - INFO - __main__ - Step 77121: {'lr': 0.00024405700621113759, 'samples': 14807232, 'steps': 77120, 'loss/train': 0.653237521648407} 08/31/2021 03:13:18 - INFO - __main__ - Step 77122: {'lr': 0.00024405170096778022, 'samples': 14807424, 'steps': 77121, 'loss/train': 1.2834272384643555} 08/31/2021 03:13:19 - INFO - __main__ - Step 77123: {'lr': 0.000244046395727103, 'samples': 14807616, 'steps': 77122, 'loss/train': 0.5262563228607178} 08/31/2021 03:13:20 - INFO - __main__ - Step 77124: {'lr': 0.00024404109048910847, 'samples': 14807808, 'steps': 77123, 'loss/train': 1.1438859701156616} 08/31/2021 03:13:21 - INFO - __main__ - Step 77125: {'lr': 0.00024403578525379887, 'samples': 14808000, 'steps': 77124, 'loss/train': 1.4811785221099854} 08/31/2021 03:13:21 - INFO - __main__ - Step 77126: {'lr': 0.00024403048002117662, 'samples': 14808192, 'steps': 77125, 'loss/train': 1.4768540859222412} 08/31/2021 03:13:22 - INFO - __main__ - Step 77127: {'lr': 0.00024402517479124418, 'samples': 14808384, 'steps': 77126, 'loss/train': 0.0808432400226593} 08/31/2021 03:13:22 - INFO - __main__ - Step 77128: {'lr': 0.0002440198695640039, 'samples': 14808576, 'steps': 77127, 'loss/train': 1.4344713687896729} 08/31/2021 03:13:24 - INFO - __main__ - Step 77129: {'lr': 0.00024401456433945814, 'samples': 14808768, 'steps': 77128, 'loss/train': 1.1640385389328003} 08/31/2021 03:13:25 - INFO - __main__ - Step 77130: {'lr': 0.00024400925911760934, 'samples': 14808960, 'steps': 77129, 'loss/train': 1.0260215997695923} 08/31/2021 03:13:25 - INFO - __main__ - Step 77131: {'lr': 0.00024400395389845988, 'samples': 14809152, 'steps': 77130, 'loss/train': 1.0471113920211792} 08/31/2021 03:13:25 - INFO - __main__ - Step 77132: {'lr': 0.00024399864868201215, 'samples': 14809344, 'steps': 77131, 'loss/train': 1.2167350053787231} 08/31/2021 03:13:26 - INFO - __main__ - Step 77133: {'lr': 0.0002439933434682686, 'samples': 14809536, 'steps': 77132, 'loss/train': 1.3903489112854004} 08/31/2021 03:13:27 - INFO - __main__ - Step 77134: {'lr': 0.0002439880382572315, 'samples': 14809728, 'steps': 77133, 'loss/train': 1.4262261390686035} 08/31/2021 03:13:28 - INFO - __main__ - Step 77135: {'lr': 0.00024398273304890327, 'samples': 14809920, 'steps': 77134, 'loss/train': 0.9825167059898376} 08/31/2021 03:13:28 - INFO - __main__ - Step 77136: {'lr': 0.00024397742784328636, 'samples': 14810112, 'steps': 77135, 'loss/train': 1.9609674215316772} 08/31/2021 03:13:28 - INFO - __main__ - Step 77137: {'lr': 0.00024397212264038313, 'samples': 14810304, 'steps': 77136, 'loss/train': 1.887458086013794} 08/31/2021 03:13:29 - INFO - __main__ - Step 77138: {'lr': 0.000243966817440196, 'samples': 14810496, 'steps': 77137, 'loss/train': 0.8497362732887268} 08/31/2021 03:13:29 - INFO - __main__ - Step 77139: {'lr': 0.00024396151224272727, 'samples': 14810688, 'steps': 77138, 'loss/train': 1.4075326919555664} 08/31/2021 03:13:30 - INFO - __main__ - Step 77140: {'lr': 0.0002439562070479794, 'samples': 14810880, 'steps': 77139, 'loss/train': 1.2720528841018677} 08/31/2021 03:13:31 - INFO - __main__ - Step 77141: {'lr': 0.0002439509018559548, 'samples': 14811072, 'steps': 77140, 'loss/train': 1.4437477588653564} 08/31/2021 03:13:31 - INFO - __main__ - Step 77142: {'lr': 0.0002439455966666558, 'samples': 14811264, 'steps': 77141, 'loss/train': 0.553723931312561} 08/31/2021 03:13:32 - INFO - __main__ - Step 77143: {'lr': 0.0002439402914800848, 'samples': 14811456, 'steps': 77142, 'loss/train': 0.9151275157928467} 08/31/2021 03:13:32 - INFO - __main__ - Step 77144: {'lr': 0.00024393498629624431, 'samples': 14811648, 'steps': 77143, 'loss/train': 1.43328058719635} 08/31/2021 03:13:34 - INFO - __main__ - Step 77145: {'lr': 0.00024392968111513656, 'samples': 14811840, 'steps': 77144, 'loss/train': 1.2822582721710205} 08/31/2021 03:13:34 - INFO - __main__ - Step 77146: {'lr': 0.00024392437593676397, 'samples': 14812032, 'steps': 77145, 'loss/train': 0.021062396466732025} 08/31/2021 03:13:35 - INFO - __main__ - Step 77147: {'lr': 0.000243919070761129, 'samples': 14812224, 'steps': 77146, 'loss/train': 0.02370845340192318} 08/31/2021 03:13:35 - INFO - __main__ - Step 77148: {'lr': 0.00024391376558823398, 'samples': 14812416, 'steps': 77147, 'loss/train': 1.419026494026184} 08/31/2021 03:13:35 - INFO - __main__ - Step 77149: {'lr': 0.00024390846041808133, 'samples': 14812608, 'steps': 77148, 'loss/train': 0.1625114381313324} 08/31/2021 03:13:36 - INFO - __main__ - Step 77150: {'lr': 0.00024390315525067341, 'samples': 14812800, 'steps': 77149, 'loss/train': 0.7039492130279541} 08/31/2021 03:13:38 - INFO - __main__ - Step 77151: {'lr': 0.00024389785008601273, 'samples': 14812992, 'steps': 77150, 'loss/train': 1.1725996732711792} 08/31/2021 03:13:38 - INFO - __main__ - Step 77152: {'lr': 0.00024389254492410148, 'samples': 14813184, 'steps': 77151, 'loss/train': 0.027782248333096504} 08/31/2021 03:13:38 - INFO - __main__ - Step 77153: {'lr': 0.0002438872397649422, 'samples': 14813376, 'steps': 77152, 'loss/train': 0.018308866769075394} 08/31/2021 03:13:39 - INFO - __main__ - Step 77154: {'lr': 0.00024388193460853723, 'samples': 14813568, 'steps': 77153, 'loss/train': 1.4507744312286377} 08/31/2021 03:13:39 - INFO - __main__ - Step 77155: {'lr': 0.000243876629454889, 'samples': 14813760, 'steps': 77154, 'loss/train': 1.2807767391204834} 08/31/2021 03:13:39 - INFO - __main__ - Step 77156: {'lr': 0.00024387132430399983, 'samples': 14813952, 'steps': 77155, 'loss/train': 1.523090124130249} 08/31/2021 03:13:41 - INFO - __main__ - Step 77157: {'lr': 0.00024386601915587215, 'samples': 14814144, 'steps': 77156, 'loss/train': 1.2094218730926514} 08/31/2021 03:13:42 - INFO - __main__ - Step 77158: {'lr': 0.00024386071401050834, 'samples': 14814336, 'steps': 77157, 'loss/train': 0.2596087157726288} 08/31/2021 03:13:42 - INFO - __main__ - Step 77159: {'lr': 0.00024385540886791076, 'samples': 14814528, 'steps': 77158, 'loss/train': 1.343500018119812} 08/31/2021 03:13:42 - INFO - __main__ - Step 77160: {'lr': 0.0002438501037280819, 'samples': 14814720, 'steps': 77159, 'loss/train': 1.5086098909378052} 08/31/2021 03:13:43 - INFO - __main__ - Step 77161: {'lr': 0.00024384479859102404, 'samples': 14814912, 'steps': 77160, 'loss/train': 0.9155309200286865} 08/31/2021 03:13:44 - INFO - __main__ - Step 77162: {'lr': 0.00024383949345673964, 'samples': 14815104, 'steps': 77161, 'loss/train': 0.8195313215255737} 08/31/2021 03:13:44 - INFO - __main__ - Step 77163: {'lr': 0.00024383418832523107, 'samples': 14815296, 'steps': 77162, 'loss/train': 1.2409358024597168} 08/31/2021 03:13:45 - INFO - __main__ - Step 77164: {'lr': 0.00024382888319650077, 'samples': 14815488, 'steps': 77163, 'loss/train': 0.5161513090133667} 08/31/2021 03:13:45 - INFO - __main__ - Step 77165: {'lr': 0.0002438235780705511, 'samples': 14815680, 'steps': 77164, 'loss/train': 0.36035990715026855} 08/31/2021 03:13:46 - INFO - __main__ - Step 77166: {'lr': 0.00024381827294738434, 'samples': 14815872, 'steps': 77165, 'loss/train': 0.05524333566427231} 08/31/2021 03:13:46 - INFO - __main__ - Step 77167: {'lr': 0.000243812967827003, 'samples': 14816064, 'steps': 77166, 'loss/train': 1.2700210809707642} 08/31/2021 03:13:47 - INFO - __main__ - Step 77168: {'lr': 0.0002438076627094094, 'samples': 14816256, 'steps': 77167, 'loss/train': 1.0326871871948242} 08/31/2021 03:13:48 - INFO - __main__ - Step 77169: {'lr': 0.000243802357594606, 'samples': 14816448, 'steps': 77168, 'loss/train': 0.943231999874115} 08/31/2021 03:13:48 - INFO - __main__ - Step 77170: {'lr': 0.00024379705248259517, 'samples': 14816640, 'steps': 77169, 'loss/train': 1.1017534732818604} 08/31/2021 03:13:48 - INFO - __main__ - Step 77171: {'lr': 0.00024379174737337931, 'samples': 14816832, 'steps': 77170, 'loss/train': 0.8608362674713135} 08/31/2021 03:13:49 - INFO - __main__ - Step 77172: {'lr': 0.00024378644226696075, 'samples': 14817024, 'steps': 77171, 'loss/train': 0.680324375629425} 08/31/2021 03:13:50 - INFO - __main__ - Step 77173: {'lr': 0.00024378113716334193, 'samples': 14817216, 'steps': 77172, 'loss/train': 1.991849422454834} 08/31/2021 03:13:51 - INFO - __main__ - Step 77174: {'lr': 0.00024377583206252527, 'samples': 14817408, 'steps': 77173, 'loss/train': 1.1324448585510254} 08/31/2021 03:13:51 - INFO - __main__ - Step 77175: {'lr': 0.0002437705269645131, 'samples': 14817600, 'steps': 77174, 'loss/train': 1.9378951787948608} 08/31/2021 03:13:51 - INFO - __main__ - Step 77176: {'lr': 0.00024376522186930782, 'samples': 14817792, 'steps': 77175, 'loss/train': 1.9435782432556152} 08/31/2021 03:13:52 - INFO - __main__ - Step 77177: {'lr': 0.00024375991677691187, 'samples': 14817984, 'steps': 77176, 'loss/train': 1.3147732019424438} 08/31/2021 03:13:54 - INFO - __main__ - Step 77178: {'lr': 0.00024375461168732769, 'samples': 14818176, 'steps': 77177, 'loss/train': 1.3732423782348633} 08/31/2021 03:13:54 - INFO - __main__ - Step 77179: {'lr': 0.00024374930660055747, 'samples': 14818368, 'steps': 77178, 'loss/train': 2.2717227935791016} 08/31/2021 03:13:55 - INFO - __main__ - Step 77180: {'lr': 0.0002437440015166037, 'samples': 14818560, 'steps': 77179, 'loss/train': 1.7775083780288696} 08/31/2021 03:13:55 - INFO - __main__ - Step 77181: {'lr': 0.00024373869643546883, 'samples': 14818752, 'steps': 77180, 'loss/train': 0.11858931183815002} 08/31/2021 03:13:55 - INFO - __main__ - Step 77182: {'lr': 0.0002437333913571552, 'samples': 14818944, 'steps': 77181, 'loss/train': 0.662792980670929} 08/31/2021 03:13:56 - INFO - __main__ - Step 77183: {'lr': 0.00024372808628166518, 'samples': 14819136, 'steps': 77182, 'loss/train': 0.9806874990463257} 08/31/2021 03:13:58 - INFO - __main__ - Step 77184: {'lr': 0.0002437227812090012, 'samples': 14819328, 'steps': 77183, 'loss/train': 1.6466891765594482} 08/31/2021 03:13:58 - INFO - __main__ - Step 77185: {'lr': 0.00024371747613916565, 'samples': 14819520, 'steps': 77184, 'loss/train': 0.820631742477417} 08/31/2021 03:13:59 - INFO - __main__ - Step 77186: {'lr': 0.0002437121710721609, 'samples': 14819712, 'steps': 77185, 'loss/train': 1.6143622398376465} 08/31/2021 03:13:59 - INFO - __main__ - Step 77187: {'lr': 0.00024370686600798936, 'samples': 14819904, 'steps': 77186, 'loss/train': 0.9816027283668518} 08/31/2021 03:13:59 - INFO - __main__ - Step 77188: {'lr': 0.0002437015609466534, 'samples': 14820096, 'steps': 77187, 'loss/train': 1.7582119703292847} 08/31/2021 03:14:01 - INFO - __main__ - Step 77189: {'lr': 0.00024369625588815542, 'samples': 14820288, 'steps': 77188, 'loss/train': 0.17845135927200317} 08/31/2021 03:14:01 - INFO - __main__ - Step 77190: {'lr': 0.0002436909508324978, 'samples': 14820480, 'steps': 77189, 'loss/train': 0.6182491779327393} 08/31/2021 03:14:01 - INFO - __main__ - Step 77191: {'lr': 0.00024368564577968306, 'samples': 14820672, 'steps': 77190, 'loss/train': 1.1151150465011597} 08/31/2021 03:14:02 - INFO - __main__ - Step 77192: {'lr': 0.00024368034072971335, 'samples': 14820864, 'steps': 77191, 'loss/train': 0.9051322937011719} 08/31/2021 03:14:02 - INFO - __main__ - Step 77193: {'lr': 0.0002436750356825912, 'samples': 14821056, 'steps': 77192, 'loss/train': 1.1495904922485352} 08/31/2021 03:14:04 - INFO - __main__ - Step 77194: {'lr': 0.00024366973063831896, 'samples': 14821248, 'steps': 77193, 'loss/train': 1.1427689790725708} 08/31/2021 03:14:04 - INFO - __main__ - Step 77195: {'lr': 0.00024366442559689905, 'samples': 14821440, 'steps': 77194, 'loss/train': 0.989798903465271} 08/31/2021 03:14:05 - INFO - __main__ - Step 77196: {'lr': 0.00024365912055833384, 'samples': 14821632, 'steps': 77195, 'loss/train': 3.2011284828186035} 08/31/2021 03:14:05 - INFO - __main__ - Step 77197: {'lr': 0.00024365381552262575, 'samples': 14821824, 'steps': 77196, 'loss/train': 1.4669772386550903} 08/31/2021 03:14:05 - INFO - __main__ - Step 77198: {'lr': 0.00024364851048977714, 'samples': 14822016, 'steps': 77197, 'loss/train': 1.5697717666625977} 08/31/2021 03:14:06 - INFO - __main__ - Step 77199: {'lr': 0.00024364320545979044, 'samples': 14822208, 'steps': 77198, 'loss/train': 1.49295973777771} 08/31/2021 03:14:07 - INFO - __main__ - Step 77200: {'lr': 0.000243637900432668, 'samples': 14822400, 'steps': 77199, 'loss/train': 0.8728979825973511} 08/31/2021 03:14:08 - INFO - __main__ - Step 77201: {'lr': 0.00024363259540841222, 'samples': 14822592, 'steps': 77200, 'loss/train': 1.3295778036117554} 08/31/2021 03:14:08 - INFO - __main__ - Step 77202: {'lr': 0.00024362729038702546, 'samples': 14822784, 'steps': 77201, 'loss/train': 0.8606972098350525} 08/31/2021 03:14:08 - INFO - __main__ - Step 77203: {'lr': 0.00024362198536851022, 'samples': 14822976, 'steps': 77202, 'loss/train': 1.0587373971939087} 08/31/2021 03:14:09 - INFO - __main__ - Step 77204: {'lr': 0.00024361668035286874, 'samples': 14823168, 'steps': 77203, 'loss/train': 1.8780699968338013} 08/31/2021 03:14:10 - INFO - __main__ - Step 77205: {'lr': 0.00024361137534010364, 'samples': 14823360, 'steps': 77204, 'loss/train': 1.7743579149246216} 08/31/2021 03:14:11 - INFO - __main__ - Step 77206: {'lr': 0.00024360607033021704, 'samples': 14823552, 'steps': 77205, 'loss/train': 0.41133975982666016} 08/31/2021 03:14:11 - INFO - __main__ - Step 77207: {'lr': 0.00024360076532321142, 'samples': 14823744, 'steps': 77206, 'loss/train': 1.7018442153930664} 08/31/2021 03:14:11 - INFO - __main__ - Step 77208: {'lr': 0.00024359546031908926, 'samples': 14823936, 'steps': 77207, 'loss/train': 1.4568233489990234} 08/31/2021 03:14:12 - INFO - __main__ - Step 77209: {'lr': 0.0002435901553178528, 'samples': 14824128, 'steps': 77208, 'loss/train': 1.0619055032730103} 08/31/2021 03:14:13 - INFO - __main__ - Step 77210: {'lr': 0.0002435848503195046, 'samples': 14824320, 'steps': 77209, 'loss/train': 1.5224027633666992} 08/31/2021 03:14:14 - INFO - __main__ - Step 77211: {'lr': 0.0002435795453240469, 'samples': 14824512, 'steps': 77210, 'loss/train': 0.8406822085380554} 08/31/2021 03:14:14 - INFO - __main__ - Step 77212: {'lr': 0.00024357424033148218, 'samples': 14824704, 'steps': 77211, 'loss/train': 1.4135303497314453} 08/31/2021 03:14:14 - INFO - __main__ - Step 77213: {'lr': 0.00024356893534181281, 'samples': 14824896, 'steps': 77212, 'loss/train': 1.02332603931427} 08/31/2021 03:14:15 - INFO - __main__ - Step 77214: {'lr': 0.0002435636303550412, 'samples': 14825088, 'steps': 77213, 'loss/train': 2.256380796432495} 08/31/2021 03:14:16 - INFO - __main__ - Step 77215: {'lr': 0.0002435583253711697, 'samples': 14825280, 'steps': 77214, 'loss/train': 1.4889456033706665} 08/31/2021 03:14:17 - INFO - __main__ - Step 77216: {'lr': 0.0002435530203902007, 'samples': 14825472, 'steps': 77215, 'loss/train': 1.4411742687225342} 08/31/2021 03:14:17 - INFO - __main__ - Step 77217: {'lr': 0.00024354771541213664, 'samples': 14825664, 'steps': 77216, 'loss/train': 0.5603659749031067} 08/31/2021 03:14:17 - INFO - __main__ - Step 77218: {'lr': 0.00024354241043698, 'samples': 14825856, 'steps': 77217, 'loss/train': 1.2773079872131348} 08/31/2021 03:14:18 - INFO - __main__ - Step 77219: {'lr': 0.0002435371054647329, 'samples': 14826048, 'steps': 77218, 'loss/train': 1.4918781518936157} 08/31/2021 03:14:20 - INFO - __main__ - Step 77220: {'lr': 0.00024353180049539792, 'samples': 14826240, 'steps': 77219, 'loss/train': 1.6274909973144531} 08/31/2021 03:14:21 - INFO - __main__ - Step 77221: {'lr': 0.00024352649552897737, 'samples': 14826432, 'steps': 77220, 'loss/train': 1.282076358795166} 08/31/2021 03:14:21 - INFO - __main__ - Step 77222: {'lr': 0.0002435211905654737, 'samples': 14826624, 'steps': 77221, 'loss/train': 0.7050003409385681} 08/31/2021 03:14:21 - INFO - __main__ - Step 77223: {'lr': 0.0002435158856048893, 'samples': 14826816, 'steps': 77222, 'loss/train': 1.6064273118972778} 08/31/2021 03:14:22 - INFO - __main__ - Step 77224: {'lr': 0.00024351058064722654, 'samples': 14827008, 'steps': 77223, 'loss/train': 0.46148592233657837} 08/31/2021 03:14:22 - INFO - __main__ - Step 77225: {'lr': 0.00024350527569248778, 'samples': 14827200, 'steps': 77224, 'loss/train': 0.4083770215511322} 08/31/2021 03:14:22 - INFO - __main__ - Step 77226: {'lr': 0.00024349997074067545, 'samples': 14827392, 'steps': 77225, 'loss/train': 0.3942808508872986} 08/31/2021 03:14:24 - INFO - __main__ - Step 77227: {'lr': 0.00024349466579179195, 'samples': 14827584, 'steps': 77226, 'loss/train': 1.2444313764572144} 08/31/2021 03:14:24 - INFO - __main__ - Step 77228: {'lr': 0.00024348936084583964, 'samples': 14827776, 'steps': 77227, 'loss/train': 1.08953058719635} 08/31/2021 03:14:25 - INFO - __main__ - Step 77229: {'lr': 0.00024348405590282095, 'samples': 14827968, 'steps': 77228, 'loss/train': 1.1635867357254028} 08/31/2021 03:14:25 - INFO - __main__ - Step 77230: {'lr': 0.00024347875096273822, 'samples': 14828160, 'steps': 77229, 'loss/train': 1.2804272174835205} 08/31/2021 03:14:25 - INFO - __main__ - Step 77231: {'lr': 0.00024347344602559386, 'samples': 14828352, 'steps': 77230, 'loss/train': 1.4817816019058228} 08/31/2021 03:14:27 - INFO - __main__ - Step 77232: {'lr': 0.0002434681410913904, 'samples': 14828544, 'steps': 77231, 'loss/train': 2.0332841873168945} 08/31/2021 03:14:27 - INFO - __main__ - Step 77233: {'lr': 0.00024346283616012997, 'samples': 14828736, 'steps': 77232, 'loss/train': 1.2924768924713135} 08/31/2021 03:14:28 - INFO - __main__ - Step 77234: {'lr': 0.00024345753123181509, 'samples': 14828928, 'steps': 77233, 'loss/train': 0.7524842023849487} 08/31/2021 03:14:28 - INFO - __main__ - Step 77235: {'lr': 0.00024345222630644812, 'samples': 14829120, 'steps': 77234, 'loss/train': 1.7622085809707642} 08/31/2021 03:14:28 - INFO - __main__ - Step 77236: {'lr': 0.0002434469213840315, 'samples': 14829312, 'steps': 77235, 'loss/train': 1.6243078708648682} 08/31/2021 03:14:31 - INFO - __main__ - Step 77237: {'lr': 0.00024344161646456757, 'samples': 14829504, 'steps': 77236, 'loss/train': 0.7789441347122192} 08/31/2021 03:14:31 - INFO - __main__ - Step 77238: {'lr': 0.00024343631154805879, 'samples': 14829696, 'steps': 77237, 'loss/train': 0.15706680715084076} 08/31/2021 03:14:32 - INFO - __main__ - Step 77239: {'lr': 0.00024343100663450746, 'samples': 14829888, 'steps': 77238, 'loss/train': 1.4849244356155396} 08/31/2021 03:14:32 - INFO - __main__ - Step 77240: {'lr': 0.00024342570172391603, 'samples': 14830080, 'steps': 77239, 'loss/train': 1.165074348449707} 08/31/2021 03:14:32 - INFO - __main__ - Step 77241: {'lr': 0.0002434203968162869, 'samples': 14830272, 'steps': 77240, 'loss/train': 0.9003637433052063} 08/31/2021 03:14:33 - INFO - __main__ - Step 77242: {'lr': 0.0002434150919116224, 'samples': 14830464, 'steps': 77241, 'loss/train': 1.10321044921875} 08/31/2021 03:14:34 - INFO - __main__ - Step 77243: {'lr': 0.00024340978700992502, 'samples': 14830656, 'steps': 77242, 'loss/train': 1.32135808467865} 08/31/2021 03:14:35 - INFO - __main__ - Step 77244: {'lr': 0.00024340448211119706, 'samples': 14830848, 'steps': 77243, 'loss/train': 0.8995869159698486} 08/31/2021 03:14:35 - INFO - __main__ - Step 77245: {'lr': 0.00024339917721544102, 'samples': 14831040, 'steps': 77244, 'loss/train': 1.4042599201202393} 08/31/2021 03:14:35 - INFO - __main__ - Step 77246: {'lr': 0.00024339387232265913, 'samples': 14831232, 'steps': 77245, 'loss/train': 1.1842050552368164} 08/31/2021 03:14:36 - INFO - __main__ - Step 77247: {'lr': 0.00024338856743285383, 'samples': 14831424, 'steps': 77246, 'loss/train': 1.2311487197875977} 08/31/2021 03:14:38 - INFO - __main__ - Step 77248: {'lr': 0.00024338326254602757, 'samples': 14831616, 'steps': 77247, 'loss/train': 1.3401176929473877} 08/31/2021 03:14:38 - INFO - __main__ - Step 77249: {'lr': 0.0002433779576621827, 'samples': 14831808, 'steps': 77248, 'loss/train': 1.0576839447021484} 08/31/2021 03:14:38 - INFO - __main__ - Step 77250: {'lr': 0.00024337265278132162, 'samples': 14832000, 'steps': 77249, 'loss/train': 0.04724552109837532} 08/31/2021 03:14:39 - INFO - __main__ - Step 77251: {'lr': 0.00024336734790344672, 'samples': 14832192, 'steps': 77250, 'loss/train': 1.4426647424697876} 08/31/2021 03:14:39 - INFO - __main__ - Step 77252: {'lr': 0.00024336204302856038, 'samples': 14832384, 'steps': 77251, 'loss/train': 0.9093353152275085} 08/31/2021 03:14:41 - INFO - __main__ - Step 77253: {'lr': 0.00024335673815666502, 'samples': 14832576, 'steps': 77252, 'loss/train': 1.2424451112747192} 08/31/2021 03:14:41 - INFO - __main__ - Step 77254: {'lr': 0.000243351433287763, 'samples': 14832768, 'steps': 77253, 'loss/train': 1.4899663925170898} 08/31/2021 03:14:42 - INFO - __main__ - Step 77255: {'lr': 0.00024334612842185672, 'samples': 14832960, 'steps': 77254, 'loss/train': 1.2714354991912842} 08/31/2021 03:14:42 - INFO - __main__ - Step 77256: {'lr': 0.00024334082355894861, 'samples': 14833152, 'steps': 77255, 'loss/train': 1.3385220766067505} 08/31/2021 03:14:42 - INFO - __main__ - Step 77257: {'lr': 0.000243335518699041, 'samples': 14833344, 'steps': 77256, 'loss/train': 1.2209272384643555} 08/31/2021 03:14:44 - INFO - __main__ - Step 77258: {'lr': 0.0002433302138421363, 'samples': 14833536, 'steps': 77257, 'loss/train': 0.8972270488739014} 08/31/2021 03:14:44 - INFO - __main__ - Step 77259: {'lr': 0.00024332490898823695, 'samples': 14833728, 'steps': 77258, 'loss/train': 0.9090967178344727} 08/31/2021 03:14:44 - INFO - __main__ - Step 77260: {'lr': 0.00024331960413734522, 'samples': 14833920, 'steps': 77259, 'loss/train': 0.03574357554316521} 08/31/2021 03:14:45 - INFO - __main__ - Step 77261: {'lr': 0.0002433142992894636, 'samples': 14834112, 'steps': 77260, 'loss/train': 1.6888349056243896} 08/31/2021 03:14:45 - INFO - __main__ - Step 77262: {'lr': 0.00024330899444459446, 'samples': 14834304, 'steps': 77261, 'loss/train': 1.0197151899337769} 08/31/2021 03:14:47 - INFO - __main__ - Step 77263: {'lr': 0.00024330368960274017, 'samples': 14834496, 'steps': 77262, 'loss/train': 1.2948123216629028} 08/31/2021 03:14:47 - INFO - __main__ - Step 77264: {'lr': 0.0002432983847639031, 'samples': 14834688, 'steps': 77263, 'loss/train': 1.6113790273666382} 08/31/2021 03:14:47 - INFO - __main__ - Step 77265: {'lr': 0.00024329307992808572, 'samples': 14834880, 'steps': 77264, 'loss/train': 0.86951744556427} 08/31/2021 03:14:48 - INFO - __main__ - Step 77266: {'lr': 0.00024328777509529035, 'samples': 14835072, 'steps': 77265, 'loss/train': 1.254511833190918} 08/31/2021 03:14:48 - INFO - __main__ - Step 77267: {'lr': 0.00024328247026551947, 'samples': 14835264, 'steps': 77266, 'loss/train': 0.8580442070960999} 08/31/2021 03:14:49 - INFO - __main__ - Step 77268: {'lr': 0.00024327716543877533, 'samples': 14835456, 'steps': 77267, 'loss/train': 1.6382561922073364} 08/31/2021 03:14:50 - INFO - __main__ - Step 77269: {'lr': 0.00024327186061506043, 'samples': 14835648, 'steps': 77268, 'loss/train': 0.20886246860027313} 08/31/2021 03:14:51 - INFO - __main__ - Step 77270: {'lr': 0.0002432665557943771, 'samples': 14835840, 'steps': 77269, 'loss/train': 1.3566526174545288} 08/31/2021 03:14:51 - INFO - __main__ - Step 77271: {'lr': 0.00024326125097672778, 'samples': 14836032, 'steps': 77270, 'loss/train': 1.0588784217834473} 08/31/2021 03:14:51 - INFO - __main__ - Step 77272: {'lr': 0.00024325594616211488, 'samples': 14836224, 'steps': 77271, 'loss/train': 1.0372849702835083} 08/31/2021 03:14:52 - INFO - __main__ - Step 77273: {'lr': 0.00024325064135054069, 'samples': 14836416, 'steps': 77272, 'loss/train': 0.9449331164360046} 08/31/2021 03:14:53 - INFO - __main__ - Step 77274: {'lr': 0.00024324533654200765, 'samples': 14836608, 'steps': 77273, 'loss/train': 0.48541730642318726} 08/31/2021 03:14:54 - INFO - __main__ - Step 77275: {'lr': 0.00024324003173651815, 'samples': 14836800, 'steps': 77274, 'loss/train': 0.3473591208457947} 08/31/2021 03:14:54 - INFO - __main__ - Step 77276: {'lr': 0.00024323472693407462, 'samples': 14836992, 'steps': 77275, 'loss/train': 1.1399458646774292} 08/31/2021 03:14:54 - INFO - __main__ - Step 77277: {'lr': 0.0002432294221346794, 'samples': 14837184, 'steps': 77276, 'loss/train': 1.406922698020935} 08/31/2021 03:14:55 - INFO - __main__ - Step 77278: {'lr': 0.00024322411733833493, 'samples': 14837376, 'steps': 77277, 'loss/train': 1.4756896495819092} 08/31/2021 03:14:56 - INFO - __main__ - Step 77279: {'lr': 0.00024321881254504355, 'samples': 14837568, 'steps': 77278, 'loss/train': 1.0181193351745605} 08/31/2021 03:14:57 - INFO - __main__ - Step 77280: {'lr': 0.00024321350775480767, 'samples': 14837760, 'steps': 77279, 'loss/train': 1.5475395917892456} 08/31/2021 03:14:57 - INFO - __main__ - Step 77281: {'lr': 0.00024320820296762962, 'samples': 14837952, 'steps': 77280, 'loss/train': 0.8634693622589111} 08/31/2021 03:14:57 - INFO - __main__ - Step 77282: {'lr': 0.0002432028981835119, 'samples': 14838144, 'steps': 77281, 'loss/train': 1.624778389930725} 08/31/2021 03:14:58 - INFO - __main__ - Step 77283: {'lr': 0.00024319759340245685, 'samples': 14838336, 'steps': 77282, 'loss/train': 1.3981066942214966} 08/31/2021 03:14:59 - INFO - __main__ - Step 77284: {'lr': 0.00024319228862446684, 'samples': 14838528, 'steps': 77283, 'loss/train': 0.06346995383501053} 08/31/2021 03:15:00 - INFO - __main__ - Step 77285: {'lr': 0.00024318698384954434, 'samples': 14838720, 'steps': 77284, 'loss/train': 1.1113333702087402} 08/31/2021 03:15:00 - INFO - __main__ - Step 77286: {'lr': 0.00024318167907769165, 'samples': 14838912, 'steps': 77285, 'loss/train': 1.3481522798538208} 08/31/2021 03:15:00 - INFO - __main__ - Step 77287: {'lr': 0.00024317637430891115, 'samples': 14839104, 'steps': 77286, 'loss/train': 1.112415075302124} 08/31/2021 03:15:01 - INFO - __main__ - Step 77288: {'lr': 0.00024317106954320532, 'samples': 14839296, 'steps': 77287, 'loss/train': 1.6633208990097046} 08/31/2021 03:15:01 - INFO - __main__ - Step 77289: {'lr': 0.0002431657647805765, 'samples': 14839488, 'steps': 77288, 'loss/train': 1.0416179895401} 08/31/2021 03:15:03 - INFO - __main__ - Step 77290: {'lr': 0.00024316046002102707, 'samples': 14839680, 'steps': 77289, 'loss/train': 1.228756070137024} 08/31/2021 03:15:03 - INFO - __main__ - Step 77291: {'lr': 0.0002431551552645594, 'samples': 14839872, 'steps': 77290, 'loss/train': 1.2612135410308838} 08/31/2021 03:15:04 - INFO - __main__ - Step 77292: {'lr': 0.00024314985051117593, 'samples': 14840064, 'steps': 77291, 'loss/train': 1.5058262348175049} 08/31/2021 03:15:04 - INFO - __main__ - Step 77293: {'lr': 0.00024314454576087902, 'samples': 14840256, 'steps': 77292, 'loss/train': 0.6106358170509338} 08/31/2021 03:15:04 - INFO - __main__ - Step 77294: {'lr': 0.0002431392410136711, 'samples': 14840448, 'steps': 77293, 'loss/train': 0.6178337931632996} 08/31/2021 03:15:06 - INFO - __main__ - Step 77295: {'lr': 0.00024313393626955448, 'samples': 14840640, 'steps': 77294, 'loss/train': 0.8332637548446655} 08/31/2021 03:15:07 - INFO - __main__ - Step 77296: {'lr': 0.00024312863152853165, 'samples': 14840832, 'steps': 77295, 'loss/train': 1.1086735725402832} 08/31/2021 03:15:07 - INFO - __main__ - Step 77297: {'lr': 0.00024312332679060492, 'samples': 14841024, 'steps': 77296, 'loss/train': 1.7242754697799683} 08/31/2021 03:15:07 - INFO - __main__ - Step 77298: {'lr': 0.00024311802205577673, 'samples': 14841216, 'steps': 77297, 'loss/train': 0.9890877604484558} 08/31/2021 03:15:08 - INFO - __main__ - Step 77299: {'lr': 0.0002431127173240495, 'samples': 14841408, 'steps': 77298, 'loss/train': 1.8692210912704468} 08/31/2021 03:15:09 - INFO - __main__ - Step 77300: {'lr': 0.0002431074125954256, 'samples': 14841600, 'steps': 77299, 'loss/train': 0.6205293536186218} 08/31/2021 03:15:10 - INFO - __main__ - Step 77301: {'lr': 0.0002431021078699073, 'samples': 14841792, 'steps': 77300, 'loss/train': 1.5849493741989136} 08/31/2021 03:15:10 - INFO - __main__ - Step 77302: {'lr': 0.0002430968031474971, 'samples': 14841984, 'steps': 77301, 'loss/train': 1.6234349012374878} 08/31/2021 03:15:10 - INFO - __main__ - Step 77303: {'lr': 0.0002430914984281974, 'samples': 14842176, 'steps': 77302, 'loss/train': 1.3040013313293457} 08/31/2021 03:15:11 - INFO - __main__ - Step 77304: {'lr': 0.0002430861937120105, 'samples': 14842368, 'steps': 77303, 'loss/train': 1.4746965169906616} 08/31/2021 03:15:12 - INFO - __main__ - Step 77305: {'lr': 0.0002430808889989389, 'samples': 14842560, 'steps': 77304, 'loss/train': 0.8885252475738525} 08/31/2021 03:15:13 - INFO - __main__ - Step 77306: {'lr': 0.00024307558428898494, 'samples': 14842752, 'steps': 77305, 'loss/train': 1.1546730995178223} 08/31/2021 03:15:13 - INFO - __main__ - Step 77307: {'lr': 0.00024307027958215104, 'samples': 14842944, 'steps': 77306, 'loss/train': 0.5686846375465393} 08/31/2021 03:15:14 - INFO - __main__ - Step 77308: {'lr': 0.0002430649748784395, 'samples': 14843136, 'steps': 77307, 'loss/train': 2.024496555328369} 08/31/2021 03:15:14 - INFO - __main__ - Step 77309: {'lr': 0.00024305967017785283, 'samples': 14843328, 'steps': 77308, 'loss/train': 0.879857063293457} 08/31/2021 03:15:14 - INFO - __main__ - Step 77310: {'lr': 0.00024305436548039335, 'samples': 14843520, 'steps': 77309, 'loss/train': 1.6196449995040894} 08/31/2021 03:15:16 - INFO - __main__ - Step 77311: {'lr': 0.00024304906078606345, 'samples': 14843712, 'steps': 77310, 'loss/train': 1.0554007291793823} 08/31/2021 03:15:17 - INFO - __main__ - Step 77312: {'lr': 0.00024304375609486567, 'samples': 14843904, 'steps': 77311, 'loss/train': 1.2701284885406494} 08/31/2021 03:15:17 - INFO - __main__ - Step 77313: {'lr': 0.00024303845140680213, 'samples': 14844096, 'steps': 77312, 'loss/train': 1.1300724744796753} 08/31/2021 03:15:17 - INFO - __main__ - Step 77314: {'lr': 0.0002430331467218754, 'samples': 14844288, 'steps': 77313, 'loss/train': 0.9029648303985596} 08/31/2021 03:15:18 - INFO - __main__ - Step 77315: {'lr': 0.0002430278420400878, 'samples': 14844480, 'steps': 77314, 'loss/train': 1.8024054765701294} 08/31/2021 03:15:18 - INFO - __main__ - Step 77316: {'lr': 0.00024302253736144177, 'samples': 14844672, 'steps': 77315, 'loss/train': 1.658441185951233} 08/31/2021 03:15:20 - INFO - __main__ - Step 77317: {'lr': 0.0002430172326859396, 'samples': 14844864, 'steps': 77316, 'loss/train': 1.7008508443832397} 08/31/2021 03:15:20 - INFO - __main__ - Step 77318: {'lr': 0.00024301192801358385, 'samples': 14845056, 'steps': 77317, 'loss/train': 0.03536499664187431} 08/31/2021 03:15:21 - INFO - __main__ - Step 77319: {'lr': 0.00024300662334437675, 'samples': 14845248, 'steps': 77318, 'loss/train': 1.2622572183609009} 08/31/2021 03:15:21 - INFO - __main__ - Step 77320: {'lr': 0.00024300131867832078, 'samples': 14845440, 'steps': 77319, 'loss/train': 1.7902050018310547} 08/31/2021 03:15:21 - INFO - __main__ - Step 77321: {'lr': 0.00024299601401541832, 'samples': 14845632, 'steps': 77320, 'loss/train': 1.1223410367965698} 08/31/2021 03:15:23 - INFO - __main__ - Step 77322: {'lr': 0.00024299070935567175, 'samples': 14845824, 'steps': 77321, 'loss/train': 1.2323169708251953} 08/31/2021 03:15:23 - INFO - __main__ - Step 77323: {'lr': 0.00024298540469908344, 'samples': 14846016, 'steps': 77322, 'loss/train': 1.028703212738037} 08/31/2021 03:15:24 - INFO - __main__ - Step 77324: {'lr': 0.00024298010004565582, 'samples': 14846208, 'steps': 77323, 'loss/train': 1.1830507516860962} 08/31/2021 03:15:24 - INFO - __main__ - Step 77325: {'lr': 0.00024297479539539126, 'samples': 14846400, 'steps': 77324, 'loss/train': 1.5813874006271362} 08/31/2021 03:15:24 - INFO - __main__ - Step 77326: {'lr': 0.00024296949074829223, 'samples': 14846592, 'steps': 77325, 'loss/train': 0.7577455043792725} 08/31/2021 03:15:26 - INFO - __main__ - Step 77327: {'lr': 0.00024296418610436095, 'samples': 14846784, 'steps': 77326, 'loss/train': 0.2777992784976959} 08/31/2021 03:15:26 - INFO - __main__ - Step 77328: {'lr': 0.0002429588814635999, 'samples': 14846976, 'steps': 77327, 'loss/train': 1.2950427532196045} 08/31/2021 03:15:27 - INFO - __main__ - Step 77329: {'lr': 0.00024295357682601145, 'samples': 14847168, 'steps': 77328, 'loss/train': 1.7894480228424072} 08/31/2021 03:15:27 - INFO - __main__ - Step 77330: {'lr': 0.00024294827219159803, 'samples': 14847360, 'steps': 77329, 'loss/train': 1.305671215057373} 08/31/2021 03:15:27 - INFO - __main__ - Step 77331: {'lr': 0.000242942967560362, 'samples': 14847552, 'steps': 77330, 'loss/train': 1.273114800453186} 08/31/2021 03:15:28 - INFO - __main__ - Step 77332: {'lr': 0.00024293766293230577, 'samples': 14847744, 'steps': 77331, 'loss/train': 1.8914176225662231} 08/31/2021 03:15:29 - INFO - __main__ - Step 77333: {'lr': 0.00024293235830743172, 'samples': 14847936, 'steps': 77332, 'loss/train': 1.3291358947753906} 08/31/2021 03:15:30 - INFO - __main__ - Step 77334: {'lr': 0.00024292705368574223, 'samples': 14848128, 'steps': 77333, 'loss/train': 0.805884838104248} 08/31/2021 03:15:30 - INFO - __main__ - Step 77335: {'lr': 0.0002429217490672397, 'samples': 14848320, 'steps': 77334, 'loss/train': 0.8516721725463867} 08/31/2021 03:15:31 - INFO - __main__ - Step 77336: {'lr': 0.00024291644445192652, 'samples': 14848512, 'steps': 77335, 'loss/train': 1.3185782432556152} 08/31/2021 03:15:31 - INFO - __main__ - Step 77337: {'lr': 0.00024291113983980505, 'samples': 14848704, 'steps': 77336, 'loss/train': 0.46483930945396423} 08/31/2021 03:15:33 - INFO - __main__ - Step 77338: {'lr': 0.00024290583523087778, 'samples': 14848896, 'steps': 77337, 'loss/train': 1.0637511014938354} 08/31/2021 03:15:34 - INFO - __main__ - Step 77339: {'lr': 0.00024290053062514712, 'samples': 14849088, 'steps': 77338, 'loss/train': 1.9514884948730469} 08/31/2021 03:15:34 - INFO - __main__ - Step 77340: {'lr': 0.00024289522602261523, 'samples': 14849280, 'steps': 77339, 'loss/train': 1.8429951667785645} 08/31/2021 03:15:35 - INFO - __main__ - Step 77341: {'lr': 0.00024288992142328463, 'samples': 14849472, 'steps': 77340, 'loss/train': 0.8740030527114868} 08/31/2021 03:15:35 - INFO - __main__ - Step 77342: {'lr': 0.00024288461682715778, 'samples': 14849664, 'steps': 77341, 'loss/train': 1.4484366178512573} 08/31/2021 03:15:35 - INFO - __main__ - Step 77343: {'lr': 0.000242879312234237, 'samples': 14849856, 'steps': 77342, 'loss/train': 0.21034115552902222} 08/31/2021 03:15:36 - INFO - __main__ - Step 77344: {'lr': 0.00024287400764452465, 'samples': 14850048, 'steps': 77343, 'loss/train': 0.5220330953598022} 08/31/2021 03:15:36 - INFO - __main__ - Step 77345: {'lr': 0.00024286870305802318, 'samples': 14850240, 'steps': 77344, 'loss/train': 0.49104321002960205} 08/31/2021 03:15:37 - INFO - __main__ - Step 77346: {'lr': 0.000242863398474735, 'samples': 14850432, 'steps': 77345, 'loss/train': 1.8339956998825073} 08/31/2021 03:15:38 - INFO - __main__ - Step 77347: {'lr': 0.0002428580938946624, 'samples': 14850624, 'steps': 77346, 'loss/train': 1.6551216840744019} 08/31/2021 03:15:38 - INFO - __main__ - Step 77348: {'lr': 0.0002428527893178079, 'samples': 14850816, 'steps': 77347, 'loss/train': 0.36371201276779175} 08/31/2021 03:15:39 - INFO - __main__ - Step 77349: {'lr': 0.00024284748474417376, 'samples': 14851008, 'steps': 77348, 'loss/train': 1.5429754257202148} 08/31/2021 03:15:39 - INFO - __main__ - Step 77350: {'lr': 0.00024284218017376247, 'samples': 14851200, 'steps': 77349, 'loss/train': 0.7137227058410645} 08/31/2021 03:15:41 - INFO - __main__ - Step 77351: {'lr': 0.00024283687560657636, 'samples': 14851392, 'steps': 77350, 'loss/train': 1.065508246421814} 08/31/2021 03:15:41 - INFO - __main__ - Step 77352: {'lr': 0.00024283157104261786, 'samples': 14851584, 'steps': 77351, 'loss/train': 1.0376466512680054} 08/31/2021 03:15:42 - INFO - __main__ - Step 77353: {'lr': 0.00024282626648188947, 'samples': 14851776, 'steps': 77352, 'loss/train': 1.733897089958191} 08/31/2021 03:15:42 - INFO - __main__ - Step 77354: {'lr': 0.0002428209619243933, 'samples': 14851968, 'steps': 77353, 'loss/train': 1.3500744104385376} 08/31/2021 03:15:42 - INFO - __main__ - Step 77355: {'lr': 0.00024281565737013192, 'samples': 14852160, 'steps': 77354, 'loss/train': 0.9183225631713867} 08/31/2021 03:15:44 - INFO - __main__ - Step 77356: {'lr': 0.0002428103528191077, 'samples': 14852352, 'steps': 77355, 'loss/train': 1.4232922792434692} 08/31/2021 03:15:44 - INFO - __main__ - Step 77357: {'lr': 0.00024280504827132302, 'samples': 14852544, 'steps': 77356, 'loss/train': 1.6383723020553589} 08/31/2021 03:15:45 - INFO - __main__ - Step 77358: {'lr': 0.00024279974372678025, 'samples': 14852736, 'steps': 77357, 'loss/train': 1.5497928857803345} 08/31/2021 03:15:45 - INFO - __main__ - Step 77359: {'lr': 0.00024279443918548183, 'samples': 14852928, 'steps': 77358, 'loss/train': 0.4538704752922058} 08/31/2021 03:15:45 - INFO - __main__ - Step 77360: {'lr': 0.00024278913464743012, 'samples': 14853120, 'steps': 77359, 'loss/train': 1.0484946966171265} 08/31/2021 03:15:47 - INFO - __main__ - Step 77361: {'lr': 0.00024278383011262753, 'samples': 14853312, 'steps': 77360, 'loss/train': 1.0058166980743408} 08/31/2021 03:15:48 - INFO - __main__ - Step 77362: {'lr': 0.0002427785255810764, 'samples': 14853504, 'steps': 77361, 'loss/train': 0.6937597393989563} 08/31/2021 03:15:48 - INFO - __main__ - Step 77363: {'lr': 0.0002427732210527792, 'samples': 14853696, 'steps': 77362, 'loss/train': 1.1289061307907104} 08/31/2021 03:15:49 - INFO - __main__ - Step 77364: {'lr': 0.00024276791652773824, 'samples': 14853888, 'steps': 77363, 'loss/train': 2.242788314819336} 08/31/2021 03:15:49 - INFO - __main__ - Step 77365: {'lr': 0.00024276261200595594, 'samples': 14854080, 'steps': 77364, 'loss/train': 3.422696828842163} 08/31/2021 03:15:49 - INFO - __main__ - Step 77366: {'lr': 0.0002427573074874348, 'samples': 14854272, 'steps': 77365, 'loss/train': 1.16033935546875} 08/31/2021 03:15:51 - INFO - __main__ - Step 77367: {'lr': 0.00024275200297217703, 'samples': 14854464, 'steps': 77366, 'loss/train': 1.5236023664474487} 08/31/2021 03:15:51 - INFO - __main__ - Step 77368: {'lr': 0.0002427466984601851, 'samples': 14854656, 'steps': 77367, 'loss/train': 1.2236956357955933} 08/31/2021 03:15:52 - INFO - __main__ - Step 77369: {'lr': 0.0002427413939514614, 'samples': 14854848, 'steps': 77368, 'loss/train': 0.9485108256340027} 08/31/2021 03:15:52 - INFO - __main__ - Step 77370: {'lr': 0.00024273608944600826, 'samples': 14855040, 'steps': 77369, 'loss/train': 0.38896411657333374} 08/31/2021 03:15:52 - INFO - __main__ - Step 77371: {'lr': 0.00024273078494382817, 'samples': 14855232, 'steps': 77370, 'loss/train': 0.8218410611152649} 08/31/2021 03:15:54 - INFO - __main__ - Step 77372: {'lr': 0.00024272548044492346, 'samples': 14855424, 'steps': 77371, 'loss/train': 0.8419135808944702} 08/31/2021 03:15:55 - INFO - __main__ - Step 77373: {'lr': 0.00024272017594929654, 'samples': 14855616, 'steps': 77372, 'loss/train': 0.7297095060348511} 08/31/2021 03:15:55 - INFO - __main__ - Step 77374: {'lr': 0.00024271487145694978, 'samples': 14855808, 'steps': 77373, 'loss/train': 0.9930762648582458} 08/31/2021 03:15:55 - INFO - __main__ - Step 77375: {'lr': 0.00024270956696788561, 'samples': 14856000, 'steps': 77374, 'loss/train': 1.157196044921875} 08/31/2021 03:15:56 - INFO - __main__ - Step 77376: {'lr': 0.0002427042624821064, 'samples': 14856192, 'steps': 77375, 'loss/train': 2.2826974391937256} 08/31/2021 03:15:57 - INFO - __main__ - Step 77377: {'lr': 0.00024269895799961452, 'samples': 14856384, 'steps': 77376, 'loss/train': 1.4380030632019043} 08/31/2021 03:15:58 - INFO - __main__ - Step 77378: {'lr': 0.0002426936535204124, 'samples': 14856576, 'steps': 77377, 'loss/train': 0.8966121077537537} 08/31/2021 03:15:58 - INFO - __main__ - Step 77379: {'lr': 0.00024268834904450239, 'samples': 14856768, 'steps': 77378, 'loss/train': 1.5771470069885254} 08/31/2021 03:15:58 - INFO - __main__ - Step 77380: {'lr': 0.000242683044571887, 'samples': 14856960, 'steps': 77379, 'loss/train': 1.7216140031814575} 08/31/2021 03:15:59 - INFO - __main__ - Step 77381: {'lr': 0.0002426777401025684, 'samples': 14857152, 'steps': 77380, 'loss/train': 2.4109952449798584} 08/31/2021 03:15:59 - INFO - __main__ - Step 77382: {'lr': 0.00024267243563654912, 'samples': 14857344, 'steps': 77381, 'loss/train': 1.1634210348129272} 08/31/2021 03:16:00 - INFO - __main__ - Step 77383: {'lr': 0.00024266713117383152, 'samples': 14857536, 'steps': 77382, 'loss/train': 1.8131303787231445} 08/31/2021 03:16:01 - INFO - __main__ - Step 77384: {'lr': 0.000242661826714418, 'samples': 14857728, 'steps': 77383, 'loss/train': 0.8250053524971008} 08/31/2021 03:16:01 - INFO - __main__ - Step 77385: {'lr': 0.00024265652225831095, 'samples': 14857920, 'steps': 77384, 'loss/train': 0.9430686831474304} 08/31/2021 03:16:02 - INFO - __main__ - Step 77386: {'lr': 0.00024265121780551275, 'samples': 14858112, 'steps': 77385, 'loss/train': 1.5243626832962036} 08/31/2021 03:16:02 - INFO - __main__ - Step 77387: {'lr': 0.00024264591335602579, 'samples': 14858304, 'steps': 77386, 'loss/train': 0.9290968179702759} 08/31/2021 03:16:04 - INFO - __main__ - Step 77388: {'lr': 0.0002426406089098525, 'samples': 14858496, 'steps': 77387, 'loss/train': 0.5007964968681335} 08/31/2021 03:16:04 - INFO - __main__ - Step 77389: {'lr': 0.0002426353044669952, 'samples': 14858688, 'steps': 77388, 'loss/train': 0.8806031942367554} 08/31/2021 03:16:04 - INFO - __main__ - Step 77390: {'lr': 0.00024263000002745634, 'samples': 14858880, 'steps': 77389, 'loss/train': 1.616040825843811} 08/31/2021 03:16:05 - INFO - __main__ - Step 77391: {'lr': 0.00024262469559123835, 'samples': 14859072, 'steps': 77390, 'loss/train': 0.8564125895500183} 08/31/2021 03:16:05 - INFO - __main__ - Step 77392: {'lr': 0.00024261939115834347, 'samples': 14859264, 'steps': 77391, 'loss/train': 1.469318151473999} 08/31/2021 03:16:07 - INFO - __main__ - Step 77393: {'lr': 0.00024261408672877425, 'samples': 14859456, 'steps': 77392, 'loss/train': 1.9247756004333496} 08/31/2021 03:16:07 - INFO - __main__ - Step 77394: {'lr': 0.00024260878230253298, 'samples': 14859648, 'steps': 77393, 'loss/train': 1.5526981353759766} 08/31/2021 03:16:07 - INFO - __main__ - Step 77395: {'lr': 0.00024260347787962203, 'samples': 14859840, 'steps': 77394, 'loss/train': 1.0321688652038574} 08/31/2021 03:16:08 - INFO - __main__ - Step 77396: {'lr': 0.00024259817346004387, 'samples': 14860032, 'steps': 77395, 'loss/train': 1.462440013885498} 08/31/2021 03:16:08 - INFO - __main__ - Step 77397: {'lr': 0.00024259286904380087, 'samples': 14860224, 'steps': 77396, 'loss/train': 1.5570917129516602} 08/31/2021 03:16:10 - INFO - __main__ - Step 77398: {'lr': 0.00024258756463089537, 'samples': 14860416, 'steps': 77397, 'loss/train': 1.87887442111969} 08/31/2021 03:16:10 - INFO - __main__ - Step 77399: {'lr': 0.00024258226022132984, 'samples': 14860608, 'steps': 77398, 'loss/train': 0.9812566041946411} 08/31/2021 03:16:10 - INFO - __main__ - Step 77400: {'lr': 0.0002425769558151066, 'samples': 14860800, 'steps': 77399, 'loss/train': 0.6072110533714294} 08/31/2021 03:16:11 - INFO - __main__ - Step 77401: {'lr': 0.00024257165141222808, 'samples': 14860992, 'steps': 77400, 'loss/train': 1.5045418739318848} 08/31/2021 03:16:11 - INFO - __main__ - Step 77402: {'lr': 0.00024256634701269673, 'samples': 14861184, 'steps': 77401, 'loss/train': 1.2399126291275024} 08/31/2021 03:16:13 - INFO - __main__ - Step 77403: {'lr': 0.0002425610426165148, 'samples': 14861376, 'steps': 77402, 'loss/train': 1.5453507900238037} 08/31/2021 03:16:13 - INFO - __main__ - Step 77404: {'lr': 0.00024255573822368475, 'samples': 14861568, 'steps': 77403, 'loss/train': 1.2212316989898682} 08/31/2021 03:16:14 - INFO - __main__ - Step 77405: {'lr': 0.00024255043383420897, 'samples': 14861760, 'steps': 77404, 'loss/train': 1.3969770669937134} 08/31/2021 03:16:14 - INFO - __main__ - Step 77406: {'lr': 0.0002425451294480899, 'samples': 14861952, 'steps': 77405, 'loss/train': 0.9228094816207886} 08/31/2021 03:16:15 - INFO - __main__ - Step 77407: {'lr': 0.0002425398250653298, 'samples': 14862144, 'steps': 77406, 'loss/train': 1.2626222372055054} 08/31/2021 03:16:15 - INFO - __main__ - Step 77408: {'lr': 0.00024253452068593117, 'samples': 14862336, 'steps': 77407, 'loss/train': 0.2121461182832718} 08/31/2021 03:16:17 - INFO - __main__ - Step 77409: {'lr': 0.00024252921630989638, 'samples': 14862528, 'steps': 77408, 'loss/train': 1.0292036533355713} 08/31/2021 03:16:17 - INFO - __main__ - Step 77410: {'lr': 0.00024252391193722782, 'samples': 14862720, 'steps': 77409, 'loss/train': 0.9349996447563171} 08/31/2021 03:16:17 - INFO - __main__ - Step 77411: {'lr': 0.00024251860756792782, 'samples': 14862912, 'steps': 77410, 'loss/train': 1.3498146533966064} 08/31/2021 03:16:18 - INFO - __main__ - Step 77412: {'lr': 0.0002425133032019989, 'samples': 14863104, 'steps': 77411, 'loss/train': 1.2879832983016968} 08/31/2021 03:16:18 - INFO - __main__ - Step 77413: {'lr': 0.00024250799883944333, 'samples': 14863296, 'steps': 77412, 'loss/train': 1.1985249519348145} 08/31/2021 03:16:20 - INFO - __main__ - Step 77414: {'lr': 0.00024250269448026352, 'samples': 14863488, 'steps': 77413, 'loss/train': 1.4255177974700928} 08/31/2021 03:16:20 - INFO - __main__ - Step 77415: {'lr': 0.0002424973901244619, 'samples': 14863680, 'steps': 77414, 'loss/train': 1.5176395177841187} 08/31/2021 03:16:21 - INFO - __main__ - Step 77416: {'lr': 0.00024249208577204083, 'samples': 14863872, 'steps': 77415, 'loss/train': 1.2324415445327759} 08/31/2021 03:16:21 - INFO - __main__ - Step 77417: {'lr': 0.00024248678142300268, 'samples': 14864064, 'steps': 77416, 'loss/train': 0.8184910416603088} 08/31/2021 03:16:21 - INFO - __main__ - Step 77418: {'lr': 0.0002424814770773499, 'samples': 14864256, 'steps': 77417, 'loss/train': 0.689530611038208} 08/31/2021 03:16:23 - INFO - __main__ - Step 77419: {'lr': 0.00024247617273508485, 'samples': 14864448, 'steps': 77418, 'loss/train': 0.06198124960064888} 08/31/2021 03:16:23 - INFO - __main__ - Step 77420: {'lr': 0.00024247086839620998, 'samples': 14864640, 'steps': 77419, 'loss/train': 1.1615487337112427} 08/31/2021 03:16:23 - INFO - __main__ - Step 77421: {'lr': 0.00024246556406072757, 'samples': 14864832, 'steps': 77420, 'loss/train': 1.470333218574524} 08/31/2021 03:16:24 - INFO - __main__ - Step 77422: {'lr': 0.00024246025972864002, 'samples': 14865024, 'steps': 77421, 'loss/train': 0.3044065535068512} 08/31/2021 03:16:24 - INFO - __main__ - Step 77423: {'lr': 0.00024245495539994985, 'samples': 14865216, 'steps': 77422, 'loss/train': 1.1758538484573364} 08/31/2021 03:16:26 - INFO - __main__ - Step 77424: {'lr': 0.00024244965107465932, 'samples': 14865408, 'steps': 77423, 'loss/train': 1.106381893157959} 08/31/2021 03:16:26 - INFO - __main__ - Step 77425: {'lr': 0.00024244434675277084, 'samples': 14865600, 'steps': 77424, 'loss/train': 0.5298746228218079} 08/31/2021 03:16:27 - INFO - __main__ - Step 77426: {'lr': 0.00024243904243428683, 'samples': 14865792, 'steps': 77425, 'loss/train': 0.7191224694252014} 08/31/2021 03:16:27 - INFO - __main__ - Step 77427: {'lr': 0.00024243373811920965, 'samples': 14865984, 'steps': 77426, 'loss/train': 0.8096314668655396} 08/31/2021 03:16:27 - INFO - __main__ - Step 77428: {'lr': 0.00024242843380754172, 'samples': 14866176, 'steps': 77427, 'loss/train': 1.912318468093872} 08/31/2021 03:16:29 - INFO - __main__ - Step 77429: {'lr': 0.00024242312949928545, 'samples': 14866368, 'steps': 77428, 'loss/train': 1.1583648920059204} 08/31/2021 03:16:30 - INFO - __main__ - Step 77430: {'lr': 0.00024241782519444317, 'samples': 14866560, 'steps': 77429, 'loss/train': 0.050582632422447205} 08/31/2021 03:16:30 - INFO - __main__ - Step 77431: {'lr': 0.0002424125208930173, 'samples': 14866752, 'steps': 77430, 'loss/train': 0.8992286920547485} 08/31/2021 03:16:30 - INFO - __main__ - Step 77432: {'lr': 0.00024240721659501022, 'samples': 14866944, 'steps': 77431, 'loss/train': 1.6326096057891846} 08/31/2021 03:16:31 - INFO - __main__ - Step 77433: {'lr': 0.0002424019123004244, 'samples': 14867136, 'steps': 77432, 'loss/train': 1.4816479682922363} 08/31/2021 03:16:32 - INFO - __main__ - Step 77434: {'lr': 0.00024239660800926216, 'samples': 14867328, 'steps': 77433, 'loss/train': 1.7415803670883179} 08/31/2021 03:16:33 - INFO - __main__ - Step 77435: {'lr': 0.00024239130372152585, 'samples': 14867520, 'steps': 77434, 'loss/train': 0.9714125394821167} 08/31/2021 03:16:33 - INFO - __main__ - Step 77436: {'lr': 0.0002423859994372179, 'samples': 14867712, 'steps': 77435, 'loss/train': 1.1355376243591309} 08/31/2021 03:16:33 - INFO - __main__ - Step 77437: {'lr': 0.00024238069515634071, 'samples': 14867904, 'steps': 77436, 'loss/train': 1.2837581634521484} 08/31/2021 03:16:34 - INFO - __main__ - Step 77438: {'lr': 0.00024237539087889663, 'samples': 14868096, 'steps': 77437, 'loss/train': 0.5779731273651123} 08/31/2021 03:16:35 - INFO - __main__ - Step 77439: {'lr': 0.0002423700866048881, 'samples': 14868288, 'steps': 77438, 'loss/train': 2.5795938968658447} 08/31/2021 03:16:36 - INFO - __main__ - Step 77440: {'lr': 0.00024236478233431746, 'samples': 14868480, 'steps': 77439, 'loss/train': 1.3125890493392944} 08/31/2021 03:16:36 - INFO - __main__ - Step 77441: {'lr': 0.00024235947806718717, 'samples': 14868672, 'steps': 77440, 'loss/train': 0.6347391605377197} 08/31/2021 03:16:37 - INFO - __main__ - Step 77442: {'lr': 0.00024235417380349958, 'samples': 14868864, 'steps': 77441, 'loss/train': 0.04962792620062828} 08/31/2021 03:16:37 - INFO - __main__ - Step 77443: {'lr': 0.00024234886954325706, 'samples': 14869056, 'steps': 77442, 'loss/train': 1.6083133220672607} 08/31/2021 03:16:37 - INFO - __main__ - Step 77444: {'lr': 0.00024234356528646204, 'samples': 14869248, 'steps': 77443, 'loss/train': 1.2935631275177002} 08/31/2021 03:16:39 - INFO - __main__ - Step 77445: {'lr': 0.00024233826103311687, 'samples': 14869440, 'steps': 77444, 'loss/train': 1.025225281715393} 08/31/2021 03:16:39 - INFO - __main__ - Step 77446: {'lr': 0.000242332956783224, 'samples': 14869632, 'steps': 77445, 'loss/train': 1.072203516960144} 08/31/2021 03:16:40 - INFO - __main__ - Step 77447: {'lr': 0.00024232765253678584, 'samples': 14869824, 'steps': 77446, 'loss/train': 1.7395644187927246} 08/31/2021 03:16:40 - INFO - __main__ - Step 77448: {'lr': 0.00024232234829380463, 'samples': 14870016, 'steps': 77447, 'loss/train': 1.8015029430389404} 08/31/2021 03:16:40 - INFO - __main__ - Step 77449: {'lr': 0.00024231704405428288, 'samples': 14870208, 'steps': 77448, 'loss/train': 0.7765381336212158} 08/31/2021 03:16:42 - INFO - __main__ - Step 77450: {'lr': 0.00024231173981822292, 'samples': 14870400, 'steps': 77449, 'loss/train': 1.2503525018692017} 08/31/2021 03:16:43 - INFO - __main__ - Step 77451: {'lr': 0.0002423064355856272, 'samples': 14870592, 'steps': 77450, 'loss/train': 0.997713565826416} 08/31/2021 03:16:43 - INFO - __main__ - Step 77452: {'lr': 0.00024230113135649805, 'samples': 14870784, 'steps': 77451, 'loss/train': 0.024369876831769943} 08/31/2021 03:16:43 - INFO - __main__ - Step 77453: {'lr': 0.00024229582713083793, 'samples': 14870976, 'steps': 77452, 'loss/train': 1.5704166889190674} 08/31/2021 03:16:44 - INFO - __main__ - Step 77454: {'lr': 0.00024229052290864915, 'samples': 14871168, 'steps': 77453, 'loss/train': 0.9049657583236694} 08/31/2021 03:16:44 - INFO - __main__ - Step 77455: {'lr': 0.00024228521868993418, 'samples': 14871360, 'steps': 77454, 'loss/train': 1.3354947566986084} 08/31/2021 03:16:45 - INFO - __main__ - Step 77456: {'lr': 0.00024227991447469533, 'samples': 14871552, 'steps': 77455, 'loss/train': 1.8544692993164062} 08/31/2021 03:16:46 - INFO - __main__ - Step 77457: {'lr': 0.00024227461026293505, 'samples': 14871744, 'steps': 77456, 'loss/train': 1.516595721244812} 08/31/2021 03:16:46 - INFO - __main__ - Step 77458: {'lr': 0.0002422693060546557, 'samples': 14871936, 'steps': 77457, 'loss/train': 1.835782527923584} 08/31/2021 03:16:47 - INFO - __main__ - Step 77459: {'lr': 0.00024226400184985969, 'samples': 14872128, 'steps': 77458, 'loss/train': 1.2981981039047241} 08/31/2021 03:16:47 - INFO - __main__ - Step 77460: {'lr': 0.00024225869764854952, 'samples': 14872320, 'steps': 77459, 'loss/train': 0.8788138628005981} 08/31/2021 03:16:49 - INFO - __main__ - Step 77461: {'lr': 0.00024225339345072735, 'samples': 14872512, 'steps': 77460, 'loss/train': 1.0525721311569214} 08/31/2021 03:16:50 - INFO - __main__ - Step 77462: {'lr': 0.00024224808925639568, 'samples': 14872704, 'steps': 77461, 'loss/train': 1.250099539756775} 08/31/2021 03:16:50 - INFO - __main__ - Step 77463: {'lr': 0.00024224278506555688, 'samples': 14872896, 'steps': 77462, 'loss/train': 2.2614994049072266} 08/31/2021 03:16:50 - INFO - __main__ - Step 77464: {'lr': 0.0002422374808782134, 'samples': 14873088, 'steps': 77463, 'loss/train': 1.4788024425506592} 08/31/2021 03:16:51 - INFO - __main__ - Step 77465: {'lr': 0.00024223217669436757, 'samples': 14873280, 'steps': 77464, 'loss/train': 1.911704182624817} 08/31/2021 03:16:52 - INFO - __main__ - Step 77466: {'lr': 0.0002422268725140218, 'samples': 14873472, 'steps': 77465, 'loss/train': 1.134461522102356} 08/31/2021 03:16:53 - INFO - __main__ - Step 77467: {'lr': 0.0002422215683371785, 'samples': 14873664, 'steps': 77466, 'loss/train': 1.1615996360778809} 08/31/2021 03:16:53 - INFO - __main__ - Step 77468: {'lr': 0.00024221626416384, 'samples': 14873856, 'steps': 77467, 'loss/train': 1.6870346069335938} 08/31/2021 03:16:54 - INFO - __main__ - Step 77469: {'lr': 0.00024221095999400877, 'samples': 14874048, 'steps': 77468, 'loss/train': 0.09807763248682022} 08/31/2021 03:16:54 - INFO - __main__ - Step 77470: {'lr': 0.00024220565582768714, 'samples': 14874240, 'steps': 77469, 'loss/train': 1.11941397190094} 08/31/2021 03:16:55 - INFO - __main__ - Step 77471: {'lr': 0.00024220035166487753, 'samples': 14874432, 'steps': 77470, 'loss/train': 0.7817838788032532} 08/31/2021 03:16:56 - INFO - __main__ - Step 77472: {'lr': 0.00024219504750558232, 'samples': 14874624, 'steps': 77471, 'loss/train': 1.2168241739273071} 08/31/2021 03:16:56 - INFO - __main__ - Step 77473: {'lr': 0.0002421897433498039, 'samples': 14874816, 'steps': 77472, 'loss/train': 1.4426772594451904} 08/31/2021 03:16:57 - INFO - __main__ - Step 77474: {'lr': 0.00024218443919754476, 'samples': 14875008, 'steps': 77473, 'loss/train': 1.0747807025909424} 08/31/2021 03:16:57 - INFO - __main__ - Step 77475: {'lr': 0.00024217913504880713, 'samples': 14875200, 'steps': 77474, 'loss/train': 1.7174524068832397} 08/31/2021 03:16:58 - INFO - __main__ - Step 77476: {'lr': 0.0002421738309035934, 'samples': 14875392, 'steps': 77475, 'loss/train': 1.04594087600708} 08/31/2021 03:16:59 - INFO - __main__ - Step 77477: {'lr': 0.00024216852676190603, 'samples': 14875584, 'steps': 77476, 'loss/train': 1.7741572856903076} 08/31/2021 03:16:59 - INFO - __main__ - Step 77478: {'lr': 0.00024216322262374742, 'samples': 14875776, 'steps': 77477, 'loss/train': 1.4819591045379639} 08/31/2021 03:17:00 - INFO - __main__ - Step 77479: {'lr': 0.00024215791848911994, 'samples': 14875968, 'steps': 77478, 'loss/train': 1.4656355381011963} 08/31/2021 03:17:00 - INFO - __main__ - Step 77480: {'lr': 0.000242152614358026, 'samples': 14876160, 'steps': 77479, 'loss/train': 1.1060738563537598} 08/31/2021 03:17:02 - INFO - __main__ - Step 77481: {'lr': 0.00024214731023046793, 'samples': 14876352, 'steps': 77480, 'loss/train': 1.047223448753357} 08/31/2021 03:17:02 - INFO - __main__ - Step 77482: {'lr': 0.00024214200610644818, 'samples': 14876544, 'steps': 77481, 'loss/train': 1.2493609189987183} 08/31/2021 03:17:02 - INFO - __main__ - Step 77483: {'lr': 0.00024213670198596914, 'samples': 14876736, 'steps': 77482, 'loss/train': 1.5796337127685547} 08/31/2021 03:17:03 - INFO - __main__ - Step 77484: {'lr': 0.00024213139786903316, 'samples': 14876928, 'steps': 77483, 'loss/train': 0.03384197875857353} 08/31/2021 03:17:03 - INFO - __main__ - Step 77485: {'lr': 0.00024212609375564266, 'samples': 14877120, 'steps': 77484, 'loss/train': 0.7422075271606445} 08/31/2021 03:17:03 - INFO - __main__ - Step 77486: {'lr': 0.0002421207896458, 'samples': 14877312, 'steps': 77485, 'loss/train': 1.1905053853988647} 08/31/2021 03:17:05 - INFO - __main__ - Step 77487: {'lr': 0.0002421154855395077, 'samples': 14877504, 'steps': 77486, 'loss/train': 1.7425711154937744} 08/31/2021 03:17:06 - INFO - __main__ - Step 77488: {'lr': 0.00024211018143676795, 'samples': 14877696, 'steps': 77487, 'loss/train': 1.112138271331787} 08/31/2021 03:17:06 - INFO - __main__ - Step 77489: {'lr': 0.00024210487733758324, 'samples': 14877888, 'steps': 77488, 'loss/train': 1.6616685390472412} 08/31/2021 03:17:06 - INFO - __main__ - Step 77490: {'lr': 0.00024209957324195593, 'samples': 14878080, 'steps': 77489, 'loss/train': 0.7101083993911743} 08/31/2021 03:17:07 - INFO - __main__ - Step 77491: {'lr': 0.0002420942691498884, 'samples': 14878272, 'steps': 77490, 'loss/train': 1.3454254865646362} 08/31/2021 03:17:08 - INFO - __main__ - Step 77492: {'lr': 0.00024208896506138313, 'samples': 14878464, 'steps': 77491, 'loss/train': 1.4317203760147095} 08/31/2021 03:17:09 - INFO - __main__ - Step 77493: {'lr': 0.00024208366097644245, 'samples': 14878656, 'steps': 77492, 'loss/train': 2.254281520843506} 08/31/2021 03:17:09 - INFO - __main__ - Step 77494: {'lr': 0.0002420783568950687, 'samples': 14878848, 'steps': 77493, 'loss/train': 1.6610987186431885} 08/31/2021 03:17:10 - INFO - __main__ - Step 77495: {'lr': 0.00024207305281726435, 'samples': 14879040, 'steps': 77494, 'loss/train': 1.3350474834442139} 08/31/2021 03:17:10 - INFO - __main__ - Step 77496: {'lr': 0.00024206774874303174, 'samples': 14879232, 'steps': 77495, 'loss/train': 0.4961455762386322} 08/31/2021 03:17:11 - INFO - __main__ - Step 77497: {'lr': 0.0002420624446723733, 'samples': 14879424, 'steps': 77496, 'loss/train': 0.8435532450675964} 08/31/2021 03:17:12 - INFO - __main__ - Step 77498: {'lr': 0.0002420571406052914, 'samples': 14879616, 'steps': 77497, 'loss/train': 1.218870759010315} 08/31/2021 03:17:12 - INFO - __main__ - Step 77499: {'lr': 0.00024205183654178844, 'samples': 14879808, 'steps': 77498, 'loss/train': 1.1151204109191895} 08/31/2021 03:17:13 - INFO - __main__ - Step 77500: {'lr': 0.00024204653248186678, 'samples': 14880000, 'steps': 77499, 'loss/train': 0.9901559352874756} 08/31/2021 03:17:13 - INFO - __main__ - Step 77501: {'lr': 0.00024204122842552895, 'samples': 14880192, 'steps': 77500, 'loss/train': 1.6733109951019287} 08/31/2021 03:17:13 - INFO - __main__ - Step 77502: {'lr': 0.00024203592437277712, 'samples': 14880384, 'steps': 77501, 'loss/train': 0.9559407830238342} 08/31/2021 03:17:15 - INFO - __main__ - Step 77503: {'lr': 0.00024203062032361375, 'samples': 14880576, 'steps': 77502, 'loss/train': 5.899015426635742} 08/31/2021 03:17:15 - INFO - __main__ - Step 77504: {'lr': 0.0002420253162780413, 'samples': 14880768, 'steps': 77503, 'loss/train': 0.06114602088928223} 08/31/2021 03:17:16 - INFO - __main__ - Step 77505: {'lr': 0.00024202001223606206, 'samples': 14880960, 'steps': 77504, 'loss/train': 1.1676255464553833} 08/31/2021 03:17:16 - INFO - __main__ - Step 77506: {'lr': 0.0002420147081976785, 'samples': 14881152, 'steps': 77505, 'loss/train': 1.8403409719467163} 08/31/2021 03:17:17 - INFO - __main__ - Step 77507: {'lr': 0.00024200940416289302, 'samples': 14881344, 'steps': 77506, 'loss/train': 1.31552255153656} 08/31/2021 03:17:18 - INFO - __main__ - Step 77508: {'lr': 0.00024200410013170795, 'samples': 14881536, 'steps': 77507, 'loss/train': 1.4019404649734497} 08/31/2021 03:17:19 - INFO - __main__ - Step 77509: {'lr': 0.00024199879610412573, 'samples': 14881728, 'steps': 77508, 'loss/train': 1.6413894891738892} 08/31/2021 03:17:19 - INFO - __main__ - Step 77510: {'lr': 0.00024199349208014874, 'samples': 14881920, 'steps': 77509, 'loss/train': 0.5871720314025879} 08/31/2021 03:17:19 - INFO - __main__ - Step 77511: {'lr': 0.0002419881880597793, 'samples': 14882112, 'steps': 77510, 'loss/train': 1.3181774616241455} 08/31/2021 03:17:20 - INFO - __main__ - Step 77512: {'lr': 0.0002419828840430199, 'samples': 14882304, 'steps': 77511, 'loss/train': 1.2990360260009766} 08/31/2021 03:17:22 - INFO - __main__ - Step 77513: {'lr': 0.00024197758002987292, 'samples': 14882496, 'steps': 77512, 'loss/train': 0.5463016033172607} 08/31/2021 03:17:22 - INFO - __main__ - Step 77514: {'lr': 0.00024197227602034077, 'samples': 14882688, 'steps': 77513, 'loss/train': 1.5987577438354492} 08/31/2021 03:17:22 - INFO - __main__ - Step 77515: {'lr': 0.00024196697201442572, 'samples': 14882880, 'steps': 77514, 'loss/train': 1.1630373001098633} 08/31/2021 03:17:23 - INFO - __main__ - Step 77516: {'lr': 0.0002419616680121302, 'samples': 14883072, 'steps': 77515, 'loss/train': 1.1834293603897095} 08/31/2021 03:17:23 - INFO - __main__ - Step 77517: {'lr': 0.00024195636401345662, 'samples': 14883264, 'steps': 77516, 'loss/train': 0.30859360098838806} 08/31/2021 03:17:25 - INFO - __main__ - Step 77518: {'lr': 0.00024195106001840741, 'samples': 14883456, 'steps': 77517, 'loss/train': 1.2333675622940063} 08/31/2021 03:17:26 - INFO - __main__ - Step 77519: {'lr': 0.00024194575602698494, 'samples': 14883648, 'steps': 77518, 'loss/train': 3.262805700302124} 08/31/2021 03:17:26 - INFO - __main__ - Step 77520: {'lr': 0.00024194045203919156, 'samples': 14883840, 'steps': 77519, 'loss/train': 1.2352596521377563} 08/31/2021 03:17:26 - INFO - __main__ - Step 77521: {'lr': 0.0002419351480550297, 'samples': 14884032, 'steps': 77520, 'loss/train': 0.029449163004755974} 08/31/2021 03:17:27 - INFO - __main__ - Step 77522: {'lr': 0.00024192984407450172, 'samples': 14884224, 'steps': 77521, 'loss/train': 1.803120493888855} 08/31/2021 03:17:27 - INFO - __main__ - Step 77523: {'lr': 0.00024192454009761002, 'samples': 14884416, 'steps': 77522, 'loss/train': 1.3410338163375854} 08/31/2021 03:17:29 - INFO - __main__ - Step 77524: {'lr': 0.00024191923612435705, 'samples': 14884608, 'steps': 77523, 'loss/train': 1.8349591493606567} 08/31/2021 03:17:30 - INFO - __main__ - Step 77525: {'lr': 0.00024191393215474517, 'samples': 14884800, 'steps': 77524, 'loss/train': 1.3883785009384155} 08/31/2021 03:17:30 - INFO - __main__ - Step 77526: {'lr': 0.00024190862818877667, 'samples': 14884992, 'steps': 77525, 'loss/train': 1.05735182762146} 08/31/2021 03:17:30 - INFO - __main__ - Step 77527: {'lr': 0.00024190332422645408, 'samples': 14885184, 'steps': 77526, 'loss/train': 1.7263870239257812} 08/31/2021 03:17:31 - INFO - __main__ - Step 77528: {'lr': 0.00024189802026777972, 'samples': 14885376, 'steps': 77527, 'loss/train': 0.35842615365982056} 08/31/2021 03:17:32 - INFO - __main__ - Step 77529: {'lr': 0.00024189271631275594, 'samples': 14885568, 'steps': 77528, 'loss/train': 0.07758883386850357} 08/31/2021 03:17:33 - INFO - __main__ - Step 77530: {'lr': 0.00024188741236138517, 'samples': 14885760, 'steps': 77529, 'loss/train': 1.228602647781372} 08/31/2021 03:17:33 - INFO - __main__ - Step 77531: {'lr': 0.00024188210841366985, 'samples': 14885952, 'steps': 77530, 'loss/train': 1.0978360176086426} 08/31/2021 03:17:33 - INFO - __main__ - Step 77532: {'lr': 0.0002418768044696123, 'samples': 14886144, 'steps': 77531, 'loss/train': 0.7562875151634216} 08/31/2021 03:17:34 - INFO - __main__ - Step 77533: {'lr': 0.00024187150052921495, 'samples': 14886336, 'steps': 77532, 'loss/train': 1.6344821453094482} 08/31/2021 03:17:34 - INFO - __main__ - Step 77534: {'lr': 0.00024186619659248015, 'samples': 14886528, 'steps': 77533, 'loss/train': 0.9700462818145752} 08/31/2021 03:17:36 - INFO - __main__ - Step 77535: {'lr': 0.00024186089265941033, 'samples': 14886720, 'steps': 77534, 'loss/train': 1.0207759141921997} 08/31/2021 03:17:36 - INFO - __main__ - Step 77536: {'lr': 0.00024185558873000794, 'samples': 14886912, 'steps': 77535, 'loss/train': 1.208788275718689} 08/31/2021 03:17:36 - INFO - __main__ - Step 77537: {'lr': 0.0002418502848042752, 'samples': 14887104, 'steps': 77536, 'loss/train': 0.9519508481025696} 08/31/2021 03:17:37 - INFO - __main__ - Step 77538: {'lr': 0.00024184498088221463, 'samples': 14887296, 'steps': 77537, 'loss/train': 1.0882391929626465} 08/31/2021 03:17:37 - INFO - __main__ - Step 77539: {'lr': 0.00024183967696382857, 'samples': 14887488, 'steps': 77538, 'loss/train': 1.3105214834213257} 08/31/2021 03:17:38 - INFO - __main__ - Step 77540: {'lr': 0.00024183437304911942, 'samples': 14887680, 'steps': 77539, 'loss/train': 1.2538152933120728} 08/31/2021 03:17:39 - INFO - __main__ - Step 77541: {'lr': 0.00024182906913808967, 'samples': 14887872, 'steps': 77540, 'loss/train': 1.4556490182876587} 08/31/2021 03:17:39 - INFO - __main__ - Step 77542: {'lr': 0.00024182376523074152, 'samples': 14888064, 'steps': 77541, 'loss/train': 0.8677530884742737} 08/31/2021 03:17:40 - INFO - __main__ - Step 77543: {'lr': 0.00024181846132707746, 'samples': 14888256, 'steps': 77542, 'loss/train': 1.087347388267517} 08/31/2021 03:17:40 - INFO - __main__ - Step 77544: {'lr': 0.00024181315742709988, 'samples': 14888448, 'steps': 77543, 'loss/train': 1.2807241678237915} 08/31/2021 03:17:42 - INFO - __main__ - Step 77545: {'lr': 0.00024180785353081116, 'samples': 14888640, 'steps': 77544, 'loss/train': 1.2490276098251343} 08/31/2021 03:17:42 - INFO - __main__ - Step 77546: {'lr': 0.0002418025496382137, 'samples': 14888832, 'steps': 77545, 'loss/train': 0.08671307563781738} 08/31/2021 03:17:42 - INFO - __main__ - Step 77547: {'lr': 0.00024179724574930998, 'samples': 14889024, 'steps': 77546, 'loss/train': 1.1039695739746094} 08/31/2021 03:17:43 - INFO - __main__ - Step 77548: {'lr': 0.0002417919418641022, 'samples': 14889216, 'steps': 77547, 'loss/train': 1.072619080543518} 08/31/2021 03:17:43 - INFO - __main__ - Step 77549: {'lr': 0.00024178663798259283, 'samples': 14889408, 'steps': 77548, 'loss/train': 1.2395457029342651} 08/31/2021 03:17:45 - INFO - __main__ - Step 77550: {'lr': 0.00024178133410478428, 'samples': 14889600, 'steps': 77549, 'loss/train': 1.2727607488632202} 08/31/2021 03:17:45 - INFO - __main__ - Step 77551: {'lr': 0.00024177603023067896, 'samples': 14889792, 'steps': 77550, 'loss/train': 1.48069167137146} 08/31/2021 03:17:45 - INFO - __main__ - Step 77552: {'lr': 0.00024177072636027923, 'samples': 14889984, 'steps': 77551, 'loss/train': 1.371583342552185} 08/31/2021 03:17:46 - INFO - __main__ - Step 77553: {'lr': 0.00024176542249358747, 'samples': 14890176, 'steps': 77552, 'loss/train': 1.1585510969161987} 08/31/2021 03:17:46 - INFO - __main__ - Step 77554: {'lr': 0.00024176011863060611, 'samples': 14890368, 'steps': 77553, 'loss/train': 1.1145622730255127} 08/31/2021 03:17:48 - INFO - __main__ - Step 77555: {'lr': 0.0002417548147713375, 'samples': 14890560, 'steps': 77554, 'loss/train': 1.536924123764038} 08/31/2021 03:17:48 - INFO - __main__ - Step 77556: {'lr': 0.00024174951091578405, 'samples': 14890752, 'steps': 77555, 'loss/train': 0.9856790900230408} 08/31/2021 03:17:49 - INFO - __main__ - Step 77557: {'lr': 0.0002417442070639481, 'samples': 14890944, 'steps': 77556, 'loss/train': 1.5055783987045288} 08/31/2021 03:17:49 - INFO - __main__ - Step 77558: {'lr': 0.00024173890321583217, 'samples': 14891136, 'steps': 77557, 'loss/train': 0.04502727836370468} 08/31/2021 03:17:49 - INFO - __main__ - Step 77559: {'lr': 0.00024173359937143852, 'samples': 14891328, 'steps': 77558, 'loss/train': 1.8099989891052246} 08/31/2021 03:17:51 - INFO - __main__ - Step 77560: {'lr': 0.00024172829553076956, 'samples': 14891520, 'steps': 77559, 'loss/train': 1.1039096117019653} 08/31/2021 03:17:51 - INFO - __main__ - Step 77561: {'lr': 0.00024172299169382768, 'samples': 14891712, 'steps': 77560, 'loss/train': 0.8884486556053162} 08/31/2021 03:17:52 - INFO - __main__ - Step 77562: {'lr': 0.00024171768786061533, 'samples': 14891904, 'steps': 77561, 'loss/train': 1.6541048288345337} 08/31/2021 03:17:52 - INFO - __main__ - Step 77563: {'lr': 0.00024171238403113485, 'samples': 14892096, 'steps': 77562, 'loss/train': 1.26822829246521} 08/31/2021 03:17:52 - INFO - __main__ - Step 77564: {'lr': 0.00024170708020538866, 'samples': 14892288, 'steps': 77563, 'loss/train': 0.9981086254119873} 08/31/2021 03:17:54 - INFO - __main__ - Step 77565: {'lr': 0.0002417017763833791, 'samples': 14892480, 'steps': 77564, 'loss/train': 1.437580943107605} 08/31/2021 03:17:54 - INFO - __main__ - Step 77566: {'lr': 0.0002416964725651086, 'samples': 14892672, 'steps': 77565, 'loss/train': 1.3417836427688599} 08/31/2021 03:17:55 - INFO - __main__ - Step 77567: {'lr': 0.00024169116875057952, 'samples': 14892864, 'steps': 77566, 'loss/train': 1.001881718635559} 08/31/2021 03:17:55 - INFO - __main__ - Step 77568: {'lr': 0.00024168586493979438, 'samples': 14893056, 'steps': 77567, 'loss/train': 1.451122522354126} 08/31/2021 03:17:55 - INFO - __main__ - Step 77569: {'lr': 0.00024168056113275544, 'samples': 14893248, 'steps': 77568, 'loss/train': 1.5094618797302246} 08/31/2021 03:17:57 - INFO - __main__ - Step 77570: {'lr': 0.00024167525732946506, 'samples': 14893440, 'steps': 77569, 'loss/train': 1.380282998085022} 08/31/2021 03:17:58 - INFO - __main__ - Step 77571: {'lr': 0.00024166995352992567, 'samples': 14893632, 'steps': 77570, 'loss/train': 1.773895025253296} 08/31/2021 03:17:58 - INFO - __main__ - Step 77572: {'lr': 0.00024166464973413964, 'samples': 14893824, 'steps': 77571, 'loss/train': 1.5190043449401855} 08/31/2021 03:17:58 - INFO - __main__ - Step 77573: {'lr': 0.00024165934594210943, 'samples': 14894016, 'steps': 77572, 'loss/train': 0.9432737827301025} 08/31/2021 03:17:59 - INFO - __main__ - Step 77574: {'lr': 0.0002416540421538374, 'samples': 14894208, 'steps': 77573, 'loss/train': 1.0368479490280151} 08/31/2021 03:18:00 - INFO - __main__ - Step 77575: {'lr': 0.00024164873836932587, 'samples': 14894400, 'steps': 77574, 'loss/train': 0.5978325605392456} 08/31/2021 03:18:01 - INFO - __main__ - Step 77576: {'lr': 0.00024164343458857735, 'samples': 14894592, 'steps': 77575, 'loss/train': 1.399742603302002} 08/31/2021 03:18:01 - INFO - __main__ - Step 77577: {'lr': 0.00024163813081159413, 'samples': 14894784, 'steps': 77576, 'loss/train': 1.434954047203064} 08/31/2021 03:18:01 - INFO - __main__ - Step 77578: {'lr': 0.00024163282703837868, 'samples': 14894976, 'steps': 77577, 'loss/train': 1.297186255455017} 08/31/2021 03:18:02 - INFO - __main__ - Step 77579: {'lr': 0.00024162752326893335, 'samples': 14895168, 'steps': 77578, 'loss/train': 1.0806763172149658} 08/31/2021 03:18:03 - INFO - __main__ - Step 77580: {'lr': 0.0002416222195032605, 'samples': 14895360, 'steps': 77579, 'loss/train': 0.9180800318717957} 08/31/2021 03:18:04 - INFO - __main__ - Step 77581: {'lr': 0.00024161691574136265, 'samples': 14895552, 'steps': 77580, 'loss/train': 1.2396937608718872} 08/31/2021 03:18:04 - INFO - __main__ - Step 77582: {'lr': 0.000241611611983242, 'samples': 14895744, 'steps': 77581, 'loss/train': 0.9307558536529541} 08/31/2021 03:18:04 - INFO - __main__ - Step 77583: {'lr': 0.000241606308228901, 'samples': 14895936, 'steps': 77582, 'loss/train': 1.3152029514312744} 08/31/2021 03:18:05 - INFO - __main__ - Step 77584: {'lr': 0.0002416010044783421, 'samples': 14896128, 'steps': 77583, 'loss/train': 0.429175466299057} 08/31/2021 03:18:06 - INFO - __main__ - Step 77585: {'lr': 0.00024159570073156765, 'samples': 14896320, 'steps': 77584, 'loss/train': 2.8081915378570557} 08/31/2021 03:18:07 - INFO - __main__ - Step 77586: {'lr': 0.00024159039698858005, 'samples': 14896512, 'steps': 77585, 'loss/train': 1.6683651208877563} 08/31/2021 03:18:07 - INFO - __main__ - Step 77587: {'lr': 0.00024158509324938168, 'samples': 14896704, 'steps': 77586, 'loss/train': 1.1911615133285522} 08/31/2021 03:18:08 - INFO - __main__ - Step 77588: {'lr': 0.00024157978951397493, 'samples': 14896896, 'steps': 77587, 'loss/train': 1.6932494640350342} 08/31/2021 03:18:08 - INFO - __main__ - Step 77589: {'lr': 0.00024157448578236221, 'samples': 14897088, 'steps': 77588, 'loss/train': 1.2329943180084229} 08/31/2021 03:18:08 - INFO - __main__ - Step 77590: {'lr': 0.00024156918205454588, 'samples': 14897280, 'steps': 77589, 'loss/train': 1.2288386821746826} 08/31/2021 03:18:10 - INFO - __main__ - Step 77591: {'lr': 0.00024156387833052838, 'samples': 14897472, 'steps': 77590, 'loss/train': 1.3905316591262817} 08/31/2021 03:18:10 - INFO - __main__ - Step 77592: {'lr': 0.00024155857461031203, 'samples': 14897664, 'steps': 77591, 'loss/train': 0.9978423714637756} 08/31/2021 03:18:11 - INFO - __main__ - Step 77593: {'lr': 0.00024155327089389928, 'samples': 14897856, 'steps': 77592, 'loss/train': 1.117232084274292} 08/31/2021 03:18:11 - INFO - __main__ - Step 77594: {'lr': 0.0002415479671812925, 'samples': 14898048, 'steps': 77593, 'loss/train': 1.2736064195632935} 08/31/2021 03:18:11 - INFO - __main__ - Step 77595: {'lr': 0.00024154266347249415, 'samples': 14898240, 'steps': 77594, 'loss/train': 1.2158665657043457} 08/31/2021 03:18:13 - INFO - __main__ - Step 77596: {'lr': 0.00024153735976750645, 'samples': 14898432, 'steps': 77595, 'loss/train': 1.3645137548446655} 08/31/2021 03:18:14 - INFO - __main__ - Step 77597: {'lr': 0.00024153205606633192, 'samples': 14898624, 'steps': 77596, 'loss/train': 1.7677783966064453} 08/31/2021 03:18:14 - INFO - __main__ - Step 77598: {'lr': 0.00024152675236897286, 'samples': 14898816, 'steps': 77597, 'loss/train': 0.8345076441764832} 08/31/2021 03:18:14 - INFO - __main__ - Step 77599: {'lr': 0.00024152144867543176, 'samples': 14899008, 'steps': 77598, 'loss/train': 2.1051101684570312} 08/31/2021 03:18:15 - INFO - __main__ - Step 77600: {'lr': 0.00024151614498571096, 'samples': 14899200, 'steps': 77599, 'loss/train': 1.2137736082077026} 08/31/2021 03:18:15 - INFO - __main__ - Step 77601: {'lr': 0.0002415108412998128, 'samples': 14899392, 'steps': 77600, 'loss/train': 1.446505069732666} 08/31/2021 03:18:16 - INFO - __main__ - Step 77602: {'lr': 0.0002415055376177398, 'samples': 14899584, 'steps': 77601, 'loss/train': 1.1744076013565063} 08/31/2021 03:18:17 - INFO - __main__ - Step 77603: {'lr': 0.00024150023393949426, 'samples': 14899776, 'steps': 77602, 'loss/train': 1.382940411567688} 08/31/2021 03:18:17 - INFO - __main__ - Step 77604: {'lr': 0.00024149493026507854, 'samples': 14899968, 'steps': 77603, 'loss/train': 0.35283809900283813} 08/31/2021 03:18:18 - INFO - __main__ - Step 77605: {'lr': 0.00024148962659449507, 'samples': 14900160, 'steps': 77604, 'loss/train': 1.6446348428726196} 08/31/2021 03:18:18 - INFO - __main__ - Step 77606: {'lr': 0.0002414843229277463, 'samples': 14900352, 'steps': 77605, 'loss/train': 1.448546051979065} 08/31/2021 03:18:19 - INFO - __main__ - Step 77607: {'lr': 0.00024147901926483453, 'samples': 14900544, 'steps': 77606, 'loss/train': 1.0131767988204956} 08/31/2021 03:18:20 - INFO - __main__ - Step 77608: {'lr': 0.00024147371560576228, 'samples': 14900736, 'steps': 77607, 'loss/train': 1.0507131814956665} 08/31/2021 03:18:20 - INFO - __main__ - Step 77609: {'lr': 0.00024146841195053176, 'samples': 14900928, 'steps': 77608, 'loss/train': 0.9217656850814819} 08/31/2021 03:18:20 - INFO - __main__ - Step 77610: {'lr': 0.00024146310829914542, 'samples': 14901120, 'steps': 77609, 'loss/train': 1.6613961458206177} 08/31/2021 03:18:21 - INFO - __main__ - Step 77611: {'lr': 0.0002414578046516057, 'samples': 14901312, 'steps': 77610, 'loss/train': 0.13818097114562988} 08/31/2021 03:18:22 - INFO - __main__ - Step 77612: {'lr': 0.00024145250100791494, 'samples': 14901504, 'steps': 77611, 'loss/train': 1.2867705821990967} 08/31/2021 03:18:23 - INFO - __main__ - Step 77613: {'lr': 0.00024144719736807552, 'samples': 14901696, 'steps': 77612, 'loss/train': 0.6764780282974243} 08/31/2021 03:18:23 - INFO - __main__ - Step 77614: {'lr': 0.00024144189373208992, 'samples': 14901888, 'steps': 77613, 'loss/train': 1.3840548992156982} 08/31/2021 03:18:24 - INFO - __main__ - Step 77615: {'lr': 0.00024143659009996044, 'samples': 14902080, 'steps': 77614, 'loss/train': 1.0259292125701904} 08/31/2021 03:18:24 - INFO - __main__ - Step 77616: {'lr': 0.00024143128647168948, 'samples': 14902272, 'steps': 77615, 'loss/train': 1.3918676376342773} 08/31/2021 03:18:26 - INFO - __main__ - Step 77617: {'lr': 0.00024142598284727947, 'samples': 14902464, 'steps': 77616, 'loss/train': 1.3002411127090454} 08/31/2021 03:18:26 - INFO - __main__ - Step 77618: {'lr': 0.0002414206792267328, 'samples': 14902656, 'steps': 77617, 'loss/train': 1.1293482780456543} 08/31/2021 03:18:26 - INFO - __main__ - Step 77619: {'lr': 0.00024141537561005183, 'samples': 14902848, 'steps': 77618, 'loss/train': 1.3547292947769165} 08/31/2021 03:18:27 - INFO - __main__ - Step 77620: {'lr': 0.00024141007199723893, 'samples': 14903040, 'steps': 77619, 'loss/train': 1.6606577634811401} 08/31/2021 03:18:27 - INFO - __main__ - Step 77621: {'lr': 0.00024140476838829656, 'samples': 14903232, 'steps': 77620, 'loss/train': 1.421048641204834} 08/31/2021 03:18:29 - INFO - __main__ - Step 77622: {'lr': 0.00024139946478322717, 'samples': 14903424, 'steps': 77621, 'loss/train': 1.080453634262085} 08/31/2021 03:18:30 - INFO - __main__ - Step 77623: {'lr': 0.00024139416118203292, 'samples': 14903616, 'steps': 77622, 'loss/train': 0.9928252696990967} 08/31/2021 03:18:30 - INFO - __main__ - Step 77624: {'lr': 0.00024138885758471633, 'samples': 14903808, 'steps': 77623, 'loss/train': 1.0033106803894043} 08/31/2021 03:18:30 - INFO - __main__ - Step 77625: {'lr': 0.00024138355399127981, 'samples': 14904000, 'steps': 77624, 'loss/train': 0.198658749461174} 08/31/2021 03:18:31 - INFO - __main__ - Step 77626: {'lr': 0.0002413782504017257, 'samples': 14904192, 'steps': 77625, 'loss/train': 2.3619747161865234} 08/31/2021 03:18:31 - INFO - __main__ - Step 77627: {'lr': 0.00024137294681605642, 'samples': 14904384, 'steps': 77626, 'loss/train': 3.3532443046569824} 08/31/2021 03:18:33 - INFO - __main__ - Step 77628: {'lr': 0.00024136764323427437, 'samples': 14904576, 'steps': 77627, 'loss/train': 1.5212236642837524} 08/31/2021 03:18:33 - INFO - __main__ - Step 77629: {'lr': 0.00024136233965638194, 'samples': 14904768, 'steps': 77628, 'loss/train': 1.0909196138381958} 08/31/2021 03:18:33 - INFO - __main__ - Step 77630: {'lr': 0.00024135703608238148, 'samples': 14904960, 'steps': 77629, 'loss/train': 1.2401103973388672} 08/31/2021 03:18:34 - INFO - __main__ - Step 77631: {'lr': 0.00024135173251227545, 'samples': 14905152, 'steps': 77630, 'loss/train': 1.3426905870437622} 08/31/2021 03:18:34 - INFO - __main__ - Step 77632: {'lr': 0.00024134642894606612, 'samples': 14905344, 'steps': 77631, 'loss/train': 1.5176445245742798} 08/31/2021 03:18:36 - INFO - __main__ - Step 77633: {'lr': 0.000241341125383756, 'samples': 14905536, 'steps': 77632, 'loss/train': 1.3161225318908691} 08/31/2021 03:18:36 - INFO - __main__ - Step 77634: {'lr': 0.00024133582182534743, 'samples': 14905728, 'steps': 77633, 'loss/train': 2.3040595054626465} 08/31/2021 03:18:36 - INFO - __main__ - Step 77635: {'lr': 0.00024133051827084293, 'samples': 14905920, 'steps': 77634, 'loss/train': 1.2905102968215942} 08/31/2021 03:18:37 - INFO - __main__ - Step 77636: {'lr': 0.00024132521472024465, 'samples': 14906112, 'steps': 77635, 'loss/train': 1.3683199882507324} 08/31/2021 03:18:37 - INFO - __main__ - Step 77637: {'lr': 0.0002413199111735551, 'samples': 14906304, 'steps': 77636, 'loss/train': 0.956687331199646} 08/31/2021 03:18:39 - INFO - __main__ - Step 77638: {'lr': 0.00024131460763077665, 'samples': 14906496, 'steps': 77637, 'loss/train': 0.7592107057571411} 08/31/2021 03:18:39 - INFO - __main__ - Step 77639: {'lr': 0.0002413093040919117, 'samples': 14906688, 'steps': 77638, 'loss/train': 1.0972256660461426} 08/31/2021 03:18:40 - INFO - __main__ - Step 77640: {'lr': 0.00024130400055696264, 'samples': 14906880, 'steps': 77639, 'loss/train': 1.1309112310409546} 08/31/2021 03:18:40 - INFO - __main__ - Step 77641: {'lr': 0.00024129869702593188, 'samples': 14907072, 'steps': 77640, 'loss/train': 0.020600588992238045} 08/31/2021 03:18:41 - INFO - __main__ - Step 77642: {'lr': 0.00024129339349882175, 'samples': 14907264, 'steps': 77641, 'loss/train': 0.05386403203010559} 08/31/2021 03:18:41 - INFO - __main__ - Step 77643: {'lr': 0.00024128808997563473, 'samples': 14907456, 'steps': 77642, 'loss/train': 1.158333659172058} 08/31/2021 03:18:41 - INFO - __main__ - Step 77644: {'lr': 0.00024128278645637317, 'samples': 14907648, 'steps': 77643, 'loss/train': 1.4374476671218872} 08/31/2021 03:18:43 - INFO - __main__ - Step 77645: {'lr': 0.00024127748294103943, 'samples': 14907840, 'steps': 77644, 'loss/train': 0.7637182474136353} 08/31/2021 03:18:43 - INFO - __main__ - Step 77646: {'lr': 0.00024127217942963592, 'samples': 14908032, 'steps': 77645, 'loss/train': 1.5280767679214478} 08/31/2021 03:18:43 - INFO - __main__ - Step 77647: {'lr': 0.00024126687592216503, 'samples': 14908224, 'steps': 77646, 'loss/train': 1.3408812284469604} 08/31/2021 03:18:44 - INFO - __main__ - Step 77648: {'lr': 0.00024126157241862925, 'samples': 14908416, 'steps': 77647, 'loss/train': 1.4054726362228394} 08/31/2021 03:18:44 - INFO - __main__ - Step 77649: {'lr': 0.00024125626891903078, 'samples': 14908608, 'steps': 77648, 'loss/train': 1.6197434663772583} 08/31/2021 03:18:46 - INFO - __main__ - Step 77650: {'lr': 0.00024125096542337211, 'samples': 14908800, 'steps': 77649, 'loss/train': 2.4357008934020996} 08/31/2021 03:18:46 - INFO - __main__ - Step 77651: {'lr': 0.0002412456619316556, 'samples': 14908992, 'steps': 77650, 'loss/train': 0.6218215823173523} 08/31/2021 03:18:47 - INFO - __main__ - Step 77652: {'lr': 0.00024124035844388367, 'samples': 14909184, 'steps': 77651, 'loss/train': 1.0966099500656128} 08/31/2021 03:18:47 - INFO - __main__ - Step 77653: {'lr': 0.00024123505496005868, 'samples': 14909376, 'steps': 77652, 'loss/train': 0.8381046056747437} 08/31/2021 03:18:47 - INFO - __main__ - Step 77654: {'lr': 0.00024122975148018304, 'samples': 14909568, 'steps': 77653, 'loss/train': 0.03371996432542801} 08/31/2021 03:18:49 - INFO - __main__ - Step 77655: {'lr': 0.00024122444800425919, 'samples': 14909760, 'steps': 77654, 'loss/train': 1.3743387460708618} 08/31/2021 03:18:49 - INFO - __main__ - Step 77656: {'lr': 0.0002412191445322894, 'samples': 14909952, 'steps': 77655, 'loss/train': 1.2626512050628662} 08/31/2021 03:18:50 - INFO - __main__ - Step 77657: {'lr': 0.0002412138410642762, 'samples': 14910144, 'steps': 77656, 'loss/train': 1.3624553680419922} 08/31/2021 03:18:50 - INFO - __main__ - Step 77658: {'lr': 0.00024120853760022185, 'samples': 14910336, 'steps': 77657, 'loss/train': 1.0739139318466187} 08/31/2021 03:18:50 - INFO - __main__ - Step 77659: {'lr': 0.00024120323414012886, 'samples': 14910528, 'steps': 77658, 'loss/train': 0.8758586049079895} 08/31/2021 03:18:52 - INFO - __main__ - Step 77660: {'lr': 0.0002411979306839995, 'samples': 14910720, 'steps': 77659, 'loss/train': 1.3373827934265137} 08/31/2021 03:18:52 - INFO - __main__ - Step 77661: {'lr': 0.00024119262723183623, 'samples': 14910912, 'steps': 77660, 'loss/train': 1.1911331415176392} 08/31/2021 03:18:53 - INFO - __main__ - Step 77662: {'lr': 0.0002411873237836415, 'samples': 14911104, 'steps': 77661, 'loss/train': 1.4599024057388306} 08/31/2021 03:18:53 - INFO - __main__ - Step 77663: {'lr': 0.00024118202033941756, 'samples': 14911296, 'steps': 77662, 'loss/train': 0.888231635093689} 08/31/2021 03:18:53 - INFO - __main__ - Step 77664: {'lr': 0.00024117671689916683, 'samples': 14911488, 'steps': 77663, 'loss/train': 1.0774821043014526} 08/31/2021 03:18:55 - INFO - __main__ - Step 77665: {'lr': 0.00024117141346289176, 'samples': 14911680, 'steps': 77664, 'loss/train': 1.6832751035690308} 08/31/2021 03:18:55 - INFO - __main__ - Step 77666: {'lr': 0.0002411661100305947, 'samples': 14911872, 'steps': 77665, 'loss/train': 1.3270224332809448} 08/31/2021 03:18:56 - INFO - __main__ - Step 77667: {'lr': 0.0002411608066022781, 'samples': 14912064, 'steps': 77666, 'loss/train': 0.9822673201560974} 08/31/2021 03:18:56 - INFO - __main__ - Step 77668: {'lr': 0.00024115550317794428, 'samples': 14912256, 'steps': 77667, 'loss/train': 0.3614366054534912} 08/31/2021 03:18:56 - INFO - __main__ - Step 77669: {'lr': 0.00024115019975759564, 'samples': 14912448, 'steps': 77668, 'loss/train': 1.349703073501587} 08/31/2021 03:18:58 - INFO - __main__ - Step 77670: {'lr': 0.00024114489634123463, 'samples': 14912640, 'steps': 77669, 'loss/train': 1.2638500928878784} 08/31/2021 03:18:58 - INFO - __main__ - Step 77671: {'lr': 0.00024113959292886356, 'samples': 14912832, 'steps': 77670, 'loss/train': 1.4584680795669556} 08/31/2021 03:18:59 - INFO - __main__ - Step 77672: {'lr': 0.00024113428952048487, 'samples': 14913024, 'steps': 77671, 'loss/train': 0.8443136811256409} 08/31/2021 03:18:59 - INFO - __main__ - Step 77673: {'lr': 0.00024112898611610087, 'samples': 14913216, 'steps': 77672, 'loss/train': 0.08504289388656616} 08/31/2021 03:18:59 - INFO - __main__ - Step 77674: {'lr': 0.00024112368271571406, 'samples': 14913408, 'steps': 77673, 'loss/train': 1.14986252784729} 08/31/2021 03:19:00 - INFO - __main__ - Step 77675: {'lr': 0.00024111837931932683, 'samples': 14913600, 'steps': 77674, 'loss/train': 1.527064323425293} 08/31/2021 03:19:01 - INFO - __main__ - Step 77676: {'lr': 0.00024111307592694146, 'samples': 14913792, 'steps': 77675, 'loss/train': 0.05500689521431923} 08/31/2021 03:19:02 - INFO - __main__ - Step 77677: {'lr': 0.00024110777253856042, 'samples': 14913984, 'steps': 77676, 'loss/train': 0.8123587965965271} 08/31/2021 03:19:02 - INFO - __main__ - Step 77678: {'lr': 0.00024110246915418605, 'samples': 14914176, 'steps': 77677, 'loss/train': 0.7227451801300049} 08/31/2021 03:19:02 - INFO - __main__ - Step 77679: {'lr': 0.0002410971657738208, 'samples': 14914368, 'steps': 77678, 'loss/train': 1.0350474119186401} 08/31/2021 03:19:03 - INFO - __main__ - Step 77680: {'lr': 0.000241091862397467, 'samples': 14914560, 'steps': 77679, 'loss/train': 0.03921257331967354} 08/31/2021 03:19:05 - INFO - __main__ - Step 77681: {'lr': 0.00024108655902512714, 'samples': 14914752, 'steps': 77680, 'loss/train': 1.2952582836151123} 08/31/2021 03:19:05 - INFO - __main__ - Step 77682: {'lr': 0.0002410812556568035, 'samples': 14914944, 'steps': 77681, 'loss/train': 1.1552592515945435} 08/31/2021 03:19:05 - INFO - __main__ - Step 77683: {'lr': 0.00024107595229249848, 'samples': 14915136, 'steps': 77682, 'loss/train': 2.0377097129821777} 08/31/2021 03:19:06 - INFO - __main__ - Step 77684: {'lr': 0.0002410706489322145, 'samples': 14915328, 'steps': 77683, 'loss/train': 0.6400656700134277} 08/31/2021 03:19:06 - INFO - __main__ - Step 77685: {'lr': 0.00024106534557595397, 'samples': 14915520, 'steps': 77684, 'loss/train': 1.9705570936203003} 08/31/2021 03:19:08 - INFO - __main__ - Step 77686: {'lr': 0.00024106004222371926, 'samples': 14915712, 'steps': 77685, 'loss/train': 1.7104251384735107} 08/31/2021 03:19:08 - INFO - __main__ - Step 77687: {'lr': 0.0002410547388755127, 'samples': 14915904, 'steps': 77686, 'loss/train': 0.857676088809967} 08/31/2021 03:19:08 - INFO - __main__ - Step 77688: {'lr': 0.0002410494355313368, 'samples': 14916096, 'steps': 77687, 'loss/train': 1.7693724632263184} 08/31/2021 03:19:09 - INFO - __main__ - Step 77689: {'lr': 0.0002410441321911939, 'samples': 14916288, 'steps': 77688, 'loss/train': 1.046905279159546} 08/31/2021 03:19:09 - INFO - __main__ - Step 77690: {'lr': 0.00024103882885508638, 'samples': 14916480, 'steps': 77689, 'loss/train': 1.3153841495513916} 08/31/2021 03:19:11 - INFO - __main__ - Step 77691: {'lr': 0.00024103352552301658, 'samples': 14916672, 'steps': 77690, 'loss/train': 1.1403096914291382} 08/31/2021 03:19:11 - INFO - __main__ - Step 77692: {'lr': 0.000241028222194987, 'samples': 14916864, 'steps': 77691, 'loss/train': 1.5684545040130615} 08/31/2021 03:19:11 - INFO - __main__ - Step 77693: {'lr': 0.0002410229188709999, 'samples': 14917056, 'steps': 77692, 'loss/train': 1.67573082447052} 08/31/2021 03:19:12 - INFO - __main__ - Step 77694: {'lr': 0.00024101761555105772, 'samples': 14917248, 'steps': 77693, 'loss/train': 0.8068703413009644} 08/31/2021 03:19:12 - INFO - __main__ - Step 77695: {'lr': 0.0002410123122351629, 'samples': 14917440, 'steps': 77694, 'loss/train': 1.7723777294158936} 08/31/2021 03:19:13 - INFO - __main__ - Step 77696: {'lr': 0.0002410070089233178, 'samples': 14917632, 'steps': 77695, 'loss/train': 1.1700401306152344} 08/31/2021 03:19:14 - INFO - __main__ - Step 77697: {'lr': 0.00024100170561552477, 'samples': 14917824, 'steps': 77696, 'loss/train': 1.1547044515609741} 08/31/2021 03:19:14 - INFO - __main__ - Step 77698: {'lr': 0.00024099640231178623, 'samples': 14918016, 'steps': 77697, 'loss/train': 1.5798171758651733} 08/31/2021 03:19:15 - INFO - __main__ - Step 77699: {'lr': 0.00024099109901210458, 'samples': 14918208, 'steps': 77698, 'loss/train': 1.5266836881637573} 08/31/2021 03:19:15 - INFO - __main__ - Step 77700: {'lr': 0.00024098579571648222, 'samples': 14918400, 'steps': 77699, 'loss/train': 1.3693665266036987} 08/31/2021 03:19:17 - INFO - __main__ - Step 77701: {'lr': 0.00024098049242492152, 'samples': 14918592, 'steps': 77700, 'loss/train': 0.8710640072822571} 08/31/2021 03:19:17 - INFO - __main__ - Step 77702: {'lr': 0.0002409751891374249, 'samples': 14918784, 'steps': 77701, 'loss/train': 3.396233320236206} 08/31/2021 03:19:18 - INFO - __main__ - Step 77703: {'lr': 0.00024096988585399474, 'samples': 14918976, 'steps': 77702, 'loss/train': 0.9310327172279358} 08/31/2021 03:19:18 - INFO - __main__ - Step 77704: {'lr': 0.00024096458257463332, 'samples': 14919168, 'steps': 77703, 'loss/train': 1.6419504880905151} 08/31/2021 03:19:18 - INFO - __main__ - Step 77705: {'lr': 0.00024095927929934316, 'samples': 14919360, 'steps': 77704, 'loss/train': 0.4198768436908722} 08/31/2021 03:19:19 - INFO - __main__ - Step 77706: {'lr': 0.00024095397602812662, 'samples': 14919552, 'steps': 77705, 'loss/train': 0.019154056906700134} 08/31/2021 03:19:19 - INFO - __main__ - Step 77707: {'lr': 0.00024094867276098605, 'samples': 14919744, 'steps': 77706, 'loss/train': 1.5250778198242188} 08/31/2021 03:19:21 - INFO - __main__ - Step 77708: {'lr': 0.00024094336949792388, 'samples': 14919936, 'steps': 77707, 'loss/train': 1.3137578964233398} 08/31/2021 03:19:21 - INFO - __main__ - Step 77709: {'lr': 0.00024093806623894248, 'samples': 14920128, 'steps': 77708, 'loss/train': 1.2915968894958496} 08/31/2021 03:19:21 - INFO - __main__ - Step 77710: {'lr': 0.00024093276298404426, 'samples': 14920320, 'steps': 77709, 'loss/train': 1.2513970136642456} 08/31/2021 03:19:22 - INFO - __main__ - Step 77711: {'lr': 0.00024092745973323156, 'samples': 14920512, 'steps': 77710, 'loss/train': 1.427871823310852} 08/31/2021 03:19:22 - INFO - __main__ - Step 77712: {'lr': 0.00024092215648650685, 'samples': 14920704, 'steps': 77711, 'loss/train': 0.34770438075065613} 08/31/2021 03:19:24 - INFO - __main__ - Step 77713: {'lr': 0.00024091685324387246, 'samples': 14920896, 'steps': 77712, 'loss/train': 1.1745061874389648} 08/31/2021 03:19:24 - INFO - __main__ - Step 77714: {'lr': 0.0002409115500053308, 'samples': 14921088, 'steps': 77713, 'loss/train': 1.5254720449447632} 08/31/2021 03:19:24 - INFO - __main__ - Step 77715: {'lr': 0.00024090624677088426, 'samples': 14921280, 'steps': 77714, 'loss/train': 0.5979713797569275} 08/31/2021 03:19:25 - INFO - __main__ - Step 77716: {'lr': 0.0002409009435405353, 'samples': 14921472, 'steps': 77715, 'loss/train': 0.7928200960159302} 08/31/2021 03:19:25 - INFO - __main__ - Step 77717: {'lr': 0.0002408956403142862, 'samples': 14921664, 'steps': 77716, 'loss/train': 0.7485215663909912} 08/31/2021 03:19:27 - INFO - __main__ - Step 77718: {'lr': 0.0002408903370921393, 'samples': 14921856, 'steps': 77717, 'loss/train': 1.3893941640853882} 08/31/2021 03:19:27 - INFO - __main__ - Step 77719: {'lr': 0.00024088503387409714, 'samples': 14922048, 'steps': 77718, 'loss/train': 1.0414252281188965} 08/31/2021 03:19:27 - INFO - __main__ - Step 77720: {'lr': 0.000240879730660162, 'samples': 14922240, 'steps': 77719, 'loss/train': 1.4916530847549438} 08/31/2021 03:19:28 - INFO - __main__ - Step 77721: {'lr': 0.00024087442745033633, 'samples': 14922432, 'steps': 77720, 'loss/train': 0.7813165187835693} 08/31/2021 03:19:28 - INFO - __main__ - Step 77722: {'lr': 0.00024086912424462248, 'samples': 14922624, 'steps': 77721, 'loss/train': 1.2069565057754517} 08/31/2021 03:19:30 - INFO - __main__ - Step 77723: {'lr': 0.00024086382104302286, 'samples': 14922816, 'steps': 77722, 'loss/train': 1.2393752336502075} 08/31/2021 03:19:30 - INFO - __main__ - Step 77724: {'lr': 0.0002408585178455399, 'samples': 14923008, 'steps': 77723, 'loss/train': 0.8789255619049072} 08/31/2021 03:19:30 - INFO - __main__ - Step 77725: {'lr': 0.00024085321465217594, 'samples': 14923200, 'steps': 77724, 'loss/train': 1.191940426826477} 08/31/2021 03:19:31 - INFO - __main__ - Step 77726: {'lr': 0.00024084791146293337, 'samples': 14923392, 'steps': 77725, 'loss/train': 1.5564371347427368} 08/31/2021 03:19:31 - INFO - __main__ - Step 77727: {'lr': 0.0002408426082778146, 'samples': 14923584, 'steps': 77726, 'loss/train': 0.6442737579345703} 08/31/2021 03:19:31 - INFO - __main__ - Step 77728: {'lr': 0.000240837305096822, 'samples': 14923776, 'steps': 77727, 'loss/train': 1.3834025859832764} 08/31/2021 03:19:33 - INFO - __main__ - Step 77729: {'lr': 0.00024083200191995808, 'samples': 14923968, 'steps': 77728, 'loss/train': 1.314473032951355} 08/31/2021 03:19:33 - INFO - __main__ - Step 77730: {'lr': 0.00024082669874722499, 'samples': 14924160, 'steps': 77729, 'loss/train': 0.6920614242553711} 08/31/2021 03:19:34 - INFO - __main__ - Step 77731: {'lr': 0.00024082139557862528, 'samples': 14924352, 'steps': 77730, 'loss/train': 0.4784131944179535} 08/31/2021 03:19:34 - INFO - __main__ - Step 77732: {'lr': 0.00024081609241416126, 'samples': 14924544, 'steps': 77731, 'loss/train': 1.3151524066925049} 08/31/2021 03:19:34 - INFO - __main__ - Step 77733: {'lr': 0.00024081078925383543, 'samples': 14924736, 'steps': 77732, 'loss/train': 0.6011932492256165} 08/31/2021 03:19:36 - INFO - __main__ - Step 77734: {'lr': 0.00024080548609765008, 'samples': 14924928, 'steps': 77733, 'loss/train': 1.5594652891159058} 08/31/2021 03:19:37 - INFO - __main__ - Step 77735: {'lr': 0.00024080018294560766, 'samples': 14925120, 'steps': 77734, 'loss/train': 1.2422679662704468} 08/31/2021 03:19:37 - INFO - __main__ - Step 77736: {'lr': 0.0002407948797977105, 'samples': 14925312, 'steps': 77735, 'loss/train': 0.994287371635437} 08/31/2021 03:19:38 - INFO - __main__ - Step 77737: {'lr': 0.00024078957665396106, 'samples': 14925504, 'steps': 77736, 'loss/train': 1.5748683214187622} 08/31/2021 03:19:38 - INFO - __main__ - Step 77738: {'lr': 0.00024078427351436165, 'samples': 14925696, 'steps': 77737, 'loss/train': 1.7512263059616089} 08/31/2021 03:19:40 - INFO - __main__ - Step 77739: {'lr': 0.00024077897037891476, 'samples': 14925888, 'steps': 77738, 'loss/train': 0.5514330267906189} 08/31/2021 03:19:40 - INFO - __main__ - Step 77740: {'lr': 0.0002407736672476227, 'samples': 14926080, 'steps': 77739, 'loss/train': 1.416450023651123} 08/31/2021 03:19:41 - INFO - __main__ - Step 77741: {'lr': 0.00024076836412048787, 'samples': 14926272, 'steps': 77740, 'loss/train': 1.4825772047042847} 08/31/2021 03:19:41 - INFO - __main__ - Step 77742: {'lr': 0.0002407630609975127, 'samples': 14926464, 'steps': 77741, 'loss/train': 1.6541242599487305} 08/31/2021 03:19:41 - INFO - __main__ - Step 77743: {'lr': 0.00024075775787869963, 'samples': 14926656, 'steps': 77742, 'loss/train': 0.5483870506286621} 08/31/2021 03:19:43 - INFO - __main__ - Step 77744: {'lr': 0.00024075245476405088, 'samples': 14926848, 'steps': 77743, 'loss/train': 1.2544106245040894} 08/31/2021 03:19:43 - INFO - __main__ - Step 77745: {'lr': 0.0002407471516535689, 'samples': 14927040, 'steps': 77744, 'loss/train': 1.5939193964004517} 08/31/2021 03:19:44 - INFO - __main__ - Step 77746: {'lr': 0.00024074184854725616, 'samples': 14927232, 'steps': 77745, 'loss/train': 1.0601184368133545} 08/31/2021 03:19:44 - INFO - __main__ - Step 77747: {'lr': 0.00024073654544511498, 'samples': 14927424, 'steps': 77746, 'loss/train': 1.7070550918579102} 08/31/2021 03:19:44 - INFO - __main__ - Step 77748: {'lr': 0.00024073124234714777, 'samples': 14927616, 'steps': 77747, 'loss/train': 1.280397891998291} 08/31/2021 03:19:46 - INFO - __main__ - Step 77749: {'lr': 0.00024072593925335693, 'samples': 14927808, 'steps': 77748, 'loss/train': 1.1591942310333252} 08/31/2021 03:19:46 - INFO - __main__ - Step 77750: {'lr': 0.00024072063616374482, 'samples': 14928000, 'steps': 77749, 'loss/train': 1.3160321712493896} 08/31/2021 03:19:47 - INFO - __main__ - Step 77751: {'lr': 0.00024071533307831383, 'samples': 14928192, 'steps': 77750, 'loss/train': 1.0399062633514404} 08/31/2021 03:19:47 - INFO - __main__ - Step 77752: {'lr': 0.0002407100299970664, 'samples': 14928384, 'steps': 77751, 'loss/train': 1.0705729722976685} 08/31/2021 03:19:47 - INFO - __main__ - Step 77753: {'lr': 0.00024070472692000488, 'samples': 14928576, 'steps': 77752, 'loss/train': 1.5414495468139648} 08/31/2021 03:19:48 - INFO - __main__ - Step 77754: {'lr': 0.00024069942384713166, 'samples': 14928768, 'steps': 77753, 'loss/train': 1.3226306438446045} 08/31/2021 03:19:49 - INFO - __main__ - Step 77755: {'lr': 0.00024069412077844916, 'samples': 14928960, 'steps': 77754, 'loss/train': 0.9242760539054871} 08/31/2021 03:19:50 - INFO - __main__ - Step 77756: {'lr': 0.00024068881771395983, 'samples': 14929152, 'steps': 77755, 'loss/train': 1.2092434167861938} 08/31/2021 03:19:50 - INFO - __main__ - Step 77757: {'lr': 0.00024068351465366587, 'samples': 14929344, 'steps': 77756, 'loss/train': 1.0494279861450195} 08/31/2021 03:19:50 - INFO - __main__ - Step 77758: {'lr': 0.0002406782115975698, 'samples': 14929536, 'steps': 77757, 'loss/train': 1.3749563694000244} 08/31/2021 03:19:51 - INFO - __main__ - Step 77759: {'lr': 0.00024067290854567396, 'samples': 14929728, 'steps': 77758, 'loss/train': 1.0523236989974976} 08/31/2021 03:19:52 - INFO - __main__ - Step 77760: {'lr': 0.00024066760549798074, 'samples': 14929920, 'steps': 77759, 'loss/train': 1.2408701181411743} 08/31/2021 03:19:53 - INFO - __main__ - Step 77761: {'lr': 0.00024066230245449257, 'samples': 14930112, 'steps': 77760, 'loss/train': 1.1638847589492798} 08/31/2021 03:19:53 - INFO - __main__ - Step 77762: {'lr': 0.00024065699941521184, 'samples': 14930304, 'steps': 77761, 'loss/train': 1.232162356376648} 08/31/2021 03:19:53 - INFO - __main__ - Step 77763: {'lr': 0.0002406516963801409, 'samples': 14930496, 'steps': 77762, 'loss/train': 1.4859026670455933} 08/31/2021 03:19:54 - INFO - __main__ - Step 77764: {'lr': 0.00024064639334928217, 'samples': 14930688, 'steps': 77763, 'loss/train': 1.4511319398880005} 08/31/2021 03:19:56 - INFO - __main__ - Step 77765: {'lr': 0.00024064109032263803, 'samples': 14930880, 'steps': 77764, 'loss/train': 0.9619301557540894} 08/31/2021 03:19:56 - INFO - __main__ - Step 77766: {'lr': 0.00024063578730021087, 'samples': 14931072, 'steps': 77765, 'loss/train': 0.916251003742218} 08/31/2021 03:19:57 - INFO - __main__ - Step 77767: {'lr': 0.0002406304842820031, 'samples': 14931264, 'steps': 77766, 'loss/train': 1.271808385848999} 08/31/2021 03:19:57 - INFO - __main__ - Step 77768: {'lr': 0.00024062518126801707, 'samples': 14931456, 'steps': 77767, 'loss/train': 0.11543063819408417} 08/31/2021 03:19:57 - INFO - __main__ - Step 77769: {'lr': 0.0002406198782582553, 'samples': 14931648, 'steps': 77768, 'loss/train': 0.9901642203330994} 08/31/2021 03:19:59 - INFO - __main__ - Step 77770: {'lr': 0.00024061457525271997, 'samples': 14931840, 'steps': 77769, 'loss/train': 1.1199114322662354} 08/31/2021 03:19:59 - INFO - __main__ - Step 77771: {'lr': 0.00024060927225141355, 'samples': 14932032, 'steps': 77770, 'loss/train': 0.849254846572876} 08/31/2021 03:20:00 - INFO - __main__ - Step 77772: {'lr': 0.00024060396925433845, 'samples': 14932224, 'steps': 77771, 'loss/train': 1.1741913557052612} 08/31/2021 03:20:00 - INFO - __main__ - Step 77773: {'lr': 0.00024059866626149708, 'samples': 14932416, 'steps': 77772, 'loss/train': 0.9340758323669434} 08/31/2021 03:20:00 - INFO - __main__ - Step 77774: {'lr': 0.00024059336327289177, 'samples': 14932608, 'steps': 77773, 'loss/train': 1.510284185409546} 08/31/2021 03:20:02 - INFO - __main__ - Step 77775: {'lr': 0.00024058806028852495, 'samples': 14932800, 'steps': 77774, 'loss/train': 0.9962763786315918} 08/31/2021 03:20:02 - INFO - __main__ - Step 77776: {'lr': 0.00024058275730839905, 'samples': 14932992, 'steps': 77775, 'loss/train': 1.3018850088119507} 08/31/2021 03:20:02 - INFO - __main__ - Step 77777: {'lr': 0.00024057745433251636, 'samples': 14933184, 'steps': 77776, 'loss/train': 0.8348286151885986} 08/31/2021 03:20:03 - INFO - __main__ - Step 77778: {'lr': 0.00024057215136087936, 'samples': 14933376, 'steps': 77777, 'loss/train': 0.7892479300498962} 08/31/2021 03:20:03 - INFO - __main__ - Step 77779: {'lr': 0.0002405668483934904, 'samples': 14933568, 'steps': 77778, 'loss/train': 0.855907142162323} 08/31/2021 03:20:05 - INFO - __main__ - Step 77780: {'lr': 0.00024056154543035182, 'samples': 14933760, 'steps': 77779, 'loss/train': 1.440987467765808} 08/31/2021 03:20:05 - INFO - __main__ - Step 77781: {'lr': 0.00024055624247146612, 'samples': 14933952, 'steps': 77780, 'loss/train': 0.8175982236862183} 08/31/2021 03:20:06 - INFO - __main__ - Step 77782: {'lr': 0.0002405509395168356, 'samples': 14934144, 'steps': 77781, 'loss/train': 0.1619696021080017} 08/31/2021 03:20:06 - INFO - __main__ - Step 77783: {'lr': 0.0002405456365664628, 'samples': 14934336, 'steps': 77782, 'loss/train': 1.1001116037368774} 08/31/2021 03:20:06 - INFO - __main__ - Step 77784: {'lr': 0.0002405403336203499, 'samples': 14934528, 'steps': 77783, 'loss/train': 1.4329850673675537} 08/31/2021 03:20:08 - INFO - __main__ - Step 77785: {'lr': 0.00024053503067849935, 'samples': 14934720, 'steps': 77784, 'loss/train': 1.4008803367614746} 08/31/2021 03:20:09 - INFO - __main__ - Step 77786: {'lr': 0.00024052972774091358, 'samples': 14934912, 'steps': 77785, 'loss/train': 0.9907264709472656} 08/31/2021 03:20:09 - INFO - __main__ - Step 77787: {'lr': 0.000240524424807595, 'samples': 14935104, 'steps': 77786, 'loss/train': 1.1718896627426147} 08/31/2021 03:20:09 - INFO - __main__ - Step 77788: {'lr': 0.00024051912187854593, 'samples': 14935296, 'steps': 77787, 'loss/train': 1.4182677268981934} 08/31/2021 03:20:10 - INFO - __main__ - Step 77789: {'lr': 0.00024051381895376882, 'samples': 14935488, 'steps': 77788, 'loss/train': 1.4799188375473022} 08/31/2021 03:20:10 - INFO - __main__ - Step 77790: {'lr': 0.000240508516033266, 'samples': 14935680, 'steps': 77789, 'loss/train': 1.7640812397003174} 08/31/2021 03:20:12 - INFO - __main__ - Step 77791: {'lr': 0.00024050321311703992, 'samples': 14935872, 'steps': 77790, 'loss/train': 1.0146453380584717} 08/31/2021 03:20:13 - INFO - __main__ - Step 77792: {'lr': 0.00024049791020509296, 'samples': 14936064, 'steps': 77791, 'loss/train': 0.8657428026199341} 08/31/2021 03:20:13 - INFO - __main__ - Step 77793: {'lr': 0.00024049260729742746, 'samples': 14936256, 'steps': 77792, 'loss/train': 1.7761911153793335} 08/31/2021 03:20:13 - INFO - __main__ - Step 77794: {'lr': 0.00024048730439404594, 'samples': 14936448, 'steps': 77793, 'loss/train': 1.402431607246399} 08/31/2021 03:20:14 - INFO - __main__ - Step 77795: {'lr': 0.00024048200149495063, 'samples': 14936640, 'steps': 77794, 'loss/train': 1.4658949375152588} 08/31/2021 03:20:15 - INFO - __main__ - Step 77796: {'lr': 0.000240476698600144, 'samples': 14936832, 'steps': 77795, 'loss/train': 1.2094706296920776} 08/31/2021 03:20:16 - INFO - __main__ - Step 77797: {'lr': 0.00024047139570962842, 'samples': 14937024, 'steps': 77796, 'loss/train': 1.206795334815979} 08/31/2021 03:20:16 - INFO - __main__ - Step 77798: {'lr': 0.00024046609282340627, 'samples': 14937216, 'steps': 77797, 'loss/train': 1.2857482433319092} 08/31/2021 03:20:16 - INFO - __main__ - Step 77799: {'lr': 0.00024046078994147992, 'samples': 14937408, 'steps': 77798, 'loss/train': 0.2165192812681198} 08/31/2021 03:20:17 - INFO - __main__ - Step 77800: {'lr': 0.0002404554870638518, 'samples': 14937600, 'steps': 77799, 'loss/train': 0.8332014679908752} 08/31/2021 03:20:17 - INFO - __main__ - Step 77801: {'lr': 0.0002404501841905243, 'samples': 14937792, 'steps': 77800, 'loss/train': 0.06597322225570679} 08/31/2021 03:20:19 - INFO - __main__ - Step 77802: {'lr': 0.0002404448813214998, 'samples': 14937984, 'steps': 77801, 'loss/train': 1.0125583410263062} 08/31/2021 03:20:19 - INFO - __main__ - Step 77803: {'lr': 0.0002404395784567807, 'samples': 14938176, 'steps': 77802, 'loss/train': 1.2549530267715454} 08/31/2021 03:20:19 - INFO - __main__ - Step 77804: {'lr': 0.00024043427559636936, 'samples': 14938368, 'steps': 77803, 'loss/train': 0.971659779548645} 08/31/2021 03:20:20 - INFO - __main__ - Step 77805: {'lr': 0.00024042897274026827, 'samples': 14938560, 'steps': 77804, 'loss/train': 0.6732304096221924} 08/31/2021 03:20:20 - INFO - __main__ - Step 77806: {'lr': 0.00024042366988847965, 'samples': 14938752, 'steps': 77805, 'loss/train': 0.9823886752128601} 08/31/2021 03:20:22 - INFO - __main__ - Step 77807: {'lr': 0.000240418367041006, 'samples': 14938944, 'steps': 77806, 'loss/train': 1.2126247882843018} 08/31/2021 03:20:22 - INFO - __main__ - Step 77808: {'lr': 0.00024041306419784968, 'samples': 14939136, 'steps': 77807, 'loss/train': 0.5241279602050781} 08/31/2021 03:20:22 - INFO - __main__ - Step 77809: {'lr': 0.00024040776135901304, 'samples': 14939328, 'steps': 77808, 'loss/train': 0.6730923652648926} 08/31/2021 03:20:23 - INFO - __main__ - Step 77810: {'lr': 0.00024040245852449864, 'samples': 14939520, 'steps': 77809, 'loss/train': 0.9587367177009583} 08/31/2021 03:20:23 - INFO - __main__ - Step 77811: {'lr': 0.00024039715569430865, 'samples': 14939712, 'steps': 77810, 'loss/train': 1.2754595279693604} 08/31/2021 03:20:25 - INFO - __main__ - Step 77812: {'lr': 0.00024039185286844555, 'samples': 14939904, 'steps': 77811, 'loss/train': 1.7088863849639893} 08/31/2021 03:20:25 - INFO - __main__ - Step 77813: {'lr': 0.00024038655004691176, 'samples': 14940096, 'steps': 77812, 'loss/train': 0.8513556122779846} 08/31/2021 03:20:25 - INFO - __main__ - Step 77814: {'lr': 0.00024038124722970962, 'samples': 14940288, 'steps': 77813, 'loss/train': 0.03624660521745682} 08/31/2021 03:20:26 - INFO - __main__ - Step 77815: {'lr': 0.00024037594441684155, 'samples': 14940480, 'steps': 77814, 'loss/train': 1.0297582149505615} 08/31/2021 03:20:26 - INFO - __main__ - Step 77816: {'lr': 0.00024037064160831, 'samples': 14940672, 'steps': 77815, 'loss/train': 0.9215832948684692} 08/31/2021 03:20:28 - INFO - __main__ - Step 77817: {'lr': 0.0002403653388041172, 'samples': 14940864, 'steps': 77816, 'loss/train': 0.9669311046600342} 08/31/2021 03:20:28 - INFO - __main__ - Step 77818: {'lr': 0.00024036003600426566, 'samples': 14941056, 'steps': 77817, 'loss/train': 1.0258941650390625} 08/31/2021 03:20:28 - INFO - __main__ - Step 77819: {'lr': 0.00024035473320875773, 'samples': 14941248, 'steps': 77818, 'loss/train': 1.0566062927246094} 08/31/2021 03:20:29 - INFO - __main__ - Step 77820: {'lr': 0.0002403494304175958, 'samples': 14941440, 'steps': 77819, 'loss/train': 1.4034782648086548} 08/31/2021 03:20:29 - INFO - __main__ - Step 77821: {'lr': 0.00024034412763078227, 'samples': 14941632, 'steps': 77820, 'loss/train': 1.2039791345596313} 08/31/2021 03:20:30 - INFO - __main__ - Step 77822: {'lr': 0.00024033882484831955, 'samples': 14941824, 'steps': 77821, 'loss/train': 1.1070570945739746} 08/31/2021 03:20:31 - INFO - __main__ - Step 77823: {'lr': 0.00024033352207021002, 'samples': 14942016, 'steps': 77822, 'loss/train': 0.37593889236450195} 08/31/2021 03:20:31 - INFO - __main__ - Step 77824: {'lr': 0.00024032821929645604, 'samples': 14942208, 'steps': 77823, 'loss/train': 1.7052439451217651} 08/31/2021 03:20:32 - INFO - __main__ - Step 77825: {'lr': 0.00024032291652705998, 'samples': 14942400, 'steps': 77824, 'loss/train': 1.1338833570480347} 08/31/2021 03:20:32 - INFO - __main__ - Step 77826: {'lr': 0.00024031761376202434, 'samples': 14942592, 'steps': 77825, 'loss/train': 1.2823747396469116} 08/31/2021 03:20:32 - INFO - __main__ - Step 77827: {'lr': 0.0002403123110013514, 'samples': 14942784, 'steps': 77826, 'loss/train': 0.049937646836042404} 08/31/2021 03:20:34 - INFO - __main__ - Step 77828: {'lr': 0.00024030700824504355, 'samples': 14942976, 'steps': 77827, 'loss/train': 1.2929514646530151} 08/31/2021 03:20:35 - INFO - __main__ - Step 77829: {'lr': 0.00024030170549310323, 'samples': 14943168, 'steps': 77828, 'loss/train': 1.6077247858047485} 08/31/2021 03:20:35 - INFO - __main__ - Step 77830: {'lr': 0.0002402964027455328, 'samples': 14943360, 'steps': 77829, 'loss/train': 1.117565393447876} 08/31/2021 03:20:35 - INFO - __main__ - Step 77831: {'lr': 0.00024029110000233468, 'samples': 14943552, 'steps': 77830, 'loss/train': 0.19724950194358826} 08/31/2021 03:20:36 - INFO - __main__ - Step 77832: {'lr': 0.00024028579726351123, 'samples': 14943744, 'steps': 77831, 'loss/train': 1.8406020402908325} 08/31/2021 03:20:37 - INFO - __main__ - Step 77833: {'lr': 0.00024028049452906483, 'samples': 14943936, 'steps': 77832, 'loss/train': 1.1182756423950195} 08/31/2021 03:20:38 - INFO - __main__ - Step 77834: {'lr': 0.0002402751917989979, 'samples': 14944128, 'steps': 77833, 'loss/train': 1.6602683067321777} 08/31/2021 03:20:38 - INFO - __main__ - Step 77835: {'lr': 0.00024026988907331281, 'samples': 14944320, 'steps': 77834, 'loss/train': 1.3343160152435303} 08/31/2021 03:20:38 - INFO - __main__ - Step 77836: {'lr': 0.000240264586352012, 'samples': 14944512, 'steps': 77835, 'loss/train': 1.0146650075912476} 08/31/2021 03:20:39 - INFO - __main__ - Step 77837: {'lr': 0.00024025928363509788, 'samples': 14944704, 'steps': 77836, 'loss/train': 1.2145851850509644} 08/31/2021 03:20:40 - INFO - __main__ - Step 77838: {'lr': 0.0002402539809225727, 'samples': 14944896, 'steps': 77837, 'loss/train': 1.751039743423462} 08/31/2021 03:20:41 - INFO - __main__ - Step 77839: {'lr': 0.0002402486782144389, 'samples': 14945088, 'steps': 77838, 'loss/train': 1.1262378692626953} 08/31/2021 03:20:41 - INFO - __main__ - Step 77840: {'lr': 0.0002402433755106989, 'samples': 14945280, 'steps': 77839, 'loss/train': 0.9286971092224121} 08/31/2021 03:20:41 - INFO - __main__ - Step 77841: {'lr': 0.0002402380728113551, 'samples': 14945472, 'steps': 77840, 'loss/train': 0.9033978581428528} 08/31/2021 03:20:42 - INFO - __main__ - Step 77842: {'lr': 0.00024023277011640988, 'samples': 14945664, 'steps': 77841, 'loss/train': 1.2130473852157593} 08/31/2021 03:20:42 - INFO - __main__ - Step 77843: {'lr': 0.0002402274674258656, 'samples': 14945856, 'steps': 77842, 'loss/train': 0.48404887318611145} 08/31/2021 03:20:44 - INFO - __main__ - Step 77844: {'lr': 0.0002402221647397247, 'samples': 14946048, 'steps': 77843, 'loss/train': 1.1796361207962036} 08/31/2021 03:20:45 - INFO - __main__ - Step 77845: {'lr': 0.00024021686205798952, 'samples': 14946240, 'steps': 77844, 'loss/train': 0.39250513911247253} 08/31/2021 03:20:45 - INFO - __main__ - Step 77846: {'lr': 0.00024021155938066247, 'samples': 14946432, 'steps': 77845, 'loss/train': 0.8023046255111694} 08/31/2021 03:20:45 - INFO - __main__ - Step 77847: {'lr': 0.00024020625670774593, 'samples': 14946624, 'steps': 77846, 'loss/train': 1.5551180839538574} 08/31/2021 03:20:46 - INFO - __main__ - Step 77848: {'lr': 0.0002402009540392423, 'samples': 14946816, 'steps': 77847, 'loss/train': 1.4643840789794922} 08/31/2021 03:20:47 - INFO - __main__ - Step 77849: {'lr': 0.000240195651375154, 'samples': 14947008, 'steps': 77848, 'loss/train': 0.8079992532730103} 08/31/2021 03:20:48 - INFO - __main__ - Step 77850: {'lr': 0.00024019034871548348, 'samples': 14947200, 'steps': 77849, 'loss/train': 1.6192142963409424} 08/31/2021 03:20:48 - INFO - __main__ - Step 77851: {'lr': 0.00024018504606023293, 'samples': 14947392, 'steps': 77850, 'loss/train': 1.0861268043518066} 08/31/2021 03:20:49 - INFO - __main__ - Step 77852: {'lr': 0.00024017974340940484, 'samples': 14947584, 'steps': 77851, 'loss/train': 0.46713313460350037} 08/31/2021 03:20:49 - INFO - __main__ - Step 77853: {'lr': 0.0002401744407630016, 'samples': 14947776, 'steps': 77852, 'loss/train': 0.8369266986846924} 08/31/2021 03:20:50 - INFO - __main__ - Step 77854: {'lr': 0.00024016913812102561, 'samples': 14947968, 'steps': 77853, 'loss/train': 1.3132215738296509} 08/31/2021 03:20:51 - INFO - __main__ - Step 77855: {'lr': 0.00024016383548347927, 'samples': 14948160, 'steps': 77854, 'loss/train': 0.9076966047286987} 08/31/2021 03:20:51 - INFO - __main__ - Step 77856: {'lr': 0.00024015853285036496, 'samples': 14948352, 'steps': 77855, 'loss/train': 1.3380354642868042} 08/31/2021 03:20:52 - INFO - __main__ - Step 77857: {'lr': 0.00024015323022168503, 'samples': 14948544, 'steps': 77856, 'loss/train': 1.1792491674423218} 08/31/2021 03:20:52 - INFO - __main__ - Step 77858: {'lr': 0.0002401479275974419, 'samples': 14948736, 'steps': 77857, 'loss/train': 1.0311697721481323} 08/31/2021 03:20:53 - INFO - __main__ - Step 77859: {'lr': 0.000240142624977638, 'samples': 14948928, 'steps': 77858, 'loss/train': 1.1692668199539185} 08/31/2021 03:20:54 - INFO - __main__ - Step 77860: {'lr': 0.00024013732236227568, 'samples': 14949120, 'steps': 77859, 'loss/train': 1.3389122486114502} 08/31/2021 03:20:54 - INFO - __main__ - Step 77861: {'lr': 0.0002401320197513573, 'samples': 14949312, 'steps': 77860, 'loss/train': 1.295764684677124} 08/31/2021 03:20:55 - INFO - __main__ - Step 77862: {'lr': 0.0002401267171448853, 'samples': 14949504, 'steps': 77861, 'loss/train': 0.42836087942123413} 08/31/2021 03:20:55 - INFO - __main__ - Step 77863: {'lr': 0.00024012141454286205, 'samples': 14949696, 'steps': 77862, 'loss/train': 1.4714076519012451} 08/31/2021 03:20:56 - INFO - __main__ - Step 77864: {'lr': 0.00024011611194529005, 'samples': 14949888, 'steps': 77863, 'loss/train': 1.1919503211975098} 08/31/2021 03:20:57 - INFO - __main__ - Step 77865: {'lr': 0.00024011080935217144, 'samples': 14950080, 'steps': 77864, 'loss/train': 1.3180683851242065} 08/31/2021 03:20:57 - INFO - __main__ - Step 77866: {'lr': 0.00024010550676350877, 'samples': 14950272, 'steps': 77865, 'loss/train': 1.3346741199493408} 08/31/2021 03:20:57 - INFO - __main__ - Step 77867: {'lr': 0.00024010020417930439, 'samples': 14950464, 'steps': 77866, 'loss/train': 1.3384536504745483} 08/31/2021 03:20:58 - INFO - __main__ - Step 77868: {'lr': 0.0002400949015995607, 'samples': 14950656, 'steps': 77867, 'loss/train': 0.5810846090316772} 08/31/2021 03:20:59 - INFO - __main__ - Step 77869: {'lr': 0.00024008959902428013, 'samples': 14950848, 'steps': 77868, 'loss/train': 1.4929848909378052} 08/31/2021 03:21:00 - INFO - __main__ - Step 77870: {'lr': 0.00024008429645346502, 'samples': 14951040, 'steps': 77869, 'loss/train': 1.7380350828170776} 08/31/2021 03:21:00 - INFO - __main__ - Step 77871: {'lr': 0.00024007899388711778, 'samples': 14951232, 'steps': 77870, 'loss/train': 1.4175931215286255} 08/31/2021 03:21:00 - INFO - __main__ - Step 77872: {'lr': 0.00024007369132524075, 'samples': 14951424, 'steps': 77871, 'loss/train': 1.5797317028045654} 08/31/2021 03:21:01 - INFO - __main__ - Step 77873: {'lr': 0.0002400683887678364, 'samples': 14951616, 'steps': 77872, 'loss/train': 1.1857773065567017} 08/31/2021 03:21:01 - INFO - __main__ - Step 77874: {'lr': 0.0002400630862149071, 'samples': 14951808, 'steps': 77873, 'loss/train': 0.7593985199928284} 08/31/2021 03:21:03 - INFO - __main__ - Step 77875: {'lr': 0.00024005778366645517, 'samples': 14952000, 'steps': 77874, 'loss/train': 0.5934191346168518} 08/31/2021 03:21:04 - INFO - __main__ - Step 77876: {'lr': 0.00024005248112248307, 'samples': 14952192, 'steps': 77875, 'loss/train': 0.6652305126190186} 08/31/2021 03:21:04 - INFO - __main__ - Step 77877: {'lr': 0.00024004717858299327, 'samples': 14952384, 'steps': 77876, 'loss/train': 1.5686975717544556} 08/31/2021 03:21:05 - INFO - __main__ - Step 77878: {'lr': 0.00024004187604798798, 'samples': 14952576, 'steps': 77877, 'loss/train': 1.8624894618988037} 08/31/2021 03:21:05 - INFO - __main__ - Step 77879: {'lr': 0.00024003657351746963, 'samples': 14952768, 'steps': 77878, 'loss/train': 1.2184804677963257} 08/31/2021 03:21:05 - INFO - __main__ - Step 77880: {'lr': 0.00024003127099144064, 'samples': 14952960, 'steps': 77879, 'loss/train': 2.329838514328003} 08/31/2021 03:21:07 - INFO - __main__ - Step 77881: {'lr': 0.00024002596846990344, 'samples': 14953152, 'steps': 77880, 'loss/train': 1.2716044187545776} 08/31/2021 03:21:07 - INFO - __main__ - Step 77882: {'lr': 0.00024002066595286037, 'samples': 14953344, 'steps': 77881, 'loss/train': 1.224921464920044} 08/31/2021 03:21:08 - INFO - __main__ - Step 77883: {'lr': 0.00024001536344031384, 'samples': 14953536, 'steps': 77882, 'loss/train': 0.8014066219329834} 08/31/2021 03:21:08 - INFO - __main__ - Step 77884: {'lr': 0.0002400100609322662, 'samples': 14953728, 'steps': 77883, 'loss/train': 1.1193493604660034} 08/31/2021 03:21:08 - INFO - __main__ - Step 77885: {'lr': 0.0002400047584287199, 'samples': 14953920, 'steps': 77884, 'loss/train': 1.6549097299575806} 08/31/2021 03:21:10 - INFO - __main__ - Step 77886: {'lr': 0.0002399994559296773, 'samples': 14954112, 'steps': 77885, 'loss/train': 1.6314243078231812} 08/31/2021 03:21:10 - INFO - __main__ - Step 77887: {'lr': 0.0002399941534351408, 'samples': 14954304, 'steps': 77886, 'loss/train': 1.1477867364883423} 08/31/2021 03:21:11 - INFO - __main__ - Step 77888: {'lr': 0.00023998885094511277, 'samples': 14954496, 'steps': 77887, 'loss/train': 1.9728857278823853} 08/31/2021 03:21:11 - INFO - __main__ - Step 77889: {'lr': 0.00023998354845959565, 'samples': 14954688, 'steps': 77888, 'loss/train': 1.3583117723464966} 08/31/2021 03:21:11 - INFO - __main__ - Step 77890: {'lr': 0.00023997824597859184, 'samples': 14954880, 'steps': 77889, 'loss/train': 1.1786503791809082} 08/31/2021 03:21:13 - INFO - __main__ - Step 77891: {'lr': 0.0002399729435021036, 'samples': 14955072, 'steps': 77890, 'loss/train': 1.8164821863174438} 08/31/2021 03:21:13 - INFO - __main__ - Step 77892: {'lr': 0.00023996764103013338, 'samples': 14955264, 'steps': 77891, 'loss/train': 0.9368343353271484} 08/31/2021 03:21:14 - INFO - __main__ - Step 77893: {'lr': 0.00023996233856268356, 'samples': 14955456, 'steps': 77892, 'loss/train': 0.6726595163345337} 08/31/2021 03:21:14 - INFO - __main__ - Step 77894: {'lr': 0.0002399570360997566, 'samples': 14955648, 'steps': 77893, 'loss/train': 0.9502268433570862} 08/31/2021 03:21:14 - INFO - __main__ - Step 77895: {'lr': 0.00023995173364135483, 'samples': 14955840, 'steps': 77894, 'loss/train': 1.0431140661239624} 08/31/2021 03:21:16 - INFO - __main__ - Step 77896: {'lr': 0.00023994643118748065, 'samples': 14956032, 'steps': 77895, 'loss/train': 1.5869054794311523} 08/31/2021 03:21:16 - INFO - __main__ - Step 77897: {'lr': 0.00023994112873813647, 'samples': 14956224, 'steps': 77896, 'loss/train': 1.3649026155471802} 08/31/2021 03:21:17 - INFO - __main__ - Step 77898: {'lr': 0.00023993582629332463, 'samples': 14956416, 'steps': 77897, 'loss/train': 1.047892451286316} 08/31/2021 03:21:17 - INFO - __main__ - Step 77899: {'lr': 0.0002399305238530476, 'samples': 14956608, 'steps': 77898, 'loss/train': 0.7953951358795166} 08/31/2021 03:21:17 - INFO - __main__ - Step 77900: {'lr': 0.00023992522141730768, 'samples': 14956800, 'steps': 77899, 'loss/train': 1.1278892755508423} 08/31/2021 03:21:19 - INFO - __main__ - Step 77901: {'lr': 0.00023991991898610732, 'samples': 14956992, 'steps': 77900, 'loss/train': 1.131091594696045} 08/31/2021 03:21:20 - INFO - __main__ - Step 77902: {'lr': 0.00023991461655944888, 'samples': 14957184, 'steps': 77901, 'loss/train': 1.2785108089447021} 08/31/2021 03:21:20 - INFO - __main__ - Step 77903: {'lr': 0.00023990931413733475, 'samples': 14957376, 'steps': 77902, 'loss/train': 0.2657453715801239} 08/31/2021 03:21:21 - INFO - __main__ - Step 77904: {'lr': 0.00023990401171976745, 'samples': 14957568, 'steps': 77903, 'loss/train': 1.343302607536316} 08/31/2021 03:21:21 - INFO - __main__ - Step 77905: {'lr': 0.00023989870930674913, 'samples': 14957760, 'steps': 77904, 'loss/train': 1.7947415113449097} 08/31/2021 03:21:21 - INFO - __main__ - Step 77906: {'lr': 0.0002398934068982823, 'samples': 14957952, 'steps': 77905, 'loss/train': 1.2544007301330566} 08/31/2021 03:21:23 - INFO - __main__ - Step 77907: {'lr': 0.00023988810449436935, 'samples': 14958144, 'steps': 77906, 'loss/train': 1.5525076389312744} 08/31/2021 03:21:24 - INFO - __main__ - Step 77908: {'lr': 0.00023988280209501266, 'samples': 14958336, 'steps': 77907, 'loss/train': 0.7245932817459106} 08/31/2021 03:21:24 - INFO - __main__ - Step 77909: {'lr': 0.0002398774997002146, 'samples': 14958528, 'steps': 77908, 'loss/train': 1.318676233291626} 08/31/2021 03:21:24 - INFO - __main__ - Step 77910: {'lr': 0.00023987219730997762, 'samples': 14958720, 'steps': 77909, 'loss/train': 1.194677710533142} 08/31/2021 03:21:25 - INFO - __main__ - Step 77911: {'lr': 0.00023986689492430405, 'samples': 14958912, 'steps': 77910, 'loss/train': 0.06701944768428802} 08/31/2021 03:21:26 - INFO - __main__ - Step 77912: {'lr': 0.0002398615925431963, 'samples': 14959104, 'steps': 77911, 'loss/train': 1.4822356700897217} 08/31/2021 03:21:27 - INFO - __main__ - Step 77913: {'lr': 0.00023985629016665678, 'samples': 14959296, 'steps': 77912, 'loss/train': 0.6278196573257446} 08/31/2021 03:21:27 - INFO - __main__ - Step 77914: {'lr': 0.00023985098779468784, 'samples': 14959488, 'steps': 77913, 'loss/train': 1.0646014213562012} 08/31/2021 03:21:28 - INFO - __main__ - Step 77915: {'lr': 0.0002398456854272919, 'samples': 14959680, 'steps': 77914, 'loss/train': 0.9946315288543701} 08/31/2021 03:21:28 - INFO - __main__ - Step 77916: {'lr': 0.00023984038306447132, 'samples': 14959872, 'steps': 77915, 'loss/train': 1.5568042993545532} 08/31/2021 03:21:29 - INFO - __main__ - Step 77917: {'lr': 0.0002398350807062286, 'samples': 14960064, 'steps': 77916, 'loss/train': 2.1888272762298584} 08/31/2021 03:21:30 - INFO - __main__ - Step 77918: {'lr': 0.00023982977835256596, 'samples': 14960256, 'steps': 77917, 'loss/train': 0.8453494310379028} 08/31/2021 03:21:30 - INFO - __main__ - Step 77919: {'lr': 0.00023982447600348587, 'samples': 14960448, 'steps': 77918, 'loss/train': 1.4693866968154907} 08/31/2021 03:21:30 - INFO - __main__ - Step 77920: {'lr': 0.0002398191736589907, 'samples': 14960640, 'steps': 77919, 'loss/train': 1.3539482355117798} 08/31/2021 03:21:31 - INFO - __main__ - Step 77921: {'lr': 0.00023981387131908287, 'samples': 14960832, 'steps': 77920, 'loss/train': 1.3006099462509155} 08/31/2021 03:21:32 - INFO - __main__ - Step 77922: {'lr': 0.00023980856898376472, 'samples': 14961024, 'steps': 77921, 'loss/train': 1.626981258392334} 08/31/2021 03:21:33 - INFO - __main__ - Step 77923: {'lr': 0.0002398032666530387, 'samples': 14961216, 'steps': 77922, 'loss/train': 1.8204632997512817} 08/31/2021 03:21:33 - INFO - __main__ - Step 77924: {'lr': 0.00023979796432690715, 'samples': 14961408, 'steps': 77923, 'loss/train': 0.0525340661406517} 08/31/2021 03:21:34 - INFO - __main__ - Step 77925: {'lr': 0.00023979266200537251, 'samples': 14961600, 'steps': 77924, 'loss/train': 1.3342474699020386} 08/31/2021 03:21:34 - INFO - __main__ - Step 77926: {'lr': 0.0002397873596884371, 'samples': 14961792, 'steps': 77925, 'loss/train': 0.03627219423651695} 08/31/2021 03:21:35 - INFO - __main__ - Step 77927: {'lr': 0.00023978205737610337, 'samples': 14961984, 'steps': 77926, 'loss/train': 1.4332691431045532} 08/31/2021 03:21:36 - INFO - __main__ - Step 77928: {'lr': 0.00023977675506837374, 'samples': 14962176, 'steps': 77927, 'loss/train': 0.793828547000885} 08/31/2021 03:21:36 - INFO - __main__ - Step 77929: {'lr': 0.00023977145276525048, 'samples': 14962368, 'steps': 77928, 'loss/train': 1.2178298234939575} 08/31/2021 03:21:37 - INFO - __main__ - Step 77930: {'lr': 0.00023976615046673606, 'samples': 14962560, 'steps': 77929, 'loss/train': 1.1880697011947632} 08/31/2021 03:21:37 - INFO - __main__ - Step 77931: {'lr': 0.00023976084817283288, 'samples': 14962752, 'steps': 77930, 'loss/train': 0.40523043274879456} 08/31/2021 03:21:37 - INFO - __main__ - Step 77932: {'lr': 0.00023975554588354328, 'samples': 14962944, 'steps': 77931, 'loss/train': 1.305057168006897} 08/31/2021 03:21:39 - INFO - __main__ - Step 77933: {'lr': 0.00023975024359886967, 'samples': 14963136, 'steps': 77932, 'loss/train': 1.9651635885238647} 08/31/2021 03:21:39 - INFO - __main__ - Step 77934: {'lr': 0.00023974494131881447, 'samples': 14963328, 'steps': 77933, 'loss/train': 1.0975724458694458} 08/31/2021 03:21:40 - INFO - __main__ - Step 77935: {'lr': 0.00023973963904338, 'samples': 14963520, 'steps': 77934, 'loss/train': 2.31272029876709} 08/31/2021 03:21:40 - INFO - __main__ - Step 77936: {'lr': 0.0002397343367725687, 'samples': 14963712, 'steps': 77935, 'loss/train': 0.8132384419441223} 08/31/2021 03:21:40 - INFO - __main__ - Step 77937: {'lr': 0.00023972903450638296, 'samples': 14963904, 'steps': 77936, 'loss/train': 1.4287735223770142} 08/31/2021 03:21:42 - INFO - __main__ - Step 77938: {'lr': 0.00023972373224482514, 'samples': 14964096, 'steps': 77937, 'loss/train': 1.6183631420135498} 08/31/2021 03:21:43 - INFO - __main__ - Step 77939: {'lr': 0.0002397184299878977, 'samples': 14964288, 'steps': 77938, 'loss/train': 0.26474729180336} 08/31/2021 03:21:43 - INFO - __main__ - Step 77940: {'lr': 0.00023971312773560295, 'samples': 14964480, 'steps': 77939, 'loss/train': 0.02163197658956051} 08/31/2021 03:21:43 - INFO - __main__ - Step 77941: {'lr': 0.00023970782548794327, 'samples': 14964672, 'steps': 77940, 'loss/train': 1.465639591217041} 08/31/2021 03:21:44 - INFO - __main__ - Step 77942: {'lr': 0.0002397025232449211, 'samples': 14964864, 'steps': 77941, 'loss/train': 0.954969048500061} 08/31/2021 03:21:44 - INFO - __main__ - Step 77943: {'lr': 0.0002396972210065388, 'samples': 14965056, 'steps': 77942, 'loss/train': 1.2764023542404175} 08/31/2021 03:21:46 - INFO - __main__ - Step 77944: {'lr': 0.00023969191877279888, 'samples': 14965248, 'steps': 77943, 'loss/train': 1.6464791297912598} 08/31/2021 03:21:46 - INFO - __main__ - Step 77945: {'lr': 0.0002396866165437035, 'samples': 14965440, 'steps': 77944, 'loss/train': 1.4981534481048584} 08/31/2021 03:21:47 - INFO - __main__ - Step 77946: {'lr': 0.00023968131431925525, 'samples': 14965632, 'steps': 77945, 'loss/train': 1.1777873039245605} 08/31/2021 03:21:47 - INFO - __main__ - Step 77947: {'lr': 0.0002396760120994564, 'samples': 14965824, 'steps': 77946, 'loss/train': 0.698027491569519} 08/31/2021 03:21:48 - INFO - __main__ - Step 77948: {'lr': 0.00023967070988430936, 'samples': 14966016, 'steps': 77947, 'loss/train': 1.371482491493225} 08/31/2021 03:21:49 - INFO - __main__ - Step 77949: {'lr': 0.00023966540767381657, 'samples': 14966208, 'steps': 77948, 'loss/train': 0.09422393143177032} 08/31/2021 03:21:49 - INFO - __main__ - Step 77950: {'lr': 0.0002396601054679804, 'samples': 14966400, 'steps': 77949, 'loss/train': 0.1377686858177185} 08/31/2021 03:21:50 - INFO - __main__ - Step 77951: {'lr': 0.0002396548032668032, 'samples': 14966592, 'steps': 77950, 'loss/train': 1.6164430379867554} 08/31/2021 03:21:50 - INFO - __main__ - Step 77952: {'lr': 0.00023964950107028738, 'samples': 14966784, 'steps': 77951, 'loss/train': 0.7381361722946167} 08/31/2021 03:21:50 - INFO - __main__ - Step 77953: {'lr': 0.00023964419887843535, 'samples': 14966976, 'steps': 77952, 'loss/train': 1.3787076473236084} 08/31/2021 03:21:53 - INFO - __main__ - Step 77954: {'lr': 0.00023963889669124946, 'samples': 14967168, 'steps': 77953, 'loss/train': 0.6509795784950256} 08/31/2021 03:21:53 - INFO - __main__ - Step 77955: {'lr': 0.00023963359450873215, 'samples': 14967360, 'steps': 77954, 'loss/train': 1.7214182615280151} 08/31/2021 03:21:54 - INFO - __main__ - Step 77956: {'lr': 0.00023962829233088577, 'samples': 14967552, 'steps': 77955, 'loss/train': 0.08006685227155685} 08/31/2021 03:21:54 - INFO - __main__ - Step 77957: {'lr': 0.00023962299015771273, 'samples': 14967744, 'steps': 77956, 'loss/train': 1.1783115863800049} 08/31/2021 03:21:54 - INFO - __main__ - Step 77958: {'lr': 0.00023961768798921545, 'samples': 14967936, 'steps': 77957, 'loss/train': 1.4889910221099854} 08/31/2021 03:21:56 - INFO - __main__ - Step 77959: {'lr': 0.00023961238582539623, 'samples': 14968128, 'steps': 77958, 'loss/train': 1.6133959293365479} 08/31/2021 03:21:56 - INFO - __main__ - Step 77960: {'lr': 0.0002396070836662575, 'samples': 14968320, 'steps': 77959, 'loss/train': 1.3883090019226074} 08/31/2021 03:21:57 - INFO - __main__ - Step 77961: {'lr': 0.00023960178151180174, 'samples': 14968512, 'steps': 77960, 'loss/train': 0.9040659666061401} 08/31/2021 03:21:57 - INFO - __main__ - Step 77962: {'lr': 0.00023959647936203118, 'samples': 14968704, 'steps': 77961, 'loss/train': 1.2123147249221802} 08/31/2021 03:21:57 - INFO - __main__ - Step 77963: {'lr': 0.00023959117721694827, 'samples': 14968896, 'steps': 77962, 'loss/train': 1.5466488599777222} 08/31/2021 03:21:59 - INFO - __main__ - Step 77964: {'lr': 0.00023958587507655544, 'samples': 14969088, 'steps': 77963, 'loss/train': 1.2272086143493652} 08/31/2021 03:21:59 - INFO - __main__ - Step 77965: {'lr': 0.00023958057294085506, 'samples': 14969280, 'steps': 77964, 'loss/train': 1.4833447933197021} 08/31/2021 03:22:00 - INFO - __main__ - Step 77966: {'lr': 0.00023957527080984952, 'samples': 14969472, 'steps': 77965, 'loss/train': 0.9950575232505798} 08/31/2021 03:22:00 - INFO - __main__ - Step 77967: {'lr': 0.00023956996868354117, 'samples': 14969664, 'steps': 77966, 'loss/train': 1.127426266670227} 08/31/2021 03:22:00 - INFO - __main__ - Step 77968: {'lr': 0.00023956466656193244, 'samples': 14969856, 'steps': 77967, 'loss/train': 0.6912267208099365} 08/31/2021 03:22:02 - INFO - __main__ - Step 77969: {'lr': 0.0002395593644450257, 'samples': 14970048, 'steps': 77968, 'loss/train': 0.4851001799106598} 08/31/2021 03:22:02 - INFO - __main__ - Step 77970: {'lr': 0.0002395540623328234, 'samples': 14970240, 'steps': 77969, 'loss/train': 0.7620725035667419} 08/31/2021 03:22:03 - INFO - __main__ - Step 77971: {'lr': 0.00023954876022532788, 'samples': 14970432, 'steps': 77970, 'loss/train': 1.8133461475372314} 08/31/2021 03:22:03 - INFO - __main__ - Step 77972: {'lr': 0.00023954345812254155, 'samples': 14970624, 'steps': 77971, 'loss/train': 0.9869385957717896} 08/31/2021 03:22:03 - INFO - __main__ - Step 77973: {'lr': 0.00023953815602446673, 'samples': 14970816, 'steps': 77972, 'loss/train': 0.6806730628013611} 08/31/2021 03:22:04 - INFO - __main__ - Step 77974: {'lr': 0.00023953285393110582, 'samples': 14971008, 'steps': 77973, 'loss/train': 1.3233542442321777} 08/31/2021 03:22:05 - INFO - __main__ - Step 77975: {'lr': 0.00023952755184246128, 'samples': 14971200, 'steps': 77974, 'loss/train': 1.8139675855636597} 08/31/2021 03:22:06 - INFO - __main__ - Step 77976: {'lr': 0.00023952224975853546, 'samples': 14971392, 'steps': 77975, 'loss/train': 1.1366336345672607} 08/31/2021 03:22:06 - INFO - __main__ - Step 77977: {'lr': 0.0002395169476793307, 'samples': 14971584, 'steps': 77976, 'loss/train': 1.1149455308914185} 08/31/2021 03:22:06 - INFO - __main__ - Step 77978: {'lr': 0.0002395116456048495, 'samples': 14971776, 'steps': 77977, 'loss/train': 1.6417547464370728} 08/31/2021 03:22:07 - INFO - __main__ - Step 77979: {'lr': 0.00023950634353509418, 'samples': 14971968, 'steps': 77978, 'loss/train': 0.5699334144592285} 08/31/2021 03:22:08 - INFO - __main__ - Step 77980: {'lr': 0.00023950104147006716, 'samples': 14972160, 'steps': 77979, 'loss/train': 1.119600772857666} 08/31/2021 03:22:09 - INFO - __main__ - Step 77981: {'lr': 0.00023949573940977077, 'samples': 14972352, 'steps': 77980, 'loss/train': 1.2945958375930786} 08/31/2021 03:22:09 - INFO - __main__ - Step 77982: {'lr': 0.00023949043735420746, 'samples': 14972544, 'steps': 77981, 'loss/train': 2.3226287364959717} 08/31/2021 03:22:10 - INFO - __main__ - Step 77983: {'lr': 0.00023948513530337956, 'samples': 14972736, 'steps': 77982, 'loss/train': 1.2031160593032837} 08/31/2021 03:22:10 - INFO - __main__ - Step 77984: {'lr': 0.00023947983325728952, 'samples': 14972928, 'steps': 77983, 'loss/train': 0.8475819230079651} 08/31/2021 03:22:12 - INFO - __main__ - Step 77985: {'lr': 0.00023947453121593985, 'samples': 14973120, 'steps': 77984, 'loss/train': 1.317986249923706} 08/31/2021 03:22:12 - INFO - __main__ - Step 77986: {'lr': 0.00023946922917933265, 'samples': 14973312, 'steps': 77985, 'loss/train': 0.8297820091247559} 08/31/2021 03:22:13 - INFO - __main__ - Step 77987: {'lr': 0.00023946392714747046, 'samples': 14973504, 'steps': 77986, 'loss/train': 0.02095908485352993} 08/31/2021 03:22:13 - INFO - __main__ - Step 77988: {'lr': 0.00023945862512035566, 'samples': 14973696, 'steps': 77987, 'loss/train': 1.2942761182785034} 08/31/2021 03:22:13 - INFO - __main__ - Step 77989: {'lr': 0.00023945332309799062, 'samples': 14973888, 'steps': 77988, 'loss/train': 0.9352356791496277} 08/31/2021 03:22:14 - INFO - __main__ - Step 77990: {'lr': 0.00023944802108037777, 'samples': 14974080, 'steps': 77989, 'loss/train': 1.234724521636963} 08/31/2021 03:22:15 - INFO - __main__ - Step 77991: {'lr': 0.00023944271906751948, 'samples': 14974272, 'steps': 77990, 'loss/train': 0.7456822991371155} 08/31/2021 03:22:16 - INFO - __main__ - Step 77992: {'lr': 0.00023943741705941812, 'samples': 14974464, 'steps': 77991, 'loss/train': 0.9821294546127319} 08/31/2021 03:22:16 - INFO - __main__ - Step 77993: {'lr': 0.0002394321150560761, 'samples': 14974656, 'steps': 77992, 'loss/train': 1.1288982629776} 08/31/2021 03:22:16 - INFO - __main__ - Step 77994: {'lr': 0.00023942681305749584, 'samples': 14974848, 'steps': 77993, 'loss/train': 1.5391757488250732} 08/31/2021 03:22:17 - INFO - __main__ - Step 77995: {'lr': 0.00023942151106367968, 'samples': 14975040, 'steps': 77994, 'loss/train': 1.0901983976364136} 08/31/2021 03:22:18 - INFO - __main__ - Step 77996: {'lr': 0.00023941620907463003, 'samples': 14975232, 'steps': 77995, 'loss/train': 0.8330249786376953} 08/31/2021 03:22:19 - INFO - __main__ - Step 77997: {'lr': 0.00023941090709034924, 'samples': 14975424, 'steps': 77996, 'loss/train': 2.042482614517212} 08/31/2021 03:22:19 - INFO - __main__ - Step 77998: {'lr': 0.00023940560511083987, 'samples': 14975616, 'steps': 77997, 'loss/train': 1.2640705108642578} 08/31/2021 03:22:19 - INFO - __main__ - Step 77999: {'lr': 0.00023940030313610402, 'samples': 14975808, 'steps': 77998, 'loss/train': 1.077365756034851} 08/31/2021 03:22:20 - INFO - __main__ - Step 78000: {'lr': 0.0002393950011661443, 'samples': 14976000, 'steps': 77999, 'loss/train': 1.714869499206543} 08/31/2021 03:22:20 - INFO - __main__ - Step 78001: {'lr': 0.00023938969920096298, 'samples': 14976192, 'steps': 78000, 'loss/train': 1.8008719682693481} 08/31/2021 03:22:22 - INFO - __main__ - Step 78002: {'lr': 0.0002393843972405625, 'samples': 14976384, 'steps': 78001, 'loss/train': 5.483547687530518} 08/31/2021 03:22:22 - INFO - __main__ - Step 78003: {'lr': 0.00023937909528494526, 'samples': 14976576, 'steps': 78002, 'loss/train': 0.9921668767929077} 08/31/2021 03:22:23 - INFO - __main__ - Step 78004: {'lr': 0.00023937379333411363, 'samples': 14976768, 'steps': 78003, 'loss/train': 0.20587150752544403} 08/31/2021 03:22:23 - INFO - __main__ - Step 78005: {'lr': 0.00023936849138807002, 'samples': 14976960, 'steps': 78004, 'loss/train': 1.44935142993927} 08/31/2021 03:22:23 - INFO - __main__ - Step 78006: {'lr': 0.0002393631894468168, 'samples': 14977152, 'steps': 78005, 'loss/train': 0.06394155323505402} 08/31/2021 03:22:24 - INFO - __main__ - Step 78007: {'lr': 0.00023935788751035635, 'samples': 14977344, 'steps': 78006, 'loss/train': 0.2405935823917389} 08/31/2021 03:22:25 - INFO - __main__ - Step 78008: {'lr': 0.00023935258557869105, 'samples': 14977536, 'steps': 78007, 'loss/train': 0.9691539406776428} 08/31/2021 03:22:26 - INFO - __main__ - Step 78009: {'lr': 0.00023934728365182335, 'samples': 14977728, 'steps': 78008, 'loss/train': 1.483738899230957} 08/31/2021 03:22:26 - INFO - __main__ - Step 78010: {'lr': 0.00023934198172975558, 'samples': 14977920, 'steps': 78009, 'loss/train': 1.7091964483261108} 08/31/2021 03:22:27 - INFO - __main__ - Step 78011: {'lr': 0.00023933667981249025, 'samples': 14978112, 'steps': 78010, 'loss/train': 1.4519087076187134} 08/31/2021 03:22:27 - INFO - __main__ - Step 78012: {'lr': 0.00023933137790002956, 'samples': 14978304, 'steps': 78011, 'loss/train': 1.2787415981292725} 08/31/2021 03:22:27 - INFO - __main__ - Step 78013: {'lr': 0.00023932607599237596, 'samples': 14978496, 'steps': 78012, 'loss/train': 1.17646062374115} 08/31/2021 03:22:30 - INFO - __main__ - Step 78014: {'lr': 0.0002393207740895319, 'samples': 14978688, 'steps': 78013, 'loss/train': 0.018346700817346573} 08/31/2021 03:22:30 - INFO - __main__ - Step 78015: {'lr': 0.00023931547219149972, 'samples': 14978880, 'steps': 78014, 'loss/train': 0.13997748494148254} 08/31/2021 03:22:31 - INFO - __main__ - Step 78016: {'lr': 0.0002393101702982818, 'samples': 14979072, 'steps': 78015, 'loss/train': 1.3214596509933472} 08/31/2021 03:22:31 - INFO - __main__ - Step 78017: {'lr': 0.00023930486840988057, 'samples': 14979264, 'steps': 78016, 'loss/train': 1.217126727104187} 08/31/2021 03:22:31 - INFO - __main__ - Step 78018: {'lr': 0.00023929956652629842, 'samples': 14979456, 'steps': 78017, 'loss/train': 1.1536465883255005} 08/31/2021 03:22:32 - INFO - __main__ - Step 78019: {'lr': 0.0002392942646475377, 'samples': 14979648, 'steps': 78018, 'loss/train': 1.340187668800354} 08/31/2021 03:22:33 - INFO - __main__ - Step 78020: {'lr': 0.00023928896277360082, 'samples': 14979840, 'steps': 78019, 'loss/train': 2.5604543685913086} 08/31/2021 03:22:33 - INFO - __main__ - Step 78021: {'lr': 0.00023928366090449017, 'samples': 14980032, 'steps': 78020, 'loss/train': 1.138717532157898} 08/31/2021 03:22:34 - INFO - __main__ - Step 78022: {'lr': 0.00023927835904020815, 'samples': 14980224, 'steps': 78021, 'loss/train': 1.4753901958465576} 08/31/2021 03:22:34 - INFO - __main__ - Step 78023: {'lr': 0.00023927305718075712, 'samples': 14980416, 'steps': 78022, 'loss/train': 1.5488505363464355} 08/31/2021 03:22:34 - INFO - __main__ - Step 78024: {'lr': 0.00023926775532613948, 'samples': 14980608, 'steps': 78023, 'loss/train': 1.0584064722061157} 08/31/2021 03:22:36 - INFO - __main__ - Step 78025: {'lr': 0.00023926245347635774, 'samples': 14980800, 'steps': 78024, 'loss/train': 1.2945095300674438} 08/31/2021 03:22:37 - INFO - __main__ - Step 78026: {'lr': 0.00023925715163141407, 'samples': 14980992, 'steps': 78025, 'loss/train': 1.3901516199111938} 08/31/2021 03:22:37 - INFO - __main__ - Step 78027: {'lr': 0.00023925184979131095, 'samples': 14981184, 'steps': 78026, 'loss/train': 1.6435452699661255} 08/31/2021 03:22:37 - INFO - __main__ - Step 78028: {'lr': 0.0002392465479560508, 'samples': 14981376, 'steps': 78027, 'loss/train': 0.9429013729095459} 08/31/2021 03:22:38 - INFO - __main__ - Step 78029: {'lr': 0.00023924124612563597, 'samples': 14981568, 'steps': 78028, 'loss/train': 0.775149405002594} 08/31/2021 03:22:38 - INFO - __main__ - Step 78030: {'lr': 0.00023923594430006888, 'samples': 14981760, 'steps': 78029, 'loss/train': 0.0448572039604187} 08/31/2021 03:22:40 - INFO - __main__ - Step 78031: {'lr': 0.0002392306424793519, 'samples': 14981952, 'steps': 78030, 'loss/train': 1.0878379344940186} 08/31/2021 03:22:40 - INFO - __main__ - Step 78032: {'lr': 0.00023922534066348744, 'samples': 14982144, 'steps': 78031, 'loss/train': 1.2554070949554443} 08/31/2021 03:22:40 - INFO - __main__ - Step 78033: {'lr': 0.00023922003885247788, 'samples': 14982336, 'steps': 78032, 'loss/train': 1.5353113412857056} 08/31/2021 03:22:41 - INFO - __main__ - Step 78034: {'lr': 0.00023921473704632557, 'samples': 14982528, 'steps': 78033, 'loss/train': 1.6128860712051392} 08/31/2021 03:22:41 - INFO - __main__ - Step 78035: {'lr': 0.00023920943524503293, 'samples': 14982720, 'steps': 78034, 'loss/train': 1.1302837133407593} 08/31/2021 03:22:43 - INFO - __main__ - Step 78036: {'lr': 0.0002392041334486024, 'samples': 14982912, 'steps': 78035, 'loss/train': 1.4218882322311401} 08/31/2021 03:22:43 - INFO - __main__ - Step 78037: {'lr': 0.0002391988316570363, 'samples': 14983104, 'steps': 78036, 'loss/train': 1.402292013168335} 08/31/2021 03:22:44 - INFO - __main__ - Step 78038: {'lr': 0.00023919352987033713, 'samples': 14983296, 'steps': 78037, 'loss/train': 1.292523741722107} 08/31/2021 03:22:44 - INFO - __main__ - Step 78039: {'lr': 0.0002391882280885071, 'samples': 14983488, 'steps': 78038, 'loss/train': 0.7646734714508057} 08/31/2021 03:22:44 - INFO - __main__ - Step 78040: {'lr': 0.00023918292631154868, 'samples': 14983680, 'steps': 78039, 'loss/train': 0.832997739315033} 08/31/2021 03:22:45 - INFO - __main__ - Step 78041: {'lr': 0.00023917762453946426, 'samples': 14983872, 'steps': 78040, 'loss/train': 1.6606872081756592} 08/31/2021 03:22:46 - INFO - __main__ - Step 78042: {'lr': 0.00023917232277225625, 'samples': 14984064, 'steps': 78041, 'loss/train': 1.2501469850540161} 08/31/2021 03:22:46 - INFO - __main__ - Step 78043: {'lr': 0.00023916702100992702, 'samples': 14984256, 'steps': 78042, 'loss/train': 1.395414113998413} 08/31/2021 03:22:47 - INFO - __main__ - Step 78044: {'lr': 0.00023916171925247894, 'samples': 14984448, 'steps': 78043, 'loss/train': 1.3744080066680908} 08/31/2021 03:22:47 - INFO - __main__ - Step 78045: {'lr': 0.00023915641749991447, 'samples': 14984640, 'steps': 78044, 'loss/train': 1.8494824171066284} 08/31/2021 03:22:48 - INFO - __main__ - Step 78046: {'lr': 0.00023915111575223592, 'samples': 14984832, 'steps': 78045, 'loss/train': 0.9881547093391418} 08/31/2021 03:22:49 - INFO - __main__ - Step 78047: {'lr': 0.00023914581400944572, 'samples': 14985024, 'steps': 78046, 'loss/train': 1.5006768703460693} 08/31/2021 03:22:49 - INFO - __main__ - Step 78048: {'lr': 0.00023914051227154622, 'samples': 14985216, 'steps': 78047, 'loss/train': 0.5493180155754089} 08/31/2021 03:22:50 - INFO - __main__ - Step 78049: {'lr': 0.00023913521053853988, 'samples': 14985408, 'steps': 78048, 'loss/train': 0.8928484320640564} 08/31/2021 03:22:50 - INFO - __main__ - Step 78050: {'lr': 0.00023912990881042902, 'samples': 14985600, 'steps': 78049, 'loss/train': 1.092922329902649} 08/31/2021 03:22:50 - INFO - __main__ - Step 78051: {'lr': 0.00023912460708721607, 'samples': 14985792, 'steps': 78050, 'loss/train': 1.508362054824829} 08/31/2021 03:22:52 - INFO - __main__ - Step 78052: {'lr': 0.00023911930536890346, 'samples': 14985984, 'steps': 78051, 'loss/train': 1.3126780986785889} 08/31/2021 03:22:53 - INFO - __main__ - Step 78053: {'lr': 0.00023911400365549348, 'samples': 14986176, 'steps': 78052, 'loss/train': 0.967075765132904} 08/31/2021 03:22:53 - INFO - __main__ - Step 78054: {'lr': 0.00023910870194698855, 'samples': 14986368, 'steps': 78053, 'loss/train': 1.0209757089614868} 08/31/2021 03:22:53 - INFO - __main__ - Step 78055: {'lr': 0.00023910340024339106, 'samples': 14986560, 'steps': 78054, 'loss/train': 1.5774259567260742} 08/31/2021 03:22:54 - INFO - __main__ - Step 78056: {'lr': 0.0002390980985447034, 'samples': 14986752, 'steps': 78055, 'loss/train': 0.8989679217338562} 08/31/2021 03:22:55 - INFO - __main__ - Step 78057: {'lr': 0.000239092796850928, 'samples': 14986944, 'steps': 78056, 'loss/train': 1.1927984952926636} 08/31/2021 03:22:56 - INFO - __main__ - Step 78058: {'lr': 0.0002390874951620672, 'samples': 14987136, 'steps': 78057, 'loss/train': 0.7128387689590454} 08/31/2021 03:22:56 - INFO - __main__ - Step 78059: {'lr': 0.0002390821934781234, 'samples': 14987328, 'steps': 78058, 'loss/train': 1.1130268573760986} 08/31/2021 03:22:56 - INFO - __main__ - Step 78060: {'lr': 0.00023907689179909896, 'samples': 14987520, 'steps': 78059, 'loss/train': 0.7780184149742126} 08/31/2021 03:22:57 - INFO - __main__ - Step 78061: {'lr': 0.00023907159012499636, 'samples': 14987712, 'steps': 78060, 'loss/train': 0.5218228101730347} 08/31/2021 03:22:57 - INFO - __main__ - Step 78062: {'lr': 0.00023906628845581798, 'samples': 14987904, 'steps': 78061, 'loss/train': 0.7931329607963562} 08/31/2021 03:22:58 - INFO - __main__ - Step 78063: {'lr': 0.0002390609867915661, 'samples': 14988096, 'steps': 78062, 'loss/train': 1.0228878259658813} 08/31/2021 03:22:59 - INFO - __main__ - Step 78064: {'lr': 0.00023905568513224316, 'samples': 14988288, 'steps': 78063, 'loss/train': 1.2944387197494507} 08/31/2021 03:22:59 - INFO - __main__ - Step 78065: {'lr': 0.00023905038347785164, 'samples': 14988480, 'steps': 78064, 'loss/train': 1.4539216756820679} 08/31/2021 03:23:00 - INFO - __main__ - Step 78066: {'lr': 0.00023904508182839376, 'samples': 14988672, 'steps': 78065, 'loss/train': 1.343084692955017} 08/31/2021 03:23:00 - INFO - __main__ - Step 78067: {'lr': 0.00023903978018387201, 'samples': 14988864, 'steps': 78066, 'loss/train': 1.7212555408477783} 08/31/2021 03:23:02 - INFO - __main__ - Step 78068: {'lr': 0.00023903447854428878, 'samples': 14989056, 'steps': 78067, 'loss/train': 0.4862534999847412} 08/31/2021 03:23:02 - INFO - __main__ - Step 78069: {'lr': 0.00023902917690964644, 'samples': 14989248, 'steps': 78068, 'loss/train': 1.1577001810073853} 08/31/2021 03:23:03 - INFO - __main__ - Step 78070: {'lr': 0.00023902387527994734, 'samples': 14989440, 'steps': 78069, 'loss/train': 1.7192400693893433} 08/31/2021 03:23:03 - INFO - __main__ - Step 78071: {'lr': 0.00023901857365519398, 'samples': 14989632, 'steps': 78070, 'loss/train': 1.691528558731079} 08/31/2021 03:23:03 - INFO - __main__ - Step 78072: {'lr': 0.00023901327203538865, 'samples': 14989824, 'steps': 78071, 'loss/train': 1.032495379447937} 08/31/2021 03:23:05 - INFO - __main__ - Step 78073: {'lr': 0.00023900797042053382, 'samples': 14990016, 'steps': 78072, 'loss/train': 1.089349627494812} 08/31/2021 03:23:06 - INFO - __main__ - Step 78074: {'lr': 0.00023900266881063175, 'samples': 14990208, 'steps': 78073, 'loss/train': 1.33424711227417} 08/31/2021 03:23:06 - INFO - __main__ - Step 78075: {'lr': 0.00023899736720568496, 'samples': 14990400, 'steps': 78074, 'loss/train': 1.1143406629562378} 08/31/2021 03:23:06 - INFO - __main__ - Step 78076: {'lr': 0.00023899206560569575, 'samples': 14990592, 'steps': 78075, 'loss/train': 1.551127314567566} 08/31/2021 03:23:07 - INFO - __main__ - Step 78077: {'lr': 0.00023898676401066659, 'samples': 14990784, 'steps': 78076, 'loss/train': 1.3733221292495728} 08/31/2021 03:23:08 - INFO - __main__ - Step 78078: {'lr': 0.00023898146242059976, 'samples': 14990976, 'steps': 78077, 'loss/train': 1.0808533430099487} 08/31/2021 03:23:08 - INFO - __main__ - Step 78079: {'lr': 0.00023897616083549782, 'samples': 14991168, 'steps': 78078, 'loss/train': 1.437813639640808} 08/31/2021 03:23:09 - INFO - __main__ - Step 78080: {'lr': 0.00023897085925536296, 'samples': 14991360, 'steps': 78079, 'loss/train': 1.0501651763916016} 08/31/2021 03:23:09 - INFO - __main__ - Step 78081: {'lr': 0.0002389655576801977, 'samples': 14991552, 'steps': 78080, 'loss/train': 1.4764318466186523} 08/31/2021 03:23:10 - INFO - __main__ - Step 78082: {'lr': 0.00023896025611000435, 'samples': 14991744, 'steps': 78081, 'loss/train': 1.1114633083343506} 08/31/2021 03:23:11 - INFO - __main__ - Step 78083: {'lr': 0.00023895495454478535, 'samples': 14991936, 'steps': 78082, 'loss/train': 0.2717806100845337} 08/31/2021 03:23:11 - INFO - __main__ - Step 78084: {'lr': 0.00023894965298454316, 'samples': 14992128, 'steps': 78083, 'loss/train': 0.3739611506462097} 08/31/2021 03:23:12 - INFO - __main__ - Step 78085: {'lr': 0.00023894435142928, 'samples': 14992320, 'steps': 78084, 'loss/train': 1.2329461574554443} 08/31/2021 03:23:12 - INFO - __main__ - Step 78086: {'lr': 0.00023893904987899836, 'samples': 14992512, 'steps': 78085, 'loss/train': 0.8661847710609436} 08/31/2021 03:23:13 - INFO - __main__ - Step 78087: {'lr': 0.0002389337483337006, 'samples': 14992704, 'steps': 78086, 'loss/train': 1.3742958307266235} 08/31/2021 03:23:14 - INFO - __main__ - Step 78088: {'lr': 0.00023892844679338914, 'samples': 14992896, 'steps': 78087, 'loss/train': 0.9815058708190918} 08/31/2021 03:23:14 - INFO - __main__ - Step 78089: {'lr': 0.00023892314525806633, 'samples': 14993088, 'steps': 78088, 'loss/train': 0.5016154050827026} 08/31/2021 03:23:15 - INFO - __main__ - Step 78090: {'lr': 0.0002389178437277346, 'samples': 14993280, 'steps': 78089, 'loss/train': 1.6381609439849854} 08/31/2021 03:23:15 - INFO - __main__ - Step 78091: {'lr': 0.0002389125422023963, 'samples': 14993472, 'steps': 78090, 'loss/train': 1.5457290410995483} 08/31/2021 03:23:15 - INFO - __main__ - Step 78092: {'lr': 0.0002389072406820539, 'samples': 14993664, 'steps': 78091, 'loss/train': 1.9879094362258911} 08/31/2021 03:23:17 - INFO - __main__ - Step 78093: {'lr': 0.00023890193916670967, 'samples': 14993856, 'steps': 78092, 'loss/train': 1.2151267528533936} 08/31/2021 03:23:17 - INFO - __main__ - Step 78094: {'lr': 0.00023889663765636607, 'samples': 14994048, 'steps': 78093, 'loss/train': 1.1658573150634766} 08/31/2021 03:23:18 - INFO - __main__ - Step 78095: {'lr': 0.0002388913361510255, 'samples': 14994240, 'steps': 78094, 'loss/train': 1.032393455505371} 08/31/2021 03:23:18 - INFO - __main__ - Step 78096: {'lr': 0.0002388860346506903, 'samples': 14994432, 'steps': 78095, 'loss/train': 0.47255322337150574} 08/31/2021 03:23:18 - INFO - __main__ - Step 78097: {'lr': 0.00023888073315536285, 'samples': 14994624, 'steps': 78096, 'loss/train': 0.7891989350318909} 08/31/2021 03:23:20 - INFO - __main__ - Step 78098: {'lr': 0.0002388754316650456, 'samples': 14994816, 'steps': 78097, 'loss/train': 1.5375676155090332} 08/31/2021 03:23:20 - INFO - __main__ - Step 78099: {'lr': 0.00023887013017974087, 'samples': 14995008, 'steps': 78098, 'loss/train': 1.1945027112960815} 08/31/2021 03:23:21 - INFO - __main__ - Step 78100: {'lr': 0.00023886482869945114, 'samples': 14995200, 'steps': 78099, 'loss/train': 0.9995191693305969} 08/31/2021 03:23:21 - INFO - __main__ - Step 78101: {'lr': 0.0002388595272241787, 'samples': 14995392, 'steps': 78100, 'loss/train': 0.9763420820236206} 08/31/2021 03:23:21 - INFO - __main__ - Step 78102: {'lr': 0.000238854225753926, 'samples': 14995584, 'steps': 78101, 'loss/train': 1.6873959302902222} 08/31/2021 03:23:22 - INFO - __main__ - Step 78103: {'lr': 0.0002388489242886954, 'samples': 14995776, 'steps': 78102, 'loss/train': 0.62419593334198} 08/31/2021 03:23:23 - INFO - __main__ - Step 78104: {'lr': 0.00023884362282848933, 'samples': 14995968, 'steps': 78103, 'loss/train': 1.6109904050827026} 08/31/2021 03:23:24 - INFO - __main__ - Step 78105: {'lr': 0.00023883832137331016, 'samples': 14996160, 'steps': 78104, 'loss/train': 1.036552906036377} 08/31/2021 03:23:24 - INFO - __main__ - Step 78106: {'lr': 0.00023883301992316038, 'samples': 14996352, 'steps': 78105, 'loss/train': 1.5352978706359863} 08/31/2021 03:23:25 - INFO - __main__ - Step 78107: {'lr': 0.00023882771847804214, 'samples': 14996544, 'steps': 78106, 'loss/train': 1.7011914253234863} 08/31/2021 03:23:25 - INFO - __main__ - Step 78108: {'lr': 0.00023882241703795793, 'samples': 14996736, 'steps': 78107, 'loss/train': 0.9066892266273499} 08/31/2021 03:23:27 - INFO - __main__ - Step 78109: {'lr': 0.0002388171156029102, 'samples': 14996928, 'steps': 78108, 'loss/train': 1.628687858581543} 08/31/2021 03:23:27 - INFO - __main__ - Step 78110: {'lr': 0.00023881181417290129, 'samples': 14997120, 'steps': 78109, 'loss/train': 1.3620561361312866} 08/31/2021 03:23:27 - INFO - __main__ - Step 78111: {'lr': 0.00023880651274793365, 'samples': 14997312, 'steps': 78110, 'loss/train': 0.04513154551386833} 08/31/2021 03:23:28 - INFO - __main__ - Step 78112: {'lr': 0.00023880121132800955, 'samples': 14997504, 'steps': 78111, 'loss/train': 1.4850835800170898} 08/31/2021 03:23:28 - INFO - __main__ - Step 78113: {'lr': 0.0002387959099131315, 'samples': 14997696, 'steps': 78112, 'loss/train': 1.3434672355651855} 08/31/2021 03:23:29 - INFO - __main__ - Step 78114: {'lr': 0.00023879060850330182, 'samples': 14997888, 'steps': 78113, 'loss/train': 1.008583426475525} 08/31/2021 03:23:30 - INFO - __main__ - Step 78115: {'lr': 0.00023878530709852292, 'samples': 14998080, 'steps': 78114, 'loss/train': 0.0439101867377758} 08/31/2021 03:23:30 - INFO - __main__ - Step 78116: {'lr': 0.00023878000569879722, 'samples': 14998272, 'steps': 78115, 'loss/train': 1.5198801755905151} 08/31/2021 03:23:31 - INFO - __main__ - Step 78117: {'lr': 0.00023877470430412704, 'samples': 14998464, 'steps': 78116, 'loss/train': 0.06222032010555267} 08/31/2021 03:23:31 - INFO - __main__ - Step 78118: {'lr': 0.00023876940291451483, 'samples': 14998656, 'steps': 78117, 'loss/train': 0.7931132316589355} 08/31/2021 03:23:33 - INFO - __main__ - Step 78119: {'lr': 0.00023876410152996302, 'samples': 14998848, 'steps': 78118, 'loss/train': 0.5852863788604736} 08/31/2021 03:23:34 - INFO - __main__ - Step 78120: {'lr': 0.00023875880015047387, 'samples': 14999040, 'steps': 78119, 'loss/train': 1.1529507637023926} 08/31/2021 03:23:34 - INFO - __main__ - Step 78121: {'lr': 0.00023875349877604978, 'samples': 14999232, 'steps': 78120, 'loss/train': 1.757617712020874} 08/31/2021 03:23:34 - INFO - __main__ - Step 78122: {'lr': 0.00023874819740669323, 'samples': 14999424, 'steps': 78121, 'loss/train': 1.3352501392364502} 08/31/2021 03:23:35 - INFO - __main__ - Step 78123: {'lr': 0.00023874289604240657, 'samples': 14999616, 'steps': 78122, 'loss/train': 0.8605626821517944} 08/31/2021 03:23:36 - INFO - __main__ - Step 78124: {'lr': 0.00023873759468319216, 'samples': 14999808, 'steps': 78123, 'loss/train': 1.2695465087890625} 08/31/2021 03:23:37 - INFO - __main__ - Step 78125: {'lr': 0.00023873229332905244, 'samples': 15000000, 'steps': 78124, 'loss/train': 0.3137355148792267} 08/31/2021 03:23:37 - INFO - __main__ - Step 78126: {'lr': 0.0002387269919799898, 'samples': 15000192, 'steps': 78125, 'loss/train': 1.4511287212371826} 08/31/2021 03:23:37 - INFO - __main__ - Step 78127: {'lr': 0.00023872169063600653, 'samples': 15000384, 'steps': 78126, 'loss/train': 0.7102576494216919} 08/31/2021 03:23:38 - INFO - __main__ - Step 78128: {'lr': 0.00023871638929710514, 'samples': 15000576, 'steps': 78127, 'loss/train': 1.209079384803772} 08/31/2021 03:23:40 - INFO - __main__ - Step 78129: {'lr': 0.000238711087963288, 'samples': 15000768, 'steps': 78128, 'loss/train': 0.9644319415092468} 08/31/2021 03:23:40 - INFO - __main__ - Step 78130: {'lr': 0.0002387057866345574, 'samples': 15000960, 'steps': 78129, 'loss/train': 1.3859546184539795} 08/31/2021 03:23:40 - INFO - __main__ - Step 78131: {'lr': 0.00023870048531091583, 'samples': 15001152, 'steps': 78130, 'loss/train': 1.3481833934783936} 08/31/2021 03:23:41 - INFO - __main__ - Step 78132: {'lr': 0.00023869518399236578, 'samples': 15001344, 'steps': 78131, 'loss/train': 0.8583213686943054} 08/31/2021 03:23:41 - INFO - __main__ - Step 78133: {'lr': 0.00023868988267890937, 'samples': 15001536, 'steps': 78132, 'loss/train': 0.037621207535266876} 08/31/2021 03:23:41 - INFO - __main__ - Step 78134: {'lr': 0.00023868458137054913, 'samples': 15001728, 'steps': 78133, 'loss/train': 0.9870736598968506} 08/31/2021 03:23:43 - INFO - __main__ - Step 78135: {'lr': 0.00023867928006728745, 'samples': 15001920, 'steps': 78134, 'loss/train': 0.021717345342040062} 08/31/2021 03:23:44 - INFO - __main__ - Step 78136: {'lr': 0.0002386739787691267, 'samples': 15002112, 'steps': 78135, 'loss/train': 1.900551438331604} 08/31/2021 03:23:44 - INFO - __main__ - Step 78137: {'lr': 0.0002386686774760693, 'samples': 15002304, 'steps': 78136, 'loss/train': 0.8265437483787537} 08/31/2021 03:23:44 - INFO - __main__ - Step 78138: {'lr': 0.0002386633761881176, 'samples': 15002496, 'steps': 78137, 'loss/train': 0.7026087045669556} 08/31/2021 03:23:45 - INFO - __main__ - Step 78139: {'lr': 0.00023865807490527403, 'samples': 15002688, 'steps': 78138, 'loss/train': 0.07471966743469238} 08/31/2021 03:23:45 - INFO - __main__ - Step 78140: {'lr': 0.0002386527736275409, 'samples': 15002880, 'steps': 78139, 'loss/train': 1.2651124000549316} 08/31/2021 03:23:47 - INFO - __main__ - Step 78141: {'lr': 0.0002386474723549207, 'samples': 15003072, 'steps': 78140, 'loss/train': 2.9594712257385254} 08/31/2021 03:23:47 - INFO - __main__ - Step 78142: {'lr': 0.00023864217108741578, 'samples': 15003264, 'steps': 78141, 'loss/train': 1.2183043956756592} 08/31/2021 03:23:47 - INFO - __main__ - Step 78143: {'lr': 0.00023863686982502852, 'samples': 15003456, 'steps': 78142, 'loss/train': 1.2930169105529785} 08/31/2021 03:23:48 - INFO - __main__ - Step 78144: {'lr': 0.0002386315685677613, 'samples': 15003648, 'steps': 78143, 'loss/train': 0.8245062232017517} 08/31/2021 03:23:48 - INFO - __main__ - Step 78145: {'lr': 0.0002386262673156165, 'samples': 15003840, 'steps': 78144, 'loss/train': 0.6255727410316467} 08/31/2021 03:23:50 - INFO - __main__ - Step 78146: {'lr': 0.0002386209660685967, 'samples': 15004032, 'steps': 78145, 'loss/train': 0.957021176815033} 08/31/2021 03:23:50 - INFO - __main__ - Step 78147: {'lr': 0.00023861566482670393, 'samples': 15004224, 'steps': 78146, 'loss/train': 1.1142961978912354} 08/31/2021 03:23:50 - INFO - __main__ - Step 78148: {'lr': 0.0002386103635899408, 'samples': 15004416, 'steps': 78147, 'loss/train': 1.4907054901123047} 08/31/2021 03:23:51 - INFO - __main__ - Step 78149: {'lr': 0.00023860506235830967, 'samples': 15004608, 'steps': 78148, 'loss/train': 1.3628923892974854} 08/31/2021 03:23:51 - INFO - __main__ - Step 78150: {'lr': 0.00023859976113181291, 'samples': 15004800, 'steps': 78149, 'loss/train': 1.526921033859253} 08/31/2021 03:23:52 - INFO - __main__ - Step 78151: {'lr': 0.00023859445991045294, 'samples': 15004992, 'steps': 78150, 'loss/train': 1.2931890487670898} 08/31/2021 03:23:53 - INFO - __main__ - Step 78152: {'lr': 0.00023858915869423214, 'samples': 15005184, 'steps': 78151, 'loss/train': 0.6638664603233337} 08/31/2021 03:23:53 - INFO - __main__ - Step 78153: {'lr': 0.00023858385748315287, 'samples': 15005376, 'steps': 78152, 'loss/train': 1.898189663887024} 08/31/2021 03:23:54 - INFO - __main__ - Step 78154: {'lr': 0.00023857855627721752, 'samples': 15005568, 'steps': 78153, 'loss/train': 1.38334059715271} 08/31/2021 03:23:54 - INFO - __main__ - Step 78155: {'lr': 0.00023857325507642852, 'samples': 15005760, 'steps': 78154, 'loss/train': 0.30661076307296753} 08/31/2021 03:23:55 - INFO - __main__ - Step 78156: {'lr': 0.00023856795388078824, 'samples': 15005952, 'steps': 78155, 'loss/train': 1.1373523473739624} 08/31/2021 03:23:56 - INFO - __main__ - Step 78157: {'lr': 0.00023856265269029902, 'samples': 15006144, 'steps': 78156, 'loss/train': 1.6207705736160278} 08/31/2021 03:23:56 - INFO - __main__ - Step 78158: {'lr': 0.00023855735150496335, 'samples': 15006336, 'steps': 78157, 'loss/train': 1.417527675628662} 08/31/2021 03:23:57 - INFO - __main__ - Step 78159: {'lr': 0.00023855205032478365, 'samples': 15006528, 'steps': 78158, 'loss/train': 1.5328247547149658} 08/31/2021 03:23:57 - INFO - __main__ - Step 78160: {'lr': 0.0002385467491497621, 'samples': 15006720, 'steps': 78159, 'loss/train': 1.140684962272644} 08/31/2021 03:23:59 - INFO - __main__ - Step 78161: {'lr': 0.0002385414479799012, 'samples': 15006912, 'steps': 78160, 'loss/train': 0.9420663714408875} 08/31/2021 03:23:59 - INFO - __main__ - Step 78162: {'lr': 0.00023853614681520338, 'samples': 15007104, 'steps': 78161, 'loss/train': 1.1336908340454102} 08/31/2021 03:23:59 - INFO - __main__ - Step 78163: {'lr': 0.00023853084565567099, 'samples': 15007296, 'steps': 78162, 'loss/train': 1.463179349899292} 08/31/2021 03:24:00 - INFO - __main__ - Step 78164: {'lr': 0.00023852554450130639, 'samples': 15007488, 'steps': 78163, 'loss/train': 1.1705166101455688} 08/31/2021 03:24:00 - INFO - __main__ - Step 78165: {'lr': 0.00023852024335211202, 'samples': 15007680, 'steps': 78164, 'loss/train': 0.9330881834030151} 08/31/2021 03:24:01 - INFO - __main__ - Step 78166: {'lr': 0.00023851494220809025, 'samples': 15007872, 'steps': 78165, 'loss/train': 1.7823864221572876} 08/31/2021 03:24:02 - INFO - __main__ - Step 78167: {'lr': 0.00023850964106924348, 'samples': 15008064, 'steps': 78166, 'loss/train': 1.7427414655685425} 08/31/2021 03:24:02 - INFO - __main__ - Step 78168: {'lr': 0.00023850433993557408, 'samples': 15008256, 'steps': 78167, 'loss/train': 1.124691367149353} 08/31/2021 03:24:03 - INFO - __main__ - Step 78169: {'lr': 0.00023849903880708445, 'samples': 15008448, 'steps': 78168, 'loss/train': 0.9794753193855286} 08/31/2021 03:24:03 - INFO - __main__ - Step 78170: {'lr': 0.00023849373768377696, 'samples': 15008640, 'steps': 78169, 'loss/train': 1.2311532497406006} 08/31/2021 03:24:03 - INFO - __main__ - Step 78171: {'lr': 0.00023848843656565407, 'samples': 15008832, 'steps': 78170, 'loss/train': 1.4158234596252441} 08/31/2021 03:24:05 - INFO - __main__ - Step 78172: {'lr': 0.00023848313545271805, 'samples': 15009024, 'steps': 78171, 'loss/train': 1.5148398876190186} 08/31/2021 03:24:05 - INFO - __main__ - Step 78173: {'lr': 0.00023847783434497146, 'samples': 15009216, 'steps': 78172, 'loss/train': 1.0394175052642822} 08/31/2021 03:24:06 - INFO - __main__ - Step 78174: {'lr': 0.00023847253324241652, 'samples': 15009408, 'steps': 78173, 'loss/train': 1.3624422550201416} 08/31/2021 03:24:06 - INFO - __main__ - Step 78175: {'lr': 0.00023846723214505564, 'samples': 15009600, 'steps': 78174, 'loss/train': 0.5411625504493713} 08/31/2021 03:24:06 - INFO - __main__ - Step 78176: {'lr': 0.00023846193105289126, 'samples': 15009792, 'steps': 78175, 'loss/train': 1.2645344734191895} 08/31/2021 03:24:09 - INFO - __main__ - Step 78177: {'lr': 0.00023845662996592576, 'samples': 15009984, 'steps': 78176, 'loss/train': 1.5853701829910278} 08/31/2021 03:24:09 - INFO - __main__ - Step 78178: {'lr': 0.0002384513288841615, 'samples': 15010176, 'steps': 78177, 'loss/train': 1.2138772010803223} 08/31/2021 03:24:09 - INFO - __main__ - Step 78179: {'lr': 0.00023844602780760094, 'samples': 15010368, 'steps': 78178, 'loss/train': 0.03522689267992973} 08/31/2021 03:24:10 - INFO - __main__ - Step 78180: {'lr': 0.0002384407267362464, 'samples': 15010560, 'steps': 78179, 'loss/train': 1.1448805332183838} 08/31/2021 03:24:10 - INFO - __main__ - Step 78181: {'lr': 0.00023843542567010027, 'samples': 15010752, 'steps': 78180, 'loss/train': 1.2667977809906006} 08/31/2021 03:24:11 - INFO - __main__ - Step 78182: {'lr': 0.00023843012460916498, 'samples': 15010944, 'steps': 78181, 'loss/train': 0.6349464058876038} 08/31/2021 03:24:12 - INFO - __main__ - Step 78183: {'lr': 0.00023842482355344288, 'samples': 15011136, 'steps': 78182, 'loss/train': 0.8692459464073181} 08/31/2021 03:24:12 - INFO - __main__ - Step 78184: {'lr': 0.0002384195225029364, 'samples': 15011328, 'steps': 78183, 'loss/train': 1.7766664028167725} 08/31/2021 03:24:13 - INFO - __main__ - Step 78185: {'lr': 0.00023841422145764787, 'samples': 15011520, 'steps': 78184, 'loss/train': 1.7524352073669434} 08/31/2021 03:24:13 - INFO - __main__ - Step 78186: {'lr': 0.00023840892041757987, 'samples': 15011712, 'steps': 78185, 'loss/train': 1.4564616680145264} 08/31/2021 03:24:14 - INFO - __main__ - Step 78187: {'lr': 0.00023840361938273446, 'samples': 15011904, 'steps': 78186, 'loss/train': 1.2878613471984863} 08/31/2021 03:24:15 - INFO - __main__ - Step 78188: {'lr': 0.00023839831835311426, 'samples': 15012096, 'steps': 78187, 'loss/train': 1.4182325601577759} 08/31/2021 03:24:15 - INFO - __main__ - Step 78189: {'lr': 0.00023839301732872157, 'samples': 15012288, 'steps': 78188, 'loss/train': 0.9624155759811401} 08/31/2021 03:24:16 - INFO - __main__ - Step 78190: {'lr': 0.0002383877163095588, 'samples': 15012480, 'steps': 78189, 'loss/train': 1.0745835304260254} 08/31/2021 03:24:16 - INFO - __main__ - Step 78191: {'lr': 0.00023838241529562838, 'samples': 15012672, 'steps': 78190, 'loss/train': 1.4624316692352295} 08/31/2021 03:24:16 - INFO - __main__ - Step 78192: {'lr': 0.00023837711428693263, 'samples': 15012864, 'steps': 78191, 'loss/train': 0.8133578896522522} 08/31/2021 03:24:18 - INFO - __main__ - Step 78193: {'lr': 0.00023837181328347398, 'samples': 15013056, 'steps': 78192, 'loss/train': 1.359044075012207} 08/31/2021 03:24:18 - INFO - __main__ - Step 78194: {'lr': 0.00023836651228525483, 'samples': 15013248, 'steps': 78193, 'loss/train': 1.256970763206482} 08/31/2021 03:24:19 - INFO - __main__ - Step 78195: {'lr': 0.00023836121129227754, 'samples': 15013440, 'steps': 78194, 'loss/train': 1.1159769296646118} 08/31/2021 03:24:19 - INFO - __main__ - Step 78196: {'lr': 0.0002383559103045445, 'samples': 15013632, 'steps': 78195, 'loss/train': 1.5364844799041748} 08/31/2021 03:24:19 - INFO - __main__ - Step 78197: {'lr': 0.00023835060932205816, 'samples': 15013824, 'steps': 78196, 'loss/train': 0.9588075876235962} 08/31/2021 03:24:21 - INFO - __main__ - Step 78198: {'lr': 0.00023834530834482078, 'samples': 15014016, 'steps': 78197, 'loss/train': 1.4844014644622803} 08/31/2021 03:24:22 - INFO - __main__ - Step 78199: {'lr': 0.00023834000737283487, 'samples': 15014208, 'steps': 78198, 'loss/train': 0.08144596964120865} 08/31/2021 03:24:22 - INFO - __main__ - Step 78200: {'lr': 0.00023833470640610281, 'samples': 15014400, 'steps': 78199, 'loss/train': 0.7676875591278076} 08/31/2021 03:24:22 - INFO - __main__ - Step 78201: {'lr': 0.0002383294054446269, 'samples': 15014592, 'steps': 78200, 'loss/train': 0.8760657906532288} 08/31/2021 03:24:23 - INFO - __main__ - Step 78202: {'lr': 0.0002383241044884096, 'samples': 15014784, 'steps': 78201, 'loss/train': 1.0638597011566162} 08/31/2021 03:24:25 - INFO - __main__ - Step 78203: {'lr': 0.00023831880353745321, 'samples': 15014976, 'steps': 78202, 'loss/train': 1.2923773527145386} 08/31/2021 03:24:25 - INFO - __main__ - Step 78204: {'lr': 0.00023831350259176024, 'samples': 15015168, 'steps': 78203, 'loss/train': 1.2592484951019287} 08/31/2021 03:24:25 - INFO - __main__ - Step 78205: {'lr': 0.000238308201651333, 'samples': 15015360, 'steps': 78204, 'loss/train': 1.1748549938201904} 08/31/2021 03:24:26 - INFO - __main__ - Step 78206: {'lr': 0.00023830290071617395, 'samples': 15015552, 'steps': 78205, 'loss/train': 1.4711549282073975} 08/31/2021 03:24:26 - INFO - __main__ - Step 78207: {'lr': 0.0002382975997862854, 'samples': 15015744, 'steps': 78206, 'loss/train': 1.8696190118789673} 08/31/2021 03:24:28 - INFO - __main__ - Step 78208: {'lr': 0.00023829229886166984, 'samples': 15015936, 'steps': 78207, 'loss/train': 0.04062221199274063} 08/31/2021 03:24:28 - INFO - __main__ - Step 78209: {'lr': 0.0002382869979423295, 'samples': 15016128, 'steps': 78208, 'loss/train': 1.3198349475860596} 08/31/2021 03:24:29 - INFO - __main__ - Step 78210: {'lr': 0.00023828169702826688, 'samples': 15016320, 'steps': 78209, 'loss/train': 0.8736208081245422} 08/31/2021 03:24:29 - INFO - __main__ - Step 78211: {'lr': 0.00023827639611948435, 'samples': 15016512, 'steps': 78210, 'loss/train': 1.3584418296813965} 08/31/2021 03:24:29 - INFO - __main__ - Step 78212: {'lr': 0.00023827109521598432, 'samples': 15016704, 'steps': 78211, 'loss/train': 1.1456013917922974} 08/31/2021 03:24:31 - INFO - __main__ - Step 78213: {'lr': 0.00023826579431776915, 'samples': 15016896, 'steps': 78212, 'loss/train': 1.1583423614501953} 08/31/2021 03:24:31 - INFO - __main__ - Step 78214: {'lr': 0.0002382604934248412, 'samples': 15017088, 'steps': 78213, 'loss/train': 1.5613878965377808} 08/31/2021 03:24:32 - INFO - __main__ - Step 78215: {'lr': 0.0002382551925372029, 'samples': 15017280, 'steps': 78214, 'loss/train': 1.6441904306411743} 08/31/2021 03:24:32 - INFO - __main__ - Step 78216: {'lr': 0.00023824989165485664, 'samples': 15017472, 'steps': 78215, 'loss/train': 0.8869835734367371} 08/31/2021 03:24:32 - INFO - __main__ - Step 78217: {'lr': 0.00023824459077780477, 'samples': 15017664, 'steps': 78216, 'loss/train': 0.7795976400375366} 08/31/2021 03:24:34 - INFO - __main__ - Step 78218: {'lr': 0.00023823928990604972, 'samples': 15017856, 'steps': 78217, 'loss/train': 1.6795610189437866} 08/31/2021 03:24:34 - INFO - __main__ - Step 78219: {'lr': 0.00023823398903959395, 'samples': 15018048, 'steps': 78218, 'loss/train': 1.4318827390670776} 08/31/2021 03:24:35 - INFO - __main__ - Step 78220: {'lr': 0.00023822868817843969, 'samples': 15018240, 'steps': 78219, 'loss/train': 1.145537257194519} 08/31/2021 03:24:35 - INFO - __main__ - Step 78221: {'lr': 0.00023822338732258937, 'samples': 15018432, 'steps': 78220, 'loss/train': 0.8685339689254761} 08/31/2021 03:24:35 - INFO - __main__ - Step 78222: {'lr': 0.00023821808647204543, 'samples': 15018624, 'steps': 78221, 'loss/train': 0.897223949432373} 08/31/2021 03:24:36 - INFO - __main__ - Step 78223: {'lr': 0.00023821278562681023, 'samples': 15018816, 'steps': 78222, 'loss/train': 1.7850440740585327} 08/31/2021 03:24:38 - INFO - __main__ - Step 78224: {'lr': 0.00023820748478688616, 'samples': 15019008, 'steps': 78223, 'loss/train': 1.652881383895874} 08/31/2021 03:24:39 - INFO - __main__ - Step 78225: {'lr': 0.00023820218395227566, 'samples': 15019200, 'steps': 78224, 'loss/train': 1.4881561994552612} 08/31/2021 03:24:39 - INFO - __main__ - Step 78226: {'lr': 0.00023819688312298106, 'samples': 15019392, 'steps': 78225, 'loss/train': 1.1478456258773804} 08/31/2021 03:24:40 - INFO - __main__ - Step 78227: {'lr': 0.0002381915822990048, 'samples': 15019584, 'steps': 78226, 'loss/train': 1.4142946004867554} 08/31/2021 03:24:40 - INFO - __main__ - Step 78228: {'lr': 0.00023818628148034916, 'samples': 15019776, 'steps': 78227, 'loss/train': 1.2313158512115479} 08/31/2021 03:24:40 - INFO - __main__ - Step 78229: {'lr': 0.0002381809806670166, 'samples': 15019968, 'steps': 78228, 'loss/train': 0.34758633375167847} 08/31/2021 03:24:42 - INFO - __main__ - Step 78230: {'lr': 0.00023817567985900959, 'samples': 15020160, 'steps': 78229, 'loss/train': 0.3280270993709564} 08/31/2021 03:24:43 - INFO - __main__ - Step 78231: {'lr': 0.00023817037905633038, 'samples': 15020352, 'steps': 78230, 'loss/train': 1.632455587387085} 08/31/2021 03:24:43 - INFO - __main__ - Step 78232: {'lr': 0.0002381650782589814, 'samples': 15020544, 'steps': 78231, 'loss/train': 1.1385527849197388} 08/31/2021 03:24:44 - INFO - __main__ - Step 78233: {'lr': 0.00023815977746696504, 'samples': 15020736, 'steps': 78232, 'loss/train': 0.6514448523521423} 08/31/2021 03:24:44 - INFO - __main__ - Step 78234: {'lr': 0.00023815447668028373, 'samples': 15020928, 'steps': 78233, 'loss/train': 0.9558273553848267} 08/31/2021 03:24:44 - INFO - __main__ - Step 78235: {'lr': 0.00023814917589893984, 'samples': 15021120, 'steps': 78234, 'loss/train': 1.330552339553833} 08/31/2021 03:24:46 - INFO - __main__ - Step 78236: {'lr': 0.00023814387512293572, 'samples': 15021312, 'steps': 78235, 'loss/train': 1.2505656480789185} 08/31/2021 03:24:46 - INFO - __main__ - Step 78237: {'lr': 0.0002381385743522738, 'samples': 15021504, 'steps': 78236, 'loss/train': 1.232426404953003} 08/31/2021 03:24:47 - INFO - __main__ - Step 78238: {'lr': 0.00023813327358695644, 'samples': 15021696, 'steps': 78237, 'loss/train': 0.5746633410453796} 08/31/2021 03:24:47 - INFO - __main__ - Step 78239: {'lr': 0.00023812797282698607, 'samples': 15021888, 'steps': 78238, 'loss/train': 1.3005317449569702} 08/31/2021 03:24:47 - INFO - __main__ - Step 78240: {'lr': 0.00023812267207236513, 'samples': 15022080, 'steps': 78239, 'loss/train': 1.7426258325576782} 08/31/2021 03:24:49 - INFO - __main__ - Step 78241: {'lr': 0.00023811737132309582, 'samples': 15022272, 'steps': 78240, 'loss/train': 1.1216719150543213} 08/31/2021 03:24:49 - INFO - __main__ - Step 78242: {'lr': 0.00023811207057918067, 'samples': 15022464, 'steps': 78241, 'loss/train': 1.4970428943634033} 08/31/2021 03:24:50 - INFO - __main__ - Step 78243: {'lr': 0.00023810676984062202, 'samples': 15022656, 'steps': 78242, 'loss/train': 1.7791038751602173} 08/31/2021 03:24:50 - INFO - __main__ - Step 78244: {'lr': 0.0002381014691074223, 'samples': 15022848, 'steps': 78243, 'loss/train': 0.45660772919654846} 08/31/2021 03:24:50 - INFO - __main__ - Step 78245: {'lr': 0.00023809616837958383, 'samples': 15023040, 'steps': 78244, 'loss/train': 1.7785332202911377} 08/31/2021 03:24:52 - INFO - __main__ - Step 78246: {'lr': 0.00023809086765710908, 'samples': 15023232, 'steps': 78245, 'loss/train': 1.3062818050384521} 08/31/2021 03:24:53 - INFO - __main__ - Step 78247: {'lr': 0.0002380855669400004, 'samples': 15023424, 'steps': 78246, 'loss/train': 0.044209208339452744} 08/31/2021 03:24:53 - INFO - __main__ - Step 78248: {'lr': 0.00023808026622826014, 'samples': 15023616, 'steps': 78247, 'loss/train': 1.0107706785202026} 08/31/2021 03:24:53 - INFO - __main__ - Step 78249: {'lr': 0.00023807496552189078, 'samples': 15023808, 'steps': 78248, 'loss/train': 0.76167231798172} 08/31/2021 03:24:54 - INFO - __main__ - Step 78250: {'lr': 0.0002380696648208946, 'samples': 15024000, 'steps': 78249, 'loss/train': 1.156950831413269} 08/31/2021 03:24:55 - INFO - __main__ - Step 78251: {'lr': 0.0002380643641252741, 'samples': 15024192, 'steps': 78250, 'loss/train': 0.5364288091659546} 08/31/2021 03:24:55 - INFO - __main__ - Step 78252: {'lr': 0.00023805906343503158, 'samples': 15024384, 'steps': 78251, 'loss/train': 0.1571752279996872} 08/31/2021 03:24:56 - INFO - __main__ - Step 78253: {'lr': 0.0002380537627501696, 'samples': 15024576, 'steps': 78252, 'loss/train': 1.2047220468521118} 08/31/2021 03:24:56 - INFO - __main__ - Step 78254: {'lr': 0.00023804846207069029, 'samples': 15024768, 'steps': 78253, 'loss/train': 1.0839697122573853} 08/31/2021 03:24:56 - INFO - __main__ - Step 78255: {'lr': 0.00023804316139659616, 'samples': 15024960, 'steps': 78254, 'loss/train': 1.6671051979064941} 08/31/2021 03:24:58 - INFO - __main__ - Step 78256: {'lr': 0.00023803786072788957, 'samples': 15025152, 'steps': 78255, 'loss/train': 0.6260072588920593} 08/31/2021 03:24:58 - INFO - __main__ - Step 78257: {'lr': 0.00023803256006457298, 'samples': 15025344, 'steps': 78256, 'loss/train': 1.434145212173462} 08/31/2021 03:24:59 - INFO - __main__ - Step 78258: {'lr': 0.00023802725940664867, 'samples': 15025536, 'steps': 78257, 'loss/train': 1.5798933506011963} 08/31/2021 03:24:59 - INFO - __main__ - Step 78259: {'lr': 0.00023802195875411914, 'samples': 15025728, 'steps': 78258, 'loss/train': 1.3788985013961792} 08/31/2021 03:24:59 - INFO - __main__ - Step 78260: {'lr': 0.00023801665810698673, 'samples': 15025920, 'steps': 78259, 'loss/train': 1.6499162912368774} 08/31/2021 03:25:01 - INFO - __main__ - Step 78261: {'lr': 0.00023801135746525382, 'samples': 15026112, 'steps': 78260, 'loss/train': 0.9781749248504639} 08/31/2021 03:25:01 - INFO - __main__ - Step 78262: {'lr': 0.00023800605682892278, 'samples': 15026304, 'steps': 78261, 'loss/train': 1.3640543222427368} 08/31/2021 03:25:02 - INFO - __main__ - Step 78263: {'lr': 0.00023800075619799608, 'samples': 15026496, 'steps': 78262, 'loss/train': 0.5042073130607605} 08/31/2021 03:25:02 - INFO - __main__ - Step 78264: {'lr': 0.000237995455572476, 'samples': 15026688, 'steps': 78263, 'loss/train': 1.670353889465332} 08/31/2021 03:25:02 - INFO - __main__ - Step 78265: {'lr': 0.00023799015495236503, 'samples': 15026880, 'steps': 78264, 'loss/train': 1.7027428150177002} 08/31/2021 03:25:03 - INFO - __main__ - Step 78266: {'lr': 0.00023798485433766548, 'samples': 15027072, 'steps': 78265, 'loss/train': 0.6824645400047302} 08/31/2021 03:25:05 - INFO - __main__ - Step 78267: {'lr': 0.0002379795537283799, 'samples': 15027264, 'steps': 78266, 'loss/train': 1.0177229642868042} 08/31/2021 03:25:05 - INFO - __main__ - Step 78268: {'lr': 0.00023797425312451043, 'samples': 15027456, 'steps': 78267, 'loss/train': 0.6875557899475098} 08/31/2021 03:25:05 - INFO - __main__ - Step 78269: {'lr': 0.00023796895252605957, 'samples': 15027648, 'steps': 78268, 'loss/train': 1.85664963722229} 08/31/2021 03:25:06 - INFO - __main__ - Step 78270: {'lr': 0.00023796365193302972, 'samples': 15027840, 'steps': 78269, 'loss/train': 1.244812250137329} 08/31/2021 03:25:06 - INFO - __main__ - Step 78271: {'lr': 0.00023795835134542327, 'samples': 15028032, 'steps': 78270, 'loss/train': 1.406625509262085} 08/31/2021 03:25:06 - INFO - __main__ - Step 78272: {'lr': 0.00023795305076324257, 'samples': 15028224, 'steps': 78271, 'loss/train': 1.4599400758743286} 08/31/2021 03:25:08 - INFO - __main__ - Step 78273: {'lr': 0.00023794775018649007, 'samples': 15028416, 'steps': 78272, 'loss/train': 0.2736840844154358} 08/31/2021 03:25:08 - INFO - __main__ - Step 78274: {'lr': 0.00023794244961516811, 'samples': 15028608, 'steps': 78273, 'loss/train': 0.6404717564582825} 08/31/2021 03:25:09 - INFO - __main__ - Step 78275: {'lr': 0.0002379371490492791, 'samples': 15028800, 'steps': 78274, 'loss/train': 1.2556567192077637} 08/31/2021 03:25:09 - INFO - __main__ - Step 78276: {'lr': 0.00023793184848882543, 'samples': 15028992, 'steps': 78275, 'loss/train': 1.0998833179473877} 08/31/2021 03:25:09 - INFO - __main__ - Step 78277: {'lr': 0.0002379265479338095, 'samples': 15029184, 'steps': 78276, 'loss/train': 1.336678385734558} 08/31/2021 03:25:11 - INFO - __main__ - Step 78278: {'lr': 0.00023792124738423366, 'samples': 15029376, 'steps': 78277, 'loss/train': 1.2434172630310059} 08/31/2021 03:25:11 - INFO - __main__ - Step 78279: {'lr': 0.0002379159468401003, 'samples': 15029568, 'steps': 78278, 'loss/train': 1.579064130783081} 08/31/2021 03:25:12 - INFO - __main__ - Step 78280: {'lr': 0.000237910646301412, 'samples': 15029760, 'steps': 78279, 'loss/train': 0.856846809387207} 08/31/2021 03:25:12 - INFO - __main__ - Step 78281: {'lr': 0.0002379053457681708, 'samples': 15029952, 'steps': 78280, 'loss/train': 0.8943584561347961} 08/31/2021 03:25:12 - INFO - __main__ - Step 78282: {'lr': 0.00023790004524037927, 'samples': 15030144, 'steps': 78281, 'loss/train': 1.3890756368637085} 08/31/2021 03:25:14 - INFO - __main__ - Step 78283: {'lr': 0.00023789474471803984, 'samples': 15030336, 'steps': 78282, 'loss/train': 1.256885051727295} 08/31/2021 03:25:15 - INFO - __main__ - Step 78284: {'lr': 0.00023788944420115483, 'samples': 15030528, 'steps': 78283, 'loss/train': 0.92320716381073} 08/31/2021 03:25:15 - INFO - __main__ - Step 78285: {'lr': 0.00023788414368972662, 'samples': 15030720, 'steps': 78284, 'loss/train': 0.5009394884109497} 08/31/2021 03:25:16 - INFO - __main__ - Step 78286: {'lr': 0.00023787884318375767, 'samples': 15030912, 'steps': 78285, 'loss/train': 1.4457945823669434} 08/31/2021 03:25:16 - INFO - __main__ - Step 78287: {'lr': 0.00023787354268325032, 'samples': 15031104, 'steps': 78286, 'loss/train': 1.3764976263046265} 08/31/2021 03:25:17 - INFO - __main__ - Step 78288: {'lr': 0.00023786824218820693, 'samples': 15031296, 'steps': 78287, 'loss/train': 0.7654241919517517} 08/31/2021 03:25:18 - INFO - __main__ - Step 78289: {'lr': 0.00023786294169862997, 'samples': 15031488, 'steps': 78288, 'loss/train': 0.9643378853797913} 08/31/2021 03:25:18 - INFO - __main__ - Step 78290: {'lr': 0.00023785764121452176, 'samples': 15031680, 'steps': 78289, 'loss/train': 1.4695605039596558} 08/31/2021 03:25:19 - INFO - __main__ - Step 78291: {'lr': 0.0002378523407358847, 'samples': 15031872, 'steps': 78290, 'loss/train': 1.6728088855743408} 08/31/2021 03:25:19 - INFO - __main__ - Step 78292: {'lr': 0.0002378470402627212, 'samples': 15032064, 'steps': 78291, 'loss/train': 0.574180543422699} 08/31/2021 03:25:19 - INFO - __main__ - Step 78293: {'lr': 0.0002378417397950336, 'samples': 15032256, 'steps': 78292, 'loss/train': 1.5380840301513672} 08/31/2021 03:25:21 - INFO - __main__ - Step 78294: {'lr': 0.00023783643933282446, 'samples': 15032448, 'steps': 78293, 'loss/train': 1.184114694595337} 08/31/2021 03:25:21 - INFO - __main__ - Step 78295: {'lr': 0.00023783113887609596, 'samples': 15032640, 'steps': 78294, 'loss/train': 1.538252353668213} 08/31/2021 03:25:21 - INFO - __main__ - Step 78296: {'lr': 0.00023782583842485054, 'samples': 15032832, 'steps': 78295, 'loss/train': 1.6911529302597046} 08/31/2021 03:25:22 - INFO - __main__ - Step 78297: {'lr': 0.00023782053797909058, 'samples': 15033024, 'steps': 78296, 'loss/train': 1.406089186668396} 08/31/2021 03:25:22 - INFO - __main__ - Step 78298: {'lr': 0.0002378152375388185, 'samples': 15033216, 'steps': 78297, 'loss/train': 0.15994314849376678} 08/31/2021 03:25:24 - INFO - __main__ - Step 78299: {'lr': 0.00023780993710403672, 'samples': 15033408, 'steps': 78298, 'loss/train': 1.5110142230987549} 08/31/2021 03:25:24 - INFO - __main__ - Step 78300: {'lr': 0.00023780463667474758, 'samples': 15033600, 'steps': 78299, 'loss/train': 1.7553577423095703} 08/31/2021 03:25:25 - INFO - __main__ - Step 78301: {'lr': 0.00023779933625095348, 'samples': 15033792, 'steps': 78300, 'loss/train': 0.8433594107627869} 08/31/2021 03:25:25 - INFO - __main__ - Step 78302: {'lr': 0.0002377940358326568, 'samples': 15033984, 'steps': 78301, 'loss/train': 0.6370825171470642} 08/31/2021 03:25:25 - INFO - __main__ - Step 78303: {'lr': 0.00023778873541985995, 'samples': 15034176, 'steps': 78302, 'loss/train': 1.2459771633148193} 08/31/2021 03:25:27 - INFO - __main__ - Step 78304: {'lr': 0.00023778343501256531, 'samples': 15034368, 'steps': 78303, 'loss/train': 1.3284282684326172} 08/31/2021 03:25:28 - INFO - __main__ - Step 78305: {'lr': 0.00023777813461077526, 'samples': 15034560, 'steps': 78304, 'loss/train': 1.542154312133789} 08/31/2021 03:25:28 - INFO - __main__ - Step 78306: {'lr': 0.0002377728342144922, 'samples': 15034752, 'steps': 78305, 'loss/train': 1.5676392316818237} 08/31/2021 03:25:28 - INFO - __main__ - Step 78307: {'lr': 0.0002377675338237186, 'samples': 15034944, 'steps': 78306, 'loss/train': 0.7160967588424683} 08/31/2021 03:25:29 - INFO - __main__ - Step 78308: {'lr': 0.0002377622334384567, 'samples': 15035136, 'steps': 78307, 'loss/train': 0.1453021615743637} 08/31/2021 03:25:29 - INFO - __main__ - Step 78309: {'lr': 0.0002377569330587089, 'samples': 15035328, 'steps': 78308, 'loss/train': 0.26045528054237366} 08/31/2021 03:25:31 - INFO - __main__ - Step 78310: {'lr': 0.00023775163268447766, 'samples': 15035520, 'steps': 78309, 'loss/train': 2.35312819480896} 08/31/2021 03:25:31 - INFO - __main__ - Step 78311: {'lr': 0.00023774633231576534, 'samples': 15035712, 'steps': 78310, 'loss/train': 1.5237070322036743} 08/31/2021 03:25:31 - INFO - __main__ - Step 78312: {'lr': 0.00023774103195257432, 'samples': 15035904, 'steps': 78311, 'loss/train': 1.317970871925354} 08/31/2021 03:25:32 - INFO - __main__ - Step 78313: {'lr': 0.000237735731594907, 'samples': 15036096, 'steps': 78312, 'loss/train': 2.035721778869629} 08/31/2021 03:25:32 - INFO - __main__ - Step 78314: {'lr': 0.0002377304312427658, 'samples': 15036288, 'steps': 78313, 'loss/train': 0.044147852808237076} 08/31/2021 03:25:34 - INFO - __main__ - Step 78315: {'lr': 0.0002377251308961531, 'samples': 15036480, 'steps': 78314, 'loss/train': 0.7458129525184631} 08/31/2021 03:25:34 - INFO - __main__ - Step 78316: {'lr': 0.0002377198305550712, 'samples': 15036672, 'steps': 78315, 'loss/train': 0.9243463277816772} 08/31/2021 03:25:35 - INFO - __main__ - Step 78317: {'lr': 0.0002377145302195226, 'samples': 15036864, 'steps': 78316, 'loss/train': 1.6148545742034912} 08/31/2021 03:25:35 - INFO - __main__ - Step 78318: {'lr': 0.0002377092298895096, 'samples': 15037056, 'steps': 78317, 'loss/train': 1.8881945610046387} 08/31/2021 03:25:35 - INFO - __main__ - Step 78319: {'lr': 0.00023770392956503467, 'samples': 15037248, 'steps': 78318, 'loss/train': 0.1868859827518463} 08/31/2021 03:25:37 - INFO - __main__ - Step 78320: {'lr': 0.00023769862924610019, 'samples': 15037440, 'steps': 78319, 'loss/train': 1.4729167222976685} 08/31/2021 03:25:37 - INFO - __main__ - Step 78321: {'lr': 0.00023769332893270855, 'samples': 15037632, 'steps': 78320, 'loss/train': 0.9139119386672974} 08/31/2021 03:25:38 - INFO - __main__ - Step 78322: {'lr': 0.00023768802862486203, 'samples': 15037824, 'steps': 78321, 'loss/train': 1.0369155406951904} 08/31/2021 03:25:38 - INFO - __main__ - Step 78323: {'lr': 0.0002376827283225631, 'samples': 15038016, 'steps': 78322, 'loss/train': 1.213600754737854} 08/31/2021 03:25:38 - INFO - __main__ - Step 78324: {'lr': 0.00023767742802581414, 'samples': 15038208, 'steps': 78323, 'loss/train': 1.4380019903182983} 08/31/2021 03:25:40 - INFO - __main__ - Step 78325: {'lr': 0.00023767212773461756, 'samples': 15038400, 'steps': 78324, 'loss/train': 0.9828669428825378} 08/31/2021 03:25:40 - INFO - __main__ - Step 78326: {'lr': 0.0002376668274489757, 'samples': 15038592, 'steps': 78325, 'loss/train': 1.142281413078308} 08/31/2021 03:25:40 - INFO - __main__ - Step 78327: {'lr': 0.00023766152716889097, 'samples': 15038784, 'steps': 78326, 'loss/train': 1.4058582782745361} 08/31/2021 03:25:41 - INFO - __main__ - Step 78328: {'lr': 0.00023765622689436578, 'samples': 15038976, 'steps': 78327, 'loss/train': 1.4101929664611816} 08/31/2021 03:25:41 - INFO - __main__ - Step 78329: {'lr': 0.00023765092662540252, 'samples': 15039168, 'steps': 78328, 'loss/train': 1.1786388158798218} 08/31/2021 03:25:43 - INFO - __main__ - Step 78330: {'lr': 0.00023764562636200353, 'samples': 15039360, 'steps': 78329, 'loss/train': 1.3123762607574463} 08/31/2021 03:25:44 - INFO - __main__ - Step 78331: {'lr': 0.0002376403261041713, 'samples': 15039552, 'steps': 78330, 'loss/train': 1.1092054843902588} 08/31/2021 03:25:44 - INFO - __main__ - Step 78332: {'lr': 0.0002376350258519081, 'samples': 15039744, 'steps': 78331, 'loss/train': 1.0187078714370728} 08/31/2021 03:25:44 - INFO - __main__ - Step 78333: {'lr': 0.00023762972560521637, 'samples': 15039936, 'steps': 78332, 'loss/train': 1.0920356512069702} 08/31/2021 03:25:45 - INFO - __main__ - Step 78334: {'lr': 0.00023762442536409855, 'samples': 15040128, 'steps': 78333, 'loss/train': 1.640413761138916} 08/31/2021 03:25:45 - INFO - __main__ - Step 78335: {'lr': 0.0002376191251285569, 'samples': 15040320, 'steps': 78334, 'loss/train': 0.5610974431037903} 08/31/2021 03:25:47 - INFO - __main__ - Step 78336: {'lr': 0.0002376138248985939, 'samples': 15040512, 'steps': 78335, 'loss/train': 1.1709703207015991} 08/31/2021 03:25:47 - INFO - __main__ - Step 78337: {'lr': 0.0002376085246742119, 'samples': 15040704, 'steps': 78336, 'loss/train': 1.004204511642456} 08/31/2021 03:25:47 - INFO - __main__ - Step 78338: {'lr': 0.00023760322445541332, 'samples': 15040896, 'steps': 78337, 'loss/train': 0.7880653142929077} 08/31/2021 03:25:48 - INFO - __main__ - Step 78339: {'lr': 0.00023759792424220052, 'samples': 15041088, 'steps': 78338, 'loss/train': 1.2230491638183594} 08/31/2021 03:25:48 - INFO - __main__ - Step 78340: {'lr': 0.00023759262403457592, 'samples': 15041280, 'steps': 78339, 'loss/train': 1.098812222480774} 08/31/2021 03:25:50 - INFO - __main__ - Step 78341: {'lr': 0.0002375873238325419, 'samples': 15041472, 'steps': 78340, 'loss/train': 1.275638461112976} 08/31/2021 03:25:50 - INFO - __main__ - Step 78342: {'lr': 0.0002375820236361009, 'samples': 15041664, 'steps': 78341, 'loss/train': 1.382359266281128} 08/31/2021 03:25:51 - INFO - __main__ - Step 78343: {'lr': 0.00023757672344525518, 'samples': 15041856, 'steps': 78342, 'loss/train': 1.0335545539855957} 08/31/2021 03:25:51 - INFO - __main__ - Step 78344: {'lr': 0.00023757142326000718, 'samples': 15042048, 'steps': 78343, 'loss/train': 1.4155791997909546} 08/31/2021 03:25:51 - INFO - __main__ - Step 78345: {'lr': 0.00023756612308035934, 'samples': 15042240, 'steps': 78344, 'loss/train': 1.5496740341186523} 08/31/2021 03:25:53 - INFO - __main__ - Step 78346: {'lr': 0.00023756082290631397, 'samples': 15042432, 'steps': 78345, 'loss/train': 1.332305669784546} 08/31/2021 03:25:53 - INFO - __main__ - Step 78347: {'lr': 0.00023755552273787355, 'samples': 15042624, 'steps': 78346, 'loss/train': 1.055264949798584} 08/31/2021 03:25:54 - INFO - __main__ - Step 78348: {'lr': 0.00023755022257504043, 'samples': 15042816, 'steps': 78347, 'loss/train': 0.3375513553619385} 08/31/2021 03:25:54 - INFO - __main__ - Step 78349: {'lr': 0.00023754492241781698, 'samples': 15043008, 'steps': 78348, 'loss/train': 1.7592934370040894} 08/31/2021 03:25:54 - INFO - __main__ - Step 78350: {'lr': 0.00023753962226620557, 'samples': 15043200, 'steps': 78349, 'loss/train': 1.6579184532165527} 08/31/2021 03:25:56 - INFO - __main__ - Step 78351: {'lr': 0.0002375343221202086, 'samples': 15043392, 'steps': 78350, 'loss/train': 1.4996129274368286} 08/31/2021 03:25:56 - INFO - __main__ - Step 78352: {'lr': 0.0002375290219798285, 'samples': 15043584, 'steps': 78351, 'loss/train': 0.8602543473243713} 08/31/2021 03:25:57 - INFO - __main__ - Step 78353: {'lr': 0.00023752372184506764, 'samples': 15043776, 'steps': 78352, 'loss/train': 1.4180083274841309} 08/31/2021 03:25:57 - INFO - __main__ - Step 78354: {'lr': 0.00023751842171592838, 'samples': 15043968, 'steps': 78353, 'loss/train': 1.0960417985916138} 08/31/2021 03:25:57 - INFO - __main__ - Step 78355: {'lr': 0.00023751312159241313, 'samples': 15044160, 'steps': 78354, 'loss/train': 1.065266489982605} 08/31/2021 03:25:59 - INFO - __main__ - Step 78356: {'lr': 0.00023750782147452426, 'samples': 15044352, 'steps': 78355, 'loss/train': 1.1911017894744873} 08/31/2021 03:25:59 - INFO - __main__ - Step 78357: {'lr': 0.00023750252136226416, 'samples': 15044544, 'steps': 78356, 'loss/train': 1.3344037532806396} 08/31/2021 03:26:00 - INFO - __main__ - Step 78358: {'lr': 0.00023749722125563524, 'samples': 15044736, 'steps': 78357, 'loss/train': 1.0875266790390015} 08/31/2021 03:26:00 - INFO - __main__ - Step 78359: {'lr': 0.00023749192115463992, 'samples': 15044928, 'steps': 78358, 'loss/train': 0.051810938864946365} 08/31/2021 03:26:00 - INFO - __main__ - Step 78360: {'lr': 0.00023748662105928052, 'samples': 15045120, 'steps': 78359, 'loss/train': 0.7680079340934753} 08/31/2021 03:26:01 - INFO - __main__ - Step 78361: {'lr': 0.0002374813209695595, 'samples': 15045312, 'steps': 78360, 'loss/train': 1.1136144399642944} 08/31/2021 03:26:02 - INFO - __main__ - Step 78362: {'lr': 0.00023747602088547914, 'samples': 15045504, 'steps': 78361, 'loss/train': 0.9729183912277222} 08/31/2021 03:26:03 - INFO - __main__ - Step 78363: {'lr': 0.00023747072080704192, 'samples': 15045696, 'steps': 78362, 'loss/train': 0.8295179009437561} 08/31/2021 03:26:03 - INFO - __main__ - Step 78364: {'lr': 0.00023746542073425022, 'samples': 15045888, 'steps': 78363, 'loss/train': 0.0645226314663887} 08/31/2021 03:26:03 - INFO - __main__ - Step 78365: {'lr': 0.00023746012066710637, 'samples': 15046080, 'steps': 78364, 'loss/train': 1.3399068117141724} 08/31/2021 03:26:04 - INFO - __main__ - Step 78366: {'lr': 0.0002374548206056128, 'samples': 15046272, 'steps': 78365, 'loss/train': 1.2674245834350586} 08/31/2021 03:26:05 - INFO - __main__ - Step 78367: {'lr': 0.0002374495205497719, 'samples': 15046464, 'steps': 78366, 'loss/train': 0.15601743757724762} 08/31/2021 03:26:06 - INFO - __main__ - Step 78368: {'lr': 0.00023744422049958605, 'samples': 15046656, 'steps': 78367, 'loss/train': 1.3019722700119019} 08/31/2021 03:26:06 - INFO - __main__ - Step 78369: {'lr': 0.00023743892045505763, 'samples': 15046848, 'steps': 78368, 'loss/train': 0.8084762692451477} 08/31/2021 03:26:07 - INFO - __main__ - Step 78370: {'lr': 0.00023743362041618905, 'samples': 15047040, 'steps': 78369, 'loss/train': 1.0720493793487549} 08/31/2021 03:26:07 - INFO - __main__ - Step 78371: {'lr': 0.00023742832038298268, 'samples': 15047232, 'steps': 78370, 'loss/train': 0.8810614347457886} 08/31/2021 03:26:09 - INFO - __main__ - Step 78372: {'lr': 0.00023742302035544092, 'samples': 15047424, 'steps': 78371, 'loss/train': 1.4776440858840942} 08/31/2021 03:26:09 - INFO - __main__ - Step 78373: {'lr': 0.00023741772033356615, 'samples': 15047616, 'steps': 78372, 'loss/train': 0.1435045450925827} 08/31/2021 03:26:09 - INFO - __main__ - Step 78374: {'lr': 0.00023741242031736077, 'samples': 15047808, 'steps': 78373, 'loss/train': 0.5163231492042542} 08/31/2021 03:26:10 - INFO - __main__ - Step 78375: {'lr': 0.00023740712030682727, 'samples': 15048000, 'steps': 78374, 'loss/train': 1.2231221199035645} 08/31/2021 03:26:10 - INFO - __main__ - Step 78376: {'lr': 0.00023740182030196778, 'samples': 15048192, 'steps': 78375, 'loss/train': 0.15352272987365723} 08/31/2021 03:26:12 - INFO - __main__ - Step 78377: {'lr': 0.00023739652030278487, 'samples': 15048384, 'steps': 78376, 'loss/train': 1.3250662088394165} 08/31/2021 03:26:12 - INFO - __main__ - Step 78378: {'lr': 0.0002373912203092809, 'samples': 15048576, 'steps': 78377, 'loss/train': 1.4365205764770508} 08/31/2021 03:26:13 - INFO - __main__ - Step 78379: {'lr': 0.00023738592032145823, 'samples': 15048768, 'steps': 78378, 'loss/train': 1.2499642372131348} 08/31/2021 03:26:13 - INFO - __main__ - Step 78380: {'lr': 0.00023738062033931925, 'samples': 15048960, 'steps': 78379, 'loss/train': 0.6728916764259338} 08/31/2021 03:26:13 - INFO - __main__ - Step 78381: {'lr': 0.0002373753203628664, 'samples': 15049152, 'steps': 78380, 'loss/train': 1.371895432472229} 08/31/2021 03:26:14 - INFO - __main__ - Step 78382: {'lr': 0.00023737002039210203, 'samples': 15049344, 'steps': 78381, 'loss/train': 1.2777695655822754} 08/31/2021 03:26:15 - INFO - __main__ - Step 78383: {'lr': 0.00023736472042702855, 'samples': 15049536, 'steps': 78382, 'loss/train': 1.283778429031372} 08/31/2021 03:26:16 - INFO - __main__ - Step 78384: {'lr': 0.0002373594204676483, 'samples': 15049728, 'steps': 78383, 'loss/train': 0.8101212978363037} 08/31/2021 03:26:16 - INFO - __main__ - Step 78385: {'lr': 0.00023735412051396375, 'samples': 15049920, 'steps': 78384, 'loss/train': 0.8693158626556396} 08/31/2021 03:26:16 - INFO - __main__ - Step 78386: {'lr': 0.00023734882056597716, 'samples': 15050112, 'steps': 78385, 'loss/train': 1.5222065448760986} 08/31/2021 03:26:17 - INFO - __main__ - Step 78387: {'lr': 0.00023734352062369107, 'samples': 15050304, 'steps': 78386, 'loss/train': 0.7905386686325073} 08/31/2021 03:26:18 - INFO - __main__ - Step 78388: {'lr': 0.00023733822068710785, 'samples': 15050496, 'steps': 78387, 'loss/train': 0.9364627599716187} 08/31/2021 03:26:19 - INFO - __main__ - Step 78389: {'lr': 0.0002373329207562298, 'samples': 15050688, 'steps': 78388, 'loss/train': 1.1497427225112915} 08/31/2021 03:26:19 - INFO - __main__ - Step 78390: {'lr': 0.00023732762083105926, 'samples': 15050880, 'steps': 78389, 'loss/train': 0.059207212179899216} 08/31/2021 03:26:19 - INFO - __main__ - Step 78391: {'lr': 0.00023732232091159872, 'samples': 15051072, 'steps': 78390, 'loss/train': 1.8437477350234985} 08/31/2021 03:26:20 - INFO - __main__ - Step 78392: {'lr': 0.00023731702099785058, 'samples': 15051264, 'steps': 78391, 'loss/train': 0.46754756569862366} 08/31/2021 03:26:22 - INFO - __main__ - Step 78393: {'lr': 0.00023731172108981712, 'samples': 15051456, 'steps': 78392, 'loss/train': 0.04262499883770943} 08/31/2021 03:26:22 - INFO - __main__ - Step 78394: {'lr': 0.00023730642118750087, 'samples': 15051648, 'steps': 78393, 'loss/train': 1.5363014936447144} 08/31/2021 03:26:23 - INFO - __main__ - Step 78395: {'lr': 0.00023730112129090414, 'samples': 15051840, 'steps': 78394, 'loss/train': 1.3360562324523926} 08/31/2021 03:26:23 - INFO - __main__ - Step 78396: {'lr': 0.00023729582140002932, 'samples': 15052032, 'steps': 78395, 'loss/train': 1.4427311420440674} 08/31/2021 03:26:23 - INFO - __main__ - Step 78397: {'lr': 0.0002372905215148788, 'samples': 15052224, 'steps': 78396, 'loss/train': 1.1490588188171387} 08/31/2021 03:26:25 - INFO - __main__ - Step 78398: {'lr': 0.000237285221635455, 'samples': 15052416, 'steps': 78397, 'loss/train': 1.0724105834960938} 08/31/2021 03:26:25 - INFO - __main__ - Step 78399: {'lr': 0.00023727992176176025, 'samples': 15052608, 'steps': 78398, 'loss/train': 2.2344560623168945} 08/31/2021 03:26:26 - INFO - __main__ - Step 78400: {'lr': 0.00023727462189379698, 'samples': 15052800, 'steps': 78399, 'loss/train': 1.5413017272949219} 08/31/2021 03:26:26 - INFO - __main__ - Step 78401: {'lr': 0.0002372693220315677, 'samples': 15052992, 'steps': 78400, 'loss/train': 1.0640225410461426} 08/31/2021 03:26:26 - INFO - __main__ - Step 78402: {'lr': 0.00023726402217507454, 'samples': 15053184, 'steps': 78401, 'loss/train': 0.029188988730311394} 08/31/2021 03:26:28 - INFO - __main__ - Step 78403: {'lr': 0.00023725872232432002, 'samples': 15053376, 'steps': 78402, 'loss/train': 1.0987063646316528} 08/31/2021 03:26:28 - INFO - __main__ - Step 78404: {'lr': 0.00023725342247930652, 'samples': 15053568, 'steps': 78403, 'loss/train': 0.9465001821517944} 08/31/2021 03:26:29 - INFO - __main__ - Step 78405: {'lr': 0.00023724812264003643, 'samples': 15053760, 'steps': 78404, 'loss/train': 0.8659319281578064} 08/31/2021 03:26:29 - INFO - __main__ - Step 78406: {'lr': 0.00023724282280651214, 'samples': 15053952, 'steps': 78405, 'loss/train': 1.3096604347229004} 08/31/2021 03:26:29 - INFO - __main__ - Step 78407: {'lr': 0.00023723752297873603, 'samples': 15054144, 'steps': 78406, 'loss/train': 0.9481505155563354} 08/31/2021 03:26:30 - INFO - __main__ - Step 78408: {'lr': 0.0002372322231567105, 'samples': 15054336, 'steps': 78407, 'loss/train': 1.4327278137207031} 08/31/2021 03:26:32 - INFO - __main__ - Step 78409: {'lr': 0.00023722692334043793, 'samples': 15054528, 'steps': 78408, 'loss/train': 0.8699550032615662} 08/31/2021 03:26:32 - INFO - __main__ - Step 78410: {'lr': 0.00023722162352992073, 'samples': 15054720, 'steps': 78409, 'loss/train': 0.03196541965007782} 08/31/2021 03:26:32 - INFO - __main__ - Step 78411: {'lr': 0.00023721632372516126, 'samples': 15054912, 'steps': 78410, 'loss/train': 1.9008138179779053} 08/31/2021 03:26:33 - INFO - __main__ - Step 78412: {'lr': 0.0002372110239261619, 'samples': 15055104, 'steps': 78411, 'loss/train': 1.1337389945983887} 08/31/2021 03:26:33 - INFO - __main__ - Step 78413: {'lr': 0.00023720572413292508, 'samples': 15055296, 'steps': 78412, 'loss/train': 0.6151060461997986} 08/31/2021 03:26:34 - INFO - __main__ - Step 78414: {'lr': 0.00023720042434545314, 'samples': 15055488, 'steps': 78413, 'loss/train': 0.9970881342887878} 08/31/2021 03:26:35 - INFO - __main__ - Step 78415: {'lr': 0.0002371951245637486, 'samples': 15055680, 'steps': 78414, 'loss/train': 1.3534481525421143} 08/31/2021 03:26:35 - INFO - __main__ - Step 78416: {'lr': 0.00023718982478781369, 'samples': 15055872, 'steps': 78415, 'loss/train': 1.3756686449050903} 08/31/2021 03:26:36 - INFO - __main__ - Step 78417: {'lr': 0.00023718452501765078, 'samples': 15056064, 'steps': 78416, 'loss/train': 0.7152353525161743} 08/31/2021 03:26:36 - INFO - __main__ - Step 78418: {'lr': 0.00023717922525326235, 'samples': 15056256, 'steps': 78417, 'loss/train': 1.2278251647949219} 08/31/2021 03:26:37 - INFO - __main__ - Step 78419: {'lr': 0.00023717392549465075, 'samples': 15056448, 'steps': 78418, 'loss/train': 1.1808745861053467} 08/31/2021 03:26:38 - INFO - __main__ - Step 78420: {'lr': 0.0002371686257418184, 'samples': 15056640, 'steps': 78419, 'loss/train': 1.487298607826233} 08/31/2021 03:26:38 - INFO - __main__ - Step 78421: {'lr': 0.00023716332599476764, 'samples': 15056832, 'steps': 78420, 'loss/train': 1.2595746517181396} 08/31/2021 03:26:39 - INFO - __main__ - Step 78422: {'lr': 0.0002371580262535009, 'samples': 15057024, 'steps': 78421, 'loss/train': 2.1493051052093506} 08/31/2021 03:26:39 - INFO - __main__ - Step 78423: {'lr': 0.00023715272651802057, 'samples': 15057216, 'steps': 78422, 'loss/train': 0.877363920211792} 08/31/2021 03:26:41 - INFO - __main__ - Step 78424: {'lr': 0.00023714742678832901, 'samples': 15057408, 'steps': 78423, 'loss/train': 1.0117827653884888} 08/31/2021 03:26:41 - INFO - __main__ - Step 78425: {'lr': 0.00023714212706442864, 'samples': 15057600, 'steps': 78424, 'loss/train': 1.4481271505355835} 08/31/2021 03:26:42 - INFO - __main__ - Step 78426: {'lr': 0.0002371368273463218, 'samples': 15057792, 'steps': 78425, 'loss/train': 0.1457945853471756} 08/31/2021 03:26:42 - INFO - __main__ - Step 78427: {'lr': 0.00023713152763401094, 'samples': 15057984, 'steps': 78426, 'loss/train': 1.2024794816970825} 08/31/2021 03:26:42 - INFO - __main__ - Step 78428: {'lr': 0.00023712622792749848, 'samples': 15058176, 'steps': 78427, 'loss/train': 0.0975404903292656} 08/31/2021 03:26:43 - INFO - __main__ - Step 78429: {'lr': 0.00023712092822678667, 'samples': 15058368, 'steps': 78428, 'loss/train': 0.12037888169288635} 08/31/2021 03:26:44 - INFO - __main__ - Step 78430: {'lr': 0.00023711562853187797, 'samples': 15058560, 'steps': 78429, 'loss/train': 1.8330309391021729} 08/31/2021 03:26:45 - INFO - __main__ - Step 78431: {'lr': 0.00023711032884277475, 'samples': 15058752, 'steps': 78430, 'loss/train': 1.3437201976776123} 08/31/2021 03:26:45 - INFO - __main__ - Step 78432: {'lr': 0.00023710502915947942, 'samples': 15058944, 'steps': 78431, 'loss/train': 1.5171172618865967} 08/31/2021 03:26:46 - INFO - __main__ - Step 78433: {'lr': 0.0002370997294819944, 'samples': 15059136, 'steps': 78432, 'loss/train': 1.3560127019882202} 08/31/2021 03:26:46 - INFO - __main__ - Step 78434: {'lr': 0.000237094429810322, 'samples': 15059328, 'steps': 78433, 'loss/train': 0.8385015726089478} 08/31/2021 03:26:46 - INFO - __main__ - Step 78435: {'lr': 0.00023708913014446468, 'samples': 15059520, 'steps': 78434, 'loss/train': 1.5148216485977173} 08/31/2021 03:26:48 - INFO - __main__ - Step 78436: {'lr': 0.00023708383048442477, 'samples': 15059712, 'steps': 78435, 'loss/train': 1.2169296741485596} 08/31/2021 03:26:48 - INFO - __main__ - Step 78437: {'lr': 0.00023707853083020469, 'samples': 15059904, 'steps': 78436, 'loss/train': 0.9439341425895691} 08/31/2021 03:26:48 - INFO - __main__ - Step 78438: {'lr': 0.00023707323118180685, 'samples': 15060096, 'steps': 78437, 'loss/train': 1.0909396409988403} 08/31/2021 03:26:49 - INFO - __main__ - Step 78439: {'lr': 0.00023706793153923362, 'samples': 15060288, 'steps': 78438, 'loss/train': 0.10683374851942062} 08/31/2021 03:26:49 - INFO - __main__ - Step 78440: {'lr': 0.00023706263190248733, 'samples': 15060480, 'steps': 78439, 'loss/train': 1.49667489528656} 08/31/2021 03:26:51 - INFO - __main__ - Step 78441: {'lr': 0.00023705733227157044, 'samples': 15060672, 'steps': 78440, 'loss/train': 0.902884840965271} 08/31/2021 03:26:51 - INFO - __main__ - Step 78442: {'lr': 0.00023705203264648544, 'samples': 15060864, 'steps': 78441, 'loss/train': 1.4564974308013916} 08/31/2021 03:26:51 - INFO - __main__ - Step 78443: {'lr': 0.00023704673302723449, 'samples': 15061056, 'steps': 78442, 'loss/train': 1.4037797451019287} 08/31/2021 03:26:52 - INFO - __main__ - Step 78444: {'lr': 0.00023704143341382006, 'samples': 15061248, 'steps': 78443, 'loss/train': 0.45491668581962585} 08/31/2021 03:26:52 - INFO - __main__ - Step 78445: {'lr': 0.00023703613380624458, 'samples': 15061440, 'steps': 78444, 'loss/train': 1.098883032798767} 08/31/2021 03:26:54 - INFO - __main__ - Step 78446: {'lr': 0.0002370308342045104, 'samples': 15061632, 'steps': 78445, 'loss/train': 0.9075435996055603} 08/31/2021 03:26:54 - INFO - __main__ - Step 78447: {'lr': 0.00023702553460861993, 'samples': 15061824, 'steps': 78446, 'loss/train': 1.3028714656829834} 08/31/2021 03:26:55 - INFO - __main__ - Step 78448: {'lr': 0.00023702023501857557, 'samples': 15062016, 'steps': 78447, 'loss/train': 0.5789878964424133} 08/31/2021 03:26:55 - INFO - __main__ - Step 78449: {'lr': 0.0002370149354343797, 'samples': 15062208, 'steps': 78448, 'loss/train': 1.8363487720489502} 08/31/2021 03:26:55 - INFO - __main__ - Step 78450: {'lr': 0.00023700963585603465, 'samples': 15062400, 'steps': 78449, 'loss/train': 1.0619999170303345} 08/31/2021 03:26:57 - INFO - __main__ - Step 78451: {'lr': 0.0002370043362835429, 'samples': 15062592, 'steps': 78450, 'loss/train': 1.4669698476791382} 08/31/2021 03:26:58 - INFO - __main__ - Step 78452: {'lr': 0.00023699903671690678, 'samples': 15062784, 'steps': 78451, 'loss/train': 1.5674808025360107} 08/31/2021 03:26:58 - INFO - __main__ - Step 78453: {'lr': 0.0002369937371561287, 'samples': 15062976, 'steps': 78452, 'loss/train': 1.0435659885406494} 08/31/2021 03:26:58 - INFO - __main__ - Step 78454: {'lr': 0.00023698843760121103, 'samples': 15063168, 'steps': 78453, 'loss/train': 1.6541484594345093} 08/31/2021 03:26:59 - INFO - __main__ - Step 78455: {'lr': 0.00023698313805215629, 'samples': 15063360, 'steps': 78454, 'loss/train': 0.19037452340126038} 08/31/2021 03:27:00 - INFO - __main__ - Step 78456: {'lr': 0.00023697783850896664, 'samples': 15063552, 'steps': 78455, 'loss/train': 0.1273006945848465} 08/31/2021 03:27:01 - INFO - __main__ - Step 78457: {'lr': 0.00023697253897164456, 'samples': 15063744, 'steps': 78456, 'loss/train': 1.3124130964279175} 08/31/2021 03:27:01 - INFO - __main__ - Step 78458: {'lr': 0.00023696723944019246, 'samples': 15063936, 'steps': 78457, 'loss/train': 0.9327784180641174} 08/31/2021 03:27:01 - INFO - __main__ - Step 78459: {'lr': 0.00023696193991461274, 'samples': 15064128, 'steps': 78458, 'loss/train': 1.1155669689178467} 08/31/2021 03:27:02 - INFO - __main__ - Step 78460: {'lr': 0.00023695664039490776, 'samples': 15064320, 'steps': 78459, 'loss/train': 0.5763663649559021} 08/31/2021 03:27:03 - INFO - __main__ - Step 78461: {'lr': 0.0002369513408810799, 'samples': 15064512, 'steps': 78460, 'loss/train': 0.6272938251495361} 08/31/2021 03:27:04 - INFO - __main__ - Step 78462: {'lr': 0.00023694604137313154, 'samples': 15064704, 'steps': 78461, 'loss/train': 1.3606266975402832} 08/31/2021 03:27:04 - INFO - __main__ - Step 78463: {'lr': 0.00023694074187106514, 'samples': 15064896, 'steps': 78462, 'loss/train': 0.8718608617782593} 08/31/2021 03:27:04 - INFO - __main__ - Step 78464: {'lr': 0.00023693544237488303, 'samples': 15065088, 'steps': 78463, 'loss/train': 2.334686756134033} 08/31/2021 03:27:05 - INFO - __main__ - Step 78465: {'lr': 0.00023693014288458762, 'samples': 15065280, 'steps': 78464, 'loss/train': 1.3954285383224487} 08/31/2021 03:27:06 - INFO - __main__ - Step 78466: {'lr': 0.0002369248434001813, 'samples': 15065472, 'steps': 78465, 'loss/train': 1.5964019298553467} 08/31/2021 03:27:07 - INFO - __main__ - Step 78467: {'lr': 0.00023691954392166643, 'samples': 15065664, 'steps': 78466, 'loss/train': 1.482763409614563} 08/31/2021 03:27:07 - INFO - __main__ - Step 78468: {'lr': 0.00023691424444904539, 'samples': 15065856, 'steps': 78467, 'loss/train': 0.9521181583404541} 08/31/2021 03:27:07 - INFO - __main__ - Step 78469: {'lr': 0.00023690894498232067, 'samples': 15066048, 'steps': 78468, 'loss/train': 1.66838538646698} 08/31/2021 03:27:08 - INFO - __main__ - Step 78470: {'lr': 0.0002369036455214945, 'samples': 15066240, 'steps': 78469, 'loss/train': 1.073154330253601} 08/31/2021 03:27:08 - INFO - __main__ - Step 78471: {'lr': 0.00023689834606656932, 'samples': 15066432, 'steps': 78470, 'loss/train': 1.3765579462051392} 08/31/2021 03:27:10 - INFO - __main__ - Step 78472: {'lr': 0.00023689304661754756, 'samples': 15066624, 'steps': 78471, 'loss/train': 1.2794289588928223} 08/31/2021 03:27:10 - INFO - __main__ - Step 78473: {'lr': 0.00023688774717443162, 'samples': 15066816, 'steps': 78472, 'loss/train': 1.699897050857544} 08/31/2021 03:27:10 - INFO - __main__ - Step 78474: {'lr': 0.00023688244773722384, 'samples': 15067008, 'steps': 78473, 'loss/train': 0.9643998742103577} 08/31/2021 03:27:11 - INFO - __main__ - Step 78475: {'lr': 0.0002368771483059266, 'samples': 15067200, 'steps': 78474, 'loss/train': 1.3784117698669434} 08/31/2021 03:27:11 - INFO - __main__ - Step 78476: {'lr': 0.00023687184888054237, 'samples': 15067392, 'steps': 78475, 'loss/train': 0.848858654499054} 08/31/2021 03:27:13 - INFO - __main__ - Step 78477: {'lr': 0.0002368665494610735, 'samples': 15067584, 'steps': 78476, 'loss/train': 0.038947343826293945} 08/31/2021 03:27:13 - INFO - __main__ - Step 78478: {'lr': 0.00023686125004752231, 'samples': 15067776, 'steps': 78477, 'loss/train': 0.25689297914505005} 08/31/2021 03:27:13 - INFO - __main__ - Step 78479: {'lr': 0.00023685595063989125, 'samples': 15067968, 'steps': 78478, 'loss/train': 1.5421918630599976} 08/31/2021 03:27:14 - INFO - __main__ - Step 78480: {'lr': 0.00023685065123818267, 'samples': 15068160, 'steps': 78479, 'loss/train': 1.176207184791565} 08/31/2021 03:27:14 - INFO - __main__ - Step 78481: {'lr': 0.000236845351842399, 'samples': 15068352, 'steps': 78480, 'loss/train': 1.210680365562439} 08/31/2021 03:27:14 - INFO - __main__ - Step 78482: {'lr': 0.00023684005245254268, 'samples': 15068544, 'steps': 78481, 'loss/train': 0.5012506246566772} 08/31/2021 03:27:16 - INFO - __main__ - Step 78483: {'lr': 0.00023683475306861596, 'samples': 15068736, 'steps': 78482, 'loss/train': 1.6027882099151611} 08/31/2021 03:27:16 - INFO - __main__ - Step 78484: {'lr': 0.0002368294536906213, 'samples': 15068928, 'steps': 78483, 'loss/train': 0.1280190497636795} 08/31/2021 03:27:17 - INFO - __main__ - Step 78485: {'lr': 0.00023682415431856108, 'samples': 15069120, 'steps': 78484, 'loss/train': 0.7858677506446838} 08/31/2021 03:27:17 - INFO - __main__ - Step 78486: {'lr': 0.0002368188549524377, 'samples': 15069312, 'steps': 78485, 'loss/train': 0.34740951657295227} 08/31/2021 03:27:17 - INFO - __main__ - Step 78487: {'lr': 0.0002368135555922536, 'samples': 15069504, 'steps': 78486, 'loss/train': 2.5028443336486816} 08/31/2021 03:27:19 - INFO - __main__ - Step 78488: {'lr': 0.00023680825623801103, 'samples': 15069696, 'steps': 78487, 'loss/train': 1.1573765277862549} 08/31/2021 03:27:19 - INFO - __main__ - Step 78489: {'lr': 0.00023680295688971247, 'samples': 15069888, 'steps': 78488, 'loss/train': 1.6640379428863525} 08/31/2021 03:27:20 - INFO - __main__ - Step 78490: {'lr': 0.0002367976575473603, 'samples': 15070080, 'steps': 78489, 'loss/train': 0.912822961807251} 08/31/2021 03:27:20 - INFO - __main__ - Step 78491: {'lr': 0.0002367923582109569, 'samples': 15070272, 'steps': 78490, 'loss/train': 1.2923566102981567} 08/31/2021 03:27:20 - INFO - __main__ - Step 78492: {'lr': 0.00023678705888050463, 'samples': 15070464, 'steps': 78491, 'loss/train': 1.0043613910675049} 08/31/2021 03:27:22 - INFO - __main__ - Step 78493: {'lr': 0.00023678175955600594, 'samples': 15070656, 'steps': 78492, 'loss/train': 0.04386604204773903} 08/31/2021 03:27:22 - INFO - __main__ - Step 78494: {'lr': 0.0002367764602374632, 'samples': 15070848, 'steps': 78493, 'loss/train': 1.7511450052261353} 08/31/2021 03:27:23 - INFO - __main__ - Step 78495: {'lr': 0.00023677116092487874, 'samples': 15071040, 'steps': 78494, 'loss/train': 0.8187929391860962} 08/31/2021 03:27:23 - INFO - __main__ - Step 78496: {'lr': 0.0002367658616182551, 'samples': 15071232, 'steps': 78495, 'loss/train': 0.036605354398489} 08/31/2021 03:27:24 - INFO - __main__ - Step 78497: {'lr': 0.00023676056231759446, 'samples': 15071424, 'steps': 78496, 'loss/train': 1.471260905265808} 08/31/2021 03:27:25 - INFO - __main__ - Step 78498: {'lr': 0.00023675526302289936, 'samples': 15071616, 'steps': 78497, 'loss/train': 1.353149652481079} 08/31/2021 03:27:26 - INFO - __main__ - Step 78499: {'lr': 0.0002367499637341721, 'samples': 15071808, 'steps': 78498, 'loss/train': 1.3293336629867554} 08/31/2021 03:27:26 - INFO - __main__ - Step 78500: {'lr': 0.0002367446644514151, 'samples': 15072000, 'steps': 78499, 'loss/train': 1.7442960739135742} 08/31/2021 03:27:26 - INFO - __main__ - Step 78501: {'lr': 0.00023673936517463074, 'samples': 15072192, 'steps': 78500, 'loss/train': 1.3827519416809082} 08/31/2021 03:27:27 - INFO - __main__ - Step 78502: {'lr': 0.0002367340659038214, 'samples': 15072384, 'steps': 78501, 'loss/train': 0.8102091550827026} 08/31/2021 03:27:29 - INFO - __main__ - Step 78503: {'lr': 0.0002367287666389895, 'samples': 15072576, 'steps': 78502, 'loss/train': 0.7232016324996948} 08/31/2021 03:27:29 - INFO - __main__ - Step 78504: {'lr': 0.00023672346738013746, 'samples': 15072768, 'steps': 78503, 'loss/train': 1.6213234663009644} 08/31/2021 03:27:29 - INFO - __main__ - Step 78505: {'lr': 0.00023671816812726758, 'samples': 15072960, 'steps': 78504, 'loss/train': 1.4650588035583496} 08/31/2021 03:27:30 - INFO - __main__ - Step 78506: {'lr': 0.00023671286888038225, 'samples': 15073152, 'steps': 78505, 'loss/train': 1.2723097801208496} 08/31/2021 03:27:30 - INFO - __main__ - Step 78507: {'lr': 0.00023670756963948395, 'samples': 15073344, 'steps': 78506, 'loss/train': 4.690213203430176} 08/31/2021 03:27:32 - INFO - __main__ - Step 78508: {'lr': 0.00023670227040457502, 'samples': 15073536, 'steps': 78507, 'loss/train': 1.6338800191879272} 08/31/2021 03:27:32 - INFO - __main__ - Step 78509: {'lr': 0.0002366969711756579, 'samples': 15073728, 'steps': 78508, 'loss/train': 0.5753220319747925} 08/31/2021 03:27:33 - INFO - __main__ - Step 78510: {'lr': 0.00023669167195273486, 'samples': 15073920, 'steps': 78509, 'loss/train': 0.0186095479875803} 08/31/2021 03:27:33 - INFO - __main__ - Step 78511: {'lr': 0.0002366863727358083, 'samples': 15074112, 'steps': 78510, 'loss/train': 1.66221022605896} 08/31/2021 03:27:33 - INFO - __main__ - Step 78512: {'lr': 0.0002366810735248807, 'samples': 15074304, 'steps': 78511, 'loss/train': 1.4303975105285645} 08/31/2021 03:27:34 - INFO - __main__ - Step 78513: {'lr': 0.00023667577431995437, 'samples': 15074496, 'steps': 78512, 'loss/train': 5.664029598236084} 08/31/2021 03:27:34 - INFO - __main__ - Step 78514: {'lr': 0.00023667047512103176, 'samples': 15074688, 'steps': 78513, 'loss/train': 1.0055005550384521} 08/31/2021 03:27:36 - INFO - __main__ - Step 78515: {'lr': 0.0002366651759281152, 'samples': 15074880, 'steps': 78514, 'loss/train': 1.4762098789215088} 08/31/2021 03:27:36 - INFO - __main__ - Step 78516: {'lr': 0.00023665987674120713, 'samples': 15075072, 'steps': 78515, 'loss/train': 1.4603593349456787} 08/31/2021 03:27:36 - INFO - __main__ - Step 78517: {'lr': 0.0002366545775603099, 'samples': 15075264, 'steps': 78516, 'loss/train': 1.1042726039886475} 08/31/2021 03:27:37 - INFO - __main__ - Step 78518: {'lr': 0.00023664927838542592, 'samples': 15075456, 'steps': 78517, 'loss/train': 1.3035238981246948} 08/31/2021 03:27:37 - INFO - __main__ - Step 78519: {'lr': 0.00023664397921655756, 'samples': 15075648, 'steps': 78518, 'loss/train': 1.1816179752349854} 08/31/2021 03:27:39 - INFO - __main__ - Step 78520: {'lr': 0.00023663868005370723, 'samples': 15075840, 'steps': 78519, 'loss/train': 1.1135735511779785} 08/31/2021 03:27:39 - INFO - __main__ - Step 78521: {'lr': 0.00023663338089687728, 'samples': 15076032, 'steps': 78520, 'loss/train': 1.2504030466079712} 08/31/2021 03:27:40 - INFO - __main__ - Step 78522: {'lr': 0.00023662808174607027, 'samples': 15076224, 'steps': 78521, 'loss/train': 0.019023535773158073} 08/31/2021 03:27:40 - INFO - __main__ - Step 78523: {'lr': 0.00023662278260128827, 'samples': 15076416, 'steps': 78522, 'loss/train': 0.6710931658744812} 08/31/2021 03:27:40 - INFO - __main__ - Step 78524: {'lr': 0.0002366174834625339, 'samples': 15076608, 'steps': 78523, 'loss/train': 0.7854605913162231} 08/31/2021 03:27:41 - INFO - __main__ - Step 78525: {'lr': 0.00023661218432980948, 'samples': 15076800, 'steps': 78524, 'loss/train': 1.5350648164749146} 08/31/2021 03:27:42 - INFO - __main__ - Step 78526: {'lr': 0.00023660688520311734, 'samples': 15076992, 'steps': 78525, 'loss/train': 1.4635884761810303} 08/31/2021 03:27:43 - INFO - __main__ - Step 78527: {'lr': 0.00023660158608245998, 'samples': 15077184, 'steps': 78526, 'loss/train': 0.9064218401908875} 08/31/2021 03:27:43 - INFO - __main__ - Step 78528: {'lr': 0.00023659628696783976, 'samples': 15077376, 'steps': 78527, 'loss/train': 0.957645058631897} 08/31/2021 03:27:43 - INFO - __main__ - Step 78529: {'lr': 0.000236590987859259, 'samples': 15077568, 'steps': 78528, 'loss/train': 1.2960752248764038} 08/31/2021 03:27:44 - INFO - __main__ - Step 78530: {'lr': 0.00023658568875672015, 'samples': 15077760, 'steps': 78529, 'loss/train': 0.5853579044342041} 08/31/2021 03:27:45 - INFO - __main__ - Step 78531: {'lr': 0.0002365803896602256, 'samples': 15077952, 'steps': 78530, 'loss/train': 0.7802433967590332} 08/31/2021 03:27:46 - INFO - __main__ - Step 78532: {'lr': 0.0002365750905697777, 'samples': 15078144, 'steps': 78531, 'loss/train': 1.323809027671814} 08/31/2021 03:27:46 - INFO - __main__ - Step 78533: {'lr': 0.00023656979148537884, 'samples': 15078336, 'steps': 78532, 'loss/train': 0.9363734126091003} 08/31/2021 03:27:46 - INFO - __main__ - Step 78534: {'lr': 0.00023656449240703144, 'samples': 15078528, 'steps': 78533, 'loss/train': 1.0209599733352661} 08/31/2021 03:27:47 - INFO - __main__ - Step 78535: {'lr': 0.0002365591933347379, 'samples': 15078720, 'steps': 78534, 'loss/train': 1.735117793083191} 08/31/2021 03:27:47 - INFO - __main__ - Step 78536: {'lr': 0.00023655389426850066, 'samples': 15078912, 'steps': 78535, 'loss/train': 1.3801189661026} 08/31/2021 03:27:49 - INFO - __main__ - Step 78537: {'lr': 0.00023654859520832195, 'samples': 15079104, 'steps': 78536, 'loss/train': 1.3955005407333374} 08/31/2021 03:27:49 - INFO - __main__ - Step 78538: {'lr': 0.0002365432961542042, 'samples': 15079296, 'steps': 78537, 'loss/train': 1.1291884183883667} 08/31/2021 03:27:49 - INFO - __main__ - Step 78539: {'lr': 0.00023653799710614983, 'samples': 15079488, 'steps': 78538, 'loss/train': 1.449708104133606} 08/31/2021 03:27:50 - INFO - __main__ - Step 78540: {'lr': 0.00023653269806416126, 'samples': 15079680, 'steps': 78539, 'loss/train': 1.4127713441848755} 08/31/2021 03:27:50 - INFO - __main__ - Step 78541: {'lr': 0.00023652739902824084, 'samples': 15079872, 'steps': 78540, 'loss/train': 0.20523667335510254} 08/31/2021 03:27:52 - INFO - __main__ - Step 78542: {'lr': 0.00023652209999839094, 'samples': 15080064, 'steps': 78541, 'loss/train': 1.1750177145004272} 08/31/2021 03:27:52 - INFO - __main__ - Step 78543: {'lr': 0.000236516800974614, 'samples': 15080256, 'steps': 78542, 'loss/train': 1.5543080568313599} 08/31/2021 03:27:53 - INFO - __main__ - Step 78544: {'lr': 0.00023651150195691238, 'samples': 15080448, 'steps': 78543, 'loss/train': 1.3476004600524902} 08/31/2021 03:27:53 - INFO - __main__ - Step 78545: {'lr': 0.00023650620294528847, 'samples': 15080640, 'steps': 78544, 'loss/train': 1.0105849504470825} 08/31/2021 03:27:53 - INFO - __main__ - Step 78546: {'lr': 0.00023650090393974467, 'samples': 15080832, 'steps': 78545, 'loss/train': 0.9778368473052979} 08/31/2021 03:27:55 - INFO - __main__ - Step 78547: {'lr': 0.0002364956049402833, 'samples': 15081024, 'steps': 78546, 'loss/train': 1.7647502422332764} 08/31/2021 03:27:55 - INFO - __main__ - Step 78548: {'lr': 0.00023649030594690684, 'samples': 15081216, 'steps': 78547, 'loss/train': 1.306663990020752} 08/31/2021 03:27:56 - INFO - __main__ - Step 78549: {'lr': 0.00023648500695961776, 'samples': 15081408, 'steps': 78548, 'loss/train': 1.336791753768921} 08/31/2021 03:27:56 - INFO - __main__ - Step 78550: {'lr': 0.00023647970797841818, 'samples': 15081600, 'steps': 78549, 'loss/train': 3.8234639167785645} 08/31/2021 03:27:56 - INFO - __main__ - Step 78551: {'lr': 0.00023647440900331068, 'samples': 15081792, 'steps': 78550, 'loss/train': 1.024324655532837} 08/31/2021 03:27:58 - INFO - __main__ - Step 78552: {'lr': 0.00023646911003429757, 'samples': 15081984, 'steps': 78551, 'loss/train': 1.3958020210266113} 08/31/2021 03:27:59 - INFO - __main__ - Step 78553: {'lr': 0.0002364638110713813, 'samples': 15082176, 'steps': 78552, 'loss/train': 1.152498483657837} 08/31/2021 03:27:59 - INFO - __main__ - Step 78554: {'lr': 0.0002364585121145642, 'samples': 15082368, 'steps': 78553, 'loss/train': 1.3838518857955933} 08/31/2021 03:27:59 - INFO - __main__ - Step 78555: {'lr': 0.0002364532131638487, 'samples': 15082560, 'steps': 78554, 'loss/train': 0.8174152970314026} 08/31/2021 03:28:00 - INFO - __main__ - Step 78556: {'lr': 0.00023644791421923716, 'samples': 15082752, 'steps': 78555, 'loss/train': 0.17644935846328735} 08/31/2021 03:28:01 - INFO - __main__ - Step 78557: {'lr': 0.000236442615280732, 'samples': 15082944, 'steps': 78556, 'loss/train': 0.773800253868103} 08/31/2021 03:28:02 - INFO - __main__ - Step 78558: {'lr': 0.00023643731634833556, 'samples': 15083136, 'steps': 78557, 'loss/train': 1.231411337852478} 08/31/2021 03:28:02 - INFO - __main__ - Step 78559: {'lr': 0.00023643201742205028, 'samples': 15083328, 'steps': 78558, 'loss/train': 0.4378577470779419} 08/31/2021 03:28:03 - INFO - __main__ - Step 78560: {'lr': 0.00023642671850187852, 'samples': 15083520, 'steps': 78559, 'loss/train': 1.3443108797073364} 08/31/2021 03:28:03 - INFO - __main__ - Step 78561: {'lr': 0.0002364214195878227, 'samples': 15083712, 'steps': 78560, 'loss/train': 1.4241338968276978} 08/31/2021 03:28:03 - INFO - __main__ - Step 78562: {'lr': 0.00023641612067988512, 'samples': 15083904, 'steps': 78561, 'loss/train': 1.519288420677185} 08/31/2021 03:28:05 - INFO - __main__ - Step 78563: {'lr': 0.00023641082177806836, 'samples': 15084096, 'steps': 78562, 'loss/train': 0.3114992678165436} 08/31/2021 03:28:06 - INFO - __main__ - Step 78564: {'lr': 0.00023640552288237458, 'samples': 15084288, 'steps': 78563, 'loss/train': 1.4691439867019653} 08/31/2021 03:28:06 - INFO - __main__ - Step 78565: {'lr': 0.00023640022399280626, 'samples': 15084480, 'steps': 78564, 'loss/train': 0.7591561079025269} 08/31/2021 03:28:06 - INFO - __main__ - Step 78566: {'lr': 0.00023639492510936575, 'samples': 15084672, 'steps': 78565, 'loss/train': 1.4933851957321167} 08/31/2021 03:28:07 - INFO - __main__ - Step 78567: {'lr': 0.0002363896262320555, 'samples': 15084864, 'steps': 78566, 'loss/train': 1.139658808708191} 08/31/2021 03:28:08 - INFO - __main__ - Step 78568: {'lr': 0.0002363843273608779, 'samples': 15085056, 'steps': 78567, 'loss/train': 1.7174804210662842} 08/31/2021 03:28:09 - INFO - __main__ - Step 78569: {'lr': 0.0002363790284958353, 'samples': 15085248, 'steps': 78568, 'loss/train': 1.3598103523254395} 08/31/2021 03:28:09 - INFO - __main__ - Step 78570: {'lr': 0.00023637372963693007, 'samples': 15085440, 'steps': 78569, 'loss/train': 0.2979290187358856} 08/31/2021 03:28:09 - INFO - __main__ - Step 78571: {'lr': 0.00023636843078416464, 'samples': 15085632, 'steps': 78570, 'loss/train': 1.2325228452682495} 08/31/2021 03:28:10 - INFO - __main__ - Step 78572: {'lr': 0.00023636313193754142, 'samples': 15085824, 'steps': 78571, 'loss/train': 1.5870617628097534} 08/31/2021 03:28:11 - INFO - __main__ - Step 78573: {'lr': 0.00023635783309706272, 'samples': 15086016, 'steps': 78572, 'loss/train': 1.6563736200332642} 08/31/2021 03:28:12 - INFO - __main__ - Step 78574: {'lr': 0.00023635253426273098, 'samples': 15086208, 'steps': 78573, 'loss/train': 0.8844487071037292} 08/31/2021 03:28:12 - INFO - __main__ - Step 78575: {'lr': 0.0002363472354345486, 'samples': 15086400, 'steps': 78574, 'loss/train': 1.6666873693466187} 08/31/2021 03:28:12 - INFO - __main__ - Step 78576: {'lr': 0.00023634193661251803, 'samples': 15086592, 'steps': 78575, 'loss/train': 0.818388819694519} 08/31/2021 03:28:13 - INFO - __main__ - Step 78577: {'lr': 0.00023633663779664148, 'samples': 15086784, 'steps': 78576, 'loss/train': 1.1326732635498047} 08/31/2021 03:28:14 - INFO - __main__ - Step 78578: {'lr': 0.0002363313389869214, 'samples': 15086976, 'steps': 78577, 'loss/train': 0.5408551692962646} 08/31/2021 03:28:15 - INFO - __main__ - Step 78579: {'lr': 0.00023632604018336025, 'samples': 15087168, 'steps': 78578, 'loss/train': 0.03250495344400406} 08/31/2021 03:28:15 - INFO - __main__ - Step 78580: {'lr': 0.00023632074138596034, 'samples': 15087360, 'steps': 78579, 'loss/train': 0.023437591269612312} 08/31/2021 03:28:16 - INFO - __main__ - Step 78581: {'lr': 0.00023631544259472413, 'samples': 15087552, 'steps': 78580, 'loss/train': 1.1563252210617065} 08/31/2021 03:28:16 - INFO - __main__ - Step 78582: {'lr': 0.00023631014380965393, 'samples': 15087744, 'steps': 78581, 'loss/train': 1.1209362745285034} 08/31/2021 03:28:16 - INFO - __main__ - Step 78583: {'lr': 0.0002363048450307522, 'samples': 15087936, 'steps': 78582, 'loss/train': 1.33039128780365} 08/31/2021 03:28:18 - INFO - __main__ - Step 78584: {'lr': 0.00023629954625802127, 'samples': 15088128, 'steps': 78583, 'loss/train': 1.4521137475967407} 08/31/2021 03:28:19 - INFO - __main__ - Step 78585: {'lr': 0.00023629424749146356, 'samples': 15088320, 'steps': 78584, 'loss/train': 1.1043955087661743} 08/31/2021 03:28:19 - INFO - __main__ - Step 78586: {'lr': 0.00023628894873108146, 'samples': 15088512, 'steps': 78585, 'loss/train': 0.999223530292511} 08/31/2021 03:28:19 - INFO - __main__ - Step 78587: {'lr': 0.00023628364997687733, 'samples': 15088704, 'steps': 78586, 'loss/train': 1.5383226871490479} 08/31/2021 03:28:20 - INFO - __main__ - Step 78588: {'lr': 0.0002362783512288536, 'samples': 15088896, 'steps': 78587, 'loss/train': 0.8235593438148499} 08/31/2021 03:28:21 - INFO - __main__ - Step 78589: {'lr': 0.00023627305248701268, 'samples': 15089088, 'steps': 78588, 'loss/train': 1.245701551437378} 08/31/2021 03:28:22 - INFO - __main__ - Step 78590: {'lr': 0.0002362677537513569, 'samples': 15089280, 'steps': 78589, 'loss/train': 1.283943772315979} 08/31/2021 03:28:22 - INFO - __main__ - Step 78591: {'lr': 0.00023626245502188863, 'samples': 15089472, 'steps': 78590, 'loss/train': 1.185682773590088} 08/31/2021 03:28:22 - INFO - __main__ - Step 78592: {'lr': 0.00023625715629861026, 'samples': 15089664, 'steps': 78591, 'loss/train': 1.1363637447357178} 08/31/2021 03:28:23 - INFO - __main__ - Step 78593: {'lr': 0.00023625185758152417, 'samples': 15089856, 'steps': 78592, 'loss/train': 0.33297836780548096} 08/31/2021 03:28:23 - INFO - __main__ - Step 78594: {'lr': 0.00023624655887063284, 'samples': 15090048, 'steps': 78593, 'loss/train': 1.5455914735794067} 08/31/2021 03:28:24 - INFO - __main__ - Step 78595: {'lr': 0.0002362412601659386, 'samples': 15090240, 'steps': 78594, 'loss/train': 0.24215373396873474} 08/31/2021 03:28:25 - INFO - __main__ - Step 78596: {'lr': 0.0002362359614674438, 'samples': 15090432, 'steps': 78595, 'loss/train': 1.1927300691604614} 08/31/2021 03:28:25 - INFO - __main__ - Step 78597: {'lr': 0.00023623066277515088, 'samples': 15090624, 'steps': 78596, 'loss/train': 1.2716182470321655} 08/31/2021 03:28:26 - INFO - __main__ - Step 78598: {'lr': 0.0002362253640890622, 'samples': 15090816, 'steps': 78597, 'loss/train': 1.3764986991882324} 08/31/2021 03:28:26 - INFO - __main__ - Step 78599: {'lr': 0.00023622006540918017, 'samples': 15091008, 'steps': 78598, 'loss/train': 0.32814833521842957} 08/31/2021 03:28:28 - INFO - __main__ - Step 78600: {'lr': 0.0002362147667355072, 'samples': 15091200, 'steps': 78599, 'loss/train': 1.3033725023269653} 08/31/2021 03:28:28 - INFO - __main__ - Step 78601: {'lr': 0.00023620946806804561, 'samples': 15091392, 'steps': 78600, 'loss/train': 1.2793684005737305} 08/31/2021 03:28:28 - INFO - __main__ - Step 78602: {'lr': 0.0002362041694067978, 'samples': 15091584, 'steps': 78601, 'loss/train': 0.06514021009206772} 08/31/2021 03:28:29 - INFO - __main__ - Step 78603: {'lr': 0.00023619887075176628, 'samples': 15091776, 'steps': 78602, 'loss/train': 2.2589714527130127} 08/31/2021 03:28:29 - INFO - __main__ - Step 78604: {'lr': 0.00023619357210295325, 'samples': 15091968, 'steps': 78603, 'loss/train': 1.2729607820510864} 08/31/2021 03:28:31 - INFO - __main__ - Step 78605: {'lr': 0.00023618827346036118, 'samples': 15092160, 'steps': 78604, 'loss/train': 1.1721326112747192} 08/31/2021 03:28:31 - INFO - __main__ - Step 78606: {'lr': 0.00023618297482399248, 'samples': 15092352, 'steps': 78605, 'loss/train': 1.4698584079742432} 08/31/2021 03:28:32 - INFO - __main__ - Step 78607: {'lr': 0.0002361776761938495, 'samples': 15092544, 'steps': 78606, 'loss/train': 1.494338035583496} 08/31/2021 03:28:32 - INFO - __main__ - Step 78608: {'lr': 0.00023617237756993464, 'samples': 15092736, 'steps': 78607, 'loss/train': 0.8415824770927429} 08/31/2021 03:28:32 - INFO - __main__ - Step 78609: {'lr': 0.00023616707895225033, 'samples': 15092928, 'steps': 78608, 'loss/train': 1.742681622505188} 08/31/2021 03:28:34 - INFO - __main__ - Step 78610: {'lr': 0.00023616178034079887, 'samples': 15093120, 'steps': 78609, 'loss/train': 0.03198622167110443} 08/31/2021 03:28:34 - INFO - __main__ - Step 78611: {'lr': 0.00023615648173558277, 'samples': 15093312, 'steps': 78610, 'loss/train': 1.3111900091171265} 08/31/2021 03:28:35 - INFO - __main__ - Step 78612: {'lr': 0.0002361511831366043, 'samples': 15093504, 'steps': 78611, 'loss/train': 1.304559350013733} 08/31/2021 03:28:35 - INFO - __main__ - Step 78613: {'lr': 0.0002361458845438659, 'samples': 15093696, 'steps': 78612, 'loss/train': 1.4148002862930298} 08/31/2021 03:28:35 - INFO - __main__ - Step 78614: {'lr': 0.00023614058595736992, 'samples': 15093888, 'steps': 78613, 'loss/train': 1.2740110158920288} 08/31/2021 03:28:37 - INFO - __main__ - Step 78615: {'lr': 0.00023613528737711882, 'samples': 15094080, 'steps': 78614, 'loss/train': 1.1456139087677002} 08/31/2021 03:28:38 - INFO - __main__ - Step 78616: {'lr': 0.00023612998880311492, 'samples': 15094272, 'steps': 78615, 'loss/train': 1.2469598054885864} 08/31/2021 03:28:38 - INFO - __main__ - Step 78617: {'lr': 0.0002361246902353607, 'samples': 15094464, 'steps': 78616, 'loss/train': 1.695272445678711} 08/31/2021 03:28:39 - INFO - __main__ - Step 78618: {'lr': 0.0002361193916738584, 'samples': 15094656, 'steps': 78617, 'loss/train': 1.2856706380844116} 08/31/2021 03:28:39 - INFO - __main__ - Step 78619: {'lr': 0.0002361140931186105, 'samples': 15094848, 'steps': 78618, 'loss/train': 1.4257949590682983} 08/31/2021 03:28:41 - INFO - __main__ - Step 78620: {'lr': 0.0002361087945696194, 'samples': 15095040, 'steps': 78619, 'loss/train': 1.2647918462753296} 08/31/2021 03:28:41 - INFO - __main__ - Step 78621: {'lr': 0.00023610349602688744, 'samples': 15095232, 'steps': 78620, 'loss/train': 1.0401034355163574} 08/31/2021 03:28:42 - INFO - __main__ - Step 78622: {'lr': 0.00023609819749041707, 'samples': 15095424, 'steps': 78621, 'loss/train': 0.8886300921440125} 08/31/2021 03:28:42 - INFO - __main__ - Step 78623: {'lr': 0.00023609289896021064, 'samples': 15095616, 'steps': 78622, 'loss/train': 0.1696263998746872} 08/31/2021 03:28:42 - INFO - __main__ - Step 78624: {'lr': 0.00023608760043627048, 'samples': 15095808, 'steps': 78623, 'loss/train': 1.6909140348434448} 08/31/2021 03:28:43 - INFO - __main__ - Step 78625: {'lr': 0.00023608230191859907, 'samples': 15096000, 'steps': 78624, 'loss/train': 1.1955780982971191} 08/31/2021 03:28:44 - INFO - __main__ - Step 78626: {'lr': 0.00023607700340719874, 'samples': 15096192, 'steps': 78625, 'loss/train': 1.1638784408569336} 08/31/2021 03:28:45 - INFO - __main__ - Step 78627: {'lr': 0.00023607170490207188, 'samples': 15096384, 'steps': 78626, 'loss/train': 1.0705755949020386} 08/31/2021 03:28:45 - INFO - __main__ - Step 78628: {'lr': 0.00023606640640322092, 'samples': 15096576, 'steps': 78627, 'loss/train': 1.3100905418395996} 08/31/2021 03:28:45 - INFO - __main__ - Step 78629: {'lr': 0.00023606110791064822, 'samples': 15096768, 'steps': 78628, 'loss/train': 1.3074893951416016} 08/31/2021 03:28:46 - INFO - __main__ - Step 78630: {'lr': 0.0002360558094243562, 'samples': 15096960, 'steps': 78629, 'loss/train': 1.5451362133026123} 08/31/2021 03:28:47 - INFO - __main__ - Step 78631: {'lr': 0.00023605051094434718, 'samples': 15097152, 'steps': 78630, 'loss/train': 0.9589002728462219} 08/31/2021 03:28:48 - INFO - __main__ - Step 78632: {'lr': 0.0002360452124706236, 'samples': 15097344, 'steps': 78631, 'loss/train': 0.9978488683700562} 08/31/2021 03:28:48 - INFO - __main__ - Step 78633: {'lr': 0.00023603991400318787, 'samples': 15097536, 'steps': 78632, 'loss/train': 1.5694620609283447} 08/31/2021 03:28:48 - INFO - __main__ - Step 78634: {'lr': 0.0002360346155420423, 'samples': 15097728, 'steps': 78633, 'loss/train': 1.2499195337295532} 08/31/2021 03:28:49 - INFO - __main__ - Step 78635: {'lr': 0.0002360293170871893, 'samples': 15097920, 'steps': 78634, 'loss/train': 1.49409019947052} 08/31/2021 03:28:50 - INFO - __main__ - Step 78636: {'lr': 0.00023602401863863126, 'samples': 15098112, 'steps': 78635, 'loss/train': 1.7734345197677612} 08/31/2021 03:28:51 - INFO - __main__ - Step 78637: {'lr': 0.00023601872019637061, 'samples': 15098304, 'steps': 78636, 'loss/train': 0.3903573155403137} 08/31/2021 03:28:51 - INFO - __main__ - Step 78638: {'lr': 0.0002360134217604097, 'samples': 15098496, 'steps': 78637, 'loss/train': 1.1490105390548706} 08/31/2021 03:28:51 - INFO - __main__ - Step 78639: {'lr': 0.00023600812333075092, 'samples': 15098688, 'steps': 78638, 'loss/train': 0.885682225227356} 08/31/2021 03:28:52 - INFO - __main__ - Step 78640: {'lr': 0.00023600282490739667, 'samples': 15098880, 'steps': 78639, 'loss/train': 0.9114589095115662} 08/31/2021 03:28:53 - INFO - __main__ - Step 78641: {'lr': 0.00023599752649034933, 'samples': 15099072, 'steps': 78640, 'loss/train': 1.3450675010681152} 08/31/2021 03:28:54 - INFO - __main__ - Step 78642: {'lr': 0.0002359922280796113, 'samples': 15099264, 'steps': 78641, 'loss/train': 1.3502486944198608} 08/31/2021 03:28:54 - INFO - __main__ - Step 78643: {'lr': 0.000235986929675185, 'samples': 15099456, 'steps': 78642, 'loss/train': 1.2594436407089233} 08/31/2021 03:28:55 - INFO - __main__ - Step 78644: {'lr': 0.00023598163127707276, 'samples': 15099648, 'steps': 78643, 'loss/train': 1.8906638622283936} 08/31/2021 03:28:55 - INFO - __main__ - Step 78645: {'lr': 0.00023597633288527695, 'samples': 15099840, 'steps': 78644, 'loss/train': 11.199014663696289} 08/31/2021 03:28:55 - INFO - __main__ - Step 78646: {'lr': 0.00023597103449979996, 'samples': 15100032, 'steps': 78645, 'loss/train': 1.256179690361023} 08/31/2021 03:28:57 - INFO - __main__ - Step 78647: {'lr': 0.00023596573612064424, 'samples': 15100224, 'steps': 78646, 'loss/train': 0.9907984733581543} 08/31/2021 03:28:58 - INFO - __main__ - Step 78648: {'lr': 0.00023596043774781213, 'samples': 15100416, 'steps': 78647, 'loss/train': 0.47054731845855713} 08/31/2021 03:28:58 - INFO - __main__ - Step 78649: {'lr': 0.000235955139381306, 'samples': 15100608, 'steps': 78648, 'loss/train': 0.792904794216156} 08/31/2021 03:28:58 - INFO - __main__ - Step 78650: {'lr': 0.00023594984102112828, 'samples': 15100800, 'steps': 78649, 'loss/train': 1.4442198276519775} 08/31/2021 03:28:59 - INFO - __main__ - Step 78651: {'lr': 0.0002359445426672814, 'samples': 15100992, 'steps': 78650, 'loss/train': 0.029730262234807014} 08/31/2021 03:28:59 - INFO - __main__ - Step 78652: {'lr': 0.00023593924431976763, 'samples': 15101184, 'steps': 78651, 'loss/train': 1.6393414735794067} 08/31/2021 03:29:01 - INFO - __main__ - Step 78653: {'lr': 0.00023593394597858945, 'samples': 15101376, 'steps': 78652, 'loss/train': 1.6422182321548462} 08/31/2021 03:29:01 - INFO - __main__ - Step 78654: {'lr': 0.0002359286476437492, 'samples': 15101568, 'steps': 78653, 'loss/train': 1.2325032949447632} 08/31/2021 03:29:02 - INFO - __main__ - Step 78655: {'lr': 0.00023592334931524928, 'samples': 15101760, 'steps': 78654, 'loss/train': 1.8060719966888428} 08/31/2021 03:29:02 - INFO - __main__ - Step 78656: {'lr': 0.00023591805099309207, 'samples': 15101952, 'steps': 78655, 'loss/train': 1.5352247953414917} 08/31/2021 03:29:03 - INFO - __main__ - Step 78657: {'lr': 0.00023591275267728014, 'samples': 15102144, 'steps': 78656, 'loss/train': 0.5991401076316833} 08/31/2021 03:29:03 - INFO - __main__ - Step 78658: {'lr': 0.00023590745436781552, 'samples': 15102336, 'steps': 78657, 'loss/train': 1.4882327318191528} 08/31/2021 03:29:04 - INFO - __main__ - Step 78659: {'lr': 0.00023590215606470084, 'samples': 15102528, 'steps': 78658, 'loss/train': 1.373469591140747} 08/31/2021 03:29:05 - INFO - __main__ - Step 78660: {'lr': 0.0002358968577679384, 'samples': 15102720, 'steps': 78659, 'loss/train': 1.162610411643982} 08/31/2021 03:29:05 - INFO - __main__ - Step 78661: {'lr': 0.00023589155947753064, 'samples': 15102912, 'steps': 78660, 'loss/train': 2.6567251682281494} 08/31/2021 03:29:06 - INFO - __main__ - Step 78662: {'lr': 0.00023588626119347991, 'samples': 15103104, 'steps': 78661, 'loss/train': 0.1355859637260437} 08/31/2021 03:29:06 - INFO - __main__ - Step 78663: {'lr': 0.0002358809629157886, 'samples': 15103296, 'steps': 78662, 'loss/train': 1.3405835628509521} 08/31/2021 03:29:07 - INFO - __main__ - Step 78664: {'lr': 0.00023587566464445915, 'samples': 15103488, 'steps': 78663, 'loss/train': 1.2486629486083984} 08/31/2021 03:29:08 - INFO - __main__ - Step 78665: {'lr': 0.00023587036637949389, 'samples': 15103680, 'steps': 78664, 'loss/train': 0.9781413674354553} 08/31/2021 03:29:08 - INFO - __main__ - Step 78666: {'lr': 0.0002358650681208952, 'samples': 15103872, 'steps': 78665, 'loss/train': 1.278095006942749} 08/31/2021 03:29:09 - INFO - __main__ - Step 78667: {'lr': 0.00023585976986866553, 'samples': 15104064, 'steps': 78666, 'loss/train': 1.6916571855545044} 08/31/2021 03:29:09 - INFO - __main__ - Step 78668: {'lr': 0.0002358544716228072, 'samples': 15104256, 'steps': 78667, 'loss/train': 1.374843955039978} 08/31/2021 03:29:11 - INFO - __main__ - Step 78669: {'lr': 0.00023584917338332264, 'samples': 15104448, 'steps': 78668, 'loss/train': 1.5265663862228394} 08/31/2021 03:29:12 - INFO - __main__ - Step 78670: {'lr': 0.00023584387515021433, 'samples': 15104640, 'steps': 78669, 'loss/train': 1.6726831197738647} 08/31/2021 03:29:12 - INFO - __main__ - Step 78671: {'lr': 0.00023583857692348445, 'samples': 15104832, 'steps': 78670, 'loss/train': 0.39106178283691406} 08/31/2021 03:29:12 - INFO - __main__ - Step 78672: {'lr': 0.00023583327870313548, 'samples': 15105024, 'steps': 78671, 'loss/train': 0.20960240066051483} 08/31/2021 03:29:13 - INFO - __main__ - Step 78673: {'lr': 0.0002358279804891698, 'samples': 15105216, 'steps': 78672, 'loss/train': 1.0659048557281494} 08/31/2021 03:29:14 - INFO - __main__ - Step 78674: {'lr': 0.00023582268228158985, 'samples': 15105408, 'steps': 78673, 'loss/train': 0.9692087769508362} 08/31/2021 03:29:15 - INFO - __main__ - Step 78675: {'lr': 0.00023581738408039797, 'samples': 15105600, 'steps': 78674, 'loss/train': 1.905779480934143} 08/31/2021 03:29:15 - INFO - __main__ - Step 78676: {'lr': 0.00023581208588559655, 'samples': 15105792, 'steps': 78675, 'loss/train': 0.07709140330553055} 08/31/2021 03:29:16 - INFO - __main__ - Step 78677: {'lr': 0.000235806787697188, 'samples': 15105984, 'steps': 78676, 'loss/train': 0.455724835395813} 08/31/2021 03:29:16 - INFO - __main__ - Step 78678: {'lr': 0.00023580148951517465, 'samples': 15106176, 'steps': 78677, 'loss/train': 1.2231156826019287} 08/31/2021 03:29:17 - INFO - __main__ - Step 78679: {'lr': 0.00023579619133955897, 'samples': 15106368, 'steps': 78678, 'loss/train': 1.3527581691741943} 08/31/2021 03:29:18 - INFO - __main__ - Step 78680: {'lr': 0.0002357908931703433, 'samples': 15106560, 'steps': 78679, 'loss/train': 1.4329166412353516} 08/31/2021 03:29:18 - INFO - __main__ - Step 78681: {'lr': 0.00023578559500753003, 'samples': 15106752, 'steps': 78680, 'loss/train': 1.1301939487457275} 08/31/2021 03:29:19 - INFO - __main__ - Step 78682: {'lr': 0.00023578029685112153, 'samples': 15106944, 'steps': 78681, 'loss/train': 1.30484139919281} 08/31/2021 03:29:19 - INFO - __main__ - Step 78683: {'lr': 0.00023577499870112024, 'samples': 15107136, 'steps': 78682, 'loss/train': 1.6286576986312866} 08/31/2021 03:29:20 - INFO - __main__ - Step 78684: {'lr': 0.0002357697005575286, 'samples': 15107328, 'steps': 78683, 'loss/train': 1.4577255249023438} 08/31/2021 03:29:21 - INFO - __main__ - Step 78685: {'lr': 0.00023576440242034885, 'samples': 15107520, 'steps': 78684, 'loss/train': 0.8039063215255737} 08/31/2021 03:29:21 - INFO - __main__ - Step 78686: {'lr': 0.00023575910428958342, 'samples': 15107712, 'steps': 78685, 'loss/train': 1.4943081140518188} 08/31/2021 03:29:22 - INFO - __main__ - Step 78687: {'lr': 0.0002357538061652347, 'samples': 15107904, 'steps': 78686, 'loss/train': 1.4660227298736572} 08/31/2021 03:29:22 - INFO - __main__ - Step 78688: {'lr': 0.0002357485080473051, 'samples': 15108096, 'steps': 78687, 'loss/train': 0.6813605427742004} 08/31/2021 03:29:22 - INFO - __main__ - Step 78689: {'lr': 0.000235743209935797, 'samples': 15108288, 'steps': 78688, 'loss/train': 1.386042833328247} 08/31/2021 03:29:24 - INFO - __main__ - Step 78690: {'lr': 0.0002357379118307128, 'samples': 15108480, 'steps': 78689, 'loss/train': 1.9815564155578613} 08/31/2021 03:29:24 - INFO - __main__ - Step 78691: {'lr': 0.00023573261373205487, 'samples': 15108672, 'steps': 78690, 'loss/train': 1.3207329511642456} 08/31/2021 03:29:25 - INFO - __main__ - Step 78692: {'lr': 0.0002357273156398256, 'samples': 15108864, 'steps': 78691, 'loss/train': 1.344741702079773} 08/31/2021 03:29:25 - INFO - __main__ - Step 78693: {'lr': 0.00023572201755402738, 'samples': 15109056, 'steps': 78692, 'loss/train': 1.0328017473220825} 08/31/2021 03:29:25 - INFO - __main__ - Step 78694: {'lr': 0.00023571671947466262, 'samples': 15109248, 'steps': 78693, 'loss/train': 1.482338547706604} 08/31/2021 03:29:27 - INFO - __main__ - Step 78695: {'lr': 0.00023571142140173365, 'samples': 15109440, 'steps': 78694, 'loss/train': 0.7073089480400085} 08/31/2021 03:29:28 - INFO - __main__ - Step 78696: {'lr': 0.00023570612333524295, 'samples': 15109632, 'steps': 78695, 'loss/train': 2.457475423812866} 08/31/2021 03:29:28 - INFO - __main__ - Step 78697: {'lr': 0.0002357008252751929, 'samples': 15109824, 'steps': 78696, 'loss/train': 0.9695630669593811} 08/31/2021 03:29:28 - INFO - __main__ - Step 78698: {'lr': 0.00023569552722158574, 'samples': 15110016, 'steps': 78697, 'loss/train': 1.3561513423919678} 08/31/2021 03:29:29 - INFO - __main__ - Step 78699: {'lr': 0.00023569022917442397, 'samples': 15110208, 'steps': 78698, 'loss/train': 0.7798616886138916} 08/31/2021 03:29:30 - INFO - __main__ - Step 78700: {'lr': 0.00023568493113371, 'samples': 15110400, 'steps': 78699, 'loss/train': 1.1420294046401978} 08/31/2021 03:29:31 - INFO - __main__ - Step 78701: {'lr': 0.0002356796330994461, 'samples': 15110592, 'steps': 78700, 'loss/train': 0.9031627774238586} 08/31/2021 03:29:31 - INFO - __main__ - Step 78702: {'lr': 0.00023567433507163478, 'samples': 15110784, 'steps': 78701, 'loss/train': 1.0360534191131592} 08/31/2021 03:29:31 - INFO - __main__ - Step 78703: {'lr': 0.00023566903705027836, 'samples': 15110976, 'steps': 78702, 'loss/train': 1.0157644748687744} 08/31/2021 03:29:32 - INFO - __main__ - Step 78704: {'lr': 0.0002356637390353793, 'samples': 15111168, 'steps': 78703, 'loss/train': 1.3419536352157593} 08/31/2021 03:29:32 - INFO - __main__ - Step 78705: {'lr': 0.0002356584410269399, 'samples': 15111360, 'steps': 78704, 'loss/train': 0.38128215074539185} 08/31/2021 03:29:34 - INFO - __main__ - Step 78706: {'lr': 0.0002356531430249626, 'samples': 15111552, 'steps': 78705, 'loss/train': 1.4898070096969604} 08/31/2021 03:29:34 - INFO - __main__ - Step 78707: {'lr': 0.00023564784502944975, 'samples': 15111744, 'steps': 78706, 'loss/train': 1.5793031454086304} 08/31/2021 03:29:34 - INFO - __main__ - Step 78708: {'lr': 0.00023564254704040377, 'samples': 15111936, 'steps': 78707, 'loss/train': 0.5538396835327148} 08/31/2021 03:29:35 - INFO - __main__ - Step 78709: {'lr': 0.00023563724905782704, 'samples': 15112128, 'steps': 78708, 'loss/train': 1.265931248664856} 08/31/2021 03:29:35 - INFO - __main__ - Step 78710: {'lr': 0.00023563195108172196, 'samples': 15112320, 'steps': 78709, 'loss/train': 1.30335533618927} 08/31/2021 03:29:37 - INFO - __main__ - Step 78711: {'lr': 0.00023562665311209098, 'samples': 15112512, 'steps': 78710, 'loss/train': 0.777033805847168} 08/31/2021 03:29:37 - INFO - __main__ - Step 78712: {'lr': 0.00023562135514893631, 'samples': 15112704, 'steps': 78711, 'loss/train': 1.1616872549057007} 08/31/2021 03:29:37 - INFO - __main__ - Step 78713: {'lr': 0.00023561605719226046, 'samples': 15112896, 'steps': 78712, 'loss/train': 1.4327266216278076} 08/31/2021 03:29:38 - INFO - __main__ - Step 78714: {'lr': 0.00023561075924206576, 'samples': 15113088, 'steps': 78713, 'loss/train': 0.17406649887561798} 08/31/2021 03:29:38 - INFO - __main__ - Step 78715: {'lr': 0.00023560546129835464, 'samples': 15113280, 'steps': 78714, 'loss/train': 1.1850875616073608} 08/31/2021 03:29:40 - INFO - __main__ - Step 78716: {'lr': 0.00023560016336112948, 'samples': 15113472, 'steps': 78715, 'loss/train': 1.2046548128128052} 08/31/2021 03:29:40 - INFO - __main__ - Step 78717: {'lr': 0.00023559486543039265, 'samples': 15113664, 'steps': 78716, 'loss/train': 1.6424871683120728} 08/31/2021 03:29:41 - INFO - __main__ - Step 78718: {'lr': 0.00023558956750614657, 'samples': 15113856, 'steps': 78717, 'loss/train': 0.8272214531898499} 08/31/2021 03:29:41 - INFO - __main__ - Step 78719: {'lr': 0.0002355842695883936, 'samples': 15114048, 'steps': 78718, 'loss/train': 0.45905259251594543} 08/31/2021 03:29:41 - INFO - __main__ - Step 78720: {'lr': 0.00023557897167713615, 'samples': 15114240, 'steps': 78719, 'loss/train': 0.04791594296693802} 08/31/2021 03:29:42 - INFO - __main__ - Step 78721: {'lr': 0.00023557367377237658, 'samples': 15114432, 'steps': 78720, 'loss/train': 0.9369577765464783} 08/31/2021 03:29:44 - INFO - __main__ - Step 78722: {'lr': 0.00023556837587411728, 'samples': 15114624, 'steps': 78721, 'loss/train': 0.02222016453742981} 08/31/2021 03:29:44 - INFO - __main__ - Step 78723: {'lr': 0.00023556307798236074, 'samples': 15114816, 'steps': 78722, 'loss/train': 0.21227788925170898} 08/31/2021 03:29:45 - INFO - __main__ - Step 78724: {'lr': 0.0002355577800971092, 'samples': 15115008, 'steps': 78723, 'loss/train': 0.21866905689239502} 08/31/2021 03:29:45 - INFO - __main__ - Step 78725: {'lr': 0.00023555248221836508, 'samples': 15115200, 'steps': 78724, 'loss/train': 1.3341025114059448} 08/31/2021 03:29:45 - INFO - __main__ - Step 78726: {'lr': 0.0002355471843461308, 'samples': 15115392, 'steps': 78725, 'loss/train': 1.298799991607666} 08/31/2021 03:29:47 - INFO - __main__ - Step 78727: {'lr': 0.0002355418864804087, 'samples': 15115584, 'steps': 78726, 'loss/train': 1.160805344581604} 08/31/2021 03:29:47 - INFO - __main__ - Step 78728: {'lr': 0.00023553658862120124, 'samples': 15115776, 'steps': 78727, 'loss/train': 1.1679325103759766} 08/31/2021 03:29:48 - INFO - __main__ - Step 78729: {'lr': 0.00023553129076851073, 'samples': 15115968, 'steps': 78728, 'loss/train': 1.5466073751449585} 08/31/2021 03:29:48 - INFO - __main__ - Step 78730: {'lr': 0.00023552599292233964, 'samples': 15116160, 'steps': 78729, 'loss/train': 1.3839668035507202} 08/31/2021 03:29:48 - INFO - __main__ - Step 78731: {'lr': 0.00023552069508269027, 'samples': 15116352, 'steps': 78730, 'loss/train': 0.7456579208374023} 08/31/2021 03:29:50 - INFO - __main__ - Step 78732: {'lr': 0.00023551539724956508, 'samples': 15116544, 'steps': 78731, 'loss/train': 1.6452271938323975} 08/31/2021 03:29:51 - INFO - __main__ - Step 78733: {'lr': 0.00023551009942296641, 'samples': 15116736, 'steps': 78732, 'loss/train': 1.5399448871612549} 08/31/2021 03:29:51 - INFO - __main__ - Step 78734: {'lr': 0.00023550480160289676, 'samples': 15116928, 'steps': 78733, 'loss/train': 0.8587362766265869} 08/31/2021 03:29:51 - INFO - __main__ - Step 78735: {'lr': 0.00023549950378935834, 'samples': 15117120, 'steps': 78734, 'loss/train': 0.44582945108413696} 08/31/2021 03:29:52 - INFO - __main__ - Step 78736: {'lr': 0.00023549420598235362, 'samples': 15117312, 'steps': 78735, 'loss/train': 1.523705005645752} 08/31/2021 03:29:52 - INFO - __main__ - Step 78737: {'lr': 0.00023548890818188498, 'samples': 15117504, 'steps': 78736, 'loss/train': 1.1844710111618042} 08/31/2021 03:29:54 - INFO - __main__ - Step 78738: {'lr': 0.00023548361038795487, 'samples': 15117696, 'steps': 78737, 'loss/train': 0.7262529730796814} 08/31/2021 03:29:54 - INFO - __main__ - Step 78739: {'lr': 0.00023547831260056556, 'samples': 15117888, 'steps': 78738, 'loss/train': 1.4762120246887207} 08/31/2021 03:29:54 - INFO - __main__ - Step 78740: {'lr': 0.00023547301481971952, 'samples': 15118080, 'steps': 78739, 'loss/train': 0.5791515707969666} 08/31/2021 03:29:55 - INFO - __main__ - Step 78741: {'lr': 0.0002354677170454191, 'samples': 15118272, 'steps': 78740, 'loss/train': 0.8695589303970337} 08/31/2021 03:29:55 - INFO - __main__ - Step 78742: {'lr': 0.00023546241927766673, 'samples': 15118464, 'steps': 78741, 'loss/train': 3.928424596786499} 08/31/2021 03:29:57 - INFO - __main__ - Step 78743: {'lr': 0.00023545712151646476, 'samples': 15118656, 'steps': 78742, 'loss/train': 1.3246315717697144} 08/31/2021 03:29:57 - INFO - __main__ - Step 78744: {'lr': 0.00023545182376181556, 'samples': 15118848, 'steps': 78743, 'loss/train': 0.4983314573764801} 08/31/2021 03:29:58 - INFO - __main__ - Step 78745: {'lr': 0.00023544652601372162, 'samples': 15119040, 'steps': 78744, 'loss/train': 1.2712147235870361} 08/31/2021 03:29:58 - INFO - __main__ - Step 78746: {'lr': 0.0002354412282721852, 'samples': 15119232, 'steps': 78745, 'loss/train': 0.017063552513718605} 08/31/2021 03:29:58 - INFO - __main__ - Step 78747: {'lr': 0.00023543593053720871, 'samples': 15119424, 'steps': 78746, 'loss/train': 0.05654957890510559} 08/31/2021 03:29:59 - INFO - __main__ - Step 78748: {'lr': 0.00023543063280879458, 'samples': 15119616, 'steps': 78747, 'loss/train': 0.048036348074674606} 08/31/2021 03:30:00 - INFO - __main__ - Step 78749: {'lr': 0.0002354253350869452, 'samples': 15119808, 'steps': 78748, 'loss/train': 0.8961228728294373} 08/31/2021 03:30:01 - INFO - __main__ - Step 78750: {'lr': 0.00023542003737166294, 'samples': 15120000, 'steps': 78749, 'loss/train': 0.9403883218765259} 08/31/2021 03:30:01 - INFO - __main__ - Step 78751: {'lr': 0.0002354147396629502, 'samples': 15120192, 'steps': 78750, 'loss/train': 0.9860718250274658} 08/31/2021 03:30:02 - INFO - __main__ - Step 78752: {'lr': 0.00023540944196080932, 'samples': 15120384, 'steps': 78751, 'loss/train': 1.23805832862854} 08/31/2021 03:30:02 - INFO - __main__ - Step 78753: {'lr': 0.00023540414426524272, 'samples': 15120576, 'steps': 78752, 'loss/train': 1.31156325340271} 08/31/2021 03:30:03 - INFO - __main__ - Step 78754: {'lr': 0.00023539884657625278, 'samples': 15120768, 'steps': 78753, 'loss/train': 1.9000074863433838} 08/31/2021 03:30:04 - INFO - __main__ - Step 78755: {'lr': 0.00023539354889384192, 'samples': 15120960, 'steps': 78754, 'loss/train': 1.5766350030899048} 08/31/2021 03:30:04 - INFO - __main__ - Step 78756: {'lr': 0.00023538825121801254, 'samples': 15121152, 'steps': 78755, 'loss/train': 1.3043897151947021} 08/31/2021 03:30:05 - INFO - __main__ - Step 78757: {'lr': 0.00023538295354876693, 'samples': 15121344, 'steps': 78756, 'loss/train': 1.214754581451416} 08/31/2021 03:30:05 - INFO - __main__ - Step 78758: {'lr': 0.00023537765588610754, 'samples': 15121536, 'steps': 78757, 'loss/train': 0.6658387780189514} 08/31/2021 03:30:07 - INFO - __main__ - Step 78759: {'lr': 0.00023537235823003678, 'samples': 15121728, 'steps': 78758, 'loss/train': 0.9044598937034607} 08/31/2021 03:30:07 - INFO - __main__ - Step 78760: {'lr': 0.00023536706058055695, 'samples': 15121920, 'steps': 78759, 'loss/train': 0.2977259159088135} 08/31/2021 03:30:07 - INFO - __main__ - Step 78761: {'lr': 0.00023536176293767057, 'samples': 15122112, 'steps': 78760, 'loss/train': 0.7925614714622498} 08/31/2021 03:30:08 - INFO - __main__ - Step 78762: {'lr': 0.00023535646530137988, 'samples': 15122304, 'steps': 78761, 'loss/train': 0.9121683835983276} 08/31/2021 03:30:08 - INFO - __main__ - Step 78763: {'lr': 0.00023535116767168737, 'samples': 15122496, 'steps': 78762, 'loss/train': 0.03750352934002876} 08/31/2021 03:30:10 - INFO - __main__ - Step 78764: {'lr': 0.00023534587004859548, 'samples': 15122688, 'steps': 78763, 'loss/train': 1.4442247152328491} 08/31/2021 03:30:10 - INFO - __main__ - Step 78765: {'lr': 0.00023534057243210644, 'samples': 15122880, 'steps': 78764, 'loss/train': 0.10214782506227493} 08/31/2021 03:30:11 - INFO - __main__ - Step 78766: {'lr': 0.0002353352748222227, 'samples': 15123072, 'steps': 78765, 'loss/train': 0.04114236310124397} 08/31/2021 03:30:11 - INFO - __main__ - Step 78767: {'lr': 0.0002353299772189467, 'samples': 15123264, 'steps': 78766, 'loss/train': 1.4873944520950317} 08/31/2021 03:30:11 - INFO - __main__ - Step 78768: {'lr': 0.00023532467962228076, 'samples': 15123456, 'steps': 78767, 'loss/train': 1.460338830947876} 08/31/2021 03:30:13 - INFO - __main__ - Step 78769: {'lr': 0.0002353193820322273, 'samples': 15123648, 'steps': 78768, 'loss/train': 2.070916175842285} 08/31/2021 03:30:14 - INFO - __main__ - Step 78770: {'lr': 0.00023531408444878868, 'samples': 15123840, 'steps': 78769, 'loss/train': 0.5539323687553406} 08/31/2021 03:30:14 - INFO - __main__ - Step 78771: {'lr': 0.00023530878687196734, 'samples': 15124032, 'steps': 78770, 'loss/train': 1.182344675064087} 08/31/2021 03:30:14 - INFO - __main__ - Step 78772: {'lr': 0.0002353034893017656, 'samples': 15124224, 'steps': 78771, 'loss/train': 0.037891898304224014} 08/31/2021 03:30:15 - INFO - __main__ - Step 78773: {'lr': 0.00023529819173818587, 'samples': 15124416, 'steps': 78772, 'loss/train': 0.019090889021754265} 08/31/2021 03:30:15 - INFO - __main__ - Step 78774: {'lr': 0.00023529289418123056, 'samples': 15124608, 'steps': 78773, 'loss/train': 1.0401537418365479} 08/31/2021 03:30:15 - INFO - __main__ - Step 78775: {'lr': 0.00023528759663090209, 'samples': 15124800, 'steps': 78774, 'loss/train': 0.8655610084533691} 08/31/2021 03:30:17 - INFO - __main__ - Step 78776: {'lr': 0.00023528229908720272, 'samples': 15124992, 'steps': 78775, 'loss/train': 1.7207292318344116} 08/31/2021 03:30:17 - INFO - __main__ - Step 78777: {'lr': 0.00023527700155013498, 'samples': 15125184, 'steps': 78776, 'loss/train': 0.753837525844574} 08/31/2021 03:30:18 - INFO - __main__ - Step 78778: {'lr': 0.00023527170401970126, 'samples': 15125376, 'steps': 78777, 'loss/train': 1.4615461826324463} 08/31/2021 03:30:18 - INFO - __main__ - Step 78779: {'lr': 0.00023526640649590384, 'samples': 15125568, 'steps': 78778, 'loss/train': 1.390011191368103} 08/31/2021 03:30:18 - INFO - __main__ - Step 78780: {'lr': 0.0002352611089787451, 'samples': 15125760, 'steps': 78779, 'loss/train': 1.319006323814392} 08/31/2021 03:30:20 - INFO - __main__ - Step 78781: {'lr': 0.00023525581146822746, 'samples': 15125952, 'steps': 78780, 'loss/train': 1.2342840433120728} 08/31/2021 03:30:21 - INFO - __main__ - Step 78782: {'lr': 0.00023525051396435336, 'samples': 15126144, 'steps': 78781, 'loss/train': 1.6332727670669556} 08/31/2021 03:30:21 - INFO - __main__ - Step 78783: {'lr': 0.00023524521646712515, 'samples': 15126336, 'steps': 78782, 'loss/train': 1.1590248346328735} 08/31/2021 03:30:21 - INFO - __main__ - Step 78784: {'lr': 0.00023523991897654524, 'samples': 15126528, 'steps': 78783, 'loss/train': 1.3861210346221924} 08/31/2021 03:30:22 - INFO - __main__ - Step 78785: {'lr': 0.00023523462149261593, 'samples': 15126720, 'steps': 78784, 'loss/train': 0.7314127683639526} 08/31/2021 03:30:23 - INFO - __main__ - Step 78786: {'lr': 0.00023522932401533973, 'samples': 15126912, 'steps': 78785, 'loss/train': 1.7369694709777832} 08/31/2021 03:30:24 - INFO - __main__ - Step 78787: {'lr': 0.00023522402654471895, 'samples': 15127104, 'steps': 78786, 'loss/train': 1.1069660186767578} 08/31/2021 03:30:24 - INFO - __main__ - Step 78788: {'lr': 0.00023521872908075598, 'samples': 15127296, 'steps': 78787, 'loss/train': 1.0600448846817017} 08/31/2021 03:30:24 - INFO - __main__ - Step 78789: {'lr': 0.00023521343162345322, 'samples': 15127488, 'steps': 78788, 'loss/train': 1.0937812328338623} 08/31/2021 03:30:25 - INFO - __main__ - Step 78790: {'lr': 0.0002352081341728131, 'samples': 15127680, 'steps': 78789, 'loss/train': 1.0190924406051636} 08/31/2021 03:30:26 - INFO - __main__ - Step 78791: {'lr': 0.00023520283672883802, 'samples': 15127872, 'steps': 78790, 'loss/train': 1.342736005783081} 08/31/2021 03:30:27 - INFO - __main__ - Step 78792: {'lr': 0.00023519753929153022, 'samples': 15128064, 'steps': 78791, 'loss/train': 1.050524353981018} 08/31/2021 03:30:27 - INFO - __main__ - Step 78793: {'lr': 0.00023519224186089222, 'samples': 15128256, 'steps': 78792, 'loss/train': 1.3048832416534424} 08/31/2021 03:30:27 - INFO - __main__ - Step 78794: {'lr': 0.00023518694443692634, 'samples': 15128448, 'steps': 78793, 'loss/train': 2.036010265350342} 08/31/2021 03:30:28 - INFO - __main__ - Step 78795: {'lr': 0.000235181647019635, 'samples': 15128640, 'steps': 78794, 'loss/train': 1.094227910041809} 08/31/2021 03:30:29 - INFO - __main__ - Step 78796: {'lr': 0.00023517634960902058, 'samples': 15128832, 'steps': 78795, 'loss/train': 0.544616162776947} 08/31/2021 03:30:30 - INFO - __main__ - Step 78797: {'lr': 0.00023517105220508544, 'samples': 15129024, 'steps': 78796, 'loss/train': 1.2869255542755127} 08/31/2021 03:30:30 - INFO - __main__ - Step 78798: {'lr': 0.00023516575480783203, 'samples': 15129216, 'steps': 78797, 'loss/train': 1.7784404754638672} 08/31/2021 03:30:30 - INFO - __main__ - Step 78799: {'lr': 0.0002351604574172627, 'samples': 15129408, 'steps': 78798, 'loss/train': 1.048302412033081} 08/31/2021 03:30:31 - INFO - __main__ - Step 78800: {'lr': 0.0002351551600333798, 'samples': 15129600, 'steps': 78799, 'loss/train': 0.19619984924793243} 08/31/2021 03:30:32 - INFO - __main__ - Step 78801: {'lr': 0.0002351498626561858, 'samples': 15129792, 'steps': 78800, 'loss/train': 1.0515486001968384} 08/31/2021 03:30:33 - INFO - __main__ - Step 78802: {'lr': 0.00023514456528568305, 'samples': 15129984, 'steps': 78801, 'loss/train': 1.7602746486663818} 08/31/2021 03:30:33 - INFO - __main__ - Step 78803: {'lr': 0.0002351392679218739, 'samples': 15130176, 'steps': 78802, 'loss/train': 1.0746229887008667} 08/31/2021 03:30:33 - INFO - __main__ - Step 78804: {'lr': 0.00023513397056476078, 'samples': 15130368, 'steps': 78803, 'loss/train': 1.200797200202942} 08/31/2021 03:30:34 - INFO - __main__ - Step 78805: {'lr': 0.00023512867321434617, 'samples': 15130560, 'steps': 78804, 'loss/train': 1.5780922174453735} 08/31/2021 03:30:34 - INFO - __main__ - Step 78806: {'lr': 0.00023512337587063223, 'samples': 15130752, 'steps': 78805, 'loss/train': 1.9186643362045288} 08/31/2021 03:30:36 - INFO - __main__ - Step 78807: {'lr': 0.00023511807853362145, 'samples': 15130944, 'steps': 78806, 'loss/train': 1.0794410705566406} 08/31/2021 03:30:36 - INFO - __main__ - Step 78808: {'lr': 0.00023511278120331628, 'samples': 15131136, 'steps': 78807, 'loss/train': 1.7946661710739136} 08/31/2021 03:30:36 - INFO - __main__ - Step 78809: {'lr': 0.00023510748387971903, 'samples': 15131328, 'steps': 78808, 'loss/train': 1.1994895935058594} 08/31/2021 03:30:37 - INFO - __main__ - Step 78810: {'lr': 0.00023510218656283213, 'samples': 15131520, 'steps': 78809, 'loss/train': 1.6145957708358765} 08/31/2021 03:30:37 - INFO - __main__ - Step 78811: {'lr': 0.00023509688925265796, 'samples': 15131712, 'steps': 78810, 'loss/train': 0.9227548837661743} 08/31/2021 03:30:39 - INFO - __main__ - Step 78812: {'lr': 0.0002350915919491989, 'samples': 15131904, 'steps': 78811, 'loss/train': 1.192744255065918} 08/31/2021 03:30:39 - INFO - __main__ - Step 78813: {'lr': 0.00023508629465245735, 'samples': 15132096, 'steps': 78812, 'loss/train': 1.6533294916152954} 08/31/2021 03:30:39 - INFO - __main__ - Step 78814: {'lr': 0.00023508099736243565, 'samples': 15132288, 'steps': 78813, 'loss/train': 1.2473676204681396} 08/31/2021 03:30:40 - INFO - __main__ - Step 78815: {'lr': 0.00023507570007913624, 'samples': 15132480, 'steps': 78814, 'loss/train': 1.607558012008667} 08/31/2021 03:30:40 - INFO - __main__ - Step 78816: {'lr': 0.0002350704028025615, 'samples': 15132672, 'steps': 78815, 'loss/train': 0.4310353696346283} 08/31/2021 03:30:42 - INFO - __main__ - Step 78817: {'lr': 0.0002350651055327138, 'samples': 15132864, 'steps': 78816, 'loss/train': 1.7212861776351929} 08/31/2021 03:30:42 - INFO - __main__ - Step 78818: {'lr': 0.00023505980826959565, 'samples': 15133056, 'steps': 78817, 'loss/train': 0.041205406188964844} 08/31/2021 03:30:43 - INFO - __main__ - Step 78819: {'lr': 0.00023505451101320918, 'samples': 15133248, 'steps': 78818, 'loss/train': 1.658638596534729} 08/31/2021 03:30:43 - INFO - __main__ - Step 78820: {'lr': 0.00023504921376355696, 'samples': 15133440, 'steps': 78819, 'loss/train': 1.7922509908676147} 08/31/2021 03:30:43 - INFO - __main__ - Step 78821: {'lr': 0.00023504391652064127, 'samples': 15133632, 'steps': 78820, 'loss/train': 2.529550552368164} 08/31/2021 03:30:45 - INFO - __main__ - Step 78822: {'lr': 0.00023503861928446463, 'samples': 15133824, 'steps': 78821, 'loss/train': 1.1300722360610962} 08/31/2021 03:30:45 - INFO - __main__ - Step 78823: {'lr': 0.00023503332205502932, 'samples': 15134016, 'steps': 78822, 'loss/train': 1.4426122903823853} 08/31/2021 03:30:46 - INFO - __main__ - Step 78824: {'lr': 0.00023502802483233776, 'samples': 15134208, 'steps': 78823, 'loss/train': 0.948233425617218} 08/31/2021 03:30:46 - INFO - __main__ - Step 78825: {'lr': 0.00023502272761639236, 'samples': 15134400, 'steps': 78824, 'loss/train': 1.3837192058563232} 08/31/2021 03:30:46 - INFO - __main__ - Step 78826: {'lr': 0.00023501743040719547, 'samples': 15134592, 'steps': 78825, 'loss/train': 0.49720558524131775} 08/31/2021 03:30:48 - INFO - __main__ - Step 78827: {'lr': 0.00023501213320474952, 'samples': 15134784, 'steps': 78826, 'loss/train': 1.1952463388442993} 08/31/2021 03:30:48 - INFO - __main__ - Step 78828: {'lr': 0.00023500683600905686, 'samples': 15134976, 'steps': 78827, 'loss/train': 0.7825779914855957} 08/31/2021 03:30:49 - INFO - __main__ - Step 78829: {'lr': 0.00023500153882011988, 'samples': 15135168, 'steps': 78828, 'loss/train': 0.341025710105896} 08/31/2021 03:30:49 - INFO - __main__ - Step 78830: {'lr': 0.00023499624163794098, 'samples': 15135360, 'steps': 78829, 'loss/train': 1.2772867679595947} 08/31/2021 03:30:49 - INFO - __main__ - Step 78831: {'lr': 0.00023499094446252256, 'samples': 15135552, 'steps': 78830, 'loss/train': 1.443359375} 08/31/2021 03:30:52 - INFO - __main__ - Step 78832: {'lr': 0.00023498564729386705, 'samples': 15135744, 'steps': 78831, 'loss/train': 0.8468368053436279} 08/31/2021 03:30:52 - INFO - __main__ - Step 78833: {'lr': 0.00023498035013197672, 'samples': 15135936, 'steps': 78832, 'loss/train': 0.7544508576393127} 08/31/2021 03:30:53 - INFO - __main__ - Step 78834: {'lr': 0.00023497505297685398, 'samples': 15136128, 'steps': 78833, 'loss/train': 1.2167524099349976} 08/31/2021 03:30:53 - INFO - __main__ - Step 78835: {'lr': 0.0002349697558285013, 'samples': 15136320, 'steps': 78834, 'loss/train': 1.5468957424163818} 08/31/2021 03:30:53 - INFO - __main__ - Step 78836: {'lr': 0.00023496445868692093, 'samples': 15136512, 'steps': 78835, 'loss/train': 1.3440884351730347} 08/31/2021 03:30:55 - INFO - __main__ - Step 78837: {'lr': 0.00023495916155211538, 'samples': 15136704, 'steps': 78836, 'loss/train': 0.8874954581260681} 08/31/2021 03:30:55 - INFO - __main__ - Step 78838: {'lr': 0.00023495386442408704, 'samples': 15136896, 'steps': 78837, 'loss/train': 1.6886167526245117} 08/31/2021 03:30:55 - INFO - __main__ - Step 78839: {'lr': 0.0002349485673028382, 'samples': 15137088, 'steps': 78838, 'loss/train': 0.750752329826355} 08/31/2021 03:30:56 - INFO - __main__ - Step 78840: {'lr': 0.00023494327018837134, 'samples': 15137280, 'steps': 78839, 'loss/train': 0.5419653654098511} 08/31/2021 03:30:56 - INFO - __main__ - Step 78841: {'lr': 0.00023493797308068878, 'samples': 15137472, 'steps': 78840, 'loss/train': 1.2593975067138672} 08/31/2021 03:30:57 - INFO - __main__ - Step 78842: {'lr': 0.00023493267597979298, 'samples': 15137664, 'steps': 78841, 'loss/train': 1.6206635236740112} 08/31/2021 03:30:58 - INFO - __main__ - Step 78843: {'lr': 0.00023492737888568623, 'samples': 15137856, 'steps': 78842, 'loss/train': 0.196064293384552} 08/31/2021 03:30:58 - INFO - __main__ - Step 78844: {'lr': 0.000234922081798371, 'samples': 15138048, 'steps': 78843, 'loss/train': 1.4484792947769165} 08/31/2021 03:30:59 - INFO - __main__ - Step 78845: {'lr': 0.00023491678471784978, 'samples': 15138240, 'steps': 78844, 'loss/train': 1.5680195093154907} 08/31/2021 03:30:59 - INFO - __main__ - Step 78846: {'lr': 0.00023491148764412468, 'samples': 15138432, 'steps': 78845, 'loss/train': 1.3054641485214233} 08/31/2021 03:30:59 - INFO - __main__ - Step 78847: {'lr': 0.00023490619057719826, 'samples': 15138624, 'steps': 78846, 'loss/train': 1.0313793420791626} 08/31/2021 03:31:01 - INFO - __main__ - Step 78848: {'lr': 0.00023490089351707282, 'samples': 15138816, 'steps': 78847, 'loss/train': 0.8593051433563232} 08/31/2021 03:31:01 - INFO - __main__ - Step 78849: {'lr': 0.00023489559646375086, 'samples': 15139008, 'steps': 78848, 'loss/train': 1.0864553451538086} 08/31/2021 03:31:02 - INFO - __main__ - Step 78850: {'lr': 0.00023489029941723468, 'samples': 15139200, 'steps': 78849, 'loss/train': 1.5531635284423828} 08/31/2021 03:31:02 - INFO - __main__ - Step 78851: {'lr': 0.00023488500237752675, 'samples': 15139392, 'steps': 78850, 'loss/train': 1.4253077507019043} 08/31/2021 03:31:02 - INFO - __main__ - Step 78852: {'lr': 0.00023487970534462934, 'samples': 15139584, 'steps': 78851, 'loss/train': 0.4566556513309479} 08/31/2021 03:31:04 - INFO - __main__ - Step 78853: {'lr': 0.00023487440831854492, 'samples': 15139776, 'steps': 78852, 'loss/train': 0.8273395895957947} 08/31/2021 03:31:04 - INFO - __main__ - Step 78854: {'lr': 0.00023486911129927588, 'samples': 15139968, 'steps': 78853, 'loss/train': 0.47643256187438965} 08/31/2021 03:31:05 - INFO - __main__ - Step 78855: {'lr': 0.00023486381428682458, 'samples': 15140160, 'steps': 78854, 'loss/train': 1.5493024587631226} 08/31/2021 03:31:05 - INFO - __main__ - Step 78856: {'lr': 0.0002348585172811934, 'samples': 15140352, 'steps': 78855, 'loss/train': 0.9076808094978333} 08/31/2021 03:31:05 - INFO - __main__ - Step 78857: {'lr': 0.00023485322028238474, 'samples': 15140544, 'steps': 78856, 'loss/train': 0.6716450452804565} 08/31/2021 03:31:07 - INFO - __main__ - Step 78858: {'lr': 0.00023484792329040105, 'samples': 15140736, 'steps': 78857, 'loss/train': 1.104735255241394} 08/31/2021 03:31:07 - INFO - __main__ - Step 78859: {'lr': 0.00023484262630524464, 'samples': 15140928, 'steps': 78858, 'loss/train': 1.2359873056411743} 08/31/2021 03:31:08 - INFO - __main__ - Step 78860: {'lr': 0.00023483732932691784, 'samples': 15141120, 'steps': 78859, 'loss/train': 1.14582097530365} 08/31/2021 03:31:08 - INFO - __main__ - Step 78861: {'lr': 0.00023483203235542314, 'samples': 15141312, 'steps': 78860, 'loss/train': 1.8354127407073975} 08/31/2021 03:31:08 - INFO - __main__ - Step 78862: {'lr': 0.00023482673539076287, 'samples': 15141504, 'steps': 78861, 'loss/train': 1.2727655172348022} 08/31/2021 03:31:10 - INFO - __main__ - Step 78863: {'lr': 0.00023482143843293944, 'samples': 15141696, 'steps': 78862, 'loss/train': 1.4417738914489746} 08/31/2021 03:31:10 - INFO - __main__ - Step 78864: {'lr': 0.00023481614148195524, 'samples': 15141888, 'steps': 78863, 'loss/train': 0.7287818789482117} 08/31/2021 03:31:11 - INFO - __main__ - Step 78865: {'lr': 0.00023481084453781266, 'samples': 15142080, 'steps': 78864, 'loss/train': 1.9872006177902222} 08/31/2021 03:31:11 - INFO - __main__ - Step 78866: {'lr': 0.00023480554760051407, 'samples': 15142272, 'steps': 78865, 'loss/train': 1.7165799140930176} 08/31/2021 03:31:12 - INFO - __main__ - Step 78867: {'lr': 0.00023480025067006187, 'samples': 15142464, 'steps': 78866, 'loss/train': 0.4285363554954529} 08/31/2021 03:31:12 - INFO - __main__ - Step 78868: {'lr': 0.00023479495374645844, 'samples': 15142656, 'steps': 78867, 'loss/train': 1.1908037662506104} 08/31/2021 03:31:13 - INFO - __main__ - Step 78869: {'lr': 0.00023478965682970622, 'samples': 15142848, 'steps': 78868, 'loss/train': 1.6718600988388062} 08/31/2021 03:31:14 - INFO - __main__ - Step 78870: {'lr': 0.00023478435991980748, 'samples': 15143040, 'steps': 78869, 'loss/train': 1.2673646211624146} 08/31/2021 03:31:14 - INFO - __main__ - Step 78871: {'lr': 0.0002347790630167647, 'samples': 15143232, 'steps': 78870, 'loss/train': 1.5910645723342896} 08/31/2021 03:31:15 - INFO - __main__ - Step 78872: {'lr': 0.00023477376612058028, 'samples': 15143424, 'steps': 78871, 'loss/train': 1.30782151222229} 08/31/2021 03:31:15 - INFO - __main__ - Step 78873: {'lr': 0.0002347684692312565, 'samples': 15143616, 'steps': 78872, 'loss/train': 1.5665392875671387} 08/31/2021 03:31:17 - INFO - __main__ - Step 78874: {'lr': 0.00023476317234879583, 'samples': 15143808, 'steps': 78873, 'loss/train': 1.7730896472930908} 08/31/2021 03:31:17 - INFO - __main__ - Step 78875: {'lr': 0.00023475787547320062, 'samples': 15144000, 'steps': 78874, 'loss/train': 0.7439590692520142} 08/31/2021 03:31:18 - INFO - __main__ - Step 78876: {'lr': 0.0002347525786044733, 'samples': 15144192, 'steps': 78875, 'loss/train': 1.2849268913269043} 08/31/2021 03:31:18 - INFO - __main__ - Step 78877: {'lr': 0.00023474728174261624, 'samples': 15144384, 'steps': 78876, 'loss/train': 0.9419573545455933} 08/31/2021 03:31:18 - INFO - __main__ - Step 78878: {'lr': 0.0002347419848876318, 'samples': 15144576, 'steps': 78877, 'loss/train': 0.04851147532463074} 08/31/2021 03:31:19 - INFO - __main__ - Step 78879: {'lr': 0.0002347366880395224, 'samples': 15144768, 'steps': 78878, 'loss/train': 1.0736221075057983} 08/31/2021 03:31:20 - INFO - __main__ - Step 78880: {'lr': 0.00023473139119829046, 'samples': 15144960, 'steps': 78879, 'loss/train': 0.8284433484077454} 08/31/2021 03:31:21 - INFO - __main__ - Step 78881: {'lr': 0.00023472609436393823, 'samples': 15145152, 'steps': 78880, 'loss/train': 0.8103633522987366} 08/31/2021 03:31:21 - INFO - __main__ - Step 78882: {'lr': 0.00023472079753646824, 'samples': 15145344, 'steps': 78881, 'loss/train': 2.9946305751800537} 08/31/2021 03:31:21 - INFO - __main__ - Step 78883: {'lr': 0.0002347155007158828, 'samples': 15145536, 'steps': 78882, 'loss/train': 1.1853898763656616} 08/31/2021 03:31:22 - INFO - __main__ - Step 78884: {'lr': 0.00023471020390218432, 'samples': 15145728, 'steps': 78883, 'loss/train': 1.161446213722229} 08/31/2021 03:31:23 - INFO - __main__ - Step 78885: {'lr': 0.00023470490709537523, 'samples': 15145920, 'steps': 78884, 'loss/train': 0.8515309691429138} 08/31/2021 03:31:24 - INFO - __main__ - Step 78886: {'lr': 0.00023469961029545783, 'samples': 15146112, 'steps': 78885, 'loss/train': 1.6786696910858154} 08/31/2021 03:31:24 - INFO - __main__ - Step 78887: {'lr': 0.00023469431350243457, 'samples': 15146304, 'steps': 78886, 'loss/train': 0.9067907929420471} 08/31/2021 03:31:24 - INFO - __main__ - Step 78888: {'lr': 0.00023468901671630776, 'samples': 15146496, 'steps': 78887, 'loss/train': 1.6140708923339844} 08/31/2021 03:31:25 - INFO - __main__ - Step 78889: {'lr': 0.0002346837199370799, 'samples': 15146688, 'steps': 78888, 'loss/train': 0.9382449388504028} 08/31/2021 03:31:27 - INFO - __main__ - Step 78890: {'lr': 0.00023467842316475328, 'samples': 15146880, 'steps': 78889, 'loss/train': 1.3663114309310913} 08/31/2021 03:31:27 - INFO - __main__ - Step 78891: {'lr': 0.00023467312639933042, 'samples': 15147072, 'steps': 78890, 'loss/train': 1.3057200908660889} 08/31/2021 03:31:28 - INFO - __main__ - Step 78892: {'lr': 0.00023466782964081352, 'samples': 15147264, 'steps': 78891, 'loss/train': 0.6113181114196777} 08/31/2021 03:31:28 - INFO - __main__ - Step 78893: {'lr': 0.00023466253288920508, 'samples': 15147456, 'steps': 78892, 'loss/train': 1.333776593208313} 08/31/2021 03:31:28 - INFO - __main__ - Step 78894: {'lr': 0.00023465723614450744, 'samples': 15147648, 'steps': 78893, 'loss/train': 1.6895021200180054} 08/31/2021 03:31:30 - INFO - __main__ - Step 78895: {'lr': 0.00023465193940672307, 'samples': 15147840, 'steps': 78894, 'loss/train': 0.7136745452880859} 08/31/2021 03:31:30 - INFO - __main__ - Step 78896: {'lr': 0.00023464664267585424, 'samples': 15148032, 'steps': 78895, 'loss/train': 1.173255205154419} 08/31/2021 03:31:31 - INFO - __main__ - Step 78897: {'lr': 0.00023464134595190341, 'samples': 15148224, 'steps': 78896, 'loss/train': 1.326904535293579} 08/31/2021 03:31:31 - INFO - __main__ - Step 78898: {'lr': 0.00023463604923487297, 'samples': 15148416, 'steps': 78897, 'loss/train': 1.4557284116744995} 08/31/2021 03:31:31 - INFO - __main__ - Step 78899: {'lr': 0.00023463075252476534, 'samples': 15148608, 'steps': 78898, 'loss/train': 1.6220588684082031} 08/31/2021 03:31:32 - INFO - __main__ - Step 78900: {'lr': 0.0002346254558215828, 'samples': 15148800, 'steps': 78899, 'loss/train': 1.0709816217422485} 08/31/2021 03:31:33 - INFO - __main__ - Step 78901: {'lr': 0.00023462015912532782, 'samples': 15148992, 'steps': 78900, 'loss/train': 1.014026403427124} 08/31/2021 03:31:34 - INFO - __main__ - Step 78902: {'lr': 0.00023461486243600275, 'samples': 15149184, 'steps': 78901, 'loss/train': 1.2519419193267822} 08/31/2021 03:31:34 - INFO - __main__ - Step 78903: {'lr': 0.00023460956575360997, 'samples': 15149376, 'steps': 78902, 'loss/train': 1.4651908874511719} 08/31/2021 03:31:34 - INFO - __main__ - Step 78904: {'lr': 0.00023460426907815184, 'samples': 15149568, 'steps': 78903, 'loss/train': 1.6736321449279785} 08/31/2021 03:31:35 - INFO - __main__ - Step 78905: {'lr': 0.00023459897240963085, 'samples': 15149760, 'steps': 78904, 'loss/train': 1.21263587474823} 08/31/2021 03:31:36 - INFO - __main__ - Step 78906: {'lr': 0.0002345936757480493, 'samples': 15149952, 'steps': 78905, 'loss/train': 1.0233553647994995} 08/31/2021 03:31:37 - INFO - __main__ - Step 78907: {'lr': 0.00023458837909340962, 'samples': 15150144, 'steps': 78906, 'loss/train': 0.573468029499054} 08/31/2021 03:31:37 - INFO - __main__ - Step 78908: {'lr': 0.00023458308244571414, 'samples': 15150336, 'steps': 78907, 'loss/train': 1.2730176448822021} 08/31/2021 03:31:37 - INFO - __main__ - Step 78909: {'lr': 0.00023457778580496531, 'samples': 15150528, 'steps': 78908, 'loss/train': 1.4270099401474} 08/31/2021 03:31:38 - INFO - __main__ - Step 78910: {'lr': 0.0002345724891711655, 'samples': 15150720, 'steps': 78909, 'loss/train': 1.5351487398147583} 08/31/2021 03:31:40 - INFO - __main__ - Step 78911: {'lr': 0.00023456719254431708, 'samples': 15150912, 'steps': 78910, 'loss/train': 0.6923508048057556} 08/31/2021 03:31:40 - INFO - __main__ - Step 78912: {'lr': 0.00023456189592442253, 'samples': 15151104, 'steps': 78911, 'loss/train': 0.06421166658401489} 08/31/2021 03:31:41 - INFO - __main__ - Step 78913: {'lr': 0.00023455659931148406, 'samples': 15151296, 'steps': 78912, 'loss/train': 1.502899169921875} 08/31/2021 03:31:41 - INFO - __main__ - Step 78914: {'lr': 0.00023455130270550416, 'samples': 15151488, 'steps': 78913, 'loss/train': 1.449341893196106} 08/31/2021 03:31:41 - INFO - __main__ - Step 78915: {'lr': 0.0002345460061064852, 'samples': 15151680, 'steps': 78914, 'loss/train': 1.2790411710739136} 08/31/2021 03:31:43 - INFO - __main__ - Step 78916: {'lr': 0.00023454070951442954, 'samples': 15151872, 'steps': 78915, 'loss/train': 0.0654577985405922} 08/31/2021 03:31:43 - INFO - __main__ - Step 78917: {'lr': 0.00023453541292933964, 'samples': 15152064, 'steps': 78916, 'loss/train': 1.0319041013717651} 08/31/2021 03:31:44 - INFO - __main__ - Step 78918: {'lr': 0.00023453011635121782, 'samples': 15152256, 'steps': 78917, 'loss/train': 0.7292093634605408} 08/31/2021 03:31:44 - INFO - __main__ - Step 78919: {'lr': 0.0002345248197800665, 'samples': 15152448, 'steps': 78918, 'loss/train': 0.8124969601631165} 08/31/2021 03:31:44 - INFO - __main__ - Step 78920: {'lr': 0.00023451952321588808, 'samples': 15152640, 'steps': 78919, 'loss/train': 1.0267788171768188} 08/31/2021 03:31:45 - INFO - __main__ - Step 78921: {'lr': 0.0002345142266586849, 'samples': 15152832, 'steps': 78920, 'loss/train': 0.6381382346153259} 08/31/2021 03:31:46 - INFO - __main__ - Step 78922: {'lr': 0.00023450893010845935, 'samples': 15153024, 'steps': 78921, 'loss/train': 0.48492321372032166} 08/31/2021 03:31:47 - INFO - __main__ - Step 78923: {'lr': 0.00023450363356521386, 'samples': 15153216, 'steps': 78922, 'loss/train': 2.7114500999450684} 08/31/2021 03:31:47 - INFO - __main__ - Step 78924: {'lr': 0.00023449833702895079, 'samples': 15153408, 'steps': 78923, 'loss/train': 1.2312443256378174} 08/31/2021 03:31:48 - INFO - __main__ - Step 78925: {'lr': 0.00023449304049967252, 'samples': 15153600, 'steps': 78924, 'loss/train': 0.7654467821121216} 08/31/2021 03:31:48 - INFO - __main__ - Step 78926: {'lr': 0.00023448774397738157, 'samples': 15153792, 'steps': 78925, 'loss/train': 0.569867730140686} 08/31/2021 03:31:49 - INFO - __main__ - Step 78927: {'lr': 0.00023448244746208008, 'samples': 15153984, 'steps': 78926, 'loss/train': 1.0426833629608154} 08/31/2021 03:31:50 - INFO - __main__ - Step 78928: {'lr': 0.00023447715095377059, 'samples': 15154176, 'steps': 78927, 'loss/train': 1.4214690923690796} 08/31/2021 03:31:50 - INFO - __main__ - Step 78929: {'lr': 0.00023447185445245544, 'samples': 15154368, 'steps': 78928, 'loss/train': 1.0715409517288208} 08/31/2021 03:31:51 - INFO - __main__ - Step 78930: {'lr': 0.00023446655795813704, 'samples': 15154560, 'steps': 78929, 'loss/train': 1.5175024271011353} 08/31/2021 03:31:51 - INFO - __main__ - Step 78931: {'lr': 0.00023446126147081775, 'samples': 15154752, 'steps': 78930, 'loss/train': 0.6445534229278564} 08/31/2021 03:31:51 - INFO - __main__ - Step 78932: {'lr': 0.00023445596499049997, 'samples': 15154944, 'steps': 78931, 'loss/train': 1.514340877532959} 08/31/2021 03:31:53 - INFO - __main__ - Step 78933: {'lr': 0.00023445066851718611, 'samples': 15155136, 'steps': 78932, 'loss/train': 0.9973500967025757} 08/31/2021 03:31:53 - INFO - __main__ - Step 78934: {'lr': 0.00023444537205087853, 'samples': 15155328, 'steps': 78933, 'loss/train': 2.021831512451172} 08/31/2021 03:31:54 - INFO - __main__ - Step 78935: {'lr': 0.00023444007559157964, 'samples': 15155520, 'steps': 78934, 'loss/train': 1.0490666627883911} 08/31/2021 03:31:54 - INFO - __main__ - Step 78936: {'lr': 0.00023443477913929182, 'samples': 15155712, 'steps': 78935, 'loss/train': 1.2666276693344116} 08/31/2021 03:31:54 - INFO - __main__ - Step 78937: {'lr': 0.00023442948269401743, 'samples': 15155904, 'steps': 78936, 'loss/train': 1.2933300733566284} 08/31/2021 03:31:56 - INFO - __main__ - Step 78938: {'lr': 0.00023442418625575887, 'samples': 15156096, 'steps': 78937, 'loss/train': 1.4801647663116455} 08/31/2021 03:31:56 - INFO - __main__ - Step 78939: {'lr': 0.00023441888982451864, 'samples': 15156288, 'steps': 78938, 'loss/train': 1.3028589487075806} 08/31/2021 03:31:57 - INFO - __main__ - Step 78940: {'lr': 0.00023441359340029892, 'samples': 15156480, 'steps': 78939, 'loss/train': 1.1875954866409302} 08/31/2021 03:31:57 - INFO - __main__ - Step 78941: {'lr': 0.00023440829698310217, 'samples': 15156672, 'steps': 78940, 'loss/train': 1.2785286903381348} 08/31/2021 03:31:57 - INFO - __main__ - Step 78942: {'lr': 0.00023440300057293083, 'samples': 15156864, 'steps': 78941, 'loss/train': 0.7577130794525146} 08/31/2021 03:32:00 - INFO - __main__ - Step 78943: {'lr': 0.00023439770416978724, 'samples': 15157056, 'steps': 78942, 'loss/train': 1.2388861179351807} 08/31/2021 03:32:00 - INFO - __main__ - Step 78944: {'lr': 0.0002343924077736738, 'samples': 15157248, 'steps': 78943, 'loss/train': 0.8931435942649841} 08/31/2021 03:32:01 - INFO - __main__ - Step 78945: {'lr': 0.00023438711138459292, 'samples': 15157440, 'steps': 78944, 'loss/train': 1.1587114334106445} 08/31/2021 03:32:01 - INFO - __main__ - Step 78946: {'lr': 0.00023438181500254695, 'samples': 15157632, 'steps': 78945, 'loss/train': 0.13546894490718842} 08/31/2021 03:32:01 - INFO - __main__ - Step 78947: {'lr': 0.00023437651862753833, 'samples': 15157824, 'steps': 78946, 'loss/train': 1.2050566673278809} 08/31/2021 03:32:03 - INFO - __main__ - Step 78948: {'lr': 0.0002343712222595694, 'samples': 15158016, 'steps': 78947, 'loss/train': 1.2087572813034058} 08/31/2021 03:32:03 - INFO - __main__ - Step 78949: {'lr': 0.00023436592589864253, 'samples': 15158208, 'steps': 78948, 'loss/train': 1.7884490489959717} 08/31/2021 03:32:04 - INFO - __main__ - Step 78950: {'lr': 0.00023436062954476013, 'samples': 15158400, 'steps': 78949, 'loss/train': 0.9866646528244019} 08/31/2021 03:32:04 - INFO - __main__ - Step 78951: {'lr': 0.0002343553331979246, 'samples': 15158592, 'steps': 78950, 'loss/train': 0.23775333166122437} 08/31/2021 03:32:05 - INFO - __main__ - Step 78952: {'lr': 0.0002343500368581383, 'samples': 15158784, 'steps': 78951, 'loss/train': 5.672922611236572} 08/31/2021 03:32:06 - INFO - __main__ - Step 78953: {'lr': 0.00023434474052540377, 'samples': 15158976, 'steps': 78952, 'loss/train': 1.4015449285507202} 08/31/2021 03:32:07 - INFO - __main__ - Step 78954: {'lr': 0.00023433944419972314, 'samples': 15159168, 'steps': 78953, 'loss/train': 1.1193015575408936} 08/31/2021 03:32:07 - INFO - __main__ - Step 78955: {'lr': 0.0002343341478810989, 'samples': 15159360, 'steps': 78954, 'loss/train': 1.3834037780761719} 08/31/2021 03:32:07 - INFO - __main__ - Step 78956: {'lr': 0.00023432885156953346, 'samples': 15159552, 'steps': 78955, 'loss/train': 0.6170735955238342} 08/31/2021 03:32:08 - INFO - __main__ - Step 78957: {'lr': 0.0002343235552650292, 'samples': 15159744, 'steps': 78956, 'loss/train': 1.358912467956543} 08/31/2021 03:32:09 - INFO - __main__ - Step 78958: {'lr': 0.0002343182589675885, 'samples': 15159936, 'steps': 78957, 'loss/train': 0.49086979031562805} 08/31/2021 03:32:10 - INFO - __main__ - Step 78959: {'lr': 0.00023431296267721374, 'samples': 15160128, 'steps': 78958, 'loss/train': 0.8005818724632263} 08/31/2021 03:32:10 - INFO - __main__ - Step 78960: {'lr': 0.00023430766639390732, 'samples': 15160320, 'steps': 78959, 'loss/train': 1.5589922666549683} 08/31/2021 03:32:10 - INFO - __main__ - Step 78961: {'lr': 0.00023430237011767165, 'samples': 15160512, 'steps': 78960, 'loss/train': 1.598841667175293} 08/31/2021 03:32:11 - INFO - __main__ - Step 78962: {'lr': 0.00023429707384850908, 'samples': 15160704, 'steps': 78961, 'loss/train': 1.001230239868164} 08/31/2021 03:32:11 - INFO - __main__ - Step 78963: {'lr': 0.000234291777586422, 'samples': 15160896, 'steps': 78962, 'loss/train': 0.9362366795539856} 08/31/2021 03:32:13 - INFO - __main__ - Step 78964: {'lr': 0.0002342864813314128, 'samples': 15161088, 'steps': 78963, 'loss/train': 1.1681241989135742} 08/31/2021 03:32:13 - INFO - __main__ - Step 78965: {'lr': 0.00023428118508348386, 'samples': 15161280, 'steps': 78964, 'loss/train': 0.5373489856719971} 08/31/2021 03:32:13 - INFO - __main__ - Step 78966: {'lr': 0.0002342758888426377, 'samples': 15161472, 'steps': 78965, 'loss/train': 5.748972415924072} 08/31/2021 03:32:14 - INFO - __main__ - Step 78967: {'lr': 0.00023427059260887649, 'samples': 15161664, 'steps': 78966, 'loss/train': 1.3199228048324585} 08/31/2021 03:32:14 - INFO - __main__ - Step 78968: {'lr': 0.00023426529638220268, 'samples': 15161856, 'steps': 78967, 'loss/train': 1.5566948652267456} 08/31/2021 03:32:16 - INFO - __main__ - Step 78969: {'lr': 0.00023426000016261867, 'samples': 15162048, 'steps': 78968, 'loss/train': 1.168359398841858} 08/31/2021 03:32:16 - INFO - __main__ - Step 78970: {'lr': 0.00023425470395012688, 'samples': 15162240, 'steps': 78969, 'loss/train': 0.7984414100646973} 08/31/2021 03:32:16 - INFO - __main__ - Step 78971: {'lr': 0.0002342494077447297, 'samples': 15162432, 'steps': 78970, 'loss/train': 0.8584005832672119} 08/31/2021 03:32:17 - INFO - __main__ - Step 78972: {'lr': 0.00023424411154642947, 'samples': 15162624, 'steps': 78971, 'loss/train': 0.9785589575767517} 08/31/2021 03:32:17 - INFO - __main__ - Step 78973: {'lr': 0.0002342388153552286, 'samples': 15162816, 'steps': 78972, 'loss/train': 1.3560205698013306} 08/31/2021 03:32:19 - INFO - __main__ - Step 78974: {'lr': 0.0002342335191711295, 'samples': 15163008, 'steps': 78973, 'loss/train': 0.7382655143737793} 08/31/2021 03:32:19 - INFO - __main__ - Step 78975: {'lr': 0.00023422822299413448, 'samples': 15163200, 'steps': 78974, 'loss/train': 0.3061879575252533} 08/31/2021 03:32:19 - INFO - __main__ - Step 78976: {'lr': 0.00023422292682424603, 'samples': 15163392, 'steps': 78975, 'loss/train': 0.7455306649208069} 08/31/2021 03:32:20 - INFO - __main__ - Step 78977: {'lr': 0.00023421763066146646, 'samples': 15163584, 'steps': 78976, 'loss/train': 0.9167117476463318} 08/31/2021 03:32:20 - INFO - __main__ - Step 78978: {'lr': 0.0002342123345057982, 'samples': 15163776, 'steps': 78977, 'loss/train': 0.7038429379463196} 08/31/2021 03:32:20 - INFO - __main__ - Step 78979: {'lr': 0.0002342070383572436, 'samples': 15163968, 'steps': 78978, 'loss/train': 1.1484808921813965} 08/31/2021 03:32:22 - INFO - __main__ - Step 78980: {'lr': 0.00023420174221580516, 'samples': 15164160, 'steps': 78979, 'loss/train': 0.8056605458259583} 08/31/2021 03:32:23 - INFO - __main__ - Step 78981: {'lr': 0.0002341964460814851, 'samples': 15164352, 'steps': 78980, 'loss/train': 1.136228322982788} 08/31/2021 03:32:23 - INFO - __main__ - Step 78982: {'lr': 0.00023419114995428585, 'samples': 15164544, 'steps': 78981, 'loss/train': 1.7169889211654663} 08/31/2021 03:32:23 - INFO - __main__ - Step 78983: {'lr': 0.00023418585383420986, 'samples': 15164736, 'steps': 78982, 'loss/train': 0.8627632856369019} 08/31/2021 03:32:24 - INFO - __main__ - Step 78984: {'lr': 0.00023418055772125946, 'samples': 15164928, 'steps': 78983, 'loss/train': 1.5413665771484375} 08/31/2021 03:32:25 - INFO - __main__ - Step 78985: {'lr': 0.00023417526161543704, 'samples': 15165120, 'steps': 78984, 'loss/train': 0.3748491406440735} 08/31/2021 03:32:26 - INFO - __main__ - Step 78986: {'lr': 0.00023416996551674503, 'samples': 15165312, 'steps': 78985, 'loss/train': 0.9404470920562744} 08/31/2021 03:32:26 - INFO - __main__ - Step 78987: {'lr': 0.00023416466942518578, 'samples': 15165504, 'steps': 78986, 'loss/train': 1.0478767156600952} 08/31/2021 03:32:27 - INFO - __main__ - Step 78988: {'lr': 0.00023415937334076169, 'samples': 15165696, 'steps': 78987, 'loss/train': 0.034035660326480865} 08/31/2021 03:32:27 - INFO - __main__ - Step 78989: {'lr': 0.00023415407726347509, 'samples': 15165888, 'steps': 78988, 'loss/train': 1.1082295179367065} 08/31/2021 03:32:27 - INFO - __main__ - Step 78990: {'lr': 0.0002341487811933285, 'samples': 15166080, 'steps': 78989, 'loss/train': 1.46906316280365} 08/31/2021 03:32:29 - INFO - __main__ - Step 78991: {'lr': 0.00023414348513032415, 'samples': 15166272, 'steps': 78990, 'loss/train': 1.2296499013900757} 08/31/2021 03:32:29 - INFO - __main__ - Step 78992: {'lr': 0.0002341381890744646, 'samples': 15166464, 'steps': 78991, 'loss/train': 0.9603040218353271} 08/31/2021 03:32:30 - INFO - __main__ - Step 78993: {'lr': 0.00023413289302575213, 'samples': 15166656, 'steps': 78992, 'loss/train': 1.3237318992614746} 08/31/2021 03:32:30 - INFO - __main__ - Step 78994: {'lr': 0.0002341275969841891, 'samples': 15166848, 'steps': 78993, 'loss/train': 1.030404806137085} 08/31/2021 03:32:30 - INFO - __main__ - Step 78995: {'lr': 0.00023412230094977787, 'samples': 15167040, 'steps': 78994, 'loss/train': 1.1718621253967285} 08/31/2021 03:32:33 - INFO - __main__ - Step 78996: {'lr': 0.00023411700492252094, 'samples': 15167232, 'steps': 78995, 'loss/train': 1.4713616371154785} 08/31/2021 03:32:33 - INFO - __main__ - Step 78997: {'lr': 0.0002341117089024206, 'samples': 15167424, 'steps': 78996, 'loss/train': 1.0605489015579224} 08/31/2021 03:32:33 - INFO - __main__ - Step 78998: {'lr': 0.00023410641288947935, 'samples': 15167616, 'steps': 78997, 'loss/train': 1.198325753211975} 08/31/2021 03:32:34 - INFO - __main__ - Step 78999: {'lr': 0.00023410111688369946, 'samples': 15167808, 'steps': 78998, 'loss/train': 1.0121586322784424} 08/31/2021 03:32:34 - INFO - __main__ - Step 79000: {'lr': 0.00023409582088508335, 'samples': 15168000, 'steps': 78999, 'loss/train': 1.7026712894439697} 08/31/2021 03:32:36 - INFO - __main__ - Step 79001: {'lr': 0.00023409052489363342, 'samples': 15168192, 'steps': 79000, 'loss/train': 0.038836002349853516} 08/31/2021 03:32:36 - INFO - __main__ - Step 79002: {'lr': 0.00023408522890935206, 'samples': 15168384, 'steps': 79001, 'loss/train': 1.1780489683151245} 08/31/2021 03:32:37 - INFO - __main__ - Step 79003: {'lr': 0.00023407993293224173, 'samples': 15168576, 'steps': 79002, 'loss/train': 0.03106614202260971} 08/31/2021 03:32:37 - INFO - __main__ - Step 79004: {'lr': 0.00023407463696230462, 'samples': 15168768, 'steps': 79003, 'loss/train': 1.9761935472488403} 08/31/2021 03:32:37 - INFO - __main__ - Step 79005: {'lr': 0.0002340693409995433, 'samples': 15168960, 'steps': 79004, 'loss/train': 0.27550753951072693} 08/31/2021 03:32:39 - INFO - __main__ - Step 79006: {'lr': 0.00023406404504396013, 'samples': 15169152, 'steps': 79005, 'loss/train': 1.4361075162887573} 08/31/2021 03:32:39 - INFO - __main__ - Step 79007: {'lr': 0.00023405874909555738, 'samples': 15169344, 'steps': 79006, 'loss/train': 1.0006904602050781} 08/31/2021 03:32:39 - INFO - __main__ - Step 79008: {'lr': 0.0002340534531543375, 'samples': 15169536, 'steps': 79007, 'loss/train': 1.153045654296875} 08/31/2021 03:32:40 - INFO - __main__ - Step 79009: {'lr': 0.00023404815722030293, 'samples': 15169728, 'steps': 79008, 'loss/train': 1.1483852863311768} 08/31/2021 03:32:40 - INFO - __main__ - Step 79010: {'lr': 0.00023404286129345597, 'samples': 15169920, 'steps': 79009, 'loss/train': 1.3220641613006592} 08/31/2021 03:32:42 - INFO - __main__ - Step 79011: {'lr': 0.00023403756537379908, 'samples': 15170112, 'steps': 79010, 'loss/train': 0.8321810960769653} 08/31/2021 03:32:43 - INFO - __main__ - Step 79012: {'lr': 0.0002340322694613346, 'samples': 15170304, 'steps': 79011, 'loss/train': 0.8215634822845459} 08/31/2021 03:32:43 - INFO - __main__ - Step 79013: {'lr': 0.00023402697355606495, 'samples': 15170496, 'steps': 79012, 'loss/train': 1.726544737815857} 08/31/2021 03:32:43 - INFO - __main__ - Step 79014: {'lr': 0.00023402167765799255, 'samples': 15170688, 'steps': 79013, 'loss/train': 0.3276982009410858} 08/31/2021 03:32:44 - INFO - __main__ - Step 79015: {'lr': 0.00023401638176711968, 'samples': 15170880, 'steps': 79014, 'loss/train': 0.17872430384159088} 08/31/2021 03:32:44 - INFO - __main__ - Step 79016: {'lr': 0.00023401108588344877, 'samples': 15171072, 'steps': 79015, 'loss/train': 0.8018963932991028} 08/31/2021 03:32:45 - INFO - __main__ - Step 79017: {'lr': 0.00023400579000698222, 'samples': 15171264, 'steps': 79016, 'loss/train': 1.3836841583251953} 08/31/2021 03:32:46 - INFO - __main__ - Step 79018: {'lr': 0.00023400049413772243, 'samples': 15171456, 'steps': 79017, 'loss/train': 1.6326441764831543} 08/31/2021 03:32:46 - INFO - __main__ - Step 79019: {'lr': 0.00023399519827567176, 'samples': 15171648, 'steps': 79018, 'loss/train': 1.3164070844650269} 08/31/2021 03:32:47 - INFO - __main__ - Step 79020: {'lr': 0.00023398990242083265, 'samples': 15171840, 'steps': 79019, 'loss/train': 1.396255612373352} 08/31/2021 03:32:47 - INFO - __main__ - Step 79021: {'lr': 0.00023398460657320742, 'samples': 15172032, 'steps': 79020, 'loss/train': 1.421840786933899} 08/31/2021 03:32:48 - INFO - __main__ - Step 79022: {'lr': 0.00023397931073279842, 'samples': 15172224, 'steps': 79021, 'loss/train': 1.3559437990188599} 08/31/2021 03:32:49 - INFO - __main__ - Step 79023: {'lr': 0.00023397401489960815, 'samples': 15172416, 'steps': 79022, 'loss/train': 1.190370798110962} 08/31/2021 03:32:49 - INFO - __main__ - Step 79024: {'lr': 0.00023396871907363894, 'samples': 15172608, 'steps': 79023, 'loss/train': 1.3857256174087524} 08/31/2021 03:32:49 - INFO - __main__ - Step 79025: {'lr': 0.0002339634232548932, 'samples': 15172800, 'steps': 79024, 'loss/train': 1.2807176113128662} 08/31/2021 03:32:50 - INFO - __main__ - Step 79026: {'lr': 0.00023395812744337328, 'samples': 15172992, 'steps': 79025, 'loss/train': 0.8696087598800659} 08/31/2021 03:32:51 - INFO - __main__ - Step 79027: {'lr': 0.00023395283163908155, 'samples': 15173184, 'steps': 79026, 'loss/train': 0.7976707220077515} 08/31/2021 03:32:52 - INFO - __main__ - Step 79028: {'lr': 0.00023394753584202044, 'samples': 15173376, 'steps': 79027, 'loss/train': 1.3980932235717773} 08/31/2021 03:32:52 - INFO - __main__ - Step 79029: {'lr': 0.0002339422400521923, 'samples': 15173568, 'steps': 79028, 'loss/train': 1.505963921546936} 08/31/2021 03:32:52 - INFO - __main__ - Step 79030: {'lr': 0.00023393694426959954, 'samples': 15173760, 'steps': 79029, 'loss/train': 1.1571431159973145} 08/31/2021 03:32:53 - INFO - __main__ - Step 79031: {'lr': 0.0002339316484942446, 'samples': 15173952, 'steps': 79030, 'loss/train': 1.1084814071655273} 08/31/2021 03:32:54 - INFO - __main__ - Step 79032: {'lr': 0.00023392635272612974, 'samples': 15174144, 'steps': 79031, 'loss/train': 0.8680849075317383} 08/31/2021 03:32:55 - INFO - __main__ - Step 79033: {'lr': 0.00023392105696525752, 'samples': 15174336, 'steps': 79032, 'loss/train': 0.7722053527832031} 08/31/2021 03:32:55 - INFO - __main__ - Step 79034: {'lr': 0.00023391576121163017, 'samples': 15174528, 'steps': 79033, 'loss/train': 1.2423474788665771} 08/31/2021 03:32:56 - INFO - __main__ - Step 79035: {'lr': 0.0002339104654652501, 'samples': 15174720, 'steps': 79034, 'loss/train': 0.059196703135967255} 08/31/2021 03:32:56 - INFO - __main__ - Step 79036: {'lr': 0.0002339051697261198, 'samples': 15174912, 'steps': 79035, 'loss/train': 0.01785440742969513} 08/31/2021 03:32:56 - INFO - __main__ - Step 79037: {'lr': 0.0002338998739942415, 'samples': 15175104, 'steps': 79036, 'loss/train': 0.0269627682864666} 08/31/2021 03:32:58 - INFO - __main__ - Step 79038: {'lr': 0.0002338945782696177, 'samples': 15175296, 'steps': 79037, 'loss/train': 1.1809827089309692} 08/31/2021 03:32:59 - INFO - __main__ - Step 79039: {'lr': 0.00023388928255225073, 'samples': 15175488, 'steps': 79038, 'loss/train': 1.655967116355896} 08/31/2021 03:32:59 - INFO - __main__ - Step 79040: {'lr': 0.00023388398684214302, 'samples': 15175680, 'steps': 79039, 'loss/train': 0.9957792162895203} 08/31/2021 03:32:59 - INFO - __main__ - Step 79041: {'lr': 0.00023387869113929694, 'samples': 15175872, 'steps': 79040, 'loss/train': 1.4468936920166016} 08/31/2021 03:33:00 - INFO - __main__ - Step 79042: {'lr': 0.00023387339544371486, 'samples': 15176064, 'steps': 79041, 'loss/train': 1.2302411794662476} 08/31/2021 03:33:01 - INFO - __main__ - Step 79043: {'lr': 0.00023386809975539918, 'samples': 15176256, 'steps': 79042, 'loss/train': 1.229551911354065} 08/31/2021 03:33:02 - INFO - __main__ - Step 79044: {'lr': 0.00023386280407435229, 'samples': 15176448, 'steps': 79043, 'loss/train': 1.371090054512024} 08/31/2021 03:33:02 - INFO - __main__ - Step 79045: {'lr': 0.00023385750840057657, 'samples': 15176640, 'steps': 79044, 'loss/train': 1.3987209796905518} 08/31/2021 03:33:02 - INFO - __main__ - Step 79046: {'lr': 0.0002338522127340744, 'samples': 15176832, 'steps': 79045, 'loss/train': 1.1997640132904053} 08/31/2021 03:33:03 - INFO - __main__ - Step 79047: {'lr': 0.0002338469170748483, 'samples': 15177024, 'steps': 79046, 'loss/train': 1.8161752223968506} 08/31/2021 03:33:04 - INFO - __main__ - Step 79048: {'lr': 0.0002338416214229004, 'samples': 15177216, 'steps': 79047, 'loss/train': 1.0895448923110962} 08/31/2021 03:33:04 - INFO - __main__ - Step 79049: {'lr': 0.00023383632577823324, 'samples': 15177408, 'steps': 79048, 'loss/train': 0.8811406493186951} 08/31/2021 03:33:05 - INFO - __main__ - Step 79050: {'lr': 0.00023383103014084917, 'samples': 15177600, 'steps': 79049, 'loss/train': 1.6464550495147705} 08/31/2021 03:33:05 - INFO - __main__ - Step 79051: {'lr': 0.0002338257345107506, 'samples': 15177792, 'steps': 79050, 'loss/train': 2.1652486324310303} 08/31/2021 03:33:06 - INFO - __main__ - Step 79052: {'lr': 0.0002338204388879399, 'samples': 15177984, 'steps': 79051, 'loss/train': 0.9266867637634277} 08/31/2021 03:33:08 - INFO - __main__ - Step 79053: {'lr': 0.00023381514327241944, 'samples': 15178176, 'steps': 79052, 'loss/train': 0.7584864497184753} 08/31/2021 03:33:08 - INFO - __main__ - Step 79054: {'lr': 0.00023380984766419163, 'samples': 15178368, 'steps': 79053, 'loss/train': 1.0862475633621216} 08/31/2021 03:33:09 - INFO - __main__ - Step 79055: {'lr': 0.00023380455206325888, 'samples': 15178560, 'steps': 79054, 'loss/train': 1.249242901802063} 08/31/2021 03:33:09 - INFO - __main__ - Step 79056: {'lr': 0.00023379925646962354, 'samples': 15178752, 'steps': 79055, 'loss/train': 1.4815030097961426} 08/31/2021 03:33:09 - INFO - __main__ - Step 79057: {'lr': 0.00023379396088328797, 'samples': 15178944, 'steps': 79056, 'loss/train': 0.7617030739784241} 08/31/2021 03:33:11 - INFO - __main__ - Step 79058: {'lr': 0.00023378866530425463, 'samples': 15179136, 'steps': 79057, 'loss/train': 1.4960919618606567} 08/31/2021 03:33:11 - INFO - __main__ - Step 79059: {'lr': 0.00023378336973252584, 'samples': 15179328, 'steps': 79058, 'loss/train': 0.9168779253959656} 08/31/2021 03:33:12 - INFO - __main__ - Step 79060: {'lr': 0.00023377807416810414, 'samples': 15179520, 'steps': 79059, 'loss/train': 1.3526099920272827} 08/31/2021 03:33:12 - INFO - __main__ - Step 79061: {'lr': 0.0002337727786109917, 'samples': 15179712, 'steps': 79060, 'loss/train': 1.2093158960342407} 08/31/2021 03:33:12 - INFO - __main__ - Step 79062: {'lr': 0.00023376748306119097, 'samples': 15179904, 'steps': 79061, 'loss/train': 1.1513296365737915} 08/31/2021 03:33:14 - INFO - __main__ - Step 79063: {'lr': 0.00023376218751870436, 'samples': 15180096, 'steps': 79062, 'loss/train': 1.5874683856964111} 08/31/2021 03:33:14 - INFO - __main__ - Step 79064: {'lr': 0.00023375689198353427, 'samples': 15180288, 'steps': 79063, 'loss/train': 0.8911608457565308} 08/31/2021 03:33:15 - INFO - __main__ - Step 79065: {'lr': 0.00023375159645568305, 'samples': 15180480, 'steps': 79064, 'loss/train': 1.1413400173187256} 08/31/2021 03:33:15 - INFO - __main__ - Step 79066: {'lr': 0.00023374630093515313, 'samples': 15180672, 'steps': 79065, 'loss/train': 1.2680622339248657} 08/31/2021 03:33:15 - INFO - __main__ - Step 79067: {'lr': 0.00023374100542194686, 'samples': 15180864, 'steps': 79066, 'loss/train': 0.1664697229862213} 08/31/2021 03:33:16 - INFO - __main__ - Step 79068: {'lr': 0.00023373570991606666, 'samples': 15181056, 'steps': 79067, 'loss/train': 0.9175055027008057} 08/31/2021 03:33:17 - INFO - __main__ - Step 79069: {'lr': 0.00023373041441751493, 'samples': 15181248, 'steps': 79068, 'loss/train': 0.322782039642334} 08/31/2021 03:33:18 - INFO - __main__ - Step 79070: {'lr': 0.00023372511892629395, 'samples': 15181440, 'steps': 79069, 'loss/train': 0.06493405252695084} 08/31/2021 03:33:18 - INFO - __main__ - Step 79071: {'lr': 0.0002337198234424062, 'samples': 15181632, 'steps': 79070, 'loss/train': 1.2483400106430054} 08/31/2021 03:33:19 - INFO - __main__ - Step 79072: {'lr': 0.00023371452796585408, 'samples': 15181824, 'steps': 79071, 'loss/train': 0.6112731695175171} 08/31/2021 03:33:19 - INFO - __main__ - Step 79073: {'lr': 0.00023370923249663994, 'samples': 15182016, 'steps': 79072, 'loss/train': 0.7677710056304932} 08/31/2021 03:33:20 - INFO - __main__ - Step 79074: {'lr': 0.00023370393703476625, 'samples': 15182208, 'steps': 79073, 'loss/train': 1.139194369316101} 08/31/2021 03:33:21 - INFO - __main__ - Step 79075: {'lr': 0.00023369864158023524, 'samples': 15182400, 'steps': 79074, 'loss/train': 1.5513300895690918} 08/31/2021 03:33:21 - INFO - __main__ - Step 79076: {'lr': 0.00023369334613304935, 'samples': 15182592, 'steps': 79075, 'loss/train': 1.1784011125564575} 08/31/2021 03:33:22 - INFO - __main__ - Step 79077: {'lr': 0.00023368805069321098, 'samples': 15182784, 'steps': 79076, 'loss/train': 1.0036823749542236} 08/31/2021 03:33:22 - INFO - __main__ - Step 79078: {'lr': 0.00023368275526072254, 'samples': 15182976, 'steps': 79077, 'loss/train': 1.2193399667739868} 08/31/2021 03:33:23 - INFO - __main__ - Step 79079: {'lr': 0.00023367745983558636, 'samples': 15183168, 'steps': 79078, 'loss/train': 0.8234918117523193} 08/31/2021 03:33:24 - INFO - __main__ - Step 79080: {'lr': 0.0002336721644178049, 'samples': 15183360, 'steps': 79079, 'loss/train': 1.3438012599945068} 08/31/2021 03:33:24 - INFO - __main__ - Step 79081: {'lr': 0.0002336668690073805, 'samples': 15183552, 'steps': 79080, 'loss/train': 0.36608806252479553} 08/31/2021 03:33:24 - INFO - __main__ - Step 79082: {'lr': 0.00023366157360431555, 'samples': 15183744, 'steps': 79081, 'loss/train': 0.8820120096206665} 08/31/2021 03:33:25 - INFO - __main__ - Step 79083: {'lr': 0.00023365627820861245, 'samples': 15183936, 'steps': 79082, 'loss/train': 0.7727766633033752} 08/31/2021 03:33:26 - INFO - __main__ - Step 79084: {'lr': 0.0002336509828202736, 'samples': 15184128, 'steps': 79083, 'loss/train': 0.9530370235443115} 08/31/2021 03:33:27 - INFO - __main__ - Step 79085: {'lr': 0.00023364568743930133, 'samples': 15184320, 'steps': 79084, 'loss/train': 1.9039450883865356} 08/31/2021 03:33:27 - INFO - __main__ - Step 79086: {'lr': 0.0002336403920656981, 'samples': 15184512, 'steps': 79085, 'loss/train': 1.1651577949523926} 08/31/2021 03:33:28 - INFO - __main__ - Step 79087: {'lr': 0.00023363509669946633, 'samples': 15184704, 'steps': 79086, 'loss/train': 1.1897765398025513} 08/31/2021 03:33:28 - INFO - __main__ - Step 79088: {'lr': 0.00023362980134060824, 'samples': 15184896, 'steps': 79087, 'loss/train': 1.0448200702667236} 08/31/2021 03:33:30 - INFO - __main__ - Step 79089: {'lr': 0.00023362450598912632, 'samples': 15185088, 'steps': 79088, 'loss/train': 1.755514144897461} 08/31/2021 03:33:31 - INFO - __main__ - Step 79090: {'lr': 0.00023361921064502292, 'samples': 15185280, 'steps': 79089, 'loss/train': 1.318441390991211} 08/31/2021 03:33:31 - INFO - __main__ - Step 79091: {'lr': 0.00023361391530830045, 'samples': 15185472, 'steps': 79090, 'loss/train': 1.1583116054534912} 08/31/2021 03:33:31 - INFO - __main__ - Step 79092: {'lr': 0.00023360861997896132, 'samples': 15185664, 'steps': 79091, 'loss/train': 1.7956583499908447} 08/31/2021 03:33:32 - INFO - __main__ - Step 79093: {'lr': 0.00023360332465700788, 'samples': 15185856, 'steps': 79092, 'loss/train': 0.8078869581222534} 08/31/2021 03:33:32 - INFO - __main__ - Step 79094: {'lr': 0.00023359802934244255, 'samples': 15186048, 'steps': 79093, 'loss/train': 1.4568262100219727} 08/31/2021 03:33:32 - INFO - __main__ - Step 79095: {'lr': 0.00023359273403526765, 'samples': 15186240, 'steps': 79094, 'loss/train': 0.06287720799446106} 08/31/2021 03:33:34 - INFO - __main__ - Step 79096: {'lr': 0.00023358743873548566, 'samples': 15186432, 'steps': 79095, 'loss/train': 0.043340276926755905} 08/31/2021 03:33:35 - INFO - __main__ - Step 79097: {'lr': 0.0002335821434430989, 'samples': 15186624, 'steps': 79096, 'loss/train': 0.8695275783538818} 08/31/2021 03:33:35 - INFO - __main__ - Step 79098: {'lr': 0.00023357684815810976, 'samples': 15186816, 'steps': 79097, 'loss/train': 1.4603252410888672} 08/31/2021 03:33:35 - INFO - __main__ - Step 79099: {'lr': 0.00023357155288052063, 'samples': 15187008, 'steps': 79098, 'loss/train': 1.1631730794906616} 08/31/2021 03:33:36 - INFO - __main__ - Step 79100: {'lr': 0.00023356625761033394, 'samples': 15187200, 'steps': 79099, 'loss/train': 0.0936891958117485} 08/31/2021 03:33:37 - INFO - __main__ - Step 79101: {'lr': 0.0002335609623475521, 'samples': 15187392, 'steps': 79100, 'loss/train': 1.4261696338653564} 08/31/2021 03:33:38 - INFO - __main__ - Step 79102: {'lr': 0.00023355566709217735, 'samples': 15187584, 'steps': 79101, 'loss/train': 1.3478610515594482} 08/31/2021 03:33:38 - INFO - __main__ - Step 79103: {'lr': 0.00023355037184421217, 'samples': 15187776, 'steps': 79102, 'loss/train': 1.274300456047058} 08/31/2021 03:33:39 - INFO - __main__ - Step 79104: {'lr': 0.00023354507660365895, 'samples': 15187968, 'steps': 79103, 'loss/train': 1.1954963207244873} 08/31/2021 03:33:39 - INFO - __main__ - Step 79105: {'lr': 0.00023353978137052007, 'samples': 15188160, 'steps': 79104, 'loss/train': 2.1514923572540283} 08/31/2021 03:33:41 - INFO - __main__ - Step 79106: {'lr': 0.0002335344861447979, 'samples': 15188352, 'steps': 79105, 'loss/train': 0.339777410030365} 08/31/2021 03:33:42 - INFO - __main__ - Step 79107: {'lr': 0.0002335291909264948, 'samples': 15188544, 'steps': 79106, 'loss/train': 1.2690045833587646} 08/31/2021 03:33:42 - INFO - __main__ - Step 79108: {'lr': 0.00023352389571561322, 'samples': 15188736, 'steps': 79107, 'loss/train': 1.0860029458999634} 08/31/2021 03:33:43 - INFO - __main__ - Step 79109: {'lr': 0.00023351860051215554, 'samples': 15188928, 'steps': 79108, 'loss/train': 1.6159167289733887} 08/31/2021 03:33:43 - INFO - __main__ - Step 79110: {'lr': 0.00023351330531612408, 'samples': 15189120, 'steps': 79109, 'loss/train': 0.07553321868181229} 08/31/2021 03:33:44 - INFO - __main__ - Step 79111: {'lr': 0.00023350801012752133, 'samples': 15189312, 'steps': 79110, 'loss/train': 1.308990240097046} 08/31/2021 03:33:45 - INFO - __main__ - Step 79112: {'lr': 0.00023350271494634956, 'samples': 15189504, 'steps': 79111, 'loss/train': 1.0509392023086548} 08/31/2021 03:33:45 - INFO - __main__ - Step 79113: {'lr': 0.00023349741977261125, 'samples': 15189696, 'steps': 79112, 'loss/train': 1.1719456911087036} 08/31/2021 03:33:45 - INFO - __main__ - Step 79114: {'lr': 0.0002334921246063088, 'samples': 15189888, 'steps': 79113, 'loss/train': 1.2116564512252808} 08/31/2021 03:33:46 - INFO - __main__ - Step 79115: {'lr': 0.0002334868294474445, 'samples': 15190080, 'steps': 79114, 'loss/train': 1.0450774431228638} 08/31/2021 03:33:46 - INFO - __main__ - Step 79116: {'lr': 0.00023348153429602077, 'samples': 15190272, 'steps': 79115, 'loss/train': 0.5753931403160095} 08/31/2021 03:33:48 - INFO - __main__ - Step 79117: {'lr': 0.00023347623915203998, 'samples': 15190464, 'steps': 79116, 'loss/train': 1.1449580192565918} 08/31/2021 03:33:48 - INFO - __main__ - Step 79118: {'lr': 0.00023347094401550457, 'samples': 15190656, 'steps': 79117, 'loss/train': 0.8042795658111572} 08/31/2021 03:33:48 - INFO - __main__ - Step 79119: {'lr': 0.00023346564888641685, 'samples': 15190848, 'steps': 79118, 'loss/train': 1.2954047918319702} 08/31/2021 03:33:49 - INFO - __main__ - Step 79120: {'lr': 0.00023346035376477928, 'samples': 15191040, 'steps': 79119, 'loss/train': 0.8021726012229919} 08/31/2021 03:33:49 - INFO - __main__ - Step 79121: {'lr': 0.00023345505865059424, 'samples': 15191232, 'steps': 79120, 'loss/train': 1.0142568349838257} 08/31/2021 03:33:51 - INFO - __main__ - Step 79122: {'lr': 0.00023344976354386406, 'samples': 15191424, 'steps': 79121, 'loss/train': 1.6660614013671875} 08/31/2021 03:33:51 - INFO - __main__ - Step 79123: {'lr': 0.0002334444684445912, 'samples': 15191616, 'steps': 79122, 'loss/train': 1.2604739665985107} 08/31/2021 03:33:52 - INFO - __main__ - Step 79124: {'lr': 0.00023343917335277799, 'samples': 15191808, 'steps': 79123, 'loss/train': 1.1790515184402466} 08/31/2021 03:33:52 - INFO - __main__ - Step 79125: {'lr': 0.00023343387826842683, 'samples': 15192000, 'steps': 79124, 'loss/train': 1.2264326810836792} 08/31/2021 03:33:52 - INFO - __main__ - Step 79126: {'lr': 0.00023342858319154008, 'samples': 15192192, 'steps': 79125, 'loss/train': 1.2542835474014282} 08/31/2021 03:33:54 - INFO - __main__ - Step 79127: {'lr': 0.0002334232881221203, 'samples': 15192384, 'steps': 79126, 'loss/train': 1.2584127187728882} 08/31/2021 03:33:54 - INFO - __main__ - Step 79128: {'lr': 0.0002334179930601696, 'samples': 15192576, 'steps': 79127, 'loss/train': 1.2338837385177612} 08/31/2021 03:33:55 - INFO - __main__ - Step 79129: {'lr': 0.00023341269800569053, 'samples': 15192768, 'steps': 79128, 'loss/train': 0.6764968037605286} 08/31/2021 03:33:55 - INFO - __main__ - Step 79130: {'lr': 0.00023340740295868542, 'samples': 15192960, 'steps': 79129, 'loss/train': 0.41483524441719055} 08/31/2021 03:33:55 - INFO - __main__ - Step 79131: {'lr': 0.00023340210791915667, 'samples': 15193152, 'steps': 79130, 'loss/train': 0.9438772201538086} 08/31/2021 03:33:57 - INFO - __main__ - Step 79132: {'lr': 0.00023339681288710667, 'samples': 15193344, 'steps': 79131, 'loss/train': 1.405869722366333} 08/31/2021 03:33:57 - INFO - __main__ - Step 79133: {'lr': 0.00023339151786253785, 'samples': 15193536, 'steps': 79132, 'loss/train': 0.8338282108306885} 08/31/2021 03:33:58 - INFO - __main__ - Step 79134: {'lr': 0.00023338622284545252, 'samples': 15193728, 'steps': 79133, 'loss/train': 1.4922294616699219} 08/31/2021 03:33:58 - INFO - __main__ - Step 79135: {'lr': 0.00023338092783585312, 'samples': 15193920, 'steps': 79134, 'loss/train': 0.935499370098114} 08/31/2021 03:33:58 - INFO - __main__ - Step 79136: {'lr': 0.000233375632833742, 'samples': 15194112, 'steps': 79135, 'loss/train': 0.7763375043869019} 08/31/2021 03:34:00 - INFO - __main__ - Step 79137: {'lr': 0.00023337033783912164, 'samples': 15194304, 'steps': 79136, 'loss/train': 1.686915636062622} 08/31/2021 03:34:00 - INFO - __main__ - Step 79138: {'lr': 0.00023336504285199428, 'samples': 15194496, 'steps': 79137, 'loss/train': 1.7636951208114624} 08/31/2021 03:34:01 - INFO - __main__ - Step 79139: {'lr': 0.00023335974787236236, 'samples': 15194688, 'steps': 79138, 'loss/train': 1.040594458580017} 08/31/2021 03:34:01 - INFO - __main__ - Step 79140: {'lr': 0.0002333544529002283, 'samples': 15194880, 'steps': 79139, 'loss/train': 1.6736228466033936} 08/31/2021 03:34:01 - INFO - __main__ - Step 79141: {'lr': 0.00023334915793559453, 'samples': 15195072, 'steps': 79140, 'loss/train': 1.6341863870620728} 08/31/2021 03:34:02 - INFO - __main__ - Step 79142: {'lr': 0.0002333438629784633, 'samples': 15195264, 'steps': 79141, 'loss/train': 2.0728440284729004} 08/31/2021 03:34:03 - INFO - __main__ - Step 79143: {'lr': 0.00023333856802883708, 'samples': 15195456, 'steps': 79142, 'loss/train': 0.9390836954116821} 08/31/2021 03:34:04 - INFO - __main__ - Step 79144: {'lr': 0.00023333327308671823, 'samples': 15195648, 'steps': 79143, 'loss/train': 1.2193670272827148} 08/31/2021 03:34:04 - INFO - __main__ - Step 79145: {'lr': 0.00023332797815210917, 'samples': 15195840, 'steps': 79144, 'loss/train': 0.695025622844696} 08/31/2021 03:34:04 - INFO - __main__ - Step 79146: {'lr': 0.00023332268322501226, 'samples': 15196032, 'steps': 79145, 'loss/train': 0.3041679859161377} 08/31/2021 03:34:05 - INFO - __main__ - Step 79147: {'lr': 0.00023331738830542986, 'samples': 15196224, 'steps': 79146, 'loss/train': 1.422894835472107} 08/31/2021 03:34:06 - INFO - __main__ - Step 79148: {'lr': 0.00023331209339336447, 'samples': 15196416, 'steps': 79147, 'loss/train': 0.9786250591278076} 08/31/2021 03:34:07 - INFO - __main__ - Step 79149: {'lr': 0.00023330679848881835, 'samples': 15196608, 'steps': 79148, 'loss/train': 0.97740638256073} 08/31/2021 03:34:07 - INFO - __main__ - Step 79150: {'lr': 0.0002333015035917939, 'samples': 15196800, 'steps': 79149, 'loss/train': 1.1481877565383911} 08/31/2021 03:34:07 - INFO - __main__ - Step 79151: {'lr': 0.00023329620870229356, 'samples': 15196992, 'steps': 79150, 'loss/train': 0.9085837602615356} 08/31/2021 03:34:08 - INFO - __main__ - Step 79152: {'lr': 0.0002332909138203197, 'samples': 15197184, 'steps': 79151, 'loss/train': 0.9573674201965332} 08/31/2021 03:34:09 - INFO - __main__ - Step 79153: {'lr': 0.00023328561894587466, 'samples': 15197376, 'steps': 79152, 'loss/train': 0.7943673133850098} 08/31/2021 03:34:10 - INFO - __main__ - Step 79154: {'lr': 0.00023328032407896095, 'samples': 15197568, 'steps': 79153, 'loss/train': 0.7068349719047546} 08/31/2021 03:34:10 - INFO - __main__ - Step 79155: {'lr': 0.0002332750292195808, 'samples': 15197760, 'steps': 79154, 'loss/train': 0.4139844477176666} 08/31/2021 03:34:10 - INFO - __main__ - Step 79156: {'lr': 0.00023326973436773666, 'samples': 15197952, 'steps': 79155, 'loss/train': 1.1299315690994263} 08/31/2021 03:34:11 - INFO - __main__ - Step 79157: {'lr': 0.0002332644395234309, 'samples': 15198144, 'steps': 79156, 'loss/train': 1.5199393033981323} 08/31/2021 03:34:13 - INFO - __main__ - Step 79158: {'lr': 0.00023325914468666595, 'samples': 15198336, 'steps': 79157, 'loss/train': 1.1092129945755005} 08/31/2021 03:34:13 - INFO - __main__ - Step 79159: {'lr': 0.00023325384985744424, 'samples': 15198528, 'steps': 79158, 'loss/train': 1.29552161693573} 08/31/2021 03:34:13 - INFO - __main__ - Step 79160: {'lr': 0.000233248555035768, 'samples': 15198720, 'steps': 79159, 'loss/train': 1.54430091381073} 08/31/2021 03:34:14 - INFO - __main__ - Step 79161: {'lr': 0.00023324326022163973, 'samples': 15198912, 'steps': 79160, 'loss/train': 0.9092010855674744} 08/31/2021 03:34:14 - INFO - __main__ - Step 79162: {'lr': 0.00023323796541506177, 'samples': 15199104, 'steps': 79161, 'loss/train': 0.5747483372688293} 08/31/2021 03:34:16 - INFO - __main__ - Step 79163: {'lr': 0.00023323267061603654, 'samples': 15199296, 'steps': 79162, 'loss/train': 0.5390555262565613} 08/31/2021 03:34:16 - INFO - __main__ - Step 79164: {'lr': 0.00023322737582456637, 'samples': 15199488, 'steps': 79163, 'loss/train': 1.1817337274551392} 08/31/2021 03:34:17 - INFO - __main__ - Step 79165: {'lr': 0.00023322208104065373, 'samples': 15199680, 'steps': 79164, 'loss/train': 0.06554839015007019} 08/31/2021 03:34:17 - INFO - __main__ - Step 79166: {'lr': 0.00023321678626430097, 'samples': 15199872, 'steps': 79165, 'loss/train': 0.8504214286804199} 08/31/2021 03:34:17 - INFO - __main__ - Step 79167: {'lr': 0.0002332114914955104, 'samples': 15200064, 'steps': 79166, 'loss/train': 1.4890732765197754} 08/31/2021 03:34:19 - INFO - __main__ - Step 79168: {'lr': 0.0002332061967342846, 'samples': 15200256, 'steps': 79167, 'loss/train': 1.0634568929672241} 08/31/2021 03:34:19 - INFO - __main__ - Step 79169: {'lr': 0.00023320090198062575, 'samples': 15200448, 'steps': 79168, 'loss/train': 0.42514732480049133} 08/31/2021 03:34:20 - INFO - __main__ - Step 79170: {'lr': 0.00023319560723453637, 'samples': 15200640, 'steps': 79169, 'loss/train': 1.1387829780578613} 08/31/2021 03:34:20 - INFO - __main__ - Step 79171: {'lr': 0.0002331903124960187, 'samples': 15200832, 'steps': 79170, 'loss/train': 0.616592526435852} 08/31/2021 03:34:20 - INFO - __main__ - Step 79172: {'lr': 0.00023318501776507526, 'samples': 15201024, 'steps': 79171, 'loss/train': 1.0323017835617065} 08/31/2021 03:34:22 - INFO - __main__ - Step 79173: {'lr': 0.00023317972304170837, 'samples': 15201216, 'steps': 79172, 'loss/train': 0.891019880771637} 08/31/2021 03:34:22 - INFO - __main__ - Step 79174: {'lr': 0.00023317442832592044, 'samples': 15201408, 'steps': 79173, 'loss/train': 0.5954088568687439} 08/31/2021 03:34:23 - INFO - __main__ - Step 79175: {'lr': 0.00023316913361771385, 'samples': 15201600, 'steps': 79174, 'loss/train': 0.9994905591011047} 08/31/2021 03:34:23 - INFO - __main__ - Step 79176: {'lr': 0.000233163838917091, 'samples': 15201792, 'steps': 79175, 'loss/train': 1.6447018384933472} 08/31/2021 03:34:23 - INFO - __main__ - Step 79177: {'lr': 0.00023315854422405427, 'samples': 15201984, 'steps': 79176, 'loss/train': 1.0527782440185547} 08/31/2021 03:34:24 - INFO - __main__ - Step 79178: {'lr': 0.00023315324953860603, 'samples': 15202176, 'steps': 79177, 'loss/train': 1.3398405313491821} 08/31/2021 03:34:26 - INFO - __main__ - Step 79179: {'lr': 0.0002331479548607487, 'samples': 15202368, 'steps': 79178, 'loss/train': 1.2859225273132324} 08/31/2021 03:34:26 - INFO - __main__ - Step 79180: {'lr': 0.00023314266019048457, 'samples': 15202560, 'steps': 79179, 'loss/train': 1.6664574146270752} 08/31/2021 03:34:26 - INFO - __main__ - Step 79181: {'lr': 0.00023313736552781628, 'samples': 15202752, 'steps': 79180, 'loss/train': 0.6843520998954773} 08/31/2021 03:34:27 - INFO - __main__ - Step 79182: {'lr': 0.0002331320708727459, 'samples': 15202944, 'steps': 79181, 'loss/train': 0.9271314740180969} 08/31/2021 03:34:27 - INFO - __main__ - Step 79183: {'lr': 0.00023312677622527595, 'samples': 15203136, 'steps': 79182, 'loss/train': 0.4159197211265564} 08/31/2021 03:34:29 - INFO - __main__ - Step 79184: {'lr': 0.0002331214815854088, 'samples': 15203328, 'steps': 79183, 'loss/train': 0.8706341981887817} 08/31/2021 03:34:29 - INFO - __main__ - Step 79185: {'lr': 0.00023311618695314685, 'samples': 15203520, 'steps': 79184, 'loss/train': 1.1591663360595703} 08/31/2021 03:34:29 - INFO - __main__ - Step 79186: {'lr': 0.0002331108923284925, 'samples': 15203712, 'steps': 79185, 'loss/train': 1.9004054069519043} 08/31/2021 03:34:30 - INFO - __main__ - Step 79187: {'lr': 0.00023310559771144812, 'samples': 15203904, 'steps': 79186, 'loss/train': 1.0534871816635132} 08/31/2021 03:34:30 - INFO - __main__ - Step 79188: {'lr': 0.00023310030310201612, 'samples': 15204096, 'steps': 79187, 'loss/train': 1.0774544477462769} 08/31/2021 03:34:31 - INFO - __main__ - Step 79189: {'lr': 0.0002330950085001988, 'samples': 15204288, 'steps': 79188, 'loss/train': 1.2684742212295532} 08/31/2021 03:34:32 - INFO - __main__ - Step 79190: {'lr': 0.00023308971390599865, 'samples': 15204480, 'steps': 79189, 'loss/train': 0.6476047039031982} 08/31/2021 03:34:32 - INFO - __main__ - Step 79191: {'lr': 0.00023308441931941802, 'samples': 15204672, 'steps': 79190, 'loss/train': 1.0824699401855469} 08/31/2021 03:34:33 - INFO - __main__ - Step 79192: {'lr': 0.00023307912474045928, 'samples': 15204864, 'steps': 79191, 'loss/train': 0.20268514752388} 08/31/2021 03:34:33 - INFO - __main__ - Step 79193: {'lr': 0.0002330738301691248, 'samples': 15205056, 'steps': 79192, 'loss/train': 1.1788640022277832} 08/31/2021 03:34:33 - INFO - __main__ - Step 79194: {'lr': 0.00023306853560541705, 'samples': 15205248, 'steps': 79193, 'loss/train': 1.3370574712753296} 08/31/2021 03:34:35 - INFO - __main__ - Step 79195: {'lr': 0.0002330632410493384, 'samples': 15205440, 'steps': 79194, 'loss/train': 1.167311191558838} 08/31/2021 03:34:35 - INFO - __main__ - Step 79196: {'lr': 0.00023305794650089112, 'samples': 15205632, 'steps': 79195, 'loss/train': 1.8346107006072998} 08/31/2021 03:34:36 - INFO - __main__ - Step 79197: {'lr': 0.0002330526519600777, 'samples': 15205824, 'steps': 79196, 'loss/train': 1.6300286054611206} 08/31/2021 03:34:36 - INFO - __main__ - Step 79198: {'lr': 0.00023304735742690042, 'samples': 15206016, 'steps': 79197, 'loss/train': 1.484020471572876} 08/31/2021 03:34:36 - INFO - __main__ - Step 79199: {'lr': 0.00023304206290136178, 'samples': 15206208, 'steps': 79198, 'loss/train': 1.3642226457595825} 08/31/2021 03:34:38 - INFO - __main__ - Step 79200: {'lr': 0.00023303676838346414, 'samples': 15206400, 'steps': 79199, 'loss/train': 1.432074785232544} 08/31/2021 03:34:38 - INFO - __main__ - Step 79201: {'lr': 0.00023303147387320982, 'samples': 15206592, 'steps': 79200, 'loss/train': 0.9904899001121521} 08/31/2021 03:34:39 - INFO - __main__ - Step 79202: {'lr': 0.0002330261793706013, 'samples': 15206784, 'steps': 79201, 'loss/train': 1.2059125900268555} 08/31/2021 03:34:39 - INFO - __main__ - Step 79203: {'lr': 0.0002330208848756409, 'samples': 15206976, 'steps': 79202, 'loss/train': 0.18386676907539368} 08/31/2021 03:34:39 - INFO - __main__ - Step 79204: {'lr': 0.00023301559038833104, 'samples': 15207168, 'steps': 79203, 'loss/train': 1.2240543365478516} 08/31/2021 03:34:41 - INFO - __main__ - Step 79205: {'lr': 0.0002330102959086741, 'samples': 15207360, 'steps': 79204, 'loss/train': 1.3061249256134033} 08/31/2021 03:34:42 - INFO - __main__ - Step 79206: {'lr': 0.00023300500143667245, 'samples': 15207552, 'steps': 79205, 'loss/train': 0.6960486769676208} 08/31/2021 03:34:42 - INFO - __main__ - Step 79207: {'lr': 0.00023299970697232848, 'samples': 15207744, 'steps': 79206, 'loss/train': 1.5954684019088745} 08/31/2021 03:34:42 - INFO - __main__ - Step 79208: {'lr': 0.00023299441251564468, 'samples': 15207936, 'steps': 79207, 'loss/train': 0.6907111406326294} 08/31/2021 03:34:43 - INFO - __main__ - Step 79209: {'lr': 0.00023298911806662322, 'samples': 15208128, 'steps': 79208, 'loss/train': 1.6696735620498657} 08/31/2021 03:34:44 - INFO - __main__ - Step 79210: {'lr': 0.00023298382362526662, 'samples': 15208320, 'steps': 79209, 'loss/train': 1.2055385112762451} 08/31/2021 03:34:45 - INFO - __main__ - Step 79211: {'lr': 0.00023297852919157725, 'samples': 15208512, 'steps': 79210, 'loss/train': 1.3750747442245483} 08/31/2021 03:34:45 - INFO - __main__ - Step 79212: {'lr': 0.00023297323476555748, 'samples': 15208704, 'steps': 79211, 'loss/train': 1.220378041267395} 08/31/2021 03:34:45 - INFO - __main__ - Step 79213: {'lr': 0.0002329679403472097, 'samples': 15208896, 'steps': 79212, 'loss/train': 1.0103394985198975} 08/31/2021 03:34:46 - INFO - __main__ - Step 79214: {'lr': 0.00023296264593653632, 'samples': 15209088, 'steps': 79213, 'loss/train': 1.1159003973007202} 08/31/2021 03:34:46 - INFO - __main__ - Step 79215: {'lr': 0.0002329573515335397, 'samples': 15209280, 'steps': 79214, 'loss/train': 0.8627204895019531} 08/31/2021 03:34:48 - INFO - __main__ - Step 79216: {'lr': 0.00023295205713822227, 'samples': 15209472, 'steps': 79215, 'loss/train': 1.3027058839797974} 08/31/2021 03:34:49 - INFO - __main__ - Step 79217: {'lr': 0.0002329467627505863, 'samples': 15209664, 'steps': 79216, 'loss/train': 1.2777262926101685} 08/31/2021 03:34:49 - INFO - __main__ - Step 79218: {'lr': 0.00023294146837063431, 'samples': 15209856, 'steps': 79217, 'loss/train': 1.088944435119629} 08/31/2021 03:34:49 - INFO - __main__ - Step 79219: {'lr': 0.00023293617399836863, 'samples': 15210048, 'steps': 79218, 'loss/train': 1.4999510049819946} 08/31/2021 03:34:50 - INFO - __main__ - Step 79220: {'lr': 0.00023293087963379168, 'samples': 15210240, 'steps': 79219, 'loss/train': 1.2307274341583252} 08/31/2021 03:34:51 - INFO - __main__ - Step 79221: {'lr': 0.00023292558527690575, 'samples': 15210432, 'steps': 79220, 'loss/train': 1.1626797914505005} 08/31/2021 03:34:52 - INFO - __main__ - Step 79222: {'lr': 0.0002329202909277134, 'samples': 15210624, 'steps': 79221, 'loss/train': 0.26612257957458496} 08/31/2021 03:34:52 - INFO - __main__ - Step 79223: {'lr': 0.00023291499658621684, 'samples': 15210816, 'steps': 79222, 'loss/train': 1.029839277267456} 08/31/2021 03:34:52 - INFO - __main__ - Step 79224: {'lr': 0.0002329097022524185, 'samples': 15211008, 'steps': 79223, 'loss/train': 0.6137822270393372} 08/31/2021 03:34:53 - INFO - __main__ - Step 79225: {'lr': 0.0002329044079263208, 'samples': 15211200, 'steps': 79224, 'loss/train': 1.5844887495040894} 08/31/2021 03:34:54 - INFO - __main__ - Step 79226: {'lr': 0.00023289911360792608, 'samples': 15211392, 'steps': 79225, 'loss/train': 1.166760802268982} 08/31/2021 03:34:55 - INFO - __main__ - Step 79227: {'lr': 0.00023289381929723674, 'samples': 15211584, 'steps': 79226, 'loss/train': 1.4969884157180786} 08/31/2021 03:34:55 - INFO - __main__ - Step 79228: {'lr': 0.00023288852499425523, 'samples': 15211776, 'steps': 79227, 'loss/train': 1.5837881565093994} 08/31/2021 03:34:55 - INFO - __main__ - Step 79229: {'lr': 0.00023288323069898384, 'samples': 15211968, 'steps': 79228, 'loss/train': 1.3246382474899292} 08/31/2021 03:34:56 - INFO - __main__ - Step 79230: {'lr': 0.000232877936411425, 'samples': 15212160, 'steps': 79229, 'loss/train': 0.9279369115829468} 08/31/2021 03:34:57 - INFO - __main__ - Step 79231: {'lr': 0.00023287264213158116, 'samples': 15212352, 'steps': 79230, 'loss/train': 1.3039405345916748} 08/31/2021 03:34:57 - INFO - __main__ - Step 79232: {'lr': 0.00023286734785945458, 'samples': 15212544, 'steps': 79231, 'loss/train': 1.3182224035263062} 08/31/2021 03:34:58 - INFO - __main__ - Step 79233: {'lr': 0.00023286205359504775, 'samples': 15212736, 'steps': 79232, 'loss/train': 1.0750147104263306} 08/31/2021 03:34:58 - INFO - __main__ - Step 79234: {'lr': 0.00023285675933836297, 'samples': 15212928, 'steps': 79233, 'loss/train': 1.7629317045211792} 08/31/2021 03:34:59 - INFO - __main__ - Step 79235: {'lr': 0.00023285146508940282, 'samples': 15213120, 'steps': 79234, 'loss/train': 1.2998746633529663} 08/31/2021 03:35:00 - INFO - __main__ - Step 79236: {'lr': 0.00023284617084816942, 'samples': 15213312, 'steps': 79235, 'loss/train': 0.9937770962715149} 08/31/2021 03:35:00 - INFO - __main__ - Step 79237: {'lr': 0.00023284087661466527, 'samples': 15213504, 'steps': 79236, 'loss/train': 1.2016282081604004} 08/31/2021 03:35:01 - INFO - __main__ - Step 79238: {'lr': 0.00023283558238889273, 'samples': 15213696, 'steps': 79237, 'loss/train': 0.7536401748657227} 08/31/2021 03:35:01 - INFO - __main__ - Step 79239: {'lr': 0.00023283028817085424, 'samples': 15213888, 'steps': 79238, 'loss/train': 1.1639050245285034} 08/31/2021 03:35:01 - INFO - __main__ - Step 79240: {'lr': 0.00023282499396055215, 'samples': 15214080, 'steps': 79239, 'loss/train': 1.0384334325790405} 08/31/2021 03:35:03 - INFO - __main__ - Step 79241: {'lr': 0.00023281969975798885, 'samples': 15214272, 'steps': 79240, 'loss/train': 1.1886448860168457} 08/31/2021 03:35:04 - INFO - __main__ - Step 79242: {'lr': 0.00023281440556316673, 'samples': 15214464, 'steps': 79241, 'loss/train': 1.2620784044265747} 08/31/2021 03:35:04 - INFO - __main__ - Step 79243: {'lr': 0.00023280911137608818, 'samples': 15214656, 'steps': 79242, 'loss/train': 1.853267788887024} 08/31/2021 03:35:04 - INFO - __main__ - Step 79244: {'lr': 0.0002328038171967556, 'samples': 15214848, 'steps': 79243, 'loss/train': 0.7748916149139404} 08/31/2021 03:35:05 - INFO - __main__ - Step 79245: {'lr': 0.00023279852302517129, 'samples': 15215040, 'steps': 79244, 'loss/train': 1.0223236083984375} 08/31/2021 03:35:06 - INFO - __main__ - Step 79246: {'lr': 0.00023279322886133775, 'samples': 15215232, 'steps': 79245, 'loss/train': 1.580461025238037} 08/31/2021 03:35:07 - INFO - __main__ - Step 79247: {'lr': 0.0002327879347052573, 'samples': 15215424, 'steps': 79246, 'loss/train': 1.1125645637512207} 08/31/2021 03:35:07 - INFO - __main__ - Step 79248: {'lr': 0.00023278264055693243, 'samples': 15215616, 'steps': 79247, 'loss/train': 1.257835030555725} 08/31/2021 03:35:07 - INFO - __main__ - Step 79249: {'lr': 0.00023277734641636536, 'samples': 15215808, 'steps': 79248, 'loss/train': 1.1059379577636719} 08/31/2021 03:35:08 - INFO - __main__ - Step 79250: {'lr': 0.00023277205228355855, 'samples': 15216000, 'steps': 79249, 'loss/train': 1.1801209449768066} 08/31/2021 03:35:09 - INFO - __main__ - Step 79251: {'lr': 0.0002327667581585144, 'samples': 15216192, 'steps': 79250, 'loss/train': 1.940804362297058} 08/31/2021 03:35:10 - INFO - __main__ - Step 79252: {'lr': 0.00023276146404123524, 'samples': 15216384, 'steps': 79251, 'loss/train': 1.232543706893921} 08/31/2021 03:35:10 - INFO - __main__ - Step 79253: {'lr': 0.0002327561699317235, 'samples': 15216576, 'steps': 79252, 'loss/train': 1.4930505752563477} 08/31/2021 03:35:10 - INFO - __main__ - Step 79254: {'lr': 0.0002327508758299816, 'samples': 15216768, 'steps': 79253, 'loss/train': 1.7233234643936157} 08/31/2021 03:35:11 - INFO - __main__ - Step 79255: {'lr': 0.00023274558173601187, 'samples': 15216960, 'steps': 79254, 'loss/train': 1.2308131456375122} 08/31/2021 03:35:13 - INFO - __main__ - Step 79256: {'lr': 0.00023274028764981672, 'samples': 15217152, 'steps': 79255, 'loss/train': 1.342047929763794} 08/31/2021 03:35:13 - INFO - __main__ - Step 79257: {'lr': 0.00023273499357139853, 'samples': 15217344, 'steps': 79256, 'loss/train': 0.9909289479255676} 08/31/2021 03:35:14 - INFO - __main__ - Step 79258: {'lr': 0.0002327296995007597, 'samples': 15217536, 'steps': 79257, 'loss/train': 1.569649338722229} 08/31/2021 03:35:14 - INFO - __main__ - Step 79259: {'lr': 0.0002327244054379026, 'samples': 15217728, 'steps': 79258, 'loss/train': 0.9431356191635132} 08/31/2021 03:35:14 - INFO - __main__ - Step 79260: {'lr': 0.00023271911138282957, 'samples': 15217920, 'steps': 79259, 'loss/train': 1.7195574045181274} 08/31/2021 03:35:15 - INFO - __main__ - Step 79261: {'lr': 0.00023271381733554314, 'samples': 15218112, 'steps': 79260, 'loss/train': 0.3672119677066803} 08/31/2021 03:35:15 - INFO - __main__ - Step 79262: {'lr': 0.00023270852329604558, 'samples': 15218304, 'steps': 79261, 'loss/train': 0.3472791910171509} 08/31/2021 03:35:16 - INFO - __main__ - Step 79263: {'lr': 0.00023270322926433924, 'samples': 15218496, 'steps': 79262, 'loss/train': 1.0027458667755127} 08/31/2021 03:35:17 - INFO - __main__ - Step 79264: {'lr': 0.00023269793524042658, 'samples': 15218688, 'steps': 79263, 'loss/train': 0.9003511667251587} 08/31/2021 03:35:17 - INFO - __main__ - Step 79265: {'lr': 0.00023269264122430992, 'samples': 15218880, 'steps': 79264, 'loss/train': 1.1886179447174072} 08/31/2021 03:35:18 - INFO - __main__ - Step 79266: {'lr': 0.00023268734721599172, 'samples': 15219072, 'steps': 79265, 'loss/train': 1.107783555984497} 08/31/2021 03:35:18 - INFO - __main__ - Step 79267: {'lr': 0.0002326820532154743, 'samples': 15219264, 'steps': 79266, 'loss/train': 1.1311818361282349} 08/31/2021 03:35:20 - INFO - __main__ - Step 79268: {'lr': 0.00023267675922276012, 'samples': 15219456, 'steps': 79267, 'loss/train': 1.2496302127838135} 08/31/2021 03:35:21 - INFO - __main__ - Step 79269: {'lr': 0.00023267146523785152, 'samples': 15219648, 'steps': 79268, 'loss/train': 0.9841256737709045} 08/31/2021 03:35:21 - INFO - __main__ - Step 79270: {'lr': 0.00023266617126075089, 'samples': 15219840, 'steps': 79269, 'loss/train': 1.130708932876587} 08/31/2021 03:35:21 - INFO - __main__ - Step 79271: {'lr': 0.0002326608772914606, 'samples': 15220032, 'steps': 79270, 'loss/train': 0.9376328587532043} 08/31/2021 03:35:22 - INFO - __main__ - Step 79272: {'lr': 0.0002326555833299831, 'samples': 15220224, 'steps': 79271, 'loss/train': 1.2319004535675049} 08/31/2021 03:35:23 - INFO - __main__ - Step 79273: {'lr': 0.0002326502893763207, 'samples': 15220416, 'steps': 79272, 'loss/train': 0.850431501865387} 08/31/2021 03:35:24 - INFO - __main__ - Step 79274: {'lr': 0.0002326449954304758, 'samples': 15220608, 'steps': 79273, 'loss/train': 0.25772368907928467} 08/31/2021 03:35:24 - INFO - __main__ - Step 79275: {'lr': 0.00023263970149245083, 'samples': 15220800, 'steps': 79274, 'loss/train': 2.002782106399536} 08/31/2021 03:35:24 - INFO - __main__ - Step 79276: {'lr': 0.00023263440756224812, 'samples': 15220992, 'steps': 79275, 'loss/train': 1.0505025386810303} 08/31/2021 03:35:25 - INFO - __main__ - Step 79277: {'lr': 0.00023262911363987004, 'samples': 15221184, 'steps': 79276, 'loss/train': 1.0568853616714478} 08/31/2021 03:35:26 - INFO - __main__ - Step 79278: {'lr': 0.00023262381972531906, 'samples': 15221376, 'steps': 79277, 'loss/train': 0.8864465355873108} 08/31/2021 03:35:27 - INFO - __main__ - Step 79279: {'lr': 0.00023261852581859749, 'samples': 15221568, 'steps': 79278, 'loss/train': 1.0153676271438599} 08/31/2021 03:35:27 - INFO - __main__ - Step 79280: {'lr': 0.00023261323191970775, 'samples': 15221760, 'steps': 79279, 'loss/train': 1.1434913873672485} 08/31/2021 03:35:27 - INFO - __main__ - Step 79281: {'lr': 0.00023260793802865225, 'samples': 15221952, 'steps': 79280, 'loss/train': 0.8248254656791687} 08/31/2021 03:35:28 - INFO - __main__ - Step 79282: {'lr': 0.0002326026441454333, 'samples': 15222144, 'steps': 79281, 'loss/train': 0.7078026533126831} 08/31/2021 03:35:28 - INFO - __main__ - Step 79283: {'lr': 0.00023259735027005338, 'samples': 15222336, 'steps': 79282, 'loss/train': 0.8533860445022583} 08/31/2021 03:35:30 - INFO - __main__ - Step 79284: {'lr': 0.0002325920564025148, 'samples': 15222528, 'steps': 79283, 'loss/train': 1.6957355737686157} 08/31/2021 03:35:30 - INFO - __main__ - Step 79285: {'lr': 0.00023258676254281997, 'samples': 15222720, 'steps': 79284, 'loss/train': 0.6177197098731995} 08/31/2021 03:35:30 - INFO - __main__ - Step 79286: {'lr': 0.00023258146869097128, 'samples': 15222912, 'steps': 79285, 'loss/train': 0.6428428888320923} 08/31/2021 03:35:31 - INFO - __main__ - Step 79287: {'lr': 0.00023257617484697107, 'samples': 15223104, 'steps': 79286, 'loss/train': 1.7392174005508423} 08/31/2021 03:35:31 - INFO - __main__ - Step 79288: {'lr': 0.0002325708810108218, 'samples': 15223296, 'steps': 79287, 'loss/train': 0.02782083861529827} 08/31/2021 03:35:33 - INFO - __main__ - Step 79289: {'lr': 0.0002325655871825259, 'samples': 15223488, 'steps': 79288, 'loss/train': 0.7344481348991394} 08/31/2021 03:35:33 - INFO - __main__ - Step 79290: {'lr': 0.00023256029336208556, 'samples': 15223680, 'steps': 79289, 'loss/train': 0.6228556036949158} 08/31/2021 03:35:33 - INFO - __main__ - Step 79291: {'lr': 0.00023255499954950333, 'samples': 15223872, 'steps': 79290, 'loss/train': 1.561629056930542} 08/31/2021 03:35:34 - INFO - __main__ - Step 79292: {'lr': 0.00023254970574478154, 'samples': 15224064, 'steps': 79291, 'loss/train': 1.4317420721054077} 08/31/2021 03:35:34 - INFO - __main__ - Step 79293: {'lr': 0.00023254441194792258, 'samples': 15224256, 'steps': 79292, 'loss/train': 0.6751099824905396} 08/31/2021 03:35:36 - INFO - __main__ - Step 79294: {'lr': 0.00023253911815892888, 'samples': 15224448, 'steps': 79293, 'loss/train': 1.522025465965271} 08/31/2021 03:35:36 - INFO - __main__ - Step 79295: {'lr': 0.00023253382437780275, 'samples': 15224640, 'steps': 79294, 'loss/train': 1.4707931280136108} 08/31/2021 03:35:36 - INFO - __main__ - Step 79296: {'lr': 0.0002325285306045466, 'samples': 15224832, 'steps': 79295, 'loss/train': 1.2797232866287231} 08/31/2021 03:35:37 - INFO - __main__ - Step 79297: {'lr': 0.00023252323683916283, 'samples': 15225024, 'steps': 79296, 'loss/train': 1.546958088874817} 08/31/2021 03:35:37 - INFO - __main__ - Step 79298: {'lr': 0.0002325179430816538, 'samples': 15225216, 'steps': 79297, 'loss/train': 1.5058616399765015} 08/31/2021 03:35:39 - INFO - __main__ - Step 79299: {'lr': 0.00023251264933202192, 'samples': 15225408, 'steps': 79298, 'loss/train': 1.33733332157135} 08/31/2021 03:35:39 - INFO - __main__ - Step 79300: {'lr': 0.0002325073555902696, 'samples': 15225600, 'steps': 79299, 'loss/train': 1.7108360528945923} 08/31/2021 03:35:39 - INFO - __main__ - Step 79301: {'lr': 0.00023250206185639917, 'samples': 15225792, 'steps': 79300, 'loss/train': 0.6771460771560669} 08/31/2021 03:35:40 - INFO - __main__ - Step 79302: {'lr': 0.0002324967681304131, 'samples': 15225984, 'steps': 79301, 'loss/train': 0.6090360283851624} 08/31/2021 03:35:40 - INFO - __main__ - Step 79303: {'lr': 0.00023249147441231367, 'samples': 15226176, 'steps': 79302, 'loss/train': 1.3688222169876099} 08/31/2021 03:35:42 - INFO - __main__ - Step 79304: {'lr': 0.0002324861807021033, 'samples': 15226368, 'steps': 79303, 'loss/train': 1.1442698240280151} 08/31/2021 03:35:42 - INFO - __main__ - Step 79305: {'lr': 0.00023248088699978446, 'samples': 15226560, 'steps': 79304, 'loss/train': 0.2495068609714508} 08/31/2021 03:35:43 - INFO - __main__ - Step 79306: {'lr': 0.00023247559330535938, 'samples': 15226752, 'steps': 79305, 'loss/train': 2.5765786170959473} 08/31/2021 03:35:43 - INFO - __main__ - Step 79307: {'lr': 0.00023247029961883053, 'samples': 15226944, 'steps': 79306, 'loss/train': 0.0556810162961483} 08/31/2021 03:35:43 - INFO - __main__ - Step 79308: {'lr': 0.00023246500594020032, 'samples': 15227136, 'steps': 79307, 'loss/train': 1.292974829673767} 08/31/2021 03:35:44 - INFO - __main__ - Step 79309: {'lr': 0.0002324597122694711, 'samples': 15227328, 'steps': 79308, 'loss/train': 1.2751774787902832} 08/31/2021 03:35:45 - INFO - __main__ - Step 79310: {'lr': 0.00023245441860664525, 'samples': 15227520, 'steps': 79309, 'loss/train': 1.5820375680923462} 08/31/2021 03:35:46 - INFO - __main__ - Step 79311: {'lr': 0.00023244912495172515, 'samples': 15227712, 'steps': 79310, 'loss/train': 1.1728073358535767} 08/31/2021 03:35:46 - INFO - __main__ - Step 79312: {'lr': 0.00023244383130471326, 'samples': 15227904, 'steps': 79311, 'loss/train': 0.08386975526809692} 08/31/2021 03:35:47 - INFO - __main__ - Step 79313: {'lr': 0.00023243853766561186, 'samples': 15228096, 'steps': 79312, 'loss/train': 1.374885082244873} 08/31/2021 03:35:47 - INFO - __main__ - Step 79314: {'lr': 0.0002324332440344234, 'samples': 15228288, 'steps': 79313, 'loss/train': 1.2457854747772217} 08/31/2021 03:35:49 - INFO - __main__ - Step 79315: {'lr': 0.00023242795041115023, 'samples': 15228480, 'steps': 79314, 'loss/train': 0.8959559798240662} 08/31/2021 03:35:49 - INFO - __main__ - Step 79316: {'lr': 0.0002324226567957949, 'samples': 15228672, 'steps': 79315, 'loss/train': 1.4469081163406372} 08/31/2021 03:35:49 - INFO - __main__ - Step 79317: {'lr': 0.00023241736318835952, 'samples': 15228864, 'steps': 79316, 'loss/train': 0.03313674405217171} 08/31/2021 03:35:50 - INFO - __main__ - Step 79318: {'lr': 0.00023241206958884658, 'samples': 15229056, 'steps': 79317, 'loss/train': 1.1112264394760132} 08/31/2021 03:35:50 - INFO - __main__ - Step 79319: {'lr': 0.00023240677599725853, 'samples': 15229248, 'steps': 79318, 'loss/train': 1.0549370050430298} 08/31/2021 03:35:52 - INFO - __main__ - Step 79320: {'lr': 0.0002324014824135977, 'samples': 15229440, 'steps': 79319, 'loss/train': 1.3010873794555664} 08/31/2021 03:35:52 - INFO - __main__ - Step 79321: {'lr': 0.00023239618883786652, 'samples': 15229632, 'steps': 79320, 'loss/train': 0.5800191760063171} 08/31/2021 03:35:52 - INFO - __main__ - Step 79322: {'lr': 0.0002323908952700673, 'samples': 15229824, 'steps': 79321, 'loss/train': 0.35525643825531006} 08/31/2021 03:35:53 - INFO - __main__ - Step 79323: {'lr': 0.0002323856017102025, 'samples': 15230016, 'steps': 79322, 'loss/train': 1.386455774307251} 08/31/2021 03:35:53 - INFO - __main__ - Step 79324: {'lr': 0.00023238030815827445, 'samples': 15230208, 'steps': 79323, 'loss/train': 1.001055121421814} 08/31/2021 03:35:55 - INFO - __main__ - Step 79325: {'lr': 0.00023237501461428555, 'samples': 15230400, 'steps': 79324, 'loss/train': 1.3476576805114746} 08/31/2021 03:35:56 - INFO - __main__ - Step 79326: {'lr': 0.00023236972107823825, 'samples': 15230592, 'steps': 79325, 'loss/train': 1.2603272199630737} 08/31/2021 03:35:56 - INFO - __main__ - Step 79327: {'lr': 0.00023236442755013485, 'samples': 15230784, 'steps': 79326, 'loss/train': 0.9742909073829651} 08/31/2021 03:35:57 - INFO - __main__ - Step 79328: {'lr': 0.00023235913402997778, 'samples': 15230976, 'steps': 79327, 'loss/train': 1.1832764148712158} 08/31/2021 03:35:57 - INFO - __main__ - Step 79329: {'lr': 0.0002323538405177695, 'samples': 15231168, 'steps': 79328, 'loss/train': 0.03827661648392677} 08/31/2021 03:35:57 - INFO - __main__ - Step 79330: {'lr': 0.0002323485470135122, 'samples': 15231360, 'steps': 79329, 'loss/train': 1.3043614625930786} 08/31/2021 03:35:59 - INFO - __main__ - Step 79331: {'lr': 0.0002323432535172084, 'samples': 15231552, 'steps': 79330, 'loss/train': 1.7828465700149536} 08/31/2021 03:35:59 - INFO - __main__ - Step 79332: {'lr': 0.00023233796002886044, 'samples': 15231744, 'steps': 79331, 'loss/train': 0.6633663773536682} 08/31/2021 03:36:00 - INFO - __main__ - Step 79333: {'lr': 0.0002323326665484707, 'samples': 15231936, 'steps': 79332, 'loss/train': 0.7774697542190552} 08/31/2021 03:36:00 - INFO - __main__ - Step 79334: {'lr': 0.00023232737307604163, 'samples': 15232128, 'steps': 79333, 'loss/train': 0.32835179567337036} 08/31/2021 03:36:00 - INFO - __main__ - Step 79335: {'lr': 0.00023232207961157555, 'samples': 15232320, 'steps': 79334, 'loss/train': 1.0082241296768188} 08/31/2021 03:36:02 - INFO - __main__ - Step 79336: {'lr': 0.00023231678615507487, 'samples': 15232512, 'steps': 79335, 'loss/train': 1.1784248352050781} 08/31/2021 03:36:02 - INFO - __main__ - Step 79337: {'lr': 0.00023231149270654198, 'samples': 15232704, 'steps': 79336, 'loss/train': 1.3877795934677124} 08/31/2021 03:36:03 - INFO - __main__ - Step 79338: {'lr': 0.00023230619926597923, 'samples': 15232896, 'steps': 79337, 'loss/train': 1.1464112997055054} 08/31/2021 03:36:03 - INFO - __main__ - Step 79339: {'lr': 0.00023230090583338907, 'samples': 15233088, 'steps': 79338, 'loss/train': 1.296174168586731} 08/31/2021 03:36:03 - INFO - __main__ - Step 79340: {'lr': 0.00023229561240877385, 'samples': 15233280, 'steps': 79339, 'loss/train': 1.0812350511550903} 08/31/2021 03:36:05 - INFO - __main__ - Step 79341: {'lr': 0.00023229031899213594, 'samples': 15233472, 'steps': 79340, 'loss/train': 0.9383136630058289} 08/31/2021 03:36:05 - INFO - __main__ - Step 79342: {'lr': 0.0002322850255834777, 'samples': 15233664, 'steps': 79341, 'loss/train': 0.9414886832237244} 08/31/2021 03:36:06 - INFO - __main__ - Step 79343: {'lr': 0.00023227973218280175, 'samples': 15233856, 'steps': 79342, 'loss/train': 1.7135183811187744} 08/31/2021 03:36:06 - INFO - __main__ - Step 79344: {'lr': 0.0002322744387901101, 'samples': 15234048, 'steps': 79343, 'loss/train': 2.210108518600464} 08/31/2021 03:36:06 - INFO - __main__ - Step 79345: {'lr': 0.00023226914540540534, 'samples': 15234240, 'steps': 79344, 'loss/train': 1.691151738166809} 08/31/2021 03:36:08 - INFO - __main__ - Step 79346: {'lr': 0.00023226385202868984, 'samples': 15234432, 'steps': 79345, 'loss/train': 1.474745273590088} 08/31/2021 03:36:08 - INFO - __main__ - Step 79347: {'lr': 0.00023225855865996594, 'samples': 15234624, 'steps': 79346, 'loss/train': 1.0254634618759155} 08/31/2021 03:36:09 - INFO - __main__ - Step 79348: {'lr': 0.00023225326529923608, 'samples': 15234816, 'steps': 79347, 'loss/train': 0.43259790539741516} 08/31/2021 03:36:09 - INFO - __main__ - Step 79349: {'lr': 0.00023224797194650263, 'samples': 15235008, 'steps': 79348, 'loss/train': 1.4028810262680054} 08/31/2021 03:36:10 - INFO - __main__ - Step 79350: {'lr': 0.00023224267860176795, 'samples': 15235200, 'steps': 79349, 'loss/train': 1.0468335151672363} 08/31/2021 03:36:11 - INFO - __main__ - Step 79351: {'lr': 0.00023223738526503447, 'samples': 15235392, 'steps': 79350, 'loss/train': 0.8526676297187805} 08/31/2021 03:36:12 - INFO - __main__ - Step 79352: {'lr': 0.00023223209193630454, 'samples': 15235584, 'steps': 79351, 'loss/train': 1.061438798904419} 08/31/2021 03:36:12 - INFO - __main__ - Step 79353: {'lr': 0.00023222679861558055, 'samples': 15235776, 'steps': 79352, 'loss/train': 0.811792254447937} 08/31/2021 03:36:12 - INFO - __main__ - Step 79354: {'lr': 0.0002322215053028649, 'samples': 15235968, 'steps': 79353, 'loss/train': 0.5758240222930908} 08/31/2021 03:36:13 - INFO - __main__ - Step 79355: {'lr': 0.00023221621199815995, 'samples': 15236160, 'steps': 79354, 'loss/train': 1.7813012599945068} 08/31/2021 03:36:13 - INFO - __main__ - Step 79356: {'lr': 0.00023221091870146823, 'samples': 15236352, 'steps': 79355, 'loss/train': 1.1735191345214844} 08/31/2021 03:36:15 - INFO - __main__ - Step 79357: {'lr': 0.0002322056254127919, 'samples': 15236544, 'steps': 79356, 'loss/train': 0.9309461712837219} 08/31/2021 03:36:15 - INFO - __main__ - Step 79358: {'lr': 0.0002322003321321334, 'samples': 15236736, 'steps': 79357, 'loss/train': 2.3990020751953125} 08/31/2021 03:36:15 - INFO - __main__ - Step 79359: {'lr': 0.00023219503885949517, 'samples': 15236928, 'steps': 79358, 'loss/train': 0.9728587865829468} 08/31/2021 03:36:16 - INFO - __main__ - Step 79360: {'lr': 0.00023218974559487956, 'samples': 15237120, 'steps': 79359, 'loss/train': 1.6722544431686401} 08/31/2021 03:36:16 - INFO - __main__ - Step 79361: {'lr': 0.00023218445233828903, 'samples': 15237312, 'steps': 79360, 'loss/train': 1.0115150213241577} 08/31/2021 03:36:18 - INFO - __main__ - Step 79362: {'lr': 0.00023217915908972588, 'samples': 15237504, 'steps': 79361, 'loss/train': 1.3047741651535034} 08/31/2021 03:36:18 - INFO - __main__ - Step 79363: {'lr': 0.00023217386584919252, 'samples': 15237696, 'steps': 79362, 'loss/train': 2.2000250816345215} 08/31/2021 03:36:18 - INFO - __main__ - Step 79364: {'lr': 0.00023216857261669133, 'samples': 15237888, 'steps': 79363, 'loss/train': 0.9529533386230469} 08/31/2021 03:36:19 - INFO - __main__ - Step 79365: {'lr': 0.00023216327939222473, 'samples': 15238080, 'steps': 79364, 'loss/train': 1.2268636226654053} 08/31/2021 03:36:19 - INFO - __main__ - Step 79366: {'lr': 0.00023215798617579509, 'samples': 15238272, 'steps': 79365, 'loss/train': 1.4311699867248535} 08/31/2021 03:36:21 - INFO - __main__ - Step 79367: {'lr': 0.00023215269296740477, 'samples': 15238464, 'steps': 79366, 'loss/train': 0.8326056599617004} 08/31/2021 03:36:21 - INFO - __main__ - Step 79368: {'lr': 0.00023214739976705614, 'samples': 15238656, 'steps': 79367, 'loss/train': 1.4144846200942993} 08/31/2021 03:36:21 - INFO - __main__ - Step 79369: {'lr': 0.00023214210657475178, 'samples': 15238848, 'steps': 79368, 'loss/train': 1.2936747074127197} 08/31/2021 03:36:22 - INFO - __main__ - Step 79370: {'lr': 0.00023213681339049377, 'samples': 15239040, 'steps': 79369, 'loss/train': 0.8876580595970154} 08/31/2021 03:36:22 - INFO - __main__ - Step 79371: {'lr': 0.00023213152021428466, 'samples': 15239232, 'steps': 79370, 'loss/train': 0.7643465399742126} 08/31/2021 03:36:24 - INFO - __main__ - Step 79372: {'lr': 0.00023212622704612678, 'samples': 15239424, 'steps': 79371, 'loss/train': 1.2580854892730713} 08/31/2021 03:36:24 - INFO - __main__ - Step 79373: {'lr': 0.00023212093388602257, 'samples': 15239616, 'steps': 79372, 'loss/train': 1.0732239484786987} 08/31/2021 03:36:24 - INFO - __main__ - Step 79374: {'lr': 0.00023211564073397436, 'samples': 15239808, 'steps': 79373, 'loss/train': 1.5753755569458008} 08/31/2021 03:36:25 - INFO - __main__ - Step 79375: {'lr': 0.00023211034758998463, 'samples': 15240000, 'steps': 79374, 'loss/train': 0.771091639995575} 08/31/2021 03:36:25 - INFO - __main__ - Step 79376: {'lr': 0.00023210505445405563, 'samples': 15240192, 'steps': 79375, 'loss/train': 0.27668941020965576} 08/31/2021 03:36:27 - INFO - __main__ - Step 79377: {'lr': 0.00023209976132618988, 'samples': 15240384, 'steps': 79376, 'loss/train': 0.5849883556365967} 08/31/2021 03:36:28 - INFO - __main__ - Step 79378: {'lr': 0.00023209446820638967, 'samples': 15240576, 'steps': 79377, 'loss/train': 1.4347378015518188} 08/31/2021 03:36:28 - INFO - __main__ - Step 79379: {'lr': 0.00023208917509465738, 'samples': 15240768, 'steps': 79378, 'loss/train': 0.3032096028327942} 08/31/2021 03:36:29 - INFO - __main__ - Step 79380: {'lr': 0.00023208388199099546, 'samples': 15240960, 'steps': 79379, 'loss/train': 1.2841943502426147} 08/31/2021 03:36:29 - INFO - __main__ - Step 79381: {'lr': 0.00023207858889540627, 'samples': 15241152, 'steps': 79380, 'loss/train': 1.7727642059326172} 08/31/2021 03:36:30 - INFO - __main__ - Step 79382: {'lr': 0.00023207329580789222, 'samples': 15241344, 'steps': 79381, 'loss/train': 1.0831083059310913} 08/31/2021 03:36:31 - INFO - __main__ - Step 79383: {'lr': 0.00023206800272845574, 'samples': 15241536, 'steps': 79382, 'loss/train': 1.4772266149520874} 08/31/2021 03:36:31 - INFO - __main__ - Step 79384: {'lr': 0.00023206270965709906, 'samples': 15241728, 'steps': 79383, 'loss/train': 1.6714293956756592} 08/31/2021 03:36:32 - INFO - __main__ - Step 79385: {'lr': 0.00023205741659382463, 'samples': 15241920, 'steps': 79384, 'loss/train': 0.9049437046051025} 08/31/2021 03:36:32 - INFO - __main__ - Step 79386: {'lr': 0.00023205212353863484, 'samples': 15242112, 'steps': 79385, 'loss/train': 1.0793604850769043} 08/31/2021 03:36:34 - INFO - __main__ - Step 79387: {'lr': 0.0002320468304915321, 'samples': 15242304, 'steps': 79386, 'loss/train': 1.0310428142547607} 08/31/2021 03:36:34 - INFO - __main__ - Step 79388: {'lr': 0.00023204153745251877, 'samples': 15242496, 'steps': 79387, 'loss/train': 1.174133539199829} 08/31/2021 03:36:34 - INFO - __main__ - Step 79389: {'lr': 0.00023203624442159727, 'samples': 15242688, 'steps': 79388, 'loss/train': 2.7897250652313232} 08/31/2021 03:36:35 - INFO - __main__ - Step 79390: {'lr': 0.00023203095139876992, 'samples': 15242880, 'steps': 79389, 'loss/train': 1.0680854320526123} 08/31/2021 03:36:35 - INFO - __main__ - Step 79391: {'lr': 0.00023202565838403917, 'samples': 15243072, 'steps': 79390, 'loss/train': 1.0228278636932373} 08/31/2021 03:36:35 - INFO - __main__ - Step 79392: {'lr': 0.00023202036537740738, 'samples': 15243264, 'steps': 79391, 'loss/train': 0.9451804757118225} 08/31/2021 03:36:37 - INFO - __main__ - Step 79393: {'lr': 0.00023201507237887695, 'samples': 15243456, 'steps': 79392, 'loss/train': 1.4730104207992554} 08/31/2021 03:36:37 - INFO - __main__ - Step 79394: {'lr': 0.00023200977938845022, 'samples': 15243648, 'steps': 79393, 'loss/train': 1.190015435218811} 08/31/2021 03:36:38 - INFO - __main__ - Step 79395: {'lr': 0.0002320044864061297, 'samples': 15243840, 'steps': 79394, 'loss/train': 1.5884288549423218} 08/31/2021 03:36:38 - INFO - __main__ - Step 79396: {'lr': 0.00023199919343191763, 'samples': 15244032, 'steps': 79395, 'loss/train': 0.9718506336212158} 08/31/2021 03:36:38 - INFO - __main__ - Step 79397: {'lr': 0.00023199390046581644, 'samples': 15244224, 'steps': 79396, 'loss/train': 1.1868840456008911} 08/31/2021 03:36:40 - INFO - __main__ - Step 79398: {'lr': 0.0002319886075078285, 'samples': 15244416, 'steps': 79397, 'loss/train': 1.1791716814041138} 08/31/2021 03:36:40 - INFO - __main__ - Step 79399: {'lr': 0.0002319833145579562, 'samples': 15244608, 'steps': 79398, 'loss/train': 1.597240686416626} 08/31/2021 03:36:41 - INFO - __main__ - Step 79400: {'lr': 0.00023197802161620197, 'samples': 15244800, 'steps': 79399, 'loss/train': 1.8300073146820068} 08/31/2021 03:36:41 - INFO - __main__ - Step 79401: {'lr': 0.00023197272868256816, 'samples': 15244992, 'steps': 79400, 'loss/train': 1.1223351955413818} 08/31/2021 03:36:41 - INFO - __main__ - Step 79402: {'lr': 0.00023196743575705714, 'samples': 15245184, 'steps': 79401, 'loss/train': 1.1869944334030151} 08/31/2021 03:36:43 - INFO - __main__ - Step 79403: {'lr': 0.00023196214283967132, 'samples': 15245376, 'steps': 79402, 'loss/train': 0.3158777058124542} 08/31/2021 03:36:43 - INFO - __main__ - Step 79404: {'lr': 0.00023195684993041312, 'samples': 15245568, 'steps': 79403, 'loss/train': 1.4704811573028564} 08/31/2021 03:36:44 - INFO - __main__ - Step 79405: {'lr': 0.00023195155702928483, 'samples': 15245760, 'steps': 79404, 'loss/train': 1.2576284408569336} 08/31/2021 03:36:44 - INFO - __main__ - Step 79406: {'lr': 0.00023194626413628898, 'samples': 15245952, 'steps': 79405, 'loss/train': 1.170789122581482} 08/31/2021 03:36:44 - INFO - __main__ - Step 79407: {'lr': 0.00023194097125142776, 'samples': 15246144, 'steps': 79406, 'loss/train': 0.6946563720703125} 08/31/2021 03:36:46 - INFO - __main__ - Step 79408: {'lr': 0.00023193567837470372, 'samples': 15246336, 'steps': 79407, 'loss/train': 1.229111909866333} 08/31/2021 03:36:46 - INFO - __main__ - Step 79409: {'lr': 0.00023193038550611917, 'samples': 15246528, 'steps': 79408, 'loss/train': 1.3901667594909668} 08/31/2021 03:36:47 - INFO - __main__ - Step 79410: {'lr': 0.00023192509264567654, 'samples': 15246720, 'steps': 79409, 'loss/train': 1.1254909038543701} 08/31/2021 03:36:47 - INFO - __main__ - Step 79411: {'lr': 0.00023191979979337815, 'samples': 15246912, 'steps': 79410, 'loss/train': 1.8123241662979126} 08/31/2021 03:36:47 - INFO - __main__ - Step 79412: {'lr': 0.00023191450694922642, 'samples': 15247104, 'steps': 79411, 'loss/train': 1.5745271444320679} 08/31/2021 03:36:49 - INFO - __main__ - Step 79413: {'lr': 0.0002319092141132237, 'samples': 15247296, 'steps': 79412, 'loss/train': 0.35929369926452637} 08/31/2021 03:36:50 - INFO - __main__ - Step 79414: {'lr': 0.00023190392128537247, 'samples': 15247488, 'steps': 79413, 'loss/train': 1.1311547756195068} 08/31/2021 03:36:50 - INFO - __main__ - Step 79415: {'lr': 0.000231898628465675, 'samples': 15247680, 'steps': 79414, 'loss/train': 0.7117965817451477} 08/31/2021 03:36:50 - INFO - __main__ - Step 79416: {'lr': 0.00023189333565413377, 'samples': 15247872, 'steps': 79415, 'loss/train': 0.03517497330904007} 08/31/2021 03:36:51 - INFO - __main__ - Step 79417: {'lr': 0.00023188804285075116, 'samples': 15248064, 'steps': 79416, 'loss/train': 0.9703050255775452} 08/31/2021 03:36:51 - INFO - __main__ - Step 79418: {'lr': 0.00023188275005552945, 'samples': 15248256, 'steps': 79417, 'loss/train': 0.9101164937019348} 08/31/2021 03:36:53 - INFO - __main__ - Step 79419: {'lr': 0.0002318774572684711, 'samples': 15248448, 'steps': 79418, 'loss/train': 1.7182987928390503} 08/31/2021 03:36:53 - INFO - __main__ - Step 79420: {'lr': 0.0002318721644895785, 'samples': 15248640, 'steps': 79419, 'loss/train': 0.5086570382118225} 08/31/2021 03:36:53 - INFO - __main__ - Step 79421: {'lr': 0.000231866871718854, 'samples': 15248832, 'steps': 79420, 'loss/train': 0.8757498264312744} 08/31/2021 03:36:54 - INFO - __main__ - Step 79422: {'lr': 0.00023186157895630004, 'samples': 15249024, 'steps': 79421, 'loss/train': 1.3459322452545166} 08/31/2021 03:36:54 - INFO - __main__ - Step 79423: {'lr': 0.000231856286201919, 'samples': 15249216, 'steps': 79422, 'loss/train': 0.8980200886726379} 08/31/2021 03:36:56 - INFO - __main__ - Step 79424: {'lr': 0.0002318509934557132, 'samples': 15249408, 'steps': 79423, 'loss/train': 1.0920463800430298} 08/31/2021 03:36:56 - INFO - __main__ - Step 79425: {'lr': 0.00023184570071768508, 'samples': 15249600, 'steps': 79424, 'loss/train': 1.0029996633529663} 08/31/2021 03:36:56 - INFO - __main__ - Step 79426: {'lr': 0.00023184040798783696, 'samples': 15249792, 'steps': 79425, 'loss/train': 1.4395115375518799} 08/31/2021 03:36:57 - INFO - __main__ - Step 79427: {'lr': 0.0002318351152661713, 'samples': 15249984, 'steps': 79426, 'loss/train': 1.036656379699707} 08/31/2021 03:36:57 - INFO - __main__ - Step 79428: {'lr': 0.0002318298225526905, 'samples': 15250176, 'steps': 79427, 'loss/train': 1.1019686460494995} 08/31/2021 03:36:59 - INFO - __main__ - Step 79429: {'lr': 0.00023182452984739686, 'samples': 15250368, 'steps': 79428, 'loss/train': 0.22405987977981567} 08/31/2021 03:36:59 - INFO - __main__ - Step 79430: {'lr': 0.00023181923715029278, 'samples': 15250560, 'steps': 79429, 'loss/train': 1.3309968709945679} 08/31/2021 03:37:00 - INFO - __main__ - Step 79431: {'lr': 0.00023181394446138072, 'samples': 15250752, 'steps': 79430, 'loss/train': 0.975807249546051} 08/31/2021 03:37:00 - INFO - __main__ - Step 79432: {'lr': 0.00023180865178066298, 'samples': 15250944, 'steps': 79431, 'loss/train': 0.48403409123420715} 08/31/2021 03:37:00 - INFO - __main__ - Step 79433: {'lr': 0.00023180335910814198, 'samples': 15251136, 'steps': 79432, 'loss/train': 0.8808110952377319} 08/31/2021 03:37:02 - INFO - __main__ - Step 79434: {'lr': 0.0002317980664438201, 'samples': 15251328, 'steps': 79433, 'loss/train': 1.2215828895568848} 08/31/2021 03:37:03 - INFO - __main__ - Step 79435: {'lr': 0.00023179277378769975, 'samples': 15251520, 'steps': 79434, 'loss/train': 1.8965137004852295} 08/31/2021 03:37:03 - INFO - __main__ - Step 79436: {'lr': 0.00023178748113978332, 'samples': 15251712, 'steps': 79435, 'loss/train': 1.5184749364852905} 08/31/2021 03:37:03 - INFO - __main__ - Step 79437: {'lr': 0.00023178218850007317, 'samples': 15251904, 'steps': 79436, 'loss/train': 0.7894878387451172} 08/31/2021 03:37:04 - INFO - __main__ - Step 79438: {'lr': 0.00023177689586857165, 'samples': 15252096, 'steps': 79437, 'loss/train': 0.8572705984115601} 08/31/2021 03:37:05 - INFO - __main__ - Step 79439: {'lr': 0.00023177160324528123, 'samples': 15252288, 'steps': 79438, 'loss/train': 0.8563585877418518} 08/31/2021 03:37:06 - INFO - __main__ - Step 79440: {'lr': 0.0002317663106302042, 'samples': 15252480, 'steps': 79439, 'loss/train': 1.1324115991592407} 08/31/2021 03:37:06 - INFO - __main__ - Step 79441: {'lr': 0.00023176101802334302, 'samples': 15252672, 'steps': 79440, 'loss/train': 1.1540038585662842} 08/31/2021 03:37:06 - INFO - __main__ - Step 79442: {'lr': 0.00023175572542469998, 'samples': 15252864, 'steps': 79441, 'loss/train': 0.94780433177948} 08/31/2021 03:37:07 - INFO - __main__ - Step 79443: {'lr': 0.00023175043283427758, 'samples': 15253056, 'steps': 79442, 'loss/train': 1.346448302268982} 08/31/2021 03:37:08 - INFO - __main__ - Step 79444: {'lr': 0.00023174514025207812, 'samples': 15253248, 'steps': 79443, 'loss/train': 0.03465031459927559} 08/31/2021 03:37:09 - INFO - __main__ - Step 79445: {'lr': 0.00023173984767810402, 'samples': 15253440, 'steps': 79444, 'loss/train': 1.0077277421951294} 08/31/2021 03:37:09 - INFO - __main__ - Step 79446: {'lr': 0.00023173455511235768, 'samples': 15253632, 'steps': 79445, 'loss/train': 1.435219168663025} 08/31/2021 03:37:09 - INFO - __main__ - Step 79447: {'lr': 0.00023172926255484146, 'samples': 15253824, 'steps': 79446, 'loss/train': 0.17747965455055237} 08/31/2021 03:37:10 - INFO - __main__ - Step 79448: {'lr': 0.00023172397000555776, 'samples': 15254016, 'steps': 79447, 'loss/train': 0.9516527056694031} 08/31/2021 03:37:10 - INFO - __main__ - Step 79449: {'lr': 0.00023171867746450895, 'samples': 15254208, 'steps': 79448, 'loss/train': 1.1771090030670166} 08/31/2021 03:37:12 - INFO - __main__ - Step 79450: {'lr': 0.00023171338493169753, 'samples': 15254400, 'steps': 79449, 'loss/train': 1.4758901596069336} 08/31/2021 03:37:12 - INFO - __main__ - Step 79451: {'lr': 0.00023170809240712566, 'samples': 15254592, 'steps': 79450, 'loss/train': 1.6155340671539307} 08/31/2021 03:37:12 - INFO - __main__ - Step 79452: {'lr': 0.00023170279989079588, 'samples': 15254784, 'steps': 79451, 'loss/train': 1.171472430229187} 08/31/2021 03:37:13 - INFO - __main__ - Step 79453: {'lr': 0.0002316975073827105, 'samples': 15254976, 'steps': 79452, 'loss/train': 1.024192214012146} 08/31/2021 03:37:13 - INFO - __main__ - Step 79454: {'lr': 0.00023169221488287194, 'samples': 15255168, 'steps': 79453, 'loss/train': 1.2369831800460815} 08/31/2021 03:37:15 - INFO - __main__ - Step 79455: {'lr': 0.0002316869223912826, 'samples': 15255360, 'steps': 79454, 'loss/train': 0.8397443890571594} 08/31/2021 03:37:15 - INFO - __main__ - Step 79456: {'lr': 0.00023168162990794484, 'samples': 15255552, 'steps': 79455, 'loss/train': 1.112673282623291} 08/31/2021 03:37:15 - INFO - __main__ - Step 79457: {'lr': 0.00023167633743286103, 'samples': 15255744, 'steps': 79456, 'loss/train': 1.2540682554244995} 08/31/2021 03:37:16 - INFO - __main__ - Step 79458: {'lr': 0.00023167104496603363, 'samples': 15255936, 'steps': 79457, 'loss/train': 0.15731114149093628} 08/31/2021 03:37:16 - INFO - __main__ - Step 79459: {'lr': 0.00023166575250746496, 'samples': 15256128, 'steps': 79458, 'loss/train': 1.510424256324768} 08/31/2021 03:37:18 - INFO - __main__ - Step 79460: {'lr': 0.0002316604600571574, 'samples': 15256320, 'steps': 79459, 'loss/train': 1.611399531364441} 08/31/2021 03:37:18 - INFO - __main__ - Step 79461: {'lr': 0.00023165516761511338, 'samples': 15256512, 'steps': 79460, 'loss/train': 1.6663222312927246} 08/31/2021 03:37:18 - INFO - __main__ - Step 79462: {'lr': 0.00023164987518133523, 'samples': 15256704, 'steps': 79461, 'loss/train': 1.149156928062439} 08/31/2021 03:37:19 - INFO - __main__ - Step 79463: {'lr': 0.00023164458275582537, 'samples': 15256896, 'steps': 79462, 'loss/train': 1.405886173248291} 08/31/2021 03:37:19 - INFO - __main__ - Step 79464: {'lr': 0.0002316392903385863, 'samples': 15257088, 'steps': 79463, 'loss/train': 0.8808979392051697} 08/31/2021 03:37:21 - INFO - __main__ - Step 79465: {'lr': 0.00023163399792962017, 'samples': 15257280, 'steps': 79464, 'loss/train': 1.2801309823989868} 08/31/2021 03:37:21 - INFO - __main__ - Step 79466: {'lr': 0.00023162870552892947, 'samples': 15257472, 'steps': 79465, 'loss/train': 2.5387790203094482} 08/31/2021 03:37:21 - INFO - __main__ - Step 79467: {'lr': 0.0002316234131365166, 'samples': 15257664, 'steps': 79466, 'loss/train': 1.3471921682357788} 08/31/2021 03:37:22 - INFO - __main__ - Step 79468: {'lr': 0.00023161812075238393, 'samples': 15257856, 'steps': 79467, 'loss/train': 0.6147345900535583} 08/31/2021 03:37:22 - INFO - __main__ - Step 79469: {'lr': 0.00023161282837653386, 'samples': 15258048, 'steps': 79468, 'loss/train': 1.448567271232605} 08/31/2021 03:37:24 - INFO - __main__ - Step 79470: {'lr': 0.00023160753600896876, 'samples': 15258240, 'steps': 79469, 'loss/train': 1.1940189599990845} 08/31/2021 03:37:24 - INFO - __main__ - Step 79471: {'lr': 0.00023160224364969102, 'samples': 15258432, 'steps': 79470, 'loss/train': 0.6963525414466858} 08/31/2021 03:37:24 - INFO - __main__ - Step 79472: {'lr': 0.00023159695129870302, 'samples': 15258624, 'steps': 79471, 'loss/train': 1.749043345451355} 08/31/2021 03:37:25 - INFO - __main__ - Step 79473: {'lr': 0.00023159165895600715, 'samples': 15258816, 'steps': 79472, 'loss/train': 1.6434932947158813} 08/31/2021 03:37:25 - INFO - __main__ - Step 79474: {'lr': 0.00023158636662160578, 'samples': 15259008, 'steps': 79473, 'loss/train': 1.836102843284607} 08/31/2021 03:37:27 - INFO - __main__ - Step 79475: {'lr': 0.00023158107429550136, 'samples': 15259200, 'steps': 79474, 'loss/train': 0.9126965999603271} 08/31/2021 03:37:28 - INFO - __main__ - Step 79476: {'lr': 0.00023157578197769617, 'samples': 15259392, 'steps': 79475, 'loss/train': 0.9723569750785828} 08/31/2021 03:37:28 - INFO - __main__ - Step 79477: {'lr': 0.00023157048966819277, 'samples': 15259584, 'steps': 79476, 'loss/train': 0.9364326596260071} 08/31/2021 03:37:29 - INFO - __main__ - Step 79478: {'lr': 0.00023156519736699334, 'samples': 15259776, 'steps': 79477, 'loss/train': 1.0803700685501099} 08/31/2021 03:37:29 - INFO - __main__ - Step 79479: {'lr': 0.00023155990507410032, 'samples': 15259968, 'steps': 79478, 'loss/train': 0.9833354353904724} 08/31/2021 03:37:29 - INFO - __main__ - Step 79480: {'lr': 0.00023155461278951612, 'samples': 15260160, 'steps': 79479, 'loss/train': 0.4038372039794922} 08/31/2021 03:37:30 - INFO - __main__ - Step 79481: {'lr': 0.00023154932051324315, 'samples': 15260352, 'steps': 79480, 'loss/train': 0.3515969514846802} 08/31/2021 03:37:31 - INFO - __main__ - Step 79482: {'lr': 0.00023154402824528375, 'samples': 15260544, 'steps': 79481, 'loss/train': 0.31742551922798157} 08/31/2021 03:37:32 - INFO - __main__ - Step 79483: {'lr': 0.00023153873598564034, 'samples': 15260736, 'steps': 79482, 'loss/train': 1.4057893753051758} 08/31/2021 03:37:32 - INFO - __main__ - Step 79484: {'lr': 0.0002315334437343153, 'samples': 15260928, 'steps': 79483, 'loss/train': 1.2220710515975952} 08/31/2021 03:37:32 - INFO - __main__ - Step 79485: {'lr': 0.00023152815149131097, 'samples': 15261120, 'steps': 79484, 'loss/train': 1.3083618879318237} 08/31/2021 03:37:33 - INFO - __main__ - Step 79486: {'lr': 0.0002315228592566298, 'samples': 15261312, 'steps': 79485, 'loss/train': 1.1846933364868164} 08/31/2021 03:37:35 - INFO - __main__ - Step 79487: {'lr': 0.00023151756703027412, 'samples': 15261504, 'steps': 79486, 'loss/train': 1.0663387775421143} 08/31/2021 03:37:35 - INFO - __main__ - Step 79488: {'lr': 0.00023151227481224638, 'samples': 15261696, 'steps': 79487, 'loss/train': 1.3338439464569092} 08/31/2021 03:37:36 - INFO - __main__ - Step 79489: {'lr': 0.00023150698260254892, 'samples': 15261888, 'steps': 79488, 'loss/train': 1.5407299995422363} 08/31/2021 03:37:36 - INFO - __main__ - Step 79490: {'lr': 0.00023150169040118417, 'samples': 15262080, 'steps': 79489, 'loss/train': 0.05190570652484894} 08/31/2021 03:37:36 - INFO - __main__ - Step 79491: {'lr': 0.00023149639820815445, 'samples': 15262272, 'steps': 79490, 'loss/train': 1.0759201049804688} 08/31/2021 03:37:38 - INFO - __main__ - Step 79492: {'lr': 0.00023149110602346213, 'samples': 15262464, 'steps': 79491, 'loss/train': 1.2422178983688354} 08/31/2021 03:37:38 - INFO - __main__ - Step 79493: {'lr': 0.00023148581384710963, 'samples': 15262656, 'steps': 79492, 'loss/train': 0.8543126583099365} 08/31/2021 03:37:39 - INFO - __main__ - Step 79494: {'lr': 0.00023148052167909933, 'samples': 15262848, 'steps': 79493, 'loss/train': 0.24384352564811707} 08/31/2021 03:37:39 - INFO - __main__ - Step 79495: {'lr': 0.00023147522951943363, 'samples': 15263040, 'steps': 79494, 'loss/train': 1.0859689712524414} 08/31/2021 03:37:39 - INFO - __main__ - Step 79496: {'lr': 0.0002314699373681149, 'samples': 15263232, 'steps': 79495, 'loss/train': 1.4447139501571655} 08/31/2021 03:37:41 - INFO - __main__ - Step 79497: {'lr': 0.00023146464522514552, 'samples': 15263424, 'steps': 79496, 'loss/train': 0.9990548491477966} 08/31/2021 03:37:41 - INFO - __main__ - Step 79498: {'lr': 0.0002314593530905279, 'samples': 15263616, 'steps': 79497, 'loss/train': 0.9792878031730652} 08/31/2021 03:37:42 - INFO - __main__ - Step 79499: {'lr': 0.00023145406096426442, 'samples': 15263808, 'steps': 79498, 'loss/train': 1.4865750074386597} 08/31/2021 03:37:42 - INFO - __main__ - Step 79500: {'lr': 0.00023144876884635744, 'samples': 15264000, 'steps': 79499, 'loss/train': 1.5430468320846558} 08/31/2021 03:37:42 - INFO - __main__ - Step 79501: {'lr': 0.00023144347673680936, 'samples': 15264192, 'steps': 79500, 'loss/train': 1.198378086090088} 08/31/2021 03:37:43 - INFO - __main__ - Step 79502: {'lr': 0.00023143818463562256, 'samples': 15264384, 'steps': 79501, 'loss/train': 1.5090415477752686} 08/31/2021 03:37:44 - INFO - __main__ - Step 79503: {'lr': 0.0002314328925427994, 'samples': 15264576, 'steps': 79502, 'loss/train': 1.5385370254516602} 08/31/2021 03:37:45 - INFO - __main__ - Step 79504: {'lr': 0.00023142760045834245, 'samples': 15264768, 'steps': 79503, 'loss/train': 1.5154563188552856} 08/31/2021 03:37:45 - INFO - __main__ - Step 79505: {'lr': 0.00023142230838225382, 'samples': 15264960, 'steps': 79504, 'loss/train': 0.7796401381492615} 08/31/2021 03:37:45 - INFO - __main__ - Step 79506: {'lr': 0.000231417016314536, 'samples': 15265152, 'steps': 79505, 'loss/train': 2.59942626953125} 08/31/2021 03:37:46 - INFO - __main__ - Step 79507: {'lr': 0.00023141172425519138, 'samples': 15265344, 'steps': 79506, 'loss/train': 1.629581332206726} 08/31/2021 03:37:47 - INFO - __main__ - Step 79508: {'lr': 0.00023140643220422236, 'samples': 15265536, 'steps': 79507, 'loss/train': 1.3739365339279175} 08/31/2021 03:37:48 - INFO - __main__ - Step 79509: {'lr': 0.00023140114016163133, 'samples': 15265728, 'steps': 79508, 'loss/train': 1.4108166694641113} 08/31/2021 03:37:48 - INFO - __main__ - Step 79510: {'lr': 0.00023139584812742063, 'samples': 15265920, 'steps': 79509, 'loss/train': 1.1927590370178223} 08/31/2021 03:37:48 - INFO - __main__ - Step 79511: {'lr': 0.0002313905561015927, 'samples': 15266112, 'steps': 79510, 'loss/train': 1.2244558334350586} 08/31/2021 03:37:49 - INFO - __main__ - Step 79512: {'lr': 0.00023138526408414986, 'samples': 15266304, 'steps': 79511, 'loss/train': 1.1878191232681274} 08/31/2021 03:37:50 - INFO - __main__ - Step 79513: {'lr': 0.00023137997207509455, 'samples': 15266496, 'steps': 79512, 'loss/train': 0.9103842377662659} 08/31/2021 03:37:51 - INFO - __main__ - Step 79514: {'lr': 0.00023137468007442916, 'samples': 15266688, 'steps': 79513, 'loss/train': 1.215651273727417} 08/31/2021 03:37:51 - INFO - __main__ - Step 79515: {'lr': 0.00023136938808215602, 'samples': 15266880, 'steps': 79514, 'loss/train': 1.3057136535644531} 08/31/2021 03:37:52 - INFO - __main__ - Step 79516: {'lr': 0.00023136409609827757, 'samples': 15267072, 'steps': 79515, 'loss/train': 0.9324748516082764} 08/31/2021 03:37:52 - INFO - __main__ - Step 79517: {'lr': 0.00023135880412279627, 'samples': 15267264, 'steps': 79516, 'loss/train': 1.9621959924697876} 08/31/2021 03:37:52 - INFO - __main__ - Step 79518: {'lr': 0.0002313535121557143, 'samples': 15267456, 'steps': 79517, 'loss/train': 5.6755757331848145} 08/31/2021 03:37:54 - INFO - __main__ - Step 79519: {'lr': 0.00023134822019703414, 'samples': 15267648, 'steps': 79518, 'loss/train': 0.7825180292129517} 08/31/2021 03:37:54 - INFO - __main__ - Step 79520: {'lr': 0.0002313429282467582, 'samples': 15267840, 'steps': 79519, 'loss/train': 1.2552993297576904} 08/31/2021 03:37:55 - INFO - __main__ - Step 79521: {'lr': 0.00023133763630488882, 'samples': 15268032, 'steps': 79520, 'loss/train': 1.7866942882537842} 08/31/2021 03:37:55 - INFO - __main__ - Step 79522: {'lr': 0.00023133234437142845, 'samples': 15268224, 'steps': 79521, 'loss/train': 0.1895105391740799} 08/31/2021 03:37:55 - INFO - __main__ - Step 79523: {'lr': 0.0002313270524463794, 'samples': 15268416, 'steps': 79522, 'loss/train': 1.888783574104309} 08/31/2021 03:37:56 - INFO - __main__ - Step 79524: {'lr': 0.00023132176052974412, 'samples': 15268608, 'steps': 79523, 'loss/train': 1.0535330772399902} 08/31/2021 03:37:57 - INFO - __main__ - Step 79525: {'lr': 0.00023131646862152496, 'samples': 15268800, 'steps': 79524, 'loss/train': 1.1888278722763062} 08/31/2021 03:37:58 - INFO - __main__ - Step 79526: {'lr': 0.0002313111767217243, 'samples': 15268992, 'steps': 79525, 'loss/train': 1.2222208976745605} 08/31/2021 03:37:58 - INFO - __main__ - Step 79527: {'lr': 0.00023130588483034456, 'samples': 15269184, 'steps': 79526, 'loss/train': 1.0958023071289062} 08/31/2021 03:37:58 - INFO - __main__ - Step 79528: {'lr': 0.0002313005929473881, 'samples': 15269376, 'steps': 79527, 'loss/train': 1.3948540687561035} 08/31/2021 03:37:59 - INFO - __main__ - Step 79529: {'lr': 0.00023129530107285728, 'samples': 15269568, 'steps': 79528, 'loss/train': 1.4402607679367065} 08/31/2021 03:38:00 - INFO - __main__ - Step 79530: {'lr': 0.00023129000920675457, 'samples': 15269760, 'steps': 79529, 'loss/train': 0.7917793393135071} 08/31/2021 03:38:01 - INFO - __main__ - Step 79531: {'lr': 0.0002312847173490823, 'samples': 15269952, 'steps': 79530, 'loss/train': 1.4480435848236084} 08/31/2021 03:38:01 - INFO - __main__ - Step 79532: {'lr': 0.0002312794254998428, 'samples': 15270144, 'steps': 79531, 'loss/train': 1.5127942562103271} 08/31/2021 03:38:01 - INFO - __main__ - Step 79533: {'lr': 0.0002312741336590385, 'samples': 15270336, 'steps': 79532, 'loss/train': 2.140129566192627} 08/31/2021 03:38:02 - INFO - __main__ - Step 79534: {'lr': 0.00023126884182667173, 'samples': 15270528, 'steps': 79533, 'loss/train': 1.0633045434951782} 08/31/2021 03:38:03 - INFO - __main__ - Step 79535: {'lr': 0.00023126355000274498, 'samples': 15270720, 'steps': 79534, 'loss/train': 1.0391556024551392} 08/31/2021 03:38:04 - INFO - __main__ - Step 79536: {'lr': 0.0002312582581872606, 'samples': 15270912, 'steps': 79535, 'loss/train': 1.5237019062042236} 08/31/2021 03:38:04 - INFO - __main__ - Step 79537: {'lr': 0.00023125296638022095, 'samples': 15271104, 'steps': 79536, 'loss/train': 0.8122073411941528} 08/31/2021 03:38:04 - INFO - __main__ - Step 79538: {'lr': 0.0002312476745816284, 'samples': 15271296, 'steps': 79537, 'loss/train': 0.8174790143966675} 08/31/2021 03:38:05 - INFO - __main__ - Step 79539: {'lr': 0.00023124238279148538, 'samples': 15271488, 'steps': 79538, 'loss/train': 1.1301277875900269} 08/31/2021 03:38:07 - INFO - __main__ - Step 79540: {'lr': 0.00023123709100979426, 'samples': 15271680, 'steps': 79539, 'loss/train': 1.730071783065796} 08/31/2021 03:38:07 - INFO - __main__ - Step 79541: {'lr': 0.00023123179923655745, 'samples': 15271872, 'steps': 79540, 'loss/train': 1.4359691143035889} 08/31/2021 03:38:08 - INFO - __main__ - Step 79542: {'lr': 0.00023122650747177726, 'samples': 15272064, 'steps': 79541, 'loss/train': 1.6644103527069092} 08/31/2021 03:38:08 - INFO - __main__ - Step 79543: {'lr': 0.00023122121571545612, 'samples': 15272256, 'steps': 79542, 'loss/train': 0.9747987985610962} 08/31/2021 03:38:08 - INFO - __main__ - Step 79544: {'lr': 0.00023121592396759645, 'samples': 15272448, 'steps': 79543, 'loss/train': 1.6990916728973389} 08/31/2021 03:38:10 - INFO - __main__ - Step 79545: {'lr': 0.00023121063222820054, 'samples': 15272640, 'steps': 79544, 'loss/train': 1.2805286645889282} 08/31/2021 03:38:10 - INFO - __main__ - Step 79546: {'lr': 0.00023120534049727085, 'samples': 15272832, 'steps': 79545, 'loss/train': 1.1947883367538452} 08/31/2021 03:38:11 - INFO - __main__ - Step 79547: {'lr': 0.00023120004877480972, 'samples': 15273024, 'steps': 79546, 'loss/train': 1.6894030570983887} 08/31/2021 03:38:11 - INFO - __main__ - Step 79548: {'lr': 0.00023119475706081957, 'samples': 15273216, 'steps': 79547, 'loss/train': 0.6630703806877136} 08/31/2021 03:38:11 - INFO - __main__ - Step 79549: {'lr': 0.00023118946535530277, 'samples': 15273408, 'steps': 79548, 'loss/train': 1.504450798034668} 08/31/2021 03:38:14 - INFO - __main__ - Step 79550: {'lr': 0.0002311841736582617, 'samples': 15273600, 'steps': 79549, 'loss/train': 1.4608546495437622} 08/31/2021 03:38:14 - INFO - __main__ - Step 79551: {'lr': 0.00023117888196969879, 'samples': 15273792, 'steps': 79550, 'loss/train': 0.9171353578567505} 08/31/2021 03:38:15 - INFO - __main__ - Step 79552: {'lr': 0.0002311735902896164, 'samples': 15273984, 'steps': 79551, 'loss/train': 1.155662178993225} 08/31/2021 03:38:15 - INFO - __main__ - Step 79553: {'lr': 0.00023116829861801686, 'samples': 15274176, 'steps': 79552, 'loss/train': 0.8418099880218506} 08/31/2021 03:38:15 - INFO - __main__ - Step 79554: {'lr': 0.00023116300695490258, 'samples': 15274368, 'steps': 79553, 'loss/train': 0.9225070476531982} 08/31/2021 03:38:16 - INFO - __main__ - Step 79555: {'lr': 0.00023115771530027597, 'samples': 15274560, 'steps': 79554, 'loss/train': 0.4113231301307678} 08/31/2021 03:38:16 - INFO - __main__ - Step 79556: {'lr': 0.00023115242365413937, 'samples': 15274752, 'steps': 79555, 'loss/train': 0.7039870023727417} 08/31/2021 03:38:18 - INFO - __main__ - Step 79557: {'lr': 0.00023114713201649524, 'samples': 15274944, 'steps': 79556, 'loss/train': 1.325192928314209} 08/31/2021 03:38:18 - INFO - __main__ - Step 79558: {'lr': 0.00023114184038734598, 'samples': 15275136, 'steps': 79557, 'loss/train': 1.0491127967834473} 08/31/2021 03:38:18 - INFO - __main__ - Step 79559: {'lr': 0.00023113654876669382, 'samples': 15275328, 'steps': 79558, 'loss/train': 1.1334856748580933} 08/31/2021 03:38:19 - INFO - __main__ - Step 79560: {'lr': 0.0002311312571545413, 'samples': 15275520, 'steps': 79559, 'loss/train': 1.3494197130203247} 08/31/2021 03:38:19 - INFO - __main__ - Step 79561: {'lr': 0.0002311259655508907, 'samples': 15275712, 'steps': 79560, 'loss/train': 1.5697743892669678} 08/31/2021 03:38:21 - INFO - __main__ - Step 79562: {'lr': 0.00023112067395574448, 'samples': 15275904, 'steps': 79561, 'loss/train': 0.8845997452735901} 08/31/2021 03:38:21 - INFO - __main__ - Step 79563: {'lr': 0.000231115382369105, 'samples': 15276096, 'steps': 79562, 'loss/train': 1.2634836435317993} 08/31/2021 03:38:21 - INFO - __main__ - Step 79564: {'lr': 0.0002311100907909746, 'samples': 15276288, 'steps': 79563, 'loss/train': 1.7858033180236816} 08/31/2021 03:38:22 - INFO - __main__ - Step 79565: {'lr': 0.0002311047992213557, 'samples': 15276480, 'steps': 79564, 'loss/train': 1.2623255252838135} 08/31/2021 03:38:22 - INFO - __main__ - Step 79566: {'lr': 0.00023109950766025071, 'samples': 15276672, 'steps': 79565, 'loss/train': 0.029730679467320442} 08/31/2021 03:38:22 - INFO - __main__ - Step 79567: {'lr': 0.00023109421610766195, 'samples': 15276864, 'steps': 79566, 'loss/train': 0.35758575797080994} 08/31/2021 03:38:24 - INFO - __main__ - Step 79568: {'lr': 0.00023108892456359187, 'samples': 15277056, 'steps': 79567, 'loss/train': 0.02827782742679119} 08/31/2021 03:38:25 - INFO - __main__ - Step 79569: {'lr': 0.00023108363302804284, 'samples': 15277248, 'steps': 79568, 'loss/train': 1.994652509689331} 08/31/2021 03:38:25 - INFO - __main__ - Step 79570: {'lr': 0.0002310783415010172, 'samples': 15277440, 'steps': 79569, 'loss/train': 0.9462840557098389} 08/31/2021 03:38:26 - INFO - __main__ - Step 79571: {'lr': 0.00023107304998251746, 'samples': 15277632, 'steps': 79570, 'loss/train': 1.744472861289978} 08/31/2021 03:38:26 - INFO - __main__ - Step 79572: {'lr': 0.0002310677584725458, 'samples': 15277824, 'steps': 79571, 'loss/train': 0.044720880687236786} 08/31/2021 03:38:27 - INFO - __main__ - Step 79573: {'lr': 0.00023106246697110483, 'samples': 15278016, 'steps': 79572, 'loss/train': 0.7772578597068787} 08/31/2021 03:38:28 - INFO - __main__ - Step 79574: {'lr': 0.00023105717547819676, 'samples': 15278208, 'steps': 79573, 'loss/train': 1.531643033027649} 08/31/2021 03:38:28 - INFO - __main__ - Step 79575: {'lr': 0.00023105188399382402, 'samples': 15278400, 'steps': 79574, 'loss/train': 0.6235365271568298} 08/31/2021 03:38:29 - INFO - __main__ - Step 79576: {'lr': 0.00023104659251798902, 'samples': 15278592, 'steps': 79575, 'loss/train': 1.6723474264144897} 08/31/2021 03:38:29 - INFO - __main__ - Step 79577: {'lr': 0.00023104130105069408, 'samples': 15278784, 'steps': 79576, 'loss/train': 1.1797726154327393} 08/31/2021 03:38:31 - INFO - __main__ - Step 79578: {'lr': 0.00023103600959194172, 'samples': 15278976, 'steps': 79577, 'loss/train': 1.3786746263504028} 08/31/2021 03:38:32 - INFO - __main__ - Step 79579: {'lr': 0.0002310307181417342, 'samples': 15279168, 'steps': 79578, 'loss/train': 2.0056159496307373} 08/31/2021 03:38:32 - INFO - __main__ - Step 79580: {'lr': 0.00023102542670007392, 'samples': 15279360, 'steps': 79579, 'loss/train': 1.307587742805481} 08/31/2021 03:38:33 - INFO - __main__ - Step 79581: {'lr': 0.00023102013526696334, 'samples': 15279552, 'steps': 79580, 'loss/train': 0.2491978257894516} 08/31/2021 03:38:33 - INFO - __main__ - Step 79582: {'lr': 0.00023101484384240476, 'samples': 15279744, 'steps': 79581, 'loss/train': 0.24041301012039185} 08/31/2021 03:38:33 - INFO - __main__ - Step 79583: {'lr': 0.00023100955242640061, 'samples': 15279936, 'steps': 79582, 'loss/train': 0.9164356589317322} 08/31/2021 03:38:34 - INFO - __main__ - Step 79584: {'lr': 0.00023100426101895324, 'samples': 15280128, 'steps': 79583, 'loss/train': 1.0675997734069824} 08/31/2021 03:38:35 - INFO - __main__ - Step 79585: {'lr': 0.0002309989696200652, 'samples': 15280320, 'steps': 79584, 'loss/train': 1.3570091724395752} 08/31/2021 03:38:36 - INFO - __main__ - Step 79586: {'lr': 0.00023099367822973862, 'samples': 15280512, 'steps': 79585, 'loss/train': 1.0548689365386963} 08/31/2021 03:38:36 - INFO - __main__ - Step 79587: {'lr': 0.000230988386847976, 'samples': 15280704, 'steps': 79586, 'loss/train': 1.3647500276565552} 08/31/2021 03:38:36 - INFO - __main__ - Step 79588: {'lr': 0.0002309830954747797, 'samples': 15280896, 'steps': 79587, 'loss/train': 1.0832911729812622} 08/31/2021 03:38:37 - INFO - __main__ - Step 79589: {'lr': 0.00023097780411015213, 'samples': 15281088, 'steps': 79588, 'loss/train': 1.1803563833236694} 08/31/2021 03:38:38 - INFO - __main__ - Step 79590: {'lr': 0.00023097251275409564, 'samples': 15281280, 'steps': 79589, 'loss/train': 1.5152984857559204} 08/31/2021 03:38:39 - INFO - __main__ - Step 79591: {'lr': 0.00023096722140661266, 'samples': 15281472, 'steps': 79590, 'loss/train': 1.435240387916565} 08/31/2021 03:38:39 - INFO - __main__ - Step 79592: {'lr': 0.0002309619300677056, 'samples': 15281664, 'steps': 79591, 'loss/train': 0.5335729718208313} 08/31/2021 03:38:39 - INFO - __main__ - Step 79593: {'lr': 0.00023095663873737673, 'samples': 15281856, 'steps': 79592, 'loss/train': 1.5781240463256836} 08/31/2021 03:38:40 - INFO - __main__ - Step 79594: {'lr': 0.00023095134741562856, 'samples': 15282048, 'steps': 79593, 'loss/train': 1.2634774446487427} 08/31/2021 03:38:41 - INFO - __main__ - Step 79595: {'lr': 0.00023094605610246338, 'samples': 15282240, 'steps': 79594, 'loss/train': 2.002967596054077} 08/31/2021 03:38:42 - INFO - __main__ - Step 79596: {'lr': 0.00023094076479788364, 'samples': 15282432, 'steps': 79595, 'loss/train': 1.7531559467315674} 08/31/2021 03:38:42 - INFO - __main__ - Step 79597: {'lr': 0.0002309354735018917, 'samples': 15282624, 'steps': 79596, 'loss/train': 1.3496346473693848} 08/31/2021 03:38:42 - INFO - __main__ - Step 79598: {'lr': 0.00023093018221449004, 'samples': 15282816, 'steps': 79597, 'loss/train': 1.279541015625} 08/31/2021 03:38:43 - INFO - __main__ - Step 79599: {'lr': 0.00023092489093568084, 'samples': 15283008, 'steps': 79598, 'loss/train': 1.4304678440093994} 08/31/2021 03:38:45 - INFO - __main__ - Step 79600: {'lr': 0.0002309195996654666, 'samples': 15283200, 'steps': 79599, 'loss/train': 1.4509057998657227} 08/31/2021 03:38:45 - INFO - __main__ - Step 79601: {'lr': 0.00023091430840384964, 'samples': 15283392, 'steps': 79600, 'loss/train': 1.6572033166885376} 08/31/2021 03:38:45 - INFO - __main__ - Step 79602: {'lr': 0.00023090901715083247, 'samples': 15283584, 'steps': 79601, 'loss/train': 1.1550087928771973} 08/31/2021 03:38:46 - INFO - __main__ - Step 79603: {'lr': 0.00023090372590641733, 'samples': 15283776, 'steps': 79602, 'loss/train': 1.3292051553726196} 08/31/2021 03:38:46 - INFO - __main__ - Step 79604: {'lr': 0.00023089843467060672, 'samples': 15283968, 'steps': 79603, 'loss/train': 1.6149334907531738} 08/31/2021 03:38:48 - INFO - __main__ - Step 79605: {'lr': 0.000230893143443403, 'samples': 15284160, 'steps': 79604, 'loss/train': 1.2885010242462158} 08/31/2021 03:38:48 - INFO - __main__ - Step 79606: {'lr': 0.0002308878522248085, 'samples': 15284352, 'steps': 79605, 'loss/train': 1.0275145769119263} 08/31/2021 03:38:49 - INFO - __main__ - Step 79607: {'lr': 0.00023088256101482565, 'samples': 15284544, 'steps': 79606, 'loss/train': 0.3548402488231659} 08/31/2021 03:38:49 - INFO - __main__ - Step 79608: {'lr': 0.00023087726981345683, 'samples': 15284736, 'steps': 79607, 'loss/train': 1.2073419094085693} 08/31/2021 03:38:49 - INFO - __main__ - Step 79609: {'lr': 0.00023087197862070442, 'samples': 15284928, 'steps': 79608, 'loss/train': 1.3885293006896973} 08/31/2021 03:38:51 - INFO - __main__ - Step 79610: {'lr': 0.00023086668743657078, 'samples': 15285120, 'steps': 79609, 'loss/train': 1.0333114862442017} 08/31/2021 03:38:51 - INFO - __main__ - Step 79611: {'lr': 0.00023086139626105843, 'samples': 15285312, 'steps': 79610, 'loss/train': 1.2651959657669067} 08/31/2021 03:38:52 - INFO - __main__ - Step 79612: {'lr': 0.00023085610509416955, 'samples': 15285504, 'steps': 79611, 'loss/train': 1.1811585426330566} 08/31/2021 03:38:52 - INFO - __main__ - Step 79613: {'lr': 0.0002308508139359066, 'samples': 15285696, 'steps': 79612, 'loss/train': 0.32189345359802246} 08/31/2021 03:38:52 - INFO - __main__ - Step 79614: {'lr': 0.00023084552278627196, 'samples': 15285888, 'steps': 79613, 'loss/train': 0.11783823370933533} 08/31/2021 03:38:54 - INFO - __main__ - Step 79615: {'lr': 0.00023084023164526808, 'samples': 15286080, 'steps': 79614, 'loss/train': 1.275122880935669} 08/31/2021 03:38:54 - INFO - __main__ - Step 79616: {'lr': 0.00023083494051289724, 'samples': 15286272, 'steps': 79615, 'loss/train': 1.3983211517333984} 08/31/2021 03:38:55 - INFO - __main__ - Step 79617: {'lr': 0.0002308296493891619, 'samples': 15286464, 'steps': 79616, 'loss/train': 1.2027252912521362} 08/31/2021 03:38:55 - INFO - __main__ - Step 79618: {'lr': 0.00023082435827406444, 'samples': 15286656, 'steps': 79617, 'loss/train': 0.4129335582256317} 08/31/2021 03:38:56 - INFO - __main__ - Step 79619: {'lr': 0.00023081906716760722, 'samples': 15286848, 'steps': 79618, 'loss/train': 1.1446032524108887} 08/31/2021 03:38:57 - INFO - __main__ - Step 79620: {'lr': 0.00023081377606979265, 'samples': 15287040, 'steps': 79619, 'loss/train': 0.9633215665817261} 08/31/2021 03:38:58 - INFO - __main__ - Step 79621: {'lr': 0.00023080848498062306, 'samples': 15287232, 'steps': 79620, 'loss/train': 1.5330162048339844} 08/31/2021 03:38:58 - INFO - __main__ - Step 79622: {'lr': 0.00023080319390010088, 'samples': 15287424, 'steps': 79621, 'loss/train': 0.8039000034332275} 08/31/2021 03:38:58 - INFO - __main__ - Step 79623: {'lr': 0.0002307979028282285, 'samples': 15287616, 'steps': 79622, 'loss/train': 1.1355949640274048} 08/31/2021 03:38:59 - INFO - __main__ - Step 79624: {'lr': 0.0002307926117650083, 'samples': 15287808, 'steps': 79623, 'loss/train': 0.6178938150405884} 08/31/2021 03:39:00 - INFO - __main__ - Step 79625: {'lr': 0.00023078732071044272, 'samples': 15288000, 'steps': 79624, 'loss/train': 0.7744815349578857} 08/31/2021 03:39:01 - INFO - __main__ - Step 79626: {'lr': 0.000230782029664534, 'samples': 15288192, 'steps': 79625, 'loss/train': 1.3283671140670776} 08/31/2021 03:39:01 - INFO - __main__ - Step 79627: {'lr': 0.0002307767386272846, 'samples': 15288384, 'steps': 79626, 'loss/train': 1.889101505279541} 08/31/2021 03:39:01 - INFO - __main__ - Step 79628: {'lr': 0.00023077144759869688, 'samples': 15288576, 'steps': 79627, 'loss/train': 1.3705981969833374} 08/31/2021 03:39:02 - INFO - __main__ - Step 79629: {'lr': 0.00023076615657877326, 'samples': 15288768, 'steps': 79628, 'loss/train': 1.525266408920288} 08/31/2021 03:39:03 - INFO - __main__ - Step 79630: {'lr': 0.00023076086556751612, 'samples': 15288960, 'steps': 79629, 'loss/train': 0.8699291944503784} 08/31/2021 03:39:04 - INFO - __main__ - Step 79631: {'lr': 0.00023075557456492786, 'samples': 15289152, 'steps': 79630, 'loss/train': 0.97762131690979} 08/31/2021 03:39:04 - INFO - __main__ - Step 79632: {'lr': 0.0002307502835710108, 'samples': 15289344, 'steps': 79631, 'loss/train': 0.4885975420475006} 08/31/2021 03:39:04 - INFO - __main__ - Step 79633: {'lr': 0.0002307449925857674, 'samples': 15289536, 'steps': 79632, 'loss/train': 1.119491457939148} 08/31/2021 03:39:05 - INFO - __main__ - Step 79634: {'lr': 0.00023073970160919995, 'samples': 15289728, 'steps': 79633, 'loss/train': 0.910434365272522} 08/31/2021 03:39:06 - INFO - __main__ - Step 79635: {'lr': 0.00023073441064131096, 'samples': 15289920, 'steps': 79634, 'loss/train': 1.9740917682647705} 08/31/2021 03:39:07 - INFO - __main__ - Step 79636: {'lr': 0.00023072911968210274, 'samples': 15290112, 'steps': 79635, 'loss/train': 0.060837626457214355} 08/31/2021 03:39:07 - INFO - __main__ - Step 79637: {'lr': 0.00023072382873157765, 'samples': 15290304, 'steps': 79636, 'loss/train': 1.0105652809143066} 08/31/2021 03:39:07 - INFO - __main__ - Step 79638: {'lr': 0.00023071853778973823, 'samples': 15290496, 'steps': 79637, 'loss/train': 1.0654326677322388} 08/31/2021 03:39:08 - INFO - __main__ - Step 79639: {'lr': 0.00023071324685658662, 'samples': 15290688, 'steps': 79638, 'loss/train': 0.20440994203090668} 08/31/2021 03:39:09 - INFO - __main__ - Step 79640: {'lr': 0.0002307079559321253, 'samples': 15290880, 'steps': 79639, 'loss/train': 0.8179335594177246} 08/31/2021 03:39:10 - INFO - __main__ - Step 79641: {'lr': 0.00023070266501635674, 'samples': 15291072, 'steps': 79640, 'loss/train': 1.356575608253479} 08/31/2021 03:39:10 - INFO - __main__ - Step 79642: {'lr': 0.00023069737410928324, 'samples': 15291264, 'steps': 79641, 'loss/train': 1.2664899826049805} 08/31/2021 03:39:11 - INFO - __main__ - Step 79643: {'lr': 0.00023069208321090717, 'samples': 15291456, 'steps': 79642, 'loss/train': 0.8353363275527954} 08/31/2021 03:39:11 - INFO - __main__ - Step 79644: {'lr': 0.000230686792321231, 'samples': 15291648, 'steps': 79643, 'loss/train': 1.1746546030044556} 08/31/2021 03:39:12 - INFO - __main__ - Step 79645: {'lr': 0.00023068150144025702, 'samples': 15291840, 'steps': 79644, 'loss/train': 0.06440634280443192} 08/31/2021 03:39:13 - INFO - __main__ - Step 79646: {'lr': 0.0002306762105679877, 'samples': 15292032, 'steps': 79645, 'loss/train': 1.7227476835250854} 08/31/2021 03:39:13 - INFO - __main__ - Step 79647: {'lr': 0.00023067091970442534, 'samples': 15292224, 'steps': 79646, 'loss/train': 1.4975606203079224} 08/31/2021 03:39:13 - INFO - __main__ - Step 79648: {'lr': 0.00023066562884957236, 'samples': 15292416, 'steps': 79647, 'loss/train': 1.3731461763381958} 08/31/2021 03:39:14 - INFO - __main__ - Step 79649: {'lr': 0.0002306603380034312, 'samples': 15292608, 'steps': 79648, 'loss/train': 1.2434715032577515} 08/31/2021 03:39:16 - INFO - __main__ - Step 79650: {'lr': 0.00023065504716600417, 'samples': 15292800, 'steps': 79649, 'loss/train': 0.6777234673500061} 08/31/2021 03:39:16 - INFO - __main__ - Step 79651: {'lr': 0.00023064975633729366, 'samples': 15292992, 'steps': 79650, 'loss/train': 1.2529029846191406} 08/31/2021 03:39:17 - INFO - __main__ - Step 79652: {'lr': 0.0002306444655173022, 'samples': 15293184, 'steps': 79651, 'loss/train': 1.6284807920455933} 08/31/2021 03:39:17 - INFO - __main__ - Step 79653: {'lr': 0.0002306391747060319, 'samples': 15293376, 'steps': 79652, 'loss/train': 0.970356285572052} 08/31/2021 03:39:18 - INFO - __main__ - Step 79654: {'lr': 0.00023063388390348534, 'samples': 15293568, 'steps': 79653, 'loss/train': 1.3123369216918945} 08/31/2021 03:39:19 - INFO - __main__ - Step 79655: {'lr': 0.00023062859310966482, 'samples': 15293760, 'steps': 79654, 'loss/train': 0.8546203970909119} 08/31/2021 03:39:19 - INFO - __main__ - Step 79656: {'lr': 0.00023062330232457277, 'samples': 15293952, 'steps': 79655, 'loss/train': 0.977169930934906} 08/31/2021 03:39:20 - INFO - __main__ - Step 79657: {'lr': 0.00023061801154821156, 'samples': 15294144, 'steps': 79656, 'loss/train': 0.9370595216751099} 08/31/2021 03:39:20 - INFO - __main__ - Step 79658: {'lr': 0.00023061272078058357, 'samples': 15294336, 'steps': 79657, 'loss/train': 0.7927143573760986} 08/31/2021 03:39:20 - INFO - __main__ - Step 79659: {'lr': 0.00023060743002169118, 'samples': 15294528, 'steps': 79658, 'loss/train': 0.15139807760715485} 08/31/2021 03:39:22 - INFO - __main__ - Step 79660: {'lr': 0.00023060213927153682, 'samples': 15294720, 'steps': 79659, 'loss/train': 0.7685268521308899} 08/31/2021 03:39:23 - INFO - __main__ - Step 79661: {'lr': 0.0002305968485301228, 'samples': 15294912, 'steps': 79660, 'loss/train': 1.3797976970672607} 08/31/2021 03:39:23 - INFO - __main__ - Step 79662: {'lr': 0.00023059155779745155, 'samples': 15295104, 'steps': 79661, 'loss/train': 1.499454140663147} 08/31/2021 03:39:23 - INFO - __main__ - Step 79663: {'lr': 0.00023058626707352545, 'samples': 15295296, 'steps': 79662, 'loss/train': 0.6082444190979004} 08/31/2021 03:39:24 - INFO - __main__ - Step 79664: {'lr': 0.00023058097635834693, 'samples': 15295488, 'steps': 79663, 'loss/train': 1.4281632900238037} 08/31/2021 03:39:25 - INFO - __main__ - Step 79665: {'lr': 0.00023057568565191833, 'samples': 15295680, 'steps': 79664, 'loss/train': 1.007881999015808} 08/31/2021 03:39:26 - INFO - __main__ - Step 79666: {'lr': 0.00023057039495424196, 'samples': 15295872, 'steps': 79665, 'loss/train': 1.0131345987319946} 08/31/2021 03:39:26 - INFO - __main__ - Step 79667: {'lr': 0.00023056510426532027, 'samples': 15296064, 'steps': 79666, 'loss/train': 0.9118033647537231} 08/31/2021 03:39:26 - INFO - __main__ - Step 79668: {'lr': 0.00023055981358515565, 'samples': 15296256, 'steps': 79667, 'loss/train': 1.2342051267623901} 08/31/2021 03:39:27 - INFO - __main__ - Step 79669: {'lr': 0.00023055452291375047, 'samples': 15296448, 'steps': 79668, 'loss/train': 1.9039651155471802} 08/31/2021 03:39:28 - INFO - __main__ - Step 79670: {'lr': 0.00023054923225110713, 'samples': 15296640, 'steps': 79669, 'loss/train': 1.990317940711975} 08/31/2021 03:39:29 - INFO - __main__ - Step 79671: {'lr': 0.000230543941597228, 'samples': 15296832, 'steps': 79670, 'loss/train': 1.0092636346817017} 08/31/2021 03:39:29 - INFO - __main__ - Step 79672: {'lr': 0.00023053865095211547, 'samples': 15297024, 'steps': 79671, 'loss/train': 1.514196753501892} 08/31/2021 03:39:29 - INFO - __main__ - Step 79673: {'lr': 0.00023053336031577193, 'samples': 15297216, 'steps': 79672, 'loss/train': 1.7057011127471924} 08/31/2021 03:39:30 - INFO - __main__ - Step 79674: {'lr': 0.00023052806968819976, 'samples': 15297408, 'steps': 79673, 'loss/train': 1.0214555263519287} 08/31/2021 03:39:30 - INFO - __main__ - Step 79675: {'lr': 0.0002305227790694014, 'samples': 15297600, 'steps': 79674, 'loss/train': 0.8247358202934265} 08/31/2021 03:39:32 - INFO - __main__ - Step 79676: {'lr': 0.0002305174884593791, 'samples': 15297792, 'steps': 79675, 'loss/train': 1.5301774740219116} 08/31/2021 03:39:32 - INFO - __main__ - Step 79677: {'lr': 0.00023051219785813533, 'samples': 15297984, 'steps': 79676, 'loss/train': 1.522267460823059} 08/31/2021 03:39:32 - INFO - __main__ - Step 79678: {'lr': 0.00023050690726567248, 'samples': 15298176, 'steps': 79677, 'loss/train': 0.9026455879211426} 08/31/2021 03:39:33 - INFO - __main__ - Step 79679: {'lr': 0.00023050161668199294, 'samples': 15298368, 'steps': 79678, 'loss/train': 0.4094217121601105} 08/31/2021 03:39:33 - INFO - __main__ - Step 79680: {'lr': 0.00023049632610709902, 'samples': 15298560, 'steps': 79679, 'loss/train': 1.6842243671417236} 08/31/2021 03:39:34 - INFO - __main__ - Step 79681: {'lr': 0.00023049103554099318, 'samples': 15298752, 'steps': 79680, 'loss/train': 0.8741511106491089} 08/31/2021 03:39:35 - INFO - __main__ - Step 79682: {'lr': 0.00023048574498367775, 'samples': 15298944, 'steps': 79681, 'loss/train': 1.6708852052688599} 08/31/2021 03:39:35 - INFO - __main__ - Step 79683: {'lr': 0.00023048045443515517, 'samples': 15299136, 'steps': 79682, 'loss/train': 1.4884145259857178} 08/31/2021 03:39:36 - INFO - __main__ - Step 79684: {'lr': 0.00023047516389542778, 'samples': 15299328, 'steps': 79683, 'loss/train': 0.8938584327697754} 08/31/2021 03:39:36 - INFO - __main__ - Step 79685: {'lr': 0.00023046987336449798, 'samples': 15299520, 'steps': 79684, 'loss/train': 1.6280370950698853} 08/31/2021 03:39:38 - INFO - __main__ - Step 79686: {'lr': 0.00023046458284236822, 'samples': 15299712, 'steps': 79685, 'loss/train': 1.0232101678848267} 08/31/2021 03:39:38 - INFO - __main__ - Step 79687: {'lr': 0.00023045929232904075, 'samples': 15299904, 'steps': 79686, 'loss/train': 1.9256490468978882} 08/31/2021 03:39:39 - INFO - __main__ - Step 79688: {'lr': 0.000230454001824518, 'samples': 15300096, 'steps': 79687, 'loss/train': 1.0297834873199463} 08/31/2021 03:39:39 - INFO - __main__ - Step 79689: {'lr': 0.0002304487113288024, 'samples': 15300288, 'steps': 79688, 'loss/train': 1.2327682971954346} 08/31/2021 03:39:39 - INFO - __main__ - Step 79690: {'lr': 0.00023044342084189631, 'samples': 15300480, 'steps': 79689, 'loss/train': 1.6158515214920044} 08/31/2021 03:39:40 - INFO - __main__ - Step 79691: {'lr': 0.00023043813036380213, 'samples': 15300672, 'steps': 79690, 'loss/train': 1.2019834518432617} 08/31/2021 03:39:41 - INFO - __main__ - Step 79692: {'lr': 0.00023043283989452226, 'samples': 15300864, 'steps': 79691, 'loss/train': 0.09913958609104156} 08/31/2021 03:39:42 - INFO - __main__ - Step 79693: {'lr': 0.000230427549434059, 'samples': 15301056, 'steps': 79692, 'loss/train': 1.1987980604171753} 08/31/2021 03:39:42 - INFO - __main__ - Step 79694: {'lr': 0.0002304222589824148, 'samples': 15301248, 'steps': 79693, 'loss/train': 1.2728221416473389} 08/31/2021 03:39:42 - INFO - __main__ - Step 79695: {'lr': 0.00023041696853959198, 'samples': 15301440, 'steps': 79694, 'loss/train': 0.7972903251647949} 08/31/2021 03:39:43 - INFO - __main__ - Step 79696: {'lr': 0.00023041167810559303, 'samples': 15301632, 'steps': 79695, 'loss/train': 1.260718584060669} 08/31/2021 03:39:44 - INFO - __main__ - Step 79697: {'lr': 0.00023040638768042027, 'samples': 15301824, 'steps': 79696, 'loss/train': 0.8556513786315918} 08/31/2021 03:39:45 - INFO - __main__ - Step 79698: {'lr': 0.00023040109726407606, 'samples': 15302016, 'steps': 79697, 'loss/train': 1.1686311960220337} 08/31/2021 03:39:45 - INFO - __main__ - Step 79699: {'lr': 0.00023039580685656284, 'samples': 15302208, 'steps': 79698, 'loss/train': 1.2782424688339233} 08/31/2021 03:39:45 - INFO - __main__ - Step 79700: {'lr': 0.00023039051645788294, 'samples': 15302400, 'steps': 79699, 'loss/train': 1.3979153633117676} 08/31/2021 03:39:46 - INFO - __main__ - Step 79701: {'lr': 0.0002303852260680388, 'samples': 15302592, 'steps': 79700, 'loss/train': 1.0574027299880981} 08/31/2021 03:39:48 - INFO - __main__ - Step 79702: {'lr': 0.00023037993568703275, 'samples': 15302784, 'steps': 79701, 'loss/train': 1.2415729761123657} 08/31/2021 03:39:48 - INFO - __main__ - Step 79703: {'lr': 0.00023037464531486718, 'samples': 15302976, 'steps': 79702, 'loss/train': 0.9561231732368469} 08/31/2021 03:39:49 - INFO - __main__ - Step 79704: {'lr': 0.00023036935495154452, 'samples': 15303168, 'steps': 79703, 'loss/train': 0.6353314518928528} 08/31/2021 03:39:49 - INFO - __main__ - Step 79705: {'lr': 0.0002303640645970671, 'samples': 15303360, 'steps': 79704, 'loss/train': 0.34688010811805725} 08/31/2021 03:39:49 - INFO - __main__ - Step 79706: {'lr': 0.0002303587742514374, 'samples': 15303552, 'steps': 79705, 'loss/train': 0.026500223204493523} 08/31/2021 03:39:50 - INFO - __main__ - Step 79707: {'lr': 0.0002303534839146577, 'samples': 15303744, 'steps': 79706, 'loss/train': 1.7384071350097656} 08/31/2021 03:39:50 - INFO - __main__ - Step 79708: {'lr': 0.00023034819358673045, 'samples': 15303936, 'steps': 79707, 'loss/train': 0.5338785648345947} 08/31/2021 03:39:52 - INFO - __main__ - Step 79709: {'lr': 0.00023034290326765793, 'samples': 15304128, 'steps': 79708, 'loss/train': 0.11907121539115906} 08/31/2021 03:39:53 - INFO - __main__ - Step 79710: {'lr': 0.00023033761295744262, 'samples': 15304320, 'steps': 79709, 'loss/train': 0.929522693157196} 08/31/2021 03:39:53 - INFO - __main__ - Step 79711: {'lr': 0.00023033232265608688, 'samples': 15304512, 'steps': 79710, 'loss/train': 1.6153327226638794} 08/31/2021 03:39:53 - INFO - __main__ - Step 79712: {'lr': 0.0002303270323635931, 'samples': 15304704, 'steps': 79711, 'loss/train': 1.6077414751052856} 08/31/2021 03:39:54 - INFO - __main__ - Step 79713: {'lr': 0.00023032174207996363, 'samples': 15304896, 'steps': 79712, 'loss/train': 0.9731844067573547} 08/31/2021 03:39:56 - INFO - __main__ - Step 79714: {'lr': 0.00023031645180520089, 'samples': 15305088, 'steps': 79713, 'loss/train': 1.0758297443389893} 08/31/2021 03:39:56 - INFO - __main__ - Step 79715: {'lr': 0.00023031116153930726, 'samples': 15305280, 'steps': 79714, 'loss/train': 1.48957359790802} 08/31/2021 03:39:56 - INFO - __main__ - Step 79716: {'lr': 0.00023030587128228507, 'samples': 15305472, 'steps': 79715, 'loss/train': 1.2781307697296143} 08/31/2021 03:39:57 - INFO - __main__ - Step 79717: {'lr': 0.0002303005810341368, 'samples': 15305664, 'steps': 79716, 'loss/train': 0.4037150740623474} 08/31/2021 03:39:57 - INFO - __main__ - Step 79718: {'lr': 0.00023029529079486477, 'samples': 15305856, 'steps': 79717, 'loss/train': 1.2770565748214722} 08/31/2021 03:39:57 - INFO - __main__ - Step 79719: {'lr': 0.0002302900005644715, 'samples': 15306048, 'steps': 79718, 'loss/train': 1.1786874532699585} 08/31/2021 03:39:59 - INFO - __main__ - Step 79720: {'lr': 0.00023028471034295913, 'samples': 15306240, 'steps': 79719, 'loss/train': 0.8808990120887756} 08/31/2021 03:39:59 - INFO - __main__ - Step 79721: {'lr': 0.0002302794201303302, 'samples': 15306432, 'steps': 79720, 'loss/train': 1.6342517137527466} 08/31/2021 03:40:00 - INFO - __main__ - Step 79722: {'lr': 0.000230274129926587, 'samples': 15306624, 'steps': 79721, 'loss/train': 1.4205790758132935} 08/31/2021 03:40:00 - INFO - __main__ - Step 79723: {'lr': 0.000230268839731732, 'samples': 15306816, 'steps': 79722, 'loss/train': 0.436458021402359} 08/31/2021 03:40:01 - INFO - __main__ - Step 79724: {'lr': 0.00023026354954576756, 'samples': 15307008, 'steps': 79723, 'loss/train': 0.7992911338806152} 08/31/2021 03:40:02 - INFO - __main__ - Step 79725: {'lr': 0.00023025825936869604, 'samples': 15307200, 'steps': 79724, 'loss/train': 1.0599607229232788} 08/31/2021 03:40:02 - INFO - __main__ - Step 79726: {'lr': 0.00023025296920051988, 'samples': 15307392, 'steps': 79725, 'loss/train': 1.2922005653381348} 08/31/2021 03:40:03 - INFO - __main__ - Step 79727: {'lr': 0.0002302476790412414, 'samples': 15307584, 'steps': 79726, 'loss/train': 2.00120210647583} 08/31/2021 03:40:03 - INFO - __main__ - Step 79728: {'lr': 0.00023024238889086303, 'samples': 15307776, 'steps': 79727, 'loss/train': 0.7896263003349304} 08/31/2021 03:40:04 - INFO - __main__ - Step 79729: {'lr': 0.0002302370987493871, 'samples': 15307968, 'steps': 79728, 'loss/train': 0.12599638104438782} 08/31/2021 03:40:06 - INFO - __main__ - Step 79730: {'lr': 0.00023023180861681607, 'samples': 15308160, 'steps': 79729, 'loss/train': 0.9670101404190063} 08/31/2021 03:40:06 - INFO - __main__ - Step 79731: {'lr': 0.00023022651849315224, 'samples': 15308352, 'steps': 79730, 'loss/train': 1.279122233390808} 08/31/2021 03:40:07 - INFO - __main__ - Step 79732: {'lr': 0.0002302212283783982, 'samples': 15308544, 'steps': 79731, 'loss/train': 1.3914579153060913} 08/31/2021 03:40:07 - INFO - __main__ - Step 79733: {'lr': 0.000230215938272556, 'samples': 15308736, 'steps': 79732, 'loss/train': 1.2454543113708496} 08/31/2021 03:40:07 - INFO - __main__ - Step 79734: {'lr': 0.00023021064817562822, 'samples': 15308928, 'steps': 79733, 'loss/train': 2.7921664714813232} 08/31/2021 03:40:08 - INFO - __main__ - Step 79735: {'lr': 0.0002302053580876172, 'samples': 15309120, 'steps': 79734, 'loss/train': 2.6817705631256104} 08/31/2021 03:40:08 - INFO - __main__ - Step 79736: {'lr': 0.0002302000680085254, 'samples': 15309312, 'steps': 79735, 'loss/train': 2.7727203369140625} 08/31/2021 03:40:10 - INFO - __main__ - Step 79737: {'lr': 0.0002301947779383551, 'samples': 15309504, 'steps': 79736, 'loss/train': 1.3130937814712524} 08/31/2021 03:40:10 - INFO - __main__ - Step 79738: {'lr': 0.00023018948787710872, 'samples': 15309696, 'steps': 79737, 'loss/train': 0.020788460969924927} 08/31/2021 03:40:11 - INFO - __main__ - Step 79739: {'lr': 0.00023018419782478867, 'samples': 15309888, 'steps': 79738, 'loss/train': 0.022461047396063805} 08/31/2021 03:40:11 - INFO - __main__ - Step 79740: {'lr': 0.00023017890778139727, 'samples': 15310080, 'steps': 79739, 'loss/train': 1.2899994850158691} 08/31/2021 03:40:11 - INFO - __main__ - Step 79741: {'lr': 0.000230173617746937, 'samples': 15310272, 'steps': 79740, 'loss/train': 1.2220271825790405} 08/31/2021 03:40:12 - INFO - __main__ - Step 79742: {'lr': 0.00023016832772141017, 'samples': 15310464, 'steps': 79741, 'loss/train': 1.1140626668930054} 08/31/2021 03:40:14 - INFO - __main__ - Step 79743: {'lr': 0.0002301630377048192, 'samples': 15310656, 'steps': 79742, 'loss/train': 1.79786217212677} 08/31/2021 03:40:15 - INFO - __main__ - Step 79744: {'lr': 0.00023015774769716643, 'samples': 15310848, 'steps': 79743, 'loss/train': 0.8992447853088379} 08/31/2021 03:40:15 - INFO - __main__ - Step 79745: {'lr': 0.0002301524576984543, 'samples': 15311040, 'steps': 79744, 'loss/train': 0.9186757206916809} 08/31/2021 03:40:15 - INFO - __main__ - Step 79746: {'lr': 0.00023014716770868525, 'samples': 15311232, 'steps': 79745, 'loss/train': 1.6769479513168335} 08/31/2021 03:40:16 - INFO - __main__ - Step 79747: {'lr': 0.00023014187772786153, 'samples': 15311424, 'steps': 79746, 'loss/train': 1.8031100034713745} 08/31/2021 03:40:16 - INFO - __main__ - Step 79748: {'lr': 0.00023013658775598552, 'samples': 15311616, 'steps': 79747, 'loss/train': 0.9770482182502747} 08/31/2021 03:40:16 - INFO - __main__ - Step 79749: {'lr': 0.00023013129779305967, 'samples': 15311808, 'steps': 79748, 'loss/train': 1.7484676837921143} 08/31/2021 03:40:18 - INFO - __main__ - Step 79750: {'lr': 0.00023012600783908633, 'samples': 15312000, 'steps': 79749, 'loss/train': 0.962674081325531} 08/31/2021 03:40:18 - INFO - __main__ - Step 79751: {'lr': 0.00023012071789406795, 'samples': 15312192, 'steps': 79750, 'loss/train': 1.3550008535385132} 08/31/2021 03:40:19 - INFO - __main__ - Step 79752: {'lr': 0.00023011542795800682, 'samples': 15312384, 'steps': 79751, 'loss/train': 1.136311650276184} 08/31/2021 03:40:19 - INFO - __main__ - Step 79753: {'lr': 0.0002301101380309054, 'samples': 15312576, 'steps': 79752, 'loss/train': 1.6623122692108154} 08/31/2021 03:40:19 - INFO - __main__ - Step 79754: {'lr': 0.00023010484811276602, 'samples': 15312768, 'steps': 79753, 'loss/train': 1.3098007440567017} 08/31/2021 03:40:21 - INFO - __main__ - Step 79755: {'lr': 0.00023009955820359112, 'samples': 15312960, 'steps': 79754, 'loss/train': 1.7344475984573364} 08/31/2021 03:40:21 - INFO - __main__ - Step 79756: {'lr': 0.00023009426830338303, 'samples': 15313152, 'steps': 79755, 'loss/train': 1.0095220804214478} 08/31/2021 03:40:22 - INFO - __main__ - Step 79757: {'lr': 0.00023008897841214415, 'samples': 15313344, 'steps': 79756, 'loss/train': 1.4654483795166016} 08/31/2021 03:40:22 - INFO - __main__ - Step 79758: {'lr': 0.0002300836885298769, 'samples': 15313536, 'steps': 79757, 'loss/train': 1.2269307374954224} 08/31/2021 03:40:22 - INFO - __main__ - Step 79759: {'lr': 0.00023007839865658373, 'samples': 15313728, 'steps': 79758, 'loss/train': 1.0916664600372314} 08/31/2021 03:40:24 - INFO - __main__ - Step 79760: {'lr': 0.0002300731087922668, 'samples': 15313920, 'steps': 79759, 'loss/train': 0.9830987453460693} 08/31/2021 03:40:24 - INFO - __main__ - Step 79761: {'lr': 0.00023006781893692864, 'samples': 15314112, 'steps': 79760, 'loss/train': 0.6262322068214417} 08/31/2021 03:40:25 - INFO - __main__ - Step 79762: {'lr': 0.0002300625290905716, 'samples': 15314304, 'steps': 79761, 'loss/train': 1.344754934310913} 08/31/2021 03:40:25 - INFO - __main__ - Step 79763: {'lr': 0.00023005723925319807, 'samples': 15314496, 'steps': 79762, 'loss/train': 1.3934720754623413} 08/31/2021 03:40:25 - INFO - __main__ - Step 79764: {'lr': 0.00023005194942481047, 'samples': 15314688, 'steps': 79763, 'loss/train': 1.1323491334915161} 08/31/2021 03:40:27 - INFO - __main__ - Step 79765: {'lr': 0.00023004665960541112, 'samples': 15314880, 'steps': 79764, 'loss/train': 1.3436400890350342} 08/31/2021 03:40:28 - INFO - __main__ - Step 79766: {'lr': 0.00023004136979500246, 'samples': 15315072, 'steps': 79765, 'loss/train': 2.2884936332702637} 08/31/2021 03:40:28 - INFO - __main__ - Step 79767: {'lr': 0.00023003607999358685, 'samples': 15315264, 'steps': 79766, 'loss/train': 1.2943624258041382} 08/31/2021 03:40:29 - INFO - __main__ - Step 79768: {'lr': 0.00023003079020116664, 'samples': 15315456, 'steps': 79767, 'loss/train': 1.2741886377334595} 08/31/2021 03:40:29 - INFO - __main__ - Step 79769: {'lr': 0.0002300255004177443, 'samples': 15315648, 'steps': 79768, 'loss/train': 1.001104712486267} 08/31/2021 03:40:29 - INFO - __main__ - Step 79770: {'lr': 0.00023002021064332212, 'samples': 15315840, 'steps': 79769, 'loss/train': 1.848813533782959} 08/31/2021 03:40:31 - INFO - __main__ - Step 79771: {'lr': 0.00023001492087790253, 'samples': 15316032, 'steps': 79770, 'loss/train': 1.1669007539749146} 08/31/2021 03:40:31 - INFO - __main__ - Step 79772: {'lr': 0.00023000963112148793, 'samples': 15316224, 'steps': 79771, 'loss/train': 1.2957022190093994} 08/31/2021 03:40:32 - INFO - __main__ - Step 79773: {'lr': 0.0002300043413740808, 'samples': 15316416, 'steps': 79772, 'loss/train': 1.323261022567749} 08/31/2021 03:40:32 - INFO - __main__ - Step 79774: {'lr': 0.00022999905163568327, 'samples': 15316608, 'steps': 79773, 'loss/train': 1.4629380702972412} 08/31/2021 03:40:32 - INFO - __main__ - Step 79775: {'lr': 0.00022999376190629788, 'samples': 15316800, 'steps': 79774, 'loss/train': 1.3958501815795898} 08/31/2021 03:40:34 - INFO - __main__ - Step 79776: {'lr': 0.00022998847218592698, 'samples': 15316992, 'steps': 79775, 'loss/train': 1.5319730043411255} 08/31/2021 03:40:34 - INFO - __main__ - Step 79777: {'lr': 0.00022998318247457295, 'samples': 15317184, 'steps': 79776, 'loss/train': 1.6507781744003296} 08/31/2021 03:40:35 - INFO - __main__ - Step 79778: {'lr': 0.0002299778927722382, 'samples': 15317376, 'steps': 79777, 'loss/train': 1.4907289743423462} 08/31/2021 03:40:35 - INFO - __main__ - Step 79779: {'lr': 0.0002299726030789251, 'samples': 15317568, 'steps': 79778, 'loss/train': 0.8544327616691589} 08/31/2021 03:40:35 - INFO - __main__ - Step 79780: {'lr': 0.00022996731339463604, 'samples': 15317760, 'steps': 79779, 'loss/train': 1.1943367719650269} 08/31/2021 03:40:37 - INFO - __main__ - Step 79781: {'lr': 0.00022996202371937342, 'samples': 15317952, 'steps': 79780, 'loss/train': 1.1503092050552368} 08/31/2021 03:40:37 - INFO - __main__ - Step 79782: {'lr': 0.00022995673405313955, 'samples': 15318144, 'steps': 79781, 'loss/train': 1.521700143814087} 08/31/2021 03:40:38 - INFO - __main__ - Step 79783: {'lr': 0.0002299514443959369, 'samples': 15318336, 'steps': 79782, 'loss/train': 1.418323278427124} 08/31/2021 03:40:38 - INFO - __main__ - Step 79784: {'lr': 0.00022994615474776785, 'samples': 15318528, 'steps': 79783, 'loss/train': 1.2009813785552979} 08/31/2021 03:40:38 - INFO - __main__ - Step 79785: {'lr': 0.00022994086510863472, 'samples': 15318720, 'steps': 79784, 'loss/train': 1.7278825044631958} 08/31/2021 03:40:40 - INFO - __main__ - Step 79786: {'lr': 0.00022993557547854002, 'samples': 15318912, 'steps': 79785, 'loss/train': 1.2897453308105469} 08/31/2021 03:40:40 - INFO - __main__ - Step 79787: {'lr': 0.00022993028585748597, 'samples': 15319104, 'steps': 79786, 'loss/train': 0.8333655595779419} 08/31/2021 03:40:41 - INFO - __main__ - Step 79788: {'lr': 0.00022992499624547498, 'samples': 15319296, 'steps': 79787, 'loss/train': 1.0156317949295044} 08/31/2021 03:40:41 - INFO - __main__ - Step 79789: {'lr': 0.0002299197066425095, 'samples': 15319488, 'steps': 79788, 'loss/train': 1.4262926578521729} 08/31/2021 03:40:41 - INFO - __main__ - Step 79790: {'lr': 0.0002299144170485919, 'samples': 15319680, 'steps': 79789, 'loss/train': 0.09216182678937912} 08/31/2021 03:40:42 - INFO - __main__ - Step 79791: {'lr': 0.00022990912746372454, 'samples': 15319872, 'steps': 79790, 'loss/train': 1.4024957418441772} 08/31/2021 03:40:43 - INFO - __main__ - Step 79792: {'lr': 0.0002299038378879098, 'samples': 15320064, 'steps': 79791, 'loss/train': 4.787179946899414} 08/31/2021 03:40:44 - INFO - __main__ - Step 79793: {'lr': 0.00022989854832115012, 'samples': 15320256, 'steps': 79792, 'loss/train': 1.3628767728805542} 08/31/2021 03:40:44 - INFO - __main__ - Step 79794: {'lr': 0.00022989325876344782, 'samples': 15320448, 'steps': 79793, 'loss/train': 0.7842892408370972} 08/31/2021 03:40:44 - INFO - __main__ - Step 79795: {'lr': 0.00022988796921480533, 'samples': 15320640, 'steps': 79794, 'loss/train': 1.3770111799240112} 08/31/2021 03:40:45 - INFO - __main__ - Step 79796: {'lr': 0.00022988267967522498, 'samples': 15320832, 'steps': 79795, 'loss/train': 1.3280727863311768} 08/31/2021 03:40:46 - INFO - __main__ - Step 79797: {'lr': 0.0002298773901447092, 'samples': 15321024, 'steps': 79796, 'loss/train': 1.1544911861419678} 08/31/2021 03:40:47 - INFO - __main__ - Step 79798: {'lr': 0.00022987210062326043, 'samples': 15321216, 'steps': 79797, 'loss/train': 0.9981493949890137} 08/31/2021 03:40:47 - INFO - __main__ - Step 79799: {'lr': 0.00022986681111088086, 'samples': 15321408, 'steps': 79798, 'loss/train': 0.03408624231815338} 08/31/2021 03:40:48 - INFO - __main__ - Step 79800: {'lr': 0.00022986152160757312, 'samples': 15321600, 'steps': 79799, 'loss/train': 1.1763513088226318} 08/31/2021 03:40:48 - INFO - __main__ - Step 79801: {'lr': 0.0002298562321133394, 'samples': 15321792, 'steps': 79800, 'loss/train': 1.209014892578125} 08/31/2021 03:40:49 - INFO - __main__ - Step 79802: {'lr': 0.00022985094262818214, 'samples': 15321984, 'steps': 79801, 'loss/train': 1.2103290557861328} 08/31/2021 03:40:50 - INFO - __main__ - Step 79803: {'lr': 0.0002298456531521037, 'samples': 15322176, 'steps': 79802, 'loss/train': 1.2660413980484009} 08/31/2021 03:40:50 - INFO - __main__ - Step 79804: {'lr': 0.00022984036368510656, 'samples': 15322368, 'steps': 79803, 'loss/train': 1.365940809249878} 08/31/2021 03:40:50 - INFO - __main__ - Step 79805: {'lr': 0.00022983507422719298, 'samples': 15322560, 'steps': 79804, 'loss/train': 1.2444384098052979} 08/31/2021 03:40:51 - INFO - __main__ - Step 79806: {'lr': 0.00022982978477836545, 'samples': 15322752, 'steps': 79805, 'loss/train': 1.3483660221099854} 08/31/2021 03:40:51 - INFO - __main__ - Step 79807: {'lr': 0.0002298244953386263, 'samples': 15322944, 'steps': 79806, 'loss/train': 0.6141770482063293} 08/31/2021 03:40:53 - INFO - __main__ - Step 79808: {'lr': 0.00022981920590797793, 'samples': 15323136, 'steps': 79807, 'loss/train': 0.9167575836181641} 08/31/2021 03:40:53 - INFO - __main__ - Step 79809: {'lr': 0.00022981391648642274, 'samples': 15323328, 'steps': 79808, 'loss/train': 1.7284276485443115} 08/31/2021 03:40:54 - INFO - __main__ - Step 79810: {'lr': 0.00022980862707396306, 'samples': 15323520, 'steps': 79809, 'loss/train': 2.161388635635376} 08/31/2021 03:40:54 - INFO - __main__ - Step 79811: {'lr': 0.00022980333767060127, 'samples': 15323712, 'steps': 79810, 'loss/train': 0.13482822477817535} 08/31/2021 03:40:54 - INFO - __main__ - Step 79812: {'lr': 0.0002297980482763398, 'samples': 15323904, 'steps': 79811, 'loss/train': 0.3819679617881775} 08/31/2021 03:40:56 - INFO - __main__ - Step 79813: {'lr': 0.00022979275889118105, 'samples': 15324096, 'steps': 79812, 'loss/train': 1.3846973180770874} 08/31/2021 03:40:56 - INFO - __main__ - Step 79814: {'lr': 0.00022978746951512737, 'samples': 15324288, 'steps': 79813, 'loss/train': 0.28598153591156006} 08/31/2021 03:40:57 - INFO - __main__ - Step 79815: {'lr': 0.0002297821801481811, 'samples': 15324480, 'steps': 79814, 'loss/train': 1.0741629600524902} 08/31/2021 03:40:57 - INFO - __main__ - Step 79816: {'lr': 0.0002297768907903447, 'samples': 15324672, 'steps': 79815, 'loss/train': 1.7140836715698242} 08/31/2021 03:40:57 - INFO - __main__ - Step 79817: {'lr': 0.0002297716014416205, 'samples': 15324864, 'steps': 79816, 'loss/train': 1.238156795501709} 08/31/2021 03:40:59 - INFO - __main__ - Step 79818: {'lr': 0.0002297663121020109, 'samples': 15325056, 'steps': 79817, 'loss/train': 0.9392926692962646} 08/31/2021 03:41:00 - INFO - __main__ - Step 79819: {'lr': 0.0002297610227715183, 'samples': 15325248, 'steps': 79818, 'loss/train': 1.27190101146698} 08/31/2021 03:41:00 - INFO - __main__ - Step 79820: {'lr': 0.0002297557334501451, 'samples': 15325440, 'steps': 79819, 'loss/train': 1.1496385335922241} 08/31/2021 03:41:01 - INFO - __main__ - Step 79821: {'lr': 0.00022975044413789365, 'samples': 15325632, 'steps': 79820, 'loss/train': 1.1070866584777832} 08/31/2021 03:41:01 - INFO - __main__ - Step 79822: {'lr': 0.0002297451548347663, 'samples': 15325824, 'steps': 79821, 'loss/train': 1.0605826377868652} 08/31/2021 03:41:03 - INFO - __main__ - Step 79823: {'lr': 0.0002297398655407655, 'samples': 15326016, 'steps': 79822, 'loss/train': 0.7497085928916931} 08/31/2021 03:41:03 - INFO - __main__ - Step 79824: {'lr': 0.00022973457625589355, 'samples': 15326208, 'steps': 79823, 'loss/train': 2.7875864505767822} 08/31/2021 03:41:04 - INFO - __main__ - Step 79825: {'lr': 0.00022972928698015293, 'samples': 15326400, 'steps': 79824, 'loss/train': 0.8114245533943176} 08/31/2021 03:41:04 - INFO - __main__ - Step 79826: {'lr': 0.00022972399771354596, 'samples': 15326592, 'steps': 79825, 'loss/train': 1.532663345336914} 08/31/2021 03:41:04 - INFO - __main__ - Step 79827: {'lr': 0.00022971870845607512, 'samples': 15326784, 'steps': 79826, 'loss/train': 0.7324280142784119} 08/31/2021 03:41:06 - INFO - __main__ - Step 79828: {'lr': 0.00022971341920774267, 'samples': 15326976, 'steps': 79827, 'loss/train': 0.40185317397117615} 08/31/2021 03:41:06 - INFO - __main__ - Step 79829: {'lr': 0.000229708129968551, 'samples': 15327168, 'steps': 79828, 'loss/train': 1.5227534770965576} 08/31/2021 03:41:06 - INFO - __main__ - Step 79830: {'lr': 0.00022970284073850256, 'samples': 15327360, 'steps': 79829, 'loss/train': 1.788718819618225} 08/31/2021 03:41:07 - INFO - __main__ - Step 79831: {'lr': 0.00022969755151759974, 'samples': 15327552, 'steps': 79830, 'loss/train': 1.076412320137024} 08/31/2021 03:41:07 - INFO - __main__ - Step 79832: {'lr': 0.00022969226230584486, 'samples': 15327744, 'steps': 79831, 'loss/train': 1.7091050148010254} 08/31/2021 03:41:08 - INFO - __main__ - Step 79833: {'lr': 0.00022968697310324032, 'samples': 15327936, 'steps': 79832, 'loss/train': 1.0450190305709839} 08/31/2021 03:41:09 - INFO - __main__ - Step 79834: {'lr': 0.00022968168390978853, 'samples': 15328128, 'steps': 79833, 'loss/train': 1.0438789129257202} 08/31/2021 03:41:10 - INFO - __main__ - Step 79835: {'lr': 0.00022967639472549185, 'samples': 15328320, 'steps': 79834, 'loss/train': 0.9730824828147888} 08/31/2021 03:41:10 - INFO - __main__ - Step 79836: {'lr': 0.00022967110555035267, 'samples': 15328512, 'steps': 79835, 'loss/train': 1.3358408212661743} 08/31/2021 03:41:10 - INFO - __main__ - Step 79837: {'lr': 0.0002296658163843734, 'samples': 15328704, 'steps': 79836, 'loss/train': 1.0459816455841064} 08/31/2021 03:41:11 - INFO - __main__ - Step 79838: {'lr': 0.00022966052722755637, 'samples': 15328896, 'steps': 79837, 'loss/train': 0.9947965145111084} 08/31/2021 03:41:12 - INFO - __main__ - Step 79839: {'lr': 0.00022965523807990399, 'samples': 15329088, 'steps': 79838, 'loss/train': 1.1433087587356567} 08/31/2021 03:41:13 - INFO - __main__ - Step 79840: {'lr': 0.00022964994894141873, 'samples': 15329280, 'steps': 79839, 'loss/train': 1.336995005607605} 08/31/2021 03:41:13 - INFO - __main__ - Step 79841: {'lr': 0.0002296446598121028, 'samples': 15329472, 'steps': 79840, 'loss/train': 0.7115391492843628} 08/31/2021 03:41:13 - INFO - __main__ - Step 79842: {'lr': 0.00022963937069195875, 'samples': 15329664, 'steps': 79841, 'loss/train': 1.196575403213501} 08/31/2021 03:41:14 - INFO - __main__ - Step 79843: {'lr': 0.00022963408158098884, 'samples': 15329856, 'steps': 79842, 'loss/train': 1.3435252904891968} 08/31/2021 03:41:15 - INFO - __main__ - Step 79844: {'lr': 0.00022962879247919547, 'samples': 15330048, 'steps': 79843, 'loss/train': 1.2710870504379272} 08/31/2021 03:41:16 - INFO - __main__ - Step 79845: {'lr': 0.00022962350338658107, 'samples': 15330240, 'steps': 79844, 'loss/train': 1.2761883735656738} 08/31/2021 03:41:16 - INFO - __main__ - Step 79846: {'lr': 0.000229618214303148, 'samples': 15330432, 'steps': 79845, 'loss/train': 1.4668431282043457} 08/31/2021 03:41:16 - INFO - __main__ - Step 79847: {'lr': 0.00022961292522889865, 'samples': 15330624, 'steps': 79846, 'loss/train': 1.2051844596862793} 08/31/2021 03:41:17 - INFO - __main__ - Step 79848: {'lr': 0.0002296076361638354, 'samples': 15330816, 'steps': 79847, 'loss/train': 1.5350571870803833} 08/31/2021 03:41:18 - INFO - __main__ - Step 79849: {'lr': 0.00022960234710796062, 'samples': 15331008, 'steps': 79848, 'loss/train': 1.089987874031067} 08/31/2021 03:41:19 - INFO - __main__ - Step 79850: {'lr': 0.00022959705806127674, 'samples': 15331200, 'steps': 79849, 'loss/train': 0.12988613545894623} 08/31/2021 03:41:19 - INFO - __main__ - Step 79851: {'lr': 0.0002295917690237861, 'samples': 15331392, 'steps': 79850, 'loss/train': 0.7805175185203552} 08/31/2021 03:41:19 - INFO - __main__ - Step 79852: {'lr': 0.00022958647999549107, 'samples': 15331584, 'steps': 79851, 'loss/train': 1.4558453559875488} 08/31/2021 03:41:20 - INFO - __main__ - Step 79853: {'lr': 0.00022958119097639417, 'samples': 15331776, 'steps': 79852, 'loss/train': 1.0306334495544434} 08/31/2021 03:41:20 - INFO - __main__ - Step 79854: {'lr': 0.00022957590196649757, 'samples': 15331968, 'steps': 79853, 'loss/train': 1.3704732656478882} 08/31/2021 03:41:21 - INFO - __main__ - Step 79855: {'lr': 0.00022957061296580378, 'samples': 15332160, 'steps': 79854, 'loss/train': 1.421869158744812} 08/31/2021 03:41:22 - INFO - __main__ - Step 79856: {'lr': 0.0002295653239743151, 'samples': 15332352, 'steps': 79855, 'loss/train': 1.1289998292922974} 08/31/2021 03:41:22 - INFO - __main__ - Step 79857: {'lr': 0.00022956003499203403, 'samples': 15332544, 'steps': 79856, 'loss/train': 0.8955118060112} 08/31/2021 03:41:23 - INFO - __main__ - Step 79858: {'lr': 0.00022955474601896286, 'samples': 15332736, 'steps': 79857, 'loss/train': 1.3120168447494507} 08/31/2021 03:41:23 - INFO - __main__ - Step 79859: {'lr': 0.00022954945705510403, 'samples': 15332928, 'steps': 79858, 'loss/train': 1.3807573318481445} 08/31/2021 03:41:24 - INFO - __main__ - Step 79860: {'lr': 0.00022954416810045986, 'samples': 15333120, 'steps': 79859, 'loss/train': 0.865451455116272} 08/31/2021 03:41:25 - INFO - __main__ - Step 79861: {'lr': 0.0002295388791550328, 'samples': 15333312, 'steps': 79860, 'loss/train': 1.0766022205352783} 08/31/2021 03:41:25 - INFO - __main__ - Step 79862: {'lr': 0.0002295335902188252, 'samples': 15333504, 'steps': 79861, 'loss/train': 1.187575101852417} 08/31/2021 03:41:26 - INFO - __main__ - Step 79863: {'lr': 0.00022952830129183943, 'samples': 15333696, 'steps': 79862, 'loss/train': 1.6676597595214844} 08/31/2021 03:41:26 - INFO - __main__ - Step 79864: {'lr': 0.00022952301237407792, 'samples': 15333888, 'steps': 79863, 'loss/train': 1.4066685438156128} 08/31/2021 03:41:28 - INFO - __main__ - Step 79865: {'lr': 0.000229517723465543, 'samples': 15334080, 'steps': 79864, 'loss/train': 1.6667064428329468} 08/31/2021 03:41:28 - INFO - __main__ - Step 79866: {'lr': 0.0002295124345662371, 'samples': 15334272, 'steps': 79865, 'loss/train': 3.9589459896087646} 08/31/2021 03:41:28 - INFO - __main__ - Step 79867: {'lr': 0.00022950714567616267, 'samples': 15334464, 'steps': 79866, 'loss/train': 1.3435536623001099} 08/31/2021 03:41:29 - INFO - __main__ - Step 79868: {'lr': 0.00022950185679532193, 'samples': 15334656, 'steps': 79867, 'loss/train': 1.10215425491333} 08/31/2021 03:41:29 - INFO - __main__ - Step 79869: {'lr': 0.00022949656792371732, 'samples': 15334848, 'steps': 79868, 'loss/train': 1.2455755472183228} 08/31/2021 03:41:30 - INFO - __main__ - Step 79870: {'lr': 0.00022949127906135122, 'samples': 15335040, 'steps': 79869, 'loss/train': 1.256679654121399} 08/31/2021 03:41:31 - INFO - __main__ - Step 79871: {'lr': 0.00022948599020822605, 'samples': 15335232, 'steps': 79870, 'loss/train': 1.7954837083816528} 08/31/2021 03:41:31 - INFO - __main__ - Step 79872: {'lr': 0.00022948070136434416, 'samples': 15335424, 'steps': 79871, 'loss/train': 1.284925103187561} 08/31/2021 03:41:32 - INFO - __main__ - Step 79873: {'lr': 0.00022947541252970797, 'samples': 15335616, 'steps': 79872, 'loss/train': 0.8479755520820618} 08/31/2021 03:41:32 - INFO - __main__ - Step 79874: {'lr': 0.00022947012370431983, 'samples': 15335808, 'steps': 79873, 'loss/train': 1.3365882635116577} 08/31/2021 03:41:32 - INFO - __main__ - Step 79875: {'lr': 0.00022946483488818216, 'samples': 15336000, 'steps': 79874, 'loss/train': 1.1995874643325806} 08/31/2021 03:41:34 - INFO - __main__ - Step 79876: {'lr': 0.00022945954608129726, 'samples': 15336192, 'steps': 79875, 'loss/train': 1.2823796272277832} 08/31/2021 03:41:35 - INFO - __main__ - Step 79877: {'lr': 0.00022945425728366763, 'samples': 15336384, 'steps': 79876, 'loss/train': 0.8468428254127502} 08/31/2021 03:41:35 - INFO - __main__ - Step 79878: {'lr': 0.00022944896849529556, 'samples': 15336576, 'steps': 79877, 'loss/train': 1.2222275733947754} 08/31/2021 03:41:35 - INFO - __main__ - Step 79879: {'lr': 0.00022944367971618348, 'samples': 15336768, 'steps': 79878, 'loss/train': 1.1773669719696045} 08/31/2021 03:41:36 - INFO - __main__ - Step 79880: {'lr': 0.0002294383909463339, 'samples': 15336960, 'steps': 79879, 'loss/train': 0.9129424095153809} 08/31/2021 03:41:37 - INFO - __main__ - Step 79881: {'lr': 0.00022943310218574893, 'samples': 15337152, 'steps': 79880, 'loss/train': 1.1465665102005005} 08/31/2021 03:41:38 - INFO - __main__ - Step 79882: {'lr': 0.00022942781343443107, 'samples': 15337344, 'steps': 79881, 'loss/train': 1.0498675107955933} 08/31/2021 03:41:38 - INFO - __main__ - Step 79883: {'lr': 0.00022942252469238274, 'samples': 15337536, 'steps': 79882, 'loss/train': 1.3057804107666016} 08/31/2021 03:41:38 - INFO - __main__ - Step 79884: {'lr': 0.00022941723595960628, 'samples': 15337728, 'steps': 79883, 'loss/train': 1.5873349905014038} 08/31/2021 03:41:39 - INFO - __main__ - Step 79885: {'lr': 0.00022941194723610412, 'samples': 15337920, 'steps': 79884, 'loss/train': 1.1098488569259644} 08/31/2021 03:41:40 - INFO - __main__ - Step 79886: {'lr': 0.0002294066585218786, 'samples': 15338112, 'steps': 79885, 'loss/train': 1.167824387550354} 08/31/2021 03:41:41 - INFO - __main__ - Step 79887: {'lr': 0.00022940136981693213, 'samples': 15338304, 'steps': 79886, 'loss/train': 1.0973637104034424} 08/31/2021 03:41:41 - INFO - __main__ - Step 79888: {'lr': 0.00022939608112126708, 'samples': 15338496, 'steps': 79887, 'loss/train': 1.375264048576355} 08/31/2021 03:41:41 - INFO - __main__ - Step 79889: {'lr': 0.00022939079243488586, 'samples': 15338688, 'steps': 79888, 'loss/train': 1.0433895587921143} 08/31/2021 03:41:42 - INFO - __main__ - Step 79890: {'lr': 0.00022938550375779083, 'samples': 15338880, 'steps': 79889, 'loss/train': 0.5357288718223572} 08/31/2021 03:41:43 - INFO - __main__ - Step 79891: {'lr': 0.00022938021508998435, 'samples': 15339072, 'steps': 79890, 'loss/train': 1.467763066291809} 08/31/2021 03:41:44 - INFO - __main__ - Step 79892: {'lr': 0.00022937492643146886, 'samples': 15339264, 'steps': 79891, 'loss/train': 0.03206828981637955} 08/31/2021 03:41:44 - INFO - __main__ - Step 79893: {'lr': 0.00022936963778224666, 'samples': 15339456, 'steps': 79892, 'loss/train': 3.0639936923980713} 08/31/2021 03:41:45 - INFO - __main__ - Step 79894: {'lr': 0.00022936434914232033, 'samples': 15339648, 'steps': 79893, 'loss/train': 0.045703135430812836} 08/31/2021 03:41:45 - INFO - __main__ - Step 79895: {'lr': 0.00022935906051169198, 'samples': 15339840, 'steps': 79894, 'loss/train': 1.4569993019104004} 08/31/2021 03:41:46 - INFO - __main__ - Step 79896: {'lr': 0.0002293537718903641, 'samples': 15340032, 'steps': 79895, 'loss/train': 0.8569870591163635} 08/31/2021 03:41:47 - INFO - __main__ - Step 79897: {'lr': 0.00022934848327833913, 'samples': 15340224, 'steps': 79896, 'loss/train': 0.7699170112609863} 08/31/2021 03:41:47 - INFO - __main__ - Step 79898: {'lr': 0.0002293431946756194, 'samples': 15340416, 'steps': 79897, 'loss/train': 0.7815845012664795} 08/31/2021 03:41:48 - INFO - __main__ - Step 79899: {'lr': 0.00022933790608220731, 'samples': 15340608, 'steps': 79898, 'loss/train': 1.1296656131744385} 08/31/2021 03:41:48 - INFO - __main__ - Step 79900: {'lr': 0.00022933261749810525, 'samples': 15340800, 'steps': 79899, 'loss/train': 0.4961404502391815} 08/31/2021 03:41:50 - INFO - __main__ - Step 79901: {'lr': 0.00022932732892331557, 'samples': 15340992, 'steps': 79900, 'loss/train': 0.5920200347900391} 08/31/2021 03:41:50 - INFO - __main__ - Step 79902: {'lr': 0.00022932204035784067, 'samples': 15341184, 'steps': 79901, 'loss/train': 1.3278307914733887} 08/31/2021 03:41:50 - INFO - __main__ - Step 79903: {'lr': 0.000229316751801683, 'samples': 15341376, 'steps': 79902, 'loss/train': 0.3948673903942108} 08/31/2021 03:41:51 - INFO - __main__ - Step 79904: {'lr': 0.0002293114632548448, 'samples': 15341568, 'steps': 79903, 'loss/train': 1.2787742614746094} 08/31/2021 03:41:51 - INFO - __main__ - Step 79905: {'lr': 0.00022930617471732858, 'samples': 15341760, 'steps': 79904, 'loss/train': 0.9479219913482666} 08/31/2021 03:41:52 - INFO - __main__ - Step 79906: {'lr': 0.00022930088618913668, 'samples': 15341952, 'steps': 79905, 'loss/train': 1.6593730449676514} 08/31/2021 03:41:53 - INFO - __main__ - Step 79907: {'lr': 0.0002292955976702716, 'samples': 15342144, 'steps': 79906, 'loss/train': 2.290722131729126} 08/31/2021 03:41:53 - INFO - __main__ - Step 79908: {'lr': 0.00022929030916073547, 'samples': 15342336, 'steps': 79907, 'loss/train': 0.7698394060134888} 08/31/2021 03:41:54 - INFO - __main__ - Step 79909: {'lr': 0.00022928502066053085, 'samples': 15342528, 'steps': 79908, 'loss/train': 1.5484787225723267} 08/31/2021 03:41:54 - INFO - __main__ - Step 79910: {'lr': 0.00022927973216966004, 'samples': 15342720, 'steps': 79909, 'loss/train': 0.7320510745048523} 08/31/2021 03:41:56 - INFO - __main__ - Step 79911: {'lr': 0.00022927444368812545, 'samples': 15342912, 'steps': 79910, 'loss/train': 0.7754265069961548} 08/31/2021 03:41:56 - INFO - __main__ - Step 79912: {'lr': 0.0002292691552159295, 'samples': 15343104, 'steps': 79911, 'loss/train': 1.2167632579803467} 08/31/2021 03:41:56 - INFO - __main__ - Step 79913: {'lr': 0.00022926386675307454, 'samples': 15343296, 'steps': 79912, 'loss/train': 1.0360000133514404} 08/31/2021 03:41:57 - INFO - __main__ - Step 79914: {'lr': 0.00022925857829956297, 'samples': 15343488, 'steps': 79913, 'loss/train': 0.3138512372970581} 08/31/2021 03:41:57 - INFO - __main__ - Step 79915: {'lr': 0.00022925328985539718, 'samples': 15343680, 'steps': 79914, 'loss/train': 0.8287833333015442} 08/31/2021 03:41:58 - INFO - __main__ - Step 79916: {'lr': 0.0002292480014205795, 'samples': 15343872, 'steps': 79915, 'loss/train': 0.8070894479751587} 08/31/2021 03:41:59 - INFO - __main__ - Step 79917: {'lr': 0.00022924271299511238, 'samples': 15344064, 'steps': 79916, 'loss/train': 1.5773922204971313} 08/31/2021 03:41:59 - INFO - __main__ - Step 79918: {'lr': 0.00022923742457899815, 'samples': 15344256, 'steps': 79917, 'loss/train': 1.8841930627822876} 08/31/2021 03:42:00 - INFO - __main__ - Step 79919: {'lr': 0.00022923213617223923, 'samples': 15344448, 'steps': 79918, 'loss/train': 1.6725553274154663} 08/31/2021 03:42:00 - INFO - __main__ - Step 79920: {'lr': 0.00022922684777483798, 'samples': 15344640, 'steps': 79919, 'loss/train': 1.2714561223983765} 08/31/2021 03:42:00 - INFO - __main__ - Step 79921: {'lr': 0.0002292215593867969, 'samples': 15344832, 'steps': 79920, 'loss/train': 1.3206923007965088} 08/31/2021 03:42:02 - INFO - __main__ - Step 79922: {'lr': 0.0002292162710081182, 'samples': 15345024, 'steps': 79921, 'loss/train': 0.6163790822029114} 08/31/2021 03:42:02 - INFO - __main__ - Step 79923: {'lr': 0.00022921098263880427, 'samples': 15345216, 'steps': 79922, 'loss/train': 0.9874709248542786} 08/31/2021 03:42:03 - INFO - __main__ - Step 79924: {'lr': 0.0002292056942788576, 'samples': 15345408, 'steps': 79923, 'loss/train': 0.9333024621009827} 08/31/2021 03:42:03 - INFO - __main__ - Step 79925: {'lr': 0.00022920040592828048, 'samples': 15345600, 'steps': 79924, 'loss/train': 1.378861427307129} 08/31/2021 03:42:03 - INFO - __main__ - Step 79926: {'lr': 0.00022919511758707535, 'samples': 15345792, 'steps': 79925, 'loss/train': 1.7351244688034058} 08/31/2021 03:42:06 - INFO - __main__ - Step 79927: {'lr': 0.00022918982925524458, 'samples': 15345984, 'steps': 79926, 'loss/train': 1.3502154350280762} 08/31/2021 03:42:06 - INFO - __main__ - Step 79928: {'lr': 0.00022918454093279056, 'samples': 15346176, 'steps': 79927, 'loss/train': 1.2783993482589722} 08/31/2021 03:42:06 - INFO - __main__ - Step 79929: {'lr': 0.00022917925261971566, 'samples': 15346368, 'steps': 79928, 'loss/train': 1.2359364032745361} 08/31/2021 03:42:07 - INFO - __main__ - Step 79930: {'lr': 0.00022917396431602224, 'samples': 15346560, 'steps': 79929, 'loss/train': 1.6352145671844482} 08/31/2021 03:42:07 - INFO - __main__ - Step 79931: {'lr': 0.00022916867602171276, 'samples': 15346752, 'steps': 79930, 'loss/train': 1.440230369567871} 08/31/2021 03:42:09 - INFO - __main__ - Step 79932: {'lr': 0.0002291633877367895, 'samples': 15346944, 'steps': 79931, 'loss/train': 0.648653507232666} 08/31/2021 03:42:09 - INFO - __main__ - Step 79933: {'lr': 0.000229158099461255, 'samples': 15347136, 'steps': 79932, 'loss/train': 0.9454703330993652} 08/31/2021 03:42:10 - INFO - __main__ - Step 79934: {'lr': 0.00022915281119511153, 'samples': 15347328, 'steps': 79933, 'loss/train': 0.06163060665130615} 08/31/2021 03:42:10 - INFO - __main__ - Step 79935: {'lr': 0.0002291475229383614, 'samples': 15347520, 'steps': 79934, 'loss/train': 2.226768732070923} 08/31/2021 03:42:10 - INFO - __main__ - Step 79936: {'lr': 0.0002291422346910071, 'samples': 15347712, 'steps': 79935, 'loss/train': 1.206886887550354} 08/31/2021 03:42:12 - INFO - __main__ - Step 79937: {'lr': 0.00022913694645305098, 'samples': 15347904, 'steps': 79936, 'loss/train': 2.1182212829589844} 08/31/2021 03:42:12 - INFO - __main__ - Step 79938: {'lr': 0.0002291316582244954, 'samples': 15348096, 'steps': 79937, 'loss/train': 1.0473262071609497} 08/31/2021 03:42:13 - INFO - __main__ - Step 79939: {'lr': 0.0002291263700053428, 'samples': 15348288, 'steps': 79938, 'loss/train': 1.2530001401901245} 08/31/2021 03:42:13 - INFO - __main__ - Step 79940: {'lr': 0.00022912108179559554, 'samples': 15348480, 'steps': 79939, 'loss/train': 0.6022147536277771} 08/31/2021 03:42:13 - INFO - __main__ - Step 79941: {'lr': 0.000229115793595256, 'samples': 15348672, 'steps': 79940, 'loss/train': 1.478481411933899} 08/31/2021 03:42:15 - INFO - __main__ - Step 79942: {'lr': 0.00022911050540432655, 'samples': 15348864, 'steps': 79941, 'loss/train': 1.2882393598556519} 08/31/2021 03:42:15 - INFO - __main__ - Step 79943: {'lr': 0.00022910521722280957, 'samples': 15349056, 'steps': 79942, 'loss/train': 1.111687421798706} 08/31/2021 03:42:16 - INFO - __main__ - Step 79944: {'lr': 0.00022909992905070754, 'samples': 15349248, 'steps': 79943, 'loss/train': 1.6065617799758911} 08/31/2021 03:42:16 - INFO - __main__ - Step 79945: {'lr': 0.0002290946408880227, 'samples': 15349440, 'steps': 79944, 'loss/train': 1.7463247776031494} 08/31/2021 03:42:16 - INFO - __main__ - Step 79946: {'lr': 0.00022908935273475747, 'samples': 15349632, 'steps': 79945, 'loss/train': 0.31540927290916443} 08/31/2021 03:42:18 - INFO - __main__ - Step 79947: {'lr': 0.0002290840645909143, 'samples': 15349824, 'steps': 79946, 'loss/train': 1.313410997390747} 08/31/2021 03:42:18 - INFO - __main__ - Step 79948: {'lr': 0.00022907877645649555, 'samples': 15350016, 'steps': 79947, 'loss/train': 1.2958978414535522} 08/31/2021 03:42:19 - INFO - __main__ - Step 79949: {'lr': 0.0002290734883315035, 'samples': 15350208, 'steps': 79948, 'loss/train': 0.39872047305107117} 08/31/2021 03:42:19 - INFO - __main__ - Step 79950: {'lr': 0.00022906820021594067, 'samples': 15350400, 'steps': 79949, 'loss/train': 1.5176382064819336} 08/31/2021 03:42:19 - INFO - __main__ - Step 79951: {'lr': 0.00022906291210980935, 'samples': 15350592, 'steps': 79950, 'loss/train': 1.238612413406372} 08/31/2021 03:42:21 - INFO - __main__ - Step 79952: {'lr': 0.00022905762401311197, 'samples': 15350784, 'steps': 79951, 'loss/train': 1.7613825798034668} 08/31/2021 03:42:21 - INFO - __main__ - Step 79953: {'lr': 0.0002290523359258509, 'samples': 15350976, 'steps': 79952, 'loss/train': 1.135054588317871} 08/31/2021 03:42:22 - INFO - __main__ - Step 79954: {'lr': 0.0002290470478480285, 'samples': 15351168, 'steps': 79953, 'loss/train': 0.38203155994415283} 08/31/2021 03:42:22 - INFO - __main__ - Step 79955: {'lr': 0.00022904175977964727, 'samples': 15351360, 'steps': 79954, 'loss/train': 1.6182160377502441} 08/31/2021 03:42:23 - INFO - __main__ - Step 79956: {'lr': 0.00022903647172070943, 'samples': 15351552, 'steps': 79955, 'loss/train': 0.6861154437065125} 08/31/2021 03:42:24 - INFO - __main__ - Step 79957: {'lr': 0.00022903118367121746, 'samples': 15351744, 'steps': 79956, 'loss/train': 1.4117388725280762} 08/31/2021 03:42:25 - INFO - __main__ - Step 79958: {'lr': 0.00022902589563117366, 'samples': 15351936, 'steps': 79957, 'loss/train': 1.540499210357666} 08/31/2021 03:42:25 - INFO - __main__ - Step 79959: {'lr': 0.0002290206076005805, 'samples': 15352128, 'steps': 79958, 'loss/train': 0.7936196327209473} 08/31/2021 03:42:25 - INFO - __main__ - Step 79960: {'lr': 0.00022901531957944033, 'samples': 15352320, 'steps': 79959, 'loss/train': 1.086419939994812} 08/31/2021 03:42:26 - INFO - __main__ - Step 79961: {'lr': 0.00022901003156775558, 'samples': 15352512, 'steps': 79960, 'loss/train': 0.8926386833190918} 08/31/2021 03:42:27 - INFO - __main__ - Step 79962: {'lr': 0.00022900474356552853, 'samples': 15352704, 'steps': 79961, 'loss/train': 0.812897264957428} 08/31/2021 03:42:28 - INFO - __main__ - Step 79963: {'lr': 0.00022899945557276164, 'samples': 15352896, 'steps': 79962, 'loss/train': 0.6121612787246704} 08/31/2021 03:42:28 - INFO - __main__ - Step 79964: {'lr': 0.00022899416758945723, 'samples': 15353088, 'steps': 79963, 'loss/train': 1.366168737411499} 08/31/2021 03:42:29 - INFO - __main__ - Step 79965: {'lr': 0.00022898887961561777, 'samples': 15353280, 'steps': 79964, 'loss/train': 1.0364614725112915} 08/31/2021 03:42:29 - INFO - __main__ - Step 79966: {'lr': 0.00022898359165124561, 'samples': 15353472, 'steps': 79965, 'loss/train': 0.8957567811012268} 08/31/2021 03:42:31 - INFO - __main__ - Step 79967: {'lr': 0.0002289783036963431, 'samples': 15353664, 'steps': 79966, 'loss/train': 0.758935809135437} 08/31/2021 03:42:31 - INFO - __main__ - Step 79968: {'lr': 0.0002289730157509126, 'samples': 15353856, 'steps': 79967, 'loss/train': 1.0584241151809692} 08/31/2021 03:42:31 - INFO - __main__ - Step 79969: {'lr': 0.00022896772781495658, 'samples': 15354048, 'steps': 79968, 'loss/train': 0.6516251564025879} 08/31/2021 03:42:32 - INFO - __main__ - Step 79970: {'lr': 0.00022896243988847738, 'samples': 15354240, 'steps': 79969, 'loss/train': 1.2127509117126465} 08/31/2021 03:42:32 - INFO - __main__ - Step 79971: {'lr': 0.00022895715197147732, 'samples': 15354432, 'steps': 79970, 'loss/train': 1.0209629535675049} 08/31/2021 03:42:32 - INFO - __main__ - Step 79972: {'lr': 0.00022895186406395892, 'samples': 15354624, 'steps': 79971, 'loss/train': 1.646138310432434} 08/31/2021 03:42:34 - INFO - __main__ - Step 79973: {'lr': 0.00022894657616592443, 'samples': 15354816, 'steps': 79972, 'loss/train': 0.900465726852417} 08/31/2021 03:42:34 - INFO - __main__ - Step 79974: {'lr': 0.00022894128827737634, 'samples': 15355008, 'steps': 79973, 'loss/train': 1.7426623106002808} 08/31/2021 03:42:35 - INFO - __main__ - Step 79975: {'lr': 0.00022893600039831694, 'samples': 15355200, 'steps': 79974, 'loss/train': 1.232600212097168} 08/31/2021 03:42:35 - INFO - __main__ - Step 79976: {'lr': 0.00022893071252874872, 'samples': 15355392, 'steps': 79975, 'loss/train': 1.1408661603927612} 08/31/2021 03:42:35 - INFO - __main__ - Step 79977: {'lr': 0.00022892542466867395, 'samples': 15355584, 'steps': 79976, 'loss/train': 1.2674534320831299} 08/31/2021 03:42:37 - INFO - __main__ - Step 79978: {'lr': 0.00022892013681809504, 'samples': 15355776, 'steps': 79977, 'loss/train': 0.9393380284309387} 08/31/2021 03:42:38 - INFO - __main__ - Step 79979: {'lr': 0.00022891484897701438, 'samples': 15355968, 'steps': 79978, 'loss/train': 0.7626662254333496} 08/31/2021 03:42:38 - INFO - __main__ - Step 79980: {'lr': 0.00022890956114543439, 'samples': 15356160, 'steps': 79979, 'loss/train': 1.3367449045181274} 08/31/2021 03:42:39 - INFO - __main__ - Step 79981: {'lr': 0.0002289042733233574, 'samples': 15356352, 'steps': 79980, 'loss/train': 1.107645869255066} 08/31/2021 03:42:39 - INFO - __main__ - Step 79982: {'lr': 0.00022889898551078583, 'samples': 15356544, 'steps': 79981, 'loss/train': 1.608412265777588} 08/31/2021 03:42:40 - INFO - __main__ - Step 79983: {'lr': 0.00022889369770772206, 'samples': 15356736, 'steps': 79982, 'loss/train': 1.172605276107788} 08/31/2021 03:42:41 - INFO - __main__ - Step 79984: {'lr': 0.00022888840991416845, 'samples': 15356928, 'steps': 79983, 'loss/train': 1.2312790155410767} 08/31/2021 03:42:41 - INFO - __main__ - Step 79985: {'lr': 0.00022888312213012742, 'samples': 15357120, 'steps': 79984, 'loss/train': 0.6215598583221436} 08/31/2021 03:42:42 - INFO - __main__ - Step 79986: {'lr': 0.00022887783435560132, 'samples': 15357312, 'steps': 79985, 'loss/train': 1.7381147146224976} 08/31/2021 03:42:42 - INFO - __main__ - Step 79987: {'lr': 0.0002288725465905925, 'samples': 15357504, 'steps': 79986, 'loss/train': 1.1370195150375366} 08/31/2021 03:42:44 - INFO - __main__ - Step 79988: {'lr': 0.00022886725883510353, 'samples': 15357696, 'steps': 79987, 'loss/train': 0.937336266040802} 08/31/2021 03:42:44 - INFO - __main__ - Step 79989: {'lr': 0.00022886197108913656, 'samples': 15357888, 'steps': 79988, 'loss/train': 0.8223235607147217} 08/31/2021 03:42:44 - INFO - __main__ - Step 79990: {'lr': 0.00022885668335269403, 'samples': 15358080, 'steps': 79989, 'loss/train': 0.7501317262649536} 08/31/2021 03:42:45 - INFO - __main__ - Step 79991: {'lr': 0.00022885139562577836, 'samples': 15358272, 'steps': 79990, 'loss/train': 1.045769214630127} 08/31/2021 03:42:45 - INFO - __main__ - Step 79992: {'lr': 0.0002288461079083919, 'samples': 15358464, 'steps': 79991, 'loss/train': 1.5394343137741089} 08/31/2021 03:42:46 - INFO - __main__ - Step 79993: {'lr': 0.00022884082020053708, 'samples': 15358656, 'steps': 79992, 'loss/train': 1.1535956859588623} 08/31/2021 03:42:47 - INFO - __main__ - Step 79994: {'lr': 0.00022883553250221627, 'samples': 15358848, 'steps': 79993, 'loss/train': 1.3435124158859253} 08/31/2021 03:42:47 - INFO - __main__ - Step 79995: {'lr': 0.00022883024481343183, 'samples': 15359040, 'steps': 79994, 'loss/train': 0.748015284538269} 08/31/2021 03:42:48 - INFO - __main__ - Step 79996: {'lr': 0.00022882495713418617, 'samples': 15359232, 'steps': 79995, 'loss/train': 1.6793628931045532} 08/31/2021 03:42:48 - INFO - __main__ - Step 79997: {'lr': 0.00022881966946448166, 'samples': 15359424, 'steps': 79996, 'loss/train': 1.561985731124878} 08/31/2021 03:42:49 - INFO - __main__ - Step 79998: {'lr': 0.00022881438180432064, 'samples': 15359616, 'steps': 79997, 'loss/train': 1.392444372177124} 08/31/2021 03:42:50 - INFO - __main__ - Step 79999: {'lr': 0.00022880909415370557, 'samples': 15359808, 'steps': 79998, 'loss/train': 0.6656218767166138} 08/31/2021 03:42:50 - INFO - __main__ - Step 80000: {'lr': 0.0002288038065126388, 'samples': 15360000, 'steps': 79999, 'loss/train': 1.7288322448730469} 08/31/2021 03:42:51 - INFO - __main__ - Step 80001: {'lr': 0.0002287985188811228, 'samples': 15360192, 'steps': 80000, 'loss/train': 0.9007559418678284} 08/31/2021 03:42:51 - INFO - __main__ - Step 80002: {'lr': 0.00022879323125915975, 'samples': 15360384, 'steps': 80001, 'loss/train': 0.7698410153388977} 08/31/2021 03:42:53 - INFO - __main__ - Step 80003: {'lr': 0.00022878794364675212, 'samples': 15360576, 'steps': 80002, 'loss/train': 1.0169118642807007} 08/31/2021 03:42:53 - INFO - __main__ - Step 80004: {'lr': 0.00022878265604390236, 'samples': 15360768, 'steps': 80003, 'loss/train': 1.6807425022125244} 08/31/2021 03:42:53 - INFO - __main__ - Step 80005: {'lr': 0.0002287773684506128, 'samples': 15360960, 'steps': 80004, 'loss/train': 1.611419916152954} 08/31/2021 03:42:54 - INFO - __main__ - Step 80006: {'lr': 0.0002287720808668858, 'samples': 15361152, 'steps': 80005, 'loss/train': 0.4751485586166382} 08/31/2021 03:42:54 - INFO - __main__ - Step 80007: {'lr': 0.00022876679329272379, 'samples': 15361344, 'steps': 80006, 'loss/train': 0.3064573407173157} 08/31/2021 03:42:56 - INFO - __main__ - Step 80008: {'lr': 0.00022876150572812912, 'samples': 15361536, 'steps': 80007, 'loss/train': 0.6581714749336243} 08/31/2021 03:42:56 - INFO - __main__ - Step 80009: {'lr': 0.00022875621817310422, 'samples': 15361728, 'steps': 80008, 'loss/train': 1.7625212669372559} 08/31/2021 03:42:56 - INFO - __main__ - Step 80010: {'lr': 0.00022875093062765141, 'samples': 15361920, 'steps': 80009, 'loss/train': 1.7485982179641724} 08/31/2021 03:42:57 - INFO - __main__ - Step 80011: {'lr': 0.00022874564309177312, 'samples': 15362112, 'steps': 80010, 'loss/train': 0.49641138315200806} 08/31/2021 03:42:57 - INFO - __main__ - Step 80012: {'lr': 0.00022874035556547171, 'samples': 15362304, 'steps': 80011, 'loss/train': 0.8272839188575745} 08/31/2021 03:42:57 - INFO - __main__ - Step 80013: {'lr': 0.0002287350680487496, 'samples': 15362496, 'steps': 80012, 'loss/train': 1.2980270385742188} 08/31/2021 03:42:59 - INFO - __main__ - Step 80014: {'lr': 0.0002287297805416091, 'samples': 15362688, 'steps': 80013, 'loss/train': 1.0676047801971436} 08/31/2021 03:42:59 - INFO - __main__ - Step 80015: {'lr': 0.00022872449304405274, 'samples': 15362880, 'steps': 80014, 'loss/train': 0.21083207428455353} 08/31/2021 03:43:00 - INFO - __main__ - Step 80016: {'lr': 0.00022871920555608268, 'samples': 15363072, 'steps': 80015, 'loss/train': 0.9569677114486694} 08/31/2021 03:43:00 - INFO - __main__ - Step 80017: {'lr': 0.00022871391807770144, 'samples': 15363264, 'steps': 80016, 'loss/train': 1.1345332860946655} 08/31/2021 03:43:00 - INFO - __main__ - Step 80018: {'lr': 0.00022870863060891138, 'samples': 15363456, 'steps': 80017, 'loss/train': 0.5410911440849304} 08/31/2021 03:43:02 - INFO - __main__ - Step 80019: {'lr': 0.00022870334314971488, 'samples': 15363648, 'steps': 80018, 'loss/train': 1.6744508743286133} 08/31/2021 03:43:03 - INFO - __main__ - Step 80020: {'lr': 0.0002286980557001143, 'samples': 15363840, 'steps': 80019, 'loss/train': 0.11152894794940948} 08/31/2021 03:43:03 - INFO - __main__ - Step 80021: {'lr': 0.0002286927682601121, 'samples': 15364032, 'steps': 80020, 'loss/train': 0.036716461181640625} 08/31/2021 03:43:03 - INFO - __main__ - Step 80022: {'lr': 0.0002286874808297106, 'samples': 15364224, 'steps': 80021, 'loss/train': 0.028586650267243385} 08/31/2021 03:43:04 - INFO - __main__ - Step 80023: {'lr': 0.00022868219340891214, 'samples': 15364416, 'steps': 80022, 'loss/train': 1.118735432624817} 08/31/2021 03:43:04 - INFO - __main__ - Step 80024: {'lr': 0.0002286769059977192, 'samples': 15364608, 'steps': 80023, 'loss/train': 1.620357871055603} 08/31/2021 03:43:06 - INFO - __main__ - Step 80025: {'lr': 0.00022867161859613412, 'samples': 15364800, 'steps': 80024, 'loss/train': 0.4290686249732971} 08/31/2021 03:43:06 - INFO - __main__ - Step 80026: {'lr': 0.00022866633120415924, 'samples': 15364992, 'steps': 80025, 'loss/train': 0.8267152905464172} 08/31/2021 03:43:06 - INFO - __main__ - Step 80027: {'lr': 0.000228661043821797, 'samples': 15365184, 'steps': 80026, 'loss/train': 1.7176601886749268} 08/31/2021 03:43:07 - INFO - __main__ - Step 80028: {'lr': 0.0002286557564490499, 'samples': 15365376, 'steps': 80027, 'loss/train': 1.820753812789917} 08/31/2021 03:43:07 - INFO - __main__ - Step 80029: {'lr': 0.00022865046908592004, 'samples': 15365568, 'steps': 80028, 'loss/train': 1.5358163118362427} 08/31/2021 03:43:09 - INFO - __main__ - Step 80030: {'lr': 0.00022864518173240997, 'samples': 15365760, 'steps': 80029, 'loss/train': 1.0254465341567993} 08/31/2021 03:43:09 - INFO - __main__ - Step 80031: {'lr': 0.00022863989438852206, 'samples': 15365952, 'steps': 80030, 'loss/train': 0.9248579144477844} 08/31/2021 03:43:10 - INFO - __main__ - Step 80032: {'lr': 0.00022863460705425866, 'samples': 15366144, 'steps': 80031, 'loss/train': 1.3788015842437744} 08/31/2021 03:43:10 - INFO - __main__ - Step 80033: {'lr': 0.0002286293197296222, 'samples': 15366336, 'steps': 80032, 'loss/train': 1.3678358793258667} 08/31/2021 03:43:10 - INFO - __main__ - Step 80034: {'lr': 0.00022862403241461502, 'samples': 15366528, 'steps': 80033, 'loss/train': 1.1784483194351196} 08/31/2021 03:43:11 - INFO - __main__ - Step 80035: {'lr': 0.0002286187451092395, 'samples': 15366720, 'steps': 80034, 'loss/train': 0.6929771900177002} 08/31/2021 03:43:13 - INFO - __main__ - Step 80036: {'lr': 0.0002286134578134981, 'samples': 15366912, 'steps': 80035, 'loss/train': 1.4115474224090576} 08/31/2021 03:43:13 - INFO - __main__ - Step 80037: {'lr': 0.00022860817052739311, 'samples': 15367104, 'steps': 80036, 'loss/train': 0.862578272819519} 08/31/2021 03:43:13 - INFO - __main__ - Step 80038: {'lr': 0.00022860288325092696, 'samples': 15367296, 'steps': 80037, 'loss/train': 0.9103729724884033} 08/31/2021 03:43:14 - INFO - __main__ - Step 80039: {'lr': 0.000228597595984102, 'samples': 15367488, 'steps': 80038, 'loss/train': 0.9456850290298462} 08/31/2021 03:43:14 - INFO - __main__ - Step 80040: {'lr': 0.00022859230872692067, 'samples': 15367680, 'steps': 80039, 'loss/train': 1.249003529548645} 08/31/2021 03:43:16 - INFO - __main__ - Step 80041: {'lr': 0.00022858702147938529, 'samples': 15367872, 'steps': 80040, 'loss/train': 1.1650587320327759} 08/31/2021 03:43:16 - INFO - __main__ - Step 80042: {'lr': 0.00022858173424149836, 'samples': 15368064, 'steps': 80041, 'loss/train': 1.0046780109405518} 08/31/2021 03:43:16 - INFO - __main__ - Step 80043: {'lr': 0.0002285764470132621, 'samples': 15368256, 'steps': 80042, 'loss/train': 1.3230364322662354} 08/31/2021 03:43:17 - INFO - __main__ - Step 80044: {'lr': 0.00022857115979467893, 'samples': 15368448, 'steps': 80043, 'loss/train': 0.8059895038604736} 08/31/2021 03:43:17 - INFO - __main__ - Step 80045: {'lr': 0.00022856587258575129, 'samples': 15368640, 'steps': 80044, 'loss/train': 1.2109993696212769} 08/31/2021 03:43:19 - INFO - __main__ - Step 80046: {'lr': 0.00022856058538648152, 'samples': 15368832, 'steps': 80045, 'loss/train': 1.2989550828933716} 08/31/2021 03:43:20 - INFO - __main__ - Step 80047: {'lr': 0.00022855529819687203, 'samples': 15369024, 'steps': 80046, 'loss/train': 2.6702492237091064} 08/31/2021 03:43:20 - INFO - __main__ - Step 80048: {'lr': 0.0002285500110169252, 'samples': 15369216, 'steps': 80047, 'loss/train': 1.383201003074646} 08/31/2021 03:43:20 - INFO - __main__ - Step 80049: {'lr': 0.00022854472384664336, 'samples': 15369408, 'steps': 80048, 'loss/train': 1.6330410242080688} 08/31/2021 03:43:21 - INFO - __main__ - Step 80050: {'lr': 0.00022853943668602901, 'samples': 15369600, 'steps': 80049, 'loss/train': 1.790152668952942} 08/31/2021 03:43:21 - INFO - __main__ - Step 80051: {'lr': 0.0002285341495350844, 'samples': 15369792, 'steps': 80050, 'loss/train': 0.3487027883529663} 08/31/2021 03:43:22 - INFO - __main__ - Step 80052: {'lr': 0.000228528862393812, 'samples': 15369984, 'steps': 80051, 'loss/train': 1.188159704208374} 08/31/2021 03:43:23 - INFO - __main__ - Step 80053: {'lr': 0.00022852357526221412, 'samples': 15370176, 'steps': 80052, 'loss/train': 0.15525208413600922} 08/31/2021 03:43:23 - INFO - __main__ - Step 80054: {'lr': 0.00022851828814029324, 'samples': 15370368, 'steps': 80053, 'loss/train': 1.3791621923446655} 08/31/2021 03:43:24 - INFO - __main__ - Step 80055: {'lr': 0.00022851300102805176, 'samples': 15370560, 'steps': 80054, 'loss/train': 0.6875711679458618} 08/31/2021 03:43:24 - INFO - __main__ - Step 80056: {'lr': 0.0002285077139254919, 'samples': 15370752, 'steps': 80055, 'loss/train': 0.7201364636421204} 08/31/2021 03:43:25 - INFO - __main__ - Step 80057: {'lr': 0.00022850242683261613, 'samples': 15370944, 'steps': 80056, 'loss/train': 1.3000762462615967} 08/31/2021 03:43:26 - INFO - __main__ - Step 80058: {'lr': 0.00022849713974942682, 'samples': 15371136, 'steps': 80057, 'loss/train': 1.5047987699508667} 08/31/2021 03:43:26 - INFO - __main__ - Step 80059: {'lr': 0.00022849185267592636, 'samples': 15371328, 'steps': 80058, 'loss/train': 1.7061913013458252} 08/31/2021 03:43:27 - INFO - __main__ - Step 80060: {'lr': 0.00022848656561211717, 'samples': 15371520, 'steps': 80059, 'loss/train': 0.5807170867919922} 08/31/2021 03:43:27 - INFO - __main__ - Step 80061: {'lr': 0.0002284812785580016, 'samples': 15371712, 'steps': 80060, 'loss/train': 0.9121744632720947} 08/31/2021 03:43:29 - INFO - __main__ - Step 80062: {'lr': 0.00022847599151358202, 'samples': 15371904, 'steps': 80061, 'loss/train': 2.158994197845459} 08/31/2021 03:43:29 - INFO - __main__ - Step 80063: {'lr': 0.00022847070447886084, 'samples': 15372096, 'steps': 80062, 'loss/train': 1.173319697380066} 08/31/2021 03:43:30 - INFO - __main__ - Step 80064: {'lr': 0.00022846541745384042, 'samples': 15372288, 'steps': 80063, 'loss/train': 1.5400471687316895} 08/31/2021 03:43:30 - INFO - __main__ - Step 80065: {'lr': 0.00022846013043852315, 'samples': 15372480, 'steps': 80064, 'loss/train': 0.4207642078399658} 08/31/2021 03:43:30 - INFO - __main__ - Step 80066: {'lr': 0.0002284548434329114, 'samples': 15372672, 'steps': 80065, 'loss/train': 0.6159775853157043} 08/31/2021 03:43:31 - INFO - __main__ - Step 80067: {'lr': 0.00022844955643700762, 'samples': 15372864, 'steps': 80066, 'loss/train': 0.020833980292081833} 08/31/2021 03:43:33 - INFO - __main__ - Step 80068: {'lr': 0.0002284442694508141, 'samples': 15373056, 'steps': 80067, 'loss/train': 1.1519155502319336} 08/31/2021 03:43:33 - INFO - __main__ - Step 80069: {'lr': 0.0002284389824743333, 'samples': 15373248, 'steps': 80068, 'loss/train': 1.0980045795440674} 08/31/2021 03:43:34 - INFO - __main__ - Step 80070: {'lr': 0.00022843369550756755, 'samples': 15373440, 'steps': 80069, 'loss/train': 1.275305151939392} 08/31/2021 03:43:34 - INFO - __main__ - Step 80071: {'lr': 0.00022842840855051918, 'samples': 15373632, 'steps': 80070, 'loss/train': 0.031669531017541885} 08/31/2021 03:43:34 - INFO - __main__ - Step 80072: {'lr': 0.00022842312160319068, 'samples': 15373824, 'steps': 80071, 'loss/train': 0.1198766678571701} 08/31/2021 03:43:35 - INFO - __main__ - Step 80073: {'lr': 0.00022841783466558436, 'samples': 15374016, 'steps': 80072, 'loss/train': 1.2406343221664429} 08/31/2021 03:43:37 - INFO - __main__ - Step 80074: {'lr': 0.00022841254773770265, 'samples': 15374208, 'steps': 80073, 'loss/train': 1.074462890625} 08/31/2021 03:43:37 - INFO - __main__ - Step 80075: {'lr': 0.0002284072608195479, 'samples': 15374400, 'steps': 80074, 'loss/train': 1.0638320446014404} 08/31/2021 03:43:38 - INFO - __main__ - Step 80076: {'lr': 0.00022840197391112252, 'samples': 15374592, 'steps': 80075, 'loss/train': 1.0872855186462402} 08/31/2021 03:43:38 - INFO - __main__ - Step 80077: {'lr': 0.0002283966870124289, 'samples': 15374784, 'steps': 80076, 'loss/train': 1.5573147535324097} 08/31/2021 03:43:38 - INFO - __main__ - Step 80078: {'lr': 0.0002283914001234694, 'samples': 15374976, 'steps': 80077, 'loss/train': 1.3883970975875854} 08/31/2021 03:43:39 - INFO - __main__ - Step 80079: {'lr': 0.00022838611324424636, 'samples': 15375168, 'steps': 80078, 'loss/train': 1.6209524869918823} 08/31/2021 03:43:40 - INFO - __main__ - Step 80080: {'lr': 0.00022838082637476222, 'samples': 15375360, 'steps': 80079, 'loss/train': 0.1608150601387024} 08/31/2021 03:43:41 - INFO - __main__ - Step 80081: {'lr': 0.00022837553951501934, 'samples': 15375552, 'steps': 80080, 'loss/train': 1.3881982564926147} 08/31/2021 03:43:41 - INFO - __main__ - Step 80082: {'lr': 0.00022837025266502016, 'samples': 15375744, 'steps': 80081, 'loss/train': 1.017437219619751} 08/31/2021 03:43:41 - INFO - __main__ - Step 80083: {'lr': 0.00022836496582476695, 'samples': 15375936, 'steps': 80082, 'loss/train': 1.18096125125885} 08/31/2021 03:43:42 - INFO - __main__ - Step 80084: {'lr': 0.00022835967899426218, 'samples': 15376128, 'steps': 80083, 'loss/train': 1.4588637351989746} 08/31/2021 03:43:43 - INFO - __main__ - Step 80085: {'lr': 0.00022835439217350816, 'samples': 15376320, 'steps': 80084, 'loss/train': 1.2138856649398804} 08/31/2021 03:43:44 - INFO - __main__ - Step 80086: {'lr': 0.00022834910536250735, 'samples': 15376512, 'steps': 80085, 'loss/train': 1.4079890251159668} 08/31/2021 03:43:44 - INFO - __main__ - Step 80087: {'lr': 0.0002283438185612621, 'samples': 15376704, 'steps': 80086, 'loss/train': 0.7824492454528809} 08/31/2021 03:43:44 - INFO - __main__ - Step 80088: {'lr': 0.00022833853176977477, 'samples': 15376896, 'steps': 80087, 'loss/train': 0.865244448184967} 08/31/2021 03:43:45 - INFO - __main__ - Step 80089: {'lr': 0.00022833324498804786, 'samples': 15377088, 'steps': 80088, 'loss/train': 1.2170544862747192} 08/31/2021 03:43:45 - INFO - __main__ - Step 80090: {'lr': 0.00022832795821608356, 'samples': 15377280, 'steps': 80089, 'loss/train': 1.161892056465149} 08/31/2021 03:43:47 - INFO - __main__ - Step 80091: {'lr': 0.00022832267145388437, 'samples': 15377472, 'steps': 80090, 'loss/train': 1.2218527793884277} 08/31/2021 03:43:48 - INFO - __main__ - Step 80092: {'lr': 0.00022831738470145262, 'samples': 15377664, 'steps': 80091, 'loss/train': 0.19427022337913513} 08/31/2021 03:43:48 - INFO - __main__ - Step 80093: {'lr': 0.00022831209795879076, 'samples': 15377856, 'steps': 80092, 'loss/train': 1.0397837162017822} 08/31/2021 03:43:48 - INFO - __main__ - Step 80094: {'lr': 0.0002283068112259011, 'samples': 15378048, 'steps': 80093, 'loss/train': 0.8531360030174255} 08/31/2021 03:43:49 - INFO - __main__ - Step 80095: {'lr': 0.00022830152450278613, 'samples': 15378240, 'steps': 80094, 'loss/train': 4.4939985275268555} 08/31/2021 03:43:50 - INFO - __main__ - Step 80096: {'lr': 0.0002282962377894481, 'samples': 15378432, 'steps': 80095, 'loss/train': 0.743789792060852} 08/31/2021 03:43:51 - INFO - __main__ - Step 80097: {'lr': 0.00022829095108588946, 'samples': 15378624, 'steps': 80096, 'loss/train': 4.525557041168213} 08/31/2021 03:43:51 - INFO - __main__ - Step 80098: {'lr': 0.00022828566439211256, 'samples': 15378816, 'steps': 80097, 'loss/train': 1.1377555131912231} 08/31/2021 03:43:51 - INFO - __main__ - Step 80099: {'lr': 0.00022828037770811983, 'samples': 15379008, 'steps': 80098, 'loss/train': 1.309487223625183} 08/31/2021 03:43:52 - INFO - __main__ - Step 80100: {'lr': 0.00022827509103391368, 'samples': 15379200, 'steps': 80099, 'loss/train': 1.4695417881011963} 08/31/2021 03:43:53 - INFO - __main__ - Step 80101: {'lr': 0.00022826980436949635, 'samples': 15379392, 'steps': 80100, 'loss/train': 1.3014699220657349} 08/31/2021 03:43:54 - INFO - __main__ - Step 80102: {'lr': 0.00022826451771487035, 'samples': 15379584, 'steps': 80101, 'loss/train': 0.5388835668563843} 08/31/2021 03:43:54 - INFO - __main__ - Step 80103: {'lr': 0.000228259231070038, 'samples': 15379776, 'steps': 80102, 'loss/train': 1.1935756206512451} 08/31/2021 03:43:54 - INFO - __main__ - Step 80104: {'lr': 0.0002282539444350017, 'samples': 15379968, 'steps': 80103, 'loss/train': 0.6384830474853516} 08/31/2021 03:43:55 - INFO - __main__ - Step 80105: {'lr': 0.00022824865780976387, 'samples': 15380160, 'steps': 80104, 'loss/train': 1.2765065431594849} 08/31/2021 03:43:55 - INFO - __main__ - Step 80106: {'lr': 0.0002282433711943268, 'samples': 15380352, 'steps': 80105, 'loss/train': 0.7432762980461121} 08/31/2021 03:43:57 - INFO - __main__ - Step 80107: {'lr': 0.000228238084588693, 'samples': 15380544, 'steps': 80106, 'loss/train': 1.1062017679214478} 08/31/2021 03:43:57 - INFO - __main__ - Step 80108: {'lr': 0.00022823279799286472, 'samples': 15380736, 'steps': 80107, 'loss/train': 1.3662638664245605} 08/31/2021 03:43:58 - INFO - __main__ - Step 80109: {'lr': 0.0002282275114068445, 'samples': 15380928, 'steps': 80108, 'loss/train': 0.9005221128463745} 08/31/2021 03:43:58 - INFO - __main__ - Step 80110: {'lr': 0.00022822222483063456, 'samples': 15381120, 'steps': 80109, 'loss/train': 1.0328853130340576} 08/31/2021 03:43:58 - INFO - __main__ - Step 80111: {'lr': 0.00022821693826423743, 'samples': 15381312, 'steps': 80110, 'loss/train': 1.5647817850112915} 08/31/2021 03:44:00 - INFO - __main__ - Step 80112: {'lr': 0.00022821165170765534, 'samples': 15381504, 'steps': 80111, 'loss/train': 0.3165013790130615} 08/31/2021 03:44:00 - INFO - __main__ - Step 80113: {'lr': 0.00022820636516089073, 'samples': 15381696, 'steps': 80112, 'loss/train': 1.3904495239257812} 08/31/2021 03:44:00 - INFO - __main__ - Step 80114: {'lr': 0.000228201078623946, 'samples': 15381888, 'steps': 80113, 'loss/train': 1.077306866645813} 08/31/2021 03:44:01 - INFO - __main__ - Step 80115: {'lr': 0.00022819579209682354, 'samples': 15382080, 'steps': 80114, 'loss/train': 1.284176230430603} 08/31/2021 03:44:01 - INFO - __main__ - Step 80116: {'lr': 0.0002281905055795257, 'samples': 15382272, 'steps': 80115, 'loss/train': 1.1757237911224365} 08/31/2021 03:44:03 - INFO - __main__ - Step 80117: {'lr': 0.00022818521907205493, 'samples': 15382464, 'steps': 80116, 'loss/train': 1.4905619621276855} 08/31/2021 03:44:03 - INFO - __main__ - Step 80118: {'lr': 0.00022817993257441348, 'samples': 15382656, 'steps': 80117, 'loss/train': 1.4799995422363281} 08/31/2021 03:44:03 - INFO - __main__ - Step 80119: {'lr': 0.00022817464608660388, 'samples': 15382848, 'steps': 80118, 'loss/train': 1.2174744606018066} 08/31/2021 03:44:04 - INFO - __main__ - Step 80120: {'lr': 0.00022816935960862846, 'samples': 15383040, 'steps': 80119, 'loss/train': 1.1378357410430908} 08/31/2021 03:44:04 - INFO - __main__ - Step 80121: {'lr': 0.00022816407314048953, 'samples': 15383232, 'steps': 80120, 'loss/train': 0.9370712041854858} 08/31/2021 03:44:06 - INFO - __main__ - Step 80122: {'lr': 0.00022815878668218967, 'samples': 15383424, 'steps': 80121, 'loss/train': 1.1112526655197144} 08/31/2021 03:44:06 - INFO - __main__ - Step 80123: {'lr': 0.00022815350023373102, 'samples': 15383616, 'steps': 80122, 'loss/train': 1.6859166622161865} 08/31/2021 03:44:07 - INFO - __main__ - Step 80124: {'lr': 0.0002281482137951161, 'samples': 15383808, 'steps': 80123, 'loss/train': 0.9284272789955139} 08/31/2021 03:44:07 - INFO - __main__ - Step 80125: {'lr': 0.00022814292736634718, 'samples': 15384000, 'steps': 80124, 'loss/train': 1.000235676765442} 08/31/2021 03:44:07 - INFO - __main__ - Step 80126: {'lr': 0.00022813764094742675, 'samples': 15384192, 'steps': 80125, 'loss/train': 1.5978765487670898} 08/31/2021 03:44:08 - INFO - __main__ - Step 80127: {'lr': 0.00022813235453835717, 'samples': 15384384, 'steps': 80126, 'loss/train': 1.3436212539672852} 08/31/2021 03:44:09 - INFO - __main__ - Step 80128: {'lr': 0.00022812706813914082, 'samples': 15384576, 'steps': 80127, 'loss/train': 0.24042144417762756} 08/31/2021 03:44:09 - INFO - __main__ - Step 80129: {'lr': 0.00022812178174978008, 'samples': 15384768, 'steps': 80128, 'loss/train': 1.6857428550720215} 08/31/2021 03:44:10 - INFO - __main__ - Step 80130: {'lr': 0.00022811649537027732, 'samples': 15384960, 'steps': 80129, 'loss/train': 0.8521960973739624} 08/31/2021 03:44:10 - INFO - __main__ - Step 80131: {'lr': 0.0002281112090006349, 'samples': 15385152, 'steps': 80130, 'loss/train': 1.228993535041809} 08/31/2021 03:44:11 - INFO - __main__ - Step 80132: {'lr': 0.00022810592264085528, 'samples': 15385344, 'steps': 80131, 'loss/train': 1.6545076370239258} 08/31/2021 03:44:12 - INFO - __main__ - Step 80133: {'lr': 0.00022810063629094077, 'samples': 15385536, 'steps': 80132, 'loss/train': 1.2294100522994995} 08/31/2021 03:44:13 - INFO - __main__ - Step 80134: {'lr': 0.00022809534995089377, 'samples': 15385728, 'steps': 80133, 'loss/train': 1.3137357234954834} 08/31/2021 03:44:13 - INFO - __main__ - Step 80135: {'lr': 0.00022809006362071668, 'samples': 15385920, 'steps': 80134, 'loss/train': 0.10841649770736694} 08/31/2021 03:44:14 - INFO - __main__ - Step 80136: {'lr': 0.00022808477730041198, 'samples': 15386112, 'steps': 80135, 'loss/train': 1.1696031093597412} 08/31/2021 03:44:14 - INFO - __main__ - Step 80137: {'lr': 0.0002280794909899818, 'samples': 15386304, 'steps': 80136, 'loss/train': 1.4459129571914673} 08/31/2021 03:44:15 - INFO - __main__ - Step 80138: {'lr': 0.00022807420468942872, 'samples': 15386496, 'steps': 80137, 'loss/train': 0.7686716914176941} 08/31/2021 03:44:16 - INFO - __main__ - Step 80139: {'lr': 0.00022806891839875502, 'samples': 15386688, 'steps': 80138, 'loss/train': 1.0970441102981567} 08/31/2021 03:44:16 - INFO - __main__ - Step 80140: {'lr': 0.00022806363211796314, 'samples': 15386880, 'steps': 80139, 'loss/train': 1.5548399686813354} 08/31/2021 03:44:16 - INFO - __main__ - Step 80141: {'lr': 0.00022805834584705545, 'samples': 15387072, 'steps': 80140, 'loss/train': 1.045656681060791} 08/31/2021 03:44:17 - INFO - __main__ - Step 80142: {'lr': 0.00022805305958603433, 'samples': 15387264, 'steps': 80141, 'loss/train': 1.3552801609039307} 08/31/2021 03:44:20 - INFO - __main__ - Step 80143: {'lr': 0.00022804777333490216, 'samples': 15387456, 'steps': 80142, 'loss/train': 1.3466781377792358} 08/31/2021 03:44:20 - INFO - __main__ - Step 80144: {'lr': 0.00022804248709366133, 'samples': 15387648, 'steps': 80143, 'loss/train': 1.0625627040863037} 08/31/2021 03:44:20 - INFO - __main__ - Step 80145: {'lr': 0.00022803720086231422, 'samples': 15387840, 'steps': 80144, 'loss/train': 1.509642481803894} 08/31/2021 03:44:21 - INFO - __main__ - Step 80146: {'lr': 0.0002280319146408632, 'samples': 15388032, 'steps': 80145, 'loss/train': 0.5735557079315186} 08/31/2021 03:44:21 - INFO - __main__ - Step 80147: {'lr': 0.00022802662842931067, 'samples': 15388224, 'steps': 80146, 'loss/train': 0.6607548594474792} 08/31/2021 03:44:21 - INFO - __main__ - Step 80148: {'lr': 0.00022802134222765896, 'samples': 15388416, 'steps': 80147, 'loss/train': 1.0251188278198242} 08/31/2021 03:44:22 - INFO - __main__ - Step 80149: {'lr': 0.00022801605603591066, 'samples': 15388608, 'steps': 80148, 'loss/train': 0.021366078406572342} 08/31/2021 03:44:23 - INFO - __main__ - Step 80150: {'lr': 0.00022801076985406784, 'samples': 15388800, 'steps': 80149, 'loss/train': 0.04997524246573448} 08/31/2021 03:44:24 - INFO - __main__ - Step 80151: {'lr': 0.00022800548368213307, 'samples': 15388992, 'steps': 80150, 'loss/train': 1.6720455884933472} 08/31/2021 03:44:24 - INFO - __main__ - Step 80152: {'lr': 0.00022800019752010865, 'samples': 15389184, 'steps': 80151, 'loss/train': 1.3186780214309692} 08/31/2021 03:44:24 - INFO - __main__ - Step 80153: {'lr': 0.000227994911367997, 'samples': 15389376, 'steps': 80152, 'loss/train': 0.9342797994613647} 08/31/2021 03:44:25 - INFO - __main__ - Step 80154: {'lr': 0.00022798962522580052, 'samples': 15389568, 'steps': 80153, 'loss/train': 1.275658130645752} 08/31/2021 03:44:25 - INFO - __main__ - Step 80155: {'lr': 0.00022798433909352158, 'samples': 15389760, 'steps': 80154, 'loss/train': 1.0234076976776123} 08/31/2021 03:44:27 - INFO - __main__ - Step 80156: {'lr': 0.00022797905297116254, 'samples': 15389952, 'steps': 80155, 'loss/train': 1.2994493246078491} 08/31/2021 03:44:27 - INFO - __main__ - Step 80157: {'lr': 0.00022797376685872582, 'samples': 15390144, 'steps': 80156, 'loss/train': 0.06086983159184456} 08/31/2021 03:44:28 - INFO - __main__ - Step 80158: {'lr': 0.00022796848075621375, 'samples': 15390336, 'steps': 80157, 'loss/train': 0.35084280371665955} 08/31/2021 03:44:28 - INFO - __main__ - Step 80159: {'lr': 0.00022796319466362875, 'samples': 15390528, 'steps': 80158, 'loss/train': 1.1756854057312012} 08/31/2021 03:44:28 - INFO - __main__ - Step 80160: {'lr': 0.0002279579085809732, 'samples': 15390720, 'steps': 80159, 'loss/train': 0.5495242476463318} 08/31/2021 03:44:30 - INFO - __main__ - Step 80161: {'lr': 0.0002279526225082495, 'samples': 15390912, 'steps': 80160, 'loss/train': 1.4922981262207031} 08/31/2021 03:44:30 - INFO - __main__ - Step 80162: {'lr': 0.00022794733644545997, 'samples': 15391104, 'steps': 80161, 'loss/train': 1.7770060300827026} 08/31/2021 03:44:31 - INFO - __main__ - Step 80163: {'lr': 0.00022794205039260718, 'samples': 15391296, 'steps': 80162, 'loss/train': 0.8814936876296997} 08/31/2021 03:44:31 - INFO - __main__ - Step 80164: {'lr': 0.00022793676434969325, 'samples': 15391488, 'steps': 80163, 'loss/train': 0.8790743350982666} 08/31/2021 03:44:31 - INFO - __main__ - Step 80165: {'lr': 0.00022793147831672063, 'samples': 15391680, 'steps': 80164, 'loss/train': 1.297476053237915} 08/31/2021 03:44:33 - INFO - __main__ - Step 80166: {'lr': 0.00022792619229369178, 'samples': 15391872, 'steps': 80165, 'loss/train': 0.552851140499115} 08/31/2021 03:44:33 - INFO - __main__ - Step 80167: {'lr': 0.00022792090628060902, 'samples': 15392064, 'steps': 80166, 'loss/train': 1.7946120500564575} 08/31/2021 03:44:34 - INFO - __main__ - Step 80168: {'lr': 0.00022791562027747478, 'samples': 15392256, 'steps': 80167, 'loss/train': 1.0870532989501953} 08/31/2021 03:44:34 - INFO - __main__ - Step 80169: {'lr': 0.00022791033428429141, 'samples': 15392448, 'steps': 80168, 'loss/train': 1.4035204648971558} 08/31/2021 03:44:34 - INFO - __main__ - Step 80170: {'lr': 0.00022790504830106132, 'samples': 15392640, 'steps': 80169, 'loss/train': 1.2950115203857422} 08/31/2021 03:44:36 - INFO - __main__ - Step 80171: {'lr': 0.00022789976232778686, 'samples': 15392832, 'steps': 80170, 'loss/train': 0.13802070915699005} 08/31/2021 03:44:36 - INFO - __main__ - Step 80172: {'lr': 0.00022789447636447044, 'samples': 15393024, 'steps': 80171, 'loss/train': 1.1876940727233887} 08/31/2021 03:44:37 - INFO - __main__ - Step 80173: {'lr': 0.00022788919041111442, 'samples': 15393216, 'steps': 80172, 'loss/train': 1.6317368745803833} 08/31/2021 03:44:37 - INFO - __main__ - Step 80174: {'lr': 0.00022788390446772116, 'samples': 15393408, 'steps': 80173, 'loss/train': 0.22042213380336761} 08/31/2021 03:44:37 - INFO - __main__ - Step 80175: {'lr': 0.0002278786185342931, 'samples': 15393600, 'steps': 80174, 'loss/train': 0.8346107602119446} 08/31/2021 03:44:39 - INFO - __main__ - Step 80176: {'lr': 0.0002278733326108327, 'samples': 15393792, 'steps': 80175, 'loss/train': 1.166884183883667} 08/31/2021 03:44:39 - INFO - __main__ - Step 80177: {'lr': 0.00022786804669734214, 'samples': 15393984, 'steps': 80176, 'loss/train': 0.7371644973754883} 08/31/2021 03:44:40 - INFO - __main__ - Step 80178: {'lr': 0.0002278627607938239, 'samples': 15394176, 'steps': 80177, 'loss/train': 1.1727732419967651} 08/31/2021 03:44:40 - INFO - __main__ - Step 80179: {'lr': 0.00022785747490028033, 'samples': 15394368, 'steps': 80178, 'loss/train': 0.9104415774345398} 08/31/2021 03:44:40 - INFO - __main__ - Step 80180: {'lr': 0.00022785218901671383, 'samples': 15394560, 'steps': 80179, 'loss/train': 1.441405177116394} 08/31/2021 03:44:41 - INFO - __main__ - Step 80181: {'lr': 0.00022784690314312683, 'samples': 15394752, 'steps': 80180, 'loss/train': 1.1235684156417847} 08/31/2021 03:44:42 - INFO - __main__ - Step 80182: {'lr': 0.00022784161727952166, 'samples': 15394944, 'steps': 80181, 'loss/train': 1.1047500371932983} 08/31/2021 03:44:43 - INFO - __main__ - Step 80183: {'lr': 0.0002278363314259007, 'samples': 15395136, 'steps': 80182, 'loss/train': 1.1406763792037964} 08/31/2021 03:44:43 - INFO - __main__ - Step 80184: {'lr': 0.00022783104558226638, 'samples': 15395328, 'steps': 80183, 'loss/train': 0.7204656004905701} 08/31/2021 03:44:43 - INFO - __main__ - Step 80185: {'lr': 0.00022782575974862103, 'samples': 15395520, 'steps': 80184, 'loss/train': 0.9398275017738342} 08/31/2021 03:44:44 - INFO - __main__ - Step 80186: {'lr': 0.00022782047392496706, 'samples': 15395712, 'steps': 80185, 'loss/train': 0.4952441155910492} 08/31/2021 03:44:45 - INFO - __main__ - Step 80187: {'lr': 0.0002278151881113068, 'samples': 15395904, 'steps': 80186, 'loss/train': 1.962864637374878} 08/31/2021 03:44:46 - INFO - __main__ - Step 80188: {'lr': 0.00022780990230764273, 'samples': 15396096, 'steps': 80187, 'loss/train': 1.3217172622680664} 08/31/2021 03:44:46 - INFO - __main__ - Step 80189: {'lr': 0.00022780461651397712, 'samples': 15396288, 'steps': 80188, 'loss/train': 1.3515701293945312} 08/31/2021 03:44:46 - INFO - __main__ - Step 80190: {'lr': 0.00022779933073031257, 'samples': 15396480, 'steps': 80189, 'loss/train': 1.4890700578689575} 08/31/2021 03:44:47 - INFO - __main__ - Step 80191: {'lr': 0.00022779404495665116, 'samples': 15396672, 'steps': 80190, 'loss/train': 0.6653159260749817} 08/31/2021 03:44:48 - INFO - __main__ - Step 80192: {'lr': 0.0002277887591929954, 'samples': 15396864, 'steps': 80191, 'loss/train': 1.0203299522399902} 08/31/2021 03:44:49 - INFO - __main__ - Step 80193: {'lr': 0.00022778347343934771, 'samples': 15397056, 'steps': 80192, 'loss/train': 1.6735519170761108} 08/31/2021 03:44:49 - INFO - __main__ - Step 80194: {'lr': 0.00022777818769571047, 'samples': 15397248, 'steps': 80193, 'loss/train': 0.04319451376795769} 08/31/2021 03:44:49 - INFO - __main__ - Step 80195: {'lr': 0.00022777290196208597, 'samples': 15397440, 'steps': 80194, 'loss/train': 1.430199146270752} 08/31/2021 03:44:50 - INFO - __main__ - Step 80196: {'lr': 0.0002277676162384767, 'samples': 15397632, 'steps': 80195, 'loss/train': 1.606976866722107} 08/31/2021 03:44:51 - INFO - __main__ - Step 80197: {'lr': 0.00022776233052488497, 'samples': 15397824, 'steps': 80196, 'loss/train': 1.0556139945983887} 08/31/2021 03:44:52 - INFO - __main__ - Step 80198: {'lr': 0.0002277570448213132, 'samples': 15398016, 'steps': 80197, 'loss/train': 1.2184717655181885} 08/31/2021 03:44:52 - INFO - __main__ - Step 80199: {'lr': 0.00022775175912776376, 'samples': 15398208, 'steps': 80198, 'loss/train': 0.8686136603355408} 08/31/2021 03:44:53 - INFO - __main__ - Step 80200: {'lr': 0.00022774647344423908, 'samples': 15398400, 'steps': 80199, 'loss/train': 0.7339074015617371} 08/31/2021 03:44:53 - INFO - __main__ - Step 80201: {'lr': 0.00022774118777074142, 'samples': 15398592, 'steps': 80200, 'loss/train': 1.365578293800354} 08/31/2021 03:44:55 - INFO - __main__ - Step 80202: {'lr': 0.00022773590210727336, 'samples': 15398784, 'steps': 80201, 'loss/train': 1.5119839906692505} 08/31/2021 03:44:56 - INFO - __main__ - Step 80203: {'lr': 0.00022773061645383713, 'samples': 15398976, 'steps': 80202, 'loss/train': 1.2521226406097412} 08/31/2021 03:44:56 - INFO - __main__ - Step 80204: {'lr': 0.00022772533081043508, 'samples': 15399168, 'steps': 80203, 'loss/train': 1.444399118423462} 08/31/2021 03:44:56 - INFO - __main__ - Step 80205: {'lr': 0.00022772004517706965, 'samples': 15399360, 'steps': 80204, 'loss/train': 0.8833972215652466} 08/31/2021 03:44:57 - INFO - __main__ - Step 80206: {'lr': 0.00022771475955374323, 'samples': 15399552, 'steps': 80205, 'loss/train': 1.4087214469909668} 08/31/2021 03:44:58 - INFO - __main__ - Step 80207: {'lr': 0.0002277094739404582, 'samples': 15399744, 'steps': 80206, 'loss/train': 0.9993147253990173} 08/31/2021 03:44:59 - INFO - __main__ - Step 80208: {'lr': 0.00022770418833721696, 'samples': 15399936, 'steps': 80207, 'loss/train': 0.4570503532886505} 08/31/2021 03:44:59 - INFO - __main__ - Step 80209: {'lr': 0.00022769890274402182, 'samples': 15400128, 'steps': 80208, 'loss/train': 1.2104644775390625} 08/31/2021 03:44:59 - INFO - __main__ - Step 80210: {'lr': 0.00022769361716087525, 'samples': 15400320, 'steps': 80209, 'loss/train': 1.2874592542648315} 08/31/2021 03:45:00 - INFO - __main__ - Step 80211: {'lr': 0.00022768833158777957, 'samples': 15400512, 'steps': 80210, 'loss/train': 1.1458055973052979} 08/31/2021 03:45:01 - INFO - __main__ - Step 80212: {'lr': 0.00022768304602473725, 'samples': 15400704, 'steps': 80211, 'loss/train': 1.4943692684173584} 08/31/2021 03:45:02 - INFO - __main__ - Step 80213: {'lr': 0.00022767776047175054, 'samples': 15400896, 'steps': 80212, 'loss/train': 1.0268663167953491} 08/31/2021 03:45:02 - INFO - __main__ - Step 80214: {'lr': 0.00022767247492882188, 'samples': 15401088, 'steps': 80213, 'loss/train': 0.6439761519432068} 08/31/2021 03:45:02 - INFO - __main__ - Step 80215: {'lr': 0.00022766718939595367, 'samples': 15401280, 'steps': 80214, 'loss/train': 0.9588294625282288} 08/31/2021 03:45:03 - INFO - __main__ - Step 80216: {'lr': 0.00022766190387314833, 'samples': 15401472, 'steps': 80215, 'loss/train': 0.8763628005981445} 08/31/2021 03:45:03 - INFO - __main__ - Step 80217: {'lr': 0.00022765661836040817, 'samples': 15401664, 'steps': 80216, 'loss/train': 1.3614245653152466} 08/31/2021 03:45:05 - INFO - __main__ - Step 80218: {'lr': 0.00022765133285773553, 'samples': 15401856, 'steps': 80217, 'loss/train': 1.1654725074768066} 08/31/2021 03:45:05 - INFO - __main__ - Step 80219: {'lr': 0.0002276460473651329, 'samples': 15402048, 'steps': 80218, 'loss/train': 0.9469161033630371} 08/31/2021 03:45:05 - INFO - __main__ - Step 80220: {'lr': 0.00022764076188260262, 'samples': 15402240, 'steps': 80219, 'loss/train': 0.6892632246017456} 08/31/2021 03:45:06 - INFO - __main__ - Step 80221: {'lr': 0.00022763547641014705, 'samples': 15402432, 'steps': 80220, 'loss/train': 1.6009392738342285} 08/31/2021 03:45:06 - INFO - __main__ - Step 80222: {'lr': 0.00022763019094776857, 'samples': 15402624, 'steps': 80221, 'loss/train': 1.3449443578720093} 08/31/2021 03:45:08 - INFO - __main__ - Step 80223: {'lr': 0.00022762490549546965, 'samples': 15402816, 'steps': 80222, 'loss/train': 1.0779000520706177} 08/31/2021 03:45:08 - INFO - __main__ - Step 80224: {'lr': 0.00022761962005325256, 'samples': 15403008, 'steps': 80223, 'loss/train': 1.8423665761947632} 08/31/2021 03:45:08 - INFO - __main__ - Step 80225: {'lr': 0.00022761433462111972, 'samples': 15403200, 'steps': 80224, 'loss/train': 1.0848811864852905} 08/31/2021 03:45:09 - INFO - __main__ - Step 80226: {'lr': 0.0002276090491990735, 'samples': 15403392, 'steps': 80225, 'loss/train': 1.0429641008377075} 08/31/2021 03:45:09 - INFO - __main__ - Step 80227: {'lr': 0.00022760376378711634, 'samples': 15403584, 'steps': 80226, 'loss/train': 0.7877474427223206} 08/31/2021 03:45:11 - INFO - __main__ - Step 80228: {'lr': 0.00022759847838525052, 'samples': 15403776, 'steps': 80227, 'loss/train': 1.2061165571212769} 08/31/2021 03:45:11 - INFO - __main__ - Step 80229: {'lr': 0.0002275931929934785, 'samples': 15403968, 'steps': 80228, 'loss/train': 0.8396041393280029} 08/31/2021 03:45:12 - INFO - __main__ - Step 80230: {'lr': 0.00022758790761180273, 'samples': 15404160, 'steps': 80229, 'loss/train': 1.0458317995071411} 08/31/2021 03:45:12 - INFO - __main__ - Step 80231: {'lr': 0.0002275826222402254, 'samples': 15404352, 'steps': 80230, 'loss/train': 1.4547059535980225} 08/31/2021 03:45:12 - INFO - __main__ - Step 80232: {'lr': 0.00022757733687874904, 'samples': 15404544, 'steps': 80231, 'loss/train': 1.1575607061386108} 08/31/2021 03:45:13 - INFO - __main__ - Step 80233: {'lr': 0.00022757205152737595, 'samples': 15404736, 'steps': 80232, 'loss/train': 0.8917491436004639} 08/31/2021 03:45:14 - INFO - __main__ - Step 80234: {'lr': 0.0002275667661861086, 'samples': 15404928, 'steps': 80233, 'loss/train': 0.4370552599430084} 08/31/2021 03:45:15 - INFO - __main__ - Step 80235: {'lr': 0.0002275614808549493, 'samples': 15405120, 'steps': 80234, 'loss/train': 1.2285243272781372} 08/31/2021 03:45:15 - INFO - __main__ - Step 80236: {'lr': 0.00022755619553390045, 'samples': 15405312, 'steps': 80235, 'loss/train': 1.6211519241333008} 08/31/2021 03:45:15 - INFO - __main__ - Step 80237: {'lr': 0.00022755091022296439, 'samples': 15405504, 'steps': 80236, 'loss/train': 1.1016567945480347} 08/31/2021 03:45:16 - INFO - __main__ - Step 80238: {'lr': 0.00022754562492214355, 'samples': 15405696, 'steps': 80237, 'loss/train': 0.9663636684417725} 08/31/2021 03:45:17 - INFO - __main__ - Step 80239: {'lr': 0.00022754033963144033, 'samples': 15405888, 'steps': 80238, 'loss/train': 1.7270864248275757} 08/31/2021 03:45:18 - INFO - __main__ - Step 80240: {'lr': 0.00022753505435085708, 'samples': 15406080, 'steps': 80239, 'loss/train': 0.9580908417701721} 08/31/2021 03:45:18 - INFO - __main__ - Step 80241: {'lr': 0.00022752976908039618, 'samples': 15406272, 'steps': 80240, 'loss/train': 1.4885828495025635} 08/31/2021 03:45:18 - INFO - __main__ - Step 80242: {'lr': 0.00022752448382006002, 'samples': 15406464, 'steps': 80241, 'loss/train': 1.22652006149292} 08/31/2021 03:45:19 - INFO - __main__ - Step 80243: {'lr': 0.00022751919856985107, 'samples': 15406656, 'steps': 80242, 'loss/train': 0.9867653250694275} 08/31/2021 03:45:20 - INFO - __main__ - Step 80244: {'lr': 0.00022751391332977153, 'samples': 15406848, 'steps': 80243, 'loss/train': 1.3449978828430176} 08/31/2021 03:45:21 - INFO - __main__ - Step 80245: {'lr': 0.00022750862809982393, 'samples': 15407040, 'steps': 80244, 'loss/train': 0.6206724047660828} 08/31/2021 03:45:21 - INFO - __main__ - Step 80246: {'lr': 0.00022750334288001054, 'samples': 15407232, 'steps': 80245, 'loss/train': 1.4147436618804932} 08/31/2021 03:45:22 - INFO - __main__ - Step 80247: {'lr': 0.0002274980576703338, 'samples': 15407424, 'steps': 80246, 'loss/train': 0.9663273096084595} 08/31/2021 03:45:22 - INFO - __main__ - Step 80248: {'lr': 0.00022749277247079608, 'samples': 15407616, 'steps': 80247, 'loss/train': 1.8764654397964478} 08/31/2021 03:45:23 - INFO - __main__ - Step 80249: {'lr': 0.00022748748728139979, 'samples': 15407808, 'steps': 80248, 'loss/train': 0.8103428483009338} 08/31/2021 03:45:24 - INFO - __main__ - Step 80250: {'lr': 0.0002274822021021473, 'samples': 15408000, 'steps': 80249, 'loss/train': 0.9822115302085876} 08/31/2021 03:45:24 - INFO - __main__ - Step 80251: {'lr': 0.00022747691693304094, 'samples': 15408192, 'steps': 80250, 'loss/train': 1.468329668045044} 08/31/2021 03:45:25 - INFO - __main__ - Step 80252: {'lr': 0.00022747163177408317, 'samples': 15408384, 'steps': 80251, 'loss/train': 1.835975170135498} 08/31/2021 03:45:25 - INFO - __main__ - Step 80253: {'lr': 0.0002274663466252763, 'samples': 15408576, 'steps': 80252, 'loss/train': 1.6526293754577637} 08/31/2021 03:45:25 - INFO - __main__ - Step 80254: {'lr': 0.0002274610614866228, 'samples': 15408768, 'steps': 80253, 'loss/train': 1.1419087648391724} 08/31/2021 03:45:27 - INFO - __main__ - Step 80255: {'lr': 0.00022745577635812495, 'samples': 15408960, 'steps': 80254, 'loss/train': 1.7429178953170776} 08/31/2021 03:45:28 - INFO - __main__ - Step 80256: {'lr': 0.0002274504912397852, 'samples': 15409152, 'steps': 80255, 'loss/train': 1.26252019405365} 08/31/2021 03:45:28 - INFO - __main__ - Step 80257: {'lr': 0.000227445206131606, 'samples': 15409344, 'steps': 80256, 'loss/train': 1.3530569076538086} 08/31/2021 03:45:28 - INFO - __main__ - Step 80258: {'lr': 0.00022743992103358958, 'samples': 15409536, 'steps': 80257, 'loss/train': 1.1094005107879639} 08/31/2021 03:45:29 - INFO - __main__ - Step 80259: {'lr': 0.00022743463594573834, 'samples': 15409728, 'steps': 80258, 'loss/train': 0.8266786336898804} 08/31/2021 03:45:30 - INFO - __main__ - Step 80260: {'lr': 0.0002274293508680547, 'samples': 15409920, 'steps': 80259, 'loss/train': 1.6378746032714844} 08/31/2021 03:45:31 - INFO - __main__ - Step 80261: {'lr': 0.00022742406580054106, 'samples': 15410112, 'steps': 80260, 'loss/train': 1.3742172718048096} 08/31/2021 03:45:31 - INFO - __main__ - Step 80262: {'lr': 0.0002274187807431998, 'samples': 15410304, 'steps': 80261, 'loss/train': 1.4211477041244507} 08/31/2021 03:45:31 - INFO - __main__ - Step 80263: {'lr': 0.00022741349569603328, 'samples': 15410496, 'steps': 80262, 'loss/train': 0.863486111164093} 08/31/2021 03:45:32 - INFO - __main__ - Step 80264: {'lr': 0.00022740821065904388, 'samples': 15410688, 'steps': 80263, 'loss/train': 1.0003478527069092} 08/31/2021 03:45:33 - INFO - __main__ - Step 80265: {'lr': 0.000227402925632234, 'samples': 15410880, 'steps': 80264, 'loss/train': 0.9362325072288513} 08/31/2021 03:45:34 - INFO - __main__ - Step 80266: {'lr': 0.00022739764061560603, 'samples': 15411072, 'steps': 80265, 'loss/train': 0.2982054352760315} 08/31/2021 03:45:34 - INFO - __main__ - Step 80267: {'lr': 0.00022739235560916232, 'samples': 15411264, 'steps': 80266, 'loss/train': 0.6876441240310669} 08/31/2021 03:45:35 - INFO - __main__ - Step 80268: {'lr': 0.00022738707061290526, 'samples': 15411456, 'steps': 80267, 'loss/train': 1.5580179691314697} 08/31/2021 03:45:35 - INFO - __main__ - Step 80269: {'lr': 0.00022738178562683724, 'samples': 15411648, 'steps': 80268, 'loss/train': 1.265526533126831} 08/31/2021 03:45:36 - INFO - __main__ - Step 80270: {'lr': 0.00022737650065096074, 'samples': 15411840, 'steps': 80269, 'loss/train': 1.3435708284378052} 08/31/2021 03:45:37 - INFO - __main__ - Step 80271: {'lr': 0.00022737121568527794, 'samples': 15412032, 'steps': 80270, 'loss/train': 1.3839678764343262} 08/31/2021 03:45:37 - INFO - __main__ - Step 80272: {'lr': 0.00022736593072979135, 'samples': 15412224, 'steps': 80271, 'loss/train': 2.2111682891845703} 08/31/2021 03:45:37 - INFO - __main__ - Step 80273: {'lr': 0.00022736064578450328, 'samples': 15412416, 'steps': 80272, 'loss/train': 0.9502593278884888} 08/31/2021 03:45:38 - INFO - __main__ - Step 80274: {'lr': 0.00022735536084941615, 'samples': 15412608, 'steps': 80273, 'loss/train': 0.8121161460876465} 08/31/2021 03:45:39 - INFO - __main__ - Step 80275: {'lr': 0.00022735007592453236, 'samples': 15412800, 'steps': 80274, 'loss/train': 1.0773061513900757} 08/31/2021 03:45:40 - INFO - __main__ - Step 80276: {'lr': 0.00022734479100985428, 'samples': 15412992, 'steps': 80275, 'loss/train': 1.1146594285964966} 08/31/2021 03:45:40 - INFO - __main__ - Step 80277: {'lr': 0.00022733950610538429, 'samples': 15413184, 'steps': 80276, 'loss/train': 0.7872962951660156} 08/31/2021 03:45:40 - INFO - __main__ - Step 80278: {'lr': 0.00022733422121112476, 'samples': 15413376, 'steps': 80277, 'loss/train': 1.4633997678756714} 08/31/2021 03:45:41 - INFO - __main__ - Step 80279: {'lr': 0.00022732893632707808, 'samples': 15413568, 'steps': 80278, 'loss/train': 0.8006643056869507} 08/31/2021 03:45:42 - INFO - __main__ - Step 80280: {'lr': 0.00022732365145324666, 'samples': 15413760, 'steps': 80279, 'loss/train': 1.1194559335708618} 08/31/2021 03:45:43 - INFO - __main__ - Step 80281: {'lr': 0.00022731836658963282, 'samples': 15413952, 'steps': 80280, 'loss/train': 1.212950587272644} 08/31/2021 03:45:43 - INFO - __main__ - Step 80282: {'lr': 0.00022731308173623896, 'samples': 15414144, 'steps': 80281, 'loss/train': 0.09061375260353088} 08/31/2021 03:45:44 - INFO - __main__ - Step 80283: {'lr': 0.0002273077968930675, 'samples': 15414336, 'steps': 80282, 'loss/train': 1.3930563926696777} 08/31/2021 03:45:44 - INFO - __main__ - Step 80284: {'lr': 0.00022730251206012092, 'samples': 15414528, 'steps': 80283, 'loss/train': 1.138759970664978} 08/31/2021 03:45:46 - INFO - __main__ - Step 80285: {'lr': 0.00022729722723740134, 'samples': 15414720, 'steps': 80284, 'loss/train': 0.031052934005856514} 08/31/2021 03:45:46 - INFO - __main__ - Step 80286: {'lr': 0.0002272919424249113, 'samples': 15414912, 'steps': 80285, 'loss/train': 1.29249906539917} 08/31/2021 03:45:47 - INFO - __main__ - Step 80287: {'lr': 0.00022728665762265316, 'samples': 15415104, 'steps': 80286, 'loss/train': 1.2474123239517212} 08/31/2021 03:45:47 - INFO - __main__ - Step 80288: {'lr': 0.00022728137283062927, 'samples': 15415296, 'steps': 80287, 'loss/train': 1.2901291847229004} 08/31/2021 03:45:47 - INFO - __main__ - Step 80289: {'lr': 0.00022727608804884209, 'samples': 15415488, 'steps': 80288, 'loss/train': 1.7596276998519897} 08/31/2021 03:45:49 - INFO - __main__ - Step 80290: {'lr': 0.0002272708032772939, 'samples': 15415680, 'steps': 80289, 'loss/train': 1.5483382940292358} 08/31/2021 03:45:49 - INFO - __main__ - Step 80291: {'lr': 0.00022726551851598719, 'samples': 15415872, 'steps': 80290, 'loss/train': 1.1052782535552979} 08/31/2021 03:45:50 - INFO - __main__ - Step 80292: {'lr': 0.00022726023376492424, 'samples': 15416064, 'steps': 80291, 'loss/train': 1.708485722541809} 08/31/2021 03:45:50 - INFO - __main__ - Step 80293: {'lr': 0.0002272549490241075, 'samples': 15416256, 'steps': 80292, 'loss/train': 0.49999499320983887} 08/31/2021 03:45:51 - INFO - __main__ - Step 80294: {'lr': 0.00022724966429353934, 'samples': 15416448, 'steps': 80293, 'loss/train': 1.4362115859985352} 08/31/2021 03:45:51 - INFO - __main__ - Step 80295: {'lr': 0.00022724437957322215, 'samples': 15416640, 'steps': 80294, 'loss/train': 1.2279729843139648} 08/31/2021 03:45:52 - INFO - __main__ - Step 80296: {'lr': 0.00022723909486315825, 'samples': 15416832, 'steps': 80295, 'loss/train': 0.6412253975868225} 08/31/2021 03:45:53 - INFO - __main__ - Step 80297: {'lr': 0.00022723381016335014, 'samples': 15417024, 'steps': 80296, 'loss/train': 1.1653434038162231} 08/31/2021 03:45:53 - INFO - __main__ - Step 80298: {'lr': 0.00022722852547380008, 'samples': 15417216, 'steps': 80297, 'loss/train': 1.1463202238082886} 08/31/2021 03:45:53 - INFO - __main__ - Step 80299: {'lr': 0.00022722324079451047, 'samples': 15417408, 'steps': 80298, 'loss/train': 0.9307375550270081} 08/31/2021 03:45:54 - INFO - __main__ - Step 80300: {'lr': 0.00022721795612548373, 'samples': 15417600, 'steps': 80299, 'loss/train': 1.4565651416778564} 08/31/2021 03:45:55 - INFO - __main__ - Step 80301: {'lr': 0.0002272126714667222, 'samples': 15417792, 'steps': 80300, 'loss/train': 0.8869895935058594} 08/31/2021 03:45:56 - INFO - __main__ - Step 80302: {'lr': 0.0002272073868182283, 'samples': 15417984, 'steps': 80301, 'loss/train': 1.493919849395752} 08/31/2021 03:45:56 - INFO - __main__ - Step 80303: {'lr': 0.00022720210218000442, 'samples': 15418176, 'steps': 80302, 'loss/train': 0.42114171385765076} 08/31/2021 03:45:57 - INFO - __main__ - Step 80304: {'lr': 0.0002271968175520529, 'samples': 15418368, 'steps': 80303, 'loss/train': 0.9088283181190491} 08/31/2021 03:45:57 - INFO - __main__ - Step 80305: {'lr': 0.00022719153293437614, 'samples': 15418560, 'steps': 80304, 'loss/train': 1.2457497119903564} 08/31/2021 03:45:59 - INFO - __main__ - Step 80306: {'lr': 0.00022718624832697654, 'samples': 15418752, 'steps': 80305, 'loss/train': 1.1884868144989014} 08/31/2021 03:45:59 - INFO - __main__ - Step 80307: {'lr': 0.00022718096372985645, 'samples': 15418944, 'steps': 80306, 'loss/train': 3.333571672439575} 08/31/2021 03:46:00 - INFO - __main__ - Step 80308: {'lr': 0.00022717567914301828, 'samples': 15419136, 'steps': 80307, 'loss/train': 1.3512054681777954} 08/31/2021 03:46:00 - INFO - __main__ - Step 80309: {'lr': 0.0002271703945664644, 'samples': 15419328, 'steps': 80308, 'loss/train': 1.6272786855697632} 08/31/2021 03:46:00 - INFO - __main__ - Step 80310: {'lr': 0.00022716511000019717, 'samples': 15419520, 'steps': 80309, 'loss/train': 0.9873403906822205} 08/31/2021 03:46:01 - INFO - __main__ - Step 80311: {'lr': 0.0002271598254442191, 'samples': 15419712, 'steps': 80310, 'loss/train': 0.9977946281433105} 08/31/2021 03:46:02 - INFO - __main__ - Step 80312: {'lr': 0.00022715454089853234, 'samples': 15419904, 'steps': 80311, 'loss/train': 2.1094748973846436} 08/31/2021 03:46:03 - INFO - __main__ - Step 80313: {'lr': 0.0002271492563631394, 'samples': 15420096, 'steps': 80312, 'loss/train': 0.9910731315612793} 08/31/2021 03:46:03 - INFO - __main__ - Step 80314: {'lr': 0.00022714397183804267, 'samples': 15420288, 'steps': 80313, 'loss/train': 1.1987556219100952} 08/31/2021 03:46:03 - INFO - __main__ - Step 80315: {'lr': 0.0002271386873232445, 'samples': 15420480, 'steps': 80314, 'loss/train': 1.4905551671981812} 08/31/2021 03:46:04 - INFO - __main__ - Step 80316: {'lr': 0.0002271334028187473, 'samples': 15420672, 'steps': 80315, 'loss/train': 1.2844332456588745} 08/31/2021 03:46:06 - INFO - __main__ - Step 80317: {'lr': 0.00022712811832455341, 'samples': 15420864, 'steps': 80316, 'loss/train': 1.33495032787323} 08/31/2021 03:46:06 - INFO - __main__ - Step 80318: {'lr': 0.00022712283384066523, 'samples': 15421056, 'steps': 80317, 'loss/train': 0.6154475808143616} 08/31/2021 03:46:06 - INFO - __main__ - Step 80319: {'lr': 0.00022711754936708518, 'samples': 15421248, 'steps': 80318, 'loss/train': 1.4999933242797852} 08/31/2021 03:46:07 - INFO - __main__ - Step 80320: {'lr': 0.0002271122649038156, 'samples': 15421440, 'steps': 80319, 'loss/train': 1.3250054121017456} 08/31/2021 03:46:07 - INFO - __main__ - Step 80321: {'lr': 0.00022710698045085888, 'samples': 15421632, 'steps': 80320, 'loss/train': 1.6549586057662964} 08/31/2021 03:46:09 - INFO - __main__ - Step 80322: {'lr': 0.0002271016960082174, 'samples': 15421824, 'steps': 80321, 'loss/train': 0.057517532259225845} 08/31/2021 03:46:09 - INFO - __main__ - Step 80323: {'lr': 0.00022709641157589352, 'samples': 15422016, 'steps': 80322, 'loss/train': 1.6224216222763062} 08/31/2021 03:46:09 - INFO - __main__ - Step 80324: {'lr': 0.0002270911271538898, 'samples': 15422208, 'steps': 80323, 'loss/train': 1.4847862720489502} 08/31/2021 03:46:10 - INFO - __main__ - Step 80325: {'lr': 0.00022708584274220832, 'samples': 15422400, 'steps': 80324, 'loss/train': 0.7695793509483337} 08/31/2021 03:46:10 - INFO - __main__ - Step 80326: {'lr': 0.0002270805583408516, 'samples': 15422592, 'steps': 80325, 'loss/train': 0.8726099133491516} 08/31/2021 03:46:11 - INFO - __main__ - Step 80327: {'lr': 0.00022707527394982206, 'samples': 15422784, 'steps': 80326, 'loss/train': 1.338325023651123} 08/31/2021 03:46:12 - INFO - __main__ - Step 80328: {'lr': 0.00022706998956912203, 'samples': 15422976, 'steps': 80327, 'loss/train': 1.020486831665039} 08/31/2021 03:46:12 - INFO - __main__ - Step 80329: {'lr': 0.00022706470519875388, 'samples': 15423168, 'steps': 80328, 'loss/train': 1.1290099620819092} 08/31/2021 03:46:13 - INFO - __main__ - Step 80330: {'lr': 0.00022705942083872004, 'samples': 15423360, 'steps': 80329, 'loss/train': 1.739928126335144} 08/31/2021 03:46:13 - INFO - __main__ - Step 80331: {'lr': 0.0002270541364890229, 'samples': 15423552, 'steps': 80330, 'loss/train': 0.8428916335105896} 08/31/2021 03:46:15 - INFO - __main__ - Step 80332: {'lr': 0.0002270488521496648, 'samples': 15423744, 'steps': 80331, 'loss/train': 1.692956805229187} 08/31/2021 03:46:15 - INFO - __main__ - Step 80333: {'lr': 0.0002270435678206481, 'samples': 15423936, 'steps': 80332, 'loss/train': 1.6040834188461304} 08/31/2021 03:46:15 - INFO - __main__ - Step 80334: {'lr': 0.00022703828350197525, 'samples': 15424128, 'steps': 80333, 'loss/train': 2.148740530014038} 08/31/2021 03:46:16 - INFO - __main__ - Step 80335: {'lr': 0.0002270329991936486, 'samples': 15424320, 'steps': 80334, 'loss/train': 1.2781387567520142} 08/31/2021 03:46:16 - INFO - __main__ - Step 80336: {'lr': 0.00022702771489567055, 'samples': 15424512, 'steps': 80335, 'loss/train': 0.9664329290390015} 08/31/2021 03:46:18 - INFO - __main__ - Step 80337: {'lr': 0.00022702243060804348, 'samples': 15424704, 'steps': 80336, 'loss/train': 0.2127363532781601} 08/31/2021 03:46:18 - INFO - __main__ - Step 80338: {'lr': 0.00022701714633076967, 'samples': 15424896, 'steps': 80337, 'loss/train': 0.0666247233748436} 08/31/2021 03:46:19 - INFO - __main__ - Step 80339: {'lr': 0.00022701186206385162, 'samples': 15425088, 'steps': 80338, 'loss/train': 1.292353868484497} 08/31/2021 03:46:19 - INFO - __main__ - Step 80340: {'lr': 0.00022700657780729162, 'samples': 15425280, 'steps': 80339, 'loss/train': 0.6589674949645996} 08/31/2021 03:46:19 - INFO - __main__ - Step 80341: {'lr': 0.00022700129356109213, 'samples': 15425472, 'steps': 80340, 'loss/train': 1.4050242900848389} 08/31/2021 03:46:20 - INFO - __main__ - Step 80342: {'lr': 0.0002269960093252555, 'samples': 15425664, 'steps': 80341, 'loss/train': 0.9212373495101929} 08/31/2021 03:46:21 - INFO - __main__ - Step 80343: {'lr': 0.0002269907250997841, 'samples': 15425856, 'steps': 80342, 'loss/train': 1.4080801010131836} 08/31/2021 03:46:22 - INFO - __main__ - Step 80344: {'lr': 0.00022698544088468035, 'samples': 15426048, 'steps': 80343, 'loss/train': 0.7686650156974792} 08/31/2021 03:46:22 - INFO - __main__ - Step 80345: {'lr': 0.0002269801566799466, 'samples': 15426240, 'steps': 80344, 'loss/train': 2.1065852642059326} 08/31/2021 03:46:22 - INFO - __main__ - Step 80346: {'lr': 0.0002269748724855852, 'samples': 15426432, 'steps': 80345, 'loss/train': 1.104130744934082} 08/31/2021 03:46:23 - INFO - __main__ - Step 80347: {'lr': 0.00022696958830159867, 'samples': 15426624, 'steps': 80346, 'loss/train': 1.3523893356323242} 08/31/2021 03:46:24 - INFO - __main__ - Step 80348: {'lr': 0.0002269643041279892, 'samples': 15426816, 'steps': 80347, 'loss/train': 1.4297983646392822} 08/31/2021 03:46:25 - INFO - __main__ - Step 80349: {'lr': 0.00022695901996475925, 'samples': 15427008, 'steps': 80348, 'loss/train': 1.188075065612793} 08/31/2021 03:46:25 - INFO - __main__ - Step 80350: {'lr': 0.00022695373581191125, 'samples': 15427200, 'steps': 80349, 'loss/train': 1.0416885614395142} 08/31/2021 03:46:26 - INFO - __main__ - Step 80351: {'lr': 0.0002269484516694476, 'samples': 15427392, 'steps': 80350, 'loss/train': 1.4551554918289185} 08/31/2021 03:46:26 - INFO - __main__ - Step 80352: {'lr': 0.00022694316753737052, 'samples': 15427584, 'steps': 80351, 'loss/train': 3.322176456451416} 08/31/2021 03:46:28 - INFO - __main__ - Step 80353: {'lr': 0.00022693788341568254, 'samples': 15427776, 'steps': 80352, 'loss/train': 0.5785526633262634} 08/31/2021 03:46:28 - INFO - __main__ - Step 80354: {'lr': 0.00022693259930438596, 'samples': 15427968, 'steps': 80353, 'loss/train': 1.5314730405807495} 08/31/2021 03:46:29 - INFO - __main__ - Step 80355: {'lr': 0.0002269273152034832, 'samples': 15428160, 'steps': 80354, 'loss/train': 1.0308382511138916} 08/31/2021 03:46:29 - INFO - __main__ - Step 80356: {'lr': 0.00022692203111297662, 'samples': 15428352, 'steps': 80355, 'loss/train': 1.3909411430358887} 08/31/2021 03:46:29 - INFO - __main__ - Step 80357: {'lr': 0.00022691674703286866, 'samples': 15428544, 'steps': 80356, 'loss/train': 0.04222985357046127} 08/31/2021 03:46:31 - INFO - __main__ - Step 80358: {'lr': 0.00022691146296316167, 'samples': 15428736, 'steps': 80357, 'loss/train': 1.155990719795227} 08/31/2021 03:46:31 - INFO - __main__ - Step 80359: {'lr': 0.000226906178903858, 'samples': 15428928, 'steps': 80358, 'loss/train': 0.9465277194976807} 08/31/2021 03:46:32 - INFO - __main__ - Step 80360: {'lr': 0.00022690089485496003, 'samples': 15429120, 'steps': 80359, 'loss/train': 1.3872627019882202} 08/31/2021 03:46:32 - INFO - __main__ - Step 80361: {'lr': 0.00022689561081647017, 'samples': 15429312, 'steps': 80360, 'loss/train': 1.4006097316741943} 08/31/2021 03:46:32 - INFO - __main__ - Step 80362: {'lr': 0.00022689032678839077, 'samples': 15429504, 'steps': 80361, 'loss/train': 0.934659481048584} 08/31/2021 03:46:34 - INFO - __main__ - Step 80363: {'lr': 0.00022688504277072424, 'samples': 15429696, 'steps': 80362, 'loss/train': 1.0419621467590332} 08/31/2021 03:46:35 - INFO - __main__ - Step 80364: {'lr': 0.00022687975876347304, 'samples': 15429888, 'steps': 80363, 'loss/train': 1.2525309324264526} 08/31/2021 03:46:35 - INFO - __main__ - Step 80365: {'lr': 0.00022687447476663937, 'samples': 15430080, 'steps': 80364, 'loss/train': 1.1989402770996094} 08/31/2021 03:46:36 - INFO - __main__ - Step 80366: {'lr': 0.00022686919078022572, 'samples': 15430272, 'steps': 80365, 'loss/train': 1.17573881149292} 08/31/2021 03:46:36 - INFO - __main__ - Step 80367: {'lr': 0.00022686390680423446, 'samples': 15430464, 'steps': 80366, 'loss/train': 1.0994055271148682} 08/31/2021 03:46:36 - INFO - __main__ - Step 80368: {'lr': 0.00022685862283866796, 'samples': 15430656, 'steps': 80367, 'loss/train': 0.9549879431724548} 08/31/2021 03:46:38 - INFO - __main__ - Step 80369: {'lr': 0.00022685333888352867, 'samples': 15430848, 'steps': 80368, 'loss/train': 1.6065876483917236} 08/31/2021 03:46:38 - INFO - __main__ - Step 80370: {'lr': 0.00022684805493881883, 'samples': 15431040, 'steps': 80369, 'loss/train': 1.162795066833496} 08/31/2021 03:46:39 - INFO - __main__ - Step 80371: {'lr': 0.0002268427710045409, 'samples': 15431232, 'steps': 80370, 'loss/train': 1.3583638668060303} 08/31/2021 03:46:39 - INFO - __main__ - Step 80372: {'lr': 0.00022683748708069728, 'samples': 15431424, 'steps': 80371, 'loss/train': 0.8680949211120605} 08/31/2021 03:46:39 - INFO - __main__ - Step 80373: {'lr': 0.00022683220316729034, 'samples': 15431616, 'steps': 80372, 'loss/train': 1.367412805557251} 08/31/2021 03:46:41 - INFO - __main__ - Step 80374: {'lr': 0.00022682691926432245, 'samples': 15431808, 'steps': 80373, 'loss/train': 1.1450697183609009} 08/31/2021 03:46:41 - INFO - __main__ - Step 80375: {'lr': 0.000226821635371796, 'samples': 15432000, 'steps': 80374, 'loss/train': 0.5517399311065674} 08/31/2021 03:46:42 - INFO - __main__ - Step 80376: {'lr': 0.00022681635148971333, 'samples': 15432192, 'steps': 80375, 'loss/train': 0.7758100032806396} 08/31/2021 03:46:42 - INFO - __main__ - Step 80377: {'lr': 0.00022681106761807685, 'samples': 15432384, 'steps': 80376, 'loss/train': 0.9115474820137024} 08/31/2021 03:46:42 - INFO - __main__ - Step 80378: {'lr': 0.00022680578375688904, 'samples': 15432576, 'steps': 80377, 'loss/train': 0.9123333692550659} 08/31/2021 03:46:44 - INFO - __main__ - Step 80379: {'lr': 0.0002268004999061521, 'samples': 15432768, 'steps': 80378, 'loss/train': 0.9097388982772827} 08/31/2021 03:46:44 - INFO - __main__ - Step 80380: {'lr': 0.00022679521606586855, 'samples': 15432960, 'steps': 80379, 'loss/train': 1.5701812505722046} 08/31/2021 03:46:45 - INFO - __main__ - Step 80381: {'lr': 0.0002267899322360407, 'samples': 15433152, 'steps': 80380, 'loss/train': 1.1058369874954224} 08/31/2021 03:46:45 - INFO - __main__ - Step 80382: {'lr': 0.0002267846484166709, 'samples': 15433344, 'steps': 80381, 'loss/train': 0.9337097406387329} 08/31/2021 03:46:45 - INFO - __main__ - Step 80383: {'lr': 0.0002267793646077616, 'samples': 15433536, 'steps': 80382, 'loss/train': 1.052376627922058} 08/31/2021 03:46:47 - INFO - __main__ - Step 80384: {'lr': 0.00022677408080931517, 'samples': 15433728, 'steps': 80383, 'loss/train': 0.04589376226067543} 08/31/2021 03:46:48 - INFO - __main__ - Step 80385: {'lr': 0.00022676879702133396, 'samples': 15433920, 'steps': 80384, 'loss/train': 1.4186125993728638} 08/31/2021 03:46:48 - INFO - __main__ - Step 80386: {'lr': 0.00022676351324382038, 'samples': 15434112, 'steps': 80385, 'loss/train': 1.090492844581604} 08/31/2021 03:46:48 - INFO - __main__ - Step 80387: {'lr': 0.00022675822947677683, 'samples': 15434304, 'steps': 80386, 'loss/train': 1.0337039232254028} 08/31/2021 03:46:49 - INFO - __main__ - Step 80388: {'lr': 0.00022675294572020564, 'samples': 15434496, 'steps': 80387, 'loss/train': 2.0029444694519043} 08/31/2021 03:46:50 - INFO - __main__ - Step 80389: {'lr': 0.0002267476619741092, 'samples': 15434688, 'steps': 80388, 'loss/train': 1.5901598930358887} 08/31/2021 03:46:51 - INFO - __main__ - Step 80390: {'lr': 0.00022674237823848992, 'samples': 15434880, 'steps': 80389, 'loss/train': 0.9663965702056885} 08/31/2021 03:46:51 - INFO - __main__ - Step 80391: {'lr': 0.0002267370945133503, 'samples': 15435072, 'steps': 80390, 'loss/train': 1.1330469846725464} 08/31/2021 03:46:51 - INFO - __main__ - Step 80392: {'lr': 0.00022673181079869244, 'samples': 15435264, 'steps': 80391, 'loss/train': 1.3226203918457031} 08/31/2021 03:46:52 - INFO - __main__ - Step 80393: {'lr': 0.00022672652709451884, 'samples': 15435456, 'steps': 80392, 'loss/train': 1.170824408531189} 08/31/2021 03:46:52 - INFO - __main__ - Step 80394: {'lr': 0.00022672124340083197, 'samples': 15435648, 'steps': 80393, 'loss/train': 1.319482445716858} 08/31/2021 03:46:54 - INFO - __main__ - Step 80395: {'lr': 0.0002267159597176341, 'samples': 15435840, 'steps': 80394, 'loss/train': 1.1625186204910278} 08/31/2021 03:46:54 - INFO - __main__ - Step 80396: {'lr': 0.0002267106760449277, 'samples': 15436032, 'steps': 80395, 'loss/train': 1.368648886680603} 08/31/2021 03:46:54 - INFO - __main__ - Step 80397: {'lr': 0.00022670539238271508, 'samples': 15436224, 'steps': 80396, 'loss/train': 0.9408208131790161} 08/31/2021 03:46:55 - INFO - __main__ - Step 80398: {'lr': 0.00022670010873099866, 'samples': 15436416, 'steps': 80397, 'loss/train': 1.7433234453201294} 08/31/2021 03:46:55 - INFO - __main__ - Step 80399: {'lr': 0.00022669482508978084, 'samples': 15436608, 'steps': 80398, 'loss/train': 2.2868101596832275} 08/31/2021 03:46:56 - INFO - __main__ - Step 80400: {'lr': 0.00022668954145906394, 'samples': 15436800, 'steps': 80399, 'loss/train': 0.061384234577417374} 08/31/2021 03:46:57 - INFO - __main__ - Step 80401: {'lr': 0.0002266842578388504, 'samples': 15436992, 'steps': 80400, 'loss/train': 1.1697789430618286} 08/31/2021 03:46:57 - INFO - __main__ - Step 80402: {'lr': 0.00022667897422914252, 'samples': 15437184, 'steps': 80401, 'loss/train': 1.6506600379943848} 08/31/2021 03:46:58 - INFO - __main__ - Step 80403: {'lr': 0.0002266736906299428, 'samples': 15437376, 'steps': 80402, 'loss/train': 1.2882468700408936} 08/31/2021 03:46:58 - INFO - __main__ - Step 80404: {'lr': 0.00022666840704125353, 'samples': 15437568, 'steps': 80403, 'loss/train': 0.8180145025253296} 08/31/2021 03:47:00 - INFO - __main__ - Step 80405: {'lr': 0.00022666312346307719, 'samples': 15437760, 'steps': 80404, 'loss/train': 1.3435826301574707} 08/31/2021 03:47:00 - INFO - __main__ - Step 80406: {'lr': 0.000226657839895416, 'samples': 15437952, 'steps': 80405, 'loss/train': 1.0718587636947632} 08/31/2021 03:47:00 - INFO - __main__ - Step 80407: {'lr': 0.00022665255633827245, 'samples': 15438144, 'steps': 80406, 'loss/train': 1.1827055215835571} 08/31/2021 03:47:01 - INFO - __main__ - Step 80408: {'lr': 0.00022664727279164888, 'samples': 15438336, 'steps': 80407, 'loss/train': 1.378591537475586} 08/31/2021 03:47:01 - INFO - __main__ - Step 80409: {'lr': 0.00022664198925554768, 'samples': 15438528, 'steps': 80408, 'loss/train': 1.1742695569992065} 08/31/2021 03:47:01 - INFO - __main__ - Step 80410: {'lr': 0.00022663670572997124, 'samples': 15438720, 'steps': 80409, 'loss/train': 1.1383349895477295} 08/31/2021 03:47:03 - INFO - __main__ - Step 80411: {'lr': 0.00022663142221492194, 'samples': 15438912, 'steps': 80410, 'loss/train': 0.7681330442428589} 08/31/2021 03:47:03 - INFO - __main__ - Step 80412: {'lr': 0.0002266261387104022, 'samples': 15439104, 'steps': 80411, 'loss/train': 1.1411997079849243} 08/31/2021 03:47:04 - INFO - __main__ - Step 80413: {'lr': 0.0002266208552164143, 'samples': 15439296, 'steps': 80412, 'loss/train': 1.2278589010238647} 08/31/2021 03:47:04 - INFO - __main__ - Step 80414: {'lr': 0.00022661557173296072, 'samples': 15439488, 'steps': 80413, 'loss/train': 0.8737099170684814} 08/31/2021 03:47:04 - INFO - __main__ - Step 80415: {'lr': 0.0002266102882600438, 'samples': 15439680, 'steps': 80414, 'loss/train': 1.7527819871902466} 08/31/2021 03:47:07 - INFO - __main__ - Step 80416: {'lr': 0.0002266050047976659, 'samples': 15439872, 'steps': 80415, 'loss/train': 1.9795234203338623} 08/31/2021 03:47:07 - INFO - __main__ - Step 80417: {'lr': 0.00022659972134582947, 'samples': 15440064, 'steps': 80416, 'loss/train': 1.2024441957473755} 08/31/2021 03:47:08 - INFO - __main__ - Step 80418: {'lr': 0.0002265944379045369, 'samples': 15440256, 'steps': 80417, 'loss/train': 0.04716983437538147} 08/31/2021 03:47:08 - INFO - __main__ - Step 80419: {'lr': 0.00022658915447379044, 'samples': 15440448, 'steps': 80418, 'loss/train': 1.2832534313201904} 08/31/2021 03:47:08 - INFO - __main__ - Step 80420: {'lr': 0.00022658387105359255, 'samples': 15440640, 'steps': 80419, 'loss/train': 0.9975003600120544} 08/31/2021 03:47:10 - INFO - __main__ - Step 80421: {'lr': 0.0002265785876439456, 'samples': 15440832, 'steps': 80420, 'loss/train': 1.3634190559387207} 08/31/2021 03:47:10 - INFO - __main__ - Step 80422: {'lr': 0.00022657330424485196, 'samples': 15441024, 'steps': 80421, 'loss/train': 1.1789473295211792} 08/31/2021 03:47:11 - INFO - __main__ - Step 80423: {'lr': 0.00022656802085631403, 'samples': 15441216, 'steps': 80422, 'loss/train': 1.060853123664856} 08/31/2021 03:47:11 - INFO - __main__ - Step 80424: {'lr': 0.0002265627374783342, 'samples': 15441408, 'steps': 80423, 'loss/train': 2.23832368850708} 08/31/2021 03:47:11 - INFO - __main__ - Step 80425: {'lr': 0.00022655745411091484, 'samples': 15441600, 'steps': 80424, 'loss/train': 1.0980029106140137} 08/31/2021 03:47:13 - INFO - __main__ - Step 80426: {'lr': 0.0002265521707540583, 'samples': 15441792, 'steps': 80425, 'loss/train': 0.8004885315895081} 08/31/2021 03:47:13 - INFO - __main__ - Step 80427: {'lr': 0.00022654688740776703, 'samples': 15441984, 'steps': 80426, 'loss/train': 0.8824889063835144} 08/31/2021 03:47:14 - INFO - __main__ - Step 80428: {'lr': 0.00022654160407204336, 'samples': 15442176, 'steps': 80427, 'loss/train': 1.1081018447875977} 08/31/2021 03:47:14 - INFO - __main__ - Step 80429: {'lr': 0.0002265363207468897, 'samples': 15442368, 'steps': 80428, 'loss/train': 1.2718346118927002} 08/31/2021 03:47:15 - INFO - __main__ - Step 80430: {'lr': 0.00022653103743230834, 'samples': 15442560, 'steps': 80429, 'loss/train': 1.1636981964111328} 08/31/2021 03:47:15 - INFO - __main__ - Step 80431: {'lr': 0.0002265257541283018, 'samples': 15442752, 'steps': 80430, 'loss/train': 0.7589371800422668} 08/31/2021 03:47:16 - INFO - __main__ - Step 80432: {'lr': 0.0002265204708348725, 'samples': 15442944, 'steps': 80431, 'loss/train': 1.4347156286239624} 08/31/2021 03:47:17 - INFO - __main__ - Step 80433: {'lr': 0.00022651518755202255, 'samples': 15443136, 'steps': 80432, 'loss/train': 1.1943777799606323} 08/31/2021 03:47:17 - INFO - __main__ - Step 80434: {'lr': 0.00022650990427975455, 'samples': 15443328, 'steps': 80433, 'loss/train': 1.265310287475586} 08/31/2021 03:47:17 - INFO - __main__ - Step 80435: {'lr': 0.0002265046210180708, 'samples': 15443520, 'steps': 80434, 'loss/train': 1.0030115842819214} 08/31/2021 03:47:18 - INFO - __main__ - Step 80436: {'lr': 0.0002264993377669737, 'samples': 15443712, 'steps': 80435, 'loss/train': 1.431503176689148} 08/31/2021 03:47:20 - INFO - __main__ - Step 80437: {'lr': 0.00022649405452646566, 'samples': 15443904, 'steps': 80436, 'loss/train': 1.297683596611023} 08/31/2021 03:47:20 - INFO - __main__ - Step 80438: {'lr': 0.000226488771296549, 'samples': 15444096, 'steps': 80437, 'loss/train': 1.2356493473052979} 08/31/2021 03:47:21 - INFO - __main__ - Step 80439: {'lr': 0.00022648348807722618, 'samples': 15444288, 'steps': 80438, 'loss/train': 1.6222885847091675} 08/31/2021 03:47:21 - INFO - __main__ - Step 80440: {'lr': 0.0002264782048684995, 'samples': 15444480, 'steps': 80439, 'loss/train': 1.780052900314331} 08/31/2021 03:47:21 - INFO - __main__ - Step 80441: {'lr': 0.00022647292167037142, 'samples': 15444672, 'steps': 80440, 'loss/train': 1.5692214965820312} 08/31/2021 03:47:22 - INFO - __main__ - Step 80442: {'lr': 0.00022646763848284423, 'samples': 15444864, 'steps': 80441, 'loss/train': 0.5888813734054565} 08/31/2021 03:47:22 - INFO - __main__ - Step 80443: {'lr': 0.00022646235530592037, 'samples': 15445056, 'steps': 80442, 'loss/train': 1.2238746881484985} 08/31/2021 03:47:24 - INFO - __main__ - Step 80444: {'lr': 0.00022645707213960224, 'samples': 15445248, 'steps': 80443, 'loss/train': 1.3822394609451294} 08/31/2021 03:47:24 - INFO - __main__ - Step 80445: {'lr': 0.0002264517889838923, 'samples': 15445440, 'steps': 80444, 'loss/train': 1.3743236064910889} 08/31/2021 03:47:24 - INFO - __main__ - Step 80446: {'lr': 0.00022644650583879267, 'samples': 15445632, 'steps': 80445, 'loss/train': 1.2160906791687012} 08/31/2021 03:47:25 - INFO - __main__ - Step 80447: {'lr': 0.00022644122270430592, 'samples': 15445824, 'steps': 80446, 'loss/train': 0.49083763360977173} 08/31/2021 03:47:25 - INFO - __main__ - Step 80448: {'lr': 0.00022643593958043438, 'samples': 15446016, 'steps': 80447, 'loss/train': 0.9287059903144836} 08/31/2021 03:47:27 - INFO - __main__ - Step 80449: {'lr': 0.0002264306564671804, 'samples': 15446208, 'steps': 80448, 'loss/train': 1.4358805418014526} 08/31/2021 03:47:27 - INFO - __main__ - Step 80450: {'lr': 0.00022642537336454646, 'samples': 15446400, 'steps': 80449, 'loss/train': 1.199231743812561} 08/31/2021 03:47:27 - INFO - __main__ - Step 80451: {'lr': 0.00022642009027253485, 'samples': 15446592, 'steps': 80450, 'loss/train': 1.3009940385818481} 08/31/2021 03:47:28 - INFO - __main__ - Step 80452: {'lr': 0.00022641480719114802, 'samples': 15446784, 'steps': 80451, 'loss/train': 1.4816206693649292} 08/31/2021 03:47:28 - INFO - __main__ - Step 80453: {'lr': 0.0002264095241203883, 'samples': 15446976, 'steps': 80452, 'loss/train': 1.4165822267532349} 08/31/2021 03:47:30 - INFO - __main__ - Step 80454: {'lr': 0.00022640424106025805, 'samples': 15447168, 'steps': 80453, 'loss/train': 1.2497999668121338} 08/31/2021 03:47:30 - INFO - __main__ - Step 80455: {'lr': 0.00022639895801075972, 'samples': 15447360, 'steps': 80454, 'loss/train': 0.7470714449882507} 08/31/2021 03:47:31 - INFO - __main__ - Step 80456: {'lr': 0.00022639367497189565, 'samples': 15447552, 'steps': 80455, 'loss/train': 0.9023649096488953} 08/31/2021 03:47:31 - INFO - __main__ - Step 80457: {'lr': 0.0002263883919436682, 'samples': 15447744, 'steps': 80456, 'loss/train': 1.2308794260025024} 08/31/2021 03:47:31 - INFO - __main__ - Step 80458: {'lr': 0.0002263831089260799, 'samples': 15447936, 'steps': 80457, 'loss/train': 0.9016671180725098} 08/31/2021 03:47:33 - INFO - __main__ - Step 80459: {'lr': 0.0002263778259191329, 'samples': 15448128, 'steps': 80458, 'loss/train': 0.5605975985527039} 08/31/2021 03:47:33 - INFO - __main__ - Step 80460: {'lr': 0.0002263725429228297, 'samples': 15448320, 'steps': 80459, 'loss/train': 0.8812772631645203} 08/31/2021 03:47:34 - INFO - __main__ - Step 80461: {'lr': 0.00022636725993717267, 'samples': 15448512, 'steps': 80460, 'loss/train': 0.8397336006164551} 08/31/2021 03:47:34 - INFO - __main__ - Step 80462: {'lr': 0.00022636197696216415, 'samples': 15448704, 'steps': 80461, 'loss/train': 1.8838436603546143} 08/31/2021 03:47:34 - INFO - __main__ - Step 80463: {'lr': 0.00022635669399780658, 'samples': 15448896, 'steps': 80462, 'loss/train': 1.2697910070419312} 08/31/2021 03:47:35 - INFO - __main__ - Step 80464: {'lr': 0.00022635141104410234, 'samples': 15449088, 'steps': 80463, 'loss/train': 0.5779284834861755} 08/31/2021 03:47:36 - INFO - __main__ - Step 80465: {'lr': 0.00022634612810105376, 'samples': 15449280, 'steps': 80464, 'loss/train': 1.148965835571289} 08/31/2021 03:47:37 - INFO - __main__ - Step 80466: {'lr': 0.00022634084516866328, 'samples': 15449472, 'steps': 80465, 'loss/train': 1.5187259912490845} 08/31/2021 03:47:37 - INFO - __main__ - Step 80467: {'lr': 0.0002263355622469332, 'samples': 15449664, 'steps': 80466, 'loss/train': 0.6286671161651611} 08/31/2021 03:47:37 - INFO - __main__ - Step 80468: {'lr': 0.000226330279335866, 'samples': 15449856, 'steps': 80467, 'loss/train': 1.1618101596832275} 08/31/2021 03:47:38 - INFO - __main__ - Step 80469: {'lr': 0.000226324996435464, 'samples': 15450048, 'steps': 80468, 'loss/train': 1.0364189147949219} 08/31/2021 03:47:39 - INFO - __main__ - Step 80470: {'lr': 0.00022631971354572964, 'samples': 15450240, 'steps': 80469, 'loss/train': 1.0962527990341187} 08/31/2021 03:47:40 - INFO - __main__ - Step 80471: {'lr': 0.00022631443066666517, 'samples': 15450432, 'steps': 80470, 'loss/train': 1.5905463695526123} 08/31/2021 03:47:40 - INFO - __main__ - Step 80472: {'lr': 0.00022630914779827316, 'samples': 15450624, 'steps': 80471, 'loss/train': 1.2769596576690674} 08/31/2021 03:47:41 - INFO - __main__ - Step 80473: {'lr': 0.0002263038649405558, 'samples': 15450816, 'steps': 80472, 'loss/train': 1.0472129583358765} 08/31/2021 03:47:41 - INFO - __main__ - Step 80474: {'lr': 0.00022629858209351555, 'samples': 15451008, 'steps': 80473, 'loss/train': 1.0443791151046753} 08/31/2021 03:47:43 - INFO - __main__ - Step 80475: {'lr': 0.0002262932992571548, 'samples': 15451200, 'steps': 80474, 'loss/train': 1.0304853916168213} 08/31/2021 03:47:44 - INFO - __main__ - Step 80476: {'lr': 0.00022628801643147592, 'samples': 15451392, 'steps': 80475, 'loss/train': 0.9425867795944214} 08/31/2021 03:47:44 - INFO - __main__ - Step 80477: {'lr': 0.0002262827336164813, 'samples': 15451584, 'steps': 80476, 'loss/train': 1.8897976875305176} 08/31/2021 03:47:44 - INFO - __main__ - Step 80478: {'lr': 0.0002262774508121733, 'samples': 15451776, 'steps': 80477, 'loss/train': 1.8206679821014404} 08/31/2021 03:47:45 - INFO - __main__ - Step 80479: {'lr': 0.00022627216801855433, 'samples': 15451968, 'steps': 80478, 'loss/train': 1.3516676425933838} 08/31/2021 03:47:46 - INFO - __main__ - Step 80480: {'lr': 0.00022626688523562675, 'samples': 15452160, 'steps': 80479, 'loss/train': 1.4036787748336792} 08/31/2021 03:47:47 - INFO - __main__ - Step 80481: {'lr': 0.000226261602463393, 'samples': 15452352, 'steps': 80480, 'loss/train': 1.2712336778640747} 08/31/2021 03:47:47 - INFO - __main__ - Step 80482: {'lr': 0.00022625631970185533, 'samples': 15452544, 'steps': 80481, 'loss/train': 1.1307094097137451} 08/31/2021 03:47:47 - INFO - __main__ - Step 80483: {'lr': 0.00022625103695101623, 'samples': 15452736, 'steps': 80482, 'loss/train': 1.3626912832260132} 08/31/2021 03:47:48 - INFO - __main__ - Step 80484: {'lr': 0.00022624575421087802, 'samples': 15452928, 'steps': 80483, 'loss/train': 0.890728235244751} 08/31/2021 03:47:48 - INFO - __main__ - Step 80485: {'lr': 0.00022624047148144316, 'samples': 15453120, 'steps': 80484, 'loss/train': 0.9792782068252563} 08/31/2021 03:47:49 - INFO - __main__ - Step 80486: {'lr': 0.00022623518876271396, 'samples': 15453312, 'steps': 80485, 'loss/train': 0.9885280132293701} 08/31/2021 03:47:50 - INFO - __main__ - Step 80487: {'lr': 0.0002262299060546928, 'samples': 15453504, 'steps': 80486, 'loss/train': 0.23532718420028687} 08/31/2021 03:47:50 - INFO - __main__ - Step 80488: {'lr': 0.00022622462335738206, 'samples': 15453696, 'steps': 80487, 'loss/train': 0.7565787434577942} 08/31/2021 03:47:51 - INFO - __main__ - Step 80489: {'lr': 0.00022621934067078414, 'samples': 15453888, 'steps': 80488, 'loss/train': 0.9298197031021118} 08/31/2021 03:47:51 - INFO - __main__ - Step 80490: {'lr': 0.00022621405799490142, 'samples': 15454080, 'steps': 80489, 'loss/train': 1.6018168926239014} 08/31/2021 03:47:53 - INFO - __main__ - Step 80491: {'lr': 0.0002262087753297363, 'samples': 15454272, 'steps': 80490, 'loss/train': 0.43257936835289} 08/31/2021 03:47:53 - INFO - __main__ - Step 80492: {'lr': 0.00022620349267529118, 'samples': 15454464, 'steps': 80491, 'loss/train': 1.1539461612701416} 08/31/2021 03:47:53 - INFO - __main__ - Step 80493: {'lr': 0.00022619821003156833, 'samples': 15454656, 'steps': 80492, 'loss/train': 1.2247822284698486} 08/31/2021 03:47:54 - INFO - __main__ - Step 80494: {'lr': 0.0002261929273985702, 'samples': 15454848, 'steps': 80493, 'loss/train': 0.6686322093009949} 08/31/2021 03:47:54 - INFO - __main__ - Step 80495: {'lr': 0.0002261876447762992, 'samples': 15455040, 'steps': 80494, 'loss/train': 0.8413817286491394} 08/31/2021 03:47:55 - INFO - __main__ - Step 80496: {'lr': 0.00022618236216475767, 'samples': 15455232, 'steps': 80495, 'loss/train': 1.4987176656723022} 08/31/2021 03:47:56 - INFO - __main__ - Step 80497: {'lr': 0.00022617707956394797, 'samples': 15455424, 'steps': 80496, 'loss/train': 4.76939582824707} 08/31/2021 03:47:56 - INFO - __main__ - Step 80498: {'lr': 0.00022617179697387253, 'samples': 15455616, 'steps': 80497, 'loss/train': 1.5727354288101196} 08/31/2021 03:47:57 - INFO - __main__ - Step 80499: {'lr': 0.00022616651439453375, 'samples': 15455808, 'steps': 80498, 'loss/train': 1.56640625} 08/31/2021 03:47:57 - INFO - __main__ - Step 80500: {'lr': 0.00022616123182593394, 'samples': 15456000, 'steps': 80499, 'loss/train': 0.5903204083442688} 08/31/2021 03:47:58 - INFO - __main__ - Step 80501: {'lr': 0.00022615594926807551, 'samples': 15456192, 'steps': 80500, 'loss/train': 1.5972254276275635} 08/31/2021 03:47:59 - INFO - __main__ - Step 80502: {'lr': 0.00022615066672096082, 'samples': 15456384, 'steps': 80501, 'loss/train': 0.6881862282752991} 08/31/2021 03:47:59 - INFO - __main__ - Step 80503: {'lr': 0.00022614538418459234, 'samples': 15456576, 'steps': 80502, 'loss/train': 1.4253088235855103} 08/31/2021 03:48:00 - INFO - __main__ - Step 80504: {'lr': 0.00022614010165897234, 'samples': 15456768, 'steps': 80503, 'loss/train': 1.6975817680358887} 08/31/2021 03:48:00 - INFO - __main__ - Step 80505: {'lr': 0.00022613481914410323, 'samples': 15456960, 'steps': 80504, 'loss/train': 1.4198309183120728} 08/31/2021 03:48:02 - INFO - __main__ - Step 80506: {'lr': 0.0002261295366399874, 'samples': 15457152, 'steps': 80505, 'loss/train': 1.2877446413040161} 08/31/2021 03:48:02 - INFO - __main__ - Step 80507: {'lr': 0.00022612425414662724, 'samples': 15457344, 'steps': 80506, 'loss/train': 1.128322958946228} 08/31/2021 03:48:02 - INFO - __main__ - Step 80508: {'lr': 0.00022611897166402512, 'samples': 15457536, 'steps': 80507, 'loss/train': 1.5571905374526978} 08/31/2021 03:48:03 - INFO - __main__ - Step 80509: {'lr': 0.00022611368919218342, 'samples': 15457728, 'steps': 80508, 'loss/train': 1.2821877002716064} 08/31/2021 03:48:03 - INFO - __main__ - Step 80510: {'lr': 0.00022610840673110454, 'samples': 15457920, 'steps': 80509, 'loss/train': 1.4293984174728394} 08/31/2021 03:48:04 - INFO - __main__ - Step 80511: {'lr': 0.0002261031242807908, 'samples': 15458112, 'steps': 80510, 'loss/train': 1.0904362201690674} 08/31/2021 03:48:05 - INFO - __main__ - Step 80512: {'lr': 0.00022609784184124472, 'samples': 15458304, 'steps': 80511, 'loss/train': 1.022161602973938} 08/31/2021 03:48:05 - INFO - __main__ - Step 80513: {'lr': 0.0002260925594124685, 'samples': 15458496, 'steps': 80512, 'loss/train': 1.4225952625274658} 08/31/2021 03:48:06 - INFO - __main__ - Step 80514: {'lr': 0.0002260872769944647, 'samples': 15458688, 'steps': 80513, 'loss/train': 0.970007598400116} 08/31/2021 03:48:06 - INFO - __main__ - Step 80515: {'lr': 0.0002260819945872355, 'samples': 15458880, 'steps': 80514, 'loss/train': 1.2660959959030151} 08/31/2021 03:48:06 - INFO - __main__ - Step 80516: {'lr': 0.00022607671219078342, 'samples': 15459072, 'steps': 80515, 'loss/train': 1.2552602291107178} 08/31/2021 03:48:08 - INFO - __main__ - Step 80517: {'lr': 0.00022607142980511077, 'samples': 15459264, 'steps': 80516, 'loss/train': 0.9029548764228821} 08/31/2021 03:48:08 - INFO - __main__ - Step 80518: {'lr': 0.00022606614743021997, 'samples': 15459456, 'steps': 80517, 'loss/train': 1.0460423231124878} 08/31/2021 03:48:09 - INFO - __main__ - Step 80519: {'lr': 0.00022606086506611343, 'samples': 15459648, 'steps': 80518, 'loss/train': 1.4316725730895996} 08/31/2021 03:48:09 - INFO - __main__ - Step 80520: {'lr': 0.00022605558271279348, 'samples': 15459840, 'steps': 80519, 'loss/train': 0.5609607100486755} 08/31/2021 03:48:09 - INFO - __main__ - Step 80521: {'lr': 0.0002260503003702625, 'samples': 15460032, 'steps': 80520, 'loss/train': 1.885536789894104} 08/31/2021 03:48:11 - INFO - __main__ - Step 80522: {'lr': 0.0002260450180385229, 'samples': 15460224, 'steps': 80521, 'loss/train': 1.222746729850769} 08/31/2021 03:48:11 - INFO - __main__ - Step 80523: {'lr': 0.000226039735717577, 'samples': 15460416, 'steps': 80522, 'loss/train': 1.296339988708496} 08/31/2021 03:48:12 - INFO - __main__ - Step 80524: {'lr': 0.00022603445340742728, 'samples': 15460608, 'steps': 80523, 'loss/train': 0.8274482488632202} 08/31/2021 03:48:12 - INFO - __main__ - Step 80525: {'lr': 0.00022602917110807605, 'samples': 15460800, 'steps': 80524, 'loss/train': 0.676497757434845} 08/31/2021 03:48:12 - INFO - __main__ - Step 80526: {'lr': 0.00022602388881952582, 'samples': 15460992, 'steps': 80525, 'loss/train': 0.9378032684326172} 08/31/2021 03:48:14 - INFO - __main__ - Step 80527: {'lr': 0.00022601860654177875, 'samples': 15461184, 'steps': 80526, 'loss/train': 0.1497090458869934} 08/31/2021 03:48:14 - INFO - __main__ - Step 80528: {'lr': 0.00022601332427483732, 'samples': 15461376, 'steps': 80527, 'loss/train': 0.21093766391277313} 08/31/2021 03:48:14 - INFO - __main__ - Step 80529: {'lr': 0.0002260080420187039, 'samples': 15461568, 'steps': 80528, 'loss/train': 1.9445970058441162} 08/31/2021 03:48:15 - INFO - __main__ - Step 80530: {'lr': 0.0002260027597733809, 'samples': 15461760, 'steps': 80529, 'loss/train': 0.9577471017837524} 08/31/2021 03:48:15 - INFO - __main__ - Step 80531: {'lr': 0.00022599747753887067, 'samples': 15461952, 'steps': 80530, 'loss/train': 1.4686305522918701} 08/31/2021 03:48:17 - INFO - __main__ - Step 80532: {'lr': 0.00022599219531517565, 'samples': 15462144, 'steps': 80531, 'loss/train': 1.3195245265960693} 08/31/2021 03:48:18 - INFO - __main__ - Step 80533: {'lr': 0.00022598691310229813, 'samples': 15462336, 'steps': 80532, 'loss/train': 0.6071151494979858} 08/31/2021 03:48:18 - INFO - __main__ - Step 80534: {'lr': 0.00022598163090024054, 'samples': 15462528, 'steps': 80533, 'loss/train': 1.1654181480407715} 08/31/2021 03:48:18 - INFO - __main__ - Step 80535: {'lr': 0.0002259763487090053, 'samples': 15462720, 'steps': 80534, 'loss/train': 0.897919774055481} 08/31/2021 03:48:19 - INFO - __main__ - Step 80536: {'lr': 0.0002259710665285947, 'samples': 15462912, 'steps': 80535, 'loss/train': 1.0545352697372437} 08/31/2021 03:48:20 - INFO - __main__ - Step 80537: {'lr': 0.00022596578435901118, 'samples': 15463104, 'steps': 80536, 'loss/train': 0.6782373189926147} 08/31/2021 03:48:21 - INFO - __main__ - Step 80538: {'lr': 0.00022596050220025714, 'samples': 15463296, 'steps': 80537, 'loss/train': 1.5414983034133911} 08/31/2021 03:48:21 - INFO - __main__ - Step 80539: {'lr': 0.00022595522005233498, 'samples': 15463488, 'steps': 80538, 'loss/train': 1.4745277166366577} 08/31/2021 03:48:21 - INFO - __main__ - Step 80540: {'lr': 0.00022594993791524696, 'samples': 15463680, 'steps': 80539, 'loss/train': 1.2624963521957397} 08/31/2021 03:48:22 - INFO - __main__ - Step 80541: {'lr': 0.0002259446557889955, 'samples': 15463872, 'steps': 80540, 'loss/train': 0.7873784899711609} 08/31/2021 03:48:23 - INFO - __main__ - Step 80542: {'lr': 0.00022593937367358302, 'samples': 15464064, 'steps': 80541, 'loss/train': 0.03132600709795952} 08/31/2021 03:48:24 - INFO - __main__ - Step 80543: {'lr': 0.00022593409156901188, 'samples': 15464256, 'steps': 80542, 'loss/train': 2.1179745197296143} 08/31/2021 03:48:24 - INFO - __main__ - Step 80544: {'lr': 0.00022592880947528446, 'samples': 15464448, 'steps': 80543, 'loss/train': 1.3935209512710571} 08/31/2021 03:48:25 - INFO - __main__ - Step 80545: {'lr': 0.00022592352739240318, 'samples': 15464640, 'steps': 80544, 'loss/train': 1.4056308269500732} 08/31/2021 03:48:25 - INFO - __main__ - Step 80546: {'lr': 0.00022591824532037036, 'samples': 15464832, 'steps': 80545, 'loss/train': 1.6491918563842773} 08/31/2021 03:48:25 - INFO - __main__ - Step 80547: {'lr': 0.0002259129632591884, 'samples': 15465024, 'steps': 80546, 'loss/train': 0.2722786068916321} 08/31/2021 03:48:27 - INFO - __main__ - Step 80548: {'lr': 0.0002259076812088597, 'samples': 15465216, 'steps': 80547, 'loss/train': 1.3468143939971924} 08/31/2021 03:48:27 - INFO - __main__ - Step 80549: {'lr': 0.0002259023991693866, 'samples': 15465408, 'steps': 80548, 'loss/train': 1.0420334339141846} 08/31/2021 03:48:28 - INFO - __main__ - Step 80550: {'lr': 0.00022589711714077158, 'samples': 15465600, 'steps': 80549, 'loss/train': 1.2543059587478638} 08/31/2021 03:48:28 - INFO - __main__ - Step 80551: {'lr': 0.0002258918351230169, 'samples': 15465792, 'steps': 80550, 'loss/train': 0.9639849066734314} 08/31/2021 03:48:28 - INFO - __main__ - Step 80552: {'lr': 0.00022588655311612496, 'samples': 15465984, 'steps': 80551, 'loss/train': 1.426984429359436} 08/31/2021 03:48:30 - INFO - __main__ - Step 80553: {'lr': 0.0002258812711200983, 'samples': 15466176, 'steps': 80552, 'loss/train': 1.273228645324707} 08/31/2021 03:48:30 - INFO - __main__ - Step 80554: {'lr': 0.0002258759891349391, 'samples': 15466368, 'steps': 80553, 'loss/train': 1.5627416372299194} 08/31/2021 03:48:31 - INFO - __main__ - Step 80555: {'lr': 0.00022587070716064976, 'samples': 15466560, 'steps': 80554, 'loss/train': 0.9725797772407532} 08/31/2021 03:48:31 - INFO - __main__ - Step 80556: {'lr': 0.0002258654251972327, 'samples': 15466752, 'steps': 80555, 'loss/train': 1.3043776750564575} 08/31/2021 03:48:31 - INFO - __main__ - Step 80557: {'lr': 0.00022586014324469034, 'samples': 15466944, 'steps': 80556, 'loss/train': 1.023862361907959} 08/31/2021 03:48:33 - INFO - __main__ - Step 80558: {'lr': 0.00022585486130302502, 'samples': 15467136, 'steps': 80557, 'loss/train': 0.9125195145606995} 08/31/2021 03:48:33 - INFO - __main__ - Step 80559: {'lr': 0.0002258495793722391, 'samples': 15467328, 'steps': 80558, 'loss/train': 2.01806378364563} 08/31/2021 03:48:34 - INFO - __main__ - Step 80560: {'lr': 0.000225844297452335, 'samples': 15467520, 'steps': 80559, 'loss/train': 1.1898869276046753} 08/31/2021 03:48:34 - INFO - __main__ - Step 80561: {'lr': 0.0002258390155433151, 'samples': 15467712, 'steps': 80560, 'loss/train': 1.9585745334625244} 08/31/2021 03:48:34 - INFO - __main__ - Step 80562: {'lr': 0.00022583373364518176, 'samples': 15467904, 'steps': 80561, 'loss/train': 1.353134274482727} 08/31/2021 03:48:36 - INFO - __main__ - Step 80563: {'lr': 0.00022582845175793734, 'samples': 15468096, 'steps': 80562, 'loss/train': 1.0048613548278809} 08/31/2021 03:48:36 - INFO - __main__ - Step 80564: {'lr': 0.00022582316988158427, 'samples': 15468288, 'steps': 80563, 'loss/train': 1.2930457592010498} 08/31/2021 03:48:37 - INFO - __main__ - Step 80565: {'lr': 0.00022581788801612492, 'samples': 15468480, 'steps': 80564, 'loss/train': 1.3237061500549316} 08/31/2021 03:48:37 - INFO - __main__ - Step 80566: {'lr': 0.00022581260616156177, 'samples': 15468672, 'steps': 80565, 'loss/train': 1.595760703086853} 08/31/2021 03:48:37 - INFO - __main__ - Step 80567: {'lr': 0.00022580732431789693, 'samples': 15468864, 'steps': 80566, 'loss/train': 0.6413630843162537} 08/31/2021 03:48:38 - INFO - __main__ - Step 80568: {'lr': 0.00022580204248513297, 'samples': 15469056, 'steps': 80567, 'loss/train': 1.3964953422546387} 08/31/2021 03:48:39 - INFO - __main__ - Step 80569: {'lr': 0.00022579676066327226, 'samples': 15469248, 'steps': 80568, 'loss/train': 0.7687377333641052} 08/31/2021 03:48:40 - INFO - __main__ - Step 80570: {'lr': 0.0002257914788523171, 'samples': 15469440, 'steps': 80569, 'loss/train': 1.1269723176956177} 08/31/2021 03:48:40 - INFO - __main__ - Step 80571: {'lr': 0.00022578619705226996, 'samples': 15469632, 'steps': 80570, 'loss/train': 1.155015230178833} 08/31/2021 03:48:40 - INFO - __main__ - Step 80572: {'lr': 0.00022578091526313318, 'samples': 15469824, 'steps': 80571, 'loss/train': 1.2553915977478027} 08/31/2021 03:48:41 - INFO - __main__ - Step 80573: {'lr': 0.00022577563348490914, 'samples': 15470016, 'steps': 80572, 'loss/train': 1.1924899816513062} 08/31/2021 03:48:42 - INFO - __main__ - Step 80574: {'lr': 0.00022577035171760025, 'samples': 15470208, 'steps': 80573, 'loss/train': 1.318561315536499} 08/31/2021 03:48:43 - INFO - __main__ - Step 80575: {'lr': 0.00022576506996120884, 'samples': 15470400, 'steps': 80574, 'loss/train': 1.234424114227295} 08/31/2021 03:48:43 - INFO - __main__ - Step 80576: {'lr': 0.00022575978821573733, 'samples': 15470592, 'steps': 80575, 'loss/train': 1.9419933557510376} 08/31/2021 03:48:43 - INFO - __main__ - Step 80577: {'lr': 0.0002257545064811881, 'samples': 15470784, 'steps': 80576, 'loss/train': 1.6270883083343506} 08/31/2021 03:48:44 - INFO - __main__ - Step 80578: {'lr': 0.0002257492247575635, 'samples': 15470976, 'steps': 80577, 'loss/train': 2.0671029090881348} 08/31/2021 03:48:46 - INFO - __main__ - Step 80579: {'lr': 0.000225743943044866, 'samples': 15471168, 'steps': 80578, 'loss/train': 1.74330472946167} 08/31/2021 03:48:46 - INFO - __main__ - Step 80580: {'lr': 0.00022573866134309784, 'samples': 15471360, 'steps': 80579, 'loss/train': 1.228745698928833} 08/31/2021 03:48:47 - INFO - __main__ - Step 80581: {'lr': 0.00022573337965226144, 'samples': 15471552, 'steps': 80580, 'loss/train': 1.0917855501174927} 08/31/2021 03:48:47 - INFO - __main__ - Step 80582: {'lr': 0.00022572809797235922, 'samples': 15471744, 'steps': 80581, 'loss/train': 1.0458098649978638} 08/31/2021 03:48:47 - INFO - __main__ - Step 80583: {'lr': 0.00022572281630339354, 'samples': 15471936, 'steps': 80582, 'loss/train': 1.4399493932724} 08/31/2021 03:48:49 - INFO - __main__ - Step 80584: {'lr': 0.00022571753464536675, 'samples': 15472128, 'steps': 80583, 'loss/train': 1.2231180667877197} 08/31/2021 03:48:50 - INFO - __main__ - Step 80585: {'lr': 0.00022571225299828132, 'samples': 15472320, 'steps': 80584, 'loss/train': 0.5437309741973877} 08/31/2021 03:48:50 - INFO - __main__ - Step 80586: {'lr': 0.00022570697136213956, 'samples': 15472512, 'steps': 80585, 'loss/train': 1.1149216890335083} 08/31/2021 03:48:50 - INFO - __main__ - Step 80587: {'lr': 0.00022570168973694386, 'samples': 15472704, 'steps': 80586, 'loss/train': 1.1429688930511475} 08/31/2021 03:48:51 - INFO - __main__ - Step 80588: {'lr': 0.00022569640812269658, 'samples': 15472896, 'steps': 80587, 'loss/train': 1.295583724975586} 08/31/2021 03:48:52 - INFO - __main__ - Step 80589: {'lr': 0.00022569112651940016, 'samples': 15473088, 'steps': 80588, 'loss/train': 0.10093934834003448} 08/31/2021 03:48:53 - INFO - __main__ - Step 80590: {'lr': 0.00022568584492705691, 'samples': 15473280, 'steps': 80589, 'loss/train': 1.0266159772872925} 08/31/2021 03:48:53 - INFO - __main__ - Step 80591: {'lr': 0.0002256805633456693, 'samples': 15473472, 'steps': 80590, 'loss/train': 0.6641771793365479} 08/31/2021 03:48:54 - INFO - __main__ - Step 80592: {'lr': 0.00022567528177523959, 'samples': 15473664, 'steps': 80591, 'loss/train': 1.4023247957229614} 08/31/2021 03:48:54 - INFO - __main__ - Step 80593: {'lr': 0.00022567000021577033, 'samples': 15473856, 'steps': 80592, 'loss/train': 0.19285491108894348} 08/31/2021 03:48:54 - INFO - __main__ - Step 80594: {'lr': 0.0002256647186672637, 'samples': 15474048, 'steps': 80593, 'loss/train': 1.2877918481826782} 08/31/2021 03:48:56 - INFO - __main__ - Step 80595: {'lr': 0.0002256594371297222, 'samples': 15474240, 'steps': 80594, 'loss/train': 1.2776238918304443} 08/31/2021 03:48:56 - INFO - __main__ - Step 80596: {'lr': 0.00022565415560314814, 'samples': 15474432, 'steps': 80595, 'loss/train': 1.4730802774429321} 08/31/2021 03:48:57 - INFO - __main__ - Step 80597: {'lr': 0.00022564887408754397, 'samples': 15474624, 'steps': 80596, 'loss/train': 1.1440608501434326} 08/31/2021 03:48:57 - INFO - __main__ - Step 80598: {'lr': 0.00022564359258291203, 'samples': 15474816, 'steps': 80597, 'loss/train': 0.05499187856912613} 08/31/2021 03:48:57 - INFO - __main__ - Step 80599: {'lr': 0.00022563831108925474, 'samples': 15475008, 'steps': 80598, 'loss/train': 1.0744999647140503} 08/31/2021 03:48:59 - INFO - __main__ - Step 80600: {'lr': 0.00022563302960657442, 'samples': 15475200, 'steps': 80599, 'loss/train': 1.6968271732330322} 08/31/2021 03:48:59 - INFO - __main__ - Step 80601: {'lr': 0.00022562774813487347, 'samples': 15475392, 'steps': 80600, 'loss/train': 1.4081873893737793} 08/31/2021 03:49:00 - INFO - __main__ - Step 80602: {'lr': 0.00022562246667415432, 'samples': 15475584, 'steps': 80601, 'loss/train': 0.830060601234436} 08/31/2021 03:49:00 - INFO - __main__ - Step 80603: {'lr': 0.00022561718522441928, 'samples': 15475776, 'steps': 80602, 'loss/train': 0.9550079703330994} 08/31/2021 03:49:00 - INFO - __main__ - Step 80604: {'lr': 0.00022561190378567075, 'samples': 15475968, 'steps': 80603, 'loss/train': 1.1363182067871094} 08/31/2021 03:49:02 - INFO - __main__ - Step 80605: {'lr': 0.0002256066223579112, 'samples': 15476160, 'steps': 80604, 'loss/train': 1.2009903192520142} 08/31/2021 03:49:03 - INFO - __main__ - Step 80606: {'lr': 0.00022560134094114294, 'samples': 15476352, 'steps': 80605, 'loss/train': 1.641005039215088} 08/31/2021 03:49:03 - INFO - __main__ - Step 80607: {'lr': 0.00022559605953536828, 'samples': 15476544, 'steps': 80606, 'loss/train': 1.1236536502838135} 08/31/2021 03:49:03 - INFO - __main__ - Step 80608: {'lr': 0.00022559077814058963, 'samples': 15476736, 'steps': 80607, 'loss/train': 1.4620466232299805} 08/31/2021 03:49:04 - INFO - __main__ - Step 80609: {'lr': 0.0002255854967568094, 'samples': 15476928, 'steps': 80608, 'loss/train': 0.2183164358139038} 08/31/2021 03:49:04 - INFO - __main__ - Step 80610: {'lr': 0.00022558021538403, 'samples': 15477120, 'steps': 80609, 'loss/train': 1.1032999753952026} 08/31/2021 03:49:06 - INFO - __main__ - Step 80611: {'lr': 0.00022557493402225375, 'samples': 15477312, 'steps': 80610, 'loss/train': 0.10159535706043243} 08/31/2021 03:49:06 - INFO - __main__ - Step 80612: {'lr': 0.00022556965267148308, 'samples': 15477504, 'steps': 80611, 'loss/train': 1.0601613521575928} 08/31/2021 03:49:06 - INFO - __main__ - Step 80613: {'lr': 0.00022556437133172035, 'samples': 15477696, 'steps': 80612, 'loss/train': 1.3275296688079834} 08/31/2021 03:49:07 - INFO - __main__ - Step 80614: {'lr': 0.0002255590900029679, 'samples': 15477888, 'steps': 80613, 'loss/train': 0.9596402645111084} 08/31/2021 03:49:07 - INFO - __main__ - Step 80615: {'lr': 0.00022555380868522818, 'samples': 15478080, 'steps': 80614, 'loss/train': 1.3229601383209229} 08/31/2021 03:49:09 - INFO - __main__ - Step 80616: {'lr': 0.00022554852737850355, 'samples': 15478272, 'steps': 80615, 'loss/train': 1.3244107961654663} 08/31/2021 03:49:09 - INFO - __main__ - Step 80617: {'lr': 0.0002255432460827964, 'samples': 15478464, 'steps': 80616, 'loss/train': 0.04745229706168175} 08/31/2021 03:49:09 - INFO - __main__ - Step 80618: {'lr': 0.00022553796479810902, 'samples': 15478656, 'steps': 80617, 'loss/train': 0.9772336483001709} 08/31/2021 03:49:10 - INFO - __main__ - Step 80619: {'lr': 0.00022553268352444385, 'samples': 15478848, 'steps': 80618, 'loss/train': 1.094949722290039} 08/31/2021 03:49:10 - INFO - __main__ - Step 80620: {'lr': 0.00022552740226180337, 'samples': 15479040, 'steps': 80619, 'loss/train': 1.4868096113204956} 08/31/2021 03:49:12 - INFO - __main__ - Step 80621: {'lr': 0.00022552212101018982, 'samples': 15479232, 'steps': 80620, 'loss/train': 1.0938694477081299} 08/31/2021 03:49:12 - INFO - __main__ - Step 80622: {'lr': 0.00022551683976960557, 'samples': 15479424, 'steps': 80621, 'loss/train': 0.06534896045923233} 08/31/2021 03:49:12 - INFO - __main__ - Step 80623: {'lr': 0.0002255115585400531, 'samples': 15479616, 'steps': 80622, 'loss/train': 0.1796434223651886} 08/31/2021 03:49:13 - INFO - __main__ - Step 80624: {'lr': 0.00022550627732153473, 'samples': 15479808, 'steps': 80623, 'loss/train': 0.9463510513305664} 08/31/2021 03:49:13 - INFO - __main__ - Step 80625: {'lr': 0.00022550099611405285, 'samples': 15480000, 'steps': 80624, 'loss/train': 1.148422122001648} 08/31/2021 03:49:15 - INFO - __main__ - Step 80626: {'lr': 0.00022549571491760985, 'samples': 15480192, 'steps': 80625, 'loss/train': 0.9354197382926941} 08/31/2021 03:49:15 - INFO - __main__ - Step 80627: {'lr': 0.00022549043373220815, 'samples': 15480384, 'steps': 80626, 'loss/train': 0.4495830833911896} 08/31/2021 03:49:16 - INFO - __main__ - Step 80628: {'lr': 0.00022548515255785002, 'samples': 15480576, 'steps': 80627, 'loss/train': 0.03414590656757355} 08/31/2021 03:49:16 - INFO - __main__ - Step 80629: {'lr': 0.0002254798713945379, 'samples': 15480768, 'steps': 80628, 'loss/train': 1.230907917022705} 08/31/2021 03:49:16 - INFO - __main__ - Step 80630: {'lr': 0.0002254745902422742, 'samples': 15480960, 'steps': 80629, 'loss/train': 0.08074115216732025} 08/31/2021 03:49:18 - INFO - __main__ - Step 80631: {'lr': 0.00022546930910106127, 'samples': 15481152, 'steps': 80630, 'loss/train': 0.049991101026535034} 08/31/2021 03:49:18 - INFO - __main__ - Step 80632: {'lr': 0.00022546402797090146, 'samples': 15481344, 'steps': 80631, 'loss/train': 1.855065107345581} 08/31/2021 03:49:19 - INFO - __main__ - Step 80633: {'lr': 0.00022545874685179723, 'samples': 15481536, 'steps': 80632, 'loss/train': 0.7256486415863037} 08/31/2021 03:49:19 - INFO - __main__ - Step 80634: {'lr': 0.00022545346574375088, 'samples': 15481728, 'steps': 80633, 'loss/train': 1.1470766067504883} 08/31/2021 03:49:19 - INFO - __main__ - Step 80635: {'lr': 0.00022544818464676484, 'samples': 15481920, 'steps': 80634, 'loss/train': 0.42017942667007446} 08/31/2021 03:49:21 - INFO - __main__ - Step 80636: {'lr': 0.00022544290356084142, 'samples': 15482112, 'steps': 80635, 'loss/train': 0.6964191794395447} 08/31/2021 03:49:22 - INFO - __main__ - Step 80637: {'lr': 0.00022543762248598316, 'samples': 15482304, 'steps': 80636, 'loss/train': 1.0771926641464233} 08/31/2021 03:49:22 - INFO - __main__ - Step 80638: {'lr': 0.00022543234142219221, 'samples': 15482496, 'steps': 80637, 'loss/train': 1.1170835494995117} 08/31/2021 03:49:23 - INFO - __main__ - Step 80639: {'lr': 0.0002254270603694711, 'samples': 15482688, 'steps': 80638, 'loss/train': 1.3088306188583374} 08/31/2021 03:49:23 - INFO - __main__ - Step 80640: {'lr': 0.00022542177932782217, 'samples': 15482880, 'steps': 80639, 'loss/train': 1.2252579927444458} 08/31/2021 03:49:23 - INFO - __main__ - Step 80641: {'lr': 0.00022541649829724782, 'samples': 15483072, 'steps': 80640, 'loss/train': 1.681516408920288} 08/31/2021 03:49:25 - INFO - __main__ - Step 80642: {'lr': 0.00022541121727775044, 'samples': 15483264, 'steps': 80641, 'loss/train': 0.856115996837616} 08/31/2021 03:49:25 - INFO - __main__ - Step 80643: {'lr': 0.00022540593626933233, 'samples': 15483456, 'steps': 80642, 'loss/train': 1.0503240823745728} 08/31/2021 03:49:25 - INFO - __main__ - Step 80644: {'lr': 0.00022540065527199596, 'samples': 15483648, 'steps': 80643, 'loss/train': 0.7287890911102295} 08/31/2021 03:49:26 - INFO - __main__ - Step 80645: {'lr': 0.00022539537428574365, 'samples': 15483840, 'steps': 80644, 'loss/train': 1.0928493738174438} 08/31/2021 03:49:26 - INFO - __main__ - Step 80646: {'lr': 0.00022539009331057783, 'samples': 15484032, 'steps': 80645, 'loss/train': 1.6381051540374756} 08/31/2021 03:49:28 - INFO - __main__ - Step 80647: {'lr': 0.0002253848123465009, 'samples': 15484224, 'steps': 80646, 'loss/train': 1.1515556573867798} 08/31/2021 03:49:28 - INFO - __main__ - Step 80648: {'lr': 0.00022537953139351518, 'samples': 15484416, 'steps': 80647, 'loss/train': 1.3616204261779785} 08/31/2021 03:49:29 - INFO - __main__ - Step 80649: {'lr': 0.00022537425045162304, 'samples': 15484608, 'steps': 80648, 'loss/train': 1.6900830268859863} 08/31/2021 03:49:29 - INFO - __main__ - Step 80650: {'lr': 0.00022536896952082686, 'samples': 15484800, 'steps': 80649, 'loss/train': 0.4901541471481323} 08/31/2021 03:49:29 - INFO - __main__ - Step 80651: {'lr': 0.00022536368860112904, 'samples': 15484992, 'steps': 80650, 'loss/train': 1.480987787246704} 08/31/2021 03:49:31 - INFO - __main__ - Step 80652: {'lr': 0.000225358407692532, 'samples': 15485184, 'steps': 80651, 'loss/train': 2.2643496990203857} 08/31/2021 03:49:31 - INFO - __main__ - Step 80653: {'lr': 0.00022535312679503803, 'samples': 15485376, 'steps': 80652, 'loss/train': 0.7839251756668091} 08/31/2021 03:49:32 - INFO - __main__ - Step 80654: {'lr': 0.0002253478459086496, 'samples': 15485568, 'steps': 80653, 'loss/train': 1.7473310232162476} 08/31/2021 03:49:32 - INFO - __main__ - Step 80655: {'lr': 0.00022534256503336904, 'samples': 15485760, 'steps': 80654, 'loss/train': 1.381109595298767} 08/31/2021 03:49:32 - INFO - __main__ - Step 80656: {'lr': 0.0002253372841691987, 'samples': 15485952, 'steps': 80655, 'loss/train': 1.6926701068878174} 08/31/2021 03:49:34 - INFO - __main__ - Step 80657: {'lr': 0.00022533200331614103, 'samples': 15486144, 'steps': 80656, 'loss/train': 0.07761619240045547} 08/31/2021 03:49:35 - INFO - __main__ - Step 80658: {'lr': 0.0002253267224741984, 'samples': 15486336, 'steps': 80657, 'loss/train': 3.9558606147766113} 08/31/2021 03:49:35 - INFO - __main__ - Step 80659: {'lr': 0.00022532144164337314, 'samples': 15486528, 'steps': 80658, 'loss/train': 1.5699362754821777} 08/31/2021 03:49:36 - INFO - __main__ - Step 80660: {'lr': 0.00022531616082366776, 'samples': 15486720, 'steps': 80659, 'loss/train': 2.9430673122406006} 08/31/2021 03:49:36 - INFO - __main__ - Step 80661: {'lr': 0.00022531088001508445, 'samples': 15486912, 'steps': 80660, 'loss/train': 2.707381010055542} 08/31/2021 03:49:36 - INFO - __main__ - Step 80662: {'lr': 0.00022530559921762566, 'samples': 15487104, 'steps': 80661, 'loss/train': 1.2140501737594604} 08/31/2021 03:49:38 - INFO - __main__ - Step 80663: {'lr': 0.0002253003184312938, 'samples': 15487296, 'steps': 80662, 'loss/train': 0.8587982058525085} 08/31/2021 03:49:38 - INFO - __main__ - Step 80664: {'lr': 0.00022529503765609125, 'samples': 15487488, 'steps': 80663, 'loss/train': 1.5719084739685059} 08/31/2021 03:49:38 - INFO - __main__ - Step 80665: {'lr': 0.00022528975689202032, 'samples': 15487680, 'steps': 80664, 'loss/train': 0.696437418460846} 08/31/2021 03:49:39 - INFO - __main__ - Step 80666: {'lr': 0.0002252844761390835, 'samples': 15487872, 'steps': 80665, 'loss/train': 1.3085402250289917} 08/31/2021 03:49:39 - INFO - __main__ - Step 80667: {'lr': 0.0002252791953972831, 'samples': 15488064, 'steps': 80666, 'loss/train': 0.8226809501647949} 08/31/2021 03:49:41 - INFO - __main__ - Step 80668: {'lr': 0.0002252739146666215, 'samples': 15488256, 'steps': 80667, 'loss/train': 1.7972980737686157} 08/31/2021 03:49:41 - INFO - __main__ - Step 80669: {'lr': 0.0002252686339471011, 'samples': 15488448, 'steps': 80668, 'loss/train': 1.4583425521850586} 08/31/2021 03:49:41 - INFO - __main__ - Step 80670: {'lr': 0.00022526335323872426, 'samples': 15488640, 'steps': 80669, 'loss/train': 1.5813300609588623} 08/31/2021 03:49:42 - INFO - __main__ - Step 80671: {'lr': 0.0002252580725414934, 'samples': 15488832, 'steps': 80670, 'loss/train': 0.9125874638557434} 08/31/2021 03:49:42 - INFO - __main__ - Step 80672: {'lr': 0.00022525279185541084, 'samples': 15489024, 'steps': 80671, 'loss/train': 1.4076740741729736} 08/31/2021 03:49:44 - INFO - __main__ - Step 80673: {'lr': 0.000225247511180479, 'samples': 15489216, 'steps': 80672, 'loss/train': 0.7555203437805176} 08/31/2021 03:49:44 - INFO - __main__ - Step 80674: {'lr': 0.00022524223051670038, 'samples': 15489408, 'steps': 80673, 'loss/train': 1.2381618022918701} 08/31/2021 03:49:44 - INFO - __main__ - Step 80675: {'lr': 0.0002252369498640771, 'samples': 15489600, 'steps': 80674, 'loss/train': 1.199519395828247} 08/31/2021 03:49:45 - INFO - __main__ - Step 80676: {'lr': 0.00022523166922261165, 'samples': 15489792, 'steps': 80675, 'loss/train': 1.4658759832382202} 08/31/2021 03:49:45 - INFO - __main__ - Step 80677: {'lr': 0.00022522638859230645, 'samples': 15489984, 'steps': 80676, 'loss/train': 1.2941627502441406} 08/31/2021 03:49:45 - INFO - __main__ - Step 80678: {'lr': 0.00022522110797316386, 'samples': 15490176, 'steps': 80677, 'loss/train': 1.2502481937408447} 08/31/2021 03:49:47 - INFO - __main__ - Step 80679: {'lr': 0.00022521582736518625, 'samples': 15490368, 'steps': 80678, 'loss/train': 1.4848166704177856} 08/31/2021 03:49:47 - INFO - __main__ - Step 80680: {'lr': 0.00022521054676837598, 'samples': 15490560, 'steps': 80679, 'loss/train': 1.5537242889404297} 08/31/2021 03:49:48 - INFO - __main__ - Step 80681: {'lr': 0.00022520526618273552, 'samples': 15490752, 'steps': 80680, 'loss/train': 0.7653557062149048} 08/31/2021 03:49:48 - INFO - __main__ - Step 80682: {'lr': 0.00022519998560826713, 'samples': 15490944, 'steps': 80681, 'loss/train': 1.0585585832595825} 08/31/2021 03:49:48 - INFO - __main__ - Step 80683: {'lr': 0.00022519470504497324, 'samples': 15491136, 'steps': 80682, 'loss/train': 1.068650722503662} 08/31/2021 03:49:50 - INFO - __main__ - Step 80684: {'lr': 0.00022518942449285627, 'samples': 15491328, 'steps': 80683, 'loss/train': 1.4741305112838745} 08/31/2021 03:49:50 - INFO - __main__ - Step 80685: {'lr': 0.00022518414395191855, 'samples': 15491520, 'steps': 80684, 'loss/train': 0.6655312776565552} 08/31/2021 03:49:51 - INFO - __main__ - Step 80686: {'lr': 0.00022517886342216247, 'samples': 15491712, 'steps': 80685, 'loss/train': 1.3426302671432495} 08/31/2021 03:49:51 - INFO - __main__ - Step 80687: {'lr': 0.0002251735829035905, 'samples': 15491904, 'steps': 80686, 'loss/train': 1.6304528713226318} 08/31/2021 03:49:51 - INFO - __main__ - Step 80688: {'lr': 0.00022516830239620485, 'samples': 15492096, 'steps': 80687, 'loss/train': 1.0883233547210693} 08/31/2021 03:49:53 - INFO - __main__ - Step 80689: {'lr': 0.00022516302190000794, 'samples': 15492288, 'steps': 80688, 'loss/train': 1.1156011819839478} 08/31/2021 03:49:54 - INFO - __main__ - Step 80690: {'lr': 0.00022515774141500223, 'samples': 15492480, 'steps': 80689, 'loss/train': 1.276424527168274} 08/31/2021 03:49:54 - INFO - __main__ - Step 80691: {'lr': 0.00022515246094119006, 'samples': 15492672, 'steps': 80690, 'loss/train': 1.2331695556640625} 08/31/2021 03:49:55 - INFO - __main__ - Step 80692: {'lr': 0.0002251471804785738, 'samples': 15492864, 'steps': 80691, 'loss/train': 1.4915783405303955} 08/31/2021 03:49:55 - INFO - __main__ - Step 80693: {'lr': 0.00022514190002715582, 'samples': 15493056, 'steps': 80692, 'loss/train': 0.053461067378520966} 08/31/2021 03:49:56 - INFO - __main__ - Step 80694: {'lr': 0.00022513661958693853, 'samples': 15493248, 'steps': 80693, 'loss/train': 0.8780736923217773} 08/31/2021 03:49:57 - INFO - __main__ - Step 80695: {'lr': 0.00022513133915792426, 'samples': 15493440, 'steps': 80694, 'loss/train': 1.0335193872451782} 08/31/2021 03:49:57 - INFO - __main__ - Step 80696: {'lr': 0.0002251260587401155, 'samples': 15493632, 'steps': 80695, 'loss/train': 1.1639175415039062} 08/31/2021 03:49:58 - INFO - __main__ - Step 80697: {'lr': 0.0002251207783335145, 'samples': 15493824, 'steps': 80696, 'loss/train': 1.725623369216919} 08/31/2021 03:49:58 - INFO - __main__ - Step 80698: {'lr': 0.0002251154979381237, 'samples': 15494016, 'steps': 80697, 'loss/train': 0.6625474095344543} 08/31/2021 03:50:00 - INFO - __main__ - Step 80699: {'lr': 0.00022511021755394547, 'samples': 15494208, 'steps': 80698, 'loss/train': 1.813173770904541} 08/31/2021 03:50:00 - INFO - __main__ - Step 80700: {'lr': 0.0002251049371809823, 'samples': 15494400, 'steps': 80699, 'loss/train': 1.2362455129623413} 08/31/2021 03:50:00 - INFO - __main__ - Step 80701: {'lr': 0.00022509965681923635, 'samples': 15494592, 'steps': 80700, 'loss/train': 0.04740992933511734} 08/31/2021 03:50:01 - INFO - __main__ - Step 80702: {'lr': 0.00022509437646871014, 'samples': 15494784, 'steps': 80701, 'loss/train': 1.327649474143982} 08/31/2021 03:50:01 - INFO - __main__ - Step 80703: {'lr': 0.00022508909612940602, 'samples': 15494976, 'steps': 80702, 'loss/train': 1.1578142642974854} 08/31/2021 03:50:01 - INFO - __main__ - Step 80704: {'lr': 0.00022508381580132634, 'samples': 15495168, 'steps': 80703, 'loss/train': 1.6352386474609375} 08/31/2021 03:50:03 - INFO - __main__ - Step 80705: {'lr': 0.0002250785354844735, 'samples': 15495360, 'steps': 80704, 'loss/train': 1.1536201238632202} 08/31/2021 03:50:03 - INFO - __main__ - Step 80706: {'lr': 0.00022507325517884992, 'samples': 15495552, 'steps': 80705, 'loss/train': 1.3683652877807617} 08/31/2021 03:50:04 - INFO - __main__ - Step 80707: {'lr': 0.0002250679748844579, 'samples': 15495744, 'steps': 80706, 'loss/train': 1.625296711921692} 08/31/2021 03:50:04 - INFO - __main__ - Step 80708: {'lr': 0.00022506269460129992, 'samples': 15495936, 'steps': 80707, 'loss/train': 1.4678068161010742} 08/31/2021 03:50:04 - INFO - __main__ - Step 80709: {'lr': 0.00022505741432937826, 'samples': 15496128, 'steps': 80708, 'loss/train': 1.004126787185669} 08/31/2021 03:50:06 - INFO - __main__ - Step 80710: {'lr': 0.00022505213406869538, 'samples': 15496320, 'steps': 80709, 'loss/train': 1.143417239189148} 08/31/2021 03:50:06 - INFO - __main__ - Step 80711: {'lr': 0.0002250468538192536, 'samples': 15496512, 'steps': 80710, 'loss/train': 1.118849277496338} 08/31/2021 03:50:07 - INFO - __main__ - Step 80712: {'lr': 0.00022504157358105534, 'samples': 15496704, 'steps': 80711, 'loss/train': 1.0782777070999146} 08/31/2021 03:50:07 - INFO - __main__ - Step 80713: {'lr': 0.00022503629335410294, 'samples': 15496896, 'steps': 80712, 'loss/train': 1.3353338241577148} 08/31/2021 03:50:07 - INFO - __main__ - Step 80714: {'lr': 0.00022503101313839895, 'samples': 15497088, 'steps': 80713, 'loss/train': 1.1745580434799194} 08/31/2021 03:50:09 - INFO - __main__ - Step 80715: {'lr': 0.00022502573293394545, 'samples': 15497280, 'steps': 80714, 'loss/train': 1.0503853559494019} 08/31/2021 03:50:10 - INFO - __main__ - Step 80716: {'lr': 0.00022502045274074497, 'samples': 15497472, 'steps': 80715, 'loss/train': 0.2761070430278778} 08/31/2021 03:50:10 - INFO - __main__ - Step 80717: {'lr': 0.00022501517255879992, 'samples': 15497664, 'steps': 80716, 'loss/train': 1.4016296863555908} 08/31/2021 03:50:10 - INFO - __main__ - Step 80718: {'lr': 0.00022500989238811262, 'samples': 15497856, 'steps': 80717, 'loss/train': 1.2704627513885498} 08/31/2021 03:50:11 - INFO - __main__ - Step 80719: {'lr': 0.00022500461222868548, 'samples': 15498048, 'steps': 80718, 'loss/train': 0.8058452606201172} 08/31/2021 03:50:12 - INFO - __main__ - Step 80720: {'lr': 0.00022499933208052088, 'samples': 15498240, 'steps': 80719, 'loss/train': 1.1318845748901367} 08/31/2021 03:50:13 - INFO - __main__ - Step 80721: {'lr': 0.0002249940519436212, 'samples': 15498432, 'steps': 80720, 'loss/train': 0.02426876127719879} 08/31/2021 03:50:13 - INFO - __main__ - Step 80722: {'lr': 0.00022498877181798883, 'samples': 15498624, 'steps': 80721, 'loss/train': 0.02340676635503769} 08/31/2021 03:50:14 - INFO - __main__ - Step 80723: {'lr': 0.0002249834917036261, 'samples': 15498816, 'steps': 80722, 'loss/train': 2.149674892425537} 08/31/2021 03:50:14 - INFO - __main__ - Step 80724: {'lr': 0.00022497821160053543, 'samples': 15499008, 'steps': 80723, 'loss/train': 1.3964791297912598} 08/31/2021 03:50:14 - INFO - __main__ - Step 80725: {'lr': 0.0002249729315087192, 'samples': 15499200, 'steps': 80724, 'loss/train': 5.68028450012207} 08/31/2021 03:50:16 - INFO - __main__ - Step 80726: {'lr': 0.0002249676514281798, 'samples': 15499392, 'steps': 80725, 'loss/train': 1.2718123197555542} 08/31/2021 03:50:16 - INFO - __main__ - Step 80727: {'lr': 0.0002249623713589197, 'samples': 15499584, 'steps': 80726, 'loss/train': 1.305845856666565} 08/31/2021 03:50:17 - INFO - __main__ - Step 80728: {'lr': 0.00022495709130094103, 'samples': 15499776, 'steps': 80727, 'loss/train': 1.2586272954940796} 08/31/2021 03:50:17 - INFO - __main__ - Step 80729: {'lr': 0.00022495181125424632, 'samples': 15499968, 'steps': 80728, 'loss/train': 1.2904425859451294} 08/31/2021 03:50:17 - INFO - __main__ - Step 80730: {'lr': 0.00022494653121883792, 'samples': 15500160, 'steps': 80729, 'loss/train': 1.1220214366912842} 08/31/2021 03:50:19 - INFO - __main__ - Step 80731: {'lr': 0.00022494125119471825, 'samples': 15500352, 'steps': 80730, 'loss/train': 1.0871371030807495} 08/31/2021 03:50:19 - INFO - __main__ - Step 80732: {'lr': 0.00022493597118188966, 'samples': 15500544, 'steps': 80731, 'loss/train': 0.3338690400123596} 08/31/2021 03:50:20 - INFO - __main__ - Step 80733: {'lr': 0.00022493069118035452, 'samples': 15500736, 'steps': 80732, 'loss/train': 1.5799298286437988} 08/31/2021 03:50:20 - INFO - __main__ - Step 80734: {'lr': 0.00022492541119011525, 'samples': 15500928, 'steps': 80733, 'loss/train': 1.538034439086914} 08/31/2021 03:50:20 - INFO - __main__ - Step 80735: {'lr': 0.00022492013121117418, 'samples': 15501120, 'steps': 80734, 'loss/train': 2.435450315475464} 08/31/2021 03:50:22 - INFO - __main__ - Step 80736: {'lr': 0.00022491485124353372, 'samples': 15501312, 'steps': 80735, 'loss/train': 1.1332337856292725} 08/31/2021 03:50:23 - INFO - __main__ - Step 80737: {'lr': 0.00022490957128719626, 'samples': 15501504, 'steps': 80736, 'loss/train': 1.2821835279464722} 08/31/2021 03:50:23 - INFO - __main__ - Step 80738: {'lr': 0.00022490429134216415, 'samples': 15501696, 'steps': 80737, 'loss/train': 1.4523496627807617} 08/31/2021 03:50:23 - INFO - __main__ - Step 80739: {'lr': 0.00022489901140843982, 'samples': 15501888, 'steps': 80738, 'loss/train': 0.147065207362175} 08/31/2021 03:50:24 - INFO - __main__ - Step 80740: {'lr': 0.00022489373148602555, 'samples': 15502080, 'steps': 80739, 'loss/train': 1.7799592018127441} 08/31/2021 03:50:24 - INFO - __main__ - Step 80741: {'lr': 0.00022488845157492385, 'samples': 15502272, 'steps': 80740, 'loss/train': 0.9751574993133545} 08/31/2021 03:50:26 - INFO - __main__ - Step 80742: {'lr': 0.00022488317167513694, 'samples': 15502464, 'steps': 80741, 'loss/train': 1.0081521272659302} 08/31/2021 03:50:26 - INFO - __main__ - Step 80743: {'lr': 0.0002248778917866673, 'samples': 15502656, 'steps': 80742, 'loss/train': 1.1761404275894165} 08/31/2021 03:50:27 - INFO - __main__ - Step 80744: {'lr': 0.00022487261190951732, 'samples': 15502848, 'steps': 80743, 'loss/train': 1.2917536497116089} 08/31/2021 03:50:27 - INFO - __main__ - Step 80745: {'lr': 0.00022486733204368932, 'samples': 15503040, 'steps': 80744, 'loss/train': 1.0360791683197021} 08/31/2021 03:50:27 - INFO - __main__ - Step 80746: {'lr': 0.00022486205218918574, 'samples': 15503232, 'steps': 80745, 'loss/train': 1.7240583896636963} 08/31/2021 03:50:29 - INFO - __main__ - Step 80747: {'lr': 0.00022485677234600893, 'samples': 15503424, 'steps': 80746, 'loss/train': 1.582744836807251} 08/31/2021 03:50:29 - INFO - __main__ - Step 80748: {'lr': 0.00022485149251416127, 'samples': 15503616, 'steps': 80747, 'loss/train': 0.053737349808216095} 08/31/2021 03:50:30 - INFO - __main__ - Step 80749: {'lr': 0.00022484621269364512, 'samples': 15503808, 'steps': 80748, 'loss/train': 0.9478066563606262} 08/31/2021 03:50:30 - INFO - __main__ - Step 80750: {'lr': 0.00022484093288446295, 'samples': 15504000, 'steps': 80749, 'loss/train': 1.571001410484314} 08/31/2021 03:50:31 - INFO - __main__ - Step 80751: {'lr': 0.00022483565308661698, 'samples': 15504192, 'steps': 80750, 'loss/train': 1.235585331916809} 08/31/2021 03:50:32 - INFO - __main__ - Step 80752: {'lr': 0.0002248303733001097, 'samples': 15504384, 'steps': 80751, 'loss/train': 1.17449951171875} 08/31/2021 03:50:33 - INFO - __main__ - Step 80753: {'lr': 0.0002248250935249435, 'samples': 15504576, 'steps': 80752, 'loss/train': 1.2234925031661987} 08/31/2021 03:50:33 - INFO - __main__ - Step 80754: {'lr': 0.00022481981376112073, 'samples': 15504768, 'steps': 80753, 'loss/train': 0.860194981098175} 08/31/2021 03:50:33 - INFO - __main__ - Step 80755: {'lr': 0.00022481453400864372, 'samples': 15504960, 'steps': 80754, 'loss/train': 1.5376570224761963} 08/31/2021 03:50:34 - INFO - __main__ - Step 80756: {'lr': 0.0002248092542675149, 'samples': 15505152, 'steps': 80755, 'loss/train': 0.5810401439666748} 08/31/2021 03:50:36 - INFO - __main__ - Step 80757: {'lr': 0.00022480397453773662, 'samples': 15505344, 'steps': 80756, 'loss/train': 1.2477401494979858} 08/31/2021 03:50:36 - INFO - __main__ - Step 80758: {'lr': 0.0002247986948193113, 'samples': 15505536, 'steps': 80757, 'loss/train': 1.478450059890747} 08/31/2021 03:50:37 - INFO - __main__ - Step 80759: {'lr': 0.0002247934151122413, 'samples': 15505728, 'steps': 80758, 'loss/train': 1.2859597206115723} 08/31/2021 03:50:37 - INFO - __main__ - Step 80760: {'lr': 0.000224788135416529, 'samples': 15505920, 'steps': 80759, 'loss/train': 1.5343129634857178} 08/31/2021 03:50:37 - INFO - __main__ - Step 80761: {'lr': 0.00022478285573217683, 'samples': 15506112, 'steps': 80760, 'loss/train': 1.3035826683044434} 08/31/2021 03:50:38 - INFO - __main__ - Step 80762: {'lr': 0.00022477757605918707, 'samples': 15506304, 'steps': 80761, 'loss/train': 1.5414100885391235} 08/31/2021 03:50:39 - INFO - __main__ - Step 80763: {'lr': 0.00022477229639756213, 'samples': 15506496, 'steps': 80762, 'loss/train': 0.08423731476068497} 08/31/2021 03:50:40 - INFO - __main__ - Step 80764: {'lr': 0.0002247670167473044, 'samples': 15506688, 'steps': 80763, 'loss/train': 1.6340676546096802} 08/31/2021 03:50:40 - INFO - __main__ - Step 80765: {'lr': 0.00022476173710841627, 'samples': 15506880, 'steps': 80764, 'loss/train': 1.0184457302093506} 08/31/2021 03:50:41 - INFO - __main__ - Step 80766: {'lr': 0.00022475645748090011, 'samples': 15507072, 'steps': 80765, 'loss/train': 0.8330401182174683} 08/31/2021 03:50:41 - INFO - __main__ - Step 80767: {'lr': 0.0002247511778647583, 'samples': 15507264, 'steps': 80766, 'loss/train': 1.3460187911987305} 08/31/2021 03:50:41 - INFO - __main__ - Step 80768: {'lr': 0.0002247458982599933, 'samples': 15507456, 'steps': 80767, 'loss/train': 1.2842283248901367} 08/31/2021 03:50:43 - INFO - __main__ - Step 80769: {'lr': 0.00022474061866660733, 'samples': 15507648, 'steps': 80768, 'loss/train': 1.3234068155288696} 08/31/2021 03:50:43 - INFO - __main__ - Step 80770: {'lr': 0.00022473533908460284, 'samples': 15507840, 'steps': 80769, 'loss/train': 1.0295538902282715} 08/31/2021 03:50:44 - INFO - __main__ - Step 80771: {'lr': 0.00022473005951398223, 'samples': 15508032, 'steps': 80770, 'loss/train': 1.320422887802124} 08/31/2021 03:50:44 - INFO - __main__ - Step 80772: {'lr': 0.0002247247799547479, 'samples': 15508224, 'steps': 80771, 'loss/train': 1.709202527999878} 08/31/2021 03:50:44 - INFO - __main__ - Step 80773: {'lr': 0.00022471950040690218, 'samples': 15508416, 'steps': 80772, 'loss/train': 1.635228157043457} 08/31/2021 03:50:46 - INFO - __main__ - Step 80774: {'lr': 0.0002247142208704474, 'samples': 15508608, 'steps': 80773, 'loss/train': 1.0002347230911255} 08/31/2021 03:50:47 - INFO - __main__ - Step 80775: {'lr': 0.00022470894134538606, 'samples': 15508800, 'steps': 80774, 'loss/train': 0.8644784688949585} 08/31/2021 03:50:47 - INFO - __main__ - Step 80776: {'lr': 0.00022470366183172048, 'samples': 15508992, 'steps': 80775, 'loss/train': 1.1793451309204102} 08/31/2021 03:50:47 - INFO - __main__ - Step 80777: {'lr': 0.000224698382329453, 'samples': 15509184, 'steps': 80776, 'loss/train': 0.07491748034954071} 08/31/2021 03:50:48 - INFO - __main__ - Step 80778: {'lr': 0.00022469310283858607, 'samples': 15509376, 'steps': 80777, 'loss/train': 0.14257922768592834} 08/31/2021 03:50:48 - INFO - __main__ - Step 80779: {'lr': 0.000224687823359122, 'samples': 15509568, 'steps': 80778, 'loss/train': 1.3308367729187012} 08/31/2021 03:50:50 - INFO - __main__ - Step 80780: {'lr': 0.00022468254389106324, 'samples': 15509760, 'steps': 80779, 'loss/train': 0.8801389932632446} 08/31/2021 03:50:51 - INFO - __main__ - Step 80781: {'lr': 0.0002246772644344122, 'samples': 15509952, 'steps': 80780, 'loss/train': 0.6483016014099121} 08/31/2021 03:50:51 - INFO - __main__ - Step 80782: {'lr': 0.0002246719849891711, 'samples': 15510144, 'steps': 80781, 'loss/train': 0.694418728351593} 08/31/2021 03:50:51 - INFO - __main__ - Step 80783: {'lr': 0.0002246667055553425, 'samples': 15510336, 'steps': 80782, 'loss/train': 1.9610538482666016} 08/31/2021 03:50:52 - INFO - __main__ - Step 80784: {'lr': 0.0002246614261329286, 'samples': 15510528, 'steps': 80783, 'loss/train': 1.5845493078231812} 08/31/2021 03:50:53 - INFO - __main__ - Step 80785: {'lr': 0.0002246561467219319, 'samples': 15510720, 'steps': 80784, 'loss/train': 1.2690033912658691} 08/31/2021 03:50:54 - INFO - __main__ - Step 80786: {'lr': 0.00022465086732235476, 'samples': 15510912, 'steps': 80785, 'loss/train': 1.037415623664856} 08/31/2021 03:50:54 - INFO - __main__ - Step 80787: {'lr': 0.00022464558793419952, 'samples': 15511104, 'steps': 80786, 'loss/train': 0.7638503909111023} 08/31/2021 03:50:54 - INFO - __main__ - Step 80788: {'lr': 0.0002246403085574686, 'samples': 15511296, 'steps': 80787, 'loss/train': 0.49164190888404846} 08/31/2021 03:50:55 - INFO - __main__ - Step 80789: {'lr': 0.00022463502919216439, 'samples': 15511488, 'steps': 80788, 'loss/train': 1.219543695449829} 08/31/2021 03:50:56 - INFO - __main__ - Step 80790: {'lr': 0.0002246297498382892, 'samples': 15511680, 'steps': 80789, 'loss/train': 1.0494086742401123} 08/31/2021 03:50:57 - INFO - __main__ - Step 80791: {'lr': 0.00022462447049584547, 'samples': 15511872, 'steps': 80790, 'loss/train': 0.9642959833145142} 08/31/2021 03:50:57 - INFO - __main__ - Step 80792: {'lr': 0.0002246191911648356, 'samples': 15512064, 'steps': 80791, 'loss/train': 1.3249703645706177} 08/31/2021 03:50:57 - INFO - __main__ - Step 80793: {'lr': 0.00022461391184526187, 'samples': 15512256, 'steps': 80792, 'loss/train': 1.723516821861267} 08/31/2021 03:50:58 - INFO - __main__ - Step 80794: {'lr': 0.00022460863253712674, 'samples': 15512448, 'steps': 80793, 'loss/train': 1.2396975755691528} 08/31/2021 03:50:59 - INFO - __main__ - Step 80795: {'lr': 0.00022460335324043268, 'samples': 15512640, 'steps': 80794, 'loss/train': 1.5323467254638672} 08/31/2021 03:51:00 - INFO - __main__ - Step 80796: {'lr': 0.00022459807395518186, 'samples': 15512832, 'steps': 80795, 'loss/train': 1.6312994956970215} 08/31/2021 03:51:00 - INFO - __main__ - Step 80797: {'lr': 0.00022459279468137674, 'samples': 15513024, 'steps': 80796, 'loss/train': 1.1446281671524048} 08/31/2021 03:51:00 - INFO - __main__ - Step 80798: {'lr': 0.00022458751541901972, 'samples': 15513216, 'steps': 80797, 'loss/train': 1.3843287229537964} 08/31/2021 03:51:01 - INFO - __main__ - Step 80799: {'lr': 0.0002245822361681132, 'samples': 15513408, 'steps': 80798, 'loss/train': 0.4877142906188965} 08/31/2021 03:51:03 - INFO - __main__ - Step 80800: {'lr': 0.00022457695692865948, 'samples': 15513600, 'steps': 80799, 'loss/train': 1.7158784866333008} 08/31/2021 03:51:04 - INFO - __main__ - Step 80801: {'lr': 0.00022457167770066104, 'samples': 15513792, 'steps': 80800, 'loss/train': 1.4777188301086426} 08/31/2021 03:51:04 - INFO - __main__ - Step 80802: {'lr': 0.0002245663984841202, 'samples': 15513984, 'steps': 80801, 'loss/train': 0.9464837908744812} 08/31/2021 03:51:04 - INFO - __main__ - Step 80803: {'lr': 0.00022456111927903933, 'samples': 15514176, 'steps': 80802, 'loss/train': 0.36484217643737793} 08/31/2021 03:51:05 - INFO - __main__ - Step 80804: {'lr': 0.00022455584008542083, 'samples': 15514368, 'steps': 80803, 'loss/train': 0.32035061717033386} 08/31/2021 03:51:05 - INFO - __main__ - Step 80805: {'lr': 0.00022455056090326707, 'samples': 15514560, 'steps': 80804, 'loss/train': 1.0833629369735718} 08/31/2021 03:51:05 - INFO - __main__ - Step 80806: {'lr': 0.00022454528173258042, 'samples': 15514752, 'steps': 80805, 'loss/train': 1.6634122133255005} 08/31/2021 03:51:07 - INFO - __main__ - Step 80807: {'lr': 0.00022454000257336333, 'samples': 15514944, 'steps': 80806, 'loss/train': 1.0478514432907104} 08/31/2021 03:51:07 - INFO - __main__ - Step 80808: {'lr': 0.0002245347234256182, 'samples': 15515136, 'steps': 80807, 'loss/train': 0.03459228575229645} 08/31/2021 03:51:08 - INFO - __main__ - Step 80809: {'lr': 0.0002245294442893472, 'samples': 15515328, 'steps': 80808, 'loss/train': 0.8109112977981567} 08/31/2021 03:51:08 - INFO - __main__ - Step 80810: {'lr': 0.00022452416516455289, 'samples': 15515520, 'steps': 80809, 'loss/train': 1.1407496929168701} 08/31/2021 03:51:08 - INFO - __main__ - Step 80811: {'lr': 0.00022451888605123756, 'samples': 15515712, 'steps': 80810, 'loss/train': 0.9103866219520569} 08/31/2021 03:51:10 - INFO - __main__ - Step 80812: {'lr': 0.00022451360694940363, 'samples': 15515904, 'steps': 80811, 'loss/train': 1.2938560247421265} 08/31/2021 03:51:10 - INFO - __main__ - Step 80813: {'lr': 0.00022450832785905346, 'samples': 15516096, 'steps': 80812, 'loss/train': 1.7607207298278809} 08/31/2021 03:51:11 - INFO - __main__ - Step 80814: {'lr': 0.00022450304878018944, 'samples': 15516288, 'steps': 80813, 'loss/train': 0.21058817207813263} 08/31/2021 03:51:11 - INFO - __main__ - Step 80815: {'lr': 0.00022449776971281398, 'samples': 15516480, 'steps': 80814, 'loss/train': 1.4635192155838013} 08/31/2021 03:51:11 - INFO - __main__ - Step 80816: {'lr': 0.00022449249065692944, 'samples': 15516672, 'steps': 80815, 'loss/train': 1.0290461778640747} 08/31/2021 03:51:13 - INFO - __main__ - Step 80817: {'lr': 0.0002244872116125382, 'samples': 15516864, 'steps': 80816, 'loss/train': 0.7604160904884338} 08/31/2021 03:51:13 - INFO - __main__ - Step 80818: {'lr': 0.0002244819325796426, 'samples': 15517056, 'steps': 80817, 'loss/train': 1.1572208404541016} 08/31/2021 03:51:14 - INFO - __main__ - Step 80819: {'lr': 0.00022447665355824505, 'samples': 15517248, 'steps': 80818, 'loss/train': 1.492904543876648} 08/31/2021 03:51:14 - INFO - __main__ - Step 80820: {'lr': 0.00022447137454834792, 'samples': 15517440, 'steps': 80819, 'loss/train': 0.9815012216567993} 08/31/2021 03:51:14 - INFO - __main__ - Step 80821: {'lr': 0.00022446609554995373, 'samples': 15517632, 'steps': 80820, 'loss/train': 1.197749137878418} 08/31/2021 03:51:16 - INFO - __main__ - Step 80822: {'lr': 0.00022446081656306462, 'samples': 15517824, 'steps': 80821, 'loss/train': 1.30806565284729} 08/31/2021 03:51:16 - INFO - __main__ - Step 80823: {'lr': 0.00022445553758768303, 'samples': 15518016, 'steps': 80822, 'loss/train': 0.8930744528770447} 08/31/2021 03:51:17 - INFO - __main__ - Step 80824: {'lr': 0.0002244502586238114, 'samples': 15518208, 'steps': 80823, 'loss/train': 0.8128377795219421} 08/31/2021 03:51:17 - INFO - __main__ - Step 80825: {'lr': 0.00022444497967145208, 'samples': 15518400, 'steps': 80824, 'loss/train': 1.4188344478607178} 08/31/2021 03:51:17 - INFO - __main__ - Step 80826: {'lr': 0.00022443970073060746, 'samples': 15518592, 'steps': 80825, 'loss/train': 1.3861385583877563} 08/31/2021 03:51:19 - INFO - __main__ - Step 80827: {'lr': 0.00022443442180127994, 'samples': 15518784, 'steps': 80826, 'loss/train': 1.5542919635772705} 08/31/2021 03:51:20 - INFO - __main__ - Step 80828: {'lr': 0.00022442914288347185, 'samples': 15518976, 'steps': 80827, 'loss/train': 1.242024302482605} 08/31/2021 03:51:20 - INFO - __main__ - Step 80829: {'lr': 0.00022442386397718563, 'samples': 15519168, 'steps': 80828, 'loss/train': 1.2512928247451782} 08/31/2021 03:51:20 - INFO - __main__ - Step 80830: {'lr': 0.00022441858508242358, 'samples': 15519360, 'steps': 80829, 'loss/train': 1.3803126811981201} 08/31/2021 03:51:21 - INFO - __main__ - Step 80831: {'lr': 0.00022441330619918812, 'samples': 15519552, 'steps': 80830, 'loss/train': 1.1430788040161133} 08/31/2021 03:51:21 - INFO - __main__ - Step 80832: {'lr': 0.00022440802732748164, 'samples': 15519744, 'steps': 80831, 'loss/train': 1.3243610858917236} 08/31/2021 03:51:23 - INFO - __main__ - Step 80833: {'lr': 0.0002244027484673065, 'samples': 15519936, 'steps': 80832, 'loss/train': 0.43625548481941223} 08/31/2021 03:51:24 - INFO - __main__ - Step 80834: {'lr': 0.00022439746961866512, 'samples': 15520128, 'steps': 80833, 'loss/train': 0.7193619012832642} 08/31/2021 03:51:24 - INFO - __main__ - Step 80835: {'lr': 0.00022439219078155992, 'samples': 15520320, 'steps': 80834, 'loss/train': 0.09112519770860672} 08/31/2021 03:51:24 - INFO - __main__ - Step 80836: {'lr': 0.00022438691195599312, 'samples': 15520512, 'steps': 80835, 'loss/train': 0.8554530739784241} 08/31/2021 03:51:25 - INFO - __main__ - Step 80837: {'lr': 0.00022438163314196716, 'samples': 15520704, 'steps': 80836, 'loss/train': 1.2796226739883423} 08/31/2021 03:51:26 - INFO - __main__ - Step 80838: {'lr': 0.00022437635433948447, 'samples': 15520896, 'steps': 80837, 'loss/train': 0.03948168456554413} 08/31/2021 03:51:27 - INFO - __main__ - Step 80839: {'lr': 0.00022437107554854738, 'samples': 15521088, 'steps': 80838, 'loss/train': 1.2981407642364502} 08/31/2021 03:51:27 - INFO - __main__ - Step 80840: {'lr': 0.00022436579676915827, 'samples': 15521280, 'steps': 80839, 'loss/train': 0.6286851763725281} 08/31/2021 03:51:28 - INFO - __main__ - Step 80841: {'lr': 0.00022436051800131957, 'samples': 15521472, 'steps': 80840, 'loss/train': 1.0844124555587769} 08/31/2021 03:51:28 - INFO - __main__ - Step 80842: {'lr': 0.0002243552392450336, 'samples': 15521664, 'steps': 80841, 'loss/train': 1.3498599529266357} 08/31/2021 03:51:29 - INFO - __main__ - Step 80843: {'lr': 0.0002243499605003028, 'samples': 15521856, 'steps': 80842, 'loss/train': 1.7995784282684326} 08/31/2021 03:51:30 - INFO - __main__ - Step 80844: {'lr': 0.00022434468176712948, 'samples': 15522048, 'steps': 80843, 'loss/train': 1.0114206075668335} 08/31/2021 03:51:30 - INFO - __main__ - Step 80845: {'lr': 0.00022433940304551604, 'samples': 15522240, 'steps': 80844, 'loss/train': 1.0496206283569336} 08/31/2021 03:51:31 - INFO - __main__ - Step 80846: {'lr': 0.00022433412433546488, 'samples': 15522432, 'steps': 80845, 'loss/train': 0.5771719217300415} 08/31/2021 03:51:31 - INFO - __main__ - Step 80847: {'lr': 0.0002243288456369784, 'samples': 15522624, 'steps': 80846, 'loss/train': 1.4512587785720825} 08/31/2021 03:51:33 - INFO - __main__ - Step 80848: {'lr': 0.00022432356695005902, 'samples': 15522816, 'steps': 80847, 'loss/train': 0.8918212652206421} 08/31/2021 03:51:33 - INFO - __main__ - Step 80849: {'lr': 0.00022431828827470894, 'samples': 15523008, 'steps': 80848, 'loss/train': 1.090055227279663} 08/31/2021 03:51:33 - INFO - __main__ - Step 80850: {'lr': 0.00022431300961093064, 'samples': 15523200, 'steps': 80849, 'loss/train': 1.352184534072876} 08/31/2021 03:51:34 - INFO - __main__ - Step 80851: {'lr': 0.0002243077309587265, 'samples': 15523392, 'steps': 80850, 'loss/train': 0.16026295721530914} 08/31/2021 03:51:34 - INFO - __main__ - Step 80852: {'lr': 0.00022430245231809892, 'samples': 15523584, 'steps': 80851, 'loss/train': 0.9110462069511414} 08/31/2021 03:51:35 - INFO - __main__ - Step 80853: {'lr': 0.00022429717368905021, 'samples': 15523776, 'steps': 80852, 'loss/train': 1.0079655647277832} 08/31/2021 03:51:36 - INFO - __main__ - Step 80854: {'lr': 0.00022429189507158288, 'samples': 15523968, 'steps': 80853, 'loss/train': 1.3945268392562866} 08/31/2021 03:51:37 - INFO - __main__ - Step 80855: {'lr': 0.00022428661646569915, 'samples': 15524160, 'steps': 80854, 'loss/train': 1.4879769086837769} 08/31/2021 03:51:37 - INFO - __main__ - Step 80856: {'lr': 0.00022428133787140151, 'samples': 15524352, 'steps': 80855, 'loss/train': 0.9566279053688049} 08/31/2021 03:51:37 - INFO - __main__ - Step 80857: {'lr': 0.0002242760592886923, 'samples': 15524544, 'steps': 80856, 'loss/train': 1.430182933807373} 08/31/2021 03:51:38 - INFO - __main__ - Step 80858: {'lr': 0.0002242707807175739, 'samples': 15524736, 'steps': 80857, 'loss/train': 1.4418760538101196} 08/31/2021 03:51:39 - INFO - __main__ - Step 80859: {'lr': 0.00022426550215804867, 'samples': 15524928, 'steps': 80858, 'loss/train': 0.021000590175390244} 08/31/2021 03:51:40 - INFO - __main__ - Step 80860: {'lr': 0.00022426022361011903, 'samples': 15525120, 'steps': 80859, 'loss/train': 1.0801832675933838} 08/31/2021 03:51:40 - INFO - __main__ - Step 80861: {'lr': 0.00022425494507378733, 'samples': 15525312, 'steps': 80860, 'loss/train': 1.2415146827697754} 08/31/2021 03:51:40 - INFO - __main__ - Step 80862: {'lr': 0.00022424966654905604, 'samples': 15525504, 'steps': 80861, 'loss/train': 1.4428249597549438} 08/31/2021 03:51:41 - INFO - __main__ - Step 80863: {'lr': 0.00022424438803592738, 'samples': 15525696, 'steps': 80862, 'loss/train': 0.7950302958488464} 08/31/2021 03:51:42 - INFO - __main__ - Step 80864: {'lr': 0.00022423910953440378, 'samples': 15525888, 'steps': 80863, 'loss/train': 1.0947340726852417} 08/31/2021 03:51:43 - INFO - __main__ - Step 80865: {'lr': 0.00022423383104448765, 'samples': 15526080, 'steps': 80864, 'loss/train': 1.2411404848098755} 08/31/2021 03:51:43 - INFO - __main__ - Step 80866: {'lr': 0.00022422855256618135, 'samples': 15526272, 'steps': 80865, 'loss/train': 1.2354302406311035} 08/31/2021 03:51:43 - INFO - __main__ - Step 80867: {'lr': 0.00022422327409948729, 'samples': 15526464, 'steps': 80866, 'loss/train': 0.7459651827812195} 08/31/2021 03:51:44 - INFO - __main__ - Step 80868: {'lr': 0.0002242179956444078, 'samples': 15526656, 'steps': 80867, 'loss/train': 0.3496339023113251} 08/31/2021 03:51:45 - INFO - __main__ - Step 80869: {'lr': 0.00022421271720094528, 'samples': 15526848, 'steps': 80868, 'loss/train': 1.3224800825119019} 08/31/2021 03:51:46 - INFO - __main__ - Step 80870: {'lr': 0.00022420743876910214, 'samples': 15527040, 'steps': 80869, 'loss/train': 1.0796570777893066} 08/31/2021 03:51:46 - INFO - __main__ - Step 80871: {'lr': 0.0002242021603488807, 'samples': 15527232, 'steps': 80870, 'loss/train': 0.10472843050956726} 08/31/2021 03:51:47 - INFO - __main__ - Step 80872: {'lr': 0.00022419688194028338, 'samples': 15527424, 'steps': 80871, 'loss/train': 1.431262493133545} 08/31/2021 03:51:47 - INFO - __main__ - Step 80873: {'lr': 0.00022419160354331257, 'samples': 15527616, 'steps': 80872, 'loss/train': 1.3494001626968384} 08/31/2021 03:51:49 - INFO - __main__ - Step 80874: {'lr': 0.00022418632515797064, 'samples': 15527808, 'steps': 80873, 'loss/train': 1.5049092769622803} 08/31/2021 03:51:49 - INFO - __main__ - Step 80875: {'lr': 0.00022418104678425995, 'samples': 15528000, 'steps': 80874, 'loss/train': 1.3553407192230225} 08/31/2021 03:51:49 - INFO - __main__ - Step 80876: {'lr': 0.00022417576842218286, 'samples': 15528192, 'steps': 80875, 'loss/train': 1.9844367504119873} 08/31/2021 03:51:50 - INFO - __main__ - Step 80877: {'lr': 0.00022417049007174175, 'samples': 15528384, 'steps': 80876, 'loss/train': 1.1160792112350464} 08/31/2021 03:51:50 - INFO - __main__ - Step 80878: {'lr': 0.00022416521173293904, 'samples': 15528576, 'steps': 80877, 'loss/train': 2.016606569290161} 08/31/2021 03:51:52 - INFO - __main__ - Step 80879: {'lr': 0.00022415993340577707, 'samples': 15528768, 'steps': 80878, 'loss/train': 0.22238169610500336} 08/31/2021 03:51:52 - INFO - __main__ - Step 80880: {'lr': 0.00022415465509025823, 'samples': 15528960, 'steps': 80879, 'loss/train': 1.1457422971725464} 08/31/2021 03:51:52 - INFO - __main__ - Step 80881: {'lr': 0.00022414937678638493, 'samples': 15529152, 'steps': 80880, 'loss/train': 0.6265806555747986} 08/31/2021 03:51:53 - INFO - __main__ - Step 80882: {'lr': 0.00022414409849415948, 'samples': 15529344, 'steps': 80881, 'loss/train': 1.0149672031402588} 08/31/2021 03:51:53 - INFO - __main__ - Step 80883: {'lr': 0.00022413882021358434, 'samples': 15529536, 'steps': 80882, 'loss/train': 1.018861174583435} 08/31/2021 03:51:55 - INFO - __main__ - Step 80884: {'lr': 0.00022413354194466187, 'samples': 15529728, 'steps': 80883, 'loss/train': 1.6559242010116577} 08/31/2021 03:51:55 - INFO - __main__ - Step 80885: {'lr': 0.00022412826368739438, 'samples': 15529920, 'steps': 80884, 'loss/train': 1.653563141822815} 08/31/2021 03:51:56 - INFO - __main__ - Step 80886: {'lr': 0.0002241229854417843, 'samples': 15530112, 'steps': 80885, 'loss/train': 0.07589811831712723} 08/31/2021 03:51:56 - INFO - __main__ - Step 80887: {'lr': 0.00022411770720783404, 'samples': 15530304, 'steps': 80886, 'loss/train': 0.11856275796890259} 08/31/2021 03:51:56 - INFO - __main__ - Step 80888: {'lr': 0.0002241124289855459, 'samples': 15530496, 'steps': 80887, 'loss/train': 1.07296884059906} 08/31/2021 03:51:59 - INFO - __main__ - Step 80889: {'lr': 0.00022410715077492236, 'samples': 15530688, 'steps': 80888, 'loss/train': 0.5570823550224304} 08/31/2021 03:52:00 - INFO - __main__ - Step 80890: {'lr': 0.00022410187257596568, 'samples': 15530880, 'steps': 80889, 'loss/train': 1.0520939826965332} 08/31/2021 03:52:00 - INFO - __main__ - Step 80891: {'lr': 0.0002240965943886783, 'samples': 15531072, 'steps': 80890, 'loss/train': 0.8425095081329346} 08/31/2021 03:52:00 - INFO - __main__ - Step 80892: {'lr': 0.00022409131621306262, 'samples': 15531264, 'steps': 80891, 'loss/train': 0.9514093995094299} 08/31/2021 03:52:01 - INFO - __main__ - Step 80893: {'lr': 0.00022408603804912095, 'samples': 15531456, 'steps': 80892, 'loss/train': 1.0431435108184814} 08/31/2021 03:52:01 - INFO - __main__ - Step 80894: {'lr': 0.00022408075989685576, 'samples': 15531648, 'steps': 80893, 'loss/train': 1.073209285736084} 08/31/2021 03:52:03 - INFO - __main__ - Step 80895: {'lr': 0.0002240754817562694, 'samples': 15531840, 'steps': 80894, 'loss/train': 0.14080454409122467} 08/31/2021 03:52:03 - INFO - __main__ - Step 80896: {'lr': 0.0002240702036273642, 'samples': 15532032, 'steps': 80895, 'loss/train': 1.637948751449585} 08/31/2021 03:52:04 - INFO - __main__ - Step 80897: {'lr': 0.0002240649255101425, 'samples': 15532224, 'steps': 80896, 'loss/train': 1.6559220552444458} 08/31/2021 03:52:04 - INFO - __main__ - Step 80898: {'lr': 0.00022405964740460682, 'samples': 15532416, 'steps': 80897, 'loss/train': 0.48505592346191406} 08/31/2021 03:52:04 - INFO - __main__ - Step 80899: {'lr': 0.00022405436931075942, 'samples': 15532608, 'steps': 80898, 'loss/train': 0.9747580289840698} 08/31/2021 03:52:05 - INFO - __main__ - Step 80900: {'lr': 0.00022404909122860272, 'samples': 15532800, 'steps': 80899, 'loss/train': 0.08929082751274109} 08/31/2021 03:52:06 - INFO - __main__ - Step 80901: {'lr': 0.00022404381315813913, 'samples': 15532992, 'steps': 80900, 'loss/train': 1.402584433555603} 08/31/2021 03:52:07 - INFO - __main__ - Step 80902: {'lr': 0.00022403853509937106, 'samples': 15533184, 'steps': 80901, 'loss/train': 1.1612387895584106} 08/31/2021 03:52:07 - INFO - __main__ - Step 80903: {'lr': 0.00022403325705230072, 'samples': 15533376, 'steps': 80902, 'loss/train': 1.8032184839248657} 08/31/2021 03:52:07 - INFO - __main__ - Step 80904: {'lr': 0.0002240279790169306, 'samples': 15533568, 'steps': 80903, 'loss/train': 0.7044284343719482} 08/31/2021 03:52:08 - INFO - __main__ - Step 80905: {'lr': 0.00022402270099326313, 'samples': 15533760, 'steps': 80904, 'loss/train': 1.133626103401184} 08/31/2021 03:52:10 - INFO - __main__ - Step 80906: {'lr': 0.00022401742298130064, 'samples': 15533952, 'steps': 80905, 'loss/train': 1.811602234840393} 08/31/2021 03:52:10 - INFO - __main__ - Step 80907: {'lr': 0.00022401214498104545, 'samples': 15534144, 'steps': 80906, 'loss/train': 0.9492254257202148} 08/31/2021 03:52:11 - INFO - __main__ - Step 80908: {'lr': 0.0002240068669925, 'samples': 15534336, 'steps': 80907, 'loss/train': 1.3835232257843018} 08/31/2021 03:52:11 - INFO - __main__ - Step 80909: {'lr': 0.00022400158901566663, 'samples': 15534528, 'steps': 80908, 'loss/train': 1.2201783657073975} 08/31/2021 03:52:11 - INFO - __main__ - Step 80910: {'lr': 0.00022399631105054775, 'samples': 15534720, 'steps': 80909, 'loss/train': 0.32909834384918213} 08/31/2021 03:52:12 - INFO - __main__ - Step 80911: {'lr': 0.00022399103309714576, 'samples': 15534912, 'steps': 80910, 'loss/train': 0.9351760149002075} 08/31/2021 03:52:13 - INFO - __main__ - Step 80912: {'lr': 0.00022398575515546296, 'samples': 15535104, 'steps': 80911, 'loss/train': 0.7836719155311584} 08/31/2021 03:52:14 - INFO - __main__ - Step 80913: {'lr': 0.0002239804772255018, 'samples': 15535296, 'steps': 80912, 'loss/train': 1.976139783859253} 08/31/2021 03:52:14 - INFO - __main__ - Step 80914: {'lr': 0.00022397519930726466, 'samples': 15535488, 'steps': 80913, 'loss/train': 1.007083773612976} 08/31/2021 03:52:14 - INFO - __main__ - Step 80915: {'lr': 0.00022396992140075387, 'samples': 15535680, 'steps': 80914, 'loss/train': 1.0061213970184326} 08/31/2021 03:52:15 - INFO - __main__ - Step 80916: {'lr': 0.00022396464350597187, 'samples': 15535872, 'steps': 80915, 'loss/train': 1.105653166770935} 08/31/2021 03:52:16 - INFO - __main__ - Step 80917: {'lr': 0.00022395936562292102, 'samples': 15536064, 'steps': 80916, 'loss/train': 1.629201054573059} 08/31/2021 03:52:17 - INFO - __main__ - Step 80918: {'lr': 0.00022395408775160362, 'samples': 15536256, 'steps': 80917, 'loss/train': 0.4243414103984833} 08/31/2021 03:52:17 - INFO - __main__ - Step 80919: {'lr': 0.0002239488098920221, 'samples': 15536448, 'steps': 80918, 'loss/train': 1.3001936674118042} 08/31/2021 03:52:17 - INFO - __main__ - Step 80920: {'lr': 0.00022394353204417886, 'samples': 15536640, 'steps': 80919, 'loss/train': 0.8348094820976257} 08/31/2021 03:52:18 - INFO - __main__ - Step 80921: {'lr': 0.00022393825420807627, 'samples': 15536832, 'steps': 80920, 'loss/train': 1.3147149085998535} 08/31/2021 03:52:19 - INFO - __main__ - Step 80922: {'lr': 0.00022393297638371667, 'samples': 15537024, 'steps': 80921, 'loss/train': 1.2393878698349} 08/31/2021 03:52:20 - INFO - __main__ - Step 80923: {'lr': 0.00022392769857110248, 'samples': 15537216, 'steps': 80922, 'loss/train': 0.6620832085609436} 08/31/2021 03:52:20 - INFO - __main__ - Step 80924: {'lr': 0.00022392242077023608, 'samples': 15537408, 'steps': 80923, 'loss/train': 1.5096758604049683} 08/31/2021 03:52:20 - INFO - __main__ - Step 80925: {'lr': 0.00022391714298111983, 'samples': 15537600, 'steps': 80924, 'loss/train': 1.1020501852035522} 08/31/2021 03:52:21 - INFO - __main__ - Step 80926: {'lr': 0.00022391186520375608, 'samples': 15537792, 'steps': 80925, 'loss/train': 0.8530185222625732} 08/31/2021 03:52:22 - INFO - __main__ - Step 80927: {'lr': 0.0002239065874381473, 'samples': 15537984, 'steps': 80926, 'loss/train': 1.2959235906600952} 08/31/2021 03:52:23 - INFO - __main__ - Step 80928: {'lr': 0.00022390130968429577, 'samples': 15538176, 'steps': 80927, 'loss/train': 1.0095570087432861} 08/31/2021 03:52:23 - INFO - __main__ - Step 80929: {'lr': 0.00022389603194220402, 'samples': 15538368, 'steps': 80928, 'loss/train': 1.1961265802383423} 08/31/2021 03:52:23 - INFO - __main__ - Step 80930: {'lr': 0.00022389075421187421, 'samples': 15538560, 'steps': 80929, 'loss/train': 0.6546404361724854} 08/31/2021 03:52:24 - INFO - __main__ - Step 80931: {'lr': 0.00022388547649330881, 'samples': 15538752, 'steps': 80930, 'loss/train': 1.0752232074737549} 08/31/2021 03:52:25 - INFO - __main__ - Step 80932: {'lr': 0.00022388019878651023, 'samples': 15538944, 'steps': 80931, 'loss/train': 1.047225832939148} 08/31/2021 03:52:26 - INFO - __main__ - Step 80933: {'lr': 0.00022387492109148083, 'samples': 15539136, 'steps': 80932, 'loss/train': 1.0022320747375488} 08/31/2021 03:52:26 - INFO - __main__ - Step 80934: {'lr': 0.00022386964340822296, 'samples': 15539328, 'steps': 80933, 'loss/train': 1.7507750988006592} 08/31/2021 03:52:26 - INFO - __main__ - Step 80935: {'lr': 0.00022386436573673907, 'samples': 15539520, 'steps': 80934, 'loss/train': 0.20357990264892578} 08/31/2021 03:52:27 - INFO - __main__ - Step 80936: {'lr': 0.00022385908807703145, 'samples': 15539712, 'steps': 80935, 'loss/train': 0.9490973353385925} 08/31/2021 03:52:27 - INFO - __main__ - Step 80937: {'lr': 0.00022385381042910256, 'samples': 15539904, 'steps': 80936, 'loss/train': 1.1153804063796997} 08/31/2021 03:52:28 - INFO - __main__ - Step 80938: {'lr': 0.00022384853279295474, 'samples': 15540096, 'steps': 80937, 'loss/train': 1.4181702136993408} 08/31/2021 03:52:29 - INFO - __main__ - Step 80939: {'lr': 0.00022384325516859032, 'samples': 15540288, 'steps': 80938, 'loss/train': 1.2675631046295166} 08/31/2021 03:52:29 - INFO - __main__ - Step 80940: {'lr': 0.00022383797755601176, 'samples': 15540480, 'steps': 80939, 'loss/train': 1.5398807525634766} 08/31/2021 03:52:30 - INFO - __main__ - Step 80941: {'lr': 0.0002238326999552214, 'samples': 15540672, 'steps': 80940, 'loss/train': 1.1702511310577393} 08/31/2021 03:52:30 - INFO - __main__ - Step 80942: {'lr': 0.00022382742236622173, 'samples': 15540864, 'steps': 80941, 'loss/train': 1.1936731338500977} 08/31/2021 03:52:32 - INFO - __main__ - Step 80943: {'lr': 0.0002238221447890149, 'samples': 15541056, 'steps': 80942, 'loss/train': 0.6177985072135925} 08/31/2021 03:52:32 - INFO - __main__ - Step 80944: {'lr': 0.00022381686722360342, 'samples': 15541248, 'steps': 80943, 'loss/train': 1.129250407218933} 08/31/2021 03:52:33 - INFO - __main__ - Step 80945: {'lr': 0.00022381158966998965, 'samples': 15541440, 'steps': 80944, 'loss/train': 1.3016266822814941} 08/31/2021 03:52:33 - INFO - __main__ - Step 80946: {'lr': 0.00022380631212817599, 'samples': 15541632, 'steps': 80945, 'loss/train': 1.238680124282837} 08/31/2021 03:52:33 - INFO - __main__ - Step 80947: {'lr': 0.00022380103459816478, 'samples': 15541824, 'steps': 80946, 'loss/train': 1.54549241065979} 08/31/2021 03:52:35 - INFO - __main__ - Step 80948: {'lr': 0.00022379575707995842, 'samples': 15542016, 'steps': 80947, 'loss/train': 1.6165424585342407} 08/31/2021 03:52:36 - INFO - __main__ - Step 80949: {'lr': 0.0002237904795735593, 'samples': 15542208, 'steps': 80948, 'loss/train': 0.7004791498184204} 08/31/2021 03:52:36 - INFO - __main__ - Step 80950: {'lr': 0.00022378520207896977, 'samples': 15542400, 'steps': 80949, 'loss/train': 0.07201140373945236} 08/31/2021 03:52:36 - INFO - __main__ - Step 80951: {'lr': 0.00022377992459619224, 'samples': 15542592, 'steps': 80950, 'loss/train': 2.316424608230591} 08/31/2021 03:52:37 - INFO - __main__ - Step 80952: {'lr': 0.00022377464712522907, 'samples': 15542784, 'steps': 80951, 'loss/train': 0.8419809341430664} 08/31/2021 03:52:38 - INFO - __main__ - Step 80953: {'lr': 0.00022376936966608262, 'samples': 15542976, 'steps': 80952, 'loss/train': 1.1524076461791992} 08/31/2021 03:52:39 - INFO - __main__ - Step 80954: {'lr': 0.00022376409221875533, 'samples': 15543168, 'steps': 80953, 'loss/train': 1.0038833618164062} 08/31/2021 03:52:39 - INFO - __main__ - Step 80955: {'lr': 0.0002237588147832495, 'samples': 15543360, 'steps': 80954, 'loss/train': 1.0131266117095947} 08/31/2021 03:52:39 - INFO - __main__ - Step 80956: {'lr': 0.00022375353735956766, 'samples': 15543552, 'steps': 80955, 'loss/train': 1.6024736166000366} 08/31/2021 03:52:40 - INFO - __main__ - Step 80957: {'lr': 0.00022374825994771194, 'samples': 15543744, 'steps': 80956, 'loss/train': 1.8742437362670898} 08/31/2021 03:52:40 - INFO - __main__ - Step 80958: {'lr': 0.00022374298254768487, 'samples': 15543936, 'steps': 80957, 'loss/train': 1.0231084823608398} 08/31/2021 03:52:41 - INFO - __main__ - Step 80959: {'lr': 0.00022373770515948883, 'samples': 15544128, 'steps': 80958, 'loss/train': 1.0673893690109253} 08/31/2021 03:52:42 - INFO - __main__ - Step 80960: {'lr': 0.00022373242778312615, 'samples': 15544320, 'steps': 80959, 'loss/train': 1.8762855529785156} 08/31/2021 03:52:42 - INFO - __main__ - Step 80961: {'lr': 0.00022372715041859924, 'samples': 15544512, 'steps': 80960, 'loss/train': 0.4751233160495758} 08/31/2021 03:52:43 - INFO - __main__ - Step 80962: {'lr': 0.00022372187306591044, 'samples': 15544704, 'steps': 80961, 'loss/train': 1.3365304470062256} 08/31/2021 03:52:43 - INFO - __main__ - Step 80963: {'lr': 0.0002237165957250622, 'samples': 15544896, 'steps': 80962, 'loss/train': 1.7343119382858276} 08/31/2021 03:52:44 - INFO - __main__ - Step 80964: {'lr': 0.00022371131839605683, 'samples': 15545088, 'steps': 80963, 'loss/train': 1.5689154863357544} 08/31/2021 03:52:45 - INFO - __main__ - Step 80965: {'lr': 0.00022370604107889674, 'samples': 15545280, 'steps': 80964, 'loss/train': 1.4110081195831299} 08/31/2021 03:52:45 - INFO - __main__ - Step 80966: {'lr': 0.0002237007637735843, 'samples': 15545472, 'steps': 80965, 'loss/train': 0.9641340970993042} 08/31/2021 03:52:46 - INFO - __main__ - Step 80967: {'lr': 0.00022369548648012188, 'samples': 15545664, 'steps': 80966, 'loss/train': 0.5374298691749573} 08/31/2021 03:52:46 - INFO - __main__ - Step 80968: {'lr': 0.00022369020919851192, 'samples': 15545856, 'steps': 80967, 'loss/train': 1.5567591190338135} 08/31/2021 03:52:48 - INFO - __main__ - Step 80969: {'lr': 0.0002236849319287568, 'samples': 15546048, 'steps': 80968, 'loss/train': 0.9637575745582581} 08/31/2021 03:52:48 - INFO - __main__ - Step 80970: {'lr': 0.00022367965467085877, 'samples': 15546240, 'steps': 80969, 'loss/train': 0.8234363198280334} 08/31/2021 03:52:48 - INFO - __main__ - Step 80971: {'lr': 0.00022367437742482025, 'samples': 15546432, 'steps': 80970, 'loss/train': 0.6319329738616943} 08/31/2021 03:52:49 - INFO - __main__ - Step 80972: {'lr': 0.00022366910019064367, 'samples': 15546624, 'steps': 80971, 'loss/train': 1.0781203508377075} 08/31/2021 03:52:49 - INFO - __main__ - Step 80973: {'lr': 0.00022366382296833137, 'samples': 15546816, 'steps': 80972, 'loss/train': 1.0083868503570557} 08/31/2021 03:52:51 - INFO - __main__ - Step 80974: {'lr': 0.00022365854575788578, 'samples': 15547008, 'steps': 80973, 'loss/train': 1.1995548009872437} 08/31/2021 03:52:51 - INFO - __main__ - Step 80975: {'lr': 0.0002236532685593092, 'samples': 15547200, 'steps': 80974, 'loss/train': 1.2001858949661255} 08/31/2021 03:52:51 - INFO - __main__ - Step 80976: {'lr': 0.0002236479913726041, 'samples': 15547392, 'steps': 80975, 'loss/train': 1.1002957820892334} 08/31/2021 03:52:52 - INFO - __main__ - Step 80977: {'lr': 0.00022364271419777275, 'samples': 15547584, 'steps': 80976, 'loss/train': 1.4111104011535645} 08/31/2021 03:52:52 - INFO - __main__ - Step 80978: {'lr': 0.00022363743703481762, 'samples': 15547776, 'steps': 80977, 'loss/train': 0.42123275995254517} 08/31/2021 03:52:54 - INFO - __main__ - Step 80979: {'lr': 0.00022363215988374102, 'samples': 15547968, 'steps': 80978, 'loss/train': 1.0759596824645996} 08/31/2021 03:52:54 - INFO - __main__ - Step 80980: {'lr': 0.0002236268827445454, 'samples': 15548160, 'steps': 80979, 'loss/train': 1.143200159072876} 08/31/2021 03:52:54 - INFO - __main__ - Step 80981: {'lr': 0.0002236216056172331, 'samples': 15548352, 'steps': 80980, 'loss/train': 1.2324426174163818} 08/31/2021 03:52:55 - INFO - __main__ - Step 80982: {'lr': 0.00022361632850180648, 'samples': 15548544, 'steps': 80981, 'loss/train': 1.7434532642364502} 08/31/2021 03:52:55 - INFO - __main__ - Step 80983: {'lr': 0.00022361105139826807, 'samples': 15548736, 'steps': 80982, 'loss/train': 1.0134871006011963} 08/31/2021 03:52:57 - INFO - __main__ - Step 80984: {'lr': 0.00022360577430662, 'samples': 15548928, 'steps': 80983, 'loss/train': 1.0708653926849365} 08/31/2021 03:52:57 - INFO - __main__ - Step 80985: {'lr': 0.00022360049722686473, 'samples': 15549120, 'steps': 80984, 'loss/train': 1.6617703437805176} 08/31/2021 03:52:57 - INFO - __main__ - Step 80986: {'lr': 0.00022359522015900468, 'samples': 15549312, 'steps': 80985, 'loss/train': 1.1285837888717651} 08/31/2021 03:52:58 - INFO - __main__ - Step 80987: {'lr': 0.00022358994310304223, 'samples': 15549504, 'steps': 80986, 'loss/train': 1.4069993495941162} 08/31/2021 03:52:58 - INFO - __main__ - Step 80988: {'lr': 0.00022358466605897973, 'samples': 15549696, 'steps': 80987, 'loss/train': 1.360795497894287} 08/31/2021 03:52:58 - INFO - __main__ - Step 80989: {'lr': 0.00022357938902681956, 'samples': 15549888, 'steps': 80988, 'loss/train': 1.5928680896759033} 08/31/2021 03:53:00 - INFO - __main__ - Step 80990: {'lr': 0.00022357411200656414, 'samples': 15550080, 'steps': 80989, 'loss/train': 1.158789038658142} 08/31/2021 03:53:00 - INFO - __main__ - Step 80991: {'lr': 0.0002235688349982158, 'samples': 15550272, 'steps': 80990, 'loss/train': 0.05909091979265213} 08/31/2021 03:53:01 - INFO - __main__ - Step 80992: {'lr': 0.00022356355800177695, 'samples': 15550464, 'steps': 80991, 'loss/train': 1.3795584440231323} 08/31/2021 03:53:01 - INFO - __main__ - Step 80993: {'lr': 0.00022355828101724992, 'samples': 15550656, 'steps': 80992, 'loss/train': 0.9739508628845215} 08/31/2021 03:53:02 - INFO - __main__ - Step 80994: {'lr': 0.00022355300404463716, 'samples': 15550848, 'steps': 80993, 'loss/train': 0.8207539916038513} 08/31/2021 03:53:04 - INFO - __main__ - Step 80995: {'lr': 0.000223547727083941, 'samples': 15551040, 'steps': 80994, 'loss/train': 1.262412428855896} 08/31/2021 03:53:04 - INFO - __main__ - Step 80996: {'lr': 0.00022354245013516392, 'samples': 15551232, 'steps': 80995, 'loss/train': 0.8268968462944031} 08/31/2021 03:53:05 - INFO - __main__ - Step 80997: {'lr': 0.0002235371731983081, 'samples': 15551424, 'steps': 80996, 'loss/train': 1.8676058053970337} 08/31/2021 03:53:05 - INFO - __main__ - Step 80998: {'lr': 0.00022353189627337603, 'samples': 15551616, 'steps': 80997, 'loss/train': 0.33300700783729553} 08/31/2021 03:53:05 - INFO - __main__ - Step 80999: {'lr': 0.00022352661936037005, 'samples': 15551808, 'steps': 80998, 'loss/train': 0.3217853009700775} 08/31/2021 03:53:06 - INFO - __main__ - Step 81000: {'lr': 0.0002235213424592926, 'samples': 15552000, 'steps': 80999, 'loss/train': 1.1351784467697144} 08/31/2021 03:53:08 - INFO - __main__ - Step 81001: {'lr': 0.000223516065570146, 'samples': 15552192, 'steps': 81000, 'loss/train': 0.7898086905479431} 08/31/2021 03:53:08 - INFO - __main__ - Step 81002: {'lr': 0.00022351078869293267, 'samples': 15552384, 'steps': 81001, 'loss/train': 0.40445616841316223} 08/31/2021 03:53:09 - INFO - __main__ - Step 81003: {'lr': 0.00022350551182765497, 'samples': 15552576, 'steps': 81002, 'loss/train': 1.3191665410995483} 08/31/2021 03:53:09 - INFO - __main__ - Step 81004: {'lr': 0.00022350023497431527, 'samples': 15552768, 'steps': 81003, 'loss/train': 0.7226006388664246} 08/31/2021 03:53:09 - INFO - __main__ - Step 81005: {'lr': 0.00022349495813291594, 'samples': 15552960, 'steps': 81004, 'loss/train': 1.0936224460601807} 08/31/2021 03:53:11 - INFO - __main__ - Step 81006: {'lr': 0.00022348968130345942, 'samples': 15553152, 'steps': 81005, 'loss/train': 0.7859306931495667} 08/31/2021 03:53:11 - INFO - __main__ - Step 81007: {'lr': 0.000223484404485948, 'samples': 15553344, 'steps': 81006, 'loss/train': 0.9514799118041992} 08/31/2021 03:53:12 - INFO - __main__ - Step 81008: {'lr': 0.00022347912768038418, 'samples': 15553536, 'steps': 81007, 'loss/train': 0.9702001810073853} 08/31/2021 03:53:12 - INFO - __main__ - Step 81009: {'lr': 0.00022347385088677016, 'samples': 15553728, 'steps': 81008, 'loss/train': 1.1245014667510986} 08/31/2021 03:53:13 - INFO - __main__ - Step 81010: {'lr': 0.0002234685741051085, 'samples': 15553920, 'steps': 81009, 'loss/train': 0.6700314283370972} 08/31/2021 03:53:13 - INFO - __main__ - Step 81011: {'lr': 0.00022346329733540144, 'samples': 15554112, 'steps': 81010, 'loss/train': 1.647396206855774} 08/31/2021 03:53:15 - INFO - __main__ - Step 81012: {'lr': 0.00022345802057765137, 'samples': 15554304, 'steps': 81011, 'loss/train': 1.451501488685608} 08/31/2021 03:53:15 - INFO - __main__ - Step 81013: {'lr': 0.00022345274383186076, 'samples': 15554496, 'steps': 81012, 'loss/train': 2.057861328125} 08/31/2021 03:53:15 - INFO - __main__ - Step 81014: {'lr': 0.0002234474670980319, 'samples': 15554688, 'steps': 81013, 'loss/train': 1.1767044067382812} 08/31/2021 03:53:16 - INFO - __main__ - Step 81015: {'lr': 0.0002234421903761672, 'samples': 15554880, 'steps': 81014, 'loss/train': 1.4704687595367432} 08/31/2021 03:53:16 - INFO - __main__ - Step 81016: {'lr': 0.00022343691366626906, 'samples': 15555072, 'steps': 81015, 'loss/train': 1.874518871307373} 08/31/2021 03:53:18 - INFO - __main__ - Step 81017: {'lr': 0.00022343163696833982, 'samples': 15555264, 'steps': 81016, 'loss/train': 1.2821478843688965} 08/31/2021 03:53:18 - INFO - __main__ - Step 81018: {'lr': 0.0002234263602823819, 'samples': 15555456, 'steps': 81017, 'loss/train': 1.9426287412643433} 08/31/2021 03:53:18 - INFO - __main__ - Step 81019: {'lr': 0.0002234210836083977, 'samples': 15555648, 'steps': 81018, 'loss/train': 1.1408339738845825} 08/31/2021 03:53:19 - INFO - __main__ - Step 81020: {'lr': 0.00022341580694638946, 'samples': 15555840, 'steps': 81019, 'loss/train': 0.9405965209007263} 08/31/2021 03:53:19 - INFO - __main__ - Step 81021: {'lr': 0.00022341053029635967, 'samples': 15556032, 'steps': 81020, 'loss/train': 1.5435912609100342} 08/31/2021 03:53:21 - INFO - __main__ - Step 81022: {'lr': 0.0002234052536583107, 'samples': 15556224, 'steps': 81021, 'loss/train': 1.3510570526123047} 08/31/2021 03:53:21 - INFO - __main__ - Step 81023: {'lr': 0.00022339997703224492, 'samples': 15556416, 'steps': 81022, 'loss/train': 1.8252549171447754} 08/31/2021 03:53:21 - INFO - __main__ - Step 81024: {'lr': 0.00022339470041816468, 'samples': 15556608, 'steps': 81023, 'loss/train': 1.1310713291168213} 08/31/2021 03:53:22 - INFO - __main__ - Step 81025: {'lr': 0.00022338942381607238, 'samples': 15556800, 'steps': 81024, 'loss/train': 1.248489260673523} 08/31/2021 03:53:22 - INFO - __main__ - Step 81026: {'lr': 0.0002233841472259704, 'samples': 15556992, 'steps': 81025, 'loss/train': 0.06222968548536301} 08/31/2021 03:53:22 - INFO - __main__ - Step 81027: {'lr': 0.00022337887064786109, 'samples': 15557184, 'steps': 81026, 'loss/train': 1.3524235486984253} 08/31/2021 03:53:24 - INFO - __main__ - Step 81028: {'lr': 0.00022337359408174687, 'samples': 15557376, 'steps': 81027, 'loss/train': 1.6100788116455078} 08/31/2021 03:53:24 - INFO - __main__ - Step 81029: {'lr': 0.0002233683175276301, 'samples': 15557568, 'steps': 81028, 'loss/train': 1.0962486267089844} 08/31/2021 03:53:25 - INFO - __main__ - Step 81030: {'lr': 0.00022336304098551318, 'samples': 15557760, 'steps': 81029, 'loss/train': 0.6971392035484314} 08/31/2021 03:53:25 - INFO - __main__ - Step 81031: {'lr': 0.00022335776445539843, 'samples': 15557952, 'steps': 81030, 'loss/train': 1.430138111114502} 08/31/2021 03:53:27 - INFO - __main__ - Step 81032: {'lr': 0.00022335248793728824, 'samples': 15558144, 'steps': 81031, 'loss/train': 1.4066740274429321} 08/31/2021 03:53:27 - INFO - __main__ - Step 81033: {'lr': 0.00022334721143118502, 'samples': 15558336, 'steps': 81032, 'loss/train': 1.724138855934143} 08/31/2021 03:53:28 - INFO - __main__ - Step 81034: {'lr': 0.00022334193493709115, 'samples': 15558528, 'steps': 81033, 'loss/train': 2.030888795852661} 08/31/2021 03:53:28 - INFO - __main__ - Step 81035: {'lr': 0.000223336658455009, 'samples': 15558720, 'steps': 81034, 'loss/train': 0.027231186628341675} 08/31/2021 03:53:28 - INFO - __main__ - Step 81036: {'lr': 0.00022333138198494092, 'samples': 15558912, 'steps': 81035, 'loss/train': 1.7895736694335938} 08/31/2021 03:53:29 - INFO - __main__ - Step 81037: {'lr': 0.00022332610552688937, 'samples': 15559104, 'steps': 81036, 'loss/train': 1.2703975439071655} 08/31/2021 03:53:29 - INFO - __main__ - Step 81038: {'lr': 0.0002233208290808566, 'samples': 15559296, 'steps': 81037, 'loss/train': 0.9086210131645203} 08/31/2021 03:53:30 - INFO - __main__ - Step 81039: {'lr': 0.00022331555264684506, 'samples': 15559488, 'steps': 81038, 'loss/train': 0.7512509822845459} 08/31/2021 03:53:31 - INFO - __main__ - Step 81040: {'lr': 0.00022331027622485712, 'samples': 15559680, 'steps': 81039, 'loss/train': 1.2401658296585083} 08/31/2021 03:53:31 - INFO - __main__ - Step 81041: {'lr': 0.00022330499981489522, 'samples': 15559872, 'steps': 81040, 'loss/train': 1.5429736375808716} 08/31/2021 03:53:32 - INFO - __main__ - Step 81042: {'lr': 0.00022329972341696158, 'samples': 15560064, 'steps': 81041, 'loss/train': 1.51185941696167} 08/31/2021 03:53:32 - INFO - __main__ - Step 81043: {'lr': 0.00022329444703105873, 'samples': 15560256, 'steps': 81042, 'loss/train': 0.5514065027236938} 08/31/2021 03:53:33 - INFO - __main__ - Step 81044: {'lr': 0.00022328917065718895, 'samples': 15560448, 'steps': 81043, 'loss/train': 1.117154598236084} 08/31/2021 03:53:34 - INFO - __main__ - Step 81045: {'lr': 0.00022328389429535469, 'samples': 15560640, 'steps': 81044, 'loss/train': 0.8992335796356201} 08/31/2021 03:53:34 - INFO - __main__ - Step 81046: {'lr': 0.00022327861794555826, 'samples': 15560832, 'steps': 81045, 'loss/train': 0.8496584296226501} 08/31/2021 03:53:35 - INFO - __main__ - Step 81047: {'lr': 0.0002232733416078021, 'samples': 15561024, 'steps': 81046, 'loss/train': 0.962186336517334} 08/31/2021 03:53:35 - INFO - __main__ - Step 81048: {'lr': 0.00022326806528208854, 'samples': 15561216, 'steps': 81047, 'loss/train': 1.6409077644348145} 08/31/2021 03:53:36 - INFO - __main__ - Step 81049: {'lr': 0.00022326278896841998, 'samples': 15561408, 'steps': 81048, 'loss/train': 1.4752150774002075} 08/31/2021 03:53:37 - INFO - __main__ - Step 81050: {'lr': 0.00022325751266679886, 'samples': 15561600, 'steps': 81049, 'loss/train': 0.9104405045509338} 08/31/2021 03:53:37 - INFO - __main__ - Step 81051: {'lr': 0.0002232522363772275, 'samples': 15561792, 'steps': 81050, 'loss/train': 1.7089194059371948} 08/31/2021 03:53:37 - INFO - __main__ - Step 81052: {'lr': 0.00022324696009970817, 'samples': 15561984, 'steps': 81051, 'loss/train': 1.1797144412994385} 08/31/2021 03:53:38 - INFO - __main__ - Step 81053: {'lr': 0.0002232416838342434, 'samples': 15562176, 'steps': 81052, 'loss/train': 1.2421244382858276} 08/31/2021 03:53:40 - INFO - __main__ - Step 81054: {'lr': 0.00022323640758083548, 'samples': 15562368, 'steps': 81053, 'loss/train': 0.7707110643386841} 08/31/2021 03:53:40 - INFO - __main__ - Step 81055: {'lr': 0.00022323113133948687, 'samples': 15562560, 'steps': 81054, 'loss/train': 1.083719253540039} 08/31/2021 03:53:41 - INFO - __main__ - Step 81056: {'lr': 0.00022322585511019984, 'samples': 15562752, 'steps': 81055, 'loss/train': 1.6758277416229248} 08/31/2021 03:53:41 - INFO - __main__ - Step 81057: {'lr': 0.00022322057889297687, 'samples': 15562944, 'steps': 81056, 'loss/train': 1.547656536102295} 08/31/2021 03:53:41 - INFO - __main__ - Step 81058: {'lr': 0.00022321530268782025, 'samples': 15563136, 'steps': 81057, 'loss/train': 1.4719150066375732} 08/31/2021 03:53:43 - INFO - __main__ - Step 81059: {'lr': 0.00022321002649473243, 'samples': 15563328, 'steps': 81058, 'loss/train': 0.6161725521087646} 08/31/2021 03:53:43 - INFO - __main__ - Step 81060: {'lr': 0.00022320475031371577, 'samples': 15563520, 'steps': 81059, 'loss/train': 0.96820068359375} 08/31/2021 03:53:44 - INFO - __main__ - Step 81061: {'lr': 0.0002231994741447726, 'samples': 15563712, 'steps': 81060, 'loss/train': 0.511599063873291} 08/31/2021 03:53:44 - INFO - __main__ - Step 81062: {'lr': 0.00022319419798790539, 'samples': 15563904, 'steps': 81061, 'loss/train': 1.6521189212799072} 08/31/2021 03:53:44 - INFO - __main__ - Step 81063: {'lr': 0.00022318892184311652, 'samples': 15564096, 'steps': 81062, 'loss/train': 0.7645238041877747} 08/31/2021 03:53:45 - INFO - __main__ - Step 81064: {'lr': 0.00022318364571040822, 'samples': 15564288, 'steps': 81063, 'loss/train': 1.037861704826355} 08/31/2021 03:53:46 - INFO - __main__ - Step 81065: {'lr': 0.00022317836958978294, 'samples': 15564480, 'steps': 81064, 'loss/train': 1.0291739702224731} 08/31/2021 03:53:47 - INFO - __main__ - Step 81066: {'lr': 0.0002231730934812431, 'samples': 15564672, 'steps': 81065, 'loss/train': 0.4724975824356079} 08/31/2021 03:53:47 - INFO - __main__ - Step 81067: {'lr': 0.00022316781738479104, 'samples': 15564864, 'steps': 81066, 'loss/train': 1.1174912452697754} 08/31/2021 03:53:47 - INFO - __main__ - Step 81068: {'lr': 0.00022316254130042912, 'samples': 15565056, 'steps': 81067, 'loss/train': 1.4020476341247559} 08/31/2021 03:53:48 - INFO - __main__ - Step 81069: {'lr': 0.00022315726522815978, 'samples': 15565248, 'steps': 81068, 'loss/train': 1.0381683111190796} 08/31/2021 03:53:49 - INFO - __main__ - Step 81070: {'lr': 0.00022315198916798533, 'samples': 15565440, 'steps': 81069, 'loss/train': 1.184887409210205} 08/31/2021 03:53:50 - INFO - __main__ - Step 81071: {'lr': 0.0002231467131199082, 'samples': 15565632, 'steps': 81070, 'loss/train': 0.6574893593788147} 08/31/2021 03:53:50 - INFO - __main__ - Step 81072: {'lr': 0.00022314143708393073, 'samples': 15565824, 'steps': 81071, 'loss/train': 1.3042594194412231} 08/31/2021 03:53:50 - INFO - __main__ - Step 81073: {'lr': 0.00022313616106005532, 'samples': 15566016, 'steps': 81072, 'loss/train': 0.20222207903862} 08/31/2021 03:53:51 - INFO - __main__ - Step 81074: {'lr': 0.00022313088504828435, 'samples': 15566208, 'steps': 81073, 'loss/train': 1.8993061780929565} 08/31/2021 03:53:52 - INFO - __main__ - Step 81075: {'lr': 0.0002231256090486202, 'samples': 15566400, 'steps': 81074, 'loss/train': 0.6684580445289612} 08/31/2021 03:53:53 - INFO - __main__ - Step 81076: {'lr': 0.0002231203330610652, 'samples': 15566592, 'steps': 81075, 'loss/train': 1.4835188388824463} 08/31/2021 03:53:53 - INFO - __main__ - Step 81077: {'lr': 0.0002231150570856219, 'samples': 15566784, 'steps': 81076, 'loss/train': 0.9082412123680115} 08/31/2021 03:53:53 - INFO - __main__ - Step 81078: {'lr': 0.00022310978112229243, 'samples': 15566976, 'steps': 81077, 'loss/train': 0.9790438413619995} 08/31/2021 03:53:54 - INFO - __main__ - Step 81079: {'lr': 0.00022310450517107927, 'samples': 15567168, 'steps': 81078, 'loss/train': 1.4435837268829346} 08/31/2021 03:53:55 - INFO - __main__ - Step 81080: {'lr': 0.00022309922923198483, 'samples': 15567360, 'steps': 81079, 'loss/train': 1.0395004749298096} 08/31/2021 03:53:56 - INFO - __main__ - Step 81081: {'lr': 0.00022309395330501143, 'samples': 15567552, 'steps': 81080, 'loss/train': 1.509413719177246} 08/31/2021 03:53:56 - INFO - __main__ - Step 81082: {'lr': 0.00022308867739016152, 'samples': 15567744, 'steps': 81081, 'loss/train': 1.0199658870697021} 08/31/2021 03:53:56 - INFO - __main__ - Step 81083: {'lr': 0.00022308340148743738, 'samples': 15567936, 'steps': 81082, 'loss/train': 1.9436283111572266} 08/31/2021 03:53:57 - INFO - __main__ - Step 81084: {'lr': 0.00022307812559684147, 'samples': 15568128, 'steps': 81083, 'loss/train': 1.4768297672271729} 08/31/2021 03:53:57 - INFO - __main__ - Step 81085: {'lr': 0.00022307284971837617, 'samples': 15568320, 'steps': 81084, 'loss/train': 1.413575530052185} 08/31/2021 03:53:58 - INFO - __main__ - Step 81086: {'lr': 0.00022306757385204376, 'samples': 15568512, 'steps': 81085, 'loss/train': 1.0788525342941284} 08/31/2021 03:53:59 - INFO - __main__ - Step 81087: {'lr': 0.00022306229799784675, 'samples': 15568704, 'steps': 81086, 'loss/train': 0.7873449921607971} 08/31/2021 03:53:59 - INFO - __main__ - Step 81088: {'lr': 0.0002230570221557874, 'samples': 15568896, 'steps': 81087, 'loss/train': 1.4308298826217651} 08/31/2021 03:54:00 - INFO - __main__ - Step 81089: {'lr': 0.0002230517463258682, 'samples': 15569088, 'steps': 81088, 'loss/train': 0.5437436699867249} 08/31/2021 03:54:00 - INFO - __main__ - Step 81090: {'lr': 0.00022304647050809155, 'samples': 15569280, 'steps': 81089, 'loss/train': 1.1389981508255005} 08/31/2021 03:54:01 - INFO - __main__ - Step 81091: {'lr': 0.00022304119470245963, 'samples': 15569472, 'steps': 81090, 'loss/train': 1.337844967842102} 08/31/2021 03:54:02 - INFO - __main__ - Step 81092: {'lr': 0.00022303591890897493, 'samples': 15569664, 'steps': 81091, 'loss/train': 1.2075695991516113} 08/31/2021 03:54:02 - INFO - __main__ - Step 81093: {'lr': 0.00022303064312763983, 'samples': 15569856, 'steps': 81092, 'loss/train': 1.3167637586593628} 08/31/2021 03:54:03 - INFO - __main__ - Step 81094: {'lr': 0.00022302536735845668, 'samples': 15570048, 'steps': 81093, 'loss/train': 0.5506929755210876} 08/31/2021 03:54:03 - INFO - __main__ - Step 81095: {'lr': 0.0002230200916014279, 'samples': 15570240, 'steps': 81094, 'loss/train': 0.844464898109436} 08/31/2021 03:54:05 - INFO - __main__ - Step 81096: {'lr': 0.0002230148158565559, 'samples': 15570432, 'steps': 81095, 'loss/train': 1.8201746940612793} 08/31/2021 03:54:06 - INFO - __main__ - Step 81097: {'lr': 0.00022300954012384296, 'samples': 15570624, 'steps': 81096, 'loss/train': 1.4784044027328491} 08/31/2021 03:54:06 - INFO - __main__ - Step 81098: {'lr': 0.0002230042644032915, 'samples': 15570816, 'steps': 81097, 'loss/train': 0.4202042818069458} 08/31/2021 03:54:07 - INFO - __main__ - Step 81099: {'lr': 0.00022299898869490394, 'samples': 15571008, 'steps': 81098, 'loss/train': 0.3397611081600189} 08/31/2021 03:54:07 - INFO - __main__ - Step 81100: {'lr': 0.00022299371299868258, 'samples': 15571200, 'steps': 81099, 'loss/train': 1.4076863527297974} 08/31/2021 03:54:07 - INFO - __main__ - Step 81101: {'lr': 0.00022298843731462985, 'samples': 15571392, 'steps': 81100, 'loss/train': 0.15081237256526947} 08/31/2021 03:54:08 - INFO - __main__ - Step 81102: {'lr': 0.00022298316164274813, 'samples': 15571584, 'steps': 81101, 'loss/train': 1.1271289587020874} 08/31/2021 03:54:09 - INFO - __main__ - Step 81103: {'lr': 0.00022297788598303974, 'samples': 15571776, 'steps': 81102, 'loss/train': 0.8639870285987854} 08/31/2021 03:54:10 - INFO - __main__ - Step 81104: {'lr': 0.00022297261033550722, 'samples': 15571968, 'steps': 81103, 'loss/train': 1.2583125829696655} 08/31/2021 03:54:10 - INFO - __main__ - Step 81105: {'lr': 0.00022296733470015273, 'samples': 15572160, 'steps': 81104, 'loss/train': 1.2042897939682007} 08/31/2021 03:54:10 - INFO - __main__ - Step 81106: {'lr': 0.00022296205907697874, 'samples': 15572352, 'steps': 81105, 'loss/train': 1.1185108423233032} 08/31/2021 03:54:11 - INFO - __main__ - Step 81107: {'lr': 0.00022295678346598763, 'samples': 15572544, 'steps': 81106, 'loss/train': 1.4768011569976807} 08/31/2021 03:54:13 - INFO - __main__ - Step 81108: {'lr': 0.00022295150786718178, 'samples': 15572736, 'steps': 81107, 'loss/train': 0.9500468969345093} 08/31/2021 03:54:13 - INFO - __main__ - Step 81109: {'lr': 0.00022294623228056353, 'samples': 15572928, 'steps': 81108, 'loss/train': 1.5217900276184082} 08/31/2021 03:54:14 - INFO - __main__ - Step 81110: {'lr': 0.00022294095670613535, 'samples': 15573120, 'steps': 81109, 'loss/train': 0.7346754670143127} 08/31/2021 03:54:14 - INFO - __main__ - Step 81111: {'lr': 0.0002229356811438995, 'samples': 15573312, 'steps': 81110, 'loss/train': 1.5073450803756714} 08/31/2021 03:54:14 - INFO - __main__ - Step 81112: {'lr': 0.00022293040559385848, 'samples': 15573504, 'steps': 81111, 'loss/train': 2.3887269496917725} 08/31/2021 03:54:16 - INFO - __main__ - Step 81113: {'lr': 0.00022292513005601453, 'samples': 15573696, 'steps': 81112, 'loss/train': 1.107286810874939} 08/31/2021 03:54:16 - INFO - __main__ - Step 81114: {'lr': 0.00022291985453037016, 'samples': 15573888, 'steps': 81113, 'loss/train': 1.297275424003601} 08/31/2021 03:54:17 - INFO - __main__ - Step 81115: {'lr': 0.00022291457901692764, 'samples': 15574080, 'steps': 81114, 'loss/train': 1.2697926759719849} 08/31/2021 03:54:17 - INFO - __main__ - Step 81116: {'lr': 0.0002229093035156894, 'samples': 15574272, 'steps': 81115, 'loss/train': 0.905008852481842} 08/31/2021 03:54:17 - INFO - __main__ - Step 81117: {'lr': 0.00022290402802665793, 'samples': 15574464, 'steps': 81116, 'loss/train': 1.5483027696609497} 08/31/2021 03:54:19 - INFO - __main__ - Step 81118: {'lr': 0.00022289875254983537, 'samples': 15574656, 'steps': 81117, 'loss/train': 0.6555827260017395} 08/31/2021 03:54:19 - INFO - __main__ - Step 81119: {'lr': 0.00022289347708522424, 'samples': 15574848, 'steps': 81118, 'loss/train': 0.9975102543830872} 08/31/2021 03:54:20 - INFO - __main__ - Step 81120: {'lr': 0.00022288820163282683, 'samples': 15575040, 'steps': 81119, 'loss/train': 1.430633544921875} 08/31/2021 03:54:20 - INFO - __main__ - Step 81121: {'lr': 0.00022288292619264565, 'samples': 15575232, 'steps': 81120, 'loss/train': 1.387539029121399} 08/31/2021 03:54:20 - INFO - __main__ - Step 81122: {'lr': 0.00022287765076468293, 'samples': 15575424, 'steps': 81121, 'loss/train': 1.5331131219863892} 08/31/2021 03:54:22 - INFO - __main__ - Step 81123: {'lr': 0.00022287237534894118, 'samples': 15575616, 'steps': 81122, 'loss/train': 1.5086145401000977} 08/31/2021 03:54:22 - INFO - __main__ - Step 81124: {'lr': 0.0002228670999454227, 'samples': 15575808, 'steps': 81123, 'loss/train': 0.09045802801847458} 08/31/2021 03:54:23 - INFO - __main__ - Step 81125: {'lr': 0.0002228618245541299, 'samples': 15576000, 'steps': 81124, 'loss/train': 1.083931565284729} 08/31/2021 03:54:23 - INFO - __main__ - Step 81126: {'lr': 0.00022285654917506513, 'samples': 15576192, 'steps': 81125, 'loss/train': 0.4121539294719696} 08/31/2021 03:54:23 - INFO - __main__ - Step 81127: {'lr': 0.0002228512738082308, 'samples': 15576384, 'steps': 81126, 'loss/train': 2.2570810317993164} 08/31/2021 03:54:24 - INFO - __main__ - Step 81128: {'lr': 0.00022284599845362924, 'samples': 15576576, 'steps': 81127, 'loss/train': 1.206504225730896} 08/31/2021 03:54:25 - INFO - __main__ - Step 81129: {'lr': 0.00022284072311126284, 'samples': 15576768, 'steps': 81128, 'loss/train': 1.7332570552825928} 08/31/2021 03:54:26 - INFO - __main__ - Step 81130: {'lr': 0.000222835447781134, 'samples': 15576960, 'steps': 81129, 'loss/train': 1.2115877866744995} 08/31/2021 03:54:26 - INFO - __main__ - Step 81131: {'lr': 0.00022283017246324524, 'samples': 15577152, 'steps': 81130, 'loss/train': 1.6355507373809814} 08/31/2021 03:54:26 - INFO - __main__ - Step 81132: {'lr': 0.00022282489715759867, 'samples': 15577344, 'steps': 81131, 'loss/train': 1.0639252662658691} 08/31/2021 03:54:27 - INFO - __main__ - Step 81133: {'lr': 0.00022281962186419674, 'samples': 15577536, 'steps': 81132, 'loss/train': 1.3146167993545532} 08/31/2021 03:54:28 - INFO - __main__ - Step 81134: {'lr': 0.00022281434658304189, 'samples': 15577728, 'steps': 81133, 'loss/train': 1.306345820426941} 08/31/2021 03:54:29 - INFO - __main__ - Step 81135: {'lr': 0.00022280907131413648, 'samples': 15577920, 'steps': 81134, 'loss/train': 1.6377441883087158} 08/31/2021 03:54:29 - INFO - __main__ - Step 81136: {'lr': 0.00022280379605748286, 'samples': 15578112, 'steps': 81135, 'loss/train': 1.0022422075271606} 08/31/2021 03:54:29 - INFO - __main__ - Step 81137: {'lr': 0.00022279852081308343, 'samples': 15578304, 'steps': 81136, 'loss/train': 0.9280018210411072} 08/31/2021 03:54:30 - INFO - __main__ - Step 81138: {'lr': 0.0002227932455809406, 'samples': 15578496, 'steps': 81137, 'loss/train': 1.2423293590545654} 08/31/2021 03:54:32 - INFO - __main__ - Step 81139: {'lr': 0.00022278797036105668, 'samples': 15578688, 'steps': 81138, 'loss/train': 1.2956767082214355} 08/31/2021 03:54:32 - INFO - __main__ - Step 81140: {'lr': 0.0002227826951534341, 'samples': 15578880, 'steps': 81139, 'loss/train': 1.581972599029541} 08/31/2021 03:54:32 - INFO - __main__ - Step 81141: {'lr': 0.00022277741995807524, 'samples': 15579072, 'steps': 81140, 'loss/train': 0.4694006145000458} 08/31/2021 03:54:33 - INFO - __main__ - Step 81142: {'lr': 0.0002227721447749825, 'samples': 15579264, 'steps': 81141, 'loss/train': 0.03524641692638397} 08/31/2021 03:54:33 - INFO - __main__ - Step 81143: {'lr': 0.00022276686960415813, 'samples': 15579456, 'steps': 81142, 'loss/train': 1.462782621383667} 08/31/2021 03:54:34 - INFO - __main__ - Step 81144: {'lr': 0.00022276159444560464, 'samples': 15579648, 'steps': 81143, 'loss/train': 1.096362590789795} 08/31/2021 03:54:35 - INFO - __main__ - Step 81145: {'lr': 0.00022275631929932432, 'samples': 15579840, 'steps': 81144, 'loss/train': 0.7180187106132507} 08/31/2021 03:54:36 - INFO - __main__ - Step 81146: {'lr': 0.00022275104416531958, 'samples': 15580032, 'steps': 81145, 'loss/train': 0.830331563949585} 08/31/2021 03:54:36 - INFO - __main__ - Step 81147: {'lr': 0.00022274576904359277, 'samples': 15580224, 'steps': 81146, 'loss/train': 0.042889825999736786} 08/31/2021 03:54:36 - INFO - __main__ - Step 81148: {'lr': 0.00022274049393414635, 'samples': 15580416, 'steps': 81147, 'loss/train': 1.1508276462554932} 08/31/2021 03:54:37 - INFO - __main__ - Step 81149: {'lr': 0.0002227352188369826, 'samples': 15580608, 'steps': 81148, 'loss/train': 1.2513808012008667} 08/31/2021 03:54:38 - INFO - __main__ - Step 81150: {'lr': 0.00022272994375210396, 'samples': 15580800, 'steps': 81149, 'loss/train': 1.4531397819519043} 08/31/2021 03:54:39 - INFO - __main__ - Step 81151: {'lr': 0.0002227246686795128, 'samples': 15580992, 'steps': 81150, 'loss/train': 0.9250515103340149} 08/31/2021 03:54:39 - INFO - __main__ - Step 81152: {'lr': 0.00022271939361921146, 'samples': 15581184, 'steps': 81151, 'loss/train': 0.9275474548339844} 08/31/2021 03:54:40 - INFO - __main__ - Step 81153: {'lr': 0.00022271411857120239, 'samples': 15581376, 'steps': 81152, 'loss/train': 1.0154459476470947} 08/31/2021 03:54:40 - INFO - __main__ - Step 81154: {'lr': 0.00022270884353548786, 'samples': 15581568, 'steps': 81153, 'loss/train': 0.7411786913871765} 08/31/2021 03:54:41 - INFO - __main__ - Step 81155: {'lr': 0.00022270356851207033, 'samples': 15581760, 'steps': 81154, 'loss/train': 0.09844258427619934} 08/31/2021 03:54:42 - INFO - __main__ - Step 81156: {'lr': 0.00022269829350095213, 'samples': 15581952, 'steps': 81155, 'loss/train': 0.9783708453178406} 08/31/2021 03:54:42 - INFO - __main__ - Step 81157: {'lr': 0.00022269301850213566, 'samples': 15582144, 'steps': 81156, 'loss/train': 0.8947803974151611} 08/31/2021 03:54:43 - INFO - __main__ - Step 81158: {'lr': 0.00022268774351562337, 'samples': 15582336, 'steps': 81157, 'loss/train': 1.942637324333191} 08/31/2021 03:54:43 - INFO - __main__ - Step 81159: {'lr': 0.0002226824685414175, 'samples': 15582528, 'steps': 81158, 'loss/train': 0.8156980872154236} 08/31/2021 03:54:45 - INFO - __main__ - Step 81160: {'lr': 0.00022267719357952045, 'samples': 15582720, 'steps': 81159, 'loss/train': 1.2830815315246582} 08/31/2021 03:54:46 - INFO - __main__ - Step 81161: {'lr': 0.00022267191862993468, 'samples': 15582912, 'steps': 81160, 'loss/train': 0.6837329864501953} 08/31/2021 03:54:46 - INFO - __main__ - Step 81162: {'lr': 0.00022266664369266248, 'samples': 15583104, 'steps': 81161, 'loss/train': 1.438975214958191} 08/31/2021 03:54:46 - INFO - __main__ - Step 81163: {'lr': 0.00022266136876770631, 'samples': 15583296, 'steps': 81162, 'loss/train': 0.8577677011489868} 08/31/2021 03:54:47 - INFO - __main__ - Step 81164: {'lr': 0.00022265609385506855, 'samples': 15583488, 'steps': 81163, 'loss/train': 1.8214377164840698} 08/31/2021 03:54:49 - INFO - __main__ - Step 81165: {'lr': 0.00022265081895475147, 'samples': 15583680, 'steps': 81164, 'loss/train': 1.1854645013809204} 08/31/2021 03:54:50 - INFO - __main__ - Step 81166: {'lr': 0.00022264554406675751, 'samples': 15583872, 'steps': 81165, 'loss/train': 1.1613670587539673} 08/31/2021 03:54:50 - INFO - __main__ - Step 81167: {'lr': 0.00022264026919108904, 'samples': 15584064, 'steps': 81166, 'loss/train': 1.698614478111267} 08/31/2021 03:54:50 - INFO - __main__ - Step 81168: {'lr': 0.00022263499432774846, 'samples': 15584256, 'steps': 81167, 'loss/train': 1.4426822662353516} 08/31/2021 03:54:51 - INFO - __main__ - Step 81169: {'lr': 0.0002226297194767381, 'samples': 15584448, 'steps': 81168, 'loss/train': 0.5399921536445618} 08/31/2021 03:54:51 - INFO - __main__ - Step 81170: {'lr': 0.00022262444463806038, 'samples': 15584640, 'steps': 81169, 'loss/train': 0.41243502497673035} 08/31/2021 03:54:51 - INFO - __main__ - Step 81171: {'lr': 0.00022261916981171774, 'samples': 15584832, 'steps': 81170, 'loss/train': 0.340715616941452} 08/31/2021 03:54:53 - INFO - __main__ - Step 81172: {'lr': 0.0002226138949977124, 'samples': 15585024, 'steps': 81171, 'loss/train': 1.2889312505722046} 08/31/2021 03:54:54 - INFO - __main__ - Step 81173: {'lr': 0.00022260862019604684, 'samples': 15585216, 'steps': 81172, 'loss/train': 1.593484878540039} 08/31/2021 03:54:54 - INFO - __main__ - Step 81174: {'lr': 0.0002226033454067234, 'samples': 15585408, 'steps': 81173, 'loss/train': 0.7841416001319885} 08/31/2021 03:54:54 - INFO - __main__ - Step 81175: {'lr': 0.0002225980706297445, 'samples': 15585600, 'steps': 81174, 'loss/train': 1.4841015338897705} 08/31/2021 03:54:55 - INFO - __main__ - Step 81176: {'lr': 0.00022259279586511245, 'samples': 15585792, 'steps': 81175, 'loss/train': 2.920262336730957} 08/31/2021 03:54:56 - INFO - __main__ - Step 81177: {'lr': 0.00022258752111282967, 'samples': 15585984, 'steps': 81176, 'loss/train': 1.1857749223709106} 08/31/2021 03:54:57 - INFO - __main__ - Step 81178: {'lr': 0.00022258224637289854, 'samples': 15586176, 'steps': 81177, 'loss/train': 1.2566741704940796} 08/31/2021 03:54:57 - INFO - __main__ - Step 81179: {'lr': 0.0002225769716453214, 'samples': 15586368, 'steps': 81178, 'loss/train': 1.0539482831954956} 08/31/2021 03:54:57 - INFO - __main__ - Step 81180: {'lr': 0.00022257169693010065, 'samples': 15586560, 'steps': 81179, 'loss/train': 1.2955090999603271} 08/31/2021 03:54:58 - INFO - __main__ - Step 81181: {'lr': 0.00022256642222723868, 'samples': 15586752, 'steps': 81180, 'loss/train': 1.2629528045654297} 08/31/2021 03:54:59 - INFO - __main__ - Step 81182: {'lr': 0.00022256114753673787, 'samples': 15586944, 'steps': 81181, 'loss/train': 1.900817632675171} 08/31/2021 03:55:00 - INFO - __main__ - Step 81183: {'lr': 0.00022255587285860057, 'samples': 15587136, 'steps': 81182, 'loss/train': 0.8529433608055115} 08/31/2021 03:55:00 - INFO - __main__ - Step 81184: {'lr': 0.00022255059819282924, 'samples': 15587328, 'steps': 81183, 'loss/train': 0.9607458710670471} 08/31/2021 03:55:00 - INFO - __main__ - Step 81185: {'lr': 0.00022254532353942614, 'samples': 15587520, 'steps': 81184, 'loss/train': 0.05705409497022629} 08/31/2021 03:55:01 - INFO - __main__ - Step 81186: {'lr': 0.0002225400488983937, 'samples': 15587712, 'steps': 81185, 'loss/train': 1.3467448949813843} 08/31/2021 03:55:02 - INFO - __main__ - Step 81187: {'lr': 0.00022253477426973427, 'samples': 15587904, 'steps': 81186, 'loss/train': 1.390552282333374} 08/31/2021 03:55:03 - INFO - __main__ - Step 81188: {'lr': 0.00022252949965345027, 'samples': 15588096, 'steps': 81187, 'loss/train': 1.039363145828247} 08/31/2021 03:55:03 - INFO - __main__ - Step 81189: {'lr': 0.000222524225049544, 'samples': 15588288, 'steps': 81188, 'loss/train': 1.6363369226455688} 08/31/2021 03:55:03 - INFO - __main__ - Step 81190: {'lr': 0.00022251895045801793, 'samples': 15588480, 'steps': 81189, 'loss/train': 1.0852853059768677} 08/31/2021 03:55:04 - INFO - __main__ - Step 81191: {'lr': 0.00022251367587887438, 'samples': 15588672, 'steps': 81190, 'loss/train': 1.4286775588989258} 08/31/2021 03:55:06 - INFO - __main__ - Step 81192: {'lr': 0.00022250840131211576, 'samples': 15588864, 'steps': 81191, 'loss/train': 1.2399790287017822} 08/31/2021 03:55:06 - INFO - __main__ - Step 81193: {'lr': 0.00022250312675774442, 'samples': 15589056, 'steps': 81192, 'loss/train': 1.1542855501174927} 08/31/2021 03:55:07 - INFO - __main__ - Step 81194: {'lr': 0.00022249785221576274, 'samples': 15589248, 'steps': 81193, 'loss/train': 0.8819241523742676} 08/31/2021 03:55:07 - INFO - __main__ - Step 81195: {'lr': 0.0002224925776861731, 'samples': 15589440, 'steps': 81194, 'loss/train': 1.5329835414886475} 08/31/2021 03:55:07 - INFO - __main__ - Step 81196: {'lr': 0.00022248730316897788, 'samples': 15589632, 'steps': 81195, 'loss/train': 1.0718640089035034} 08/31/2021 03:55:08 - INFO - __main__ - Step 81197: {'lr': 0.00022248202866417946, 'samples': 15589824, 'steps': 81196, 'loss/train': 1.2278382778167725} 08/31/2021 03:55:08 - INFO - __main__ - Step 81198: {'lr': 0.00022247675417178035, 'samples': 15590016, 'steps': 81197, 'loss/train': 0.9413731694221497} 08/31/2021 03:55:09 - INFO - __main__ - Step 81199: {'lr': 0.00022247147969178265, 'samples': 15590208, 'steps': 81198, 'loss/train': 2.150970458984375} 08/31/2021 03:55:10 - INFO - __main__ - Step 81200: {'lr': 0.0002224662052241889, 'samples': 15590400, 'steps': 81199, 'loss/train': 1.8852288722991943} 08/31/2021 03:55:10 - INFO - __main__ - Step 81201: {'lr': 0.00022246093076900143, 'samples': 15590592, 'steps': 81200, 'loss/train': 1.349224328994751} 08/31/2021 03:55:11 - INFO - __main__ - Step 81202: {'lr': 0.00022245565632622263, 'samples': 15590784, 'steps': 81201, 'loss/train': 1.310663104057312} 08/31/2021 03:55:11 - INFO - __main__ - Step 81203: {'lr': 0.00022245038189585493, 'samples': 15590976, 'steps': 81202, 'loss/train': 1.085099697113037} 08/31/2021 03:55:12 - INFO - __main__ - Step 81204: {'lr': 0.00022244510747790062, 'samples': 15591168, 'steps': 81203, 'loss/train': 1.2060387134552002} 08/31/2021 03:55:13 - INFO - __main__ - Step 81205: {'lr': 0.00022243983307236213, 'samples': 15591360, 'steps': 81204, 'loss/train': 0.8481497168540955} 08/31/2021 03:55:13 - INFO - __main__ - Step 81206: {'lr': 0.00022243455867924184, 'samples': 15591552, 'steps': 81205, 'loss/train': 0.8539053201675415} 08/31/2021 03:55:14 - INFO - __main__ - Step 81207: {'lr': 0.0002224292842985421, 'samples': 15591744, 'steps': 81206, 'loss/train': 1.4117318391799927} 08/31/2021 03:55:14 - INFO - __main__ - Step 81208: {'lr': 0.00022242400993026528, 'samples': 15591936, 'steps': 81207, 'loss/train': 1.5301789045333862} 08/31/2021 03:55:15 - INFO - __main__ - Step 81209: {'lr': 0.0002224187355744138, 'samples': 15592128, 'steps': 81208, 'loss/train': 1.3944921493530273} 08/31/2021 03:55:16 - INFO - __main__ - Step 81210: {'lr': 0.00022241346123099, 'samples': 15592320, 'steps': 81209, 'loss/train': 1.15073823928833} 08/31/2021 03:55:16 - INFO - __main__ - Step 81211: {'lr': 0.00022240818689999643, 'samples': 15592512, 'steps': 81210, 'loss/train': 1.3115545511245728} 08/31/2021 03:55:17 - INFO - __main__ - Step 81212: {'lr': 0.00022240291258143513, 'samples': 15592704, 'steps': 81211, 'loss/train': 0.7616055607795715} 08/31/2021 03:55:17 - INFO - __main__ - Step 81213: {'lr': 0.00022239763827530868, 'samples': 15592896, 'steps': 81212, 'loss/train': 1.5348560810089111} 08/31/2021 03:55:18 - INFO - __main__ - Step 81214: {'lr': 0.00022239236398161944, 'samples': 15593088, 'steps': 81213, 'loss/train': 1.362579584121704} 08/31/2021 03:55:19 - INFO - __main__ - Step 81215: {'lr': 0.00022238708970036974, 'samples': 15593280, 'steps': 81214, 'loss/train': 1.1129286289215088} 08/31/2021 03:55:19 - INFO - __main__ - Step 81216: {'lr': 0.00022238181543156202, 'samples': 15593472, 'steps': 81215, 'loss/train': 1.4115217924118042} 08/31/2021 03:55:20 - INFO - __main__ - Step 81217: {'lr': 0.00022237654117519863, 'samples': 15593664, 'steps': 81216, 'loss/train': 1.7648918628692627} 08/31/2021 03:55:20 - INFO - __main__ - Step 81218: {'lr': 0.00022237126693128192, 'samples': 15593856, 'steps': 81217, 'loss/train': 1.021330714225769} 08/31/2021 03:55:22 - INFO - __main__ - Step 81219: {'lr': 0.0002223659926998143, 'samples': 15594048, 'steps': 81218, 'loss/train': 1.6093246936798096} 08/31/2021 03:55:23 - INFO - __main__ - Step 81220: {'lr': 0.00022236071848079814, 'samples': 15594240, 'steps': 81219, 'loss/train': 2.0919973850250244} 08/31/2021 03:55:23 - INFO - __main__ - Step 81221: {'lr': 0.00022235544427423582, 'samples': 15594432, 'steps': 81220, 'loss/train': 1.0497214794158936} 08/31/2021 03:55:23 - INFO - __main__ - Step 81222: {'lr': 0.0002223501700801297, 'samples': 15594624, 'steps': 81221, 'loss/train': 0.9738814234733582} 08/31/2021 03:55:24 - INFO - __main__ - Step 81223: {'lr': 0.00022234489589848216, 'samples': 15594816, 'steps': 81222, 'loss/train': 0.5837546586990356} 08/31/2021 03:55:24 - INFO - __main__ - Step 81224: {'lr': 0.00022233962172929562, 'samples': 15595008, 'steps': 81223, 'loss/train': 0.3260704576969147} 08/31/2021 03:55:26 - INFO - __main__ - Step 81225: {'lr': 0.00022233434757257248, 'samples': 15595200, 'steps': 81224, 'loss/train': 2.440964937210083} 08/31/2021 03:55:26 - INFO - __main__ - Step 81226: {'lr': 0.00022232907342831497, 'samples': 15595392, 'steps': 81225, 'loss/train': 1.2024954557418823} 08/31/2021 03:55:26 - INFO - __main__ - Step 81227: {'lr': 0.00022232379929652558, 'samples': 15595584, 'steps': 81226, 'loss/train': 1.156670331954956} 08/31/2021 03:55:27 - INFO - __main__ - Step 81228: {'lr': 0.00022231852517720662, 'samples': 15595776, 'steps': 81227, 'loss/train': 1.2487045526504517} 08/31/2021 03:55:27 - INFO - __main__ - Step 81229: {'lr': 0.00022231325107036052, 'samples': 15595968, 'steps': 81228, 'loss/train': 1.4144779443740845} 08/31/2021 03:55:29 - INFO - __main__ - Step 81230: {'lr': 0.00022230797697598965, 'samples': 15596160, 'steps': 81229, 'loss/train': 1.4293949604034424} 08/31/2021 03:55:29 - INFO - __main__ - Step 81231: {'lr': 0.00022230270289409635, 'samples': 15596352, 'steps': 81230, 'loss/train': 1.2754476070404053} 08/31/2021 03:55:30 - INFO - __main__ - Step 81232: {'lr': 0.00022229742882468303, 'samples': 15596544, 'steps': 81231, 'loss/train': 1.0221468210220337} 08/31/2021 03:55:30 - INFO - __main__ - Step 81233: {'lr': 0.00022229215476775207, 'samples': 15596736, 'steps': 81232, 'loss/train': 1.6392852067947388} 08/31/2021 03:55:30 - INFO - __main__ - Step 81234: {'lr': 0.00022228688072330587, 'samples': 15596928, 'steps': 81233, 'loss/train': 2.3800666332244873} 08/31/2021 03:55:32 - INFO - __main__ - Step 81235: {'lr': 0.00022228160669134672, 'samples': 15597120, 'steps': 81234, 'loss/train': 2.497239112854004} 08/31/2021 03:55:32 - INFO - __main__ - Step 81236: {'lr': 0.0002222763326718771, 'samples': 15597312, 'steps': 81235, 'loss/train': 0.8293744325637817} 08/31/2021 03:55:33 - INFO - __main__ - Step 81237: {'lr': 0.00022227105866489931, 'samples': 15597504, 'steps': 81236, 'loss/train': 0.638760507106781} 08/31/2021 03:55:33 - INFO - __main__ - Step 81238: {'lr': 0.00022226578467041586, 'samples': 15597696, 'steps': 81237, 'loss/train': 2.6852872371673584} 08/31/2021 03:55:33 - INFO - __main__ - Step 81239: {'lr': 0.00022226051068842889, 'samples': 15597888, 'steps': 81238, 'loss/train': 1.517189383506775} 08/31/2021 03:55:35 - INFO - __main__ - Step 81240: {'lr': 0.00022225523671894092, 'samples': 15598080, 'steps': 81239, 'loss/train': 0.9587659239768982} 08/31/2021 03:55:35 - INFO - __main__ - Step 81241: {'lr': 0.00022224996276195435, 'samples': 15598272, 'steps': 81240, 'loss/train': 0.8824927806854248} 08/31/2021 03:55:36 - INFO - __main__ - Step 81242: {'lr': 0.00022224468881747148, 'samples': 15598464, 'steps': 81241, 'loss/train': 1.2489572763442993} 08/31/2021 03:55:36 - INFO - __main__ - Step 81243: {'lr': 0.00022223941488549475, 'samples': 15598656, 'steps': 81242, 'loss/train': 1.3290716409683228} 08/31/2021 03:55:36 - INFO - __main__ - Step 81244: {'lr': 0.00022223414096602648, 'samples': 15598848, 'steps': 81243, 'loss/train': 1.296196699142456} 08/31/2021 03:55:37 - INFO - __main__ - Step 81245: {'lr': 0.00022222886705906912, 'samples': 15599040, 'steps': 81244, 'loss/train': 1.3266743421554565} 08/31/2021 03:55:39 - INFO - __main__ - Step 81246: {'lr': 0.00022222359316462497, 'samples': 15599232, 'steps': 81245, 'loss/train': 1.3149094581604004} 08/31/2021 03:55:39 - INFO - __main__ - Step 81247: {'lr': 0.0002222183192826964, 'samples': 15599424, 'steps': 81246, 'loss/train': 0.9113367199897766} 08/31/2021 03:55:39 - INFO - __main__ - Step 81248: {'lr': 0.00022221304541328592, 'samples': 15599616, 'steps': 81247, 'loss/train': 0.03837204352021217} 08/31/2021 03:55:40 - INFO - __main__ - Step 81249: {'lr': 0.00022220777155639577, 'samples': 15599808, 'steps': 81248, 'loss/train': 1.2587717771530151} 08/31/2021 03:55:40 - INFO - __main__ - Step 81250: {'lr': 0.00022220249771202837, 'samples': 15600000, 'steps': 81249, 'loss/train': 1.4393466711044312} 08/31/2021 03:55:42 - INFO - __main__ - Step 81251: {'lr': 0.0002221972238801861, 'samples': 15600192, 'steps': 81250, 'loss/train': 1.0768436193466187} 08/31/2021 03:55:42 - INFO - __main__ - Step 81252: {'lr': 0.00022219195006087142, 'samples': 15600384, 'steps': 81251, 'loss/train': 1.4103872776031494} 08/31/2021 03:55:43 - INFO - __main__ - Step 81253: {'lr': 0.0002221866762540865, 'samples': 15600576, 'steps': 81252, 'loss/train': 1.824507474899292} 08/31/2021 03:55:43 - INFO - __main__ - Step 81254: {'lr': 0.00022218140245983386, 'samples': 15600768, 'steps': 81253, 'loss/train': 1.1523357629776} 08/31/2021 03:55:43 - INFO - __main__ - Step 81255: {'lr': 0.0002221761286781159, 'samples': 15600960, 'steps': 81254, 'loss/train': 1.3341270685195923} 08/31/2021 03:55:44 - INFO - __main__ - Step 81256: {'lr': 0.00022217085490893485, 'samples': 15601152, 'steps': 81255, 'loss/train': 5.827413558959961} 08/31/2021 03:55:45 - INFO - __main__ - Step 81257: {'lr': 0.00022216558115229325, 'samples': 15601344, 'steps': 81256, 'loss/train': 1.14103364944458} 08/31/2021 03:55:46 - INFO - __main__ - Step 81258: {'lr': 0.00022216030740819338, 'samples': 15601536, 'steps': 81257, 'loss/train': 0.3946451246738434} 08/31/2021 03:55:46 - INFO - __main__ - Step 81259: {'lr': 0.00022215503367663765, 'samples': 15601728, 'steps': 81258, 'loss/train': 1.47266685962677} 08/31/2021 03:55:46 - INFO - __main__ - Step 81260: {'lr': 0.00022214975995762842, 'samples': 15601920, 'steps': 81259, 'loss/train': 1.3531662225723267} 08/31/2021 03:55:47 - INFO - __main__ - Step 81261: {'lr': 0.00022214448625116812, 'samples': 15602112, 'steps': 81260, 'loss/train': 1.170169711112976} 08/31/2021 03:55:48 - INFO - __main__ - Step 81262: {'lr': 0.00022213921255725906, 'samples': 15602304, 'steps': 81261, 'loss/train': 1.030124545097351} 08/31/2021 03:55:49 - INFO - __main__ - Step 81263: {'lr': 0.00022213393887590363, 'samples': 15602496, 'steps': 81262, 'loss/train': 1.119438886642456} 08/31/2021 03:55:49 - INFO - __main__ - Step 81264: {'lr': 0.00022212866520710423, 'samples': 15602688, 'steps': 81263, 'loss/train': 1.302961826324463} 08/31/2021 03:55:49 - INFO - __main__ - Step 81265: {'lr': 0.00022212339155086333, 'samples': 15602880, 'steps': 81264, 'loss/train': 1.0766786336898804} 08/31/2021 03:55:50 - INFO - __main__ - Step 81266: {'lr': 0.00022211811790718308, 'samples': 15603072, 'steps': 81265, 'loss/train': 1.02251136302948} 08/31/2021 03:55:50 - INFO - __main__ - Step 81267: {'lr': 0.000222112844276066, 'samples': 15603264, 'steps': 81266, 'loss/train': 1.4782769680023193} 08/31/2021 03:55:52 - INFO - __main__ - Step 81268: {'lr': 0.0002221075706575144, 'samples': 15603456, 'steps': 81267, 'loss/train': 1.1064515113830566} 08/31/2021 03:55:52 - INFO - __main__ - Step 81269: {'lr': 0.00022210229705153076, 'samples': 15603648, 'steps': 81268, 'loss/train': 1.234009861946106} 08/31/2021 03:55:52 - INFO - __main__ - Step 81270: {'lr': 0.00022209702345811735, 'samples': 15603840, 'steps': 81269, 'loss/train': 0.7098515629768372} 08/31/2021 03:55:53 - INFO - __main__ - Step 81271: {'lr': 0.0002220917498772766, 'samples': 15604032, 'steps': 81270, 'loss/train': 1.2549564838409424} 08/31/2021 03:55:53 - INFO - __main__ - Step 81272: {'lr': 0.00022208647630901087, 'samples': 15604224, 'steps': 81271, 'loss/train': 1.2912852764129639} 08/31/2021 03:55:55 - INFO - __main__ - Step 81273: {'lr': 0.00022208120275332254, 'samples': 15604416, 'steps': 81272, 'loss/train': 1.5829222202301025} 08/31/2021 03:55:56 - INFO - __main__ - Step 81274: {'lr': 0.00022207592921021403, 'samples': 15604608, 'steps': 81273, 'loss/train': 0.6898332238197327} 08/31/2021 03:55:56 - INFO - __main__ - Step 81275: {'lr': 0.00022207065567968765, 'samples': 15604800, 'steps': 81274, 'loss/train': 1.8940069675445557} 08/31/2021 03:55:56 - INFO - __main__ - Step 81276: {'lr': 0.0002220653821617458, 'samples': 15604992, 'steps': 81275, 'loss/train': 0.7272449135780334} 08/31/2021 03:55:57 - INFO - __main__ - Step 81277: {'lr': 0.0002220601086563909, 'samples': 15605184, 'steps': 81276, 'loss/train': 1.299033761024475} 08/31/2021 03:55:58 - INFO - __main__ - Step 81278: {'lr': 0.00022205483516362523, 'samples': 15605376, 'steps': 81277, 'loss/train': 0.9572373032569885} 08/31/2021 03:55:59 - INFO - __main__ - Step 81279: {'lr': 0.0002220495616834513, 'samples': 15605568, 'steps': 81278, 'loss/train': 1.6089872121810913} 08/31/2021 03:55:59 - INFO - __main__ - Step 81280: {'lr': 0.00022204428821587133, 'samples': 15605760, 'steps': 81279, 'loss/train': 1.0049793720245361} 08/31/2021 03:55:59 - INFO - __main__ - Step 81281: {'lr': 0.0002220390147608878, 'samples': 15605952, 'steps': 81280, 'loss/train': 1.0913206338882446} 08/31/2021 03:56:00 - INFO - __main__ - Step 81282: {'lr': 0.000222033741318503, 'samples': 15606144, 'steps': 81281, 'loss/train': 0.9565778374671936} 08/31/2021 03:56:01 - INFO - __main__ - Step 81283: {'lr': 0.00022202846788871942, 'samples': 15606336, 'steps': 81282, 'loss/train': 1.4271163940429688} 08/31/2021 03:56:02 - INFO - __main__ - Step 81284: {'lr': 0.00022202319447153933, 'samples': 15606528, 'steps': 81283, 'loss/train': 1.6487865447998047} 08/31/2021 03:56:02 - INFO - __main__ - Step 81285: {'lr': 0.0002220179210669652, 'samples': 15606720, 'steps': 81284, 'loss/train': 1.384352445602417} 08/31/2021 03:56:02 - INFO - __main__ - Step 81286: {'lr': 0.00022201264767499938, 'samples': 15606912, 'steps': 81285, 'loss/train': 1.4435086250305176} 08/31/2021 03:56:03 - INFO - __main__ - Step 81287: {'lr': 0.00022200737429564423, 'samples': 15607104, 'steps': 81286, 'loss/train': 0.8815749883651733} 08/31/2021 03:56:04 - INFO - __main__ - Step 81288: {'lr': 0.0002220021009289021, 'samples': 15607296, 'steps': 81287, 'loss/train': 1.3082304000854492} 08/31/2021 03:56:05 - INFO - __main__ - Step 81289: {'lr': 0.0002219968275747754, 'samples': 15607488, 'steps': 81288, 'loss/train': 1.2217381000518799} 08/31/2021 03:56:05 - INFO - __main__ - Step 81290: {'lr': 0.0002219915542332665, 'samples': 15607680, 'steps': 81289, 'loss/train': 0.5219679474830627} 08/31/2021 03:56:05 - INFO - __main__ - Step 81291: {'lr': 0.00022198628090437775, 'samples': 15607872, 'steps': 81290, 'loss/train': 1.3457809686660767} 08/31/2021 03:56:06 - INFO - __main__ - Step 81292: {'lr': 0.0002219810075881116, 'samples': 15608064, 'steps': 81291, 'loss/train': 1.1341224908828735} 08/31/2021 03:56:08 - INFO - __main__ - Step 81293: {'lr': 0.00022197573428447035, 'samples': 15608256, 'steps': 81292, 'loss/train': 0.4829605519771576} 08/31/2021 03:56:08 - INFO - __main__ - Step 81294: {'lr': 0.0002219704609934564, 'samples': 15608448, 'steps': 81293, 'loss/train': 1.164750099182129} 08/31/2021 03:56:08 - INFO - __main__ - Step 81295: {'lr': 0.0002219651877150721, 'samples': 15608640, 'steps': 81294, 'loss/train': 0.029842263087630272} 08/31/2021 03:56:09 - INFO - __main__ - Step 81296: {'lr': 0.00022195991444931985, 'samples': 15608832, 'steps': 81295, 'loss/train': 2.675550937652588} 08/31/2021 03:56:09 - INFO - __main__ - Step 81297: {'lr': 0.00022195464119620207, 'samples': 15609024, 'steps': 81296, 'loss/train': 0.7037002444267273} 08/31/2021 03:56:09 - INFO - __main__ - Step 81298: {'lr': 0.0002219493679557211, 'samples': 15609216, 'steps': 81297, 'loss/train': 0.9377514719963074} 08/31/2021 03:56:10 - INFO - __main__ - Step 81299: {'lr': 0.0002219440947278793, 'samples': 15609408, 'steps': 81298, 'loss/train': 0.7616352438926697} 08/31/2021 03:56:11 - INFO - __main__ - Step 81300: {'lr': 0.000221938821512679, 'samples': 15609600, 'steps': 81299, 'loss/train': 0.23385190963745117} 08/31/2021 03:56:12 - INFO - __main__ - Step 81301: {'lr': 0.0002219335483101227, 'samples': 15609792, 'steps': 81300, 'loss/train': 0.33186569809913635} 08/31/2021 03:56:12 - INFO - __main__ - Step 81302: {'lr': 0.0002219282751202127, 'samples': 15609984, 'steps': 81301, 'loss/train': 1.346740484237671} 08/31/2021 03:56:13 - INFO - __main__ - Step 81303: {'lr': 0.00022192300194295137, 'samples': 15610176, 'steps': 81302, 'loss/train': 1.2649800777435303} 08/31/2021 03:56:13 - INFO - __main__ - Step 81304: {'lr': 0.0002219177287783411, 'samples': 15610368, 'steps': 81303, 'loss/train': 1.4772610664367676} 08/31/2021 03:56:14 - INFO - __main__ - Step 81305: {'lr': 0.00022191245562638436, 'samples': 15610560, 'steps': 81304, 'loss/train': 1.116743564605713} 08/31/2021 03:56:15 - INFO - __main__ - Step 81306: {'lr': 0.00022190718248708333, 'samples': 15610752, 'steps': 81305, 'loss/train': 1.5329786539077759} 08/31/2021 03:56:15 - INFO - __main__ - Step 81307: {'lr': 0.0002219019093604405, 'samples': 15610944, 'steps': 81306, 'loss/train': 1.096988558769226} 08/31/2021 03:56:16 - INFO - __main__ - Step 81308: {'lr': 0.00022189663624645823, 'samples': 15611136, 'steps': 81307, 'loss/train': 1.664670705795288} 08/31/2021 03:56:16 - INFO - __main__ - Step 81309: {'lr': 0.00022189136314513898, 'samples': 15611328, 'steps': 81308, 'loss/train': 0.07391093671321869} 08/31/2021 03:56:18 - INFO - __main__ - Step 81310: {'lr': 0.00022188609005648497, 'samples': 15611520, 'steps': 81309, 'loss/train': 1.1985670328140259} 08/31/2021 03:56:18 - INFO - __main__ - Step 81311: {'lr': 0.00022188081698049867, 'samples': 15611712, 'steps': 81310, 'loss/train': 1.306648850440979} 08/31/2021 03:56:19 - INFO - __main__ - Step 81312: {'lr': 0.00022187554391718247, 'samples': 15611904, 'steps': 81311, 'loss/train': 0.06518332660198212} 08/31/2021 03:56:19 - INFO - __main__ - Step 81313: {'lr': 0.00022187027086653866, 'samples': 15612096, 'steps': 81312, 'loss/train': 1.6196345090866089} 08/31/2021 03:56:19 - INFO - __main__ - Step 81314: {'lr': 0.0002218649978285697, 'samples': 15612288, 'steps': 81313, 'loss/train': 0.8709620833396912} 08/31/2021 03:56:20 - INFO - __main__ - Step 81315: {'lr': 0.00022185972480327792, 'samples': 15612480, 'steps': 81314, 'loss/train': 1.078816294670105} 08/31/2021 03:56:21 - INFO - __main__ - Step 81316: {'lr': 0.00022185445179066573, 'samples': 15612672, 'steps': 81315, 'loss/train': 1.2644890546798706} 08/31/2021 03:56:22 - INFO - __main__ - Step 81317: {'lr': 0.00022184917879073548, 'samples': 15612864, 'steps': 81316, 'loss/train': 1.0752595663070679} 08/31/2021 03:56:22 - INFO - __main__ - Step 81318: {'lr': 0.00022184390580348956, 'samples': 15613056, 'steps': 81317, 'loss/train': 1.8139296770095825} 08/31/2021 03:56:22 - INFO - __main__ - Step 81319: {'lr': 0.0002218386328289304, 'samples': 15613248, 'steps': 81318, 'loss/train': 1.546973466873169} 08/31/2021 03:56:23 - INFO - __main__ - Step 81320: {'lr': 0.00022183335986706033, 'samples': 15613440, 'steps': 81319, 'loss/train': 0.6727402210235596} 08/31/2021 03:56:24 - INFO - __main__ - Step 81321: {'lr': 0.00022182808691788164, 'samples': 15613632, 'steps': 81320, 'loss/train': 0.4601733386516571} 08/31/2021 03:56:25 - INFO - __main__ - Step 81322: {'lr': 0.0002218228139813968, 'samples': 15613824, 'steps': 81321, 'loss/train': 1.2891615629196167} 08/31/2021 03:56:25 - INFO - __main__ - Step 81323: {'lr': 0.00022181754105760813, 'samples': 15614016, 'steps': 81322, 'loss/train': 1.0185186862945557} 08/31/2021 03:56:25 - INFO - __main__ - Step 81324: {'lr': 0.00022181226814651806, 'samples': 15614208, 'steps': 81323, 'loss/train': 1.2376376390457153} 08/31/2021 03:56:26 - INFO - __main__ - Step 81325: {'lr': 0.00022180699524812896, 'samples': 15614400, 'steps': 81324, 'loss/train': 1.560712456703186} 08/31/2021 03:56:28 - INFO - __main__ - Step 81326: {'lr': 0.00022180172236244318, 'samples': 15614592, 'steps': 81325, 'loss/train': 0.7847331166267395} 08/31/2021 03:56:28 - INFO - __main__ - Step 81327: {'lr': 0.00022179644948946308, 'samples': 15614784, 'steps': 81326, 'loss/train': 1.3153481483459473} 08/31/2021 03:56:29 - INFO - __main__ - Step 81328: {'lr': 0.0002217911766291911, 'samples': 15614976, 'steps': 81327, 'loss/train': 1.5373142957687378} 08/31/2021 03:56:29 - INFO - __main__ - Step 81329: {'lr': 0.00022178590378162956, 'samples': 15615168, 'steps': 81328, 'loss/train': 1.5369590520858765} 08/31/2021 03:56:29 - INFO - __main__ - Step 81330: {'lr': 0.00022178063094678089, 'samples': 15615360, 'steps': 81329, 'loss/train': 1.1403495073318481} 08/31/2021 03:56:30 - INFO - __main__ - Step 81331: {'lr': 0.0002217753581246474, 'samples': 15615552, 'steps': 81330, 'loss/train': 0.82725989818573} 08/31/2021 03:56:31 - INFO - __main__ - Step 81332: {'lr': 0.00022177008531523162, 'samples': 15615744, 'steps': 81331, 'loss/train': 1.3800474405288696} 08/31/2021 03:56:32 - INFO - __main__ - Step 81333: {'lr': 0.0002217648125185357, 'samples': 15615936, 'steps': 81332, 'loss/train': 1.6725119352340698} 08/31/2021 03:56:32 - INFO - __main__ - Step 81334: {'lr': 0.0002217595397345621, 'samples': 15616128, 'steps': 81333, 'loss/train': 1.1415153741836548} 08/31/2021 03:56:32 - INFO - __main__ - Step 81335: {'lr': 0.00022175426696331325, 'samples': 15616320, 'steps': 81334, 'loss/train': 1.4040862321853638} 08/31/2021 03:56:33 - INFO - __main__ - Step 81336: {'lr': 0.00022174899420479148, 'samples': 15616512, 'steps': 81335, 'loss/train': 1.4468623399734497} 08/31/2021 03:56:35 - INFO - __main__ - Step 81337: {'lr': 0.00022174372145899914, 'samples': 15616704, 'steps': 81336, 'loss/train': 0.8420079350471497} 08/31/2021 03:56:35 - INFO - __main__ - Step 81338: {'lr': 0.00022173844872593867, 'samples': 15616896, 'steps': 81337, 'loss/train': 0.07226993888616562} 08/31/2021 03:56:36 - INFO - __main__ - Step 81339: {'lr': 0.00022173317600561243, 'samples': 15617088, 'steps': 81338, 'loss/train': 0.14461059868335724} 08/31/2021 03:56:36 - INFO - __main__ - Step 81340: {'lr': 0.0002217279032980228, 'samples': 15617280, 'steps': 81339, 'loss/train': 1.5247647762298584} 08/31/2021 03:56:36 - INFO - __main__ - Step 81341: {'lr': 0.0002217226306031721, 'samples': 15617472, 'steps': 81340, 'loss/train': 1.4955973625183105} 08/31/2021 03:56:38 - INFO - __main__ - Step 81342: {'lr': 0.00022171735792106276, 'samples': 15617664, 'steps': 81341, 'loss/train': 1.9104965925216675} 08/31/2021 03:56:38 - INFO - __main__ - Step 81343: {'lr': 0.00022171208525169713, 'samples': 15617856, 'steps': 81342, 'loss/train': 0.9157038927078247} 08/31/2021 03:56:39 - INFO - __main__ - Step 81344: {'lr': 0.00022170681259507763, 'samples': 15618048, 'steps': 81343, 'loss/train': 0.8571834564208984} 08/31/2021 03:56:39 - INFO - __main__ - Step 81345: {'lr': 0.0002217015399512066, 'samples': 15618240, 'steps': 81344, 'loss/train': 1.5710200071334839} 08/31/2021 03:56:39 - INFO - __main__ - Step 81346: {'lr': 0.0002216962673200865, 'samples': 15618432, 'steps': 81345, 'loss/train': 0.47863295674324036} 08/31/2021 03:56:41 - INFO - __main__ - Step 81347: {'lr': 0.0002216909947017195, 'samples': 15618624, 'steps': 81346, 'loss/train': 1.5605969429016113} 08/31/2021 03:56:41 - INFO - __main__ - Step 81348: {'lr': 0.00022168572209610814, 'samples': 15618816, 'steps': 81347, 'loss/train': 1.4706237316131592} 08/31/2021 03:56:42 - INFO - __main__ - Step 81349: {'lr': 0.00022168044950325477, 'samples': 15619008, 'steps': 81348, 'loss/train': 1.1866581439971924} 08/31/2021 03:56:42 - INFO - __main__ - Step 81350: {'lr': 0.00022167517692316173, 'samples': 15619200, 'steps': 81349, 'loss/train': 1.1213667392730713} 08/31/2021 03:56:42 - INFO - __main__ - Step 81351: {'lr': 0.00022166990435583143, 'samples': 15619392, 'steps': 81350, 'loss/train': 1.1812043190002441} 08/31/2021 03:56:43 - INFO - __main__ - Step 81352: {'lr': 0.00022166463180126622, 'samples': 15619584, 'steps': 81351, 'loss/train': 1.2653241157531738} 08/31/2021 03:56:44 - INFO - __main__ - Step 81353: {'lr': 0.00022165935925946847, 'samples': 15619776, 'steps': 81352, 'loss/train': 1.6379457712173462} 08/31/2021 03:56:45 - INFO - __main__ - Step 81354: {'lr': 0.0002216540867304406, 'samples': 15619968, 'steps': 81353, 'loss/train': 1.592985987663269} 08/31/2021 03:56:45 - INFO - __main__ - Step 81355: {'lr': 0.00022164881421418497, 'samples': 15620160, 'steps': 81354, 'loss/train': 1.5392541885375977} 08/31/2021 03:56:45 - INFO - __main__ - Step 81356: {'lr': 0.00022164354171070396, 'samples': 15620352, 'steps': 81355, 'loss/train': 1.3832179307937622} 08/31/2021 03:56:46 - INFO - __main__ - Step 81357: {'lr': 0.00022163826921999988, 'samples': 15620544, 'steps': 81356, 'loss/train': 1.1405999660491943} 08/31/2021 03:56:47 - INFO - __main__ - Step 81358: {'lr': 0.00022163299674207517, 'samples': 15620736, 'steps': 81357, 'loss/train': 1.274831771850586} 08/31/2021 03:56:48 - INFO - __main__ - Step 81359: {'lr': 0.00022162772427693233, 'samples': 15620928, 'steps': 81358, 'loss/train': 0.7617724537849426} 08/31/2021 03:56:48 - INFO - __main__ - Step 81360: {'lr': 0.00022162245182457348, 'samples': 15621120, 'steps': 81359, 'loss/train': 0.8102594614028931} 08/31/2021 03:56:48 - INFO - __main__ - Step 81361: {'lr': 0.00022161717938500112, 'samples': 15621312, 'steps': 81360, 'loss/train': 0.8527951240539551} 08/31/2021 03:56:49 - INFO - __main__ - Step 81362: {'lr': 0.00022161190695821762, 'samples': 15621504, 'steps': 81361, 'loss/train': 1.0635124444961548} 08/31/2021 03:56:50 - INFO - __main__ - Step 81363: {'lr': 0.00022160663454422536, 'samples': 15621696, 'steps': 81362, 'loss/train': 0.41038861870765686} 08/31/2021 03:56:51 - INFO - __main__ - Step 81364: {'lr': 0.0002216013621430267, 'samples': 15621888, 'steps': 81363, 'loss/train': 2.0095627307891846} 08/31/2021 03:56:51 - INFO - __main__ - Step 81365: {'lr': 0.00022159608975462402, 'samples': 15622080, 'steps': 81364, 'loss/train': 1.677768588066101} 08/31/2021 03:56:51 - INFO - __main__ - Step 81366: {'lr': 0.00022159081737901975, 'samples': 15622272, 'steps': 81365, 'loss/train': 1.5706425905227661} 08/31/2021 03:56:52 - INFO - __main__ - Step 81367: {'lr': 0.00022158554501621616, 'samples': 15622464, 'steps': 81366, 'loss/train': 1.674764633178711} 08/31/2021 03:56:53 - INFO - __main__ - Step 81368: {'lr': 0.00022158027266621573, 'samples': 15622656, 'steps': 81367, 'loss/train': 0.9186696410179138} 08/31/2021 03:56:54 - INFO - __main__ - Step 81369: {'lr': 0.00022157500032902075, 'samples': 15622848, 'steps': 81368, 'loss/train': 1.60708487033844} 08/31/2021 03:56:54 - INFO - __main__ - Step 81370: {'lr': 0.00022156972800463365, 'samples': 15623040, 'steps': 81369, 'loss/train': 1.410237193107605} 08/31/2021 03:56:54 - INFO - __main__ - Step 81371: {'lr': 0.0002215644556930568, 'samples': 15623232, 'steps': 81370, 'loss/train': 0.9848952889442444} 08/31/2021 03:56:55 - INFO - __main__ - Step 81372: {'lr': 0.0002215591833942926, 'samples': 15623424, 'steps': 81371, 'loss/train': 1.0311893224716187} 08/31/2021 03:56:56 - INFO - __main__ - Step 81373: {'lr': 0.00022155391110834343, 'samples': 15623616, 'steps': 81372, 'loss/train': 1.1463589668273926} 08/31/2021 03:56:56 - INFO - __main__ - Step 81374: {'lr': 0.00022154863883521158, 'samples': 15623808, 'steps': 81373, 'loss/train': 2.248354196548462} 08/31/2021 03:56:57 - INFO - __main__ - Step 81375: {'lr': 0.00022154336657489947, 'samples': 15624000, 'steps': 81374, 'loss/train': 1.0515577793121338} 08/31/2021 03:56:57 - INFO - __main__ - Step 81376: {'lr': 0.00022153809432740946, 'samples': 15624192, 'steps': 81375, 'loss/train': 1.0288246870040894} 08/31/2021 03:56:57 - INFO - __main__ - Step 81377: {'lr': 0.00022153282209274396, 'samples': 15624384, 'steps': 81376, 'loss/train': 1.3860856294631958} 08/31/2021 03:56:58 - INFO - __main__ - Step 81378: {'lr': 0.0002215275498709053, 'samples': 15624576, 'steps': 81377, 'loss/train': 1.0205892324447632} 08/31/2021 03:56:59 - INFO - __main__ - Step 81379: {'lr': 0.0002215222776618959, 'samples': 15624768, 'steps': 81378, 'loss/train': 1.396028995513916} 08/31/2021 03:57:00 - INFO - __main__ - Step 81380: {'lr': 0.00022151700546571812, 'samples': 15624960, 'steps': 81379, 'loss/train': 1.409452199935913} 08/31/2021 03:57:00 - INFO - __main__ - Step 81381: {'lr': 0.00022151173328237436, 'samples': 15625152, 'steps': 81380, 'loss/train': 1.3412913084030151} 08/31/2021 03:57:00 - INFO - __main__ - Step 81382: {'lr': 0.00022150646111186695, 'samples': 15625344, 'steps': 81381, 'loss/train': 1.5094205141067505} 08/31/2021 03:57:01 - INFO - __main__ - Step 81383: {'lr': 0.0002215011889541983, 'samples': 15625536, 'steps': 81382, 'loss/train': 1.3603568077087402} 08/31/2021 03:57:03 - INFO - __main__ - Step 81384: {'lr': 0.0002214959168093708, 'samples': 15625728, 'steps': 81383, 'loss/train': 1.4930144548416138} 08/31/2021 03:57:03 - INFO - __main__ - Step 81385: {'lr': 0.00022149064467738675, 'samples': 15625920, 'steps': 81384, 'loss/train': 1.4956458806991577} 08/31/2021 03:57:04 - INFO - __main__ - Step 81386: {'lr': 0.0002214853725582487, 'samples': 15626112, 'steps': 81385, 'loss/train': 1.0467931032180786} 08/31/2021 03:57:04 - INFO - __main__ - Step 81387: {'lr': 0.00022148010045195882, 'samples': 15626304, 'steps': 81386, 'loss/train': 0.9952368140220642} 08/31/2021 03:57:04 - INFO - __main__ - Step 81388: {'lr': 0.00022147482835851954, 'samples': 15626496, 'steps': 81387, 'loss/train': 1.2416276931762695} 08/31/2021 03:57:06 - INFO - __main__ - Step 81389: {'lr': 0.00022146955627793327, 'samples': 15626688, 'steps': 81388, 'loss/train': 1.1843631267547607} 08/31/2021 03:57:06 - INFO - __main__ - Step 81390: {'lr': 0.00022146428421020238, 'samples': 15626880, 'steps': 81389, 'loss/train': 0.8227275013923645} 08/31/2021 03:57:07 - INFO - __main__ - Step 81391: {'lr': 0.00022145901215532923, 'samples': 15627072, 'steps': 81390, 'loss/train': 0.675348162651062} 08/31/2021 03:57:07 - INFO - __main__ - Step 81392: {'lr': 0.00022145374011331624, 'samples': 15627264, 'steps': 81391, 'loss/train': 0.9682301878929138} 08/31/2021 03:57:07 - INFO - __main__ - Step 81393: {'lr': 0.0002214484680841657, 'samples': 15627456, 'steps': 81392, 'loss/train': 2.028813362121582} 08/31/2021 03:57:09 - INFO - __main__ - Step 81394: {'lr': 0.00022144319606788007, 'samples': 15627648, 'steps': 81393, 'loss/train': 1.1232991218566895} 08/31/2021 03:57:10 - INFO - __main__ - Step 81395: {'lr': 0.00022143792406446172, 'samples': 15627840, 'steps': 81394, 'loss/train': 1.8277630805969238} 08/31/2021 03:57:10 - INFO - __main__ - Step 81396: {'lr': 0.00022143265207391296, 'samples': 15628032, 'steps': 81395, 'loss/train': 1.1877638101577759} 08/31/2021 03:57:10 - INFO - __main__ - Step 81397: {'lr': 0.00022142738009623626, 'samples': 15628224, 'steps': 81396, 'loss/train': 1.2215315103530884} 08/31/2021 03:57:11 - INFO - __main__ - Step 81398: {'lr': 0.00022142210813143388, 'samples': 15628416, 'steps': 81397, 'loss/train': 0.1324024796485901} 08/31/2021 03:57:11 - INFO - __main__ - Step 81399: {'lr': 0.00022141683617950828, 'samples': 15628608, 'steps': 81398, 'loss/train': 1.0474259853363037} 08/31/2021 03:57:13 - INFO - __main__ - Step 81400: {'lr': 0.00022141156424046194, 'samples': 15628800, 'steps': 81399, 'loss/train': 0.10485701262950897} 08/31/2021 03:57:13 - INFO - __main__ - Step 81401: {'lr': 0.00022140629231429698, 'samples': 15628992, 'steps': 81400, 'loss/train': 1.2002886533737183} 08/31/2021 03:57:13 - INFO - __main__ - Step 81402: {'lr': 0.0002214010204010159, 'samples': 15629184, 'steps': 81401, 'loss/train': 1.210716724395752} 08/31/2021 03:57:14 - INFO - __main__ - Step 81403: {'lr': 0.0002213957485006211, 'samples': 15629376, 'steps': 81402, 'loss/train': 1.026706337928772} 08/31/2021 03:57:14 - INFO - __main__ - Step 81404: {'lr': 0.0002213904766131149, 'samples': 15629568, 'steps': 81403, 'loss/train': 0.21009354293346405} 08/31/2021 03:57:16 - INFO - __main__ - Step 81405: {'lr': 0.00022138520473849975, 'samples': 15629760, 'steps': 81404, 'loss/train': 0.6003952622413635} 08/31/2021 03:57:16 - INFO - __main__ - Step 81406: {'lr': 0.00022137993287677795, 'samples': 15629952, 'steps': 81405, 'loss/train': 1.6419904232025146} 08/31/2021 03:57:17 - INFO - __main__ - Step 81407: {'lr': 0.00022137466102795192, 'samples': 15630144, 'steps': 81406, 'loss/train': 0.20470206439495087} 08/31/2021 03:57:17 - INFO - __main__ - Step 81408: {'lr': 0.00022136938919202403, 'samples': 15630336, 'steps': 81407, 'loss/train': 1.3072861433029175} 08/31/2021 03:57:17 - INFO - __main__ - Step 81409: {'lr': 0.00022136411736899667, 'samples': 15630528, 'steps': 81408, 'loss/train': 1.028720498085022} 08/31/2021 03:57:18 - INFO - __main__ - Step 81410: {'lr': 0.00022135884555887216, 'samples': 15630720, 'steps': 81409, 'loss/train': 1.8645254373550415} 08/31/2021 03:57:19 - INFO - __main__ - Step 81411: {'lr': 0.000221353573761653, 'samples': 15630912, 'steps': 81410, 'loss/train': 1.3904685974121094} 08/31/2021 03:57:20 - INFO - __main__ - Step 81412: {'lr': 0.00022134830197734142, 'samples': 15631104, 'steps': 81411, 'loss/train': 1.2286851406097412} 08/31/2021 03:57:20 - INFO - __main__ - Step 81413: {'lr': 0.0002213430302059399, 'samples': 15631296, 'steps': 81412, 'loss/train': 0.03418242186307907} 08/31/2021 03:57:21 - INFO - __main__ - Step 81414: {'lr': 0.0002213377584474507, 'samples': 15631488, 'steps': 81413, 'loss/train': 0.14104244112968445} 08/31/2021 03:57:21 - INFO - __main__ - Step 81415: {'lr': 0.00022133248670187628, 'samples': 15631680, 'steps': 81414, 'loss/train': 1.156541347503662} 08/31/2021 03:57:21 - INFO - __main__ - Step 81416: {'lr': 0.00022132721496921897, 'samples': 15631872, 'steps': 81415, 'loss/train': 1.4933598041534424} 08/31/2021 03:57:22 - INFO - __main__ - Step 81417: {'lr': 0.00022132194324948123, 'samples': 15632064, 'steps': 81416, 'loss/train': 0.8870672583580017} 08/31/2021 03:57:23 - INFO - __main__ - Step 81418: {'lr': 0.00022131667154266535, 'samples': 15632256, 'steps': 81417, 'loss/train': 1.7855353355407715} 08/31/2021 03:57:24 - INFO - __main__ - Step 81419: {'lr': 0.00022131139984877372, 'samples': 15632448, 'steps': 81418, 'loss/train': 1.664479374885559} 08/31/2021 03:57:24 - INFO - __main__ - Step 81420: {'lr': 0.00022130612816780878, 'samples': 15632640, 'steps': 81419, 'loss/train': 1.1531676054000854} 08/31/2021 03:57:25 - INFO - __main__ - Step 81421: {'lr': 0.0002213008564997728, 'samples': 15632832, 'steps': 81420, 'loss/train': 0.8731114864349365} 08/31/2021 03:57:25 - INFO - __main__ - Step 81422: {'lr': 0.00022129558484466826, 'samples': 15633024, 'steps': 81421, 'loss/train': 1.077886700630188} 08/31/2021 03:57:27 - INFO - __main__ - Step 81423: {'lr': 0.00022129031320249748, 'samples': 15633216, 'steps': 81422, 'loss/train': 1.273419976234436} 08/31/2021 03:57:27 - INFO - __main__ - Step 81424: {'lr': 0.0002212850415732628, 'samples': 15633408, 'steps': 81423, 'loss/train': 1.3678793907165527} 08/31/2021 03:57:27 - INFO - __main__ - Step 81425: {'lr': 0.00022127976995696665, 'samples': 15633600, 'steps': 81424, 'loss/train': 0.6416597366333008} 08/31/2021 03:57:28 - INFO - __main__ - Step 81426: {'lr': 0.00022127449835361145, 'samples': 15633792, 'steps': 81425, 'loss/train': 1.084979772567749} 08/31/2021 03:57:28 - INFO - __main__ - Step 81427: {'lr': 0.00022126922676319948, 'samples': 15633984, 'steps': 81426, 'loss/train': 0.8077211380004883} 08/31/2021 03:57:30 - INFO - __main__ - Step 81428: {'lr': 0.00022126395518573316, 'samples': 15634176, 'steps': 81427, 'loss/train': 0.8898316621780396} 08/31/2021 03:57:30 - INFO - __main__ - Step 81429: {'lr': 0.00022125868362121481, 'samples': 15634368, 'steps': 81428, 'loss/train': 0.8566944003105164} 08/31/2021 03:57:31 - INFO - __main__ - Step 81430: {'lr': 0.0002212534120696469, 'samples': 15634560, 'steps': 81429, 'loss/train': 1.0063951015472412} 08/31/2021 03:57:31 - INFO - __main__ - Step 81431: {'lr': 0.00022124814053103175, 'samples': 15634752, 'steps': 81430, 'loss/train': 1.0932347774505615} 08/31/2021 03:57:31 - INFO - __main__ - Step 81432: {'lr': 0.00022124286900537175, 'samples': 15634944, 'steps': 81431, 'loss/train': 1.1566739082336426} 08/31/2021 03:57:32 - INFO - __main__ - Step 81433: {'lr': 0.0002212375974926693, 'samples': 15635136, 'steps': 81432, 'loss/train': 1.5360673666000366} 08/31/2021 03:57:33 - INFO - __main__ - Step 81434: {'lr': 0.0002212323259929267, 'samples': 15635328, 'steps': 81433, 'loss/train': 1.1763217449188232} 08/31/2021 03:57:34 - INFO - __main__ - Step 81435: {'lr': 0.00022122705450614637, 'samples': 15635520, 'steps': 81434, 'loss/train': 1.1548264026641846} 08/31/2021 03:57:34 - INFO - __main__ - Step 81436: {'lr': 0.00022122178303233067, 'samples': 15635712, 'steps': 81435, 'loss/train': 0.736851155757904} 08/31/2021 03:57:35 - INFO - __main__ - Step 81437: {'lr': 0.000221216511571482, 'samples': 15635904, 'steps': 81436, 'loss/train': 0.6696107387542725} 08/31/2021 03:57:35 - INFO - __main__ - Step 81438: {'lr': 0.00022121124012360274, 'samples': 15636096, 'steps': 81437, 'loss/train': 0.08732550591230392} 08/31/2021 03:57:37 - INFO - __main__ - Step 81439: {'lr': 0.00022120596868869524, 'samples': 15636288, 'steps': 81438, 'loss/train': 1.106961965560913} 08/31/2021 03:57:38 - INFO - __main__ - Step 81440: {'lr': 0.00022120069726676194, 'samples': 15636480, 'steps': 81439, 'loss/train': 1.370679497718811} 08/31/2021 03:57:38 - INFO - __main__ - Step 81441: {'lr': 0.00022119542585780511, 'samples': 15636672, 'steps': 81440, 'loss/train': 1.6429402828216553} 08/31/2021 03:57:38 - INFO - __main__ - Step 81442: {'lr': 0.0002211901544618272, 'samples': 15636864, 'steps': 81441, 'loss/train': 1.1706783771514893} 08/31/2021 03:57:39 - INFO - __main__ - Step 81443: {'lr': 0.00022118488307883052, 'samples': 15637056, 'steps': 81442, 'loss/train': 0.24880251288414001} 08/31/2021 03:57:40 - INFO - __main__ - Step 81444: {'lr': 0.00022117961170881756, 'samples': 15637248, 'steps': 81443, 'loss/train': 1.0167996883392334} 08/31/2021 03:57:41 - INFO - __main__ - Step 81445: {'lr': 0.00022117434035179057, 'samples': 15637440, 'steps': 81444, 'loss/train': 0.933974027633667} 08/31/2021 03:57:41 - INFO - __main__ - Step 81446: {'lr': 0.00022116906900775197, 'samples': 15637632, 'steps': 81445, 'loss/train': 1.6549947261810303} 08/31/2021 03:57:41 - INFO - __main__ - Step 81447: {'lr': 0.00022116379767670417, 'samples': 15637824, 'steps': 81446, 'loss/train': 0.8932545185089111} 08/31/2021 03:57:42 - INFO - __main__ - Step 81448: {'lr': 0.00022115852635864948, 'samples': 15638016, 'steps': 81447, 'loss/train': 1.3874913454055786} 08/31/2021 03:57:44 - INFO - __main__ - Step 81449: {'lr': 0.00022115325505359034, 'samples': 15638208, 'steps': 81448, 'loss/train': 1.2245064973831177} 08/31/2021 03:57:44 - INFO - __main__ - Step 81450: {'lr': 0.0002211479837615291, 'samples': 15638400, 'steps': 81449, 'loss/train': 1.073526382446289} 08/31/2021 03:57:44 - INFO - __main__ - Step 81451: {'lr': 0.0002211427124824681, 'samples': 15638592, 'steps': 81450, 'loss/train': 1.9603770971298218} 08/31/2021 03:57:45 - INFO - __main__ - Step 81452: {'lr': 0.00022113744121640978, 'samples': 15638784, 'steps': 81451, 'loss/train': 2.6673989295959473} 08/31/2021 03:57:45 - INFO - __main__ - Step 81453: {'lr': 0.0002211321699633565, 'samples': 15638976, 'steps': 81452, 'loss/train': 2.6620335578918457} 08/31/2021 03:57:46 - INFO - __main__ - Step 81454: {'lr': 0.0002211268987233106, 'samples': 15639168, 'steps': 81453, 'loss/train': 1.657159447669983} 08/31/2021 03:57:46 - INFO - __main__ - Step 81455: {'lr': 0.00022112162749627452, 'samples': 15639360, 'steps': 81454, 'loss/train': 1.1328933238983154} 08/31/2021 03:57:48 - INFO - __main__ - Step 81456: {'lr': 0.00022111635628225052, 'samples': 15639552, 'steps': 81455, 'loss/train': 0.7440992593765259} 08/31/2021 03:57:48 - INFO - __main__ - Step 81457: {'lr': 0.00022111108508124106, 'samples': 15639744, 'steps': 81456, 'loss/train': 1.319069266319275} 08/31/2021 03:57:48 - INFO - __main__ - Step 81458: {'lr': 0.0002211058138932485, 'samples': 15639936, 'steps': 81457, 'loss/train': 1.612846851348877} 08/31/2021 03:57:49 - INFO - __main__ - Step 81459: {'lr': 0.00022110054271827522, 'samples': 15640128, 'steps': 81458, 'loss/train': 0.24436624348163605} 08/31/2021 03:57:49 - INFO - __main__ - Step 81460: {'lr': 0.00022109527155632358, 'samples': 15640320, 'steps': 81459, 'loss/train': 0.6206966042518616} 08/31/2021 03:57:50 - INFO - __main__ - Step 81461: {'lr': 0.00022109000040739597, 'samples': 15640512, 'steps': 81460, 'loss/train': 1.9516364336013794} 08/31/2021 03:57:51 - INFO - __main__ - Step 81462: {'lr': 0.00022108472927149475, 'samples': 15640704, 'steps': 81461, 'loss/train': 1.2525502443313599} 08/31/2021 03:57:51 - INFO - __main__ - Step 81463: {'lr': 0.0002210794581486223, 'samples': 15640896, 'steps': 81462, 'loss/train': 0.2639131546020508} 08/31/2021 03:57:52 - INFO - __main__ - Step 81464: {'lr': 0.000221074187038781, 'samples': 15641088, 'steps': 81463, 'loss/train': 1.0685276985168457} 08/31/2021 03:57:52 - INFO - __main__ - Step 81465: {'lr': 0.00022106891594197325, 'samples': 15641280, 'steps': 81464, 'loss/train': 0.9954816102981567} 08/31/2021 03:57:53 - INFO - __main__ - Step 81466: {'lr': 0.0002210636448582014, 'samples': 15641472, 'steps': 81465, 'loss/train': 1.388486623764038} 08/31/2021 03:57:54 - INFO - __main__ - Step 81467: {'lr': 0.0002210583737874679, 'samples': 15641664, 'steps': 81466, 'loss/train': 0.618189811706543} 08/31/2021 03:57:54 - INFO - __main__ - Step 81468: {'lr': 0.00022105310272977496, 'samples': 15641856, 'steps': 81467, 'loss/train': 0.05923748388886452} 08/31/2021 03:57:55 - INFO - __main__ - Step 81469: {'lr': 0.00022104783168512505, 'samples': 15642048, 'steps': 81468, 'loss/train': 0.5227741003036499} 08/31/2021 03:57:55 - INFO - __main__ - Step 81470: {'lr': 0.00022104256065352056, 'samples': 15642240, 'steps': 81469, 'loss/train': 1.6243329048156738} 08/31/2021 03:57:55 - INFO - __main__ - Step 81471: {'lr': 0.00022103728963496382, 'samples': 15642432, 'steps': 81470, 'loss/train': 1.331590175628662} 08/31/2021 03:57:57 - INFO - __main__ - Step 81472: {'lr': 0.0002210320186294572, 'samples': 15642624, 'steps': 81471, 'loss/train': 0.8261121511459351} 08/31/2021 03:57:57 - INFO - __main__ - Step 81473: {'lr': 0.00022102674763700315, 'samples': 15642816, 'steps': 81472, 'loss/train': 1.5291893482208252} 08/31/2021 03:57:58 - INFO - __main__ - Step 81474: {'lr': 0.000221021476657604, 'samples': 15643008, 'steps': 81473, 'loss/train': 1.589268445968628} 08/31/2021 03:57:58 - INFO - __main__ - Step 81475: {'lr': 0.0002210162056912621, 'samples': 15643200, 'steps': 81474, 'loss/train': 1.6496974229812622} 08/31/2021 03:57:58 - INFO - __main__ - Step 81476: {'lr': 0.00022101093473797986, 'samples': 15643392, 'steps': 81475, 'loss/train': 1.1611465215682983} 08/31/2021 03:58:00 - INFO - __main__ - Step 81477: {'lr': 0.00022100566379775965, 'samples': 15643584, 'steps': 81476, 'loss/train': 1.5701364278793335} 08/31/2021 03:58:00 - INFO - __main__ - Step 81478: {'lr': 0.00022100039287060384, 'samples': 15643776, 'steps': 81477, 'loss/train': 1.363970160484314} 08/31/2021 03:58:01 - INFO - __main__ - Step 81479: {'lr': 0.0002209951219565148, 'samples': 15643968, 'steps': 81478, 'loss/train': 1.0008922815322876} 08/31/2021 03:58:01 - INFO - __main__ - Step 81480: {'lr': 0.00022098985105549503, 'samples': 15644160, 'steps': 81479, 'loss/train': 1.3605585098266602} 08/31/2021 03:58:02 - INFO - __main__ - Step 81481: {'lr': 0.00022098458016754665, 'samples': 15644352, 'steps': 81480, 'loss/train': 1.343543529510498} 08/31/2021 03:58:03 - INFO - __main__ - Step 81482: {'lr': 0.0002209793092926722, 'samples': 15644544, 'steps': 81481, 'loss/train': 2.128727674484253} 08/31/2021 03:58:03 - INFO - __main__ - Step 81483: {'lr': 0.00022097403843087402, 'samples': 15644736, 'steps': 81482, 'loss/train': 1.1504517793655396} 08/31/2021 03:58:04 - INFO - __main__ - Step 81484: {'lr': 0.0002209687675821545, 'samples': 15644928, 'steps': 81483, 'loss/train': 0.21715950965881348} 08/31/2021 03:58:04 - INFO - __main__ - Step 81485: {'lr': 0.000220963496746516, 'samples': 15645120, 'steps': 81484, 'loss/train': 0.9513477087020874} 08/31/2021 03:58:05 - INFO - __main__ - Step 81486: {'lr': 0.0002209582259239609, 'samples': 15645312, 'steps': 81485, 'loss/train': 1.2352497577667236} 08/31/2021 03:58:06 - INFO - __main__ - Step 81487: {'lr': 0.00022095295511449155, 'samples': 15645504, 'steps': 81486, 'loss/train': 0.784654974937439} 08/31/2021 03:58:07 - INFO - __main__ - Step 81488: {'lr': 0.00022094768431811035, 'samples': 15645696, 'steps': 81487, 'loss/train': 1.0880296230316162} 08/31/2021 03:58:07 - INFO - __main__ - Step 81489: {'lr': 0.0002209424135348197, 'samples': 15645888, 'steps': 81488, 'loss/train': 1.0118759870529175} 08/31/2021 03:58:07 - INFO - __main__ - Step 81490: {'lr': 0.00022093714276462194, 'samples': 15646080, 'steps': 81489, 'loss/train': 1.2140835523605347} 08/31/2021 03:58:08 - INFO - __main__ - Step 81491: {'lr': 0.00022093187200751947, 'samples': 15646272, 'steps': 81490, 'loss/train': 1.0809481143951416} 08/31/2021 03:58:08 - INFO - __main__ - Step 81492: {'lr': 0.00022092660126351462, 'samples': 15646464, 'steps': 81491, 'loss/train': 1.260490894317627} 08/31/2021 03:58:09 - INFO - __main__ - Step 81493: {'lr': 0.0002209213305326098, 'samples': 15646656, 'steps': 81492, 'loss/train': 0.4540611803531647} 08/31/2021 03:58:10 - INFO - __main__ - Step 81494: {'lr': 0.00022091605981480752, 'samples': 15646848, 'steps': 81493, 'loss/train': 1.467560052871704} 08/31/2021 03:58:10 - INFO - __main__ - Step 81495: {'lr': 0.00022091078911010988, 'samples': 15647040, 'steps': 81494, 'loss/train': 1.657295823097229} 08/31/2021 03:58:10 - INFO - __main__ - Step 81496: {'lr': 0.0002209055184185194, 'samples': 15647232, 'steps': 81495, 'loss/train': 1.5232230424880981} 08/31/2021 03:58:11 - INFO - __main__ - Step 81497: {'lr': 0.00022090024774003847, 'samples': 15647424, 'steps': 81496, 'loss/train': 1.0251176357269287} 08/31/2021 03:58:13 - INFO - __main__ - Step 81498: {'lr': 0.0002208949770746694, 'samples': 15647616, 'steps': 81497, 'loss/train': 1.1184691190719604} 08/31/2021 03:58:13 - INFO - __main__ - Step 81499: {'lr': 0.00022088970642241462, 'samples': 15647808, 'steps': 81498, 'loss/train': 0.8826694488525391} 08/31/2021 03:58:14 - INFO - __main__ - Step 81500: {'lr': 0.00022088443578327648, 'samples': 15648000, 'steps': 81499, 'loss/train': 1.0799076557159424} 08/31/2021 03:58:14 - INFO - __main__ - Step 81501: {'lr': 0.00022087916515725736, 'samples': 15648192, 'steps': 81500, 'loss/train': 1.1557334661483765} 08/31/2021 03:58:14 - INFO - __main__ - Step 81502: {'lr': 0.00022087389454435966, 'samples': 15648384, 'steps': 81501, 'loss/train': 1.1047720909118652} 08/31/2021 03:58:16 - INFO - __main__ - Step 81503: {'lr': 0.0002208686239445857, 'samples': 15648576, 'steps': 81502, 'loss/train': 0.06849173456430435} 08/31/2021 03:58:16 - INFO - __main__ - Step 81504: {'lr': 0.00022086335335793792, 'samples': 15648768, 'steps': 81503, 'loss/train': 1.326446294784546} 08/31/2021 03:58:17 - INFO - __main__ - Step 81505: {'lr': 0.00022085808278441866, 'samples': 15648960, 'steps': 81504, 'loss/train': 1.0848559141159058} 08/31/2021 03:58:17 - INFO - __main__ - Step 81506: {'lr': 0.00022085281222403028, 'samples': 15649152, 'steps': 81505, 'loss/train': 0.8959706425666809} 08/31/2021 03:58:17 - INFO - __main__ - Step 81507: {'lr': 0.00022084754167677527, 'samples': 15649344, 'steps': 81506, 'loss/train': 0.5009400248527527} 08/31/2021 03:58:19 - INFO - __main__ - Step 81508: {'lr': 0.00022084227114265584, 'samples': 15649536, 'steps': 81507, 'loss/train': 1.1916364431381226} 08/31/2021 03:58:19 - INFO - __main__ - Step 81509: {'lr': 0.0002208370006216744, 'samples': 15649728, 'steps': 81508, 'loss/train': 1.8311631679534912} 08/31/2021 03:58:20 - INFO - __main__ - Step 81510: {'lr': 0.0002208317301138334, 'samples': 15649920, 'steps': 81509, 'loss/train': 1.066001057624817} 08/31/2021 03:58:20 - INFO - __main__ - Step 81511: {'lr': 0.00022082645961913513, 'samples': 15650112, 'steps': 81510, 'loss/train': 1.0681648254394531} 08/31/2021 03:58:20 - INFO - __main__ - Step 81512: {'lr': 0.00022082118913758204, 'samples': 15650304, 'steps': 81511, 'loss/train': 0.6391887664794922} 08/31/2021 03:58:21 - INFO - __main__ - Step 81513: {'lr': 0.00022081591866917645, 'samples': 15650496, 'steps': 81512, 'loss/train': 1.4013197422027588} 08/31/2021 03:58:22 - INFO - __main__ - Step 81514: {'lr': 0.00022081064821392074, 'samples': 15650688, 'steps': 81513, 'loss/train': 1.556177020072937} 08/31/2021 03:58:23 - INFO - __main__ - Step 81515: {'lr': 0.00022080537777181733, 'samples': 15650880, 'steps': 81514, 'loss/train': 1.0307343006134033} 08/31/2021 03:58:23 - INFO - __main__ - Step 81516: {'lr': 0.00022080010734286856, 'samples': 15651072, 'steps': 81515, 'loss/train': 1.12687349319458} 08/31/2021 03:58:24 - INFO - __main__ - Step 81517: {'lr': 0.0002207948369270768, 'samples': 15651264, 'steps': 81516, 'loss/train': 1.2799745798110962} 08/31/2021 03:58:24 - INFO - __main__ - Step 81518: {'lr': 0.00022078956652444445, 'samples': 15651456, 'steps': 81517, 'loss/train': 0.9325786232948303} 08/31/2021 03:58:25 - INFO - __main__ - Step 81519: {'lr': 0.00022078429613497385, 'samples': 15651648, 'steps': 81518, 'loss/train': 1.4700490236282349} 08/31/2021 03:58:26 - INFO - __main__ - Step 81520: {'lr': 0.00022077902575866744, 'samples': 15651840, 'steps': 81519, 'loss/train': 1.1376177072525024} 08/31/2021 03:58:26 - INFO - __main__ - Step 81521: {'lr': 0.00022077375539552763, 'samples': 15652032, 'steps': 81520, 'loss/train': 1.5856727361679077} 08/31/2021 03:58:26 - INFO - __main__ - Step 81522: {'lr': 0.0002207684850455566, 'samples': 15652224, 'steps': 81521, 'loss/train': 1.587440013885498} 08/31/2021 03:58:27 - INFO - __main__ - Step 81523: {'lr': 0.00022076321470875684, 'samples': 15652416, 'steps': 81522, 'loss/train': 0.15659596025943756} 08/31/2021 03:58:28 - INFO - __main__ - Step 81524: {'lr': 0.00022075794438513073, 'samples': 15652608, 'steps': 81523, 'loss/train': 1.1081470251083374} 08/31/2021 03:58:29 - INFO - __main__ - Step 81525: {'lr': 0.00022075267407468063, 'samples': 15652800, 'steps': 81524, 'loss/train': 1.1498668193817139} 08/31/2021 03:58:29 - INFO - __main__ - Step 81526: {'lr': 0.00022074740377740892, 'samples': 15652992, 'steps': 81525, 'loss/train': 1.3770875930786133} 08/31/2021 03:58:29 - INFO - __main__ - Step 81527: {'lr': 0.000220742133493318, 'samples': 15653184, 'steps': 81526, 'loss/train': 1.1923372745513916} 08/31/2021 03:58:30 - INFO - __main__ - Step 81528: {'lr': 0.00022073686322241021, 'samples': 15653376, 'steps': 81527, 'loss/train': 1.2283074855804443} 08/31/2021 03:58:31 - INFO - __main__ - Step 81529: {'lr': 0.00022073159296468796, 'samples': 15653568, 'steps': 81528, 'loss/train': 1.0992379188537598} 08/31/2021 03:58:32 - INFO - __main__ - Step 81530: {'lr': 0.00022072632272015358, 'samples': 15653760, 'steps': 81529, 'loss/train': 4.408356666564941} 08/31/2021 03:58:32 - INFO - __main__ - Step 81531: {'lr': 0.00022072105248880947, 'samples': 15653952, 'steps': 81530, 'loss/train': 5.786291122436523} 08/31/2021 03:58:33 - INFO - __main__ - Step 81532: {'lr': 0.000220715782270658, 'samples': 15654144, 'steps': 81531, 'loss/train': 1.2292886972427368} 08/31/2021 03:58:33 - INFO - __main__ - Step 81533: {'lr': 0.00022071051206570155, 'samples': 15654336, 'steps': 81532, 'loss/train': 1.3798327445983887} 08/31/2021 03:58:33 - INFO - __main__ - Step 81534: {'lr': 0.0002207052418739426, 'samples': 15654528, 'steps': 81533, 'loss/train': 1.1262563467025757} 08/31/2021 03:58:35 - INFO - __main__ - Step 81535: {'lr': 0.00022069997169538332, 'samples': 15654720, 'steps': 81534, 'loss/train': 1.5474421977996826} 08/31/2021 03:58:35 - INFO - __main__ - Step 81536: {'lr': 0.00022069470153002617, 'samples': 15654912, 'steps': 81535, 'loss/train': 0.9326137900352478} 08/31/2021 03:58:36 - INFO - __main__ - Step 81537: {'lr': 0.00022068943137787354, 'samples': 15655104, 'steps': 81536, 'loss/train': 1.2037323713302612} 08/31/2021 03:58:36 - INFO - __main__ - Step 81538: {'lr': 0.00022068416123892777, 'samples': 15655296, 'steps': 81537, 'loss/train': 1.246264100074768} 08/31/2021 03:58:36 - INFO - __main__ - Step 81539: {'lr': 0.00022067889111319127, 'samples': 15655488, 'steps': 81538, 'loss/train': 0.8589525818824768} 08/31/2021 03:58:37 - INFO - __main__ - Step 81540: {'lr': 0.00022067362100066645, 'samples': 15655680, 'steps': 81539, 'loss/train': 1.6575664281845093} 08/31/2021 03:58:38 - INFO - __main__ - Step 81541: {'lr': 0.00022066835090135562, 'samples': 15655872, 'steps': 81540, 'loss/train': 1.3464548587799072} 08/31/2021 03:58:39 - INFO - __main__ - Step 81542: {'lr': 0.00022066308081526118, 'samples': 15656064, 'steps': 81541, 'loss/train': 0.7277238368988037} 08/31/2021 03:58:39 - INFO - __main__ - Step 81543: {'lr': 0.0002206578107423855, 'samples': 15656256, 'steps': 81542, 'loss/train': 0.7277891635894775} 08/31/2021 03:58:39 - INFO - __main__ - Step 81544: {'lr': 0.00022065254068273096, 'samples': 15656448, 'steps': 81543, 'loss/train': 1.6933637857437134} 08/31/2021 03:58:40 - INFO - __main__ - Step 81545: {'lr': 0.0002206472706363, 'samples': 15656640, 'steps': 81544, 'loss/train': 0.8712599277496338} 08/31/2021 03:58:41 - INFO - __main__ - Step 81546: {'lr': 0.00022064200060309486, 'samples': 15656832, 'steps': 81545, 'loss/train': 0.430493026971817} 08/31/2021 03:58:42 - INFO - __main__ - Step 81547: {'lr': 0.000220636730583118, 'samples': 15657024, 'steps': 81546, 'loss/train': 0.8768284916877747} 08/31/2021 03:58:42 - INFO - __main__ - Step 81548: {'lr': 0.0002206314605763718, 'samples': 15657216, 'steps': 81547, 'loss/train': 1.7485977411270142} 08/31/2021 03:58:42 - INFO - __main__ - Step 81549: {'lr': 0.00022062619058285855, 'samples': 15657408, 'steps': 81548, 'loss/train': 1.48787522315979} 08/31/2021 03:58:43 - INFO - __main__ - Step 81550: {'lr': 0.0002206209206025807, 'samples': 15657600, 'steps': 81549, 'loss/train': 1.1982442140579224} 08/31/2021 03:58:45 - INFO - __main__ - Step 81551: {'lr': 0.00022061565063554063, 'samples': 15657792, 'steps': 81550, 'loss/train': 0.6801550984382629} 08/31/2021 03:58:45 - INFO - __main__ - Step 81552: {'lr': 0.00022061038068174065, 'samples': 15657984, 'steps': 81551, 'loss/train': 1.4404692649841309} 08/31/2021 03:58:46 - INFO - __main__ - Step 81553: {'lr': 0.00022060511074118322, 'samples': 15658176, 'steps': 81552, 'loss/train': 1.2802519798278809} 08/31/2021 03:58:46 - INFO - __main__ - Step 81554: {'lr': 0.00022059984081387066, 'samples': 15658368, 'steps': 81553, 'loss/train': 1.2804820537567139} 08/31/2021 03:58:46 - INFO - __main__ - Step 81555: {'lr': 0.00022059457089980533, 'samples': 15658560, 'steps': 81554, 'loss/train': 1.7338615655899048} 08/31/2021 03:58:48 - INFO - __main__ - Step 81556: {'lr': 0.00022058930099898974, 'samples': 15658752, 'steps': 81555, 'loss/train': 1.7612643241882324} 08/31/2021 03:58:48 - INFO - __main__ - Step 81557: {'lr': 0.00022058403111142609, 'samples': 15658944, 'steps': 81556, 'loss/train': 1.3588905334472656} 08/31/2021 03:58:49 - INFO - __main__ - Step 81558: {'lr': 0.0002205787612371168, 'samples': 15659136, 'steps': 81557, 'loss/train': 1.4974838495254517} 08/31/2021 03:58:49 - INFO - __main__ - Step 81559: {'lr': 0.00022057349137606424, 'samples': 15659328, 'steps': 81558, 'loss/train': 0.14772586524486542} 08/31/2021 03:58:49 - INFO - __main__ - Step 81560: {'lr': 0.00022056822152827086, 'samples': 15659520, 'steps': 81559, 'loss/train': 0.8983531594276428} 08/31/2021 03:58:51 - INFO - __main__ - Step 81561: {'lr': 0.00022056295169373903, 'samples': 15659712, 'steps': 81560, 'loss/train': 1.2210410833358765} 08/31/2021 03:58:51 - INFO - __main__ - Step 81562: {'lr': 0.00022055768187247103, 'samples': 15659904, 'steps': 81561, 'loss/train': 1.0120704174041748} 08/31/2021 03:58:52 - INFO - __main__ - Step 81563: {'lr': 0.00022055241206446927, 'samples': 15660096, 'steps': 81562, 'loss/train': 1.0437146425247192} 08/31/2021 03:58:52 - INFO - __main__ - Step 81564: {'lr': 0.00022054714226973617, 'samples': 15660288, 'steps': 81563, 'loss/train': 0.8485695719718933} 08/31/2021 03:58:53 - INFO - __main__ - Step 81565: {'lr': 0.000220541872488274, 'samples': 15660480, 'steps': 81564, 'loss/train': 1.1845759153366089} 08/31/2021 03:58:54 - INFO - __main__ - Step 81566: {'lr': 0.00022053660272008528, 'samples': 15660672, 'steps': 81565, 'loss/train': 1.7574810981750488} 08/31/2021 03:58:55 - INFO - __main__ - Step 81567: {'lr': 0.00022053133296517233, 'samples': 15660864, 'steps': 81566, 'loss/train': 1.4354736804962158} 08/31/2021 03:58:55 - INFO - __main__ - Step 81568: {'lr': 0.00022052606322353746, 'samples': 15661056, 'steps': 81567, 'loss/train': 0.6661167144775391} 08/31/2021 03:58:55 - INFO - __main__ - Step 81569: {'lr': 0.00022052079349518312, 'samples': 15661248, 'steps': 81568, 'loss/train': 1.17686128616333} 08/31/2021 03:58:56 - INFO - __main__ - Step 81570: {'lr': 0.0002205155237801116, 'samples': 15661440, 'steps': 81569, 'loss/train': 1.6209018230438232} 08/31/2021 03:58:57 - INFO - __main__ - Step 81571: {'lr': 0.00022051025407832537, 'samples': 15661632, 'steps': 81570, 'loss/train': 2.0024425983428955} 08/31/2021 03:58:58 - INFO - __main__ - Step 81572: {'lr': 0.00022050498438982673, 'samples': 15661824, 'steps': 81571, 'loss/train': 0.6222386956214905} 08/31/2021 03:58:58 - INFO - __main__ - Step 81573: {'lr': 0.00022049971471461814, 'samples': 15662016, 'steps': 81572, 'loss/train': 1.2176729440689087} 08/31/2021 03:58:58 - INFO - __main__ - Step 81574: {'lr': 0.00022049444505270195, 'samples': 15662208, 'steps': 81573, 'loss/train': 1.2134641408920288} 08/31/2021 03:58:59 - INFO - __main__ - Step 81575: {'lr': 0.00022048917540408046, 'samples': 15662400, 'steps': 81574, 'loss/train': 1.2972161769866943} 08/31/2021 03:59:00 - INFO - __main__ - Step 81576: {'lr': 0.00022048390576875608, 'samples': 15662592, 'steps': 81575, 'loss/train': 0.7300187945365906} 08/31/2021 03:59:01 - INFO - __main__ - Step 81577: {'lr': 0.00022047863614673118, 'samples': 15662784, 'steps': 81576, 'loss/train': 0.9652557969093323} 08/31/2021 03:59:01 - INFO - __main__ - Step 81578: {'lr': 0.00022047336653800825, 'samples': 15662976, 'steps': 81577, 'loss/train': 1.4348902702331543} 08/31/2021 03:59:01 - INFO - __main__ - Step 81579: {'lr': 0.00022046809694258949, 'samples': 15663168, 'steps': 81578, 'loss/train': 1.0089439153671265} 08/31/2021 03:59:02 - INFO - __main__ - Step 81580: {'lr': 0.00022046282736047735, 'samples': 15663360, 'steps': 81579, 'loss/train': 1.4697716236114502} 08/31/2021 03:59:02 - INFO - __main__ - Step 81581: {'lr': 0.0002204575577916742, 'samples': 15663552, 'steps': 81580, 'loss/train': 0.28578269481658936} 08/31/2021 03:59:04 - INFO - __main__ - Step 81582: {'lr': 0.00022045228823618242, 'samples': 15663744, 'steps': 81581, 'loss/train': 1.3312355279922485} 08/31/2021 03:59:04 - INFO - __main__ - Step 81583: {'lr': 0.0002204470186940044, 'samples': 15663936, 'steps': 81582, 'loss/train': 1.112342357635498} 08/31/2021 03:59:04 - INFO - __main__ - Step 81584: {'lr': 0.00022044174916514248, 'samples': 15664128, 'steps': 81583, 'loss/train': 1.3662352561950684} 08/31/2021 03:59:05 - INFO - __main__ - Step 81585: {'lr': 0.00022043647964959905, 'samples': 15664320, 'steps': 81584, 'loss/train': 1.3323943614959717} 08/31/2021 03:59:05 - INFO - __main__ - Step 81586: {'lr': 0.0002204312101473765, 'samples': 15664512, 'steps': 81585, 'loss/train': 1.2911771535873413} 08/31/2021 03:59:07 - INFO - __main__ - Step 81587: {'lr': 0.00022042594065847717, 'samples': 15664704, 'steps': 81586, 'loss/train': 5.399631977081299} 08/31/2021 03:59:07 - INFO - __main__ - Step 81588: {'lr': 0.0002204206711829035, 'samples': 15664896, 'steps': 81587, 'loss/train': 1.0568733215332031} 08/31/2021 03:59:07 - INFO - __main__ - Step 81589: {'lr': 0.00022041540172065786, 'samples': 15665088, 'steps': 81588, 'loss/train': 0.6195120811462402} 08/31/2021 03:59:08 - INFO - __main__ - Step 81590: {'lr': 0.0002204101322717425, 'samples': 15665280, 'steps': 81589, 'loss/train': 1.0925341844558716} 08/31/2021 03:59:08 - INFO - __main__ - Step 81591: {'lr': 0.00022040486283615991, 'samples': 15665472, 'steps': 81590, 'loss/train': 0.8560903072357178} 08/31/2021 03:59:10 - INFO - __main__ - Step 81592: {'lr': 0.00022039959341391238, 'samples': 15665664, 'steps': 81591, 'loss/train': 1.8700696229934692} 08/31/2021 03:59:10 - INFO - __main__ - Step 81593: {'lr': 0.00022039432400500236, 'samples': 15665856, 'steps': 81592, 'loss/train': 1.258354663848877} 08/31/2021 03:59:10 - INFO - __main__ - Step 81594: {'lr': 0.00022038905460943224, 'samples': 15666048, 'steps': 81593, 'loss/train': 1.2107839584350586} 08/31/2021 03:59:11 - INFO - __main__ - Step 81595: {'lr': 0.00022038378522720432, 'samples': 15666240, 'steps': 81594, 'loss/train': 0.040301915258169174} 08/31/2021 03:59:11 - INFO - __main__ - Step 81596: {'lr': 0.000220378515858321, 'samples': 15666432, 'steps': 81595, 'loss/train': 1.118853211402893} 08/31/2021 03:59:13 - INFO - __main__ - Step 81597: {'lr': 0.00022037324650278468, 'samples': 15666624, 'steps': 81596, 'loss/train': 1.499510407447815} 08/31/2021 03:59:13 - INFO - __main__ - Step 81598: {'lr': 0.0002203679771605977, 'samples': 15666816, 'steps': 81597, 'loss/train': 0.6318666934967041} 08/31/2021 03:59:13 - INFO - __main__ - Step 81599: {'lr': 0.00022036270783176246, 'samples': 15667008, 'steps': 81598, 'loss/train': 1.5297813415527344} 08/31/2021 03:59:14 - INFO - __main__ - Step 81600: {'lr': 0.00022035743851628133, 'samples': 15667200, 'steps': 81599, 'loss/train': 1.4256325960159302} 08/31/2021 03:59:14 - INFO - __main__ - Step 81601: {'lr': 0.00022035216921415679, 'samples': 15667392, 'steps': 81600, 'loss/train': 1.5876520872116089} 08/31/2021 03:59:17 - INFO - __main__ - Step 81602: {'lr': 0.000220346899925391, 'samples': 15667584, 'steps': 81601, 'loss/train': 0.4080903232097626} 08/31/2021 03:59:17 - INFO - __main__ - Step 81603: {'lr': 0.00022034163064998645, 'samples': 15667776, 'steps': 81602, 'loss/train': 0.5098589062690735} 08/31/2021 03:59:18 - INFO - __main__ - Step 81604: {'lr': 0.00022033636138794546, 'samples': 15667968, 'steps': 81603, 'loss/train': 1.2549808025360107} 08/31/2021 03:59:18 - INFO - __main__ - Step 81605: {'lr': 0.00022033109213927049, 'samples': 15668160, 'steps': 81604, 'loss/train': 1.0754774808883667} 08/31/2021 03:59:18 - INFO - __main__ - Step 81606: {'lr': 0.00022032582290396386, 'samples': 15668352, 'steps': 81605, 'loss/train': 1.182210087776184} 08/31/2021 03:59:19 - INFO - __main__ - Step 81607: {'lr': 0.00022032055368202794, 'samples': 15668544, 'steps': 81606, 'loss/train': 0.8944811224937439} 08/31/2021 03:59:20 - INFO - __main__ - Step 81608: {'lr': 0.00022031528447346514, 'samples': 15668736, 'steps': 81607, 'loss/train': 0.03034803830087185} 08/31/2021 03:59:21 - INFO - __main__ - Step 81609: {'lr': 0.0002203100152782778, 'samples': 15668928, 'steps': 81608, 'loss/train': 1.4039859771728516} 08/31/2021 03:59:21 - INFO - __main__ - Step 81610: {'lr': 0.00022030474609646832, 'samples': 15669120, 'steps': 81609, 'loss/train': 0.40929657220840454} 08/31/2021 03:59:22 - INFO - __main__ - Step 81611: {'lr': 0.00022029947692803908, 'samples': 15669312, 'steps': 81610, 'loss/train': 1.0236643552780151} 08/31/2021 03:59:22 - INFO - __main__ - Step 81612: {'lr': 0.00022029420777299242, 'samples': 15669504, 'steps': 81611, 'loss/train': 1.0201218128204346} 08/31/2021 03:59:22 - INFO - __main__ - Step 81613: {'lr': 0.00022028893863133074, 'samples': 15669696, 'steps': 81612, 'loss/train': 0.5810878276824951} 08/31/2021 03:59:24 - INFO - __main__ - Step 81614: {'lr': 0.0002202836695030564, 'samples': 15669888, 'steps': 81613, 'loss/train': 1.144677996635437} 08/31/2021 03:59:24 - INFO - __main__ - Step 81615: {'lr': 0.00022027840038817188, 'samples': 15670080, 'steps': 81614, 'loss/train': 2.097684144973755} 08/31/2021 03:59:25 - INFO - __main__ - Step 81616: {'lr': 0.00022027313128667933, 'samples': 15670272, 'steps': 81615, 'loss/train': 1.223254680633545} 08/31/2021 03:59:25 - INFO - __main__ - Step 81617: {'lr': 0.00022026786219858129, 'samples': 15670464, 'steps': 81616, 'loss/train': 1.0168360471725464} 08/31/2021 03:59:25 - INFO - __main__ - Step 81618: {'lr': 0.00022026259312388005, 'samples': 15670656, 'steps': 81617, 'loss/train': 1.6143134832382202} 08/31/2021 03:59:27 - INFO - __main__ - Step 81619: {'lr': 0.00022025732406257806, 'samples': 15670848, 'steps': 81618, 'loss/train': 0.22388093173503876} 08/31/2021 03:59:27 - INFO - __main__ - Step 81620: {'lr': 0.00022025205501467765, 'samples': 15671040, 'steps': 81619, 'loss/train': 1.1973462104797363} 08/31/2021 03:59:27 - INFO - __main__ - Step 81621: {'lr': 0.00022024678598018123, 'samples': 15671232, 'steps': 81620, 'loss/train': 1.3361268043518066} 08/31/2021 03:59:28 - INFO - __main__ - Step 81622: {'lr': 0.00022024151695909108, 'samples': 15671424, 'steps': 81621, 'loss/train': 1.3466854095458984} 08/31/2021 03:59:28 - INFO - __main__ - Step 81623: {'lr': 0.0002202362479514097, 'samples': 15671616, 'steps': 81622, 'loss/train': 2.483682632446289} 08/31/2021 03:59:30 - INFO - __main__ - Step 81624: {'lr': 0.0002202309789571394, 'samples': 15671808, 'steps': 81623, 'loss/train': 1.1300878524780273} 08/31/2021 03:59:30 - INFO - __main__ - Step 81625: {'lr': 0.00022022570997628254, 'samples': 15672000, 'steps': 81624, 'loss/train': 1.470728874206543} 08/31/2021 03:59:31 - INFO - __main__ - Step 81626: {'lr': 0.00022022044100884154, 'samples': 15672192, 'steps': 81625, 'loss/train': 0.06962278485298157} 08/31/2021 03:59:31 - INFO - __main__ - Step 81627: {'lr': 0.00022021517205481875, 'samples': 15672384, 'steps': 81626, 'loss/train': 1.6929622888565063} 08/31/2021 03:59:31 - INFO - __main__ - Step 81628: {'lr': 0.00022020990311421665, 'samples': 15672576, 'steps': 81627, 'loss/train': 1.228886365890503} 08/31/2021 03:59:33 - INFO - __main__ - Step 81629: {'lr': 0.0002202046341870374, 'samples': 15672768, 'steps': 81628, 'loss/train': 0.9560842514038086} 08/31/2021 03:59:33 - INFO - __main__ - Step 81630: {'lr': 0.00022019936527328346, 'samples': 15672960, 'steps': 81629, 'loss/train': 1.447513461112976} 08/31/2021 03:59:34 - INFO - __main__ - Step 81631: {'lr': 0.00022019409637295722, 'samples': 15673152, 'steps': 81630, 'loss/train': 1.104257583618164} 08/31/2021 03:59:34 - INFO - __main__ - Step 81632: {'lr': 0.0002201888274860611, 'samples': 15673344, 'steps': 81631, 'loss/train': 0.8340432643890381} 08/31/2021 03:59:34 - INFO - __main__ - Step 81633: {'lr': 0.0002201835586125974, 'samples': 15673536, 'steps': 81632, 'loss/train': 1.8119611740112305} 08/31/2021 03:59:36 - INFO - __main__ - Step 81634: {'lr': 0.00022017828975256856, 'samples': 15673728, 'steps': 81633, 'loss/train': 1.5608539581298828} 08/31/2021 03:59:36 - INFO - __main__ - Step 81635: {'lr': 0.0002201730209059769, 'samples': 15673920, 'steps': 81634, 'loss/train': 1.7709715366363525} 08/31/2021 03:59:37 - INFO - __main__ - Step 81636: {'lr': 0.00022016775207282484, 'samples': 15674112, 'steps': 81635, 'loss/train': 1.0432403087615967} 08/31/2021 03:59:37 - INFO - __main__ - Step 81637: {'lr': 0.00022016248325311473, 'samples': 15674304, 'steps': 81636, 'loss/train': 1.4154117107391357} 08/31/2021 03:59:38 - INFO - __main__ - Step 81638: {'lr': 0.0002201572144468489, 'samples': 15674496, 'steps': 81637, 'loss/train': 0.9968791604042053} 08/31/2021 03:59:39 - INFO - __main__ - Step 81639: {'lr': 0.0002201519456540298, 'samples': 15674688, 'steps': 81638, 'loss/train': 1.3208093643188477} 08/31/2021 03:59:39 - INFO - __main__ - Step 81640: {'lr': 0.00022014667687465979, 'samples': 15674880, 'steps': 81639, 'loss/train': 1.1983187198638916} 08/31/2021 03:59:40 - INFO - __main__ - Step 81641: {'lr': 0.0002201414081087412, 'samples': 15675072, 'steps': 81640, 'loss/train': 1.146524429321289} 08/31/2021 03:59:40 - INFO - __main__ - Step 81642: {'lr': 0.00022013613935627653, 'samples': 15675264, 'steps': 81641, 'loss/train': 0.2078447937965393} 08/31/2021 03:59:40 - INFO - __main__ - Step 81643: {'lr': 0.00022013087061726797, 'samples': 15675456, 'steps': 81642, 'loss/train': 1.336316466331482} 08/31/2021 03:59:41 - INFO - __main__ - Step 81644: {'lr': 0.00022012560189171797, 'samples': 15675648, 'steps': 81643, 'loss/train': 1.4191529750823975} 08/31/2021 03:59:42 - INFO - __main__ - Step 81645: {'lr': 0.0002201203331796289, 'samples': 15675840, 'steps': 81644, 'loss/train': 1.602706789970398} 08/31/2021 03:59:43 - INFO - __main__ - Step 81646: {'lr': 0.00022011506448100317, 'samples': 15676032, 'steps': 81645, 'loss/train': 1.241109013557434} 08/31/2021 03:59:43 - INFO - __main__ - Step 81647: {'lr': 0.0002201097957958431, 'samples': 15676224, 'steps': 81646, 'loss/train': 0.6944698095321655} 08/31/2021 03:59:44 - INFO - __main__ - Step 81648: {'lr': 0.00022010452712415112, 'samples': 15676416, 'steps': 81647, 'loss/train': 1.960761547088623} 08/31/2021 03:59:44 - INFO - __main__ - Step 81649: {'lr': 0.0002200992584659296, 'samples': 15676608, 'steps': 81648, 'loss/train': 1.3255654573440552} 08/31/2021 03:59:45 - INFO - __main__ - Step 81650: {'lr': 0.00022009398982118087, 'samples': 15676800, 'steps': 81649, 'loss/train': 1.247483491897583} 08/31/2021 03:59:46 - INFO - __main__ - Step 81651: {'lr': 0.0002200887211899073, 'samples': 15676992, 'steps': 81650, 'loss/train': 0.5262839198112488} 08/31/2021 03:59:46 - INFO - __main__ - Step 81652: {'lr': 0.0002200834525721113, 'samples': 15677184, 'steps': 81651, 'loss/train': 0.4085105061531067} 08/31/2021 03:59:47 - INFO - __main__ - Step 81653: {'lr': 0.00022007818396779528, 'samples': 15677376, 'steps': 81652, 'loss/train': 0.6240471601486206} 08/31/2021 03:59:47 - INFO - __main__ - Step 81654: {'lr': 0.00022007291537696154, 'samples': 15677568, 'steps': 81653, 'loss/train': 0.6307128667831421} 08/31/2021 03:59:49 - INFO - __main__ - Step 81655: {'lr': 0.00022006764679961257, 'samples': 15677760, 'steps': 81654, 'loss/train': 0.2206958830356598} 08/31/2021 03:59:50 - INFO - __main__ - Step 81656: {'lr': 0.0002200623782357506, 'samples': 15677952, 'steps': 81655, 'loss/train': 0.3106834292411804} 08/31/2021 03:59:50 - INFO - __main__ - Step 81657: {'lr': 0.000220057109685378, 'samples': 15678144, 'steps': 81656, 'loss/train': 1.4763292074203491} 08/31/2021 03:59:50 - INFO - __main__ - Step 81658: {'lr': 0.00022005184114849723, 'samples': 15678336, 'steps': 81657, 'loss/train': 0.3960680067539215} 08/31/2021 03:59:51 - INFO - __main__ - Step 81659: {'lr': 0.00022004657262511066, 'samples': 15678528, 'steps': 81658, 'loss/train': 1.4179701805114746} 08/31/2021 03:59:52 - INFO - __main__ - Step 81660: {'lr': 0.0002200413041152206, 'samples': 15678720, 'steps': 81659, 'loss/train': 1.5296238660812378} 08/31/2021 03:59:53 - INFO - __main__ - Step 81661: {'lr': 0.0002200360356188295, 'samples': 15678912, 'steps': 81660, 'loss/train': 1.2621254920959473} 08/31/2021 03:59:53 - INFO - __main__ - Step 81662: {'lr': 0.0002200307671359397, 'samples': 15679104, 'steps': 81661, 'loss/train': 1.2572581768035889} 08/31/2021 03:59:54 - INFO - __main__ - Step 81663: {'lr': 0.00022002549866655355, 'samples': 15679296, 'steps': 81662, 'loss/train': 0.9098880290985107} 08/31/2021 03:59:54 - INFO - __main__ - Step 81664: {'lr': 0.00022002023021067347, 'samples': 15679488, 'steps': 81663, 'loss/train': 0.04105767235159874} 08/31/2021 03:59:56 - INFO - __main__ - Step 81665: {'lr': 0.00022001496176830178, 'samples': 15679680, 'steps': 81664, 'loss/train': 0.7857460975646973} 08/31/2021 03:59:56 - INFO - __main__ - Step 81666: {'lr': 0.00022000969333944094, 'samples': 15679872, 'steps': 81665, 'loss/train': 1.339245080947876} 08/31/2021 03:59:56 - INFO - __main__ - Step 81667: {'lr': 0.00022000442492409322, 'samples': 15680064, 'steps': 81666, 'loss/train': 1.079775333404541} 08/31/2021 03:59:57 - INFO - __main__ - Step 81668: {'lr': 0.00021999915652226115, 'samples': 15680256, 'steps': 81667, 'loss/train': 1.190344214439392} 08/31/2021 03:59:57 - INFO - __main__ - Step 81669: {'lr': 0.00021999388813394695, 'samples': 15680448, 'steps': 81668, 'loss/train': 1.509814739227295} 08/31/2021 03:59:59 - INFO - __main__ - Step 81670: {'lr': 0.00021998861975915297, 'samples': 15680640, 'steps': 81669, 'loss/train': 1.2443231344223022} 08/31/2021 03:59:59 - INFO - __main__ - Step 81671: {'lr': 0.0002199833513978817, 'samples': 15680832, 'steps': 81670, 'loss/train': 1.429674506187439} 08/31/2021 03:59:59 - INFO - __main__ - Step 81672: {'lr': 0.00021997808305013544, 'samples': 15681024, 'steps': 81671, 'loss/train': 0.8548336029052734} 08/31/2021 04:00:00 - INFO - __main__ - Step 81673: {'lr': 0.00021997281471591658, 'samples': 15681216, 'steps': 81672, 'loss/train': 0.7610018253326416} 08/31/2021 04:00:00 - INFO - __main__ - Step 81674: {'lr': 0.00021996754639522757, 'samples': 15681408, 'steps': 81673, 'loss/train': 0.9837254881858826} 08/31/2021 04:00:02 - INFO - __main__ - Step 81675: {'lr': 0.00021996227808807067, 'samples': 15681600, 'steps': 81674, 'loss/train': 1.2032523155212402} 08/31/2021 04:00:02 - INFO - __main__ - Step 81676: {'lr': 0.0002199570097944483, 'samples': 15681792, 'steps': 81675, 'loss/train': 1.369490623474121} 08/31/2021 04:00:02 - INFO - __main__ - Step 81677: {'lr': 0.00021995174151436287, 'samples': 15681984, 'steps': 81676, 'loss/train': 1.122678279876709} 08/31/2021 04:00:03 - INFO - __main__ - Step 81678: {'lr': 0.0002199464732478167, 'samples': 15682176, 'steps': 81677, 'loss/train': 1.3383711576461792} 08/31/2021 04:00:03 - INFO - __main__ - Step 81679: {'lr': 0.0002199412049948122, 'samples': 15682368, 'steps': 81678, 'loss/train': 1.4478148221969604} 08/31/2021 04:00:05 - INFO - __main__ - Step 81680: {'lr': 0.00021993593675535177, 'samples': 15682560, 'steps': 81679, 'loss/train': 1.3303583860397339} 08/31/2021 04:00:05 - INFO - __main__ - Step 81681: {'lr': 0.00021993066852943766, 'samples': 15682752, 'steps': 81680, 'loss/train': 0.8853694796562195} 08/31/2021 04:00:05 - INFO - __main__ - Step 81682: {'lr': 0.00021992540031707243, 'samples': 15682944, 'steps': 81681, 'loss/train': 1.5583213567733765} 08/31/2021 04:00:06 - INFO - __main__ - Step 81683: {'lr': 0.00021992013211825828, 'samples': 15683136, 'steps': 81682, 'loss/train': 0.8976211547851562} 08/31/2021 04:00:06 - INFO - __main__ - Step 81684: {'lr': 0.00021991486393299763, 'samples': 15683328, 'steps': 81683, 'loss/train': 1.2391053438186646} 08/31/2021 04:00:08 - INFO - __main__ - Step 81685: {'lr': 0.00021990959576129293, 'samples': 15683520, 'steps': 81684, 'loss/train': 1.2662324905395508} 08/31/2021 04:00:08 - INFO - __main__ - Step 81686: {'lr': 0.00021990432760314647, 'samples': 15683712, 'steps': 81685, 'loss/train': 1.2622004747390747} 08/31/2021 04:00:08 - INFO - __main__ - Step 81687: {'lr': 0.00021989905945856065, 'samples': 15683904, 'steps': 81686, 'loss/train': 0.8226631283760071} 08/31/2021 04:00:09 - INFO - __main__ - Step 81688: {'lr': 0.00021989379132753787, 'samples': 15684096, 'steps': 81687, 'loss/train': 0.305679053068161} 08/31/2021 04:00:09 - INFO - __main__ - Step 81689: {'lr': 0.00021988852321008046, 'samples': 15684288, 'steps': 81688, 'loss/train': 1.5374782085418701} 08/31/2021 04:00:10 - INFO - __main__ - Step 81690: {'lr': 0.00021988325510619085, 'samples': 15684480, 'steps': 81689, 'loss/train': 1.6261624097824097} 08/31/2021 04:00:11 - INFO - __main__ - Step 81691: {'lr': 0.0002198779870158714, 'samples': 15684672, 'steps': 81690, 'loss/train': 1.1639779806137085} 08/31/2021 04:00:12 - INFO - __main__ - Step 81692: {'lr': 0.0002198727189391244, 'samples': 15684864, 'steps': 81691, 'loss/train': 1.655617117881775} 08/31/2021 04:00:12 - INFO - __main__ - Step 81693: {'lr': 0.00021986745087595232, 'samples': 15685056, 'steps': 81692, 'loss/train': 1.6068031787872314} 08/31/2021 04:00:12 - INFO - __main__ - Step 81694: {'lr': 0.0002198621828263575, 'samples': 15685248, 'steps': 81693, 'loss/train': 0.03883868828415871} 08/31/2021 04:00:13 - INFO - __main__ - Step 81695: {'lr': 0.00021985691479034237, 'samples': 15685440, 'steps': 81694, 'loss/train': 1.5853211879730225} 08/31/2021 04:00:14 - INFO - __main__ - Step 81696: {'lr': 0.00021985164676790916, 'samples': 15685632, 'steps': 81695, 'loss/train': 1.884417176246643} 08/31/2021 04:00:15 - INFO - __main__ - Step 81697: {'lr': 0.00021984637875906038, 'samples': 15685824, 'steps': 81696, 'loss/train': 1.4217039346694946} 08/31/2021 04:00:15 - INFO - __main__ - Step 81698: {'lr': 0.00021984111076379833, 'samples': 15686016, 'steps': 81697, 'loss/train': 0.9679291248321533} 08/31/2021 04:00:15 - INFO - __main__ - Step 81699: {'lr': 0.00021983584278212543, 'samples': 15686208, 'steps': 81698, 'loss/train': 1.3289306163787842} 08/31/2021 04:00:16 - INFO - __main__ - Step 81700: {'lr': 0.000219830574814044, 'samples': 15686400, 'steps': 81699, 'loss/train': 1.3792990446090698} 08/31/2021 04:00:17 - INFO - __main__ - Step 81701: {'lr': 0.00021982530685955653, 'samples': 15686592, 'steps': 81700, 'loss/train': 0.9306716322898865} 08/31/2021 04:00:18 - INFO - __main__ - Step 81702: {'lr': 0.00021982003891866527, 'samples': 15686784, 'steps': 81701, 'loss/train': 1.3313559293746948} 08/31/2021 04:00:18 - INFO - __main__ - Step 81703: {'lr': 0.00021981477099137259, 'samples': 15686976, 'steps': 81702, 'loss/train': 1.7266442775726318} 08/31/2021 04:00:18 - INFO - __main__ - Step 81704: {'lr': 0.00021980950307768095, 'samples': 15687168, 'steps': 81703, 'loss/train': 0.9324973225593567} 08/31/2021 04:00:19 - INFO - __main__ - Step 81705: {'lr': 0.00021980423517759264, 'samples': 15687360, 'steps': 81704, 'loss/train': 1.2939649820327759} 08/31/2021 04:00:20 - INFO - __main__ - Step 81706: {'lr': 0.0002197989672911101, 'samples': 15687552, 'steps': 81705, 'loss/train': 0.5348305106163025} 08/31/2021 04:00:20 - INFO - __main__ - Step 81707: {'lr': 0.00021979369941823568, 'samples': 15687744, 'steps': 81706, 'loss/train': 1.3319871425628662} 08/31/2021 04:00:21 - INFO - __main__ - Step 81708: {'lr': 0.00021978843155897175, 'samples': 15687936, 'steps': 81707, 'loss/train': 0.9605355858802795} 08/31/2021 04:00:21 - INFO - __main__ - Step 81709: {'lr': 0.00021978316371332074, 'samples': 15688128, 'steps': 81708, 'loss/train': 0.8616621494293213} 08/31/2021 04:00:22 - INFO - __main__ - Step 81710: {'lr': 0.00021977789588128492, 'samples': 15688320, 'steps': 81709, 'loss/train': 1.6264358758926392} 08/31/2021 04:00:23 - INFO - __main__ - Step 81711: {'lr': 0.0002197726280628667, 'samples': 15688512, 'steps': 81710, 'loss/train': 1.2798869609832764} 08/31/2021 04:00:24 - INFO - __main__ - Step 81712: {'lr': 0.00021976736025806855, 'samples': 15688704, 'steps': 81711, 'loss/train': 1.166094183921814} 08/31/2021 04:00:24 - INFO - __main__ - Step 81713: {'lr': 0.00021976209246689268, 'samples': 15688896, 'steps': 81712, 'loss/train': 1.291081428527832} 08/31/2021 04:00:25 - INFO - __main__ - Step 81714: {'lr': 0.00021975682468934154, 'samples': 15689088, 'steps': 81713, 'loss/train': 0.8587938547134399} 08/31/2021 04:00:25 - INFO - __main__ - Step 81715: {'lr': 0.00021975155692541753, 'samples': 15689280, 'steps': 81714, 'loss/train': 1.199022650718689} 08/31/2021 04:00:25 - INFO - __main__ - Step 81716: {'lr': 0.00021974628917512302, 'samples': 15689472, 'steps': 81715, 'loss/train': 2.0911011695861816} 08/31/2021 04:00:27 - INFO - __main__ - Step 81717: {'lr': 0.00021974102143846032, 'samples': 15689664, 'steps': 81716, 'loss/train': 1.204851746559143} 08/31/2021 04:00:27 - INFO - __main__ - Step 81718: {'lr': 0.00021973575371543187, 'samples': 15689856, 'steps': 81717, 'loss/train': 1.464585542678833} 08/31/2021 04:00:28 - INFO - __main__ - Step 81719: {'lr': 0.00021973048600604, 'samples': 15690048, 'steps': 81718, 'loss/train': 1.3360804319381714} 08/31/2021 04:00:28 - INFO - __main__ - Step 81720: {'lr': 0.00021972521831028715, 'samples': 15690240, 'steps': 81719, 'loss/train': 1.7880736589431763} 08/31/2021 04:00:28 - INFO - __main__ - Step 81721: {'lr': 0.00021971995062817563, 'samples': 15690432, 'steps': 81720, 'loss/train': 1.258573293685913} 08/31/2021 04:00:30 - INFO - __main__ - Step 81722: {'lr': 0.00021971468295970786, 'samples': 15690624, 'steps': 81721, 'loss/train': 1.8285572528839111} 08/31/2021 04:00:31 - INFO - __main__ - Step 81723: {'lr': 0.00021970941530488622, 'samples': 15690816, 'steps': 81722, 'loss/train': 1.2724943161010742} 08/31/2021 04:00:31 - INFO - __main__ - Step 81724: {'lr': 0.000219704147663713, 'samples': 15691008, 'steps': 81723, 'loss/train': 0.061348237097263336} 08/31/2021 04:00:31 - INFO - __main__ - Step 81725: {'lr': 0.0002196988800361906, 'samples': 15691200, 'steps': 81724, 'loss/train': 1.2702583074569702} 08/31/2021 04:00:32 - INFO - __main__ - Step 81726: {'lr': 0.00021969361242232143, 'samples': 15691392, 'steps': 81725, 'loss/train': 1.4495775699615479} 08/31/2021 04:00:33 - INFO - __main__ - Step 81727: {'lr': 0.00021968834482210783, 'samples': 15691584, 'steps': 81726, 'loss/train': 1.430176854133606} 08/31/2021 04:00:34 - INFO - __main__ - Step 81728: {'lr': 0.0002196830772355522, 'samples': 15691776, 'steps': 81727, 'loss/train': 2.1434874534606934} 08/31/2021 04:00:34 - INFO - __main__ - Step 81729: {'lr': 0.00021967780966265692, 'samples': 15691968, 'steps': 81728, 'loss/train': 1.5203300714492798} 08/31/2021 04:00:34 - INFO - __main__ - Step 81730: {'lr': 0.00021967254210342437, 'samples': 15692160, 'steps': 81729, 'loss/train': 1.6334196329116821} 08/31/2021 04:00:35 - INFO - __main__ - Step 81731: {'lr': 0.0002196672745578569, 'samples': 15692352, 'steps': 81730, 'loss/train': 0.955494225025177} 08/31/2021 04:00:36 - INFO - __main__ - Step 81732: {'lr': 0.00021966200702595688, 'samples': 15692544, 'steps': 81731, 'loss/train': 1.3649238348007202} 08/31/2021 04:00:37 - INFO - __main__ - Step 81733: {'lr': 0.00021965673950772666, 'samples': 15692736, 'steps': 81732, 'loss/train': 1.1645798683166504} 08/31/2021 04:00:37 - INFO - __main__ - Step 81734: {'lr': 0.0002196514720031687, 'samples': 15692928, 'steps': 81733, 'loss/train': 1.2220561504364014} 08/31/2021 04:00:37 - INFO - __main__ - Step 81735: {'lr': 0.00021964620451228527, 'samples': 15693120, 'steps': 81734, 'loss/train': 0.8411522507667542} 08/31/2021 04:00:38 - INFO - __main__ - Step 81736: {'lr': 0.00021964093703507893, 'samples': 15693312, 'steps': 81735, 'loss/train': 1.8491846323013306} 08/31/2021 04:00:39 - INFO - __main__ - Step 81737: {'lr': 0.00021963566957155178, 'samples': 15693504, 'steps': 81736, 'loss/train': 1.3240153789520264} 08/31/2021 04:00:40 - INFO - __main__ - Step 81738: {'lr': 0.00021963040212170636, 'samples': 15693696, 'steps': 81737, 'loss/train': 1.1066080331802368} 08/31/2021 04:00:40 - INFO - __main__ - Step 81739: {'lr': 0.00021962513468554498, 'samples': 15693888, 'steps': 81738, 'loss/train': 1.7276250123977661} 08/31/2021 04:00:40 - INFO - __main__ - Step 81740: {'lr': 0.00021961986726307006, 'samples': 15694080, 'steps': 81739, 'loss/train': 1.1773253679275513} 08/31/2021 04:00:41 - INFO - __main__ - Step 81741: {'lr': 0.00021961459985428395, 'samples': 15694272, 'steps': 81740, 'loss/train': 1.370980143547058} 08/31/2021 04:00:42 - INFO - __main__ - Step 81742: {'lr': 0.00021960933245918903, 'samples': 15694464, 'steps': 81741, 'loss/train': 1.4796606302261353} 08/31/2021 04:00:42 - INFO - __main__ - Step 81743: {'lr': 0.0002196040650777877, 'samples': 15694656, 'steps': 81742, 'loss/train': 1.0248041152954102} 08/31/2021 04:00:43 - INFO - __main__ - Step 81744: {'lr': 0.00021959879771008228, 'samples': 15694848, 'steps': 81743, 'loss/train': 1.030967116355896} 08/31/2021 04:00:43 - INFO - __main__ - Step 81745: {'lr': 0.00021959353035607522, 'samples': 15695040, 'steps': 81744, 'loss/train': 1.3144794702529907} 08/31/2021 04:00:44 - INFO - __main__ - Step 81746: {'lr': 0.0002195882630157688, 'samples': 15695232, 'steps': 81745, 'loss/train': 1.0460548400878906} 08/31/2021 04:00:45 - INFO - __main__ - Step 81747: {'lr': 0.00021958299568916546, 'samples': 15695424, 'steps': 81746, 'loss/train': 1.24160635471344} 08/31/2021 04:00:46 - INFO - __main__ - Step 81748: {'lr': 0.00021957772837626755, 'samples': 15695616, 'steps': 81747, 'loss/train': 1.8086342811584473} 08/31/2021 04:00:46 - INFO - __main__ - Step 81749: {'lr': 0.00021957246107707758, 'samples': 15695808, 'steps': 81748, 'loss/train': 1.6412262916564941} 08/31/2021 04:00:46 - INFO - __main__ - Step 81750: {'lr': 0.00021956719379159762, 'samples': 15696000, 'steps': 81749, 'loss/train': 0.9887018203735352} 08/31/2021 04:00:47 - INFO - __main__ - Step 81751: {'lr': 0.00021956192651983027, 'samples': 15696192, 'steps': 81750, 'loss/train': 1.0185965299606323} 08/31/2021 04:00:47 - INFO - __main__ - Step 81752: {'lr': 0.0002195566592617778, 'samples': 15696384, 'steps': 81751, 'loss/train': 1.3473694324493408} 08/31/2021 04:00:48 - INFO - __main__ - Step 81753: {'lr': 0.00021955139201744266, 'samples': 15696576, 'steps': 81752, 'loss/train': 1.1946282386779785} 08/31/2021 04:00:49 - INFO - __main__ - Step 81754: {'lr': 0.00021954612478682718, 'samples': 15696768, 'steps': 81753, 'loss/train': 1.2112451791763306} 08/31/2021 04:00:49 - INFO - __main__ - Step 81755: {'lr': 0.00021954085756993374, 'samples': 15696960, 'steps': 81754, 'loss/train': 1.0287128686904907} 08/31/2021 04:00:50 - INFO - __main__ - Step 81756: {'lr': 0.00021953559036676473, 'samples': 15697152, 'steps': 81755, 'loss/train': 1.9334745407104492} 08/31/2021 04:00:50 - INFO - __main__ - Step 81757: {'lr': 0.00021953032317732253, 'samples': 15697344, 'steps': 81756, 'loss/train': 1.1302069425582886} 08/31/2021 04:00:51 - INFO - __main__ - Step 81758: {'lr': 0.0002195250560016095, 'samples': 15697536, 'steps': 81757, 'loss/train': 0.7364793419837952} 08/31/2021 04:00:52 - INFO - __main__ - Step 81759: {'lr': 0.00021951978883962797, 'samples': 15697728, 'steps': 81758, 'loss/train': 0.6362631320953369} 08/31/2021 04:00:52 - INFO - __main__ - Step 81760: {'lr': 0.00021951452169138036, 'samples': 15697920, 'steps': 81759, 'loss/train': 1.2541974782943726} 08/31/2021 04:00:53 - INFO - __main__ - Step 81761: {'lr': 0.00021950925455686908, 'samples': 15698112, 'steps': 81760, 'loss/train': 0.8744879364967346} 08/31/2021 04:00:53 - INFO - __main__ - Step 81762: {'lr': 0.0002195039874360964, 'samples': 15698304, 'steps': 81761, 'loss/train': 1.1632336378097534} 08/31/2021 04:00:55 - INFO - __main__ - Step 81763: {'lr': 0.0002194987203290649, 'samples': 15698496, 'steps': 81762, 'loss/train': 1.2894736528396606} 08/31/2021 04:00:55 - INFO - __main__ - Step 81764: {'lr': 0.00021949345323577668, 'samples': 15698688, 'steps': 81763, 'loss/train': 1.0094949007034302} 08/31/2021 04:00:56 - INFO - __main__ - Step 81765: {'lr': 0.00021948818615623425, 'samples': 15698880, 'steps': 81764, 'loss/train': 1.3158767223358154} 08/31/2021 04:00:56 - INFO - __main__ - Step 81766: {'lr': 0.00021948291909043997, 'samples': 15699072, 'steps': 81765, 'loss/train': 2.1072661876678467} 08/31/2021 04:00:56 - INFO - __main__ - Step 81767: {'lr': 0.0002194776520383962, 'samples': 15699264, 'steps': 81766, 'loss/train': 0.7216132879257202} 08/31/2021 04:00:58 - INFO - __main__ - Step 81768: {'lr': 0.00021947238500010535, 'samples': 15699456, 'steps': 81767, 'loss/train': 1.5641703605651855} 08/31/2021 04:00:58 - INFO - __main__ - Step 81769: {'lr': 0.0002194671179755698, 'samples': 15699648, 'steps': 81768, 'loss/train': 1.5278739929199219} 08/31/2021 04:00:59 - INFO - __main__ - Step 81770: {'lr': 0.00021946185096479186, 'samples': 15699840, 'steps': 81769, 'loss/train': 1.2485623359680176} 08/31/2021 04:00:59 - INFO - __main__ - Step 81771: {'lr': 0.0002194565839677739, 'samples': 15700032, 'steps': 81770, 'loss/train': 0.8892080187797546} 08/31/2021 04:00:59 - INFO - __main__ - Step 81772: {'lr': 0.0002194513169845184, 'samples': 15700224, 'steps': 81771, 'loss/train': 1.392530918121338} 08/31/2021 04:01:01 - INFO - __main__ - Step 81773: {'lr': 0.00021944605001502761, 'samples': 15700416, 'steps': 81772, 'loss/train': 1.281558632850647} 08/31/2021 04:01:02 - INFO - __main__ - Step 81774: {'lr': 0.000219440783059304, 'samples': 15700608, 'steps': 81773, 'loss/train': 1.147586464881897} 08/31/2021 04:01:02 - INFO - __main__ - Step 81775: {'lr': 0.00021943551611734987, 'samples': 15700800, 'steps': 81774, 'loss/train': 0.11247597634792328} 08/31/2021 04:01:02 - INFO - __main__ - Step 81776: {'lr': 0.00021943024918916776, 'samples': 15700992, 'steps': 81775, 'loss/train': 1.5926802158355713} 08/31/2021 04:01:03 - INFO - __main__ - Step 81777: {'lr': 0.0002194249822747598, 'samples': 15701184, 'steps': 81776, 'loss/train': 1.1261591911315918} 08/31/2021 04:01:03 - INFO - __main__ - Step 81778: {'lr': 0.00021941971537412847, 'samples': 15701376, 'steps': 81777, 'loss/train': 2.2222249507904053} 08/31/2021 04:01:05 - INFO - __main__ - Step 81779: {'lr': 0.00021941444848727612, 'samples': 15701568, 'steps': 81778, 'loss/train': 0.7898132801055908} 08/31/2021 04:01:05 - INFO - __main__ - Step 81780: {'lr': 0.00021940918161420517, 'samples': 15701760, 'steps': 81779, 'loss/train': 0.8479971885681152} 08/31/2021 04:01:05 - INFO - __main__ - Step 81781: {'lr': 0.00021940391475491793, 'samples': 15701952, 'steps': 81780, 'loss/train': 1.3926291465759277} 08/31/2021 04:01:06 - INFO - __main__ - Step 81782: {'lr': 0.0002193986479094169, 'samples': 15702144, 'steps': 81781, 'loss/train': 1.4505292177200317} 08/31/2021 04:01:06 - INFO - __main__ - Step 81783: {'lr': 0.0002193933810777043, 'samples': 15702336, 'steps': 81782, 'loss/train': 1.3673274517059326} 08/31/2021 04:01:08 - INFO - __main__ - Step 81784: {'lr': 0.0002193881142597826, 'samples': 15702528, 'steps': 81783, 'loss/train': 1.2959405183792114} 08/31/2021 04:01:08 - INFO - __main__ - Step 81785: {'lr': 0.00021938284745565408, 'samples': 15702720, 'steps': 81784, 'loss/train': 1.363623023033142} 08/31/2021 04:01:09 - INFO - __main__ - Step 81786: {'lr': 0.00021937758066532123, 'samples': 15702912, 'steps': 81785, 'loss/train': 0.9866858720779419} 08/31/2021 04:01:09 - INFO - __main__ - Step 81787: {'lr': 0.00021937231388878637, 'samples': 15703104, 'steps': 81786, 'loss/train': 0.1924288123846054} 08/31/2021 04:01:10 - INFO - __main__ - Step 81788: {'lr': 0.00021936704712605188, 'samples': 15703296, 'steps': 81787, 'loss/train': 0.06392157077789307} 08/31/2021 04:01:10 - INFO - __main__ - Step 81789: {'lr': 0.0002193617803771202, 'samples': 15703488, 'steps': 81788, 'loss/train': 0.3036917746067047} 08/31/2021 04:01:11 - INFO - __main__ - Step 81790: {'lr': 0.00021935651364199355, 'samples': 15703680, 'steps': 81789, 'loss/train': 1.7113839387893677} 08/31/2021 04:01:12 - INFO - __main__ - Step 81791: {'lr': 0.00021935124692067437, 'samples': 15703872, 'steps': 81790, 'loss/train': 1.452292799949646} 08/31/2021 04:01:12 - INFO - __main__ - Step 81792: {'lr': 0.00021934598021316508, 'samples': 15704064, 'steps': 81791, 'loss/train': 0.6324912309646606} 08/31/2021 04:01:13 - INFO - __main__ - Step 81793: {'lr': 0.00021934071351946795, 'samples': 15704256, 'steps': 81792, 'loss/train': 1.0893183946609497} 08/31/2021 04:01:13 - INFO - __main__ - Step 81794: {'lr': 0.0002193354468395855, 'samples': 15704448, 'steps': 81793, 'loss/train': 1.478966474533081} 08/31/2021 04:01:14 - INFO - __main__ - Step 81795: {'lr': 0.00021933018017351996, 'samples': 15704640, 'steps': 81794, 'loss/train': 0.29559171199798584} 08/31/2021 04:01:15 - INFO - __main__ - Step 81796: {'lr': 0.00021932491352127378, 'samples': 15704832, 'steps': 81795, 'loss/train': 1.0609116554260254} 08/31/2021 04:01:15 - INFO - __main__ - Step 81797: {'lr': 0.00021931964688284933, 'samples': 15705024, 'steps': 81796, 'loss/train': 0.5369564890861511} 08/31/2021 04:01:16 - INFO - __main__ - Step 81798: {'lr': 0.00021931438025824898, 'samples': 15705216, 'steps': 81797, 'loss/train': 2.4054481983184814} 08/31/2021 04:01:16 - INFO - __main__ - Step 81799: {'lr': 0.0002193091136474751, 'samples': 15705408, 'steps': 81798, 'loss/train': 0.9664212465286255} 08/31/2021 04:01:18 - INFO - __main__ - Step 81800: {'lr': 0.00021930384705053004, 'samples': 15705600, 'steps': 81799, 'loss/train': 1.6289153099060059} 08/31/2021 04:01:18 - INFO - __main__ - Step 81801: {'lr': 0.00021929858046741623, 'samples': 15705792, 'steps': 81800, 'loss/train': 1.4859486818313599} 08/31/2021 04:01:18 - INFO - __main__ - Step 81802: {'lr': 0.00021929331389813596, 'samples': 15705984, 'steps': 81801, 'loss/train': 1.4721428155899048} 08/31/2021 04:01:19 - INFO - __main__ - Step 81803: {'lr': 0.00021928804734269177, 'samples': 15706176, 'steps': 81802, 'loss/train': 0.11550718545913696} 08/31/2021 04:01:19 - INFO - __main__ - Step 81804: {'lr': 0.00021928278080108582, 'samples': 15706368, 'steps': 81803, 'loss/train': 1.48243248462677} 08/31/2021 04:01:20 - INFO - __main__ - Step 81805: {'lr': 0.00021927751427332058, 'samples': 15706560, 'steps': 81804, 'loss/train': 1.3302665948867798} 08/31/2021 04:01:21 - INFO - __main__ - Step 81806: {'lr': 0.00021927224775939838, 'samples': 15706752, 'steps': 81805, 'loss/train': 1.382186770439148} 08/31/2021 04:01:21 - INFO - __main__ - Step 81807: {'lr': 0.00021926698125932168, 'samples': 15706944, 'steps': 81806, 'loss/train': 1.4052609205245972} 08/31/2021 04:01:22 - INFO - __main__ - Step 81808: {'lr': 0.00021926171477309276, 'samples': 15707136, 'steps': 81807, 'loss/train': 0.178801029920578} 08/31/2021 04:01:22 - INFO - __main__ - Step 81809: {'lr': 0.00021925644830071407, 'samples': 15707328, 'steps': 81808, 'loss/train': 0.629083514213562} 08/31/2021 04:01:24 - INFO - __main__ - Step 81810: {'lr': 0.00021925118184218793, 'samples': 15707520, 'steps': 81809, 'loss/train': 1.121187448501587} 08/31/2021 04:01:24 - INFO - __main__ - Step 81811: {'lr': 0.00021924591539751673, 'samples': 15707712, 'steps': 81810, 'loss/train': 0.6216833591461182} 08/31/2021 04:01:24 - INFO - __main__ - Step 81812: {'lr': 0.00021924064896670288, 'samples': 15707904, 'steps': 81811, 'loss/train': 1.3108526468276978} 08/31/2021 04:01:25 - INFO - __main__ - Step 81813: {'lr': 0.00021923538254974868, 'samples': 15708096, 'steps': 81812, 'loss/train': 0.4908945560455322} 08/31/2021 04:01:25 - INFO - __main__ - Step 81814: {'lr': 0.0002192301161466566, 'samples': 15708288, 'steps': 81813, 'loss/train': 1.2013659477233887} 08/31/2021 04:01:27 - INFO - __main__ - Step 81815: {'lr': 0.00021922484975742893, 'samples': 15708480, 'steps': 81814, 'loss/train': 1.0749644041061401} 08/31/2021 04:01:27 - INFO - __main__ - Step 81816: {'lr': 0.0002192195833820681, 'samples': 15708672, 'steps': 81815, 'loss/train': 1.2135207653045654} 08/31/2021 04:01:27 - INFO - __main__ - Step 81817: {'lr': 0.0002192143170205764, 'samples': 15708864, 'steps': 81816, 'loss/train': 0.3923115134239197} 08/31/2021 04:01:28 - INFO - __main__ - Step 81818: {'lr': 0.00021920905067295625, 'samples': 15709056, 'steps': 81817, 'loss/train': 1.805199384689331} 08/31/2021 04:01:28 - INFO - __main__ - Step 81819: {'lr': 0.00021920378433921002, 'samples': 15709248, 'steps': 81818, 'loss/train': 1.3579915761947632} 08/31/2021 04:01:30 - INFO - __main__ - Step 81820: {'lr': 0.0002191985180193401, 'samples': 15709440, 'steps': 81819, 'loss/train': 0.5946467518806458} 08/31/2021 04:01:31 - INFO - __main__ - Step 81821: {'lr': 0.00021919325171334885, 'samples': 15709632, 'steps': 81820, 'loss/train': 1.2789232730865479} 08/31/2021 04:01:31 - INFO - __main__ - Step 81822: {'lr': 0.00021918798542123864, 'samples': 15709824, 'steps': 81821, 'loss/train': 1.462181568145752} 08/31/2021 04:01:32 - INFO - __main__ - Step 81823: {'lr': 0.00021918271914301185, 'samples': 15710016, 'steps': 81822, 'loss/train': 1.3735989332199097} 08/31/2021 04:01:32 - INFO - __main__ - Step 81824: {'lr': 0.00021917745287867085, 'samples': 15710208, 'steps': 81823, 'loss/train': 0.9102192521095276} 08/31/2021 04:01:32 - INFO - __main__ - Step 81825: {'lr': 0.0002191721866282181, 'samples': 15710400, 'steps': 81824, 'loss/train': 1.622238039970398} 08/31/2021 04:01:34 - INFO - __main__ - Step 81826: {'lr': 0.00021916692039165582, 'samples': 15710592, 'steps': 81825, 'loss/train': 1.3934894800186157} 08/31/2021 04:01:34 - INFO - __main__ - Step 81827: {'lr': 0.00021916165416898642, 'samples': 15710784, 'steps': 81826, 'loss/train': 0.8979273438453674} 08/31/2021 04:01:35 - INFO - __main__ - Step 81828: {'lr': 0.00021915638796021232, 'samples': 15710976, 'steps': 81827, 'loss/train': 1.5821990966796875} 08/31/2021 04:01:35 - INFO - __main__ - Step 81829: {'lr': 0.00021915112176533588, 'samples': 15711168, 'steps': 81828, 'loss/train': 1.0553903579711914} 08/31/2021 04:01:35 - INFO - __main__ - Step 81830: {'lr': 0.0002191458555843595, 'samples': 15711360, 'steps': 81829, 'loss/train': 0.8568384647369385} 08/31/2021 04:01:37 - INFO - __main__ - Step 81831: {'lr': 0.0002191405894172855, 'samples': 15711552, 'steps': 81830, 'loss/train': 1.688751220703125} 08/31/2021 04:01:37 - INFO - __main__ - Step 81832: {'lr': 0.00021913532326411626, 'samples': 15711744, 'steps': 81831, 'loss/train': 1.595999836921692} 08/31/2021 04:01:38 - INFO - __main__ - Step 81833: {'lr': 0.0002191300571248542, 'samples': 15711936, 'steps': 81832, 'loss/train': 0.9686757922172546} 08/31/2021 04:01:38 - INFO - __main__ - Step 81834: {'lr': 0.00021912479099950161, 'samples': 15712128, 'steps': 81833, 'loss/train': 1.6010947227478027} 08/31/2021 04:01:38 - INFO - __main__ - Step 81835: {'lr': 0.00021911952488806093, 'samples': 15712320, 'steps': 81834, 'loss/train': 0.9234331846237183} 08/31/2021 04:01:40 - INFO - __main__ - Step 81836: {'lr': 0.00021911425879053456, 'samples': 15712512, 'steps': 81835, 'loss/train': 1.375856876373291} 08/31/2021 04:01:40 - INFO - __main__ - Step 81837: {'lr': 0.00021910899270692478, 'samples': 15712704, 'steps': 81836, 'loss/train': 1.2417680025100708} 08/31/2021 04:01:41 - INFO - __main__ - Step 81838: {'lr': 0.00021910372663723403, 'samples': 15712896, 'steps': 81837, 'loss/train': 0.9175012111663818} 08/31/2021 04:01:41 - INFO - __main__ - Step 81839: {'lr': 0.00021909846058146463, 'samples': 15713088, 'steps': 81838, 'loss/train': 1.035434603691101} 08/31/2021 04:01:41 - INFO - __main__ - Step 81840: {'lr': 0.00021909319453961902, 'samples': 15713280, 'steps': 81839, 'loss/train': 1.612577199935913} 08/31/2021 04:01:42 - INFO - __main__ - Step 81841: {'lr': 0.00021908792851169952, 'samples': 15713472, 'steps': 81840, 'loss/train': 1.3359912633895874} 08/31/2021 04:01:44 - INFO - __main__ - Step 81842: {'lr': 0.00021908266249770852, 'samples': 15713664, 'steps': 81841, 'loss/train': 0.3898927867412567} 08/31/2021 04:01:44 - INFO - __main__ - Step 81843: {'lr': 0.00021907739649764846, 'samples': 15713856, 'steps': 81842, 'loss/train': 1.5296889543533325} 08/31/2021 04:01:45 - INFO - __main__ - Step 81844: {'lr': 0.00021907213051152157, 'samples': 15714048, 'steps': 81843, 'loss/train': 0.6017743945121765} 08/31/2021 04:01:45 - INFO - __main__ - Step 81845: {'lr': 0.00021906686453933034, 'samples': 15714240, 'steps': 81844, 'loss/train': 1.3799883127212524} 08/31/2021 04:01:45 - INFO - __main__ - Step 81846: {'lr': 0.0002190615985810771, 'samples': 15714432, 'steps': 81845, 'loss/train': 1.208176612854004} 08/31/2021 04:01:46 - INFO - __main__ - Step 81847: {'lr': 0.00021905633263676424, 'samples': 15714624, 'steps': 81846, 'loss/train': 0.5416164994239807} 08/31/2021 04:01:47 - INFO - __main__ - Step 81848: {'lr': 0.0002190510667063941, 'samples': 15714816, 'steps': 81847, 'loss/train': 1.537815809249878} 08/31/2021 04:01:48 - INFO - __main__ - Step 81849: {'lr': 0.00021904580078996904, 'samples': 15715008, 'steps': 81848, 'loss/train': 0.6242749094963074} 08/31/2021 04:01:48 - INFO - __main__ - Step 81850: {'lr': 0.00021904053488749152, 'samples': 15715200, 'steps': 81849, 'loss/train': 1.1828080415725708} 08/31/2021 04:01:48 - INFO - __main__ - Step 81851: {'lr': 0.0002190352689989638, 'samples': 15715392, 'steps': 81850, 'loss/train': 1.0296066999435425} 08/31/2021 04:01:49 - INFO - __main__ - Step 81852: {'lr': 0.00021903000312438833, 'samples': 15715584, 'steps': 81851, 'loss/train': 1.9334040880203247} 08/31/2021 04:01:50 - INFO - __main__ - Step 81853: {'lr': 0.0002190247372637675, 'samples': 15715776, 'steps': 81852, 'loss/train': 1.0196822881698608} 08/31/2021 04:01:51 - INFO - __main__ - Step 81854: {'lr': 0.0002190194714171036, 'samples': 15715968, 'steps': 81853, 'loss/train': 1.2924702167510986} 08/31/2021 04:01:51 - INFO - __main__ - Step 81855: {'lr': 0.00021901420558439905, 'samples': 15716160, 'steps': 81854, 'loss/train': 0.32839128375053406} 08/31/2021 04:01:52 - INFO - __main__ - Step 81856: {'lr': 0.00021900893976565622, 'samples': 15716352, 'steps': 81855, 'loss/train': 1.5056270360946655} 08/31/2021 04:01:52 - INFO - __main__ - Step 81857: {'lr': 0.00021900367396087756, 'samples': 15716544, 'steps': 81856, 'loss/train': 0.14841865003108978} 08/31/2021 04:01:54 - INFO - __main__ - Step 81858: {'lr': 0.00021899840817006535, 'samples': 15716736, 'steps': 81857, 'loss/train': 0.732855498790741} 08/31/2021 04:01:54 - INFO - __main__ - Step 81859: {'lr': 0.00021899314239322192, 'samples': 15716928, 'steps': 81858, 'loss/train': 1.5168015956878662} 08/31/2021 04:01:55 - INFO - __main__ - Step 81860: {'lr': 0.00021898787663034974, 'samples': 15717120, 'steps': 81859, 'loss/train': 0.13635829091072083} 08/31/2021 04:01:55 - INFO - __main__ - Step 81861: {'lr': 0.0002189826108814511, 'samples': 15717312, 'steps': 81860, 'loss/train': 0.5756320953369141} 08/31/2021 04:01:55 - INFO - __main__ - Step 81862: {'lr': 0.00021897734514652844, 'samples': 15717504, 'steps': 81861, 'loss/train': 1.0907065868377686} 08/31/2021 04:01:56 - INFO - __main__ - Step 81863: {'lr': 0.00021897207942558411, 'samples': 15717696, 'steps': 81862, 'loss/train': 1.462077260017395} 08/31/2021 04:01:57 - INFO - __main__ - Step 81864: {'lr': 0.00021896681371862047, 'samples': 15717888, 'steps': 81863, 'loss/train': 1.8227206468582153} 08/31/2021 04:01:58 - INFO - __main__ - Step 81865: {'lr': 0.00021896154802563992, 'samples': 15718080, 'steps': 81864, 'loss/train': 1.3017528057098389} 08/31/2021 04:01:58 - INFO - __main__ - Step 81866: {'lr': 0.0002189562823466448, 'samples': 15718272, 'steps': 81865, 'loss/train': 1.3727308511734009} 08/31/2021 04:01:58 - INFO - __main__ - Step 81867: {'lr': 0.0002189510166816375, 'samples': 15718464, 'steps': 81866, 'loss/train': 1.4116696119308472} 08/31/2021 04:01:59 - INFO - __main__ - Step 81868: {'lr': 0.00021894575103062038, 'samples': 15718656, 'steps': 81867, 'loss/train': 0.45198512077331543} 08/31/2021 04:02:01 - INFO - __main__ - Step 81869: {'lr': 0.00021894048539359588, 'samples': 15718848, 'steps': 81868, 'loss/train': 0.8744821548461914} 08/31/2021 04:02:01 - INFO - __main__ - Step 81870: {'lr': 0.00021893521977056637, 'samples': 15719040, 'steps': 81869, 'loss/train': 1.089308738708496} 08/31/2021 04:02:01 - INFO - __main__ - Step 81871: {'lr': 0.00021892995416153408, 'samples': 15719232, 'steps': 81870, 'loss/train': 0.35333606600761414} 08/31/2021 04:02:02 - INFO - __main__ - Step 81872: {'lr': 0.00021892468856650148, 'samples': 15719424, 'steps': 81871, 'loss/train': 1.4854052066802979} 08/31/2021 04:02:02 - INFO - __main__ - Step 81873: {'lr': 0.00021891942298547093, 'samples': 15719616, 'steps': 81872, 'loss/train': 0.040543634444475174} 08/31/2021 04:02:02 - INFO - __main__ - Step 81874: {'lr': 0.0002189141574184448, 'samples': 15719808, 'steps': 81873, 'loss/train': 0.027640199288725853} 08/31/2021 04:02:05 - INFO - __main__ - Step 81875: {'lr': 0.0002189088918654255, 'samples': 15720000, 'steps': 81874, 'loss/train': 1.0046896934509277} 08/31/2021 04:02:05 - INFO - __main__ - Step 81876: {'lr': 0.00021890362632641537, 'samples': 15720192, 'steps': 81875, 'loss/train': 1.3978604078292847} 08/31/2021 04:02:05 - INFO - __main__ - Step 81877: {'lr': 0.00021889836080141677, 'samples': 15720384, 'steps': 81876, 'loss/train': 1.5122238397598267} 08/31/2021 04:02:06 - INFO - __main__ - Step 81878: {'lr': 0.00021889309529043207, 'samples': 15720576, 'steps': 81877, 'loss/train': 1.8890721797943115} 08/31/2021 04:02:06 - INFO - __main__ - Step 81879: {'lr': 0.0002188878297934637, 'samples': 15720768, 'steps': 81878, 'loss/train': 0.6286133527755737} 08/31/2021 04:02:08 - INFO - __main__ - Step 81880: {'lr': 0.00021888256431051395, 'samples': 15720960, 'steps': 81879, 'loss/train': 1.3909811973571777} 08/31/2021 04:02:08 - INFO - __main__ - Step 81881: {'lr': 0.00021887729884158527, 'samples': 15721152, 'steps': 81880, 'loss/train': 1.191032886505127} 08/31/2021 04:02:09 - INFO - __main__ - Step 81882: {'lr': 0.00021887203338668, 'samples': 15721344, 'steps': 81881, 'loss/train': 0.634589433670044} 08/31/2021 04:02:09 - INFO - __main__ - Step 81883: {'lr': 0.0002188667679458005, 'samples': 15721536, 'steps': 81882, 'loss/train': 0.7327703833580017} 08/31/2021 04:02:09 - INFO - __main__ - Step 81884: {'lr': 0.00021886150251894927, 'samples': 15721728, 'steps': 81883, 'loss/train': 1.5368916988372803} 08/31/2021 04:02:10 - INFO - __main__ - Step 81885: {'lr': 0.00021885623710612845, 'samples': 15721920, 'steps': 81884, 'loss/train': 0.27413210272789} 08/31/2021 04:02:11 - INFO - __main__ - Step 81886: {'lr': 0.00021885097170734052, 'samples': 15722112, 'steps': 81885, 'loss/train': 0.6935034990310669} 08/31/2021 04:02:11 - INFO - __main__ - Step 81887: {'lr': 0.00021884570632258788, 'samples': 15722304, 'steps': 81886, 'loss/train': 1.7664155960083008} 08/31/2021 04:02:12 - INFO - __main__ - Step 81888: {'lr': 0.0002188404409518729, 'samples': 15722496, 'steps': 81887, 'loss/train': 0.9428133964538574} 08/31/2021 04:02:12 - INFO - __main__ - Step 81889: {'lr': 0.00021883517559519787, 'samples': 15722688, 'steps': 81888, 'loss/train': 1.883790373802185} 08/31/2021 04:02:13 - INFO - __main__ - Step 81890: {'lr': 0.0002188299102525653, 'samples': 15722880, 'steps': 81889, 'loss/train': 0.2278684824705124} 08/31/2021 04:02:14 - INFO - __main__ - Step 81891: {'lr': 0.00021882464492397748, 'samples': 15723072, 'steps': 81890, 'loss/train': 0.7174011468887329} 08/31/2021 04:02:14 - INFO - __main__ - Step 81892: {'lr': 0.00021881937960943677, 'samples': 15723264, 'steps': 81891, 'loss/train': 1.344870924949646} 08/31/2021 04:02:15 - INFO - __main__ - Step 81893: {'lr': 0.00021881411430894554, 'samples': 15723456, 'steps': 81892, 'loss/train': 1.0771678686141968} 08/31/2021 04:02:15 - INFO - __main__ - Step 81894: {'lr': 0.00021880884902250624, 'samples': 15723648, 'steps': 81893, 'loss/train': 0.6704292297363281} 08/31/2021 04:02:15 - INFO - __main__ - Step 81895: {'lr': 0.00021880358375012116, 'samples': 15723840, 'steps': 81894, 'loss/train': 1.371573805809021} 08/31/2021 04:02:17 - INFO - __main__ - Step 81896: {'lr': 0.00021879831849179275, 'samples': 15724032, 'steps': 81895, 'loss/train': 0.8151004314422607} 08/31/2021 04:02:18 - INFO - __main__ - Step 81897: {'lr': 0.00021879305324752342, 'samples': 15724224, 'steps': 81896, 'loss/train': 1.1338756084442139} 08/31/2021 04:02:18 - INFO - __main__ - Step 81898: {'lr': 0.00021878778801731532, 'samples': 15724416, 'steps': 81897, 'loss/train': 0.20797191560268402} 08/31/2021 04:02:18 - INFO - __main__ - Step 81899: {'lr': 0.00021878252280117097, 'samples': 15724608, 'steps': 81898, 'loss/train': 1.310976266860962} 08/31/2021 04:02:19 - INFO - __main__ - Step 81900: {'lr': 0.00021877725759909274, 'samples': 15724800, 'steps': 81899, 'loss/train': 0.5060407519340515} 08/31/2021 04:02:20 - INFO - __main__ - Step 81901: {'lr': 0.00021877199241108304, 'samples': 15724992, 'steps': 81900, 'loss/train': 0.6667828559875488} 08/31/2021 04:02:21 - INFO - __main__ - Step 81902: {'lr': 0.00021876672723714413, 'samples': 15725184, 'steps': 81901, 'loss/train': 0.5931065678596497} 08/31/2021 04:02:21 - INFO - __main__ - Step 81903: {'lr': 0.00021876146207727847, 'samples': 15725376, 'steps': 81902, 'loss/train': 1.1847054958343506} 08/31/2021 04:02:21 - INFO - __main__ - Step 81904: {'lr': 0.00021875619693148847, 'samples': 15725568, 'steps': 81903, 'loss/train': 1.7334883213043213} 08/31/2021 04:02:22 - INFO - __main__ - Step 81905: {'lr': 0.0002187509317997764, 'samples': 15725760, 'steps': 81904, 'loss/train': 0.895738422870636} 08/31/2021 04:02:23 - INFO - __main__ - Step 81906: {'lr': 0.00021874566668214466, 'samples': 15725952, 'steps': 81905, 'loss/train': 0.43008852005004883} 08/31/2021 04:02:24 - INFO - __main__ - Step 81907: {'lr': 0.00021874040157859564, 'samples': 15726144, 'steps': 81906, 'loss/train': 1.0401216745376587} 08/31/2021 04:02:24 - INFO - __main__ - Step 81908: {'lr': 0.00021873513648913178, 'samples': 15726336, 'steps': 81907, 'loss/train': 1.5915590524673462} 08/31/2021 04:02:24 - INFO - __main__ - Step 81909: {'lr': 0.0002187298714137553, 'samples': 15726528, 'steps': 81908, 'loss/train': 1.34050714969635} 08/31/2021 04:02:25 - INFO - __main__ - Step 81910: {'lr': 0.00021872460635246883, 'samples': 15726720, 'steps': 81909, 'loss/train': 0.7394696474075317} 08/31/2021 04:02:27 - INFO - __main__ - Step 81911: {'lr': 0.00021871934130527444, 'samples': 15726912, 'steps': 81910, 'loss/train': 0.4822825491428375} 08/31/2021 04:02:27 - INFO - __main__ - Step 81912: {'lr': 0.0002187140762721746, 'samples': 15727104, 'steps': 81911, 'loss/train': 1.1267908811569214} 08/31/2021 04:02:27 - INFO - __main__ - Step 81913: {'lr': 0.00021870881125317173, 'samples': 15727296, 'steps': 81912, 'loss/train': 0.8997759222984314} 08/31/2021 04:02:28 - INFO - __main__ - Step 81914: {'lr': 0.0002187035462482682, 'samples': 15727488, 'steps': 81913, 'loss/train': 0.02178932912647724} 08/31/2021 04:02:28 - INFO - __main__ - Step 81915: {'lr': 0.00021869828125746637, 'samples': 15727680, 'steps': 81914, 'loss/train': 0.6328867077827454} 08/31/2021 04:02:28 - INFO - __main__ - Step 81916: {'lr': 0.00021869301628076862, 'samples': 15727872, 'steps': 81915, 'loss/train': 1.0459150075912476} 08/31/2021 04:02:29 - INFO - __main__ - Step 81917: {'lr': 0.0002186877513181773, 'samples': 15728064, 'steps': 81916, 'loss/train': 0.5553115606307983} 08/31/2021 04:02:31 - INFO - __main__ - Step 81918: {'lr': 0.00021868248636969478, 'samples': 15728256, 'steps': 81917, 'loss/train': 2.644864082336426} 08/31/2021 04:02:31 - INFO - __main__ - Step 81919: {'lr': 0.0002186772214353235, 'samples': 15728448, 'steps': 81918, 'loss/train': 1.1494086980819702} 08/31/2021 04:02:31 - INFO - __main__ - Step 81920: {'lr': 0.00021867195651506576, 'samples': 15728640, 'steps': 81919, 'loss/train': 1.3841685056686401} 08/31/2021 04:02:32 - INFO - __main__ - Step 81921: {'lr': 0.00021866669160892392, 'samples': 15728832, 'steps': 81920, 'loss/train': 1.2484484910964966} 08/31/2021 04:02:32 - INFO - __main__ - Step 81922: {'lr': 0.0002186614267169004, 'samples': 15729024, 'steps': 81921, 'loss/train': 1.4594513177871704} 08/31/2021 04:02:34 - INFO - __main__ - Step 81923: {'lr': 0.00021865616183899757, 'samples': 15729216, 'steps': 81922, 'loss/train': 0.061861973255872726} 08/31/2021 04:02:34 - INFO - __main__ - Step 81924: {'lr': 0.0002186508969752179, 'samples': 15729408, 'steps': 81923, 'loss/train': 0.723072350025177} 08/31/2021 04:02:34 - INFO - __main__ - Step 81925: {'lr': 0.00021864563212556351, 'samples': 15729600, 'steps': 81924, 'loss/train': 1.3908699750900269} 08/31/2021 04:02:35 - INFO - __main__ - Step 81926: {'lr': 0.00021864036729003693, 'samples': 15729792, 'steps': 81925, 'loss/train': 1.596592664718628} 08/31/2021 04:02:35 - INFO - __main__ - Step 81927: {'lr': 0.00021863510246864054, 'samples': 15729984, 'steps': 81926, 'loss/train': 0.9779976010322571} 08/31/2021 04:02:35 - INFO - __main__ - Step 81928: {'lr': 0.00021862983766137667, 'samples': 15730176, 'steps': 81927, 'loss/train': 0.8749363422393799} 08/31/2021 04:02:38 - INFO - __main__ - Step 81929: {'lr': 0.0002186245728682477, 'samples': 15730368, 'steps': 81928, 'loss/train': 1.7328373193740845} 08/31/2021 04:02:38 - INFO - __main__ - Step 81930: {'lr': 0.00021861930808925607, 'samples': 15730560, 'steps': 81929, 'loss/train': 1.224126935005188} 08/31/2021 04:02:39 - INFO - __main__ - Step 81931: {'lr': 0.00021861404332440405, 'samples': 15730752, 'steps': 81930, 'loss/train': 1.448651909828186} 08/31/2021 04:02:39 - INFO - __main__ - Step 81932: {'lr': 0.00021860877857369403, 'samples': 15730944, 'steps': 81931, 'loss/train': 1.5986835956573486} 08/31/2021 04:02:39 - INFO - __main__ - Step 81933: {'lr': 0.00021860351383712847, 'samples': 15731136, 'steps': 81932, 'loss/train': 1.5630309581756592} 08/31/2021 04:02:41 - INFO - __main__ - Step 81934: {'lr': 0.00021859824911470965, 'samples': 15731328, 'steps': 81933, 'loss/train': 0.372530460357666} 08/31/2021 04:02:41 - INFO - __main__ - Step 81935: {'lr': 0.00021859298440644, 'samples': 15731520, 'steps': 81934, 'loss/train': 1.2785359621047974} 08/31/2021 04:02:41 - INFO - __main__ - Step 81936: {'lr': 0.00021858771971232184, 'samples': 15731712, 'steps': 81935, 'loss/train': 1.302064061164856} 08/31/2021 04:02:42 - INFO - __main__ - Step 81937: {'lr': 0.00021858245503235765, 'samples': 15731904, 'steps': 81936, 'loss/train': 1.5913342237472534} 08/31/2021 04:02:42 - INFO - __main__ - Step 81938: {'lr': 0.00021857719036654966, 'samples': 15732096, 'steps': 81937, 'loss/train': 0.8621087670326233} 08/31/2021 04:02:44 - INFO - __main__ - Step 81939: {'lr': 0.00021857192571490028, 'samples': 15732288, 'steps': 81938, 'loss/train': 1.5058027505874634} 08/31/2021 04:02:44 - INFO - __main__ - Step 81940: {'lr': 0.00021856666107741192, 'samples': 15732480, 'steps': 81939, 'loss/train': 1.481328010559082} 08/31/2021 04:02:44 - INFO - __main__ - Step 81941: {'lr': 0.00021856139645408694, 'samples': 15732672, 'steps': 81940, 'loss/train': 1.349172592163086} 08/31/2021 04:02:45 - INFO - __main__ - Step 81942: {'lr': 0.0002185561318449277, 'samples': 15732864, 'steps': 81941, 'loss/train': 0.03912884369492531} 08/31/2021 04:02:45 - INFO - __main__ - Step 81943: {'lr': 0.00021855086724993658, 'samples': 15733056, 'steps': 81942, 'loss/train': 1.698216438293457} 08/31/2021 04:02:47 - INFO - __main__ - Step 81944: {'lr': 0.00021854560266911595, 'samples': 15733248, 'steps': 81943, 'loss/train': 1.2686930894851685} 08/31/2021 04:02:47 - INFO - __main__ - Step 81945: {'lr': 0.0002185403381024682, 'samples': 15733440, 'steps': 81944, 'loss/train': 1.2710514068603516} 08/31/2021 04:02:47 - INFO - __main__ - Step 81946: {'lr': 0.0002185350735499957, 'samples': 15733632, 'steps': 81945, 'loss/train': 1.49440598487854} 08/31/2021 04:02:48 - INFO - __main__ - Step 81947: {'lr': 0.00021852980901170078, 'samples': 15733824, 'steps': 81946, 'loss/train': 1.1808985471725464} 08/31/2021 04:02:48 - INFO - __main__ - Step 81948: {'lr': 0.0002185245444875859, 'samples': 15734016, 'steps': 81947, 'loss/train': 1.3516288995742798} 08/31/2021 04:02:48 - INFO - __main__ - Step 81949: {'lr': 0.00021851927997765334, 'samples': 15734208, 'steps': 81948, 'loss/train': 1.1992101669311523} 08/31/2021 04:02:50 - INFO - __main__ - Step 81950: {'lr': 0.00021851401548190547, 'samples': 15734400, 'steps': 81949, 'loss/train': 0.3901791572570801} 08/31/2021 04:02:51 - INFO - __main__ - Step 81951: {'lr': 0.00021850875100034477, 'samples': 15734592, 'steps': 81950, 'loss/train': 1.6965734958648682} 08/31/2021 04:02:51 - INFO - __main__ - Step 81952: {'lr': 0.00021850348653297351, 'samples': 15734784, 'steps': 81951, 'loss/train': 1.682214379310608} 08/31/2021 04:02:51 - INFO - __main__ - Step 81953: {'lr': 0.00021849822207979408, 'samples': 15734976, 'steps': 81952, 'loss/train': 1.0217921733856201} 08/31/2021 04:02:52 - INFO - __main__ - Step 81954: {'lr': 0.00021849295764080886, 'samples': 15735168, 'steps': 81953, 'loss/train': 0.32208797335624695} 08/31/2021 04:02:53 - INFO - __main__ - Step 81955: {'lr': 0.00021848769321602024, 'samples': 15735360, 'steps': 81954, 'loss/train': 1.0116976499557495} 08/31/2021 04:02:54 - INFO - __main__ - Step 81956: {'lr': 0.00021848242880543058, 'samples': 15735552, 'steps': 81955, 'loss/train': 1.4846069812774658} 08/31/2021 04:02:54 - INFO - __main__ - Step 81957: {'lr': 0.00021847716440904222, 'samples': 15735744, 'steps': 81956, 'loss/train': 0.7656634449958801} 08/31/2021 04:02:54 - INFO - __main__ - Step 81958: {'lr': 0.00021847190002685757, 'samples': 15735936, 'steps': 81957, 'loss/train': 1.3023991584777832} 08/31/2021 04:02:55 - INFO - __main__ - Step 81959: {'lr': 0.00021846663565887908, 'samples': 15736128, 'steps': 81958, 'loss/train': 1.7238337993621826} 08/31/2021 04:02:56 - INFO - __main__ - Step 81960: {'lr': 0.00021846137130510895, 'samples': 15736320, 'steps': 81959, 'loss/train': 1.1592316627502441} 08/31/2021 04:02:57 - INFO - __main__ - Step 81961: {'lr': 0.00021845610696554968, 'samples': 15736512, 'steps': 81960, 'loss/train': 0.5014976859092712} 08/31/2021 04:02:57 - INFO - __main__ - Step 81962: {'lr': 0.00021845084264020357, 'samples': 15736704, 'steps': 81961, 'loss/train': 1.9614413976669312} 08/31/2021 04:02:57 - INFO - __main__ - Step 81963: {'lr': 0.00021844557832907303, 'samples': 15736896, 'steps': 81962, 'loss/train': 1.5837057828903198} 08/31/2021 04:02:58 - INFO - __main__ - Step 81964: {'lr': 0.00021844031403216047, 'samples': 15737088, 'steps': 81963, 'loss/train': 1.5177032947540283} 08/31/2021 04:02:59 - INFO - __main__ - Step 81965: {'lr': 0.00021843504974946817, 'samples': 15737280, 'steps': 81964, 'loss/train': 1.2456668615341187} 08/31/2021 04:02:59 - INFO - __main__ - Step 81966: {'lr': 0.00021842978548099857, 'samples': 15737472, 'steps': 81965, 'loss/train': 1.0491021871566772} 08/31/2021 04:03:00 - INFO - __main__ - Step 81967: {'lr': 0.000218424521226754, 'samples': 15737664, 'steps': 81966, 'loss/train': 1.6903057098388672} 08/31/2021 04:03:00 - INFO - __main__ - Step 81968: {'lr': 0.00021841925698673687, 'samples': 15737856, 'steps': 81967, 'loss/train': 0.9090187549591064} 08/31/2021 04:03:01 - INFO - __main__ - Step 81969: {'lr': 0.0002184139927609495, 'samples': 15738048, 'steps': 81968, 'loss/train': 1.5919108390808105} 08/31/2021 04:03:02 - INFO - __main__ - Step 81970: {'lr': 0.00021840872854939436, 'samples': 15738240, 'steps': 81969, 'loss/train': 0.9819814562797546} 08/31/2021 04:03:03 - INFO - __main__ - Step 81971: {'lr': 0.00021840346435207376, 'samples': 15738432, 'steps': 81970, 'loss/train': 0.8554028272628784} 08/31/2021 04:03:03 - INFO - __main__ - Step 81972: {'lr': 0.00021839820016899002, 'samples': 15738624, 'steps': 81971, 'loss/train': 1.4777634143829346} 08/31/2021 04:03:03 - INFO - __main__ - Step 81973: {'lr': 0.00021839293600014556, 'samples': 15738816, 'steps': 81972, 'loss/train': 1.1005419492721558} 08/31/2021 04:03:04 - INFO - __main__ - Step 81974: {'lr': 0.00021838767184554278, 'samples': 15739008, 'steps': 81973, 'loss/train': 2.1736385822296143} 08/31/2021 04:03:05 - INFO - __main__ - Step 81975: {'lr': 0.00021838240770518402, 'samples': 15739200, 'steps': 81974, 'loss/train': 0.7397082448005676} 08/31/2021 04:03:06 - INFO - __main__ - Step 81976: {'lr': 0.00021837714357907166, 'samples': 15739392, 'steps': 81975, 'loss/train': 1.1402188539505005} 08/31/2021 04:03:06 - INFO - __main__ - Step 81977: {'lr': 0.00021837187946720804, 'samples': 15739584, 'steps': 81976, 'loss/train': 1.075486660003662} 08/31/2021 04:03:07 - INFO - __main__ - Step 81978: {'lr': 0.00021836661536959567, 'samples': 15739776, 'steps': 81977, 'loss/train': 0.9507874250411987} 08/31/2021 04:03:07 - INFO - __main__ - Step 81979: {'lr': 0.00021836135128623673, 'samples': 15739968, 'steps': 81978, 'loss/train': 0.7758558988571167} 08/31/2021 04:03:07 - INFO - __main__ - Step 81980: {'lr': 0.00021835608721713367, 'samples': 15740160, 'steps': 81979, 'loss/train': 1.75319504737854} 08/31/2021 04:03:09 - INFO - __main__ - Step 81981: {'lr': 0.00021835082316228892, 'samples': 15740352, 'steps': 81980, 'loss/train': 1.2537813186645508} 08/31/2021 04:03:10 - INFO - __main__ - Step 81982: {'lr': 0.0002183455591217048, 'samples': 15740544, 'steps': 81981, 'loss/train': 1.1665500402450562} 08/31/2021 04:03:10 - INFO - __main__ - Step 81983: {'lr': 0.00021834029509538365, 'samples': 15740736, 'steps': 81982, 'loss/train': 1.3265812397003174} 08/31/2021 04:03:10 - INFO - __main__ - Step 81984: {'lr': 0.00021833503108332786, 'samples': 15740928, 'steps': 81983, 'loss/train': 0.05097486451268196} 08/31/2021 04:03:11 - INFO - __main__ - Step 81985: {'lr': 0.0002183297670855398, 'samples': 15741120, 'steps': 81984, 'loss/train': 1.444785714149475} 08/31/2021 04:03:13 - INFO - __main__ - Step 81986: {'lr': 0.0002183245031020219, 'samples': 15741312, 'steps': 81985, 'loss/train': 1.2836428880691528} 08/31/2021 04:03:13 - INFO - __main__ - Step 81987: {'lr': 0.00021831923913277648, 'samples': 15741504, 'steps': 81986, 'loss/train': 1.4052376747131348} 08/31/2021 04:03:13 - INFO - __main__ - Step 81988: {'lr': 0.00021831397517780592, 'samples': 15741696, 'steps': 81987, 'loss/train': 0.5416253209114075} 08/31/2021 04:03:14 - INFO - __main__ - Step 81989: {'lr': 0.0002183087112371126, 'samples': 15741888, 'steps': 81988, 'loss/train': 0.9858121871948242} 08/31/2021 04:03:14 - INFO - __main__ - Step 81990: {'lr': 0.00021830344731069886, 'samples': 15742080, 'steps': 81989, 'loss/train': 1.2841895818710327} 08/31/2021 04:03:16 - INFO - __main__ - Step 81991: {'lr': 0.00021829818339856716, 'samples': 15742272, 'steps': 81990, 'loss/train': 0.9257730841636658} 08/31/2021 04:03:16 - INFO - __main__ - Step 81992: {'lr': 0.00021829291950071984, 'samples': 15742464, 'steps': 81991, 'loss/train': 1.0905282497406006} 08/31/2021 04:03:16 - INFO - __main__ - Step 81993: {'lr': 0.00021828765561715915, 'samples': 15742656, 'steps': 81992, 'loss/train': 0.7526831030845642} 08/31/2021 04:03:17 - INFO - __main__ - Step 81994: {'lr': 0.00021828239174788756, 'samples': 15742848, 'steps': 81993, 'loss/train': 1.1457847356796265} 08/31/2021 04:03:17 - INFO - __main__ - Step 81995: {'lr': 0.00021827712789290743, 'samples': 15743040, 'steps': 81994, 'loss/train': 0.6628753542900085} 08/31/2021 04:03:19 - INFO - __main__ - Step 81996: {'lr': 0.00021827186405222115, 'samples': 15743232, 'steps': 81995, 'loss/train': 1.5799425840377808} 08/31/2021 04:03:19 - INFO - __main__ - Step 81997: {'lr': 0.0002182666002258311, 'samples': 15743424, 'steps': 81996, 'loss/train': 0.6701232194900513} 08/31/2021 04:03:19 - INFO - __main__ - Step 81998: {'lr': 0.00021826133641373961, 'samples': 15743616, 'steps': 81997, 'loss/train': 1.3947597742080688} 08/31/2021 04:03:20 - INFO - __main__ - Step 81999: {'lr': 0.00021825607261594904, 'samples': 15743808, 'steps': 81998, 'loss/train': 0.8219894766807556} 08/31/2021 04:03:20 - INFO - __main__ - Step 82000: {'lr': 0.00021825080883246186, 'samples': 15744000, 'steps': 81999, 'loss/train': 0.7817355990409851} 08/31/2021 04:03:22 - INFO - __main__ - Step 82001: {'lr': 0.0002182455450632803, 'samples': 15744192, 'steps': 82000, 'loss/train': 0.8922874331474304} 08/31/2021 04:03:22 - INFO - __main__ - Step 82002: {'lr': 0.00021824028130840688, 'samples': 15744384, 'steps': 82001, 'loss/train': 0.5618041753768921} 08/31/2021 04:03:23 - INFO - __main__ - Step 82003: {'lr': 0.00021823501756784385, 'samples': 15744576, 'steps': 82002, 'loss/train': 0.6666083335876465} 08/31/2021 04:03:23 - INFO - __main__ - Step 82004: {'lr': 0.00021822975384159365, 'samples': 15744768, 'steps': 82003, 'loss/train': 1.1005070209503174} 08/31/2021 04:03:23 - INFO - __main__ - Step 82005: {'lr': 0.00021822449012965872, 'samples': 15744960, 'steps': 82004, 'loss/train': 0.630719780921936} 08/31/2021 04:03:25 - INFO - __main__ - Step 82006: {'lr': 0.00021821922643204127, 'samples': 15745152, 'steps': 82005, 'loss/train': 1.1281098127365112} 08/31/2021 04:03:26 - INFO - __main__ - Step 82007: {'lr': 0.00021821396274874372, 'samples': 15745344, 'steps': 82006, 'loss/train': 0.05306578427553177} 08/31/2021 04:03:26 - INFO - __main__ - Step 82008: {'lr': 0.00021820869907976847, 'samples': 15745536, 'steps': 82007, 'loss/train': 1.7055108547210693} 08/31/2021 04:03:26 - INFO - __main__ - Step 82009: {'lr': 0.0002182034354251179, 'samples': 15745728, 'steps': 82008, 'loss/train': 1.4072611331939697} 08/31/2021 04:03:27 - INFO - __main__ - Step 82010: {'lr': 0.00021819817178479436, 'samples': 15745920, 'steps': 82009, 'loss/train': 0.6622198820114136} 08/31/2021 04:03:28 - INFO - __main__ - Step 82011: {'lr': 0.00021819290815880028, 'samples': 15746112, 'steps': 82010, 'loss/train': 0.08669630438089371} 08/31/2021 04:03:28 - INFO - __main__ - Step 82012: {'lr': 0.00021818764454713792, 'samples': 15746304, 'steps': 82011, 'loss/train': 0.8982341885566711} 08/31/2021 04:03:29 - INFO - __main__ - Step 82013: {'lr': 0.00021818238094980973, 'samples': 15746496, 'steps': 82012, 'loss/train': 1.411412239074707} 08/31/2021 04:03:29 - INFO - __main__ - Step 82014: {'lr': 0.00021817711736681812, 'samples': 15746688, 'steps': 82013, 'loss/train': 0.4244047999382019} 08/31/2021 04:03:29 - INFO - __main__ - Step 82015: {'lr': 0.00021817185379816536, 'samples': 15746880, 'steps': 82014, 'loss/train': 1.198298692703247} 08/31/2021 04:03:31 - INFO - __main__ - Step 82016: {'lr': 0.00021816659024385387, 'samples': 15747072, 'steps': 82015, 'loss/train': 1.185205101966858} 08/31/2021 04:03:31 - INFO - __main__ - Step 82017: {'lr': 0.00021816132670388603, 'samples': 15747264, 'steps': 82016, 'loss/train': 1.9335178136825562} 08/31/2021 04:03:32 - INFO - __main__ - Step 82018: {'lr': 0.0002181560631782643, 'samples': 15747456, 'steps': 82017, 'loss/train': 0.332885205745697} 08/31/2021 04:03:32 - INFO - __main__ - Step 82019: {'lr': 0.0002181507996669909, 'samples': 15747648, 'steps': 82018, 'loss/train': 1.1602238416671753} 08/31/2021 04:03:32 - INFO - __main__ - Step 82020: {'lr': 0.00021814553617006822, 'samples': 15747840, 'steps': 82019, 'loss/train': 0.9338942766189575} 08/31/2021 04:03:33 - INFO - __main__ - Step 82021: {'lr': 0.00021814027268749866, 'samples': 15748032, 'steps': 82020, 'loss/train': 1.4087181091308594} 08/31/2021 04:03:34 - INFO - __main__ - Step 82022: {'lr': 0.00021813500921928465, 'samples': 15748224, 'steps': 82021, 'loss/train': 1.383581280708313} 08/31/2021 04:03:35 - INFO - __main__ - Step 82023: {'lr': 0.00021812974576542845, 'samples': 15748416, 'steps': 82022, 'loss/train': 0.9863107800483704} 08/31/2021 04:03:35 - INFO - __main__ - Step 82024: {'lr': 0.00021812448232593252, 'samples': 15748608, 'steps': 82023, 'loss/train': 1.4335049390792847} 08/31/2021 04:03:35 - INFO - __main__ - Step 82025: {'lr': 0.00021811921890079922, 'samples': 15748800, 'steps': 82024, 'loss/train': 1.6437486410140991} 08/31/2021 04:03:36 - INFO - __main__ - Step 82026: {'lr': 0.00021811395549003088, 'samples': 15748992, 'steps': 82025, 'loss/train': 1.435939073562622} 08/31/2021 04:03:37 - INFO - __main__ - Step 82027: {'lr': 0.00021810869209362994, 'samples': 15749184, 'steps': 82026, 'loss/train': 1.6644728183746338} 08/31/2021 04:03:38 - INFO - __main__ - Step 82028: {'lr': 0.00021810342871159873, 'samples': 15749376, 'steps': 82027, 'loss/train': 0.19493745267391205} 08/31/2021 04:03:38 - INFO - __main__ - Step 82029: {'lr': 0.00021809816534393956, 'samples': 15749568, 'steps': 82028, 'loss/train': 1.2965179681777954} 08/31/2021 04:03:38 - INFO - __main__ - Step 82030: {'lr': 0.00021809290199065494, 'samples': 15749760, 'steps': 82029, 'loss/train': 1.2871394157409668} 08/31/2021 04:03:39 - INFO - __main__ - Step 82031: {'lr': 0.0002180876386517472, 'samples': 15749952, 'steps': 82030, 'loss/train': 1.4173134565353394} 08/31/2021 04:03:40 - INFO - __main__ - Step 82032: {'lr': 0.00021808237532721864, 'samples': 15750144, 'steps': 82031, 'loss/train': 1.6226152181625366} 08/31/2021 04:03:41 - INFO - __main__ - Step 82033: {'lr': 0.00021807711201707165, 'samples': 15750336, 'steps': 82032, 'loss/train': 1.5575804710388184} 08/31/2021 04:03:41 - INFO - __main__ - Step 82034: {'lr': 0.00021807184872130858, 'samples': 15750528, 'steps': 82033, 'loss/train': 1.3488729000091553} 08/31/2021 04:03:41 - INFO - __main__ - Step 82035: {'lr': 0.00021806658543993188, 'samples': 15750720, 'steps': 82034, 'loss/train': 1.2212198972702026} 08/31/2021 04:03:42 - INFO - __main__ - Step 82036: {'lr': 0.0002180613221729439, 'samples': 15750912, 'steps': 82035, 'loss/train': 1.3482927083969116} 08/31/2021 04:03:44 - INFO - __main__ - Step 82037: {'lr': 0.00021805605892034695, 'samples': 15751104, 'steps': 82036, 'loss/train': 1.0298478603363037} 08/31/2021 04:03:44 - INFO - __main__ - Step 82038: {'lr': 0.00021805079568214348, 'samples': 15751296, 'steps': 82037, 'loss/train': 0.9653325080871582} 08/31/2021 04:03:45 - INFO - __main__ - Step 82039: {'lr': 0.0002180455324583358, 'samples': 15751488, 'steps': 82038, 'loss/train': 1.0880858898162842} 08/31/2021 04:03:45 - INFO - __main__ - Step 82040: {'lr': 0.00021804026924892634, 'samples': 15751680, 'steps': 82039, 'loss/train': 1.2976208925247192} 08/31/2021 04:03:45 - INFO - __main__ - Step 82041: {'lr': 0.0002180350060539174, 'samples': 15751872, 'steps': 82040, 'loss/train': 1.0664966106414795} 08/31/2021 04:03:47 - INFO - __main__ - Step 82042: {'lr': 0.00021802974287331146, 'samples': 15752064, 'steps': 82041, 'loss/train': 0.8573023676872253} 08/31/2021 04:03:47 - INFO - __main__ - Step 82043: {'lr': 0.00021802447970711074, 'samples': 15752256, 'steps': 82042, 'loss/train': 0.03203684836626053} 08/31/2021 04:03:48 - INFO - __main__ - Step 82044: {'lr': 0.00021801921655531775, 'samples': 15752448, 'steps': 82043, 'loss/train': 1.4335209131240845} 08/31/2021 04:03:48 - INFO - __main__ - Step 82045: {'lr': 0.00021801395341793493, 'samples': 15752640, 'steps': 82044, 'loss/train': 1.7589876651763916} 08/31/2021 04:03:48 - INFO - __main__ - Step 82046: {'lr': 0.0002180086902949644, 'samples': 15752832, 'steps': 82045, 'loss/train': 0.8486446738243103} 08/31/2021 04:03:50 - INFO - __main__ - Step 82047: {'lr': 0.00021800342718640865, 'samples': 15753024, 'steps': 82046, 'loss/train': 1.2820390462875366} 08/31/2021 04:03:50 - INFO - __main__ - Step 82048: {'lr': 0.00021799816409227008, 'samples': 15753216, 'steps': 82047, 'loss/train': 1.2730600833892822} 08/31/2021 04:03:51 - INFO - __main__ - Step 82049: {'lr': 0.00021799290101255105, 'samples': 15753408, 'steps': 82048, 'loss/train': 1.652482271194458} 08/31/2021 04:03:51 - INFO - __main__ - Step 82050: {'lr': 0.00021798763794725391, 'samples': 15753600, 'steps': 82049, 'loss/train': 0.7137287855148315} 08/31/2021 04:03:51 - INFO - __main__ - Step 82051: {'lr': 0.00021798237489638103, 'samples': 15753792, 'steps': 82050, 'loss/train': 1.28959059715271} 08/31/2021 04:03:53 - INFO - __main__ - Step 82052: {'lr': 0.00021797711185993478, 'samples': 15753984, 'steps': 82051, 'loss/train': 1.4844728708267212} 08/31/2021 04:03:54 - INFO - __main__ - Step 82053: {'lr': 0.00021797184883791762, 'samples': 15754176, 'steps': 82052, 'loss/train': 0.6583536863327026} 08/31/2021 04:03:54 - INFO - __main__ - Step 82054: {'lr': 0.0002179665858303318, 'samples': 15754368, 'steps': 82053, 'loss/train': 1.7348860502243042} 08/31/2021 04:03:54 - INFO - __main__ - Step 82055: {'lr': 0.00021796132283717976, 'samples': 15754560, 'steps': 82054, 'loss/train': 1.356460690498352} 08/31/2021 04:03:55 - INFO - __main__ - Step 82056: {'lr': 0.00021795605985846383, 'samples': 15754752, 'steps': 82055, 'loss/train': 1.4566998481750488} 08/31/2021 04:03:55 - INFO - __main__ - Step 82057: {'lr': 0.00021795079689418645, 'samples': 15754944, 'steps': 82056, 'loss/train': 1.3096336126327515} 08/31/2021 04:03:56 - INFO - __main__ - Step 82058: {'lr': 0.00021794553394435, 'samples': 15755136, 'steps': 82057, 'loss/train': 1.1387393474578857} 08/31/2021 04:03:57 - INFO - __main__ - Step 82059: {'lr': 0.00021794027100895675, 'samples': 15755328, 'steps': 82058, 'loss/train': 0.7021702527999878} 08/31/2021 04:03:57 - INFO - __main__ - Step 82060: {'lr': 0.0002179350080880091, 'samples': 15755520, 'steps': 82059, 'loss/train': 0.4793241322040558} 08/31/2021 04:03:58 - INFO - __main__ - Step 82061: {'lr': 0.00021792974518150941, 'samples': 15755712, 'steps': 82060, 'loss/train': 0.570813775062561} 08/31/2021 04:03:58 - INFO - __main__ - Step 82062: {'lr': 0.00021792448228946011, 'samples': 15755904, 'steps': 82061, 'loss/train': 1.1913882493972778} 08/31/2021 04:03:59 - INFO - __main__ - Step 82063: {'lr': 0.00021791921941186353, 'samples': 15756096, 'steps': 82062, 'loss/train': 1.5207337141036987} 08/31/2021 04:04:00 - INFO - __main__ - Step 82064: {'lr': 0.00021791395654872204, 'samples': 15756288, 'steps': 82063, 'loss/train': 0.6137406826019287} 08/31/2021 04:04:00 - INFO - __main__ - Step 82065: {'lr': 0.00021790869370003803, 'samples': 15756480, 'steps': 82064, 'loss/train': 1.270148754119873} 08/31/2021 04:04:00 - INFO - __main__ - Step 82066: {'lr': 0.0002179034308658139, 'samples': 15756672, 'steps': 82065, 'loss/train': 1.3006690740585327} 08/31/2021 04:04:01 - INFO - __main__ - Step 82067: {'lr': 0.000217898168046052, 'samples': 15756864, 'steps': 82066, 'loss/train': 1.3536125421524048} 08/31/2021 04:04:02 - INFO - __main__ - Step 82068: {'lr': 0.00021789290524075464, 'samples': 15757056, 'steps': 82067, 'loss/train': 1.1756417751312256} 08/31/2021 04:04:03 - INFO - __main__ - Step 82069: {'lr': 0.00021788764244992426, 'samples': 15757248, 'steps': 82068, 'loss/train': 0.8971790075302124} 08/31/2021 04:04:03 - INFO - __main__ - Step 82070: {'lr': 0.00021788237967356323, 'samples': 15757440, 'steps': 82069, 'loss/train': 1.3212722539901733} 08/31/2021 04:04:04 - INFO - __main__ - Step 82071: {'lr': 0.00021787711691167387, 'samples': 15757632, 'steps': 82070, 'loss/train': 1.2378894090652466} 08/31/2021 04:04:04 - INFO - __main__ - Step 82072: {'lr': 0.00021787185416425873, 'samples': 15757824, 'steps': 82071, 'loss/train': 1.3483270406723022} 08/31/2021 04:04:05 - INFO - __main__ - Step 82073: {'lr': 0.0002178665914313199, 'samples': 15758016, 'steps': 82072, 'loss/train': 1.3523597717285156} 08/31/2021 04:04:06 - INFO - __main__ - Step 82074: {'lr': 0.0002178613287128599, 'samples': 15758208, 'steps': 82073, 'loss/train': 1.1668357849121094} 08/31/2021 04:04:06 - INFO - __main__ - Step 82075: {'lr': 0.00021785606600888108, 'samples': 15758400, 'steps': 82074, 'loss/train': 0.669256329536438} 08/31/2021 04:04:07 - INFO - __main__ - Step 82076: {'lr': 0.00021785080331938585, 'samples': 15758592, 'steps': 82075, 'loss/train': 1.1880998611450195} 08/31/2021 04:04:07 - INFO - __main__ - Step 82077: {'lr': 0.0002178455406443765, 'samples': 15758784, 'steps': 82076, 'loss/train': 1.08310067653656} 08/31/2021 04:04:08 - INFO - __main__ - Step 82078: {'lr': 0.0002178402779838555, 'samples': 15758976, 'steps': 82077, 'loss/train': 0.7388936281204224} 08/31/2021 04:04:09 - INFO - __main__ - Step 82079: {'lr': 0.00021783501533782516, 'samples': 15759168, 'steps': 82078, 'loss/train': 1.4404696226119995} 08/31/2021 04:04:09 - INFO - __main__ - Step 82080: {'lr': 0.00021782975270628785, 'samples': 15759360, 'steps': 82079, 'loss/train': 1.0426422357559204} 08/31/2021 04:04:10 - INFO - __main__ - Step 82081: {'lr': 0.000217824490089246, 'samples': 15759552, 'steps': 82080, 'loss/train': 1.1989014148712158} 08/31/2021 04:04:10 - INFO - __main__ - Step 82082: {'lr': 0.00021781922748670188, 'samples': 15759744, 'steps': 82081, 'loss/train': 1.2511788606643677} 08/31/2021 04:04:11 - INFO - __main__ - Step 82083: {'lr': 0.000217813964898658, 'samples': 15759936, 'steps': 82082, 'loss/train': 1.3675141334533691} 08/31/2021 04:04:12 - INFO - __main__ - Step 82084: {'lr': 0.00021780870232511663, 'samples': 15760128, 'steps': 82083, 'loss/train': 2.9833221435546875} 08/31/2021 04:04:12 - INFO - __main__ - Step 82085: {'lr': 0.00021780343976608016, 'samples': 15760320, 'steps': 82084, 'loss/train': 1.7622054815292358} 08/31/2021 04:04:13 - INFO - __main__ - Step 82086: {'lr': 0.00021779817722155094, 'samples': 15760512, 'steps': 82085, 'loss/train': 1.9986093044281006} 08/31/2021 04:04:13 - INFO - __main__ - Step 82087: {'lr': 0.00021779291469153136, 'samples': 15760704, 'steps': 82086, 'loss/train': 1.2686877250671387} 08/31/2021 04:04:15 - INFO - __main__ - Step 82088: {'lr': 0.00021778765217602382, 'samples': 15760896, 'steps': 82087, 'loss/train': 1.0267150402069092} 08/31/2021 04:04:16 - INFO - __main__ - Step 82089: {'lr': 0.0002177823896750306, 'samples': 15761088, 'steps': 82088, 'loss/train': 1.3964611291885376} 08/31/2021 04:04:16 - INFO - __main__ - Step 82090: {'lr': 0.0002177771271885542, 'samples': 15761280, 'steps': 82089, 'loss/train': 1.1634877920150757} 08/31/2021 04:04:17 - INFO - __main__ - Step 82091: {'lr': 0.0002177718647165969, 'samples': 15761472, 'steps': 82090, 'loss/train': 0.06514439731836319} 08/31/2021 04:04:17 - INFO - __main__ - Step 82092: {'lr': 0.00021776660225916112, 'samples': 15761664, 'steps': 82091, 'loss/train': 1.4008716344833374} 08/31/2021 04:04:18 - INFO - __main__ - Step 82093: {'lr': 0.00021776133981624921, 'samples': 15761856, 'steps': 82092, 'loss/train': 0.2564848065376282} 08/31/2021 04:04:19 - INFO - __main__ - Step 82094: {'lr': 0.00021775607738786358, 'samples': 15762048, 'steps': 82093, 'loss/train': 1.3149447441101074} 08/31/2021 04:04:19 - INFO - __main__ - Step 82095: {'lr': 0.0002177508149740065, 'samples': 15762240, 'steps': 82094, 'loss/train': 1.5262759923934937} 08/31/2021 04:04:20 - INFO - __main__ - Step 82096: {'lr': 0.00021774555257468044, 'samples': 15762432, 'steps': 82095, 'loss/train': 1.3958971500396729} 08/31/2021 04:04:20 - INFO - __main__ - Step 82097: {'lr': 0.00021774029018988773, 'samples': 15762624, 'steps': 82096, 'loss/train': 1.4855107069015503} 08/31/2021 04:04:20 - INFO - __main__ - Step 82098: {'lr': 0.00021773502781963073, 'samples': 15762816, 'steps': 82097, 'loss/train': 0.0951836034655571} 08/31/2021 04:04:22 - INFO - __main__ - Step 82099: {'lr': 0.00021772976546391188, 'samples': 15763008, 'steps': 82098, 'loss/train': 1.1941423416137695} 08/31/2021 04:04:22 - INFO - __main__ - Step 82100: {'lr': 0.00021772450312273345, 'samples': 15763200, 'steps': 82099, 'loss/train': 1.15571928024292} 08/31/2021 04:04:23 - INFO - __main__ - Step 82101: {'lr': 0.00021771924079609788, 'samples': 15763392, 'steps': 82100, 'loss/train': 1.8735194206237793} 08/31/2021 04:04:23 - INFO - __main__ - Step 82102: {'lr': 0.00021771397848400752, 'samples': 15763584, 'steps': 82101, 'loss/train': 0.9423435926437378} 08/31/2021 04:04:23 - INFO - __main__ - Step 82103: {'lr': 0.0002177087161864647, 'samples': 15763776, 'steps': 82102, 'loss/train': 1.0872883796691895} 08/31/2021 04:04:25 - INFO - __main__ - Step 82104: {'lr': 0.00021770345390347188, 'samples': 15763968, 'steps': 82103, 'loss/train': 0.8596224784851074} 08/31/2021 04:04:25 - INFO - __main__ - Step 82105: {'lr': 0.00021769819163503144, 'samples': 15764160, 'steps': 82104, 'loss/train': 0.04857596382498741} 08/31/2021 04:04:26 - INFO - __main__ - Step 82106: {'lr': 0.00021769292938114563, 'samples': 15764352, 'steps': 82105, 'loss/train': 1.3397420644760132} 08/31/2021 04:04:26 - INFO - __main__ - Step 82107: {'lr': 0.00021768766714181688, 'samples': 15764544, 'steps': 82106, 'loss/train': 1.5250500440597534} 08/31/2021 04:04:26 - INFO - __main__ - Step 82108: {'lr': 0.00021768240491704756, 'samples': 15764736, 'steps': 82107, 'loss/train': 1.2127811908721924} 08/31/2021 04:04:28 - INFO - __main__ - Step 82109: {'lr': 0.00021767714270684008, 'samples': 15764928, 'steps': 82108, 'loss/train': 1.0987244844436646} 08/31/2021 04:04:28 - INFO - __main__ - Step 82110: {'lr': 0.00021767188051119673, 'samples': 15765120, 'steps': 82109, 'loss/train': 0.12260116636753082} 08/31/2021 04:04:29 - INFO - __main__ - Step 82111: {'lr': 0.00021766661833012, 'samples': 15765312, 'steps': 82110, 'loss/train': 1.2652771472930908} 08/31/2021 04:04:29 - INFO - __main__ - Step 82112: {'lr': 0.0002176613561636122, 'samples': 15765504, 'steps': 82111, 'loss/train': 0.8108921051025391} 08/31/2021 04:04:29 - INFO - __main__ - Step 82113: {'lr': 0.00021765609401167566, 'samples': 15765696, 'steps': 82112, 'loss/train': 0.9723032712936401} 08/31/2021 04:04:31 - INFO - __main__ - Step 82114: {'lr': 0.0002176508318743128, 'samples': 15765888, 'steps': 82113, 'loss/train': 1.223886251449585} 08/31/2021 04:04:31 - INFO - __main__ - Step 82115: {'lr': 0.00021764556975152591, 'samples': 15766080, 'steps': 82114, 'loss/train': 1.1304125785827637} 08/31/2021 04:04:32 - INFO - __main__ - Step 82116: {'lr': 0.00021764030764331754, 'samples': 15766272, 'steps': 82115, 'loss/train': 1.0056957006454468} 08/31/2021 04:04:32 - INFO - __main__ - Step 82117: {'lr': 0.00021763504554968987, 'samples': 15766464, 'steps': 82116, 'loss/train': 0.0627484992146492} 08/31/2021 04:04:32 - INFO - __main__ - Step 82118: {'lr': 0.00021762978347064535, 'samples': 15766656, 'steps': 82117, 'loss/train': 1.550263524055481} 08/31/2021 04:04:33 - INFO - __main__ - Step 82119: {'lr': 0.00021762452140618638, 'samples': 15766848, 'steps': 82118, 'loss/train': 1.2896960973739624} 08/31/2021 04:04:34 - INFO - __main__ - Step 82120: {'lr': 0.00021761925935631526, 'samples': 15767040, 'steps': 82119, 'loss/train': 0.84333735704422} 08/31/2021 04:04:35 - INFO - __main__ - Step 82121: {'lr': 0.00021761399732103442, 'samples': 15767232, 'steps': 82120, 'loss/train': 1.0700067281723022} 08/31/2021 04:04:35 - INFO - __main__ - Step 82122: {'lr': 0.0002176087353003462, 'samples': 15767424, 'steps': 82121, 'loss/train': 1.072906255722046} 08/31/2021 04:04:35 - INFO - __main__ - Step 82123: {'lr': 0.00021760347329425302, 'samples': 15767616, 'steps': 82122, 'loss/train': 1.1851954460144043} 08/31/2021 04:04:36 - INFO - __main__ - Step 82124: {'lr': 0.0002175982113027572, 'samples': 15767808, 'steps': 82123, 'loss/train': 1.007064938545227} 08/31/2021 04:04:37 - INFO - __main__ - Step 82125: {'lr': 0.0002175929493258611, 'samples': 15768000, 'steps': 82124, 'loss/train': 1.1432671546936035} 08/31/2021 04:04:38 - INFO - __main__ - Step 82126: {'lr': 0.00021758768736356726, 'samples': 15768192, 'steps': 82125, 'loss/train': 1.1059753894805908} 08/31/2021 04:04:38 - INFO - __main__ - Step 82127: {'lr': 0.00021758242541587778, 'samples': 15768384, 'steps': 82126, 'loss/train': 1.1186871528625488} 08/31/2021 04:04:39 - INFO - __main__ - Step 82128: {'lr': 0.00021757716348279517, 'samples': 15768576, 'steps': 82127, 'loss/train': 1.17215895652771} 08/31/2021 04:04:39 - INFO - __main__ - Step 82129: {'lr': 0.00021757190156432177, 'samples': 15768768, 'steps': 82128, 'loss/train': 1.626833438873291} 08/31/2021 04:04:41 - INFO - __main__ - Step 82130: {'lr': 0.00021756663966045997, 'samples': 15768960, 'steps': 82129, 'loss/train': 1.9726706743240356} 08/31/2021 04:04:41 - INFO - __main__ - Step 82131: {'lr': 0.00021756137777121217, 'samples': 15769152, 'steps': 82130, 'loss/train': 1.0242358446121216} 08/31/2021 04:04:41 - INFO - __main__ - Step 82132: {'lr': 0.0002175561158965807, 'samples': 15769344, 'steps': 82131, 'loss/train': 0.8664902448654175} 08/31/2021 04:04:42 - INFO - __main__ - Step 82133: {'lr': 0.00021755085403656795, 'samples': 15769536, 'steps': 82132, 'loss/train': 0.8886207938194275} 08/31/2021 04:04:42 - INFO - __main__ - Step 82134: {'lr': 0.00021754559219117626, 'samples': 15769728, 'steps': 82133, 'loss/train': 1.726285457611084} 08/31/2021 04:04:43 - INFO - __main__ - Step 82135: {'lr': 0.00021754033036040804, 'samples': 15769920, 'steps': 82134, 'loss/train': 1.7267136573791504} 08/31/2021 04:04:44 - INFO - __main__ - Step 82136: {'lr': 0.00021753506854426562, 'samples': 15770112, 'steps': 82135, 'loss/train': 1.1852761507034302} 08/31/2021 04:04:44 - INFO - __main__ - Step 82137: {'lr': 0.00021752980674275146, 'samples': 15770304, 'steps': 82136, 'loss/train': 0.9496798515319824} 08/31/2021 04:04:45 - INFO - __main__ - Step 82138: {'lr': 0.0002175245449558678, 'samples': 15770496, 'steps': 82137, 'loss/train': 1.5291396379470825} 08/31/2021 04:04:45 - INFO - __main__ - Step 82139: {'lr': 0.00021751928318361724, 'samples': 15770688, 'steps': 82138, 'loss/train': 1.1593199968338013} 08/31/2021 04:04:46 - INFO - __main__ - Step 82140: {'lr': 0.00021751402142600185, 'samples': 15770880, 'steps': 82139, 'loss/train': 1.161133885383606} 08/31/2021 04:04:47 - INFO - __main__ - Step 82141: {'lr': 0.00021750875968302416, 'samples': 15771072, 'steps': 82140, 'loss/train': 1.2836580276489258} 08/31/2021 04:04:47 - INFO - __main__ - Step 82142: {'lr': 0.0002175034979546865, 'samples': 15771264, 'steps': 82141, 'loss/train': 1.2329444885253906} 08/31/2021 04:04:48 - INFO - __main__ - Step 82143: {'lr': 0.0002174982362409913, 'samples': 15771456, 'steps': 82142, 'loss/train': 1.6150649785995483} 08/31/2021 04:04:48 - INFO - __main__ - Step 82144: {'lr': 0.00021749297454194086, 'samples': 15771648, 'steps': 82143, 'loss/train': 1.006542444229126} 08/31/2021 04:04:48 - INFO - __main__ - Step 82145: {'lr': 0.0002174877128575376, 'samples': 15771840, 'steps': 82144, 'loss/train': 0.640092134475708} 08/31/2021 04:04:51 - INFO - __main__ - Step 82146: {'lr': 0.00021748245118778387, 'samples': 15772032, 'steps': 82145, 'loss/train': 0.2320055067539215} 08/31/2021 04:04:51 - INFO - __main__ - Step 82147: {'lr': 0.00021747718953268202, 'samples': 15772224, 'steps': 82146, 'loss/train': 1.174485683441162} 08/31/2021 04:04:52 - INFO - __main__ - Step 82148: {'lr': 0.0002174719278922345, 'samples': 15772416, 'steps': 82147, 'loss/train': 1.1807186603546143} 08/31/2021 04:04:52 - INFO - __main__ - Step 82149: {'lr': 0.00021746666626644358, 'samples': 15772608, 'steps': 82148, 'loss/train': 0.9894577860832214} 08/31/2021 04:04:52 - INFO - __main__ - Step 82150: {'lr': 0.00021746140465531168, 'samples': 15772800, 'steps': 82149, 'loss/train': 0.16748309135437012} 08/31/2021 04:04:54 - INFO - __main__ - Step 82151: {'lr': 0.0002174561430588412, 'samples': 15772992, 'steps': 82150, 'loss/train': 1.3517117500305176} 08/31/2021 04:04:54 - INFO - __main__ - Step 82152: {'lr': 0.00021745088147703457, 'samples': 15773184, 'steps': 82151, 'loss/train': 1.3633593320846558} 08/31/2021 04:04:55 - INFO - __main__ - Step 82153: {'lr': 0.00021744561990989398, 'samples': 15773376, 'steps': 82152, 'loss/train': 1.130657434463501} 08/31/2021 04:04:55 - INFO - __main__ - Step 82154: {'lr': 0.00021744035835742187, 'samples': 15773568, 'steps': 82153, 'loss/train': 0.8907738327980042} 08/31/2021 04:04:55 - INFO - __main__ - Step 82155: {'lr': 0.00021743509681962066, 'samples': 15773760, 'steps': 82154, 'loss/train': 0.4941052794456482} 08/31/2021 04:04:57 - INFO - __main__ - Step 82156: {'lr': 0.00021742983529649264, 'samples': 15773952, 'steps': 82155, 'loss/train': 1.0680066347122192} 08/31/2021 04:04:57 - INFO - __main__ - Step 82157: {'lr': 0.00021742457378804027, 'samples': 15774144, 'steps': 82156, 'loss/train': 0.47741231322288513} 08/31/2021 04:04:58 - INFO - __main__ - Step 82158: {'lr': 0.00021741931229426586, 'samples': 15774336, 'steps': 82157, 'loss/train': 1.266937494277954} 08/31/2021 04:04:58 - INFO - __main__ - Step 82159: {'lr': 0.00021741405081517184, 'samples': 15774528, 'steps': 82158, 'loss/train': 1.601791262626648} 08/31/2021 04:04:58 - INFO - __main__ - Step 82160: {'lr': 0.00021740878935076053, 'samples': 15774720, 'steps': 82159, 'loss/train': 1.1425890922546387} 08/31/2021 04:05:00 - INFO - __main__ - Step 82161: {'lr': 0.00021740352790103432, 'samples': 15774912, 'steps': 82160, 'loss/train': 1.221527099609375} 08/31/2021 04:05:00 - INFO - __main__ - Step 82162: {'lr': 0.00021739826646599558, 'samples': 15775104, 'steps': 82161, 'loss/train': 0.4164866507053375} 08/31/2021 04:05:01 - INFO - __main__ - Step 82163: {'lr': 0.00021739300504564665, 'samples': 15775296, 'steps': 82162, 'loss/train': 1.1261179447174072} 08/31/2021 04:05:01 - INFO - __main__ - Step 82164: {'lr': 0.00021738774363998998, 'samples': 15775488, 'steps': 82163, 'loss/train': 1.4660645723342896} 08/31/2021 04:05:01 - INFO - __main__ - Step 82165: {'lr': 0.00021738248224902783, 'samples': 15775680, 'steps': 82164, 'loss/train': 0.842690646648407} 08/31/2021 04:05:03 - INFO - __main__ - Step 82166: {'lr': 0.0002173772208727628, 'samples': 15775872, 'steps': 82165, 'loss/train': 1.2519237995147705} 08/31/2021 04:05:04 - INFO - __main__ - Step 82167: {'lr': 0.00021737195951119693, 'samples': 15776064, 'steps': 82166, 'loss/train': 1.3584307432174683} 08/31/2021 04:05:04 - INFO - __main__ - Step 82168: {'lr': 0.00021736669816433278, 'samples': 15776256, 'steps': 82167, 'loss/train': 1.042169213294983} 08/31/2021 04:05:04 - INFO - __main__ - Step 82169: {'lr': 0.00021736143683217268, 'samples': 15776448, 'steps': 82168, 'loss/train': 1.4497363567352295} 08/31/2021 04:05:05 - INFO - __main__ - Step 82170: {'lr': 0.00021735617551471903, 'samples': 15776640, 'steps': 82169, 'loss/train': 1.3244175910949707} 08/31/2021 04:05:05 - INFO - __main__ - Step 82171: {'lr': 0.00021735091421197416, 'samples': 15776832, 'steps': 82170, 'loss/train': 0.5798838138580322} 08/31/2021 04:05:07 - INFO - __main__ - Step 82172: {'lr': 0.00021734565292394047, 'samples': 15777024, 'steps': 82171, 'loss/train': 1.0620317459106445} 08/31/2021 04:05:07 - INFO - __main__ - Step 82173: {'lr': 0.00021734039165062033, 'samples': 15777216, 'steps': 82172, 'loss/train': 1.0914965867996216} 08/31/2021 04:05:07 - INFO - __main__ - Step 82174: {'lr': 0.00021733513039201612, 'samples': 15777408, 'steps': 82173, 'loss/train': 1.4426743984222412} 08/31/2021 04:05:08 - INFO - __main__ - Step 82175: {'lr': 0.0002173298691481302, 'samples': 15777600, 'steps': 82174, 'loss/train': 1.510008454322815} 08/31/2021 04:05:08 - INFO - __main__ - Step 82176: {'lr': 0.0002173246079189649, 'samples': 15777792, 'steps': 82175, 'loss/train': 1.578916311264038} 08/31/2021 04:05:10 - INFO - __main__ - Step 82177: {'lr': 0.00021731934670452265, 'samples': 15777984, 'steps': 82176, 'loss/train': 1.0759387016296387} 08/31/2021 04:05:10 - INFO - __main__ - Step 82178: {'lr': 0.00021731408550480576, 'samples': 15778176, 'steps': 82177, 'loss/train': 1.2917590141296387} 08/31/2021 04:05:11 - INFO - __main__ - Step 82179: {'lr': 0.0002173088243198168, 'samples': 15778368, 'steps': 82178, 'loss/train': 1.0843991041183472} 08/31/2021 04:05:11 - INFO - __main__ - Step 82180: {'lr': 0.00021730356314955785, 'samples': 15778560, 'steps': 82179, 'loss/train': 1.4906913042068481} 08/31/2021 04:05:11 - INFO - __main__ - Step 82181: {'lr': 0.00021729830199403142, 'samples': 15778752, 'steps': 82180, 'loss/train': 0.20800426602363586} 08/31/2021 04:05:13 - INFO - __main__ - Step 82182: {'lr': 0.00021729304085323987, 'samples': 15778944, 'steps': 82181, 'loss/train': 1.6426761150360107} 08/31/2021 04:05:13 - INFO - __main__ - Step 82183: {'lr': 0.00021728777972718555, 'samples': 15779136, 'steps': 82182, 'loss/train': 1.3428314924240112} 08/31/2021 04:05:14 - INFO - __main__ - Step 82184: {'lr': 0.00021728251861587085, 'samples': 15779328, 'steps': 82183, 'loss/train': 1.153684377670288} 08/31/2021 04:05:14 - INFO - __main__ - Step 82185: {'lr': 0.00021727725751929816, 'samples': 15779520, 'steps': 82184, 'loss/train': 1.974343180656433} 08/31/2021 04:05:14 - INFO - __main__ - Step 82186: {'lr': 0.00021727199643746986, 'samples': 15779712, 'steps': 82185, 'loss/train': 0.15917931497097015} 08/31/2021 04:05:16 - INFO - __main__ - Step 82187: {'lr': 0.00021726673537038826, 'samples': 15779904, 'steps': 82186, 'loss/train': 0.9462859034538269} 08/31/2021 04:05:16 - INFO - __main__ - Step 82188: {'lr': 0.00021726147431805576, 'samples': 15780096, 'steps': 82187, 'loss/train': 1.3009159564971924} 08/31/2021 04:05:17 - INFO - __main__ - Step 82189: {'lr': 0.00021725621328047472, 'samples': 15780288, 'steps': 82188, 'loss/train': 0.45614421367645264} 08/31/2021 04:05:17 - INFO - __main__ - Step 82190: {'lr': 0.00021725095225764757, 'samples': 15780480, 'steps': 82189, 'loss/train': 0.9824421405792236} 08/31/2021 04:05:17 - INFO - __main__ - Step 82191: {'lr': 0.0002172456912495766, 'samples': 15780672, 'steps': 82190, 'loss/train': 1.2334948778152466} 08/31/2021 04:05:18 - INFO - __main__ - Step 82192: {'lr': 0.00021724043025626424, 'samples': 15780864, 'steps': 82191, 'loss/train': 1.7672030925750732} 08/31/2021 04:05:19 - INFO - __main__ - Step 82193: {'lr': 0.00021723516927771294, 'samples': 15781056, 'steps': 82192, 'loss/train': 1.209227442741394} 08/31/2021 04:05:20 - INFO - __main__ - Step 82194: {'lr': 0.00021722990831392485, 'samples': 15781248, 'steps': 82193, 'loss/train': 1.706403136253357} 08/31/2021 04:05:20 - INFO - __main__ - Step 82195: {'lr': 0.00021722464736490245, 'samples': 15781440, 'steps': 82194, 'loss/train': 1.5125417709350586} 08/31/2021 04:05:21 - INFO - __main__ - Step 82196: {'lr': 0.00021721938643064814, 'samples': 15781632, 'steps': 82195, 'loss/train': 1.318091869354248} 08/31/2021 04:05:21 - INFO - __main__ - Step 82197: {'lr': 0.00021721412551116426, 'samples': 15781824, 'steps': 82196, 'loss/train': 0.10154449194669724} 08/31/2021 04:05:21 - INFO - __main__ - Step 82198: {'lr': 0.00021720886460645318, 'samples': 15782016, 'steps': 82197, 'loss/train': 1.07939875125885} 08/31/2021 04:05:23 - INFO - __main__ - Step 82199: {'lr': 0.0002172036037165173, 'samples': 15782208, 'steps': 82198, 'loss/train': 0.6389252543449402} 08/31/2021 04:05:24 - INFO - __main__ - Step 82200: {'lr': 0.00021719834284135894, 'samples': 15782400, 'steps': 82199, 'loss/train': 1.4057313203811646} 08/31/2021 04:05:24 - INFO - __main__ - Step 82201: {'lr': 0.00021719308198098054, 'samples': 15782592, 'steps': 82200, 'loss/train': 0.8447322249412537} 08/31/2021 04:05:24 - INFO - __main__ - Step 82202: {'lr': 0.00021718782113538438, 'samples': 15782784, 'steps': 82201, 'loss/train': 1.5266927480697632} 08/31/2021 04:05:25 - INFO - __main__ - Step 82203: {'lr': 0.00021718256030457293, 'samples': 15782976, 'steps': 82202, 'loss/train': 0.5534607768058777} 08/31/2021 04:05:26 - INFO - __main__ - Step 82204: {'lr': 0.00021717729948854847, 'samples': 15783168, 'steps': 82203, 'loss/train': 1.2585721015930176} 08/31/2021 04:05:27 - INFO - __main__ - Step 82205: {'lr': 0.00021717203868731346, 'samples': 15783360, 'steps': 82204, 'loss/train': 1.235781192779541} 08/31/2021 04:05:27 - INFO - __main__ - Step 82206: {'lr': 0.0002171667779008703, 'samples': 15783552, 'steps': 82205, 'loss/train': 0.9409655928611755} 08/31/2021 04:05:27 - INFO - __main__ - Step 82207: {'lr': 0.00021716151712922118, 'samples': 15783744, 'steps': 82206, 'loss/train': 1.5540978908538818} 08/31/2021 04:05:28 - INFO - __main__ - Step 82208: {'lr': 0.00021715625637236857, 'samples': 15783936, 'steps': 82207, 'loss/train': 1.2278072834014893} 08/31/2021 04:05:29 - INFO - __main__ - Step 82209: {'lr': 0.00021715099563031484, 'samples': 15784128, 'steps': 82208, 'loss/train': 0.05688420310616493} 08/31/2021 04:05:30 - INFO - __main__ - Step 82210: {'lr': 0.0002171457349030624, 'samples': 15784320, 'steps': 82209, 'loss/train': 1.3346481323242188} 08/31/2021 04:05:30 - INFO - __main__ - Step 82211: {'lr': 0.00021714047419061353, 'samples': 15784512, 'steps': 82210, 'loss/train': 1.3890591859817505} 08/31/2021 04:05:30 - INFO - __main__ - Step 82212: {'lr': 0.0002171352134929707, 'samples': 15784704, 'steps': 82211, 'loss/train': 1.381849765777588} 08/31/2021 04:05:31 - INFO - __main__ - Step 82213: {'lr': 0.0002171299528101362, 'samples': 15784896, 'steps': 82212, 'loss/train': 0.910905122756958} 08/31/2021 04:05:32 - INFO - __main__ - Step 82214: {'lr': 0.00021712469214211244, 'samples': 15785088, 'steps': 82213, 'loss/train': 4.238159656524658} 08/31/2021 04:05:33 - INFO - __main__ - Step 82215: {'lr': 0.0002171194314889018, 'samples': 15785280, 'steps': 82214, 'loss/train': 1.102882742881775} 08/31/2021 04:05:33 - INFO - __main__ - Step 82216: {'lr': 0.00021711417085050667, 'samples': 15785472, 'steps': 82215, 'loss/train': 0.4114207327365875} 08/31/2021 04:05:33 - INFO - __main__ - Step 82217: {'lr': 0.00021710891022692937, 'samples': 15785664, 'steps': 82216, 'loss/train': 1.2625112533569336} 08/31/2021 04:05:34 - INFO - __main__ - Step 82218: {'lr': 0.0002171036496181723, 'samples': 15785856, 'steps': 82217, 'loss/train': 0.615330159664154} 08/31/2021 04:05:35 - INFO - __main__ - Step 82219: {'lr': 0.00021709838902423778, 'samples': 15786048, 'steps': 82218, 'loss/train': 1.442043423652649} 08/31/2021 04:05:36 - INFO - __main__ - Step 82220: {'lr': 0.0002170931284451283, 'samples': 15786240, 'steps': 82219, 'loss/train': 1.7656753063201904} 08/31/2021 04:05:36 - INFO - __main__ - Step 82221: {'lr': 0.00021708786788084605, 'samples': 15786432, 'steps': 82220, 'loss/train': 1.4740679264068604} 08/31/2021 04:05:36 - INFO - __main__ - Step 82222: {'lr': 0.00021708260733139354, 'samples': 15786624, 'steps': 82221, 'loss/train': 1.3324174880981445} 08/31/2021 04:05:37 - INFO - __main__ - Step 82223: {'lr': 0.00021707734679677308, 'samples': 15786816, 'steps': 82222, 'loss/train': 0.8738778829574585} 08/31/2021 04:05:38 - INFO - __main__ - Step 82224: {'lr': 0.00021707208627698709, 'samples': 15787008, 'steps': 82223, 'loss/train': 0.11161868274211884} 08/31/2021 04:05:39 - INFO - __main__ - Step 82225: {'lr': 0.00021706682577203785, 'samples': 15787200, 'steps': 82224, 'loss/train': 0.6342440247535706} 08/31/2021 04:05:39 - INFO - __main__ - Step 82226: {'lr': 0.00021706156528192782, 'samples': 15787392, 'steps': 82225, 'loss/train': 1.3999696969985962} 08/31/2021 04:05:39 - INFO - __main__ - Step 82227: {'lr': 0.00021705630480665935, 'samples': 15787584, 'steps': 82226, 'loss/train': 1.2946267127990723} 08/31/2021 04:05:40 - INFO - __main__ - Step 82228: {'lr': 0.00021705104434623486, 'samples': 15787776, 'steps': 82227, 'loss/train': 1.043308138847351} 08/31/2021 04:05:40 - INFO - __main__ - Step 82229: {'lr': 0.0002170457839006566, 'samples': 15787968, 'steps': 82228, 'loss/train': 0.057357307523489} 08/31/2021 04:05:42 - INFO - __main__ - Step 82230: {'lr': 0.000217040523469927, 'samples': 15788160, 'steps': 82229, 'loss/train': 0.1279166042804718} 08/31/2021 04:05:42 - INFO - __main__ - Step 82231: {'lr': 0.0002170352630540484, 'samples': 15788352, 'steps': 82230, 'loss/train': 1.0517706871032715} 08/31/2021 04:05:42 - INFO - __main__ - Step 82232: {'lr': 0.00021703000265302326, 'samples': 15788544, 'steps': 82231, 'loss/train': 1.6006797552108765} 08/31/2021 04:05:43 - INFO - __main__ - Step 82233: {'lr': 0.0002170247422668539, 'samples': 15788736, 'steps': 82232, 'loss/train': 1.2974497079849243} 08/31/2021 04:05:43 - INFO - __main__ - Step 82234: {'lr': 0.00021701948189554267, 'samples': 15788928, 'steps': 82233, 'loss/train': 1.2761882543563843} 08/31/2021 04:05:45 - INFO - __main__ - Step 82235: {'lr': 0.0002170142215390919, 'samples': 15789120, 'steps': 82234, 'loss/train': 1.6523985862731934} 08/31/2021 04:05:45 - INFO - __main__ - Step 82236: {'lr': 0.00021700896119750406, 'samples': 15789312, 'steps': 82235, 'loss/train': 0.048531610518693924} 08/31/2021 04:05:45 - INFO - __main__ - Step 82237: {'lr': 0.00021700370087078145, 'samples': 15789504, 'steps': 82236, 'loss/train': 1.2714588642120361} 08/31/2021 04:05:46 - INFO - __main__ - Step 82238: {'lr': 0.00021699844055892646, 'samples': 15789696, 'steps': 82237, 'loss/train': 1.5542402267456055} 08/31/2021 04:05:46 - INFO - __main__ - Step 82239: {'lr': 0.00021699318026194154, 'samples': 15789888, 'steps': 82238, 'loss/train': 1.1158530712127686} 08/31/2021 04:05:48 - INFO - __main__ - Step 82240: {'lr': 0.0002169879199798289, 'samples': 15790080, 'steps': 82239, 'loss/train': 1.0667634010314941} 08/31/2021 04:05:48 - INFO - __main__ - Step 82241: {'lr': 0.000216982659712591, 'samples': 15790272, 'steps': 82240, 'loss/train': 1.1117051839828491} 08/31/2021 04:05:49 - INFO - __main__ - Step 82242: {'lr': 0.0002169773994602302, 'samples': 15790464, 'steps': 82241, 'loss/train': 1.2030911445617676} 08/31/2021 04:05:49 - INFO - __main__ - Step 82243: {'lr': 0.0002169721392227489, 'samples': 15790656, 'steps': 82242, 'loss/train': 1.1555010080337524} 08/31/2021 04:05:50 - INFO - __main__ - Step 82244: {'lr': 0.00021696687900014944, 'samples': 15790848, 'steps': 82243, 'loss/train': 0.0963398665189743} 08/31/2021 04:05:51 - INFO - __main__ - Step 82245: {'lr': 0.00021696161879243417, 'samples': 15791040, 'steps': 82244, 'loss/train': 0.698992133140564} 08/31/2021 04:05:51 - INFO - __main__ - Step 82246: {'lr': 0.0002169563585996055, 'samples': 15791232, 'steps': 82245, 'loss/train': 0.9884874224662781} 08/31/2021 04:05:52 - INFO - __main__ - Step 82247: {'lr': 0.0002169510984216658, 'samples': 15791424, 'steps': 82246, 'loss/train': 1.5920839309692383} 08/31/2021 04:05:52 - INFO - __main__ - Step 82248: {'lr': 0.00021694583825861743, 'samples': 15791616, 'steps': 82247, 'loss/train': 1.4425407648086548} 08/31/2021 04:05:52 - INFO - __main__ - Step 82249: {'lr': 0.00021694057811046276, 'samples': 15791808, 'steps': 82248, 'loss/train': 1.4943385124206543} 08/31/2021 04:05:55 - INFO - __main__ - Step 82250: {'lr': 0.00021693531797720416, 'samples': 15792000, 'steps': 82249, 'loss/train': 1.2104244232177734} 08/31/2021 04:05:55 - INFO - __main__ - Step 82251: {'lr': 0.000216930057858844, 'samples': 15792192, 'steps': 82250, 'loss/train': 1.161704421043396} 08/31/2021 04:05:55 - INFO - __main__ - Step 82252: {'lr': 0.0002169247977553846, 'samples': 15792384, 'steps': 82251, 'loss/train': 1.5301897525787354} 08/31/2021 04:05:56 - INFO - __main__ - Step 82253: {'lr': 0.00021691953766682837, 'samples': 15792576, 'steps': 82252, 'loss/train': 1.0293265581130981} 08/31/2021 04:05:56 - INFO - __main__ - Step 82254: {'lr': 0.0002169142775931777, 'samples': 15792768, 'steps': 82253, 'loss/train': 1.0124140977859497} 08/31/2021 04:05:56 - INFO - __main__ - Step 82255: {'lr': 0.00021690901753443494, 'samples': 15792960, 'steps': 82254, 'loss/train': 0.8499459028244019} 08/31/2021 04:05:58 - INFO - __main__ - Step 82256: {'lr': 0.00021690375749060248, 'samples': 15793152, 'steps': 82255, 'loss/train': 0.9643071293830872} 08/31/2021 04:05:59 - INFO - __main__ - Step 82257: {'lr': 0.0002168984974616827, 'samples': 15793344, 'steps': 82256, 'loss/train': 1.248154878616333} 08/31/2021 04:05:59 - INFO - __main__ - Step 82258: {'lr': 0.0002168932374476779, 'samples': 15793536, 'steps': 82257, 'loss/train': 1.7172704935073853} 08/31/2021 04:05:59 - INFO - __main__ - Step 82259: {'lr': 0.00021688797744859052, 'samples': 15793728, 'steps': 82258, 'loss/train': 0.6780146956443787} 08/31/2021 04:06:00 - INFO - __main__ - Step 82260: {'lr': 0.00021688271746442294, 'samples': 15793920, 'steps': 82259, 'loss/train': 1.471394419670105} 08/31/2021 04:06:01 - INFO - __main__ - Step 82261: {'lr': 0.00021687745749517751, 'samples': 15794112, 'steps': 82260, 'loss/train': 1.0487407445907593} 08/31/2021 04:06:02 - INFO - __main__ - Step 82262: {'lr': 0.00021687219754085654, 'samples': 15794304, 'steps': 82261, 'loss/train': 0.9366028904914856} 08/31/2021 04:06:02 - INFO - __main__ - Step 82263: {'lr': 0.00021686693760146245, 'samples': 15794496, 'steps': 82262, 'loss/train': 0.48861488699913025} 08/31/2021 04:06:02 - INFO - __main__ - Step 82264: {'lr': 0.0002168616776769976, 'samples': 15794688, 'steps': 82263, 'loss/train': 1.0960373878479004} 08/31/2021 04:06:03 - INFO - __main__ - Step 82265: {'lr': 0.00021685641776746434, 'samples': 15794880, 'steps': 82264, 'loss/train': 1.073081135749817} 08/31/2021 04:06:04 - INFO - __main__ - Step 82266: {'lr': 0.00021685115787286512, 'samples': 15795072, 'steps': 82265, 'loss/train': 0.9321628212928772} 08/31/2021 04:06:04 - INFO - __main__ - Step 82267: {'lr': 0.0002168458979932022, 'samples': 15795264, 'steps': 82266, 'loss/train': 1.1688134670257568} 08/31/2021 04:06:05 - INFO - __main__ - Step 82268: {'lr': 0.00021684063812847803, 'samples': 15795456, 'steps': 82267, 'loss/train': 0.17404623329639435} 08/31/2021 04:06:05 - INFO - __main__ - Step 82269: {'lr': 0.00021683537827869498, 'samples': 15795648, 'steps': 82268, 'loss/train': 1.7947496175765991} 08/31/2021 04:06:06 - INFO - __main__ - Step 82270: {'lr': 0.00021683011844385536, 'samples': 15795840, 'steps': 82269, 'loss/train': 1.3855881690979004} 08/31/2021 04:06:07 - INFO - __main__ - Step 82271: {'lr': 0.00021682485862396163, 'samples': 15796032, 'steps': 82270, 'loss/train': 1.267892837524414} 08/31/2021 04:06:08 - INFO - __main__ - Step 82272: {'lr': 0.00021681959881901603, 'samples': 15796224, 'steps': 82271, 'loss/train': 1.3182753324508667} 08/31/2021 04:06:08 - INFO - __main__ - Step 82273: {'lr': 0.00021681433902902118, 'samples': 15796416, 'steps': 82272, 'loss/train': 1.3130877017974854} 08/31/2021 04:06:09 - INFO - __main__ - Step 82274: {'lr': 0.00021680907925397913, 'samples': 15796608, 'steps': 82273, 'loss/train': 1.0896456241607666} 08/31/2021 04:06:09 - INFO - __main__ - Step 82275: {'lr': 0.0002168038194938924, 'samples': 15796800, 'steps': 82274, 'loss/train': 0.9216708540916443} 08/31/2021 04:06:11 - INFO - __main__ - Step 82276: {'lr': 0.00021679855974876338, 'samples': 15796992, 'steps': 82275, 'loss/train': 1.665792465209961} 08/31/2021 04:06:11 - INFO - __main__ - Step 82277: {'lr': 0.0002167933000185944, 'samples': 15797184, 'steps': 82276, 'loss/train': 1.3081371784210205} 08/31/2021 04:06:11 - INFO - __main__ - Step 82278: {'lr': 0.00021678804030338786, 'samples': 15797376, 'steps': 82277, 'loss/train': 1.2196016311645508} 08/31/2021 04:06:12 - INFO - __main__ - Step 82279: {'lr': 0.0002167827806031461, 'samples': 15797568, 'steps': 82278, 'loss/train': 1.426082730293274} 08/31/2021 04:06:12 - INFO - __main__ - Step 82280: {'lr': 0.0002167775209178715, 'samples': 15797760, 'steps': 82279, 'loss/train': 0.07107029110193253} 08/31/2021 04:06:14 - INFO - __main__ - Step 82281: {'lr': 0.00021677226124756647, 'samples': 15797952, 'steps': 82280, 'loss/train': 0.14785543084144592} 08/31/2021 04:06:14 - INFO - __main__ - Step 82282: {'lr': 0.0002167670015922333, 'samples': 15798144, 'steps': 82281, 'loss/train': 1.262171745300293} 08/31/2021 04:06:15 - INFO - __main__ - Step 82283: {'lr': 0.00021676174195187444, 'samples': 15798336, 'steps': 82282, 'loss/train': 1.0789508819580078} 08/31/2021 04:06:15 - INFO - __main__ - Step 82284: {'lr': 0.00021675648232649222, 'samples': 15798528, 'steps': 82283, 'loss/train': 1.4479154348373413} 08/31/2021 04:06:15 - INFO - __main__ - Step 82285: {'lr': 0.00021675122271608903, 'samples': 15798720, 'steps': 82284, 'loss/train': 1.164634346961975} 08/31/2021 04:06:16 - INFO - __main__ - Step 82286: {'lr': 0.0002167459631206672, 'samples': 15798912, 'steps': 82285, 'loss/train': 0.5686583518981934} 08/31/2021 04:06:17 - INFO - __main__ - Step 82287: {'lr': 0.00021674070354022926, 'samples': 15799104, 'steps': 82286, 'loss/train': 1.823250412940979} 08/31/2021 04:06:18 - INFO - __main__ - Step 82288: {'lr': 0.00021673544397477732, 'samples': 15799296, 'steps': 82287, 'loss/train': 0.9238502383232117} 08/31/2021 04:06:18 - INFO - __main__ - Step 82289: {'lr': 0.00021673018442431387, 'samples': 15799488, 'steps': 82288, 'loss/train': 1.7587159872055054} 08/31/2021 04:06:18 - INFO - __main__ - Step 82290: {'lr': 0.0002167249248888413, 'samples': 15799680, 'steps': 82289, 'loss/train': 1.0925687551498413} 08/31/2021 04:06:19 - INFO - __main__ - Step 82291: {'lr': 0.00021671966536836195, 'samples': 15799872, 'steps': 82290, 'loss/train': 1.4730819463729858} 08/31/2021 04:06:20 - INFO - __main__ - Step 82292: {'lr': 0.00021671440586287823, 'samples': 15800064, 'steps': 82291, 'loss/train': 1.7919416427612305} 08/31/2021 04:06:21 - INFO - __main__ - Step 82293: {'lr': 0.00021670914637239244, 'samples': 15800256, 'steps': 82292, 'loss/train': 1.1706159114837646} 08/31/2021 04:06:21 - INFO - __main__ - Step 82294: {'lr': 0.00021670388689690705, 'samples': 15800448, 'steps': 82293, 'loss/train': 1.2164291143417358} 08/31/2021 04:06:21 - INFO - __main__ - Step 82295: {'lr': 0.00021669862743642433, 'samples': 15800640, 'steps': 82294, 'loss/train': 1.4012548923492432} 08/31/2021 04:06:22 - INFO - __main__ - Step 82296: {'lr': 0.00021669336799094672, 'samples': 15800832, 'steps': 82295, 'loss/train': 1.3190776109695435} 08/31/2021 04:06:22 - INFO - __main__ - Step 82297: {'lr': 0.00021668810856047654, 'samples': 15801024, 'steps': 82296, 'loss/train': 1.1550109386444092} 08/31/2021 04:06:24 - INFO - __main__ - Step 82298: {'lr': 0.00021668284914501623, 'samples': 15801216, 'steps': 82297, 'loss/train': 1.520721435546875} 08/31/2021 04:06:24 - INFO - __main__ - Step 82299: {'lr': 0.0002166775897445681, 'samples': 15801408, 'steps': 82298, 'loss/train': 1.200711727142334} 08/31/2021 04:06:25 - INFO - __main__ - Step 82300: {'lr': 0.0002166723303591346, 'samples': 15801600, 'steps': 82299, 'loss/train': 1.2413057088851929} 08/31/2021 04:06:25 - INFO - __main__ - Step 82301: {'lr': 0.00021666707098871797, 'samples': 15801792, 'steps': 82300, 'loss/train': 1.4296108484268188} 08/31/2021 04:06:25 - INFO - __main__ - Step 82302: {'lr': 0.0002166618116333206, 'samples': 15801984, 'steps': 82301, 'loss/train': 1.3165229558944702} 08/31/2021 04:06:27 - INFO - __main__ - Step 82303: {'lr': 0.00021665655229294496, 'samples': 15802176, 'steps': 82302, 'loss/train': 2.8330864906311035} 08/31/2021 04:06:28 - INFO - __main__ - Step 82304: {'lr': 0.00021665129296759335, 'samples': 15802368, 'steps': 82303, 'loss/train': 1.4434829950332642} 08/31/2021 04:06:28 - INFO - __main__ - Step 82305: {'lr': 0.0002166460336572681, 'samples': 15802560, 'steps': 82304, 'loss/train': 0.25075629353523254} 08/31/2021 04:06:29 - INFO - __main__ - Step 82306: {'lr': 0.0002166407743619717, 'samples': 15802752, 'steps': 82305, 'loss/train': 1.5969702005386353} 08/31/2021 04:06:29 - INFO - __main__ - Step 82307: {'lr': 0.0002166355150817064, 'samples': 15802944, 'steps': 82306, 'loss/train': 1.0033471584320068} 08/31/2021 04:06:30 - INFO - __main__ - Step 82308: {'lr': 0.00021663025581647463, 'samples': 15803136, 'steps': 82307, 'loss/train': 1.260888695716858} 08/31/2021 04:06:31 - INFO - __main__ - Step 82309: {'lr': 0.00021662499656627878, 'samples': 15803328, 'steps': 82308, 'loss/train': 1.077850580215454} 08/31/2021 04:06:31 - INFO - __main__ - Step 82310: {'lr': 0.00021661973733112116, 'samples': 15803520, 'steps': 82309, 'loss/train': 0.6576191186904907} 08/31/2021 04:06:31 - INFO - __main__ - Step 82311: {'lr': 0.00021661447811100422, 'samples': 15803712, 'steps': 82310, 'loss/train': 1.316928744316101} 08/31/2021 04:06:32 - INFO - __main__ - Step 82312: {'lr': 0.0002166092189059302, 'samples': 15803904, 'steps': 82311, 'loss/train': 1.6946488618850708} 08/31/2021 04:06:33 - INFO - __main__ - Step 82313: {'lr': 0.00021660395971590164, 'samples': 15804096, 'steps': 82312, 'loss/train': 1.5200941562652588} 08/31/2021 04:06:34 - INFO - __main__ - Step 82314: {'lr': 0.00021659870054092087, 'samples': 15804288, 'steps': 82313, 'loss/train': 1.3788707256317139} 08/31/2021 04:06:34 - INFO - __main__ - Step 82315: {'lr': 0.00021659344138099014, 'samples': 15804480, 'steps': 82314, 'loss/train': 0.8133255839347839} 08/31/2021 04:06:35 - INFO - __main__ - Step 82316: {'lr': 0.00021658818223611184, 'samples': 15804672, 'steps': 82315, 'loss/train': 1.8512762784957886} 08/31/2021 04:06:35 - INFO - __main__ - Step 82317: {'lr': 0.00021658292310628842, 'samples': 15804864, 'steps': 82316, 'loss/train': 1.5601089000701904} 08/31/2021 04:06:37 - INFO - __main__ - Step 82318: {'lr': 0.00021657766399152224, 'samples': 15805056, 'steps': 82317, 'loss/train': 0.05670005828142166} 08/31/2021 04:06:37 - INFO - __main__ - Step 82319: {'lr': 0.00021657240489181563, 'samples': 15805248, 'steps': 82318, 'loss/train': 1.2652326822280884} 08/31/2021 04:06:37 - INFO - __main__ - Step 82320: {'lr': 0.00021656714580717097, 'samples': 15805440, 'steps': 82319, 'loss/train': 1.4410815238952637} 08/31/2021 04:06:38 - INFO - __main__ - Step 82321: {'lr': 0.00021656188673759065, 'samples': 15805632, 'steps': 82320, 'loss/train': 0.6778865456581116} 08/31/2021 04:06:38 - INFO - __main__ - Step 82322: {'lr': 0.00021655662768307703, 'samples': 15805824, 'steps': 82321, 'loss/train': 0.890548050403595} 08/31/2021 04:06:40 - INFO - __main__ - Step 82323: {'lr': 0.00021655136864363246, 'samples': 15806016, 'steps': 82322, 'loss/train': 1.9829295873641968} 08/31/2021 04:06:40 - INFO - __main__ - Step 82324: {'lr': 0.00021654610961925933, 'samples': 15806208, 'steps': 82323, 'loss/train': 1.4505133628845215} 08/31/2021 04:06:41 - INFO - __main__ - Step 82325: {'lr': 0.00021654085060996, 'samples': 15806400, 'steps': 82324, 'loss/train': 1.4861825704574585} 08/31/2021 04:06:41 - INFO - __main__ - Step 82326: {'lr': 0.00021653559161573688, 'samples': 15806592, 'steps': 82325, 'loss/train': 0.7655500769615173} 08/31/2021 04:06:41 - INFO - __main__ - Step 82327: {'lr': 0.00021653033263659239, 'samples': 15806784, 'steps': 82326, 'loss/train': 1.2995572090148926} 08/31/2021 04:06:42 - INFO - __main__ - Step 82328: {'lr': 0.0002165250736725287, 'samples': 15806976, 'steps': 82327, 'loss/train': 1.6796927452087402} 08/31/2021 04:06:43 - INFO - __main__ - Step 82329: {'lr': 0.00021651981472354832, 'samples': 15807168, 'steps': 82328, 'loss/train': 1.2798384428024292} 08/31/2021 04:06:44 - INFO - __main__ - Step 82330: {'lr': 0.00021651455578965357, 'samples': 15807360, 'steps': 82329, 'loss/train': 0.9844555854797363} 08/31/2021 04:06:44 - INFO - __main__ - Step 82331: {'lr': 0.00021650929687084687, 'samples': 15807552, 'steps': 82330, 'loss/train': 1.6579365730285645} 08/31/2021 04:06:44 - INFO - __main__ - Step 82332: {'lr': 0.00021650403796713054, 'samples': 15807744, 'steps': 82331, 'loss/train': 1.3709553480148315} 08/31/2021 04:06:46 - INFO - __main__ - Step 82333: {'lr': 0.00021649877907850697, 'samples': 15807936, 'steps': 82332, 'loss/train': 1.7191821336746216} 08/31/2021 04:06:46 - INFO - __main__ - Step 82334: {'lr': 0.00021649352020497857, 'samples': 15808128, 'steps': 82333, 'loss/train': 1.1765811443328857} 08/31/2021 04:06:47 - INFO - __main__ - Step 82335: {'lr': 0.00021648826134654765, 'samples': 15808320, 'steps': 82334, 'loss/train': 1.2547471523284912} 08/31/2021 04:06:47 - INFO - __main__ - Step 82336: {'lr': 0.00021648300250321658, 'samples': 15808512, 'steps': 82335, 'loss/train': 1.1205337047576904} 08/31/2021 04:06:47 - INFO - __main__ - Step 82337: {'lr': 0.0002164777436749878, 'samples': 15808704, 'steps': 82336, 'loss/train': 1.143615484237671} 08/31/2021 04:06:48 - INFO - __main__ - Step 82338: {'lr': 0.0002164724848618636, 'samples': 15808896, 'steps': 82337, 'loss/train': 0.5972062945365906} 08/31/2021 04:06:49 - INFO - __main__ - Step 82339: {'lr': 0.00021646722606384638, 'samples': 15809088, 'steps': 82338, 'loss/train': 2.3573031425476074} 08/31/2021 04:06:50 - INFO - __main__ - Step 82340: {'lr': 0.00021646196728093852, 'samples': 15809280, 'steps': 82339, 'loss/train': 1.2258027791976929} 08/31/2021 04:06:50 - INFO - __main__ - Step 82341: {'lr': 0.00021645670851314249, 'samples': 15809472, 'steps': 82340, 'loss/train': 1.0826090574264526} 08/31/2021 04:06:50 - INFO - __main__ - Step 82342: {'lr': 0.00021645144976046045, 'samples': 15809664, 'steps': 82341, 'loss/train': 0.987231433391571} 08/31/2021 04:06:51 - INFO - __main__ - Step 82343: {'lr': 0.00021644619102289484, 'samples': 15809856, 'steps': 82342, 'loss/train': 1.2227827310562134} 08/31/2021 04:06:52 - INFO - __main__ - Step 82344: {'lr': 0.00021644093230044806, 'samples': 15810048, 'steps': 82343, 'loss/train': 0.8287492394447327} 08/31/2021 04:06:53 - INFO - __main__ - Step 82345: {'lr': 0.0002164356735931225, 'samples': 15810240, 'steps': 82344, 'loss/train': 0.8358079791069031} 08/31/2021 04:06:53 - INFO - __main__ - Step 82346: {'lr': 0.0002164304149009205, 'samples': 15810432, 'steps': 82345, 'loss/train': 0.7987075448036194} 08/31/2021 04:06:53 - INFO - __main__ - Step 82347: {'lr': 0.00021642515622384442, 'samples': 15810624, 'steps': 82346, 'loss/train': 1.190276026725769} 08/31/2021 04:06:54 - INFO - __main__ - Step 82348: {'lr': 0.00021641989756189666, 'samples': 15810816, 'steps': 82347, 'loss/train': 0.21969585120677948} 08/31/2021 04:06:56 - INFO - __main__ - Step 82349: {'lr': 0.0002164146389150796, 'samples': 15811008, 'steps': 82348, 'loss/train': 1.4142924547195435} 08/31/2021 04:06:56 - INFO - __main__ - Step 82350: {'lr': 0.00021640938028339557, 'samples': 15811200, 'steps': 82349, 'loss/train': 1.0910016298294067} 08/31/2021 04:06:56 - INFO - __main__ - Step 82351: {'lr': 0.00021640412166684694, 'samples': 15811392, 'steps': 82350, 'loss/train': 0.6667269468307495} 08/31/2021 04:06:57 - INFO - __main__ - Step 82352: {'lr': 0.00021639886306543615, 'samples': 15811584, 'steps': 82351, 'loss/train': 1.270593285560608} 08/31/2021 04:06:57 - INFO - __main__ - Step 82353: {'lr': 0.00021639360447916548, 'samples': 15811776, 'steps': 82352, 'loss/train': 0.8184831738471985} 08/31/2021 04:06:58 - INFO - __main__ - Step 82354: {'lr': 0.00021638834590803738, 'samples': 15811968, 'steps': 82353, 'loss/train': 1.2664299011230469} 08/31/2021 04:06:59 - INFO - __main__ - Step 82355: {'lr': 0.00021638308735205412, 'samples': 15812160, 'steps': 82354, 'loss/train': 0.02197415940463543} 08/31/2021 04:07:00 - INFO - __main__ - Step 82356: {'lr': 0.00021637782881121808, 'samples': 15812352, 'steps': 82355, 'loss/train': 0.5115124583244324} 08/31/2021 04:07:00 - INFO - __main__ - Step 82357: {'lr': 0.00021637257028553174, 'samples': 15812544, 'steps': 82356, 'loss/train': 1.0092114210128784} 08/31/2021 04:07:00 - INFO - __main__ - Step 82358: {'lr': 0.00021636731177499736, 'samples': 15812736, 'steps': 82357, 'loss/train': 1.499934434890747} 08/31/2021 04:07:01 - INFO - __main__ - Step 82359: {'lr': 0.00021636205327961737, 'samples': 15812928, 'steps': 82358, 'loss/train': 1.1267553567886353} 08/31/2021 04:07:03 - INFO - __main__ - Step 82360: {'lr': 0.0002163567947993941, 'samples': 15813120, 'steps': 82359, 'loss/train': 2.278092861175537} 08/31/2021 04:07:03 - INFO - __main__ - Step 82361: {'lr': 0.00021635153633432994, 'samples': 15813312, 'steps': 82360, 'loss/train': 0.9283990263938904} 08/31/2021 04:07:04 - INFO - __main__ - Step 82362: {'lr': 0.00021634627788442732, 'samples': 15813504, 'steps': 82361, 'loss/train': 1.1293275356292725} 08/31/2021 04:07:04 - INFO - __main__ - Step 82363: {'lr': 0.0002163410194496885, 'samples': 15813696, 'steps': 82362, 'loss/train': 0.03716028481721878} 08/31/2021 04:07:05 - INFO - __main__ - Step 82364: {'lr': 0.0002163357610301159, 'samples': 15813888, 'steps': 82363, 'loss/train': 0.0207970067858696} 08/31/2021 04:07:05 - INFO - __main__ - Step 82365: {'lr': 0.00021633050262571187, 'samples': 15814080, 'steps': 82364, 'loss/train': 0.5778903365135193} 08/31/2021 04:07:06 - INFO - __main__ - Step 82366: {'lr': 0.0002163252442364788, 'samples': 15814272, 'steps': 82365, 'loss/train': 0.48282164335250854} 08/31/2021 04:07:07 - INFO - __main__ - Step 82367: {'lr': 0.00021631998586241904, 'samples': 15814464, 'steps': 82366, 'loss/train': 1.2746707201004028} 08/31/2021 04:07:07 - INFO - __main__ - Step 82368: {'lr': 0.00021631472750353506, 'samples': 15814656, 'steps': 82367, 'loss/train': 1.538712501525879} 08/31/2021 04:07:08 - INFO - __main__ - Step 82369: {'lr': 0.00021630946915982907, 'samples': 15814848, 'steps': 82368, 'loss/train': 0.047921571880578995} 08/31/2021 04:07:08 - INFO - __main__ - Step 82370: {'lr': 0.00021630421083130351, 'samples': 15815040, 'steps': 82369, 'loss/train': 1.3416800498962402} 08/31/2021 04:07:09 - INFO - __main__ - Step 82371: {'lr': 0.00021629895251796077, 'samples': 15815232, 'steps': 82370, 'loss/train': 1.0982192754745483} 08/31/2021 04:07:10 - INFO - __main__ - Step 82372: {'lr': 0.00021629369421980322, 'samples': 15815424, 'steps': 82371, 'loss/train': 1.3083643913269043} 08/31/2021 04:07:10 - INFO - __main__ - Step 82373: {'lr': 0.00021628843593683324, 'samples': 15815616, 'steps': 82372, 'loss/train': 1.181313157081604} 08/31/2021 04:07:11 - INFO - __main__ - Step 82374: {'lr': 0.0002162831776690531, 'samples': 15815808, 'steps': 82373, 'loss/train': 1.4117811918258667} 08/31/2021 04:07:11 - INFO - __main__ - Step 82375: {'lr': 0.00021627791941646526, 'samples': 15816000, 'steps': 82374, 'loss/train': 1.0780091285705566} 08/31/2021 04:07:12 - INFO - __main__ - Step 82376: {'lr': 0.00021627266117907207, 'samples': 15816192, 'steps': 82375, 'loss/train': 1.2255045175552368} 08/31/2021 04:07:13 - INFO - __main__ - Step 82377: {'lr': 0.0002162674029568759, 'samples': 15816384, 'steps': 82376, 'loss/train': 1.504178524017334} 08/31/2021 04:07:13 - INFO - __main__ - Step 82378: {'lr': 0.0002162621447498791, 'samples': 15816576, 'steps': 82377, 'loss/train': 1.153205156326294} 08/31/2021 04:07:14 - INFO - __main__ - Step 82379: {'lr': 0.00021625688655808406, 'samples': 15816768, 'steps': 82378, 'loss/train': 0.8427334427833557} 08/31/2021 04:07:14 - INFO - __main__ - Step 82380: {'lr': 0.00021625162838149317, 'samples': 15816960, 'steps': 82379, 'loss/train': 1.3966116905212402} 08/31/2021 04:07:16 - INFO - __main__ - Step 82381: {'lr': 0.00021624637022010882, 'samples': 15817152, 'steps': 82380, 'loss/train': 1.6294419765472412} 08/31/2021 04:07:16 - INFO - __main__ - Step 82382: {'lr': 0.00021624111207393327, 'samples': 15817344, 'steps': 82381, 'loss/train': 0.019384324550628662} 08/31/2021 04:07:16 - INFO - __main__ - Step 82383: {'lr': 0.00021623585394296897, 'samples': 15817536, 'steps': 82382, 'loss/train': 0.017416464164853096} 08/31/2021 04:07:17 - INFO - __main__ - Step 82384: {'lr': 0.00021623059582721833, 'samples': 15817728, 'steps': 82383, 'loss/train': 0.036746133118867874} 08/31/2021 04:07:17 - INFO - __main__ - Step 82385: {'lr': 0.00021622533772668357, 'samples': 15817920, 'steps': 82384, 'loss/train': 0.03033684939146042} 08/31/2021 04:07:17 - INFO - __main__ - Step 82386: {'lr': 0.0002162200796413672, 'samples': 15818112, 'steps': 82385, 'loss/train': 0.9767144918441772} 08/31/2021 04:07:19 - INFO - __main__ - Step 82387: {'lr': 0.00021621482157127152, 'samples': 15818304, 'steps': 82386, 'loss/train': 1.8437515497207642} 08/31/2021 04:07:19 - INFO - __main__ - Step 82388: {'lr': 0.00021620956351639888, 'samples': 15818496, 'steps': 82387, 'loss/train': 0.9454585313796997} 08/31/2021 04:07:20 - INFO - __main__ - Step 82389: {'lr': 0.00021620430547675173, 'samples': 15818688, 'steps': 82388, 'loss/train': 1.1606789827346802} 08/31/2021 04:07:20 - INFO - __main__ - Step 82390: {'lr': 0.0002161990474523324, 'samples': 15818880, 'steps': 82389, 'loss/train': 1.1658709049224854} 08/31/2021 04:07:21 - INFO - __main__ - Step 82391: {'lr': 0.00021619378944314328, 'samples': 15819072, 'steps': 82390, 'loss/train': 1.357400894165039} 08/31/2021 04:07:21 - INFO - __main__ - Step 82392: {'lr': 0.00021618853144918668, 'samples': 15819264, 'steps': 82391, 'loss/train': 1.3218345642089844} 08/31/2021 04:07:23 - INFO - __main__ - Step 82393: {'lr': 0.00021618327347046502, 'samples': 15819456, 'steps': 82392, 'loss/train': 0.9760894775390625} 08/31/2021 04:07:23 - INFO - __main__ - Step 82394: {'lr': 0.00021617801550698068, 'samples': 15819648, 'steps': 82393, 'loss/train': 1.0312474966049194} 08/31/2021 04:07:23 - INFO - __main__ - Step 82395: {'lr': 0.00021617275755873605, 'samples': 15819840, 'steps': 82394, 'loss/train': 1.127712607383728} 08/31/2021 04:07:24 - INFO - __main__ - Step 82396: {'lr': 0.00021616749962573338, 'samples': 15820032, 'steps': 82395, 'loss/train': 0.979669988155365} 08/31/2021 04:07:24 - INFO - __main__ - Step 82397: {'lr': 0.0002161622417079751, 'samples': 15820224, 'steps': 82396, 'loss/train': 0.7188208699226379} 08/31/2021 04:07:26 - INFO - __main__ - Step 82398: {'lr': 0.00021615698380546362, 'samples': 15820416, 'steps': 82397, 'loss/train': 1.3659303188323975} 08/31/2021 04:07:26 - INFO - __main__ - Step 82399: {'lr': 0.00021615172591820127, 'samples': 15820608, 'steps': 82398, 'loss/train': 2.2959728240966797} 08/31/2021 04:07:27 - INFO - __main__ - Step 82400: {'lr': 0.0002161464680461904, 'samples': 15820800, 'steps': 82399, 'loss/train': 1.7558908462524414} 08/31/2021 04:07:27 - INFO - __main__ - Step 82401: {'lr': 0.00021614121018943345, 'samples': 15820992, 'steps': 82400, 'loss/train': 0.8637447357177734} 08/31/2021 04:07:27 - INFO - __main__ - Step 82402: {'lr': 0.0002161359523479327, 'samples': 15821184, 'steps': 82401, 'loss/train': 1.6498970985412598} 08/31/2021 04:07:29 - INFO - __main__ - Step 82403: {'lr': 0.00021613069452169063, 'samples': 15821376, 'steps': 82402, 'loss/train': 0.49004456400871277} 08/31/2021 04:07:29 - INFO - __main__ - Step 82404: {'lr': 0.0002161254367107095, 'samples': 15821568, 'steps': 82403, 'loss/train': 1.413736343383789} 08/31/2021 04:07:29 - INFO - __main__ - Step 82405: {'lr': 0.00021612017891499175, 'samples': 15821760, 'steps': 82404, 'loss/train': 0.7026843428611755} 08/31/2021 04:07:30 - INFO - __main__ - Step 82406: {'lr': 0.0002161149211345397, 'samples': 15821952, 'steps': 82405, 'loss/train': 0.9724634289741516} 08/31/2021 04:07:30 - INFO - __main__ - Step 82407: {'lr': 0.00021610966336935579, 'samples': 15822144, 'steps': 82406, 'loss/train': 1.1354758739471436} 08/31/2021 04:07:32 - INFO - __main__ - Step 82408: {'lr': 0.0002161044056194424, 'samples': 15822336, 'steps': 82407, 'loss/train': 0.420255184173584} 08/31/2021 04:07:32 - INFO - __main__ - Step 82409: {'lr': 0.00021609914788480177, 'samples': 15822528, 'steps': 82408, 'loss/train': 1.1334127187728882} 08/31/2021 04:07:33 - INFO - __main__ - Step 82410: {'lr': 0.00021609389016543628, 'samples': 15822720, 'steps': 82409, 'loss/train': 0.30177152156829834} 08/31/2021 04:07:33 - INFO - __main__ - Step 82411: {'lr': 0.00021608863246134845, 'samples': 15822912, 'steps': 82410, 'loss/train': 1.4691212177276611} 08/31/2021 04:07:33 - INFO - __main__ - Step 82412: {'lr': 0.00021608337477254047, 'samples': 15823104, 'steps': 82411, 'loss/train': 0.7084919810295105} 08/31/2021 04:07:35 - INFO - __main__ - Step 82413: {'lr': 0.00021607811709901487, 'samples': 15823296, 'steps': 82412, 'loss/train': 1.8390483856201172} 08/31/2021 04:07:36 - INFO - __main__ - Step 82414: {'lr': 0.00021607285944077393, 'samples': 15823488, 'steps': 82413, 'loss/train': 1.715490698814392} 08/31/2021 04:07:36 - INFO - __main__ - Step 82415: {'lr': 0.00021606760179782, 'samples': 15823680, 'steps': 82414, 'loss/train': 1.1689159870147705} 08/31/2021 04:07:37 - INFO - __main__ - Step 82416: {'lr': 0.00021606234417015553, 'samples': 15823872, 'steps': 82415, 'loss/train': 1.1487122774124146} 08/31/2021 04:07:37 - INFO - __main__ - Step 82417: {'lr': 0.0002160570865577828, 'samples': 15824064, 'steps': 82416, 'loss/train': 1.6712852716445923} 08/31/2021 04:07:39 - INFO - __main__ - Step 82418: {'lr': 0.00021605182896070423, 'samples': 15824256, 'steps': 82417, 'loss/train': 1.0693714618682861} 08/31/2021 04:07:39 - INFO - __main__ - Step 82419: {'lr': 0.00021604657137892221, 'samples': 15824448, 'steps': 82418, 'loss/train': 1.2583179473876953} 08/31/2021 04:07:39 - INFO - __main__ - Step 82420: {'lr': 0.00021604131381243907, 'samples': 15824640, 'steps': 82419, 'loss/train': 1.057275652885437} 08/31/2021 04:07:40 - INFO - __main__ - Step 82421: {'lr': 0.0002160360562612573, 'samples': 15824832, 'steps': 82420, 'loss/train': 1.166791319847107} 08/31/2021 04:07:40 - INFO - __main__ - Step 82422: {'lr': 0.00021603079872537905, 'samples': 15825024, 'steps': 82421, 'loss/train': 1.1474065780639648} 08/31/2021 04:07:42 - INFO - __main__ - Step 82423: {'lr': 0.0002160255412048068, 'samples': 15825216, 'steps': 82422, 'loss/train': 0.7845175266265869} 08/31/2021 04:07:42 - INFO - __main__ - Step 82424: {'lr': 0.0002160202836995429, 'samples': 15825408, 'steps': 82423, 'loss/train': 0.7465054988861084} 08/31/2021 04:07:42 - INFO - __main__ - Step 82425: {'lr': 0.00021601502620958977, 'samples': 15825600, 'steps': 82424, 'loss/train': 1.8593920469284058} 08/31/2021 04:07:43 - INFO - __main__ - Step 82426: {'lr': 0.00021600976873494972, 'samples': 15825792, 'steps': 82425, 'loss/train': 1.2127981185913086} 08/31/2021 04:07:43 - INFO - __main__ - Step 82427: {'lr': 0.00021600451127562514, 'samples': 15825984, 'steps': 82426, 'loss/train': 1.7147895097732544} 08/31/2021 04:07:44 - INFO - __main__ - Step 82428: {'lr': 0.0002159992538316184, 'samples': 15826176, 'steps': 82427, 'loss/train': 1.500097393989563} 08/31/2021 04:07:45 - INFO - __main__ - Step 82429: {'lr': 0.0002159939964029319, 'samples': 15826368, 'steps': 82428, 'loss/train': 1.2766276597976685} 08/31/2021 04:07:46 - INFO - __main__ - Step 82430: {'lr': 0.00021598873898956794, 'samples': 15826560, 'steps': 82429, 'loss/train': 1.3018076419830322} 08/31/2021 04:07:46 - INFO - __main__ - Step 82431: {'lr': 0.00021598348159152897, 'samples': 15826752, 'steps': 82430, 'loss/train': 1.2751073837280273} 08/31/2021 04:07:46 - INFO - __main__ - Step 82432: {'lr': 0.0002159782242088173, 'samples': 15826944, 'steps': 82431, 'loss/train': 0.37592846155166626} 08/31/2021 04:07:47 - INFO - __main__ - Step 82433: {'lr': 0.0002159729668414353, 'samples': 15827136, 'steps': 82432, 'loss/train': 1.0546003580093384} 08/31/2021 04:07:47 - INFO - __main__ - Step 82434: {'lr': 0.0002159677094893854, 'samples': 15827328, 'steps': 82433, 'loss/train': 5.834619522094727} 08/31/2021 04:07:48 - INFO - __main__ - Step 82435: {'lr': 0.00021596245215267, 'samples': 15827520, 'steps': 82434, 'loss/train': 1.226811170578003} 08/31/2021 04:07:49 - INFO - __main__ - Step 82436: {'lr': 0.00021595719483129128, 'samples': 15827712, 'steps': 82435, 'loss/train': 1.0311634540557861} 08/31/2021 04:07:49 - INFO - __main__ - Step 82437: {'lr': 0.00021595193752525175, 'samples': 15827904, 'steps': 82436, 'loss/train': 0.9990193247795105} 08/31/2021 04:07:50 - INFO - __main__ - Step 82438: {'lr': 0.00021594668023455373, 'samples': 15828096, 'steps': 82437, 'loss/train': 0.6708624958992004} 08/31/2021 04:07:50 - INFO - __main__ - Step 82439: {'lr': 0.0002159414229591996, 'samples': 15828288, 'steps': 82438, 'loss/train': 1.6177595853805542} 08/31/2021 04:07:51 - INFO - __main__ - Step 82440: {'lr': 0.00021593616569919177, 'samples': 15828480, 'steps': 82439, 'loss/train': 0.14394864439964294} 08/31/2021 04:07:52 - INFO - __main__ - Step 82441: {'lr': 0.00021593090845453255, 'samples': 15828672, 'steps': 82440, 'loss/train': 1.8343379497528076} 08/31/2021 04:07:52 - INFO - __main__ - Step 82442: {'lr': 0.00021592565122522436, 'samples': 15828864, 'steps': 82441, 'loss/train': 1.634940505027771} 08/31/2021 04:07:53 - INFO - __main__ - Step 82443: {'lr': 0.00021592039401126953, 'samples': 15829056, 'steps': 82442, 'loss/train': 1.222602128982544} 08/31/2021 04:07:53 - INFO - __main__ - Step 82444: {'lr': 0.00021591513681267044, 'samples': 15829248, 'steps': 82443, 'loss/train': 0.5800179243087769} 08/31/2021 04:07:55 - INFO - __main__ - Step 82445: {'lr': 0.00021590987962942949, 'samples': 15829440, 'steps': 82444, 'loss/train': 1.5345669984817505} 08/31/2021 04:07:55 - INFO - __main__ - Step 82446: {'lr': 0.00021590462246154902, 'samples': 15829632, 'steps': 82445, 'loss/train': 1.7257914543151855} 08/31/2021 04:07:55 - INFO - __main__ - Step 82447: {'lr': 0.00021589936530903137, 'samples': 15829824, 'steps': 82446, 'loss/train': 0.7808037996292114} 08/31/2021 04:07:56 - INFO - __main__ - Step 82448: {'lr': 0.00021589410817187906, 'samples': 15830016, 'steps': 82447, 'loss/train': 1.1472647190093994} 08/31/2021 04:07:56 - INFO - __main__ - Step 82449: {'lr': 0.00021588885105009427, 'samples': 15830208, 'steps': 82448, 'loss/train': 1.072537899017334} 08/31/2021 04:07:58 - INFO - __main__ - Step 82450: {'lr': 0.00021588359394367936, 'samples': 15830400, 'steps': 82449, 'loss/train': 0.9270260334014893} 08/31/2021 04:07:58 - INFO - __main__ - Step 82451: {'lr': 0.00021587833685263684, 'samples': 15830592, 'steps': 82450, 'loss/train': 1.5074928998947144} 08/31/2021 04:07:58 - INFO - __main__ - Step 82452: {'lr': 0.000215873079776969, 'samples': 15830784, 'steps': 82451, 'loss/train': 0.5598421096801758} 08/31/2021 04:07:59 - INFO - __main__ - Step 82453: {'lr': 0.00021586782271667822, 'samples': 15830976, 'steps': 82452, 'loss/train': 1.3876591920852661} 08/31/2021 04:07:59 - INFO - __main__ - Step 82454: {'lr': 0.00021586256567176688, 'samples': 15831168, 'steps': 82453, 'loss/train': 0.33988073468208313} 08/31/2021 04:08:01 - INFO - __main__ - Step 82455: {'lr': 0.00021585730864223733, 'samples': 15831360, 'steps': 82454, 'loss/train': 1.605892300605774} 08/31/2021 04:08:01 - INFO - __main__ - Step 82456: {'lr': 0.00021585205162809193, 'samples': 15831552, 'steps': 82455, 'loss/train': 0.7293034195899963} 08/31/2021 04:08:01 - INFO - __main__ - Step 82457: {'lr': 0.0002158467946293331, 'samples': 15831744, 'steps': 82456, 'loss/train': 1.1999095678329468} 08/31/2021 04:08:02 - INFO - __main__ - Step 82458: {'lr': 0.00021584153764596316, 'samples': 15831936, 'steps': 82457, 'loss/train': 1.4389480352401733} 08/31/2021 04:08:02 - INFO - __main__ - Step 82459: {'lr': 0.0002158362806779845, 'samples': 15832128, 'steps': 82458, 'loss/train': 0.814817488193512} 08/31/2021 04:08:04 - INFO - __main__ - Step 82460: {'lr': 0.00021583102372539948, 'samples': 15832320, 'steps': 82459, 'loss/train': 1.3640244007110596} 08/31/2021 04:08:04 - INFO - __main__ - Step 82461: {'lr': 0.00021582576678821048, 'samples': 15832512, 'steps': 82460, 'loss/train': 1.0080530643463135} 08/31/2021 04:08:04 - INFO - __main__ - Step 82462: {'lr': 0.00021582050986642, 'samples': 15832704, 'steps': 82461, 'loss/train': 1.3186217546463013} 08/31/2021 04:08:05 - INFO - __main__ - Step 82463: {'lr': 0.00021581525296003013, 'samples': 15832896, 'steps': 82462, 'loss/train': 1.1175473928451538} 08/31/2021 04:08:05 - INFO - __main__ - Step 82464: {'lr': 0.00021580999606904337, 'samples': 15833088, 'steps': 82463, 'loss/train': 0.3004101812839508} 08/31/2021 04:08:05 - INFO - __main__ - Step 82465: {'lr': 0.0002158047391934621, 'samples': 15833280, 'steps': 82464, 'loss/train': 0.8695633411407471} 08/31/2021 04:08:07 - INFO - __main__ - Step 82466: {'lr': 0.00021579948233328873, 'samples': 15833472, 'steps': 82465, 'loss/train': 1.2453516721725464} 08/31/2021 04:08:08 - INFO - __main__ - Step 82467: {'lr': 0.00021579422548852553, 'samples': 15833664, 'steps': 82466, 'loss/train': 0.2728550434112549} 08/31/2021 04:08:08 - INFO - __main__ - Step 82468: {'lr': 0.00021578896865917497, 'samples': 15833856, 'steps': 82467, 'loss/train': 0.11987628042697906} 08/31/2021 04:08:09 - INFO - __main__ - Step 82469: {'lr': 0.00021578371184523935, 'samples': 15834048, 'steps': 82468, 'loss/train': 0.49502331018447876} 08/31/2021 04:08:09 - INFO - __main__ - Step 82470: {'lr': 0.00021577845504672105, 'samples': 15834240, 'steps': 82469, 'loss/train': 1.7142574787139893} 08/31/2021 04:08:11 - INFO - __main__ - Step 82471: {'lr': 0.00021577319826362245, 'samples': 15834432, 'steps': 82470, 'loss/train': 1.1805423498153687} 08/31/2021 04:08:12 - INFO - __main__ - Step 82472: {'lr': 0.00021576794149594594, 'samples': 15834624, 'steps': 82471, 'loss/train': 0.3219194710254669} 08/31/2021 04:08:12 - INFO - __main__ - Step 82473: {'lr': 0.00021576268474369386, 'samples': 15834816, 'steps': 82472, 'loss/train': 1.7839076519012451} 08/31/2021 04:08:12 - INFO - __main__ - Step 82474: {'lr': 0.0002157574280068686, 'samples': 15835008, 'steps': 82473, 'loss/train': 0.906516969203949} 08/31/2021 04:08:13 - INFO - __main__ - Step 82475: {'lr': 0.00021575217128547258, 'samples': 15835200, 'steps': 82474, 'loss/train': 1.2468054294586182} 08/31/2021 04:08:14 - INFO - __main__ - Step 82476: {'lr': 0.00021574691457950805, 'samples': 15835392, 'steps': 82475, 'loss/train': 1.0321834087371826} 08/31/2021 04:08:15 - INFO - __main__ - Step 82477: {'lr': 0.0002157416578889774, 'samples': 15835584, 'steps': 82476, 'loss/train': 1.1529043912887573} 08/31/2021 04:08:15 - INFO - __main__ - Step 82478: {'lr': 0.000215736401213883, 'samples': 15835776, 'steps': 82477, 'loss/train': 1.183288335800171} 08/31/2021 04:08:15 - INFO - __main__ - Step 82479: {'lr': 0.00021573114455422732, 'samples': 15835968, 'steps': 82478, 'loss/train': 1.656986951828003} 08/31/2021 04:08:16 - INFO - __main__ - Step 82480: {'lr': 0.0002157258879100126, 'samples': 15836160, 'steps': 82479, 'loss/train': 0.47596096992492676} 08/31/2021 04:08:18 - INFO - __main__ - Step 82481: {'lr': 0.0002157206312812413, 'samples': 15836352, 'steps': 82480, 'loss/train': 0.9578299522399902} 08/31/2021 04:08:18 - INFO - __main__ - Step 82482: {'lr': 0.00021571537466791576, 'samples': 15836544, 'steps': 82481, 'loss/train': 1.101263403892517} 08/31/2021 04:08:18 - INFO - __main__ - Step 82483: {'lr': 0.00021571011807003832, 'samples': 15836736, 'steps': 82482, 'loss/train': 1.0543180704116821} 08/31/2021 04:08:19 - INFO - __main__ - Step 82484: {'lr': 0.00021570486148761136, 'samples': 15836928, 'steps': 82483, 'loss/train': 1.3226237297058105} 08/31/2021 04:08:19 - INFO - __main__ - Step 82485: {'lr': 0.00021569960492063729, 'samples': 15837120, 'steps': 82484, 'loss/train': 1.3267810344696045} 08/31/2021 04:08:19 - INFO - __main__ - Step 82486: {'lr': 0.00021569434836911846, 'samples': 15837312, 'steps': 82485, 'loss/train': 1.5555847883224487} 08/31/2021 04:08:21 - INFO - __main__ - Step 82487: {'lr': 0.00021568909183305722, 'samples': 15837504, 'steps': 82486, 'loss/train': 1.2161610126495361} 08/31/2021 04:08:21 - INFO - __main__ - Step 82488: {'lr': 0.00021568383531245594, 'samples': 15837696, 'steps': 82487, 'loss/train': 0.6311428546905518} 08/31/2021 04:08:22 - INFO - __main__ - Step 82489: {'lr': 0.00021567857880731703, 'samples': 15837888, 'steps': 82488, 'loss/train': 0.16407129168510437} 08/31/2021 04:08:22 - INFO - __main__ - Step 82490: {'lr': 0.00021567332231764278, 'samples': 15838080, 'steps': 82489, 'loss/train': 1.3743274211883545} 08/31/2021 04:08:22 - INFO - __main__ - Step 82491: {'lr': 0.0002156680658434356, 'samples': 15838272, 'steps': 82490, 'loss/train': 0.7334270477294922} 08/31/2021 04:08:24 - INFO - __main__ - Step 82492: {'lr': 0.00021566280938469784, 'samples': 15838464, 'steps': 82491, 'loss/train': 0.8711608648300171} 08/31/2021 04:08:24 - INFO - __main__ - Step 82493: {'lr': 0.0002156575529414319, 'samples': 15838656, 'steps': 82492, 'loss/train': 0.6020982265472412} 08/31/2021 04:08:25 - INFO - __main__ - Step 82494: {'lr': 0.00021565229651364015, 'samples': 15838848, 'steps': 82493, 'loss/train': 1.468302607536316} 08/31/2021 04:08:25 - INFO - __main__ - Step 82495: {'lr': 0.00021564704010132495, 'samples': 15839040, 'steps': 82494, 'loss/train': 1.1182301044464111} 08/31/2021 04:08:25 - INFO - __main__ - Step 82496: {'lr': 0.00021564178370448865, 'samples': 15839232, 'steps': 82495, 'loss/train': 1.309699535369873} 08/31/2021 04:08:27 - INFO - __main__ - Step 82497: {'lr': 0.00021563652732313365, 'samples': 15839424, 'steps': 82496, 'loss/train': 0.6757398247718811} 08/31/2021 04:08:27 - INFO - __main__ - Step 82498: {'lr': 0.0002156312709572623, 'samples': 15839616, 'steps': 82497, 'loss/train': 0.8205418586730957} 08/31/2021 04:08:28 - INFO - __main__ - Step 82499: {'lr': 0.00021562601460687697, 'samples': 15839808, 'steps': 82498, 'loss/train': 1.5543965101242065} 08/31/2021 04:08:28 - INFO - __main__ - Step 82500: {'lr': 0.00021562075827197998, 'samples': 15840000, 'steps': 82499, 'loss/train': 0.9459472298622131} 08/31/2021 04:08:28 - INFO - __main__ - Step 82501: {'lr': 0.0002156155019525738, 'samples': 15840192, 'steps': 82500, 'loss/train': 1.3077610731124878} 08/31/2021 04:08:30 - INFO - __main__ - Step 82502: {'lr': 0.00021561024564866079, 'samples': 15840384, 'steps': 82501, 'loss/train': 0.9786359667778015} 08/31/2021 04:08:30 - INFO - __main__ - Step 82503: {'lr': 0.00021560498936024316, 'samples': 15840576, 'steps': 82502, 'loss/train': 1.2277029752731323} 08/31/2021 04:08:31 - INFO - __main__ - Step 82504: {'lr': 0.00021559973308732345, 'samples': 15840768, 'steps': 82503, 'loss/train': 1.4334731101989746} 08/31/2021 04:08:31 - INFO - __main__ - Step 82505: {'lr': 0.00021559447682990395, 'samples': 15840960, 'steps': 82504, 'loss/train': 1.782763957977295} 08/31/2021 04:08:31 - INFO - __main__ - Step 82506: {'lr': 0.00021558922058798706, 'samples': 15841152, 'steps': 82505, 'loss/train': 1.0359346866607666} 08/31/2021 04:08:33 - INFO - __main__ - Step 82507: {'lr': 0.00021558396436157512, 'samples': 15841344, 'steps': 82506, 'loss/train': 1.8745957612991333} 08/31/2021 04:08:34 - INFO - __main__ - Step 82508: {'lr': 0.00021557870815067058, 'samples': 15841536, 'steps': 82507, 'loss/train': 0.05419657379388809} 08/31/2021 04:08:34 - INFO - __main__ - Step 82509: {'lr': 0.00021557345195527566, 'samples': 15841728, 'steps': 82508, 'loss/train': 0.1713501214981079} 08/31/2021 04:08:35 - INFO - __main__ - Step 82510: {'lr': 0.00021556819577539285, 'samples': 15841920, 'steps': 82509, 'loss/train': 1.1979223489761353} 08/31/2021 04:08:35 - INFO - __main__ - Step 82511: {'lr': 0.00021556293961102446, 'samples': 15842112, 'steps': 82510, 'loss/train': 1.2280694246292114} 08/31/2021 04:08:36 - INFO - __main__ - Step 82512: {'lr': 0.00021555768346217288, 'samples': 15842304, 'steps': 82511, 'loss/train': 0.5744165182113647} 08/31/2021 04:08:37 - INFO - __main__ - Step 82513: {'lr': 0.0002155524273288405, 'samples': 15842496, 'steps': 82512, 'loss/train': 1.4402621984481812} 08/31/2021 04:08:37 - INFO - __main__ - Step 82514: {'lr': 0.00021554717121102964, 'samples': 15842688, 'steps': 82513, 'loss/train': 1.283274531364441} 08/31/2021 04:08:38 - INFO - __main__ - Step 82515: {'lr': 0.00021554191510874275, 'samples': 15842880, 'steps': 82514, 'loss/train': 0.7517218589782715} 08/31/2021 04:08:38 - INFO - __main__ - Step 82516: {'lr': 0.0002155366590219821, 'samples': 15843072, 'steps': 82515, 'loss/train': 1.3563895225524902} 08/31/2021 04:08:39 - INFO - __main__ - Step 82517: {'lr': 0.00021553140295075009, 'samples': 15843264, 'steps': 82516, 'loss/train': 0.19832511246204376} 08/31/2021 04:08:40 - INFO - __main__ - Step 82518: {'lr': 0.00021552614689504906, 'samples': 15843456, 'steps': 82517, 'loss/train': 0.14540086686611176} 08/31/2021 04:08:40 - INFO - __main__ - Step 82519: {'lr': 0.00021552089085488153, 'samples': 15843648, 'steps': 82518, 'loss/train': 0.9827099442481995} 08/31/2021 04:08:41 - INFO - __main__ - Step 82520: {'lr': 0.00021551563483024967, 'samples': 15843840, 'steps': 82519, 'loss/train': 1.1661310195922852} 08/31/2021 04:08:41 - INFO - __main__ - Step 82521: {'lr': 0.00021551037882115592, 'samples': 15844032, 'steps': 82520, 'loss/train': 1.209884524345398} 08/31/2021 04:08:43 - INFO - __main__ - Step 82522: {'lr': 0.0002155051228276027, 'samples': 15844224, 'steps': 82521, 'loss/train': 0.8490942716598511} 08/31/2021 04:08:44 - INFO - __main__ - Step 82523: {'lr': 0.00021549986684959234, 'samples': 15844416, 'steps': 82522, 'loss/train': 1.4197218418121338} 08/31/2021 04:08:44 - INFO - __main__ - Step 82524: {'lr': 0.00021549461088712717, 'samples': 15844608, 'steps': 82523, 'loss/train': 1.151057243347168} 08/31/2021 04:08:44 - INFO - __main__ - Step 82525: {'lr': 0.0002154893549402096, 'samples': 15844800, 'steps': 82524, 'loss/train': 1.7858220338821411} 08/31/2021 04:08:45 - INFO - __main__ - Step 82526: {'lr': 0.00021548409900884203, 'samples': 15844992, 'steps': 82525, 'loss/train': 0.84963059425354} 08/31/2021 04:08:45 - INFO - __main__ - Step 82527: {'lr': 0.00021547884309302675, 'samples': 15845184, 'steps': 82526, 'loss/train': 1.36491858959198} 08/31/2021 04:08:47 - INFO - __main__ - Step 82528: {'lr': 0.0002154735871927662, 'samples': 15845376, 'steps': 82527, 'loss/train': 0.6746163964271545} 08/31/2021 04:08:47 - INFO - __main__ - Step 82529: {'lr': 0.00021546833130806276, 'samples': 15845568, 'steps': 82528, 'loss/train': 1.1270034313201904} 08/31/2021 04:08:47 - INFO - __main__ - Step 82530: {'lr': 0.00021546307543891878, 'samples': 15845760, 'steps': 82529, 'loss/train': 1.1274775266647339} 08/31/2021 04:08:48 - INFO - __main__ - Step 82531: {'lr': 0.0002154578195853365, 'samples': 15845952, 'steps': 82530, 'loss/train': 1.2223024368286133} 08/31/2021 04:08:48 - INFO - __main__ - Step 82532: {'lr': 0.00021545256374731845, 'samples': 15846144, 'steps': 82531, 'loss/train': 1.4059866666793823} 08/31/2021 04:08:50 - INFO - __main__ - Step 82533: {'lr': 0.0002154473079248669, 'samples': 15846336, 'steps': 82532, 'loss/train': 2.491978168487549} 08/31/2021 04:08:50 - INFO - __main__ - Step 82534: {'lr': 0.0002154420521179843, 'samples': 15846528, 'steps': 82533, 'loss/train': 1.1217514276504517} 08/31/2021 04:08:50 - INFO - __main__ - Step 82535: {'lr': 0.00021543679632667293, 'samples': 15846720, 'steps': 82534, 'loss/train': 1.1871473789215088} 08/31/2021 04:08:51 - INFO - __main__ - Step 82536: {'lr': 0.00021543154055093524, 'samples': 15846912, 'steps': 82535, 'loss/train': 1.0250822305679321} 08/31/2021 04:08:51 - INFO - __main__ - Step 82537: {'lr': 0.00021542628479077354, 'samples': 15847104, 'steps': 82536, 'loss/train': 1.509700059890747} 08/31/2021 04:08:51 - INFO - __main__ - Step 82538: {'lr': 0.00021542102904619027, 'samples': 15847296, 'steps': 82537, 'loss/train': 1.6982916593551636} 08/31/2021 04:08:53 - INFO - __main__ - Step 82539: {'lr': 0.0002154157733171877, 'samples': 15847488, 'steps': 82538, 'loss/train': 1.7354329824447632} 08/31/2021 04:08:53 - INFO - __main__ - Step 82540: {'lr': 0.00021541051760376828, 'samples': 15847680, 'steps': 82539, 'loss/train': 1.0560033321380615} 08/31/2021 04:08:54 - INFO - __main__ - Step 82541: {'lr': 0.0002154052619059343, 'samples': 15847872, 'steps': 82540, 'loss/train': 0.8357874155044556} 08/31/2021 04:08:54 - INFO - __main__ - Step 82542: {'lr': 0.00021540000622368832, 'samples': 15848064, 'steps': 82541, 'loss/train': 0.9047871232032776} 08/31/2021 04:08:54 - INFO - __main__ - Step 82543: {'lr': 0.00021539475055703248, 'samples': 15848256, 'steps': 82542, 'loss/train': 1.6823945045471191} 08/31/2021 04:08:56 - INFO - __main__ - Step 82544: {'lr': 0.0002153894949059692, 'samples': 15848448, 'steps': 82543, 'loss/train': 1.4745861291885376} 08/31/2021 04:08:56 - INFO - __main__ - Step 82545: {'lr': 0.00021538423927050087, 'samples': 15848640, 'steps': 82544, 'loss/train': 0.9639161229133606} 08/31/2021 04:08:57 - INFO - __main__ - Step 82546: {'lr': 0.0002153789836506299, 'samples': 15848832, 'steps': 82545, 'loss/train': 1.6689610481262207} 08/31/2021 04:08:57 - INFO - __main__ - Step 82547: {'lr': 0.0002153737280463586, 'samples': 15849024, 'steps': 82546, 'loss/train': 2.3087353706359863} 08/31/2021 04:08:58 - INFO - __main__ - Step 82548: {'lr': 0.00021536847245768936, 'samples': 15849216, 'steps': 82547, 'loss/train': 0.8960351347923279} 08/31/2021 04:08:59 - INFO - __main__ - Step 82549: {'lr': 0.00021536321688462456, 'samples': 15849408, 'steps': 82548, 'loss/train': 1.149214744567871} 08/31/2021 04:09:00 - INFO - __main__ - Step 82550: {'lr': 0.00021535796132716658, 'samples': 15849600, 'steps': 82549, 'loss/train': 0.3573833405971527} 08/31/2021 04:09:00 - INFO - __main__ - Step 82551: {'lr': 0.00021535270578531773, 'samples': 15849792, 'steps': 82550, 'loss/train': 1.5820807218551636} 08/31/2021 04:09:00 - INFO - __main__ - Step 82552: {'lr': 0.00021534745025908046, 'samples': 15849984, 'steps': 82551, 'loss/train': 1.087409496307373} 08/31/2021 04:09:01 - INFO - __main__ - Step 82553: {'lr': 0.00021534219474845707, 'samples': 15850176, 'steps': 82552, 'loss/train': 1.5964124202728271} 08/31/2021 04:09:02 - INFO - __main__ - Step 82554: {'lr': 0.00021533693925344995, 'samples': 15850368, 'steps': 82553, 'loss/train': 0.03531185910105705} 08/31/2021 04:09:03 - INFO - __main__ - Step 82555: {'lr': 0.0002153316837740615, 'samples': 15850560, 'steps': 82554, 'loss/train': 0.8233292698860168} 08/31/2021 04:09:03 - INFO - __main__ - Step 82556: {'lr': 0.0002153264283102941, 'samples': 15850752, 'steps': 82555, 'loss/train': 0.6860018968582153} 08/31/2021 04:09:03 - INFO - __main__ - Step 82557: {'lr': 0.00021532117286215003, 'samples': 15850944, 'steps': 82556, 'loss/train': 1.0263028144836426} 08/31/2021 04:09:04 - INFO - __main__ - Step 82558: {'lr': 0.0002153159174296317, 'samples': 15851136, 'steps': 82557, 'loss/train': 0.9178967475891113} 08/31/2021 04:09:05 - INFO - __main__ - Step 82559: {'lr': 0.00021531066201274144, 'samples': 15851328, 'steps': 82558, 'loss/train': 0.6055713891983032} 08/31/2021 04:09:05 - INFO - __main__ - Step 82560: {'lr': 0.00021530540661148168, 'samples': 15851520, 'steps': 82559, 'loss/train': 1.3622465133666992} 08/31/2021 04:09:06 - INFO - __main__ - Step 82561: {'lr': 0.00021530015122585478, 'samples': 15851712, 'steps': 82560, 'loss/train': 1.1187512874603271} 08/31/2021 04:09:06 - INFO - __main__ - Step 82562: {'lr': 0.0002152948958558631, 'samples': 15851904, 'steps': 82561, 'loss/train': 1.1681647300720215} 08/31/2021 04:09:06 - INFO - __main__ - Step 82563: {'lr': 0.00021528964050150897, 'samples': 15852096, 'steps': 82562, 'loss/train': 1.3379325866699219} 08/31/2021 04:09:08 - INFO - __main__ - Step 82564: {'lr': 0.00021528438516279483, 'samples': 15852288, 'steps': 82563, 'loss/train': 0.8569117188453674} 08/31/2021 04:09:09 - INFO - __main__ - Step 82565: {'lr': 0.000215279129839723, 'samples': 15852480, 'steps': 82564, 'loss/train': 0.40124237537384033} 08/31/2021 04:09:09 - INFO - __main__ - Step 82566: {'lr': 0.00021527387453229585, 'samples': 15852672, 'steps': 82565, 'loss/train': 1.5031100511550903} 08/31/2021 04:09:10 - INFO - __main__ - Step 82567: {'lr': 0.00021526861924051578, 'samples': 15852864, 'steps': 82566, 'loss/train': 0.01876341924071312} 08/31/2021 04:09:10 - INFO - __main__ - Step 82568: {'lr': 0.00021526336396438512, 'samples': 15853056, 'steps': 82567, 'loss/train': 1.3013607263565063} 08/31/2021 04:09:10 - INFO - __main__ - Step 82569: {'lr': 0.00021525810870390635, 'samples': 15853248, 'steps': 82568, 'loss/train': 1.5198992490768433} 08/31/2021 04:09:11 - INFO - __main__ - Step 82570: {'lr': 0.00021525285345908162, 'samples': 15853440, 'steps': 82569, 'loss/train': 1.0969042778015137} 08/31/2021 04:09:12 - INFO - __main__ - Step 82571: {'lr': 0.00021524759822991348, 'samples': 15853632, 'steps': 82570, 'loss/train': 0.7260648608207703} 08/31/2021 04:09:13 - INFO - __main__ - Step 82572: {'lr': 0.00021524234301640416, 'samples': 15853824, 'steps': 82571, 'loss/train': 0.6853105425834656} 08/31/2021 04:09:13 - INFO - __main__ - Step 82573: {'lr': 0.00021523708781855615, 'samples': 15854016, 'steps': 82572, 'loss/train': 1.0175788402557373} 08/31/2021 04:09:13 - INFO - __main__ - Step 82574: {'lr': 0.00021523183263637174, 'samples': 15854208, 'steps': 82573, 'loss/train': 0.9242661595344543} 08/31/2021 04:09:14 - INFO - __main__ - Step 82575: {'lr': 0.00021522657746985335, 'samples': 15854400, 'steps': 82574, 'loss/train': 1.0582282543182373} 08/31/2021 04:09:16 - INFO - __main__ - Step 82576: {'lr': 0.00021522132231900336, 'samples': 15854592, 'steps': 82575, 'loss/train': 1.0739412307739258} 08/31/2021 04:09:16 - INFO - __main__ - Step 82577: {'lr': 0.00021521606718382405, 'samples': 15854784, 'steps': 82576, 'loss/train': 0.483481764793396} 08/31/2021 04:09:17 - INFO - __main__ - Step 82578: {'lr': 0.00021521081206431786, 'samples': 15854976, 'steps': 82577, 'loss/train': 1.2358062267303467} 08/31/2021 04:09:17 - INFO - __main__ - Step 82579: {'lr': 0.00021520555696048717, 'samples': 15855168, 'steps': 82578, 'loss/train': 1.4182106256484985} 08/31/2021 04:09:17 - INFO - __main__ - Step 82580: {'lr': 0.00021520030187233429, 'samples': 15855360, 'steps': 82579, 'loss/train': 1.264650821685791} 08/31/2021 04:09:19 - INFO - __main__ - Step 82581: {'lr': 0.0002151950467998616, 'samples': 15855552, 'steps': 82580, 'loss/train': 0.9453312158584595} 08/31/2021 04:09:19 - INFO - __main__ - Step 82582: {'lr': 0.0002151897917430715, 'samples': 15855744, 'steps': 82581, 'loss/train': 0.4190158247947693} 08/31/2021 04:09:20 - INFO - __main__ - Step 82583: {'lr': 0.00021518453670196647, 'samples': 15855936, 'steps': 82582, 'loss/train': 1.3643653392791748} 08/31/2021 04:09:20 - INFO - __main__ - Step 82584: {'lr': 0.00021517928167654862, 'samples': 15856128, 'steps': 82583, 'loss/train': 1.2558060884475708} 08/31/2021 04:09:20 - INFO - __main__ - Step 82585: {'lr': 0.0002151740266668205, 'samples': 15856320, 'steps': 82584, 'loss/train': 1.5473371744155884} 08/31/2021 04:09:22 - INFO - __main__ - Step 82586: {'lr': 0.00021516877167278436, 'samples': 15856512, 'steps': 82585, 'loss/train': 1.0833762884140015} 08/31/2021 04:09:22 - INFO - __main__ - Step 82587: {'lr': 0.00021516351669444267, 'samples': 15856704, 'steps': 82586, 'loss/train': 1.306809902191162} 08/31/2021 04:09:23 - INFO - __main__ - Step 82588: {'lr': 0.00021515826173179774, 'samples': 15856896, 'steps': 82587, 'loss/train': 0.4520867168903351} 08/31/2021 04:09:23 - INFO - __main__ - Step 82589: {'lr': 0.00021515300678485197, 'samples': 15857088, 'steps': 82588, 'loss/train': 1.2869874238967896} 08/31/2021 04:09:23 - INFO - __main__ - Step 82590: {'lr': 0.00021514775185360773, 'samples': 15857280, 'steps': 82589, 'loss/train': 0.8896592855453491} 08/31/2021 04:09:25 - INFO - __main__ - Step 82591: {'lr': 0.00021514249693806734, 'samples': 15857472, 'steps': 82590, 'loss/train': 0.7472659945487976} 08/31/2021 04:09:26 - INFO - __main__ - Step 82592: {'lr': 0.00021513724203823324, 'samples': 15857664, 'steps': 82591, 'loss/train': 1.72776198387146} 08/31/2021 04:09:26 - INFO - __main__ - Step 82593: {'lr': 0.00021513198715410775, 'samples': 15857856, 'steps': 82592, 'loss/train': 1.0566723346710205} 08/31/2021 04:09:26 - INFO - __main__ - Step 82594: {'lr': 0.00021512673228569324, 'samples': 15858048, 'steps': 82593, 'loss/train': 1.3455824851989746} 08/31/2021 04:09:27 - INFO - __main__ - Step 82595: {'lr': 0.0002151214774329921, 'samples': 15858240, 'steps': 82594, 'loss/train': 0.38099128007888794} 08/31/2021 04:09:27 - INFO - __main__ - Step 82596: {'lr': 0.00021511622259600676, 'samples': 15858432, 'steps': 82595, 'loss/train': 0.542997419834137} 08/31/2021 04:09:27 - INFO - __main__ - Step 82597: {'lr': 0.00021511096777473943, 'samples': 15858624, 'steps': 82596, 'loss/train': 0.019906995818018913} 08/31/2021 04:09:30 - INFO - __main__ - Step 82598: {'lr': 0.00021510571296919258, 'samples': 15858816, 'steps': 82597, 'loss/train': 1.5219658613204956} 08/31/2021 04:09:30 - INFO - __main__ - Step 82599: {'lr': 0.00021510045817936852, 'samples': 15859008, 'steps': 82598, 'loss/train': 1.2573193311691284} 08/31/2021 04:09:31 - INFO - __main__ - Step 82600: {'lr': 0.00021509520340526968, 'samples': 15859200, 'steps': 82599, 'loss/train': 6.922261714935303} 08/31/2021 04:09:31 - INFO - __main__ - Step 82601: {'lr': 0.00021508994864689838, 'samples': 15859392, 'steps': 82600, 'loss/train': 6.670793056488037} 08/31/2021 04:09:31 - INFO - __main__ - Step 82602: {'lr': 0.00021508469390425704, 'samples': 15859584, 'steps': 82601, 'loss/train': 6.090807914733887} 08/31/2021 04:09:32 - INFO - __main__ - Step 82603: {'lr': 0.00021507943917734796, 'samples': 15859776, 'steps': 82602, 'loss/train': 1.3168481588363647} 08/31/2021 04:09:34 - INFO - __main__ - Step 82604: {'lr': 0.00021507418446617359, 'samples': 15859968, 'steps': 82603, 'loss/train': 2.0498828887939453} 08/31/2021 04:09:34 - INFO - __main__ - Step 82605: {'lr': 0.0002150689297707362, 'samples': 15860160, 'steps': 82604, 'loss/train': 1.7711272239685059} 08/31/2021 04:09:35 - INFO - __main__ - Step 82606: {'lr': 0.00021506367509103826, 'samples': 15860352, 'steps': 82605, 'loss/train': 0.7378116846084595} 08/31/2021 04:09:35 - INFO - __main__ - Step 82607: {'lr': 0.00021505842042708208, 'samples': 15860544, 'steps': 82606, 'loss/train': 0.6467121243476868} 08/31/2021 04:09:35 - INFO - __main__ - Step 82608: {'lr': 0.00021505316577887003, 'samples': 15860736, 'steps': 82607, 'loss/train': 1.5929417610168457} 08/31/2021 04:09:36 - INFO - __main__ - Step 82609: {'lr': 0.0002150479111464045, 'samples': 15860928, 'steps': 82608, 'loss/train': 1.2757725715637207} 08/31/2021 04:09:37 - INFO - __main__ - Step 82610: {'lr': 0.0002150426565296879, 'samples': 15861120, 'steps': 82609, 'loss/train': 1.733278512954712} 08/31/2021 04:09:37 - INFO - __main__ - Step 82611: {'lr': 0.00021503740192872246, 'samples': 15861312, 'steps': 82610, 'loss/train': 0.9249753952026367} 08/31/2021 04:09:38 - INFO - __main__ - Step 82612: {'lr': 0.0002150321473435106, 'samples': 15861504, 'steps': 82611, 'loss/train': 1.712761640548706} 08/31/2021 04:09:38 - INFO - __main__ - Step 82613: {'lr': 0.00021502689277405477, 'samples': 15861696, 'steps': 82612, 'loss/train': 1.677584171295166} 08/31/2021 04:09:39 - INFO - __main__ - Step 82614: {'lr': 0.00021502163822035726, 'samples': 15861888, 'steps': 82613, 'loss/train': 1.4989018440246582} 08/31/2021 04:09:40 - INFO - __main__ - Step 82615: {'lr': 0.00021501638368242045, 'samples': 15862080, 'steps': 82614, 'loss/train': 1.5495030879974365} 08/31/2021 04:09:41 - INFO - __main__ - Step 82616: {'lr': 0.00021501112916024674, 'samples': 15862272, 'steps': 82615, 'loss/train': 2.6105403900146484} 08/31/2021 04:09:41 - INFO - __main__ - Step 82617: {'lr': 0.00021500587465383844, 'samples': 15862464, 'steps': 82616, 'loss/train': 1.5386431217193604} 08/31/2021 04:09:41 - INFO - __main__ - Step 82618: {'lr': 0.000215000620163198, 'samples': 15862656, 'steps': 82617, 'loss/train': 1.0981053113937378} 08/31/2021 04:09:42 - INFO - __main__ - Step 82619: {'lr': 0.0002149953656883277, 'samples': 15862848, 'steps': 82618, 'loss/train': 1.0244696140289307} 08/31/2021 04:09:42 - INFO - __main__ - Step 82620: {'lr': 0.00021499011122923, 'samples': 15863040, 'steps': 82619, 'loss/train': 1.3258658647537231} 08/31/2021 04:09:44 - INFO - __main__ - Step 82621: {'lr': 0.00021498485678590718, 'samples': 15863232, 'steps': 82620, 'loss/train': 0.8639309406280518} 08/31/2021 04:09:44 - INFO - __main__ - Step 82622: {'lr': 0.00021497960235836164, 'samples': 15863424, 'steps': 82621, 'loss/train': 2.4136462211608887} 08/31/2021 04:09:44 - INFO - __main__ - Step 82623: {'lr': 0.00021497434794659582, 'samples': 15863616, 'steps': 82622, 'loss/train': 1.064667820930481} 08/31/2021 04:09:45 - INFO - __main__ - Step 82624: {'lr': 0.00021496909355061194, 'samples': 15863808, 'steps': 82623, 'loss/train': 1.2610048055648804} 08/31/2021 04:09:45 - INFO - __main__ - Step 82625: {'lr': 0.00021496383917041245, 'samples': 15864000, 'steps': 82624, 'loss/train': 1.4945008754730225} 08/31/2021 04:09:47 - INFO - __main__ - Step 82626: {'lr': 0.00021495858480599973, 'samples': 15864192, 'steps': 82625, 'loss/train': 1.4342026710510254} 08/31/2021 04:09:47 - INFO - __main__ - Step 82627: {'lr': 0.0002149533304573761, 'samples': 15864384, 'steps': 82626, 'loss/train': 0.19893580675125122} 08/31/2021 04:09:47 - INFO - __main__ - Step 82628: {'lr': 0.00021494807612454397, 'samples': 15864576, 'steps': 82627, 'loss/train': 1.060526967048645} 08/31/2021 04:09:48 - INFO - __main__ - Step 82629: {'lr': 0.00021494282180750573, 'samples': 15864768, 'steps': 82628, 'loss/train': 1.3316336870193481} 08/31/2021 04:09:48 - INFO - __main__ - Step 82630: {'lr': 0.0002149375675062637, 'samples': 15864960, 'steps': 82629, 'loss/train': 1.4332163333892822} 08/31/2021 04:09:50 - INFO - __main__ - Step 82631: {'lr': 0.0002149323132208203, 'samples': 15865152, 'steps': 82630, 'loss/train': 0.7682183980941772} 08/31/2021 04:09:50 - INFO - __main__ - Step 82632: {'lr': 0.00021492705895117777, 'samples': 15865344, 'steps': 82631, 'loss/train': 1.31145179271698} 08/31/2021 04:09:50 - INFO - __main__ - Step 82633: {'lr': 0.00021492180469733863, 'samples': 15865536, 'steps': 82632, 'loss/train': 1.2205208539962769} 08/31/2021 04:09:51 - INFO - __main__ - Step 82634: {'lr': 0.00021491655045930515, 'samples': 15865728, 'steps': 82633, 'loss/train': 1.7897305488586426} 08/31/2021 04:09:51 - INFO - __main__ - Step 82635: {'lr': 0.0002149112962370797, 'samples': 15865920, 'steps': 82634, 'loss/train': 1.9024474620819092} 08/31/2021 04:09:53 - INFO - __main__ - Step 82636: {'lr': 0.0002149060420306648, 'samples': 15866112, 'steps': 82635, 'loss/train': 1.4506603479385376} 08/31/2021 04:09:53 - INFO - __main__ - Step 82637: {'lr': 0.00021490078784006263, 'samples': 15866304, 'steps': 82636, 'loss/train': 1.423722267150879} 08/31/2021 04:09:54 - INFO - __main__ - Step 82638: {'lr': 0.0002148955336652756, 'samples': 15866496, 'steps': 82637, 'loss/train': 1.754095435142517} 08/31/2021 04:09:54 - INFO - __main__ - Step 82639: {'lr': 0.0002148902795063061, 'samples': 15866688, 'steps': 82638, 'loss/train': 0.6503499746322632} 08/31/2021 04:09:55 - INFO - __main__ - Step 82640: {'lr': 0.0002148850253631565, 'samples': 15866880, 'steps': 82639, 'loss/train': 1.2823461294174194} 08/31/2021 04:09:55 - INFO - __main__ - Step 82641: {'lr': 0.0002148797712358292, 'samples': 15867072, 'steps': 82640, 'loss/train': 1.5009243488311768} 08/31/2021 04:09:56 - INFO - __main__ - Step 82642: {'lr': 0.00021487451712432653, 'samples': 15867264, 'steps': 82641, 'loss/train': 0.11417749524116516} 08/31/2021 04:09:57 - INFO - __main__ - Step 82643: {'lr': 0.00021486926302865085, 'samples': 15867456, 'steps': 82642, 'loss/train': 1.4507277011871338} 08/31/2021 04:09:57 - INFO - __main__ - Step 82644: {'lr': 0.0002148640089488045, 'samples': 15867648, 'steps': 82643, 'loss/train': 1.5994418859481812} 08/31/2021 04:09:58 - INFO - __main__ - Step 82645: {'lr': 0.0002148587548847899, 'samples': 15867840, 'steps': 82644, 'loss/train': 0.6938914656639099} 08/31/2021 04:09:58 - INFO - __main__ - Step 82646: {'lr': 0.00021485350083660942, 'samples': 15868032, 'steps': 82645, 'loss/train': 1.1271976232528687} 08/31/2021 04:10:00 - INFO - __main__ - Step 82647: {'lr': 0.0002148482468042654, 'samples': 15868224, 'steps': 82646, 'loss/train': 1.7231653928756714} 08/31/2021 04:10:00 - INFO - __main__ - Step 82648: {'lr': 0.00021484299278776023, 'samples': 15868416, 'steps': 82647, 'loss/train': 0.11219700425863266} 08/31/2021 04:10:00 - INFO - __main__ - Step 82649: {'lr': 0.00021483773878709625, 'samples': 15868608, 'steps': 82648, 'loss/train': 1.46506667137146} 08/31/2021 04:10:01 - INFO - __main__ - Step 82650: {'lr': 0.0002148324848022759, 'samples': 15868800, 'steps': 82649, 'loss/train': 0.6044778227806091} 08/31/2021 04:10:01 - INFO - __main__ - Step 82651: {'lr': 0.00021482723083330143, 'samples': 15868992, 'steps': 82650, 'loss/train': 1.1989864110946655} 08/31/2021 04:10:03 - INFO - __main__ - Step 82652: {'lr': 0.00021482197688017527, 'samples': 15869184, 'steps': 82651, 'loss/train': 0.9284889698028564} 08/31/2021 04:10:03 - INFO - __main__ - Step 82653: {'lr': 0.00021481672294289982, 'samples': 15869376, 'steps': 82652, 'loss/train': 1.3663153648376465} 08/31/2021 04:10:04 - INFO - __main__ - Step 82654: {'lr': 0.00021481146902147742, 'samples': 15869568, 'steps': 82653, 'loss/train': 1.4998806715011597} 08/31/2021 04:10:04 - INFO - __main__ - Step 82655: {'lr': 0.00021480621511591036, 'samples': 15869760, 'steps': 82654, 'loss/train': 1.6487606763839722} 08/31/2021 04:10:04 - INFO - __main__ - Step 82656: {'lr': 0.00021480096122620114, 'samples': 15869952, 'steps': 82655, 'loss/train': 1.4818531274795532} 08/31/2021 04:10:05 - INFO - __main__ - Step 82657: {'lr': 0.00021479570735235198, 'samples': 15870144, 'steps': 82656, 'loss/train': 1.0021746158599854} 08/31/2021 04:10:06 - INFO - __main__ - Step 82658: {'lr': 0.0002147904534943654, 'samples': 15870336, 'steps': 82657, 'loss/train': 1.5310157537460327} 08/31/2021 04:10:07 - INFO - __main__ - Step 82659: {'lr': 0.00021478519965224368, 'samples': 15870528, 'steps': 82658, 'loss/train': 0.6350890398025513} 08/31/2021 04:10:07 - INFO - __main__ - Step 82660: {'lr': 0.0002147799458259892, 'samples': 15870720, 'steps': 82659, 'loss/train': 1.8326317071914673} 08/31/2021 04:10:07 - INFO - __main__ - Step 82661: {'lr': 0.00021477469201560434, 'samples': 15870912, 'steps': 82660, 'loss/train': 1.4836969375610352} 08/31/2021 04:10:08 - INFO - __main__ - Step 82662: {'lr': 0.00021476943822109146, 'samples': 15871104, 'steps': 82661, 'loss/train': 1.5019646883010864} 08/31/2021 04:10:08 - INFO - __main__ - Step 82663: {'lr': 0.00021476418444245297, 'samples': 15871296, 'steps': 82662, 'loss/train': 1.8352347612380981} 08/31/2021 04:10:10 - INFO - __main__ - Step 82664: {'lr': 0.00021475893067969122, 'samples': 15871488, 'steps': 82663, 'loss/train': 1.0317623615264893} 08/31/2021 04:10:10 - INFO - __main__ - Step 82665: {'lr': 0.00021475367693280845, 'samples': 15871680, 'steps': 82664, 'loss/train': 1.2991183996200562} 08/31/2021 04:10:10 - INFO - __main__ - Step 82666: {'lr': 0.00021474842320180716, 'samples': 15871872, 'steps': 82665, 'loss/train': 1.2498552799224854} 08/31/2021 04:10:11 - INFO - __main__ - Step 82667: {'lr': 0.0002147431694866897, 'samples': 15872064, 'steps': 82666, 'loss/train': 1.5600947141647339} 08/31/2021 04:10:11 - INFO - __main__ - Step 82668: {'lr': 0.0002147379157874584, 'samples': 15872256, 'steps': 82667, 'loss/train': 1.6168227195739746} 08/31/2021 04:10:13 - INFO - __main__ - Step 82669: {'lr': 0.00021473266210411565, 'samples': 15872448, 'steps': 82668, 'loss/train': 1.680130958557129} 08/31/2021 04:10:13 - INFO - __main__ - Step 82670: {'lr': 0.00021472740843666384, 'samples': 15872640, 'steps': 82669, 'loss/train': 1.5827038288116455} 08/31/2021 04:10:14 - INFO - __main__ - Step 82671: {'lr': 0.00021472215478510531, 'samples': 15872832, 'steps': 82670, 'loss/train': 1.3379690647125244} 08/31/2021 04:10:14 - INFO - __main__ - Step 82672: {'lr': 0.00021471690114944242, 'samples': 15873024, 'steps': 82671, 'loss/train': 1.0586503744125366} 08/31/2021 04:10:14 - INFO - __main__ - Step 82673: {'lr': 0.00021471164752967755, 'samples': 15873216, 'steps': 82672, 'loss/train': 2.120755434036255} 08/31/2021 04:10:16 - INFO - __main__ - Step 82674: {'lr': 0.00021470639392581309, 'samples': 15873408, 'steps': 82673, 'loss/train': 0.8521180748939514} 08/31/2021 04:10:16 - INFO - __main__ - Step 82675: {'lr': 0.00021470114033785137, 'samples': 15873600, 'steps': 82674, 'loss/train': 1.4038851261138916} 08/31/2021 04:10:17 - INFO - __main__ - Step 82676: {'lr': 0.00021469588676579476, 'samples': 15873792, 'steps': 82675, 'loss/train': 0.9344996809959412} 08/31/2021 04:10:17 - INFO - __main__ - Step 82677: {'lr': 0.00021469063320964576, 'samples': 15873984, 'steps': 82676, 'loss/train': 1.0922330617904663} 08/31/2021 04:10:17 - INFO - __main__ - Step 82678: {'lr': 0.00021468537966940648, 'samples': 15874176, 'steps': 82677, 'loss/train': 1.0769233703613281} 08/31/2021 04:10:19 - INFO - __main__ - Step 82679: {'lr': 0.0002146801261450795, 'samples': 15874368, 'steps': 82678, 'loss/train': 1.66250479221344} 08/31/2021 04:10:19 - INFO - __main__ - Step 82680: {'lr': 0.000214674872636667, 'samples': 15874560, 'steps': 82679, 'loss/train': 0.9078148603439331} 08/31/2021 04:10:20 - INFO - __main__ - Step 82681: {'lr': 0.00021466961914417155, 'samples': 15874752, 'steps': 82680, 'loss/train': 1.1554841995239258} 08/31/2021 04:10:20 - INFO - __main__ - Step 82682: {'lr': 0.00021466436566759537, 'samples': 15874944, 'steps': 82681, 'loss/train': 0.7110564112663269} 08/31/2021 04:10:20 - INFO - __main__ - Step 82683: {'lr': 0.0002146591122069409, 'samples': 15875136, 'steps': 82682, 'loss/train': 1.1229249238967896} 08/31/2021 04:10:22 - INFO - __main__ - Step 82684: {'lr': 0.0002146538587622105, 'samples': 15875328, 'steps': 82683, 'loss/train': 1.4350206851959229} 08/31/2021 04:10:22 - INFO - __main__ - Step 82685: {'lr': 0.0002146486053334065, 'samples': 15875520, 'steps': 82684, 'loss/train': 0.5688480734825134} 08/31/2021 04:10:22 - INFO - __main__ - Step 82686: {'lr': 0.0002146433519205313, 'samples': 15875712, 'steps': 82685, 'loss/train': 1.8218528032302856} 08/31/2021 04:10:23 - INFO - __main__ - Step 82687: {'lr': 0.00021463809852358728, 'samples': 15875904, 'steps': 82686, 'loss/train': 1.6487114429473877} 08/31/2021 04:10:23 - INFO - __main__ - Step 82688: {'lr': 0.00021463284514257677, 'samples': 15876096, 'steps': 82687, 'loss/train': 1.7092759609222412} 08/31/2021 04:10:25 - INFO - __main__ - Step 82689: {'lr': 0.0002146275917775022, 'samples': 15876288, 'steps': 82688, 'loss/train': 1.1756316423416138} 08/31/2021 04:10:26 - INFO - __main__ - Step 82690: {'lr': 0.00021462233842836593, 'samples': 15876480, 'steps': 82689, 'loss/train': 1.2467031478881836} 08/31/2021 04:10:26 - INFO - __main__ - Step 82691: {'lr': 0.0002146170850951702, 'samples': 15876672, 'steps': 82690, 'loss/train': 1.753489375114441} 08/31/2021 04:10:27 - INFO - __main__ - Step 82692: {'lr': 0.00021461183177791748, 'samples': 15876864, 'steps': 82691, 'loss/train': 0.07943687587976456} 08/31/2021 04:10:27 - INFO - __main__ - Step 82693: {'lr': 0.00021460657847661012, 'samples': 15877056, 'steps': 82692, 'loss/train': 1.6053698062896729} 08/31/2021 04:10:29 - INFO - __main__ - Step 82694: {'lr': 0.00021460132519125047, 'samples': 15877248, 'steps': 82693, 'loss/train': 1.3176488876342773} 08/31/2021 04:10:29 - INFO - __main__ - Step 82695: {'lr': 0.00021459607192184094, 'samples': 15877440, 'steps': 82694, 'loss/train': 1.0879582166671753} 08/31/2021 04:10:29 - INFO - __main__ - Step 82696: {'lr': 0.00021459081866838386, 'samples': 15877632, 'steps': 82695, 'loss/train': 1.150633454322815} 08/31/2021 04:10:30 - INFO - __main__ - Step 82697: {'lr': 0.00021458556543088163, 'samples': 15877824, 'steps': 82696, 'loss/train': 0.9265128970146179} 08/31/2021 04:10:30 - INFO - __main__ - Step 82698: {'lr': 0.0002145803122093366, 'samples': 15878016, 'steps': 82697, 'loss/train': 1.6138627529144287} 08/31/2021 04:10:31 - INFO - __main__ - Step 82699: {'lr': 0.0002145750590037511, 'samples': 15878208, 'steps': 82698, 'loss/train': 0.9025946259498596} 08/31/2021 04:10:32 - INFO - __main__ - Step 82700: {'lr': 0.00021456980581412754, 'samples': 15878400, 'steps': 82699, 'loss/train': 1.032547950744629} 08/31/2021 04:10:32 - INFO - __main__ - Step 82701: {'lr': 0.00021456455264046831, 'samples': 15878592, 'steps': 82700, 'loss/train': 0.3145556151866913} 08/31/2021 04:10:33 - INFO - __main__ - Step 82702: {'lr': 0.00021455929948277573, 'samples': 15878784, 'steps': 82701, 'loss/train': 0.7822951078414917} 08/31/2021 04:10:33 - INFO - __main__ - Step 82703: {'lr': 0.0002145540463410522, 'samples': 15878976, 'steps': 82702, 'loss/train': 1.4359420537948608} 08/31/2021 04:10:34 - INFO - __main__ - Step 82704: {'lr': 0.00021454879321530012, 'samples': 15879168, 'steps': 82703, 'loss/train': 1.4257712364196777} 08/31/2021 04:10:35 - INFO - __main__ - Step 82705: {'lr': 0.00021454354010552173, 'samples': 15879360, 'steps': 82704, 'loss/train': 1.1485689878463745} 08/31/2021 04:10:35 - INFO - __main__ - Step 82706: {'lr': 0.00021453828701171952, 'samples': 15879552, 'steps': 82705, 'loss/train': 2.7848737239837646} 08/31/2021 04:10:36 - INFO - __main__ - Step 82707: {'lr': 0.00021453303393389575, 'samples': 15879744, 'steps': 82706, 'loss/train': 1.2871116399765015} 08/31/2021 04:10:36 - INFO - __main__ - Step 82708: {'lr': 0.0002145277808720529, 'samples': 15879936, 'steps': 82707, 'loss/train': 0.24509364366531372} 08/31/2021 04:10:37 - INFO - __main__ - Step 82709: {'lr': 0.0002145225278261932, 'samples': 15880128, 'steps': 82708, 'loss/train': 1.52230703830719} 08/31/2021 04:10:38 - INFO - __main__ - Step 82710: {'lr': 0.00021451727479631917, 'samples': 15880320, 'steps': 82709, 'loss/train': 1.348433494567871} 08/31/2021 04:10:38 - INFO - __main__ - Step 82711: {'lr': 0.0002145120217824331, 'samples': 15880512, 'steps': 82710, 'loss/train': 0.9346003532409668} 08/31/2021 04:10:39 - INFO - __main__ - Step 82712: {'lr': 0.00021450676878453736, 'samples': 15880704, 'steps': 82711, 'loss/train': 2.0569822788238525} 08/31/2021 04:10:39 - INFO - __main__ - Step 82713: {'lr': 0.0002145015158026343, 'samples': 15880896, 'steps': 82712, 'loss/train': 0.062371522188186646} 08/31/2021 04:10:39 - INFO - __main__ - Step 82714: {'lr': 0.00021449626283672634, 'samples': 15881088, 'steps': 82713, 'loss/train': 1.2037243843078613} 08/31/2021 04:10:41 - INFO - __main__ - Step 82715: {'lr': 0.0002144910098868158, 'samples': 15881280, 'steps': 82714, 'loss/train': 0.7933821678161621} 08/31/2021 04:10:41 - INFO - __main__ - Step 82716: {'lr': 0.00021448575695290508, 'samples': 15881472, 'steps': 82715, 'loss/train': 1.0071194171905518} 08/31/2021 04:10:42 - INFO - __main__ - Step 82717: {'lr': 0.00021448050403499662, 'samples': 15881664, 'steps': 82716, 'loss/train': 0.9775266647338867} 08/31/2021 04:10:42 - INFO - __main__ - Step 82718: {'lr': 0.0002144752511330926, 'samples': 15881856, 'steps': 82717, 'loss/train': 1.4858547449111938} 08/31/2021 04:10:43 - INFO - __main__ - Step 82719: {'lr': 0.0002144699982471955, 'samples': 15882048, 'steps': 82718, 'loss/train': 0.7082375288009644} 08/31/2021 04:10:44 - INFO - __main__ - Step 82720: {'lr': 0.00021446474537730763, 'samples': 15882240, 'steps': 82719, 'loss/train': 1.4561576843261719} 08/31/2021 04:10:44 - INFO - __main__ - Step 82721: {'lr': 0.0002144594925234314, 'samples': 15882432, 'steps': 82720, 'loss/train': 1.4660964012145996} 08/31/2021 04:10:45 - INFO - __main__ - Step 82722: {'lr': 0.0002144542396855692, 'samples': 15882624, 'steps': 82721, 'loss/train': 1.9564146995544434} 08/31/2021 04:10:45 - INFO - __main__ - Step 82723: {'lr': 0.00021444898686372337, 'samples': 15882816, 'steps': 82722, 'loss/train': 1.0364798307418823} 08/31/2021 04:10:45 - INFO - __main__ - Step 82724: {'lr': 0.00021444373405789623, 'samples': 15883008, 'steps': 82723, 'loss/train': 1.2210556268692017} 08/31/2021 04:10:47 - INFO - __main__ - Step 82725: {'lr': 0.00021443848126809028, 'samples': 15883200, 'steps': 82724, 'loss/train': 1.8382643461227417} 08/31/2021 04:10:47 - INFO - __main__ - Step 82726: {'lr': 0.00021443322849430774, 'samples': 15883392, 'steps': 82725, 'loss/train': 1.9600032567977905} 08/31/2021 04:10:48 - INFO - __main__ - Step 82727: {'lr': 0.00021442797573655104, 'samples': 15883584, 'steps': 82726, 'loss/train': 2.172715187072754} 08/31/2021 04:10:48 - INFO - __main__ - Step 82728: {'lr': 0.00021442272299482257, 'samples': 15883776, 'steps': 82727, 'loss/train': 1.700068712234497} 08/31/2021 04:10:48 - INFO - __main__ - Step 82729: {'lr': 0.00021441747026912467, 'samples': 15883968, 'steps': 82728, 'loss/train': 1.16815984249115} 08/31/2021 04:10:50 - INFO - __main__ - Step 82730: {'lr': 0.00021441221755945968, 'samples': 15884160, 'steps': 82729, 'loss/train': 1.2694119215011597} 08/31/2021 04:10:50 - INFO - __main__ - Step 82731: {'lr': 0.00021440696486583013, 'samples': 15884352, 'steps': 82730, 'loss/train': 1.2457411289215088} 08/31/2021 04:10:51 - INFO - __main__ - Step 82732: {'lr': 0.00021440171218823815, 'samples': 15884544, 'steps': 82731, 'loss/train': 0.7605500221252441} 08/31/2021 04:10:51 - INFO - __main__ - Step 82733: {'lr': 0.00021439645952668618, 'samples': 15884736, 'steps': 82732, 'loss/train': 1.746116042137146} 08/31/2021 04:10:51 - INFO - __main__ - Step 82734: {'lr': 0.00021439120688117663, 'samples': 15884928, 'steps': 82733, 'loss/train': 0.9674834609031677} 08/31/2021 04:10:53 - INFO - __main__ - Step 82735: {'lr': 0.00021438595425171187, 'samples': 15885120, 'steps': 82734, 'loss/train': 1.469176173210144} 08/31/2021 04:10:53 - INFO - __main__ - Step 82736: {'lr': 0.00021438070163829422, 'samples': 15885312, 'steps': 82735, 'loss/train': 1.0336323976516724} 08/31/2021 04:10:54 - INFO - __main__ - Step 82737: {'lr': 0.0002143754490409261, 'samples': 15885504, 'steps': 82736, 'loss/train': 1.604997992515564} 08/31/2021 04:10:54 - INFO - __main__ - Step 82738: {'lr': 0.00021437019645960986, 'samples': 15885696, 'steps': 82737, 'loss/train': 1.4780629873275757} 08/31/2021 04:10:54 - INFO - __main__ - Step 82739: {'lr': 0.00021436494389434786, 'samples': 15885888, 'steps': 82738, 'loss/train': 1.480204701423645} 08/31/2021 04:10:57 - INFO - __main__ - Step 82740: {'lr': 0.00021435969134514244, 'samples': 15886080, 'steps': 82739, 'loss/train': 1.2029831409454346} 08/31/2021 04:10:57 - INFO - __main__ - Step 82741: {'lr': 0.00021435443881199598, 'samples': 15886272, 'steps': 82740, 'loss/train': 2.368699789047241} 08/31/2021 04:10:57 - INFO - __main__ - Step 82742: {'lr': 0.0002143491862949109, 'samples': 15886464, 'steps': 82741, 'loss/train': 1.1901730298995972} 08/31/2021 04:10:58 - INFO - __main__ - Step 82743: {'lr': 0.0002143439337938895, 'samples': 15886656, 'steps': 82742, 'loss/train': 0.7373120784759521} 08/31/2021 04:10:58 - INFO - __main__ - Step 82744: {'lr': 0.0002143386813089343, 'samples': 15886848, 'steps': 82743, 'loss/train': 1.3701660633087158} 08/31/2021 04:10:58 - INFO - __main__ - Step 82745: {'lr': 0.0002143334288400474, 'samples': 15887040, 'steps': 82744, 'loss/train': 1.1371054649353027} 08/31/2021 04:11:00 - INFO - __main__ - Step 82746: {'lr': 0.00021432817638723136, 'samples': 15887232, 'steps': 82745, 'loss/train': 1.3027249574661255} 08/31/2021 04:11:01 - INFO - __main__ - Step 82747: {'lr': 0.00021432292395048846, 'samples': 15887424, 'steps': 82746, 'loss/train': 1.353400707244873} 08/31/2021 04:11:01 - INFO - __main__ - Step 82748: {'lr': 0.0002143176715298211, 'samples': 15887616, 'steps': 82747, 'loss/train': 1.065402865409851} 08/31/2021 04:11:01 - INFO - __main__ - Step 82749: {'lr': 0.00021431241912523165, 'samples': 15887808, 'steps': 82748, 'loss/train': 1.8596758842468262} 08/31/2021 04:11:02 - INFO - __main__ - Step 82750: {'lr': 0.00021430716673672247, 'samples': 15888000, 'steps': 82749, 'loss/train': 0.2431895136833191} 08/31/2021 04:11:03 - INFO - __main__ - Step 82751: {'lr': 0.00021430191436429594, 'samples': 15888192, 'steps': 82750, 'loss/train': 0.9380027651786804} 08/31/2021 04:11:04 - INFO - __main__ - Step 82752: {'lr': 0.0002142966620079544, 'samples': 15888384, 'steps': 82751, 'loss/train': 0.43198755383491516} 08/31/2021 04:11:04 - INFO - __main__ - Step 82753: {'lr': 0.00021429140966770026, 'samples': 15888576, 'steps': 82752, 'loss/train': 0.3689103126525879} 08/31/2021 04:11:04 - INFO - __main__ - Step 82754: {'lr': 0.00021428615734353585, 'samples': 15888768, 'steps': 82753, 'loss/train': 0.9036312103271484} 08/31/2021 04:11:05 - INFO - __main__ - Step 82755: {'lr': 0.00021428090503546358, 'samples': 15888960, 'steps': 82754, 'loss/train': 2.6574957370758057} 08/31/2021 04:11:06 - INFO - __main__ - Step 82756: {'lr': 0.00021427565274348575, 'samples': 15889152, 'steps': 82755, 'loss/train': 0.8084809184074402} 08/31/2021 04:11:07 - INFO - __main__ - Step 82757: {'lr': 0.0002142704004676048, 'samples': 15889344, 'steps': 82756, 'loss/train': 1.6221108436584473} 08/31/2021 04:11:07 - INFO - __main__ - Step 82758: {'lr': 0.000214265148207823, 'samples': 15889536, 'steps': 82757, 'loss/train': 1.3182811737060547} 08/31/2021 04:11:07 - INFO - __main__ - Step 82759: {'lr': 0.00021425989596414279, 'samples': 15889728, 'steps': 82758, 'loss/train': 0.523614764213562} 08/31/2021 04:11:08 - INFO - __main__ - Step 82760: {'lr': 0.0002142546437365665, 'samples': 15889920, 'steps': 82759, 'loss/train': 1.0840139389038086} 08/31/2021 04:11:09 - INFO - __main__ - Step 82761: {'lr': 0.00021424939152509654, 'samples': 15890112, 'steps': 82760, 'loss/train': 1.2202465534210205} 08/31/2021 04:11:10 - INFO - __main__ - Step 82762: {'lr': 0.0002142441393297352, 'samples': 15890304, 'steps': 82761, 'loss/train': 1.2499815225601196} 08/31/2021 04:11:10 - INFO - __main__ - Step 82763: {'lr': 0.00021423888715048494, 'samples': 15890496, 'steps': 82762, 'loss/train': 0.06899399310350418} 08/31/2021 04:11:11 - INFO - __main__ - Step 82764: {'lr': 0.0002142336349873481, 'samples': 15890688, 'steps': 82763, 'loss/train': 1.2811126708984375} 08/31/2021 04:11:11 - INFO - __main__ - Step 82765: {'lr': 0.00021422838284032702, 'samples': 15890880, 'steps': 82764, 'loss/train': 1.5257452726364136} 08/31/2021 04:11:13 - INFO - __main__ - Step 82766: {'lr': 0.00021422313070942412, 'samples': 15891072, 'steps': 82765, 'loss/train': 1.0889742374420166} 08/31/2021 04:11:13 - INFO - __main__ - Step 82767: {'lr': 0.0002142178785946417, 'samples': 15891264, 'steps': 82766, 'loss/train': 1.105093002319336} 08/31/2021 04:11:14 - INFO - __main__ - Step 82768: {'lr': 0.0002142126264959821, 'samples': 15891456, 'steps': 82767, 'loss/train': 1.3515466451644897} 08/31/2021 04:11:14 - INFO - __main__ - Step 82769: {'lr': 0.0002142073744134478, 'samples': 15891648, 'steps': 82768, 'loss/train': 1.0670299530029297} 08/31/2021 04:11:14 - INFO - __main__ - Step 82770: {'lr': 0.00021420212234704106, 'samples': 15891840, 'steps': 82769, 'loss/train': 0.960314929485321} 08/31/2021 04:11:15 - INFO - __main__ - Step 82771: {'lr': 0.0002141968702967644, 'samples': 15892032, 'steps': 82770, 'loss/train': 1.6743433475494385} 08/31/2021 04:11:16 - INFO - __main__ - Step 82772: {'lr': 0.00021419161826261997, 'samples': 15892224, 'steps': 82771, 'loss/train': 1.2312545776367188} 08/31/2021 04:11:17 - INFO - __main__ - Step 82773: {'lr': 0.00021418636624461024, 'samples': 15892416, 'steps': 82772, 'loss/train': 1.377009630203247} 08/31/2021 04:11:17 - INFO - __main__ - Step 82774: {'lr': 0.00021418111424273759, 'samples': 15892608, 'steps': 82773, 'loss/train': 0.9395130276679993} 08/31/2021 04:11:17 - INFO - __main__ - Step 82775: {'lr': 0.0002141758622570044, 'samples': 15892800, 'steps': 82774, 'loss/train': 0.08978397399187088} 08/31/2021 04:11:18 - INFO - __main__ - Step 82776: {'lr': 0.00021417061028741302, 'samples': 15892992, 'steps': 82775, 'loss/train': 1.6309731006622314} 08/31/2021 04:11:19 - INFO - __main__ - Step 82777: {'lr': 0.0002141653583339658, 'samples': 15893184, 'steps': 82776, 'loss/train': 0.6139726042747498} 08/31/2021 04:11:20 - INFO - __main__ - Step 82778: {'lr': 0.0002141601063966651, 'samples': 15893376, 'steps': 82777, 'loss/train': 0.9704306721687317} 08/31/2021 04:11:20 - INFO - __main__ - Step 82779: {'lr': 0.0002141548544755133, 'samples': 15893568, 'steps': 82778, 'loss/train': 1.0600252151489258} 08/31/2021 04:11:20 - INFO - __main__ - Step 82780: {'lr': 0.0002141496025705128, 'samples': 15893760, 'steps': 82779, 'loss/train': 1.8181872367858887} 08/31/2021 04:11:21 - INFO - __main__ - Step 82781: {'lr': 0.0002141443506816659, 'samples': 15893952, 'steps': 82780, 'loss/train': 1.02351975440979} 08/31/2021 04:11:22 - INFO - __main__ - Step 82782: {'lr': 0.00021413909880897502, 'samples': 15894144, 'steps': 82781, 'loss/train': 0.22727227210998535} 08/31/2021 04:11:23 - INFO - __main__ - Step 82783: {'lr': 0.0002141338469524425, 'samples': 15894336, 'steps': 82782, 'loss/train': 1.187574028968811} 08/31/2021 04:11:23 - INFO - __main__ - Step 82784: {'lr': 0.00021412859511207077, 'samples': 15894528, 'steps': 82783, 'loss/train': 1.344214677810669} 08/31/2021 04:11:23 - INFO - __main__ - Step 82785: {'lr': 0.0002141233432878621, 'samples': 15894720, 'steps': 82784, 'loss/train': 1.0515292882919312} 08/31/2021 04:11:24 - INFO - __main__ - Step 82786: {'lr': 0.0002141180914798189, 'samples': 15894912, 'steps': 82785, 'loss/train': 1.0449458360671997} 08/31/2021 04:11:25 - INFO - __main__ - Step 82787: {'lr': 0.0002141128396879436, 'samples': 15895104, 'steps': 82786, 'loss/train': 1.4051812887191772} 08/31/2021 04:11:25 - INFO - __main__ - Step 82788: {'lr': 0.0002141075879122384, 'samples': 15895296, 'steps': 82787, 'loss/train': 1.8452191352844238} 08/31/2021 04:11:26 - INFO - __main__ - Step 82789: {'lr': 0.0002141023361527058, 'samples': 15895488, 'steps': 82788, 'loss/train': 1.6081914901733398} 08/31/2021 04:11:26 - INFO - __main__ - Step 82790: {'lr': 0.00021409708440934812, 'samples': 15895680, 'steps': 82789, 'loss/train': 1.6631406545639038} 08/31/2021 04:11:26 - INFO - __main__ - Step 82791: {'lr': 0.00021409183268216776, 'samples': 15895872, 'steps': 82790, 'loss/train': 1.3501405715942383} 08/31/2021 04:11:27 - INFO - __main__ - Step 82792: {'lr': 0.00021408658097116703, 'samples': 15896064, 'steps': 82791, 'loss/train': 0.4496173858642578} 08/31/2021 04:11:28 - INFO - __main__ - Step 82793: {'lr': 0.00021408132927634835, 'samples': 15896256, 'steps': 82792, 'loss/train': 1.035050868988037} 08/31/2021 04:11:29 - INFO - __main__ - Step 82794: {'lr': 0.0002140760775977141, 'samples': 15896448, 'steps': 82793, 'loss/train': 1.2004072666168213} 08/31/2021 04:11:29 - INFO - __main__ - Step 82795: {'lr': 0.00021407082593526657, 'samples': 15896640, 'steps': 82794, 'loss/train': 1.3410389423370361} 08/31/2021 04:11:30 - INFO - __main__ - Step 82796: {'lr': 0.00021406557428900819, 'samples': 15896832, 'steps': 82795, 'loss/train': 0.9770579934120178} 08/31/2021 04:11:30 - INFO - __main__ - Step 82797: {'lr': 0.00021406032265894128, 'samples': 15897024, 'steps': 82796, 'loss/train': 1.3106966018676758} 08/31/2021 04:11:32 - INFO - __main__ - Step 82798: {'lr': 0.00021405507104506837, 'samples': 15897216, 'steps': 82797, 'loss/train': 1.1548397541046143} 08/31/2021 04:11:32 - INFO - __main__ - Step 82799: {'lr': 0.0002140498194473916, 'samples': 15897408, 'steps': 82798, 'loss/train': 1.3961929082870483} 08/31/2021 04:11:33 - INFO - __main__ - Step 82800: {'lr': 0.00021404456786591343, 'samples': 15897600, 'steps': 82799, 'loss/train': 0.6845840811729431} 08/31/2021 04:11:33 - INFO - __main__ - Step 82801: {'lr': 0.00021403931630063617, 'samples': 15897792, 'steps': 82800, 'loss/train': 1.1205103397369385} 08/31/2021 04:11:34 - INFO - __main__ - Step 82802: {'lr': 0.00021403406475156228, 'samples': 15897984, 'steps': 82801, 'loss/train': 1.1785413026809692} 08/31/2021 04:11:35 - INFO - __main__ - Step 82803: {'lr': 0.00021402881321869408, 'samples': 15898176, 'steps': 82802, 'loss/train': 1.2875362634658813} 08/31/2021 04:11:35 - INFO - __main__ - Step 82804: {'lr': 0.00021402356170203393, 'samples': 15898368, 'steps': 82803, 'loss/train': 1.0384877920150757} 08/31/2021 04:11:36 - INFO - __main__ - Step 82805: {'lr': 0.0002140183102015842, 'samples': 15898560, 'steps': 82804, 'loss/train': 1.4782137870788574} 08/31/2021 04:11:36 - INFO - __main__ - Step 82806: {'lr': 0.00021401305871734727, 'samples': 15898752, 'steps': 82805, 'loss/train': 1.2711092233657837} 08/31/2021 04:11:36 - INFO - __main__ - Step 82807: {'lr': 0.00021400780724932554, 'samples': 15898944, 'steps': 82806, 'loss/train': 1.7819527387619019} 08/31/2021 04:11:38 - INFO - __main__ - Step 82808: {'lr': 0.0002140025557975213, 'samples': 15899136, 'steps': 82807, 'loss/train': 1.1477601528167725} 08/31/2021 04:11:39 - INFO - __main__ - Step 82809: {'lr': 0.00021399730436193694, 'samples': 15899328, 'steps': 82808, 'loss/train': 1.2756624221801758} 08/31/2021 04:11:39 - INFO - __main__ - Step 82810: {'lr': 0.00021399205294257486, 'samples': 15899520, 'steps': 82809, 'loss/train': 1.7757847309112549} 08/31/2021 04:11:39 - INFO - __main__ - Step 82811: {'lr': 0.00021398680153943752, 'samples': 15899712, 'steps': 82810, 'loss/train': 1.0553765296936035} 08/31/2021 04:11:40 - INFO - __main__ - Step 82812: {'lr': 0.00021398155015252707, 'samples': 15899904, 'steps': 82811, 'loss/train': 1.3220547437667847} 08/31/2021 04:11:41 - INFO - __main__ - Step 82813: {'lr': 0.00021397629878184594, 'samples': 15900096, 'steps': 82812, 'loss/train': 1.0871453285217285} 08/31/2021 04:11:42 - INFO - __main__ - Step 82814: {'lr': 0.00021397104742739657, 'samples': 15900288, 'steps': 82813, 'loss/train': 1.6472582817077637} 08/31/2021 04:11:42 - INFO - __main__ - Step 82815: {'lr': 0.00021396579608918127, 'samples': 15900480, 'steps': 82814, 'loss/train': 1.189142107963562} 08/31/2021 04:11:42 - INFO - __main__ - Step 82816: {'lr': 0.00021396054476720245, 'samples': 15900672, 'steps': 82815, 'loss/train': 0.45187196135520935} 08/31/2021 04:11:43 - INFO - __main__ - Step 82817: {'lr': 0.00021395529346146243, 'samples': 15900864, 'steps': 82816, 'loss/train': 1.0933308601379395} 08/31/2021 04:11:44 - INFO - __main__ - Step 82818: {'lr': 0.0002139500421719636, 'samples': 15901056, 'steps': 82817, 'loss/train': 1.1512714624404907} 08/31/2021 04:11:45 - INFO - __main__ - Step 82819: {'lr': 0.00021394479089870832, 'samples': 15901248, 'steps': 82818, 'loss/train': 1.0234631299972534} 08/31/2021 04:11:45 - INFO - __main__ - Step 82820: {'lr': 0.00021393953964169896, 'samples': 15901440, 'steps': 82819, 'loss/train': 1.4793952703475952} 08/31/2021 04:11:45 - INFO - __main__ - Step 82821: {'lr': 0.0002139342884009379, 'samples': 15901632, 'steps': 82820, 'loss/train': 0.8631516098976135} 08/31/2021 04:11:46 - INFO - __main__ - Step 82822: {'lr': 0.00021392903717642748, 'samples': 15901824, 'steps': 82821, 'loss/train': 1.1548385620117188} 08/31/2021 04:11:46 - INFO - __main__ - Step 82823: {'lr': 0.00021392378596817008, 'samples': 15902016, 'steps': 82822, 'loss/train': 0.9988948702812195} 08/31/2021 04:11:48 - INFO - __main__ - Step 82824: {'lr': 0.0002139185347761681, 'samples': 15902208, 'steps': 82823, 'loss/train': 1.1942206621170044} 08/31/2021 04:11:48 - INFO - __main__ - Step 82825: {'lr': 0.00021391328360042394, 'samples': 15902400, 'steps': 82824, 'loss/train': 4.528920650482178} 08/31/2021 04:11:49 - INFO - __main__ - Step 82826: {'lr': 0.0002139080324409398, 'samples': 15902592, 'steps': 82825, 'loss/train': 0.9832924604415894} 08/31/2021 04:11:49 - INFO - __main__ - Step 82827: {'lr': 0.00021390278129771814, 'samples': 15902784, 'steps': 82826, 'loss/train': 1.3320013284683228} 08/31/2021 04:11:49 - INFO - __main__ - Step 82828: {'lr': 0.00021389753017076135, 'samples': 15902976, 'steps': 82827, 'loss/train': 1.0878665447235107} 08/31/2021 04:11:51 - INFO - __main__ - Step 82829: {'lr': 0.00021389227906007174, 'samples': 15903168, 'steps': 82828, 'loss/train': 0.2752847373485565} 08/31/2021 04:11:51 - INFO - __main__ - Step 82830: {'lr': 0.00021388702796565177, 'samples': 15903360, 'steps': 82829, 'loss/train': 1.1288853883743286} 08/31/2021 04:11:52 - INFO - __main__ - Step 82831: {'lr': 0.0002138817768875037, 'samples': 15903552, 'steps': 82830, 'loss/train': 1.7074466943740845} 08/31/2021 04:11:52 - INFO - __main__ - Step 82832: {'lr': 0.00021387652582562994, 'samples': 15903744, 'steps': 82831, 'loss/train': 0.2580782473087311} 08/31/2021 04:11:52 - INFO - __main__ - Step 82833: {'lr': 0.00021387127478003287, 'samples': 15903936, 'steps': 82832, 'loss/train': 1.3886505365371704} 08/31/2021 04:11:54 - INFO - __main__ - Step 82834: {'lr': 0.00021386602375071488, 'samples': 15904128, 'steps': 82833, 'loss/train': 0.8936673402786255} 08/31/2021 04:11:54 - INFO - __main__ - Step 82835: {'lr': 0.00021386077273767825, 'samples': 15904320, 'steps': 82834, 'loss/train': 1.2270121574401855} 08/31/2021 04:11:54 - INFO - __main__ - Step 82836: {'lr': 0.00021385552174092544, 'samples': 15904512, 'steps': 82835, 'loss/train': 0.6172914505004883} 08/31/2021 04:11:55 - INFO - __main__ - Step 82837: {'lr': 0.00021385027076045875, 'samples': 15904704, 'steps': 82836, 'loss/train': 1.1059411764144897} 08/31/2021 04:11:55 - INFO - __main__ - Step 82838: {'lr': 0.0002138450197962807, 'samples': 15904896, 'steps': 82837, 'loss/train': 0.6347883343696594} 08/31/2021 04:11:57 - INFO - __main__ - Step 82839: {'lr': 0.0002138397688483934, 'samples': 15905088, 'steps': 82838, 'loss/train': 1.3584831953048706} 08/31/2021 04:11:57 - INFO - __main__ - Step 82840: {'lr': 0.00021383451791679933, 'samples': 15905280, 'steps': 82839, 'loss/train': 1.2828656435012817} 08/31/2021 04:11:57 - INFO - __main__ - Step 82841: {'lr': 0.00021382926700150087, 'samples': 15905472, 'steps': 82840, 'loss/train': 1.0726369619369507} 08/31/2021 04:11:58 - INFO - __main__ - Step 82842: {'lr': 0.0002138240161025004, 'samples': 15905664, 'steps': 82841, 'loss/train': 0.30919551849365234} 08/31/2021 04:11:58 - INFO - __main__ - Step 82843: {'lr': 0.0002138187652198003, 'samples': 15905856, 'steps': 82842, 'loss/train': 1.1268678903579712} 08/31/2021 04:12:00 - INFO - __main__ - Step 82844: {'lr': 0.00021381351435340284, 'samples': 15906048, 'steps': 82843, 'loss/train': 1.040138840675354} 08/31/2021 04:12:01 - INFO - __main__ - Step 82845: {'lr': 0.00021380826350331052, 'samples': 15906240, 'steps': 82844, 'loss/train': 1.6305632591247559} 08/31/2021 04:12:01 - INFO - __main__ - Step 82846: {'lr': 0.00021380301266952557, 'samples': 15906432, 'steps': 82845, 'loss/train': 1.2782340049743652} 08/31/2021 04:12:01 - INFO - __main__ - Step 82847: {'lr': 0.00021379776185205047, 'samples': 15906624, 'steps': 82846, 'loss/train': 0.02220970019698143} 08/31/2021 04:12:02 - INFO - __main__ - Step 82848: {'lr': 0.00021379251105088754, 'samples': 15906816, 'steps': 82847, 'loss/train': 0.022461462765932083} 08/31/2021 04:12:02 - INFO - __main__ - Step 82849: {'lr': 0.0002137872602660391, 'samples': 15907008, 'steps': 82848, 'loss/train': 1.1802804470062256} 08/31/2021 04:12:02 - INFO - __main__ - Step 82850: {'lr': 0.0002137820094975076, 'samples': 15907200, 'steps': 82849, 'loss/train': 0.8127484321594238} 08/31/2021 04:12:04 - INFO - __main__ - Step 82851: {'lr': 0.00021377675874529537, 'samples': 15907392, 'steps': 82850, 'loss/train': 1.2948925495147705} 08/31/2021 04:12:05 - INFO - __main__ - Step 82852: {'lr': 0.00021377150800940486, 'samples': 15907584, 'steps': 82851, 'loss/train': 1.1719117164611816} 08/31/2021 04:12:05 - INFO - __main__ - Step 82853: {'lr': 0.00021376625728983828, 'samples': 15907776, 'steps': 82852, 'loss/train': 0.8069456219673157} 08/31/2021 04:12:06 - INFO - __main__ - Step 82854: {'lr': 0.00021376100658659802, 'samples': 15907968, 'steps': 82853, 'loss/train': 1.1216639280319214} 08/31/2021 04:12:06 - INFO - __main__ - Step 82855: {'lr': 0.00021375575589968653, 'samples': 15908160, 'steps': 82854, 'loss/train': 1.5154118537902832} 08/31/2021 04:12:07 - INFO - __main__ - Step 82856: {'lr': 0.0002137505052291061, 'samples': 15908352, 'steps': 82855, 'loss/train': 1.7821428775787354} 08/31/2021 04:12:08 - INFO - __main__ - Step 82857: {'lr': 0.00021374525457485915, 'samples': 15908544, 'steps': 82856, 'loss/train': 1.0975017547607422} 08/31/2021 04:12:08 - INFO - __main__ - Step 82858: {'lr': 0.00021374000393694804, 'samples': 15908736, 'steps': 82857, 'loss/train': 0.3881746828556061} 08/31/2021 04:12:09 - INFO - __main__ - Step 82859: {'lr': 0.00021373475331537512, 'samples': 15908928, 'steps': 82858, 'loss/train': 1.457929253578186} 08/31/2021 04:12:09 - INFO - __main__ - Step 82860: {'lr': 0.00021372950271014273, 'samples': 15909120, 'steps': 82859, 'loss/train': 0.593620240688324} 08/31/2021 04:12:10 - INFO - __main__ - Step 82861: {'lr': 0.00021372425212125333, 'samples': 15909312, 'steps': 82860, 'loss/train': 0.13941985368728638} 08/31/2021 04:12:11 - INFO - __main__ - Step 82862: {'lr': 0.00021371900154870915, 'samples': 15909504, 'steps': 82861, 'loss/train': 1.02889084815979} 08/31/2021 04:12:11 - INFO - __main__ - Step 82863: {'lr': 0.00021371375099251268, 'samples': 15909696, 'steps': 82862, 'loss/train': 1.4276225566864014} 08/31/2021 04:12:12 - INFO - __main__ - Step 82864: {'lr': 0.0002137085004526662, 'samples': 15909888, 'steps': 82863, 'loss/train': 1.0479239225387573} 08/31/2021 04:12:12 - INFO - __main__ - Step 82865: {'lr': 0.00021370324992917226, 'samples': 15910080, 'steps': 82864, 'loss/train': 1.087213158607483} 08/31/2021 04:12:13 - INFO - __main__ - Step 82866: {'lr': 0.00021369799942203295, 'samples': 15910272, 'steps': 82865, 'loss/train': 1.3976757526397705} 08/31/2021 04:12:14 - INFO - __main__ - Step 82867: {'lr': 0.00021369274893125073, 'samples': 15910464, 'steps': 82866, 'loss/train': 1.5743210315704346} 08/31/2021 04:12:14 - INFO - __main__ - Step 82868: {'lr': 0.00021368749845682803, 'samples': 15910656, 'steps': 82867, 'loss/train': 1.2093263864517212} 08/31/2021 04:12:15 - INFO - __main__ - Step 82869: {'lr': 0.00021368224799876717, 'samples': 15910848, 'steps': 82868, 'loss/train': 0.989073634147644} 08/31/2021 04:12:15 - INFO - __main__ - Step 82870: {'lr': 0.00021367699755707055, 'samples': 15911040, 'steps': 82869, 'loss/train': 0.7990376353263855} 08/31/2021 04:12:16 - INFO - __main__ - Step 82871: {'lr': 0.00021367174713174048, 'samples': 15911232, 'steps': 82870, 'loss/train': 0.8786953687667847} 08/31/2021 04:12:17 - INFO - __main__ - Step 82872: {'lr': 0.0002136664967227794, 'samples': 15911424, 'steps': 82871, 'loss/train': 1.5684144496917725} 08/31/2021 04:12:17 - INFO - __main__ - Step 82873: {'lr': 0.00021366124633018956, 'samples': 15911616, 'steps': 82872, 'loss/train': 0.3439192771911621} 08/31/2021 04:12:18 - INFO - __main__ - Step 82874: {'lr': 0.00021365599595397347, 'samples': 15911808, 'steps': 82873, 'loss/train': 1.4955697059631348} 08/31/2021 04:12:18 - INFO - __main__ - Step 82875: {'lr': 0.0002136507455941334, 'samples': 15912000, 'steps': 82874, 'loss/train': 0.6185488700866699} 08/31/2021 04:12:20 - INFO - __main__ - Step 82876: {'lr': 0.0002136454952506718, 'samples': 15912192, 'steps': 82875, 'loss/train': 1.1495379209518433} 08/31/2021 04:12:20 - INFO - __main__ - Step 82877: {'lr': 0.0002136402449235909, 'samples': 15912384, 'steps': 82876, 'loss/train': 0.07931777834892273} 08/31/2021 04:12:20 - INFO - __main__ - Step 82878: {'lr': 0.0002136349946128933, 'samples': 15912576, 'steps': 82877, 'loss/train': 1.0274823904037476} 08/31/2021 04:12:21 - INFO - __main__ - Step 82879: {'lr': 0.0002136297443185811, 'samples': 15912768, 'steps': 82878, 'loss/train': 0.9578185081481934} 08/31/2021 04:12:21 - INFO - __main__ - Step 82880: {'lr': 0.00021362449404065676, 'samples': 15912960, 'steps': 82879, 'loss/train': 1.2999248504638672} 08/31/2021 04:12:23 - INFO - __main__ - Step 82881: {'lr': 0.00021361924377912264, 'samples': 15913152, 'steps': 82880, 'loss/train': 1.2666505575180054} 08/31/2021 04:12:23 - INFO - __main__ - Step 82882: {'lr': 0.00021361399353398116, 'samples': 15913344, 'steps': 82881, 'loss/train': 1.8905689716339111} 08/31/2021 04:12:23 - INFO - __main__ - Step 82883: {'lr': 0.00021360874330523467, 'samples': 15913536, 'steps': 82882, 'loss/train': 1.3737339973449707} 08/31/2021 04:12:24 - INFO - __main__ - Step 82884: {'lr': 0.00021360349309288546, 'samples': 15913728, 'steps': 82883, 'loss/train': 0.44283849000930786} 08/31/2021 04:12:24 - INFO - __main__ - Step 82885: {'lr': 0.000213598242896936, 'samples': 15913920, 'steps': 82884, 'loss/train': 0.87423175573349} 08/31/2021 04:12:24 - INFO - __main__ - Step 82886: {'lr': 0.0002135929927173886, 'samples': 15914112, 'steps': 82885, 'loss/train': 0.6350866556167603} 08/31/2021 04:12:26 - INFO - __main__ - Step 82887: {'lr': 0.00021358774255424563, 'samples': 15914304, 'steps': 82886, 'loss/train': 1.4853554964065552} 08/31/2021 04:12:26 - INFO - __main__ - Step 82888: {'lr': 0.0002135824924075095, 'samples': 15914496, 'steps': 82887, 'loss/train': 1.216498613357544} 08/31/2021 04:12:27 - INFO - __main__ - Step 82889: {'lr': 0.00021357724227718253, 'samples': 15914688, 'steps': 82888, 'loss/train': 1.674655556678772} 08/31/2021 04:12:27 - INFO - __main__ - Step 82890: {'lr': 0.00021357199216326706, 'samples': 15914880, 'steps': 82889, 'loss/train': 1.3716167211532593} 08/31/2021 04:12:27 - INFO - __main__ - Step 82891: {'lr': 0.0002135667420657655, 'samples': 15915072, 'steps': 82890, 'loss/train': 2.3305323123931885} 08/31/2021 04:12:29 - INFO - __main__ - Step 82892: {'lr': 0.00021356149198468026, 'samples': 15915264, 'steps': 82891, 'loss/train': 1.2118176221847534} 08/31/2021 04:12:29 - INFO - __main__ - Step 82893: {'lr': 0.0002135562419200136, 'samples': 15915456, 'steps': 82892, 'loss/train': 1.026017189025879} 08/31/2021 04:12:30 - INFO - __main__ - Step 82894: {'lr': 0.00021355099187176792, 'samples': 15915648, 'steps': 82893, 'loss/train': 1.2950804233551025} 08/31/2021 04:12:30 - INFO - __main__ - Step 82895: {'lr': 0.00021354574183994558, 'samples': 15915840, 'steps': 82894, 'loss/train': 1.150290846824646} 08/31/2021 04:12:31 - INFO - __main__ - Step 82896: {'lr': 0.000213540491824549, 'samples': 15916032, 'steps': 82895, 'loss/train': 1.0802773237228394} 08/31/2021 04:12:32 - INFO - __main__ - Step 82897: {'lr': 0.0002135352418255805, 'samples': 15916224, 'steps': 82896, 'loss/train': 1.133555293083191} 08/31/2021 04:12:33 - INFO - __main__ - Step 82898: {'lr': 0.00021352999184304244, 'samples': 15916416, 'steps': 82897, 'loss/train': 1.2935771942138672} 08/31/2021 04:12:33 - INFO - __main__ - Step 82899: {'lr': 0.00021352474187693723, 'samples': 15916608, 'steps': 82898, 'loss/train': 0.8395490050315857} 08/31/2021 04:12:33 - INFO - __main__ - Step 82900: {'lr': 0.00021351949192726727, 'samples': 15916800, 'steps': 82899, 'loss/train': 1.1363575458526611} 08/31/2021 04:12:34 - INFO - __main__ - Step 82901: {'lr': 0.00021351424199403477, 'samples': 15916992, 'steps': 82900, 'loss/train': 1.4903098344802856} 08/31/2021 04:12:36 - INFO - __main__ - Step 82902: {'lr': 0.00021350899207724222, 'samples': 15917184, 'steps': 82901, 'loss/train': 1.8810460567474365} 08/31/2021 04:12:36 - INFO - __main__ - Step 82903: {'lr': 0.00021350374217689194, 'samples': 15917376, 'steps': 82902, 'loss/train': 1.1668519973754883} 08/31/2021 04:12:37 - INFO - __main__ - Step 82904: {'lr': 0.0002134984922929863, 'samples': 15917568, 'steps': 82903, 'loss/train': 1.0271679162979126} 08/31/2021 04:12:37 - INFO - __main__ - Step 82905: {'lr': 0.0002134932424255278, 'samples': 15917760, 'steps': 82904, 'loss/train': 1.390539526939392} 08/31/2021 04:12:37 - INFO - __main__ - Step 82906: {'lr': 0.00021348799257451856, 'samples': 15917952, 'steps': 82905, 'loss/train': 1.830981969833374} 08/31/2021 04:12:39 - INFO - __main__ - Step 82907: {'lr': 0.00021348274273996106, 'samples': 15918144, 'steps': 82906, 'loss/train': 1.5453522205352783} 08/31/2021 04:12:39 - INFO - __main__ - Step 82908: {'lr': 0.00021347749292185768, 'samples': 15918336, 'steps': 82907, 'loss/train': 1.2139267921447754} 08/31/2021 04:12:40 - INFO - __main__ - Step 82909: {'lr': 0.00021347224312021082, 'samples': 15918528, 'steps': 82908, 'loss/train': 1.3598204851150513} 08/31/2021 04:12:40 - INFO - __main__ - Step 82910: {'lr': 0.0002134669933350228, 'samples': 15918720, 'steps': 82909, 'loss/train': 1.3012878894805908} 08/31/2021 04:12:40 - INFO - __main__ - Step 82911: {'lr': 0.000213461743566296, 'samples': 15918912, 'steps': 82910, 'loss/train': 1.9621222019195557} 08/31/2021 04:12:42 - INFO - __main__ - Step 82912: {'lr': 0.00021345649381403277, 'samples': 15919104, 'steps': 82911, 'loss/train': 1.5700782537460327} 08/31/2021 04:12:42 - INFO - __main__ - Step 82913: {'lr': 0.00021345124407823543, 'samples': 15919296, 'steps': 82912, 'loss/train': 1.302049160003662} 08/31/2021 04:12:43 - INFO - __main__ - Step 82914: {'lr': 0.0002134459943589064, 'samples': 15919488, 'steps': 82913, 'loss/train': 1.4023759365081787} 08/31/2021 04:12:43 - INFO - __main__ - Step 82915: {'lr': 0.00021344074465604808, 'samples': 15919680, 'steps': 82914, 'loss/train': 1.138651967048645} 08/31/2021 04:12:43 - INFO - __main__ - Step 82916: {'lr': 0.00021343549496966277, 'samples': 15919872, 'steps': 82915, 'loss/train': 1.2442890405654907} 08/31/2021 04:12:44 - INFO - __main__ - Step 82917: {'lr': 0.00021343024529975286, 'samples': 15920064, 'steps': 82916, 'loss/train': 1.2082948684692383} 08/31/2021 04:12:45 - INFO - __main__ - Step 82918: {'lr': 0.00021342499564632074, 'samples': 15920256, 'steps': 82917, 'loss/train': 1.4044955968856812} 08/31/2021 04:12:46 - INFO - __main__ - Step 82919: {'lr': 0.0002134197460093688, 'samples': 15920448, 'steps': 82918, 'loss/train': 0.7875766754150391} 08/31/2021 04:12:46 - INFO - __main__ - Step 82920: {'lr': 0.00021341449638889926, 'samples': 15920640, 'steps': 82919, 'loss/train': 0.8730988502502441} 08/31/2021 04:12:46 - INFO - __main__ - Step 82921: {'lr': 0.00021340924678491462, 'samples': 15920832, 'steps': 82920, 'loss/train': 0.3448783755302429} 08/31/2021 04:12:47 - INFO - __main__ - Step 82922: {'lr': 0.00021340399719741725, 'samples': 15921024, 'steps': 82921, 'loss/train': 1.2422326803207397} 08/31/2021 04:12:48 - INFO - __main__ - Step 82923: {'lr': 0.00021339874762640946, 'samples': 15921216, 'steps': 82922, 'loss/train': 1.4820173978805542} 08/31/2021 04:12:49 - INFO - __main__ - Step 82924: {'lr': 0.0002133934980718936, 'samples': 15921408, 'steps': 82923, 'loss/train': 0.7231789231300354} 08/31/2021 04:12:49 - INFO - __main__ - Step 82925: {'lr': 0.00021338824853387207, 'samples': 15921600, 'steps': 82924, 'loss/train': 1.5069928169250488} 08/31/2021 04:12:50 - INFO - __main__ - Step 82926: {'lr': 0.0002133829990123472, 'samples': 15921792, 'steps': 82925, 'loss/train': 0.9292284250259399} 08/31/2021 04:12:50 - INFO - __main__ - Step 82927: {'lr': 0.00021337774950732141, 'samples': 15921984, 'steps': 82926, 'loss/train': 1.591049313545227} 08/31/2021 04:12:50 - INFO - __main__ - Step 82928: {'lr': 0.00021337250001879704, 'samples': 15922176, 'steps': 82927, 'loss/train': 1.0467948913574219} 08/31/2021 04:12:52 - INFO - __main__ - Step 82929: {'lr': 0.00021336725054677647, 'samples': 15922368, 'steps': 82928, 'loss/train': 1.0543678998947144} 08/31/2021 04:12:53 - INFO - __main__ - Step 82930: {'lr': 0.00021336200109126202, 'samples': 15922560, 'steps': 82929, 'loss/train': 0.6188216805458069} 08/31/2021 04:12:53 - INFO - __main__ - Step 82931: {'lr': 0.00021335675165225614, 'samples': 15922752, 'steps': 82930, 'loss/train': 1.017235517501831} 08/31/2021 04:12:53 - INFO - __main__ - Step 82932: {'lr': 0.00021335150222976114, 'samples': 15922944, 'steps': 82931, 'loss/train': 1.318854570388794} 08/31/2021 04:12:54 - INFO - __main__ - Step 82933: {'lr': 0.0002133462528237794, 'samples': 15923136, 'steps': 82932, 'loss/train': 0.025685541331768036} 08/31/2021 04:12:54 - INFO - __main__ - Step 82934: {'lr': 0.00021334100343431322, 'samples': 15923328, 'steps': 82933, 'loss/train': 0.018849721178412437} 08/31/2021 04:12:56 - INFO - __main__ - Step 82935: {'lr': 0.00021333575406136504, 'samples': 15923520, 'steps': 82934, 'loss/train': 1.2110811471939087} 08/31/2021 04:12:56 - INFO - __main__ - Step 82936: {'lr': 0.0002133305047049372, 'samples': 15923712, 'steps': 82935, 'loss/train': 1.1885544061660767} 08/31/2021 04:12:56 - INFO - __main__ - Step 82937: {'lr': 0.00021332525536503207, 'samples': 15923904, 'steps': 82936, 'loss/train': 0.9368789196014404} 08/31/2021 04:12:57 - INFO - __main__ - Step 82938: {'lr': 0.00021332000604165198, 'samples': 15924096, 'steps': 82937, 'loss/train': 0.34992867708206177} 08/31/2021 04:12:57 - INFO - __main__ - Step 82939: {'lr': 0.00021331475673479935, 'samples': 15924288, 'steps': 82938, 'loss/train': 1.2685863971710205} 08/31/2021 04:12:59 - INFO - __main__ - Step 82940: {'lr': 0.00021330950744447653, 'samples': 15924480, 'steps': 82939, 'loss/train': 1.0630254745483398} 08/31/2021 04:12:59 - INFO - __main__ - Step 82941: {'lr': 0.00021330425817068588, 'samples': 15924672, 'steps': 82940, 'loss/train': 1.4857831001281738} 08/31/2021 04:13:00 - INFO - __main__ - Step 82942: {'lr': 0.00021329900891342977, 'samples': 15924864, 'steps': 82941, 'loss/train': 1.5517725944519043} 08/31/2021 04:13:00 - INFO - __main__ - Step 82943: {'lr': 0.00021329375967271054, 'samples': 15925056, 'steps': 82942, 'loss/train': 1.046645998954773} 08/31/2021 04:13:00 - INFO - __main__ - Step 82944: {'lr': 0.0002132885104485306, 'samples': 15925248, 'steps': 82943, 'loss/train': 1.4431555271148682} 08/31/2021 04:13:02 - INFO - __main__ - Step 82945: {'lr': 0.00021328326124089227, 'samples': 15925440, 'steps': 82944, 'loss/train': 1.002848744392395} 08/31/2021 04:13:02 - INFO - __main__ - Step 82946: {'lr': 0.00021327801204979805, 'samples': 15925632, 'steps': 82945, 'loss/train': 0.7593664526939392} 08/31/2021 04:13:03 - INFO - __main__ - Step 82947: {'lr': 0.0002132727628752501, 'samples': 15925824, 'steps': 82946, 'loss/train': 0.10423333197832108} 08/31/2021 04:13:03 - INFO - __main__ - Step 82948: {'lr': 0.00021326751371725084, 'samples': 15926016, 'steps': 82947, 'loss/train': 0.8188174962997437} 08/31/2021 04:13:03 - INFO - __main__ - Step 82949: {'lr': 0.0002132622645758027, 'samples': 15926208, 'steps': 82948, 'loss/train': 0.6126895546913147} 08/31/2021 04:13:05 - INFO - __main__ - Step 82950: {'lr': 0.000213257015450908, 'samples': 15926400, 'steps': 82949, 'loss/train': 0.9263335466384888} 08/31/2021 04:13:05 - INFO - __main__ - Step 82951: {'lr': 0.00021325176634256915, 'samples': 15926592, 'steps': 82950, 'loss/train': 1.4553196430206299} 08/31/2021 04:13:06 - INFO - __main__ - Step 82952: {'lr': 0.00021324651725078848, 'samples': 15926784, 'steps': 82951, 'loss/train': 1.2798271179199219} 08/31/2021 04:13:06 - INFO - __main__ - Step 82953: {'lr': 0.00021324126817556831, 'samples': 15926976, 'steps': 82952, 'loss/train': 1.1994643211364746} 08/31/2021 04:13:06 - INFO - __main__ - Step 82954: {'lr': 0.00021323601911691113, 'samples': 15927168, 'steps': 82953, 'loss/train': 0.7946373224258423} 08/31/2021 04:13:08 - INFO - __main__ - Step 82955: {'lr': 0.0002132307700748192, 'samples': 15927360, 'steps': 82954, 'loss/train': 1.151835322380066} 08/31/2021 04:13:08 - INFO - __main__ - Step 82956: {'lr': 0.0002132255210492949, 'samples': 15927552, 'steps': 82955, 'loss/train': 1.3720371723175049} 08/31/2021 04:13:09 - INFO - __main__ - Step 82957: {'lr': 0.00021322027204034063, 'samples': 15927744, 'steps': 82956, 'loss/train': 0.8491474986076355} 08/31/2021 04:13:09 - INFO - __main__ - Step 82958: {'lr': 0.00021321502304795875, 'samples': 15927936, 'steps': 82957, 'loss/train': 1.5417288541793823} 08/31/2021 04:13:09 - INFO - __main__ - Step 82959: {'lr': 0.00021320977407215168, 'samples': 15928128, 'steps': 82958, 'loss/train': 0.5285980105400085} 08/31/2021 04:13:12 - INFO - __main__ - Step 82960: {'lr': 0.00021320452511292167, 'samples': 15928320, 'steps': 82959, 'loss/train': 0.7193666696548462} 08/31/2021 04:13:12 - INFO - __main__ - Step 82961: {'lr': 0.0002131992761702711, 'samples': 15928512, 'steps': 82960, 'loss/train': 1.7699732780456543} 08/31/2021 04:13:13 - INFO - __main__ - Step 82962: {'lr': 0.00021319402724420236, 'samples': 15928704, 'steps': 82961, 'loss/train': 0.7523795962333679} 08/31/2021 04:13:13 - INFO - __main__ - Step 82963: {'lr': 0.00021318877833471784, 'samples': 15928896, 'steps': 82962, 'loss/train': 5.828737258911133} 08/31/2021 04:13:13 - INFO - __main__ - Step 82964: {'lr': 0.0002131835294418199, 'samples': 15929088, 'steps': 82963, 'loss/train': 0.8326038718223572} 08/31/2021 04:13:14 - INFO - __main__ - Step 82965: {'lr': 0.00021317828056551086, 'samples': 15929280, 'steps': 82964, 'loss/train': 1.6605031490325928} 08/31/2021 04:13:15 - INFO - __main__ - Step 82966: {'lr': 0.00021317303170579314, 'samples': 15929472, 'steps': 82965, 'loss/train': 0.972537636756897} 08/31/2021 04:13:16 - INFO - __main__ - Step 82967: {'lr': 0.0002131677828626691, 'samples': 15929664, 'steps': 82966, 'loss/train': 1.7931636571884155} 08/31/2021 04:13:16 - INFO - __main__ - Step 82968: {'lr': 0.00021316253403614105, 'samples': 15929856, 'steps': 82967, 'loss/train': 1.5495415925979614} 08/31/2021 04:13:16 - INFO - __main__ - Step 82969: {'lr': 0.00021315728522621142, 'samples': 15930048, 'steps': 82968, 'loss/train': 1.4602771997451782} 08/31/2021 04:13:17 - INFO - __main__ - Step 82970: {'lr': 0.00021315203643288252, 'samples': 15930240, 'steps': 82969, 'loss/train': 0.597655177116394} 08/31/2021 04:13:18 - INFO - __main__ - Step 82971: {'lr': 0.00021314678765615676, 'samples': 15930432, 'steps': 82970, 'loss/train': 1.6355605125427246} 08/31/2021 04:13:19 - INFO - __main__ - Step 82972: {'lr': 0.0002131415388960365, 'samples': 15930624, 'steps': 82971, 'loss/train': 0.7113564014434814} 08/31/2021 04:13:19 - INFO - __main__ - Step 82973: {'lr': 0.00021313629015252419, 'samples': 15930816, 'steps': 82972, 'loss/train': 1.3568826913833618} 08/31/2021 04:13:19 - INFO - __main__ - Step 82974: {'lr': 0.000213131041425622, 'samples': 15931008, 'steps': 82973, 'loss/train': 1.1838096380233765} 08/31/2021 04:13:20 - INFO - __main__ - Step 82975: {'lr': 0.00021312579271533239, 'samples': 15931200, 'steps': 82974, 'loss/train': 0.10115726292133331} 08/31/2021 04:13:21 - INFO - __main__ - Step 82976: {'lr': 0.00021312054402165774, 'samples': 15931392, 'steps': 82975, 'loss/train': 1.9162013530731201} 08/31/2021 04:13:22 - INFO - __main__ - Step 82977: {'lr': 0.0002131152953446004, 'samples': 15931584, 'steps': 82976, 'loss/train': 1.4431169033050537} 08/31/2021 04:13:22 - INFO - __main__ - Step 82978: {'lr': 0.00021311004668416272, 'samples': 15931776, 'steps': 82977, 'loss/train': 0.867879331111908} 08/31/2021 04:13:22 - INFO - __main__ - Step 82979: {'lr': 0.00021310479804034711, 'samples': 15931968, 'steps': 82978, 'loss/train': 1.2126855850219727} 08/31/2021 04:13:23 - INFO - __main__ - Step 82980: {'lr': 0.00021309954941315588, 'samples': 15932160, 'steps': 82979, 'loss/train': 1.5201674699783325} 08/31/2021 04:13:24 - INFO - __main__ - Step 82981: {'lr': 0.00021309430080259143, 'samples': 15932352, 'steps': 82980, 'loss/train': 1.7767202854156494} 08/31/2021 04:13:25 - INFO - __main__ - Step 82982: {'lr': 0.00021308905220865612, 'samples': 15932544, 'steps': 82981, 'loss/train': 1.2279356718063354} 08/31/2021 04:13:25 - INFO - __main__ - Step 82983: {'lr': 0.00021308380363135233, 'samples': 15932736, 'steps': 82982, 'loss/train': 1.564319133758545} 08/31/2021 04:13:25 - INFO - __main__ - Step 82984: {'lr': 0.00021307855507068238, 'samples': 15932928, 'steps': 82983, 'loss/train': 2.520827293395996} 08/31/2021 04:13:26 - INFO - __main__ - Step 82985: {'lr': 0.0002130733065266487, 'samples': 15933120, 'steps': 82984, 'loss/train': 1.3754245042800903} 08/31/2021 04:13:27 - INFO - __main__ - Step 82986: {'lr': 0.0002130680579992537, 'samples': 15933312, 'steps': 82985, 'loss/train': 1.4708857536315918} 08/31/2021 04:13:28 - INFO - __main__ - Step 82987: {'lr': 0.00021306280948849953, 'samples': 15933504, 'steps': 82986, 'loss/train': 0.9495126605033875} 08/31/2021 04:13:28 - INFO - __main__ - Step 82988: {'lr': 0.00021305756099438875, 'samples': 15933696, 'steps': 82987, 'loss/train': 1.5124661922454834} 08/31/2021 04:13:28 - INFO - __main__ - Step 82989: {'lr': 0.00021305231251692364, 'samples': 15933888, 'steps': 82988, 'loss/train': 0.9264002442359924} 08/31/2021 04:13:29 - INFO - __main__ - Step 82990: {'lr': 0.00021304706405610656, 'samples': 15934080, 'steps': 82989, 'loss/train': 1.035693645477295} 08/31/2021 04:13:29 - INFO - __main__ - Step 82991: {'lr': 0.00021304181561193993, 'samples': 15934272, 'steps': 82990, 'loss/train': 1.1253582239151} 08/31/2021 04:13:30 - INFO - __main__ - Step 82992: {'lr': 0.0002130365671844261, 'samples': 15934464, 'steps': 82991, 'loss/train': 0.9330130815505981} 08/31/2021 04:13:31 - INFO - __main__ - Step 82993: {'lr': 0.00021303131877356738, 'samples': 15934656, 'steps': 82992, 'loss/train': 1.6388847827911377} 08/31/2021 04:13:31 - INFO - __main__ - Step 82994: {'lr': 0.0002130260703793662, 'samples': 15934848, 'steps': 82993, 'loss/train': 1.5189416408538818} 08/31/2021 04:13:31 - INFO - __main__ - Step 82995: {'lr': 0.00021302082200182491, 'samples': 15935040, 'steps': 82994, 'loss/train': 1.2207555770874023} 08/31/2021 04:13:32 - INFO - __main__ - Step 82996: {'lr': 0.00021301557364094588, 'samples': 15935232, 'steps': 82995, 'loss/train': 0.8430322408676147} 08/31/2021 04:13:33 - INFO - __main__ - Step 82997: {'lr': 0.00021301032529673141, 'samples': 15935424, 'steps': 82996, 'loss/train': 1.4954123497009277} 08/31/2021 04:13:34 - INFO - __main__ - Step 82998: {'lr': 0.00021300507696918398, 'samples': 15935616, 'steps': 82997, 'loss/train': 1.2901597023010254} 08/31/2021 04:13:34 - INFO - __main__ - Step 82999: {'lr': 0.00021299982865830583, 'samples': 15935808, 'steps': 82998, 'loss/train': 1.2238224744796753} 08/31/2021 04:13:35 - INFO - __main__ - Step 83000: {'lr': 0.0002129945803640995, 'samples': 15936000, 'steps': 82999, 'loss/train': 1.179946780204773} 08/31/2021 04:13:35 - INFO - __main__ - Step 83001: {'lr': 0.00021298933208656717, 'samples': 15936192, 'steps': 83000, 'loss/train': 1.7942025661468506} 08/31/2021 04:13:36 - INFO - __main__ - Step 83002: {'lr': 0.00021298408382571128, 'samples': 15936384, 'steps': 83001, 'loss/train': 0.6375513076782227} 08/31/2021 04:13:37 - INFO - __main__ - Step 83003: {'lr': 0.0002129788355815342, 'samples': 15936576, 'steps': 83002, 'loss/train': 1.4622931480407715} 08/31/2021 04:13:37 - INFO - __main__ - Step 83004: {'lr': 0.00021297358735403824, 'samples': 15936768, 'steps': 83003, 'loss/train': 0.8368719220161438} 08/31/2021 04:13:38 - INFO - __main__ - Step 83005: {'lr': 0.00021296833914322583, 'samples': 15936960, 'steps': 83004, 'loss/train': 1.4332151412963867} 08/31/2021 04:13:38 - INFO - __main__ - Step 83006: {'lr': 0.0002129630909490993, 'samples': 15937152, 'steps': 83005, 'loss/train': 1.103479027748108} 08/31/2021 04:13:40 - INFO - __main__ - Step 83007: {'lr': 0.00021295784277166105, 'samples': 15937344, 'steps': 83006, 'loss/train': 1.1764189004898071} 08/31/2021 04:13:40 - INFO - __main__ - Step 83008: {'lr': 0.00021295259461091343, 'samples': 15937536, 'steps': 83007, 'loss/train': 1.63512122631073} 08/31/2021 04:13:40 - INFO - __main__ - Step 83009: {'lr': 0.0002129473464668588, 'samples': 15937728, 'steps': 83008, 'loss/train': 0.41385558247566223} 08/31/2021 04:13:41 - INFO - __main__ - Step 83010: {'lr': 0.00021294209833949948, 'samples': 15937920, 'steps': 83009, 'loss/train': 0.062340207397937775} 08/31/2021 04:13:41 - INFO - __main__ - Step 83011: {'lr': 0.0002129368502288379, 'samples': 15938112, 'steps': 83010, 'loss/train': 0.9974087476730347} 08/31/2021 04:13:41 - INFO - __main__ - Step 83012: {'lr': 0.00021293160213487644, 'samples': 15938304, 'steps': 83011, 'loss/train': 1.1234620809555054} 08/31/2021 04:13:44 - INFO - __main__ - Step 83013: {'lr': 0.0002129263540576175, 'samples': 15938496, 'steps': 83012, 'loss/train': 1.5753437280654907} 08/31/2021 04:13:44 - INFO - __main__ - Step 83014: {'lr': 0.00021292110599706326, 'samples': 15938688, 'steps': 83013, 'loss/train': 2.0297927856445312} 08/31/2021 04:13:44 - INFO - __main__ - Step 83015: {'lr': 0.00021291585795321622, 'samples': 15938880, 'steps': 83014, 'loss/train': 1.6623388528823853} 08/31/2021 04:13:45 - INFO - __main__ - Step 83016: {'lr': 0.0002129106099260787, 'samples': 15939072, 'steps': 83015, 'loss/train': 1.1279852390289307} 08/31/2021 04:13:45 - INFO - __main__ - Step 83017: {'lr': 0.00021290536191565312, 'samples': 15939264, 'steps': 83016, 'loss/train': 1.183713436126709} 08/31/2021 04:13:47 - INFO - __main__ - Step 83018: {'lr': 0.0002129001139219418, 'samples': 15939456, 'steps': 83017, 'loss/train': 0.15065167844295502} 08/31/2021 04:13:48 - INFO - __main__ - Step 83019: {'lr': 0.0002128948659449471, 'samples': 15939648, 'steps': 83018, 'loss/train': 0.798602819442749} 08/31/2021 04:13:48 - INFO - __main__ - Step 83020: {'lr': 0.0002128896179846714, 'samples': 15939840, 'steps': 83019, 'loss/train': 0.8156294226646423} 08/31/2021 04:13:48 - INFO - __main__ - Step 83021: {'lr': 0.0002128843700411171, 'samples': 15940032, 'steps': 83020, 'loss/train': 0.5626160502433777} 08/31/2021 04:13:49 - INFO - __main__ - Step 83022: {'lr': 0.0002128791221142865, 'samples': 15940224, 'steps': 83021, 'loss/train': 1.326850414276123} 08/31/2021 04:13:50 - INFO - __main__ - Step 83023: {'lr': 0.00021287387420418206, 'samples': 15940416, 'steps': 83022, 'loss/train': 0.8099812865257263} 08/31/2021 04:13:51 - INFO - __main__ - Step 83024: {'lr': 0.000212868626310806, 'samples': 15940608, 'steps': 83023, 'loss/train': 0.8393821120262146} 08/31/2021 04:13:51 - INFO - __main__ - Step 83025: {'lr': 0.00021286337843416078, 'samples': 15940800, 'steps': 83024, 'loss/train': 1.0749821662902832} 08/31/2021 04:13:51 - INFO - __main__ - Step 83026: {'lr': 0.0002128581305742488, 'samples': 15940992, 'steps': 83025, 'loss/train': 1.0445743799209595} 08/31/2021 04:13:52 - INFO - __main__ - Step 83027: {'lr': 0.00021285288273107235, 'samples': 15941184, 'steps': 83026, 'loss/train': 0.3107922673225403} 08/31/2021 04:13:53 - INFO - __main__ - Step 83028: {'lr': 0.00021284763490463378, 'samples': 15941376, 'steps': 83027, 'loss/train': 1.1637506484985352} 08/31/2021 04:13:54 - INFO - __main__ - Step 83029: {'lr': 0.0002128423870949355, 'samples': 15941568, 'steps': 83028, 'loss/train': 0.34087854623794556} 08/31/2021 04:13:54 - INFO - __main__ - Step 83030: {'lr': 0.00021283713930197987, 'samples': 15941760, 'steps': 83029, 'loss/train': 1.5362569093704224} 08/31/2021 04:13:54 - INFO - __main__ - Step 83031: {'lr': 0.00021283189152576927, 'samples': 15941952, 'steps': 83030, 'loss/train': 1.3080811500549316} 08/31/2021 04:13:55 - INFO - __main__ - Step 83032: {'lr': 0.000212826643766306, 'samples': 15942144, 'steps': 83031, 'loss/train': 1.1333314180374146} 08/31/2021 04:13:55 - INFO - __main__ - Step 83033: {'lr': 0.00021282139602359253, 'samples': 15942336, 'steps': 83032, 'loss/train': 0.9764856696128845} 08/31/2021 04:13:57 - INFO - __main__ - Step 83034: {'lr': 0.00021281614829763118, 'samples': 15942528, 'steps': 83033, 'loss/train': 1.519010305404663} 08/31/2021 04:13:57 - INFO - __main__ - Step 83035: {'lr': 0.00021281090058842425, 'samples': 15942720, 'steps': 83034, 'loss/train': 0.9539114236831665} 08/31/2021 04:13:57 - INFO - __main__ - Step 83036: {'lr': 0.00021280565289597418, 'samples': 15942912, 'steps': 83035, 'loss/train': 1.227795958518982} 08/31/2021 04:13:58 - INFO - __main__ - Step 83037: {'lr': 0.00021280040522028327, 'samples': 15943104, 'steps': 83036, 'loss/train': 1.1012691259384155} 08/31/2021 04:13:58 - INFO - __main__ - Step 83038: {'lr': 0.00021279515756135396, 'samples': 15943296, 'steps': 83037, 'loss/train': 0.8370503187179565} 08/31/2021 04:14:00 - INFO - __main__ - Step 83039: {'lr': 0.00021278990991918857, 'samples': 15943488, 'steps': 83038, 'loss/train': 1.2030328512191772} 08/31/2021 04:14:00 - INFO - __main__ - Step 83040: {'lr': 0.00021278466229378951, 'samples': 15943680, 'steps': 83039, 'loss/train': 0.048722218722105026} 08/31/2021 04:14:01 - INFO - __main__ - Step 83041: {'lr': 0.00021277941468515906, 'samples': 15943872, 'steps': 83040, 'loss/train': 1.4892241954803467} 08/31/2021 04:14:01 - INFO - __main__ - Step 83042: {'lr': 0.0002127741670932996, 'samples': 15944064, 'steps': 83041, 'loss/train': 1.0460737943649292} 08/31/2021 04:14:01 - INFO - __main__ - Step 83043: {'lr': 0.00021276891951821359, 'samples': 15944256, 'steps': 83042, 'loss/train': 1.1834769248962402} 08/31/2021 04:14:03 - INFO - __main__ - Step 83044: {'lr': 0.00021276367195990328, 'samples': 15944448, 'steps': 83043, 'loss/train': 1.041662573814392} 08/31/2021 04:14:04 - INFO - __main__ - Step 83045: {'lr': 0.00021275842441837115, 'samples': 15944640, 'steps': 83044, 'loss/train': 1.5268025398254395} 08/31/2021 04:14:04 - INFO - __main__ - Step 83046: {'lr': 0.00021275317689361945, 'samples': 15944832, 'steps': 83045, 'loss/train': 1.1493384838104248} 08/31/2021 04:14:04 - INFO - __main__ - Step 83047: {'lr': 0.0002127479293856506, 'samples': 15945024, 'steps': 83046, 'loss/train': 1.0076758861541748} 08/31/2021 04:14:05 - INFO - __main__ - Step 83048: {'lr': 0.00021274268189446695, 'samples': 15945216, 'steps': 83047, 'loss/train': 1.8762314319610596} 08/31/2021 04:14:06 - INFO - __main__ - Step 83049: {'lr': 0.00021273743442007089, 'samples': 15945408, 'steps': 83048, 'loss/train': 1.372523307800293} 08/31/2021 04:14:07 - INFO - __main__ - Step 83050: {'lr': 0.00021273218696246475, 'samples': 15945600, 'steps': 83049, 'loss/train': 1.374112844467163} 08/31/2021 04:14:07 - INFO - __main__ - Step 83051: {'lr': 0.0002127269395216509, 'samples': 15945792, 'steps': 83050, 'loss/train': 2.0199055671691895} 08/31/2021 04:14:07 - INFO - __main__ - Step 83052: {'lr': 0.00021272169209763173, 'samples': 15945984, 'steps': 83051, 'loss/train': 1.4810771942138672} 08/31/2021 04:14:08 - INFO - __main__ - Step 83053: {'lr': 0.00021271644469040966, 'samples': 15946176, 'steps': 83052, 'loss/train': 1.4763859510421753} 08/31/2021 04:14:10 - INFO - __main__ - Step 83054: {'lr': 0.0002127111972999869, 'samples': 15946368, 'steps': 83053, 'loss/train': 0.3866415321826935} 08/31/2021 04:14:10 - INFO - __main__ - Step 83055: {'lr': 0.0002127059499263659, 'samples': 15946560, 'steps': 83054, 'loss/train': 1.3287546634674072} 08/31/2021 04:14:10 - INFO - __main__ - Step 83056: {'lr': 0.0002127007025695491, 'samples': 15946752, 'steps': 83055, 'loss/train': 1.5926671028137207} 08/31/2021 04:14:11 - INFO - __main__ - Step 83057: {'lr': 0.00021269545522953874, 'samples': 15946944, 'steps': 83056, 'loss/train': 1.545867919921875} 08/31/2021 04:14:11 - INFO - __main__ - Step 83058: {'lr': 0.0002126902079063372, 'samples': 15947136, 'steps': 83057, 'loss/train': 1.3539481163024902} 08/31/2021 04:14:13 - INFO - __main__ - Step 83059: {'lr': 0.0002126849605999469, 'samples': 15947328, 'steps': 83058, 'loss/train': 0.7163387537002563} 08/31/2021 04:14:13 - INFO - __main__ - Step 83060: {'lr': 0.00021267971331037018, 'samples': 15947520, 'steps': 83059, 'loss/train': 1.9792892932891846} 08/31/2021 04:14:13 - INFO - __main__ - Step 83061: {'lr': 0.0002126744660376094, 'samples': 15947712, 'steps': 83060, 'loss/train': 1.3711398839950562} 08/31/2021 04:14:14 - INFO - __main__ - Step 83062: {'lr': 0.00021266921878166693, 'samples': 15947904, 'steps': 83061, 'loss/train': 1.1541714668273926} 08/31/2021 04:14:14 - INFO - __main__ - Step 83063: {'lr': 0.00021266397154254512, 'samples': 15948096, 'steps': 83062, 'loss/train': 0.44749918580055237} 08/31/2021 04:14:14 - INFO - __main__ - Step 83064: {'lr': 0.0002126587243202464, 'samples': 15948288, 'steps': 83063, 'loss/train': 1.2297041416168213} 08/31/2021 04:14:17 - INFO - __main__ - Step 83065: {'lr': 0.00021265347711477302, 'samples': 15948480, 'steps': 83064, 'loss/train': 0.8230679631233215} 08/31/2021 04:14:17 - INFO - __main__ - Step 83066: {'lr': 0.00021264822992612741, 'samples': 15948672, 'steps': 83065, 'loss/train': 1.7878471612930298} 08/31/2021 04:14:18 - INFO - __main__ - Step 83067: {'lr': 0.0002126429827543121, 'samples': 15948864, 'steps': 83066, 'loss/train': 0.022131582722067833} 08/31/2021 04:14:18 - INFO - __main__ - Step 83068: {'lr': 0.00021263773559932915, 'samples': 15949056, 'steps': 83067, 'loss/train': 0.046631306409835815} 08/31/2021 04:14:19 - INFO - __main__ - Step 83069: {'lr': 0.00021263248846118101, 'samples': 15949248, 'steps': 83068, 'loss/train': 1.2341622114181519} 08/31/2021 04:14:19 - INFO - __main__ - Step 83070: {'lr': 0.00021262724133987016, 'samples': 15949440, 'steps': 83069, 'loss/train': 0.877712607383728} 08/31/2021 04:14:20 - INFO - __main__ - Step 83071: {'lr': 0.00021262199423539884, 'samples': 15949632, 'steps': 83070, 'loss/train': 1.053399682044983} 08/31/2021 04:14:21 - INFO - __main__ - Step 83072: {'lr': 0.00021261674714776951, 'samples': 15949824, 'steps': 83071, 'loss/train': 0.6946830749511719} 08/31/2021 04:14:21 - INFO - __main__ - Step 83073: {'lr': 0.0002126115000769845, 'samples': 15950016, 'steps': 83072, 'loss/train': 1.3125275373458862} 08/31/2021 04:14:22 - INFO - __main__ - Step 83074: {'lr': 0.00021260625302304615, 'samples': 15950208, 'steps': 83073, 'loss/train': 1.0847903490066528} 08/31/2021 04:14:22 - INFO - __main__ - Step 83075: {'lr': 0.00021260100598595688, 'samples': 15950400, 'steps': 83074, 'loss/train': 1.7160727977752686} 08/31/2021 04:14:22 - INFO - __main__ - Step 83076: {'lr': 0.000212595758965719, 'samples': 15950592, 'steps': 83075, 'loss/train': 0.8730493187904358} 08/31/2021 04:14:24 - INFO - __main__ - Step 83077: {'lr': 0.00021259051196233485, 'samples': 15950784, 'steps': 83076, 'loss/train': 0.5815089344978333} 08/31/2021 04:14:25 - INFO - __main__ - Step 83078: {'lr': 0.00021258526497580692, 'samples': 15950976, 'steps': 83077, 'loss/train': 1.2683401107788086} 08/31/2021 04:14:25 - INFO - __main__ - Step 83079: {'lr': 0.00021258001800613743, 'samples': 15951168, 'steps': 83078, 'loss/train': 0.9519487023353577} 08/31/2021 04:14:25 - INFO - __main__ - Step 83080: {'lr': 0.00021257477105332895, 'samples': 15951360, 'steps': 83079, 'loss/train': 1.8377660512924194} 08/31/2021 04:14:26 - INFO - __main__ - Step 83081: {'lr': 0.00021256952411738357, 'samples': 15951552, 'steps': 83080, 'loss/train': 1.3028837442398071} 08/31/2021 04:14:27 - INFO - __main__ - Step 83082: {'lr': 0.0002125642771983038, 'samples': 15951744, 'steps': 83081, 'loss/train': 1.2628334760665894} 08/31/2021 04:14:28 - INFO - __main__ - Step 83083: {'lr': 0.00021255903029609197, 'samples': 15951936, 'steps': 83082, 'loss/train': 1.5372282266616821} 08/31/2021 04:14:28 - INFO - __main__ - Step 83084: {'lr': 0.00021255378341075048, 'samples': 15952128, 'steps': 83083, 'loss/train': 1.9047092199325562} 08/31/2021 04:14:28 - INFO - __main__ - Step 83085: {'lr': 0.00021254853654228167, 'samples': 15952320, 'steps': 83084, 'loss/train': 1.7269960641860962} 08/31/2021 04:14:29 - INFO - __main__ - Step 83086: {'lr': 0.00021254328969068793, 'samples': 15952512, 'steps': 83085, 'loss/train': 0.7645082473754883} 08/31/2021 04:14:30 - INFO - __main__ - Step 83087: {'lr': 0.00021253804285597156, 'samples': 15952704, 'steps': 83086, 'loss/train': 0.9078798294067383} 08/31/2021 04:14:31 - INFO - __main__ - Step 83088: {'lr': 0.00021253279603813502, 'samples': 15952896, 'steps': 83087, 'loss/train': 1.2744325399398804} 08/31/2021 04:14:31 - INFO - __main__ - Step 83089: {'lr': 0.0002125275492371806, 'samples': 15953088, 'steps': 83088, 'loss/train': 1.4002065658569336} 08/31/2021 04:14:31 - INFO - __main__ - Step 83090: {'lr': 0.0002125223024531107, 'samples': 15953280, 'steps': 83089, 'loss/train': 1.4640854597091675} 08/31/2021 04:14:32 - INFO - __main__ - Step 83091: {'lr': 0.00021251705568592767, 'samples': 15953472, 'steps': 83090, 'loss/train': 1.6825933456420898} 08/31/2021 04:14:32 - INFO - __main__ - Step 83092: {'lr': 0.00021251180893563384, 'samples': 15953664, 'steps': 83091, 'loss/train': 0.8747135996818542} 08/31/2021 04:14:34 - INFO - __main__ - Step 83093: {'lr': 0.00021250656220223163, 'samples': 15953856, 'steps': 83092, 'loss/train': 1.4029359817504883} 08/31/2021 04:14:34 - INFO - __main__ - Step 83094: {'lr': 0.00021250131548572351, 'samples': 15954048, 'steps': 83093, 'loss/train': 1.3707002401351929} 08/31/2021 04:14:34 - INFO - __main__ - Step 83095: {'lr': 0.0002124960687861116, 'samples': 15954240, 'steps': 83094, 'loss/train': 1.007067322731018} 08/31/2021 04:14:35 - INFO - __main__ - Step 83096: {'lr': 0.0002124908221033984, 'samples': 15954432, 'steps': 83095, 'loss/train': 0.7171798944473267} 08/31/2021 04:14:35 - INFO - __main__ - Step 83097: {'lr': 0.00021248557543758622, 'samples': 15954624, 'steps': 83096, 'loss/train': 0.945853590965271} 08/31/2021 04:14:36 - INFO - __main__ - Step 83098: {'lr': 0.00021248032878867752, 'samples': 15954816, 'steps': 83097, 'loss/train': 2.1094419956207275} 08/31/2021 04:14:37 - INFO - __main__ - Step 83099: {'lr': 0.00021247508215667456, 'samples': 15955008, 'steps': 83098, 'loss/train': 0.9013224840164185} 08/31/2021 04:14:37 - INFO - __main__ - Step 83100: {'lr': 0.00021246983554157976, 'samples': 15955200, 'steps': 83099, 'loss/train': 1.4757417440414429} 08/31/2021 04:14:38 - INFO - __main__ - Step 83101: {'lr': 0.00021246458894339545, 'samples': 15955392, 'steps': 83100, 'loss/train': 0.8110625743865967} 08/31/2021 04:14:38 - INFO - __main__ - Step 83102: {'lr': 0.00021245934236212405, 'samples': 15955584, 'steps': 83101, 'loss/train': 1.469563603401184} 08/31/2021 04:14:40 - INFO - __main__ - Step 83103: {'lr': 0.00021245409579776785, 'samples': 15955776, 'steps': 83102, 'loss/train': 1.0160695314407349} 08/31/2021 04:14:40 - INFO - __main__ - Step 83104: {'lr': 0.0002124488492503293, 'samples': 15955968, 'steps': 83103, 'loss/train': 0.7394027709960938} 08/31/2021 04:14:40 - INFO - __main__ - Step 83105: {'lr': 0.00021244360271981073, 'samples': 15956160, 'steps': 83104, 'loss/train': 1.6387126445770264} 08/31/2021 04:14:41 - INFO - __main__ - Step 83106: {'lr': 0.00021243835620621444, 'samples': 15956352, 'steps': 83105, 'loss/train': 1.273881196975708} 08/31/2021 04:14:41 - INFO - __main__ - Step 83107: {'lr': 0.00021243310970954298, 'samples': 15956544, 'steps': 83106, 'loss/train': 0.09470920264720917} 08/31/2021 04:14:41 - INFO - __main__ - Step 83108: {'lr': 0.0002124278632297985, 'samples': 15956736, 'steps': 83107, 'loss/train': 1.229906439781189} 08/31/2021 04:14:43 - INFO - __main__ - Step 83109: {'lr': 0.0002124226167669834, 'samples': 15956928, 'steps': 83108, 'loss/train': 1.632763385772705} 08/31/2021 04:14:43 - INFO - __main__ - Step 83110: {'lr': 0.00021241737032110013, 'samples': 15957120, 'steps': 83109, 'loss/train': 1.1648648977279663} 08/31/2021 04:14:44 - INFO - __main__ - Step 83111: {'lr': 0.00021241212389215097, 'samples': 15957312, 'steps': 83110, 'loss/train': 0.7087621092796326} 08/31/2021 04:14:44 - INFO - __main__ - Step 83112: {'lr': 0.00021240687748013835, 'samples': 15957504, 'steps': 83111, 'loss/train': 0.8656339049339294} 08/31/2021 04:14:45 - INFO - __main__ - Step 83113: {'lr': 0.0002124016310850646, 'samples': 15957696, 'steps': 83112, 'loss/train': 2.225867748260498} 08/31/2021 04:14:46 - INFO - __main__ - Step 83114: {'lr': 0.0002123963847069321, 'samples': 15957888, 'steps': 83113, 'loss/train': 1.0884419679641724} 08/31/2021 04:14:47 - INFO - __main__ - Step 83115: {'lr': 0.00021239113834574323, 'samples': 15958080, 'steps': 83114, 'loss/train': 1.0010385513305664} 08/31/2021 04:14:47 - INFO - __main__ - Step 83116: {'lr': 0.00021238589200150033, 'samples': 15958272, 'steps': 83115, 'loss/train': 1.2691731452941895} 08/31/2021 04:14:47 - INFO - __main__ - Step 83117: {'lr': 0.00021238064567420572, 'samples': 15958464, 'steps': 83116, 'loss/train': 1.15602707862854} 08/31/2021 04:14:48 - INFO - __main__ - Step 83118: {'lr': 0.00021237539936386186, 'samples': 15958656, 'steps': 83117, 'loss/train': 1.4251704216003418} 08/31/2021 04:14:49 - INFO - __main__ - Step 83119: {'lr': 0.00021237015307047104, 'samples': 15958848, 'steps': 83118, 'loss/train': 1.7098950147628784} 08/31/2021 04:14:50 - INFO - __main__ - Step 83120: {'lr': 0.00021236490679403563, 'samples': 15959040, 'steps': 83119, 'loss/train': 0.738664448261261} 08/31/2021 04:14:50 - INFO - __main__ - Step 83121: {'lr': 0.0002123596605345582, 'samples': 15959232, 'steps': 83120, 'loss/train': 1.012649655342102} 08/31/2021 04:14:50 - INFO - __main__ - Step 83122: {'lr': 0.00021235441429204072, 'samples': 15959424, 'steps': 83121, 'loss/train': 0.950498104095459} 08/31/2021 04:14:51 - INFO - __main__ - Step 83123: {'lr': 0.00021234916806648583, 'samples': 15959616, 'steps': 83122, 'loss/train': 1.3604109287261963} 08/31/2021 04:14:53 - INFO - __main__ - Step 83124: {'lr': 0.00021234392185789577, 'samples': 15959808, 'steps': 83123, 'loss/train': 1.114702820777893} 08/31/2021 04:14:54 - INFO - __main__ - Step 83125: {'lr': 0.00021233867566627302, 'samples': 15960000, 'steps': 83124, 'loss/train': 0.8839694857597351} 08/31/2021 04:14:54 - INFO - __main__ - Step 83126: {'lr': 0.00021233342949161983, 'samples': 15960192, 'steps': 83125, 'loss/train': 1.330851674079895} 08/31/2021 04:14:54 - INFO - __main__ - Step 83127: {'lr': 0.00021232818333393862, 'samples': 15960384, 'steps': 83126, 'loss/train': 1.0504096746444702} 08/31/2021 04:14:55 - INFO - __main__ - Step 83128: {'lr': 0.00021232293719323177, 'samples': 15960576, 'steps': 83127, 'loss/train': 1.4029722213745117} 08/31/2021 04:14:56 - INFO - __main__ - Step 83129: {'lr': 0.0002123176910695016, 'samples': 15960768, 'steps': 83128, 'loss/train': 1.3885034322738647} 08/31/2021 04:14:57 - INFO - __main__ - Step 83130: {'lr': 0.00021231244496275055, 'samples': 15960960, 'steps': 83129, 'loss/train': 1.465491771697998} 08/31/2021 04:14:57 - INFO - __main__ - Step 83131: {'lr': 0.00021230719887298087, 'samples': 15961152, 'steps': 83130, 'loss/train': 0.8752467036247253} 08/31/2021 04:14:57 - INFO - __main__ - Step 83132: {'lr': 0.00021230195280019502, 'samples': 15961344, 'steps': 83131, 'loss/train': 0.2964852750301361} 08/31/2021 04:14:58 - INFO - __main__ - Step 83133: {'lr': 0.0002122967067443953, 'samples': 15961536, 'steps': 83132, 'loss/train': 1.497725009918213} 08/31/2021 04:14:59 - INFO - __main__ - Step 83134: {'lr': 0.00021229146070558423, 'samples': 15961728, 'steps': 83133, 'loss/train': 0.9816148281097412} 08/31/2021 04:15:00 - INFO - __main__ - Step 83135: {'lr': 0.00021228621468376394, 'samples': 15961920, 'steps': 83134, 'loss/train': 1.6750199794769287} 08/31/2021 04:15:00 - INFO - __main__ - Step 83136: {'lr': 0.00021228096867893686, 'samples': 15962112, 'steps': 83135, 'loss/train': 1.2676146030426025} 08/31/2021 04:15:01 - INFO - __main__ - Step 83137: {'lr': 0.00021227572269110544, 'samples': 15962304, 'steps': 83136, 'loss/train': 1.2933114767074585} 08/31/2021 04:15:01 - INFO - __main__ - Step 83138: {'lr': 0.000212270476720272, 'samples': 15962496, 'steps': 83137, 'loss/train': 1.123691201210022} 08/31/2021 04:15:01 - INFO - __main__ - Step 83139: {'lr': 0.0002122652307664389, 'samples': 15962688, 'steps': 83138, 'loss/train': 0.6941483020782471} 08/31/2021 04:15:03 - INFO - __main__ - Step 83140: {'lr': 0.00021225998482960845, 'samples': 15962880, 'steps': 83139, 'loss/train': 0.7271498441696167} 08/31/2021 04:15:03 - INFO - __main__ - Step 83141: {'lr': 0.00021225473890978315, 'samples': 15963072, 'steps': 83140, 'loss/train': 1.4956055879592896} 08/31/2021 04:15:04 - INFO - __main__ - Step 83142: {'lr': 0.00021224949300696522, 'samples': 15963264, 'steps': 83141, 'loss/train': 1.4085402488708496} 08/31/2021 04:15:04 - INFO - __main__ - Step 83143: {'lr': 0.00021224424712115708, 'samples': 15963456, 'steps': 83142, 'loss/train': 0.9138798713684082} 08/31/2021 04:15:04 - INFO - __main__ - Step 83144: {'lr': 0.00021223900125236114, 'samples': 15963648, 'steps': 83143, 'loss/train': 1.159250020980835} 08/31/2021 04:15:06 - INFO - __main__ - Step 83145: {'lr': 0.00021223375540057972, 'samples': 15963840, 'steps': 83144, 'loss/train': 1.0698798894882202} 08/31/2021 04:15:06 - INFO - __main__ - Step 83146: {'lr': 0.00021222850956581518, 'samples': 15964032, 'steps': 83145, 'loss/train': 1.4154926538467407} 08/31/2021 04:15:06 - INFO - __main__ - Step 83147: {'lr': 0.00021222326374807, 'samples': 15964224, 'steps': 83146, 'loss/train': 1.1964069604873657} 08/31/2021 04:15:07 - INFO - __main__ - Step 83148: {'lr': 0.0002122180179473463, 'samples': 15964416, 'steps': 83147, 'loss/train': 1.192659616470337} 08/31/2021 04:15:07 - INFO - __main__ - Step 83149: {'lr': 0.0002122127721636466, 'samples': 15964608, 'steps': 83148, 'loss/train': 1.4212543964385986} 08/31/2021 04:15:09 - INFO - __main__ - Step 83150: {'lr': 0.00021220752639697325, 'samples': 15964800, 'steps': 83149, 'loss/train': 1.3056070804595947} 08/31/2021 04:15:09 - INFO - __main__ - Step 83151: {'lr': 0.0002122022806473286, 'samples': 15964992, 'steps': 83150, 'loss/train': 1.8999276161193848} 08/31/2021 04:15:10 - INFO - __main__ - Step 83152: {'lr': 0.00021219703491471501, 'samples': 15965184, 'steps': 83151, 'loss/train': 1.3567065000534058} 08/31/2021 04:15:10 - INFO - __main__ - Step 83153: {'lr': 0.00021219178919913484, 'samples': 15965376, 'steps': 83152, 'loss/train': 1.4727426767349243} 08/31/2021 04:15:10 - INFO - __main__ - Step 83154: {'lr': 0.00021218654350059048, 'samples': 15965568, 'steps': 83153, 'loss/train': 1.1676056385040283} 08/31/2021 04:15:12 - INFO - __main__ - Step 83155: {'lr': 0.0002121812978190843, 'samples': 15965760, 'steps': 83154, 'loss/train': 1.3742754459381104} 08/31/2021 04:15:12 - INFO - __main__ - Step 83156: {'lr': 0.00021217605215461863, 'samples': 15965952, 'steps': 83155, 'loss/train': 1.025046467781067} 08/31/2021 04:15:12 - INFO - __main__ - Step 83157: {'lr': 0.00021217080650719582, 'samples': 15966144, 'steps': 83156, 'loss/train': 1.2890173196792603} 08/31/2021 04:15:13 - INFO - __main__ - Step 83158: {'lr': 0.00021216556087681838, 'samples': 15966336, 'steps': 83157, 'loss/train': 1.1829227209091187} 08/31/2021 04:15:13 - INFO - __main__ - Step 83159: {'lr': 0.00021216031526348844, 'samples': 15966528, 'steps': 83158, 'loss/train': 1.7657967805862427} 08/31/2021 04:15:15 - INFO - __main__ - Step 83160: {'lr': 0.00021215506966720853, 'samples': 15966720, 'steps': 83159, 'loss/train': 1.081512689590454} 08/31/2021 04:15:15 - INFO - __main__ - Step 83161: {'lr': 0.00021214982408798098, 'samples': 15966912, 'steps': 83160, 'loss/train': 1.6844499111175537} 08/31/2021 04:15:16 - INFO - __main__ - Step 83162: {'lr': 0.00021214457852580806, 'samples': 15967104, 'steps': 83161, 'loss/train': 1.6350533962249756} 08/31/2021 04:15:16 - INFO - __main__ - Step 83163: {'lr': 0.00021213933298069225, 'samples': 15967296, 'steps': 83162, 'loss/train': 1.311242938041687} 08/31/2021 04:15:16 - INFO - __main__ - Step 83164: {'lr': 0.00021213408745263584, 'samples': 15967488, 'steps': 83163, 'loss/train': 1.1887834072113037} 08/31/2021 04:15:18 - INFO - __main__ - Step 83165: {'lr': 0.00021212884194164126, 'samples': 15967680, 'steps': 83164, 'loss/train': 0.7705188989639282} 08/31/2021 04:15:18 - INFO - __main__ - Step 83166: {'lr': 0.00021212359644771082, 'samples': 15967872, 'steps': 83165, 'loss/train': 1.175745964050293} 08/31/2021 04:15:19 - INFO - __main__ - Step 83167: {'lr': 0.0002121183509708469, 'samples': 15968064, 'steps': 83166, 'loss/train': 1.13267183303833} 08/31/2021 04:15:19 - INFO - __main__ - Step 83168: {'lr': 0.00021211310551105187, 'samples': 15968256, 'steps': 83167, 'loss/train': 1.7386982440948486} 08/31/2021 04:15:19 - INFO - __main__ - Step 83169: {'lr': 0.00021210786006832817, 'samples': 15968448, 'steps': 83168, 'loss/train': 1.191039800643921} 08/31/2021 04:15:20 - INFO - __main__ - Step 83170: {'lr': 0.000212102614642678, 'samples': 15968640, 'steps': 83169, 'loss/train': 1.455028772354126} 08/31/2021 04:15:21 - INFO - __main__ - Step 83171: {'lr': 0.0002120973692341038, 'samples': 15968832, 'steps': 83170, 'loss/train': 1.0643523931503296} 08/31/2021 04:15:22 - INFO - __main__ - Step 83172: {'lr': 0.00021209212384260795, 'samples': 15969024, 'steps': 83171, 'loss/train': 1.5065743923187256} 08/31/2021 04:15:22 - INFO - __main__ - Step 83173: {'lr': 0.0002120868784681928, 'samples': 15969216, 'steps': 83172, 'loss/train': 1.4894167184829712} 08/31/2021 04:15:22 - INFO - __main__ - Step 83174: {'lr': 0.00021208163311086078, 'samples': 15969408, 'steps': 83173, 'loss/train': 0.4324169158935547} 08/31/2021 04:15:23 - INFO - __main__ - Step 83175: {'lr': 0.00021207638777061413, 'samples': 15969600, 'steps': 83174, 'loss/train': 1.288562297821045} 08/31/2021 04:15:24 - INFO - __main__ - Step 83176: {'lr': 0.0002120711424474553, 'samples': 15969792, 'steps': 83175, 'loss/train': 0.9488716721534729} 08/31/2021 04:15:24 - INFO - __main__ - Step 83177: {'lr': 0.0002120658971413866, 'samples': 15969984, 'steps': 83176, 'loss/train': 1.4114947319030762} 08/31/2021 04:15:25 - INFO - __main__ - Step 83178: {'lr': 0.0002120606518524104, 'samples': 15970176, 'steps': 83177, 'loss/train': 1.6227340698242188} 08/31/2021 04:15:25 - INFO - __main__ - Step 83179: {'lr': 0.00021205540658052912, 'samples': 15970368, 'steps': 83178, 'loss/train': 0.8794837594032288} 08/31/2021 04:15:25 - INFO - __main__ - Step 83180: {'lr': 0.00021205016132574517, 'samples': 15970560, 'steps': 83179, 'loss/train': 0.5761649012565613} 08/31/2021 04:15:27 - INFO - __main__ - Step 83181: {'lr': 0.00021204491608806073, 'samples': 15970752, 'steps': 83180, 'loss/train': 1.582075834274292} 08/31/2021 04:15:28 - INFO - __main__ - Step 83182: {'lr': 0.00021203967086747826, 'samples': 15970944, 'steps': 83181, 'loss/train': 0.6944921016693115} 08/31/2021 04:15:28 - INFO - __main__ - Step 83183: {'lr': 0.00021203442566400016, 'samples': 15971136, 'steps': 83182, 'loss/train': 1.2345991134643555} 08/31/2021 04:15:29 - INFO - __main__ - Step 83184: {'lr': 0.00021202918047762874, 'samples': 15971328, 'steps': 83183, 'loss/train': 1.3627734184265137} 08/31/2021 04:15:29 - INFO - __main__ - Step 83185: {'lr': 0.00021202393530836641, 'samples': 15971520, 'steps': 83184, 'loss/train': 0.9379372596740723} 08/31/2021 04:15:30 - INFO - __main__ - Step 83186: {'lr': 0.0002120186901562155, 'samples': 15971712, 'steps': 83185, 'loss/train': 1.1290732622146606} 08/31/2021 04:15:31 - INFO - __main__ - Step 83187: {'lr': 0.00021201344502117837, 'samples': 15971904, 'steps': 83186, 'loss/train': 1.2271621227264404} 08/31/2021 04:15:31 - INFO - __main__ - Step 83188: {'lr': 0.00021200819990325746, 'samples': 15972096, 'steps': 83187, 'loss/train': 1.235074520111084} 08/31/2021 04:15:32 - INFO - __main__ - Step 83189: {'lr': 0.00021200295480245502, 'samples': 15972288, 'steps': 83188, 'loss/train': 0.7290339469909668} 08/31/2021 04:15:32 - INFO - __main__ - Step 83190: {'lr': 0.00021199770971877345, 'samples': 15972480, 'steps': 83189, 'loss/train': 1.3385872840881348} 08/31/2021 04:15:33 - INFO - __main__ - Step 83191: {'lr': 0.00021199246465221515, 'samples': 15972672, 'steps': 83190, 'loss/train': 1.1570581197738647} 08/31/2021 04:15:34 - INFO - __main__ - Step 83192: {'lr': 0.00021198721960278245, 'samples': 15972864, 'steps': 83191, 'loss/train': 1.3634377717971802} 08/31/2021 04:15:34 - INFO - __main__ - Step 83193: {'lr': 0.0002119819745704777, 'samples': 15973056, 'steps': 83192, 'loss/train': 2.1246590614318848} 08/31/2021 04:15:35 - INFO - __main__ - Step 83194: {'lr': 0.0002119767295553033, 'samples': 15973248, 'steps': 83193, 'loss/train': 2.049870729446411} 08/31/2021 04:15:35 - INFO - __main__ - Step 83195: {'lr': 0.00021197148455726162, 'samples': 15973440, 'steps': 83194, 'loss/train': 1.1218798160552979} 08/31/2021 04:15:36 - INFO - __main__ - Step 83196: {'lr': 0.00021196623957635497, 'samples': 15973632, 'steps': 83195, 'loss/train': 1.266923189163208} 08/31/2021 04:15:37 - INFO - __main__ - Step 83197: {'lr': 0.00021196099461258576, 'samples': 15973824, 'steps': 83196, 'loss/train': 0.730553925037384} 08/31/2021 04:15:37 - INFO - __main__ - Step 83198: {'lr': 0.00021195574966595632, 'samples': 15974016, 'steps': 83197, 'loss/train': 0.47512108087539673} 08/31/2021 04:15:38 - INFO - __main__ - Step 83199: {'lr': 0.00021195050473646904, 'samples': 15974208, 'steps': 83198, 'loss/train': 1.1545188426971436} 08/31/2021 04:15:38 - INFO - __main__ - Step 83200: {'lr': 0.00021194525982412628, 'samples': 15974400, 'steps': 83199, 'loss/train': 0.9550042748451233} 08/31/2021 04:15:40 - INFO - __main__ - Step 83201: {'lr': 0.0002119400149289305, 'samples': 15974592, 'steps': 83200, 'loss/train': 0.9807231426239014} 08/31/2021 04:15:40 - INFO - __main__ - Step 83202: {'lr': 0.00021193477005088386, 'samples': 15974784, 'steps': 83201, 'loss/train': 1.0893422365188599} 08/31/2021 04:15:40 - INFO - __main__ - Step 83203: {'lr': 0.00021192952518998883, 'samples': 15974976, 'steps': 83202, 'loss/train': 1.223537802696228} 08/31/2021 04:15:41 - INFO - __main__ - Step 83204: {'lr': 0.00021192428034624776, 'samples': 15975168, 'steps': 83203, 'loss/train': 1.1101713180541992} 08/31/2021 04:15:41 - INFO - __main__ - Step 83205: {'lr': 0.000211919035519663, 'samples': 15975360, 'steps': 83204, 'loss/train': 1.2973880767822266} 08/31/2021 04:15:41 - INFO - __main__ - Step 83206: {'lr': 0.00021191379071023697, 'samples': 15975552, 'steps': 83205, 'loss/train': 1.0459308624267578} 08/31/2021 04:15:43 - INFO - __main__ - Step 83207: {'lr': 0.00021190854591797198, 'samples': 15975744, 'steps': 83206, 'loss/train': 0.8265268206596375} 08/31/2021 04:15:43 - INFO - __main__ - Step 83208: {'lr': 0.00021190330114287043, 'samples': 15975936, 'steps': 83207, 'loss/train': 1.190839409828186} 08/31/2021 04:15:44 - INFO - __main__ - Step 83209: {'lr': 0.00021189805638493464, 'samples': 15976128, 'steps': 83208, 'loss/train': 1.8508259057998657} 08/31/2021 04:15:44 - INFO - __main__ - Step 83210: {'lr': 0.000211892811644167, 'samples': 15976320, 'steps': 83209, 'loss/train': 1.4314377307891846} 08/31/2021 04:15:44 - INFO - __main__ - Step 83211: {'lr': 0.0002118875669205699, 'samples': 15976512, 'steps': 83210, 'loss/train': 1.3069883584976196} 08/31/2021 04:15:46 - INFO - __main__ - Step 83212: {'lr': 0.00021188232221414565, 'samples': 15976704, 'steps': 83211, 'loss/train': 0.9716368317604065} 08/31/2021 04:15:47 - INFO - __main__ - Step 83213: {'lr': 0.00021187707752489665, 'samples': 15976896, 'steps': 83212, 'loss/train': 0.913612425327301} 08/31/2021 04:15:47 - INFO - __main__ - Step 83214: {'lr': 0.00021187183285282523, 'samples': 15977088, 'steps': 83213, 'loss/train': 0.09279996901750565} 08/31/2021 04:15:47 - INFO - __main__ - Step 83215: {'lr': 0.00021186658819793392, 'samples': 15977280, 'steps': 83214, 'loss/train': 0.9893968105316162} 08/31/2021 04:15:48 - INFO - __main__ - Step 83216: {'lr': 0.0002118613435602248, 'samples': 15977472, 'steps': 83215, 'loss/train': 1.05055832862854} 08/31/2021 04:15:49 - INFO - __main__ - Step 83217: {'lr': 0.00021185609893970036, 'samples': 15977664, 'steps': 83216, 'loss/train': 1.351904034614563} 08/31/2021 04:15:50 - INFO - __main__ - Step 83218: {'lr': 0.000211850854336363, 'samples': 15977856, 'steps': 83217, 'loss/train': 0.23355813324451447} 08/31/2021 04:15:50 - INFO - __main__ - Step 83219: {'lr': 0.00021184560975021506, 'samples': 15978048, 'steps': 83218, 'loss/train': 1.0329899787902832} 08/31/2021 04:15:50 - INFO - __main__ - Step 83220: {'lr': 0.00021184036518125888, 'samples': 15978240, 'steps': 83219, 'loss/train': 1.465665340423584} 08/31/2021 04:15:51 - INFO - __main__ - Step 83221: {'lr': 0.00021183512062949682, 'samples': 15978432, 'steps': 83220, 'loss/train': 1.5868585109710693} 08/31/2021 04:15:52 - INFO - __main__ - Step 83222: {'lr': 0.00021182987609493132, 'samples': 15978624, 'steps': 83221, 'loss/train': 0.8951586484909058} 08/31/2021 04:15:53 - INFO - __main__ - Step 83223: {'lr': 0.00021182463157756466, 'samples': 15978816, 'steps': 83222, 'loss/train': 1.6486752033233643} 08/31/2021 04:15:53 - INFO - __main__ - Step 83224: {'lr': 0.00021181938707739924, 'samples': 15979008, 'steps': 83223, 'loss/train': 0.9400146007537842} 08/31/2021 04:15:53 - INFO - __main__ - Step 83225: {'lr': 0.0002118141425944374, 'samples': 15979200, 'steps': 83224, 'loss/train': 1.6982184648513794} 08/31/2021 04:15:54 - INFO - __main__ - Step 83226: {'lr': 0.00021180889812868155, 'samples': 15979392, 'steps': 83225, 'loss/train': 0.9583619832992554} 08/31/2021 04:15:55 - INFO - __main__ - Step 83227: {'lr': 0.000211803653680134, 'samples': 15979584, 'steps': 83226, 'loss/train': 1.1365426778793335} 08/31/2021 04:15:56 - INFO - __main__ - Step 83228: {'lr': 0.00021179840924879723, 'samples': 15979776, 'steps': 83227, 'loss/train': 1.6406739950180054} 08/31/2021 04:15:56 - INFO - __main__ - Step 83229: {'lr': 0.0002117931648346734, 'samples': 15979968, 'steps': 83228, 'loss/train': 1.4661900997161865} 08/31/2021 04:15:57 - INFO - __main__ - Step 83230: {'lr': 0.000211787920437765, 'samples': 15980160, 'steps': 83229, 'loss/train': 0.11665437370538712} 08/31/2021 04:15:57 - INFO - __main__ - Step 83231: {'lr': 0.00021178267605807436, 'samples': 15980352, 'steps': 83230, 'loss/train': 0.19426672160625458} 08/31/2021 04:15:59 - INFO - __main__ - Step 83232: {'lr': 0.00021177743169560384, 'samples': 15980544, 'steps': 83231, 'loss/train': 0.09100951254367828} 08/31/2021 04:16:00 - INFO - __main__ - Step 83233: {'lr': 0.00021177218735035587, 'samples': 15980736, 'steps': 83232, 'loss/train': 1.18548583984375} 08/31/2021 04:16:00 - INFO - __main__ - Step 83234: {'lr': 0.0002117669430223327, 'samples': 15980928, 'steps': 83233, 'loss/train': 1.4828191995620728} 08/31/2021 04:16:00 - INFO - __main__ - Step 83235: {'lr': 0.0002117616987115368, 'samples': 15981120, 'steps': 83234, 'loss/train': 1.0163569450378418} 08/31/2021 04:16:01 - INFO - __main__ - Step 83236: {'lr': 0.00021175645441797047, 'samples': 15981312, 'steps': 83235, 'loss/train': 0.9881911873817444} 08/31/2021 04:16:02 - INFO - __main__ - Step 83237: {'lr': 0.0002117512101416361, 'samples': 15981504, 'steps': 83236, 'loss/train': 1.4253394603729248} 08/31/2021 04:16:03 - INFO - __main__ - Step 83238: {'lr': 0.00021174596588253603, 'samples': 15981696, 'steps': 83237, 'loss/train': 0.883152961730957} 08/31/2021 04:16:03 - INFO - __main__ - Step 83239: {'lr': 0.00021174072164067265, 'samples': 15981888, 'steps': 83238, 'loss/train': 0.46082836389541626} 08/31/2021 04:16:04 - INFO - __main__ - Step 83240: {'lr': 0.00021173547741604832, 'samples': 15982080, 'steps': 83239, 'loss/train': 1.0187047719955444} 08/31/2021 04:16:04 - INFO - __main__ - Step 83241: {'lr': 0.00021173023320866539, 'samples': 15982272, 'steps': 83240, 'loss/train': 1.0170254707336426} 08/31/2021 04:16:06 - INFO - __main__ - Step 83242: {'lr': 0.00021172498901852633, 'samples': 15982464, 'steps': 83241, 'loss/train': 1.068087100982666} 08/31/2021 04:16:06 - INFO - __main__ - Step 83243: {'lr': 0.00021171974484563327, 'samples': 15982656, 'steps': 83242, 'loss/train': 1.0487102270126343} 08/31/2021 04:16:07 - INFO - __main__ - Step 83244: {'lr': 0.0002117145006899887, 'samples': 15982848, 'steps': 83243, 'loss/train': 2.2220611572265625} 08/31/2021 04:16:07 - INFO - __main__ - Step 83245: {'lr': 0.00021170925655159505, 'samples': 15983040, 'steps': 83244, 'loss/train': 1.273695945739746} 08/31/2021 04:16:07 - INFO - __main__ - Step 83246: {'lr': 0.00021170401243045457, 'samples': 15983232, 'steps': 83245, 'loss/train': 1.1279704570770264} 08/31/2021 04:16:08 - INFO - __main__ - Step 83247: {'lr': 0.00021169876832656965, 'samples': 15983424, 'steps': 83246, 'loss/train': 0.7756161689758301} 08/31/2021 04:16:09 - INFO - __main__ - Step 83248: {'lr': 0.0002116935242399427, 'samples': 15983616, 'steps': 83247, 'loss/train': 1.5677964687347412} 08/31/2021 04:16:10 - INFO - __main__ - Step 83249: {'lr': 0.00021168828017057605, 'samples': 15983808, 'steps': 83248, 'loss/train': 1.2888108491897583} 08/31/2021 04:16:10 - INFO - __main__ - Step 83250: {'lr': 0.0002116830361184721, 'samples': 15984000, 'steps': 83249, 'loss/train': 1.4164198637008667} 08/31/2021 04:16:10 - INFO - __main__ - Step 83251: {'lr': 0.00021167779208363313, 'samples': 15984192, 'steps': 83250, 'loss/train': 1.638501763343811} 08/31/2021 04:16:11 - INFO - __main__ - Step 83252: {'lr': 0.0002116725480660616, 'samples': 15984384, 'steps': 83251, 'loss/train': 1.0862791538238525} 08/31/2021 04:16:12 - INFO - __main__ - Step 83253: {'lr': 0.0002116673040657598, 'samples': 15984576, 'steps': 83252, 'loss/train': 1.0485162734985352} 08/31/2021 04:16:13 - INFO - __main__ - Step 83254: {'lr': 0.00021166206008273015, 'samples': 15984768, 'steps': 83253, 'loss/train': 0.09242855757474899} 08/31/2021 04:16:13 - INFO - __main__ - Step 83255: {'lr': 0.00021165681611697506, 'samples': 15984960, 'steps': 83254, 'loss/train': 1.2419449090957642} 08/31/2021 04:16:14 - INFO - __main__ - Step 83256: {'lr': 0.00021165157216849673, 'samples': 15985152, 'steps': 83255, 'loss/train': 0.13162021338939667} 08/31/2021 04:16:14 - INFO - __main__ - Step 83257: {'lr': 0.00021164632823729763, 'samples': 15985344, 'steps': 83256, 'loss/train': 1.3717875480651855} 08/31/2021 04:16:15 - INFO - __main__ - Step 83258: {'lr': 0.00021164108432338005, 'samples': 15985536, 'steps': 83257, 'loss/train': 1.396836757659912} 08/31/2021 04:16:16 - INFO - __main__ - Step 83259: {'lr': 0.00021163584042674643, 'samples': 15985728, 'steps': 83258, 'loss/train': 1.260087251663208} 08/31/2021 04:16:16 - INFO - __main__ - Step 83260: {'lr': 0.00021163059654739913, 'samples': 15985920, 'steps': 83259, 'loss/train': 1.27071213722229} 08/31/2021 04:16:17 - INFO - __main__ - Step 83261: {'lr': 0.00021162535268534047, 'samples': 15986112, 'steps': 83260, 'loss/train': 1.1765947341918945} 08/31/2021 04:16:17 - INFO - __main__ - Step 83262: {'lr': 0.00021162010884057285, 'samples': 15986304, 'steps': 83261, 'loss/train': 1.084720253944397} 08/31/2021 04:16:18 - INFO - __main__ - Step 83263: {'lr': 0.00021161486501309858, 'samples': 15986496, 'steps': 83262, 'loss/train': 1.1312439441680908} 08/31/2021 04:16:19 - INFO - __main__ - Step 83264: {'lr': 0.0002116096212029201, 'samples': 15986688, 'steps': 83263, 'loss/train': 0.7033579349517822} 08/31/2021 04:16:19 - INFO - __main__ - Step 83265: {'lr': 0.00021160437741003972, 'samples': 15986880, 'steps': 83264, 'loss/train': 1.6229383945465088} 08/31/2021 04:16:20 - INFO - __main__ - Step 83266: {'lr': 0.00021159913363445979, 'samples': 15987072, 'steps': 83265, 'loss/train': 1.5549386739730835} 08/31/2021 04:16:20 - INFO - __main__ - Step 83267: {'lr': 0.00021159388987618272, 'samples': 15987264, 'steps': 83266, 'loss/train': 1.1207040548324585} 08/31/2021 04:16:21 - INFO - __main__ - Step 83268: {'lr': 0.00021158864613521095, 'samples': 15987456, 'steps': 83267, 'loss/train': 1.181736707687378} 08/31/2021 04:16:22 - INFO - __main__ - Step 83269: {'lr': 0.00021158340241154663, 'samples': 15987648, 'steps': 83268, 'loss/train': 0.7969127893447876} 08/31/2021 04:16:22 - INFO - __main__ - Step 83270: {'lr': 0.00021157815870519227, 'samples': 15987840, 'steps': 83269, 'loss/train': 0.028394198045134544} 08/31/2021 04:16:23 - INFO - __main__ - Step 83271: {'lr': 0.00021157291501615016, 'samples': 15988032, 'steps': 83270, 'loss/train': 1.408816933631897} 08/31/2021 04:16:23 - INFO - __main__ - Step 83272: {'lr': 0.00021156767134442272, 'samples': 15988224, 'steps': 83271, 'loss/train': 0.5540890097618103} 08/31/2021 04:16:24 - INFO - __main__ - Step 83273: {'lr': 0.0002115624276900123, 'samples': 15988416, 'steps': 83272, 'loss/train': 1.0355949401855469} 08/31/2021 04:16:25 - INFO - __main__ - Step 83274: {'lr': 0.00021155718405292123, 'samples': 15988608, 'steps': 83273, 'loss/train': 1.9220423698425293} 08/31/2021 04:16:25 - INFO - __main__ - Step 83275: {'lr': 0.00021155194043315193, 'samples': 15988800, 'steps': 83274, 'loss/train': 1.495369553565979} 08/31/2021 04:16:26 - INFO - __main__ - Step 83276: {'lr': 0.00021154669683070673, 'samples': 15988992, 'steps': 83275, 'loss/train': 1.7574255466461182} 08/31/2021 04:16:26 - INFO - __main__ - Step 83277: {'lr': 0.000211541453245588, 'samples': 15989184, 'steps': 83276, 'loss/train': 1.1641908884048462} 08/31/2021 04:16:26 - INFO - __main__ - Step 83278: {'lr': 0.00021153620967779806, 'samples': 15989376, 'steps': 83277, 'loss/train': 0.6961456537246704} 08/31/2021 04:16:28 - INFO - __main__ - Step 83279: {'lr': 0.00021153096612733935, 'samples': 15989568, 'steps': 83278, 'loss/train': 0.5348959565162659} 08/31/2021 04:16:28 - INFO - __main__ - Step 83280: {'lr': 0.00021152572259421415, 'samples': 15989760, 'steps': 83279, 'loss/train': 1.1118108034133911} 08/31/2021 04:16:29 - INFO - __main__ - Step 83281: {'lr': 0.00021152047907842497, 'samples': 15989952, 'steps': 83280, 'loss/train': 1.4013713598251343} 08/31/2021 04:16:29 - INFO - __main__ - Step 83282: {'lr': 0.00021151523557997405, 'samples': 15990144, 'steps': 83281, 'loss/train': 1.535379409790039} 08/31/2021 04:16:30 - INFO - __main__ - Step 83283: {'lr': 0.0002115099920988637, 'samples': 15990336, 'steps': 83282, 'loss/train': 3.352078914642334} 08/31/2021 04:16:32 - INFO - __main__ - Step 83284: {'lr': 0.00021150474863509635, 'samples': 15990528, 'steps': 83283, 'loss/train': 1.4274473190307617} 08/31/2021 04:16:32 - INFO - __main__ - Step 83285: {'lr': 0.0002114995051886744, 'samples': 15990720, 'steps': 83284, 'loss/train': 1.4140788316726685} 08/31/2021 04:16:32 - INFO - __main__ - Step 83286: {'lr': 0.00021149426175960017, 'samples': 15990912, 'steps': 83285, 'loss/train': 1.7443698644638062} 08/31/2021 04:16:33 - INFO - __main__ - Step 83287: {'lr': 0.00021148901834787601, 'samples': 15991104, 'steps': 83286, 'loss/train': 1.1686537265777588} 08/31/2021 04:16:33 - INFO - __main__ - Step 83288: {'lr': 0.00021148377495350433, 'samples': 15991296, 'steps': 83287, 'loss/train': 1.021224856376648} 08/31/2021 04:16:35 - INFO - __main__ - Step 83289: {'lr': 0.00021147853157648744, 'samples': 15991488, 'steps': 83288, 'loss/train': 1.0051968097686768} 08/31/2021 04:16:35 - INFO - __main__ - Step 83290: {'lr': 0.00021147328821682776, 'samples': 15991680, 'steps': 83289, 'loss/train': 1.2478816509246826} 08/31/2021 04:16:35 - INFO - __main__ - Step 83291: {'lr': 0.0002114680448745276, 'samples': 15991872, 'steps': 83290, 'loss/train': 0.9882538318634033} 08/31/2021 04:16:36 - INFO - __main__ - Step 83292: {'lr': 0.00021146280154958939, 'samples': 15992064, 'steps': 83291, 'loss/train': 1.151334285736084} 08/31/2021 04:16:36 - INFO - __main__ - Step 83293: {'lr': 0.0002114575582420154, 'samples': 15992256, 'steps': 83292, 'loss/train': 1.2565141916275024} 08/31/2021 04:16:36 - INFO - __main__ - Step 83294: {'lr': 0.00021145231495180806, 'samples': 15992448, 'steps': 83293, 'loss/train': 1.2813875675201416} 08/31/2021 04:16:38 - INFO - __main__ - Step 83295: {'lr': 0.00021144707167896975, 'samples': 15992640, 'steps': 83294, 'loss/train': 0.3869950771331787} 08/31/2021 04:16:38 - INFO - __main__ - Step 83296: {'lr': 0.00021144182842350274, 'samples': 15992832, 'steps': 83295, 'loss/train': 1.404746651649475} 08/31/2021 04:16:39 - INFO - __main__ - Step 83297: {'lr': 0.00021143658518540945, 'samples': 15993024, 'steps': 83296, 'loss/train': 0.3079380691051483} 08/31/2021 04:16:39 - INFO - __main__ - Step 83298: {'lr': 0.00021143134196469223, 'samples': 15993216, 'steps': 83297, 'loss/train': 1.1609512567520142} 08/31/2021 04:16:40 - INFO - __main__ - Step 83299: {'lr': 0.00021142609876135347, 'samples': 15993408, 'steps': 83298, 'loss/train': 0.7069187760353088} 08/31/2021 04:16:42 - INFO - __main__ - Step 83300: {'lr': 0.0002114208555753955, 'samples': 15993600, 'steps': 83299, 'loss/train': 1.7667323350906372} 08/31/2021 04:16:42 - INFO - __main__ - Step 83301: {'lr': 0.00021141561240682068, 'samples': 15993792, 'steps': 83300, 'loss/train': 1.2833365201950073} 08/31/2021 04:16:43 - INFO - __main__ - Step 83302: {'lr': 0.00021141036925563145, 'samples': 15993984, 'steps': 83301, 'loss/train': 0.6314284801483154} 08/31/2021 04:16:43 - INFO - __main__ - Step 83303: {'lr': 0.00021140512612183012, 'samples': 15994176, 'steps': 83302, 'loss/train': 0.7397109270095825} 08/31/2021 04:16:44 - INFO - __main__ - Step 83304: {'lr': 0.00021139988300541897, 'samples': 15994368, 'steps': 83303, 'loss/train': 1.781352162361145} 08/31/2021 04:16:44 - INFO - __main__ - Step 83305: {'lr': 0.0002113946399064005, 'samples': 15994560, 'steps': 83304, 'loss/train': 1.4450167417526245} 08/31/2021 04:16:44 - INFO - __main__ - Step 83306: {'lr': 0.00021138939682477698, 'samples': 15994752, 'steps': 83305, 'loss/train': 1.1365059614181519} 08/31/2021 04:16:46 - INFO - __main__ - Step 83307: {'lr': 0.0002113841537605508, 'samples': 15994944, 'steps': 83306, 'loss/train': 1.500900149345398} 08/31/2021 04:16:46 - INFO - __main__ - Step 83308: {'lr': 0.00021137891071372432, 'samples': 15995136, 'steps': 83307, 'loss/train': 1.5305938720703125} 08/31/2021 04:16:47 - INFO - __main__ - Step 83309: {'lr': 0.00021137366768429994, 'samples': 15995328, 'steps': 83308, 'loss/train': 1.1989818811416626} 08/31/2021 04:16:47 - INFO - __main__ - Step 83310: {'lr': 0.00021136842467227995, 'samples': 15995520, 'steps': 83309, 'loss/train': 1.5664676427841187} 08/31/2021 04:16:47 - INFO - __main__ - Step 83311: {'lr': 0.00021136318167766678, 'samples': 15995712, 'steps': 83310, 'loss/train': 0.9873847961425781} 08/31/2021 04:16:49 - INFO - __main__ - Step 83312: {'lr': 0.00021135793870046275, 'samples': 15995904, 'steps': 83311, 'loss/train': 0.2724045217037201} 08/31/2021 04:16:49 - INFO - __main__ - Step 83313: {'lr': 0.00021135269574067023, 'samples': 15996096, 'steps': 83312, 'loss/train': 1.1763842105865479} 08/31/2021 04:16:49 - INFO - __main__ - Step 83314: {'lr': 0.00021134745279829164, 'samples': 15996288, 'steps': 83313, 'loss/train': 1.3873482942581177} 08/31/2021 04:16:50 - INFO - __main__ - Step 83315: {'lr': 0.00021134220987332924, 'samples': 15996480, 'steps': 83314, 'loss/train': 2.195909023284912} 08/31/2021 04:16:50 - INFO - __main__ - Step 83316: {'lr': 0.00021133696696578545, 'samples': 15996672, 'steps': 83315, 'loss/train': 1.2448712587356567} 08/31/2021 04:16:52 - INFO - __main__ - Step 83317: {'lr': 0.00021133172407566261, 'samples': 15996864, 'steps': 83316, 'loss/train': 0.4439723491668701} 08/31/2021 04:16:52 - INFO - __main__ - Step 83318: {'lr': 0.0002113264812029631, 'samples': 15997056, 'steps': 83317, 'loss/train': 0.8995093703269958} 08/31/2021 04:16:53 - INFO - __main__ - Step 83319: {'lr': 0.0002113212383476893, 'samples': 15997248, 'steps': 83318, 'loss/train': 0.5358600616455078} 08/31/2021 04:16:53 - INFO - __main__ - Step 83320: {'lr': 0.00021131599550984354, 'samples': 15997440, 'steps': 83319, 'loss/train': 0.7164923548698425} 08/31/2021 04:16:53 - INFO - __main__ - Step 83321: {'lr': 0.0002113107526894282, 'samples': 15997632, 'steps': 83320, 'loss/train': 1.2455332279205322} 08/31/2021 04:16:54 - INFO - __main__ - Step 83322: {'lr': 0.0002113055098864457, 'samples': 15997824, 'steps': 83321, 'loss/train': 1.1706223487854004} 08/31/2021 04:16:55 - INFO - __main__ - Step 83323: {'lr': 0.00021130026710089827, 'samples': 15998016, 'steps': 83322, 'loss/train': 1.7356526851654053} 08/31/2021 04:16:56 - INFO - __main__ - Step 83324: {'lr': 0.00021129502433278835, 'samples': 15998208, 'steps': 83323, 'loss/train': 0.4868875741958618} 08/31/2021 04:16:56 - INFO - __main__ - Step 83325: {'lr': 0.00021128978158211834, 'samples': 15998400, 'steps': 83324, 'loss/train': 1.5111279487609863} 08/31/2021 04:16:56 - INFO - __main__ - Step 83326: {'lr': 0.0002112845388488905, 'samples': 15998592, 'steps': 83325, 'loss/train': 3.3127965927124023} 08/31/2021 04:16:57 - INFO - __main__ - Step 83327: {'lr': 0.00021127929613310725, 'samples': 15998784, 'steps': 83326, 'loss/train': 1.0921236276626587} 08/31/2021 04:16:58 - INFO - __main__ - Step 83328: {'lr': 0.000211274053434771, 'samples': 15998976, 'steps': 83327, 'loss/train': 1.410658836364746} 08/31/2021 04:16:59 - INFO - __main__ - Step 83329: {'lr': 0.00021126881075388403, 'samples': 15999168, 'steps': 83328, 'loss/train': 0.8231792449951172} 08/31/2021 04:16:59 - INFO - __main__ - Step 83330: {'lr': 0.00021126356809044873, 'samples': 15999360, 'steps': 83329, 'loss/train': 1.406597375869751} 08/31/2021 04:17:00 - INFO - __main__ - Step 83331: {'lr': 0.00021125832544446744, 'samples': 15999552, 'steps': 83330, 'loss/train': 1.5777356624603271} 08/31/2021 04:17:00 - INFO - __main__ - Step 83332: {'lr': 0.0002112530828159426, 'samples': 15999744, 'steps': 83331, 'loss/train': 0.2461230307817459} 08/31/2021 04:17:01 - INFO - __main__ - Step 83333: {'lr': 0.0002112478402048765, 'samples': 15999936, 'steps': 83332, 'loss/train': 1.1995688676834106} 08/31/2021 04:17:02 - INFO - __main__ - Step 83334: {'lr': 0.00021124259761127153, 'samples': 16000128, 'steps': 83333, 'loss/train': 1.3135700225830078} 08/31/2021 04:17:02 - INFO - __main__ - Step 83335: {'lr': 0.00021123735503513004, 'samples': 16000320, 'steps': 83334, 'loss/train': 1.0239791870117188} 08/31/2021 04:17:03 - INFO - __main__ - Step 83336: {'lr': 0.00021123211247645453, 'samples': 16000512, 'steps': 83335, 'loss/train': 1.5261833667755127} 08/31/2021 04:17:03 - INFO - __main__ - Step 83337: {'lr': 0.0002112268699352471, 'samples': 16000704, 'steps': 83336, 'loss/train': 0.7518793940544128} 08/31/2021 04:17:04 - INFO - __main__ - Step 83338: {'lr': 0.00021122162741151024, 'samples': 16000896, 'steps': 83337, 'loss/train': 0.813057005405426} 08/31/2021 04:17:05 - INFO - __main__ - Step 83339: {'lr': 0.00021121638490524634, 'samples': 16001088, 'steps': 83338, 'loss/train': 0.9654436111450195} 08/31/2021 04:17:05 - INFO - __main__ - Step 83340: {'lr': 0.00021121114241645772, 'samples': 16001280, 'steps': 83339, 'loss/train': 0.6877073645591736} 08/31/2021 04:17:06 - INFO - __main__ - Step 83341: {'lr': 0.0002112058999451468, 'samples': 16001472, 'steps': 83340, 'loss/train': 1.3021280765533447} 08/31/2021 04:17:06 - INFO - __main__ - Step 83342: {'lr': 0.00021120065749131585, 'samples': 16001664, 'steps': 83341, 'loss/train': 1.6394673585891724} 08/31/2021 04:17:08 - INFO - __main__ - Step 83343: {'lr': 0.0002111954150549673, 'samples': 16001856, 'steps': 83342, 'loss/train': 2.15260648727417} 08/31/2021 04:17:08 - INFO - __main__ - Step 83344: {'lr': 0.0002111901726361035, 'samples': 16002048, 'steps': 83343, 'loss/train': 1.126521110534668} 08/31/2021 04:17:09 - INFO - __main__ - Step 83345: {'lr': 0.00021118493023472682, 'samples': 16002240, 'steps': 83344, 'loss/train': 1.3681939840316772} 08/31/2021 04:17:09 - INFO - __main__ - Step 83346: {'lr': 0.0002111796878508396, 'samples': 16002432, 'steps': 83345, 'loss/train': 0.7589008212089539} 08/31/2021 04:17:09 - INFO - __main__ - Step 83347: {'lr': 0.00021117444548444424, 'samples': 16002624, 'steps': 83346, 'loss/train': 1.215505838394165} 08/31/2021 04:17:11 - INFO - __main__ - Step 83348: {'lr': 0.00021116920313554304, 'samples': 16002816, 'steps': 83347, 'loss/train': 1.6087939739227295} 08/31/2021 04:17:11 - INFO - __main__ - Step 83349: {'lr': 0.00021116396080413853, 'samples': 16003008, 'steps': 83348, 'loss/train': 1.1259461641311646} 08/31/2021 04:17:12 - INFO - __main__ - Step 83350: {'lr': 0.0002111587184902328, 'samples': 16003200, 'steps': 83349, 'loss/train': 1.352907657623291} 08/31/2021 04:17:12 - INFO - __main__ - Step 83351: {'lr': 0.00021115347619382838, 'samples': 16003392, 'steps': 83350, 'loss/train': 1.618986964225769} 08/31/2021 04:17:12 - INFO - __main__ - Step 83352: {'lr': 0.0002111482339149276, 'samples': 16003584, 'steps': 83351, 'loss/train': 0.47227609157562256} 08/31/2021 04:17:14 - INFO - __main__ - Step 83353: {'lr': 0.00021114299165353283, 'samples': 16003776, 'steps': 83352, 'loss/train': 1.5707446336746216} 08/31/2021 04:17:14 - INFO - __main__ - Step 83354: {'lr': 0.00021113774940964642, 'samples': 16003968, 'steps': 83353, 'loss/train': 0.9011204242706299} 08/31/2021 04:17:15 - INFO - __main__ - Step 83355: {'lr': 0.00021113250718327072, 'samples': 16004160, 'steps': 83354, 'loss/train': 1.1646244525909424} 08/31/2021 04:17:15 - INFO - __main__ - Step 83356: {'lr': 0.00021112726497440814, 'samples': 16004352, 'steps': 83355, 'loss/train': 1.3566099405288696} 08/31/2021 04:17:15 - INFO - __main__ - Step 83357: {'lr': 0.00021112202278306103, 'samples': 16004544, 'steps': 83356, 'loss/train': 1.3852311372756958} 08/31/2021 04:17:17 - INFO - __main__ - Step 83358: {'lr': 0.0002111167806092317, 'samples': 16004736, 'steps': 83357, 'loss/train': 1.2140992879867554} 08/31/2021 04:17:17 - INFO - __main__ - Step 83359: {'lr': 0.00021111153845292257, 'samples': 16004928, 'steps': 83358, 'loss/train': 0.22965937852859497} 08/31/2021 04:17:18 - INFO - __main__ - Step 83360: {'lr': 0.00021110629631413598, 'samples': 16005120, 'steps': 83359, 'loss/train': 0.7958980202674866} 08/31/2021 04:17:18 - INFO - __main__ - Step 83361: {'lr': 0.00021110105419287428, 'samples': 16005312, 'steps': 83360, 'loss/train': 1.4192497730255127} 08/31/2021 04:17:18 - INFO - __main__ - Step 83362: {'lr': 0.00021109581208913987, 'samples': 16005504, 'steps': 83361, 'loss/train': 0.2997550070285797} 08/31/2021 04:17:19 - INFO - __main__ - Step 83363: {'lr': 0.00021109057000293516, 'samples': 16005696, 'steps': 83362, 'loss/train': 0.9989827275276184} 08/31/2021 04:17:20 - INFO - __main__ - Step 83364: {'lr': 0.00021108532793426236, 'samples': 16005888, 'steps': 83363, 'loss/train': 1.1497284173965454} 08/31/2021 04:17:21 - INFO - __main__ - Step 83365: {'lr': 0.00021108008588312387, 'samples': 16006080, 'steps': 83364, 'loss/train': 0.5453353524208069} 08/31/2021 04:17:21 - INFO - __main__ - Step 83366: {'lr': 0.00021107484384952214, 'samples': 16006272, 'steps': 83365, 'loss/train': 1.442607045173645} 08/31/2021 04:17:21 - INFO - __main__ - Step 83367: {'lr': 0.00021106960183345946, 'samples': 16006464, 'steps': 83366, 'loss/train': 1.2018405199050903} 08/31/2021 04:17:22 - INFO - __main__ - Step 83368: {'lr': 0.00021106435983493822, 'samples': 16006656, 'steps': 83367, 'loss/train': 1.617476224899292} 08/31/2021 04:17:24 - INFO - __main__ - Step 83369: {'lr': 0.0002110591178539608, 'samples': 16006848, 'steps': 83368, 'loss/train': 1.1719738245010376} 08/31/2021 04:17:24 - INFO - __main__ - Step 83370: {'lr': 0.0002110538758905295, 'samples': 16007040, 'steps': 83369, 'loss/train': 1.194054126739502} 08/31/2021 04:17:24 - INFO - __main__ - Step 83371: {'lr': 0.00021104863394464678, 'samples': 16007232, 'steps': 83370, 'loss/train': 0.1575275957584381} 08/31/2021 04:17:25 - INFO - __main__ - Step 83372: {'lr': 0.0002110433920163149, 'samples': 16007424, 'steps': 83371, 'loss/train': 1.4741690158843994} 08/31/2021 04:17:25 - INFO - __main__ - Step 83373: {'lr': 0.00021103815010553627, 'samples': 16007616, 'steps': 83372, 'loss/train': 1.1769026517868042} 08/31/2021 04:17:27 - INFO - __main__ - Step 83374: {'lr': 0.00021103290821231324, 'samples': 16007808, 'steps': 83373, 'loss/train': 0.27156862616539} 08/31/2021 04:17:27 - INFO - __main__ - Step 83375: {'lr': 0.0002110276663366482, 'samples': 16008000, 'steps': 83374, 'loss/train': 0.8436658382415771} 08/31/2021 04:17:28 - INFO - __main__ - Step 83376: {'lr': 0.0002110224244785436, 'samples': 16008192, 'steps': 83375, 'loss/train': 1.934710144996643} 08/31/2021 04:17:28 - INFO - __main__ - Step 83377: {'lr': 0.00021101718263800157, 'samples': 16008384, 'steps': 83376, 'loss/train': 0.7042102217674255} 08/31/2021 04:17:28 - INFO - __main__ - Step 83378: {'lr': 0.00021101194081502462, 'samples': 16008576, 'steps': 83377, 'loss/train': 0.999701976776123} 08/31/2021 04:17:30 - INFO - __main__ - Step 83379: {'lr': 0.00021100669900961505, 'samples': 16008768, 'steps': 83378, 'loss/train': 0.5615323781967163} 08/31/2021 04:17:30 - INFO - __main__ - Step 83380: {'lr': 0.0002110014572217753, 'samples': 16008960, 'steps': 83379, 'loss/train': 1.211995005607605} 08/31/2021 04:17:31 - INFO - __main__ - Step 83381: {'lr': 0.00021099621545150768, 'samples': 16009152, 'steps': 83380, 'loss/train': 1.2283854484558105} 08/31/2021 04:17:31 - INFO - __main__ - Step 83382: {'lr': 0.00021099097369881457, 'samples': 16009344, 'steps': 83381, 'loss/train': 0.7423892617225647} 08/31/2021 04:17:31 - INFO - __main__ - Step 83383: {'lr': 0.0002109857319636983, 'samples': 16009536, 'steps': 83382, 'loss/train': 0.581821084022522} 08/31/2021 04:17:32 - INFO - __main__ - Step 83384: {'lr': 0.00021098049024616128, 'samples': 16009728, 'steps': 83383, 'loss/train': 1.3760387897491455} 08/31/2021 04:17:33 - INFO - __main__ - Step 83385: {'lr': 0.00021097524854620585, 'samples': 16009920, 'steps': 83384, 'loss/train': 1.1897566318511963} 08/31/2021 04:17:34 - INFO - __main__ - Step 83386: {'lr': 0.00021097000686383437, 'samples': 16010112, 'steps': 83385, 'loss/train': 0.8216682076454163} 08/31/2021 04:17:34 - INFO - __main__ - Step 83387: {'lr': 0.00021096476519904918, 'samples': 16010304, 'steps': 83386, 'loss/train': 0.9852937459945679} 08/31/2021 04:17:34 - INFO - __main__ - Step 83388: {'lr': 0.00021095952355185265, 'samples': 16010496, 'steps': 83387, 'loss/train': 1.1235438585281372} 08/31/2021 04:17:35 - INFO - __main__ - Step 83389: {'lr': 0.0002109542819222473, 'samples': 16010688, 'steps': 83388, 'loss/train': 0.9800348281860352} 08/31/2021 04:17:36 - INFO - __main__ - Step 83390: {'lr': 0.00021094904031023525, 'samples': 16010880, 'steps': 83389, 'loss/train': 1.1968514919281006} 08/31/2021 04:17:37 - INFO - __main__ - Step 83391: {'lr': 0.00021094379871581896, 'samples': 16011072, 'steps': 83390, 'loss/train': 1.3639472723007202} 08/31/2021 04:17:37 - INFO - __main__ - Step 83392: {'lr': 0.00021093855713900077, 'samples': 16011264, 'steps': 83391, 'loss/train': 1.2476238012313843} 08/31/2021 04:17:38 - INFO - __main__ - Step 83393: {'lr': 0.00021093331557978307, 'samples': 16011456, 'steps': 83392, 'loss/train': 1.1049615144729614} 08/31/2021 04:17:38 - INFO - __main__ - Step 83394: {'lr': 0.00021092807403816819, 'samples': 16011648, 'steps': 83393, 'loss/train': 0.40808379650115967} 08/31/2021 04:17:40 - INFO - __main__ - Step 83395: {'lr': 0.00021092283251415855, 'samples': 16011840, 'steps': 83394, 'loss/train': 0.8479914665222168} 08/31/2021 04:17:41 - INFO - __main__ - Step 83396: {'lr': 0.0002109175910077565, 'samples': 16012032, 'steps': 83395, 'loss/train': 1.6289153099060059} 08/31/2021 04:17:41 - INFO - __main__ - Step 83397: {'lr': 0.0002109123495189643, 'samples': 16012224, 'steps': 83396, 'loss/train': 1.5121147632598877} 08/31/2021 04:17:41 - INFO - __main__ - Step 83398: {'lr': 0.00021090710804778446, 'samples': 16012416, 'steps': 83397, 'loss/train': 1.5475871562957764} 08/31/2021 04:17:42 - INFO - __main__ - Step 83399: {'lr': 0.00021090186659421926, 'samples': 16012608, 'steps': 83398, 'loss/train': 0.25875383615493774} 08/31/2021 04:17:43 - INFO - __main__ - Step 83400: {'lr': 0.00021089662515827107, 'samples': 16012800, 'steps': 83399, 'loss/train': 1.0106432437896729} 08/31/2021 04:17:44 - INFO - __main__ - Step 83401: {'lr': 0.00021089138373994224, 'samples': 16012992, 'steps': 83400, 'loss/train': 0.3152414560317993} 08/31/2021 04:17:44 - INFO - __main__ - Step 83402: {'lr': 0.00021088614233923518, 'samples': 16013184, 'steps': 83401, 'loss/train': 0.7226964235305786} 08/31/2021 04:17:44 - INFO - __main__ - Step 83403: {'lr': 0.0002108809009561523, 'samples': 16013376, 'steps': 83402, 'loss/train': 1.2770740985870361} 08/31/2021 04:17:45 - INFO - __main__ - Step 83404: {'lr': 0.0002108756595906958, 'samples': 16013568, 'steps': 83403, 'loss/train': 0.9048340916633606} 08/31/2021 04:17:46 - INFO - __main__ - Step 83405: {'lr': 0.00021087041824286812, 'samples': 16013760, 'steps': 83404, 'loss/train': 1.4884980916976929} 08/31/2021 04:17:47 - INFO - __main__ - Step 83406: {'lr': 0.00021086517691267163, 'samples': 16013952, 'steps': 83405, 'loss/train': 1.3566349744796753} 08/31/2021 04:17:47 - INFO - __main__ - Step 83407: {'lr': 0.00021085993560010865, 'samples': 16014144, 'steps': 83406, 'loss/train': 1.3216954469680786} 08/31/2021 04:17:47 - INFO - __main__ - Step 83408: {'lr': 0.0002108546943051816, 'samples': 16014336, 'steps': 83407, 'loss/train': 0.9939111471176147} 08/31/2021 04:17:48 - INFO - __main__ - Step 83409: {'lr': 0.00021084945302789286, 'samples': 16014528, 'steps': 83408, 'loss/train': 1.0492042303085327} 08/31/2021 04:17:50 - INFO - __main__ - Step 83410: {'lr': 0.0002108442117682447, 'samples': 16014720, 'steps': 83409, 'loss/train': 1.3589352369308472} 08/31/2021 04:17:50 - INFO - __main__ - Step 83411: {'lr': 0.00021083897052623956, 'samples': 16014912, 'steps': 83410, 'loss/train': 0.9542245268821716} 08/31/2021 04:17:51 - INFO - __main__ - Step 83412: {'lr': 0.00021083372930187977, 'samples': 16015104, 'steps': 83411, 'loss/train': 1.3218400478363037} 08/31/2021 04:17:51 - INFO - __main__ - Step 83413: {'lr': 0.0002108284880951677, 'samples': 16015296, 'steps': 83412, 'loss/train': 1.338430404663086} 08/31/2021 04:17:51 - INFO - __main__ - Step 83414: {'lr': 0.0002108232469061057, 'samples': 16015488, 'steps': 83413, 'loss/train': 0.025522474199533463} 08/31/2021 04:17:52 - INFO - __main__ - Step 83415: {'lr': 0.00021081800573469615, 'samples': 16015680, 'steps': 83414, 'loss/train': 0.8494752645492554} 08/31/2021 04:17:53 - INFO - __main__ - Step 83416: {'lr': 0.0002108127645809415, 'samples': 16015872, 'steps': 83415, 'loss/train': 0.1271897554397583} 08/31/2021 04:17:54 - INFO - __main__ - Step 83417: {'lr': 0.00021080752344484392, 'samples': 16016064, 'steps': 83416, 'loss/train': 1.3899964094161987} 08/31/2021 04:17:54 - INFO - __main__ - Step 83418: {'lr': 0.00021080228232640586, 'samples': 16016256, 'steps': 83417, 'loss/train': 1.4962159395217896} 08/31/2021 04:17:54 - INFO - __main__ - Step 83419: {'lr': 0.0002107970412256297, 'samples': 16016448, 'steps': 83418, 'loss/train': 0.7857679724693298} 08/31/2021 04:17:55 - INFO - __main__ - Step 83420: {'lr': 0.00021079180014251775, 'samples': 16016640, 'steps': 83419, 'loss/train': 3.0868191719055176} 08/31/2021 04:17:56 - INFO - __main__ - Step 83421: {'lr': 0.00021078655907707242, 'samples': 16016832, 'steps': 83420, 'loss/train': 1.1432794332504272} 08/31/2021 04:17:57 - INFO - __main__ - Step 83422: {'lr': 0.00021078131802929607, 'samples': 16017024, 'steps': 83421, 'loss/train': 0.30823323130607605} 08/31/2021 04:17:57 - INFO - __main__ - Step 83423: {'lr': 0.00021077607699919104, 'samples': 16017216, 'steps': 83422, 'loss/train': 1.0843729972839355} 08/31/2021 04:17:57 - INFO - __main__ - Step 83424: {'lr': 0.00021077083598675973, 'samples': 16017408, 'steps': 83423, 'loss/train': 1.3692609071731567} 08/31/2021 04:17:58 - INFO - __main__ - Step 83425: {'lr': 0.0002107655949920045, 'samples': 16017600, 'steps': 83424, 'loss/train': 1.387143850326538} 08/31/2021 04:17:59 - INFO - __main__ - Step 83426: {'lr': 0.00021076035401492764, 'samples': 16017792, 'steps': 83425, 'loss/train': 1.0111627578735352} 08/31/2021 04:18:00 - INFO - __main__ - Step 83427: {'lr': 0.0002107551130555316, 'samples': 16017984, 'steps': 83426, 'loss/train': 1.8230043649673462} 08/31/2021 04:18:00 - INFO - __main__ - Step 83428: {'lr': 0.00021074987211381867, 'samples': 16018176, 'steps': 83427, 'loss/train': 1.5604636669158936} 08/31/2021 04:18:00 - INFO - __main__ - Step 83429: {'lr': 0.00021074463118979126, 'samples': 16018368, 'steps': 83428, 'loss/train': 0.8233278393745422} 08/31/2021 04:18:01 - INFO - __main__ - Step 83430: {'lr': 0.00021073939028345173, 'samples': 16018560, 'steps': 83429, 'loss/train': 0.8233450651168823} 08/31/2021 04:18:01 - INFO - __main__ - Step 83431: {'lr': 0.00021073414939480243, 'samples': 16018752, 'steps': 83430, 'loss/train': 1.009826421737671} 08/31/2021 04:18:02 - INFO - __main__ - Step 83432: {'lr': 0.00021072890852384565, 'samples': 16018944, 'steps': 83431, 'loss/train': 0.7750988602638245} 08/31/2021 04:18:03 - INFO - __main__ - Step 83433: {'lr': 0.00021072366767058387, 'samples': 16019136, 'steps': 83432, 'loss/train': 1.448671579360962} 08/31/2021 04:18:03 - INFO - __main__ - Step 83434: {'lr': 0.00021071842683501938, 'samples': 16019328, 'steps': 83433, 'loss/train': 1.034340262413025} 08/31/2021 04:18:04 - INFO - __main__ - Step 83435: {'lr': 0.00021071318601715455, 'samples': 16019520, 'steps': 83434, 'loss/train': 1.699137568473816} 08/31/2021 04:18:04 - INFO - __main__ - Step 83436: {'lr': 0.00021070794521699178, 'samples': 16019712, 'steps': 83435, 'loss/train': 1.3223092555999756} 08/31/2021 04:18:07 - INFO - __main__ - Step 83437: {'lr': 0.0002107027044345334, 'samples': 16019904, 'steps': 83436, 'loss/train': 1.1791657209396362} 08/31/2021 04:18:07 - INFO - __main__ - Step 83438: {'lr': 0.00021069746366978177, 'samples': 16020096, 'steps': 83437, 'loss/train': 0.8346964120864868} 08/31/2021 04:18:07 - INFO - __main__ - Step 83439: {'lr': 0.00021069222292273922, 'samples': 16020288, 'steps': 83438, 'loss/train': 0.6831377744674683} 08/31/2021 04:18:08 - INFO - __main__ - Step 83440: {'lr': 0.0002106869821934082, 'samples': 16020480, 'steps': 83439, 'loss/train': 1.4299253225326538} 08/31/2021 04:18:08 - INFO - __main__ - Step 83441: {'lr': 0.00021068174148179098, 'samples': 16020672, 'steps': 83440, 'loss/train': 1.0950496196746826} 08/31/2021 04:18:09 - INFO - __main__ - Step 83442: {'lr': 0.00021067650078788997, 'samples': 16020864, 'steps': 83441, 'loss/train': 1.6664198637008667} 08/31/2021 04:18:09 - INFO - __main__ - Step 83443: {'lr': 0.0002106712601117076, 'samples': 16021056, 'steps': 83442, 'loss/train': 1.7395826578140259} 08/31/2021 04:18:09 - INFO - __main__ - Step 83444: {'lr': 0.00021066601945324607, 'samples': 16021248, 'steps': 83443, 'loss/train': 1.7795354127883911} 08/31/2021 04:18:11 - INFO - __main__ - Step 83445: {'lr': 0.00021066077881250783, 'samples': 16021440, 'steps': 83444, 'loss/train': 1.4890029430389404} 08/31/2021 04:18:11 - INFO - __main__ - Step 83446: {'lr': 0.00021065553818949524, 'samples': 16021632, 'steps': 83445, 'loss/train': 1.2571384906768799} 08/31/2021 04:18:11 - INFO - __main__ - Step 83447: {'lr': 0.00021065029758421063, 'samples': 16021824, 'steps': 83446, 'loss/train': 1.021432876586914} 08/31/2021 04:18:12 - INFO - __main__ - Step 83448: {'lr': 0.00021064505699665647, 'samples': 16022016, 'steps': 83447, 'loss/train': 1.1288384199142456} 08/31/2021 04:18:12 - INFO - __main__ - Step 83449: {'lr': 0.000210639816426835, 'samples': 16022208, 'steps': 83448, 'loss/train': 1.3455524444580078} 08/31/2021 04:18:14 - INFO - __main__ - Step 83450: {'lr': 0.0002106345758747486, 'samples': 16022400, 'steps': 83449, 'loss/train': 1.5828028917312622} 08/31/2021 04:18:14 - INFO - __main__ - Step 83451: {'lr': 0.00021062933534039965, 'samples': 16022592, 'steps': 83450, 'loss/train': 0.6953757405281067} 08/31/2021 04:18:15 - INFO - __main__ - Step 83452: {'lr': 0.00021062409482379052, 'samples': 16022784, 'steps': 83451, 'loss/train': 1.391615390777588} 08/31/2021 04:18:15 - INFO - __main__ - Step 83453: {'lr': 0.00021061885432492358, 'samples': 16022976, 'steps': 83452, 'loss/train': 0.16490770876407623} 08/31/2021 04:18:15 - INFO - __main__ - Step 83454: {'lr': 0.00021061361384380119, 'samples': 16023168, 'steps': 83453, 'loss/train': 1.844387173652649} 08/31/2021 04:18:17 - INFO - __main__ - Step 83455: {'lr': 0.00021060837338042566, 'samples': 16023360, 'steps': 83454, 'loss/train': 1.0763320922851562} 08/31/2021 04:18:18 - INFO - __main__ - Step 83456: {'lr': 0.0002106031329347994, 'samples': 16023552, 'steps': 83455, 'loss/train': 1.519611120223999} 08/31/2021 04:18:18 - INFO - __main__ - Step 83457: {'lr': 0.0002105978925069248, 'samples': 16023744, 'steps': 83456, 'loss/train': 0.7476758360862732} 08/31/2021 04:18:18 - INFO - __main__ - Step 83458: {'lr': 0.00021059265209680413, 'samples': 16023936, 'steps': 83457, 'loss/train': 1.4203829765319824} 08/31/2021 04:18:19 - INFO - __main__ - Step 83459: {'lr': 0.0002105874117044399, 'samples': 16024128, 'steps': 83458, 'loss/train': 1.4425958395004272} 08/31/2021 04:18:21 - INFO - __main__ - Step 83460: {'lr': 0.00021058217132983426, 'samples': 16024320, 'steps': 83459, 'loss/train': 0.9348284602165222} 08/31/2021 04:18:21 - INFO - __main__ - Step 83461: {'lr': 0.00021057693097298975, 'samples': 16024512, 'steps': 83460, 'loss/train': 0.997927725315094} 08/31/2021 04:18:21 - INFO - __main__ - Step 83462: {'lr': 0.0002105716906339086, 'samples': 16024704, 'steps': 83461, 'loss/train': 1.1930159330368042} 08/31/2021 04:18:22 - INFO - __main__ - Step 83463: {'lr': 0.0002105664503125933, 'samples': 16024896, 'steps': 83462, 'loss/train': 1.5860507488250732} 08/31/2021 04:18:22 - INFO - __main__ - Step 83464: {'lr': 0.0002105612100090461, 'samples': 16025088, 'steps': 83463, 'loss/train': 1.386692762374878} 08/31/2021 04:18:22 - INFO - __main__ - Step 83465: {'lr': 0.00021055596972326942, 'samples': 16025280, 'steps': 83464, 'loss/train': 1.4907050132751465} 08/31/2021 04:18:24 - INFO - __main__ - Step 83466: {'lr': 0.00021055072945526564, 'samples': 16025472, 'steps': 83465, 'loss/train': 1.1739211082458496} 08/31/2021 04:18:24 - INFO - __main__ - Step 83467: {'lr': 0.00021054548920503705, 'samples': 16025664, 'steps': 83466, 'loss/train': 1.3022174835205078} 08/31/2021 04:18:25 - INFO - __main__ - Step 83468: {'lr': 0.0002105402489725861, 'samples': 16025856, 'steps': 83467, 'loss/train': 1.1940480470657349} 08/31/2021 04:18:25 - INFO - __main__ - Step 83469: {'lr': 0.00021053500875791508, 'samples': 16026048, 'steps': 83468, 'loss/train': 1.4787451028823853} 08/31/2021 04:18:25 - INFO - __main__ - Step 83470: {'lr': 0.00021052976856102647, 'samples': 16026240, 'steps': 83469, 'loss/train': 0.8561457395553589} 08/31/2021 04:18:27 - INFO - __main__ - Step 83471: {'lr': 0.00021052452838192244, 'samples': 16026432, 'steps': 83470, 'loss/train': 1.3598034381866455} 08/31/2021 04:18:27 - INFO - __main__ - Step 83472: {'lr': 0.00021051928822060544, 'samples': 16026624, 'steps': 83471, 'loss/train': 0.7417938709259033} 08/31/2021 04:18:28 - INFO - __main__ - Step 83473: {'lr': 0.00021051404807707785, 'samples': 16026816, 'steps': 83472, 'loss/train': 0.8415448665618896} 08/31/2021 04:18:28 - INFO - __main__ - Step 83474: {'lr': 0.00021050880795134202, 'samples': 16027008, 'steps': 83473, 'loss/train': 0.5819481611251831} 08/31/2021 04:18:28 - INFO - __main__ - Step 83475: {'lr': 0.00021050356784340033, 'samples': 16027200, 'steps': 83474, 'loss/train': 1.2278409004211426} 08/31/2021 04:18:30 - INFO - __main__ - Step 83476: {'lr': 0.0002104983277532551, 'samples': 16027392, 'steps': 83475, 'loss/train': 1.4207881689071655} 08/31/2021 04:18:30 - INFO - __main__ - Step 83477: {'lr': 0.00021049308768090875, 'samples': 16027584, 'steps': 83476, 'loss/train': 1.0913524627685547} 08/31/2021 04:18:31 - INFO - __main__ - Step 83478: {'lr': 0.00021048784762636355, 'samples': 16027776, 'steps': 83477, 'loss/train': 1.3168498277664185} 08/31/2021 04:18:31 - INFO - __main__ - Step 83479: {'lr': 0.00021048260758962196, 'samples': 16027968, 'steps': 83478, 'loss/train': 1.1844736337661743} 08/31/2021 04:18:31 - INFO - __main__ - Step 83480: {'lr': 0.00021047736757068627, 'samples': 16028160, 'steps': 83479, 'loss/train': 1.043850302696228} 08/31/2021 04:18:33 - INFO - __main__ - Step 83481: {'lr': 0.00021047212756955888, 'samples': 16028352, 'steps': 83480, 'loss/train': 1.2281006574630737} 08/31/2021 04:18:34 - INFO - __main__ - Step 83482: {'lr': 0.00021046688758624213, 'samples': 16028544, 'steps': 83481, 'loss/train': 0.9118609428405762} 08/31/2021 04:18:34 - INFO - __main__ - Step 83483: {'lr': 0.0002104616476207384, 'samples': 16028736, 'steps': 83482, 'loss/train': 1.8784639835357666} 08/31/2021 04:18:34 - INFO - __main__ - Step 83484: {'lr': 0.00021045640767305016, 'samples': 16028928, 'steps': 83483, 'loss/train': 1.274304747581482} 08/31/2021 04:18:35 - INFO - __main__ - Step 83485: {'lr': 0.00021045116774317952, 'samples': 16029120, 'steps': 83484, 'loss/train': 1.7465219497680664} 08/31/2021 04:18:35 - INFO - __main__ - Step 83486: {'lr': 0.00021044592783112898, 'samples': 16029312, 'steps': 83485, 'loss/train': 0.6804070472717285} 08/31/2021 04:18:36 - INFO - __main__ - Step 83487: {'lr': 0.0002104406879369009, 'samples': 16029504, 'steps': 83486, 'loss/train': 0.8751457929611206} 08/31/2021 04:18:37 - INFO - __main__ - Step 83488: {'lr': 0.00021043544806049764, 'samples': 16029696, 'steps': 83487, 'loss/train': 1.3737581968307495} 08/31/2021 04:18:37 - INFO - __main__ - Step 83489: {'lr': 0.00021043020820192155, 'samples': 16029888, 'steps': 83488, 'loss/train': 1.2048217058181763} 08/31/2021 04:18:38 - INFO - __main__ - Step 83490: {'lr': 0.000210424968361175, 'samples': 16030080, 'steps': 83489, 'loss/train': 1.163397192955017} 08/31/2021 04:18:38 - INFO - __main__ - Step 83491: {'lr': 0.00021041972853826036, 'samples': 16030272, 'steps': 83490, 'loss/train': 1.8122408390045166} 08/31/2021 04:18:39 - INFO - __main__ - Step 83492: {'lr': 0.00021041448873317998, 'samples': 16030464, 'steps': 83491, 'loss/train': 0.5231692790985107} 08/31/2021 04:18:40 - INFO - __main__ - Step 83493: {'lr': 0.00021040924894593618, 'samples': 16030656, 'steps': 83492, 'loss/train': 1.1848173141479492} 08/31/2021 04:18:40 - INFO - __main__ - Step 83494: {'lr': 0.00021040400917653142, 'samples': 16030848, 'steps': 83493, 'loss/train': 1.5313925743103027} 08/31/2021 04:18:41 - INFO - __main__ - Step 83495: {'lr': 0.00021039876942496793, 'samples': 16031040, 'steps': 83494, 'loss/train': 0.43109798431396484} 08/31/2021 04:18:41 - INFO - __main__ - Step 83496: {'lr': 0.0002103935296912482, 'samples': 16031232, 'steps': 83495, 'loss/train': 1.6834006309509277} 08/31/2021 04:18:41 - INFO - __main__ - Step 83497: {'lr': 0.00021038828997537462, 'samples': 16031424, 'steps': 83496, 'loss/train': 0.6357600688934326} 08/31/2021 04:18:43 - INFO - __main__ - Step 83498: {'lr': 0.0002103830502773494, 'samples': 16031616, 'steps': 83497, 'loss/train': 1.06563138961792} 08/31/2021 04:18:43 - INFO - __main__ - Step 83499: {'lr': 0.00021037781059717492, 'samples': 16031808, 'steps': 83498, 'loss/train': 1.1567360162734985} 08/31/2021 04:18:44 - INFO - __main__ - Step 83500: {'lr': 0.0002103725709348536, 'samples': 16032000, 'steps': 83499, 'loss/train': 1.481453537940979} 08/31/2021 04:18:44 - INFO - __main__ - Step 83501: {'lr': 0.0002103673312903878, 'samples': 16032192, 'steps': 83500, 'loss/train': 1.008307933807373} 08/31/2021 04:18:44 - INFO - __main__ - Step 83502: {'lr': 0.00021036209166377985, 'samples': 16032384, 'steps': 83501, 'loss/train': 1.5289582014083862} 08/31/2021 04:18:46 - INFO - __main__ - Step 83503: {'lr': 0.00021035685205503214, 'samples': 16032576, 'steps': 83502, 'loss/train': 1.4092252254486084} 08/31/2021 04:18:46 - INFO - __main__ - Step 83504: {'lr': 0.000210351612464147, 'samples': 16032768, 'steps': 83503, 'loss/train': 1.3958196640014648} 08/31/2021 04:18:47 - INFO - __main__ - Step 83505: {'lr': 0.0002103463728911268, 'samples': 16032960, 'steps': 83504, 'loss/train': 1.4144562482833862} 08/31/2021 04:18:47 - INFO - __main__ - Step 83506: {'lr': 0.00021034113333597397, 'samples': 16033152, 'steps': 83505, 'loss/train': 1.121858835220337} 08/31/2021 04:18:47 - INFO - __main__ - Step 83507: {'lr': 0.0002103358937986908, 'samples': 16033344, 'steps': 83506, 'loss/train': 1.1840194463729858} 08/31/2021 04:18:50 - INFO - __main__ - Step 83508: {'lr': 0.00021033065427927963, 'samples': 16033536, 'steps': 83507, 'loss/train': 1.1765109300613403} 08/31/2021 04:18:50 - INFO - __main__ - Step 83509: {'lr': 0.00021032541477774286, 'samples': 16033728, 'steps': 83508, 'loss/train': 0.7891305685043335} 08/31/2021 04:18:51 - INFO - __main__ - Step 83510: {'lr': 0.000210320175294083, 'samples': 16033920, 'steps': 83509, 'loss/train': 1.324711799621582} 08/31/2021 04:18:51 - INFO - __main__ - Step 83511: {'lr': 0.0002103149358283021, 'samples': 16034112, 'steps': 83510, 'loss/train': 1.2111228704452515} 08/31/2021 04:18:51 - INFO - __main__ - Step 83512: {'lr': 0.0002103096963804027, 'samples': 16034304, 'steps': 83511, 'loss/train': 1.172622561454773} 08/31/2021 04:18:53 - INFO - __main__ - Step 83513: {'lr': 0.00021030445695038714, 'samples': 16034496, 'steps': 83512, 'loss/train': 1.2752883434295654} 08/31/2021 04:18:53 - INFO - __main__ - Step 83514: {'lr': 0.00021029921753825775, 'samples': 16034688, 'steps': 83513, 'loss/train': 1.4171006679534912} 08/31/2021 04:18:54 - INFO - __main__ - Step 83515: {'lr': 0.00021029397814401694, 'samples': 16034880, 'steps': 83514, 'loss/train': 1.3044334650039673} 08/31/2021 04:18:54 - INFO - __main__ - Step 83516: {'lr': 0.00021028873876766704, 'samples': 16035072, 'steps': 83515, 'loss/train': 0.5615414977073669} 08/31/2021 04:18:54 - INFO - __main__ - Step 83517: {'lr': 0.00021028349940921043, 'samples': 16035264, 'steps': 83516, 'loss/train': 0.8433008790016174} 08/31/2021 04:18:56 - INFO - __main__ - Step 83518: {'lr': 0.00021027826006864947, 'samples': 16035456, 'steps': 83517, 'loss/train': 1.4392515420913696} 08/31/2021 04:18:56 - INFO - __main__ - Step 83519: {'lr': 0.00021027302074598652, 'samples': 16035648, 'steps': 83518, 'loss/train': 1.4305294752120972} 08/31/2021 04:18:57 - INFO - __main__ - Step 83520: {'lr': 0.00021026778144122394, 'samples': 16035840, 'steps': 83519, 'loss/train': 0.821109414100647} 08/31/2021 04:18:57 - INFO - __main__ - Step 83521: {'lr': 0.00021026254215436406, 'samples': 16036032, 'steps': 83520, 'loss/train': 1.3307193517684937} 08/31/2021 04:18:57 - INFO - __main__ - Step 83522: {'lr': 0.00021025730288540926, 'samples': 16036224, 'steps': 83521, 'loss/train': 1.2168866395950317} 08/31/2021 04:18:59 - INFO - __main__ - Step 83523: {'lr': 0.0002102520636343619, 'samples': 16036416, 'steps': 83522, 'loss/train': 0.8389881253242493} 08/31/2021 04:19:00 - INFO - __main__ - Step 83524: {'lr': 0.0002102468244012245, 'samples': 16036608, 'steps': 83523, 'loss/train': 1.1187739372253418} 08/31/2021 04:19:00 - INFO - __main__ - Step 83525: {'lr': 0.0002102415851859991, 'samples': 16036800, 'steps': 83524, 'loss/train': 1.3837153911590576} 08/31/2021 04:19:00 - INFO - __main__ - Step 83526: {'lr': 0.00021023634598868829, 'samples': 16036992, 'steps': 83525, 'loss/train': 0.9625760316848755} 08/31/2021 04:19:01 - INFO - __main__ - Step 83527: {'lr': 0.00021023110680929433, 'samples': 16037184, 'steps': 83526, 'loss/train': 0.8647640943527222} 08/31/2021 04:19:01 - INFO - __main__ - Step 83528: {'lr': 0.00021022586764781964, 'samples': 16037376, 'steps': 83527, 'loss/train': 1.9286530017852783} 08/31/2021 04:19:02 - INFO - __main__ - Step 83529: {'lr': 0.00021022062850426654, 'samples': 16037568, 'steps': 83528, 'loss/train': 1.1762402057647705} 08/31/2021 04:19:03 - INFO - __main__ - Step 83530: {'lr': 0.00021021538937863744, 'samples': 16037760, 'steps': 83529, 'loss/train': 0.9088078737258911} 08/31/2021 04:19:03 - INFO - __main__ - Step 83531: {'lr': 0.00021021015027093465, 'samples': 16037952, 'steps': 83530, 'loss/train': 1.5758541822433472} 08/31/2021 04:19:04 - INFO - __main__ - Step 83532: {'lr': 0.00021020491118116052, 'samples': 16038144, 'steps': 83531, 'loss/train': 1.1639790534973145} 08/31/2021 04:19:04 - INFO - __main__ - Step 83533: {'lr': 0.0002101996721093175, 'samples': 16038336, 'steps': 83532, 'loss/train': 1.6584694385528564} 08/31/2021 04:19:06 - INFO - __main__ - Step 83534: {'lr': 0.00021019443305540786, 'samples': 16038528, 'steps': 83533, 'loss/train': 1.1430442333221436} 08/31/2021 04:19:06 - INFO - __main__ - Step 83535: {'lr': 0.000210189194019434, 'samples': 16038720, 'steps': 83534, 'loss/train': 0.9613259434700012} 08/31/2021 04:19:06 - INFO - __main__ - Step 83536: {'lr': 0.00021018395500139832, 'samples': 16038912, 'steps': 83535, 'loss/train': 1.4028838872909546} 08/31/2021 04:19:07 - INFO - __main__ - Step 83537: {'lr': 0.00021017871600130316, 'samples': 16039104, 'steps': 83536, 'loss/train': 0.9207504987716675} 08/31/2021 04:19:07 - INFO - __main__ - Step 83538: {'lr': 0.0002101734770191508, 'samples': 16039296, 'steps': 83537, 'loss/train': 0.05171799659729004} 08/31/2021 04:19:09 - INFO - __main__ - Step 83539: {'lr': 0.00021016823805494368, 'samples': 16039488, 'steps': 83538, 'loss/train': 1.109748363494873} 08/31/2021 04:19:10 - INFO - __main__ - Step 83540: {'lr': 0.0002101629991086841, 'samples': 16039680, 'steps': 83539, 'loss/train': 1.2528437376022339} 08/31/2021 04:19:10 - INFO - __main__ - Step 83541: {'lr': 0.00021015776018037445, 'samples': 16039872, 'steps': 83540, 'loss/train': 1.2795135974884033} 08/31/2021 04:19:10 - INFO - __main__ - Step 83542: {'lr': 0.0002101525212700171, 'samples': 16040064, 'steps': 83541, 'loss/train': 1.3041713237762451} 08/31/2021 04:19:11 - INFO - __main__ - Step 83543: {'lr': 0.00021014728237761445, 'samples': 16040256, 'steps': 83542, 'loss/train': 0.8246865272521973} 08/31/2021 04:19:12 - INFO - __main__ - Step 83544: {'lr': 0.00021014204350316875, 'samples': 16040448, 'steps': 83543, 'loss/train': 0.2632055878639221} 08/31/2021 04:19:13 - INFO - __main__ - Step 83545: {'lr': 0.0002101368046466825, 'samples': 16040640, 'steps': 83544, 'loss/train': 0.9487083554267883} 08/31/2021 04:19:13 - INFO - __main__ - Step 83546: {'lr': 0.00021013156580815796, 'samples': 16040832, 'steps': 83545, 'loss/train': 0.9251202940940857} 08/31/2021 04:19:13 - INFO - __main__ - Step 83547: {'lr': 0.00021012632698759752, 'samples': 16041024, 'steps': 83546, 'loss/train': 0.9965189695358276} 08/31/2021 04:19:14 - INFO - __main__ - Step 83548: {'lr': 0.00021012108818500353, 'samples': 16041216, 'steps': 83547, 'loss/train': 1.0299136638641357} 08/31/2021 04:19:14 - INFO - __main__ - Step 83549: {'lr': 0.00021011584940037838, 'samples': 16041408, 'steps': 83548, 'loss/train': 1.5638545751571655} 08/31/2021 04:19:15 - INFO - __main__ - Step 83550: {'lr': 0.00021011061063372447, 'samples': 16041600, 'steps': 83549, 'loss/train': 1.7178325653076172} 08/31/2021 04:19:16 - INFO - __main__ - Step 83551: {'lr': 0.0002101053718850441, 'samples': 16041792, 'steps': 83550, 'loss/train': 1.2243123054504395} 08/31/2021 04:19:16 - INFO - __main__ - Step 83552: {'lr': 0.00021010013315433956, 'samples': 16041984, 'steps': 83551, 'loss/train': 1.3323149681091309} 08/31/2021 04:19:17 - INFO - __main__ - Step 83553: {'lr': 0.0002100948944416133, 'samples': 16042176, 'steps': 83552, 'loss/train': 0.647853434085846} 08/31/2021 04:19:17 - INFO - __main__ - Step 83554: {'lr': 0.00021008965574686767, 'samples': 16042368, 'steps': 83553, 'loss/train': 5.794396877288818} 08/31/2021 04:19:19 - INFO - __main__ - Step 83555: {'lr': 0.00021008441707010504, 'samples': 16042560, 'steps': 83554, 'loss/train': 1.7748035192489624} 08/31/2021 04:19:19 - INFO - __main__ - Step 83556: {'lr': 0.00021007917841132774, 'samples': 16042752, 'steps': 83555, 'loss/train': 1.570228934288025} 08/31/2021 04:19:19 - INFO - __main__ - Step 83557: {'lr': 0.00021007393977053813, 'samples': 16042944, 'steps': 83556, 'loss/train': 1.1520065069198608} 08/31/2021 04:19:20 - INFO - __main__ - Step 83558: {'lr': 0.0002100687011477386, 'samples': 16043136, 'steps': 83557, 'loss/train': 0.6211302876472473} 08/31/2021 04:19:20 - INFO - __main__ - Step 83559: {'lr': 0.0002100634625429315, 'samples': 16043328, 'steps': 83558, 'loss/train': 1.465447187423706} 08/31/2021 04:19:22 - INFO - __main__ - Step 83560: {'lr': 0.00021005822395611917, 'samples': 16043520, 'steps': 83559, 'loss/train': 1.3490396738052368} 08/31/2021 04:19:23 - INFO - __main__ - Step 83561: {'lr': 0.00021005298538730405, 'samples': 16043712, 'steps': 83560, 'loss/train': 1.323330044746399} 08/31/2021 04:19:23 - INFO - __main__ - Step 83562: {'lr': 0.00021004774683648842, 'samples': 16043904, 'steps': 83561, 'loss/train': 0.9287164211273193} 08/31/2021 04:19:23 - INFO - __main__ - Step 83563: {'lr': 0.00021004250830367462, 'samples': 16044096, 'steps': 83562, 'loss/train': 1.1066893339157104} 08/31/2021 04:19:24 - INFO - __main__ - Step 83564: {'lr': 0.00021003726978886513, 'samples': 16044288, 'steps': 83563, 'loss/train': 1.266977310180664} 08/31/2021 04:19:25 - INFO - __main__ - Step 83565: {'lr': 0.00021003203129206215, 'samples': 16044480, 'steps': 83564, 'loss/train': 1.0963834524154663} 08/31/2021 04:19:26 - INFO - __main__ - Step 83566: {'lr': 0.00021002679281326812, 'samples': 16044672, 'steps': 83565, 'loss/train': 1.1614315509796143} 08/31/2021 04:19:26 - INFO - __main__ - Step 83567: {'lr': 0.0002100215543524854, 'samples': 16044864, 'steps': 83566, 'loss/train': 1.2497904300689697} 08/31/2021 04:19:26 - INFO - __main__ - Step 83568: {'lr': 0.00021001631590971637, 'samples': 16045056, 'steps': 83567, 'loss/train': 1.0001682043075562} 08/31/2021 04:19:27 - INFO - __main__ - Step 83569: {'lr': 0.00021001107748496334, 'samples': 16045248, 'steps': 83568, 'loss/train': 1.279005527496338} 08/31/2021 04:19:27 - INFO - __main__ - Step 83570: {'lr': 0.00021000583907822873, 'samples': 16045440, 'steps': 83569, 'loss/train': 1.1659938097000122} 08/31/2021 04:19:29 - INFO - __main__ - Step 83571: {'lr': 0.00021000060068951488, 'samples': 16045632, 'steps': 83570, 'loss/train': 1.2080425024032593} 08/31/2021 04:19:29 - INFO - __main__ - Step 83572: {'lr': 0.00020999536231882415, 'samples': 16045824, 'steps': 83571, 'loss/train': 1.081825852394104} 08/31/2021 04:19:30 - INFO - __main__ - Step 83573: {'lr': 0.00020999012396615889, 'samples': 16046016, 'steps': 83572, 'loss/train': 0.14192143082618713} 08/31/2021 04:19:30 - INFO - __main__ - Step 83574: {'lr': 0.00020998488563152143, 'samples': 16046208, 'steps': 83573, 'loss/train': 1.1225159168243408} 08/31/2021 04:19:30 - INFO - __main__ - Step 83575: {'lr': 0.00020997964731491418, 'samples': 16046400, 'steps': 83574, 'loss/train': 1.2360508441925049} 08/31/2021 04:19:32 - INFO - __main__ - Step 83576: {'lr': 0.00020997440901633947, 'samples': 16046592, 'steps': 83575, 'loss/train': 1.3439579010009766} 08/31/2021 04:19:32 - INFO - __main__ - Step 83577: {'lr': 0.0002099691707357997, 'samples': 16046784, 'steps': 83576, 'loss/train': 0.15262532234191895} 08/31/2021 04:19:33 - INFO - __main__ - Step 83578: {'lr': 0.0002099639324732972, 'samples': 16046976, 'steps': 83577, 'loss/train': 1.0980089902877808} 08/31/2021 04:19:33 - INFO - __main__ - Step 83579: {'lr': 0.00020995869422883436, 'samples': 16047168, 'steps': 83578, 'loss/train': 1.530393362045288} 08/31/2021 04:19:33 - INFO - __main__ - Step 83580: {'lr': 0.00020995345600241346, 'samples': 16047360, 'steps': 83579, 'loss/train': 1.2879141569137573} 08/31/2021 04:19:35 - INFO - __main__ - Step 83581: {'lr': 0.0002099482177940369, 'samples': 16047552, 'steps': 83580, 'loss/train': 0.8606127500534058} 08/31/2021 04:19:35 - INFO - __main__ - Step 83582: {'lr': 0.00020994297960370712, 'samples': 16047744, 'steps': 83581, 'loss/train': 0.8869674801826477} 08/31/2021 04:19:36 - INFO - __main__ - Step 83583: {'lr': 0.00020993774143142642, 'samples': 16047936, 'steps': 83582, 'loss/train': 0.9655495882034302} 08/31/2021 04:19:36 - INFO - __main__ - Step 83584: {'lr': 0.0002099325032771971, 'samples': 16048128, 'steps': 83583, 'loss/train': 1.3858855962753296} 08/31/2021 04:19:36 - INFO - __main__ - Step 83585: {'lr': 0.00020992726514102158, 'samples': 16048320, 'steps': 83584, 'loss/train': 1.4247514009475708} 08/31/2021 04:19:38 - INFO - __main__ - Step 83586: {'lr': 0.00020992202702290225, 'samples': 16048512, 'steps': 83585, 'loss/train': 2.03957200050354} 08/31/2021 04:19:39 - INFO - __main__ - Step 83587: {'lr': 0.0002099167889228414, 'samples': 16048704, 'steps': 83586, 'loss/train': 1.3107491731643677} 08/31/2021 04:19:39 - INFO - __main__ - Step 83588: {'lr': 0.00020991155084084146, 'samples': 16048896, 'steps': 83587, 'loss/train': 0.16822193562984467} 08/31/2021 04:19:39 - INFO - __main__ - Step 83589: {'lr': 0.0002099063127769047, 'samples': 16049088, 'steps': 83588, 'loss/train': 1.2343560457229614} 08/31/2021 04:19:40 - INFO - __main__ - Step 83590: {'lr': 0.00020990107473103358, 'samples': 16049280, 'steps': 83589, 'loss/train': 1.0336350202560425} 08/31/2021 04:19:40 - INFO - __main__ - Step 83591: {'lr': 0.00020989583670323047, 'samples': 16049472, 'steps': 83590, 'loss/train': 1.3969182968139648} 08/31/2021 04:19:41 - INFO - __main__ - Step 83592: {'lr': 0.00020989059869349762, 'samples': 16049664, 'steps': 83591, 'loss/train': 1.470342755317688} 08/31/2021 04:19:42 - INFO - __main__ - Step 83593: {'lr': 0.00020988536070183744, 'samples': 16049856, 'steps': 83592, 'loss/train': 2.1878490447998047} 08/31/2021 04:19:42 - INFO - __main__ - Step 83594: {'lr': 0.00020988012272825236, 'samples': 16050048, 'steps': 83593, 'loss/train': 1.183208703994751} 08/31/2021 04:19:43 - INFO - __main__ - Step 83595: {'lr': 0.0002098748847727446, 'samples': 16050240, 'steps': 83594, 'loss/train': 1.3682222366333008} 08/31/2021 04:19:43 - INFO - __main__ - Step 83596: {'lr': 0.00020986964683531662, 'samples': 16050432, 'steps': 83595, 'loss/train': 0.549917459487915} 08/31/2021 04:19:44 - INFO - __main__ - Step 83597: {'lr': 0.00020986440891597075, 'samples': 16050624, 'steps': 83596, 'loss/train': 1.5295705795288086} 08/31/2021 04:19:45 - INFO - __main__ - Step 83598: {'lr': 0.00020985917101470935, 'samples': 16050816, 'steps': 83597, 'loss/train': 1.2171636819839478} 08/31/2021 04:19:45 - INFO - __main__ - Step 83599: {'lr': 0.00020985393313153485, 'samples': 16051008, 'steps': 83598, 'loss/train': 0.9890875220298767} 08/31/2021 04:19:46 - INFO - __main__ - Step 83600: {'lr': 0.00020984869526644948, 'samples': 16051200, 'steps': 83599, 'loss/train': 4.655396461486816} 08/31/2021 04:19:46 - INFO - __main__ - Step 83601: {'lr': 0.00020984345741945567, 'samples': 16051392, 'steps': 83600, 'loss/train': 1.7842705249786377} 08/31/2021 04:19:47 - INFO - __main__ - Step 83602: {'lr': 0.0002098382195905558, 'samples': 16051584, 'steps': 83601, 'loss/train': 0.9713468551635742} 08/31/2021 04:19:48 - INFO - __main__ - Step 83603: {'lr': 0.00020983298177975222, 'samples': 16051776, 'steps': 83602, 'loss/train': 0.8485664129257202} 08/31/2021 04:19:48 - INFO - __main__ - Step 83604: {'lr': 0.00020982774398704723, 'samples': 16051968, 'steps': 83603, 'loss/train': 1.571914792060852} 08/31/2021 04:19:49 - INFO - __main__ - Step 83605: {'lr': 0.00020982250621244338, 'samples': 16052160, 'steps': 83604, 'loss/train': 1.4903361797332764} 08/31/2021 04:19:49 - INFO - __main__ - Step 83606: {'lr': 0.00020981726845594278, 'samples': 16052352, 'steps': 83605, 'loss/train': 1.1565426588058472} 08/31/2021 04:19:50 - INFO - __main__ - Step 83607: {'lr': 0.0002098120307175479, 'samples': 16052544, 'steps': 83606, 'loss/train': 1.9038723707199097} 08/31/2021 04:19:51 - INFO - __main__ - Step 83608: {'lr': 0.0002098067929972611, 'samples': 16052736, 'steps': 83607, 'loss/train': 1.1001520156860352} 08/31/2021 04:19:51 - INFO - __main__ - Step 83609: {'lr': 0.00020980155529508473, 'samples': 16052928, 'steps': 83608, 'loss/train': 1.4606322050094604} 08/31/2021 04:19:52 - INFO - __main__ - Step 83610: {'lr': 0.0002097963176110212, 'samples': 16053120, 'steps': 83609, 'loss/train': 0.04100820794701576} 08/31/2021 04:19:52 - INFO - __main__ - Step 83611: {'lr': 0.00020979107994507278, 'samples': 16053312, 'steps': 83610, 'loss/train': 0.04690781608223915} 08/31/2021 04:19:54 - INFO - __main__ - Step 83612: {'lr': 0.00020978584229724187, 'samples': 16053504, 'steps': 83611, 'loss/train': 0.8958415389060974} 08/31/2021 04:19:54 - INFO - __main__ - Step 83613: {'lr': 0.00020978060466753088, 'samples': 16053696, 'steps': 83612, 'loss/train': 1.2944087982177734} 08/31/2021 04:19:55 - INFO - __main__ - Step 83614: {'lr': 0.0002097753670559421, 'samples': 16053888, 'steps': 83613, 'loss/train': 0.23890984058380127} 08/31/2021 04:19:55 - INFO - __main__ - Step 83615: {'lr': 0.00020977012946247792, 'samples': 16054080, 'steps': 83614, 'loss/train': 1.7300678491592407} 08/31/2021 04:19:55 - INFO - __main__ - Step 83616: {'lr': 0.0002097648918871407, 'samples': 16054272, 'steps': 83615, 'loss/train': 1.4492039680480957} 08/31/2021 04:19:57 - INFO - __main__ - Step 83617: {'lr': 0.00020975965432993283, 'samples': 16054464, 'steps': 83616, 'loss/train': 0.941531240940094} 08/31/2021 04:19:57 - INFO - __main__ - Step 83618: {'lr': 0.00020975441679085672, 'samples': 16054656, 'steps': 83617, 'loss/train': 1.018749713897705} 08/31/2021 04:19:58 - INFO - __main__ - Step 83619: {'lr': 0.00020974917926991455, 'samples': 16054848, 'steps': 83618, 'loss/train': 1.1679353713989258} 08/31/2021 04:19:58 - INFO - __main__ - Step 83620: {'lr': 0.00020974394176710877, 'samples': 16055040, 'steps': 83619, 'loss/train': 1.1886909008026123} 08/31/2021 04:19:58 - INFO - __main__ - Step 83621: {'lr': 0.00020973870428244175, 'samples': 16055232, 'steps': 83620, 'loss/train': 0.05343780666589737} 08/31/2021 04:20:00 - INFO - __main__ - Step 83622: {'lr': 0.00020973346681591584, 'samples': 16055424, 'steps': 83621, 'loss/train': 0.031341154128313065} 08/31/2021 04:20:01 - INFO - __main__ - Step 83623: {'lr': 0.00020972822936753344, 'samples': 16055616, 'steps': 83622, 'loss/train': 1.054966688156128} 08/31/2021 04:20:01 - INFO - __main__ - Step 83624: {'lr': 0.00020972299193729686, 'samples': 16055808, 'steps': 83623, 'loss/train': 1.338235855102539} 08/31/2021 04:20:01 - INFO - __main__ - Step 83625: {'lr': 0.00020971775452520848, 'samples': 16056000, 'steps': 83624, 'loss/train': 1.0197374820709229} 08/31/2021 04:20:02 - INFO - __main__ - Step 83626: {'lr': 0.00020971251713127064, 'samples': 16056192, 'steps': 83625, 'loss/train': 0.045310478657484055} 08/31/2021 04:20:02 - INFO - __main__ - Step 83627: {'lr': 0.00020970727975548573, 'samples': 16056384, 'steps': 83626, 'loss/train': 1.590527057647705} 08/31/2021 04:20:04 - INFO - __main__ - Step 83628: {'lr': 0.0002097020423978561, 'samples': 16056576, 'steps': 83627, 'loss/train': 1.1475127935409546} 08/31/2021 04:20:04 - INFO - __main__ - Step 83629: {'lr': 0.00020969680505838413, 'samples': 16056768, 'steps': 83628, 'loss/train': 1.1436262130737305} 08/31/2021 04:20:04 - INFO - __main__ - Step 83630: {'lr': 0.00020969156773707209, 'samples': 16056960, 'steps': 83629, 'loss/train': 1.0833723545074463} 08/31/2021 04:20:05 - INFO - __main__ - Step 83631: {'lr': 0.0002096863304339226, 'samples': 16057152, 'steps': 83630, 'loss/train': 0.9395298957824707} 08/31/2021 04:20:05 - INFO - __main__ - Step 83632: {'lr': 0.00020968109314893765, 'samples': 16057344, 'steps': 83631, 'loss/train': 1.082980751991272} 08/31/2021 04:20:07 - INFO - __main__ - Step 83633: {'lr': 0.00020967585588211983, 'samples': 16057536, 'steps': 83632, 'loss/train': 1.086732029914856} 08/31/2021 04:20:07 - INFO - __main__ - Step 83634: {'lr': 0.00020967061863347143, 'samples': 16057728, 'steps': 83633, 'loss/train': 1.4080567359924316} 08/31/2021 04:20:07 - INFO - __main__ - Step 83635: {'lr': 0.0002096653814029948, 'samples': 16057920, 'steps': 83634, 'loss/train': 1.2285319566726685} 08/31/2021 04:20:08 - INFO - __main__ - Step 83636: {'lr': 0.00020966014419069234, 'samples': 16058112, 'steps': 83635, 'loss/train': 1.6584527492523193} 08/31/2021 04:20:08 - INFO - __main__ - Step 83637: {'lr': 0.00020965490699656643, 'samples': 16058304, 'steps': 83636, 'loss/train': 1.1835362911224365} 08/31/2021 04:20:09 - INFO - __main__ - Step 83638: {'lr': 0.00020964966982061936, 'samples': 16058496, 'steps': 83637, 'loss/train': 1.4666087627410889} 08/31/2021 04:20:10 - INFO - __main__ - Step 83639: {'lr': 0.00020964443266285356, 'samples': 16058688, 'steps': 83638, 'loss/train': 0.4578741192817688} 08/31/2021 04:20:11 - INFO - __main__ - Step 83640: {'lr': 0.0002096391955232713, 'samples': 16058880, 'steps': 83639, 'loss/train': 1.134865164756775} 08/31/2021 04:20:11 - INFO - __main__ - Step 83641: {'lr': 0.00020963395840187504, 'samples': 16059072, 'steps': 83640, 'loss/train': 1.7488417625427246} 08/31/2021 04:20:11 - INFO - __main__ - Step 83642: {'lr': 0.0002096287212986671, 'samples': 16059264, 'steps': 83641, 'loss/train': 1.4744768142700195} 08/31/2021 04:20:12 - INFO - __main__ - Step 83643: {'lr': 0.0002096234842136498, 'samples': 16059456, 'steps': 83642, 'loss/train': 0.9293054938316345} 08/31/2021 04:20:13 - INFO - __main__ - Step 83644: {'lr': 0.00020961824714682556, 'samples': 16059648, 'steps': 83643, 'loss/train': 1.1271488666534424} 08/31/2021 04:20:14 - INFO - __main__ - Step 83645: {'lr': 0.00020961301009819684, 'samples': 16059840, 'steps': 83644, 'loss/train': 1.0502004623413086} 08/31/2021 04:20:14 - INFO - __main__ - Step 83646: {'lr': 0.00020960777306776573, 'samples': 16060032, 'steps': 83645, 'loss/train': 1.4659937620162964} 08/31/2021 04:20:14 - INFO - __main__ - Step 83647: {'lr': 0.00020960253605553476, 'samples': 16060224, 'steps': 83646, 'loss/train': 1.5745656490325928} 08/31/2021 04:20:15 - INFO - __main__ - Step 83648: {'lr': 0.00020959729906150622, 'samples': 16060416, 'steps': 83647, 'loss/train': 0.06574544310569763} 08/31/2021 04:20:16 - INFO - __main__ - Step 83649: {'lr': 0.00020959206208568255, 'samples': 16060608, 'steps': 83648, 'loss/train': 0.7746247053146362} 08/31/2021 04:20:17 - INFO - __main__ - Step 83650: {'lr': 0.0002095868251280661, 'samples': 16060800, 'steps': 83649, 'loss/train': 0.7217034101486206} 08/31/2021 04:20:17 - INFO - __main__ - Step 83651: {'lr': 0.00020958158818865915, 'samples': 16060992, 'steps': 83650, 'loss/train': 1.1861213445663452} 08/31/2021 04:20:17 - INFO - __main__ - Step 83652: {'lr': 0.00020957635126746415, 'samples': 16061184, 'steps': 83651, 'loss/train': 0.8902682662010193} 08/31/2021 04:20:18 - INFO - __main__ - Step 83653: {'lr': 0.0002095711143644834, 'samples': 16061376, 'steps': 83652, 'loss/train': 1.1830161809921265} 08/31/2021 04:20:20 - INFO - __main__ - Step 83654: {'lr': 0.00020956587747971927, 'samples': 16061568, 'steps': 83653, 'loss/train': 1.6959681510925293} 08/31/2021 04:20:20 - INFO - __main__ - Step 83655: {'lr': 0.00020956064061317415, 'samples': 16061760, 'steps': 83654, 'loss/train': 1.785517930984497} 08/31/2021 04:20:20 - INFO - __main__ - Step 83656: {'lr': 0.00020955540376485038, 'samples': 16061952, 'steps': 83655, 'loss/train': 0.5810448527336121} 08/31/2021 04:20:21 - INFO - __main__ - Step 83657: {'lr': 0.0002095501669347503, 'samples': 16062144, 'steps': 83656, 'loss/train': 0.5663058757781982} 08/31/2021 04:20:21 - INFO - __main__ - Step 83658: {'lr': 0.00020954493012287646, 'samples': 16062336, 'steps': 83657, 'loss/train': 1.8780375719070435} 08/31/2021 04:20:23 - INFO - __main__ - Step 83659: {'lr': 0.0002095396933292309, 'samples': 16062528, 'steps': 83658, 'loss/train': 1.226372480392456} 08/31/2021 04:20:23 - INFO - __main__ - Step 83660: {'lr': 0.00020953445655381615, 'samples': 16062720, 'steps': 83659, 'loss/train': 1.255311369895935} 08/31/2021 04:20:23 - INFO - __main__ - Step 83661: {'lr': 0.00020952921979663453, 'samples': 16062912, 'steps': 83660, 'loss/train': 0.9467138051986694} 08/31/2021 04:20:24 - INFO - __main__ - Step 83662: {'lr': 0.0002095239830576884, 'samples': 16063104, 'steps': 83661, 'loss/train': 0.869175136089325} 08/31/2021 04:20:24 - INFO - __main__ - Step 83663: {'lr': 0.00020951874633698018, 'samples': 16063296, 'steps': 83662, 'loss/train': 0.9187675714492798} 08/31/2021 04:20:26 - INFO - __main__ - Step 83664: {'lr': 0.00020951350963451215, 'samples': 16063488, 'steps': 83663, 'loss/train': 1.180845022201538} 08/31/2021 04:20:26 - INFO - __main__ - Step 83665: {'lr': 0.00020950827295028674, 'samples': 16063680, 'steps': 83664, 'loss/train': 1.112155795097351} 08/31/2021 04:20:26 - INFO - __main__ - Step 83666: {'lr': 0.00020950303628430625, 'samples': 16063872, 'steps': 83665, 'loss/train': 1.1947156190872192} 08/31/2021 04:20:27 - INFO - __main__ - Step 83667: {'lr': 0.00020949779963657308, 'samples': 16064064, 'steps': 83666, 'loss/train': 1.160025715827942} 08/31/2021 04:20:27 - INFO - __main__ - Step 83668: {'lr': 0.00020949256300708958, 'samples': 16064256, 'steps': 83667, 'loss/train': 0.3730832636356354} 08/31/2021 04:20:27 - INFO - __main__ - Step 83669: {'lr': 0.0002094873263958581, 'samples': 16064448, 'steps': 83668, 'loss/train': 1.407073974609375} 08/31/2021 04:20:30 - INFO - __main__ - Step 83670: {'lr': 0.00020948208980288102, 'samples': 16064640, 'steps': 83669, 'loss/train': 1.6273880004882812} 08/31/2021 04:20:30 - INFO - __main__ - Step 83671: {'lr': 0.00020947685322816068, 'samples': 16064832, 'steps': 83670, 'loss/train': 4.274143695831299} 08/31/2021 04:20:30 - INFO - __main__ - Step 83672: {'lr': 0.00020947161667169957, 'samples': 16065024, 'steps': 83671, 'loss/train': 1.3525766134262085} 08/31/2021 04:20:31 - INFO - __main__ - Step 83673: {'lr': 0.00020946638013349977, 'samples': 16065216, 'steps': 83672, 'loss/train': 1.5026837587356567} 08/31/2021 04:20:31 - INFO - __main__ - Step 83674: {'lr': 0.0002094611436135638, 'samples': 16065408, 'steps': 83673, 'loss/train': 1.0488860607147217} 08/31/2021 04:20:33 - INFO - __main__ - Step 83675: {'lr': 0.00020945590711189406, 'samples': 16065600, 'steps': 83674, 'loss/train': 1.3318097591400146} 08/31/2021 04:20:33 - INFO - __main__ - Step 83676: {'lr': 0.0002094506706284928, 'samples': 16065792, 'steps': 83675, 'loss/train': 0.05401526764035225} 08/31/2021 04:20:33 - INFO - __main__ - Step 83677: {'lr': 0.00020944543416336249, 'samples': 16065984, 'steps': 83676, 'loss/train': 0.5922229886054993} 08/31/2021 04:20:34 - INFO - __main__ - Step 83678: {'lr': 0.0002094401977165054, 'samples': 16066176, 'steps': 83677, 'loss/train': 1.191573977470398} 08/31/2021 04:20:34 - INFO - __main__ - Step 83679: {'lr': 0.000209434961287924, 'samples': 16066368, 'steps': 83678, 'loss/train': 0.5560085773468018} 08/31/2021 04:20:35 - INFO - __main__ - Step 83680: {'lr': 0.0002094297248776205, 'samples': 16066560, 'steps': 83679, 'loss/train': 0.9986333250999451} 08/31/2021 04:20:36 - INFO - __main__ - Step 83681: {'lr': 0.0002094244884855974, 'samples': 16066752, 'steps': 83680, 'loss/train': 1.6265884637832642} 08/31/2021 04:20:37 - INFO - __main__ - Step 83682: {'lr': 0.00020941925211185697, 'samples': 16066944, 'steps': 83681, 'loss/train': 1.025556206703186} 08/31/2021 04:20:37 - INFO - __main__ - Step 83683: {'lr': 0.00020941401575640163, 'samples': 16067136, 'steps': 83682, 'loss/train': 1.1051253080368042} 08/31/2021 04:20:37 - INFO - __main__ - Step 83684: {'lr': 0.00020940877941923373, 'samples': 16067328, 'steps': 83683, 'loss/train': 1.3680346012115479} 08/31/2021 04:20:38 - INFO - __main__ - Step 83685: {'lr': 0.0002094035431003556, 'samples': 16067520, 'steps': 83684, 'loss/train': 1.6586552858352661} 08/31/2021 04:20:39 - INFO - __main__ - Step 83686: {'lr': 0.00020939830679976958, 'samples': 16067712, 'steps': 83685, 'loss/train': 1.884842038154602} 08/31/2021 04:20:40 - INFO - __main__ - Step 83687: {'lr': 0.00020939307051747803, 'samples': 16067904, 'steps': 83686, 'loss/train': 1.2719926834106445} 08/31/2021 04:20:40 - INFO - __main__ - Step 83688: {'lr': 0.00020938783425348333, 'samples': 16068096, 'steps': 83687, 'loss/train': 1.480313777923584} 08/31/2021 04:20:40 - INFO - __main__ - Step 83689: {'lr': 0.00020938259800778788, 'samples': 16068288, 'steps': 83688, 'loss/train': 1.2404685020446777} 08/31/2021 04:20:41 - INFO - __main__ - Step 83690: {'lr': 0.000209377361780394, 'samples': 16068480, 'steps': 83689, 'loss/train': 1.2538141012191772} 08/31/2021 04:20:42 - INFO - __main__ - Step 83691: {'lr': 0.00020937212557130405, 'samples': 16068672, 'steps': 83690, 'loss/train': 1.2493252754211426} 08/31/2021 04:20:43 - INFO - __main__ - Step 83692: {'lr': 0.0002093668893805204, 'samples': 16068864, 'steps': 83691, 'loss/train': 1.4308656454086304} 08/31/2021 04:20:43 - INFO - __main__ - Step 83693: {'lr': 0.00020936165320804538, 'samples': 16069056, 'steps': 83692, 'loss/train': 0.8893563151359558} 08/31/2021 04:20:43 - INFO - __main__ - Step 83694: {'lr': 0.00020935641705388137, 'samples': 16069248, 'steps': 83693, 'loss/train': 1.3908851146697998} 08/31/2021 04:20:44 - INFO - __main__ - Step 83695: {'lr': 0.00020935118091803078, 'samples': 16069440, 'steps': 83694, 'loss/train': 0.5243972539901733} 08/31/2021 04:20:46 - INFO - __main__ - Step 83696: {'lr': 0.0002093459448004959, 'samples': 16069632, 'steps': 83695, 'loss/train': 1.8886280059814453} 08/31/2021 04:20:46 - INFO - __main__ - Step 83697: {'lr': 0.0002093407087012791, 'samples': 16069824, 'steps': 83696, 'loss/train': 0.6838205456733704} 08/31/2021 04:20:47 - INFO - __main__ - Step 83698: {'lr': 0.00020933547262038274, 'samples': 16070016, 'steps': 83697, 'loss/train': 2.573843240737915} 08/31/2021 04:20:47 - INFO - __main__ - Step 83699: {'lr': 0.00020933023655780926, 'samples': 16070208, 'steps': 83698, 'loss/train': 2.599865198135376} 08/31/2021 04:20:47 - INFO - __main__ - Step 83700: {'lr': 0.00020932500051356088, 'samples': 16070400, 'steps': 83699, 'loss/train': 1.3997149467468262} 08/31/2021 04:20:48 - INFO - __main__ - Step 83701: {'lr': 0.00020931976448764001, 'samples': 16070592, 'steps': 83700, 'loss/train': 1.4027955532073975} 08/31/2021 04:20:49 - INFO - __main__ - Step 83702: {'lr': 0.00020931452848004905, 'samples': 16070784, 'steps': 83701, 'loss/train': 0.5629938244819641} 08/31/2021 04:20:50 - INFO - __main__ - Step 83703: {'lr': 0.00020930929249079035, 'samples': 16070976, 'steps': 83702, 'loss/train': 0.9979010820388794} 08/31/2021 04:20:50 - INFO - __main__ - Step 83704: {'lr': 0.00020930405651986623, 'samples': 16071168, 'steps': 83703, 'loss/train': 0.2855425179004669} 08/31/2021 04:20:50 - INFO - __main__ - Step 83705: {'lr': 0.00020929882056727907, 'samples': 16071360, 'steps': 83704, 'loss/train': 1.3610843420028687} 08/31/2021 04:20:51 - INFO - __main__ - Step 83706: {'lr': 0.0002092935846330313, 'samples': 16071552, 'steps': 83705, 'loss/train': 1.8146885633468628} 08/31/2021 04:20:51 - INFO - __main__ - Step 83707: {'lr': 0.00020928834871712516, 'samples': 16071744, 'steps': 83706, 'loss/train': 0.8740019798278809} 08/31/2021 04:20:53 - INFO - __main__ - Step 83708: {'lr': 0.00020928311281956307, 'samples': 16071936, 'steps': 83707, 'loss/train': 2.0854783058166504} 08/31/2021 04:20:54 - INFO - __main__ - Step 83709: {'lr': 0.00020927787694034733, 'samples': 16072128, 'steps': 83708, 'loss/train': 1.2201106548309326} 08/31/2021 04:20:54 - INFO - __main__ - Step 83710: {'lr': 0.00020927264107948042, 'samples': 16072320, 'steps': 83709, 'loss/train': 1.300301194190979} 08/31/2021 04:20:54 - INFO - __main__ - Step 83711: {'lr': 0.00020926740523696458, 'samples': 16072512, 'steps': 83710, 'loss/train': 1.2139958143234253} 08/31/2021 04:20:55 - INFO - __main__ - Step 83712: {'lr': 0.0002092621694128023, 'samples': 16072704, 'steps': 83711, 'loss/train': 0.851047158241272} 08/31/2021 04:20:56 - INFO - __main__ - Step 83713: {'lr': 0.00020925693360699578, 'samples': 16072896, 'steps': 83712, 'loss/train': 1.4493132829666138} 08/31/2021 04:20:57 - INFO - __main__ - Step 83714: {'lr': 0.0002092516978195475, 'samples': 16073088, 'steps': 83713, 'loss/train': 0.08671850711107254} 08/31/2021 04:20:57 - INFO - __main__ - Step 83715: {'lr': 0.00020924646205045972, 'samples': 16073280, 'steps': 83714, 'loss/train': 0.07495462894439697} 08/31/2021 04:20:57 - INFO - __main__ - Step 83716: {'lr': 0.00020924122629973488, 'samples': 16073472, 'steps': 83715, 'loss/train': 1.337110996246338} 08/31/2021 04:20:58 - INFO - __main__ - Step 83717: {'lr': 0.00020923599056737536, 'samples': 16073664, 'steps': 83716, 'loss/train': 0.8565772175788879} 08/31/2021 04:20:59 - INFO - __main__ - Step 83718: {'lr': 0.00020923075485338344, 'samples': 16073856, 'steps': 83717, 'loss/train': 0.13218282163143158} 08/31/2021 04:21:00 - INFO - __main__ - Step 83719: {'lr': 0.0002092255191577615, 'samples': 16074048, 'steps': 83718, 'loss/train': 1.34867262840271} 08/31/2021 04:21:00 - INFO - __main__ - Step 83720: {'lr': 0.0002092202834805119, 'samples': 16074240, 'steps': 83719, 'loss/train': 1.2416903972625732} 08/31/2021 04:21:00 - INFO - __main__ - Step 83721: {'lr': 0.00020921504782163704, 'samples': 16074432, 'steps': 83720, 'loss/train': 0.883040726184845} 08/31/2021 04:21:01 - INFO - __main__ - Step 83722: {'lr': 0.00020920981218113923, 'samples': 16074624, 'steps': 83721, 'loss/train': 1.052935004234314} 08/31/2021 04:21:02 - INFO - __main__ - Step 83723: {'lr': 0.00020920457655902087, 'samples': 16074816, 'steps': 83722, 'loss/train': 1.2196300029754639} 08/31/2021 04:21:03 - INFO - __main__ - Step 83724: {'lr': 0.0002091993409552843, 'samples': 16075008, 'steps': 83723, 'loss/train': 0.9264554977416992} 08/31/2021 04:21:03 - INFO - __main__ - Step 83725: {'lr': 0.00020919410536993183, 'samples': 16075200, 'steps': 83724, 'loss/train': 1.1415834426879883} 08/31/2021 04:21:04 - INFO - __main__ - Step 83726: {'lr': 0.00020918886980296594, 'samples': 16075392, 'steps': 83725, 'loss/train': 1.4804235696792603} 08/31/2021 04:21:04 - INFO - __main__ - Step 83727: {'lr': 0.00020918363425438888, 'samples': 16075584, 'steps': 83726, 'loss/train': 0.6547801494598389} 08/31/2021 04:21:04 - INFO - __main__ - Step 83728: {'lr': 0.00020917839872420312, 'samples': 16075776, 'steps': 83727, 'loss/train': 1.784218192100525} 08/31/2021 04:21:06 - INFO - __main__ - Step 83729: {'lr': 0.00020917316321241084, 'samples': 16075968, 'steps': 83728, 'loss/train': 1.7434531450271606} 08/31/2021 04:21:06 - INFO - __main__ - Step 83730: {'lr': 0.00020916792771901452, 'samples': 16076160, 'steps': 83729, 'loss/train': 1.010172963142395} 08/31/2021 04:21:07 - INFO - __main__ - Step 83731: {'lr': 0.00020916269224401652, 'samples': 16076352, 'steps': 83730, 'loss/train': 1.080782413482666} 08/31/2021 04:21:07 - INFO - __main__ - Step 83732: {'lr': 0.00020915745678741916, 'samples': 16076544, 'steps': 83731, 'loss/train': 1.3669849634170532} 08/31/2021 04:21:07 - INFO - __main__ - Step 83733: {'lr': 0.00020915222134922483, 'samples': 16076736, 'steps': 83732, 'loss/train': 1.2640533447265625} 08/31/2021 04:21:09 - INFO - __main__ - Step 83734: {'lr': 0.00020914698592943586, 'samples': 16076928, 'steps': 83733, 'loss/train': 1.0662364959716797} 08/31/2021 04:21:09 - INFO - __main__ - Step 83735: {'lr': 0.00020914175052805464, 'samples': 16077120, 'steps': 83734, 'loss/train': 0.7446686625480652} 08/31/2021 04:21:10 - INFO - __main__ - Step 83736: {'lr': 0.00020913651514508353, 'samples': 16077312, 'steps': 83735, 'loss/train': 1.1598947048187256} 08/31/2021 04:21:10 - INFO - __main__ - Step 83737: {'lr': 0.00020913127978052488, 'samples': 16077504, 'steps': 83736, 'loss/train': 1.1245155334472656} 08/31/2021 04:21:10 - INFO - __main__ - Step 83738: {'lr': 0.00020912604443438102, 'samples': 16077696, 'steps': 83737, 'loss/train': 0.5194594264030457} 08/31/2021 04:21:12 - INFO - __main__ - Step 83739: {'lr': 0.00020912080910665443, 'samples': 16077888, 'steps': 83738, 'loss/train': 1.4154162406921387} 08/31/2021 04:21:12 - INFO - __main__ - Step 83740: {'lr': 0.00020911557379734732, 'samples': 16078080, 'steps': 83739, 'loss/train': 1.0542124509811401} 08/31/2021 04:21:13 - INFO - __main__ - Step 83741: {'lr': 0.00020911033850646205, 'samples': 16078272, 'steps': 83740, 'loss/train': 1.3326700925827026} 08/31/2021 04:21:13 - INFO - __main__ - Step 83742: {'lr': 0.00020910510323400103, 'samples': 16078464, 'steps': 83741, 'loss/train': 1.0179039239883423} 08/31/2021 04:21:13 - INFO - __main__ - Step 83743: {'lr': 0.00020909986797996665, 'samples': 16078656, 'steps': 83742, 'loss/train': 0.810261070728302} 08/31/2021 04:21:15 - INFO - __main__ - Step 83744: {'lr': 0.00020909463274436122, 'samples': 16078848, 'steps': 83743, 'loss/train': 1.5886141061782837} 08/31/2021 04:21:16 - INFO - __main__ - Step 83745: {'lr': 0.00020908939752718714, 'samples': 16079040, 'steps': 83744, 'loss/train': 1.3474351167678833} 08/31/2021 04:21:16 - INFO - __main__ - Step 83746: {'lr': 0.0002090841623284467, 'samples': 16079232, 'steps': 83745, 'loss/train': 5.427116394042969} 08/31/2021 04:21:16 - INFO - __main__ - Step 83747: {'lr': 0.00020907892714814235, 'samples': 16079424, 'steps': 83746, 'loss/train': 5.5241241455078125} 08/31/2021 04:21:17 - INFO - __main__ - Step 83748: {'lr': 0.00020907369198627638, 'samples': 16079616, 'steps': 83747, 'loss/train': 1.2727289199829102} 08/31/2021 04:21:17 - INFO - __main__ - Step 83749: {'lr': 0.0002090684568428512, 'samples': 16079808, 'steps': 83748, 'loss/train': 1.2160227298736572} 08/31/2021 04:21:19 - INFO - __main__ - Step 83750: {'lr': 0.00020906322171786914, 'samples': 16080000, 'steps': 83749, 'loss/train': 0.7654573917388916} 08/31/2021 04:21:19 - INFO - __main__ - Step 83751: {'lr': 0.00020905798661133252, 'samples': 16080192, 'steps': 83750, 'loss/train': 0.7699839472770691} 08/31/2021 04:21:19 - INFO - __main__ - Step 83752: {'lr': 0.00020905275152324388, 'samples': 16080384, 'steps': 83751, 'loss/train': 1.2618443965911865} 08/31/2021 04:21:20 - INFO - __main__ - Step 83753: {'lr': 0.00020904751645360532, 'samples': 16080576, 'steps': 83752, 'loss/train': 1.1761292219161987} 08/31/2021 04:21:20 - INFO - __main__ - Step 83754: {'lr': 0.0002090422814024193, 'samples': 16080768, 'steps': 83753, 'loss/train': 1.3468968868255615} 08/31/2021 04:21:22 - INFO - __main__ - Step 83755: {'lr': 0.00020903704636968822, 'samples': 16080960, 'steps': 83754, 'loss/train': 1.4938814640045166} 08/31/2021 04:21:22 - INFO - __main__ - Step 83756: {'lr': 0.0002090318113554144, 'samples': 16081152, 'steps': 83755, 'loss/train': 1.2104506492614746} 08/31/2021 04:21:23 - INFO - __main__ - Step 83757: {'lr': 0.00020902657635960022, 'samples': 16081344, 'steps': 83756, 'loss/train': 1.2694945335388184} 08/31/2021 04:21:23 - INFO - __main__ - Step 83758: {'lr': 0.00020902134138224804, 'samples': 16081536, 'steps': 83757, 'loss/train': 1.2436060905456543} 08/31/2021 04:21:24 - INFO - __main__ - Step 83759: {'lr': 0.00020901610642336022, 'samples': 16081728, 'steps': 83758, 'loss/train': 2.0029170513153076} 08/31/2021 04:21:24 - INFO - __main__ - Step 83760: {'lr': 0.00020901087148293907, 'samples': 16081920, 'steps': 83759, 'loss/train': 1.5480051040649414} 08/31/2021 04:21:24 - INFO - __main__ - Step 83761: {'lr': 0.00020900563656098704, 'samples': 16082112, 'steps': 83760, 'loss/train': 1.9530678987503052} 08/31/2021 04:21:27 - INFO - __main__ - Step 83762: {'lr': 0.0002090004016575064, 'samples': 16082304, 'steps': 83761, 'loss/train': 0.8859835267066956} 08/31/2021 04:21:27 - INFO - __main__ - Step 83763: {'lr': 0.00020899516677249955, 'samples': 16082496, 'steps': 83762, 'loss/train': 1.8466711044311523} 08/31/2021 04:21:27 - INFO - __main__ - Step 83764: {'lr': 0.00020898993190596887, 'samples': 16082688, 'steps': 83763, 'loss/train': 0.45215827226638794} 08/31/2021 04:21:28 - INFO - __main__ - Step 83765: {'lr': 0.00020898469705791668, 'samples': 16082880, 'steps': 83764, 'loss/train': 0.023923052474856377} 08/31/2021 04:21:28 - INFO - __main__ - Step 83766: {'lr': 0.00020897946222834548, 'samples': 16083072, 'steps': 83765, 'loss/train': 1.118023157119751} 08/31/2021 04:21:28 - INFO - __main__ - Step 83767: {'lr': 0.00020897422741725734, 'samples': 16083264, 'steps': 83766, 'loss/train': 1.4722329378128052} 08/31/2021 04:21:30 - INFO - __main__ - Step 83768: {'lr': 0.00020896899262465483, 'samples': 16083456, 'steps': 83767, 'loss/train': 0.7549628615379333} 08/31/2021 04:21:31 - INFO - __main__ - Step 83769: {'lr': 0.00020896375785054021, 'samples': 16083648, 'steps': 83768, 'loss/train': 0.858726441860199} 08/31/2021 04:21:31 - INFO - __main__ - Step 83770: {'lr': 0.0002089585230949159, 'samples': 16083840, 'steps': 83769, 'loss/train': 1.2118918895721436} 08/31/2021 04:21:31 - INFO - __main__ - Step 83771: {'lr': 0.0002089532883577843, 'samples': 16084032, 'steps': 83770, 'loss/train': 1.241033673286438} 08/31/2021 04:21:32 - INFO - __main__ - Step 83772: {'lr': 0.00020894805363914768, 'samples': 16084224, 'steps': 83771, 'loss/train': 0.02020811289548874} 08/31/2021 04:21:32 - INFO - __main__ - Step 83773: {'lr': 0.00020894281893900842, 'samples': 16084416, 'steps': 83772, 'loss/train': 0.8402754068374634} 08/31/2021 04:21:34 - INFO - __main__ - Step 83774: {'lr': 0.0002089375842573689, 'samples': 16084608, 'steps': 83773, 'loss/train': 0.747136652469635} 08/31/2021 04:21:34 - INFO - __main__ - Step 83775: {'lr': 0.0002089323495942315, 'samples': 16084800, 'steps': 83774, 'loss/train': 0.8090877532958984} 08/31/2021 04:21:34 - INFO - __main__ - Step 83776: {'lr': 0.0002089271149495985, 'samples': 16084992, 'steps': 83775, 'loss/train': 1.5892270803451538} 08/31/2021 04:21:35 - INFO - __main__ - Step 83777: {'lr': 0.00020892188032347234, 'samples': 16085184, 'steps': 83776, 'loss/train': 0.7339495420455933} 08/31/2021 04:21:35 - INFO - __main__ - Step 83778: {'lr': 0.00020891664571585534, 'samples': 16085376, 'steps': 83777, 'loss/train': 1.0489333868026733} 08/31/2021 04:21:37 - INFO - __main__ - Step 83779: {'lr': 0.00020891141112675, 'samples': 16085568, 'steps': 83778, 'loss/train': 1.534964680671692} 08/31/2021 04:21:37 - INFO - __main__ - Step 83780: {'lr': 0.0002089061765561584, 'samples': 16085760, 'steps': 83779, 'loss/train': 1.2432445287704468} 08/31/2021 04:21:38 - INFO - __main__ - Step 83781: {'lr': 0.00020890094200408304, 'samples': 16085952, 'steps': 83780, 'loss/train': 1.7622792720794678} 08/31/2021 04:21:38 - INFO - __main__ - Step 83782: {'lr': 0.0002088957074705263, 'samples': 16086144, 'steps': 83781, 'loss/train': 1.0837379693984985} 08/31/2021 04:21:38 - INFO - __main__ - Step 83783: {'lr': 0.00020889047295549051, 'samples': 16086336, 'steps': 83782, 'loss/train': 0.9428108930587769} 08/31/2021 04:21:39 - INFO - __main__ - Step 83784: {'lr': 0.00020888523845897806, 'samples': 16086528, 'steps': 83783, 'loss/train': 1.3234152793884277} 08/31/2021 04:21:40 - INFO - __main__ - Step 83785: {'lr': 0.00020888000398099126, 'samples': 16086720, 'steps': 83784, 'loss/train': 0.017000624909996986} 08/31/2021 04:21:41 - INFO - __main__ - Step 83786: {'lr': 0.0002088747695215325, 'samples': 16086912, 'steps': 83785, 'loss/train': 1.0175291299819946} 08/31/2021 04:21:41 - INFO - __main__ - Step 83787: {'lr': 0.00020886953508060413, 'samples': 16087104, 'steps': 83786, 'loss/train': 0.938085675239563} 08/31/2021 04:21:42 - INFO - __main__ - Step 83788: {'lr': 0.00020886430065820852, 'samples': 16087296, 'steps': 83787, 'loss/train': 1.0637226104736328} 08/31/2021 04:21:42 - INFO - __main__ - Step 83789: {'lr': 0.00020885906625434802, 'samples': 16087488, 'steps': 83788, 'loss/train': 1.4415751695632935} 08/31/2021 04:21:43 - INFO - __main__ - Step 83790: {'lr': 0.000208853831869025, 'samples': 16087680, 'steps': 83789, 'loss/train': 1.3771770000457764} 08/31/2021 04:21:44 - INFO - __main__ - Step 83791: {'lr': 0.0002088485975022418, 'samples': 16087872, 'steps': 83790, 'loss/train': 1.090226411819458} 08/31/2021 04:21:44 - INFO - __main__ - Step 83792: {'lr': 0.0002088433631540008, 'samples': 16088064, 'steps': 83791, 'loss/train': 0.03851045295596123} 08/31/2021 04:21:45 - INFO - __main__ - Step 83793: {'lr': 0.00020883812882430445, 'samples': 16088256, 'steps': 83792, 'loss/train': 1.1586755514144897} 08/31/2021 04:21:45 - INFO - __main__ - Step 83794: {'lr': 0.00020883289451315487, 'samples': 16088448, 'steps': 83793, 'loss/train': 1.2787944078445435} 08/31/2021 04:21:45 - INFO - __main__ - Step 83795: {'lr': 0.00020882766022055458, 'samples': 16088640, 'steps': 83794, 'loss/train': 0.5270560383796692} 08/31/2021 04:21:47 - INFO - __main__ - Step 83796: {'lr': 0.0002088224259465059, 'samples': 16088832, 'steps': 83795, 'loss/train': 0.8322535157203674} 08/31/2021 04:21:47 - INFO - __main__ - Step 83797: {'lr': 0.0002088171916910112, 'samples': 16089024, 'steps': 83796, 'loss/train': 1.3275362253189087} 08/31/2021 04:21:48 - INFO - __main__ - Step 83798: {'lr': 0.00020881195745407283, 'samples': 16089216, 'steps': 83797, 'loss/train': 1.5659207105636597} 08/31/2021 04:21:48 - INFO - __main__ - Step 83799: {'lr': 0.0002088067232356932, 'samples': 16089408, 'steps': 83798, 'loss/train': 1.3113020658493042} 08/31/2021 04:21:49 - INFO - __main__ - Step 83800: {'lr': 0.00020880148903587456, 'samples': 16089600, 'steps': 83799, 'loss/train': 2.0118136405944824} 08/31/2021 04:21:50 - INFO - __main__ - Step 83801: {'lr': 0.00020879625485461937, 'samples': 16089792, 'steps': 83800, 'loss/train': 0.6563053131103516} 08/31/2021 04:21:50 - INFO - __main__ - Step 83802: {'lr': 0.00020879102069192997, 'samples': 16089984, 'steps': 83801, 'loss/train': 1.0261964797973633} 08/31/2021 04:21:51 - INFO - __main__ - Step 83803: {'lr': 0.00020878578654780867, 'samples': 16090176, 'steps': 83802, 'loss/train': 0.9861587882041931} 08/31/2021 04:21:51 - INFO - __main__ - Step 83804: {'lr': 0.00020878055242225786, 'samples': 16090368, 'steps': 83803, 'loss/train': 1.6232430934906006} 08/31/2021 04:21:51 - INFO - __main__ - Step 83805: {'lr': 0.00020877531831527992, 'samples': 16090560, 'steps': 83804, 'loss/train': 0.6996109485626221} 08/31/2021 04:21:53 - INFO - __main__ - Step 83806: {'lr': 0.00020877008422687726, 'samples': 16090752, 'steps': 83805, 'loss/train': 2.410210609436035} 08/31/2021 04:21:53 - INFO - __main__ - Step 83807: {'lr': 0.00020876485015705205, 'samples': 16090944, 'steps': 83806, 'loss/train': 1.5244479179382324} 08/31/2021 04:21:54 - INFO - __main__ - Step 83808: {'lr': 0.0002087596161058068, 'samples': 16091136, 'steps': 83807, 'loss/train': 1.857285976409912} 08/31/2021 04:21:54 - INFO - __main__ - Step 83809: {'lr': 0.00020875438207314378, 'samples': 16091328, 'steps': 83808, 'loss/train': 1.4696643352508545} 08/31/2021 04:21:54 - INFO - __main__ - Step 83810: {'lr': 0.00020874914805906549, 'samples': 16091520, 'steps': 83809, 'loss/train': 0.5773149132728577} 08/31/2021 04:21:56 - INFO - __main__ - Step 83811: {'lr': 0.00020874391406357413, 'samples': 16091712, 'steps': 83810, 'loss/train': 1.0944145917892456} 08/31/2021 04:21:56 - INFO - __main__ - Step 83812: {'lr': 0.00020873868008667212, 'samples': 16091904, 'steps': 83811, 'loss/train': 1.517388105392456} 08/31/2021 04:21:57 - INFO - __main__ - Step 83813: {'lr': 0.00020873344612836186, 'samples': 16092096, 'steps': 83812, 'loss/train': 0.8670008778572083} 08/31/2021 04:21:57 - INFO - __main__ - Step 83814: {'lr': 0.00020872821218864563, 'samples': 16092288, 'steps': 83813, 'loss/train': 1.2231991291046143} 08/31/2021 04:21:57 - INFO - __main__ - Step 83815: {'lr': 0.00020872297826752585, 'samples': 16092480, 'steps': 83814, 'loss/train': 0.6251710653305054} 08/31/2021 04:21:59 - INFO - __main__ - Step 83816: {'lr': 0.00020871774436500486, 'samples': 16092672, 'steps': 83815, 'loss/train': 1.1951069831848145} 08/31/2021 04:21:59 - INFO - __main__ - Step 83817: {'lr': 0.00020871251048108503, 'samples': 16092864, 'steps': 83816, 'loss/train': 0.4082587659358978} 08/31/2021 04:22:00 - INFO - __main__ - Step 83818: {'lr': 0.00020870727661576868, 'samples': 16093056, 'steps': 83817, 'loss/train': 1.743154525756836} 08/31/2021 04:22:00 - INFO - __main__ - Step 83819: {'lr': 0.00020870204276905827, 'samples': 16093248, 'steps': 83818, 'loss/train': 1.5087999105453491} 08/31/2021 04:22:00 - INFO - __main__ - Step 83820: {'lr': 0.00020869680894095607, 'samples': 16093440, 'steps': 83819, 'loss/train': 0.026133891195058823} 08/31/2021 04:22:03 - INFO - __main__ - Step 83821: {'lr': 0.00020869157513146442, 'samples': 16093632, 'steps': 83820, 'loss/train': 1.3713815212249756} 08/31/2021 04:22:03 - INFO - __main__ - Step 83822: {'lr': 0.00020868634134058568, 'samples': 16093824, 'steps': 83821, 'loss/train': 0.28386247158050537} 08/31/2021 04:22:03 - INFO - __main__ - Step 83823: {'lr': 0.00020868110756832225, 'samples': 16094016, 'steps': 83822, 'loss/train': 0.07427546381950378} 08/31/2021 04:22:04 - INFO - __main__ - Step 83824: {'lr': 0.00020867587381467645, 'samples': 16094208, 'steps': 83823, 'loss/train': 1.2955962419509888} 08/31/2021 04:22:04 - INFO - __main__ - Step 83825: {'lr': 0.0002086706400796507, 'samples': 16094400, 'steps': 83824, 'loss/train': 0.8695271611213684} 08/31/2021 04:22:04 - INFO - __main__ - Step 83826: {'lr': 0.00020866540636324733, 'samples': 16094592, 'steps': 83825, 'loss/train': 0.029940759763121605} 08/31/2021 04:22:06 - INFO - __main__ - Step 83827: {'lr': 0.00020866017266546867, 'samples': 16094784, 'steps': 83826, 'loss/train': 1.1745786666870117} 08/31/2021 04:22:06 - INFO - __main__ - Step 83828: {'lr': 0.00020865493898631707, 'samples': 16094976, 'steps': 83827, 'loss/train': 1.8401530981063843} 08/31/2021 04:22:07 - INFO - __main__ - Step 83829: {'lr': 0.00020864970532579494, 'samples': 16095168, 'steps': 83828, 'loss/train': 1.6505714654922485} 08/31/2021 04:22:07 - INFO - __main__ - Step 83830: {'lr': 0.00020864447168390468, 'samples': 16095360, 'steps': 83829, 'loss/train': 1.488042950630188} 08/31/2021 04:22:08 - INFO - __main__ - Step 83831: {'lr': 0.00020863923806064852, 'samples': 16095552, 'steps': 83830, 'loss/train': 1.1500298976898193} 08/31/2021 04:22:09 - INFO - __main__ - Step 83832: {'lr': 0.00020863400445602886, 'samples': 16095744, 'steps': 83831, 'loss/train': 0.9835835695266724} 08/31/2021 04:22:10 - INFO - __main__ - Step 83833: {'lr': 0.00020862877087004817, 'samples': 16095936, 'steps': 83832, 'loss/train': 0.7615727186203003} 08/31/2021 04:22:10 - INFO - __main__ - Step 83834: {'lr': 0.00020862353730270866, 'samples': 16096128, 'steps': 83833, 'loss/train': 1.6441988945007324} 08/31/2021 04:22:10 - INFO - __main__ - Step 83835: {'lr': 0.00020861830375401273, 'samples': 16096320, 'steps': 83834, 'loss/train': 1.1375035047531128} 08/31/2021 04:22:11 - INFO - __main__ - Step 83836: {'lr': 0.00020861307022396276, 'samples': 16096512, 'steps': 83835, 'loss/train': 0.8951647281646729} 08/31/2021 04:22:12 - INFO - __main__ - Step 83837: {'lr': 0.00020860783671256108, 'samples': 16096704, 'steps': 83836, 'loss/train': 1.0713671445846558} 08/31/2021 04:22:13 - INFO - __main__ - Step 83838: {'lr': 0.00020860260321981013, 'samples': 16096896, 'steps': 83837, 'loss/train': 0.9073906540870667} 08/31/2021 04:22:13 - INFO - __main__ - Step 83839: {'lr': 0.00020859736974571214, 'samples': 16097088, 'steps': 83838, 'loss/train': 1.7332954406738281} 08/31/2021 04:22:13 - INFO - __main__ - Step 83840: {'lr': 0.00020859213629026958, 'samples': 16097280, 'steps': 83839, 'loss/train': 2.998800277709961} 08/31/2021 04:22:14 - INFO - __main__ - Step 83841: {'lr': 0.00020858690285348482, 'samples': 16097472, 'steps': 83840, 'loss/train': 1.4977201223373413} 08/31/2021 04:22:15 - INFO - __main__ - Step 83842: {'lr': 0.00020858166943536007, 'samples': 16097664, 'steps': 83841, 'loss/train': 0.9755485653877258} 08/31/2021 04:22:16 - INFO - __main__ - Step 83843: {'lr': 0.0002085764360358978, 'samples': 16097856, 'steps': 83842, 'loss/train': 1.4439356327056885} 08/31/2021 04:22:16 - INFO - __main__ - Step 83844: {'lr': 0.00020857120265510036, 'samples': 16098048, 'steps': 83843, 'loss/train': 1.4043501615524292} 08/31/2021 04:22:17 - INFO - __main__ - Step 83845: {'lr': 0.00020856596929297007, 'samples': 16098240, 'steps': 83844, 'loss/train': 1.1440593004226685} 08/31/2021 04:22:17 - INFO - __main__ - Step 83846: {'lr': 0.00020856073594950934, 'samples': 16098432, 'steps': 83845, 'loss/train': 0.6164247989654541} 08/31/2021 04:22:18 - INFO - __main__ - Step 83847: {'lr': 0.00020855550262472057, 'samples': 16098624, 'steps': 83846, 'loss/train': 0.7275766730308533} 08/31/2021 04:22:19 - INFO - __main__ - Step 83848: {'lr': 0.00020855026931860596, 'samples': 16098816, 'steps': 83847, 'loss/train': 1.2405678033828735} 08/31/2021 04:22:19 - INFO - __main__ - Step 83849: {'lr': 0.000208545036031168, 'samples': 16099008, 'steps': 83848, 'loss/train': 1.189247488975525} 08/31/2021 04:22:20 - INFO - __main__ - Step 83850: {'lr': 0.00020853980276240895, 'samples': 16099200, 'steps': 83849, 'loss/train': 1.3973373174667358} 08/31/2021 04:22:20 - INFO - __main__ - Step 83851: {'lr': 0.00020853456951233133, 'samples': 16099392, 'steps': 83850, 'loss/train': 1.5739343166351318} 08/31/2021 04:22:20 - INFO - __main__ - Step 83852: {'lr': 0.00020852933628093728, 'samples': 16099584, 'steps': 83851, 'loss/train': 1.410321831703186} 08/31/2021 04:22:22 - INFO - __main__ - Step 83853: {'lr': 0.00020852410306822932, 'samples': 16099776, 'steps': 83852, 'loss/train': 1.450503945350647} 08/31/2021 04:22:22 - INFO - __main__ - Step 83854: {'lr': 0.00020851886987420976, 'samples': 16099968, 'steps': 83853, 'loss/train': 1.2908631563186646} 08/31/2021 04:22:22 - INFO - __main__ - Step 83855: {'lr': 0.00020851363669888097, 'samples': 16100160, 'steps': 83854, 'loss/train': 1.363702654838562} 08/31/2021 04:22:23 - INFO - __main__ - Step 83856: {'lr': 0.00020850840354224526, 'samples': 16100352, 'steps': 83855, 'loss/train': 1.6360859870910645} 08/31/2021 04:22:23 - INFO - __main__ - Step 83857: {'lr': 0.00020850317040430503, 'samples': 16100544, 'steps': 83856, 'loss/train': 1.2957382202148438} 08/31/2021 04:22:25 - INFO - __main__ - Step 83858: {'lr': 0.00020849793728506264, 'samples': 16100736, 'steps': 83857, 'loss/train': 1.2580807209014893} 08/31/2021 04:22:25 - INFO - __main__ - Step 83859: {'lr': 0.00020849270418452044, 'samples': 16100928, 'steps': 83858, 'loss/train': 1.0166431665420532} 08/31/2021 04:22:26 - INFO - __main__ - Step 83860: {'lr': 0.00020848747110268086, 'samples': 16101120, 'steps': 83859, 'loss/train': 2.1032469272613525} 08/31/2021 04:22:26 - INFO - __main__ - Step 83861: {'lr': 0.00020848223803954607, 'samples': 16101312, 'steps': 83860, 'loss/train': 1.3014448881149292} 08/31/2021 04:22:26 - INFO - __main__ - Step 83862: {'lr': 0.00020847700499511865, 'samples': 16101504, 'steps': 83861, 'loss/train': 0.3886444568634033} 08/31/2021 04:22:28 - INFO - __main__ - Step 83863: {'lr': 0.0002084717719694008, 'samples': 16101696, 'steps': 83862, 'loss/train': 0.8531657457351685} 08/31/2021 04:22:28 - INFO - __main__ - Step 83864: {'lr': 0.0002084665389623949, 'samples': 16101888, 'steps': 83863, 'loss/train': 1.1495870351791382} 08/31/2021 04:22:29 - INFO - __main__ - Step 83865: {'lr': 0.00020846130597410335, 'samples': 16102080, 'steps': 83864, 'loss/train': 0.7356175184249878} 08/31/2021 04:22:29 - INFO - __main__ - Step 83866: {'lr': 0.00020845607300452849, 'samples': 16102272, 'steps': 83865, 'loss/train': 0.9909865856170654} 08/31/2021 04:22:29 - INFO - __main__ - Step 83867: {'lr': 0.00020845084005367267, 'samples': 16102464, 'steps': 83866, 'loss/train': 1.3080284595489502} 08/31/2021 04:22:31 - INFO - __main__ - Step 83868: {'lr': 0.0002084456071215383, 'samples': 16102656, 'steps': 83867, 'loss/train': 1.389320731163025} 08/31/2021 04:22:31 - INFO - __main__ - Step 83869: {'lr': 0.00020844037420812768, 'samples': 16102848, 'steps': 83868, 'loss/train': 1.5460211038589478} 08/31/2021 04:22:32 - INFO - __main__ - Step 83870: {'lr': 0.00020843514131344316, 'samples': 16103040, 'steps': 83869, 'loss/train': 1.113715410232544} 08/31/2021 04:22:32 - INFO - __main__ - Step 83871: {'lr': 0.00020842990843748712, 'samples': 16103232, 'steps': 83870, 'loss/train': 1.0889469385147095} 08/31/2021 04:22:32 - INFO - __main__ - Step 83872: {'lr': 0.00020842467558026195, 'samples': 16103424, 'steps': 83871, 'loss/train': 1.3013827800750732} 08/31/2021 04:22:33 - INFO - __main__ - Step 83873: {'lr': 0.0002084194427417701, 'samples': 16103616, 'steps': 83872, 'loss/train': 1.8482720851898193} 08/31/2021 04:22:35 - INFO - __main__ - Step 83874: {'lr': 0.0002084142099220137, 'samples': 16103808, 'steps': 83873, 'loss/train': 1.1546860933303833} 08/31/2021 04:22:35 - INFO - __main__ - Step 83875: {'lr': 0.00020840897712099516, 'samples': 16104000, 'steps': 83874, 'loss/train': 1.599013328552246} 08/31/2021 04:22:36 - INFO - __main__ - Step 83876: {'lr': 0.00020840374433871695, 'samples': 16104192, 'steps': 83875, 'loss/train': 0.532658040523529} 08/31/2021 04:22:36 - INFO - __main__ - Step 83877: {'lr': 0.00020839851157518135, 'samples': 16104384, 'steps': 83876, 'loss/train': 1.1948224306106567} 08/31/2021 04:22:36 - INFO - __main__ - Step 83878: {'lr': 0.0002083932788303907, 'samples': 16104576, 'steps': 83877, 'loss/train': 0.8064478635787964} 08/31/2021 04:22:38 - INFO - __main__ - Step 83879: {'lr': 0.00020838804610434747, 'samples': 16104768, 'steps': 83878, 'loss/train': 1.1262880563735962} 08/31/2021 04:22:38 - INFO - __main__ - Step 83880: {'lr': 0.00020838281339705393, 'samples': 16104960, 'steps': 83879, 'loss/train': 1.5560094118118286} 08/31/2021 04:22:39 - INFO - __main__ - Step 83881: {'lr': 0.00020837758070851243, 'samples': 16105152, 'steps': 83880, 'loss/train': 0.04263194277882576} 08/31/2021 04:22:39 - INFO - __main__ - Step 83882: {'lr': 0.00020837234803872535, 'samples': 16105344, 'steps': 83881, 'loss/train': 1.2240920066833496} 08/31/2021 04:22:39 - INFO - __main__ - Step 83883: {'lr': 0.00020836711538769505, 'samples': 16105536, 'steps': 83882, 'loss/train': 0.8566211462020874} 08/31/2021 04:22:41 - INFO - __main__ - Step 83884: {'lr': 0.00020836188275542386, 'samples': 16105728, 'steps': 83883, 'loss/train': 0.3352147042751312} 08/31/2021 04:22:42 - INFO - __main__ - Step 83885: {'lr': 0.00020835665014191422, 'samples': 16105920, 'steps': 83884, 'loss/train': 0.9173763394355774} 08/31/2021 04:22:42 - INFO - __main__ - Step 83886: {'lr': 0.00020835141754716837, 'samples': 16106112, 'steps': 83885, 'loss/train': 1.2105690240859985} 08/31/2021 04:22:43 - INFO - __main__ - Step 83887: {'lr': 0.00020834618497118888, 'samples': 16106304, 'steps': 83886, 'loss/train': 1.3002251386642456} 08/31/2021 04:22:43 - INFO - __main__ - Step 83888: {'lr': 0.00020834095241397782, 'samples': 16106496, 'steps': 83887, 'loss/train': 1.3962738513946533} 08/31/2021 04:22:43 - INFO - __main__ - Step 83889: {'lr': 0.0002083357198755377, 'samples': 16106688, 'steps': 83888, 'loss/train': 0.040145393460989} 08/31/2021 04:22:45 - INFO - __main__ - Step 83890: {'lr': 0.00020833048735587086, 'samples': 16106880, 'steps': 83889, 'loss/train': 0.09317013621330261} 08/31/2021 04:22:45 - INFO - __main__ - Step 83891: {'lr': 0.00020832525485497966, 'samples': 16107072, 'steps': 83890, 'loss/train': 0.8592601418495178} 08/31/2021 04:22:46 - INFO - __main__ - Step 83892: {'lr': 0.00020832002237286646, 'samples': 16107264, 'steps': 83891, 'loss/train': 1.5023599863052368} 08/31/2021 04:22:46 - INFO - __main__ - Step 83893: {'lr': 0.00020831478990953361, 'samples': 16107456, 'steps': 83892, 'loss/train': 0.8051605820655823} 08/31/2021 04:22:46 - INFO - __main__ - Step 83894: {'lr': 0.0002083095574649835, 'samples': 16107648, 'steps': 83893, 'loss/train': 1.3394134044647217} 08/31/2021 04:22:48 - INFO - __main__ - Step 83895: {'lr': 0.00020830432503921842, 'samples': 16107840, 'steps': 83894, 'loss/train': 1.1619309186935425} 08/31/2021 04:22:48 - INFO - __main__ - Step 83896: {'lr': 0.00020829909263224078, 'samples': 16108032, 'steps': 83895, 'loss/train': 0.9610984921455383} 08/31/2021 04:22:49 - INFO - __main__ - Step 83897: {'lr': 0.00020829386024405293, 'samples': 16108224, 'steps': 83896, 'loss/train': 1.363729476928711} 08/31/2021 04:22:49 - INFO - __main__ - Step 83898: {'lr': 0.0002082886278746572, 'samples': 16108416, 'steps': 83897, 'loss/train': 1.1778854131698608} 08/31/2021 04:22:49 - INFO - __main__ - Step 83899: {'lr': 0.000208283395524056, 'samples': 16108608, 'steps': 83898, 'loss/train': 1.2468825578689575} 08/31/2021 04:22:51 - INFO - __main__ - Step 83900: {'lr': 0.00020827816319225176, 'samples': 16108800, 'steps': 83899, 'loss/train': 1.8778432607650757} 08/31/2021 04:22:52 - INFO - __main__ - Step 83901: {'lr': 0.00020827293087924664, 'samples': 16108992, 'steps': 83900, 'loss/train': 0.04119161143898964} 08/31/2021 04:22:52 - INFO - __main__ - Step 83902: {'lr': 0.00020826769858504307, 'samples': 16109184, 'steps': 83901, 'loss/train': 1.4197336435317993} 08/31/2021 04:22:52 - INFO - __main__ - Step 83903: {'lr': 0.00020826246630964342, 'samples': 16109376, 'steps': 83902, 'loss/train': 0.12218032777309418} 08/31/2021 04:22:53 - INFO - __main__ - Step 83904: {'lr': 0.00020825723405305008, 'samples': 16109568, 'steps': 83903, 'loss/train': 1.6433111429214478} 08/31/2021 04:22:53 - INFO - __main__ - Step 83905: {'lr': 0.0002082520018152654, 'samples': 16109760, 'steps': 83904, 'loss/train': 1.1494925022125244} 08/31/2021 04:22:55 - INFO - __main__ - Step 83906: {'lr': 0.0002082467695962917, 'samples': 16109952, 'steps': 83905, 'loss/train': 1.11443030834198} 08/31/2021 04:22:55 - INFO - __main__ - Step 83907: {'lr': 0.00020824153739613138, 'samples': 16110144, 'steps': 83906, 'loss/train': 0.9426016807556152} 08/31/2021 04:22:55 - INFO - __main__ - Step 83908: {'lr': 0.00020823630521478676, 'samples': 16110336, 'steps': 83907, 'loss/train': 0.9547783732414246} 08/31/2021 04:22:56 - INFO - __main__ - Step 83909: {'lr': 0.00020823107305226025, 'samples': 16110528, 'steps': 83908, 'loss/train': 0.9110376834869385} 08/31/2021 04:22:56 - INFO - __main__ - Step 83910: {'lr': 0.0002082258409085541, 'samples': 16110720, 'steps': 83909, 'loss/train': 1.0612906217575073} 08/31/2021 04:22:58 - INFO - __main__ - Step 83911: {'lr': 0.00020822060878367084, 'samples': 16110912, 'steps': 83910, 'loss/train': 1.148608922958374} 08/31/2021 04:22:58 - INFO - __main__ - Step 83912: {'lr': 0.00020821537667761264, 'samples': 16111104, 'steps': 83911, 'loss/train': 0.9283157587051392} 08/31/2021 04:22:58 - INFO - __main__ - Step 83913: {'lr': 0.000208210144590382, 'samples': 16111296, 'steps': 83912, 'loss/train': 1.3276028633117676} 08/31/2021 04:22:59 - INFO - __main__ - Step 83914: {'lr': 0.00020820491252198132, 'samples': 16111488, 'steps': 83913, 'loss/train': 1.035224437713623} 08/31/2021 04:22:59 - INFO - __main__ - Step 83915: {'lr': 0.00020819968047241274, 'samples': 16111680, 'steps': 83914, 'loss/train': 0.7583062648773193} 08/31/2021 04:23:01 - INFO - __main__ - Step 83916: {'lr': 0.00020819444844167876, 'samples': 16111872, 'steps': 83915, 'loss/train': 0.4689413607120514} 08/31/2021 04:23:01 - INFO - __main__ - Step 83917: {'lr': 0.0002081892164297817, 'samples': 16112064, 'steps': 83916, 'loss/train': 0.690874457359314} 08/31/2021 04:23:01 - INFO - __main__ - Step 83918: {'lr': 0.00020818398443672395, 'samples': 16112256, 'steps': 83917, 'loss/train': 0.8720648884773254} 08/31/2021 04:23:02 - INFO - __main__ - Step 83919: {'lr': 0.00020817875246250783, 'samples': 16112448, 'steps': 83918, 'loss/train': 0.9043247103691101} 08/31/2021 04:23:02 - INFO - __main__ - Step 83920: {'lr': 0.00020817352050713574, 'samples': 16112640, 'steps': 83919, 'loss/train': 1.0250163078308105} 08/31/2021 04:23:04 - INFO - __main__ - Step 83921: {'lr': 0.00020816828857061, 'samples': 16112832, 'steps': 83920, 'loss/train': 1.1236493587493896} 08/31/2021 04:23:04 - INFO - __main__ - Step 83922: {'lr': 0.000208163056652933, 'samples': 16113024, 'steps': 83921, 'loss/train': 1.0147382020950317} 08/31/2021 04:23:04 - INFO - __main__ - Step 83923: {'lr': 0.00020815782475410707, 'samples': 16113216, 'steps': 83922, 'loss/train': 1.566736102104187} 08/31/2021 04:23:05 - INFO - __main__ - Step 83924: {'lr': 0.00020815259287413457, 'samples': 16113408, 'steps': 83923, 'loss/train': 0.8998357057571411} 08/31/2021 04:23:05 - INFO - __main__ - Step 83925: {'lr': 0.0002081473610130179, 'samples': 16113600, 'steps': 83924, 'loss/train': 0.8218896985054016} 08/31/2021 04:23:07 - INFO - __main__ - Step 83926: {'lr': 0.00020814212917075935, 'samples': 16113792, 'steps': 83925, 'loss/train': 1.5097088813781738} 08/31/2021 04:23:07 - INFO - __main__ - Step 83927: {'lr': 0.00020813689734736142, 'samples': 16113984, 'steps': 83926, 'loss/train': 1.4738680124282837} 08/31/2021 04:23:08 - INFO - __main__ - Step 83928: {'lr': 0.00020813166554282624, 'samples': 16114176, 'steps': 83927, 'loss/train': 1.2902663946151733} 08/31/2021 04:23:08 - INFO - __main__ - Step 83929: {'lr': 0.00020812643375715635, 'samples': 16114368, 'steps': 83928, 'loss/train': 1.642045021057129} 08/31/2021 04:23:08 - INFO - __main__ - Step 83930: {'lr': 0.00020812120199035396, 'samples': 16114560, 'steps': 83929, 'loss/train': 1.1986411809921265} 08/31/2021 04:23:09 - INFO - __main__ - Step 83931: {'lr': 0.00020811597024242157, 'samples': 16114752, 'steps': 83930, 'loss/train': 0.46069952845573425} 08/31/2021 04:23:11 - INFO - __main__ - Step 83932: {'lr': 0.00020811073851336142, 'samples': 16114944, 'steps': 83931, 'loss/train': 0.805388867855072} 08/31/2021 04:23:11 - INFO - __main__ - Step 83933: {'lr': 0.00020810550680317596, 'samples': 16115136, 'steps': 83932, 'loss/train': 0.986049234867096} 08/31/2021 04:23:11 - INFO - __main__ - Step 83934: {'lr': 0.00020810027511186752, 'samples': 16115328, 'steps': 83933, 'loss/train': 1.2991926670074463} 08/31/2021 04:23:12 - INFO - __main__ - Step 83935: {'lr': 0.00020809504343943848, 'samples': 16115520, 'steps': 83934, 'loss/train': 0.897307813167572} 08/31/2021 04:23:12 - INFO - __main__ - Step 83936: {'lr': 0.0002080898117858911, 'samples': 16115712, 'steps': 83935, 'loss/train': 1.2207725048065186} 08/31/2021 04:23:14 - INFO - __main__ - Step 83937: {'lr': 0.00020808458015122782, 'samples': 16115904, 'steps': 83936, 'loss/train': 1.1620107889175415} 08/31/2021 04:23:14 - INFO - __main__ - Step 83938: {'lr': 0.00020807934853545103, 'samples': 16116096, 'steps': 83937, 'loss/train': 1.1857811212539673} 08/31/2021 04:23:14 - INFO - __main__ - Step 83939: {'lr': 0.00020807411693856299, 'samples': 16116288, 'steps': 83938, 'loss/train': 1.0283499956130981} 08/31/2021 04:23:15 - INFO - __main__ - Step 83940: {'lr': 0.0002080688853605661, 'samples': 16116480, 'steps': 83939, 'loss/train': 2.4808640480041504} 08/31/2021 04:23:15 - INFO - __main__ - Step 83941: {'lr': 0.00020806365380146287, 'samples': 16116672, 'steps': 83940, 'loss/train': 0.975736141204834} 08/31/2021 04:23:17 - INFO - __main__ - Step 83942: {'lr': 0.00020805842226125537, 'samples': 16116864, 'steps': 83941, 'loss/train': 1.4492499828338623} 08/31/2021 04:23:17 - INFO - __main__ - Step 83943: {'lr': 0.00020805319073994612, 'samples': 16117056, 'steps': 83942, 'loss/train': 0.9792436957359314} 08/31/2021 04:23:18 - INFO - __main__ - Step 83944: {'lr': 0.0002080479592375374, 'samples': 16117248, 'steps': 83943, 'loss/train': 1.185634732246399} 08/31/2021 04:23:18 - INFO - __main__ - Step 83945: {'lr': 0.00020804272775403168, 'samples': 16117440, 'steps': 83944, 'loss/train': 0.983002781867981} 08/31/2021 04:23:18 - INFO - __main__ - Step 83946: {'lr': 0.00020803749628943124, 'samples': 16117632, 'steps': 83945, 'loss/train': 1.1576707363128662} 08/31/2021 04:23:20 - INFO - __main__ - Step 83947: {'lr': 0.00020803226484373847, 'samples': 16117824, 'steps': 83946, 'loss/train': 1.3612490892410278} 08/31/2021 04:23:20 - INFO - __main__ - Step 83948: {'lr': 0.00020802703341695573, 'samples': 16118016, 'steps': 83947, 'loss/train': 1.286720871925354} 08/31/2021 04:23:21 - INFO - __main__ - Step 83949: {'lr': 0.00020802180200908533, 'samples': 16118208, 'steps': 83948, 'loss/train': 1.2502591609954834} 08/31/2021 04:23:21 - INFO - __main__ - Step 83950: {'lr': 0.00020801657062012965, 'samples': 16118400, 'steps': 83949, 'loss/train': 0.8794767260551453} 08/31/2021 04:23:22 - INFO - __main__ - Step 83951: {'lr': 0.00020801133925009107, 'samples': 16118592, 'steps': 83950, 'loss/train': 1.110563039779663} 08/31/2021 04:23:23 - INFO - __main__ - Step 83952: {'lr': 0.00020800610789897196, 'samples': 16118784, 'steps': 83951, 'loss/train': 1.4871231317520142} 08/31/2021 04:23:23 - INFO - __main__ - Step 83953: {'lr': 0.00020800087656677467, 'samples': 16118976, 'steps': 83952, 'loss/train': 1.5645463466644287} 08/31/2021 04:23:24 - INFO - __main__ - Step 83954: {'lr': 0.00020799564525350153, 'samples': 16119168, 'steps': 83953, 'loss/train': 1.3661012649536133} 08/31/2021 04:23:24 - INFO - __main__ - Step 83955: {'lr': 0.00020799041395915484, 'samples': 16119360, 'steps': 83954, 'loss/train': 1.0973894596099854} 08/31/2021 04:23:24 - INFO - __main__ - Step 83956: {'lr': 0.00020798518268373706, 'samples': 16119552, 'steps': 83955, 'loss/train': 1.285827875137329} 08/31/2021 04:23:26 - INFO - __main__ - Step 83957: {'lr': 0.00020797995142725052, 'samples': 16119744, 'steps': 83956, 'loss/train': 0.5270465612411499} 08/31/2021 04:23:26 - INFO - __main__ - Step 83958: {'lr': 0.00020797472018969752, 'samples': 16119936, 'steps': 83957, 'loss/train': 1.5109132528305054} 08/31/2021 04:23:27 - INFO - __main__ - Step 83959: {'lr': 0.0002079694889710805, 'samples': 16120128, 'steps': 83958, 'loss/train': 1.1288155317306519} 08/31/2021 04:23:27 - INFO - __main__ - Step 83960: {'lr': 0.00020796425777140173, 'samples': 16120320, 'steps': 83959, 'loss/train': 1.6406919956207275} 08/31/2021 04:23:27 - INFO - __main__ - Step 83961: {'lr': 0.00020795902659066366, 'samples': 16120512, 'steps': 83960, 'loss/train': 1.6063498258590698} 08/31/2021 04:23:28 - INFO - __main__ - Step 83962: {'lr': 0.0002079537954288686, 'samples': 16120704, 'steps': 83961, 'loss/train': 1.176451325416565} 08/31/2021 04:23:29 - INFO - __main__ - Step 83963: {'lr': 0.00020794856428601888, 'samples': 16120896, 'steps': 83962, 'loss/train': 0.9323374629020691} 08/31/2021 04:23:30 - INFO - __main__ - Step 83964: {'lr': 0.000207943333162117, 'samples': 16121088, 'steps': 83963, 'loss/train': 1.603104829788208} 08/31/2021 04:23:30 - INFO - __main__ - Step 83965: {'lr': 0.0002079381020571651, 'samples': 16121280, 'steps': 83964, 'loss/train': 0.20267528295516968} 08/31/2021 04:23:30 - INFO - __main__ - Step 83966: {'lr': 0.00020793287097116563, 'samples': 16121472, 'steps': 83965, 'loss/train': 1.0026775598526} 08/31/2021 04:23:31 - INFO - __main__ - Step 83967: {'lr': 0.00020792763990412101, 'samples': 16121664, 'steps': 83966, 'loss/train': 0.9241771697998047} 08/31/2021 04:23:32 - INFO - __main__ - Step 83968: {'lr': 0.0002079224088560336, 'samples': 16121856, 'steps': 83967, 'loss/train': 1.4147037267684937} 08/31/2021 04:23:33 - INFO - __main__ - Step 83969: {'lr': 0.0002079171778269056, 'samples': 16122048, 'steps': 83968, 'loss/train': 0.1650792360305786} 08/31/2021 04:23:33 - INFO - __main__ - Step 83970: {'lr': 0.0002079119468167395, 'samples': 16122240, 'steps': 83969, 'loss/train': 0.05881567299365997} 08/31/2021 04:23:34 - INFO - __main__ - Step 83971: {'lr': 0.00020790671582553762, 'samples': 16122432, 'steps': 83970, 'loss/train': 0.534284234046936} 08/31/2021 04:23:34 - INFO - __main__ - Step 83972: {'lr': 0.00020790148485330234, 'samples': 16122624, 'steps': 83971, 'loss/train': 0.3691268563270569} 08/31/2021 04:23:35 - INFO - __main__ - Step 83973: {'lr': 0.000207896253900036, 'samples': 16122816, 'steps': 83972, 'loss/train': 1.1231181621551514} 08/31/2021 04:23:36 - INFO - __main__ - Step 83974: {'lr': 0.00020789102296574094, 'samples': 16123008, 'steps': 83973, 'loss/train': 1.7554062604904175} 08/31/2021 04:23:36 - INFO - __main__ - Step 83975: {'lr': 0.0002078857920504196, 'samples': 16123200, 'steps': 83974, 'loss/train': 1.3844529390335083} 08/31/2021 04:23:37 - INFO - __main__ - Step 83976: {'lr': 0.0002078805611540742, 'samples': 16123392, 'steps': 83975, 'loss/train': 1.1940902471542358} 08/31/2021 04:23:37 - INFO - __main__ - Step 83977: {'lr': 0.00020787533027670719, 'samples': 16123584, 'steps': 83976, 'loss/train': 1.5750783681869507} 08/31/2021 04:23:39 - INFO - __main__ - Step 83978: {'lr': 0.0002078700994183209, 'samples': 16123776, 'steps': 83977, 'loss/train': 1.5244163274765015} 08/31/2021 04:23:39 - INFO - __main__ - Step 83979: {'lr': 0.0002078648685789177, 'samples': 16123968, 'steps': 83978, 'loss/train': 1.460788369178772} 08/31/2021 04:23:39 - INFO - __main__ - Step 83980: {'lr': 0.00020785963775849992, 'samples': 16124160, 'steps': 83979, 'loss/train': 1.4721267223358154} 08/31/2021 04:23:40 - INFO - __main__ - Step 83981: {'lr': 0.00020785440695707003, 'samples': 16124352, 'steps': 83980, 'loss/train': 1.520963191986084} 08/31/2021 04:23:40 - INFO - __main__ - Step 83982: {'lr': 0.0002078491761746302, 'samples': 16124544, 'steps': 83981, 'loss/train': 0.8911744356155396} 08/31/2021 04:23:42 - INFO - __main__ - Step 83983: {'lr': 0.0002078439454111829, 'samples': 16124736, 'steps': 83982, 'loss/train': 0.5144715309143066} 08/31/2021 04:23:42 - INFO - __main__ - Step 83984: {'lr': 0.00020783871466673046, 'samples': 16124928, 'steps': 83983, 'loss/train': 1.2048770189285278} 08/31/2021 04:23:43 - INFO - __main__ - Step 83985: {'lr': 0.00020783348394127528, 'samples': 16125120, 'steps': 83984, 'loss/train': 1.3067408800125122} 08/31/2021 04:23:43 - INFO - __main__ - Step 83986: {'lr': 0.00020782825323481969, 'samples': 16125312, 'steps': 83985, 'loss/train': 1.180586338043213} 08/31/2021 04:23:44 - INFO - __main__ - Step 83987: {'lr': 0.00020782302254736598, 'samples': 16125504, 'steps': 83986, 'loss/train': 0.952953577041626} 08/31/2021 04:23:45 - INFO - __main__ - Step 83988: {'lr': 0.00020781779187891659, 'samples': 16125696, 'steps': 83987, 'loss/train': 1.5815999507904053} 08/31/2021 04:23:45 - INFO - __main__ - Step 83989: {'lr': 0.00020781256122947385, 'samples': 16125888, 'steps': 83988, 'loss/train': 1.5954787731170654} 08/31/2021 04:23:46 - INFO - __main__ - Step 83990: {'lr': 0.00020780733059904013, 'samples': 16126080, 'steps': 83989, 'loss/train': 1.2908949851989746} 08/31/2021 04:23:46 - INFO - __main__ - Step 83991: {'lr': 0.00020780209998761773, 'samples': 16126272, 'steps': 83990, 'loss/train': 0.994359016418457} 08/31/2021 04:23:46 - INFO - __main__ - Step 83992: {'lr': 0.0002077968693952091, 'samples': 16126464, 'steps': 83991, 'loss/train': 1.2159541845321655} 08/31/2021 04:23:48 - INFO - __main__ - Step 83993: {'lr': 0.00020779163882181655, 'samples': 16126656, 'steps': 83992, 'loss/train': 1.2080720663070679} 08/31/2021 04:23:49 - INFO - __main__ - Step 83994: {'lr': 0.00020778640826744243, 'samples': 16126848, 'steps': 83993, 'loss/train': 1.3607527017593384} 08/31/2021 04:23:49 - INFO - __main__ - Step 83995: {'lr': 0.0002077811777320891, 'samples': 16127040, 'steps': 83994, 'loss/train': 1.6415026187896729} 08/31/2021 04:23:49 - INFO - __main__ - Step 83996: {'lr': 0.00020777594721575892, 'samples': 16127232, 'steps': 83995, 'loss/train': 1.302653193473816} 08/31/2021 04:23:50 - INFO - __main__ - Step 83997: {'lr': 0.0002077707167184543, 'samples': 16127424, 'steps': 83996, 'loss/train': 1.4682365655899048} 08/31/2021 04:23:50 - INFO - __main__ - Step 83998: {'lr': 0.0002077654862401775, 'samples': 16127616, 'steps': 83997, 'loss/train': 0.666555643081665} 08/31/2021 04:23:52 - INFO - __main__ - Step 83999: {'lr': 0.0002077602557809309, 'samples': 16127808, 'steps': 83998, 'loss/train': 0.3613995313644409} 08/31/2021 04:23:52 - INFO - __main__ - Step 84000: {'lr': 0.00020775502534071686, 'samples': 16128000, 'steps': 83999, 'loss/train': 0.8114161491394043} 08/31/2021 04:23:53 - INFO - __main__ - Step 84001: {'lr': 0.00020774979491953777, 'samples': 16128192, 'steps': 84000, 'loss/train': 0.7792066931724548} 08/31/2021 04:23:53 - INFO - __main__ - Step 84002: {'lr': 0.00020774456451739599, 'samples': 16128384, 'steps': 84001, 'loss/train': 0.9962515830993652} 08/31/2021 04:23:53 - INFO - __main__ - Step 84003: {'lr': 0.00020773933413429383, 'samples': 16128576, 'steps': 84002, 'loss/train': 0.29039856791496277} 08/31/2021 04:23:55 - INFO - __main__ - Step 84004: {'lr': 0.00020773410377023367, 'samples': 16128768, 'steps': 84003, 'loss/train': 0.5509300827980042} 08/31/2021 04:23:55 - INFO - __main__ - Step 84005: {'lr': 0.0002077288734252179, 'samples': 16128960, 'steps': 84004, 'loss/train': 1.276431918144226} 08/31/2021 04:23:56 - INFO - __main__ - Step 84006: {'lr': 0.0002077236430992488, 'samples': 16129152, 'steps': 84005, 'loss/train': 1.0615235567092896} 08/31/2021 04:23:56 - INFO - __main__ - Step 84007: {'lr': 0.00020771841279232885, 'samples': 16129344, 'steps': 84006, 'loss/train': 1.4135799407958984} 08/31/2021 04:23:56 - INFO - __main__ - Step 84008: {'lr': 0.00020771318250446035, 'samples': 16129536, 'steps': 84007, 'loss/train': 1.0648353099822998} 08/31/2021 04:23:58 - INFO - __main__ - Step 84009: {'lr': 0.0002077079522356456, 'samples': 16129728, 'steps': 84008, 'loss/train': 0.8240970373153687} 08/31/2021 04:23:58 - INFO - __main__ - Step 84010: {'lr': 0.00020770272198588697, 'samples': 16129920, 'steps': 84009, 'loss/train': 0.9867939949035645} 08/31/2021 04:23:59 - INFO - __main__ - Step 84011: {'lr': 0.00020769749175518682, 'samples': 16130112, 'steps': 84010, 'loss/train': 1.0396556854248047} 08/31/2021 04:23:59 - INFO - __main__ - Step 84012: {'lr': 0.00020769226154354755, 'samples': 16130304, 'steps': 84011, 'loss/train': 0.8514745831489563} 08/31/2021 04:23:59 - INFO - __main__ - Step 84013: {'lr': 0.0002076870313509715, 'samples': 16130496, 'steps': 84012, 'loss/train': 0.035408083349466324} 08/31/2021 04:24:01 - INFO - __main__ - Step 84014: {'lr': 0.000207681801177461, 'samples': 16130688, 'steps': 84013, 'loss/train': 0.7834672927856445} 08/31/2021 04:24:02 - INFO - __main__ - Step 84015: {'lr': 0.00020767657102301846, 'samples': 16130880, 'steps': 84014, 'loss/train': 1.4245411157608032} 08/31/2021 04:24:02 - INFO - __main__ - Step 84016: {'lr': 0.00020767134088764617, 'samples': 16131072, 'steps': 84015, 'loss/train': 1.4206430912017822} 08/31/2021 04:24:02 - INFO - __main__ - Step 84017: {'lr': 0.00020766611077134654, 'samples': 16131264, 'steps': 84016, 'loss/train': 0.9177194237709045} 08/31/2021 04:24:03 - INFO - __main__ - Step 84018: {'lr': 0.0002076608806741219, 'samples': 16131456, 'steps': 84017, 'loss/train': 1.0647772550582886} 08/31/2021 04:24:03 - INFO - __main__ - Step 84019: {'lr': 0.0002076556505959746, 'samples': 16131648, 'steps': 84018, 'loss/train': 1.3532943725585938} 08/31/2021 04:24:05 - INFO - __main__ - Step 84020: {'lr': 0.00020765042053690703, 'samples': 16131840, 'steps': 84019, 'loss/train': 0.0894237607717514} 08/31/2021 04:24:05 - INFO - __main__ - Step 84021: {'lr': 0.00020764519049692163, 'samples': 16132032, 'steps': 84020, 'loss/train': 0.9068212509155273} 08/31/2021 04:24:05 - INFO - __main__ - Step 84022: {'lr': 0.00020763996047602054, 'samples': 16132224, 'steps': 84021, 'loss/train': 1.8163702487945557} 08/31/2021 04:24:06 - INFO - __main__ - Step 84023: {'lr': 0.00020763473047420624, 'samples': 16132416, 'steps': 84022, 'loss/train': 1.135358452796936} 08/31/2021 04:24:06 - INFO - __main__ - Step 84024: {'lr': 0.00020762950049148108, 'samples': 16132608, 'steps': 84023, 'loss/train': 1.4293098449707031} 08/31/2021 04:24:07 - INFO - __main__ - Step 84025: {'lr': 0.00020762427052784741, 'samples': 16132800, 'steps': 84024, 'loss/train': 1.230481743812561} 08/31/2021 04:24:08 - INFO - __main__ - Step 84026: {'lr': 0.00020761904058330758, 'samples': 16132992, 'steps': 84025, 'loss/train': 0.9097481369972229} 08/31/2021 04:24:08 - INFO - __main__ - Step 84027: {'lr': 0.00020761381065786394, 'samples': 16133184, 'steps': 84026, 'loss/train': 1.0303764343261719} 08/31/2021 04:24:09 - INFO - __main__ - Step 84028: {'lr': 0.0002076085807515189, 'samples': 16133376, 'steps': 84027, 'loss/train': 1.5922191143035889} 08/31/2021 04:24:09 - INFO - __main__ - Step 84029: {'lr': 0.00020760335086427475, 'samples': 16133568, 'steps': 84028, 'loss/train': 1.0983134508132935} 08/31/2021 04:24:11 - INFO - __main__ - Step 84030: {'lr': 0.0002075981209961339, 'samples': 16133760, 'steps': 84029, 'loss/train': 1.397121548652649} 08/31/2021 04:24:11 - INFO - __main__ - Step 84031: {'lr': 0.00020759289114709867, 'samples': 16133952, 'steps': 84030, 'loss/train': 0.7559865117073059} 08/31/2021 04:24:11 - INFO - __main__ - Step 84032: {'lr': 0.00020758766131717145, 'samples': 16134144, 'steps': 84031, 'loss/train': 1.542454481124878} 08/31/2021 04:24:12 - INFO - __main__ - Step 84033: {'lr': 0.00020758243150635454, 'samples': 16134336, 'steps': 84032, 'loss/train': 1.2121565341949463} 08/31/2021 04:24:12 - INFO - __main__ - Step 84034: {'lr': 0.00020757720171465035, 'samples': 16134528, 'steps': 84033, 'loss/train': 1.0201412439346313} 08/31/2021 04:24:12 - INFO - __main__ - Step 84035: {'lr': 0.00020757197194206132, 'samples': 16134720, 'steps': 84034, 'loss/train': 1.5856345891952515} 08/31/2021 04:24:15 - INFO - __main__ - Step 84036: {'lr': 0.00020756674218858962, 'samples': 16134912, 'steps': 84035, 'loss/train': 1.329203486442566} 08/31/2021 04:24:15 - INFO - __main__ - Step 84037: {'lr': 0.00020756151245423767, 'samples': 16135104, 'steps': 84036, 'loss/train': 1.248746395111084} 08/31/2021 04:24:15 - INFO - __main__ - Step 84038: {'lr': 0.00020755628273900784, 'samples': 16135296, 'steps': 84037, 'loss/train': 1.3442729711532593} 08/31/2021 04:24:16 - INFO - __main__ - Step 84039: {'lr': 0.0002075510530429025, 'samples': 16135488, 'steps': 84038, 'loss/train': 0.053128503262996674} 08/31/2021 04:24:16 - INFO - __main__ - Step 84040: {'lr': 0.000207545823365924, 'samples': 16135680, 'steps': 84039, 'loss/train': 1.6664403676986694} 08/31/2021 04:24:17 - INFO - __main__ - Step 84041: {'lr': 0.0002075405937080747, 'samples': 16135872, 'steps': 84040, 'loss/train': 0.30310341715812683} 08/31/2021 04:24:18 - INFO - __main__ - Step 84042: {'lr': 0.00020753536406935698, 'samples': 16136064, 'steps': 84041, 'loss/train': 1.115602731704712} 08/31/2021 04:24:18 - INFO - __main__ - Step 84043: {'lr': 0.0002075301344497731, 'samples': 16136256, 'steps': 84042, 'loss/train': 1.3787126541137695} 08/31/2021 04:24:19 - INFO - __main__ - Step 84044: {'lr': 0.00020752490484932557, 'samples': 16136448, 'steps': 84043, 'loss/train': 1.4581880569458008} 08/31/2021 04:24:19 - INFO - __main__ - Step 84045: {'lr': 0.0002075196752680166, 'samples': 16136640, 'steps': 84044, 'loss/train': 1.231882095336914} 08/31/2021 04:24:20 - INFO - __main__ - Step 84046: {'lr': 0.00020751444570584864, 'samples': 16136832, 'steps': 84045, 'loss/train': 1.719419002532959} 08/31/2021 04:24:21 - INFO - __main__ - Step 84047: {'lr': 0.000207509216162824, 'samples': 16137024, 'steps': 84046, 'loss/train': 1.4325575828552246} 08/31/2021 04:24:21 - INFO - __main__ - Step 84048: {'lr': 0.00020750398663894518, 'samples': 16137216, 'steps': 84047, 'loss/train': 1.9208753108978271} 08/31/2021 04:24:22 - INFO - __main__ - Step 84049: {'lr': 0.0002074987571342143, 'samples': 16137408, 'steps': 84048, 'loss/train': 1.1748954057693481} 08/31/2021 04:24:22 - INFO - __main__ - Step 84050: {'lr': 0.0002074935276486338, 'samples': 16137600, 'steps': 84049, 'loss/train': 0.7152084708213806} 08/31/2021 04:24:24 - INFO - __main__ - Step 84051: {'lr': 0.00020748829818220603, 'samples': 16137792, 'steps': 84050, 'loss/train': 0.9972022175788879} 08/31/2021 04:24:24 - INFO - __main__ - Step 84052: {'lr': 0.00020748306873493344, 'samples': 16137984, 'steps': 84051, 'loss/train': 0.6199202537536621} 08/31/2021 04:24:24 - INFO - __main__ - Step 84053: {'lr': 0.0002074778393068183, 'samples': 16138176, 'steps': 84052, 'loss/train': 0.8731797933578491} 08/31/2021 04:24:25 - INFO - __main__ - Step 84054: {'lr': 0.00020747260989786298, 'samples': 16138368, 'steps': 84053, 'loss/train': 1.1344858407974243} 08/31/2021 04:24:25 - INFO - __main__ - Step 84055: {'lr': 0.00020746738050806987, 'samples': 16138560, 'steps': 84054, 'loss/train': 1.6005243062973022} 08/31/2021 04:24:27 - INFO - __main__ - Step 84056: {'lr': 0.0002074621511374413, 'samples': 16138752, 'steps': 84055, 'loss/train': 1.3268835544586182} 08/31/2021 04:24:27 - INFO - __main__ - Step 84057: {'lr': 0.00020745692178597962, 'samples': 16138944, 'steps': 84056, 'loss/train': 1.6216248273849487} 08/31/2021 04:24:27 - INFO - __main__ - Step 84058: {'lr': 0.00020745169245368718, 'samples': 16139136, 'steps': 84057, 'loss/train': 1.1551839113235474} 08/31/2021 04:24:28 - INFO - __main__ - Step 84059: {'lr': 0.00020744646314056636, 'samples': 16139328, 'steps': 84058, 'loss/train': 0.7312164306640625} 08/31/2021 04:24:28 - INFO - __main__ - Step 84060: {'lr': 0.0002074412338466195, 'samples': 16139520, 'steps': 84059, 'loss/train': 2.029043436050415} 08/31/2021 04:24:30 - INFO - __main__ - Step 84061: {'lr': 0.00020743600457184897, 'samples': 16139712, 'steps': 84060, 'loss/train': 1.408746600151062} 08/31/2021 04:24:30 - INFO - __main__ - Step 84062: {'lr': 0.00020743077531625725, 'samples': 16139904, 'steps': 84061, 'loss/train': 0.71277916431427} 08/31/2021 04:24:31 - INFO - __main__ - Step 84063: {'lr': 0.00020742554607984642, 'samples': 16140096, 'steps': 84062, 'loss/train': 1.5724828243255615} 08/31/2021 04:24:31 - INFO - __main__ - Step 84064: {'lr': 0.000207420316862619, 'samples': 16140288, 'steps': 84063, 'loss/train': 1.4668776988983154} 08/31/2021 04:24:31 - INFO - __main__ - Step 84065: {'lr': 0.00020741508766457733, 'samples': 16140480, 'steps': 84064, 'loss/train': 0.028122855350375175} 08/31/2021 04:24:32 - INFO - __main__ - Step 84066: {'lr': 0.00020740985848572379, 'samples': 16140672, 'steps': 84065, 'loss/train': 1.5561517477035522} 08/31/2021 04:24:34 - INFO - __main__ - Step 84067: {'lr': 0.00020740462932606067, 'samples': 16140864, 'steps': 84066, 'loss/train': 0.7909387946128845} 08/31/2021 04:24:34 - INFO - __main__ - Step 84068: {'lr': 0.00020739940018559035, 'samples': 16141056, 'steps': 84067, 'loss/train': 0.03852745518088341} 08/31/2021 04:24:34 - INFO - __main__ - Step 84069: {'lr': 0.00020739417106431523, 'samples': 16141248, 'steps': 84068, 'loss/train': 1.5546399354934692} 08/31/2021 04:24:35 - INFO - __main__ - Step 84070: {'lr': 0.00020738894196223768, 'samples': 16141440, 'steps': 84069, 'loss/train': 0.9688546061515808} 08/31/2021 04:24:35 - INFO - __main__ - Step 84071: {'lr': 0.00020738371287935998, 'samples': 16141632, 'steps': 84070, 'loss/train': 0.9428066611289978} 08/31/2021 04:24:36 - INFO - __main__ - Step 84072: {'lr': 0.0002073784838156845, 'samples': 16141824, 'steps': 84071, 'loss/train': 0.9905032515525818} 08/31/2021 04:24:37 - INFO - __main__ - Step 84073: {'lr': 0.00020737325477121363, 'samples': 16142016, 'steps': 84072, 'loss/train': 0.8049349188804626} 08/31/2021 04:24:37 - INFO - __main__ - Step 84074: {'lr': 0.0002073680257459497, 'samples': 16142208, 'steps': 84073, 'loss/train': 0.9331351518630981} 08/31/2021 04:24:38 - INFO - __main__ - Step 84075: {'lr': 0.00020736279673989522, 'samples': 16142400, 'steps': 84074, 'loss/train': 0.9415481090545654} 08/31/2021 04:24:38 - INFO - __main__ - Step 84076: {'lr': 0.0002073575677530523, 'samples': 16142592, 'steps': 84075, 'loss/train': 0.22787097096443176} 08/31/2021 04:24:40 - INFO - __main__ - Step 84077: {'lr': 0.00020735233878542336, 'samples': 16142784, 'steps': 84076, 'loss/train': 0.914162814617157} 08/31/2021 04:24:40 - INFO - __main__ - Step 84078: {'lr': 0.00020734710983701086, 'samples': 16142976, 'steps': 84077, 'loss/train': 1.5822170972824097} 08/31/2021 04:24:41 - INFO - __main__ - Step 84079: {'lr': 0.00020734188090781706, 'samples': 16143168, 'steps': 84078, 'loss/train': 0.8868333101272583} 08/31/2021 04:24:41 - INFO - __main__ - Step 84080: {'lr': 0.00020733665199784435, 'samples': 16143360, 'steps': 84079, 'loss/train': 1.2312260866165161} 08/31/2021 04:24:41 - INFO - __main__ - Step 84081: {'lr': 0.00020733142310709507, 'samples': 16143552, 'steps': 84080, 'loss/train': 0.747288703918457} 08/31/2021 04:24:43 - INFO - __main__ - Step 84082: {'lr': 0.0002073261942355716, 'samples': 16143744, 'steps': 84081, 'loss/train': 0.09130659699440002} 08/31/2021 04:24:44 - INFO - __main__ - Step 84083: {'lr': 0.0002073209653832763, 'samples': 16143936, 'steps': 84082, 'loss/train': 1.439864993095398} 08/31/2021 04:24:44 - INFO - __main__ - Step 84084: {'lr': 0.00020731573655021152, 'samples': 16144128, 'steps': 84083, 'loss/train': 0.9389670491218567} 08/31/2021 04:24:44 - INFO - __main__ - Step 84085: {'lr': 0.0002073105077363796, 'samples': 16144320, 'steps': 84084, 'loss/train': 0.993013322353363} 08/31/2021 04:24:45 - INFO - __main__ - Step 84086: {'lr': 0.00020730527894178292, 'samples': 16144512, 'steps': 84085, 'loss/train': 0.10540774464607239} 08/31/2021 04:24:47 - INFO - __main__ - Step 84087: {'lr': 0.00020730005016642377, 'samples': 16144704, 'steps': 84086, 'loss/train': 1.9471337795257568} 08/31/2021 04:24:47 - INFO - __main__ - Step 84088: {'lr': 0.00020729482141030467, 'samples': 16144896, 'steps': 84087, 'loss/train': 2.239704132080078} 08/31/2021 04:24:47 - INFO - __main__ - Step 84089: {'lr': 0.00020728959267342785, 'samples': 16145088, 'steps': 84088, 'loss/train': 1.47012460231781} 08/31/2021 04:24:48 - INFO - __main__ - Step 84090: {'lr': 0.0002072843639557956, 'samples': 16145280, 'steps': 84089, 'loss/train': 1.4233227968215942} 08/31/2021 04:24:48 - INFO - __main__ - Step 84091: {'lr': 0.0002072791352574104, 'samples': 16145472, 'steps': 84090, 'loss/train': 1.0442699193954468} 08/31/2021 04:24:48 - INFO - __main__ - Step 84092: {'lr': 0.00020727390657827456, 'samples': 16145664, 'steps': 84091, 'loss/train': 1.1381908655166626} 08/31/2021 04:24:50 - INFO - __main__ - Step 84093: {'lr': 0.0002072686779183904, 'samples': 16145856, 'steps': 84092, 'loss/train': 0.7543154358863831} 08/31/2021 04:24:50 - INFO - __main__ - Step 84094: {'lr': 0.00020726344927776032, 'samples': 16146048, 'steps': 84093, 'loss/train': 0.7157547473907471} 08/31/2021 04:24:51 - INFO - __main__ - Step 84095: {'lr': 0.00020725822065638673, 'samples': 16146240, 'steps': 84094, 'loss/train': 1.4244139194488525} 08/31/2021 04:24:51 - INFO - __main__ - Step 84096: {'lr': 0.00020725299205427185, 'samples': 16146432, 'steps': 84095, 'loss/train': 0.746374785900116} 08/31/2021 04:24:51 - INFO - __main__ - Step 84097: {'lr': 0.00020724776347141817, 'samples': 16146624, 'steps': 84096, 'loss/train': 1.5931285619735718} 08/31/2021 04:24:53 - INFO - __main__ - Step 84098: {'lr': 0.000207242534907828, 'samples': 16146816, 'steps': 84097, 'loss/train': 1.6070343255996704} 08/31/2021 04:24:53 - INFO - __main__ - Step 84099: {'lr': 0.00020723730636350364, 'samples': 16147008, 'steps': 84098, 'loss/train': 1.0615679025650024} 08/31/2021 04:24:54 - INFO - __main__ - Step 84100: {'lr': 0.0002072320778384475, 'samples': 16147200, 'steps': 84099, 'loss/train': 0.3765754997730255} 08/31/2021 04:24:54 - INFO - __main__ - Step 84101: {'lr': 0.00020722684933266192, 'samples': 16147392, 'steps': 84100, 'loss/train': 1.6184791326522827} 08/31/2021 04:24:55 - INFO - __main__ - Step 84102: {'lr': 0.0002072216208461493, 'samples': 16147584, 'steps': 84101, 'loss/train': 1.2705247402191162} 08/31/2021 04:24:56 - INFO - __main__ - Step 84103: {'lr': 0.00020721639237891194, 'samples': 16147776, 'steps': 84102, 'loss/train': 0.8526174426078796} 08/31/2021 04:24:57 - INFO - __main__ - Step 84104: {'lr': 0.00020721116393095218, 'samples': 16147968, 'steps': 84103, 'loss/train': 1.8763750791549683} 08/31/2021 04:24:57 - INFO - __main__ - Step 84105: {'lr': 0.00020720593550227243, 'samples': 16148160, 'steps': 84104, 'loss/train': 3.4987568855285645} 08/31/2021 04:24:57 - INFO - __main__ - Step 84106: {'lr': 0.00020720070709287502, 'samples': 16148352, 'steps': 84105, 'loss/train': 1.0259500741958618} 08/31/2021 04:24:58 - INFO - __main__ - Step 84107: {'lr': 0.00020719547870276232, 'samples': 16148544, 'steps': 84106, 'loss/train': 1.2114626169204712} 08/31/2021 04:24:59 - INFO - __main__ - Step 84108: {'lr': 0.00020719025033193666, 'samples': 16148736, 'steps': 84107, 'loss/train': 1.5580458641052246} 08/31/2021 04:25:00 - INFO - __main__ - Step 84109: {'lr': 0.00020718502198040047, 'samples': 16148928, 'steps': 84108, 'loss/train': 1.6066266298294067} 08/31/2021 04:25:00 - INFO - __main__ - Step 84110: {'lr': 0.00020717979364815597, 'samples': 16149120, 'steps': 84109, 'loss/train': 0.8271237015724182} 08/31/2021 04:25:00 - INFO - __main__ - Step 84111: {'lr': 0.00020717456533520564, 'samples': 16149312, 'steps': 84110, 'loss/train': 1.5461703538894653} 08/31/2021 04:25:01 - INFO - __main__ - Step 84112: {'lr': 0.00020716933704155178, 'samples': 16149504, 'steps': 84111, 'loss/train': 1.291229248046875} 08/31/2021 04:25:01 - INFO - __main__ - Step 84113: {'lr': 0.00020716410876719674, 'samples': 16149696, 'steps': 84112, 'loss/train': 0.9860996603965759} 08/31/2021 04:25:03 - INFO - __main__ - Step 84114: {'lr': 0.00020715888051214292, 'samples': 16149888, 'steps': 84113, 'loss/train': 1.0664143562316895} 08/31/2021 04:25:03 - INFO - __main__ - Step 84115: {'lr': 0.00020715365227639266, 'samples': 16150080, 'steps': 84114, 'loss/train': 2.6697089672088623} 08/31/2021 04:25:04 - INFO - __main__ - Step 84116: {'lr': 0.00020714842405994828, 'samples': 16150272, 'steps': 84115, 'loss/train': 1.0214297771453857} 08/31/2021 04:25:04 - INFO - __main__ - Step 84117: {'lr': 0.00020714319586281213, 'samples': 16150464, 'steps': 84116, 'loss/train': 1.38523268699646} 08/31/2021 04:25:04 - INFO - __main__ - Step 84118: {'lr': 0.00020713796768498662, 'samples': 16150656, 'steps': 84117, 'loss/train': 0.7122229337692261} 08/31/2021 04:25:06 - INFO - __main__ - Step 84119: {'lr': 0.00020713273952647408, 'samples': 16150848, 'steps': 84118, 'loss/train': 0.4681571125984192} 08/31/2021 04:25:06 - INFO - __main__ - Step 84120: {'lr': 0.00020712751138727694, 'samples': 16151040, 'steps': 84119, 'loss/train': 1.0764169692993164} 08/31/2021 04:25:07 - INFO - __main__ - Step 84121: {'lr': 0.00020712228326739737, 'samples': 16151232, 'steps': 84120, 'loss/train': 0.70119708776474} 08/31/2021 04:25:07 - INFO - __main__ - Step 84122: {'lr': 0.00020711705516683788, 'samples': 16151424, 'steps': 84121, 'loss/train': 1.3405168056488037} 08/31/2021 04:25:07 - INFO - __main__ - Step 84123: {'lr': 0.00020711182708560075, 'samples': 16151616, 'steps': 84122, 'loss/train': 1.9189667701721191} 08/31/2021 04:25:08 - INFO - __main__ - Step 84124: {'lr': 0.00020710659902368838, 'samples': 16151808, 'steps': 84123, 'loss/train': 1.138474464416504} 08/31/2021 04:25:09 - INFO - __main__ - Step 84125: {'lr': 0.00020710137098110316, 'samples': 16152000, 'steps': 84124, 'loss/train': 1.323412537574768} 08/31/2021 04:25:10 - INFO - __main__ - Step 84126: {'lr': 0.00020709614295784734, 'samples': 16152192, 'steps': 84125, 'loss/train': 1.1879805326461792} 08/31/2021 04:25:10 - INFO - __main__ - Step 84127: {'lr': 0.0002070909149539234, 'samples': 16152384, 'steps': 84126, 'loss/train': 0.858887255191803} 08/31/2021 04:25:10 - INFO - __main__ - Step 84128: {'lr': 0.00020708568696933355, 'samples': 16152576, 'steps': 84127, 'loss/train': 1.122378945350647} 08/31/2021 04:25:11 - INFO - __main__ - Step 84129: {'lr': 0.00020708045900408035, 'samples': 16152768, 'steps': 84128, 'loss/train': 1.3852591514587402} 08/31/2021 04:25:12 - INFO - __main__ - Step 84130: {'lr': 0.00020707523105816596, 'samples': 16152960, 'steps': 84129, 'loss/train': 0.9277246594429016} 08/31/2021 04:25:13 - INFO - __main__ - Step 84131: {'lr': 0.00020707000313159284, 'samples': 16153152, 'steps': 84130, 'loss/train': 1.2088563442230225} 08/31/2021 04:25:13 - INFO - __main__ - Step 84132: {'lr': 0.0002070647752243633, 'samples': 16153344, 'steps': 84131, 'loss/train': 1.3980839252471924} 08/31/2021 04:25:13 - INFO - __main__ - Step 84133: {'lr': 0.00020705954733647966, 'samples': 16153536, 'steps': 84132, 'loss/train': 1.095967411994934} 08/31/2021 04:25:14 - INFO - __main__ - Step 84134: {'lr': 0.00020705431946794434, 'samples': 16153728, 'steps': 84133, 'loss/train': 1.782335877418518} 08/31/2021 04:25:16 - INFO - __main__ - Step 84135: {'lr': 0.0002070490916187597, 'samples': 16153920, 'steps': 84134, 'loss/train': 1.8401461839675903} 08/31/2021 04:25:16 - INFO - __main__ - Step 84136: {'lr': 0.00020704386378892807, 'samples': 16154112, 'steps': 84135, 'loss/train': 0.7250221371650696} 08/31/2021 04:25:16 - INFO - __main__ - Step 84137: {'lr': 0.0002070386359784518, 'samples': 16154304, 'steps': 84136, 'loss/train': 0.0189021285623312} 08/31/2021 04:25:17 - INFO - __main__ - Step 84138: {'lr': 0.00020703340818733327, 'samples': 16154496, 'steps': 84137, 'loss/train': 0.05613337457180023} 08/31/2021 04:25:17 - INFO - __main__ - Step 84139: {'lr': 0.00020702818041557484, 'samples': 16154688, 'steps': 84138, 'loss/train': 0.7969303131103516} 08/31/2021 04:25:17 - INFO - __main__ - Step 84140: {'lr': 0.00020702295266317882, 'samples': 16154880, 'steps': 84139, 'loss/train': 1.4101372957229614} 08/31/2021 04:25:19 - INFO - __main__ - Step 84141: {'lr': 0.00020701772493014758, 'samples': 16155072, 'steps': 84140, 'loss/train': 0.9133666753768921} 08/31/2021 04:25:19 - INFO - __main__ - Step 84142: {'lr': 0.00020701249721648363, 'samples': 16155264, 'steps': 84141, 'loss/train': 1.2800209522247314} 08/31/2021 04:25:20 - INFO - __main__ - Step 84143: {'lr': 0.00020700726952218906, 'samples': 16155456, 'steps': 84142, 'loss/train': 0.8334326148033142} 08/31/2021 04:25:20 - INFO - __main__ - Step 84144: {'lr': 0.0002070020418472664, 'samples': 16155648, 'steps': 84143, 'loss/train': 0.9858244061470032} 08/31/2021 04:25:21 - INFO - __main__ - Step 84145: {'lr': 0.0002069968141917179, 'samples': 16155840, 'steps': 84144, 'loss/train': 1.4670042991638184} 08/31/2021 04:25:23 - INFO - __main__ - Step 84146: {'lr': 0.000206991586555546, 'samples': 16156032, 'steps': 84145, 'loss/train': 1.331199288368225} 08/31/2021 04:25:24 - INFO - __main__ - Step 84147: {'lr': 0.000206986358938753, 'samples': 16156224, 'steps': 84146, 'loss/train': 1.0711764097213745} 08/31/2021 04:25:24 - INFO - __main__ - Step 84148: {'lr': 0.0002069811313413413, 'samples': 16156416, 'steps': 84147, 'loss/train': 0.9861230254173279} 08/31/2021 04:25:25 - INFO - __main__ - Step 84149: {'lr': 0.00020697590376331324, 'samples': 16156608, 'steps': 84148, 'loss/train': 0.18648071587085724} 08/31/2021 04:25:25 - INFO - __main__ - Step 84150: {'lr': 0.0002069706762046712, 'samples': 16156800, 'steps': 84149, 'loss/train': 1.5644469261169434} 08/31/2021 04:25:25 - INFO - __main__ - Step 84151: {'lr': 0.00020696544866541744, 'samples': 16156992, 'steps': 84150, 'loss/train': 1.3147727251052856} 08/31/2021 04:25:27 - INFO - __main__ - Step 84152: {'lr': 0.00020696022114555443, 'samples': 16157184, 'steps': 84151, 'loss/train': 0.17107947170734406} 08/31/2021 04:25:27 - INFO - __main__ - Step 84153: {'lr': 0.0002069549936450845, 'samples': 16157376, 'steps': 84152, 'loss/train': 1.2194372415542603} 08/31/2021 04:25:28 - INFO - __main__ - Step 84154: {'lr': 0.00020694976616400995, 'samples': 16157568, 'steps': 84153, 'loss/train': 2.7326242923736572} 08/31/2021 04:25:28 - INFO - __main__ - Step 84155: {'lr': 0.00020694453870233318, 'samples': 16157760, 'steps': 84154, 'loss/train': 1.1844223737716675} 08/31/2021 04:25:28 - INFO - __main__ - Step 84156: {'lr': 0.00020693931126005666, 'samples': 16157952, 'steps': 84155, 'loss/train': 1.3450186252593994} 08/31/2021 04:25:29 - INFO - __main__ - Step 84157: {'lr': 0.00020693408383718248, 'samples': 16158144, 'steps': 84156, 'loss/train': 1.1788429021835327} 08/31/2021 04:25:30 - INFO - __main__ - Step 84158: {'lr': 0.00020692885643371317, 'samples': 16158336, 'steps': 84157, 'loss/train': 1.6017578840255737} 08/31/2021 04:25:31 - INFO - __main__ - Step 84159: {'lr': 0.00020692362904965104, 'samples': 16158528, 'steps': 84158, 'loss/train': 1.6154881715774536} 08/31/2021 04:25:31 - INFO - __main__ - Step 84160: {'lr': 0.00020691840168499844, 'samples': 16158720, 'steps': 84159, 'loss/train': 1.1770365238189697} 08/31/2021 04:25:31 - INFO - __main__ - Step 84161: {'lr': 0.00020691317433975777, 'samples': 16158912, 'steps': 84160, 'loss/train': 1.1425296068191528} 08/31/2021 04:25:32 - INFO - __main__ - Step 84162: {'lr': 0.00020690794701393137, 'samples': 16159104, 'steps': 84161, 'loss/train': 1.2113739252090454} 08/31/2021 04:25:33 - INFO - __main__ - Step 84163: {'lr': 0.00020690271970752157, 'samples': 16159296, 'steps': 84162, 'loss/train': 0.9664656519889832} 08/31/2021 04:25:34 - INFO - __main__ - Step 84164: {'lr': 0.00020689749242053075, 'samples': 16159488, 'steps': 84163, 'loss/train': 0.20819765329360962} 08/31/2021 04:25:34 - INFO - __main__ - Step 84165: {'lr': 0.00020689226515296122, 'samples': 16159680, 'steps': 84164, 'loss/train': 1.3730355501174927} 08/31/2021 04:25:34 - INFO - __main__ - Step 84166: {'lr': 0.00020688703790481538, 'samples': 16159872, 'steps': 84165, 'loss/train': 0.9204843044281006} 08/31/2021 04:25:35 - INFO - __main__ - Step 84167: {'lr': 0.00020688181067609558, 'samples': 16160064, 'steps': 84166, 'loss/train': 1.4309358596801758} 08/31/2021 04:25:36 - INFO - __main__ - Step 84168: {'lr': 0.00020687658346680418, 'samples': 16160256, 'steps': 84167, 'loss/train': 1.331043004989624} 08/31/2021 04:25:37 - INFO - __main__ - Step 84169: {'lr': 0.00020687135627694365, 'samples': 16160448, 'steps': 84168, 'loss/train': 1.4778847694396973} 08/31/2021 04:25:37 - INFO - __main__ - Step 84170: {'lr': 0.00020686612910651608, 'samples': 16160640, 'steps': 84169, 'loss/train': 0.9151732921600342} 08/31/2021 04:25:37 - INFO - __main__ - Step 84171: {'lr': 0.00020686090195552398, 'samples': 16160832, 'steps': 84170, 'loss/train': 0.9381585121154785} 08/31/2021 04:25:38 - INFO - __main__ - Step 84172: {'lr': 0.0002068556748239697, 'samples': 16161024, 'steps': 84171, 'loss/train': 1.1398555040359497} 08/31/2021 04:25:39 - INFO - __main__ - Step 84173: {'lr': 0.00020685044771185556, 'samples': 16161216, 'steps': 84172, 'loss/train': 1.0976746082305908} 08/31/2021 04:25:40 - INFO - __main__ - Step 84174: {'lr': 0.000206845220619184, 'samples': 16161408, 'steps': 84173, 'loss/train': 0.9138550162315369} 08/31/2021 04:25:40 - INFO - __main__ - Step 84175: {'lr': 0.00020683999354595726, 'samples': 16161600, 'steps': 84174, 'loss/train': 0.1669134944677353} 08/31/2021 04:25:40 - INFO - __main__ - Step 84176: {'lr': 0.00020683476649217776, 'samples': 16161792, 'steps': 84175, 'loss/train': 1.14673912525177} 08/31/2021 04:25:41 - INFO - __main__ - Step 84177: {'lr': 0.00020682953945784787, 'samples': 16161984, 'steps': 84176, 'loss/train': 1.013815999031067} 08/31/2021 04:25:42 - INFO - __main__ - Step 84178: {'lr': 0.0002068243124429699, 'samples': 16162176, 'steps': 84177, 'loss/train': 1.2540632486343384} 08/31/2021 04:25:43 - INFO - __main__ - Step 84179: {'lr': 0.00020681908544754624, 'samples': 16162368, 'steps': 84178, 'loss/train': 0.9019933938980103} 08/31/2021 04:25:43 - INFO - __main__ - Step 84180: {'lr': 0.00020681385847157925, 'samples': 16162560, 'steps': 84179, 'loss/train': 1.1812113523483276} 08/31/2021 04:25:43 - INFO - __main__ - Step 84181: {'lr': 0.00020680863151507122, 'samples': 16162752, 'steps': 84180, 'loss/train': 1.8152134418487549} 08/31/2021 04:25:44 - INFO - __main__ - Step 84182: {'lr': 0.0002068034045780246, 'samples': 16162944, 'steps': 84181, 'loss/train': 2.0657811164855957} 08/31/2021 04:25:45 - INFO - __main__ - Step 84183: {'lr': 0.0002067981776604418, 'samples': 16163136, 'steps': 84182, 'loss/train': 1.3121981620788574} 08/31/2021 04:25:46 - INFO - __main__ - Step 84184: {'lr': 0.00020679295076232498, 'samples': 16163328, 'steps': 84183, 'loss/train': 1.4773435592651367} 08/31/2021 04:25:46 - INFO - __main__ - Step 84185: {'lr': 0.00020678772388367655, 'samples': 16163520, 'steps': 84184, 'loss/train': 1.5519821643829346} 08/31/2021 04:25:47 - INFO - __main__ - Step 84186: {'lr': 0.00020678249702449895, 'samples': 16163712, 'steps': 84185, 'loss/train': 1.5278252363204956} 08/31/2021 04:25:47 - INFO - __main__ - Step 84187: {'lr': 0.00020677727018479446, 'samples': 16163904, 'steps': 84186, 'loss/train': 2.1315622329711914} 08/31/2021 04:25:47 - INFO - __main__ - Step 84188: {'lr': 0.00020677204336456547, 'samples': 16164096, 'steps': 84187, 'loss/train': 1.3729223012924194} 08/31/2021 04:25:49 - INFO - __main__ - Step 84189: {'lr': 0.00020676681656381436, 'samples': 16164288, 'steps': 84188, 'loss/train': 1.4868091344833374} 08/31/2021 04:25:50 - INFO - __main__ - Step 84190: {'lr': 0.00020676158978254338, 'samples': 16164480, 'steps': 84189, 'loss/train': 0.90289306640625} 08/31/2021 04:25:50 - INFO - __main__ - Step 84191: {'lr': 0.00020675636302075503, 'samples': 16164672, 'steps': 84190, 'loss/train': 1.1675504446029663} 08/31/2021 04:25:50 - INFO - __main__ - Step 84192: {'lr': 0.00020675113627845158, 'samples': 16164864, 'steps': 84191, 'loss/train': 0.06452204287052155} 08/31/2021 04:25:51 - INFO - __main__ - Step 84193: {'lr': 0.00020674590955563539, 'samples': 16165056, 'steps': 84192, 'loss/train': 0.23773348331451416} 08/31/2021 04:25:52 - INFO - __main__ - Step 84194: {'lr': 0.00020674068285230884, 'samples': 16165248, 'steps': 84193, 'loss/train': 0.3254261016845703} 08/31/2021 04:25:53 - INFO - __main__ - Step 84195: {'lr': 0.00020673545616847424, 'samples': 16165440, 'steps': 84194, 'loss/train': 1.198342204093933} 08/31/2021 04:25:53 - INFO - __main__ - Step 84196: {'lr': 0.00020673022950413412, 'samples': 16165632, 'steps': 84195, 'loss/train': 0.8163972496986389} 08/31/2021 04:25:53 - INFO - __main__ - Step 84197: {'lr': 0.00020672500285929057, 'samples': 16165824, 'steps': 84196, 'loss/train': 0.4892439842224121} 08/31/2021 04:25:54 - INFO - __main__ - Step 84198: {'lr': 0.00020671977623394605, 'samples': 16166016, 'steps': 84197, 'loss/train': 0.7459668517112732} 08/31/2021 04:25:56 - INFO - __main__ - Step 84199: {'lr': 0.00020671454962810297, 'samples': 16166208, 'steps': 84198, 'loss/train': 0.4025275409221649} 08/31/2021 04:25:56 - INFO - __main__ - Step 84200: {'lr': 0.0002067093230417636, 'samples': 16166400, 'steps': 84199, 'loss/train': 1.3877179622650146} 08/31/2021 04:25:57 - INFO - __main__ - Step 84201: {'lr': 0.00020670409647493039, 'samples': 16166592, 'steps': 84200, 'loss/train': 1.1499062776565552} 08/31/2021 04:25:57 - INFO - __main__ - Step 84202: {'lr': 0.0002066988699276056, 'samples': 16166784, 'steps': 84201, 'loss/train': 1.2854896783828735} 08/31/2021 04:25:57 - INFO - __main__ - Step 84203: {'lr': 0.00020669364339979162, 'samples': 16166976, 'steps': 84202, 'loss/train': 0.16433003544807434} 08/31/2021 04:25:58 - INFO - __main__ - Step 84204: {'lr': 0.00020668841689149088, 'samples': 16167168, 'steps': 84203, 'loss/train': 1.3939467668533325} 08/31/2021 04:25:59 - INFO - __main__ - Step 84205: {'lr': 0.0002066831904027056, 'samples': 16167360, 'steps': 84204, 'loss/train': 1.1054784059524536} 08/31/2021 04:26:00 - INFO - __main__ - Step 84206: {'lr': 0.00020667796393343828, 'samples': 16167552, 'steps': 84205, 'loss/train': 1.2178153991699219} 08/31/2021 04:26:00 - INFO - __main__ - Step 84207: {'lr': 0.00020667273748369114, 'samples': 16167744, 'steps': 84206, 'loss/train': 1.5484434366226196} 08/31/2021 04:26:00 - INFO - __main__ - Step 84208: {'lr': 0.0002066675110534666, 'samples': 16167936, 'steps': 84207, 'loss/train': 0.8725272417068481} 08/31/2021 04:26:01 - INFO - __main__ - Step 84209: {'lr': 0.00020666228464276707, 'samples': 16168128, 'steps': 84208, 'loss/train': 0.8694460391998291} 08/31/2021 04:26:02 - INFO - __main__ - Step 84210: {'lr': 0.00020665705825159488, 'samples': 16168320, 'steps': 84209, 'loss/train': 1.1239787340164185} 08/31/2021 04:26:03 - INFO - __main__ - Step 84211: {'lr': 0.0002066518318799523, 'samples': 16168512, 'steps': 84210, 'loss/train': 1.1516574621200562} 08/31/2021 04:26:03 - INFO - __main__ - Step 84212: {'lr': 0.0002066466055278417, 'samples': 16168704, 'steps': 84211, 'loss/train': 1.161759376525879} 08/31/2021 04:26:03 - INFO - __main__ - Step 84213: {'lr': 0.0002066413791952655, 'samples': 16168896, 'steps': 84212, 'loss/train': 1.0563488006591797} 08/31/2021 04:26:04 - INFO - __main__ - Step 84214: {'lr': 0.000206636152882226, 'samples': 16169088, 'steps': 84213, 'loss/train': 1.514377474784851} 08/31/2021 04:26:05 - INFO - __main__ - Step 84215: {'lr': 0.00020663092658872558, 'samples': 16169280, 'steps': 84214, 'loss/train': 0.6445379853248596} 08/31/2021 04:26:06 - INFO - __main__ - Step 84216: {'lr': 0.0002066257003147666, 'samples': 16169472, 'steps': 84215, 'loss/train': 1.4867832660675049} 08/31/2021 04:26:06 - INFO - __main__ - Step 84217: {'lr': 0.0002066204740603514, 'samples': 16169664, 'steps': 84216, 'loss/train': 1.7548002004623413} 08/31/2021 04:26:06 - INFO - __main__ - Step 84218: {'lr': 0.00020661524782548238, 'samples': 16169856, 'steps': 84217, 'loss/train': 1.4116123914718628} 08/31/2021 04:26:07 - INFO - __main__ - Step 84219: {'lr': 0.00020661002161016185, 'samples': 16170048, 'steps': 84218, 'loss/train': 1.149670958518982} 08/31/2021 04:26:09 - INFO - __main__ - Step 84220: {'lr': 0.00020660479541439214, 'samples': 16170240, 'steps': 84219, 'loss/train': 1.3564732074737549} 08/31/2021 04:26:09 - INFO - __main__ - Step 84221: {'lr': 0.00020659956923817568, 'samples': 16170432, 'steps': 84220, 'loss/train': 0.9021915197372437} 08/31/2021 04:26:09 - INFO - __main__ - Step 84222: {'lr': 0.00020659434308151482, 'samples': 16170624, 'steps': 84221, 'loss/train': 0.19263188540935516} 08/31/2021 04:26:10 - INFO - __main__ - Step 84223: {'lr': 0.0002065891169444119, 'samples': 16170816, 'steps': 84222, 'loss/train': 1.3870571851730347} 08/31/2021 04:26:10 - INFO - __main__ - Step 84224: {'lr': 0.00020658389082686915, 'samples': 16171008, 'steps': 84223, 'loss/train': 1.4726014137268066} 08/31/2021 04:26:10 - INFO - __main__ - Step 84225: {'lr': 0.00020657866472888905, 'samples': 16171200, 'steps': 84224, 'loss/train': 1.0561639070510864} 08/31/2021 04:26:12 - INFO - __main__ - Step 84226: {'lr': 0.00020657343865047395, 'samples': 16171392, 'steps': 84225, 'loss/train': 1.5448272228240967} 08/31/2021 04:26:12 - INFO - __main__ - Step 84227: {'lr': 0.0002065682125916262, 'samples': 16171584, 'steps': 84226, 'loss/train': 1.1422535181045532} 08/31/2021 04:26:13 - INFO - __main__ - Step 84228: {'lr': 0.00020656298655234812, 'samples': 16171776, 'steps': 84227, 'loss/train': 1.684194564819336} 08/31/2021 04:26:13 - INFO - __main__ - Step 84229: {'lr': 0.00020655776053264208, 'samples': 16171968, 'steps': 84228, 'loss/train': 1.6133679151535034} 08/31/2021 04:26:13 - INFO - __main__ - Step 84230: {'lr': 0.00020655253453251047, 'samples': 16172160, 'steps': 84229, 'loss/train': 1.6154298782348633} 08/31/2021 04:26:15 - INFO - __main__ - Step 84231: {'lr': 0.0002065473085519556, 'samples': 16172352, 'steps': 84230, 'loss/train': 1.0255787372589111} 08/31/2021 04:26:15 - INFO - __main__ - Step 84232: {'lr': 0.00020654208259097983, 'samples': 16172544, 'steps': 84231, 'loss/train': 1.1148191690444946} 08/31/2021 04:26:16 - INFO - __main__ - Step 84233: {'lr': 0.0002065368566495856, 'samples': 16172736, 'steps': 84232, 'loss/train': 1.346081018447876} 08/31/2021 04:26:16 - INFO - __main__ - Step 84234: {'lr': 0.00020653163072777513, 'samples': 16172928, 'steps': 84233, 'loss/train': 1.7758127450942993} 08/31/2021 04:26:16 - INFO - __main__ - Step 84235: {'lr': 0.00020652640482555086, 'samples': 16173120, 'steps': 84234, 'loss/train': 1.1186765432357788} 08/31/2021 04:26:18 - INFO - __main__ - Step 84236: {'lr': 0.00020652117894291513, 'samples': 16173312, 'steps': 84235, 'loss/train': 1.5728647708892822} 08/31/2021 04:26:18 - INFO - __main__ - Step 84237: {'lr': 0.00020651595307987026, 'samples': 16173504, 'steps': 84236, 'loss/train': 1.2279789447784424} 08/31/2021 04:26:19 - INFO - __main__ - Step 84238: {'lr': 0.00020651072723641865, 'samples': 16173696, 'steps': 84237, 'loss/train': 1.6474952697753906} 08/31/2021 04:26:19 - INFO - __main__ - Step 84239: {'lr': 0.0002065055014125626, 'samples': 16173888, 'steps': 84238, 'loss/train': 0.7153722047805786} 08/31/2021 04:26:19 - INFO - __main__ - Step 84240: {'lr': 0.0002065002756083045, 'samples': 16174080, 'steps': 84239, 'loss/train': 1.4754897356033325} 08/31/2021 04:26:21 - INFO - __main__ - Step 84241: {'lr': 0.00020649504982364673, 'samples': 16174272, 'steps': 84240, 'loss/train': 1.428183674812317} 08/31/2021 04:26:21 - INFO - __main__ - Step 84242: {'lr': 0.00020648982405859162, 'samples': 16174464, 'steps': 84241, 'loss/train': 1.9000113010406494} 08/31/2021 04:26:22 - INFO - __main__ - Step 84243: {'lr': 0.00020648459831314151, 'samples': 16174656, 'steps': 84242, 'loss/train': 1.1269248723983765} 08/31/2021 04:26:22 - INFO - __main__ - Step 84244: {'lr': 0.00020647937258729882, 'samples': 16174848, 'steps': 84243, 'loss/train': 1.19756281375885} 08/31/2021 04:26:22 - INFO - __main__ - Step 84245: {'lr': 0.0002064741468810658, 'samples': 16175040, 'steps': 84244, 'loss/train': 1.0142042636871338} 08/31/2021 04:26:24 - INFO - __main__ - Step 84246: {'lr': 0.00020646892119444485, 'samples': 16175232, 'steps': 84245, 'loss/train': 0.7572419047355652} 08/31/2021 04:26:24 - INFO - __main__ - Step 84247: {'lr': 0.00020646369552743834, 'samples': 16175424, 'steps': 84246, 'loss/train': 0.2923159897327423} 08/31/2021 04:26:25 - INFO - __main__ - Step 84248: {'lr': 0.00020645846988004863, 'samples': 16175616, 'steps': 84247, 'loss/train': 1.481764316558838} 08/31/2021 04:26:25 - INFO - __main__ - Step 84249: {'lr': 0.00020645324425227804, 'samples': 16175808, 'steps': 84248, 'loss/train': 1.4157140254974365} 08/31/2021 04:26:25 - INFO - __main__ - Step 84250: {'lr': 0.00020644801864412902, 'samples': 16176000, 'steps': 84249, 'loss/train': 0.8234243392944336} 08/31/2021 04:26:27 - INFO - __main__ - Step 84251: {'lr': 0.00020644279305560379, 'samples': 16176192, 'steps': 84250, 'loss/train': 1.420096516609192} 08/31/2021 04:26:28 - INFO - __main__ - Step 84252: {'lr': 0.00020643756748670475, 'samples': 16176384, 'steps': 84251, 'loss/train': 1.4716901779174805} 08/31/2021 04:26:28 - INFO - __main__ - Step 84253: {'lr': 0.0002064323419374343, 'samples': 16176576, 'steps': 84252, 'loss/train': 0.9089338183403015} 08/31/2021 04:26:28 - INFO - __main__ - Step 84254: {'lr': 0.00020642711640779475, 'samples': 16176768, 'steps': 84253, 'loss/train': 0.05311674624681473} 08/31/2021 04:26:29 - INFO - __main__ - Step 84255: {'lr': 0.00020642189089778852, 'samples': 16176960, 'steps': 84254, 'loss/train': 1.4891917705535889} 08/31/2021 04:26:29 - INFO - __main__ - Step 84256: {'lr': 0.00020641666540741784, 'samples': 16177152, 'steps': 84255, 'loss/train': 1.120257019996643} 08/31/2021 04:26:31 - INFO - __main__ - Step 84257: {'lr': 0.00020641143993668516, 'samples': 16177344, 'steps': 84256, 'loss/train': 1.4468656778335571} 08/31/2021 04:26:31 - INFO - __main__ - Step 84258: {'lr': 0.00020640621448559282, 'samples': 16177536, 'steps': 84257, 'loss/train': 1.1910676956176758} 08/31/2021 04:26:31 - INFO - __main__ - Step 84259: {'lr': 0.00020640098905414314, 'samples': 16177728, 'steps': 84258, 'loss/train': 0.8788592219352722} 08/31/2021 04:26:32 - INFO - __main__ - Step 84260: {'lr': 0.00020639576364233852, 'samples': 16177920, 'steps': 84259, 'loss/train': 0.5039450526237488} 08/31/2021 04:26:32 - INFO - __main__ - Step 84261: {'lr': 0.0002063905382501813, 'samples': 16178112, 'steps': 84260, 'loss/train': 1.3305000066757202} 08/31/2021 04:26:34 - INFO - __main__ - Step 84262: {'lr': 0.00020638531287767384, 'samples': 16178304, 'steps': 84261, 'loss/train': 1.26513671875} 08/31/2021 04:26:34 - INFO - __main__ - Step 84263: {'lr': 0.00020638008752481851, 'samples': 16178496, 'steps': 84262, 'loss/train': 1.249720811843872} 08/31/2021 04:26:34 - INFO - __main__ - Step 84264: {'lr': 0.0002063748621916176, 'samples': 16178688, 'steps': 84263, 'loss/train': 0.8315446376800537} 08/31/2021 04:26:35 - INFO - __main__ - Step 84265: {'lr': 0.00020636963687807356, 'samples': 16178880, 'steps': 84264, 'loss/train': 1.1776325702667236} 08/31/2021 04:26:35 - INFO - __main__ - Step 84266: {'lr': 0.00020636441158418864, 'samples': 16179072, 'steps': 84265, 'loss/train': 1.84601628780365} 08/31/2021 04:26:37 - INFO - __main__ - Step 84267: {'lr': 0.0002063591863099652, 'samples': 16179264, 'steps': 84266, 'loss/train': 1.3175811767578125} 08/31/2021 04:26:37 - INFO - __main__ - Step 84268: {'lr': 0.00020635396105540572, 'samples': 16179456, 'steps': 84267, 'loss/train': 1.1786037683486938} 08/31/2021 04:26:37 - INFO - __main__ - Step 84269: {'lr': 0.00020634873582051243, 'samples': 16179648, 'steps': 84268, 'loss/train': 1.8394005298614502} 08/31/2021 04:26:38 - INFO - __main__ - Step 84270: {'lr': 0.0002063435106052877, 'samples': 16179840, 'steps': 84269, 'loss/train': 1.4810123443603516} 08/31/2021 04:26:38 - INFO - __main__ - Step 84271: {'lr': 0.00020633828540973393, 'samples': 16180032, 'steps': 84270, 'loss/train': 0.8557626605033875} 08/31/2021 04:26:40 - INFO - __main__ - Step 84272: {'lr': 0.00020633306023385345, 'samples': 16180224, 'steps': 84271, 'loss/train': 1.4337255954742432} 08/31/2021 04:26:40 - INFO - __main__ - Step 84273: {'lr': 0.00020632783507764862, 'samples': 16180416, 'steps': 84272, 'loss/train': 1.3249847888946533} 08/31/2021 04:26:40 - INFO - __main__ - Step 84274: {'lr': 0.0002063226099411218, 'samples': 16180608, 'steps': 84273, 'loss/train': 1.2209447622299194} 08/31/2021 04:26:41 - INFO - __main__ - Step 84275: {'lr': 0.00020631738482427533, 'samples': 16180800, 'steps': 84274, 'loss/train': 1.490047574043274} 08/31/2021 04:26:41 - INFO - __main__ - Step 84276: {'lr': 0.00020631215972711158, 'samples': 16180992, 'steps': 84275, 'loss/train': 1.3708844184875488} 08/31/2021 04:26:43 - INFO - __main__ - Step 84277: {'lr': 0.000206306934649633, 'samples': 16181184, 'steps': 84276, 'loss/train': 1.207153081893921} 08/31/2021 04:26:43 - INFO - __main__ - Step 84278: {'lr': 0.00020630170959184174, 'samples': 16181376, 'steps': 84277, 'loss/train': 1.568418264389038} 08/31/2021 04:26:44 - INFO - __main__ - Step 84279: {'lr': 0.00020629648455374025, 'samples': 16181568, 'steps': 84278, 'loss/train': 1.5589216947555542} 08/31/2021 04:26:44 - INFO - __main__ - Step 84280: {'lr': 0.0002062912595353309, 'samples': 16181760, 'steps': 84279, 'loss/train': 0.8505460619926453} 08/31/2021 04:26:44 - INFO - __main__ - Step 84281: {'lr': 0.00020628603453661605, 'samples': 16181952, 'steps': 84280, 'loss/train': 0.8804190754890442} 08/31/2021 04:26:45 - INFO - __main__ - Step 84282: {'lr': 0.00020628080955759797, 'samples': 16182144, 'steps': 84281, 'loss/train': 0.45703575015068054} 08/31/2021 04:26:46 - INFO - __main__ - Step 84283: {'lr': 0.00020627558459827917, 'samples': 16182336, 'steps': 84282, 'loss/train': 0.1412734091281891} 08/31/2021 04:26:47 - INFO - __main__ - Step 84284: {'lr': 0.00020627035965866186, 'samples': 16182528, 'steps': 84283, 'loss/train': 0.550568699836731} 08/31/2021 04:26:47 - INFO - __main__ - Step 84285: {'lr': 0.00020626513473874847, 'samples': 16182720, 'steps': 84284, 'loss/train': 1.159865140914917} 08/31/2021 04:26:47 - INFO - __main__ - Step 84286: {'lr': 0.00020625990983854132, 'samples': 16182912, 'steps': 84285, 'loss/train': 1.1491824388504028} 08/31/2021 04:26:48 - INFO - __main__ - Step 84287: {'lr': 0.0002062546849580428, 'samples': 16183104, 'steps': 84286, 'loss/train': 0.9807035326957703} 08/31/2021 04:26:49 - INFO - __main__ - Step 84288: {'lr': 0.0002062494600972552, 'samples': 16183296, 'steps': 84287, 'loss/train': 0.9037405848503113} 08/31/2021 04:26:50 - INFO - __main__ - Step 84289: {'lr': 0.00020624423525618098, 'samples': 16183488, 'steps': 84288, 'loss/train': 2.053718328475952} 08/31/2021 04:26:50 - INFO - __main__ - Step 84290: {'lr': 0.0002062390104348225, 'samples': 16183680, 'steps': 84289, 'loss/train': 1.159755825996399} 08/31/2021 04:26:51 - INFO - __main__ - Step 84291: {'lr': 0.00020623378563318197, 'samples': 16183872, 'steps': 84290, 'loss/train': 0.53410404920578} 08/31/2021 04:26:51 - INFO - __main__ - Step 84292: {'lr': 0.00020622856085126179, 'samples': 16184064, 'steps': 84291, 'loss/train': 1.7991689443588257} 08/31/2021 04:26:52 - INFO - __main__ - Step 84293: {'lr': 0.00020622333608906436, 'samples': 16184256, 'steps': 84292, 'loss/train': 0.8610715866088867} 08/31/2021 04:26:53 - INFO - __main__ - Step 84294: {'lr': 0.00020621811134659203, 'samples': 16184448, 'steps': 84293, 'loss/train': 1.479347586631775} 08/31/2021 04:26:53 - INFO - __main__ - Step 84295: {'lr': 0.0002062128866238471, 'samples': 16184640, 'steps': 84294, 'loss/train': 0.9691479206085205} 08/31/2021 04:26:53 - INFO - __main__ - Step 84296: {'lr': 0.000206207661920832, 'samples': 16184832, 'steps': 84295, 'loss/train': 1.247785210609436} 08/31/2021 04:26:54 - INFO - __main__ - Step 84297: {'lr': 0.00020620243723754907, 'samples': 16185024, 'steps': 84296, 'loss/train': 1.32886803150177} 08/31/2021 04:26:55 - INFO - __main__ - Step 84298: {'lr': 0.0002061972125740006, 'samples': 16185216, 'steps': 84297, 'loss/train': 1.1498984098434448} 08/31/2021 04:26:56 - INFO - __main__ - Step 84299: {'lr': 0.000206191987930189, 'samples': 16185408, 'steps': 84298, 'loss/train': 0.7827286124229431} 08/31/2021 04:26:56 - INFO - __main__ - Step 84300: {'lr': 0.00020618676330611663, 'samples': 16185600, 'steps': 84299, 'loss/train': 1.3269572257995605} 08/31/2021 04:26:56 - INFO - __main__ - Step 84301: {'lr': 0.00020618153870178587, 'samples': 16185792, 'steps': 84300, 'loss/train': 0.910213828086853} 08/31/2021 04:26:57 - INFO - __main__ - Step 84302: {'lr': 0.00020617631411719894, 'samples': 16185984, 'steps': 84301, 'loss/train': 0.7371280789375305} 08/31/2021 04:26:58 - INFO - __main__ - Step 84303: {'lr': 0.00020617108955235837, 'samples': 16186176, 'steps': 84302, 'loss/train': 1.5058690309524536} 08/31/2021 04:26:59 - INFO - __main__ - Step 84304: {'lr': 0.00020616586500726651, 'samples': 16186368, 'steps': 84303, 'loss/train': 1.4621050357818604} 08/31/2021 04:26:59 - INFO - __main__ - Step 84305: {'lr': 0.00020616064048192552, 'samples': 16186560, 'steps': 84304, 'loss/train': 1.214760661125183} 08/31/2021 04:26:59 - INFO - __main__ - Step 84306: {'lr': 0.00020615541597633787, 'samples': 16186752, 'steps': 84305, 'loss/train': 1.677514672279358} 08/31/2021 04:27:00 - INFO - __main__ - Step 84307: {'lr': 0.0002061501914905059, 'samples': 16186944, 'steps': 84306, 'loss/train': 0.9925464391708374} 08/31/2021 04:27:02 - INFO - __main__ - Step 84308: {'lr': 0.00020614496702443198, 'samples': 16187136, 'steps': 84307, 'loss/train': 0.9853701591491699} 08/31/2021 04:27:03 - INFO - __main__ - Step 84309: {'lr': 0.0002061397425781185, 'samples': 16187328, 'steps': 84308, 'loss/train': 1.3528246879577637} 08/31/2021 04:27:03 - INFO - __main__ - Step 84310: {'lr': 0.00020613451815156773, 'samples': 16187520, 'steps': 84309, 'loss/train': 1.1850008964538574} 08/31/2021 04:27:03 - INFO - __main__ - Step 84311: {'lr': 0.0002061292937447821, 'samples': 16187712, 'steps': 84310, 'loss/train': 1.3084172010421753} 08/31/2021 04:27:04 - INFO - __main__ - Step 84312: {'lr': 0.0002061240693577639, 'samples': 16187904, 'steps': 84311, 'loss/train': 1.7554287910461426} 08/31/2021 04:27:04 - INFO - __main__ - Step 84313: {'lr': 0.00020611884499051553, 'samples': 16188096, 'steps': 84312, 'loss/train': 0.030902322381734848} 08/31/2021 04:27:05 - INFO - __main__ - Step 84314: {'lr': 0.00020611362064303936, 'samples': 16188288, 'steps': 84313, 'loss/train': 0.9374603033065796} 08/31/2021 04:27:06 - INFO - __main__ - Step 84315: {'lr': 0.00020610839631533768, 'samples': 16188480, 'steps': 84314, 'loss/train': 0.7065959572792053} 08/31/2021 04:27:06 - INFO - __main__ - Step 84316: {'lr': 0.0002061031720074129, 'samples': 16188672, 'steps': 84315, 'loss/train': 1.2970551252365112} 08/31/2021 04:27:07 - INFO - __main__ - Step 84317: {'lr': 0.00020609794771926746, 'samples': 16188864, 'steps': 84316, 'loss/train': 1.109289288520813} 08/31/2021 04:27:07 - INFO - __main__ - Step 84318: {'lr': 0.0002060927234509035, 'samples': 16189056, 'steps': 84317, 'loss/train': 0.6118989586830139} 08/31/2021 04:27:08 - INFO - __main__ - Step 84319: {'lr': 0.00020608749920232345, 'samples': 16189248, 'steps': 84318, 'loss/train': 0.9217641353607178} 08/31/2021 04:27:09 - INFO - __main__ - Step 84320: {'lr': 0.00020608227497352971, 'samples': 16189440, 'steps': 84319, 'loss/train': 5.584159851074219} 08/31/2021 04:27:09 - INFO - __main__ - Step 84321: {'lr': 0.00020607705076452465, 'samples': 16189632, 'steps': 84320, 'loss/train': 1.5937962532043457} 08/31/2021 04:27:10 - INFO - __main__ - Step 84322: {'lr': 0.00020607182657531056, 'samples': 16189824, 'steps': 84321, 'loss/train': 1.7430120706558228} 08/31/2021 04:27:10 - INFO - __main__ - Step 84323: {'lr': 0.00020606660240588985, 'samples': 16190016, 'steps': 84322, 'loss/train': 0.7850659489631653} 08/31/2021 04:27:12 - INFO - __main__ - Step 84324: {'lr': 0.00020606137825626483, 'samples': 16190208, 'steps': 84323, 'loss/train': 1.384621024131775} 08/31/2021 04:27:12 - INFO - __main__ - Step 84325: {'lr': 0.00020605615412643788, 'samples': 16190400, 'steps': 84324, 'loss/train': 0.7644514441490173} 08/31/2021 04:27:12 - INFO - __main__ - Step 84326: {'lr': 0.00020605093001641137, 'samples': 16190592, 'steps': 84325, 'loss/train': 1.4829233884811401} 08/31/2021 04:27:13 - INFO - __main__ - Step 84327: {'lr': 0.0002060457059261876, 'samples': 16190784, 'steps': 84326, 'loss/train': 1.2112082242965698} 08/31/2021 04:27:13 - INFO - __main__ - Step 84328: {'lr': 0.000206040481855769, 'samples': 16190976, 'steps': 84327, 'loss/train': 0.7799010872840881} 08/31/2021 04:27:14 - INFO - __main__ - Step 84329: {'lr': 0.00020603525780515784, 'samples': 16191168, 'steps': 84328, 'loss/train': 0.7352956533432007} 08/31/2021 04:27:15 - INFO - __main__ - Step 84330: {'lr': 0.00020603003377435653, 'samples': 16191360, 'steps': 84329, 'loss/train': 0.8545922636985779} 08/31/2021 04:27:15 - INFO - __main__ - Step 84331: {'lr': 0.00020602480976336752, 'samples': 16191552, 'steps': 84330, 'loss/train': 0.6474881172180176} 08/31/2021 04:27:16 - INFO - __main__ - Step 84332: {'lr': 0.00020601958577219293, 'samples': 16191744, 'steps': 84331, 'loss/train': 1.5740857124328613} 08/31/2021 04:27:16 - INFO - __main__ - Step 84333: {'lr': 0.00020601436180083525, 'samples': 16191936, 'steps': 84332, 'loss/train': 1.4819387197494507} 08/31/2021 04:27:16 - INFO - __main__ - Step 84334: {'lr': 0.0002060091378492968, 'samples': 16192128, 'steps': 84333, 'loss/train': 0.5727298855781555} 08/31/2021 04:27:18 - INFO - __main__ - Step 84335: {'lr': 0.00020600391391758, 'samples': 16192320, 'steps': 84334, 'loss/train': 1.0376453399658203} 08/31/2021 04:27:18 - INFO - __main__ - Step 84336: {'lr': 0.0002059986900056871, 'samples': 16192512, 'steps': 84335, 'loss/train': 0.09169252216815948} 08/31/2021 04:27:19 - INFO - __main__ - Step 84337: {'lr': 0.00020599346611362054, 'samples': 16192704, 'steps': 84336, 'loss/train': 1.0025240182876587} 08/31/2021 04:27:19 - INFO - __main__ - Step 84338: {'lr': 0.00020598824224138265, 'samples': 16192896, 'steps': 84337, 'loss/train': 0.8196871280670166} 08/31/2021 04:27:19 - INFO - __main__ - Step 84339: {'lr': 0.00020598301838897575, 'samples': 16193088, 'steps': 84338, 'loss/train': 1.0521352291107178} 08/31/2021 04:27:21 - INFO - __main__ - Step 84340: {'lr': 0.00020597779455640226, 'samples': 16193280, 'steps': 84339, 'loss/train': 0.936220645904541} 08/31/2021 04:27:21 - INFO - __main__ - Step 84341: {'lr': 0.0002059725707436645, 'samples': 16193472, 'steps': 84340, 'loss/train': 0.5858005285263062} 08/31/2021 04:27:22 - INFO - __main__ - Step 84342: {'lr': 0.0002059673469507648, 'samples': 16193664, 'steps': 84341, 'loss/train': 1.1761958599090576} 08/31/2021 04:27:22 - INFO - __main__ - Step 84343: {'lr': 0.00020596212317770552, 'samples': 16193856, 'steps': 84342, 'loss/train': 0.18161648511886597} 08/31/2021 04:27:22 - INFO - __main__ - Step 84344: {'lr': 0.00020595689942448913, 'samples': 16194048, 'steps': 84343, 'loss/train': 1.2871023416519165} 08/31/2021 04:27:24 - INFO - __main__ - Step 84345: {'lr': 0.0002059516756911178, 'samples': 16194240, 'steps': 84344, 'loss/train': 0.7961243391036987} 08/31/2021 04:27:24 - INFO - __main__ - Step 84346: {'lr': 0.00020594645197759398, 'samples': 16194432, 'steps': 84345, 'loss/train': 0.6898558139801025} 08/31/2021 04:27:25 - INFO - __main__ - Step 84347: {'lr': 0.00020594122828392, 'samples': 16194624, 'steps': 84346, 'loss/train': 1.3583941459655762} 08/31/2021 04:27:25 - INFO - __main__ - Step 84348: {'lr': 0.0002059360046100982, 'samples': 16194816, 'steps': 84347, 'loss/train': 0.5009068250656128} 08/31/2021 04:27:25 - INFO - __main__ - Step 84349: {'lr': 0.00020593078095613096, 'samples': 16195008, 'steps': 84348, 'loss/train': 1.546010971069336} 08/31/2021 04:27:27 - INFO - __main__ - Step 84350: {'lr': 0.00020592555732202062, 'samples': 16195200, 'steps': 84349, 'loss/train': 0.8409929871559143} 08/31/2021 04:27:28 - INFO - __main__ - Step 84351: {'lr': 0.00020592033370776957, 'samples': 16195392, 'steps': 84350, 'loss/train': 1.3567835092544556} 08/31/2021 04:27:28 - INFO - __main__ - Step 84352: {'lr': 0.00020591511011338012, 'samples': 16195584, 'steps': 84351, 'loss/train': 1.4582358598709106} 08/31/2021 04:27:28 - INFO - __main__ - Step 84353: {'lr': 0.00020590988653885467, 'samples': 16195776, 'steps': 84352, 'loss/train': 0.7370646595954895} 08/31/2021 04:27:29 - INFO - __main__ - Step 84354: {'lr': 0.0002059046629841955, 'samples': 16195968, 'steps': 84353, 'loss/train': 1.6412080526351929} 08/31/2021 04:27:30 - INFO - __main__ - Step 84355: {'lr': 0.00020589943944940504, 'samples': 16196160, 'steps': 84354, 'loss/train': 1.727636694908142} 08/31/2021 04:27:31 - INFO - __main__ - Step 84356: {'lr': 0.00020589421593448568, 'samples': 16196352, 'steps': 84355, 'loss/train': 1.3131325244903564} 08/31/2021 04:27:31 - INFO - __main__ - Step 84357: {'lr': 0.00020588899243943967, 'samples': 16196544, 'steps': 84356, 'loss/train': 1.23484206199646} 08/31/2021 04:27:32 - INFO - __main__ - Step 84358: {'lr': 0.00020588376896426937, 'samples': 16196736, 'steps': 84357, 'loss/train': 1.5452618598937988} 08/31/2021 04:27:32 - INFO - __main__ - Step 84359: {'lr': 0.00020587854550897715, 'samples': 16196928, 'steps': 84358, 'loss/train': 0.16699562966823578} 08/31/2021 04:27:33 - INFO - __main__ - Step 84360: {'lr': 0.00020587332207356538, 'samples': 16197120, 'steps': 84359, 'loss/train': 1.1142562627792358} 08/31/2021 04:27:34 - INFO - __main__ - Step 84361: {'lr': 0.0002058680986580364, 'samples': 16197312, 'steps': 84360, 'loss/train': 1.687637448310852} 08/31/2021 04:27:34 - INFO - __main__ - Step 84362: {'lr': 0.00020586287526239258, 'samples': 16197504, 'steps': 84361, 'loss/train': 1.2753798961639404} 08/31/2021 04:27:35 - INFO - __main__ - Step 84363: {'lr': 0.00020585765188663627, 'samples': 16197696, 'steps': 84362, 'loss/train': 1.4976017475128174} 08/31/2021 04:27:35 - INFO - __main__ - Step 84364: {'lr': 0.00020585242853076984, 'samples': 16197888, 'steps': 84363, 'loss/train': 0.88899827003479} 08/31/2021 04:27:37 - INFO - __main__ - Step 84365: {'lr': 0.0002058472051947956, 'samples': 16198080, 'steps': 84364, 'loss/train': 1.099798560142517} 08/31/2021 04:27:38 - INFO - __main__ - Step 84366: {'lr': 0.00020584198187871596, 'samples': 16198272, 'steps': 84365, 'loss/train': 0.42123943567276} 08/31/2021 04:27:38 - INFO - __main__ - Step 84367: {'lr': 0.00020583675858253325, 'samples': 16198464, 'steps': 84366, 'loss/train': 1.2182456254959106} 08/31/2021 04:27:38 - INFO - __main__ - Step 84368: {'lr': 0.00020583153530624975, 'samples': 16198656, 'steps': 84367, 'loss/train': 1.3788502216339111} 08/31/2021 04:27:39 - INFO - __main__ - Step 84369: {'lr': 0.00020582631204986792, 'samples': 16198848, 'steps': 84368, 'loss/train': 1.132706642150879} 08/31/2021 04:27:39 - INFO - __main__ - Step 84370: {'lr': 0.00020582108881339007, 'samples': 16199040, 'steps': 84369, 'loss/train': 0.16735662519931793} 08/31/2021 04:27:41 - INFO - __main__ - Step 84371: {'lr': 0.0002058158655968186, 'samples': 16199232, 'steps': 84370, 'loss/train': 1.4950376749038696} 08/31/2021 04:27:41 - INFO - __main__ - Step 84372: {'lr': 0.00020581064240015576, 'samples': 16199424, 'steps': 84371, 'loss/train': 0.6952535510063171} 08/31/2021 04:27:42 - INFO - __main__ - Step 84373: {'lr': 0.000205805419223404, 'samples': 16199616, 'steps': 84372, 'loss/train': 1.8825095891952515} 08/31/2021 04:27:42 - INFO - __main__ - Step 84374: {'lr': 0.00020580019606656559, 'samples': 16199808, 'steps': 84373, 'loss/train': 1.2020652294158936} 08/31/2021 04:27:42 - INFO - __main__ - Step 84375: {'lr': 0.00020579497292964294, 'samples': 16200000, 'steps': 84374, 'loss/train': 5.729276180267334} 08/31/2021 04:27:44 - INFO - __main__ - Step 84376: {'lr': 0.0002057897498126384, 'samples': 16200192, 'steps': 84375, 'loss/train': 1.6704639196395874} 08/31/2021 04:27:44 - INFO - __main__ - Step 84377: {'lr': 0.00020578452671555432, 'samples': 16200384, 'steps': 84376, 'loss/train': 1.45100736618042} 08/31/2021 04:27:45 - INFO - __main__ - Step 84378: {'lr': 0.00020577930363839308, 'samples': 16200576, 'steps': 84377, 'loss/train': 0.6573840379714966} 08/31/2021 04:27:45 - INFO - __main__ - Step 84379: {'lr': 0.000205774080581157, 'samples': 16200768, 'steps': 84378, 'loss/train': 0.5833319425582886} 08/31/2021 04:27:45 - INFO - __main__ - Step 84380: {'lr': 0.00020576885754384838, 'samples': 16200960, 'steps': 84379, 'loss/train': 1.2573494911193848} 08/31/2021 04:27:46 - INFO - __main__ - Step 84381: {'lr': 0.00020576363452646964, 'samples': 16201152, 'steps': 84380, 'loss/train': 1.5944451093673706} 08/31/2021 04:27:47 - INFO - __main__ - Step 84382: {'lr': 0.00020575841152902313, 'samples': 16201344, 'steps': 84381, 'loss/train': 1.7943931818008423} 08/31/2021 04:27:48 - INFO - __main__ - Step 84383: {'lr': 0.00020575318855151124, 'samples': 16201536, 'steps': 84382, 'loss/train': 1.3111144304275513} 08/31/2021 04:27:48 - INFO - __main__ - Step 84384: {'lr': 0.0002057479655939363, 'samples': 16201728, 'steps': 84383, 'loss/train': 1.3379908800125122} 08/31/2021 04:27:48 - INFO - __main__ - Step 84385: {'lr': 0.00020574274265630057, 'samples': 16201920, 'steps': 84384, 'loss/train': 1.4506269693374634} 08/31/2021 04:27:49 - INFO - __main__ - Step 84386: {'lr': 0.00020573751973860648, 'samples': 16202112, 'steps': 84385, 'loss/train': 1.4684185981750488} 08/31/2021 04:27:50 - INFO - __main__ - Step 84387: {'lr': 0.00020573229684085642, 'samples': 16202304, 'steps': 84386, 'loss/train': 0.8366422653198242} 08/31/2021 04:27:51 - INFO - __main__ - Step 84388: {'lr': 0.00020572707396305267, 'samples': 16202496, 'steps': 84387, 'loss/train': 1.6062941551208496} 08/31/2021 04:27:51 - INFO - __main__ - Step 84389: {'lr': 0.0002057218511051977, 'samples': 16202688, 'steps': 84388, 'loss/train': 1.7780227661132812} 08/31/2021 04:27:51 - INFO - __main__ - Step 84390: {'lr': 0.0002057166282672937, 'samples': 16202880, 'steps': 84389, 'loss/train': 1.1812937259674072} 08/31/2021 04:27:52 - INFO - __main__ - Step 84391: {'lr': 0.00020571140544934315, 'samples': 16203072, 'steps': 84390, 'loss/train': 0.8644008636474609} 08/31/2021 04:27:53 - INFO - __main__ - Step 84392: {'lr': 0.0002057061826513483, 'samples': 16203264, 'steps': 84391, 'loss/train': 1.4972853660583496} 08/31/2021 04:27:54 - INFO - __main__ - Step 84393: {'lr': 0.00020570095987331154, 'samples': 16203456, 'steps': 84392, 'loss/train': 0.8819939494132996} 08/31/2021 04:27:54 - INFO - __main__ - Step 84394: {'lr': 0.00020569573711523532, 'samples': 16203648, 'steps': 84393, 'loss/train': 1.860200047492981} 08/31/2021 04:27:54 - INFO - __main__ - Step 84395: {'lr': 0.0002056905143771219, 'samples': 16203840, 'steps': 84394, 'loss/train': 0.8288773894309998} 08/31/2021 04:27:55 - INFO - __main__ - Step 84396: {'lr': 0.0002056852916589736, 'samples': 16204032, 'steps': 84395, 'loss/train': 1.4676449298858643} 08/31/2021 04:27:56 - INFO - __main__ - Step 84397: {'lr': 0.00020568006896079286, 'samples': 16204224, 'steps': 84396, 'loss/train': 1.5193508863449097} 08/31/2021 04:27:57 - INFO - __main__ - Step 84398: {'lr': 0.00020567484628258203, 'samples': 16204416, 'steps': 84397, 'loss/train': 1.4710506200790405} 08/31/2021 04:27:57 - INFO - __main__ - Step 84399: {'lr': 0.00020566962362434342, 'samples': 16204608, 'steps': 84398, 'loss/train': 1.216556429862976} 08/31/2021 04:27:57 - INFO - __main__ - Step 84400: {'lr': 0.00020566440098607943, 'samples': 16204800, 'steps': 84399, 'loss/train': 1.3387107849121094} 08/31/2021 04:27:58 - INFO - __main__ - Step 84401: {'lr': 0.0002056591783677923, 'samples': 16204992, 'steps': 84400, 'loss/train': 1.307749629020691} 08/31/2021 04:27:59 - INFO - __main__ - Step 84402: {'lr': 0.00020565395576948448, 'samples': 16205184, 'steps': 84401, 'loss/train': 0.979790985584259} 08/31/2021 04:28:00 - INFO - __main__ - Step 84403: {'lr': 0.0002056487331911583, 'samples': 16205376, 'steps': 84402, 'loss/train': 1.178367257118225} 08/31/2021 04:28:00 - INFO - __main__ - Step 84404: {'lr': 0.00020564351063281612, 'samples': 16205568, 'steps': 84403, 'loss/train': 0.9696745276451111} 08/31/2021 04:28:00 - INFO - __main__ - Step 84405: {'lr': 0.00020563828809446027, 'samples': 16205760, 'steps': 84404, 'loss/train': 1.357594609260559} 08/31/2021 04:28:01 - INFO - __main__ - Step 84406: {'lr': 0.00020563306557609313, 'samples': 16205952, 'steps': 84405, 'loss/train': 0.915936291217804} 08/31/2021 04:28:02 - INFO - __main__ - Step 84407: {'lr': 0.00020562784307771707, 'samples': 16206144, 'steps': 84406, 'loss/train': 1.4472442865371704} 08/31/2021 04:28:03 - INFO - __main__ - Step 84408: {'lr': 0.0002056226205993344, 'samples': 16206336, 'steps': 84407, 'loss/train': 1.6669942140579224} 08/31/2021 04:28:03 - INFO - __main__ - Step 84409: {'lr': 0.0002056173981409475, 'samples': 16206528, 'steps': 84408, 'loss/train': 1.1204420328140259} 08/31/2021 04:28:03 - INFO - __main__ - Step 84410: {'lr': 0.00020561217570255869, 'samples': 16206720, 'steps': 84409, 'loss/train': 0.970011830329895} 08/31/2021 04:28:04 - INFO - __main__ - Step 84411: {'lr': 0.00020560695328417048, 'samples': 16206912, 'steps': 84410, 'loss/train': 1.1983660459518433} 08/31/2021 04:28:04 - INFO - __main__ - Step 84412: {'lr': 0.000205601730885785, 'samples': 16207104, 'steps': 84411, 'loss/train': 0.9145699739456177} 08/31/2021 04:28:06 - INFO - __main__ - Step 84413: {'lr': 0.00020559650850740467, 'samples': 16207296, 'steps': 84412, 'loss/train': 1.1202954053878784} 08/31/2021 04:28:07 - INFO - __main__ - Step 84414: {'lr': 0.00020559128614903186, 'samples': 16207488, 'steps': 84413, 'loss/train': 0.5495821237564087} 08/31/2021 04:28:07 - INFO - __main__ - Step 84415: {'lr': 0.00020558606381066897, 'samples': 16207680, 'steps': 84414, 'loss/train': 1.2172642946243286} 08/31/2021 04:28:08 - INFO - __main__ - Step 84416: {'lr': 0.00020558084149231826, 'samples': 16207872, 'steps': 84415, 'loss/train': 0.2965998351573944} 08/31/2021 04:28:08 - INFO - __main__ - Step 84417: {'lr': 0.0002055756191939822, 'samples': 16208064, 'steps': 84416, 'loss/train': 1.4331881999969482} 08/31/2021 04:28:10 - INFO - __main__ - Step 84418: {'lr': 0.00020557039691566301, 'samples': 16208256, 'steps': 84417, 'loss/train': 1.4621374607086182} 08/31/2021 04:28:10 - INFO - __main__ - Step 84419: {'lr': 0.00020556517465736314, 'samples': 16208448, 'steps': 84418, 'loss/train': 0.9131744503974915} 08/31/2021 04:28:10 - INFO - __main__ - Step 84420: {'lr': 0.00020555995241908497, 'samples': 16208640, 'steps': 84419, 'loss/train': 0.6125689148902893} 08/31/2021 04:28:11 - INFO - __main__ - Step 84421: {'lr': 0.00020555473020083073, 'samples': 16208832, 'steps': 84420, 'loss/train': 1.386609435081482} 08/31/2021 04:28:11 - INFO - __main__ - Step 84422: {'lr': 0.00020554950800260287, 'samples': 16209024, 'steps': 84421, 'loss/train': 1.119667410850525} 08/31/2021 04:28:13 - INFO - __main__ - Step 84423: {'lr': 0.00020554428582440372, 'samples': 16209216, 'steps': 84422, 'loss/train': 0.0760989785194397} 08/31/2021 04:28:13 - INFO - __main__ - Step 84424: {'lr': 0.0002055390636662356, 'samples': 16209408, 'steps': 84423, 'loss/train': 1.252130150794983} 08/31/2021 04:28:14 - INFO - __main__ - Step 84425: {'lr': 0.00020553384152810107, 'samples': 16209600, 'steps': 84424, 'loss/train': 1.284835696220398} 08/31/2021 04:28:14 - INFO - __main__ - Step 84426: {'lr': 0.00020552861941000212, 'samples': 16209792, 'steps': 84425, 'loss/train': 1.6796237230300903} 08/31/2021 04:28:14 - INFO - __main__ - Step 84427: {'lr': 0.0002055233973119413, 'samples': 16209984, 'steps': 84426, 'loss/train': 0.04822145402431488} 08/31/2021 04:28:16 - INFO - __main__ - Step 84428: {'lr': 0.000205518175233921, 'samples': 16210176, 'steps': 84427, 'loss/train': 1.6868195533752441} 08/31/2021 04:28:17 - INFO - __main__ - Step 84429: {'lr': 0.00020551295317594348, 'samples': 16210368, 'steps': 84428, 'loss/train': 0.6080952882766724} 08/31/2021 04:28:17 - INFO - __main__ - Step 84430: {'lr': 0.00020550773113801117, 'samples': 16210560, 'steps': 84429, 'loss/train': 0.05972965806722641} 08/31/2021 04:28:17 - INFO - __main__ - Step 84431: {'lr': 0.00020550250912012636, 'samples': 16210752, 'steps': 84430, 'loss/train': 0.16363351047039032} 08/31/2021 04:28:18 - INFO - __main__ - Step 84432: {'lr': 0.00020549728712229142, 'samples': 16210944, 'steps': 84431, 'loss/train': 0.08040980249643326} 08/31/2021 04:28:18 - INFO - __main__ - Step 84433: {'lr': 0.00020549206514450876, 'samples': 16211136, 'steps': 84432, 'loss/train': 0.9521697759628296} 08/31/2021 04:28:18 - INFO - __main__ - Step 84434: {'lr': 0.00020548684318678065, 'samples': 16211328, 'steps': 84433, 'loss/train': 1.252769112586975} 08/31/2021 04:28:20 - INFO - __main__ - Step 84435: {'lr': 0.0002054816212491095, 'samples': 16211520, 'steps': 84434, 'loss/train': 1.5565261840820312} 08/31/2021 04:28:20 - INFO - __main__ - Step 84436: {'lr': 0.00020547639933149765, 'samples': 16211712, 'steps': 84435, 'loss/train': 2.200313091278076} 08/31/2021 04:28:21 - INFO - __main__ - Step 84437: {'lr': 0.00020547117743394743, 'samples': 16211904, 'steps': 84436, 'loss/train': 1.3958439826965332} 08/31/2021 04:28:21 - INFO - __main__ - Step 84438: {'lr': 0.00020546595555646135, 'samples': 16212096, 'steps': 84437, 'loss/train': 1.457295298576355} 08/31/2021 04:28:21 - INFO - __main__ - Step 84439: {'lr': 0.0002054607336990415, 'samples': 16212288, 'steps': 84438, 'loss/train': 1.2092608213424683} 08/31/2021 04:28:24 - INFO - __main__ - Step 84440: {'lr': 0.00020545551186169035, 'samples': 16212480, 'steps': 84439, 'loss/train': 1.1730986833572388} 08/31/2021 04:28:24 - INFO - __main__ - Step 84441: {'lr': 0.00020545029004441024, 'samples': 16212672, 'steps': 84440, 'loss/train': 0.5717772841453552} 08/31/2021 04:28:24 - INFO - __main__ - Step 84442: {'lr': 0.00020544506824720355, 'samples': 16212864, 'steps': 84441, 'loss/train': 0.45837894082069397} 08/31/2021 04:28:25 - INFO - __main__ - Step 84443: {'lr': 0.00020543984647007263, 'samples': 16213056, 'steps': 84442, 'loss/train': 1.3992570638656616} 08/31/2021 04:28:25 - INFO - __main__ - Step 84444: {'lr': 0.00020543462471301987, 'samples': 16213248, 'steps': 84443, 'loss/train': 1.8282848596572876} 08/31/2021 04:28:25 - INFO - __main__ - Step 84445: {'lr': 0.00020542940297604752, 'samples': 16213440, 'steps': 84444, 'loss/train': 1.260511040687561} 08/31/2021 04:28:27 - INFO - __main__ - Step 84446: {'lr': 0.00020542418125915802, 'samples': 16213632, 'steps': 84445, 'loss/train': 1.2172300815582275} 08/31/2021 04:28:28 - INFO - __main__ - Step 84447: {'lr': 0.0002054189595623537, 'samples': 16213824, 'steps': 84446, 'loss/train': 1.189969778060913} 08/31/2021 04:28:28 - INFO - __main__ - Step 84448: {'lr': 0.0002054137378856369, 'samples': 16214016, 'steps': 84447, 'loss/train': 1.7834511995315552} 08/31/2021 04:28:29 - INFO - __main__ - Step 84449: {'lr': 0.00020540851622900997, 'samples': 16214208, 'steps': 84448, 'loss/train': 1.8596023321151733} 08/31/2021 04:28:29 - INFO - __main__ - Step 84450: {'lr': 0.0002054032945924753, 'samples': 16214400, 'steps': 84449, 'loss/train': 1.095099925994873} 08/31/2021 04:28:29 - INFO - __main__ - Step 84451: {'lr': 0.00020539807297603518, 'samples': 16214592, 'steps': 84450, 'loss/train': 0.04794361814856529} 08/31/2021 04:28:31 - INFO - __main__ - Step 84452: {'lr': 0.00020539285137969216, 'samples': 16214784, 'steps': 84451, 'loss/train': 2.072206735610962} 08/31/2021 04:28:31 - INFO - __main__ - Step 84453: {'lr': 0.0002053876298034483, 'samples': 16214976, 'steps': 84452, 'loss/train': 0.9681753516197205} 08/31/2021 04:28:31 - INFO - __main__ - Step 84454: {'lr': 0.0002053824082473061, 'samples': 16215168, 'steps': 84453, 'loss/train': 0.7006139159202576} 08/31/2021 04:28:32 - INFO - __main__ - Step 84455: {'lr': 0.00020537718671126786, 'samples': 16215360, 'steps': 84454, 'loss/train': 1.2904150485992432} 08/31/2021 04:28:32 - INFO - __main__ - Step 84456: {'lr': 0.000205371965195336, 'samples': 16215552, 'steps': 84455, 'loss/train': 1.358020544052124} 08/31/2021 04:28:34 - INFO - __main__ - Step 84457: {'lr': 0.00020536674369951282, 'samples': 16215744, 'steps': 84456, 'loss/train': 0.464703232049942} 08/31/2021 04:28:34 - INFO - __main__ - Step 84458: {'lr': 0.00020536152222380073, 'samples': 16215936, 'steps': 84457, 'loss/train': 0.7107825875282288} 08/31/2021 04:28:34 - INFO - __main__ - Step 84459: {'lr': 0.00020535630076820203, 'samples': 16216128, 'steps': 84458, 'loss/train': 0.6118854284286499} 08/31/2021 04:28:35 - INFO - __main__ - Step 84460: {'lr': 0.0002053510793327191, 'samples': 16216320, 'steps': 84459, 'loss/train': 1.5289710760116577} 08/31/2021 04:28:35 - INFO - __main__ - Step 84461: {'lr': 0.00020534585791735427, 'samples': 16216512, 'steps': 84460, 'loss/train': 1.1409207582473755} 08/31/2021 04:28:37 - INFO - __main__ - Step 84462: {'lr': 0.0002053406365221099, 'samples': 16216704, 'steps': 84461, 'loss/train': 1.3630852699279785} 08/31/2021 04:28:37 - INFO - __main__ - Step 84463: {'lr': 0.00020533541514698839, 'samples': 16216896, 'steps': 84462, 'loss/train': 1.0812623500823975} 08/31/2021 04:28:38 - INFO - __main__ - Step 84464: {'lr': 0.00020533019379199202, 'samples': 16217088, 'steps': 84463, 'loss/train': 1.3958433866500854} 08/31/2021 04:28:38 - INFO - __main__ - Step 84465: {'lr': 0.0002053249724571233, 'samples': 16217280, 'steps': 84464, 'loss/train': 1.5571179389953613} 08/31/2021 04:28:38 - INFO - __main__ - Step 84466: {'lr': 0.00020531975114238433, 'samples': 16217472, 'steps': 84465, 'loss/train': 1.735029697418213} 08/31/2021 04:28:40 - INFO - __main__ - Step 84467: {'lr': 0.0002053145298477776, 'samples': 16217664, 'steps': 84466, 'loss/train': 1.056477665901184} 08/31/2021 04:28:41 - INFO - __main__ - Step 84468: {'lr': 0.00020530930857330548, 'samples': 16217856, 'steps': 84467, 'loss/train': 1.3703796863555908} 08/31/2021 04:28:41 - INFO - __main__ - Step 84469: {'lr': 0.00020530408731897026, 'samples': 16218048, 'steps': 84468, 'loss/train': 2.1276092529296875} 08/31/2021 04:28:41 - INFO - __main__ - Step 84470: {'lr': 0.00020529886608477434, 'samples': 16218240, 'steps': 84469, 'loss/train': 1.226240634918213} 08/31/2021 04:28:42 - INFO - __main__ - Step 84471: {'lr': 0.00020529364487072006, 'samples': 16218432, 'steps': 84470, 'loss/train': 1.5659857988357544} 08/31/2021 04:28:42 - INFO - __main__ - Step 84472: {'lr': 0.00020528842367680978, 'samples': 16218624, 'steps': 84471, 'loss/train': 1.153452754020691} 08/31/2021 04:28:44 - INFO - __main__ - Step 84473: {'lr': 0.00020528320250304586, 'samples': 16218816, 'steps': 84472, 'loss/train': 0.9060950875282288} 08/31/2021 04:28:44 - INFO - __main__ - Step 84474: {'lr': 0.0002052779813494306, 'samples': 16219008, 'steps': 84473, 'loss/train': 1.0569074153900146} 08/31/2021 04:28:45 - INFO - __main__ - Step 84475: {'lr': 0.00020527276021596643, 'samples': 16219200, 'steps': 84474, 'loss/train': 1.2913968563079834} 08/31/2021 04:28:45 - INFO - __main__ - Step 84476: {'lr': 0.00020526753910265564, 'samples': 16219392, 'steps': 84475, 'loss/train': 1.4987399578094482} 08/31/2021 04:28:45 - INFO - __main__ - Step 84477: {'lr': 0.00020526231800950062, 'samples': 16219584, 'steps': 84476, 'loss/train': 1.927097201347351} 08/31/2021 04:28:46 - INFO - __main__ - Step 84478: {'lr': 0.0002052570969365038, 'samples': 16219776, 'steps': 84477, 'loss/train': 0.03736957162618637} 08/31/2021 04:28:47 - INFO - __main__ - Step 84479: {'lr': 0.00020525187588366734, 'samples': 16219968, 'steps': 84478, 'loss/train': 1.2065554857254028} 08/31/2021 04:28:48 - INFO - __main__ - Step 84480: {'lr': 0.0002052466548509937, 'samples': 16220160, 'steps': 84479, 'loss/train': 1.0320839881896973} 08/31/2021 04:28:48 - INFO - __main__ - Step 84481: {'lr': 0.00020524143383848523, 'samples': 16220352, 'steps': 84480, 'loss/train': 1.7503377199172974} 08/31/2021 04:28:48 - INFO - __main__ - Step 84482: {'lr': 0.00020523621284614427, 'samples': 16220544, 'steps': 84481, 'loss/train': 0.7695490717887878} 08/31/2021 04:28:49 - INFO - __main__ - Step 84483: {'lr': 0.0002052309918739732, 'samples': 16220736, 'steps': 84482, 'loss/train': 1.608711838722229} 08/31/2021 04:28:50 - INFO - __main__ - Step 84484: {'lr': 0.00020522577092197433, 'samples': 16220928, 'steps': 84483, 'loss/train': 1.5570495128631592} 08/31/2021 04:28:51 - INFO - __main__ - Step 84485: {'lr': 0.00020522054999015004, 'samples': 16221120, 'steps': 84484, 'loss/train': 0.7030011415481567} 08/31/2021 04:28:51 - INFO - __main__ - Step 84486: {'lr': 0.00020521532907850272, 'samples': 16221312, 'steps': 84485, 'loss/train': 1.5693938732147217} 08/31/2021 04:28:51 - INFO - __main__ - Step 84487: {'lr': 0.00020521010818703463, 'samples': 16221504, 'steps': 84486, 'loss/train': 1.238739013671875} 08/31/2021 04:28:52 - INFO - __main__ - Step 84488: {'lr': 0.00020520488731574818, 'samples': 16221696, 'steps': 84487, 'loss/train': 1.6360864639282227} 08/31/2021 04:28:53 - INFO - __main__ - Step 84489: {'lr': 0.00020519966646464574, 'samples': 16221888, 'steps': 84488, 'loss/train': 1.804375171661377} 08/31/2021 04:28:54 - INFO - __main__ - Step 84490: {'lr': 0.00020519444563372964, 'samples': 16222080, 'steps': 84489, 'loss/train': 0.9589853882789612} 08/31/2021 04:28:54 - INFO - __main__ - Step 84491: {'lr': 0.00020518922482300225, 'samples': 16222272, 'steps': 84490, 'loss/train': 1.5270540714263916} 08/31/2021 04:28:54 - INFO - __main__ - Step 84492: {'lr': 0.00020518400403246595, 'samples': 16222464, 'steps': 84491, 'loss/train': 0.6027384400367737} 08/31/2021 04:28:55 - INFO - __main__ - Step 84493: {'lr': 0.00020517878326212297, 'samples': 16222656, 'steps': 84492, 'loss/train': 0.9233735799789429} 08/31/2021 04:28:56 - INFO - __main__ - Step 84494: {'lr': 0.00020517356251197573, 'samples': 16222848, 'steps': 84493, 'loss/train': 1.509850263595581} 08/31/2021 04:28:57 - INFO - __main__ - Step 84495: {'lr': 0.0002051683417820266, 'samples': 16223040, 'steps': 84494, 'loss/train': 0.8924422264099121} 08/31/2021 04:28:57 - INFO - __main__ - Step 84496: {'lr': 0.00020516312107227792, 'samples': 16223232, 'steps': 84495, 'loss/train': 1.3906505107879639} 08/31/2021 04:28:57 - INFO - __main__ - Step 84497: {'lr': 0.00020515790038273205, 'samples': 16223424, 'steps': 84496, 'loss/train': 1.367546796798706} 08/31/2021 04:28:58 - INFO - __main__ - Step 84498: {'lr': 0.00020515267971339132, 'samples': 16223616, 'steps': 84497, 'loss/train': 1.4125064611434937} 08/31/2021 04:28:58 - INFO - __main__ - Step 84499: {'lr': 0.00020514745906425813, 'samples': 16223808, 'steps': 84498, 'loss/train': 1.3092293739318848} 08/31/2021 04:28:59 - INFO - __main__ - Step 84500: {'lr': 0.0002051422384353348, 'samples': 16224000, 'steps': 84499, 'loss/train': 1.7120646238327026} 08/31/2021 04:29:00 - INFO - __main__ - Step 84501: {'lr': 0.00020513701782662368, 'samples': 16224192, 'steps': 84500, 'loss/train': 0.5861998796463013} 08/31/2021 04:29:00 - INFO - __main__ - Step 84502: {'lr': 0.00020513179723812716, 'samples': 16224384, 'steps': 84501, 'loss/train': 1.5040565729141235} 08/31/2021 04:29:01 - INFO - __main__ - Step 84503: {'lr': 0.0002051265766698475, 'samples': 16224576, 'steps': 84502, 'loss/train': 0.9437225461006165} 08/31/2021 04:29:01 - INFO - __main__ - Step 84504: {'lr': 0.00020512135612178717, 'samples': 16224768, 'steps': 84503, 'loss/train': 0.6206661462783813} 08/31/2021 04:29:03 - INFO - __main__ - Step 84505: {'lr': 0.00020511613559394848, 'samples': 16224960, 'steps': 84504, 'loss/train': 0.8007174730300903} 08/31/2021 04:29:04 - INFO - __main__ - Step 84506: {'lr': 0.0002051109150863337, 'samples': 16225152, 'steps': 84505, 'loss/train': 0.44545572996139526} 08/31/2021 04:29:04 - INFO - __main__ - Step 84507: {'lr': 0.00020510569459894525, 'samples': 16225344, 'steps': 84506, 'loss/train': 1.157081961631775} 08/31/2021 04:29:04 - INFO - __main__ - Step 84508: {'lr': 0.0002051004741317855, 'samples': 16225536, 'steps': 84507, 'loss/train': 1.4071401357650757} 08/31/2021 04:29:05 - INFO - __main__ - Step 84509: {'lr': 0.00020509525368485679, 'samples': 16225728, 'steps': 84508, 'loss/train': 1.7117501497268677} 08/31/2021 04:29:05 - INFO - __main__ - Step 84510: {'lr': 0.00020509003325816145, 'samples': 16225920, 'steps': 84509, 'loss/train': 1.6413789987564087} 08/31/2021 04:29:06 - INFO - __main__ - Step 84511: {'lr': 0.00020508481285170185, 'samples': 16226112, 'steps': 84510, 'loss/train': 1.39054274559021} 08/31/2021 04:29:07 - INFO - __main__ - Step 84512: {'lr': 0.00020507959246548042, 'samples': 16226304, 'steps': 84511, 'loss/train': 1.663975477218628} 08/31/2021 04:29:07 - INFO - __main__ - Step 84513: {'lr': 0.00020507437209949937, 'samples': 16226496, 'steps': 84512, 'loss/train': 1.1737366914749146} 08/31/2021 04:29:08 - INFO - __main__ - Step 84514: {'lr': 0.00020506915175376106, 'samples': 16226688, 'steps': 84513, 'loss/train': 1.3260493278503418} 08/31/2021 04:29:08 - INFO - __main__ - Step 84515: {'lr': 0.00020506393142826797, 'samples': 16226880, 'steps': 84514, 'loss/train': 0.8905900120735168} 08/31/2021 04:29:08 - INFO - __main__ - Step 84516: {'lr': 0.00020505871112302233, 'samples': 16227072, 'steps': 84515, 'loss/train': 1.445493221282959} 08/31/2021 04:29:10 - INFO - __main__ - Step 84517: {'lr': 0.00020505349083802654, 'samples': 16227264, 'steps': 84516, 'loss/train': 0.9091760516166687} 08/31/2021 04:29:10 - INFO - __main__ - Step 84518: {'lr': 0.00020504827057328298, 'samples': 16227456, 'steps': 84517, 'loss/train': 0.3723870813846588} 08/31/2021 04:29:11 - INFO - __main__ - Step 84519: {'lr': 0.00020504305032879402, 'samples': 16227648, 'steps': 84518, 'loss/train': 0.2384290099143982} 08/31/2021 04:29:11 - INFO - __main__ - Step 84520: {'lr': 0.00020503783010456192, 'samples': 16227840, 'steps': 84519, 'loss/train': 1.2026848793029785} 08/31/2021 04:29:11 - INFO - __main__ - Step 84521: {'lr': 0.00020503260990058908, 'samples': 16228032, 'steps': 84520, 'loss/train': 1.7040966749191284} 08/31/2021 04:29:13 - INFO - __main__ - Step 84522: {'lr': 0.00020502738971687784, 'samples': 16228224, 'steps': 84521, 'loss/train': 1.0166758298873901} 08/31/2021 04:29:13 - INFO - __main__ - Step 84523: {'lr': 0.0002050221695534306, 'samples': 16228416, 'steps': 84522, 'loss/train': 1.4160692691802979} 08/31/2021 04:29:14 - INFO - __main__ - Step 84524: {'lr': 0.00020501694941024967, 'samples': 16228608, 'steps': 84523, 'loss/train': 1.1817809343338013} 08/31/2021 04:29:14 - INFO - __main__ - Step 84525: {'lr': 0.0002050117292873374, 'samples': 16228800, 'steps': 84524, 'loss/train': 1.4806221723556519} 08/31/2021 04:29:14 - INFO - __main__ - Step 84526: {'lr': 0.00020500650918469612, 'samples': 16228992, 'steps': 84525, 'loss/train': 1.68168044090271} 08/31/2021 04:29:17 - INFO - __main__ - Step 84527: {'lr': 0.00020500128910232824, 'samples': 16229184, 'steps': 84526, 'loss/train': 1.3982001543045044} 08/31/2021 04:29:17 - INFO - __main__ - Step 84528: {'lr': 0.00020499606904023608, 'samples': 16229376, 'steps': 84527, 'loss/train': 1.0345463752746582} 08/31/2021 04:29:17 - INFO - __main__ - Step 84529: {'lr': 0.000204990848998422, 'samples': 16229568, 'steps': 84528, 'loss/train': 0.6218650937080383} 08/31/2021 04:29:18 - INFO - __main__ - Step 84530: {'lr': 0.00020498562897688832, 'samples': 16229760, 'steps': 84529, 'loss/train': 1.974472999572754} 08/31/2021 04:29:18 - INFO - __main__ - Step 84531: {'lr': 0.00020498040897563743, 'samples': 16229952, 'steps': 84530, 'loss/train': 1.35662841796875} 08/31/2021 04:29:20 - INFO - __main__ - Step 84532: {'lr': 0.00020497518899467173, 'samples': 16230144, 'steps': 84531, 'loss/train': 0.7778935432434082} 08/31/2021 04:29:21 - INFO - __main__ - Step 84533: {'lr': 0.00020496996903399348, 'samples': 16230336, 'steps': 84532, 'loss/train': 1.414777398109436} 08/31/2021 04:29:21 - INFO - __main__ - Step 84534: {'lr': 0.00020496474909360512, 'samples': 16230528, 'steps': 84533, 'loss/train': 1.332396388053894} 08/31/2021 04:29:21 - INFO - __main__ - Step 84535: {'lr': 0.00020495952917350889, 'samples': 16230720, 'steps': 84534, 'loss/train': 1.4694266319274902} 08/31/2021 04:29:22 - INFO - __main__ - Step 84536: {'lr': 0.00020495430927370718, 'samples': 16230912, 'steps': 84535, 'loss/train': 1.4335671663284302} 08/31/2021 04:29:22 - INFO - __main__ - Step 84537: {'lr': 0.00020494908939420236, 'samples': 16231104, 'steps': 84536, 'loss/train': 2.1920080184936523} 08/31/2021 04:29:23 - INFO - __main__ - Step 84538: {'lr': 0.00020494386953499684, 'samples': 16231296, 'steps': 84537, 'loss/train': 0.11342644691467285} 08/31/2021 04:29:24 - INFO - __main__ - Step 84539: {'lr': 0.00020493864969609287, 'samples': 16231488, 'steps': 84538, 'loss/train': 1.436125636100769} 08/31/2021 04:29:24 - INFO - __main__ - Step 84540: {'lr': 0.00020493342987749287, 'samples': 16231680, 'steps': 84539, 'loss/train': 1.3481426239013672} 08/31/2021 04:29:25 - INFO - __main__ - Step 84541: {'lr': 0.00020492821007919915, 'samples': 16231872, 'steps': 84540, 'loss/train': 1.3207194805145264} 08/31/2021 04:29:25 - INFO - __main__ - Step 84542: {'lr': 0.0002049229903012141, 'samples': 16232064, 'steps': 84541, 'loss/train': 1.91371488571167} 08/31/2021 04:29:26 - INFO - __main__ - Step 84543: {'lr': 0.00020491777054354004, 'samples': 16232256, 'steps': 84542, 'loss/train': 1.0029373168945312} 08/31/2021 04:29:27 - INFO - __main__ - Step 84544: {'lr': 0.00020491255080617936, 'samples': 16232448, 'steps': 84543, 'loss/train': 1.3442258834838867} 08/31/2021 04:29:27 - INFO - __main__ - Step 84545: {'lr': 0.00020490733108913438, 'samples': 16232640, 'steps': 84544, 'loss/train': 1.2156926393508911} 08/31/2021 04:29:28 - INFO - __main__ - Step 84546: {'lr': 0.00020490211139240756, 'samples': 16232832, 'steps': 84545, 'loss/train': 1.5860602855682373} 08/31/2021 04:29:28 - INFO - __main__ - Step 84547: {'lr': 0.00020489689171600105, 'samples': 16233024, 'steps': 84546, 'loss/train': 1.8026759624481201} 08/31/2021 04:29:30 - INFO - __main__ - Step 84548: {'lr': 0.0002048916720599173, 'samples': 16233216, 'steps': 84547, 'loss/train': 1.2735731601715088} 08/31/2021 04:29:30 - INFO - __main__ - Step 84549: {'lr': 0.00020488645242415865, 'samples': 16233408, 'steps': 84548, 'loss/train': 1.34683358669281} 08/31/2021 04:29:31 - INFO - __main__ - Step 84550: {'lr': 0.0002048812328087275, 'samples': 16233600, 'steps': 84549, 'loss/train': 0.8324514627456665} 08/31/2021 04:29:31 - INFO - __main__ - Step 84551: {'lr': 0.00020487601321362615, 'samples': 16233792, 'steps': 84550, 'loss/train': 1.899340271949768} 08/31/2021 04:29:31 - INFO - __main__ - Step 84552: {'lr': 0.000204870793638857, 'samples': 16233984, 'steps': 84551, 'loss/train': 0.031564872711896896} 08/31/2021 04:29:32 - INFO - __main__ - Step 84553: {'lr': 0.00020486557408442235, 'samples': 16234176, 'steps': 84552, 'loss/train': 0.9250288605690002} 08/31/2021 04:29:33 - INFO - __main__ - Step 84554: {'lr': 0.00020486035455032458, 'samples': 16234368, 'steps': 84553, 'loss/train': 0.8939282298088074} 08/31/2021 04:29:34 - INFO - __main__ - Step 84555: {'lr': 0.00020485513503656604, 'samples': 16234560, 'steps': 84554, 'loss/train': 0.9678554534912109} 08/31/2021 04:29:34 - INFO - __main__ - Step 84556: {'lr': 0.00020484991554314908, 'samples': 16234752, 'steps': 84555, 'loss/train': 0.6925719976425171} 08/31/2021 04:29:34 - INFO - __main__ - Step 84557: {'lr': 0.00020484469607007604, 'samples': 16234944, 'steps': 84556, 'loss/train': 0.5313868522644043} 08/31/2021 04:29:35 - INFO - __main__ - Step 84558: {'lr': 0.0002048394766173493, 'samples': 16235136, 'steps': 84557, 'loss/train': 0.8822910189628601} 08/31/2021 04:29:36 - INFO - __main__ - Step 84559: {'lr': 0.00020483425718497127, 'samples': 16235328, 'steps': 84558, 'loss/train': 1.1608706712722778} 08/31/2021 04:29:37 - INFO - __main__ - Step 84560: {'lr': 0.00020482903777294416, 'samples': 16235520, 'steps': 84559, 'loss/train': 1.6949931383132935} 08/31/2021 04:29:37 - INFO - __main__ - Step 84561: {'lr': 0.00020482381838127038, 'samples': 16235712, 'steps': 84560, 'loss/train': 0.028251396492123604} 08/31/2021 04:29:37 - INFO - __main__ - Step 84562: {'lr': 0.0002048185990099523, 'samples': 16235904, 'steps': 84561, 'loss/train': 1.4381890296936035} 08/31/2021 04:29:38 - INFO - __main__ - Step 84563: {'lr': 0.0002048133796589922, 'samples': 16236096, 'steps': 84562, 'loss/train': 1.2753899097442627} 08/31/2021 04:29:40 - INFO - __main__ - Step 84564: {'lr': 0.00020480816032839255, 'samples': 16236288, 'steps': 84563, 'loss/train': 0.3307887017726898} 08/31/2021 04:29:40 - INFO - __main__ - Step 84565: {'lr': 0.00020480294101815565, 'samples': 16236480, 'steps': 84564, 'loss/train': 0.8924537301063538} 08/31/2021 04:29:41 - INFO - __main__ - Step 84566: {'lr': 0.00020479772172828382, 'samples': 16236672, 'steps': 84565, 'loss/train': 0.03390417993068695} 08/31/2021 04:29:41 - INFO - __main__ - Step 84567: {'lr': 0.00020479250245877944, 'samples': 16236864, 'steps': 84566, 'loss/train': 0.518231213092804} 08/31/2021 04:29:41 - INFO - __main__ - Step 84568: {'lr': 0.0002047872832096449, 'samples': 16237056, 'steps': 84567, 'loss/train': 1.57807457447052} 08/31/2021 04:29:43 - INFO - __main__ - Step 84569: {'lr': 0.00020478206398088247, 'samples': 16237248, 'steps': 84568, 'loss/train': 1.1745344400405884} 08/31/2021 04:29:43 - INFO - __main__ - Step 84570: {'lr': 0.00020477684477249457, 'samples': 16237440, 'steps': 84569, 'loss/train': 1.2823805809020996} 08/31/2021 04:29:44 - INFO - __main__ - Step 84571: {'lr': 0.00020477162558448352, 'samples': 16237632, 'steps': 84570, 'loss/train': 1.0628761053085327} 08/31/2021 04:29:44 - INFO - __main__ - Step 84572: {'lr': 0.00020476640641685164, 'samples': 16237824, 'steps': 84571, 'loss/train': 0.8213136196136475} 08/31/2021 04:29:44 - INFO - __main__ - Step 84573: {'lr': 0.00020476118726960146, 'samples': 16238016, 'steps': 84572, 'loss/train': 1.3450102806091309} 08/31/2021 04:29:45 - INFO - __main__ - Step 84574: {'lr': 0.00020475596814273513, 'samples': 16238208, 'steps': 84573, 'loss/train': 1.5645582675933838} 08/31/2021 04:29:46 - INFO - __main__ - Step 84575: {'lr': 0.000204750749036255, 'samples': 16238400, 'steps': 84574, 'loss/train': 1.3057100772857666} 08/31/2021 04:29:47 - INFO - __main__ - Step 84576: {'lr': 0.0002047455299501635, 'samples': 16238592, 'steps': 84575, 'loss/train': 1.5840096473693848} 08/31/2021 04:29:47 - INFO - __main__ - Step 84577: {'lr': 0.00020474031088446294, 'samples': 16238784, 'steps': 84576, 'loss/train': 1.7750256061553955} 08/31/2021 04:29:47 - INFO - __main__ - Step 84578: {'lr': 0.00020473509183915572, 'samples': 16238976, 'steps': 84577, 'loss/train': 1.156553864479065} 08/31/2021 04:29:48 - INFO - __main__ - Step 84579: {'lr': 0.00020472987281424418, 'samples': 16239168, 'steps': 84578, 'loss/train': 0.9694676995277405} 08/31/2021 04:29:49 - INFO - __main__ - Step 84580: {'lr': 0.00020472465380973065, 'samples': 16239360, 'steps': 84579, 'loss/train': 0.7302741408348083} 08/31/2021 04:29:49 - INFO - __main__ - Step 84581: {'lr': 0.0002047194348256175, 'samples': 16239552, 'steps': 84580, 'loss/train': 1.0432350635528564} 08/31/2021 04:29:50 - INFO - __main__ - Step 84582: {'lr': 0.00020471421586190706, 'samples': 16239744, 'steps': 84581, 'loss/train': 0.9388827681541443} 08/31/2021 04:29:50 - INFO - __main__ - Step 84583: {'lr': 0.0002047089969186017, 'samples': 16239936, 'steps': 84582, 'loss/train': 1.125150203704834} 08/31/2021 04:29:51 - INFO - __main__ - Step 84584: {'lr': 0.00020470377799570378, 'samples': 16240128, 'steps': 84583, 'loss/train': 1.282658576965332} 08/31/2021 04:29:53 - INFO - __main__ - Step 84585: {'lr': 0.00020469855909321564, 'samples': 16240320, 'steps': 84584, 'loss/train': 1.5162811279296875} 08/31/2021 04:29:53 - INFO - __main__ - Step 84586: {'lr': 0.0002046933402111397, 'samples': 16240512, 'steps': 84585, 'loss/train': 1.1680699586868286} 08/31/2021 04:29:53 - INFO - __main__ - Step 84587: {'lr': 0.00020468812134947817, 'samples': 16240704, 'steps': 84586, 'loss/train': 0.8210222721099854} 08/31/2021 04:29:54 - INFO - __main__ - Step 84588: {'lr': 0.00020468290250823346, 'samples': 16240896, 'steps': 84587, 'loss/train': 1.648847222328186} 08/31/2021 04:29:54 - INFO - __main__ - Step 84589: {'lr': 0.00020467768368740796, 'samples': 16241088, 'steps': 84588, 'loss/train': 1.032598853111267} 08/31/2021 04:29:56 - INFO - __main__ - Step 84590: {'lr': 0.00020467246488700398, 'samples': 16241280, 'steps': 84589, 'loss/train': 1.6753290891647339} 08/31/2021 04:29:56 - INFO - __main__ - Step 84591: {'lr': 0.00020466724610702388, 'samples': 16241472, 'steps': 84590, 'loss/train': 1.7695616483688354} 08/31/2021 04:29:56 - INFO - __main__ - Step 84592: {'lr': 0.00020466202734747003, 'samples': 16241664, 'steps': 84591, 'loss/train': 1.1721781492233276} 08/31/2021 04:29:57 - INFO - __main__ - Step 84593: {'lr': 0.00020465680860834475, 'samples': 16241856, 'steps': 84592, 'loss/train': 1.5643318891525269} 08/31/2021 04:29:57 - INFO - __main__ - Step 84594: {'lr': 0.00020465158988965045, 'samples': 16242048, 'steps': 84593, 'loss/train': 0.7802611589431763} 08/31/2021 04:29:59 - INFO - __main__ - Step 84595: {'lr': 0.0002046463711913894, 'samples': 16242240, 'steps': 84594, 'loss/train': 1.6501951217651367} 08/31/2021 04:30:00 - INFO - __main__ - Step 84596: {'lr': 0.00020464115251356401, 'samples': 16242432, 'steps': 84595, 'loss/train': 1.2853028774261475} 08/31/2021 04:30:00 - INFO - __main__ - Step 84597: {'lr': 0.00020463593385617663, 'samples': 16242624, 'steps': 84596, 'loss/train': 5.268214702606201} 08/31/2021 04:30:00 - INFO - __main__ - Step 84598: {'lr': 0.0002046307152192296, 'samples': 16242816, 'steps': 84597, 'loss/train': 5.180700778961182} 08/31/2021 04:30:01 - INFO - __main__ - Step 84599: {'lr': 0.00020462549660272536, 'samples': 16243008, 'steps': 84598, 'loss/train': 0.11421706527471542} 08/31/2021 04:30:01 - INFO - __main__ - Step 84600: {'lr': 0.00020462027800666608, 'samples': 16243200, 'steps': 84599, 'loss/train': 1.8874682188034058} 08/31/2021 04:30:01 - INFO - __main__ - Step 84601: {'lr': 0.00020461505943105419, 'samples': 16243392, 'steps': 84600, 'loss/train': 0.9346858859062195} 08/31/2021 04:30:03 - INFO - __main__ - Step 84602: {'lr': 0.00020460984087589205, 'samples': 16243584, 'steps': 84601, 'loss/train': 1.4959467649459839} 08/31/2021 04:30:03 - INFO - __main__ - Step 84603: {'lr': 0.00020460462234118203, 'samples': 16243776, 'steps': 84602, 'loss/train': 1.2589967250823975} 08/31/2021 04:30:04 - INFO - __main__ - Step 84604: {'lr': 0.00020459940382692646, 'samples': 16243968, 'steps': 84603, 'loss/train': 1.4602770805358887} 08/31/2021 04:30:04 - INFO - __main__ - Step 84605: {'lr': 0.00020459418533312767, 'samples': 16244160, 'steps': 84604, 'loss/train': 0.5637125372886658} 08/31/2021 04:30:04 - INFO - __main__ - Step 84606: {'lr': 0.0002045889668597881, 'samples': 16244352, 'steps': 84605, 'loss/train': 0.8445156216621399} 08/31/2021 04:30:06 - INFO - __main__ - Step 84607: {'lr': 0.00020458374840691, 'samples': 16244544, 'steps': 84606, 'loss/train': 0.7382444143295288} 08/31/2021 04:30:06 - INFO - __main__ - Step 84608: {'lr': 0.00020457852997449579, 'samples': 16244736, 'steps': 84607, 'loss/train': 1.791587471961975} 08/31/2021 04:30:07 - INFO - __main__ - Step 84609: {'lr': 0.00020457331156254776, 'samples': 16244928, 'steps': 84608, 'loss/train': 1.4695310592651367} 08/31/2021 04:30:07 - INFO - __main__ - Step 84610: {'lr': 0.0002045680931710683, 'samples': 16245120, 'steps': 84609, 'loss/train': 1.2800296545028687} 08/31/2021 04:30:07 - INFO - __main__ - Step 84611: {'lr': 0.00020456287480005974, 'samples': 16245312, 'steps': 84610, 'loss/train': 0.7624430060386658} 08/31/2021 04:30:09 - INFO - __main__ - Step 84612: {'lr': 0.0002045576564495245, 'samples': 16245504, 'steps': 84611, 'loss/train': 0.7349294424057007} 08/31/2021 04:30:09 - INFO - __main__ - Step 84613: {'lr': 0.00020455243811946496, 'samples': 16245696, 'steps': 84612, 'loss/train': 0.9478061199188232} 08/31/2021 04:30:10 - INFO - __main__ - Step 84614: {'lr': 0.00020454721980988329, 'samples': 16245888, 'steps': 84613, 'loss/train': 0.8684604167938232} 08/31/2021 04:30:10 - INFO - __main__ - Step 84615: {'lr': 0.00020454200152078192, 'samples': 16246080, 'steps': 84614, 'loss/train': 1.7378984689712524} 08/31/2021 04:30:10 - INFO - __main__ - Step 84616: {'lr': 0.00020453678325216325, 'samples': 16246272, 'steps': 84615, 'loss/train': 2.1741085052490234} 08/31/2021 04:30:12 - INFO - __main__ - Step 84617: {'lr': 0.00020453156500402958, 'samples': 16246464, 'steps': 84616, 'loss/train': 1.8384208679199219} 08/31/2021 04:30:12 - INFO - __main__ - Step 84618: {'lr': 0.00020452634677638328, 'samples': 16246656, 'steps': 84617, 'loss/train': 1.3725262880325317} 08/31/2021 04:30:13 - INFO - __main__ - Step 84619: {'lr': 0.00020452112856922673, 'samples': 16246848, 'steps': 84618, 'loss/train': 1.926589012145996} 08/31/2021 04:30:13 - INFO - __main__ - Step 84620: {'lr': 0.00020451591038256223, 'samples': 16247040, 'steps': 84619, 'loss/train': 1.190579891204834} 08/31/2021 04:30:13 - INFO - __main__ - Step 84621: {'lr': 0.00020451069221639218, 'samples': 16247232, 'steps': 84620, 'loss/train': 1.2036685943603516} 08/31/2021 04:30:15 - INFO - __main__ - Step 84622: {'lr': 0.00020450547407071894, 'samples': 16247424, 'steps': 84621, 'loss/train': 1.1263126134872437} 08/31/2021 04:30:16 - INFO - __main__ - Step 84623: {'lr': 0.00020450025594554477, 'samples': 16247616, 'steps': 84622, 'loss/train': 1.470803141593933} 08/31/2021 04:30:16 - INFO - __main__ - Step 84624: {'lr': 0.0002044950378408721, 'samples': 16247808, 'steps': 84623, 'loss/train': 0.7935805916786194} 08/31/2021 04:30:16 - INFO - __main__ - Step 84625: {'lr': 0.00020448981975670336, 'samples': 16248000, 'steps': 84624, 'loss/train': 1.099164366722107} 08/31/2021 04:30:17 - INFO - __main__ - Step 84626: {'lr': 0.00020448460169304074, 'samples': 16248192, 'steps': 84625, 'loss/train': 1.4500631093978882} 08/31/2021 04:30:18 - INFO - __main__ - Step 84627: {'lr': 0.00020447938364988666, 'samples': 16248384, 'steps': 84626, 'loss/train': 2.089493751525879} 08/31/2021 04:30:19 - INFO - __main__ - Step 84628: {'lr': 0.00020447416562724345, 'samples': 16248576, 'steps': 84627, 'loss/train': 1.4024724960327148} 08/31/2021 04:30:19 - INFO - __main__ - Step 84629: {'lr': 0.00020446894762511346, 'samples': 16248768, 'steps': 84628, 'loss/train': 1.2415128946304321} 08/31/2021 04:30:19 - INFO - __main__ - Step 84630: {'lr': 0.00020446372964349907, 'samples': 16248960, 'steps': 84629, 'loss/train': 1.1871905326843262} 08/31/2021 04:30:20 - INFO - __main__ - Step 84631: {'lr': 0.00020445851168240264, 'samples': 16249152, 'steps': 84630, 'loss/train': 1.7259122133255005} 08/31/2021 04:30:20 - INFO - __main__ - Step 84632: {'lr': 0.00020445329374182646, 'samples': 16249344, 'steps': 84631, 'loss/train': 0.9172227382659912} 08/31/2021 04:30:21 - INFO - __main__ - Step 84633: {'lr': 0.00020444807582177296, 'samples': 16249536, 'steps': 84632, 'loss/train': 1.0638291835784912} 08/31/2021 04:30:22 - INFO - __main__ - Step 84634: {'lr': 0.00020444285792224444, 'samples': 16249728, 'steps': 84633, 'loss/train': 1.2640517950057983} 08/31/2021 04:30:22 - INFO - __main__ - Step 84635: {'lr': 0.00020443764004324328, 'samples': 16249920, 'steps': 84634, 'loss/train': 0.381023645401001} 08/31/2021 04:30:23 - INFO - __main__ - Step 84636: {'lr': 0.00020443242218477184, 'samples': 16250112, 'steps': 84635, 'loss/train': 0.2182699739933014} 08/31/2021 04:30:23 - INFO - __main__ - Step 84637: {'lr': 0.00020442720434683242, 'samples': 16250304, 'steps': 84636, 'loss/train': 1.363998532295227} 08/31/2021 04:30:25 - INFO - __main__ - Step 84638: {'lr': 0.0002044219865294274, 'samples': 16250496, 'steps': 84637, 'loss/train': 1.3953375816345215} 08/31/2021 04:30:25 - INFO - __main__ - Step 84639: {'lr': 0.0002044167687325591, 'samples': 16250688, 'steps': 84638, 'loss/train': 1.3711750507354736} 08/31/2021 04:30:26 - INFO - __main__ - Step 84640: {'lr': 0.00020441155095622998, 'samples': 16250880, 'steps': 84639, 'loss/train': 1.4707763195037842} 08/31/2021 04:30:26 - INFO - __main__ - Step 84641: {'lr': 0.00020440633320044225, 'samples': 16251072, 'steps': 84640, 'loss/train': 1.3151357173919678} 08/31/2021 04:30:27 - INFO - __main__ - Step 84642: {'lr': 0.00020440111546519833, 'samples': 16251264, 'steps': 84641, 'loss/train': 1.458260178565979} 08/31/2021 04:30:28 - INFO - __main__ - Step 84643: {'lr': 0.00020439589775050055, 'samples': 16251456, 'steps': 84642, 'loss/train': 0.8522238731384277} 08/31/2021 04:30:29 - INFO - __main__ - Step 84644: {'lr': 0.00020439068005635128, 'samples': 16251648, 'steps': 84643, 'loss/train': 0.9155744910240173} 08/31/2021 04:30:29 - INFO - __main__ - Step 84645: {'lr': 0.00020438546238275287, 'samples': 16251840, 'steps': 84644, 'loss/train': 0.9753713607788086} 08/31/2021 04:30:29 - INFO - __main__ - Step 84646: {'lr': 0.00020438024472970768, 'samples': 16252032, 'steps': 84645, 'loss/train': 1.4073357582092285} 08/31/2021 04:30:30 - INFO - __main__ - Step 84647: {'lr': 0.00020437502709721805, 'samples': 16252224, 'steps': 84646, 'loss/train': 1.5534852743148804} 08/31/2021 04:30:31 - INFO - __main__ - Step 84648: {'lr': 0.00020436980948528632, 'samples': 16252416, 'steps': 84647, 'loss/train': 1.489311695098877} 08/31/2021 04:30:31 - INFO - __main__ - Step 84649: {'lr': 0.00020436459189391486, 'samples': 16252608, 'steps': 84648, 'loss/train': 1.857591986656189} 08/31/2021 04:30:32 - INFO - __main__ - Step 84650: {'lr': 0.00020435937432310597, 'samples': 16252800, 'steps': 84649, 'loss/train': 1.934131383895874} 08/31/2021 04:30:32 - INFO - __main__ - Step 84651: {'lr': 0.00020435415677286207, 'samples': 16252992, 'steps': 84650, 'loss/train': 0.6319000124931335} 08/31/2021 04:30:33 - INFO - __main__ - Step 84652: {'lr': 0.00020434893924318548, 'samples': 16253184, 'steps': 84651, 'loss/train': 1.2565869092941284} 08/31/2021 04:30:34 - INFO - __main__ - Step 84653: {'lr': 0.00020434372173407862, 'samples': 16253376, 'steps': 84652, 'loss/train': 0.8460128307342529} 08/31/2021 04:30:35 - INFO - __main__ - Step 84654: {'lr': 0.00020433850424554368, 'samples': 16253568, 'steps': 84653, 'loss/train': 1.7587491273880005} 08/31/2021 04:30:35 - INFO - __main__ - Step 84655: {'lr': 0.00020433328677758314, 'samples': 16253760, 'steps': 84654, 'loss/train': 1.3020641803741455} 08/31/2021 04:30:35 - INFO - __main__ - Step 84656: {'lr': 0.0002043280693301993, 'samples': 16253952, 'steps': 84655, 'loss/train': 1.2144635915756226} 08/31/2021 04:30:36 - INFO - __main__ - Step 84657: {'lr': 0.00020432285190339453, 'samples': 16254144, 'steps': 84656, 'loss/train': 1.4613343477249146} 08/31/2021 04:30:37 - INFO - __main__ - Step 84658: {'lr': 0.00020431763449717122, 'samples': 16254336, 'steps': 84657, 'loss/train': 0.3157605826854706} 08/31/2021 04:30:38 - INFO - __main__ - Step 84659: {'lr': 0.00020431241711153165, 'samples': 16254528, 'steps': 84658, 'loss/train': 1.1039255857467651} 08/31/2021 04:30:38 - INFO - __main__ - Step 84660: {'lr': 0.0002043071997464782, 'samples': 16254720, 'steps': 84659, 'loss/train': 0.03688950091600418} 08/31/2021 04:30:38 - INFO - __main__ - Step 84661: {'lr': 0.0002043019824020132, 'samples': 16254912, 'steps': 84660, 'loss/train': 1.1743566989898682} 08/31/2021 04:30:39 - INFO - __main__ - Step 84662: {'lr': 0.00020429676507813905, 'samples': 16255104, 'steps': 84661, 'loss/train': 1.3523311614990234} 08/31/2021 04:30:40 - INFO - __main__ - Step 84663: {'lr': 0.00020429154777485802, 'samples': 16255296, 'steps': 84662, 'loss/train': 1.215545654296875} 08/31/2021 04:30:41 - INFO - __main__ - Step 84664: {'lr': 0.00020428633049217258, 'samples': 16255488, 'steps': 84663, 'loss/train': 1.4677011966705322} 08/31/2021 04:30:41 - INFO - __main__ - Step 84665: {'lr': 0.00020428111323008498, 'samples': 16255680, 'steps': 84664, 'loss/train': 1.1099927425384521} 08/31/2021 04:30:41 - INFO - __main__ - Step 84666: {'lr': 0.0002042758959885976, 'samples': 16255872, 'steps': 84665, 'loss/train': 1.090349555015564} 08/31/2021 04:30:42 - INFO - __main__ - Step 84667: {'lr': 0.00020427067876771285, 'samples': 16256064, 'steps': 84666, 'loss/train': 1.3001818656921387} 08/31/2021 04:30:43 - INFO - __main__ - Step 84668: {'lr': 0.00020426546156743298, 'samples': 16256256, 'steps': 84667, 'loss/train': 1.0099555253982544} 08/31/2021 04:30:44 - INFO - __main__ - Step 84669: {'lr': 0.00020426024438776043, 'samples': 16256448, 'steps': 84668, 'loss/train': 0.7805726528167725} 08/31/2021 04:30:44 - INFO - __main__ - Step 84670: {'lr': 0.0002042550272286975, 'samples': 16256640, 'steps': 84669, 'loss/train': 1.004654049873352} 08/31/2021 04:30:45 - INFO - __main__ - Step 84671: {'lr': 0.00020424981009024647, 'samples': 16256832, 'steps': 84670, 'loss/train': 0.7783727645874023} 08/31/2021 04:30:45 - INFO - __main__ - Step 84672: {'lr': 0.00020424459297240983, 'samples': 16257024, 'steps': 84671, 'loss/train': 0.8919099569320679} 08/31/2021 04:30:45 - INFO - __main__ - Step 84673: {'lr': 0.00020423937587518988, 'samples': 16257216, 'steps': 84672, 'loss/train': 0.6984131932258606} 08/31/2021 04:30:47 - INFO - __main__ - Step 84674: {'lr': 0.0002042341587985889, 'samples': 16257408, 'steps': 84673, 'loss/train': 1.058016061782837} 08/31/2021 04:30:47 - INFO - __main__ - Step 84675: {'lr': 0.00020422894174260933, 'samples': 16257600, 'steps': 84674, 'loss/train': 1.4660285711288452} 08/31/2021 04:30:48 - INFO - __main__ - Step 84676: {'lr': 0.0002042237247072535, 'samples': 16257792, 'steps': 84675, 'loss/train': 1.1564384698867798} 08/31/2021 04:30:48 - INFO - __main__ - Step 84677: {'lr': 0.00020421850769252375, 'samples': 16257984, 'steps': 84676, 'loss/train': 1.6752734184265137} 08/31/2021 04:30:48 - INFO - __main__ - Step 84678: {'lr': 0.00020421329069842246, 'samples': 16258176, 'steps': 84677, 'loss/train': 1.3879115581512451} 08/31/2021 04:30:50 - INFO - __main__ - Step 84679: {'lr': 0.00020420807372495192, 'samples': 16258368, 'steps': 84678, 'loss/train': 0.5662429928779602} 08/31/2021 04:30:50 - INFO - __main__ - Step 84680: {'lr': 0.00020420285677211463, 'samples': 16258560, 'steps': 84679, 'loss/train': 1.6026530265808105} 08/31/2021 04:30:51 - INFO - __main__ - Step 84681: {'lr': 0.00020419763983991275, 'samples': 16258752, 'steps': 84680, 'loss/train': 1.0312949419021606} 08/31/2021 04:30:51 - INFO - __main__ - Step 84682: {'lr': 0.00020419242292834866, 'samples': 16258944, 'steps': 84681, 'loss/train': 1.2286441326141357} 08/31/2021 04:30:51 - INFO - __main__ - Step 84683: {'lr': 0.00020418720603742477, 'samples': 16259136, 'steps': 84682, 'loss/train': 1.8410990238189697} 08/31/2021 04:30:53 - INFO - __main__ - Step 84684: {'lr': 0.00020418198916714343, 'samples': 16259328, 'steps': 84683, 'loss/train': 1.0548955202102661} 08/31/2021 04:30:53 - INFO - __main__ - Step 84685: {'lr': 0.00020417677231750696, 'samples': 16259520, 'steps': 84684, 'loss/train': 2.111682176589966} 08/31/2021 04:30:54 - INFO - __main__ - Step 84686: {'lr': 0.00020417155548851774, 'samples': 16259712, 'steps': 84685, 'loss/train': 1.5353477001190186} 08/31/2021 04:30:54 - INFO - __main__ - Step 84687: {'lr': 0.00020416633868017812, 'samples': 16259904, 'steps': 84686, 'loss/train': 0.68857741355896} 08/31/2021 04:30:54 - INFO - __main__ - Step 84688: {'lr': 0.00020416112189249042, 'samples': 16260096, 'steps': 84687, 'loss/train': 1.465735673904419} 08/31/2021 04:30:56 - INFO - __main__ - Step 84689: {'lr': 0.00020415590512545703, 'samples': 16260288, 'steps': 84688, 'loss/train': 0.5628434419631958} 08/31/2021 04:30:57 - INFO - __main__ - Step 84690: {'lr': 0.0002041506883790803, 'samples': 16260480, 'steps': 84689, 'loss/train': 1.1477305889129639} 08/31/2021 04:30:57 - INFO - __main__ - Step 84691: {'lr': 0.0002041454716533625, 'samples': 16260672, 'steps': 84690, 'loss/train': 1.4447286128997803} 08/31/2021 04:30:57 - INFO - __main__ - Step 84692: {'lr': 0.0002041402549483061, 'samples': 16260864, 'steps': 84691, 'loss/train': 0.8609048128128052} 08/31/2021 04:30:58 - INFO - __main__ - Step 84693: {'lr': 0.0002041350382639134, 'samples': 16261056, 'steps': 84692, 'loss/train': 1.0229384899139404} 08/31/2021 04:30:59 - INFO - __main__ - Step 84694: {'lr': 0.00020412982160018678, 'samples': 16261248, 'steps': 84693, 'loss/train': 1.7835289239883423} 08/31/2021 04:31:00 - INFO - __main__ - Step 84695: {'lr': 0.0002041246049571285, 'samples': 16261440, 'steps': 84694, 'loss/train': 1.3581287860870361} 08/31/2021 04:31:00 - INFO - __main__ - Step 84696: {'lr': 0.00020411938833474097, 'samples': 16261632, 'steps': 84695, 'loss/train': 1.1430532932281494} 08/31/2021 04:31:01 - INFO - __main__ - Step 84697: {'lr': 0.0002041141717330265, 'samples': 16261824, 'steps': 84696, 'loss/train': 1.3968052864074707} 08/31/2021 04:31:01 - INFO - __main__ - Step 84698: {'lr': 0.00020410895515198752, 'samples': 16262016, 'steps': 84697, 'loss/train': 1.1543940305709839} 08/31/2021 04:31:02 - INFO - __main__ - Step 84699: {'lr': 0.0002041037385916263, 'samples': 16262208, 'steps': 84698, 'loss/train': 1.470012903213501} 08/31/2021 04:31:03 - INFO - __main__ - Step 84700: {'lr': 0.00020409852205194526, 'samples': 16262400, 'steps': 84699, 'loss/train': 0.8820517659187317} 08/31/2021 04:31:03 - INFO - __main__ - Step 84701: {'lr': 0.0002040933055329467, 'samples': 16262592, 'steps': 84700, 'loss/train': 0.7531233429908752} 08/31/2021 04:31:03 - INFO - __main__ - Step 84702: {'lr': 0.000204088089034633, 'samples': 16262784, 'steps': 84701, 'loss/train': 0.8488095998764038} 08/31/2021 04:31:04 - INFO - __main__ - Step 84703: {'lr': 0.00020408287255700648, 'samples': 16262976, 'steps': 84702, 'loss/train': 1.6328697204589844} 08/31/2021 04:31:05 - INFO - __main__ - Step 84704: {'lr': 0.0002040776561000695, 'samples': 16263168, 'steps': 84703, 'loss/train': 1.7369942665100098} 08/31/2021 04:31:06 - INFO - __main__ - Step 84705: {'lr': 0.00020407243966382444, 'samples': 16263360, 'steps': 84704, 'loss/train': 1.5067880153656006} 08/31/2021 04:31:06 - INFO - __main__ - Step 84706: {'lr': 0.00020406722324827365, 'samples': 16263552, 'steps': 84705, 'loss/train': 1.1679763793945312} 08/31/2021 04:31:06 - INFO - __main__ - Step 84707: {'lr': 0.00020406200685341952, 'samples': 16263744, 'steps': 84706, 'loss/train': 1.1243053674697876} 08/31/2021 04:31:07 - INFO - __main__ - Step 84708: {'lr': 0.00020405679047926425, 'samples': 16263936, 'steps': 84707, 'loss/train': 0.8670626878738403} 08/31/2021 04:31:08 - INFO - __main__ - Step 84709: {'lr': 0.0002040515741258103, 'samples': 16264128, 'steps': 84708, 'loss/train': 1.634728193283081} 08/31/2021 04:31:09 - INFO - __main__ - Step 84710: {'lr': 0.00020404635779305998, 'samples': 16264320, 'steps': 84709, 'loss/train': 1.1274856328964233} 08/31/2021 04:31:09 - INFO - __main__ - Step 84711: {'lr': 0.0002040411414810157, 'samples': 16264512, 'steps': 84710, 'loss/train': 1.2615505456924438} 08/31/2021 04:31:10 - INFO - __main__ - Step 84712: {'lr': 0.00020403592518967973, 'samples': 16264704, 'steps': 84711, 'loss/train': 1.5600272417068481} 08/31/2021 04:31:10 - INFO - __main__ - Step 84713: {'lr': 0.0002040307089190545, 'samples': 16264896, 'steps': 84712, 'loss/train': 1.1928050518035889} 08/31/2021 04:31:10 - INFO - __main__ - Step 84714: {'lr': 0.00020402549266914228, 'samples': 16265088, 'steps': 84713, 'loss/train': 1.436352252960205} 08/31/2021 04:31:12 - INFO - __main__ - Step 84715: {'lr': 0.00020402027643994547, 'samples': 16265280, 'steps': 84714, 'loss/train': 1.0143097639083862} 08/31/2021 04:31:12 - INFO - __main__ - Step 84716: {'lr': 0.00020401506023146643, 'samples': 16265472, 'steps': 84715, 'loss/train': 1.5113097429275513} 08/31/2021 04:31:13 - INFO - __main__ - Step 84717: {'lr': 0.00020400984404370752, 'samples': 16265664, 'steps': 84716, 'loss/train': 1.355127215385437} 08/31/2021 04:31:13 - INFO - __main__ - Step 84718: {'lr': 0.00020400462787667102, 'samples': 16265856, 'steps': 84717, 'loss/train': 0.5966939330101013} 08/31/2021 04:31:13 - INFO - __main__ - Step 84719: {'lr': 0.00020399941173035934, 'samples': 16266048, 'steps': 84718, 'loss/train': 1.2578223943710327} 08/31/2021 04:31:15 - INFO - __main__ - Step 84720: {'lr': 0.00020399419560477493, 'samples': 16266240, 'steps': 84719, 'loss/train': 1.6136740446090698} 08/31/2021 04:31:15 - INFO - __main__ - Step 84721: {'lr': 0.0002039889794999199, 'samples': 16266432, 'steps': 84720, 'loss/train': 1.026685357093811} 08/31/2021 04:31:15 - INFO - __main__ - Step 84722: {'lr': 0.00020398376341579675, 'samples': 16266624, 'steps': 84721, 'loss/train': 1.4913630485534668} 08/31/2021 04:31:16 - INFO - __main__ - Step 84723: {'lr': 0.0002039785473524078, 'samples': 16266816, 'steps': 84722, 'loss/train': 1.7553563117980957} 08/31/2021 04:31:16 - INFO - __main__ - Step 84724: {'lr': 0.0002039733313097554, 'samples': 16267008, 'steps': 84723, 'loss/train': 1.2555034160614014} 08/31/2021 04:31:18 - INFO - __main__ - Step 84725: {'lr': 0.0002039681152878419, 'samples': 16267200, 'steps': 84724, 'loss/train': 1.1355688571929932} 08/31/2021 04:31:18 - INFO - __main__ - Step 84726: {'lr': 0.00020396289928666968, 'samples': 16267392, 'steps': 84725, 'loss/train': 0.9284418821334839} 08/31/2021 04:31:19 - INFO - __main__ - Step 84727: {'lr': 0.00020395768330624104, 'samples': 16267584, 'steps': 84726, 'loss/train': 1.0244958400726318} 08/31/2021 04:31:19 - INFO - __main__ - Step 84728: {'lr': 0.00020395246734655837, 'samples': 16267776, 'steps': 84727, 'loss/train': 1.1371408700942993} 08/31/2021 04:31:19 - INFO - __main__ - Step 84729: {'lr': 0.000203947251407624, 'samples': 16267968, 'steps': 84728, 'loss/train': 1.0388548374176025} 08/31/2021 04:31:21 - INFO - __main__ - Step 84730: {'lr': 0.0002039420354894403, 'samples': 16268160, 'steps': 84729, 'loss/train': 1.1974513530731201} 08/31/2021 04:31:21 - INFO - __main__ - Step 84731: {'lr': 0.0002039368195920096, 'samples': 16268352, 'steps': 84730, 'loss/train': 0.7065281867980957} 08/31/2021 04:31:22 - INFO - __main__ - Step 84732: {'lr': 0.00020393160371533426, 'samples': 16268544, 'steps': 84731, 'loss/train': 1.4528372287750244} 08/31/2021 04:31:22 - INFO - __main__ - Step 84733: {'lr': 0.00020392638785941665, 'samples': 16268736, 'steps': 84732, 'loss/train': 1.4445645809173584} 08/31/2021 04:31:22 - INFO - __main__ - Step 84734: {'lr': 0.00020392117202425918, 'samples': 16268928, 'steps': 84733, 'loss/train': 1.325258493423462} 08/31/2021 04:31:24 - INFO - __main__ - Step 84735: {'lr': 0.000203915956209864, 'samples': 16269120, 'steps': 84734, 'loss/train': 0.9562880992889404} 08/31/2021 04:31:24 - INFO - __main__ - Step 84736: {'lr': 0.0002039107404162336, 'samples': 16269312, 'steps': 84735, 'loss/train': 0.8331207036972046} 08/31/2021 04:31:25 - INFO - __main__ - Step 84737: {'lr': 0.0002039055246433703, 'samples': 16269504, 'steps': 84736, 'loss/train': 1.6611818075180054} 08/31/2021 04:31:25 - INFO - __main__ - Step 84738: {'lr': 0.00020390030889127649, 'samples': 16269696, 'steps': 84737, 'loss/train': 1.0952234268188477} 08/31/2021 04:31:25 - INFO - __main__ - Step 84739: {'lr': 0.00020389509315995444, 'samples': 16269888, 'steps': 84738, 'loss/train': 0.8368931412696838} 08/31/2021 04:31:28 - INFO - __main__ - Step 84740: {'lr': 0.00020388987744940658, 'samples': 16270080, 'steps': 84739, 'loss/train': 0.8109778761863708} 08/31/2021 04:31:28 - INFO - __main__ - Step 84741: {'lr': 0.00020388466175963522, 'samples': 16270272, 'steps': 84740, 'loss/train': 0.7586427927017212} 08/31/2021 04:31:29 - INFO - __main__ - Step 84742: {'lr': 0.00020387944609064274, 'samples': 16270464, 'steps': 84741, 'loss/train': 0.018321162089705467} 08/31/2021 04:31:29 - INFO - __main__ - Step 84743: {'lr': 0.00020387423044243143, 'samples': 16270656, 'steps': 84742, 'loss/train': 1.5220086574554443} 08/31/2021 04:31:29 - INFO - __main__ - Step 84744: {'lr': 0.0002038690148150037, 'samples': 16270848, 'steps': 84743, 'loss/train': 0.5082000494003296} 08/31/2021 04:31:30 - INFO - __main__ - Step 84745: {'lr': 0.0002038637992083619, 'samples': 16271040, 'steps': 84744, 'loss/train': 1.3999518156051636} 08/31/2021 04:31:32 - INFO - __main__ - Step 84746: {'lr': 0.00020385858362250832, 'samples': 16271232, 'steps': 84745, 'loss/train': 1.401397705078125} 08/31/2021 04:31:32 - INFO - __main__ - Step 84747: {'lr': 0.0002038533680574455, 'samples': 16271424, 'steps': 84746, 'loss/train': 0.6921067833900452} 08/31/2021 04:31:32 - INFO - __main__ - Step 84748: {'lr': 0.0002038481525131755, 'samples': 16271616, 'steps': 84747, 'loss/train': 1.0584816932678223} 08/31/2021 04:31:33 - INFO - __main__ - Step 84749: {'lr': 0.00020384293698970087, 'samples': 16271808, 'steps': 84748, 'loss/train': 1.6825673580169678} 08/31/2021 04:31:33 - INFO - __main__ - Step 84750: {'lr': 0.00020383772148702383, 'samples': 16272000, 'steps': 84749, 'loss/train': 1.1230883598327637} 08/31/2021 04:31:34 - INFO - __main__ - Step 84751: {'lr': 0.00020383250600514684, 'samples': 16272192, 'steps': 84750, 'loss/train': 0.9626840949058533} 08/31/2021 04:31:35 - INFO - __main__ - Step 84752: {'lr': 0.00020382729054407218, 'samples': 16272384, 'steps': 84751, 'loss/train': 1.122146725654602} 08/31/2021 04:31:35 - INFO - __main__ - Step 84753: {'lr': 0.00020382207510380223, 'samples': 16272576, 'steps': 84752, 'loss/train': 1.821378469467163} 08/31/2021 04:31:36 - INFO - __main__ - Step 84754: {'lr': 0.0002038168596843394, 'samples': 16272768, 'steps': 84753, 'loss/train': 1.215323567390442} 08/31/2021 04:31:36 - INFO - __main__ - Step 84755: {'lr': 0.00020381164428568592, 'samples': 16272960, 'steps': 84754, 'loss/train': 1.3041056394577026} 08/31/2021 04:31:37 - INFO - __main__ - Step 84756: {'lr': 0.0002038064289078442, 'samples': 16273152, 'steps': 84755, 'loss/train': 1.0477702617645264} 08/31/2021 04:31:38 - INFO - __main__ - Step 84757: {'lr': 0.0002038012135508166, 'samples': 16273344, 'steps': 84756, 'loss/train': 1.7890862226486206} 08/31/2021 04:31:38 - INFO - __main__ - Step 84758: {'lr': 0.00020379599821460548, 'samples': 16273536, 'steps': 84757, 'loss/train': 1.2941486835479736} 08/31/2021 04:31:39 - INFO - __main__ - Step 84759: {'lr': 0.0002037907828992132, 'samples': 16273728, 'steps': 84758, 'loss/train': 1.086531400680542} 08/31/2021 04:31:39 - INFO - __main__ - Step 84760: {'lr': 0.00020378556760464205, 'samples': 16273920, 'steps': 84759, 'loss/train': 1.4588844776153564} 08/31/2021 04:31:39 - INFO - __main__ - Step 84761: {'lr': 0.00020378035233089444, 'samples': 16274112, 'steps': 84760, 'loss/train': 0.7105628252029419} 08/31/2021 04:31:41 - INFO - __main__ - Step 84762: {'lr': 0.00020377513707797265, 'samples': 16274304, 'steps': 84761, 'loss/train': 1.2701315879821777} 08/31/2021 04:31:41 - INFO - __main__ - Step 84763: {'lr': 0.00020376992184587908, 'samples': 16274496, 'steps': 84762, 'loss/train': 1.0465413331985474} 08/31/2021 04:31:42 - INFO - __main__ - Step 84764: {'lr': 0.00020376470663461605, 'samples': 16274688, 'steps': 84763, 'loss/train': 0.4981254041194916} 08/31/2021 04:31:42 - INFO - __main__ - Step 84765: {'lr': 0.00020375949144418594, 'samples': 16274880, 'steps': 84764, 'loss/train': 1.204838514328003} 08/31/2021 04:31:42 - INFO - __main__ - Step 84766: {'lr': 0.0002037542762745911, 'samples': 16275072, 'steps': 84765, 'loss/train': 1.3864552974700928} 08/31/2021 04:31:44 - INFO - __main__ - Step 84767: {'lr': 0.00020374906112583386, 'samples': 16275264, 'steps': 84766, 'loss/train': 0.9033673405647278} 08/31/2021 04:31:45 - INFO - __main__ - Step 84768: {'lr': 0.00020374384599791657, 'samples': 16275456, 'steps': 84767, 'loss/train': 1.8839701414108276} 08/31/2021 04:31:45 - INFO - __main__ - Step 84769: {'lr': 0.0002037386308908416, 'samples': 16275648, 'steps': 84768, 'loss/train': 0.47604042291641235} 08/31/2021 04:31:46 - INFO - __main__ - Step 84770: {'lr': 0.00020373341580461133, 'samples': 16275840, 'steps': 84769, 'loss/train': 1.3376072645187378} 08/31/2021 04:31:46 - INFO - __main__ - Step 84771: {'lr': 0.00020372820073922803, 'samples': 16276032, 'steps': 84770, 'loss/train': 1.2383322715759277} 08/31/2021 04:31:48 - INFO - __main__ - Step 84772: {'lr': 0.0002037229856946941, 'samples': 16276224, 'steps': 84771, 'loss/train': 0.031966328620910645} 08/31/2021 04:31:48 - INFO - __main__ - Step 84773: {'lr': 0.00020371777067101183, 'samples': 16276416, 'steps': 84772, 'loss/train': 0.028092866763472557} 08/31/2021 04:31:49 - INFO - __main__ - Step 84774: {'lr': 0.00020371255566818368, 'samples': 16276608, 'steps': 84773, 'loss/train': 0.8615524768829346} 08/31/2021 04:31:49 - INFO - __main__ - Step 84775: {'lr': 0.00020370734068621193, 'samples': 16276800, 'steps': 84774, 'loss/train': 1.0379955768585205} 08/31/2021 04:31:49 - INFO - __main__ - Step 84776: {'lr': 0.00020370212572509892, 'samples': 16276992, 'steps': 84775, 'loss/train': 1.4664026498794556} 08/31/2021 04:31:51 - INFO - __main__ - Step 84777: {'lr': 0.00020369691078484702, 'samples': 16277184, 'steps': 84776, 'loss/train': 0.8918171525001526} 08/31/2021 04:31:51 - INFO - __main__ - Step 84778: {'lr': 0.00020369169586545856, 'samples': 16277376, 'steps': 84777, 'loss/train': 0.32880696654319763} 08/31/2021 04:31:52 - INFO - __main__ - Step 84779: {'lr': 0.00020368648096693592, 'samples': 16277568, 'steps': 84778, 'loss/train': 1.598102331161499} 08/31/2021 04:31:52 - INFO - __main__ - Step 84780: {'lr': 0.00020368126608928146, 'samples': 16277760, 'steps': 84779, 'loss/train': 2.0559589862823486} 08/31/2021 04:31:52 - INFO - __main__ - Step 84781: {'lr': 0.00020367605123249749, 'samples': 16277952, 'steps': 84780, 'loss/train': 1.9718034267425537} 08/31/2021 04:31:53 - INFO - __main__ - Step 84782: {'lr': 0.0002036708363965864, 'samples': 16278144, 'steps': 84781, 'loss/train': 1.1234744787216187} 08/31/2021 04:31:54 - INFO - __main__ - Step 84783: {'lr': 0.00020366562158155048, 'samples': 16278336, 'steps': 84782, 'loss/train': 1.0795302391052246} 08/31/2021 04:31:55 - INFO - __main__ - Step 84784: {'lr': 0.0002036604067873921, 'samples': 16278528, 'steps': 84783, 'loss/train': 1.773276448249817} 08/31/2021 04:31:55 - INFO - __main__ - Step 84785: {'lr': 0.00020365519201411364, 'samples': 16278720, 'steps': 84784, 'loss/train': 0.040744855999946594} 08/31/2021 04:31:55 - INFO - __main__ - Step 84786: {'lr': 0.00020364997726171746, 'samples': 16278912, 'steps': 84785, 'loss/train': 0.9671341180801392} 08/31/2021 04:31:56 - INFO - __main__ - Step 84787: {'lr': 0.00020364476253020587, 'samples': 16279104, 'steps': 84786, 'loss/train': 1.674696445465088} 08/31/2021 04:31:57 - INFO - __main__ - Step 84788: {'lr': 0.00020363954781958126, 'samples': 16279296, 'steps': 84787, 'loss/train': 1.0377436876296997} 08/31/2021 04:31:58 - INFO - __main__ - Step 84789: {'lr': 0.00020363433312984596, 'samples': 16279488, 'steps': 84788, 'loss/train': 0.47210437059402466} 08/31/2021 04:31:58 - INFO - __main__ - Step 84790: {'lr': 0.00020362911846100228, 'samples': 16279680, 'steps': 84789, 'loss/train': 1.179039478302002} 08/31/2021 04:31:59 - INFO - __main__ - Step 84791: {'lr': 0.00020362390381305256, 'samples': 16279872, 'steps': 84790, 'loss/train': 0.7555726766586304} 08/31/2021 04:31:59 - INFO - __main__ - Step 84792: {'lr': 0.0002036186891859993, 'samples': 16280064, 'steps': 84791, 'loss/train': 1.1318929195404053} 08/31/2021 04:31:59 - INFO - __main__ - Step 84793: {'lr': 0.0002036134745798447, 'samples': 16280256, 'steps': 84792, 'loss/train': 1.188409686088562} 08/31/2021 04:32:01 - INFO - __main__ - Step 84794: {'lr': 0.00020360825999459113, 'samples': 16280448, 'steps': 84793, 'loss/train': 1.2254096269607544} 08/31/2021 04:32:01 - INFO - __main__ - Step 84795: {'lr': 0.00020360304543024096, 'samples': 16280640, 'steps': 84794, 'loss/train': 1.5044384002685547} 08/31/2021 04:32:02 - INFO - __main__ - Step 84796: {'lr': 0.00020359783088679654, 'samples': 16280832, 'steps': 84795, 'loss/train': 1.0569939613342285} 08/31/2021 04:32:02 - INFO - __main__ - Step 84797: {'lr': 0.00020359261636426025, 'samples': 16281024, 'steps': 84796, 'loss/train': 2.9954493045806885} 08/31/2021 04:32:02 - INFO - __main__ - Step 84798: {'lr': 0.00020358740186263437, 'samples': 16281216, 'steps': 84797, 'loss/train': 3.62605619430542} 08/31/2021 04:32:05 - INFO - __main__ - Step 84799: {'lr': 0.0002035821873819213, 'samples': 16281408, 'steps': 84798, 'loss/train': 1.5994305610656738} 08/31/2021 04:32:05 - INFO - __main__ - Step 84800: {'lr': 0.00020357697292212342, 'samples': 16281600, 'steps': 84799, 'loss/train': 1.180112361907959} 08/31/2021 04:32:06 - INFO - __main__ - Step 84801: {'lr': 0.00020357175848324306, 'samples': 16281792, 'steps': 84800, 'loss/train': 2.0865204334259033} 08/31/2021 04:32:06 - INFO - __main__ - Step 84802: {'lr': 0.00020356654406528246, 'samples': 16281984, 'steps': 84801, 'loss/train': 0.8039007186889648} 08/31/2021 04:32:06 - INFO - __main__ - Step 84803: {'lr': 0.00020356132966824417, 'samples': 16282176, 'steps': 84802, 'loss/train': 1.1591589450836182} 08/31/2021 04:32:08 - INFO - __main__ - Step 84804: {'lr': 0.00020355611529213036, 'samples': 16282368, 'steps': 84803, 'loss/train': 1.0393787622451782} 08/31/2021 04:32:08 - INFO - __main__ - Step 84805: {'lr': 0.00020355090093694342, 'samples': 16282560, 'steps': 84804, 'loss/train': 1.2219828367233276} 08/31/2021 04:32:09 - INFO - __main__ - Step 84806: {'lr': 0.00020354568660268578, 'samples': 16282752, 'steps': 84805, 'loss/train': 1.011152982711792} 08/31/2021 04:32:09 - INFO - __main__ - Step 84807: {'lr': 0.00020354047228935969, 'samples': 16282944, 'steps': 84806, 'loss/train': 0.02445470355451107} 08/31/2021 04:32:09 - INFO - __main__ - Step 84808: {'lr': 0.00020353525799696756, 'samples': 16283136, 'steps': 84807, 'loss/train': 1.0519105195999146} 08/31/2021 04:32:11 - INFO - __main__ - Step 84809: {'lr': 0.00020353004372551173, 'samples': 16283328, 'steps': 84808, 'loss/train': 0.9490104913711548} 08/31/2021 04:32:11 - INFO - __main__ - Step 84810: {'lr': 0.00020352482947499453, 'samples': 16283520, 'steps': 84809, 'loss/train': 0.27174127101898193} 08/31/2021 04:32:12 - INFO - __main__ - Step 84811: {'lr': 0.00020351961524541835, 'samples': 16283712, 'steps': 84810, 'loss/train': 1.1247930526733398} 08/31/2021 04:32:12 - INFO - __main__ - Step 84812: {'lr': 0.0002035144010367855, 'samples': 16283904, 'steps': 84811, 'loss/train': 1.2807685136795044} 08/31/2021 04:32:12 - INFO - __main__ - Step 84813: {'lr': 0.00020350918684909836, 'samples': 16284096, 'steps': 84812, 'loss/train': 0.8115270733833313} 08/31/2021 04:32:15 - INFO - __main__ - Step 84814: {'lr': 0.00020350397268235922, 'samples': 16284288, 'steps': 84813, 'loss/train': 0.9552626609802246} 08/31/2021 04:32:15 - INFO - __main__ - Step 84815: {'lr': 0.00020349875853657061, 'samples': 16284480, 'steps': 84814, 'loss/train': 1.3833725452423096} 08/31/2021 04:32:15 - INFO - __main__ - Step 84816: {'lr': 0.00020349354441173464, 'samples': 16284672, 'steps': 84815, 'loss/train': 0.8574713468551636} 08/31/2021 04:32:16 - INFO - __main__ - Step 84817: {'lr': 0.00020348833030785378, 'samples': 16284864, 'steps': 84816, 'loss/train': 0.8844285607337952} 08/31/2021 04:32:16 - INFO - __main__ - Step 84818: {'lr': 0.00020348311622493033, 'samples': 16285056, 'steps': 84817, 'loss/train': 0.905114471912384} 08/31/2021 04:32:16 - INFO - __main__ - Step 84819: {'lr': 0.00020347790216296665, 'samples': 16285248, 'steps': 84818, 'loss/train': 0.020662905648350716} 08/31/2021 04:32:18 - INFO - __main__ - Step 84820: {'lr': 0.00020347268812196515, 'samples': 16285440, 'steps': 84819, 'loss/train': 1.4957475662231445} 08/31/2021 04:32:18 - INFO - __main__ - Step 84821: {'lr': 0.0002034674741019281, 'samples': 16285632, 'steps': 84820, 'loss/train': 0.5771607160568237} 08/31/2021 04:32:19 - INFO - __main__ - Step 84822: {'lr': 0.00020346226010285794, 'samples': 16285824, 'steps': 84821, 'loss/train': 1.3202786445617676} 08/31/2021 04:32:19 - INFO - __main__ - Step 84823: {'lr': 0.00020345704612475694, 'samples': 16286016, 'steps': 84822, 'loss/train': 0.7282024621963501} 08/31/2021 04:32:19 - INFO - __main__ - Step 84824: {'lr': 0.00020345183216762748, 'samples': 16286208, 'steps': 84823, 'loss/train': 1.560055136680603} 08/31/2021 04:32:21 - INFO - __main__ - Step 84825: {'lr': 0.0002034466182314719, 'samples': 16286400, 'steps': 84824, 'loss/train': 1.9633443355560303} 08/31/2021 04:32:21 - INFO - __main__ - Step 84826: {'lr': 0.00020344140431629256, 'samples': 16286592, 'steps': 84825, 'loss/train': 1.6554663181304932} 08/31/2021 04:32:22 - INFO - __main__ - Step 84827: {'lr': 0.00020343619042209176, 'samples': 16286784, 'steps': 84826, 'loss/train': 0.25026851892471313} 08/31/2021 04:32:22 - INFO - __main__ - Step 84828: {'lr': 0.0002034309765488721, 'samples': 16286976, 'steps': 84827, 'loss/train': 0.7310279607772827} 08/31/2021 04:32:22 - INFO - __main__ - Step 84829: {'lr': 0.00020342576269663553, 'samples': 16287168, 'steps': 84828, 'loss/train': 2.0977303981781006} 08/31/2021 04:32:24 - INFO - __main__ - Step 84830: {'lr': 0.00020342054886538465, 'samples': 16287360, 'steps': 84829, 'loss/train': 1.7014299631118774} 08/31/2021 04:32:24 - INFO - __main__ - Step 84831: {'lr': 0.0002034153350551217, 'samples': 16287552, 'steps': 84830, 'loss/train': 1.1543606519699097} 08/31/2021 04:32:25 - INFO - __main__ - Step 84832: {'lr': 0.0002034101212658491, 'samples': 16287744, 'steps': 84831, 'loss/train': 1.2362985610961914} 08/31/2021 04:32:25 - INFO - __main__ - Step 84833: {'lr': 0.0002034049074975692, 'samples': 16287936, 'steps': 84832, 'loss/train': 0.6823738217353821} 08/31/2021 04:32:25 - INFO - __main__ - Step 84834: {'lr': 0.0002033996937502843, 'samples': 16288128, 'steps': 84833, 'loss/train': 0.4336068332195282} 08/31/2021 04:32:27 - INFO - __main__ - Step 84835: {'lr': 0.00020339448002399679, 'samples': 16288320, 'steps': 84834, 'loss/train': 0.9969907402992249} 08/31/2021 04:32:27 - INFO - __main__ - Step 84836: {'lr': 0.00020338926631870903, 'samples': 16288512, 'steps': 84835, 'loss/train': 1.0105637311935425} 08/31/2021 04:32:27 - INFO - __main__ - Step 84837: {'lr': 0.00020338405263442333, 'samples': 16288704, 'steps': 84836, 'loss/train': 1.1201114654541016} 08/31/2021 04:32:28 - INFO - __main__ - Step 84838: {'lr': 0.00020337883897114203, 'samples': 16288896, 'steps': 84837, 'loss/train': 0.7309637069702148} 08/31/2021 04:32:28 - INFO - __main__ - Step 84839: {'lr': 0.00020337362532886756, 'samples': 16289088, 'steps': 84838, 'loss/train': 0.255204439163208} 08/31/2021 04:32:30 - INFO - __main__ - Step 84840: {'lr': 0.00020336841170760217, 'samples': 16289280, 'steps': 84839, 'loss/train': 1.2861063480377197} 08/31/2021 04:32:30 - INFO - __main__ - Step 84841: {'lr': 0.00020336319810734837, 'samples': 16289472, 'steps': 84840, 'loss/train': 0.5218310356140137} 08/31/2021 04:32:31 - INFO - __main__ - Step 84842: {'lr': 0.0002033579845281083, 'samples': 16289664, 'steps': 84841, 'loss/train': 1.0659668445587158} 08/31/2021 04:32:31 - INFO - __main__ - Step 84843: {'lr': 0.0002033527709698844, 'samples': 16289856, 'steps': 84842, 'loss/train': 1.3113114833831787} 08/31/2021 04:32:31 - INFO - __main__ - Step 84844: {'lr': 0.00020334755743267903, 'samples': 16290048, 'steps': 84843, 'loss/train': 1.084106206893921} 08/31/2021 04:32:32 - INFO - __main__ - Step 84845: {'lr': 0.0002033423439164945, 'samples': 16290240, 'steps': 84844, 'loss/train': 1.7254225015640259} 08/31/2021 04:32:33 - INFO - __main__ - Step 84846: {'lr': 0.00020333713042133323, 'samples': 16290432, 'steps': 84845, 'loss/train': 1.1028248071670532} 08/31/2021 04:32:34 - INFO - __main__ - Step 84847: {'lr': 0.0002033319169471975, 'samples': 16290624, 'steps': 84846, 'loss/train': 1.6729251146316528} 08/31/2021 04:32:34 - INFO - __main__ - Step 84848: {'lr': 0.00020332670349408968, 'samples': 16290816, 'steps': 84847, 'loss/train': 1.1170830726623535} 08/31/2021 04:32:34 - INFO - __main__ - Step 84849: {'lr': 0.00020332149006201217, 'samples': 16291008, 'steps': 84848, 'loss/train': 1.59390127658844} 08/31/2021 04:32:35 - INFO - __main__ - Step 84850: {'lr': 0.00020331627665096723, 'samples': 16291200, 'steps': 84849, 'loss/train': 1.4912821054458618} 08/31/2021 04:32:36 - INFO - __main__ - Step 84851: {'lr': 0.00020331106326095728, 'samples': 16291392, 'steps': 84850, 'loss/train': 1.509232997894287} 08/31/2021 04:32:37 - INFO - __main__ - Step 84852: {'lr': 0.00020330584989198465, 'samples': 16291584, 'steps': 84851, 'loss/train': 1.289096474647522} 08/31/2021 04:32:37 - INFO - __main__ - Step 84853: {'lr': 0.0002033006365440517, 'samples': 16291776, 'steps': 84852, 'loss/train': 1.315247893333435} 08/31/2021 04:32:37 - INFO - __main__ - Step 84854: {'lr': 0.0002032954232171607, 'samples': 16291968, 'steps': 84853, 'loss/train': 1.538138747215271} 08/31/2021 04:32:38 - INFO - __main__ - Step 84855: {'lr': 0.0002032902099113142, 'samples': 16292160, 'steps': 84854, 'loss/train': 1.3115777969360352} 08/31/2021 04:32:40 - INFO - __main__ - Step 84856: {'lr': 0.0002032849966265143, 'samples': 16292352, 'steps': 84855, 'loss/train': 0.9034084677696228} 08/31/2021 04:32:40 - INFO - __main__ - Step 84857: {'lr': 0.0002032797833627635, 'samples': 16292544, 'steps': 84856, 'loss/train': 1.227455496788025} 08/31/2021 04:32:41 - INFO - __main__ - Step 84858: {'lr': 0.00020327457012006407, 'samples': 16292736, 'steps': 84857, 'loss/train': 0.8816849589347839} 08/31/2021 04:32:41 - INFO - __main__ - Step 84859: {'lr': 0.00020326935689841838, 'samples': 16292928, 'steps': 84858, 'loss/train': 1.8449662923812866} 08/31/2021 04:32:41 - INFO - __main__ - Step 84860: {'lr': 0.00020326414369782885, 'samples': 16293120, 'steps': 84859, 'loss/train': 0.6491222381591797} 08/31/2021 04:32:43 - INFO - __main__ - Step 84861: {'lr': 0.00020325893051829772, 'samples': 16293312, 'steps': 84860, 'loss/train': 0.8284891843795776} 08/31/2021 04:32:43 - INFO - __main__ - Step 84862: {'lr': 0.0002032537173598274, 'samples': 16293504, 'steps': 84861, 'loss/train': 1.3272264003753662} 08/31/2021 04:32:44 - INFO - __main__ - Step 84863: {'lr': 0.00020324850422242028, 'samples': 16293696, 'steps': 84862, 'loss/train': 1.278389811515808} 08/31/2021 04:32:44 - INFO - __main__ - Step 84864: {'lr': 0.00020324329110607865, 'samples': 16293888, 'steps': 84863, 'loss/train': 0.7204024791717529} 08/31/2021 04:32:44 - INFO - __main__ - Step 84865: {'lr': 0.00020323807801080486, 'samples': 16294080, 'steps': 84864, 'loss/train': 0.7098343968391418} 08/31/2021 04:32:46 - INFO - __main__ - Step 84866: {'lr': 0.00020323286493660126, 'samples': 16294272, 'steps': 84865, 'loss/train': 1.4102997779846191} 08/31/2021 04:32:46 - INFO - __main__ - Step 84867: {'lr': 0.0002032276518834702, 'samples': 16294464, 'steps': 84866, 'loss/train': 1.6620584726333618} 08/31/2021 04:32:47 - INFO - __main__ - Step 84868: {'lr': 0.00020322243885141417, 'samples': 16294656, 'steps': 84867, 'loss/train': 0.9186716675758362} 08/31/2021 04:32:47 - INFO - __main__ - Step 84869: {'lr': 0.00020321722584043528, 'samples': 16294848, 'steps': 84868, 'loss/train': 1.0690208673477173} 08/31/2021 04:32:47 - INFO - __main__ - Step 84870: {'lr': 0.000203212012850536, 'samples': 16295040, 'steps': 84869, 'loss/train': 1.2625724077224731} 08/31/2021 04:32:49 - INFO - __main__ - Step 84871: {'lr': 0.00020320679988171863, 'samples': 16295232, 'steps': 84870, 'loss/train': 0.28006017208099365} 08/31/2021 04:32:49 - INFO - __main__ - Step 84872: {'lr': 0.00020320158693398554, 'samples': 16295424, 'steps': 84871, 'loss/train': 0.9492990374565125} 08/31/2021 04:32:50 - INFO - __main__ - Step 84873: {'lr': 0.00020319637400733915, 'samples': 16295616, 'steps': 84872, 'loss/train': 1.1328092813491821} 08/31/2021 04:32:50 - INFO - __main__ - Step 84874: {'lr': 0.0002031911611017817, 'samples': 16295808, 'steps': 84873, 'loss/train': 0.38246414065361023} 08/31/2021 04:32:50 - INFO - __main__ - Step 84875: {'lr': 0.0002031859482173156, 'samples': 16296000, 'steps': 84874, 'loss/train': 1.1666903495788574} 08/31/2021 04:32:51 - INFO - __main__ - Step 84876: {'lr': 0.00020318073535394325, 'samples': 16296192, 'steps': 84875, 'loss/train': 0.8179662227630615} 08/31/2021 04:32:52 - INFO - __main__ - Step 84877: {'lr': 0.00020317552251166687, 'samples': 16296384, 'steps': 84876, 'loss/train': 1.1581073999404907} 08/31/2021 04:32:53 - INFO - __main__ - Step 84878: {'lr': 0.00020317030969048888, 'samples': 16296576, 'steps': 84877, 'loss/train': 1.4506322145462036} 08/31/2021 04:32:53 - INFO - __main__ - Step 84879: {'lr': 0.00020316509689041168, 'samples': 16296768, 'steps': 84878, 'loss/train': 0.6495543122291565} 08/31/2021 04:32:53 - INFO - __main__ - Step 84880: {'lr': 0.00020315988411143753, 'samples': 16296960, 'steps': 84879, 'loss/train': 0.850400447845459} 08/31/2021 04:32:54 - INFO - __main__ - Step 84881: {'lr': 0.0002031546713535688, 'samples': 16297152, 'steps': 84880, 'loss/train': 1.3822669982910156} 08/31/2021 04:32:55 - INFO - __main__ - Step 84882: {'lr': 0.00020314945861680798, 'samples': 16297344, 'steps': 84881, 'loss/train': 1.2375943660736084} 08/31/2021 04:32:56 - INFO - __main__ - Step 84883: {'lr': 0.00020314424590115715, 'samples': 16297536, 'steps': 84882, 'loss/train': 0.944474458694458} 08/31/2021 04:32:56 - INFO - __main__ - Step 84884: {'lr': 0.00020313903320661885, 'samples': 16297728, 'steps': 84883, 'loss/train': 1.4278966188430786} 08/31/2021 04:32:56 - INFO - __main__ - Step 84885: {'lr': 0.00020313382053319535, 'samples': 16297920, 'steps': 84884, 'loss/train': 1.596185564994812} 08/31/2021 04:32:57 - INFO - __main__ - Step 84886: {'lr': 0.00020312860788088903, 'samples': 16298112, 'steps': 84885, 'loss/train': 0.9816408753395081} 08/31/2021 04:32:58 - INFO - __main__ - Step 84887: {'lr': 0.00020312339524970226, 'samples': 16298304, 'steps': 84886, 'loss/train': 1.2088395357131958} 08/31/2021 04:32:59 - INFO - __main__ - Step 84888: {'lr': 0.00020311818263963732, 'samples': 16298496, 'steps': 84887, 'loss/train': 1.098998785018921} 08/31/2021 04:32:59 - INFO - __main__ - Step 84889: {'lr': 0.00020311297005069662, 'samples': 16298688, 'steps': 84888, 'loss/train': 1.3085600137710571} 08/31/2021 04:32:59 - INFO - __main__ - Step 84890: {'lr': 0.0002031077574828825, 'samples': 16298880, 'steps': 84889, 'loss/train': 0.5627284646034241} 08/31/2021 04:33:00 - INFO - __main__ - Step 84891: {'lr': 0.00020310254493619728, 'samples': 16299072, 'steps': 84890, 'loss/train': 1.5647327899932861} 08/31/2021 04:33:01 - INFO - __main__ - Step 84892: {'lr': 0.00020309733241064337, 'samples': 16299264, 'steps': 84891, 'loss/train': 1.0290333032608032} 08/31/2021 04:33:02 - INFO - __main__ - Step 84893: {'lr': 0.00020309211990622307, 'samples': 16299456, 'steps': 84892, 'loss/train': 0.8706345558166504} 08/31/2021 04:33:02 - INFO - __main__ - Step 84894: {'lr': 0.00020308690742293876, 'samples': 16299648, 'steps': 84893, 'loss/train': 1.4388803243637085} 08/31/2021 04:33:02 - INFO - __main__ - Step 84895: {'lr': 0.0002030816949607928, 'samples': 16299840, 'steps': 84894, 'loss/train': 1.5354833602905273} 08/31/2021 04:33:03 - INFO - __main__ - Step 84896: {'lr': 0.00020307648251978742, 'samples': 16300032, 'steps': 84895, 'loss/train': 1.133060336112976} 08/31/2021 04:33:03 - INFO - __main__ - Step 84897: {'lr': 0.00020307127009992505, 'samples': 16300224, 'steps': 84896, 'loss/train': 1.7028815746307373} 08/31/2021 04:33:05 - INFO - __main__ - Step 84898: {'lr': 0.00020306605770120805, 'samples': 16300416, 'steps': 84897, 'loss/train': 1.4880117177963257} 08/31/2021 04:33:05 - INFO - __main__ - Step 84899: {'lr': 0.00020306084532363878, 'samples': 16300608, 'steps': 84898, 'loss/train': 1.2532944679260254} 08/31/2021 04:33:05 - INFO - __main__ - Step 84900: {'lr': 0.00020305563296721957, 'samples': 16300800, 'steps': 84899, 'loss/train': 1.1205652952194214} 08/31/2021 04:33:06 - INFO - __main__ - Step 84901: {'lr': 0.00020305042063195275, 'samples': 16300992, 'steps': 84900, 'loss/train': 1.5823655128479004} 08/31/2021 04:33:06 - INFO - __main__ - Step 84902: {'lr': 0.00020304520831784068, 'samples': 16301184, 'steps': 84901, 'loss/train': 1.5921088457107544} 08/31/2021 04:33:08 - INFO - __main__ - Step 84903: {'lr': 0.00020303999602488574, 'samples': 16301376, 'steps': 84902, 'loss/train': 0.7596609592437744} 08/31/2021 04:33:08 - INFO - __main__ - Step 84904: {'lr': 0.00020303478375309023, 'samples': 16301568, 'steps': 84903, 'loss/train': 1.11794912815094} 08/31/2021 04:33:08 - INFO - __main__ - Step 84905: {'lr': 0.00020302957150245658, 'samples': 16301760, 'steps': 84904, 'loss/train': 1.095254898071289} 08/31/2021 04:33:09 - INFO - __main__ - Step 84906: {'lr': 0.000203024359272987, 'samples': 16301952, 'steps': 84905, 'loss/train': 1.1306511163711548} 08/31/2021 04:33:09 - INFO - __main__ - Step 84907: {'lr': 0.00020301914706468397, 'samples': 16302144, 'steps': 84906, 'loss/train': 0.5897401571273804} 08/31/2021 04:33:11 - INFO - __main__ - Step 84908: {'lr': 0.00020301393487754977, 'samples': 16302336, 'steps': 84907, 'loss/train': 1.11453378200531} 08/31/2021 04:33:12 - INFO - __main__ - Step 84909: {'lr': 0.00020300872271158683, 'samples': 16302528, 'steps': 84908, 'loss/train': 1.5657281875610352} 08/31/2021 04:33:12 - INFO - __main__ - Step 84910: {'lr': 0.00020300351056679736, 'samples': 16302720, 'steps': 84909, 'loss/train': 0.83599853515625} 08/31/2021 04:33:13 - INFO - __main__ - Step 84911: {'lr': 0.0002029982984431838, 'samples': 16302912, 'steps': 84910, 'loss/train': 1.2419377565383911} 08/31/2021 04:33:13 - INFO - __main__ - Step 84912: {'lr': 0.00020299308634074846, 'samples': 16303104, 'steps': 84911, 'loss/train': 1.011865258216858} 08/31/2021 04:33:13 - INFO - __main__ - Step 84913: {'lr': 0.00020298787425949372, 'samples': 16303296, 'steps': 84912, 'loss/train': 0.018482206389307976} 08/31/2021 04:33:15 - INFO - __main__ - Step 84914: {'lr': 0.0002029826621994219, 'samples': 16303488, 'steps': 84913, 'loss/train': 1.2104600667953491} 08/31/2021 04:33:15 - INFO - __main__ - Step 84915: {'lr': 0.00020297745016053539, 'samples': 16303680, 'steps': 84914, 'loss/train': 1.5982879400253296} 08/31/2021 04:33:16 - INFO - __main__ - Step 84916: {'lr': 0.00020297223814283658, 'samples': 16303872, 'steps': 84915, 'loss/train': 2.2397849559783936} 08/31/2021 04:33:16 - INFO - __main__ - Step 84917: {'lr': 0.00020296702614632767, 'samples': 16304064, 'steps': 84916, 'loss/train': 0.9503352642059326} 08/31/2021 04:33:17 - INFO - __main__ - Step 84918: {'lr': 0.0002029618141710111, 'samples': 16304256, 'steps': 84917, 'loss/train': 0.9707450270652771} 08/31/2021 04:33:18 - INFO - __main__ - Step 84919: {'lr': 0.00020295660221688922, 'samples': 16304448, 'steps': 84918, 'loss/train': 0.8964095115661621} 08/31/2021 04:33:18 - INFO - __main__ - Step 84920: {'lr': 0.00020295139028396437, 'samples': 16304640, 'steps': 84919, 'loss/train': 1.4740769863128662} 08/31/2021 04:33:19 - INFO - __main__ - Step 84921: {'lr': 0.0002029461783722389, 'samples': 16304832, 'steps': 84920, 'loss/train': 0.9053316712379456} 08/31/2021 04:33:19 - INFO - __main__ - Step 84922: {'lr': 0.0002029409664817152, 'samples': 16305024, 'steps': 84921, 'loss/train': 1.496065616607666} 08/31/2021 04:33:20 - INFO - __main__ - Step 84923: {'lr': 0.00020293575461239553, 'samples': 16305216, 'steps': 84922, 'loss/train': 1.0438610315322876} 08/31/2021 04:33:21 - INFO - __main__ - Step 84924: {'lr': 0.00020293054276428226, 'samples': 16305408, 'steps': 84923, 'loss/train': 1.0267106294631958} 08/31/2021 04:33:22 - INFO - __main__ - Step 84925: {'lr': 0.0002029253309373778, 'samples': 16305600, 'steps': 84924, 'loss/train': 1.223430871963501} 08/31/2021 04:33:22 - INFO - __main__ - Step 84926: {'lr': 0.00020292011913168449, 'samples': 16305792, 'steps': 84925, 'loss/train': 1.305324912071228} 08/31/2021 04:33:22 - INFO - __main__ - Step 84927: {'lr': 0.0002029149073472046, 'samples': 16305984, 'steps': 84926, 'loss/train': 1.184288740158081} 08/31/2021 04:33:23 - INFO - __main__ - Step 84928: {'lr': 0.00020290969558394052, 'samples': 16306176, 'steps': 84927, 'loss/train': 0.7795431017875671} 08/31/2021 04:33:24 - INFO - __main__ - Step 84929: {'lr': 0.00020290448384189462, 'samples': 16306368, 'steps': 84928, 'loss/train': 1.543953537940979} 08/31/2021 04:33:25 - INFO - __main__ - Step 84930: {'lr': 0.0002028992721210692, 'samples': 16306560, 'steps': 84929, 'loss/train': 1.2391867637634277} 08/31/2021 04:33:25 - INFO - __main__ - Step 84931: {'lr': 0.00020289406042146667, 'samples': 16306752, 'steps': 84930, 'loss/train': 0.6907256841659546} 08/31/2021 04:33:26 - INFO - __main__ - Step 84932: {'lr': 0.00020288884874308932, 'samples': 16306944, 'steps': 84931, 'loss/train': 0.03220343962311745} 08/31/2021 04:33:26 - INFO - __main__ - Step 84933: {'lr': 0.00020288363708593956, 'samples': 16307136, 'steps': 84932, 'loss/train': 0.7189399600028992} 08/31/2021 04:33:27 - INFO - __main__ - Step 84934: {'lr': 0.0002028784254500197, 'samples': 16307328, 'steps': 84933, 'loss/train': 0.020773353055119514} 08/31/2021 04:33:28 - INFO - __main__ - Step 84935: {'lr': 0.00020287321383533207, 'samples': 16307520, 'steps': 84934, 'loss/train': 1.430877447128296} 08/31/2021 04:33:28 - INFO - __main__ - Step 84936: {'lr': 0.00020286800224187914, 'samples': 16307712, 'steps': 84935, 'loss/train': 0.8347545266151428} 08/31/2021 04:33:29 - INFO - __main__ - Step 84937: {'lr': 0.00020286279066966312, 'samples': 16307904, 'steps': 84936, 'loss/train': 2.020962715148926} 08/31/2021 04:33:29 - INFO - __main__ - Step 84938: {'lr': 0.00020285757911868635, 'samples': 16308096, 'steps': 84937, 'loss/train': 1.0328357219696045} 08/31/2021 04:33:31 - INFO - __main__ - Step 84939: {'lr': 0.00020285236758895125, 'samples': 16308288, 'steps': 84938, 'loss/train': 0.925250232219696} 08/31/2021 04:33:31 - INFO - __main__ - Step 84940: {'lr': 0.00020284715608046014, 'samples': 16308480, 'steps': 84939, 'loss/train': 0.8705142140388489} 08/31/2021 04:33:31 - INFO - __main__ - Step 84941: {'lr': 0.00020284194459321538, 'samples': 16308672, 'steps': 84940, 'loss/train': 1.066577434539795} 08/31/2021 04:33:32 - INFO - __main__ - Step 84942: {'lr': 0.0002028367331272193, 'samples': 16308864, 'steps': 84941, 'loss/train': 1.6231679916381836} 08/31/2021 04:33:32 - INFO - __main__ - Step 84943: {'lr': 0.00020283152168247423, 'samples': 16309056, 'steps': 84942, 'loss/train': 1.5210179090499878} 08/31/2021 04:33:34 - INFO - __main__ - Step 84944: {'lr': 0.0002028263102589826, 'samples': 16309248, 'steps': 84943, 'loss/train': 1.3267213106155396} 08/31/2021 04:33:34 - INFO - __main__ - Step 84945: {'lr': 0.00020282109885674668, 'samples': 16309440, 'steps': 84944, 'loss/train': 0.5412212610244751} 08/31/2021 04:33:35 - INFO - __main__ - Step 84946: {'lr': 0.00020281588747576883, 'samples': 16309632, 'steps': 84945, 'loss/train': 1.5912619829177856} 08/31/2021 04:33:35 - INFO - __main__ - Step 84947: {'lr': 0.00020281067611605146, 'samples': 16309824, 'steps': 84946, 'loss/train': 0.9978020787239075} 08/31/2021 04:33:35 - INFO - __main__ - Step 84948: {'lr': 0.00020280546477759686, 'samples': 16310016, 'steps': 84947, 'loss/train': 0.8543598055839539} 08/31/2021 04:33:36 - INFO - __main__ - Step 84949: {'lr': 0.00020280025346040744, 'samples': 16310208, 'steps': 84948, 'loss/train': 1.3278310298919678} 08/31/2021 04:33:37 - INFO - __main__ - Step 84950: {'lr': 0.00020279504216448547, 'samples': 16310400, 'steps': 84949, 'loss/train': 1.487207055091858} 08/31/2021 04:33:38 - INFO - __main__ - Step 84951: {'lr': 0.00020278983088983327, 'samples': 16310592, 'steps': 84950, 'loss/train': 1.2688030004501343} 08/31/2021 04:33:38 - INFO - __main__ - Step 84952: {'lr': 0.00020278461963645325, 'samples': 16310784, 'steps': 84951, 'loss/train': 0.9102261662483215} 08/31/2021 04:33:38 - INFO - __main__ - Step 84953: {'lr': 0.00020277940840434777, 'samples': 16310976, 'steps': 84952, 'loss/train': 1.3616594076156616} 08/31/2021 04:33:39 - INFO - __main__ - Step 84954: {'lr': 0.00020277419719351913, 'samples': 16311168, 'steps': 84953, 'loss/train': 0.9667484164237976} 08/31/2021 04:33:40 - INFO - __main__ - Step 84955: {'lr': 0.00020276898600396975, 'samples': 16311360, 'steps': 84954, 'loss/train': 1.3095694780349731} 08/31/2021 04:33:41 - INFO - __main__ - Step 84956: {'lr': 0.0002027637748357019, 'samples': 16311552, 'steps': 84955, 'loss/train': 0.9998411536216736} 08/31/2021 04:33:41 - INFO - __main__ - Step 84957: {'lr': 0.000202758563688718, 'samples': 16311744, 'steps': 84956, 'loss/train': 0.8564178943634033} 08/31/2021 04:33:41 - INFO - __main__ - Step 84958: {'lr': 0.00020275335256302035, 'samples': 16311936, 'steps': 84957, 'loss/train': 0.05159386992454529} 08/31/2021 04:33:42 - INFO - __main__ - Step 84959: {'lr': 0.00020274814145861128, 'samples': 16312128, 'steps': 84958, 'loss/train': 1.242299199104309} 08/31/2021 04:33:44 - INFO - __main__ - Step 84960: {'lr': 0.0002027429303754932, 'samples': 16312320, 'steps': 84959, 'loss/train': 1.6610933542251587} 08/31/2021 04:33:44 - INFO - __main__ - Step 84961: {'lr': 0.00020273771931366842, 'samples': 16312512, 'steps': 84960, 'loss/train': 1.13578462600708} 08/31/2021 04:33:44 - INFO - __main__ - Step 84962: {'lr': 0.0002027325082731394, 'samples': 16312704, 'steps': 84961, 'loss/train': 0.9373626112937927} 08/31/2021 04:33:45 - INFO - __main__ - Step 84963: {'lr': 0.00020272729725390827, 'samples': 16312896, 'steps': 84962, 'loss/train': 0.4857926368713379} 08/31/2021 04:33:45 - INFO - __main__ - Step 84964: {'lr': 0.0002027220862559775, 'samples': 16313088, 'steps': 84963, 'loss/train': 1.800171136856079} 08/31/2021 04:33:46 - INFO - __main__ - Step 84965: {'lr': 0.00020271687527934944, 'samples': 16313280, 'steps': 84964, 'loss/train': 1.00052809715271} 08/31/2021 04:33:47 - INFO - __main__ - Step 84966: {'lr': 0.00020271166432402638, 'samples': 16313472, 'steps': 84965, 'loss/train': 0.9243264198303223} 08/31/2021 04:33:48 - INFO - __main__ - Step 84967: {'lr': 0.00020270645339001076, 'samples': 16313664, 'steps': 84966, 'loss/train': 1.0561482906341553} 08/31/2021 04:33:48 - INFO - __main__ - Step 84968: {'lr': 0.00020270124247730487, 'samples': 16313856, 'steps': 84967, 'loss/train': 1.4969018697738647} 08/31/2021 04:33:48 - INFO - __main__ - Step 84969: {'lr': 0.00020269603158591104, 'samples': 16314048, 'steps': 84968, 'loss/train': 0.41058292984962463} 08/31/2021 04:33:49 - INFO - __main__ - Step 84970: {'lr': 0.0002026908207158317, 'samples': 16314240, 'steps': 84969, 'loss/train': 0.7749044895172119} 08/31/2021 04:33:50 - INFO - __main__ - Step 84971: {'lr': 0.0002026856098670691, 'samples': 16314432, 'steps': 84970, 'loss/train': 0.6319014430046082} 08/31/2021 04:33:50 - INFO - __main__ - Step 84972: {'lr': 0.00020268039903962565, 'samples': 16314624, 'steps': 84971, 'loss/train': 0.1452242136001587} 08/31/2021 04:33:51 - INFO - __main__ - Step 84973: {'lr': 0.0002026751882335037, 'samples': 16314816, 'steps': 84972, 'loss/train': 1.0555669069290161} 08/31/2021 04:33:51 - INFO - __main__ - Step 84974: {'lr': 0.00020266997744870557, 'samples': 16315008, 'steps': 84973, 'loss/train': 1.0717898607254028} 08/31/2021 04:33:51 - INFO - __main__ - Step 84975: {'lr': 0.00020266476668523363, 'samples': 16315200, 'steps': 84974, 'loss/train': 0.8893710374832153} 08/31/2021 04:33:53 - INFO - __main__ - Step 84976: {'lr': 0.0002026595559430903, 'samples': 16315392, 'steps': 84975, 'loss/train': 1.9794516563415527} 08/31/2021 04:33:54 - INFO - __main__ - Step 84977: {'lr': 0.00020265434522227774, 'samples': 16315584, 'steps': 84976, 'loss/train': 1.566311001777649} 08/31/2021 04:33:54 - INFO - __main__ - Step 84978: {'lr': 0.0002026491345227984, 'samples': 16315776, 'steps': 84977, 'loss/train': 5.730052471160889} 08/31/2021 04:33:54 - INFO - __main__ - Step 84979: {'lr': 0.00020264392384465463, 'samples': 16315968, 'steps': 84978, 'loss/train': 1.0827559232711792} 08/31/2021 04:33:55 - INFO - __main__ - Step 84980: {'lr': 0.0002026387131878488, 'samples': 16316160, 'steps': 84979, 'loss/train': 1.1141239404678345} 08/31/2021 04:33:55 - INFO - __main__ - Step 84981: {'lr': 0.00020263350255238322, 'samples': 16316352, 'steps': 84980, 'loss/train': 0.7698062062263489} 08/31/2021 04:33:57 - INFO - __main__ - Step 84982: {'lr': 0.00020262829193826024, 'samples': 16316544, 'steps': 84981, 'loss/train': 1.3143103122711182} 08/31/2021 04:33:57 - INFO - __main__ - Step 84983: {'lr': 0.00020262308134548224, 'samples': 16316736, 'steps': 84982, 'loss/train': 1.166740894317627} 08/31/2021 04:33:58 - INFO - __main__ - Step 84984: {'lr': 0.00020261787077405154, 'samples': 16316928, 'steps': 84983, 'loss/train': 1.6166960000991821} 08/31/2021 04:33:58 - INFO - __main__ - Step 84985: {'lr': 0.00020261266022397048, 'samples': 16317120, 'steps': 84984, 'loss/train': 1.1088476181030273} 08/31/2021 04:33:58 - INFO - __main__ - Step 84986: {'lr': 0.00020260744969524146, 'samples': 16317312, 'steps': 84985, 'loss/train': 1.2013497352600098} 08/31/2021 04:34:00 - INFO - __main__ - Step 84987: {'lr': 0.00020260223918786675, 'samples': 16317504, 'steps': 84986, 'loss/train': 1.4673161506652832} 08/31/2021 04:34:00 - INFO - __main__ - Step 84988: {'lr': 0.00020259702870184876, 'samples': 16317696, 'steps': 84987, 'loss/train': 1.4237459897994995} 08/31/2021 04:34:01 - INFO - __main__ - Step 84989: {'lr': 0.00020259181823718993, 'samples': 16317888, 'steps': 84988, 'loss/train': 0.8658033013343811} 08/31/2021 04:34:01 - INFO - __main__ - Step 84990: {'lr': 0.00020258660779389238, 'samples': 16318080, 'steps': 84989, 'loss/train': 1.1952215433120728} 08/31/2021 04:34:01 - INFO - __main__ - Step 84991: {'lr': 0.00020258139737195857, 'samples': 16318272, 'steps': 84990, 'loss/train': 1.1787806749343872} 08/31/2021 04:34:03 - INFO - __main__ - Step 84992: {'lr': 0.00020257618697139086, 'samples': 16318464, 'steps': 84991, 'loss/train': 0.6128515601158142} 08/31/2021 04:34:03 - INFO - __main__ - Step 84993: {'lr': 0.0002025709765921916, 'samples': 16318656, 'steps': 84992, 'loss/train': 0.03517666086554527} 08/31/2021 04:34:04 - INFO - __main__ - Step 84994: {'lr': 0.0002025657662343631, 'samples': 16318848, 'steps': 84993, 'loss/train': 0.768079936504364} 08/31/2021 04:34:04 - INFO - __main__ - Step 84995: {'lr': 0.00020256055589790771, 'samples': 16319040, 'steps': 84994, 'loss/train': 1.150542140007019} 08/31/2021 04:34:04 - INFO - __main__ - Step 84996: {'lr': 0.00020255534558282786, 'samples': 16319232, 'steps': 84995, 'loss/train': 0.5390722155570984} 08/31/2021 04:34:06 - INFO - __main__ - Step 84997: {'lr': 0.00020255013528912584, 'samples': 16319424, 'steps': 84996, 'loss/train': 1.5297746658325195} 08/31/2021 04:34:06 - INFO - __main__ - Step 84998: {'lr': 0.00020254492501680396, 'samples': 16319616, 'steps': 84997, 'loss/train': 1.1354522705078125} 08/31/2021 04:34:07 - INFO - __main__ - Step 84999: {'lr': 0.0002025397147658646, 'samples': 16319808, 'steps': 84998, 'loss/train': 1.1534966230392456} 08/31/2021 04:34:07 - INFO - __main__ - Step 85000: {'lr': 0.00020253450453631015, 'samples': 16320000, 'steps': 84999, 'loss/train': 0.5417101979255676} 08/31/2021 04:34:08 - INFO - __main__ - Step 85001: {'lr': 0.00020252929432814287, 'samples': 16320192, 'steps': 85000, 'loss/train': 1.5140894651412964} 08/31/2021 04:34:08 - INFO - __main__ - Step 85002: {'lr': 0.0002025240841413652, 'samples': 16320384, 'steps': 85001, 'loss/train': 2.0527451038360596} 08/31/2021 04:34:09 - INFO - __main__ - Step 85003: {'lr': 0.00020251887397597956, 'samples': 16320576, 'steps': 85002, 'loss/train': 1.0887728929519653} 08/31/2021 04:34:10 - INFO - __main__ - Step 85004: {'lr': 0.00020251366383198805, 'samples': 16320768, 'steps': 85003, 'loss/train': 1.4708439111709595} 08/31/2021 04:34:10 - INFO - __main__ - Step 85005: {'lr': 0.00020250845370939314, 'samples': 16320960, 'steps': 85004, 'loss/train': 1.8408750295639038} 08/31/2021 04:34:11 - INFO - __main__ - Step 85006: {'lr': 0.0002025032436081972, 'samples': 16321152, 'steps': 85005, 'loss/train': 0.7226660251617432} 08/31/2021 04:34:11 - INFO - __main__ - Step 85007: {'lr': 0.00020249803352840256, 'samples': 16321344, 'steps': 85006, 'loss/train': 1.447428584098816} 08/31/2021 04:34:12 - INFO - __main__ - Step 85008: {'lr': 0.0002024928234700116, 'samples': 16321536, 'steps': 85007, 'loss/train': 1.386142373085022} 08/31/2021 04:34:13 - INFO - __main__ - Step 85009: {'lr': 0.00020248761343302663, 'samples': 16321728, 'steps': 85008, 'loss/train': 0.9638626575469971} 08/31/2021 04:34:13 - INFO - __main__ - Step 85010: {'lr': 0.00020248240341745, 'samples': 16321920, 'steps': 85009, 'loss/train': 0.8457719087600708} 08/31/2021 04:34:14 - INFO - __main__ - Step 85011: {'lr': 0.00020247719342328404, 'samples': 16322112, 'steps': 85010, 'loss/train': 0.0810837596654892} 08/31/2021 04:34:14 - INFO - __main__ - Step 85012: {'lr': 0.00020247198345053116, 'samples': 16322304, 'steps': 85011, 'loss/train': 0.02695641852915287} 08/31/2021 04:34:15 - INFO - __main__ - Step 85013: {'lr': 0.00020246677349919367, 'samples': 16322496, 'steps': 85012, 'loss/train': 0.7178746461868286} 08/31/2021 04:34:16 - INFO - __main__ - Step 85014: {'lr': 0.00020246156356927393, 'samples': 16322688, 'steps': 85013, 'loss/train': 1.457735300064087} 08/31/2021 04:34:16 - INFO - __main__ - Step 85015: {'lr': 0.00020245635366077422, 'samples': 16322880, 'steps': 85014, 'loss/train': 0.6230224370956421} 08/31/2021 04:34:17 - INFO - __main__ - Step 85016: {'lr': 0.0002024511437736971, 'samples': 16323072, 'steps': 85015, 'loss/train': 1.3768068552017212} 08/31/2021 04:34:17 - INFO - __main__ - Step 85017: {'lr': 0.00020244593390804464, 'samples': 16323264, 'steps': 85016, 'loss/train': 0.9855383634567261} 08/31/2021 04:34:19 - INFO - __main__ - Step 85018: {'lr': 0.0002024407240638193, 'samples': 16323456, 'steps': 85017, 'loss/train': 1.2343775033950806} 08/31/2021 04:34:20 - INFO - __main__ - Step 85019: {'lr': 0.00020243551424102343, 'samples': 16323648, 'steps': 85018, 'loss/train': 0.8740812540054321} 08/31/2021 04:34:20 - INFO - __main__ - Step 85020: {'lr': 0.0002024303044396594, 'samples': 16323840, 'steps': 85019, 'loss/train': 1.0344469547271729} 08/31/2021 04:34:20 - INFO - __main__ - Step 85021: {'lr': 0.00020242509465972955, 'samples': 16324032, 'steps': 85020, 'loss/train': 1.4693344831466675} 08/31/2021 04:34:21 - INFO - __main__ - Step 85022: {'lr': 0.0002024198849012362, 'samples': 16324224, 'steps': 85021, 'loss/train': 0.4820970296859741} 08/31/2021 04:34:22 - INFO - __main__ - Step 85023: {'lr': 0.00020241467516418171, 'samples': 16324416, 'steps': 85022, 'loss/train': 0.3194655179977417} 08/31/2021 04:34:23 - INFO - __main__ - Step 85024: {'lr': 0.00020240946544856846, 'samples': 16324608, 'steps': 85023, 'loss/train': 1.6810001134872437} 08/31/2021 04:34:23 - INFO - __main__ - Step 85025: {'lr': 0.00020240425575439875, 'samples': 16324800, 'steps': 85024, 'loss/train': 1.3616338968276978} 08/31/2021 04:34:23 - INFO - __main__ - Step 85026: {'lr': 0.00020239904608167496, 'samples': 16324992, 'steps': 85025, 'loss/train': 1.4129949808120728} 08/31/2021 04:34:24 - INFO - __main__ - Step 85027: {'lr': 0.0002023938364303994, 'samples': 16325184, 'steps': 85026, 'loss/train': 1.4675236940383911} 08/31/2021 04:34:24 - INFO - __main__ - Step 85028: {'lr': 0.0002023886268005745, 'samples': 16325376, 'steps': 85027, 'loss/train': 1.1681846380233765} 08/31/2021 04:34:25 - INFO - __main__ - Step 85029: {'lr': 0.00020238341719220254, 'samples': 16325568, 'steps': 85028, 'loss/train': 1.0254396200180054} 08/31/2021 04:34:26 - INFO - __main__ - Step 85030: {'lr': 0.00020237820760528587, 'samples': 16325760, 'steps': 85029, 'loss/train': 0.3528350591659546} 08/31/2021 04:34:26 - INFO - __main__ - Step 85031: {'lr': 0.00020237299803982684, 'samples': 16325952, 'steps': 85030, 'loss/train': 1.189818263053894} 08/31/2021 04:34:27 - INFO - __main__ - Step 85032: {'lr': 0.0002023677884958278, 'samples': 16326144, 'steps': 85031, 'loss/train': 1.0878794193267822} 08/31/2021 04:34:27 - INFO - __main__ - Step 85033: {'lr': 0.0002023625789732911, 'samples': 16326336, 'steps': 85032, 'loss/train': 0.8302627801895142} 08/31/2021 04:34:28 - INFO - __main__ - Step 85034: {'lr': 0.00020235736947221906, 'samples': 16326528, 'steps': 85033, 'loss/train': 0.8787997364997864} 08/31/2021 04:34:29 - INFO - __main__ - Step 85035: {'lr': 0.00020235215999261406, 'samples': 16326720, 'steps': 85034, 'loss/train': 1.575711965560913} 08/31/2021 04:34:29 - INFO - __main__ - Step 85036: {'lr': 0.00020234695053447844, 'samples': 16326912, 'steps': 85035, 'loss/train': 0.9064432382583618} 08/31/2021 04:34:30 - INFO - __main__ - Step 85037: {'lr': 0.00020234174109781455, 'samples': 16327104, 'steps': 85036, 'loss/train': 0.5173043012619019} 08/31/2021 04:34:30 - INFO - __main__ - Step 85038: {'lr': 0.00020233653168262475, 'samples': 16327296, 'steps': 85037, 'loss/train': 0.9804704785346985} 08/31/2021 04:34:31 - INFO - __main__ - Step 85039: {'lr': 0.00020233132228891142, 'samples': 16327488, 'steps': 85038, 'loss/train': 0.5997515320777893} 08/31/2021 04:34:32 - INFO - __main__ - Step 85040: {'lr': 0.0002023261129166768, 'samples': 16327680, 'steps': 85039, 'loss/train': 0.9782964587211609} 08/31/2021 04:34:32 - INFO - __main__ - Step 85041: {'lr': 0.0002023209035659233, 'samples': 16327872, 'steps': 85040, 'loss/train': 1.0833157300949097} 08/31/2021 04:34:32 - INFO - __main__ - Step 85042: {'lr': 0.00020231569423665328, 'samples': 16328064, 'steps': 85041, 'loss/train': 1.4016841650009155} 08/31/2021 04:34:33 - INFO - __main__ - Step 85043: {'lr': 0.00020231048492886912, 'samples': 16328256, 'steps': 85042, 'loss/train': 1.2382959127426147} 08/31/2021 04:34:34 - INFO - __main__ - Step 85044: {'lr': 0.00020230527564257307, 'samples': 16328448, 'steps': 85043, 'loss/train': 1.1632733345031738} 08/31/2021 04:34:35 - INFO - __main__ - Step 85045: {'lr': 0.0002023000663777675, 'samples': 16328640, 'steps': 85044, 'loss/train': 1.0163429975509644} 08/31/2021 04:34:35 - INFO - __main__ - Step 85046: {'lr': 0.00020229485713445477, 'samples': 16328832, 'steps': 85045, 'loss/train': 1.4254074096679688} 08/31/2021 04:34:35 - INFO - __main__ - Step 85047: {'lr': 0.00020228964791263728, 'samples': 16329024, 'steps': 85046, 'loss/train': 0.9011194705963135} 08/31/2021 04:34:36 - INFO - __main__ - Step 85048: {'lr': 0.00020228443871231732, 'samples': 16329216, 'steps': 85047, 'loss/train': 0.5307168960571289} 08/31/2021 04:34:38 - INFO - __main__ - Step 85049: {'lr': 0.00020227922953349728, 'samples': 16329408, 'steps': 85048, 'loss/train': 2.391576051712036} 08/31/2021 04:34:38 - INFO - __main__ - Step 85050: {'lr': 0.00020227402037617954, 'samples': 16329600, 'steps': 85049, 'loss/train': 0.49921324849128723} 08/31/2021 04:34:38 - INFO - __main__ - Step 85051: {'lr': 0.0002022688112403663, 'samples': 16329792, 'steps': 85050, 'loss/train': 0.8655327558517456} 08/31/2021 04:34:39 - INFO - __main__ - Step 85052: {'lr': 0.00020226360212606003, 'samples': 16329984, 'steps': 85051, 'loss/train': 0.021511342376470566} 08/31/2021 04:34:39 - INFO - __main__ - Step 85053: {'lr': 0.00020225839303326305, 'samples': 16330176, 'steps': 85052, 'loss/train': 0.8424955010414124} 08/31/2021 04:34:40 - INFO - __main__ - Step 85054: {'lr': 0.00020225318396197768, 'samples': 16330368, 'steps': 85053, 'loss/train': 0.8778678178787231} 08/31/2021 04:34:41 - INFO - __main__ - Step 85055: {'lr': 0.00020224797491220627, 'samples': 16330560, 'steps': 85054, 'loss/train': 1.66426420211792} 08/31/2021 04:34:41 - INFO - __main__ - Step 85056: {'lr': 0.00020224276588395122, 'samples': 16330752, 'steps': 85055, 'loss/train': 1.169681429862976} 08/31/2021 04:34:42 - INFO - __main__ - Step 85057: {'lr': 0.00020223755687721488, 'samples': 16330944, 'steps': 85056, 'loss/train': 1.2710905075073242} 08/31/2021 04:34:42 - INFO - __main__ - Step 85058: {'lr': 0.00020223234789199952, 'samples': 16331136, 'steps': 85057, 'loss/train': 1.0638298988342285} 08/31/2021 04:34:42 - INFO - __main__ - Step 85059: {'lr': 0.0002022271389283075, 'samples': 16331328, 'steps': 85058, 'loss/train': 1.0133016109466553} 08/31/2021 04:34:44 - INFO - __main__ - Step 85060: {'lr': 0.0002022219299861412, 'samples': 16331520, 'steps': 85059, 'loss/train': 0.6929616332054138} 08/31/2021 04:34:44 - INFO - __main__ - Step 85061: {'lr': 0.00020221672106550303, 'samples': 16331712, 'steps': 85060, 'loss/train': 1.776059627532959} 08/31/2021 04:34:45 - INFO - __main__ - Step 85062: {'lr': 0.00020221151216639522, 'samples': 16331904, 'steps': 85061, 'loss/train': 1.2965972423553467} 08/31/2021 04:34:45 - INFO - __main__ - Step 85063: {'lr': 0.00020220630328882013, 'samples': 16332096, 'steps': 85062, 'loss/train': 1.2834950685501099} 08/31/2021 04:34:45 - INFO - __main__ - Step 85064: {'lr': 0.00020220109443278017, 'samples': 16332288, 'steps': 85063, 'loss/train': 1.3722209930419922} 08/31/2021 04:34:47 - INFO - __main__ - Step 85065: {'lr': 0.00020219588559827767, 'samples': 16332480, 'steps': 85064, 'loss/train': 1.5727344751358032} 08/31/2021 04:34:48 - INFO - __main__ - Step 85066: {'lr': 0.00020219067678531495, 'samples': 16332672, 'steps': 85065, 'loss/train': 1.6014469861984253} 08/31/2021 04:34:48 - INFO - __main__ - Step 85067: {'lr': 0.00020218546799389436, 'samples': 16332864, 'steps': 85066, 'loss/train': 2.4105989933013916} 08/31/2021 04:34:48 - INFO - __main__ - Step 85068: {'lr': 0.00020218025922401827, 'samples': 16333056, 'steps': 85067, 'loss/train': 1.0861965417861938} 08/31/2021 04:34:49 - INFO - __main__ - Step 85069: {'lr': 0.00020217505047568905, 'samples': 16333248, 'steps': 85068, 'loss/train': 1.3909943103790283} 08/31/2021 04:34:51 - INFO - __main__ - Step 85070: {'lr': 0.00020216984174890903, 'samples': 16333440, 'steps': 85069, 'loss/train': 1.0578242540359497} 08/31/2021 04:34:51 - INFO - __main__ - Step 85071: {'lr': 0.0002021646330436805, 'samples': 16333632, 'steps': 85070, 'loss/train': 0.35839807987213135} 08/31/2021 04:34:51 - INFO - __main__ - Step 85072: {'lr': 0.0002021594243600059, 'samples': 16333824, 'steps': 85071, 'loss/train': 1.4952502250671387} 08/31/2021 04:34:52 - INFO - __main__ - Step 85073: {'lr': 0.00020215421569788746, 'samples': 16334016, 'steps': 85072, 'loss/train': 0.875522792339325} 08/31/2021 04:34:52 - INFO - __main__ - Step 85074: {'lr': 0.00020214900705732761, 'samples': 16334208, 'steps': 85073, 'loss/train': 1.2520830631256104} 08/31/2021 04:34:52 - INFO - __main__ - Step 85075: {'lr': 0.00020214379843832867, 'samples': 16334400, 'steps': 85074, 'loss/train': 1.6269744634628296} 08/31/2021 04:34:54 - INFO - __main__ - Step 85076: {'lr': 0.00020213858984089301, 'samples': 16334592, 'steps': 85075, 'loss/train': 1.1301215887069702} 08/31/2021 04:34:55 - INFO - __main__ - Step 85077: {'lr': 0.00020213338126502295, 'samples': 16334784, 'steps': 85076, 'loss/train': 0.6240871548652649} 08/31/2021 04:34:55 - INFO - __main__ - Step 85078: {'lr': 0.00020212817271072085, 'samples': 16334976, 'steps': 85077, 'loss/train': 1.284735083580017} 08/31/2021 04:34:55 - INFO - __main__ - Step 85079: {'lr': 0.00020212296417798905, 'samples': 16335168, 'steps': 85078, 'loss/train': 1.599229335784912} 08/31/2021 04:34:56 - INFO - __main__ - Step 85080: {'lr': 0.00020211775566682992, 'samples': 16335360, 'steps': 85079, 'loss/train': 0.823249101638794} 08/31/2021 04:34:57 - INFO - __main__ - Step 85081: {'lr': 0.0002021125471772458, 'samples': 16335552, 'steps': 85080, 'loss/train': 1.7091926336288452} 08/31/2021 04:34:57 - INFO - __main__ - Step 85082: {'lr': 0.00020210733870923897, 'samples': 16335744, 'steps': 85081, 'loss/train': 2.0878615379333496} 08/31/2021 04:34:58 - INFO - __main__ - Step 85083: {'lr': 0.000202102130262812, 'samples': 16335936, 'steps': 85082, 'loss/train': 1.4675565958023071} 08/31/2021 04:34:58 - INFO - __main__ - Step 85084: {'lr': 0.00020209692183796696, 'samples': 16336128, 'steps': 85083, 'loss/train': 1.4114450216293335} 08/31/2021 04:34:58 - INFO - __main__ - Step 85085: {'lr': 0.00020209171343470628, 'samples': 16336320, 'steps': 85084, 'loss/train': 1.2628028392791748} 08/31/2021 04:35:00 - INFO - __main__ - Step 85086: {'lr': 0.00020208650505303233, 'samples': 16336512, 'steps': 85085, 'loss/train': 0.6416606307029724} 08/31/2021 04:35:01 - INFO - __main__ - Step 85087: {'lr': 0.0002020812966929475, 'samples': 16336704, 'steps': 85086, 'loss/train': 1.1856566667556763} 08/31/2021 04:35:01 - INFO - __main__ - Step 85088: {'lr': 0.00020207608835445408, 'samples': 16336896, 'steps': 85087, 'loss/train': 1.170706033706665} 08/31/2021 04:35:01 - INFO - __main__ - Step 85089: {'lr': 0.0002020708800375544, 'samples': 16337088, 'steps': 85088, 'loss/train': 0.7277336716651917} 08/31/2021 04:35:02 - INFO - __main__ - Step 85090: {'lr': 0.0002020656717422509, 'samples': 16337280, 'steps': 85089, 'loss/train': 0.08260774612426758} 08/31/2021 04:35:03 - INFO - __main__ - Step 85091: {'lr': 0.00020206046346854585, 'samples': 16337472, 'steps': 85090, 'loss/train': 1.1276663541793823} 08/31/2021 04:35:04 - INFO - __main__ - Step 85092: {'lr': 0.00020205525521644157, 'samples': 16337664, 'steps': 85091, 'loss/train': 0.9766324758529663} 08/31/2021 04:35:04 - INFO - __main__ - Step 85093: {'lr': 0.0002020500469859405, 'samples': 16337856, 'steps': 85092, 'loss/train': 0.49654635787010193} 08/31/2021 04:35:04 - INFO - __main__ - Step 85094: {'lr': 0.00020204483877704494, 'samples': 16338048, 'steps': 85093, 'loss/train': 0.5255009531974792} 08/31/2021 04:35:05 - INFO - __main__ - Step 85095: {'lr': 0.00020203963058975722, 'samples': 16338240, 'steps': 85094, 'loss/train': 0.7032850384712219} 08/31/2021 04:35:05 - INFO - __main__ - Step 85096: {'lr': 0.0002020344224240797, 'samples': 16338432, 'steps': 85095, 'loss/train': 0.6507991552352905} 08/31/2021 04:35:07 - INFO - __main__ - Step 85097: {'lr': 0.00020202921428001487, 'samples': 16338624, 'steps': 85096, 'loss/train': 1.4603692293167114} 08/31/2021 04:35:07 - INFO - __main__ - Step 85098: {'lr': 0.00020202400615756478, 'samples': 16338816, 'steps': 85097, 'loss/train': 1.2649189233779907} 08/31/2021 04:35:07 - INFO - __main__ - Step 85099: {'lr': 0.00020201879805673196, 'samples': 16339008, 'steps': 85098, 'loss/train': 1.5559114217758179} 08/31/2021 04:35:08 - INFO - __main__ - Step 85100: {'lr': 0.00020201358997751874, 'samples': 16339200, 'steps': 85099, 'loss/train': 1.4113703966140747} 08/31/2021 04:35:08 - INFO - __main__ - Step 85101: {'lr': 0.00020200838191992743, 'samples': 16339392, 'steps': 85100, 'loss/train': 0.7284859418869019} 08/31/2021 04:35:10 - INFO - __main__ - Step 85102: {'lr': 0.00020200317388396042, 'samples': 16339584, 'steps': 85101, 'loss/train': 1.073427438735962} 08/31/2021 04:35:10 - INFO - __main__ - Step 85103: {'lr': 0.00020199796586962003, 'samples': 16339776, 'steps': 85102, 'loss/train': 1.6408199071884155} 08/31/2021 04:35:11 - INFO - __main__ - Step 85104: {'lr': 0.0002019927578769086, 'samples': 16339968, 'steps': 85103, 'loss/train': 1.20403254032135} 08/31/2021 04:35:11 - INFO - __main__ - Step 85105: {'lr': 0.00020198754990582852, 'samples': 16340160, 'steps': 85104, 'loss/train': 0.2599397301673889} 08/31/2021 04:35:11 - INFO - __main__ - Step 85106: {'lr': 0.0002019823419563821, 'samples': 16340352, 'steps': 85105, 'loss/train': 0.8820486664772034} 08/31/2021 04:35:13 - INFO - __main__ - Step 85107: {'lr': 0.0002019771340285717, 'samples': 16340544, 'steps': 85106, 'loss/train': 1.5599188804626465} 08/31/2021 04:35:13 - INFO - __main__ - Step 85108: {'lr': 0.00020197192612239964, 'samples': 16340736, 'steps': 85107, 'loss/train': 0.5982658267021179} 08/31/2021 04:35:14 - INFO - __main__ - Step 85109: {'lr': 0.0002019667182378683, 'samples': 16340928, 'steps': 85108, 'loss/train': 0.6197927594184875} 08/31/2021 04:35:14 - INFO - __main__ - Step 85110: {'lr': 0.00020196151037498014, 'samples': 16341120, 'steps': 85109, 'loss/train': 1.289245843887329} 08/31/2021 04:35:14 - INFO - __main__ - Step 85111: {'lr': 0.00020195630253373725, 'samples': 16341312, 'steps': 85110, 'loss/train': 1.8362261056900024} 08/31/2021 04:35:16 - INFO - __main__ - Step 85112: {'lr': 0.00020195109471414215, 'samples': 16341504, 'steps': 85111, 'loss/train': 1.190670132637024} 08/31/2021 04:35:16 - INFO - __main__ - Step 85113: {'lr': 0.00020194588691619712, 'samples': 16341696, 'steps': 85112, 'loss/train': 0.8428611159324646} 08/31/2021 04:35:17 - INFO - __main__ - Step 85114: {'lr': 0.00020194067913990453, 'samples': 16341888, 'steps': 85113, 'loss/train': 1.4420539140701294} 08/31/2021 04:35:17 - INFO - __main__ - Step 85115: {'lr': 0.00020193547138526671, 'samples': 16342080, 'steps': 85114, 'loss/train': 1.1450014114379883} 08/31/2021 04:35:17 - INFO - __main__ - Step 85116: {'lr': 0.00020193026365228605, 'samples': 16342272, 'steps': 85115, 'loss/train': 2.707890033721924} 08/31/2021 04:35:19 - INFO - __main__ - Step 85117: {'lr': 0.00020192505594096485, 'samples': 16342464, 'steps': 85116, 'loss/train': 1.3355815410614014} 08/31/2021 04:35:19 - INFO - __main__ - Step 85118: {'lr': 0.0002019198482513055, 'samples': 16342656, 'steps': 85117, 'loss/train': 1.1177226305007935} 08/31/2021 04:35:20 - INFO - __main__ - Step 85119: {'lr': 0.00020191464058331033, 'samples': 16342848, 'steps': 85118, 'loss/train': 0.5949825048446655} 08/31/2021 04:35:20 - INFO - __main__ - Step 85120: {'lr': 0.00020190943293698166, 'samples': 16343040, 'steps': 85119, 'loss/train': 0.8044148087501526} 08/31/2021 04:35:20 - INFO - __main__ - Step 85121: {'lr': 0.00020190422531232187, 'samples': 16343232, 'steps': 85120, 'loss/train': 0.4280868172645569} 08/31/2021 04:35:22 - INFO - __main__ - Step 85122: {'lr': 0.00020189901770933328, 'samples': 16343424, 'steps': 85121, 'loss/train': 1.453078031539917} 08/31/2021 04:35:23 - INFO - __main__ - Step 85123: {'lr': 0.00020189381012801824, 'samples': 16343616, 'steps': 85122, 'loss/train': 0.5937091112136841} 08/31/2021 04:35:23 - INFO - __main__ - Step 85124: {'lr': 0.00020188860256837926, 'samples': 16343808, 'steps': 85123, 'loss/train': 1.4869881868362427} 08/31/2021 04:35:23 - INFO - __main__ - Step 85125: {'lr': 0.00020188339503041837, 'samples': 16344000, 'steps': 85124, 'loss/train': 1.948272943496704} 08/31/2021 04:35:24 - INFO - __main__ - Step 85126: {'lr': 0.00020187818751413812, 'samples': 16344192, 'steps': 85125, 'loss/train': 0.9751508831977844} 08/31/2021 04:35:24 - INFO - __main__ - Step 85127: {'lr': 0.0002018729800195408, 'samples': 16344384, 'steps': 85126, 'loss/train': 1.0409674644470215} 08/31/2021 04:35:26 - INFO - __main__ - Step 85128: {'lr': 0.0002018677725466288, 'samples': 16344576, 'steps': 85127, 'loss/train': 1.1013251543045044} 08/31/2021 04:35:26 - INFO - __main__ - Step 85129: {'lr': 0.00020186256509540442, 'samples': 16344768, 'steps': 85128, 'loss/train': 1.2530617713928223} 08/31/2021 04:35:27 - INFO - __main__ - Step 85130: {'lr': 0.00020185735766587, 'samples': 16344960, 'steps': 85129, 'loss/train': 0.616084635257721} 08/31/2021 04:35:27 - INFO - __main__ - Step 85131: {'lr': 0.00020185215025802795, 'samples': 16345152, 'steps': 85130, 'loss/train': 1.0328547954559326} 08/31/2021 04:35:28 - INFO - __main__ - Step 85132: {'lr': 0.00020184694287188055, 'samples': 16345344, 'steps': 85131, 'loss/train': 0.6934661269187927} 08/31/2021 04:35:29 - INFO - __main__ - Step 85133: {'lr': 0.00020184173550743018, 'samples': 16345536, 'steps': 85132, 'loss/train': 1.2048187255859375} 08/31/2021 04:35:30 - INFO - __main__ - Step 85134: {'lr': 0.0002018365281646792, 'samples': 16345728, 'steps': 85133, 'loss/train': 0.3882705569267273} 08/31/2021 04:35:30 - INFO - __main__ - Step 85135: {'lr': 0.00020183132084362993, 'samples': 16345920, 'steps': 85134, 'loss/train': 1.4194726943969727} 08/31/2021 04:35:30 - INFO - __main__ - Step 85136: {'lr': 0.0002018261135442847, 'samples': 16346112, 'steps': 85135, 'loss/train': 1.110200047492981} 08/31/2021 04:35:31 - INFO - __main__ - Step 85137: {'lr': 0.000201820906266646, 'samples': 16346304, 'steps': 85136, 'loss/train': 1.06981360912323} 08/31/2021 04:35:32 - INFO - __main__ - Step 85138: {'lr': 0.00020181569901071597, 'samples': 16346496, 'steps': 85137, 'loss/train': 1.5595271587371826} 08/31/2021 04:35:33 - INFO - __main__ - Step 85139: {'lr': 0.00020181049177649701, 'samples': 16346688, 'steps': 85138, 'loss/train': 1.4306409358978271} 08/31/2021 04:35:33 - INFO - __main__ - Step 85140: {'lr': 0.00020180528456399153, 'samples': 16346880, 'steps': 85139, 'loss/train': 1.713165283203125} 08/31/2021 04:35:33 - INFO - __main__ - Step 85141: {'lr': 0.00020180007737320184, 'samples': 16347072, 'steps': 85140, 'loss/train': 1.4140738248825073} 08/31/2021 04:35:34 - INFO - __main__ - Step 85142: {'lr': 0.00020179487020413028, 'samples': 16347264, 'steps': 85141, 'loss/train': 1.0256808996200562} 08/31/2021 04:35:34 - INFO - __main__ - Step 85143: {'lr': 0.0002017896630567792, 'samples': 16347456, 'steps': 85142, 'loss/train': 1.6336169242858887} 08/31/2021 04:35:35 - INFO - __main__ - Step 85144: {'lr': 0.00020178445593115098, 'samples': 16347648, 'steps': 85143, 'loss/train': 1.1752521991729736} 08/31/2021 04:35:36 - INFO - __main__ - Step 85145: {'lr': 0.00020177924882724792, 'samples': 16347840, 'steps': 85144, 'loss/train': 1.3834991455078125} 08/31/2021 04:35:36 - INFO - __main__ - Step 85146: {'lr': 0.00020177404174507237, 'samples': 16348032, 'steps': 85145, 'loss/train': 1.2812278270721436} 08/31/2021 04:35:37 - INFO - __main__ - Step 85147: {'lr': 0.00020176883468462674, 'samples': 16348224, 'steps': 85146, 'loss/train': 1.0648128986358643} 08/31/2021 04:35:37 - INFO - __main__ - Step 85148: {'lr': 0.00020176362764591328, 'samples': 16348416, 'steps': 85147, 'loss/train': 1.2993144989013672} 08/31/2021 04:35:39 - INFO - __main__ - Step 85149: {'lr': 0.0002017584206289344, 'samples': 16348608, 'steps': 85148, 'loss/train': 1.2364948987960815} 08/31/2021 04:35:39 - INFO - __main__ - Step 85150: {'lr': 0.00020175321363369246, 'samples': 16348800, 'steps': 85149, 'loss/train': 1.1241955757141113} 08/31/2021 04:35:39 - INFO - __main__ - Step 85151: {'lr': 0.00020174800666018986, 'samples': 16348992, 'steps': 85150, 'loss/train': 1.8969898223876953} 08/31/2021 04:35:40 - INFO - __main__ - Step 85152: {'lr': 0.00020174279970842874, 'samples': 16349184, 'steps': 85151, 'loss/train': 1.3052400350570679} 08/31/2021 04:35:40 - INFO - __main__ - Step 85153: {'lr': 0.00020173759277841157, 'samples': 16349376, 'steps': 85152, 'loss/train': 1.1598405838012695} 08/31/2021 04:35:41 - INFO - __main__ - Step 85154: {'lr': 0.00020173238587014076, 'samples': 16349568, 'steps': 85153, 'loss/train': 1.0290497541427612} 08/31/2021 04:35:42 - INFO - __main__ - Step 85155: {'lr': 0.00020172717898361852, 'samples': 16349760, 'steps': 85154, 'loss/train': 1.4261201620101929} 08/31/2021 04:35:42 - INFO - __main__ - Step 85156: {'lr': 0.0002017219721188473, 'samples': 16349952, 'steps': 85155, 'loss/train': 1.3927114009857178} 08/31/2021 04:35:43 - INFO - __main__ - Step 85157: {'lr': 0.00020171676527582942, 'samples': 16350144, 'steps': 85156, 'loss/train': 0.6817115545272827} 08/31/2021 04:35:43 - INFO - __main__ - Step 85158: {'lr': 0.0002017115584545672, 'samples': 16350336, 'steps': 85157, 'loss/train': 0.6238501667976379} 08/31/2021 04:35:45 - INFO - __main__ - Step 85159: {'lr': 0.00020170635165506302, 'samples': 16350528, 'steps': 85158, 'loss/train': 1.1619716882705688} 08/31/2021 04:35:46 - INFO - __main__ - Step 85160: {'lr': 0.00020170114487731922, 'samples': 16350720, 'steps': 85159, 'loss/train': 0.9843535423278809} 08/31/2021 04:35:46 - INFO - __main__ - Step 85161: {'lr': 0.0002016959381213381, 'samples': 16350912, 'steps': 85160, 'loss/train': 0.6790834665298462} 08/31/2021 04:35:46 - INFO - __main__ - Step 85162: {'lr': 0.00020169073138712206, 'samples': 16351104, 'steps': 85161, 'loss/train': 1.5165899991989136} 08/31/2021 04:35:47 - INFO - __main__ - Step 85163: {'lr': 0.00020168552467467353, 'samples': 16351296, 'steps': 85162, 'loss/train': 0.7653011679649353} 08/31/2021 04:35:48 - INFO - __main__ - Step 85164: {'lr': 0.00020168031798399472, 'samples': 16351488, 'steps': 85163, 'loss/train': 0.7841886878013611} 08/31/2021 04:35:49 - INFO - __main__ - Step 85165: {'lr': 0.000201675111315088, 'samples': 16351680, 'steps': 85164, 'loss/train': 1.6417232751846313} 08/31/2021 04:35:49 - INFO - __main__ - Step 85166: {'lr': 0.00020166990466795564, 'samples': 16351872, 'steps': 85165, 'loss/train': 0.7336635589599609} 08/31/2021 04:35:49 - INFO - __main__ - Step 85167: {'lr': 0.00020166469804260012, 'samples': 16352064, 'steps': 85166, 'loss/train': 1.1605339050292969} 08/31/2021 04:35:50 - INFO - __main__ - Step 85168: {'lr': 0.00020165949143902375, 'samples': 16352256, 'steps': 85167, 'loss/train': 0.5184975862503052} 08/31/2021 04:35:51 - INFO - __main__ - Step 85169: {'lr': 0.0002016542848572289, 'samples': 16352448, 'steps': 85168, 'loss/train': 1.4504197835922241} 08/31/2021 04:35:52 - INFO - __main__ - Step 85170: {'lr': 0.00020164907829721784, 'samples': 16352640, 'steps': 85169, 'loss/train': 1.1515287160873413} 08/31/2021 04:35:52 - INFO - __main__ - Step 85171: {'lr': 0.00020164387175899295, 'samples': 16352832, 'steps': 85170, 'loss/train': 1.5572587251663208} 08/31/2021 04:35:53 - INFO - __main__ - Step 85172: {'lr': 0.00020163866524255662, 'samples': 16353024, 'steps': 85171, 'loss/train': 1.4760291576385498} 08/31/2021 04:35:53 - INFO - __main__ - Step 85173: {'lr': 0.00020163345874791119, 'samples': 16353216, 'steps': 85172, 'loss/train': 1.0756086111068726} 08/31/2021 04:35:54 - INFO - __main__ - Step 85174: {'lr': 0.00020162825227505894, 'samples': 16353408, 'steps': 85173, 'loss/train': 0.7437639236450195} 08/31/2021 04:35:55 - INFO - __main__ - Step 85175: {'lr': 0.00020162304582400226, 'samples': 16353600, 'steps': 85174, 'loss/train': 0.49095049500465393} 08/31/2021 04:35:55 - INFO - __main__ - Step 85176: {'lr': 0.00020161783939474346, 'samples': 16353792, 'steps': 85175, 'loss/train': 1.5322787761688232} 08/31/2021 04:35:55 - INFO - __main__ - Step 85177: {'lr': 0.00020161263298728495, 'samples': 16353984, 'steps': 85176, 'loss/train': 1.6278599500656128} 08/31/2021 04:35:56 - INFO - __main__ - Step 85178: {'lr': 0.00020160742660162907, 'samples': 16354176, 'steps': 85177, 'loss/train': 1.8239929676055908} 08/31/2021 04:35:56 - INFO - __main__ - Step 85179: {'lr': 0.00020160222023777807, 'samples': 16354368, 'steps': 85178, 'loss/train': 0.9515306353569031} 08/31/2021 04:35:58 - INFO - __main__ - Step 85180: {'lr': 0.00020159701389573436, 'samples': 16354560, 'steps': 85179, 'loss/train': 1.2807281017303467} 08/31/2021 04:35:58 - INFO - __main__ - Step 85181: {'lr': 0.00020159180757550033, 'samples': 16354752, 'steps': 85180, 'loss/train': 0.07252248376607895} 08/31/2021 04:35:59 - INFO - __main__ - Step 85182: {'lr': 0.00020158660127707825, 'samples': 16354944, 'steps': 85181, 'loss/train': 1.3897334337234497} 08/31/2021 04:35:59 - INFO - __main__ - Step 85183: {'lr': 0.0002015813950004705, 'samples': 16355136, 'steps': 85182, 'loss/train': 1.508615493774414} 08/31/2021 04:35:59 - INFO - __main__ - Step 85184: {'lr': 0.0002015761887456795, 'samples': 16355328, 'steps': 85183, 'loss/train': 0.5877112150192261} 08/31/2021 04:36:01 - INFO - __main__ - Step 85185: {'lr': 0.00020157098251270751, 'samples': 16355520, 'steps': 85184, 'loss/train': 1.1703203916549683} 08/31/2021 04:36:01 - INFO - __main__ - Step 85186: {'lr': 0.00020156577630155682, 'samples': 16355712, 'steps': 85185, 'loss/train': 0.032839931547641754} 08/31/2021 04:36:02 - INFO - __main__ - Step 85187: {'lr': 0.00020156057011222987, 'samples': 16355904, 'steps': 85186, 'loss/train': 1.2077949047088623} 08/31/2021 04:36:02 - INFO - __main__ - Step 85188: {'lr': 0.00020155536394472895, 'samples': 16356096, 'steps': 85187, 'loss/train': 5.773046016693115} 08/31/2021 04:36:02 - INFO - __main__ - Step 85189: {'lr': 0.00020155015779905648, 'samples': 16356288, 'steps': 85188, 'loss/train': 1.482998251914978} 08/31/2021 04:36:04 - INFO - __main__ - Step 85190: {'lr': 0.00020154495167521471, 'samples': 16356480, 'steps': 85189, 'loss/train': 1.4457683563232422} 08/31/2021 04:36:04 - INFO - __main__ - Step 85191: {'lr': 0.00020153974557320616, 'samples': 16356672, 'steps': 85190, 'loss/train': 1.0258618593215942} 08/31/2021 04:36:05 - INFO - __main__ - Step 85192: {'lr': 0.00020153453949303294, 'samples': 16356864, 'steps': 85191, 'loss/train': 1.055904746055603} 08/31/2021 04:36:05 - INFO - __main__ - Step 85193: {'lr': 0.00020152933343469754, 'samples': 16357056, 'steps': 85192, 'loss/train': 1.1737051010131836} 08/31/2021 04:36:05 - INFO - __main__ - Step 85194: {'lr': 0.00020152412739820225, 'samples': 16357248, 'steps': 85193, 'loss/train': 1.3487271070480347} 08/31/2021 04:36:07 - INFO - __main__ - Step 85195: {'lr': 0.0002015189213835495, 'samples': 16357440, 'steps': 85194, 'loss/train': 2.2145230770111084} 08/31/2021 04:36:07 - INFO - __main__ - Step 85196: {'lr': 0.00020151371539074153, 'samples': 16357632, 'steps': 85195, 'loss/train': 1.4870152473449707} 08/31/2021 04:36:08 - INFO - __main__ - Step 85197: {'lr': 0.00020150850941978076, 'samples': 16357824, 'steps': 85196, 'loss/train': 0.5226499438285828} 08/31/2021 04:36:08 - INFO - __main__ - Step 85198: {'lr': 0.00020150330347066948, 'samples': 16358016, 'steps': 85197, 'loss/train': 2.360502004623413} 08/31/2021 04:36:08 - INFO - __main__ - Step 85199: {'lr': 0.00020149809754341002, 'samples': 16358208, 'steps': 85198, 'loss/train': 1.0841825008392334} 08/31/2021 04:36:09 - INFO - __main__ - Step 85200: {'lr': 0.00020149289163800483, 'samples': 16358400, 'steps': 85199, 'loss/train': 1.5807006359100342} 08/31/2021 04:36:10 - INFO - __main__ - Step 85201: {'lr': 0.00020148768575445618, 'samples': 16358592, 'steps': 85200, 'loss/train': 1.2633247375488281} 08/31/2021 04:36:11 - INFO - __main__ - Step 85202: {'lr': 0.0002014824798927664, 'samples': 16358784, 'steps': 85201, 'loss/train': 1.4984056949615479} 08/31/2021 04:36:11 - INFO - __main__ - Step 85203: {'lr': 0.00020147727405293793, 'samples': 16358976, 'steps': 85202, 'loss/train': 1.0801920890808105} 08/31/2021 04:36:12 - INFO - __main__ - Step 85204: {'lr': 0.00020147206823497305, 'samples': 16359168, 'steps': 85203, 'loss/train': 1.4035770893096924} 08/31/2021 04:36:12 - INFO - __main__ - Step 85205: {'lr': 0.00020146686243887409, 'samples': 16359360, 'steps': 85204, 'loss/train': 1.2743529081344604} 08/31/2021 04:36:13 - INFO - __main__ - Step 85206: {'lr': 0.00020146165666464343, 'samples': 16359552, 'steps': 85205, 'loss/train': 1.2606580257415771} 08/31/2021 04:36:14 - INFO - __main__ - Step 85207: {'lr': 0.00020145645091228337, 'samples': 16359744, 'steps': 85206, 'loss/train': 1.6239622831344604} 08/31/2021 04:36:14 - INFO - __main__ - Step 85208: {'lr': 0.00020145124518179626, 'samples': 16359936, 'steps': 85207, 'loss/train': 0.8045185208320618} 08/31/2021 04:36:15 - INFO - __main__ - Step 85209: {'lr': 0.0002014460394731845, 'samples': 16360128, 'steps': 85208, 'loss/train': 1.5108580589294434} 08/31/2021 04:36:15 - INFO - __main__ - Step 85210: {'lr': 0.00020144083378645036, 'samples': 16360320, 'steps': 85209, 'loss/train': 1.9809489250183105} 08/31/2021 04:36:17 - INFO - __main__ - Step 85211: {'lr': 0.00020143562812159626, 'samples': 16360512, 'steps': 85210, 'loss/train': 1.2910212278366089} 08/31/2021 04:36:17 - INFO - __main__ - Step 85212: {'lr': 0.00020143042247862454, 'samples': 16360704, 'steps': 85211, 'loss/train': 1.0781925916671753} 08/31/2021 04:36:18 - INFO - __main__ - Step 85213: {'lr': 0.00020142521685753752, 'samples': 16360896, 'steps': 85212, 'loss/train': 4.5716352462768555} 08/31/2021 04:36:18 - INFO - __main__ - Step 85214: {'lr': 0.0002014200112583375, 'samples': 16361088, 'steps': 85213, 'loss/train': 1.140733242034912} 08/31/2021 04:36:18 - INFO - __main__ - Step 85215: {'lr': 0.0002014148056810269, 'samples': 16361280, 'steps': 85214, 'loss/train': 0.7209360599517822} 08/31/2021 04:36:20 - INFO - __main__ - Step 85216: {'lr': 0.00020140960012560806, 'samples': 16361472, 'steps': 85215, 'loss/train': 1.0010299682617188} 08/31/2021 04:36:21 - INFO - __main__ - Step 85217: {'lr': 0.00020140439459208326, 'samples': 16361664, 'steps': 85216, 'loss/train': 0.7539138793945312} 08/31/2021 04:36:21 - INFO - __main__ - Step 85218: {'lr': 0.00020139918908045504, 'samples': 16361856, 'steps': 85217, 'loss/train': 1.20552659034729} 08/31/2021 04:36:22 - INFO - __main__ - Step 85219: {'lr': 0.00020139398359072548, 'samples': 16362048, 'steps': 85218, 'loss/train': 1.6313130855560303} 08/31/2021 04:36:22 - INFO - __main__ - Step 85220: {'lr': 0.00020138877812289703, 'samples': 16362240, 'steps': 85219, 'loss/train': 1.3151379823684692} 08/31/2021 04:36:22 - INFO - __main__ - Step 85221: {'lr': 0.00020138357267697203, 'samples': 16362432, 'steps': 85220, 'loss/train': 0.7442259192466736} 08/31/2021 04:36:23 - INFO - __main__ - Step 85222: {'lr': 0.00020137836725295287, 'samples': 16362624, 'steps': 85221, 'loss/train': 0.05861392989754677} 08/31/2021 04:36:24 - INFO - __main__ - Step 85223: {'lr': 0.00020137316185084184, 'samples': 16362816, 'steps': 85222, 'loss/train': 0.15307268500328064} 08/31/2021 04:36:25 - INFO - __main__ - Step 85224: {'lr': 0.00020136795647064133, 'samples': 16363008, 'steps': 85223, 'loss/train': 1.0296050310134888} 08/31/2021 04:36:25 - INFO - __main__ - Step 85225: {'lr': 0.00020136275111235367, 'samples': 16363200, 'steps': 85224, 'loss/train': 1.4298862218856812} 08/31/2021 04:36:25 - INFO - __main__ - Step 85226: {'lr': 0.0002013575457759812, 'samples': 16363392, 'steps': 85225, 'loss/train': 0.7374494671821594} 08/31/2021 04:36:26 - INFO - __main__ - Step 85227: {'lr': 0.0002013523404615263, 'samples': 16363584, 'steps': 85226, 'loss/train': 0.5525590181350708} 08/31/2021 04:36:27 - INFO - __main__ - Step 85228: {'lr': 0.00020134713516899123, 'samples': 16363776, 'steps': 85227, 'loss/train': 1.2795590162277222} 08/31/2021 04:36:28 - INFO - __main__ - Step 85229: {'lr': 0.00020134192989837841, 'samples': 16363968, 'steps': 85228, 'loss/train': 1.0617082118988037} 08/31/2021 04:36:28 - INFO - __main__ - Step 85230: {'lr': 0.00020133672464969017, 'samples': 16364160, 'steps': 85229, 'loss/train': 0.9122040271759033} 08/31/2021 04:36:28 - INFO - __main__ - Step 85231: {'lr': 0.00020133151942292897, 'samples': 16364352, 'steps': 85230, 'loss/train': 1.296004056930542} 08/31/2021 04:36:29 - INFO - __main__ - Step 85232: {'lr': 0.00020132631421809693, 'samples': 16364544, 'steps': 85231, 'loss/train': 1.243274450302124} 08/31/2021 04:36:30 - INFO - __main__ - Step 85233: {'lr': 0.00020132110903519645, 'samples': 16364736, 'steps': 85232, 'loss/train': 1.2285271883010864} 08/31/2021 04:36:31 - INFO - __main__ - Step 85234: {'lr': 0.00020131590387423, 'samples': 16364928, 'steps': 85233, 'loss/train': 1.449376106262207} 08/31/2021 04:36:31 - INFO - __main__ - Step 85235: {'lr': 0.0002013106987351998, 'samples': 16365120, 'steps': 85234, 'loss/train': 1.4268825054168701} 08/31/2021 04:36:31 - INFO - __main__ - Step 85236: {'lr': 0.0002013054936181083, 'samples': 16365312, 'steps': 85235, 'loss/train': 1.3632992506027222} 08/31/2021 04:36:32 - INFO - __main__ - Step 85237: {'lr': 0.00020130028852295774, 'samples': 16365504, 'steps': 85236, 'loss/train': 1.2453044652938843} 08/31/2021 04:36:33 - INFO - __main__ - Step 85238: {'lr': 0.00020129508344975054, 'samples': 16365696, 'steps': 85237, 'loss/train': 0.06336729228496552} 08/31/2021 04:36:34 - INFO - __main__ - Step 85239: {'lr': 0.00020128987839848904, 'samples': 16365888, 'steps': 85238, 'loss/train': 1.0464904308319092} 08/31/2021 04:36:34 - INFO - __main__ - Step 85240: {'lr': 0.00020128467336917556, 'samples': 16366080, 'steps': 85239, 'loss/train': 1.6802581548690796} 08/31/2021 04:36:34 - INFO - __main__ - Step 85241: {'lr': 0.00020127946836181242, 'samples': 16366272, 'steps': 85240, 'loss/train': 1.007898211479187} 08/31/2021 04:36:35 - INFO - __main__ - Step 85242: {'lr': 0.00020127426337640202, 'samples': 16366464, 'steps': 85241, 'loss/train': 1.8499013185501099} 08/31/2021 04:36:36 - INFO - __main__ - Step 85243: {'lr': 0.00020126905841294672, 'samples': 16366656, 'steps': 85242, 'loss/train': 0.8352445960044861} 08/31/2021 04:36:37 - INFO - __main__ - Step 85244: {'lr': 0.00020126385347144876, 'samples': 16366848, 'steps': 85243, 'loss/train': 1.2641401290893555} 08/31/2021 04:36:37 - INFO - __main__ - Step 85245: {'lr': 0.00020125864855191072, 'samples': 16367040, 'steps': 85244, 'loss/train': 0.337247371673584} 08/31/2021 04:36:37 - INFO - __main__ - Step 85246: {'lr': 0.00020125344365433468, 'samples': 16367232, 'steps': 85245, 'loss/train': 1.4631710052490234} 08/31/2021 04:36:38 - INFO - __main__ - Step 85247: {'lr': 0.00020124823877872307, 'samples': 16367424, 'steps': 85246, 'loss/train': 1.368386149406433} 08/31/2021 04:36:39 - INFO - __main__ - Step 85248: {'lr': 0.00020124303392507823, 'samples': 16367616, 'steps': 85247, 'loss/train': 1.380527377128601} 08/31/2021 04:36:40 - INFO - __main__ - Step 85249: {'lr': 0.00020123782909340255, 'samples': 16367808, 'steps': 85248, 'loss/train': 1.4479427337646484} 08/31/2021 04:36:40 - INFO - __main__ - Step 85250: {'lr': 0.0002012326242836983, 'samples': 16368000, 'steps': 85249, 'loss/train': 1.3348060846328735} 08/31/2021 04:36:41 - INFO - __main__ - Step 85251: {'lr': 0.00020122741949596797, 'samples': 16368192, 'steps': 85250, 'loss/train': 0.6027450561523438} 08/31/2021 04:36:41 - INFO - __main__ - Step 85252: {'lr': 0.00020122221473021373, 'samples': 16368384, 'steps': 85251, 'loss/train': 0.16674762964248657} 08/31/2021 04:36:42 - INFO - __main__ - Step 85253: {'lr': 0.00020121700998643804, 'samples': 16368576, 'steps': 85252, 'loss/train': 0.6227095127105713} 08/31/2021 04:36:43 - INFO - __main__ - Step 85254: {'lr': 0.0002012118052646432, 'samples': 16368768, 'steps': 85253, 'loss/train': 1.0821305513381958} 08/31/2021 04:36:43 - INFO - __main__ - Step 85255: {'lr': 0.00020120660056483161, 'samples': 16368960, 'steps': 85254, 'loss/train': 0.9883646965026855} 08/31/2021 04:36:43 - INFO - __main__ - Step 85256: {'lr': 0.00020120139588700552, 'samples': 16369152, 'steps': 85255, 'loss/train': 1.267540693283081} 08/31/2021 04:36:44 - INFO - __main__ - Step 85257: {'lr': 0.00020119619123116738, 'samples': 16369344, 'steps': 85256, 'loss/train': 1.3452237844467163} 08/31/2021 04:36:45 - INFO - __main__ - Step 85258: {'lr': 0.00020119098659731954, 'samples': 16369536, 'steps': 85257, 'loss/train': 1.4899272918701172} 08/31/2021 04:36:46 - INFO - __main__ - Step 85259: {'lr': 0.00020118578198546422, 'samples': 16369728, 'steps': 85258, 'loss/train': 1.3654999732971191} 08/31/2021 04:36:46 - INFO - __main__ - Step 85260: {'lr': 0.0002011805773956038, 'samples': 16369920, 'steps': 85259, 'loss/train': 1.0406111478805542} 08/31/2021 04:36:46 - INFO - __main__ - Step 85261: {'lr': 0.0002011753728277407, 'samples': 16370112, 'steps': 85260, 'loss/train': 1.1325591802597046} 08/31/2021 04:36:47 - INFO - __main__ - Step 85262: {'lr': 0.0002011701682818772, 'samples': 16370304, 'steps': 85261, 'loss/train': 1.715670108795166} 08/31/2021 04:36:47 - INFO - __main__ - Step 85263: {'lr': 0.00020116496375801565, 'samples': 16370496, 'steps': 85262, 'loss/train': 1.2009496688842773} 08/31/2021 04:36:49 - INFO - __main__ - Step 85264: {'lr': 0.00020115975925615842, 'samples': 16370688, 'steps': 85263, 'loss/train': 1.654104471206665} 08/31/2021 04:36:50 - INFO - __main__ - Step 85265: {'lr': 0.0002011545547763079, 'samples': 16370880, 'steps': 85264, 'loss/train': 0.36545470356941223} 08/31/2021 04:36:50 - INFO - __main__ - Step 85266: {'lr': 0.00020114935031846631, 'samples': 16371072, 'steps': 85265, 'loss/train': 1.239802360534668} 08/31/2021 04:36:50 - INFO - __main__ - Step 85267: {'lr': 0.00020114414588263613, 'samples': 16371264, 'steps': 85266, 'loss/train': 0.8713997006416321} 08/31/2021 04:36:51 - INFO - __main__ - Step 85268: {'lr': 0.0002011389414688196, 'samples': 16371456, 'steps': 85267, 'loss/train': 0.7303861975669861} 08/31/2021 04:36:52 - INFO - __main__ - Step 85269: {'lr': 0.00020113373707701912, 'samples': 16371648, 'steps': 85268, 'loss/train': 0.9346989393234253} 08/31/2021 04:36:53 - INFO - __main__ - Step 85270: {'lr': 0.00020112853270723704, 'samples': 16371840, 'steps': 85269, 'loss/train': 1.164262294769287} 08/31/2021 04:36:53 - INFO - __main__ - Step 85271: {'lr': 0.00020112332835947567, 'samples': 16372032, 'steps': 85270, 'loss/train': 1.566371202468872} 08/31/2021 04:36:54 - INFO - __main__ - Step 85272: {'lr': 0.00020111812403373749, 'samples': 16372224, 'steps': 85271, 'loss/train': 1.4543863534927368} 08/31/2021 04:36:54 - INFO - __main__ - Step 85273: {'lr': 0.00020111291973002462, 'samples': 16372416, 'steps': 85272, 'loss/train': 1.6974937915802002} 08/31/2021 04:36:56 - INFO - __main__ - Step 85274: {'lr': 0.00020110771544833953, 'samples': 16372608, 'steps': 85273, 'loss/train': 2.282027006149292} 08/31/2021 04:36:56 - INFO - __main__ - Step 85275: {'lr': 0.00020110251118868452, 'samples': 16372800, 'steps': 85274, 'loss/train': 0.034538690000772476} 08/31/2021 04:36:56 - INFO - __main__ - Step 85276: {'lr': 0.000201097306951062, 'samples': 16372992, 'steps': 85275, 'loss/train': 1.0680863857269287} 08/31/2021 04:36:57 - INFO - __main__ - Step 85277: {'lr': 0.00020109210273547423, 'samples': 16373184, 'steps': 85276, 'loss/train': 0.7208306193351746} 08/31/2021 04:36:57 - INFO - __main__ - Step 85278: {'lr': 0.00020108689854192362, 'samples': 16373376, 'steps': 85277, 'loss/train': 0.8004865050315857} 08/31/2021 04:36:59 - INFO - __main__ - Step 85279: {'lr': 0.00020108169437041255, 'samples': 16373568, 'steps': 85278, 'loss/train': 1.4010846614837646} 08/31/2021 04:36:59 - INFO - __main__ - Step 85280: {'lr': 0.00020107649022094328, 'samples': 16373760, 'steps': 85279, 'loss/train': 1.0539379119873047} 08/31/2021 04:37:00 - INFO - __main__ - Step 85281: {'lr': 0.00020107128609351817, 'samples': 16373952, 'steps': 85280, 'loss/train': 1.1155287027359009} 08/31/2021 04:37:00 - INFO - __main__ - Step 85282: {'lr': 0.00020106608198813957, 'samples': 16374144, 'steps': 85281, 'loss/train': 0.7980086207389832} 08/31/2021 04:37:00 - INFO - __main__ - Step 85283: {'lr': 0.00020106087790480986, 'samples': 16374336, 'steps': 85282, 'loss/train': 0.18152378499507904} 08/31/2021 04:37:02 - INFO - __main__ - Step 85284: {'lr': 0.0002010556738435314, 'samples': 16374528, 'steps': 85283, 'loss/train': 0.7289451360702515} 08/31/2021 04:37:02 - INFO - __main__ - Step 85285: {'lr': 0.00020105046980430658, 'samples': 16374720, 'steps': 85284, 'loss/train': 1.525172472000122} 08/31/2021 04:37:03 - INFO - __main__ - Step 85286: {'lr': 0.00020104526578713754, 'samples': 16374912, 'steps': 85285, 'loss/train': 1.0651376247406006} 08/31/2021 04:37:03 - INFO - __main__ - Step 85287: {'lr': 0.00020104006179202675, 'samples': 16375104, 'steps': 85286, 'loss/train': 0.9443767666816711} 08/31/2021 04:37:03 - INFO - __main__ - Step 85288: {'lr': 0.00020103485781897658, 'samples': 16375296, 'steps': 85287, 'loss/train': 0.9907423853874207} 08/31/2021 04:37:05 - INFO - __main__ - Step 85289: {'lr': 0.0002010296538679893, 'samples': 16375488, 'steps': 85288, 'loss/train': 1.0842205286026} 08/31/2021 04:37:05 - INFO - __main__ - Step 85290: {'lr': 0.00020102444993906732, 'samples': 16375680, 'steps': 85289, 'loss/train': 1.0651158094406128} 08/31/2021 04:37:06 - INFO - __main__ - Step 85291: {'lr': 0.000201019246032213, 'samples': 16375872, 'steps': 85290, 'loss/train': 1.4414429664611816} 08/31/2021 04:37:06 - INFO - __main__ - Step 85292: {'lr': 0.00020101404214742862, 'samples': 16376064, 'steps': 85291, 'loss/train': 1.3035237789154053} 08/31/2021 04:37:06 - INFO - __main__ - Step 85293: {'lr': 0.00020100883828471654, 'samples': 16376256, 'steps': 85292, 'loss/train': 0.41740214824676514} 08/31/2021 04:37:08 - INFO - __main__ - Step 85294: {'lr': 0.00020100363444407914, 'samples': 16376448, 'steps': 85293, 'loss/train': 0.8603418469429016} 08/31/2021 04:37:08 - INFO - __main__ - Step 85295: {'lr': 0.00020099843062551878, 'samples': 16376640, 'steps': 85294, 'loss/train': 1.0775278806686401} 08/31/2021 04:37:09 - INFO - __main__ - Step 85296: {'lr': 0.00020099322682903776, 'samples': 16376832, 'steps': 85295, 'loss/train': 1.8839117288589478} 08/31/2021 04:37:09 - INFO - __main__ - Step 85297: {'lr': 0.00020098802305463845, 'samples': 16377024, 'steps': 85296, 'loss/train': 1.1943840980529785} 08/31/2021 04:37:09 - INFO - __main__ - Step 85298: {'lr': 0.00020098281930232314, 'samples': 16377216, 'steps': 85297, 'loss/train': 1.6727230548858643} 08/31/2021 04:37:10 - INFO - __main__ - Step 85299: {'lr': 0.0002009776155720943, 'samples': 16377408, 'steps': 85298, 'loss/train': 1.3742132186889648} 08/31/2021 04:37:12 - INFO - __main__ - Step 85300: {'lr': 0.0002009724118639541, 'samples': 16377600, 'steps': 85299, 'loss/train': 0.32790371775627136} 08/31/2021 04:37:13 - INFO - __main__ - Step 85301: {'lr': 0.00020096720817790498, 'samples': 16377792, 'steps': 85300, 'loss/train': 0.9524267315864563} 08/31/2021 04:37:13 - INFO - __main__ - Step 85302: {'lr': 0.0002009620045139493, 'samples': 16377984, 'steps': 85301, 'loss/train': 0.024161089211702347} 08/31/2021 04:37:13 - INFO - __main__ - Step 85303: {'lr': 0.00020095680087208937, 'samples': 16378176, 'steps': 85302, 'loss/train': 1.397708773612976} 08/31/2021 04:37:14 - INFO - __main__ - Step 85304: {'lr': 0.00020095159725232756, 'samples': 16378368, 'steps': 85303, 'loss/train': 1.1927036046981812} 08/31/2021 04:37:14 - INFO - __main__ - Step 85305: {'lr': 0.00020094639365466618, 'samples': 16378560, 'steps': 85304, 'loss/train': 1.026808261871338} 08/31/2021 04:37:15 - INFO - __main__ - Step 85306: {'lr': 0.00020094119007910765, 'samples': 16378752, 'steps': 85305, 'loss/train': 0.5855581164360046} 08/31/2021 04:37:16 - INFO - __main__ - Step 85307: {'lr': 0.0002009359865256542, 'samples': 16378944, 'steps': 85306, 'loss/train': 1.4071162939071655} 08/31/2021 04:37:16 - INFO - __main__ - Step 85308: {'lr': 0.00020093078299430835, 'samples': 16379136, 'steps': 85307, 'loss/train': 0.546836793422699} 08/31/2021 04:37:17 - INFO - __main__ - Step 85309: {'lr': 0.00020092557948507222, 'samples': 16379328, 'steps': 85308, 'loss/train': 0.6162468791007996} 08/31/2021 04:37:17 - INFO - __main__ - Step 85310: {'lr': 0.0002009203759979483, 'samples': 16379520, 'steps': 85309, 'loss/train': 1.2206770181655884} 08/31/2021 04:37:18 - INFO - __main__ - Step 85311: {'lr': 0.0002009151725329389, 'samples': 16379712, 'steps': 85310, 'loss/train': 1.3418240547180176} 08/31/2021 04:37:19 - INFO - __main__ - Step 85312: {'lr': 0.0002009099690900464, 'samples': 16379904, 'steps': 85311, 'loss/train': 1.037787675857544} 08/31/2021 04:37:19 - INFO - __main__ - Step 85313: {'lr': 0.00020090476566927306, 'samples': 16380096, 'steps': 85312, 'loss/train': 1.474941611289978} 08/31/2021 04:37:20 - INFO - __main__ - Step 85314: {'lr': 0.00020089956227062127, 'samples': 16380288, 'steps': 85313, 'loss/train': 0.8505895733833313} 08/31/2021 04:37:20 - INFO - __main__ - Step 85315: {'lr': 0.00020089435889409342, 'samples': 16380480, 'steps': 85314, 'loss/train': 0.9943304061889648} 08/31/2021 04:37:20 - INFO - __main__ - Step 85316: {'lr': 0.00020088915553969177, 'samples': 16380672, 'steps': 85315, 'loss/train': 0.8234908580780029} 08/31/2021 04:37:22 - INFO - __main__ - Step 85317: {'lr': 0.00020088395220741874, 'samples': 16380864, 'steps': 85316, 'loss/train': 1.1113166809082031} 08/31/2021 04:37:22 - INFO - __main__ - Step 85318: {'lr': 0.00020087874889727661, 'samples': 16381056, 'steps': 85317, 'loss/train': 1.1184812784194946} 08/31/2021 04:37:23 - INFO - __main__ - Step 85319: {'lr': 0.00020087354560926785, 'samples': 16381248, 'steps': 85318, 'loss/train': 1.900887370109558} 08/31/2021 04:37:23 - INFO - __main__ - Step 85320: {'lr': 0.00020086834234339461, 'samples': 16381440, 'steps': 85319, 'loss/train': 1.442149043083191} 08/31/2021 04:37:23 - INFO - __main__ - Step 85321: {'lr': 0.00020086313909965938, 'samples': 16381632, 'steps': 85320, 'loss/train': 1.3267377614974976} 08/31/2021 04:37:26 - INFO - __main__ - Step 85322: {'lr': 0.00020085793587806445, 'samples': 16381824, 'steps': 85321, 'loss/train': 1.016053318977356} 08/31/2021 04:37:26 - INFO - __main__ - Step 85323: {'lr': 0.00020085273267861218, 'samples': 16382016, 'steps': 85322, 'loss/train': 0.925966739654541} 08/31/2021 04:37:26 - INFO - __main__ - Step 85324: {'lr': 0.00020084752950130493, 'samples': 16382208, 'steps': 85323, 'loss/train': 2.0779783725738525} 08/31/2021 04:37:27 - INFO - __main__ - Step 85325: {'lr': 0.00020084232634614503, 'samples': 16382400, 'steps': 85324, 'loss/train': 0.521560549736023} 08/31/2021 04:37:27 - INFO - __main__ - Step 85326: {'lr': 0.0002008371232131348, 'samples': 16382592, 'steps': 85325, 'loss/train': 1.4592537879943848} 08/31/2021 04:37:29 - INFO - __main__ - Step 85327: {'lr': 0.00020083192010227657, 'samples': 16382784, 'steps': 85326, 'loss/train': 1.1246960163116455} 08/31/2021 04:37:29 - INFO - __main__ - Step 85328: {'lr': 0.00020082671701357273, 'samples': 16382976, 'steps': 85327, 'loss/train': 1.264214277267456} 08/31/2021 04:37:29 - INFO - __main__ - Step 85329: {'lr': 0.00020082151394702562, 'samples': 16383168, 'steps': 85328, 'loss/train': 1.4155129194259644} 08/31/2021 04:37:30 - INFO - __main__ - Step 85330: {'lr': 0.00020081631090263766, 'samples': 16383360, 'steps': 85329, 'loss/train': 1.0838409662246704} 08/31/2021 04:37:30 - INFO - __main__ - Step 85331: {'lr': 0.00020081110788041102, 'samples': 16383552, 'steps': 85330, 'loss/train': 1.8384844064712524} 08/31/2021 04:37:32 - INFO - __main__ - Step 85332: {'lr': 0.00020080590488034817, 'samples': 16383744, 'steps': 85331, 'loss/train': 0.8763782382011414} 08/31/2021 04:37:32 - INFO - __main__ - Step 85333: {'lr': 0.00020080070190245136, 'samples': 16383936, 'steps': 85332, 'loss/train': 1.10930335521698} 08/31/2021 04:37:32 - INFO - __main__ - Step 85334: {'lr': 0.00020079549894672305, 'samples': 16384128, 'steps': 85333, 'loss/train': 1.3296741247177124} 08/31/2021 04:37:33 - INFO - __main__ - Step 85335: {'lr': 0.0002007902960131655, 'samples': 16384320, 'steps': 85334, 'loss/train': 1.3544484376907349} 08/31/2021 04:37:33 - INFO - __main__ - Step 85336: {'lr': 0.00020078509310178112, 'samples': 16384512, 'steps': 85335, 'loss/train': 0.9075659513473511} 08/31/2021 04:37:35 - INFO - __main__ - Step 85337: {'lr': 0.00020077989021257217, 'samples': 16384704, 'steps': 85336, 'loss/train': 0.8331218361854553} 08/31/2021 04:37:35 - INFO - __main__ - Step 85338: {'lr': 0.00020077468734554105, 'samples': 16384896, 'steps': 85337, 'loss/train': 0.3257528245449066} 08/31/2021 04:37:35 - INFO - __main__ - Step 85339: {'lr': 0.0002007694845006902, 'samples': 16385088, 'steps': 85338, 'loss/train': 1.0006744861602783} 08/31/2021 04:37:36 - INFO - __main__ - Step 85340: {'lr': 0.00020076428167802179, 'samples': 16385280, 'steps': 85339, 'loss/train': 1.0996567010879517} 08/31/2021 04:37:36 - INFO - __main__ - Step 85341: {'lr': 0.00020075907887753822, 'samples': 16385472, 'steps': 85340, 'loss/train': 1.4886677265167236} 08/31/2021 04:37:38 - INFO - __main__ - Step 85342: {'lr': 0.00020075387609924184, 'samples': 16385664, 'steps': 85341, 'loss/train': 1.399476170539856} 08/31/2021 04:37:38 - INFO - __main__ - Step 85343: {'lr': 0.00020074867334313502, 'samples': 16385856, 'steps': 85342, 'loss/train': 1.467676043510437} 08/31/2021 04:37:38 - INFO - __main__ - Step 85344: {'lr': 0.00020074347060922008, 'samples': 16386048, 'steps': 85343, 'loss/train': 0.7109706997871399} 08/31/2021 04:37:39 - INFO - __main__ - Step 85345: {'lr': 0.00020073826789749935, 'samples': 16386240, 'steps': 85344, 'loss/train': 1.3784898519515991} 08/31/2021 04:37:39 - INFO - __main__ - Step 85346: {'lr': 0.00020073306520797525, 'samples': 16386432, 'steps': 85345, 'loss/train': 1.6848289966583252} 08/31/2021 04:37:41 - INFO - __main__ - Step 85347: {'lr': 0.00020072786254065, 'samples': 16386624, 'steps': 85346, 'loss/train': 1.1025500297546387} 08/31/2021 04:37:41 - INFO - __main__ - Step 85348: {'lr': 0.00020072265989552607, 'samples': 16386816, 'steps': 85347, 'loss/train': 1.516940712928772} 08/31/2021 04:37:42 - INFO - __main__ - Step 85349: {'lr': 0.0002007174572726057, 'samples': 16387008, 'steps': 85348, 'loss/train': 0.8252407312393188} 08/31/2021 04:37:42 - INFO - __main__ - Step 85350: {'lr': 0.00020071225467189132, 'samples': 16387200, 'steps': 85349, 'loss/train': 1.0940064191818237} 08/31/2021 04:37:42 - INFO - __main__ - Step 85351: {'lr': 0.00020070705209338524, 'samples': 16387392, 'steps': 85350, 'loss/train': 0.05276162922382355} 08/31/2021 04:37:43 - INFO - __main__ - Step 85352: {'lr': 0.0002007018495370899, 'samples': 16387584, 'steps': 85351, 'loss/train': 0.17654505372047424} 08/31/2021 04:37:44 - INFO - __main__ - Step 85353: {'lr': 0.00020069664700300745, 'samples': 16387776, 'steps': 85352, 'loss/train': 1.2261391878128052} 08/31/2021 04:37:45 - INFO - __main__ - Step 85354: {'lr': 0.00020069144449114029, 'samples': 16387968, 'steps': 85353, 'loss/train': 1.2017289400100708} 08/31/2021 04:37:45 - INFO - __main__ - Step 85355: {'lr': 0.00020068624200149084, 'samples': 16388160, 'steps': 85354, 'loss/train': 0.03998388350009918} 08/31/2021 04:37:46 - INFO - __main__ - Step 85356: {'lr': 0.00020068103953406138, 'samples': 16388352, 'steps': 85355, 'loss/train': 1.2431340217590332} 08/31/2021 04:37:46 - INFO - __main__ - Step 85357: {'lr': 0.0002006758370888543, 'samples': 16388544, 'steps': 85356, 'loss/train': 1.239869475364685} 08/31/2021 04:37:47 - INFO - __main__ - Step 85358: {'lr': 0.00020067063466587193, 'samples': 16388736, 'steps': 85357, 'loss/train': 0.17389018833637238} 08/31/2021 04:37:48 - INFO - __main__ - Step 85359: {'lr': 0.00020066543226511662, 'samples': 16388928, 'steps': 85358, 'loss/train': 0.6326729655265808} 08/31/2021 04:37:48 - INFO - __main__ - Step 85360: {'lr': 0.0002006602298865907, 'samples': 16389120, 'steps': 85359, 'loss/train': 1.070863962173462} 08/31/2021 04:37:49 - INFO - __main__ - Step 85361: {'lr': 0.0002006550275302965, 'samples': 16389312, 'steps': 85360, 'loss/train': 1.4865939617156982} 08/31/2021 04:37:49 - INFO - __main__ - Step 85362: {'lr': 0.0002006498251962364, 'samples': 16389504, 'steps': 85361, 'loss/train': 1.3561186790466309} 08/31/2021 04:37:49 - INFO - __main__ - Step 85363: {'lr': 0.00020064462288441274, 'samples': 16389696, 'steps': 85362, 'loss/train': 1.0640413761138916} 08/31/2021 04:37:51 - INFO - __main__ - Step 85364: {'lr': 0.0002006394205948278, 'samples': 16389888, 'steps': 85363, 'loss/train': 1.4606070518493652} 08/31/2021 04:37:51 - INFO - __main__ - Step 85365: {'lr': 0.000200634218327484, 'samples': 16390080, 'steps': 85364, 'loss/train': 1.2232164144515991} 08/31/2021 04:37:52 - INFO - __main__ - Step 85366: {'lr': 0.00020062901608238382, 'samples': 16390272, 'steps': 85365, 'loss/train': 1.6542569398880005} 08/31/2021 04:37:52 - INFO - __main__ - Step 85367: {'lr': 0.00020062381385952928, 'samples': 16390464, 'steps': 85366, 'loss/train': 1.4301562309265137} 08/31/2021 04:37:52 - INFO - __main__ - Step 85368: {'lr': 0.00020061861165892293, 'samples': 16390656, 'steps': 85367, 'loss/train': 0.6503135561943054} 08/31/2021 04:37:54 - INFO - __main__ - Step 85369: {'lr': 0.00020061340948056703, 'samples': 16390848, 'steps': 85368, 'loss/train': 1.271653652191162} 08/31/2021 04:37:54 - INFO - __main__ - Step 85370: {'lr': 0.00020060820732446398, 'samples': 16391040, 'steps': 85369, 'loss/train': 1.4240429401397705} 08/31/2021 04:37:55 - INFO - __main__ - Step 85371: {'lr': 0.00020060300519061607, 'samples': 16391232, 'steps': 85370, 'loss/train': 1.3416128158569336} 08/31/2021 04:37:55 - INFO - __main__ - Step 85372: {'lr': 0.00020059780307902576, 'samples': 16391424, 'steps': 85371, 'loss/train': 0.9217828512191772} 08/31/2021 04:37:55 - INFO - __main__ - Step 85373: {'lr': 0.00020059260098969525, 'samples': 16391616, 'steps': 85372, 'loss/train': 1.5508378744125366} 08/31/2021 04:37:58 - INFO - __main__ - Step 85374: {'lr': 0.000200587398922627, 'samples': 16391808, 'steps': 85373, 'loss/train': 0.20933368802070618} 08/31/2021 04:37:58 - INFO - __main__ - Step 85375: {'lr': 0.00020058219687782327, 'samples': 16392000, 'steps': 85374, 'loss/train': 1.6658198833465576} 08/31/2021 04:37:58 - INFO - __main__ - Step 85376: {'lr': 0.00020057699485528647, 'samples': 16392192, 'steps': 85375, 'loss/train': 0.061150066554546356} 08/31/2021 04:37:59 - INFO - __main__ - Step 85377: {'lr': 0.0002005717928550189, 'samples': 16392384, 'steps': 85376, 'loss/train': 0.8916683793067932} 08/31/2021 04:37:59 - INFO - __main__ - Step 85378: {'lr': 0.00020056659087702293, 'samples': 16392576, 'steps': 85377, 'loss/train': 1.0644166469573975} 08/31/2021 04:38:01 - INFO - __main__ - Step 85379: {'lr': 0.00020056138892130096, 'samples': 16392768, 'steps': 85378, 'loss/train': 0.9230688214302063} 08/31/2021 04:38:01 - INFO - __main__ - Step 85380: {'lr': 0.0002005561869878552, 'samples': 16392960, 'steps': 85379, 'loss/train': 0.42088156938552856} 08/31/2021 04:38:01 - INFO - __main__ - Step 85381: {'lr': 0.00020055098507668805, 'samples': 16393152, 'steps': 85380, 'loss/train': 1.1973347663879395} 08/31/2021 04:38:02 - INFO - __main__ - Step 85382: {'lr': 0.00020054578318780183, 'samples': 16393344, 'steps': 85381, 'loss/train': 1.1368046998977661} 08/31/2021 04:38:02 - INFO - __main__ - Step 85383: {'lr': 0.00020054058132119894, 'samples': 16393536, 'steps': 85382, 'loss/train': 1.1604063510894775} 08/31/2021 04:38:03 - INFO - __main__ - Step 85384: {'lr': 0.00020053537947688172, 'samples': 16393728, 'steps': 85383, 'loss/train': 1.133693814277649} 08/31/2021 04:38:04 - INFO - __main__ - Step 85385: {'lr': 0.00020053017765485248, 'samples': 16393920, 'steps': 85384, 'loss/train': 0.8012704253196716} 08/31/2021 04:38:04 - INFO - __main__ - Step 85386: {'lr': 0.00020052497585511356, 'samples': 16394112, 'steps': 85385, 'loss/train': 0.8982642292976379} 08/31/2021 04:38:05 - INFO - __main__ - Step 85387: {'lr': 0.00020051977407766736, 'samples': 16394304, 'steps': 85386, 'loss/train': 1.7304586172103882} 08/31/2021 04:38:05 - INFO - __main__ - Step 85388: {'lr': 0.00020051457232251615, 'samples': 16394496, 'steps': 85387, 'loss/train': 1.112964391708374} 08/31/2021 04:38:05 - INFO - __main__ - Step 85389: {'lr': 0.0002005093705896623, 'samples': 16394688, 'steps': 85388, 'loss/train': 1.1393303871154785} 08/31/2021 04:38:07 - INFO - __main__ - Step 85390: {'lr': 0.0002005041688791082, 'samples': 16394880, 'steps': 85389, 'loss/train': 1.2894779443740845} 08/31/2021 04:38:08 - INFO - __main__ - Step 85391: {'lr': 0.00020049896719085618, 'samples': 16395072, 'steps': 85390, 'loss/train': 0.9238841533660889} 08/31/2021 04:38:08 - INFO - __main__ - Step 85392: {'lr': 0.0002004937655249085, 'samples': 16395264, 'steps': 85391, 'loss/train': 0.6434853076934814} 08/31/2021 04:38:08 - INFO - __main__ - Step 85393: {'lr': 0.0002004885638812677, 'samples': 16395456, 'steps': 85392, 'loss/train': 0.1405521184206009} 08/31/2021 04:38:09 - INFO - __main__ - Step 85394: {'lr': 0.00020048336225993591, 'samples': 16395648, 'steps': 85393, 'loss/train': 0.8993867039680481} 08/31/2021 04:38:10 - INFO - __main__ - Step 85395: {'lr': 0.0002004781606609155, 'samples': 16395840, 'steps': 85394, 'loss/train': 0.5985766649246216} 08/31/2021 04:38:11 - INFO - __main__ - Step 85396: {'lr': 0.0002004729590842089, 'samples': 16396032, 'steps': 85395, 'loss/train': 1.0439664125442505} 08/31/2021 04:38:11 - INFO - __main__ - Step 85397: {'lr': 0.0002004677575298184, 'samples': 16396224, 'steps': 85396, 'loss/train': 1.2692025899887085} 08/31/2021 04:38:11 - INFO - __main__ - Step 85398: {'lr': 0.00020046255599774637, 'samples': 16396416, 'steps': 85397, 'loss/train': 0.7463116645812988} 08/31/2021 04:38:12 - INFO - __main__ - Step 85399: {'lr': 0.0002004573544879952, 'samples': 16396608, 'steps': 85398, 'loss/train': 0.7855637669563293} 08/31/2021 04:38:13 - INFO - __main__ - Step 85400: {'lr': 0.00020045215300056713, 'samples': 16396800, 'steps': 85399, 'loss/train': 0.5815981030464172} 08/31/2021 04:38:14 - INFO - __main__ - Step 85401: {'lr': 0.00020044695153546456, 'samples': 16396992, 'steps': 85400, 'loss/train': 1.1150283813476562} 08/31/2021 04:38:14 - INFO - __main__ - Step 85402: {'lr': 0.0002004417500926898, 'samples': 16397184, 'steps': 85401, 'loss/train': 1.2859127521514893} 08/31/2021 04:38:15 - INFO - __main__ - Step 85403: {'lr': 0.00020043654867224527, 'samples': 16397376, 'steps': 85402, 'loss/train': 1.7519958019256592} 08/31/2021 04:38:15 - INFO - __main__ - Step 85404: {'lr': 0.00020043134727413327, 'samples': 16397568, 'steps': 85403, 'loss/train': 1.5906882286071777} 08/31/2021 04:38:15 - INFO - __main__ - Step 85405: {'lr': 0.00020042614589835608, 'samples': 16397760, 'steps': 85404, 'loss/train': 1.0795739889144897} 08/31/2021 04:38:17 - INFO - __main__ - Step 85406: {'lr': 0.00020042094454491628, 'samples': 16397952, 'steps': 85405, 'loss/train': 1.5521923303604126} 08/31/2021 04:38:17 - INFO - __main__ - Step 85407: {'lr': 0.0002004157432138159, 'samples': 16398144, 'steps': 85406, 'loss/train': 1.7751202583312988} 08/31/2021 04:38:18 - INFO - __main__ - Step 85408: {'lr': 0.0002004105419050574, 'samples': 16398336, 'steps': 85407, 'loss/train': 1.3046201467514038} 08/31/2021 04:38:18 - INFO - __main__ - Step 85409: {'lr': 0.00020040534061864317, 'samples': 16398528, 'steps': 85408, 'loss/train': 0.4240208864212036} 08/31/2021 04:38:18 - INFO - __main__ - Step 85410: {'lr': 0.0002004001393545755, 'samples': 16398720, 'steps': 85409, 'loss/train': 1.2312780618667603} 08/31/2021 04:38:20 - INFO - __main__ - Step 85411: {'lr': 0.0002003949381128568, 'samples': 16398912, 'steps': 85410, 'loss/train': 1.1363615989685059} 08/31/2021 04:38:20 - INFO - __main__ - Step 85412: {'lr': 0.00020038973689348938, 'samples': 16399104, 'steps': 85411, 'loss/train': 1.1591005325317383} 08/31/2021 04:38:21 - INFO - __main__ - Step 85413: {'lr': 0.00020038453569647555, 'samples': 16399296, 'steps': 85412, 'loss/train': 1.014478325843811} 08/31/2021 04:38:21 - INFO - __main__ - Step 85414: {'lr': 0.0002003793345218177, 'samples': 16399488, 'steps': 85413, 'loss/train': 1.6699812412261963} 08/31/2021 04:38:21 - INFO - __main__ - Step 85415: {'lr': 0.00020037413336951816, 'samples': 16399680, 'steps': 85414, 'loss/train': 0.8169043064117432} 08/31/2021 04:38:23 - INFO - __main__ - Step 85416: {'lr': 0.00020036893223957924, 'samples': 16399872, 'steps': 85415, 'loss/train': 1.2034579515457153} 08/31/2021 04:38:23 - INFO - __main__ - Step 85417: {'lr': 0.00020036373113200333, 'samples': 16400064, 'steps': 85416, 'loss/train': 1.1786795854568481} 08/31/2021 04:38:24 - INFO - __main__ - Step 85418: {'lr': 0.0002003585300467928, 'samples': 16400256, 'steps': 85417, 'loss/train': 0.8975640535354614} 08/31/2021 04:38:24 - INFO - __main__ - Step 85419: {'lr': 0.00020035332898394988, 'samples': 16400448, 'steps': 85418, 'loss/train': 1.2868397235870361} 08/31/2021 04:38:24 - INFO - __main__ - Step 85420: {'lr': 0.00020034812794347712, 'samples': 16400640, 'steps': 85419, 'loss/train': 1.038123369216919} 08/31/2021 04:38:26 - INFO - __main__ - Step 85421: {'lr': 0.00020034292692537662, 'samples': 16400832, 'steps': 85420, 'loss/train': 0.8165764212608337} 08/31/2021 04:38:27 - INFO - __main__ - Step 85422: {'lr': 0.00020033772592965084, 'samples': 16401024, 'steps': 85421, 'loss/train': 1.4115759134292603} 08/31/2021 04:38:27 - INFO - __main__ - Step 85423: {'lr': 0.00020033252495630212, 'samples': 16401216, 'steps': 85422, 'loss/train': 1.1024092435836792} 08/31/2021 04:38:27 - INFO - __main__ - Step 85424: {'lr': 0.00020032732400533277, 'samples': 16401408, 'steps': 85423, 'loss/train': 0.036601241677999496} 08/31/2021 04:38:28 - INFO - __main__ - Step 85425: {'lr': 0.00020032212307674515, 'samples': 16401600, 'steps': 85424, 'loss/train': 1.331433892250061} 08/31/2021 04:38:28 - INFO - __main__ - Step 85426: {'lr': 0.00020031692217054164, 'samples': 16401792, 'steps': 85425, 'loss/train': 1.144425630569458} 08/31/2021 04:38:30 - INFO - __main__ - Step 85427: {'lr': 0.0002003117212867246, 'samples': 16401984, 'steps': 85426, 'loss/train': 1.2924754619598389} 08/31/2021 04:38:30 - INFO - __main__ - Step 85428: {'lr': 0.00020030652042529626, 'samples': 16402176, 'steps': 85427, 'loss/train': 0.7488583922386169} 08/31/2021 04:38:31 - INFO - __main__ - Step 85429: {'lr': 0.00020030131958625907, 'samples': 16402368, 'steps': 85428, 'loss/train': 0.1433274745941162} 08/31/2021 04:38:31 - INFO - __main__ - Step 85430: {'lr': 0.00020029611876961535, 'samples': 16402560, 'steps': 85429, 'loss/train': 1.1322296857833862} 08/31/2021 04:38:31 - INFO - __main__ - Step 85431: {'lr': 0.00020029091797536748, 'samples': 16402752, 'steps': 85430, 'loss/train': 1.0073606967926025} 08/31/2021 04:38:34 - INFO - __main__ - Step 85432: {'lr': 0.00020028571720351768, 'samples': 16402944, 'steps': 85431, 'loss/train': 0.9845877885818481} 08/31/2021 04:38:34 - INFO - __main__ - Step 85433: {'lr': 0.00020028051645406842, 'samples': 16403136, 'steps': 85432, 'loss/train': 1.9152683019638062} 08/31/2021 04:38:34 - INFO - __main__ - Step 85434: {'lr': 0.00020027531572702195, 'samples': 16403328, 'steps': 85433, 'loss/train': 0.8023630380630493} 08/31/2021 04:38:35 - INFO - __main__ - Step 85435: {'lr': 0.00020027011502238065, 'samples': 16403520, 'steps': 85434, 'loss/train': 1.1396242380142212} 08/31/2021 04:38:35 - INFO - __main__ - Step 85436: {'lr': 0.00020026491434014688, 'samples': 16403712, 'steps': 85435, 'loss/train': 1.2573927640914917} 08/31/2021 04:38:37 - INFO - __main__ - Step 85437: {'lr': 0.00020025971368032298, 'samples': 16403904, 'steps': 85436, 'loss/train': 0.8333296775817871} 08/31/2021 04:38:37 - INFO - __main__ - Step 85438: {'lr': 0.00020025451304291127, 'samples': 16404096, 'steps': 85437, 'loss/train': 1.1741092205047607} 08/31/2021 04:38:37 - INFO - __main__ - Step 85439: {'lr': 0.0002002493124279141, 'samples': 16404288, 'steps': 85438, 'loss/train': 1.4228672981262207} 08/31/2021 04:38:38 - INFO - __main__ - Step 85440: {'lr': 0.00020024411183533383, 'samples': 16404480, 'steps': 85439, 'loss/train': 1.044329285621643} 08/31/2021 04:38:38 - INFO - __main__ - Step 85441: {'lr': 0.0002002389112651728, 'samples': 16404672, 'steps': 85440, 'loss/train': 1.3621777296066284} 08/31/2021 04:38:40 - INFO - __main__ - Step 85442: {'lr': 0.0002002337107174334, 'samples': 16404864, 'steps': 85441, 'loss/train': 1.0583628416061401} 08/31/2021 04:38:40 - INFO - __main__ - Step 85443: {'lr': 0.00020022851019211788, 'samples': 16405056, 'steps': 85442, 'loss/train': 1.3932245969772339} 08/31/2021 04:38:40 - INFO - __main__ - Step 85444: {'lr': 0.0002002233096892286, 'samples': 16405248, 'steps': 85443, 'loss/train': 1.349109172821045} 08/31/2021 04:38:41 - INFO - __main__ - Step 85445: {'lr': 0.00020021810920876795, 'samples': 16405440, 'steps': 85444, 'loss/train': 0.6901698708534241} 08/31/2021 04:38:41 - INFO - __main__ - Step 85446: {'lr': 0.0002002129087507383, 'samples': 16405632, 'steps': 85445, 'loss/train': 1.6616153717041016} 08/31/2021 04:38:41 - INFO - __main__ - Step 85447: {'lr': 0.0002002077083151419, 'samples': 16405824, 'steps': 85446, 'loss/train': 0.5325416326522827} 08/31/2021 04:38:43 - INFO - __main__ - Step 85448: {'lr': 0.00020020250790198113, 'samples': 16406016, 'steps': 85447, 'loss/train': 1.1677882671356201} 08/31/2021 04:38:44 - INFO - __main__ - Step 85449: {'lr': 0.00020019730751125834, 'samples': 16406208, 'steps': 85448, 'loss/train': 1.3899927139282227} 08/31/2021 04:38:44 - INFO - __main__ - Step 85450: {'lr': 0.00020019210714297586, 'samples': 16406400, 'steps': 85449, 'loss/train': 0.2908085584640503} 08/31/2021 04:38:44 - INFO - __main__ - Step 85451: {'lr': 0.0002001869067971361, 'samples': 16406592, 'steps': 85450, 'loss/train': 2.1564764976501465} 08/31/2021 04:38:45 - INFO - __main__ - Step 85452: {'lr': 0.00020018170647374128, 'samples': 16406784, 'steps': 85451, 'loss/train': 0.9817142486572266} 08/31/2021 04:38:46 - INFO - __main__ - Step 85453: {'lr': 0.00020017650617279394, 'samples': 16406976, 'steps': 85452, 'loss/train': 1.6801440715789795} 08/31/2021 04:38:47 - INFO - __main__ - Step 85454: {'lr': 0.00020017130589429619, 'samples': 16407168, 'steps': 85453, 'loss/train': 1.194581151008606} 08/31/2021 04:38:47 - INFO - __main__ - Step 85455: {'lr': 0.0002001661056382505, 'samples': 16407360, 'steps': 85454, 'loss/train': 2.0884275436401367} 08/31/2021 04:38:47 - INFO - __main__ - Step 85456: {'lr': 0.00020016090540465919, 'samples': 16407552, 'steps': 85455, 'loss/train': 1.3142821788787842} 08/31/2021 04:38:48 - INFO - __main__ - Step 85457: {'lr': 0.0002001557051935246, 'samples': 16407744, 'steps': 85456, 'loss/train': 0.9252378940582275} 08/31/2021 04:38:49 - INFO - __main__ - Step 85458: {'lr': 0.0002001505050048491, 'samples': 16407936, 'steps': 85457, 'loss/train': 1.2509032487869263} 08/31/2021 04:38:50 - INFO - __main__ - Step 85459: {'lr': 0.00020014530483863498, 'samples': 16408128, 'steps': 85458, 'loss/train': 0.8561175465583801} 08/31/2021 04:38:50 - INFO - __main__ - Step 85460: {'lr': 0.0002001401046948847, 'samples': 16408320, 'steps': 85459, 'loss/train': 1.6475048065185547} 08/31/2021 04:38:51 - INFO - __main__ - Step 85461: {'lr': 0.00020013490457360046, 'samples': 16408512, 'steps': 85460, 'loss/train': 1.3331904411315918} 08/31/2021 04:38:51 - INFO - __main__ - Step 85462: {'lr': 0.00020012970447478464, 'samples': 16408704, 'steps': 85461, 'loss/train': 0.7944254279136658} 08/31/2021 04:38:51 - INFO - __main__ - Step 85463: {'lr': 0.00020012450439843967, 'samples': 16408896, 'steps': 85462, 'loss/train': 1.7681361436843872} 08/31/2021 04:38:53 - INFO - __main__ - Step 85464: {'lr': 0.00020011930434456782, 'samples': 16409088, 'steps': 85463, 'loss/train': 1.3871347904205322} 08/31/2021 04:38:53 - INFO - __main__ - Step 85465: {'lr': 0.0002001141043131714, 'samples': 16409280, 'steps': 85464, 'loss/train': 0.8510814309120178} 08/31/2021 04:38:54 - INFO - __main__ - Step 85466: {'lr': 0.0002001089043042528, 'samples': 16409472, 'steps': 85465, 'loss/train': 0.7432960867881775} 08/31/2021 04:38:54 - INFO - __main__ - Step 85467: {'lr': 0.00020010370431781436, 'samples': 16409664, 'steps': 85466, 'loss/train': 1.3425487279891968} 08/31/2021 04:38:54 - INFO - __main__ - Step 85468: {'lr': 0.0002000985043538584, 'samples': 16409856, 'steps': 85467, 'loss/train': 1.455763578414917} 08/31/2021 04:38:57 - INFO - __main__ - Step 85469: {'lr': 0.00020009330441238732, 'samples': 16410048, 'steps': 85468, 'loss/train': 1.4877089262008667} 08/31/2021 04:38:57 - INFO - __main__ - Step 85470: {'lr': 0.00020008810449340342, 'samples': 16410240, 'steps': 85469, 'loss/train': 1.0905789136886597} 08/31/2021 04:38:57 - INFO - __main__ - Step 85471: {'lr': 0.00020008290459690904, 'samples': 16410432, 'steps': 85470, 'loss/train': 1.1436806917190552} 08/31/2021 04:38:58 - INFO - __main__ - Step 85472: {'lr': 0.00020007770472290652, 'samples': 16410624, 'steps': 85471, 'loss/train': 0.08943641930818558} 08/31/2021 04:38:58 - INFO - __main__ - Step 85473: {'lr': 0.00020007250487139827, 'samples': 16410816, 'steps': 85472, 'loss/train': 1.706981897354126} 08/31/2021 04:39:00 - INFO - __main__ - Step 85474: {'lr': 0.00020006730504238654, 'samples': 16411008, 'steps': 85473, 'loss/train': 0.8988862633705139} 08/31/2021 04:39:00 - INFO - __main__ - Step 85475: {'lr': 0.00020006210523587376, 'samples': 16411200, 'steps': 85474, 'loss/train': 1.2371158599853516} 08/31/2021 04:39:00 - INFO - __main__ - Step 85476: {'lr': 0.0002000569054518622, 'samples': 16411392, 'steps': 85475, 'loss/train': 0.9286513328552246} 08/31/2021 04:39:01 - INFO - __main__ - Step 85477: {'lr': 0.0002000517056903542, 'samples': 16411584, 'steps': 85476, 'loss/train': 1.5470095872879028} 08/31/2021 04:39:01 - INFO - __main__ - Step 85478: {'lr': 0.00020004650595135213, 'samples': 16411776, 'steps': 85477, 'loss/train': 1.3889715671539307} 08/31/2021 04:39:02 - INFO - __main__ - Step 85479: {'lr': 0.00020004130623485833, 'samples': 16411968, 'steps': 85478, 'loss/train': 0.4539860486984253} 08/31/2021 04:39:03 - INFO - __main__ - Step 85480: {'lr': 0.00020003610654087514, 'samples': 16412160, 'steps': 85479, 'loss/train': 0.38359400629997253} 08/31/2021 04:39:04 - INFO - __main__ - Step 85481: {'lr': 0.00020003090686940495, 'samples': 16412352, 'steps': 85480, 'loss/train': 1.1354703903198242} 08/31/2021 04:39:04 - INFO - __main__ - Step 85482: {'lr': 0.00020002570722045003, 'samples': 16412544, 'steps': 85481, 'loss/train': 1.271784782409668} 08/31/2021 04:39:04 - INFO - __main__ - Step 85483: {'lr': 0.00020002050759401275, 'samples': 16412736, 'steps': 85482, 'loss/train': 1.2989307641983032} 08/31/2021 04:39:05 - INFO - __main__ - Step 85484: {'lr': 0.00020001530799009545, 'samples': 16412928, 'steps': 85483, 'loss/train': 1.4965161085128784} 08/31/2021 04:39:06 - INFO - __main__ - Step 85485: {'lr': 0.0002000101084087005, 'samples': 16413120, 'steps': 85484, 'loss/train': 1.4162477254867554} 08/31/2021 04:39:07 - INFO - __main__ - Step 85486: {'lr': 0.00020000490884983024, 'samples': 16413312, 'steps': 85485, 'loss/train': 0.9711363315582275} 08/31/2021 04:39:07 - INFO - __main__ - Step 85487: {'lr': 0.0001999997093134871, 'samples': 16413504, 'steps': 85486, 'loss/train': 1.2943130731582642} 08/31/2021 04:39:08 - INFO - __main__ - Step 85488: {'lr': 0.00019999450979967318, 'samples': 16413696, 'steps': 85487, 'loss/train': 1.7927961349487305} 08/31/2021 04:39:08 - INFO - __main__ - Step 85489: {'lr': 0.000199989310308391, 'samples': 16413888, 'steps': 85488, 'loss/train': 1.070345163345337} 08/31/2021 04:39:10 - INFO - __main__ - Step 85490: {'lr': 0.00019998411083964283, 'samples': 16414080, 'steps': 85489, 'loss/train': 1.5852210521697998} 08/31/2021 04:39:10 - INFO - __main__ - Step 85491: {'lr': 0.00019997891139343106, 'samples': 16414272, 'steps': 85490, 'loss/train': 1.418286919593811} 08/31/2021 04:39:10 - INFO - __main__ - Step 85492: {'lr': 0.00019997371196975802, 'samples': 16414464, 'steps': 85491, 'loss/train': 0.7815229296684265} 08/31/2021 04:39:11 - INFO - __main__ - Step 85493: {'lr': 0.00019996851256862605, 'samples': 16414656, 'steps': 85492, 'loss/train': 1.522064447402954} 08/31/2021 04:39:11 - INFO - __main__ - Step 85494: {'lr': 0.0001999633131900375, 'samples': 16414848, 'steps': 85493, 'loss/train': 0.41679537296295166} 08/31/2021 04:39:11 - INFO - __main__ - Step 85495: {'lr': 0.00019995811383399472, 'samples': 16415040, 'steps': 85494, 'loss/train': 1.0212650299072266} 08/31/2021 04:39:13 - INFO - __main__ - Step 85496: {'lr': 0.00019995291450050005, 'samples': 16415232, 'steps': 85495, 'loss/train': 1.8213727474212646} 08/31/2021 04:39:14 - INFO - __main__ - Step 85497: {'lr': 0.0001999477151895558, 'samples': 16415424, 'steps': 85496, 'loss/train': 1.7926064729690552} 08/31/2021 04:39:14 - INFO - __main__ - Step 85498: {'lr': 0.00019994251590116436, 'samples': 16415616, 'steps': 85497, 'loss/train': 1.1287059783935547} 08/31/2021 04:39:14 - INFO - __main__ - Step 85499: {'lr': 0.00019993731663532803, 'samples': 16415808, 'steps': 85498, 'loss/train': 1.391150712966919} 08/31/2021 04:39:15 - INFO - __main__ - Step 85500: {'lr': 0.00019993211739204928, 'samples': 16416000, 'steps': 85499, 'loss/train': 0.07564244419336319} 08/31/2021 04:39:16 - INFO - __main__ - Step 85501: {'lr': 0.00019992691817133024, 'samples': 16416192, 'steps': 85500, 'loss/train': 0.920734703540802} 08/31/2021 04:39:17 - INFO - __main__ - Step 85502: {'lr': 0.00019992171897317338, 'samples': 16416384, 'steps': 85501, 'loss/train': 1.3028043508529663} 08/31/2021 04:39:17 - INFO - __main__ - Step 85503: {'lr': 0.000199916519797581, 'samples': 16416576, 'steps': 85502, 'loss/train': 0.9778087139129639} 08/31/2021 04:39:17 - INFO - __main__ - Step 85504: {'lr': 0.00019991132064455547, 'samples': 16416768, 'steps': 85503, 'loss/train': 1.2678276300430298} 08/31/2021 04:39:18 - INFO - __main__ - Step 85505: {'lr': 0.0001999061215140991, 'samples': 16416960, 'steps': 85504, 'loss/train': 1.325211763381958} 08/31/2021 04:39:19 - INFO - __main__ - Step 85506: {'lr': 0.0001999009224062143, 'samples': 16417152, 'steps': 85505, 'loss/train': 1.1058238744735718} 08/31/2021 04:39:20 - INFO - __main__ - Step 85507: {'lr': 0.00019989572332090335, 'samples': 16417344, 'steps': 85506, 'loss/train': 0.048863232135772705} 08/31/2021 04:39:20 - INFO - __main__ - Step 85508: {'lr': 0.00019989052425816863, 'samples': 16417536, 'steps': 85507, 'loss/train': 1.4692928791046143} 08/31/2021 04:39:21 - INFO - __main__ - Step 85509: {'lr': 0.00019988532521801242, 'samples': 16417728, 'steps': 85508, 'loss/train': 0.887588620185852} 08/31/2021 04:39:21 - INFO - __main__ - Step 85510: {'lr': 0.00019988012620043716, 'samples': 16417920, 'steps': 85509, 'loss/train': 1.2859816551208496} 08/31/2021 04:39:22 - INFO - __main__ - Step 85511: {'lr': 0.0001998749272054451, 'samples': 16418112, 'steps': 85510, 'loss/train': 0.8665157556533813} 08/31/2021 04:39:23 - INFO - __main__ - Step 85512: {'lr': 0.00019986972823303868, 'samples': 16418304, 'steps': 85511, 'loss/train': 1.6169259548187256} 08/31/2021 04:39:23 - INFO - __main__ - Step 85513: {'lr': 0.00019986452928322013, 'samples': 16418496, 'steps': 85512, 'loss/train': 1.5299880504608154} 08/31/2021 04:39:24 - INFO - __main__ - Step 85514: {'lr': 0.000199859330355992, 'samples': 16418688, 'steps': 85513, 'loss/train': 2.607133626937866} 08/31/2021 04:39:24 - INFO - __main__ - Step 85515: {'lr': 0.00019985413145135633, 'samples': 16418880, 'steps': 85514, 'loss/train': 1.5962789058685303} 08/31/2021 04:39:25 - INFO - __main__ - Step 85516: {'lr': 0.00019984893256931566, 'samples': 16419072, 'steps': 85515, 'loss/train': 1.0826948881149292} 08/31/2021 04:39:26 - INFO - __main__ - Step 85517: {'lr': 0.00019984373370987227, 'samples': 16419264, 'steps': 85516, 'loss/train': 1.3759188652038574} 08/31/2021 04:39:26 - INFO - __main__ - Step 85518: {'lr': 0.0001998385348730285, 'samples': 16419456, 'steps': 85517, 'loss/train': 1.0423012971878052} 08/31/2021 04:39:27 - INFO - __main__ - Step 85519: {'lr': 0.00019983333605878674, 'samples': 16419648, 'steps': 85518, 'loss/train': 1.1884740591049194} 08/31/2021 04:39:27 - INFO - __main__ - Step 85520: {'lr': 0.0001998281372671493, 'samples': 16419840, 'steps': 85519, 'loss/train': 1.6335424184799194} 08/31/2021 04:39:28 - INFO - __main__ - Step 85521: {'lr': 0.0001998229384981185, 'samples': 16420032, 'steps': 85520, 'loss/train': 1.6788538694381714} 08/31/2021 04:39:29 - INFO - __main__ - Step 85522: {'lr': 0.00019981773975169675, 'samples': 16420224, 'steps': 85521, 'loss/train': 0.5506168007850647} 08/31/2021 04:39:29 - INFO - __main__ - Step 85523: {'lr': 0.00019981254102788631, 'samples': 16420416, 'steps': 85522, 'loss/train': 1.2689273357391357} 08/31/2021 04:39:30 - INFO - __main__ - Step 85524: {'lr': 0.00019980734232668963, 'samples': 16420608, 'steps': 85523, 'loss/train': 1.3233213424682617} 08/31/2021 04:39:30 - INFO - __main__ - Step 85525: {'lr': 0.0001998021436481089, 'samples': 16420800, 'steps': 85524, 'loss/train': 1.3808228969573975} 08/31/2021 04:39:30 - INFO - __main__ - Step 85526: {'lr': 0.00019979694499214662, 'samples': 16420992, 'steps': 85525, 'loss/train': 0.9701073169708252} 08/31/2021 04:39:32 - INFO - __main__ - Step 85527: {'lr': 0.00019979174635880516, 'samples': 16421184, 'steps': 85526, 'loss/train': 0.9323834776878357} 08/31/2021 04:39:32 - INFO - __main__ - Step 85528: {'lr': 0.00019978654774808664, 'samples': 16421376, 'steps': 85527, 'loss/train': 1.4909723997116089} 08/31/2021 04:39:32 - INFO - __main__ - Step 85529: {'lr': 0.0001997813491599935, 'samples': 16421568, 'steps': 85528, 'loss/train': 1.3975337743759155} 08/31/2021 04:39:33 - INFO - __main__ - Step 85530: {'lr': 0.00019977615059452815, 'samples': 16421760, 'steps': 85529, 'loss/train': 1.3233461380004883} 08/31/2021 04:39:33 - INFO - __main__ - Step 85531: {'lr': 0.00019977095205169287, 'samples': 16421952, 'steps': 85530, 'loss/train': 1.7441167831420898} 08/31/2021 04:39:35 - INFO - __main__ - Step 85532: {'lr': 0.00019976575353149005, 'samples': 16422144, 'steps': 85531, 'loss/train': 1.8643243312835693} 08/31/2021 04:39:35 - INFO - __main__ - Step 85533: {'lr': 0.00019976055503392195, 'samples': 16422336, 'steps': 85532, 'loss/train': 1.1378002166748047} 08/31/2021 04:39:35 - INFO - __main__ - Step 85534: {'lr': 0.00019975535655899102, 'samples': 16422528, 'steps': 85533, 'loss/train': 1.5082746744155884} 08/31/2021 04:39:36 - INFO - __main__ - Step 85535: {'lr': 0.00019975015810669956, 'samples': 16422720, 'steps': 85534, 'loss/train': 1.1440004110336304} 08/31/2021 04:39:36 - INFO - __main__ - Step 85536: {'lr': 0.00019974495967704987, 'samples': 16422912, 'steps': 85535, 'loss/train': 1.3610413074493408} 08/31/2021 04:39:38 - INFO - __main__ - Step 85537: {'lr': 0.00019973976127004434, 'samples': 16423104, 'steps': 85536, 'loss/train': 1.5245176553726196} 08/31/2021 04:39:39 - INFO - __main__ - Step 85538: {'lr': 0.0001997345628856853, 'samples': 16423296, 'steps': 85537, 'loss/train': 1.1091439723968506} 08/31/2021 04:39:39 - INFO - __main__ - Step 85539: {'lr': 0.00019972936452397505, 'samples': 16423488, 'steps': 85538, 'loss/train': 1.5019173622131348} 08/31/2021 04:39:39 - INFO - __main__ - Step 85540: {'lr': 0.000199724166184916, 'samples': 16423680, 'steps': 85539, 'loss/train': 1.2706631422042847} 08/31/2021 04:39:40 - INFO - __main__ - Step 85541: {'lr': 0.00019971896786851059, 'samples': 16423872, 'steps': 85540, 'loss/train': 0.5988816618919373} 08/31/2021 04:39:41 - INFO - __main__ - Step 85542: {'lr': 0.00019971376957476095, 'samples': 16424064, 'steps': 85541, 'loss/train': 0.1551867127418518} 08/31/2021 04:39:42 - INFO - __main__ - Step 85543: {'lr': 0.00019970857130366949, 'samples': 16424256, 'steps': 85542, 'loss/train': 1.4619605541229248} 08/31/2021 04:39:42 - INFO - __main__ - Step 85544: {'lr': 0.00019970337305523852, 'samples': 16424448, 'steps': 85543, 'loss/train': 0.3177872896194458} 08/31/2021 04:39:42 - INFO - __main__ - Step 85545: {'lr': 0.0001996981748294705, 'samples': 16424640, 'steps': 85544, 'loss/train': 1.1272732019424438} 08/31/2021 04:39:43 - INFO - __main__ - Step 85546: {'lr': 0.00019969297662636768, 'samples': 16424832, 'steps': 85545, 'loss/train': 0.5779917240142822} 08/31/2021 04:39:44 - INFO - __main__ - Step 85547: {'lr': 0.0001996877784459324, 'samples': 16425024, 'steps': 85546, 'loss/train': 1.1938326358795166} 08/31/2021 04:39:45 - INFO - __main__ - Step 85548: {'lr': 0.00019968258028816706, 'samples': 16425216, 'steps': 85547, 'loss/train': 1.0691802501678467} 08/31/2021 04:39:45 - INFO - __main__ - Step 85549: {'lr': 0.000199677382153074, 'samples': 16425408, 'steps': 85548, 'loss/train': 1.3876410722732544} 08/31/2021 04:39:45 - INFO - __main__ - Step 85550: {'lr': 0.0001996721840406555, 'samples': 16425600, 'steps': 85549, 'loss/train': 1.2898849248886108} 08/31/2021 04:39:46 - INFO - __main__ - Step 85551: {'lr': 0.00019966698595091397, 'samples': 16425792, 'steps': 85550, 'loss/train': 1.7465492486953735} 08/31/2021 04:39:47 - INFO - __main__ - Step 85552: {'lr': 0.00019966178788385168, 'samples': 16425984, 'steps': 85551, 'loss/train': 1.3644113540649414} 08/31/2021 04:39:48 - INFO - __main__ - Step 85553: {'lr': 0.000199656589839471, 'samples': 16426176, 'steps': 85552, 'loss/train': 0.9644867181777954} 08/31/2021 04:39:48 - INFO - __main__ - Step 85554: {'lr': 0.00019965139181777445, 'samples': 16426368, 'steps': 85553, 'loss/train': 0.824061930179596} 08/31/2021 04:39:48 - INFO - __main__ - Step 85555: {'lr': 0.00019964619381876406, 'samples': 16426560, 'steps': 85554, 'loss/train': 1.4848666191101074} 08/31/2021 04:39:49 - INFO - __main__ - Step 85556: {'lr': 0.00019964099584244234, 'samples': 16426752, 'steps': 85555, 'loss/train': 1.2945561408996582} 08/31/2021 04:39:50 - INFO - __main__ - Step 85557: {'lr': 0.0001996357978888116, 'samples': 16426944, 'steps': 85556, 'loss/train': 0.8212812542915344} 08/31/2021 04:39:51 - INFO - __main__ - Step 85558: {'lr': 0.00019963059995787416, 'samples': 16427136, 'steps': 85557, 'loss/train': 1.2034142017364502} 08/31/2021 04:39:51 - INFO - __main__ - Step 85559: {'lr': 0.00019962540204963242, 'samples': 16427328, 'steps': 85558, 'loss/train': 0.5633610486984253} 08/31/2021 04:39:51 - INFO - __main__ - Step 85560: {'lr': 0.00019962020416408873, 'samples': 16427520, 'steps': 85559, 'loss/train': 1.5850874185562134} 08/31/2021 04:39:52 - INFO - __main__ - Step 85561: {'lr': 0.00019961500630124535, 'samples': 16427712, 'steps': 85560, 'loss/train': 0.759199857711792} 08/31/2021 04:39:53 - INFO - __main__ - Step 85562: {'lr': 0.00019960980846110465, 'samples': 16427904, 'steps': 85561, 'loss/train': 1.5677555799484253} 08/31/2021 04:39:54 - INFO - __main__ - Step 85563: {'lr': 0.00019960461064366905, 'samples': 16428096, 'steps': 85562, 'loss/train': 1.6889352798461914} 08/31/2021 04:39:54 - INFO - __main__ - Step 85564: {'lr': 0.0001995994128489408, 'samples': 16428288, 'steps': 85563, 'loss/train': 1.429490327835083} 08/31/2021 04:39:54 - INFO - __main__ - Step 85565: {'lr': 0.0001995942150769223, 'samples': 16428480, 'steps': 85564, 'loss/train': 0.35729679465293884} 08/31/2021 04:39:55 - INFO - __main__ - Step 85566: {'lr': 0.00019958901732761592, 'samples': 16428672, 'steps': 85565, 'loss/train': 1.5256986618041992} 08/31/2021 04:39:55 - INFO - __main__ - Step 85567: {'lr': 0.00019958381960102396, 'samples': 16428864, 'steps': 85566, 'loss/train': 1.5127477645874023} 08/31/2021 04:39:57 - INFO - __main__ - Step 85568: {'lr': 0.00019957862189714867, 'samples': 16429056, 'steps': 85567, 'loss/train': 1.2789074182510376} 08/31/2021 04:39:57 - INFO - __main__ - Step 85569: {'lr': 0.0001995734242159925, 'samples': 16429248, 'steps': 85568, 'loss/train': 1.2448372840881348} 08/31/2021 04:39:58 - INFO - __main__ - Step 85570: {'lr': 0.00019956822655755775, 'samples': 16429440, 'steps': 85569, 'loss/train': 0.3602845072746277} 08/31/2021 04:39:58 - INFO - __main__ - Step 85571: {'lr': 0.00019956302892184678, 'samples': 16429632, 'steps': 85570, 'loss/train': 1.2275066375732422} 08/31/2021 04:39:58 - INFO - __main__ - Step 85572: {'lr': 0.00019955783130886192, 'samples': 16429824, 'steps': 85571, 'loss/train': 0.5374863147735596} 08/31/2021 04:40:00 - INFO - __main__ - Step 85573: {'lr': 0.00019955263371860554, 'samples': 16430016, 'steps': 85572, 'loss/train': 1.4517852067947388} 08/31/2021 04:40:00 - INFO - __main__ - Step 85574: {'lr': 0.00019954743615108, 'samples': 16430208, 'steps': 85573, 'loss/train': 1.709329605102539} 08/31/2021 04:40:01 - INFO - __main__ - Step 85575: {'lr': 0.00019954223860628757, 'samples': 16430400, 'steps': 85574, 'loss/train': 1.537475824356079} 08/31/2021 04:40:01 - INFO - __main__ - Step 85576: {'lr': 0.0001995370410842306, 'samples': 16430592, 'steps': 85575, 'loss/train': 1.2984226942062378} 08/31/2021 04:40:01 - INFO - __main__ - Step 85577: {'lr': 0.00019953184358491156, 'samples': 16430784, 'steps': 85576, 'loss/train': 1.3508602380752563} 08/31/2021 04:40:02 - INFO - __main__ - Step 85578: {'lr': 0.0001995266461083326, 'samples': 16430976, 'steps': 85577, 'loss/train': 1.3871114253997803} 08/31/2021 04:40:03 - INFO - __main__ - Step 85579: {'lr': 0.00019952144865449618, 'samples': 16431168, 'steps': 85578, 'loss/train': 1.6810797452926636} 08/31/2021 04:40:04 - INFO - __main__ - Step 85580: {'lr': 0.0001995162512234046, 'samples': 16431360, 'steps': 85579, 'loss/train': 0.7333092093467712} 08/31/2021 04:40:04 - INFO - __main__ - Step 85581: {'lr': 0.0001995110538150603, 'samples': 16431552, 'steps': 85580, 'loss/train': 0.04715195670723915} 08/31/2021 04:40:04 - INFO - __main__ - Step 85582: {'lr': 0.00019950585642946548, 'samples': 16431744, 'steps': 85581, 'loss/train': 1.457513451576233} 08/31/2021 04:40:05 - INFO - __main__ - Step 85583: {'lr': 0.0001995006590666225, 'samples': 16431936, 'steps': 85582, 'loss/train': 1.6929932832717896} 08/31/2021 04:40:06 - INFO - __main__ - Step 85584: {'lr': 0.0001994954617265338, 'samples': 16432128, 'steps': 85583, 'loss/train': 1.1636308431625366} 08/31/2021 04:40:07 - INFO - __main__ - Step 85585: {'lr': 0.00019949026440920165, 'samples': 16432320, 'steps': 85584, 'loss/train': 1.3735440969467163} 08/31/2021 04:40:07 - INFO - __main__ - Step 85586: {'lr': 0.0001994850671146284, 'samples': 16432512, 'steps': 85585, 'loss/train': 1.1327931880950928} 08/31/2021 04:40:07 - INFO - __main__ - Step 85587: {'lr': 0.00019947986984281647, 'samples': 16432704, 'steps': 85586, 'loss/train': 1.3018710613250732} 08/31/2021 04:40:08 - INFO - __main__ - Step 85588: {'lr': 0.00019947467259376803, 'samples': 16432896, 'steps': 85587, 'loss/train': 0.900297999382019} 08/31/2021 04:40:10 - INFO - __main__ - Step 85589: {'lr': 0.00019946947536748555, 'samples': 16433088, 'steps': 85588, 'loss/train': 0.7165108323097229} 08/31/2021 04:40:11 - INFO - __main__ - Step 85590: {'lr': 0.00019946427816397138, 'samples': 16433280, 'steps': 85589, 'loss/train': 1.1387650966644287} 08/31/2021 04:40:11 - INFO - __main__ - Step 85591: {'lr': 0.00019945908098322778, 'samples': 16433472, 'steps': 85590, 'loss/train': 1.5677307844161987} 08/31/2021 04:40:11 - INFO - __main__ - Step 85592: {'lr': 0.00019945388382525714, 'samples': 16433664, 'steps': 85591, 'loss/train': 1.48851478099823} 08/31/2021 04:40:12 - INFO - __main__ - Step 85593: {'lr': 0.00019944868669006182, 'samples': 16433856, 'steps': 85592, 'loss/train': 0.9681209325790405} 08/31/2021 04:40:13 - INFO - __main__ - Step 85594: {'lr': 0.00019944348957764418, 'samples': 16434048, 'steps': 85593, 'loss/train': 1.4330812692642212} 08/31/2021 04:40:14 - INFO - __main__ - Step 85595: {'lr': 0.0001994382924880065, 'samples': 16434240, 'steps': 85594, 'loss/train': 1.1601371765136719} 08/31/2021 04:40:14 - INFO - __main__ - Step 85596: {'lr': 0.0001994330954211511, 'samples': 16434432, 'steps': 85595, 'loss/train': 0.43446555733680725} 08/31/2021 04:40:15 - INFO - __main__ - Step 85597: {'lr': 0.0001994278983770804, 'samples': 16434624, 'steps': 85596, 'loss/train': 1.0272358655929565} 08/31/2021 04:40:15 - INFO - __main__ - Step 85598: {'lr': 0.00019942270135579672, 'samples': 16434816, 'steps': 85597, 'loss/train': 0.867853581905365} 08/31/2021 04:40:16 - INFO - __main__ - Step 85599: {'lr': 0.0001994175043573024, 'samples': 16435008, 'steps': 85598, 'loss/train': 0.9505021572113037} 08/31/2021 04:40:17 - INFO - __main__ - Step 85600: {'lr': 0.00019941230738159974, 'samples': 16435200, 'steps': 85599, 'loss/train': 0.6028183698654175} 08/31/2021 04:40:17 - INFO - __main__ - Step 85601: {'lr': 0.00019940711042869112, 'samples': 16435392, 'steps': 85600, 'loss/train': 0.031036468222737312} 08/31/2021 04:40:18 - INFO - __main__ - Step 85602: {'lr': 0.00019940191349857887, 'samples': 16435584, 'steps': 85601, 'loss/train': 0.9889318943023682} 08/31/2021 04:40:18 - INFO - __main__ - Step 85603: {'lr': 0.00019939671659126532, 'samples': 16435776, 'steps': 85602, 'loss/train': 1.0039405822753906} 08/31/2021 04:40:18 - INFO - __main__ - Step 85604: {'lr': 0.00019939151970675285, 'samples': 16435968, 'steps': 85603, 'loss/train': 1.1378390789031982} 08/31/2021 04:40:20 - INFO - __main__ - Step 85605: {'lr': 0.00019938632284504377, 'samples': 16436160, 'steps': 85604, 'loss/train': 0.5910728573799133} 08/31/2021 04:40:20 - INFO - __main__ - Step 85606: {'lr': 0.00019938112600614044, 'samples': 16436352, 'steps': 85605, 'loss/train': 0.9780813455581665} 08/31/2021 04:40:21 - INFO - __main__ - Step 85607: {'lr': 0.00019937592919004517, 'samples': 16436544, 'steps': 85606, 'loss/train': 1.362364649772644} 08/31/2021 04:40:21 - INFO - __main__ - Step 85608: {'lr': 0.00019937073239676044, 'samples': 16436736, 'steps': 85607, 'loss/train': 0.4922121465206146} 08/31/2021 04:40:21 - INFO - __main__ - Step 85609: {'lr': 0.00019936553562628843, 'samples': 16436928, 'steps': 85608, 'loss/train': 0.7130575776100159} 08/31/2021 04:40:23 - INFO - __main__ - Step 85610: {'lr': 0.00019936033887863147, 'samples': 16437120, 'steps': 85609, 'loss/train': 1.0998339653015137} 08/31/2021 04:40:23 - INFO - __main__ - Step 85611: {'lr': 0.00019935514215379196, 'samples': 16437312, 'steps': 85610, 'loss/train': 1.1888246536254883} 08/31/2021 04:40:24 - INFO - __main__ - Step 85612: {'lr': 0.00019934994545177227, 'samples': 16437504, 'steps': 85611, 'loss/train': 1.122816562652588} 08/31/2021 04:40:24 - INFO - __main__ - Step 85613: {'lr': 0.00019934474877257469, 'samples': 16437696, 'steps': 85612, 'loss/train': 0.18349240720272064} 08/31/2021 04:40:24 - INFO - __main__ - Step 85614: {'lr': 0.0001993395521162016, 'samples': 16437888, 'steps': 85613, 'loss/train': 1.269549012184143} 08/31/2021 04:40:26 - INFO - __main__ - Step 85615: {'lr': 0.0001993343554826553, 'samples': 16438080, 'steps': 85614, 'loss/train': 1.072028398513794} 08/31/2021 04:40:26 - INFO - __main__ - Step 85616: {'lr': 0.00019932915887193816, 'samples': 16438272, 'steps': 85615, 'loss/train': 1.105480670928955} 08/31/2021 04:40:27 - INFO - __main__ - Step 85617: {'lr': 0.00019932396228405252, 'samples': 16438464, 'steps': 85616, 'loss/train': 1.1579734086990356} 08/31/2021 04:40:27 - INFO - __main__ - Step 85618: {'lr': 0.00019931876571900077, 'samples': 16438656, 'steps': 85617, 'loss/train': 1.1783543825149536} 08/31/2021 04:40:27 - INFO - __main__ - Step 85619: {'lr': 0.00019931356917678517, 'samples': 16438848, 'steps': 85618, 'loss/train': 0.6618236899375916} 08/31/2021 04:40:28 - INFO - __main__ - Step 85620: {'lr': 0.0001993083726574081, 'samples': 16439040, 'steps': 85619, 'loss/train': 0.9101880788803101} 08/31/2021 04:40:29 - INFO - __main__ - Step 85621: {'lr': 0.00019930317616087195, 'samples': 16439232, 'steps': 85620, 'loss/train': 0.7629544138908386} 08/31/2021 04:40:30 - INFO - __main__ - Step 85622: {'lr': 0.00019929797968717896, 'samples': 16439424, 'steps': 85621, 'loss/train': 0.7623233199119568} 08/31/2021 04:40:30 - INFO - __main__ - Step 85623: {'lr': 0.00019929278323633148, 'samples': 16439616, 'steps': 85622, 'loss/train': 1.134597897529602} 08/31/2021 04:40:30 - INFO - __main__ - Step 85624: {'lr': 0.0001992875868083319, 'samples': 16439808, 'steps': 85623, 'loss/train': 1.1164894104003906} 08/31/2021 04:40:31 - INFO - __main__ - Step 85625: {'lr': 0.00019928239040318258, 'samples': 16440000, 'steps': 85624, 'loss/train': 1.4300435781478882} 08/31/2021 04:40:32 - INFO - __main__ - Step 85626: {'lr': 0.00019927719402088582, 'samples': 16440192, 'steps': 85625, 'loss/train': 1.0236496925354004} 08/31/2021 04:40:33 - INFO - __main__ - Step 85627: {'lr': 0.00019927199766144396, 'samples': 16440384, 'steps': 85626, 'loss/train': 0.9326188564300537} 08/31/2021 04:40:33 - INFO - __main__ - Step 85628: {'lr': 0.00019926680132485936, 'samples': 16440576, 'steps': 85627, 'loss/train': 1.592358946800232} 08/31/2021 04:40:33 - INFO - __main__ - Step 85629: {'lr': 0.00019926160501113435, 'samples': 16440768, 'steps': 85628, 'loss/train': 0.8708612322807312} 08/31/2021 04:40:34 - INFO - __main__ - Step 85630: {'lr': 0.00019925640872027128, 'samples': 16440960, 'steps': 85629, 'loss/train': 1.3007878065109253} 08/31/2021 04:40:35 - INFO - __main__ - Step 85631: {'lr': 0.00019925121245227252, 'samples': 16441152, 'steps': 85630, 'loss/train': 0.8293433785438538} 08/31/2021 04:40:36 - INFO - __main__ - Step 85632: {'lr': 0.00019924601620714032, 'samples': 16441344, 'steps': 85631, 'loss/train': 0.7385545969009399} 08/31/2021 04:40:36 - INFO - __main__ - Step 85633: {'lr': 0.00019924081998487714, 'samples': 16441536, 'steps': 85632, 'loss/train': 1.3494267463684082} 08/31/2021 04:40:36 - INFO - __main__ - Step 85634: {'lr': 0.0001992356237854852, 'samples': 16441728, 'steps': 85633, 'loss/train': 1.1207785606384277} 08/31/2021 04:40:37 - INFO - __main__ - Step 85635: {'lr': 0.0001992304276089671, 'samples': 16441920, 'steps': 85634, 'loss/train': 1.3818413019180298} 08/31/2021 04:40:38 - INFO - __main__ - Step 85636: {'lr': 0.0001992252314553248, 'samples': 16442112, 'steps': 85635, 'loss/train': 1.8572736978530884} 08/31/2021 04:40:39 - INFO - __main__ - Step 85637: {'lr': 0.00019922003532456088, 'samples': 16442304, 'steps': 85636, 'loss/train': 1.199598789215088} 08/31/2021 04:40:39 - INFO - __main__ - Step 85638: {'lr': 0.0001992148392166776, 'samples': 16442496, 'steps': 85637, 'loss/train': 1.3427287340164185} 08/31/2021 04:40:39 - INFO - __main__ - Step 85639: {'lr': 0.00019920964313167733, 'samples': 16442688, 'steps': 85638, 'loss/train': 1.2955725193023682} 08/31/2021 04:40:40 - INFO - __main__ - Step 85640: {'lr': 0.0001992044470695624, 'samples': 16442880, 'steps': 85639, 'loss/train': 0.37405312061309814} 08/31/2021 04:40:41 - INFO - __main__ - Step 85641: {'lr': 0.00019919925103033517, 'samples': 16443072, 'steps': 85640, 'loss/train': 0.17576810717582703} 08/31/2021 04:40:42 - INFO - __main__ - Step 85642: {'lr': 0.000199194055013998, 'samples': 16443264, 'steps': 85641, 'loss/train': 1.1985108852386475} 08/31/2021 04:40:42 - INFO - __main__ - Step 85643: {'lr': 0.00019918885902055317, 'samples': 16443456, 'steps': 85642, 'loss/train': 1.3600233793258667} 08/31/2021 04:40:42 - INFO - __main__ - Step 85644: {'lr': 0.00019918366305000308, 'samples': 16443648, 'steps': 85643, 'loss/train': 1.2229511737823486} 08/31/2021 04:40:43 - INFO - __main__ - Step 85645: {'lr': 0.00019917846710235004, 'samples': 16443840, 'steps': 85644, 'loss/train': 1.3038983345031738} 08/31/2021 04:40:45 - INFO - __main__ - Step 85646: {'lr': 0.0001991732711775964, 'samples': 16444032, 'steps': 85645, 'loss/train': 1.2646404504776} 08/31/2021 04:40:45 - INFO - __main__ - Step 85647: {'lr': 0.0001991680752757445, 'samples': 16444224, 'steps': 85646, 'loss/train': 1.2340853214263916} 08/31/2021 04:40:45 - INFO - __main__ - Step 85648: {'lr': 0.00019916287939679677, 'samples': 16444416, 'steps': 85647, 'loss/train': 1.4226309061050415} 08/31/2021 04:40:46 - INFO - __main__ - Step 85649: {'lr': 0.0001991576835407554, 'samples': 16444608, 'steps': 85648, 'loss/train': 1.8634096384048462} 08/31/2021 04:40:46 - INFO - __main__ - Step 85650: {'lr': 0.00019915248770762276, 'samples': 16444800, 'steps': 85649, 'loss/train': 1.0644409656524658} 08/31/2021 04:40:48 - INFO - __main__ - Step 85651: {'lr': 0.0001991472918974012, 'samples': 16444992, 'steps': 85650, 'loss/train': 0.9693078994750977} 08/31/2021 04:40:48 - INFO - __main__ - Step 85652: {'lr': 0.00019914209611009316, 'samples': 16445184, 'steps': 85651, 'loss/train': 1.2015794515609741} 08/31/2021 04:40:48 - INFO - __main__ - Step 85653: {'lr': 0.00019913690034570084, 'samples': 16445376, 'steps': 85652, 'loss/train': 1.1936122179031372} 08/31/2021 04:40:49 - INFO - __main__ - Step 85654: {'lr': 0.00019913170460422668, 'samples': 16445568, 'steps': 85653, 'loss/train': 1.128044605255127} 08/31/2021 04:40:49 - INFO - __main__ - Step 85655: {'lr': 0.00019912650888567296, 'samples': 16445760, 'steps': 85654, 'loss/train': 0.7206740379333496} 08/31/2021 04:40:51 - INFO - __main__ - Step 85656: {'lr': 0.00019912131319004206, 'samples': 16445952, 'steps': 85655, 'loss/train': 1.2027604579925537} 08/31/2021 04:40:51 - INFO - __main__ - Step 85657: {'lr': 0.00019911611751733633, 'samples': 16446144, 'steps': 85656, 'loss/train': 1.8154762983322144} 08/31/2021 04:40:51 - INFO - __main__ - Step 85658: {'lr': 0.00019911092186755808, 'samples': 16446336, 'steps': 85657, 'loss/train': 0.9111756682395935} 08/31/2021 04:40:52 - INFO - __main__ - Step 85659: {'lr': 0.00019910572624070967, 'samples': 16446528, 'steps': 85658, 'loss/train': 0.979683518409729} 08/31/2021 04:40:52 - INFO - __main__ - Step 85660: {'lr': 0.00019910053063679342, 'samples': 16446720, 'steps': 85659, 'loss/train': 1.063758134841919} 08/31/2021 04:40:54 - INFO - __main__ - Step 85661: {'lr': 0.0001990953350558117, 'samples': 16446912, 'steps': 85660, 'loss/train': 1.5916353464126587} 08/31/2021 04:40:54 - INFO - __main__ - Step 85662: {'lr': 0.00019909013949776695, 'samples': 16447104, 'steps': 85661, 'loss/train': 1.3456525802612305} 08/31/2021 04:40:54 - INFO - __main__ - Step 85663: {'lr': 0.00019908494396266127, 'samples': 16447296, 'steps': 85662, 'loss/train': 1.930700659751892} 08/31/2021 04:40:55 - INFO - __main__ - Step 85664: {'lr': 0.00019907974845049714, 'samples': 16447488, 'steps': 85663, 'loss/train': 1.8715050220489502} 08/31/2021 04:40:55 - INFO - __main__ - Step 85665: {'lr': 0.00019907455296127688, 'samples': 16447680, 'steps': 85664, 'loss/train': 1.7306783199310303} 08/31/2021 04:40:55 - INFO - __main__ - Step 85666: {'lr': 0.00019906935749500285, 'samples': 16447872, 'steps': 85665, 'loss/train': 1.429817795753479} 08/31/2021 04:40:57 - INFO - __main__ - Step 85667: {'lr': 0.00019906416205167738, 'samples': 16448064, 'steps': 85666, 'loss/train': 0.7009660601615906} 08/31/2021 04:40:57 - INFO - __main__ - Step 85668: {'lr': 0.0001990589666313028, 'samples': 16448256, 'steps': 85667, 'loss/train': 0.7803055644035339} 08/31/2021 04:40:58 - INFO - __main__ - Step 85669: {'lr': 0.00019905377123388148, 'samples': 16448448, 'steps': 85668, 'loss/train': 0.3244876563549042} 08/31/2021 04:40:58 - INFO - __main__ - Step 85670: {'lr': 0.00019904857585941574, 'samples': 16448640, 'steps': 85669, 'loss/train': 1.091058611869812} 08/31/2021 04:40:58 - INFO - __main__ - Step 85671: {'lr': 0.00019904338050790794, 'samples': 16448832, 'steps': 85670, 'loss/train': 0.6478506326675415} 08/31/2021 04:41:00 - INFO - __main__ - Step 85672: {'lr': 0.00019903818517936039, 'samples': 16449024, 'steps': 85671, 'loss/train': 1.3376914262771606} 08/31/2021 04:41:00 - INFO - __main__ - Step 85673: {'lr': 0.00019903298987377545, 'samples': 16449216, 'steps': 85672, 'loss/train': 1.4303240776062012} 08/31/2021 04:41:01 - INFO - __main__ - Step 85674: {'lr': 0.00019902779459115544, 'samples': 16449408, 'steps': 85673, 'loss/train': 1.118856430053711} 08/31/2021 04:41:01 - INFO - __main__ - Step 85675: {'lr': 0.00019902259933150286, 'samples': 16449600, 'steps': 85674, 'loss/train': 0.8567394614219666} 08/31/2021 04:41:01 - INFO - __main__ - Step 85676: {'lr': 0.0001990174040948198, 'samples': 16449792, 'steps': 85675, 'loss/train': 1.2625969648361206} 08/31/2021 04:41:03 - INFO - __main__ - Step 85677: {'lr': 0.00019901220888110868, 'samples': 16449984, 'steps': 85676, 'loss/train': 1.3460288047790527} 08/31/2021 04:41:03 - INFO - __main__ - Step 85678: {'lr': 0.00019900701369037188, 'samples': 16450176, 'steps': 85677, 'loss/train': 1.6067461967468262} 08/31/2021 04:41:04 - INFO - __main__ - Step 85679: {'lr': 0.00019900181852261175, 'samples': 16450368, 'steps': 85678, 'loss/train': 1.6357930898666382} 08/31/2021 04:41:04 - INFO - __main__ - Step 85680: {'lr': 0.00019899662337783061, 'samples': 16450560, 'steps': 85679, 'loss/train': 0.5168907642364502} 08/31/2021 04:41:04 - INFO - __main__ - Step 85681: {'lr': 0.00019899142825603077, 'samples': 16450752, 'steps': 85680, 'loss/train': 0.8624014854431152} 08/31/2021 04:41:05 - INFO - __main__ - Step 85682: {'lr': 0.00019898623315721468, 'samples': 16450944, 'steps': 85681, 'loss/train': 1.2613728046417236} 08/31/2021 04:41:06 - INFO - __main__ - Step 85683: {'lr': 0.00019898103808138455, 'samples': 16451136, 'steps': 85682, 'loss/train': 0.6121528148651123} 08/31/2021 04:41:07 - INFO - __main__ - Step 85684: {'lr': 0.00019897584302854278, 'samples': 16451328, 'steps': 85683, 'loss/train': 0.8126635551452637} 08/31/2021 04:41:07 - INFO - __main__ - Step 85685: {'lr': 0.0001989706479986917, 'samples': 16451520, 'steps': 85684, 'loss/train': 1.2866179943084717} 08/31/2021 04:41:08 - INFO - __main__ - Step 85686: {'lr': 0.0001989654529918337, 'samples': 16451712, 'steps': 85685, 'loss/train': 1.368411898612976} 08/31/2021 04:41:08 - INFO - __main__ - Step 85687: {'lr': 0.00019896025800797103, 'samples': 16451904, 'steps': 85686, 'loss/train': 1.158968210220337} 08/31/2021 04:41:09 - INFO - __main__ - Step 85688: {'lr': 0.00019895506304710623, 'samples': 16452096, 'steps': 85687, 'loss/train': 1.3211137056350708} 08/31/2021 04:41:10 - INFO - __main__ - Step 85689: {'lr': 0.00019894986810924136, 'samples': 16452288, 'steps': 85688, 'loss/train': 1.0980697870254517} 08/31/2021 04:41:10 - INFO - __main__ - Step 85690: {'lr': 0.00019894467319437893, 'samples': 16452480, 'steps': 85689, 'loss/train': 1.1675019264221191} 08/31/2021 04:41:11 - INFO - __main__ - Step 85691: {'lr': 0.00019893947830252118, 'samples': 16452672, 'steps': 85690, 'loss/train': 0.995097279548645} 08/31/2021 04:41:11 - INFO - __main__ - Step 85692: {'lr': 0.00019893428343367053, 'samples': 16452864, 'steps': 85691, 'loss/train': 1.0512397289276123} 08/31/2021 04:41:13 - INFO - __main__ - Step 85693: {'lr': 0.00019892908858782933, 'samples': 16453056, 'steps': 85692, 'loss/train': 0.06031937524676323} 08/31/2021 04:41:13 - INFO - __main__ - Step 85694: {'lr': 0.00019892389376499988, 'samples': 16453248, 'steps': 85693, 'loss/train': 1.2465049028396606} 08/31/2021 04:41:13 - INFO - __main__ - Step 85695: {'lr': 0.00019891869896518455, 'samples': 16453440, 'steps': 85694, 'loss/train': 1.6058342456817627} 08/31/2021 04:41:14 - INFO - __main__ - Step 85696: {'lr': 0.00019891350418838567, 'samples': 16453632, 'steps': 85695, 'loss/train': 1.712149977684021} 08/31/2021 04:41:14 - INFO - __main__ - Step 85697: {'lr': 0.00019890830943460552, 'samples': 16453824, 'steps': 85696, 'loss/train': 1.071163535118103} 08/31/2021 04:41:14 - INFO - __main__ - Step 85698: {'lr': 0.00019890311470384655, 'samples': 16454016, 'steps': 85697, 'loss/train': 1.3094145059585571} 08/31/2021 04:41:16 - INFO - __main__ - Step 85699: {'lr': 0.00019889791999611105, 'samples': 16454208, 'steps': 85698, 'loss/train': 1.1955188512802124} 08/31/2021 04:41:17 - INFO - __main__ - Step 85700: {'lr': 0.0001988927253114014, 'samples': 16454400, 'steps': 85699, 'loss/train': 1.3148411512374878} 08/31/2021 04:41:17 - INFO - __main__ - Step 85701: {'lr': 0.00019888753064971983, 'samples': 16454592, 'steps': 85700, 'loss/train': 0.9998956918716431} 08/31/2021 04:41:17 - INFO - __main__ - Step 85702: {'lr': 0.00019888233601106882, 'samples': 16454784, 'steps': 85701, 'loss/train': 1.9077049493789673} 08/31/2021 04:41:18 - INFO - __main__ - Step 85703: {'lr': 0.00019887714139545058, 'samples': 16454976, 'steps': 85702, 'loss/train': 1.6098031997680664} 08/31/2021 04:41:19 - INFO - __main__ - Step 85704: {'lr': 0.0001988719468028675, 'samples': 16455168, 'steps': 85703, 'loss/train': 1.5051655769348145} 08/31/2021 04:41:20 - INFO - __main__ - Step 85705: {'lr': 0.00019886675223332195, 'samples': 16455360, 'steps': 85704, 'loss/train': 0.5243515968322754} 08/31/2021 04:41:20 - INFO - __main__ - Step 85706: {'lr': 0.00019886155768681626, 'samples': 16455552, 'steps': 85705, 'loss/train': 0.8583292961120605} 08/31/2021 04:41:20 - INFO - __main__ - Step 85707: {'lr': 0.00019885636316335276, 'samples': 16455744, 'steps': 85706, 'loss/train': 1.238473653793335} 08/31/2021 04:41:21 - INFO - __main__ - Step 85708: {'lr': 0.0001988511686629338, 'samples': 16455936, 'steps': 85707, 'loss/train': 1.0763695240020752} 08/31/2021 04:41:22 - INFO - __main__ - Step 85709: {'lr': 0.00019884597418556166, 'samples': 16456128, 'steps': 85708, 'loss/train': 0.8105754256248474} 08/31/2021 04:41:23 - INFO - __main__ - Step 85710: {'lr': 0.0001988407797312388, 'samples': 16456320, 'steps': 85709, 'loss/train': 1.2224950790405273} 08/31/2021 04:41:23 - INFO - __main__ - Step 85711: {'lr': 0.0001988355852999675, 'samples': 16456512, 'steps': 85710, 'loss/train': 1.016045331954956} 08/31/2021 04:41:23 - INFO - __main__ - Step 85712: {'lr': 0.00019883039089175009, 'samples': 16456704, 'steps': 85711, 'loss/train': 1.0355138778686523} 08/31/2021 04:41:24 - INFO - __main__ - Step 85713: {'lr': 0.00019882519650658885, 'samples': 16456896, 'steps': 85712, 'loss/train': 1.2971553802490234} 08/31/2021 04:41:25 - INFO - __main__ - Step 85714: {'lr': 0.00019882000214448625, 'samples': 16457088, 'steps': 85713, 'loss/train': 1.668594479560852} 08/31/2021 04:41:26 - INFO - __main__ - Step 85715: {'lr': 0.00019881480780544462, 'samples': 16457280, 'steps': 85714, 'loss/train': 0.10671313107013702} 08/31/2021 04:41:26 - INFO - __main__ - Step 85716: {'lr': 0.00019880961348946616, 'samples': 16457472, 'steps': 85715, 'loss/train': 1.2259206771850586} 08/31/2021 04:41:27 - INFO - __main__ - Step 85717: {'lr': 0.00019880441919655333, 'samples': 16457664, 'steps': 85716, 'loss/train': 0.1343860924243927} 08/31/2021 04:41:27 - INFO - __main__ - Step 85718: {'lr': 0.0001987992249267084, 'samples': 16457856, 'steps': 85717, 'loss/train': 0.2685365080833435} 08/31/2021 04:41:28 - INFO - __main__ - Step 85719: {'lr': 0.0001987940306799338, 'samples': 16458048, 'steps': 85718, 'loss/train': 0.9693337678909302} 08/31/2021 04:41:29 - INFO - __main__ - Step 85720: {'lr': 0.00019878883645623176, 'samples': 16458240, 'steps': 85719, 'loss/train': 1.9134207963943481} 08/31/2021 04:41:29 - INFO - __main__ - Step 85721: {'lr': 0.00019878364225560472, 'samples': 16458432, 'steps': 85720, 'loss/train': 1.3445155620574951} 08/31/2021 04:41:30 - INFO - __main__ - Step 85722: {'lr': 0.000198778448078055, 'samples': 16458624, 'steps': 85721, 'loss/train': 1.1373051404953003} 08/31/2021 04:41:30 - INFO - __main__ - Step 85723: {'lr': 0.00019877325392358492, 'samples': 16458816, 'steps': 85722, 'loss/train': 1.3187518119812012} 08/31/2021 04:41:31 - INFO - __main__ - Step 85724: {'lr': 0.0001987680597921968, 'samples': 16459008, 'steps': 85723, 'loss/train': 1.4795050621032715} 08/31/2021 04:41:32 - INFO - __main__ - Step 85725: {'lr': 0.00019876286568389296, 'samples': 16459200, 'steps': 85724, 'loss/train': 1.256821632385254} 08/31/2021 04:41:32 - INFO - __main__ - Step 85726: {'lr': 0.00019875767159867582, 'samples': 16459392, 'steps': 85725, 'loss/train': 0.4471982717514038} 08/31/2021 04:41:33 - INFO - __main__ - Step 85727: {'lr': 0.00019875247753654767, 'samples': 16459584, 'steps': 85726, 'loss/train': 0.9202399253845215} 08/31/2021 04:41:33 - INFO - __main__ - Step 85728: {'lr': 0.0001987472834975109, 'samples': 16459776, 'steps': 85727, 'loss/train': 1.0998363494873047} 08/31/2021 04:41:35 - INFO - __main__ - Step 85729: {'lr': 0.00019874208948156781, 'samples': 16459968, 'steps': 85728, 'loss/train': 1.5855199098587036} 08/31/2021 04:41:35 - INFO - __main__ - Step 85730: {'lr': 0.00019873689548872072, 'samples': 16460160, 'steps': 85729, 'loss/train': 1.0420933961868286} 08/31/2021 04:41:36 - INFO - __main__ - Step 85731: {'lr': 0.00019873170151897201, 'samples': 16460352, 'steps': 85730, 'loss/train': 1.5322450399398804} 08/31/2021 04:41:36 - INFO - __main__ - Step 85732: {'lr': 0.00019872650757232397, 'samples': 16460544, 'steps': 85731, 'loss/train': 1.4869728088378906} 08/31/2021 04:41:37 - INFO - __main__ - Step 85733: {'lr': 0.00019872131364877905, 'samples': 16460736, 'steps': 85732, 'loss/train': 1.2695008516311646} 08/31/2021 04:41:37 - INFO - __main__ - Step 85734: {'lr': 0.00019871611974833949, 'samples': 16460928, 'steps': 85733, 'loss/train': 1.3144652843475342} 08/31/2021 04:41:39 - INFO - __main__ - Step 85735: {'lr': 0.00019871092587100757, 'samples': 16461120, 'steps': 85734, 'loss/train': 0.4428783059120178} 08/31/2021 04:41:39 - INFO - __main__ - Step 85736: {'lr': 0.00019870573201678576, 'samples': 16461312, 'steps': 85735, 'loss/train': 1.4346106052398682} 08/31/2021 04:41:39 - INFO - __main__ - Step 85737: {'lr': 0.00019870053818567637, 'samples': 16461504, 'steps': 85736, 'loss/train': 1.8751273155212402} 08/31/2021 04:41:40 - INFO - __main__ - Step 85738: {'lr': 0.0001986953443776817, 'samples': 16461696, 'steps': 85737, 'loss/train': 0.1799999475479126} 08/31/2021 04:41:40 - INFO - __main__ - Step 85739: {'lr': 0.00019869015059280416, 'samples': 16461888, 'steps': 85738, 'loss/train': 0.05853130668401718} 08/31/2021 04:41:42 - INFO - __main__ - Step 85740: {'lr': 0.00019868495683104603, 'samples': 16462080, 'steps': 85739, 'loss/train': 0.8778491616249084} 08/31/2021 04:41:42 - INFO - __main__ - Step 85741: {'lr': 0.00019867976309240965, 'samples': 16462272, 'steps': 85740, 'loss/train': 0.9869219064712524} 08/31/2021 04:41:43 - INFO - __main__ - Step 85742: {'lr': 0.00019867456937689744, 'samples': 16462464, 'steps': 85741, 'loss/train': 0.076075978577137} 08/31/2021 04:41:43 - INFO - __main__ - Step 85743: {'lr': 0.0001986693756845116, 'samples': 16462656, 'steps': 85742, 'loss/train': 0.08649920672178268} 08/31/2021 04:41:44 - INFO - __main__ - Step 85744: {'lr': 0.00019866418201525463, 'samples': 16462848, 'steps': 85743, 'loss/train': 1.0995509624481201} 08/31/2021 04:41:44 - INFO - __main__ - Step 85745: {'lr': 0.00019865898836912875, 'samples': 16463040, 'steps': 85744, 'loss/train': 0.9908921718597412} 08/31/2021 04:41:45 - INFO - __main__ - Step 85746: {'lr': 0.0001986537947461363, 'samples': 16463232, 'steps': 85745, 'loss/train': 0.10110081732273102} 08/31/2021 04:41:46 - INFO - __main__ - Step 85747: {'lr': 0.00019864860114627967, 'samples': 16463424, 'steps': 85746, 'loss/train': 1.2475398778915405} 08/31/2021 04:41:46 - INFO - __main__ - Step 85748: {'lr': 0.00019864340756956116, 'samples': 16463616, 'steps': 85747, 'loss/train': 1.4393147230148315} 08/31/2021 04:41:47 - INFO - __main__ - Step 85749: {'lr': 0.0001986382140159832, 'samples': 16463808, 'steps': 85748, 'loss/train': 1.2638592720031738} 08/31/2021 04:41:47 - INFO - __main__ - Step 85750: {'lr': 0.00019863302048554803, 'samples': 16464000, 'steps': 85749, 'loss/train': 1.655155062675476} 08/31/2021 04:41:47 - INFO - __main__ - Step 85751: {'lr': 0.00019862782697825803, 'samples': 16464192, 'steps': 85750, 'loss/train': 1.5120643377304077} 08/31/2021 04:41:49 - INFO - __main__ - Step 85752: {'lr': 0.00019862263349411553, 'samples': 16464384, 'steps': 85751, 'loss/train': 1.387354850769043} 08/31/2021 04:41:49 - INFO - __main__ - Step 85753: {'lr': 0.0001986174400331229, 'samples': 16464576, 'steps': 85752, 'loss/train': 1.4867076873779297} 08/31/2021 04:41:50 - INFO - __main__ - Step 85754: {'lr': 0.00019861224659528244, 'samples': 16464768, 'steps': 85753, 'loss/train': 1.130858302116394} 08/31/2021 04:41:50 - INFO - __main__ - Step 85755: {'lr': 0.00019860705318059651, 'samples': 16464960, 'steps': 85754, 'loss/train': 0.5270319581031799} 08/31/2021 04:41:50 - INFO - __main__ - Step 85756: {'lr': 0.0001986018597890676, 'samples': 16465152, 'steps': 85755, 'loss/train': 1.6679980754852295} 08/31/2021 04:41:52 - INFO - __main__ - Step 85757: {'lr': 0.00019859666642069773, 'samples': 16465344, 'steps': 85756, 'loss/train': 1.4037083387374878} 08/31/2021 04:41:53 - INFO - __main__ - Step 85758: {'lr': 0.00019859147307548942, 'samples': 16465536, 'steps': 85757, 'loss/train': 0.9647307991981506} 08/31/2021 04:41:53 - INFO - __main__ - Step 85759: {'lr': 0.00019858627975344502, 'samples': 16465728, 'steps': 85758, 'loss/train': 1.0994702577590942} 08/31/2021 04:41:54 - INFO - __main__ - Step 85760: {'lr': 0.00019858108645456684, 'samples': 16465920, 'steps': 85759, 'loss/train': 1.3640168905258179} 08/31/2021 04:41:54 - INFO - __main__ - Step 85761: {'lr': 0.00019857589317885725, 'samples': 16466112, 'steps': 85760, 'loss/train': 1.2962957620620728} 08/31/2021 04:41:55 - INFO - __main__ - Step 85762: {'lr': 0.00019857069992631855, 'samples': 16466304, 'steps': 85761, 'loss/train': 1.0895555019378662} 08/31/2021 04:41:56 - INFO - __main__ - Step 85763: {'lr': 0.00019856550669695308, 'samples': 16466496, 'steps': 85762, 'loss/train': 1.39971125125885} 08/31/2021 04:41:56 - INFO - __main__ - Step 85764: {'lr': 0.00019856031349076324, 'samples': 16466688, 'steps': 85763, 'loss/train': 1.2541308403015137} 08/31/2021 04:41:56 - INFO - __main__ - Step 85765: {'lr': 0.0001985551203077513, 'samples': 16466880, 'steps': 85764, 'loss/train': 6.227570533752441} 08/31/2021 04:41:57 - INFO - __main__ - Step 85766: {'lr': 0.00019854992714791962, 'samples': 16467072, 'steps': 85765, 'loss/train': 0.5946958065032959} 08/31/2021 04:41:58 - INFO - __main__ - Step 85767: {'lr': 0.00019854473401127056, 'samples': 16467264, 'steps': 85766, 'loss/train': 0.6621997356414795} 08/31/2021 04:41:59 - INFO - __main__ - Step 85768: {'lr': 0.00019853954089780646, 'samples': 16467456, 'steps': 85767, 'loss/train': 1.2026005983352661} 08/31/2021 04:41:59 - INFO - __main__ - Step 85769: {'lr': 0.00019853434780752973, 'samples': 16467648, 'steps': 85768, 'loss/train': 0.9492356777191162} 08/31/2021 04:42:00 - INFO - __main__ - Step 85770: {'lr': 0.00019852915474044257, 'samples': 16467840, 'steps': 85769, 'loss/train': 1.6673866510391235} 08/31/2021 04:42:00 - INFO - __main__ - Step 85771: {'lr': 0.00019852396169654736, 'samples': 16468032, 'steps': 85770, 'loss/train': 0.5880999565124512} 08/31/2021 04:42:01 - INFO - __main__ - Step 85772: {'lr': 0.00019851876867584643, 'samples': 16468224, 'steps': 85771, 'loss/train': 1.0664063692092896} 08/31/2021 04:42:02 - INFO - __main__ - Step 85773: {'lr': 0.00019851357567834217, 'samples': 16468416, 'steps': 85772, 'loss/train': 1.2982765436172485} 08/31/2021 04:42:02 - INFO - __main__ - Step 85774: {'lr': 0.00019850838270403688, 'samples': 16468608, 'steps': 85773, 'loss/train': 0.04807029664516449} 08/31/2021 04:42:03 - INFO - __main__ - Step 85775: {'lr': 0.00019850318975293295, 'samples': 16468800, 'steps': 85774, 'loss/train': 0.8339177966117859} 08/31/2021 04:42:03 - INFO - __main__ - Step 85776: {'lr': 0.00019849799682503265, 'samples': 16468992, 'steps': 85775, 'loss/train': 0.7079260349273682} 08/31/2021 04:42:04 - INFO - __main__ - Step 85777: {'lr': 0.00019849280392033838, 'samples': 16469184, 'steps': 85776, 'loss/train': 2.458911180496216} 08/31/2021 04:42:05 - INFO - __main__ - Step 85778: {'lr': 0.00019848761103885245, 'samples': 16469376, 'steps': 85777, 'loss/train': 1.2811508178710938} 08/31/2021 04:42:05 - INFO - __main__ - Step 85779: {'lr': 0.00019848241818057723, 'samples': 16469568, 'steps': 85778, 'loss/train': 1.599682092666626} 08/31/2021 04:42:06 - INFO - __main__ - Step 85780: {'lr': 0.00019847722534551502, 'samples': 16469760, 'steps': 85779, 'loss/train': 1.0834871530532837} 08/31/2021 04:42:06 - INFO - __main__ - Step 85781: {'lr': 0.0001984720325336682, 'samples': 16469952, 'steps': 85780, 'loss/train': 0.7196716070175171} 08/31/2021 04:42:06 - INFO - __main__ - Step 85782: {'lr': 0.00019846683974503903, 'samples': 16470144, 'steps': 85781, 'loss/train': 0.749151349067688} 08/31/2021 04:42:08 - INFO - __main__ - Step 85783: {'lr': 0.00019846164697963006, 'samples': 16470336, 'steps': 85782, 'loss/train': 1.0186216831207275} 08/31/2021 04:42:09 - INFO - __main__ - Step 85784: {'lr': 0.00019845645423744335, 'samples': 16470528, 'steps': 85783, 'loss/train': 0.9739255309104919} 08/31/2021 04:42:09 - INFO - __main__ - Step 85785: {'lr': 0.0001984512615184814, 'samples': 16470720, 'steps': 85784, 'loss/train': 0.017240464687347412} 08/31/2021 04:42:09 - INFO - __main__ - Step 85786: {'lr': 0.00019844606882274648, 'samples': 16470912, 'steps': 85785, 'loss/train': 0.5817976593971252} 08/31/2021 04:42:10 - INFO - __main__ - Step 85787: {'lr': 0.00019844087615024099, 'samples': 16471104, 'steps': 85786, 'loss/train': 1.1918673515319824} 08/31/2021 04:42:11 - INFO - __main__ - Step 85788: {'lr': 0.00019843568350096723, 'samples': 16471296, 'steps': 85787, 'loss/train': 1.2832894325256348} 08/31/2021 04:42:12 - INFO - __main__ - Step 85789: {'lr': 0.00019843049087492755, 'samples': 16471488, 'steps': 85788, 'loss/train': 1.0263898372650146} 08/31/2021 04:42:12 - INFO - __main__ - Step 85790: {'lr': 0.0001984252982721243, 'samples': 16471680, 'steps': 85789, 'loss/train': 2.622922658920288} 08/31/2021 04:42:12 - INFO - __main__ - Step 85791: {'lr': 0.0001984201056925598, 'samples': 16471872, 'steps': 85790, 'loss/train': 0.7493818402290344} 08/31/2021 04:42:13 - INFO - __main__ - Step 85792: {'lr': 0.00019841491313623644, 'samples': 16472064, 'steps': 85791, 'loss/train': 1.5698704719543457} 08/31/2021 04:42:13 - INFO - __main__ - Step 85793: {'lr': 0.00019840972060315652, 'samples': 16472256, 'steps': 85792, 'loss/train': 1.7074220180511475} 08/31/2021 04:42:15 - INFO - __main__ - Step 85794: {'lr': 0.00019840452809332236, 'samples': 16472448, 'steps': 85793, 'loss/train': 1.1523548364639282} 08/31/2021 04:42:15 - INFO - __main__ - Step 85795: {'lr': 0.00019839933560673634, 'samples': 16472640, 'steps': 85794, 'loss/train': 1.3439507484436035} 08/31/2021 04:42:15 - INFO - __main__ - Step 85796: {'lr': 0.00019839414314340087, 'samples': 16472832, 'steps': 85795, 'loss/train': 1.343683123588562} 08/31/2021 04:42:16 - INFO - __main__ - Step 85797: {'lr': 0.0001983889507033181, 'samples': 16473024, 'steps': 85796, 'loss/train': 0.801470935344696} 08/31/2021 04:42:16 - INFO - __main__ - Step 85798: {'lr': 0.00019838375828649048, 'samples': 16473216, 'steps': 85797, 'loss/train': 0.5788127183914185} 08/31/2021 04:42:18 - INFO - __main__ - Step 85799: {'lr': 0.00019837856589292036, 'samples': 16473408, 'steps': 85798, 'loss/train': 0.7152830362319946} 08/31/2021 04:42:19 - INFO - __main__ - Step 85800: {'lr': 0.00019837337352261004, 'samples': 16473600, 'steps': 85799, 'loss/train': 0.6578176021575928} 08/31/2021 04:42:19 - INFO - __main__ - Step 85801: {'lr': 0.00019836818117556187, 'samples': 16473792, 'steps': 85800, 'loss/train': 0.9710917472839355} 08/31/2021 04:42:19 - INFO - __main__ - Step 85802: {'lr': 0.00019836298885177826, 'samples': 16473984, 'steps': 85801, 'loss/train': 1.207189679145813} 08/31/2021 04:42:20 - INFO - __main__ - Step 85803: {'lr': 0.00019835779655126145, 'samples': 16474176, 'steps': 85802, 'loss/train': 0.15288816392421722} 08/31/2021 04:42:21 - INFO - __main__ - Step 85804: {'lr': 0.0001983526042740138, 'samples': 16474368, 'steps': 85803, 'loss/train': 0.09601065516471863} 08/31/2021 04:42:22 - INFO - __main__ - Step 85805: {'lr': 0.0001983474120200377, 'samples': 16474560, 'steps': 85804, 'loss/train': 1.2719676494598389} 08/31/2021 04:42:22 - INFO - __main__ - Step 85806: {'lr': 0.00019834221978933542, 'samples': 16474752, 'steps': 85805, 'loss/train': 0.19857801496982574} 08/31/2021 04:42:23 - INFO - __main__ - Step 85807: {'lr': 0.0001983370275819094, 'samples': 16474944, 'steps': 85806, 'loss/train': 0.8165096640586853} 08/31/2021 04:42:23 - INFO - __main__ - Step 85808: {'lr': 0.00019833183539776187, 'samples': 16475136, 'steps': 85807, 'loss/train': 1.37930428981781} 08/31/2021 04:42:23 - INFO - __main__ - Step 85809: {'lr': 0.00019832664323689533, 'samples': 16475328, 'steps': 85808, 'loss/train': 1.0861889123916626} 08/31/2021 04:42:25 - INFO - __main__ - Step 85810: {'lr': 0.0001983214510993119, 'samples': 16475520, 'steps': 85809, 'loss/train': 1.2672126293182373} 08/31/2021 04:42:26 - INFO - __main__ - Step 85811: {'lr': 0.00019831625898501405, 'samples': 16475712, 'steps': 85810, 'loss/train': 1.2334827184677124} 08/31/2021 04:42:26 - INFO - __main__ - Step 85812: {'lr': 0.00019831106689400407, 'samples': 16475904, 'steps': 85811, 'loss/train': 1.0996516942977905} 08/31/2021 04:42:26 - INFO - __main__ - Step 85813: {'lr': 0.00019830587482628435, 'samples': 16476096, 'steps': 85812, 'loss/train': 1.447413444519043} 08/31/2021 04:42:27 - INFO - __main__ - Step 85814: {'lr': 0.0001983006827818572, 'samples': 16476288, 'steps': 85813, 'loss/train': 0.9377215504646301} 08/31/2021 04:42:28 - INFO - __main__ - Step 85815: {'lr': 0.00019829549076072494, 'samples': 16476480, 'steps': 85814, 'loss/train': 1.2748146057128906} 08/31/2021 04:42:29 - INFO - __main__ - Step 85816: {'lr': 0.00019829029876288994, 'samples': 16476672, 'steps': 85815, 'loss/train': 1.245263934135437} 08/31/2021 04:42:29 - INFO - __main__ - Step 85817: {'lr': 0.00019828510678835456, 'samples': 16476864, 'steps': 85816, 'loss/train': 0.8163567185401917} 08/31/2021 04:42:29 - INFO - __main__ - Step 85818: {'lr': 0.00019827991483712111, 'samples': 16477056, 'steps': 85817, 'loss/train': 1.5248998403549194} 08/31/2021 04:42:30 - INFO - __main__ - Step 85819: {'lr': 0.00019827472290919192, 'samples': 16477248, 'steps': 85818, 'loss/train': 1.740402340888977} 08/31/2021 04:42:32 - INFO - __main__ - Step 85820: {'lr': 0.00019826953100456933, 'samples': 16477440, 'steps': 85819, 'loss/train': 1.6193602085113525} 08/31/2021 04:42:32 - INFO - __main__ - Step 85821: {'lr': 0.0001982643391232557, 'samples': 16477632, 'steps': 85820, 'loss/train': 1.0045785903930664} 08/31/2021 04:42:33 - INFO - __main__ - Step 85822: {'lr': 0.00019825914726525335, 'samples': 16477824, 'steps': 85821, 'loss/train': 0.8472772836685181} 08/31/2021 04:42:33 - INFO - __main__ - Step 85823: {'lr': 0.00019825395543056476, 'samples': 16478016, 'steps': 85822, 'loss/train': 0.9995690584182739} 08/31/2021 04:42:33 - INFO - __main__ - Step 85824: {'lr': 0.00019824876361919204, 'samples': 16478208, 'steps': 85823, 'loss/train': 0.35091516375541687} 08/31/2021 04:42:34 - INFO - __main__ - Step 85825: {'lr': 0.00019824357183113758, 'samples': 16478400, 'steps': 85824, 'loss/train': 1.7685043811798096} 08/31/2021 04:42:35 - INFO - __main__ - Step 85826: {'lr': 0.00019823838006640383, 'samples': 16478592, 'steps': 85825, 'loss/train': 1.9484490156173706} 08/31/2021 04:42:36 - INFO - __main__ - Step 85827: {'lr': 0.00019823318832499302, 'samples': 16478784, 'steps': 85826, 'loss/train': 1.1479928493499756} 08/31/2021 04:42:36 - INFO - __main__ - Step 85828: {'lr': 0.00019822799660690755, 'samples': 16478976, 'steps': 85827, 'loss/train': 1.0540274381637573} 08/31/2021 04:42:36 - INFO - __main__ - Step 85829: {'lr': 0.00019822280491214975, 'samples': 16479168, 'steps': 85828, 'loss/train': 0.8597629070281982} 08/31/2021 04:42:37 - INFO - __main__ - Step 85830: {'lr': 0.00019821761324072197, 'samples': 16479360, 'steps': 85829, 'loss/train': 1.1756255626678467} 08/31/2021 04:42:38 - INFO - __main__ - Step 85831: {'lr': 0.0001982124215926265, 'samples': 16479552, 'steps': 85830, 'loss/train': 1.3792766332626343} 08/31/2021 04:42:39 - INFO - __main__ - Step 85832: {'lr': 0.0001982072299678657, 'samples': 16479744, 'steps': 85831, 'loss/train': 1.1033917665481567} 08/31/2021 04:42:39 - INFO - __main__ - Step 85833: {'lr': 0.000198202038366442, 'samples': 16479936, 'steps': 85832, 'loss/train': 1.135403037071228} 08/31/2021 04:42:39 - INFO - __main__ - Step 85834: {'lr': 0.00019819684678835765, 'samples': 16480128, 'steps': 85833, 'loss/train': 0.620194673538208} 08/31/2021 04:42:40 - INFO - __main__ - Step 85835: {'lr': 0.000198191655233615, 'samples': 16480320, 'steps': 85834, 'loss/train': 0.7884411215782166} 08/31/2021 04:42:41 - INFO - __main__ - Step 85836: {'lr': 0.00019818646370221637, 'samples': 16480512, 'steps': 85835, 'loss/train': 0.9501611590385437} 08/31/2021 04:42:42 - INFO - __main__ - Step 85837: {'lr': 0.00019818127219416412, 'samples': 16480704, 'steps': 85836, 'loss/train': 1.087540864944458} 08/31/2021 04:42:42 - INFO - __main__ - Step 85838: {'lr': 0.0001981760807094606, 'samples': 16480896, 'steps': 85837, 'loss/train': 0.7621690034866333} 08/31/2021 04:42:42 - INFO - __main__ - Step 85839: {'lr': 0.0001981708892481081, 'samples': 16481088, 'steps': 85838, 'loss/train': 1.107860803604126} 08/31/2021 04:42:43 - INFO - __main__ - Step 85840: {'lr': 0.00019816569781010902, 'samples': 16481280, 'steps': 85839, 'loss/train': 0.5137778520584106} 08/31/2021 04:42:45 - INFO - __main__ - Step 85841: {'lr': 0.00019816050639546564, 'samples': 16481472, 'steps': 85840, 'loss/train': 1.662595272064209} 08/31/2021 04:42:45 - INFO - __main__ - Step 85842: {'lr': 0.0001981553150041804, 'samples': 16481664, 'steps': 85841, 'loss/train': 0.9110990762710571} 08/31/2021 04:42:45 - INFO - __main__ - Step 85843: {'lr': 0.0001981501236362555, 'samples': 16481856, 'steps': 85842, 'loss/train': 1.1942527294158936} 08/31/2021 04:42:46 - INFO - __main__ - Step 85844: {'lr': 0.00019814493229169342, 'samples': 16482048, 'steps': 85843, 'loss/train': 1.1202034950256348} 08/31/2021 04:42:46 - INFO - __main__ - Step 85845: {'lr': 0.00019813974097049648, 'samples': 16482240, 'steps': 85844, 'loss/train': 1.2353880405426025} 08/31/2021 04:42:48 - INFO - __main__ - Step 85846: {'lr': 0.0001981345496726669, 'samples': 16482432, 'steps': 85845, 'loss/train': 1.1669840812683105} 08/31/2021 04:42:49 - INFO - __main__ - Step 85847: {'lr': 0.00019812935839820707, 'samples': 16482624, 'steps': 85846, 'loss/train': 2.0257225036621094} 08/31/2021 04:42:49 - INFO - __main__ - Step 85848: {'lr': 0.0001981241671471194, 'samples': 16482816, 'steps': 85847, 'loss/train': 1.2195359468460083} 08/31/2021 04:42:49 - INFO - __main__ - Step 85849: {'lr': 0.00019811897591940614, 'samples': 16483008, 'steps': 85848, 'loss/train': 0.08009442687034607} 08/31/2021 04:42:50 - INFO - __main__ - Step 85850: {'lr': 0.00019811378471506976, 'samples': 16483200, 'steps': 85849, 'loss/train': 0.87320876121521} 08/31/2021 04:42:50 - INFO - __main__ - Step 85851: {'lr': 0.0001981085935341124, 'samples': 16483392, 'steps': 85850, 'loss/train': 1.7258939743041992} 08/31/2021 04:42:52 - INFO - __main__ - Step 85852: {'lr': 0.00019810340237653653, 'samples': 16483584, 'steps': 85851, 'loss/train': 1.2949479818344116} 08/31/2021 04:42:52 - INFO - __main__ - Step 85853: {'lr': 0.00019809821124234448, 'samples': 16483776, 'steps': 85852, 'loss/train': 1.2107455730438232} 08/31/2021 04:42:53 - INFO - __main__ - Step 85854: {'lr': 0.00019809302013153857, 'samples': 16483968, 'steps': 85853, 'loss/train': 0.9370104670524597} 08/31/2021 04:42:53 - INFO - __main__ - Step 85855: {'lr': 0.00019808782904412114, 'samples': 16484160, 'steps': 85854, 'loss/train': 0.6196433901786804} 08/31/2021 04:42:53 - INFO - __main__ - Step 85856: {'lr': 0.00019808263798009457, 'samples': 16484352, 'steps': 85855, 'loss/train': 0.08254914730787277} 08/31/2021 04:42:54 - INFO - __main__ - Step 85857: {'lr': 0.00019807744693946114, 'samples': 16484544, 'steps': 85856, 'loss/train': 1.4491654634475708} 08/31/2021 04:42:55 - INFO - __main__ - Step 85858: {'lr': 0.0001980722559222232, 'samples': 16484736, 'steps': 85857, 'loss/train': 2.159968137741089} 08/31/2021 04:42:55 - INFO - __main__ - Step 85859: {'lr': 0.0001980670649283831, 'samples': 16484928, 'steps': 85858, 'loss/train': 1.4751532077789307} 08/31/2021 04:42:56 - INFO - __main__ - Step 85860: {'lr': 0.00019806187395794318, 'samples': 16485120, 'steps': 85859, 'loss/train': 1.3456714153289795} 08/31/2021 04:42:56 - INFO - __main__ - Step 85861: {'lr': 0.00019805668301090578, 'samples': 16485312, 'steps': 85860, 'loss/train': 1.1614784002304077} 08/31/2021 04:42:56 - INFO - __main__ - Step 85862: {'lr': 0.00019805149208727325, 'samples': 16485504, 'steps': 85861, 'loss/train': 0.5423374772071838} 08/31/2021 04:42:58 - INFO - __main__ - Step 85863: {'lr': 0.0001980463011870479, 'samples': 16485696, 'steps': 85862, 'loss/train': 1.058182954788208} 08/31/2021 04:42:58 - INFO - __main__ - Step 85864: {'lr': 0.00019804111031023212, 'samples': 16485888, 'steps': 85863, 'loss/train': 0.03270743414759636} 08/31/2021 04:42:59 - INFO - __main__ - Step 85865: {'lr': 0.00019803591945682816, 'samples': 16486080, 'steps': 85864, 'loss/train': 0.33318454027175903} 08/31/2021 04:42:59 - INFO - __main__ - Step 85866: {'lr': 0.00019803072862683847, 'samples': 16486272, 'steps': 85865, 'loss/train': 1.0634464025497437} 08/31/2021 04:43:00 - INFO - __main__ - Step 85867: {'lr': 0.00019802553782026532, 'samples': 16486464, 'steps': 85866, 'loss/train': 1.0231913328170776} 08/31/2021 04:43:01 - INFO - __main__ - Step 85868: {'lr': 0.00019802034703711102, 'samples': 16486656, 'steps': 85867, 'loss/train': 1.2271825075149536} 08/31/2021 04:43:02 - INFO - __main__ - Step 85869: {'lr': 0.00019801515627737798, 'samples': 16486848, 'steps': 85868, 'loss/train': 1.1628670692443848} 08/31/2021 04:43:02 - INFO - __main__ - Step 85870: {'lr': 0.00019800996554106848, 'samples': 16487040, 'steps': 85869, 'loss/train': 1.478384017944336} 08/31/2021 04:43:03 - INFO - __main__ - Step 85871: {'lr': 0.0001980047748281849, 'samples': 16487232, 'steps': 85870, 'loss/train': 0.8939818739891052} 08/31/2021 04:43:03 - INFO - __main__ - Step 85872: {'lr': 0.00019799958413872957, 'samples': 16487424, 'steps': 85871, 'loss/train': 1.0184139013290405} 08/31/2021 04:43:05 - INFO - __main__ - Step 85873: {'lr': 0.0001979943934727048, 'samples': 16487616, 'steps': 85872, 'loss/train': 0.8988059163093567} 08/31/2021 04:43:05 - INFO - __main__ - Step 85874: {'lr': 0.000197989202830113, 'samples': 16487808, 'steps': 85873, 'loss/train': 1.2114598751068115} 08/31/2021 04:43:05 - INFO - __main__ - Step 85875: {'lr': 0.00019798401221095643, 'samples': 16488000, 'steps': 85874, 'loss/train': 0.45483338832855225} 08/31/2021 04:43:06 - INFO - __main__ - Step 85876: {'lr': 0.00019797882161523748, 'samples': 16488192, 'steps': 85875, 'loss/train': 1.7097147703170776} 08/31/2021 04:43:06 - INFO - __main__ - Step 85877: {'lr': 0.00019797363104295853, 'samples': 16488384, 'steps': 85876, 'loss/train': 0.9332416653633118} 08/31/2021 04:43:07 - INFO - __main__ - Step 85878: {'lr': 0.00019796844049412184, 'samples': 16488576, 'steps': 85877, 'loss/train': 1.390376329421997} 08/31/2021 04:43:08 - INFO - __main__ - Step 85879: {'lr': 0.0001979632499687297, 'samples': 16488768, 'steps': 85878, 'loss/train': 0.971798300743103} 08/31/2021 04:43:09 - INFO - __main__ - Step 85880: {'lr': 0.00019795805946678453, 'samples': 16488960, 'steps': 85879, 'loss/train': 2.1267764568328857} 08/31/2021 04:43:09 - INFO - __main__ - Step 85881: {'lr': 0.00019795286898828865, 'samples': 16489152, 'steps': 85880, 'loss/train': 2.04067063331604} 08/31/2021 04:43:09 - INFO - __main__ - Step 85882: {'lr': 0.00019794767853324442, 'samples': 16489344, 'steps': 85881, 'loss/train': 1.262587308883667} 08/31/2021 04:43:10 - INFO - __main__ - Step 85883: {'lr': 0.00019794248810165414, 'samples': 16489536, 'steps': 85882, 'loss/train': 1.6442190408706665} 08/31/2021 04:43:11 - INFO - __main__ - Step 85884: {'lr': 0.0001979372976935202, 'samples': 16489728, 'steps': 85883, 'loss/train': 0.6829435229301453} 08/31/2021 04:43:12 - INFO - __main__ - Step 85885: {'lr': 0.0001979321073088449, 'samples': 16489920, 'steps': 85884, 'loss/train': 1.547692894935608} 08/31/2021 04:43:12 - INFO - __main__ - Step 85886: {'lr': 0.00019792691694763058, 'samples': 16490112, 'steps': 85885, 'loss/train': 1.108771800994873} 08/31/2021 04:43:13 - INFO - __main__ - Step 85887: {'lr': 0.0001979217266098796, 'samples': 16490304, 'steps': 85886, 'loss/train': 1.1182574033737183} 08/31/2021 04:43:13 - INFO - __main__ - Step 85888: {'lr': 0.00019791653629559424, 'samples': 16490496, 'steps': 85887, 'loss/train': 1.3848344087600708} 08/31/2021 04:43:13 - INFO - __main__ - Step 85889: {'lr': 0.00019791134600477694, 'samples': 16490688, 'steps': 85888, 'loss/train': 0.4258202314376831} 08/31/2021 04:43:15 - INFO - __main__ - Step 85890: {'lr': 0.00019790615573743009, 'samples': 16490880, 'steps': 85889, 'loss/train': 0.9729516506195068} 08/31/2021 04:43:15 - INFO - __main__ - Step 85891: {'lr': 0.0001979009654935558, 'samples': 16491072, 'steps': 85890, 'loss/train': 0.8688183426856995} 08/31/2021 04:43:16 - INFO - __main__ - Step 85892: {'lr': 0.00019789577527315653, 'samples': 16491264, 'steps': 85891, 'loss/train': 0.8861263990402222} 08/31/2021 04:43:16 - INFO - __main__ - Step 85893: {'lr': 0.0001978905850762346, 'samples': 16491456, 'steps': 85892, 'loss/train': 1.1036591529846191} 08/31/2021 04:43:16 - INFO - __main__ - Step 85894: {'lr': 0.0001978853949027924, 'samples': 16491648, 'steps': 85893, 'loss/train': 0.998386561870575} 08/31/2021 04:43:18 - INFO - __main__ - Step 85895: {'lr': 0.00019788020475283223, 'samples': 16491840, 'steps': 85894, 'loss/train': 1.269556999206543} 08/31/2021 04:43:18 - INFO - __main__ - Step 85896: {'lr': 0.00019787501462635644, 'samples': 16492032, 'steps': 85895, 'loss/train': 2.022300958633423} 08/31/2021 04:43:18 - INFO - __main__ - Step 85897: {'lr': 0.00019786982452336732, 'samples': 16492224, 'steps': 85896, 'loss/train': 1.0326993465423584} 08/31/2021 04:43:19 - INFO - __main__ - Step 85898: {'lr': 0.00019786463444386733, 'samples': 16492416, 'steps': 85897, 'loss/train': 1.1219388246536255} 08/31/2021 04:43:19 - INFO - __main__ - Step 85899: {'lr': 0.00019785944438785867, 'samples': 16492608, 'steps': 85898, 'loss/train': 1.4327317476272583} 08/31/2021 04:43:21 - INFO - __main__ - Step 85900: {'lr': 0.00019785425435534377, 'samples': 16492800, 'steps': 85899, 'loss/train': 0.8673099875450134} 08/31/2021 04:43:21 - INFO - __main__ - Step 85901: {'lr': 0.0001978490643463249, 'samples': 16492992, 'steps': 85900, 'loss/train': 0.7253594398498535} 08/31/2021 04:43:21 - INFO - __main__ - Step 85902: {'lr': 0.00019784387436080447, 'samples': 16493184, 'steps': 85901, 'loss/train': 1.3948673009872437} 08/31/2021 04:43:22 - INFO - __main__ - Step 85903: {'lr': 0.00019783868439878478, 'samples': 16493376, 'steps': 85902, 'loss/train': 1.1237818002700806} 08/31/2021 04:43:22 - INFO - __main__ - Step 85904: {'lr': 0.00019783349446026826, 'samples': 16493568, 'steps': 85903, 'loss/train': 1.1804988384246826} 08/31/2021 04:43:24 - INFO - __main__ - Step 85905: {'lr': 0.0001978283045452571, 'samples': 16493760, 'steps': 85904, 'loss/train': 1.2277191877365112} 08/31/2021 04:43:24 - INFO - __main__ - Step 85906: {'lr': 0.0001978231146537537, 'samples': 16493952, 'steps': 85905, 'loss/train': 0.9996578693389893} 08/31/2021 04:43:25 - INFO - __main__ - Step 85907: {'lr': 0.00019781792478576035, 'samples': 16494144, 'steps': 85906, 'loss/train': 0.9683232307434082} 08/31/2021 04:43:25 - INFO - __main__ - Step 85908: {'lr': 0.00019781273494127947, 'samples': 16494336, 'steps': 85907, 'loss/train': 1.025559425354004} 08/31/2021 04:43:25 - INFO - __main__ - Step 85909: {'lr': 0.00019780754512031335, 'samples': 16494528, 'steps': 85908, 'loss/train': 1.1452440023422241} 08/31/2021 04:43:27 - INFO - __main__ - Step 85910: {'lr': 0.00019780235532286435, 'samples': 16494720, 'steps': 85909, 'loss/train': 0.8166155219078064} 08/31/2021 04:43:27 - INFO - __main__ - Step 85911: {'lr': 0.00019779716554893482, 'samples': 16494912, 'steps': 85910, 'loss/train': 0.653001606464386} 08/31/2021 04:43:28 - INFO - __main__ - Step 85912: {'lr': 0.00019779197579852705, 'samples': 16495104, 'steps': 85911, 'loss/train': 1.4115644693374634} 08/31/2021 04:43:28 - INFO - __main__ - Step 85913: {'lr': 0.00019778678607164347, 'samples': 16495296, 'steps': 85912, 'loss/train': 0.6206653118133545} 08/31/2021 04:43:28 - INFO - __main__ - Step 85914: {'lr': 0.0001977815963682863, 'samples': 16495488, 'steps': 85913, 'loss/train': 0.6718196868896484} 08/31/2021 04:43:29 - INFO - __main__ - Step 85915: {'lr': 0.00019777640668845796, 'samples': 16495680, 'steps': 85914, 'loss/train': 0.5166252255439758} 08/31/2021 04:43:30 - INFO - __main__ - Step 85916: {'lr': 0.00019777121703216076, 'samples': 16495872, 'steps': 85915, 'loss/train': 0.08422800153493881} 08/31/2021 04:43:31 - INFO - __main__ - Step 85917: {'lr': 0.00019776602739939714, 'samples': 16496064, 'steps': 85916, 'loss/train': 0.8362308144569397} 08/31/2021 04:43:31 - INFO - __main__ - Step 85918: {'lr': 0.00019776083779016927, 'samples': 16496256, 'steps': 85917, 'loss/train': 1.7834045886993408} 08/31/2021 04:43:31 - INFO - __main__ - Step 85919: {'lr': 0.00019775564820447952, 'samples': 16496448, 'steps': 85918, 'loss/train': 1.2283291816711426} 08/31/2021 04:43:32 - INFO - __main__ - Step 85920: {'lr': 0.0001977504586423303, 'samples': 16496640, 'steps': 85919, 'loss/train': 1.2329466342926025} 08/31/2021 04:43:34 - INFO - __main__ - Step 85921: {'lr': 0.0001977452691037239, 'samples': 16496832, 'steps': 85920, 'loss/train': 1.0533615350723267} 08/31/2021 04:43:34 - INFO - __main__ - Step 85922: {'lr': 0.00019774007958866266, 'samples': 16497024, 'steps': 85921, 'loss/train': 1.6535537242889404} 08/31/2021 04:43:35 - INFO - __main__ - Step 85923: {'lr': 0.00019773489009714896, 'samples': 16497216, 'steps': 85922, 'loss/train': 1.4483823776245117} 08/31/2021 04:43:35 - INFO - __main__ - Step 85924: {'lr': 0.0001977297006291851, 'samples': 16497408, 'steps': 85923, 'loss/train': 0.8142130374908447} 08/31/2021 04:43:35 - INFO - __main__ - Step 85925: {'lr': 0.00019772451118477344, 'samples': 16497600, 'steps': 85924, 'loss/train': 1.332254409790039} 08/31/2021 04:43:37 - INFO - __main__ - Step 85926: {'lr': 0.0001977193217639163, 'samples': 16497792, 'steps': 85925, 'loss/train': 1.4645923376083374} 08/31/2021 04:43:37 - INFO - __main__ - Step 85927: {'lr': 0.00019771413236661602, 'samples': 16497984, 'steps': 85926, 'loss/train': 0.2511695921421051} 08/31/2021 04:43:38 - INFO - __main__ - Step 85928: {'lr': 0.00019770894299287495, 'samples': 16498176, 'steps': 85927, 'loss/train': 0.3959660530090332} 08/31/2021 04:43:38 - INFO - __main__ - Step 85929: {'lr': 0.00019770375364269545, 'samples': 16498368, 'steps': 85928, 'loss/train': 1.5253826379776} 08/31/2021 04:43:38 - INFO - __main__ - Step 85930: {'lr': 0.0001976985643160799, 'samples': 16498560, 'steps': 85929, 'loss/train': 1.2833400964736938} 08/31/2021 04:43:39 - INFO - __main__ - Step 85931: {'lr': 0.00019769337501303048, 'samples': 16498752, 'steps': 85930, 'loss/train': 1.1373811960220337} 08/31/2021 04:43:40 - INFO - __main__ - Step 85932: {'lr': 0.00019768818573354964, 'samples': 16498944, 'steps': 85931, 'loss/train': 1.0221612453460693} 08/31/2021 04:43:41 - INFO - __main__ - Step 85933: {'lr': 0.00019768299647763966, 'samples': 16499136, 'steps': 85932, 'loss/train': 1.3015300035476685} 08/31/2021 04:43:41 - INFO - __main__ - Step 85934: {'lr': 0.00019767780724530294, 'samples': 16499328, 'steps': 85933, 'loss/train': 1.408957600593567} 08/31/2021 04:43:41 - INFO - __main__ - Step 85935: {'lr': 0.00019767261803654176, 'samples': 16499520, 'steps': 85934, 'loss/train': 0.992297887802124} 08/31/2021 04:43:42 - INFO - __main__ - Step 85936: {'lr': 0.00019766742885135854, 'samples': 16499712, 'steps': 85935, 'loss/train': 0.8372706770896912} 08/31/2021 04:43:43 - INFO - __main__ - Step 85937: {'lr': 0.00019766223968975552, 'samples': 16499904, 'steps': 85936, 'loss/train': 1.264384388923645} 08/31/2021 04:43:44 - INFO - __main__ - Step 85938: {'lr': 0.00019765705055173512, 'samples': 16500096, 'steps': 85937, 'loss/train': 1.0307915210723877} 08/31/2021 04:43:44 - INFO - __main__ - Step 85939: {'lr': 0.00019765186143729963, 'samples': 16500288, 'steps': 85938, 'loss/train': 1.3477476835250854} 08/31/2021 04:43:45 - INFO - __main__ - Step 85940: {'lr': 0.0001976466723464514, 'samples': 16500480, 'steps': 85939, 'loss/train': 0.11957249790430069} 08/31/2021 04:43:45 - INFO - __main__ - Step 85941: {'lr': 0.0001976414832791928, 'samples': 16500672, 'steps': 85940, 'loss/train': 0.11841892451047897} 08/31/2021 04:43:45 - INFO - __main__ - Step 85942: {'lr': 0.00019763629423552608, 'samples': 16500864, 'steps': 85941, 'loss/train': 1.2543137073516846} 08/31/2021 04:43:47 - INFO - __main__ - Step 85943: {'lr': 0.00019763110521545368, 'samples': 16501056, 'steps': 85942, 'loss/train': 1.0905301570892334} 08/31/2021 04:43:47 - INFO - __main__ - Step 85944: {'lr': 0.000197625916218978, 'samples': 16501248, 'steps': 85943, 'loss/train': 1.1023472547531128} 08/31/2021 04:43:48 - INFO - __main__ - Step 85945: {'lr': 0.00019762072724610117, 'samples': 16501440, 'steps': 85944, 'loss/train': 0.7532040476799011} 08/31/2021 04:43:48 - INFO - __main__ - Step 85946: {'lr': 0.00019761553829682562, 'samples': 16501632, 'steps': 85945, 'loss/train': 1.1541903018951416} 08/31/2021 04:43:48 - INFO - __main__ - Step 85947: {'lr': 0.00019761034937115373, 'samples': 16501824, 'steps': 85946, 'loss/train': 0.9002530574798584} 08/31/2021 04:43:50 - INFO - __main__ - Step 85948: {'lr': 0.00019760516046908778, 'samples': 16502016, 'steps': 85947, 'loss/train': 1.1368850469589233} 08/31/2021 04:43:50 - INFO - __main__ - Step 85949: {'lr': 0.00019759997159063015, 'samples': 16502208, 'steps': 85948, 'loss/train': 0.8034539222717285} 08/31/2021 04:43:51 - INFO - __main__ - Step 85950: {'lr': 0.00019759478273578314, 'samples': 16502400, 'steps': 85949, 'loss/train': 0.4362964332103729} 08/31/2021 04:43:51 - INFO - __main__ - Step 85951: {'lr': 0.00019758959390454915, 'samples': 16502592, 'steps': 85950, 'loss/train': 1.3080849647521973} 08/31/2021 04:43:51 - INFO - __main__ - Step 85952: {'lr': 0.00019758440509693042, 'samples': 16502784, 'steps': 85951, 'loss/train': 0.7379423379898071} 08/31/2021 04:43:53 - INFO - __main__ - Step 85953: {'lr': 0.0001975792163129294, 'samples': 16502976, 'steps': 85952, 'loss/train': 1.8061219453811646} 08/31/2021 04:43:53 - INFO - __main__ - Step 85954: {'lr': 0.00019757402755254838, 'samples': 16503168, 'steps': 85953, 'loss/train': 1.4830315113067627} 08/31/2021 04:43:54 - INFO - __main__ - Step 85955: {'lr': 0.00019756883881578969, 'samples': 16503360, 'steps': 85954, 'loss/train': 1.4888964891433716} 08/31/2021 04:43:54 - INFO - __main__ - Step 85956: {'lr': 0.00019756365010265565, 'samples': 16503552, 'steps': 85955, 'loss/train': 1.3756306171417236} 08/31/2021 04:43:54 - INFO - __main__ - Step 85957: {'lr': 0.00019755846141314873, 'samples': 16503744, 'steps': 85956, 'loss/train': 1.4050185680389404} 08/31/2021 04:43:56 - INFO - __main__ - Step 85958: {'lr': 0.00019755327274727105, 'samples': 16503936, 'steps': 85957, 'loss/train': 1.1263841390609741} 08/31/2021 04:43:57 - INFO - __main__ - Step 85959: {'lr': 0.00019754808410502505, 'samples': 16504128, 'steps': 85958, 'loss/train': 0.9894527196884155} 08/31/2021 04:43:57 - INFO - __main__ - Step 85960: {'lr': 0.00019754289548641312, 'samples': 16504320, 'steps': 85959, 'loss/train': 1.115617036819458} 08/31/2021 04:43:58 - INFO - __main__ - Step 85961: {'lr': 0.00019753770689143752, 'samples': 16504512, 'steps': 85960, 'loss/train': 1.3745753765106201} 08/31/2021 04:43:58 - INFO - __main__ - Step 85962: {'lr': 0.00019753251832010062, 'samples': 16504704, 'steps': 85961, 'loss/train': 1.2111514806747437} 08/31/2021 04:43:58 - INFO - __main__ - Step 85963: {'lr': 0.00019752732977240472, 'samples': 16504896, 'steps': 85962, 'loss/train': 1.3454852104187012} 08/31/2021 04:44:00 - INFO - __main__ - Step 85964: {'lr': 0.00019752214124835226, 'samples': 16505088, 'steps': 85963, 'loss/train': 0.13571837544441223} 08/31/2021 04:44:00 - INFO - __main__ - Step 85965: {'lr': 0.0001975169527479455, 'samples': 16505280, 'steps': 85964, 'loss/train': 1.1472136974334717} 08/31/2021 04:44:01 - INFO - __main__ - Step 85966: {'lr': 0.00019751176427118677, 'samples': 16505472, 'steps': 85965, 'loss/train': 0.641965925693512} 08/31/2021 04:44:01 - INFO - __main__ - Step 85967: {'lr': 0.00019750657581807843, 'samples': 16505664, 'steps': 85966, 'loss/train': 0.9480318427085876} 08/31/2021 04:44:01 - INFO - __main__ - Step 85968: {'lr': 0.00019750138738862283, 'samples': 16505856, 'steps': 85967, 'loss/train': 2.03071665763855} 08/31/2021 04:44:03 - INFO - __main__ - Step 85969: {'lr': 0.00019749619898282235, 'samples': 16506048, 'steps': 85968, 'loss/train': 1.3010202646255493} 08/31/2021 04:44:03 - INFO - __main__ - Step 85970: {'lr': 0.0001974910106006792, 'samples': 16506240, 'steps': 85969, 'loss/train': 1.7214939594268799} 08/31/2021 04:44:04 - INFO - __main__ - Step 85971: {'lr': 0.00019748582224219586, 'samples': 16506432, 'steps': 85970, 'loss/train': 1.3650089502334595} 08/31/2021 04:44:04 - INFO - __main__ - Step 85972: {'lr': 0.00019748063390737452, 'samples': 16506624, 'steps': 85971, 'loss/train': 0.21768885850906372} 08/31/2021 04:44:04 - INFO - __main__ - Step 85973: {'lr': 0.0001974754455962176, 'samples': 16506816, 'steps': 85972, 'loss/train': 1.3894654512405396} 08/31/2021 04:44:05 - INFO - __main__ - Step 85974: {'lr': 0.00019747025730872748, 'samples': 16507008, 'steps': 85973, 'loss/train': 1.0933247804641724} 08/31/2021 04:44:07 - INFO - __main__ - Step 85975: {'lr': 0.0001974650690449064, 'samples': 16507200, 'steps': 85974, 'loss/train': 0.9943190813064575} 08/31/2021 04:44:07 - INFO - __main__ - Step 85976: {'lr': 0.0001974598808047568, 'samples': 16507392, 'steps': 85975, 'loss/train': 1.699421763420105} 08/31/2021 04:44:08 - INFO - __main__ - Step 85977: {'lr': 0.00019745469258828093, 'samples': 16507584, 'steps': 85976, 'loss/train': 2.1713643074035645} 08/31/2021 04:44:08 - INFO - __main__ - Step 85978: {'lr': 0.00019744950439548115, 'samples': 16507776, 'steps': 85977, 'loss/train': 1.4229623079299927} 08/31/2021 04:44:08 - INFO - __main__ - Step 85979: {'lr': 0.00019744431622635984, 'samples': 16507968, 'steps': 85978, 'loss/train': 0.8731341361999512} 08/31/2021 04:44:10 - INFO - __main__ - Step 85980: {'lr': 0.00019743912808091934, 'samples': 16508160, 'steps': 85979, 'loss/train': 1.3362047672271729} 08/31/2021 04:44:10 - INFO - __main__ - Step 85981: {'lr': 0.00019743393995916192, 'samples': 16508352, 'steps': 85980, 'loss/train': 1.266367793083191} 08/31/2021 04:44:10 - INFO - __main__ - Step 85982: {'lr': 0.00019742875186108997, 'samples': 16508544, 'steps': 85981, 'loss/train': 0.8970478177070618} 08/31/2021 04:44:11 - INFO - __main__ - Step 85983: {'lr': 0.0001974235637867058, 'samples': 16508736, 'steps': 85982, 'loss/train': 1.0711101293563843} 08/31/2021 04:44:11 - INFO - __main__ - Step 85984: {'lr': 0.00019741837573601182, 'samples': 16508928, 'steps': 85983, 'loss/train': 1.108225703239441} 08/31/2021 04:44:13 - INFO - __main__ - Step 85985: {'lr': 0.00019741318770901027, 'samples': 16509120, 'steps': 85984, 'loss/train': 1.338097095489502} 08/31/2021 04:44:13 - INFO - __main__ - Step 85986: {'lr': 0.0001974079997057035, 'samples': 16509312, 'steps': 85985, 'loss/train': 1.3697583675384521} 08/31/2021 04:44:14 - INFO - __main__ - Step 85987: {'lr': 0.00019740281172609387, 'samples': 16509504, 'steps': 85986, 'loss/train': 1.2349435091018677} 08/31/2021 04:44:14 - INFO - __main__ - Step 85988: {'lr': 0.00019739762377018373, 'samples': 16509696, 'steps': 85987, 'loss/train': 1.2312476634979248} 08/31/2021 04:44:14 - INFO - __main__ - Step 85989: {'lr': 0.0001973924358379754, 'samples': 16509888, 'steps': 85988, 'loss/train': 0.8096123337745667} 08/31/2021 04:44:16 - INFO - __main__ - Step 85990: {'lr': 0.00019738724792947124, 'samples': 16510080, 'steps': 85989, 'loss/train': 0.10041513293981552} 08/31/2021 04:44:16 - INFO - __main__ - Step 85991: {'lr': 0.00019738206004467362, 'samples': 16510272, 'steps': 85990, 'loss/train': 1.3558119535446167} 08/31/2021 04:44:17 - INFO - __main__ - Step 85992: {'lr': 0.0001973768721835848, 'samples': 16510464, 'steps': 85991, 'loss/train': 1.571451187133789} 08/31/2021 04:44:17 - INFO - __main__ - Step 85993: {'lr': 0.00019737168434620712, 'samples': 16510656, 'steps': 85992, 'loss/train': 1.722273826599121} 08/31/2021 04:44:17 - INFO - __main__ - Step 85994: {'lr': 0.00019736649653254295, 'samples': 16510848, 'steps': 85993, 'loss/train': 1.2487736940383911} 08/31/2021 04:44:18 - INFO - __main__ - Step 85995: {'lr': 0.00019736130874259465, 'samples': 16511040, 'steps': 85994, 'loss/train': 1.4798967838287354} 08/31/2021 04:44:19 - INFO - __main__ - Step 85996: {'lr': 0.00019735612097636452, 'samples': 16511232, 'steps': 85995, 'loss/train': 1.334768533706665} 08/31/2021 04:44:20 - INFO - __main__ - Step 85997: {'lr': 0.00019735093323385489, 'samples': 16511424, 'steps': 85996, 'loss/train': 1.145772099494934} 08/31/2021 04:44:20 - INFO - __main__ - Step 85998: {'lr': 0.00019734574551506817, 'samples': 16511616, 'steps': 85997, 'loss/train': 1.256800889968872} 08/31/2021 04:44:21 - INFO - __main__ - Step 85999: {'lr': 0.00019734055782000663, 'samples': 16511808, 'steps': 85998, 'loss/train': 1.1638882160186768} 08/31/2021 04:44:21 - INFO - __main__ - Step 86000: {'lr': 0.0001973353701486726, 'samples': 16512000, 'steps': 85999, 'loss/train': 0.9246269464492798} 08/31/2021 04:44:22 - INFO - __main__ - Step 86001: {'lr': 0.0001973301825010685, 'samples': 16512192, 'steps': 86000, 'loss/train': 1.5072736740112305} 08/31/2021 04:44:23 - INFO - __main__ - Step 86002: {'lr': 0.00019732499487719652, 'samples': 16512384, 'steps': 86001, 'loss/train': 0.9642947912216187} 08/31/2021 04:44:23 - INFO - __main__ - Step 86003: {'lr': 0.0001973198072770591, 'samples': 16512576, 'steps': 86002, 'loss/train': 0.8306342363357544} 08/31/2021 04:44:24 - INFO - __main__ - Step 86004: {'lr': 0.00019731461970065857, 'samples': 16512768, 'steps': 86003, 'loss/train': 0.8647605776786804} 08/31/2021 04:44:24 - INFO - __main__ - Step 86005: {'lr': 0.0001973094321479973, 'samples': 16512960, 'steps': 86004, 'loss/train': 0.8405005931854248} 08/31/2021 04:44:25 - INFO - __main__ - Step 86006: {'lr': 0.00019730424461907752, 'samples': 16513152, 'steps': 86005, 'loss/train': 1.5356287956237793} 08/31/2021 04:44:26 - INFO - __main__ - Step 86007: {'lr': 0.00019729905711390167, 'samples': 16513344, 'steps': 86006, 'loss/train': 1.246408462524414} 08/31/2021 04:44:26 - INFO - __main__ - Step 86008: {'lr': 0.00019729386963247204, 'samples': 16513536, 'steps': 86007, 'loss/train': 1.2006316184997559} 08/31/2021 04:44:27 - INFO - __main__ - Step 86009: {'lr': 0.000197288682174791, 'samples': 16513728, 'steps': 86008, 'loss/train': 1.2035125494003296} 08/31/2021 04:44:27 - INFO - __main__ - Step 86010: {'lr': 0.00019728349474086083, 'samples': 16513920, 'steps': 86009, 'loss/train': 0.9479027986526489} 08/31/2021 04:44:29 - INFO - __main__ - Step 86011: {'lr': 0.00019727830733068396, 'samples': 16514112, 'steps': 86010, 'loss/train': 1.0575640201568604} 08/31/2021 04:44:29 - INFO - __main__ - Step 86012: {'lr': 0.00019727311994426273, 'samples': 16514304, 'steps': 86011, 'loss/train': 0.7639605402946472} 08/31/2021 04:44:29 - INFO - __main__ - Step 86013: {'lr': 0.0001972679325815993, 'samples': 16514496, 'steps': 86012, 'loss/train': 1.3678772449493408} 08/31/2021 04:44:30 - INFO - __main__ - Step 86014: {'lr': 0.00019726274524269616, 'samples': 16514688, 'steps': 86013, 'loss/train': 0.9087634682655334} 08/31/2021 04:44:30 - INFO - __main__ - Step 86015: {'lr': 0.00019725755792755558, 'samples': 16514880, 'steps': 86014, 'loss/train': 0.6336455345153809} 08/31/2021 04:44:31 - INFO - __main__ - Step 86016: {'lr': 0.00019725237063617995, 'samples': 16515072, 'steps': 86015, 'loss/train': 0.9689747095108032} 08/31/2021 04:44:32 - INFO - __main__ - Step 86017: {'lr': 0.0001972471833685716, 'samples': 16515264, 'steps': 86016, 'loss/train': 1.0428844690322876} 08/31/2021 04:44:32 - INFO - __main__ - Step 86018: {'lr': 0.00019724199612473285, 'samples': 16515456, 'steps': 86017, 'loss/train': 1.0477489233016968} 08/31/2021 04:44:32 - INFO - __main__ - Step 86019: {'lr': 0.00019723680890466606, 'samples': 16515648, 'steps': 86018, 'loss/train': 0.7586791515350342} 08/31/2021 04:44:33 - INFO - __main__ - Step 86020: {'lr': 0.0001972316217083735, 'samples': 16515840, 'steps': 86019, 'loss/train': 1.0066092014312744} 08/31/2021 04:44:34 - INFO - __main__ - Step 86021: {'lr': 0.0001972264345358576, 'samples': 16516032, 'steps': 86020, 'loss/train': 1.1165862083435059} 08/31/2021 04:44:35 - INFO - __main__ - Step 86022: {'lr': 0.00019722124738712064, 'samples': 16516224, 'steps': 86021, 'loss/train': 1.5250539779663086} 08/31/2021 04:44:35 - INFO - __main__ - Step 86023: {'lr': 0.00019721606026216497, 'samples': 16516416, 'steps': 86022, 'loss/train': 0.49428242444992065} 08/31/2021 04:44:35 - INFO - __main__ - Step 86024: {'lr': 0.00019721087316099294, 'samples': 16516608, 'steps': 86023, 'loss/train': 0.16022594273090363} 08/31/2021 04:44:36 - INFO - __main__ - Step 86025: {'lr': 0.00019720568608360694, 'samples': 16516800, 'steps': 86024, 'loss/train': 1.0862267017364502} 08/31/2021 04:44:37 - INFO - __main__ - Step 86026: {'lr': 0.0001972004990300092, 'samples': 16516992, 'steps': 86025, 'loss/train': 0.48990973830223083} 08/31/2021 04:44:38 - INFO - __main__ - Step 86027: {'lr': 0.00019719531200020204, 'samples': 16517184, 'steps': 86026, 'loss/train': 0.8494810461997986} 08/31/2021 04:44:38 - INFO - __main__ - Step 86028: {'lr': 0.0001971901249941879, 'samples': 16517376, 'steps': 86027, 'loss/train': 1.7059571743011475} 08/31/2021 04:44:38 - INFO - __main__ - Step 86029: {'lr': 0.00019718493801196906, 'samples': 16517568, 'steps': 86028, 'loss/train': 1.04911470413208} 08/31/2021 04:44:39 - INFO - __main__ - Step 86030: {'lr': 0.00019717975105354785, 'samples': 16517760, 'steps': 86029, 'loss/train': 0.8005928993225098} 08/31/2021 04:44:39 - INFO - __main__ - Step 86031: {'lr': 0.00019717456411892667, 'samples': 16517952, 'steps': 86030, 'loss/train': 1.3292620182037354} 08/31/2021 04:44:41 - INFO - __main__ - Step 86032: {'lr': 0.0001971693772081078, 'samples': 16518144, 'steps': 86031, 'loss/train': 1.805860996246338} 08/31/2021 04:44:42 - INFO - __main__ - Step 86033: {'lr': 0.0001971641903210936, 'samples': 16518336, 'steps': 86032, 'loss/train': 1.170637845993042} 08/31/2021 04:44:42 - INFO - __main__ - Step 86034: {'lr': 0.00019715900345788638, 'samples': 16518528, 'steps': 86033, 'loss/train': 0.7053272128105164} 08/31/2021 04:44:42 - INFO - __main__ - Step 86035: {'lr': 0.00019715381661848853, 'samples': 16518720, 'steps': 86034, 'loss/train': 1.6213880777359009} 08/31/2021 04:44:43 - INFO - __main__ - Step 86036: {'lr': 0.0001971486298029023, 'samples': 16518912, 'steps': 86035, 'loss/train': 1.2295759916305542} 08/31/2021 04:44:44 - INFO - __main__ - Step 86037: {'lr': 0.00019714344301113013, 'samples': 16519104, 'steps': 86036, 'loss/train': 0.40250134468078613} 08/31/2021 04:44:45 - INFO - __main__ - Step 86038: {'lr': 0.00019713825624317438, 'samples': 16519296, 'steps': 86037, 'loss/train': 1.0192936658859253} 08/31/2021 04:44:45 - INFO - __main__ - Step 86039: {'lr': 0.00019713306949903725, 'samples': 16519488, 'steps': 86038, 'loss/train': 1.3111867904663086} 08/31/2021 04:44:45 - INFO - __main__ - Step 86040: {'lr': 0.00019712788277872112, 'samples': 16519680, 'steps': 86039, 'loss/train': 0.9949564933776855} 08/31/2021 04:44:46 - INFO - __main__ - Step 86041: {'lr': 0.00019712269608222836, 'samples': 16519872, 'steps': 86040, 'loss/train': 0.9578365683555603} 08/31/2021 04:44:47 - INFO - __main__ - Step 86042: {'lr': 0.0001971175094095613, 'samples': 16520064, 'steps': 86041, 'loss/train': 0.8807184100151062} 08/31/2021 04:44:48 - INFO - __main__ - Step 86043: {'lr': 0.00019711232276072228, 'samples': 16520256, 'steps': 86042, 'loss/train': 1.4885642528533936} 08/31/2021 04:44:48 - INFO - __main__ - Step 86044: {'lr': 0.0001971071361357136, 'samples': 16520448, 'steps': 86043, 'loss/train': 0.9545963406562805} 08/31/2021 04:44:49 - INFO - __main__ - Step 86045: {'lr': 0.00019710194953453765, 'samples': 16520640, 'steps': 86044, 'loss/train': 0.6446437239646912} 08/31/2021 04:44:49 - INFO - __main__ - Step 86046: {'lr': 0.00019709676295719673, 'samples': 16520832, 'steps': 86045, 'loss/train': 1.1208938360214233} 08/31/2021 04:44:50 - INFO - __main__ - Step 86047: {'lr': 0.0001970915764036932, 'samples': 16521024, 'steps': 86046, 'loss/train': 0.9069966673851013} 08/31/2021 04:44:51 - INFO - __main__ - Step 86048: {'lr': 0.00019708638987402937, 'samples': 16521216, 'steps': 86047, 'loss/train': 1.253699541091919} 08/31/2021 04:44:51 - INFO - __main__ - Step 86049: {'lr': 0.00019708120336820766, 'samples': 16521408, 'steps': 86048, 'loss/train': 1.1231157779693604} 08/31/2021 04:44:51 - INFO - __main__ - Step 86050: {'lr': 0.00019707601688623028, 'samples': 16521600, 'steps': 86049, 'loss/train': 0.8306739330291748} 08/31/2021 04:44:52 - INFO - __main__ - Step 86051: {'lr': 0.00019707083042809975, 'samples': 16521792, 'steps': 86050, 'loss/train': 1.0490080118179321} 08/31/2021 04:44:53 - INFO - __main__ - Step 86052: {'lr': 0.00019706564399381822, 'samples': 16521984, 'steps': 86051, 'loss/train': 0.2803492248058319} 08/31/2021 04:44:54 - INFO - __main__ - Step 86053: {'lr': 0.00019706045758338802, 'samples': 16522176, 'steps': 86052, 'loss/train': 1.5237879753112793} 08/31/2021 04:44:54 - INFO - __main__ - Step 86054: {'lr': 0.00019705527119681163, 'samples': 16522368, 'steps': 86053, 'loss/train': 0.2330004870891571} 08/31/2021 04:44:54 - INFO - __main__ - Step 86055: {'lr': 0.0001970500848340913, 'samples': 16522560, 'steps': 86054, 'loss/train': 1.505736231803894} 08/31/2021 04:44:55 - INFO - __main__ - Step 86056: {'lr': 0.0001970448984952294, 'samples': 16522752, 'steps': 86055, 'loss/train': 1.346944808959961} 08/31/2021 04:44:56 - INFO - __main__ - Step 86057: {'lr': 0.0001970397121802282, 'samples': 16522944, 'steps': 86056, 'loss/train': 1.1406933069229126} 08/31/2021 04:44:57 - INFO - __main__ - Step 86058: {'lr': 0.0001970345258890901, 'samples': 16523136, 'steps': 86057, 'loss/train': 1.3940958976745605} 08/31/2021 04:44:57 - INFO - __main__ - Step 86059: {'lr': 0.00019702933962181747, 'samples': 16523328, 'steps': 86058, 'loss/train': 1.0952166318893433} 08/31/2021 04:44:57 - INFO - __main__ - Step 86060: {'lr': 0.00019702415337841255, 'samples': 16523520, 'steps': 86059, 'loss/train': 0.031316716223955154} 08/31/2021 04:44:58 - INFO - __main__ - Step 86061: {'lr': 0.00019701896715887775, 'samples': 16523712, 'steps': 86060, 'loss/train': 1.0161490440368652} 08/31/2021 04:44:59 - INFO - __main__ - Step 86062: {'lr': 0.0001970137809632154, 'samples': 16523904, 'steps': 86061, 'loss/train': 0.9125886559486389} 08/31/2021 04:45:00 - INFO - __main__ - Step 86063: {'lr': 0.0001970085947914278, 'samples': 16524096, 'steps': 86062, 'loss/train': 0.9825177192687988} 08/31/2021 04:45:00 - INFO - __main__ - Step 86064: {'lr': 0.00019700340864351734, 'samples': 16524288, 'steps': 86063, 'loss/train': 1.379156231880188} 08/31/2021 04:45:00 - INFO - __main__ - Step 86065: {'lr': 0.0001969982225194864, 'samples': 16524480, 'steps': 86064, 'loss/train': 1.6797772645950317} 08/31/2021 04:45:01 - INFO - __main__ - Step 86066: {'lr': 0.00019699303641933715, 'samples': 16524672, 'steps': 86065, 'loss/train': 1.0069717168807983} 08/31/2021 04:45:01 - INFO - __main__ - Step 86067: {'lr': 0.00019698785034307203, 'samples': 16524864, 'steps': 86066, 'loss/train': 0.7353418469429016} 08/31/2021 04:45:03 - INFO - __main__ - Step 86068: {'lr': 0.00019698266429069334, 'samples': 16525056, 'steps': 86067, 'loss/train': 1.1758830547332764} 08/31/2021 04:45:03 - INFO - __main__ - Step 86069: {'lr': 0.00019697747826220348, 'samples': 16525248, 'steps': 86068, 'loss/train': 1.1111575365066528} 08/31/2021 04:45:04 - INFO - __main__ - Step 86070: {'lr': 0.0001969722922576047, 'samples': 16525440, 'steps': 86069, 'loss/train': 0.7751523852348328} 08/31/2021 04:45:04 - INFO - __main__ - Step 86071: {'lr': 0.00019696710627689946, 'samples': 16525632, 'steps': 86070, 'loss/train': 2.0331225395202637} 08/31/2021 04:45:04 - INFO - __main__ - Step 86072: {'lr': 0.00019696192032008997, 'samples': 16525824, 'steps': 86071, 'loss/train': 0.7235093712806702} 08/31/2021 04:45:06 - INFO - __main__ - Step 86073: {'lr': 0.00019695673438717862, 'samples': 16526016, 'steps': 86072, 'loss/train': 1.5668967962265015} 08/31/2021 04:45:06 - INFO - __main__ - Step 86074: {'lr': 0.00019695154847816776, 'samples': 16526208, 'steps': 86073, 'loss/train': 1.4573874473571777} 08/31/2021 04:45:07 - INFO - __main__ - Step 86075: {'lr': 0.0001969463625930597, 'samples': 16526400, 'steps': 86074, 'loss/train': 1.287371277809143} 08/31/2021 04:45:07 - INFO - __main__ - Step 86076: {'lr': 0.0001969411767318568, 'samples': 16526592, 'steps': 86075, 'loss/train': 1.525526762008667} 08/31/2021 04:45:07 - INFO - __main__ - Step 86077: {'lr': 0.00019693599089456141, 'samples': 16526784, 'steps': 86076, 'loss/train': 1.4831132888793945} 08/31/2021 04:45:09 - INFO - __main__ - Step 86078: {'lr': 0.0001969308050811759, 'samples': 16526976, 'steps': 86077, 'loss/train': 1.0529630184173584} 08/31/2021 04:45:09 - INFO - __main__ - Step 86079: {'lr': 0.0001969256192917025, 'samples': 16527168, 'steps': 86078, 'loss/train': 0.6364708542823792} 08/31/2021 04:45:10 - INFO - __main__ - Step 86080: {'lr': 0.00019692043352614356, 'samples': 16527360, 'steps': 86079, 'loss/train': 1.2376229763031006} 08/31/2021 04:45:10 - INFO - __main__ - Step 86081: {'lr': 0.00019691524778450145, 'samples': 16527552, 'steps': 86080, 'loss/train': 0.8112936019897461} 08/31/2021 04:45:10 - INFO - __main__ - Step 86082: {'lr': 0.00019691006206677854, 'samples': 16527744, 'steps': 86081, 'loss/train': 0.5339118242263794} 08/31/2021 04:45:12 - INFO - __main__ - Step 86083: {'lr': 0.00019690487637297711, 'samples': 16527936, 'steps': 86082, 'loss/train': 1.3102574348449707} 08/31/2021 04:45:13 - INFO - __main__ - Step 86084: {'lr': 0.00019689969070309953, 'samples': 16528128, 'steps': 86083, 'loss/train': 1.2623934745788574} 08/31/2021 04:45:13 - INFO - __main__ - Step 86085: {'lr': 0.00019689450505714815, 'samples': 16528320, 'steps': 86084, 'loss/train': 1.0354174375534058} 08/31/2021 04:45:13 - INFO - __main__ - Step 86086: {'lr': 0.00019688931943512527, 'samples': 16528512, 'steps': 86085, 'loss/train': 1.2556979656219482} 08/31/2021 04:45:14 - INFO - __main__ - Step 86087: {'lr': 0.00019688413383703323, 'samples': 16528704, 'steps': 86086, 'loss/train': 1.7141640186309814} 08/31/2021 04:45:14 - INFO - __main__ - Step 86088: {'lr': 0.00019687894826287439, 'samples': 16528896, 'steps': 86087, 'loss/train': 0.9929306507110596} 08/31/2021 04:45:16 - INFO - __main__ - Step 86089: {'lr': 0.0001968737627126511, 'samples': 16529088, 'steps': 86088, 'loss/train': 1.3724592924118042} 08/31/2021 04:45:17 - INFO - __main__ - Step 86090: {'lr': 0.00019686857718636565, 'samples': 16529280, 'steps': 86089, 'loss/train': 0.018460342660546303} 08/31/2021 04:45:17 - INFO - __main__ - Step 86091: {'lr': 0.0001968633916840204, 'samples': 16529472, 'steps': 86090, 'loss/train': 0.019224125891923904} 08/31/2021 04:45:17 - INFO - __main__ - Step 86092: {'lr': 0.00019685820620561777, 'samples': 16529664, 'steps': 86091, 'loss/train': 0.4698926508426666} 08/31/2021 04:45:18 - INFO - __main__ - Step 86093: {'lr': 0.00019685302075115997, 'samples': 16529856, 'steps': 86092, 'loss/train': 0.8673104047775269} 08/31/2021 04:45:18 - INFO - __main__ - Step 86094: {'lr': 0.00019684783532064931, 'samples': 16530048, 'steps': 86093, 'loss/train': 1.0357762575149536} 08/31/2021 04:45:20 - INFO - __main__ - Step 86095: {'lr': 0.00019684264991408823, 'samples': 16530240, 'steps': 86094, 'loss/train': 0.8331097960472107} 08/31/2021 04:45:20 - INFO - __main__ - Step 86096: {'lr': 0.000196837464531479, 'samples': 16530432, 'steps': 86095, 'loss/train': 1.5258830785751343} 08/31/2021 04:45:21 - INFO - __main__ - Step 86097: {'lr': 0.00019683227917282405, 'samples': 16530624, 'steps': 86096, 'loss/train': 1.3249837160110474} 08/31/2021 04:45:21 - INFO - __main__ - Step 86098: {'lr': 0.00019682709383812562, 'samples': 16530816, 'steps': 86097, 'loss/train': 0.9623909592628479} 08/31/2021 04:45:21 - INFO - __main__ - Step 86099: {'lr': 0.00019682190852738607, 'samples': 16531008, 'steps': 86098, 'loss/train': 1.6058483123779297} 08/31/2021 04:45:23 - INFO - __main__ - Step 86100: {'lr': 0.00019681672324060775, 'samples': 16531200, 'steps': 86099, 'loss/train': 1.1654472351074219} 08/31/2021 04:45:23 - INFO - __main__ - Step 86101: {'lr': 0.000196811537977793, 'samples': 16531392, 'steps': 86100, 'loss/train': 1.0729988813400269} 08/31/2021 04:45:24 - INFO - __main__ - Step 86102: {'lr': 0.00019680635273894415, 'samples': 16531584, 'steps': 86101, 'loss/train': 1.8921289443969727} 08/31/2021 04:45:24 - INFO - __main__ - Step 86103: {'lr': 0.00019680116752406358, 'samples': 16531776, 'steps': 86102, 'loss/train': 1.1651681661605835} 08/31/2021 04:45:24 - INFO - __main__ - Step 86104: {'lr': 0.00019679598233315356, 'samples': 16531968, 'steps': 86103, 'loss/train': 0.500037670135498} 08/31/2021 04:45:26 - INFO - __main__ - Step 86105: {'lr': 0.0001967907971662165, 'samples': 16532160, 'steps': 86104, 'loss/train': 0.8684805035591125} 08/31/2021 04:45:26 - INFO - __main__ - Step 86106: {'lr': 0.0001967856120232546, 'samples': 16532352, 'steps': 86105, 'loss/train': 1.4943903684616089} 08/31/2021 04:45:27 - INFO - __main__ - Step 86107: {'lr': 0.00019678042690427029, 'samples': 16532544, 'steps': 86106, 'loss/train': 0.3472408354282379} 08/31/2021 04:45:27 - INFO - __main__ - Step 86108: {'lr': 0.0001967752418092659, 'samples': 16532736, 'steps': 86107, 'loss/train': 1.7055587768554688} 08/31/2021 04:45:27 - INFO - __main__ - Step 86109: {'lr': 0.00019677005673824377, 'samples': 16532928, 'steps': 86108, 'loss/train': 0.9534680843353271} 08/31/2021 04:45:28 - INFO - __main__ - Step 86110: {'lr': 0.0001967648716912062, 'samples': 16533120, 'steps': 86109, 'loss/train': 0.030756643041968346} 08/31/2021 04:45:29 - INFO - __main__ - Step 86111: {'lr': 0.00019675968666815562, 'samples': 16533312, 'steps': 86110, 'loss/train': 1.2479864358901978} 08/31/2021 04:45:30 - INFO - __main__ - Step 86112: {'lr': 0.00019675450166909425, 'samples': 16533504, 'steps': 86111, 'loss/train': 0.8341053128242493} 08/31/2021 04:45:30 - INFO - __main__ - Step 86113: {'lr': 0.00019674931669402452, 'samples': 16533696, 'steps': 86112, 'loss/train': 0.8274508714675903} 08/31/2021 04:45:30 - INFO - __main__ - Step 86114: {'lr': 0.00019674413174294874, 'samples': 16533888, 'steps': 86113, 'loss/train': 1.5373305082321167} 08/31/2021 04:45:31 - INFO - __main__ - Step 86115: {'lr': 0.00019673894681586924, 'samples': 16534080, 'steps': 86114, 'loss/train': 0.7048106789588928} 08/31/2021 04:45:32 - INFO - __main__ - Step 86116: {'lr': 0.0001967337619127883, 'samples': 16534272, 'steps': 86115, 'loss/train': 1.0926772356033325} 08/31/2021 04:45:32 - INFO - __main__ - Step 86117: {'lr': 0.0001967285770337083, 'samples': 16534464, 'steps': 86116, 'loss/train': 1.1929004192352295} 08/31/2021 04:45:33 - INFO - __main__ - Step 86118: {'lr': 0.0001967233921786316, 'samples': 16534656, 'steps': 86117, 'loss/train': 1.54234778881073} 08/31/2021 04:45:33 - INFO - __main__ - Step 86119: {'lr': 0.00019671820734756059, 'samples': 16534848, 'steps': 86118, 'loss/train': 1.8373444080352783} 08/31/2021 04:45:34 - INFO - __main__ - Step 86120: {'lr': 0.00019671302254049743, 'samples': 16535040, 'steps': 86119, 'loss/train': 1.4163894653320312} 08/31/2021 04:45:35 - INFO - __main__ - Step 86121: {'lr': 0.00019670783775744462, 'samples': 16535232, 'steps': 86120, 'loss/train': 0.854058563709259} 08/31/2021 04:45:35 - INFO - __main__ - Step 86122: {'lr': 0.00019670265299840436, 'samples': 16535424, 'steps': 86121, 'loss/train': 0.18080952763557434} 08/31/2021 04:45:36 - INFO - __main__ - Step 86123: {'lr': 0.00019669746826337913, 'samples': 16535616, 'steps': 86122, 'loss/train': 0.999518096446991} 08/31/2021 04:45:36 - INFO - __main__ - Step 86124: {'lr': 0.00019669228355237116, 'samples': 16535808, 'steps': 86123, 'loss/train': 1.5822733640670776} 08/31/2021 04:45:36 - INFO - __main__ - Step 86125: {'lr': 0.0001966870988653829, 'samples': 16536000, 'steps': 86124, 'loss/train': 1.4056951999664307} 08/31/2021 04:45:38 - INFO - __main__ - Step 86126: {'lr': 0.00019668191420241655, 'samples': 16536192, 'steps': 86125, 'loss/train': 0.8580085635185242} 08/31/2021 04:45:38 - INFO - __main__ - Step 86127: {'lr': 0.00019667672956347448, 'samples': 16536384, 'steps': 86126, 'loss/train': 0.9528007507324219} 08/31/2021 04:45:39 - INFO - __main__ - Step 86128: {'lr': 0.0001966715449485591, 'samples': 16536576, 'steps': 86127, 'loss/train': 0.09868507832288742} 08/31/2021 04:45:39 - INFO - __main__ - Step 86129: {'lr': 0.00019666636035767265, 'samples': 16536768, 'steps': 86128, 'loss/train': 1.5926164388656616} 08/31/2021 04:45:39 - INFO - __main__ - Step 86130: {'lr': 0.00019666117579081755, 'samples': 16536960, 'steps': 86129, 'loss/train': 1.207236886024475} 08/31/2021 04:45:41 - INFO - __main__ - Step 86131: {'lr': 0.0001966559912479961, 'samples': 16537152, 'steps': 86130, 'loss/train': 1.1874644756317139} 08/31/2021 04:45:42 - INFO - __main__ - Step 86132: {'lr': 0.00019665080672921068, 'samples': 16537344, 'steps': 86131, 'loss/train': 0.38971254229545593} 08/31/2021 04:45:42 - INFO - __main__ - Step 86133: {'lr': 0.00019664562223446354, 'samples': 16537536, 'steps': 86132, 'loss/train': 1.604351282119751} 08/31/2021 04:45:42 - INFO - __main__ - Step 86134: {'lr': 0.00019664043776375706, 'samples': 16537728, 'steps': 86133, 'loss/train': 2.1093056201934814} 08/31/2021 04:45:43 - INFO - __main__ - Step 86135: {'lr': 0.00019663525331709356, 'samples': 16537920, 'steps': 86134, 'loss/train': 0.7924755215644836} 08/31/2021 04:45:43 - INFO - __main__ - Step 86136: {'lr': 0.00019663006889447543, 'samples': 16538112, 'steps': 86135, 'loss/train': 0.7514973878860474} 08/31/2021 04:45:46 - INFO - __main__ - Step 86137: {'lr': 0.00019662488449590496, 'samples': 16538304, 'steps': 86136, 'loss/train': 1.1755995750427246} 08/31/2021 04:45:46 - INFO - __main__ - Step 86138: {'lr': 0.00019661970012138446, 'samples': 16538496, 'steps': 86137, 'loss/train': 0.9621732234954834} 08/31/2021 04:45:46 - INFO - __main__ - Step 86139: {'lr': 0.00019661451577091633, 'samples': 16538688, 'steps': 86138, 'loss/train': 1.3107519149780273} 08/31/2021 04:45:47 - INFO - __main__ - Step 86140: {'lr': 0.00019660933144450283, 'samples': 16538880, 'steps': 86139, 'loss/train': 0.8364901542663574} 08/31/2021 04:45:47 - INFO - __main__ - Step 86141: {'lr': 0.00019660414714214636, 'samples': 16539072, 'steps': 86140, 'loss/train': 1.0099689960479736} 08/31/2021 04:45:49 - INFO - __main__ - Step 86142: {'lr': 0.00019659896286384926, 'samples': 16539264, 'steps': 86141, 'loss/train': 0.03129846975207329} 08/31/2021 04:45:49 - INFO - __main__ - Step 86143: {'lr': 0.00019659377860961383, 'samples': 16539456, 'steps': 86142, 'loss/train': 1.1798795461654663} 08/31/2021 04:45:50 - INFO - __main__ - Step 86144: {'lr': 0.0001965885943794424, 'samples': 16539648, 'steps': 86143, 'loss/train': 0.2549121379852295} 08/31/2021 04:45:50 - INFO - __main__ - Step 86145: {'lr': 0.00019658341017333736, 'samples': 16539840, 'steps': 86144, 'loss/train': 0.780624270439148} 08/31/2021 04:45:51 - INFO - __main__ - Step 86146: {'lr': 0.00019657822599130105, 'samples': 16540032, 'steps': 86145, 'loss/train': 1.6931672096252441} 08/31/2021 04:45:52 - INFO - __main__ - Step 86147: {'lr': 0.00019657304183333575, 'samples': 16540224, 'steps': 86146, 'loss/train': 1.4028453826904297} 08/31/2021 04:45:52 - INFO - __main__ - Step 86148: {'lr': 0.00019656785769944378, 'samples': 16540416, 'steps': 86147, 'loss/train': 1.389618158340454} 08/31/2021 04:45:53 - INFO - __main__ - Step 86149: {'lr': 0.0001965626735896275, 'samples': 16540608, 'steps': 86148, 'loss/train': 1.090847373008728} 08/31/2021 04:45:53 - INFO - __main__ - Step 86150: {'lr': 0.00019655748950388925, 'samples': 16540800, 'steps': 86149, 'loss/train': 1.251272439956665} 08/31/2021 04:45:53 - INFO - __main__ - Step 86151: {'lr': 0.0001965523054422314, 'samples': 16540992, 'steps': 86150, 'loss/train': 1.011736273765564} 08/31/2021 04:45:55 - INFO - __main__ - Step 86152: {'lr': 0.0001965471214046562, 'samples': 16541184, 'steps': 86151, 'loss/train': 0.43178507685661316} 08/31/2021 04:45:55 - INFO - __main__ - Step 86153: {'lr': 0.00019654193739116607, 'samples': 16541376, 'steps': 86152, 'loss/train': 1.030668020248413} 08/31/2021 04:45:56 - INFO - __main__ - Step 86154: {'lr': 0.00019653675340176334, 'samples': 16541568, 'steps': 86153, 'loss/train': 0.8919233679771423} 08/31/2021 04:45:56 - INFO - __main__ - Step 86155: {'lr': 0.00019653156943645028, 'samples': 16541760, 'steps': 86154, 'loss/train': 0.5120477080345154} 08/31/2021 04:45:57 - INFO - __main__ - Step 86156: {'lr': 0.0001965263854952293, 'samples': 16541952, 'steps': 86155, 'loss/train': 0.49863260984420776} 08/31/2021 04:45:57 - INFO - __main__ - Step 86157: {'lr': 0.00019652120157810272, 'samples': 16542144, 'steps': 86156, 'loss/train': 1.2267704010009766} 08/31/2021 04:45:58 - INFO - __main__ - Step 86158: {'lr': 0.00019651601768507282, 'samples': 16542336, 'steps': 86157, 'loss/train': 0.6908884644508362} 08/31/2021 04:45:59 - INFO - __main__ - Step 86159: {'lr': 0.00019651083381614214, 'samples': 16542528, 'steps': 86158, 'loss/train': 0.034770771861076355} 08/31/2021 04:45:59 - INFO - __main__ - Step 86160: {'lr': 0.0001965056499713127, 'samples': 16542720, 'steps': 86159, 'loss/train': 1.2289992570877075} 08/31/2021 04:46:00 - INFO - __main__ - Step 86161: {'lr': 0.000196500466150587, 'samples': 16542912, 'steps': 86160, 'loss/train': 1.7663971185684204} 08/31/2021 04:46:00 - INFO - __main__ - Step 86162: {'lr': 0.00019649528235396736, 'samples': 16543104, 'steps': 86161, 'loss/train': 1.6433560848236084} 08/31/2021 04:46:01 - INFO - __main__ - Step 86163: {'lr': 0.00019649009858145613, 'samples': 16543296, 'steps': 86162, 'loss/train': 1.5214943885803223} 08/31/2021 04:46:02 - INFO - __main__ - Step 86164: {'lr': 0.00019648491483305563, 'samples': 16543488, 'steps': 86163, 'loss/train': 1.1864349842071533} 08/31/2021 04:46:02 - INFO - __main__ - Step 86165: {'lr': 0.0001964797311087682, 'samples': 16543680, 'steps': 86164, 'loss/train': 1.2589292526245117} 08/31/2021 04:46:02 - INFO - __main__ - Step 86166: {'lr': 0.00019647454740859618, 'samples': 16543872, 'steps': 86165, 'loss/train': 1.683451533317566} 08/31/2021 04:46:03 - INFO - __main__ - Step 86167: {'lr': 0.00019646936373254192, 'samples': 16544064, 'steps': 86166, 'loss/train': 1.4683496952056885} 08/31/2021 04:46:05 - INFO - __main__ - Step 86168: {'lr': 0.00019646418008060774, 'samples': 16544256, 'steps': 86167, 'loss/train': 1.7581496238708496} 08/31/2021 04:46:05 - INFO - __main__ - Step 86169: {'lr': 0.00019645899645279595, 'samples': 16544448, 'steps': 86168, 'loss/train': 1.8114262819290161} 08/31/2021 04:46:06 - INFO - __main__ - Step 86170: {'lr': 0.0001964538128491089, 'samples': 16544640, 'steps': 86169, 'loss/train': 0.08470946550369263} 08/31/2021 04:46:06 - INFO - __main__ - Step 86171: {'lr': 0.00019644862926954896, 'samples': 16544832, 'steps': 86170, 'loss/train': 0.684992790222168} 08/31/2021 04:46:06 - INFO - __main__ - Step 86172: {'lr': 0.00019644344571411853, 'samples': 16545024, 'steps': 86171, 'loss/train': 1.7102875709533691} 08/31/2021 04:46:08 - INFO - __main__ - Step 86173: {'lr': 0.00019643826218281976, 'samples': 16545216, 'steps': 86172, 'loss/train': 1.5294015407562256} 08/31/2021 04:46:08 - INFO - __main__ - Step 86174: {'lr': 0.0001964330786756551, 'samples': 16545408, 'steps': 86173, 'loss/train': 0.8435633182525635} 08/31/2021 04:46:08 - INFO - __main__ - Step 86175: {'lr': 0.00019642789519262686, 'samples': 16545600, 'steps': 86174, 'loss/train': 1.0269677639007568} 08/31/2021 04:46:09 - INFO - __main__ - Step 86176: {'lr': 0.00019642271173373735, 'samples': 16545792, 'steps': 86175, 'loss/train': 0.8461791276931763} 08/31/2021 04:46:09 - INFO - __main__ - Step 86177: {'lr': 0.00019641752829898897, 'samples': 16545984, 'steps': 86176, 'loss/train': 1.476948618888855} 08/31/2021 04:46:11 - INFO - __main__ - Step 86178: {'lr': 0.00019641234488838402, 'samples': 16546176, 'steps': 86177, 'loss/train': 0.4666009545326233} 08/31/2021 04:46:11 - INFO - __main__ - Step 86179: {'lr': 0.00019640716150192485, 'samples': 16546368, 'steps': 86178, 'loss/train': 1.4029195308685303} 08/31/2021 04:46:11 - INFO - __main__ - Step 86180: {'lr': 0.00019640197813961379, 'samples': 16546560, 'steps': 86179, 'loss/train': 1.356183409690857} 08/31/2021 04:46:12 - INFO - __main__ - Step 86181: {'lr': 0.00019639679480145314, 'samples': 16546752, 'steps': 86180, 'loss/train': 1.0292061567306519} 08/31/2021 04:46:12 - INFO - __main__ - Step 86182: {'lr': 0.00019639161148744528, 'samples': 16546944, 'steps': 86181, 'loss/train': 0.681540846824646} 08/31/2021 04:46:14 - INFO - __main__ - Step 86183: {'lr': 0.00019638642819759256, 'samples': 16547136, 'steps': 86182, 'loss/train': 1.0866862535476685} 08/31/2021 04:46:14 - INFO - __main__ - Step 86184: {'lr': 0.00019638124493189725, 'samples': 16547328, 'steps': 86183, 'loss/train': 1.1052587032318115} 08/31/2021 04:46:14 - INFO - __main__ - Step 86185: {'lr': 0.00019637606169036173, 'samples': 16547520, 'steps': 86184, 'loss/train': 1.4169354438781738} 08/31/2021 04:46:15 - INFO - __main__ - Step 86186: {'lr': 0.00019637087847298846, 'samples': 16547712, 'steps': 86185, 'loss/train': 1.1562303304672241} 08/31/2021 04:46:15 - INFO - __main__ - Step 86187: {'lr': 0.00019636569527977952, 'samples': 16547904, 'steps': 86186, 'loss/train': 0.6221326589584351} 08/31/2021 04:46:17 - INFO - __main__ - Step 86188: {'lr': 0.00019636051211073736, 'samples': 16548096, 'steps': 86187, 'loss/train': 0.6687264442443848} 08/31/2021 04:46:17 - INFO - __main__ - Step 86189: {'lr': 0.00019635532896586437, 'samples': 16548288, 'steps': 86188, 'loss/train': 0.8961384296417236} 08/31/2021 04:46:17 - INFO - __main__ - Step 86190: {'lr': 0.00019635014584516277, 'samples': 16548480, 'steps': 86189, 'loss/train': 0.3450978100299835} 08/31/2021 04:46:18 - INFO - __main__ - Step 86191: {'lr': 0.00019634496274863503, 'samples': 16548672, 'steps': 86190, 'loss/train': 1.3924365043640137} 08/31/2021 04:46:18 - INFO - __main__ - Step 86192: {'lr': 0.00019633977967628338, 'samples': 16548864, 'steps': 86191, 'loss/train': 1.137037992477417} 08/31/2021 04:46:18 - INFO - __main__ - Step 86193: {'lr': 0.00019633459662811025, 'samples': 16549056, 'steps': 86192, 'loss/train': 1.4186291694641113} 08/31/2021 04:46:21 - INFO - __main__ - Step 86194: {'lr': 0.00019632941360411788, 'samples': 16549248, 'steps': 86193, 'loss/train': 0.5808840990066528} 08/31/2021 04:46:21 - INFO - __main__ - Step 86195: {'lr': 0.00019632423060430865, 'samples': 16549440, 'steps': 86194, 'loss/train': 0.7848246693611145} 08/31/2021 04:46:21 - INFO - __main__ - Step 86196: {'lr': 0.0001963190476286849, 'samples': 16549632, 'steps': 86195, 'loss/train': 1.5999069213867188} 08/31/2021 04:46:22 - INFO - __main__ - Step 86197: {'lr': 0.00019631386467724895, 'samples': 16549824, 'steps': 86196, 'loss/train': 1.2734969854354858} 08/31/2021 04:46:22 - INFO - __main__ - Step 86198: {'lr': 0.00019630868175000315, 'samples': 16550016, 'steps': 86197, 'loss/train': 1.119499683380127} 08/31/2021 04:46:24 - INFO - __main__ - Step 86199: {'lr': 0.00019630349884694996, 'samples': 16550208, 'steps': 86198, 'loss/train': 0.9832254648208618} 08/31/2021 04:46:25 - INFO - __main__ - Step 86200: {'lr': 0.00019629831596809145, 'samples': 16550400, 'steps': 86199, 'loss/train': 0.7683120369911194} 08/31/2021 04:46:25 - INFO - __main__ - Step 86201: {'lr': 0.00019629313311343008, 'samples': 16550592, 'steps': 86200, 'loss/train': 1.7235044240951538} 08/31/2021 04:46:25 - INFO - __main__ - Step 86202: {'lr': 0.00019628795028296821, 'samples': 16550784, 'steps': 86201, 'loss/train': 0.8347142338752747} 08/31/2021 04:46:26 - INFO - __main__ - Step 86203: {'lr': 0.00019628276747670818, 'samples': 16550976, 'steps': 86202, 'loss/train': 2.332383871078491} 08/31/2021 04:46:26 - INFO - __main__ - Step 86204: {'lr': 0.00019627758469465228, 'samples': 16551168, 'steps': 86203, 'loss/train': 1.1536152362823486} 08/31/2021 04:46:27 - INFO - __main__ - Step 86205: {'lr': 0.00019627240193680287, 'samples': 16551360, 'steps': 86204, 'loss/train': 2.105390787124634} 08/31/2021 04:46:28 - INFO - __main__ - Step 86206: {'lr': 0.00019626721920316232, 'samples': 16551552, 'steps': 86205, 'loss/train': 1.1582958698272705} 08/31/2021 04:46:28 - INFO - __main__ - Step 86207: {'lr': 0.0001962620364937329, 'samples': 16551744, 'steps': 86206, 'loss/train': 1.706377387046814} 08/31/2021 04:46:29 - INFO - __main__ - Step 86208: {'lr': 0.00019625685380851698, 'samples': 16551936, 'steps': 86207, 'loss/train': 1.2604740858078003} 08/31/2021 04:46:29 - INFO - __main__ - Step 86209: {'lr': 0.00019625167114751692, 'samples': 16552128, 'steps': 86208, 'loss/train': 1.3417646884918213} 08/31/2021 04:46:30 - INFO - __main__ - Step 86210: {'lr': 0.00019624648851073497, 'samples': 16552320, 'steps': 86209, 'loss/train': 1.2061179876327515} 08/31/2021 04:46:31 - INFO - __main__ - Step 86211: {'lr': 0.00019624130589817357, 'samples': 16552512, 'steps': 86210, 'loss/train': 1.2434543371200562} 08/31/2021 04:46:31 - INFO - __main__ - Step 86212: {'lr': 0.000196236123309835, 'samples': 16552704, 'steps': 86211, 'loss/train': 1.0111206769943237} 08/31/2021 04:46:32 - INFO - __main__ - Step 86213: {'lr': 0.00019623094074572173, 'samples': 16552896, 'steps': 86212, 'loss/train': 1.3123995065689087} 08/31/2021 04:46:32 - INFO - __main__ - Step 86214: {'lr': 0.00019622575820583583, 'samples': 16553088, 'steps': 86213, 'loss/train': 1.360701084136963} 08/31/2021 04:46:33 - INFO - __main__ - Step 86215: {'lr': 0.00019622057569017976, 'samples': 16553280, 'steps': 86214, 'loss/train': 1.594971776008606} 08/31/2021 04:46:34 - INFO - __main__ - Step 86216: {'lr': 0.0001962153931987559, 'samples': 16553472, 'steps': 86215, 'loss/train': 0.544543445110321} 08/31/2021 04:46:34 - INFO - __main__ - Step 86217: {'lr': 0.00019621021073156655, 'samples': 16553664, 'steps': 86216, 'loss/train': 0.041863907128572464} 08/31/2021 04:46:35 - INFO - __main__ - Step 86218: {'lr': 0.00019620502828861404, 'samples': 16553856, 'steps': 86217, 'loss/train': 1.703092336654663} 08/31/2021 04:46:35 - INFO - __main__ - Step 86219: {'lr': 0.00019619984586990072, 'samples': 16554048, 'steps': 86218, 'loss/train': 1.6314308643341064} 08/31/2021 04:46:37 - INFO - __main__ - Step 86220: {'lr': 0.0001961946634754289, 'samples': 16554240, 'steps': 86219, 'loss/train': 1.6697688102722168} 08/31/2021 04:46:37 - INFO - __main__ - Step 86221: {'lr': 0.00019618948110520097, 'samples': 16554432, 'steps': 86220, 'loss/train': 1.355759859085083} 08/31/2021 04:46:37 - INFO - __main__ - Step 86222: {'lr': 0.00019618429875921923, 'samples': 16554624, 'steps': 86221, 'loss/train': 0.7602499127388} 08/31/2021 04:46:38 - INFO - __main__ - Step 86223: {'lr': 0.00019617911643748598, 'samples': 16554816, 'steps': 86222, 'loss/train': 0.4653046727180481} 08/31/2021 04:46:38 - INFO - __main__ - Step 86224: {'lr': 0.0001961739341400036, 'samples': 16555008, 'steps': 86223, 'loss/train': 1.4642186164855957} 08/31/2021 04:46:40 - INFO - __main__ - Step 86225: {'lr': 0.00019616875186677442, 'samples': 16555200, 'steps': 86224, 'loss/train': 0.9532167911529541} 08/31/2021 04:46:40 - INFO - __main__ - Step 86226: {'lr': 0.00019616356961780088, 'samples': 16555392, 'steps': 86225, 'loss/train': 0.5761336088180542} 08/31/2021 04:46:40 - INFO - __main__ - Step 86227: {'lr': 0.00019615838739308507, 'samples': 16555584, 'steps': 86226, 'loss/train': 0.8329707384109497} 08/31/2021 04:46:41 - INFO - __main__ - Step 86228: {'lr': 0.00019615320519262953, 'samples': 16555776, 'steps': 86227, 'loss/train': 1.670736312866211} 08/31/2021 04:46:41 - INFO - __main__ - Step 86229: {'lr': 0.00019614802301643646, 'samples': 16555968, 'steps': 86228, 'loss/train': 0.5836076736450195} 08/31/2021 04:46:43 - INFO - __main__ - Step 86230: {'lr': 0.0001961428408645083, 'samples': 16556160, 'steps': 86229, 'loss/train': 1.2271671295166016} 08/31/2021 04:46:43 - INFO - __main__ - Step 86231: {'lr': 0.0001961376587368473, 'samples': 16556352, 'steps': 86230, 'loss/train': 1.5418295860290527} 08/31/2021 04:46:43 - INFO - __main__ - Step 86232: {'lr': 0.00019613247663345586, 'samples': 16556544, 'steps': 86231, 'loss/train': 0.3763062059879303} 08/31/2021 04:46:44 - INFO - __main__ - Step 86233: {'lr': 0.0001961272945543363, 'samples': 16556736, 'steps': 86232, 'loss/train': 1.1399565935134888} 08/31/2021 04:46:44 - INFO - __main__ - Step 86234: {'lr': 0.00019612211249949097, 'samples': 16556928, 'steps': 86233, 'loss/train': 0.6046929955482483} 08/31/2021 04:46:46 - INFO - __main__ - Step 86235: {'lr': 0.00019611693046892216, 'samples': 16557120, 'steps': 86234, 'loss/train': 1.748504877090454} 08/31/2021 04:46:46 - INFO - __main__ - Step 86236: {'lr': 0.0001961117484626322, 'samples': 16557312, 'steps': 86235, 'loss/train': 0.9894658923149109} 08/31/2021 04:46:47 - INFO - __main__ - Step 86237: {'lr': 0.0001961065664806235, 'samples': 16557504, 'steps': 86236, 'loss/train': 1.0549904108047485} 08/31/2021 04:46:47 - INFO - __main__ - Step 86238: {'lr': 0.0001961013845228984, 'samples': 16557696, 'steps': 86237, 'loss/train': 1.3209812641143799} 08/31/2021 04:46:47 - INFO - __main__ - Step 86239: {'lr': 0.0001960962025894591, 'samples': 16557888, 'steps': 86238, 'loss/train': 0.7751185894012451} 08/31/2021 04:46:49 - INFO - __main__ - Step 86240: {'lr': 0.0001960910206803081, 'samples': 16558080, 'steps': 86239, 'loss/train': 1.296797752380371} 08/31/2021 04:46:50 - INFO - __main__ - Step 86241: {'lr': 0.0001960858387954476, 'samples': 16558272, 'steps': 86240, 'loss/train': 1.364907145500183} 08/31/2021 04:46:50 - INFO - __main__ - Step 86242: {'lr': 0.00019608065693487998, 'samples': 16558464, 'steps': 86241, 'loss/train': 1.0606296062469482} 08/31/2021 04:46:50 - INFO - __main__ - Step 86243: {'lr': 0.0001960754750986076, 'samples': 16558656, 'steps': 86242, 'loss/train': 0.06534026563167572} 08/31/2021 04:46:51 - INFO - __main__ - Step 86244: {'lr': 0.00019607029328663276, 'samples': 16558848, 'steps': 86243, 'loss/train': 1.4162132740020752} 08/31/2021 04:46:51 - INFO - __main__ - Step 86245: {'lr': 0.00019606511149895784, 'samples': 16559040, 'steps': 86244, 'loss/train': 0.8362350463867188} 08/31/2021 04:46:53 - INFO - __main__ - Step 86246: {'lr': 0.00019605992973558512, 'samples': 16559232, 'steps': 86245, 'loss/train': 1.6542930603027344} 08/31/2021 04:46:54 - INFO - __main__ - Step 86247: {'lr': 0.00019605474799651697, 'samples': 16559424, 'steps': 86246, 'loss/train': 1.2046735286712646} 08/31/2021 04:46:54 - INFO - __main__ - Step 86248: {'lr': 0.00019604956628175576, 'samples': 16559616, 'steps': 86247, 'loss/train': 1.4005621671676636} 08/31/2021 04:46:54 - INFO - __main__ - Step 86249: {'lr': 0.00019604438459130375, 'samples': 16559808, 'steps': 86248, 'loss/train': 0.8694655299186707} 08/31/2021 04:46:55 - INFO - __main__ - Step 86250: {'lr': 0.0001960392029251633, 'samples': 16560000, 'steps': 86249, 'loss/train': 0.31262150406837463} 08/31/2021 04:46:56 - INFO - __main__ - Step 86251: {'lr': 0.00019603402128333676, 'samples': 16560192, 'steps': 86250, 'loss/train': 1.3320598602294922} 08/31/2021 04:46:57 - INFO - __main__ - Step 86252: {'lr': 0.00019602883966582643, 'samples': 16560384, 'steps': 86251, 'loss/train': 0.8234953284263611} 08/31/2021 04:46:57 - INFO - __main__ - Step 86253: {'lr': 0.00019602365807263475, 'samples': 16560576, 'steps': 86252, 'loss/train': 0.8507929444313049} 08/31/2021 04:46:57 - INFO - __main__ - Step 86254: {'lr': 0.00019601847650376392, 'samples': 16560768, 'steps': 86253, 'loss/train': 1.1977424621582031} 08/31/2021 04:46:58 - INFO - __main__ - Step 86255: {'lr': 0.00019601329495921632, 'samples': 16560960, 'steps': 86254, 'loss/train': 1.2903257608413696} 08/31/2021 04:46:59 - INFO - __main__ - Step 86256: {'lr': 0.00019600811343899432, 'samples': 16561152, 'steps': 86255, 'loss/train': 1.6271213293075562} 08/31/2021 04:47:00 - INFO - __main__ - Step 86257: {'lr': 0.00019600293194310024, 'samples': 16561344, 'steps': 86256, 'loss/train': 1.2890807390213013} 08/31/2021 04:47:00 - INFO - __main__ - Step 86258: {'lr': 0.00019599775047153637, 'samples': 16561536, 'steps': 86257, 'loss/train': 1.1576184034347534} 08/31/2021 04:47:00 - INFO - __main__ - Step 86259: {'lr': 0.00019599256902430516, 'samples': 16561728, 'steps': 86258, 'loss/train': 1.6784878969192505} 08/31/2021 04:47:01 - INFO - __main__ - Step 86260: {'lr': 0.00019598738760140877, 'samples': 16561920, 'steps': 86259, 'loss/train': 1.3855202198028564} 08/31/2021 04:47:01 - INFO - __main__ - Step 86261: {'lr': 0.00019598220620284967, 'samples': 16562112, 'steps': 86260, 'loss/train': 1.3715885877609253} 08/31/2021 04:47:02 - INFO - __main__ - Step 86262: {'lr': 0.00019597702482863013, 'samples': 16562304, 'steps': 86261, 'loss/train': 1.2046254873275757} 08/31/2021 04:47:03 - INFO - __main__ - Step 86263: {'lr': 0.00019597184347875255, 'samples': 16562496, 'steps': 86262, 'loss/train': 0.964601457118988} 08/31/2021 04:47:03 - INFO - __main__ - Step 86264: {'lr': 0.00019596666215321916, 'samples': 16562688, 'steps': 86263, 'loss/train': 1.4912296533584595} 08/31/2021 04:47:04 - INFO - __main__ - Step 86265: {'lr': 0.0001959614808520324, 'samples': 16562880, 'steps': 86264, 'loss/train': 0.7595239281654358} 08/31/2021 04:47:04 - INFO - __main__ - Step 86266: {'lr': 0.00019595629957519457, 'samples': 16563072, 'steps': 86265, 'loss/train': 1.3304249048233032} 08/31/2021 04:47:06 - INFO - __main__ - Step 86267: {'lr': 0.00019595111832270803, 'samples': 16563264, 'steps': 86266, 'loss/train': 1.0528451204299927} 08/31/2021 04:47:06 - INFO - __main__ - Step 86268: {'lr': 0.00019594593709457503, 'samples': 16563456, 'steps': 86267, 'loss/train': 0.7465692758560181} 08/31/2021 04:47:07 - INFO - __main__ - Step 86269: {'lr': 0.00019594075589079798, 'samples': 16563648, 'steps': 86268, 'loss/train': 1.2767282724380493} 08/31/2021 04:47:07 - INFO - __main__ - Step 86270: {'lr': 0.00019593557471137924, 'samples': 16563840, 'steps': 86269, 'loss/train': 0.6449199914932251} 08/31/2021 04:47:07 - INFO - __main__ - Step 86271: {'lr': 0.00019593039355632103, 'samples': 16564032, 'steps': 86270, 'loss/train': 1.8149080276489258} 08/31/2021 04:47:09 - INFO - __main__ - Step 86272: {'lr': 0.00019592521242562576, 'samples': 16564224, 'steps': 86271, 'loss/train': 1.1522631645202637} 08/31/2021 04:47:09 - INFO - __main__ - Step 86273: {'lr': 0.00019592003131929572, 'samples': 16564416, 'steps': 86272, 'loss/train': 0.9792656302452087} 08/31/2021 04:47:10 - INFO - __main__ - Step 86274: {'lr': 0.0001959148502373333, 'samples': 16564608, 'steps': 86273, 'loss/train': 0.7450571060180664} 08/31/2021 04:47:10 - INFO - __main__ - Step 86275: {'lr': 0.0001959096691797408, 'samples': 16564800, 'steps': 86274, 'loss/train': 0.22493180632591248} 08/31/2021 04:47:10 - INFO - __main__ - Step 86276: {'lr': 0.00019590448814652063, 'samples': 16564992, 'steps': 86275, 'loss/train': 1.568922758102417} 08/31/2021 04:47:12 - INFO - __main__ - Step 86277: {'lr': 0.000195899307137675, 'samples': 16565184, 'steps': 86276, 'loss/train': 1.3153010606765747} 08/31/2021 04:47:13 - INFO - __main__ - Step 86278: {'lr': 0.00019589412615320635, 'samples': 16565376, 'steps': 86277, 'loss/train': 1.2158464193344116} 08/31/2021 04:47:13 - INFO - __main__ - Step 86279: {'lr': 0.00019588894519311694, 'samples': 16565568, 'steps': 86278, 'loss/train': 1.6088870763778687} 08/31/2021 04:47:13 - INFO - __main__ - Step 86280: {'lr': 0.0001958837642574092, 'samples': 16565760, 'steps': 86279, 'loss/train': 1.0964628458023071} 08/31/2021 04:47:14 - INFO - __main__ - Step 86281: {'lr': 0.00019587858334608538, 'samples': 16565952, 'steps': 86280, 'loss/train': 1.431740641593933} 08/31/2021 04:47:14 - INFO - __main__ - Step 86282: {'lr': 0.00019587340245914782, 'samples': 16566144, 'steps': 86281, 'loss/train': 5.795553207397461} 08/31/2021 04:47:14 - INFO - __main__ - Step 86283: {'lr': 0.00019586822159659885, 'samples': 16566336, 'steps': 86282, 'loss/train': 5.774330139160156} 08/31/2021 04:47:16 - INFO - __main__ - Step 86284: {'lr': 0.0001958630407584408, 'samples': 16566528, 'steps': 86283, 'loss/train': 1.749084711074829} 08/31/2021 04:47:17 - INFO - __main__ - Step 86285: {'lr': 0.00019585785994467606, 'samples': 16566720, 'steps': 86284, 'loss/train': 1.209397792816162} 08/31/2021 04:47:17 - INFO - __main__ - Step 86286: {'lr': 0.00019585267915530694, 'samples': 16566912, 'steps': 86285, 'loss/train': 0.5786347389221191} 08/31/2021 04:47:17 - INFO - __main__ - Step 86287: {'lr': 0.00019584749839033575, 'samples': 16567104, 'steps': 86286, 'loss/train': 1.4387285709381104} 08/31/2021 04:47:18 - INFO - __main__ - Step 86288: {'lr': 0.00019584231764976484, 'samples': 16567296, 'steps': 86287, 'loss/train': 1.1880388259887695} 08/31/2021 04:47:19 - INFO - __main__ - Step 86289: {'lr': 0.00019583713693359657, 'samples': 16567488, 'steps': 86288, 'loss/train': 1.163683295249939} 08/31/2021 04:47:20 - INFO - __main__ - Step 86290: {'lr': 0.0001958319562418332, 'samples': 16567680, 'steps': 86289, 'loss/train': 1.4457114934921265} 08/31/2021 04:47:20 - INFO - __main__ - Step 86291: {'lr': 0.00019582677557447714, 'samples': 16567872, 'steps': 86290, 'loss/train': 1.3489019870758057} 08/31/2021 04:47:20 - INFO - __main__ - Step 86292: {'lr': 0.00019582159493153074, 'samples': 16568064, 'steps': 86291, 'loss/train': 1.05537748336792} 08/31/2021 04:47:21 - INFO - __main__ - Step 86293: {'lr': 0.00019581641431299634, 'samples': 16568256, 'steps': 86292, 'loss/train': 1.3392884731292725} 08/31/2021 04:47:22 - INFO - __main__ - Step 86294: {'lr': 0.00019581123371887615, 'samples': 16568448, 'steps': 86293, 'loss/train': 0.5790871977806091} 08/31/2021 04:47:22 - INFO - __main__ - Step 86295: {'lr': 0.00019580605314917257, 'samples': 16568640, 'steps': 86294, 'loss/train': 0.9348123073577881} 08/31/2021 04:47:23 - INFO - __main__ - Step 86296: {'lr': 0.00019580087260388795, 'samples': 16568832, 'steps': 86295, 'loss/train': 1.0026240348815918} 08/31/2021 04:47:23 - INFO - __main__ - Step 86297: {'lr': 0.00019579569208302464, 'samples': 16569024, 'steps': 86296, 'loss/train': 1.590785264968872} 08/31/2021 04:47:23 - INFO - __main__ - Step 86298: {'lr': 0.00019579051158658496, 'samples': 16569216, 'steps': 86297, 'loss/train': 1.3805274963378906} 08/31/2021 04:47:26 - INFO - __main__ - Step 86299: {'lr': 0.0001957853311145712, 'samples': 16569408, 'steps': 86298, 'loss/train': 1.321824073791504} 08/31/2021 04:47:26 - INFO - __main__ - Step 86300: {'lr': 0.00019578015066698572, 'samples': 16569600, 'steps': 86299, 'loss/train': 1.6932865381240845} 08/31/2021 04:47:26 - INFO - __main__ - Step 86301: {'lr': 0.00019577497024383093, 'samples': 16569792, 'steps': 86300, 'loss/train': 1.7278543710708618} 08/31/2021 04:47:27 - INFO - __main__ - Step 86302: {'lr': 0.00019576978984510906, 'samples': 16569984, 'steps': 86301, 'loss/train': 0.6685875058174133} 08/31/2021 04:47:27 - INFO - __main__ - Step 86303: {'lr': 0.00019576460947082252, 'samples': 16570176, 'steps': 86302, 'loss/train': 1.4095054864883423} 08/31/2021 04:47:29 - INFO - __main__ - Step 86304: {'lr': 0.00019575942912097359, 'samples': 16570368, 'steps': 86303, 'loss/train': 0.803988516330719} 08/31/2021 04:47:29 - INFO - __main__ - Step 86305: {'lr': 0.0001957542487955646, 'samples': 16570560, 'steps': 86304, 'loss/train': 1.6345672607421875} 08/31/2021 04:47:30 - INFO - __main__ - Step 86306: {'lr': 0.00019574906849459793, 'samples': 16570752, 'steps': 86305, 'loss/train': 0.4120306968688965} 08/31/2021 04:47:30 - INFO - __main__ - Step 86307: {'lr': 0.000195743888218076, 'samples': 16570944, 'steps': 86306, 'loss/train': 1.1162744760513306} 08/31/2021 04:47:30 - INFO - __main__ - Step 86308: {'lr': 0.00019573870796600094, 'samples': 16571136, 'steps': 86307, 'loss/train': 1.454590916633606} 08/31/2021 04:47:32 - INFO - __main__ - Step 86309: {'lr': 0.00019573352773837515, 'samples': 16571328, 'steps': 86308, 'loss/train': 1.5454894304275513} 08/31/2021 04:47:32 - INFO - __main__ - Step 86310: {'lr': 0.00019572834753520102, 'samples': 16571520, 'steps': 86309, 'loss/train': 1.3400875329971313} 08/31/2021 04:47:33 - INFO - __main__ - Step 86311: {'lr': 0.00019572316735648086, 'samples': 16571712, 'steps': 86310, 'loss/train': 1.5764338970184326} 08/31/2021 04:47:33 - INFO - __main__ - Step 86312: {'lr': 0.000195717987202217, 'samples': 16571904, 'steps': 86311, 'loss/train': 1.1276284456253052} 08/31/2021 04:47:33 - INFO - __main__ - Step 86313: {'lr': 0.00019571280707241176, 'samples': 16572096, 'steps': 86312, 'loss/train': 1.5682717561721802} 08/31/2021 04:47:34 - INFO - __main__ - Step 86314: {'lr': 0.0001957076269670675, 'samples': 16572288, 'steps': 86313, 'loss/train': 1.502191424369812} 08/31/2021 04:47:35 - INFO - __main__ - Step 86315: {'lr': 0.00019570244688618655, 'samples': 16572480, 'steps': 86314, 'loss/train': 1.4431368112564087} 08/31/2021 04:47:36 - INFO - __main__ - Step 86316: {'lr': 0.00019569726682977124, 'samples': 16572672, 'steps': 86315, 'loss/train': 1.6560288667678833} 08/31/2021 04:47:36 - INFO - __main__ - Step 86317: {'lr': 0.00019569208679782392, 'samples': 16572864, 'steps': 86316, 'loss/train': 1.2769076824188232} 08/31/2021 04:47:36 - INFO - __main__ - Step 86318: {'lr': 0.0001956869067903469, 'samples': 16573056, 'steps': 86317, 'loss/train': 1.1023746728897095} 08/31/2021 04:47:38 - INFO - __main__ - Step 86319: {'lr': 0.0001956817268073425, 'samples': 16573248, 'steps': 86318, 'loss/train': 1.4486730098724365} 08/31/2021 04:47:39 - INFO - __main__ - Step 86320: {'lr': 0.0001956765468488132, 'samples': 16573440, 'steps': 86319, 'loss/train': 1.0634968280792236} 08/31/2021 04:47:39 - INFO - __main__ - Step 86321: {'lr': 0.0001956713669147611, 'samples': 16573632, 'steps': 86320, 'loss/train': 0.7069753408432007} 08/31/2021 04:47:40 - INFO - __main__ - Step 86322: {'lr': 0.00019566618700518862, 'samples': 16573824, 'steps': 86321, 'loss/train': 1.0154147148132324} 08/31/2021 04:47:40 - INFO - __main__ - Step 86323: {'lr': 0.00019566100712009815, 'samples': 16574016, 'steps': 86322, 'loss/train': 0.09952790290117264} 08/31/2021 04:47:40 - INFO - __main__ - Step 86324: {'lr': 0.00019565582725949198, 'samples': 16574208, 'steps': 86323, 'loss/train': 0.06799011677503586} 08/31/2021 04:47:42 - INFO - __main__ - Step 86325: {'lr': 0.00019565064742337247, 'samples': 16574400, 'steps': 86324, 'loss/train': 1.0658760070800781} 08/31/2021 04:47:43 - INFO - __main__ - Step 86326: {'lr': 0.00019564546761174193, 'samples': 16574592, 'steps': 86325, 'loss/train': 0.041166987270116806} 08/31/2021 04:47:43 - INFO - __main__ - Step 86327: {'lr': 0.00019564028782460268, 'samples': 16574784, 'steps': 86326, 'loss/train': 1.2770419120788574} 08/31/2021 04:47:43 - INFO - __main__ - Step 86328: {'lr': 0.0001956351080619571, 'samples': 16574976, 'steps': 86327, 'loss/train': 1.2298250198364258} 08/31/2021 04:47:44 - INFO - __main__ - Step 86329: {'lr': 0.0001956299283238075, 'samples': 16575168, 'steps': 86328, 'loss/train': 1.399011254310608} 08/31/2021 04:47:45 - INFO - __main__ - Step 86330: {'lr': 0.00019562474861015621, 'samples': 16575360, 'steps': 86329, 'loss/train': 1.0728486776351929} 08/31/2021 04:47:46 - INFO - __main__ - Step 86331: {'lr': 0.00019561956892100561, 'samples': 16575552, 'steps': 86330, 'loss/train': 0.9076402187347412} 08/31/2021 04:47:46 - INFO - __main__ - Step 86332: {'lr': 0.00019561438925635793, 'samples': 16575744, 'steps': 86331, 'loss/train': 1.5396647453308105} 08/31/2021 04:47:47 - INFO - __main__ - Step 86333: {'lr': 0.0001956092096162156, 'samples': 16575936, 'steps': 86332, 'loss/train': 0.9602342844009399} 08/31/2021 04:47:47 - INFO - __main__ - Step 86334: {'lr': 0.00019560403000058103, 'samples': 16576128, 'steps': 86333, 'loss/train': 0.5169702768325806} 08/31/2021 04:47:48 - INFO - __main__ - Step 86335: {'lr': 0.00019559885040945632, 'samples': 16576320, 'steps': 86334, 'loss/train': 1.0660264492034912} 08/31/2021 04:47:49 - INFO - __main__ - Step 86336: {'lr': 0.00019559367084284396, 'samples': 16576512, 'steps': 86335, 'loss/train': 1.167826533317566} 08/31/2021 04:47:49 - INFO - __main__ - Step 86337: {'lr': 0.00019558849130074622, 'samples': 16576704, 'steps': 86336, 'loss/train': 1.3899173736572266} 08/31/2021 04:47:50 - INFO - __main__ - Step 86338: {'lr': 0.00019558331178316546, 'samples': 16576896, 'steps': 86337, 'loss/train': 0.9138818383216858} 08/31/2021 04:47:50 - INFO - __main__ - Step 86339: {'lr': 0.00019557813229010405, 'samples': 16577088, 'steps': 86338, 'loss/train': 1.6023184061050415} 08/31/2021 04:47:52 - INFO - __main__ - Step 86340: {'lr': 0.00019557295282156427, 'samples': 16577280, 'steps': 86339, 'loss/train': 0.7009370923042297} 08/31/2021 04:47:52 - INFO - __main__ - Step 86341: {'lr': 0.0001955677733775485, 'samples': 16577472, 'steps': 86340, 'loss/train': 0.8461728692054749} 08/31/2021 04:47:53 - INFO - __main__ - Step 86342: {'lr': 0.00019556259395805904, 'samples': 16577664, 'steps': 86341, 'loss/train': 5.780470371246338} 08/31/2021 04:47:53 - INFO - __main__ - Step 86343: {'lr': 0.00019555741456309822, 'samples': 16577856, 'steps': 86342, 'loss/train': 3.7538609504699707} 08/31/2021 04:47:53 - INFO - __main__ - Step 86344: {'lr': 0.00019555223519266841, 'samples': 16578048, 'steps': 86343, 'loss/train': 0.33687055110931396} 08/31/2021 04:47:54 - INFO - __main__ - Step 86345: {'lr': 0.00019554705584677194, 'samples': 16578240, 'steps': 86344, 'loss/train': 1.9324212074279785} 08/31/2021 04:47:55 - INFO - __main__ - Step 86346: {'lr': 0.0001955418765254111, 'samples': 16578432, 'steps': 86345, 'loss/train': 1.0133438110351562} 08/31/2021 04:47:56 - INFO - __main__ - Step 86347: {'lr': 0.00019553669722858835, 'samples': 16578624, 'steps': 86346, 'loss/train': 0.9725199937820435} 08/31/2021 04:47:56 - INFO - __main__ - Step 86348: {'lr': 0.00019553151795630584, 'samples': 16578816, 'steps': 86347, 'loss/train': 1.450828194618225} 08/31/2021 04:47:56 - INFO - __main__ - Step 86349: {'lr': 0.00019552633870856595, 'samples': 16579008, 'steps': 86348, 'loss/train': 1.8126027584075928} 08/31/2021 04:47:57 - INFO - __main__ - Step 86350: {'lr': 0.00019552115948537108, 'samples': 16579200, 'steps': 86349, 'loss/train': 1.0200098752975464} 08/31/2021 04:47:58 - INFO - __main__ - Step 86351: {'lr': 0.00019551598028672354, 'samples': 16579392, 'steps': 86350, 'loss/train': 1.3867353200912476} 08/31/2021 04:47:59 - INFO - __main__ - Step 86352: {'lr': 0.00019551080111262565, 'samples': 16579584, 'steps': 86351, 'loss/train': 1.4939919710159302} 08/31/2021 04:47:59 - INFO - __main__ - Step 86353: {'lr': 0.00019550562196307976, 'samples': 16579776, 'steps': 86352, 'loss/train': 1.180060863494873} 08/31/2021 04:47:59 - INFO - __main__ - Step 86354: {'lr': 0.00019550044283808815, 'samples': 16579968, 'steps': 86353, 'loss/train': 1.0515600442886353} 08/31/2021 04:48:00 - INFO - __main__ - Step 86355: {'lr': 0.00019549526373765326, 'samples': 16580160, 'steps': 86354, 'loss/train': 0.9484845995903015} 08/31/2021 04:48:02 - INFO - __main__ - Step 86356: {'lr': 0.00019549008466177733, 'samples': 16580352, 'steps': 86355, 'loss/train': 1.3635507822036743} 08/31/2021 04:48:02 - INFO - __main__ - Step 86357: {'lr': 0.00019548490561046273, 'samples': 16580544, 'steps': 86356, 'loss/train': 1.5906139612197876} 08/31/2021 04:48:03 - INFO - __main__ - Step 86358: {'lr': 0.00019547972658371182, 'samples': 16580736, 'steps': 86357, 'loss/train': 0.821186900138855} 08/31/2021 04:48:03 - INFO - __main__ - Step 86359: {'lr': 0.0001954745475815269, 'samples': 16580928, 'steps': 86358, 'loss/train': 1.4790546894073486} 08/31/2021 04:48:03 - INFO - __main__ - Step 86360: {'lr': 0.00019546936860391026, 'samples': 16581120, 'steps': 86359, 'loss/train': 1.1965724229812622} 08/31/2021 04:48:05 - INFO - __main__ - Step 86361: {'lr': 0.00019546418965086444, 'samples': 16581312, 'steps': 86360, 'loss/train': 1.195862889289856} 08/31/2021 04:48:05 - INFO - __main__ - Step 86362: {'lr': 0.00019545901072239147, 'samples': 16581504, 'steps': 86361, 'loss/train': 0.8995250463485718} 08/31/2021 04:48:06 - INFO - __main__ - Step 86363: {'lr': 0.00019545383181849383, 'samples': 16581696, 'steps': 86362, 'loss/train': 1.601991891860962} 08/31/2021 04:48:06 - INFO - __main__ - Step 86364: {'lr': 0.00019544865293917384, 'samples': 16581888, 'steps': 86363, 'loss/train': 1.4620338678359985} 08/31/2021 04:48:06 - INFO - __main__ - Step 86365: {'lr': 0.00019544347408443388, 'samples': 16582080, 'steps': 86364, 'loss/train': 1.0607887506484985} 08/31/2021 04:48:07 - INFO - __main__ - Step 86366: {'lr': 0.00019543829525427625, 'samples': 16582272, 'steps': 86365, 'loss/train': 2.2352709770202637} 08/31/2021 04:48:08 - INFO - __main__ - Step 86367: {'lr': 0.00019543311644870326, 'samples': 16582464, 'steps': 86366, 'loss/train': 1.6547527313232422} 08/31/2021 04:48:09 - INFO - __main__ - Step 86368: {'lr': 0.00019542793766771726, 'samples': 16582656, 'steps': 86367, 'loss/train': 0.7614696025848389} 08/31/2021 04:48:09 - INFO - __main__ - Step 86369: {'lr': 0.00019542275891132064, 'samples': 16582848, 'steps': 86368, 'loss/train': 1.0861040353775024} 08/31/2021 04:48:09 - INFO - __main__ - Step 86370: {'lr': 0.00019541758017951563, 'samples': 16583040, 'steps': 86369, 'loss/train': 0.03497728705406189} 08/31/2021 04:48:10 - INFO - __main__ - Step 86371: {'lr': 0.00019541240147230462, 'samples': 16583232, 'steps': 86370, 'loss/train': 1.4201158285140991} 08/31/2021 04:48:11 - INFO - __main__ - Step 86372: {'lr': 0.00019540722278969002, 'samples': 16583424, 'steps': 86371, 'loss/train': 0.7580575942993164} 08/31/2021 04:48:12 - INFO - __main__ - Step 86373: {'lr': 0.000195402044131674, 'samples': 16583616, 'steps': 86372, 'loss/train': 1.4391818046569824} 08/31/2021 04:48:12 - INFO - __main__ - Step 86374: {'lr': 0.00019539686549825908, 'samples': 16583808, 'steps': 86373, 'loss/train': 1.5438904762268066} 08/31/2021 04:48:12 - INFO - __main__ - Step 86375: {'lr': 0.0001953916868894474, 'samples': 16584000, 'steps': 86374, 'loss/train': 1.1092263460159302} 08/31/2021 04:48:13 - INFO - __main__ - Step 86376: {'lr': 0.00019538650830524138, 'samples': 16584192, 'steps': 86375, 'loss/train': 1.0720471143722534} 08/31/2021 04:48:14 - INFO - __main__ - Step 86377: {'lr': 0.00019538132974564334, 'samples': 16584384, 'steps': 86376, 'loss/train': 1.567082405090332} 08/31/2021 04:48:15 - INFO - __main__ - Step 86378: {'lr': 0.00019537615121065566, 'samples': 16584576, 'steps': 86377, 'loss/train': 0.8979570865631104} 08/31/2021 04:48:15 - INFO - __main__ - Step 86379: {'lr': 0.00019537097270028064, 'samples': 16584768, 'steps': 86378, 'loss/train': 1.3040637969970703} 08/31/2021 04:48:15 - INFO - __main__ - Step 86380: {'lr': 0.00019536579421452062, 'samples': 16584960, 'steps': 86379, 'loss/train': 1.1503808498382568} 08/31/2021 04:48:16 - INFO - __main__ - Step 86381: {'lr': 0.00019536061575337792, 'samples': 16585152, 'steps': 86380, 'loss/train': 0.9518219828605652} 08/31/2021 04:48:18 - INFO - __main__ - Step 86382: {'lr': 0.00019535543731685488, 'samples': 16585344, 'steps': 86381, 'loss/train': 1.2219890356063843} 08/31/2021 04:48:18 - INFO - __main__ - Step 86383: {'lr': 0.0001953502589049539, 'samples': 16585536, 'steps': 86382, 'loss/train': 0.8931750655174255} 08/31/2021 04:48:18 - INFO - __main__ - Step 86384: {'lr': 0.0001953450805176772, 'samples': 16585728, 'steps': 86383, 'loss/train': 1.3520300388336182} 08/31/2021 04:48:19 - INFO - __main__ - Step 86385: {'lr': 0.00019533990215502714, 'samples': 16585920, 'steps': 86384, 'loss/train': 1.2011882066726685} 08/31/2021 04:48:19 - INFO - __main__ - Step 86386: {'lr': 0.00019533472381700608, 'samples': 16586112, 'steps': 86385, 'loss/train': 1.4443836212158203} 08/31/2021 04:48:21 - INFO - __main__ - Step 86387: {'lr': 0.00019532954550361637, 'samples': 16586304, 'steps': 86386, 'loss/train': 1.2723441123962402} 08/31/2021 04:48:21 - INFO - __main__ - Step 86388: {'lr': 0.00019532436721486038, 'samples': 16586496, 'steps': 86387, 'loss/train': 1.3126552104949951} 08/31/2021 04:48:21 - INFO - __main__ - Step 86389: {'lr': 0.00019531918895074034, 'samples': 16586688, 'steps': 86388, 'loss/train': 0.8381240367889404} 08/31/2021 04:48:22 - INFO - __main__ - Step 86390: {'lr': 0.0001953140107112586, 'samples': 16586880, 'steps': 86389, 'loss/train': 1.4022691249847412} 08/31/2021 04:48:22 - INFO - __main__ - Step 86391: {'lr': 0.0001953088324964175, 'samples': 16587072, 'steps': 86390, 'loss/train': 1.320359468460083} 08/31/2021 04:48:24 - INFO - __main__ - Step 86392: {'lr': 0.00019530365430621947, 'samples': 16587264, 'steps': 86391, 'loss/train': 3.6906607151031494} 08/31/2021 04:48:24 - INFO - __main__ - Step 86393: {'lr': 0.00019529847614066672, 'samples': 16587456, 'steps': 86392, 'loss/train': 0.337687611579895} 08/31/2021 04:48:25 - INFO - __main__ - Step 86394: {'lr': 0.0001952932979997617, 'samples': 16587648, 'steps': 86393, 'loss/train': 1.9256517887115479} 08/31/2021 04:48:25 - INFO - __main__ - Step 86395: {'lr': 0.0001952881198835066, 'samples': 16587840, 'steps': 86394, 'loss/train': 1.078112244606018} 08/31/2021 04:48:25 - INFO - __main__ - Step 86396: {'lr': 0.00019528294179190387, 'samples': 16588032, 'steps': 86395, 'loss/train': 1.159318447113037} 08/31/2021 04:48:26 - INFO - __main__ - Step 86397: {'lr': 0.00019527776372495575, 'samples': 16588224, 'steps': 86396, 'loss/train': 0.4177796542644501} 08/31/2021 04:48:27 - INFO - __main__ - Step 86398: {'lr': 0.0001952725856826647, 'samples': 16588416, 'steps': 86397, 'loss/train': 1.8456659317016602} 08/31/2021 04:48:28 - INFO - __main__ - Step 86399: {'lr': 0.0001952674076650329, 'samples': 16588608, 'steps': 86398, 'loss/train': 1.1935560703277588} 08/31/2021 04:48:28 - INFO - __main__ - Step 86400: {'lr': 0.0001952622296720628, 'samples': 16588800, 'steps': 86399, 'loss/train': 1.3285727500915527} 08/31/2021 04:48:28 - INFO - __main__ - Step 86401: {'lr': 0.00019525705170375673, 'samples': 16588992, 'steps': 86400, 'loss/train': 1.0030065774917603} 08/31/2021 04:48:29 - INFO - __main__ - Step 86402: {'lr': 0.00019525187376011696, 'samples': 16589184, 'steps': 86401, 'loss/train': 1.5388234853744507} 08/31/2021 04:48:30 - INFO - __main__ - Step 86403: {'lr': 0.00019524669584114585, 'samples': 16589376, 'steps': 86402, 'loss/train': 0.5110324025154114} 08/31/2021 04:48:31 - INFO - __main__ - Step 86404: {'lr': 0.0001952415179468457, 'samples': 16589568, 'steps': 86403, 'loss/train': 1.0801339149475098} 08/31/2021 04:48:31 - INFO - __main__ - Step 86405: {'lr': 0.00019523634007721896, 'samples': 16589760, 'steps': 86404, 'loss/train': 1.5089688301086426} 08/31/2021 04:48:31 - INFO - __main__ - Step 86406: {'lr': 0.00019523116223226782, 'samples': 16589952, 'steps': 86405, 'loss/train': 0.9687036871910095} 08/31/2021 04:48:32 - INFO - __main__ - Step 86407: {'lr': 0.00019522598441199467, 'samples': 16590144, 'steps': 86406, 'loss/train': 0.9125522971153259} 08/31/2021 04:48:33 - INFO - __main__ - Step 86408: {'lr': 0.00019522080661640184, 'samples': 16590336, 'steps': 86407, 'loss/train': 1.3757075071334839} 08/31/2021 04:48:34 - INFO - __main__ - Step 86409: {'lr': 0.00019521562884549168, 'samples': 16590528, 'steps': 86408, 'loss/train': 1.008568525314331} 08/31/2021 04:48:34 - INFO - __main__ - Step 86410: {'lr': 0.00019521045109926653, 'samples': 16590720, 'steps': 86409, 'loss/train': 1.2439419031143188} 08/31/2021 04:48:34 - INFO - __main__ - Step 86411: {'lr': 0.00019520527337772868, 'samples': 16590912, 'steps': 86410, 'loss/train': 1.4691922664642334} 08/31/2021 04:48:35 - INFO - __main__ - Step 86412: {'lr': 0.00019520009568088048, 'samples': 16591104, 'steps': 86411, 'loss/train': 0.9054619073867798} 08/31/2021 04:48:37 - INFO - __main__ - Step 86413: {'lr': 0.0001951949180087243, 'samples': 16591296, 'steps': 86412, 'loss/train': 0.3428639769554138} 08/31/2021 04:48:37 - INFO - __main__ - Step 86414: {'lr': 0.00019518974036126247, 'samples': 16591488, 'steps': 86413, 'loss/train': 1.2082960605621338} 08/31/2021 04:48:37 - INFO - __main__ - Step 86415: {'lr': 0.00019518456273849731, 'samples': 16591680, 'steps': 86414, 'loss/train': 1.1043269634246826} 08/31/2021 04:48:38 - INFO - __main__ - Step 86416: {'lr': 0.0001951793851404311, 'samples': 16591872, 'steps': 86415, 'loss/train': 0.8770592212677002} 08/31/2021 04:48:38 - INFO - __main__ - Step 86417: {'lr': 0.00019517420756706618, 'samples': 16592064, 'steps': 86416, 'loss/train': 1.3482862710952759} 08/31/2021 04:48:40 - INFO - __main__ - Step 86418: {'lr': 0.00019516903001840494, 'samples': 16592256, 'steps': 86417, 'loss/train': 0.9670127630233765} 08/31/2021 04:48:40 - INFO - __main__ - Step 86419: {'lr': 0.00019516385249444967, 'samples': 16592448, 'steps': 86418, 'loss/train': 1.5955380201339722} 08/31/2021 04:48:41 - INFO - __main__ - Step 86420: {'lr': 0.00019515867499520273, 'samples': 16592640, 'steps': 86419, 'loss/train': 2.2964584827423096} 08/31/2021 04:48:41 - INFO - __main__ - Step 86421: {'lr': 0.00019515349752066648, 'samples': 16592832, 'steps': 86420, 'loss/train': 1.2918208837509155} 08/31/2021 04:48:41 - INFO - __main__ - Step 86422: {'lr': 0.00019514832007084317, 'samples': 16593024, 'steps': 86421, 'loss/train': 0.8663538694381714} 08/31/2021 04:48:42 - INFO - __main__ - Step 86423: {'lr': 0.0001951431426457352, 'samples': 16593216, 'steps': 86422, 'loss/train': 1.2665821313858032} 08/31/2021 04:48:43 - INFO - __main__ - Step 86424: {'lr': 0.00019513796524534487, 'samples': 16593408, 'steps': 86423, 'loss/train': 1.2987053394317627} 08/31/2021 04:48:44 - INFO - __main__ - Step 86425: {'lr': 0.00019513278786967457, 'samples': 16593600, 'steps': 86424, 'loss/train': 1.23130464553833} 08/31/2021 04:48:44 - INFO - __main__ - Step 86426: {'lr': 0.00019512761051872655, 'samples': 16593792, 'steps': 86425, 'loss/train': 1.0940667390823364} 08/31/2021 04:48:44 - INFO - __main__ - Step 86427: {'lr': 0.00019512243319250318, 'samples': 16593984, 'steps': 86426, 'loss/train': 0.7686198353767395} 08/31/2021 04:48:45 - INFO - __main__ - Step 86428: {'lr': 0.00019511725589100692, 'samples': 16594176, 'steps': 86427, 'loss/train': 1.3975698947906494} 08/31/2021 04:48:46 - INFO - __main__ - Step 86429: {'lr': 0.00019511207861423984, 'samples': 16594368, 'steps': 86428, 'loss/train': 1.2612193822860718} 08/31/2021 04:48:47 - INFO - __main__ - Step 86430: {'lr': 0.00019510690136220445, 'samples': 16594560, 'steps': 86429, 'loss/train': 1.2688322067260742} 08/31/2021 04:48:47 - INFO - __main__ - Step 86431: {'lr': 0.00019510172413490302, 'samples': 16594752, 'steps': 86430, 'loss/train': 1.4711796045303345} 08/31/2021 04:48:47 - INFO - __main__ - Step 86432: {'lr': 0.00019509654693233792, 'samples': 16594944, 'steps': 86431, 'loss/train': 1.2777317762374878} 08/31/2021 04:48:48 - INFO - __main__ - Step 86433: {'lr': 0.00019509136975451148, 'samples': 16595136, 'steps': 86432, 'loss/train': 1.402367115020752} 08/31/2021 04:48:49 - INFO - __main__ - Step 86434: {'lr': 0.000195086192601426, 'samples': 16595328, 'steps': 86433, 'loss/train': 1.6396821737289429} 08/31/2021 04:48:50 - INFO - __main__ - Step 86435: {'lr': 0.00019508101547308383, 'samples': 16595520, 'steps': 86434, 'loss/train': 1.178935170173645} 08/31/2021 04:48:50 - INFO - __main__ - Step 86436: {'lr': 0.00019507583836948732, 'samples': 16595712, 'steps': 86435, 'loss/train': 1.2270716428756714} 08/31/2021 04:48:50 - INFO - __main__ - Step 86437: {'lr': 0.00019507066129063877, 'samples': 16595904, 'steps': 86436, 'loss/train': 1.2267168760299683} 08/31/2021 04:48:51 - INFO - __main__ - Step 86438: {'lr': 0.00019506548423654056, 'samples': 16596096, 'steps': 86437, 'loss/train': 1.048105239868164} 08/31/2021 04:48:52 - INFO - __main__ - Step 86439: {'lr': 0.00019506030720719498, 'samples': 16596288, 'steps': 86438, 'loss/train': 1.3018356561660767} 08/31/2021 04:48:53 - INFO - __main__ - Step 86440: {'lr': 0.00019505513020260434, 'samples': 16596480, 'steps': 86439, 'loss/train': 1.4698991775512695} 08/31/2021 04:48:53 - INFO - __main__ - Step 86441: {'lr': 0.0001950499532227712, 'samples': 16596672, 'steps': 86440, 'loss/train': 1.6210476160049438} 08/31/2021 04:48:53 - INFO - __main__ - Step 86442: {'lr': 0.00019504477626769754, 'samples': 16596864, 'steps': 86441, 'loss/train': 1.3963146209716797} 08/31/2021 04:48:54 - INFO - __main__ - Step 86443: {'lr': 0.00019503959933738586, 'samples': 16597056, 'steps': 86442, 'loss/train': 1.4400389194488525} 08/31/2021 04:48:56 - INFO - __main__ - Step 86444: {'lr': 0.0001950344224318385, 'samples': 16597248, 'steps': 86443, 'loss/train': 1.0774205923080444} 08/31/2021 04:48:56 - INFO - __main__ - Step 86445: {'lr': 0.00019502924555105778, 'samples': 16597440, 'steps': 86444, 'loss/train': 1.4156149625778198} 08/31/2021 04:48:57 - INFO - __main__ - Step 86446: {'lr': 0.000195024068695046, 'samples': 16597632, 'steps': 86445, 'loss/train': 0.986877977848053} 08/31/2021 04:48:57 - INFO - __main__ - Step 86447: {'lr': 0.00019501889186380558, 'samples': 16597824, 'steps': 86446, 'loss/train': 1.235837697982788} 08/31/2021 04:48:57 - INFO - __main__ - Step 86448: {'lr': 0.0001950137150573388, 'samples': 16598016, 'steps': 86447, 'loss/train': 1.1734365224838257} 08/31/2021 04:48:58 - INFO - __main__ - Step 86449: {'lr': 0.00019500853827564795, 'samples': 16598208, 'steps': 86448, 'loss/train': 0.02057219296693802} 08/31/2021 04:48:58 - INFO - __main__ - Step 86450: {'lr': 0.0001950033615187354, 'samples': 16598400, 'steps': 86449, 'loss/train': 0.018185272812843323} 08/31/2021 04:48:59 - INFO - __main__ - Step 86451: {'lr': 0.00019499818478660352, 'samples': 16598592, 'steps': 86450, 'loss/train': 1.7110378742218018} 08/31/2021 04:49:00 - INFO - __main__ - Step 86452: {'lr': 0.0001949930080792546, 'samples': 16598784, 'steps': 86451, 'loss/train': 0.6936678886413574} 08/31/2021 04:49:00 - INFO - __main__ - Step 86453: {'lr': 0.000194987831396691, 'samples': 16598976, 'steps': 86452, 'loss/train': 1.4584383964538574} 08/31/2021 04:49:01 - INFO - __main__ - Step 86454: {'lr': 0.000194982654738915, 'samples': 16599168, 'steps': 86453, 'loss/train': 0.4569149911403656} 08/31/2021 04:49:01 - INFO - __main__ - Step 86455: {'lr': 0.00019497747810592907, 'samples': 16599360, 'steps': 86454, 'loss/train': 0.9243428707122803} 08/31/2021 04:49:02 - INFO - __main__ - Step 86456: {'lr': 0.00019497230149773538, 'samples': 16599552, 'steps': 86455, 'loss/train': 2.0789477825164795} 08/31/2021 04:49:03 - INFO - __main__ - Step 86457: {'lr': 0.00019496712491433627, 'samples': 16599744, 'steps': 86456, 'loss/train': 1.578992247581482} 08/31/2021 04:49:03 - INFO - __main__ - Step 86458: {'lr': 0.00019496194835573417, 'samples': 16599936, 'steps': 86457, 'loss/train': 1.1463059186935425} 08/31/2021 04:49:04 - INFO - __main__ - Step 86459: {'lr': 0.00019495677182193133, 'samples': 16600128, 'steps': 86458, 'loss/train': 1.2667030096054077} 08/31/2021 04:49:04 - INFO - __main__ - Step 86460: {'lr': 0.00019495159531293015, 'samples': 16600320, 'steps': 86459, 'loss/train': 1.3264334201812744} 08/31/2021 04:49:06 - INFO - __main__ - Step 86461: {'lr': 0.00019494641882873289, 'samples': 16600512, 'steps': 86460, 'loss/train': 1.440791368484497} 08/31/2021 04:49:06 - INFO - __main__ - Step 86462: {'lr': 0.00019494124236934192, 'samples': 16600704, 'steps': 86461, 'loss/train': 0.9556764960289001} 08/31/2021 04:49:06 - INFO - __main__ - Step 86463: {'lr': 0.00019493606593475962, 'samples': 16600896, 'steps': 86462, 'loss/train': 1.3141725063323975} 08/31/2021 04:49:07 - INFO - __main__ - Step 86464: {'lr': 0.0001949308895249883, 'samples': 16601088, 'steps': 86463, 'loss/train': 0.7778187394142151} 08/31/2021 04:49:07 - INFO - __main__ - Step 86465: {'lr': 0.00019492571314003022, 'samples': 16601280, 'steps': 86464, 'loss/train': 1.3194295167922974} 08/31/2021 04:49:09 - INFO - __main__ - Step 86466: {'lr': 0.00019492053677988777, 'samples': 16601472, 'steps': 86465, 'loss/train': 1.7562227249145508} 08/31/2021 04:49:10 - INFO - __main__ - Step 86467: {'lr': 0.0001949153604445633, 'samples': 16601664, 'steps': 86466, 'loss/train': 1.1179677248001099} 08/31/2021 04:49:10 - INFO - __main__ - Step 86468: {'lr': 0.0001949101841340592, 'samples': 16601856, 'steps': 86467, 'loss/train': 1.2240149974822998} 08/31/2021 04:49:10 - INFO - __main__ - Step 86469: {'lr': 0.00019490500784837762, 'samples': 16602048, 'steps': 86468, 'loss/train': 0.9697097539901733} 08/31/2021 04:49:11 - INFO - __main__ - Step 86470: {'lr': 0.000194899831587521, 'samples': 16602240, 'steps': 86469, 'loss/train': 0.9864286780357361} 08/31/2021 04:49:11 - INFO - __main__ - Step 86471: {'lr': 0.00019489465535149164, 'samples': 16602432, 'steps': 86470, 'loss/train': 0.04035637900233269} 08/31/2021 04:49:12 - INFO - __main__ - Step 86472: {'lr': 0.00019488947914029193, 'samples': 16602624, 'steps': 86471, 'loss/train': 0.47912585735321045} 08/31/2021 04:49:13 - INFO - __main__ - Step 86473: {'lr': 0.00019488430295392417, 'samples': 16602816, 'steps': 86472, 'loss/train': 1.6553955078125} 08/31/2021 04:49:13 - INFO - __main__ - Step 86474: {'lr': 0.00019487912679239068, 'samples': 16603008, 'steps': 86473, 'loss/train': 1.5116407871246338} 08/31/2021 04:49:14 - INFO - __main__ - Step 86475: {'lr': 0.0001948739506556938, 'samples': 16603200, 'steps': 86474, 'loss/train': 0.38435783982276917} 08/31/2021 04:49:14 - INFO - __main__ - Step 86476: {'lr': 0.0001948687745438359, 'samples': 16603392, 'steps': 86475, 'loss/train': 0.24713531136512756} 08/31/2021 04:49:16 - INFO - __main__ - Step 86477: {'lr': 0.00019486359845681926, 'samples': 16603584, 'steps': 86476, 'loss/train': 2.175596237182617} 08/31/2021 04:49:16 - INFO - __main__ - Step 86478: {'lr': 0.0001948584223946462, 'samples': 16603776, 'steps': 86477, 'loss/train': 0.8420671224594116} 08/31/2021 04:49:16 - INFO - __main__ - Step 86479: {'lr': 0.00019485324635731913, 'samples': 16603968, 'steps': 86478, 'loss/train': 1.2707608938217163} 08/31/2021 04:49:17 - INFO - __main__ - Step 86480: {'lr': 0.00019484807034484032, 'samples': 16604160, 'steps': 86479, 'loss/train': 1.1084436178207397} 08/31/2021 04:49:17 - INFO - __main__ - Step 86481: {'lr': 0.00019484289435721212, 'samples': 16604352, 'steps': 86480, 'loss/train': 1.3609150648117065} 08/31/2021 04:49:18 - INFO - __main__ - Step 86482: {'lr': 0.00019483771839443696, 'samples': 16604544, 'steps': 86481, 'loss/train': 0.9744909405708313} 08/31/2021 04:49:19 - INFO - __main__ - Step 86483: {'lr': 0.00019483254245651697, 'samples': 16604736, 'steps': 86482, 'loss/train': 1.020114541053772} 08/31/2021 04:49:19 - INFO - __main__ - Step 86484: {'lr': 0.00019482736654345456, 'samples': 16604928, 'steps': 86483, 'loss/train': 1.2512383460998535} 08/31/2021 04:49:20 - INFO - __main__ - Step 86485: {'lr': 0.00019482219065525215, 'samples': 16605120, 'steps': 86484, 'loss/train': 1.6920065879821777} 08/31/2021 04:49:20 - INFO - __main__ - Step 86486: {'lr': 0.00019481701479191193, 'samples': 16605312, 'steps': 86485, 'loss/train': 1.3192921876907349} 08/31/2021 04:49:22 - INFO - __main__ - Step 86487: {'lr': 0.00019481183895343637, 'samples': 16605504, 'steps': 86486, 'loss/train': 1.173780083656311} 08/31/2021 04:49:22 - INFO - __main__ - Step 86488: {'lr': 0.00019480666313982772, 'samples': 16605696, 'steps': 86487, 'loss/train': 1.5069514513015747} 08/31/2021 04:49:22 - INFO - __main__ - Step 86489: {'lr': 0.00019480148735108834, 'samples': 16605888, 'steps': 86488, 'loss/train': 1.1302454471588135} 08/31/2021 04:49:23 - INFO - __main__ - Step 86490: {'lr': 0.00019479631158722058, 'samples': 16606080, 'steps': 86489, 'loss/train': 0.978501558303833} 08/31/2021 04:49:23 - INFO - __main__ - Step 86491: {'lr': 0.00019479113584822672, 'samples': 16606272, 'steps': 86490, 'loss/train': 1.0572514533996582} 08/31/2021 04:49:25 - INFO - __main__ - Step 86492: {'lr': 0.00019478596013410915, 'samples': 16606464, 'steps': 86491, 'loss/train': 1.2541066408157349} 08/31/2021 04:49:25 - INFO - __main__ - Step 86493: {'lr': 0.00019478078444487015, 'samples': 16606656, 'steps': 86492, 'loss/train': 0.9666765332221985} 08/31/2021 04:49:25 - INFO - __main__ - Step 86494: {'lr': 0.0001947756087805121, 'samples': 16606848, 'steps': 86493, 'loss/train': 1.469343662261963} 08/31/2021 04:49:26 - INFO - __main__ - Step 86495: {'lr': 0.00019477043314103737, 'samples': 16607040, 'steps': 86494, 'loss/train': 1.4966413974761963} 08/31/2021 04:49:26 - INFO - __main__ - Step 86496: {'lr': 0.00019476525752644817, 'samples': 16607232, 'steps': 86495, 'loss/train': 1.6882741451263428} 08/31/2021 04:49:28 - INFO - __main__ - Step 86497: {'lr': 0.00019476008193674687, 'samples': 16607424, 'steps': 86496, 'loss/train': 1.6880455017089844} 08/31/2021 04:49:28 - INFO - __main__ - Step 86498: {'lr': 0.00019475490637193584, 'samples': 16607616, 'steps': 86497, 'loss/train': 1.3212034702301025} 08/31/2021 04:49:28 - INFO - __main__ - Step 86499: {'lr': 0.00019474973083201738, 'samples': 16607808, 'steps': 86498, 'loss/train': 1.4652221202850342} 08/31/2021 04:49:29 - INFO - __main__ - Step 86500: {'lr': 0.00019474455531699384, 'samples': 16608000, 'steps': 86499, 'loss/train': 1.1365432739257812} 08/31/2021 04:49:29 - INFO - __main__ - Step 86501: {'lr': 0.00019473937982686756, 'samples': 16608192, 'steps': 86500, 'loss/train': 1.142922282218933} 08/31/2021 04:49:31 - INFO - __main__ - Step 86502: {'lr': 0.00019473420436164085, 'samples': 16608384, 'steps': 86501, 'loss/train': 1.4109784364700317} 08/31/2021 04:49:31 - INFO - __main__ - Step 86503: {'lr': 0.0001947290289213161, 'samples': 16608576, 'steps': 86502, 'loss/train': 1.5168207883834839} 08/31/2021 04:49:31 - INFO - __main__ - Step 86504: {'lr': 0.00019472385350589552, 'samples': 16608768, 'steps': 86503, 'loss/train': 1.6804331541061401} 08/31/2021 04:49:32 - INFO - __main__ - Step 86505: {'lr': 0.00019471867811538158, 'samples': 16608960, 'steps': 86504, 'loss/train': 2.057305097579956} 08/31/2021 04:49:32 - INFO - __main__ - Step 86506: {'lr': 0.00019471350274977657, 'samples': 16609152, 'steps': 86505, 'loss/train': 1.024780035018921} 08/31/2021 04:49:34 - INFO - __main__ - Step 86507: {'lr': 0.0001947083274090828, 'samples': 16609344, 'steps': 86506, 'loss/train': 1.554795503616333} 08/31/2021 04:49:34 - INFO - __main__ - Step 86508: {'lr': 0.00019470315209330253, 'samples': 16609536, 'steps': 86507, 'loss/train': 1.4663792848587036} 08/31/2021 04:49:35 - INFO - __main__ - Step 86509: {'lr': 0.00019469797680243827, 'samples': 16609728, 'steps': 86508, 'loss/train': 0.912157416343689} 08/31/2021 04:49:35 - INFO - __main__ - Step 86510: {'lr': 0.00019469280153649218, 'samples': 16609920, 'steps': 86509, 'loss/train': 1.410749912261963} 08/31/2021 04:49:35 - INFO - __main__ - Step 86511: {'lr': 0.00019468762629546666, 'samples': 16610112, 'steps': 86510, 'loss/train': 1.1754332780838013} 08/31/2021 04:49:36 - INFO - __main__ - Step 86512: {'lr': 0.00019468245107936405, 'samples': 16610304, 'steps': 86511, 'loss/train': 1.2284282445907593} 08/31/2021 04:49:37 - INFO - __main__ - Step 86513: {'lr': 0.00019467727588818665, 'samples': 16610496, 'steps': 86512, 'loss/train': 0.03708498552441597} 08/31/2021 04:49:38 - INFO - __main__ - Step 86514: {'lr': 0.00019467210072193682, 'samples': 16610688, 'steps': 86513, 'loss/train': 0.8777913451194763} 08/31/2021 04:49:38 - INFO - __main__ - Step 86515: {'lr': 0.00019466692558061695, 'samples': 16610880, 'steps': 86514, 'loss/train': 1.404975414276123} 08/31/2021 04:49:39 - INFO - __main__ - Step 86516: {'lr': 0.00019466175046422922, 'samples': 16611072, 'steps': 86515, 'loss/train': 1.1851152181625366} 08/31/2021 04:49:39 - INFO - __main__ - Step 86517: {'lr': 0.00019465657537277614, 'samples': 16611264, 'steps': 86516, 'loss/train': 1.0584628582000732} 08/31/2021 04:49:39 - INFO - __main__ - Step 86518: {'lr': 0.00019465140030625993, 'samples': 16611456, 'steps': 86517, 'loss/train': 1.1206127405166626} 08/31/2021 04:49:41 - INFO - __main__ - Step 86519: {'lr': 0.00019464622526468292, 'samples': 16611648, 'steps': 86518, 'loss/train': 0.03441493958234787} 08/31/2021 04:49:42 - INFO - __main__ - Step 86520: {'lr': 0.00019464105024804746, 'samples': 16611840, 'steps': 86519, 'loss/train': 1.4595367908477783} 08/31/2021 04:49:42 - INFO - __main__ - Step 86521: {'lr': 0.00019463587525635589, 'samples': 16612032, 'steps': 86520, 'loss/train': 1.4937689304351807} 08/31/2021 04:49:42 - INFO - __main__ - Step 86522: {'lr': 0.00019463070028961061, 'samples': 16612224, 'steps': 86521, 'loss/train': 1.4583635330200195} 08/31/2021 04:49:43 - INFO - __main__ - Step 86523: {'lr': 0.0001946255253478138, 'samples': 16612416, 'steps': 86522, 'loss/train': 1.3266682624816895} 08/31/2021 04:49:44 - INFO - __main__ - Step 86524: {'lr': 0.0001946203504309679, 'samples': 16612608, 'steps': 86523, 'loss/train': 1.2893167734146118} 08/31/2021 04:49:45 - INFO - __main__ - Step 86525: {'lr': 0.0001946151755390752, 'samples': 16612800, 'steps': 86524, 'loss/train': 1.3676434755325317} 08/31/2021 04:49:45 - INFO - __main__ - Step 86526: {'lr': 0.00019461000067213808, 'samples': 16612992, 'steps': 86525, 'loss/train': 0.7034791707992554} 08/31/2021 04:49:45 - INFO - __main__ - Step 86527: {'lr': 0.0001946048258301588, 'samples': 16613184, 'steps': 86526, 'loss/train': 1.1104755401611328} 08/31/2021 04:49:46 - INFO - __main__ - Step 86528: {'lr': 0.00019459965101313982, 'samples': 16613376, 'steps': 86527, 'loss/train': 1.824181079864502} 08/31/2021 04:49:47 - INFO - __main__ - Step 86529: {'lr': 0.0001945944762210833, 'samples': 16613568, 'steps': 86528, 'loss/train': 1.0603463649749756} 08/31/2021 04:49:48 - INFO - __main__ - Step 86530: {'lr': 0.00019458930145399166, 'samples': 16613760, 'steps': 86529, 'loss/train': 1.174401879310608} 08/31/2021 04:49:48 - INFO - __main__ - Step 86531: {'lr': 0.00019458412671186721, 'samples': 16613952, 'steps': 86530, 'loss/train': 0.7192752957344055} 08/31/2021 04:49:48 - INFO - __main__ - Step 86532: {'lr': 0.00019457895199471233, 'samples': 16614144, 'steps': 86531, 'loss/train': 1.2384592294692993} 08/31/2021 04:49:49 - INFO - __main__ - Step 86533: {'lr': 0.00019457377730252928, 'samples': 16614336, 'steps': 86532, 'loss/train': 1.024206280708313} 08/31/2021 04:49:51 - INFO - __main__ - Step 86534: {'lr': 0.00019456860263532044, 'samples': 16614528, 'steps': 86533, 'loss/train': 1.5145180225372314} 08/31/2021 04:49:51 - INFO - __main__ - Step 86535: {'lr': 0.00019456342799308824, 'samples': 16614720, 'steps': 86534, 'loss/train': 1.3110933303833008} 08/31/2021 04:49:51 - INFO - __main__ - Step 86536: {'lr': 0.0001945582533758348, 'samples': 16614912, 'steps': 86535, 'loss/train': 1.0172250270843506} 08/31/2021 04:49:52 - INFO - __main__ - Step 86537: {'lr': 0.00019455307878356255, 'samples': 16615104, 'steps': 86536, 'loss/train': 1.2677364349365234} 08/31/2021 04:49:52 - INFO - __main__ - Step 86538: {'lr': 0.00019454790421627387, 'samples': 16615296, 'steps': 86537, 'loss/train': 0.01949344202876091} 08/31/2021 04:49:52 - INFO - __main__ - Step 86539: {'lr': 0.00019454272967397103, 'samples': 16615488, 'steps': 86538, 'loss/train': 1.6517419815063477} 08/31/2021 04:49:54 - INFO - __main__ - Step 86540: {'lr': 0.00019453755515665637, 'samples': 16615680, 'steps': 86539, 'loss/train': 1.339764952659607} 08/31/2021 04:49:55 - INFO - __main__ - Step 86541: {'lr': 0.00019453238066433228, 'samples': 16615872, 'steps': 86540, 'loss/train': 1.6186244487762451} 08/31/2021 04:49:55 - INFO - __main__ - Step 86542: {'lr': 0.000194527206197001, 'samples': 16616064, 'steps': 86541, 'loss/train': 0.4857548773288727} 08/31/2021 04:49:55 - INFO - __main__ - Step 86543: {'lr': 0.00019452203175466488, 'samples': 16616256, 'steps': 86542, 'loss/train': 1.2146624326705933} 08/31/2021 04:49:56 - INFO - __main__ - Step 86544: {'lr': 0.0001945168573373263, 'samples': 16616448, 'steps': 86543, 'loss/train': 1.1444166898727417} 08/31/2021 04:49:57 - INFO - __main__ - Step 86545: {'lr': 0.00019451168294498756, 'samples': 16616640, 'steps': 86544, 'loss/train': 0.03016815148293972} 08/31/2021 04:49:58 - INFO - __main__ - Step 86546: {'lr': 0.00019450650857765102, 'samples': 16616832, 'steps': 86545, 'loss/train': 1.744771122932434} 08/31/2021 04:49:58 - INFO - __main__ - Step 86547: {'lr': 0.00019450133423531897, 'samples': 16617024, 'steps': 86546, 'loss/train': 1.1761832237243652} 08/31/2021 04:49:58 - INFO - __main__ - Step 86548: {'lr': 0.00019449615991799375, 'samples': 16617216, 'steps': 86547, 'loss/train': 0.04163867607712746} 08/31/2021 04:49:59 - INFO - __main__ - Step 86549: {'lr': 0.0001944909856256778, 'samples': 16617408, 'steps': 86548, 'loss/train': 1.6476892232894897} 08/31/2021 04:50:00 - INFO - __main__ - Step 86550: {'lr': 0.00019448581135837333, 'samples': 16617600, 'steps': 86549, 'loss/train': 0.037678901106119156} 08/31/2021 04:50:01 - INFO - __main__ - Step 86551: {'lr': 0.00019448063711608262, 'samples': 16617792, 'steps': 86550, 'loss/train': 1.7309898138046265} 08/31/2021 04:50:01 - INFO - __main__ - Step 86552: {'lr': 0.0001944754628988081, 'samples': 16617984, 'steps': 86551, 'loss/train': 1.0985023975372314} 08/31/2021 04:50:01 - INFO - __main__ - Step 86553: {'lr': 0.0001944702887065521, 'samples': 16618176, 'steps': 86552, 'loss/train': 0.8191848993301392} 08/31/2021 04:50:02 - INFO - __main__ - Step 86554: {'lr': 0.0001944651145393169, 'samples': 16618368, 'steps': 86553, 'loss/train': 0.7885763049125671} 08/31/2021 04:50:03 - INFO - __main__ - Step 86555: {'lr': 0.00019445994039710488, 'samples': 16618560, 'steps': 86554, 'loss/train': 0.9230712652206421} 08/31/2021 04:50:04 - INFO - __main__ - Step 86556: {'lr': 0.00019445476627991834, 'samples': 16618752, 'steps': 86555, 'loss/train': 1.1537489891052246} 08/31/2021 04:50:04 - INFO - __main__ - Step 86557: {'lr': 0.00019444959218775965, 'samples': 16618944, 'steps': 86556, 'loss/train': 1.0571811199188232} 08/31/2021 04:50:04 - INFO - __main__ - Step 86558: {'lr': 0.0001944444181206311, 'samples': 16619136, 'steps': 86557, 'loss/train': 0.8808786869049072} 08/31/2021 04:50:05 - INFO - __main__ - Step 86559: {'lr': 0.00019443924407853503, 'samples': 16619328, 'steps': 86558, 'loss/train': 0.8374236822128296} 08/31/2021 04:50:05 - INFO - __main__ - Step 86560: {'lr': 0.0001944340700614738, 'samples': 16619520, 'steps': 86559, 'loss/train': 0.42836838960647583} 08/31/2021 04:50:06 - INFO - __main__ - Step 86561: {'lr': 0.0001944288960694497, 'samples': 16619712, 'steps': 86560, 'loss/train': 0.6316639184951782} 08/31/2021 04:50:07 - INFO - __main__ - Step 86562: {'lr': 0.0001944237221024652, 'samples': 16619904, 'steps': 86561, 'loss/train': 0.9386820197105408} 08/31/2021 04:50:07 - INFO - __main__ - Step 86563: {'lr': 0.0001944185481605224, 'samples': 16620096, 'steps': 86562, 'loss/train': 0.1315075010061264} 08/31/2021 04:50:08 - INFO - __main__ - Step 86564: {'lr': 0.00019441337424362377, 'samples': 16620288, 'steps': 86563, 'loss/train': 1.2496628761291504} 08/31/2021 04:50:08 - INFO - __main__ - Step 86565: {'lr': 0.0001944082003517716, 'samples': 16620480, 'steps': 86564, 'loss/train': 0.9408508539199829} 08/31/2021 04:50:10 - INFO - __main__ - Step 86566: {'lr': 0.00019440302648496822, 'samples': 16620672, 'steps': 86565, 'loss/train': 1.5318937301635742} 08/31/2021 04:50:10 - INFO - __main__ - Step 86567: {'lr': 0.00019439785264321598, 'samples': 16620864, 'steps': 86566, 'loss/train': 0.6687679886817932} 08/31/2021 04:50:10 - INFO - __main__ - Step 86568: {'lr': 0.00019439267882651723, 'samples': 16621056, 'steps': 86567, 'loss/train': 1.8087671995162964} 08/31/2021 04:50:11 - INFO - __main__ - Step 86569: {'lr': 0.00019438750503487427, 'samples': 16621248, 'steps': 86568, 'loss/train': 1.3956495523452759} 08/31/2021 04:50:11 - INFO - __main__ - Step 86570: {'lr': 0.0001943823312682894, 'samples': 16621440, 'steps': 86569, 'loss/train': 1.4869353771209717} 08/31/2021 04:50:13 - INFO - __main__ - Step 86571: {'lr': 0.00019437715752676504, 'samples': 16621632, 'steps': 86570, 'loss/train': 1.8905155658721924} 08/31/2021 04:50:13 - INFO - __main__ - Step 86572: {'lr': 0.0001943719838103035, 'samples': 16621824, 'steps': 86571, 'loss/train': 1.1960546970367432} 08/31/2021 04:50:13 - INFO - __main__ - Step 86573: {'lr': 0.00019436681011890706, 'samples': 16622016, 'steps': 86572, 'loss/train': 0.8277456164360046} 08/31/2021 04:50:14 - INFO - __main__ - Step 86574: {'lr': 0.00019436163645257808, 'samples': 16622208, 'steps': 86573, 'loss/train': 1.0117367506027222} 08/31/2021 04:50:14 - INFO - __main__ - Step 86575: {'lr': 0.00019435646281131886, 'samples': 16622400, 'steps': 86574, 'loss/train': 1.5956907272338867} 08/31/2021 04:50:16 - INFO - __main__ - Step 86576: {'lr': 0.0001943512891951319, 'samples': 16622592, 'steps': 86575, 'loss/train': 1.1922886371612549} 08/31/2021 04:50:17 - INFO - __main__ - Step 86577: {'lr': 0.00019434611560401928, 'samples': 16622784, 'steps': 86576, 'loss/train': 1.520137906074524} 08/31/2021 04:50:17 - INFO - __main__ - Step 86578: {'lr': 0.0001943409420379834, 'samples': 16622976, 'steps': 86577, 'loss/train': 1.2017576694488525} 08/31/2021 04:50:17 - INFO - __main__ - Step 86579: {'lr': 0.00019433576849702666, 'samples': 16623168, 'steps': 86578, 'loss/train': 0.30124741792678833} 08/31/2021 04:50:18 - INFO - __main__ - Step 86580: {'lr': 0.0001943305949811514, 'samples': 16623360, 'steps': 86579, 'loss/train': 1.2295969724655151} 08/31/2021 04:50:18 - INFO - __main__ - Step 86581: {'lr': 0.00019432542149035986, 'samples': 16623552, 'steps': 86580, 'loss/train': 1.0358062982559204} 08/31/2021 04:50:20 - INFO - __main__ - Step 86582: {'lr': 0.00019432024802465444, 'samples': 16623744, 'steps': 86581, 'loss/train': 0.18468227982521057} 08/31/2021 04:50:20 - INFO - __main__ - Step 86583: {'lr': 0.00019431507458403749, 'samples': 16623936, 'steps': 86582, 'loss/train': 1.5286099910736084} 08/31/2021 04:50:20 - INFO - __main__ - Step 86584: {'lr': 0.00019430990116851127, 'samples': 16624128, 'steps': 86583, 'loss/train': 1.2165378332138062} 08/31/2021 04:50:21 - INFO - __main__ - Step 86585: {'lr': 0.00019430472777807816, 'samples': 16624320, 'steps': 86584, 'loss/train': 1.447737693786621} 08/31/2021 04:50:21 - INFO - __main__ - Step 86586: {'lr': 0.0001942995544127405, 'samples': 16624512, 'steps': 86585, 'loss/train': 0.8908039927482605} 08/31/2021 04:50:22 - INFO - __main__ - Step 86587: {'lr': 0.0001942943810725006, 'samples': 16624704, 'steps': 86586, 'loss/train': 0.906074047088623} 08/31/2021 04:50:23 - INFO - __main__ - Step 86588: {'lr': 0.00019428920775736076, 'samples': 16624896, 'steps': 86587, 'loss/train': 0.27902480959892273} 08/31/2021 04:50:23 - INFO - __main__ - Step 86589: {'lr': 0.00019428403446732344, 'samples': 16625088, 'steps': 86588, 'loss/train': 0.6669439673423767} 08/31/2021 04:50:24 - INFO - __main__ - Step 86590: {'lr': 0.00019427886120239083, 'samples': 16625280, 'steps': 86589, 'loss/train': 1.313517451286316} 08/31/2021 04:50:24 - INFO - __main__ - Step 86591: {'lr': 0.00019427368796256527, 'samples': 16625472, 'steps': 86590, 'loss/train': 1.7040117979049683} 08/31/2021 04:50:26 - INFO - __main__ - Step 86592: {'lr': 0.00019426851474784913, 'samples': 16625664, 'steps': 86591, 'loss/train': 1.6859982013702393} 08/31/2021 04:50:26 - INFO - __main__ - Step 86593: {'lr': 0.0001942633415582447, 'samples': 16625856, 'steps': 86592, 'loss/train': 1.1160348653793335} 08/31/2021 04:50:26 - INFO - __main__ - Step 86594: {'lr': 0.0001942581683937544, 'samples': 16626048, 'steps': 86593, 'loss/train': 1.637442708015442} 08/31/2021 04:50:27 - INFO - __main__ - Step 86595: {'lr': 0.0001942529952543805, 'samples': 16626240, 'steps': 86594, 'loss/train': 1.165555715560913} 08/31/2021 04:50:27 - INFO - __main__ - Step 86596: {'lr': 0.00019424782214012533, 'samples': 16626432, 'steps': 86595, 'loss/train': 3.821700096130371} 08/31/2021 04:50:27 - INFO - __main__ - Step 86597: {'lr': 0.00019424264905099124, 'samples': 16626624, 'steps': 86596, 'loss/train': 1.6141902208328247} 08/31/2021 04:50:29 - INFO - __main__ - Step 86598: {'lr': 0.00019423747598698053, 'samples': 16626816, 'steps': 86597, 'loss/train': 0.43385064601898193} 08/31/2021 04:50:29 - INFO - __main__ - Step 86599: {'lr': 0.00019423230294809558, 'samples': 16627008, 'steps': 86598, 'loss/train': 0.7800701260566711} 08/31/2021 04:50:30 - INFO - __main__ - Step 86600: {'lr': 0.00019422712993433867, 'samples': 16627200, 'steps': 86599, 'loss/train': 1.1031895875930786} 08/31/2021 04:50:30 - INFO - __main__ - Step 86601: {'lr': 0.00019422195694571216, 'samples': 16627392, 'steps': 86600, 'loss/train': 1.2596911191940308} 08/31/2021 04:50:30 - INFO - __main__ - Step 86602: {'lr': 0.00019421678398221838, 'samples': 16627584, 'steps': 86601, 'loss/train': 1.128416657447815} 08/31/2021 04:50:32 - INFO - __main__ - Step 86603: {'lr': 0.00019421161104385976, 'samples': 16627776, 'steps': 86602, 'loss/train': 1.1817823648452759} 08/31/2021 04:50:32 - INFO - __main__ - Step 86604: {'lr': 0.00019420643813063842, 'samples': 16627968, 'steps': 86603, 'loss/train': 1.5096567869186401} 08/31/2021 04:50:33 - INFO - __main__ - Step 86605: {'lr': 0.00019420126524255683, 'samples': 16628160, 'steps': 86604, 'loss/train': 0.5361066460609436} 08/31/2021 04:50:33 - INFO - __main__ - Step 86606: {'lr': 0.00019419609237961724, 'samples': 16628352, 'steps': 86605, 'loss/train': 1.752293586730957} 08/31/2021 04:50:33 - INFO - __main__ - Step 86607: {'lr': 0.00019419091954182206, 'samples': 16628544, 'steps': 86606, 'loss/train': 0.9600533843040466} 08/31/2021 04:50:35 - INFO - __main__ - Step 86608: {'lr': 0.00019418574672917357, 'samples': 16628736, 'steps': 86607, 'loss/train': 0.9386041760444641} 08/31/2021 04:50:35 - INFO - __main__ - Step 86609: {'lr': 0.00019418057394167415, 'samples': 16628928, 'steps': 86608, 'loss/train': 1.4773707389831543} 08/31/2021 04:50:36 - INFO - __main__ - Step 86610: {'lr': 0.00019417540117932608, 'samples': 16629120, 'steps': 86609, 'loss/train': 1.1219919919967651} 08/31/2021 04:50:36 - INFO - __main__ - Step 86611: {'lr': 0.0001941702284421317, 'samples': 16629312, 'steps': 86610, 'loss/train': 0.9517839550971985} 08/31/2021 04:50:36 - INFO - __main__ - Step 86612: {'lr': 0.0001941650557300934, 'samples': 16629504, 'steps': 86611, 'loss/train': 0.763411819934845} 08/31/2021 04:50:38 - INFO - __main__ - Step 86613: {'lr': 0.0001941598830432134, 'samples': 16629696, 'steps': 86612, 'loss/train': 1.0588246583938599} 08/31/2021 04:50:39 - INFO - __main__ - Step 86614: {'lr': 0.00019415471038149415, 'samples': 16629888, 'steps': 86613, 'loss/train': 0.6224884986877441} 08/31/2021 04:50:39 - INFO - __main__ - Step 86615: {'lr': 0.0001941495377449379, 'samples': 16630080, 'steps': 86614, 'loss/train': 1.4002351760864258} 08/31/2021 04:50:39 - INFO - __main__ - Step 86616: {'lr': 0.00019414436513354714, 'samples': 16630272, 'steps': 86615, 'loss/train': 0.6461011171340942} 08/31/2021 04:50:40 - INFO - __main__ - Step 86617: {'lr': 0.00019413919254732392, 'samples': 16630464, 'steps': 86616, 'loss/train': 0.10201554000377655} 08/31/2021 04:50:41 - INFO - __main__ - Step 86618: {'lr': 0.00019413401998627074, 'samples': 16630656, 'steps': 86617, 'loss/train': 1.1348904371261597} 08/31/2021 04:50:42 - INFO - __main__ - Step 86619: {'lr': 0.00019412884745038993, 'samples': 16630848, 'steps': 86618, 'loss/train': 0.8535502552986145} 08/31/2021 04:50:42 - INFO - __main__ - Step 86620: {'lr': 0.00019412367493968374, 'samples': 16631040, 'steps': 86619, 'loss/train': 1.3646000623703003} 08/31/2021 04:50:42 - INFO - __main__ - Step 86621: {'lr': 0.0001941185024541546, 'samples': 16631232, 'steps': 86620, 'loss/train': 1.470400094985962} 08/31/2021 04:50:43 - INFO - __main__ - Step 86622: {'lr': 0.00019411332999380481, 'samples': 16631424, 'steps': 86621, 'loss/train': 1.3431713581085205} 08/31/2021 04:50:45 - INFO - __main__ - Step 86623: {'lr': 0.00019410815755863668, 'samples': 16631616, 'steps': 86622, 'loss/train': 1.6533702611923218} 08/31/2021 04:50:45 - INFO - __main__ - Step 86624: {'lr': 0.00019410298514865255, 'samples': 16631808, 'steps': 86623, 'loss/train': 1.260469675064087} 08/31/2021 04:50:45 - INFO - __main__ - Step 86625: {'lr': 0.00019409781276385474, 'samples': 16632000, 'steps': 86624, 'loss/train': 1.0624580383300781} 08/31/2021 04:50:46 - INFO - __main__ - Step 86626: {'lr': 0.00019409264040424562, 'samples': 16632192, 'steps': 86625, 'loss/train': 0.7625706791877747} 08/31/2021 04:50:46 - INFO - __main__ - Step 86627: {'lr': 0.00019408746806982746, 'samples': 16632384, 'steps': 86626, 'loss/train': 1.4212692975997925} 08/31/2021 04:50:46 - INFO - __main__ - Step 86628: {'lr': 0.00019408229576060266, 'samples': 16632576, 'steps': 86627, 'loss/train': 1.588189721107483} 08/31/2021 04:50:48 - INFO - __main__ - Step 86629: {'lr': 0.00019407712347657347, 'samples': 16632768, 'steps': 86628, 'loss/train': 1.2683926820755005} 08/31/2021 04:50:48 - INFO - __main__ - Step 86630: {'lr': 0.0001940719512177424, 'samples': 16632960, 'steps': 86629, 'loss/train': 2.074483633041382} 08/31/2021 04:50:49 - INFO - __main__ - Step 86631: {'lr': 0.00019406677898411154, 'samples': 16633152, 'steps': 86630, 'loss/train': 1.406792163848877} 08/31/2021 04:50:49 - INFO - __main__ - Step 86632: {'lr': 0.0001940616067756833, 'samples': 16633344, 'steps': 86631, 'loss/train': 2.3096048831939697} 08/31/2021 04:50:49 - INFO - __main__ - Step 86633: {'lr': 0.0001940564345924601, 'samples': 16633536, 'steps': 86632, 'loss/train': 1.3757673501968384} 08/31/2021 04:50:51 - INFO - __main__ - Step 86634: {'lr': 0.00019405126243444415, 'samples': 16633728, 'steps': 86633, 'loss/train': 0.5943538546562195} 08/31/2021 04:50:51 - INFO - __main__ - Step 86635: {'lr': 0.00019404609030163785, 'samples': 16633920, 'steps': 86634, 'loss/train': 0.8672186732292175} 08/31/2021 04:50:52 - INFO - __main__ - Step 86636: {'lr': 0.00019404091819404354, 'samples': 16634112, 'steps': 86635, 'loss/train': 1.3014402389526367} 08/31/2021 04:50:52 - INFO - __main__ - Step 86637: {'lr': 0.00019403574611166354, 'samples': 16634304, 'steps': 86636, 'loss/train': 1.312309980392456} 08/31/2021 04:50:53 - INFO - __main__ - Step 86638: {'lr': 0.00019403057405450013, 'samples': 16634496, 'steps': 86637, 'loss/train': 0.9475820660591125} 08/31/2021 04:50:54 - INFO - __main__ - Step 86639: {'lr': 0.00019402540202255567, 'samples': 16634688, 'steps': 86638, 'loss/train': 0.35185015201568604} 08/31/2021 04:50:55 - INFO - __main__ - Step 86640: {'lr': 0.00019402023001583251, 'samples': 16634880, 'steps': 86639, 'loss/train': 1.4336988925933838} 08/31/2021 04:50:55 - INFO - __main__ - Step 86641: {'lr': 0.00019401505803433305, 'samples': 16635072, 'steps': 86640, 'loss/train': 1.2341015338897705} 08/31/2021 04:50:56 - INFO - __main__ - Step 86642: {'lr': 0.00019400988607805948, 'samples': 16635264, 'steps': 86641, 'loss/train': 1.3282060623168945} 08/31/2021 04:50:56 - INFO - __main__ - Step 86643: {'lr': 0.00019400471414701424, 'samples': 16635456, 'steps': 86642, 'loss/train': 1.8365641832351685} 08/31/2021 04:50:57 - INFO - __main__ - Step 86644: {'lr': 0.00019399954224119957, 'samples': 16635648, 'steps': 86643, 'loss/train': 1.929198145866394} 08/31/2021 04:50:58 - INFO - __main__ - Step 86645: {'lr': 0.0001939943703606178, 'samples': 16635840, 'steps': 86644, 'loss/train': 1.1325536966323853} 08/31/2021 04:50:58 - INFO - __main__ - Step 86646: {'lr': 0.00019398919850527132, 'samples': 16636032, 'steps': 86645, 'loss/train': 1.3540432453155518} 08/31/2021 04:50:59 - INFO - __main__ - Step 86647: {'lr': 0.00019398402667516245, 'samples': 16636224, 'steps': 86646, 'loss/train': 1.2027896642684937} 08/31/2021 04:50:59 - INFO - __main__ - Step 86648: {'lr': 0.00019397885487029354, 'samples': 16636416, 'steps': 86647, 'loss/train': 1.6870293617248535} 08/31/2021 04:51:01 - INFO - __main__ - Step 86649: {'lr': 0.00019397368309066688, 'samples': 16636608, 'steps': 86648, 'loss/train': 1.6168190240859985} 08/31/2021 04:51:02 - INFO - __main__ - Step 86650: {'lr': 0.0001939685113362848, 'samples': 16636800, 'steps': 86649, 'loss/train': 1.3493223190307617} 08/31/2021 04:51:02 - INFO - __main__ - Step 86651: {'lr': 0.00019396333960714965, 'samples': 16636992, 'steps': 86650, 'loss/train': 1.2277127504348755} 08/31/2021 04:51:02 - INFO - __main__ - Step 86652: {'lr': 0.00019395816790326382, 'samples': 16637184, 'steps': 86651, 'loss/train': 1.2314989566802979} 08/31/2021 04:51:03 - INFO - __main__ - Step 86653: {'lr': 0.00019395299622462949, 'samples': 16637376, 'steps': 86652, 'loss/train': 1.331282138824463} 08/31/2021 04:51:03 - INFO - __main__ - Step 86654: {'lr': 0.0001939478245712491, 'samples': 16637568, 'steps': 86653, 'loss/train': 1.2690454721450806} 08/31/2021 04:51:03 - INFO - __main__ - Step 86655: {'lr': 0.00019394265294312495, 'samples': 16637760, 'steps': 86654, 'loss/train': 2.04845929145813} 08/31/2021 04:51:05 - INFO - __main__ - Step 86656: {'lr': 0.0001939374813402594, 'samples': 16637952, 'steps': 86655, 'loss/train': 2.1746292114257812} 08/31/2021 04:51:05 - INFO - __main__ - Step 86657: {'lr': 0.00019393230976265475, 'samples': 16638144, 'steps': 86656, 'loss/train': 1.376954436302185} 08/31/2021 04:51:06 - INFO - __main__ - Step 86658: {'lr': 0.00019392713821031333, 'samples': 16638336, 'steps': 86657, 'loss/train': 0.04186885058879852} 08/31/2021 04:51:06 - INFO - __main__ - Step 86659: {'lr': 0.00019392196668323745, 'samples': 16638528, 'steps': 86658, 'loss/train': 0.6927186846733093} 08/31/2021 04:51:06 - INFO - __main__ - Step 86660: {'lr': 0.00019391679518142947, 'samples': 16638720, 'steps': 86659, 'loss/train': 0.9528427720069885} 08/31/2021 04:51:08 - INFO - __main__ - Step 86661: {'lr': 0.00019391162370489175, 'samples': 16638912, 'steps': 86660, 'loss/train': 1.3172959089279175} 08/31/2021 04:51:08 - INFO - __main__ - Step 86662: {'lr': 0.00019390645225362657, 'samples': 16639104, 'steps': 86661, 'loss/train': 1.1794047355651855} 08/31/2021 04:51:09 - INFO - __main__ - Step 86663: {'lr': 0.00019390128082763628, 'samples': 16639296, 'steps': 86662, 'loss/train': 1.3643192052841187} 08/31/2021 04:51:09 - INFO - __main__ - Step 86664: {'lr': 0.0001938961094269232, 'samples': 16639488, 'steps': 86663, 'loss/train': 1.5287657976150513} 08/31/2021 04:51:09 - INFO - __main__ - Step 86665: {'lr': 0.00019389093805148965, 'samples': 16639680, 'steps': 86664, 'loss/train': 1.8350204229354858} 08/31/2021 04:51:11 - INFO - __main__ - Step 86666: {'lr': 0.000193885766701338, 'samples': 16639872, 'steps': 86665, 'loss/train': 1.1706784963607788} 08/31/2021 04:51:11 - INFO - __main__ - Step 86667: {'lr': 0.00019388059537647057, 'samples': 16640064, 'steps': 86666, 'loss/train': 1.3705211877822876} 08/31/2021 04:51:12 - INFO - __main__ - Step 86668: {'lr': 0.00019387542407688964, 'samples': 16640256, 'steps': 86667, 'loss/train': 0.7708420753479004} 08/31/2021 04:51:12 - INFO - __main__ - Step 86669: {'lr': 0.0001938702528025976, 'samples': 16640448, 'steps': 86668, 'loss/train': 1.2308801412582397} 08/31/2021 04:51:13 - INFO - __main__ - Step 86670: {'lr': 0.00019386508155359682, 'samples': 16640640, 'steps': 86669, 'loss/train': 1.314949631690979} 08/31/2021 04:51:13 - INFO - __main__ - Step 86671: {'lr': 0.0001938599103298895, 'samples': 16640832, 'steps': 86670, 'loss/train': 1.787473440170288} 08/31/2021 04:51:15 - INFO - __main__ - Step 86672: {'lr': 0.00019385473913147803, 'samples': 16641024, 'steps': 86671, 'loss/train': 0.6457524299621582} 08/31/2021 04:51:15 - INFO - __main__ - Step 86673: {'lr': 0.0001938495679583648, 'samples': 16641216, 'steps': 86672, 'loss/train': 1.0588700771331787} 08/31/2021 04:51:16 - INFO - __main__ - Step 86674: {'lr': 0.00019384439681055204, 'samples': 16641408, 'steps': 86673, 'loss/train': 0.8586721420288086} 08/31/2021 04:51:16 - INFO - __main__ - Step 86675: {'lr': 0.00019383922568804213, 'samples': 16641600, 'steps': 86674, 'loss/train': 0.8314334154129028} 08/31/2021 04:51:16 - INFO - __main__ - Step 86676: {'lr': 0.00019383405459083743, 'samples': 16641792, 'steps': 86675, 'loss/train': 0.05161738023161888} 08/31/2021 04:51:18 - INFO - __main__ - Step 86677: {'lr': 0.00019382888351894017, 'samples': 16641984, 'steps': 86676, 'loss/train': 1.4732614755630493} 08/31/2021 04:51:18 - INFO - __main__ - Step 86678: {'lr': 0.00019382371247235282, 'samples': 16642176, 'steps': 86677, 'loss/train': 1.2458525896072388} 08/31/2021 04:51:19 - INFO - __main__ - Step 86679: {'lr': 0.00019381854145107758, 'samples': 16642368, 'steps': 86678, 'loss/train': 0.24853301048278809} 08/31/2021 04:51:19 - INFO - __main__ - Step 86680: {'lr': 0.00019381337045511687, 'samples': 16642560, 'steps': 86679, 'loss/train': 1.190008282661438} 08/31/2021 04:51:20 - INFO - __main__ - Step 86681: {'lr': 0.00019380819948447298, 'samples': 16642752, 'steps': 86680, 'loss/train': 1.5272613763809204} 08/31/2021 04:51:21 - INFO - __main__ - Step 86682: {'lr': 0.00019380302853914827, 'samples': 16642944, 'steps': 86681, 'loss/train': 1.114903450012207} 08/31/2021 04:51:22 - INFO - __main__ - Step 86683: {'lr': 0.00019379785761914505, 'samples': 16643136, 'steps': 86682, 'loss/train': 1.681018352508545} 08/31/2021 04:51:22 - INFO - __main__ - Step 86684: {'lr': 0.0001937926867244657, 'samples': 16643328, 'steps': 86683, 'loss/train': 0.6286449432373047} 08/31/2021 04:51:23 - INFO - __main__ - Step 86685: {'lr': 0.00019378751585511243, 'samples': 16643520, 'steps': 86684, 'loss/train': 0.15889573097229004} 08/31/2021 04:51:23 - INFO - __main__ - Step 86686: {'lr': 0.00019378234501108763, 'samples': 16643712, 'steps': 86685, 'loss/train': 1.1239314079284668} 08/31/2021 04:51:25 - INFO - __main__ - Step 86687: {'lr': 0.00019377717419239365, 'samples': 16643904, 'steps': 86686, 'loss/train': 1.3776862621307373} 08/31/2021 04:51:25 - INFO - __main__ - Step 86688: {'lr': 0.00019377200339903278, 'samples': 16644096, 'steps': 86687, 'loss/train': 0.86391282081604} 08/31/2021 04:51:26 - INFO - __main__ - Step 86689: {'lr': 0.0001937668326310074, 'samples': 16644288, 'steps': 86688, 'loss/train': 0.018619511276483536} 08/31/2021 04:51:26 - INFO - __main__ - Step 86690: {'lr': 0.00019376166188831982, 'samples': 16644480, 'steps': 86689, 'loss/train': 1.162625789642334} 08/31/2021 04:51:26 - INFO - __main__ - Step 86691: {'lr': 0.00019375649117097236, 'samples': 16644672, 'steps': 86690, 'loss/train': 0.38047221302986145} 08/31/2021 04:51:27 - INFO - __main__ - Step 86692: {'lr': 0.00019375132047896735, 'samples': 16644864, 'steps': 86691, 'loss/train': 1.5448685884475708} 08/31/2021 04:51:27 - INFO - __main__ - Step 86693: {'lr': 0.00019374614981230716, 'samples': 16645056, 'steps': 86692, 'loss/train': 0.07609371840953827} 08/31/2021 04:51:28 - INFO - __main__ - Step 86694: {'lr': 0.00019374097917099404, 'samples': 16645248, 'steps': 86693, 'loss/train': 0.9487885236740112} 08/31/2021 04:51:29 - INFO - __main__ - Step 86695: {'lr': 0.00019373580855503038, 'samples': 16645440, 'steps': 86694, 'loss/train': 0.9734379053115845} 08/31/2021 04:51:29 - INFO - __main__ - Step 86696: {'lr': 0.00019373063796441852, 'samples': 16645632, 'steps': 86695, 'loss/train': 1.8702436685562134} 08/31/2021 04:51:30 - INFO - __main__ - Step 86697: {'lr': 0.00019372546739916086, 'samples': 16645824, 'steps': 86696, 'loss/train': 1.3838027715682983} 08/31/2021 04:51:30 - INFO - __main__ - Step 86698: {'lr': 0.00019372029685925951, 'samples': 16646016, 'steps': 86697, 'loss/train': 1.442886233329773} 08/31/2021 04:51:31 - INFO - __main__ - Step 86699: {'lr': 0.00019371512634471695, 'samples': 16646208, 'steps': 86698, 'loss/train': 1.1996923685073853} 08/31/2021 04:51:32 - INFO - __main__ - Step 86700: {'lr': 0.00019370995585553548, 'samples': 16646400, 'steps': 86699, 'loss/train': 0.5917452573776245} 08/31/2021 04:51:32 - INFO - __main__ - Step 86701: {'lr': 0.00019370478539171743, 'samples': 16646592, 'steps': 86700, 'loss/train': 1.0675013065338135} 08/31/2021 04:51:33 - INFO - __main__ - Step 86702: {'lr': 0.00019369961495326515, 'samples': 16646784, 'steps': 86701, 'loss/train': 0.7094294428825378} 08/31/2021 04:51:33 - INFO - __main__ - Step 86703: {'lr': 0.00019369444454018096, 'samples': 16646976, 'steps': 86702, 'loss/train': 0.49932557344436646} 08/31/2021 04:51:34 - INFO - __main__ - Step 86704: {'lr': 0.00019368927415246715, 'samples': 16647168, 'steps': 86703, 'loss/train': 0.43043145537376404} 08/31/2021 04:51:35 - INFO - __main__ - Step 86705: {'lr': 0.0001936841037901261, 'samples': 16647360, 'steps': 86704, 'loss/train': 1.667035460472107} 08/31/2021 04:51:35 - INFO - __main__ - Step 86706: {'lr': 0.00019367893345316012, 'samples': 16647552, 'steps': 86705, 'loss/train': 0.2970310151576996} 08/31/2021 04:51:36 - INFO - __main__ - Step 86707: {'lr': 0.00019367376314157156, 'samples': 16647744, 'steps': 86706, 'loss/train': 1.2818683385849} 08/31/2021 04:51:36 - INFO - __main__ - Step 86708: {'lr': 0.00019366859285536273, 'samples': 16647936, 'steps': 86707, 'loss/train': 1.7633265256881714} 08/31/2021 04:51:37 - INFO - __main__ - Step 86709: {'lr': 0.00019366342259453595, 'samples': 16648128, 'steps': 86708, 'loss/train': 1.5192601680755615} 08/31/2021 04:51:38 - INFO - __main__ - Step 86710: {'lr': 0.00019365825235909367, 'samples': 16648320, 'steps': 86709, 'loss/train': 1.6708381175994873} 08/31/2021 04:51:38 - INFO - __main__ - Step 86711: {'lr': 0.00019365308214903802, 'samples': 16648512, 'steps': 86710, 'loss/train': 1.0350360870361328} 08/31/2021 04:51:39 - INFO - __main__ - Step 86712: {'lr': 0.0001936479119643714, 'samples': 16648704, 'steps': 86711, 'loss/train': 0.834457278251648} 08/31/2021 04:51:39 - INFO - __main__ - Step 86713: {'lr': 0.00019364274180509616, 'samples': 16648896, 'steps': 86712, 'loss/train': 0.6474347710609436} 08/31/2021 04:51:40 - INFO - __main__ - Step 86714: {'lr': 0.00019363757167121466, 'samples': 16649088, 'steps': 86713, 'loss/train': 1.0858657360076904} 08/31/2021 04:51:41 - INFO - __main__ - Step 86715: {'lr': 0.00019363240156272917, 'samples': 16649280, 'steps': 86714, 'loss/train': 1.5588823556900024} 08/31/2021 04:51:41 - INFO - __main__ - Step 86716: {'lr': 0.0001936272314796421, 'samples': 16649472, 'steps': 86715, 'loss/train': 0.8166685104370117} 08/31/2021 04:51:42 - INFO - __main__ - Step 86717: {'lr': 0.0001936220614219557, 'samples': 16649664, 'steps': 86716, 'loss/train': 0.5952292680740356} 08/31/2021 04:51:42 - INFO - __main__ - Step 86718: {'lr': 0.0001936168913896723, 'samples': 16649856, 'steps': 86717, 'loss/train': 0.9591256380081177} 08/31/2021 04:51:42 - INFO - __main__ - Step 86719: {'lr': 0.0001936117213827943, 'samples': 16650048, 'steps': 86718, 'loss/train': 1.7147223949432373} 08/31/2021 04:51:44 - INFO - __main__ - Step 86720: {'lr': 0.00019360655140132394, 'samples': 16650240, 'steps': 86719, 'loss/train': 1.0912178754806519} 08/31/2021 04:51:44 - INFO - __main__ - Step 86721: {'lr': 0.00019360138144526362, 'samples': 16650432, 'steps': 86720, 'loss/train': 2.1420578956604004} 08/31/2021 04:51:45 - INFO - __main__ - Step 86722: {'lr': 0.00019359621151461567, 'samples': 16650624, 'steps': 86721, 'loss/train': 1.1818132400512695} 08/31/2021 04:51:45 - INFO - __main__ - Step 86723: {'lr': 0.0001935910416093824, 'samples': 16650816, 'steps': 86722, 'loss/train': 1.5900946855545044} 08/31/2021 04:51:45 - INFO - __main__ - Step 86724: {'lr': 0.00019358587172956621, 'samples': 16651008, 'steps': 86723, 'loss/train': 1.5216388702392578} 08/31/2021 04:51:48 - INFO - __main__ - Step 86725: {'lr': 0.00019358070187516926, 'samples': 16651200, 'steps': 86724, 'loss/train': 1.2520402669906616} 08/31/2021 04:51:48 - INFO - __main__ - Step 86726: {'lr': 0.000193575532046194, 'samples': 16651392, 'steps': 86725, 'loss/train': 1.403374433517456} 08/31/2021 04:51:48 - INFO - __main__ - Step 86727: {'lr': 0.00019357036224264268, 'samples': 16651584, 'steps': 86726, 'loss/train': 1.6245250701904297} 08/31/2021 04:51:49 - INFO - __main__ - Step 86728: {'lr': 0.00019356519246451772, 'samples': 16651776, 'steps': 86727, 'loss/train': 1.4801355600357056} 08/31/2021 04:51:49 - INFO - __main__ - Step 86729: {'lr': 0.00019356002271182145, 'samples': 16651968, 'steps': 86728, 'loss/train': 0.020115625113248825} 08/31/2021 04:51:49 - INFO - __main__ - Step 86730: {'lr': 0.0001935548529845561, 'samples': 16652160, 'steps': 86729, 'loss/train': 0.017938684672117233} 08/31/2021 04:51:50 - INFO - __main__ - Step 86731: {'lr': 0.0001935496832827241, 'samples': 16652352, 'steps': 86730, 'loss/train': 0.7880355715751648} 08/31/2021 04:51:52 - INFO - __main__ - Step 86732: {'lr': 0.00019354451360632772, 'samples': 16652544, 'steps': 86731, 'loss/train': 1.2769829034805298} 08/31/2021 04:51:52 - INFO - __main__ - Step 86733: {'lr': 0.00019353934395536932, 'samples': 16652736, 'steps': 86732, 'loss/train': 0.9384817481040955} 08/31/2021 04:51:53 - INFO - __main__ - Step 86734: {'lr': 0.0001935341743298512, 'samples': 16652928, 'steps': 86733, 'loss/train': 1.1748557090759277} 08/31/2021 04:51:53 - INFO - __main__ - Step 86735: {'lr': 0.00019352900472977574, 'samples': 16653120, 'steps': 86734, 'loss/train': 1.1312648057937622} 08/31/2021 04:51:53 - INFO - __main__ - Step 86736: {'lr': 0.00019352383515514523, 'samples': 16653312, 'steps': 86735, 'loss/train': 1.190089225769043} 08/31/2021 04:51:55 - INFO - __main__ - Step 86737: {'lr': 0.00019351866560596214, 'samples': 16653504, 'steps': 86736, 'loss/train': 1.3273534774780273} 08/31/2021 04:51:55 - INFO - __main__ - Step 86738: {'lr': 0.00019351349608222852, 'samples': 16653696, 'steps': 86737, 'loss/train': 1.3930244445800781} 08/31/2021 04:51:56 - INFO - __main__ - Step 86739: {'lr': 0.00019350832658394685, 'samples': 16653888, 'steps': 86738, 'loss/train': 1.2930951118469238} 08/31/2021 04:51:56 - INFO - __main__ - Step 86740: {'lr': 0.00019350315711111945, 'samples': 16654080, 'steps': 86739, 'loss/train': 1.249154806137085} 08/31/2021 04:51:56 - INFO - __main__ - Step 86741: {'lr': 0.00019349798766374869, 'samples': 16654272, 'steps': 86740, 'loss/train': 1.4422882795333862} 08/31/2021 04:51:58 - INFO - __main__ - Step 86742: {'lr': 0.00019349281824183683, 'samples': 16654464, 'steps': 86741, 'loss/train': 1.3494553565979004} 08/31/2021 04:51:58 - INFO - __main__ - Step 86743: {'lr': 0.00019348764884538627, 'samples': 16654656, 'steps': 86742, 'loss/train': 1.38868248462677} 08/31/2021 04:51:58 - INFO - __main__ - Step 86744: {'lr': 0.0001934824794743993, 'samples': 16654848, 'steps': 86743, 'loss/train': 1.9961297512054443} 08/31/2021 04:51:59 - INFO - __main__ - Step 86745: {'lr': 0.00019347731012887823, 'samples': 16655040, 'steps': 86744, 'loss/train': 1.1521049737930298} 08/31/2021 04:51:59 - INFO - __main__ - Step 86746: {'lr': 0.0001934721408088254, 'samples': 16655232, 'steps': 86745, 'loss/train': 1.997460961341858} 08/31/2021 04:52:01 - INFO - __main__ - Step 86747: {'lr': 0.0001934669715142432, 'samples': 16655424, 'steps': 86746, 'loss/train': 1.3468014001846313} 08/31/2021 04:52:01 - INFO - __main__ - Step 86748: {'lr': 0.00019346180224513387, 'samples': 16655616, 'steps': 86747, 'loss/train': 1.3271065950393677} 08/31/2021 04:52:02 - INFO - __main__ - Step 86749: {'lr': 0.0001934566330014998, 'samples': 16655808, 'steps': 86748, 'loss/train': 1.3907991647720337} 08/31/2021 04:52:02 - INFO - __main__ - Step 86750: {'lr': 0.00019345146378334327, 'samples': 16656000, 'steps': 86749, 'loss/train': 1.5387202501296997} 08/31/2021 04:52:02 - INFO - __main__ - Step 86751: {'lr': 0.00019344629459066675, 'samples': 16656192, 'steps': 86750, 'loss/train': 0.9685660600662231} 08/31/2021 04:52:04 - INFO - __main__ - Step 86752: {'lr': 0.0001934411254234724, 'samples': 16656384, 'steps': 86751, 'loss/train': 0.8896159529685974} 08/31/2021 04:52:04 - INFO - __main__ - Step 86753: {'lr': 0.00019343595628176256, 'samples': 16656576, 'steps': 86752, 'loss/train': 0.9920819997787476} 08/31/2021 04:52:05 - INFO - __main__ - Step 86754: {'lr': 0.00019343078716553962, 'samples': 16656768, 'steps': 86753, 'loss/train': 1.6718612909317017} 08/31/2021 04:52:05 - INFO - __main__ - Step 86755: {'lr': 0.00019342561807480588, 'samples': 16656960, 'steps': 86754, 'loss/train': 1.2283354997634888} 08/31/2021 04:52:05 - INFO - __main__ - Step 86756: {'lr': 0.0001934204490095637, 'samples': 16657152, 'steps': 86755, 'loss/train': 0.8165379166603088} 08/31/2021 04:52:06 - INFO - __main__ - Step 86757: {'lr': 0.0001934152799698154, 'samples': 16657344, 'steps': 86756, 'loss/train': 1.0587798357009888} 08/31/2021 04:52:07 - INFO - __main__ - Step 86758: {'lr': 0.00019341011095556327, 'samples': 16657536, 'steps': 86757, 'loss/train': 3.4982643127441406} 08/31/2021 04:52:08 - INFO - __main__ - Step 86759: {'lr': 0.0001934049419668097, 'samples': 16657728, 'steps': 86758, 'loss/train': 1.1860631704330444} 08/31/2021 04:52:08 - INFO - __main__ - Step 86760: {'lr': 0.00019339977300355697, 'samples': 16657920, 'steps': 86759, 'loss/train': 1.2368667125701904} 08/31/2021 04:52:08 - INFO - __main__ - Step 86761: {'lr': 0.00019339460406580744, 'samples': 16658112, 'steps': 86760, 'loss/train': 1.852339267730713} 08/31/2021 04:52:09 - INFO - __main__ - Step 86762: {'lr': 0.0001933894351535634, 'samples': 16658304, 'steps': 86761, 'loss/train': 1.202102780342102} 08/31/2021 04:52:10 - INFO - __main__ - Step 86763: {'lr': 0.00019338426626682725, 'samples': 16658496, 'steps': 86762, 'loss/train': 1.4072558879852295} 08/31/2021 04:52:11 - INFO - __main__ - Step 86764: {'lr': 0.00019337909740560136, 'samples': 16658688, 'steps': 86763, 'loss/train': 1.1612015962600708} 08/31/2021 04:52:11 - INFO - __main__ - Step 86765: {'lr': 0.00019337392856988789, 'samples': 16658880, 'steps': 86764, 'loss/train': 1.5346267223358154} 08/31/2021 04:52:11 - INFO - __main__ - Step 86766: {'lr': 0.00019336875975968924, 'samples': 16659072, 'steps': 86765, 'loss/train': 1.1914399862289429} 08/31/2021 04:52:12 - INFO - __main__ - Step 86767: {'lr': 0.00019336359097500773, 'samples': 16659264, 'steps': 86766, 'loss/train': 0.03198707103729248} 08/31/2021 04:52:13 - INFO - __main__ - Step 86768: {'lr': 0.00019335842221584573, 'samples': 16659456, 'steps': 86767, 'loss/train': 1.6249713897705078} 08/31/2021 04:52:14 - INFO - __main__ - Step 86769: {'lr': 0.00019335325348220555, 'samples': 16659648, 'steps': 86768, 'loss/train': 1.8613026142120361} 08/31/2021 04:52:14 - INFO - __main__ - Step 86770: {'lr': 0.00019334808477408953, 'samples': 16659840, 'steps': 86769, 'loss/train': 0.9373705983161926} 08/31/2021 04:52:15 - INFO - __main__ - Step 86771: {'lr': 0.0001933429160915, 'samples': 16660032, 'steps': 86770, 'loss/train': 1.3805593252182007} 08/31/2021 04:52:15 - INFO - __main__ - Step 86772: {'lr': 0.00019333774743443923, 'samples': 16660224, 'steps': 86771, 'loss/train': 1.708207368850708} 08/31/2021 04:52:15 - INFO - __main__ - Step 86773: {'lr': 0.00019333257880290962, 'samples': 16660416, 'steps': 86772, 'loss/train': 0.0188579261302948} 08/31/2021 04:52:17 - INFO - __main__ - Step 86774: {'lr': 0.0001933274101969135, 'samples': 16660608, 'steps': 86773, 'loss/train': 0.5729804635047913} 08/31/2021 04:52:17 - INFO - __main__ - Step 86775: {'lr': 0.0001933222416164532, 'samples': 16660800, 'steps': 86774, 'loss/train': 1.005381464958191} 08/31/2021 04:52:18 - INFO - __main__ - Step 86776: {'lr': 0.00019331707306153098, 'samples': 16660992, 'steps': 86775, 'loss/train': 1.2309495210647583} 08/31/2021 04:52:18 - INFO - __main__ - Step 86777: {'lr': 0.0001933119045321493, 'samples': 16661184, 'steps': 86776, 'loss/train': 1.5695241689682007} 08/31/2021 04:52:18 - INFO - __main__ - Step 86778: {'lr': 0.0001933067360283103, 'samples': 16661376, 'steps': 86777, 'loss/train': 0.8637733459472656} 08/31/2021 04:52:20 - INFO - __main__ - Step 86779: {'lr': 0.0001933015675500164, 'samples': 16661568, 'steps': 86778, 'loss/train': 1.0256274938583374} 08/31/2021 04:52:21 - INFO - __main__ - Step 86780: {'lr': 0.00019329639909727, 'samples': 16661760, 'steps': 86779, 'loss/train': 1.2988805770874023} 08/31/2021 04:52:21 - INFO - __main__ - Step 86781: {'lr': 0.00019329123067007332, 'samples': 16661952, 'steps': 86780, 'loss/train': 0.8159204125404358} 08/31/2021 04:52:21 - INFO - __main__ - Step 86782: {'lr': 0.0001932860622684287, 'samples': 16662144, 'steps': 86781, 'loss/train': 1.3298951387405396} 08/31/2021 04:52:22 - INFO - __main__ - Step 86783: {'lr': 0.0001932808938923386, 'samples': 16662336, 'steps': 86782, 'loss/train': 1.1608586311340332} 08/31/2021 04:52:23 - INFO - __main__ - Step 86784: {'lr': 0.00019327572554180518, 'samples': 16662528, 'steps': 86783, 'loss/train': 1.1480472087860107} 08/31/2021 04:52:24 - INFO - __main__ - Step 86785: {'lr': 0.00019327055721683086, 'samples': 16662720, 'steps': 86784, 'loss/train': 1.6297270059585571} 08/31/2021 04:52:24 - INFO - __main__ - Step 86786: {'lr': 0.00019326538891741802, 'samples': 16662912, 'steps': 86785, 'loss/train': 1.4389994144439697} 08/31/2021 04:52:24 - INFO - __main__ - Step 86787: {'lr': 0.00019326022064356885, 'samples': 16663104, 'steps': 86786, 'loss/train': 1.1618539094924927} 08/31/2021 04:52:25 - INFO - __main__ - Step 86788: {'lr': 0.00019325505239528576, 'samples': 16663296, 'steps': 86787, 'loss/train': 1.1775779724121094} 08/31/2021 04:52:25 - INFO - __main__ - Step 86789: {'lr': 0.00019324988417257106, 'samples': 16663488, 'steps': 86788, 'loss/train': 1.320299744606018} 08/31/2021 04:52:27 - INFO - __main__ - Step 86790: {'lr': 0.00019324471597542708, 'samples': 16663680, 'steps': 86789, 'loss/train': 1.736222505569458} 08/31/2021 04:52:27 - INFO - __main__ - Step 86791: {'lr': 0.00019323954780385626, 'samples': 16663872, 'steps': 86790, 'loss/train': 0.8733345866203308} 08/31/2021 04:52:28 - INFO - __main__ - Step 86792: {'lr': 0.00019323437965786073, 'samples': 16664064, 'steps': 86791, 'loss/train': 1.2313545942306519} 08/31/2021 04:52:28 - INFO - __main__ - Step 86793: {'lr': 0.00019322921153744292, 'samples': 16664256, 'steps': 86792, 'loss/train': 1.5882339477539062} 08/31/2021 04:52:29 - INFO - __main__ - Step 86794: {'lr': 0.00019322404344260512, 'samples': 16664448, 'steps': 86793, 'loss/train': 1.0390199422836304} 08/31/2021 04:52:30 - INFO - __main__ - Step 86795: {'lr': 0.00019321887537334973, 'samples': 16664640, 'steps': 86794, 'loss/train': 1.3975592851638794} 08/31/2021 04:52:30 - INFO - __main__ - Step 86796: {'lr': 0.00019321370732967904, 'samples': 16664832, 'steps': 86795, 'loss/train': 1.1569572687149048} 08/31/2021 04:52:31 - INFO - __main__ - Step 86797: {'lr': 0.00019320853931159538, 'samples': 16665024, 'steps': 86796, 'loss/train': 0.9999446868896484} 08/31/2021 04:52:31 - INFO - __main__ - Step 86798: {'lr': 0.00019320337131910106, 'samples': 16665216, 'steps': 86797, 'loss/train': 1.321176528930664} 08/31/2021 04:52:31 - INFO - __main__ - Step 86799: {'lr': 0.00019319820335219842, 'samples': 16665408, 'steps': 86798, 'loss/train': 0.538657546043396} 08/31/2021 04:52:33 - INFO - __main__ - Step 86800: {'lr': 0.0001931930354108898, 'samples': 16665600, 'steps': 86799, 'loss/train': 1.1019172668457031} 08/31/2021 04:52:34 - INFO - __main__ - Step 86801: {'lr': 0.00019318786749517752, 'samples': 16665792, 'steps': 86800, 'loss/train': 0.8194169402122498} 08/31/2021 04:52:34 - INFO - __main__ - Step 86802: {'lr': 0.0001931826996050639, 'samples': 16665984, 'steps': 86801, 'loss/train': 1.116165041923523} 08/31/2021 04:52:34 - INFO - __main__ - Step 86803: {'lr': 0.0001931775317405513, 'samples': 16666176, 'steps': 86802, 'loss/train': 0.3953496515750885} 08/31/2021 04:52:35 - INFO - __main__ - Step 86804: {'lr': 0.00019317236390164206, 'samples': 16666368, 'steps': 86803, 'loss/train': 1.0721442699432373} 08/31/2021 04:52:36 - INFO - __main__ - Step 86805: {'lr': 0.00019316719608833844, 'samples': 16666560, 'steps': 86804, 'loss/train': 0.9615010619163513} 08/31/2021 04:52:37 - INFO - __main__ - Step 86806: {'lr': 0.00019316202830064279, 'samples': 16666752, 'steps': 86805, 'loss/train': 1.7639766931533813} 08/31/2021 04:52:37 - INFO - __main__ - Step 86807: {'lr': 0.00019315686053855745, 'samples': 16666944, 'steps': 86806, 'loss/train': 1.1009058952331543} 08/31/2021 04:52:38 - INFO - __main__ - Step 86808: {'lr': 0.0001931516928020848, 'samples': 16667136, 'steps': 86807, 'loss/train': 0.9620521664619446} 08/31/2021 04:52:38 - INFO - __main__ - Step 86809: {'lr': 0.00019314652509122706, 'samples': 16667328, 'steps': 86808, 'loss/train': 0.5072591304779053} 08/31/2021 04:52:38 - INFO - __main__ - Step 86810: {'lr': 0.00019314135740598664, 'samples': 16667520, 'steps': 86809, 'loss/train': 1.8626090288162231} 08/31/2021 04:52:40 - INFO - __main__ - Step 86811: {'lr': 0.00019313618974636587, 'samples': 16667712, 'steps': 86810, 'loss/train': 1.6651493310928345} 08/31/2021 04:52:40 - INFO - __main__ - Step 86812: {'lr': 0.000193131022112367, 'samples': 16667904, 'steps': 86811, 'loss/train': 1.1575018167495728} 08/31/2021 04:52:40 - INFO - __main__ - Step 86813: {'lr': 0.00019312585450399246, 'samples': 16668096, 'steps': 86812, 'loss/train': 1.383925199508667} 08/31/2021 04:52:41 - INFO - __main__ - Step 86814: {'lr': 0.00019312068692124452, 'samples': 16668288, 'steps': 86813, 'loss/train': 1.6899365186691284} 08/31/2021 04:52:41 - INFO - __main__ - Step 86815: {'lr': 0.00019311551936412551, 'samples': 16668480, 'steps': 86814, 'loss/train': 1.3020659685134888} 08/31/2021 04:52:43 - INFO - __main__ - Step 86816: {'lr': 0.00019311035183263778, 'samples': 16668672, 'steps': 86815, 'loss/train': 1.5218822956085205} 08/31/2021 04:52:43 - INFO - __main__ - Step 86817: {'lr': 0.00019310518432678366, 'samples': 16668864, 'steps': 86816, 'loss/train': 1.497167944908142} 08/31/2021 04:52:43 - INFO - __main__ - Step 86818: {'lr': 0.00019310001684656546, 'samples': 16669056, 'steps': 86817, 'loss/train': 0.9398149847984314} 08/31/2021 04:52:44 - INFO - __main__ - Step 86819: {'lr': 0.00019309484939198558, 'samples': 16669248, 'steps': 86818, 'loss/train': 0.8223086595535278} 08/31/2021 04:52:44 - INFO - __main__ - Step 86820: {'lr': 0.00019308968196304622, 'samples': 16669440, 'steps': 86819, 'loss/train': 1.4166642427444458} 08/31/2021 04:52:46 - INFO - __main__ - Step 86821: {'lr': 0.00019308451455974973, 'samples': 16669632, 'steps': 86820, 'loss/train': 1.079384684562683} 08/31/2021 04:52:46 - INFO - __main__ - Step 86822: {'lr': 0.00019307934718209853, 'samples': 16669824, 'steps': 86821, 'loss/train': 2.0233492851257324} 08/31/2021 04:52:46 - INFO - __main__ - Step 86823: {'lr': 0.00019307417983009485, 'samples': 16670016, 'steps': 86822, 'loss/train': 0.8618850708007812} 08/31/2021 04:52:47 - INFO - __main__ - Step 86824: {'lr': 0.0001930690125037411, 'samples': 16670208, 'steps': 86823, 'loss/train': 0.810478687286377} 08/31/2021 04:52:47 - INFO - __main__ - Step 86825: {'lr': 0.00019306384520303955, 'samples': 16670400, 'steps': 86824, 'loss/train': 1.1488218307495117} 08/31/2021 04:52:49 - INFO - __main__ - Step 86826: {'lr': 0.0001930586779279926, 'samples': 16670592, 'steps': 86825, 'loss/train': 1.1322970390319824} 08/31/2021 04:52:49 - INFO - __main__ - Step 86827: {'lr': 0.00019305351067860246, 'samples': 16670784, 'steps': 86826, 'loss/train': 0.8460708856582642} 08/31/2021 04:52:50 - INFO - __main__ - Step 86828: {'lr': 0.00019304834345487158, 'samples': 16670976, 'steps': 86827, 'loss/train': 0.9410282969474792} 08/31/2021 04:52:50 - INFO - __main__ - Step 86829: {'lr': 0.00019304317625680223, 'samples': 16671168, 'steps': 86828, 'loss/train': 1.2354750633239746} 08/31/2021 04:52:50 - INFO - __main__ - Step 86830: {'lr': 0.00019303800908439673, 'samples': 16671360, 'steps': 86829, 'loss/train': 1.478289008140564} 08/31/2021 04:52:51 - INFO - __main__ - Step 86831: {'lr': 0.00019303284193765755, 'samples': 16671552, 'steps': 86830, 'loss/train': 1.281376600265503} 08/31/2021 04:52:52 - INFO - __main__ - Step 86832: {'lr': 0.00019302767481658677, 'samples': 16671744, 'steps': 86831, 'loss/train': 0.8612679243087769} 08/31/2021 04:52:53 - INFO - __main__ - Step 86833: {'lr': 0.00019302250772118684, 'samples': 16671936, 'steps': 86832, 'loss/train': 1.0270533561706543} 08/31/2021 04:52:53 - INFO - __main__ - Step 86834: {'lr': 0.00019301734065146008, 'samples': 16672128, 'steps': 86833, 'loss/train': 1.4772330522537231} 08/31/2021 04:52:53 - INFO - __main__ - Step 86835: {'lr': 0.00019301217360740886, 'samples': 16672320, 'steps': 86834, 'loss/train': 0.0647524818778038} 08/31/2021 04:52:54 - INFO - __main__ - Step 86836: {'lr': 0.00019300700658903547, 'samples': 16672512, 'steps': 86835, 'loss/train': 0.6970973610877991} 08/31/2021 04:52:55 - INFO - __main__ - Step 86837: {'lr': 0.00019300183959634223, 'samples': 16672704, 'steps': 86836, 'loss/train': 0.6693023443222046} 08/31/2021 04:52:56 - INFO - __main__ - Step 86838: {'lr': 0.00019299667262933149, 'samples': 16672896, 'steps': 86837, 'loss/train': 0.6184312105178833} 08/31/2021 04:52:56 - INFO - __main__ - Step 86839: {'lr': 0.00019299150568800554, 'samples': 16673088, 'steps': 86838, 'loss/train': 0.29710328578948975} 08/31/2021 04:52:57 - INFO - __main__ - Step 86840: {'lr': 0.0001929863387723668, 'samples': 16673280, 'steps': 86839, 'loss/train': 1.3141553401947021} 08/31/2021 04:52:57 - INFO - __main__ - Step 86841: {'lr': 0.00019298117188241748, 'samples': 16673472, 'steps': 86840, 'loss/train': 1.4752551317214966} 08/31/2021 04:52:59 - INFO - __main__ - Step 86842: {'lr': 0.00019297600501816, 'samples': 16673664, 'steps': 86841, 'loss/train': 0.46555814146995544} 08/31/2021 04:52:59 - INFO - __main__ - Step 86843: {'lr': 0.00019297083817959663, 'samples': 16673856, 'steps': 86842, 'loss/train': 1.0470631122589111} 08/31/2021 04:53:00 - INFO - __main__ - Step 86844: {'lr': 0.0001929656713667297, 'samples': 16674048, 'steps': 86843, 'loss/train': 1.547519564628601} 08/31/2021 04:53:00 - INFO - __main__ - Step 86845: {'lr': 0.00019296050457956172, 'samples': 16674240, 'steps': 86844, 'loss/train': 1.7233037948608398} 08/31/2021 04:53:00 - INFO - __main__ - Step 86846: {'lr': 0.0001929553378180947, 'samples': 16674432, 'steps': 86845, 'loss/train': 1.1900817155838013} 08/31/2021 04:53:02 - INFO - __main__ - Step 86847: {'lr': 0.00019295017108233114, 'samples': 16674624, 'steps': 86846, 'loss/train': 0.8171091675758362} 08/31/2021 04:53:02 - INFO - __main__ - Step 86848: {'lr': 0.00019294500437227335, 'samples': 16674816, 'steps': 86847, 'loss/train': 1.2493281364440918} 08/31/2021 04:53:03 - INFO - __main__ - Step 86849: {'lr': 0.00019293983768792366, 'samples': 16675008, 'steps': 86848, 'loss/train': 1.3218950033187866} 08/31/2021 04:53:03 - INFO - __main__ - Step 86850: {'lr': 0.0001929346710292844, 'samples': 16675200, 'steps': 86849, 'loss/train': 0.05552220717072487} 08/31/2021 04:53:03 - INFO - __main__ - Step 86851: {'lr': 0.00019292950439635793, 'samples': 16675392, 'steps': 86850, 'loss/train': 1.29593825340271} 08/31/2021 04:53:05 - INFO - __main__ - Step 86852: {'lr': 0.0001929243377891465, 'samples': 16675584, 'steps': 86851, 'loss/train': 1.3414851427078247} 08/31/2021 04:53:05 - INFO - __main__ - Step 86853: {'lr': 0.00019291917120765252, 'samples': 16675776, 'steps': 86852, 'loss/train': 0.7404730319976807} 08/31/2021 04:53:06 - INFO - __main__ - Step 86854: {'lr': 0.00019291400465187825, 'samples': 16675968, 'steps': 86853, 'loss/train': 0.3674701750278473} 08/31/2021 04:53:06 - INFO - __main__ - Step 86855: {'lr': 0.00019290883812182605, 'samples': 16676160, 'steps': 86854, 'loss/train': 0.9922357797622681} 08/31/2021 04:53:06 - INFO - __main__ - Step 86856: {'lr': 0.0001929036716174983, 'samples': 16676352, 'steps': 86855, 'loss/train': 1.3025144338607788} 08/31/2021 04:53:08 - INFO - __main__ - Step 86857: {'lr': 0.00019289850513889718, 'samples': 16676544, 'steps': 86856, 'loss/train': 1.3870261907577515} 08/31/2021 04:53:09 - INFO - __main__ - Step 86858: {'lr': 0.00019289333868602527, 'samples': 16676736, 'steps': 86857, 'loss/train': 1.1826246976852417} 08/31/2021 04:53:09 - INFO - __main__ - Step 86859: {'lr': 0.00019288817225888465, 'samples': 16676928, 'steps': 86858, 'loss/train': 0.8699436187744141} 08/31/2021 04:53:09 - INFO - __main__ - Step 86860: {'lr': 0.0001928830058574777, 'samples': 16677120, 'steps': 86859, 'loss/train': 0.83468097448349} 08/31/2021 04:53:10 - INFO - __main__ - Step 86861: {'lr': 0.0001928778394818068, 'samples': 16677312, 'steps': 86860, 'loss/train': 1.7842843532562256} 08/31/2021 04:53:12 - INFO - __main__ - Step 86862: {'lr': 0.0001928726731318743, 'samples': 16677504, 'steps': 86861, 'loss/train': 1.1959673166275024} 08/31/2021 04:53:12 - INFO - __main__ - Step 86863: {'lr': 0.00019286750680768246, 'samples': 16677696, 'steps': 86862, 'loss/train': 0.19012844562530518} 08/31/2021 04:53:12 - INFO - __main__ - Step 86864: {'lr': 0.00019286234050923363, 'samples': 16677888, 'steps': 86863, 'loss/train': 0.9578079581260681} 08/31/2021 04:53:13 - INFO - __main__ - Step 86865: {'lr': 0.00019285717423653015, 'samples': 16678080, 'steps': 86864, 'loss/train': 1.4852793216705322} 08/31/2021 04:53:13 - INFO - __main__ - Step 86866: {'lr': 0.00019285200798957436, 'samples': 16678272, 'steps': 86865, 'loss/train': 0.392747163772583} 08/31/2021 04:53:14 - INFO - __main__ - Step 86867: {'lr': 0.0001928468417683686, 'samples': 16678464, 'steps': 86866, 'loss/train': 0.2587509751319885} 08/31/2021 04:53:15 - INFO - __main__ - Step 86868: {'lr': 0.00019284167557291512, 'samples': 16678656, 'steps': 86867, 'loss/train': 1.6227003335952759} 08/31/2021 04:53:16 - INFO - __main__ - Step 86869: {'lr': 0.00019283650940321633, 'samples': 16678848, 'steps': 86868, 'loss/train': 0.7463813424110413} 08/31/2021 04:53:16 - INFO - __main__ - Step 86870: {'lr': 0.00019283134325927452, 'samples': 16679040, 'steps': 86869, 'loss/train': 1.1379314661026} 08/31/2021 04:53:16 - INFO - __main__ - Step 86871: {'lr': 0.00019282617714109202, 'samples': 16679232, 'steps': 86870, 'loss/train': 1.489164113998413} 08/31/2021 04:53:17 - INFO - __main__ - Step 86872: {'lr': 0.00019282101104867126, 'samples': 16679424, 'steps': 86871, 'loss/train': 0.5538334250450134} 08/31/2021 04:53:18 - INFO - __main__ - Step 86873: {'lr': 0.0001928158449820144, 'samples': 16679616, 'steps': 86872, 'loss/train': 1.0292924642562866} 08/31/2021 04:53:19 - INFO - __main__ - Step 86874: {'lr': 0.00019281067894112377, 'samples': 16679808, 'steps': 86873, 'loss/train': 1.7413935661315918} 08/31/2021 04:53:19 - INFO - __main__ - Step 86875: {'lr': 0.00019280551292600182, 'samples': 16680000, 'steps': 86874, 'loss/train': 0.04461786895990372} 08/31/2021 04:53:20 - INFO - __main__ - Step 86876: {'lr': 0.0001928003469366508, 'samples': 16680192, 'steps': 86875, 'loss/train': 1.1268826723098755} 08/31/2021 04:53:20 - INFO - __main__ - Step 86877: {'lr': 0.0001927951809730731, 'samples': 16680384, 'steps': 86876, 'loss/train': 0.5156170725822449} 08/31/2021 04:53:22 - INFO - __main__ - Step 86878: {'lr': 0.00019279001503527096, 'samples': 16680576, 'steps': 86877, 'loss/train': 1.0321729183197021} 08/31/2021 04:53:22 - INFO - __main__ - Step 86879: {'lr': 0.00019278484912324678, 'samples': 16680768, 'steps': 86878, 'loss/train': 1.3572025299072266} 08/31/2021 04:53:23 - INFO - __main__ - Step 86880: {'lr': 0.00019277968323700285, 'samples': 16680960, 'steps': 86879, 'loss/train': 0.9591379761695862} 08/31/2021 04:53:23 - INFO - __main__ - Step 86881: {'lr': 0.00019277451737654153, 'samples': 16681152, 'steps': 86880, 'loss/train': 0.9474815130233765} 08/31/2021 04:53:23 - INFO - __main__ - Step 86882: {'lr': 0.00019276935154186511, 'samples': 16681344, 'steps': 86881, 'loss/train': 1.0131601095199585} 08/31/2021 04:53:25 - INFO - __main__ - Step 86883: {'lr': 0.00019276418573297596, 'samples': 16681536, 'steps': 86882, 'loss/train': 0.049746010452508926} 08/31/2021 04:53:25 - INFO - __main__ - Step 86884: {'lr': 0.0001927590199498764, 'samples': 16681728, 'steps': 86883, 'loss/train': 1.7294533252716064} 08/31/2021 04:53:26 - INFO - __main__ - Step 86885: {'lr': 0.0001927538541925688, 'samples': 16681920, 'steps': 86884, 'loss/train': 0.8801373839378357} 08/31/2021 04:53:26 - INFO - __main__ - Step 86886: {'lr': 0.00019274868846105533, 'samples': 16682112, 'steps': 86885, 'loss/train': 1.1867281198501587} 08/31/2021 04:53:26 - INFO - __main__ - Step 86887: {'lr': 0.00019274352275533844, 'samples': 16682304, 'steps': 86886, 'loss/train': 2.5211236476898193} 08/31/2021 04:53:27 - INFO - __main__ - Step 86888: {'lr': 0.00019273835707542042, 'samples': 16682496, 'steps': 86887, 'loss/train': 1.7195881605148315} 08/31/2021 04:53:28 - INFO - __main__ - Step 86889: {'lr': 0.00019273319142130364, 'samples': 16682688, 'steps': 86888, 'loss/train': 1.3205252885818481} 08/31/2021 04:53:29 - INFO - __main__ - Step 86890: {'lr': 0.00019272802579299036, 'samples': 16682880, 'steps': 86889, 'loss/train': 1.626285195350647} 08/31/2021 04:53:29 - INFO - __main__ - Step 86891: {'lr': 0.000192722860190483, 'samples': 16683072, 'steps': 86890, 'loss/train': 1.048530101776123} 08/31/2021 04:53:29 - INFO - __main__ - Step 86892: {'lr': 0.0001927176946137838, 'samples': 16683264, 'steps': 86891, 'loss/train': 1.529083251953125} 08/31/2021 04:53:30 - INFO - __main__ - Step 86893: {'lr': 0.0001927125290628951, 'samples': 16683456, 'steps': 86892, 'loss/train': 0.0327274464070797} 08/31/2021 04:53:32 - INFO - __main__ - Step 86894: {'lr': 0.00019270736353781928, 'samples': 16683648, 'steps': 86893, 'loss/train': 1.6022191047668457} 08/31/2021 04:53:33 - INFO - __main__ - Step 86895: {'lr': 0.00019270219803855864, 'samples': 16683840, 'steps': 86894, 'loss/train': 1.1880180835723877} 08/31/2021 04:53:33 - INFO - __main__ - Step 86896: {'lr': 0.0001926970325651155, 'samples': 16684032, 'steps': 86895, 'loss/train': 1.2941950559616089} 08/31/2021 04:53:33 - INFO - __main__ - Step 86897: {'lr': 0.0001926918671174922, 'samples': 16684224, 'steps': 86896, 'loss/train': 0.044504281133413315} 08/31/2021 04:53:34 - INFO - __main__ - Step 86898: {'lr': 0.00019268670169569115, 'samples': 16684416, 'steps': 86897, 'loss/train': 0.665470540523529} 08/31/2021 04:53:35 - INFO - __main__ - Step 86899: {'lr': 0.0001926815362997145, 'samples': 16684608, 'steps': 86898, 'loss/train': 0.8934013247489929} 08/31/2021 04:53:36 - INFO - __main__ - Step 86900: {'lr': 0.00019267637092956468, 'samples': 16684800, 'steps': 86899, 'loss/train': 0.8173649907112122} 08/31/2021 04:53:36 - INFO - __main__ - Step 86901: {'lr': 0.00019267120558524395, 'samples': 16684992, 'steps': 86900, 'loss/train': 1.1633630990982056} 08/31/2021 04:53:36 - INFO - __main__ - Step 86902: {'lr': 0.00019266604026675472, 'samples': 16685184, 'steps': 86901, 'loss/train': 1.8409405946731567} 08/31/2021 04:53:37 - INFO - __main__ - Step 86903: {'lr': 0.0001926608749740993, 'samples': 16685376, 'steps': 86902, 'loss/train': 0.9470528364181519} 08/31/2021 04:53:38 - INFO - __main__ - Step 86904: {'lr': 0.00019265570970728, 'samples': 16685568, 'steps': 86903, 'loss/train': 0.5587805509567261} 08/31/2021 04:53:39 - INFO - __main__ - Step 86905: {'lr': 0.00019265054446629916, 'samples': 16685760, 'steps': 86904, 'loss/train': 0.7317600250244141} 08/31/2021 04:53:39 - INFO - __main__ - Step 86906: {'lr': 0.00019264537925115904, 'samples': 16685952, 'steps': 86905, 'loss/train': 1.0613129138946533} 08/31/2021 04:53:39 - INFO - __main__ - Step 86907: {'lr': 0.0001926402140618621, 'samples': 16686144, 'steps': 86906, 'loss/train': 1.3256880044937134} 08/31/2021 04:53:40 - INFO - __main__ - Step 86908: {'lr': 0.00019263504889841055, 'samples': 16686336, 'steps': 86907, 'loss/train': 0.5517844557762146} 08/31/2021 04:53:41 - INFO - __main__ - Step 86909: {'lr': 0.00019262988376080685, 'samples': 16686528, 'steps': 86908, 'loss/train': 1.0403507947921753} 08/31/2021 04:53:42 - INFO - __main__ - Step 86910: {'lr': 0.00019262471864905315, 'samples': 16686720, 'steps': 86909, 'loss/train': 1.4296470880508423} 08/31/2021 04:53:42 - INFO - __main__ - Step 86911: {'lr': 0.00019261955356315188, 'samples': 16686912, 'steps': 86910, 'loss/train': 1.1015647649765015} 08/31/2021 04:53:42 - INFO - __main__ - Step 86912: {'lr': 0.00019261438850310541, 'samples': 16687104, 'steps': 86911, 'loss/train': 1.5542758703231812} 08/31/2021 04:53:43 - INFO - __main__ - Step 86913: {'lr': 0.00019260922346891595, 'samples': 16687296, 'steps': 86912, 'loss/train': 0.38732674717903137} 08/31/2021 04:53:44 - INFO - __main__ - Step 86914: {'lr': 0.00019260405846058593, 'samples': 16687488, 'steps': 86913, 'loss/train': 0.5233181715011597} 08/31/2021 04:53:45 - INFO - __main__ - Step 86915: {'lr': 0.0001925988934781176, 'samples': 16687680, 'steps': 86914, 'loss/train': 1.3549381494522095} 08/31/2021 04:53:45 - INFO - __main__ - Step 86916: {'lr': 0.0001925937285215133, 'samples': 16687872, 'steps': 86915, 'loss/train': 1.7787606716156006} 08/31/2021 04:53:45 - INFO - __main__ - Step 86917: {'lr': 0.00019258856359077541, 'samples': 16688064, 'steps': 86916, 'loss/train': 1.4730117321014404} 08/31/2021 04:53:46 - INFO - __main__ - Step 86918: {'lr': 0.00019258339868590625, 'samples': 16688256, 'steps': 86917, 'loss/train': 1.06820547580719} 08/31/2021 04:53:46 - INFO - __main__ - Step 86919: {'lr': 0.00019257823380690808, 'samples': 16688448, 'steps': 86918, 'loss/train': 1.3038527965545654} 08/31/2021 04:53:48 - INFO - __main__ - Step 86920: {'lr': 0.00019257306895378336, 'samples': 16688640, 'steps': 86919, 'loss/train': 1.5823321342468262} 08/31/2021 04:53:48 - INFO - __main__ - Step 86921: {'lr': 0.00019256790412653423, 'samples': 16688832, 'steps': 86920, 'loss/train': 1.40879487991333} 08/31/2021 04:53:48 - INFO - __main__ - Step 86922: {'lr': 0.00019256273932516317, 'samples': 16689024, 'steps': 86921, 'loss/train': 0.5991170406341553} 08/31/2021 04:53:49 - INFO - __main__ - Step 86923: {'lr': 0.0001925575745496724, 'samples': 16689216, 'steps': 86922, 'loss/train': 0.9481639266014099} 08/31/2021 04:53:49 - INFO - __main__ - Step 86924: {'lr': 0.00019255240980006432, 'samples': 16689408, 'steps': 86923, 'loss/train': 1.1355892419815063} 08/31/2021 04:53:51 - INFO - __main__ - Step 86925: {'lr': 0.0001925472450763413, 'samples': 16689600, 'steps': 86924, 'loss/train': 0.9916552901268005} 08/31/2021 04:53:51 - INFO - __main__ - Step 86926: {'lr': 0.00019254208037850556, 'samples': 16689792, 'steps': 86925, 'loss/train': 1.99295973777771} 08/31/2021 04:53:51 - INFO - __main__ - Step 86927: {'lr': 0.00019253691570655945, 'samples': 16689984, 'steps': 86926, 'loss/train': 0.8533482551574707} 08/31/2021 04:53:52 - INFO - __main__ - Step 86928: {'lr': 0.00019253175106050536, 'samples': 16690176, 'steps': 86927, 'loss/train': 1.4692182540893555} 08/31/2021 04:53:52 - INFO - __main__ - Step 86929: {'lr': 0.00019252658644034555, 'samples': 16690368, 'steps': 86928, 'loss/train': 0.33866679668426514} 08/31/2021 04:53:54 - INFO - __main__ - Step 86930: {'lr': 0.00019252142184608234, 'samples': 16690560, 'steps': 86929, 'loss/train': 1.3078467845916748} 08/31/2021 04:53:54 - INFO - __main__ - Step 86931: {'lr': 0.00019251625727771817, 'samples': 16690752, 'steps': 86930, 'loss/train': 1.2471965551376343} 08/31/2021 04:53:55 - INFO - __main__ - Step 86932: {'lr': 0.00019251109273525524, 'samples': 16690944, 'steps': 86931, 'loss/train': 0.29431405663490295} 08/31/2021 04:53:55 - INFO - __main__ - Step 86933: {'lr': 0.00019250592821869596, 'samples': 16691136, 'steps': 86932, 'loss/train': 1.0615333318710327} 08/31/2021 04:53:55 - INFO - __main__ - Step 86934: {'lr': 0.00019250076372804258, 'samples': 16691328, 'steps': 86933, 'loss/train': 0.8733311891555786} 08/31/2021 04:53:57 - INFO - __main__ - Step 86935: {'lr': 0.00019249559926329745, 'samples': 16691520, 'steps': 86934, 'loss/train': 1.2618542909622192} 08/31/2021 04:53:57 - INFO - __main__ - Step 86936: {'lr': 0.00019249043482446294, 'samples': 16691712, 'steps': 86935, 'loss/train': 1.481809377670288} 08/31/2021 04:53:58 - INFO - __main__ - Step 86937: {'lr': 0.00019248527041154136, 'samples': 16691904, 'steps': 86936, 'loss/train': 1.6586604118347168} 08/31/2021 04:53:58 - INFO - __main__ - Step 86938: {'lr': 0.00019248010602453502, 'samples': 16692096, 'steps': 86937, 'loss/train': 0.8241472244262695} 08/31/2021 04:53:58 - INFO - __main__ - Step 86939: {'lr': 0.00019247494166344632, 'samples': 16692288, 'steps': 86938, 'loss/train': 0.6593896746635437} 08/31/2021 04:53:59 - INFO - __main__ - Step 86940: {'lr': 0.00019246977732827745, 'samples': 16692480, 'steps': 86939, 'loss/train': 1.3145591020584106} 08/31/2021 04:54:00 - INFO - __main__ - Step 86941: {'lr': 0.00019246461301903082, 'samples': 16692672, 'steps': 86940, 'loss/train': 1.6444181203842163} 08/31/2021 04:54:01 - INFO - __main__ - Step 86942: {'lr': 0.0001924594487357088, 'samples': 16692864, 'steps': 86941, 'loss/train': 1.737827181816101} 08/31/2021 04:54:01 - INFO - __main__ - Step 86943: {'lr': 0.00019245428447831362, 'samples': 16693056, 'steps': 86942, 'loss/train': 1.221346378326416} 08/31/2021 04:54:01 - INFO - __main__ - Step 86944: {'lr': 0.00019244912024684764, 'samples': 16693248, 'steps': 86943, 'loss/train': 1.595180630683899} 08/31/2021 04:54:02 - INFO - __main__ - Step 86945: {'lr': 0.00019244395604131321, 'samples': 16693440, 'steps': 86944, 'loss/train': 1.831153154373169} 08/31/2021 04:54:04 - INFO - __main__ - Step 86946: {'lr': 0.00019243879186171264, 'samples': 16693632, 'steps': 86945, 'loss/train': 1.3026139736175537} 08/31/2021 04:54:04 - INFO - __main__ - Step 86947: {'lr': 0.00019243362770804827, 'samples': 16693824, 'steps': 86946, 'loss/train': 1.1411832571029663} 08/31/2021 04:54:05 - INFO - __main__ - Step 86948: {'lr': 0.0001924284635803224, 'samples': 16694016, 'steps': 86947, 'loss/train': 0.6179497838020325} 08/31/2021 04:54:05 - INFO - __main__ - Step 86949: {'lr': 0.00019242329947853737, 'samples': 16694208, 'steps': 86948, 'loss/train': 1.2376059293746948} 08/31/2021 04:54:05 - INFO - __main__ - Step 86950: {'lr': 0.00019241813540269554, 'samples': 16694400, 'steps': 86949, 'loss/train': 1.1783146858215332} 08/31/2021 04:54:07 - INFO - __main__ - Step 86951: {'lr': 0.0001924129713527992, 'samples': 16694592, 'steps': 86950, 'loss/train': 1.875393033027649} 08/31/2021 04:54:07 - INFO - __main__ - Step 86952: {'lr': 0.00019240780732885073, 'samples': 16694784, 'steps': 86951, 'loss/train': 4.268414497375488} 08/31/2021 04:54:08 - INFO - __main__ - Step 86953: {'lr': 0.00019240264333085245, 'samples': 16694976, 'steps': 86952, 'loss/train': 0.9629439115524292} 08/31/2021 04:54:08 - INFO - __main__ - Step 86954: {'lr': 0.00019239747935880655, 'samples': 16695168, 'steps': 86953, 'loss/train': 1.090367317199707} 08/31/2021 04:54:08 - INFO - __main__ - Step 86955: {'lr': 0.00019239231541271547, 'samples': 16695360, 'steps': 86954, 'loss/train': 0.3071580231189728} 08/31/2021 04:54:10 - INFO - __main__ - Step 86956: {'lr': 0.00019238715149258155, 'samples': 16695552, 'steps': 86955, 'loss/train': 1.5857874155044556} 08/31/2021 04:54:10 - INFO - __main__ - Step 86957: {'lr': 0.00019238198759840707, 'samples': 16695744, 'steps': 86956, 'loss/train': 0.025160912424325943} 08/31/2021 04:54:11 - INFO - __main__ - Step 86958: {'lr': 0.00019237682373019437, 'samples': 16695936, 'steps': 86957, 'loss/train': 1.0241985321044922} 08/31/2021 04:54:11 - INFO - __main__ - Step 86959: {'lr': 0.00019237165988794576, 'samples': 16696128, 'steps': 86958, 'loss/train': 1.4227479696273804} 08/31/2021 04:54:11 - INFO - __main__ - Step 86960: {'lr': 0.00019236649607166364, 'samples': 16696320, 'steps': 86959, 'loss/train': 0.8126445412635803} 08/31/2021 04:54:13 - INFO - __main__ - Step 86961: {'lr': 0.00019236133228135027, 'samples': 16696512, 'steps': 86960, 'loss/train': 1.6289581060409546} 08/31/2021 04:54:14 - INFO - __main__ - Step 86962: {'lr': 0.000192356168517008, 'samples': 16696704, 'steps': 86961, 'loss/train': 1.259082555770874} 08/31/2021 04:54:14 - INFO - __main__ - Step 86963: {'lr': 0.00019235100477863916, 'samples': 16696896, 'steps': 86962, 'loss/train': 1.3767732381820679} 08/31/2021 04:54:14 - INFO - __main__ - Step 86964: {'lr': 0.00019234584106624604, 'samples': 16697088, 'steps': 86963, 'loss/train': 1.6754392385482788} 08/31/2021 04:54:15 - INFO - __main__ - Step 86965: {'lr': 0.000192340677379831, 'samples': 16697280, 'steps': 86964, 'loss/train': 0.7811563611030579} 08/31/2021 04:54:16 - INFO - __main__ - Step 86966: {'lr': 0.00019233551371939647, 'samples': 16697472, 'steps': 86965, 'loss/train': 1.4873167276382446} 08/31/2021 04:54:17 - INFO - __main__ - Step 86967: {'lr': 0.00019233035008494456, 'samples': 16697664, 'steps': 86966, 'loss/train': 0.8498023748397827} 08/31/2021 04:54:17 - INFO - __main__ - Step 86968: {'lr': 0.00019232518647647773, 'samples': 16697856, 'steps': 86967, 'loss/train': 1.2960669994354248} 08/31/2021 04:54:18 - INFO - __main__ - Step 86969: {'lr': 0.00019232002289399825, 'samples': 16698048, 'steps': 86968, 'loss/train': 1.1602766513824463} 08/31/2021 04:54:18 - INFO - __main__ - Step 86970: {'lr': 0.00019231485933750848, 'samples': 16698240, 'steps': 86969, 'loss/train': 0.4881156384944916} 08/31/2021 04:54:20 - INFO - __main__ - Step 86971: {'lr': 0.00019230969580701077, 'samples': 16698432, 'steps': 86970, 'loss/train': 1.419355034828186} 08/31/2021 04:54:21 - INFO - __main__ - Step 86972: {'lr': 0.00019230453230250738, 'samples': 16698624, 'steps': 86971, 'loss/train': 1.236310362815857} 08/31/2021 04:54:21 - INFO - __main__ - Step 86973: {'lr': 0.00019229936882400074, 'samples': 16698816, 'steps': 86972, 'loss/train': 1.6770731210708618} 08/31/2021 04:54:21 - INFO - __main__ - Step 86974: {'lr': 0.00019229420537149306, 'samples': 16699008, 'steps': 86973, 'loss/train': 2.080470561981201} 08/31/2021 04:54:22 - INFO - __main__ - Step 86975: {'lr': 0.00019228904194498674, 'samples': 16699200, 'steps': 86974, 'loss/train': 0.051969218999147415} 08/31/2021 04:54:22 - INFO - __main__ - Step 86976: {'lr': 0.00019228387854448406, 'samples': 16699392, 'steps': 86975, 'loss/train': 1.2857823371887207} 08/31/2021 04:54:24 - INFO - __main__ - Step 86977: {'lr': 0.0001922787151699874, 'samples': 16699584, 'steps': 86976, 'loss/train': 0.749630868434906} 08/31/2021 04:54:24 - INFO - __main__ - Step 86978: {'lr': 0.00019227355182149905, 'samples': 16699776, 'steps': 86977, 'loss/train': 1.2067941427230835} 08/31/2021 04:54:25 - INFO - __main__ - Step 86979: {'lr': 0.00019226838849902147, 'samples': 16699968, 'steps': 86978, 'loss/train': 0.10838828235864639} 08/31/2021 04:54:25 - INFO - __main__ - Step 86980: {'lr': 0.00019226322520255674, 'samples': 16700160, 'steps': 86979, 'loss/train': 0.8932547569274902} 08/31/2021 04:54:25 - INFO - __main__ - Step 86981: {'lr': 0.0001922580619321073, 'samples': 16700352, 'steps': 86980, 'loss/train': 1.428666353225708} 08/31/2021 04:54:27 - INFO - __main__ - Step 86982: {'lr': 0.00019225289868767553, 'samples': 16700544, 'steps': 86981, 'loss/train': 1.2295327186584473} 08/31/2021 04:54:27 - INFO - __main__ - Step 86983: {'lr': 0.0001922477354692637, 'samples': 16700736, 'steps': 86982, 'loss/train': 1.322314739227295} 08/31/2021 04:54:28 - INFO - __main__ - Step 86984: {'lr': 0.0001922425722768741, 'samples': 16700928, 'steps': 86983, 'loss/train': 0.9417511820793152} 08/31/2021 04:54:28 - INFO - __main__ - Step 86985: {'lr': 0.00019223740911050916, 'samples': 16701120, 'steps': 86984, 'loss/train': 1.0490714311599731} 08/31/2021 04:54:28 - INFO - __main__ - Step 86986: {'lr': 0.00019223224597017115, 'samples': 16701312, 'steps': 86985, 'loss/train': 1.0607441663742065} 08/31/2021 04:54:29 - INFO - __main__ - Step 86987: {'lr': 0.0001922270828558624, 'samples': 16701504, 'steps': 86986, 'loss/train': 1.4595110416412354} 08/31/2021 04:54:30 - INFO - __main__ - Step 86988: {'lr': 0.0001922219197675852, 'samples': 16701696, 'steps': 86987, 'loss/train': 1.0451390743255615} 08/31/2021 04:54:31 - INFO - __main__ - Step 86989: {'lr': 0.0001922167567053419, 'samples': 16701888, 'steps': 86988, 'loss/train': 0.20374271273612976} 08/31/2021 04:54:31 - INFO - __main__ - Step 86990: {'lr': 0.00019221159366913487, 'samples': 16702080, 'steps': 86989, 'loss/train': 0.708710789680481} 08/31/2021 04:54:31 - INFO - __main__ - Step 86991: {'lr': 0.00019220643065896638, 'samples': 16702272, 'steps': 86990, 'loss/train': 1.2636500597000122} 08/31/2021 04:54:32 - INFO - __main__ - Step 86992: {'lr': 0.0001922012676748388, 'samples': 16702464, 'steps': 86991, 'loss/train': 1.062809944152832} 08/31/2021 04:54:33 - INFO - __main__ - Step 86993: {'lr': 0.00019219610471675458, 'samples': 16702656, 'steps': 86992, 'loss/train': 0.9661100506782532} 08/31/2021 04:54:34 - INFO - __main__ - Step 86994: {'lr': 0.00019219094178471574, 'samples': 16702848, 'steps': 86993, 'loss/train': 1.3814465999603271} 08/31/2021 04:54:34 - INFO - __main__ - Step 86995: {'lr': 0.0001921857788787248, 'samples': 16703040, 'steps': 86994, 'loss/train': 1.2426917552947998} 08/31/2021 04:54:34 - INFO - __main__ - Step 86996: {'lr': 0.00019218061599878407, 'samples': 16703232, 'steps': 86995, 'loss/train': 1.794305682182312} 08/31/2021 04:54:35 - INFO - __main__ - Step 86997: {'lr': 0.00019217545314489582, 'samples': 16703424, 'steps': 86996, 'loss/train': 1.0332448482513428} 08/31/2021 04:54:37 - INFO - __main__ - Step 86998: {'lr': 0.00019217029031706243, 'samples': 16703616, 'steps': 86997, 'loss/train': 1.2025272846221924} 08/31/2021 04:54:37 - INFO - __main__ - Step 86999: {'lr': 0.00019216512751528623, 'samples': 16703808, 'steps': 86998, 'loss/train': 1.6350897550582886} 08/31/2021 04:54:38 - INFO - __main__ - Step 87000: {'lr': 0.0001921599647395695, 'samples': 16704000, 'steps': 86999, 'loss/train': 0.37507468461990356} 08/31/2021 04:54:38 - INFO - __main__ - Step 87001: {'lr': 0.00019215480198991463, 'samples': 16704192, 'steps': 87000, 'loss/train': 1.3630588054656982} 08/31/2021 04:54:38 - INFO - __main__ - Step 87002: {'lr': 0.0001921496392663239, 'samples': 16704384, 'steps': 87001, 'loss/train': 1.117529034614563} 08/31/2021 04:54:39 - INFO - __main__ - Step 87003: {'lr': 0.00019214447656879966, 'samples': 16704576, 'steps': 87002, 'loss/train': 0.21791505813598633} 08/31/2021 04:54:39 - INFO - __main__ - Step 87004: {'lr': 0.0001921393138973442, 'samples': 16704768, 'steps': 87003, 'loss/train': 0.1299220323562622} 08/31/2021 04:54:41 - INFO - __main__ - Step 87005: {'lr': 0.0001921341512519599, 'samples': 16704960, 'steps': 87004, 'loss/train': 1.6452140808105469} 08/31/2021 04:54:42 - INFO - __main__ - Step 87006: {'lr': 0.00019212898863264915, 'samples': 16705152, 'steps': 87005, 'loss/train': 0.7346314787864685} 08/31/2021 04:54:42 - INFO - __main__ - Step 87007: {'lr': 0.00019212382603941408, 'samples': 16705344, 'steps': 87006, 'loss/train': 0.9408602118492126} 08/31/2021 04:54:43 - INFO - __main__ - Step 87008: {'lr': 0.00019211866347225716, 'samples': 16705536, 'steps': 87007, 'loss/train': 0.11046716570854187} 08/31/2021 04:54:43 - INFO - __main__ - Step 87009: {'lr': 0.00019211350093118062, 'samples': 16705728, 'steps': 87008, 'loss/train': 1.3729737997055054} 08/31/2021 04:54:44 - INFO - __main__ - Step 87010: {'lr': 0.00019210833841618686, 'samples': 16705920, 'steps': 87009, 'loss/train': 0.6305505037307739} 08/31/2021 04:54:45 - INFO - __main__ - Step 87011: {'lr': 0.00019210317592727823, 'samples': 16706112, 'steps': 87010, 'loss/train': 1.2116775512695312} 08/31/2021 04:54:45 - INFO - __main__ - Step 87012: {'lr': 0.00019209801346445696, 'samples': 16706304, 'steps': 87011, 'loss/train': 1.1521310806274414} 08/31/2021 04:54:45 - INFO - __main__ - Step 87013: {'lr': 0.00019209285102772544, 'samples': 16706496, 'steps': 87012, 'loss/train': 0.7372493147850037} 08/31/2021 04:54:46 - INFO - __main__ - Step 87014: {'lr': 0.000192087688617086, 'samples': 16706688, 'steps': 87013, 'loss/train': 1.299773097038269} 08/31/2021 04:54:47 - INFO - __main__ - Step 87015: {'lr': 0.00019208252623254096, 'samples': 16706880, 'steps': 87014, 'loss/train': 1.5614744424819946} 08/31/2021 04:54:48 - INFO - __main__ - Step 87016: {'lr': 0.00019207736387409264, 'samples': 16707072, 'steps': 87015, 'loss/train': 1.569230318069458} 08/31/2021 04:54:48 - INFO - __main__ - Step 87017: {'lr': 0.00019207220154174336, 'samples': 16707264, 'steps': 87016, 'loss/train': 0.8716436624526978} 08/31/2021 04:54:48 - INFO - __main__ - Step 87018: {'lr': 0.00019206703923549544, 'samples': 16707456, 'steps': 87017, 'loss/train': 0.14153017103672028} 08/31/2021 04:54:49 - INFO - __main__ - Step 87019: {'lr': 0.00019206187695535134, 'samples': 16707648, 'steps': 87018, 'loss/train': 1.4459364414215088} 08/31/2021 04:54:50 - INFO - __main__ - Step 87020: {'lr': 0.00019205671470131318, 'samples': 16707840, 'steps': 87019, 'loss/train': 0.44774889945983887} 08/31/2021 04:54:51 - INFO - __main__ - Step 87021: {'lr': 0.00019205155247338333, 'samples': 16708032, 'steps': 87020, 'loss/train': 0.9972495436668396} 08/31/2021 04:54:51 - INFO - __main__ - Step 87022: {'lr': 0.00019204639027156417, 'samples': 16708224, 'steps': 87021, 'loss/train': 0.542634904384613} 08/31/2021 04:54:52 - INFO - __main__ - Step 87023: {'lr': 0.000192041228095858, 'samples': 16708416, 'steps': 87022, 'loss/train': 0.18815065920352936} 08/31/2021 04:54:52 - INFO - __main__ - Step 87024: {'lr': 0.0001920360659462672, 'samples': 16708608, 'steps': 87023, 'loss/train': 1.2260043621063232} 08/31/2021 04:54:54 - INFO - __main__ - Step 87025: {'lr': 0.000192030903822794, 'samples': 16708800, 'steps': 87024, 'loss/train': 1.3745931386947632} 08/31/2021 04:54:54 - INFO - __main__ - Step 87026: {'lr': 0.00019202574172544082, 'samples': 16708992, 'steps': 87025, 'loss/train': 1.4381790161132812} 08/31/2021 04:54:54 - INFO - __main__ - Step 87027: {'lr': 0.00019202057965420993, 'samples': 16709184, 'steps': 87026, 'loss/train': 1.1903852224349976} 08/31/2021 04:54:55 - INFO - __main__ - Step 87028: {'lr': 0.00019201541760910368, 'samples': 16709376, 'steps': 87027, 'loss/train': 0.9849291443824768} 08/31/2021 04:54:55 - INFO - __main__ - Step 87029: {'lr': 0.00019201025559012437, 'samples': 16709568, 'steps': 87028, 'loss/train': 0.8943513035774231} 08/31/2021 04:54:55 - INFO - __main__ - Step 87030: {'lr': 0.00019200509359727436, 'samples': 16709760, 'steps': 87029, 'loss/train': 0.9558135867118835} 08/31/2021 04:54:57 - INFO - __main__ - Step 87031: {'lr': 0.00019199993163055595, 'samples': 16709952, 'steps': 87030, 'loss/train': 0.4871996343135834} 08/31/2021 04:54:57 - INFO - __main__ - Step 87032: {'lr': 0.00019199476968997147, 'samples': 16710144, 'steps': 87031, 'loss/train': 1.207826852798462} 08/31/2021 04:54:58 - INFO - __main__ - Step 87033: {'lr': 0.00019198960777552337, 'samples': 16710336, 'steps': 87032, 'loss/train': 0.8509449362754822} 08/31/2021 04:54:58 - INFO - __main__ - Step 87034: {'lr': 0.00019198444588721379, 'samples': 16710528, 'steps': 87033, 'loss/train': 1.0728739500045776} 08/31/2021 04:54:59 - INFO - __main__ - Step 87035: {'lr': 0.00019197928402504505, 'samples': 16710720, 'steps': 87034, 'loss/train': 1.687317967414856} 08/31/2021 04:55:01 - INFO - __main__ - Step 87036: {'lr': 0.00019197412218901962, 'samples': 16710912, 'steps': 87035, 'loss/train': 0.8436697125434875} 08/31/2021 04:55:01 - INFO - __main__ - Step 87037: {'lr': 0.0001919689603791397, 'samples': 16711104, 'steps': 87036, 'loss/train': 0.7761732339859009} 08/31/2021 04:55:01 - INFO - __main__ - Step 87038: {'lr': 0.0001919637985954077, 'samples': 16711296, 'steps': 87037, 'loss/train': 0.07945263385772705} 08/31/2021 04:55:02 - INFO - __main__ - Step 87039: {'lr': 0.00019195863683782588, 'samples': 16711488, 'steps': 87038, 'loss/train': 1.407077670097351} 08/31/2021 04:55:02 - INFO - __main__ - Step 87040: {'lr': 0.00019195347510639666, 'samples': 16711680, 'steps': 87039, 'loss/train': 0.881497859954834} 08/31/2021 04:55:02 - INFO - __main__ - Step 87041: {'lr': 0.00019194831340112227, 'samples': 16711872, 'steps': 87040, 'loss/train': 0.75943922996521} 08/31/2021 04:55:04 - INFO - __main__ - Step 87042: {'lr': 0.00019194315172200508, 'samples': 16712064, 'steps': 87041, 'loss/train': 1.147861361503601} 08/31/2021 04:55:05 - INFO - __main__ - Step 87043: {'lr': 0.0001919379900690474, 'samples': 16712256, 'steps': 87042, 'loss/train': 0.8033968806266785} 08/31/2021 04:55:05 - INFO - __main__ - Step 87044: {'lr': 0.00019193282844225164, 'samples': 16712448, 'steps': 87043, 'loss/train': 1.2180932760238647} 08/31/2021 04:55:05 - INFO - __main__ - Step 87045: {'lr': 0.00019192766684162, 'samples': 16712640, 'steps': 87044, 'loss/train': 0.8000372052192688} 08/31/2021 04:55:06 - INFO - __main__ - Step 87046: {'lr': 0.00019192250526715488, 'samples': 16712832, 'steps': 87045, 'loss/train': 0.8201853036880493} 08/31/2021 04:55:07 - INFO - __main__ - Step 87047: {'lr': 0.00019191734371885855, 'samples': 16713024, 'steps': 87046, 'loss/train': 0.5026364922523499} 08/31/2021 04:55:08 - INFO - __main__ - Step 87048: {'lr': 0.00019191218219673337, 'samples': 16713216, 'steps': 87047, 'loss/train': 1.460425615310669} 08/31/2021 04:55:08 - INFO - __main__ - Step 87049: {'lr': 0.00019190702070078167, 'samples': 16713408, 'steps': 87048, 'loss/train': 1.0459650754928589} 08/31/2021 04:55:08 - INFO - __main__ - Step 87050: {'lr': 0.00019190185923100578, 'samples': 16713600, 'steps': 87049, 'loss/train': 0.718872606754303} 08/31/2021 04:55:09 - INFO - __main__ - Step 87051: {'lr': 0.00019189669778740798, 'samples': 16713792, 'steps': 87050, 'loss/train': 0.9684431552886963} 08/31/2021 04:55:09 - INFO - __main__ - Step 87052: {'lr': 0.00019189153636999066, 'samples': 16713984, 'steps': 87051, 'loss/train': 1.2163994312286377} 08/31/2021 04:55:11 - INFO - __main__ - Step 87053: {'lr': 0.0001918863749787561, 'samples': 16714176, 'steps': 87052, 'loss/train': 1.3360008001327515} 08/31/2021 04:55:11 - INFO - __main__ - Step 87054: {'lr': 0.00019188121361370664, 'samples': 16714368, 'steps': 87053, 'loss/train': 1.8026032447814941} 08/31/2021 04:55:12 - INFO - __main__ - Step 87055: {'lr': 0.00019187605227484467, 'samples': 16714560, 'steps': 87054, 'loss/train': 1.6983102560043335} 08/31/2021 04:55:12 - INFO - __main__ - Step 87056: {'lr': 0.0001918708909621724, 'samples': 16714752, 'steps': 87055, 'loss/train': 0.058056604117155075} 08/31/2021 04:55:12 - INFO - __main__ - Step 87057: {'lr': 0.0001918657296756922, 'samples': 16714944, 'steps': 87056, 'loss/train': 0.6903667449951172} 08/31/2021 04:55:13 - INFO - __main__ - Step 87058: {'lr': 0.00019186056841540645, 'samples': 16715136, 'steps': 87057, 'loss/train': 1.3383922576904297} 08/31/2021 04:55:13 - INFO - __main__ - Step 87059: {'lr': 0.0001918554071813174, 'samples': 16715328, 'steps': 87058, 'loss/train': 1.4642446041107178} 08/31/2021 04:55:15 - INFO - __main__ - Step 87060: {'lr': 0.00019185024597342742, 'samples': 16715520, 'steps': 87059, 'loss/train': 0.904654860496521} 08/31/2021 04:55:15 - INFO - __main__ - Step 87061: {'lr': 0.00019184508479173885, 'samples': 16715712, 'steps': 87060, 'loss/train': 0.5323853492736816} 08/31/2021 04:55:16 - INFO - __main__ - Step 87062: {'lr': 0.00019183992363625392, 'samples': 16715904, 'steps': 87061, 'loss/train': 0.7440147995948792} 08/31/2021 04:55:16 - INFO - __main__ - Step 87063: {'lr': 0.00019183476250697503, 'samples': 16716096, 'steps': 87062, 'loss/train': 1.6955732107162476} 08/31/2021 04:55:16 - INFO - __main__ - Step 87064: {'lr': 0.00019182960140390454, 'samples': 16716288, 'steps': 87063, 'loss/train': 1.0769039392471313} 08/31/2021 04:55:18 - INFO - __main__ - Step 87065: {'lr': 0.0001918244403270447, 'samples': 16716480, 'steps': 87064, 'loss/train': 0.9481585621833801} 08/31/2021 04:55:19 - INFO - __main__ - Step 87066: {'lr': 0.0001918192792763979, 'samples': 16716672, 'steps': 87065, 'loss/train': 1.089992880821228} 08/31/2021 04:55:19 - INFO - __main__ - Step 87067: {'lr': 0.00019181411825196644, 'samples': 16716864, 'steps': 87066, 'loss/train': 1.0026878118515015} 08/31/2021 04:55:19 - INFO - __main__ - Step 87068: {'lr': 0.0001918089572537526, 'samples': 16717056, 'steps': 87067, 'loss/train': 1.1695687770843506} 08/31/2021 04:55:20 - INFO - __main__ - Step 87069: {'lr': 0.00019180379628175879, 'samples': 16717248, 'steps': 87068, 'loss/train': 0.027262723073363304} 08/31/2021 04:55:22 - INFO - __main__ - Step 87070: {'lr': 0.00019179863533598724, 'samples': 16717440, 'steps': 87069, 'loss/train': 1.3561147451400757} 08/31/2021 04:55:22 - INFO - __main__ - Step 87071: {'lr': 0.00019179347441644035, 'samples': 16717632, 'steps': 87070, 'loss/train': 1.16355299949646} 08/31/2021 04:55:23 - INFO - __main__ - Step 87072: {'lr': 0.00019178831352312042, 'samples': 16717824, 'steps': 87071, 'loss/train': 1.4854309558868408} 08/31/2021 04:55:23 - INFO - __main__ - Step 87073: {'lr': 0.00019178315265602983, 'samples': 16718016, 'steps': 87072, 'loss/train': 0.06561987102031708} 08/31/2021 04:55:23 - INFO - __main__ - Step 87074: {'lr': 0.0001917779918151708, 'samples': 16718208, 'steps': 87073, 'loss/train': 1.3329473733901978} 08/31/2021 04:55:24 - INFO - __main__ - Step 87075: {'lr': 0.0001917728310005457, 'samples': 16718400, 'steps': 87074, 'loss/train': 0.7483730912208557} 08/31/2021 04:55:25 - INFO - __main__ - Step 87076: {'lr': 0.00019176767021215693, 'samples': 16718592, 'steps': 87075, 'loss/train': 0.03911340609192848} 08/31/2021 04:55:26 - INFO - __main__ - Step 87077: {'lr': 0.0001917625094500067, 'samples': 16718784, 'steps': 87076, 'loss/train': 1.0971893072128296} 08/31/2021 04:55:26 - INFO - __main__ - Step 87078: {'lr': 0.0001917573487140974, 'samples': 16718976, 'steps': 87077, 'loss/train': 0.9475259780883789} 08/31/2021 04:55:26 - INFO - __main__ - Step 87079: {'lr': 0.00019175218800443128, 'samples': 16719168, 'steps': 87078, 'loss/train': 0.7732200026512146} 08/31/2021 04:55:27 - INFO - __main__ - Step 87080: {'lr': 0.0001917470273210108, 'samples': 16719360, 'steps': 87079, 'loss/train': 1.1334813833236694} 08/31/2021 04:55:28 - INFO - __main__ - Step 87081: {'lr': 0.00019174186666383813, 'samples': 16719552, 'steps': 87080, 'loss/train': 1.4763201475143433} 08/31/2021 04:55:29 - INFO - __main__ - Step 87082: {'lr': 0.00019173670603291575, 'samples': 16719744, 'steps': 87081, 'loss/train': 0.6281802654266357} 08/31/2021 04:55:29 - INFO - __main__ - Step 87083: {'lr': 0.00019173154542824586, 'samples': 16719936, 'steps': 87082, 'loss/train': 0.9041939377784729} 08/31/2021 04:55:29 - INFO - __main__ - Step 87084: {'lr': 0.00019172638484983085, 'samples': 16720128, 'steps': 87083, 'loss/train': 1.2059104442596436} 08/31/2021 04:55:30 - INFO - __main__ - Step 87085: {'lr': 0.00019172122429767305, 'samples': 16720320, 'steps': 87084, 'loss/train': 1.2089956998825073} 08/31/2021 04:55:31 - INFO - __main__ - Step 87086: {'lr': 0.00019171606377177476, 'samples': 16720512, 'steps': 87085, 'loss/train': 1.4877198934555054} 08/31/2021 04:55:32 - INFO - __main__ - Step 87087: {'lr': 0.00019171090327213842, 'samples': 16720704, 'steps': 87086, 'loss/train': 2.9909067153930664} 08/31/2021 04:55:32 - INFO - __main__ - Step 87088: {'lr': 0.00019170574279876612, 'samples': 16720896, 'steps': 87087, 'loss/train': 1.3027952909469604} 08/31/2021 04:55:32 - INFO - __main__ - Step 87089: {'lr': 0.00019170058235166033, 'samples': 16721088, 'steps': 87088, 'loss/train': 1.0045524835586548} 08/31/2021 04:55:33 - INFO - __main__ - Step 87090: {'lr': 0.00019169542193082334, 'samples': 16721280, 'steps': 87089, 'loss/train': 1.4140417575836182} 08/31/2021 04:55:34 - INFO - __main__ - Step 87091: {'lr': 0.00019169026153625752, 'samples': 16721472, 'steps': 87090, 'loss/train': 1.7735745906829834} 08/31/2021 04:55:35 - INFO - __main__ - Step 87092: {'lr': 0.00019168510116796518, 'samples': 16721664, 'steps': 87091, 'loss/train': 1.468076229095459} 08/31/2021 04:55:35 - INFO - __main__ - Step 87093: {'lr': 0.00019167994082594858, 'samples': 16721856, 'steps': 87092, 'loss/train': 1.3147997856140137} 08/31/2021 04:55:35 - INFO - __main__ - Step 87094: {'lr': 0.00019167478051021014, 'samples': 16722048, 'steps': 87093, 'loss/train': 0.9789337515830994} 08/31/2021 04:55:36 - INFO - __main__ - Step 87095: {'lr': 0.00019166962022075214, 'samples': 16722240, 'steps': 87094, 'loss/train': 0.6771771311759949} 08/31/2021 04:55:37 - INFO - __main__ - Step 87096: {'lr': 0.00019166445995757688, 'samples': 16722432, 'steps': 87095, 'loss/train': 1.272554874420166} 08/31/2021 04:55:38 - INFO - __main__ - Step 87097: {'lr': 0.00019165929972068675, 'samples': 16722624, 'steps': 87096, 'loss/train': 0.9931771159172058} 08/31/2021 04:55:38 - INFO - __main__ - Step 87098: {'lr': 0.00019165413951008405, 'samples': 16722816, 'steps': 87097, 'loss/train': 0.9081915616989136} 08/31/2021 04:55:38 - INFO - __main__ - Step 87099: {'lr': 0.00019164897932577105, 'samples': 16723008, 'steps': 87098, 'loss/train': 1.5524842739105225} 08/31/2021 04:55:39 - INFO - __main__ - Step 87100: {'lr': 0.00019164381916775026, 'samples': 16723200, 'steps': 87099, 'loss/train': 1.4988703727722168} 08/31/2021 04:55:40 - INFO - __main__ - Step 87101: {'lr': 0.00019163865903602372, 'samples': 16723392, 'steps': 87100, 'loss/train': 1.9088079929351807} 08/31/2021 04:55:41 - INFO - __main__ - Step 87102: {'lr': 0.00019163349893059392, 'samples': 16723584, 'steps': 87101, 'loss/train': 1.7102147340774536} 08/31/2021 04:55:41 - INFO - __main__ - Step 87103: {'lr': 0.0001916283388514632, 'samples': 16723776, 'steps': 87102, 'loss/train': 1.4689472913742065} 08/31/2021 04:55:41 - INFO - __main__ - Step 87104: {'lr': 0.00019162317879863378, 'samples': 16723968, 'steps': 87103, 'loss/train': 1.071472406387329} 08/31/2021 04:55:42 - INFO - __main__ - Step 87105: {'lr': 0.00019161801877210812, 'samples': 16724160, 'steps': 87104, 'loss/train': 0.9262034893035889} 08/31/2021 04:55:43 - INFO - __main__ - Step 87106: {'lr': 0.00019161285877188845, 'samples': 16724352, 'steps': 87105, 'loss/train': 1.519302487373352} 08/31/2021 04:55:44 - INFO - __main__ - Step 87107: {'lr': 0.00019160769879797714, 'samples': 16724544, 'steps': 87106, 'loss/train': 1.4312875270843506} 08/31/2021 04:55:44 - INFO - __main__ - Step 87108: {'lr': 0.00019160253885037646, 'samples': 16724736, 'steps': 87107, 'loss/train': 1.2695825099945068} 08/31/2021 04:55:44 - INFO - __main__ - Step 87109: {'lr': 0.0001915973789290888, 'samples': 16724928, 'steps': 87108, 'loss/train': 1.2497762441635132} 08/31/2021 04:55:45 - INFO - __main__ - Step 87110: {'lr': 0.00019159221903411648, 'samples': 16725120, 'steps': 87109, 'loss/train': 0.8796913623809814} 08/31/2021 04:55:47 - INFO - __main__ - Step 87111: {'lr': 0.00019158705916546176, 'samples': 16725312, 'steps': 87110, 'loss/train': 1.3172003030776978} 08/31/2021 04:55:47 - INFO - __main__ - Step 87112: {'lr': 0.00019158189932312706, 'samples': 16725504, 'steps': 87111, 'loss/train': 1.5225632190704346} 08/31/2021 04:55:48 - INFO - __main__ - Step 87113: {'lr': 0.00019157673950711464, 'samples': 16725696, 'steps': 87112, 'loss/train': 0.7111274600028992} 08/31/2021 04:55:48 - INFO - __main__ - Step 87114: {'lr': 0.00019157157971742692, 'samples': 16725888, 'steps': 87113, 'loss/train': 0.6668897271156311} 08/31/2021 04:55:48 - INFO - __main__ - Step 87115: {'lr': 0.00019156641995406604, 'samples': 16726080, 'steps': 87114, 'loss/train': 0.9401153326034546} 08/31/2021 04:55:50 - INFO - __main__ - Step 87116: {'lr': 0.00019156126021703445, 'samples': 16726272, 'steps': 87115, 'loss/train': 1.5756646394729614} 08/31/2021 04:55:50 - INFO - __main__ - Step 87117: {'lr': 0.00019155610050633446, 'samples': 16726464, 'steps': 87116, 'loss/train': 0.1499294489622116} 08/31/2021 04:55:51 - INFO - __main__ - Step 87118: {'lr': 0.0001915509408219684, 'samples': 16726656, 'steps': 87117, 'loss/train': 1.4432686567306519} 08/31/2021 04:55:51 - INFO - __main__ - Step 87119: {'lr': 0.00019154578116393854, 'samples': 16726848, 'steps': 87118, 'loss/train': 1.6170505285263062} 08/31/2021 04:55:51 - INFO - __main__ - Step 87120: {'lr': 0.00019154062153224727, 'samples': 16727040, 'steps': 87119, 'loss/train': 1.5285780429840088} 08/31/2021 04:55:53 - INFO - __main__ - Step 87121: {'lr': 0.0001915354619268969, 'samples': 16727232, 'steps': 87120, 'loss/train': 1.205583930015564} 08/31/2021 04:55:54 - INFO - __main__ - Step 87122: {'lr': 0.00019153030234788973, 'samples': 16727424, 'steps': 87121, 'loss/train': 0.9664940237998962} 08/31/2021 04:55:54 - INFO - __main__ - Step 87123: {'lr': 0.00019152514279522815, 'samples': 16727616, 'steps': 87122, 'loss/train': 1.7736756801605225} 08/31/2021 04:55:54 - INFO - __main__ - Step 87124: {'lr': 0.0001915199832689144, 'samples': 16727808, 'steps': 87123, 'loss/train': 0.7761889696121216} 08/31/2021 04:55:55 - INFO - __main__ - Step 87125: {'lr': 0.00019151482376895086, 'samples': 16728000, 'steps': 87124, 'loss/train': 1.3637019395828247} 08/31/2021 04:55:56 - INFO - __main__ - Step 87126: {'lr': 0.00019150966429533982, 'samples': 16728192, 'steps': 87125, 'loss/train': 1.590166449546814} 08/31/2021 04:55:57 - INFO - __main__ - Step 87127: {'lr': 0.00019150450484808375, 'samples': 16728384, 'steps': 87126, 'loss/train': 1.1929821968078613} 08/31/2021 04:55:57 - INFO - __main__ - Step 87128: {'lr': 0.0001914993454271847, 'samples': 16728576, 'steps': 87127, 'loss/train': 1.4955024719238281} 08/31/2021 04:55:58 - INFO - __main__ - Step 87129: {'lr': 0.0001914941860326452, 'samples': 16728768, 'steps': 87128, 'loss/train': 1.5494080781936646} 08/31/2021 04:55:58 - INFO - __main__ - Step 87130: {'lr': 0.00019148902666446746, 'samples': 16728960, 'steps': 87129, 'loss/train': 1.0050888061523438} 08/31/2021 04:56:00 - INFO - __main__ - Step 87131: {'lr': 0.00019148386732265388, 'samples': 16729152, 'steps': 87130, 'loss/train': 1.0727920532226562} 08/31/2021 04:56:00 - INFO - __main__ - Step 87132: {'lr': 0.0001914787080072068, 'samples': 16729344, 'steps': 87131, 'loss/train': 0.0845966562628746} 08/31/2021 04:56:00 - INFO - __main__ - Step 87133: {'lr': 0.00019147354871812847, 'samples': 16729536, 'steps': 87132, 'loss/train': 0.927153468132019} 08/31/2021 04:56:01 - INFO - __main__ - Step 87134: {'lr': 0.00019146838945542129, 'samples': 16729728, 'steps': 87133, 'loss/train': 0.6407215595245361} 08/31/2021 04:56:01 - INFO - __main__ - Step 87135: {'lr': 0.0001914632302190875, 'samples': 16729920, 'steps': 87134, 'loss/train': 1.5624374151229858} 08/31/2021 04:56:01 - INFO - __main__ - Step 87136: {'lr': 0.00019145807100912952, 'samples': 16730112, 'steps': 87135, 'loss/train': 1.3482917547225952} 08/31/2021 04:56:03 - INFO - __main__ - Step 87137: {'lr': 0.0001914529118255496, 'samples': 16730304, 'steps': 87136, 'loss/train': 0.6556650996208191} 08/31/2021 04:56:04 - INFO - __main__ - Step 87138: {'lr': 0.00019144775266835012, 'samples': 16730496, 'steps': 87137, 'loss/train': 0.7782500982284546} 08/31/2021 04:56:04 - INFO - __main__ - Step 87139: {'lr': 0.00019144259353753339, 'samples': 16730688, 'steps': 87138, 'loss/train': 0.8064630627632141} 08/31/2021 04:56:04 - INFO - __main__ - Step 87140: {'lr': 0.0001914374344331018, 'samples': 16730880, 'steps': 87139, 'loss/train': 0.15521477162837982} 08/31/2021 04:56:05 - INFO - __main__ - Step 87141: {'lr': 0.0001914322753550575, 'samples': 16731072, 'steps': 87140, 'loss/train': 1.888177752494812} 08/31/2021 04:56:06 - INFO - __main__ - Step 87142: {'lr': 0.00019142711630340293, 'samples': 16731264, 'steps': 87141, 'loss/train': 0.7206213474273682} 08/31/2021 04:56:06 - INFO - __main__ - Step 87143: {'lr': 0.00019142195727814038, 'samples': 16731456, 'steps': 87142, 'loss/train': 1.2332948446273804} 08/31/2021 04:56:07 - INFO - __main__ - Step 87144: {'lr': 0.0001914167982792722, 'samples': 16731648, 'steps': 87143, 'loss/train': 0.6754763126373291} 08/31/2021 04:56:07 - INFO - __main__ - Step 87145: {'lr': 0.0001914116393068007, 'samples': 16731840, 'steps': 87144, 'loss/train': 0.8584535717964172} 08/31/2021 04:56:08 - INFO - __main__ - Step 87146: {'lr': 0.00019140648036072822, 'samples': 16732032, 'steps': 87145, 'loss/train': 1.418512225151062} 08/31/2021 04:56:09 - INFO - __main__ - Step 87147: {'lr': 0.00019140132144105705, 'samples': 16732224, 'steps': 87146, 'loss/train': 1.7625459432601929} 08/31/2021 04:56:09 - INFO - __main__ - Step 87148: {'lr': 0.00019139616254778958, 'samples': 16732416, 'steps': 87147, 'loss/train': 1.41298246383667} 08/31/2021 04:56:10 - INFO - __main__ - Step 87149: {'lr': 0.00019139100368092805, 'samples': 16732608, 'steps': 87148, 'loss/train': 1.145256519317627} 08/31/2021 04:56:10 - INFO - __main__ - Step 87150: {'lr': 0.00019138584484047487, 'samples': 16732800, 'steps': 87149, 'loss/train': 1.0106911659240723} 08/31/2021 04:56:11 - INFO - __main__ - Step 87151: {'lr': 0.0001913806860264323, 'samples': 16732992, 'steps': 87150, 'loss/train': 1.4106478691101074} 08/31/2021 04:56:12 - INFO - __main__ - Step 87152: {'lr': 0.0001913755272388027, 'samples': 16733184, 'steps': 87151, 'loss/train': 1.68027663230896} 08/31/2021 04:56:12 - INFO - __main__ - Step 87153: {'lr': 0.00019137036847758837, 'samples': 16733376, 'steps': 87152, 'loss/train': 1.2115761041641235} 08/31/2021 04:56:13 - INFO - __main__ - Step 87154: {'lr': 0.00019136520974279175, 'samples': 16733568, 'steps': 87153, 'loss/train': 1.2367149591445923} 08/31/2021 04:56:13 - INFO - __main__ - Step 87155: {'lr': 0.00019136005103441499, 'samples': 16733760, 'steps': 87154, 'loss/train': 0.7387121915817261} 08/31/2021 04:56:13 - INFO - __main__ - Step 87156: {'lr': 0.00019135489235246045, 'samples': 16733952, 'steps': 87155, 'loss/train': 0.2023647129535675} 08/31/2021 04:56:15 - INFO - __main__ - Step 87157: {'lr': 0.00019134973369693052, 'samples': 16734144, 'steps': 87156, 'loss/train': 0.665708065032959} 08/31/2021 04:56:15 - INFO - __main__ - Step 87158: {'lr': 0.00019134457506782748, 'samples': 16734336, 'steps': 87157, 'loss/train': 1.2080310583114624} 08/31/2021 04:56:16 - INFO - __main__ - Step 87159: {'lr': 0.00019133941646515368, 'samples': 16734528, 'steps': 87158, 'loss/train': 0.7837457656860352} 08/31/2021 04:56:16 - INFO - __main__ - Step 87160: {'lr': 0.0001913342578889114, 'samples': 16734720, 'steps': 87159, 'loss/train': 1.3355083465576172} 08/31/2021 04:56:16 - INFO - __main__ - Step 87161: {'lr': 0.00019132909933910304, 'samples': 16734912, 'steps': 87160, 'loss/train': 1.2719457149505615} 08/31/2021 04:56:18 - INFO - __main__ - Step 87162: {'lr': 0.00019132394081573085, 'samples': 16735104, 'steps': 87161, 'loss/train': 1.4506055116653442} 08/31/2021 04:56:19 - INFO - __main__ - Step 87163: {'lr': 0.0001913187823187972, 'samples': 16735296, 'steps': 87162, 'loss/train': 1.2713702917099} 08/31/2021 04:56:19 - INFO - __main__ - Step 87164: {'lr': 0.00019131362384830443, 'samples': 16735488, 'steps': 87163, 'loss/train': 1.011196494102478} 08/31/2021 04:56:19 - INFO - __main__ - Step 87165: {'lr': 0.00019130846540425477, 'samples': 16735680, 'steps': 87164, 'loss/train': 1.5216834545135498} 08/31/2021 04:56:20 - INFO - __main__ - Step 87166: {'lr': 0.00019130330698665065, 'samples': 16735872, 'steps': 87165, 'loss/train': 1.0582033395767212} 08/31/2021 04:56:20 - INFO - __main__ - Step 87167: {'lr': 0.00019129814859549445, 'samples': 16736064, 'steps': 87166, 'loss/train': 0.7606630325317383} 08/31/2021 04:56:22 - INFO - __main__ - Step 87168: {'lr': 0.00019129299023078831, 'samples': 16736256, 'steps': 87167, 'loss/train': 0.05380095914006233} 08/31/2021 04:56:22 - INFO - __main__ - Step 87169: {'lr': 0.00019128783189253462, 'samples': 16736448, 'steps': 87168, 'loss/train': 0.9449707269668579} 08/31/2021 04:56:22 - INFO - __main__ - Step 87170: {'lr': 0.00019128267358073576, 'samples': 16736640, 'steps': 87169, 'loss/train': 1.15837562084198} 08/31/2021 04:56:23 - INFO - __main__ - Step 87171: {'lr': 0.000191277515295394, 'samples': 16736832, 'steps': 87170, 'loss/train': 0.7489791512489319} 08/31/2021 04:56:23 - INFO - __main__ - Step 87172: {'lr': 0.0001912723570365117, 'samples': 16737024, 'steps': 87171, 'loss/train': 1.799087405204773} 08/31/2021 04:56:26 - INFO - __main__ - Step 87173: {'lr': 0.00019126719880409112, 'samples': 16737216, 'steps': 87172, 'loss/train': 0.9344125390052795} 08/31/2021 04:56:26 - INFO - __main__ - Step 87174: {'lr': 0.00019126204059813468, 'samples': 16737408, 'steps': 87173, 'loss/train': 0.9330008029937744} 08/31/2021 04:56:26 - INFO - __main__ - Step 87175: {'lr': 0.00019125688241864464, 'samples': 16737600, 'steps': 87174, 'loss/train': 1.077451229095459} 08/31/2021 04:56:27 - INFO - __main__ - Step 87176: {'lr': 0.00019125172426562336, 'samples': 16737792, 'steps': 87175, 'loss/train': 0.5405447483062744} 08/31/2021 04:56:27 - INFO - __main__ - Step 87177: {'lr': 0.00019124656613907315, 'samples': 16737984, 'steps': 87176, 'loss/train': 1.224136233329773} 08/31/2021 04:56:27 - INFO - __main__ - Step 87178: {'lr': 0.00019124140803899637, 'samples': 16738176, 'steps': 87177, 'loss/train': 0.811302900314331} 08/31/2021 04:56:29 - INFO - __main__ - Step 87179: {'lr': 0.00019123624996539524, 'samples': 16738368, 'steps': 87178, 'loss/train': 0.6052725911140442} 08/31/2021 04:56:30 - INFO - __main__ - Step 87180: {'lr': 0.00019123109191827216, 'samples': 16738560, 'steps': 87179, 'loss/train': 1.3493149280548096} 08/31/2021 04:56:30 - INFO - __main__ - Step 87181: {'lr': 0.00019122593389762948, 'samples': 16738752, 'steps': 87180, 'loss/train': 1.4955228567123413} 08/31/2021 04:56:30 - INFO - __main__ - Step 87182: {'lr': 0.0001912207759034695, 'samples': 16738944, 'steps': 87181, 'loss/train': 0.027809076011180878} 08/31/2021 04:56:31 - INFO - __main__ - Step 87183: {'lr': 0.00019121561793579444, 'samples': 16739136, 'steps': 87182, 'loss/train': 1.778344988822937} 08/31/2021 04:56:32 - INFO - __main__ - Step 87184: {'lr': 0.00019121045999460676, 'samples': 16739328, 'steps': 87183, 'loss/train': 1.1918057203292847} 08/31/2021 04:56:32 - INFO - __main__ - Step 87185: {'lr': 0.00019120530207990873, 'samples': 16739520, 'steps': 87184, 'loss/train': 1.216282844543457} 08/31/2021 04:56:33 - INFO - __main__ - Step 87186: {'lr': 0.0001912001441917027, 'samples': 16739712, 'steps': 87185, 'loss/train': 1.196148157119751} 08/31/2021 04:56:33 - INFO - __main__ - Step 87187: {'lr': 0.000191194986329991, 'samples': 16739904, 'steps': 87186, 'loss/train': 0.9609034657478333} 08/31/2021 04:56:34 - INFO - __main__ - Step 87188: {'lr': 0.00019118982849477588, 'samples': 16740096, 'steps': 87187, 'loss/train': 1.2490519285202026} 08/31/2021 04:56:35 - INFO - __main__ - Step 87189: {'lr': 0.0001911846706860598, 'samples': 16740288, 'steps': 87188, 'loss/train': 1.1282187700271606} 08/31/2021 04:56:36 - INFO - __main__ - Step 87190: {'lr': 0.00019117951290384492, 'samples': 16740480, 'steps': 87189, 'loss/train': 1.3947738409042358} 08/31/2021 04:56:36 - INFO - __main__ - Step 87191: {'lr': 0.00019117435514813368, 'samples': 16740672, 'steps': 87190, 'loss/train': 0.5672881007194519} 08/31/2021 04:56:36 - INFO - __main__ - Step 87192: {'lr': 0.00019116919741892833, 'samples': 16740864, 'steps': 87191, 'loss/train': 1.0677589178085327} 08/31/2021 04:56:37 - INFO - __main__ - Step 87193: {'lr': 0.00019116403971623124, 'samples': 16741056, 'steps': 87192, 'loss/train': 0.8124350905418396} 08/31/2021 04:56:39 - INFO - __main__ - Step 87194: {'lr': 0.00019115888204004482, 'samples': 16741248, 'steps': 87193, 'loss/train': 1.427817463874817} 08/31/2021 04:56:39 - INFO - __main__ - Step 87195: {'lr': 0.0001911537243903712, 'samples': 16741440, 'steps': 87194, 'loss/train': 1.6149587631225586} 08/31/2021 04:56:39 - INFO - __main__ - Step 87196: {'lr': 0.0001911485667672128, 'samples': 16741632, 'steps': 87195, 'loss/train': 0.9640446901321411} 08/31/2021 04:56:40 - INFO - __main__ - Step 87197: {'lr': 0.000191143409170572, 'samples': 16741824, 'steps': 87196, 'loss/train': 1.89422607421875} 08/31/2021 04:56:40 - INFO - __main__ - Step 87198: {'lr': 0.00019113825160045102, 'samples': 16742016, 'steps': 87197, 'loss/train': 0.3436064124107361} 08/31/2021 04:56:40 - INFO - __main__ - Step 87199: {'lr': 0.00019113309405685225, 'samples': 16742208, 'steps': 87198, 'loss/train': 1.769856333732605} 08/31/2021 04:56:42 - INFO - __main__ - Step 87200: {'lr': 0.00019112793653977805, 'samples': 16742400, 'steps': 87199, 'loss/train': 1.5448580980300903} 08/31/2021 04:56:42 - INFO - __main__ - Step 87201: {'lr': 0.00019112277904923065, 'samples': 16742592, 'steps': 87200, 'loss/train': 1.5453966856002808} 08/31/2021 04:56:43 - INFO - __main__ - Step 87202: {'lr': 0.00019111762158521243, 'samples': 16742784, 'steps': 87201, 'loss/train': 1.5756772756576538} 08/31/2021 04:56:43 - INFO - __main__ - Step 87203: {'lr': 0.0001911124641477257, 'samples': 16742976, 'steps': 87202, 'loss/train': 0.8826466202735901} 08/31/2021 04:56:43 - INFO - __main__ - Step 87204: {'lr': 0.00019110730673677274, 'samples': 16743168, 'steps': 87203, 'loss/train': 1.0464985370635986} 08/31/2021 04:56:45 - INFO - __main__ - Step 87205: {'lr': 0.00019110214935235596, 'samples': 16743360, 'steps': 87204, 'loss/train': 0.9951457977294922} 08/31/2021 04:56:45 - INFO - __main__ - Step 87206: {'lr': 0.0001910969919944776, 'samples': 16743552, 'steps': 87205, 'loss/train': 1.1421383619308472} 08/31/2021 04:56:46 - INFO - __main__ - Step 87207: {'lr': 0.0001910918346631401, 'samples': 16743744, 'steps': 87206, 'loss/train': 0.8964880108833313} 08/31/2021 04:56:46 - INFO - __main__ - Step 87208: {'lr': 0.0001910866773583457, 'samples': 16743936, 'steps': 87207, 'loss/train': 1.9909579753875732} 08/31/2021 04:56:46 - INFO - __main__ - Step 87209: {'lr': 0.00019108152008009673, 'samples': 16744128, 'steps': 87208, 'loss/train': 1.198523998260498} 08/31/2021 04:56:48 - INFO - __main__ - Step 87210: {'lr': 0.00019107636282839546, 'samples': 16744320, 'steps': 87209, 'loss/train': 1.1764506101608276} 08/31/2021 04:56:48 - INFO - __main__ - Step 87211: {'lr': 0.00019107120560324438, 'samples': 16744512, 'steps': 87210, 'loss/train': 0.6076928973197937} 08/31/2021 04:56:49 - INFO - __main__ - Step 87212: {'lr': 0.00019106604840464562, 'samples': 16744704, 'steps': 87211, 'loss/train': 0.8801749348640442} 08/31/2021 04:56:49 - INFO - __main__ - Step 87213: {'lr': 0.00019106089123260158, 'samples': 16744896, 'steps': 87212, 'loss/train': 1.3785772323608398} 08/31/2021 04:56:49 - INFO - __main__ - Step 87214: {'lr': 0.00019105573408711464, 'samples': 16745088, 'steps': 87213, 'loss/train': 0.8618983626365662} 08/31/2021 04:56:51 - INFO - __main__ - Step 87215: {'lr': 0.000191050576968187, 'samples': 16745280, 'steps': 87214, 'loss/train': 1.4013943672180176} 08/31/2021 04:56:51 - INFO - __main__ - Step 87216: {'lr': 0.00019104541987582113, 'samples': 16745472, 'steps': 87215, 'loss/train': 1.3128372430801392} 08/31/2021 04:56:52 - INFO - __main__ - Step 87217: {'lr': 0.00019104026281001926, 'samples': 16745664, 'steps': 87216, 'loss/train': 1.1447175741195679} 08/31/2021 04:56:52 - INFO - __main__ - Step 87218: {'lr': 0.00019103510577078372, 'samples': 16745856, 'steps': 87217, 'loss/train': 1.430959939956665} 08/31/2021 04:56:52 - INFO - __main__ - Step 87219: {'lr': 0.0001910299487581169, 'samples': 16746048, 'steps': 87218, 'loss/train': 0.3431977331638336} 08/31/2021 04:56:54 - INFO - __main__ - Step 87220: {'lr': 0.00019102479177202103, 'samples': 16746240, 'steps': 87219, 'loss/train': 0.6916235685348511} 08/31/2021 04:56:55 - INFO - __main__ - Step 87221: {'lr': 0.00019101963481249853, 'samples': 16746432, 'steps': 87220, 'loss/train': 0.9144596457481384} 08/31/2021 04:56:55 - INFO - __main__ - Step 87222: {'lr': 0.0001910144778795517, 'samples': 16746624, 'steps': 87221, 'loss/train': 1.6696537733078003} 08/31/2021 04:56:55 - INFO - __main__ - Step 87223: {'lr': 0.00019100932097318278, 'samples': 16746816, 'steps': 87222, 'loss/train': 0.7653724551200867} 08/31/2021 04:56:56 - INFO - __main__ - Step 87224: {'lr': 0.00019100416409339414, 'samples': 16747008, 'steps': 87223, 'loss/train': 1.6089472770690918} 08/31/2021 04:56:58 - INFO - __main__ - Step 87225: {'lr': 0.00019099900724018812, 'samples': 16747200, 'steps': 87224, 'loss/train': 1.1475402116775513} 08/31/2021 04:56:59 - INFO - __main__ - Step 87226: {'lr': 0.00019099385041356705, 'samples': 16747392, 'steps': 87225, 'loss/train': 1.3867958784103394} 08/31/2021 04:56:59 - INFO - __main__ - Step 87227: {'lr': 0.0001909886936135332, 'samples': 16747584, 'steps': 87226, 'loss/train': 0.8334174156188965} 08/31/2021 04:56:59 - INFO - __main__ - Step 87228: {'lr': 0.00019098353684008897, 'samples': 16747776, 'steps': 87227, 'loss/train': 1.5141246318817139} 08/31/2021 04:57:00 - INFO - __main__ - Step 87229: {'lr': 0.00019097838009323663, 'samples': 16747968, 'steps': 87228, 'loss/train': 1.1399897336959839} 08/31/2021 04:57:00 - INFO - __main__ - Step 87230: {'lr': 0.00019097322337297852, 'samples': 16748160, 'steps': 87229, 'loss/train': 0.031615860760211945} 08/31/2021 04:57:01 - INFO - __main__ - Step 87231: {'lr': 0.00019096806667931695, 'samples': 16748352, 'steps': 87230, 'loss/train': 1.373029351234436} 08/31/2021 04:57:02 - INFO - __main__ - Step 87232: {'lr': 0.0001909629100122543, 'samples': 16748544, 'steps': 87231, 'loss/train': 1.102378010749817} 08/31/2021 04:57:02 - INFO - __main__ - Step 87233: {'lr': 0.00019095775337179283, 'samples': 16748736, 'steps': 87232, 'loss/train': 1.2651253938674927} 08/31/2021 04:57:03 - INFO - __main__ - Step 87234: {'lr': 0.00019095259675793488, 'samples': 16748928, 'steps': 87233, 'loss/train': 1.0246856212615967} 08/31/2021 04:57:03 - INFO - __main__ - Step 87235: {'lr': 0.00019094744017068288, 'samples': 16749120, 'steps': 87234, 'loss/train': 0.7946223616600037} 08/31/2021 04:57:03 - INFO - __main__ - Step 87236: {'lr': 0.00019094228361003895, 'samples': 16749312, 'steps': 87235, 'loss/train': 1.461676836013794} 08/31/2021 04:57:05 - INFO - __main__ - Step 87237: {'lr': 0.00019093712707600553, 'samples': 16749504, 'steps': 87236, 'loss/train': 0.8682688474655151} 08/31/2021 04:57:06 - INFO - __main__ - Step 87238: {'lr': 0.00019093197056858495, 'samples': 16749696, 'steps': 87237, 'loss/train': 1.0990650653839111} 08/31/2021 04:57:06 - INFO - __main__ - Step 87239: {'lr': 0.00019092681408777946, 'samples': 16749888, 'steps': 87238, 'loss/train': 0.03949914500117302} 08/31/2021 04:57:06 - INFO - __main__ - Step 87240: {'lr': 0.00019092165763359145, 'samples': 16750080, 'steps': 87239, 'loss/train': 1.2499897480010986} 08/31/2021 04:57:07 - INFO - __main__ - Step 87241: {'lr': 0.00019091650120602326, 'samples': 16750272, 'steps': 87240, 'loss/train': 1.2701376676559448} 08/31/2021 04:57:08 - INFO - __main__ - Step 87242: {'lr': 0.00019091134480507717, 'samples': 16750464, 'steps': 87241, 'loss/train': 1.5410544872283936} 08/31/2021 04:57:09 - INFO - __main__ - Step 87243: {'lr': 0.0001909061884307555, 'samples': 16750656, 'steps': 87242, 'loss/train': 0.6538148522377014} 08/31/2021 04:57:09 - INFO - __main__ - Step 87244: {'lr': 0.0001909010320830606, 'samples': 16750848, 'steps': 87243, 'loss/train': 1.1497951745986938} 08/31/2021 04:57:09 - INFO - __main__ - Step 87245: {'lr': 0.00019089587576199478, 'samples': 16751040, 'steps': 87244, 'loss/train': 1.1824243068695068} 08/31/2021 04:57:10 - INFO - __main__ - Step 87246: {'lr': 0.00019089071946756038, 'samples': 16751232, 'steps': 87245, 'loss/train': 1.2262749671936035} 08/31/2021 04:57:11 - INFO - __main__ - Step 87247: {'lr': 0.00019088556319975966, 'samples': 16751424, 'steps': 87246, 'loss/train': 0.7784069180488586} 08/31/2021 04:57:12 - INFO - __main__ - Step 87248: {'lr': 0.00019088040695859515, 'samples': 16751616, 'steps': 87247, 'loss/train': 2.125732421875} 08/31/2021 04:57:12 - INFO - __main__ - Step 87249: {'lr': 0.0001908752507440689, 'samples': 16751808, 'steps': 87248, 'loss/train': 0.9227509498596191} 08/31/2021 04:57:12 - INFO - __main__ - Step 87250: {'lr': 0.00019087009455618335, 'samples': 16752000, 'steps': 87249, 'loss/train': 0.778741717338562} 08/31/2021 04:57:13 - INFO - __main__ - Step 87251: {'lr': 0.0001908649383949408, 'samples': 16752192, 'steps': 87250, 'loss/train': 1.0533671379089355} 08/31/2021 04:57:14 - INFO - __main__ - Step 87252: {'lr': 0.00019085978226034362, 'samples': 16752384, 'steps': 87251, 'loss/train': 0.9477798342704773} 08/31/2021 04:57:15 - INFO - __main__ - Step 87253: {'lr': 0.00019085462615239413, 'samples': 16752576, 'steps': 87252, 'loss/train': 0.8924488425254822} 08/31/2021 04:57:15 - INFO - __main__ - Step 87254: {'lr': 0.00019084947007109459, 'samples': 16752768, 'steps': 87253, 'loss/train': 1.3680546283721924} 08/31/2021 04:57:15 - INFO - __main__ - Step 87255: {'lr': 0.00019084431401644738, 'samples': 16752960, 'steps': 87254, 'loss/train': 1.183971881866455} 08/31/2021 04:57:16 - INFO - __main__ - Step 87256: {'lr': 0.0001908391579884548, 'samples': 16753152, 'steps': 87255, 'loss/train': 0.2390296757221222} 08/31/2021 04:57:16 - INFO - __main__ - Step 87257: {'lr': 0.0001908340019871192, 'samples': 16753344, 'steps': 87256, 'loss/train': 1.3891260623931885} 08/31/2021 04:57:18 - INFO - __main__ - Step 87258: {'lr': 0.0001908288460124429, 'samples': 16753536, 'steps': 87257, 'loss/train': 0.9514842629432678} 08/31/2021 04:57:18 - INFO - __main__ - Step 87259: {'lr': 0.0001908236900644282, 'samples': 16753728, 'steps': 87258, 'loss/train': 1.4211103916168213} 08/31/2021 04:57:18 - INFO - __main__ - Step 87260: {'lr': 0.00019081853414307739, 'samples': 16753920, 'steps': 87259, 'loss/train': 0.9295938014984131} 08/31/2021 04:57:19 - INFO - __main__ - Step 87261: {'lr': 0.000190813378248393, 'samples': 16754112, 'steps': 87260, 'loss/train': 1.6079413890838623} 08/31/2021 04:57:19 - INFO - __main__ - Step 87262: {'lr': 0.00019080822238037705, 'samples': 16754304, 'steps': 87261, 'loss/train': 0.8387322425842285} 08/31/2021 04:57:21 - INFO - __main__ - Step 87263: {'lr': 0.000190803066539032, 'samples': 16754496, 'steps': 87262, 'loss/train': 1.6157130002975464} 08/31/2021 04:57:21 - INFO - __main__ - Step 87264: {'lr': 0.00019079791072436017, 'samples': 16754688, 'steps': 87263, 'loss/train': 0.6334044337272644} 08/31/2021 04:57:22 - INFO - __main__ - Step 87265: {'lr': 0.00019079275493636392, 'samples': 16754880, 'steps': 87264, 'loss/train': 1.046448826789856} 08/31/2021 04:57:22 - INFO - __main__ - Step 87266: {'lr': 0.0001907875991750455, 'samples': 16755072, 'steps': 87265, 'loss/train': 1.3291138410568237} 08/31/2021 04:57:22 - INFO - __main__ - Step 87267: {'lr': 0.0001907824434404073, 'samples': 16755264, 'steps': 87266, 'loss/train': 0.07932128012180328} 08/31/2021 04:57:24 - INFO - __main__ - Step 87268: {'lr': 0.00019077728773245163, 'samples': 16755456, 'steps': 87267, 'loss/train': 1.2243587970733643} 08/31/2021 04:57:24 - INFO - __main__ - Step 87269: {'lr': 0.00019077213205118078, 'samples': 16755648, 'steps': 87268, 'loss/train': 1.0217485427856445} 08/31/2021 04:57:24 - INFO - __main__ - Step 87270: {'lr': 0.0001907669763965971, 'samples': 16755840, 'steps': 87269, 'loss/train': 1.7560962438583374} 08/31/2021 04:57:25 - INFO - __main__ - Step 87271: {'lr': 0.00019076182076870288, 'samples': 16756032, 'steps': 87270, 'loss/train': 0.8969759345054626} 08/31/2021 04:57:25 - INFO - __main__ - Step 87272: {'lr': 0.00019075666516750052, 'samples': 16756224, 'steps': 87271, 'loss/train': 1.404345989227295} 08/31/2021 04:57:27 - INFO - __main__ - Step 87273: {'lr': 0.00019075150959299225, 'samples': 16756416, 'steps': 87272, 'loss/train': 1.2797726392745972} 08/31/2021 04:57:27 - INFO - __main__ - Step 87274: {'lr': 0.00019074635404518045, 'samples': 16756608, 'steps': 87273, 'loss/train': 0.7808676958084106} 08/31/2021 04:57:28 - INFO - __main__ - Step 87275: {'lr': 0.00019074119852406751, 'samples': 16756800, 'steps': 87274, 'loss/train': 1.372112512588501} 08/31/2021 04:57:28 - INFO - __main__ - Step 87276: {'lr': 0.0001907360430296556, 'samples': 16756992, 'steps': 87275, 'loss/train': 0.6350386142730713} 08/31/2021 04:57:28 - INFO - __main__ - Step 87277: {'lr': 0.00019073088756194713, 'samples': 16757184, 'steps': 87276, 'loss/train': 1.41512930393219} 08/31/2021 04:57:30 - INFO - __main__ - Step 87278: {'lr': 0.00019072573212094434, 'samples': 16757376, 'steps': 87277, 'loss/train': 1.06391441822052} 08/31/2021 04:57:31 - INFO - __main__ - Step 87279: {'lr': 0.00019072057670664968, 'samples': 16757568, 'steps': 87278, 'loss/train': 1.31126868724823} 08/31/2021 04:57:31 - INFO - __main__ - Step 87280: {'lr': 0.0001907154213190654, 'samples': 16757760, 'steps': 87279, 'loss/train': 1.6932884454727173} 08/31/2021 04:57:31 - INFO - __main__ - Step 87281: {'lr': 0.00019071026595819386, 'samples': 16757952, 'steps': 87280, 'loss/train': 0.7794960737228394} 08/31/2021 04:57:32 - INFO - __main__ - Step 87282: {'lr': 0.0001907051106240373, 'samples': 16758144, 'steps': 87281, 'loss/train': 0.8164147734642029} 08/31/2021 04:57:34 - INFO - __main__ - Step 87283: {'lr': 0.00019069995531659814, 'samples': 16758336, 'steps': 87282, 'loss/train': 1.4297822713851929} 08/31/2021 04:57:34 - INFO - __main__ - Step 87284: {'lr': 0.00019069480003587865, 'samples': 16758528, 'steps': 87283, 'loss/train': 1.153796672821045} 08/31/2021 04:57:34 - INFO - __main__ - Step 87285: {'lr': 0.0001906896447818812, 'samples': 16758720, 'steps': 87284, 'loss/train': 1.4771220684051514} 08/31/2021 04:57:35 - INFO - __main__ - Step 87286: {'lr': 0.00019068448955460805, 'samples': 16758912, 'steps': 87285, 'loss/train': 0.020425107330083847} 08/31/2021 04:57:35 - INFO - __main__ - Step 87287: {'lr': 0.00019067933435406155, 'samples': 16759104, 'steps': 87286, 'loss/train': 0.5155258774757385} 08/31/2021 04:57:36 - INFO - __main__ - Step 87288: {'lr': 0.00019067417918024415, 'samples': 16759296, 'steps': 87287, 'loss/train': 0.6782276630401611} 08/31/2021 04:57:37 - INFO - __main__ - Step 87289: {'lr': 0.00019066902403315795, 'samples': 16759488, 'steps': 87288, 'loss/train': 1.2977955341339111} 08/31/2021 04:57:37 - INFO - __main__ - Step 87290: {'lr': 0.00019066386891280536, 'samples': 16759680, 'steps': 87289, 'loss/train': 1.3638136386871338} 08/31/2021 04:57:38 - INFO - __main__ - Step 87291: {'lr': 0.0001906587138191887, 'samples': 16759872, 'steps': 87290, 'loss/train': 1.0765596628189087} 08/31/2021 04:57:38 - INFO - __main__ - Step 87292: {'lr': 0.00019065355875231034, 'samples': 16760064, 'steps': 87291, 'loss/train': 1.2232178449630737} 08/31/2021 04:57:38 - INFO - __main__ - Step 87293: {'lr': 0.00019064840371217255, 'samples': 16760256, 'steps': 87292, 'loss/train': 1.1067566871643066} 08/31/2021 04:57:40 - INFO - __main__ - Step 87294: {'lr': 0.00019064324869877766, 'samples': 16760448, 'steps': 87293, 'loss/train': 0.8235892057418823} 08/31/2021 04:57:40 - INFO - __main__ - Step 87295: {'lr': 0.00019063809371212804, 'samples': 16760640, 'steps': 87294, 'loss/train': 0.8246103525161743} 08/31/2021 04:57:41 - INFO - __main__ - Step 87296: {'lr': 0.00019063293875222595, 'samples': 16760832, 'steps': 87295, 'loss/train': 1.4395239353179932} 08/31/2021 04:57:41 - INFO - __main__ - Step 87297: {'lr': 0.00019062778381907376, 'samples': 16761024, 'steps': 87296, 'loss/train': 1.4359465837478638} 08/31/2021 04:57:41 - INFO - __main__ - Step 87298: {'lr': 0.00019062262891267378, 'samples': 16761216, 'steps': 87297, 'loss/train': 0.9732019901275635} 08/31/2021 04:57:42 - INFO - __main__ - Step 87299: {'lr': 0.0001906174740330283, 'samples': 16761408, 'steps': 87298, 'loss/train': 1.2960422039031982} 08/31/2021 04:57:43 - INFO - __main__ - Step 87300: {'lr': 0.00019061231918013967, 'samples': 16761600, 'steps': 87299, 'loss/train': 1.926311731338501} 08/31/2021 04:57:44 - INFO - __main__ - Step 87301: {'lr': 0.00019060716435401025, 'samples': 16761792, 'steps': 87300, 'loss/train': 0.8788306713104248} 08/31/2021 04:57:44 - INFO - __main__ - Step 87302: {'lr': 0.0001906020095546424, 'samples': 16761984, 'steps': 87301, 'loss/train': 0.6056697368621826} 08/31/2021 04:57:45 - INFO - __main__ - Step 87303: {'lr': 0.00019059685478203824, 'samples': 16762176, 'steps': 87302, 'loss/train': 1.5033246278762817} 08/31/2021 04:57:45 - INFO - __main__ - Step 87304: {'lr': 0.00019059170003620028, 'samples': 16762368, 'steps': 87303, 'loss/train': 1.0228021144866943} 08/31/2021 04:57:46 - INFO - __main__ - Step 87305: {'lr': 0.00019058654531713075, 'samples': 16762560, 'steps': 87304, 'loss/train': 1.3840692043304443} 08/31/2021 04:57:47 - INFO - __main__ - Step 87306: {'lr': 0.000190581390624832, 'samples': 16762752, 'steps': 87305, 'loss/train': 1.291624665260315} 08/31/2021 04:57:47 - INFO - __main__ - Step 87307: {'lr': 0.00019057623595930637, 'samples': 16762944, 'steps': 87306, 'loss/train': 1.7520211935043335} 08/31/2021 04:57:48 - INFO - __main__ - Step 87308: {'lr': 0.00019057108132055617, 'samples': 16763136, 'steps': 87307, 'loss/train': 1.2270368337631226} 08/31/2021 04:57:48 - INFO - __main__ - Step 87309: {'lr': 0.00019056592670858372, 'samples': 16763328, 'steps': 87308, 'loss/train': 1.4168118238449097} 08/31/2021 04:57:50 - INFO - __main__ - Step 87310: {'lr': 0.00019056077212339134, 'samples': 16763520, 'steps': 87309, 'loss/train': 0.8156211376190186} 08/31/2021 04:57:50 - INFO - __main__ - Step 87311: {'lr': 0.00019055561756498138, 'samples': 16763712, 'steps': 87310, 'loss/train': 1.4655146598815918} 08/31/2021 04:57:50 - INFO - __main__ - Step 87312: {'lr': 0.00019055046303335617, 'samples': 16763904, 'steps': 87311, 'loss/train': 1.5094006061553955} 08/31/2021 04:57:51 - INFO - __main__ - Step 87313: {'lr': 0.00019054530852851797, 'samples': 16764096, 'steps': 87312, 'loss/train': 0.8925663232803345} 08/31/2021 04:57:51 - INFO - __main__ - Step 87314: {'lr': 0.00019054015405046916, 'samples': 16764288, 'steps': 87313, 'loss/train': 0.028872787952423096} 08/31/2021 04:57:52 - INFO - __main__ - Step 87315: {'lr': 0.00019053499959921207, 'samples': 16764480, 'steps': 87314, 'loss/train': 1.3928290605545044} 08/31/2021 04:57:53 - INFO - __main__ - Step 87316: {'lr': 0.00019052984517474892, 'samples': 16764672, 'steps': 87315, 'loss/train': 0.45044979453086853} 08/31/2021 04:57:53 - INFO - __main__ - Step 87317: {'lr': 0.00019052469077708212, 'samples': 16764864, 'steps': 87316, 'loss/train': 0.9891980886459351} 08/31/2021 04:57:54 - INFO - __main__ - Step 87318: {'lr': 0.00019051953640621393, 'samples': 16765056, 'steps': 87317, 'loss/train': 1.794775128364563} 08/31/2021 04:57:54 - INFO - __main__ - Step 87319: {'lr': 0.00019051438206214678, 'samples': 16765248, 'steps': 87318, 'loss/train': 0.48979130387306213} 08/31/2021 04:57:55 - INFO - __main__ - Step 87320: {'lr': 0.0001905092277448829, 'samples': 16765440, 'steps': 87319, 'loss/train': 0.8886155486106873} 08/31/2021 04:57:56 - INFO - __main__ - Step 87321: {'lr': 0.00019050407345442468, 'samples': 16765632, 'steps': 87320, 'loss/train': 1.0562031269073486} 08/31/2021 04:57:56 - INFO - __main__ - Step 87322: {'lr': 0.00019049891919077438, 'samples': 16765824, 'steps': 87321, 'loss/train': 0.8929270505905151} 08/31/2021 04:57:57 - INFO - __main__ - Step 87323: {'lr': 0.0001904937649539344, 'samples': 16766016, 'steps': 87322, 'loss/train': 1.5225142240524292} 08/31/2021 04:57:57 - INFO - __main__ - Step 87324: {'lr': 0.00019048861074390697, 'samples': 16766208, 'steps': 87323, 'loss/train': 0.05601072311401367} 08/31/2021 04:57:59 - INFO - __main__ - Step 87325: {'lr': 0.00019048345656069444, 'samples': 16766400, 'steps': 87324, 'loss/train': 0.9746887683868408} 08/31/2021 04:57:59 - INFO - __main__ - Step 87326: {'lr': 0.00019047830240429914, 'samples': 16766592, 'steps': 87325, 'loss/train': 1.0767792463302612} 08/31/2021 04:57:59 - INFO - __main__ - Step 87327: {'lr': 0.00019047314827472342, 'samples': 16766784, 'steps': 87326, 'loss/train': 0.4270825684070587} 08/31/2021 04:58:00 - INFO - __main__ - Step 87328: {'lr': 0.0001904679941719696, 'samples': 16766976, 'steps': 87327, 'loss/train': 0.7903062105178833} 08/31/2021 04:58:00 - INFO - __main__ - Step 87329: {'lr': 0.00019046284009603998, 'samples': 16767168, 'steps': 87328, 'loss/train': 1.6056081056594849} 08/31/2021 04:58:02 - INFO - __main__ - Step 87330: {'lr': 0.00019045768604693687, 'samples': 16767360, 'steps': 87329, 'loss/train': 0.593222439289093} 08/31/2021 04:58:03 - INFO - __main__ - Step 87331: {'lr': 0.00019045253202466258, 'samples': 16767552, 'steps': 87330, 'loss/train': 1.3378058671951294} 08/31/2021 04:58:03 - INFO - __main__ - Step 87332: {'lr': 0.0001904473780292195, 'samples': 16767744, 'steps': 87331, 'loss/train': 1.4414089918136597} 08/31/2021 04:58:03 - INFO - __main__ - Step 87333: {'lr': 0.0001904422240606099, 'samples': 16767936, 'steps': 87332, 'loss/train': 1.4288145303726196} 08/31/2021 04:58:04 - INFO - __main__ - Step 87334: {'lr': 0.00019043707011883615, 'samples': 16768128, 'steps': 87333, 'loss/train': 1.0935356616973877} 08/31/2021 04:58:05 - INFO - __main__ - Step 87335: {'lr': 0.0001904319162039005, 'samples': 16768320, 'steps': 87334, 'loss/train': 1.3438383340835571} 08/31/2021 04:58:06 - INFO - __main__ - Step 87336: {'lr': 0.0001904267623158053, 'samples': 16768512, 'steps': 87335, 'loss/train': 1.2196097373962402} 08/31/2021 04:58:06 - INFO - __main__ - Step 87337: {'lr': 0.00019042160845455285, 'samples': 16768704, 'steps': 87336, 'loss/train': 1.0645556449890137} 08/31/2021 04:58:06 - INFO - __main__ - Step 87338: {'lr': 0.00019041645462014557, 'samples': 16768896, 'steps': 87337, 'loss/train': 0.4362349510192871} 08/31/2021 04:58:07 - INFO - __main__ - Step 87339: {'lr': 0.00019041130081258567, 'samples': 16769088, 'steps': 87338, 'loss/train': 0.6364063024520874} 08/31/2021 04:58:08 - INFO - __main__ - Step 87340: {'lr': 0.00019040614703187553, 'samples': 16769280, 'steps': 87339, 'loss/train': 0.44345220923423767} 08/31/2021 04:58:08 - INFO - __main__ - Step 87341: {'lr': 0.00019040099327801747, 'samples': 16769472, 'steps': 87340, 'loss/train': 1.4144372940063477} 08/31/2021 04:58:09 - INFO - __main__ - Step 87342: {'lr': 0.00019039583955101386, 'samples': 16769664, 'steps': 87341, 'loss/train': 0.772038459777832} 08/31/2021 04:58:09 - INFO - __main__ - Step 87343: {'lr': 0.00019039068585086687, 'samples': 16769856, 'steps': 87342, 'loss/train': 0.5083562135696411} 08/31/2021 04:58:10 - INFO - __main__ - Step 87344: {'lr': 0.00019038553217757897, 'samples': 16770048, 'steps': 87343, 'loss/train': 0.9889734983444214} 08/31/2021 04:58:10 - INFO - __main__ - Step 87345: {'lr': 0.00019038037853115247, 'samples': 16770240, 'steps': 87344, 'loss/train': 1.146846055984497} 08/31/2021 04:58:11 - INFO - __main__ - Step 87346: {'lr': 0.0001903752249115896, 'samples': 16770432, 'steps': 87345, 'loss/train': 1.694149136543274} 08/31/2021 04:58:12 - INFO - __main__ - Step 87347: {'lr': 0.00019037007131889272, 'samples': 16770624, 'steps': 87346, 'loss/train': 0.4291367828845978} 08/31/2021 04:58:12 - INFO - __main__ - Step 87348: {'lr': 0.00019036491775306413, 'samples': 16770816, 'steps': 87347, 'loss/train': 1.1924501657485962} 08/31/2021 04:58:13 - INFO - __main__ - Step 87349: {'lr': 0.00019035976421410625, 'samples': 16771008, 'steps': 87348, 'loss/train': 1.889816164970398} 08/31/2021 04:58:13 - INFO - __main__ - Step 87350: {'lr': 0.00019035461070202132, 'samples': 16771200, 'steps': 87349, 'loss/train': 1.5682400465011597} 08/31/2021 04:58:14 - INFO - __main__ - Step 87351: {'lr': 0.0001903494572168117, 'samples': 16771392, 'steps': 87350, 'loss/train': 0.5307074785232544} 08/31/2021 04:58:15 - INFO - __main__ - Step 87352: {'lr': 0.00019034430375847964, 'samples': 16771584, 'steps': 87351, 'loss/train': 1.0003243684768677} 08/31/2021 04:58:15 - INFO - __main__ - Step 87353: {'lr': 0.00019033915032702755, 'samples': 16771776, 'steps': 87352, 'loss/train': 1.4456982612609863} 08/31/2021 04:58:16 - INFO - __main__ - Step 87354: {'lr': 0.00019033399692245772, 'samples': 16771968, 'steps': 87353, 'loss/train': 1.3280576467514038} 08/31/2021 04:58:16 - INFO - __main__ - Step 87355: {'lr': 0.00019032884354477247, 'samples': 16772160, 'steps': 87354, 'loss/train': 1.2325191497802734} 08/31/2021 04:58:16 - INFO - __main__ - Step 87356: {'lr': 0.0001903236901939742, 'samples': 16772352, 'steps': 87355, 'loss/train': 1.4738868474960327} 08/31/2021 04:58:18 - INFO - __main__ - Step 87357: {'lr': 0.0001903185368700651, 'samples': 16772544, 'steps': 87356, 'loss/train': 0.449296236038208} 08/31/2021 04:58:18 - INFO - __main__ - Step 87358: {'lr': 0.00019031338357304752, 'samples': 16772736, 'steps': 87357, 'loss/train': 1.3989118337631226} 08/31/2021 04:58:19 - INFO - __main__ - Step 87359: {'lr': 0.0001903082303029238, 'samples': 16772928, 'steps': 87358, 'loss/train': 1.1489990949630737} 08/31/2021 04:58:19 - INFO - __main__ - Step 87360: {'lr': 0.00019030307705969628, 'samples': 16773120, 'steps': 87359, 'loss/train': 1.6076699495315552} 08/31/2021 04:58:19 - INFO - __main__ - Step 87361: {'lr': 0.00019029792384336728, 'samples': 16773312, 'steps': 87360, 'loss/train': 1.6215438842773438} 08/31/2021 04:58:21 - INFO - __main__ - Step 87362: {'lr': 0.0001902927706539391, 'samples': 16773504, 'steps': 87361, 'loss/train': 1.0698535442352295} 08/31/2021 04:58:21 - INFO - __main__ - Step 87363: {'lr': 0.00019028761749141407, 'samples': 16773696, 'steps': 87362, 'loss/train': 0.7485693693161011} 08/31/2021 04:58:22 - INFO - __main__ - Step 87364: {'lr': 0.00019028246435579454, 'samples': 16773888, 'steps': 87363, 'loss/train': 1.5438034534454346} 08/31/2021 04:58:22 - INFO - __main__ - Step 87365: {'lr': 0.0001902773112470828, 'samples': 16774080, 'steps': 87364, 'loss/train': 1.3464539051055908} 08/31/2021 04:58:22 - INFO - __main__ - Step 87366: {'lr': 0.00019027215816528118, 'samples': 16774272, 'steps': 87365, 'loss/train': 0.9426698088645935} 08/31/2021 04:58:24 - INFO - __main__ - Step 87367: {'lr': 0.000190267005110392, 'samples': 16774464, 'steps': 87366, 'loss/train': 1.2909653186798096} 08/31/2021 04:58:24 - INFO - __main__ - Step 87368: {'lr': 0.0001902618520824176, 'samples': 16774656, 'steps': 87367, 'loss/train': 1.1809135675430298} 08/31/2021 04:58:25 - INFO - __main__ - Step 87369: {'lr': 0.0001902566990813604, 'samples': 16774848, 'steps': 87368, 'loss/train': 0.760941207408905} 08/31/2021 04:58:25 - INFO - __main__ - Step 87370: {'lr': 0.00019025154610722246, 'samples': 16775040, 'steps': 87369, 'loss/train': 1.3348644971847534} 08/31/2021 04:58:25 - INFO - __main__ - Step 87371: {'lr': 0.0001902463931600063, 'samples': 16775232, 'steps': 87370, 'loss/train': 1.7654404640197754} 08/31/2021 04:58:27 - INFO - __main__ - Step 87372: {'lr': 0.00019024124023971417, 'samples': 16775424, 'steps': 87371, 'loss/train': 0.6641506552696228} 08/31/2021 04:58:27 - INFO - __main__ - Step 87373: {'lr': 0.0001902360873463484, 'samples': 16775616, 'steps': 87372, 'loss/train': 1.9628126621246338} 08/31/2021 04:58:28 - INFO - __main__ - Step 87374: {'lr': 0.00019023093447991137, 'samples': 16775808, 'steps': 87373, 'loss/train': 0.9146454334259033} 08/31/2021 04:58:28 - INFO - __main__ - Step 87375: {'lr': 0.00019022578164040532, 'samples': 16776000, 'steps': 87374, 'loss/train': 1.2583003044128418} 08/31/2021 04:58:28 - INFO - __main__ - Step 87376: {'lr': 0.0001902206288278326, 'samples': 16776192, 'steps': 87375, 'loss/train': 1.2540102005004883} 08/31/2021 04:58:29 - INFO - __main__ - Step 87377: {'lr': 0.00019021547604219558, 'samples': 16776384, 'steps': 87376, 'loss/train': 1.6161245107650757} 08/31/2021 04:58:30 - INFO - __main__ - Step 87378: {'lr': 0.00019021032328349653, 'samples': 16776576, 'steps': 87377, 'loss/train': 1.1572870016098022} 08/31/2021 04:58:31 - INFO - __main__ - Step 87379: {'lr': 0.0001902051705517378, 'samples': 16776768, 'steps': 87378, 'loss/train': 0.7930241227149963} 08/31/2021 04:58:31 - INFO - __main__ - Step 87380: {'lr': 0.00019020001784692168, 'samples': 16776960, 'steps': 87379, 'loss/train': 1.2548494338989258} 08/31/2021 04:58:31 - INFO - __main__ - Step 87381: {'lr': 0.0001901948651690505, 'samples': 16777152, 'steps': 87380, 'loss/train': 0.9208473563194275} 08/31/2021 04:58:32 - INFO - __main__ - Step 87382: {'lr': 0.00019018971251812673, 'samples': 16777344, 'steps': 87381, 'loss/train': 1.2530802488327026} 08/31/2021 04:58:33 - INFO - __main__ - Step 87383: {'lr': 0.0001901845598941524, 'samples': 16777536, 'steps': 87382, 'loss/train': 0.7242869734764099} 08/31/2021 04:58:34 - INFO - __main__ - Step 87384: {'lr': 0.00019017940729713, 'samples': 16777728, 'steps': 87383, 'loss/train': 1.4573649168014526} 08/31/2021 04:58:34 - INFO - __main__ - Step 87385: {'lr': 0.00019017425472706188, 'samples': 16777920, 'steps': 87384, 'loss/train': 1.6098157167434692} 08/31/2021 04:58:34 - INFO - __main__ - Step 87386: {'lr': 0.00019016910218395028, 'samples': 16778112, 'steps': 87385, 'loss/train': 0.3147002160549164} 08/31/2021 04:58:35 - INFO - __main__ - Step 87387: {'lr': 0.00019016394966779755, 'samples': 16778304, 'steps': 87386, 'loss/train': 1.9130116701126099} 08/31/2021 04:58:37 - INFO - __main__ - Step 87388: {'lr': 0.00019015879717860604, 'samples': 16778496, 'steps': 87387, 'loss/train': 1.7933456897735596} 08/31/2021 04:58:37 - INFO - __main__ - Step 87389: {'lr': 0.00019015364471637803, 'samples': 16778688, 'steps': 87388, 'loss/train': 1.0308966636657715} 08/31/2021 04:58:38 - INFO - __main__ - Step 87390: {'lr': 0.0001901484922811159, 'samples': 16778880, 'steps': 87389, 'loss/train': 1.057643175125122} 08/31/2021 04:58:38 - INFO - __main__ - Step 87391: {'lr': 0.0001901433398728219, 'samples': 16779072, 'steps': 87390, 'loss/train': 1.4922854900360107} 08/31/2021 04:58:39 - INFO - __main__ - Step 87392: {'lr': 0.00019013818749149842, 'samples': 16779264, 'steps': 87391, 'loss/train': 1.081297755241394} 08/31/2021 04:58:40 - INFO - __main__ - Step 87393: {'lr': 0.0001901330351371477, 'samples': 16779456, 'steps': 87392, 'loss/train': 1.332507610321045} 08/31/2021 04:58:40 - INFO - __main__ - Step 87394: {'lr': 0.00019012788280977217, 'samples': 16779648, 'steps': 87393, 'loss/train': 1.244632601737976} 08/31/2021 04:58:41 - INFO - __main__ - Step 87395: {'lr': 0.00019012273050937405, 'samples': 16779840, 'steps': 87394, 'loss/train': 1.8506566286087036} 08/31/2021 04:58:41 - INFO - __main__ - Step 87396: {'lr': 0.00019011757823595582, 'samples': 16780032, 'steps': 87395, 'loss/train': 1.0350812673568726} 08/31/2021 04:58:41 - INFO - __main__ - Step 87397: {'lr': 0.0001901124259895196, 'samples': 16780224, 'steps': 87396, 'loss/train': 1.0878376960754395} 08/31/2021 04:58:43 - INFO - __main__ - Step 87398: {'lr': 0.00019010727377006777, 'samples': 16780416, 'steps': 87397, 'loss/train': 0.7838340401649475} 08/31/2021 04:58:43 - INFO - __main__ - Step 87399: {'lr': 0.0001901021215776027, 'samples': 16780608, 'steps': 87398, 'loss/train': 1.3344732522964478} 08/31/2021 04:58:44 - INFO - __main__ - Step 87400: {'lr': 0.00019009696941212667, 'samples': 16780800, 'steps': 87399, 'loss/train': 1.0932601690292358} 08/31/2021 04:58:44 - INFO - __main__ - Step 87401: {'lr': 0.00019009181727364205, 'samples': 16780992, 'steps': 87400, 'loss/train': 1.0338973999023438} 08/31/2021 04:58:45 - INFO - __main__ - Step 87402: {'lr': 0.00019008666516215112, 'samples': 16781184, 'steps': 87401, 'loss/train': 1.0673853158950806} 08/31/2021 04:58:46 - INFO - __main__ - Step 87403: {'lr': 0.0001900815130776562, 'samples': 16781376, 'steps': 87402, 'loss/train': 3.2081220149993896} 08/31/2021 04:58:47 - INFO - __main__ - Step 87404: {'lr': 0.00019007636102015964, 'samples': 16781568, 'steps': 87403, 'loss/train': 1.4017231464385986} 08/31/2021 04:58:47 - INFO - __main__ - Step 87405: {'lr': 0.00019007120898966373, 'samples': 16781760, 'steps': 87404, 'loss/train': 0.9635457396507263} 08/31/2021 04:58:47 - INFO - __main__ - Step 87406: {'lr': 0.0001900660569861708, 'samples': 16781952, 'steps': 87405, 'loss/train': 0.933553159236908} 08/31/2021 04:58:48 - INFO - __main__ - Step 87407: {'lr': 0.0001900609050096832, 'samples': 16782144, 'steps': 87406, 'loss/train': 0.15275748074054718} 08/31/2021 04:58:48 - INFO - __main__ - Step 87408: {'lr': 0.00019005575306020323, 'samples': 16782336, 'steps': 87407, 'loss/train': 0.0270854402333498} 08/31/2021 04:58:49 - INFO - __main__ - Step 87409: {'lr': 0.00019005060113773333, 'samples': 16782528, 'steps': 87408, 'loss/train': 1.0990839004516602} 08/31/2021 04:58:50 - INFO - __main__ - Step 87410: {'lr': 0.00019004544924227558, 'samples': 16782720, 'steps': 87409, 'loss/train': 1.6473487615585327} 08/31/2021 04:58:50 - INFO - __main__ - Step 87411: {'lr': 0.00019004029737383244, 'samples': 16782912, 'steps': 87410, 'loss/train': 1.4237148761749268} 08/31/2021 04:58:51 - INFO - __main__ - Step 87412: {'lr': 0.0001900351455324062, 'samples': 16783104, 'steps': 87411, 'loss/train': 0.9741008281707764} 08/31/2021 04:58:51 - INFO - __main__ - Step 87413: {'lr': 0.0001900299937179992, 'samples': 16783296, 'steps': 87412, 'loss/train': 1.1299513578414917} 08/31/2021 04:58:53 - INFO - __main__ - Step 87414: {'lr': 0.00019002484193061378, 'samples': 16783488, 'steps': 87413, 'loss/train': 1.394288182258606} 08/31/2021 04:58:53 - INFO - __main__ - Step 87415: {'lr': 0.00019001969017025223, 'samples': 16783680, 'steps': 87414, 'loss/train': 0.9833813309669495} 08/31/2021 04:58:54 - INFO - __main__ - Step 87416: {'lr': 0.00019001453843691687, 'samples': 16783872, 'steps': 87415, 'loss/train': 0.03850236535072327} 08/31/2021 04:58:54 - INFO - __main__ - Step 87417: {'lr': 0.00019000938673061006, 'samples': 16784064, 'steps': 87416, 'loss/train': 0.7767504453659058} 08/31/2021 04:58:54 - INFO - __main__ - Step 87418: {'lr': 0.00019000423505133407, 'samples': 16784256, 'steps': 87417, 'loss/train': 0.9952538013458252} 08/31/2021 04:58:56 - INFO - __main__ - Step 87419: {'lr': 0.00018999908339909126, 'samples': 16784448, 'steps': 87418, 'loss/train': 0.10060697048902512} 08/31/2021 04:58:56 - INFO - __main__ - Step 87420: {'lr': 0.00018999393177388392, 'samples': 16784640, 'steps': 87419, 'loss/train': 1.1168968677520752} 08/31/2021 04:58:57 - INFO - __main__ - Step 87421: {'lr': 0.00018998878017571438, 'samples': 16784832, 'steps': 87420, 'loss/train': 1.171931505203247} 08/31/2021 04:58:57 - INFO - __main__ - Step 87422: {'lr': 0.000189983628604585, 'samples': 16785024, 'steps': 87421, 'loss/train': 1.313069224357605} 08/31/2021 04:58:58 - INFO - __main__ - Step 87423: {'lr': 0.00018997847706049816, 'samples': 16785216, 'steps': 87422, 'loss/train': 1.3178759813308716} 08/31/2021 04:58:59 - INFO - __main__ - Step 87424: {'lr': 0.00018997332554345598, 'samples': 16785408, 'steps': 87423, 'loss/train': 0.9733052253723145} 08/31/2021 04:58:59 - INFO - __main__ - Step 87425: {'lr': 0.00018996817405346093, 'samples': 16785600, 'steps': 87424, 'loss/train': 1.2687110900878906} 08/31/2021 04:59:00 - INFO - __main__ - Step 87426: {'lr': 0.00018996302259051526, 'samples': 16785792, 'steps': 87425, 'loss/train': 1.4523988962173462} 08/31/2021 04:59:00 - INFO - __main__ - Step 87427: {'lr': 0.00018995787115462132, 'samples': 16785984, 'steps': 87426, 'loss/train': 0.9322891235351562} 08/31/2021 04:59:00 - INFO - __main__ - Step 87428: {'lr': 0.00018995271974578146, 'samples': 16786176, 'steps': 87427, 'loss/train': 0.8709313273429871} 08/31/2021 04:59:01 - INFO - __main__ - Step 87429: {'lr': 0.00018994756836399794, 'samples': 16786368, 'steps': 87428, 'loss/train': 1.8195704221725464} 08/31/2021 04:59:02 - INFO - __main__ - Step 87430: {'lr': 0.00018994241700927316, 'samples': 16786560, 'steps': 87429, 'loss/train': 0.7487571835517883} 08/31/2021 04:59:03 - INFO - __main__ - Step 87431: {'lr': 0.0001899372656816094, 'samples': 16786752, 'steps': 87430, 'loss/train': 1.4046295881271362} 08/31/2021 04:59:03 - INFO - __main__ - Step 87432: {'lr': 0.00018993211438100897, 'samples': 16786944, 'steps': 87431, 'loss/train': 1.5823146104812622} 08/31/2021 04:59:04 - INFO - __main__ - Step 87433: {'lr': 0.0001899269631074742, 'samples': 16787136, 'steps': 87432, 'loss/train': 0.912431538105011} 08/31/2021 04:59:04 - INFO - __main__ - Step 87434: {'lr': 0.00018992181186100744, 'samples': 16787328, 'steps': 87433, 'loss/train': 0.12709452211856842} 08/31/2021 04:59:06 - INFO - __main__ - Step 87435: {'lr': 0.00018991666064161096, 'samples': 16787520, 'steps': 87434, 'loss/train': 1.9754586219787598} 08/31/2021 04:59:06 - INFO - __main__ - Step 87436: {'lr': 0.0001899115094492872, 'samples': 16787712, 'steps': 87435, 'loss/train': 0.6820817589759827} 08/31/2021 04:59:06 - INFO - __main__ - Step 87437: {'lr': 0.00018990635828403828, 'samples': 16787904, 'steps': 87436, 'loss/train': 1.0578943490982056} 08/31/2021 04:59:07 - INFO - __main__ - Step 87438: {'lr': 0.00018990120714586665, 'samples': 16788096, 'steps': 87437, 'loss/train': 1.185151219367981} 08/31/2021 04:59:07 - INFO - __main__ - Step 87439: {'lr': 0.00018989605603477458, 'samples': 16788288, 'steps': 87438, 'loss/train': 1.3511930704116821} 08/31/2021 04:59:09 - INFO - __main__ - Step 87440: {'lr': 0.00018989090495076443, 'samples': 16788480, 'steps': 87439, 'loss/train': 0.26334843039512634} 08/31/2021 04:59:10 - INFO - __main__ - Step 87441: {'lr': 0.0001898857538938385, 'samples': 16788672, 'steps': 87440, 'loss/train': 1.2956819534301758} 08/31/2021 04:59:10 - INFO - __main__ - Step 87442: {'lr': 0.00018988060286399916, 'samples': 16788864, 'steps': 87441, 'loss/train': 1.0809026956558228} 08/31/2021 04:59:10 - INFO - __main__ - Step 87443: {'lr': 0.0001898754518612487, 'samples': 16789056, 'steps': 87442, 'loss/train': 1.3318029642105103} 08/31/2021 04:59:11 - INFO - __main__ - Step 87444: {'lr': 0.00018987030088558936, 'samples': 16789248, 'steps': 87443, 'loss/train': 1.179945945739746} 08/31/2021 04:59:12 - INFO - __main__ - Step 87445: {'lr': 0.00018986514993702362, 'samples': 16789440, 'steps': 87444, 'loss/train': 0.7585727572441101} 08/31/2021 04:59:13 - INFO - __main__ - Step 87446: {'lr': 0.00018985999901555367, 'samples': 16789632, 'steps': 87445, 'loss/train': 1.2021201848983765} 08/31/2021 04:59:13 - INFO - __main__ - Step 87447: {'lr': 0.00018985484812118192, 'samples': 16789824, 'steps': 87446, 'loss/train': 2.0304644107818604} 08/31/2021 04:59:13 - INFO - __main__ - Step 87448: {'lr': 0.00018984969725391063, 'samples': 16790016, 'steps': 87447, 'loss/train': 1.6273159980773926} 08/31/2021 04:59:14 - INFO - __main__ - Step 87449: {'lr': 0.0001898445464137421, 'samples': 16790208, 'steps': 87448, 'loss/train': 1.2864950895309448} 08/31/2021 04:59:16 - INFO - __main__ - Step 87450: {'lr': 0.00018983939560067876, 'samples': 16790400, 'steps': 87449, 'loss/train': 1.3729640245437622} 08/31/2021 04:59:16 - INFO - __main__ - Step 87451: {'lr': 0.00018983424481472283, 'samples': 16790592, 'steps': 87450, 'loss/train': 1.136553406715393} 08/31/2021 04:59:17 - INFO - __main__ - Step 87452: {'lr': 0.00018982909405587661, 'samples': 16790784, 'steps': 87451, 'loss/train': 0.9685046672821045} 08/31/2021 04:59:17 - INFO - __main__ - Step 87453: {'lr': 0.00018982394332414253, 'samples': 16790976, 'steps': 87452, 'loss/train': 0.8265669345855713} 08/31/2021 04:59:17 - INFO - __main__ - Step 87454: {'lr': 0.00018981879261952282, 'samples': 16791168, 'steps': 87453, 'loss/train': 1.246416449546814} 08/31/2021 04:59:18 - INFO - __main__ - Step 87455: {'lr': 0.00018981364194201983, 'samples': 16791360, 'steps': 87454, 'loss/train': 0.020436817780137062} 08/31/2021 04:59:18 - INFO - __main__ - Step 87456: {'lr': 0.00018980849129163587, 'samples': 16791552, 'steps': 87455, 'loss/train': 0.36667320132255554} 08/31/2021 04:59:19 - INFO - __main__ - Step 87457: {'lr': 0.0001898033406683733, 'samples': 16791744, 'steps': 87456, 'loss/train': 1.3442391157150269} 08/31/2021 04:59:20 - INFO - __main__ - Step 87458: {'lr': 0.00018979819007223448, 'samples': 16791936, 'steps': 87457, 'loss/train': 1.484141230583191} 08/31/2021 04:59:20 - INFO - __main__ - Step 87459: {'lr': 0.00018979303950322158, 'samples': 16792128, 'steps': 87458, 'loss/train': 1.0669918060302734} 08/31/2021 04:59:20 - INFO - __main__ - Step 87460: {'lr': 0.00018978788896133704, 'samples': 16792320, 'steps': 87459, 'loss/train': 1.1000367403030396} 08/31/2021 04:59:21 - INFO - __main__ - Step 87461: {'lr': 0.00018978273844658312, 'samples': 16792512, 'steps': 87460, 'loss/train': 1.828002691268921} 08/31/2021 04:59:23 - INFO - __main__ - Step 87462: {'lr': 0.0001897775879589622, 'samples': 16792704, 'steps': 87461, 'loss/train': 1.2249430418014526} 08/31/2021 04:59:23 - INFO - __main__ - Step 87463: {'lr': 0.00018977243749847663, 'samples': 16792896, 'steps': 87462, 'loss/train': 1.525619387626648} 08/31/2021 04:59:24 - INFO - __main__ - Step 87464: {'lr': 0.00018976728706512856, 'samples': 16793088, 'steps': 87463, 'loss/train': 0.04618634656071663} 08/31/2021 04:59:24 - INFO - __main__ - Step 87465: {'lr': 0.00018976213665892046, 'samples': 16793280, 'steps': 87464, 'loss/train': 1.6042896509170532} 08/31/2021 04:59:24 - INFO - __main__ - Step 87466: {'lr': 0.0001897569862798546, 'samples': 16793472, 'steps': 87465, 'loss/train': 0.9479241371154785} 08/31/2021 04:59:26 - INFO - __main__ - Step 87467: {'lr': 0.0001897518359279333, 'samples': 16793664, 'steps': 87466, 'loss/train': 1.5062332153320312} 08/31/2021 04:59:27 - INFO - __main__ - Step 87468: {'lr': 0.0001897466856031589, 'samples': 16793856, 'steps': 87467, 'loss/train': 1.4394516944885254} 08/31/2021 04:59:27 - INFO - __main__ - Step 87469: {'lr': 0.00018974153530553378, 'samples': 16794048, 'steps': 87468, 'loss/train': 1.6179364919662476} 08/31/2021 04:59:27 - INFO - __main__ - Step 87470: {'lr': 0.00018973638503506015, 'samples': 16794240, 'steps': 87469, 'loss/train': 1.3380266427993774} 08/31/2021 04:59:28 - INFO - __main__ - Step 87471: {'lr': 0.00018973123479174036, 'samples': 16794432, 'steps': 87470, 'loss/train': 1.2382487058639526} 08/31/2021 04:59:29 - INFO - __main__ - Step 87472: {'lr': 0.00018972608457557675, 'samples': 16794624, 'steps': 87471, 'loss/train': 1.256646990776062} 08/31/2021 04:59:30 - INFO - __main__ - Step 87473: {'lr': 0.00018972093438657164, 'samples': 16794816, 'steps': 87472, 'loss/train': 1.1378023624420166} 08/31/2021 04:59:30 - INFO - __main__ - Step 87474: {'lr': 0.00018971578422472736, 'samples': 16795008, 'steps': 87473, 'loss/train': 0.8568986058235168} 08/31/2021 04:59:30 - INFO - __main__ - Step 87475: {'lr': 0.00018971063409004617, 'samples': 16795200, 'steps': 87474, 'loss/train': 1.1685453653335571} 08/31/2021 04:59:31 - INFO - __main__ - Step 87476: {'lr': 0.00018970548398253049, 'samples': 16795392, 'steps': 87475, 'loss/train': 1.265830159187317} 08/31/2021 04:59:32 - INFO - __main__ - Step 87477: {'lr': 0.0001897003339021826, 'samples': 16795584, 'steps': 87476, 'loss/train': 1.358838677406311} 08/31/2021 04:59:32 - INFO - __main__ - Step 87478: {'lr': 0.00018969518384900477, 'samples': 16795776, 'steps': 87477, 'loss/train': 1.567311406135559} 08/31/2021 04:59:33 - INFO - __main__ - Step 87479: {'lr': 0.00018969003382299937, 'samples': 16795968, 'steps': 87478, 'loss/train': 1.5013012886047363} 08/31/2021 04:59:33 - INFO - __main__ - Step 87480: {'lr': 0.00018968488382416877, 'samples': 16796160, 'steps': 87479, 'loss/train': 1.512805700302124} 08/31/2021 04:59:34 - INFO - __main__ - Step 87481: {'lr': 0.00018967973385251516, 'samples': 16796352, 'steps': 87480, 'loss/train': 1.4925730228424072} 08/31/2021 04:59:34 - INFO - __main__ - Step 87482: {'lr': 0.00018967458390804092, 'samples': 16796544, 'steps': 87481, 'loss/train': 1.1739702224731445} 08/31/2021 04:59:36 - INFO - __main__ - Step 87483: {'lr': 0.0001896694339907484, 'samples': 16796736, 'steps': 87482, 'loss/train': 1.7488504648208618} 08/31/2021 04:59:36 - INFO - __main__ - Step 87484: {'lr': 0.0001896642841006399, 'samples': 16796928, 'steps': 87483, 'loss/train': 0.8949593305587769} 08/31/2021 04:59:37 - INFO - __main__ - Step 87485: {'lr': 0.00018965913423771774, 'samples': 16797120, 'steps': 87484, 'loss/train': 0.018533138558268547} 08/31/2021 04:59:37 - INFO - __main__ - Step 87486: {'lr': 0.00018965398440198427, 'samples': 16797312, 'steps': 87485, 'loss/train': 1.6163902282714844} 08/31/2021 04:59:37 - INFO - __main__ - Step 87487: {'lr': 0.00018964883459344174, 'samples': 16797504, 'steps': 87486, 'loss/train': 1.2929155826568604} 08/31/2021 04:59:38 - INFO - __main__ - Step 87488: {'lr': 0.00018964368481209253, 'samples': 16797696, 'steps': 87487, 'loss/train': 1.4428197145462036} 08/31/2021 04:59:39 - INFO - __main__ - Step 87489: {'lr': 0.00018963853505793896, 'samples': 16797888, 'steps': 87488, 'loss/train': 0.2689794600009918} 08/31/2021 04:59:40 - INFO - __main__ - Step 87490: {'lr': 0.00018963338533098344, 'samples': 16798080, 'steps': 87489, 'loss/train': 1.487538456916809} 08/31/2021 04:59:40 - INFO - __main__ - Step 87491: {'lr': 0.00018962823563122805, 'samples': 16798272, 'steps': 87490, 'loss/train': 1.2545654773712158} 08/31/2021 04:59:40 - INFO - __main__ - Step 87492: {'lr': 0.00018962308595867525, 'samples': 16798464, 'steps': 87491, 'loss/train': 0.7809642553329468} 08/31/2021 04:59:41 - INFO - __main__ - Step 87493: {'lr': 0.00018961793631332738, 'samples': 16798656, 'steps': 87492, 'loss/train': 1.0108085870742798} 08/31/2021 04:59:44 - INFO - __main__ - Step 87494: {'lr': 0.00018961278669518672, 'samples': 16798848, 'steps': 87493, 'loss/train': 1.056255578994751} 08/31/2021 04:59:44 - INFO - __main__ - Step 87495: {'lr': 0.0001896076371042556, 'samples': 16799040, 'steps': 87494, 'loss/train': 1.2068240642547607} 08/31/2021 04:59:44 - INFO - __main__ - Step 87496: {'lr': 0.00018960248754053638, 'samples': 16799232, 'steps': 87495, 'loss/train': 1.1161729097366333} 08/31/2021 04:59:45 - INFO - __main__ - Step 87497: {'lr': 0.00018959733800403132, 'samples': 16799424, 'steps': 87496, 'loss/train': 0.6460865139961243} 08/31/2021 04:59:45 - INFO - __main__ - Step 87498: {'lr': 0.00018959218849474277, 'samples': 16799616, 'steps': 87497, 'loss/train': 1.2198455333709717} 08/31/2021 04:59:46 - INFO - __main__ - Step 87499: {'lr': 0.00018958703901267304, 'samples': 16799808, 'steps': 87498, 'loss/train': 1.761319875717163} 08/31/2021 04:59:46 - INFO - __main__ - Step 87500: {'lr': 0.00018958188955782446, 'samples': 16800000, 'steps': 87499, 'loss/train': 1.6835052967071533} 08/31/2021 04:59:48 - INFO - __main__ - Step 87501: {'lr': 0.00018957674013019937, 'samples': 16800192, 'steps': 87500, 'loss/train': 1.8178470134735107} 08/31/2021 04:59:48 - INFO - __main__ - Step 87502: {'lr': 0.00018957159072980004, 'samples': 16800384, 'steps': 87501, 'loss/train': 0.03408370912075043} 08/31/2021 04:59:48 - INFO - __main__ - Step 87503: {'lr': 0.00018956644135662896, 'samples': 16800576, 'steps': 87502, 'loss/train': 1.2386631965637207} 08/31/2021 04:59:49 - INFO - __main__ - Step 87504: {'lr': 0.00018956129201068818, 'samples': 16800768, 'steps': 87503, 'loss/train': 1.6018025875091553} 08/31/2021 04:59:49 - INFO - __main__ - Step 87505: {'lr': 0.00018955614269198012, 'samples': 16800960, 'steps': 87504, 'loss/train': 0.846524715423584} 08/31/2021 04:59:51 - INFO - __main__ - Step 87506: {'lr': 0.0001895509934005072, 'samples': 16801152, 'steps': 87505, 'loss/train': 0.9336935877799988} 08/31/2021 04:59:51 - INFO - __main__ - Step 87507: {'lr': 0.00018954584413627163, 'samples': 16801344, 'steps': 87506, 'loss/train': 1.3012490272521973} 08/31/2021 04:59:51 - INFO - __main__ - Step 87508: {'lr': 0.00018954069489927574, 'samples': 16801536, 'steps': 87507, 'loss/train': 1.7214415073394775} 08/31/2021 04:59:52 - INFO - __main__ - Step 87509: {'lr': 0.00018953554568952192, 'samples': 16801728, 'steps': 87508, 'loss/train': 1.1115723848342896} 08/31/2021 04:59:52 - INFO - __main__ - Step 87510: {'lr': 0.00018953039650701243, 'samples': 16801920, 'steps': 87509, 'loss/train': 0.7799316048622131} 08/31/2021 04:59:54 - INFO - __main__ - Step 87511: {'lr': 0.00018952524735174964, 'samples': 16802112, 'steps': 87510, 'loss/train': 1.3875885009765625} 08/31/2021 04:59:54 - INFO - __main__ - Step 87512: {'lr': 0.0001895200982237358, 'samples': 16802304, 'steps': 87511, 'loss/train': 1.693814754486084} 08/31/2021 04:59:54 - INFO - __main__ - Step 87513: {'lr': 0.00018951494912297328, 'samples': 16802496, 'steps': 87512, 'loss/train': 0.6189706921577454} 08/31/2021 04:59:55 - INFO - __main__ - Step 87514: {'lr': 0.00018950980004946443, 'samples': 16802688, 'steps': 87513, 'loss/train': 1.025327205657959} 08/31/2021 04:59:55 - INFO - __main__ - Step 87515: {'lr': 0.0001895046510032115, 'samples': 16802880, 'steps': 87514, 'loss/train': 1.198191523551941} 08/31/2021 04:59:55 - INFO - __main__ - Step 87516: {'lr': 0.00018949950198421684, 'samples': 16803072, 'steps': 87515, 'loss/train': 1.0667601823806763} 08/31/2021 04:59:57 - INFO - __main__ - Step 87517: {'lr': 0.00018949435299248289, 'samples': 16803264, 'steps': 87516, 'loss/train': 1.2744921445846558} 08/31/2021 04:59:57 - INFO - __main__ - Step 87518: {'lr': 0.00018948920402801173, 'samples': 16803456, 'steps': 87517, 'loss/train': 1.241650938987732} 08/31/2021 04:59:58 - INFO - __main__ - Step 87519: {'lr': 0.0001894840550908058, 'samples': 16803648, 'steps': 87518, 'loss/train': 1.240497350692749} 08/31/2021 04:59:58 - INFO - __main__ - Step 87520: {'lr': 0.00018947890618086744, 'samples': 16803840, 'steps': 87519, 'loss/train': 0.03487124294042587} 08/31/2021 04:59:59 - INFO - __main__ - Step 87521: {'lr': 0.00018947375729819893, 'samples': 16804032, 'steps': 87520, 'loss/train': 1.3387962579727173} 08/31/2021 05:00:00 - INFO - __main__ - Step 87522: {'lr': 0.0001894686084428026, 'samples': 16804224, 'steps': 87521, 'loss/train': 1.0548784732818604} 08/31/2021 05:00:01 - INFO - __main__ - Step 87523: {'lr': 0.0001894634596146808, 'samples': 16804416, 'steps': 87522, 'loss/train': 1.1868228912353516} 08/31/2021 05:00:01 - INFO - __main__ - Step 87524: {'lr': 0.00018945831081383587, 'samples': 16804608, 'steps': 87523, 'loss/train': 1.5766724348068237} 08/31/2021 05:00:01 - INFO - __main__ - Step 87525: {'lr': 0.00018945316204027003, 'samples': 16804800, 'steps': 87524, 'loss/train': 1.3222531080245972} 08/31/2021 05:00:02 - INFO - __main__ - Step 87526: {'lr': 0.00018944801329398567, 'samples': 16804992, 'steps': 87525, 'loss/train': 0.45959460735321045} 08/31/2021 05:00:03 - INFO - __main__ - Step 87527: {'lr': 0.0001894428645749851, 'samples': 16805184, 'steps': 87526, 'loss/train': 1.2883615493774414} 08/31/2021 05:00:04 - INFO - __main__ - Step 87528: {'lr': 0.00018943771588327067, 'samples': 16805376, 'steps': 87527, 'loss/train': 1.8339695930480957} 08/31/2021 05:00:04 - INFO - __main__ - Step 87529: {'lr': 0.00018943256721884466, 'samples': 16805568, 'steps': 87528, 'loss/train': 1.1266063451766968} 08/31/2021 05:00:04 - INFO - __main__ - Step 87530: {'lr': 0.0001894274185817095, 'samples': 16805760, 'steps': 87529, 'loss/train': 1.5665884017944336} 08/31/2021 05:00:05 - INFO - __main__ - Step 87531: {'lr': 0.00018942226997186728, 'samples': 16805952, 'steps': 87530, 'loss/train': 1.8901135921478271} 08/31/2021 05:00:07 - INFO - __main__ - Step 87532: {'lr': 0.0001894171213893205, 'samples': 16806144, 'steps': 87531, 'loss/train': 1.4824579954147339} 08/31/2021 05:00:07 - INFO - __main__ - Step 87533: {'lr': 0.00018941197283407142, 'samples': 16806336, 'steps': 87532, 'loss/train': 1.2027844190597534} 08/31/2021 05:00:08 - INFO - __main__ - Step 87534: {'lr': 0.00018940682430612234, 'samples': 16806528, 'steps': 87533, 'loss/train': 2.4367835521698} 08/31/2021 05:00:08 - INFO - __main__ - Step 87535: {'lr': 0.00018940167580547564, 'samples': 16806720, 'steps': 87534, 'loss/train': 1.6443692445755005} 08/31/2021 05:00:08 - INFO - __main__ - Step 87536: {'lr': 0.0001893965273321336, 'samples': 16806912, 'steps': 87535, 'loss/train': 0.8829948306083679} 08/31/2021 05:00:10 - INFO - __main__ - Step 87537: {'lr': 0.00018939137888609854, 'samples': 16807104, 'steps': 87536, 'loss/train': 1.7600270509719849} 08/31/2021 05:00:10 - INFO - __main__ - Step 87538: {'lr': 0.00018938623046737277, 'samples': 16807296, 'steps': 87537, 'loss/train': 1.3126320838928223} 08/31/2021 05:00:11 - INFO - __main__ - Step 87539: {'lr': 0.00018938108207595865, 'samples': 16807488, 'steps': 87538, 'loss/train': 1.2624201774597168} 08/31/2021 05:00:11 - INFO - __main__ - Step 87540: {'lr': 0.0001893759337118585, 'samples': 16807680, 'steps': 87539, 'loss/train': 1.2231477499008179} 08/31/2021 05:00:11 - INFO - __main__ - Step 87541: {'lr': 0.0001893707853750746, 'samples': 16807872, 'steps': 87540, 'loss/train': 1.3985092639923096} 08/31/2021 05:00:13 - INFO - __main__ - Step 87542: {'lr': 0.00018936563706560926, 'samples': 16808064, 'steps': 87541, 'loss/train': 1.2987521886825562} 08/31/2021 05:00:13 - INFO - __main__ - Step 87543: {'lr': 0.0001893604887834649, 'samples': 16808256, 'steps': 87542, 'loss/train': 0.7694045901298523} 08/31/2021 05:00:13 - INFO - __main__ - Step 87544: {'lr': 0.00018935534052864385, 'samples': 16808448, 'steps': 87543, 'loss/train': 1.8321599960327148} 08/31/2021 05:00:14 - INFO - __main__ - Step 87545: {'lr': 0.0001893501923011482, 'samples': 16808640, 'steps': 87544, 'loss/train': 0.5964593887329102} 08/31/2021 05:00:14 - INFO - __main__ - Step 87546: {'lr': 0.00018934504410098043, 'samples': 16808832, 'steps': 87545, 'loss/train': 1.2382742166519165} 08/31/2021 05:00:14 - INFO - __main__ - Step 87547: {'lr': 0.00018933989592814288, 'samples': 16809024, 'steps': 87546, 'loss/train': 1.6970916986465454} 08/31/2021 05:00:16 - INFO - __main__ - Step 87548: {'lr': 0.00018933474778263783, 'samples': 16809216, 'steps': 87547, 'loss/train': 1.2438455820083618} 08/31/2021 05:00:16 - INFO - __main__ - Step 87549: {'lr': 0.00018932959966446757, 'samples': 16809408, 'steps': 87548, 'loss/train': 1.171042561531067} 08/31/2021 05:00:17 - INFO - __main__ - Step 87550: {'lr': 0.0001893244515736345, 'samples': 16809600, 'steps': 87549, 'loss/train': 1.1702646017074585} 08/31/2021 05:00:17 - INFO - __main__ - Step 87551: {'lr': 0.00018931930351014084, 'samples': 16809792, 'steps': 87550, 'loss/train': 0.8239463567733765} 08/31/2021 05:00:17 - INFO - __main__ - Step 87552: {'lr': 0.000189314155473989, 'samples': 16809984, 'steps': 87551, 'loss/train': 0.7800195813179016} 08/31/2021 05:00:19 - INFO - __main__ - Step 87553: {'lr': 0.00018930900746518125, 'samples': 16810176, 'steps': 87552, 'loss/train': 1.7869012355804443} 08/31/2021 05:00:20 - INFO - __main__ - Step 87554: {'lr': 0.00018930385948371997, 'samples': 16810368, 'steps': 87553, 'loss/train': 1.385563850402832} 08/31/2021 05:00:20 - INFO - __main__ - Step 87555: {'lr': 0.00018929871152960739, 'samples': 16810560, 'steps': 87554, 'loss/train': 1.0154345035552979} 08/31/2021 05:00:21 - INFO - __main__ - Step 87556: {'lr': 0.0001892935636028459, 'samples': 16810752, 'steps': 87555, 'loss/train': 1.7382677793502808} 08/31/2021 05:00:21 - INFO - __main__ - Step 87557: {'lr': 0.0001892884157034379, 'samples': 16810944, 'steps': 87556, 'loss/train': 1.1675786972045898} 08/31/2021 05:00:23 - INFO - __main__ - Step 87558: {'lr': 0.00018928326783138546, 'samples': 16811136, 'steps': 87557, 'loss/train': 1.384823203086853} 08/31/2021 05:00:23 - INFO - __main__ - Step 87559: {'lr': 0.0001892781199866911, 'samples': 16811328, 'steps': 87558, 'loss/train': 1.6044560670852661} 08/31/2021 05:00:23 - INFO - __main__ - Step 87560: {'lr': 0.00018927297216935702, 'samples': 16811520, 'steps': 87559, 'loss/train': 0.6498855352401733} 08/31/2021 05:00:24 - INFO - __main__ - Step 87561: {'lr': 0.00018926782437938563, 'samples': 16811712, 'steps': 87560, 'loss/train': 1.5945978164672852} 08/31/2021 05:00:24 - INFO - __main__ - Step 87562: {'lr': 0.00018926267661677923, 'samples': 16811904, 'steps': 87561, 'loss/train': 1.6045267581939697} 08/31/2021 05:00:26 - INFO - __main__ - Step 87563: {'lr': 0.00018925752888154012, 'samples': 16812096, 'steps': 87562, 'loss/train': 1.102227807044983} 08/31/2021 05:00:26 - INFO - __main__ - Step 87564: {'lr': 0.00018925238117367064, 'samples': 16812288, 'steps': 87563, 'loss/train': 0.5310251116752625} 08/31/2021 05:00:26 - INFO - __main__ - Step 87565: {'lr': 0.00018924723349317306, 'samples': 16812480, 'steps': 87564, 'loss/train': 1.0370643138885498} 08/31/2021 05:00:27 - INFO - __main__ - Step 87566: {'lr': 0.0001892420858400498, 'samples': 16812672, 'steps': 87565, 'loss/train': 1.0595347881317139} 08/31/2021 05:00:27 - INFO - __main__ - Step 87567: {'lr': 0.0001892369382143031, 'samples': 16812864, 'steps': 87566, 'loss/train': 0.825505256652832} 08/31/2021 05:00:29 - INFO - __main__ - Step 87568: {'lr': 0.0001892317906159353, 'samples': 16813056, 'steps': 87567, 'loss/train': 0.9595996737480164} 08/31/2021 05:00:29 - INFO - __main__ - Step 87569: {'lr': 0.0001892266430449487, 'samples': 16813248, 'steps': 87568, 'loss/train': 0.3005039691925049} 08/31/2021 05:00:29 - INFO - __main__ - Step 87570: {'lr': 0.00018922149550134568, 'samples': 16813440, 'steps': 87569, 'loss/train': 1.100324034690857} 08/31/2021 05:00:30 - INFO - __main__ - Step 87571: {'lr': 0.00018921634798512853, 'samples': 16813632, 'steps': 87570, 'loss/train': 1.5021424293518066} 08/31/2021 05:00:30 - INFO - __main__ - Step 87572: {'lr': 0.00018921120049629952, 'samples': 16813824, 'steps': 87571, 'loss/train': 1.1767628192901611} 08/31/2021 05:00:32 - INFO - __main__ - Step 87573: {'lr': 0.00018920605303486099, 'samples': 16814016, 'steps': 87572, 'loss/train': 1.4410983324050903} 08/31/2021 05:00:32 - INFO - __main__ - Step 87574: {'lr': 0.00018920090560081528, 'samples': 16814208, 'steps': 87573, 'loss/train': 1.5585076808929443} 08/31/2021 05:00:33 - INFO - __main__ - Step 87575: {'lr': 0.00018919575819416467, 'samples': 16814400, 'steps': 87574, 'loss/train': 0.043250277638435364} 08/31/2021 05:00:33 - INFO - __main__ - Step 87576: {'lr': 0.00018919061081491156, 'samples': 16814592, 'steps': 87575, 'loss/train': 0.6140099763870239} 08/31/2021 05:00:33 - INFO - __main__ - Step 87577: {'lr': 0.0001891854634630582, 'samples': 16814784, 'steps': 87576, 'loss/train': 0.670953631401062} 08/31/2021 05:00:35 - INFO - __main__ - Step 87578: {'lr': 0.0001891803161386069, 'samples': 16814976, 'steps': 87577, 'loss/train': 0.4182716906070709} 08/31/2021 05:00:35 - INFO - __main__ - Step 87579: {'lr': 0.00018917516884156007, 'samples': 16815168, 'steps': 87578, 'loss/train': 1.0520020723342896} 08/31/2021 05:00:36 - INFO - __main__ - Step 87580: {'lr': 0.00018917002157191996, 'samples': 16815360, 'steps': 87579, 'loss/train': 1.397661566734314} 08/31/2021 05:00:36 - INFO - __main__ - Step 87581: {'lr': 0.00018916487432968894, 'samples': 16815552, 'steps': 87580, 'loss/train': 1.2575052976608276} 08/31/2021 05:00:36 - INFO - __main__ - Step 87582: {'lr': 0.00018915972711486923, 'samples': 16815744, 'steps': 87581, 'loss/train': 0.26792773604393005} 08/31/2021 05:00:37 - INFO - __main__ - Step 87583: {'lr': 0.0001891545799274632, 'samples': 16815936, 'steps': 87582, 'loss/train': 1.1736465692520142} 08/31/2021 05:00:38 - INFO - __main__ - Step 87584: {'lr': 0.00018914943276747325, 'samples': 16816128, 'steps': 87583, 'loss/train': 1.4948358535766602} 08/31/2021 05:00:39 - INFO - __main__ - Step 87585: {'lr': 0.00018914428563490159, 'samples': 16816320, 'steps': 87584, 'loss/train': 1.5901509523391724} 08/31/2021 05:00:39 - INFO - __main__ - Step 87586: {'lr': 0.00018913913852975053, 'samples': 16816512, 'steps': 87585, 'loss/train': 1.3924721479415894} 08/31/2021 05:00:40 - INFO - __main__ - Step 87587: {'lr': 0.00018913399145202247, 'samples': 16816704, 'steps': 87586, 'loss/train': 1.7794057130813599} 08/31/2021 05:00:40 - INFO - __main__ - Step 87588: {'lr': 0.00018912884440171968, 'samples': 16816896, 'steps': 87587, 'loss/train': 1.110365390777588} 08/31/2021 05:00:42 - INFO - __main__ - Step 87589: {'lr': 0.0001891236973788445, 'samples': 16817088, 'steps': 87588, 'loss/train': 0.029431115835905075} 08/31/2021 05:00:42 - INFO - __main__ - Step 87590: {'lr': 0.00018911855038339923, 'samples': 16817280, 'steps': 87589, 'loss/train': 1.1346571445465088} 08/31/2021 05:00:43 - INFO - __main__ - Step 87591: {'lr': 0.00018911340341538622, 'samples': 16817472, 'steps': 87590, 'loss/train': 1.6544252634048462} 08/31/2021 05:00:43 - INFO - __main__ - Step 87592: {'lr': 0.00018910825647480781, 'samples': 16817664, 'steps': 87591, 'loss/train': 1.2989439964294434} 08/31/2021 05:00:43 - INFO - __main__ - Step 87593: {'lr': 0.00018910310956166623, 'samples': 16817856, 'steps': 87592, 'loss/train': 1.0839914083480835} 08/31/2021 05:00:45 - INFO - __main__ - Step 87594: {'lr': 0.00018909796267596384, 'samples': 16818048, 'steps': 87593, 'loss/train': 1.379433512687683} 08/31/2021 05:00:46 - INFO - __main__ - Step 87595: {'lr': 0.000189092815817703, 'samples': 16818240, 'steps': 87594, 'loss/train': 1.4698737859725952} 08/31/2021 05:00:46 - INFO - __main__ - Step 87596: {'lr': 0.00018908766898688596, 'samples': 16818432, 'steps': 87595, 'loss/train': 1.1276156902313232} 08/31/2021 05:00:46 - INFO - __main__ - Step 87597: {'lr': 0.0001890825221835151, 'samples': 16818624, 'steps': 87596, 'loss/train': 0.827409029006958} 08/31/2021 05:00:47 - INFO - __main__ - Step 87598: {'lr': 0.00018907737540759277, 'samples': 16818816, 'steps': 87597, 'loss/train': 0.02662024460732937} 08/31/2021 05:00:47 - INFO - __main__ - Step 87599: {'lr': 0.00018907222865912116, 'samples': 16819008, 'steps': 87598, 'loss/train': 0.9015306830406189} 08/31/2021 05:00:49 - INFO - __main__ - Step 87600: {'lr': 0.0001890670819381027, 'samples': 16819200, 'steps': 87599, 'loss/train': 0.7079293131828308} 08/31/2021 05:00:49 - INFO - __main__ - Step 87601: {'lr': 0.00018906193524453963, 'samples': 16819392, 'steps': 87600, 'loss/train': 0.6174303293228149} 08/31/2021 05:00:50 - INFO - __main__ - Step 87602: {'lr': 0.00018905678857843432, 'samples': 16819584, 'steps': 87601, 'loss/train': 0.6392700672149658} 08/31/2021 05:00:50 - INFO - __main__ - Step 87603: {'lr': 0.00018905164193978914, 'samples': 16819776, 'steps': 87602, 'loss/train': 1.2003666162490845} 08/31/2021 05:00:50 - INFO - __main__ - Step 87604: {'lr': 0.0001890464953286063, 'samples': 16819968, 'steps': 87603, 'loss/train': 1.1734296083450317} 08/31/2021 05:00:52 - INFO - __main__ - Step 87605: {'lr': 0.00018904134874488817, 'samples': 16820160, 'steps': 87604, 'loss/train': 1.4449400901794434} 08/31/2021 05:00:53 - INFO - __main__ - Step 87606: {'lr': 0.00018903620218863707, 'samples': 16820352, 'steps': 87605, 'loss/train': 0.9423737525939941} 08/31/2021 05:00:53 - INFO - __main__ - Step 87607: {'lr': 0.00018903105565985532, 'samples': 16820544, 'steps': 87606, 'loss/train': 1.0451629161834717} 08/31/2021 05:00:54 - INFO - __main__ - Step 87608: {'lr': 0.00018902590915854521, 'samples': 16820736, 'steps': 87607, 'loss/train': 1.2676833868026733} 08/31/2021 05:00:54 - INFO - __main__ - Step 87609: {'lr': 0.00018902076268470912, 'samples': 16820928, 'steps': 87608, 'loss/train': 1.425310730934143} 08/31/2021 05:00:54 - INFO - __main__ - Step 87610: {'lr': 0.0001890156162383493, 'samples': 16821120, 'steps': 87609, 'loss/train': 1.2389769554138184} 08/31/2021 05:00:56 - INFO - __main__ - Step 87611: {'lr': 0.00018901046981946817, 'samples': 16821312, 'steps': 87610, 'loss/train': 0.9767462015151978} 08/31/2021 05:00:56 - INFO - __main__ - Step 87612: {'lr': 0.00018900532342806795, 'samples': 16821504, 'steps': 87611, 'loss/train': 1.382727861404419} 08/31/2021 05:00:57 - INFO - __main__ - Step 87613: {'lr': 0.00018900017706415095, 'samples': 16821696, 'steps': 87612, 'loss/train': 1.247602105140686} 08/31/2021 05:00:57 - INFO - __main__ - Step 87614: {'lr': 0.00018899503072771962, 'samples': 16821888, 'steps': 87613, 'loss/train': 0.7859625816345215} 08/31/2021 05:00:57 - INFO - __main__ - Step 87615: {'lr': 0.00018898988441877612, 'samples': 16822080, 'steps': 87614, 'loss/train': 1.4916578531265259} 08/31/2021 05:00:59 - INFO - __main__ - Step 87616: {'lr': 0.0001889847381373228, 'samples': 16822272, 'steps': 87615, 'loss/train': 1.0944734811782837} 08/31/2021 05:00:59 - INFO - __main__ - Step 87617: {'lr': 0.00018897959188336205, 'samples': 16822464, 'steps': 87616, 'loss/train': 0.660775363445282} 08/31/2021 05:01:00 - INFO - __main__ - Step 87618: {'lr': 0.00018897444565689616, 'samples': 16822656, 'steps': 87617, 'loss/train': 1.2624986171722412} 08/31/2021 05:01:00 - INFO - __main__ - Step 87619: {'lr': 0.00018896929945792746, 'samples': 16822848, 'steps': 87618, 'loss/train': 0.9400045871734619} 08/31/2021 05:01:00 - INFO - __main__ - Step 87620: {'lr': 0.00018896415328645822, 'samples': 16823040, 'steps': 87619, 'loss/train': 2.221515655517578} 08/31/2021 05:01:02 - INFO - __main__ - Step 87621: {'lr': 0.0001889590071424908, 'samples': 16823232, 'steps': 87620, 'loss/train': 0.7693132162094116} 08/31/2021 05:01:02 - INFO - __main__ - Step 87622: {'lr': 0.00018895386102602753, 'samples': 16823424, 'steps': 87621, 'loss/train': 1.5172557830810547} 08/31/2021 05:01:03 - INFO - __main__ - Step 87623: {'lr': 0.00018894871493707065, 'samples': 16823616, 'steps': 87622, 'loss/train': 1.1466654539108276} 08/31/2021 05:01:03 - INFO - __main__ - Step 87624: {'lr': 0.0001889435688756226, 'samples': 16823808, 'steps': 87623, 'loss/train': 0.8831070065498352} 08/31/2021 05:01:03 - INFO - __main__ - Step 87625: {'lr': 0.00018893842284168572, 'samples': 16824000, 'steps': 87624, 'loss/train': 1.355364203453064} 08/31/2021 05:01:05 - INFO - __main__ - Step 87626: {'lr': 0.0001889332768352621, 'samples': 16824192, 'steps': 87625, 'loss/train': 0.9385840892791748} 08/31/2021 05:01:05 - INFO - __main__ - Step 87627: {'lr': 0.00018892813085635425, 'samples': 16824384, 'steps': 87626, 'loss/train': 1.0758860111236572} 08/31/2021 05:01:06 - INFO - __main__ - Step 87628: {'lr': 0.00018892298490496442, 'samples': 16824576, 'steps': 87627, 'loss/train': 1.7731623649597168} 08/31/2021 05:01:06 - INFO - __main__ - Step 87629: {'lr': 0.00018891783898109497, 'samples': 16824768, 'steps': 87628, 'loss/train': 4.559376239776611} 08/31/2021 05:01:06 - INFO - __main__ - Step 87630: {'lr': 0.00018891269308474819, 'samples': 16824960, 'steps': 87629, 'loss/train': 1.1128993034362793} 08/31/2021 05:01:08 - INFO - __main__ - Step 87631: {'lr': 0.0001889075472159264, 'samples': 16825152, 'steps': 87630, 'loss/train': 0.5233262777328491} 08/31/2021 05:01:09 - INFO - __main__ - Step 87632: {'lr': 0.00018890240137463195, 'samples': 16825344, 'steps': 87631, 'loss/train': 0.9396036267280579} 08/31/2021 05:01:09 - INFO - __main__ - Step 87633: {'lr': 0.0001888972555608671, 'samples': 16825536, 'steps': 87632, 'loss/train': 1.2016310691833496} 08/31/2021 05:01:09 - INFO - __main__ - Step 87634: {'lr': 0.00018889210977463423, 'samples': 16825728, 'steps': 87633, 'loss/train': 0.7552478909492493} 08/31/2021 05:01:10 - INFO - __main__ - Step 87635: {'lr': 0.00018888696401593563, 'samples': 16825920, 'steps': 87634, 'loss/train': 0.8119034767150879} 08/31/2021 05:01:11 - INFO - __main__ - Step 87636: {'lr': 0.0001888818182847736, 'samples': 16826112, 'steps': 87635, 'loss/train': 1.2639062404632568} 08/31/2021 05:01:12 - INFO - __main__ - Step 87637: {'lr': 0.00018887667258115048, 'samples': 16826304, 'steps': 87636, 'loss/train': 1.0716862678527832} 08/31/2021 05:01:12 - INFO - __main__ - Step 87638: {'lr': 0.00018887152690506872, 'samples': 16826496, 'steps': 87637, 'loss/train': 0.9433358311653137} 08/31/2021 05:01:13 - INFO - __main__ - Step 87639: {'lr': 0.00018886638125653038, 'samples': 16826688, 'steps': 87638, 'loss/train': 1.2667045593261719} 08/31/2021 05:01:13 - INFO - __main__ - Step 87640: {'lr': 0.00018886123563553793, 'samples': 16826880, 'steps': 87639, 'loss/train': 0.8672013282775879} 08/31/2021 05:01:13 - INFO - __main__ - Step 87641: {'lr': 0.00018885609004209365, 'samples': 16827072, 'steps': 87640, 'loss/train': 0.049089815467596054} 08/31/2021 05:01:15 - INFO - __main__ - Step 87642: {'lr': 0.0001888509444761999, 'samples': 16827264, 'steps': 87641, 'loss/train': 0.6239923238754272} 08/31/2021 05:01:15 - INFO - __main__ - Step 87643: {'lr': 0.00018884579893785892, 'samples': 16827456, 'steps': 87642, 'loss/train': 1.098771095275879} 08/31/2021 05:01:16 - INFO - __main__ - Step 87644: {'lr': 0.0001888406534270731, 'samples': 16827648, 'steps': 87643, 'loss/train': 1.2051138877868652} 08/31/2021 05:01:16 - INFO - __main__ - Step 87645: {'lr': 0.00018883550794384474, 'samples': 16827840, 'steps': 87644, 'loss/train': 1.5721015930175781} 08/31/2021 05:01:16 - INFO - __main__ - Step 87646: {'lr': 0.00018883036248817613, 'samples': 16828032, 'steps': 87645, 'loss/train': 0.6186257600784302} 08/31/2021 05:01:18 - INFO - __main__ - Step 87647: {'lr': 0.00018882521706006967, 'samples': 16828224, 'steps': 87646, 'loss/train': 1.5597294569015503} 08/31/2021 05:01:18 - INFO - __main__ - Step 87648: {'lr': 0.0001888200716595276, 'samples': 16828416, 'steps': 87647, 'loss/train': 1.232041835784912} 08/31/2021 05:01:19 - INFO - __main__ - Step 87649: {'lr': 0.00018881492628655222, 'samples': 16828608, 'steps': 87648, 'loss/train': 1.6671818494796753} 08/31/2021 05:01:19 - INFO - __main__ - Step 87650: {'lr': 0.0001888097809411459, 'samples': 16828800, 'steps': 87649, 'loss/train': 1.6673823595046997} 08/31/2021 05:01:19 - INFO - __main__ - Step 87651: {'lr': 0.00018880463562331114, 'samples': 16828992, 'steps': 87650, 'loss/train': 1.4508662223815918} 08/31/2021 05:01:21 - INFO - __main__ - Step 87652: {'lr': 0.00018879949033304987, 'samples': 16829184, 'steps': 87651, 'loss/train': 1.0213290452957153} 08/31/2021 05:01:21 - INFO - __main__ - Step 87653: {'lr': 0.00018879434507036464, 'samples': 16829376, 'steps': 87652, 'loss/train': 1.2162737846374512} 08/31/2021 05:01:22 - INFO - __main__ - Step 87654: {'lr': 0.00018878919983525771, 'samples': 16829568, 'steps': 87653, 'loss/train': 1.2505362033843994} 08/31/2021 05:01:22 - INFO - __main__ - Step 87655: {'lr': 0.00018878405462773146, 'samples': 16829760, 'steps': 87654, 'loss/train': 1.1380488872528076} 08/31/2021 05:01:22 - INFO - __main__ - Step 87656: {'lr': 0.00018877890944778814, 'samples': 16829952, 'steps': 87655, 'loss/train': 1.405378818511963} 08/31/2021 05:01:23 - INFO - __main__ - Step 87657: {'lr': 0.00018877376429543013, 'samples': 16830144, 'steps': 87656, 'loss/train': 1.4562500715255737} 08/31/2021 05:01:25 - INFO - __main__ - Step 87658: {'lr': 0.0001887686191706597, 'samples': 16830336, 'steps': 87657, 'loss/train': 1.42887544631958} 08/31/2021 05:01:25 - INFO - __main__ - Step 87659: {'lr': 0.00018876347407347914, 'samples': 16830528, 'steps': 87658, 'loss/train': 4.5748209953308105} 08/31/2021 05:01:26 - INFO - __main__ - Step 87660: {'lr': 0.0001887583290038909, 'samples': 16830720, 'steps': 87659, 'loss/train': 0.8782449960708618} 08/31/2021 05:01:26 - INFO - __main__ - Step 87661: {'lr': 0.00018875318396189718, 'samples': 16830912, 'steps': 87660, 'loss/train': 1.4055585861206055} 08/31/2021 05:01:26 - INFO - __main__ - Step 87662: {'lr': 0.0001887480389475003, 'samples': 16831104, 'steps': 87661, 'loss/train': 1.1401381492614746} 08/31/2021 05:01:28 - INFO - __main__ - Step 87663: {'lr': 0.00018874289396070263, 'samples': 16831296, 'steps': 87662, 'loss/train': 1.4099528789520264} 08/31/2021 05:01:29 - INFO - __main__ - Step 87664: {'lr': 0.00018873774900150645, 'samples': 16831488, 'steps': 87663, 'loss/train': 1.1233681440353394} 08/31/2021 05:01:29 - INFO - __main__ - Step 87665: {'lr': 0.00018873260406991423, 'samples': 16831680, 'steps': 87664, 'loss/train': 0.618031919002533} 08/31/2021 05:01:29 - INFO - __main__ - Step 87666: {'lr': 0.00018872745916592804, 'samples': 16831872, 'steps': 87665, 'loss/train': 0.6951519846916199} 08/31/2021 05:01:30 - INFO - __main__ - Step 87667: {'lr': 0.00018872231428955028, 'samples': 16832064, 'steps': 87666, 'loss/train': 0.049467068165540695} 08/31/2021 05:01:31 - INFO - __main__ - Step 87668: {'lr': 0.00018871716944078332, 'samples': 16832256, 'steps': 87667, 'loss/train': 1.3738692998886108} 08/31/2021 05:01:32 - INFO - __main__ - Step 87669: {'lr': 0.00018871202461962947, 'samples': 16832448, 'steps': 87668, 'loss/train': 0.8642687201499939} 08/31/2021 05:01:32 - INFO - __main__ - Step 87670: {'lr': 0.00018870687982609102, 'samples': 16832640, 'steps': 87669, 'loss/train': 0.9849345684051514} 08/31/2021 05:01:32 - INFO - __main__ - Step 87671: {'lr': 0.0001887017350601703, 'samples': 16832832, 'steps': 87670, 'loss/train': 0.7856100797653198} 08/31/2021 05:01:33 - INFO - __main__ - Step 87672: {'lr': 0.00018869659032186964, 'samples': 16833024, 'steps': 87671, 'loss/train': 0.7346975207328796} 08/31/2021 05:01:34 - INFO - __main__ - Step 87673: {'lr': 0.00018869144561119137, 'samples': 16833216, 'steps': 87672, 'loss/train': 0.5098791718482971} 08/31/2021 05:01:35 - INFO - __main__ - Step 87674: {'lr': 0.00018868630092813777, 'samples': 16833408, 'steps': 87673, 'loss/train': 1.5095820426940918} 08/31/2021 05:01:35 - INFO - __main__ - Step 87675: {'lr': 0.00018868115627271117, 'samples': 16833600, 'steps': 87674, 'loss/train': 0.38220322132110596} 08/31/2021 05:01:35 - INFO - __main__ - Step 87676: {'lr': 0.0001886760116449139, 'samples': 16833792, 'steps': 87675, 'loss/train': 2.2256691455841064} 08/31/2021 05:01:36 - INFO - __main__ - Step 87677: {'lr': 0.00018867086704474828, 'samples': 16833984, 'steps': 87676, 'loss/train': 1.6846940517425537} 08/31/2021 05:01:36 - INFO - __main__ - Step 87678: {'lr': 0.00018866572247221676, 'samples': 16834176, 'steps': 87677, 'loss/train': 0.7473151087760925} 08/31/2021 05:01:38 - INFO - __main__ - Step 87679: {'lr': 0.00018866057792732137, 'samples': 16834368, 'steps': 87678, 'loss/train': 0.5471866130828857} 08/31/2021 05:01:38 - INFO - __main__ - Step 87680: {'lr': 0.0001886554334100646, 'samples': 16834560, 'steps': 87679, 'loss/train': 1.7186557054519653} 08/31/2021 05:01:38 - INFO - __main__ - Step 87681: {'lr': 0.0001886502889204487, 'samples': 16834752, 'steps': 87680, 'loss/train': 1.3499863147735596} 08/31/2021 05:01:39 - INFO - __main__ - Step 87682: {'lr': 0.00018864514445847606, 'samples': 16834944, 'steps': 87681, 'loss/train': 1.0364683866500854} 08/31/2021 05:01:39 - INFO - __main__ - Step 87683: {'lr': 0.00018864000002414896, 'samples': 16835136, 'steps': 87682, 'loss/train': 0.30979469418525696} 08/31/2021 05:01:41 - INFO - __main__ - Step 87684: {'lr': 0.00018863485561746975, 'samples': 16835328, 'steps': 87683, 'loss/train': 1.6548479795455933} 08/31/2021 05:01:41 - INFO - __main__ - Step 87685: {'lr': 0.00018862971123844073, 'samples': 16835520, 'steps': 87684, 'loss/train': 1.2075875997543335} 08/31/2021 05:01:41 - INFO - __main__ - Step 87686: {'lr': 0.0001886245668870642, 'samples': 16835712, 'steps': 87685, 'loss/train': 1.482149600982666} 08/31/2021 05:01:42 - INFO - __main__ - Step 87687: {'lr': 0.0001886194225633425, 'samples': 16835904, 'steps': 87686, 'loss/train': 1.4967635869979858} 08/31/2021 05:01:42 - INFO - __main__ - Step 87688: {'lr': 0.00018861427826727793, 'samples': 16836096, 'steps': 87687, 'loss/train': 1.0802104473114014} 08/31/2021 05:01:44 - INFO - __main__ - Step 87689: {'lr': 0.0001886091339988728, 'samples': 16836288, 'steps': 87688, 'loss/train': 1.497554898262024} 08/31/2021 05:01:44 - INFO - __main__ - Step 87690: {'lr': 0.00018860398975812948, 'samples': 16836480, 'steps': 87689, 'loss/train': 0.9380743503570557} 08/31/2021 05:01:44 - INFO - __main__ - Step 87691: {'lr': 0.00018859884554505026, 'samples': 16836672, 'steps': 87690, 'loss/train': 0.8468037843704224} 08/31/2021 05:01:45 - INFO - __main__ - Step 87692: {'lr': 0.00018859370135963755, 'samples': 16836864, 'steps': 87691, 'loss/train': 1.1663777828216553} 08/31/2021 05:01:45 - INFO - __main__ - Step 87693: {'lr': 0.00018858855720189346, 'samples': 16837056, 'steps': 87692, 'loss/train': 1.5370224714279175} 08/31/2021 05:01:47 - INFO - __main__ - Step 87694: {'lr': 0.0001885834130718204, 'samples': 16837248, 'steps': 87693, 'loss/train': 1.4168463945388794} 08/31/2021 05:01:47 - INFO - __main__ - Step 87695: {'lr': 0.00018857826896942077, 'samples': 16837440, 'steps': 87694, 'loss/train': 1.0090280771255493} 08/31/2021 05:01:47 - INFO - __main__ - Step 87696: {'lr': 0.00018857312489469676, 'samples': 16837632, 'steps': 87695, 'loss/train': 1.5642423629760742} 08/31/2021 05:01:48 - INFO - __main__ - Step 87697: {'lr': 0.0001885679808476508, 'samples': 16837824, 'steps': 87696, 'loss/train': 0.4360247850418091} 08/31/2021 05:01:48 - INFO - __main__ - Step 87698: {'lr': 0.00018856283682828514, 'samples': 16838016, 'steps': 87697, 'loss/train': 0.028989067301154137} 08/31/2021 05:01:51 - INFO - __main__ - Step 87699: {'lr': 0.00018855769283660206, 'samples': 16838208, 'steps': 87698, 'loss/train': 0.578815758228302} 08/31/2021 05:01:51 - INFO - __main__ - Step 87700: {'lr': 0.000188552548872604, 'samples': 16838400, 'steps': 87699, 'loss/train': 1.4242284297943115} 08/31/2021 05:01:51 - INFO - __main__ - Step 87701: {'lr': 0.0001885474049362932, 'samples': 16838592, 'steps': 87700, 'loss/train': 0.7125387787818909} 08/31/2021 05:01:52 - INFO - __main__ - Step 87702: {'lr': 0.000188542261027672, 'samples': 16838784, 'steps': 87701, 'loss/train': 0.3816681206226349} 08/31/2021 05:01:52 - INFO - __main__ - Step 87703: {'lr': 0.0001885371171467427, 'samples': 16838976, 'steps': 87702, 'loss/train': 0.34239572286605835} 08/31/2021 05:01:52 - INFO - __main__ - Step 87704: {'lr': 0.00018853197329350764, 'samples': 16839168, 'steps': 87703, 'loss/train': 1.4232187271118164} 08/31/2021 05:01:54 - INFO - __main__ - Step 87705: {'lr': 0.0001885268294679692, 'samples': 16839360, 'steps': 87704, 'loss/train': 0.9564942121505737} 08/31/2021 05:01:54 - INFO - __main__ - Step 87706: {'lr': 0.00018852168567012954, 'samples': 16839552, 'steps': 87705, 'loss/train': 1.3402228355407715} 08/31/2021 05:01:55 - INFO - __main__ - Step 87707: {'lr': 0.00018851654189999103, 'samples': 16839744, 'steps': 87706, 'loss/train': 0.8834487199783325} 08/31/2021 05:01:55 - INFO - __main__ - Step 87708: {'lr': 0.00018851139815755606, 'samples': 16839936, 'steps': 87707, 'loss/train': 1.4697798490524292} 08/31/2021 05:01:55 - INFO - __main__ - Step 87709: {'lr': 0.00018850625444282688, 'samples': 16840128, 'steps': 87708, 'loss/train': 0.9187296628952026} 08/31/2021 05:01:56 - INFO - __main__ - Step 87710: {'lr': 0.00018850111075580583, 'samples': 16840320, 'steps': 87709, 'loss/train': 1.0200681686401367} 08/31/2021 05:01:57 - INFO - __main__ - Step 87711: {'lr': 0.00018849596709649526, 'samples': 16840512, 'steps': 87710, 'loss/train': 1.2679914236068726} 08/31/2021 05:01:58 - INFO - __main__ - Step 87712: {'lr': 0.00018849082346489743, 'samples': 16840704, 'steps': 87711, 'loss/train': 0.7841387987136841} 08/31/2021 05:01:58 - INFO - __main__ - Step 87713: {'lr': 0.00018848567986101466, 'samples': 16840896, 'steps': 87712, 'loss/train': 0.34043851494789124} 08/31/2021 05:01:58 - INFO - __main__ - Step 87714: {'lr': 0.00018848053628484936, 'samples': 16841088, 'steps': 87713, 'loss/train': 1.3184776306152344} 08/31/2021 05:01:59 - INFO - __main__ - Step 87715: {'lr': 0.00018847539273640374, 'samples': 16841280, 'steps': 87714, 'loss/train': 1.0883190631866455} 08/31/2021 05:02:01 - INFO - __main__ - Step 87716: {'lr': 0.0001884702492156802, 'samples': 16841472, 'steps': 87715, 'loss/train': 0.8511882424354553} 08/31/2021 05:02:02 - INFO - __main__ - Step 87717: {'lr': 0.000188465105722681, 'samples': 16841664, 'steps': 87716, 'loss/train': 0.8164122104644775} 08/31/2021 05:02:02 - INFO - __main__ - Step 87718: {'lr': 0.00018845996225740844, 'samples': 16841856, 'steps': 87717, 'loss/train': 0.1054539829492569} 08/31/2021 05:02:02 - INFO - __main__ - Step 87719: {'lr': 0.00018845481881986495, 'samples': 16842048, 'steps': 87718, 'loss/train': 1.2411892414093018} 08/31/2021 05:02:03 - INFO - __main__ - Step 87720: {'lr': 0.0001884496754100527, 'samples': 16842240, 'steps': 87719, 'loss/train': 0.8426893353462219} 08/31/2021 05:02:04 - INFO - __main__ - Step 87721: {'lr': 0.00018844453202797407, 'samples': 16842432, 'steps': 87720, 'loss/train': 0.6768439412117004} 08/31/2021 05:02:05 - INFO - __main__ - Step 87722: {'lr': 0.0001884393886736314, 'samples': 16842624, 'steps': 87721, 'loss/train': 0.9961228370666504} 08/31/2021 05:02:05 - INFO - __main__ - Step 87723: {'lr': 0.000188434245347027, 'samples': 16842816, 'steps': 87722, 'loss/train': 1.288070559501648} 08/31/2021 05:02:05 - INFO - __main__ - Step 87724: {'lr': 0.00018842910204816315, 'samples': 16843008, 'steps': 87723, 'loss/train': 1.1136776208877563} 08/31/2021 05:02:06 - INFO - __main__ - Step 87725: {'lr': 0.00018842395877704222, 'samples': 16843200, 'steps': 87724, 'loss/train': 0.4457085430622101} 08/31/2021 05:02:07 - INFO - __main__ - Step 87726: {'lr': 0.00018841881553366652, 'samples': 16843392, 'steps': 87725, 'loss/train': 1.2360467910766602} 08/31/2021 05:02:08 - INFO - __main__ - Step 87727: {'lr': 0.00018841367231803836, 'samples': 16843584, 'steps': 87726, 'loss/train': 0.8075674176216125} 08/31/2021 05:02:08 - INFO - __main__ - Step 87728: {'lr': 0.00018840852913016, 'samples': 16843776, 'steps': 87727, 'loss/train': 1.7552430629730225} 08/31/2021 05:02:09 - INFO - __main__ - Step 87729: {'lr': 0.00018840338597003384, 'samples': 16843968, 'steps': 87728, 'loss/train': 2.1889073848724365} 08/31/2021 05:02:09 - INFO - __main__ - Step 87730: {'lr': 0.00018839824283766216, 'samples': 16844160, 'steps': 87729, 'loss/train': 1.1064380407333374} 08/31/2021 05:02:09 - INFO - __main__ - Step 87731: {'lr': 0.00018839309973304728, 'samples': 16844352, 'steps': 87730, 'loss/train': 1.1826772689819336} 08/31/2021 05:02:11 - INFO - __main__ - Step 87732: {'lr': 0.00018838795665619156, 'samples': 16844544, 'steps': 87731, 'loss/train': 1.367646336555481} 08/31/2021 05:02:11 - INFO - __main__ - Step 87733: {'lr': 0.00018838281360709718, 'samples': 16844736, 'steps': 87732, 'loss/train': 1.0209847688674927} 08/31/2021 05:02:12 - INFO - __main__ - Step 87734: {'lr': 0.00018837767058576662, 'samples': 16844928, 'steps': 87733, 'loss/train': 1.0556539297103882} 08/31/2021 05:02:12 - INFO - __main__ - Step 87735: {'lr': 0.0001883725275922021, 'samples': 16845120, 'steps': 87734, 'loss/train': 1.2140153646469116} 08/31/2021 05:02:12 - INFO - __main__ - Step 87736: {'lr': 0.000188367384626406, 'samples': 16845312, 'steps': 87735, 'loss/train': 1.4816359281539917} 08/31/2021 05:02:14 - INFO - __main__ - Step 87737: {'lr': 0.00018836224168838062, 'samples': 16845504, 'steps': 87736, 'loss/train': 1.1854413747787476} 08/31/2021 05:02:14 - INFO - __main__ - Step 87738: {'lr': 0.00018835709877812823, 'samples': 16845696, 'steps': 87737, 'loss/train': 0.6264582872390747} 08/31/2021 05:02:15 - INFO - __main__ - Step 87739: {'lr': 0.0001883519558956512, 'samples': 16845888, 'steps': 87738, 'loss/train': 0.6552189588546753} 08/31/2021 05:02:15 - INFO - __main__ - Step 87740: {'lr': 0.00018834681304095177, 'samples': 16846080, 'steps': 87739, 'loss/train': 1.4156805276870728} 08/31/2021 05:02:15 - INFO - __main__ - Step 87741: {'lr': 0.00018834167021403235, 'samples': 16846272, 'steps': 87740, 'loss/train': 0.919901430606842} 08/31/2021 05:02:16 - INFO - __main__ - Step 87742: {'lr': 0.0001883365274148952, 'samples': 16846464, 'steps': 87741, 'loss/train': 0.8981384038925171} 08/31/2021 05:02:17 - INFO - __main__ - Step 87743: {'lr': 0.00018833138464354268, 'samples': 16846656, 'steps': 87742, 'loss/train': 0.8784300088882446} 08/31/2021 05:02:18 - INFO - __main__ - Step 87744: {'lr': 0.0001883262418999771, 'samples': 16846848, 'steps': 87743, 'loss/train': 0.7421632409095764} 08/31/2021 05:02:18 - INFO - __main__ - Step 87745: {'lr': 0.00018832109918420073, 'samples': 16847040, 'steps': 87744, 'loss/train': 1.7716513872146606} 08/31/2021 05:02:18 - INFO - __main__ - Step 87746: {'lr': 0.000188315956496216, 'samples': 16847232, 'steps': 87745, 'loss/train': 1.233412265777588} 08/31/2021 05:02:19 - INFO - __main__ - Step 87747: {'lr': 0.00018831081383602512, 'samples': 16847424, 'steps': 87746, 'loss/train': 1.0770777463912964} 08/31/2021 05:02:20 - INFO - __main__ - Step 87748: {'lr': 0.00018830567120363043, 'samples': 16847616, 'steps': 87747, 'loss/train': 1.346032977104187} 08/31/2021 05:02:21 - INFO - __main__ - Step 87749: {'lr': 0.00018830052859903425, 'samples': 16847808, 'steps': 87748, 'loss/train': 1.3188834190368652} 08/31/2021 05:02:21 - INFO - __main__ - Step 87750: {'lr': 0.00018829538602223883, 'samples': 16848000, 'steps': 87749, 'loss/train': 1.1759768724441528} 08/31/2021 05:02:21 - INFO - __main__ - Step 87751: {'lr': 0.0001882902434732466, 'samples': 16848192, 'steps': 87750, 'loss/train': 1.685357689857483} 08/31/2021 05:02:22 - INFO - __main__ - Step 87752: {'lr': 0.00018828510095205987, 'samples': 16848384, 'steps': 87751, 'loss/train': 0.6877356171607971} 08/31/2021 05:02:24 - INFO - __main__ - Step 87753: {'lr': 0.00018827995845868088, 'samples': 16848576, 'steps': 87752, 'loss/train': 1.2399040460586548} 08/31/2021 05:02:24 - INFO - __main__ - Step 87754: {'lr': 0.00018827481599311197, 'samples': 16848768, 'steps': 87753, 'loss/train': 1.7543489933013916} 08/31/2021 05:02:25 - INFO - __main__ - Step 87755: {'lr': 0.0001882696735553555, 'samples': 16848960, 'steps': 87754, 'loss/train': 0.04037616401910782} 08/31/2021 05:02:25 - INFO - __main__ - Step 87756: {'lr': 0.00018826453114541378, 'samples': 16849152, 'steps': 87755, 'loss/train': 0.0845833420753479} 08/31/2021 05:02:25 - INFO - __main__ - Step 87757: {'lr': 0.00018825938876328909, 'samples': 16849344, 'steps': 87756, 'loss/train': 1.255202054977417} 08/31/2021 05:02:26 - INFO - __main__ - Step 87758: {'lr': 0.00018825424640898374, 'samples': 16849536, 'steps': 87757, 'loss/train': 0.21684859693050385} 08/31/2021 05:02:27 - INFO - __main__ - Step 87759: {'lr': 0.00018824910408250022, 'samples': 16849728, 'steps': 87758, 'loss/train': 0.9889643788337708} 08/31/2021 05:02:28 - INFO - __main__ - Step 87760: {'lr': 0.0001882439617838406, 'samples': 16849920, 'steps': 87759, 'loss/train': 0.8782464861869812} 08/31/2021 05:02:28 - INFO - __main__ - Step 87761: {'lr': 0.00018823881951300728, 'samples': 16850112, 'steps': 87760, 'loss/train': 1.334596037864685} 08/31/2021 05:02:28 - INFO - __main__ - Step 87762: {'lr': 0.00018823367727000258, 'samples': 16850304, 'steps': 87761, 'loss/train': 1.3833587169647217} 08/31/2021 05:02:29 - INFO - __main__ - Step 87763: {'lr': 0.00018822853505482887, 'samples': 16850496, 'steps': 87762, 'loss/train': 1.8146984577178955} 08/31/2021 05:02:30 - INFO - __main__ - Step 87764: {'lr': 0.0001882233928674884, 'samples': 16850688, 'steps': 87763, 'loss/train': 1.7101967334747314} 08/31/2021 05:02:31 - INFO - __main__ - Step 87765: {'lr': 0.00018821825070798354, 'samples': 16850880, 'steps': 87764, 'loss/train': 1.0667911767959595} 08/31/2021 05:02:31 - INFO - __main__ - Step 87766: {'lr': 0.00018821310857631654, 'samples': 16851072, 'steps': 87765, 'loss/train': 0.9922916293144226} 08/31/2021 05:02:31 - INFO - __main__ - Step 87767: {'lr': 0.00018820796647248982, 'samples': 16851264, 'steps': 87766, 'loss/train': 0.9645146727561951} 08/31/2021 05:02:32 - INFO - __main__ - Step 87768: {'lr': 0.00018820282439650557, 'samples': 16851456, 'steps': 87767, 'loss/train': 1.168538212776184} 08/31/2021 05:02:32 - INFO - __main__ - Step 87769: {'lr': 0.0001881976823483662, 'samples': 16851648, 'steps': 87768, 'loss/train': 0.6766788363456726} 08/31/2021 05:02:34 - INFO - __main__ - Step 87770: {'lr': 0.00018819254032807403, 'samples': 16851840, 'steps': 87769, 'loss/train': 1.4775499105453491} 08/31/2021 05:02:35 - INFO - __main__ - Step 87771: {'lr': 0.0001881873983356313, 'samples': 16852032, 'steps': 87770, 'loss/train': 1.3530224561691284} 08/31/2021 05:02:35 - INFO - __main__ - Step 87772: {'lr': 0.00018818225637104053, 'samples': 16852224, 'steps': 87771, 'loss/train': 0.11436553299427032} 08/31/2021 05:02:35 - INFO - __main__ - Step 87773: {'lr': 0.00018817711443430373, 'samples': 16852416, 'steps': 87772, 'loss/train': 1.6147940158843994} 08/31/2021 05:02:36 - INFO - __main__ - Step 87774: {'lr': 0.0001881719725254234, 'samples': 16852608, 'steps': 87773, 'loss/train': 1.396083950996399} 08/31/2021 05:02:37 - INFO - __main__ - Step 87775: {'lr': 0.0001881668306444018, 'samples': 16852800, 'steps': 87774, 'loss/train': 1.268493890762329} 08/31/2021 05:02:38 - INFO - __main__ - Step 87776: {'lr': 0.0001881616887912413, 'samples': 16852992, 'steps': 87775, 'loss/train': 0.7227810621261597} 08/31/2021 05:02:38 - INFO - __main__ - Step 87777: {'lr': 0.00018815654696594417, 'samples': 16853184, 'steps': 87776, 'loss/train': 0.4632784426212311} 08/31/2021 05:02:38 - INFO - __main__ - Step 87778: {'lr': 0.00018815140516851276, 'samples': 16853376, 'steps': 87777, 'loss/train': 1.2511202096939087} 08/31/2021 05:02:39 - INFO - __main__ - Step 87779: {'lr': 0.00018814626339894936, 'samples': 16853568, 'steps': 87778, 'loss/train': 1.2325814962387085} 08/31/2021 05:02:40 - INFO - __main__ - Step 87780: {'lr': 0.0001881411216572563, 'samples': 16853760, 'steps': 87779, 'loss/train': 0.9317692518234253} 08/31/2021 05:02:41 - INFO - __main__ - Step 87781: {'lr': 0.00018813597994343589, 'samples': 16853952, 'steps': 87780, 'loss/train': 1.8736544847488403} 08/31/2021 05:02:41 - INFO - __main__ - Step 87782: {'lr': 0.00018813083825749047, 'samples': 16854144, 'steps': 87781, 'loss/train': 0.7608731985092163} 08/31/2021 05:02:42 - INFO - __main__ - Step 87783: {'lr': 0.00018812569659942233, 'samples': 16854336, 'steps': 87782, 'loss/train': 1.0685367584228516} 08/31/2021 05:02:42 - INFO - __main__ - Step 87784: {'lr': 0.0001881205549692338, 'samples': 16854528, 'steps': 87783, 'loss/train': 0.18216849863529205} 08/31/2021 05:02:43 - INFO - __main__ - Step 87785: {'lr': 0.00018811541336692718, 'samples': 16854720, 'steps': 87784, 'loss/train': 1.403089165687561} 08/31/2021 05:02:44 - INFO - __main__ - Step 87786: {'lr': 0.0001881102717925049, 'samples': 16854912, 'steps': 87785, 'loss/train': 1.5599688291549683} 08/31/2021 05:02:44 - INFO - __main__ - Step 87787: {'lr': 0.00018810513024596908, 'samples': 16855104, 'steps': 87786, 'loss/train': 1.6833535432815552} 08/31/2021 05:02:45 - INFO - __main__ - Step 87788: {'lr': 0.00018809998872732219, 'samples': 16855296, 'steps': 87787, 'loss/train': 1.133932113647461} 08/31/2021 05:02:45 - INFO - __main__ - Step 87789: {'lr': 0.00018809484723656642, 'samples': 16855488, 'steps': 87788, 'loss/train': 1.1176856756210327} 08/31/2021 05:02:47 - INFO - __main__ - Step 87790: {'lr': 0.00018808970577370416, 'samples': 16855680, 'steps': 87789, 'loss/train': 1.0640281438827515} 08/31/2021 05:02:47 - INFO - __main__ - Step 87791: {'lr': 0.00018808456433873775, 'samples': 16855872, 'steps': 87790, 'loss/train': 0.8947929739952087} 08/31/2021 05:02:47 - INFO - __main__ - Step 87792: {'lr': 0.00018807942293166946, 'samples': 16856064, 'steps': 87791, 'loss/train': 1.138733983039856} 08/31/2021 05:02:48 - INFO - __main__ - Step 87793: {'lr': 0.00018807428155250165, 'samples': 16856256, 'steps': 87792, 'loss/train': 1.1945332288742065} 08/31/2021 05:02:48 - INFO - __main__ - Step 87794: {'lr': 0.00018806914020123657, 'samples': 16856448, 'steps': 87793, 'loss/train': 0.7799059748649597} 08/31/2021 05:02:48 - INFO - __main__ - Step 87795: {'lr': 0.00018806399887787663, 'samples': 16856640, 'steps': 87794, 'loss/train': 1.197265625} 08/31/2021 05:02:50 - INFO - __main__ - Step 87796: {'lr': 0.00018805885758242408, 'samples': 16856832, 'steps': 87795, 'loss/train': 0.9948073625564575} 08/31/2021 05:02:50 - INFO - __main__ - Step 87797: {'lr': 0.00018805371631488125, 'samples': 16857024, 'steps': 87796, 'loss/train': 0.731002688407898} 08/31/2021 05:02:51 - INFO - __main__ - Step 87798: {'lr': 0.00018804857507525045, 'samples': 16857216, 'steps': 87797, 'loss/train': 0.07261429727077484} 08/31/2021 05:02:51 - INFO - __main__ - Step 87799: {'lr': 0.00018804343386353412, 'samples': 16857408, 'steps': 87798, 'loss/train': 2.004716396331787} 08/31/2021 05:02:51 - INFO - __main__ - Step 87800: {'lr': 0.00018803829267973436, 'samples': 16857600, 'steps': 87799, 'loss/train': 1.595908522605896} 08/31/2021 05:02:53 - INFO - __main__ - Step 87801: {'lr': 0.0001880331515238536, 'samples': 16857792, 'steps': 87800, 'loss/train': 1.069930076599121} 08/31/2021 05:02:53 - INFO - __main__ - Step 87802: {'lr': 0.00018802801039589413, 'samples': 16857984, 'steps': 87801, 'loss/train': 1.2658032178878784} 08/31/2021 05:02:54 - INFO - __main__ - Step 87803: {'lr': 0.00018802286929585826, 'samples': 16858176, 'steps': 87802, 'loss/train': 0.06709493696689606} 08/31/2021 05:02:54 - INFO - __main__ - Step 87804: {'lr': 0.00018801772822374835, 'samples': 16858368, 'steps': 87803, 'loss/train': 1.3256858587265015} 08/31/2021 05:02:54 - INFO - __main__ - Step 87805: {'lr': 0.0001880125871795667, 'samples': 16858560, 'steps': 87804, 'loss/train': 2.2524569034576416} 08/31/2021 05:02:56 - INFO - __main__ - Step 87806: {'lr': 0.00018800744616331562, 'samples': 16858752, 'steps': 87805, 'loss/train': 1.4279394149780273} 08/31/2021 05:02:56 - INFO - __main__ - Step 87807: {'lr': 0.00018800230517499743, 'samples': 16858944, 'steps': 87806, 'loss/train': 1.259835124015808} 08/31/2021 05:02:57 - INFO - __main__ - Step 87808: {'lr': 0.00018799716421461442, 'samples': 16859136, 'steps': 87807, 'loss/train': 1.1712496280670166} 08/31/2021 05:02:57 - INFO - __main__ - Step 87809: {'lr': 0.00018799202328216897, 'samples': 16859328, 'steps': 87808, 'loss/train': 1.1456717252731323} 08/31/2021 05:02:57 - INFO - __main__ - Step 87810: {'lr': 0.00018798688237766335, 'samples': 16859520, 'steps': 87809, 'loss/train': 0.7487286925315857} 08/31/2021 05:02:58 - INFO - __main__ - Step 87811: {'lr': 0.00018798174150109988, 'samples': 16859712, 'steps': 87810, 'loss/train': 1.3180510997772217} 08/31/2021 05:02:59 - INFO - __main__ - Step 87812: {'lr': 0.00018797660065248084, 'samples': 16859904, 'steps': 87811, 'loss/train': 1.2285306453704834} 08/31/2021 05:03:00 - INFO - __main__ - Step 87813: {'lr': 0.00018797145983180875, 'samples': 16860096, 'steps': 87812, 'loss/train': 1.5132790803909302} 08/31/2021 05:03:00 - INFO - __main__ - Step 87814: {'lr': 0.00018796631903908562, 'samples': 16860288, 'steps': 87813, 'loss/train': 1.0919033288955688} 08/31/2021 05:03:00 - INFO - __main__ - Step 87815: {'lr': 0.00018796117827431396, 'samples': 16860480, 'steps': 87814, 'loss/train': 0.4598868787288666} 08/31/2021 05:03:01 - INFO - __main__ - Step 87816: {'lr': 0.00018795603753749595, 'samples': 16860672, 'steps': 87815, 'loss/train': 3.613938331604004} 08/31/2021 05:03:02 - INFO - __main__ - Step 87817: {'lr': 0.00018795089682863405, 'samples': 16860864, 'steps': 87816, 'loss/train': 1.5138834714889526} 08/31/2021 05:03:03 - INFO - __main__ - Step 87818: {'lr': 0.00018794575614773052, 'samples': 16861056, 'steps': 87817, 'loss/train': 0.8352594375610352} 08/31/2021 05:03:03 - INFO - __main__ - Step 87819: {'lr': 0.00018794061549478767, 'samples': 16861248, 'steps': 87818, 'loss/train': 1.2662397623062134} 08/31/2021 05:03:03 - INFO - __main__ - Step 87820: {'lr': 0.0001879354748698078, 'samples': 16861440, 'steps': 87819, 'loss/train': 1.1483172178268433} 08/31/2021 05:03:04 - INFO - __main__ - Step 87821: {'lr': 0.00018793033427279328, 'samples': 16861632, 'steps': 87820, 'loss/train': 1.2029613256454468} 08/31/2021 05:03:05 - INFO - __main__ - Step 87822: {'lr': 0.00018792519370374638, 'samples': 16861824, 'steps': 87821, 'loss/train': 0.9245237708091736} 08/31/2021 05:03:06 - INFO - __main__ - Step 87823: {'lr': 0.00018792005316266942, 'samples': 16862016, 'steps': 87822, 'loss/train': 1.3068734407424927} 08/31/2021 05:03:06 - INFO - __main__ - Step 87824: {'lr': 0.00018791491264956472, 'samples': 16862208, 'steps': 87823, 'loss/train': 1.1754329204559326} 08/31/2021 05:03:06 - INFO - __main__ - Step 87825: {'lr': 0.0001879097721644346, 'samples': 16862400, 'steps': 87824, 'loss/train': 1.1233559846878052} 08/31/2021 05:03:07 - INFO - __main__ - Step 87826: {'lr': 0.00018790463170728153, 'samples': 16862592, 'steps': 87825, 'loss/train': 0.1842261701822281} 08/31/2021 05:03:09 - INFO - __main__ - Step 87827: {'lr': 0.00018789949127810755, 'samples': 16862784, 'steps': 87826, 'loss/train': 1.228790283203125} 08/31/2021 05:03:09 - INFO - __main__ - Step 87828: {'lr': 0.0001878943508769151, 'samples': 16862976, 'steps': 87827, 'loss/train': 1.0003752708435059} 08/31/2021 05:03:10 - INFO - __main__ - Step 87829: {'lr': 0.00018788921050370646, 'samples': 16863168, 'steps': 87828, 'loss/train': 1.1449978351593018} 08/31/2021 05:03:10 - INFO - __main__ - Step 87830: {'lr': 0.000187884070158484, 'samples': 16863360, 'steps': 87829, 'loss/train': 0.8037636280059814} 08/31/2021 05:03:10 - INFO - __main__ - Step 87831: {'lr': 0.00018787892984125005, 'samples': 16863552, 'steps': 87830, 'loss/train': 1.123879075050354} 08/31/2021 05:03:12 - INFO - __main__ - Step 87832: {'lr': 0.00018787378955200686, 'samples': 16863744, 'steps': 87831, 'loss/train': 0.9916397333145142} 08/31/2021 05:03:12 - INFO - __main__ - Step 87833: {'lr': 0.00018786864929075682, 'samples': 16863936, 'steps': 87832, 'loss/train': 1.2720129489898682} 08/31/2021 05:03:13 - INFO - __main__ - Step 87834: {'lr': 0.00018786350905750215, 'samples': 16864128, 'steps': 87833, 'loss/train': 0.7879672646522522} 08/31/2021 05:03:13 - INFO - __main__ - Step 87835: {'lr': 0.00018785836885224527, 'samples': 16864320, 'steps': 87834, 'loss/train': 1.3344651460647583} 08/31/2021 05:03:13 - INFO - __main__ - Step 87836: {'lr': 0.00018785322867498843, 'samples': 16864512, 'steps': 87835, 'loss/train': 0.4690137505531311} 08/31/2021 05:03:14 - INFO - __main__ - Step 87837: {'lr': 0.00018784808852573398, 'samples': 16864704, 'steps': 87836, 'loss/train': 1.1503745317459106} 08/31/2021 05:03:16 - INFO - __main__ - Step 87838: {'lr': 0.0001878429484044842, 'samples': 16864896, 'steps': 87837, 'loss/train': 0.6367311477661133} 08/31/2021 05:03:16 - INFO - __main__ - Step 87839: {'lr': 0.0001878378083112415, 'samples': 16865088, 'steps': 87838, 'loss/train': 2.752065420150757} 08/31/2021 05:03:16 - INFO - __main__ - Step 87840: {'lr': 0.00018783266824600814, 'samples': 16865280, 'steps': 87839, 'loss/train': 1.1256195306777954} 08/31/2021 05:03:17 - INFO - __main__ - Step 87841: {'lr': 0.00018782752820878634, 'samples': 16865472, 'steps': 87840, 'loss/train': 1.3726898431777954} 08/31/2021 05:03:17 - INFO - __main__ - Step 87842: {'lr': 0.0001878223881995785, 'samples': 16865664, 'steps': 87841, 'loss/train': 1.489460825920105} 08/31/2021 05:03:17 - INFO - __main__ - Step 87843: {'lr': 0.00018781724821838693, 'samples': 16865856, 'steps': 87842, 'loss/train': 0.8737189173698425} 08/31/2021 05:03:19 - INFO - __main__ - Step 87844: {'lr': 0.00018781210826521397, 'samples': 16866048, 'steps': 87843, 'loss/train': 1.1251704692840576} 08/31/2021 05:03:19 - INFO - __main__ - Step 87845: {'lr': 0.0001878069683400619, 'samples': 16866240, 'steps': 87844, 'loss/train': 1.2751858234405518} 08/31/2021 05:03:20 - INFO - __main__ - Step 87846: {'lr': 0.00018780182844293307, 'samples': 16866432, 'steps': 87845, 'loss/train': 1.2705806493759155} 08/31/2021 05:03:20 - INFO - __main__ - Step 87847: {'lr': 0.00018779668857382977, 'samples': 16866624, 'steps': 87846, 'loss/train': 1.3587936162948608} 08/31/2021 05:03:20 - INFO - __main__ - Step 87848: {'lr': 0.00018779154873275428, 'samples': 16866816, 'steps': 87847, 'loss/train': 1.1155307292938232} 08/31/2021 05:03:22 - INFO - __main__ - Step 87849: {'lr': 0.000187786408919709, 'samples': 16867008, 'steps': 87848, 'loss/train': 1.3080605268478394} 08/31/2021 05:03:23 - INFO - __main__ - Step 87850: {'lr': 0.00018778126913469623, 'samples': 16867200, 'steps': 87849, 'loss/train': 0.9813787341117859} 08/31/2021 05:03:23 - INFO - __main__ - Step 87851: {'lr': 0.00018777612937771824, 'samples': 16867392, 'steps': 87850, 'loss/train': 1.5511624813079834} 08/31/2021 05:03:23 - INFO - __main__ - Step 87852: {'lr': 0.00018777098964877734, 'samples': 16867584, 'steps': 87851, 'loss/train': 0.05008181184530258} 08/31/2021 05:03:24 - INFO - __main__ - Step 87853: {'lr': 0.00018776584994787594, 'samples': 16867776, 'steps': 87852, 'loss/train': 1.1421934366226196} 08/31/2021 05:03:25 - INFO - __main__ - Step 87854: {'lr': 0.00018776071027501624, 'samples': 16867968, 'steps': 87853, 'loss/train': 1.193242073059082} 08/31/2021 05:03:26 - INFO - __main__ - Step 87855: {'lr': 0.00018775557063020057, 'samples': 16868160, 'steps': 87854, 'loss/train': 1.2747215032577515} 08/31/2021 05:03:26 - INFO - __main__ - Step 87856: {'lr': 0.0001877504310134313, 'samples': 16868352, 'steps': 87855, 'loss/train': 1.1135985851287842} 08/31/2021 05:03:26 - INFO - __main__ - Step 87857: {'lr': 0.0001877452914247107, 'samples': 16868544, 'steps': 87856, 'loss/train': 1.1530747413635254} 08/31/2021 05:03:27 - INFO - __main__ - Step 87858: {'lr': 0.00018774015186404116, 'samples': 16868736, 'steps': 87857, 'loss/train': 0.9665501713752747} 08/31/2021 05:03:28 - INFO - __main__ - Step 87859: {'lr': 0.00018773501233142493, 'samples': 16868928, 'steps': 87858, 'loss/train': 0.5167943239212036} 08/31/2021 05:03:29 - INFO - __main__ - Step 87860: {'lr': 0.0001877298728268643, 'samples': 16869120, 'steps': 87859, 'loss/train': 0.6281676888465881} 08/31/2021 05:03:29 - INFO - __main__ - Step 87861: {'lr': 0.00018772473335036175, 'samples': 16869312, 'steps': 87860, 'loss/train': 1.1511664390563965} 08/31/2021 05:03:29 - INFO - __main__ - Step 87862: {'lr': 0.0001877195939019194, 'samples': 16869504, 'steps': 87861, 'loss/train': 0.8165410161018372} 08/31/2021 05:03:30 - INFO - __main__ - Step 87863: {'lr': 0.00018771445448153963, 'samples': 16869696, 'steps': 87862, 'loss/train': 0.4919743537902832} 08/31/2021 05:03:31 - INFO - __main__ - Step 87864: {'lr': 0.00018770931508922475, 'samples': 16869888, 'steps': 87863, 'loss/train': 1.2361700534820557} 08/31/2021 05:03:32 - INFO - __main__ - Step 87865: {'lr': 0.00018770417572497712, 'samples': 16870080, 'steps': 87864, 'loss/train': 1.2641713619232178} 08/31/2021 05:03:32 - INFO - __main__ - Step 87866: {'lr': 0.000187699036388799, 'samples': 16870272, 'steps': 87865, 'loss/train': 0.9783965945243835} 08/31/2021 05:03:32 - INFO - __main__ - Step 87867: {'lr': 0.0001876938970806928, 'samples': 16870464, 'steps': 87866, 'loss/train': 0.8474758863449097} 08/31/2021 05:03:33 - INFO - __main__ - Step 87868: {'lr': 0.00018768875780066072, 'samples': 16870656, 'steps': 87867, 'loss/train': 1.7828302383422852} 08/31/2021 05:03:33 - INFO - __main__ - Step 87869: {'lr': 0.00018768361854870513, 'samples': 16870848, 'steps': 87868, 'loss/train': 1.1804637908935547} 08/31/2021 05:03:35 - INFO - __main__ - Step 87870: {'lr': 0.00018767847932482832, 'samples': 16871040, 'steps': 87869, 'loss/train': 1.174636721611023} 08/31/2021 05:03:35 - INFO - __main__ - Step 87871: {'lr': 0.00018767334012903265, 'samples': 16871232, 'steps': 87870, 'loss/train': 1.1051396131515503} 08/31/2021 05:03:35 - INFO - __main__ - Step 87872: {'lr': 0.0001876682009613204, 'samples': 16871424, 'steps': 87871, 'loss/train': 0.18797409534454346} 08/31/2021 05:03:36 - INFO - __main__ - Step 87873: {'lr': 0.00018766306182169392, 'samples': 16871616, 'steps': 87872, 'loss/train': 1.5741949081420898} 08/31/2021 05:03:36 - INFO - __main__ - Step 87874: {'lr': 0.00018765792271015547, 'samples': 16871808, 'steps': 87873, 'loss/train': 1.1707147359848022} 08/31/2021 05:03:38 - INFO - __main__ - Step 87875: {'lr': 0.0001876527836267074, 'samples': 16872000, 'steps': 87874, 'loss/train': 1.4737656116485596} 08/31/2021 05:03:38 - INFO - __main__ - Step 87876: {'lr': 0.00018764764457135204, 'samples': 16872192, 'steps': 87875, 'loss/train': 1.3597395420074463} 08/31/2021 05:03:39 - INFO - __main__ - Step 87877: {'lr': 0.00018764250554409169, 'samples': 16872384, 'steps': 87876, 'loss/train': 1.467342734336853} 08/31/2021 05:03:39 - INFO - __main__ - Step 87878: {'lr': 0.00018763736654492863, 'samples': 16872576, 'steps': 87877, 'loss/train': 1.175284504890442} 08/31/2021 05:03:39 - INFO - __main__ - Step 87879: {'lr': 0.0001876322275738652, 'samples': 16872768, 'steps': 87878, 'loss/train': 0.7966988682746887} 08/31/2021 05:03:41 - INFO - __main__ - Step 87880: {'lr': 0.00018762708863090383, 'samples': 16872960, 'steps': 87879, 'loss/train': 1.0654516220092773} 08/31/2021 05:03:42 - INFO - __main__ - Step 87881: {'lr': 0.00018762194971604668, 'samples': 16873152, 'steps': 87880, 'loss/train': 0.5600159764289856} 08/31/2021 05:03:42 - INFO - __main__ - Step 87882: {'lr': 0.0001876168108292961, 'samples': 16873344, 'steps': 87881, 'loss/train': 1.9821062088012695} 08/31/2021 05:03:43 - INFO - __main__ - Step 87883: {'lr': 0.00018761167197065446, 'samples': 16873536, 'steps': 87882, 'loss/train': 1.2938368320465088} 08/31/2021 05:03:43 - INFO - __main__ - Step 87884: {'lr': 0.000187606533140124, 'samples': 16873728, 'steps': 87883, 'loss/train': 0.04023873433470726} 08/31/2021 05:03:43 - INFO - __main__ - Step 87885: {'lr': 0.00018760139433770707, 'samples': 16873920, 'steps': 87884, 'loss/train': 1.6447089910507202} 08/31/2021 05:03:45 - INFO - __main__ - Step 87886: {'lr': 0.000187596255563406, 'samples': 16874112, 'steps': 87885, 'loss/train': 0.42914968729019165} 08/31/2021 05:03:45 - INFO - __main__ - Step 87887: {'lr': 0.00018759111681722308, 'samples': 16874304, 'steps': 87886, 'loss/train': 0.6399257183074951} 08/31/2021 05:03:46 - INFO - __main__ - Step 87888: {'lr': 0.00018758597809916063, 'samples': 16874496, 'steps': 87887, 'loss/train': 1.6187902688980103} 08/31/2021 05:03:46 - INFO - __main__ - Step 87889: {'lr': 0.000187580839409221, 'samples': 16874688, 'steps': 87888, 'loss/train': 1.1763176918029785} 08/31/2021 05:03:46 - INFO - __main__ - Step 87890: {'lr': 0.00018757570074740644, 'samples': 16874880, 'steps': 87889, 'loss/train': 1.5336724519729614} 08/31/2021 05:03:48 - INFO - __main__ - Step 87891: {'lr': 0.00018757056211371934, 'samples': 16875072, 'steps': 87890, 'loss/train': 1.0358961820602417} 08/31/2021 05:03:48 - INFO - __main__ - Step 87892: {'lr': 0.00018756542350816197, 'samples': 16875264, 'steps': 87891, 'loss/train': 1.1900049448013306} 08/31/2021 05:03:49 - INFO - __main__ - Step 87893: {'lr': 0.00018756028493073675, 'samples': 16875456, 'steps': 87892, 'loss/train': 1.1422836780548096} 08/31/2021 05:03:49 - INFO - __main__ - Step 87894: {'lr': 0.00018755514638144584, 'samples': 16875648, 'steps': 87893, 'loss/train': 1.6287561655044556} 08/31/2021 05:03:49 - INFO - __main__ - Step 87895: {'lr': 0.00018755000786029158, 'samples': 16875840, 'steps': 87894, 'loss/train': 1.4046087265014648} 08/31/2021 05:03:51 - INFO - __main__ - Step 87896: {'lr': 0.00018754486936727632, 'samples': 16876032, 'steps': 87895, 'loss/train': 1.5254030227661133} 08/31/2021 05:03:51 - INFO - __main__ - Step 87897: {'lr': 0.00018753973090240243, 'samples': 16876224, 'steps': 87896, 'loss/train': 0.7936315536499023} 08/31/2021 05:03:52 - INFO - __main__ - Step 87898: {'lr': 0.00018753459246567211, 'samples': 16876416, 'steps': 87897, 'loss/train': 0.30992335081100464} 08/31/2021 05:03:52 - INFO - __main__ - Step 87899: {'lr': 0.00018752945405708777, 'samples': 16876608, 'steps': 87898, 'loss/train': 0.7564946413040161} 08/31/2021 05:03:52 - INFO - __main__ - Step 87900: {'lr': 0.00018752431567665168, 'samples': 16876800, 'steps': 87899, 'loss/train': 1.286726713180542} 08/31/2021 05:03:53 - INFO - __main__ - Step 87901: {'lr': 0.0001875191773243662, 'samples': 16876992, 'steps': 87900, 'loss/train': 1.291385531425476} 08/31/2021 05:03:54 - INFO - __main__ - Step 87902: {'lr': 0.00018751403900023355, 'samples': 16877184, 'steps': 87901, 'loss/train': 1.2352001667022705} 08/31/2021 05:03:55 - INFO - __main__ - Step 87903: {'lr': 0.00018750890070425618, 'samples': 16877376, 'steps': 87902, 'loss/train': 3.1953907012939453} 08/31/2021 05:03:55 - INFO - __main__ - Step 87904: {'lr': 0.0001875037624364363, 'samples': 16877568, 'steps': 87903, 'loss/train': 0.18288807570934296} 08/31/2021 05:03:55 - INFO - __main__ - Step 87905: {'lr': 0.00018749862419677627, 'samples': 16877760, 'steps': 87904, 'loss/train': 0.6021679043769836} 08/31/2021 05:03:56 - INFO - __main__ - Step 87906: {'lr': 0.0001874934859852784, 'samples': 16877952, 'steps': 87905, 'loss/train': 0.7551607489585876} 08/31/2021 05:03:57 - INFO - __main__ - Step 87907: {'lr': 0.0001874883478019451, 'samples': 16878144, 'steps': 87906, 'loss/train': 0.7771364450454712} 08/31/2021 05:03:58 - INFO - __main__ - Step 87908: {'lr': 0.0001874832096467785, 'samples': 16878336, 'steps': 87907, 'loss/train': 0.509131133556366} 08/31/2021 05:03:58 - INFO - __main__ - Step 87909: {'lr': 0.00018747807151978097, 'samples': 16878528, 'steps': 87908, 'loss/train': 1.4230281114578247} 08/31/2021 05:03:58 - INFO - __main__ - Step 87910: {'lr': 0.00018747293342095484, 'samples': 16878720, 'steps': 87909, 'loss/train': 0.865989089012146} 08/31/2021 05:03:59 - INFO - __main__ - Step 87911: {'lr': 0.0001874677953503025, 'samples': 16878912, 'steps': 87910, 'loss/train': 1.0032777786254883} 08/31/2021 05:04:00 - INFO - __main__ - Step 87912: {'lr': 0.00018746265730782614, 'samples': 16879104, 'steps': 87911, 'loss/train': 1.5566762685775757} 08/31/2021 05:04:01 - INFO - __main__ - Step 87913: {'lr': 0.00018745751929352816, 'samples': 16879296, 'steps': 87912, 'loss/train': 1.0368541479110718} 08/31/2021 05:04:01 - INFO - __main__ - Step 87914: {'lr': 0.0001874523813074109, 'samples': 16879488, 'steps': 87913, 'loss/train': 0.13357143104076385} 08/31/2021 05:04:01 - INFO - __main__ - Step 87915: {'lr': 0.0001874472433494766, 'samples': 16879680, 'steps': 87914, 'loss/train': 1.1977932453155518} 08/31/2021 05:04:02 - INFO - __main__ - Step 87916: {'lr': 0.00018744210541972762, 'samples': 16879872, 'steps': 87915, 'loss/train': 1.4207810163497925} 08/31/2021 05:04:03 - INFO - __main__ - Step 87917: {'lr': 0.00018743696751816625, 'samples': 16880064, 'steps': 87916, 'loss/train': 1.6226242780685425} 08/31/2021 05:04:04 - INFO - __main__ - Step 87918: {'lr': 0.00018743182964479481, 'samples': 16880256, 'steps': 87917, 'loss/train': 1.069605827331543} 08/31/2021 05:04:04 - INFO - __main__ - Step 87919: {'lr': 0.00018742669179961564, 'samples': 16880448, 'steps': 87918, 'loss/train': 0.9424306750297546} 08/31/2021 05:04:04 - INFO - __main__ - Step 87920: {'lr': 0.00018742155398263115, 'samples': 16880640, 'steps': 87919, 'loss/train': 2.901819944381714} 08/31/2021 05:04:05 - INFO - __main__ - Step 87921: {'lr': 0.00018741641619384342, 'samples': 16880832, 'steps': 87920, 'loss/train': 1.6976940631866455} 08/31/2021 05:04:07 - INFO - __main__ - Step 87922: {'lr': 0.0001874112784332549, 'samples': 16881024, 'steps': 87921, 'loss/train': 1.0684914588928223} 08/31/2021 05:04:07 - INFO - __main__ - Step 87923: {'lr': 0.00018740614070086785, 'samples': 16881216, 'steps': 87922, 'loss/train': 0.7758627533912659} 08/31/2021 05:04:08 - INFO - __main__ - Step 87924: {'lr': 0.00018740100299668468, 'samples': 16881408, 'steps': 87923, 'loss/train': 0.7039389610290527} 08/31/2021 05:04:08 - INFO - __main__ - Step 87925: {'lr': 0.00018739586532070762, 'samples': 16881600, 'steps': 87924, 'loss/train': 0.8392972946166992} 08/31/2021 05:04:08 - INFO - __main__ - Step 87926: {'lr': 0.00018739072767293903, 'samples': 16881792, 'steps': 87925, 'loss/train': 1.6741586923599243} 08/31/2021 05:04:09 - INFO - __main__ - Step 87927: {'lr': 0.0001873855900533812, 'samples': 16881984, 'steps': 87926, 'loss/train': 1.0051225423812866} 08/31/2021 05:04:09 - INFO - __main__ - Step 87928: {'lr': 0.00018738045246203644, 'samples': 16882176, 'steps': 87927, 'loss/train': 1.6150727272033691} 08/31/2021 05:04:11 - INFO - __main__ - Step 87929: {'lr': 0.00018737531489890712, 'samples': 16882368, 'steps': 87928, 'loss/train': 0.07964233309030533} 08/31/2021 05:04:11 - INFO - __main__ - Step 87930: {'lr': 0.00018737017736399552, 'samples': 16882560, 'steps': 87929, 'loss/train': 0.027670463547110558} 08/31/2021 05:04:12 - INFO - __main__ - Step 87931: {'lr': 0.00018736503985730395, 'samples': 16882752, 'steps': 87930, 'loss/train': 1.097015619277954} 08/31/2021 05:04:12 - INFO - __main__ - Step 87932: {'lr': 0.00018735990237883472, 'samples': 16882944, 'steps': 87931, 'loss/train': 1.5868091583251953} 08/31/2021 05:04:12 - INFO - __main__ - Step 87933: {'lr': 0.0001873547649285901, 'samples': 16883136, 'steps': 87932, 'loss/train': 1.145449161529541} 08/31/2021 05:04:14 - INFO - __main__ - Step 87934: {'lr': 0.00018734962750657265, 'samples': 16883328, 'steps': 87933, 'loss/train': 0.7959785461425781} 08/31/2021 05:04:15 - INFO - __main__ - Step 87935: {'lr': 0.00018734449011278433, 'samples': 16883520, 'steps': 87934, 'loss/train': 1.3377916812896729} 08/31/2021 05:04:15 - INFO - __main__ - Step 87936: {'lr': 0.00018733935274722763, 'samples': 16883712, 'steps': 87935, 'loss/train': 1.578958511352539} 08/31/2021 05:04:16 - INFO - __main__ - Step 87937: {'lr': 0.00018733421540990483, 'samples': 16883904, 'steps': 87936, 'loss/train': 1.5534104108810425} 08/31/2021 05:04:16 - INFO - __main__ - Step 87938: {'lr': 0.0001873290781008183, 'samples': 16884096, 'steps': 87937, 'loss/train': 1.0518503189086914} 08/31/2021 05:04:17 - INFO - __main__ - Step 87939: {'lr': 0.00018732394081997028, 'samples': 16884288, 'steps': 87938, 'loss/train': 1.8864425420761108} 08/31/2021 05:04:18 - INFO - __main__ - Step 87940: {'lr': 0.00018731880356736313, 'samples': 16884480, 'steps': 87939, 'loss/train': 1.0342472791671753} 08/31/2021 05:04:18 - INFO - __main__ - Step 87941: {'lr': 0.0001873136663429992, 'samples': 16884672, 'steps': 87940, 'loss/train': 0.9701363444328308} 08/31/2021 05:04:19 - INFO - __main__ - Step 87942: {'lr': 0.00018730852914688073, 'samples': 16884864, 'steps': 87941, 'loss/train': 1.3328114748001099} 08/31/2021 05:04:19 - INFO - __main__ - Step 87943: {'lr': 0.0001873033919790101, 'samples': 16885056, 'steps': 87942, 'loss/train': 0.8551356792449951} 08/31/2021 05:04:21 - INFO - __main__ - Step 87944: {'lr': 0.00018729825483938955, 'samples': 16885248, 'steps': 87943, 'loss/train': 1.3870633840560913} 08/31/2021 05:04:21 - INFO - __main__ - Step 87945: {'lr': 0.0001872931177280215, 'samples': 16885440, 'steps': 87944, 'loss/train': 0.48754364252090454} 08/31/2021 05:04:21 - INFO - __main__ - Step 87946: {'lr': 0.00018728798064490814, 'samples': 16885632, 'steps': 87945, 'loss/train': 1.0518498420715332} 08/31/2021 05:04:22 - INFO - __main__ - Step 87947: {'lr': 0.00018728284359005202, 'samples': 16885824, 'steps': 87946, 'loss/train': 1.403928518295288} 08/31/2021 05:04:22 - INFO - __main__ - Step 87948: {'lr': 0.00018727770656345514, 'samples': 16886016, 'steps': 87947, 'loss/train': 0.3579142987728119} 08/31/2021 05:04:24 - INFO - __main__ - Step 87949: {'lr': 0.00018727256956511997, 'samples': 16886208, 'steps': 87948, 'loss/train': 0.03068387694656849} 08/31/2021 05:04:24 - INFO - __main__ - Step 87950: {'lr': 0.00018726743259504878, 'samples': 16886400, 'steps': 87949, 'loss/train': 0.06716706603765488} 08/31/2021 05:04:24 - INFO - __main__ - Step 87951: {'lr': 0.00018726229565324394, 'samples': 16886592, 'steps': 87950, 'loss/train': 1.8576126098632812} 08/31/2021 05:04:25 - INFO - __main__ - Step 87952: {'lr': 0.0001872571587397077, 'samples': 16886784, 'steps': 87951, 'loss/train': 1.750714659690857} 08/31/2021 05:04:25 - INFO - __main__ - Step 87953: {'lr': 0.0001872520218544425, 'samples': 16886976, 'steps': 87952, 'loss/train': 1.4822026491165161} 08/31/2021 05:04:27 - INFO - __main__ - Step 87954: {'lr': 0.00018724688499745053, 'samples': 16887168, 'steps': 87953, 'loss/train': 0.8406476378440857} 08/31/2021 05:04:27 - INFO - __main__ - Step 87955: {'lr': 0.00018724174816873412, 'samples': 16887360, 'steps': 87954, 'loss/train': 1.4596015214920044} 08/31/2021 05:04:27 - INFO - __main__ - Step 87956: {'lr': 0.0001872366113682956, 'samples': 16887552, 'steps': 87955, 'loss/train': 1.373038411140442} 08/31/2021 05:04:28 - INFO - __main__ - Step 87957: {'lr': 0.00018723147459613737, 'samples': 16887744, 'steps': 87956, 'loss/train': 1.3600643873214722} 08/31/2021 05:04:28 - INFO - __main__ - Step 87958: {'lr': 0.00018722633785226163, 'samples': 16887936, 'steps': 87957, 'loss/train': 1.275463342666626} 08/31/2021 05:04:30 - INFO - __main__ - Step 87959: {'lr': 0.00018722120113667072, 'samples': 16888128, 'steps': 87958, 'loss/train': 1.3546582460403442} 08/31/2021 05:04:30 - INFO - __main__ - Step 87960: {'lr': 0.00018721606444936696, 'samples': 16888320, 'steps': 87959, 'loss/train': 0.9261822700500488} 08/31/2021 05:04:31 - INFO - __main__ - Step 87961: {'lr': 0.0001872109277903528, 'samples': 16888512, 'steps': 87960, 'loss/train': 1.190708875656128} 08/31/2021 05:04:31 - INFO - __main__ - Step 87962: {'lr': 0.00018720579115963032, 'samples': 16888704, 'steps': 87961, 'loss/train': 0.9636353850364685} 08/31/2021 05:04:31 - INFO - __main__ - Step 87963: {'lr': 0.00018720065455720192, 'samples': 16888896, 'steps': 87962, 'loss/train': 1.299691915512085} 08/31/2021 05:04:32 - INFO - __main__ - Step 87964: {'lr': 0.00018719551798306996, 'samples': 16889088, 'steps': 87963, 'loss/train': 0.9736922979354858} 08/31/2021 05:04:33 - INFO - __main__ - Step 87965: {'lr': 0.00018719038143723672, 'samples': 16889280, 'steps': 87964, 'loss/train': 0.9475696682929993} 08/31/2021 05:04:34 - INFO - __main__ - Step 87966: {'lr': 0.00018718524491970453, 'samples': 16889472, 'steps': 87965, 'loss/train': 0.40166813135147095} 08/31/2021 05:04:34 - INFO - __main__ - Step 87967: {'lr': 0.0001871801084304757, 'samples': 16889664, 'steps': 87966, 'loss/train': 0.04299214109778404} 08/31/2021 05:04:35 - INFO - __main__ - Step 87968: {'lr': 0.00018717497196955255, 'samples': 16889856, 'steps': 87967, 'loss/train': 2.183974027633667} 08/31/2021 05:04:35 - INFO - __main__ - Step 87969: {'lr': 0.00018716983553693738, 'samples': 16890048, 'steps': 87968, 'loss/train': 0.8055828213691711} 08/31/2021 05:04:37 - INFO - __main__ - Step 87970: {'lr': 0.0001871646991326325, 'samples': 16890240, 'steps': 87969, 'loss/train': 0.08520742505788803} 08/31/2021 05:04:37 - INFO - __main__ - Step 87971: {'lr': 0.00018715956275664025, 'samples': 16890432, 'steps': 87970, 'loss/train': 1.4914214611053467} 08/31/2021 05:04:37 - INFO - __main__ - Step 87972: {'lr': 0.00018715442640896294, 'samples': 16890624, 'steps': 87971, 'loss/train': 1.4626753330230713} 08/31/2021 05:04:38 - INFO - __main__ - Step 87973: {'lr': 0.0001871492900896029, 'samples': 16890816, 'steps': 87972, 'loss/train': 1.3224561214447021} 08/31/2021 05:04:38 - INFO - __main__ - Step 87974: {'lr': 0.00018714415379856244, 'samples': 16891008, 'steps': 87973, 'loss/train': 1.265640377998352} 08/31/2021 05:04:40 - INFO - __main__ - Step 87975: {'lr': 0.0001871390175358438, 'samples': 16891200, 'steps': 87974, 'loss/train': 1.565905213356018} 08/31/2021 05:04:40 - INFO - __main__ - Step 87976: {'lr': 0.00018713388130144938, 'samples': 16891392, 'steps': 87975, 'loss/train': 1.479518175125122} 08/31/2021 05:04:41 - INFO - __main__ - Step 87977: {'lr': 0.00018712874509538142, 'samples': 16891584, 'steps': 87976, 'loss/train': 1.8675456047058105} 08/31/2021 05:04:41 - INFO - __main__ - Step 87978: {'lr': 0.0001871236089176423, 'samples': 16891776, 'steps': 87977, 'loss/train': 1.142824649810791} 08/31/2021 05:04:41 - INFO - __main__ - Step 87979: {'lr': 0.0001871184727682343, 'samples': 16891968, 'steps': 87978, 'loss/train': 1.433449149131775} 08/31/2021 05:04:42 - INFO - __main__ - Step 87980: {'lr': 0.00018711333664715973, 'samples': 16892160, 'steps': 87979, 'loss/train': 0.9837577939033508} 08/31/2021 05:04:43 - INFO - __main__ - Step 87981: {'lr': 0.00018710820055442093, 'samples': 16892352, 'steps': 87980, 'loss/train': 0.056119393557310104} 08/31/2021 05:04:44 - INFO - __main__ - Step 87982: {'lr': 0.00018710306449002022, 'samples': 16892544, 'steps': 87981, 'loss/train': 1.3569170236587524} 08/31/2021 05:04:44 - INFO - __main__ - Step 87983: {'lr': 0.0001870979284539599, 'samples': 16892736, 'steps': 87982, 'loss/train': 1.43682861328125} 08/31/2021 05:04:44 - INFO - __main__ - Step 87984: {'lr': 0.0001870927924462423, 'samples': 16892928, 'steps': 87983, 'loss/train': 1.894497036933899} 08/31/2021 05:04:45 - INFO - __main__ - Step 87985: {'lr': 0.0001870876564668697, 'samples': 16893120, 'steps': 87984, 'loss/train': 1.3099018335342407} 08/31/2021 05:04:47 - INFO - __main__ - Step 87986: {'lr': 0.0001870825205158444, 'samples': 16893312, 'steps': 87985, 'loss/train': 1.0076228380203247} 08/31/2021 05:04:47 - INFO - __main__ - Step 87987: {'lr': 0.0001870773845931688, 'samples': 16893504, 'steps': 87986, 'loss/train': 1.5215227603912354} 08/31/2021 05:04:48 - INFO - __main__ - Step 87988: {'lr': 0.00018707224869884514, 'samples': 16893696, 'steps': 87987, 'loss/train': 1.2030948400497437} 08/31/2021 05:04:48 - INFO - __main__ - Step 87989: {'lr': 0.00018706711283287576, 'samples': 16893888, 'steps': 87988, 'loss/train': 1.135973334312439} 08/31/2021 05:04:48 - INFO - __main__ - Step 87990: {'lr': 0.00018706197699526296, 'samples': 16894080, 'steps': 87989, 'loss/train': 1.1376646757125854} 08/31/2021 05:04:50 - INFO - __main__ - Step 87991: {'lr': 0.000187056841186009, 'samples': 16894272, 'steps': 87990, 'loss/train': 0.28942304849624634} 08/31/2021 05:04:50 - INFO - __main__ - Step 87992: {'lr': 0.00018705170540511635, 'samples': 16894464, 'steps': 87991, 'loss/train': 1.0309717655181885} 08/31/2021 05:04:51 - INFO - __main__ - Step 87993: {'lr': 0.00018704656965258718, 'samples': 16894656, 'steps': 87992, 'loss/train': 1.2042683362960815} 08/31/2021 05:04:51 - INFO - __main__ - Step 87994: {'lr': 0.0001870414339284239, 'samples': 16894848, 'steps': 87993, 'loss/train': 1.8413679599761963} 08/31/2021 05:04:51 - INFO - __main__ - Step 87995: {'lr': 0.00018703629823262874, 'samples': 16895040, 'steps': 87994, 'loss/train': 1.2385663986206055} 08/31/2021 05:04:53 - INFO - __main__ - Step 87996: {'lr': 0.00018703116256520405, 'samples': 16895232, 'steps': 87995, 'loss/train': 0.8800784349441528} 08/31/2021 05:04:53 - INFO - __main__ - Step 87997: {'lr': 0.00018702602692615217, 'samples': 16895424, 'steps': 87996, 'loss/train': 1.0106662511825562} 08/31/2021 05:04:54 - INFO - __main__ - Step 87998: {'lr': 0.00018702089131547535, 'samples': 16895616, 'steps': 87997, 'loss/train': 1.594944715499878} 08/31/2021 05:04:54 - INFO - __main__ - Step 87999: {'lr': 0.00018701575573317597, 'samples': 16895808, 'steps': 87998, 'loss/train': 0.4215506315231323} 08/31/2021 05:04:54 - INFO - __main__ - Step 88000: {'lr': 0.0001870106201792563, 'samples': 16896000, 'steps': 87999, 'loss/train': 1.243678331375122} 08/31/2021 05:04:56 - INFO - __main__ - Step 88001: {'lr': 0.00018700548465371876, 'samples': 16896192, 'steps': 88000, 'loss/train': 0.419956237077713} 08/31/2021 05:04:56 - INFO - __main__ - Step 88002: {'lr': 0.0001870003491565655, 'samples': 16896384, 'steps': 88001, 'loss/train': 1.132949709892273} 08/31/2021 05:04:57 - INFO - __main__ - Step 88003: {'lr': 0.0001869952136877989, 'samples': 16896576, 'steps': 88002, 'loss/train': 1.1262729167938232} 08/31/2021 05:04:57 - INFO - __main__ - Step 88004: {'lr': 0.0001869900782474213, 'samples': 16896768, 'steps': 88003, 'loss/train': 1.1083396673202515} 08/31/2021 05:04:57 - INFO - __main__ - Step 88005: {'lr': 0.00018698494283543498, 'samples': 16896960, 'steps': 88004, 'loss/train': 1.867095708847046} 08/31/2021 05:04:59 - INFO - __main__ - Step 88006: {'lr': 0.00018697980745184235, 'samples': 16897152, 'steps': 88005, 'loss/train': 1.1079292297363281} 08/31/2021 05:05:00 - INFO - __main__ - Step 88007: {'lr': 0.0001869746720966456, 'samples': 16897344, 'steps': 88006, 'loss/train': 0.5455666780471802} 08/31/2021 05:05:00 - INFO - __main__ - Step 88008: {'lr': 0.00018696953676984704, 'samples': 16897536, 'steps': 88007, 'loss/train': 1.223612666130066} 08/31/2021 05:05:00 - INFO - __main__ - Step 88009: {'lr': 0.00018696440147144904, 'samples': 16897728, 'steps': 88008, 'loss/train': 1.1149394512176514} 08/31/2021 05:05:01 - INFO - __main__ - Step 88010: {'lr': 0.00018695926620145397, 'samples': 16897920, 'steps': 88009, 'loss/train': 0.8921820521354675} 08/31/2021 05:05:01 - INFO - __main__ - Step 88011: {'lr': 0.00018695413095986402, 'samples': 16898112, 'steps': 88010, 'loss/train': 0.05213044211268425} 08/31/2021 05:05:02 - INFO - __main__ - Step 88012: {'lr': 0.00018694899574668163, 'samples': 16898304, 'steps': 88011, 'loss/train': 0.8664929270744324} 08/31/2021 05:05:03 - INFO - __main__ - Step 88013: {'lr': 0.000186943860561909, 'samples': 16898496, 'steps': 88012, 'loss/train': 0.08550307154655457} 08/31/2021 05:05:03 - INFO - __main__ - Step 88014: {'lr': 0.00018693872540554858, 'samples': 16898688, 'steps': 88013, 'loss/train': 1.267161250114441} 08/31/2021 05:05:04 - INFO - __main__ - Step 88015: {'lr': 0.00018693359027760248, 'samples': 16898880, 'steps': 88014, 'loss/train': 1.5516351461410522} 08/31/2021 05:05:04 - INFO - __main__ - Step 88016: {'lr': 0.00018692845517807318, 'samples': 16899072, 'steps': 88015, 'loss/train': 1.5395036935806274} 08/31/2021 05:05:05 - INFO - __main__ - Step 88017: {'lr': 0.000186923320106963, 'samples': 16899264, 'steps': 88016, 'loss/train': 1.3286874294281006} 08/31/2021 05:05:06 - INFO - __main__ - Step 88018: {'lr': 0.00018691818506427413, 'samples': 16899456, 'steps': 88017, 'loss/train': 1.5383926630020142} 08/31/2021 05:05:06 - INFO - __main__ - Step 88019: {'lr': 0.00018691305005000898, 'samples': 16899648, 'steps': 88018, 'loss/train': 0.9564063549041748} 08/31/2021 05:05:07 - INFO - __main__ - Step 88020: {'lr': 0.0001869079150641698, 'samples': 16899840, 'steps': 88019, 'loss/train': 0.6073505282402039} 08/31/2021 05:05:07 - INFO - __main__ - Step 88021: {'lr': 0.00018690278010675897, 'samples': 16900032, 'steps': 88020, 'loss/train': 0.6649644374847412} 08/31/2021 05:05:09 - INFO - __main__ - Step 88022: {'lr': 0.00018689764517777874, 'samples': 16900224, 'steps': 88021, 'loss/train': 0.7746558785438538} 08/31/2021 05:05:09 - INFO - __main__ - Step 88023: {'lr': 0.00018689251027723147, 'samples': 16900416, 'steps': 88022, 'loss/train': 1.265573263168335} 08/31/2021 05:05:09 - INFO - __main__ - Step 88024: {'lr': 0.00018688737540511945, 'samples': 16900608, 'steps': 88023, 'loss/train': 1.6317949295043945} 08/31/2021 05:05:10 - INFO - __main__ - Step 88025: {'lr': 0.00018688224056144504, 'samples': 16900800, 'steps': 88024, 'loss/train': 1.2712640762329102} 08/31/2021 05:05:10 - INFO - __main__ - Step 88026: {'lr': 0.00018687710574621051, 'samples': 16900992, 'steps': 88025, 'loss/train': 1.2237465381622314} 08/31/2021 05:05:12 - INFO - __main__ - Step 88027: {'lr': 0.00018687197095941817, 'samples': 16901184, 'steps': 88026, 'loss/train': 1.6762356758117676} 08/31/2021 05:05:12 - INFO - __main__ - Step 88028: {'lr': 0.00018686683620107046, 'samples': 16901376, 'steps': 88027, 'loss/train': 0.8916530609130859} 08/31/2021 05:05:13 - INFO - __main__ - Step 88029: {'lr': 0.00018686170147116945, 'samples': 16901568, 'steps': 88028, 'loss/train': 0.6923814415931702} 08/31/2021 05:05:13 - INFO - __main__ - Step 88030: {'lr': 0.00018685656676971764, 'samples': 16901760, 'steps': 88029, 'loss/train': 1.4009411334991455} 08/31/2021 05:05:13 - INFO - __main__ - Step 88031: {'lr': 0.00018685143209671724, 'samples': 16901952, 'steps': 88030, 'loss/train': 1.1749964952468872} 08/31/2021 05:05:15 - INFO - __main__ - Step 88032: {'lr': 0.00018684629745217057, 'samples': 16902144, 'steps': 88031, 'loss/train': 0.9526212811470032} 08/31/2021 05:05:15 - INFO - __main__ - Step 88033: {'lr': 0.00018684116283608005, 'samples': 16902336, 'steps': 88032, 'loss/train': 0.7983134388923645} 08/31/2021 05:05:16 - INFO - __main__ - Step 88034: {'lr': 0.00018683602824844792, 'samples': 16902528, 'steps': 88033, 'loss/train': 1.2707988023757935} 08/31/2021 05:05:16 - INFO - __main__ - Step 88035: {'lr': 0.00018683089368927647, 'samples': 16902720, 'steps': 88034, 'loss/train': 0.14376817643642426} 08/31/2021 05:05:16 - INFO - __main__ - Step 88036: {'lr': 0.0001868257591585681, 'samples': 16902912, 'steps': 88035, 'loss/train': 0.8185265064239502} 08/31/2021 05:05:17 - INFO - __main__ - Step 88037: {'lr': 0.000186820624656325, 'samples': 16903104, 'steps': 88036, 'loss/train': 1.5418998003005981} 08/31/2021 05:05:18 - INFO - __main__ - Step 88038: {'lr': 0.00018681549018254959, 'samples': 16903296, 'steps': 88037, 'loss/train': 0.8436320424079895} 08/31/2021 05:05:19 - INFO - __main__ - Step 88039: {'lr': 0.00018681035573724414, 'samples': 16903488, 'steps': 88038, 'loss/train': 1.4974477291107178} 08/31/2021 05:05:19 - INFO - __main__ - Step 88040: {'lr': 0.00018680522132041098, 'samples': 16903680, 'steps': 88039, 'loss/train': 1.7525553703308105} 08/31/2021 05:05:19 - INFO - __main__ - Step 88041: {'lr': 0.0001868000869320525, 'samples': 16903872, 'steps': 88040, 'loss/train': 1.1716984510421753} 08/31/2021 05:05:20 - INFO - __main__ - Step 88042: {'lr': 0.00018679495257217083, 'samples': 16904064, 'steps': 88041, 'loss/train': 0.9832903146743774} 08/31/2021 05:05:22 - INFO - __main__ - Step 88043: {'lr': 0.00018678981824076836, 'samples': 16904256, 'steps': 88042, 'loss/train': 0.9735815525054932} 08/31/2021 05:05:22 - INFO - __main__ - Step 88044: {'lr': 0.00018678468393784744, 'samples': 16904448, 'steps': 88043, 'loss/train': 0.9782058596611023} 08/31/2021 05:05:23 - INFO - __main__ - Step 88045: {'lr': 0.00018677954966341036, 'samples': 16904640, 'steps': 88044, 'loss/train': 1.3276556730270386} 08/31/2021 05:05:23 - INFO - __main__ - Step 88046: {'lr': 0.00018677441541745942, 'samples': 16904832, 'steps': 88045, 'loss/train': 1.2187833786010742} 08/31/2021 05:05:23 - INFO - __main__ - Step 88047: {'lr': 0.000186769281199997, 'samples': 16905024, 'steps': 88046, 'loss/train': 1.1730449199676514} 08/31/2021 05:05:25 - INFO - __main__ - Step 88048: {'lr': 0.00018676414701102533, 'samples': 16905216, 'steps': 88047, 'loss/train': 2.0224921703338623} 08/31/2021 05:05:25 - INFO - __main__ - Step 88049: {'lr': 0.0001867590128505468, 'samples': 16905408, 'steps': 88048, 'loss/train': 0.707152247428894} 08/31/2021 05:05:26 - INFO - __main__ - Step 88050: {'lr': 0.00018675387871856363, 'samples': 16905600, 'steps': 88049, 'loss/train': 1.4813727140426636} 08/31/2021 05:05:26 - INFO - __main__ - Step 88051: {'lr': 0.00018674874461507824, 'samples': 16905792, 'steps': 88050, 'loss/train': 0.8761430382728577} 08/31/2021 05:05:26 - INFO - __main__ - Step 88052: {'lr': 0.00018674361054009283, 'samples': 16905984, 'steps': 88051, 'loss/train': 0.49319398403167725} 08/31/2021 05:05:27 - INFO - __main__ - Step 88053: {'lr': 0.0001867384764936098, 'samples': 16906176, 'steps': 88052, 'loss/train': 0.33415505290031433} 08/31/2021 05:05:28 - INFO - __main__ - Step 88054: {'lr': 0.00018673334247563145, 'samples': 16906368, 'steps': 88053, 'loss/train': 1.161020278930664} 08/31/2021 05:05:29 - INFO - __main__ - Step 88055: {'lr': 0.00018672820848616019, 'samples': 16906560, 'steps': 88054, 'loss/train': 1.1886346340179443} 08/31/2021 05:05:29 - INFO - __main__ - Step 88056: {'lr': 0.0001867230745251981, 'samples': 16906752, 'steps': 88055, 'loss/train': 0.8351187705993652} 08/31/2021 05:05:29 - INFO - __main__ - Step 88057: {'lr': 0.0001867179405927476, 'samples': 16906944, 'steps': 88056, 'loss/train': 0.6159610152244568} 08/31/2021 05:05:30 - INFO - __main__ - Step 88058: {'lr': 0.00018671280668881103, 'samples': 16907136, 'steps': 88057, 'loss/train': 1.4658838510513306} 08/31/2021 05:05:31 - INFO - __main__ - Step 88059: {'lr': 0.0001867076728133907, 'samples': 16907328, 'steps': 88058, 'loss/train': 1.3000792264938354} 08/31/2021 05:05:32 - INFO - __main__ - Step 88060: {'lr': 0.00018670253896648891, 'samples': 16907520, 'steps': 88059, 'loss/train': 1.099714756011963} 08/31/2021 05:05:32 - INFO - __main__ - Step 88061: {'lr': 0.000186697405148108, 'samples': 16907712, 'steps': 88060, 'loss/train': 1.5862338542938232} 08/31/2021 05:05:32 - INFO - __main__ - Step 88062: {'lr': 0.00018669227135825024, 'samples': 16907904, 'steps': 88061, 'loss/train': 0.7232120633125305} 08/31/2021 05:05:33 - INFO - __main__ - Step 88063: {'lr': 0.00018668713759691796, 'samples': 16908096, 'steps': 88062, 'loss/train': 0.06023288890719414} 08/31/2021 05:05:34 - INFO - __main__ - Step 88064: {'lr': 0.0001866820038641135, 'samples': 16908288, 'steps': 88063, 'loss/train': 1.3874980211257935} 08/31/2021 05:05:35 - INFO - __main__ - Step 88065: {'lr': 0.00018667687015983913, 'samples': 16908480, 'steps': 88064, 'loss/train': 0.36560797691345215} 08/31/2021 05:05:35 - INFO - __main__ - Step 88066: {'lr': 0.00018667173648409725, 'samples': 16908672, 'steps': 88065, 'loss/train': 1.4287595748901367} 08/31/2021 05:05:36 - INFO - __main__ - Step 88067: {'lr': 0.00018666660283689002, 'samples': 16908864, 'steps': 88066, 'loss/train': 1.498094081878662} 08/31/2021 05:05:36 - INFO - __main__ - Step 88068: {'lr': 0.00018666146921822, 'samples': 16909056, 'steps': 88067, 'loss/train': 1.0423521995544434} 08/31/2021 05:05:37 - INFO - __main__ - Step 88069: {'lr': 0.0001866563356280892, 'samples': 16909248, 'steps': 88068, 'loss/train': 1.1662935018539429} 08/31/2021 05:05:38 - INFO - __main__ - Step 88070: {'lr': 0.00018665120206650011, 'samples': 16909440, 'steps': 88069, 'loss/train': 0.8589054346084595} 08/31/2021 05:05:38 - INFO - __main__ - Step 88071: {'lr': 0.000186646068533455, 'samples': 16909632, 'steps': 88070, 'loss/train': 0.9647652506828308} 08/31/2021 05:05:39 - INFO - __main__ - Step 88072: {'lr': 0.00018664093502895621, 'samples': 16909824, 'steps': 88071, 'loss/train': 1.2257376909255981} 08/31/2021 05:05:39 - INFO - __main__ - Step 88073: {'lr': 0.00018663580155300603, 'samples': 16910016, 'steps': 88072, 'loss/train': 0.9991770386695862} 08/31/2021 05:05:41 - INFO - __main__ - Step 88074: {'lr': 0.00018663066810560675, 'samples': 16910208, 'steps': 88073, 'loss/train': 1.0120347738265991} 08/31/2021 05:05:42 - INFO - __main__ - Step 88075: {'lr': 0.00018662553468676074, 'samples': 16910400, 'steps': 88074, 'loss/train': 0.9466102123260498} 08/31/2021 05:05:42 - INFO - __main__ - Step 88076: {'lr': 0.00018662040129647028, 'samples': 16910592, 'steps': 88075, 'loss/train': 1.4318493604660034} 08/31/2021 05:05:42 - INFO - __main__ - Step 88077: {'lr': 0.0001866152679347377, 'samples': 16910784, 'steps': 88076, 'loss/train': 0.5609256625175476} 08/31/2021 05:05:43 - INFO - __main__ - Step 88078: {'lr': 0.00018661013460156528, 'samples': 16910976, 'steps': 88077, 'loss/train': 0.4616323709487915} 08/31/2021 05:05:43 - INFO - __main__ - Step 88079: {'lr': 0.0001866050012969554, 'samples': 16911168, 'steps': 88078, 'loss/train': 0.04948851466178894} 08/31/2021 05:05:43 - INFO - __main__ - Step 88080: {'lr': 0.00018659986802091027, 'samples': 16911360, 'steps': 88079, 'loss/train': 0.12114919722080231} 08/31/2021 05:05:45 - INFO - __main__ - Step 88081: {'lr': 0.0001865947347734323, 'samples': 16911552, 'steps': 88080, 'loss/train': 1.4846855401992798} 08/31/2021 05:05:45 - INFO - __main__ - Step 88082: {'lr': 0.00018658960155452386, 'samples': 16911744, 'steps': 88081, 'loss/train': 1.0392634868621826} 08/31/2021 05:05:46 - INFO - __main__ - Step 88083: {'lr': 0.0001865844683641871, 'samples': 16911936, 'steps': 88082, 'loss/train': 1.5706425905227661} 08/31/2021 05:05:46 - INFO - __main__ - Step 88084: {'lr': 0.0001865793352024243, 'samples': 16912128, 'steps': 88083, 'loss/train': 0.9616642594337463} 08/31/2021 05:05:46 - INFO - __main__ - Step 88085: {'lr': 0.00018657420206923795, 'samples': 16912320, 'steps': 88084, 'loss/train': 1.7678158283233643} 08/31/2021 05:05:47 - INFO - __main__ - Step 88086: {'lr': 0.00018656906896463027, 'samples': 16912512, 'steps': 88085, 'loss/train': 1.4306079149246216} 08/31/2021 05:05:48 - INFO - __main__ - Step 88087: {'lr': 0.0001865639358886036, 'samples': 16912704, 'steps': 88086, 'loss/train': 5.72302770614624} 08/31/2021 05:05:49 - INFO - __main__ - Step 88088: {'lr': 0.00018655880284116022, 'samples': 16912896, 'steps': 88087, 'loss/train': 0.5570491552352905} 08/31/2021 05:05:49 - INFO - __main__ - Step 88089: {'lr': 0.0001865536698223025, 'samples': 16913088, 'steps': 88088, 'loss/train': 1.460676908493042} 08/31/2021 05:05:49 - INFO - __main__ - Step 88090: {'lr': 0.00018654853683203266, 'samples': 16913280, 'steps': 88089, 'loss/train': 1.472597599029541} 08/31/2021 05:05:50 - INFO - __main__ - Step 88091: {'lr': 0.0001865434038703531, 'samples': 16913472, 'steps': 88090, 'loss/train': 1.151869773864746} 08/31/2021 05:05:51 - INFO - __main__ - Step 88092: {'lr': 0.00018653827093726612, 'samples': 16913664, 'steps': 88091, 'loss/train': 1.012215256690979} 08/31/2021 05:05:52 - INFO - __main__ - Step 88093: {'lr': 0.000186533138032774, 'samples': 16913856, 'steps': 88092, 'loss/train': 1.0422108173370361} 08/31/2021 05:05:52 - INFO - __main__ - Step 88094: {'lr': 0.00018652800515687906, 'samples': 16914048, 'steps': 88093, 'loss/train': 0.8542627096176147} 08/31/2021 05:05:52 - INFO - __main__ - Step 88095: {'lr': 0.00018652287230958372, 'samples': 16914240, 'steps': 88094, 'loss/train': 1.203995943069458} 08/31/2021 05:05:53 - INFO - __main__ - Step 88096: {'lr': 0.00018651773949089013, 'samples': 16914432, 'steps': 88095, 'loss/train': 1.2545720338821411} 08/31/2021 05:05:55 - INFO - __main__ - Step 88097: {'lr': 0.0001865126067008006, 'samples': 16914624, 'steps': 88096, 'loss/train': 1.2500025033950806} 08/31/2021 05:05:55 - INFO - __main__ - Step 88098: {'lr': 0.00018650747393931754, 'samples': 16914816, 'steps': 88097, 'loss/train': 0.9068148136138916} 08/31/2021 05:05:55 - INFO - __main__ - Step 88099: {'lr': 0.00018650234120644326, 'samples': 16915008, 'steps': 88098, 'loss/train': 1.629009485244751} 08/31/2021 05:05:56 - INFO - __main__ - Step 88100: {'lr': 0.00018649720850218005, 'samples': 16915200, 'steps': 88099, 'loss/train': 0.03672754392027855} 08/31/2021 05:05:56 - INFO - __main__ - Step 88101: {'lr': 0.00018649207582653018, 'samples': 16915392, 'steps': 88100, 'loss/train': 1.0389299392700195} 08/31/2021 05:05:56 - INFO - __main__ - Step 88102: {'lr': 0.00018648694317949601, 'samples': 16915584, 'steps': 88101, 'loss/train': 1.4422510862350464} 08/31/2021 05:05:58 - INFO - __main__ - Step 88103: {'lr': 0.00018648181056107988, 'samples': 16915776, 'steps': 88102, 'loss/train': 1.813497543334961} 08/31/2021 05:05:58 - INFO - __main__ - Step 88104: {'lr': 0.00018647667797128405, 'samples': 16915968, 'steps': 88103, 'loss/train': 0.15366913378238678} 08/31/2021 05:05:59 - INFO - __main__ - Step 88105: {'lr': 0.0001864715454101108, 'samples': 16916160, 'steps': 88104, 'loss/train': 1.4894227981567383} 08/31/2021 05:05:59 - INFO - __main__ - Step 88106: {'lr': 0.00018646641287756253, 'samples': 16916352, 'steps': 88105, 'loss/train': 1.6206387281417847} 08/31/2021 05:05:59 - INFO - __main__ - Step 88107: {'lr': 0.00018646128037364153, 'samples': 16916544, 'steps': 88106, 'loss/train': 0.5548027753829956} 08/31/2021 05:06:01 - INFO - __main__ - Step 88108: {'lr': 0.0001864561478983501, 'samples': 16916736, 'steps': 88107, 'loss/train': 1.4678153991699219} 08/31/2021 05:06:02 - INFO - __main__ - Step 88109: {'lr': 0.00018645101545169057, 'samples': 16916928, 'steps': 88108, 'loss/train': 1.6957513093948364} 08/31/2021 05:06:02 - INFO - __main__ - Step 88110: {'lr': 0.0001864458830336652, 'samples': 16917120, 'steps': 88109, 'loss/train': 0.7279377579689026} 08/31/2021 05:06:03 - INFO - __main__ - Step 88111: {'lr': 0.00018644075064427632, 'samples': 16917312, 'steps': 88110, 'loss/train': 0.03225810453295708} 08/31/2021 05:06:03 - INFO - __main__ - Step 88112: {'lr': 0.00018643561828352625, 'samples': 16917504, 'steps': 88111, 'loss/train': 1.4198901653289795} 08/31/2021 05:06:05 - INFO - __main__ - Step 88113: {'lr': 0.0001864304859514173, 'samples': 16917696, 'steps': 88112, 'loss/train': 0.9880501627922058} 08/31/2021 05:06:06 - INFO - __main__ - Step 88114: {'lr': 0.00018642535364795182, 'samples': 16917888, 'steps': 88113, 'loss/train': 1.398849606513977} 08/31/2021 05:06:06 - INFO - __main__ - Step 88115: {'lr': 0.0001864202213731321, 'samples': 16918080, 'steps': 88114, 'loss/train': 0.7501015067100525} 08/31/2021 05:06:06 - INFO - __main__ - Step 88116: {'lr': 0.00018641508912696042, 'samples': 16918272, 'steps': 88115, 'loss/train': 1.291480302810669} 08/31/2021 05:06:07 - INFO - __main__ - Step 88117: {'lr': 0.00018640995690943915, 'samples': 16918464, 'steps': 88116, 'loss/train': 0.9282532334327698} 08/31/2021 05:06:07 - INFO - __main__ - Step 88118: {'lr': 0.00018640482472057058, 'samples': 16918656, 'steps': 88117, 'loss/train': 1.4634674787521362} 08/31/2021 05:06:09 - INFO - __main__ - Step 88119: {'lr': 0.00018639969256035703, 'samples': 16918848, 'steps': 88118, 'loss/train': 0.20272225141525269} 08/31/2021 05:06:09 - INFO - __main__ - Step 88120: {'lr': 0.00018639456042880077, 'samples': 16919040, 'steps': 88119, 'loss/train': 1.114029884338379} 08/31/2021 05:06:09 - INFO - __main__ - Step 88121: {'lr': 0.00018638942832590412, 'samples': 16919232, 'steps': 88120, 'loss/train': 0.4244998097419739} 08/31/2021 05:06:10 - INFO - __main__ - Step 88122: {'lr': 0.00018638429625166946, 'samples': 16919424, 'steps': 88121, 'loss/train': 1.2116124629974365} 08/31/2021 05:06:10 - INFO - __main__ - Step 88123: {'lr': 0.00018637916420609902, 'samples': 16919616, 'steps': 88122, 'loss/train': 1.0656132698059082} 08/31/2021 05:06:12 - INFO - __main__ - Step 88124: {'lr': 0.00018637403218919513, 'samples': 16919808, 'steps': 88123, 'loss/train': 1.2240768671035767} 08/31/2021 05:06:12 - INFO - __main__ - Step 88125: {'lr': 0.00018636890020096012, 'samples': 16920000, 'steps': 88124, 'loss/train': 1.3706873655319214} 08/31/2021 05:06:13 - INFO - __main__ - Step 88126: {'lr': 0.0001863637682413963, 'samples': 16920192, 'steps': 88125, 'loss/train': 0.0360540933907032} 08/31/2021 05:06:13 - INFO - __main__ - Step 88127: {'lr': 0.00018635863631050602, 'samples': 16920384, 'steps': 88126, 'loss/train': 1.4100197553634644} 08/31/2021 05:06:13 - INFO - __main__ - Step 88128: {'lr': 0.00018635350440829153, 'samples': 16920576, 'steps': 88127, 'loss/train': 1.5794299840927124} 08/31/2021 05:06:14 - INFO - __main__ - Step 88129: {'lr': 0.00018634837253475519, 'samples': 16920768, 'steps': 88128, 'loss/train': 1.4352145195007324} 08/31/2021 05:06:15 - INFO - __main__ - Step 88130: {'lr': 0.00018634324068989927, 'samples': 16920960, 'steps': 88129, 'loss/train': 0.5833008289337158} 08/31/2021 05:06:16 - INFO - __main__ - Step 88131: {'lr': 0.00018633810887372612, 'samples': 16921152, 'steps': 88130, 'loss/train': 1.2529270648956299} 08/31/2021 05:06:16 - INFO - __main__ - Step 88132: {'lr': 0.00018633297708623803, 'samples': 16921344, 'steps': 88131, 'loss/train': 0.2892618179321289} 08/31/2021 05:06:17 - INFO - __main__ - Step 88133: {'lr': 0.0001863278453274373, 'samples': 16921536, 'steps': 88132, 'loss/train': 1.4833402633666992} 08/31/2021 05:06:17 - INFO - __main__ - Step 88134: {'lr': 0.00018632271359732627, 'samples': 16921728, 'steps': 88133, 'loss/train': 0.018608657643198967} 08/31/2021 05:06:17 - INFO - __main__ - Step 88135: {'lr': 0.0001863175818959073, 'samples': 16921920, 'steps': 88134, 'loss/train': 0.95108562707901} 08/31/2021 05:06:19 - INFO - __main__ - Step 88136: {'lr': 0.00018631245022318258, 'samples': 16922112, 'steps': 88135, 'loss/train': 1.664706826210022} 08/31/2021 05:06:19 - INFO - __main__ - Step 88137: {'lr': 0.00018630731857915452, 'samples': 16922304, 'steps': 88136, 'loss/train': 1.6043670177459717} 08/31/2021 05:06:20 - INFO - __main__ - Step 88138: {'lr': 0.00018630218696382534, 'samples': 16922496, 'steps': 88137, 'loss/train': 1.6758286952972412} 08/31/2021 05:06:20 - INFO - __main__ - Step 88139: {'lr': 0.00018629705537719744, 'samples': 16922688, 'steps': 88138, 'loss/train': 0.7478255033493042} 08/31/2021 05:06:20 - INFO - __main__ - Step 88140: {'lr': 0.00018629192381927314, 'samples': 16922880, 'steps': 88139, 'loss/train': 1.25774085521698} 08/31/2021 05:06:22 - INFO - __main__ - Step 88141: {'lr': 0.00018628679229005471, 'samples': 16923072, 'steps': 88140, 'loss/train': 1.464821457862854} 08/31/2021 05:06:22 - INFO - __main__ - Step 88142: {'lr': 0.00018628166078954445, 'samples': 16923264, 'steps': 88141, 'loss/train': 0.37410375475883484} 08/31/2021 05:06:23 - INFO - __main__ - Step 88143: {'lr': 0.00018627652931774467, 'samples': 16923456, 'steps': 88142, 'loss/train': 0.9992749691009521} 08/31/2021 05:06:23 - INFO - __main__ - Step 88144: {'lr': 0.0001862713978746577, 'samples': 16923648, 'steps': 88143, 'loss/train': 0.995439350605011} 08/31/2021 05:06:24 - INFO - __main__ - Step 88145: {'lr': 0.0001862662664602859, 'samples': 16923840, 'steps': 88144, 'loss/train': 1.2308013439178467} 08/31/2021 05:06:24 - INFO - __main__ - Step 88146: {'lr': 0.0001862611350746315, 'samples': 16924032, 'steps': 88145, 'loss/train': 1.2627363204956055} 08/31/2021 05:06:25 - INFO - __main__ - Step 88147: {'lr': 0.00018625600371769685, 'samples': 16924224, 'steps': 88146, 'loss/train': 0.024930931627750397} 08/31/2021 05:06:26 - INFO - __main__ - Step 88148: {'lr': 0.00018625087238948427, 'samples': 16924416, 'steps': 88147, 'loss/train': 1.1828203201293945} 08/31/2021 05:06:26 - INFO - __main__ - Step 88149: {'lr': 0.0001862457410899961, 'samples': 16924608, 'steps': 88148, 'loss/train': 1.2773017883300781} 08/31/2021 05:06:27 - INFO - __main__ - Step 88150: {'lr': 0.00018624060981923458, 'samples': 16924800, 'steps': 88149, 'loss/train': 1.2192881107330322} 08/31/2021 05:06:27 - INFO - __main__ - Step 88151: {'lr': 0.0001862354785772021, 'samples': 16924992, 'steps': 88150, 'loss/train': 0.7973419427871704} 08/31/2021 05:06:28 - INFO - __main__ - Step 88152: {'lr': 0.00018623034736390087, 'samples': 16925184, 'steps': 88151, 'loss/train': 1.2303991317749023} 08/31/2021 05:06:29 - INFO - __main__ - Step 88153: {'lr': 0.0001862252161793333, 'samples': 16925376, 'steps': 88152, 'loss/train': 1.6066362857818604} 08/31/2021 05:06:29 - INFO - __main__ - Step 88154: {'lr': 0.00018622008502350163, 'samples': 16925568, 'steps': 88153, 'loss/train': 0.8142213225364685} 08/31/2021 05:06:30 - INFO - __main__ - Step 88155: {'lr': 0.00018621495389640818, 'samples': 16925760, 'steps': 88154, 'loss/train': 1.5555247068405151} 08/31/2021 05:06:30 - INFO - __main__ - Step 88156: {'lr': 0.00018620982279805533, 'samples': 16925952, 'steps': 88155, 'loss/train': 1.1910252571105957} 08/31/2021 05:06:32 - INFO - __main__ - Step 88157: {'lr': 0.00018620469172844534, 'samples': 16926144, 'steps': 88156, 'loss/train': 1.6184544563293457} 08/31/2021 05:06:32 - INFO - __main__ - Step 88158: {'lr': 0.00018619956068758055, 'samples': 16926336, 'steps': 88157, 'loss/train': 1.1037689447402954} 08/31/2021 05:06:32 - INFO - __main__ - Step 88159: {'lr': 0.00018619442967546325, 'samples': 16926528, 'steps': 88158, 'loss/train': 1.0161635875701904} 08/31/2021 05:06:33 - INFO - __main__ - Step 88160: {'lr': 0.00018618929869209573, 'samples': 16926720, 'steps': 88159, 'loss/train': 0.9855750799179077} 08/31/2021 05:06:33 - INFO - __main__ - Step 88161: {'lr': 0.0001861841677374803, 'samples': 16926912, 'steps': 88160, 'loss/train': 0.0821850374341011} 08/31/2021 05:06:35 - INFO - __main__ - Step 88162: {'lr': 0.00018617903681161947, 'samples': 16927104, 'steps': 88161, 'loss/train': 1.4685556888580322} 08/31/2021 05:06:35 - INFO - __main__ - Step 88163: {'lr': 0.00018617390591451526, 'samples': 16927296, 'steps': 88162, 'loss/train': 1.7137424945831299} 08/31/2021 05:06:36 - INFO - __main__ - Step 88164: {'lr': 0.00018616877504617008, 'samples': 16927488, 'steps': 88163, 'loss/train': 1.0964754819869995} 08/31/2021 05:06:36 - INFO - __main__ - Step 88165: {'lr': 0.00018616364420658628, 'samples': 16927680, 'steps': 88164, 'loss/train': 1.4774738550186157} 08/31/2021 05:06:36 - INFO - __main__ - Step 88166: {'lr': 0.00018615851339576616, 'samples': 16927872, 'steps': 88165, 'loss/train': 1.0828250646591187} 08/31/2021 05:06:37 - INFO - __main__ - Step 88167: {'lr': 0.000186153382613712, 'samples': 16928064, 'steps': 88166, 'loss/train': 1.5554416179656982} 08/31/2021 05:06:39 - INFO - __main__ - Step 88168: {'lr': 0.00018614825186042617, 'samples': 16928256, 'steps': 88167, 'loss/train': 0.028819628059864044} 08/31/2021 05:06:39 - INFO - __main__ - Step 88169: {'lr': 0.00018614312113591095, 'samples': 16928448, 'steps': 88168, 'loss/train': 1.666943073272705} 08/31/2021 05:06:40 - INFO - __main__ - Step 88170: {'lr': 0.00018613799044016867, 'samples': 16928640, 'steps': 88169, 'loss/train': 1.4438228607177734} 08/31/2021 05:06:40 - INFO - __main__ - Step 88171: {'lr': 0.00018613285977320157, 'samples': 16928832, 'steps': 88170, 'loss/train': 1.350167155265808} 08/31/2021 05:06:41 - INFO - __main__ - Step 88172: {'lr': 0.00018612772913501207, 'samples': 16929024, 'steps': 88171, 'loss/train': 0.872926652431488} 08/31/2021 05:06:42 - INFO - __main__ - Step 88173: {'lr': 0.0001861225985256024, 'samples': 16929216, 'steps': 88172, 'loss/train': 1.3386338949203491} 08/31/2021 05:06:42 - INFO - __main__ - Step 88174: {'lr': 0.00018611746794497492, 'samples': 16929408, 'steps': 88173, 'loss/train': 0.9016819596290588} 08/31/2021 05:06:43 - INFO - __main__ - Step 88175: {'lr': 0.0001861123373931319, 'samples': 16929600, 'steps': 88174, 'loss/train': 1.4613959789276123} 08/31/2021 05:06:43 - INFO - __main__ - Step 88176: {'lr': 0.0001861072068700758, 'samples': 16929792, 'steps': 88175, 'loss/train': 1.2586308717727661} 08/31/2021 05:06:43 - INFO - __main__ - Step 88177: {'lr': 0.00018610207637580873, 'samples': 16929984, 'steps': 88176, 'loss/train': 1.07135808467865} 08/31/2021 05:06:45 - INFO - __main__ - Step 88178: {'lr': 0.00018609694591033301, 'samples': 16930176, 'steps': 88177, 'loss/train': 1.2579058408737183} 08/31/2021 05:06:45 - INFO - __main__ - Step 88179: {'lr': 0.00018609181547365105, 'samples': 16930368, 'steps': 88178, 'loss/train': 1.5349171161651611} 08/31/2021 05:06:46 - INFO - __main__ - Step 88180: {'lr': 0.00018608668506576515, 'samples': 16930560, 'steps': 88179, 'loss/train': 1.0662834644317627} 08/31/2021 05:06:46 - INFO - __main__ - Step 88181: {'lr': 0.00018608155468667758, 'samples': 16930752, 'steps': 88180, 'loss/train': 1.3401650190353394} 08/31/2021 05:06:46 - INFO - __main__ - Step 88182: {'lr': 0.0001860764243363907, 'samples': 16930944, 'steps': 88181, 'loss/train': 0.39939072728157043} 08/31/2021 05:06:48 - INFO - __main__ - Step 88183: {'lr': 0.0001860712940149068, 'samples': 16931136, 'steps': 88182, 'loss/train': 0.8127105832099915} 08/31/2021 05:06:48 - INFO - __main__ - Step 88184: {'lr': 0.0001860661637222282, 'samples': 16931328, 'steps': 88183, 'loss/train': 1.227745532989502} 08/31/2021 05:06:49 - INFO - __main__ - Step 88185: {'lr': 0.00018606103345835713, 'samples': 16931520, 'steps': 88184, 'loss/train': 1.393812894821167} 08/31/2021 05:06:49 - INFO - __main__ - Step 88186: {'lr': 0.000186055903223296, 'samples': 16931712, 'steps': 88185, 'loss/train': 0.03726163133978844} 08/31/2021 05:06:50 - INFO - __main__ - Step 88187: {'lr': 0.00018605077301704712, 'samples': 16931904, 'steps': 88186, 'loss/train': 1.368104100227356} 08/31/2021 05:06:51 - INFO - __main__ - Step 88188: {'lr': 0.00018604564283961278, 'samples': 16932096, 'steps': 88187, 'loss/train': 1.255409598350525} 08/31/2021 05:06:52 - INFO - __main__ - Step 88189: {'lr': 0.00018604051269099537, 'samples': 16932288, 'steps': 88188, 'loss/train': 1.47235107421875} 08/31/2021 05:06:52 - INFO - __main__ - Step 88190: {'lr': 0.000186035382571197, 'samples': 16932480, 'steps': 88189, 'loss/train': 1.1875598430633545} 08/31/2021 05:06:52 - INFO - __main__ - Step 88191: {'lr': 0.00018603025248022011, 'samples': 16932672, 'steps': 88190, 'loss/train': 1.2460100650787354} 08/31/2021 05:06:53 - INFO - __main__ - Step 88192: {'lr': 0.000186025122418067, 'samples': 16932864, 'steps': 88191, 'loss/train': 1.9242507219314575} 08/31/2021 05:06:53 - INFO - __main__ - Step 88193: {'lr': 0.00018601999238474003, 'samples': 16933056, 'steps': 88192, 'loss/train': 0.7977360486984253} 08/31/2021 05:06:55 - INFO - __main__ - Step 88194: {'lr': 0.0001860148623802414, 'samples': 16933248, 'steps': 88193, 'loss/train': 1.06411874294281} 08/31/2021 05:06:55 - INFO - __main__ - Step 88195: {'lr': 0.00018600973240457354, 'samples': 16933440, 'steps': 88194, 'loss/train': 1.7455787658691406} 08/31/2021 05:06:55 - INFO - __main__ - Step 88196: {'lr': 0.00018600460245773865, 'samples': 16933632, 'steps': 88195, 'loss/train': 0.8659244179725647} 08/31/2021 05:06:56 - INFO - __main__ - Step 88197: {'lr': 0.00018599947253973914, 'samples': 16933824, 'steps': 88196, 'loss/train': 1.3187129497528076} 08/31/2021 05:06:56 - INFO - __main__ - Step 88198: {'lr': 0.00018599434265057725, 'samples': 16934016, 'steps': 88197, 'loss/train': 1.102843999862671} 08/31/2021 05:06:58 - INFO - __main__ - Step 88199: {'lr': 0.00018598921279025532, 'samples': 16934208, 'steps': 88198, 'loss/train': 1.0053887367248535} 08/31/2021 05:06:58 - INFO - __main__ - Step 88200: {'lr': 0.00018598408295877569, 'samples': 16934400, 'steps': 88199, 'loss/train': 1.0450783967971802} 08/31/2021 05:06:59 - INFO - __main__ - Step 88201: {'lr': 0.00018597895315614066, 'samples': 16934592, 'steps': 88200, 'loss/train': 1.7611678838729858} 08/31/2021 05:06:59 - INFO - __main__ - Step 88202: {'lr': 0.00018597382338235248, 'samples': 16934784, 'steps': 88201, 'loss/train': 1.7220381498336792} 08/31/2021 05:07:00 - INFO - __main__ - Step 88203: {'lr': 0.00018596869363741365, 'samples': 16934976, 'steps': 88202, 'loss/train': 1.3473762273788452} 08/31/2021 05:07:00 - INFO - __main__ - Step 88204: {'lr': 0.0001859635639213262, 'samples': 16935168, 'steps': 88203, 'loss/train': 1.2311789989471436} 08/31/2021 05:07:00 - INFO - __main__ - Step 88205: {'lr': 0.0001859584342340926, 'samples': 16935360, 'steps': 88204, 'loss/train': 1.4571526050567627} 08/31/2021 05:07:02 - INFO - __main__ - Step 88206: {'lr': 0.00018595330457571514, 'samples': 16935552, 'steps': 88205, 'loss/train': 1.29172682762146} 08/31/2021 05:07:02 - INFO - __main__ - Step 88207: {'lr': 0.00018594817494619614, 'samples': 16935744, 'steps': 88206, 'loss/train': 1.506442666053772} 08/31/2021 05:07:03 - INFO - __main__ - Step 88208: {'lr': 0.0001859430453455379, 'samples': 16935936, 'steps': 88207, 'loss/train': 0.026816243305802345} 08/31/2021 05:07:03 - INFO - __main__ - Step 88209: {'lr': 0.0001859379157737427, 'samples': 16936128, 'steps': 88208, 'loss/train': 1.0222294330596924} 08/31/2021 05:07:03 - INFO - __main__ - Step 88210: {'lr': 0.00018593278623081294, 'samples': 16936320, 'steps': 88209, 'loss/train': 1.2593047618865967} 08/31/2021 05:07:05 - INFO - __main__ - Step 88211: {'lr': 0.00018592765671675081, 'samples': 16936512, 'steps': 88210, 'loss/train': 0.8489750623703003} 08/31/2021 05:07:05 - INFO - __main__ - Step 88212: {'lr': 0.00018592252723155877, 'samples': 16936704, 'steps': 88211, 'loss/train': 1.1663514375686646} 08/31/2021 05:07:06 - INFO - __main__ - Step 88213: {'lr': 0.00018591739777523903, 'samples': 16936896, 'steps': 88212, 'loss/train': 1.318610668182373} 08/31/2021 05:07:06 - INFO - __main__ - Step 88214: {'lr': 0.0001859122683477939, 'samples': 16937088, 'steps': 88213, 'loss/train': 1.2409306764602661} 08/31/2021 05:07:06 - INFO - __main__ - Step 88215: {'lr': 0.0001859071389492257, 'samples': 16937280, 'steps': 88214, 'loss/train': 0.5559994578361511} 08/31/2021 05:07:08 - INFO - __main__ - Step 88216: {'lr': 0.00018590200957953687, 'samples': 16937472, 'steps': 88215, 'loss/train': 1.7285765409469604} 08/31/2021 05:07:08 - INFO - __main__ - Step 88217: {'lr': 0.00018589688023872952, 'samples': 16937664, 'steps': 88216, 'loss/train': 1.1022255420684814} 08/31/2021 05:07:08 - INFO - __main__ - Step 88218: {'lr': 0.00018589175092680605, 'samples': 16937856, 'steps': 88217, 'loss/train': 1.8720289468765259} 08/31/2021 05:07:09 - INFO - __main__ - Step 88219: {'lr': 0.00018588662164376873, 'samples': 16938048, 'steps': 88218, 'loss/train': 1.6129488945007324} 08/31/2021 05:07:09 - INFO - __main__ - Step 88220: {'lr': 0.00018588149238961993, 'samples': 16938240, 'steps': 88219, 'loss/train': 0.09391655027866364} 08/31/2021 05:07:11 - INFO - __main__ - Step 88221: {'lr': 0.00018587636316436197, 'samples': 16938432, 'steps': 88220, 'loss/train': 1.2877758741378784} 08/31/2021 05:07:11 - INFO - __main__ - Step 88222: {'lr': 0.00018587123396799707, 'samples': 16938624, 'steps': 88221, 'loss/train': 1.2850902080535889} 08/31/2021 05:07:12 - INFO - __main__ - Step 88223: {'lr': 0.00018586610480052763, 'samples': 16938816, 'steps': 88222, 'loss/train': 0.6229005455970764} 08/31/2021 05:07:12 - INFO - __main__ - Step 88224: {'lr': 0.00018586097566195594, 'samples': 16939008, 'steps': 88223, 'loss/train': 0.27434679865837097} 08/31/2021 05:07:12 - INFO - __main__ - Step 88225: {'lr': 0.00018585584655228432, 'samples': 16939200, 'steps': 88224, 'loss/train': 0.03907999023795128} 08/31/2021 05:07:14 - INFO - __main__ - Step 88226: {'lr': 0.00018585071747151505, 'samples': 16939392, 'steps': 88225, 'loss/train': 1.0237010717391968} 08/31/2021 05:07:15 - INFO - __main__ - Step 88227: {'lr': 0.00018584558841965043, 'samples': 16939584, 'steps': 88226, 'loss/train': 1.0720847845077515} 08/31/2021 05:07:15 - INFO - __main__ - Step 88228: {'lr': 0.00018584045939669283, 'samples': 16939776, 'steps': 88227, 'loss/train': 1.6691136360168457} 08/31/2021 05:07:16 - INFO - __main__ - Step 88229: {'lr': 0.00018583533040264456, 'samples': 16939968, 'steps': 88228, 'loss/train': 0.7894421219825745} 08/31/2021 05:07:16 - INFO - __main__ - Step 88230: {'lr': 0.00018583020143750795, 'samples': 16940160, 'steps': 88229, 'loss/train': 0.9446120858192444} 08/31/2021 05:07:16 - INFO - __main__ - Step 88231: {'lr': 0.00018582507250128517, 'samples': 16940352, 'steps': 88230, 'loss/train': 0.917838990688324} 08/31/2021 05:07:18 - INFO - __main__ - Step 88232: {'lr': 0.00018581994359397863, 'samples': 16940544, 'steps': 88231, 'loss/train': 0.9539543986320496} 08/31/2021 05:07:18 - INFO - __main__ - Step 88233: {'lr': 0.0001858148147155906, 'samples': 16940736, 'steps': 88232, 'loss/train': 1.1140767335891724} 08/31/2021 05:07:18 - INFO - __main__ - Step 88234: {'lr': 0.00018580968586612347, 'samples': 16940928, 'steps': 88233, 'loss/train': 1.1828525066375732} 08/31/2021 05:07:19 - INFO - __main__ - Step 88235: {'lr': 0.00018580455704557948, 'samples': 16941120, 'steps': 88234, 'loss/train': 0.5161780118942261} 08/31/2021 05:07:19 - INFO - __main__ - Step 88236: {'lr': 0.000185799428253961, 'samples': 16941312, 'steps': 88235, 'loss/train': 1.3921812772750854} 08/31/2021 05:07:21 - INFO - __main__ - Step 88237: {'lr': 0.00018579429949127025, 'samples': 16941504, 'steps': 88236, 'loss/train': 1.3930273056030273} 08/31/2021 05:07:21 - INFO - __main__ - Step 88238: {'lr': 0.00018578917075750965, 'samples': 16941696, 'steps': 88237, 'loss/train': 1.1618404388427734} 08/31/2021 05:07:21 - INFO - __main__ - Step 88239: {'lr': 0.00018578404205268144, 'samples': 16941888, 'steps': 88238, 'loss/train': 1.1199952363967896} 08/31/2021 05:07:22 - INFO - __main__ - Step 88240: {'lr': 0.00018577891337678794, 'samples': 16942080, 'steps': 88239, 'loss/train': 1.369828224182129} 08/31/2021 05:07:22 - INFO - __main__ - Step 88241: {'lr': 0.00018577378472983146, 'samples': 16942272, 'steps': 88240, 'loss/train': 1.312348484992981} 08/31/2021 05:07:24 - INFO - __main__ - Step 88242: {'lr': 0.00018576865611181443, 'samples': 16942464, 'steps': 88241, 'loss/train': 1.559334635734558} 08/31/2021 05:07:24 - INFO - __main__ - Step 88243: {'lr': 0.000185763527522739, 'samples': 16942656, 'steps': 88242, 'loss/train': 1.3833013772964478} 08/31/2021 05:07:25 - INFO - __main__ - Step 88244: {'lr': 0.00018575839896260748, 'samples': 16942848, 'steps': 88243, 'loss/train': 0.7544865012168884} 08/31/2021 05:07:25 - INFO - __main__ - Step 88245: {'lr': 0.00018575327043142227, 'samples': 16943040, 'steps': 88244, 'loss/train': 0.4949396252632141} 08/31/2021 05:07:25 - INFO - __main__ - Step 88246: {'lr': 0.0001857481419291856, 'samples': 16943232, 'steps': 88245, 'loss/train': 0.9518331289291382} 08/31/2021 05:07:26 - INFO - __main__ - Step 88247: {'lr': 0.00018574301345589987, 'samples': 16943424, 'steps': 88246, 'loss/train': 1.1999603509902954} 08/31/2021 05:07:27 - INFO - __main__ - Step 88248: {'lr': 0.0001857378850115673, 'samples': 16943616, 'steps': 88247, 'loss/train': 0.6692808270454407} 08/31/2021 05:07:28 - INFO - __main__ - Step 88249: {'lr': 0.0001857327565961903, 'samples': 16943808, 'steps': 88248, 'loss/train': 1.148358941078186} 08/31/2021 05:07:28 - INFO - __main__ - Step 88250: {'lr': 0.00018572762820977107, 'samples': 16944000, 'steps': 88249, 'loss/train': 0.6869919896125793} 08/31/2021 05:07:28 - INFO - __main__ - Step 88251: {'lr': 0.00018572249985231206, 'samples': 16944192, 'steps': 88250, 'loss/train': 1.477371096611023} 08/31/2021 05:07:29 - INFO - __main__ - Step 88252: {'lr': 0.0001857173715238154, 'samples': 16944384, 'steps': 88251, 'loss/train': 1.0166488885879517} 08/31/2021 05:07:30 - INFO - __main__ - Step 88253: {'lr': 0.0001857122432242836, 'samples': 16944576, 'steps': 88252, 'loss/train': 1.3888778686523438} 08/31/2021 05:07:31 - INFO - __main__ - Step 88254: {'lr': 0.00018570711495371884, 'samples': 16944768, 'steps': 88253, 'loss/train': 1.363547444343567} 08/31/2021 05:07:31 - INFO - __main__ - Step 88255: {'lr': 0.00018570198671212347, 'samples': 16944960, 'steps': 88254, 'loss/train': 1.0289247035980225} 08/31/2021 05:07:31 - INFO - __main__ - Step 88256: {'lr': 0.0001856968584994998, 'samples': 16945152, 'steps': 88255, 'loss/train': 1.2985503673553467} 08/31/2021 05:07:32 - INFO - __main__ - Step 88257: {'lr': 0.0001856917303158501, 'samples': 16945344, 'steps': 88256, 'loss/train': 1.3276987075805664} 08/31/2021 05:07:33 - INFO - __main__ - Step 88258: {'lr': 0.00018568660216117673, 'samples': 16945536, 'steps': 88257, 'loss/train': 1.1490858793258667} 08/31/2021 05:07:34 - INFO - __main__ - Step 88259: {'lr': 0.00018568147403548197, 'samples': 16945728, 'steps': 88258, 'loss/train': 1.2743122577667236} 08/31/2021 05:07:34 - INFO - __main__ - Step 88260: {'lr': 0.00018567634593876815, 'samples': 16945920, 'steps': 88259, 'loss/train': 0.7604942917823792} 08/31/2021 05:07:34 - INFO - __main__ - Step 88261: {'lr': 0.00018567121787103755, 'samples': 16946112, 'steps': 88260, 'loss/train': 1.2317734956741333} 08/31/2021 05:07:35 - INFO - __main__ - Step 88262: {'lr': 0.00018566608983229253, 'samples': 16946304, 'steps': 88261, 'loss/train': 0.7006445527076721} 08/31/2021 05:07:36 - INFO - __main__ - Step 88263: {'lr': 0.00018566096182253536, 'samples': 16946496, 'steps': 88262, 'loss/train': 1.3678945302963257} 08/31/2021 05:07:37 - INFO - __main__ - Step 88264: {'lr': 0.00018565583384176843, 'samples': 16946688, 'steps': 88263, 'loss/train': 1.2142711877822876} 08/31/2021 05:07:37 - INFO - __main__ - Step 88265: {'lr': 0.00018565070588999393, 'samples': 16946880, 'steps': 88264, 'loss/train': 1.4826433658599854} 08/31/2021 05:07:38 - INFO - __main__ - Step 88266: {'lr': 0.00018564557796721425, 'samples': 16947072, 'steps': 88265, 'loss/train': 0.8924927115440369} 08/31/2021 05:07:38 - INFO - __main__ - Step 88267: {'lr': 0.00018564045007343167, 'samples': 16947264, 'steps': 88266, 'loss/train': 1.4809645414352417} 08/31/2021 05:07:38 - INFO - __main__ - Step 88268: {'lr': 0.0001856353222086485, 'samples': 16947456, 'steps': 88267, 'loss/train': 1.206968903541565} 08/31/2021 05:07:40 - INFO - __main__ - Step 88269: {'lr': 0.0001856301943728671, 'samples': 16947648, 'steps': 88268, 'loss/train': 1.397655725479126} 08/31/2021 05:07:40 - INFO - __main__ - Step 88270: {'lr': 0.00018562506656608974, 'samples': 16947840, 'steps': 88269, 'loss/train': 0.7645599842071533} 08/31/2021 05:07:41 - INFO - __main__ - Step 88271: {'lr': 0.00018561993878831874, 'samples': 16948032, 'steps': 88270, 'loss/train': 0.2460959553718567} 08/31/2021 05:07:41 - INFO - __main__ - Step 88272: {'lr': 0.00018561481103955636, 'samples': 16948224, 'steps': 88271, 'loss/train': 1.7599263191223145} 08/31/2021 05:07:41 - INFO - __main__ - Step 88273: {'lr': 0.00018560968331980495, 'samples': 16948416, 'steps': 88272, 'loss/train': 1.3599531650543213} 08/31/2021 05:07:43 - INFO - __main__ - Step 88274: {'lr': 0.0001856045556290668, 'samples': 16948608, 'steps': 88273, 'loss/train': 1.4892003536224365} 08/31/2021 05:07:43 - INFO - __main__ - Step 88275: {'lr': 0.00018559942796734434, 'samples': 16948800, 'steps': 88274, 'loss/train': 1.3532555103302002} 08/31/2021 05:07:44 - INFO - __main__ - Step 88276: {'lr': 0.0001855943003346397, 'samples': 16948992, 'steps': 88275, 'loss/train': 1.401917815208435} 08/31/2021 05:07:44 - INFO - __main__ - Step 88277: {'lr': 0.00018558917273095533, 'samples': 16949184, 'steps': 88276, 'loss/train': 1.0446840524673462} 08/31/2021 05:07:44 - INFO - __main__ - Step 88278: {'lr': 0.0001855840451562934, 'samples': 16949376, 'steps': 88277, 'loss/train': 0.8756791949272156} 08/31/2021 05:07:46 - INFO - __main__ - Step 88279: {'lr': 0.00018557891761065637, 'samples': 16949568, 'steps': 88278, 'loss/train': 1.0971864461898804} 08/31/2021 05:07:47 - INFO - __main__ - Step 88280: {'lr': 0.00018557379009404647, 'samples': 16949760, 'steps': 88279, 'loss/train': 1.4580949544906616} 08/31/2021 05:07:47 - INFO - __main__ - Step 88281: {'lr': 0.00018556866260646606, 'samples': 16949952, 'steps': 88280, 'loss/train': 1.091831088066101} 08/31/2021 05:07:48 - INFO - __main__ - Step 88282: {'lr': 0.00018556353514791735, 'samples': 16950144, 'steps': 88281, 'loss/train': 1.1303517818450928} 08/31/2021 05:07:48 - INFO - __main__ - Step 88283: {'lr': 0.0001855584077184028, 'samples': 16950336, 'steps': 88282, 'loss/train': 1.6084027290344238} 08/31/2021 05:07:49 - INFO - __main__ - Step 88284: {'lr': 0.00018555328031792456, 'samples': 16950528, 'steps': 88283, 'loss/train': 1.1899775266647339} 08/31/2021 05:07:50 - INFO - __main__ - Step 88285: {'lr': 0.00018554815294648505, 'samples': 16950720, 'steps': 88284, 'loss/train': 0.8412714600563049} 08/31/2021 05:07:50 - INFO - __main__ - Step 88286: {'lr': 0.0001855430256040866, 'samples': 16950912, 'steps': 88285, 'loss/train': 1.200361967086792} 08/31/2021 05:07:51 - INFO - __main__ - Step 88287: {'lr': 0.00018553789829073143, 'samples': 16951104, 'steps': 88286, 'loss/train': 1.3823908567428589} 08/31/2021 05:07:51 - INFO - __main__ - Step 88288: {'lr': 0.00018553277100642185, 'samples': 16951296, 'steps': 88287, 'loss/train': 0.6996343731880188} 08/31/2021 05:07:53 - INFO - __main__ - Step 88289: {'lr': 0.0001855276437511602, 'samples': 16951488, 'steps': 88288, 'loss/train': 1.0921306610107422} 08/31/2021 05:07:53 - INFO - __main__ - Step 88290: {'lr': 0.00018552251652494885, 'samples': 16951680, 'steps': 88289, 'loss/train': 1.2760729789733887} 08/31/2021 05:07:53 - INFO - __main__ - Step 88291: {'lr': 0.00018551738932779, 'samples': 16951872, 'steps': 88290, 'loss/train': 1.0588879585266113} 08/31/2021 05:07:54 - INFO - __main__ - Step 88292: {'lr': 0.00018551226215968609, 'samples': 16952064, 'steps': 88291, 'loss/train': 1.6310914754867554} 08/31/2021 05:07:54 - INFO - __main__ - Step 88293: {'lr': 0.00018550713502063932, 'samples': 16952256, 'steps': 88292, 'loss/train': 1.3880153894424438} 08/31/2021 05:07:54 - INFO - __main__ - Step 88294: {'lr': 0.00018550200791065202, 'samples': 16952448, 'steps': 88293, 'loss/train': 0.6895928978919983} 08/31/2021 05:07:56 - INFO - __main__ - Step 88295: {'lr': 0.00018549688082972654, 'samples': 16952640, 'steps': 88294, 'loss/train': 0.5249020457267761} 08/31/2021 05:07:57 - INFO - __main__ - Step 88296: {'lr': 0.00018549175377786516, 'samples': 16952832, 'steps': 88295, 'loss/train': 0.04984721168875694} 08/31/2021 05:07:57 - INFO - __main__ - Step 88297: {'lr': 0.00018548662675507032, 'samples': 16953024, 'steps': 88296, 'loss/train': 1.1503278017044067} 08/31/2021 05:07:57 - INFO - __main__ - Step 88298: {'lr': 0.0001854814997613441, 'samples': 16953216, 'steps': 88297, 'loss/train': 0.8464875817298889} 08/31/2021 05:07:58 - INFO - __main__ - Step 88299: {'lr': 0.00018547637279668893, 'samples': 16953408, 'steps': 88298, 'loss/train': 1.4151819944381714} 08/31/2021 05:07:59 - INFO - __main__ - Step 88300: {'lr': 0.0001854712458611071, 'samples': 16953600, 'steps': 88299, 'loss/train': 1.4783251285552979} 08/31/2021 05:08:00 - INFO - __main__ - Step 88301: {'lr': 0.00018546611895460093, 'samples': 16953792, 'steps': 88300, 'loss/train': 1.1873382329940796} 08/31/2021 05:08:00 - INFO - __main__ - Step 88302: {'lr': 0.00018546099207717275, 'samples': 16953984, 'steps': 88301, 'loss/train': 0.9507588744163513} 08/31/2021 05:08:00 - INFO - __main__ - Step 88303: {'lr': 0.00018545586522882482, 'samples': 16954176, 'steps': 88302, 'loss/train': 1.3223530054092407} 08/31/2021 05:08:01 - INFO - __main__ - Step 88304: {'lr': 0.0001854507384095595, 'samples': 16954368, 'steps': 88303, 'loss/train': 1.457416296005249} 08/31/2021 05:08:02 - INFO - __main__ - Step 88305: {'lr': 0.00018544561161937907, 'samples': 16954560, 'steps': 88304, 'loss/train': 1.4202321767807007} 08/31/2021 05:08:03 - INFO - __main__ - Step 88306: {'lr': 0.00018544048485828586, 'samples': 16954752, 'steps': 88305, 'loss/train': 1.1883755922317505} 08/31/2021 05:08:03 - INFO - __main__ - Step 88307: {'lr': 0.00018543535812628217, 'samples': 16954944, 'steps': 88306, 'loss/train': 1.3657183647155762} 08/31/2021 05:08:03 - INFO - __main__ - Step 88308: {'lr': 0.0001854302314233703, 'samples': 16955136, 'steps': 88307, 'loss/train': 1.5742648839950562} 08/31/2021 05:08:04 - INFO - __main__ - Step 88309: {'lr': 0.00018542510474955259, 'samples': 16955328, 'steps': 88308, 'loss/train': 0.8727539777755737} 08/31/2021 05:08:05 - INFO - __main__ - Step 88310: {'lr': 0.00018541997810483146, 'samples': 16955520, 'steps': 88309, 'loss/train': 0.9064446687698364} 08/31/2021 05:08:06 - INFO - __main__ - Step 88311: {'lr': 0.00018541485148920896, 'samples': 16955712, 'steps': 88310, 'loss/train': 1.2063761949539185} 08/31/2021 05:08:06 - INFO - __main__ - Step 88312: {'lr': 0.0001854097249026875, 'samples': 16955904, 'steps': 88311, 'loss/train': 1.3063288927078247} 08/31/2021 05:08:06 - INFO - __main__ - Step 88313: {'lr': 0.00018540459834526945, 'samples': 16956096, 'steps': 88312, 'loss/train': 0.9642904996871948} 08/31/2021 05:08:07 - INFO - __main__ - Step 88314: {'lr': 0.0001853994718169571, 'samples': 16956288, 'steps': 88313, 'loss/train': 1.0731381177902222} 08/31/2021 05:08:07 - INFO - __main__ - Step 88315: {'lr': 0.00018539434531775274, 'samples': 16956480, 'steps': 88314, 'loss/train': 1.2645103931427002} 08/31/2021 05:08:09 - INFO - __main__ - Step 88316: {'lr': 0.0001853892188476587, 'samples': 16956672, 'steps': 88315, 'loss/train': 1.1306856870651245} 08/31/2021 05:08:09 - INFO - __main__ - Step 88317: {'lr': 0.00018538409240667725, 'samples': 16956864, 'steps': 88316, 'loss/train': 1.1568477153778076} 08/31/2021 05:08:10 - INFO - __main__ - Step 88318: {'lr': 0.00018537896599481077, 'samples': 16957056, 'steps': 88317, 'loss/train': 0.7976504564285278} 08/31/2021 05:08:10 - INFO - __main__ - Step 88319: {'lr': 0.0001853738396120615, 'samples': 16957248, 'steps': 88318, 'loss/train': 1.4883735179901123} 08/31/2021 05:08:10 - INFO - __main__ - Step 88320: {'lr': 0.0001853687132584318, 'samples': 16957440, 'steps': 88319, 'loss/train': 1.0560240745544434} 08/31/2021 05:08:12 - INFO - __main__ - Step 88321: {'lr': 0.00018536358693392396, 'samples': 16957632, 'steps': 88320, 'loss/train': 0.07328388094902039} 08/31/2021 05:08:12 - INFO - __main__ - Step 88322: {'lr': 0.00018535846063854027, 'samples': 16957824, 'steps': 88321, 'loss/train': 1.44451904296875} 08/31/2021 05:08:13 - INFO - __main__ - Step 88323: {'lr': 0.0001853533343722831, 'samples': 16958016, 'steps': 88322, 'loss/train': 1.588422179222107} 08/31/2021 05:08:13 - INFO - __main__ - Step 88324: {'lr': 0.00018534820813515478, 'samples': 16958208, 'steps': 88323, 'loss/train': 0.12690380215644836} 08/31/2021 05:08:13 - INFO - __main__ - Step 88325: {'lr': 0.0001853430819271575, 'samples': 16958400, 'steps': 88324, 'loss/train': 1.0230693817138672} 08/31/2021 05:08:15 - INFO - __main__ - Step 88326: {'lr': 0.0001853379557482936, 'samples': 16958592, 'steps': 88325, 'loss/train': 1.0269924402236938} 08/31/2021 05:08:15 - INFO - __main__ - Step 88327: {'lr': 0.00018533282959856543, 'samples': 16958784, 'steps': 88326, 'loss/train': 0.03138868138194084} 08/31/2021 05:08:16 - INFO - __main__ - Step 88328: {'lr': 0.00018532770347797528, 'samples': 16958976, 'steps': 88327, 'loss/train': 0.5639373064041138} 08/31/2021 05:08:16 - INFO - __main__ - Step 88329: {'lr': 0.00018532257738652547, 'samples': 16959168, 'steps': 88328, 'loss/train': 0.8565815687179565} 08/31/2021 05:08:16 - INFO - __main__ - Step 88330: {'lr': 0.0001853174513242183, 'samples': 16959360, 'steps': 88329, 'loss/train': 0.9226431250572205} 08/31/2021 05:08:18 - INFO - __main__ - Step 88331: {'lr': 0.00018531232529105614, 'samples': 16959552, 'steps': 88330, 'loss/train': 1.3665626049041748} 08/31/2021 05:08:18 - INFO - __main__ - Step 88332: {'lr': 0.00018530719928704117, 'samples': 16959744, 'steps': 88331, 'loss/train': 1.1814647912979126} 08/31/2021 05:08:19 - INFO - __main__ - Step 88333: {'lr': 0.0001853020733121758, 'samples': 16959936, 'steps': 88332, 'loss/train': 1.3042622804641724} 08/31/2021 05:08:19 - INFO - __main__ - Step 88334: {'lr': 0.00018529694736646235, 'samples': 16960128, 'steps': 88333, 'loss/train': 1.4318392276763916} 08/31/2021 05:08:19 - INFO - __main__ - Step 88335: {'lr': 0.00018529182144990308, 'samples': 16960320, 'steps': 88334, 'loss/train': 1.0920344591140747} 08/31/2021 05:08:21 - INFO - __main__ - Step 88336: {'lr': 0.00018528669556250034, 'samples': 16960512, 'steps': 88335, 'loss/train': 1.2671451568603516} 08/31/2021 05:08:22 - INFO - __main__ - Step 88337: {'lr': 0.00018528156970425646, 'samples': 16960704, 'steps': 88336, 'loss/train': 0.9552784562110901} 08/31/2021 05:08:22 - INFO - __main__ - Step 88338: {'lr': 0.00018527644387517368, 'samples': 16960896, 'steps': 88337, 'loss/train': 0.7266471982002258} 08/31/2021 05:08:22 - INFO - __main__ - Step 88339: {'lr': 0.00018527131807525427, 'samples': 16961088, 'steps': 88338, 'loss/train': 1.2938885688781738} 08/31/2021 05:08:23 - INFO - __main__ - Step 88340: {'lr': 0.00018526619230450065, 'samples': 16961280, 'steps': 88339, 'loss/train': 1.4202384948730469} 08/31/2021 05:08:25 - INFO - __main__ - Step 88341: {'lr': 0.00018526106656291505, 'samples': 16961472, 'steps': 88340, 'loss/train': 0.9487646818161011} 08/31/2021 05:08:25 - INFO - __main__ - Step 88342: {'lr': 0.00018525594085049983, 'samples': 16961664, 'steps': 88341, 'loss/train': 1.496353268623352} 08/31/2021 05:08:26 - INFO - __main__ - Step 88343: {'lr': 0.0001852508151672573, 'samples': 16961856, 'steps': 88342, 'loss/train': 1.5927678346633911} 08/31/2021 05:08:26 - INFO - __main__ - Step 88344: {'lr': 0.00018524568951318971, 'samples': 16962048, 'steps': 88343, 'loss/train': 1.0278819799423218} 08/31/2021 05:08:26 - INFO - __main__ - Step 88345: {'lr': 0.00018524056388829945, 'samples': 16962240, 'steps': 88344, 'loss/train': 0.6610270738601685} 08/31/2021 05:08:27 - INFO - __main__ - Step 88346: {'lr': 0.00018523543829258876, 'samples': 16962432, 'steps': 88345, 'loss/train': 1.5011613368988037} 08/31/2021 05:08:27 - INFO - __main__ - Step 88347: {'lr': 0.00018523031272606004, 'samples': 16962624, 'steps': 88346, 'loss/train': 1.5174616575241089} 08/31/2021 05:08:29 - INFO - __main__ - Step 88348: {'lr': 0.0001852251871887155, 'samples': 16962816, 'steps': 88347, 'loss/train': 1.4801572561264038} 08/31/2021 05:08:29 - INFO - __main__ - Step 88349: {'lr': 0.0001852200616805575, 'samples': 16963008, 'steps': 88348, 'loss/train': 1.0051156282424927} 08/31/2021 05:08:29 - INFO - __main__ - Step 88350: {'lr': 0.00018521493620158832, 'samples': 16963200, 'steps': 88349, 'loss/train': 1.0452908277511597} 08/31/2021 05:08:30 - INFO - __main__ - Step 88351: {'lr': 0.00018520981075181042, 'samples': 16963392, 'steps': 88350, 'loss/train': 1.1366699934005737} 08/31/2021 05:08:30 - INFO - __main__ - Step 88352: {'lr': 0.00018520468533122586, 'samples': 16963584, 'steps': 88351, 'loss/train': 1.4272912740707397} 08/31/2021 05:08:32 - INFO - __main__ - Step 88353: {'lr': 0.00018519955993983708, 'samples': 16963776, 'steps': 88352, 'loss/train': 1.0339161157608032} 08/31/2021 05:08:32 - INFO - __main__ - Step 88354: {'lr': 0.0001851944345776464, 'samples': 16963968, 'steps': 88353, 'loss/train': 0.9745159149169922} 08/31/2021 05:08:32 - INFO - __main__ - Step 88355: {'lr': 0.00018518930924465605, 'samples': 16964160, 'steps': 88354, 'loss/train': 1.05054771900177} 08/31/2021 05:08:33 - INFO - __main__ - Step 88356: {'lr': 0.00018518418394086844, 'samples': 16964352, 'steps': 88355, 'loss/train': 1.0901131629943848} 08/31/2021 05:08:33 - INFO - __main__ - Step 88357: {'lr': 0.00018517905866628583, 'samples': 16964544, 'steps': 88356, 'loss/train': 1.2048362493515015} 08/31/2021 05:08:35 - INFO - __main__ - Step 88358: {'lr': 0.00018517393342091054, 'samples': 16964736, 'steps': 88357, 'loss/train': 0.19978578388690948} 08/31/2021 05:08:35 - INFO - __main__ - Step 88359: {'lr': 0.00018516880820474484, 'samples': 16964928, 'steps': 88358, 'loss/train': 1.1276886463165283} 08/31/2021 05:08:35 - INFO - __main__ - Step 88360: {'lr': 0.00018516368301779113, 'samples': 16965120, 'steps': 88359, 'loss/train': 1.2429925203323364} 08/31/2021 05:08:36 - INFO - __main__ - Step 88361: {'lr': 0.00018515855786005163, 'samples': 16965312, 'steps': 88360, 'loss/train': 1.337601661682129} 08/31/2021 05:08:36 - INFO - __main__ - Step 88362: {'lr': 0.0001851534327315287, 'samples': 16965504, 'steps': 88361, 'loss/train': 1.0049580335617065} 08/31/2021 05:08:38 - INFO - __main__ - Step 88363: {'lr': 0.00018514830763222462, 'samples': 16965696, 'steps': 88362, 'loss/train': 1.1575491428375244} 08/31/2021 05:08:38 - INFO - __main__ - Step 88364: {'lr': 0.0001851431825621418, 'samples': 16965888, 'steps': 88363, 'loss/train': 0.5562657117843628} 08/31/2021 05:08:38 - INFO - __main__ - Step 88365: {'lr': 0.0001851380575212824, 'samples': 16966080, 'steps': 88364, 'loss/train': 0.8368054628372192} 08/31/2021 05:08:39 - INFO - __main__ - Step 88366: {'lr': 0.00018513293250964875, 'samples': 16966272, 'steps': 88365, 'loss/train': 1.3178260326385498} 08/31/2021 05:08:39 - INFO - __main__ - Step 88367: {'lr': 0.00018512780752724323, 'samples': 16966464, 'steps': 88366, 'loss/train': 1.1544729471206665} 08/31/2021 05:08:40 - INFO - __main__ - Step 88368: {'lr': 0.0001851226825740681, 'samples': 16966656, 'steps': 88367, 'loss/train': 1.1055186986923218} 08/31/2021 05:08:41 - INFO - __main__ - Step 88369: {'lr': 0.00018511755765012567, 'samples': 16966848, 'steps': 88368, 'loss/train': 1.5346479415893555} 08/31/2021 05:08:41 - INFO - __main__ - Step 88370: {'lr': 0.00018511243275541828, 'samples': 16967040, 'steps': 88369, 'loss/train': 0.9387703537940979} 08/31/2021 05:08:42 - INFO - __main__ - Step 88371: {'lr': 0.00018510730788994827, 'samples': 16967232, 'steps': 88370, 'loss/train': 1.443812370300293} 08/31/2021 05:08:42 - INFO - __main__ - Step 88372: {'lr': 0.00018510218305371783, 'samples': 16967424, 'steps': 88371, 'loss/train': 1.5418119430541992} 08/31/2021 05:08:42 - INFO - __main__ - Step 88373: {'lr': 0.0001850970582467294, 'samples': 16967616, 'steps': 88372, 'loss/train': 1.298216700553894} 08/31/2021 05:08:44 - INFO - __main__ - Step 88374: {'lr': 0.00018509193346898524, 'samples': 16967808, 'steps': 88373, 'loss/train': 0.8707524538040161} 08/31/2021 05:08:44 - INFO - __main__ - Step 88375: {'lr': 0.0001850868087204876, 'samples': 16968000, 'steps': 88374, 'loss/train': 1.4844026565551758} 08/31/2021 05:08:45 - INFO - __main__ - Step 88376: {'lr': 0.0001850816840012389, 'samples': 16968192, 'steps': 88375, 'loss/train': 1.142441987991333} 08/31/2021 05:08:45 - INFO - __main__ - Step 88377: {'lr': 0.00018507655931124145, 'samples': 16968384, 'steps': 88376, 'loss/train': 0.7149749398231506} 08/31/2021 05:08:45 - INFO - __main__ - Step 88378: {'lr': 0.00018507143465049746, 'samples': 16968576, 'steps': 88377, 'loss/train': 0.5841454863548279} 08/31/2021 05:08:47 - INFO - __main__ - Step 88379: {'lr': 0.0001850663100190092, 'samples': 16968768, 'steps': 88378, 'loss/train': 0.5147900581359863} 08/31/2021 05:08:48 - INFO - __main__ - Step 88380: {'lr': 0.00018506118541677913, 'samples': 16968960, 'steps': 88379, 'loss/train': 1.052036166191101} 08/31/2021 05:08:48 - INFO - __main__ - Step 88381: {'lr': 0.00018505606084380944, 'samples': 16969152, 'steps': 88380, 'loss/train': 1.0993318557739258} 08/31/2021 05:08:48 - INFO - __main__ - Step 88382: {'lr': 0.0001850509363001025, 'samples': 16969344, 'steps': 88381, 'loss/train': 0.07648106664419174} 08/31/2021 05:08:49 - INFO - __main__ - Step 88383: {'lr': 0.0001850458117856606, 'samples': 16969536, 'steps': 88382, 'loss/train': 1.4377542734146118} 08/31/2021 05:08:51 - INFO - __main__ - Step 88384: {'lr': 0.00018504068730048606, 'samples': 16969728, 'steps': 88383, 'loss/train': 1.0846848487854004} 08/31/2021 05:08:51 - INFO - __main__ - Step 88385: {'lr': 0.00018503556284458117, 'samples': 16969920, 'steps': 88384, 'loss/train': 0.8149740099906921} 08/31/2021 05:08:51 - INFO - __main__ - Step 88386: {'lr': 0.00018503043841794828, 'samples': 16970112, 'steps': 88385, 'loss/train': 0.8113385438919067} 08/31/2021 05:08:52 - INFO - __main__ - Step 88387: {'lr': 0.00018502531402058973, 'samples': 16970304, 'steps': 88386, 'loss/train': 1.2604775428771973} 08/31/2021 05:08:52 - INFO - __main__ - Step 88388: {'lr': 0.0001850201896525077, 'samples': 16970496, 'steps': 88387, 'loss/train': 1.4425629377365112} 08/31/2021 05:08:52 - INFO - __main__ - Step 88389: {'lr': 0.00018501506531370455, 'samples': 16970688, 'steps': 88388, 'loss/train': 1.5767724514007568} 08/31/2021 05:08:55 - INFO - __main__ - Step 88390: {'lr': 0.00018500994100418265, 'samples': 16970880, 'steps': 88389, 'loss/train': 1.1041072607040405} 08/31/2021 05:08:55 - INFO - __main__ - Step 88391: {'lr': 0.0001850048167239443, 'samples': 16971072, 'steps': 88390, 'loss/train': 1.5604394674301147} 08/31/2021 05:08:55 - INFO - __main__ - Step 88392: {'lr': 0.00018499969247299172, 'samples': 16971264, 'steps': 88391, 'loss/train': 1.2595877647399902} 08/31/2021 05:08:56 - INFO - __main__ - Step 88393: {'lr': 0.00018499456825132727, 'samples': 16971456, 'steps': 88392, 'loss/train': 0.7793040871620178} 08/31/2021 05:08:56 - INFO - __main__ - Step 88394: {'lr': 0.0001849894440589533, 'samples': 16971648, 'steps': 88393, 'loss/train': 1.36497962474823} 08/31/2021 05:08:57 - INFO - __main__ - Step 88395: {'lr': 0.00018498431989587204, 'samples': 16971840, 'steps': 88394, 'loss/train': 1.631459355354309} 08/31/2021 05:08:58 - INFO - __main__ - Step 88396: {'lr': 0.00018497919576208587, 'samples': 16972032, 'steps': 88395, 'loss/train': 1.5001020431518555} 08/31/2021 05:08:58 - INFO - __main__ - Step 88397: {'lr': 0.00018497407165759706, 'samples': 16972224, 'steps': 88396, 'loss/train': 0.8267704248428345} 08/31/2021 05:08:59 - INFO - __main__ - Step 88398: {'lr': 0.00018496894758240797, 'samples': 16972416, 'steps': 88397, 'loss/train': 1.3881579637527466} 08/31/2021 05:08:59 - INFO - __main__ - Step 88399: {'lr': 0.00018496382353652084, 'samples': 16972608, 'steps': 88398, 'loss/train': 1.3973644971847534} 08/31/2021 05:09:01 - INFO - __main__ - Step 88400: {'lr': 0.000184958699519938, 'samples': 16972800, 'steps': 88399, 'loss/train': 1.7439019680023193} 08/31/2021 05:09:01 - INFO - __main__ - Step 88401: {'lr': 0.00018495357553266177, 'samples': 16972992, 'steps': 88400, 'loss/train': 1.2042127847671509} 08/31/2021 05:09:01 - INFO - __main__ - Step 88402: {'lr': 0.00018494845157469443, 'samples': 16973184, 'steps': 88401, 'loss/train': 1.0164570808410645} 08/31/2021 05:09:02 - INFO - __main__ - Step 88403: {'lr': 0.00018494332764603833, 'samples': 16973376, 'steps': 88402, 'loss/train': 0.5805397033691406} 08/31/2021 05:09:02 - INFO - __main__ - Step 88404: {'lr': 0.00018493820374669584, 'samples': 16973568, 'steps': 88403, 'loss/train': 1.1492606401443481} 08/31/2021 05:09:03 - INFO - __main__ - Step 88405: {'lr': 0.0001849330798766691, 'samples': 16973760, 'steps': 88404, 'loss/train': 0.8899372816085815} 08/31/2021 05:09:04 - INFO - __main__ - Step 88406: {'lr': 0.0001849279560359605, 'samples': 16973952, 'steps': 88405, 'loss/train': 1.224069356918335} 08/31/2021 05:09:04 - INFO - __main__ - Step 88407: {'lr': 0.0001849228322245724, 'samples': 16974144, 'steps': 88406, 'loss/train': 1.5649101734161377} 08/31/2021 05:09:05 - INFO - __main__ - Step 88408: {'lr': 0.00018491770844250704, 'samples': 16974336, 'steps': 88407, 'loss/train': 1.0222123861312866} 08/31/2021 05:09:05 - INFO - __main__ - Step 88409: {'lr': 0.00018491258468976684, 'samples': 16974528, 'steps': 88408, 'loss/train': 0.9574568271636963} 08/31/2021 05:09:07 - INFO - __main__ - Step 88410: {'lr': 0.00018490746096635398, 'samples': 16974720, 'steps': 88409, 'loss/train': 1.3356484174728394} 08/31/2021 05:09:07 - INFO - __main__ - Step 88411: {'lr': 0.00018490233727227077, 'samples': 16974912, 'steps': 88410, 'loss/train': 1.3866418600082397} 08/31/2021 05:09:08 - INFO - __main__ - Step 88412: {'lr': 0.0001848972136075196, 'samples': 16975104, 'steps': 88411, 'loss/train': 1.3357402086257935} 08/31/2021 05:09:08 - INFO - __main__ - Step 88413: {'lr': 0.00018489208997210272, 'samples': 16975296, 'steps': 88412, 'loss/train': 1.5736267566680908} 08/31/2021 05:09:08 - INFO - __main__ - Step 88414: {'lr': 0.00018488696636602243, 'samples': 16975488, 'steps': 88413, 'loss/train': 1.3005069494247437} 08/31/2021 05:09:09 - INFO - __main__ - Step 88415: {'lr': 0.00018488184278928112, 'samples': 16975680, 'steps': 88414, 'loss/train': 1.2109806537628174} 08/31/2021 05:09:10 - INFO - __main__ - Step 88416: {'lr': 0.000184876719241881, 'samples': 16975872, 'steps': 88415, 'loss/train': 0.06252343952655792} 08/31/2021 05:09:11 - INFO - __main__ - Step 88417: {'lr': 0.00018487159572382446, 'samples': 16976064, 'steps': 88416, 'loss/train': 1.2255959510803223} 08/31/2021 05:09:11 - INFO - __main__ - Step 88418: {'lr': 0.00018486647223511383, 'samples': 16976256, 'steps': 88417, 'loss/train': 1.0797066688537598} 08/31/2021 05:09:11 - INFO - __main__ - Step 88419: {'lr': 0.00018486134877575129, 'samples': 16976448, 'steps': 88418, 'loss/train': 0.05420547351241112} 08/31/2021 05:09:12 - INFO - __main__ - Step 88420: {'lr': 0.00018485622534573928, 'samples': 16976640, 'steps': 88419, 'loss/train': 1.0238282680511475} 08/31/2021 05:09:13 - INFO - __main__ - Step 88421: {'lr': 0.00018485110194508002, 'samples': 16976832, 'steps': 88420, 'loss/train': 1.201305627822876} 08/31/2021 05:09:14 - INFO - __main__ - Step 88422: {'lr': 0.00018484597857377583, 'samples': 16977024, 'steps': 88421, 'loss/train': 1.5056160688400269} 08/31/2021 05:09:14 - INFO - __main__ - Step 88423: {'lr': 0.00018484085523182904, 'samples': 16977216, 'steps': 88422, 'loss/train': 1.0160574913024902} 08/31/2021 05:09:14 - INFO - __main__ - Step 88424: {'lr': 0.0001848357319192419, 'samples': 16977408, 'steps': 88423, 'loss/train': 1.1253914833068848} 08/31/2021 05:09:15 - INFO - __main__ - Step 88425: {'lr': 0.00018483060863601686, 'samples': 16977600, 'steps': 88424, 'loss/train': 1.1598858833312988} 08/31/2021 05:09:16 - INFO - __main__ - Step 88426: {'lr': 0.0001848254853821561, 'samples': 16977792, 'steps': 88425, 'loss/train': 1.046933889389038} 08/31/2021 05:09:17 - INFO - __main__ - Step 88427: {'lr': 0.00018482036215766197, 'samples': 16977984, 'steps': 88426, 'loss/train': 1.0228561162948608} 08/31/2021 05:09:17 - INFO - __main__ - Step 88428: {'lr': 0.00018481523896253678, 'samples': 16978176, 'steps': 88427, 'loss/train': 1.2412583827972412} 08/31/2021 05:09:17 - INFO - __main__ - Step 88429: {'lr': 0.00018481011579678288, 'samples': 16978368, 'steps': 88428, 'loss/train': 1.4697269201278687} 08/31/2021 05:09:18 - INFO - __main__ - Step 88430: {'lr': 0.00018480499266040247, 'samples': 16978560, 'steps': 88429, 'loss/train': 1.3231005668640137} 08/31/2021 05:09:20 - INFO - __main__ - Step 88431: {'lr': 0.00018479986955339807, 'samples': 16978752, 'steps': 88430, 'loss/train': 1.0329220294952393} 08/31/2021 05:09:20 - INFO - __main__ - Step 88432: {'lr': 0.00018479474647577172, 'samples': 16978944, 'steps': 88431, 'loss/train': 0.35474807024002075} 08/31/2021 05:09:20 - INFO - __main__ - Step 88433: {'lr': 0.00018478962342752584, 'samples': 16979136, 'steps': 88432, 'loss/train': 1.0469609498977661} 08/31/2021 05:09:21 - INFO - __main__ - Step 88434: {'lr': 0.00018478450040866276, 'samples': 16979328, 'steps': 88433, 'loss/train': 1.0733327865600586} 08/31/2021 05:09:21 - INFO - __main__ - Step 88435: {'lr': 0.00018477937741918476, 'samples': 16979520, 'steps': 88434, 'loss/train': 1.3999698162078857} 08/31/2021 05:09:23 - INFO - __main__ - Step 88436: {'lr': 0.00018477425445909422, 'samples': 16979712, 'steps': 88435, 'loss/train': 1.5799564123153687} 08/31/2021 05:09:23 - INFO - __main__ - Step 88437: {'lr': 0.00018476913152839337, 'samples': 16979904, 'steps': 88436, 'loss/train': 1.6858943700790405} 08/31/2021 05:09:23 - INFO - __main__ - Step 88438: {'lr': 0.00018476400862708453, 'samples': 16980096, 'steps': 88437, 'loss/train': 1.9752683639526367} 08/31/2021 05:09:24 - INFO - __main__ - Step 88439: {'lr': 0.00018475888575517004, 'samples': 16980288, 'steps': 88438, 'loss/train': 1.114585518836975} 08/31/2021 05:09:24 - INFO - __main__ - Step 88440: {'lr': 0.00018475376291265217, 'samples': 16980480, 'steps': 88439, 'loss/train': 1.0732306241989136} 08/31/2021 05:09:24 - INFO - __main__ - Step 88441: {'lr': 0.00018474864009953323, 'samples': 16980672, 'steps': 88440, 'loss/train': 1.3331080675125122} 08/31/2021 05:09:27 - INFO - __main__ - Step 88442: {'lr': 0.00018474351731581558, 'samples': 16980864, 'steps': 88441, 'loss/train': 0.9347245693206787} 08/31/2021 05:09:27 - INFO - __main__ - Step 88443: {'lr': 0.0001847383945615015, 'samples': 16981056, 'steps': 88442, 'loss/train': 1.3939768075942993} 08/31/2021 05:09:27 - INFO - __main__ - Step 88444: {'lr': 0.00018473327183659327, 'samples': 16981248, 'steps': 88443, 'loss/train': 1.2480735778808594} 08/31/2021 05:09:28 - INFO - __main__ - Step 88445: {'lr': 0.00018472814914109333, 'samples': 16981440, 'steps': 88444, 'loss/train': 1.615021824836731} 08/31/2021 05:09:28 - INFO - __main__ - Step 88446: {'lr': 0.00018472302647500378, 'samples': 16981632, 'steps': 88445, 'loss/train': 1.1873201131820679} 08/31/2021 05:09:29 - INFO - __main__ - Step 88447: {'lr': 0.000184717903838327, 'samples': 16981824, 'steps': 88446, 'loss/train': 1.0113033056259155} 08/31/2021 05:09:30 - INFO - __main__ - Step 88448: {'lr': 0.00018471278123106537, 'samples': 16982016, 'steps': 88447, 'loss/train': 1.767581820487976} 08/31/2021 05:09:30 - INFO - __main__ - Step 88449: {'lr': 0.00018470765865322112, 'samples': 16982208, 'steps': 88448, 'loss/train': 1.3266997337341309} 08/31/2021 05:09:31 - INFO - __main__ - Step 88450: {'lr': 0.0001847025361047966, 'samples': 16982400, 'steps': 88449, 'loss/train': 0.9366247057914734} 08/31/2021 05:09:31 - INFO - __main__ - Step 88451: {'lr': 0.0001846974135857941, 'samples': 16982592, 'steps': 88450, 'loss/train': 1.0380805730819702} 08/31/2021 05:09:33 - INFO - __main__ - Step 88452: {'lr': 0.00018469229109621595, 'samples': 16982784, 'steps': 88451, 'loss/train': 0.15946651995182037} 08/31/2021 05:09:33 - INFO - __main__ - Step 88453: {'lr': 0.00018468716863606445, 'samples': 16982976, 'steps': 88452, 'loss/train': 0.6560239791870117} 08/31/2021 05:09:34 - INFO - __main__ - Step 88454: {'lr': 0.0001846820462053419, 'samples': 16983168, 'steps': 88453, 'loss/train': 0.03035224787890911} 08/31/2021 05:09:34 - INFO - __main__ - Step 88455: {'lr': 0.0001846769238040506, 'samples': 16983360, 'steps': 88454, 'loss/train': 0.7679263353347778} 08/31/2021 05:09:34 - INFO - __main__ - Step 88456: {'lr': 0.00018467180143219293, 'samples': 16983552, 'steps': 88455, 'loss/train': 0.030824188143014908} 08/31/2021 05:09:36 - INFO - __main__ - Step 88457: {'lr': 0.00018466667908977107, 'samples': 16983744, 'steps': 88456, 'loss/train': 1.458554983139038} 08/31/2021 05:09:36 - INFO - __main__ - Step 88458: {'lr': 0.00018466155677678754, 'samples': 16983936, 'steps': 88457, 'loss/train': 1.5334845781326294} 08/31/2021 05:09:37 - INFO - __main__ - Step 88459: {'lr': 0.00018465643449324436, 'samples': 16984128, 'steps': 88458, 'loss/train': 0.7361019849777222} 08/31/2021 05:09:37 - INFO - __main__ - Step 88460: {'lr': 0.000184651312239144, 'samples': 16984320, 'steps': 88459, 'loss/train': 1.0134303569793701} 08/31/2021 05:09:37 - INFO - __main__ - Step 88461: {'lr': 0.00018464619001448874, 'samples': 16984512, 'steps': 88460, 'loss/train': 1.2001746892929077} 08/31/2021 05:09:39 - INFO - __main__ - Step 88462: {'lr': 0.0001846410678192809, 'samples': 16984704, 'steps': 88461, 'loss/train': 1.0929423570632935} 08/31/2021 05:09:39 - INFO - __main__ - Step 88463: {'lr': 0.00018463594565352282, 'samples': 16984896, 'steps': 88462, 'loss/train': 1.5399963855743408} 08/31/2021 05:09:40 - INFO - __main__ - Step 88464: {'lr': 0.00018463082351721677, 'samples': 16985088, 'steps': 88463, 'loss/train': 1.785410761833191} 08/31/2021 05:09:40 - INFO - __main__ - Step 88465: {'lr': 0.00018462570141036504, 'samples': 16985280, 'steps': 88464, 'loss/train': 1.5826283693313599} 08/31/2021 05:09:40 - INFO - __main__ - Step 88466: {'lr': 0.00018462057933296995, 'samples': 16985472, 'steps': 88465, 'loss/train': 1.4632939100265503} 08/31/2021 05:09:42 - INFO - __main__ - Step 88467: {'lr': 0.00018461545728503382, 'samples': 16985664, 'steps': 88466, 'loss/train': 0.9882969260215759} 08/31/2021 05:09:42 - INFO - __main__ - Step 88468: {'lr': 0.000184610335266559, 'samples': 16985856, 'steps': 88467, 'loss/train': 0.9967914819717407} 08/31/2021 05:09:43 - INFO - __main__ - Step 88469: {'lr': 0.0001846052132775477, 'samples': 16986048, 'steps': 88468, 'loss/train': 1.1021063327789307} 08/31/2021 05:09:43 - INFO - __main__ - Step 88470: {'lr': 0.00018460009131800233, 'samples': 16986240, 'steps': 88469, 'loss/train': 1.4069665670394897} 08/31/2021 05:09:43 - INFO - __main__ - Step 88471: {'lr': 0.0001845949693879251, 'samples': 16986432, 'steps': 88470, 'loss/train': 1.1997647285461426} 08/31/2021 05:09:45 - INFO - __main__ - Step 88472: {'lr': 0.0001845898474873185, 'samples': 16986624, 'steps': 88471, 'loss/train': 0.9919636249542236} 08/31/2021 05:09:45 - INFO - __main__ - Step 88473: {'lr': 0.0001845847256161846, 'samples': 16986816, 'steps': 88472, 'loss/train': 0.9809831380844116} 08/31/2021 05:09:45 - INFO - __main__ - Step 88474: {'lr': 0.00018457960377452583, 'samples': 16987008, 'steps': 88473, 'loss/train': 1.1802361011505127} 08/31/2021 05:09:46 - INFO - __main__ - Step 88475: {'lr': 0.00018457448196234445, 'samples': 16987200, 'steps': 88474, 'loss/train': 1.3822693824768066} 08/31/2021 05:09:46 - INFO - __main__ - Step 88476: {'lr': 0.00018456936017964283, 'samples': 16987392, 'steps': 88475, 'loss/train': 1.2390531301498413} 08/31/2021 05:09:47 - INFO - __main__ - Step 88477: {'lr': 0.0001845642384264232, 'samples': 16987584, 'steps': 88476, 'loss/train': 1.3567239046096802} 08/31/2021 05:09:48 - INFO - __main__ - Step 88478: {'lr': 0.00018455911670268792, 'samples': 16987776, 'steps': 88477, 'loss/train': 0.5181277990341187} 08/31/2021 05:09:48 - INFO - __main__ - Step 88479: {'lr': 0.00018455399500843934, 'samples': 16987968, 'steps': 88478, 'loss/train': 1.4249587059020996} 08/31/2021 05:09:49 - INFO - __main__ - Step 88480: {'lr': 0.0001845488733436797, 'samples': 16988160, 'steps': 88479, 'loss/train': 1.558497667312622} 08/31/2021 05:09:49 - INFO - __main__ - Step 88481: {'lr': 0.00018454375170841132, 'samples': 16988352, 'steps': 88480, 'loss/train': 1.1740609407424927} 08/31/2021 05:09:49 - INFO - __main__ - Step 88482: {'lr': 0.0001845386301026365, 'samples': 16988544, 'steps': 88481, 'loss/train': 0.787442684173584} 08/31/2021 05:09:51 - INFO - __main__ - Step 88483: {'lr': 0.0001845335085263576, 'samples': 16988736, 'steps': 88482, 'loss/train': 1.440207600593567} 08/31/2021 05:09:52 - INFO - __main__ - Step 88484: {'lr': 0.00018452838697957685, 'samples': 16988928, 'steps': 88483, 'loss/train': 1.303175449371338} 08/31/2021 05:09:52 - INFO - __main__ - Step 88485: {'lr': 0.00018452326546229673, 'samples': 16989120, 'steps': 88484, 'loss/train': 0.9707807898521423} 08/31/2021 05:09:52 - INFO - __main__ - Step 88486: {'lr': 0.0001845181439745193, 'samples': 16989312, 'steps': 88485, 'loss/train': 0.8221902847290039} 08/31/2021 05:09:53 - INFO - __main__ - Step 88487: {'lr': 0.000184513022516247, 'samples': 16989504, 'steps': 88486, 'loss/train': 0.05278918147087097} 08/31/2021 05:09:53 - INFO - __main__ - Step 88488: {'lr': 0.00018450790108748212, 'samples': 16989696, 'steps': 88487, 'loss/train': 0.023936506360769272} 08/31/2021 05:09:55 - INFO - __main__ - Step 88489: {'lr': 0.00018450277968822692, 'samples': 16989888, 'steps': 88488, 'loss/train': 1.1039884090423584} 08/31/2021 05:09:55 - INFO - __main__ - Step 88490: {'lr': 0.0001844976583184838, 'samples': 16990080, 'steps': 88489, 'loss/train': 1.0801209211349487} 08/31/2021 05:09:55 - INFO - __main__ - Step 88491: {'lr': 0.00018449253697825501, 'samples': 16990272, 'steps': 88490, 'loss/train': 1.2400416135787964} 08/31/2021 05:09:56 - INFO - __main__ - Step 88492: {'lr': 0.0001844874156675429, 'samples': 16990464, 'steps': 88491, 'loss/train': 1.022560715675354} 08/31/2021 05:09:56 - INFO - __main__ - Step 88493: {'lr': 0.00018448229438634974, 'samples': 16990656, 'steps': 88492, 'loss/train': 1.8070056438446045} 08/31/2021 05:09:58 - INFO - __main__ - Step 88494: {'lr': 0.00018447717313467785, 'samples': 16990848, 'steps': 88493, 'loss/train': 0.830556333065033} 08/31/2021 05:09:58 - INFO - __main__ - Step 88495: {'lr': 0.00018447205191252954, 'samples': 16991040, 'steps': 88494, 'loss/train': 0.029453566297888756} 08/31/2021 05:09:59 - INFO - __main__ - Step 88496: {'lr': 0.0001844669307199071, 'samples': 16991232, 'steps': 88495, 'loss/train': 1.3505839109420776} 08/31/2021 05:09:59 - INFO - __main__ - Step 88497: {'lr': 0.00018446180955681283, 'samples': 16991424, 'steps': 88496, 'loss/train': 0.3503618836402893} 08/31/2021 05:09:59 - INFO - __main__ - Step 88498: {'lr': 0.00018445668842324918, 'samples': 16991616, 'steps': 88497, 'loss/train': 1.4841657876968384} 08/31/2021 05:10:01 - INFO - __main__ - Step 88499: {'lr': 0.00018445156731921821, 'samples': 16991808, 'steps': 88498, 'loss/train': 1.3924857378005981} 08/31/2021 05:10:02 - INFO - __main__ - Step 88500: {'lr': 0.0001844464462447224, 'samples': 16992000, 'steps': 88499, 'loss/train': 1.1964099407196045} 08/31/2021 05:10:02 - INFO - __main__ - Step 88501: {'lr': 0.000184441325199764, 'samples': 16992192, 'steps': 88500, 'loss/train': 1.3394272327423096} 08/31/2021 05:10:02 - INFO - __main__ - Step 88502: {'lr': 0.00018443620418434525, 'samples': 16992384, 'steps': 88501, 'loss/train': 1.8147934675216675} 08/31/2021 05:10:03 - INFO - __main__ - Step 88503: {'lr': 0.00018443108319846863, 'samples': 16992576, 'steps': 88502, 'loss/train': 1.5253419876098633} 08/31/2021 05:10:04 - INFO - __main__ - Step 88504: {'lr': 0.0001844259622421363, 'samples': 16992768, 'steps': 88503, 'loss/train': 1.2761882543563843} 08/31/2021 05:10:05 - INFO - __main__ - Step 88505: {'lr': 0.00018442084131535064, 'samples': 16992960, 'steps': 88504, 'loss/train': 0.13467441499233246} 08/31/2021 05:10:05 - INFO - __main__ - Step 88506: {'lr': 0.00018441572041811395, 'samples': 16993152, 'steps': 88505, 'loss/train': 0.3304104804992676} 08/31/2021 05:10:06 - INFO - __main__ - Step 88507: {'lr': 0.0001844105995504285, 'samples': 16993344, 'steps': 88506, 'loss/train': 1.6636903285980225} 08/31/2021 05:10:06 - INFO - __main__ - Step 88508: {'lr': 0.00018440547871229662, 'samples': 16993536, 'steps': 88507, 'loss/train': 1.1031303405761719} 08/31/2021 05:10:07 - INFO - __main__ - Step 88509: {'lr': 0.0001844003579037206, 'samples': 16993728, 'steps': 88508, 'loss/train': 1.1743842363357544} 08/31/2021 05:10:08 - INFO - __main__ - Step 88510: {'lr': 0.0001843952371247028, 'samples': 16993920, 'steps': 88509, 'loss/train': 0.5016095042228699} 08/31/2021 05:10:08 - INFO - __main__ - Step 88511: {'lr': 0.00018439011637524556, 'samples': 16994112, 'steps': 88510, 'loss/train': 5.747910499572754} 08/31/2021 05:10:09 - INFO - __main__ - Step 88512: {'lr': 0.0001843849956553511, 'samples': 16994304, 'steps': 88511, 'loss/train': 1.4836455583572388} 08/31/2021 05:10:09 - INFO - __main__ - Step 88513: {'lr': 0.00018437987496502166, 'samples': 16994496, 'steps': 88512, 'loss/train': 0.5590672492980957} 08/31/2021 05:10:09 - INFO - __main__ - Step 88514: {'lr': 0.0001843747543042597, 'samples': 16994688, 'steps': 88513, 'loss/train': 1.3315138816833496} 08/31/2021 05:10:11 - INFO - __main__ - Step 88515: {'lr': 0.00018436963367306742, 'samples': 16994880, 'steps': 88514, 'loss/train': 1.3635984659194946} 08/31/2021 05:10:11 - INFO - __main__ - Step 88516: {'lr': 0.00018436451307144718, 'samples': 16995072, 'steps': 88515, 'loss/train': 1.4432820081710815} 08/31/2021 05:10:12 - INFO - __main__ - Step 88517: {'lr': 0.00018435939249940132, 'samples': 16995264, 'steps': 88516, 'loss/train': 0.5470353364944458} 08/31/2021 05:10:12 - INFO - __main__ - Step 88518: {'lr': 0.00018435427195693206, 'samples': 16995456, 'steps': 88517, 'loss/train': 1.1657967567443848} 08/31/2021 05:10:12 - INFO - __main__ - Step 88519: {'lr': 0.00018434915144404173, 'samples': 16995648, 'steps': 88518, 'loss/train': 0.9177528619766235} 08/31/2021 05:10:14 - INFO - __main__ - Step 88520: {'lr': 0.0001843440309607327, 'samples': 16995840, 'steps': 88519, 'loss/train': 1.0460717678070068} 08/31/2021 05:10:14 - INFO - __main__ - Step 88521: {'lr': 0.00018433891050700723, 'samples': 16996032, 'steps': 88520, 'loss/train': 1.0687742233276367} 08/31/2021 05:10:15 - INFO - __main__ - Step 88522: {'lr': 0.00018433379008286769, 'samples': 16996224, 'steps': 88521, 'loss/train': 1.0795326232910156} 08/31/2021 05:10:15 - INFO - __main__ - Step 88523: {'lr': 0.00018432866968831624, 'samples': 16996416, 'steps': 88522, 'loss/train': 1.6204817295074463} 08/31/2021 05:10:15 - INFO - __main__ - Step 88524: {'lr': 0.00018432354932335532, 'samples': 16996608, 'steps': 88523, 'loss/train': 1.139430046081543} 08/31/2021 05:10:17 - INFO - __main__ - Step 88525: {'lr': 0.00018431842898798724, 'samples': 16996800, 'steps': 88524, 'loss/train': 0.7232455015182495} 08/31/2021 05:10:17 - INFO - __main__ - Step 88526: {'lr': 0.00018431330868221422, 'samples': 16996992, 'steps': 88525, 'loss/train': 1.6883150339126587} 08/31/2021 05:10:18 - INFO - __main__ - Step 88527: {'lr': 0.00018430818840603857, 'samples': 16997184, 'steps': 88526, 'loss/train': 0.8817641735076904} 08/31/2021 05:10:18 - INFO - __main__ - Step 88528: {'lr': 0.0001843030681594627, 'samples': 16997376, 'steps': 88527, 'loss/train': 0.994479775428772} 08/31/2021 05:10:18 - INFO - __main__ - Step 88529: {'lr': 0.0001842979479424888, 'samples': 16997568, 'steps': 88528, 'loss/train': 1.3615597486495972} 08/31/2021 05:10:20 - INFO - __main__ - Step 88530: {'lr': 0.00018429282775511924, 'samples': 16997760, 'steps': 88529, 'loss/train': 1.8139458894729614} 08/31/2021 05:10:20 - INFO - __main__ - Step 88531: {'lr': 0.00018428770759735633, 'samples': 16997952, 'steps': 88530, 'loss/train': 1.0113734006881714} 08/31/2021 05:10:21 - INFO - __main__ - Step 88532: {'lr': 0.00018428258746920235, 'samples': 16998144, 'steps': 88531, 'loss/train': 1.6840393543243408} 08/31/2021 05:10:21 - INFO - __main__ - Step 88533: {'lr': 0.0001842774673706597, 'samples': 16998336, 'steps': 88532, 'loss/train': 1.383294939994812} 08/31/2021 05:10:21 - INFO - __main__ - Step 88534: {'lr': 0.00018427234730173053, 'samples': 16998528, 'steps': 88533, 'loss/train': 0.7426701188087463} 08/31/2021 05:10:22 - INFO - __main__ - Step 88535: {'lr': 0.00018426722726241725, 'samples': 16998720, 'steps': 88534, 'loss/train': 0.5047844648361206} 08/31/2021 05:10:23 - INFO - __main__ - Step 88536: {'lr': 0.00018426210725272214, 'samples': 16998912, 'steps': 88535, 'loss/train': 0.23071783781051636} 08/31/2021 05:10:24 - INFO - __main__ - Step 88537: {'lr': 0.00018425698727264747, 'samples': 16999104, 'steps': 88536, 'loss/train': 1.3747426271438599} 08/31/2021 05:10:24 - INFO - __main__ - Step 88538: {'lr': 0.0001842518673221956, 'samples': 16999296, 'steps': 88537, 'loss/train': 1.3794012069702148} 08/31/2021 05:10:24 - INFO - __main__ - Step 88539: {'lr': 0.00018424674740136893, 'samples': 16999488, 'steps': 88538, 'loss/train': 1.4384047985076904} 08/31/2021 05:10:25 - INFO - __main__ - Step 88540: {'lr': 0.00018424162751016953, 'samples': 16999680, 'steps': 88539, 'loss/train': 0.8452135920524597} 08/31/2021 05:10:26 - INFO - __main__ - Step 88541: {'lr': 0.0001842365076485999, 'samples': 16999872, 'steps': 88540, 'loss/train': 1.1783536672592163} 08/31/2021 05:10:27 - INFO - __main__ - Step 88542: {'lr': 0.00018423138781666225, 'samples': 17000064, 'steps': 88541, 'loss/train': 1.2527607679367065} 08/31/2021 05:10:27 - INFO - __main__ - Step 88543: {'lr': 0.00018422626801435895, 'samples': 17000256, 'steps': 88542, 'loss/train': 0.951884388923645} 08/31/2021 05:10:28 - INFO - __main__ - Step 88544: {'lr': 0.00018422114824169234, 'samples': 17000448, 'steps': 88543, 'loss/train': 1.5888258218765259} 08/31/2021 05:10:28 - INFO - __main__ - Step 88545: {'lr': 0.0001842160284986646, 'samples': 17000640, 'steps': 88544, 'loss/train': 1.2625601291656494} 08/31/2021 05:10:30 - INFO - __main__ - Step 88546: {'lr': 0.00018421090878527807, 'samples': 17000832, 'steps': 88545, 'loss/train': 1.8840885162353516} 08/31/2021 05:10:30 - INFO - __main__ - Step 88547: {'lr': 0.00018420578910153512, 'samples': 17001024, 'steps': 88546, 'loss/train': 0.6978611946105957} 08/31/2021 05:10:30 - INFO - __main__ - Step 88548: {'lr': 0.00018420066944743803, 'samples': 17001216, 'steps': 88547, 'loss/train': 1.3482561111450195} 08/31/2021 05:10:31 - INFO - __main__ - Step 88549: {'lr': 0.0001841955498229891, 'samples': 17001408, 'steps': 88548, 'loss/train': 1.5601917505264282} 08/31/2021 05:10:31 - INFO - __main__ - Step 88550: {'lr': 0.0001841904302281906, 'samples': 17001600, 'steps': 88549, 'loss/train': 1.4925028085708618} 08/31/2021 05:10:34 - INFO - __main__ - Step 88551: {'lr': 0.00018418531066304492, 'samples': 17001792, 'steps': 88550, 'loss/train': 1.274473786354065} 08/31/2021 05:10:34 - INFO - __main__ - Step 88552: {'lr': 0.00018418019112755436, 'samples': 17001984, 'steps': 88551, 'loss/train': 1.3369587659835815} 08/31/2021 05:10:34 - INFO - __main__ - Step 88553: {'lr': 0.00018417507162172116, 'samples': 17002176, 'steps': 88552, 'loss/train': 0.592883825302124} 08/31/2021 05:10:35 - INFO - __main__ - Step 88554: {'lr': 0.0001841699521455476, 'samples': 17002368, 'steps': 88553, 'loss/train': 0.9737109541893005} 08/31/2021 05:10:35 - INFO - __main__ - Step 88555: {'lr': 0.00018416483269903617, 'samples': 17002560, 'steps': 88554, 'loss/train': 1.4510995149612427} 08/31/2021 05:10:35 - INFO - __main__ - Step 88556: {'lr': 0.00018415971328218894, 'samples': 17002752, 'steps': 88555, 'loss/train': 0.4813094437122345} 08/31/2021 05:10:37 - INFO - __main__ - Step 88557: {'lr': 0.00018415459389500835, 'samples': 17002944, 'steps': 88556, 'loss/train': 1.5307340621948242} 08/31/2021 05:10:38 - INFO - __main__ - Step 88558: {'lr': 0.0001841494745374967, 'samples': 17003136, 'steps': 88557, 'loss/train': 1.9408742189407349} 08/31/2021 05:10:38 - INFO - __main__ - Step 88559: {'lr': 0.00018414435520965625, 'samples': 17003328, 'steps': 88558, 'loss/train': 1.2879501581192017} 08/31/2021 05:10:38 - INFO - __main__ - Step 88560: {'lr': 0.00018413923591148934, 'samples': 17003520, 'steps': 88559, 'loss/train': 1.0477714538574219} 08/31/2021 05:10:39 - INFO - __main__ - Step 88561: {'lr': 0.0001841341166429983, 'samples': 17003712, 'steps': 88560, 'loss/train': 0.9077060222625732} 08/31/2021 05:10:40 - INFO - __main__ - Step 88562: {'lr': 0.0001841289974041854, 'samples': 17003904, 'steps': 88561, 'loss/train': 0.7978463768959045} 08/31/2021 05:10:41 - INFO - __main__ - Step 88563: {'lr': 0.00018412387819505293, 'samples': 17004096, 'steps': 88562, 'loss/train': 1.3039851188659668} 08/31/2021 05:10:41 - INFO - __main__ - Step 88564: {'lr': 0.00018411875901560326, 'samples': 17004288, 'steps': 88563, 'loss/train': 0.9434150457382202} 08/31/2021 05:10:41 - INFO - __main__ - Step 88565: {'lr': 0.0001841136398658387, 'samples': 17004480, 'steps': 88564, 'loss/train': 0.8139641284942627} 08/31/2021 05:10:42 - INFO - __main__ - Step 88566: {'lr': 0.00018410852074576153, 'samples': 17004672, 'steps': 88565, 'loss/train': 1.7281750440597534} 08/31/2021 05:10:43 - INFO - __main__ - Step 88567: {'lr': 0.00018410340165537397, 'samples': 17004864, 'steps': 88566, 'loss/train': 1.0426379442214966} 08/31/2021 05:10:44 - INFO - __main__ - Step 88568: {'lr': 0.00018409828259467842, 'samples': 17005056, 'steps': 88567, 'loss/train': 0.1763869673013687} 08/31/2021 05:10:44 - INFO - __main__ - Step 88569: {'lr': 0.00018409316356367717, 'samples': 17005248, 'steps': 88568, 'loss/train': 0.8541689515113831} 08/31/2021 05:10:44 - INFO - __main__ - Step 88570: {'lr': 0.00018408804456237249, 'samples': 17005440, 'steps': 88569, 'loss/train': 1.1248691082000732} 08/31/2021 05:10:45 - INFO - __main__ - Step 88571: {'lr': 0.00018408292559076676, 'samples': 17005632, 'steps': 88570, 'loss/train': 1.4133564233779907} 08/31/2021 05:10:46 - INFO - __main__ - Step 88572: {'lr': 0.0001840778066488622, 'samples': 17005824, 'steps': 88571, 'loss/train': 0.9878440499305725} 08/31/2021 05:10:46 - INFO - __main__ - Step 88573: {'lr': 0.00018407268773666118, 'samples': 17006016, 'steps': 88572, 'loss/train': 1.2800980806350708} 08/31/2021 05:10:47 - INFO - __main__ - Step 88574: {'lr': 0.00018406756885416603, 'samples': 17006208, 'steps': 88573, 'loss/train': 1.1860392093658447} 08/31/2021 05:10:47 - INFO - __main__ - Step 88575: {'lr': 0.000184062450001379, 'samples': 17006400, 'steps': 88574, 'loss/train': 0.12000888586044312} 08/31/2021 05:10:48 - INFO - __main__ - Step 88576: {'lr': 0.00018405733117830237, 'samples': 17006592, 'steps': 88575, 'loss/train': 0.9703536629676819} 08/31/2021 05:10:48 - INFO - __main__ - Step 88577: {'lr': 0.00018405221238493853, 'samples': 17006784, 'steps': 88576, 'loss/train': 1.0233794450759888} 08/31/2021 05:10:49 - INFO - __main__ - Step 88578: {'lr': 0.00018404709362128974, 'samples': 17006976, 'steps': 88577, 'loss/train': 1.3986594676971436} 08/31/2021 05:10:50 - INFO - __main__ - Step 88579: {'lr': 0.00018404197488735842, 'samples': 17007168, 'steps': 88578, 'loss/train': 1.7030384540557861} 08/31/2021 05:10:50 - INFO - __main__ - Step 88580: {'lr': 0.00018403685618314665, 'samples': 17007360, 'steps': 88579, 'loss/train': 1.4855303764343262} 08/31/2021 05:10:51 - INFO - __main__ - Step 88581: {'lr': 0.00018403173750865685, 'samples': 17007552, 'steps': 88580, 'loss/train': 1.2210431098937988} 08/31/2021 05:10:51 - INFO - __main__ - Step 88582: {'lr': 0.00018402661886389132, 'samples': 17007744, 'steps': 88581, 'loss/train': 1.1203440427780151} 08/31/2021 05:10:52 - INFO - __main__ - Step 88583: {'lr': 0.00018402150024885238, 'samples': 17007936, 'steps': 88582, 'loss/train': 1.414815068244934} 08/31/2021 05:10:53 - INFO - __main__ - Step 88584: {'lr': 0.00018401638166354236, 'samples': 17008128, 'steps': 88583, 'loss/train': 0.9159174561500549} 08/31/2021 05:10:53 - INFO - __main__ - Step 88585: {'lr': 0.00018401126310796354, 'samples': 17008320, 'steps': 88584, 'loss/train': 1.3977020978927612} 08/31/2021 05:10:54 - INFO - __main__ - Step 88586: {'lr': 0.00018400614458211824, 'samples': 17008512, 'steps': 88585, 'loss/train': 0.17011979222297668} 08/31/2021 05:10:54 - INFO - __main__ - Step 88587: {'lr': 0.00018400102608600872, 'samples': 17008704, 'steps': 88586, 'loss/train': 1.207958459854126} 08/31/2021 05:10:56 - INFO - __main__ - Step 88588: {'lr': 0.0001839959076196373, 'samples': 17008896, 'steps': 88587, 'loss/train': 1.5541292428970337} 08/31/2021 05:10:56 - INFO - __main__ - Step 88589: {'lr': 0.00018399078918300636, 'samples': 17009088, 'steps': 88588, 'loss/train': 0.8931440711021423} 08/31/2021 05:10:56 - INFO - __main__ - Step 88590: {'lr': 0.00018398567077611812, 'samples': 17009280, 'steps': 88589, 'loss/train': 1.2446197271347046} 08/31/2021 05:10:57 - INFO - __main__ - Step 88591: {'lr': 0.00018398055239897493, 'samples': 17009472, 'steps': 88590, 'loss/train': 1.4380834102630615} 08/31/2021 05:10:57 - INFO - __main__ - Step 88592: {'lr': 0.00018397543405157906, 'samples': 17009664, 'steps': 88591, 'loss/train': 0.20174933969974518} 08/31/2021 05:10:58 - INFO - __main__ - Step 88593: {'lr': 0.00018397031573393296, 'samples': 17009856, 'steps': 88592, 'loss/train': 1.4412912130355835} 08/31/2021 05:10:59 - INFO - __main__ - Step 88594: {'lr': 0.00018396519744603873, 'samples': 17010048, 'steps': 88593, 'loss/train': 0.9320571422576904} 08/31/2021 05:10:59 - INFO - __main__ - Step 88595: {'lr': 0.00018396007918789875, 'samples': 17010240, 'steps': 88594, 'loss/train': 0.21061502397060394} 08/31/2021 05:11:00 - INFO - __main__ - Step 88596: {'lr': 0.00018395496095951537, 'samples': 17010432, 'steps': 88595, 'loss/train': 0.703516960144043} 08/31/2021 05:11:00 - INFO - __main__ - Step 88597: {'lr': 0.00018394984276089084, 'samples': 17010624, 'steps': 88596, 'loss/train': 1.536217451095581} 08/31/2021 05:11:02 - INFO - __main__ - Step 88598: {'lr': 0.00018394472459202742, 'samples': 17010816, 'steps': 88597, 'loss/train': 0.9452290534973145} 08/31/2021 05:11:03 - INFO - __main__ - Step 88599: {'lr': 0.0001839396064529276, 'samples': 17011008, 'steps': 88598, 'loss/train': 0.44475603103637695} 08/31/2021 05:11:03 - INFO - __main__ - Step 88600: {'lr': 0.0001839344883435935, 'samples': 17011200, 'steps': 88599, 'loss/train': 1.4110596179962158} 08/31/2021 05:11:04 - INFO - __main__ - Step 88601: {'lr': 0.00018392937026402758, 'samples': 17011392, 'steps': 88600, 'loss/train': 1.3603531122207642} 08/31/2021 05:11:04 - INFO - __main__ - Step 88602: {'lr': 0.00018392425221423197, 'samples': 17011584, 'steps': 88601, 'loss/train': 0.7186333537101746} 08/31/2021 05:11:04 - INFO - __main__ - Step 88603: {'lr': 0.00018391913419420913, 'samples': 17011776, 'steps': 88602, 'loss/train': 1.0132912397384644} 08/31/2021 05:11:05 - INFO - __main__ - Step 88604: {'lr': 0.00018391401620396127, 'samples': 17011968, 'steps': 88603, 'loss/train': 1.776883602142334} 08/31/2021 05:11:05 - INFO - __main__ - Step 88605: {'lr': 0.00018390889824349078, 'samples': 17012160, 'steps': 88604, 'loss/train': 1.7759977579116821} 08/31/2021 05:11:07 - INFO - __main__ - Step 88606: {'lr': 0.0001839037803128, 'samples': 17012352, 'steps': 88605, 'loss/train': 1.7766753435134888} 08/31/2021 05:11:08 - INFO - __main__ - Step 88607: {'lr': 0.00018389866241189107, 'samples': 17012544, 'steps': 88606, 'loss/train': 1.1851634979248047} 08/31/2021 05:11:08 - INFO - __main__ - Step 88608: {'lr': 0.00018389354454076634, 'samples': 17012736, 'steps': 88607, 'loss/train': 1.5916171073913574} 08/31/2021 05:11:08 - INFO - __main__ - Step 88609: {'lr': 0.0001838884266994282, 'samples': 17012928, 'steps': 88608, 'loss/train': 0.036570239812135696} 08/31/2021 05:11:09 - INFO - __main__ - Step 88610: {'lr': 0.0001838833088878789, 'samples': 17013120, 'steps': 88609, 'loss/train': 1.3393577337265015} 08/31/2021 05:11:11 - INFO - __main__ - Step 88611: {'lr': 0.00018387819110612076, 'samples': 17013312, 'steps': 88610, 'loss/train': 0.03801896050572395} 08/31/2021 05:11:11 - INFO - __main__ - Step 88612: {'lr': 0.0001838730733541561, 'samples': 17013504, 'steps': 88611, 'loss/train': 1.0952180624008179} 08/31/2021 05:11:11 - INFO - __main__ - Step 88613: {'lr': 0.00018386795563198722, 'samples': 17013696, 'steps': 88612, 'loss/train': 1.1908047199249268} 08/31/2021 05:11:12 - INFO - __main__ - Step 88614: {'lr': 0.0001838628379396164, 'samples': 17013888, 'steps': 88613, 'loss/train': 0.6808992028236389} 08/31/2021 05:11:12 - INFO - __main__ - Step 88615: {'lr': 0.00018385772027704596, 'samples': 17014080, 'steps': 88614, 'loss/train': 0.028949450701475143} 08/31/2021 05:11:13 - INFO - __main__ - Step 88616: {'lr': 0.00018385260264427823, 'samples': 17014272, 'steps': 88615, 'loss/train': 0.9524254202842712} 08/31/2021 05:11:14 - INFO - __main__ - Step 88617: {'lr': 0.00018384748504131547, 'samples': 17014464, 'steps': 88616, 'loss/train': 1.1702055931091309} 08/31/2021 05:11:14 - INFO - __main__ - Step 88618: {'lr': 0.00018384236746816002, 'samples': 17014656, 'steps': 88617, 'loss/train': 1.5753962993621826} 08/31/2021 05:11:15 - INFO - __main__ - Step 88619: {'lr': 0.0001838372499248143, 'samples': 17014848, 'steps': 88618, 'loss/train': 1.4574940204620361} 08/31/2021 05:11:15 - INFO - __main__ - Step 88620: {'lr': 0.00018383213241128038, 'samples': 17015040, 'steps': 88619, 'loss/train': 0.948091983795166} 08/31/2021 05:11:15 - INFO - __main__ - Step 88621: {'lr': 0.00018382701492756067, 'samples': 17015232, 'steps': 88620, 'loss/train': 1.2659105062484741} 08/31/2021 05:11:17 - INFO - __main__ - Step 88622: {'lr': 0.00018382189747365748, 'samples': 17015424, 'steps': 88621, 'loss/train': 1.5302538871765137} 08/31/2021 05:11:18 - INFO - __main__ - Step 88623: {'lr': 0.00018381678004957314, 'samples': 17015616, 'steps': 88622, 'loss/train': 1.2931663990020752} 08/31/2021 05:11:18 - INFO - __main__ - Step 88624: {'lr': 0.00018381166265530994, 'samples': 17015808, 'steps': 88623, 'loss/train': 0.9078379273414612} 08/31/2021 05:11:18 - INFO - __main__ - Step 88625: {'lr': 0.0001838065452908702, 'samples': 17016000, 'steps': 88624, 'loss/train': 1.6952170133590698} 08/31/2021 05:11:19 - INFO - __main__ - Step 88626: {'lr': 0.00018380142795625616, 'samples': 17016192, 'steps': 88625, 'loss/train': 0.7308538556098938} 08/31/2021 05:11:20 - INFO - __main__ - Step 88627: {'lr': 0.00018379631065147022, 'samples': 17016384, 'steps': 88626, 'loss/train': 0.9926562905311584} 08/31/2021 05:11:21 - INFO - __main__ - Step 88628: {'lr': 0.00018379119337651463, 'samples': 17016576, 'steps': 88627, 'loss/train': 3.961655378341675} 08/31/2021 05:11:21 - INFO - __main__ - Step 88629: {'lr': 0.00018378607613139168, 'samples': 17016768, 'steps': 88628, 'loss/train': 0.5028245449066162} 08/31/2021 05:11:21 - INFO - __main__ - Step 88630: {'lr': 0.00018378095891610373, 'samples': 17016960, 'steps': 88629, 'loss/train': 0.2882001996040344} 08/31/2021 05:11:22 - INFO - __main__ - Step 88631: {'lr': 0.00018377584173065304, 'samples': 17017152, 'steps': 88630, 'loss/train': 0.7351564168930054} 08/31/2021 05:11:22 - INFO - __main__ - Step 88632: {'lr': 0.00018377072457504196, 'samples': 17017344, 'steps': 88631, 'loss/train': 1.371459722518921} 08/31/2021 05:11:23 - INFO - __main__ - Step 88633: {'lr': 0.00018376560744927283, 'samples': 17017536, 'steps': 88632, 'loss/train': 1.4769607782363892} 08/31/2021 05:11:24 - INFO - __main__ - Step 88634: {'lr': 0.0001837604903533478, 'samples': 17017728, 'steps': 88633, 'loss/train': 2.1274681091308594} 08/31/2021 05:11:24 - INFO - __main__ - Step 88635: {'lr': 0.00018375537328726933, 'samples': 17017920, 'steps': 88634, 'loss/train': 0.679259181022644} 08/31/2021 05:11:25 - INFO - __main__ - Step 88636: {'lr': 0.00018375025625103961, 'samples': 17018112, 'steps': 88635, 'loss/train': 1.0885552167892456} 08/31/2021 05:11:25 - INFO - __main__ - Step 88637: {'lr': 0.00018374513924466102, 'samples': 17018304, 'steps': 88636, 'loss/train': 1.0679255723953247} 08/31/2021 05:11:27 - INFO - __main__ - Step 88638: {'lr': 0.00018374002226813585, 'samples': 17018496, 'steps': 88637, 'loss/train': 1.1275324821472168} 08/31/2021 05:11:27 - INFO - __main__ - Step 88639: {'lr': 0.00018373490532146638, 'samples': 17018688, 'steps': 88638, 'loss/train': 0.7457171678543091} 08/31/2021 05:11:27 - INFO - __main__ - Step 88640: {'lr': 0.00018372978840465497, 'samples': 17018880, 'steps': 88639, 'loss/train': 1.0046732425689697} 08/31/2021 05:11:28 - INFO - __main__ - Step 88641: {'lr': 0.0001837246715177039, 'samples': 17019072, 'steps': 88640, 'loss/train': 1.3394476175308228} 08/31/2021 05:11:28 - INFO - __main__ - Step 88642: {'lr': 0.00018371955466061545, 'samples': 17019264, 'steps': 88641, 'loss/train': 0.9450643062591553} 08/31/2021 05:11:30 - INFO - __main__ - Step 88643: {'lr': 0.00018371443783339193, 'samples': 17019456, 'steps': 88642, 'loss/train': 1.4529362916946411} 08/31/2021 05:11:30 - INFO - __main__ - Step 88644: {'lr': 0.0001837093210360357, 'samples': 17019648, 'steps': 88643, 'loss/train': 0.9919413924217224} 08/31/2021 05:11:30 - INFO - __main__ - Step 88645: {'lr': 0.00018370420426854904, 'samples': 17019840, 'steps': 88644, 'loss/train': 1.1509909629821777} 08/31/2021 05:11:31 - INFO - __main__ - Step 88646: {'lr': 0.00018369908753093427, 'samples': 17020032, 'steps': 88645, 'loss/train': 1.4468063116073608} 08/31/2021 05:11:31 - INFO - __main__ - Step 88647: {'lr': 0.0001836939708231936, 'samples': 17020224, 'steps': 88646, 'loss/train': 1.086378574371338} 08/31/2021 05:11:33 - INFO - __main__ - Step 88648: {'lr': 0.00018368885414532944, 'samples': 17020416, 'steps': 88647, 'loss/train': 1.2136445045471191} 08/31/2021 05:11:33 - INFO - __main__ - Step 88649: {'lr': 0.000183683737497344, 'samples': 17020608, 'steps': 88648, 'loss/train': 1.320515513420105} 08/31/2021 05:11:33 - INFO - __main__ - Step 88650: {'lr': 0.0001836786208792397, 'samples': 17020800, 'steps': 88649, 'loss/train': 0.6902278065681458} 08/31/2021 05:11:34 - INFO - __main__ - Step 88651: {'lr': 0.00018367350429101875, 'samples': 17020992, 'steps': 88650, 'loss/train': 1.0329716205596924} 08/31/2021 05:11:34 - INFO - __main__ - Step 88652: {'lr': 0.00018366838773268353, 'samples': 17021184, 'steps': 88651, 'loss/train': 0.7761998772621155} 08/31/2021 05:11:34 - INFO - __main__ - Step 88653: {'lr': 0.00018366327120423627, 'samples': 17021376, 'steps': 88652, 'loss/train': 1.3178311586380005} 08/31/2021 05:11:36 - INFO - __main__ - Step 88654: {'lr': 0.00018365815470567935, 'samples': 17021568, 'steps': 88653, 'loss/train': 1.3228421211242676} 08/31/2021 05:11:37 - INFO - __main__ - Step 88655: {'lr': 0.00018365303823701502, 'samples': 17021760, 'steps': 88654, 'loss/train': 1.0064901113510132} 08/31/2021 05:11:37 - INFO - __main__ - Step 88656: {'lr': 0.0001836479217982457, 'samples': 17021952, 'steps': 88655, 'loss/train': 0.40461552143096924} 08/31/2021 05:11:37 - INFO - __main__ - Step 88657: {'lr': 0.0001836428053893735, 'samples': 17022144, 'steps': 88656, 'loss/train': 0.9480193853378296} 08/31/2021 05:11:38 - INFO - __main__ - Step 88658: {'lr': 0.00018363768901040085, 'samples': 17022336, 'steps': 88657, 'loss/train': 1.2064270973205566} 08/31/2021 05:11:40 - INFO - __main__ - Step 88659: {'lr': 0.00018363257266133004, 'samples': 17022528, 'steps': 88658, 'loss/train': 1.1708998680114746} 08/31/2021 05:11:40 - INFO - __main__ - Step 88660: {'lr': 0.00018362745634216337, 'samples': 17022720, 'steps': 88659, 'loss/train': 1.6339683532714844} 08/31/2021 05:11:41 - INFO - __main__ - Step 88661: {'lr': 0.0001836223400529032, 'samples': 17022912, 'steps': 88660, 'loss/train': 0.5662149786949158} 08/31/2021 05:11:41 - INFO - __main__ - Step 88662: {'lr': 0.00018361722379355166, 'samples': 17023104, 'steps': 88661, 'loss/train': 0.7769138813018799} 08/31/2021 05:11:41 - INFO - __main__ - Step 88663: {'lr': 0.00018361210756411123, 'samples': 17023296, 'steps': 88662, 'loss/train': 1.26990807056427} 08/31/2021 05:11:43 - INFO - __main__ - Step 88664: {'lr': 0.00018360699136458418, 'samples': 17023488, 'steps': 88663, 'loss/train': 1.012699842453003} 08/31/2021 05:11:43 - INFO - __main__ - Step 88665: {'lr': 0.00018360187519497276, 'samples': 17023680, 'steps': 88664, 'loss/train': 0.9249206185340881} 08/31/2021 05:11:44 - INFO - __main__ - Step 88666: {'lr': 0.00018359675905527933, 'samples': 17023872, 'steps': 88665, 'loss/train': 1.5264960527420044} 08/31/2021 05:11:44 - INFO - __main__ - Step 88667: {'lr': 0.00018359164294550623, 'samples': 17024064, 'steps': 88666, 'loss/train': 1.8968788385391235} 08/31/2021 05:11:44 - INFO - __main__ - Step 88668: {'lr': 0.00018358652686565564, 'samples': 17024256, 'steps': 88667, 'loss/train': 1.1025351285934448} 08/31/2021 05:11:46 - INFO - __main__ - Step 88669: {'lr': 0.00018358141081572992, 'samples': 17024448, 'steps': 88668, 'loss/train': 0.9356406927108765} 08/31/2021 05:11:47 - INFO - __main__ - Step 88670: {'lr': 0.00018357629479573146, 'samples': 17024640, 'steps': 88669, 'loss/train': 1.3198285102844238} 08/31/2021 05:11:47 - INFO - __main__ - Step 88671: {'lr': 0.00018357117880566244, 'samples': 17024832, 'steps': 88670, 'loss/train': 0.7098138332366943} 08/31/2021 05:11:47 - INFO - __main__ - Step 88672: {'lr': 0.00018356606284552525, 'samples': 17025024, 'steps': 88671, 'loss/train': 1.059743046760559} 08/31/2021 05:11:48 - INFO - __main__ - Step 88673: {'lr': 0.00018356094691532218, 'samples': 17025216, 'steps': 88672, 'loss/train': 0.053958792239427567} 08/31/2021 05:11:49 - INFO - __main__ - Step 88674: {'lr': 0.00018355583101505553, 'samples': 17025408, 'steps': 88673, 'loss/train': 0.0940098837018013} 08/31/2021 05:11:50 - INFO - __main__ - Step 88675: {'lr': 0.00018355071514472755, 'samples': 17025600, 'steps': 88674, 'loss/train': 1.3134472370147705} 08/31/2021 05:11:50 - INFO - __main__ - Step 88676: {'lr': 0.00018354559930434057, 'samples': 17025792, 'steps': 88675, 'loss/train': 1.374699592590332} 08/31/2021 05:11:50 - INFO - __main__ - Step 88677: {'lr': 0.00018354048349389696, 'samples': 17025984, 'steps': 88676, 'loss/train': 1.7821083068847656} 08/31/2021 05:11:51 - INFO - __main__ - Step 88678: {'lr': 0.00018353536771339903, 'samples': 17026176, 'steps': 88677, 'loss/train': 1.6006748676300049} 08/31/2021 05:11:52 - INFO - __main__ - Step 88679: {'lr': 0.000183530251962849, 'samples': 17026368, 'steps': 88678, 'loss/train': 0.9403285980224609} 08/31/2021 05:11:53 - INFO - __main__ - Step 88680: {'lr': 0.0001835251362422492, 'samples': 17026560, 'steps': 88679, 'loss/train': 1.499391794204712} 08/31/2021 05:11:53 - INFO - __main__ - Step 88681: {'lr': 0.00018352002055160193, 'samples': 17026752, 'steps': 88680, 'loss/train': 1.153347373008728} 08/31/2021 05:11:53 - INFO - __main__ - Step 88682: {'lr': 0.00018351490489090954, 'samples': 17026944, 'steps': 88681, 'loss/train': 0.7515097260475159} 08/31/2021 05:11:54 - INFO - __main__ - Step 88683: {'lr': 0.00018350978926017427, 'samples': 17027136, 'steps': 88682, 'loss/train': 0.9223098158836365} 08/31/2021 05:11:54 - INFO - __main__ - Step 88684: {'lr': 0.0001835046736593985, 'samples': 17027328, 'steps': 88683, 'loss/train': 0.11647850275039673} 08/31/2021 05:11:56 - INFO - __main__ - Step 88685: {'lr': 0.0001834995580885845, 'samples': 17027520, 'steps': 88684, 'loss/train': 1.1261593103408813} 08/31/2021 05:11:56 - INFO - __main__ - Step 88686: {'lr': 0.00018349444254773454, 'samples': 17027712, 'steps': 88685, 'loss/train': 0.9633519649505615} 08/31/2021 05:11:56 - INFO - __main__ - Step 88687: {'lr': 0.000183489327036851, 'samples': 17027904, 'steps': 88686, 'loss/train': 0.8210461139678955} 08/31/2021 05:11:57 - INFO - __main__ - Step 88688: {'lr': 0.00018348421155593613, 'samples': 17028096, 'steps': 88687, 'loss/train': 1.434948444366455} 08/31/2021 05:11:57 - INFO - __main__ - Step 88689: {'lr': 0.0001834790961049923, 'samples': 17028288, 'steps': 88688, 'loss/train': 1.1999280452728271} 08/31/2021 05:11:59 - INFO - __main__ - Step 88690: {'lr': 0.00018347398068402172, 'samples': 17028480, 'steps': 88689, 'loss/train': 1.042475938796997} 08/31/2021 05:11:59 - INFO - __main__ - Step 88691: {'lr': 0.0001834688652930267, 'samples': 17028672, 'steps': 88690, 'loss/train': 1.4108940362930298} 08/31/2021 05:11:59 - INFO - __main__ - Step 88692: {'lr': 0.0001834637499320096, 'samples': 17028864, 'steps': 88691, 'loss/train': 1.0326132774353027} 08/31/2021 05:12:00 - INFO - __main__ - Step 88693: {'lr': 0.00018345863460097271, 'samples': 17029056, 'steps': 88692, 'loss/train': 1.3493512868881226} 08/31/2021 05:12:00 - INFO - __main__ - Step 88694: {'lr': 0.0001834535192999183, 'samples': 17029248, 'steps': 88693, 'loss/train': 1.361793041229248} 08/31/2021 05:12:02 - INFO - __main__ - Step 88695: {'lr': 0.00018344840402884877, 'samples': 17029440, 'steps': 88694, 'loss/train': 0.5984891653060913} 08/31/2021 05:12:02 - INFO - __main__ - Step 88696: {'lr': 0.00018344328878776634, 'samples': 17029632, 'steps': 88695, 'loss/train': 1.2167826890945435} 08/31/2021 05:12:03 - INFO - __main__ - Step 88697: {'lr': 0.0001834381735766733, 'samples': 17029824, 'steps': 88696, 'loss/train': 0.6950976848602295} 08/31/2021 05:12:03 - INFO - __main__ - Step 88698: {'lr': 0.000183433058395572, 'samples': 17030016, 'steps': 88697, 'loss/train': 1.4269442558288574} 08/31/2021 05:12:03 - INFO - __main__ - Step 88699: {'lr': 0.00018342794324446477, 'samples': 17030208, 'steps': 88698, 'loss/train': 0.03604958578944206} 08/31/2021 05:12:05 - INFO - __main__ - Step 88700: {'lr': 0.00018342282812335397, 'samples': 17030400, 'steps': 88699, 'loss/train': 0.5912666916847229} 08/31/2021 05:12:05 - INFO - __main__ - Step 88701: {'lr': 0.0001834177130322417, 'samples': 17030592, 'steps': 88700, 'loss/train': 1.140114665031433} 08/31/2021 05:12:05 - INFO - __main__ - Step 88702: {'lr': 0.00018341259797113041, 'samples': 17030784, 'steps': 88701, 'loss/train': 1.2006319761276245} 08/31/2021 05:12:06 - INFO - __main__ - Step 88703: {'lr': 0.00018340748294002235, 'samples': 17030976, 'steps': 88702, 'loss/train': 1.4101758003234863} 08/31/2021 05:12:06 - INFO - __main__ - Step 88704: {'lr': 0.00018340236793891988, 'samples': 17031168, 'steps': 88703, 'loss/train': 1.1551941633224487} 08/31/2021 05:12:08 - INFO - __main__ - Step 88705: {'lr': 0.00018339725296782526, 'samples': 17031360, 'steps': 88704, 'loss/train': 0.7739184498786926} 08/31/2021 05:12:08 - INFO - __main__ - Step 88706: {'lr': 0.00018339213802674083, 'samples': 17031552, 'steps': 88705, 'loss/train': 1.079188346862793} 08/31/2021 05:12:09 - INFO - __main__ - Step 88707: {'lr': 0.00018338702311566883, 'samples': 17031744, 'steps': 88706, 'loss/train': 0.016990438103675842} 08/31/2021 05:12:09 - INFO - __main__ - Step 88708: {'lr': 0.00018338190823461163, 'samples': 17031936, 'steps': 88707, 'loss/train': 1.2033876180648804} 08/31/2021 05:12:10 - INFO - __main__ - Step 88709: {'lr': 0.0001833767933835715, 'samples': 17032128, 'steps': 88708, 'loss/train': 1.0251729488372803} 08/31/2021 05:12:10 - INFO - __main__ - Step 88710: {'lr': 0.00018337167856255076, 'samples': 17032320, 'steps': 88709, 'loss/train': 1.255963921546936} 08/31/2021 05:12:11 - INFO - __main__ - Step 88711: {'lr': 0.00018336656377155176, 'samples': 17032512, 'steps': 88710, 'loss/train': 1.5524324178695679} 08/31/2021 05:12:12 - INFO - __main__ - Step 88712: {'lr': 0.0001833614490105767, 'samples': 17032704, 'steps': 88711, 'loss/train': 0.985800564289093} 08/31/2021 05:12:12 - INFO - __main__ - Step 88713: {'lr': 0.00018335633427962798, 'samples': 17032896, 'steps': 88712, 'loss/train': 1.1493085622787476} 08/31/2021 05:12:13 - INFO - __main__ - Step 88714: {'lr': 0.00018335121957870795, 'samples': 17033088, 'steps': 88713, 'loss/train': 1.1616637706756592} 08/31/2021 05:12:13 - INFO - __main__ - Step 88715: {'lr': 0.00018334610490781874, 'samples': 17033280, 'steps': 88714, 'loss/train': 0.950549304485321} 08/31/2021 05:12:15 - INFO - __main__ - Step 88716: {'lr': 0.00018334099026696274, 'samples': 17033472, 'steps': 88715, 'loss/train': 1.0823752880096436} 08/31/2021 05:12:15 - INFO - __main__ - Step 88717: {'lr': 0.00018333587565614226, 'samples': 17033664, 'steps': 88716, 'loss/train': 1.0074106454849243} 08/31/2021 05:12:16 - INFO - __main__ - Step 88718: {'lr': 0.00018333076107535963, 'samples': 17033856, 'steps': 88717, 'loss/train': 1.3976577520370483} 08/31/2021 05:12:16 - INFO - __main__ - Step 88719: {'lr': 0.0001833256465246171, 'samples': 17034048, 'steps': 88718, 'loss/train': 1.0645055770874023} 08/31/2021 05:12:16 - INFO - __main__ - Step 88720: {'lr': 0.00018332053200391702, 'samples': 17034240, 'steps': 88719, 'loss/train': 1.3333024978637695} 08/31/2021 05:12:17 - INFO - __main__ - Step 88721: {'lr': 0.00018331541751326168, 'samples': 17034432, 'steps': 88720, 'loss/train': 1.000659465789795} 08/31/2021 05:12:18 - INFO - __main__ - Step 88722: {'lr': 0.00018331030305265337, 'samples': 17034624, 'steps': 88721, 'loss/train': 0.3623213469982147} 08/31/2021 05:12:19 - INFO - __main__ - Step 88723: {'lr': 0.0001833051886220944, 'samples': 17034816, 'steps': 88722, 'loss/train': 1.3844980001449585} 08/31/2021 05:12:19 - INFO - __main__ - Step 88724: {'lr': 0.0001833000742215871, 'samples': 17035008, 'steps': 88723, 'loss/train': 1.353659987449646} 08/31/2021 05:12:19 - INFO - __main__ - Step 88725: {'lr': 0.00018329495985113377, 'samples': 17035200, 'steps': 88724, 'loss/train': 0.482361763715744} 08/31/2021 05:12:20 - INFO - __main__ - Step 88726: {'lr': 0.00018328984551073667, 'samples': 17035392, 'steps': 88725, 'loss/train': 1.746354341506958} 08/31/2021 05:12:21 - INFO - __main__ - Step 88727: {'lr': 0.0001832847312003983, 'samples': 17035584, 'steps': 88726, 'loss/train': 1.3847603797912598} 08/31/2021 05:12:22 - INFO - __main__ - Step 88728: {'lr': 0.00018327961692012062, 'samples': 17035776, 'steps': 88727, 'loss/train': 1.1674362421035767} 08/31/2021 05:12:22 - INFO - __main__ - Step 88729: {'lr': 0.00018327450266990617, 'samples': 17035968, 'steps': 88728, 'loss/train': 1.0538520812988281} 08/31/2021 05:12:22 - INFO - __main__ - Step 88730: {'lr': 0.00018326938844975715, 'samples': 17036160, 'steps': 88729, 'loss/train': 1.0455403327941895} 08/31/2021 05:12:23 - INFO - __main__ - Step 88731: {'lr': 0.00018326427425967596, 'samples': 17036352, 'steps': 88730, 'loss/train': 0.5140112042427063} 08/31/2021 05:12:25 - INFO - __main__ - Step 88732: {'lr': 0.00018325916009966488, 'samples': 17036544, 'steps': 88731, 'loss/train': 1.041869878768921} 08/31/2021 05:12:25 - INFO - __main__ - Step 88733: {'lr': 0.00018325404596972612, 'samples': 17036736, 'steps': 88732, 'loss/train': 1.1368424892425537} 08/31/2021 05:12:25 - INFO - __main__ - Step 88734: {'lr': 0.00018324893186986207, 'samples': 17036928, 'steps': 88733, 'loss/train': 1.4836424589157104} 08/31/2021 05:12:26 - INFO - __main__ - Step 88735: {'lr': 0.00018324381780007506, 'samples': 17037120, 'steps': 88734, 'loss/train': 0.9922913908958435} 08/31/2021 05:12:26 - INFO - __main__ - Step 88736: {'lr': 0.00018323870376036732, 'samples': 17037312, 'steps': 88735, 'loss/train': 0.027341218665242195} 08/31/2021 05:12:26 - INFO - __main__ - Step 88737: {'lr': 0.00018323358975074123, 'samples': 17037504, 'steps': 88736, 'loss/train': 0.018382852897047997} 08/31/2021 05:12:28 - INFO - __main__ - Step 88738: {'lr': 0.00018322847577119906, 'samples': 17037696, 'steps': 88737, 'loss/train': 0.7256503105163574} 08/31/2021 05:12:28 - INFO - __main__ - Step 88739: {'lr': 0.00018322336182174308, 'samples': 17037888, 'steps': 88738, 'loss/train': 0.7556273341178894} 08/31/2021 05:12:29 - INFO - __main__ - Step 88740: {'lr': 0.0001832182479023757, 'samples': 17038080, 'steps': 88739, 'loss/train': 0.5093262791633606} 08/31/2021 05:12:29 - INFO - __main__ - Step 88741: {'lr': 0.0001832131340130991, 'samples': 17038272, 'steps': 88740, 'loss/train': 0.7961485981941223} 08/31/2021 05:12:29 - INFO - __main__ - Step 88742: {'lr': 0.0001832080201539156, 'samples': 17038464, 'steps': 88741, 'loss/train': 1.4977715015411377} 08/31/2021 05:12:31 - INFO - __main__ - Step 88743: {'lr': 0.00018320290632482754, 'samples': 17038656, 'steps': 88742, 'loss/train': 0.1745625138282776} 08/31/2021 05:12:32 - INFO - __main__ - Step 88744: {'lr': 0.00018319779252583718, 'samples': 17038848, 'steps': 88743, 'loss/train': 1.9524333477020264} 08/31/2021 05:12:32 - INFO - __main__ - Step 88745: {'lr': 0.00018319267875694693, 'samples': 17039040, 'steps': 88744, 'loss/train': 1.0941238403320312} 08/31/2021 05:12:32 - INFO - __main__ - Step 88746: {'lr': 0.00018318756501815896, 'samples': 17039232, 'steps': 88745, 'loss/train': 0.8680212497711182} 08/31/2021 05:12:33 - INFO - __main__ - Step 88747: {'lr': 0.0001831824513094757, 'samples': 17039424, 'steps': 88746, 'loss/train': 0.7350479364395142} 08/31/2021 05:12:33 - INFO - __main__ - Step 88748: {'lr': 0.0001831773376308994, 'samples': 17039616, 'steps': 88747, 'loss/train': 1.1763572692871094} 08/31/2021 05:12:34 - INFO - __main__ - Step 88749: {'lr': 0.00018317222398243232, 'samples': 17039808, 'steps': 88748, 'loss/train': 0.032784853130578995} 08/31/2021 05:12:35 - INFO - __main__ - Step 88750: {'lr': 0.00018316711036407685, 'samples': 17040000, 'steps': 88749, 'loss/train': 1.1325496435165405} 08/31/2021 05:12:35 - INFO - __main__ - Step 88751: {'lr': 0.0001831619967758352, 'samples': 17040192, 'steps': 88750, 'loss/train': 0.8320730328559875} 08/31/2021 05:12:36 - INFO - __main__ - Step 88752: {'lr': 0.00018315688321770974, 'samples': 17040384, 'steps': 88751, 'loss/train': 1.0355604887008667} 08/31/2021 05:12:36 - INFO - __main__ - Step 88753: {'lr': 0.00018315176968970276, 'samples': 17040576, 'steps': 88752, 'loss/train': 1.431780457496643} 08/31/2021 05:12:37 - INFO - __main__ - Step 88754: {'lr': 0.0001831466561918167, 'samples': 17040768, 'steps': 88753, 'loss/train': 0.6446025967597961} 08/31/2021 05:12:38 - INFO - __main__ - Step 88755: {'lr': 0.00018314154272405355, 'samples': 17040960, 'steps': 88754, 'loss/train': 1.0775141716003418} 08/31/2021 05:12:38 - INFO - __main__ - Step 88756: {'lr': 0.00018313642928641583, 'samples': 17041152, 'steps': 88755, 'loss/train': 1.5097320079803467} 08/31/2021 05:12:39 - INFO - __main__ - Step 88757: {'lr': 0.0001831313158789058, 'samples': 17041344, 'steps': 88756, 'loss/train': 1.2524027824401855} 08/31/2021 05:12:39 - INFO - __main__ - Step 88758: {'lr': 0.00018312620250152578, 'samples': 17041536, 'steps': 88757, 'loss/train': 1.3865976333618164} 08/31/2021 05:12:40 - INFO - __main__ - Step 88759: {'lr': 0.00018312108915427805, 'samples': 17041728, 'steps': 88758, 'loss/train': 1.054921269416809} 08/31/2021 05:12:41 - INFO - __main__ - Step 88760: {'lr': 0.00018311597583716495, 'samples': 17041920, 'steps': 88759, 'loss/train': 1.2727620601654053} 08/31/2021 05:12:41 - INFO - __main__ - Step 88761: {'lr': 0.00018311086255018872, 'samples': 17042112, 'steps': 88760, 'loss/train': 0.4848373830318451} 08/31/2021 05:12:42 - INFO - __main__ - Step 88762: {'lr': 0.00018310574929335168, 'samples': 17042304, 'steps': 88761, 'loss/train': 1.1060336828231812} 08/31/2021 05:12:42 - INFO - __main__ - Step 88763: {'lr': 0.00018310063606665622, 'samples': 17042496, 'steps': 88762, 'loss/train': 1.6947342157363892} 08/31/2021 05:12:43 - INFO - __main__ - Step 88764: {'lr': 0.00018309552287010456, 'samples': 17042688, 'steps': 88763, 'loss/train': 0.9688491225242615} 08/31/2021 05:12:44 - INFO - __main__ - Step 88765: {'lr': 0.000183090409703699, 'samples': 17042880, 'steps': 88764, 'loss/train': 1.6891491413116455} 08/31/2021 05:12:44 - INFO - __main__ - Step 88766: {'lr': 0.0001830852965674419, 'samples': 17043072, 'steps': 88765, 'loss/train': 0.9339343905448914} 08/31/2021 05:12:45 - INFO - __main__ - Step 88767: {'lr': 0.00018308018346133563, 'samples': 17043264, 'steps': 88766, 'loss/train': 0.8619819283485413} 08/31/2021 05:12:45 - INFO - __main__ - Step 88768: {'lr': 0.0001830750703853823, 'samples': 17043456, 'steps': 88767, 'loss/train': 0.8653989434242249} 08/31/2021 05:12:45 - INFO - __main__ - Step 88769: {'lr': 0.00018306995733958427, 'samples': 17043648, 'steps': 88768, 'loss/train': 0.7949069142341614} 08/31/2021 05:12:48 - INFO - __main__ - Step 88770: {'lr': 0.00018306484432394394, 'samples': 17043840, 'steps': 88769, 'loss/train': 1.660791039466858} 08/31/2021 05:12:48 - INFO - __main__ - Step 88771: {'lr': 0.0001830597313384635, 'samples': 17044032, 'steps': 88770, 'loss/train': 0.9416682720184326} 08/31/2021 05:12:48 - INFO - __main__ - Step 88772: {'lr': 0.00018305461838314535, 'samples': 17044224, 'steps': 88771, 'loss/train': 1.6569887399673462} 08/31/2021 05:12:49 - INFO - __main__ - Step 88773: {'lr': 0.00018304950545799175, 'samples': 17044416, 'steps': 88772, 'loss/train': 1.4765968322753906} 08/31/2021 05:12:49 - INFO - __main__ - Step 88774: {'lr': 0.00018304439256300502, 'samples': 17044608, 'steps': 88773, 'loss/train': 0.9425601959228516} 08/31/2021 05:12:51 - INFO - __main__ - Step 88775: {'lr': 0.00018303927969818743, 'samples': 17044800, 'steps': 88774, 'loss/train': 1.1427757740020752} 08/31/2021 05:12:51 - INFO - __main__ - Step 88776: {'lr': 0.00018303416686354132, 'samples': 17044992, 'steps': 88775, 'loss/train': 0.35506632924079895} 08/31/2021 05:12:51 - INFO - __main__ - Step 88777: {'lr': 0.000183029054059069, 'samples': 17045184, 'steps': 88776, 'loss/train': 1.5346109867095947} 08/31/2021 05:12:52 - INFO - __main__ - Step 88778: {'lr': 0.00018302394128477274, 'samples': 17045376, 'steps': 88777, 'loss/train': 0.15870095789432526} 08/31/2021 05:12:52 - INFO - __main__ - Step 88779: {'lr': 0.00018301882854065483, 'samples': 17045568, 'steps': 88778, 'loss/train': 1.1679728031158447} 08/31/2021 05:12:54 - INFO - __main__ - Step 88780: {'lr': 0.00018301371582671766, 'samples': 17045760, 'steps': 88779, 'loss/train': 1.6496191024780273} 08/31/2021 05:12:54 - INFO - __main__ - Step 88781: {'lr': 0.00018300860314296352, 'samples': 17045952, 'steps': 88780, 'loss/train': 1.2379428148269653} 08/31/2021 05:12:54 - INFO - __main__ - Step 88782: {'lr': 0.00018300349048939457, 'samples': 17046144, 'steps': 88781, 'loss/train': 1.2478617429733276} 08/31/2021 05:12:55 - INFO - __main__ - Step 88783: {'lr': 0.00018299837786601324, 'samples': 17046336, 'steps': 88782, 'loss/train': 0.9687444567680359} 08/31/2021 05:12:55 - INFO - __main__ - Step 88784: {'lr': 0.0001829932652728218, 'samples': 17046528, 'steps': 88783, 'loss/train': 0.487181156873703} 08/31/2021 05:12:57 - INFO - __main__ - Step 88785: {'lr': 0.00018298815270982257, 'samples': 17046720, 'steps': 88784, 'loss/train': 1.332748293876648} 08/31/2021 05:12:57 - INFO - __main__ - Step 88786: {'lr': 0.00018298304017701783, 'samples': 17046912, 'steps': 88785, 'loss/train': 1.1223982572555542} 08/31/2021 05:12:58 - INFO - __main__ - Step 88787: {'lr': 0.0001829779276744099, 'samples': 17047104, 'steps': 88786, 'loss/train': 0.019549177959561348} 08/31/2021 05:12:58 - INFO - __main__ - Step 88788: {'lr': 0.0001829728152020011, 'samples': 17047296, 'steps': 88787, 'loss/train': 0.6585462093353271} 08/31/2021 05:12:58 - INFO - __main__ - Step 88789: {'lr': 0.00018296770275979372, 'samples': 17047488, 'steps': 88788, 'loss/train': 1.5398502349853516} 08/31/2021 05:12:59 - INFO - __main__ - Step 88790: {'lr': 0.00018296259034779002, 'samples': 17047680, 'steps': 88789, 'loss/train': 1.8719691038131714} 08/31/2021 05:13:01 - INFO - __main__ - Step 88791: {'lr': 0.00018295747796599244, 'samples': 17047872, 'steps': 88790, 'loss/train': 0.7411912083625793} 08/31/2021 05:13:01 - INFO - __main__ - Step 88792: {'lr': 0.0001829523656144031, 'samples': 17048064, 'steps': 88791, 'loss/train': 1.0495872497558594} 08/31/2021 05:13:01 - INFO - __main__ - Step 88793: {'lr': 0.0001829472532930244, 'samples': 17048256, 'steps': 88792, 'loss/train': 3.7792551517486572} 08/31/2021 05:13:02 - INFO - __main__ - Step 88794: {'lr': 0.0001829421410018587, 'samples': 17048448, 'steps': 88793, 'loss/train': 1.3452038764953613} 08/31/2021 05:13:02 - INFO - __main__ - Step 88795: {'lr': 0.00018293702874090816, 'samples': 17048640, 'steps': 88794, 'loss/train': 1.2483844757080078} 08/31/2021 05:13:02 - INFO - __main__ - Step 88796: {'lr': 0.00018293191651017515, 'samples': 17048832, 'steps': 88795, 'loss/train': 1.1484827995300293} 08/31/2021 05:13:04 - INFO - __main__ - Step 88797: {'lr': 0.000182926804309662, 'samples': 17049024, 'steps': 88796, 'loss/train': 1.3799749612808228} 08/31/2021 05:13:05 - INFO - __main__ - Step 88798: {'lr': 0.000182921692139371, 'samples': 17049216, 'steps': 88797, 'loss/train': 0.8777961134910583} 08/31/2021 05:13:05 - INFO - __main__ - Step 88799: {'lr': 0.00018291657999930445, 'samples': 17049408, 'steps': 88798, 'loss/train': 1.1561241149902344} 08/31/2021 05:13:05 - INFO - __main__ - Step 88800: {'lr': 0.00018291146788946468, 'samples': 17049600, 'steps': 88799, 'loss/train': 0.8997936248779297} 08/31/2021 05:13:06 - INFO - __main__ - Step 88801: {'lr': 0.00018290635580985392, 'samples': 17049792, 'steps': 88800, 'loss/train': 1.4781413078308105} 08/31/2021 05:13:06 - INFO - __main__ - Step 88802: {'lr': 0.0001829012437604746, 'samples': 17049984, 'steps': 88801, 'loss/train': 0.9820154309272766} 08/31/2021 05:13:08 - INFO - __main__ - Step 88803: {'lr': 0.00018289613174132888, 'samples': 17050176, 'steps': 88802, 'loss/train': 1.410470962524414} 08/31/2021 05:13:08 - INFO - __main__ - Step 88804: {'lr': 0.00018289101975241912, 'samples': 17050368, 'steps': 88803, 'loss/train': 0.029225418344140053} 08/31/2021 05:13:08 - INFO - __main__ - Step 88805: {'lr': 0.00018288590779374765, 'samples': 17050560, 'steps': 88804, 'loss/train': 0.8939024209976196} 08/31/2021 05:13:09 - INFO - __main__ - Step 88806: {'lr': 0.00018288079586531675, 'samples': 17050752, 'steps': 88805, 'loss/train': 1.2182488441467285} 08/31/2021 05:13:09 - INFO - __main__ - Step 88807: {'lr': 0.00018287568396712872, 'samples': 17050944, 'steps': 88806, 'loss/train': 0.9756112098693848} 08/31/2021 05:13:11 - INFO - __main__ - Step 88808: {'lr': 0.00018287057209918594, 'samples': 17051136, 'steps': 88807, 'loss/train': 1.103347659111023} 08/31/2021 05:13:11 - INFO - __main__ - Step 88809: {'lr': 0.0001828654602614906, 'samples': 17051328, 'steps': 88808, 'loss/train': 1.3436923027038574} 08/31/2021 05:13:11 - INFO - __main__ - Step 88810: {'lr': 0.00018286034845404502, 'samples': 17051520, 'steps': 88809, 'loss/train': 0.6545324921607971} 08/31/2021 05:13:12 - INFO - __main__ - Step 88811: {'lr': 0.00018285523667685154, 'samples': 17051712, 'steps': 88810, 'loss/train': 0.8435086607933044} 08/31/2021 05:13:12 - INFO - __main__ - Step 88812: {'lr': 0.0001828501249299125, 'samples': 17051904, 'steps': 88811, 'loss/train': 1.9860260486602783} 08/31/2021 05:13:13 - INFO - __main__ - Step 88813: {'lr': 0.0001828450132132301, 'samples': 17052096, 'steps': 88812, 'loss/train': 0.7606033086776733} 08/31/2021 05:13:14 - INFO - __main__ - Step 88814: {'lr': 0.0001828399015268067, 'samples': 17052288, 'steps': 88813, 'loss/train': 0.9668825268745422} 08/31/2021 05:13:14 - INFO - __main__ - Step 88815: {'lr': 0.0001828347898706446, 'samples': 17052480, 'steps': 88814, 'loss/train': 1.4719135761260986} 08/31/2021 05:13:15 - INFO - __main__ - Step 88816: {'lr': 0.00018282967824474617, 'samples': 17052672, 'steps': 88815, 'loss/train': 1.1900426149368286} 08/31/2021 05:13:15 - INFO - __main__ - Step 88817: {'lr': 0.0001828245666491136, 'samples': 17052864, 'steps': 88816, 'loss/train': 0.6861922144889832} 08/31/2021 05:13:17 - INFO - __main__ - Step 88818: {'lr': 0.00018281945508374925, 'samples': 17053056, 'steps': 88817, 'loss/train': 1.5669440031051636} 08/31/2021 05:13:17 - INFO - __main__ - Step 88819: {'lr': 0.0001828143435486554, 'samples': 17053248, 'steps': 88818, 'loss/train': 0.7182765007019043} 08/31/2021 05:13:17 - INFO - __main__ - Step 88820: {'lr': 0.00018280923204383437, 'samples': 17053440, 'steps': 88819, 'loss/train': 1.7870975732803345} 08/31/2021 05:13:18 - INFO - __main__ - Step 88821: {'lr': 0.00018280412056928856, 'samples': 17053632, 'steps': 88820, 'loss/train': 0.6073706150054932} 08/31/2021 05:13:18 - INFO - __main__ - Step 88822: {'lr': 0.00018279900912502006, 'samples': 17053824, 'steps': 88821, 'loss/train': 1.38174569606781} 08/31/2021 05:13:19 - INFO - __main__ - Step 88823: {'lr': 0.00018279389771103138, 'samples': 17054016, 'steps': 88822, 'loss/train': 0.5726516842842102} 08/31/2021 05:13:20 - INFO - __main__ - Step 88824: {'lr': 0.0001827887863273247, 'samples': 17054208, 'steps': 88823, 'loss/train': 1.2968981266021729} 08/31/2021 05:13:20 - INFO - __main__ - Step 88825: {'lr': 0.0001827836749739023, 'samples': 17054400, 'steps': 88824, 'loss/train': 1.0961014032363892} 08/31/2021 05:13:21 - INFO - __main__ - Step 88826: {'lr': 0.00018277856365076658, 'samples': 17054592, 'steps': 88825, 'loss/train': 0.6359878778457642} 08/31/2021 05:13:21 - INFO - __main__ - Step 88827: {'lr': 0.00018277345235791982, 'samples': 17054784, 'steps': 88826, 'loss/train': 1.2837491035461426} 08/31/2021 05:13:23 - INFO - __main__ - Step 88828: {'lr': 0.00018276834109536428, 'samples': 17054976, 'steps': 88827, 'loss/train': 1.3361047506332397} 08/31/2021 05:13:23 - INFO - __main__ - Step 88829: {'lr': 0.00018276322986310228, 'samples': 17055168, 'steps': 88828, 'loss/train': 0.7515337467193604} 08/31/2021 05:13:24 - INFO - __main__ - Step 88830: {'lr': 0.0001827581186611361, 'samples': 17055360, 'steps': 88829, 'loss/train': 1.3636155128479004} 08/31/2021 05:13:24 - INFO - __main__ - Step 88831: {'lr': 0.00018275300748946813, 'samples': 17055552, 'steps': 88830, 'loss/train': 1.0445476770401} 08/31/2021 05:13:24 - INFO - __main__ - Step 88832: {'lr': 0.0001827478963481006, 'samples': 17055744, 'steps': 88831, 'loss/train': 1.3786474466323853} 08/31/2021 05:13:25 - INFO - __main__ - Step 88833: {'lr': 0.00018274278523703583, 'samples': 17055936, 'steps': 88832, 'loss/train': 1.0293644666671753} 08/31/2021 05:13:26 - INFO - __main__ - Step 88834: {'lr': 0.00018273767415627611, 'samples': 17056128, 'steps': 88833, 'loss/train': 0.7177866697311401} 08/31/2021 05:13:27 - INFO - __main__ - Step 88835: {'lr': 0.0001827325631058239, 'samples': 17056320, 'steps': 88834, 'loss/train': 1.164414405822754} 08/31/2021 05:13:27 - INFO - __main__ - Step 88836: {'lr': 0.0001827274520856812, 'samples': 17056512, 'steps': 88835, 'loss/train': 1.6187669038772583} 08/31/2021 05:13:27 - INFO - __main__ - Step 88837: {'lr': 0.0001827223410958505, 'samples': 17056704, 'steps': 88836, 'loss/train': 0.4199560284614563} 08/31/2021 05:13:28 - INFO - __main__ - Step 88838: {'lr': 0.0001827172301363341, 'samples': 17056896, 'steps': 88837, 'loss/train': 0.962984025478363} 08/31/2021 05:13:29 - INFO - __main__ - Step 88839: {'lr': 0.00018271211920713423, 'samples': 17057088, 'steps': 88838, 'loss/train': 1.0972261428833008} 08/31/2021 05:13:30 - INFO - __main__ - Step 88840: {'lr': 0.00018270700830825325, 'samples': 17057280, 'steps': 88839, 'loss/train': 1.03273344039917} 08/31/2021 05:13:30 - INFO - __main__ - Step 88841: {'lr': 0.00018270189743969348, 'samples': 17057472, 'steps': 88840, 'loss/train': 0.5274719595909119} 08/31/2021 05:13:31 - INFO - __main__ - Step 88842: {'lr': 0.0001826967866014572, 'samples': 17057664, 'steps': 88841, 'loss/train': 1.1634160280227661} 08/31/2021 05:13:31 - INFO - __main__ - Step 88843: {'lr': 0.00018269167579354668, 'samples': 17057856, 'steps': 88842, 'loss/train': 0.46846625208854675} 08/31/2021 05:13:32 - INFO - __main__ - Step 88844: {'lr': 0.00018268656501596426, 'samples': 17058048, 'steps': 88843, 'loss/train': 1.1632894277572632} 08/31/2021 05:13:33 - INFO - __main__ - Step 88845: {'lr': 0.00018268145426871224, 'samples': 17058240, 'steps': 88844, 'loss/train': 0.6723256707191467} 08/31/2021 05:13:33 - INFO - __main__ - Step 88846: {'lr': 0.00018267634355179291, 'samples': 17058432, 'steps': 88845, 'loss/train': 1.2082843780517578} 08/31/2021 05:13:34 - INFO - __main__ - Step 88847: {'lr': 0.0001826712328652086, 'samples': 17058624, 'steps': 88846, 'loss/train': 1.047569751739502} 08/31/2021 05:13:34 - INFO - __main__ - Step 88848: {'lr': 0.00018266612220896168, 'samples': 17058816, 'steps': 88847, 'loss/train': 1.2460845708847046} 08/31/2021 05:13:36 - INFO - __main__ - Step 88849: {'lr': 0.00018266101158305426, 'samples': 17059008, 'steps': 88848, 'loss/train': 2.179586887359619} 08/31/2021 05:13:36 - INFO - __main__ - Step 88850: {'lr': 0.00018265590098748876, 'samples': 17059200, 'steps': 88849, 'loss/train': 1.316523790359497} 08/31/2021 05:13:36 - INFO - __main__ - Step 88851: {'lr': 0.00018265079042226748, 'samples': 17059392, 'steps': 88850, 'loss/train': 1.227262020111084} 08/31/2021 05:13:37 - INFO - __main__ - Step 88852: {'lr': 0.0001826456798873927, 'samples': 17059584, 'steps': 88851, 'loss/train': 1.7816017866134644} 08/31/2021 05:13:37 - INFO - __main__ - Step 88853: {'lr': 0.00018264056938286676, 'samples': 17059776, 'steps': 88852, 'loss/train': 1.3632879257202148} 08/31/2021 05:13:38 - INFO - __main__ - Step 88854: {'lr': 0.0001826354589086919, 'samples': 17059968, 'steps': 88853, 'loss/train': 0.9098474383354187} 08/31/2021 05:13:39 - INFO - __main__ - Step 88855: {'lr': 0.0001826303484648705, 'samples': 17060160, 'steps': 88854, 'loss/train': 1.2366201877593994} 08/31/2021 05:13:39 - INFO - __main__ - Step 88856: {'lr': 0.0001826252380514048, 'samples': 17060352, 'steps': 88855, 'loss/train': 1.18278968334198} 08/31/2021 05:13:40 - INFO - __main__ - Step 88857: {'lr': 0.00018262012766829714, 'samples': 17060544, 'steps': 88856, 'loss/train': 0.33412736654281616} 08/31/2021 05:13:40 - INFO - __main__ - Step 88858: {'lr': 0.0001826150173155498, 'samples': 17060736, 'steps': 88857, 'loss/train': 1.4842058420181274} 08/31/2021 05:13:42 - INFO - __main__ - Step 88859: {'lr': 0.0001826099069931651, 'samples': 17060928, 'steps': 88858, 'loss/train': 1.1156871318817139} 08/31/2021 05:13:42 - INFO - __main__ - Step 88860: {'lr': 0.00018260479670114532, 'samples': 17061120, 'steps': 88859, 'loss/train': 0.41711947321891785} 08/31/2021 05:13:43 - INFO - __main__ - Step 88861: {'lr': 0.00018259968643949293, 'samples': 17061312, 'steps': 88860, 'loss/train': 0.6261047720909119} 08/31/2021 05:13:43 - INFO - __main__ - Step 88862: {'lr': 0.00018259457620820992, 'samples': 17061504, 'steps': 88861, 'loss/train': 1.276086688041687} 08/31/2021 05:13:43 - INFO - __main__ - Step 88863: {'lr': 0.0001825894660072988, 'samples': 17061696, 'steps': 88862, 'loss/train': 1.5023105144500732} 08/31/2021 05:13:44 - INFO - __main__ - Step 88864: {'lr': 0.00018258435583676182, 'samples': 17061888, 'steps': 88863, 'loss/train': 0.5845376253128052} 08/31/2021 05:13:46 - INFO - __main__ - Step 88865: {'lr': 0.00018257924569660126, 'samples': 17062080, 'steps': 88864, 'loss/train': 1.3283445835113525} 08/31/2021 05:13:46 - INFO - __main__ - Step 88866: {'lr': 0.00018257413558681946, 'samples': 17062272, 'steps': 88865, 'loss/train': 1.4163131713867188} 08/31/2021 05:13:46 - INFO - __main__ - Step 88867: {'lr': 0.0001825690255074187, 'samples': 17062464, 'steps': 88866, 'loss/train': 0.6883567571640015} 08/31/2021 05:13:47 - INFO - __main__ - Step 88868: {'lr': 0.00018256391545840134, 'samples': 17062656, 'steps': 88867, 'loss/train': 0.08407348394393921} 08/31/2021 05:13:47 - INFO - __main__ - Step 88869: {'lr': 0.0001825588054397696, 'samples': 17062848, 'steps': 88868, 'loss/train': 1.2757676839828491} 08/31/2021 05:13:49 - INFO - __main__ - Step 88870: {'lr': 0.00018255369545152586, 'samples': 17063040, 'steps': 88869, 'loss/train': 0.733051598072052} 08/31/2021 05:13:49 - INFO - __main__ - Step 88871: {'lr': 0.00018254858549367236, 'samples': 17063232, 'steps': 88870, 'loss/train': 1.1115814447402954} 08/31/2021 05:13:49 - INFO - __main__ - Step 88872: {'lr': 0.00018254347556621143, 'samples': 17063424, 'steps': 88871, 'loss/train': 1.4738415479660034} 08/31/2021 05:13:50 - INFO - __main__ - Step 88873: {'lr': 0.0001825383656691454, 'samples': 17063616, 'steps': 88872, 'loss/train': 1.6434309482574463} 08/31/2021 05:13:50 - INFO - __main__ - Step 88874: {'lr': 0.00018253325580247647, 'samples': 17063808, 'steps': 88873, 'loss/train': 1.415657639503479} 08/31/2021 05:13:52 - INFO - __main__ - Step 88875: {'lr': 0.00018252814596620716, 'samples': 17064000, 'steps': 88874, 'loss/train': 1.659178376197815} 08/31/2021 05:13:52 - INFO - __main__ - Step 88876: {'lr': 0.00018252303616033956, 'samples': 17064192, 'steps': 88875, 'loss/train': 1.033128023147583} 08/31/2021 05:13:52 - INFO - __main__ - Step 88877: {'lr': 0.00018251792638487597, 'samples': 17064384, 'steps': 88876, 'loss/train': 0.925006091594696} 08/31/2021 05:13:53 - INFO - __main__ - Step 88878: {'lr': 0.00018251281663981877, 'samples': 17064576, 'steps': 88877, 'loss/train': 0.8554568290710449} 08/31/2021 05:13:53 - INFO - __main__ - Step 88879: {'lr': 0.0001825077069251703, 'samples': 17064768, 'steps': 88878, 'loss/train': 1.3474262952804565} 08/31/2021 05:13:55 - INFO - __main__ - Step 88880: {'lr': 0.00018250259724093276, 'samples': 17064960, 'steps': 88879, 'loss/train': 1.0848801136016846} 08/31/2021 05:13:56 - INFO - __main__ - Step 88881: {'lr': 0.00018249748758710854, 'samples': 17065152, 'steps': 88880, 'loss/train': 1.075641393661499} 08/31/2021 05:13:56 - INFO - __main__ - Step 88882: {'lr': 0.00018249237796369994, 'samples': 17065344, 'steps': 88881, 'loss/train': 0.7466609477996826} 08/31/2021 05:13:56 - INFO - __main__ - Step 88883: {'lr': 0.00018248726837070918, 'samples': 17065536, 'steps': 88882, 'loss/train': 1.7714464664459229} 08/31/2021 05:13:57 - INFO - __main__ - Step 88884: {'lr': 0.00018248215880813863, 'samples': 17065728, 'steps': 88883, 'loss/train': 1.2127432823181152} 08/31/2021 05:13:57 - INFO - __main__ - Step 88885: {'lr': 0.0001824770492759906, 'samples': 17065920, 'steps': 88884, 'loss/train': 1.7686846256256104} 08/31/2021 05:13:58 - INFO - __main__ - Step 88886: {'lr': 0.00018247193977426735, 'samples': 17066112, 'steps': 88885, 'loss/train': 0.48480796813964844} 08/31/2021 05:13:59 - INFO - __main__ - Step 88887: {'lr': 0.0001824668303029712, 'samples': 17066304, 'steps': 88886, 'loss/train': 0.6082956194877625} 08/31/2021 05:13:59 - INFO - __main__ - Step 88888: {'lr': 0.00018246172086210455, 'samples': 17066496, 'steps': 88887, 'loss/train': 1.195451021194458} 08/31/2021 05:14:00 - INFO - __main__ - Step 88889: {'lr': 0.00018245661145166952, 'samples': 17066688, 'steps': 88888, 'loss/train': 1.3717594146728516} 08/31/2021 05:14:00 - INFO - __main__ - Step 88890: {'lr': 0.0001824515020716685, 'samples': 17066880, 'steps': 88889, 'loss/train': 0.6164624094963074} 08/31/2021 05:14:01 - INFO - __main__ - Step 88891: {'lr': 0.0001824463927221038, 'samples': 17067072, 'steps': 88890, 'loss/train': 0.75240558385849} 08/31/2021 05:14:02 - INFO - __main__ - Step 88892: {'lr': 0.00018244128340297766, 'samples': 17067264, 'steps': 88891, 'loss/train': 1.2970508337020874} 08/31/2021 05:14:02 - INFO - __main__ - Step 88893: {'lr': 0.00018243617411429247, 'samples': 17067456, 'steps': 88892, 'loss/train': 0.8612682223320007} 08/31/2021 05:14:03 - INFO - __main__ - Step 88894: {'lr': 0.00018243106485605053, 'samples': 17067648, 'steps': 88893, 'loss/train': 0.7163987755775452} 08/31/2021 05:14:03 - INFO - __main__ - Step 88895: {'lr': 0.0001824259556282541, 'samples': 17067840, 'steps': 88894, 'loss/train': 1.445415735244751} 08/31/2021 05:14:04 - INFO - __main__ - Step 88896: {'lr': 0.00018242084643090546, 'samples': 17068032, 'steps': 88895, 'loss/train': 1.1571760177612305} 08/31/2021 05:14:05 - INFO - __main__ - Step 88897: {'lr': 0.00018241573726400696, 'samples': 17068224, 'steps': 88896, 'loss/train': 0.276584267616272} 08/31/2021 05:14:05 - INFO - __main__ - Step 88898: {'lr': 0.00018241062812756088, 'samples': 17068416, 'steps': 88897, 'loss/train': 0.03600747138261795} 08/31/2021 05:14:06 - INFO - __main__ - Step 88899: {'lr': 0.00018240551902156952, 'samples': 17068608, 'steps': 88898, 'loss/train': 0.9329914450645447} 08/31/2021 05:14:06 - INFO - __main__ - Step 88900: {'lr': 0.0001824004099460352, 'samples': 17068800, 'steps': 88899, 'loss/train': 1.1944953203201294} 08/31/2021 05:14:07 - INFO - __main__ - Step 88901: {'lr': 0.00018239530090096017, 'samples': 17068992, 'steps': 88900, 'loss/train': 1.037459135055542} 08/31/2021 05:14:08 - INFO - __main__ - Step 88902: {'lr': 0.00018239019188634695, 'samples': 17069184, 'steps': 88901, 'loss/train': 0.8427203893661499} 08/31/2021 05:14:08 - INFO - __main__ - Step 88903: {'lr': 0.00018238508290219753, 'samples': 17069376, 'steps': 88902, 'loss/train': 1.307766079902649} 08/31/2021 05:14:09 - INFO - __main__ - Step 88904: {'lr': 0.00018237997394851435, 'samples': 17069568, 'steps': 88903, 'loss/train': 0.32898297905921936} 08/31/2021 05:14:09 - INFO - __main__ - Step 88905: {'lr': 0.00018237486502529972, 'samples': 17069760, 'steps': 88904, 'loss/train': 1.1299841403961182} 08/31/2021 05:14:10 - INFO - __main__ - Step 88906: {'lr': 0.00018236975613255592, 'samples': 17069952, 'steps': 88905, 'loss/train': 1.025947093963623} 08/31/2021 05:14:11 - INFO - __main__ - Step 88907: {'lr': 0.00018236464727028527, 'samples': 17070144, 'steps': 88906, 'loss/train': 0.3806231617927551} 08/31/2021 05:14:11 - INFO - __main__ - Step 88908: {'lr': 0.00018235953843849008, 'samples': 17070336, 'steps': 88907, 'loss/train': 1.0096005201339722} 08/31/2021 05:14:12 - INFO - __main__ - Step 88909: {'lr': 0.00018235442963717257, 'samples': 17070528, 'steps': 88908, 'loss/train': 1.2606379985809326} 08/31/2021 05:14:12 - INFO - __main__ - Step 88910: {'lr': 0.00018234932086633518, 'samples': 17070720, 'steps': 88909, 'loss/train': 1.5174357891082764} 08/31/2021 05:14:14 - INFO - __main__ - Step 88911: {'lr': 0.0001823442121259801, 'samples': 17070912, 'steps': 88910, 'loss/train': 1.5858876705169678} 08/31/2021 05:14:14 - INFO - __main__ - Step 88912: {'lr': 0.00018233910341610972, 'samples': 17071104, 'steps': 88911, 'loss/train': 1.6092894077301025} 08/31/2021 05:14:15 - INFO - __main__ - Step 88913: {'lr': 0.0001823339947367263, 'samples': 17071296, 'steps': 88912, 'loss/train': 0.5501593351364136} 08/31/2021 05:14:15 - INFO - __main__ - Step 88914: {'lr': 0.00018232888608783217, 'samples': 17071488, 'steps': 88913, 'loss/train': 0.030225558206439018} 08/31/2021 05:14:15 - INFO - __main__ - Step 88915: {'lr': 0.00018232377746942957, 'samples': 17071680, 'steps': 88914, 'loss/train': 1.1972968578338623} 08/31/2021 05:14:17 - INFO - __main__ - Step 88916: {'lr': 0.0001823186688815208, 'samples': 17071872, 'steps': 88915, 'loss/train': 1.3566786050796509} 08/31/2021 05:14:17 - INFO - __main__ - Step 88917: {'lr': 0.0001823135603241082, 'samples': 17072064, 'steps': 88916, 'loss/train': 0.03326544538140297} 08/31/2021 05:14:18 - INFO - __main__ - Step 88918: {'lr': 0.0001823084517971941, 'samples': 17072256, 'steps': 88917, 'loss/train': 0.990207314491272} 08/31/2021 05:14:18 - INFO - __main__ - Step 88919: {'lr': 0.00018230334330078069, 'samples': 17072448, 'steps': 88918, 'loss/train': 1.7147153615951538} 08/31/2021 05:14:18 - INFO - __main__ - Step 88920: {'lr': 0.0001822982348348704, 'samples': 17072640, 'steps': 88919, 'loss/train': 1.5914356708526611} 08/31/2021 05:14:20 - INFO - __main__ - Step 88921: {'lr': 0.00018229312639946545, 'samples': 17072832, 'steps': 88920, 'loss/train': 1.2107268571853638} 08/31/2021 05:14:21 - INFO - __main__ - Step 88922: {'lr': 0.00018228801799456817, 'samples': 17073024, 'steps': 88921, 'loss/train': 1.5734827518463135} 08/31/2021 05:14:21 - INFO - __main__ - Step 88923: {'lr': 0.0001822829096201809, 'samples': 17073216, 'steps': 88922, 'loss/train': 0.9086034297943115} 08/31/2021 05:14:22 - INFO - __main__ - Step 88924: {'lr': 0.0001822778012763059, 'samples': 17073408, 'steps': 88923, 'loss/train': 1.3055623769760132} 08/31/2021 05:14:22 - INFO - __main__ - Step 88925: {'lr': 0.00018227269296294552, 'samples': 17073600, 'steps': 88924, 'loss/train': 1.2322182655334473} 08/31/2021 05:14:22 - INFO - __main__ - Step 88926: {'lr': 0.00018226758468010195, 'samples': 17073792, 'steps': 88925, 'loss/train': 1.5508205890655518} 08/31/2021 05:14:23 - INFO - __main__ - Step 88927: {'lr': 0.0001822624764277776, 'samples': 17073984, 'steps': 88926, 'loss/train': 1.1489044427871704} 08/31/2021 05:14:24 - INFO - __main__ - Step 88928: {'lr': 0.0001822573682059747, 'samples': 17074176, 'steps': 88927, 'loss/train': 0.1317274123430252} 08/31/2021 05:14:25 - INFO - __main__ - Step 88929: {'lr': 0.00018225226001469564, 'samples': 17074368, 'steps': 88928, 'loss/train': 1.207882285118103} 08/31/2021 05:14:25 - INFO - __main__ - Step 88930: {'lr': 0.00018224715185394263, 'samples': 17074560, 'steps': 88929, 'loss/train': 1.1322404146194458} 08/31/2021 05:14:25 - INFO - __main__ - Step 88931: {'lr': 0.000182242043723718, 'samples': 17074752, 'steps': 88930, 'loss/train': 1.5690486431121826} 08/31/2021 05:14:26 - INFO - __main__ - Step 88932: {'lr': 0.00018223693562402404, 'samples': 17074944, 'steps': 88931, 'loss/train': 1.7989150285720825} 08/31/2021 05:14:28 - INFO - __main__ - Step 88933: {'lr': 0.0001822318275548631, 'samples': 17075136, 'steps': 88932, 'loss/train': 1.029403567314148} 08/31/2021 05:14:29 - INFO - __main__ - Step 88934: {'lr': 0.00018222671951623746, 'samples': 17075328, 'steps': 88933, 'loss/train': 1.0780097246170044} 08/31/2021 05:14:29 - INFO - __main__ - Step 88935: {'lr': 0.0001822216115081494, 'samples': 17075520, 'steps': 88934, 'loss/train': 1.1016334295272827} 08/31/2021 05:14:29 - INFO - __main__ - Step 88936: {'lr': 0.0001822165035306013, 'samples': 17075712, 'steps': 88935, 'loss/train': 1.1557573080062866} 08/31/2021 05:14:30 - INFO - __main__ - Step 88937: {'lr': 0.0001822113955835953, 'samples': 17075904, 'steps': 88936, 'loss/train': 0.5859193205833435} 08/31/2021 05:14:31 - INFO - __main__ - Step 88938: {'lr': 0.00018220628766713384, 'samples': 17076096, 'steps': 88937, 'loss/train': 0.07702422142028809} 08/31/2021 05:14:32 - INFO - __main__ - Step 88939: {'lr': 0.0001822011797812192, 'samples': 17076288, 'steps': 88938, 'loss/train': 1.2832386493682861} 08/31/2021 05:14:32 - INFO - __main__ - Step 88940: {'lr': 0.0001821960719258536, 'samples': 17076480, 'steps': 88939, 'loss/train': 0.8214393258094788} 08/31/2021 05:14:32 - INFO - __main__ - Step 88941: {'lr': 0.00018219096410103947, 'samples': 17076672, 'steps': 88940, 'loss/train': 0.5765737891197205} 08/31/2021 05:14:33 - INFO - __main__ - Step 88942: {'lr': 0.00018218585630677903, 'samples': 17076864, 'steps': 88941, 'loss/train': 1.3705742359161377} 08/31/2021 05:14:33 - INFO - __main__ - Step 88943: {'lr': 0.0001821807485430746, 'samples': 17077056, 'steps': 88942, 'loss/train': 0.37589311599731445} 08/31/2021 05:14:34 - INFO - __main__ - Step 88944: {'lr': 0.00018217564080992845, 'samples': 17077248, 'steps': 88943, 'loss/train': 1.4552797079086304} 08/31/2021 05:14:35 - INFO - __main__ - Step 88945: {'lr': 0.00018217053310734294, 'samples': 17077440, 'steps': 88944, 'loss/train': 1.6692286729812622} 08/31/2021 05:14:35 - INFO - __main__ - Step 88946: {'lr': 0.0001821654254353203, 'samples': 17077632, 'steps': 88945, 'loss/train': 0.7492942214012146} 08/31/2021 05:14:36 - INFO - __main__ - Step 88947: {'lr': 0.00018216031779386295, 'samples': 17077824, 'steps': 88946, 'loss/train': 1.159666657447815} 08/31/2021 05:14:36 - INFO - __main__ - Step 88948: {'lr': 0.00018215521018297303, 'samples': 17078016, 'steps': 88947, 'loss/train': 0.9494639039039612} 08/31/2021 05:14:38 - INFO - __main__ - Step 88949: {'lr': 0.00018215010260265297, 'samples': 17078208, 'steps': 88948, 'loss/train': 0.7236019968986511} 08/31/2021 05:14:38 - INFO - __main__ - Step 88950: {'lr': 0.000182144995052905, 'samples': 17078400, 'steps': 88949, 'loss/train': 2.011378049850464} 08/31/2021 05:14:38 - INFO - __main__ - Step 88951: {'lr': 0.00018213988753373146, 'samples': 17078592, 'steps': 88950, 'loss/train': 1.0576668977737427} 08/31/2021 05:14:39 - INFO - __main__ - Step 88952: {'lr': 0.0001821347800451346, 'samples': 17078784, 'steps': 88951, 'loss/train': 1.3913244009017944} 08/31/2021 05:14:39 - INFO - __main__ - Step 88953: {'lr': 0.0001821296725871168, 'samples': 17078976, 'steps': 88952, 'loss/train': 1.0788497924804688} 08/31/2021 05:14:41 - INFO - __main__ - Step 88954: {'lr': 0.00018212456515968035, 'samples': 17079168, 'steps': 88953, 'loss/train': 0.6531969904899597} 08/31/2021 05:14:41 - INFO - __main__ - Step 88955: {'lr': 0.0001821194577628275, 'samples': 17079360, 'steps': 88954, 'loss/train': 0.28845956921577454} 08/31/2021 05:14:41 - INFO - __main__ - Step 88956: {'lr': 0.0001821143503965606, 'samples': 17079552, 'steps': 88955, 'loss/train': 1.9608771800994873} 08/31/2021 05:14:42 - INFO - __main__ - Step 88957: {'lr': 0.0001821092430608819, 'samples': 17079744, 'steps': 88956, 'loss/train': 1.5226547718048096} 08/31/2021 05:14:42 - INFO - __main__ - Step 88958: {'lr': 0.00018210413575579378, 'samples': 17079936, 'steps': 88957, 'loss/train': 0.4408711791038513} 08/31/2021 05:14:44 - INFO - __main__ - Step 88959: {'lr': 0.00018209902848129842, 'samples': 17080128, 'steps': 88958, 'loss/train': 1.15605890750885} 08/31/2021 05:14:44 - INFO - __main__ - Step 88960: {'lr': 0.00018209392123739822, 'samples': 17080320, 'steps': 88959, 'loss/train': 1.2628989219665527} 08/31/2021 05:14:45 - INFO - __main__ - Step 88961: {'lr': 0.0001820888140240954, 'samples': 17080512, 'steps': 88960, 'loss/train': 0.45721015334129333} 08/31/2021 05:14:45 - INFO - __main__ - Step 88962: {'lr': 0.00018208370684139237, 'samples': 17080704, 'steps': 88961, 'loss/train': 0.7512385249137878} 08/31/2021 05:14:45 - INFO - __main__ - Step 88963: {'lr': 0.00018207859968929132, 'samples': 17080896, 'steps': 88962, 'loss/train': 1.3081387281417847} 08/31/2021 05:14:47 - INFO - __main__ - Step 88964: {'lr': 0.00018207349256779465, 'samples': 17081088, 'steps': 88963, 'loss/train': 0.5653383135795593} 08/31/2021 05:14:48 - INFO - __main__ - Step 88965: {'lr': 0.00018206838547690457, 'samples': 17081280, 'steps': 88964, 'loss/train': 0.08910832554101944} 08/31/2021 05:14:48 - INFO - __main__ - Step 88966: {'lr': 0.00018206327841662346, 'samples': 17081472, 'steps': 88965, 'loss/train': 0.035074375569820404} 08/31/2021 05:14:48 - INFO - __main__ - Step 88967: {'lr': 0.00018205817138695356, 'samples': 17081664, 'steps': 88966, 'loss/train': 1.161281704902649} 08/31/2021 05:14:49 - INFO - __main__ - Step 88968: {'lr': 0.00018205306438789725, 'samples': 17081856, 'steps': 88967, 'loss/train': 1.287825107574463} 08/31/2021 05:14:49 - INFO - __main__ - Step 88969: {'lr': 0.00018204795741945685, 'samples': 17082048, 'steps': 88968, 'loss/train': 0.9450089335441589} 08/31/2021 05:14:49 - INFO - __main__ - Step 88970: {'lr': 0.0001820428504816345, 'samples': 17082240, 'steps': 88969, 'loss/train': 0.5691683888435364} 08/31/2021 05:14:51 - INFO - __main__ - Step 88971: {'lr': 0.0001820377435744326, 'samples': 17082432, 'steps': 88970, 'loss/train': 1.144134283065796} 08/31/2021 05:14:51 - INFO - __main__ - Step 88972: {'lr': 0.00018203263669785342, 'samples': 17082624, 'steps': 88971, 'loss/train': 1.1274091005325317} 08/31/2021 05:14:52 - INFO - __main__ - Step 88973: {'lr': 0.0001820275298518993, 'samples': 17082816, 'steps': 88972, 'loss/train': 1.3353896141052246} 08/31/2021 05:14:52 - INFO - __main__ - Step 88974: {'lr': 0.00018202242303657251, 'samples': 17083008, 'steps': 88973, 'loss/train': 1.264772891998291} 08/31/2021 05:14:52 - INFO - __main__ - Step 88975: {'lr': 0.00018201731625187538, 'samples': 17083200, 'steps': 88974, 'loss/train': 1.5549700260162354} 08/31/2021 05:14:54 - INFO - __main__ - Step 88976: {'lr': 0.00018201220949781022, 'samples': 17083392, 'steps': 88975, 'loss/train': 1.2292226552963257} 08/31/2021 05:14:55 - INFO - __main__ - Step 88977: {'lr': 0.00018200710277437927, 'samples': 17083584, 'steps': 88976, 'loss/train': 1.1109422445297241} 08/31/2021 05:14:55 - INFO - __main__ - Step 88978: {'lr': 0.0001820019960815849, 'samples': 17083776, 'steps': 88977, 'loss/train': 0.8006174564361572} 08/31/2021 05:14:55 - INFO - __main__ - Step 88979: {'lr': 0.00018199688941942938, 'samples': 17083968, 'steps': 88978, 'loss/train': 1.2070586681365967} 08/31/2021 05:14:56 - INFO - __main__ - Step 88980: {'lr': 0.000181991782787915, 'samples': 17084160, 'steps': 88979, 'loss/train': 0.6911382675170898} 08/31/2021 05:14:57 - INFO - __main__ - Step 88981: {'lr': 0.00018198667618704408, 'samples': 17084352, 'steps': 88980, 'loss/train': 1.5170713663101196} 08/31/2021 05:14:58 - INFO - __main__ - Step 88982: {'lr': 0.000181981569616819, 'samples': 17084544, 'steps': 88981, 'loss/train': 1.5824618339538574} 08/31/2021 05:14:58 - INFO - __main__ - Step 88983: {'lr': 0.0001819764630772419, 'samples': 17084736, 'steps': 88982, 'loss/train': 1.4662744998931885} 08/31/2021 05:14:58 - INFO - __main__ - Step 88984: {'lr': 0.0001819713565683151, 'samples': 17084928, 'steps': 88983, 'loss/train': 1.1636197566986084} 08/31/2021 05:14:59 - INFO - __main__ - Step 88985: {'lr': 0.00018196625009004103, 'samples': 17085120, 'steps': 88984, 'loss/train': 1.2848575115203857} 08/31/2021 05:14:59 - INFO - __main__ - Step 88986: {'lr': 0.0001819611436424219, 'samples': 17085312, 'steps': 88985, 'loss/train': 0.975022554397583} 08/31/2021 05:15:01 - INFO - __main__ - Step 88987: {'lr': 0.00018195603722546, 'samples': 17085504, 'steps': 88986, 'loss/train': 1.5808944702148438} 08/31/2021 05:15:01 - INFO - __main__ - Step 88988: {'lr': 0.00018195093083915766, 'samples': 17085696, 'steps': 88987, 'loss/train': 0.110102578997612} 08/31/2021 05:15:01 - INFO - __main__ - Step 88989: {'lr': 0.00018194582448351722, 'samples': 17085888, 'steps': 88988, 'loss/train': 1.4940396547317505} 08/31/2021 05:15:02 - INFO - __main__ - Step 88990: {'lr': 0.00018194071815854092, 'samples': 17086080, 'steps': 88989, 'loss/train': 1.3511168956756592} 08/31/2021 05:15:02 - INFO - __main__ - Step 88991: {'lr': 0.00018193561186423106, 'samples': 17086272, 'steps': 88990, 'loss/train': 1.5664708614349365} 08/31/2021 05:15:04 - INFO - __main__ - Step 88992: {'lr': 0.00018193050560058997, 'samples': 17086464, 'steps': 88991, 'loss/train': 1.5652718544006348} 08/31/2021 05:15:05 - INFO - __main__ - Step 88993: {'lr': 0.00018192539936761997, 'samples': 17086656, 'steps': 88992, 'loss/train': 1.0065947771072388} 08/31/2021 05:15:05 - INFO - __main__ - Step 88994: {'lr': 0.0001819202931653233, 'samples': 17086848, 'steps': 88993, 'loss/train': 1.3956904411315918} 08/31/2021 05:15:05 - INFO - __main__ - Step 88995: {'lr': 0.0001819151869937023, 'samples': 17087040, 'steps': 88994, 'loss/train': 1.0151761770248413} 08/31/2021 05:15:06 - INFO - __main__ - Step 88996: {'lr': 0.0001819100808527594, 'samples': 17087232, 'steps': 88995, 'loss/train': 1.1096662282943726} 08/31/2021 05:15:07 - INFO - __main__ - Step 88997: {'lr': 0.00018190497474249664, 'samples': 17087424, 'steps': 88996, 'loss/train': 2.676705837249756} 08/31/2021 05:15:07 - INFO - __main__ - Step 88998: {'lr': 0.00018189986866291646, 'samples': 17087616, 'steps': 88997, 'loss/train': 1.283479928970337} 08/31/2021 05:15:08 - INFO - __main__ - Step 88999: {'lr': 0.00018189476261402116, 'samples': 17087808, 'steps': 88998, 'loss/train': 0.9352823495864868} 08/31/2021 05:15:08 - INFO - __main__ - Step 89000: {'lr': 0.000181889656595813, 'samples': 17088000, 'steps': 88999, 'loss/train': 0.8499459028244019} 08/31/2021 05:15:08 - INFO - __main__ - Step 89001: {'lr': 0.0001818845506082943, 'samples': 17088192, 'steps': 89000, 'loss/train': 1.3258572816848755} 08/31/2021 05:15:10 - INFO - __main__ - Step 89002: {'lr': 0.00018187944465146742, 'samples': 17088384, 'steps': 89001, 'loss/train': 1.0022140741348267} 08/31/2021 05:15:11 - INFO - __main__ - Step 89003: {'lr': 0.00018187433872533457, 'samples': 17088576, 'steps': 89002, 'loss/train': 0.4698513448238373} 08/31/2021 05:15:11 - INFO - __main__ - Step 89004: {'lr': 0.00018186923282989808, 'samples': 17088768, 'steps': 89003, 'loss/train': 1.0627084970474243} 08/31/2021 05:15:11 - INFO - __main__ - Step 89005: {'lr': 0.00018186412696516031, 'samples': 17088960, 'steps': 89004, 'loss/train': 0.6413737535476685} 08/31/2021 05:15:12 - INFO - __main__ - Step 89006: {'lr': 0.00018185902113112352, 'samples': 17089152, 'steps': 89005, 'loss/train': 1.0449013710021973} 08/31/2021 05:15:12 - INFO - __main__ - Step 89007: {'lr': 0.00018185391532778993, 'samples': 17089344, 'steps': 89006, 'loss/train': 0.880723237991333} 08/31/2021 05:15:13 - INFO - __main__ - Step 89008: {'lr': 0.00018184880955516197, 'samples': 17089536, 'steps': 89007, 'loss/train': 1.3319305181503296} 08/31/2021 05:15:14 - INFO - __main__ - Step 89009: {'lr': 0.000181843703813242, 'samples': 17089728, 'steps': 89008, 'loss/train': 1.2019109725952148} 08/31/2021 05:15:14 - INFO - __main__ - Step 89010: {'lr': 0.00018183859810203207, 'samples': 17089920, 'steps': 89009, 'loss/train': 0.8371458649635315} 08/31/2021 05:15:14 - INFO - __main__ - Step 89011: {'lr': 0.00018183349242153462, 'samples': 17090112, 'steps': 89010, 'loss/train': 0.7554504871368408} 08/31/2021 05:15:15 - INFO - __main__ - Step 89012: {'lr': 0.00018182838677175195, 'samples': 17090304, 'steps': 89011, 'loss/train': 1.7447227239608765} 08/31/2021 05:15:16 - INFO - __main__ - Step 89013: {'lr': 0.00018182328115268638, 'samples': 17090496, 'steps': 89012, 'loss/train': 1.1151717901229858} 08/31/2021 05:15:17 - INFO - __main__ - Step 89014: {'lr': 0.00018181817556434015, 'samples': 17090688, 'steps': 89013, 'loss/train': 1.2591662406921387} 08/31/2021 05:15:17 - INFO - __main__ - Step 89015: {'lr': 0.0001818130700067156, 'samples': 17090880, 'steps': 89014, 'loss/train': 1.141608715057373} 08/31/2021 05:15:18 - INFO - __main__ - Step 89016: {'lr': 0.00018180796447981508, 'samples': 17091072, 'steps': 89015, 'loss/train': 2.049461603164673} 08/31/2021 05:15:18 - INFO - __main__ - Step 89017: {'lr': 0.00018180285898364076, 'samples': 17091264, 'steps': 89016, 'loss/train': 1.1633896827697754} 08/31/2021 05:15:19 - INFO - __main__ - Step 89018: {'lr': 0.00018179775351819506, 'samples': 17091456, 'steps': 89017, 'loss/train': 1.2656073570251465} 08/31/2021 05:15:20 - INFO - __main__ - Step 89019: {'lr': 0.00018179264808348026, 'samples': 17091648, 'steps': 89018, 'loss/train': 1.3511135578155518} 08/31/2021 05:15:20 - INFO - __main__ - Step 89020: {'lr': 0.0001817875426794986, 'samples': 17091840, 'steps': 89019, 'loss/train': 0.7242335081100464} 08/31/2021 05:15:20 - INFO - __main__ - Step 89021: {'lr': 0.00018178243730625242, 'samples': 17092032, 'steps': 89020, 'loss/train': 1.2604235410690308} 08/31/2021 05:15:21 - INFO - __main__ - Step 89022: {'lr': 0.00018177733196374408, 'samples': 17092224, 'steps': 89021, 'loss/train': 0.9640050530433655} 08/31/2021 05:15:22 - INFO - __main__ - Step 89023: {'lr': 0.0001817722266519759, 'samples': 17092416, 'steps': 89022, 'loss/train': 1.1206274032592773} 08/31/2021 05:15:23 - INFO - __main__ - Step 89024: {'lr': 0.00018176712137094996, 'samples': 17092608, 'steps': 89023, 'loss/train': 1.2239842414855957} 08/31/2021 05:15:23 - INFO - __main__ - Step 89025: {'lr': 0.00018176201612066874, 'samples': 17092800, 'steps': 89024, 'loss/train': 1.139163851737976} 08/31/2021 05:15:23 - INFO - __main__ - Step 89026: {'lr': 0.0001817569109011345, 'samples': 17092992, 'steps': 89025, 'loss/train': 0.8928403258323669} 08/31/2021 05:15:24 - INFO - __main__ - Step 89027: {'lr': 0.0001817518057123495, 'samples': 17093184, 'steps': 89026, 'loss/train': 0.9906213283538818} 08/31/2021 05:15:24 - INFO - __main__ - Step 89028: {'lr': 0.00018174670055431613, 'samples': 17093376, 'steps': 89027, 'loss/train': 1.0101220607757568} 08/31/2021 05:15:26 - INFO - __main__ - Step 89029: {'lr': 0.00018174159542703664, 'samples': 17093568, 'steps': 89028, 'loss/train': 1.748155117034912} 08/31/2021 05:15:26 - INFO - __main__ - Step 89030: {'lr': 0.0001817364903305133, 'samples': 17093760, 'steps': 89029, 'loss/train': 1.582718849182129} 08/31/2021 05:15:26 - INFO - __main__ - Step 89031: {'lr': 0.00018173138526474846, 'samples': 17093952, 'steps': 89030, 'loss/train': 1.045913815498352} 08/31/2021 05:15:27 - INFO - __main__ - Step 89032: {'lr': 0.00018172628022974444, 'samples': 17094144, 'steps': 89031, 'loss/train': 0.3865605890750885} 08/31/2021 05:15:27 - INFO - __main__ - Step 89033: {'lr': 0.00018172117522550346, 'samples': 17094336, 'steps': 89032, 'loss/train': 1.2128610610961914} 08/31/2021 05:15:28 - INFO - __main__ - Step 89034: {'lr': 0.00018171607025202792, 'samples': 17094528, 'steps': 89033, 'loss/train': 1.4306306838989258} 08/31/2021 05:15:29 - INFO - __main__ - Step 89035: {'lr': 0.00018171096530932002, 'samples': 17094720, 'steps': 89034, 'loss/train': 1.2589341402053833} 08/31/2021 05:15:29 - INFO - __main__ - Step 89036: {'lr': 0.0001817058603973822, 'samples': 17094912, 'steps': 89035, 'loss/train': 1.6483362913131714} 08/31/2021 05:15:30 - INFO - __main__ - Step 89037: {'lr': 0.00018170075551621656, 'samples': 17095104, 'steps': 89036, 'loss/train': 1.6227571964263916} 08/31/2021 05:15:30 - INFO - __main__ - Step 89038: {'lr': 0.00018169565066582555, 'samples': 17095296, 'steps': 89037, 'loss/train': 0.3342217803001404} 08/31/2021 05:15:32 - INFO - __main__ - Step 89039: {'lr': 0.0001816905458462114, 'samples': 17095488, 'steps': 89038, 'loss/train': 1.801139235496521} 08/31/2021 05:15:32 - INFO - __main__ - Step 89040: {'lr': 0.00018168544105737642, 'samples': 17095680, 'steps': 89039, 'loss/train': 1.854394555091858} 08/31/2021 05:15:33 - INFO - __main__ - Step 89041: {'lr': 0.00018168033629932295, 'samples': 17095872, 'steps': 89040, 'loss/train': 0.9598881602287292} 08/31/2021 05:15:33 - INFO - __main__ - Step 89042: {'lr': 0.00018167523157205324, 'samples': 17096064, 'steps': 89041, 'loss/train': 0.7459109425544739} 08/31/2021 05:15:33 - INFO - __main__ - Step 89043: {'lr': 0.00018167012687556963, 'samples': 17096256, 'steps': 89042, 'loss/train': 1.3115851879119873} 08/31/2021 05:15:34 - INFO - __main__ - Step 89044: {'lr': 0.00018166502220987442, 'samples': 17096448, 'steps': 89043, 'loss/train': 1.1972540616989136} 08/31/2021 05:15:36 - INFO - __main__ - Step 89045: {'lr': 0.0001816599175749699, 'samples': 17096640, 'steps': 89044, 'loss/train': 0.06224428489804268} 08/31/2021 05:15:36 - INFO - __main__ - Step 89046: {'lr': 0.00018165481297085834, 'samples': 17096832, 'steps': 89045, 'loss/train': 1.3887754678726196} 08/31/2021 05:15:37 - INFO - __main__ - Step 89047: {'lr': 0.00018164970839754208, 'samples': 17097024, 'steps': 89046, 'loss/train': 0.5803648233413696} 08/31/2021 05:15:37 - INFO - __main__ - Step 89048: {'lr': 0.00018164460385502345, 'samples': 17097216, 'steps': 89047, 'loss/train': 1.0545965433120728} 08/31/2021 05:15:37 - INFO - __main__ - Step 89049: {'lr': 0.00018163949934330467, 'samples': 17097408, 'steps': 89048, 'loss/train': 1.066563367843628} 08/31/2021 05:15:39 - INFO - __main__ - Step 89050: {'lr': 0.00018163439486238814, 'samples': 17097600, 'steps': 89049, 'loss/train': 0.46315690875053406} 08/31/2021 05:15:39 - INFO - __main__ - Step 89051: {'lr': 0.000181629290412276, 'samples': 17097792, 'steps': 89050, 'loss/train': 0.9939972162246704} 08/31/2021 05:15:40 - INFO - __main__ - Step 89052: {'lr': 0.0001816241859929707, 'samples': 17097984, 'steps': 89051, 'loss/train': 0.693375825881958} 08/31/2021 05:15:40 - INFO - __main__ - Step 89053: {'lr': 0.00018161908160447442, 'samples': 17098176, 'steps': 89052, 'loss/train': 1.5155590772628784} 08/31/2021 05:15:40 - INFO - __main__ - Step 89054: {'lr': 0.00018161397724678958, 'samples': 17098368, 'steps': 89053, 'loss/train': 1.289293885231018} 08/31/2021 05:15:42 - INFO - __main__ - Step 89055: {'lr': 0.00018160887291991844, 'samples': 17098560, 'steps': 89054, 'loss/train': 1.17653489112854} 08/31/2021 05:15:43 - INFO - __main__ - Step 89056: {'lr': 0.00018160376862386325, 'samples': 17098752, 'steps': 89055, 'loss/train': 1.1878224611282349} 08/31/2021 05:15:43 - INFO - __main__ - Step 89057: {'lr': 0.00018159866435862634, 'samples': 17098944, 'steps': 89056, 'loss/train': 1.5293545722961426} 08/31/2021 05:15:43 - INFO - __main__ - Step 89058: {'lr': 0.00018159356012421003, 'samples': 17099136, 'steps': 89057, 'loss/train': 1.2310773134231567} 08/31/2021 05:15:44 - INFO - __main__ - Step 89059: {'lr': 0.00018158845592061669, 'samples': 17099328, 'steps': 89058, 'loss/train': 1.2875523567199707} 08/31/2021 05:15:45 - INFO - __main__ - Step 89060: {'lr': 0.00018158335174784843, 'samples': 17099520, 'steps': 89059, 'loss/train': 0.25284868478775024} 08/31/2021 05:15:46 - INFO - __main__ - Step 89061: {'lr': 0.00018157824760590768, 'samples': 17099712, 'steps': 89060, 'loss/train': 1.0289621353149414} 08/31/2021 05:15:46 - INFO - __main__ - Step 89062: {'lr': 0.00018157314349479672, 'samples': 17099904, 'steps': 89061, 'loss/train': 1.243369221687317} 08/31/2021 05:15:46 - INFO - __main__ - Step 89063: {'lr': 0.00018156803941451788, 'samples': 17100096, 'steps': 89062, 'loss/train': 1.0412912368774414} 08/31/2021 05:15:47 - INFO - __main__ - Step 89064: {'lr': 0.0001815629353650734, 'samples': 17100288, 'steps': 89063, 'loss/train': 0.9454995393753052} 08/31/2021 05:15:48 - INFO - __main__ - Step 89065: {'lr': 0.0001815578313464656, 'samples': 17100480, 'steps': 89064, 'loss/train': 1.5381742715835571} 08/31/2021 05:15:49 - INFO - __main__ - Step 89066: {'lr': 0.00018155272735869676, 'samples': 17100672, 'steps': 89065, 'loss/train': 1.8471845388412476} 08/31/2021 05:15:49 - INFO - __main__ - Step 89067: {'lr': 0.00018154762340176923, 'samples': 17100864, 'steps': 89066, 'loss/train': 0.8575035929679871} 08/31/2021 05:15:49 - INFO - __main__ - Step 89068: {'lr': 0.0001815425194756853, 'samples': 17101056, 'steps': 89067, 'loss/train': 1.254875898361206} 08/31/2021 05:15:50 - INFO - __main__ - Step 89069: {'lr': 0.00018153741558044723, 'samples': 17101248, 'steps': 89068, 'loss/train': 1.4269405603408813} 08/31/2021 05:15:51 - INFO - __main__ - Step 89070: {'lr': 0.00018153231171605738, 'samples': 17101440, 'steps': 89069, 'loss/train': 1.7494996786117554} 08/31/2021 05:15:52 - INFO - __main__ - Step 89071: {'lr': 0.000181527207882518, 'samples': 17101632, 'steps': 89070, 'loss/train': 0.902834951877594} 08/31/2021 05:15:52 - INFO - __main__ - Step 89072: {'lr': 0.00018152210407983138, 'samples': 17101824, 'steps': 89071, 'loss/train': 0.5826428532600403} 08/31/2021 05:15:52 - INFO - __main__ - Step 89073: {'lr': 0.00018151700030799985, 'samples': 17102016, 'steps': 89072, 'loss/train': 1.3286867141723633} 08/31/2021 05:15:53 - INFO - __main__ - Step 89074: {'lr': 0.00018151189656702568, 'samples': 17102208, 'steps': 89073, 'loss/train': 0.1721077859401703} 08/31/2021 05:15:53 - INFO - __main__ - Step 89075: {'lr': 0.0001815067928569112, 'samples': 17102400, 'steps': 89074, 'loss/train': 0.6255244612693787} 08/31/2021 05:15:54 - INFO - __main__ - Step 89076: {'lr': 0.00018150168917765874, 'samples': 17102592, 'steps': 89075, 'loss/train': 1.3150877952575684} 08/31/2021 05:15:55 - INFO - __main__ - Step 89077: {'lr': 0.00018149658552927056, 'samples': 17102784, 'steps': 89076, 'loss/train': 0.9311350584030151} 08/31/2021 05:15:55 - INFO - __main__ - Step 89078: {'lr': 0.00018149148191174896, 'samples': 17102976, 'steps': 89077, 'loss/train': 1.170235276222229} 08/31/2021 05:15:56 - INFO - __main__ - Step 89079: {'lr': 0.0001814863783250962, 'samples': 17103168, 'steps': 89078, 'loss/train': 1.4875487089157104} 08/31/2021 05:15:56 - INFO - __main__ - Step 89080: {'lr': 0.00018148127476931463, 'samples': 17103360, 'steps': 89079, 'loss/train': 1.1179291009902954} 08/31/2021 05:15:57 - INFO - __main__ - Step 89081: {'lr': 0.00018147617124440662, 'samples': 17103552, 'steps': 89080, 'loss/train': 1.2402079105377197} 08/31/2021 05:15:58 - INFO - __main__ - Step 89082: {'lr': 0.00018147106775037432, 'samples': 17103744, 'steps': 89081, 'loss/train': 1.2825671434402466} 08/31/2021 05:15:58 - INFO - __main__ - Step 89083: {'lr': 0.00018146596428722013, 'samples': 17103936, 'steps': 89082, 'loss/train': 0.7386088371276855} 08/31/2021 05:15:59 - INFO - __main__ - Step 89084: {'lr': 0.00018146086085494626, 'samples': 17104128, 'steps': 89083, 'loss/train': 1.1103291511535645} 08/31/2021 05:15:59 - INFO - __main__ - Step 89085: {'lr': 0.00018145575745355508, 'samples': 17104320, 'steps': 89084, 'loss/train': 1.2720417976379395} 08/31/2021 05:16:00 - INFO - __main__ - Step 89086: {'lr': 0.0001814506540830489, 'samples': 17104512, 'steps': 89085, 'loss/train': 1.587116003036499} 08/31/2021 05:16:01 - INFO - __main__ - Step 89087: {'lr': 0.00018144555074343, 'samples': 17104704, 'steps': 89086, 'loss/train': 1.5387176275253296} 08/31/2021 05:16:01 - INFO - __main__ - Step 89088: {'lr': 0.00018144044743470067, 'samples': 17104896, 'steps': 89087, 'loss/train': 0.9617849588394165} 08/31/2021 05:16:02 - INFO - __main__ - Step 89089: {'lr': 0.00018143534415686322, 'samples': 17105088, 'steps': 89088, 'loss/train': 1.267156720161438} 08/31/2021 05:16:02 - INFO - __main__ - Step 89090: {'lr': 0.00018143024090992, 'samples': 17105280, 'steps': 89089, 'loss/train': 0.13071642816066742} 08/31/2021 05:16:04 - INFO - __main__ - Step 89091: {'lr': 0.0001814251376938732, 'samples': 17105472, 'steps': 89090, 'loss/train': 1.3632994890213013} 08/31/2021 05:16:04 - INFO - __main__ - Step 89092: {'lr': 0.0001814200345087252, 'samples': 17105664, 'steps': 89091, 'loss/train': 0.05619695037603378} 08/31/2021 05:16:05 - INFO - __main__ - Step 89093: {'lr': 0.00018141493135447826, 'samples': 17105856, 'steps': 89092, 'loss/train': 1.5287989377975464} 08/31/2021 05:16:05 - INFO - __main__ - Step 89094: {'lr': 0.00018140982823113466, 'samples': 17106048, 'steps': 89093, 'loss/train': 0.8913781046867371} 08/31/2021 05:16:05 - INFO - __main__ - Step 89095: {'lr': 0.00018140472513869676, 'samples': 17106240, 'steps': 89094, 'loss/train': 1.46551513671875} 08/31/2021 05:16:07 - INFO - __main__ - Step 89096: {'lr': 0.00018139962207716683, 'samples': 17106432, 'steps': 89095, 'loss/train': 1.7206474542617798} 08/31/2021 05:16:08 - INFO - __main__ - Step 89097: {'lr': 0.00018139451904654718, 'samples': 17106624, 'steps': 89096, 'loss/train': 1.8167674541473389} 08/31/2021 05:16:08 - INFO - __main__ - Step 89098: {'lr': 0.00018138941604684005, 'samples': 17106816, 'steps': 89097, 'loss/train': 0.4205950200557709} 08/31/2021 05:16:09 - INFO - __main__ - Step 89099: {'lr': 0.00018138431307804784, 'samples': 17107008, 'steps': 89098, 'loss/train': 1.2005512714385986} 08/31/2021 05:16:09 - INFO - __main__ - Step 89100: {'lr': 0.00018137921014017277, 'samples': 17107200, 'steps': 89099, 'loss/train': 0.5106401443481445} 08/31/2021 05:16:10 - INFO - __main__ - Step 89101: {'lr': 0.0001813741072332172, 'samples': 17107392, 'steps': 89100, 'loss/train': 1.8260201215744019} 08/31/2021 05:16:11 - INFO - __main__ - Step 89102: {'lr': 0.0001813690043571834, 'samples': 17107584, 'steps': 89101, 'loss/train': 0.9900686740875244} 08/31/2021 05:16:11 - INFO - __main__ - Step 89103: {'lr': 0.00018136390151207376, 'samples': 17107776, 'steps': 89102, 'loss/train': 1.5138834714889526} 08/31/2021 05:16:12 - INFO - __main__ - Step 89104: {'lr': 0.00018135879869789038, 'samples': 17107968, 'steps': 89103, 'loss/train': 0.6785022020339966} 08/31/2021 05:16:12 - INFO - __main__ - Step 89105: {'lr': 0.00018135369591463566, 'samples': 17108160, 'steps': 89104, 'loss/train': 0.783819317817688} 08/31/2021 05:16:13 - INFO - __main__ - Step 89106: {'lr': 0.0001813485931623119, 'samples': 17108352, 'steps': 89105, 'loss/train': 1.2016786336898804} 08/31/2021 05:16:14 - INFO - __main__ - Step 89107: {'lr': 0.0001813434904409214, 'samples': 17108544, 'steps': 89106, 'loss/train': 0.6336665153503418} 08/31/2021 05:16:14 - INFO - __main__ - Step 89108: {'lr': 0.00018133838775046652, 'samples': 17108736, 'steps': 89107, 'loss/train': 0.0357595793902874} 08/31/2021 05:16:15 - INFO - __main__ - Step 89109: {'lr': 0.00018133328509094943, 'samples': 17108928, 'steps': 89108, 'loss/train': 1.8507345914840698} 08/31/2021 05:16:15 - INFO - __main__ - Step 89110: {'lr': 0.00018132818246237255, 'samples': 17109120, 'steps': 89109, 'loss/train': 1.0339741706848145} 08/31/2021 05:16:17 - INFO - __main__ - Step 89111: {'lr': 0.0001813230798647381, 'samples': 17109312, 'steps': 89110, 'loss/train': 0.8233396410942078} 08/31/2021 05:16:17 - INFO - __main__ - Step 89112: {'lr': 0.00018131797729804844, 'samples': 17109504, 'steps': 89111, 'loss/train': 0.03444259613752365} 08/31/2021 05:16:18 - INFO - __main__ - Step 89113: {'lr': 0.00018131287476230582, 'samples': 17109696, 'steps': 89112, 'loss/train': 0.37693291902542114} 08/31/2021 05:16:18 - INFO - __main__ - Step 89114: {'lr': 0.00018130777225751254, 'samples': 17109888, 'steps': 89113, 'loss/train': 0.38944146037101746} 08/31/2021 05:16:18 - INFO - __main__ - Step 89115: {'lr': 0.00018130266978367096, 'samples': 17110080, 'steps': 89114, 'loss/train': 0.5524070858955383} 08/31/2021 05:16:19 - INFO - __main__ - Step 89116: {'lr': 0.00018129756734078334, 'samples': 17110272, 'steps': 89115, 'loss/train': 0.06124740093946457} 08/31/2021 05:16:20 - INFO - __main__ - Step 89117: {'lr': 0.00018129246492885203, 'samples': 17110464, 'steps': 89116, 'loss/train': 0.021369649097323418} 08/31/2021 05:16:21 - INFO - __main__ - Step 89118: {'lr': 0.0001812873625478792, 'samples': 17110656, 'steps': 89117, 'loss/train': 1.0191736221313477} 08/31/2021 05:16:21 - INFO - __main__ - Step 89119: {'lr': 0.00018128226019786724, 'samples': 17110848, 'steps': 89118, 'loss/train': 0.4109939932823181} 08/31/2021 05:16:21 - INFO - __main__ - Step 89120: {'lr': 0.00018127715787881842, 'samples': 17111040, 'steps': 89119, 'loss/train': 0.776229739189148} 08/31/2021 05:16:22 - INFO - __main__ - Step 89121: {'lr': 0.00018127205559073507, 'samples': 17111232, 'steps': 89120, 'loss/train': 1.5178287029266357} 08/31/2021 05:16:23 - INFO - __main__ - Step 89122: {'lr': 0.00018126695333361943, 'samples': 17111424, 'steps': 89121, 'loss/train': 0.9106194972991943} 08/31/2021 05:16:24 - INFO - __main__ - Step 89123: {'lr': 0.00018126185110747383, 'samples': 17111616, 'steps': 89122, 'loss/train': 1.0673221349716187} 08/31/2021 05:16:24 - INFO - __main__ - Step 89124: {'lr': 0.00018125674891230064, 'samples': 17111808, 'steps': 89123, 'loss/train': 1.3943758010864258} 08/31/2021 05:16:24 - INFO - __main__ - Step 89125: {'lr': 0.00018125164674810207, 'samples': 17112000, 'steps': 89124, 'loss/train': 1.5840201377868652} 08/31/2021 05:16:25 - INFO - __main__ - Step 89126: {'lr': 0.00018124654461488043, 'samples': 17112192, 'steps': 89125, 'loss/train': 1.0570389032363892} 08/31/2021 05:16:25 - INFO - __main__ - Step 89127: {'lr': 0.00018124144251263809, 'samples': 17112384, 'steps': 89126, 'loss/train': 1.1775782108306885} 08/31/2021 05:16:27 - INFO - __main__ - Step 89128: {'lr': 0.00018123634044137722, 'samples': 17112576, 'steps': 89127, 'loss/train': 0.9156466722488403} 08/31/2021 05:16:27 - INFO - __main__ - Step 89129: {'lr': 0.00018123123840110023, 'samples': 17112768, 'steps': 89128, 'loss/train': 1.553799033164978} 08/31/2021 05:16:27 - INFO - __main__ - Step 89130: {'lr': 0.0001812261363918095, 'samples': 17112960, 'steps': 89129, 'loss/train': 1.4032567739486694} 08/31/2021 05:16:28 - INFO - __main__ - Step 89131: {'lr': 0.00018122103441350706, 'samples': 17113152, 'steps': 89130, 'loss/train': 2.422693967819214} 08/31/2021 05:16:28 - INFO - __main__ - Step 89132: {'lr': 0.00018121593246619544, 'samples': 17113344, 'steps': 89131, 'loss/train': 0.8915297985076904} 08/31/2021 05:16:29 - INFO - __main__ - Step 89133: {'lr': 0.0001812108305498768, 'samples': 17113536, 'steps': 89132, 'loss/train': 1.1342982053756714} 08/31/2021 05:16:30 - INFO - __main__ - Step 89134: {'lr': 0.0001812057286645535, 'samples': 17113728, 'steps': 89133, 'loss/train': 0.9267929792404175} 08/31/2021 05:16:30 - INFO - __main__ - Step 89135: {'lr': 0.00018120062681022787, 'samples': 17113920, 'steps': 89134, 'loss/train': 1.2735743522644043} 08/31/2021 05:16:31 - INFO - __main__ - Step 89136: {'lr': 0.00018119552498690214, 'samples': 17114112, 'steps': 89135, 'loss/train': 0.4497835636138916} 08/31/2021 05:16:31 - INFO - __main__ - Step 89137: {'lr': 0.00018119042319457868, 'samples': 17114304, 'steps': 89136, 'loss/train': 0.8713930249214172} 08/31/2021 05:16:33 - INFO - __main__ - Step 89138: {'lr': 0.00018118532143325972, 'samples': 17114496, 'steps': 89137, 'loss/train': 1.6616305112838745} 08/31/2021 05:16:33 - INFO - __main__ - Step 89139: {'lr': 0.00018118021970294762, 'samples': 17114688, 'steps': 89138, 'loss/train': 0.706882655620575} 08/31/2021 05:16:33 - INFO - __main__ - Step 89140: {'lr': 0.00018117511800364462, 'samples': 17114880, 'steps': 89139, 'loss/train': 0.6847748160362244} 08/31/2021 05:16:34 - INFO - __main__ - Step 89141: {'lr': 0.00018117001633535308, 'samples': 17115072, 'steps': 89140, 'loss/train': 1.0743721723556519} 08/31/2021 05:16:34 - INFO - __main__ - Step 89142: {'lr': 0.00018116491469807525, 'samples': 17115264, 'steps': 89141, 'loss/train': 1.352509617805481} 08/31/2021 05:16:36 - INFO - __main__ - Step 89143: {'lr': 0.00018115981309181346, 'samples': 17115456, 'steps': 89142, 'loss/train': 1.2023550271987915} 08/31/2021 05:16:36 - INFO - __main__ - Step 89144: {'lr': 0.0001811547115165701, 'samples': 17115648, 'steps': 89143, 'loss/train': 1.534180998802185} 08/31/2021 05:16:36 - INFO - __main__ - Step 89145: {'lr': 0.00018114960997234726, 'samples': 17115840, 'steps': 89144, 'loss/train': 0.766410231590271} 08/31/2021 05:16:37 - INFO - __main__ - Step 89146: {'lr': 0.00018114450845914732, 'samples': 17116032, 'steps': 89145, 'loss/train': 1.3861111402511597} 08/31/2021 05:16:37 - INFO - __main__ - Step 89147: {'lr': 0.00018113940697697263, 'samples': 17116224, 'steps': 89146, 'loss/train': 1.0241752862930298} 08/31/2021 05:16:39 - INFO - __main__ - Step 89148: {'lr': 0.00018113430552582543, 'samples': 17116416, 'steps': 89147, 'loss/train': 0.7047937512397766} 08/31/2021 05:16:39 - INFO - __main__ - Step 89149: {'lr': 0.00018112920410570806, 'samples': 17116608, 'steps': 89148, 'loss/train': 1.0765588283538818} 08/31/2021 05:16:39 - INFO - __main__ - Step 89150: {'lr': 0.00018112410271662284, 'samples': 17116800, 'steps': 89149, 'loss/train': 1.2450628280639648} 08/31/2021 05:16:40 - INFO - __main__ - Step 89151: {'lr': 0.000181119001358572, 'samples': 17116992, 'steps': 89150, 'loss/train': 1.7049696445465088} 08/31/2021 05:16:40 - INFO - __main__ - Step 89152: {'lr': 0.00018111390003155788, 'samples': 17117184, 'steps': 89151, 'loss/train': 1.0789340734481812} 08/31/2021 05:16:42 - INFO - __main__ - Step 89153: {'lr': 0.00018110879873558278, 'samples': 17117376, 'steps': 89152, 'loss/train': 0.7281062602996826} 08/31/2021 05:16:43 - INFO - __main__ - Step 89154: {'lr': 0.000181103697470649, 'samples': 17117568, 'steps': 89153, 'loss/train': 1.769575834274292} 08/31/2021 05:16:43 - INFO - __main__ - Step 89155: {'lr': 0.00018109859623675884, 'samples': 17117760, 'steps': 89154, 'loss/train': 0.935334324836731} 08/31/2021 05:16:43 - INFO - __main__ - Step 89156: {'lr': 0.00018109349503391456, 'samples': 17117952, 'steps': 89155, 'loss/train': 1.0837039947509766} 08/31/2021 05:16:44 - INFO - __main__ - Step 89157: {'lr': 0.0001810883938621186, 'samples': 17118144, 'steps': 89156, 'loss/train': 1.2090431451797485} 08/31/2021 05:16:45 - INFO - __main__ - Step 89158: {'lr': 0.0001810832927213731, 'samples': 17118336, 'steps': 89157, 'loss/train': 0.9175284504890442} 08/31/2021 05:16:46 - INFO - __main__ - Step 89159: {'lr': 0.00018107819161168032, 'samples': 17118528, 'steps': 89158, 'loss/train': 0.6440255641937256} 08/31/2021 05:16:46 - INFO - __main__ - Step 89160: {'lr': 0.00018107309053304267, 'samples': 17118720, 'steps': 89159, 'loss/train': 1.6155563592910767} 08/31/2021 05:16:46 - INFO - __main__ - Step 89161: {'lr': 0.00018106798948546243, 'samples': 17118912, 'steps': 89160, 'loss/train': 1.4006882905960083} 08/31/2021 05:16:47 - INFO - __main__ - Step 89162: {'lr': 0.0001810628884689419, 'samples': 17119104, 'steps': 89161, 'loss/train': 0.9417176842689514} 08/31/2021 05:16:49 - INFO - __main__ - Step 89163: {'lr': 0.00018105778748348333, 'samples': 17119296, 'steps': 89162, 'loss/train': 1.191951870918274} 08/31/2021 05:16:49 - INFO - __main__ - Step 89164: {'lr': 0.0001810526865290891, 'samples': 17119488, 'steps': 89163, 'loss/train': 1.9376208782196045} 08/31/2021 05:16:49 - INFO - __main__ - Step 89165: {'lr': 0.00018104758560576146, 'samples': 17119680, 'steps': 89164, 'loss/train': 0.3942842483520508} 08/31/2021 05:16:50 - INFO - __main__ - Step 89166: {'lr': 0.0001810424847135027, 'samples': 17119872, 'steps': 89165, 'loss/train': 1.798172116279602} 08/31/2021 05:16:50 - INFO - __main__ - Step 89167: {'lr': 0.00018103738385231514, 'samples': 17120064, 'steps': 89166, 'loss/train': 0.7961907982826233} 08/31/2021 05:16:51 - INFO - __main__ - Step 89168: {'lr': 0.00018103228302220108, 'samples': 17120256, 'steps': 89167, 'loss/train': 1.034618854522705} 08/31/2021 05:16:51 - INFO - __main__ - Step 89169: {'lr': 0.00018102718222316277, 'samples': 17120448, 'steps': 89168, 'loss/train': 1.539513349533081} 08/31/2021 05:16:52 - INFO - __main__ - Step 89170: {'lr': 0.00018102208145520258, 'samples': 17120640, 'steps': 89169, 'loss/train': 0.5496383309364319} 08/31/2021 05:16:53 - INFO - __main__ - Step 89171: {'lr': 0.00018101698071832287, 'samples': 17120832, 'steps': 89170, 'loss/train': 0.8641846776008606} 08/31/2021 05:16:53 - INFO - __main__ - Step 89172: {'lr': 0.00018101188001252576, 'samples': 17121024, 'steps': 89171, 'loss/train': 0.1778487265110016} 08/31/2021 05:16:53 - INFO - __main__ - Step 89173: {'lr': 0.00018100677933781362, 'samples': 17121216, 'steps': 89172, 'loss/train': 1.4726266860961914} 08/31/2021 05:16:54 - INFO - __main__ - Step 89174: {'lr': 0.00018100167869418874, 'samples': 17121408, 'steps': 89173, 'loss/train': 0.3841724693775177} 08/31/2021 05:16:55 - INFO - __main__ - Step 89175: {'lr': 0.00018099657808165346, 'samples': 17121600, 'steps': 89174, 'loss/train': 1.1930385828018188} 08/31/2021 05:16:56 - INFO - __main__ - Step 89176: {'lr': 0.00018099147750021006, 'samples': 17121792, 'steps': 89175, 'loss/train': 1.151142954826355} 08/31/2021 05:16:56 - INFO - __main__ - Step 89177: {'lr': 0.00018098637694986082, 'samples': 17121984, 'steps': 89176, 'loss/train': 1.4610669612884521} 08/31/2021 05:16:56 - INFO - __main__ - Step 89178: {'lr': 0.00018098127643060804, 'samples': 17122176, 'steps': 89177, 'loss/train': 0.802544116973877} 08/31/2021 05:16:57 - INFO - __main__ - Step 89179: {'lr': 0.00018097617594245408, 'samples': 17122368, 'steps': 89178, 'loss/train': 1.2890411615371704} 08/31/2021 05:16:58 - INFO - __main__ - Step 89180: {'lr': 0.00018097107548540115, 'samples': 17122560, 'steps': 89179, 'loss/train': 1.2792644500732422} 08/31/2021 05:16:59 - INFO - __main__ - Step 89181: {'lr': 0.0001809659750594516, 'samples': 17122752, 'steps': 89180, 'loss/train': 1.8347138166427612} 08/31/2021 05:16:59 - INFO - __main__ - Step 89182: {'lr': 0.0001809608746646077, 'samples': 17122944, 'steps': 89181, 'loss/train': 0.4961671233177185} 08/31/2021 05:16:59 - INFO - __main__ - Step 89183: {'lr': 0.00018095577430087185, 'samples': 17123136, 'steps': 89182, 'loss/train': 1.0483475923538208} 08/31/2021 05:17:00 - INFO - __main__ - Step 89184: {'lr': 0.00018095067396824626, 'samples': 17123328, 'steps': 89183, 'loss/train': 0.9565391540527344} 08/31/2021 05:17:01 - INFO - __main__ - Step 89185: {'lr': 0.00018094557366673313, 'samples': 17123520, 'steps': 89184, 'loss/train': 1.4632563591003418} 08/31/2021 05:17:02 - INFO - __main__ - Step 89186: {'lr': 0.0001809404733963349, 'samples': 17123712, 'steps': 89185, 'loss/train': 1.1973474025726318} 08/31/2021 05:17:02 - INFO - __main__ - Step 89187: {'lr': 0.00018093537315705383, 'samples': 17123904, 'steps': 89186, 'loss/train': 1.1892379522323608} 08/31/2021 05:17:03 - INFO - __main__ - Step 89188: {'lr': 0.0001809302729488922, 'samples': 17124096, 'steps': 89187, 'loss/train': 1.3476247787475586} 08/31/2021 05:17:03 - INFO - __main__ - Step 89189: {'lr': 0.00018092517277185232, 'samples': 17124288, 'steps': 89188, 'loss/train': 1.3617818355560303} 08/31/2021 05:17:03 - INFO - __main__ - Step 89190: {'lr': 0.0001809200726259365, 'samples': 17124480, 'steps': 89189, 'loss/train': 0.9424638152122498} 08/31/2021 05:17:05 - INFO - __main__ - Step 89191: {'lr': 0.0001809149725111471, 'samples': 17124672, 'steps': 89190, 'loss/train': 0.5616836547851562} 08/31/2021 05:17:05 - INFO - __main__ - Step 89192: {'lr': 0.00018090987242748625, 'samples': 17124864, 'steps': 89191, 'loss/train': 1.0948909521102905} 08/31/2021 05:17:06 - INFO - __main__ - Step 89193: {'lr': 0.00018090477237495638, 'samples': 17125056, 'steps': 89192, 'loss/train': 1.2717070579528809} 08/31/2021 05:17:06 - INFO - __main__ - Step 89194: {'lr': 0.00018089967235355978, 'samples': 17125248, 'steps': 89193, 'loss/train': 1.906477689743042} 08/31/2021 05:17:07 - INFO - __main__ - Step 89195: {'lr': 0.0001808945723632987, 'samples': 17125440, 'steps': 89194, 'loss/train': 0.5230347514152527} 08/31/2021 05:17:08 - INFO - __main__ - Step 89196: {'lr': 0.00018088947240417545, 'samples': 17125632, 'steps': 89195, 'loss/train': 1.0779550075531006} 08/31/2021 05:17:08 - INFO - __main__ - Step 89197: {'lr': 0.00018088437247619233, 'samples': 17125824, 'steps': 89196, 'loss/train': 0.9954699277877808} 08/31/2021 05:17:09 - INFO - __main__ - Step 89198: {'lr': 0.0001808792725793517, 'samples': 17126016, 'steps': 89197, 'loss/train': 1.0026956796646118} 08/31/2021 05:17:09 - INFO - __main__ - Step 89199: {'lr': 0.00018087417271365574, 'samples': 17126208, 'steps': 89198, 'loss/train': 1.346908688545227} 08/31/2021 05:17:10 - INFO - __main__ - Step 89200: {'lr': 0.0001808690728791068, 'samples': 17126400, 'steps': 89199, 'loss/train': 0.1603405773639679} 08/31/2021 05:17:11 - INFO - __main__ - Step 89201: {'lr': 0.00018086397307570724, 'samples': 17126592, 'steps': 89200, 'loss/train': 0.7863248586654663} 08/31/2021 05:17:12 - INFO - __main__ - Step 89202: {'lr': 0.0001808588733034593, 'samples': 17126784, 'steps': 89201, 'loss/train': 0.24779827892780304} 08/31/2021 05:17:12 - INFO - __main__ - Step 89203: {'lr': 0.00018085377356236526, 'samples': 17126976, 'steps': 89202, 'loss/train': 1.7807071208953857} 08/31/2021 05:17:12 - INFO - __main__ - Step 89204: {'lr': 0.00018084867385242742, 'samples': 17127168, 'steps': 89203, 'loss/train': 1.1514450311660767} 08/31/2021 05:17:13 - INFO - __main__ - Step 89205: {'lr': 0.0001808435741736482, 'samples': 17127360, 'steps': 89204, 'loss/train': 1.1154536008834839} 08/31/2021 05:17:15 - INFO - __main__ - Step 89206: {'lr': 0.00018083847452602972, 'samples': 17127552, 'steps': 89205, 'loss/train': 1.759871006011963} 08/31/2021 05:17:15 - INFO - __main__ - Step 89207: {'lr': 0.00018083337490957437, 'samples': 17127744, 'steps': 89206, 'loss/train': 0.5174328684806824} 08/31/2021 05:17:16 - INFO - __main__ - Step 89208: {'lr': 0.00018082827532428443, 'samples': 17127936, 'steps': 89207, 'loss/train': 0.5542557239532471} 08/31/2021 05:17:16 - INFO - __main__ - Step 89209: {'lr': 0.0001808231757701622, 'samples': 17128128, 'steps': 89208, 'loss/train': 0.9259899854660034} 08/31/2021 05:17:16 - INFO - __main__ - Step 89210: {'lr': 0.00018081807624720998, 'samples': 17128320, 'steps': 89209, 'loss/train': 0.7831102609634399} 08/31/2021 05:17:17 - INFO - __main__ - Step 89211: {'lr': 0.0001808129767554301, 'samples': 17128512, 'steps': 89210, 'loss/train': 1.588718056678772} 08/31/2021 05:17:18 - INFO - __main__ - Step 89212: {'lr': 0.0001808078772948248, 'samples': 17128704, 'steps': 89211, 'loss/train': 0.574012279510498} 08/31/2021 05:17:19 - INFO - __main__ - Step 89213: {'lr': 0.0001808027778653964, 'samples': 17128896, 'steps': 89212, 'loss/train': 1.336372971534729} 08/31/2021 05:17:19 - INFO - __main__ - Step 89214: {'lr': 0.00018079767846714717, 'samples': 17129088, 'steps': 89213, 'loss/train': 1.5192720890045166} 08/31/2021 05:17:20 - INFO - __main__ - Step 89215: {'lr': 0.00018079257910007945, 'samples': 17129280, 'steps': 89214, 'loss/train': 1.5017138719558716} 08/31/2021 05:17:20 - INFO - __main__ - Step 89216: {'lr': 0.00018078747976419562, 'samples': 17129472, 'steps': 89215, 'loss/train': 1.3362340927124023} 08/31/2021 05:17:21 - INFO - __main__ - Step 89217: {'lr': 0.0001807823804594978, 'samples': 17129664, 'steps': 89216, 'loss/train': 0.7837679982185364} 08/31/2021 05:17:22 - INFO - __main__ - Step 89218: {'lr': 0.00018077728118598836, 'samples': 17129856, 'steps': 89217, 'loss/train': 0.14204463362693787} 08/31/2021 05:17:22 - INFO - __main__ - Step 89219: {'lr': 0.00018077218194366963, 'samples': 17130048, 'steps': 89218, 'loss/train': 0.7804165482521057} 08/31/2021 05:17:23 - INFO - __main__ - Step 89220: {'lr': 0.00018076708273254388, 'samples': 17130240, 'steps': 89219, 'loss/train': 1.202527403831482} 08/31/2021 05:17:23 - INFO - __main__ - Step 89221: {'lr': 0.00018076198355261342, 'samples': 17130432, 'steps': 89220, 'loss/train': 0.9220773577690125} 08/31/2021 05:17:24 - INFO - __main__ - Step 89222: {'lr': 0.00018075688440388052, 'samples': 17130624, 'steps': 89221, 'loss/train': 1.432171106338501} 08/31/2021 05:17:25 - INFO - __main__ - Step 89223: {'lr': 0.0001807517852863475, 'samples': 17130816, 'steps': 89222, 'loss/train': 0.9453957676887512} 08/31/2021 05:17:25 - INFO - __main__ - Step 89224: {'lr': 0.00018074668620001672, 'samples': 17131008, 'steps': 89223, 'loss/train': 0.311640202999115} 08/31/2021 05:17:26 - INFO - __main__ - Step 89225: {'lr': 0.00018074158714489037, 'samples': 17131200, 'steps': 89224, 'loss/train': 0.4375126361846924} 08/31/2021 05:17:26 - INFO - __main__ - Step 89226: {'lr': 0.00018073648812097086, 'samples': 17131392, 'steps': 89225, 'loss/train': 1.7486379146575928} 08/31/2021 05:17:26 - INFO - __main__ - Step 89227: {'lr': 0.00018073138912826032, 'samples': 17131584, 'steps': 89226, 'loss/train': 1.344899296760559} 08/31/2021 05:17:28 - INFO - __main__ - Step 89228: {'lr': 0.00018072629016676117, 'samples': 17131776, 'steps': 89227, 'loss/train': 0.7640872001647949} 08/31/2021 05:17:28 - INFO - __main__ - Step 89229: {'lr': 0.00018072119123647572, 'samples': 17131968, 'steps': 89228, 'loss/train': 1.2454477548599243} 08/31/2021 05:17:28 - INFO - __main__ - Step 89230: {'lr': 0.00018071609233740618, 'samples': 17132160, 'steps': 89229, 'loss/train': 1.0079412460327148} 08/31/2021 05:17:29 - INFO - __main__ - Step 89231: {'lr': 0.00018071099346955494, 'samples': 17132352, 'steps': 89230, 'loss/train': 1.123243808746338} 08/31/2021 05:17:29 - INFO - __main__ - Step 89232: {'lr': 0.00018070589463292422, 'samples': 17132544, 'steps': 89231, 'loss/train': 1.506133794784546} 08/31/2021 05:17:31 - INFO - __main__ - Step 89233: {'lr': 0.00018070079582751636, 'samples': 17132736, 'steps': 89232, 'loss/train': 0.7506524920463562} 08/31/2021 05:17:31 - INFO - __main__ - Step 89234: {'lr': 0.00018069569705333365, 'samples': 17132928, 'steps': 89233, 'loss/train': 0.9262365698814392} 08/31/2021 05:17:32 - INFO - __main__ - Step 89235: {'lr': 0.00018069059831037843, 'samples': 17133120, 'steps': 89234, 'loss/train': 1.3427834510803223} 08/31/2021 05:17:32 - INFO - __main__ - Step 89236: {'lr': 0.00018068549959865293, 'samples': 17133312, 'steps': 89235, 'loss/train': 0.4054630994796753} 08/31/2021 05:17:32 - INFO - __main__ - Step 89237: {'lr': 0.00018068040091815947, 'samples': 17133504, 'steps': 89236, 'loss/train': 1.642588496208191} 08/31/2021 05:17:34 - INFO - __main__ - Step 89238: {'lr': 0.00018067530226890046, 'samples': 17133696, 'steps': 89237, 'loss/train': 1.3553045988082886} 08/31/2021 05:17:34 - INFO - __main__ - Step 89239: {'lr': 0.000180670203650878, 'samples': 17133888, 'steps': 89238, 'loss/train': 0.9127393960952759} 08/31/2021 05:17:35 - INFO - __main__ - Step 89240: {'lr': 0.00018066510506409446, 'samples': 17134080, 'steps': 89239, 'loss/train': 1.0476603507995605} 08/31/2021 05:17:35 - INFO - __main__ - Step 89241: {'lr': 0.00018066000650855213, 'samples': 17134272, 'steps': 89240, 'loss/train': 0.7932202219963074} 08/31/2021 05:17:35 - INFO - __main__ - Step 89242: {'lr': 0.00018065490798425339, 'samples': 17134464, 'steps': 89241, 'loss/train': 1.0171843767166138} 08/31/2021 05:17:37 - INFO - __main__ - Step 89243: {'lr': 0.0001806498094912004, 'samples': 17134656, 'steps': 89242, 'loss/train': 1.0429631471633911} 08/31/2021 05:17:37 - INFO - __main__ - Step 89244: {'lr': 0.0001806447110293956, 'samples': 17134848, 'steps': 89243, 'loss/train': 1.2043251991271973} 08/31/2021 05:17:38 - INFO - __main__ - Step 89245: {'lr': 0.00018063961259884122, 'samples': 17135040, 'steps': 89244, 'loss/train': 1.733673095703125} 08/31/2021 05:17:38 - INFO - __main__ - Step 89246: {'lr': 0.00018063451419953952, 'samples': 17135232, 'steps': 89245, 'loss/train': 0.951189398765564} 08/31/2021 05:17:38 - INFO - __main__ - Step 89247: {'lr': 0.0001806294158314929, 'samples': 17135424, 'steps': 89246, 'loss/train': 1.1469252109527588} 08/31/2021 05:17:40 - INFO - __main__ - Step 89248: {'lr': 0.00018062431749470354, 'samples': 17135616, 'steps': 89247, 'loss/train': 1.313392996788025} 08/31/2021 05:17:40 - INFO - __main__ - Step 89249: {'lr': 0.00018061921918917378, 'samples': 17135808, 'steps': 89248, 'loss/train': 0.8194369673728943} 08/31/2021 05:17:41 - INFO - __main__ - Step 89250: {'lr': 0.00018061412091490597, 'samples': 17136000, 'steps': 89249, 'loss/train': 1.5105886459350586} 08/31/2021 05:17:41 - INFO - __main__ - Step 89251: {'lr': 0.0001806090226719025, 'samples': 17136192, 'steps': 89250, 'loss/train': 1.4120100736618042} 08/31/2021 05:17:41 - INFO - __main__ - Step 89252: {'lr': 0.00018060392446016537, 'samples': 17136384, 'steps': 89251, 'loss/train': 1.0198311805725098} 08/31/2021 05:17:43 - INFO - __main__ - Step 89253: {'lr': 0.00018059882627969703, 'samples': 17136576, 'steps': 89252, 'loss/train': 1.3545876741409302} 08/31/2021 05:17:43 - INFO - __main__ - Step 89254: {'lr': 0.00018059372813049985, 'samples': 17136768, 'steps': 89253, 'loss/train': 1.5746029615402222} 08/31/2021 05:17:44 - INFO - __main__ - Step 89255: {'lr': 0.00018058863001257602, 'samples': 17136960, 'steps': 89254, 'loss/train': 1.1265794038772583} 08/31/2021 05:17:44 - INFO - __main__ - Step 89256: {'lr': 0.0001805835319259279, 'samples': 17137152, 'steps': 89255, 'loss/train': 1.2081377506256104} 08/31/2021 05:17:44 - INFO - __main__ - Step 89257: {'lr': 0.00018057843387055776, 'samples': 17137344, 'steps': 89256, 'loss/train': 0.9851383566856384} 08/31/2021 05:17:46 - INFO - __main__ - Step 89258: {'lr': 0.0001805733358464679, 'samples': 17137536, 'steps': 89257, 'loss/train': 0.7330259680747986} 08/31/2021 05:17:46 - INFO - __main__ - Step 89259: {'lr': 0.00018056823785366063, 'samples': 17137728, 'steps': 89258, 'loss/train': 0.7981858253479004} 08/31/2021 05:17:47 - INFO - __main__ - Step 89260: {'lr': 0.00018056313989213825, 'samples': 17137920, 'steps': 89259, 'loss/train': 1.162850260734558} 08/31/2021 05:17:47 - INFO - __main__ - Step 89261: {'lr': 0.00018055804196190304, 'samples': 17138112, 'steps': 89260, 'loss/train': 0.062063366174697876} 08/31/2021 05:17:47 - INFO - __main__ - Step 89262: {'lr': 0.00018055294406295731, 'samples': 17138304, 'steps': 89261, 'loss/train': 0.9884238243103027} 08/31/2021 05:17:50 - INFO - __main__ - Step 89263: {'lr': 0.00018054784619530334, 'samples': 17138496, 'steps': 89262, 'loss/train': 1.1564314365386963} 08/31/2021 05:17:50 - INFO - __main__ - Step 89264: {'lr': 0.00018054274835894345, 'samples': 17138688, 'steps': 89263, 'loss/train': 1.4676165580749512} 08/31/2021 05:17:51 - INFO - __main__ - Step 89265: {'lr': 0.00018053765055388004, 'samples': 17138880, 'steps': 89264, 'loss/train': 0.04931225627660751} 08/31/2021 05:17:51 - INFO - __main__ - Step 89266: {'lr': 0.00018053255278011515, 'samples': 17139072, 'steps': 89265, 'loss/train': 1.3875861167907715} 08/31/2021 05:17:51 - INFO - __main__ - Step 89267: {'lr': 0.00018052745503765124, 'samples': 17139264, 'steps': 89266, 'loss/train': 0.9248291850090027} 08/31/2021 05:17:53 - INFO - __main__ - Step 89268: {'lr': 0.0001805223573264906, 'samples': 17139456, 'steps': 89267, 'loss/train': 1.3101273775100708} 08/31/2021 05:17:53 - INFO - __main__ - Step 89269: {'lr': 0.0001805172596466355, 'samples': 17139648, 'steps': 89268, 'loss/train': 1.1391505002975464} 08/31/2021 05:17:54 - INFO - __main__ - Step 89270: {'lr': 0.00018051216199808828, 'samples': 17139840, 'steps': 89269, 'loss/train': 1.155965805053711} 08/31/2021 05:17:54 - INFO - __main__ - Step 89271: {'lr': 0.00018050706438085118, 'samples': 17140032, 'steps': 89270, 'loss/train': 1.1579631567001343} 08/31/2021 05:17:54 - INFO - __main__ - Step 89272: {'lr': 0.00018050196679492654, 'samples': 17140224, 'steps': 89271, 'loss/train': 1.2164702415466309} 08/31/2021 05:17:56 - INFO - __main__ - Step 89273: {'lr': 0.0001804968692403166, 'samples': 17140416, 'steps': 89272, 'loss/train': 0.902221143245697} 08/31/2021 05:17:56 - INFO - __main__ - Step 89274: {'lr': 0.00018049177171702374, 'samples': 17140608, 'steps': 89273, 'loss/train': 0.5303767323493958} 08/31/2021 05:17:57 - INFO - __main__ - Step 89275: {'lr': 0.0001804866742250502, 'samples': 17140800, 'steps': 89274, 'loss/train': 0.8637574911117554} 08/31/2021 05:17:57 - INFO - __main__ - Step 89276: {'lr': 0.0001804815767643983, 'samples': 17140992, 'steps': 89275, 'loss/train': 1.1650445461273193} 08/31/2021 05:17:57 - INFO - __main__ - Step 89277: {'lr': 0.00018047647933507033, 'samples': 17141184, 'steps': 89276, 'loss/train': 1.2268174886703491} 08/31/2021 05:17:58 - INFO - __main__ - Step 89278: {'lr': 0.0001804713819370687, 'samples': 17141376, 'steps': 89277, 'loss/train': 0.5857293605804443} 08/31/2021 05:17:59 - INFO - __main__ - Step 89279: {'lr': 0.00018046628457039544, 'samples': 17141568, 'steps': 89278, 'loss/train': 0.043318748474121094} 08/31/2021 05:18:00 - INFO - __main__ - Step 89280: {'lr': 0.00018046118723505304, 'samples': 17141760, 'steps': 89279, 'loss/train': 1.3216336965560913} 08/31/2021 05:18:00 - INFO - __main__ - Step 89281: {'lr': 0.00018045608993104374, 'samples': 17141952, 'steps': 89280, 'loss/train': 1.2952152490615845} 08/31/2021 05:18:00 - INFO - __main__ - Step 89282: {'lr': 0.00018045099265836983, 'samples': 17142144, 'steps': 89281, 'loss/train': 1.4075062274932861} 08/31/2021 05:18:01 - INFO - __main__ - Step 89283: {'lr': 0.00018044589541703368, 'samples': 17142336, 'steps': 89282, 'loss/train': 0.8836895227432251} 08/31/2021 05:18:02 - INFO - __main__ - Step 89284: {'lr': 0.00018044079820703752, 'samples': 17142528, 'steps': 89283, 'loss/train': 0.9729380011558533} 08/31/2021 05:18:03 - INFO - __main__ - Step 89285: {'lr': 0.00018043570102838367, 'samples': 17142720, 'steps': 89284, 'loss/train': 1.0951783657073975} 08/31/2021 05:18:03 - INFO - __main__ - Step 89286: {'lr': 0.0001804306038810744, 'samples': 17142912, 'steps': 89285, 'loss/train': 1.1694211959838867} 08/31/2021 05:18:03 - INFO - __main__ - Step 89287: {'lr': 0.00018042550676511206, 'samples': 17143104, 'steps': 89286, 'loss/train': 0.9963874220848083} 08/31/2021 05:18:04 - INFO - __main__ - Step 89288: {'lr': 0.00018042040968049885, 'samples': 17143296, 'steps': 89287, 'loss/train': 0.3821960687637329} 08/31/2021 05:18:05 - INFO - __main__ - Step 89289: {'lr': 0.00018041531262723718, 'samples': 17143488, 'steps': 89288, 'loss/train': 0.8673788905143738} 08/31/2021 05:18:06 - INFO - __main__ - Step 89290: {'lr': 0.0001804102156053293, 'samples': 17143680, 'steps': 89289, 'loss/train': 0.9390000700950623} 08/31/2021 05:18:06 - INFO - __main__ - Step 89291: {'lr': 0.00018040511861477747, 'samples': 17143872, 'steps': 89290, 'loss/train': 1.0912766456604004} 08/31/2021 05:18:06 - INFO - __main__ - Step 89292: {'lr': 0.00018040002165558414, 'samples': 17144064, 'steps': 89291, 'loss/train': 1.70343017578125} 08/31/2021 05:18:07 - INFO - __main__ - Step 89293: {'lr': 0.00018039492472775138, 'samples': 17144256, 'steps': 89292, 'loss/train': 1.150412917137146} 08/31/2021 05:18:08 - INFO - __main__ - Step 89294: {'lr': 0.00018038982783128162, 'samples': 17144448, 'steps': 89293, 'loss/train': 1.4271016120910645} 08/31/2021 05:18:09 - INFO - __main__ - Step 89295: {'lr': 0.00018038473096617709, 'samples': 17144640, 'steps': 89294, 'loss/train': 0.537250280380249} 08/31/2021 05:18:09 - INFO - __main__ - Step 89296: {'lr': 0.00018037963413244012, 'samples': 17144832, 'steps': 89295, 'loss/train': 0.8954921960830688} 08/31/2021 05:18:10 - INFO - __main__ - Step 89297: {'lr': 0.00018037453733007303, 'samples': 17145024, 'steps': 89296, 'loss/train': 1.2944201231002808} 08/31/2021 05:18:10 - INFO - __main__ - Step 89298: {'lr': 0.00018036944055907812, 'samples': 17145216, 'steps': 89297, 'loss/train': 0.5061538815498352} 08/31/2021 05:18:11 - INFO - __main__ - Step 89299: {'lr': 0.00018036434381945766, 'samples': 17145408, 'steps': 89298, 'loss/train': 1.1224886178970337} 08/31/2021 05:18:12 - INFO - __main__ - Step 89300: {'lr': 0.00018035924711121392, 'samples': 17145600, 'steps': 89299, 'loss/train': 1.4205118417739868} 08/31/2021 05:18:12 - INFO - __main__ - Step 89301: {'lr': 0.00018035415043434925, 'samples': 17145792, 'steps': 89300, 'loss/train': 1.0375778675079346} 08/31/2021 05:18:12 - INFO - __main__ - Step 89302: {'lr': 0.0001803490537888659, 'samples': 17145984, 'steps': 89301, 'loss/train': 1.4926173686981201} 08/31/2021 05:18:13 - INFO - __main__ - Step 89303: {'lr': 0.00018034395717476622, 'samples': 17146176, 'steps': 89302, 'loss/train': 1.4255716800689697} 08/31/2021 05:18:15 - INFO - __main__ - Step 89304: {'lr': 0.00018033886059205248, 'samples': 17146368, 'steps': 89303, 'loss/train': 0.7528828382492065} 08/31/2021 05:18:15 - INFO - __main__ - Step 89305: {'lr': 0.0001803337640407271, 'samples': 17146560, 'steps': 89304, 'loss/train': 1.1372909545898438} 08/31/2021 05:18:15 - INFO - __main__ - Step 89306: {'lr': 0.0001803286675207921, 'samples': 17146752, 'steps': 89305, 'loss/train': 1.0290688276290894} 08/31/2021 05:18:16 - INFO - __main__ - Step 89307: {'lr': 0.00018032357103224994, 'samples': 17146944, 'steps': 89306, 'loss/train': 1.1399250030517578} 08/31/2021 05:18:16 - INFO - __main__ - Step 89308: {'lr': 0.0001803184745751029, 'samples': 17147136, 'steps': 89307, 'loss/train': 1.191898226737976} 08/31/2021 05:18:16 - INFO - __main__ - Step 89309: {'lr': 0.0001803133781493533, 'samples': 17147328, 'steps': 89308, 'loss/train': 0.8720194697380066} 08/31/2021 05:18:18 - INFO - __main__ - Step 89310: {'lr': 0.00018030828175500342, 'samples': 17147520, 'steps': 89309, 'loss/train': 1.6723846197128296} 08/31/2021 05:18:18 - INFO - __main__ - Step 89311: {'lr': 0.00018030318539205553, 'samples': 17147712, 'steps': 89310, 'loss/train': 1.7957948446273804} 08/31/2021 05:18:19 - INFO - __main__ - Step 89312: {'lr': 0.00018029808906051196, 'samples': 17147904, 'steps': 89311, 'loss/train': 1.524009346961975} 08/31/2021 05:18:19 - INFO - __main__ - Step 89313: {'lr': 0.00018029299276037497, 'samples': 17148096, 'steps': 89312, 'loss/train': 1.1533533334732056} 08/31/2021 05:18:19 - INFO - __main__ - Step 89314: {'lr': 0.00018028789649164693, 'samples': 17148288, 'steps': 89313, 'loss/train': 1.3893461227416992} 08/31/2021 05:18:21 - INFO - __main__ - Step 89315: {'lr': 0.00018028280025433007, 'samples': 17148480, 'steps': 89314, 'loss/train': 1.2643437385559082} 08/31/2021 05:18:22 - INFO - __main__ - Step 89316: {'lr': 0.0001802777040484267, 'samples': 17148672, 'steps': 89315, 'loss/train': 0.61710524559021} 08/31/2021 05:18:22 - INFO - __main__ - Step 89317: {'lr': 0.00018027260787393918, 'samples': 17148864, 'steps': 89316, 'loss/train': 0.894040584564209} 08/31/2021 05:18:23 - INFO - __main__ - Step 89318: {'lr': 0.00018026751173086966, 'samples': 17149056, 'steps': 89317, 'loss/train': 1.399841070175171} 08/31/2021 05:18:23 - INFO - __main__ - Step 89319: {'lr': 0.00018026241561922062, 'samples': 17149248, 'steps': 89318, 'loss/train': 1.8552148342132568} 08/31/2021 05:18:24 - INFO - __main__ - Step 89320: {'lr': 0.00018025731953899416, 'samples': 17149440, 'steps': 89319, 'loss/train': 0.8761206269264221} 08/31/2021 05:18:25 - INFO - __main__ - Step 89321: {'lr': 0.0001802522234901927, 'samples': 17149632, 'steps': 89320, 'loss/train': 1.3645814657211304} 08/31/2021 05:18:25 - INFO - __main__ - Step 89322: {'lr': 0.0001802471274728185, 'samples': 17149824, 'steps': 89321, 'loss/train': 1.036409616470337} 08/31/2021 05:18:26 - INFO - __main__ - Step 89323: {'lr': 0.0001802420314868739, 'samples': 17150016, 'steps': 89322, 'loss/train': 1.5974763631820679} 08/31/2021 05:18:26 - INFO - __main__ - Step 89324: {'lr': 0.00018023693553236115, 'samples': 17150208, 'steps': 89323, 'loss/train': 0.11857376992702484} 08/31/2021 05:18:28 - INFO - __main__ - Step 89325: {'lr': 0.0001802318396092826, 'samples': 17150400, 'steps': 89324, 'loss/train': 1.3536115884780884} 08/31/2021 05:18:28 - INFO - __main__ - Step 89326: {'lr': 0.00018022674371764042, 'samples': 17150592, 'steps': 89325, 'loss/train': 1.0961440801620483} 08/31/2021 05:18:28 - INFO - __main__ - Step 89327: {'lr': 0.00018022164785743704, 'samples': 17150784, 'steps': 89326, 'loss/train': 1.6502509117126465} 08/31/2021 05:18:29 - INFO - __main__ - Step 89328: {'lr': 0.00018021655202867478, 'samples': 17150976, 'steps': 89327, 'loss/train': 0.8393951058387756} 08/31/2021 05:18:29 - INFO - __main__ - Step 89329: {'lr': 0.00018021145623135575, 'samples': 17151168, 'steps': 89328, 'loss/train': 1.0500484704971313} 08/31/2021 05:18:29 - INFO - __main__ - Step 89330: {'lr': 0.00018020636046548244, 'samples': 17151360, 'steps': 89329, 'loss/train': 0.8789210319519043} 08/31/2021 05:18:31 - INFO - __main__ - Step 89331: {'lr': 0.000180201264731057, 'samples': 17151552, 'steps': 89330, 'loss/train': 0.501914381980896} 08/31/2021 05:18:31 - INFO - __main__ - Step 89332: {'lr': 0.0001801961690280819, 'samples': 17151744, 'steps': 89331, 'loss/train': 1.2154096364974976} 08/31/2021 05:18:32 - INFO - __main__ - Step 89333: {'lr': 0.00018019107335655925, 'samples': 17151936, 'steps': 89332, 'loss/train': 1.2956668138504028} 08/31/2021 05:18:32 - INFO - __main__ - Step 89334: {'lr': 0.00018018597771649142, 'samples': 17152128, 'steps': 89333, 'loss/train': 0.9099131226539612} 08/31/2021 05:18:32 - INFO - __main__ - Step 89335: {'lr': 0.00018018088210788072, 'samples': 17152320, 'steps': 89334, 'loss/train': 1.6122411489486694} 08/31/2021 05:18:34 - INFO - __main__ - Step 89336: {'lr': 0.00018017578653072944, 'samples': 17152512, 'steps': 89335, 'loss/train': 0.031698040664196014} 08/31/2021 05:18:34 - INFO - __main__ - Step 89337: {'lr': 0.00018017069098503986, 'samples': 17152704, 'steps': 89336, 'loss/train': 0.3153490126132965} 08/31/2021 05:18:35 - INFO - __main__ - Step 89338: {'lr': 0.0001801655954708143, 'samples': 17152896, 'steps': 89337, 'loss/train': 1.3432464599609375} 08/31/2021 05:18:35 - INFO - __main__ - Step 89339: {'lr': 0.00018016049998805512, 'samples': 17153088, 'steps': 89338, 'loss/train': 1.4881008863449097} 08/31/2021 05:18:35 - INFO - __main__ - Step 89340: {'lr': 0.00018015540453676442, 'samples': 17153280, 'steps': 89339, 'loss/train': 0.8849678635597229} 08/31/2021 05:18:37 - INFO - __main__ - Step 89341: {'lr': 0.00018015030911694468, 'samples': 17153472, 'steps': 89340, 'loss/train': 1.2342392206192017} 08/31/2021 05:18:38 - INFO - __main__ - Step 89342: {'lr': 0.0001801452137285981, 'samples': 17153664, 'steps': 89341, 'loss/train': 0.04671013727784157} 08/31/2021 05:18:38 - INFO - __main__ - Step 89343: {'lr': 0.00018014011837172702, 'samples': 17153856, 'steps': 89342, 'loss/train': 0.6817558407783508} 08/31/2021 05:18:38 - INFO - __main__ - Step 89344: {'lr': 0.00018013502304633372, 'samples': 17154048, 'steps': 89343, 'loss/train': 1.3765414953231812} 08/31/2021 05:18:39 - INFO - __main__ - Step 89345: {'lr': 0.00018012992775242058, 'samples': 17154240, 'steps': 89344, 'loss/train': 1.7002002000808716} 08/31/2021 05:18:40 - INFO - __main__ - Step 89346: {'lr': 0.00018012483248998974, 'samples': 17154432, 'steps': 89345, 'loss/train': 1.0514293909072876} 08/31/2021 05:18:41 - INFO - __main__ - Step 89347: {'lr': 0.00018011973725904357, 'samples': 17154624, 'steps': 89346, 'loss/train': 1.1029261350631714} 08/31/2021 05:18:41 - INFO - __main__ - Step 89348: {'lr': 0.0001801146420595844, 'samples': 17154816, 'steps': 89347, 'loss/train': 1.180573582649231} 08/31/2021 05:18:41 - INFO - __main__ - Step 89349: {'lr': 0.00018010954689161445, 'samples': 17155008, 'steps': 89348, 'loss/train': 0.8798718452453613} 08/31/2021 05:18:42 - INFO - __main__ - Step 89350: {'lr': 0.00018010445175513612, 'samples': 17155200, 'steps': 89349, 'loss/train': 1.428399682044983} 08/31/2021 05:18:43 - INFO - __main__ - Step 89351: {'lr': 0.0001800993566501516, 'samples': 17155392, 'steps': 89350, 'loss/train': 0.7111440300941467} 08/31/2021 05:18:43 - INFO - __main__ - Step 89352: {'lr': 0.00018009426157666324, 'samples': 17155584, 'steps': 89351, 'loss/train': 0.4546368718147278} 08/31/2021 05:18:44 - INFO - __main__ - Step 89353: {'lr': 0.00018008916653467334, 'samples': 17155776, 'steps': 89352, 'loss/train': 1.3264601230621338} 08/31/2021 05:18:44 - INFO - __main__ - Step 89354: {'lr': 0.00018008407152418415, 'samples': 17155968, 'steps': 89353, 'loss/train': 1.1063250303268433} 08/31/2021 05:18:44 - INFO - __main__ - Step 89355: {'lr': 0.000180078976545198, 'samples': 17156160, 'steps': 89354, 'loss/train': 1.910452127456665} 08/31/2021 05:18:46 - INFO - __main__ - Step 89356: {'lr': 0.00018007388159771721, 'samples': 17156352, 'steps': 89355, 'loss/train': 0.4141000807285309} 08/31/2021 05:18:46 - INFO - __main__ - Step 89357: {'lr': 0.00018006878668174402, 'samples': 17156544, 'steps': 89356, 'loss/train': 1.3013982772827148} 08/31/2021 05:18:47 - INFO - __main__ - Step 89358: {'lr': 0.00018006369179728078, 'samples': 17156736, 'steps': 89357, 'loss/train': 0.5323385000228882} 08/31/2021 05:18:47 - INFO - __main__ - Step 89359: {'lr': 0.0001800585969443298, 'samples': 17156928, 'steps': 89358, 'loss/train': 0.6930841207504272} 08/31/2021 05:18:47 - INFO - __main__ - Step 89360: {'lr': 0.0001800535021228933, 'samples': 17157120, 'steps': 89359, 'loss/train': 0.9327465891838074} 08/31/2021 05:18:49 - INFO - __main__ - Step 89361: {'lr': 0.00018004840733297365, 'samples': 17157312, 'steps': 89360, 'loss/train': 1.2002910375595093} 08/31/2021 05:18:49 - INFO - __main__ - Step 89362: {'lr': 0.00018004331257457306, 'samples': 17157504, 'steps': 89361, 'loss/train': 1.0273911952972412} 08/31/2021 05:18:50 - INFO - __main__ - Step 89363: {'lr': 0.00018003821784769386, 'samples': 17157696, 'steps': 89362, 'loss/train': 1.085848093032837} 08/31/2021 05:18:50 - INFO - __main__ - Step 89364: {'lr': 0.0001800331231523384, 'samples': 17157888, 'steps': 89363, 'loss/train': 1.0168017148971558} 08/31/2021 05:18:50 - INFO - __main__ - Step 89365: {'lr': 0.0001800280284885089, 'samples': 17158080, 'steps': 89364, 'loss/train': 1.2098687887191772} 08/31/2021 05:18:51 - INFO - __main__ - Step 89366: {'lr': 0.0001800229338562077, 'samples': 17158272, 'steps': 89365, 'loss/train': 1.4485496282577515} 08/31/2021 05:18:53 - INFO - __main__ - Step 89367: {'lr': 0.00018001783925543707, 'samples': 17158464, 'steps': 89366, 'loss/train': 1.8202251195907593} 08/31/2021 05:18:53 - INFO - __main__ - Step 89368: {'lr': 0.00018001274468619933, 'samples': 17158656, 'steps': 89367, 'loss/train': 1.4035454988479614} 08/31/2021 05:18:54 - INFO - __main__ - Step 89369: {'lr': 0.0001800076501484968, 'samples': 17158848, 'steps': 89368, 'loss/train': 0.9236470460891724} 08/31/2021 05:18:54 - INFO - __main__ - Step 89370: {'lr': 0.0001800025556423317, 'samples': 17159040, 'steps': 89369, 'loss/train': 0.9990233778953552} 08/31/2021 05:18:54 - INFO - __main__ - Step 89371: {'lr': 0.0001799974611677064, 'samples': 17159232, 'steps': 89370, 'loss/train': 1.3596911430358887} 08/31/2021 05:18:57 - INFO - __main__ - Step 89372: {'lr': 0.00017999236672462326, 'samples': 17159424, 'steps': 89371, 'loss/train': 0.7123777866363525} 08/31/2021 05:18:57 - INFO - __main__ - Step 89373: {'lr': 0.00017998727231308438, 'samples': 17159616, 'steps': 89372, 'loss/train': 1.2663203477859497} 08/31/2021 05:18:58 - INFO - __main__ - Step 89374: {'lr': 0.00017998217793309214, 'samples': 17159808, 'steps': 89373, 'loss/train': 1.283389687538147} 08/31/2021 05:18:58 - INFO - __main__ - Step 89375: {'lr': 0.0001799770835846488, 'samples': 17160000, 'steps': 89374, 'loss/train': 1.6147737503051758} 08/31/2021 05:18:58 - INFO - __main__ - Step 89376: {'lr': 0.00017997198926775679, 'samples': 17160192, 'steps': 89375, 'loss/train': 1.0028760433197021} 08/31/2021 05:18:59 - INFO - __main__ - Step 89377: {'lr': 0.0001799668949824183, 'samples': 17160384, 'steps': 89376, 'loss/train': 1.2457232475280762} 08/31/2021 05:18:59 - INFO - __main__ - Step 89378: {'lr': 0.00017996180072863563, 'samples': 17160576, 'steps': 89377, 'loss/train': 0.9232348203659058} 08/31/2021 05:19:01 - INFO - __main__ - Step 89379: {'lr': 0.0001799567065064111, 'samples': 17160768, 'steps': 89378, 'loss/train': 0.7319039106369019} 08/31/2021 05:19:01 - INFO - __main__ - Step 89380: {'lr': 0.000179951612315747, 'samples': 17160960, 'steps': 89379, 'loss/train': 1.3355913162231445} 08/31/2021 05:19:02 - INFO - __main__ - Step 89381: {'lr': 0.00017994651815664563, 'samples': 17161152, 'steps': 89380, 'loss/train': 1.846914529800415} 08/31/2021 05:19:02 - INFO - __main__ - Step 89382: {'lr': 0.00017994142402910925, 'samples': 17161344, 'steps': 89381, 'loss/train': 0.9777548313140869} 08/31/2021 05:19:02 - INFO - __main__ - Step 89383: {'lr': 0.0001799363299331402, 'samples': 17161536, 'steps': 89382, 'loss/train': 0.9592664837837219} 08/31/2021 05:19:04 - INFO - __main__ - Step 89384: {'lr': 0.00017993123586874078, 'samples': 17161728, 'steps': 89383, 'loss/train': 0.9124548435211182} 08/31/2021 05:19:04 - INFO - __main__ - Step 89385: {'lr': 0.00017992614183591322, 'samples': 17161920, 'steps': 89384, 'loss/train': 1.3906744718551636} 08/31/2021 05:19:05 - INFO - __main__ - Step 89386: {'lr': 0.00017992104783466, 'samples': 17162112, 'steps': 89385, 'loss/train': 1.4173383712768555} 08/31/2021 05:19:05 - INFO - __main__ - Step 89387: {'lr': 0.00017991595386498315, 'samples': 17162304, 'steps': 89386, 'loss/train': 0.9323851466178894} 08/31/2021 05:19:05 - INFO - __main__ - Step 89388: {'lr': 0.0001799108599268851, 'samples': 17162496, 'steps': 89387, 'loss/train': 1.2332019805908203} 08/31/2021 05:19:07 - INFO - __main__ - Step 89389: {'lr': 0.00017990576602036813, 'samples': 17162688, 'steps': 89388, 'loss/train': 0.9165918827056885} 08/31/2021 05:19:07 - INFO - __main__ - Step 89390: {'lr': 0.00017990067214543453, 'samples': 17162880, 'steps': 89389, 'loss/train': 0.836692214012146} 08/31/2021 05:19:07 - INFO - __main__ - Step 89391: {'lr': 0.00017989557830208665, 'samples': 17163072, 'steps': 89390, 'loss/train': 0.9418025016784668} 08/31/2021 05:19:08 - INFO - __main__ - Step 89392: {'lr': 0.0001798904844903267, 'samples': 17163264, 'steps': 89391, 'loss/train': 0.43370699882507324} 08/31/2021 05:19:08 - INFO - __main__ - Step 89393: {'lr': 0.000179885390710157, 'samples': 17163456, 'steps': 89392, 'loss/train': 1.7962772846221924} 08/31/2021 05:19:10 - INFO - __main__ - Step 89394: {'lr': 0.00017988029696157986, 'samples': 17163648, 'steps': 89393, 'loss/train': 1.1151413917541504} 08/31/2021 05:19:10 - INFO - __main__ - Step 89395: {'lr': 0.0001798752032445976, 'samples': 17163840, 'steps': 89394, 'loss/train': 0.845194399356842} 08/31/2021 05:19:10 - INFO - __main__ - Step 89396: {'lr': 0.0001798701095592125, 'samples': 17164032, 'steps': 89395, 'loss/train': 2.2304999828338623} 08/31/2021 05:19:11 - INFO - __main__ - Step 89397: {'lr': 0.00017986501590542688, 'samples': 17164224, 'steps': 89396, 'loss/train': 0.9785304069519043} 08/31/2021 05:19:11 - INFO - __main__ - Step 89398: {'lr': 0.00017985992228324293, 'samples': 17164416, 'steps': 89397, 'loss/train': 2.0201406478881836} 08/31/2021 05:19:11 - INFO - __main__ - Step 89399: {'lr': 0.00017985482869266315, 'samples': 17164608, 'steps': 89398, 'loss/train': 1.1876798868179321} 08/31/2021 05:19:13 - INFO - __main__ - Step 89400: {'lr': 0.0001798497351336896, 'samples': 17164800, 'steps': 89399, 'loss/train': 1.3525152206420898} 08/31/2021 05:19:13 - INFO - __main__ - Step 89401: {'lr': 0.00017984464160632468, 'samples': 17164992, 'steps': 89400, 'loss/train': 1.055506706237793} 08/31/2021 05:19:14 - INFO - __main__ - Step 89402: {'lr': 0.00017983954811057068, 'samples': 17165184, 'steps': 89401, 'loss/train': 1.6552263498306274} 08/31/2021 05:19:14 - INFO - __main__ - Step 89403: {'lr': 0.00017983445464642988, 'samples': 17165376, 'steps': 89402, 'loss/train': 0.37994107604026794} 08/31/2021 05:19:15 - INFO - __main__ - Step 89404: {'lr': 0.0001798293612139046, 'samples': 17165568, 'steps': 89403, 'loss/train': 0.8914740681648254} 08/31/2021 05:19:16 - INFO - __main__ - Step 89405: {'lr': 0.00017982426781299715, 'samples': 17165760, 'steps': 89404, 'loss/train': 1.2519675493240356} 08/31/2021 05:19:16 - INFO - __main__ - Step 89406: {'lr': 0.00017981917444370976, 'samples': 17165952, 'steps': 89405, 'loss/train': 0.6540614366531372} 08/31/2021 05:19:17 - INFO - __main__ - Step 89407: {'lr': 0.0001798140811060448, 'samples': 17166144, 'steps': 89406, 'loss/train': 1.1647998094558716} 08/31/2021 05:19:17 - INFO - __main__ - Step 89408: {'lr': 0.00017980898780000455, 'samples': 17166336, 'steps': 89407, 'loss/train': 0.43893468379974365} 08/31/2021 05:19:18 - INFO - __main__ - Step 89409: {'lr': 0.00017980389452559124, 'samples': 17166528, 'steps': 89408, 'loss/train': 1.0689254999160767} 08/31/2021 05:19:20 - INFO - __main__ - Step 89410: {'lr': 0.00017979880128280722, 'samples': 17166720, 'steps': 89409, 'loss/train': 1.1513915061950684} 08/31/2021 05:19:20 - INFO - __main__ - Step 89411: {'lr': 0.00017979370807165478, 'samples': 17166912, 'steps': 89410, 'loss/train': 1.5387516021728516} 08/31/2021 05:19:20 - INFO - __main__ - Step 89412: {'lr': 0.00017978861489213624, 'samples': 17167104, 'steps': 89411, 'loss/train': 1.7667312622070312} 08/31/2021 05:19:21 - INFO - __main__ - Step 89413: {'lr': 0.00017978352174425393, 'samples': 17167296, 'steps': 89412, 'loss/train': 1.7550359964370728} 08/31/2021 05:19:21 - INFO - __main__ - Step 89414: {'lr': 0.00017977842862801002, 'samples': 17167488, 'steps': 89413, 'loss/train': 1.5543912649154663} 08/31/2021 05:19:21 - INFO - __main__ - Step 89415: {'lr': 0.00017977333554340685, 'samples': 17167680, 'steps': 89414, 'loss/train': 1.1157604455947876} 08/31/2021 05:19:23 - INFO - __main__ - Step 89416: {'lr': 0.0001797682424904467, 'samples': 17167872, 'steps': 89415, 'loss/train': 1.1256985664367676} 08/31/2021 05:19:23 - INFO - __main__ - Step 89417: {'lr': 0.00017976314946913197, 'samples': 17168064, 'steps': 89416, 'loss/train': 0.8024462461471558} 08/31/2021 05:19:24 - INFO - __main__ - Step 89418: {'lr': 0.0001797580564794648, 'samples': 17168256, 'steps': 89417, 'loss/train': 1.1758904457092285} 08/31/2021 05:19:24 - INFO - __main__ - Step 89419: {'lr': 0.0001797529635214476, 'samples': 17168448, 'steps': 89418, 'loss/train': 1.2275217771530151} 08/31/2021 05:19:24 - INFO - __main__ - Step 89420: {'lr': 0.00017974787059508264, 'samples': 17168640, 'steps': 89419, 'loss/train': 0.3458670675754547} 08/31/2021 05:19:25 - INFO - __main__ - Step 89421: {'lr': 0.0001797427777003722, 'samples': 17168832, 'steps': 89420, 'loss/train': 1.2267045974731445} 08/31/2021 05:19:26 - INFO - __main__ - Step 89422: {'lr': 0.0001797376848373186, 'samples': 17169024, 'steps': 89421, 'loss/train': 0.9077795147895813} 08/31/2021 05:19:27 - INFO - __main__ - Step 89423: {'lr': 0.00017973259200592407, 'samples': 17169216, 'steps': 89422, 'loss/train': 1.2512050867080688} 08/31/2021 05:19:27 - INFO - __main__ - Step 89424: {'lr': 0.00017972749920619097, 'samples': 17169408, 'steps': 89423, 'loss/train': 1.4534683227539062} 08/31/2021 05:19:27 - INFO - __main__ - Step 89425: {'lr': 0.0001797224064381216, 'samples': 17169600, 'steps': 89424, 'loss/train': 1.4609074592590332} 08/31/2021 05:19:28 - INFO - __main__ - Step 89426: {'lr': 0.00017971731370171828, 'samples': 17169792, 'steps': 89425, 'loss/train': 1.0477972030639648} 08/31/2021 05:19:30 - INFO - __main__ - Step 89427: {'lr': 0.0001797122209969832, 'samples': 17169984, 'steps': 89426, 'loss/train': 1.3610832691192627} 08/31/2021 05:19:31 - INFO - __main__ - Step 89428: {'lr': 0.00017970712832391866, 'samples': 17170176, 'steps': 89427, 'loss/train': 1.1135374307632446} 08/31/2021 05:19:31 - INFO - __main__ - Step 89429: {'lr': 0.00017970203568252704, 'samples': 17170368, 'steps': 89428, 'loss/train': 1.4942489862442017} 08/31/2021 05:19:31 - INFO - __main__ - Step 89430: {'lr': 0.0001796969430728106, 'samples': 17170560, 'steps': 89429, 'loss/train': 1.306906819343567} 08/31/2021 05:19:32 - INFO - __main__ - Step 89431: {'lr': 0.0001796918504947716, 'samples': 17170752, 'steps': 89430, 'loss/train': 1.368201494216919} 08/31/2021 05:19:33 - INFO - __main__ - Step 89432: {'lr': 0.00017968675794841242, 'samples': 17170944, 'steps': 89431, 'loss/train': 1.320691466331482} 08/31/2021 05:19:34 - INFO - __main__ - Step 89433: {'lr': 0.00017968166543373527, 'samples': 17171136, 'steps': 89432, 'loss/train': 1.2345014810562134} 08/31/2021 05:19:34 - INFO - __main__ - Step 89434: {'lr': 0.00017967657295074247, 'samples': 17171328, 'steps': 89433, 'loss/train': 1.292934536933899} 08/31/2021 05:19:34 - INFO - __main__ - Step 89435: {'lr': 0.00017967148049943634, 'samples': 17171520, 'steps': 89434, 'loss/train': 1.0525500774383545} 08/31/2021 05:19:35 - INFO - __main__ - Step 89436: {'lr': 0.0001796663880798191, 'samples': 17171712, 'steps': 89435, 'loss/train': 1.922364354133606} 08/31/2021 05:19:36 - INFO - __main__ - Step 89437: {'lr': 0.00017966129569189316, 'samples': 17171904, 'steps': 89436, 'loss/train': 1.7544538974761963} 08/31/2021 05:19:36 - INFO - __main__ - Step 89438: {'lr': 0.00017965620333566074, 'samples': 17172096, 'steps': 89437, 'loss/train': 1.2000261545181274} 08/31/2021 05:19:37 - INFO - __main__ - Step 89439: {'lr': 0.00017965111101112417, 'samples': 17172288, 'steps': 89438, 'loss/train': 1.629036545753479} 08/31/2021 05:19:37 - INFO - __main__ - Step 89440: {'lr': 0.00017964601871828579, 'samples': 17172480, 'steps': 89439, 'loss/train': 1.0599948167800903} 08/31/2021 05:19:38 - INFO - __main__ - Step 89441: {'lr': 0.00017964092645714774, 'samples': 17172672, 'steps': 89440, 'loss/train': 0.41473188996315} 08/31/2021 05:19:39 - INFO - __main__ - Step 89442: {'lr': 0.0001796358342277124, 'samples': 17172864, 'steps': 89441, 'loss/train': 1.2589998245239258} 08/31/2021 05:19:39 - INFO - __main__ - Step 89443: {'lr': 0.0001796307420299821, 'samples': 17173056, 'steps': 89442, 'loss/train': 0.7145262360572815} 08/31/2021 05:19:40 - INFO - __main__ - Step 89444: {'lr': 0.00017962564986395908, 'samples': 17173248, 'steps': 89443, 'loss/train': 1.1598479747772217} 08/31/2021 05:19:40 - INFO - __main__ - Step 89445: {'lr': 0.00017962055772964563, 'samples': 17173440, 'steps': 89444, 'loss/train': 0.808767557144165} 08/31/2021 05:19:40 - INFO - __main__ - Step 89446: {'lr': 0.00017961546562704405, 'samples': 17173632, 'steps': 89445, 'loss/train': 1.3591444492340088} 08/31/2021 05:19:42 - INFO - __main__ - Step 89447: {'lr': 0.00017961037355615673, 'samples': 17173824, 'steps': 89446, 'loss/train': 1.1275659799575806} 08/31/2021 05:19:42 - INFO - __main__ - Step 89448: {'lr': 0.00017960528151698586, 'samples': 17174016, 'steps': 89447, 'loss/train': 1.5734437704086304} 08/31/2021 05:19:43 - INFO - __main__ - Step 89449: {'lr': 0.00017960018950953375, 'samples': 17174208, 'steps': 89448, 'loss/train': 1.3120490312576294} 08/31/2021 05:19:43 - INFO - __main__ - Step 89450: {'lr': 0.0001795950975338027, 'samples': 17174400, 'steps': 89449, 'loss/train': 1.5783190727233887} 08/31/2021 05:19:43 - INFO - __main__ - Step 89451: {'lr': 0.00017959000558979505, 'samples': 17174592, 'steps': 89450, 'loss/train': 1.118168830871582} 08/31/2021 05:19:45 - INFO - __main__ - Step 89452: {'lr': 0.00017958491367751306, 'samples': 17174784, 'steps': 89451, 'loss/train': 1.4637831449508667} 08/31/2021 05:19:45 - INFO - __main__ - Step 89453: {'lr': 0.0001795798217969591, 'samples': 17174976, 'steps': 89452, 'loss/train': 1.357663869857788} 08/31/2021 05:19:46 - INFO - __main__ - Step 89454: {'lr': 0.00017957472994813525, 'samples': 17175168, 'steps': 89453, 'loss/train': 1.037036418914795} 08/31/2021 05:19:46 - INFO - __main__ - Step 89455: {'lr': 0.000179569638131044, 'samples': 17175360, 'steps': 89454, 'loss/train': 1.251562237739563} 08/31/2021 05:19:46 - INFO - __main__ - Step 89456: {'lr': 0.00017956454634568753, 'samples': 17175552, 'steps': 89455, 'loss/train': 1.6181285381317139} 08/31/2021 05:19:48 - INFO - __main__ - Step 89457: {'lr': 0.0001795594545920682, 'samples': 17175744, 'steps': 89456, 'loss/train': 1.3659334182739258} 08/31/2021 05:19:48 - INFO - __main__ - Step 89458: {'lr': 0.00017955436287018833, 'samples': 17175936, 'steps': 89457, 'loss/train': 0.31901487708091736} 08/31/2021 05:19:49 - INFO - __main__ - Step 89459: {'lr': 0.00017954927118005016, 'samples': 17176128, 'steps': 89458, 'loss/train': 0.9627367854118347} 08/31/2021 05:19:49 - INFO - __main__ - Step 89460: {'lr': 0.00017954417952165596, 'samples': 17176320, 'steps': 89459, 'loss/train': 1.0792797803878784} 08/31/2021 05:19:49 - INFO - __main__ - Step 89461: {'lr': 0.0001795390878950081, 'samples': 17176512, 'steps': 89460, 'loss/train': 1.449806809425354} 08/31/2021 05:19:50 - INFO - __main__ - Step 89462: {'lr': 0.0001795339963001089, 'samples': 17176704, 'steps': 89461, 'loss/train': 0.7444747090339661} 08/31/2021 05:19:51 - INFO - __main__ - Step 89463: {'lr': 0.00017952890473696054, 'samples': 17176896, 'steps': 89462, 'loss/train': 1.155840516090393} 08/31/2021 05:19:52 - INFO - __main__ - Step 89464: {'lr': 0.00017952381320556537, 'samples': 17177088, 'steps': 89463, 'loss/train': 1.2438292503356934} 08/31/2021 05:19:52 - INFO - __main__ - Step 89465: {'lr': 0.0001795187217059257, 'samples': 17177280, 'steps': 89464, 'loss/train': 0.8456114530563354} 08/31/2021 05:19:52 - INFO - __main__ - Step 89466: {'lr': 0.00017951363023804381, 'samples': 17177472, 'steps': 89465, 'loss/train': 1.66215181350708} 08/31/2021 05:19:53 - INFO - __main__ - Step 89467: {'lr': 0.00017950853880192196, 'samples': 17177664, 'steps': 89466, 'loss/train': 1.1712251901626587} 08/31/2021 05:19:54 - INFO - __main__ - Step 89468: {'lr': 0.00017950344739756248, 'samples': 17177856, 'steps': 89467, 'loss/train': 0.7070050835609436} 08/31/2021 05:19:55 - INFO - __main__ - Step 89469: {'lr': 0.00017949835602496767, 'samples': 17178048, 'steps': 89468, 'loss/train': 0.8070352673530579} 08/31/2021 05:19:55 - INFO - __main__ - Step 89470: {'lr': 0.00017949326468413978, 'samples': 17178240, 'steps': 89469, 'loss/train': 1.3592431545257568} 08/31/2021 05:19:55 - INFO - __main__ - Step 89471: {'lr': 0.00017948817337508116, 'samples': 17178432, 'steps': 89470, 'loss/train': 0.7666183710098267} 08/31/2021 05:19:56 - INFO - __main__ - Step 89472: {'lr': 0.00017948308209779406, 'samples': 17178624, 'steps': 89471, 'loss/train': 1.3569332361221313} 08/31/2021 05:19:58 - INFO - __main__ - Step 89473: {'lr': 0.00017947799085228088, 'samples': 17178816, 'steps': 89472, 'loss/train': 1.6284996271133423} 08/31/2021 05:19:58 - INFO - __main__ - Step 89474: {'lr': 0.0001794728996385438, 'samples': 17179008, 'steps': 89473, 'loss/train': 1.1220723390579224} 08/31/2021 05:19:58 - INFO - __main__ - Step 89475: {'lr': 0.0001794678084565851, 'samples': 17179200, 'steps': 89474, 'loss/train': 0.3526250422000885} 08/31/2021 05:19:59 - INFO - __main__ - Step 89476: {'lr': 0.0001794627173064071, 'samples': 17179392, 'steps': 89475, 'loss/train': 0.022618956863880157} 08/31/2021 05:19:59 - INFO - __main__ - Step 89477: {'lr': 0.00017945762618801214, 'samples': 17179584, 'steps': 89476, 'loss/train': 1.6407657861709595} 08/31/2021 05:20:00 - INFO - __main__ - Step 89478: {'lr': 0.00017945253510140248, 'samples': 17179776, 'steps': 89477, 'loss/train': 1.0948419570922852} 08/31/2021 05:20:01 - INFO - __main__ - Step 89479: {'lr': 0.0001794474440465804, 'samples': 17179968, 'steps': 89478, 'loss/train': 0.6902107000350952} 08/31/2021 05:20:02 - INFO - __main__ - Step 89480: {'lr': 0.00017944235302354828, 'samples': 17180160, 'steps': 89479, 'loss/train': 0.8212034702301025} 08/31/2021 05:20:02 - INFO - __main__ - Step 89481: {'lr': 0.00017943726203230832, 'samples': 17180352, 'steps': 89480, 'loss/train': 1.0326597690582275} 08/31/2021 05:20:03 - INFO - __main__ - Step 89482: {'lr': 0.0001794321710728628, 'samples': 17180544, 'steps': 89481, 'loss/train': 0.21456773579120636} 08/31/2021 05:20:03 - INFO - __main__ - Step 89483: {'lr': 0.00017942708014521408, 'samples': 17180736, 'steps': 89482, 'loss/train': 1.2035882472991943} 08/31/2021 05:20:05 - INFO - __main__ - Step 89484: {'lr': 0.00017942198924936447, 'samples': 17180928, 'steps': 89483, 'loss/train': 1.57435142993927} 08/31/2021 05:20:05 - INFO - __main__ - Step 89485: {'lr': 0.00017941689838531615, 'samples': 17181120, 'steps': 89484, 'loss/train': 0.8818378448486328} 08/31/2021 05:20:06 - INFO - __main__ - Step 89486: {'lr': 0.00017941180755307154, 'samples': 17181312, 'steps': 89485, 'loss/train': 1.2139261960983276} 08/31/2021 05:20:06 - INFO - __main__ - Step 89487: {'lr': 0.00017940671675263284, 'samples': 17181504, 'steps': 89486, 'loss/train': 0.9077622294425964} 08/31/2021 05:20:06 - INFO - __main__ - Step 89488: {'lr': 0.00017940162598400238, 'samples': 17181696, 'steps': 89487, 'loss/train': 0.05874764546751976} 08/31/2021 05:20:07 - INFO - __main__ - Step 89489: {'lr': 0.0001793965352471825, 'samples': 17181888, 'steps': 89488, 'loss/train': 1.233365774154663} 08/31/2021 05:20:08 - INFO - __main__ - Step 89490: {'lr': 0.00017939144454217544, 'samples': 17182080, 'steps': 89489, 'loss/train': 0.6273094415664673} 08/31/2021 05:20:09 - INFO - __main__ - Step 89491: {'lr': 0.00017938635386898348, 'samples': 17182272, 'steps': 89490, 'loss/train': 0.8272380828857422} 08/31/2021 05:20:09 - INFO - __main__ - Step 89492: {'lr': 0.00017938126322760895, 'samples': 17182464, 'steps': 89491, 'loss/train': 0.943832278251648} 08/31/2021 05:20:09 - INFO - __main__ - Step 89493: {'lr': 0.00017937617261805418, 'samples': 17182656, 'steps': 89492, 'loss/train': 1.179972767829895} 08/31/2021 05:20:10 - INFO - __main__ - Step 89494: {'lr': 0.00017937108204032137, 'samples': 17182848, 'steps': 89493, 'loss/train': 1.2797030210494995} 08/31/2021 05:20:11 - INFO - __main__ - Step 89495: {'lr': 0.0001793659914944129, 'samples': 17183040, 'steps': 89494, 'loss/train': 1.558642864227295} 08/31/2021 05:20:12 - INFO - __main__ - Step 89496: {'lr': 0.00017936090098033097, 'samples': 17183232, 'steps': 89495, 'loss/train': 0.719626784324646} 08/31/2021 05:20:12 - INFO - __main__ - Step 89497: {'lr': 0.000179355810498078, 'samples': 17183424, 'steps': 89496, 'loss/train': 0.8214021921157837} 08/31/2021 05:20:13 - INFO - __main__ - Step 89498: {'lr': 0.00017935072004765613, 'samples': 17183616, 'steps': 89497, 'loss/train': 4.590539455413818} 08/31/2021 05:20:13 - INFO - __main__ - Step 89499: {'lr': 0.00017934562962906774, 'samples': 17183808, 'steps': 89498, 'loss/train': 0.864774227142334} 08/31/2021 05:20:13 - INFO - __main__ - Step 89500: {'lr': 0.00017934053924231514, 'samples': 17184000, 'steps': 89499, 'loss/train': 0.5673182606697083} 08/31/2021 05:20:15 - INFO - __main__ - Step 89501: {'lr': 0.00017933544888740062, 'samples': 17184192, 'steps': 89500, 'loss/train': 1.2059975862503052} 08/31/2021 05:20:16 - INFO - __main__ - Step 89502: {'lr': 0.00017933035856432643, 'samples': 17184384, 'steps': 89501, 'loss/train': 0.06588242202997208} 08/31/2021 05:20:16 - INFO - __main__ - Step 89503: {'lr': 0.00017932526827309486, 'samples': 17184576, 'steps': 89502, 'loss/train': 5.616609573364258} 08/31/2021 05:20:16 - INFO - __main__ - Step 89504: {'lr': 0.0001793201780137083, 'samples': 17184768, 'steps': 89503, 'loss/train': 1.4258909225463867} 08/31/2021 05:20:17 - INFO - __main__ - Step 89505: {'lr': 0.00017931508778616895, 'samples': 17184960, 'steps': 89504, 'loss/train': 1.3322805166244507} 08/31/2021 05:20:18 - INFO - __main__ - Step 89506: {'lr': 0.0001793099975904791, 'samples': 17185152, 'steps': 89505, 'loss/train': 1.52822744846344} 08/31/2021 05:20:19 - INFO - __main__ - Step 89507: {'lr': 0.00017930490742664124, 'samples': 17185344, 'steps': 89506, 'loss/train': 1.2871370315551758} 08/31/2021 05:20:19 - INFO - __main__ - Step 89508: {'lr': 0.00017929981729465733, 'samples': 17185536, 'steps': 89507, 'loss/train': 1.0717558860778809} 08/31/2021 05:20:19 - INFO - __main__ - Step 89509: {'lr': 0.0001792947271945299, 'samples': 17185728, 'steps': 89508, 'loss/train': 0.9317751526832581} 08/31/2021 05:20:20 - INFO - __main__ - Step 89510: {'lr': 0.00017928963712626113, 'samples': 17185920, 'steps': 89509, 'loss/train': 1.336552619934082} 08/31/2021 05:20:21 - INFO - __main__ - Step 89511: {'lr': 0.00017928454708985336, 'samples': 17186112, 'steps': 89510, 'loss/train': 1.3394191265106201} 08/31/2021 05:20:22 - INFO - __main__ - Step 89512: {'lr': 0.00017927945708530888, 'samples': 17186304, 'steps': 89511, 'loss/train': 1.2871443033218384} 08/31/2021 05:20:22 - INFO - __main__ - Step 89513: {'lr': 0.00017927436711262997, 'samples': 17186496, 'steps': 89512, 'loss/train': 0.6918759346008301} 08/31/2021 05:20:22 - INFO - __main__ - Step 89514: {'lr': 0.000179269277171819, 'samples': 17186688, 'steps': 89513, 'loss/train': 1.1570322513580322} 08/31/2021 05:20:23 - INFO - __main__ - Step 89515: {'lr': 0.00017926418726287813, 'samples': 17186880, 'steps': 89514, 'loss/train': 0.5389476418495178} 08/31/2021 05:20:23 - INFO - __main__ - Step 89516: {'lr': 0.00017925909738580976, 'samples': 17187072, 'steps': 89515, 'loss/train': 1.0225801467895508} 08/31/2021 05:20:24 - INFO - __main__ - Step 89517: {'lr': 0.00017925400754061616, 'samples': 17187264, 'steps': 89516, 'loss/train': 0.6810110807418823} 08/31/2021 05:20:25 - INFO - __main__ - Step 89518: {'lr': 0.0001792489177272996, 'samples': 17187456, 'steps': 89517, 'loss/train': 1.0047643184661865} 08/31/2021 05:20:25 - INFO - __main__ - Step 89519: {'lr': 0.0001792438279458624, 'samples': 17187648, 'steps': 89518, 'loss/train': 1.4878594875335693} 08/31/2021 05:20:26 - INFO - __main__ - Step 89520: {'lr': 0.00017923873819630692, 'samples': 17187840, 'steps': 89519, 'loss/train': 1.1367782354354858} 08/31/2021 05:20:26 - INFO - __main__ - Step 89521: {'lr': 0.00017923364847863526, 'samples': 17188032, 'steps': 89520, 'loss/train': 0.3203141391277313} 08/31/2021 05:20:27 - INFO - __main__ - Step 89522: {'lr': 0.00017922855879284985, 'samples': 17188224, 'steps': 89521, 'loss/train': 1.205936074256897} 08/31/2021 05:20:28 - INFO - __main__ - Step 89523: {'lr': 0.00017922346913895295, 'samples': 17188416, 'steps': 89522, 'loss/train': 1.2981994152069092} 08/31/2021 05:20:28 - INFO - __main__ - Step 89524: {'lr': 0.00017921837951694687, 'samples': 17188608, 'steps': 89523, 'loss/train': 1.0725178718566895} 08/31/2021 05:20:29 - INFO - __main__ - Step 89525: {'lr': 0.00017921328992683388, 'samples': 17188800, 'steps': 89524, 'loss/train': 1.7438263893127441} 08/31/2021 05:20:29 - INFO - __main__ - Step 89526: {'lr': 0.00017920820036861632, 'samples': 17188992, 'steps': 89525, 'loss/train': 2.426492214202881} 08/31/2021 05:20:30 - INFO - __main__ - Step 89527: {'lr': 0.00017920311084229645, 'samples': 17189184, 'steps': 89526, 'loss/train': 1.7333863973617554} 08/31/2021 05:20:31 - INFO - __main__ - Step 89528: {'lr': 0.00017919802134787655, 'samples': 17189376, 'steps': 89527, 'loss/train': 0.7916527986526489} 08/31/2021 05:20:31 - INFO - __main__ - Step 89529: {'lr': 0.0001791929318853589, 'samples': 17189568, 'steps': 89528, 'loss/train': 0.7960778474807739} 08/31/2021 05:20:32 - INFO - __main__ - Step 89530: {'lr': 0.00017918784245474586, 'samples': 17189760, 'steps': 89529, 'loss/train': 1.4416345357894897} 08/31/2021 05:20:32 - INFO - __main__ - Step 89531: {'lr': 0.00017918275305603968, 'samples': 17189952, 'steps': 89530, 'loss/train': 0.7718437910079956} 08/31/2021 05:20:33 - INFO - __main__ - Step 89532: {'lr': 0.00017917766368924265, 'samples': 17190144, 'steps': 89531, 'loss/train': 0.8518874049186707} 08/31/2021 05:20:34 - INFO - __main__ - Step 89533: {'lr': 0.00017917257435435708, 'samples': 17190336, 'steps': 89532, 'loss/train': 1.1786152124404907} 08/31/2021 05:20:34 - INFO - __main__ - Step 89534: {'lr': 0.00017916748505138536, 'samples': 17190528, 'steps': 89533, 'loss/train': 0.5797526240348816} 08/31/2021 05:20:35 - INFO - __main__ - Step 89535: {'lr': 0.00017916239578032956, 'samples': 17190720, 'steps': 89534, 'loss/train': 1.2888978719711304} 08/31/2021 05:20:35 - INFO - __main__ - Step 89536: {'lr': 0.0001791573065411921, 'samples': 17190912, 'steps': 89535, 'loss/train': 1.0688011646270752} 08/31/2021 05:20:37 - INFO - __main__ - Step 89537: {'lr': 0.0001791522173339753, 'samples': 17191104, 'steps': 89536, 'loss/train': 0.48210057616233826} 08/31/2021 05:20:37 - INFO - __main__ - Step 89538: {'lr': 0.00017914712815868136, 'samples': 17191296, 'steps': 89537, 'loss/train': 0.9907416105270386} 08/31/2021 05:20:38 - INFO - __main__ - Step 89539: {'lr': 0.00017914203901531268, 'samples': 17191488, 'steps': 89538, 'loss/train': 1.2840945720672607} 08/31/2021 05:20:38 - INFO - __main__ - Step 89540: {'lr': 0.00017913694990387148, 'samples': 17191680, 'steps': 89539, 'loss/train': 1.8056029081344604} 08/31/2021 05:20:39 - INFO - __main__ - Step 89541: {'lr': 0.00017913186082436005, 'samples': 17191872, 'steps': 89540, 'loss/train': 1.5207127332687378} 08/31/2021 05:20:39 - INFO - __main__ - Step 89542: {'lr': 0.00017912677177678074, 'samples': 17192064, 'steps': 89541, 'loss/train': 1.8299379348754883} 08/31/2021 05:20:40 - INFO - __main__ - Step 89543: {'lr': 0.00017912168276113582, 'samples': 17192256, 'steps': 89542, 'loss/train': 1.1429184675216675} 08/31/2021 05:20:41 - INFO - __main__ - Step 89544: {'lr': 0.00017911659377742756, 'samples': 17192448, 'steps': 89543, 'loss/train': 0.2874279022216797} 08/31/2021 05:20:41 - INFO - __main__ - Step 89545: {'lr': 0.00017911150482565827, 'samples': 17192640, 'steps': 89544, 'loss/train': 0.2751895487308502} 08/31/2021 05:20:42 - INFO - __main__ - Step 89546: {'lr': 0.00017910641590583023, 'samples': 17192832, 'steps': 89545, 'loss/train': 1.3876278400421143} 08/31/2021 05:20:42 - INFO - __main__ - Step 89547: {'lr': 0.00017910132701794588, 'samples': 17193024, 'steps': 89546, 'loss/train': 1.0994980335235596} 08/31/2021 05:20:43 - INFO - __main__ - Step 89548: {'lr': 0.00017909623816200727, 'samples': 17193216, 'steps': 89547, 'loss/train': 1.3959182500839233} 08/31/2021 05:20:44 - INFO - __main__ - Step 89549: {'lr': 0.0001790911493380168, 'samples': 17193408, 'steps': 89548, 'loss/train': 0.5873259902000427} 08/31/2021 05:20:44 - INFO - __main__ - Step 89550: {'lr': 0.00017908606054597672, 'samples': 17193600, 'steps': 89549, 'loss/train': 1.5835566520690918} 08/31/2021 05:20:44 - INFO - __main__ - Step 89551: {'lr': 0.00017908097178588942, 'samples': 17193792, 'steps': 89550, 'loss/train': 1.319416880607605} 08/31/2021 05:20:45 - INFO - __main__ - Step 89552: {'lr': 0.00017907588305775713, 'samples': 17193984, 'steps': 89551, 'loss/train': 1.1290634870529175} 08/31/2021 05:20:47 - INFO - __main__ - Step 89553: {'lr': 0.00017907079436158213, 'samples': 17194176, 'steps': 89552, 'loss/train': 1.233777642250061} 08/31/2021 05:20:47 - INFO - __main__ - Step 89554: {'lr': 0.00017906570569736673, 'samples': 17194368, 'steps': 89553, 'loss/train': 1.2263638973236084} 08/31/2021 05:20:48 - INFO - __main__ - Step 89555: {'lr': 0.00017906061706511326, 'samples': 17194560, 'steps': 89554, 'loss/train': 1.4295858144760132} 08/31/2021 05:20:48 - INFO - __main__ - Step 89556: {'lr': 0.00017905552846482397, 'samples': 17194752, 'steps': 89555, 'loss/train': 1.4262185096740723} 08/31/2021 05:20:48 - INFO - __main__ - Step 89557: {'lr': 0.00017905043989650116, 'samples': 17194944, 'steps': 89556, 'loss/train': 1.2478327751159668} 08/31/2021 05:20:49 - INFO - __main__ - Step 89558: {'lr': 0.00017904535136014713, 'samples': 17195136, 'steps': 89557, 'loss/train': 2.580583333969116} 08/31/2021 05:20:50 - INFO - __main__ - Step 89559: {'lr': 0.00017904026285576417, 'samples': 17195328, 'steps': 89558, 'loss/train': 1.1621131896972656} 08/31/2021 05:20:51 - INFO - __main__ - Step 89560: {'lr': 0.00017903517438335457, 'samples': 17195520, 'steps': 89559, 'loss/train': 0.3182975947856903} 08/31/2021 05:20:51 - INFO - __main__ - Step 89561: {'lr': 0.00017903008594292075, 'samples': 17195712, 'steps': 89560, 'loss/train': 0.474325567483902} 08/31/2021 05:20:52 - INFO - __main__ - Step 89562: {'lr': 0.0001790249975344647, 'samples': 17195904, 'steps': 89561, 'loss/train': 1.2659796476364136} 08/31/2021 05:20:52 - INFO - __main__ - Step 89563: {'lr': 0.00017901990915798898, 'samples': 17196096, 'steps': 89562, 'loss/train': 0.8327518701553345} 08/31/2021 05:20:53 - INFO - __main__ - Step 89564: {'lr': 0.00017901482081349578, 'samples': 17196288, 'steps': 89563, 'loss/train': 1.400264024734497} 08/31/2021 05:20:54 - INFO - __main__ - Step 89565: {'lr': 0.00017900973250098738, 'samples': 17196480, 'steps': 89564, 'loss/train': 1.1283185482025146} 08/31/2021 05:20:54 - INFO - __main__ - Step 89566: {'lr': 0.00017900464422046609, 'samples': 17196672, 'steps': 89565, 'loss/train': 1.1665867567062378} 08/31/2021 05:20:55 - INFO - __main__ - Step 89567: {'lr': 0.00017899955597193423, 'samples': 17196864, 'steps': 89566, 'loss/train': 1.0933837890625} 08/31/2021 05:20:55 - INFO - __main__ - Step 89568: {'lr': 0.00017899446775539407, 'samples': 17197056, 'steps': 89567, 'loss/train': 1.0475554466247559} 08/31/2021 05:20:55 - INFO - __main__ - Step 89569: {'lr': 0.0001789893795708479, 'samples': 17197248, 'steps': 89568, 'loss/train': 1.4835823774337769} 08/31/2021 05:20:57 - INFO - __main__ - Step 89570: {'lr': 0.00017898429141829803, 'samples': 17197440, 'steps': 89569, 'loss/train': 1.6595499515533447} 08/31/2021 05:20:57 - INFO - __main__ - Step 89571: {'lr': 0.00017897920329774676, 'samples': 17197632, 'steps': 89570, 'loss/train': 1.2162258625030518} 08/31/2021 05:20:58 - INFO - __main__ - Step 89572: {'lr': 0.0001789741152091963, 'samples': 17197824, 'steps': 89571, 'loss/train': 1.3995429277420044} 08/31/2021 05:20:58 - INFO - __main__ - Step 89573: {'lr': 0.0001789690271526491, 'samples': 17198016, 'steps': 89572, 'loss/train': 1.5993659496307373} 08/31/2021 05:20:58 - INFO - __main__ - Step 89574: {'lr': 0.0001789639391281074, 'samples': 17198208, 'steps': 89573, 'loss/train': 1.9115678071975708} 08/31/2021 05:21:00 - INFO - __main__ - Step 89575: {'lr': 0.00017895885113557337, 'samples': 17198400, 'steps': 89574, 'loss/train': 1.368856430053711} 08/31/2021 05:21:01 - INFO - __main__ - Step 89576: {'lr': 0.0001789537631750494, 'samples': 17198592, 'steps': 89575, 'loss/train': 1.2034332752227783} 08/31/2021 05:21:01 - INFO - __main__ - Step 89577: {'lr': 0.00017894867524653773, 'samples': 17198784, 'steps': 89576, 'loss/train': 1.3798075914382935} 08/31/2021 05:21:01 - INFO - __main__ - Step 89578: {'lr': 0.00017894358735004074, 'samples': 17198976, 'steps': 89577, 'loss/train': 1.3194148540496826} 08/31/2021 05:21:02 - INFO - __main__ - Step 89579: {'lr': 0.00017893849948556062, 'samples': 17199168, 'steps': 89578, 'loss/train': 1.0027713775634766} 08/31/2021 05:21:03 - INFO - __main__ - Step 89580: {'lr': 0.00017893341165309973, 'samples': 17199360, 'steps': 89579, 'loss/train': 1.356939435005188} 08/31/2021 05:21:04 - INFO - __main__ - Step 89581: {'lr': 0.00017892832385266037, 'samples': 17199552, 'steps': 89580, 'loss/train': 0.6588947176933289} 08/31/2021 05:21:04 - INFO - __main__ - Step 89582: {'lr': 0.00017892323608424479, 'samples': 17199744, 'steps': 89581, 'loss/train': 1.4648085832595825} 08/31/2021 05:21:04 - INFO - __main__ - Step 89583: {'lr': 0.0001789181483478553, 'samples': 17199936, 'steps': 89582, 'loss/train': 1.1557331085205078} 08/31/2021 05:21:05 - INFO - __main__ - Step 89584: {'lr': 0.0001789130606434942, 'samples': 17200128, 'steps': 89583, 'loss/train': 1.326011061668396} 08/31/2021 05:21:05 - INFO - __main__ - Step 89585: {'lr': 0.0001789079729711638, 'samples': 17200320, 'steps': 89584, 'loss/train': 1.246350646018982} 08/31/2021 05:21:07 - INFO - __main__ - Step 89586: {'lr': 0.00017890288533086641, 'samples': 17200512, 'steps': 89585, 'loss/train': 1.6406952142715454} 08/31/2021 05:21:07 - INFO - __main__ - Step 89587: {'lr': 0.00017889779772260427, 'samples': 17200704, 'steps': 89586, 'loss/train': 1.0112522840499878} 08/31/2021 05:21:07 - INFO - __main__ - Step 89588: {'lr': 0.00017889271014637966, 'samples': 17200896, 'steps': 89587, 'loss/train': 0.3486311137676239} 08/31/2021 05:21:08 - INFO - __main__ - Step 89589: {'lr': 0.00017888762260219487, 'samples': 17201088, 'steps': 89588, 'loss/train': 1.7990164756774902} 08/31/2021 05:21:08 - INFO - __main__ - Step 89590: {'lr': 0.00017888253509005226, 'samples': 17201280, 'steps': 89589, 'loss/train': 1.4770143032073975} 08/31/2021 05:21:10 - INFO - __main__ - Step 89591: {'lr': 0.00017887744760995404, 'samples': 17201472, 'steps': 89590, 'loss/train': 0.24731211364269257} 08/31/2021 05:21:11 - INFO - __main__ - Step 89592: {'lr': 0.00017887236016190256, 'samples': 17201664, 'steps': 89591, 'loss/train': 1.539939284324646} 08/31/2021 05:21:11 - INFO - __main__ - Step 89593: {'lr': 0.0001788672727459001, 'samples': 17201856, 'steps': 89592, 'loss/train': 0.7407469749450684} 08/31/2021 05:21:12 - INFO - __main__ - Step 89594: {'lr': 0.00017886218536194892, 'samples': 17202048, 'steps': 89593, 'loss/train': 1.2222745418548584} 08/31/2021 05:21:12 - INFO - __main__ - Step 89595: {'lr': 0.00017885709801005137, 'samples': 17202240, 'steps': 89594, 'loss/train': 1.2220019102096558} 08/31/2021 05:21:14 - INFO - __main__ - Step 89596: {'lr': 0.0001788520106902097, 'samples': 17202432, 'steps': 89595, 'loss/train': 1.6910935640335083} 08/31/2021 05:21:14 - INFO - __main__ - Step 89597: {'lr': 0.00017884692340242627, 'samples': 17202624, 'steps': 89596, 'loss/train': 1.5219953060150146} 08/31/2021 05:21:14 - INFO - __main__ - Step 89598: {'lr': 0.00017884183614670329, 'samples': 17202816, 'steps': 89597, 'loss/train': 1.346639633178711} 08/31/2021 05:21:15 - INFO - __main__ - Step 89599: {'lr': 0.00017883674892304308, 'samples': 17203008, 'steps': 89598, 'loss/train': 0.12204107642173767} 08/31/2021 05:21:15 - INFO - __main__ - Step 89600: {'lr': 0.00017883166173144789, 'samples': 17203200, 'steps': 89599, 'loss/train': 1.7520383596420288} 08/31/2021 05:21:17 - INFO - __main__ - Step 89601: {'lr': 0.00017882657457192014, 'samples': 17203392, 'steps': 89600, 'loss/train': 2.1083436012268066} 08/31/2021 05:21:17 - INFO - __main__ - Step 89602: {'lr': 0.00017882148744446198, 'samples': 17203584, 'steps': 89601, 'loss/train': 1.8192484378814697} 08/31/2021 05:21:18 - INFO - __main__ - Step 89603: {'lr': 0.00017881640034907577, 'samples': 17203776, 'steps': 89602, 'loss/train': 0.1196768656373024} 08/31/2021 05:21:18 - INFO - __main__ - Step 89604: {'lr': 0.00017881131328576378, 'samples': 17203968, 'steps': 89603, 'loss/train': 1.9249908924102783} 08/31/2021 05:21:18 - INFO - __main__ - Step 89605: {'lr': 0.0001788062262545283, 'samples': 17204160, 'steps': 89604, 'loss/train': 1.4826197624206543} 08/31/2021 05:21:21 - INFO - __main__ - Step 89606: {'lr': 0.00017880113925537166, 'samples': 17204352, 'steps': 89605, 'loss/train': 1.4504021406173706} 08/31/2021 05:21:21 - INFO - __main__ - Step 89607: {'lr': 0.0001787960522882961, 'samples': 17204544, 'steps': 89606, 'loss/train': 0.82563716173172} 08/31/2021 05:21:21 - INFO - __main__ - Step 89608: {'lr': 0.00017879096535330404, 'samples': 17204736, 'steps': 89607, 'loss/train': 1.4508343935012817} 08/31/2021 05:21:22 - INFO - __main__ - Step 89609: {'lr': 0.00017878587845039756, 'samples': 17204928, 'steps': 89608, 'loss/train': 0.5702003836631775} 08/31/2021 05:21:22 - INFO - __main__ - Step 89610: {'lr': 0.0001787807915795791, 'samples': 17205120, 'steps': 89609, 'loss/train': 0.9146798849105835} 08/31/2021 05:21:22 - INFO - __main__ - Step 89611: {'lr': 0.00017877570474085093, 'samples': 17205312, 'steps': 89610, 'loss/train': 1.7487767934799194} 08/31/2021 05:21:23 - INFO - __main__ - Step 89612: {'lr': 0.0001787706179342153, 'samples': 17205504, 'steps': 89611, 'loss/train': 0.13912338018417358} 08/31/2021 05:21:24 - INFO - __main__ - Step 89613: {'lr': 0.00017876553115967454, 'samples': 17205696, 'steps': 89612, 'loss/train': 1.0564281940460205} 08/31/2021 05:21:25 - INFO - __main__ - Step 89614: {'lr': 0.000178760444417231, 'samples': 17205888, 'steps': 89613, 'loss/train': 1.3292499780654907} 08/31/2021 05:21:25 - INFO - __main__ - Step 89615: {'lr': 0.0001787553577068868, 'samples': 17206080, 'steps': 89614, 'loss/train': 1.6412787437438965} 08/31/2021 05:21:26 - INFO - __main__ - Step 89616: {'lr': 0.0001787502710286444, 'samples': 17206272, 'steps': 89615, 'loss/train': 0.8761885762214661} 08/31/2021 05:21:26 - INFO - __main__ - Step 89617: {'lr': 0.00017874518438250596, 'samples': 17206464, 'steps': 89616, 'loss/train': 0.8032889366149902} 08/31/2021 05:21:27 - INFO - __main__ - Step 89618: {'lr': 0.0001787400977684739, 'samples': 17206656, 'steps': 89617, 'loss/train': 1.384266972541809} 08/31/2021 05:21:28 - INFO - __main__ - Step 89619: {'lr': 0.0001787350111865505, 'samples': 17206848, 'steps': 89618, 'loss/train': 0.916641354560852} 08/31/2021 05:21:28 - INFO - __main__ - Step 89620: {'lr': 0.00017872992463673792, 'samples': 17207040, 'steps': 89619, 'loss/train': 1.0109713077545166} 08/31/2021 05:21:28 - INFO - __main__ - Step 89621: {'lr': 0.00017872483811903856, 'samples': 17207232, 'steps': 89620, 'loss/train': 1.2760009765625} 08/31/2021 05:21:29 - INFO - __main__ - Step 89622: {'lr': 0.0001787197516334547, 'samples': 17207424, 'steps': 89621, 'loss/train': 1.1385971307754517} 08/31/2021 05:21:30 - INFO - __main__ - Step 89623: {'lr': 0.00017871466517998857, 'samples': 17207616, 'steps': 89622, 'loss/train': 1.692326307296753} 08/31/2021 05:21:31 - INFO - __main__ - Step 89624: {'lr': 0.0001787095787586426, 'samples': 17207808, 'steps': 89623, 'loss/train': 0.9638115167617798} 08/31/2021 05:21:31 - INFO - __main__ - Step 89625: {'lr': 0.00017870449236941888, 'samples': 17208000, 'steps': 89624, 'loss/train': 1.3289026021957397} 08/31/2021 05:21:31 - INFO - __main__ - Step 89626: {'lr': 0.00017869940601231987, 'samples': 17208192, 'steps': 89625, 'loss/train': 1.5479694604873657} 08/31/2021 05:21:32 - INFO - __main__ - Step 89627: {'lr': 0.00017869431968734785, 'samples': 17208384, 'steps': 89626, 'loss/train': 1.3210428953170776} 08/31/2021 05:21:32 - INFO - __main__ - Step 89628: {'lr': 0.00017868923339450508, 'samples': 17208576, 'steps': 89627, 'loss/train': 0.6997695565223694} 08/31/2021 05:21:34 - INFO - __main__ - Step 89629: {'lr': 0.00017868414713379378, 'samples': 17208768, 'steps': 89628, 'loss/train': 0.9110156297683716} 08/31/2021 05:21:34 - INFO - __main__ - Step 89630: {'lr': 0.00017867906090521634, 'samples': 17208960, 'steps': 89629, 'loss/train': 1.186086654663086} 08/31/2021 05:21:35 - INFO - __main__ - Step 89631: {'lr': 0.000178673974708775, 'samples': 17209152, 'steps': 89630, 'loss/train': 0.97236567735672} 08/31/2021 05:21:35 - INFO - __main__ - Step 89632: {'lr': 0.00017866888854447204, 'samples': 17209344, 'steps': 89631, 'loss/train': 2.180434226989746} 08/31/2021 05:21:35 - INFO - __main__ - Step 89633: {'lr': 0.00017866380241230985, 'samples': 17209536, 'steps': 89632, 'loss/train': 0.9094570875167847} 08/31/2021 05:21:37 - INFO - __main__ - Step 89634: {'lr': 0.0001786587163122906, 'samples': 17209728, 'steps': 89633, 'loss/train': 0.47992807626724243} 08/31/2021 05:21:37 - INFO - __main__ - Step 89635: {'lr': 0.0001786536302444166, 'samples': 17209920, 'steps': 89634, 'loss/train': 0.9843771457672119} 08/31/2021 05:21:37 - INFO - __main__ - Step 89636: {'lr': 0.0001786485442086902, 'samples': 17210112, 'steps': 89635, 'loss/train': 1.1198434829711914} 08/31/2021 05:21:38 - INFO - __main__ - Step 89637: {'lr': 0.00017864345820511364, 'samples': 17210304, 'steps': 89636, 'loss/train': 1.4236598014831543} 08/31/2021 05:21:38 - INFO - __main__ - Step 89638: {'lr': 0.00017863837223368927, 'samples': 17210496, 'steps': 89637, 'loss/train': 0.29143765568733215} 08/31/2021 05:21:40 - INFO - __main__ - Step 89639: {'lr': 0.00017863328629441933, 'samples': 17210688, 'steps': 89638, 'loss/train': 0.7382112741470337} 08/31/2021 05:21:40 - INFO - __main__ - Step 89640: {'lr': 0.00017862820038730615, 'samples': 17210880, 'steps': 89639, 'loss/train': 1.3467429876327515} 08/31/2021 05:21:41 - INFO - __main__ - Step 89641: {'lr': 0.0001786231145123521, 'samples': 17211072, 'steps': 89640, 'loss/train': 1.1740847826004028} 08/31/2021 05:21:41 - INFO - __main__ - Step 89642: {'lr': 0.00017861802866955926, 'samples': 17211264, 'steps': 89641, 'loss/train': 1.8124430179595947} 08/31/2021 05:21:41 - INFO - __main__ - Step 89643: {'lr': 0.00017861294285893004, 'samples': 17211456, 'steps': 89642, 'loss/train': 1.3059087991714478} 08/31/2021 05:21:44 - INFO - __main__ - Step 89644: {'lr': 0.00017860785708046672, 'samples': 17211648, 'steps': 89643, 'loss/train': 1.0348455905914307} 08/31/2021 05:21:44 - INFO - __main__ - Step 89645: {'lr': 0.00017860277133417156, 'samples': 17211840, 'steps': 89644, 'loss/train': 1.5732423067092896} 08/31/2021 05:21:44 - INFO - __main__ - Step 89646: {'lr': 0.00017859768562004697, 'samples': 17212032, 'steps': 89645, 'loss/train': 0.5909266471862793} 08/31/2021 05:21:45 - INFO - __main__ - Step 89647: {'lr': 0.00017859259993809512, 'samples': 17212224, 'steps': 89646, 'loss/train': 1.635990023612976} 08/31/2021 05:21:45 - INFO - __main__ - Step 89648: {'lr': 0.00017858751428831833, 'samples': 17212416, 'steps': 89647, 'loss/train': 0.952958345413208} 08/31/2021 05:21:47 - INFO - __main__ - Step 89649: {'lr': 0.00017858242867071895, 'samples': 17212608, 'steps': 89648, 'loss/train': 1.208156943321228} 08/31/2021 05:21:47 - INFO - __main__ - Step 89650: {'lr': 0.00017857734308529915, 'samples': 17212800, 'steps': 89649, 'loss/train': 1.4121358394622803} 08/31/2021 05:21:47 - INFO - __main__ - Step 89651: {'lr': 0.00017857225753206135, 'samples': 17212992, 'steps': 89650, 'loss/train': 1.2624859809875488} 08/31/2021 05:21:48 - INFO - __main__ - Step 89652: {'lr': 0.0001785671720110078, 'samples': 17213184, 'steps': 89651, 'loss/train': 1.5359340906143188} 08/31/2021 05:21:48 - INFO - __main__ - Step 89653: {'lr': 0.00017856208652214072, 'samples': 17213376, 'steps': 89652, 'loss/train': 1.2377887964248657} 08/31/2021 05:21:48 - INFO - __main__ - Step 89654: {'lr': 0.00017855700106546253, 'samples': 17213568, 'steps': 89653, 'loss/train': 1.6060264110565186} 08/31/2021 05:21:50 - INFO - __main__ - Step 89655: {'lr': 0.00017855191564097552, 'samples': 17213760, 'steps': 89654, 'loss/train': 1.08369779586792} 08/31/2021 05:21:50 - INFO - __main__ - Step 89656: {'lr': 0.00017854683024868184, 'samples': 17213952, 'steps': 89655, 'loss/train': 1.3446171283721924} 08/31/2021 05:21:51 - INFO - __main__ - Step 89657: {'lr': 0.00017854174488858384, 'samples': 17214144, 'steps': 89656, 'loss/train': 1.0662815570831299} 08/31/2021 05:21:51 - INFO - __main__ - Step 89658: {'lr': 0.00017853665956068382, 'samples': 17214336, 'steps': 89657, 'loss/train': 0.4817590117454529} 08/31/2021 05:21:51 - INFO - __main__ - Step 89659: {'lr': 0.00017853157426498407, 'samples': 17214528, 'steps': 89658, 'loss/train': 0.11681783199310303} 08/31/2021 05:21:53 - INFO - __main__ - Step 89660: {'lr': 0.00017852648900148688, 'samples': 17214720, 'steps': 89659, 'loss/train': 1.0143080949783325} 08/31/2021 05:21:54 - INFO - __main__ - Step 89661: {'lr': 0.00017852140377019461, 'samples': 17214912, 'steps': 89660, 'loss/train': 0.025945506989955902} 08/31/2021 05:21:54 - INFO - __main__ - Step 89662: {'lr': 0.00017851631857110944, 'samples': 17215104, 'steps': 89661, 'loss/train': 0.9619515538215637} 08/31/2021 05:21:54 - INFO - __main__ - Step 89663: {'lr': 0.0001785112334042337, 'samples': 17215296, 'steps': 89662, 'loss/train': 0.2542925775051117} 08/31/2021 05:21:55 - INFO - __main__ - Step 89664: {'lr': 0.00017850614826956973, 'samples': 17215488, 'steps': 89663, 'loss/train': 1.3359564542770386} 08/31/2021 05:21:55 - INFO - __main__ - Step 89665: {'lr': 0.00017850106316711977, 'samples': 17215680, 'steps': 89664, 'loss/train': 1.3199822902679443} 08/31/2021 05:21:57 - INFO - __main__ - Step 89666: {'lr': 0.00017849597809688618, 'samples': 17215872, 'steps': 89665, 'loss/train': 1.1052418947219849} 08/31/2021 05:21:57 - INFO - __main__ - Step 89667: {'lr': 0.0001784908930588711, 'samples': 17216064, 'steps': 89666, 'loss/train': 1.4632439613342285} 08/31/2021 05:21:57 - INFO - __main__ - Step 89668: {'lr': 0.00017848580805307712, 'samples': 17216256, 'steps': 89667, 'loss/train': 1.1535890102386475} 08/31/2021 05:21:58 - INFO - __main__ - Step 89669: {'lr': 0.0001784807230795062, 'samples': 17216448, 'steps': 89668, 'loss/train': 1.1235548257827759} 08/31/2021 05:21:58 - INFO - __main__ - Step 89670: {'lr': 0.00017847563813816074, 'samples': 17216640, 'steps': 89669, 'loss/train': 0.7953580617904663} 08/31/2021 05:21:59 - INFO - __main__ - Step 89671: {'lr': 0.00017847055322904305, 'samples': 17216832, 'steps': 89670, 'loss/train': 1.106484293937683} 08/31/2021 05:22:00 - INFO - __main__ - Step 89672: {'lr': 0.00017846546835215545, 'samples': 17217024, 'steps': 89671, 'loss/train': 1.339498519897461} 08/31/2021 05:22:00 - INFO - __main__ - Step 89673: {'lr': 0.0001784603835075002, 'samples': 17217216, 'steps': 89672, 'loss/train': 1.704330325126648} 08/31/2021 05:22:01 - INFO - __main__ - Step 89674: {'lr': 0.00017845529869507957, 'samples': 17217408, 'steps': 89673, 'loss/train': 0.8206011056900024} 08/31/2021 05:22:01 - INFO - __main__ - Step 89675: {'lr': 0.00017845021391489592, 'samples': 17217600, 'steps': 89674, 'loss/train': 1.5266224145889282} 08/31/2021 05:22:02 - INFO - __main__ - Step 89676: {'lr': 0.00017844512916695147, 'samples': 17217792, 'steps': 89675, 'loss/train': 1.2565357685089111} 08/31/2021 05:22:03 - INFO - __main__ - Step 89677: {'lr': 0.00017844004445124854, 'samples': 17217984, 'steps': 89676, 'loss/train': 1.9389315843582153} 08/31/2021 05:22:03 - INFO - __main__ - Step 89678: {'lr': 0.00017843495976778943, 'samples': 17218176, 'steps': 89677, 'loss/train': 1.2625840902328491} 08/31/2021 05:22:04 - INFO - __main__ - Step 89679: {'lr': 0.00017842987511657642, 'samples': 17218368, 'steps': 89678, 'loss/train': 1.0127942562103271} 08/31/2021 05:22:04 - INFO - __main__ - Step 89680: {'lr': 0.0001784247904976118, 'samples': 17218560, 'steps': 89679, 'loss/train': 1.6849277019500732} 08/31/2021 05:22:06 - INFO - __main__ - Step 89681: {'lr': 0.0001784197059108979, 'samples': 17218752, 'steps': 89680, 'loss/train': 1.380398154258728} 08/31/2021 05:22:06 - INFO - __main__ - Step 89682: {'lr': 0.00017841462135643704, 'samples': 17218944, 'steps': 89681, 'loss/train': 0.2746597230434418} 08/31/2021 05:22:06 - INFO - __main__ - Step 89683: {'lr': 0.00017840953683423137, 'samples': 17219136, 'steps': 89682, 'loss/train': 1.7101702690124512} 08/31/2021 05:22:07 - INFO - __main__ - Step 89684: {'lr': 0.00017840445234428324, 'samples': 17219328, 'steps': 89683, 'loss/train': 0.5692147612571716} 08/31/2021 05:22:07 - INFO - __main__ - Step 89685: {'lr': 0.00017839936788659495, 'samples': 17219520, 'steps': 89684, 'loss/train': 1.5620938539505005} 08/31/2021 05:22:09 - INFO - __main__ - Step 89686: {'lr': 0.0001783942834611688, 'samples': 17219712, 'steps': 89685, 'loss/train': 0.624501645565033} 08/31/2021 05:22:09 - INFO - __main__ - Step 89687: {'lr': 0.0001783891990680071, 'samples': 17219904, 'steps': 89686, 'loss/train': 0.9066065549850464} 08/31/2021 05:22:10 - INFO - __main__ - Step 89688: {'lr': 0.00017838411470711213, 'samples': 17220096, 'steps': 89687, 'loss/train': 0.9487035870552063} 08/31/2021 05:22:10 - INFO - __main__ - Step 89689: {'lr': 0.00017837903037848615, 'samples': 17220288, 'steps': 89688, 'loss/train': 0.28689149022102356} 08/31/2021 05:22:10 - INFO - __main__ - Step 89690: {'lr': 0.00017837394608213148, 'samples': 17220480, 'steps': 89689, 'loss/train': 1.1768985986709595} 08/31/2021 05:22:12 - INFO - __main__ - Step 89691: {'lr': 0.0001783688618180504, 'samples': 17220672, 'steps': 89690, 'loss/train': 1.5145095586776733} 08/31/2021 05:22:12 - INFO - __main__ - Step 89692: {'lr': 0.00017836377758624522, 'samples': 17220864, 'steps': 89691, 'loss/train': 1.1295603513717651} 08/31/2021 05:22:13 - INFO - __main__ - Step 89693: {'lr': 0.00017835869338671823, 'samples': 17221056, 'steps': 89692, 'loss/train': 1.067649483680725} 08/31/2021 05:22:13 - INFO - __main__ - Step 89694: {'lr': 0.00017835360921947168, 'samples': 17221248, 'steps': 89693, 'loss/train': 0.7092368006706238} 08/31/2021 05:22:13 - INFO - __main__ - Step 89695: {'lr': 0.00017834852508450799, 'samples': 17221440, 'steps': 89694, 'loss/train': 1.356563687324524} 08/31/2021 05:22:15 - INFO - __main__ - Step 89696: {'lr': 0.00017834344098182926, 'samples': 17221632, 'steps': 89695, 'loss/train': 1.5321671962738037} 08/31/2021 05:22:15 - INFO - __main__ - Step 89697: {'lr': 0.00017833835691143785, 'samples': 17221824, 'steps': 89696, 'loss/train': 1.1548491716384888} 08/31/2021 05:22:16 - INFO - __main__ - Step 89698: {'lr': 0.0001783332728733361, 'samples': 17222016, 'steps': 89697, 'loss/train': 0.8765019774436951} 08/31/2021 05:22:16 - INFO - __main__ - Step 89699: {'lr': 0.00017832818886752625, 'samples': 17222208, 'steps': 89698, 'loss/train': 0.5430566072463989} 08/31/2021 05:22:16 - INFO - __main__ - Step 89700: {'lr': 0.0001783231048940106, 'samples': 17222400, 'steps': 89699, 'loss/train': 0.6908502578735352} 08/31/2021 05:22:17 - INFO - __main__ - Step 89701: {'lr': 0.00017831802095279149, 'samples': 17222592, 'steps': 89700, 'loss/train': 0.9888712763786316} 08/31/2021 05:22:19 - INFO - __main__ - Step 89702: {'lr': 0.00017831293704387115, 'samples': 17222784, 'steps': 89701, 'loss/train': 0.9531211256980896} 08/31/2021 05:22:19 - INFO - __main__ - Step 89703: {'lr': 0.0001783078531672519, 'samples': 17222976, 'steps': 89702, 'loss/train': 1.595207691192627} 08/31/2021 05:22:19 - INFO - __main__ - Step 89704: {'lr': 0.000178302769322936, 'samples': 17223168, 'steps': 89703, 'loss/train': 1.1042519807815552} 08/31/2021 05:22:20 - INFO - __main__ - Step 89705: {'lr': 0.00017829768551092578, 'samples': 17223360, 'steps': 89704, 'loss/train': 1.4778138399124146} 08/31/2021 05:22:20 - INFO - __main__ - Step 89706: {'lr': 0.00017829260173122356, 'samples': 17223552, 'steps': 89705, 'loss/train': 0.910477340221405} 08/31/2021 05:22:22 - INFO - __main__ - Step 89707: {'lr': 0.00017828751798383154, 'samples': 17223744, 'steps': 89706, 'loss/train': 1.3327205181121826} 08/31/2021 05:22:22 - INFO - __main__ - Step 89708: {'lr': 0.00017828243426875218, 'samples': 17223936, 'steps': 89707, 'loss/train': 1.455584168434143} 08/31/2021 05:22:22 - INFO - __main__ - Step 89709: {'lr': 0.00017827735058598753, 'samples': 17224128, 'steps': 89708, 'loss/train': 0.8950501084327698} 08/31/2021 05:22:23 - INFO - __main__ - Step 89710: {'lr': 0.00017827226693554, 'samples': 17224320, 'steps': 89709, 'loss/train': 0.7918677926063538} 08/31/2021 05:22:23 - INFO - __main__ - Step 89711: {'lr': 0.0001782671833174119, 'samples': 17224512, 'steps': 89710, 'loss/train': 0.14316581189632416} 08/31/2021 05:22:25 - INFO - __main__ - Step 89712: {'lr': 0.0001782620997316055, 'samples': 17224704, 'steps': 89711, 'loss/train': 1.529651403427124} 08/31/2021 05:22:25 - INFO - __main__ - Step 89713: {'lr': 0.00017825701617812308, 'samples': 17224896, 'steps': 89712, 'loss/train': 0.5987410545349121} 08/31/2021 05:22:26 - INFO - __main__ - Step 89714: {'lr': 0.00017825193265696694, 'samples': 17225088, 'steps': 89713, 'loss/train': 1.5936425924301147} 08/31/2021 05:22:26 - INFO - __main__ - Step 89715: {'lr': 0.00017824684916813938, 'samples': 17225280, 'steps': 89714, 'loss/train': 1.2581913471221924} 08/31/2021 05:22:26 - INFO - __main__ - Step 89716: {'lr': 0.00017824176571164265, 'samples': 17225472, 'steps': 89715, 'loss/train': 1.2787055969238281} 08/31/2021 05:22:28 - INFO - __main__ - Step 89717: {'lr': 0.0001782366822874791, 'samples': 17225664, 'steps': 89716, 'loss/train': 0.5818040370941162} 08/31/2021 05:22:28 - INFO - __main__ - Step 89718: {'lr': 0.000178231598895651, 'samples': 17225856, 'steps': 89717, 'loss/train': 1.3152004480361938} 08/31/2021 05:22:29 - INFO - __main__ - Step 89719: {'lr': 0.00017822651553616063, 'samples': 17226048, 'steps': 89718, 'loss/train': 1.3132346868515015} 08/31/2021 05:22:29 - INFO - __main__ - Step 89720: {'lr': 0.00017822143220901034, 'samples': 17226240, 'steps': 89719, 'loss/train': 0.4948262572288513} 08/31/2021 05:22:29 - INFO - __main__ - Step 89721: {'lr': 0.0001782163489142023, 'samples': 17226432, 'steps': 89720, 'loss/train': 1.213571310043335} 08/31/2021 05:22:31 - INFO - __main__ - Step 89722: {'lr': 0.0001782112656517389, 'samples': 17226624, 'steps': 89721, 'loss/train': 1.3606311082839966} 08/31/2021 05:22:31 - INFO - __main__ - Step 89723: {'lr': 0.00017820618242162238, 'samples': 17226816, 'steps': 89722, 'loss/train': 1.0563095808029175} 08/31/2021 05:22:32 - INFO - __main__ - Step 89724: {'lr': 0.00017820109922385503, 'samples': 17227008, 'steps': 89723, 'loss/train': 1.2632648944854736} 08/31/2021 05:22:32 - INFO - __main__ - Step 89725: {'lr': 0.00017819601605843915, 'samples': 17227200, 'steps': 89724, 'loss/train': 1.3275374174118042} 08/31/2021 05:22:32 - INFO - __main__ - Step 89726: {'lr': 0.00017819093292537706, 'samples': 17227392, 'steps': 89725, 'loss/train': 1.4093060493469238} 08/31/2021 05:22:33 - INFO - __main__ - Step 89727: {'lr': 0.000178185849824671, 'samples': 17227584, 'steps': 89726, 'loss/train': 0.9247557520866394} 08/31/2021 05:22:34 - INFO - __main__ - Step 89728: {'lr': 0.00017818076675632334, 'samples': 17227776, 'steps': 89727, 'loss/train': 1.8632917404174805} 08/31/2021 05:22:35 - INFO - __main__ - Step 89729: {'lr': 0.00017817568372033627, 'samples': 17227968, 'steps': 89728, 'loss/train': 1.6597529649734497} 08/31/2021 05:22:35 - INFO - __main__ - Step 89730: {'lr': 0.00017817060071671212, 'samples': 17228160, 'steps': 89729, 'loss/train': 0.9289268255233765} 08/31/2021 05:22:35 - INFO - __main__ - Step 89731: {'lr': 0.00017816551774545327, 'samples': 17228352, 'steps': 89730, 'loss/train': 0.6885883808135986} 08/31/2021 05:22:36 - INFO - __main__ - Step 89732: {'lr': 0.00017816043480656186, 'samples': 17228544, 'steps': 89731, 'loss/train': 0.871190071105957} 08/31/2021 05:22:37 - INFO - __main__ - Step 89733: {'lr': 0.00017815535190004027, 'samples': 17228736, 'steps': 89732, 'loss/train': 1.0198112726211548} 08/31/2021 05:22:38 - INFO - __main__ - Step 89734: {'lr': 0.00017815026902589075, 'samples': 17228928, 'steps': 89733, 'loss/train': 0.8489392995834351} 08/31/2021 05:22:38 - INFO - __main__ - Step 89735: {'lr': 0.00017814518618411567, 'samples': 17229120, 'steps': 89734, 'loss/train': 1.1037118434906006} 08/31/2021 05:22:38 - INFO - __main__ - Step 89736: {'lr': 0.0001781401033747172, 'samples': 17229312, 'steps': 89735, 'loss/train': 1.0976097583770752} 08/31/2021 05:22:39 - INFO - __main__ - Step 89737: {'lr': 0.0001781350205976977, 'samples': 17229504, 'steps': 89736, 'loss/train': 1.0872188806533813} 08/31/2021 05:22:40 - INFO - __main__ - Step 89738: {'lr': 0.00017812993785305944, 'samples': 17229696, 'steps': 89737, 'loss/train': 0.2888268530368805} 08/31/2021 05:22:41 - INFO - __main__ - Step 89739: {'lr': 0.00017812485514080473, 'samples': 17229888, 'steps': 89738, 'loss/train': 1.5349751710891724} 08/31/2021 05:22:41 - INFO - __main__ - Step 89740: {'lr': 0.00017811977246093587, 'samples': 17230080, 'steps': 89739, 'loss/train': 0.8548718094825745} 08/31/2021 05:22:41 - INFO - __main__ - Step 89741: {'lr': 0.00017811468981345508, 'samples': 17230272, 'steps': 89740, 'loss/train': 0.22610585391521454} 08/31/2021 05:22:42 - INFO - __main__ - Step 89742: {'lr': 0.0001781096071983648, 'samples': 17230464, 'steps': 89741, 'loss/train': 1.0039865970611572} 08/31/2021 05:22:43 - INFO - __main__ - Step 89743: {'lr': 0.00017810452461566718, 'samples': 17230656, 'steps': 89742, 'loss/train': 0.664352297782898} 08/31/2021 05:22:44 - INFO - __main__ - Step 89744: {'lr': 0.0001780994420653645, 'samples': 17230848, 'steps': 89743, 'loss/train': 1.5906562805175781} 08/31/2021 05:22:44 - INFO - __main__ - Step 89745: {'lr': 0.0001780943595474591, 'samples': 17231040, 'steps': 89744, 'loss/train': 1.1545660495758057} 08/31/2021 05:22:44 - INFO - __main__ - Step 89746: {'lr': 0.00017808927706195333, 'samples': 17231232, 'steps': 89745, 'loss/train': 0.3939502537250519} 08/31/2021 05:22:45 - INFO - __main__ - Step 89747: {'lr': 0.0001780841946088494, 'samples': 17231424, 'steps': 89746, 'loss/train': 1.265552282333374} 08/31/2021 05:22:46 - INFO - __main__ - Step 89748: {'lr': 0.0001780791121881496, 'samples': 17231616, 'steps': 89747, 'loss/train': 1.2824472188949585} 08/31/2021 05:22:47 - INFO - __main__ - Step 89749: {'lr': 0.0001780740297998563, 'samples': 17231808, 'steps': 89748, 'loss/train': 1.0109020471572876} 08/31/2021 05:22:47 - INFO - __main__ - Step 89750: {'lr': 0.00017806894744397172, 'samples': 17232000, 'steps': 89749, 'loss/train': 1.331814169883728} 08/31/2021 05:22:47 - INFO - __main__ - Step 89751: {'lr': 0.0001780638651204981, 'samples': 17232192, 'steps': 89750, 'loss/train': 0.2596592903137207} 08/31/2021 05:22:48 - INFO - __main__ - Step 89752: {'lr': 0.00017805878282943784, 'samples': 17232384, 'steps': 89751, 'loss/train': 1.1898322105407715} 08/31/2021 05:22:50 - INFO - __main__ - Step 89753: {'lr': 0.00017805370057079323, 'samples': 17232576, 'steps': 89752, 'loss/train': 1.5939167737960815} 08/31/2021 05:22:50 - INFO - __main__ - Step 89754: {'lr': 0.00017804861834456643, 'samples': 17232768, 'steps': 89753, 'loss/train': 1.3076562881469727} 08/31/2021 05:22:51 - INFO - __main__ - Step 89755: {'lr': 0.00017804353615075985, 'samples': 17232960, 'steps': 89754, 'loss/train': 1.2973370552062988} 08/31/2021 05:22:51 - INFO - __main__ - Step 89756: {'lr': 0.00017803845398937573, 'samples': 17233152, 'steps': 89755, 'loss/train': 1.1850563287734985} 08/31/2021 05:22:51 - INFO - __main__ - Step 89757: {'lr': 0.00017803337186041634, 'samples': 17233344, 'steps': 89756, 'loss/train': 1.9657647609710693} 08/31/2021 05:22:53 - INFO - __main__ - Step 89758: {'lr': 0.00017802828976388403, 'samples': 17233536, 'steps': 89757, 'loss/train': 1.1993526220321655} 08/31/2021 05:22:53 - INFO - __main__ - Step 89759: {'lr': 0.0001780232076997811, 'samples': 17233728, 'steps': 89758, 'loss/train': 1.5471088886260986} 08/31/2021 05:22:53 - INFO - __main__ - Step 89760: {'lr': 0.00017801812566810974, 'samples': 17233920, 'steps': 89759, 'loss/train': 0.9718987941741943} 08/31/2021 05:22:54 - INFO - __main__ - Step 89761: {'lr': 0.00017801304366887234, 'samples': 17234112, 'steps': 89760, 'loss/train': 1.1990445852279663} 08/31/2021 05:22:54 - INFO - __main__ - Step 89762: {'lr': 0.0001780079617020712, 'samples': 17234304, 'steps': 89761, 'loss/train': 1.5024490356445312} 08/31/2021 05:22:56 - INFO - __main__ - Step 89763: {'lr': 0.00017800287976770847, 'samples': 17234496, 'steps': 89762, 'loss/train': 1.5076426267623901} 08/31/2021 05:22:56 - INFO - __main__ - Step 89764: {'lr': 0.0001779977978657866, 'samples': 17234688, 'steps': 89763, 'loss/train': 1.5447204113006592} 08/31/2021 05:22:56 - INFO - __main__ - Step 89765: {'lr': 0.0001779927159963078, 'samples': 17234880, 'steps': 89764, 'loss/train': 0.9487125873565674} 08/31/2021 05:22:57 - INFO - __main__ - Step 89766: {'lr': 0.00017798763415927433, 'samples': 17235072, 'steps': 89765, 'loss/train': 1.086397409439087} 08/31/2021 05:22:57 - INFO - __main__ - Step 89767: {'lr': 0.00017798255235468852, 'samples': 17235264, 'steps': 89766, 'loss/train': 0.6574840545654297} 08/31/2021 05:22:57 - INFO - __main__ - Step 89768: {'lr': 0.00017797747058255264, 'samples': 17235456, 'steps': 89767, 'loss/train': 0.7966678738594055} 08/31/2021 05:22:59 - INFO - __main__ - Step 89769: {'lr': 0.00017797238884286905, 'samples': 17235648, 'steps': 89768, 'loss/train': 0.9805670976638794} 08/31/2021 05:23:00 - INFO - __main__ - Step 89770: {'lr': 0.00017796730713563996, 'samples': 17235840, 'steps': 89769, 'loss/train': 0.8425589799880981} 08/31/2021 05:23:00 - INFO - __main__ - Step 89771: {'lr': 0.0001779622254608677, 'samples': 17236032, 'steps': 89770, 'loss/train': 1.0044044256210327} 08/31/2021 05:23:00 - INFO - __main__ - Step 89772: {'lr': 0.00017795714381855458, 'samples': 17236224, 'steps': 89771, 'loss/train': 0.7922032475471497} 08/31/2021 05:23:01 - INFO - __main__ - Step 89773: {'lr': 0.0001779520622087028, 'samples': 17236416, 'steps': 89772, 'loss/train': 0.9737626314163208} 08/31/2021 05:23:02 - INFO - __main__ - Step 89774: {'lr': 0.00017794698063131476, 'samples': 17236608, 'steps': 89773, 'loss/train': 0.8036304116249084} 08/31/2021 05:23:03 - INFO - __main__ - Step 89775: {'lr': 0.0001779418990863927, 'samples': 17236800, 'steps': 89774, 'loss/train': 0.23969878256320953} 08/31/2021 05:23:03 - INFO - __main__ - Step 89776: {'lr': 0.00017793681757393898, 'samples': 17236992, 'steps': 89775, 'loss/train': 0.04038698598742485} 08/31/2021 05:23:04 - INFO - __main__ - Step 89777: {'lr': 0.00017793173609395571, 'samples': 17237184, 'steps': 89776, 'loss/train': 0.8368945717811584} 08/31/2021 05:23:04 - INFO - __main__ - Step 89778: {'lr': 0.0001779266546464453, 'samples': 17237376, 'steps': 89777, 'loss/train': 1.0382224321365356} 08/31/2021 05:23:04 - INFO - __main__ - Step 89779: {'lr': 0.00017792157323141003, 'samples': 17237568, 'steps': 89778, 'loss/train': 0.9884607195854187} 08/31/2021 05:23:06 - INFO - __main__ - Step 89780: {'lr': 0.0001779164918488522, 'samples': 17237760, 'steps': 89779, 'loss/train': 1.115096926689148} 08/31/2021 05:23:06 - INFO - __main__ - Step 89781: {'lr': 0.00017791141049877408, 'samples': 17237952, 'steps': 89780, 'loss/train': 1.2016035318374634} 08/31/2021 05:23:07 - INFO - __main__ - Step 89782: {'lr': 0.00017790632918117795, 'samples': 17238144, 'steps': 89781, 'loss/train': 1.0337029695510864} 08/31/2021 05:23:07 - INFO - __main__ - Step 89783: {'lr': 0.00017790124789606612, 'samples': 17238336, 'steps': 89782, 'loss/train': 1.5523744821548462} 08/31/2021 05:23:07 - INFO - __main__ - Step 89784: {'lr': 0.0001778961666434409, 'samples': 17238528, 'steps': 89783, 'loss/train': 1.586200475692749} 08/31/2021 05:23:09 - INFO - __main__ - Step 89785: {'lr': 0.0001778910854233045, 'samples': 17238720, 'steps': 89784, 'loss/train': 0.057208362966775894} 08/31/2021 05:23:10 - INFO - __main__ - Step 89786: {'lr': 0.0001778860042356593, 'samples': 17238912, 'steps': 89785, 'loss/train': 1.5670713186264038} 08/31/2021 05:23:10 - INFO - __main__ - Step 89787: {'lr': 0.00017788092308050756, 'samples': 17239104, 'steps': 89786, 'loss/train': 0.8447813987731934} 08/31/2021 05:23:10 - INFO - __main__ - Step 89788: {'lr': 0.00017787584195785156, 'samples': 17239296, 'steps': 89787, 'loss/train': 1.2821714878082275} 08/31/2021 05:23:11 - INFO - __main__ - Step 89789: {'lr': 0.00017787076086769372, 'samples': 17239488, 'steps': 89788, 'loss/train': 0.9899274110794067} 08/31/2021 05:23:12 - INFO - __main__ - Step 89790: {'lr': 0.00017786567981003604, 'samples': 17239680, 'steps': 89789, 'loss/train': 1.1246355772018433} 08/31/2021 05:23:12 - INFO - __main__ - Step 89791: {'lr': 0.00017786059878488103, 'samples': 17239872, 'steps': 89790, 'loss/train': 0.6460076570510864} 08/31/2021 05:23:13 - INFO - __main__ - Step 89792: {'lr': 0.00017785551779223087, 'samples': 17240064, 'steps': 89791, 'loss/train': 1.4592654705047607} 08/31/2021 05:23:13 - INFO - __main__ - Step 89793: {'lr': 0.00017785043683208793, 'samples': 17240256, 'steps': 89792, 'loss/train': 1.04425847530365} 08/31/2021 05:23:13 - INFO - __main__ - Step 89794: {'lr': 0.00017784535590445447, 'samples': 17240448, 'steps': 89793, 'loss/train': 1.7441010475158691} 08/31/2021 05:23:15 - INFO - __main__ - Step 89795: {'lr': 0.00017784027500933276, 'samples': 17240640, 'steps': 89794, 'loss/train': 0.8301870226860046} 08/31/2021 05:23:16 - INFO - __main__ - Step 89796: {'lr': 0.0001778351941467251, 'samples': 17240832, 'steps': 89795, 'loss/train': 1.5415228605270386} 08/31/2021 05:23:16 - INFO - __main__ - Step 89797: {'lr': 0.00017783011331663385, 'samples': 17241024, 'steps': 89796, 'loss/train': 0.6752435564994812} 08/31/2021 05:23:17 - INFO - __main__ - Step 89798: {'lr': 0.00017782503251906117, 'samples': 17241216, 'steps': 89797, 'loss/train': 0.8689156770706177} 08/31/2021 05:23:17 - INFO - __main__ - Step 89799: {'lr': 0.00017781995175400944, 'samples': 17241408, 'steps': 89798, 'loss/train': 1.0618126392364502} 08/31/2021 05:23:17 - INFO - __main__ - Step 89800: {'lr': 0.00017781487102148095, 'samples': 17241600, 'steps': 89799, 'loss/train': 0.034944262355566025} 08/31/2021 05:23:19 - INFO - __main__ - Step 89801: {'lr': 0.00017780979032147793, 'samples': 17241792, 'steps': 89800, 'loss/train': 0.047974031418561935} 08/31/2021 05:23:19 - INFO - __main__ - Step 89802: {'lr': 0.0001778047096540027, 'samples': 17241984, 'steps': 89801, 'loss/train': 0.9168676733970642} 08/31/2021 05:23:20 - INFO - __main__ - Step 89803: {'lr': 0.00017779962901905773, 'samples': 17242176, 'steps': 89802, 'loss/train': 0.9945697784423828} 08/31/2021 05:23:20 - INFO - __main__ - Step 89804: {'lr': 0.00017779454841664494, 'samples': 17242368, 'steps': 89803, 'loss/train': 0.8898043036460876} 08/31/2021 05:23:21 - INFO - __main__ - Step 89805: {'lr': 0.00017778946784676686, 'samples': 17242560, 'steps': 89804, 'loss/train': 1.2620174884796143} 08/31/2021 05:23:21 - INFO - __main__ - Step 89806: {'lr': 0.0001777843873094257, 'samples': 17242752, 'steps': 89805, 'loss/train': 0.4753352999687195} 08/31/2021 05:23:23 - INFO - __main__ - Step 89807: {'lr': 0.00017777930680462381, 'samples': 17242944, 'steps': 89806, 'loss/train': 1.3091894388198853} 08/31/2021 05:23:23 - INFO - __main__ - Step 89808: {'lr': 0.00017777422633236345, 'samples': 17243136, 'steps': 89807, 'loss/train': 1.2107104063034058} 08/31/2021 05:23:24 - INFO - __main__ - Step 89809: {'lr': 0.0001777691458926469, 'samples': 17243328, 'steps': 89808, 'loss/train': 1.2258570194244385} 08/31/2021 05:23:24 - INFO - __main__ - Step 89810: {'lr': 0.00017776406548547646, 'samples': 17243520, 'steps': 89809, 'loss/train': 0.9449456334114075} 08/31/2021 05:23:24 - INFO - __main__ - Step 89811: {'lr': 0.0001777589851108544, 'samples': 17243712, 'steps': 89810, 'loss/train': 1.4050748348236084} 08/31/2021 05:23:26 - INFO - __main__ - Step 89812: {'lr': 0.00017775390476878306, 'samples': 17243904, 'steps': 89811, 'loss/train': 1.627867341041565} 08/31/2021 05:23:27 - INFO - __main__ - Step 89813: {'lr': 0.00017774882445926465, 'samples': 17244096, 'steps': 89812, 'loss/train': 1.7039852142333984} 08/31/2021 05:23:27 - INFO - __main__ - Step 89814: {'lr': 0.00017774374418230154, 'samples': 17244288, 'steps': 89813, 'loss/train': 1.408022403717041} 08/31/2021 05:23:27 - INFO - __main__ - Step 89815: {'lr': 0.000177738663937896, 'samples': 17244480, 'steps': 89814, 'loss/train': 1.2398419380187988} 08/31/2021 05:23:28 - INFO - __main__ - Step 89816: {'lr': 0.00017773358372605037, 'samples': 17244672, 'steps': 89815, 'loss/train': 1.1903449296951294} 08/31/2021 05:23:29 - INFO - __main__ - Step 89817: {'lr': 0.00017772850354676677, 'samples': 17244864, 'steps': 89816, 'loss/train': 1.5614910125732422} 08/31/2021 05:23:30 - INFO - __main__ - Step 89818: {'lr': 0.0001777234234000476, 'samples': 17245056, 'steps': 89817, 'loss/train': 0.910092294216156} 08/31/2021 05:23:30 - INFO - __main__ - Step 89819: {'lr': 0.00017771834328589515, 'samples': 17245248, 'steps': 89818, 'loss/train': 1.38117253780365} 08/31/2021 05:23:30 - INFO - __main__ - Step 89820: {'lr': 0.0001777132632043117, 'samples': 17245440, 'steps': 89819, 'loss/train': 1.1337252855300903} 08/31/2021 05:23:31 - INFO - __main__ - Step 89821: {'lr': 0.00017770818315529952, 'samples': 17245632, 'steps': 89820, 'loss/train': 1.0304540395736694} 08/31/2021 05:23:31 - INFO - __main__ - Step 89822: {'lr': 0.00017770310313886093, 'samples': 17245824, 'steps': 89821, 'loss/train': 1.2377010583877563} 08/31/2021 05:23:33 - INFO - __main__ - Step 89823: {'lr': 0.00017769802315499821, 'samples': 17246016, 'steps': 89822, 'loss/train': 1.0827525854110718} 08/31/2021 05:23:33 - INFO - __main__ - Step 89824: {'lr': 0.00017769294320371367, 'samples': 17246208, 'steps': 89823, 'loss/train': 1.2207750082015991} 08/31/2021 05:23:34 - INFO - __main__ - Step 89825: {'lr': 0.00017768786328500953, 'samples': 17246400, 'steps': 89824, 'loss/train': 1.8273965120315552} 08/31/2021 05:23:34 - INFO - __main__ - Step 89826: {'lr': 0.0001776827833988881, 'samples': 17246592, 'steps': 89825, 'loss/train': 1.1859679222106934} 08/31/2021 05:23:34 - INFO - __main__ - Step 89827: {'lr': 0.00017767770354535172, 'samples': 17246784, 'steps': 89826, 'loss/train': 0.24259734153747559} 08/31/2021 05:23:36 - INFO - __main__ - Step 89828: {'lr': 0.0001776726237244027, 'samples': 17246976, 'steps': 89827, 'loss/train': 0.5701987147331238} 08/31/2021 05:23:36 - INFO - __main__ - Step 89829: {'lr': 0.00017766754393604332, 'samples': 17247168, 'steps': 89828, 'loss/train': 0.7196890711784363} 08/31/2021 05:23:37 - INFO - __main__ - Step 89830: {'lr': 0.00017766246418027574, 'samples': 17247360, 'steps': 89829, 'loss/train': 0.5059236288070679} 08/31/2021 05:23:37 - INFO - __main__ - Step 89831: {'lr': 0.00017765738445710234, 'samples': 17247552, 'steps': 89830, 'loss/train': 0.6641010642051697} 08/31/2021 05:23:37 - INFO - __main__ - Step 89832: {'lr': 0.00017765230476652542, 'samples': 17247744, 'steps': 89831, 'loss/train': 1.0065895318984985} 08/31/2021 05:23:39 - INFO - __main__ - Step 89833: {'lr': 0.00017764722510854724, 'samples': 17247936, 'steps': 89832, 'loss/train': 1.249830722808838} 08/31/2021 05:23:39 - INFO - __main__ - Step 89834: {'lr': 0.0001776421454831701, 'samples': 17248128, 'steps': 89833, 'loss/train': 2.2678966522216797} 08/31/2021 05:23:40 - INFO - __main__ - Step 89835: {'lr': 0.0001776370658903963, 'samples': 17248320, 'steps': 89834, 'loss/train': 1.5424619913101196} 08/31/2021 05:23:40 - INFO - __main__ - Step 89836: {'lr': 0.00017763198633022814, 'samples': 17248512, 'steps': 89835, 'loss/train': 1.5559054613113403} 08/31/2021 05:23:40 - INFO - __main__ - Step 89837: {'lr': 0.00017762690680266785, 'samples': 17248704, 'steps': 89836, 'loss/train': 1.1326122283935547} 08/31/2021 05:23:43 - INFO - __main__ - Step 89838: {'lr': 0.00017762182730771781, 'samples': 17248896, 'steps': 89837, 'loss/train': 0.08155541121959686} 08/31/2021 05:23:43 - INFO - __main__ - Step 89839: {'lr': 0.0001776167478453802, 'samples': 17249088, 'steps': 89838, 'loss/train': 0.5978497862815857} 08/31/2021 05:23:43 - INFO - __main__ - Step 89840: {'lr': 0.0001776116684156574, 'samples': 17249280, 'steps': 89839, 'loss/train': 1.1640783548355103} 08/31/2021 05:23:44 - INFO - __main__ - Step 89841: {'lr': 0.00017760658901855167, 'samples': 17249472, 'steps': 89840, 'loss/train': 0.7991330623626709} 08/31/2021 05:23:44 - INFO - __main__ - Step 89842: {'lr': 0.00017760150965406528, 'samples': 17249664, 'steps': 89841, 'loss/train': 0.2009931057691574} 08/31/2021 05:23:46 - INFO - __main__ - Step 89843: {'lr': 0.00017759643032220064, 'samples': 17249856, 'steps': 89842, 'loss/train': 1.0244191884994507} 08/31/2021 05:23:46 - INFO - __main__ - Step 89844: {'lr': 0.00017759135102295983, 'samples': 17250048, 'steps': 89843, 'loss/train': 1.5399012565612793} 08/31/2021 05:23:46 - INFO - __main__ - Step 89845: {'lr': 0.00017758627175634524, 'samples': 17250240, 'steps': 89844, 'loss/train': 1.3968851566314697} 08/31/2021 05:23:47 - INFO - __main__ - Step 89846: {'lr': 0.00017758119252235914, 'samples': 17250432, 'steps': 89845, 'loss/train': 1.0122138261795044} 08/31/2021 05:23:47 - INFO - __main__ - Step 89847: {'lr': 0.00017757611332100388, 'samples': 17250624, 'steps': 89846, 'loss/train': 1.245772123336792} 08/31/2021 05:23:49 - INFO - __main__ - Step 89848: {'lr': 0.00017757103415228168, 'samples': 17250816, 'steps': 89847, 'loss/train': 0.9754287600517273} 08/31/2021 05:23:49 - INFO - __main__ - Step 89849: {'lr': 0.00017756595501619484, 'samples': 17251008, 'steps': 89848, 'loss/train': 1.192352533340454} 08/31/2021 05:23:50 - INFO - __main__ - Step 89850: {'lr': 0.00017756087591274566, 'samples': 17251200, 'steps': 89849, 'loss/train': 1.3905653953552246} 08/31/2021 05:23:50 - INFO - __main__ - Step 89851: {'lr': 0.00017755579684193646, 'samples': 17251392, 'steps': 89850, 'loss/train': 1.8062859773635864} 08/31/2021 05:23:50 - INFO - __main__ - Step 89852: {'lr': 0.00017755071780376953, 'samples': 17251584, 'steps': 89851, 'loss/train': 1.1603715419769287} 08/31/2021 05:23:52 - INFO - __main__ - Step 89853: {'lr': 0.00017754563879824706, 'samples': 17251776, 'steps': 89852, 'loss/train': 0.8023338913917542} 08/31/2021 05:23:52 - INFO - __main__ - Step 89854: {'lr': 0.00017754055982537143, 'samples': 17251968, 'steps': 89853, 'loss/train': 1.1357157230377197} 08/31/2021 05:23:53 - INFO - __main__ - Step 89855: {'lr': 0.00017753548088514498, 'samples': 17252160, 'steps': 89854, 'loss/train': 0.08285296708345413} 08/31/2021 05:23:53 - INFO - __main__ - Step 89856: {'lr': 0.0001775304019775699, 'samples': 17252352, 'steps': 89855, 'loss/train': 1.2263215780258179} 08/31/2021 05:23:53 - INFO - __main__ - Step 89857: {'lr': 0.00017752532310264847, 'samples': 17252544, 'steps': 89856, 'loss/train': 1.5100442171096802} 08/31/2021 05:23:54 - INFO - __main__ - Step 89858: {'lr': 0.000177520244260383, 'samples': 17252736, 'steps': 89857, 'loss/train': 1.5615506172180176} 08/31/2021 05:23:56 - INFO - __main__ - Step 89859: {'lr': 0.00017751516545077577, 'samples': 17252928, 'steps': 89858, 'loss/train': 1.4710721969604492} 08/31/2021 05:23:56 - INFO - __main__ - Step 89860: {'lr': 0.0001775100866738291, 'samples': 17253120, 'steps': 89859, 'loss/train': 1.6404401063919067} 08/31/2021 05:23:56 - INFO - __main__ - Step 89861: {'lr': 0.00017750500792954526, 'samples': 17253312, 'steps': 89860, 'loss/train': 1.6858868598937988} 08/31/2021 05:23:57 - INFO - __main__ - Step 89862: {'lr': 0.00017749992921792658, 'samples': 17253504, 'steps': 89861, 'loss/train': 1.2919323444366455} 08/31/2021 05:23:57 - INFO - __main__ - Step 89863: {'lr': 0.0001774948505389753, 'samples': 17253696, 'steps': 89862, 'loss/train': 1.2901700735092163} 08/31/2021 05:23:59 - INFO - __main__ - Step 89864: {'lr': 0.0001774897718926937, 'samples': 17253888, 'steps': 89863, 'loss/train': 0.8392931222915649} 08/31/2021 05:23:59 - INFO - __main__ - Step 89865: {'lr': 0.0001774846932790841, 'samples': 17254080, 'steps': 89864, 'loss/train': 0.34320002794265747} 08/31/2021 05:23:59 - INFO - __main__ - Step 89866: {'lr': 0.00017747961469814883, 'samples': 17254272, 'steps': 89865, 'loss/train': 0.8745949864387512} 08/31/2021 05:24:00 - INFO - __main__ - Step 89867: {'lr': 0.00017747453614989006, 'samples': 17254464, 'steps': 89866, 'loss/train': 1.2785218954086304} 08/31/2021 05:24:00 - INFO - __main__ - Step 89868: {'lr': 0.00017746945763431017, 'samples': 17254656, 'steps': 89867, 'loss/train': 1.7959644794464111} 08/31/2021 05:24:02 - INFO - __main__ - Step 89869: {'lr': 0.00017746437915141142, 'samples': 17254848, 'steps': 89868, 'loss/train': 1.2489157915115356} 08/31/2021 05:24:02 - INFO - __main__ - Step 89870: {'lr': 0.00017745930070119616, 'samples': 17255040, 'steps': 89869, 'loss/train': 1.4023634195327759} 08/31/2021 05:24:03 - INFO - __main__ - Step 89871: {'lr': 0.00017745422228366653, 'samples': 17255232, 'steps': 89870, 'loss/train': 0.6750486493110657} 08/31/2021 05:24:03 - INFO - __main__ - Step 89872: {'lr': 0.00017744914389882495, 'samples': 17255424, 'steps': 89871, 'loss/train': 0.14330896735191345} 08/31/2021 05:24:03 - INFO - __main__ - Step 89873: {'lr': 0.00017744406554667363, 'samples': 17255616, 'steps': 89872, 'loss/train': 1.2049309015274048} 08/31/2021 05:24:05 - INFO - __main__ - Step 89874: {'lr': 0.0001774389872272149, 'samples': 17255808, 'steps': 89873, 'loss/train': 1.1109592914581299} 08/31/2021 05:24:06 - INFO - __main__ - Step 89875: {'lr': 0.00017743390894045107, 'samples': 17256000, 'steps': 89874, 'loss/train': 0.8979440331459045} 08/31/2021 05:24:06 - INFO - __main__ - Step 89876: {'lr': 0.00017742883068638446, 'samples': 17256192, 'steps': 89875, 'loss/train': 0.9187178611755371} 08/31/2021 05:24:06 - INFO - __main__ - Step 89877: {'lr': 0.00017742375246501723, 'samples': 17256384, 'steps': 89876, 'loss/train': 1.3163366317749023} 08/31/2021 05:24:07 - INFO - __main__ - Step 89878: {'lr': 0.00017741867427635173, 'samples': 17256576, 'steps': 89877, 'loss/train': 0.6540854573249817} 08/31/2021 05:24:07 - INFO - __main__ - Step 89879: {'lr': 0.00017741359612039026, 'samples': 17256768, 'steps': 89878, 'loss/train': 1.0544923543930054} 08/31/2021 05:24:09 - INFO - __main__ - Step 89880: {'lr': 0.0001774085179971351, 'samples': 17256960, 'steps': 89879, 'loss/train': 1.4425584077835083} 08/31/2021 05:24:09 - INFO - __main__ - Step 89881: {'lr': 0.00017740343990658853, 'samples': 17257152, 'steps': 89880, 'loss/train': 0.07896904647350311} 08/31/2021 05:24:09 - INFO - __main__ - Step 89882: {'lr': 0.0001773983618487529, 'samples': 17257344, 'steps': 89881, 'loss/train': 1.0386326313018799} 08/31/2021 05:24:10 - INFO - __main__ - Step 89883: {'lr': 0.00017739328382363045, 'samples': 17257536, 'steps': 89882, 'loss/train': 1.4379981756210327} 08/31/2021 05:24:10 - INFO - __main__ - Step 89884: {'lr': 0.00017738820583122343, 'samples': 17257728, 'steps': 89883, 'loss/train': 2.7016685009002686} 08/31/2021 05:24:12 - INFO - __main__ - Step 89885: {'lr': 0.00017738312787153417, 'samples': 17257920, 'steps': 89884, 'loss/train': 1.4144771099090576} 08/31/2021 05:24:12 - INFO - __main__ - Step 89886: {'lr': 0.0001773780499445649, 'samples': 17258112, 'steps': 89885, 'loss/train': 0.37656864523887634} 08/31/2021 05:24:12 - INFO - __main__ - Step 89887: {'lr': 0.00017737297205031808, 'samples': 17258304, 'steps': 89886, 'loss/train': 1.335420846939087} 08/31/2021 05:24:13 - INFO - __main__ - Step 89888: {'lr': 0.0001773678941887958, 'samples': 17258496, 'steps': 89887, 'loss/train': 1.2088209390640259} 08/31/2021 05:24:13 - INFO - __main__ - Step 89889: {'lr': 0.00017736281636000043, 'samples': 17258688, 'steps': 89888, 'loss/train': 1.37308669090271} 08/31/2021 05:24:15 - INFO - __main__ - Step 89890: {'lr': 0.00017735773856393424, 'samples': 17258880, 'steps': 89889, 'loss/train': 1.430201768875122} 08/31/2021 05:24:15 - INFO - __main__ - Step 89891: {'lr': 0.00017735266080059955, 'samples': 17259072, 'steps': 89890, 'loss/train': 1.6889008283615112} 08/31/2021 05:24:16 - INFO - __main__ - Step 89892: {'lr': 0.00017734758306999862, 'samples': 17259264, 'steps': 89891, 'loss/train': 1.201080083847046} 08/31/2021 05:24:16 - INFO - __main__ - Step 89893: {'lr': 0.00017734250537213375, 'samples': 17259456, 'steps': 89892, 'loss/train': 1.0921698808670044} 08/31/2021 05:24:16 - INFO - __main__ - Step 89894: {'lr': 0.00017733742770700722, 'samples': 17259648, 'steps': 89893, 'loss/train': 1.0230045318603516} 08/31/2021 05:24:17 - INFO - __main__ - Step 89895: {'lr': 0.00017733235007462135, 'samples': 17259840, 'steps': 89894, 'loss/train': 1.673559546470642} 08/31/2021 05:24:18 - INFO - __main__ - Step 89896: {'lr': 0.00017732727247497836, 'samples': 17260032, 'steps': 89895, 'loss/train': 0.8419666290283203} 08/31/2021 05:24:19 - INFO - __main__ - Step 89897: {'lr': 0.0001773221949080807, 'samples': 17260224, 'steps': 89896, 'loss/train': 1.583066701889038} 08/31/2021 05:24:19 - INFO - __main__ - Step 89898: {'lr': 0.00017731711737393048, 'samples': 17260416, 'steps': 89897, 'loss/train': 0.8717067837715149} 08/31/2021 05:24:19 - INFO - __main__ - Step 89899: {'lr': 0.00017731203987253, 'samples': 17260608, 'steps': 89898, 'loss/train': 1.0820105075836182} 08/31/2021 05:24:20 - INFO - __main__ - Step 89900: {'lr': 0.00017730696240388162, 'samples': 17260800, 'steps': 89899, 'loss/train': 0.9834031462669373} 08/31/2021 05:24:21 - INFO - __main__ - Step 89901: {'lr': 0.00017730188496798755, 'samples': 17260992, 'steps': 89900, 'loss/train': 0.800453245639801} 08/31/2021 05:24:22 - INFO - __main__ - Step 89902: {'lr': 0.00017729680756485016, 'samples': 17261184, 'steps': 89901, 'loss/train': 0.7764948606491089} 08/31/2021 05:24:22 - INFO - __main__ - Step 89903: {'lr': 0.0001772917301944717, 'samples': 17261376, 'steps': 89902, 'loss/train': 1.293687105178833} 08/31/2021 05:24:22 - INFO - __main__ - Step 89904: {'lr': 0.00017728665285685446, 'samples': 17261568, 'steps': 89903, 'loss/train': 1.8199398517608643} 08/31/2021 05:24:23 - INFO - __main__ - Step 89905: {'lr': 0.00017728157555200075, 'samples': 17261760, 'steps': 89904, 'loss/train': 0.9935567378997803} 08/31/2021 05:24:23 - INFO - __main__ - Step 89906: {'lr': 0.00017727649827991286, 'samples': 17261952, 'steps': 89905, 'loss/train': 1.6063036918640137} 08/31/2021 05:24:25 - INFO - __main__ - Step 89907: {'lr': 0.00017727142104059302, 'samples': 17262144, 'steps': 89906, 'loss/train': 1.5411595106124878} 08/31/2021 05:24:25 - INFO - __main__ - Step 89908: {'lr': 0.00017726634383404355, 'samples': 17262336, 'steps': 89907, 'loss/train': 1.1501516103744507} 08/31/2021 05:24:25 - INFO - __main__ - Step 89909: {'lr': 0.00017726126666026677, 'samples': 17262528, 'steps': 89908, 'loss/train': 1.293003797531128} 08/31/2021 05:24:26 - INFO - __main__ - Step 89910: {'lr': 0.00017725618951926504, 'samples': 17262720, 'steps': 89909, 'loss/train': 1.2258843183517456} 08/31/2021 05:24:26 - INFO - __main__ - Step 89911: {'lr': 0.00017725111241104045, 'samples': 17262912, 'steps': 89910, 'loss/train': 0.4266906976699829} 08/31/2021 05:24:28 - INFO - __main__ - Step 89912: {'lr': 0.00017724603533559536, 'samples': 17263104, 'steps': 89911, 'loss/train': 1.7047719955444336} 08/31/2021 05:24:28 - INFO - __main__ - Step 89913: {'lr': 0.0001772409582929321, 'samples': 17263296, 'steps': 89912, 'loss/train': 1.2128032445907593} 08/31/2021 05:24:28 - INFO - __main__ - Step 89914: {'lr': 0.00017723588128305297, 'samples': 17263488, 'steps': 89913, 'loss/train': 0.9231934547424316} 08/31/2021 05:24:29 - INFO - __main__ - Step 89915: {'lr': 0.00017723080430596017, 'samples': 17263680, 'steps': 89914, 'loss/train': 1.7336422204971313} 08/31/2021 05:24:29 - INFO - __main__ - Step 89916: {'lr': 0.00017722572736165608, 'samples': 17263872, 'steps': 89915, 'loss/train': 0.7921473979949951} 08/31/2021 05:24:31 - INFO - __main__ - Step 89917: {'lr': 0.00017722065045014293, 'samples': 17264064, 'steps': 89916, 'loss/train': 1.5814297199249268} 08/31/2021 05:24:32 - INFO - __main__ - Step 89918: {'lr': 0.00017721557357142307, 'samples': 17264256, 'steps': 89917, 'loss/train': 1.3038042783737183} 08/31/2021 05:24:32 - INFO - __main__ - Step 89919: {'lr': 0.00017721049672549872, 'samples': 17264448, 'steps': 89918, 'loss/train': 2.640643835067749} 08/31/2021 05:24:33 - INFO - __main__ - Step 89920: {'lr': 0.0001772054199123722, 'samples': 17264640, 'steps': 89919, 'loss/train': 1.2529609203338623} 08/31/2021 05:24:33 - INFO - __main__ - Step 89921: {'lr': 0.0001772003431320458, 'samples': 17264832, 'steps': 89920, 'loss/train': 0.8448530435562134} 08/31/2021 05:24:34 - INFO - __main__ - Step 89922: {'lr': 0.00017719526638452184, 'samples': 17265024, 'steps': 89921, 'loss/train': 1.2166695594787598} 08/31/2021 05:24:35 - INFO - __main__ - Step 89923: {'lr': 0.0001771901896698025, 'samples': 17265216, 'steps': 89922, 'loss/train': 1.6400986909866333} 08/31/2021 05:24:35 - INFO - __main__ - Step 89924: {'lr': 0.0001771851129878903, 'samples': 17265408, 'steps': 89923, 'loss/train': 1.107947826385498} 08/31/2021 05:24:35 - INFO - __main__ - Step 89925: {'lr': 0.0001771800363387872, 'samples': 17265600, 'steps': 89924, 'loss/train': 0.4503001570701599} 08/31/2021 05:24:36 - INFO - __main__ - Step 89926: {'lr': 0.0001771749597224957, 'samples': 17265792, 'steps': 89925, 'loss/train': 1.1429780721664429} 08/31/2021 05:24:37 - INFO - __main__ - Step 89927: {'lr': 0.00017716988313901805, 'samples': 17265984, 'steps': 89926, 'loss/train': 1.7828192710876465} 08/31/2021 05:24:38 - INFO - __main__ - Step 89928: {'lr': 0.0001771648065883565, 'samples': 17266176, 'steps': 89927, 'loss/train': 0.9830446243286133} 08/31/2021 05:24:38 - INFO - __main__ - Step 89929: {'lr': 0.00017715973007051332, 'samples': 17266368, 'steps': 89928, 'loss/train': 1.001702070236206} 08/31/2021 05:24:38 - INFO - __main__ - Step 89930: {'lr': 0.00017715465358549094, 'samples': 17266560, 'steps': 89929, 'loss/train': 1.2080777883529663} 08/31/2021 05:24:39 - INFO - __main__ - Step 89931: {'lr': 0.0001771495771332915, 'samples': 17266752, 'steps': 89930, 'loss/train': 0.9288521409034729} 08/31/2021 05:24:41 - INFO - __main__ - Step 89932: {'lr': 0.0001771445007139173, 'samples': 17266944, 'steps': 89931, 'loss/train': 1.6035821437835693} 08/31/2021 05:24:41 - INFO - __main__ - Step 89933: {'lr': 0.0001771394243273707, 'samples': 17267136, 'steps': 89932, 'loss/train': 0.846390426158905} 08/31/2021 05:24:41 - INFO - __main__ - Step 89934: {'lr': 0.00017713434797365398, 'samples': 17267328, 'steps': 89933, 'loss/train': 0.17106087505817413} 08/31/2021 05:24:42 - INFO - __main__ - Step 89935: {'lr': 0.00017712927165276933, 'samples': 17267520, 'steps': 89934, 'loss/train': 0.9303752183914185} 08/31/2021 05:24:42 - INFO - __main__ - Step 89936: {'lr': 0.00017712419536471916, 'samples': 17267712, 'steps': 89935, 'loss/train': 1.4627379179000854} 08/31/2021 05:24:44 - INFO - __main__ - Step 89937: {'lr': 0.00017711911910950578, 'samples': 17267904, 'steps': 89936, 'loss/train': 1.1805753707885742} 08/31/2021 05:24:44 - INFO - __main__ - Step 89938: {'lr': 0.00017711404288713134, 'samples': 17268096, 'steps': 89937, 'loss/train': 1.2829631567001343} 08/31/2021 05:24:45 - INFO - __main__ - Step 89939: {'lr': 0.00017710896669759812, 'samples': 17268288, 'steps': 89938, 'loss/train': 0.791583240032196} 08/31/2021 05:24:45 - INFO - __main__ - Step 89940: {'lr': 0.00017710389054090853, 'samples': 17268480, 'steps': 89939, 'loss/train': 0.4846285283565521} 08/31/2021 05:24:45 - INFO - __main__ - Step 89941: {'lr': 0.00017709881441706476, 'samples': 17268672, 'steps': 89940, 'loss/train': 0.07189541310071945} 08/31/2021 05:24:47 - INFO - __main__ - Step 89942: {'lr': 0.00017709373832606917, 'samples': 17268864, 'steps': 89941, 'loss/train': 0.05221514776349068} 08/31/2021 05:24:47 - INFO - __main__ - Step 89943: {'lr': 0.00017708866226792404, 'samples': 17269056, 'steps': 89942, 'loss/train': 1.0409644842147827} 08/31/2021 05:24:48 - INFO - __main__ - Step 89944: {'lr': 0.00017708358624263156, 'samples': 17269248, 'steps': 89943, 'loss/train': 1.2056716680526733} 08/31/2021 05:24:48 - INFO - __main__ - Step 89945: {'lr': 0.00017707851025019415, 'samples': 17269440, 'steps': 89944, 'loss/train': 1.54019033908844} 08/31/2021 05:24:48 - INFO - __main__ - Step 89946: {'lr': 0.000177073434290614, 'samples': 17269632, 'steps': 89945, 'loss/train': 0.9973135590553284} 08/31/2021 05:24:49 - INFO - __main__ - Step 89947: {'lr': 0.00017706835836389344, 'samples': 17269824, 'steps': 89946, 'loss/train': 1.1661251783370972} 08/31/2021 05:24:50 - INFO - __main__ - Step 89948: {'lr': 0.00017706328247003478, 'samples': 17270016, 'steps': 89947, 'loss/train': 0.6890100240707397} 08/31/2021 05:24:51 - INFO - __main__ - Step 89949: {'lr': 0.0001770582066090403, 'samples': 17270208, 'steps': 89948, 'loss/train': 1.1281406879425049} 08/31/2021 05:24:51 - INFO - __main__ - Step 89950: {'lr': 0.00017705313078091235, 'samples': 17270400, 'steps': 89949, 'loss/train': 1.2362288236618042} 08/31/2021 05:24:51 - INFO - __main__ - Step 89951: {'lr': 0.00017704805498565298, 'samples': 17270592, 'steps': 89950, 'loss/train': 1.5810450315475464} 08/31/2021 05:24:52 - INFO - __main__ - Step 89952: {'lr': 0.00017704297922326468, 'samples': 17270784, 'steps': 89951, 'loss/train': 0.36966612935066223} 08/31/2021 05:24:53 - INFO - __main__ - Step 89953: {'lr': 0.00017703790349374968, 'samples': 17270976, 'steps': 89952, 'loss/train': 0.18341119587421417} 08/31/2021 05:24:54 - INFO - __main__ - Step 89954: {'lr': 0.00017703282779711027, 'samples': 17271168, 'steps': 89953, 'loss/train': 1.2972904443740845} 08/31/2021 05:24:54 - INFO - __main__ - Step 89955: {'lr': 0.00017702775213334872, 'samples': 17271360, 'steps': 89954, 'loss/train': 2.0167860984802246} 08/31/2021 05:24:54 - INFO - __main__ - Step 89956: {'lr': 0.0001770226765024674, 'samples': 17271552, 'steps': 89955, 'loss/train': 1.319325566291809} 08/31/2021 05:24:55 - INFO - __main__ - Step 89957: {'lr': 0.00017701760090446848, 'samples': 17271744, 'steps': 89956, 'loss/train': 1.3600571155548096} 08/31/2021 05:24:56 - INFO - __main__ - Step 89958: {'lr': 0.0001770125253393543, 'samples': 17271936, 'steps': 89957, 'loss/train': 1.4234848022460938} 08/31/2021 05:24:57 - INFO - __main__ - Step 89959: {'lr': 0.0001770074498071272, 'samples': 17272128, 'steps': 89958, 'loss/train': 1.2564677000045776} 08/31/2021 05:24:57 - INFO - __main__ - Step 89960: {'lr': 0.00017700237430778938, 'samples': 17272320, 'steps': 89959, 'loss/train': 1.0874546766281128} 08/31/2021 05:24:57 - INFO - __main__ - Step 89961: {'lr': 0.00017699729884134316, 'samples': 17272512, 'steps': 89960, 'loss/train': 1.4561586380004883} 08/31/2021 05:24:58 - INFO - __main__ - Step 89962: {'lr': 0.00017699222340779083, 'samples': 17272704, 'steps': 89961, 'loss/train': 1.1590989828109741} 08/31/2021 05:24:59 - INFO - __main__ - Step 89963: {'lr': 0.00017698714800713468, 'samples': 17272896, 'steps': 89962, 'loss/train': 1.350452184677124} 08/31/2021 05:25:00 - INFO - __main__ - Step 89964: {'lr': 0.00017698207263937713, 'samples': 17273088, 'steps': 89963, 'loss/train': 0.07668250054121017} 08/31/2021 05:25:00 - INFO - __main__ - Step 89965: {'lr': 0.0001769769973045202, 'samples': 17273280, 'steps': 89964, 'loss/train': 1.2719534635543823} 08/31/2021 05:25:00 - INFO - __main__ - Step 89966: {'lr': 0.0001769719220025663, 'samples': 17273472, 'steps': 89965, 'loss/train': 1.5468735694885254} 08/31/2021 05:25:01 - INFO - __main__ - Step 89967: {'lr': 0.00017696684673351777, 'samples': 17273664, 'steps': 89966, 'loss/train': 1.103371262550354} 08/31/2021 05:25:02 - INFO - __main__ - Step 89968: {'lr': 0.0001769617714973768, 'samples': 17273856, 'steps': 89967, 'loss/train': 0.659169614315033} 08/31/2021 05:25:03 - INFO - __main__ - Step 89969: {'lr': 0.00017695669629414575, 'samples': 17274048, 'steps': 89968, 'loss/train': 1.3424466848373413} 08/31/2021 05:25:03 - INFO - __main__ - Step 89970: {'lr': 0.00017695162112382689, 'samples': 17274240, 'steps': 89969, 'loss/train': 1.4891300201416016} 08/31/2021 05:25:03 - INFO - __main__ - Step 89971: {'lr': 0.00017694654598642248, 'samples': 17274432, 'steps': 89970, 'loss/train': 1.416353702545166} 08/31/2021 05:25:04 - INFO - __main__ - Step 89972: {'lr': 0.00017694147088193486, 'samples': 17274624, 'steps': 89971, 'loss/train': 1.5144155025482178} 08/31/2021 05:25:06 - INFO - __main__ - Step 89973: {'lr': 0.00017693639581036624, 'samples': 17274816, 'steps': 89972, 'loss/train': 1.1221593618392944} 08/31/2021 05:25:06 - INFO - __main__ - Step 89974: {'lr': 0.000176931320771719, 'samples': 17275008, 'steps': 89973, 'loss/train': 1.2418736219406128} 08/31/2021 05:25:07 - INFO - __main__ - Step 89975: {'lr': 0.00017692624576599536, 'samples': 17275200, 'steps': 89974, 'loss/train': 1.659682273864746} 08/31/2021 05:25:07 - INFO - __main__ - Step 89976: {'lr': 0.00017692117079319764, 'samples': 17275392, 'steps': 89975, 'loss/train': 1.6008846759796143} 08/31/2021 05:25:07 - INFO - __main__ - Step 89977: {'lr': 0.00017691609585332818, 'samples': 17275584, 'steps': 89976, 'loss/train': 0.9048541784286499} 08/31/2021 05:25:09 - INFO - __main__ - Step 89978: {'lr': 0.00017691102094638913, 'samples': 17275776, 'steps': 89977, 'loss/train': 1.9433321952819824} 08/31/2021 05:25:09 - INFO - __main__ - Step 89979: {'lr': 0.00017690594607238286, 'samples': 17275968, 'steps': 89978, 'loss/train': 1.595145344734192} 08/31/2021 05:25:10 - INFO - __main__ - Step 89980: {'lr': 0.0001769008712313116, 'samples': 17276160, 'steps': 89979, 'loss/train': 1.485284447669983} 08/31/2021 05:25:10 - INFO - __main__ - Step 89981: {'lr': 0.00017689579642317773, 'samples': 17276352, 'steps': 89980, 'loss/train': 1.2386412620544434} 08/31/2021 05:25:10 - INFO - __main__ - Step 89982: {'lr': 0.00017689072164798342, 'samples': 17276544, 'steps': 89981, 'loss/train': 1.8034034967422485} 08/31/2021 05:25:11 - INFO - __main__ - Step 89983: {'lr': 0.00017688564690573105, 'samples': 17276736, 'steps': 89982, 'loss/train': 1.242100715637207} 08/31/2021 05:25:12 - INFO - __main__ - Step 89984: {'lr': 0.0001768805721964229, 'samples': 17276928, 'steps': 89983, 'loss/train': 1.4610402584075928} 08/31/2021 05:25:13 - INFO - __main__ - Step 89985: {'lr': 0.0001768754975200612, 'samples': 17277120, 'steps': 89984, 'loss/train': 1.452368974685669} 08/31/2021 05:25:13 - INFO - __main__ - Step 89986: {'lr': 0.00017687042287664834, 'samples': 17277312, 'steps': 89985, 'loss/train': 0.03524332121014595} 08/31/2021 05:25:14 - INFO - __main__ - Step 89987: {'lr': 0.00017686534826618646, 'samples': 17277504, 'steps': 89986, 'loss/train': 2.0682506561279297} 08/31/2021 05:25:14 - INFO - __main__ - Step 89988: {'lr': 0.00017686027368867796, 'samples': 17277696, 'steps': 89987, 'loss/train': 0.6335607767105103} 08/31/2021 05:25:15 - INFO - __main__ - Step 89989: {'lr': 0.00017685519914412517, 'samples': 17277888, 'steps': 89988, 'loss/train': 1.7809679508209229} 08/31/2021 05:25:16 - INFO - __main__ - Step 89990: {'lr': 0.0001768501246325302, 'samples': 17278080, 'steps': 89989, 'loss/train': 1.0711790323257446} 08/31/2021 05:25:16 - INFO - __main__ - Step 89991: {'lr': 0.00017684505015389551, 'samples': 17278272, 'steps': 89990, 'loss/train': 1.2253971099853516} 08/31/2021 05:25:17 - INFO - __main__ - Step 89992: {'lr': 0.00017683997570822326, 'samples': 17278464, 'steps': 89991, 'loss/train': 1.7414755821228027} 08/31/2021 05:25:17 - INFO - __main__ - Step 89993: {'lr': 0.00017683490129551577, 'samples': 17278656, 'steps': 89992, 'loss/train': 1.6262640953063965} 08/31/2021 05:25:18 - INFO - __main__ - Step 89994: {'lr': 0.00017682982691577537, 'samples': 17278848, 'steps': 89993, 'loss/train': 0.8977103233337402} 08/31/2021 05:25:19 - INFO - __main__ - Step 89995: {'lr': 0.00017682475256900433, 'samples': 17279040, 'steps': 89994, 'loss/train': 1.4490455389022827} 08/31/2021 05:25:19 - INFO - __main__ - Step 89996: {'lr': 0.0001768196782552049, 'samples': 17279232, 'steps': 89995, 'loss/train': 1.2356233596801758} 08/31/2021 05:25:20 - INFO - __main__ - Step 89997: {'lr': 0.0001768146039743794, 'samples': 17279424, 'steps': 89996, 'loss/train': 0.5019046664237976} 08/31/2021 05:25:20 - INFO - __main__ - Step 89998: {'lr': 0.0001768095297265301, 'samples': 17279616, 'steps': 89997, 'loss/train': 0.9086312055587769} 08/31/2021 05:25:21 - INFO - __main__ - Step 89999: {'lr': 0.0001768044555116593, 'samples': 17279808, 'steps': 89998, 'loss/train': 0.7257075905799866} 08/31/2021 05:25:22 - INFO - __main__ - Step 90000: {'lr': 0.00017679938132976936, 'samples': 17280000, 'steps': 89999, 'loss/train': 1.803838849067688} 08/31/2021 05:25:22 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 05:34:02 - INFO - __main__ - Step 90000: {'loss/eval': 1.070123553276062, 'perplexity': 2.9157397747039795} 08/31/2021 05:34:02 - INFO - __main__ - Saving model checkpoint 08/31/2021 05:34:58 - INFO - __main__ - Step 90001: {'lr': 0.00017679430718086243, 'samples': 17280192, 'steps': 90000, 'loss/train': 0.6236558556556702} 08/31/2021 05:34:58 - INFO - __main__ - Step 90002: {'lr': 0.00017678923306494083, 'samples': 17280384, 'steps': 90001, 'loss/train': 1.4533902406692505} 08/31/2021 05:34:59 - INFO - __main__ - Step 90003: {'lr': 0.0001767841589820069, 'samples': 17280576, 'steps': 90002, 'loss/train': 0.3911879360675812} 08/31/2021 05:34:59 - INFO - __main__ - Step 90004: {'lr': 0.00017677908493206294, 'samples': 17280768, 'steps': 90003, 'loss/train': 1.122878909111023} 08/31/2021 05:35:00 - INFO - __main__ - Step 90005: {'lr': 0.00017677401091511114, 'samples': 17280960, 'steps': 90004, 'loss/train': 1.6945669651031494} 08/31/2021 05:35:01 - INFO - __main__ - Step 90006: {'lr': 0.00017676893693115384, 'samples': 17281152, 'steps': 90005, 'loss/train': 1.2002686262130737} 08/31/2021 05:35:01 - INFO - __main__ - Step 90007: {'lr': 0.0001767638629801933, 'samples': 17281344, 'steps': 90006, 'loss/train': 1.1484876871109009} 08/31/2021 05:35:01 - INFO - __main__ - Step 90008: {'lr': 0.0001767587890622319, 'samples': 17281536, 'steps': 90007, 'loss/train': 1.109266996383667} 08/31/2021 05:35:02 - INFO - __main__ - Step 90009: {'lr': 0.0001767537151772718, 'samples': 17281728, 'steps': 90008, 'loss/train': 1.0512694120407104} 08/31/2021 05:35:04 - INFO - __main__ - Step 90010: {'lr': 0.00017674864132531537, 'samples': 17281920, 'steps': 90009, 'loss/train': 0.7695026993751526} 08/31/2021 05:35:04 - INFO - __main__ - Step 90011: {'lr': 0.00017674356750636494, 'samples': 17282112, 'steps': 90010, 'loss/train': 1.0070197582244873} 08/31/2021 05:35:04 - INFO - __main__ - Step 90012: {'lr': 0.00017673849372042263, 'samples': 17282304, 'steps': 90011, 'loss/train': 1.4458527565002441} 08/31/2021 05:35:05 - INFO - __main__ - Step 90013: {'lr': 0.00017673341996749087, 'samples': 17282496, 'steps': 90012, 'loss/train': 1.0264805555343628} 08/31/2021 05:35:05 - INFO - __main__ - Step 90014: {'lr': 0.0001767283462475719, 'samples': 17282688, 'steps': 90013, 'loss/train': 1.178551435470581} 08/31/2021 05:35:07 - INFO - __main__ - Step 90015: {'lr': 0.00017672327256066796, 'samples': 17282880, 'steps': 90014, 'loss/train': 1.1957274675369263} 08/31/2021 05:35:07 - INFO - __main__ - Step 90016: {'lr': 0.00017671819890678142, 'samples': 17283072, 'steps': 90015, 'loss/train': 1.6588139533996582} 08/31/2021 05:35:08 - INFO - __main__ - Step 90017: {'lr': 0.0001767131252859145, 'samples': 17283264, 'steps': 90016, 'loss/train': 1.3931071758270264} 08/31/2021 05:35:08 - INFO - __main__ - Step 90018: {'lr': 0.00017670805169806957, 'samples': 17283456, 'steps': 90017, 'loss/train': 1.03911554813385} 08/31/2021 05:35:08 - INFO - __main__ - Step 90019: {'lr': 0.00017670297814324887, 'samples': 17283648, 'steps': 90018, 'loss/train': 0.5256543159484863} 08/31/2021 05:35:10 - INFO - __main__ - Step 90020: {'lr': 0.00017669790462145464, 'samples': 17283840, 'steps': 90019, 'loss/train': 1.4160579442977905} 08/31/2021 05:35:10 - INFO - __main__ - Step 90021: {'lr': 0.00017669283113268917, 'samples': 17284032, 'steps': 90020, 'loss/train': 1.3123480081558228} 08/31/2021 05:35:11 - INFO - __main__ - Step 90022: {'lr': 0.00017668775767695487, 'samples': 17284224, 'steps': 90021, 'loss/train': 0.8276984691619873} 08/31/2021 05:35:11 - INFO - __main__ - Step 90023: {'lr': 0.00017668268425425384, 'samples': 17284416, 'steps': 90022, 'loss/train': 0.5629829168319702} 08/31/2021 05:35:11 - INFO - __main__ - Step 90024: {'lr': 0.0001766776108645885, 'samples': 17284608, 'steps': 90023, 'loss/train': 1.257006287574768} 08/31/2021 05:35:13 - INFO - __main__ - Step 90025: {'lr': 0.00017667253750796108, 'samples': 17284800, 'steps': 90024, 'loss/train': 1.703650712966919} 08/31/2021 05:35:14 - INFO - __main__ - Step 90026: {'lr': 0.00017666746418437392, 'samples': 17284992, 'steps': 90025, 'loss/train': 1.0733880996704102} 08/31/2021 05:35:14 - INFO - __main__ - Step 90027: {'lr': 0.00017666239089382925, 'samples': 17285184, 'steps': 90026, 'loss/train': 1.4982000589370728} 08/31/2021 05:35:14 - INFO - __main__ - Step 90028: {'lr': 0.00017665731763632933, 'samples': 17285376, 'steps': 90027, 'loss/train': 1.505240797996521} 08/31/2021 05:35:15 - INFO - __main__ - Step 90029: {'lr': 0.00017665224441187655, 'samples': 17285568, 'steps': 90028, 'loss/train': 0.2015945464372635} 08/31/2021 05:35:17 - INFO - __main__ - Step 90030: {'lr': 0.00017664717122047307, 'samples': 17285760, 'steps': 90029, 'loss/train': 1.2443265914916992} 08/31/2021 05:35:17 - INFO - __main__ - Step 90031: {'lr': 0.00017664209806212138, 'samples': 17285952, 'steps': 90030, 'loss/train': 1.1609976291656494} 08/31/2021 05:35:17 - INFO - __main__ - Step 90032: {'lr': 0.00017663702493682352, 'samples': 17286144, 'steps': 90031, 'loss/train': 1.1125646829605103} 08/31/2021 05:35:18 - INFO - __main__ - Step 90033: {'lr': 0.00017663195184458195, 'samples': 17286336, 'steps': 90032, 'loss/train': 1.5436458587646484} 08/31/2021 05:35:18 - INFO - __main__ - Step 90034: {'lr': 0.00017662687878539885, 'samples': 17286528, 'steps': 90033, 'loss/train': 1.2573500871658325} 08/31/2021 05:35:18 - INFO - __main__ - Step 90035: {'lr': 0.0001766218057592765, 'samples': 17286720, 'steps': 90034, 'loss/train': 0.39406245946884155} 08/31/2021 05:35:20 - INFO - __main__ - Step 90036: {'lr': 0.0001766167327662173, 'samples': 17286912, 'steps': 90035, 'loss/train': 0.04850785434246063} 08/31/2021 05:35:21 - INFO - __main__ - Step 90037: {'lr': 0.0001766116598062234, 'samples': 17287104, 'steps': 90036, 'loss/train': 1.320379376411438} 08/31/2021 05:35:21 - INFO - __main__ - Step 90038: {'lr': 0.00017660658687929722, 'samples': 17287296, 'steps': 90037, 'loss/train': 1.1758537292480469} 08/31/2021 05:35:21 - INFO - __main__ - Step 90039: {'lr': 0.00017660151398544093, 'samples': 17287488, 'steps': 90038, 'loss/train': 1.1625492572784424} 08/31/2021 05:35:22 - INFO - __main__ - Step 90040: {'lr': 0.0001765964411246569, 'samples': 17287680, 'steps': 90039, 'loss/train': 0.03384154662489891} 08/31/2021 05:35:22 - INFO - __main__ - Step 90041: {'lr': 0.00017659136829694736, 'samples': 17287872, 'steps': 90040, 'loss/train': 0.0213280338793993} 08/31/2021 05:35:24 - INFO - __main__ - Step 90042: {'lr': 0.00017658629550231463, 'samples': 17288064, 'steps': 90041, 'loss/train': 1.2908477783203125} 08/31/2021 05:35:24 - INFO - __main__ - Step 90043: {'lr': 0.00017658122274076093, 'samples': 17288256, 'steps': 90042, 'loss/train': 1.2000900506973267} 08/31/2021 05:35:25 - INFO - __main__ - Step 90044: {'lr': 0.00017657615001228865, 'samples': 17288448, 'steps': 90043, 'loss/train': 1.5943520069122314} 08/31/2021 05:35:25 - INFO - __main__ - Step 90045: {'lr': 0.00017657107731690013, 'samples': 17288640, 'steps': 90044, 'loss/train': 0.7438217997550964} 08/31/2021 05:35:25 - INFO - __main__ - Step 90046: {'lr': 0.00017656600465459744, 'samples': 17288832, 'steps': 90045, 'loss/train': 1.004214882850647} 08/31/2021 05:35:27 - INFO - __main__ - Step 90047: {'lr': 0.00017656093202538298, 'samples': 17289024, 'steps': 90046, 'loss/train': 1.322293996810913} 08/31/2021 05:35:27 - INFO - __main__ - Step 90048: {'lr': 0.000176555859429259, 'samples': 17289216, 'steps': 90047, 'loss/train': 0.04075290262699127} 08/31/2021 05:35:28 - INFO - __main__ - Step 90049: {'lr': 0.00017655078686622784, 'samples': 17289408, 'steps': 90048, 'loss/train': 0.047957442700862885} 08/31/2021 05:35:28 - INFO - __main__ - Step 90050: {'lr': 0.00017654571433629176, 'samples': 17289600, 'steps': 90049, 'loss/train': 1.1730164289474487} 08/31/2021 05:35:28 - INFO - __main__ - Step 90051: {'lr': 0.00017654064183945307, 'samples': 17289792, 'steps': 90050, 'loss/train': 0.9638638496398926} 08/31/2021 05:35:30 - INFO - __main__ - Step 90052: {'lr': 0.000176535569375714, 'samples': 17289984, 'steps': 90051, 'loss/train': 0.9904090166091919} 08/31/2021 05:35:30 - INFO - __main__ - Step 90053: {'lr': 0.00017653049694507688, 'samples': 17290176, 'steps': 90052, 'loss/train': 1.4037619829177856} 08/31/2021 05:35:31 - INFO - __main__ - Step 90054: {'lr': 0.00017652542454754398, 'samples': 17290368, 'steps': 90053, 'loss/train': 0.9571220874786377} 08/31/2021 05:35:31 - INFO - __main__ - Step 90055: {'lr': 0.00017652035218311757, 'samples': 17290560, 'steps': 90054, 'loss/train': 0.9943689107894897} 08/31/2021 05:35:31 - INFO - __main__ - Step 90056: {'lr': 0.0001765152798518, 'samples': 17290752, 'steps': 90055, 'loss/train': 1.5688999891281128} 08/31/2021 05:35:33 - INFO - __main__ - Step 90057: {'lr': 0.00017651020755359348, 'samples': 17290944, 'steps': 90056, 'loss/train': 1.3986691236495972} 08/31/2021 05:35:33 - INFO - __main__ - Step 90058: {'lr': 0.00017650513528850043, 'samples': 17291136, 'steps': 90057, 'loss/train': 1.3831011056900024} 08/31/2021 05:35:34 - INFO - __main__ - Step 90059: {'lr': 0.00017650006305652293, 'samples': 17291328, 'steps': 90058, 'loss/train': 0.6473748087882996} 08/31/2021 05:35:34 - INFO - __main__ - Step 90060: {'lr': 0.0001764949908576634, 'samples': 17291520, 'steps': 90059, 'loss/train': 0.8321754932403564} 08/31/2021 05:35:35 - INFO - __main__ - Step 90061: {'lr': 0.00017648991869192405, 'samples': 17291712, 'steps': 90060, 'loss/train': 1.6263599395751953} 08/31/2021 05:35:36 - INFO - __main__ - Step 90062: {'lr': 0.00017648484655930725, 'samples': 17291904, 'steps': 90061, 'loss/train': 1.2409001588821411} 08/31/2021 05:35:37 - INFO - __main__ - Step 90063: {'lr': 0.00017647977445981524, 'samples': 17292096, 'steps': 90062, 'loss/train': 0.5816328525543213} 08/31/2021 05:35:37 - INFO - __main__ - Step 90064: {'lr': 0.00017647470239345026, 'samples': 17292288, 'steps': 90063, 'loss/train': 0.710265040397644} 08/31/2021 05:35:38 - INFO - __main__ - Step 90065: {'lr': 0.0001764696303602147, 'samples': 17292480, 'steps': 90064, 'loss/train': 1.2920666933059692} 08/31/2021 05:35:38 - INFO - __main__ - Step 90066: {'lr': 0.0001764645583601107, 'samples': 17292672, 'steps': 90065, 'loss/train': 1.2225807905197144} 08/31/2021 05:35:38 - INFO - __main__ - Step 90067: {'lr': 0.00017645948639314076, 'samples': 17292864, 'steps': 90066, 'loss/train': 0.1694938689470291} 08/31/2021 05:35:40 - INFO - __main__ - Step 90068: {'lr': 0.00017645441445930692, 'samples': 17293056, 'steps': 90067, 'loss/train': 0.16608525812625885} 08/31/2021 05:35:40 - INFO - __main__ - Step 90069: {'lr': 0.00017644934255861168, 'samples': 17293248, 'steps': 90068, 'loss/train': 0.6465747356414795} 08/31/2021 05:35:41 - INFO - __main__ - Step 90070: {'lr': 0.00017644427069105718, 'samples': 17293440, 'steps': 90069, 'loss/train': 1.741187334060669} 08/31/2021 05:35:41 - INFO - __main__ - Step 90071: {'lr': 0.00017643919885664588, 'samples': 17293632, 'steps': 90070, 'loss/train': 1.3328957557678223} 08/31/2021 05:35:41 - INFO - __main__ - Step 90072: {'lr': 0.00017643412705537986, 'samples': 17293824, 'steps': 90071, 'loss/train': 0.11071494221687317} 08/31/2021 05:35:43 - INFO - __main__ - Step 90073: {'lr': 0.00017642905528726145, 'samples': 17294016, 'steps': 90072, 'loss/train': 0.16367298364639282} 08/31/2021 05:35:43 - INFO - __main__ - Step 90074: {'lr': 0.000176423983552293, 'samples': 17294208, 'steps': 90073, 'loss/train': 1.7898516654968262} 08/31/2021 05:35:44 - INFO - __main__ - Step 90075: {'lr': 0.00017641891185047674, 'samples': 17294400, 'steps': 90074, 'loss/train': 1.5146293640136719} 08/31/2021 05:35:44 - INFO - __main__ - Step 90076: {'lr': 0.000176413840181815, 'samples': 17294592, 'steps': 90075, 'loss/train': 1.1221672296524048} 08/31/2021 05:35:44 - INFO - __main__ - Step 90077: {'lr': 0.00017640876854631006, 'samples': 17294784, 'steps': 90076, 'loss/train': 0.5349798202514648} 08/31/2021 05:35:47 - INFO - __main__ - Step 90078: {'lr': 0.00017640369694396413, 'samples': 17294976, 'steps': 90077, 'loss/train': 1.3468416929244995} 08/31/2021 05:35:47 - INFO - __main__ - Step 90079: {'lr': 0.00017639862537477963, 'samples': 17295168, 'steps': 90078, 'loss/train': 0.21998730301856995} 08/31/2021 05:35:47 - INFO - __main__ - Step 90080: {'lr': 0.00017639355383875874, 'samples': 17295360, 'steps': 90079, 'loss/train': 1.2010947465896606} 08/31/2021 05:35:48 - INFO - __main__ - Step 90081: {'lr': 0.00017638848233590378, 'samples': 17295552, 'steps': 90080, 'loss/train': 1.019187092781067} 08/31/2021 05:35:48 - INFO - __main__ - Step 90082: {'lr': 0.00017638341086621706, 'samples': 17295744, 'steps': 90081, 'loss/train': 1.4193081855773926} 08/31/2021 05:35:50 - INFO - __main__ - Step 90083: {'lr': 0.00017637833942970083, 'samples': 17295936, 'steps': 90082, 'loss/train': 1.07837975025177} 08/31/2021 05:35:50 - INFO - __main__ - Step 90084: {'lr': 0.00017637326802635736, 'samples': 17296128, 'steps': 90083, 'loss/train': 0.7668256759643555} 08/31/2021 05:35:51 - INFO - __main__ - Step 90085: {'lr': 0.00017636819665618907, 'samples': 17296320, 'steps': 90084, 'loss/train': 1.3687688112258911} 08/31/2021 05:35:51 - INFO - __main__ - Step 90086: {'lr': 0.00017636312531919804, 'samples': 17296512, 'steps': 90085, 'loss/train': 1.6189032793045044} 08/31/2021 05:35:51 - INFO - __main__ - Step 90087: {'lr': 0.00017635805401538667, 'samples': 17296704, 'steps': 90086, 'loss/train': 1.0109190940856934} 08/31/2021 05:35:52 - INFO - __main__ - Step 90088: {'lr': 0.0001763529827447572, 'samples': 17296896, 'steps': 90087, 'loss/train': 1.4110201597213745} 08/31/2021 05:35:53 - INFO - __main__ - Step 90089: {'lr': 0.00017634791150731194, 'samples': 17297088, 'steps': 90088, 'loss/train': 0.8254387378692627} 08/31/2021 05:35:54 - INFO - __main__ - Step 90090: {'lr': 0.00017634284030305317, 'samples': 17297280, 'steps': 90089, 'loss/train': 0.7959288358688354} 08/31/2021 05:35:54 - INFO - __main__ - Step 90091: {'lr': 0.0001763377691319832, 'samples': 17297472, 'steps': 90090, 'loss/train': 1.0334806442260742} 08/31/2021 05:35:54 - INFO - __main__ - Step 90092: {'lr': 0.00017633269799410427, 'samples': 17297664, 'steps': 90091, 'loss/train': 0.7700389623641968} 08/31/2021 05:35:55 - INFO - __main__ - Step 90093: {'lr': 0.0001763276268894187, 'samples': 17297856, 'steps': 90092, 'loss/train': 1.2997726202011108} 08/31/2021 05:35:57 - INFO - __main__ - Step 90094: {'lr': 0.0001763225558179288, 'samples': 17298048, 'steps': 90093, 'loss/train': 0.9967615008354187} 08/31/2021 05:35:57 - INFO - __main__ - Step 90095: {'lr': 0.00017631748477963673, 'samples': 17298240, 'steps': 90094, 'loss/train': 1.0660429000854492} 08/31/2021 05:35:57 - INFO - __main__ - Step 90096: {'lr': 0.00017631241377454493, 'samples': 17298432, 'steps': 90095, 'loss/train': 0.8308448195457458} 08/31/2021 05:35:58 - INFO - __main__ - Step 90097: {'lr': 0.0001763073428026556, 'samples': 17298624, 'steps': 90096, 'loss/train': 0.9245634078979492} 08/31/2021 05:35:58 - INFO - __main__ - Step 90098: {'lr': 0.00017630227186397118, 'samples': 17298816, 'steps': 90097, 'loss/train': 0.07108151167631149} 08/31/2021 05:36:00 - INFO - __main__ - Step 90099: {'lr': 0.00017629720095849367, 'samples': 17299008, 'steps': 90098, 'loss/train': 1.6855158805847168} 08/31/2021 05:36:00 - INFO - __main__ - Step 90100: {'lr': 0.00017629213008622552, 'samples': 17299200, 'steps': 90099, 'loss/train': 1.0469952821731567} 08/31/2021 05:36:00 - INFO - __main__ - Step 90101: {'lr': 0.00017628705924716903, 'samples': 17299392, 'steps': 90100, 'loss/train': 1.3262927532196045} 08/31/2021 05:36:01 - INFO - __main__ - Step 90102: {'lr': 0.00017628198844132643, 'samples': 17299584, 'steps': 90101, 'loss/train': 1.185128092765808} 08/31/2021 05:36:01 - INFO - __main__ - Step 90103: {'lr': 0.0001762769176687, 'samples': 17299776, 'steps': 90102, 'loss/train': 1.089962124824524} 08/31/2021 05:36:03 - INFO - __main__ - Step 90104: {'lr': 0.0001762718469292921, 'samples': 17299968, 'steps': 90103, 'loss/train': 0.7075847387313843} 08/31/2021 05:36:03 - INFO - __main__ - Step 90105: {'lr': 0.00017626677622310495, 'samples': 17300160, 'steps': 90104, 'loss/train': 1.5113420486450195} 08/31/2021 05:36:03 - INFO - __main__ - Step 90106: {'lr': 0.0001762617055501408, 'samples': 17300352, 'steps': 90105, 'loss/train': 1.3306043148040771} 08/31/2021 05:36:04 - INFO - __main__ - Step 90107: {'lr': 0.00017625663491040205, 'samples': 17300544, 'steps': 90106, 'loss/train': 1.3139864206314087} 08/31/2021 05:36:04 - INFO - __main__ - Step 90108: {'lr': 0.00017625156430389093, 'samples': 17300736, 'steps': 90107, 'loss/train': 0.6654941439628601} 08/31/2021 05:36:06 - INFO - __main__ - Step 90109: {'lr': 0.0001762464937306097, 'samples': 17300928, 'steps': 90108, 'loss/train': 1.5510203838348389} 08/31/2021 05:36:06 - INFO - __main__ - Step 90110: {'lr': 0.00017624142319056066, 'samples': 17301120, 'steps': 90109, 'loss/train': 2.05781626701355} 08/31/2021 05:36:07 - INFO - __main__ - Step 90111: {'lr': 0.0001762363526837461, 'samples': 17301312, 'steps': 90110, 'loss/train': 1.221097469329834} 08/31/2021 05:36:07 - INFO - __main__ - Step 90112: {'lr': 0.0001762312822101684, 'samples': 17301504, 'steps': 90111, 'loss/train': 1.1158342361450195} 08/31/2021 05:36:07 - INFO - __main__ - Step 90113: {'lr': 0.00017622621176982965, 'samples': 17301696, 'steps': 90112, 'loss/train': 1.0378531217575073} 08/31/2021 05:36:09 - INFO - __main__ - Step 90114: {'lr': 0.0001762211413627322, 'samples': 17301888, 'steps': 90113, 'loss/train': 0.9093189835548401} 08/31/2021 05:36:10 - INFO - __main__ - Step 90115: {'lr': 0.0001762160709888784, 'samples': 17302080, 'steps': 90114, 'loss/train': 0.027012350037693977} 08/31/2021 05:36:10 - INFO - __main__ - Step 90116: {'lr': 0.0001762110006482705, 'samples': 17302272, 'steps': 90115, 'loss/train': 1.3384864330291748} 08/31/2021 05:36:10 - INFO - __main__ - Step 90117: {'lr': 0.00017620593034091075, 'samples': 17302464, 'steps': 90116, 'loss/train': 0.3302481770515442} 08/31/2021 05:36:11 - INFO - __main__ - Step 90118: {'lr': 0.0001762008600668015, 'samples': 17302656, 'steps': 90117, 'loss/train': 1.3296148777008057} 08/31/2021 05:36:11 - INFO - __main__ - Step 90119: {'lr': 0.000176195789825945, 'samples': 17302848, 'steps': 90118, 'loss/train': 1.280656099319458} 08/31/2021 05:36:13 - INFO - __main__ - Step 90120: {'lr': 0.00017619071961834354, 'samples': 17303040, 'steps': 90119, 'loss/train': 0.017905624583363533} 08/31/2021 05:36:13 - INFO - __main__ - Step 90121: {'lr': 0.0001761856494439994, 'samples': 17303232, 'steps': 90120, 'loss/train': 1.4250943660736084} 08/31/2021 05:36:13 - INFO - __main__ - Step 90122: {'lr': 0.00017618057930291487, 'samples': 17303424, 'steps': 90121, 'loss/train': 2.3790957927703857} 08/31/2021 05:36:14 - INFO - __main__ - Step 90123: {'lr': 0.00017617550919509227, 'samples': 17303616, 'steps': 90122, 'loss/train': 1.6139745712280273} 08/31/2021 05:36:14 - INFO - __main__ - Step 90124: {'lr': 0.0001761704391205338, 'samples': 17303808, 'steps': 90123, 'loss/train': 2.109504461288452} 08/31/2021 05:36:14 - INFO - __main__ - Step 90125: {'lr': 0.00017616536907924185, 'samples': 17304000, 'steps': 90124, 'loss/train': 0.9549168944358826} 08/31/2021 05:36:16 - INFO - __main__ - Step 90126: {'lr': 0.00017616029907121858, 'samples': 17304192, 'steps': 90125, 'loss/train': 0.04604203626513481} 08/31/2021 05:36:16 - INFO - __main__ - Step 90127: {'lr': 0.00017615522909646638, 'samples': 17304384, 'steps': 90126, 'loss/train': 1.6500121355056763} 08/31/2021 05:36:17 - INFO - __main__ - Step 90128: {'lr': 0.00017615015915498745, 'samples': 17304576, 'steps': 90127, 'loss/train': 1.6204262971878052} 08/31/2021 05:36:17 - INFO - __main__ - Step 90129: {'lr': 0.00017614508924678412, 'samples': 17304768, 'steps': 90128, 'loss/train': 1.0882689952850342} 08/31/2021 05:36:17 - INFO - __main__ - Step 90130: {'lr': 0.0001761400193718587, 'samples': 17304960, 'steps': 90129, 'loss/train': 1.546911597251892} 08/31/2021 05:36:19 - INFO - __main__ - Step 90131: {'lr': 0.00017613494953021343, 'samples': 17305152, 'steps': 90130, 'loss/train': 1.6846284866333008} 08/31/2021 05:36:19 - INFO - __main__ - Step 90132: {'lr': 0.00017612987972185056, 'samples': 17305344, 'steps': 90131, 'loss/train': 0.9315588474273682} 08/31/2021 05:36:20 - INFO - __main__ - Step 90133: {'lr': 0.00017612480994677252, 'samples': 17305536, 'steps': 90132, 'loss/train': 1.1532068252563477} 08/31/2021 05:36:20 - INFO - __main__ - Step 90134: {'lr': 0.0001761197402049815, 'samples': 17305728, 'steps': 90133, 'loss/train': 1.66531240940094} 08/31/2021 05:36:20 - INFO - __main__ - Step 90135: {'lr': 0.00017611467049647976, 'samples': 17305920, 'steps': 90134, 'loss/train': 1.1300731897354126} 08/31/2021 05:36:23 - INFO - __main__ - Step 90136: {'lr': 0.00017610960082126958, 'samples': 17306112, 'steps': 90135, 'loss/train': 1.3549563884735107} 08/31/2021 05:36:23 - INFO - __main__ - Step 90137: {'lr': 0.0001761045311793533, 'samples': 17306304, 'steps': 90136, 'loss/train': 1.3624186515808105} 08/31/2021 05:36:23 - INFO - __main__ - Step 90138: {'lr': 0.00017609946157073314, 'samples': 17306496, 'steps': 90137, 'loss/train': 1.4462742805480957} 08/31/2021 05:36:24 - INFO - __main__ - Step 90139: {'lr': 0.0001760943919954115, 'samples': 17306688, 'steps': 90138, 'loss/train': 1.650553822517395} 08/31/2021 05:36:24 - INFO - __main__ - Step 90140: {'lr': 0.00017608932245339055, 'samples': 17306880, 'steps': 90139, 'loss/train': 1.1005172729492188} 08/31/2021 05:36:26 - INFO - __main__ - Step 90141: {'lr': 0.00017608425294467263, 'samples': 17307072, 'steps': 90140, 'loss/train': 1.3379074335098267} 08/31/2021 05:36:26 - INFO - __main__ - Step 90142: {'lr': 0.00017607918346925993, 'samples': 17307264, 'steps': 90141, 'loss/train': 1.329990029335022} 08/31/2021 05:36:26 - INFO - __main__ - Step 90143: {'lr': 0.00017607411402715487, 'samples': 17307456, 'steps': 90142, 'loss/train': 0.6646939516067505} 08/31/2021 05:36:27 - INFO - __main__ - Step 90144: {'lr': 0.00017606904461835965, 'samples': 17307648, 'steps': 90143, 'loss/train': 1.1972049474716187} 08/31/2021 05:36:27 - INFO - __main__ - Step 90145: {'lr': 0.00017606397524287665, 'samples': 17307840, 'steps': 90144, 'loss/train': 1.9308176040649414} 08/31/2021 05:36:29 - INFO - __main__ - Step 90146: {'lr': 0.000176058905900708, 'samples': 17308032, 'steps': 90145, 'loss/train': 0.8553135395050049} 08/31/2021 05:36:29 - INFO - __main__ - Step 90147: {'lr': 0.00017605383659185608, 'samples': 17308224, 'steps': 90146, 'loss/train': 1.064767837524414} 08/31/2021 05:36:29 - INFO - __main__ - Step 90148: {'lr': 0.00017604876731632316, 'samples': 17308416, 'steps': 90147, 'loss/train': 0.3670177757740021} 08/31/2021 05:36:30 - INFO - __main__ - Step 90149: {'lr': 0.00017604369807411153, 'samples': 17308608, 'steps': 90148, 'loss/train': 0.3966473340988159} 08/31/2021 05:36:30 - INFO - __main__ - Step 90150: {'lr': 0.00017603862886522346, 'samples': 17308800, 'steps': 90149, 'loss/train': 1.219763994216919} 08/31/2021 05:36:32 - INFO - __main__ - Step 90151: {'lr': 0.00017603355968966123, 'samples': 17308992, 'steps': 90150, 'loss/train': 1.555325984954834} 08/31/2021 05:36:32 - INFO - __main__ - Step 90152: {'lr': 0.0001760284905474272, 'samples': 17309184, 'steps': 90151, 'loss/train': 1.3887908458709717} 08/31/2021 05:36:32 - INFO - __main__ - Step 90153: {'lr': 0.00017602342143852357, 'samples': 17309376, 'steps': 90152, 'loss/train': 0.030749712139368057} 08/31/2021 05:36:33 - INFO - __main__ - Step 90154: {'lr': 0.0001760183523629526, 'samples': 17309568, 'steps': 90153, 'loss/train': 0.832252562046051} 08/31/2021 05:36:33 - INFO - __main__ - Step 90155: {'lr': 0.00017601328332071664, 'samples': 17309760, 'steps': 90154, 'loss/train': 0.05888700485229492} 08/31/2021 05:36:35 - INFO - __main__ - Step 90156: {'lr': 0.000176008214311818, 'samples': 17309952, 'steps': 90155, 'loss/train': 1.233632206916809} 08/31/2021 05:36:35 - INFO - __main__ - Step 90157: {'lr': 0.00017600314533625889, 'samples': 17310144, 'steps': 90156, 'loss/train': 1.954687476158142} 08/31/2021 05:36:35 - INFO - __main__ - Step 90158: {'lr': 0.00017599807639404158, 'samples': 17310336, 'steps': 90157, 'loss/train': 0.8068680763244629} 08/31/2021 05:36:36 - INFO - __main__ - Step 90159: {'lr': 0.0001759930074851684, 'samples': 17310528, 'steps': 90158, 'loss/train': 0.7817055583000183} 08/31/2021 05:36:36 - INFO - __main__ - Step 90160: {'lr': 0.00017598793860964165, 'samples': 17310720, 'steps': 90159, 'loss/train': 1.061640739440918} 08/31/2021 05:36:37 - INFO - __main__ - Step 90161: {'lr': 0.00017598286976746357, 'samples': 17310912, 'steps': 90160, 'loss/train': 1.3016536235809326} 08/31/2021 05:36:38 - INFO - __main__ - Step 90162: {'lr': 0.0001759778009586365, 'samples': 17311104, 'steps': 90161, 'loss/train': 0.9954972267150879} 08/31/2021 05:36:38 - INFO - __main__ - Step 90163: {'lr': 0.00017597273218316267, 'samples': 17311296, 'steps': 90162, 'loss/train': 1.1302119493484497} 08/31/2021 05:36:39 - INFO - __main__ - Step 90164: {'lr': 0.00017596766344104436, 'samples': 17311488, 'steps': 90163, 'loss/train': 1.1043950319290161} 08/31/2021 05:36:39 - INFO - __main__ - Step 90165: {'lr': 0.00017596259473228392, 'samples': 17311680, 'steps': 90164, 'loss/train': 0.23807962238788605} 08/31/2021 05:36:39 - INFO - __main__ - Step 90166: {'lr': 0.00017595752605688365, 'samples': 17311872, 'steps': 90165, 'loss/train': 1.4189671277999878} 08/31/2021 05:36:41 - INFO - __main__ - Step 90167: {'lr': 0.00017595245741484572, 'samples': 17312064, 'steps': 90166, 'loss/train': 1.3369897603988647} 08/31/2021 05:36:41 - INFO - __main__ - Step 90168: {'lr': 0.00017594738880617245, 'samples': 17312256, 'steps': 90167, 'loss/train': 1.6490145921707153} 08/31/2021 05:36:42 - INFO - __main__ - Step 90169: {'lr': 0.00017594232023086616, 'samples': 17312448, 'steps': 90168, 'loss/train': 1.5592913627624512} 08/31/2021 05:36:42 - INFO - __main__ - Step 90170: {'lr': 0.0001759372516889291, 'samples': 17312640, 'steps': 90169, 'loss/train': 1.3801380395889282} 08/31/2021 05:36:43 - INFO - __main__ - Step 90171: {'lr': 0.00017593218318036357, 'samples': 17312832, 'steps': 90170, 'loss/train': 0.14434711635112762} 08/31/2021 05:36:44 - INFO - __main__ - Step 90172: {'lr': 0.00017592711470517186, 'samples': 17313024, 'steps': 90171, 'loss/train': 1.1073691844940186} 08/31/2021 05:36:45 - INFO - __main__ - Step 90173: {'lr': 0.00017592204626335628, 'samples': 17313216, 'steps': 90172, 'loss/train': 0.21121561527252197} 08/31/2021 05:36:45 - INFO - __main__ - Step 90174: {'lr': 0.00017591697785491905, 'samples': 17313408, 'steps': 90173, 'loss/train': 1.3773248195648193} 08/31/2021 05:36:45 - INFO - __main__ - Step 90175: {'lr': 0.00017591190947986246, 'samples': 17313600, 'steps': 90174, 'loss/train': 1.5253814458847046} 08/31/2021 05:36:46 - INFO - __main__ - Step 90176: {'lr': 0.00017590684113818886, 'samples': 17313792, 'steps': 90175, 'loss/train': 1.503152847290039} 08/31/2021 05:36:47 - INFO - __main__ - Step 90177: {'lr': 0.0001759017728299005, 'samples': 17313984, 'steps': 90176, 'loss/train': 0.19450010359287262} 08/31/2021 05:36:48 - INFO - __main__ - Step 90178: {'lr': 0.0001758967045549996, 'samples': 17314176, 'steps': 90177, 'loss/train': 1.0108940601348877} 08/31/2021 05:36:48 - INFO - __main__ - Step 90179: {'lr': 0.0001758916363134887, 'samples': 17314368, 'steps': 90178, 'loss/train': 0.9577595591545105} 08/31/2021 05:36:48 - INFO - __main__ - Step 90180: {'lr': 0.0001758865681053697, 'samples': 17314560, 'steps': 90179, 'loss/train': 0.6436782479286194} 08/31/2021 05:36:49 - INFO - __main__ - Step 90181: {'lr': 0.0001758814999306451, 'samples': 17314752, 'steps': 90180, 'loss/train': 1.260712742805481} 08/31/2021 05:36:50 - INFO - __main__ - Step 90182: {'lr': 0.00017587643178931716, 'samples': 17314944, 'steps': 90181, 'loss/train': 0.8482513427734375} 08/31/2021 05:36:51 - INFO - __main__ - Step 90183: {'lr': 0.00017587136368138812, 'samples': 17315136, 'steps': 90182, 'loss/train': 0.5676414966583252} 08/31/2021 05:36:51 - INFO - __main__ - Step 90184: {'lr': 0.00017586629560686036, 'samples': 17315328, 'steps': 90183, 'loss/train': 0.9477927088737488} 08/31/2021 05:36:51 - INFO - __main__ - Step 90185: {'lr': 0.00017586122756573606, 'samples': 17315520, 'steps': 90184, 'loss/train': 0.1902981847524643} 08/31/2021 05:36:52 - INFO - __main__ - Step 90186: {'lr': 0.00017585615955801755, 'samples': 17315712, 'steps': 90185, 'loss/train': 0.6944738626480103} 08/31/2021 05:36:52 - INFO - __main__ - Step 90187: {'lr': 0.0001758510915837071, 'samples': 17315904, 'steps': 90186, 'loss/train': 0.9981388449668884} 08/31/2021 05:36:54 - INFO - __main__ - Step 90188: {'lr': 0.00017584602364280704, 'samples': 17316096, 'steps': 90187, 'loss/train': 1.80573570728302} 08/31/2021 05:36:54 - INFO - __main__ - Step 90189: {'lr': 0.0001758409557353196, 'samples': 17316288, 'steps': 90188, 'loss/train': 1.316604733467102} 08/31/2021 05:36:55 - INFO - __main__ - Step 90190: {'lr': 0.00017583588786124703, 'samples': 17316480, 'steps': 90189, 'loss/train': 0.9061189889907837} 08/31/2021 05:36:55 - INFO - __main__ - Step 90191: {'lr': 0.00017583082002059174, 'samples': 17316672, 'steps': 90190, 'loss/train': 0.9453169703483582} 08/31/2021 05:36:56 - INFO - __main__ - Step 90192: {'lr': 0.000175825752213356, 'samples': 17316864, 'steps': 90191, 'loss/train': 1.0197298526763916} 08/31/2021 05:36:58 - INFO - __main__ - Step 90193: {'lr': 0.00017582068443954197, 'samples': 17317056, 'steps': 90192, 'loss/train': 1.3006463050842285} 08/31/2021 05:36:58 - INFO - __main__ - Step 90194: {'lr': 0.00017581561669915196, 'samples': 17317248, 'steps': 90193, 'loss/train': 0.8261393904685974} 08/31/2021 05:36:59 - INFO - __main__ - Step 90195: {'lr': 0.00017581054899218828, 'samples': 17317440, 'steps': 90194, 'loss/train': 1.7657358646392822} 08/31/2021 05:36:59 - INFO - __main__ - Step 90196: {'lr': 0.00017580548131865327, 'samples': 17317632, 'steps': 90195, 'loss/train': 1.753114104270935} 08/31/2021 05:36:59 - INFO - __main__ - Step 90197: {'lr': 0.0001758004136785491, 'samples': 17317824, 'steps': 90196, 'loss/train': 1.4270446300506592} 08/31/2021 05:37:00 - INFO - __main__ - Step 90198: {'lr': 0.00017579534607187815, 'samples': 17318016, 'steps': 90197, 'loss/train': 0.672988772392273} 08/31/2021 05:37:01 - INFO - __main__ - Step 90199: {'lr': 0.0001757902784986427, 'samples': 17318208, 'steps': 90198, 'loss/train': 0.4904402494430542} 08/31/2021 05:37:02 - INFO - __main__ - Step 90200: {'lr': 0.00017578521095884498, 'samples': 17318400, 'steps': 90199, 'loss/train': 1.3747657537460327} 08/31/2021 05:37:02 - INFO - __main__ - Step 90201: {'lr': 0.00017578014345248728, 'samples': 17318592, 'steps': 90200, 'loss/train': 0.5156236886978149} 08/31/2021 05:37:02 - INFO - __main__ - Step 90202: {'lr': 0.00017577507597957192, 'samples': 17318784, 'steps': 90201, 'loss/train': 2.3035690784454346} 08/31/2021 05:37:03 - INFO - __main__ - Step 90203: {'lr': 0.00017577000854010117, 'samples': 17318976, 'steps': 90202, 'loss/train': 0.05941939353942871} 08/31/2021 05:37:03 - INFO - __main__ - Step 90204: {'lr': 0.00017576494113407732, 'samples': 17319168, 'steps': 90203, 'loss/train': 1.1076678037643433} 08/31/2021 05:37:05 - INFO - __main__ - Step 90205: {'lr': 0.0001757598737615026, 'samples': 17319360, 'steps': 90204, 'loss/train': 0.1990482062101364} 08/31/2021 05:37:05 - INFO - __main__ - Step 90206: {'lr': 0.00017575480642237945, 'samples': 17319552, 'steps': 90205, 'loss/train': 0.1883077770471573} 08/31/2021 05:37:05 - INFO - __main__ - Step 90207: {'lr': 0.00017574973911670998, 'samples': 17319744, 'steps': 90206, 'loss/train': 0.734074056148529} 08/31/2021 05:37:06 - INFO - __main__ - Step 90208: {'lr': 0.0001757446718444965, 'samples': 17319936, 'steps': 90207, 'loss/train': 1.1320271492004395} 08/31/2021 05:37:06 - INFO - __main__ - Step 90209: {'lr': 0.00017573960460574132, 'samples': 17320128, 'steps': 90208, 'loss/train': 1.2367256879806519} 08/31/2021 05:37:08 - INFO - __main__ - Step 90210: {'lr': 0.00017573453740044674, 'samples': 17320320, 'steps': 90209, 'loss/train': 0.9409935474395752} 08/31/2021 05:37:08 - INFO - __main__ - Step 90211: {'lr': 0.000175729470228615, 'samples': 17320512, 'steps': 90210, 'loss/train': 1.0901368856430054} 08/31/2021 05:37:08 - INFO - __main__ - Step 90212: {'lr': 0.00017572440309024845, 'samples': 17320704, 'steps': 90211, 'loss/train': 0.6178426146507263} 08/31/2021 05:37:09 - INFO - __main__ - Step 90213: {'lr': 0.00017571933598534934, 'samples': 17320896, 'steps': 90212, 'loss/train': 1.8029831647872925} 08/31/2021 05:37:09 - INFO - __main__ - Step 90214: {'lr': 0.00017571426891391996, 'samples': 17321088, 'steps': 90213, 'loss/train': 0.5874577760696411} 08/31/2021 05:37:10 - INFO - __main__ - Step 90215: {'lr': 0.00017570920187596253, 'samples': 17321280, 'steps': 90214, 'loss/train': 1.496584415435791} 08/31/2021 05:37:11 - INFO - __main__ - Step 90216: {'lr': 0.00017570413487147943, 'samples': 17321472, 'steps': 90215, 'loss/train': 1.816597819328308} 08/31/2021 05:37:11 - INFO - __main__ - Step 90217: {'lr': 0.0001756990679004729, 'samples': 17321664, 'steps': 90216, 'loss/train': 0.7818118929862976} 08/31/2021 05:37:12 - INFO - __main__ - Step 90218: {'lr': 0.0001756940009629452, 'samples': 17321856, 'steps': 90217, 'loss/train': 1.1919752359390259} 08/31/2021 05:37:12 - INFO - __main__ - Step 90219: {'lr': 0.00017568893405889874, 'samples': 17322048, 'steps': 90218, 'loss/train': 0.13386599719524384} 08/31/2021 05:37:14 - INFO - __main__ - Step 90220: {'lr': 0.00017568386718833562, 'samples': 17322240, 'steps': 90219, 'loss/train': 0.5637043118476868} 08/31/2021 05:37:14 - INFO - __main__ - Step 90221: {'lr': 0.00017567880035125822, 'samples': 17322432, 'steps': 90220, 'loss/train': 1.1631659269332886} 08/31/2021 05:37:15 - INFO - __main__ - Step 90222: {'lr': 0.00017567373354766876, 'samples': 17322624, 'steps': 90221, 'loss/train': 1.3304052352905273} 08/31/2021 05:37:15 - INFO - __main__ - Step 90223: {'lr': 0.0001756686667775696, 'samples': 17322816, 'steps': 90222, 'loss/train': 0.05631401389837265} 08/31/2021 05:37:15 - INFO - __main__ - Step 90224: {'lr': 0.00017566360004096296, 'samples': 17323008, 'steps': 90223, 'loss/train': 1.038717269897461} 08/31/2021 05:37:16 - INFO - __main__ - Step 90225: {'lr': 0.0001756585333378512, 'samples': 17323200, 'steps': 90224, 'loss/train': 0.9768301248550415} 08/31/2021 05:37:17 - INFO - __main__ - Step 90226: {'lr': 0.0001756534666682365, 'samples': 17323392, 'steps': 90225, 'loss/train': 1.2976163625717163} 08/31/2021 05:37:17 - INFO - __main__ - Step 90227: {'lr': 0.00017564840003212123, 'samples': 17323584, 'steps': 90226, 'loss/train': 0.5634863972663879} 08/31/2021 05:37:18 - INFO - __main__ - Step 90228: {'lr': 0.00017564333342950768, 'samples': 17323776, 'steps': 90227, 'loss/train': 1.5190469026565552} 08/31/2021 05:37:18 - INFO - __main__ - Step 90229: {'lr': 0.00017563826686039805, 'samples': 17323968, 'steps': 90228, 'loss/train': 1.244820237159729} 08/31/2021 05:37:19 - INFO - __main__ - Step 90230: {'lr': 0.0001756332003247947, 'samples': 17324160, 'steps': 90229, 'loss/train': 0.8046113848686218} 08/31/2021 05:37:20 - INFO - __main__ - Step 90231: {'lr': 0.00017562813382269985, 'samples': 17324352, 'steps': 90230, 'loss/train': 0.5682360529899597} 08/31/2021 05:37:20 - INFO - __main__ - Step 90232: {'lr': 0.00017562306735411582, 'samples': 17324544, 'steps': 90231, 'loss/train': 1.1893267631530762} 08/31/2021 05:37:21 - INFO - __main__ - Step 90233: {'lr': 0.000175618000919045, 'samples': 17324736, 'steps': 90232, 'loss/train': 1.024566888809204} 08/31/2021 05:37:21 - INFO - __main__ - Step 90234: {'lr': 0.00017561293451748947, 'samples': 17324928, 'steps': 90233, 'loss/train': 0.9920583963394165} 08/31/2021 05:37:21 - INFO - __main__ - Step 90235: {'lr': 0.00017560786814945157, 'samples': 17325120, 'steps': 90234, 'loss/train': 0.5899689197540283} 08/31/2021 05:37:23 - INFO - __main__ - Step 90236: {'lr': 0.00017560280181493367, 'samples': 17325312, 'steps': 90235, 'loss/train': 1.1186643838882446} 08/31/2021 05:37:23 - INFO - __main__ - Step 90237: {'lr': 0.00017559773551393797, 'samples': 17325504, 'steps': 90236, 'loss/train': 0.5278226733207703} 08/31/2021 05:37:24 - INFO - __main__ - Step 90238: {'lr': 0.00017559266924646678, 'samples': 17325696, 'steps': 90237, 'loss/train': 0.6733282804489136} 08/31/2021 05:37:24 - INFO - __main__ - Step 90239: {'lr': 0.00017558760301252235, 'samples': 17325888, 'steps': 90238, 'loss/train': 1.749489426612854} 08/31/2021 05:37:25 - INFO - __main__ - Step 90240: {'lr': 0.00017558253681210705, 'samples': 17326080, 'steps': 90239, 'loss/train': 0.8675248026847839} 08/31/2021 05:37:27 - INFO - __main__ - Step 90241: {'lr': 0.0001755774706452231, 'samples': 17326272, 'steps': 90240, 'loss/train': 0.8268287181854248} 08/31/2021 05:37:27 - INFO - __main__ - Step 90242: {'lr': 0.0001755724045118728, 'samples': 17326464, 'steps': 90241, 'loss/train': 1.2485859394073486} 08/31/2021 05:37:27 - INFO - __main__ - Step 90243: {'lr': 0.00017556733841205842, 'samples': 17326656, 'steps': 90242, 'loss/train': 1.6161469221115112} 08/31/2021 05:37:28 - INFO - __main__ - Step 90244: {'lr': 0.00017556227234578222, 'samples': 17326848, 'steps': 90243, 'loss/train': 1.5462228059768677} 08/31/2021 05:37:28 - INFO - __main__ - Step 90245: {'lr': 0.00017555720631304655, 'samples': 17327040, 'steps': 90244, 'loss/train': 0.9001061320304871} 08/31/2021 05:37:30 - INFO - __main__ - Step 90246: {'lr': 0.00017555214031385376, 'samples': 17327232, 'steps': 90245, 'loss/train': 1.072013258934021} 08/31/2021 05:37:30 - INFO - __main__ - Step 90247: {'lr': 0.0001755470743482059, 'samples': 17327424, 'steps': 90246, 'loss/train': 1.2444016933441162} 08/31/2021 05:37:30 - INFO - __main__ - Step 90248: {'lr': 0.00017554200841610534, 'samples': 17327616, 'steps': 90247, 'loss/train': 1.253421425819397} 08/31/2021 05:37:31 - INFO - __main__ - Step 90249: {'lr': 0.0001755369425175545, 'samples': 17327808, 'steps': 90248, 'loss/train': 1.0231010913848877} 08/31/2021 05:37:31 - INFO - __main__ - Step 90250: {'lr': 0.0001755318766525555, 'samples': 17328000, 'steps': 90249, 'loss/train': 1.1011005640029907} 08/31/2021 05:37:33 - INFO - __main__ - Step 90251: {'lr': 0.00017552681082111065, 'samples': 17328192, 'steps': 90250, 'loss/train': 0.6336726546287537} 08/31/2021 05:37:33 - INFO - __main__ - Step 90252: {'lr': 0.00017552174502322236, 'samples': 17328384, 'steps': 90251, 'loss/train': 1.18721342086792} 08/31/2021 05:37:33 - INFO - __main__ - Step 90253: {'lr': 0.00017551667925889275, 'samples': 17328576, 'steps': 90252, 'loss/train': 0.5019151568412781} 08/31/2021 05:37:34 - INFO - __main__ - Step 90254: {'lr': 0.0001755116135281242, 'samples': 17328768, 'steps': 90253, 'loss/train': 1.3500014543533325} 08/31/2021 05:37:34 - INFO - __main__ - Step 90255: {'lr': 0.00017550654783091903, 'samples': 17328960, 'steps': 90254, 'loss/train': 0.962963879108429} 08/31/2021 05:37:34 - INFO - __main__ - Step 90256: {'lr': 0.00017550148216727938, 'samples': 17329152, 'steps': 90255, 'loss/train': 1.153626799583435} 08/31/2021 05:37:36 - INFO - __main__ - Step 90257: {'lr': 0.00017549641653720764, 'samples': 17329344, 'steps': 90256, 'loss/train': 0.8053175210952759} 08/31/2021 05:37:36 - INFO - __main__ - Step 90258: {'lr': 0.0001754913509407061, 'samples': 17329536, 'steps': 90257, 'loss/train': 0.8050095438957214} 08/31/2021 05:37:37 - INFO - __main__ - Step 90259: {'lr': 0.00017548628537777697, 'samples': 17329728, 'steps': 90258, 'loss/train': 1.1217975616455078} 08/31/2021 05:37:37 - INFO - __main__ - Step 90260: {'lr': 0.00017548121984842263, 'samples': 17329920, 'steps': 90259, 'loss/train': 1.0094165802001953} 08/31/2021 05:37:37 - INFO - __main__ - Step 90261: {'lr': 0.00017547615435264523, 'samples': 17330112, 'steps': 90260, 'loss/train': 1.4380908012390137} 08/31/2021 05:37:39 - INFO - __main__ - Step 90262: {'lr': 0.00017547108889044713, 'samples': 17330304, 'steps': 90261, 'loss/train': 1.6394555568695068} 08/31/2021 05:37:39 - INFO - __main__ - Step 90263: {'lr': 0.0001754660234618306, 'samples': 17330496, 'steps': 90262, 'loss/train': 1.9222041368484497} 08/31/2021 05:37:40 - INFO - __main__ - Step 90264: {'lr': 0.00017546095806679796, 'samples': 17330688, 'steps': 90263, 'loss/train': 1.1186223030090332} 08/31/2021 05:37:40 - INFO - __main__ - Step 90265: {'lr': 0.00017545589270535146, 'samples': 17330880, 'steps': 90264, 'loss/train': 1.068536639213562} 08/31/2021 05:37:40 - INFO - __main__ - Step 90266: {'lr': 0.00017545082737749335, 'samples': 17331072, 'steps': 90265, 'loss/train': 1.3937283754348755} 08/31/2021 05:37:42 - INFO - __main__ - Step 90267: {'lr': 0.000175445762083226, 'samples': 17331264, 'steps': 90266, 'loss/train': 1.0295164585113525} 08/31/2021 05:37:42 - INFO - __main__ - Step 90268: {'lr': 0.0001754406968225516, 'samples': 17331456, 'steps': 90267, 'loss/train': 0.4476536214351654} 08/31/2021 05:37:43 - INFO - __main__ - Step 90269: {'lr': 0.0001754356315954725, 'samples': 17331648, 'steps': 90268, 'loss/train': 2.606174945831299} 08/31/2021 05:37:43 - INFO - __main__ - Step 90270: {'lr': 0.00017543056640199095, 'samples': 17331840, 'steps': 90269, 'loss/train': 1.1283916234970093} 08/31/2021 05:37:44 - INFO - __main__ - Step 90271: {'lr': 0.0001754255012421092, 'samples': 17332032, 'steps': 90270, 'loss/train': 1.218800663948059} 08/31/2021 05:37:45 - INFO - __main__ - Step 90272: {'lr': 0.0001754204361158296, 'samples': 17332224, 'steps': 90271, 'loss/train': 1.5961581468582153} 08/31/2021 05:37:45 - INFO - __main__ - Step 90273: {'lr': 0.00017541537102315442, 'samples': 17332416, 'steps': 90272, 'loss/train': 1.226319432258606} 08/31/2021 05:37:46 - INFO - __main__ - Step 90274: {'lr': 0.0001754103059640859, 'samples': 17332608, 'steps': 90273, 'loss/train': 0.3446284830570221} 08/31/2021 05:37:46 - INFO - __main__ - Step 90275: {'lr': 0.00017540524093862631, 'samples': 17332800, 'steps': 90274, 'loss/train': 0.5276992917060852} 08/31/2021 05:37:46 - INFO - __main__ - Step 90276: {'lr': 0.00017540017594677802, 'samples': 17332992, 'steps': 90275, 'loss/train': 0.1666392683982849} 08/31/2021 05:37:48 - INFO - __main__ - Step 90277: {'lr': 0.0001753951109885432, 'samples': 17333184, 'steps': 90276, 'loss/train': 0.7927765846252441} 08/31/2021 05:37:49 - INFO - __main__ - Step 90278: {'lr': 0.00017539004606392423, 'samples': 17333376, 'steps': 90277, 'loss/train': 1.319915771484375} 08/31/2021 05:37:49 - INFO - __main__ - Step 90279: {'lr': 0.00017538498117292335, 'samples': 17333568, 'steps': 90278, 'loss/train': 1.7285912036895752} 08/31/2021 05:37:49 - INFO - __main__ - Step 90280: {'lr': 0.0001753799163155429, 'samples': 17333760, 'steps': 90279, 'loss/train': 0.1522650569677353} 08/31/2021 05:37:50 - INFO - __main__ - Step 90281: {'lr': 0.00017537485149178507, 'samples': 17333952, 'steps': 90280, 'loss/train': 1.4179749488830566} 08/31/2021 05:37:51 - INFO - __main__ - Step 90282: {'lr': 0.00017536978670165215, 'samples': 17334144, 'steps': 90281, 'loss/train': 1.726318597793579} 08/31/2021 05:37:52 - INFO - __main__ - Step 90283: {'lr': 0.00017536472194514647, 'samples': 17334336, 'steps': 90282, 'loss/train': 0.863826334476471} 08/31/2021 05:37:52 - INFO - __main__ - Step 90284: {'lr': 0.00017535965722227027, 'samples': 17334528, 'steps': 90283, 'loss/train': 0.8401824831962585} 08/31/2021 05:37:52 - INFO - __main__ - Step 90285: {'lr': 0.0001753545925330259, 'samples': 17334720, 'steps': 90284, 'loss/train': 0.9841895699501038} 08/31/2021 05:37:53 - INFO - __main__ - Step 90286: {'lr': 0.00017534952787741554, 'samples': 17334912, 'steps': 90285, 'loss/train': 0.023605624213814735} 08/31/2021 05:37:53 - INFO - __main__ - Step 90287: {'lr': 0.00017534446325544162, 'samples': 17335104, 'steps': 90286, 'loss/train': 1.406664490699768} 08/31/2021 05:37:55 - INFO - __main__ - Step 90288: {'lr': 0.0001753393986671063, 'samples': 17335296, 'steps': 90287, 'loss/train': 1.1318129301071167} 08/31/2021 05:37:55 - INFO - __main__ - Step 90289: {'lr': 0.00017533433411241186, 'samples': 17335488, 'steps': 90288, 'loss/train': 1.6390904188156128} 08/31/2021 05:37:56 - INFO - __main__ - Step 90290: {'lr': 0.00017532926959136063, 'samples': 17335680, 'steps': 90289, 'loss/train': 1.060004711151123} 08/31/2021 05:37:56 - INFO - __main__ - Step 90291: {'lr': 0.0001753242051039549, 'samples': 17335872, 'steps': 90290, 'loss/train': 1.6834415197372437} 08/31/2021 05:37:56 - INFO - __main__ - Step 90292: {'lr': 0.00017531914065019693, 'samples': 17336064, 'steps': 90291, 'loss/train': 0.9864886403083801} 08/31/2021 05:37:58 - INFO - __main__ - Step 90293: {'lr': 0.00017531407623008898, 'samples': 17336256, 'steps': 90292, 'loss/train': 0.9462712407112122} 08/31/2021 05:37:58 - INFO - __main__ - Step 90294: {'lr': 0.00017530901184363337, 'samples': 17336448, 'steps': 90293, 'loss/train': 1.6432956457138062} 08/31/2021 05:37:58 - INFO - __main__ - Step 90295: {'lr': 0.00017530394749083235, 'samples': 17336640, 'steps': 90294, 'loss/train': 1.2098848819732666} 08/31/2021 05:37:59 - INFO - __main__ - Step 90296: {'lr': 0.00017529888317168824, 'samples': 17336832, 'steps': 90295, 'loss/train': 1.293592929840088} 08/31/2021 05:37:59 - INFO - __main__ - Step 90297: {'lr': 0.00017529381888620326, 'samples': 17337024, 'steps': 90296, 'loss/train': 2.118051290512085} 08/31/2021 05:38:01 - INFO - __main__ - Step 90298: {'lr': 0.00017528875463437976, 'samples': 17337216, 'steps': 90297, 'loss/train': 0.7318799495697021} 08/31/2021 05:38:02 - INFO - __main__ - Step 90299: {'lr': 0.00017528369041622, 'samples': 17337408, 'steps': 90298, 'loss/train': 0.9650369882583618} 08/31/2021 05:38:02 - INFO - __main__ - Step 90300: {'lr': 0.0001752786262317263, 'samples': 17337600, 'steps': 90299, 'loss/train': 1.0038572549819946} 08/31/2021 05:38:02 - INFO - __main__ - Step 90301: {'lr': 0.0001752735620809009, 'samples': 17337792, 'steps': 90300, 'loss/train': 1.251832365989685} 08/31/2021 05:38:03 - INFO - __main__ - Step 90302: {'lr': 0.000175268497963746, 'samples': 17337984, 'steps': 90301, 'loss/train': 0.8939571976661682} 08/31/2021 05:38:04 - INFO - __main__ - Step 90303: {'lr': 0.000175263433880264, 'samples': 17338176, 'steps': 90302, 'loss/train': 1.5317414999008179} 08/31/2021 05:38:05 - INFO - __main__ - Step 90304: {'lr': 0.00017525836983045713, 'samples': 17338368, 'steps': 90303, 'loss/train': 1.3071670532226562} 08/31/2021 05:38:05 - INFO - __main__ - Step 90305: {'lr': 0.0001752533058143277, 'samples': 17338560, 'steps': 90304, 'loss/train': 1.2187191247940063} 08/31/2021 05:38:05 - INFO - __main__ - Step 90306: {'lr': 0.00017524824183187793, 'samples': 17338752, 'steps': 90305, 'loss/train': 0.7392969727516174} 08/31/2021 05:38:06 - INFO - __main__ - Step 90307: {'lr': 0.00017524317788311018, 'samples': 17338944, 'steps': 90306, 'loss/train': 1.1796071529388428} 08/31/2021 05:38:08 - INFO - __main__ - Step 90308: {'lr': 0.0001752381139680267, 'samples': 17339136, 'steps': 90307, 'loss/train': 0.9947128295898438} 08/31/2021 05:38:08 - INFO - __main__ - Step 90309: {'lr': 0.00017523305008662976, 'samples': 17339328, 'steps': 90308, 'loss/train': 1.5310726165771484} 08/31/2021 05:38:08 - INFO - __main__ - Step 90310: {'lr': 0.00017522798623892166, 'samples': 17339520, 'steps': 90309, 'loss/train': 0.531004786491394} 08/31/2021 05:38:09 - INFO - __main__ - Step 90311: {'lr': 0.0001752229224249047, 'samples': 17339712, 'steps': 90310, 'loss/train': 0.018978754058480263} 08/31/2021 05:38:09 - INFO - __main__ - Step 90312: {'lr': 0.0001752178586445811, 'samples': 17339904, 'steps': 90311, 'loss/train': 1.541792869567871} 08/31/2021 05:38:09 - INFO - __main__ - Step 90313: {'lr': 0.00017521279489795334, 'samples': 17340096, 'steps': 90312, 'loss/train': 1.2091857194900513} 08/31/2021 05:38:11 - INFO - __main__ - Step 90314: {'lr': 0.00017520773118502337, 'samples': 17340288, 'steps': 90313, 'loss/train': 1.3065173625946045} 08/31/2021 05:38:11 - INFO - __main__ - Step 90315: {'lr': 0.00017520266750579367, 'samples': 17340480, 'steps': 90314, 'loss/train': 1.1802594661712646} 08/31/2021 05:38:12 - INFO - __main__ - Step 90316: {'lr': 0.00017519760386026652, 'samples': 17340672, 'steps': 90315, 'loss/train': 1.33851158618927} 08/31/2021 05:38:12 - INFO - __main__ - Step 90317: {'lr': 0.00017519254024844414, 'samples': 17340864, 'steps': 90316, 'loss/train': 1.050034523010254} 08/31/2021 05:38:12 - INFO - __main__ - Step 90318: {'lr': 0.00017518747667032885, 'samples': 17341056, 'steps': 90317, 'loss/train': 1.4579048156738281} 08/31/2021 05:38:14 - INFO - __main__ - Step 90319: {'lr': 0.00017518241312592292, 'samples': 17341248, 'steps': 90318, 'loss/train': 0.16526146233081818} 08/31/2021 05:38:15 - INFO - __main__ - Step 90320: {'lr': 0.0001751773496152287, 'samples': 17341440, 'steps': 90319, 'loss/train': 1.2857139110565186} 08/31/2021 05:38:15 - INFO - __main__ - Step 90321: {'lr': 0.00017517228613824835, 'samples': 17341632, 'steps': 90320, 'loss/train': 1.2707936763763428} 08/31/2021 05:38:15 - INFO - __main__ - Step 90322: {'lr': 0.00017516722269498422, 'samples': 17341824, 'steps': 90321, 'loss/train': 1.0497748851776123} 08/31/2021 05:38:16 - INFO - __main__ - Step 90323: {'lr': 0.0001751621592854386, 'samples': 17342016, 'steps': 90322, 'loss/train': 1.2711673974990845} 08/31/2021 05:38:17 - INFO - __main__ - Step 90324: {'lr': 0.00017515709590961375, 'samples': 17342208, 'steps': 90323, 'loss/train': 1.5670751333236694} 08/31/2021 05:38:17 - INFO - __main__ - Step 90325: {'lr': 0.00017515203256751195, 'samples': 17342400, 'steps': 90324, 'loss/train': 1.003631353378296} 08/31/2021 05:38:18 - INFO - __main__ - Step 90326: {'lr': 0.00017514696925913548, 'samples': 17342592, 'steps': 90325, 'loss/train': 1.0861939191818237} 08/31/2021 05:38:18 - INFO - __main__ - Step 90327: {'lr': 0.00017514190598448675, 'samples': 17342784, 'steps': 90326, 'loss/train': 0.7159954309463501} 08/31/2021 05:38:19 - INFO - __main__ - Step 90328: {'lr': 0.00017513684274356783, 'samples': 17342976, 'steps': 90327, 'loss/train': 0.7060829401016235} 08/31/2021 05:38:20 - INFO - __main__ - Step 90329: {'lr': 0.00017513177953638108, 'samples': 17343168, 'steps': 90328, 'loss/train': 0.911945641040802} 08/31/2021 05:38:21 - INFO - __main__ - Step 90330: {'lr': 0.0001751267163629288, 'samples': 17343360, 'steps': 90329, 'loss/train': 1.2993571758270264} 08/31/2021 05:38:21 - INFO - __main__ - Step 90331: {'lr': 0.00017512165322321327, 'samples': 17343552, 'steps': 90330, 'loss/train': 0.01830383762717247} 08/31/2021 05:38:22 - INFO - __main__ - Step 90332: {'lr': 0.0001751165901172368, 'samples': 17343744, 'steps': 90331, 'loss/train': 0.4907994270324707} 08/31/2021 05:38:22 - INFO - __main__ - Step 90333: {'lr': 0.00017511152704500157, 'samples': 17343936, 'steps': 90332, 'loss/train': 1.6426422595977783} 08/31/2021 05:38:22 - INFO - __main__ - Step 90334: {'lr': 0.00017510646400650999, 'samples': 17344128, 'steps': 90333, 'loss/train': 0.7568968534469604} 08/31/2021 05:38:24 - INFO - __main__ - Step 90335: {'lr': 0.00017510140100176425, 'samples': 17344320, 'steps': 90334, 'loss/train': 0.8150379061698914} 08/31/2021 05:38:24 - INFO - __main__ - Step 90336: {'lr': 0.00017509633803076665, 'samples': 17344512, 'steps': 90335, 'loss/train': 0.5044503211975098} 08/31/2021 05:38:25 - INFO - __main__ - Step 90337: {'lr': 0.00017509127509351952, 'samples': 17344704, 'steps': 90336, 'loss/train': 1.188422679901123} 08/31/2021 05:38:25 - INFO - __main__ - Step 90338: {'lr': 0.00017508621219002507, 'samples': 17344896, 'steps': 90337, 'loss/train': 1.4128528833389282} 08/31/2021 05:38:25 - INFO - __main__ - Step 90339: {'lr': 0.00017508114932028563, 'samples': 17345088, 'steps': 90338, 'loss/train': 0.9724122881889343} 08/31/2021 05:38:26 - INFO - __main__ - Step 90340: {'lr': 0.00017507608648430355, 'samples': 17345280, 'steps': 90339, 'loss/train': 0.9521151185035706} 08/31/2021 05:38:27 - INFO - __main__ - Step 90341: {'lr': 0.00017507102368208096, 'samples': 17345472, 'steps': 90340, 'loss/train': 1.2826834917068481} 08/31/2021 05:38:28 - INFO - __main__ - Step 90342: {'lr': 0.0001750659609136202, 'samples': 17345664, 'steps': 90341, 'loss/train': 1.2862465381622314} 08/31/2021 05:38:28 - INFO - __main__ - Step 90343: {'lr': 0.00017506089817892356, 'samples': 17345856, 'steps': 90342, 'loss/train': 0.5324711203575134} 08/31/2021 05:38:28 - INFO - __main__ - Step 90344: {'lr': 0.00017505583547799337, 'samples': 17346048, 'steps': 90343, 'loss/train': 1.0319314002990723} 08/31/2021 05:38:29 - INFO - __main__ - Step 90345: {'lr': 0.00017505077281083182, 'samples': 17346240, 'steps': 90344, 'loss/train': 0.7815768122673035} 08/31/2021 05:38:30 - INFO - __main__ - Step 90346: {'lr': 0.0001750457101774412, 'samples': 17346432, 'steps': 90345, 'loss/train': 0.6356849670410156} 08/31/2021 05:38:31 - INFO - __main__ - Step 90347: {'lr': 0.00017504064757782386, 'samples': 17346624, 'steps': 90346, 'loss/train': 1.0779922008514404} 08/31/2021 05:38:31 - INFO - __main__ - Step 90348: {'lr': 0.0001750355850119821, 'samples': 17346816, 'steps': 90347, 'loss/train': 2.806556224822998} 08/31/2021 05:38:31 - INFO - __main__ - Step 90349: {'lr': 0.00017503052247991806, 'samples': 17347008, 'steps': 90348, 'loss/train': 1.4416148662567139} 08/31/2021 05:38:32 - INFO - __main__ - Step 90350: {'lr': 0.00017502545998163415, 'samples': 17347200, 'steps': 90349, 'loss/train': 1.0256906747817993} 08/31/2021 05:38:34 - INFO - __main__ - Step 90351: {'lr': 0.00017502039751713262, 'samples': 17347392, 'steps': 90350, 'loss/train': 0.8978736400604248} 08/31/2021 05:38:34 - INFO - __main__ - Step 90352: {'lr': 0.00017501533508641572, 'samples': 17347584, 'steps': 90351, 'loss/train': 0.6961362361907959} 08/31/2021 05:38:35 - INFO - __main__ - Step 90353: {'lr': 0.00017501027268948579, 'samples': 17347776, 'steps': 90352, 'loss/train': 1.755818486213684} 08/31/2021 05:38:35 - INFO - __main__ - Step 90354: {'lr': 0.00017500521032634512, 'samples': 17347968, 'steps': 90353, 'loss/train': 1.5722228288650513} 08/31/2021 05:38:35 - INFO - __main__ - Step 90355: {'lr': 0.00017500014799699587, 'samples': 17348160, 'steps': 90354, 'loss/train': 1.706916332244873} 08/31/2021 05:38:37 - INFO - __main__ - Step 90356: {'lr': 0.0001749950857014404, 'samples': 17348352, 'steps': 90355, 'loss/train': 1.1618434190750122} 08/31/2021 05:38:37 - INFO - __main__ - Step 90357: {'lr': 0.00017499002343968097, 'samples': 17348544, 'steps': 90356, 'loss/train': 1.739884614944458} 08/31/2021 05:38:38 - INFO - __main__ - Step 90358: {'lr': 0.0001749849612117199, 'samples': 17348736, 'steps': 90357, 'loss/train': 0.8091534972190857} 08/31/2021 05:38:38 - INFO - __main__ - Step 90359: {'lr': 0.00017497989901755945, 'samples': 17348928, 'steps': 90358, 'loss/train': 0.9282197952270508} 08/31/2021 05:38:38 - INFO - __main__ - Step 90360: {'lr': 0.00017497483685720189, 'samples': 17349120, 'steps': 90359, 'loss/train': 0.8351259231567383} 08/31/2021 05:38:40 - INFO - __main__ - Step 90361: {'lr': 0.0001749697747306495, 'samples': 17349312, 'steps': 90360, 'loss/train': 1.1826094388961792} 08/31/2021 05:38:40 - INFO - __main__ - Step 90362: {'lr': 0.00017496471263790458, 'samples': 17349504, 'steps': 90361, 'loss/train': 1.4241182804107666} 08/31/2021 05:38:41 - INFO - __main__ - Step 90363: {'lr': 0.0001749596505789694, 'samples': 17349696, 'steps': 90362, 'loss/train': 1.4877735376358032} 08/31/2021 05:38:41 - INFO - __main__ - Step 90364: {'lr': 0.00017495458855384626, 'samples': 17349888, 'steps': 90363, 'loss/train': 1.3528180122375488} 08/31/2021 05:38:41 - INFO - __main__ - Step 90365: {'lr': 0.00017494952656253742, 'samples': 17350080, 'steps': 90364, 'loss/train': 0.8138183355331421} 08/31/2021 05:38:42 - INFO - __main__ - Step 90366: {'lr': 0.00017494446460504515, 'samples': 17350272, 'steps': 90365, 'loss/train': 0.5408366322517395} 08/31/2021 05:38:43 - INFO - __main__ - Step 90367: {'lr': 0.00017493940268137188, 'samples': 17350464, 'steps': 90366, 'loss/train': 0.6322221755981445} 08/31/2021 05:38:44 - INFO - __main__ - Step 90368: {'lr': 0.0001749343407915196, 'samples': 17350656, 'steps': 90367, 'loss/train': 0.9593145251274109} 08/31/2021 05:38:44 - INFO - __main__ - Step 90369: {'lr': 0.00017492927893549083, 'samples': 17350848, 'steps': 90368, 'loss/train': 1.3238332271575928} 08/31/2021 05:38:44 - INFO - __main__ - Step 90370: {'lr': 0.0001749242171132877, 'samples': 17351040, 'steps': 90369, 'loss/train': 1.076855182647705} 08/31/2021 05:38:45 - INFO - __main__ - Step 90371: {'lr': 0.0001749191553249126, 'samples': 17351232, 'steps': 90370, 'loss/train': 2.071329355239868} 08/31/2021 05:38:46 - INFO - __main__ - Step 90372: {'lr': 0.00017491409357036773, 'samples': 17351424, 'steps': 90371, 'loss/train': 0.8727225661277771} 08/31/2021 05:38:47 - INFO - __main__ - Step 90373: {'lr': 0.00017490903184965543, 'samples': 17351616, 'steps': 90372, 'loss/train': 1.7394930124282837} 08/31/2021 05:38:47 - INFO - __main__ - Step 90374: {'lr': 0.00017490397016277796, 'samples': 17351808, 'steps': 90373, 'loss/train': 1.3965603113174438} 08/31/2021 05:38:47 - INFO - __main__ - Step 90375: {'lr': 0.00017489890850973762, 'samples': 17352000, 'steps': 90374, 'loss/train': 1.7420705556869507} 08/31/2021 05:38:48 - INFO - __main__ - Step 90376: {'lr': 0.00017489384689053662, 'samples': 17352192, 'steps': 90375, 'loss/train': 1.115196704864502} 08/31/2021 05:38:49 - INFO - __main__ - Step 90377: {'lr': 0.00017488878530517733, 'samples': 17352384, 'steps': 90376, 'loss/train': 0.6264412999153137} 08/31/2021 05:38:50 - INFO - __main__ - Step 90378: {'lr': 0.000174883723753662, 'samples': 17352576, 'steps': 90377, 'loss/train': 1.57503080368042} 08/31/2021 05:38:50 - INFO - __main__ - Step 90379: {'lr': 0.0001748786622359929, 'samples': 17352768, 'steps': 90378, 'loss/train': 0.9071710109710693} 08/31/2021 05:38:50 - INFO - __main__ - Step 90380: {'lr': 0.00017487360075217232, 'samples': 17352960, 'steps': 90379, 'loss/train': 1.2321690320968628} 08/31/2021 05:38:51 - INFO - __main__ - Step 90381: {'lr': 0.00017486853930220265, 'samples': 17353152, 'steps': 90380, 'loss/train': 0.9330723881721497} 08/31/2021 05:38:52 - INFO - __main__ - Step 90382: {'lr': 0.0001748634778860859, 'samples': 17353344, 'steps': 90381, 'loss/train': 0.9562753438949585} 08/31/2021 05:38:53 - INFO - __main__ - Step 90383: {'lr': 0.00017485841650382455, 'samples': 17353536, 'steps': 90382, 'loss/train': 1.1620270013809204} 08/31/2021 05:38:53 - INFO - __main__ - Step 90384: {'lr': 0.00017485335515542085, 'samples': 17353728, 'steps': 90383, 'loss/train': 1.5999172925949097} 08/31/2021 05:38:53 - INFO - __main__ - Step 90385: {'lr': 0.00017484829384087702, 'samples': 17353920, 'steps': 90384, 'loss/train': 1.1508296728134155} 08/31/2021 05:38:54 - INFO - __main__ - Step 90386: {'lr': 0.00017484323256019546, 'samples': 17354112, 'steps': 90385, 'loss/train': 0.6559374332427979} 08/31/2021 05:38:54 - INFO - __main__ - Step 90387: {'lr': 0.0001748381713133783, 'samples': 17354304, 'steps': 90386, 'loss/train': 1.491787314414978} 08/31/2021 05:38:56 - INFO - __main__ - Step 90388: {'lr': 0.00017483311010042796, 'samples': 17354496, 'steps': 90387, 'loss/train': 2.1460177898406982} 08/31/2021 05:38:56 - INFO - __main__ - Step 90389: {'lr': 0.00017482804892134666, 'samples': 17354688, 'steps': 90388, 'loss/train': 1.4604357481002808} 08/31/2021 05:38:56 - INFO - __main__ - Step 90390: {'lr': 0.00017482298777613664, 'samples': 17354880, 'steps': 90389, 'loss/train': 1.2121660709381104} 08/31/2021 05:38:57 - INFO - __main__ - Step 90391: {'lr': 0.00017481792666480025, 'samples': 17355072, 'steps': 90390, 'loss/train': 1.1994407176971436} 08/31/2021 05:38:57 - INFO - __main__ - Step 90392: {'lr': 0.00017481286558733978, 'samples': 17355264, 'steps': 90391, 'loss/train': 0.517629861831665} 08/31/2021 05:38:59 - INFO - __main__ - Step 90393: {'lr': 0.00017480780454375743, 'samples': 17355456, 'steps': 90392, 'loss/train': 1.7797852754592896} 08/31/2021 05:39:00 - INFO - __main__ - Step 90394: {'lr': 0.00017480274353405558, 'samples': 17355648, 'steps': 90393, 'loss/train': 0.644370973110199} 08/31/2021 05:39:00 - INFO - __main__ - Step 90395: {'lr': 0.0001747976825582364, 'samples': 17355840, 'steps': 90394, 'loss/train': 0.5057873129844666} 08/31/2021 05:39:00 - INFO - __main__ - Step 90396: {'lr': 0.00017479262161630222, 'samples': 17356032, 'steps': 90395, 'loss/train': 0.8619333505630493} 08/31/2021 05:39:01 - INFO - __main__ - Step 90397: {'lr': 0.00017478756070825533, 'samples': 17356224, 'steps': 90396, 'loss/train': 1.4905434846878052} 08/31/2021 05:39:02 - INFO - __main__ - Step 90398: {'lr': 0.000174782499834098, 'samples': 17356416, 'steps': 90397, 'loss/train': 1.228662371635437} 08/31/2021 05:39:03 - INFO - __main__ - Step 90399: {'lr': 0.0001747774389938325, 'samples': 17356608, 'steps': 90398, 'loss/train': 0.7520235776901245} 08/31/2021 05:39:03 - INFO - __main__ - Step 90400: {'lr': 0.00017477237818746115, 'samples': 17356800, 'steps': 90399, 'loss/train': 1.04792320728302} 08/31/2021 05:39:03 - INFO - __main__ - Step 90401: {'lr': 0.00017476731741498618, 'samples': 17356992, 'steps': 90400, 'loss/train': 1.4109110832214355} 08/31/2021 05:39:04 - INFO - __main__ - Step 90402: {'lr': 0.0001747622566764099, 'samples': 17357184, 'steps': 90401, 'loss/train': 0.040179044008255005} 08/31/2021 05:39:04 - INFO - __main__ - Step 90403: {'lr': 0.00017475719597173468, 'samples': 17357376, 'steps': 90402, 'loss/train': 1.3198775053024292} 08/31/2021 05:39:06 - INFO - __main__ - Step 90404: {'lr': 0.0001747521353009626, 'samples': 17357568, 'steps': 90403, 'loss/train': 1.5193908214569092} 08/31/2021 05:39:06 - INFO - __main__ - Step 90405: {'lr': 0.00017474707466409606, 'samples': 17357760, 'steps': 90404, 'loss/train': 1.128712773323059} 08/31/2021 05:39:07 - INFO - __main__ - Step 90406: {'lr': 0.00017474201406113735, 'samples': 17357952, 'steps': 90405, 'loss/train': 1.0848443508148193} 08/31/2021 05:39:07 - INFO - __main__ - Step 90407: {'lr': 0.0001747369534920887, 'samples': 17358144, 'steps': 90406, 'loss/train': 1.385940432548523} 08/31/2021 05:39:07 - INFO - __main__ - Step 90408: {'lr': 0.00017473189295695249, 'samples': 17358336, 'steps': 90407, 'loss/train': 0.7338990569114685} 08/31/2021 05:39:09 - INFO - __main__ - Step 90409: {'lr': 0.00017472683245573086, 'samples': 17358528, 'steps': 90408, 'loss/train': 0.7645944952964783} 08/31/2021 05:39:09 - INFO - __main__ - Step 90410: {'lr': 0.00017472177198842617, 'samples': 17358720, 'steps': 90409, 'loss/train': 1.0665223598480225} 08/31/2021 05:39:10 - INFO - __main__ - Step 90411: {'lr': 0.0001747167115550407, 'samples': 17358912, 'steps': 90410, 'loss/train': 1.178969383239746} 08/31/2021 05:39:10 - INFO - __main__ - Step 90412: {'lr': 0.0001747116511555767, 'samples': 17359104, 'steps': 90411, 'loss/train': 1.4166597127914429} 08/31/2021 05:39:10 - INFO - __main__ - Step 90413: {'lr': 0.00017470659079003644, 'samples': 17359296, 'steps': 90412, 'loss/train': 1.195432424545288} 08/31/2021 05:39:12 - INFO - __main__ - Step 90414: {'lr': 0.00017470153045842234, 'samples': 17359488, 'steps': 90413, 'loss/train': 0.16765671968460083} 08/31/2021 05:39:13 - INFO - __main__ - Step 90415: {'lr': 0.00017469647016073647, 'samples': 17359680, 'steps': 90414, 'loss/train': 1.104249358177185} 08/31/2021 05:39:13 - INFO - __main__ - Step 90416: {'lr': 0.00017469140989698122, 'samples': 17359872, 'steps': 90415, 'loss/train': 1.3605945110321045} 08/31/2021 05:39:13 - INFO - __main__ - Step 90417: {'lr': 0.00017468634966715885, 'samples': 17360064, 'steps': 90416, 'loss/train': 0.7187938094139099} 08/31/2021 05:39:14 - INFO - __main__ - Step 90418: {'lr': 0.00017468128947127168, 'samples': 17360256, 'steps': 90417, 'loss/train': 0.04798689857125282} 08/31/2021 05:39:15 - INFO - __main__ - Step 90419: {'lr': 0.00017467622930932193, 'samples': 17360448, 'steps': 90418, 'loss/train': 1.3501076698303223} 08/31/2021 05:39:16 - INFO - __main__ - Step 90420: {'lr': 0.00017467116918131194, 'samples': 17360640, 'steps': 90419, 'loss/train': 1.4906589984893799} 08/31/2021 05:39:16 - INFO - __main__ - Step 90421: {'lr': 0.00017466610908724398, 'samples': 17360832, 'steps': 90420, 'loss/train': 1.3807475566864014} 08/31/2021 05:39:16 - INFO - __main__ - Step 90422: {'lr': 0.00017466104902712025, 'samples': 17361024, 'steps': 90421, 'loss/train': 1.2639131546020508} 08/31/2021 05:39:17 - INFO - __main__ - Step 90423: {'lr': 0.0001746559890009431, 'samples': 17361216, 'steps': 90422, 'loss/train': 1.0346429347991943} 08/31/2021 05:39:18 - INFO - __main__ - Step 90424: {'lr': 0.0001746509290087148, 'samples': 17361408, 'steps': 90423, 'loss/train': 0.6090699434280396} 08/31/2021 05:39:19 - INFO - __main__ - Step 90425: {'lr': 0.00017464586905043772, 'samples': 17361600, 'steps': 90424, 'loss/train': 2.124150514602661} 08/31/2021 05:39:19 - INFO - __main__ - Step 90426: {'lr': 0.00017464080912611395, 'samples': 17361792, 'steps': 90425, 'loss/train': 1.4667435884475708} 08/31/2021 05:39:19 - INFO - __main__ - Step 90427: {'lr': 0.00017463574923574587, 'samples': 17361984, 'steps': 90426, 'loss/train': 1.3340927362442017} 08/31/2021 05:39:20 - INFO - __main__ - Step 90428: {'lr': 0.0001746306893793358, 'samples': 17362176, 'steps': 90427, 'loss/train': 0.27864861488342285} 08/31/2021 05:39:21 - INFO - __main__ - Step 90429: {'lr': 0.00017462562955688593, 'samples': 17362368, 'steps': 90428, 'loss/train': 1.6163363456726074} 08/31/2021 05:39:22 - INFO - __main__ - Step 90430: {'lr': 0.0001746205697683986, 'samples': 17362560, 'steps': 90429, 'loss/train': 1.5915418863296509} 08/31/2021 05:39:22 - INFO - __main__ - Step 90431: {'lr': 0.0001746155100138761, 'samples': 17362752, 'steps': 90430, 'loss/train': 1.230279803276062} 08/31/2021 05:39:23 - INFO - __main__ - Step 90432: {'lr': 0.00017461045029332068, 'samples': 17362944, 'steps': 90431, 'loss/train': 0.09103348851203918} 08/31/2021 05:39:23 - INFO - __main__ - Step 90433: {'lr': 0.00017460539060673458, 'samples': 17363136, 'steps': 90432, 'loss/train': 0.8303605318069458} 08/31/2021 05:39:25 - INFO - __main__ - Step 90434: {'lr': 0.00017460033095412024, 'samples': 17363328, 'steps': 90433, 'loss/train': 1.5037678480148315} 08/31/2021 05:39:25 - INFO - __main__ - Step 90435: {'lr': 0.00017459527133547976, 'samples': 17363520, 'steps': 90434, 'loss/train': 1.2393604516983032} 08/31/2021 05:39:26 - INFO - __main__ - Step 90436: {'lr': 0.00017459021175081552, 'samples': 17363712, 'steps': 90435, 'loss/train': 1.3324228525161743} 08/31/2021 05:39:26 - INFO - __main__ - Step 90437: {'lr': 0.00017458515220012972, 'samples': 17363904, 'steps': 90436, 'loss/train': 0.7147760391235352} 08/31/2021 05:39:27 - INFO - __main__ - Step 90438: {'lr': 0.00017458009268342474, 'samples': 17364096, 'steps': 90437, 'loss/train': 0.5197595357894897} 08/31/2021 05:39:27 - INFO - __main__ - Step 90439: {'lr': 0.00017457503320070271, 'samples': 17364288, 'steps': 90438, 'loss/train': 1.7052370309829712} 08/31/2021 05:39:28 - INFO - __main__ - Step 90440: {'lr': 0.0001745699737519661, 'samples': 17364480, 'steps': 90439, 'loss/train': 1.500339150428772} 08/31/2021 05:39:29 - INFO - __main__ - Step 90441: {'lr': 0.00017456491433721704, 'samples': 17364672, 'steps': 90440, 'loss/train': 1.0491098165512085} 08/31/2021 05:39:29 - INFO - __main__ - Step 90442: {'lr': 0.00017455985495645786, 'samples': 17364864, 'steps': 90441, 'loss/train': 0.6585280299186707} 08/31/2021 05:39:30 - INFO - __main__ - Step 90443: {'lr': 0.00017455479560969086, 'samples': 17365056, 'steps': 90442, 'loss/train': 1.0520968437194824} 08/31/2021 05:39:30 - INFO - __main__ - Step 90444: {'lr': 0.00017454973629691835, 'samples': 17365248, 'steps': 90443, 'loss/train': 0.5169045925140381} 08/31/2021 05:39:30 - INFO - __main__ - Step 90445: {'lr': 0.0001745446770181425, 'samples': 17365440, 'steps': 90444, 'loss/train': 0.9716899394989014} 08/31/2021 05:39:32 - INFO - __main__ - Step 90446: {'lr': 0.0001745396177733657, 'samples': 17365632, 'steps': 90445, 'loss/train': 1.4351993799209595} 08/31/2021 05:39:32 - INFO - __main__ - Step 90447: {'lr': 0.00017453455856259015, 'samples': 17365824, 'steps': 90446, 'loss/train': 1.6884498596191406} 08/31/2021 05:39:33 - INFO - __main__ - Step 90448: {'lr': 0.00017452949938581824, 'samples': 17366016, 'steps': 90447, 'loss/train': 1.4109678268432617} 08/31/2021 05:39:33 - INFO - __main__ - Step 90449: {'lr': 0.00017452444024305215, 'samples': 17366208, 'steps': 90448, 'loss/train': 1.0716553926467896} 08/31/2021 05:39:33 - INFO - __main__ - Step 90450: {'lr': 0.00017451938113429412, 'samples': 17366400, 'steps': 90449, 'loss/train': 0.8396533727645874} 08/31/2021 05:39:35 - INFO - __main__ - Step 90451: {'lr': 0.00017451432205954653, 'samples': 17366592, 'steps': 90450, 'loss/train': 1.4847209453582764} 08/31/2021 05:39:36 - INFO - __main__ - Step 90452: {'lr': 0.00017450926301881158, 'samples': 17366784, 'steps': 90451, 'loss/train': 1.1293543577194214} 08/31/2021 05:39:36 - INFO - __main__ - Step 90453: {'lr': 0.00017450420401209164, 'samples': 17366976, 'steps': 90452, 'loss/train': 2.4468488693237305} 08/31/2021 05:39:36 - INFO - __main__ - Step 90454: {'lr': 0.00017449914503938892, 'samples': 17367168, 'steps': 90453, 'loss/train': 0.021349988877773285} 08/31/2021 05:39:37 - INFO - __main__ - Step 90455: {'lr': 0.00017449408610070572, 'samples': 17367360, 'steps': 90454, 'loss/train': 0.07943255454301834} 08/31/2021 05:39:37 - INFO - __main__ - Step 90456: {'lr': 0.0001744890271960443, 'samples': 17367552, 'steps': 90455, 'loss/train': 1.1947391033172607} 08/31/2021 05:39:39 - INFO - __main__ - Step 90457: {'lr': 0.00017448396832540696, 'samples': 17367744, 'steps': 90456, 'loss/train': 0.8662247657775879} 08/31/2021 05:39:39 - INFO - __main__ - Step 90458: {'lr': 0.00017447890948879603, 'samples': 17367936, 'steps': 90457, 'loss/train': 1.2732654809951782} 08/31/2021 05:39:39 - INFO - __main__ - Step 90459: {'lr': 0.00017447385068621369, 'samples': 17368128, 'steps': 90458, 'loss/train': 1.2980334758758545} 08/31/2021 05:39:40 - INFO - __main__ - Step 90460: {'lr': 0.00017446879191766228, 'samples': 17368320, 'steps': 90459, 'loss/train': 1.3384146690368652} 08/31/2021 05:39:40 - INFO - __main__ - Step 90461: {'lr': 0.00017446373318314416, 'samples': 17368512, 'steps': 90460, 'loss/train': 0.2824973165988922} 08/31/2021 05:39:42 - INFO - __main__ - Step 90462: {'lr': 0.00017445867448266143, 'samples': 17368704, 'steps': 90461, 'loss/train': 1.375030517578125} 08/31/2021 05:39:43 - INFO - __main__ - Step 90463: {'lr': 0.00017445361581621644, 'samples': 17368896, 'steps': 90462, 'loss/train': 0.9050424098968506} 08/31/2021 05:39:43 - INFO - __main__ - Step 90464: {'lr': 0.00017444855718381147, 'samples': 17369088, 'steps': 90463, 'loss/train': 1.9287605285644531} 08/31/2021 05:39:43 - INFO - __main__ - Step 90465: {'lr': 0.00017444349858544887, 'samples': 17369280, 'steps': 90464, 'loss/train': 0.44193223118782043} 08/31/2021 05:39:44 - INFO - __main__ - Step 90466: {'lr': 0.00017443844002113082, 'samples': 17369472, 'steps': 90465, 'loss/train': 1.0507100820541382} 08/31/2021 05:39:45 - INFO - __main__ - Step 90467: {'lr': 0.00017443338149085964, 'samples': 17369664, 'steps': 90466, 'loss/train': 1.6441304683685303} 08/31/2021 05:39:46 - INFO - __main__ - Step 90468: {'lr': 0.00017442832299463762, 'samples': 17369856, 'steps': 90467, 'loss/train': 0.45597952604293823} 08/31/2021 05:39:46 - INFO - __main__ - Step 90469: {'lr': 0.00017442326453246705, 'samples': 17370048, 'steps': 90468, 'loss/train': 1.2802966833114624} 08/31/2021 05:39:46 - INFO - __main__ - Step 90470: {'lr': 0.0001744182061043502, 'samples': 17370240, 'steps': 90469, 'loss/train': 0.7161186337471008} 08/31/2021 05:39:47 - INFO - __main__ - Step 90471: {'lr': 0.0001744131477102893, 'samples': 17370432, 'steps': 90470, 'loss/train': 1.3876643180847168} 08/31/2021 05:39:48 - INFO - __main__ - Step 90472: {'lr': 0.0001744080893502867, 'samples': 17370624, 'steps': 90471, 'loss/train': 1.335185170173645} 08/31/2021 05:39:49 - INFO - __main__ - Step 90473: {'lr': 0.00017440303102434464, 'samples': 17370816, 'steps': 90472, 'loss/train': 0.9728289246559143} 08/31/2021 05:39:49 - INFO - __main__ - Step 90474: {'lr': 0.0001743979727324654, 'samples': 17371008, 'steps': 90473, 'loss/train': 0.8961261510848999} 08/31/2021 05:39:49 - INFO - __main__ - Step 90475: {'lr': 0.00017439291447465138, 'samples': 17371200, 'steps': 90474, 'loss/train': 0.6230168342590332} 08/31/2021 05:39:50 - INFO - __main__ - Step 90476: {'lr': 0.00017438785625090465, 'samples': 17371392, 'steps': 90475, 'loss/train': 0.45761722326278687} 08/31/2021 05:39:51 - INFO - __main__ - Step 90477: {'lr': 0.00017438279806122753, 'samples': 17371584, 'steps': 90476, 'loss/train': 1.6092153787612915} 08/31/2021 05:39:52 - INFO - __main__ - Step 90478: {'lr': 0.00017437773990562242, 'samples': 17371776, 'steps': 90477, 'loss/train': 1.2650516033172607} 08/31/2021 05:39:52 - INFO - __main__ - Step 90479: {'lr': 0.00017437268178409148, 'samples': 17371968, 'steps': 90478, 'loss/train': 1.1571887731552124} 08/31/2021 05:39:52 - INFO - __main__ - Step 90480: {'lr': 0.00017436762369663712, 'samples': 17372160, 'steps': 90479, 'loss/train': 0.7190709114074707} 08/31/2021 05:39:53 - INFO - __main__ - Step 90481: {'lr': 0.00017436256564326146, 'samples': 17372352, 'steps': 90480, 'loss/train': 1.3164831399917603} 08/31/2021 05:39:54 - INFO - __main__ - Step 90482: {'lr': 0.0001743575076239669, 'samples': 17372544, 'steps': 90481, 'loss/train': 1.7576090097427368} 08/31/2021 05:39:55 - INFO - __main__ - Step 90483: {'lr': 0.00017435244963875569, 'samples': 17372736, 'steps': 90482, 'loss/train': 1.5570542812347412} 08/31/2021 05:39:55 - INFO - __main__ - Step 90484: {'lr': 0.00017434739168763007, 'samples': 17372928, 'steps': 90483, 'loss/train': 1.6914072036743164} 08/31/2021 05:39:55 - INFO - __main__ - Step 90485: {'lr': 0.00017434233377059235, 'samples': 17373120, 'steps': 90484, 'loss/train': 1.2067466974258423} 08/31/2021 05:39:56 - INFO - __main__ - Step 90486: {'lr': 0.00017433727588764484, 'samples': 17373312, 'steps': 90485, 'loss/train': 0.9982943534851074} 08/31/2021 05:39:56 - INFO - __main__ - Step 90487: {'lr': 0.00017433221803878974, 'samples': 17373504, 'steps': 90486, 'loss/train': 0.8626116514205933} 08/31/2021 05:39:57 - INFO - __main__ - Step 90488: {'lr': 0.0001743271602240295, 'samples': 17373696, 'steps': 90487, 'loss/train': 1.1817541122436523} 08/31/2021 05:39:58 - INFO - __main__ - Step 90489: {'lr': 0.00017432210244336618, 'samples': 17373888, 'steps': 90488, 'loss/train': 1.234610915184021} 08/31/2021 05:39:58 - INFO - __main__ - Step 90490: {'lr': 0.00017431704469680215, 'samples': 17374080, 'steps': 90489, 'loss/train': 0.7689778208732605} 08/31/2021 05:39:59 - INFO - __main__ - Step 90491: {'lr': 0.0001743119869843397, 'samples': 17374272, 'steps': 90490, 'loss/train': 0.19323040544986725} 08/31/2021 05:39:59 - INFO - __main__ - Step 90492: {'lr': 0.00017430692930598107, 'samples': 17374464, 'steps': 90491, 'loss/train': 1.308514952659607} 08/31/2021 05:40:00 - INFO - __main__ - Step 90493: {'lr': 0.0001743018716617286, 'samples': 17374656, 'steps': 90492, 'loss/train': 0.9066900610923767} 08/31/2021 05:40:01 - INFO - __main__ - Step 90494: {'lr': 0.00017429681405158455, 'samples': 17374848, 'steps': 90493, 'loss/train': 1.2741742134094238} 08/31/2021 05:40:01 - INFO - __main__ - Step 90495: {'lr': 0.00017429175647555115, 'samples': 17375040, 'steps': 90494, 'loss/train': 1.4818308353424072} 08/31/2021 05:40:02 - INFO - __main__ - Step 90496: {'lr': 0.00017428669893363073, 'samples': 17375232, 'steps': 90495, 'loss/train': 1.0533603429794312} 08/31/2021 05:40:02 - INFO - __main__ - Step 90497: {'lr': 0.00017428164142582552, 'samples': 17375424, 'steps': 90496, 'loss/train': 1.0221518278121948} 08/31/2021 05:40:03 - INFO - __main__ - Step 90498: {'lr': 0.0001742765839521379, 'samples': 17375616, 'steps': 90497, 'loss/train': 1.4603580236434937} 08/31/2021 05:40:04 - INFO - __main__ - Step 90499: {'lr': 0.00017427152651257005, 'samples': 17375808, 'steps': 90498, 'loss/train': 0.5083498954772949} 08/31/2021 05:40:04 - INFO - __main__ - Step 90500: {'lr': 0.00017426646910712428, 'samples': 17376000, 'steps': 90499, 'loss/train': 1.6782636642456055} 08/31/2021 05:40:04 - INFO - __main__ - Step 90501: {'lr': 0.00017426141173580289, 'samples': 17376192, 'steps': 90500, 'loss/train': 1.2367714643478394} 08/31/2021 05:40:05 - INFO - __main__ - Step 90502: {'lr': 0.00017425635439860822, 'samples': 17376384, 'steps': 90501, 'loss/train': 1.695432424545288} 08/31/2021 05:40:06 - INFO - __main__ - Step 90503: {'lr': 0.0001742512970955424, 'samples': 17376576, 'steps': 90502, 'loss/train': 0.8424674272537231} 08/31/2021 05:40:07 - INFO - __main__ - Step 90504: {'lr': 0.0001742462398266077, 'samples': 17376768, 'steps': 90503, 'loss/train': 1.2889906167984009} 08/31/2021 05:40:07 - INFO - __main__ - Step 90505: {'lr': 0.00017424118259180656, 'samples': 17376960, 'steps': 90504, 'loss/train': 1.453696608543396} 08/31/2021 05:40:07 - INFO - __main__ - Step 90506: {'lr': 0.0001742361253911411, 'samples': 17377152, 'steps': 90505, 'loss/train': 1.238756775856018} 08/31/2021 05:40:08 - INFO - __main__ - Step 90507: {'lr': 0.0001742310682246137, 'samples': 17377344, 'steps': 90506, 'loss/train': 1.678985357284546} 08/31/2021 05:40:09 - INFO - __main__ - Step 90508: {'lr': 0.00017422601109222662, 'samples': 17377536, 'steps': 90507, 'loss/train': 1.4834188222885132} 08/31/2021 05:40:10 - INFO - __main__ - Step 90509: {'lr': 0.00017422095399398217, 'samples': 17377728, 'steps': 90508, 'loss/train': 1.4575440883636475} 08/31/2021 05:40:10 - INFO - __main__ - Step 90510: {'lr': 0.00017421589692988255, 'samples': 17377920, 'steps': 90509, 'loss/train': 1.078772783279419} 08/31/2021 05:40:10 - INFO - __main__ - Step 90511: {'lr': 0.0001742108398999301, 'samples': 17378112, 'steps': 90510, 'loss/train': 1.0353925228118896} 08/31/2021 05:40:11 - INFO - __main__ - Step 90512: {'lr': 0.00017420578290412703, 'samples': 17378304, 'steps': 90511, 'loss/train': 1.74613356590271} 08/31/2021 05:40:13 - INFO - __main__ - Step 90513: {'lr': 0.00017420072594247568, 'samples': 17378496, 'steps': 90512, 'loss/train': 1.214607834815979} 08/31/2021 05:40:13 - INFO - __main__ - Step 90514: {'lr': 0.00017419566901497833, 'samples': 17378688, 'steps': 90513, 'loss/train': 0.8165680766105652} 08/31/2021 05:40:14 - INFO - __main__ - Step 90515: {'lr': 0.00017419061212163732, 'samples': 17378880, 'steps': 90514, 'loss/train': 1.1514590978622437} 08/31/2021 05:40:14 - INFO - __main__ - Step 90516: {'lr': 0.00017418555526245476, 'samples': 17379072, 'steps': 90515, 'loss/train': 0.6082566976547241} 08/31/2021 05:40:15 - INFO - __main__ - Step 90517: {'lr': 0.00017418049843743305, 'samples': 17379264, 'steps': 90516, 'loss/train': 1.791019320487976} 08/31/2021 05:40:16 - INFO - __main__ - Step 90518: {'lr': 0.0001741754416465744, 'samples': 17379456, 'steps': 90517, 'loss/train': 1.5622801780700684} 08/31/2021 05:40:16 - INFO - __main__ - Step 90519: {'lr': 0.00017417038488988114, 'samples': 17379648, 'steps': 90518, 'loss/train': 0.9743002653121948} 08/31/2021 05:40:17 - INFO - __main__ - Step 90520: {'lr': 0.00017416532816735554, 'samples': 17379840, 'steps': 90519, 'loss/train': 0.8874178528785706} 08/31/2021 05:40:17 - INFO - __main__ - Step 90521: {'lr': 0.00017416027147899984, 'samples': 17380032, 'steps': 90520, 'loss/train': 1.0251327753067017} 08/31/2021 05:40:17 - INFO - __main__ - Step 90522: {'lr': 0.00017415521482481639, 'samples': 17380224, 'steps': 90521, 'loss/train': 0.9394521117210388} 08/31/2021 05:40:19 - INFO - __main__ - Step 90523: {'lr': 0.00017415015820480739, 'samples': 17380416, 'steps': 90522, 'loss/train': 1.370225191116333} 08/31/2021 05:40:19 - INFO - __main__ - Step 90524: {'lr': 0.0001741451016189752, 'samples': 17380608, 'steps': 90523, 'loss/train': 0.7666499018669128} 08/31/2021 05:40:20 - INFO - __main__ - Step 90525: {'lr': 0.00017414004506732206, 'samples': 17380800, 'steps': 90524, 'loss/train': 0.5996936559677124} 08/31/2021 05:40:20 - INFO - __main__ - Step 90526: {'lr': 0.0001741349885498502, 'samples': 17380992, 'steps': 90525, 'loss/train': 1.9144428968429565} 08/31/2021 05:40:21 - INFO - __main__ - Step 90527: {'lr': 0.00017412993206656203, 'samples': 17381184, 'steps': 90526, 'loss/train': 1.113328218460083} 08/31/2021 05:40:22 - INFO - __main__ - Step 90528: {'lr': 0.00017412487561745967, 'samples': 17381376, 'steps': 90527, 'loss/train': 1.123314380645752} 08/31/2021 05:40:23 - INFO - __main__ - Step 90529: {'lr': 0.00017411981920254554, 'samples': 17381568, 'steps': 90528, 'loss/train': 1.2774813175201416} 08/31/2021 05:40:23 - INFO - __main__ - Step 90530: {'lr': 0.0001741147628218218, 'samples': 17381760, 'steps': 90529, 'loss/train': 0.7565098404884338} 08/31/2021 05:40:23 - INFO - __main__ - Step 90531: {'lr': 0.00017410970647529077, 'samples': 17381952, 'steps': 90530, 'loss/train': 1.1482397317886353} 08/31/2021 05:40:24 - INFO - __main__ - Step 90532: {'lr': 0.00017410465016295474, 'samples': 17382144, 'steps': 90531, 'loss/train': 0.2737088203430176} 08/31/2021 05:40:25 - INFO - __main__ - Step 90533: {'lr': 0.00017409959388481593, 'samples': 17382336, 'steps': 90532, 'loss/train': 1.2169685363769531} 08/31/2021 05:40:26 - INFO - __main__ - Step 90534: {'lr': 0.00017409453764087674, 'samples': 17382528, 'steps': 90533, 'loss/train': 1.3066586256027222} 08/31/2021 05:40:26 - INFO - __main__ - Step 90535: {'lr': 0.00017408948143113936, 'samples': 17382720, 'steps': 90534, 'loss/train': 1.1105743646621704} 08/31/2021 05:40:26 - INFO - __main__ - Step 90536: {'lr': 0.0001740844252556061, 'samples': 17382912, 'steps': 90535, 'loss/train': 1.1041958332061768} 08/31/2021 05:40:27 - INFO - __main__ - Step 90537: {'lr': 0.00017407936911427923, 'samples': 17383104, 'steps': 90536, 'loss/train': 0.15969786047935486} 08/31/2021 05:40:28 - INFO - __main__ - Step 90538: {'lr': 0.00017407431300716104, 'samples': 17383296, 'steps': 90537, 'loss/train': 1.363688349723816} 08/31/2021 05:40:28 - INFO - __main__ - Step 90539: {'lr': 0.00017406925693425374, 'samples': 17383488, 'steps': 90538, 'loss/train': 1.4292975664138794} 08/31/2021 05:40:29 - INFO - __main__ - Step 90540: {'lr': 0.0001740642008955597, 'samples': 17383680, 'steps': 90539, 'loss/train': 0.8267409801483154} 08/31/2021 05:40:29 - INFO - __main__ - Step 90541: {'lr': 0.00017405914489108113, 'samples': 17383872, 'steps': 90540, 'loss/train': 1.2324460744857788} 08/31/2021 05:40:30 - INFO - __main__ - Step 90542: {'lr': 0.0001740540889208204, 'samples': 17384064, 'steps': 90541, 'loss/train': 1.2905025482177734} 08/31/2021 05:40:30 - INFO - __main__ - Step 90543: {'lr': 0.00017404903298477966, 'samples': 17384256, 'steps': 90542, 'loss/train': 1.3806400299072266} 08/31/2021 05:40:31 - INFO - __main__ - Step 90544: {'lr': 0.00017404397708296128, 'samples': 17384448, 'steps': 90543, 'loss/train': 1.7504122257232666} 08/31/2021 05:40:32 - INFO - __main__ - Step 90545: {'lr': 0.0001740389212153675, 'samples': 17384640, 'steps': 90544, 'loss/train': 1.776775598526001} 08/31/2021 05:40:32 - INFO - __main__ - Step 90546: {'lr': 0.0001740338653820006, 'samples': 17384832, 'steps': 90545, 'loss/train': 1.1591602563858032} 08/31/2021 05:40:33 - INFO - __main__ - Step 90547: {'lr': 0.0001740288095828629, 'samples': 17385024, 'steps': 90546, 'loss/train': 2.0141990184783936} 08/31/2021 05:40:33 - INFO - __main__ - Step 90548: {'lr': 0.00017402375381795666, 'samples': 17385216, 'steps': 90547, 'loss/train': 0.9989401698112488} 08/31/2021 05:40:34 - INFO - __main__ - Step 90549: {'lr': 0.0001740186980872841, 'samples': 17385408, 'steps': 90548, 'loss/train': 0.6625173091888428} 08/31/2021 05:40:35 - INFO - __main__ - Step 90550: {'lr': 0.00017401364239084754, 'samples': 17385600, 'steps': 90549, 'loss/train': 1.2723115682601929} 08/31/2021 05:40:35 - INFO - __main__ - Step 90551: {'lr': 0.00017400858672864927, 'samples': 17385792, 'steps': 90550, 'loss/train': 1.3795450925827026} 08/31/2021 05:40:36 - INFO - __main__ - Step 90552: {'lr': 0.00017400353110069155, 'samples': 17385984, 'steps': 90551, 'loss/train': 1.2368251085281372} 08/31/2021 05:40:36 - INFO - __main__ - Step 90553: {'lr': 0.00017399847550697667, 'samples': 17386176, 'steps': 90552, 'loss/train': 1.394653558731079} 08/31/2021 05:40:37 - INFO - __main__ - Step 90554: {'lr': 0.00017399341994750692, 'samples': 17386368, 'steps': 90553, 'loss/train': 1.3480374813079834} 08/31/2021 05:40:38 - INFO - __main__ - Step 90555: {'lr': 0.00017398836442228461, 'samples': 17386560, 'steps': 90554, 'loss/train': 1.057462453842163} 08/31/2021 05:40:38 - INFO - __main__ - Step 90556: {'lr': 0.00017398330893131193, 'samples': 17386752, 'steps': 90555, 'loss/train': 1.1775028705596924} 08/31/2021 05:40:39 - INFO - __main__ - Step 90557: {'lr': 0.00017397825347459118, 'samples': 17386944, 'steps': 90556, 'loss/train': 1.295541524887085} 08/31/2021 05:40:39 - INFO - __main__ - Step 90558: {'lr': 0.00017397319805212465, 'samples': 17387136, 'steps': 90557, 'loss/train': 1.3022949695587158} 08/31/2021 05:40:40 - INFO - __main__ - Step 90559: {'lr': 0.00017396814266391463, 'samples': 17387328, 'steps': 90558, 'loss/train': 0.7058913111686707} 08/31/2021 05:40:41 - INFO - __main__ - Step 90560: {'lr': 0.00017396308730996342, 'samples': 17387520, 'steps': 90559, 'loss/train': 1.4229247570037842} 08/31/2021 05:40:41 - INFO - __main__ - Step 90561: {'lr': 0.00017395803199027324, 'samples': 17387712, 'steps': 90560, 'loss/train': 1.530866265296936} 08/31/2021 05:40:41 - INFO - __main__ - Step 90562: {'lr': 0.0001739529767048464, 'samples': 17387904, 'steps': 90561, 'loss/train': 2.08894419670105} 08/31/2021 05:40:42 - INFO - __main__ - Step 90563: {'lr': 0.00017394792145368514, 'samples': 17388096, 'steps': 90562, 'loss/train': 1.0355675220489502} 08/31/2021 05:40:44 - INFO - __main__ - Step 90564: {'lr': 0.00017394286623679183, 'samples': 17388288, 'steps': 90563, 'loss/train': 1.3470540046691895} 08/31/2021 05:40:44 - INFO - __main__ - Step 90565: {'lr': 0.00017393781105416866, 'samples': 17388480, 'steps': 90564, 'loss/train': 0.8574814796447754} 08/31/2021 05:40:44 - INFO - __main__ - Step 90566: {'lr': 0.00017393275590581793, 'samples': 17388672, 'steps': 90565, 'loss/train': 1.3013279438018799} 08/31/2021 05:40:45 - INFO - __main__ - Step 90567: {'lr': 0.00017392770079174198, 'samples': 17388864, 'steps': 90566, 'loss/train': 1.4019335508346558} 08/31/2021 05:40:45 - INFO - __main__ - Step 90568: {'lr': 0.00017392264571194297, 'samples': 17389056, 'steps': 90567, 'loss/train': 0.9496216773986816} 08/31/2021 05:40:47 - INFO - __main__ - Step 90569: {'lr': 0.00017391759066642332, 'samples': 17389248, 'steps': 90568, 'loss/train': 1.366290807723999} 08/31/2021 05:40:48 - INFO - __main__ - Step 90570: {'lr': 0.00017391253565518522, 'samples': 17389440, 'steps': 90569, 'loss/train': 1.1912953853607178} 08/31/2021 05:40:48 - INFO - __main__ - Step 90571: {'lr': 0.00017390748067823092, 'samples': 17389632, 'steps': 90570, 'loss/train': 1.56602144241333} 08/31/2021 05:40:48 - INFO - __main__ - Step 90572: {'lr': 0.00017390242573556272, 'samples': 17389824, 'steps': 90571, 'loss/train': 1.449115514755249} 08/31/2021 05:40:49 - INFO - __main__ - Step 90573: {'lr': 0.00017389737082718293, 'samples': 17390016, 'steps': 90572, 'loss/train': 1.1206536293029785} 08/31/2021 05:40:49 - INFO - __main__ - Step 90574: {'lr': 0.0001738923159530938, 'samples': 17390208, 'steps': 90573, 'loss/train': 1.1317672729492188} 08/31/2021 05:40:51 - INFO - __main__ - Step 90575: {'lr': 0.0001738872611132976, 'samples': 17390400, 'steps': 90574, 'loss/train': 4.336518287658691} 08/31/2021 05:40:51 - INFO - __main__ - Step 90576: {'lr': 0.00017388220630779665, 'samples': 17390592, 'steps': 90575, 'loss/train': 1.3408327102661133} 08/31/2021 05:40:52 - INFO - __main__ - Step 90577: {'lr': 0.0001738771515365932, 'samples': 17390784, 'steps': 90576, 'loss/train': 1.0609581470489502} 08/31/2021 05:40:52 - INFO - __main__ - Step 90578: {'lr': 0.00017387209679968954, 'samples': 17390976, 'steps': 90577, 'loss/train': 1.6235913038253784} 08/31/2021 05:40:52 - INFO - __main__ - Step 90579: {'lr': 0.00017386704209708794, 'samples': 17391168, 'steps': 90578, 'loss/train': 0.07703686505556107} 08/31/2021 05:40:54 - INFO - __main__ - Step 90580: {'lr': 0.00017386198742879068, 'samples': 17391360, 'steps': 90579, 'loss/train': 1.226595401763916} 08/31/2021 05:40:55 - INFO - __main__ - Step 90581: {'lr': 0.0001738569327948, 'samples': 17391552, 'steps': 90580, 'loss/train': 0.8464341759681702} 08/31/2021 05:40:55 - INFO - __main__ - Step 90582: {'lr': 0.00017385187819511834, 'samples': 17391744, 'steps': 90581, 'loss/train': 0.6346291899681091} 08/31/2021 05:40:55 - INFO - __main__ - Step 90583: {'lr': 0.00017384682362974775, 'samples': 17391936, 'steps': 90582, 'loss/train': 0.018568512052297592} 08/31/2021 05:40:56 - INFO - __main__ - Step 90584: {'lr': 0.00017384176909869057, 'samples': 17392128, 'steps': 90583, 'loss/train': 2.238717555999756} 08/31/2021 05:40:56 - INFO - __main__ - Step 90585: {'lr': 0.00017383671460194914, 'samples': 17392320, 'steps': 90584, 'loss/train': 1.324268102645874} 08/31/2021 05:40:58 - INFO - __main__ - Step 90586: {'lr': 0.0001738316601395257, 'samples': 17392512, 'steps': 90585, 'loss/train': 0.5098134875297546} 08/31/2021 05:40:59 - INFO - __main__ - Step 90587: {'lr': 0.00017382660571142256, 'samples': 17392704, 'steps': 90586, 'loss/train': 1.5886478424072266} 08/31/2021 05:40:59 - INFO - __main__ - Step 90588: {'lr': 0.00017382155131764193, 'samples': 17392896, 'steps': 90587, 'loss/train': 1.4075095653533936} 08/31/2021 05:40:59 - INFO - __main__ - Step 90589: {'lr': 0.0001738164969581862, 'samples': 17393088, 'steps': 90588, 'loss/train': 0.9020574688911438} 08/31/2021 05:41:00 - INFO - __main__ - Step 90590: {'lr': 0.00017381144263305755, 'samples': 17393280, 'steps': 90589, 'loss/train': 1.0642120838165283} 08/31/2021 05:41:00 - INFO - __main__ - Step 90591: {'lr': 0.00017380638834225826, 'samples': 17393472, 'steps': 90590, 'loss/train': 0.6257680654525757} 08/31/2021 05:41:02 - INFO - __main__ - Step 90592: {'lr': 0.00017380133408579067, 'samples': 17393664, 'steps': 90591, 'loss/train': 0.7946217060089111} 08/31/2021 05:41:02 - INFO - __main__ - Step 90593: {'lr': 0.000173796279863657, 'samples': 17393856, 'steps': 90592, 'loss/train': 0.6607397198677063} 08/31/2021 05:41:02 - INFO - __main__ - Step 90594: {'lr': 0.00017379122567585958, 'samples': 17394048, 'steps': 90593, 'loss/train': 0.9928617477416992} 08/31/2021 05:41:03 - INFO - __main__ - Step 90595: {'lr': 0.00017378617152240063, 'samples': 17394240, 'steps': 90594, 'loss/train': 1.5332449674606323} 08/31/2021 05:41:03 - INFO - __main__ - Step 90596: {'lr': 0.00017378111740328257, 'samples': 17394432, 'steps': 90595, 'loss/train': 1.489275574684143} 08/31/2021 05:41:05 - INFO - __main__ - Step 90597: {'lr': 0.00017377606331850747, 'samples': 17394624, 'steps': 90596, 'loss/train': 1.7915163040161133} 08/31/2021 05:41:05 - INFO - __main__ - Step 90598: {'lr': 0.0001737710092680777, 'samples': 17394816, 'steps': 90597, 'loss/train': 0.9804489612579346} 08/31/2021 05:41:05 - INFO - __main__ - Step 90599: {'lr': 0.00017376595525199552, 'samples': 17395008, 'steps': 90598, 'loss/train': 1.445299506187439} 08/31/2021 05:41:06 - INFO - __main__ - Step 90600: {'lr': 0.00017376090127026322, 'samples': 17395200, 'steps': 90599, 'loss/train': 0.39357608556747437} 08/31/2021 05:41:06 - INFO - __main__ - Step 90601: {'lr': 0.00017375584732288307, 'samples': 17395392, 'steps': 90600, 'loss/train': 1.1577122211456299} 08/31/2021 05:41:08 - INFO - __main__ - Step 90602: {'lr': 0.0001737507934098574, 'samples': 17395584, 'steps': 90601, 'loss/train': 1.6631135940551758} 08/31/2021 05:41:08 - INFO - __main__ - Step 90603: {'lr': 0.00017374573953118843, 'samples': 17395776, 'steps': 90602, 'loss/train': 1.8416963815689087} 08/31/2021 05:41:09 - INFO - __main__ - Step 90604: {'lr': 0.00017374068568687845, 'samples': 17395968, 'steps': 90603, 'loss/train': 0.9086402654647827} 08/31/2021 05:41:09 - INFO - __main__ - Step 90605: {'lr': 0.00017373563187692974, 'samples': 17396160, 'steps': 90604, 'loss/train': 0.9759713411331177} 08/31/2021 05:41:09 - INFO - __main__ - Step 90606: {'lr': 0.00017373057810134458, 'samples': 17396352, 'steps': 90605, 'loss/train': 1.1099450588226318} 08/31/2021 05:41:11 - INFO - __main__ - Step 90607: {'lr': 0.00017372552436012523, 'samples': 17396544, 'steps': 90606, 'loss/train': 0.9449359178543091} 08/31/2021 05:41:11 - INFO - __main__ - Step 90608: {'lr': 0.00017372047065327401, 'samples': 17396736, 'steps': 90607, 'loss/train': 0.9746782779693604} 08/31/2021 05:41:11 - INFO - __main__ - Step 90609: {'lr': 0.00017371541698079325, 'samples': 17396928, 'steps': 90608, 'loss/train': 2.1301376819610596} 08/31/2021 05:41:12 - INFO - __main__ - Step 90610: {'lr': 0.00017371036334268503, 'samples': 17397120, 'steps': 90609, 'loss/train': 1.0425708293914795} 08/31/2021 05:41:12 - INFO - __main__ - Step 90611: {'lr': 0.00017370530973895176, 'samples': 17397312, 'steps': 90610, 'loss/train': 1.0434046983718872} 08/31/2021 05:41:14 - INFO - __main__ - Step 90612: {'lr': 0.00017370025616959573, 'samples': 17397504, 'steps': 90611, 'loss/train': 1.3996444940567017} 08/31/2021 05:41:15 - INFO - __main__ - Step 90613: {'lr': 0.00017369520263461912, 'samples': 17397696, 'steps': 90612, 'loss/train': 0.21954628825187683} 08/31/2021 05:41:15 - INFO - __main__ - Step 90614: {'lr': 0.00017369014913402433, 'samples': 17397888, 'steps': 90613, 'loss/train': 0.05565611645579338} 08/31/2021 05:41:15 - INFO - __main__ - Step 90615: {'lr': 0.0001736850956678136, 'samples': 17398080, 'steps': 90614, 'loss/train': 1.376076340675354} 08/31/2021 05:41:16 - INFO - __main__ - Step 90616: {'lr': 0.00017368004223598912, 'samples': 17398272, 'steps': 90615, 'loss/train': 0.8901642560958862} 08/31/2021 05:41:16 - INFO - __main__ - Step 90617: {'lr': 0.00017367498883855327, 'samples': 17398464, 'steps': 90616, 'loss/train': 2.2645621299743652} 08/31/2021 05:41:17 - INFO - __main__ - Step 90618: {'lr': 0.0001736699354755083, 'samples': 17398656, 'steps': 90617, 'loss/train': 1.152834177017212} 08/31/2021 05:41:18 - INFO - __main__ - Step 90619: {'lr': 0.00017366488214685648, 'samples': 17398848, 'steps': 90618, 'loss/train': 1.4161595106124878} 08/31/2021 05:41:18 - INFO - __main__ - Step 90620: {'lr': 0.00017365982885260008, 'samples': 17399040, 'steps': 90619, 'loss/train': 1.0574922561645508} 08/31/2021 05:41:19 - INFO - __main__ - Step 90621: {'lr': 0.00017365477559274135, 'samples': 17399232, 'steps': 90620, 'loss/train': 0.7039802670478821} 08/31/2021 05:41:19 - INFO - __main__ - Step 90622: {'lr': 0.00017364972236728267, 'samples': 17399424, 'steps': 90621, 'loss/train': 0.21239861845970154} 08/31/2021 05:41:21 - INFO - __main__ - Step 90623: {'lr': 0.0001736446691762263, 'samples': 17399616, 'steps': 90622, 'loss/train': 1.1710411310195923} 08/31/2021 05:41:22 - INFO - __main__ - Step 90624: {'lr': 0.00017363961601957434, 'samples': 17399808, 'steps': 90623, 'loss/train': 2.127063512802124} 08/31/2021 05:41:22 - INFO - __main__ - Step 90625: {'lr': 0.00017363456289732924, 'samples': 17400000, 'steps': 90624, 'loss/train': 0.5979472994804382} 08/31/2021 05:41:22 - INFO - __main__ - Step 90626: {'lr': 0.00017362950980949322, 'samples': 17400192, 'steps': 90625, 'loss/train': 1.4227346181869507} 08/31/2021 05:41:23 - INFO - __main__ - Step 90627: {'lr': 0.00017362445675606853, 'samples': 17400384, 'steps': 90626, 'loss/train': 1.2666085958480835} 08/31/2021 05:41:24 - INFO - __main__ - Step 90628: {'lr': 0.0001736194037370575, 'samples': 17400576, 'steps': 90627, 'loss/train': 0.7571197152137756} 08/31/2021 05:41:25 - INFO - __main__ - Step 90629: {'lr': 0.00017361435075246242, 'samples': 17400768, 'steps': 90628, 'loss/train': 1.5046684741973877} 08/31/2021 05:41:25 - INFO - __main__ - Step 90630: {'lr': 0.00017360929780228546, 'samples': 17400960, 'steps': 90629, 'loss/train': 0.6276510953903198} 08/31/2021 05:41:25 - INFO - __main__ - Step 90631: {'lr': 0.00017360424488652905, 'samples': 17401152, 'steps': 90630, 'loss/train': 1.3390358686447144} 08/31/2021 05:41:26 - INFO - __main__ - Step 90632: {'lr': 0.00017359919200519536, 'samples': 17401344, 'steps': 90631, 'loss/train': 1.032749891281128} 08/31/2021 05:41:26 - INFO - __main__ - Step 90633: {'lr': 0.00017359413915828668, 'samples': 17401536, 'steps': 90632, 'loss/train': 0.8773845434188843} 08/31/2021 05:41:28 - INFO - __main__ - Step 90634: {'lr': 0.0001735890863458053, 'samples': 17401728, 'steps': 90633, 'loss/train': 0.9151371717453003} 08/31/2021 05:41:28 - INFO - __main__ - Step 90635: {'lr': 0.0001735840335677535, 'samples': 17401920, 'steps': 90634, 'loss/train': 0.7310080528259277} 08/31/2021 05:41:29 - INFO - __main__ - Step 90636: {'lr': 0.00017357898082413371, 'samples': 17402112, 'steps': 90635, 'loss/train': 1.3040823936462402} 08/31/2021 05:41:29 - INFO - __main__ - Step 90637: {'lr': 0.00017357392811494788, 'samples': 17402304, 'steps': 90636, 'loss/train': 0.8221182823181152} 08/31/2021 05:41:29 - INFO - __main__ - Step 90638: {'lr': 0.0001735688754401985, 'samples': 17402496, 'steps': 90637, 'loss/train': 1.1201651096343994} 08/31/2021 05:41:31 - INFO - __main__ - Step 90639: {'lr': 0.0001735638227998878, 'samples': 17402688, 'steps': 90638, 'loss/train': 1.2007994651794434} 08/31/2021 05:41:31 - INFO - __main__ - Step 90640: {'lr': 0.00017355877019401805, 'samples': 17402880, 'steps': 90639, 'loss/train': 0.2342844158411026} 08/31/2021 05:41:32 - INFO - __main__ - Step 90641: {'lr': 0.00017355371762259154, 'samples': 17403072, 'steps': 90640, 'loss/train': 1.3546600341796875} 08/31/2021 05:41:32 - INFO - __main__ - Step 90642: {'lr': 0.00017354866508561054, 'samples': 17403264, 'steps': 90641, 'loss/train': 0.5008506178855896} 08/31/2021 05:41:32 - INFO - __main__ - Step 90643: {'lr': 0.00017354361258307735, 'samples': 17403456, 'steps': 90642, 'loss/train': 1.288116455078125} 08/31/2021 05:41:34 - INFO - __main__ - Step 90644: {'lr': 0.00017353856011499423, 'samples': 17403648, 'steps': 90643, 'loss/train': 0.4478635787963867} 08/31/2021 05:41:34 - INFO - __main__ - Step 90645: {'lr': 0.00017353350768136344, 'samples': 17403840, 'steps': 90644, 'loss/train': 0.5425105690956116} 08/31/2021 05:41:35 - INFO - __main__ - Step 90646: {'lr': 0.00017352845528218724, 'samples': 17404032, 'steps': 90645, 'loss/train': 1.237168312072754} 08/31/2021 05:41:35 - INFO - __main__ - Step 90647: {'lr': 0.000173523402917468, 'samples': 17404224, 'steps': 90646, 'loss/train': 1.0908637046813965} 08/31/2021 05:41:35 - INFO - __main__ - Step 90648: {'lr': 0.00017351835058720792, 'samples': 17404416, 'steps': 90647, 'loss/train': 0.7943020462989807} 08/31/2021 05:41:37 - INFO - __main__ - Step 90649: {'lr': 0.00017351329829140926, 'samples': 17404608, 'steps': 90648, 'loss/train': 1.3382611274719238} 08/31/2021 05:41:37 - INFO - __main__ - Step 90650: {'lr': 0.00017350824603007444, 'samples': 17404800, 'steps': 90649, 'loss/train': 0.9760000705718994} 08/31/2021 05:41:38 - INFO - __main__ - Step 90651: {'lr': 0.00017350319380320556, 'samples': 17404992, 'steps': 90650, 'loss/train': 1.1723954677581787} 08/31/2021 05:41:38 - INFO - __main__ - Step 90652: {'lr': 0.0001734981416108049, 'samples': 17405184, 'steps': 90651, 'loss/train': 0.17393696308135986} 08/31/2021 05:41:38 - INFO - __main__ - Step 90653: {'lr': 0.00017349308945287484, 'samples': 17405376, 'steps': 90652, 'loss/train': 1.446771264076233} 08/31/2021 05:41:40 - INFO - __main__ - Step 90654: {'lr': 0.0001734880373294176, 'samples': 17405568, 'steps': 90653, 'loss/train': 2.265864849090576} 08/31/2021 05:41:41 - INFO - __main__ - Step 90655: {'lr': 0.0001734829852404355, 'samples': 17405760, 'steps': 90654, 'loss/train': 1.4200387001037598} 08/31/2021 05:41:41 - INFO - __main__ - Step 90656: {'lr': 0.00017347793318593074, 'samples': 17405952, 'steps': 90655, 'loss/train': 0.026470769196748734} 08/31/2021 05:41:41 - INFO - __main__ - Step 90657: {'lr': 0.00017347288116590566, 'samples': 17406144, 'steps': 90656, 'loss/train': 0.041233256459236145} 08/31/2021 05:41:42 - INFO - __main__ - Step 90658: {'lr': 0.0001734678291803625, 'samples': 17406336, 'steps': 90657, 'loss/train': 0.6100925803184509} 08/31/2021 05:41:43 - INFO - __main__ - Step 90659: {'lr': 0.00017346277722930358, 'samples': 17406528, 'steps': 90658, 'loss/train': 1.756144642829895} 08/31/2021 05:41:44 - INFO - __main__ - Step 90660: {'lr': 0.00017345772531273117, 'samples': 17406720, 'steps': 90659, 'loss/train': 1.217769742012024} 08/31/2021 05:41:44 - INFO - __main__ - Step 90661: {'lr': 0.00017345267343064753, 'samples': 17406912, 'steps': 90660, 'loss/train': 1.1531124114990234} 08/31/2021 05:41:44 - INFO - __main__ - Step 90662: {'lr': 0.0001734476215830549, 'samples': 17407104, 'steps': 90661, 'loss/train': 1.6857253313064575} 08/31/2021 05:41:45 - INFO - __main__ - Step 90663: {'lr': 0.00017344256976995566, 'samples': 17407296, 'steps': 90662, 'loss/train': 1.3715871572494507} 08/31/2021 05:41:46 - INFO - __main__ - Step 90664: {'lr': 0.00017343751799135196, 'samples': 17407488, 'steps': 90663, 'loss/train': 0.9661069512367249} 08/31/2021 05:41:47 - INFO - __main__ - Step 90665: {'lr': 0.00017343246624724614, 'samples': 17407680, 'steps': 90664, 'loss/train': 1.1604944467544556} 08/31/2021 05:41:47 - INFO - __main__ - Step 90666: {'lr': 0.00017342741453764044, 'samples': 17407872, 'steps': 90665, 'loss/train': 1.0662366151809692} 08/31/2021 05:41:48 - INFO - __main__ - Step 90667: {'lr': 0.00017342236286253717, 'samples': 17408064, 'steps': 90666, 'loss/train': 1.2706050872802734} 08/31/2021 05:41:48 - INFO - __main__ - Step 90668: {'lr': 0.00017341731122193864, 'samples': 17408256, 'steps': 90667, 'loss/train': 1.5994229316711426} 08/31/2021 05:41:48 - INFO - __main__ - Step 90669: {'lr': 0.00017341225961584706, 'samples': 17408448, 'steps': 90668, 'loss/train': 1.0321123600006104} 08/31/2021 05:41:50 - INFO - __main__ - Step 90670: {'lr': 0.00017340720804426475, 'samples': 17408640, 'steps': 90669, 'loss/train': 1.140354871749878} 08/31/2021 05:41:50 - INFO - __main__ - Step 90671: {'lr': 0.00017340215650719394, 'samples': 17408832, 'steps': 90670, 'loss/train': 1.3499000072479248} 08/31/2021 05:41:51 - INFO - __main__ - Step 90672: {'lr': 0.000173397105004637, 'samples': 17409024, 'steps': 90671, 'loss/train': 1.2477636337280273} 08/31/2021 05:41:51 - INFO - __main__ - Step 90673: {'lr': 0.0001733920535365961, 'samples': 17409216, 'steps': 90672, 'loss/train': 1.4933242797851562} 08/31/2021 05:41:51 - INFO - __main__ - Step 90674: {'lr': 0.00017338700210307355, 'samples': 17409408, 'steps': 90673, 'loss/train': 1.6137615442276} 08/31/2021 05:41:52 - INFO - __main__ - Step 90675: {'lr': 0.00017338195070407163, 'samples': 17409600, 'steps': 90674, 'loss/train': 1.1524277925491333} 08/31/2021 05:41:54 - INFO - __main__ - Step 90676: {'lr': 0.00017337689933959267, 'samples': 17409792, 'steps': 90675, 'loss/train': 1.404761552810669} 08/31/2021 05:41:54 - INFO - __main__ - Step 90677: {'lr': 0.00017337184800963887, 'samples': 17409984, 'steps': 90676, 'loss/train': 0.9130239486694336} 08/31/2021 05:41:54 - INFO - __main__ - Step 90678: {'lr': 0.00017336679671421253, 'samples': 17410176, 'steps': 90677, 'loss/train': 1.5754581689834595} 08/31/2021 05:41:55 - INFO - __main__ - Step 90679: {'lr': 0.0001733617454533159, 'samples': 17410368, 'steps': 90678, 'loss/train': 1.4380161762237549} 08/31/2021 05:41:55 - INFO - __main__ - Step 90680: {'lr': 0.0001733566942269513, 'samples': 17410560, 'steps': 90679, 'loss/train': 0.6977389454841614} 08/31/2021 05:41:57 - INFO - __main__ - Step 90681: {'lr': 0.000173351643035121, 'samples': 17410752, 'steps': 90680, 'loss/train': 1.1571688652038574} 08/31/2021 05:41:57 - INFO - __main__ - Step 90682: {'lr': 0.00017334659187782724, 'samples': 17410944, 'steps': 90681, 'loss/train': 1.0487364530563354} 08/31/2021 05:41:57 - INFO - __main__ - Step 90683: {'lr': 0.00017334154075507243, 'samples': 17411136, 'steps': 90682, 'loss/train': 1.2416352033615112} 08/31/2021 05:41:58 - INFO - __main__ - Step 90684: {'lr': 0.0001733364896668586, 'samples': 17411328, 'steps': 90683, 'loss/train': 1.4877294301986694} 08/31/2021 05:41:58 - INFO - __main__ - Step 90685: {'lr': 0.00017333143861318823, 'samples': 17411520, 'steps': 90684, 'loss/train': 1.203941822052002} 08/31/2021 05:42:00 - INFO - __main__ - Step 90686: {'lr': 0.00017332638759406355, 'samples': 17411712, 'steps': 90685, 'loss/train': 1.3683528900146484} 08/31/2021 05:42:00 - INFO - __main__ - Step 90687: {'lr': 0.00017332133660948677, 'samples': 17411904, 'steps': 90686, 'loss/train': 1.36384117603302} 08/31/2021 05:42:00 - INFO - __main__ - Step 90688: {'lr': 0.00017331628565946022, 'samples': 17412096, 'steps': 90687, 'loss/train': 1.4992971420288086} 08/31/2021 05:42:01 - INFO - __main__ - Step 90689: {'lr': 0.00017331123474398618, 'samples': 17412288, 'steps': 90688, 'loss/train': 1.6421164274215698} 08/31/2021 05:42:01 - INFO - __main__ - Step 90690: {'lr': 0.00017330618386306697, 'samples': 17412480, 'steps': 90689, 'loss/train': 1.4025932550430298} 08/31/2021 05:42:03 - INFO - __main__ - Step 90691: {'lr': 0.00017330113301670475, 'samples': 17412672, 'steps': 90690, 'loss/train': 0.9549787044525146} 08/31/2021 05:42:03 - INFO - __main__ - Step 90692: {'lr': 0.00017329608220490185, 'samples': 17412864, 'steps': 90691, 'loss/train': 0.8308404684066772} 08/31/2021 05:42:04 - INFO - __main__ - Step 90693: {'lr': 0.00017329103142766055, 'samples': 17413056, 'steps': 90692, 'loss/train': 0.7347807288169861} 08/31/2021 05:42:04 - INFO - __main__ - Step 90694: {'lr': 0.0001732859806849832, 'samples': 17413248, 'steps': 90693, 'loss/train': 1.1905871629714966} 08/31/2021 05:42:04 - INFO - __main__ - Step 90695: {'lr': 0.00017328092997687193, 'samples': 17413440, 'steps': 90694, 'loss/train': 0.9457021951675415} 08/31/2021 05:42:06 - INFO - __main__ - Step 90696: {'lr': 0.0001732758793033291, 'samples': 17413632, 'steps': 90695, 'loss/train': 1.317866325378418} 08/31/2021 05:42:07 - INFO - __main__ - Step 90697: {'lr': 0.00017327082866435694, 'samples': 17413824, 'steps': 90696, 'loss/train': 1.4154261350631714} 08/31/2021 05:42:07 - INFO - __main__ - Step 90698: {'lr': 0.0001732657780599578, 'samples': 17414016, 'steps': 90697, 'loss/train': 1.12264883518219} 08/31/2021 05:42:07 - INFO - __main__ - Step 90699: {'lr': 0.00017326072749013392, 'samples': 17414208, 'steps': 90698, 'loss/train': 1.5480085611343384} 08/31/2021 05:42:08 - INFO - __main__ - Step 90700: {'lr': 0.00017325567695488753, 'samples': 17414400, 'steps': 90699, 'loss/train': 1.0076512098312378} 08/31/2021 05:42:08 - INFO - __main__ - Step 90701: {'lr': 0.00017325062645422103, 'samples': 17414592, 'steps': 90700, 'loss/train': 0.4844662547111511} 08/31/2021 05:42:10 - INFO - __main__ - Step 90702: {'lr': 0.00017324557598813654, 'samples': 17414784, 'steps': 90701, 'loss/train': 1.2185732126235962} 08/31/2021 05:42:10 - INFO - __main__ - Step 90703: {'lr': 0.00017324052555663647, 'samples': 17414976, 'steps': 90702, 'loss/train': 1.5349305868148804} 08/31/2021 05:42:10 - INFO - __main__ - Step 90704: {'lr': 0.000173235475159723, 'samples': 17415168, 'steps': 90703, 'loss/train': 1.4472004175186157} 08/31/2021 05:42:11 - INFO - __main__ - Step 90705: {'lr': 0.00017323042479739848, 'samples': 17415360, 'steps': 90704, 'loss/train': 1.7620692253112793} 08/31/2021 05:42:11 - INFO - __main__ - Step 90706: {'lr': 0.0001732253744696651, 'samples': 17415552, 'steps': 90705, 'loss/train': 0.7232752442359924} 08/31/2021 05:42:12 - INFO - __main__ - Step 90707: {'lr': 0.00017322032417652517, 'samples': 17415744, 'steps': 90706, 'loss/train': 0.036786727607250214} 08/31/2021 05:42:13 - INFO - __main__ - Step 90708: {'lr': 0.000173215273917981, 'samples': 17415936, 'steps': 90707, 'loss/train': 1.7618446350097656} 08/31/2021 05:42:13 - INFO - __main__ - Step 90709: {'lr': 0.00017321022369403484, 'samples': 17416128, 'steps': 90708, 'loss/train': 1.4114547967910767} 08/31/2021 05:42:14 - INFO - __main__ - Step 90710: {'lr': 0.00017320517350468895, 'samples': 17416320, 'steps': 90709, 'loss/train': 1.5034180879592896} 08/31/2021 05:42:14 - INFO - __main__ - Step 90711: {'lr': 0.00017320012334994564, 'samples': 17416512, 'steps': 90710, 'loss/train': 1.6181269884109497} 08/31/2021 05:42:16 - INFO - __main__ - Step 90712: {'lr': 0.00017319507322980716, 'samples': 17416704, 'steps': 90711, 'loss/train': 1.2207051515579224} 08/31/2021 05:42:16 - INFO - __main__ - Step 90713: {'lr': 0.0001731900231442758, 'samples': 17416896, 'steps': 90712, 'loss/train': 1.4578956365585327} 08/31/2021 05:42:16 - INFO - __main__ - Step 90714: {'lr': 0.00017318497309335386, 'samples': 17417088, 'steps': 90713, 'loss/train': 0.596380352973938} 08/31/2021 05:42:17 - INFO - __main__ - Step 90715: {'lr': 0.00017317992307704352, 'samples': 17417280, 'steps': 90714, 'loss/train': 1.243363618850708} 08/31/2021 05:42:17 - INFO - __main__ - Step 90716: {'lr': 0.0001731748730953472, 'samples': 17417472, 'steps': 90715, 'loss/train': 1.4093670845031738} 08/31/2021 05:42:19 - INFO - __main__ - Step 90717: {'lr': 0.0001731698231482671, 'samples': 17417664, 'steps': 90716, 'loss/train': 1.404779076576233} 08/31/2021 05:42:19 - INFO - __main__ - Step 90718: {'lr': 0.00017316477323580547, 'samples': 17417856, 'steps': 90717, 'loss/train': 0.8559150099754333} 08/31/2021 05:42:19 - INFO - __main__ - Step 90719: {'lr': 0.0001731597233579646, 'samples': 17418048, 'steps': 90718, 'loss/train': 1.349069356918335} 08/31/2021 05:42:20 - INFO - __main__ - Step 90720: {'lr': 0.00017315467351474673, 'samples': 17418240, 'steps': 90719, 'loss/train': 0.9712318778038025} 08/31/2021 05:42:20 - INFO - __main__ - Step 90721: {'lr': 0.00017314962370615423, 'samples': 17418432, 'steps': 90720, 'loss/train': 1.8196192979812622} 08/31/2021 05:42:22 - INFO - __main__ - Step 90722: {'lr': 0.00017314457393218928, 'samples': 17418624, 'steps': 90721, 'loss/train': 0.7928387522697449} 08/31/2021 05:42:22 - INFO - __main__ - Step 90723: {'lr': 0.0001731395241928542, 'samples': 17418816, 'steps': 90722, 'loss/train': 0.8377772569656372} 08/31/2021 05:42:22 - INFO - __main__ - Step 90724: {'lr': 0.00017313447448815127, 'samples': 17419008, 'steps': 90723, 'loss/train': 1.2717243432998657} 08/31/2021 05:42:23 - INFO - __main__ - Step 90725: {'lr': 0.0001731294248180828, 'samples': 17419200, 'steps': 90724, 'loss/train': 1.5185437202453613} 08/31/2021 05:42:23 - INFO - __main__ - Step 90726: {'lr': 0.000173124375182651, 'samples': 17419392, 'steps': 90725, 'loss/train': 0.21028713881969452} 08/31/2021 05:42:23 - INFO - __main__ - Step 90727: {'lr': 0.00017311932558185817, 'samples': 17419584, 'steps': 90726, 'loss/train': 1.023869276046753} 08/31/2021 05:42:26 - INFO - __main__ - Step 90728: {'lr': 0.00017311427601570656, 'samples': 17419776, 'steps': 90727, 'loss/train': 0.8646367192268372} 08/31/2021 05:42:26 - INFO - __main__ - Step 90729: {'lr': 0.0001731092264841985, 'samples': 17419968, 'steps': 90728, 'loss/train': 1.3816661834716797} 08/31/2021 05:42:27 - INFO - __main__ - Step 90730: {'lr': 0.00017310417698733631, 'samples': 17420160, 'steps': 90729, 'loss/train': 1.0112003087997437} 08/31/2021 05:42:27 - INFO - __main__ - Step 90731: {'lr': 0.00017309912752512213, 'samples': 17420352, 'steps': 90730, 'loss/train': 0.6693297028541565} 08/31/2021 05:42:27 - INFO - __main__ - Step 90732: {'lr': 0.00017309407809755828, 'samples': 17420544, 'steps': 90731, 'loss/train': 0.9481481313705444} 08/31/2021 05:42:29 - INFO - __main__ - Step 90733: {'lr': 0.00017308902870464705, 'samples': 17420736, 'steps': 90732, 'loss/train': 0.060035742819309235} 08/31/2021 05:42:30 - INFO - __main__ - Step 90734: {'lr': 0.0001730839793463907, 'samples': 17420928, 'steps': 90733, 'loss/train': 0.2218261957168579} 08/31/2021 05:42:30 - INFO - __main__ - Step 90735: {'lr': 0.00017307893002279154, 'samples': 17421120, 'steps': 90734, 'loss/train': 1.5330415964126587} 08/31/2021 05:42:31 - INFO - __main__ - Step 90736: {'lr': 0.00017307388073385183, 'samples': 17421312, 'steps': 90735, 'loss/train': 1.2726191282272339} 08/31/2021 05:42:31 - INFO - __main__ - Step 90737: {'lr': 0.00017306883147957382, 'samples': 17421504, 'steps': 90736, 'loss/train': 1.6296266317367554} 08/31/2021 05:42:31 - INFO - __main__ - Step 90738: {'lr': 0.00017306378225995984, 'samples': 17421696, 'steps': 90737, 'loss/train': 0.9076969623565674} 08/31/2021 05:42:33 - INFO - __main__ - Step 90739: {'lr': 0.00017305873307501212, 'samples': 17421888, 'steps': 90738, 'loss/train': 0.10228787362575531} 08/31/2021 05:42:34 - INFO - __main__ - Step 90740: {'lr': 0.00017305368392473293, 'samples': 17422080, 'steps': 90739, 'loss/train': 0.5061398148536682} 08/31/2021 05:42:34 - INFO - __main__ - Step 90741: {'lr': 0.0001730486348091246, 'samples': 17422272, 'steps': 90740, 'loss/train': 0.018712645396590233} 08/31/2021 05:42:34 - INFO - __main__ - Step 90742: {'lr': 0.00017304358572818934, 'samples': 17422464, 'steps': 90741, 'loss/train': 1.119669795036316} 08/31/2021 05:42:35 - INFO - __main__ - Step 90743: {'lr': 0.00017303853668192943, 'samples': 17422656, 'steps': 90742, 'loss/train': 0.6274909377098083} 08/31/2021 05:42:35 - INFO - __main__ - Step 90744: {'lr': 0.0001730334876703473, 'samples': 17422848, 'steps': 90743, 'loss/train': 1.3694980144500732} 08/31/2021 05:42:37 - INFO - __main__ - Step 90745: {'lr': 0.000173028438693445, 'samples': 17423040, 'steps': 90744, 'loss/train': 0.4949724078178406} 08/31/2021 05:42:37 - INFO - __main__ - Step 90746: {'lr': 0.00017302338975122488, 'samples': 17423232, 'steps': 90745, 'loss/train': 0.8891132473945618} 08/31/2021 05:42:37 - INFO - __main__ - Step 90747: {'lr': 0.00017301834084368923, 'samples': 17423424, 'steps': 90746, 'loss/train': 3.4925973415374756} 08/31/2021 05:42:38 - INFO - __main__ - Step 90748: {'lr': 0.00017301329197084037, 'samples': 17423616, 'steps': 90747, 'loss/train': 0.8765302300453186} 08/31/2021 05:42:38 - INFO - __main__ - Step 90749: {'lr': 0.0001730082431326805, 'samples': 17423808, 'steps': 90748, 'loss/train': 1.4941526651382446} 08/31/2021 05:42:39 - INFO - __main__ - Step 90750: {'lr': 0.0001730031943292119, 'samples': 17424000, 'steps': 90749, 'loss/train': 1.704667329788208} 08/31/2021 05:42:40 - INFO - __main__ - Step 90751: {'lr': 0.0001729981455604369, 'samples': 17424192, 'steps': 90750, 'loss/train': 0.897257387638092} 08/31/2021 05:42:40 - INFO - __main__ - Step 90752: {'lr': 0.00017299309682635775, 'samples': 17424384, 'steps': 90751, 'loss/train': 0.6421748995780945} 08/31/2021 05:42:41 - INFO - __main__ - Step 90753: {'lr': 0.00017298804812697672, 'samples': 17424576, 'steps': 90752, 'loss/train': 1.0368815660476685} 08/31/2021 05:42:41 - INFO - __main__ - Step 90754: {'lr': 0.00017298299946229607, 'samples': 17424768, 'steps': 90753, 'loss/train': 0.9037743806838989} 08/31/2021 05:42:42 - INFO - __main__ - Step 90755: {'lr': 0.0001729779508323181, 'samples': 17424960, 'steps': 90754, 'loss/train': 1.7958688735961914} 08/31/2021 05:42:43 - INFO - __main__ - Step 90756: {'lr': 0.00017297290223704508, 'samples': 17425152, 'steps': 90755, 'loss/train': 0.8247308135032654} 08/31/2021 05:42:43 - INFO - __main__ - Step 90757: {'lr': 0.0001729678536764794, 'samples': 17425344, 'steps': 90756, 'loss/train': 1.255821943283081} 08/31/2021 05:42:44 - INFO - __main__ - Step 90758: {'lr': 0.00017296280515062312, 'samples': 17425536, 'steps': 90757, 'loss/train': 1.258691430091858} 08/31/2021 05:42:44 - INFO - __main__ - Step 90759: {'lr': 0.0001729577566594786, 'samples': 17425728, 'steps': 90758, 'loss/train': 1.207643747329712} 08/31/2021 05:42:44 - INFO - __main__ - Step 90760: {'lr': 0.0001729527082030481, 'samples': 17425920, 'steps': 90759, 'loss/train': 0.24432997405529022} 08/31/2021 05:42:46 - INFO - __main__ - Step 90761: {'lr': 0.00017294765978133396, 'samples': 17426112, 'steps': 90760, 'loss/train': 1.5618910789489746} 08/31/2021 05:42:47 - INFO - __main__ - Step 90762: {'lr': 0.00017294261139433838, 'samples': 17426304, 'steps': 90761, 'loss/train': 0.5202217698097229} 08/31/2021 05:42:47 - INFO - __main__ - Step 90763: {'lr': 0.0001729375630420637, 'samples': 17426496, 'steps': 90762, 'loss/train': 1.3012477159500122} 08/31/2021 05:42:47 - INFO - __main__ - Step 90764: {'lr': 0.00017293251472451216, 'samples': 17426688, 'steps': 90763, 'loss/train': 1.453386902809143} 08/31/2021 05:42:48 - INFO - __main__ - Step 90765: {'lr': 0.000172927466441686, 'samples': 17426880, 'steps': 90764, 'loss/train': 0.018915321677923203} 08/31/2021 05:42:48 - INFO - __main__ - Step 90766: {'lr': 0.00017292241819358756, 'samples': 17427072, 'steps': 90765, 'loss/train': 0.9995896816253662} 08/31/2021 05:42:50 - INFO - __main__ - Step 90767: {'lr': 0.00017291736998021912, 'samples': 17427264, 'steps': 90766, 'loss/train': 0.12131483107805252} 08/31/2021 05:42:50 - INFO - __main__ - Step 90768: {'lr': 0.00017291232180158289, 'samples': 17427456, 'steps': 90767, 'loss/train': 0.7162519693374634} 08/31/2021 05:42:50 - INFO - __main__ - Step 90769: {'lr': 0.00017290727365768115, 'samples': 17427648, 'steps': 90768, 'loss/train': 1.1644635200500488} 08/31/2021 05:42:51 - INFO - __main__ - Step 90770: {'lr': 0.00017290222554851626, 'samples': 17427840, 'steps': 90769, 'loss/train': 1.6479665040969849} 08/31/2021 05:42:51 - INFO - __main__ - Step 90771: {'lr': 0.00017289717747409053, 'samples': 17428032, 'steps': 90770, 'loss/train': 1.3754678964614868} 08/31/2021 05:42:53 - INFO - __main__ - Step 90772: {'lr': 0.00017289212943440602, 'samples': 17428224, 'steps': 90771, 'loss/train': 1.270966649055481} 08/31/2021 05:42:53 - INFO - __main__ - Step 90773: {'lr': 0.00017288708142946513, 'samples': 17428416, 'steps': 90772, 'loss/train': 0.5961886048316956} 08/31/2021 05:42:54 - INFO - __main__ - Step 90774: {'lr': 0.00017288203345927015, 'samples': 17428608, 'steps': 90773, 'loss/train': 1.2036714553833008} 08/31/2021 05:42:54 - INFO - __main__ - Step 90775: {'lr': 0.0001728769855238233, 'samples': 17428800, 'steps': 90774, 'loss/train': 1.3097951412200928} 08/31/2021 05:42:54 - INFO - __main__ - Step 90776: {'lr': 0.0001728719376231269, 'samples': 17428992, 'steps': 90775, 'loss/train': 0.027103137224912643} 08/31/2021 05:42:57 - INFO - __main__ - Step 90777: {'lr': 0.00017286688975718325, 'samples': 17429184, 'steps': 90776, 'loss/train': 1.5664788484573364} 08/31/2021 05:42:57 - INFO - __main__ - Step 90778: {'lr': 0.0001728618419259946, 'samples': 17429376, 'steps': 90777, 'loss/train': 1.0183839797973633} 08/31/2021 05:42:58 - INFO - __main__ - Step 90779: {'lr': 0.00017285679412956315, 'samples': 17429568, 'steps': 90778, 'loss/train': 0.6557900309562683} 08/31/2021 05:42:58 - INFO - __main__ - Step 90780: {'lr': 0.00017285174636789125, 'samples': 17429760, 'steps': 90779, 'loss/train': 0.358715295791626} 08/31/2021 05:42:58 - INFO - __main__ - Step 90781: {'lr': 0.00017284669864098119, 'samples': 17429952, 'steps': 90780, 'loss/train': 0.6263635158538818} 08/31/2021 05:42:59 - INFO - __main__ - Step 90782: {'lr': 0.00017284165094883522, 'samples': 17430144, 'steps': 90781, 'loss/train': 0.8275656700134277} 08/31/2021 05:42:59 - INFO - __main__ - Step 90783: {'lr': 0.00017283660329145558, 'samples': 17430336, 'steps': 90782, 'loss/train': 1.0923722982406616} 08/31/2021 05:43:00 - INFO - __main__ - Step 90784: {'lr': 0.00017283155566884473, 'samples': 17430528, 'steps': 90783, 'loss/train': 1.7695754766464233} 08/31/2021 05:43:01 - INFO - __main__ - Step 90785: {'lr': 0.00017282650808100465, 'samples': 17430720, 'steps': 90784, 'loss/train': 0.5074482560157776} 08/31/2021 05:43:01 - INFO - __main__ - Step 90786: {'lr': 0.00017282146052793773, 'samples': 17430912, 'steps': 90785, 'loss/train': 0.8937087059020996} 08/31/2021 05:43:02 - INFO - __main__ - Step 90787: {'lr': 0.00017281641300964632, 'samples': 17431104, 'steps': 90786, 'loss/train': 1.0101627111434937} 08/31/2021 05:43:02 - INFO - __main__ - Step 90788: {'lr': 0.00017281136552613265, 'samples': 17431296, 'steps': 90787, 'loss/train': 1.2799830436706543} 08/31/2021 05:43:04 - INFO - __main__ - Step 90789: {'lr': 0.00017280631807739893, 'samples': 17431488, 'steps': 90788, 'loss/train': 1.5340198278427124} 08/31/2021 05:43:05 - INFO - __main__ - Step 90790: {'lr': 0.00017280127066344753, 'samples': 17431680, 'steps': 90789, 'loss/train': 1.7780969142913818} 08/31/2021 05:43:05 - INFO - __main__ - Step 90791: {'lr': 0.00017279622328428068, 'samples': 17431872, 'steps': 90790, 'loss/train': 1.000496506690979} 08/31/2021 05:43:05 - INFO - __main__ - Step 90792: {'lr': 0.00017279117593990063, 'samples': 17432064, 'steps': 90791, 'loss/train': 0.34320321679115295} 08/31/2021 05:43:06 - INFO - __main__ - Step 90793: {'lr': 0.00017278612863030974, 'samples': 17432256, 'steps': 90792, 'loss/train': 1.0684870481491089} 08/31/2021 05:43:07 - INFO - __main__ - Step 90794: {'lr': 0.0001727810813555102, 'samples': 17432448, 'steps': 90793, 'loss/train': 1.3616694211959839} 08/31/2021 05:43:07 - INFO - __main__ - Step 90795: {'lr': 0.00017277603411550437, 'samples': 17432640, 'steps': 90794, 'loss/train': 0.6839326620101929} 08/31/2021 05:43:08 - INFO - __main__ - Step 90796: {'lr': 0.00017277098691029441, 'samples': 17432832, 'steps': 90795, 'loss/train': 1.1915158033370972} 08/31/2021 05:43:08 - INFO - __main__ - Step 90797: {'lr': 0.0001727659397398827, 'samples': 17433024, 'steps': 90796, 'loss/train': 1.3291857242584229} 08/31/2021 05:43:09 - INFO - __main__ - Step 90798: {'lr': 0.0001727608926042714, 'samples': 17433216, 'steps': 90797, 'loss/train': 1.1286953687667847} 08/31/2021 05:43:09 - INFO - __main__ - Step 90799: {'lr': 0.00017275584550346287, 'samples': 17433408, 'steps': 90798, 'loss/train': 1.9062082767486572} 08/31/2021 05:43:10 - INFO - __main__ - Step 90800: {'lr': 0.0001727507984374594, 'samples': 17433600, 'steps': 90799, 'loss/train': 1.4065805673599243} 08/31/2021 05:43:11 - INFO - __main__ - Step 90801: {'lr': 0.00017274575140626317, 'samples': 17433792, 'steps': 90800, 'loss/train': 1.3438541889190674} 08/31/2021 05:43:11 - INFO - __main__ - Step 90802: {'lr': 0.00017274070440987654, 'samples': 17433984, 'steps': 90801, 'loss/train': 0.5867409110069275} 08/31/2021 05:43:12 - INFO - __main__ - Step 90803: {'lr': 0.00017273565744830172, 'samples': 17434176, 'steps': 90802, 'loss/train': 1.0062737464904785} 08/31/2021 05:43:12 - INFO - __main__ - Step 90804: {'lr': 0.00017273061052154107, 'samples': 17434368, 'steps': 90803, 'loss/train': 0.8952381610870361} 08/31/2021 05:43:13 - INFO - __main__ - Step 90805: {'lr': 0.00017272556362959678, 'samples': 17434560, 'steps': 90804, 'loss/train': 1.443341612815857} 08/31/2021 05:43:14 - INFO - __main__ - Step 90806: {'lr': 0.00017272051677247124, 'samples': 17434752, 'steps': 90805, 'loss/train': 0.8501542210578918} 08/31/2021 05:43:14 - INFO - __main__ - Step 90807: {'lr': 0.00017271546995016658, 'samples': 17434944, 'steps': 90806, 'loss/train': 0.9403319954872131} 08/31/2021 05:43:14 - INFO - __main__ - Step 90808: {'lr': 0.00017271042316268514, 'samples': 17435136, 'steps': 90807, 'loss/train': 0.8049054741859436} 08/31/2021 05:43:15 - INFO - __main__ - Step 90809: {'lr': 0.00017270537641002917, 'samples': 17435328, 'steps': 90808, 'loss/train': 0.8397760391235352} 08/31/2021 05:43:16 - INFO - __main__ - Step 90810: {'lr': 0.00017270032969220097, 'samples': 17435520, 'steps': 90809, 'loss/train': 1.1214832067489624} 08/31/2021 05:43:17 - INFO - __main__ - Step 90811: {'lr': 0.0001726952830092029, 'samples': 17435712, 'steps': 90810, 'loss/train': 1.181719183921814} 08/31/2021 05:43:17 - INFO - __main__ - Step 90812: {'lr': 0.00017269023636103703, 'samples': 17435904, 'steps': 90811, 'loss/train': 1.2731424570083618} 08/31/2021 05:43:18 - INFO - __main__ - Step 90813: {'lr': 0.0001726851897477058, 'samples': 17436096, 'steps': 90812, 'loss/train': 0.3942873477935791} 08/31/2021 05:43:18 - INFO - __main__ - Step 90814: {'lr': 0.00017268014316921138, 'samples': 17436288, 'steps': 90813, 'loss/train': 1.191461205482483} 08/31/2021 05:43:20 - INFO - __main__ - Step 90815: {'lr': 0.00017267509662555614, 'samples': 17436480, 'steps': 90814, 'loss/train': 0.9988872408866882} 08/31/2021 05:43:20 - INFO - __main__ - Step 90816: {'lr': 0.0001726700501167423, 'samples': 17436672, 'steps': 90815, 'loss/train': 1.0924065113067627} 08/31/2021 05:43:20 - INFO - __main__ - Step 90817: {'lr': 0.00017266500364277216, 'samples': 17436864, 'steps': 90816, 'loss/train': 0.5209054946899414} 08/31/2021 05:43:21 - INFO - __main__ - Step 90818: {'lr': 0.00017265995720364797, 'samples': 17437056, 'steps': 90817, 'loss/train': 1.5167654752731323} 08/31/2021 05:43:21 - INFO - __main__ - Step 90819: {'lr': 0.00017265491079937196, 'samples': 17437248, 'steps': 90818, 'loss/train': 1.2231343984603882} 08/31/2021 05:43:23 - INFO - __main__ - Step 90820: {'lr': 0.00017264986442994652, 'samples': 17437440, 'steps': 90819, 'loss/train': 0.6529433727264404} 08/31/2021 05:43:23 - INFO - __main__ - Step 90821: {'lr': 0.0001726448180953738, 'samples': 17437632, 'steps': 90820, 'loss/train': 1.0842293500900269} 08/31/2021 05:43:23 - INFO - __main__ - Step 90822: {'lr': 0.00017263977179565615, 'samples': 17437824, 'steps': 90821, 'loss/train': 1.4457882642745972} 08/31/2021 05:43:24 - INFO - __main__ - Step 90823: {'lr': 0.00017263472553079583, 'samples': 17438016, 'steps': 90822, 'loss/train': 1.4988874197006226} 08/31/2021 05:43:24 - INFO - __main__ - Step 90824: {'lr': 0.00017262967930079516, 'samples': 17438208, 'steps': 90823, 'loss/train': 0.41762569546699524} 08/31/2021 05:43:26 - INFO - __main__ - Step 90825: {'lr': 0.0001726246331056563, 'samples': 17438400, 'steps': 90824, 'loss/train': 1.4461337327957153} 08/31/2021 05:43:26 - INFO - __main__ - Step 90826: {'lr': 0.0001726195869453816, 'samples': 17438592, 'steps': 90825, 'loss/train': 1.3335206508636475} 08/31/2021 05:43:27 - INFO - __main__ - Step 90827: {'lr': 0.0001726145408199733, 'samples': 17438784, 'steps': 90826, 'loss/train': 0.506770133972168} 08/31/2021 05:43:27 - INFO - __main__ - Step 90828: {'lr': 0.00017260949472943377, 'samples': 17438976, 'steps': 90827, 'loss/train': 0.832069456577301} 08/31/2021 05:43:27 - INFO - __main__ - Step 90829: {'lr': 0.00017260444867376514, 'samples': 17439168, 'steps': 90828, 'loss/train': 1.182030439376831} 08/31/2021 05:43:29 - INFO - __main__ - Step 90830: {'lr': 0.00017259940265296976, 'samples': 17439360, 'steps': 90829, 'loss/train': 0.8687127232551575} 08/31/2021 05:43:29 - INFO - __main__ - Step 90831: {'lr': 0.00017259435666704988, 'samples': 17439552, 'steps': 90830, 'loss/train': 1.6036195755004883} 08/31/2021 05:43:30 - INFO - __main__ - Step 90832: {'lr': 0.0001725893107160078, 'samples': 17439744, 'steps': 90831, 'loss/train': 1.4013867378234863} 08/31/2021 05:43:30 - INFO - __main__ - Step 90833: {'lr': 0.0001725842647998458, 'samples': 17439936, 'steps': 90832, 'loss/train': 1.0902107954025269} 08/31/2021 05:43:30 - INFO - __main__ - Step 90834: {'lr': 0.0001725792189185661, 'samples': 17440128, 'steps': 90833, 'loss/train': 1.0649957656860352} 08/31/2021 05:43:31 - INFO - __main__ - Step 90835: {'lr': 0.00017257417307217103, 'samples': 17440320, 'steps': 90834, 'loss/train': 1.2122828960418701} 08/31/2021 05:43:32 - INFO - __main__ - Step 90836: {'lr': 0.00017256912726066283, 'samples': 17440512, 'steps': 90835, 'loss/train': 0.9702490568161011} 08/31/2021 05:43:33 - INFO - __main__ - Step 90837: {'lr': 0.0001725640814840438, 'samples': 17440704, 'steps': 90836, 'loss/train': 1.386277437210083} 08/31/2021 05:43:33 - INFO - __main__ - Step 90838: {'lr': 0.00017255903574231625, 'samples': 17440896, 'steps': 90837, 'loss/train': 1.5129621028900146} 08/31/2021 05:43:33 - INFO - __main__ - Step 90839: {'lr': 0.0001725539900354824, 'samples': 17441088, 'steps': 90838, 'loss/train': 1.7424256801605225} 08/31/2021 05:43:34 - INFO - __main__ - Step 90840: {'lr': 0.00017254894436354447, 'samples': 17441280, 'steps': 90839, 'loss/train': 1.2074790000915527} 08/31/2021 05:43:36 - INFO - __main__ - Step 90841: {'lr': 0.00017254389872650477, 'samples': 17441472, 'steps': 90840, 'loss/train': 1.1835417747497559} 08/31/2021 05:43:36 - INFO - __main__ - Step 90842: {'lr': 0.00017253885312436563, 'samples': 17441664, 'steps': 90841, 'loss/train': 1.0619999170303345} 08/31/2021 05:43:36 - INFO - __main__ - Step 90843: {'lr': 0.00017253380755712926, 'samples': 17441856, 'steps': 90842, 'loss/train': 0.945121169090271} 08/31/2021 05:43:37 - INFO - __main__ - Step 90844: {'lr': 0.000172528762024798, 'samples': 17442048, 'steps': 90843, 'loss/train': 1.252211332321167} 08/31/2021 05:43:37 - INFO - __main__ - Step 90845: {'lr': 0.00017252371652737408, 'samples': 17442240, 'steps': 90844, 'loss/train': 1.2632914781570435} 08/31/2021 05:43:39 - INFO - __main__ - Step 90846: {'lr': 0.00017251867106485974, 'samples': 17442432, 'steps': 90845, 'loss/train': 1.45930016040802} 08/31/2021 05:43:39 - INFO - __main__ - Step 90847: {'lr': 0.0001725136256372573, 'samples': 17442624, 'steps': 90846, 'loss/train': 1.1800869703292847} 08/31/2021 05:43:40 - INFO - __main__ - Step 90848: {'lr': 0.00017250858024456906, 'samples': 17442816, 'steps': 90847, 'loss/train': 0.29690760374069214} 08/31/2021 05:43:40 - INFO - __main__ - Step 90849: {'lr': 0.00017250353488679725, 'samples': 17443008, 'steps': 90848, 'loss/train': 0.8973831534385681} 08/31/2021 05:43:40 - INFO - __main__ - Step 90850: {'lr': 0.0001724984895639441, 'samples': 17443200, 'steps': 90849, 'loss/train': 0.9960607290267944} 08/31/2021 05:43:42 - INFO - __main__ - Step 90851: {'lr': 0.0001724934442760121, 'samples': 17443392, 'steps': 90850, 'loss/train': 0.7505674362182617} 08/31/2021 05:43:42 - INFO - __main__ - Step 90852: {'lr': 0.00017248839902300322, 'samples': 17443584, 'steps': 90851, 'loss/train': 1.1885747909545898} 08/31/2021 05:43:43 - INFO - __main__ - Step 90853: {'lr': 0.00017248335380491987, 'samples': 17443776, 'steps': 90852, 'loss/train': 1.3146984577178955} 08/31/2021 05:43:43 - INFO - __main__ - Step 90854: {'lr': 0.00017247830862176435, 'samples': 17443968, 'steps': 90853, 'loss/train': 1.207932949066162} 08/31/2021 05:43:43 - INFO - __main__ - Step 90855: {'lr': 0.00017247326347353886, 'samples': 17444160, 'steps': 90854, 'loss/train': 1.0172642469406128} 08/31/2021 05:43:44 - INFO - __main__ - Step 90856: {'lr': 0.0001724682183602458, 'samples': 17444352, 'steps': 90855, 'loss/train': 1.7592225074768066} 08/31/2021 05:43:45 - INFO - __main__ - Step 90857: {'lr': 0.0001724631732818873, 'samples': 17444544, 'steps': 90856, 'loss/train': 1.1826192140579224} 08/31/2021 05:43:46 - INFO - __main__ - Step 90858: {'lr': 0.0001724581282384657, 'samples': 17444736, 'steps': 90857, 'loss/train': 0.548163890838623} 08/31/2021 05:43:46 - INFO - __main__ - Step 90859: {'lr': 0.0001724530832299833, 'samples': 17444928, 'steps': 90858, 'loss/train': 1.3048571348190308} 08/31/2021 05:43:47 - INFO - __main__ - Step 90860: {'lr': 0.00017244803825644235, 'samples': 17445120, 'steps': 90859, 'loss/train': 1.411014437675476} 08/31/2021 05:43:47 - INFO - __main__ - Step 90861: {'lr': 0.00017244299331784508, 'samples': 17445312, 'steps': 90860, 'loss/train': 1.3167158365249634} 08/31/2021 05:43:48 - INFO - __main__ - Step 90862: {'lr': 0.0001724379484141938, 'samples': 17445504, 'steps': 90861, 'loss/train': 1.0946779251098633} 08/31/2021 05:43:49 - INFO - __main__ - Step 90863: {'lr': 0.00017243290354549082, 'samples': 17445696, 'steps': 90862, 'loss/train': 1.1985801458358765} 08/31/2021 05:43:49 - INFO - __main__ - Step 90864: {'lr': 0.00017242785871173836, 'samples': 17445888, 'steps': 90863, 'loss/train': 1.3338857889175415} 08/31/2021 05:43:50 - INFO - __main__ - Step 90865: {'lr': 0.0001724228139129388, 'samples': 17446080, 'steps': 90864, 'loss/train': 0.9763408899307251} 08/31/2021 05:43:50 - INFO - __main__ - Step 90866: {'lr': 0.00017241776914909423, 'samples': 17446272, 'steps': 90865, 'loss/train': 1.3009237051010132} 08/31/2021 05:43:51 - INFO - __main__ - Step 90867: {'lr': 0.00017241272442020702, 'samples': 17446464, 'steps': 90866, 'loss/train': 1.148541808128357} 08/31/2021 05:43:52 - INFO - __main__ - Step 90868: {'lr': 0.00017240767972627943, 'samples': 17446656, 'steps': 90867, 'loss/train': 0.4553602635860443} 08/31/2021 05:43:52 - INFO - __main__ - Step 90869: {'lr': 0.00017240263506731375, 'samples': 17446848, 'steps': 90868, 'loss/train': 1.089103102684021} 08/31/2021 05:43:53 - INFO - __main__ - Step 90870: {'lr': 0.00017239759044331227, 'samples': 17447040, 'steps': 90869, 'loss/train': 1.4207990169525146} 08/31/2021 05:43:53 - INFO - __main__ - Step 90871: {'lr': 0.00017239254585427722, 'samples': 17447232, 'steps': 90870, 'loss/train': 0.9203070402145386} 08/31/2021 05:43:54 - INFO - __main__ - Step 90872: {'lr': 0.00017238750130021087, 'samples': 17447424, 'steps': 90871, 'loss/train': 0.8113464117050171} 08/31/2021 05:43:55 - INFO - __main__ - Step 90873: {'lr': 0.0001723824567811155, 'samples': 17447616, 'steps': 90872, 'loss/train': 1.235695719718933} 08/31/2021 05:43:55 - INFO - __main__ - Step 90874: {'lr': 0.00017237741229699343, 'samples': 17447808, 'steps': 90873, 'loss/train': 2.3284616470336914} 08/31/2021 05:43:56 - INFO - __main__ - Step 90875: {'lr': 0.00017237236784784692, 'samples': 17448000, 'steps': 90874, 'loss/train': 2.0222134590148926} 08/31/2021 05:43:56 - INFO - __main__ - Step 90876: {'lr': 0.00017236732343367818, 'samples': 17448192, 'steps': 90875, 'loss/train': 0.5167170166969299} 08/31/2021 05:43:56 - INFO - __main__ - Step 90877: {'lr': 0.00017236227905448955, 'samples': 17448384, 'steps': 90876, 'loss/train': 0.9592614769935608} 08/31/2021 05:43:58 - INFO - __main__ - Step 90878: {'lr': 0.00017235723471028337, 'samples': 17448576, 'steps': 90877, 'loss/train': 0.6264645457267761} 08/31/2021 05:43:58 - INFO - __main__ - Step 90879: {'lr': 0.00017235219040106174, 'samples': 17448768, 'steps': 90878, 'loss/train': 0.5584279894828796} 08/31/2021 05:43:59 - INFO - __main__ - Step 90880: {'lr': 0.000172347146126827, 'samples': 17448960, 'steps': 90879, 'loss/train': 2.2039225101470947} 08/31/2021 05:43:59 - INFO - __main__ - Step 90881: {'lr': 0.00017234210188758143, 'samples': 17449152, 'steps': 90880, 'loss/train': 0.6276072859764099} 08/31/2021 05:43:59 - INFO - __main__ - Step 90882: {'lr': 0.0001723370576833273, 'samples': 17449344, 'steps': 90881, 'loss/train': 1.5287058353424072} 08/31/2021 05:44:01 - INFO - __main__ - Step 90883: {'lr': 0.00017233201351406693, 'samples': 17449536, 'steps': 90882, 'loss/train': 1.1617993116378784} 08/31/2021 05:44:01 - INFO - __main__ - Step 90884: {'lr': 0.00017232696937980252, 'samples': 17449728, 'steps': 90883, 'loss/train': 1.1862863302230835} 08/31/2021 05:44:02 - INFO - __main__ - Step 90885: {'lr': 0.00017232192528053643, 'samples': 17449920, 'steps': 90884, 'loss/train': 0.8073505163192749} 08/31/2021 05:44:02 - INFO - __main__ - Step 90886: {'lr': 0.00017231688121627082, 'samples': 17450112, 'steps': 90885, 'loss/train': 1.397275686264038} 08/31/2021 05:44:02 - INFO - __main__ - Step 90887: {'lr': 0.00017231183718700808, 'samples': 17450304, 'steps': 90886, 'loss/train': 1.6494957208633423} 08/31/2021 05:44:04 - INFO - __main__ - Step 90888: {'lr': 0.00017230679319275039, 'samples': 17450496, 'steps': 90887, 'loss/train': 1.1849972009658813} 08/31/2021 05:44:04 - INFO - __main__ - Step 90889: {'lr': 0.00017230174923350006, 'samples': 17450688, 'steps': 90888, 'loss/train': 1.1807982921600342} 08/31/2021 05:44:05 - INFO - __main__ - Step 90890: {'lr': 0.0001722967053092594, 'samples': 17450880, 'steps': 90889, 'loss/train': 0.6305946111679077} 08/31/2021 05:44:05 - INFO - __main__ - Step 90891: {'lr': 0.0001722916614200306, 'samples': 17451072, 'steps': 90890, 'loss/train': 0.6372113823890686} 08/31/2021 05:44:05 - INFO - __main__ - Step 90892: {'lr': 0.0001722866175658161, 'samples': 17451264, 'steps': 90891, 'loss/train': 0.880398690700531} 08/31/2021 05:44:07 - INFO - __main__ - Step 90893: {'lr': 0.00017228157374661796, 'samples': 17451456, 'steps': 90892, 'loss/train': 1.5814995765686035} 08/31/2021 05:44:07 - INFO - __main__ - Step 90894: {'lr': 0.00017227652996243853, 'samples': 17451648, 'steps': 90893, 'loss/train': 1.2864940166473389} 08/31/2021 05:44:08 - INFO - __main__ - Step 90895: {'lr': 0.0001722714862132801, 'samples': 17451840, 'steps': 90894, 'loss/train': 1.3498029708862305} 08/31/2021 05:44:08 - INFO - __main__ - Step 90896: {'lr': 0.0001722664424991449, 'samples': 17452032, 'steps': 90895, 'loss/train': 1.3348156213760376} 08/31/2021 05:44:08 - INFO - __main__ - Step 90897: {'lr': 0.00017226139882003534, 'samples': 17452224, 'steps': 90896, 'loss/train': 0.8972432017326355} 08/31/2021 05:44:10 - INFO - __main__ - Step 90898: {'lr': 0.0001722563551759535, 'samples': 17452416, 'steps': 90897, 'loss/train': 1.4388415813446045} 08/31/2021 05:44:11 - INFO - __main__ - Step 90899: {'lr': 0.00017225131156690178, 'samples': 17452608, 'steps': 90898, 'loss/train': 0.7612341046333313} 08/31/2021 05:44:11 - INFO - __main__ - Step 90900: {'lr': 0.00017224626799288242, 'samples': 17452800, 'steps': 90899, 'loss/train': 1.2942256927490234} 08/31/2021 05:44:12 - INFO - __main__ - Step 90901: {'lr': 0.0001722412244538977, 'samples': 17452992, 'steps': 90900, 'loss/train': 1.3017889261245728} 08/31/2021 05:44:12 - INFO - __main__ - Step 90902: {'lr': 0.00017223618094994986, 'samples': 17453184, 'steps': 90901, 'loss/train': 2.431161642074585} 08/31/2021 05:44:13 - INFO - __main__ - Step 90903: {'lr': 0.0001722311374810412, 'samples': 17453376, 'steps': 90902, 'loss/train': 1.462094783782959} 08/31/2021 05:44:14 - INFO - __main__ - Step 90904: {'lr': 0.00017222609404717403, 'samples': 17453568, 'steps': 90903, 'loss/train': 1.4359099864959717} 08/31/2021 05:44:14 - INFO - __main__ - Step 90905: {'lr': 0.00017222105064835063, 'samples': 17453760, 'steps': 90904, 'loss/train': 0.28048059344291687} 08/31/2021 05:44:15 - INFO - __main__ - Step 90906: {'lr': 0.00017221600728457314, 'samples': 17453952, 'steps': 90905, 'loss/train': 1.530826210975647} 08/31/2021 05:44:15 - INFO - __main__ - Step 90907: {'lr': 0.00017221096395584395, 'samples': 17454144, 'steps': 90906, 'loss/train': 0.5747814774513245} 08/31/2021 05:44:15 - INFO - __main__ - Step 90908: {'lr': 0.00017220592066216527, 'samples': 17454336, 'steps': 90907, 'loss/train': 0.5117108225822449} 08/31/2021 05:44:17 - INFO - __main__ - Step 90909: {'lr': 0.0001722008774035394, 'samples': 17454528, 'steps': 90908, 'loss/train': 0.8385559916496277} 08/31/2021 05:44:17 - INFO - __main__ - Step 90910: {'lr': 0.00017219583417996866, 'samples': 17454720, 'steps': 90909, 'loss/train': 1.0067906379699707} 08/31/2021 05:44:18 - INFO - __main__ - Step 90911: {'lr': 0.0001721907909914552, 'samples': 17454912, 'steps': 90910, 'loss/train': 1.2638708353042603} 08/31/2021 05:44:18 - INFO - __main__ - Step 90912: {'lr': 0.0001721857478380014, 'samples': 17455104, 'steps': 90911, 'loss/train': 1.0717747211456299} 08/31/2021 05:44:18 - INFO - __main__ - Step 90913: {'lr': 0.0001721807047196095, 'samples': 17455296, 'steps': 90912, 'loss/train': 1.5089432001113892} 08/31/2021 05:44:20 - INFO - __main__ - Step 90914: {'lr': 0.00017217566163628178, 'samples': 17455488, 'steps': 90913, 'loss/train': 0.5965180993080139} 08/31/2021 05:44:20 - INFO - __main__ - Step 90915: {'lr': 0.00017217061858802051, 'samples': 17455680, 'steps': 90914, 'loss/train': 0.8419532775878906} 08/31/2021 05:44:21 - INFO - __main__ - Step 90916: {'lr': 0.00017216557557482798, 'samples': 17455872, 'steps': 90915, 'loss/train': 1.231751799583435} 08/31/2021 05:44:21 - INFO - __main__ - Step 90917: {'lr': 0.00017216053259670638, 'samples': 17456064, 'steps': 90916, 'loss/train': 0.8454513549804688} 08/31/2021 05:44:22 - INFO - __main__ - Step 90918: {'lr': 0.0001721554896536582, 'samples': 17456256, 'steps': 90917, 'loss/train': 1.527361273765564} 08/31/2021 05:44:23 - INFO - __main__ - Step 90919: {'lr': 0.00017215044674568543, 'samples': 17456448, 'steps': 90918, 'loss/train': 1.2875467538833618} 08/31/2021 05:44:24 - INFO - __main__ - Step 90920: {'lr': 0.00017214540387279048, 'samples': 17456640, 'steps': 90919, 'loss/train': 1.7486448287963867} 08/31/2021 05:44:24 - INFO - __main__ - Step 90921: {'lr': 0.0001721403610349756, 'samples': 17456832, 'steps': 90920, 'loss/train': 0.8587740063667297} 08/31/2021 05:44:24 - INFO - __main__ - Step 90922: {'lr': 0.00017213531823224307, 'samples': 17457024, 'steps': 90921, 'loss/train': 0.05530434101819992} 08/31/2021 05:44:25 - INFO - __main__ - Step 90923: {'lr': 0.00017213027546459517, 'samples': 17457216, 'steps': 90922, 'loss/train': 0.8274599313735962} 08/31/2021 05:44:26 - INFO - __main__ - Step 90924: {'lr': 0.0001721252327320342, 'samples': 17457408, 'steps': 90923, 'loss/train': 1.470104455947876} 08/31/2021 05:44:27 - INFO - __main__ - Step 90925: {'lr': 0.0001721201900345623, 'samples': 17457600, 'steps': 90924, 'loss/train': 1.35759437084198} 08/31/2021 05:44:27 - INFO - __main__ - Step 90926: {'lr': 0.00017211514737218192, 'samples': 17457792, 'steps': 90925, 'loss/train': 1.4972347021102905} 08/31/2021 05:44:27 - INFO - __main__ - Step 90927: {'lr': 0.00017211010474489524, 'samples': 17457984, 'steps': 90926, 'loss/train': 1.5670443773269653} 08/31/2021 05:44:28 - INFO - __main__ - Step 90928: {'lr': 0.00017210506215270454, 'samples': 17458176, 'steps': 90927, 'loss/train': 4.1567840576171875} 08/31/2021 05:44:30 - INFO - __main__ - Step 90929: {'lr': 0.0001721000195956121, 'samples': 17458368, 'steps': 90928, 'loss/train': 1.1850460767745972} 08/31/2021 05:44:30 - INFO - __main__ - Step 90930: {'lr': 0.0001720949770736202, 'samples': 17458560, 'steps': 90929, 'loss/train': 1.2774182558059692} 08/31/2021 05:44:30 - INFO - __main__ - Step 90931: {'lr': 0.0001720899345867311, 'samples': 17458752, 'steps': 90930, 'loss/train': 0.052851397544145584} 08/31/2021 05:44:31 - INFO - __main__ - Step 90932: {'lr': 0.00017208489213494714, 'samples': 17458944, 'steps': 90931, 'loss/train': 1.4482485055923462} 08/31/2021 05:44:31 - INFO - __main__ - Step 90933: {'lr': 0.0001720798497182704, 'samples': 17459136, 'steps': 90932, 'loss/train': 0.390391081571579} 08/31/2021 05:44:31 - INFO - __main__ - Step 90934: {'lr': 0.00017207480733670333, 'samples': 17459328, 'steps': 90933, 'loss/train': 0.054080523550510406} 08/31/2021 05:44:32 - INFO - __main__ - Step 90935: {'lr': 0.00017206976499024819, 'samples': 17459520, 'steps': 90934, 'loss/train': 0.02104560099542141} 08/31/2021 05:44:33 - INFO - __main__ - Step 90936: {'lr': 0.00017206472267890713, 'samples': 17459712, 'steps': 90935, 'loss/train': 1.592301368713379} 08/31/2021 05:44:34 - INFO - __main__ - Step 90937: {'lr': 0.00017205968040268256, 'samples': 17459904, 'steps': 90936, 'loss/train': 2.2414214611053467} 08/31/2021 05:44:34 - INFO - __main__ - Step 90938: {'lr': 0.00017205463816157666, 'samples': 17460096, 'steps': 90937, 'loss/train': 1.154259204864502} 08/31/2021 05:44:35 - INFO - __main__ - Step 90939: {'lr': 0.00017204959595559173, 'samples': 17460288, 'steps': 90938, 'loss/train': 3.4996955394744873} 08/31/2021 05:44:35 - INFO - __main__ - Step 90940: {'lr': 0.0001720445537847301, 'samples': 17460480, 'steps': 90939, 'loss/train': 0.1232762411236763} 08/31/2021 05:44:37 - INFO - __main__ - Step 90941: {'lr': 0.000172039511648994, 'samples': 17460672, 'steps': 90940, 'loss/train': 0.15703317523002625} 08/31/2021 05:44:37 - INFO - __main__ - Step 90942: {'lr': 0.00017203446954838563, 'samples': 17460864, 'steps': 90941, 'loss/train': 1.7747955322265625} 08/31/2021 05:44:38 - INFO - __main__ - Step 90943: {'lr': 0.00017202942748290734, 'samples': 17461056, 'steps': 90942, 'loss/train': 0.9442822933197021} 08/31/2021 05:44:38 - INFO - __main__ - Step 90944: {'lr': 0.00017202438545256142, 'samples': 17461248, 'steps': 90943, 'loss/train': 5.771514415740967} 08/31/2021 05:44:38 - INFO - __main__ - Step 90945: {'lr': 0.00017201934345735013, 'samples': 17461440, 'steps': 90944, 'loss/train': 1.4664201736450195} 08/31/2021 05:44:40 - INFO - __main__ - Step 90946: {'lr': 0.00017201430149727567, 'samples': 17461632, 'steps': 90945, 'loss/train': 1.536852240562439} 08/31/2021 05:44:40 - INFO - __main__ - Step 90947: {'lr': 0.00017200925957234036, 'samples': 17461824, 'steps': 90946, 'loss/train': 1.1647127866744995} 08/31/2021 05:44:41 - INFO - __main__ - Step 90948: {'lr': 0.00017200421768254648, 'samples': 17462016, 'steps': 90947, 'loss/train': 1.658612608909607} 08/31/2021 05:44:41 - INFO - __main__ - Step 90949: {'lr': 0.00017199917582789631, 'samples': 17462208, 'steps': 90948, 'loss/train': 1.1069127321243286} 08/31/2021 05:44:41 - INFO - __main__ - Step 90950: {'lr': 0.00017199413400839208, 'samples': 17462400, 'steps': 90949, 'loss/train': 1.4964138269424438} 08/31/2021 05:44:42 - INFO - __main__ - Step 90951: {'lr': 0.00017198909222403616, 'samples': 17462592, 'steps': 90950, 'loss/train': 1.612916111946106} 08/31/2021 05:44:44 - INFO - __main__ - Step 90952: {'lr': 0.00017198405047483067, 'samples': 17462784, 'steps': 90951, 'loss/train': 0.19203631579875946} 08/31/2021 05:44:44 - INFO - __main__ - Step 90953: {'lr': 0.00017197900876077802, 'samples': 17462976, 'steps': 90952, 'loss/train': 1.2398509979248047} 08/31/2021 05:44:44 - INFO - __main__ - Step 90954: {'lr': 0.0001719739670818804, 'samples': 17463168, 'steps': 90953, 'loss/train': 0.5201798677444458} 08/31/2021 05:44:45 - INFO - __main__ - Step 90955: {'lr': 0.00017196892543814006, 'samples': 17463360, 'steps': 90954, 'loss/train': 0.8124864101409912} 08/31/2021 05:44:45 - INFO - __main__ - Step 90956: {'lr': 0.0001719638838295594, 'samples': 17463552, 'steps': 90955, 'loss/train': 1.768354058265686} 08/31/2021 05:44:47 - INFO - __main__ - Step 90957: {'lr': 0.00017195884225614056, 'samples': 17463744, 'steps': 90956, 'loss/train': 0.2978844940662384} 08/31/2021 05:44:47 - INFO - __main__ - Step 90958: {'lr': 0.00017195380071788585, 'samples': 17463936, 'steps': 90957, 'loss/train': 1.2412759065628052} 08/31/2021 05:44:47 - INFO - __main__ - Step 90959: {'lr': 0.00017194875921479764, 'samples': 17464128, 'steps': 90958, 'loss/train': 1.0973803997039795} 08/31/2021 05:44:48 - INFO - __main__ - Step 90960: {'lr': 0.00017194371774687802, 'samples': 17464320, 'steps': 90959, 'loss/train': 1.2293301820755005} 08/31/2021 05:44:48 - INFO - __main__ - Step 90961: {'lr': 0.0001719386763141294, 'samples': 17464512, 'steps': 90960, 'loss/train': 1.0742098093032837} 08/31/2021 05:44:50 - INFO - __main__ - Step 90962: {'lr': 0.00017193363491655402, 'samples': 17464704, 'steps': 90961, 'loss/train': 1.004538893699646} 08/31/2021 05:44:50 - INFO - __main__ - Step 90963: {'lr': 0.00017192859355415413, 'samples': 17464896, 'steps': 90962, 'loss/train': 1.4034909009933472} 08/31/2021 05:44:50 - INFO - __main__ - Step 90964: {'lr': 0.00017192355222693198, 'samples': 17465088, 'steps': 90963, 'loss/train': 1.7135112285614014} 08/31/2021 05:44:51 - INFO - __main__ - Step 90965: {'lr': 0.0001719185109348899, 'samples': 17465280, 'steps': 90964, 'loss/train': 1.6814907789230347} 08/31/2021 05:44:51 - INFO - __main__ - Step 90966: {'lr': 0.0001719134696780301, 'samples': 17465472, 'steps': 90965, 'loss/train': 1.0822515487670898} 08/31/2021 05:44:51 - INFO - __main__ - Step 90967: {'lr': 0.00017190842845635492, 'samples': 17465664, 'steps': 90966, 'loss/train': 1.2728171348571777} 08/31/2021 05:44:53 - INFO - __main__ - Step 90968: {'lr': 0.00017190338726986654, 'samples': 17465856, 'steps': 90967, 'loss/train': 0.9997496008872986} 08/31/2021 05:44:53 - INFO - __main__ - Step 90969: {'lr': 0.00017189834611856737, 'samples': 17466048, 'steps': 90968, 'loss/train': 0.9745091199874878} 08/31/2021 05:44:54 - INFO - __main__ - Step 90970: {'lr': 0.00017189330500245954, 'samples': 17466240, 'steps': 90969, 'loss/train': 0.8736932277679443} 08/31/2021 05:44:54 - INFO - __main__ - Step 90971: {'lr': 0.00017188826392154538, 'samples': 17466432, 'steps': 90970, 'loss/train': 1.4604805707931519} 08/31/2021 05:44:56 - INFO - __main__ - Step 90972: {'lr': 0.00017188322287582726, 'samples': 17466624, 'steps': 90971, 'loss/train': 1.1491533517837524} 08/31/2021 05:44:56 - INFO - __main__ - Step 90973: {'lr': 0.00017187818186530733, 'samples': 17466816, 'steps': 90972, 'loss/train': 0.5599284768104553} 08/31/2021 05:44:56 - INFO - __main__ - Step 90974: {'lr': 0.0001718731408899878, 'samples': 17467008, 'steps': 90973, 'loss/train': 1.4432463645935059} 08/31/2021 05:44:57 - INFO - __main__ - Step 90975: {'lr': 0.00017186809994987107, 'samples': 17467200, 'steps': 90974, 'loss/train': 0.8557958006858826} 08/31/2021 05:44:57 - INFO - __main__ - Step 90976: {'lr': 0.00017186305904495937, 'samples': 17467392, 'steps': 90975, 'loss/train': 2.11617112159729} 08/31/2021 05:44:57 - INFO - __main__ - Step 90977: {'lr': 0.00017185801817525494, 'samples': 17467584, 'steps': 90976, 'loss/train': 1.1488450765609741} 08/31/2021 05:44:59 - INFO - __main__ - Step 90978: {'lr': 0.00017185297734076011, 'samples': 17467776, 'steps': 90977, 'loss/train': 1.1353843212127686} 08/31/2021 05:44:59 - INFO - __main__ - Step 90979: {'lr': 0.0001718479365414771, 'samples': 17467968, 'steps': 90978, 'loss/train': 0.12814056873321533} 08/31/2021 05:45:00 - INFO - __main__ - Step 90980: {'lr': 0.00017184289577740824, 'samples': 17468160, 'steps': 90979, 'loss/train': 0.7580072283744812} 08/31/2021 05:45:00 - INFO - __main__ - Step 90981: {'lr': 0.00017183785504855574, 'samples': 17468352, 'steps': 90980, 'loss/train': 1.4558935165405273} 08/31/2021 05:45:00 - INFO - __main__ - Step 90982: {'lr': 0.00017183281435492187, 'samples': 17468544, 'steps': 90981, 'loss/train': 1.2475756406784058} 08/31/2021 05:45:02 - INFO - __main__ - Step 90983: {'lr': 0.00017182777369650898, 'samples': 17468736, 'steps': 90982, 'loss/train': 0.7573660612106323} 08/31/2021 05:45:02 - INFO - __main__ - Step 90984: {'lr': 0.00017182273307331925, 'samples': 17468928, 'steps': 90983, 'loss/train': 1.2447818517684937} 08/31/2021 05:45:03 - INFO - __main__ - Step 90985: {'lr': 0.000171817692485355, 'samples': 17469120, 'steps': 90984, 'loss/train': 0.9689986109733582} 08/31/2021 05:45:03 - INFO - __main__ - Step 90986: {'lr': 0.00017181265193261865, 'samples': 17469312, 'steps': 90985, 'loss/train': 1.4272500276565552} 08/31/2021 05:45:03 - INFO - __main__ - Step 90987: {'lr': 0.00017180761141511215, 'samples': 17469504, 'steps': 90986, 'loss/train': 1.0198620557785034} 08/31/2021 05:45:05 - INFO - __main__ - Step 90988: {'lr': 0.0001718025709328379, 'samples': 17469696, 'steps': 90987, 'loss/train': 0.16397617757320404} 08/31/2021 05:45:05 - INFO - __main__ - Step 90989: {'lr': 0.00017179753048579828, 'samples': 17469888, 'steps': 90988, 'loss/train': 0.8708529472351074} 08/31/2021 05:45:06 - INFO - __main__ - Step 90990: {'lr': 0.00017179249007399545, 'samples': 17470080, 'steps': 90989, 'loss/train': 0.8160247206687927} 08/31/2021 05:45:06 - INFO - __main__ - Step 90991: {'lr': 0.0001717874496974317, 'samples': 17470272, 'steps': 90990, 'loss/train': 1.3293070793151855} 08/31/2021 05:45:06 - INFO - __main__ - Step 90992: {'lr': 0.00017178240935610933, 'samples': 17470464, 'steps': 90991, 'loss/train': 1.2116235494613647} 08/31/2021 05:45:08 - INFO - __main__ - Step 90993: {'lr': 0.0001717773690500306, 'samples': 17470656, 'steps': 90992, 'loss/train': 0.954754650592804} 08/31/2021 05:45:09 - INFO - __main__ - Step 90994: {'lr': 0.0001717723287791978, 'samples': 17470848, 'steps': 90993, 'loss/train': 1.1726782321929932} 08/31/2021 05:45:09 - INFO - __main__ - Step 90995: {'lr': 0.00017176728854361318, 'samples': 17471040, 'steps': 90994, 'loss/train': 0.04529386758804321} 08/31/2021 05:45:09 - INFO - __main__ - Step 90996: {'lr': 0.000171762248343279, 'samples': 17471232, 'steps': 90995, 'loss/train': 1.2938724756240845} 08/31/2021 05:45:10 - INFO - __main__ - Step 90997: {'lr': 0.00017175720817819753, 'samples': 17471424, 'steps': 90996, 'loss/train': 0.9281088709831238} 08/31/2021 05:45:12 - INFO - __main__ - Step 90998: {'lr': 0.00017175216804837107, 'samples': 17471616, 'steps': 90997, 'loss/train': 0.238095223903656} 08/31/2021 05:45:13 - INFO - __main__ - Step 90999: {'lr': 0.000171747127953802, 'samples': 17471808, 'steps': 90998, 'loss/train': 0.01793414168059826} 08/31/2021 05:45:13 - INFO - __main__ - Step 91000: {'lr': 0.00017174208789449234, 'samples': 17472000, 'steps': 90999, 'loss/train': 0.016876766458153725} 08/31/2021 05:45:13 - INFO - __main__ - Step 91001: {'lr': 0.00017173704787044446, 'samples': 17472192, 'steps': 91000, 'loss/train': 0.05235663428902626} 08/31/2021 05:45:14 - INFO - __main__ - Step 91002: {'lr': 0.00017173200788166073, 'samples': 17472384, 'steps': 91001, 'loss/train': 1.2535003423690796} 08/31/2021 05:45:14 - INFO - __main__ - Step 91003: {'lr': 0.0001717269679281433, 'samples': 17472576, 'steps': 91002, 'loss/train': 0.14082451164722443} 08/31/2021 05:45:15 - INFO - __main__ - Step 91004: {'lr': 0.0001717219280098945, 'samples': 17472768, 'steps': 91003, 'loss/train': 1.131034016609192} 08/31/2021 05:45:16 - INFO - __main__ - Step 91005: {'lr': 0.00017171688812691658, 'samples': 17472960, 'steps': 91004, 'loss/train': 1.2134250402450562} 08/31/2021 05:45:16 - INFO - __main__ - Step 91006: {'lr': 0.00017171184827921183, 'samples': 17473152, 'steps': 91005, 'loss/train': 5.810992240905762} 08/31/2021 05:45:17 - INFO - __main__ - Step 91007: {'lr': 0.0001717068084667825, 'samples': 17473344, 'steps': 91006, 'loss/train': 0.19514307379722595} 08/31/2021 05:45:17 - INFO - __main__ - Step 91008: {'lr': 0.0001717017686896309, 'samples': 17473536, 'steps': 91007, 'loss/train': 1.6311975717544556} 08/31/2021 05:45:19 - INFO - __main__ - Step 91009: {'lr': 0.0001716967289477593, 'samples': 17473728, 'steps': 91008, 'loss/train': 0.565496027469635} 08/31/2021 05:45:19 - INFO - __main__ - Step 91010: {'lr': 0.00017169168924116988, 'samples': 17473920, 'steps': 91009, 'loss/train': 1.3892548084259033} 08/31/2021 05:45:19 - INFO - __main__ - Step 91011: {'lr': 0.00017168664956986501, 'samples': 17474112, 'steps': 91010, 'loss/train': 1.304580807685852} 08/31/2021 05:45:20 - INFO - __main__ - Step 91012: {'lr': 0.00017168160993384692, 'samples': 17474304, 'steps': 91011, 'loss/train': 1.7136027812957764} 08/31/2021 05:45:20 - INFO - __main__ - Step 91013: {'lr': 0.000171676570333118, 'samples': 17474496, 'steps': 91012, 'loss/train': 0.49241456389427185} 08/31/2021 05:45:20 - INFO - __main__ - Step 91014: {'lr': 0.00017167153076768027, 'samples': 17474688, 'steps': 91013, 'loss/train': 1.331392765045166} 08/31/2021 05:45:22 - INFO - __main__ - Step 91015: {'lr': 0.0001716664912375362, 'samples': 17474880, 'steps': 91014, 'loss/train': 0.34656497836112976} 08/31/2021 05:45:23 - INFO - __main__ - Step 91016: {'lr': 0.00017166145174268797, 'samples': 17475072, 'steps': 91015, 'loss/train': 1.0841665267944336} 08/31/2021 05:45:23 - INFO - __main__ - Step 91017: {'lr': 0.0001716564122831379, 'samples': 17475264, 'steps': 91016, 'loss/train': 0.9820373058319092} 08/31/2021 05:45:23 - INFO - __main__ - Step 91018: {'lr': 0.0001716513728588882, 'samples': 17475456, 'steps': 91017, 'loss/train': 1.151803970336914} 08/31/2021 05:45:24 - INFO - __main__ - Step 91019: {'lr': 0.00017164633346994118, 'samples': 17475648, 'steps': 91018, 'loss/train': 1.2548874616622925} 08/31/2021 05:45:25 - INFO - __main__ - Step 91020: {'lr': 0.00017164129411629915, 'samples': 17475840, 'steps': 91019, 'loss/train': 1.751366376876831} 08/31/2021 05:45:26 - INFO - __main__ - Step 91021: {'lr': 0.00017163625479796435, 'samples': 17476032, 'steps': 91020, 'loss/train': 1.056251883506775} 08/31/2021 05:45:26 - INFO - __main__ - Step 91022: {'lr': 0.000171631215514939, 'samples': 17476224, 'steps': 91021, 'loss/train': 1.6581761837005615} 08/31/2021 05:45:26 - INFO - __main__ - Step 91023: {'lr': 0.00017162617626722545, 'samples': 17476416, 'steps': 91022, 'loss/train': 1.0313082933425903} 08/31/2021 05:45:27 - INFO - __main__ - Step 91024: {'lr': 0.00017162113705482593, 'samples': 17476608, 'steps': 91023, 'loss/train': 0.8587303161621094} 08/31/2021 05:45:28 - INFO - __main__ - Step 91025: {'lr': 0.0001716160978777427, 'samples': 17476800, 'steps': 91024, 'loss/train': 1.8142211437225342} 08/31/2021 05:45:29 - INFO - __main__ - Step 91026: {'lr': 0.0001716110587359782, 'samples': 17476992, 'steps': 91025, 'loss/train': 1.9630414247512817} 08/31/2021 05:45:29 - INFO - __main__ - Step 91027: {'lr': 0.00017160601962953436, 'samples': 17477184, 'steps': 91026, 'loss/train': 1.1977214813232422} 08/31/2021 05:45:30 - INFO - __main__ - Step 91028: {'lr': 0.00017160098055841373, 'samples': 17477376, 'steps': 91027, 'loss/train': 0.12505421042442322} 08/31/2021 05:45:30 - INFO - __main__ - Step 91029: {'lr': 0.00017159594152261841, 'samples': 17477568, 'steps': 91028, 'loss/train': 1.3638660907745361} 08/31/2021 05:45:30 - INFO - __main__ - Step 91030: {'lr': 0.00017159090252215082, 'samples': 17477760, 'steps': 91029, 'loss/train': 1.10369074344635} 08/31/2021 05:45:32 - INFO - __main__ - Step 91031: {'lr': 0.00017158586355701312, 'samples': 17477952, 'steps': 91030, 'loss/train': 1.8106333017349243} 08/31/2021 05:45:32 - INFO - __main__ - Step 91032: {'lr': 0.0001715808246272076, 'samples': 17478144, 'steps': 91031, 'loss/train': 2.0228216648101807} 08/31/2021 05:45:33 - INFO - __main__ - Step 91033: {'lr': 0.0001715757857327366, 'samples': 17478336, 'steps': 91032, 'loss/train': 1.2890697717666626} 08/31/2021 05:45:33 - INFO - __main__ - Step 91034: {'lr': 0.0001715707468736023, 'samples': 17478528, 'steps': 91033, 'loss/train': 1.69429349899292} 08/31/2021 05:45:33 - INFO - __main__ - Step 91035: {'lr': 0.000171565708049807, 'samples': 17478720, 'steps': 91034, 'loss/train': 1.0284637212753296} 08/31/2021 05:45:36 - INFO - __main__ - Step 91036: {'lr': 0.000171560669261353, 'samples': 17478912, 'steps': 91035, 'loss/train': 1.9822486639022827} 08/31/2021 05:45:36 - INFO - __main__ - Step 91037: {'lr': 0.0001715556305082426, 'samples': 17479104, 'steps': 91036, 'loss/train': 0.37747132778167725} 08/31/2021 05:45:37 - INFO - __main__ - Step 91038: {'lr': 0.00017155059179047795, 'samples': 17479296, 'steps': 91037, 'loss/train': 0.31737184524536133} 08/31/2021 05:45:37 - INFO - __main__ - Step 91039: {'lr': 0.00017154555310806152, 'samples': 17479488, 'steps': 91038, 'loss/train': 0.31398677825927734} 08/31/2021 05:45:37 - INFO - __main__ - Step 91040: {'lr': 0.00017154051446099537, 'samples': 17479680, 'steps': 91039, 'loss/train': 0.2410258799791336} 08/31/2021 05:45:38 - INFO - __main__ - Step 91041: {'lr': 0.00017153547584928183, 'samples': 17479872, 'steps': 91040, 'loss/train': 0.12176206707954407} 08/31/2021 05:45:38 - INFO - __main__ - Step 91042: {'lr': 0.00017153043727292323, 'samples': 17480064, 'steps': 91041, 'loss/train': 1.6902062892913818} 08/31/2021 05:45:40 - INFO - __main__ - Step 91043: {'lr': 0.00017152539873192176, 'samples': 17480256, 'steps': 91042, 'loss/train': 1.331680178642273} 08/31/2021 05:45:40 - INFO - __main__ - Step 91044: {'lr': 0.00017152036022627975, 'samples': 17480448, 'steps': 91043, 'loss/train': 2.035454750061035} 08/31/2021 05:45:40 - INFO - __main__ - Step 91045: {'lr': 0.00017151532175599943, 'samples': 17480640, 'steps': 91044, 'loss/train': 0.1682804524898529} 08/31/2021 05:45:41 - INFO - __main__ - Step 91046: {'lr': 0.00017151028332108314, 'samples': 17480832, 'steps': 91045, 'loss/train': 1.4508864879608154} 08/31/2021 05:45:41 - INFO - __main__ - Step 91047: {'lr': 0.00017150524492153308, 'samples': 17481024, 'steps': 91046, 'loss/train': 1.1878150701522827} 08/31/2021 05:45:43 - INFO - __main__ - Step 91048: {'lr': 0.00017150020655735154, 'samples': 17481216, 'steps': 91047, 'loss/train': 1.0626351833343506} 08/31/2021 05:45:43 - INFO - __main__ - Step 91049: {'lr': 0.00017149516822854082, 'samples': 17481408, 'steps': 91048, 'loss/train': 1.391242265701294} 08/31/2021 05:45:43 - INFO - __main__ - Step 91050: {'lr': 0.00017149012993510315, 'samples': 17481600, 'steps': 91049, 'loss/train': 1.2046242952346802} 08/31/2021 05:45:44 - INFO - __main__ - Step 91051: {'lr': 0.00017148509167704083, 'samples': 17481792, 'steps': 91050, 'loss/train': 1.262729287147522} 08/31/2021 05:45:44 - INFO - __main__ - Step 91052: {'lr': 0.0001714800534543561, 'samples': 17481984, 'steps': 91051, 'loss/train': 0.16544444859027863} 08/31/2021 05:45:45 - INFO - __main__ - Step 91053: {'lr': 0.00017147501526705133, 'samples': 17482176, 'steps': 91052, 'loss/train': 1.2105916738510132} 08/31/2021 05:45:47 - INFO - __main__ - Step 91054: {'lr': 0.00017146997711512866, 'samples': 17482368, 'steps': 91053, 'loss/train': 2.3436741828918457} 08/31/2021 05:45:47 - INFO - __main__ - Step 91055: {'lr': 0.00017146493899859036, 'samples': 17482560, 'steps': 91054, 'loss/train': 1.0988050699234009} 08/31/2021 05:45:47 - INFO - __main__ - Step 91056: {'lr': 0.00017145990091743877, 'samples': 17482752, 'steps': 91055, 'loss/train': 1.627381443977356} 08/31/2021 05:45:48 - INFO - __main__ - Step 91057: {'lr': 0.0001714548628716761, 'samples': 17482944, 'steps': 91056, 'loss/train': 0.9696332216262817} 08/31/2021 05:45:48 - INFO - __main__ - Step 91058: {'lr': 0.00017144982486130473, 'samples': 17483136, 'steps': 91057, 'loss/train': 1.3669774532318115} 08/31/2021 05:45:50 - INFO - __main__ - Step 91059: {'lr': 0.0001714447868863268, 'samples': 17483328, 'steps': 91058, 'loss/train': 1.1637426614761353} 08/31/2021 05:45:50 - INFO - __main__ - Step 91060: {'lr': 0.00017143974894674464, 'samples': 17483520, 'steps': 91059, 'loss/train': 0.6132662296295166} 08/31/2021 05:45:50 - INFO - __main__ - Step 91061: {'lr': 0.00017143471104256054, 'samples': 17483712, 'steps': 91060, 'loss/train': 1.3338665962219238} 08/31/2021 05:45:51 - INFO - __main__ - Step 91062: {'lr': 0.00017142967317377672, 'samples': 17483904, 'steps': 91061, 'loss/train': 1.5694302320480347} 08/31/2021 05:45:51 - INFO - __main__ - Step 91063: {'lr': 0.0001714246353403955, 'samples': 17484096, 'steps': 91062, 'loss/train': 1.71333646774292} 08/31/2021 05:45:53 - INFO - __main__ - Step 91064: {'lr': 0.00017141959754241916, 'samples': 17484288, 'steps': 91063, 'loss/train': 0.04349673166871071} 08/31/2021 05:45:53 - INFO - __main__ - Step 91065: {'lr': 0.00017141455977984988, 'samples': 17484480, 'steps': 91064, 'loss/train': 1.2313246726989746} 08/31/2021 05:45:53 - INFO - __main__ - Step 91066: {'lr': 0.00017140952205269006, 'samples': 17484672, 'steps': 91065, 'loss/train': 0.06664885580539703} 08/31/2021 05:45:54 - INFO - __main__ - Step 91067: {'lr': 0.00017140448436094182, 'samples': 17484864, 'steps': 91066, 'loss/train': 0.8148946166038513} 08/31/2021 05:45:54 - INFO - __main__ - Step 91068: {'lr': 0.00017139944670460755, 'samples': 17485056, 'steps': 91067, 'loss/train': 1.2934091091156006} 08/31/2021 05:45:55 - INFO - __main__ - Step 91069: {'lr': 0.00017139440908368943, 'samples': 17485248, 'steps': 91068, 'loss/train': 1.4961390495300293} 08/31/2021 05:45:56 - INFO - __main__ - Step 91070: {'lr': 0.00017138937149818978, 'samples': 17485440, 'steps': 91069, 'loss/train': 1.001347303390503} 08/31/2021 05:45:56 - INFO - __main__ - Step 91071: {'lr': 0.0001713843339481109, 'samples': 17485632, 'steps': 91070, 'loss/train': 1.1569021940231323} 08/31/2021 05:45:57 - INFO - __main__ - Step 91072: {'lr': 0.000171379296433455, 'samples': 17485824, 'steps': 91071, 'loss/train': 0.3628638982772827} 08/31/2021 05:45:57 - INFO - __main__ - Step 91073: {'lr': 0.00017137425895422437, 'samples': 17486016, 'steps': 91072, 'loss/train': 0.9286978840827942} 08/31/2021 05:45:59 - INFO - __main__ - Step 91074: {'lr': 0.00017136922151042133, 'samples': 17486208, 'steps': 91073, 'loss/train': 1.058770775794983} 08/31/2021 05:45:59 - INFO - __main__ - Step 91075: {'lr': 0.00017136418410204814, 'samples': 17486400, 'steps': 91074, 'loss/train': 1.2358647584915161} 08/31/2021 05:45:59 - INFO - __main__ - Step 91076: {'lr': 0.00017135914672910697, 'samples': 17486592, 'steps': 91075, 'loss/train': 1.6915009021759033} 08/31/2021 05:46:00 - INFO - __main__ - Step 91077: {'lr': 0.00017135410939160013, 'samples': 17486784, 'steps': 91076, 'loss/train': 0.9340865612030029} 08/31/2021 05:46:00 - INFO - __main__ - Step 91078: {'lr': 0.00017134907208952993, 'samples': 17486976, 'steps': 91077, 'loss/train': 1.2941854000091553} 08/31/2021 05:46:00 - INFO - __main__ - Step 91079: {'lr': 0.00017134403482289864, 'samples': 17487168, 'steps': 91078, 'loss/train': 1.3643970489501953} 08/31/2021 05:46:02 - INFO - __main__ - Step 91080: {'lr': 0.00017133899759170856, 'samples': 17487360, 'steps': 91079, 'loss/train': 0.49077171087265015} 08/31/2021 05:46:03 - INFO - __main__ - Step 91081: {'lr': 0.00017133396039596186, 'samples': 17487552, 'steps': 91080, 'loss/train': 1.2032086849212646} 08/31/2021 05:46:03 - INFO - __main__ - Step 91082: {'lr': 0.00017132892323566085, 'samples': 17487744, 'steps': 91081, 'loss/train': 1.33196222782135} 08/31/2021 05:46:04 - INFO - __main__ - Step 91083: {'lr': 0.00017132388611080786, 'samples': 17487936, 'steps': 91082, 'loss/train': 0.031334180384874344} 08/31/2021 05:46:04 - INFO - __main__ - Step 91084: {'lr': 0.00017131884902140508, 'samples': 17488128, 'steps': 91083, 'loss/train': 1.672255277633667} 08/31/2021 05:46:04 - INFO - __main__ - Step 91085: {'lr': 0.00017131381196745478, 'samples': 17488320, 'steps': 91084, 'loss/train': 0.11684360355138779} 08/31/2021 05:46:06 - INFO - __main__ - Step 91086: {'lr': 0.00017130877494895937, 'samples': 17488512, 'steps': 91085, 'loss/train': 1.1326669454574585} 08/31/2021 05:46:06 - INFO - __main__ - Step 91087: {'lr': 0.00017130373796592094, 'samples': 17488704, 'steps': 91086, 'loss/train': 1.1077215671539307} 08/31/2021 05:46:06 - INFO - __main__ - Step 91088: {'lr': 0.00017129870101834183, 'samples': 17488896, 'steps': 91087, 'loss/train': 1.1029284000396729} 08/31/2021 05:46:07 - INFO - __main__ - Step 91089: {'lr': 0.00017129366410622432, 'samples': 17489088, 'steps': 91088, 'loss/train': 1.1199655532836914} 08/31/2021 05:46:07 - INFO - __main__ - Step 91090: {'lr': 0.00017128862722957065, 'samples': 17489280, 'steps': 91089, 'loss/train': 1.4540222883224487} 08/31/2021 05:46:09 - INFO - __main__ - Step 91091: {'lr': 0.0001712835903883831, 'samples': 17489472, 'steps': 91090, 'loss/train': 1.357535481452942} 08/31/2021 05:46:09 - INFO - __main__ - Step 91092: {'lr': 0.00017127855358266397, 'samples': 17489664, 'steps': 91091, 'loss/train': 0.035043563693761826} 08/31/2021 05:46:10 - INFO - __main__ - Step 91093: {'lr': 0.00017127351681241556, 'samples': 17489856, 'steps': 91092, 'loss/train': 0.33691325783729553} 08/31/2021 05:46:10 - INFO - __main__ - Step 91094: {'lr': 0.00017126848007764008, 'samples': 17490048, 'steps': 91093, 'loss/train': 0.16279219090938568} 08/31/2021 05:46:10 - INFO - __main__ - Step 91095: {'lr': 0.00017126344337833974, 'samples': 17490240, 'steps': 91094, 'loss/train': 1.887627363204956} 08/31/2021 05:46:11 - INFO - __main__ - Step 91096: {'lr': 0.0001712584067145169, 'samples': 17490432, 'steps': 91095, 'loss/train': 1.2776693105697632} 08/31/2021 05:46:13 - INFO - __main__ - Step 91097: {'lr': 0.00017125337008617387, 'samples': 17490624, 'steps': 91096, 'loss/train': 1.5936853885650635} 08/31/2021 05:46:13 - INFO - __main__ - Step 91098: {'lr': 0.00017124833349331278, 'samples': 17490816, 'steps': 91097, 'loss/train': 1.482906699180603} 08/31/2021 05:46:13 - INFO - __main__ - Step 91099: {'lr': 0.00017124329693593598, 'samples': 17491008, 'steps': 91098, 'loss/train': 0.024358101189136505} 08/31/2021 05:46:14 - INFO - __main__ - Step 91100: {'lr': 0.00017123826041404579, 'samples': 17491200, 'steps': 91099, 'loss/train': 1.1230987310409546} 08/31/2021 05:46:14 - INFO - __main__ - Step 91101: {'lr': 0.00017123322392764435, 'samples': 17491392, 'steps': 91100, 'loss/train': 1.1437093019485474} 08/31/2021 05:46:14 - INFO - __main__ - Step 91102: {'lr': 0.00017122818747673403, 'samples': 17491584, 'steps': 91101, 'loss/train': 1.117323637008667} 08/31/2021 05:46:16 - INFO - __main__ - Step 91103: {'lr': 0.00017122315106131707, 'samples': 17491776, 'steps': 91102, 'loss/train': 1.0514676570892334} 08/31/2021 05:46:17 - INFO - __main__ - Step 91104: {'lr': 0.00017121811468139575, 'samples': 17491968, 'steps': 91103, 'loss/train': 1.220996379852295} 08/31/2021 05:46:17 - INFO - __main__ - Step 91105: {'lr': 0.00017121307833697235, 'samples': 17492160, 'steps': 91104, 'loss/train': 1.5346850156784058} 08/31/2021 05:46:17 - INFO - __main__ - Step 91106: {'lr': 0.0001712080420280491, 'samples': 17492352, 'steps': 91105, 'loss/train': 1.6383341550827026} 08/31/2021 05:46:18 - INFO - __main__ - Step 91107: {'lr': 0.00017120300575462836, 'samples': 17492544, 'steps': 91106, 'loss/train': 1.48788583278656} 08/31/2021 05:46:18 - INFO - __main__ - Step 91108: {'lr': 0.0001711979695167123, 'samples': 17492736, 'steps': 91107, 'loss/train': 1.3982620239257812} 08/31/2021 05:46:19 - INFO - __main__ - Step 91109: {'lr': 0.0001711929333143032, 'samples': 17492928, 'steps': 91108, 'loss/train': 1.3940863609313965} 08/31/2021 05:46:20 - INFO - __main__ - Step 91110: {'lr': 0.00017118789714740332, 'samples': 17493120, 'steps': 91109, 'loss/train': 1.3789671659469604} 08/31/2021 05:46:20 - INFO - __main__ - Step 91111: {'lr': 0.000171182861016015, 'samples': 17493312, 'steps': 91110, 'loss/train': 1.0991113185882568} 08/31/2021 05:46:21 - INFO - __main__ - Step 91112: {'lr': 0.0001711778249201404, 'samples': 17493504, 'steps': 91111, 'loss/train': 1.4298145771026611} 08/31/2021 05:46:21 - INFO - __main__ - Step 91113: {'lr': 0.0001711727888597819, 'samples': 17493696, 'steps': 91112, 'loss/train': 1.355703592300415} 08/31/2021 05:46:23 - INFO - __main__ - Step 91114: {'lr': 0.00017116775283494172, 'samples': 17493888, 'steps': 91113, 'loss/train': 1.0314207077026367} 08/31/2021 05:46:23 - INFO - __main__ - Step 91115: {'lr': 0.00017116271684562213, 'samples': 17494080, 'steps': 91114, 'loss/train': 1.4548933506011963} 08/31/2021 05:46:24 - INFO - __main__ - Step 91116: {'lr': 0.00017115768089182539, 'samples': 17494272, 'steps': 91115, 'loss/train': 1.5214502811431885} 08/31/2021 05:46:24 - INFO - __main__ - Step 91117: {'lr': 0.00017115264497355383, 'samples': 17494464, 'steps': 91116, 'loss/train': 1.7697179317474365} 08/31/2021 05:46:24 - INFO - __main__ - Step 91118: {'lr': 0.00017114760909080963, 'samples': 17494656, 'steps': 91117, 'loss/train': 1.147649884223938} 08/31/2021 05:46:26 - INFO - __main__ - Step 91119: {'lr': 0.00017114257324359508, 'samples': 17494848, 'steps': 91118, 'loss/train': 0.839748740196228} 08/31/2021 05:46:26 - INFO - __main__ - Step 91120: {'lr': 0.0001711375374319126, 'samples': 17495040, 'steps': 91119, 'loss/train': 2.1656606197357178} 08/31/2021 05:46:27 - INFO - __main__ - Step 91121: {'lr': 0.0001711325016557642, 'samples': 17495232, 'steps': 91120, 'loss/train': 1.7276383638381958} 08/31/2021 05:46:27 - INFO - __main__ - Step 91122: {'lr': 0.00017112746591515233, 'samples': 17495424, 'steps': 91121, 'loss/train': 1.2293304204940796} 08/31/2021 05:46:27 - INFO - __main__ - Step 91123: {'lr': 0.00017112243021007918, 'samples': 17495616, 'steps': 91122, 'loss/train': 1.0706586837768555} 08/31/2021 05:46:29 - INFO - __main__ - Step 91124: {'lr': 0.00017111739454054702, 'samples': 17495808, 'steps': 91123, 'loss/train': 1.6463905572891235} 08/31/2021 05:46:30 - INFO - __main__ - Step 91125: {'lr': 0.00017111235890655818, 'samples': 17496000, 'steps': 91124, 'loss/train': 1.9268982410430908} 08/31/2021 05:46:31 - INFO - __main__ - Step 91126: {'lr': 0.0001711073233081149, 'samples': 17496192, 'steps': 91125, 'loss/train': 1.809248924255371} 08/31/2021 05:46:31 - INFO - __main__ - Step 91127: {'lr': 0.00017110228774521943, 'samples': 17496384, 'steps': 91126, 'loss/train': 1.8315136432647705} 08/31/2021 05:46:31 - INFO - __main__ - Step 91128: {'lr': 0.00017109725221787405, 'samples': 17496576, 'steps': 91127, 'loss/train': 0.030464202165603638} 08/31/2021 05:46:32 - INFO - __main__ - Step 91129: {'lr': 0.00017109221672608106, 'samples': 17496768, 'steps': 91128, 'loss/train': 1.9046683311462402} 08/31/2021 05:46:32 - INFO - __main__ - Step 91130: {'lr': 0.00017108718126984264, 'samples': 17496960, 'steps': 91129, 'loss/train': 1.4812196493148804} 08/31/2021 05:46:32 - INFO - __main__ - Step 91131: {'lr': 0.00017108214584916114, 'samples': 17497152, 'steps': 91130, 'loss/train': 0.7698671817779541} 08/31/2021 05:46:34 - INFO - __main__ - Step 91132: {'lr': 0.00017107711046403885, 'samples': 17497344, 'steps': 91131, 'loss/train': 1.6743072271347046} 08/31/2021 05:46:34 - INFO - __main__ - Step 91133: {'lr': 0.00017107207511447793, 'samples': 17497536, 'steps': 91132, 'loss/train': 1.1222306489944458} 08/31/2021 05:46:35 - INFO - __main__ - Step 91134: {'lr': 0.00017106703980048084, 'samples': 17497728, 'steps': 91133, 'loss/train': 0.9562334418296814} 08/31/2021 05:46:35 - INFO - __main__ - Step 91135: {'lr': 0.00017106200452204966, 'samples': 17497920, 'steps': 91134, 'loss/train': 0.9763485193252563} 08/31/2021 05:46:35 - INFO - __main__ - Step 91136: {'lr': 0.00017105696927918667, 'samples': 17498112, 'steps': 91135, 'loss/train': 0.991174042224884} 08/31/2021 05:46:37 - INFO - __main__ - Step 91137: {'lr': 0.00017105193407189424, 'samples': 17498304, 'steps': 91136, 'loss/train': 1.1010651588439941} 08/31/2021 05:46:37 - INFO - __main__ - Step 91138: {'lr': 0.00017104689890017454, 'samples': 17498496, 'steps': 91137, 'loss/train': 0.7108782529830933} 08/31/2021 05:46:38 - INFO - __main__ - Step 91139: {'lr': 0.00017104186376402992, 'samples': 17498688, 'steps': 91138, 'loss/train': 1.3825891017913818} 08/31/2021 05:46:38 - INFO - __main__ - Step 91140: {'lr': 0.0001710368286634626, 'samples': 17498880, 'steps': 91139, 'loss/train': 1.13723623752594} 08/31/2021 05:46:38 - INFO - __main__ - Step 91141: {'lr': 0.00017103179359847487, 'samples': 17499072, 'steps': 91140, 'loss/train': 0.7255374789237976} 08/31/2021 05:46:40 - INFO - __main__ - Step 91142: {'lr': 0.000171026758569069, 'samples': 17499264, 'steps': 91141, 'loss/train': 0.5507801175117493} 08/31/2021 05:46:40 - INFO - __main__ - Step 91143: {'lr': 0.0001710217235752473, 'samples': 17499456, 'steps': 91142, 'loss/train': 1.200390338897705} 08/31/2021 05:46:41 - INFO - __main__ - Step 91144: {'lr': 0.00017101668861701193, 'samples': 17499648, 'steps': 91143, 'loss/train': 1.4691784381866455} 08/31/2021 05:46:41 - INFO - __main__ - Step 91145: {'lr': 0.00017101165369436523, 'samples': 17499840, 'steps': 91144, 'loss/train': 0.744489848613739} 08/31/2021 05:46:41 - INFO - __main__ - Step 91146: {'lr': 0.0001710066188073095, 'samples': 17500032, 'steps': 91145, 'loss/train': 1.133280873298645} 08/31/2021 05:46:43 - INFO - __main__ - Step 91147: {'lr': 0.00017100158395584703, 'samples': 17500224, 'steps': 91146, 'loss/train': 1.3951730728149414} 08/31/2021 05:46:43 - INFO - __main__ - Step 91148: {'lr': 0.0001709965491399799, 'samples': 17500416, 'steps': 91147, 'loss/train': 0.587582528591156} 08/31/2021 05:46:44 - INFO - __main__ - Step 91149: {'lr': 0.00017099151435971056, 'samples': 17500608, 'steps': 91148, 'loss/train': 0.7344940304756165} 08/31/2021 05:46:44 - INFO - __main__ - Step 91150: {'lr': 0.0001709864796150412, 'samples': 17500800, 'steps': 91149, 'loss/train': 1.3192561864852905} 08/31/2021 05:46:44 - INFO - __main__ - Step 91151: {'lr': 0.00017098144490597413, 'samples': 17500992, 'steps': 91150, 'loss/train': 0.7835680246353149} 08/31/2021 05:46:45 - INFO - __main__ - Step 91152: {'lr': 0.0001709764102325116, 'samples': 17501184, 'steps': 91151, 'loss/train': 1.355960488319397} 08/31/2021 05:46:46 - INFO - __main__ - Step 91153: {'lr': 0.00017097137559465587, 'samples': 17501376, 'steps': 91152, 'loss/train': 0.129905566573143} 08/31/2021 05:46:47 - INFO - __main__ - Step 91154: {'lr': 0.0001709663409924092, 'samples': 17501568, 'steps': 91153, 'loss/train': 0.3740858733654022} 08/31/2021 05:46:47 - INFO - __main__ - Step 91155: {'lr': 0.00017096130642577393, 'samples': 17501760, 'steps': 91154, 'loss/train': 1.5963555574417114} 08/31/2021 05:46:48 - INFO - __main__ - Step 91156: {'lr': 0.00017095627189475223, 'samples': 17501952, 'steps': 91155, 'loss/train': 6.33020544052124} 08/31/2021 05:46:48 - INFO - __main__ - Step 91157: {'lr': 0.00017095123739934643, 'samples': 17502144, 'steps': 91156, 'loss/train': 1.7429757118225098} 08/31/2021 05:46:48 - INFO - __main__ - Step 91158: {'lr': 0.0001709462029395588, 'samples': 17502336, 'steps': 91157, 'loss/train': 1.1278855800628662} 08/31/2021 05:46:50 - INFO - __main__ - Step 91159: {'lr': 0.00017094116851539153, 'samples': 17502528, 'steps': 91158, 'loss/train': 1.4770716428756714} 08/31/2021 05:46:50 - INFO - __main__ - Step 91160: {'lr': 0.0001709361341268471, 'samples': 17502720, 'steps': 91159, 'loss/train': 1.0023345947265625} 08/31/2021 05:46:51 - INFO - __main__ - Step 91161: {'lr': 0.00017093109977392754, 'samples': 17502912, 'steps': 91160, 'loss/train': 1.7933725118637085} 08/31/2021 05:46:51 - INFO - __main__ - Step 91162: {'lr': 0.00017092606545663518, 'samples': 17503104, 'steps': 91161, 'loss/train': 0.9480769634246826} 08/31/2021 05:46:51 - INFO - __main__ - Step 91163: {'lr': 0.0001709210311749723, 'samples': 17503296, 'steps': 91162, 'loss/train': 0.9759781956672668} 08/31/2021 05:46:53 - INFO - __main__ - Step 91164: {'lr': 0.00017091599692894123, 'samples': 17503488, 'steps': 91163, 'loss/train': 1.3948675394058228} 08/31/2021 05:46:53 - INFO - __main__ - Step 91165: {'lr': 0.00017091096271854418, 'samples': 17503680, 'steps': 91164, 'loss/train': 1.509735345840454} 08/31/2021 05:46:53 - INFO - __main__ - Step 91166: {'lr': 0.0001709059285437834, 'samples': 17503872, 'steps': 91165, 'loss/train': 1.4731329679489136} 08/31/2021 05:46:54 - INFO - __main__ - Step 91167: {'lr': 0.0001709008944046612, 'samples': 17504064, 'steps': 91166, 'loss/train': 2.0414538383483887} 08/31/2021 05:46:54 - INFO - __main__ - Step 91168: {'lr': 0.0001708958603011798, 'samples': 17504256, 'steps': 91167, 'loss/train': 1.2893576622009277} 08/31/2021 05:46:56 - INFO - __main__ - Step 91169: {'lr': 0.00017089082623334158, 'samples': 17504448, 'steps': 91168, 'loss/train': 1.4462528228759766} 08/31/2021 05:46:57 - INFO - __main__ - Step 91170: {'lr': 0.0001708857922011487, 'samples': 17504640, 'steps': 91169, 'loss/train': 1.4290248155593872} 08/31/2021 05:46:57 - INFO - __main__ - Step 91171: {'lr': 0.00017088075820460348, 'samples': 17504832, 'steps': 91170, 'loss/train': 1.389906644821167} 08/31/2021 05:46:57 - INFO - __main__ - Step 91172: {'lr': 0.00017087572424370813, 'samples': 17505024, 'steps': 91171, 'loss/train': 0.40433910489082336} 08/31/2021 05:46:58 - INFO - __main__ - Step 91173: {'lr': 0.00017087069031846498, 'samples': 17505216, 'steps': 91172, 'loss/train': 1.2337180376052856} 08/31/2021 05:46:59 - INFO - __main__ - Step 91174: {'lr': 0.00017086565642887637, 'samples': 17505408, 'steps': 91173, 'loss/train': 1.605295181274414} 08/31/2021 05:47:00 - INFO - __main__ - Step 91175: {'lr': 0.00017086062257494437, 'samples': 17505600, 'steps': 91174, 'loss/train': 1.1008789539337158} 08/31/2021 05:47:00 - INFO - __main__ - Step 91176: {'lr': 0.00017085558875667135, 'samples': 17505792, 'steps': 91175, 'loss/train': 1.165114164352417} 08/31/2021 05:47:00 - INFO - __main__ - Step 91177: {'lr': 0.0001708505549740596, 'samples': 17505984, 'steps': 91176, 'loss/train': 0.8045783042907715} 08/31/2021 05:47:01 - INFO - __main__ - Step 91178: {'lr': 0.00017084552122711134, 'samples': 17506176, 'steps': 91177, 'loss/train': 1.2924296855926514} 08/31/2021 05:47:01 - INFO - __main__ - Step 91179: {'lr': 0.00017084048751582888, 'samples': 17506368, 'steps': 91178, 'loss/train': 0.7656028270721436} 08/31/2021 05:47:03 - INFO - __main__ - Step 91180: {'lr': 0.00017083545384021447, 'samples': 17506560, 'steps': 91179, 'loss/train': 1.0223921537399292} 08/31/2021 05:47:03 - INFO - __main__ - Step 91181: {'lr': 0.0001708304202002704, 'samples': 17506752, 'steps': 91180, 'loss/train': 1.4933019876480103} 08/31/2021 05:47:03 - INFO - __main__ - Step 91182: {'lr': 0.0001708253865959989, 'samples': 17506944, 'steps': 91181, 'loss/train': 1.1980195045471191} 08/31/2021 05:47:04 - INFO - __main__ - Step 91183: {'lr': 0.00017082035302740228, 'samples': 17507136, 'steps': 91182, 'loss/train': 0.8855717182159424} 08/31/2021 05:47:04 - INFO - __main__ - Step 91184: {'lr': 0.0001708153194944828, 'samples': 17507328, 'steps': 91183, 'loss/train': 1.4952278137207031} 08/31/2021 05:47:06 - INFO - __main__ - Step 91185: {'lr': 0.00017081028599724268, 'samples': 17507520, 'steps': 91184, 'loss/train': 0.9485859274864197} 08/31/2021 05:47:06 - INFO - __main__ - Step 91186: {'lr': 0.00017080525253568423, 'samples': 17507712, 'steps': 91185, 'loss/train': 1.6232571601867676} 08/31/2021 05:47:06 - INFO - __main__ - Step 91187: {'lr': 0.0001708002191098098, 'samples': 17507904, 'steps': 91186, 'loss/train': 0.8607884645462036} 08/31/2021 05:47:07 - INFO - __main__ - Step 91188: {'lr': 0.0001707951857196215, 'samples': 17508096, 'steps': 91187, 'loss/train': 1.4691336154937744} 08/31/2021 05:47:07 - INFO - __main__ - Step 91189: {'lr': 0.00017079015236512167, 'samples': 17508288, 'steps': 91188, 'loss/train': 1.1065921783447266} 08/31/2021 05:47:09 - INFO - __main__ - Step 91190: {'lr': 0.00017078511904631256, 'samples': 17508480, 'steps': 91189, 'loss/train': 1.3112668991088867} 08/31/2021 05:47:09 - INFO - __main__ - Step 91191: {'lr': 0.00017078008576319642, 'samples': 17508672, 'steps': 91190, 'loss/train': 1.0035836696624756} 08/31/2021 05:47:09 - INFO - __main__ - Step 91192: {'lr': 0.0001707750525157756, 'samples': 17508864, 'steps': 91191, 'loss/train': 1.105150580406189} 08/31/2021 05:47:10 - INFO - __main__ - Step 91193: {'lr': 0.0001707700193040523, 'samples': 17509056, 'steps': 91192, 'loss/train': 1.2668707370758057} 08/31/2021 05:47:10 - INFO - __main__ - Step 91194: {'lr': 0.00017076498612802882, 'samples': 17509248, 'steps': 91193, 'loss/train': 1.1180211305618286} 08/31/2021 05:47:12 - INFO - __main__ - Step 91195: {'lr': 0.00017075995298770742, 'samples': 17509440, 'steps': 91194, 'loss/train': 0.8925227522850037} 08/31/2021 05:47:12 - INFO - __main__ - Step 91196: {'lr': 0.00017075491988309034, 'samples': 17509632, 'steps': 91195, 'loss/train': 0.8483335375785828} 08/31/2021 05:47:13 - INFO - __main__ - Step 91197: {'lr': 0.00017074988681417986, 'samples': 17509824, 'steps': 91196, 'loss/train': 1.1512210369110107} 08/31/2021 05:47:13 - INFO - __main__ - Step 91198: {'lr': 0.0001707448537809783, 'samples': 17510016, 'steps': 91197, 'loss/train': 1.5847936868667603} 08/31/2021 05:47:14 - INFO - __main__ - Step 91199: {'lr': 0.00017073982078348788, 'samples': 17510208, 'steps': 91198, 'loss/train': 1.5981664657592773} 08/31/2021 05:47:14 - INFO - __main__ - Step 91200: {'lr': 0.00017073478782171086, 'samples': 17510400, 'steps': 91199, 'loss/train': 0.031971972435712814} 08/31/2021 05:47:15 - INFO - __main__ - Step 91201: {'lr': 0.00017072975489564957, 'samples': 17510592, 'steps': 91200, 'loss/train': 1.0581448078155518} 08/31/2021 05:47:16 - INFO - __main__ - Step 91202: {'lr': 0.00017072472200530616, 'samples': 17510784, 'steps': 91201, 'loss/train': 1.2997153997421265} 08/31/2021 05:47:16 - INFO - __main__ - Step 91203: {'lr': 0.00017071968915068297, 'samples': 17510976, 'steps': 91202, 'loss/train': 1.7292301654815674} 08/31/2021 05:47:16 - INFO - __main__ - Step 91204: {'lr': 0.0001707146563317823, 'samples': 17511168, 'steps': 91203, 'loss/train': 0.4400879442691803} 08/31/2021 05:47:17 - INFO - __main__ - Step 91205: {'lr': 0.00017070962354860637, 'samples': 17511360, 'steps': 91204, 'loss/train': 1.2384166717529297} 08/31/2021 05:47:17 - INFO - __main__ - Step 91206: {'lr': 0.0001707045908011574, 'samples': 17511552, 'steps': 91205, 'loss/train': 1.481101393699646} 08/31/2021 05:47:19 - INFO - __main__ - Step 91207: {'lr': 0.0001706995580894378, 'samples': 17511744, 'steps': 91206, 'loss/train': 0.8278005123138428} 08/31/2021 05:47:19 - INFO - __main__ - Step 91208: {'lr': 0.00017069452541344972, 'samples': 17511936, 'steps': 91207, 'loss/train': 1.3875473737716675} 08/31/2021 05:47:20 - INFO - __main__ - Step 91209: {'lr': 0.0001706894927731955, 'samples': 17512128, 'steps': 91208, 'loss/train': 0.5742800235748291} 08/31/2021 05:47:20 - INFO - __main__ - Step 91210: {'lr': 0.00017068446016867733, 'samples': 17512320, 'steps': 91209, 'loss/train': 1.3544921875} 08/31/2021 05:47:20 - INFO - __main__ - Step 91211: {'lr': 0.00017067942759989752, 'samples': 17512512, 'steps': 91210, 'loss/train': 1.0022785663604736} 08/31/2021 05:47:22 - INFO - __main__ - Step 91212: {'lr': 0.00017067439506685832, 'samples': 17512704, 'steps': 91211, 'loss/train': 1.1528931856155396} 08/31/2021 05:47:22 - INFO - __main__ - Step 91213: {'lr': 0.00017066936256956205, 'samples': 17512896, 'steps': 91212, 'loss/train': 1.5481849908828735} 08/31/2021 05:47:23 - INFO - __main__ - Step 91214: {'lr': 0.000170664330108011, 'samples': 17513088, 'steps': 91213, 'loss/train': 0.781757116317749} 08/31/2021 05:47:23 - INFO - __main__ - Step 91215: {'lr': 0.0001706592976822073, 'samples': 17513280, 'steps': 91214, 'loss/train': 1.1729583740234375} 08/31/2021 05:47:23 - INFO - __main__ - Step 91216: {'lr': 0.00017065426529215327, 'samples': 17513472, 'steps': 91215, 'loss/train': 1.7142874002456665} 08/31/2021 05:47:25 - INFO - __main__ - Step 91217: {'lr': 0.00017064923293785126, 'samples': 17513664, 'steps': 91216, 'loss/train': 1.3061195611953735} 08/31/2021 05:47:25 - INFO - __main__ - Step 91218: {'lr': 0.00017064420061930344, 'samples': 17513856, 'steps': 91217, 'loss/train': 1.1442420482635498} 08/31/2021 05:47:26 - INFO - __main__ - Step 91219: {'lr': 0.00017063916833651215, 'samples': 17514048, 'steps': 91218, 'loss/train': 0.15884552896022797} 08/31/2021 05:47:26 - INFO - __main__ - Step 91220: {'lr': 0.00017063413608947963, 'samples': 17514240, 'steps': 91219, 'loss/train': 1.366459608078003} 08/31/2021 05:47:26 - INFO - __main__ - Step 91221: {'lr': 0.00017062910387820811, 'samples': 17514432, 'steps': 91220, 'loss/train': 0.9647477865219116} 08/31/2021 05:47:28 - INFO - __main__ - Step 91222: {'lr': 0.00017062407170269996, 'samples': 17514624, 'steps': 91221, 'loss/train': 0.0929044708609581} 08/31/2021 05:47:28 - INFO - __main__ - Step 91223: {'lr': 0.0001706190395629573, 'samples': 17514816, 'steps': 91222, 'loss/train': 0.8429276943206787} 08/31/2021 05:47:28 - INFO - __main__ - Step 91224: {'lr': 0.0001706140074589825, 'samples': 17515008, 'steps': 91223, 'loss/train': 0.9324246048927307} 08/31/2021 05:47:29 - INFO - __main__ - Step 91225: {'lr': 0.0001706089753907778, 'samples': 17515200, 'steps': 91224, 'loss/train': 1.4786691665649414} 08/31/2021 05:47:29 - INFO - __main__ - Step 91226: {'lr': 0.00017060394335834545, 'samples': 17515392, 'steps': 91225, 'loss/train': 1.4257385730743408} 08/31/2021 05:47:32 - INFO - __main__ - Step 91227: {'lr': 0.00017059891136168777, 'samples': 17515584, 'steps': 91226, 'loss/train': 1.1354807615280151} 08/31/2021 05:47:32 - INFO - __main__ - Step 91228: {'lr': 0.00017059387940080703, 'samples': 17515776, 'steps': 91227, 'loss/train': 1.1789370775222778} 08/31/2021 05:47:32 - INFO - __main__ - Step 91229: {'lr': 0.00017058884747570542, 'samples': 17515968, 'steps': 91228, 'loss/train': 2.025175094604492} 08/31/2021 05:47:33 - INFO - __main__ - Step 91230: {'lr': 0.00017058381558638524, 'samples': 17516160, 'steps': 91229, 'loss/train': 0.7734950184822083} 08/31/2021 05:47:33 - INFO - __main__ - Step 91231: {'lr': 0.00017057878373284886, 'samples': 17516352, 'steps': 91230, 'loss/train': 0.4308869540691376} 08/31/2021 05:47:33 - INFO - __main__ - Step 91232: {'lr': 0.00017057375191509834, 'samples': 17516544, 'steps': 91231, 'loss/train': 0.9964208006858826} 08/31/2021 05:47:35 - INFO - __main__ - Step 91233: {'lr': 0.0001705687201331361, 'samples': 17516736, 'steps': 91232, 'loss/train': 0.03141103312373161} 08/31/2021 05:47:36 - INFO - __main__ - Step 91234: {'lr': 0.00017056368838696433, 'samples': 17516928, 'steps': 91233, 'loss/train': 0.5049709677696228} 08/31/2021 05:47:36 - INFO - __main__ - Step 91235: {'lr': 0.00017055865667658539, 'samples': 17517120, 'steps': 91234, 'loss/train': 5.944053649902344} 08/31/2021 05:47:36 - INFO - __main__ - Step 91236: {'lr': 0.00017055362500200148, 'samples': 17517312, 'steps': 91235, 'loss/train': 1.0488251447677612} 08/31/2021 05:47:37 - INFO - __main__ - Step 91237: {'lr': 0.00017054859336321487, 'samples': 17517504, 'steps': 91236, 'loss/train': 1.5861542224884033} 08/31/2021 05:47:37 - INFO - __main__ - Step 91238: {'lr': 0.00017054356176022785, 'samples': 17517696, 'steps': 91237, 'loss/train': 0.03817170113325119} 08/31/2021 05:47:38 - INFO - __main__ - Step 91239: {'lr': 0.00017053853019304263, 'samples': 17517888, 'steps': 91238, 'loss/train': 1.4982024431228638} 08/31/2021 05:47:39 - INFO - __main__ - Step 91240: {'lr': 0.00017053349866166158, 'samples': 17518080, 'steps': 91239, 'loss/train': 1.439855694770813} 08/31/2021 05:47:39 - INFO - __main__ - Step 91241: {'lr': 0.0001705284671660869, 'samples': 17518272, 'steps': 91240, 'loss/train': 0.7485061883926392} 08/31/2021 05:47:40 - INFO - __main__ - Step 91242: {'lr': 0.0001705234357063209, 'samples': 17518464, 'steps': 91241, 'loss/train': 1.4662249088287354} 08/31/2021 05:47:40 - INFO - __main__ - Step 91243: {'lr': 0.0001705184042823658, 'samples': 17518656, 'steps': 91242, 'loss/train': 1.3251489400863647} 08/31/2021 05:47:41 - INFO - __main__ - Step 91244: {'lr': 0.0001705133728942238, 'samples': 17518848, 'steps': 91243, 'loss/train': 1.4665746688842773} 08/31/2021 05:47:42 - INFO - __main__ - Step 91245: {'lr': 0.00017050834154189732, 'samples': 17519040, 'steps': 91244, 'loss/train': 1.200044870376587} 08/31/2021 05:47:42 - INFO - __main__ - Step 91246: {'lr': 0.0001705033102253885, 'samples': 17519232, 'steps': 91245, 'loss/train': 1.4748455286026} 08/31/2021 05:47:42 - INFO - __main__ - Step 91247: {'lr': 0.00017049827894469972, 'samples': 17519424, 'steps': 91246, 'loss/train': 0.91477370262146} 08/31/2021 05:47:43 - INFO - __main__ - Step 91248: {'lr': 0.00017049324769983316, 'samples': 17519616, 'steps': 91247, 'loss/train': 1.0537720918655396} 08/31/2021 05:47:44 - INFO - __main__ - Step 91249: {'lr': 0.0001704882164907911, 'samples': 17519808, 'steps': 91248, 'loss/train': 0.3956505358219147} 08/31/2021 05:47:45 - INFO - __main__ - Step 91250: {'lr': 0.00017048318531757585, 'samples': 17520000, 'steps': 91249, 'loss/train': 1.3170199394226074} 08/31/2021 05:47:45 - INFO - __main__ - Step 91251: {'lr': 0.00017047815418018964, 'samples': 17520192, 'steps': 91250, 'loss/train': 1.8635145425796509} 08/31/2021 05:47:45 - INFO - __main__ - Step 91252: {'lr': 0.00017047312307863472, 'samples': 17520384, 'steps': 91251, 'loss/train': 0.8491937518119812} 08/31/2021 05:47:46 - INFO - __main__ - Step 91253: {'lr': 0.0001704680920129134, 'samples': 17520576, 'steps': 91252, 'loss/train': 0.9244742393493652} 08/31/2021 05:47:47 - INFO - __main__ - Step 91254: {'lr': 0.00017046306098302794, 'samples': 17520768, 'steps': 91253, 'loss/train': 1.3629950284957886} 08/31/2021 05:47:48 - INFO - __main__ - Step 91255: {'lr': 0.00017045802998898069, 'samples': 17520960, 'steps': 91254, 'loss/train': 1.1513310670852661} 08/31/2021 05:47:48 - INFO - __main__ - Step 91256: {'lr': 0.00017045299903077374, 'samples': 17521152, 'steps': 91255, 'loss/train': 1.131535530090332} 08/31/2021 05:47:49 - INFO - __main__ - Step 91257: {'lr': 0.00017044796810840944, 'samples': 17521344, 'steps': 91256, 'loss/train': 0.7470303177833557} 08/31/2021 05:47:49 - INFO - __main__ - Step 91258: {'lr': 0.00017044293722189003, 'samples': 17521536, 'steps': 91257, 'loss/train': 1.4886077642440796} 08/31/2021 05:47:51 - INFO - __main__ - Step 91259: {'lr': 0.0001704379063712178, 'samples': 17521728, 'steps': 91258, 'loss/train': 0.17533913254737854} 08/31/2021 05:47:51 - INFO - __main__ - Step 91260: {'lr': 0.00017043287555639508, 'samples': 17521920, 'steps': 91259, 'loss/train': 0.939712643623352} 08/31/2021 05:47:52 - INFO - __main__ - Step 91261: {'lr': 0.00017042784477742403, 'samples': 17522112, 'steps': 91260, 'loss/train': 1.654911994934082} 08/31/2021 05:47:52 - INFO - __main__ - Step 91262: {'lr': 0.000170422814034307, 'samples': 17522304, 'steps': 91261, 'loss/train': 1.4147247076034546} 08/31/2021 05:47:52 - INFO - __main__ - Step 91263: {'lr': 0.00017041778332704615, 'samples': 17522496, 'steps': 91262, 'loss/train': 1.2605504989624023} 08/31/2021 05:47:53 - INFO - __main__ - Step 91264: {'lr': 0.00017041275265564389, 'samples': 17522688, 'steps': 91263, 'loss/train': 0.022043120115995407} 08/31/2021 05:47:53 - INFO - __main__ - Step 91265: {'lr': 0.0001704077220201024, 'samples': 17522880, 'steps': 91264, 'loss/train': 0.018593156710267067} 08/31/2021 05:47:54 - INFO - __main__ - Step 91266: {'lr': 0.00017040269142042395, 'samples': 17523072, 'steps': 91265, 'loss/train': 1.1607064008712769} 08/31/2021 05:47:55 - INFO - __main__ - Step 91267: {'lr': 0.0001703976608566108, 'samples': 17523264, 'steps': 91266, 'loss/train': 1.3284333944320679} 08/31/2021 05:47:55 - INFO - __main__ - Step 91268: {'lr': 0.0001703926303286654, 'samples': 17523456, 'steps': 91267, 'loss/train': 0.8727527260780334} 08/31/2021 05:47:56 - INFO - __main__ - Step 91269: {'lr': 0.0001703875998365897, 'samples': 17523648, 'steps': 91268, 'loss/train': 1.368183970451355} 08/31/2021 05:47:56 - INFO - __main__ - Step 91270: {'lr': 0.00017038256938038614, 'samples': 17523840, 'steps': 91269, 'loss/train': 0.5253578424453735} 08/31/2021 05:47:58 - INFO - __main__ - Step 91271: {'lr': 0.00017037753896005696, 'samples': 17524032, 'steps': 91270, 'loss/train': 0.8369527459144592} 08/31/2021 05:47:58 - INFO - __main__ - Step 91272: {'lr': 0.00017037250857560444, 'samples': 17524224, 'steps': 91271, 'loss/train': 1.5787227153778076} 08/31/2021 05:47:58 - INFO - __main__ - Step 91273: {'lr': 0.0001703674782270308, 'samples': 17524416, 'steps': 91272, 'loss/train': 0.5293254852294922} 08/31/2021 05:47:59 - INFO - __main__ - Step 91274: {'lr': 0.0001703624479143384, 'samples': 17524608, 'steps': 91273, 'loss/train': 1.4708366394042969} 08/31/2021 05:47:59 - INFO - __main__ - Step 91275: {'lr': 0.0001703574176375294, 'samples': 17524800, 'steps': 91274, 'loss/train': 1.1981788873672485} 08/31/2021 05:48:01 - INFO - __main__ - Step 91276: {'lr': 0.00017035238739660614, 'samples': 17524992, 'steps': 91275, 'loss/train': 1.4728083610534668} 08/31/2021 05:48:01 - INFO - __main__ - Step 91277: {'lr': 0.0001703473571915709, 'samples': 17525184, 'steps': 91276, 'loss/train': 0.45631203055381775} 08/31/2021 05:48:02 - INFO - __main__ - Step 91278: {'lr': 0.00017034232702242585, 'samples': 17525376, 'steps': 91277, 'loss/train': 0.6769919991493225} 08/31/2021 05:48:02 - INFO - __main__ - Step 91279: {'lr': 0.00017033729688917338, 'samples': 17525568, 'steps': 91278, 'loss/train': 0.11890745162963867} 08/31/2021 05:48:02 - INFO - __main__ - Step 91280: {'lr': 0.00017033226679181562, 'samples': 17525760, 'steps': 91279, 'loss/train': 1.3310625553131104} 08/31/2021 05:48:04 - INFO - __main__ - Step 91281: {'lr': 0.0001703272367303551, 'samples': 17525952, 'steps': 91280, 'loss/train': 0.8802390694618225} 08/31/2021 05:48:05 - INFO - __main__ - Step 91282: {'lr': 0.00017032220670479376, 'samples': 17526144, 'steps': 91281, 'loss/train': 1.1045576333999634} 08/31/2021 05:48:05 - INFO - __main__ - Step 91283: {'lr': 0.00017031717671513397, 'samples': 17526336, 'steps': 91282, 'loss/train': 1.2453466653823853} 08/31/2021 05:48:06 - INFO - __main__ - Step 91284: {'lr': 0.00017031214676137808, 'samples': 17526528, 'steps': 91283, 'loss/train': 1.7543028593063354} 08/31/2021 05:48:06 - INFO - __main__ - Step 91285: {'lr': 0.00017030711684352828, 'samples': 17526720, 'steps': 91284, 'loss/train': 1.2002618312835693} 08/31/2021 05:48:07 - INFO - __main__ - Step 91286: {'lr': 0.00017030208696158685, 'samples': 17526912, 'steps': 91285, 'loss/train': 1.0652788877487183} 08/31/2021 05:48:08 - INFO - __main__ - Step 91287: {'lr': 0.0001702970571155561, 'samples': 17527104, 'steps': 91286, 'loss/train': 1.2997100353240967} 08/31/2021 05:48:08 - INFO - __main__ - Step 91288: {'lr': 0.00017029202730543824, 'samples': 17527296, 'steps': 91287, 'loss/train': 1.3115954399108887} 08/31/2021 05:48:09 - INFO - __main__ - Step 91289: {'lr': 0.00017028699753123558, 'samples': 17527488, 'steps': 91288, 'loss/train': 0.7126951813697815} 08/31/2021 05:48:09 - INFO - __main__ - Step 91290: {'lr': 0.00017028196779295034, 'samples': 17527680, 'steps': 91289, 'loss/train': 1.7981197834014893} 08/31/2021 05:48:09 - INFO - __main__ - Step 91291: {'lr': 0.00017027693809058486, 'samples': 17527872, 'steps': 91290, 'loss/train': 1.224229097366333} 08/31/2021 05:48:11 - INFO - __main__ - Step 91292: {'lr': 0.00017027190842414135, 'samples': 17528064, 'steps': 91291, 'loss/train': 0.714683473110199} 08/31/2021 05:48:11 - INFO - __main__ - Step 91293: {'lr': 0.00017026687879362207, 'samples': 17528256, 'steps': 91292, 'loss/train': 0.7864177823066711} 08/31/2021 05:48:12 - INFO - __main__ - Step 91294: {'lr': 0.00017026184919902932, 'samples': 17528448, 'steps': 91293, 'loss/train': 1.1457738876342773} 08/31/2021 05:48:12 - INFO - __main__ - Step 91295: {'lr': 0.00017025681964036546, 'samples': 17528640, 'steps': 91294, 'loss/train': 1.0948842763900757} 08/31/2021 05:48:12 - INFO - __main__ - Step 91296: {'lr': 0.00017025179011763254, 'samples': 17528832, 'steps': 91295, 'loss/train': 1.877705454826355} 08/31/2021 05:48:14 - INFO - __main__ - Step 91297: {'lr': 0.0001702467606308329, 'samples': 17529024, 'steps': 91296, 'loss/train': 0.6894670724868774} 08/31/2021 05:48:15 - INFO - __main__ - Step 91298: {'lr': 0.00017024173117996888, 'samples': 17529216, 'steps': 91297, 'loss/train': 1.5289630889892578} 08/31/2021 05:48:15 - INFO - __main__ - Step 91299: {'lr': 0.00017023670176504268, 'samples': 17529408, 'steps': 91298, 'loss/train': 1.3130102157592773} 08/31/2021 05:48:15 - INFO - __main__ - Step 91300: {'lr': 0.0001702316723860566, 'samples': 17529600, 'steps': 91299, 'loss/train': 1.3620270490646362} 08/31/2021 05:48:16 - INFO - __main__ - Step 91301: {'lr': 0.00017022664304301287, 'samples': 17529792, 'steps': 91300, 'loss/train': 1.7672240734100342} 08/31/2021 05:48:17 - INFO - __main__ - Step 91302: {'lr': 0.00017022161373591384, 'samples': 17529984, 'steps': 91301, 'loss/train': 2.070897102355957} 08/31/2021 05:48:18 - INFO - __main__ - Step 91303: {'lr': 0.0001702165844647617, 'samples': 17530176, 'steps': 91302, 'loss/train': 0.9236499071121216} 08/31/2021 05:48:18 - INFO - __main__ - Step 91304: {'lr': 0.00017021155522955873, 'samples': 17530368, 'steps': 91303, 'loss/train': 0.6336966753005981} 08/31/2021 05:48:18 - INFO - __main__ - Step 91305: {'lr': 0.00017020652603030718, 'samples': 17530560, 'steps': 91304, 'loss/train': 1.2280133962631226} 08/31/2021 05:48:19 - INFO - __main__ - Step 91306: {'lr': 0.00017020149686700937, 'samples': 17530752, 'steps': 91305, 'loss/train': 1.427353858947754} 08/31/2021 05:48:19 - INFO - __main__ - Step 91307: {'lr': 0.0001701964677396675, 'samples': 17530944, 'steps': 91306, 'loss/train': 1.646188735961914} 08/31/2021 05:48:21 - INFO - __main__ - Step 91308: {'lr': 0.00017019143864828402, 'samples': 17531136, 'steps': 91307, 'loss/train': 1.433630347251892} 08/31/2021 05:48:21 - INFO - __main__ - Step 91309: {'lr': 0.00017018640959286092, 'samples': 17531328, 'steps': 91308, 'loss/train': 1.5102397203445435} 08/31/2021 05:48:21 - INFO - __main__ - Step 91310: {'lr': 0.0001701813805734006, 'samples': 17531520, 'steps': 91309, 'loss/train': 1.1354496479034424} 08/31/2021 05:48:22 - INFO - __main__ - Step 91311: {'lr': 0.0001701763515899053, 'samples': 17531712, 'steps': 91310, 'loss/train': 0.09147045761346817} 08/31/2021 05:48:22 - INFO - __main__ - Step 91312: {'lr': 0.00017017132264237727, 'samples': 17531904, 'steps': 91311, 'loss/train': 1.051212191581726} 08/31/2021 05:48:24 - INFO - __main__ - Step 91313: {'lr': 0.00017016629373081888, 'samples': 17532096, 'steps': 91312, 'loss/train': 1.4107404947280884} 08/31/2021 05:48:24 - INFO - __main__ - Step 91314: {'lr': 0.0001701612648552323, 'samples': 17532288, 'steps': 91313, 'loss/train': 1.3497008085250854} 08/31/2021 05:48:24 - INFO - __main__ - Step 91315: {'lr': 0.0001701562360156198, 'samples': 17532480, 'steps': 91314, 'loss/train': 1.5314476490020752} 08/31/2021 05:48:25 - INFO - __main__ - Step 91316: {'lr': 0.00017015120721198371, 'samples': 17532672, 'steps': 91315, 'loss/train': 1.441654086112976} 08/31/2021 05:48:25 - INFO - __main__ - Step 91317: {'lr': 0.00017014617844432622, 'samples': 17532864, 'steps': 91316, 'loss/train': 0.888295590877533} 08/31/2021 05:48:27 - INFO - __main__ - Step 91318: {'lr': 0.00017014114971264965, 'samples': 17533056, 'steps': 91317, 'loss/train': 1.425864577293396} 08/31/2021 05:48:27 - INFO - __main__ - Step 91319: {'lr': 0.00017013612101695623, 'samples': 17533248, 'steps': 91318, 'loss/train': 1.1642035245895386} 08/31/2021 05:48:27 - INFO - __main__ - Step 91320: {'lr': 0.00017013109235724827, 'samples': 17533440, 'steps': 91319, 'loss/train': 0.7618164420127869} 08/31/2021 05:48:28 - INFO - __main__ - Step 91321: {'lr': 0.00017012606373352797, 'samples': 17533632, 'steps': 91320, 'loss/train': 0.5638982653617859} 08/31/2021 05:48:28 - INFO - __main__ - Step 91322: {'lr': 0.00017012103514579775, 'samples': 17533824, 'steps': 91321, 'loss/train': 1.344921350479126} 08/31/2021 05:48:30 - INFO - __main__ - Step 91323: {'lr': 0.00017011600659405969, 'samples': 17534016, 'steps': 91322, 'loss/train': 1.3640040159225464} 08/31/2021 05:48:30 - INFO - __main__ - Step 91324: {'lr': 0.00017011097807831607, 'samples': 17534208, 'steps': 91323, 'loss/train': 1.6247098445892334} 08/31/2021 05:48:30 - INFO - __main__ - Step 91325: {'lr': 0.00017010594959856922, 'samples': 17534400, 'steps': 91324, 'loss/train': 1.3892107009887695} 08/31/2021 05:48:31 - INFO - __main__ - Step 91326: {'lr': 0.00017010092115482143, 'samples': 17534592, 'steps': 91325, 'loss/train': 1.0003725290298462} 08/31/2021 05:48:31 - INFO - __main__ - Step 91327: {'lr': 0.0001700958927470749, 'samples': 17534784, 'steps': 91326, 'loss/train': 1.1661022901535034} 08/31/2021 05:48:33 - INFO - __main__ - Step 91328: {'lr': 0.00017009086437533194, 'samples': 17534976, 'steps': 91327, 'loss/train': 1.432029366493225} 08/31/2021 05:48:33 - INFO - __main__ - Step 91329: {'lr': 0.0001700858360395948, 'samples': 17535168, 'steps': 91328, 'loss/train': 1.3737760782241821} 08/31/2021 05:48:34 - INFO - __main__ - Step 91330: {'lr': 0.00017008080773986577, 'samples': 17535360, 'steps': 91329, 'loss/train': 0.5887100100517273} 08/31/2021 05:48:34 - INFO - __main__ - Step 91331: {'lr': 0.00017007577947614704, 'samples': 17535552, 'steps': 91330, 'loss/train': 0.09704574197530746} 08/31/2021 05:48:34 - INFO - __main__ - Step 91332: {'lr': 0.000170070751248441, 'samples': 17535744, 'steps': 91331, 'loss/train': 1.7224942445755005} 08/31/2021 05:48:35 - INFO - __main__ - Step 91333: {'lr': 0.00017006572305674987, 'samples': 17535936, 'steps': 91332, 'loss/train': 1.4602071046829224} 08/31/2021 05:48:37 - INFO - __main__ - Step 91334: {'lr': 0.00017006069490107584, 'samples': 17536128, 'steps': 91333, 'loss/train': 1.240134596824646} 08/31/2021 05:48:37 - INFO - __main__ - Step 91335: {'lr': 0.00017005566678142127, 'samples': 17536320, 'steps': 91334, 'loss/train': 0.867171049118042} 08/31/2021 05:48:38 - INFO - __main__ - Step 91336: {'lr': 0.00017005063869778833, 'samples': 17536512, 'steps': 91335, 'loss/train': 1.1093162298202515} 08/31/2021 05:48:38 - INFO - __main__ - Step 91337: {'lr': 0.00017004561065017934, 'samples': 17536704, 'steps': 91336, 'loss/train': 1.3848915100097656} 08/31/2021 05:48:38 - INFO - __main__ - Step 91338: {'lr': 0.00017004058263859657, 'samples': 17536896, 'steps': 91337, 'loss/train': 1.500885248184204} 08/31/2021 05:48:40 - INFO - __main__ - Step 91339: {'lr': 0.00017003555466304227, 'samples': 17537088, 'steps': 91338, 'loss/train': 1.5033072233200073} 08/31/2021 05:48:41 - INFO - __main__ - Step 91340: {'lr': 0.00017003052672351875, 'samples': 17537280, 'steps': 91339, 'loss/train': 1.1464381217956543} 08/31/2021 05:48:41 - INFO - __main__ - Step 91341: {'lr': 0.00017002549882002822, 'samples': 17537472, 'steps': 91340, 'loss/train': 0.857001543045044} 08/31/2021 05:48:42 - INFO - __main__ - Step 91342: {'lr': 0.00017002047095257295, 'samples': 17537664, 'steps': 91341, 'loss/train': 1.4473917484283447} 08/31/2021 05:48:42 - INFO - __main__ - Step 91343: {'lr': 0.00017001544312115522, 'samples': 17537856, 'steps': 91342, 'loss/train': 0.4370471239089966} 08/31/2021 05:48:43 - INFO - __main__ - Step 91344: {'lr': 0.00017001041532577736, 'samples': 17538048, 'steps': 91343, 'loss/train': 0.9387325048446655} 08/31/2021 05:48:45 - INFO - __main__ - Step 91345: {'lr': 0.00017000538756644151, 'samples': 17538240, 'steps': 91344, 'loss/train': 1.4024853706359863} 08/31/2021 05:48:45 - INFO - __main__ - Step 91346: {'lr': 0.00017000035984315003, 'samples': 17538432, 'steps': 91345, 'loss/train': 1.0455609560012817} 08/31/2021 05:48:46 - INFO - __main__ - Step 91347: {'lr': 0.00016999533215590512, 'samples': 17538624, 'steps': 91346, 'loss/train': 0.0413847342133522} 08/31/2021 05:48:46 - INFO - __main__ - Step 91348: {'lr': 0.0001699903045047091, 'samples': 17538816, 'steps': 91347, 'loss/train': 1.0204765796661377} 08/31/2021 05:48:46 - INFO - __main__ - Step 91349: {'lr': 0.00016998527688956425, 'samples': 17539008, 'steps': 91348, 'loss/train': 0.3792668879032135} 08/31/2021 05:48:47 - INFO - __main__ - Step 91350: {'lr': 0.00016998024931047273, 'samples': 17539200, 'steps': 91349, 'loss/train': 0.3305332064628601} 08/31/2021 05:48:48 - INFO - __main__ - Step 91351: {'lr': 0.0001699752217674369, 'samples': 17539392, 'steps': 91350, 'loss/train': 0.6065579056739807} 08/31/2021 05:48:49 - INFO - __main__ - Step 91352: {'lr': 0.000169970194260459, 'samples': 17539584, 'steps': 91351, 'loss/train': 1.5439130067825317} 08/31/2021 05:48:49 - INFO - __main__ - Step 91353: {'lr': 0.00016996516678954133, 'samples': 17539776, 'steps': 91352, 'loss/train': 1.4125715494155884} 08/31/2021 05:48:49 - INFO - __main__ - Step 91354: {'lr': 0.00016996013935468608, 'samples': 17539968, 'steps': 91353, 'loss/train': 1.9709993600845337} 08/31/2021 05:48:50 - INFO - __main__ - Step 91355: {'lr': 0.0001699551119558956, 'samples': 17540160, 'steps': 91354, 'loss/train': 1.1873455047607422} 08/31/2021 05:48:51 - INFO - __main__ - Step 91356: {'lr': 0.00016995008459317208, 'samples': 17540352, 'steps': 91355, 'loss/train': 1.1384563446044922} 08/31/2021 05:48:52 - INFO - __main__ - Step 91357: {'lr': 0.00016994505726651782, 'samples': 17540544, 'steps': 91356, 'loss/train': 0.775890588760376} 08/31/2021 05:48:52 - INFO - __main__ - Step 91358: {'lr': 0.00016994002997593505, 'samples': 17540736, 'steps': 91357, 'loss/train': 1.4153960943222046} 08/31/2021 05:48:52 - INFO - __main__ - Step 91359: {'lr': 0.0001699350027214261, 'samples': 17540928, 'steps': 91358, 'loss/train': 1.4344338178634644} 08/31/2021 05:48:53 - INFO - __main__ - Step 91360: {'lr': 0.00016992997550299322, 'samples': 17541120, 'steps': 91359, 'loss/train': 1.788774847984314} 08/31/2021 05:48:54 - INFO - __main__ - Step 91361: {'lr': 0.0001699249483206386, 'samples': 17541312, 'steps': 91360, 'loss/train': 1.2108567953109741} 08/31/2021 05:48:55 - INFO - __main__ - Step 91362: {'lr': 0.00016991992117436466, 'samples': 17541504, 'steps': 91361, 'loss/train': 1.3951683044433594} 08/31/2021 05:48:55 - INFO - __main__ - Step 91363: {'lr': 0.00016991489406417348, 'samples': 17541696, 'steps': 91362, 'loss/train': 1.3439780473709106} 08/31/2021 05:48:56 - INFO - __main__ - Step 91364: {'lr': 0.00016990986699006743, 'samples': 17541888, 'steps': 91363, 'loss/train': 0.6906851530075073} 08/31/2021 05:48:56 - INFO - __main__ - Step 91365: {'lr': 0.00016990483995204877, 'samples': 17542080, 'steps': 91364, 'loss/train': 1.0229424238204956} 08/31/2021 05:48:56 - INFO - __main__ - Step 91366: {'lr': 0.0001698998129501198, 'samples': 17542272, 'steps': 91365, 'loss/train': 1.5176688432693481} 08/31/2021 05:48:58 - INFO - __main__ - Step 91367: {'lr': 0.00016989478598428267, 'samples': 17542464, 'steps': 91366, 'loss/train': 1.6400749683380127} 08/31/2021 05:48:58 - INFO - __main__ - Step 91368: {'lr': 0.00016988975905453974, 'samples': 17542656, 'steps': 91367, 'loss/train': 1.6351065635681152} 08/31/2021 05:48:59 - INFO - __main__ - Step 91369: {'lr': 0.00016988473216089322, 'samples': 17542848, 'steps': 91368, 'loss/train': 1.1807550191879272} 08/31/2021 05:48:59 - INFO - __main__ - Step 91370: {'lr': 0.00016987970530334544, 'samples': 17543040, 'steps': 91369, 'loss/train': 1.291395664215088} 08/31/2021 05:48:59 - INFO - __main__ - Step 91371: {'lr': 0.00016987467848189857, 'samples': 17543232, 'steps': 91370, 'loss/train': 0.8143513202667236} 08/31/2021 05:49:01 - INFO - __main__ - Step 91372: {'lr': 0.000169869651696555, 'samples': 17543424, 'steps': 91371, 'loss/train': 1.2884101867675781} 08/31/2021 05:49:01 - INFO - __main__ - Step 91373: {'lr': 0.0001698646249473169, 'samples': 17543616, 'steps': 91372, 'loss/train': 1.6638318300247192} 08/31/2021 05:49:02 - INFO - __main__ - Step 91374: {'lr': 0.00016985959823418657, 'samples': 17543808, 'steps': 91373, 'loss/train': 0.8596237301826477} 08/31/2021 05:49:02 - INFO - __main__ - Step 91375: {'lr': 0.00016985457155716625, 'samples': 17544000, 'steps': 91374, 'loss/train': 0.6142308712005615} 08/31/2021 05:49:02 - INFO - __main__ - Step 91376: {'lr': 0.00016984954491625832, 'samples': 17544192, 'steps': 91375, 'loss/train': 1.4150645732879639} 08/31/2021 05:49:04 - INFO - __main__ - Step 91377: {'lr': 0.00016984451831146487, 'samples': 17544384, 'steps': 91376, 'loss/train': 1.4868963956832886} 08/31/2021 05:49:04 - INFO - __main__ - Step 91378: {'lr': 0.00016983949174278822, 'samples': 17544576, 'steps': 91377, 'loss/train': 1.2146750688552856} 08/31/2021 05:49:05 - INFO - __main__ - Step 91379: {'lr': 0.0001698344652102307, 'samples': 17544768, 'steps': 91378, 'loss/train': 0.909951388835907} 08/31/2021 05:49:05 - INFO - __main__ - Step 91380: {'lr': 0.0001698294387137945, 'samples': 17544960, 'steps': 91379, 'loss/train': 2.0648539066314697} 08/31/2021 05:49:05 - INFO - __main__ - Step 91381: {'lr': 0.0001698244122534819, 'samples': 17545152, 'steps': 91380, 'loss/train': 1.13325834274292} 08/31/2021 05:49:07 - INFO - __main__ - Step 91382: {'lr': 0.00016981938582929522, 'samples': 17545344, 'steps': 91381, 'loss/train': 1.0035892724990845} 08/31/2021 05:49:07 - INFO - __main__ - Step 91383: {'lr': 0.0001698143594412367, 'samples': 17545536, 'steps': 91382, 'loss/train': 1.4643886089324951} 08/31/2021 05:49:07 - INFO - __main__ - Step 91384: {'lr': 0.00016980933308930854, 'samples': 17545728, 'steps': 91383, 'loss/train': 1.4377561807632446} 08/31/2021 05:49:08 - INFO - __main__ - Step 91385: {'lr': 0.00016980430677351308, 'samples': 17545920, 'steps': 91384, 'loss/train': 0.3943841755390167} 08/31/2021 05:49:08 - INFO - __main__ - Step 91386: {'lr': 0.00016979928049385258, 'samples': 17546112, 'steps': 91385, 'loss/train': 1.3218812942504883} 08/31/2021 05:49:10 - INFO - __main__ - Step 91387: {'lr': 0.00016979425425032925, 'samples': 17546304, 'steps': 91386, 'loss/train': 1.4403477907180786} 08/31/2021 05:49:10 - INFO - __main__ - Step 91388: {'lr': 0.00016978922804294545, 'samples': 17546496, 'steps': 91387, 'loss/train': 0.8767483830451965} 08/31/2021 05:49:11 - INFO - __main__ - Step 91389: {'lr': 0.00016978420187170343, 'samples': 17546688, 'steps': 91388, 'loss/train': 0.8830411434173584} 08/31/2021 05:49:11 - INFO - __main__ - Step 91390: {'lr': 0.00016977917573660534, 'samples': 17546880, 'steps': 91389, 'loss/train': 1.2486809492111206} 08/31/2021 05:49:11 - INFO - __main__ - Step 91391: {'lr': 0.00016977414963765348, 'samples': 17547072, 'steps': 91390, 'loss/train': 1.2700997591018677} 08/31/2021 05:49:12 - INFO - __main__ - Step 91392: {'lr': 0.0001697691235748502, 'samples': 17547264, 'steps': 91391, 'loss/train': 1.3806027173995972} 08/31/2021 05:49:14 - INFO - __main__ - Step 91393: {'lr': 0.00016976409754819767, 'samples': 17547456, 'steps': 91392, 'loss/train': 2.073333740234375} 08/31/2021 05:49:14 - INFO - __main__ - Step 91394: {'lr': 0.0001697590715576982, 'samples': 17547648, 'steps': 91393, 'loss/train': 0.9348171353340149} 08/31/2021 05:49:14 - INFO - __main__ - Step 91395: {'lr': 0.00016975404560335412, 'samples': 17547840, 'steps': 91394, 'loss/train': 1.1286656856536865} 08/31/2021 05:49:15 - INFO - __main__ - Step 91396: {'lr': 0.00016974901968516758, 'samples': 17548032, 'steps': 91395, 'loss/train': 0.9479541182518005} 08/31/2021 05:49:15 - INFO - __main__ - Step 91397: {'lr': 0.00016974399380314086, 'samples': 17548224, 'steps': 91396, 'loss/train': 1.246535301208496} 08/31/2021 05:49:17 - INFO - __main__ - Step 91398: {'lr': 0.0001697389679572763, 'samples': 17548416, 'steps': 91397, 'loss/train': 1.0723148584365845} 08/31/2021 05:49:17 - INFO - __main__ - Step 91399: {'lr': 0.00016973394214757614, 'samples': 17548608, 'steps': 91398, 'loss/train': 0.02839229628443718} 08/31/2021 05:49:18 - INFO - __main__ - Step 91400: {'lr': 0.00016972891637404258, 'samples': 17548800, 'steps': 91399, 'loss/train': 0.04132167994976044} 08/31/2021 05:49:18 - INFO - __main__ - Step 91401: {'lr': 0.00016972389063667798, 'samples': 17548992, 'steps': 91400, 'loss/train': 1.323939323425293} 08/31/2021 05:49:18 - INFO - __main__ - Step 91402: {'lr': 0.0001697188649354846, 'samples': 17549184, 'steps': 91401, 'loss/train': 1.4610093832015991} 08/31/2021 05:49:19 - INFO - __main__ - Step 91403: {'lr': 0.00016971383927046464, 'samples': 17549376, 'steps': 91402, 'loss/train': 1.470297932624817} 08/31/2021 05:49:20 - INFO - __main__ - Step 91404: {'lr': 0.00016970881364162033, 'samples': 17549568, 'steps': 91403, 'loss/train': 1.4109845161437988} 08/31/2021 05:49:21 - INFO - __main__ - Step 91405: {'lr': 0.00016970378804895397, 'samples': 17549760, 'steps': 91404, 'loss/train': 0.3576775789260864} 08/31/2021 05:49:21 - INFO - __main__ - Step 91406: {'lr': 0.00016969876249246787, 'samples': 17549952, 'steps': 91405, 'loss/train': 0.9588830471038818} 08/31/2021 05:49:21 - INFO - __main__ - Step 91407: {'lr': 0.0001696937369721643, 'samples': 17550144, 'steps': 91406, 'loss/train': 1.721817135810852} 08/31/2021 05:49:22 - INFO - __main__ - Step 91408: {'lr': 0.00016968871148804543, 'samples': 17550336, 'steps': 91407, 'loss/train': 1.5620673894882202} 08/31/2021 05:49:23 - INFO - __main__ - Step 91409: {'lr': 0.00016968368604011364, 'samples': 17550528, 'steps': 91408, 'loss/train': 1.0306401252746582} 08/31/2021 05:49:24 - INFO - __main__ - Step 91410: {'lr': 0.0001696786606283711, 'samples': 17550720, 'steps': 91409, 'loss/train': 1.3535186052322388} 08/31/2021 05:49:24 - INFO - __main__ - Step 91411: {'lr': 0.00016967363525282014, 'samples': 17550912, 'steps': 91410, 'loss/train': 0.4780014157295227} 08/31/2021 05:49:24 - INFO - __main__ - Step 91412: {'lr': 0.000169668609913463, 'samples': 17551104, 'steps': 91411, 'loss/train': 0.9718641638755798} 08/31/2021 05:49:25 - INFO - __main__ - Step 91413: {'lr': 0.00016966358461030195, 'samples': 17551296, 'steps': 91412, 'loss/train': 0.28973981738090515} 08/31/2021 05:49:26 - INFO - __main__ - Step 91414: {'lr': 0.00016965855934333925, 'samples': 17551488, 'steps': 91413, 'loss/train': 1.477731704711914} 08/31/2021 05:49:27 - INFO - __main__ - Step 91415: {'lr': 0.00016965353411257713, 'samples': 17551680, 'steps': 91414, 'loss/train': 0.6798974275588989} 08/31/2021 05:49:27 - INFO - __main__ - Step 91416: {'lr': 0.00016964850891801802, 'samples': 17551872, 'steps': 91415, 'loss/train': 1.042907476425171} 08/31/2021 05:49:28 - INFO - __main__ - Step 91417: {'lr': 0.00016964348375966395, 'samples': 17552064, 'steps': 91416, 'loss/train': 1.3899264335632324} 08/31/2021 05:49:28 - INFO - __main__ - Step 91418: {'lr': 0.0001696384586375173, 'samples': 17552256, 'steps': 91417, 'loss/train': 1.0051177740097046} 08/31/2021 05:49:29 - INFO - __main__ - Step 91419: {'lr': 0.00016963343355158028, 'samples': 17552448, 'steps': 91418, 'loss/train': 1.0549428462982178} 08/31/2021 05:49:30 - INFO - __main__ - Step 91420: {'lr': 0.00016962840850185524, 'samples': 17552640, 'steps': 91419, 'loss/train': 0.9110798239707947} 08/31/2021 05:49:30 - INFO - __main__ - Step 91421: {'lr': 0.00016962338348834436, 'samples': 17552832, 'steps': 91420, 'loss/train': 0.7335741519927979} 08/31/2021 05:49:30 - INFO - __main__ - Step 91422: {'lr': 0.00016961835851104996, 'samples': 17553024, 'steps': 91421, 'loss/train': 0.7384383082389832} 08/31/2021 05:49:31 - INFO - __main__ - Step 91423: {'lr': 0.00016961333356997426, 'samples': 17553216, 'steps': 91422, 'loss/train': 0.7187880873680115} 08/31/2021 05:49:32 - INFO - __main__ - Step 91424: {'lr': 0.0001696083086651196, 'samples': 17553408, 'steps': 91423, 'loss/train': 1.3286486864089966} 08/31/2021 05:49:33 - INFO - __main__ - Step 91425: {'lr': 0.00016960328379648818, 'samples': 17553600, 'steps': 91424, 'loss/train': 1.5120115280151367} 08/31/2021 05:49:33 - INFO - __main__ - Step 91426: {'lr': 0.00016959825896408227, 'samples': 17553792, 'steps': 91425, 'loss/train': 1.4880733489990234} 08/31/2021 05:49:33 - INFO - __main__ - Step 91427: {'lr': 0.00016959323416790414, 'samples': 17553984, 'steps': 91426, 'loss/train': 1.3771607875823975} 08/31/2021 05:49:34 - INFO - __main__ - Step 91428: {'lr': 0.00016958820940795604, 'samples': 17554176, 'steps': 91427, 'loss/train': 0.9587509036064148} 08/31/2021 05:49:35 - INFO - __main__ - Step 91429: {'lr': 0.00016958318468424043, 'samples': 17554368, 'steps': 91428, 'loss/train': 0.6322752237319946} 08/31/2021 05:49:36 - INFO - __main__ - Step 91430: {'lr': 0.00016957815999675923, 'samples': 17554560, 'steps': 91429, 'loss/train': 1.1914613246917725} 08/31/2021 05:49:36 - INFO - __main__ - Step 91431: {'lr': 0.0001695731353455149, 'samples': 17554752, 'steps': 91430, 'loss/train': 1.658683180809021} 08/31/2021 05:49:36 - INFO - __main__ - Step 91432: {'lr': 0.00016956811073050963, 'samples': 17554944, 'steps': 91431, 'loss/train': 1.2796744108200073} 08/31/2021 05:49:37 - INFO - __main__ - Step 91433: {'lr': 0.00016956308615174575, 'samples': 17555136, 'steps': 91432, 'loss/train': 1.4406778812408447} 08/31/2021 05:49:37 - INFO - __main__ - Step 91434: {'lr': 0.00016955806160922553, 'samples': 17555328, 'steps': 91433, 'loss/train': 1.0909595489501953} 08/31/2021 05:49:39 - INFO - __main__ - Step 91435: {'lr': 0.00016955303710295116, 'samples': 17555520, 'steps': 91434, 'loss/train': 0.9877644777297974} 08/31/2021 05:49:39 - INFO - __main__ - Step 91436: {'lr': 0.00016954801263292498, 'samples': 17555712, 'steps': 91435, 'loss/train': 1.1587269306182861} 08/31/2021 05:49:40 - INFO - __main__ - Step 91437: {'lr': 0.0001695429881991492, 'samples': 17555904, 'steps': 91436, 'loss/train': 1.1825274229049683} 08/31/2021 05:49:40 - INFO - __main__ - Step 91438: {'lr': 0.00016953796380162614, 'samples': 17556096, 'steps': 91437, 'loss/train': 1.4064127206802368} 08/31/2021 05:49:40 - INFO - __main__ - Step 91439: {'lr': 0.00016953293944035801, 'samples': 17556288, 'steps': 91438, 'loss/train': 1.460370421409607} 08/31/2021 05:49:42 - INFO - __main__ - Step 91440: {'lr': 0.0001695279151153471, 'samples': 17556480, 'steps': 91439, 'loss/train': 0.46564537286758423} 08/31/2021 05:49:42 - INFO - __main__ - Step 91441: {'lr': 0.00016952289082659567, 'samples': 17556672, 'steps': 91440, 'loss/train': 1.1715965270996094} 08/31/2021 05:49:42 - INFO - __main__ - Step 91442: {'lr': 0.000169517866574106, 'samples': 17556864, 'steps': 91441, 'loss/train': 1.078773021697998} 08/31/2021 05:49:43 - INFO - __main__ - Step 91443: {'lr': 0.00016951284235788041, 'samples': 17557056, 'steps': 91442, 'loss/train': 1.1598222255706787} 08/31/2021 05:49:43 - INFO - __main__ - Step 91444: {'lr': 0.00016950781817792103, 'samples': 17557248, 'steps': 91443, 'loss/train': 1.2079423666000366} 08/31/2021 05:49:45 - INFO - __main__ - Step 91445: {'lr': 0.00016950279403423014, 'samples': 17557440, 'steps': 91444, 'loss/train': 1.7341734170913696} 08/31/2021 05:49:46 - INFO - __main__ - Step 91446: {'lr': 0.00016949776992681009, 'samples': 17557632, 'steps': 91445, 'loss/train': 0.8111395835876465} 08/31/2021 05:49:46 - INFO - __main__ - Step 91447: {'lr': 0.00016949274585566308, 'samples': 17557824, 'steps': 91446, 'loss/train': 1.0065897703170776} 08/31/2021 05:49:47 - INFO - __main__ - Step 91448: {'lr': 0.00016948772182079138, 'samples': 17558016, 'steps': 91447, 'loss/train': 1.4258205890655518} 08/31/2021 05:49:47 - INFO - __main__ - Step 91449: {'lr': 0.0001694826978221973, 'samples': 17558208, 'steps': 91448, 'loss/train': 1.3883018493652344} 08/31/2021 05:49:48 - INFO - __main__ - Step 91450: {'lr': 0.00016947767385988306, 'samples': 17558400, 'steps': 91449, 'loss/train': 0.6359497308731079} 08/31/2021 05:49:49 - INFO - __main__ - Step 91451: {'lr': 0.00016947264993385093, 'samples': 17558592, 'steps': 91450, 'loss/train': 1.3114092350006104} 08/31/2021 05:49:49 - INFO - __main__ - Step 91452: {'lr': 0.00016946762604410322, 'samples': 17558784, 'steps': 91451, 'loss/train': 1.0317999124526978} 08/31/2021 05:49:50 - INFO - __main__ - Step 91453: {'lr': 0.0001694626021906421, 'samples': 17558976, 'steps': 91452, 'loss/train': 1.0093989372253418} 08/31/2021 05:49:50 - INFO - __main__ - Step 91454: {'lr': 0.0001694575783734699, 'samples': 17559168, 'steps': 91453, 'loss/train': 1.1752532720565796} 08/31/2021 05:49:51 - INFO - __main__ - Step 91455: {'lr': 0.0001694525545925889, 'samples': 17559360, 'steps': 91454, 'loss/train': 1.425511121749878} 08/31/2021 05:49:52 - INFO - __main__ - Step 91456: {'lr': 0.00016944753084800144, 'samples': 17559552, 'steps': 91455, 'loss/train': 1.6813952922821045} 08/31/2021 05:49:52 - INFO - __main__ - Step 91457: {'lr': 0.00016944250713970955, 'samples': 17559744, 'steps': 91456, 'loss/train': 1.3288819789886475} 08/31/2021 05:49:53 - INFO - __main__ - Step 91458: {'lr': 0.00016943748346771563, 'samples': 17559936, 'steps': 91457, 'loss/train': 1.3665099143981934} 08/31/2021 05:49:53 - INFO - __main__ - Step 91459: {'lr': 0.00016943245983202195, 'samples': 17560128, 'steps': 91458, 'loss/train': 1.5503877401351929} 08/31/2021 05:49:54 - INFO - __main__ - Step 91460: {'lr': 0.00016942743623263074, 'samples': 17560320, 'steps': 91459, 'loss/train': 0.5828975439071655} 08/31/2021 05:49:55 - INFO - __main__ - Step 91461: {'lr': 0.0001694224126695443, 'samples': 17560512, 'steps': 91460, 'loss/train': 1.3572925329208374} 08/31/2021 05:49:55 - INFO - __main__ - Step 91462: {'lr': 0.00016941738914276488, 'samples': 17560704, 'steps': 91461, 'loss/train': 0.7594534158706665} 08/31/2021 05:49:56 - INFO - __main__ - Step 91463: {'lr': 0.00016941236565229474, 'samples': 17560896, 'steps': 91462, 'loss/train': 1.523589015007019} 08/31/2021 05:49:56 - INFO - __main__ - Step 91464: {'lr': 0.00016940734219813615, 'samples': 17561088, 'steps': 91463, 'loss/train': 1.0915460586547852} 08/31/2021 05:49:58 - INFO - __main__ - Step 91465: {'lr': 0.00016940231878029134, 'samples': 17561280, 'steps': 91464, 'loss/train': 0.9862818121910095} 08/31/2021 05:49:58 - INFO - __main__ - Step 91466: {'lr': 0.00016939729539876264, 'samples': 17561472, 'steps': 91465, 'loss/train': 1.2935301065444946} 08/31/2021 05:49:59 - INFO - __main__ - Step 91467: {'lr': 0.0001693922720535523, 'samples': 17561664, 'steps': 91466, 'loss/train': 1.2685145139694214} 08/31/2021 05:49:59 - INFO - __main__ - Step 91468: {'lr': 0.0001693872487446625, 'samples': 17561856, 'steps': 91467, 'loss/train': 1.2421070337295532} 08/31/2021 05:50:00 - INFO - __main__ - Step 91469: {'lr': 0.0001693822254720956, 'samples': 17562048, 'steps': 91468, 'loss/train': 1.0772178173065186} 08/31/2021 05:50:00 - INFO - __main__ - Step 91470: {'lr': 0.00016937720223585384, 'samples': 17562240, 'steps': 91469, 'loss/train': 0.8903568983078003} 08/31/2021 05:50:02 - INFO - __main__ - Step 91471: {'lr': 0.00016937217903593944, 'samples': 17562432, 'steps': 91470, 'loss/train': 0.5818225741386414} 08/31/2021 05:50:02 - INFO - __main__ - Step 91472: {'lr': 0.00016936715587235465, 'samples': 17562624, 'steps': 91471, 'loss/train': 0.9906777143478394} 08/31/2021 05:50:03 - INFO - __main__ - Step 91473: {'lr': 0.00016936213274510183, 'samples': 17562816, 'steps': 91472, 'loss/train': 1.0928184986114502} 08/31/2021 05:50:03 - INFO - __main__ - Step 91474: {'lr': 0.00016935710965418317, 'samples': 17563008, 'steps': 91473, 'loss/train': 0.4803248345851898} 08/31/2021 05:50:03 - INFO - __main__ - Step 91475: {'lr': 0.00016935208659960094, 'samples': 17563200, 'steps': 91474, 'loss/train': 0.14246834814548492} 08/31/2021 05:50:04 - INFO - __main__ - Step 91476: {'lr': 0.0001693470635813574, 'samples': 17563392, 'steps': 91475, 'loss/train': 0.020449010655283928} 08/31/2021 05:50:04 - INFO - __main__ - Step 91477: {'lr': 0.00016934204059945485, 'samples': 17563584, 'steps': 91476, 'loss/train': 0.6092349290847778} 08/31/2021 05:50:06 - INFO - __main__ - Step 91478: {'lr': 0.00016933701765389558, 'samples': 17563776, 'steps': 91477, 'loss/train': 1.2502822875976562} 08/31/2021 05:50:06 - INFO - __main__ - Step 91479: {'lr': 0.00016933199474468175, 'samples': 17563968, 'steps': 91478, 'loss/train': 0.4973326027393341} 08/31/2021 05:50:07 - INFO - __main__ - Step 91480: {'lr': 0.0001693269718718157, 'samples': 17564160, 'steps': 91479, 'loss/train': 0.9016074538230896} 08/31/2021 05:50:07 - INFO - __main__ - Step 91481: {'lr': 0.00016932194903529965, 'samples': 17564352, 'steps': 91480, 'loss/train': 0.7897214293479919} 08/31/2021 05:50:07 - INFO - __main__ - Step 91482: {'lr': 0.0001693169262351359, 'samples': 17564544, 'steps': 91481, 'loss/train': 0.5338445901870728} 08/31/2021 05:50:09 - INFO - __main__ - Step 91483: {'lr': 0.00016931190347132676, 'samples': 17564736, 'steps': 91482, 'loss/train': 0.031952712684869766} 08/31/2021 05:50:09 - INFO - __main__ - Step 91484: {'lr': 0.00016930688074387435, 'samples': 17564928, 'steps': 91483, 'loss/train': 1.0514787435531616} 08/31/2021 05:50:10 - INFO - __main__ - Step 91485: {'lr': 0.00016930185805278102, 'samples': 17565120, 'steps': 91484, 'loss/train': 0.8765170574188232} 08/31/2021 05:50:10 - INFO - __main__ - Step 91486: {'lr': 0.000169296835398049, 'samples': 17565312, 'steps': 91485, 'loss/train': 1.0839110612869263} 08/31/2021 05:50:10 - INFO - __main__ - Step 91487: {'lr': 0.00016929181277968065, 'samples': 17565504, 'steps': 91486, 'loss/train': 1.1388235092163086} 08/31/2021 05:50:12 - INFO - __main__ - Step 91488: {'lr': 0.00016928679019767812, 'samples': 17565696, 'steps': 91487, 'loss/train': 0.9620020389556885} 08/31/2021 05:50:12 - INFO - __main__ - Step 91489: {'lr': 0.0001692817676520438, 'samples': 17565888, 'steps': 91488, 'loss/train': 1.1122316122055054} 08/31/2021 05:50:13 - INFO - __main__ - Step 91490: {'lr': 0.00016927674514277978, 'samples': 17566080, 'steps': 91489, 'loss/train': 1.979467511177063} 08/31/2021 05:50:13 - INFO - __main__ - Step 91491: {'lr': 0.00016927172266988842, 'samples': 17566272, 'steps': 91490, 'loss/train': 0.8451074361801147} 08/31/2021 05:50:13 - INFO - __main__ - Step 91492: {'lr': 0.000169266700233372, 'samples': 17566464, 'steps': 91491, 'loss/train': 0.7311586141586304} 08/31/2021 05:50:15 - INFO - __main__ - Step 91493: {'lr': 0.00016926167783323272, 'samples': 17566656, 'steps': 91492, 'loss/train': 1.2544031143188477} 08/31/2021 05:50:15 - INFO - __main__ - Step 91494: {'lr': 0.0001692566554694729, 'samples': 17566848, 'steps': 91493, 'loss/train': 1.168348789215088} 08/31/2021 05:50:16 - INFO - __main__ - Step 91495: {'lr': 0.0001692516331420948, 'samples': 17567040, 'steps': 91494, 'loss/train': 1.2890160083770752} 08/31/2021 05:50:16 - INFO - __main__ - Step 91496: {'lr': 0.00016924661085110064, 'samples': 17567232, 'steps': 91495, 'loss/train': 1.1132999658584595} 08/31/2021 05:50:16 - INFO - __main__ - Step 91497: {'lr': 0.0001692415885964928, 'samples': 17567424, 'steps': 91496, 'loss/train': 1.7270991802215576} 08/31/2021 05:50:18 - INFO - __main__ - Step 91498: {'lr': 0.00016923656637827337, 'samples': 17567616, 'steps': 91497, 'loss/train': 0.47937726974487305} 08/31/2021 05:50:19 - INFO - __main__ - Step 91499: {'lr': 0.0001692315441964447, 'samples': 17567808, 'steps': 91498, 'loss/train': 0.9060978293418884} 08/31/2021 05:50:19 - INFO - __main__ - Step 91500: {'lr': 0.00016922652205100913, 'samples': 17568000, 'steps': 91499, 'loss/train': 1.3839325904846191} 08/31/2021 05:50:20 - INFO - __main__ - Step 91501: {'lr': 0.0001692214999419688, 'samples': 17568192, 'steps': 91500, 'loss/train': 1.3121511936187744} 08/31/2021 05:50:20 - INFO - __main__ - Step 91502: {'lr': 0.00016921647786932595, 'samples': 17568384, 'steps': 91501, 'loss/train': 1.3974684476852417} 08/31/2021 05:50:20 - INFO - __main__ - Step 91503: {'lr': 0.00016921145583308295, 'samples': 17568576, 'steps': 91502, 'loss/train': 1.7802003622055054} 08/31/2021 05:50:22 - INFO - __main__ - Step 91504: {'lr': 0.00016920643383324201, 'samples': 17568768, 'steps': 91503, 'loss/train': 3.7630157470703125} 08/31/2021 05:50:22 - INFO - __main__ - Step 91505: {'lr': 0.00016920141186980541, 'samples': 17568960, 'steps': 91504, 'loss/train': 0.6659139394760132} 08/31/2021 05:50:23 - INFO - __main__ - Step 91506: {'lr': 0.00016919638994277543, 'samples': 17569152, 'steps': 91505, 'loss/train': 1.2978274822235107} 08/31/2021 05:50:23 - INFO - __main__ - Step 91507: {'lr': 0.00016919136805215428, 'samples': 17569344, 'steps': 91506, 'loss/train': 1.4377830028533936} 08/31/2021 05:50:23 - INFO - __main__ - Step 91508: {'lr': 0.00016918634619794427, 'samples': 17569536, 'steps': 91507, 'loss/train': 0.5198234915733337} 08/31/2021 05:50:25 - INFO - __main__ - Step 91509: {'lr': 0.0001691813243801476, 'samples': 17569728, 'steps': 91508, 'loss/train': 0.19594483077526093} 08/31/2021 05:50:26 - INFO - __main__ - Step 91510: {'lr': 0.00016917630259876668, 'samples': 17569920, 'steps': 91509, 'loss/train': 1.419993281364441} 08/31/2021 05:50:26 - INFO - __main__ - Step 91511: {'lr': 0.00016917128085380367, 'samples': 17570112, 'steps': 91510, 'loss/train': 1.3328639268875122} 08/31/2021 05:50:26 - INFO - __main__ - Step 91512: {'lr': 0.00016916625914526075, 'samples': 17570304, 'steps': 91511, 'loss/train': 1.2802412509918213} 08/31/2021 05:50:27 - INFO - __main__ - Step 91513: {'lr': 0.0001691612374731403, 'samples': 17570496, 'steps': 91512, 'loss/train': 1.433781385421753} 08/31/2021 05:50:29 - INFO - __main__ - Step 91514: {'lr': 0.00016915621583744452, 'samples': 17570688, 'steps': 91513, 'loss/train': 1.9040863513946533} 08/31/2021 05:50:29 - INFO - __main__ - Step 91515: {'lr': 0.0001691511942381757, 'samples': 17570880, 'steps': 91514, 'loss/train': 1.31661057472229} 08/31/2021 05:50:29 - INFO - __main__ - Step 91516: {'lr': 0.00016914617267533617, 'samples': 17571072, 'steps': 91515, 'loss/train': 1.077660322189331} 08/31/2021 05:50:30 - INFO - __main__ - Step 91517: {'lr': 0.00016914115114892805, 'samples': 17571264, 'steps': 91516, 'loss/train': 1.037528395652771} 08/31/2021 05:50:30 - INFO - __main__ - Step 91518: {'lr': 0.0001691361296589537, 'samples': 17571456, 'steps': 91517, 'loss/train': 1.1429821252822876} 08/31/2021 05:50:31 - INFO - __main__ - Step 91519: {'lr': 0.00016913110820541538, 'samples': 17571648, 'steps': 91518, 'loss/train': 1.2615803480148315} 08/31/2021 05:50:32 - INFO - __main__ - Step 91520: {'lr': 0.00016912608678831532, 'samples': 17571840, 'steps': 91519, 'loss/train': 1.1856540441513062} 08/31/2021 05:50:32 - INFO - __main__ - Step 91521: {'lr': 0.00016912106540765582, 'samples': 17572032, 'steps': 91520, 'loss/train': 1.4839015007019043} 08/31/2021 05:50:33 - INFO - __main__ - Step 91522: {'lr': 0.0001691160440634391, 'samples': 17572224, 'steps': 91521, 'loss/train': 0.9179629683494568} 08/31/2021 05:50:33 - INFO - __main__ - Step 91523: {'lr': 0.00016911102275566752, 'samples': 17572416, 'steps': 91522, 'loss/train': 1.527716040611267} 08/31/2021 05:50:33 - INFO - __main__ - Step 91524: {'lr': 0.0001691060014843432, 'samples': 17572608, 'steps': 91523, 'loss/train': 0.5242365598678589} 08/31/2021 05:50:35 - INFO - __main__ - Step 91525: {'lr': 0.00016910098024946847, 'samples': 17572800, 'steps': 91524, 'loss/train': 0.9602606296539307} 08/31/2021 05:50:35 - INFO - __main__ - Step 91526: {'lr': 0.00016909595905104558, 'samples': 17572992, 'steps': 91525, 'loss/train': 1.0545936822891235} 08/31/2021 05:50:36 - INFO - __main__ - Step 91527: {'lr': 0.00016909093788907678, 'samples': 17573184, 'steps': 91526, 'loss/train': 0.4940008521080017} 08/31/2021 05:50:36 - INFO - __main__ - Step 91528: {'lr': 0.0001690859167635644, 'samples': 17573376, 'steps': 91527, 'loss/train': 0.9966353178024292} 08/31/2021 05:50:36 - INFO - __main__ - Step 91529: {'lr': 0.0001690808956745106, 'samples': 17573568, 'steps': 91528, 'loss/train': 1.1148664951324463} 08/31/2021 05:50:38 - INFO - __main__ - Step 91530: {'lr': 0.00016907587462191773, 'samples': 17573760, 'steps': 91529, 'loss/train': 1.2550941705703735} 08/31/2021 05:50:38 - INFO - __main__ - Step 91531: {'lr': 0.00016907085360578803, 'samples': 17573952, 'steps': 91530, 'loss/train': 1.2162920236587524} 08/31/2021 05:50:39 - INFO - __main__ - Step 91532: {'lr': 0.00016906583262612374, 'samples': 17574144, 'steps': 91531, 'loss/train': 1.1831241846084595} 08/31/2021 05:50:39 - INFO - __main__ - Step 91533: {'lr': 0.00016906081168292715, 'samples': 17574336, 'steps': 91532, 'loss/train': 1.3396682739257812} 08/31/2021 05:50:39 - INFO - __main__ - Step 91534: {'lr': 0.00016905579077620048, 'samples': 17574528, 'steps': 91533, 'loss/train': 0.7392792105674744} 08/31/2021 05:50:41 - INFO - __main__ - Step 91535: {'lr': 0.00016905076990594606, 'samples': 17574720, 'steps': 91534, 'loss/train': 1.2155550718307495} 08/31/2021 05:50:41 - INFO - __main__ - Step 91536: {'lr': 0.0001690457490721661, 'samples': 17574912, 'steps': 91535, 'loss/train': 0.7318831086158752} 08/31/2021 05:50:42 - INFO - __main__ - Step 91537: {'lr': 0.000169040728274863, 'samples': 17575104, 'steps': 91536, 'loss/train': 0.604024350643158} 08/31/2021 05:50:42 - INFO - __main__ - Step 91538: {'lr': 0.00016903570751403873, 'samples': 17575296, 'steps': 91537, 'loss/train': 1.41647207736969} 08/31/2021 05:50:43 - INFO - __main__ - Step 91539: {'lr': 0.0001690306867896958, 'samples': 17575488, 'steps': 91538, 'loss/train': 1.5541660785675049} 08/31/2021 05:50:43 - INFO - __main__ - Step 91540: {'lr': 0.00016902566610183634, 'samples': 17575680, 'steps': 91539, 'loss/train': 0.38456833362579346} 08/31/2021 05:50:45 - INFO - __main__ - Step 91541: {'lr': 0.0001690206454504627, 'samples': 17575872, 'steps': 91540, 'loss/train': 0.20919464528560638} 08/31/2021 05:50:45 - INFO - __main__ - Step 91542: {'lr': 0.00016901562483557708, 'samples': 17576064, 'steps': 91541, 'loss/train': 0.01605714112520218} 08/31/2021 05:50:46 - INFO - __main__ - Step 91543: {'lr': 0.0001690106042571818, 'samples': 17576256, 'steps': 91542, 'loss/train': 1.2977031469345093} 08/31/2021 05:50:46 - INFO - __main__ - Step 91544: {'lr': 0.00016900558371527906, 'samples': 17576448, 'steps': 91543, 'loss/train': 1.2110893726348877} 08/31/2021 05:50:46 - INFO - __main__ - Step 91545: {'lr': 0.00016900056320987117, 'samples': 17576640, 'steps': 91544, 'loss/train': 1.511946439743042} 08/31/2021 05:50:47 - INFO - __main__ - Step 91546: {'lr': 0.00016899554274096035, 'samples': 17576832, 'steps': 91545, 'loss/train': 0.7680003643035889} 08/31/2021 05:50:48 - INFO - __main__ - Step 91547: {'lr': 0.00016899052230854892, 'samples': 17577024, 'steps': 91546, 'loss/train': 1.3596817255020142} 08/31/2021 05:50:49 - INFO - __main__ - Step 91548: {'lr': 0.0001689855019126391, 'samples': 17577216, 'steps': 91547, 'loss/train': 0.16125920414924622} 08/31/2021 05:50:49 - INFO - __main__ - Step 91549: {'lr': 0.00016898048155323313, 'samples': 17577408, 'steps': 91548, 'loss/train': 1.0810186862945557} 08/31/2021 05:50:50 - INFO - __main__ - Step 91550: {'lr': 0.00016897546123033347, 'samples': 17577600, 'steps': 91549, 'loss/train': 0.6952499151229858} 08/31/2021 05:50:50 - INFO - __main__ - Step 91551: {'lr': 0.0001689704409439421, 'samples': 17577792, 'steps': 91550, 'loss/train': 0.10718467831611633} 08/31/2021 05:50:50 - INFO - __main__ - Step 91552: {'lr': 0.0001689654206940614, 'samples': 17577984, 'steps': 91551, 'loss/train': 0.016831660643219948} 08/31/2021 05:50:52 - INFO - __main__ - Step 91553: {'lr': 0.00016896040048069362, 'samples': 17578176, 'steps': 91552, 'loss/train': 1.1789271831512451} 08/31/2021 05:50:53 - INFO - __main__ - Step 91554: {'lr': 0.000168955380303841, 'samples': 17578368, 'steps': 91553, 'loss/train': 1.4794460535049438} 08/31/2021 05:50:53 - INFO - __main__ - Step 91555: {'lr': 0.00016895036016350589, 'samples': 17578560, 'steps': 91554, 'loss/train': 1.3978660106658936} 08/31/2021 05:50:53 - INFO - __main__ - Step 91556: {'lr': 0.00016894534005969044, 'samples': 17578752, 'steps': 91555, 'loss/train': 0.3426051735877991} 08/31/2021 05:50:54 - INFO - __main__ - Step 91557: {'lr': 0.00016894031999239702, 'samples': 17578944, 'steps': 91556, 'loss/train': 1.167972445487976} 08/31/2021 05:50:56 - INFO - __main__ - Step 91558: {'lr': 0.00016893529996162782, 'samples': 17579136, 'steps': 91557, 'loss/train': 1.653528094291687} 08/31/2021 05:50:56 - INFO - __main__ - Step 91559: {'lr': 0.0001689302799673851, 'samples': 17579328, 'steps': 91558, 'loss/train': 1.0998860597610474} 08/31/2021 05:50:57 - INFO - __main__ - Step 91560: {'lr': 0.00016892526000967118, 'samples': 17579520, 'steps': 91559, 'loss/train': 0.8321914076805115} 08/31/2021 05:50:57 - INFO - __main__ - Step 91561: {'lr': 0.00016892024008848826, 'samples': 17579712, 'steps': 91560, 'loss/train': 0.7430253028869629} 08/31/2021 05:50:57 - INFO - __main__ - Step 91562: {'lr': 0.00016891522020383865, 'samples': 17579904, 'steps': 91561, 'loss/train': 0.0655723437666893} 08/31/2021 05:50:59 - INFO - __main__ - Step 91563: {'lr': 0.0001689102003557246, 'samples': 17580096, 'steps': 91562, 'loss/train': 0.7818594574928284} 08/31/2021 05:50:59 - INFO - __main__ - Step 91564: {'lr': 0.00016890518054414843, 'samples': 17580288, 'steps': 91563, 'loss/train': 1.2452784776687622} 08/31/2021 05:51:00 - INFO - __main__ - Step 91565: {'lr': 0.00016890016076911228, 'samples': 17580480, 'steps': 91564, 'loss/train': 0.9457087516784668} 08/31/2021 05:51:00 - INFO - __main__ - Step 91566: {'lr': 0.00016889514103061843, 'samples': 17580672, 'steps': 91565, 'loss/train': 1.205485224723816} 08/31/2021 05:51:00 - INFO - __main__ - Step 91567: {'lr': 0.0001688901213286692, 'samples': 17580864, 'steps': 91566, 'loss/train': 0.03715650364756584} 08/31/2021 05:51:02 - INFO - __main__ - Step 91568: {'lr': 0.00016888510166326683, 'samples': 17581056, 'steps': 91567, 'loss/train': 1.1667308807373047} 08/31/2021 05:51:02 - INFO - __main__ - Step 91569: {'lr': 0.00016888008203441352, 'samples': 17581248, 'steps': 91568, 'loss/train': 1.0607918500900269} 08/31/2021 05:51:03 - INFO - __main__ - Step 91570: {'lr': 0.00016887506244211165, 'samples': 17581440, 'steps': 91569, 'loss/train': 1.2897213697433472} 08/31/2021 05:51:03 - INFO - __main__ - Step 91571: {'lr': 0.00016887004288636343, 'samples': 17581632, 'steps': 91570, 'loss/train': 0.6768883466720581} 08/31/2021 05:51:03 - INFO - __main__ - Step 91572: {'lr': 0.00016886502336717108, 'samples': 17581824, 'steps': 91571, 'loss/train': 1.4377409219741821} 08/31/2021 05:51:04 - INFO - __main__ - Step 91573: {'lr': 0.00016886000388453693, 'samples': 17582016, 'steps': 91572, 'loss/train': 0.7450218796730042} 08/31/2021 05:51:05 - INFO - __main__ - Step 91574: {'lr': 0.0001688549844384632, 'samples': 17582208, 'steps': 91573, 'loss/train': 0.754762589931488} 08/31/2021 05:51:06 - INFO - __main__ - Step 91575: {'lr': 0.00016884996502895217, 'samples': 17582400, 'steps': 91574, 'loss/train': 1.0591334104537964} 08/31/2021 05:51:06 - INFO - __main__ - Step 91576: {'lr': 0.00016884494565600608, 'samples': 17582592, 'steps': 91575, 'loss/train': 0.7747682929039001} 08/31/2021 05:51:06 - INFO - __main__ - Step 91577: {'lr': 0.00016883992631962731, 'samples': 17582784, 'steps': 91576, 'loss/train': 1.0088950395584106} 08/31/2021 05:51:07 - INFO - __main__ - Step 91578: {'lr': 0.0001688349070198179, 'samples': 17582976, 'steps': 91577, 'loss/train': 0.9683976173400879} 08/31/2021 05:51:08 - INFO - __main__ - Step 91579: {'lr': 0.00016882988775658025, 'samples': 17583168, 'steps': 91578, 'loss/train': 0.052015725523233414} 08/31/2021 05:51:09 - INFO - __main__ - Step 91580: {'lr': 0.00016882486852991664, 'samples': 17583360, 'steps': 91579, 'loss/train': 1.151258111000061} 08/31/2021 05:51:09 - INFO - __main__ - Step 91581: {'lr': 0.00016881984933982922, 'samples': 17583552, 'steps': 91580, 'loss/train': 1.1496188640594482} 08/31/2021 05:51:09 - INFO - __main__ - Step 91582: {'lr': 0.00016881483018632034, 'samples': 17583744, 'steps': 91581, 'loss/train': 0.9226559996604919} 08/31/2021 05:51:10 - INFO - __main__ - Step 91583: {'lr': 0.00016880981106939227, 'samples': 17583936, 'steps': 91582, 'loss/train': 1.3496161699295044} 08/31/2021 05:51:11 - INFO - __main__ - Step 91584: {'lr': 0.00016880479198904725, 'samples': 17584128, 'steps': 91583, 'loss/train': 1.3722704648971558} 08/31/2021 05:51:12 - INFO - __main__ - Step 91585: {'lr': 0.0001687997729452875, 'samples': 17584320, 'steps': 91584, 'loss/train': 1.0677051544189453} 08/31/2021 05:51:12 - INFO - __main__ - Step 91586: {'lr': 0.00016879475393811533, 'samples': 17584512, 'steps': 91585, 'loss/train': 1.1943957805633545} 08/31/2021 05:51:12 - INFO - __main__ - Step 91587: {'lr': 0.00016878973496753301, 'samples': 17584704, 'steps': 91586, 'loss/train': 1.8239985704421997} 08/31/2021 05:51:13 - INFO - __main__ - Step 91588: {'lr': 0.0001687847160335428, 'samples': 17584896, 'steps': 91587, 'loss/train': 1.1934500932693481} 08/31/2021 05:51:14 - INFO - __main__ - Step 91589: {'lr': 0.00016877969713614688, 'samples': 17585088, 'steps': 91588, 'loss/train': 1.5970815420150757} 08/31/2021 05:51:15 - INFO - __main__ - Step 91590: {'lr': 0.00016877467827534762, 'samples': 17585280, 'steps': 91589, 'loss/train': 1.3428690433502197} 08/31/2021 05:51:15 - INFO - __main__ - Step 91591: {'lr': 0.00016876965945114734, 'samples': 17585472, 'steps': 91590, 'loss/train': 1.4517549276351929} 08/31/2021 05:51:15 - INFO - __main__ - Step 91592: {'lr': 0.00016876464066354808, 'samples': 17585664, 'steps': 91591, 'loss/train': 1.4231691360473633} 08/31/2021 05:51:16 - INFO - __main__ - Step 91593: {'lr': 0.00016875962191255223, 'samples': 17585856, 'steps': 91592, 'loss/train': 1.7091997861862183} 08/31/2021 05:51:17 - INFO - __main__ - Step 91594: {'lr': 0.00016875460319816204, 'samples': 17586048, 'steps': 91593, 'loss/train': 1.4166635274887085} 08/31/2021 05:51:18 - INFO - __main__ - Step 91595: {'lr': 0.00016874958452037976, 'samples': 17586240, 'steps': 91594, 'loss/train': 0.0308699868619442} 08/31/2021 05:51:18 - INFO - __main__ - Step 91596: {'lr': 0.00016874456587920766, 'samples': 17586432, 'steps': 91595, 'loss/train': 1.4285788536071777} 08/31/2021 05:51:18 - INFO - __main__ - Step 91597: {'lr': 0.00016873954727464802, 'samples': 17586624, 'steps': 91596, 'loss/train': 1.399344563484192} 08/31/2021 05:51:19 - INFO - __main__ - Step 91598: {'lr': 0.0001687345287067031, 'samples': 17586816, 'steps': 91597, 'loss/train': 0.6448860168457031} 08/31/2021 05:51:20 - INFO - __main__ - Step 91599: {'lr': 0.00016872951017537512, 'samples': 17587008, 'steps': 91598, 'loss/train': 1.0869736671447754} 08/31/2021 05:51:21 - INFO - __main__ - Step 91600: {'lr': 0.0001687244916806664, 'samples': 17587200, 'steps': 91599, 'loss/train': 1.030351996421814} 08/31/2021 05:51:21 - INFO - __main__ - Step 91601: {'lr': 0.00016871947322257913, 'samples': 17587392, 'steps': 91600, 'loss/train': 0.6256658434867859} 08/31/2021 05:51:21 - INFO - __main__ - Step 91602: {'lr': 0.0001687144548011157, 'samples': 17587584, 'steps': 91601, 'loss/train': 0.8827449679374695} 08/31/2021 05:51:22 - INFO - __main__ - Step 91603: {'lr': 0.00016870943641627818, 'samples': 17587776, 'steps': 91602, 'loss/train': 0.7879541516304016} 08/31/2021 05:51:23 - INFO - __main__ - Step 91604: {'lr': 0.00016870441806806903, 'samples': 17587968, 'steps': 91603, 'loss/train': 1.1975353956222534} 08/31/2021 05:51:24 - INFO - __main__ - Step 91605: {'lr': 0.00016869939975649035, 'samples': 17588160, 'steps': 91604, 'loss/train': 1.509791612625122} 08/31/2021 05:51:24 - INFO - __main__ - Step 91606: {'lr': 0.00016869438148154448, 'samples': 17588352, 'steps': 91605, 'loss/train': 1.1467903852462769} 08/31/2021 05:51:24 - INFO - __main__ - Step 91607: {'lr': 0.00016868936324323364, 'samples': 17588544, 'steps': 91606, 'loss/train': 1.2830936908721924} 08/31/2021 05:51:25 - INFO - __main__ - Step 91608: {'lr': 0.00016868434504156013, 'samples': 17588736, 'steps': 91607, 'loss/train': 0.7141162753105164} 08/31/2021 05:51:27 - INFO - __main__ - Step 91609: {'lr': 0.0001686793268765262, 'samples': 17588928, 'steps': 91608, 'loss/train': 1.422434687614441} 08/31/2021 05:51:27 - INFO - __main__ - Step 91610: {'lr': 0.0001686743087481341, 'samples': 17589120, 'steps': 91609, 'loss/train': 2.235090494155884} 08/31/2021 05:51:28 - INFO - __main__ - Step 91611: {'lr': 0.00016866929065638615, 'samples': 17589312, 'steps': 91610, 'loss/train': 1.4461541175842285} 08/31/2021 05:51:28 - INFO - __main__ - Step 91612: {'lr': 0.00016866427260128455, 'samples': 17589504, 'steps': 91611, 'loss/train': 0.45171353220939636} 08/31/2021 05:51:28 - INFO - __main__ - Step 91613: {'lr': 0.00016865925458283155, 'samples': 17589696, 'steps': 91612, 'loss/train': 0.872932493686676} 08/31/2021 05:51:30 - INFO - __main__ - Step 91614: {'lr': 0.00016865423660102945, 'samples': 17589888, 'steps': 91613, 'loss/train': 0.6987766027450562} 08/31/2021 05:51:30 - INFO - __main__ - Step 91615: {'lr': 0.00016864921865588045, 'samples': 17590080, 'steps': 91614, 'loss/train': 0.7637222409248352} 08/31/2021 05:51:31 - INFO - __main__ - Step 91616: {'lr': 0.0001686442007473869, 'samples': 17590272, 'steps': 91615, 'loss/train': 2.028411388397217} 08/31/2021 05:51:31 - INFO - __main__ - Step 91617: {'lr': 0.00016863918287555102, 'samples': 17590464, 'steps': 91616, 'loss/train': 0.6924902200698853} 08/31/2021 05:51:32 - INFO - __main__ - Step 91618: {'lr': 0.0001686341650403751, 'samples': 17590656, 'steps': 91617, 'loss/train': 1.5926902294158936} 08/31/2021 05:51:32 - INFO - __main__ - Step 91619: {'lr': 0.00016862914724186128, 'samples': 17590848, 'steps': 91618, 'loss/train': 0.8024004101753235} 08/31/2021 05:51:33 - INFO - __main__ - Step 91620: {'lr': 0.000168624129480012, 'samples': 17591040, 'steps': 91619, 'loss/train': 1.1730647087097168} 08/31/2021 05:51:34 - INFO - __main__ - Step 91621: {'lr': 0.00016861911175482936, 'samples': 17591232, 'steps': 91620, 'loss/train': 0.9675580859184265} 08/31/2021 05:51:34 - INFO - __main__ - Step 91622: {'lr': 0.00016861409406631573, 'samples': 17591424, 'steps': 91621, 'loss/train': 0.39086607098579407} 08/31/2021 05:51:34 - INFO - __main__ - Step 91623: {'lr': 0.00016860907641447337, 'samples': 17591616, 'steps': 91622, 'loss/train': 1.337845802307129} 08/31/2021 05:51:35 - INFO - __main__ - Step 91624: {'lr': 0.00016860405879930447, 'samples': 17591808, 'steps': 91623, 'loss/train': 1.6031142473220825} 08/31/2021 05:51:37 - INFO - __main__ - Step 91625: {'lr': 0.00016859904122081129, 'samples': 17592000, 'steps': 91624, 'loss/train': 0.4997215270996094} 08/31/2021 05:51:37 - INFO - __main__ - Step 91626: {'lr': 0.00016859402367899615, 'samples': 17592192, 'steps': 91625, 'loss/train': 0.931833028793335} 08/31/2021 05:51:38 - INFO - __main__ - Step 91627: {'lr': 0.00016858900617386128, 'samples': 17592384, 'steps': 91626, 'loss/train': 4.341217517852783} 08/31/2021 05:51:38 - INFO - __main__ - Step 91628: {'lr': 0.00016858398870540895, 'samples': 17592576, 'steps': 91627, 'loss/train': 0.13456694781780243} 08/31/2021 05:51:38 - INFO - __main__ - Step 91629: {'lr': 0.00016857897127364141, 'samples': 17592768, 'steps': 91628, 'loss/train': 0.2182837724685669} 08/31/2021 05:51:40 - INFO - __main__ - Step 91630: {'lr': 0.00016857395387856095, 'samples': 17592960, 'steps': 91629, 'loss/train': 1.36353600025177} 08/31/2021 05:51:40 - INFO - __main__ - Step 91631: {'lr': 0.00016856893652016986, 'samples': 17593152, 'steps': 91630, 'loss/train': 1.407884120941162} 08/31/2021 05:51:41 - INFO - __main__ - Step 91632: {'lr': 0.0001685639191984703, 'samples': 17593344, 'steps': 91631, 'loss/train': 0.8788257241249084} 08/31/2021 05:51:41 - INFO - __main__ - Step 91633: {'lr': 0.00016855890191346453, 'samples': 17593536, 'steps': 91632, 'loss/train': 1.205546259880066} 08/31/2021 05:51:41 - INFO - __main__ - Step 91634: {'lr': 0.00016855388466515499, 'samples': 17593728, 'steps': 91633, 'loss/train': 1.8063373565673828} 08/31/2021 05:51:43 - INFO - __main__ - Step 91635: {'lr': 0.0001685488674535437, 'samples': 17593920, 'steps': 91634, 'loss/train': 1.3833802938461304} 08/31/2021 05:51:43 - INFO - __main__ - Step 91636: {'lr': 0.00016854385027863307, 'samples': 17594112, 'steps': 91635, 'loss/train': 2.91418719291687} 08/31/2021 05:51:44 - INFO - __main__ - Step 91637: {'lr': 0.00016853883314042528, 'samples': 17594304, 'steps': 91636, 'loss/train': 1.7005974054336548} 08/31/2021 05:51:44 - INFO - __main__ - Step 91638: {'lr': 0.0001685338160389227, 'samples': 17594496, 'steps': 91637, 'loss/train': 0.9589086174964905} 08/31/2021 05:51:44 - INFO - __main__ - Step 91639: {'lr': 0.00016852879897412748, 'samples': 17594688, 'steps': 91638, 'loss/train': 1.5451757907867432} 08/31/2021 05:51:45 - INFO - __main__ - Step 91640: {'lr': 0.00016852378194604195, 'samples': 17594880, 'steps': 91639, 'loss/train': 0.4106956124305725} 08/31/2021 05:51:46 - INFO - __main__ - Step 91641: {'lr': 0.00016851876495466834, 'samples': 17595072, 'steps': 91640, 'loss/train': 1.1783251762390137} 08/31/2021 05:51:47 - INFO - __main__ - Step 91642: {'lr': 0.0001685137480000089, 'samples': 17595264, 'steps': 91641, 'loss/train': 0.3334853947162628} 08/31/2021 05:51:47 - INFO - __main__ - Step 91643: {'lr': 0.00016850873108206592, 'samples': 17595456, 'steps': 91642, 'loss/train': 1.3747079372406006} 08/31/2021 05:51:47 - INFO - __main__ - Step 91644: {'lr': 0.00016850371420084172, 'samples': 17595648, 'steps': 91643, 'loss/train': 1.2126587629318237} 08/31/2021 05:51:48 - INFO - __main__ - Step 91645: {'lr': 0.00016849869735633844, 'samples': 17595840, 'steps': 91644, 'loss/train': 0.8896657824516296} 08/31/2021 05:51:49 - INFO - __main__ - Step 91646: {'lr': 0.00016849368054855837, 'samples': 17596032, 'steps': 91645, 'loss/train': 0.8665193319320679} 08/31/2021 05:51:50 - INFO - __main__ - Step 91647: {'lr': 0.00016848866377750378, 'samples': 17596224, 'steps': 91646, 'loss/train': 0.04658342897891998} 08/31/2021 05:51:50 - INFO - __main__ - Step 91648: {'lr': 0.00016848364704317697, 'samples': 17596416, 'steps': 91647, 'loss/train': 0.8704347014427185} 08/31/2021 05:51:51 - INFO - __main__ - Step 91649: {'lr': 0.00016847863034558013, 'samples': 17596608, 'steps': 91648, 'loss/train': 0.9581796526908875} 08/31/2021 05:51:51 - INFO - __main__ - Step 91650: {'lr': 0.00016847361368471558, 'samples': 17596800, 'steps': 91649, 'loss/train': 0.5283058881759644} 08/31/2021 05:51:52 - INFO - __main__ - Step 91651: {'lr': 0.00016846859706058553, 'samples': 17596992, 'steps': 91650, 'loss/train': 1.6498883962631226} 08/31/2021 05:51:53 - INFO - __main__ - Step 91652: {'lr': 0.00016846358047319232, 'samples': 17597184, 'steps': 91651, 'loss/train': 0.6203469634056091} 08/31/2021 05:51:53 - INFO - __main__ - Step 91653: {'lr': 0.00016845856392253816, 'samples': 17597376, 'steps': 91652, 'loss/train': 1.0097028017044067} 08/31/2021 05:51:54 - INFO - __main__ - Step 91654: {'lr': 0.0001684535474086253, 'samples': 17597568, 'steps': 91653, 'loss/train': 1.1957305669784546} 08/31/2021 05:51:54 - INFO - __main__ - Step 91655: {'lr': 0.00016844853093145602, 'samples': 17597760, 'steps': 91654, 'loss/train': 1.2707022428512573} 08/31/2021 05:51:54 - INFO - __main__ - Step 91656: {'lr': 0.00016844351449103254, 'samples': 17597952, 'steps': 91655, 'loss/train': 0.6614430546760559} 08/31/2021 05:51:56 - INFO - __main__ - Step 91657: {'lr': 0.00016843849808735717, 'samples': 17598144, 'steps': 91656, 'loss/train': 1.6719039678573608} 08/31/2021 05:51:56 - INFO - __main__ - Step 91658: {'lr': 0.00016843348172043227, 'samples': 17598336, 'steps': 91657, 'loss/train': 1.361039638519287} 08/31/2021 05:51:57 - INFO - __main__ - Step 91659: {'lr': 0.0001684284653902599, 'samples': 17598528, 'steps': 91658, 'loss/train': 0.8915242552757263} 08/31/2021 05:51:57 - INFO - __main__ - Step 91660: {'lr': 0.00016842344909684238, 'samples': 17598720, 'steps': 91659, 'loss/train': 0.29257988929748535} 08/31/2021 05:51:57 - INFO - __main__ - Step 91661: {'lr': 0.00016841843284018198, 'samples': 17598912, 'steps': 91660, 'loss/train': 0.5194793939590454} 08/31/2021 05:51:59 - INFO - __main__ - Step 91662: {'lr': 0.000168413416620281, 'samples': 17599104, 'steps': 91661, 'loss/train': 0.5418067574501038} 08/31/2021 05:51:59 - INFO - __main__ - Step 91663: {'lr': 0.00016840840043714166, 'samples': 17599296, 'steps': 91662, 'loss/train': 1.3339197635650635} 08/31/2021 05:52:00 - INFO - __main__ - Step 91664: {'lr': 0.00016840338429076625, 'samples': 17599488, 'steps': 91663, 'loss/train': 1.5350568294525146} 08/31/2021 05:52:00 - INFO - __main__ - Step 91665: {'lr': 0.000168398368181157, 'samples': 17599680, 'steps': 91664, 'loss/train': 1.4537402391433716} 08/31/2021 05:52:00 - INFO - __main__ - Step 91666: {'lr': 0.0001683933521083162, 'samples': 17599872, 'steps': 91665, 'loss/train': 0.46337324380874634} 08/31/2021 05:52:03 - INFO - __main__ - Step 91667: {'lr': 0.00016838833607224607, 'samples': 17600064, 'steps': 91666, 'loss/train': 0.5098502039909363} 08/31/2021 05:52:03 - INFO - __main__ - Step 91668: {'lr': 0.00016838332007294894, 'samples': 17600256, 'steps': 91667, 'loss/train': 1.386516809463501} 08/31/2021 05:52:04 - INFO - __main__ - Step 91669: {'lr': 0.00016837830411042698, 'samples': 17600448, 'steps': 91668, 'loss/train': 0.04905381426215172} 08/31/2021 05:52:04 - INFO - __main__ - Step 91670: {'lr': 0.00016837328818468253, 'samples': 17600640, 'steps': 91669, 'loss/train': 0.09173925966024399} 08/31/2021 05:52:05 - INFO - __main__ - Step 91671: {'lr': 0.00016836827229571794, 'samples': 17600832, 'steps': 91670, 'loss/train': 1.1266947984695435} 08/31/2021 05:52:05 - INFO - __main__ - Step 91672: {'lr': 0.00016836325644353518, 'samples': 17601024, 'steps': 91671, 'loss/train': 1.282527208328247} 08/31/2021 05:52:06 - INFO - __main__ - Step 91673: {'lr': 0.0001683582406281367, 'samples': 17601216, 'steps': 91672, 'loss/train': 0.9440956115722656} 08/31/2021 05:52:07 - INFO - __main__ - Step 91674: {'lr': 0.00016835322484952476, 'samples': 17601408, 'steps': 91673, 'loss/train': 1.3200429677963257} 08/31/2021 05:52:07 - INFO - __main__ - Step 91675: {'lr': 0.0001683482091077016, 'samples': 17601600, 'steps': 91674, 'loss/train': 1.398792028427124} 08/31/2021 05:52:08 - INFO - __main__ - Step 91676: {'lr': 0.00016834319340266945, 'samples': 17601792, 'steps': 91675, 'loss/train': 1.732067584991455} 08/31/2021 05:52:08 - INFO - __main__ - Step 91677: {'lr': 0.0001683381777344306, 'samples': 17601984, 'steps': 91676, 'loss/train': 1.3062686920166016} 08/31/2021 05:52:10 - INFO - __main__ - Step 91678: {'lr': 0.0001683331621029873, 'samples': 17602176, 'steps': 91677, 'loss/train': 1.208859920501709} 08/31/2021 05:52:10 - INFO - __main__ - Step 91679: {'lr': 0.0001683281465083419, 'samples': 17602368, 'steps': 91678, 'loss/train': 0.9892907738685608} 08/31/2021 05:52:10 - INFO - __main__ - Step 91680: {'lr': 0.00016832313095049647, 'samples': 17602560, 'steps': 91679, 'loss/train': 0.6346583962440491} 08/31/2021 05:52:11 - INFO - __main__ - Step 91681: {'lr': 0.00016831811542945341, 'samples': 17602752, 'steps': 91680, 'loss/train': 0.8312298059463501} 08/31/2021 05:52:11 - INFO - __main__ - Step 91682: {'lr': 0.00016831309994521499, 'samples': 17602944, 'steps': 91681, 'loss/train': 1.0358350276947021} 08/31/2021 05:52:11 - INFO - __main__ - Step 91683: {'lr': 0.00016830808449778338, 'samples': 17603136, 'steps': 91682, 'loss/train': 0.19086170196533203} 08/31/2021 05:52:13 - INFO - __main__ - Step 91684: {'lr': 0.00016830306908716087, 'samples': 17603328, 'steps': 91683, 'loss/train': 1.401363730430603} 08/31/2021 05:52:13 - INFO - __main__ - Step 91685: {'lr': 0.0001682980537133499, 'samples': 17603520, 'steps': 91684, 'loss/train': 1.393496036529541} 08/31/2021 05:52:14 - INFO - __main__ - Step 91686: {'lr': 0.0001682930383763524, 'samples': 17603712, 'steps': 91685, 'loss/train': 1.4637925624847412} 08/31/2021 05:52:14 - INFO - __main__ - Step 91687: {'lr': 0.00016828802307617083, 'samples': 17603904, 'steps': 91686, 'loss/train': 0.2288408875465393} 08/31/2021 05:52:14 - INFO - __main__ - Step 91688: {'lr': 0.00016828300781280742, 'samples': 17604096, 'steps': 91687, 'loss/train': 0.982745885848999} 08/31/2021 05:52:17 - INFO - __main__ - Step 91689: {'lr': 0.00016827799258626442, 'samples': 17604288, 'steps': 91688, 'loss/train': 1.0322599411010742} 08/31/2021 05:52:17 - INFO - __main__ - Step 91690: {'lr': 0.00016827297739654406, 'samples': 17604480, 'steps': 91689, 'loss/train': 0.3506413698196411} 08/31/2021 05:52:17 - INFO - __main__ - Step 91691: {'lr': 0.00016826796224364871, 'samples': 17604672, 'steps': 91690, 'loss/train': 0.3366491496562958} 08/31/2021 05:52:18 - INFO - __main__ - Step 91692: {'lr': 0.0001682629471275805, 'samples': 17604864, 'steps': 91691, 'loss/train': 1.6053656339645386} 08/31/2021 05:52:18 - INFO - __main__ - Step 91693: {'lr': 0.00016825793204834177, 'samples': 17605056, 'steps': 91692, 'loss/train': 0.7723433375358582} 08/31/2021 05:52:19 - INFO - __main__ - Step 91694: {'lr': 0.00016825291700593473, 'samples': 17605248, 'steps': 91693, 'loss/train': 0.29363933205604553} 08/31/2021 05:52:20 - INFO - __main__ - Step 91695: {'lr': 0.00016824790200036167, 'samples': 17605440, 'steps': 91694, 'loss/train': 0.7660925388336182} 08/31/2021 05:52:21 - INFO - __main__ - Step 91696: {'lr': 0.00016824288703162486, 'samples': 17605632, 'steps': 91695, 'loss/train': 1.5174449682235718} 08/31/2021 05:52:21 - INFO - __main__ - Step 91697: {'lr': 0.0001682378720997265, 'samples': 17605824, 'steps': 91696, 'loss/train': 1.3298894166946411} 08/31/2021 05:52:21 - INFO - __main__ - Step 91698: {'lr': 0.00016823285720466907, 'samples': 17606016, 'steps': 91697, 'loss/train': 0.3988206088542938} 08/31/2021 05:52:22 - INFO - __main__ - Step 91699: {'lr': 0.00016822784234645448, 'samples': 17606208, 'steps': 91698, 'loss/train': 2.2745559215545654} 08/31/2021 05:52:24 - INFO - __main__ - Step 91700: {'lr': 0.00016822282752508523, 'samples': 17606400, 'steps': 91699, 'loss/train': 1.033920407295227} 08/31/2021 05:52:24 - INFO - __main__ - Step 91701: {'lr': 0.00016821781274056348, 'samples': 17606592, 'steps': 91700, 'loss/train': 1.1791542768478394} 08/31/2021 05:52:24 - INFO - __main__ - Step 91702: {'lr': 0.0001682127979928915, 'samples': 17606784, 'steps': 91701, 'loss/train': 1.0522193908691406} 08/31/2021 05:52:25 - INFO - __main__ - Step 91703: {'lr': 0.00016820778328207158, 'samples': 17606976, 'steps': 91702, 'loss/train': 1.4216248989105225} 08/31/2021 05:52:25 - INFO - __main__ - Step 91704: {'lr': 0.00016820276860810595, 'samples': 17607168, 'steps': 91703, 'loss/train': 1.5134245157241821} 08/31/2021 05:52:25 - INFO - __main__ - Step 91705: {'lr': 0.00016819775397099697, 'samples': 17607360, 'steps': 91704, 'loss/train': 0.8288015127182007} 08/31/2021 05:52:27 - INFO - __main__ - Step 91706: {'lr': 0.00016819273937074676, 'samples': 17607552, 'steps': 91705, 'loss/train': 1.1072163581848145} 08/31/2021 05:52:28 - INFO - __main__ - Step 91707: {'lr': 0.00016818772480735761, 'samples': 17607744, 'steps': 91706, 'loss/train': 1.398580551147461} 08/31/2021 05:52:28 - INFO - __main__ - Step 91708: {'lr': 0.00016818271028083188, 'samples': 17607936, 'steps': 91707, 'loss/train': 1.1037318706512451} 08/31/2021 05:52:28 - INFO - __main__ - Step 91709: {'lr': 0.0001681776957911717, 'samples': 17608128, 'steps': 91708, 'loss/train': 1.312426209449768} 08/31/2021 05:52:29 - INFO - __main__ - Step 91710: {'lr': 0.00016817268133837942, 'samples': 17608320, 'steps': 91709, 'loss/train': 0.06508849561214447} 08/31/2021 05:52:30 - INFO - __main__ - Step 91711: {'lr': 0.00016816766692245727, 'samples': 17608512, 'steps': 91710, 'loss/train': 0.40407848358154297} 08/31/2021 05:52:31 - INFO - __main__ - Step 91712: {'lr': 0.0001681626525434076, 'samples': 17608704, 'steps': 91711, 'loss/train': 1.6861644983291626} 08/31/2021 05:52:31 - INFO - __main__ - Step 91713: {'lr': 0.00016815763820123247, 'samples': 17608896, 'steps': 91712, 'loss/train': 1.0661916732788086} 08/31/2021 05:52:32 - INFO - __main__ - Step 91714: {'lr': 0.0001681526238959342, 'samples': 17609088, 'steps': 91713, 'loss/train': 1.6585626602172852} 08/31/2021 05:52:32 - INFO - __main__ - Step 91715: {'lr': 0.0001681476096275152, 'samples': 17609280, 'steps': 91714, 'loss/train': 1.5135571956634521} 08/31/2021 05:52:32 - INFO - __main__ - Step 91716: {'lr': 0.00016814259539597753, 'samples': 17609472, 'steps': 91715, 'loss/train': 1.8269175291061401} 08/31/2021 05:52:34 - INFO - __main__ - Step 91717: {'lr': 0.00016813758120132362, 'samples': 17609664, 'steps': 91716, 'loss/train': 1.0604602098464966} 08/31/2021 05:52:34 - INFO - __main__ - Step 91718: {'lr': 0.0001681325670435556, 'samples': 17609856, 'steps': 91717, 'loss/train': 1.3714709281921387} 08/31/2021 05:52:35 - INFO - __main__ - Step 91719: {'lr': 0.00016812755292267578, 'samples': 17610048, 'steps': 91718, 'loss/train': 1.1319833993911743} 08/31/2021 05:52:35 - INFO - __main__ - Step 91720: {'lr': 0.00016812253883868644, 'samples': 17610240, 'steps': 91719, 'loss/train': 1.1996454000473022} 08/31/2021 05:52:35 - INFO - __main__ - Step 91721: {'lr': 0.0001681175247915898, 'samples': 17610432, 'steps': 91720, 'loss/train': 1.7408397197723389} 08/31/2021 05:52:37 - INFO - __main__ - Step 91722: {'lr': 0.00016811251078138818, 'samples': 17610624, 'steps': 91721, 'loss/train': 1.0146631002426147} 08/31/2021 05:52:38 - INFO - __main__ - Step 91723: {'lr': 0.00016810749680808373, 'samples': 17610816, 'steps': 91722, 'loss/train': 1.433640480041504} 08/31/2021 05:52:38 - INFO - __main__ - Step 91724: {'lr': 0.00016810248287167884, 'samples': 17611008, 'steps': 91723, 'loss/train': 1.2859125137329102} 08/31/2021 05:52:39 - INFO - __main__ - Step 91725: {'lr': 0.00016809746897217582, 'samples': 17611200, 'steps': 91724, 'loss/train': 1.0968921184539795} 08/31/2021 05:52:39 - INFO - __main__ - Step 91726: {'lr': 0.00016809245510957666, 'samples': 17611392, 'steps': 91725, 'loss/train': 1.3785699605941772} 08/31/2021 05:52:41 - INFO - __main__ - Step 91727: {'lr': 0.00016808744128388382, 'samples': 17611584, 'steps': 91726, 'loss/train': 1.0161305665969849} 08/31/2021 05:52:41 - INFO - __main__ - Step 91728: {'lr': 0.0001680824274950995, 'samples': 17611776, 'steps': 91727, 'loss/train': 0.10128924250602722} 08/31/2021 05:52:42 - INFO - __main__ - Step 91729: {'lr': 0.00016807741374322597, 'samples': 17611968, 'steps': 91728, 'loss/train': 1.2187528610229492} 08/31/2021 05:52:42 - INFO - __main__ - Step 91730: {'lr': 0.0001680724000282655, 'samples': 17612160, 'steps': 91729, 'loss/train': 0.05459362640976906} 08/31/2021 05:52:42 - INFO - __main__ - Step 91731: {'lr': 0.0001680673863502203, 'samples': 17612352, 'steps': 91730, 'loss/train': 1.540379524230957} 08/31/2021 05:52:44 - INFO - __main__ - Step 91732: {'lr': 0.00016806237270909275, 'samples': 17612544, 'steps': 91731, 'loss/train': 0.730887770652771} 08/31/2021 05:52:44 - INFO - __main__ - Step 91733: {'lr': 0.00016805735910488496, 'samples': 17612736, 'steps': 91732, 'loss/train': 1.4792115688323975} 08/31/2021 05:52:45 - INFO - __main__ - Step 91734: {'lr': 0.0001680523455375993, 'samples': 17612928, 'steps': 91733, 'loss/train': 1.1534433364868164} 08/31/2021 05:52:45 - INFO - __main__ - Step 91735: {'lr': 0.000168047332007238, 'samples': 17613120, 'steps': 91734, 'loss/train': 0.16651566326618195} 08/31/2021 05:52:45 - INFO - __main__ - Step 91736: {'lr': 0.0001680423185138033, 'samples': 17613312, 'steps': 91735, 'loss/train': 0.9308152794837952} 08/31/2021 05:52:47 - INFO - __main__ - Step 91737: {'lr': 0.00016803730505729746, 'samples': 17613504, 'steps': 91736, 'loss/train': 1.683815360069275} 08/31/2021 05:52:47 - INFO - __main__ - Step 91738: {'lr': 0.00016803229163772274, 'samples': 17613696, 'steps': 91737, 'loss/train': 1.4852402210235596} 08/31/2021 05:52:48 - INFO - __main__ - Step 91739: {'lr': 0.00016802727825508147, 'samples': 17613888, 'steps': 91738, 'loss/train': 0.4066827595233917} 08/31/2021 05:52:48 - INFO - __main__ - Step 91740: {'lr': 0.00016802226490937575, 'samples': 17614080, 'steps': 91739, 'loss/train': 1.249662160873413} 08/31/2021 05:52:49 - INFO - __main__ - Step 91741: {'lr': 0.00016801725160060796, 'samples': 17614272, 'steps': 91740, 'loss/train': 0.5849102735519409} 08/31/2021 05:52:50 - INFO - __main__ - Step 91742: {'lr': 0.0001680122383287803, 'samples': 17614464, 'steps': 91741, 'loss/train': 0.08198398351669312} 08/31/2021 05:52:50 - INFO - __main__ - Step 91743: {'lr': 0.0001680072250938951, 'samples': 17614656, 'steps': 91742, 'loss/train': 0.7937849164009094} 08/31/2021 05:52:51 - INFO - __main__ - Step 91744: {'lr': 0.0001680022118959546, 'samples': 17614848, 'steps': 91743, 'loss/train': 0.8752064108848572} 08/31/2021 05:52:51 - INFO - __main__ - Step 91745: {'lr': 0.000167997198734961, 'samples': 17615040, 'steps': 91744, 'loss/train': 1.4712730646133423} 08/31/2021 05:52:51 - INFO - __main__ - Step 91746: {'lr': 0.0001679921856109166, 'samples': 17615232, 'steps': 91745, 'loss/train': 1.2225767374038696} 08/31/2021 05:52:53 - INFO - __main__ - Step 91747: {'lr': 0.0001679871725238237, 'samples': 17615424, 'steps': 91746, 'loss/train': 0.8523516654968262} 08/31/2021 05:52:54 - INFO - __main__ - Step 91748: {'lr': 0.00016798215947368448, 'samples': 17615616, 'steps': 91747, 'loss/train': 1.0233919620513916} 08/31/2021 05:52:54 - INFO - __main__ - Step 91749: {'lr': 0.0001679771464605012, 'samples': 17615808, 'steps': 91748, 'loss/train': 1.1472017765045166} 08/31/2021 05:52:54 - INFO - __main__ - Step 91750: {'lr': 0.00016797213348427621, 'samples': 17616000, 'steps': 91749, 'loss/train': 0.4936332106590271} 08/31/2021 05:52:55 - INFO - __main__ - Step 91751: {'lr': 0.00016796712054501168, 'samples': 17616192, 'steps': 91750, 'loss/train': 1.330253005027771} 08/31/2021 05:52:56 - INFO - __main__ - Step 91752: {'lr': 0.00016796210764270995, 'samples': 17616384, 'steps': 91751, 'loss/train': 1.2063120603561401} 08/31/2021 05:52:57 - INFO - __main__ - Step 91753: {'lr': 0.00016795709477737317, 'samples': 17616576, 'steps': 91752, 'loss/train': 0.5086641311645508} 08/31/2021 05:52:57 - INFO - __main__ - Step 91754: {'lr': 0.00016795208194900365, 'samples': 17616768, 'steps': 91753, 'loss/train': 1.2009414434432983} 08/31/2021 05:52:57 - INFO - __main__ - Step 91755: {'lr': 0.00016794706915760369, 'samples': 17616960, 'steps': 91754, 'loss/train': 1.6642483472824097} 08/31/2021 05:52:58 - INFO - __main__ - Step 91756: {'lr': 0.0001679420564031755, 'samples': 17617152, 'steps': 91755, 'loss/train': 1.180468201637268} 08/31/2021 05:52:58 - INFO - __main__ - Step 91757: {'lr': 0.00016793704368572133, 'samples': 17617344, 'steps': 91756, 'loss/train': 0.9945201873779297} 08/31/2021 05:52:59 - INFO - __main__ - Step 91758: {'lr': 0.00016793203100524354, 'samples': 17617536, 'steps': 91757, 'loss/train': 1.1980400085449219} 08/31/2021 05:53:00 - INFO - __main__ - Step 91759: {'lr': 0.00016792701836174423, 'samples': 17617728, 'steps': 91758, 'loss/train': 1.1478710174560547} 08/31/2021 05:53:00 - INFO - __main__ - Step 91760: {'lr': 0.00016792200575522576, 'samples': 17617920, 'steps': 91759, 'loss/train': 1.2170273065567017} 08/31/2021 05:53:01 - INFO - __main__ - Step 91761: {'lr': 0.00016791699318569037, 'samples': 17618112, 'steps': 91760, 'loss/train': 1.3372716903686523} 08/31/2021 05:53:01 - INFO - __main__ - Step 91762: {'lr': 0.00016791198065314034, 'samples': 17618304, 'steps': 91761, 'loss/train': 1.0374492406845093} 08/31/2021 05:53:02 - INFO - __main__ - Step 91763: {'lr': 0.00016790696815757787, 'samples': 17618496, 'steps': 91762, 'loss/train': 0.95231032371521} 08/31/2021 05:53:03 - INFO - __main__ - Step 91764: {'lr': 0.00016790195569900524, 'samples': 17618688, 'steps': 91763, 'loss/train': 1.1288825273513794} 08/31/2021 05:53:03 - INFO - __main__ - Step 91765: {'lr': 0.00016789694327742482, 'samples': 17618880, 'steps': 91764, 'loss/train': 0.03281842917203903} 08/31/2021 05:53:04 - INFO - __main__ - Step 91766: {'lr': 0.00016789193089283868, 'samples': 17619072, 'steps': 91765, 'loss/train': 0.9668779373168945} 08/31/2021 05:53:04 - INFO - __main__ - Step 91767: {'lr': 0.00016788691854524918, 'samples': 17619264, 'steps': 91766, 'loss/train': 0.9687778949737549} 08/31/2021 05:53:05 - INFO - __main__ - Step 91768: {'lr': 0.00016788190623465856, 'samples': 17619456, 'steps': 91767, 'loss/train': 1.2590339183807373} 08/31/2021 05:53:06 - INFO - __main__ - Step 91769: {'lr': 0.00016787689396106917, 'samples': 17619648, 'steps': 91768, 'loss/train': 1.2600849866867065} 08/31/2021 05:53:06 - INFO - __main__ - Step 91770: {'lr': 0.00016787188172448308, 'samples': 17619840, 'steps': 91769, 'loss/train': 0.781781017780304} 08/31/2021 05:53:07 - INFO - __main__ - Step 91771: {'lr': 0.0001678668695249027, 'samples': 17620032, 'steps': 91770, 'loss/train': 1.1077029705047607} 08/31/2021 05:53:07 - INFO - __main__ - Step 91772: {'lr': 0.00016786185736233022, 'samples': 17620224, 'steps': 91771, 'loss/train': 1.4929420948028564} 08/31/2021 05:53:07 - INFO - __main__ - Step 91773: {'lr': 0.00016785684523676792, 'samples': 17620416, 'steps': 91772, 'loss/train': 1.1640241146087646} 08/31/2021 05:53:10 - INFO - __main__ - Step 91774: {'lr': 0.00016785183314821806, 'samples': 17620608, 'steps': 91773, 'loss/train': 0.6845400333404541} 08/31/2021 05:53:10 - INFO - __main__ - Step 91775: {'lr': 0.00016784682109668292, 'samples': 17620800, 'steps': 91774, 'loss/train': 1.3657009601593018} 08/31/2021 05:53:10 - INFO - __main__ - Step 91776: {'lr': 0.0001678418090821647, 'samples': 17620992, 'steps': 91775, 'loss/train': 0.4221869707107544} 08/31/2021 05:53:11 - INFO - __main__ - Step 91777: {'lr': 0.0001678367971046657, 'samples': 17621184, 'steps': 91776, 'loss/train': 0.37186405062675476} 08/31/2021 05:53:11 - INFO - __main__ - Step 91778: {'lr': 0.00016783178516418818, 'samples': 17621376, 'steps': 91777, 'loss/train': 1.199532151222229} 08/31/2021 05:53:13 - INFO - __main__ - Step 91779: {'lr': 0.00016782677326073446, 'samples': 17621568, 'steps': 91778, 'loss/train': 1.678814172744751} 08/31/2021 05:53:13 - INFO - __main__ - Step 91780: {'lr': 0.00016782176139430673, 'samples': 17621760, 'steps': 91779, 'loss/train': 1.5467451810836792} 08/31/2021 05:53:13 - INFO - __main__ - Step 91781: {'lr': 0.00016781674956490715, 'samples': 17621952, 'steps': 91780, 'loss/train': 2.5536694526672363} 08/31/2021 05:53:14 - INFO - __main__ - Step 91782: {'lr': 0.00016781173777253807, 'samples': 17622144, 'steps': 91781, 'loss/train': 1.5651636123657227} 08/31/2021 05:53:14 - INFO - __main__ - Step 91783: {'lr': 0.0001678067260172018, 'samples': 17622336, 'steps': 91782, 'loss/train': 1.316271185874939} 08/31/2021 05:53:16 - INFO - __main__ - Step 91784: {'lr': 0.00016780171429890052, 'samples': 17622528, 'steps': 91783, 'loss/train': 0.8736894130706787} 08/31/2021 05:53:16 - INFO - __main__ - Step 91785: {'lr': 0.00016779670261763652, 'samples': 17622720, 'steps': 91784, 'loss/train': 1.0760709047317505} 08/31/2021 05:53:17 - INFO - __main__ - Step 91786: {'lr': 0.00016779169097341207, 'samples': 17622912, 'steps': 91785, 'loss/train': 0.7664957046508789} 08/31/2021 05:53:17 - INFO - __main__ - Step 91787: {'lr': 0.00016778667936622943, 'samples': 17623104, 'steps': 91786, 'loss/train': 0.0783260315656662} 08/31/2021 05:53:17 - INFO - __main__ - Step 91788: {'lr': 0.00016778166779609084, 'samples': 17623296, 'steps': 91787, 'loss/train': 1.2227689027786255} 08/31/2021 05:53:19 - INFO - __main__ - Step 91789: {'lr': 0.00016777665626299855, 'samples': 17623488, 'steps': 91788, 'loss/train': 0.756713330745697} 08/31/2021 05:53:20 - INFO - __main__ - Step 91790: {'lr': 0.00016777164476695477, 'samples': 17623680, 'steps': 91789, 'loss/train': 1.0930650234222412} 08/31/2021 05:53:20 - INFO - __main__ - Step 91791: {'lr': 0.0001677666333079619, 'samples': 17623872, 'steps': 91790, 'loss/train': 1.0490596294403076} 08/31/2021 05:53:20 - INFO - __main__ - Step 91792: {'lr': 0.00016776162188602217, 'samples': 17624064, 'steps': 91791, 'loss/train': 1.1381607055664062} 08/31/2021 05:53:21 - INFO - __main__ - Step 91793: {'lr': 0.0001677566105011377, 'samples': 17624256, 'steps': 91792, 'loss/train': 0.895359992980957} 08/31/2021 05:53:21 - INFO - __main__ - Step 91794: {'lr': 0.00016775159915331087, 'samples': 17624448, 'steps': 91793, 'loss/train': 1.3256653547286987} 08/31/2021 05:53:23 - INFO - __main__ - Step 91795: {'lr': 0.00016774658784254388, 'samples': 17624640, 'steps': 91794, 'loss/train': 0.7768949270248413} 08/31/2021 05:53:23 - INFO - __main__ - Step 91796: {'lr': 0.00016774157656883898, 'samples': 17624832, 'steps': 91795, 'loss/train': 0.9653608202934265} 08/31/2021 05:53:24 - INFO - __main__ - Step 91797: {'lr': 0.00016773656533219846, 'samples': 17625024, 'steps': 91796, 'loss/train': 1.2200337648391724} 08/31/2021 05:53:24 - INFO - __main__ - Step 91798: {'lr': 0.0001677315541326246, 'samples': 17625216, 'steps': 91797, 'loss/train': 0.018067292869091034} 08/31/2021 05:53:24 - INFO - __main__ - Step 91799: {'lr': 0.00016772654297011964, 'samples': 17625408, 'steps': 91798, 'loss/train': 1.2990107536315918} 08/31/2021 05:53:26 - INFO - __main__ - Step 91800: {'lr': 0.0001677215318446858, 'samples': 17625600, 'steps': 91799, 'loss/train': 1.5097475051879883} 08/31/2021 05:53:26 - INFO - __main__ - Step 91801: {'lr': 0.00016771652075632537, 'samples': 17625792, 'steps': 91800, 'loss/train': 0.4140867590904236} 08/31/2021 05:53:27 - INFO - __main__ - Step 91802: {'lr': 0.00016771150970504062, 'samples': 17625984, 'steps': 91801, 'loss/train': 1.1664286851882935} 08/31/2021 05:53:27 - INFO - __main__ - Step 91803: {'lr': 0.00016770649869083377, 'samples': 17626176, 'steps': 91802, 'loss/train': 0.9183977842330933} 08/31/2021 05:53:27 - INFO - __main__ - Step 91804: {'lr': 0.00016770148771370715, 'samples': 17626368, 'steps': 91803, 'loss/train': 1.9167017936706543} 08/31/2021 05:53:28 - INFO - __main__ - Step 91805: {'lr': 0.0001676964767736629, 'samples': 17626560, 'steps': 91804, 'loss/train': 1.2326340675354004} 08/31/2021 05:53:29 - INFO - __main__ - Step 91806: {'lr': 0.0001676914658707035, 'samples': 17626752, 'steps': 91805, 'loss/train': 1.3036930561065674} 08/31/2021 05:53:30 - INFO - __main__ - Step 91807: {'lr': 0.00016768645500483094, 'samples': 17626944, 'steps': 91806, 'loss/train': 1.3479738235473633} 08/31/2021 05:53:30 - INFO - __main__ - Step 91808: {'lr': 0.00016768144417604757, 'samples': 17627136, 'steps': 91807, 'loss/train': 1.3292936086654663} 08/31/2021 05:53:31 - INFO - __main__ - Step 91809: {'lr': 0.00016767643338435573, 'samples': 17627328, 'steps': 91808, 'loss/train': 0.11084108799695969} 08/31/2021 05:53:31 - INFO - __main__ - Step 91810: {'lr': 0.00016767142262975757, 'samples': 17627520, 'steps': 91809, 'loss/train': 1.0283679962158203} 08/31/2021 05:53:32 - INFO - __main__ - Step 91811: {'lr': 0.0001676664119122554, 'samples': 17627712, 'steps': 91810, 'loss/train': 1.3265182971954346} 08/31/2021 05:53:33 - INFO - __main__ - Step 91812: {'lr': 0.0001676614012318515, 'samples': 17627904, 'steps': 91811, 'loss/train': 1.2474826574325562} 08/31/2021 05:53:33 - INFO - __main__ - Step 91813: {'lr': 0.0001676563905885481, 'samples': 17628096, 'steps': 91812, 'loss/train': 1.000881314277649} 08/31/2021 05:53:34 - INFO - __main__ - Step 91814: {'lr': 0.00016765137998234742, 'samples': 17628288, 'steps': 91813, 'loss/train': 1.3683632612228394} 08/31/2021 05:53:34 - INFO - __main__ - Step 91815: {'lr': 0.00016764636941325178, 'samples': 17628480, 'steps': 91814, 'loss/train': 0.9569525122642517} 08/31/2021 05:53:36 - INFO - __main__ - Step 91816: {'lr': 0.00016764135888126341, 'samples': 17628672, 'steps': 91815, 'loss/train': 1.5000147819519043} 08/31/2021 05:53:36 - INFO - __main__ - Step 91817: {'lr': 0.0001676363483863846, 'samples': 17628864, 'steps': 91816, 'loss/train': 1.851040005683899} 08/31/2021 05:53:37 - INFO - __main__ - Step 91818: {'lr': 0.00016763133792861758, 'samples': 17629056, 'steps': 91817, 'loss/train': 0.10350337624549866} 08/31/2021 05:53:37 - INFO - __main__ - Step 91819: {'lr': 0.0001676263275079647, 'samples': 17629248, 'steps': 91818, 'loss/train': 1.5551848411560059} 08/31/2021 05:53:37 - INFO - __main__ - Step 91820: {'lr': 0.00016762131712442802, 'samples': 17629440, 'steps': 91819, 'loss/train': 1.264161467552185} 08/31/2021 05:53:39 - INFO - __main__ - Step 91821: {'lr': 0.00016761630677800989, 'samples': 17629632, 'steps': 91820, 'loss/train': 1.6978638172149658} 08/31/2021 05:53:39 - INFO - __main__ - Step 91822: {'lr': 0.00016761129646871258, 'samples': 17629824, 'steps': 91821, 'loss/train': 0.9594314694404602} 08/31/2021 05:53:40 - INFO - __main__ - Step 91823: {'lr': 0.00016760628619653836, 'samples': 17630016, 'steps': 91822, 'loss/train': 0.7715468406677246} 08/31/2021 05:53:40 - INFO - __main__ - Step 91824: {'lr': 0.00016760127596148947, 'samples': 17630208, 'steps': 91823, 'loss/train': 1.271281361579895} 08/31/2021 05:53:40 - INFO - __main__ - Step 91825: {'lr': 0.0001675962657635682, 'samples': 17630400, 'steps': 91824, 'loss/train': 1.5144850015640259} 08/31/2021 05:53:42 - INFO - __main__ - Step 91826: {'lr': 0.00016759125560277674, 'samples': 17630592, 'steps': 91825, 'loss/train': 0.7694547176361084} 08/31/2021 05:53:42 - INFO - __main__ - Step 91827: {'lr': 0.0001675862454791174, 'samples': 17630784, 'steps': 91826, 'loss/train': 0.715798020362854} 08/31/2021 05:53:43 - INFO - __main__ - Step 91828: {'lr': 0.00016758123539259247, 'samples': 17630976, 'steps': 91827, 'loss/train': 1.4696681499481201} 08/31/2021 05:53:43 - INFO - __main__ - Step 91829: {'lr': 0.0001675762253432041, 'samples': 17631168, 'steps': 91828, 'loss/train': 1.264663815498352} 08/31/2021 05:53:43 - INFO - __main__ - Step 91830: {'lr': 0.00016757121533095466, 'samples': 17631360, 'steps': 91829, 'loss/train': 1.2169874906539917} 08/31/2021 05:53:45 - INFO - __main__ - Step 91831: {'lr': 0.00016756620535584633, 'samples': 17631552, 'steps': 91830, 'loss/train': 0.8905811905860901} 08/31/2021 05:53:46 - INFO - __main__ - Step 91832: {'lr': 0.00016756119541788138, 'samples': 17631744, 'steps': 91831, 'loss/train': 0.7132580876350403} 08/31/2021 05:53:46 - INFO - __main__ - Step 91833: {'lr': 0.00016755618551706224, 'samples': 17631936, 'steps': 91832, 'loss/train': 0.9624786972999573} 08/31/2021 05:53:47 - INFO - __main__ - Step 91834: {'lr': 0.00016755117565339084, 'samples': 17632128, 'steps': 91833, 'loss/train': 1.074312448501587} 08/31/2021 05:53:47 - INFO - __main__ - Step 91835: {'lr': 0.00016754616582686965, 'samples': 17632320, 'steps': 91834, 'loss/train': 1.5821832418441772} 08/31/2021 05:53:48 - INFO - __main__ - Step 91836: {'lr': 0.0001675411560375009, 'samples': 17632512, 'steps': 91835, 'loss/train': 1.2089914083480835} 08/31/2021 05:53:49 - INFO - __main__ - Step 91837: {'lr': 0.00016753614628528678, 'samples': 17632704, 'steps': 91836, 'loss/train': 0.8588213324546814} 08/31/2021 05:53:49 - INFO - __main__ - Step 91838: {'lr': 0.00016753113657022966, 'samples': 17632896, 'steps': 91837, 'loss/train': 0.9603636860847473} 08/31/2021 05:53:50 - INFO - __main__ - Step 91839: {'lr': 0.00016752612689233172, 'samples': 17633088, 'steps': 91838, 'loss/train': 0.916606605052948} 08/31/2021 05:53:50 - INFO - __main__ - Step 91840: {'lr': 0.00016752111725159522, 'samples': 17633280, 'steps': 91839, 'loss/train': 0.9993312954902649} 08/31/2021 05:53:52 - INFO - __main__ - Step 91841: {'lr': 0.00016751610764802245, 'samples': 17633472, 'steps': 91840, 'loss/train': 0.9077557921409607} 08/31/2021 05:53:52 - INFO - __main__ - Step 91842: {'lr': 0.00016751109808161563, 'samples': 17633664, 'steps': 91841, 'loss/train': 0.6428993344306946} 08/31/2021 05:53:52 - INFO - __main__ - Step 91843: {'lr': 0.00016750608855237704, 'samples': 17633856, 'steps': 91842, 'loss/train': 0.659929633140564} 08/31/2021 05:53:53 - INFO - __main__ - Step 91844: {'lr': 0.0001675010790603089, 'samples': 17634048, 'steps': 91843, 'loss/train': 1.0517187118530273} 08/31/2021 05:53:53 - INFO - __main__ - Step 91845: {'lr': 0.00016749606960541358, 'samples': 17634240, 'steps': 91844, 'loss/train': 1.5815629959106445} 08/31/2021 05:53:55 - INFO - __main__ - Step 91846: {'lr': 0.00016749106018769332, 'samples': 17634432, 'steps': 91845, 'loss/train': 0.9320741891860962} 08/31/2021 05:53:55 - INFO - __main__ - Step 91847: {'lr': 0.00016748605080715018, 'samples': 17634624, 'steps': 91846, 'loss/train': 1.146531105041504} 08/31/2021 05:53:56 - INFO - __main__ - Step 91848: {'lr': 0.0001674810414637866, 'samples': 17634816, 'steps': 91847, 'loss/train': 0.8211968541145325} 08/31/2021 05:53:56 - INFO - __main__ - Step 91849: {'lr': 0.00016747603215760477, 'samples': 17635008, 'steps': 91848, 'loss/train': 0.5871129631996155} 08/31/2021 05:53:56 - INFO - __main__ - Step 91850: {'lr': 0.00016747102288860695, 'samples': 17635200, 'steps': 91849, 'loss/train': 1.4785007238388062} 08/31/2021 05:53:57 - INFO - __main__ - Step 91851: {'lr': 0.00016746601365679543, 'samples': 17635392, 'steps': 91850, 'loss/train': 0.01734791323542595} 08/31/2021 05:53:58 - INFO - __main__ - Step 91852: {'lr': 0.00016746100446217245, 'samples': 17635584, 'steps': 91851, 'loss/train': 0.9673913717269897} 08/31/2021 05:53:59 - INFO - __main__ - Step 91853: {'lr': 0.0001674559953047403, 'samples': 17635776, 'steps': 91852, 'loss/train': 1.5011794567108154} 08/31/2021 05:53:59 - INFO - __main__ - Step 91854: {'lr': 0.00016745098618450117, 'samples': 17635968, 'steps': 91853, 'loss/train': 1.132612705230713} 08/31/2021 05:53:59 - INFO - __main__ - Step 91855: {'lr': 0.00016744597710145734, 'samples': 17636160, 'steps': 91854, 'loss/train': 1.4949065446853638} 08/31/2021 05:54:00 - INFO - __main__ - Step 91856: {'lr': 0.0001674409680556111, 'samples': 17636352, 'steps': 91855, 'loss/train': 1.4771441221237183} 08/31/2021 05:54:01 - INFO - __main__ - Step 91857: {'lr': 0.00016743595904696469, 'samples': 17636544, 'steps': 91856, 'loss/train': 2.1169328689575195} 08/31/2021 05:54:02 - INFO - __main__ - Step 91858: {'lr': 0.00016743095007552033, 'samples': 17636736, 'steps': 91857, 'loss/train': 1.0750662088394165} 08/31/2021 05:54:02 - INFO - __main__ - Step 91859: {'lr': 0.0001674259411412804, 'samples': 17636928, 'steps': 91858, 'loss/train': 1.1185094118118286} 08/31/2021 05:54:02 - INFO - __main__ - Step 91860: {'lr': 0.00016742093224424704, 'samples': 17637120, 'steps': 91859, 'loss/train': 1.288013219833374} 08/31/2021 05:54:03 - INFO - __main__ - Step 91861: {'lr': 0.00016741592338442252, 'samples': 17637312, 'steps': 91860, 'loss/train': 0.6614132523536682} 08/31/2021 05:54:03 - INFO - __main__ - Step 91862: {'lr': 0.00016741091456180907, 'samples': 17637504, 'steps': 91861, 'loss/train': 0.993766188621521} 08/31/2021 05:54:05 - INFO - __main__ - Step 91863: {'lr': 0.000167405905776409, 'samples': 17637696, 'steps': 91862, 'loss/train': 0.9920129776000977} 08/31/2021 05:54:05 - INFO - __main__ - Step 91864: {'lr': 0.00016740089702822457, 'samples': 17637888, 'steps': 91863, 'loss/train': 1.4712275266647339} 08/31/2021 05:54:05 - INFO - __main__ - Step 91865: {'lr': 0.000167395888317258, 'samples': 17638080, 'steps': 91864, 'loss/train': 1.1161328554153442} 08/31/2021 05:54:06 - INFO - __main__ - Step 91866: {'lr': 0.00016739087964351158, 'samples': 17638272, 'steps': 91865, 'loss/train': 0.965638279914856} 08/31/2021 05:54:06 - INFO - __main__ - Step 91867: {'lr': 0.00016738587100698755, 'samples': 17638464, 'steps': 91866, 'loss/train': 1.488904595375061} 08/31/2021 05:54:08 - INFO - __main__ - Step 91868: {'lr': 0.0001673808624076882, 'samples': 17638656, 'steps': 91867, 'loss/train': 1.0073879957199097} 08/31/2021 05:54:08 - INFO - __main__ - Step 91869: {'lr': 0.0001673758538456157, 'samples': 17638848, 'steps': 91868, 'loss/train': 0.43635812401771545} 08/31/2021 05:54:08 - INFO - __main__ - Step 91870: {'lr': 0.00016737084532077246, 'samples': 17639040, 'steps': 91869, 'loss/train': 0.7145663499832153} 08/31/2021 05:54:09 - INFO - __main__ - Step 91871: {'lr': 0.00016736583683316057, 'samples': 17639232, 'steps': 91870, 'loss/train': 1.4706432819366455} 08/31/2021 05:54:09 - INFO - __main__ - Step 91872: {'lr': 0.00016736082838278234, 'samples': 17639424, 'steps': 91871, 'loss/train': 1.0784579515457153} 08/31/2021 05:54:11 - INFO - __main__ - Step 91873: {'lr': 0.00016735581996964015, 'samples': 17639616, 'steps': 91872, 'loss/train': 0.9720486402511597} 08/31/2021 05:54:11 - INFO - __main__ - Step 91874: {'lr': 0.00016735081159373604, 'samples': 17639808, 'steps': 91873, 'loss/train': 1.38437819480896} 08/31/2021 05:54:12 - INFO - __main__ - Step 91875: {'lr': 0.00016734580325507243, 'samples': 17640000, 'steps': 91874, 'loss/train': 1.1911007165908813} 08/31/2021 05:54:12 - INFO - __main__ - Step 91876: {'lr': 0.0001673407949536515, 'samples': 17640192, 'steps': 91875, 'loss/train': 0.4583318531513214} 08/31/2021 05:54:12 - INFO - __main__ - Step 91877: {'lr': 0.0001673357866894756, 'samples': 17640384, 'steps': 91876, 'loss/train': 1.1960179805755615} 08/31/2021 05:54:14 - INFO - __main__ - Step 91878: {'lr': 0.00016733077846254682, 'samples': 17640576, 'steps': 91877, 'loss/train': 0.7781983017921448} 08/31/2021 05:54:14 - INFO - __main__ - Step 91879: {'lr': 0.00016732577027286756, 'samples': 17640768, 'steps': 91878, 'loss/train': 0.9531161785125732} 08/31/2021 05:54:15 - INFO - __main__ - Step 91880: {'lr': 0.00016732076212044002, 'samples': 17640960, 'steps': 91879, 'loss/train': 1.4579302072525024} 08/31/2021 05:54:15 - INFO - __main__ - Step 91881: {'lr': 0.00016731575400526656, 'samples': 17641152, 'steps': 91880, 'loss/train': 0.9074618220329285} 08/31/2021 05:54:16 - INFO - __main__ - Step 91882: {'lr': 0.00016731074592734924, 'samples': 17641344, 'steps': 91881, 'loss/train': 1.1335548162460327} 08/31/2021 05:54:18 - INFO - __main__ - Step 91883: {'lr': 0.00016730573788669047, 'samples': 17641536, 'steps': 91882, 'loss/train': 1.1537847518920898} 08/31/2021 05:54:18 - INFO - __main__ - Step 91884: {'lr': 0.0001673007298832924, 'samples': 17641728, 'steps': 91883, 'loss/train': 1.2201040983200073} 08/31/2021 05:54:18 - INFO - __main__ - Step 91885: {'lr': 0.00016729572191715735, 'samples': 17641920, 'steps': 91884, 'loss/train': 1.2740812301635742} 08/31/2021 05:54:19 - INFO - __main__ - Step 91886: {'lr': 0.0001672907139882877, 'samples': 17642112, 'steps': 91885, 'loss/train': 2.2019429206848145} 08/31/2021 05:54:19 - INFO - __main__ - Step 91887: {'lr': 0.00016728570609668547, 'samples': 17642304, 'steps': 91886, 'loss/train': 1.3314779996871948} 08/31/2021 05:54:21 - INFO - __main__ - Step 91888: {'lr': 0.00016728069824235303, 'samples': 17642496, 'steps': 91887, 'loss/train': 0.8738577961921692} 08/31/2021 05:54:22 - INFO - __main__ - Step 91889: {'lr': 0.0001672756904252926, 'samples': 17642688, 'steps': 91888, 'loss/train': 1.3144886493682861} 08/31/2021 05:54:22 - INFO - __main__ - Step 91890: {'lr': 0.00016727068264550652, 'samples': 17642880, 'steps': 91889, 'loss/train': 1.6487098932266235} 08/31/2021 05:54:22 - INFO - __main__ - Step 91891: {'lr': 0.00016726567490299698, 'samples': 17643072, 'steps': 91890, 'loss/train': 0.5115002393722534} 08/31/2021 05:54:23 - INFO - __main__ - Step 91892: {'lr': 0.00016726066719776627, 'samples': 17643264, 'steps': 91891, 'loss/train': 1.0505878925323486} 08/31/2021 05:54:24 - INFO - __main__ - Step 91893: {'lr': 0.00016725565952981663, 'samples': 17643456, 'steps': 91892, 'loss/train': 1.629658579826355} 08/31/2021 05:54:25 - INFO - __main__ - Step 91894: {'lr': 0.00016725065189915028, 'samples': 17643648, 'steps': 91893, 'loss/train': 1.162990927696228} 08/31/2021 05:54:25 - INFO - __main__ - Step 91895: {'lr': 0.0001672456443057695, 'samples': 17643840, 'steps': 91894, 'loss/train': 0.5463242530822754} 08/31/2021 05:54:26 - INFO - __main__ - Step 91896: {'lr': 0.00016724063674967656, 'samples': 17644032, 'steps': 91895, 'loss/train': 0.7719002366065979} 08/31/2021 05:54:26 - INFO - __main__ - Step 91897: {'lr': 0.00016723562923087374, 'samples': 17644224, 'steps': 91896, 'loss/train': 1.2394499778747559} 08/31/2021 05:54:26 - INFO - __main__ - Step 91898: {'lr': 0.00016723062174936327, 'samples': 17644416, 'steps': 91897, 'loss/train': 1.0597928762435913} 08/31/2021 05:54:28 - INFO - __main__ - Step 91899: {'lr': 0.00016722561430514737, 'samples': 17644608, 'steps': 91898, 'loss/train': 1.6912736892700195} 08/31/2021 05:54:28 - INFO - __main__ - Step 91900: {'lr': 0.00016722060689822838, 'samples': 17644800, 'steps': 91899, 'loss/train': 1.5370665788650513} 08/31/2021 05:54:29 - INFO - __main__ - Step 91901: {'lr': 0.0001672155995286085, 'samples': 17644992, 'steps': 91900, 'loss/train': 0.7514282464981079} 08/31/2021 05:54:29 - INFO - __main__ - Step 91902: {'lr': 0.0001672105921962899, 'samples': 17645184, 'steps': 91901, 'loss/train': 1.4343149662017822} 08/31/2021 05:54:29 - INFO - __main__ - Step 91903: {'lr': 0.0001672055849012751, 'samples': 17645376, 'steps': 91902, 'loss/train': 1.6991207599639893} 08/31/2021 05:54:31 - INFO - __main__ - Step 91904: {'lr': 0.00016720057764356606, 'samples': 17645568, 'steps': 91903, 'loss/train': 1.3147168159484863} 08/31/2021 05:54:31 - INFO - __main__ - Step 91905: {'lr': 0.0001671955704231652, 'samples': 17645760, 'steps': 91904, 'loss/train': 1.0543605089187622} 08/31/2021 05:54:31 - INFO - __main__ - Step 91906: {'lr': 0.0001671905632400747, 'samples': 17645952, 'steps': 91905, 'loss/train': 1.7402598857879639} 08/31/2021 05:54:32 - INFO - __main__ - Step 91907: {'lr': 0.0001671855560942969, 'samples': 17646144, 'steps': 91906, 'loss/train': 0.7948249578475952} 08/31/2021 05:54:32 - INFO - __main__ - Step 91908: {'lr': 0.00016718054898583396, 'samples': 17646336, 'steps': 91907, 'loss/train': 0.892385721206665} 08/31/2021 05:54:34 - INFO - __main__ - Step 91909: {'lr': 0.00016717554191468824, 'samples': 17646528, 'steps': 91908, 'loss/train': 1.0049293041229248} 08/31/2021 05:54:34 - INFO - __main__ - Step 91910: {'lr': 0.0001671705348808619, 'samples': 17646720, 'steps': 91909, 'loss/train': 0.8748869299888611} 08/31/2021 05:54:34 - INFO - __main__ - Step 91911: {'lr': 0.00016716552788435723, 'samples': 17646912, 'steps': 91910, 'loss/train': 1.0293807983398438} 08/31/2021 05:54:35 - INFO - __main__ - Step 91912: {'lr': 0.00016716052092517652, 'samples': 17647104, 'steps': 91911, 'loss/train': 1.1617844104766846} 08/31/2021 05:54:35 - INFO - __main__ - Step 91913: {'lr': 0.00016715551400332208, 'samples': 17647296, 'steps': 91912, 'loss/train': 1.034908652305603} 08/31/2021 05:54:37 - INFO - __main__ - Step 91914: {'lr': 0.00016715050711879604, 'samples': 17647488, 'steps': 91913, 'loss/train': 0.6317837834358215} 08/31/2021 05:54:37 - INFO - __main__ - Step 91915: {'lr': 0.0001671455002716007, 'samples': 17647680, 'steps': 91914, 'loss/train': 1.2171953916549683} 08/31/2021 05:54:37 - INFO - __main__ - Step 91916: {'lr': 0.00016714049346173827, 'samples': 17647872, 'steps': 91915, 'loss/train': 0.8661403059959412} 08/31/2021 05:54:38 - INFO - __main__ - Step 91917: {'lr': 0.00016713548668921107, 'samples': 17648064, 'steps': 91916, 'loss/train': 1.1322919130325317} 08/31/2021 05:54:38 - INFO - __main__ - Step 91918: {'lr': 0.00016713047995402136, 'samples': 17648256, 'steps': 91917, 'loss/train': 0.6463611721992493} 08/31/2021 05:54:40 - INFO - __main__ - Step 91919: {'lr': 0.00016712547325617132, 'samples': 17648448, 'steps': 91918, 'loss/train': 1.0028223991394043} 08/31/2021 05:54:40 - INFO - __main__ - Step 91920: {'lr': 0.00016712046659566332, 'samples': 17648640, 'steps': 91919, 'loss/train': 1.2459443807601929} 08/31/2021 05:54:40 - INFO - __main__ - Step 91921: {'lr': 0.00016711545997249956, 'samples': 17648832, 'steps': 91920, 'loss/train': 0.75472092628479} 08/31/2021 05:54:41 - INFO - __main__ - Step 91922: {'lr': 0.0001671104533866823, 'samples': 17649024, 'steps': 91921, 'loss/train': 1.401382327079773} 08/31/2021 05:54:41 - INFO - __main__ - Step 91923: {'lr': 0.00016710544683821375, 'samples': 17649216, 'steps': 91922, 'loss/train': 2.492358922958374} 08/31/2021 05:54:42 - INFO - __main__ - Step 91924: {'lr': 0.0001671004403270962, 'samples': 17649408, 'steps': 91923, 'loss/train': 0.7222216725349426} 08/31/2021 05:54:43 - INFO - __main__ - Step 91925: {'lr': 0.00016709543385333198, 'samples': 17649600, 'steps': 91924, 'loss/train': 1.3430278301239014} 08/31/2021 05:54:44 - INFO - __main__ - Step 91926: {'lr': 0.0001670904274169232, 'samples': 17649792, 'steps': 91925, 'loss/train': 0.9493975639343262} 08/31/2021 05:54:44 - INFO - __main__ - Step 91927: {'lr': 0.00016708542101787237, 'samples': 17649984, 'steps': 91926, 'loss/train': 0.8366975784301758} 08/31/2021 05:54:44 - INFO - __main__ - Step 91928: {'lr': 0.0001670804146561814, 'samples': 17650176, 'steps': 91927, 'loss/train': 0.8029015064239502} 08/31/2021 05:54:45 - INFO - __main__ - Step 91929: {'lr': 0.00016707540833185274, 'samples': 17650368, 'steps': 91928, 'loss/train': 1.541301965713501} 08/31/2021 05:54:46 - INFO - __main__ - Step 91930: {'lr': 0.00016707040204488866, 'samples': 17650560, 'steps': 91929, 'loss/train': 0.8383387327194214} 08/31/2021 05:54:47 - INFO - __main__ - Step 91931: {'lr': 0.00016706539579529133, 'samples': 17650752, 'steps': 91930, 'loss/train': 1.0423247814178467} 08/31/2021 05:54:47 - INFO - __main__ - Step 91932: {'lr': 0.00016706038958306306, 'samples': 17650944, 'steps': 91931, 'loss/train': 1.0846186876296997} 08/31/2021 05:54:47 - INFO - __main__ - Step 91933: {'lr': 0.0001670553834082061, 'samples': 17651136, 'steps': 91932, 'loss/train': 2.1840755939483643} 08/31/2021 05:54:48 - INFO - __main__ - Step 91934: {'lr': 0.00016705037727072271, 'samples': 17651328, 'steps': 91933, 'loss/train': 0.9139794707298279} 08/31/2021 05:54:48 - INFO - __main__ - Step 91935: {'lr': 0.00016704537117061513, 'samples': 17651520, 'steps': 91934, 'loss/train': 0.21522827446460724} 08/31/2021 05:54:50 - INFO - __main__ - Step 91936: {'lr': 0.00016704036510788568, 'samples': 17651712, 'steps': 91935, 'loss/train': 0.8817808032035828} 08/31/2021 05:54:50 - INFO - __main__ - Step 91937: {'lr': 0.00016703535908253647, 'samples': 17651904, 'steps': 91936, 'loss/train': 1.4146982431411743} 08/31/2021 05:54:50 - INFO - __main__ - Step 91938: {'lr': 0.00016703035309456992, 'samples': 17652096, 'steps': 91937, 'loss/train': 0.6922023296356201} 08/31/2021 05:54:51 - INFO - __main__ - Step 91939: {'lr': 0.0001670253471439882, 'samples': 17652288, 'steps': 91938, 'loss/train': 1.543115258216858} 08/31/2021 05:54:51 - INFO - __main__ - Step 91940: {'lr': 0.00016702034123079366, 'samples': 17652480, 'steps': 91939, 'loss/train': 1.2869356870651245} 08/31/2021 05:54:53 - INFO - __main__ - Step 91941: {'lr': 0.00016701533535498837, 'samples': 17652672, 'steps': 91940, 'loss/train': 1.0676698684692383} 08/31/2021 05:54:54 - INFO - __main__ - Step 91942: {'lr': 0.00016701032951657469, 'samples': 17652864, 'steps': 91941, 'loss/train': 1.363939642906189} 08/31/2021 05:54:54 - INFO - __main__ - Step 91943: {'lr': 0.00016700532371555487, 'samples': 17653056, 'steps': 91942, 'loss/train': 0.5674118399620056} 08/31/2021 05:54:54 - INFO - __main__ - Step 91944: {'lr': 0.00016700031795193122, 'samples': 17653248, 'steps': 91943, 'loss/train': 1.2208976745605469} 08/31/2021 05:54:55 - INFO - __main__ - Step 91945: {'lr': 0.0001669953122257059, 'samples': 17653440, 'steps': 91944, 'loss/train': 0.8156231641769409} 08/31/2021 05:54:56 - INFO - __main__ - Step 91946: {'lr': 0.00016699030653688122, 'samples': 17653632, 'steps': 91945, 'loss/train': 0.9011988639831543} 08/31/2021 05:54:57 - INFO - __main__ - Step 91947: {'lr': 0.00016698530088545943, 'samples': 17653824, 'steps': 91946, 'loss/train': 0.8862199783325195} 08/31/2021 05:54:57 - INFO - __main__ - Step 91948: {'lr': 0.00016698029527144277, 'samples': 17654016, 'steps': 91947, 'loss/train': 1.1371880769729614} 08/31/2021 05:54:57 - INFO - __main__ - Step 91949: {'lr': 0.00016697528969483353, 'samples': 17654208, 'steps': 91948, 'loss/train': 0.8624998927116394} 08/31/2021 05:54:58 - INFO - __main__ - Step 91950: {'lr': 0.00016697028415563393, 'samples': 17654400, 'steps': 91949, 'loss/train': 1.059914469718933} 08/31/2021 05:54:59 - INFO - __main__ - Step 91951: {'lr': 0.00016696527865384627, 'samples': 17654592, 'steps': 91950, 'loss/train': 1.3645752668380737} 08/31/2021 05:55:00 - INFO - __main__ - Step 91952: {'lr': 0.0001669602731894727, 'samples': 17654784, 'steps': 91951, 'loss/train': 1.8285338878631592} 08/31/2021 05:55:00 - INFO - __main__ - Step 91953: {'lr': 0.0001669552677625156, 'samples': 17654976, 'steps': 91952, 'loss/train': 1.2667895555496216} 08/31/2021 05:55:00 - INFO - __main__ - Step 91954: {'lr': 0.00016695026237297729, 'samples': 17655168, 'steps': 91953, 'loss/train': 0.99178147315979} 08/31/2021 05:55:01 - INFO - __main__ - Step 91955: {'lr': 0.00016694525702085978, 'samples': 17655360, 'steps': 91954, 'loss/train': 1.6677827835083008} 08/31/2021 05:55:02 - INFO - __main__ - Step 91956: {'lr': 0.00016694025170616546, 'samples': 17655552, 'steps': 91955, 'loss/train': 1.2487311363220215} 08/31/2021 05:55:03 - INFO - __main__ - Step 91957: {'lr': 0.00016693524642889658, 'samples': 17655744, 'steps': 91956, 'loss/train': 1.2177481651306152} 08/31/2021 05:55:03 - INFO - __main__ - Step 91958: {'lr': 0.0001669302411890554, 'samples': 17655936, 'steps': 91957, 'loss/train': 0.9513242840766907} 08/31/2021 05:55:04 - INFO - __main__ - Step 91959: {'lr': 0.00016692523598664416, 'samples': 17656128, 'steps': 91958, 'loss/train': 1.2970277070999146} 08/31/2021 05:55:04 - INFO - __main__ - Step 91960: {'lr': 0.00016692023082166515, 'samples': 17656320, 'steps': 91959, 'loss/train': 1.495201826095581} 08/31/2021 05:55:04 - INFO - __main__ - Step 91961: {'lr': 0.0001669152256941206, 'samples': 17656512, 'steps': 91960, 'loss/train': 1.1347774267196655} 08/31/2021 05:55:06 - INFO - __main__ - Step 91962: {'lr': 0.00016691022060401274, 'samples': 17656704, 'steps': 91961, 'loss/train': 0.04678839445114136} 08/31/2021 05:55:06 - INFO - __main__ - Step 91963: {'lr': 0.00016690521555134388, 'samples': 17656896, 'steps': 91962, 'loss/train': 1.9719672203063965} 08/31/2021 05:55:07 - INFO - __main__ - Step 91964: {'lr': 0.00016690021053611626, 'samples': 17657088, 'steps': 91963, 'loss/train': 1.582905650138855} 08/31/2021 05:55:07 - INFO - __main__ - Step 91965: {'lr': 0.0001668952055583321, 'samples': 17657280, 'steps': 91964, 'loss/train': 0.09126084297895432} 08/31/2021 05:55:07 - INFO - __main__ - Step 91966: {'lr': 0.00016689020061799368, 'samples': 17657472, 'steps': 91965, 'loss/train': 0.3711850643157959} 08/31/2021 05:55:09 - INFO - __main__ - Step 91967: {'lr': 0.00016688519571510336, 'samples': 17657664, 'steps': 91966, 'loss/train': 1.8324923515319824} 08/31/2021 05:55:09 - INFO - __main__ - Step 91968: {'lr': 0.00016688019084966317, 'samples': 17657856, 'steps': 91967, 'loss/train': 1.7232797145843506} 08/31/2021 05:55:10 - INFO - __main__ - Step 91969: {'lr': 0.0001668751860216755, 'samples': 17658048, 'steps': 91968, 'loss/train': 0.6250990629196167} 08/31/2021 05:55:10 - INFO - __main__ - Step 91970: {'lr': 0.00016687018123114257, 'samples': 17658240, 'steps': 91969, 'loss/train': 1.2699990272521973} 08/31/2021 05:55:10 - INFO - __main__ - Step 91971: {'lr': 0.00016686517647806668, 'samples': 17658432, 'steps': 91970, 'loss/train': 1.194043755531311} 08/31/2021 05:55:11 - INFO - __main__ - Step 91972: {'lr': 0.00016686017176245006, 'samples': 17658624, 'steps': 91971, 'loss/train': 1.404995322227478} 08/31/2021 05:55:12 - INFO - __main__ - Step 91973: {'lr': 0.00016685516708429493, 'samples': 17658816, 'steps': 91972, 'loss/train': 0.49751386046409607} 08/31/2021 05:55:13 - INFO - __main__ - Step 91974: {'lr': 0.0001668501624436036, 'samples': 17659008, 'steps': 91973, 'loss/train': 1.2459807395935059} 08/31/2021 05:55:13 - INFO - __main__ - Step 91975: {'lr': 0.0001668451578403783, 'samples': 17659200, 'steps': 91974, 'loss/train': 1.8552024364471436} 08/31/2021 05:55:13 - INFO - __main__ - Step 91976: {'lr': 0.0001668401532746213, 'samples': 17659392, 'steps': 91975, 'loss/train': 0.6765051484107971} 08/31/2021 05:55:14 - INFO - __main__ - Step 91977: {'lr': 0.00016683514874633483, 'samples': 17659584, 'steps': 91976, 'loss/train': 1.2987381219863892} 08/31/2021 05:55:16 - INFO - __main__ - Step 91978: {'lr': 0.00016683014425552116, 'samples': 17659776, 'steps': 91977, 'loss/train': 0.9537914991378784} 08/31/2021 05:55:16 - INFO - __main__ - Step 91979: {'lr': 0.00016682513980218256, 'samples': 17659968, 'steps': 91978, 'loss/train': 1.2982308864593506} 08/31/2021 05:55:17 - INFO - __main__ - Step 91980: {'lr': 0.00016682013538632125, 'samples': 17660160, 'steps': 91979, 'loss/train': 0.7676099538803101} 08/31/2021 05:55:17 - INFO - __main__ - Step 91981: {'lr': 0.0001668151310079396, 'samples': 17660352, 'steps': 91980, 'loss/train': 0.9007136821746826} 08/31/2021 05:55:17 - INFO - __main__ - Step 91982: {'lr': 0.0001668101266670397, 'samples': 17660544, 'steps': 91981, 'loss/train': 0.9024258255958557} 08/31/2021 05:55:18 - INFO - __main__ - Step 91983: {'lr': 0.00016680512236362383, 'samples': 17660736, 'steps': 91982, 'loss/train': 1.2959612607955933} 08/31/2021 05:55:19 - INFO - __main__ - Step 91984: {'lr': 0.0001668001180976943, 'samples': 17660928, 'steps': 91983, 'loss/train': 0.07340458780527115} 08/31/2021 05:55:20 - INFO - __main__ - Step 91985: {'lr': 0.00016679511386925337, 'samples': 17661120, 'steps': 91984, 'loss/train': 1.5971983671188354} 08/31/2021 05:55:20 - INFO - __main__ - Step 91986: {'lr': 0.00016679010967830327, 'samples': 17661312, 'steps': 91985, 'loss/train': 0.6783047318458557} 08/31/2021 05:55:20 - INFO - __main__ - Step 91987: {'lr': 0.00016678510552484626, 'samples': 17661504, 'steps': 91986, 'loss/train': 0.9898818135261536} 08/31/2021 05:55:21 - INFO - __main__ - Step 91988: {'lr': 0.0001667801014088846, 'samples': 17661696, 'steps': 91987, 'loss/train': 0.9741455912590027} 08/31/2021 05:55:22 - INFO - __main__ - Step 91989: {'lr': 0.0001667750973304205, 'samples': 17661888, 'steps': 91988, 'loss/train': 1.1740667819976807} 08/31/2021 05:55:22 - INFO - __main__ - Step 91990: {'lr': 0.00016677009328945632, 'samples': 17662080, 'steps': 91989, 'loss/train': 1.460663080215454} 08/31/2021 05:55:23 - INFO - __main__ - Step 91991: {'lr': 0.00016676508928599424, 'samples': 17662272, 'steps': 91990, 'loss/train': 1.0171090364456177} 08/31/2021 05:55:23 - INFO - __main__ - Step 91992: {'lr': 0.0001667600853200365, 'samples': 17662464, 'steps': 91991, 'loss/train': 1.318803071975708} 08/31/2021 05:55:24 - INFO - __main__ - Step 91993: {'lr': 0.0001667550813915854, 'samples': 17662656, 'steps': 91992, 'loss/train': 1.0973106622695923} 08/31/2021 05:55:26 - INFO - __main__ - Step 91994: {'lr': 0.00016675007750064331, 'samples': 17662848, 'steps': 91993, 'loss/train': 1.558916687965393} 08/31/2021 05:55:26 - INFO - __main__ - Step 91995: {'lr': 0.0001667450736472122, 'samples': 17663040, 'steps': 91994, 'loss/train': 0.745836615562439} 08/31/2021 05:55:27 - INFO - __main__ - Step 91996: {'lr': 0.00016674006983129447, 'samples': 17663232, 'steps': 91995, 'loss/train': 0.027277732267975807} 08/31/2021 05:55:27 - INFO - __main__ - Step 91997: {'lr': 0.0001667350660528924, 'samples': 17663424, 'steps': 91996, 'loss/train': 1.2298924922943115} 08/31/2021 05:55:27 - INFO - __main__ - Step 91998: {'lr': 0.00016673006231200823, 'samples': 17663616, 'steps': 91997, 'loss/train': 1.0067188739776611} 08/31/2021 05:55:29 - INFO - __main__ - Step 91999: {'lr': 0.0001667250586086442, 'samples': 17663808, 'steps': 91998, 'loss/train': 0.4805457890033722} 08/31/2021 05:55:29 - INFO - __main__ - Step 92000: {'lr': 0.00016672005494280256, 'samples': 17664000, 'steps': 91999, 'loss/train': 0.919045090675354} 08/31/2021 05:55:30 - INFO - __main__ - Step 92001: {'lr': 0.0001667150513144856, 'samples': 17664192, 'steps': 92000, 'loss/train': 0.3331758677959442} 08/31/2021 05:55:30 - INFO - __main__ - Step 92002: {'lr': 0.00016671004772369555, 'samples': 17664384, 'steps': 92001, 'loss/train': 1.3527183532714844} 08/31/2021 05:55:30 - INFO - __main__ - Step 92003: {'lr': 0.00016670504417043465, 'samples': 17664576, 'steps': 92002, 'loss/train': 1.1432838439941406} 08/31/2021 05:55:32 - INFO - __main__ - Step 92004: {'lr': 0.0001667000406547052, 'samples': 17664768, 'steps': 92003, 'loss/train': 0.03033997118473053} 08/31/2021 05:55:32 - INFO - __main__ - Step 92005: {'lr': 0.00016669503717650947, 'samples': 17664960, 'steps': 92004, 'loss/train': 0.04090656340122223} 08/31/2021 05:55:33 - INFO - __main__ - Step 92006: {'lr': 0.0001666900337358496, 'samples': 17665152, 'steps': 92005, 'loss/train': 1.1000930070877075} 08/31/2021 05:55:33 - INFO - __main__ - Step 92007: {'lr': 0.00016668503033272797, 'samples': 17665344, 'steps': 92006, 'loss/train': 1.9476739168167114} 08/31/2021 05:55:33 - INFO - __main__ - Step 92008: {'lr': 0.00016668002696714675, 'samples': 17665536, 'steps': 92007, 'loss/train': 1.113944411277771} 08/31/2021 05:55:34 - INFO - __main__ - Step 92009: {'lr': 0.0001666750236391082, 'samples': 17665728, 'steps': 92008, 'loss/train': 1.2944241762161255} 08/31/2021 05:55:35 - INFO - __main__ - Step 92010: {'lr': 0.00016667002034861461, 'samples': 17665920, 'steps': 92009, 'loss/train': 0.9297904372215271} 08/31/2021 05:55:36 - INFO - __main__ - Step 92011: {'lr': 0.00016666501709566823, 'samples': 17666112, 'steps': 92010, 'loss/train': 0.31732359528541565} 08/31/2021 05:55:36 - INFO - __main__ - Step 92012: {'lr': 0.0001666600138802713, 'samples': 17666304, 'steps': 92011, 'loss/train': 1.4740331172943115} 08/31/2021 05:55:36 - INFO - __main__ - Step 92013: {'lr': 0.0001666550107024261, 'samples': 17666496, 'steps': 92012, 'loss/train': 1.2337095737457275} 08/31/2021 05:55:37 - INFO - __main__ - Step 92014: {'lr': 0.00016665000756213482, 'samples': 17666688, 'steps': 92013, 'loss/train': 1.1381700038909912} 08/31/2021 05:55:38 - INFO - __main__ - Step 92015: {'lr': 0.0001666450044593998, 'samples': 17666880, 'steps': 92014, 'loss/train': 0.8304467797279358} 08/31/2021 05:55:39 - INFO - __main__ - Step 92016: {'lr': 0.0001666400013942233, 'samples': 17667072, 'steps': 92015, 'loss/train': 1.3940762281417847} 08/31/2021 05:55:39 - INFO - __main__ - Step 92017: {'lr': 0.00016663499836660746, 'samples': 17667264, 'steps': 92016, 'loss/train': 0.8817962408065796} 08/31/2021 05:55:39 - INFO - __main__ - Step 92018: {'lr': 0.0001666299953765546, 'samples': 17667456, 'steps': 92017, 'loss/train': 0.8676589727401733} 08/31/2021 05:55:40 - INFO - __main__ - Step 92019: {'lr': 0.000166624992424067, 'samples': 17667648, 'steps': 92018, 'loss/train': 1.1881510019302368} 08/31/2021 05:55:41 - INFO - __main__ - Step 92020: {'lr': 0.0001666199895091469, 'samples': 17667840, 'steps': 92019, 'loss/train': 1.1671926975250244} 08/31/2021 05:55:42 - INFO - __main__ - Step 92021: {'lr': 0.0001666149866317966, 'samples': 17668032, 'steps': 92020, 'loss/train': 1.2380659580230713} 08/31/2021 05:55:42 - INFO - __main__ - Step 92022: {'lr': 0.0001666099837920182, 'samples': 17668224, 'steps': 92021, 'loss/train': 0.7029987573623657} 08/31/2021 05:55:42 - INFO - __main__ - Step 92023: {'lr': 0.00016660498098981409, 'samples': 17668416, 'steps': 92022, 'loss/train': 1.167054533958435} 08/31/2021 05:55:43 - INFO - __main__ - Step 92024: {'lr': 0.0001665999782251865, 'samples': 17668608, 'steps': 92023, 'loss/train': 1.4014664888381958} 08/31/2021 05:55:45 - INFO - __main__ - Step 92025: {'lr': 0.00016659497549813761, 'samples': 17668800, 'steps': 92024, 'loss/train': 1.2964119911193848} 08/31/2021 05:55:45 - INFO - __main__ - Step 92026: {'lr': 0.00016658997280866988, 'samples': 17668992, 'steps': 92025, 'loss/train': 1.2341471910476685} 08/31/2021 05:55:45 - INFO - __main__ - Step 92027: {'lr': 0.00016658497015678531, 'samples': 17669184, 'steps': 92026, 'loss/train': 1.092199683189392} 08/31/2021 05:55:46 - INFO - __main__ - Step 92028: {'lr': 0.00016657996754248627, 'samples': 17669376, 'steps': 92027, 'loss/train': 1.5196324586868286} 08/31/2021 05:55:46 - INFO - __main__ - Step 92029: {'lr': 0.00016657496496577505, 'samples': 17669568, 'steps': 92028, 'loss/train': 1.2479143142700195} 08/31/2021 05:55:46 - INFO - __main__ - Step 92030: {'lr': 0.00016656996242665382, 'samples': 17669760, 'steps': 92029, 'loss/train': 0.01878305710852146} 08/31/2021 05:55:48 - INFO - __main__ - Step 92031: {'lr': 0.0001665649599251249, 'samples': 17669952, 'steps': 92030, 'loss/train': 1.051853060722351} 08/31/2021 05:55:49 - INFO - __main__ - Step 92032: {'lr': 0.0001665599574611905, 'samples': 17670144, 'steps': 92031, 'loss/train': 0.8840014338493347} 08/31/2021 05:55:49 - INFO - __main__ - Step 92033: {'lr': 0.0001665549550348529, 'samples': 17670336, 'steps': 92032, 'loss/train': 1.7758504152297974} 08/31/2021 05:55:49 - INFO - __main__ - Step 92034: {'lr': 0.0001665499526461144, 'samples': 17670528, 'steps': 92033, 'loss/train': 1.7640674114227295} 08/31/2021 05:55:50 - INFO - __main__ - Step 92035: {'lr': 0.00016654495029497717, 'samples': 17670720, 'steps': 92034, 'loss/train': 0.6760334372520447} 08/31/2021 05:55:50 - INFO - __main__ - Step 92036: {'lr': 0.0001665399479814435, 'samples': 17670912, 'steps': 92035, 'loss/train': 1.6052823066711426} 08/31/2021 05:55:52 - INFO - __main__ - Step 92037: {'lr': 0.0001665349457055157, 'samples': 17671104, 'steps': 92036, 'loss/train': 1.4493374824523926} 08/31/2021 05:55:52 - INFO - __main__ - Step 92038: {'lr': 0.0001665299434671959, 'samples': 17671296, 'steps': 92037, 'loss/train': 0.753395140171051} 08/31/2021 05:55:53 - INFO - __main__ - Step 92039: {'lr': 0.00016652494126648636, 'samples': 17671488, 'steps': 92038, 'loss/train': 1.8253535032272339} 08/31/2021 05:55:53 - INFO - __main__ - Step 92040: {'lr': 0.00016651993910338946, 'samples': 17671680, 'steps': 92039, 'loss/train': 1.476396083831787} 08/31/2021 05:55:53 - INFO - __main__ - Step 92041: {'lr': 0.0001665149369779074, 'samples': 17671872, 'steps': 92040, 'loss/train': 1.2900604009628296} 08/31/2021 05:55:54 - INFO - __main__ - Step 92042: {'lr': 0.0001665099348900424, 'samples': 17672064, 'steps': 92041, 'loss/train': 1.1348315477371216} 08/31/2021 05:55:55 - INFO - __main__ - Step 92043: {'lr': 0.00016650493283979672, 'samples': 17672256, 'steps': 92042, 'loss/train': 1.5513029098510742} 08/31/2021 05:55:56 - INFO - __main__ - Step 92044: {'lr': 0.00016649993082717263, 'samples': 17672448, 'steps': 92043, 'loss/train': 0.7796447277069092} 08/31/2021 05:55:56 - INFO - __main__ - Step 92045: {'lr': 0.00016649492885217242, 'samples': 17672640, 'steps': 92044, 'loss/train': 1.431495189666748} 08/31/2021 05:55:56 - INFO - __main__ - Step 92046: {'lr': 0.00016648992691479828, 'samples': 17672832, 'steps': 92045, 'loss/train': 1.2393096685409546} 08/31/2021 05:55:57 - INFO - __main__ - Step 92047: {'lr': 0.00016648492501505246, 'samples': 17673024, 'steps': 92046, 'loss/train': 1.3225529193878174} 08/31/2021 05:55:59 - INFO - __main__ - Step 92048: {'lr': 0.00016647992315293742, 'samples': 17673216, 'steps': 92047, 'loss/train': 1.3187527656555176} 08/31/2021 05:55:59 - INFO - __main__ - Step 92049: {'lr': 0.00016647492132845508, 'samples': 17673408, 'steps': 92048, 'loss/train': 0.8138348460197449} 08/31/2021 05:56:00 - INFO - __main__ - Step 92050: {'lr': 0.00016646991954160785, 'samples': 17673600, 'steps': 92049, 'loss/train': 1.3040649890899658} 08/31/2021 05:56:00 - INFO - __main__ - Step 92051: {'lr': 0.000166464917792398, 'samples': 17673792, 'steps': 92050, 'loss/train': 1.3290374279022217} 08/31/2021 05:56:00 - INFO - __main__ - Step 92052: {'lr': 0.00016645991608082777, 'samples': 17673984, 'steps': 92051, 'loss/train': 1.138204574584961} 08/31/2021 05:56:02 - INFO - __main__ - Step 92053: {'lr': 0.00016645491440689942, 'samples': 17674176, 'steps': 92052, 'loss/train': 1.4379212856292725} 08/31/2021 05:56:02 - INFO - __main__ - Step 92054: {'lr': 0.00016644991277061516, 'samples': 17674368, 'steps': 92053, 'loss/train': 1.1537567377090454} 08/31/2021 05:56:03 - INFO - __main__ - Step 92055: {'lr': 0.00016644491117197733, 'samples': 17674560, 'steps': 92054, 'loss/train': 0.9857545495033264} 08/31/2021 05:56:03 - INFO - __main__ - Step 92056: {'lr': 0.0001664399096109881, 'samples': 17674752, 'steps': 92055, 'loss/train': 1.5932563543319702} 08/31/2021 05:56:03 - INFO - __main__ - Step 92057: {'lr': 0.00016643490808764978, 'samples': 17674944, 'steps': 92056, 'loss/train': 1.2529798746109009} 08/31/2021 05:56:05 - INFO - __main__ - Step 92058: {'lr': 0.00016642990660196462, 'samples': 17675136, 'steps': 92057, 'loss/train': 1.6301947832107544} 08/31/2021 05:56:05 - INFO - __main__ - Step 92059: {'lr': 0.0001664249051539348, 'samples': 17675328, 'steps': 92058, 'loss/train': 1.485026240348816} 08/31/2021 05:56:06 - INFO - __main__ - Step 92060: {'lr': 0.00016641990374356263, 'samples': 17675520, 'steps': 92059, 'loss/train': 1.1155147552490234} 08/31/2021 05:56:06 - INFO - __main__ - Step 92061: {'lr': 0.0001664149023708505, 'samples': 17675712, 'steps': 92060, 'loss/train': 0.7753612995147705} 08/31/2021 05:56:06 - INFO - __main__ - Step 92062: {'lr': 0.0001664099010358004, 'samples': 17675904, 'steps': 92061, 'loss/train': 1.322608232498169} 08/31/2021 05:56:08 - INFO - __main__ - Step 92063: {'lr': 0.00016640489973841473, 'samples': 17676096, 'steps': 92062, 'loss/train': 1.2029165029525757} 08/31/2021 05:56:08 - INFO - __main__ - Step 92064: {'lr': 0.0001663998984786957, 'samples': 17676288, 'steps': 92063, 'loss/train': 1.384680151939392} 08/31/2021 05:56:09 - INFO - __main__ - Step 92065: {'lr': 0.0001663948972566456, 'samples': 17676480, 'steps': 92064, 'loss/train': 0.9186170697212219} 08/31/2021 05:56:09 - INFO - __main__ - Step 92066: {'lr': 0.00016638989607226668, 'samples': 17676672, 'steps': 92065, 'loss/train': 1.0917984247207642} 08/31/2021 05:56:09 - INFO - __main__ - Step 92067: {'lr': 0.00016638489492556115, 'samples': 17676864, 'steps': 92066, 'loss/train': 0.6495090126991272} 08/31/2021 05:56:11 - INFO - __main__ - Step 92068: {'lr': 0.00016637989381653131, 'samples': 17677056, 'steps': 92067, 'loss/train': 1.2057287693023682} 08/31/2021 05:56:11 - INFO - __main__ - Step 92069: {'lr': 0.0001663748927451794, 'samples': 17677248, 'steps': 92068, 'loss/train': 1.7657054662704468} 08/31/2021 05:56:12 - INFO - __main__ - Step 92070: {'lr': 0.00016636989171150767, 'samples': 17677440, 'steps': 92069, 'loss/train': 1.6461752653121948} 08/31/2021 05:56:12 - INFO - __main__ - Step 92071: {'lr': 0.0001663648907155184, 'samples': 17677632, 'steps': 92070, 'loss/train': 1.4342764616012573} 08/31/2021 05:56:12 - INFO - __main__ - Step 92072: {'lr': 0.0001663598897572138, 'samples': 17677824, 'steps': 92071, 'loss/train': 1.2587920427322388} 08/31/2021 05:56:14 - INFO - __main__ - Step 92073: {'lr': 0.00016635488883659616, 'samples': 17678016, 'steps': 92072, 'loss/train': 1.6352756023406982} 08/31/2021 05:56:14 - INFO - __main__ - Step 92074: {'lr': 0.00016634988795366767, 'samples': 17678208, 'steps': 92073, 'loss/train': 1.4173791408538818} 08/31/2021 05:56:15 - INFO - __main__ - Step 92075: {'lr': 0.00016634488710843076, 'samples': 17678400, 'steps': 92074, 'loss/train': 1.289307713508606} 08/31/2021 05:56:15 - INFO - __main__ - Step 92076: {'lr': 0.00016633988630088747, 'samples': 17678592, 'steps': 92075, 'loss/train': 1.261245846748352} 08/31/2021 05:56:15 - INFO - __main__ - Step 92077: {'lr': 0.00016633488553104015, 'samples': 17678784, 'steps': 92076, 'loss/train': 1.6840031147003174} 08/31/2021 05:56:17 - INFO - __main__ - Step 92078: {'lr': 0.000166329884798891, 'samples': 17678976, 'steps': 92077, 'loss/train': 1.2331833839416504} 08/31/2021 05:56:17 - INFO - __main__ - Step 92079: {'lr': 0.0001663248841044423, 'samples': 17679168, 'steps': 92078, 'loss/train': 1.4752165079116821} 08/31/2021 05:56:18 - INFO - __main__ - Step 92080: {'lr': 0.00016631988344769632, 'samples': 17679360, 'steps': 92079, 'loss/train': 0.9509297013282776} 08/31/2021 05:56:18 - INFO - __main__ - Step 92081: {'lr': 0.00016631488282865537, 'samples': 17679552, 'steps': 92080, 'loss/train': 1.4089434146881104} 08/31/2021 05:56:18 - INFO - __main__ - Step 92082: {'lr': 0.00016630988224732157, 'samples': 17679744, 'steps': 92081, 'loss/train': 0.7562434673309326} 08/31/2021 05:56:19 - INFO - __main__ - Step 92083: {'lr': 0.0001663048817036973, 'samples': 17679936, 'steps': 92082, 'loss/train': 1.0257054567337036} 08/31/2021 05:56:20 - INFO - __main__ - Step 92084: {'lr': 0.00016629988119778473, 'samples': 17680128, 'steps': 92083, 'loss/train': 0.808858335018158} 08/31/2021 05:56:21 - INFO - __main__ - Step 92085: {'lr': 0.00016629488072958615, 'samples': 17680320, 'steps': 92084, 'loss/train': 0.6652652621269226} 08/31/2021 05:56:21 - INFO - __main__ - Step 92086: {'lr': 0.00016628988029910381, 'samples': 17680512, 'steps': 92085, 'loss/train': 0.801990807056427} 08/31/2021 05:56:21 - INFO - __main__ - Step 92087: {'lr': 0.00016628487990633995, 'samples': 17680704, 'steps': 92086, 'loss/train': 1.1488300561904907} 08/31/2021 05:56:22 - INFO - __main__ - Step 92088: {'lr': 0.00016627987955129692, 'samples': 17680896, 'steps': 92087, 'loss/train': 1.094689130783081} 08/31/2021 05:56:23 - INFO - __main__ - Step 92089: {'lr': 0.0001662748792339768, 'samples': 17681088, 'steps': 92088, 'loss/train': 1.682841181755066} 08/31/2021 05:56:24 - INFO - __main__ - Step 92090: {'lr': 0.0001662698789543819, 'samples': 17681280, 'steps': 92089, 'loss/train': 0.9566135406494141} 08/31/2021 05:56:24 - INFO - __main__ - Step 92091: {'lr': 0.00016626487871251457, 'samples': 17681472, 'steps': 92090, 'loss/train': 0.32970717549324036} 08/31/2021 05:56:24 - INFO - __main__ - Step 92092: {'lr': 0.00016625987850837692, 'samples': 17681664, 'steps': 92091, 'loss/train': 1.1793663501739502} 08/31/2021 05:56:25 - INFO - __main__ - Step 92093: {'lr': 0.00016625487834197132, 'samples': 17681856, 'steps': 92092, 'loss/train': 1.9567506313323975} 08/31/2021 05:56:26 - INFO - __main__ - Step 92094: {'lr': 0.00016624987821329995, 'samples': 17682048, 'steps': 92093, 'loss/train': 1.5465494394302368} 08/31/2021 05:56:27 - INFO - __main__ - Step 92095: {'lr': 0.0001662448781223651, 'samples': 17682240, 'steps': 92094, 'loss/train': 1.0178508758544922} 08/31/2021 05:56:27 - INFO - __main__ - Step 92096: {'lr': 0.00016623987806916902, 'samples': 17682432, 'steps': 92095, 'loss/train': 0.7332293391227722} 08/31/2021 05:56:27 - INFO - __main__ - Step 92097: {'lr': 0.00016623487805371396, 'samples': 17682624, 'steps': 92096, 'loss/train': 1.2726116180419922} 08/31/2021 05:56:28 - INFO - __main__ - Step 92098: {'lr': 0.00016622987807600218, 'samples': 17682816, 'steps': 92097, 'loss/train': 1.7392356395721436} 08/31/2021 05:56:30 - INFO - __main__ - Step 92099: {'lr': 0.00016622487813603592, 'samples': 17683008, 'steps': 92098, 'loss/train': 0.35133177042007446} 08/31/2021 05:56:30 - INFO - __main__ - Step 92100: {'lr': 0.00016621987823381743, 'samples': 17683200, 'steps': 92099, 'loss/train': 0.9808086156845093} 08/31/2021 05:56:31 - INFO - __main__ - Step 92101: {'lr': 0.00016621487836934897, 'samples': 17683392, 'steps': 92100, 'loss/train': 1.4685778617858887} 08/31/2021 05:56:31 - INFO - __main__ - Step 92102: {'lr': 0.00016620987854263288, 'samples': 17683584, 'steps': 92101, 'loss/train': 1.3952158689498901} 08/31/2021 05:56:31 - INFO - __main__ - Step 92103: {'lr': 0.00016620487875367124, 'samples': 17683776, 'steps': 92102, 'loss/train': 1.048322319984436} 08/31/2021 05:56:33 - INFO - __main__ - Step 92104: {'lr': 0.00016619987900246642, 'samples': 17683968, 'steps': 92103, 'loss/train': 1.9496569633483887} 08/31/2021 05:56:34 - INFO - __main__ - Step 92105: {'lr': 0.0001661948792890206, 'samples': 17684160, 'steps': 92104, 'loss/train': 1.3366533517837524} 08/31/2021 05:56:34 - INFO - __main__ - Step 92106: {'lr': 0.0001661898796133361, 'samples': 17684352, 'steps': 92105, 'loss/train': 0.5384691953659058} 08/31/2021 05:56:34 - INFO - __main__ - Step 92107: {'lr': 0.00016618487997541512, 'samples': 17684544, 'steps': 92106, 'loss/train': 0.11026830971240997} 08/31/2021 05:56:35 - INFO - __main__ - Step 92108: {'lr': 0.00016617988037525994, 'samples': 17684736, 'steps': 92107, 'loss/train': 1.4504188299179077} 08/31/2021 05:56:37 - INFO - __main__ - Step 92109: {'lr': 0.00016617488081287286, 'samples': 17684928, 'steps': 92108, 'loss/train': 0.9248689413070679} 08/31/2021 05:56:37 - INFO - __main__ - Step 92110: {'lr': 0.00016616988128825602, 'samples': 17685120, 'steps': 92109, 'loss/train': 0.848236083984375} 08/31/2021 05:56:38 - INFO - __main__ - Step 92111: {'lr': 0.00016616488180141176, 'samples': 17685312, 'steps': 92110, 'loss/train': 1.6206815242767334} 08/31/2021 05:56:38 - INFO - __main__ - Step 92112: {'lr': 0.00016615988235234235, 'samples': 17685504, 'steps': 92111, 'loss/train': 1.6279642581939697} 08/31/2021 05:56:38 - INFO - __main__ - Step 92113: {'lr': 0.00016615488294104998, 'samples': 17685696, 'steps': 92112, 'loss/train': 0.9801508784294128} 08/31/2021 05:56:39 - INFO - __main__ - Step 92114: {'lr': 0.0001661498835675369, 'samples': 17685888, 'steps': 92113, 'loss/train': 1.6328125} 08/31/2021 05:56:40 - INFO - __main__ - Step 92115: {'lr': 0.00016614488423180552, 'samples': 17686080, 'steps': 92114, 'loss/train': 1.706592321395874} 08/31/2021 05:56:40 - INFO - __main__ - Step 92116: {'lr': 0.00016613988493385784, 'samples': 17686272, 'steps': 92115, 'loss/train': 1.1826131343841553} 08/31/2021 05:56:41 - INFO - __main__ - Step 92117: {'lr': 0.0001661348856736962, 'samples': 17686464, 'steps': 92116, 'loss/train': 1.6584093570709229} 08/31/2021 05:56:41 - INFO - __main__ - Step 92118: {'lr': 0.00016612988645132296, 'samples': 17686656, 'steps': 92117, 'loss/train': 0.6595825552940369} 08/31/2021 05:56:41 - INFO - __main__ - Step 92119: {'lr': 0.00016612488726674027, 'samples': 17686848, 'steps': 92118, 'loss/train': 1.4076850414276123} 08/31/2021 05:56:43 - INFO - __main__ - Step 92120: {'lr': 0.0001661198881199504, 'samples': 17687040, 'steps': 92119, 'loss/train': 0.6293383240699768} 08/31/2021 05:56:43 - INFO - __main__ - Step 92121: {'lr': 0.00016611488901095562, 'samples': 17687232, 'steps': 92120, 'loss/train': 0.9715032577514648} 08/31/2021 05:56:44 - INFO - __main__ - Step 92122: {'lr': 0.00016610988993975818, 'samples': 17687424, 'steps': 92121, 'loss/train': 1.2875150442123413} 08/31/2021 05:56:44 - INFO - __main__ - Step 92123: {'lr': 0.00016610489090636033, 'samples': 17687616, 'steps': 92122, 'loss/train': 1.389857292175293} 08/31/2021 05:56:44 - INFO - __main__ - Step 92124: {'lr': 0.00016609989191076433, 'samples': 17687808, 'steps': 92123, 'loss/train': 0.818956732749939} 08/31/2021 05:56:45 - INFO - __main__ - Step 92125: {'lr': 0.00016609489295297243, 'samples': 17688000, 'steps': 92124, 'loss/train': 0.925512433052063} 08/31/2021 05:56:46 - INFO - __main__ - Step 92126: {'lr': 0.00016608989403298684, 'samples': 17688192, 'steps': 92125, 'loss/train': 1.023316502571106} 08/31/2021 05:56:47 - INFO - __main__ - Step 92127: {'lr': 0.00016608489515080989, 'samples': 17688384, 'steps': 92126, 'loss/train': 0.8008375763893127} 08/31/2021 05:56:47 - INFO - __main__ - Step 92128: {'lr': 0.00016607989630644385, 'samples': 17688576, 'steps': 92127, 'loss/train': 0.7531054019927979} 08/31/2021 05:56:48 - INFO - __main__ - Step 92129: {'lr': 0.00016607489749989086, 'samples': 17688768, 'steps': 92128, 'loss/train': 1.0426883697509766} 08/31/2021 05:56:48 - INFO - __main__ - Step 92130: {'lr': 0.0001660698987311532, 'samples': 17688960, 'steps': 92129, 'loss/train': 1.5285247564315796} 08/31/2021 05:56:51 - INFO - __main__ - Step 92131: {'lr': 0.0001660649000002331, 'samples': 17689152, 'steps': 92130, 'loss/train': 0.9690958261489868} 08/31/2021 05:56:51 - INFO - __main__ - Step 92132: {'lr': 0.00016605990130713294, 'samples': 17689344, 'steps': 92131, 'loss/train': 1.9888389110565186} 08/31/2021 05:56:52 - INFO - __main__ - Step 92133: {'lr': 0.00016605490265185485, 'samples': 17689536, 'steps': 92132, 'loss/train': 1.334275484085083} 08/31/2021 05:56:52 - INFO - __main__ - Step 92134: {'lr': 0.0001660499040344011, 'samples': 17689728, 'steps': 92133, 'loss/train': 1.5774602890014648} 08/31/2021 05:56:52 - INFO - __main__ - Step 92135: {'lr': 0.00016604490545477405, 'samples': 17689920, 'steps': 92134, 'loss/train': 0.985214114189148} 08/31/2021 05:56:53 - INFO - __main__ - Step 92136: {'lr': 0.00016603990691297583, 'samples': 17690112, 'steps': 92135, 'loss/train': 1.7870845794677734} 08/31/2021 05:56:53 - INFO - __main__ - Step 92137: {'lr': 0.00016603490840900873, 'samples': 17690304, 'steps': 92136, 'loss/train': 1.7699397802352905} 08/31/2021 05:56:53 - INFO - __main__ - Step 92138: {'lr': 0.00016602990994287497, 'samples': 17690496, 'steps': 92137, 'loss/train': 1.759620189666748} 08/31/2021 05:56:55 - INFO - __main__ - Step 92139: {'lr': 0.00016602491151457695, 'samples': 17690688, 'steps': 92138, 'loss/train': 1.7373226881027222} 08/31/2021 05:56:55 - INFO - __main__ - Step 92140: {'lr': 0.00016601991312411674, 'samples': 17690880, 'steps': 92139, 'loss/train': 0.9529328942298889} 08/31/2021 05:56:56 - INFO - __main__ - Step 92141: {'lr': 0.00016601491477149664, 'samples': 17691072, 'steps': 92140, 'loss/train': 1.2430036067962646} 08/31/2021 05:56:56 - INFO - __main__ - Step 92142: {'lr': 0.00016600991645671897, 'samples': 17691264, 'steps': 92141, 'loss/train': 1.496221661567688} 08/31/2021 05:56:56 - INFO - __main__ - Step 92143: {'lr': 0.00016600491817978592, 'samples': 17691456, 'steps': 92142, 'loss/train': 0.7107855677604675} 08/31/2021 05:56:59 - INFO - __main__ - Step 92144: {'lr': 0.00016599991994069974, 'samples': 17691648, 'steps': 92143, 'loss/train': 1.1338024139404297} 08/31/2021 05:56:59 - INFO - __main__ - Step 92145: {'lr': 0.00016599492173946268, 'samples': 17691840, 'steps': 92144, 'loss/train': 1.4384926557540894} 08/31/2021 05:57:00 - INFO - __main__ - Step 92146: {'lr': 0.00016598992357607704, 'samples': 17692032, 'steps': 92145, 'loss/train': 0.5884960889816284} 08/31/2021 05:57:00 - INFO - __main__ - Step 92147: {'lr': 0.00016598492545054502, 'samples': 17692224, 'steps': 92146, 'loss/train': 1.2906819581985474} 08/31/2021 05:57:00 - INFO - __main__ - Step 92148: {'lr': 0.00016597992736286894, 'samples': 17692416, 'steps': 92147, 'loss/train': 0.43983399868011475} 08/31/2021 05:57:01 - INFO - __main__ - Step 92149: {'lr': 0.00016597492931305096, 'samples': 17692608, 'steps': 92148, 'loss/train': 0.3832111954689026} 08/31/2021 05:57:02 - INFO - __main__ - Step 92150: {'lr': 0.00016596993130109345, 'samples': 17692800, 'steps': 92149, 'loss/train': 0.34910833835601807} 08/31/2021 05:57:03 - INFO - __main__ - Step 92151: {'lr': 0.00016596493332699853, 'samples': 17692992, 'steps': 92150, 'loss/train': 1.0299768447875977} 08/31/2021 05:57:03 - INFO - __main__ - Step 92152: {'lr': 0.00016595993539076853, 'samples': 17693184, 'steps': 92151, 'loss/train': 0.9321531653404236} 08/31/2021 05:57:04 - INFO - __main__ - Step 92153: {'lr': 0.0001659549374924057, 'samples': 17693376, 'steps': 92152, 'loss/train': 1.307681918144226} 08/31/2021 05:57:04 - INFO - __main__ - Step 92154: {'lr': 0.00016594993963191224, 'samples': 17693568, 'steps': 92153, 'loss/train': 0.962431788444519} 08/31/2021 05:57:04 - INFO - __main__ - Step 92155: {'lr': 0.0001659449418092905, 'samples': 17693760, 'steps': 92154, 'loss/train': 0.04329104721546173} 08/31/2021 05:57:06 - INFO - __main__ - Step 92156: {'lr': 0.00016593994402454266, 'samples': 17693952, 'steps': 92155, 'loss/train': 0.027161559090018272} 08/31/2021 05:57:06 - INFO - __main__ - Step 92157: {'lr': 0.00016593494627767095, 'samples': 17694144, 'steps': 92156, 'loss/train': 1.4354584217071533} 08/31/2021 05:57:07 - INFO - __main__ - Step 92158: {'lr': 0.00016592994856867767, 'samples': 17694336, 'steps': 92157, 'loss/train': 1.1981070041656494} 08/31/2021 05:57:07 - INFO - __main__ - Step 92159: {'lr': 0.00016592495089756505, 'samples': 17694528, 'steps': 92158, 'loss/train': 1.5298317670822144} 08/31/2021 05:57:07 - INFO - __main__ - Step 92160: {'lr': 0.00016591995326433536, 'samples': 17694720, 'steps': 92159, 'loss/train': 1.1478739976882935} 08/31/2021 05:57:09 - INFO - __main__ - Step 92161: {'lr': 0.00016591495566899085, 'samples': 17694912, 'steps': 92160, 'loss/train': 1.758270025253296} 08/31/2021 05:57:10 - INFO - __main__ - Step 92162: {'lr': 0.00016590995811153374, 'samples': 17695104, 'steps': 92161, 'loss/train': 1.3046133518218994} 08/31/2021 05:57:10 - INFO - __main__ - Step 92163: {'lr': 0.0001659049605919663, 'samples': 17695296, 'steps': 92162, 'loss/train': 1.1346139907836914} 08/31/2021 05:57:10 - INFO - __main__ - Step 92164: {'lr': 0.00016589996311029082, 'samples': 17695488, 'steps': 92163, 'loss/train': 1.392462134361267} 08/31/2021 05:57:11 - INFO - __main__ - Step 92165: {'lr': 0.00016589496566650946, 'samples': 17695680, 'steps': 92164, 'loss/train': 2.0235981941223145} 08/31/2021 05:57:12 - INFO - __main__ - Step 92166: {'lr': 0.00016588996826062458, 'samples': 17695872, 'steps': 92165, 'loss/train': 1.0976805686950684} 08/31/2021 05:57:13 - INFO - __main__ - Step 92167: {'lr': 0.00016588497089263838, 'samples': 17696064, 'steps': 92166, 'loss/train': 0.9638625979423523} 08/31/2021 05:57:13 - INFO - __main__ - Step 92168: {'lr': 0.0001658799735625531, 'samples': 17696256, 'steps': 92167, 'loss/train': 1.1234102249145508} 08/31/2021 05:57:13 - INFO - __main__ - Step 92169: {'lr': 0.00016587497627037107, 'samples': 17696448, 'steps': 92168, 'loss/train': 0.7637662291526794} 08/31/2021 05:57:14 - INFO - __main__ - Step 92170: {'lr': 0.0001658699790160944, 'samples': 17696640, 'steps': 92169, 'loss/train': 1.3252108097076416} 08/31/2021 05:57:15 - INFO - __main__ - Step 92171: {'lr': 0.00016586498179972545, 'samples': 17696832, 'steps': 92170, 'loss/train': 1.0284273624420166} 08/31/2021 05:57:16 - INFO - __main__ - Step 92172: {'lr': 0.00016585998462126646, 'samples': 17697024, 'steps': 92171, 'loss/train': 0.895496666431427} 08/31/2021 05:57:16 - INFO - __main__ - Step 92173: {'lr': 0.00016585498748071965, 'samples': 17697216, 'steps': 92172, 'loss/train': 1.5491091012954712} 08/31/2021 05:57:16 - INFO - __main__ - Step 92174: {'lr': 0.00016584999037808727, 'samples': 17697408, 'steps': 92173, 'loss/train': 1.5842649936676025} 08/31/2021 05:57:17 - INFO - __main__ - Step 92175: {'lr': 0.00016584499331337156, 'samples': 17697600, 'steps': 92174, 'loss/train': 1.6402018070220947} 08/31/2021 05:57:17 - INFO - __main__ - Step 92176: {'lr': 0.00016583999628657481, 'samples': 17697792, 'steps': 92175, 'loss/train': 1.4137743711471558} 08/31/2021 05:57:19 - INFO - __main__ - Step 92177: {'lr': 0.0001658349992976993, 'samples': 17697984, 'steps': 92176, 'loss/train': 0.9593359231948853} 08/31/2021 05:57:19 - INFO - __main__ - Step 92178: {'lr': 0.00016583000234674718, 'samples': 17698176, 'steps': 92177, 'loss/train': 0.9309485554695129} 08/31/2021 05:57:20 - INFO - __main__ - Step 92179: {'lr': 0.0001658250054337208, 'samples': 17698368, 'steps': 92178, 'loss/train': 1.382492184638977} 08/31/2021 05:57:20 - INFO - __main__ - Step 92180: {'lr': 0.00016582000855862232, 'samples': 17698560, 'steps': 92179, 'loss/train': 5.444582462310791} 08/31/2021 05:57:20 - INFO - __main__ - Step 92181: {'lr': 0.00016581501172145414, 'samples': 17698752, 'steps': 92180, 'loss/train': 5.354642868041992} 08/31/2021 05:57:21 - INFO - __main__ - Step 92182: {'lr': 0.0001658100149222184, 'samples': 17698944, 'steps': 92181, 'loss/train': 1.1062498092651367} 08/31/2021 05:57:22 - INFO - __main__ - Step 92183: {'lr': 0.00016580501816091737, 'samples': 17699136, 'steps': 92182, 'loss/train': 1.5762560367584229} 08/31/2021 05:57:23 - INFO - __main__ - Step 92184: {'lr': 0.00016580002143755328, 'samples': 17699328, 'steps': 92183, 'loss/train': 0.9316197633743286} 08/31/2021 05:57:23 - INFO - __main__ - Step 92185: {'lr': 0.00016579502475212837, 'samples': 17699520, 'steps': 92184, 'loss/train': 1.4564803838729858} 08/31/2021 05:57:23 - INFO - __main__ - Step 92186: {'lr': 0.00016579002810464494, 'samples': 17699712, 'steps': 92185, 'loss/train': 1.1982266902923584} 08/31/2021 05:57:24 - INFO - __main__ - Step 92187: {'lr': 0.00016578503149510522, 'samples': 17699904, 'steps': 92186, 'loss/train': 0.7202942967414856} 08/31/2021 05:57:24 - INFO - __main__ - Step 92188: {'lr': 0.00016578003492351146, 'samples': 17700096, 'steps': 92187, 'loss/train': 0.786143958568573} 08/31/2021 05:57:25 - INFO - __main__ - Step 92189: {'lr': 0.00016577503838986592, 'samples': 17700288, 'steps': 92188, 'loss/train': 0.7017450332641602} 08/31/2021 05:57:26 - INFO - __main__ - Step 92190: {'lr': 0.00016577004189417084, 'samples': 17700480, 'steps': 92189, 'loss/train': 1.4495220184326172} 08/31/2021 05:57:26 - INFO - __main__ - Step 92191: {'lr': 0.0001657650454364285, 'samples': 17700672, 'steps': 92190, 'loss/train': 1.3648254871368408} 08/31/2021 05:57:27 - INFO - __main__ - Step 92192: {'lr': 0.0001657600490166411, 'samples': 17700864, 'steps': 92191, 'loss/train': 1.2441582679748535} 08/31/2021 05:57:27 - INFO - __main__ - Step 92193: {'lr': 0.00016575505263481094, 'samples': 17701056, 'steps': 92192, 'loss/train': 0.915675699710846} 08/31/2021 05:57:28 - INFO - __main__ - Step 92194: {'lr': 0.00016575005629094024, 'samples': 17701248, 'steps': 92193, 'loss/train': 0.8883053064346313} 08/31/2021 05:57:29 - INFO - __main__ - Step 92195: {'lr': 0.0001657450599850313, 'samples': 17701440, 'steps': 92194, 'loss/train': 1.3661819696426392} 08/31/2021 05:57:29 - INFO - __main__ - Step 92196: {'lr': 0.00016574006371708645, 'samples': 17701632, 'steps': 92195, 'loss/train': 1.4787670373916626} 08/31/2021 05:57:30 - INFO - __main__ - Step 92197: {'lr': 0.00016573506748710764, 'samples': 17701824, 'steps': 92196, 'loss/train': 1.6531020402908325} 08/31/2021 05:57:30 - INFO - __main__ - Step 92198: {'lr': 0.00016573007129509738, 'samples': 17702016, 'steps': 92197, 'loss/train': 1.3860149383544922} 08/31/2021 05:57:32 - INFO - __main__ - Step 92199: {'lr': 0.00016572507514105785, 'samples': 17702208, 'steps': 92198, 'loss/train': 0.7821670770645142} 08/31/2021 05:57:32 - INFO - __main__ - Step 92200: {'lr': 0.00016572007902499125, 'samples': 17702400, 'steps': 92199, 'loss/train': 1.1286582946777344} 08/31/2021 05:57:33 - INFO - __main__ - Step 92201: {'lr': 0.0001657150829468999, 'samples': 17702592, 'steps': 92200, 'loss/train': 0.5516769289970398} 08/31/2021 05:57:33 - INFO - __main__ - Step 92202: {'lr': 0.00016571008690678609, 'samples': 17702784, 'steps': 92201, 'loss/train': 1.5751858949661255} 08/31/2021 05:57:33 - INFO - __main__ - Step 92203: {'lr': 0.00016570509090465196, 'samples': 17702976, 'steps': 92202, 'loss/train': 1.0084441900253296} 08/31/2021 05:57:35 - INFO - __main__ - Step 92204: {'lr': 0.00016570009494049981, 'samples': 17703168, 'steps': 92203, 'loss/train': 1.753941535949707} 08/31/2021 05:57:35 - INFO - __main__ - Step 92205: {'lr': 0.0001656950990143319, 'samples': 17703360, 'steps': 92204, 'loss/train': 1.4605718851089478} 08/31/2021 05:57:35 - INFO - __main__ - Step 92206: {'lr': 0.00016569010312615052, 'samples': 17703552, 'steps': 92205, 'loss/train': 0.6622886061668396} 08/31/2021 05:57:36 - INFO - __main__ - Step 92207: {'lr': 0.0001656851072759578, 'samples': 17703744, 'steps': 92206, 'loss/train': 1.1382787227630615} 08/31/2021 05:57:36 - INFO - __main__ - Step 92208: {'lr': 0.00016568011146375617, 'samples': 17703936, 'steps': 92207, 'loss/train': 0.6132063269615173} 08/31/2021 05:57:38 - INFO - __main__ - Step 92209: {'lr': 0.0001656751156895478, 'samples': 17704128, 'steps': 92208, 'loss/train': 1.4012773036956787} 08/31/2021 05:57:38 - INFO - __main__ - Step 92210: {'lr': 0.00016567011995333487, 'samples': 17704320, 'steps': 92209, 'loss/train': 0.8945189118385315} 08/31/2021 05:57:38 - INFO - __main__ - Step 92211: {'lr': 0.00016566512425511966, 'samples': 17704512, 'steps': 92210, 'loss/train': 0.6345015168190002} 08/31/2021 05:57:39 - INFO - __main__ - Step 92212: {'lr': 0.00016566012859490443, 'samples': 17704704, 'steps': 92211, 'loss/train': 1.123835563659668} 08/31/2021 05:57:39 - INFO - __main__ - Step 92213: {'lr': 0.00016565513297269146, 'samples': 17704896, 'steps': 92212, 'loss/train': 1.3096636533737183} 08/31/2021 05:57:39 - INFO - __main__ - Step 92214: {'lr': 0.000165650137388483, 'samples': 17705088, 'steps': 92213, 'loss/train': 1.240914225578308} 08/31/2021 05:57:42 - INFO - __main__ - Step 92215: {'lr': 0.00016564514184228124, 'samples': 17705280, 'steps': 92214, 'loss/train': 0.8461881279945374} 08/31/2021 05:57:42 - INFO - __main__ - Step 92216: {'lr': 0.00016564014633408853, 'samples': 17705472, 'steps': 92215, 'loss/train': 1.8949525356292725} 08/31/2021 05:57:43 - INFO - __main__ - Step 92217: {'lr': 0.00016563515086390706, 'samples': 17705664, 'steps': 92216, 'loss/train': 1.500275731086731} 08/31/2021 05:57:43 - INFO - __main__ - Step 92218: {'lr': 0.00016563015543173907, 'samples': 17705856, 'steps': 92217, 'loss/train': 0.4158064126968384} 08/31/2021 05:57:43 - INFO - __main__ - Step 92219: {'lr': 0.0001656251600375868, 'samples': 17706048, 'steps': 92218, 'loss/train': 0.849388062953949} 08/31/2021 05:57:46 - INFO - __main__ - Step 92220: {'lr': 0.00016562016468145261, 'samples': 17706240, 'steps': 92219, 'loss/train': 1.356076955795288} 08/31/2021 05:57:46 - INFO - __main__ - Step 92221: {'lr': 0.00016561516936333863, 'samples': 17706432, 'steps': 92220, 'loss/train': 1.38840651512146} 08/31/2021 05:57:47 - INFO - __main__ - Step 92222: {'lr': 0.00016561017408324712, 'samples': 17706624, 'steps': 92221, 'loss/train': 1.2094699144363403} 08/31/2021 05:57:47 - INFO - __main__ - Step 92223: {'lr': 0.00016560517884118054, 'samples': 17706816, 'steps': 92222, 'loss/train': 1.727332592010498} 08/31/2021 05:57:47 - INFO - __main__ - Step 92224: {'lr': 0.0001656001836371408, 'samples': 17707008, 'steps': 92223, 'loss/train': 1.6911594867706299} 08/31/2021 05:57:48 - INFO - __main__ - Step 92225: {'lr': 0.00016559518847113035, 'samples': 17707200, 'steps': 92224, 'loss/train': 1.6744256019592285} 08/31/2021 05:57:48 - INFO - __main__ - Step 92226: {'lr': 0.00016559019334315138, 'samples': 17707392, 'steps': 92225, 'loss/train': 0.9984157681465149} 08/31/2021 05:57:50 - INFO - __main__ - Step 92227: {'lr': 0.00016558519825320616, 'samples': 17707584, 'steps': 92226, 'loss/train': 0.1992235779762268} 08/31/2021 05:57:50 - INFO - __main__ - Step 92228: {'lr': 0.00016558020320129696, 'samples': 17707776, 'steps': 92227, 'loss/train': 0.9738049507141113} 08/31/2021 05:57:51 - INFO - __main__ - Step 92229: {'lr': 0.00016557520818742607, 'samples': 17707968, 'steps': 92228, 'loss/train': 1.2393665313720703} 08/31/2021 05:57:51 - INFO - __main__ - Step 92230: {'lr': 0.0001655702132115956, 'samples': 17708160, 'steps': 92229, 'loss/train': 1.3744341135025024} 08/31/2021 05:57:51 - INFO - __main__ - Step 92231: {'lr': 0.00016556521827380794, 'samples': 17708352, 'steps': 92230, 'loss/train': 2.1450653076171875} 08/31/2021 05:57:53 - INFO - __main__ - Step 92232: {'lr': 0.0001655602233740653, 'samples': 17708544, 'steps': 92231, 'loss/train': 1.4524340629577637} 08/31/2021 05:57:53 - INFO - __main__ - Step 92233: {'lr': 0.00016555522851236987, 'samples': 17708736, 'steps': 92232, 'loss/train': 1.231136441230774} 08/31/2021 05:57:53 - INFO - __main__ - Step 92234: {'lr': 0.00016555023368872396, 'samples': 17708928, 'steps': 92233, 'loss/train': 1.2048145532608032} 08/31/2021 05:57:54 - INFO - __main__ - Step 92235: {'lr': 0.00016554523890312982, 'samples': 17709120, 'steps': 92234, 'loss/train': 1.1912274360656738} 08/31/2021 05:57:54 - INFO - __main__ - Step 92236: {'lr': 0.00016554024415558983, 'samples': 17709312, 'steps': 92235, 'loss/train': 0.21516834199428558} 08/31/2021 05:57:56 - INFO - __main__ - Step 92237: {'lr': 0.000165535249446106, 'samples': 17709504, 'steps': 92236, 'loss/train': 1.2709741592407227} 08/31/2021 05:57:56 - INFO - __main__ - Step 92238: {'lr': 0.00016553025477468065, 'samples': 17709696, 'steps': 92237, 'loss/train': 1.1931722164154053} 08/31/2021 05:57:56 - INFO - __main__ - Step 92239: {'lr': 0.0001655252601413161, 'samples': 17709888, 'steps': 92238, 'loss/train': 1.463158130645752} 08/31/2021 05:57:57 - INFO - __main__ - Step 92240: {'lr': 0.0001655202655460145, 'samples': 17710080, 'steps': 92239, 'loss/train': 1.5987809896469116} 08/31/2021 05:57:57 - INFO - __main__ - Step 92241: {'lr': 0.00016551527098877821, 'samples': 17710272, 'steps': 92240, 'loss/train': 1.4034849405288696} 08/31/2021 05:57:59 - INFO - __main__ - Step 92242: {'lr': 0.00016551027646960942, 'samples': 17710464, 'steps': 92241, 'loss/train': 0.027071652933955193} 08/31/2021 05:57:59 - INFO - __main__ - Step 92243: {'lr': 0.0001655052819885104, 'samples': 17710656, 'steps': 92242, 'loss/train': 1.1963212490081787} 08/31/2021 05:57:59 - INFO - __main__ - Step 92244: {'lr': 0.00016550028754548342, 'samples': 17710848, 'steps': 92243, 'loss/train': 1.1285961866378784} 08/31/2021 05:58:00 - INFO - __main__ - Step 92245: {'lr': 0.0001654952931405307, 'samples': 17711040, 'steps': 92244, 'loss/train': 0.8567956686019897} 08/31/2021 05:58:00 - INFO - __main__ - Step 92246: {'lr': 0.00016549029877365446, 'samples': 17711232, 'steps': 92245, 'loss/train': 0.8476430177688599} 08/31/2021 05:58:02 - INFO - __main__ - Step 92247: {'lr': 0.00016548530444485698, 'samples': 17711424, 'steps': 92246, 'loss/train': 1.8431013822555542} 08/31/2021 05:58:02 - INFO - __main__ - Step 92248: {'lr': 0.00016548031015414056, 'samples': 17711616, 'steps': 92247, 'loss/train': 1.0254480838775635} 08/31/2021 05:58:02 - INFO - __main__ - Step 92249: {'lr': 0.0001654753159015074, 'samples': 17711808, 'steps': 92248, 'loss/train': 1.4760068655014038} 08/31/2021 05:58:03 - INFO - __main__ - Step 92250: {'lr': 0.00016547032168695987, 'samples': 17712000, 'steps': 92249, 'loss/train': 1.1105375289916992} 08/31/2021 05:58:03 - INFO - __main__ - Step 92251: {'lr': 0.00016546532751049998, 'samples': 17712192, 'steps': 92250, 'loss/train': 1.2927217483520508} 08/31/2021 05:58:03 - INFO - __main__ - Step 92252: {'lr': 0.00016546033337213012, 'samples': 17712384, 'steps': 92251, 'loss/train': 2.97513747215271} 08/31/2021 05:58:05 - INFO - __main__ - Step 92253: {'lr': 0.00016545533927185254, 'samples': 17712576, 'steps': 92252, 'loss/train': 1.3614559173583984} 08/31/2021 05:58:05 - INFO - __main__ - Step 92254: {'lr': 0.00016545034520966945, 'samples': 17712768, 'steps': 92253, 'loss/train': 1.8241349458694458} 08/31/2021 05:58:06 - INFO - __main__ - Step 92255: {'lr': 0.00016544535118558318, 'samples': 17712960, 'steps': 92254, 'loss/train': 1.2253068685531616} 08/31/2021 05:58:06 - INFO - __main__ - Step 92256: {'lr': 0.00016544035719959587, 'samples': 17713152, 'steps': 92255, 'loss/train': 1.5148953199386597} 08/31/2021 05:58:06 - INFO - __main__ - Step 92257: {'lr': 0.00016543536325170987, 'samples': 17713344, 'steps': 92256, 'loss/train': 1.3952500820159912} 08/31/2021 05:58:08 - INFO - __main__ - Step 92258: {'lr': 0.0001654303693419274, 'samples': 17713536, 'steps': 92257, 'loss/train': 0.6675517559051514} 08/31/2021 05:58:08 - INFO - __main__ - Step 92259: {'lr': 0.00016542537547025067, 'samples': 17713728, 'steps': 92258, 'loss/train': 2.067218542098999} 08/31/2021 05:58:09 - INFO - __main__ - Step 92260: {'lr': 0.00016542038163668197, 'samples': 17713920, 'steps': 92259, 'loss/train': 0.962549090385437} 08/31/2021 05:58:09 - INFO - __main__ - Step 92261: {'lr': 0.00016541538784122357, 'samples': 17714112, 'steps': 92260, 'loss/train': 0.28651291131973267} 08/31/2021 05:58:09 - INFO - __main__ - Step 92262: {'lr': 0.00016541039408387765, 'samples': 17714304, 'steps': 92261, 'loss/train': 1.5880275964736938} 08/31/2021 05:58:11 - INFO - __main__ - Step 92263: {'lr': 0.0001654054003646466, 'samples': 17714496, 'steps': 92262, 'loss/train': 0.9814208745956421} 08/31/2021 05:58:12 - INFO - __main__ - Step 92264: {'lr': 0.0001654004066835325, 'samples': 17714688, 'steps': 92263, 'loss/train': 1.2525553703308105} 08/31/2021 05:58:12 - INFO - __main__ - Step 92265: {'lr': 0.00016539541304053766, 'samples': 17714880, 'steps': 92264, 'loss/train': 1.177505612373352} 08/31/2021 05:58:12 - INFO - __main__ - Step 92266: {'lr': 0.00016539041943566433, 'samples': 17715072, 'steps': 92265, 'loss/train': 1.4251481294631958} 08/31/2021 05:58:13 - INFO - __main__ - Step 92267: {'lr': 0.00016538542586891478, 'samples': 17715264, 'steps': 92266, 'loss/train': 0.5035631060600281} 08/31/2021 05:58:13 - INFO - __main__ - Step 92268: {'lr': 0.00016538043234029127, 'samples': 17715456, 'steps': 92267, 'loss/train': 0.9555255174636841} 08/31/2021 05:58:14 - INFO - __main__ - Step 92269: {'lr': 0.000165375438849796, 'samples': 17715648, 'steps': 92268, 'loss/train': 0.9360253810882568} 08/31/2021 05:58:15 - INFO - __main__ - Step 92270: {'lr': 0.00016537044539743126, 'samples': 17715840, 'steps': 92269, 'loss/train': 1.4642471075057983} 08/31/2021 05:58:15 - INFO - __main__ - Step 92271: {'lr': 0.0001653654519831993, 'samples': 17716032, 'steps': 92270, 'loss/train': 0.750959038734436} 08/31/2021 05:58:16 - INFO - __main__ - Step 92272: {'lr': 0.00016536045860710236, 'samples': 17716224, 'steps': 92271, 'loss/train': 0.9297258257865906} 08/31/2021 05:58:16 - INFO - __main__ - Step 92273: {'lr': 0.00016535546526914274, 'samples': 17716416, 'steps': 92272, 'loss/train': 1.0956591367721558} 08/31/2021 05:58:18 - INFO - __main__ - Step 92274: {'lr': 0.00016535047196932257, 'samples': 17716608, 'steps': 92273, 'loss/train': 1.3826899528503418} 08/31/2021 05:58:18 - INFO - __main__ - Step 92275: {'lr': 0.00016534547870764423, 'samples': 17716800, 'steps': 92274, 'loss/train': 0.8578910827636719} 08/31/2021 05:58:19 - INFO - __main__ - Step 92276: {'lr': 0.0001653404854841099, 'samples': 17716992, 'steps': 92275, 'loss/train': 0.4138699173927307} 08/31/2021 05:58:19 - INFO - __main__ - Step 92277: {'lr': 0.0001653354922987218, 'samples': 17717184, 'steps': 92276, 'loss/train': 1.0146257877349854} 08/31/2021 05:58:19 - INFO - __main__ - Step 92278: {'lr': 0.00016533049915148224, 'samples': 17717376, 'steps': 92277, 'loss/train': 1.1776162385940552} 08/31/2021 05:58:21 - INFO - __main__ - Step 92279: {'lr': 0.00016532550604239345, 'samples': 17717568, 'steps': 92278, 'loss/train': 0.847850501537323} 08/31/2021 05:58:21 - INFO - __main__ - Step 92280: {'lr': 0.00016532051297145768, 'samples': 17717760, 'steps': 92279, 'loss/train': 1.5584663152694702} 08/31/2021 05:58:22 - INFO - __main__ - Step 92281: {'lr': 0.00016531551993867715, 'samples': 17717952, 'steps': 92280, 'loss/train': 0.8545266389846802} 08/31/2021 05:58:22 - INFO - __main__ - Step 92282: {'lr': 0.00016531052694405417, 'samples': 17718144, 'steps': 92281, 'loss/train': 0.8794910311698914} 08/31/2021 05:58:23 - INFO - __main__ - Step 92283: {'lr': 0.00016530553398759097, 'samples': 17718336, 'steps': 92282, 'loss/train': 1.5298548936843872} 08/31/2021 05:58:24 - INFO - __main__ - Step 92284: {'lr': 0.00016530054106928983, 'samples': 17718528, 'steps': 92283, 'loss/train': 2.463904619216919} 08/31/2021 05:58:25 - INFO - __main__ - Step 92285: {'lr': 0.00016529554818915288, 'samples': 17718720, 'steps': 92284, 'loss/train': 1.671520709991455} 08/31/2021 05:58:25 - INFO - __main__ - Step 92286: {'lr': 0.00016529055534718248, 'samples': 17718912, 'steps': 92285, 'loss/train': 1.1893833875656128} 08/31/2021 05:58:25 - INFO - __main__ - Step 92287: {'lr': 0.00016528556254338084, 'samples': 17719104, 'steps': 92286, 'loss/train': 0.9640740156173706} 08/31/2021 05:58:26 - INFO - __main__ - Step 92288: {'lr': 0.00016528056977775023, 'samples': 17719296, 'steps': 92287, 'loss/train': 0.2845718562602997} 08/31/2021 05:58:26 - INFO - __main__ - Step 92289: {'lr': 0.00016527557705029288, 'samples': 17719488, 'steps': 92288, 'loss/train': 1.572783350944519} 08/31/2021 05:58:27 - INFO - __main__ - Step 92290: {'lr': 0.00016527058436101107, 'samples': 17719680, 'steps': 92289, 'loss/train': 1.432100534439087} 08/31/2021 05:58:28 - INFO - __main__ - Step 92291: {'lr': 0.000165265591709907, 'samples': 17719872, 'steps': 92290, 'loss/train': 0.8887072801589966} 08/31/2021 05:58:28 - INFO - __main__ - Step 92292: {'lr': 0.00016526059909698296, 'samples': 17720064, 'steps': 92291, 'loss/train': 1.0440975427627563} 08/31/2021 05:58:29 - INFO - __main__ - Step 92293: {'lr': 0.0001652556065222412, 'samples': 17720256, 'steps': 92292, 'loss/train': 0.901477038860321} 08/31/2021 05:58:30 - INFO - __main__ - Step 92294: {'lr': 0.00016525061398568391, 'samples': 17720448, 'steps': 92293, 'loss/train': 1.4885436296463013} 08/31/2021 05:58:31 - INFO - __main__ - Step 92295: {'lr': 0.00016524562148731347, 'samples': 17720640, 'steps': 92294, 'loss/train': 1.042694330215454} 08/31/2021 05:58:31 - INFO - __main__ - Step 92296: {'lr': 0.00016524062902713196, 'samples': 17720832, 'steps': 92295, 'loss/train': 0.960229754447937} 08/31/2021 05:58:31 - INFO - __main__ - Step 92297: {'lr': 0.00016523563660514174, 'samples': 17721024, 'steps': 92296, 'loss/train': 1.2294707298278809} 08/31/2021 05:58:32 - INFO - __main__ - Step 92298: {'lr': 0.00016523064422134504, 'samples': 17721216, 'steps': 92297, 'loss/train': 0.9604257345199585} 08/31/2021 05:58:32 - INFO - __main__ - Step 92299: {'lr': 0.0001652256518757441, 'samples': 17721408, 'steps': 92298, 'loss/train': 0.9913737177848816} 08/31/2021 05:58:34 - INFO - __main__ - Step 92300: {'lr': 0.00016522065956834115, 'samples': 17721600, 'steps': 92299, 'loss/train': 0.5780948996543884} 08/31/2021 05:58:34 - INFO - __main__ - Step 92301: {'lr': 0.0001652156672991385, 'samples': 17721792, 'steps': 92300, 'loss/train': 0.3715669512748718} 08/31/2021 05:58:34 - INFO - __main__ - Step 92302: {'lr': 0.00016521067506813832, 'samples': 17721984, 'steps': 92301, 'loss/train': 0.8067490458488464} 08/31/2021 05:58:35 - INFO - __main__ - Step 92303: {'lr': 0.000165205682875343, 'samples': 17722176, 'steps': 92302, 'loss/train': 1.4448269605636597} 08/31/2021 05:58:35 - INFO - __main__ - Step 92304: {'lr': 0.0001652006907207546, 'samples': 17722368, 'steps': 92303, 'loss/train': 3.856781005859375} 08/31/2021 05:58:37 - INFO - __main__ - Step 92305: {'lr': 0.00016519569860437547, 'samples': 17722560, 'steps': 92304, 'loss/train': 1.1706751585006714} 08/31/2021 05:58:38 - INFO - __main__ - Step 92306: {'lr': 0.0001651907065262079, 'samples': 17722752, 'steps': 92305, 'loss/train': 1.5617121458053589} 08/31/2021 05:58:38 - INFO - __main__ - Step 92307: {'lr': 0.00016518571448625405, 'samples': 17722944, 'steps': 92306, 'loss/train': 1.0504872798919678} 08/31/2021 05:58:38 - INFO - __main__ - Step 92308: {'lr': 0.0001651807224845162, 'samples': 17723136, 'steps': 92307, 'loss/train': 1.461667776107788} 08/31/2021 05:58:39 - INFO - __main__ - Step 92309: {'lr': 0.0001651757305209966, 'samples': 17723328, 'steps': 92308, 'loss/train': 5.901083469390869} 08/31/2021 05:58:39 - INFO - __main__ - Step 92310: {'lr': 0.00016517073859569753, 'samples': 17723520, 'steps': 92309, 'loss/train': 5.81333065032959} 08/31/2021 05:58:39 - INFO - __main__ - Step 92311: {'lr': 0.0001651657467086212, 'samples': 17723712, 'steps': 92310, 'loss/train': 0.9442615509033203} 08/31/2021 05:58:41 - INFO - __main__ - Step 92312: {'lr': 0.0001651607548597699, 'samples': 17723904, 'steps': 92311, 'loss/train': 0.8830752372741699} 08/31/2021 05:58:41 - INFO - __main__ - Step 92313: {'lr': 0.00016515576304914581, 'samples': 17724096, 'steps': 92312, 'loss/train': 1.8585443496704102} 08/31/2021 05:58:42 - INFO - __main__ - Step 92314: {'lr': 0.00016515077127675124, 'samples': 17724288, 'steps': 92313, 'loss/train': 1.3506979942321777} 08/31/2021 05:58:42 - INFO - __main__ - Step 92315: {'lr': 0.00016514577954258842, 'samples': 17724480, 'steps': 92314, 'loss/train': 2.0532047748565674} 08/31/2021 05:58:42 - INFO - __main__ - Step 92316: {'lr': 0.0001651407878466596, 'samples': 17724672, 'steps': 92315, 'loss/train': 1.9705195426940918} 08/31/2021 05:58:44 - INFO - __main__ - Step 92317: {'lr': 0.00016513579618896717, 'samples': 17724864, 'steps': 92316, 'loss/train': 1.2683335542678833} 08/31/2021 05:58:45 - INFO - __main__ - Step 92318: {'lr': 0.00016513080456951313, 'samples': 17725056, 'steps': 92317, 'loss/train': 1.7888354063034058} 08/31/2021 05:58:45 - INFO - __main__ - Step 92319: {'lr': 0.00016512581298829982, 'samples': 17725248, 'steps': 92318, 'loss/train': 0.1844903975725174} 08/31/2021 05:58:45 - INFO - __main__ - Step 92320: {'lr': 0.0001651208214453295, 'samples': 17725440, 'steps': 92319, 'loss/train': 1.6222617626190186} 08/31/2021 05:58:46 - INFO - __main__ - Step 92321: {'lr': 0.00016511582994060443, 'samples': 17725632, 'steps': 92320, 'loss/train': 0.6512491106987} 08/31/2021 05:58:46 - INFO - __main__ - Step 92322: {'lr': 0.00016511083847412688, 'samples': 17725824, 'steps': 92321, 'loss/train': 0.020344998687505722} 08/31/2021 05:58:47 - INFO - __main__ - Step 92323: {'lr': 0.00016510584704589908, 'samples': 17726016, 'steps': 92322, 'loss/train': 0.0201275572180748} 08/31/2021 05:58:48 - INFO - __main__ - Step 92324: {'lr': 0.00016510085565592326, 'samples': 17726208, 'steps': 92323, 'loss/train': 1.113118052482605} 08/31/2021 05:58:48 - INFO - __main__ - Step 92325: {'lr': 0.00016509586430420164, 'samples': 17726400, 'steps': 92324, 'loss/train': 0.17354202270507812} 08/31/2021 05:58:49 - INFO - __main__ - Step 92326: {'lr': 0.0001650908729907366, 'samples': 17726592, 'steps': 92325, 'loss/train': 1.2561525106430054} 08/31/2021 05:58:49 - INFO - __main__ - Step 92327: {'lr': 0.00016508588171553024, 'samples': 17726784, 'steps': 92326, 'loss/train': 1.1856516599655151} 08/31/2021 05:58:51 - INFO - __main__ - Step 92328: {'lr': 0.00016508089047858487, 'samples': 17726976, 'steps': 92327, 'loss/train': 0.06998352706432343} 08/31/2021 05:58:51 - INFO - __main__ - Step 92329: {'lr': 0.0001650758992799028, 'samples': 17727168, 'steps': 92328, 'loss/train': 1.517018437385559} 08/31/2021 05:58:52 - INFO - __main__ - Step 92330: {'lr': 0.00016507090811948628, 'samples': 17727360, 'steps': 92329, 'loss/train': 1.2821274995803833} 08/31/2021 05:58:52 - INFO - __main__ - Step 92331: {'lr': 0.00016506591699733738, 'samples': 17727552, 'steps': 92330, 'loss/train': 1.5775063037872314} 08/31/2021 05:58:52 - INFO - __main__ - Step 92332: {'lr': 0.0001650609259134585, 'samples': 17727744, 'steps': 92331, 'loss/train': 0.5881690979003906} 08/31/2021 05:58:53 - INFO - __main__ - Step 92333: {'lr': 0.00016505593486785183, 'samples': 17727936, 'steps': 92332, 'loss/train': 0.6997869610786438} 08/31/2021 05:58:54 - INFO - __main__ - Step 92334: {'lr': 0.00016505094386051966, 'samples': 17728128, 'steps': 92333, 'loss/train': 1.4573830366134644} 08/31/2021 05:58:55 - INFO - __main__ - Step 92335: {'lr': 0.00016504595289146422, 'samples': 17728320, 'steps': 92334, 'loss/train': 2.126291036605835} 08/31/2021 05:58:55 - INFO - __main__ - Step 92336: {'lr': 0.00016504096196068776, 'samples': 17728512, 'steps': 92335, 'loss/train': 1.1129186153411865} 08/31/2021 05:58:55 - INFO - __main__ - Step 92337: {'lr': 0.00016503597106819255, 'samples': 17728704, 'steps': 92336, 'loss/train': 1.1482224464416504} 08/31/2021 05:58:56 - INFO - __main__ - Step 92338: {'lr': 0.0001650309802139808, 'samples': 17728896, 'steps': 92337, 'loss/train': 0.8738605380058289} 08/31/2021 05:58:57 - INFO - __main__ - Step 92339: {'lr': 0.0001650259893980548, 'samples': 17729088, 'steps': 92338, 'loss/train': 1.3476448059082031} 08/31/2021 05:58:58 - INFO - __main__ - Step 92340: {'lr': 0.00016502099862041676, 'samples': 17729280, 'steps': 92339, 'loss/train': 1.4353251457214355} 08/31/2021 05:58:58 - INFO - __main__ - Step 92341: {'lr': 0.00016501600788106893, 'samples': 17729472, 'steps': 92340, 'loss/train': 1.3606714010238647} 08/31/2021 05:58:59 - INFO - __main__ - Step 92342: {'lr': 0.0001650110171800136, 'samples': 17729664, 'steps': 92341, 'loss/train': 1.355794906616211} 08/31/2021 05:58:59 - INFO - __main__ - Step 92343: {'lr': 0.000165006026517253, 'samples': 17729856, 'steps': 92342, 'loss/train': 1.7432739734649658} 08/31/2021 05:59:00 - INFO - __main__ - Step 92344: {'lr': 0.00016500103589278946, 'samples': 17730048, 'steps': 92343, 'loss/train': 1.3094347715377808} 08/31/2021 05:59:01 - INFO - __main__ - Step 92345: {'lr': 0.00016499604530662503, 'samples': 17730240, 'steps': 92344, 'loss/train': 1.5606553554534912} 08/31/2021 05:59:01 - INFO - __main__ - Step 92346: {'lr': 0.00016499105475876208, 'samples': 17730432, 'steps': 92345, 'loss/train': 1.2938584089279175} 08/31/2021 05:59:02 - INFO - __main__ - Step 92347: {'lr': 0.00016498606424920288, 'samples': 17730624, 'steps': 92346, 'loss/train': 1.3376126289367676} 08/31/2021 05:59:02 - INFO - __main__ - Step 92348: {'lr': 0.0001649810737779496, 'samples': 17730816, 'steps': 92347, 'loss/train': 1.1712145805358887} 08/31/2021 05:59:02 - INFO - __main__ - Step 92349: {'lr': 0.0001649760833450046, 'samples': 17731008, 'steps': 92348, 'loss/train': 0.6901984214782715} 08/31/2021 05:59:04 - INFO - __main__ - Step 92350: {'lr': 0.00016497109295037, 'samples': 17731200, 'steps': 92349, 'loss/train': 0.403356671333313} 08/31/2021 05:59:04 - INFO - __main__ - Step 92351: {'lr': 0.0001649661025940481, 'samples': 17731392, 'steps': 92350, 'loss/train': 1.3117671012878418} 08/31/2021 05:59:05 - INFO - __main__ - Step 92352: {'lr': 0.0001649611122760412, 'samples': 17731584, 'steps': 92351, 'loss/train': 1.7093541622161865} 08/31/2021 05:59:05 - INFO - __main__ - Step 92353: {'lr': 0.0001649561219963515, 'samples': 17731776, 'steps': 92352, 'loss/train': 1.0462168455123901} 08/31/2021 05:59:05 - INFO - __main__ - Step 92354: {'lr': 0.0001649511317549813, 'samples': 17731968, 'steps': 92353, 'loss/train': 0.428946316242218} 08/31/2021 05:59:07 - INFO - __main__ - Step 92355: {'lr': 0.00016494614155193276, 'samples': 17732160, 'steps': 92354, 'loss/train': 1.2530510425567627} 08/31/2021 05:59:07 - INFO - __main__ - Step 92356: {'lr': 0.00016494115138720818, 'samples': 17732352, 'steps': 92355, 'loss/train': 1.4507719278335571} 08/31/2021 05:59:08 - INFO - __main__ - Step 92357: {'lr': 0.00016493616126080993, 'samples': 17732544, 'steps': 92356, 'loss/train': 1.573195219039917} 08/31/2021 05:59:08 - INFO - __main__ - Step 92358: {'lr': 0.00016493117117274004, 'samples': 17732736, 'steps': 92357, 'loss/train': 0.9750187993049622} 08/31/2021 05:59:08 - INFO - __main__ - Step 92359: {'lr': 0.00016492618112300082, 'samples': 17732928, 'steps': 92358, 'loss/train': 1.0154836177825928} 08/31/2021 05:59:10 - INFO - __main__ - Step 92360: {'lr': 0.00016492119111159454, 'samples': 17733120, 'steps': 92359, 'loss/train': 1.233148455619812} 08/31/2021 05:59:10 - INFO - __main__ - Step 92361: {'lr': 0.00016491620113852348, 'samples': 17733312, 'steps': 92360, 'loss/train': 1.4647287130355835} 08/31/2021 05:59:10 - INFO - __main__ - Step 92362: {'lr': 0.00016491121120378987, 'samples': 17733504, 'steps': 92361, 'loss/train': 0.40313586592674255} 08/31/2021 05:59:11 - INFO - __main__ - Step 92363: {'lr': 0.00016490622130739598, 'samples': 17733696, 'steps': 92362, 'loss/train': 1.534638524055481} 08/31/2021 05:59:11 - INFO - __main__ - Step 92364: {'lr': 0.000164901231449344, 'samples': 17733888, 'steps': 92363, 'loss/train': 1.061460256576538} 08/31/2021 05:59:13 - INFO - __main__ - Step 92365: {'lr': 0.00016489624162963618, 'samples': 17734080, 'steps': 92364, 'loss/train': 1.2037346363067627} 08/31/2021 05:59:13 - INFO - __main__ - Step 92366: {'lr': 0.00016489125184827486, 'samples': 17734272, 'steps': 92365, 'loss/train': 0.941632866859436} 08/31/2021 05:59:13 - INFO - __main__ - Step 92367: {'lr': 0.00016488626210526218, 'samples': 17734464, 'steps': 92366, 'loss/train': 1.0295019149780273} 08/31/2021 05:59:14 - INFO - __main__ - Step 92368: {'lr': 0.00016488127240060047, 'samples': 17734656, 'steps': 92367, 'loss/train': 0.7649924755096436} 08/31/2021 05:59:14 - INFO - __main__ - Step 92369: {'lr': 0.00016487628273429195, 'samples': 17734848, 'steps': 92368, 'loss/train': 0.6564489603042603} 08/31/2021 05:59:16 - INFO - __main__ - Step 92370: {'lr': 0.00016487129310633887, 'samples': 17735040, 'steps': 92369, 'loss/train': 0.9482630491256714} 08/31/2021 05:59:16 - INFO - __main__ - Step 92371: {'lr': 0.00016486630351674353, 'samples': 17735232, 'steps': 92370, 'loss/train': 1.2909506559371948} 08/31/2021 05:59:16 - INFO - __main__ - Step 92372: {'lr': 0.00016486131396550803, 'samples': 17735424, 'steps': 92371, 'loss/train': 0.986855685710907} 08/31/2021 05:59:17 - INFO - __main__ - Step 92373: {'lr': 0.00016485632445263472, 'samples': 17735616, 'steps': 92372, 'loss/train': 0.8776211142539978} 08/31/2021 05:59:17 - INFO - __main__ - Step 92374: {'lr': 0.00016485133497812584, 'samples': 17735808, 'steps': 92373, 'loss/train': 1.3234626054763794} 08/31/2021 05:59:18 - INFO - __main__ - Step 92375: {'lr': 0.00016484634554198363, 'samples': 17736000, 'steps': 92374, 'loss/train': 1.2725417613983154} 08/31/2021 05:59:19 - INFO - __main__ - Step 92376: {'lr': 0.00016484135614421036, 'samples': 17736192, 'steps': 92375, 'loss/train': 1.2633479833602905} 08/31/2021 05:59:19 - INFO - __main__ - Step 92377: {'lr': 0.00016483636678480825, 'samples': 17736384, 'steps': 92376, 'loss/train': 0.5616261959075928} 08/31/2021 05:59:20 - INFO - __main__ - Step 92378: {'lr': 0.00016483137746377952, 'samples': 17736576, 'steps': 92377, 'loss/train': 0.9655128717422485} 08/31/2021 05:59:20 - INFO - __main__ - Step 92379: {'lr': 0.0001648263881811265, 'samples': 17736768, 'steps': 92378, 'loss/train': 0.773581326007843} 08/31/2021 05:59:21 - INFO - __main__ - Step 92380: {'lr': 0.00016482139893685138, 'samples': 17736960, 'steps': 92379, 'loss/train': 0.8886029720306396} 08/31/2021 05:59:22 - INFO - __main__ - Step 92381: {'lr': 0.00016481640973095647, 'samples': 17737152, 'steps': 92380, 'loss/train': 1.0445736646652222} 08/31/2021 05:59:22 - INFO - __main__ - Step 92382: {'lr': 0.00016481142056344388, 'samples': 17737344, 'steps': 92381, 'loss/train': 0.0751526728272438} 08/31/2021 05:59:23 - INFO - __main__ - Step 92383: {'lr': 0.00016480643143431601, 'samples': 17737536, 'steps': 92382, 'loss/train': 1.065528392791748} 08/31/2021 05:59:23 - INFO - __main__ - Step 92384: {'lr': 0.00016480144234357514, 'samples': 17737728, 'steps': 92383, 'loss/train': 0.3879828453063965} 08/31/2021 05:59:25 - INFO - __main__ - Step 92385: {'lr': 0.00016479645329122334, 'samples': 17737920, 'steps': 92384, 'loss/train': 1.2281150817871094} 08/31/2021 05:59:26 - INFO - __main__ - Step 92386: {'lr': 0.00016479146427726294, 'samples': 17738112, 'steps': 92385, 'loss/train': 1.500357985496521} 08/31/2021 05:59:26 - INFO - __main__ - Step 92387: {'lr': 0.00016478647530169616, 'samples': 17738304, 'steps': 92386, 'loss/train': 1.490067481994629} 08/31/2021 05:59:26 - INFO - __main__ - Step 92388: {'lr': 0.00016478148636452528, 'samples': 17738496, 'steps': 92387, 'loss/train': 0.9462091326713562} 08/31/2021 05:59:27 - INFO - __main__ - Step 92389: {'lr': 0.00016477649746575256, 'samples': 17738688, 'steps': 92388, 'loss/train': 1.2353767156600952} 08/31/2021 05:59:28 - INFO - __main__ - Step 92390: {'lr': 0.00016477150860538025, 'samples': 17738880, 'steps': 92389, 'loss/train': 1.2392030954360962} 08/31/2021 05:59:29 - INFO - __main__ - Step 92391: {'lr': 0.00016476651978341057, 'samples': 17739072, 'steps': 92390, 'loss/train': 0.6747114658355713} 08/31/2021 05:59:29 - INFO - __main__ - Step 92392: {'lr': 0.00016476153099984582, 'samples': 17739264, 'steps': 92391, 'loss/train': 0.22092700004577637} 08/31/2021 05:59:29 - INFO - __main__ - Step 92393: {'lr': 0.00016475654225468815, 'samples': 17739456, 'steps': 92392, 'loss/train': 1.016485333442688} 08/31/2021 05:59:30 - INFO - __main__ - Step 92394: {'lr': 0.0001647515535479399, 'samples': 17739648, 'steps': 92393, 'loss/train': 1.268245816230774} 08/31/2021 05:59:31 - INFO - __main__ - Step 92395: {'lr': 0.00016474656487960326, 'samples': 17739840, 'steps': 92394, 'loss/train': 0.6037169098854065} 08/31/2021 05:59:32 - INFO - __main__ - Step 92396: {'lr': 0.0001647415762496805, 'samples': 17740032, 'steps': 92395, 'loss/train': 1.169874668121338} 08/31/2021 05:59:32 - INFO - __main__ - Step 92397: {'lr': 0.000164736587658174, 'samples': 17740224, 'steps': 92396, 'loss/train': 1.29795503616333} 08/31/2021 05:59:32 - INFO - __main__ - Step 92398: {'lr': 0.0001647315991050858, 'samples': 17740416, 'steps': 92397, 'loss/train': 1.3598724603652954} 08/31/2021 05:59:33 - INFO - __main__ - Step 92399: {'lr': 0.00016472661059041815, 'samples': 17740608, 'steps': 92398, 'loss/train': 1.8603624105453491} 08/31/2021 05:59:33 - INFO - __main__ - Step 92400: {'lr': 0.0001647216221141734, 'samples': 17740800, 'steps': 92399, 'loss/train': 1.784467339515686} 08/31/2021 05:59:35 - INFO - __main__ - Step 92401: {'lr': 0.00016471663367635382, 'samples': 17740992, 'steps': 92400, 'loss/train': 1.6525418758392334} 08/31/2021 05:59:35 - INFO - __main__ - Step 92402: {'lr': 0.00016471164527696156, 'samples': 17741184, 'steps': 92401, 'loss/train': 0.0437735877931118} 08/31/2021 05:59:35 - INFO - __main__ - Step 92403: {'lr': 0.00016470665691599892, 'samples': 17741376, 'steps': 92402, 'loss/train': 1.883217692375183} 08/31/2021 05:59:36 - INFO - __main__ - Step 92404: {'lr': 0.00016470166859346814, 'samples': 17741568, 'steps': 92403, 'loss/train': 1.319069504737854} 08/31/2021 05:59:36 - INFO - __main__ - Step 92405: {'lr': 0.0001646966803093715, 'samples': 17741760, 'steps': 92404, 'loss/train': 4.162759304046631} 08/31/2021 05:59:38 - INFO - __main__ - Step 92406: {'lr': 0.0001646916920637112, 'samples': 17741952, 'steps': 92405, 'loss/train': 1.358152151107788} 08/31/2021 05:59:38 - INFO - __main__ - Step 92407: {'lr': 0.00016468670385648952, 'samples': 17742144, 'steps': 92406, 'loss/train': 0.03353139013051987} 08/31/2021 05:59:39 - INFO - __main__ - Step 92408: {'lr': 0.00016468171568770874, 'samples': 17742336, 'steps': 92407, 'loss/train': 1.0778181552886963} 08/31/2021 05:59:39 - INFO - __main__ - Step 92409: {'lr': 0.000164676727557371, 'samples': 17742528, 'steps': 92408, 'loss/train': 1.4682265520095825} 08/31/2021 05:59:39 - INFO - __main__ - Step 92410: {'lr': 0.00016467173946547865, 'samples': 17742720, 'steps': 92409, 'loss/train': 0.3833632171154022} 08/31/2021 05:59:41 - INFO - __main__ - Step 92411: {'lr': 0.0001646667514120339, 'samples': 17742912, 'steps': 92410, 'loss/train': 1.3027112483978271} 08/31/2021 05:59:41 - INFO - __main__ - Step 92412: {'lr': 0.00016466176339703894, 'samples': 17743104, 'steps': 92411, 'loss/train': 0.939421534538269} 08/31/2021 05:59:42 - INFO - __main__ - Step 92413: {'lr': 0.00016465677542049613, 'samples': 17743296, 'steps': 92412, 'loss/train': 0.6714807748794556} 08/31/2021 05:59:42 - INFO - __main__ - Step 92414: {'lr': 0.0001646517874824076, 'samples': 17743488, 'steps': 92413, 'loss/train': 1.5002520084381104} 08/31/2021 05:59:42 - INFO - __main__ - Step 92415: {'lr': 0.00016464679958277568, 'samples': 17743680, 'steps': 92414, 'loss/train': 0.9470371007919312} 08/31/2021 05:59:44 - INFO - __main__ - Step 92416: {'lr': 0.0001646418117216026, 'samples': 17743872, 'steps': 92415, 'loss/train': 0.3037092089653015} 08/31/2021 05:59:44 - INFO - __main__ - Step 92417: {'lr': 0.00016463682389889059, 'samples': 17744064, 'steps': 92416, 'loss/train': 1.5701346397399902} 08/31/2021 05:59:45 - INFO - __main__ - Step 92418: {'lr': 0.00016463183611464195, 'samples': 17744256, 'steps': 92417, 'loss/train': 0.6332276463508606} 08/31/2021 05:59:45 - INFO - __main__ - Step 92419: {'lr': 0.00016462684836885888, 'samples': 17744448, 'steps': 92418, 'loss/train': 1.4215835332870483} 08/31/2021 05:59:45 - INFO - __main__ - Step 92420: {'lr': 0.0001646218606615436, 'samples': 17744640, 'steps': 92419, 'loss/train': 1.2869601249694824} 08/31/2021 05:59:46 - INFO - __main__ - Step 92421: {'lr': 0.00016461687299269842, 'samples': 17744832, 'steps': 92420, 'loss/train': 1.4141196012496948} 08/31/2021 05:59:47 - INFO - __main__ - Step 92422: {'lr': 0.00016461188536232555, 'samples': 17745024, 'steps': 92421, 'loss/train': 1.7589715719223022} 08/31/2021 05:59:48 - INFO - __main__ - Step 92423: {'lr': 0.00016460689777042723, 'samples': 17745216, 'steps': 92422, 'loss/train': 1.1098077297210693} 08/31/2021 05:59:48 - INFO - __main__ - Step 92424: {'lr': 0.00016460191021700578, 'samples': 17745408, 'steps': 92423, 'loss/train': 1.0035666227340698} 08/31/2021 05:59:48 - INFO - __main__ - Step 92425: {'lr': 0.00016459692270206334, 'samples': 17745600, 'steps': 92424, 'loss/train': 1.6675611734390259} 08/31/2021 05:59:49 - INFO - __main__ - Step 92426: {'lr': 0.00016459193522560224, 'samples': 17745792, 'steps': 92425, 'loss/train': 1.311637282371521} 08/31/2021 05:59:50 - INFO - __main__ - Step 92427: {'lr': 0.00016458694778762468, 'samples': 17745984, 'steps': 92426, 'loss/train': 0.3486171364784241} 08/31/2021 05:59:51 - INFO - __main__ - Step 92428: {'lr': 0.0001645819603881329, 'samples': 17746176, 'steps': 92427, 'loss/train': 0.6206984519958496} 08/31/2021 05:59:51 - INFO - __main__ - Step 92429: {'lr': 0.00016457697302712918, 'samples': 17746368, 'steps': 92428, 'loss/train': 1.5725921392440796} 08/31/2021 05:59:51 - INFO - __main__ - Step 92430: {'lr': 0.0001645719857046158, 'samples': 17746560, 'steps': 92429, 'loss/train': 2.1567132472991943} 08/31/2021 05:59:52 - INFO - __main__ - Step 92431: {'lr': 0.00016456699842059492, 'samples': 17746752, 'steps': 92430, 'loss/train': 0.7140920162200928} 08/31/2021 05:59:53 - INFO - __main__ - Step 92432: {'lr': 0.00016456201117506886, 'samples': 17746944, 'steps': 92431, 'loss/train': 1.515427827835083} 08/31/2021 05:59:54 - INFO - __main__ - Step 92433: {'lr': 0.0001645570239680398, 'samples': 17747136, 'steps': 92432, 'loss/train': 1.4884202480316162} 08/31/2021 05:59:54 - INFO - __main__ - Step 92434: {'lr': 0.00016455203679951005, 'samples': 17747328, 'steps': 92433, 'loss/train': 1.5588688850402832} 08/31/2021 05:59:54 - INFO - __main__ - Step 92435: {'lr': 0.00016454704966948185, 'samples': 17747520, 'steps': 92434, 'loss/train': 1.9126769304275513} 08/31/2021 05:59:55 - INFO - __main__ - Step 92436: {'lr': 0.0001645420625779574, 'samples': 17747712, 'steps': 92435, 'loss/train': 1.304559588432312} 08/31/2021 05:59:57 - INFO - __main__ - Step 92437: {'lr': 0.00016453707552493895, 'samples': 17747904, 'steps': 92436, 'loss/train': 0.8938472867012024} 08/31/2021 05:59:57 - INFO - __main__ - Step 92438: {'lr': 0.0001645320885104289, 'samples': 17748096, 'steps': 92437, 'loss/train': 1.5255402326583862} 08/31/2021 05:59:58 - INFO - __main__ - Step 92439: {'lr': 0.00016452710153442928, 'samples': 17748288, 'steps': 92438, 'loss/train': 0.8716250061988831} 08/31/2021 05:59:58 - INFO - __main__ - Step 92440: {'lr': 0.00016452211459694243, 'samples': 17748480, 'steps': 92439, 'loss/train': 1.7174046039581299} 08/31/2021 05:59:58 - INFO - __main__ - Step 92441: {'lr': 0.00016451712769797067, 'samples': 17748672, 'steps': 92440, 'loss/train': 1.0563875436782837} 08/31/2021 06:00:00 - INFO - __main__ - Step 92442: {'lr': 0.0001645121408375161, 'samples': 17748864, 'steps': 92441, 'loss/train': 1.5056287050247192} 08/31/2021 06:00:01 - INFO - __main__ - Step 92443: {'lr': 0.00016450715401558104, 'samples': 17749056, 'steps': 92442, 'loss/train': 1.3133878707885742} 08/31/2021 06:00:01 - INFO - __main__ - Step 92444: {'lr': 0.00016450216723216775, 'samples': 17749248, 'steps': 92443, 'loss/train': 0.018884439021348953} 08/31/2021 06:00:01 - INFO - __main__ - Step 92445: {'lr': 0.00016449718048727844, 'samples': 17749440, 'steps': 92444, 'loss/train': 0.016219619661569595} 08/31/2021 06:00:02 - INFO - __main__ - Step 92446: {'lr': 0.0001644921937809154, 'samples': 17749632, 'steps': 92445, 'loss/train': 1.0060558319091797} 08/31/2021 06:00:02 - INFO - __main__ - Step 92447: {'lr': 0.00016448720711308086, 'samples': 17749824, 'steps': 92446, 'loss/train': 1.3458038568496704} 08/31/2021 06:00:03 - INFO - __main__ - Step 92448: {'lr': 0.00016448222048377704, 'samples': 17750016, 'steps': 92447, 'loss/train': 0.12302890419960022} 08/31/2021 06:00:04 - INFO - __main__ - Step 92449: {'lr': 0.00016447723389300623, 'samples': 17750208, 'steps': 92448, 'loss/train': 1.3398746252059937} 08/31/2021 06:00:04 - INFO - __main__ - Step 92450: {'lr': 0.00016447224734077065, 'samples': 17750400, 'steps': 92449, 'loss/train': 1.1941015720367432} 08/31/2021 06:00:05 - INFO - __main__ - Step 92451: {'lr': 0.0001644672608270727, 'samples': 17750592, 'steps': 92450, 'loss/train': 1.1543759107589722} 08/31/2021 06:00:05 - INFO - __main__ - Step 92452: {'lr': 0.00016446227435191433, 'samples': 17750784, 'steps': 92451, 'loss/train': 0.9702516794204712} 08/31/2021 06:00:05 - INFO - __main__ - Step 92453: {'lr': 0.00016445728791529795, 'samples': 17750976, 'steps': 92452, 'loss/train': 0.6540101170539856} 08/31/2021 06:00:07 - INFO - __main__ - Step 92454: {'lr': 0.00016445230151722578, 'samples': 17751168, 'steps': 92453, 'loss/train': 1.025498390197754} 08/31/2021 06:00:07 - INFO - __main__ - Step 92455: {'lr': 0.00016444731515770011, 'samples': 17751360, 'steps': 92454, 'loss/train': 0.8456242680549622} 08/31/2021 06:00:08 - INFO - __main__ - Step 92456: {'lr': 0.00016444232883672317, 'samples': 17751552, 'steps': 92455, 'loss/train': 0.046777088195085526} 08/31/2021 06:00:08 - INFO - __main__ - Step 92457: {'lr': 0.00016443734255429718, 'samples': 17751744, 'steps': 92456, 'loss/train': 1.4784510135650635} 08/31/2021 06:00:09 - INFO - __main__ - Step 92458: {'lr': 0.00016443235631042442, 'samples': 17751936, 'steps': 92457, 'loss/train': 0.9535707235336304} 08/31/2021 06:00:10 - INFO - __main__ - Step 92459: {'lr': 0.0001644273701051071, 'samples': 17752128, 'steps': 92458, 'loss/train': 0.769375741481781} 08/31/2021 06:00:11 - INFO - __main__ - Step 92460: {'lr': 0.00016442238393834746, 'samples': 17752320, 'steps': 92459, 'loss/train': 1.1863442659378052} 08/31/2021 06:00:11 - INFO - __main__ - Step 92461: {'lr': 0.00016441739781014784, 'samples': 17752512, 'steps': 92460, 'loss/train': 0.08712565898895264} 08/31/2021 06:00:11 - INFO - __main__ - Step 92462: {'lr': 0.00016441241172051037, 'samples': 17752704, 'steps': 92461, 'loss/train': 1.2354786396026611} 08/31/2021 06:00:12 - INFO - __main__ - Step 92463: {'lr': 0.00016440742566943737, 'samples': 17752896, 'steps': 92462, 'loss/train': 1.1571569442749023} 08/31/2021 06:00:13 - INFO - __main__ - Step 92464: {'lr': 0.00016440243965693105, 'samples': 17753088, 'steps': 92463, 'loss/train': 0.9800881743431091} 08/31/2021 06:00:14 - INFO - __main__ - Step 92465: {'lr': 0.00016439745368299378, 'samples': 17753280, 'steps': 92464, 'loss/train': 0.9070718884468079} 08/31/2021 06:00:14 - INFO - __main__ - Step 92466: {'lr': 0.0001643924677476276, 'samples': 17753472, 'steps': 92465, 'loss/train': 0.045014794915914536} 08/31/2021 06:00:14 - INFO - __main__ - Step 92467: {'lr': 0.00016438748185083484, 'samples': 17753664, 'steps': 92466, 'loss/train': 0.7342996001243591} 08/31/2021 06:00:15 - INFO - __main__ - Step 92468: {'lr': 0.00016438249599261772, 'samples': 17753856, 'steps': 92467, 'loss/train': 0.9380789399147034} 08/31/2021 06:00:15 - INFO - __main__ - Step 92469: {'lr': 0.00016437751017297857, 'samples': 17754048, 'steps': 92468, 'loss/train': 1.289747953414917} 08/31/2021 06:00:16 - INFO - __main__ - Step 92470: {'lr': 0.00016437252439191962, 'samples': 17754240, 'steps': 92469, 'loss/train': 0.7196014523506165} 08/31/2021 06:00:17 - INFO - __main__ - Step 92471: {'lr': 0.00016436753864944304, 'samples': 17754432, 'steps': 92470, 'loss/train': 1.2045117616653442} 08/31/2021 06:00:17 - INFO - __main__ - Step 92472: {'lr': 0.00016436255294555117, 'samples': 17754624, 'steps': 92471, 'loss/train': 1.224756121635437} 08/31/2021 06:00:18 - INFO - __main__ - Step 92473: {'lr': 0.0001643575672802462, 'samples': 17754816, 'steps': 92472, 'loss/train': 1.528896689414978} 08/31/2021 06:00:18 - INFO - __main__ - Step 92474: {'lr': 0.00016435258165353034, 'samples': 17755008, 'steps': 92473, 'loss/train': 0.9379045963287354} 08/31/2021 06:00:19 - INFO - __main__ - Step 92475: {'lr': 0.00016434759606540595, 'samples': 17755200, 'steps': 92474, 'loss/train': 0.794718325138092} 08/31/2021 06:00:20 - INFO - __main__ - Step 92476: {'lr': 0.00016434261051587518, 'samples': 17755392, 'steps': 92475, 'loss/train': 0.7442927956581116} 08/31/2021 06:00:20 - INFO - __main__ - Step 92477: {'lr': 0.00016433762500494032, 'samples': 17755584, 'steps': 92476, 'loss/train': 1.337996006011963} 08/31/2021 06:00:21 - INFO - __main__ - Step 92478: {'lr': 0.00016433263953260368, 'samples': 17755776, 'steps': 92477, 'loss/train': 1.6740680932998657} 08/31/2021 06:00:21 - INFO - __main__ - Step 92479: {'lr': 0.00016432765409886736, 'samples': 17755968, 'steps': 92478, 'loss/train': 1.0049986839294434} 08/31/2021 06:00:22 - INFO - __main__ - Step 92480: {'lr': 0.00016432266870373367, 'samples': 17756160, 'steps': 92479, 'loss/train': 0.7209677696228027} 08/31/2021 06:00:23 - INFO - __main__ - Step 92481: {'lr': 0.00016431768334720484, 'samples': 17756352, 'steps': 92480, 'loss/train': 0.8616386651992798} 08/31/2021 06:00:23 - INFO - __main__ - Step 92482: {'lr': 0.00016431269802928317, 'samples': 17756544, 'steps': 92481, 'loss/train': 1.0936341285705566} 08/31/2021 06:00:23 - INFO - __main__ - Step 92483: {'lr': 0.00016430771274997087, 'samples': 17756736, 'steps': 92482, 'loss/train': 1.1819298267364502} 08/31/2021 06:00:24 - INFO - __main__ - Step 92484: {'lr': 0.00016430272750927018, 'samples': 17756928, 'steps': 92483, 'loss/train': 1.2543559074401855} 08/31/2021 06:00:26 - INFO - __main__ - Step 92485: {'lr': 0.00016429774230718338, 'samples': 17757120, 'steps': 92484, 'loss/train': 1.9218213558197021} 08/31/2021 06:00:26 - INFO - __main__ - Step 92486: {'lr': 0.00016429275714371268, 'samples': 17757312, 'steps': 92485, 'loss/train': 1.3937015533447266} 08/31/2021 06:00:27 - INFO - __main__ - Step 92487: {'lr': 0.0001642877720188603, 'samples': 17757504, 'steps': 92486, 'loss/train': 1.7487163543701172} 08/31/2021 06:00:27 - INFO - __main__ - Step 92488: {'lr': 0.00016428278693262857, 'samples': 17757696, 'steps': 92487, 'loss/train': 1.4196170568466187} 08/31/2021 06:00:27 - INFO - __main__ - Step 92489: {'lr': 0.0001642778018850197, 'samples': 17757888, 'steps': 92488, 'loss/train': 0.9963312149047852} 08/31/2021 06:00:29 - INFO - __main__ - Step 92490: {'lr': 0.0001642728168760359, 'samples': 17758080, 'steps': 92489, 'loss/train': 1.5858491659164429} 08/31/2021 06:00:29 - INFO - __main__ - Step 92491: {'lr': 0.0001642678319056795, 'samples': 17758272, 'steps': 92490, 'loss/train': 0.8366240859031677} 08/31/2021 06:00:30 - INFO - __main__ - Step 92492: {'lr': 0.00016426284697395276, 'samples': 17758464, 'steps': 92491, 'loss/train': 0.5779441595077515} 08/31/2021 06:00:30 - INFO - __main__ - Step 92493: {'lr': 0.00016425786208085775, 'samples': 17758656, 'steps': 92492, 'loss/train': 1.2281551361083984} 08/31/2021 06:00:30 - INFO - __main__ - Step 92494: {'lr': 0.00016425287722639681, 'samples': 17758848, 'steps': 92493, 'loss/train': 1.4408152103424072} 08/31/2021 06:00:32 - INFO - __main__ - Step 92495: {'lr': 0.00016424789241057224, 'samples': 17759040, 'steps': 92494, 'loss/train': 1.7272214889526367} 08/31/2021 06:00:32 - INFO - __main__ - Step 92496: {'lr': 0.00016424290763338622, 'samples': 17759232, 'steps': 92495, 'loss/train': 1.1915336847305298} 08/31/2021 06:00:33 - INFO - __main__ - Step 92497: {'lr': 0.00016423792289484103, 'samples': 17759424, 'steps': 92496, 'loss/train': 1.0740834474563599} 08/31/2021 06:00:33 - INFO - __main__ - Step 92498: {'lr': 0.0001642329381949389, 'samples': 17759616, 'steps': 92497, 'loss/train': 1.5406043529510498} 08/31/2021 06:00:33 - INFO - __main__ - Step 92499: {'lr': 0.00016422795353368208, 'samples': 17759808, 'steps': 92498, 'loss/train': 0.04464372992515564} 08/31/2021 06:00:34 - INFO - __main__ - Step 92500: {'lr': 0.00016422296891107285, 'samples': 17760000, 'steps': 92499, 'loss/train': 0.5063144564628601} 08/31/2021 06:00:35 - INFO - __main__ - Step 92501: {'lr': 0.00016421798432711345, 'samples': 17760192, 'steps': 92500, 'loss/train': 1.2658367156982422} 08/31/2021 06:00:36 - INFO - __main__ - Step 92502: {'lr': 0.00016421299978180604, 'samples': 17760384, 'steps': 92501, 'loss/train': 0.8112426400184631} 08/31/2021 06:00:36 - INFO - __main__ - Step 92503: {'lr': 0.00016420801527515294, 'samples': 17760576, 'steps': 92502, 'loss/train': 1.298343300819397} 08/31/2021 06:00:37 - INFO - __main__ - Step 92504: {'lr': 0.0001642030308071564, 'samples': 17760768, 'steps': 92503, 'loss/train': 0.8456876873970032} 08/31/2021 06:00:37 - INFO - __main__ - Step 92505: {'lr': 0.00016419804637781874, 'samples': 17760960, 'steps': 92504, 'loss/train': 1.8107813596725464} 08/31/2021 06:00:39 - INFO - __main__ - Step 92506: {'lr': 0.00016419306198714201, 'samples': 17761152, 'steps': 92505, 'loss/train': 1.5940505266189575} 08/31/2021 06:00:39 - INFO - __main__ - Step 92507: {'lr': 0.0001641880776351286, 'samples': 17761344, 'steps': 92506, 'loss/train': 1.0454490184783936} 08/31/2021 06:00:39 - INFO - __main__ - Step 92508: {'lr': 0.00016418309332178065, 'samples': 17761536, 'steps': 92507, 'loss/train': 0.882041871547699} 08/31/2021 06:00:40 - INFO - __main__ - Step 92509: {'lr': 0.00016417810904710057, 'samples': 17761728, 'steps': 92508, 'loss/train': 1.4038275480270386} 08/31/2021 06:00:40 - INFO - __main__ - Step 92510: {'lr': 0.00016417312481109043, 'samples': 17761920, 'steps': 92509, 'loss/train': 1.1483726501464844} 08/31/2021 06:00:41 - INFO - __main__ - Step 92511: {'lr': 0.00016416814061375257, 'samples': 17762112, 'steps': 92510, 'loss/train': 1.2644450664520264} 08/31/2021 06:00:42 - INFO - __main__ - Step 92512: {'lr': 0.00016416315645508925, 'samples': 17762304, 'steps': 92511, 'loss/train': 1.3880598545074463} 08/31/2021 06:00:42 - INFO - __main__ - Step 92513: {'lr': 0.00016415817233510267, 'samples': 17762496, 'steps': 92512, 'loss/train': 1.2211991548538208} 08/31/2021 06:00:43 - INFO - __main__ - Step 92514: {'lr': 0.0001641531882537951, 'samples': 17762688, 'steps': 92513, 'loss/train': 0.98692387342453} 08/31/2021 06:00:43 - INFO - __main__ - Step 92515: {'lr': 0.00016414820421116878, 'samples': 17762880, 'steps': 92514, 'loss/train': 0.9623355865478516} 08/31/2021 06:00:44 - INFO - __main__ - Step 92516: {'lr': 0.00016414322020722594, 'samples': 17763072, 'steps': 92515, 'loss/train': 0.8477640151977539} 08/31/2021 06:00:45 - INFO - __main__ - Step 92517: {'lr': 0.00016413823624196884, 'samples': 17763264, 'steps': 92516, 'loss/train': 1.0641449689865112} 08/31/2021 06:00:45 - INFO - __main__ - Step 92518: {'lr': 0.00016413325231539984, 'samples': 17763456, 'steps': 92517, 'loss/train': 1.0806485414505005} 08/31/2021 06:00:46 - INFO - __main__ - Step 92519: {'lr': 0.00016412826842752097, 'samples': 17763648, 'steps': 92518, 'loss/train': 0.7259964942932129} 08/31/2021 06:00:46 - INFO - __main__ - Step 92520: {'lr': 0.00016412328457833457, 'samples': 17763840, 'steps': 92519, 'loss/train': 1.0765392780303955} 08/31/2021 06:00:46 - INFO - __main__ - Step 92521: {'lr': 0.00016411830076784289, 'samples': 17764032, 'steps': 92520, 'loss/train': 1.4192225933074951} 08/31/2021 06:00:48 - INFO - __main__ - Step 92522: {'lr': 0.00016411331699604816, 'samples': 17764224, 'steps': 92521, 'loss/train': 1.1097882986068726} 08/31/2021 06:00:48 - INFO - __main__ - Step 92523: {'lr': 0.00016410833326295268, 'samples': 17764416, 'steps': 92522, 'loss/train': 1.4710853099822998} 08/31/2021 06:00:49 - INFO - __main__ - Step 92524: {'lr': 0.00016410334956855867, 'samples': 17764608, 'steps': 92523, 'loss/train': 1.4197558164596558} 08/31/2021 06:00:49 - INFO - __main__ - Step 92525: {'lr': 0.0001640983659128683, 'samples': 17764800, 'steps': 92524, 'loss/train': 0.8940437436103821} 08/31/2021 06:00:49 - INFO - __main__ - Step 92526: {'lr': 0.00016409338229588394, 'samples': 17764992, 'steps': 92525, 'loss/train': 0.7567919492721558} 08/31/2021 06:00:51 - INFO - __main__ - Step 92527: {'lr': 0.0001640883987176078, 'samples': 17765184, 'steps': 92526, 'loss/train': 0.9746317863464355} 08/31/2021 06:00:51 - INFO - __main__ - Step 92528: {'lr': 0.00016408341517804205, 'samples': 17765376, 'steps': 92527, 'loss/train': 1.2921441793441772} 08/31/2021 06:00:51 - INFO - __main__ - Step 92529: {'lr': 0.00016407843167718896, 'samples': 17765568, 'steps': 92528, 'loss/train': 0.8421849012374878} 08/31/2021 06:00:52 - INFO - __main__ - Step 92530: {'lr': 0.00016407344821505086, 'samples': 17765760, 'steps': 92529, 'loss/train': 0.8759863972663879} 08/31/2021 06:00:52 - INFO - __main__ - Step 92531: {'lr': 0.00016406846479162995, 'samples': 17765952, 'steps': 92530, 'loss/train': 1.3951033353805542} 08/31/2021 06:00:54 - INFO - __main__ - Step 92532: {'lr': 0.0001640634814069285, 'samples': 17766144, 'steps': 92531, 'loss/train': 0.741302490234375} 08/31/2021 06:00:55 - INFO - __main__ - Step 92533: {'lr': 0.00016405849806094862, 'samples': 17766336, 'steps': 92532, 'loss/train': 1.291884422302246} 08/31/2021 06:00:55 - INFO - __main__ - Step 92534: {'lr': 0.0001640535147536927, 'samples': 17766528, 'steps': 92533, 'loss/train': 0.6743781566619873} 08/31/2021 06:00:55 - INFO - __main__ - Step 92535: {'lr': 0.00016404853148516293, 'samples': 17766720, 'steps': 92534, 'loss/train': 1.913382649421692} 08/31/2021 06:00:56 - INFO - __main__ - Step 92536: {'lr': 0.00016404354825536155, 'samples': 17766912, 'steps': 92535, 'loss/train': 0.41744861006736755} 08/31/2021 06:00:58 - INFO - __main__ - Step 92537: {'lr': 0.00016403856506429085, 'samples': 17767104, 'steps': 92536, 'loss/train': 0.07329563051462173} 08/31/2021 06:00:58 - INFO - __main__ - Step 92538: {'lr': 0.00016403358191195304, 'samples': 17767296, 'steps': 92537, 'loss/train': 1.4185798168182373} 08/31/2021 06:00:59 - INFO - __main__ - Step 92539: {'lr': 0.00016402859879835035, 'samples': 17767488, 'steps': 92538, 'loss/train': 0.5814980268478394} 08/31/2021 06:00:59 - INFO - __main__ - Step 92540: {'lr': 0.00016402361572348507, 'samples': 17767680, 'steps': 92539, 'loss/train': 0.8482833504676819} 08/31/2021 06:00:59 - INFO - __main__ - Step 92541: {'lr': 0.00016401863268735939, 'samples': 17767872, 'steps': 92540, 'loss/train': 0.7942261099815369} 08/31/2021 06:01:01 - INFO - __main__ - Step 92542: {'lr': 0.00016401364968997566, 'samples': 17768064, 'steps': 92541, 'loss/train': 2.5668325424194336} 08/31/2021 06:01:01 - INFO - __main__ - Step 92543: {'lr': 0.00016400866673133599, 'samples': 17768256, 'steps': 92542, 'loss/train': 1.1356000900268555} 08/31/2021 06:01:02 - INFO - __main__ - Step 92544: {'lr': 0.0001640036838114427, 'samples': 17768448, 'steps': 92543, 'loss/train': 1.2797824144363403} 08/31/2021 06:01:02 - INFO - __main__ - Step 92545: {'lr': 0.00016399870093029807, 'samples': 17768640, 'steps': 92544, 'loss/train': 0.5458996891975403} 08/31/2021 06:01:02 - INFO - __main__ - Step 92546: {'lr': 0.00016399371808790424, 'samples': 17768832, 'steps': 92545, 'loss/train': 1.5170750617980957} 08/31/2021 06:01:03 - INFO - __main__ - Step 92547: {'lr': 0.00016398873528426352, 'samples': 17769024, 'steps': 92546, 'loss/train': 1.2587320804595947} 08/31/2021 06:01:04 - INFO - __main__ - Step 92548: {'lr': 0.00016398375251937817, 'samples': 17769216, 'steps': 92547, 'loss/train': 0.2864692807197571} 08/31/2021 06:01:05 - INFO - __main__ - Step 92549: {'lr': 0.0001639787697932504, 'samples': 17769408, 'steps': 92548, 'loss/train': 1.2825778722763062} 08/31/2021 06:01:05 - INFO - __main__ - Step 92550: {'lr': 0.00016397378710588246, 'samples': 17769600, 'steps': 92549, 'loss/train': 1.3809974193572998} 08/31/2021 06:01:05 - INFO - __main__ - Step 92551: {'lr': 0.0001639688044572766, 'samples': 17769792, 'steps': 92550, 'loss/train': 2.847018241882324} 08/31/2021 06:01:06 - INFO - __main__ - Step 92552: {'lr': 0.0001639638218474351, 'samples': 17769984, 'steps': 92551, 'loss/train': 1.6393769979476929} 08/31/2021 06:01:08 - INFO - __main__ - Step 92553: {'lr': 0.00016395883927636018, 'samples': 17770176, 'steps': 92552, 'loss/train': 0.9684471487998962} 08/31/2021 06:01:08 - INFO - __main__ - Step 92554: {'lr': 0.00016395385674405406, 'samples': 17770368, 'steps': 92553, 'loss/train': 0.04424570873379707} 08/31/2021 06:01:08 - INFO - __main__ - Step 92555: {'lr': 0.00016394887425051895, 'samples': 17770560, 'steps': 92554, 'loss/train': 0.03403055667877197} 08/31/2021 06:01:09 - INFO - __main__ - Step 92556: {'lr': 0.00016394389179575722, 'samples': 17770752, 'steps': 92555, 'loss/train': 1.5770028829574585} 08/31/2021 06:01:09 - INFO - __main__ - Step 92557: {'lr': 0.000163938909379771, 'samples': 17770944, 'steps': 92556, 'loss/train': 0.45082420110702515} 08/31/2021 06:01:09 - INFO - __main__ - Step 92558: {'lr': 0.0001639339270025626, 'samples': 17771136, 'steps': 92557, 'loss/train': 0.01691993698477745} 08/31/2021 06:01:11 - INFO - __main__ - Step 92559: {'lr': 0.00016392894466413433, 'samples': 17771328, 'steps': 92558, 'loss/train': 0.8250104188919067} 08/31/2021 06:01:11 - INFO - __main__ - Step 92560: {'lr': 0.00016392396236448827, 'samples': 17771520, 'steps': 92559, 'loss/train': 0.4868456721305847} 08/31/2021 06:01:12 - INFO - __main__ - Step 92561: {'lr': 0.00016391898010362671, 'samples': 17771712, 'steps': 92560, 'loss/train': 1.4892668724060059} 08/31/2021 06:01:12 - INFO - __main__ - Step 92562: {'lr': 0.00016391399788155195, 'samples': 17771904, 'steps': 92561, 'loss/train': 1.4981186389923096} 08/31/2021 06:01:13 - INFO - __main__ - Step 92563: {'lr': 0.0001639090156982662, 'samples': 17772096, 'steps': 92562, 'loss/train': 1.1077840328216553} 08/31/2021 06:01:14 - INFO - __main__ - Step 92564: {'lr': 0.0001639040335537718, 'samples': 17772288, 'steps': 92563, 'loss/train': 1.010576844215393} 08/31/2021 06:01:15 - INFO - __main__ - Step 92565: {'lr': 0.00016389905144807088, 'samples': 17772480, 'steps': 92564, 'loss/train': 0.019094193354249} 08/31/2021 06:01:15 - INFO - __main__ - Step 92566: {'lr': 0.0001638940693811657, 'samples': 17772672, 'steps': 92565, 'loss/train': 0.26149967312812805} 08/31/2021 06:01:16 - INFO - __main__ - Step 92567: {'lr': 0.0001638890873530585, 'samples': 17772864, 'steps': 92566, 'loss/train': 1.5026334524154663} 08/31/2021 06:01:16 - INFO - __main__ - Step 92568: {'lr': 0.00016388410536375154, 'samples': 17773056, 'steps': 92567, 'loss/train': 0.35258007049560547} 08/31/2021 06:01:16 - INFO - __main__ - Step 92569: {'lr': 0.00016387912341324712, 'samples': 17773248, 'steps': 92568, 'loss/train': 3.5402750968933105} 08/31/2021 06:01:18 - INFO - __main__ - Step 92570: {'lr': 0.0001638741415015474, 'samples': 17773440, 'steps': 92569, 'loss/train': 1.2124505043029785} 08/31/2021 06:01:18 - INFO - __main__ - Step 92571: {'lr': 0.00016386915962865467, 'samples': 17773632, 'steps': 92570, 'loss/train': 0.8435919880867004} 08/31/2021 06:01:19 - INFO - __main__ - Step 92572: {'lr': 0.00016386417779457125, 'samples': 17773824, 'steps': 92571, 'loss/train': 1.2777183055877686} 08/31/2021 06:01:19 - INFO - __main__ - Step 92573: {'lr': 0.0001638591959992992, 'samples': 17774016, 'steps': 92572, 'loss/train': 1.0960489511489868} 08/31/2021 06:01:19 - INFO - __main__ - Step 92574: {'lr': 0.00016385421424284092, 'samples': 17774208, 'steps': 92573, 'loss/train': 1.5664180517196655} 08/31/2021 06:01:20 - INFO - __main__ - Step 92575: {'lr': 0.00016384923252519862, 'samples': 17774400, 'steps': 92574, 'loss/train': 0.8435459733009338} 08/31/2021 06:01:21 - INFO - __main__ - Step 92576: {'lr': 0.00016384425084637447, 'samples': 17774592, 'steps': 92575, 'loss/train': 0.6424159407615662} 08/31/2021 06:01:22 - INFO - __main__ - Step 92577: {'lr': 0.00016383926920637078, 'samples': 17774784, 'steps': 92576, 'loss/train': 1.0962433815002441} 08/31/2021 06:01:22 - INFO - __main__ - Step 92578: {'lr': 0.00016383428760518982, 'samples': 17774976, 'steps': 92577, 'loss/train': 0.020985925570130348} 08/31/2021 06:01:23 - INFO - __main__ - Step 92579: {'lr': 0.00016382930604283375, 'samples': 17775168, 'steps': 92578, 'loss/train': 0.044762227684259415} 08/31/2021 06:01:23 - INFO - __main__ - Step 92580: {'lr': 0.00016382432451930487, 'samples': 17775360, 'steps': 92579, 'loss/train': 1.1339821815490723} 08/31/2021 06:01:23 - INFO - __main__ - Step 92581: {'lr': 0.00016381934303460544, 'samples': 17775552, 'steps': 92580, 'loss/train': 0.045004360377788544} 08/31/2021 06:01:25 - INFO - __main__ - Step 92582: {'lr': 0.00016381436158873769, 'samples': 17775744, 'steps': 92581, 'loss/train': 1.326798439025879} 08/31/2021 06:01:25 - INFO - __main__ - Step 92583: {'lr': 0.00016380938018170383, 'samples': 17775936, 'steps': 92582, 'loss/train': 1.4121001958847046} 08/31/2021 06:01:26 - INFO - __main__ - Step 92584: {'lr': 0.00016380439881350618, 'samples': 17776128, 'steps': 92583, 'loss/train': 1.5960949659347534} 08/31/2021 06:01:26 - INFO - __main__ - Step 92585: {'lr': 0.0001637994174841469, 'samples': 17776320, 'steps': 92584, 'loss/train': 1.4075119495391846} 08/31/2021 06:01:26 - INFO - __main__ - Step 92586: {'lr': 0.00016379443619362837, 'samples': 17776512, 'steps': 92585, 'loss/train': 0.9051564335823059} 08/31/2021 06:01:28 - INFO - __main__ - Step 92587: {'lr': 0.00016378945494195264, 'samples': 17776704, 'steps': 92586, 'loss/train': 0.977942168712616} 08/31/2021 06:01:29 - INFO - __main__ - Step 92588: {'lr': 0.00016378447372912205, 'samples': 17776896, 'steps': 92587, 'loss/train': 1.098565697669983} 08/31/2021 06:01:29 - INFO - __main__ - Step 92589: {'lr': 0.00016377949255513887, 'samples': 17777088, 'steps': 92588, 'loss/train': 0.8110116124153137} 08/31/2021 06:01:29 - INFO - __main__ - Step 92590: {'lr': 0.0001637745114200053, 'samples': 17777280, 'steps': 92589, 'loss/train': 1.1527199745178223} 08/31/2021 06:01:30 - INFO - __main__ - Step 92591: {'lr': 0.0001637695303237236, 'samples': 17777472, 'steps': 92590, 'loss/train': 1.126254916191101} 08/31/2021 06:01:30 - INFO - __main__ - Step 92592: {'lr': 0.00016376454926629602, 'samples': 17777664, 'steps': 92591, 'loss/train': 1.0604212284088135} 08/31/2021 06:01:32 - INFO - __main__ - Step 92593: {'lr': 0.0001637595682477248, 'samples': 17777856, 'steps': 92592, 'loss/train': 0.9336429238319397} 08/31/2021 06:01:32 - INFO - __main__ - Step 92594: {'lr': 0.00016375458726801225, 'samples': 17778048, 'steps': 92593, 'loss/train': 0.6420275568962097} 08/31/2021 06:01:32 - INFO - __main__ - Step 92595: {'lr': 0.00016374960632716047, 'samples': 17778240, 'steps': 92594, 'loss/train': 0.8990071415901184} 08/31/2021 06:01:33 - INFO - __main__ - Step 92596: {'lr': 0.0001637446254251718, 'samples': 17778432, 'steps': 92595, 'loss/train': 0.06383595615625381} 08/31/2021 06:01:33 - INFO - __main__ - Step 92597: {'lr': 0.00016373964456204852, 'samples': 17778624, 'steps': 92596, 'loss/train': 1.4940190315246582} 08/31/2021 06:01:35 - INFO - __main__ - Step 92598: {'lr': 0.00016373466373779277, 'samples': 17778816, 'steps': 92597, 'loss/train': 1.9342254400253296} 08/31/2021 06:01:36 - INFO - __main__ - Step 92599: {'lr': 0.00016372968295240697, 'samples': 17779008, 'steps': 92598, 'loss/train': 1.6095068454742432} 08/31/2021 06:01:36 - INFO - __main__ - Step 92600: {'lr': 0.00016372470220589317, 'samples': 17779200, 'steps': 92599, 'loss/train': 0.5891411304473877} 08/31/2021 06:01:36 - INFO - __main__ - Step 92601: {'lr': 0.00016371972149825366, 'samples': 17779392, 'steps': 92600, 'loss/train': 1.1236732006072998} 08/31/2021 06:01:37 - INFO - __main__ - Step 92602: {'lr': 0.00016371474082949071, 'samples': 17779584, 'steps': 92601, 'loss/train': 1.1708248853683472} 08/31/2021 06:01:38 - INFO - __main__ - Step 92603: {'lr': 0.0001637097601996066, 'samples': 17779776, 'steps': 92602, 'loss/train': 1.403633713722229} 08/31/2021 06:01:39 - INFO - __main__ - Step 92604: {'lr': 0.0001637047796086035, 'samples': 17779968, 'steps': 92603, 'loss/train': 1.140313744544983} 08/31/2021 06:01:39 - INFO - __main__ - Step 92605: {'lr': 0.0001636997990564837, 'samples': 17780160, 'steps': 92604, 'loss/train': 0.9615741968154907} 08/31/2021 06:01:39 - INFO - __main__ - Step 92606: {'lr': 0.00016369481854324947, 'samples': 17780352, 'steps': 92605, 'loss/train': 1.5968763828277588} 08/31/2021 06:01:40 - INFO - __main__ - Step 92607: {'lr': 0.00016368983806890297, 'samples': 17780544, 'steps': 92606, 'loss/train': 0.772363543510437} 08/31/2021 06:01:41 - INFO - __main__ - Step 92608: {'lr': 0.00016368485763344653, 'samples': 17780736, 'steps': 92607, 'loss/train': 1.1821988821029663} 08/31/2021 06:01:41 - INFO - __main__ - Step 92609: {'lr': 0.00016367987723688238, 'samples': 17780928, 'steps': 92608, 'loss/train': 1.4600194692611694} 08/31/2021 06:01:42 - INFO - __main__ - Step 92610: {'lr': 0.0001636748968792127, 'samples': 17781120, 'steps': 92609, 'loss/train': 1.1794923543930054} 08/31/2021 06:01:42 - INFO - __main__ - Step 92611: {'lr': 0.00016366991656043982, 'samples': 17781312, 'steps': 92610, 'loss/train': 1.6969865560531616} 08/31/2021 06:01:43 - INFO - __main__ - Step 92612: {'lr': 0.0001636649362805659, 'samples': 17781504, 'steps': 92611, 'loss/train': 0.10157696157693863} 08/31/2021 06:01:44 - INFO - __main__ - Step 92613: {'lr': 0.00016365995603959338, 'samples': 17781696, 'steps': 92612, 'loss/train': 1.466554880142212} 08/31/2021 06:01:45 - INFO - __main__ - Step 92614: {'lr': 0.00016365497583752423, 'samples': 17781888, 'steps': 92613, 'loss/train': 1.2962162494659424} 08/31/2021 06:01:45 - INFO - __main__ - Step 92615: {'lr': 0.00016364999567436078, 'samples': 17782080, 'steps': 92614, 'loss/train': 1.5822269916534424} 08/31/2021 06:01:45 - INFO - __main__ - Step 92616: {'lr': 0.00016364501555010536, 'samples': 17782272, 'steps': 92615, 'loss/train': 1.0990886688232422} 08/31/2021 06:01:46 - INFO - __main__ - Step 92617: {'lr': 0.00016364003546476014, 'samples': 17782464, 'steps': 92616, 'loss/train': 1.2612171173095703} 08/31/2021 06:01:47 - INFO - __main__ - Step 92618: {'lr': 0.0001636350554183274, 'samples': 17782656, 'steps': 92617, 'loss/train': 0.7282096147537231} 08/31/2021 06:01:48 - INFO - __main__ - Step 92619: {'lr': 0.00016363007541080938, 'samples': 17782848, 'steps': 92618, 'loss/train': 1.3861756324768066} 08/31/2021 06:01:48 - INFO - __main__ - Step 92620: {'lr': 0.00016362509544220826, 'samples': 17783040, 'steps': 92619, 'loss/train': 1.2551442384719849} 08/31/2021 06:01:48 - INFO - __main__ - Step 92621: {'lr': 0.0001636201155125264, 'samples': 17783232, 'steps': 92620, 'loss/train': 1.3531081676483154} 08/31/2021 06:01:49 - INFO - __main__ - Step 92622: {'lr': 0.00016361513562176595, 'samples': 17783424, 'steps': 92621, 'loss/train': 1.1685117483139038} 08/31/2021 06:01:51 - INFO - __main__ - Step 92623: {'lr': 0.00016361015576992922, 'samples': 17783616, 'steps': 92622, 'loss/train': 1.4962246417999268} 08/31/2021 06:01:51 - INFO - __main__ - Step 92624: {'lr': 0.00016360517595701837, 'samples': 17783808, 'steps': 92623, 'loss/train': 1.303908109664917} 08/31/2021 06:01:51 - INFO - __main__ - Step 92625: {'lr': 0.00016360019618303574, 'samples': 17784000, 'steps': 92624, 'loss/train': 1.095750093460083} 08/31/2021 06:01:52 - INFO - __main__ - Step 92626: {'lr': 0.0001635952164479836, 'samples': 17784192, 'steps': 92625, 'loss/train': 2.4109458923339844} 08/31/2021 06:01:52 - INFO - __main__ - Step 92627: {'lr': 0.00016359023675186401, 'samples': 17784384, 'steps': 92626, 'loss/train': 1.6274070739746094} 08/31/2021 06:01:52 - INFO - __main__ - Step 92628: {'lr': 0.00016358525709467937, 'samples': 17784576, 'steps': 92627, 'loss/train': 1.0193605422973633} 08/31/2021 06:01:54 - INFO - __main__ - Step 92629: {'lr': 0.00016358027747643186, 'samples': 17784768, 'steps': 92628, 'loss/train': 0.950944185256958} 08/31/2021 06:01:54 - INFO - __main__ - Step 92630: {'lr': 0.00016357529789712375, 'samples': 17784960, 'steps': 92629, 'loss/train': 0.9082892537117004} 08/31/2021 06:01:55 - INFO - __main__ - Step 92631: {'lr': 0.00016357031835675728, 'samples': 17785152, 'steps': 92630, 'loss/train': 0.8086317181587219} 08/31/2021 06:01:55 - INFO - __main__ - Step 92632: {'lr': 0.00016356533885533467, 'samples': 17785344, 'steps': 92631, 'loss/train': 1.023867130279541} 08/31/2021 06:01:55 - INFO - __main__ - Step 92633: {'lr': 0.00016356035939285818, 'samples': 17785536, 'steps': 92632, 'loss/train': 0.7404251098632812} 08/31/2021 06:01:57 - INFO - __main__ - Step 92634: {'lr': 0.00016355537996933008, 'samples': 17785728, 'steps': 92633, 'loss/train': 0.90505450963974} 08/31/2021 06:01:57 - INFO - __main__ - Step 92635: {'lr': 0.00016355040058475256, 'samples': 17785920, 'steps': 92634, 'loss/train': 1.468437671661377} 08/31/2021 06:01:58 - INFO - __main__ - Step 92636: {'lr': 0.00016354542123912796, 'samples': 17786112, 'steps': 92635, 'loss/train': 1.1135894060134888} 08/31/2021 06:01:58 - INFO - __main__ - Step 92637: {'lr': 0.0001635404419324584, 'samples': 17786304, 'steps': 92636, 'loss/train': 1.8644826412200928} 08/31/2021 06:01:58 - INFO - __main__ - Step 92638: {'lr': 0.00016353546266474622, 'samples': 17786496, 'steps': 92637, 'loss/train': 1.0013600587844849} 08/31/2021 06:02:00 - INFO - __main__ - Step 92639: {'lr': 0.00016353048343599368, 'samples': 17786688, 'steps': 92638, 'loss/train': 1.0977106094360352} 08/31/2021 06:02:00 - INFO - __main__ - Step 92640: {'lr': 0.0001635255042462029, 'samples': 17786880, 'steps': 92639, 'loss/train': 1.0896739959716797} 08/31/2021 06:02:01 - INFO - __main__ - Step 92641: {'lr': 0.0001635205250953762, 'samples': 17787072, 'steps': 92640, 'loss/train': 0.7636237740516663} 08/31/2021 06:02:01 - INFO - __main__ - Step 92642: {'lr': 0.0001635155459835158, 'samples': 17787264, 'steps': 92641, 'loss/train': 0.4287237823009491} 08/31/2021 06:02:01 - INFO - __main__ - Step 92643: {'lr': 0.00016351056691062398, 'samples': 17787456, 'steps': 92642, 'loss/train': 1.7409747838974} 08/31/2021 06:02:02 - INFO - __main__ - Step 92644: {'lr': 0.00016350558787670295, 'samples': 17787648, 'steps': 92643, 'loss/train': 1.1429331302642822} 08/31/2021 06:02:03 - INFO - __main__ - Step 92645: {'lr': 0.000163500608881755, 'samples': 17787840, 'steps': 92644, 'loss/train': 1.2256393432617188} 08/31/2021 06:02:04 - INFO - __main__ - Step 92646: {'lr': 0.0001634956299257823, 'samples': 17788032, 'steps': 92645, 'loss/train': 0.24620838463306427} 08/31/2021 06:02:04 - INFO - __main__ - Step 92647: {'lr': 0.00016349065100878713, 'samples': 17788224, 'steps': 92646, 'loss/train': 1.0829592943191528} 08/31/2021 06:02:04 - INFO - __main__ - Step 92648: {'lr': 0.00016348567213077175, 'samples': 17788416, 'steps': 92647, 'loss/train': 1.369242787361145} 08/31/2021 06:02:05 - INFO - __main__ - Step 92649: {'lr': 0.0001634806932917384, 'samples': 17788608, 'steps': 92648, 'loss/train': 1.4847078323364258} 08/31/2021 06:02:07 - INFO - __main__ - Step 92650: {'lr': 0.00016347571449168929, 'samples': 17788800, 'steps': 92649, 'loss/train': 0.35828256607055664} 08/31/2021 06:02:07 - INFO - __main__ - Step 92651: {'lr': 0.0001634707357306267, 'samples': 17788992, 'steps': 92650, 'loss/train': 0.7222928404808044} 08/31/2021 06:02:08 - INFO - __main__ - Step 92652: {'lr': 0.00016346575700855288, 'samples': 17789184, 'steps': 92651, 'loss/train': 1.4409255981445312} 08/31/2021 06:02:08 - INFO - __main__ - Step 92653: {'lr': 0.00016346077832547017, 'samples': 17789376, 'steps': 92652, 'loss/train': 1.5592716932296753} 08/31/2021 06:02:08 - INFO - __main__ - Step 92654: {'lr': 0.0001634557996813806, 'samples': 17789568, 'steps': 92653, 'loss/train': 1.251657247543335} 08/31/2021 06:02:09 - INFO - __main__ - Step 92655: {'lr': 0.00016345082107628646, 'samples': 17789760, 'steps': 92654, 'loss/train': 1.7250819206237793} 08/31/2021 06:02:10 - INFO - __main__ - Step 92656: {'lr': 0.00016344584251019005, 'samples': 17789952, 'steps': 92655, 'loss/train': 1.4177067279815674} 08/31/2021 06:02:11 - INFO - __main__ - Step 92657: {'lr': 0.0001634408639830936, 'samples': 17790144, 'steps': 92656, 'loss/train': 1.1587268114089966} 08/31/2021 06:02:11 - INFO - __main__ - Step 92658: {'lr': 0.0001634358854949994, 'samples': 17790336, 'steps': 92657, 'loss/train': 1.38227379322052} 08/31/2021 06:02:11 - INFO - __main__ - Step 92659: {'lr': 0.00016343090704590963, 'samples': 17790528, 'steps': 92658, 'loss/train': 1.314247965812683} 08/31/2021 06:02:12 - INFO - __main__ - Step 92660: {'lr': 0.00016342592863582655, 'samples': 17790720, 'steps': 92659, 'loss/train': 1.6360149383544922} 08/31/2021 06:02:13 - INFO - __main__ - Step 92661: {'lr': 0.00016342095026475244, 'samples': 17790912, 'steps': 92660, 'loss/train': 1.4627865552902222} 08/31/2021 06:02:14 - INFO - __main__ - Step 92662: {'lr': 0.00016341597193268953, 'samples': 17791104, 'steps': 92661, 'loss/train': 1.514195203781128} 08/31/2021 06:02:14 - INFO - __main__ - Step 92663: {'lr': 0.00016341099363964, 'samples': 17791296, 'steps': 92662, 'loss/train': 1.3217015266418457} 08/31/2021 06:02:14 - INFO - __main__ - Step 92664: {'lr': 0.00016340601538560617, 'samples': 17791488, 'steps': 92663, 'loss/train': 1.4137386083602905} 08/31/2021 06:02:15 - INFO - __main__ - Step 92665: {'lr': 0.00016340103717059023, 'samples': 17791680, 'steps': 92664, 'loss/train': 0.5310604572296143} 08/31/2021 06:02:16 - INFO - __main__ - Step 92666: {'lr': 0.00016339605899459456, 'samples': 17791872, 'steps': 92665, 'loss/train': 0.8031025528907776} 08/31/2021 06:02:17 - INFO - __main__ - Step 92667: {'lr': 0.0001633910808576212, 'samples': 17792064, 'steps': 92666, 'loss/train': 1.5972740650177002} 08/31/2021 06:02:17 - INFO - __main__ - Step 92668: {'lr': 0.00016338610275967247, 'samples': 17792256, 'steps': 92667, 'loss/train': 1.4809328317642212} 08/31/2021 06:02:17 - INFO - __main__ - Step 92669: {'lr': 0.0001633811247007506, 'samples': 17792448, 'steps': 92668, 'loss/train': 1.1890754699707031} 08/31/2021 06:02:18 - INFO - __main__ - Step 92670: {'lr': 0.0001633761466808579, 'samples': 17792640, 'steps': 92669, 'loss/train': 0.21081633865833282} 08/31/2021 06:02:19 - INFO - __main__ - Step 92671: {'lr': 0.00016337116869999654, 'samples': 17792832, 'steps': 92670, 'loss/train': 1.3564915657043457} 08/31/2021 06:02:20 - INFO - __main__ - Step 92672: {'lr': 0.00016336619075816883, 'samples': 17793024, 'steps': 92671, 'loss/train': 0.7803316712379456} 08/31/2021 06:02:20 - INFO - __main__ - Step 92673: {'lr': 0.00016336121285537696, 'samples': 17793216, 'steps': 92672, 'loss/train': 1.0070699453353882} 08/31/2021 06:02:21 - INFO - __main__ - Step 92674: {'lr': 0.00016335623499162316, 'samples': 17793408, 'steps': 92673, 'loss/train': 1.1203445196151733} 08/31/2021 06:02:21 - INFO - __main__ - Step 92675: {'lr': 0.00016335125716690973, 'samples': 17793600, 'steps': 92674, 'loss/train': 1.4679640531539917} 08/31/2021 06:02:22 - INFO - __main__ - Step 92676: {'lr': 0.0001633462793812389, 'samples': 17793792, 'steps': 92675, 'loss/train': 1.6832752227783203} 08/31/2021 06:02:23 - INFO - __main__ - Step 92677: {'lr': 0.00016334130163461294, 'samples': 17793984, 'steps': 92676, 'loss/train': 1.4568661451339722} 08/31/2021 06:02:23 - INFO - __main__ - Step 92678: {'lr': 0.00016333632392703402, 'samples': 17794176, 'steps': 92677, 'loss/train': 1.2508015632629395} 08/31/2021 06:02:24 - INFO - __main__ - Step 92679: {'lr': 0.00016333134625850438, 'samples': 17794368, 'steps': 92678, 'loss/train': 1.780562400817871} 08/31/2021 06:02:24 - INFO - __main__ - Step 92680: {'lr': 0.00016332636862902635, 'samples': 17794560, 'steps': 92679, 'loss/train': 1.322367787361145} 08/31/2021 06:02:24 - INFO - __main__ - Step 92681: {'lr': 0.0001633213910386021, 'samples': 17794752, 'steps': 92680, 'loss/train': 1.0181320905685425} 08/31/2021 06:02:26 - INFO - __main__ - Step 92682: {'lr': 0.00016331641348723387, 'samples': 17794944, 'steps': 92681, 'loss/train': 0.9682519435882568} 08/31/2021 06:02:27 - INFO - __main__ - Step 92683: {'lr': 0.00016331143597492394, 'samples': 17795136, 'steps': 92682, 'loss/train': 0.03528430685400963} 08/31/2021 06:02:27 - INFO - __main__ - Step 92684: {'lr': 0.00016330645850167453, 'samples': 17795328, 'steps': 92683, 'loss/train': 0.14888663589954376} 08/31/2021 06:02:27 - INFO - __main__ - Step 92685: {'lr': 0.00016330148106748787, 'samples': 17795520, 'steps': 92684, 'loss/train': 0.14349602162837982} 08/31/2021 06:02:28 - INFO - __main__ - Step 92686: {'lr': 0.00016329650367236627, 'samples': 17795712, 'steps': 92685, 'loss/train': 1.69286048412323} 08/31/2021 06:02:30 - INFO - __main__ - Step 92687: {'lr': 0.00016329152631631196, 'samples': 17795904, 'steps': 92686, 'loss/train': 0.817807674407959} 08/31/2021 06:02:31 - INFO - __main__ - Step 92688: {'lr': 0.0001632865489993271, 'samples': 17796096, 'steps': 92687, 'loss/train': 1.0584949254989624} 08/31/2021 06:02:31 - INFO - __main__ - Step 92689: {'lr': 0.000163281571721414, 'samples': 17796288, 'steps': 92688, 'loss/train': 1.3772526979446411} 08/31/2021 06:02:31 - INFO - __main__ - Step 92690: {'lr': 0.00016327659448257486, 'samples': 17796480, 'steps': 92689, 'loss/train': 1.3605819940567017} 08/31/2021 06:02:32 - INFO - __main__ - Step 92691: {'lr': 0.00016327161728281196, 'samples': 17796672, 'steps': 92690, 'loss/train': 0.9700971841812134} 08/31/2021 06:02:32 - INFO - __main__ - Step 92692: {'lr': 0.0001632666401221275, 'samples': 17796864, 'steps': 92691, 'loss/train': 0.01725166290998459} 08/31/2021 06:02:34 - INFO - __main__ - Step 92693: {'lr': 0.00016326166300052383, 'samples': 17797056, 'steps': 92692, 'loss/train': 0.05541640520095825} 08/31/2021 06:02:34 - INFO - __main__ - Step 92694: {'lr': 0.00016325668591800308, 'samples': 17797248, 'steps': 92693, 'loss/train': 1.380101203918457} 08/31/2021 06:02:35 - INFO - __main__ - Step 92695: {'lr': 0.00016325170887456752, 'samples': 17797440, 'steps': 92694, 'loss/train': 0.9328592419624329} 08/31/2021 06:02:35 - INFO - __main__ - Step 92696: {'lr': 0.00016324673187021938, 'samples': 17797632, 'steps': 92695, 'loss/train': 0.015261692926287651} 08/31/2021 06:02:36 - INFO - __main__ - Step 92697: {'lr': 0.00016324175490496095, 'samples': 17797824, 'steps': 92696, 'loss/train': 2.027141809463501} 08/31/2021 06:02:36 - INFO - __main__ - Step 92698: {'lr': 0.00016323677797879448, 'samples': 17798016, 'steps': 92697, 'loss/train': 1.9764679670333862} 08/31/2021 06:02:36 - INFO - __main__ - Step 92699: {'lr': 0.00016323180109172216, 'samples': 17798208, 'steps': 92698, 'loss/train': 1.4675747156143188} 08/31/2021 06:02:38 - INFO - __main__ - Step 92700: {'lr': 0.00016322682424374618, 'samples': 17798400, 'steps': 92699, 'loss/train': 0.6981837749481201} 08/31/2021 06:02:38 - INFO - __main__ - Step 92701: {'lr': 0.00016322184743486893, 'samples': 17798592, 'steps': 92700, 'loss/train': 0.9671646952629089} 08/31/2021 06:02:39 - INFO - __main__ - Step 92702: {'lr': 0.00016321687066509256, 'samples': 17798784, 'steps': 92701, 'loss/train': 1.2061536312103271} 08/31/2021 06:02:39 - INFO - __main__ - Step 92703: {'lr': 0.0001632118939344193, 'samples': 17798976, 'steps': 92702, 'loss/train': 1.5228251218795776} 08/31/2021 06:02:39 - INFO - __main__ - Step 92704: {'lr': 0.0001632069172428514, 'samples': 17799168, 'steps': 92703, 'loss/train': 0.6797686219215393} 08/31/2021 06:02:42 - INFO - __main__ - Step 92705: {'lr': 0.00016320194059039116, 'samples': 17799360, 'steps': 92704, 'loss/train': 0.789157509803772} 08/31/2021 06:02:42 - INFO - __main__ - Step 92706: {'lr': 0.00016319696397704082, 'samples': 17799552, 'steps': 92705, 'loss/train': 0.06363530457019806} 08/31/2021 06:02:43 - INFO - __main__ - Step 92707: {'lr': 0.00016319198740280262, 'samples': 17799744, 'steps': 92706, 'loss/train': 0.9376745223999023} 08/31/2021 06:02:43 - INFO - __main__ - Step 92708: {'lr': 0.00016318701086767869, 'samples': 17799936, 'steps': 92707, 'loss/train': 1.1036312580108643} 08/31/2021 06:02:44 - INFO - __main__ - Step 92709: {'lr': 0.0001631820343716714, 'samples': 17800128, 'steps': 92708, 'loss/train': 0.7911555767059326} 08/31/2021 06:02:44 - INFO - __main__ - Step 92710: {'lr': 0.00016317705791478294, 'samples': 17800320, 'steps': 92709, 'loss/train': 1.223718285560608} 08/31/2021 06:02:45 - INFO - __main__ - Step 92711: {'lr': 0.00016317208149701555, 'samples': 17800512, 'steps': 92710, 'loss/train': 0.1694421023130417} 08/31/2021 06:02:46 - INFO - __main__ - Step 92712: {'lr': 0.00016316710511837145, 'samples': 17800704, 'steps': 92711, 'loss/train': 0.9601850509643555} 08/31/2021 06:02:46 - INFO - __main__ - Step 92713: {'lr': 0.00016316212877885293, 'samples': 17800896, 'steps': 92712, 'loss/train': 0.8181211948394775} 08/31/2021 06:02:46 - INFO - __main__ - Step 92714: {'lr': 0.00016315715247846219, 'samples': 17801088, 'steps': 92713, 'loss/train': 1.4818590879440308} 08/31/2021 06:02:47 - INFO - __main__ - Step 92715: {'lr': 0.00016315217621720152, 'samples': 17801280, 'steps': 92714, 'loss/train': 0.19553814828395844} 08/31/2021 06:02:49 - INFO - __main__ - Step 92716: {'lr': 0.00016314719999507317, 'samples': 17801472, 'steps': 92715, 'loss/train': 0.7221108675003052} 08/31/2021 06:02:49 - INFO - __main__ - Step 92717: {'lr': 0.0001631422238120793, 'samples': 17801664, 'steps': 92716, 'loss/train': 0.6068568229675293} 08/31/2021 06:02:49 - INFO - __main__ - Step 92718: {'lr': 0.00016313724766822221, 'samples': 17801856, 'steps': 92717, 'loss/train': 1.0915793180465698} 08/31/2021 06:02:50 - INFO - __main__ - Step 92719: {'lr': 0.00016313227156350416, 'samples': 17802048, 'steps': 92718, 'loss/train': 1.399472951889038} 08/31/2021 06:02:50 - INFO - __main__ - Step 92720: {'lr': 0.00016312729549792745, 'samples': 17802240, 'steps': 92719, 'loss/train': 0.49864649772644043} 08/31/2021 06:02:51 - INFO - __main__ - Step 92721: {'lr': 0.00016312231947149413, 'samples': 17802432, 'steps': 92720, 'loss/train': 0.038980867713689804} 08/31/2021 06:02:52 - INFO - __main__ - Step 92722: {'lr': 0.0001631173434842066, 'samples': 17802624, 'steps': 92721, 'loss/train': 0.1416483074426651} 08/31/2021 06:02:52 - INFO - __main__ - Step 92723: {'lr': 0.00016311236753606702, 'samples': 17802816, 'steps': 92722, 'loss/train': 1.0216959714889526} 08/31/2021 06:02:53 - INFO - __main__ - Step 92724: {'lr': 0.00016310739162707767, 'samples': 17803008, 'steps': 92723, 'loss/train': 1.5872915983200073} 08/31/2021 06:02:53 - INFO - __main__ - Step 92725: {'lr': 0.00016310241575724077, 'samples': 17803200, 'steps': 92724, 'loss/train': 3.61780047416687} 08/31/2021 06:02:53 - INFO - __main__ - Step 92726: {'lr': 0.00016309743992655863, 'samples': 17803392, 'steps': 92725, 'loss/train': 1.199471116065979} 08/31/2021 06:02:55 - INFO - __main__ - Step 92727: {'lr': 0.0001630924641350334, 'samples': 17803584, 'steps': 92726, 'loss/train': 1.5879205465316772} 08/31/2021 06:02:55 - INFO - __main__ - Step 92728: {'lr': 0.00016308748838266736, 'samples': 17803776, 'steps': 92727, 'loss/train': 1.0719642639160156} 08/31/2021 06:02:56 - INFO - __main__ - Step 92729: {'lr': 0.00016308251266946279, 'samples': 17803968, 'steps': 92728, 'loss/train': 1.28947913646698} 08/31/2021 06:02:56 - INFO - __main__ - Step 92730: {'lr': 0.0001630775369954219, 'samples': 17804160, 'steps': 92729, 'loss/train': 1.45073401927948} 08/31/2021 06:02:56 - INFO - __main__ - Step 92731: {'lr': 0.0001630725613605469, 'samples': 17804352, 'steps': 92730, 'loss/train': 1.4036444425582886} 08/31/2021 06:02:58 - INFO - __main__ - Step 92732: {'lr': 0.00016306758576484004, 'samples': 17804544, 'steps': 92731, 'loss/train': 1.1716893911361694} 08/31/2021 06:02:58 - INFO - __main__ - Step 92733: {'lr': 0.00016306261020830365, 'samples': 17804736, 'steps': 92732, 'loss/train': 1.2044777870178223} 08/31/2021 06:02:59 - INFO - __main__ - Step 92734: {'lr': 0.00016305763469093998, 'samples': 17804928, 'steps': 92733, 'loss/train': 2.1341705322265625} 08/31/2021 06:02:59 - INFO - __main__ - Step 92735: {'lr': 0.00016305265921275107, 'samples': 17805120, 'steps': 92734, 'loss/train': 1.0749398469924927} 08/31/2021 06:02:59 - INFO - __main__ - Step 92736: {'lr': 0.00016304768377373933, 'samples': 17805312, 'steps': 92735, 'loss/train': 1.0369385480880737} 08/31/2021 06:03:01 - INFO - __main__ - Step 92737: {'lr': 0.00016304270837390694, 'samples': 17805504, 'steps': 92736, 'loss/train': 0.9331275224685669} 08/31/2021 06:03:01 - INFO - __main__ - Step 92738: {'lr': 0.00016303773301325618, 'samples': 17805696, 'steps': 92737, 'loss/train': 5.764297962188721} 08/31/2021 06:03:02 - INFO - __main__ - Step 92739: {'lr': 0.00016303275769178924, 'samples': 17805888, 'steps': 92738, 'loss/train': 0.6385617256164551} 08/31/2021 06:03:02 - INFO - __main__ - Step 92740: {'lr': 0.00016302778240950843, 'samples': 17806080, 'steps': 92739, 'loss/train': 1.1754252910614014} 08/31/2021 06:03:02 - INFO - __main__ - Step 92741: {'lr': 0.00016302280716641593, 'samples': 17806272, 'steps': 92740, 'loss/train': 0.8707464933395386} 08/31/2021 06:03:03 - INFO - __main__ - Step 92742: {'lr': 0.00016301783196251405, 'samples': 17806464, 'steps': 92741, 'loss/train': 1.1680375337600708} 08/31/2021 06:03:04 - INFO - __main__ - Step 92743: {'lr': 0.00016301285679780496, 'samples': 17806656, 'steps': 92742, 'loss/train': 1.533673644065857} 08/31/2021 06:03:05 - INFO - __main__ - Step 92744: {'lr': 0.00016300788167229098, 'samples': 17806848, 'steps': 92743, 'loss/train': 1.324849247932434} 08/31/2021 06:03:05 - INFO - __main__ - Step 92745: {'lr': 0.00016300290658597427, 'samples': 17807040, 'steps': 92744, 'loss/train': 0.7410359382629395} 08/31/2021 06:03:05 - INFO - __main__ - Step 92746: {'lr': 0.0001629979315388571, 'samples': 17807232, 'steps': 92745, 'loss/train': 1.3531980514526367} 08/31/2021 06:03:06 - INFO - __main__ - Step 92747: {'lr': 0.00016299295653094182, 'samples': 17807424, 'steps': 92746, 'loss/train': 0.8568736910820007} 08/31/2021 06:03:07 - INFO - __main__ - Step 92748: {'lr': 0.0001629879815622305, 'samples': 17807616, 'steps': 92747, 'loss/train': 1.3909521102905273} 08/31/2021 06:03:08 - INFO - __main__ - Step 92749: {'lr': 0.0001629830066327254, 'samples': 17807808, 'steps': 92748, 'loss/train': 1.736345887184143} 08/31/2021 06:03:08 - INFO - __main__ - Step 92750: {'lr': 0.00016297803174242887, 'samples': 17808000, 'steps': 92749, 'loss/train': 0.9071005582809448} 08/31/2021 06:03:08 - INFO - __main__ - Step 92751: {'lr': 0.0001629730568913431, 'samples': 17808192, 'steps': 92750, 'loss/train': 0.9409435987472534} 08/31/2021 06:03:09 - INFO - __main__ - Step 92752: {'lr': 0.00016296808207947027, 'samples': 17808384, 'steps': 92751, 'loss/train': 0.9843371510505676} 08/31/2021 06:03:10 - INFO - __main__ - Step 92753: {'lr': 0.00016296310730681273, 'samples': 17808576, 'steps': 92752, 'loss/train': 1.587067723274231} 08/31/2021 06:03:11 - INFO - __main__ - Step 92754: {'lr': 0.00016295813257337266, 'samples': 17808768, 'steps': 92753, 'loss/train': 0.9570016860961914} 08/31/2021 06:03:11 - INFO - __main__ - Step 92755: {'lr': 0.00016295315787915232, 'samples': 17808960, 'steps': 92754, 'loss/train': 0.3817659616470337} 08/31/2021 06:03:11 - INFO - __main__ - Step 92756: {'lr': 0.00016294818322415392, 'samples': 17809152, 'steps': 92755, 'loss/train': 0.8158107995986938} 08/31/2021 06:03:12 - INFO - __main__ - Step 92757: {'lr': 0.00016294320860837976, 'samples': 17809344, 'steps': 92756, 'loss/train': 0.030280333012342453} 08/31/2021 06:03:13 - INFO - __main__ - Step 92758: {'lr': 0.000162938234031832, 'samples': 17809536, 'steps': 92757, 'loss/train': 1.0549521446228027} 08/31/2021 06:03:14 - INFO - __main__ - Step 92759: {'lr': 0.00016293325949451293, 'samples': 17809728, 'steps': 92758, 'loss/train': 2.4317054748535156} 08/31/2021 06:03:14 - INFO - __main__ - Step 92760: {'lr': 0.00016292828499642493, 'samples': 17809920, 'steps': 92759, 'loss/train': 0.5841332077980042} 08/31/2021 06:03:14 - INFO - __main__ - Step 92761: {'lr': 0.00016292331053756998, 'samples': 17810112, 'steps': 92760, 'loss/train': 0.8689881563186646} 08/31/2021 06:03:15 - INFO - __main__ - Step 92762: {'lr': 0.00016291833611795046, 'samples': 17810304, 'steps': 92761, 'loss/train': 0.8472656607627869} 08/31/2021 06:03:17 - INFO - __main__ - Step 92763: {'lr': 0.00016291336173756857, 'samples': 17810496, 'steps': 92762, 'loss/train': 0.8409862518310547} 08/31/2021 06:03:17 - INFO - __main__ - Step 92764: {'lr': 0.00016290838739642662, 'samples': 17810688, 'steps': 92763, 'loss/train': 1.013561487197876} 08/31/2021 06:03:18 - INFO - __main__ - Step 92765: {'lr': 0.0001629034130945267, 'samples': 17810880, 'steps': 92764, 'loss/train': 1.3197810649871826} 08/31/2021 06:03:18 - INFO - __main__ - Step 92766: {'lr': 0.00016289843883187128, 'samples': 17811072, 'steps': 92765, 'loss/train': 1.5109208822250366} 08/31/2021 06:03:18 - INFO - __main__ - Step 92767: {'lr': 0.0001628934646084624, 'samples': 17811264, 'steps': 92766, 'loss/train': 1.122603178024292} 08/31/2021 06:03:21 - INFO - __main__ - Step 92768: {'lr': 0.00016288849042430244, 'samples': 17811456, 'steps': 92767, 'loss/train': 1.2110170125961304} 08/31/2021 06:03:21 - INFO - __main__ - Step 92769: {'lr': 0.0001628835162793935, 'samples': 17811648, 'steps': 92768, 'loss/train': 0.32366663217544556} 08/31/2021 06:03:22 - INFO - __main__ - Step 92770: {'lr': 0.000162878542173738, 'samples': 17811840, 'steps': 92769, 'loss/train': 0.273818701505661} 08/31/2021 06:03:22 - INFO - __main__ - Step 92771: {'lr': 0.00016287356810733804, 'samples': 17812032, 'steps': 92770, 'loss/train': 0.3396163284778595} 08/31/2021 06:03:22 - INFO - __main__ - Step 92772: {'lr': 0.00016286859408019588, 'samples': 17812224, 'steps': 92771, 'loss/train': 1.2753489017486572} 08/31/2021 06:03:23 - INFO - __main__ - Step 92773: {'lr': 0.0001628636200923138, 'samples': 17812416, 'steps': 92772, 'loss/train': 1.1993802785873413} 08/31/2021 06:03:23 - INFO - __main__ - Step 92774: {'lr': 0.00016285864614369418, 'samples': 17812608, 'steps': 92773, 'loss/train': 1.722671627998352} 08/31/2021 06:03:25 - INFO - __main__ - Step 92775: {'lr': 0.00016285367223433893, 'samples': 17812800, 'steps': 92774, 'loss/train': 1.903552770614624} 08/31/2021 06:03:25 - INFO - __main__ - Step 92776: {'lr': 0.00016284869836425054, 'samples': 17812992, 'steps': 92775, 'loss/train': 1.3152196407318115} 08/31/2021 06:03:26 - INFO - __main__ - Step 92777: {'lr': 0.00016284372453343116, 'samples': 17813184, 'steps': 92776, 'loss/train': 0.0791829526424408} 08/31/2021 06:03:26 - INFO - __main__ - Step 92778: {'lr': 0.00016283875074188302, 'samples': 17813376, 'steps': 92777, 'loss/train': 1.1955538988113403} 08/31/2021 06:03:26 - INFO - __main__ - Step 92779: {'lr': 0.00016283377698960843, 'samples': 17813568, 'steps': 92778, 'loss/train': 1.5258305072784424} 08/31/2021 06:03:28 - INFO - __main__ - Step 92780: {'lr': 0.0001628288032766096, 'samples': 17813760, 'steps': 92779, 'loss/train': 1.0025805234909058} 08/31/2021 06:03:28 - INFO - __main__ - Step 92781: {'lr': 0.00016282382960288873, 'samples': 17813952, 'steps': 92780, 'loss/train': 1.5076427459716797} 08/31/2021 06:03:29 - INFO - __main__ - Step 92782: {'lr': 0.00016281885596844812, 'samples': 17814144, 'steps': 92781, 'loss/train': 1.1920037269592285} 08/31/2021 06:03:29 - INFO - __main__ - Step 92783: {'lr': 0.00016281388237328998, 'samples': 17814336, 'steps': 92782, 'loss/train': 1.1911624670028687} 08/31/2021 06:03:29 - INFO - __main__ - Step 92784: {'lr': 0.00016280890881741655, 'samples': 17814528, 'steps': 92783, 'loss/train': 1.137881875038147} 08/31/2021 06:03:31 - INFO - __main__ - Step 92785: {'lr': 0.0001628039353008301, 'samples': 17814720, 'steps': 92784, 'loss/train': 0.7868019342422485} 08/31/2021 06:03:31 - INFO - __main__ - Step 92786: {'lr': 0.00016279896182353284, 'samples': 17814912, 'steps': 92785, 'loss/train': 1.2034802436828613} 08/31/2021 06:03:32 - INFO - __main__ - Step 92787: {'lr': 0.00016279398838552715, 'samples': 17815104, 'steps': 92786, 'loss/train': 0.67193204164505} 08/31/2021 06:03:32 - INFO - __main__ - Step 92788: {'lr': 0.00016278901498681503, 'samples': 17815296, 'steps': 92787, 'loss/train': 1.2807931900024414} 08/31/2021 06:03:33 - INFO - __main__ - Step 92789: {'lr': 0.00016278404162739879, 'samples': 17815488, 'steps': 92788, 'loss/train': 1.0392427444458008} 08/31/2021 06:03:33 - INFO - __main__ - Step 92790: {'lr': 0.00016277906830728078, 'samples': 17815680, 'steps': 92789, 'loss/train': 0.3058653473854065} 08/31/2021 06:03:34 - INFO - __main__ - Step 92791: {'lr': 0.00016277409502646312, 'samples': 17815872, 'steps': 92790, 'loss/train': 1.2296022176742554} 08/31/2021 06:03:35 - INFO - __main__ - Step 92792: {'lr': 0.00016276912178494812, 'samples': 17816064, 'steps': 92791, 'loss/train': 4.122035980224609} 08/31/2021 06:03:35 - INFO - __main__ - Step 92793: {'lr': 0.00016276414858273802, 'samples': 17816256, 'steps': 92792, 'loss/train': 0.9921654462814331} 08/31/2021 06:03:36 - INFO - __main__ - Step 92794: {'lr': 0.0001627591754198351, 'samples': 17816448, 'steps': 92793, 'loss/train': 1.5134474039077759} 08/31/2021 06:03:36 - INFO - __main__ - Step 92795: {'lr': 0.00016275420229624148, 'samples': 17816640, 'steps': 92794, 'loss/train': 1.4683873653411865} 08/31/2021 06:03:38 - INFO - __main__ - Step 92796: {'lr': 0.00016274922921195948, 'samples': 17816832, 'steps': 92795, 'loss/train': 1.1818851232528687} 08/31/2021 06:03:38 - INFO - __main__ - Step 92797: {'lr': 0.00016274425616699133, 'samples': 17817024, 'steps': 92796, 'loss/train': 1.6359025239944458} 08/31/2021 06:03:39 - INFO - __main__ - Step 92798: {'lr': 0.00016273928316133928, 'samples': 17817216, 'steps': 92797, 'loss/train': 0.7432870268821716} 08/31/2021 06:03:39 - INFO - __main__ - Step 92799: {'lr': 0.00016273431019500558, 'samples': 17817408, 'steps': 92798, 'loss/train': 1.4704221487045288} 08/31/2021 06:03:39 - INFO - __main__ - Step 92800: {'lr': 0.0001627293372679925, 'samples': 17817600, 'steps': 92799, 'loss/train': 0.017665842548012733} 08/31/2021 06:03:40 - INFO - __main__ - Step 92801: {'lr': 0.00016272436438030219, 'samples': 17817792, 'steps': 92800, 'loss/train': 0.8468104600906372} 08/31/2021 06:03:41 - INFO - __main__ - Step 92802: {'lr': 0.00016271939153193694, 'samples': 17817984, 'steps': 92801, 'loss/train': 1.1930266618728638} 08/31/2021 06:03:42 - INFO - __main__ - Step 92803: {'lr': 0.00016271441872289894, 'samples': 17818176, 'steps': 92802, 'loss/train': 1.5612366199493408} 08/31/2021 06:03:42 - INFO - __main__ - Step 92804: {'lr': 0.0001627094459531905, 'samples': 17818368, 'steps': 92803, 'loss/train': 0.9606048464775085} 08/31/2021 06:03:42 - INFO - __main__ - Step 92805: {'lr': 0.00016270447322281383, 'samples': 17818560, 'steps': 92804, 'loss/train': 1.1723353862762451} 08/31/2021 06:03:43 - INFO - __main__ - Step 92806: {'lr': 0.00016269950053177118, 'samples': 17818752, 'steps': 92805, 'loss/train': 1.1322375535964966} 08/31/2021 06:03:44 - INFO - __main__ - Step 92807: {'lr': 0.00016269452788006479, 'samples': 17818944, 'steps': 92806, 'loss/train': 1.2295399904251099} 08/31/2021 06:03:45 - INFO - __main__ - Step 92808: {'lr': 0.0001626895552676969, 'samples': 17819136, 'steps': 92807, 'loss/train': 0.5409063100814819} 08/31/2021 06:03:45 - INFO - __main__ - Step 92809: {'lr': 0.00016268458269466974, 'samples': 17819328, 'steps': 92808, 'loss/train': 1.1123896837234497} 08/31/2021 06:03:45 - INFO - __main__ - Step 92810: {'lr': 0.00016267961016098559, 'samples': 17819520, 'steps': 92809, 'loss/train': 1.306723952293396} 08/31/2021 06:03:46 - INFO - __main__ - Step 92811: {'lr': 0.00016267463766664667, 'samples': 17819712, 'steps': 92810, 'loss/train': 1.3729243278503418} 08/31/2021 06:03:47 - INFO - __main__ - Step 92812: {'lr': 0.00016266966521165518, 'samples': 17819904, 'steps': 92811, 'loss/train': 0.8122789263725281} 08/31/2021 06:03:48 - INFO - __main__ - Step 92813: {'lr': 0.00016266469279601337, 'samples': 17820096, 'steps': 92812, 'loss/train': 0.8024110794067383} 08/31/2021 06:03:48 - INFO - __main__ - Step 92814: {'lr': 0.0001626597204197236, 'samples': 17820288, 'steps': 92813, 'loss/train': 1.000313639640808} 08/31/2021 06:03:49 - INFO - __main__ - Step 92815: {'lr': 0.00016265474808278791, 'samples': 17820480, 'steps': 92814, 'loss/train': 1.6866518259048462} 08/31/2021 06:03:49 - INFO - __main__ - Step 92816: {'lr': 0.00016264977578520868, 'samples': 17820672, 'steps': 92815, 'loss/train': 1.4306997060775757} 08/31/2021 06:03:49 - INFO - __main__ - Step 92817: {'lr': 0.0001626448035269881, 'samples': 17820864, 'steps': 92816, 'loss/train': 0.4416625499725342} 08/31/2021 06:03:51 - INFO - __main__ - Step 92818: {'lr': 0.00016263983130812844, 'samples': 17821056, 'steps': 92817, 'loss/train': 1.2808780670166016} 08/31/2021 06:03:52 - INFO - __main__ - Step 92819: {'lr': 0.00016263485912863189, 'samples': 17821248, 'steps': 92818, 'loss/train': 1.211301326751709} 08/31/2021 06:03:52 - INFO - __main__ - Step 92820: {'lr': 0.00016262988698850073, 'samples': 17821440, 'steps': 92819, 'loss/train': 0.9784559011459351} 08/31/2021 06:03:53 - INFO - __main__ - Step 92821: {'lr': 0.0001626249148877372, 'samples': 17821632, 'steps': 92820, 'loss/train': 0.04850833863019943} 08/31/2021 06:03:53 - INFO - __main__ - Step 92822: {'lr': 0.0001626199428263436, 'samples': 17821824, 'steps': 92821, 'loss/train': 1.4690064191818237} 08/31/2021 06:03:54 - INFO - __main__ - Step 92823: {'lr': 0.00016261497080432202, 'samples': 17822016, 'steps': 92822, 'loss/train': 1.894921898841858} 08/31/2021 06:03:55 - INFO - __main__ - Step 92824: {'lr': 0.0001626099988216748, 'samples': 17822208, 'steps': 92823, 'loss/train': 1.3139222860336304} 08/31/2021 06:03:55 - INFO - __main__ - Step 92825: {'lr': 0.00016260502687840423, 'samples': 17822400, 'steps': 92824, 'loss/train': 1.6560595035552979} 08/31/2021 06:03:56 - INFO - __main__ - Step 92826: {'lr': 0.0001626000549745124, 'samples': 17822592, 'steps': 92825, 'loss/train': 1.282023549079895} 08/31/2021 06:03:56 - INFO - __main__ - Step 92827: {'lr': 0.00016259508311000168, 'samples': 17822784, 'steps': 92826, 'loss/train': 1.2305707931518555} 08/31/2021 06:03:58 - INFO - __main__ - Step 92828: {'lr': 0.00016259011128487433, 'samples': 17822976, 'steps': 92827, 'loss/train': 0.8536060452461243} 08/31/2021 06:03:58 - INFO - __main__ - Step 92829: {'lr': 0.00016258513949913246, 'samples': 17823168, 'steps': 92828, 'loss/train': 0.9317957758903503} 08/31/2021 06:03:58 - INFO - __main__ - Step 92830: {'lr': 0.00016258016775277833, 'samples': 17823360, 'steps': 92829, 'loss/train': 0.11542128771543503} 08/31/2021 06:03:59 - INFO - __main__ - Step 92831: {'lr': 0.00016257519604581427, 'samples': 17823552, 'steps': 92830, 'loss/train': 0.9216220378875732} 08/31/2021 06:03:59 - INFO - __main__ - Step 92832: {'lr': 0.00016257022437824248, 'samples': 17823744, 'steps': 92831, 'loss/train': 1.6030970811843872} 08/31/2021 06:04:01 - INFO - __main__ - Step 92833: {'lr': 0.00016256525275006525, 'samples': 17823936, 'steps': 92832, 'loss/train': 1.421883463859558} 08/31/2021 06:04:01 - INFO - __main__ - Step 92834: {'lr': 0.0001625602811612847, 'samples': 17824128, 'steps': 92833, 'loss/train': 1.5337131023406982} 08/31/2021 06:04:02 - INFO - __main__ - Step 92835: {'lr': 0.0001625553096119032, 'samples': 17824320, 'steps': 92834, 'loss/train': 1.3116426467895508} 08/31/2021 06:04:02 - INFO - __main__ - Step 92836: {'lr': 0.00016255033810192284, 'samples': 17824512, 'steps': 92835, 'loss/train': 0.7199862003326416} 08/31/2021 06:04:02 - INFO - __main__ - Step 92837: {'lr': 0.000162545366631346, 'samples': 17824704, 'steps': 92836, 'loss/train': 0.14525750279426575} 08/31/2021 06:04:04 - INFO - __main__ - Step 92838: {'lr': 0.00016254039520017483, 'samples': 17824896, 'steps': 92837, 'loss/train': 1.3510545492172241} 08/31/2021 06:04:04 - INFO - __main__ - Step 92839: {'lr': 0.00016253542380841162, 'samples': 17825088, 'steps': 92838, 'loss/train': 1.2111225128173828} 08/31/2021 06:04:05 - INFO - __main__ - Step 92840: {'lr': 0.00016253045245605863, 'samples': 17825280, 'steps': 92839, 'loss/train': 1.516353964805603} 08/31/2021 06:04:05 - INFO - __main__ - Step 92841: {'lr': 0.0001625254811431181, 'samples': 17825472, 'steps': 92840, 'loss/train': 1.1897244453430176} 08/31/2021 06:04:05 - INFO - __main__ - Step 92842: {'lr': 0.00016252050986959222, 'samples': 17825664, 'steps': 92841, 'loss/train': 1.1627140045166016} 08/31/2021 06:04:07 - INFO - __main__ - Step 92843: {'lr': 0.00016251553863548318, 'samples': 17825856, 'steps': 92842, 'loss/train': 1.040063738822937} 08/31/2021 06:04:07 - INFO - __main__ - Step 92844: {'lr': 0.0001625105674407934, 'samples': 17826048, 'steps': 92843, 'loss/train': 1.3008543252944946} 08/31/2021 06:04:08 - INFO - __main__ - Step 92845: {'lr': 0.0001625055962855249, 'samples': 17826240, 'steps': 92844, 'loss/train': 0.9409511685371399} 08/31/2021 06:04:08 - INFO - __main__ - Step 92846: {'lr': 0.00016250062516968007, 'samples': 17826432, 'steps': 92845, 'loss/train': 1.1647167205810547} 08/31/2021 06:04:08 - INFO - __main__ - Step 92847: {'lr': 0.0001624956540932611, 'samples': 17826624, 'steps': 92846, 'loss/train': 1.372702956199646} 08/31/2021 06:04:10 - INFO - __main__ - Step 92848: {'lr': 0.00016249068305627023, 'samples': 17826816, 'steps': 92847, 'loss/train': 0.8453388810157776} 08/31/2021 06:04:10 - INFO - __main__ - Step 92849: {'lr': 0.0001624857120587097, 'samples': 17827008, 'steps': 92848, 'loss/train': 5.062452793121338} 08/31/2021 06:04:10 - INFO - __main__ - Step 92850: {'lr': 0.0001624807411005818, 'samples': 17827200, 'steps': 92849, 'loss/train': 1.123009204864502} 08/31/2021 06:04:11 - INFO - __main__ - Step 92851: {'lr': 0.0001624757701818887, 'samples': 17827392, 'steps': 92850, 'loss/train': 1.2613673210144043} 08/31/2021 06:04:11 - INFO - __main__ - Step 92852: {'lr': 0.00016247079930263266, 'samples': 17827584, 'steps': 92851, 'loss/train': 1.5890278816223145} 08/31/2021 06:04:13 - INFO - __main__ - Step 92853: {'lr': 0.00016246582846281594, 'samples': 17827776, 'steps': 92852, 'loss/train': 1.4581550359725952} 08/31/2021 06:04:13 - INFO - __main__ - Step 92854: {'lr': 0.00016246085766244078, 'samples': 17827968, 'steps': 92853, 'loss/train': 1.0894801616668701} 08/31/2021 06:04:14 - INFO - __main__ - Step 92855: {'lr': 0.00016245588690150947, 'samples': 17828160, 'steps': 92854, 'loss/train': 0.5538333058357239} 08/31/2021 06:04:14 - INFO - __main__ - Step 92856: {'lr': 0.00016245091618002412, 'samples': 17828352, 'steps': 92855, 'loss/train': 1.5053911209106445} 08/31/2021 06:04:14 - INFO - __main__ - Step 92857: {'lr': 0.00016244594549798703, 'samples': 17828544, 'steps': 92856, 'loss/train': 0.6136094927787781} 08/31/2021 06:04:16 - INFO - __main__ - Step 92858: {'lr': 0.00016244097485540045, 'samples': 17828736, 'steps': 92857, 'loss/train': 1.3223116397857666} 08/31/2021 06:04:16 - INFO - __main__ - Step 92859: {'lr': 0.00016243600425226658, 'samples': 17828928, 'steps': 92858, 'loss/train': 1.3764700889587402} 08/31/2021 06:04:17 - INFO - __main__ - Step 92860: {'lr': 0.0001624310336885877, 'samples': 17829120, 'steps': 92859, 'loss/train': 0.9179240465164185} 08/31/2021 06:04:17 - INFO - __main__ - Step 92861: {'lr': 0.0001624260631643661, 'samples': 17829312, 'steps': 92860, 'loss/train': 1.329260230064392} 08/31/2021 06:04:17 - INFO - __main__ - Step 92862: {'lr': 0.0001624210926796039, 'samples': 17829504, 'steps': 92861, 'loss/train': 1.4562300443649292} 08/31/2021 06:04:18 - INFO - __main__ - Step 92863: {'lr': 0.00016241612223430343, 'samples': 17829696, 'steps': 92862, 'loss/train': 0.9077481031417847} 08/31/2021 06:04:19 - INFO - __main__ - Step 92864: {'lr': 0.00016241115182846687, 'samples': 17829888, 'steps': 92863, 'loss/train': 0.7700551152229309} 08/31/2021 06:04:20 - INFO - __main__ - Step 92865: {'lr': 0.00016240618146209657, 'samples': 17830080, 'steps': 92864, 'loss/train': 1.2583962678909302} 08/31/2021 06:04:20 - INFO - __main__ - Step 92866: {'lr': 0.00016240121113519462, 'samples': 17830272, 'steps': 92865, 'loss/train': 1.3105446100234985} 08/31/2021 06:04:20 - INFO - __main__ - Step 92867: {'lr': 0.0001623962408477634, 'samples': 17830464, 'steps': 92866, 'loss/train': 0.8479514718055725} 08/31/2021 06:04:21 - INFO - __main__ - Step 92868: {'lr': 0.00016239127059980513, 'samples': 17830656, 'steps': 92867, 'loss/train': 1.126763105392456} 08/31/2021 06:04:22 - INFO - __main__ - Step 92869: {'lr': 0.00016238630039132194, 'samples': 17830848, 'steps': 92868, 'loss/train': 1.0684372186660767} 08/31/2021 06:04:23 - INFO - __main__ - Step 92870: {'lr': 0.00016238133022231611, 'samples': 17831040, 'steps': 92869, 'loss/train': 1.2576051950454712} 08/31/2021 06:04:23 - INFO - __main__ - Step 92871: {'lr': 0.0001623763600927899, 'samples': 17831232, 'steps': 92870, 'loss/train': 1.438032627105713} 08/31/2021 06:04:23 - INFO - __main__ - Step 92872: {'lr': 0.00016237139000274553, 'samples': 17831424, 'steps': 92871, 'loss/train': 1.2141708135604858} 08/31/2021 06:04:24 - INFO - __main__ - Step 92873: {'lr': 0.0001623664199521853, 'samples': 17831616, 'steps': 92872, 'loss/train': 0.26481547951698303} 08/31/2021 06:04:26 - INFO - __main__ - Step 92874: {'lr': 0.0001623614499411114, 'samples': 17831808, 'steps': 92873, 'loss/train': 1.3077892065048218} 08/31/2021 06:04:26 - INFO - __main__ - Step 92875: {'lr': 0.00016235647996952604, 'samples': 17832000, 'steps': 92874, 'loss/train': 0.7128578424453735} 08/31/2021 06:04:27 - INFO - __main__ - Step 92876: {'lr': 0.00016235151003743154, 'samples': 17832192, 'steps': 92875, 'loss/train': 1.4692271947860718} 08/31/2021 06:04:27 - INFO - __main__ - Step 92877: {'lr': 0.00016234654014483008, 'samples': 17832384, 'steps': 92876, 'loss/train': 1.6896271705627441} 08/31/2021 06:04:27 - INFO - __main__ - Step 92878: {'lr': 0.00016234157029172393, 'samples': 17832576, 'steps': 92877, 'loss/train': 0.7486164569854736} 08/31/2021 06:04:29 - INFO - __main__ - Step 92879: {'lr': 0.00016233660047811527, 'samples': 17832768, 'steps': 92878, 'loss/train': 1.5001646280288696} 08/31/2021 06:04:29 - INFO - __main__ - Step 92880: {'lr': 0.00016233163070400642, 'samples': 17832960, 'steps': 92879, 'loss/train': 0.48445168137550354} 08/31/2021 06:04:30 - INFO - __main__ - Step 92881: {'lr': 0.00016232666096939967, 'samples': 17833152, 'steps': 92880, 'loss/train': 0.6686707139015198} 08/31/2021 06:04:30 - INFO - __main__ - Step 92882: {'lr': 0.0001623216912742971, 'samples': 17833344, 'steps': 92881, 'loss/train': 1.7391383647918701} 08/31/2021 06:04:30 - INFO - __main__ - Step 92883: {'lr': 0.00016231672161870104, 'samples': 17833536, 'steps': 92882, 'loss/train': 1.118222951889038} 08/31/2021 06:04:32 - INFO - __main__ - Step 92884: {'lr': 0.00016231175200261366, 'samples': 17833728, 'steps': 92883, 'loss/train': 0.892760694026947} 08/31/2021 06:04:32 - INFO - __main__ - Step 92885: {'lr': 0.00016230678242603726, 'samples': 17833920, 'steps': 92884, 'loss/train': 0.6856019496917725} 08/31/2021 06:04:33 - INFO - __main__ - Step 92886: {'lr': 0.0001623018128889741, 'samples': 17834112, 'steps': 92885, 'loss/train': 1.178547978401184} 08/31/2021 06:04:33 - INFO - __main__ - Step 92887: {'lr': 0.00016229684339142636, 'samples': 17834304, 'steps': 92886, 'loss/train': 1.851391315460205} 08/31/2021 06:04:33 - INFO - __main__ - Step 92888: {'lr': 0.00016229187393339633, 'samples': 17834496, 'steps': 92887, 'loss/train': 5.027653217315674} 08/31/2021 06:04:35 - INFO - __main__ - Step 92889: {'lr': 0.0001622869045148862, 'samples': 17834688, 'steps': 92888, 'loss/train': 1.3849701881408691} 08/31/2021 06:04:36 - INFO - __main__ - Step 92890: {'lr': 0.00016228193513589828, 'samples': 17834880, 'steps': 92889, 'loss/train': 1.2579455375671387} 08/31/2021 06:04:36 - INFO - __main__ - Step 92891: {'lr': 0.00016227696579643476, 'samples': 17835072, 'steps': 92890, 'loss/train': 0.04738476499915123} 08/31/2021 06:04:36 - INFO - __main__ - Step 92892: {'lr': 0.00016227199649649786, 'samples': 17835264, 'steps': 92891, 'loss/train': 1.84577476978302} 08/31/2021 06:04:37 - INFO - __main__ - Step 92893: {'lr': 0.00016226702723608983, 'samples': 17835456, 'steps': 92892, 'loss/train': 1.6937170028686523} 08/31/2021 06:04:37 - INFO - __main__ - Step 92894: {'lr': 0.00016226205801521295, 'samples': 17835648, 'steps': 92893, 'loss/train': 1.0232222080230713} 08/31/2021 06:04:38 - INFO - __main__ - Step 92895: {'lr': 0.00016225708883386956, 'samples': 17835840, 'steps': 92894, 'loss/train': 1.2351188659667969} 08/31/2021 06:04:39 - INFO - __main__ - Step 92896: {'lr': 0.00016225211969206165, 'samples': 17836032, 'steps': 92895, 'loss/train': 1.2460803985595703} 08/31/2021 06:04:39 - INFO - __main__ - Step 92897: {'lr': 0.00016224715058979155, 'samples': 17836224, 'steps': 92896, 'loss/train': 1.1175986528396606} 08/31/2021 06:04:40 - INFO - __main__ - Step 92898: {'lr': 0.00016224218152706155, 'samples': 17836416, 'steps': 92897, 'loss/train': 0.9418742656707764} 08/31/2021 06:04:40 - INFO - __main__ - Step 92899: {'lr': 0.00016223721250387387, 'samples': 17836608, 'steps': 92898, 'loss/train': 1.24630868434906} 08/31/2021 06:04:42 - INFO - __main__ - Step 92900: {'lr': 0.00016223224352023076, 'samples': 17836800, 'steps': 92899, 'loss/train': 1.5813961029052734} 08/31/2021 06:04:42 - INFO - __main__ - Step 92901: {'lr': 0.00016222727457613446, 'samples': 17836992, 'steps': 92900, 'loss/train': 1.2072709798812866} 08/31/2021 06:04:42 - INFO - __main__ - Step 92902: {'lr': 0.00016222230567158714, 'samples': 17837184, 'steps': 92901, 'loss/train': 0.3466912508010864} 08/31/2021 06:04:43 - INFO - __main__ - Step 92903: {'lr': 0.00016221733680659112, 'samples': 17837376, 'steps': 92902, 'loss/train': 0.6965704560279846} 08/31/2021 06:04:43 - INFO - __main__ - Step 92904: {'lr': 0.00016221236798114863, 'samples': 17837568, 'steps': 92903, 'loss/train': 1.5418016910552979} 08/31/2021 06:04:44 - INFO - __main__ - Step 92905: {'lr': 0.0001622073991952619, 'samples': 17837760, 'steps': 92904, 'loss/train': 1.4997999668121338} 08/31/2021 06:04:45 - INFO - __main__ - Step 92906: {'lr': 0.00016220243044893313, 'samples': 17837952, 'steps': 92905, 'loss/train': 0.6640836000442505} 08/31/2021 06:04:45 - INFO - __main__ - Step 92907: {'lr': 0.0001621974617421646, 'samples': 17838144, 'steps': 92906, 'loss/train': 1.2359780073165894} 08/31/2021 06:04:46 - INFO - __main__ - Step 92908: {'lr': 0.00016219249307495865, 'samples': 17838336, 'steps': 92907, 'loss/train': 0.9501781463623047} 08/31/2021 06:04:46 - INFO - __main__ - Step 92909: {'lr': 0.00016218752444731733, 'samples': 17838528, 'steps': 92908, 'loss/train': 1.217472791671753} 08/31/2021 06:04:46 - INFO - __main__ - Step 92910: {'lr': 0.0001621825558592429, 'samples': 17838720, 'steps': 92909, 'loss/train': 1.062938928604126} 08/31/2021 06:04:48 - INFO - __main__ - Step 92911: {'lr': 0.00016217758731073767, 'samples': 17838912, 'steps': 92910, 'loss/train': 1.3136919736862183} 08/31/2021 06:04:48 - INFO - __main__ - Step 92912: {'lr': 0.00016217261880180388, 'samples': 17839104, 'steps': 92911, 'loss/train': 1.444398283958435} 08/31/2021 06:04:49 - INFO - __main__ - Step 92913: {'lr': 0.00016216765033244377, 'samples': 17839296, 'steps': 92912, 'loss/train': 1.262939453125} 08/31/2021 06:04:49 - INFO - __main__ - Step 92914: {'lr': 0.00016216268190265954, 'samples': 17839488, 'steps': 92913, 'loss/train': 1.4039549827575684} 08/31/2021 06:04:49 - INFO - __main__ - Step 92915: {'lr': 0.00016215771351245345, 'samples': 17839680, 'steps': 92914, 'loss/train': 1.0036615133285522} 08/31/2021 06:04:51 - INFO - __main__ - Step 92916: {'lr': 0.00016215274516182774, 'samples': 17839872, 'steps': 92915, 'loss/train': 0.6397667527198792} 08/31/2021 06:04:51 - INFO - __main__ - Step 92917: {'lr': 0.00016214777685078465, 'samples': 17840064, 'steps': 92916, 'loss/train': 1.4314059019088745} 08/31/2021 06:04:52 - INFO - __main__ - Step 92918: {'lr': 0.0001621428085793264, 'samples': 17840256, 'steps': 92917, 'loss/train': 1.2612289190292358} 08/31/2021 06:04:52 - INFO - __main__ - Step 92919: {'lr': 0.00016213784034745527, 'samples': 17840448, 'steps': 92918, 'loss/train': 1.1654831171035767} 08/31/2021 06:04:52 - INFO - __main__ - Step 92920: {'lr': 0.00016213287215517347, 'samples': 17840640, 'steps': 92919, 'loss/train': 1.3055131435394287} 08/31/2021 06:04:54 - INFO - __main__ - Step 92921: {'lr': 0.00016212790400248322, 'samples': 17840832, 'steps': 92920, 'loss/train': 1.2747501134872437} 08/31/2021 06:04:54 - INFO - __main__ - Step 92922: {'lr': 0.0001621229358893869, 'samples': 17841024, 'steps': 92921, 'loss/train': 0.851895272731781} 08/31/2021 06:04:55 - INFO - __main__ - Step 92923: {'lr': 0.0001621179678158865, 'samples': 17841216, 'steps': 92922, 'loss/train': 1.241403579711914} 08/31/2021 06:04:55 - INFO - __main__ - Step 92924: {'lr': 0.00016211299978198442, 'samples': 17841408, 'steps': 92923, 'loss/train': 1.7515345811843872} 08/31/2021 06:04:55 - INFO - __main__ - Step 92925: {'lr': 0.00016210803178768286, 'samples': 17841600, 'steps': 92924, 'loss/train': 1.6366711854934692} 08/31/2021 06:04:57 - INFO - __main__ - Step 92926: {'lr': 0.00016210306383298407, 'samples': 17841792, 'steps': 92925, 'loss/train': 1.0035797357559204} 08/31/2021 06:04:58 - INFO - __main__ - Step 92927: {'lr': 0.00016209809591789025, 'samples': 17841984, 'steps': 92926, 'loss/train': 1.0836808681488037} 08/31/2021 06:04:58 - INFO - __main__ - Step 92928: {'lr': 0.00016209312804240373, 'samples': 17842176, 'steps': 92927, 'loss/train': 1.098713755607605} 08/31/2021 06:04:59 - INFO - __main__ - Step 92929: {'lr': 0.00016208816020652663, 'samples': 17842368, 'steps': 92928, 'loss/train': 1.0110706090927124} 08/31/2021 06:04:59 - INFO - __main__ - Step 92930: {'lr': 0.0001620831924102613, 'samples': 17842560, 'steps': 92929, 'loss/train': 1.2390903234481812} 08/31/2021 06:05:01 - INFO - __main__ - Step 92931: {'lr': 0.00016207822465360989, 'samples': 17842752, 'steps': 92930, 'loss/train': 1.3424463272094727} 08/31/2021 06:05:01 - INFO - __main__ - Step 92932: {'lr': 0.00016207325693657468, 'samples': 17842944, 'steps': 92931, 'loss/train': 0.16101470589637756} 08/31/2021 06:05:01 - INFO - __main__ - Step 92933: {'lr': 0.0001620682892591579, 'samples': 17843136, 'steps': 92932, 'loss/train': 1.1139612197875977} 08/31/2021 06:05:02 - INFO - __main__ - Step 92934: {'lr': 0.00016206332162136186, 'samples': 17843328, 'steps': 92933, 'loss/train': 1.133834958076477} 08/31/2021 06:05:02 - INFO - __main__ - Step 92935: {'lr': 0.00016205835402318875, 'samples': 17843520, 'steps': 92934, 'loss/train': 1.0208772420883179} 08/31/2021 06:05:02 - INFO - __main__ - Step 92936: {'lr': 0.00016205338646464067, 'samples': 17843712, 'steps': 92935, 'loss/train': 1.0935078859329224} 08/31/2021 06:05:05 - INFO - __main__ - Step 92937: {'lr': 0.00016204841894572003, 'samples': 17843904, 'steps': 92936, 'loss/train': 1.10813570022583} 08/31/2021 06:05:05 - INFO - __main__ - Step 92938: {'lr': 0.00016204345146642903, 'samples': 17844096, 'steps': 92937, 'loss/train': 1.4479540586471558} 08/31/2021 06:05:06 - INFO - __main__ - Step 92939: {'lr': 0.00016203848402676985, 'samples': 17844288, 'steps': 92938, 'loss/train': 1.4395060539245605} 08/31/2021 06:05:06 - INFO - __main__ - Step 92940: {'lr': 0.0001620335166267448, 'samples': 17844480, 'steps': 92939, 'loss/train': 1.2867622375488281} 08/31/2021 06:05:06 - INFO - __main__ - Step 92941: {'lr': 0.00016202854926635607, 'samples': 17844672, 'steps': 92940, 'loss/train': 1.5508315563201904} 08/31/2021 06:05:07 - INFO - __main__ - Step 92942: {'lr': 0.0001620235819456059, 'samples': 17844864, 'steps': 92941, 'loss/train': 1.1946649551391602} 08/31/2021 06:05:08 - INFO - __main__ - Step 92943: {'lr': 0.00016201861466449657, 'samples': 17845056, 'steps': 92942, 'loss/train': 1.2381253242492676} 08/31/2021 06:05:09 - INFO - __main__ - Step 92944: {'lr': 0.00016201364742303033, 'samples': 17845248, 'steps': 92943, 'loss/train': 0.7634170055389404} 08/31/2021 06:05:09 - INFO - __main__ - Step 92945: {'lr': 0.0001620086802212094, 'samples': 17845440, 'steps': 92944, 'loss/train': 0.6666200757026672} 08/31/2021 06:05:09 - INFO - __main__ - Step 92946: {'lr': 0.00016200371305903594, 'samples': 17845632, 'steps': 92945, 'loss/train': 0.2122177928686142} 08/31/2021 06:05:10 - INFO - __main__ - Step 92947: {'lr': 0.00016199874593651227, 'samples': 17845824, 'steps': 92946, 'loss/train': 1.2836014032363892} 08/31/2021 06:05:12 - INFO - __main__ - Step 92948: {'lr': 0.00016199377885364058, 'samples': 17846016, 'steps': 92947, 'loss/train': 0.362137109041214} 08/31/2021 06:05:12 - INFO - __main__ - Step 92949: {'lr': 0.00016198881181042323, 'samples': 17846208, 'steps': 92948, 'loss/train': 1.6656304597854614} 08/31/2021 06:05:13 - INFO - __main__ - Step 92950: {'lr': 0.00016198384480686228, 'samples': 17846400, 'steps': 92949, 'loss/train': 0.015264205634593964} 08/31/2021 06:05:13 - INFO - __main__ - Step 92951: {'lr': 0.00016197887784296007, 'samples': 17846592, 'steps': 92950, 'loss/train': 1.1778934001922607} 08/31/2021 06:05:13 - INFO - __main__ - Step 92952: {'lr': 0.00016197391091871878, 'samples': 17846784, 'steps': 92951, 'loss/train': 0.9916595816612244} 08/31/2021 06:05:14 - INFO - __main__ - Step 92953: {'lr': 0.00016196894403414073, 'samples': 17846976, 'steps': 92952, 'loss/train': 1.0404555797576904} 08/31/2021 06:05:15 - INFO - __main__ - Step 92954: {'lr': 0.0001619639771892281, 'samples': 17847168, 'steps': 92953, 'loss/train': 1.5505099296569824} 08/31/2021 06:05:16 - INFO - __main__ - Step 92955: {'lr': 0.00016195901038398313, 'samples': 17847360, 'steps': 92954, 'loss/train': 1.0486818552017212} 08/31/2021 06:05:16 - INFO - __main__ - Step 92956: {'lr': 0.00016195404361840816, 'samples': 17847552, 'steps': 92955, 'loss/train': 1.2797014713287354} 08/31/2021 06:05:16 - INFO - __main__ - Step 92957: {'lr': 0.00016194907689250524, 'samples': 17847744, 'steps': 92956, 'loss/train': 0.7789962291717529} 08/31/2021 06:05:17 - INFO - __main__ - Step 92958: {'lr': 0.00016194411020627674, 'samples': 17847936, 'steps': 92957, 'loss/train': 0.4883604049682617} 08/31/2021 06:05:17 - INFO - __main__ - Step 92959: {'lr': 0.00016193914355972484, 'samples': 17848128, 'steps': 92958, 'loss/train': 1.5736714601516724} 08/31/2021 06:05:19 - INFO - __main__ - Step 92960: {'lr': 0.00016193417695285184, 'samples': 17848320, 'steps': 92959, 'loss/train': 1.1000217199325562} 08/31/2021 06:05:19 - INFO - __main__ - Step 92961: {'lr': 0.0001619292103856599, 'samples': 17848512, 'steps': 92960, 'loss/train': 1.5767037868499756} 08/31/2021 06:05:19 - INFO - __main__ - Step 92962: {'lr': 0.0001619242438581514, 'samples': 17848704, 'steps': 92961, 'loss/train': 0.5742932558059692} 08/31/2021 06:05:20 - INFO - __main__ - Step 92963: {'lr': 0.00016191927737032834, 'samples': 17848896, 'steps': 92962, 'loss/train': 1.183353304862976} 08/31/2021 06:05:20 - INFO - __main__ - Step 92964: {'lr': 0.00016191431092219317, 'samples': 17849088, 'steps': 92963, 'loss/train': 0.8532246351242065} 08/31/2021 06:05:22 - INFO - __main__ - Step 92965: {'lr': 0.00016190934451374805, 'samples': 17849280, 'steps': 92964, 'loss/train': 1.112805724143982} 08/31/2021 06:05:22 - INFO - __main__ - Step 92966: {'lr': 0.0001619043781449952, 'samples': 17849472, 'steps': 92965, 'loss/train': 1.0949733257293701} 08/31/2021 06:05:23 - INFO - __main__ - Step 92967: {'lr': 0.00016189941181593692, 'samples': 17849664, 'steps': 92966, 'loss/train': 1.9044109582901} 08/31/2021 06:05:23 - INFO - __main__ - Step 92968: {'lr': 0.0001618944455265754, 'samples': 17849856, 'steps': 92967, 'loss/train': 1.55818772315979} 08/31/2021 06:05:23 - INFO - __main__ - Step 92969: {'lr': 0.00016188947927691283, 'samples': 17850048, 'steps': 92968, 'loss/train': 0.828266441822052} 08/31/2021 06:05:25 - INFO - __main__ - Step 92970: {'lr': 0.00016188451306695152, 'samples': 17850240, 'steps': 92969, 'loss/train': 1.4029043912887573} 08/31/2021 06:05:25 - INFO - __main__ - Step 92971: {'lr': 0.00016187954689669368, 'samples': 17850432, 'steps': 92970, 'loss/train': 0.721688985824585} 08/31/2021 06:05:26 - INFO - __main__ - Step 92972: {'lr': 0.0001618745807661416, 'samples': 17850624, 'steps': 92971, 'loss/train': 0.3279648423194885} 08/31/2021 06:05:26 - INFO - __main__ - Step 92973: {'lr': 0.0001618696146752974, 'samples': 17850816, 'steps': 92972, 'loss/train': 1.341712236404419} 08/31/2021 06:05:26 - INFO - __main__ - Step 92974: {'lr': 0.00016186464862416345, 'samples': 17851008, 'steps': 92973, 'loss/train': 0.779901921749115} 08/31/2021 06:05:28 - INFO - __main__ - Step 92975: {'lr': 0.0001618596826127419, 'samples': 17851200, 'steps': 92974, 'loss/train': 1.1809896230697632} 08/31/2021 06:05:29 - INFO - __main__ - Step 92976: {'lr': 0.00016185471664103507, 'samples': 17851392, 'steps': 92975, 'loss/train': 1.3292433023452759} 08/31/2021 06:05:29 - INFO - __main__ - Step 92977: {'lr': 0.00016184975070904513, 'samples': 17851584, 'steps': 92976, 'loss/train': 1.3711880445480347} 08/31/2021 06:05:29 - INFO - __main__ - Step 92978: {'lr': 0.00016184478481677433, 'samples': 17851776, 'steps': 92977, 'loss/train': 1.8401968479156494} 08/31/2021 06:05:30 - INFO - __main__ - Step 92979: {'lr': 0.0001618398189642249, 'samples': 17851968, 'steps': 92978, 'loss/train': 0.6622599363327026} 08/31/2021 06:05:30 - INFO - __main__ - Step 92980: {'lr': 0.00016183485315139905, 'samples': 17852160, 'steps': 92979, 'loss/train': 0.015253803692758083} 08/31/2021 06:05:30 - INFO - __main__ - Step 92981: {'lr': 0.00016182988737829907, 'samples': 17852352, 'steps': 92980, 'loss/train': 1.7034845352172852} 08/31/2021 06:05:32 - INFO - __main__ - Step 92982: {'lr': 0.00016182492164492718, 'samples': 17852544, 'steps': 92981, 'loss/train': 1.0552754402160645} 08/31/2021 06:05:33 - INFO - __main__ - Step 92983: {'lr': 0.00016181995595128564, 'samples': 17852736, 'steps': 92982, 'loss/train': 1.3222235441207886} 08/31/2021 06:05:33 - INFO - __main__ - Step 92984: {'lr': 0.0001618149902973767, 'samples': 17852928, 'steps': 92983, 'loss/train': 1.5502188205718994} 08/31/2021 06:05:34 - INFO - __main__ - Step 92985: {'lr': 0.0001618100246832025, 'samples': 17853120, 'steps': 92984, 'loss/train': 0.25085821747779846} 08/31/2021 06:05:34 - INFO - __main__ - Step 92986: {'lr': 0.00016180505910876533, 'samples': 17853312, 'steps': 92985, 'loss/train': 0.9498203992843628} 08/31/2021 06:05:34 - INFO - __main__ - Step 92987: {'lr': 0.0001618000935740675, 'samples': 17853504, 'steps': 92986, 'loss/train': 1.3854347467422485} 08/31/2021 06:05:36 - INFO - __main__ - Step 92988: {'lr': 0.00016179512807911112, 'samples': 17853696, 'steps': 92987, 'loss/train': 1.3423140048980713} 08/31/2021 06:05:36 - INFO - __main__ - Step 92989: {'lr': 0.00016179016262389865, 'samples': 17853888, 'steps': 92988, 'loss/train': 0.9023157358169556} 08/31/2021 06:05:37 - INFO - __main__ - Step 92990: {'lr': 0.00016178519720843205, 'samples': 17854080, 'steps': 92989, 'loss/train': 2.0447542667388916} 08/31/2021 06:05:37 - INFO - __main__ - Step 92991: {'lr': 0.00016178023183271368, 'samples': 17854272, 'steps': 92990, 'loss/train': 1.4341719150543213} 08/31/2021 06:05:37 - INFO - __main__ - Step 92992: {'lr': 0.00016177526649674577, 'samples': 17854464, 'steps': 92991, 'loss/train': 1.16050124168396} 08/31/2021 06:05:39 - INFO - __main__ - Step 92993: {'lr': 0.0001617703012005306, 'samples': 17854656, 'steps': 92992, 'loss/train': 0.5621235370635986} 08/31/2021 06:05:40 - INFO - __main__ - Step 92994: {'lr': 0.00016176533594407033, 'samples': 17854848, 'steps': 92993, 'loss/train': 1.2791398763656616} 08/31/2021 06:05:40 - INFO - __main__ - Step 92995: {'lr': 0.00016176037072736723, 'samples': 17855040, 'steps': 92994, 'loss/train': 1.1615254878997803} 08/31/2021 06:05:40 - INFO - __main__ - Step 92996: {'lr': 0.00016175540555042356, 'samples': 17855232, 'steps': 92995, 'loss/train': 1.1751164197921753} 08/31/2021 06:05:41 - INFO - __main__ - Step 92997: {'lr': 0.00016175044041324155, 'samples': 17855424, 'steps': 92996, 'loss/train': 1.1145782470703125} 08/31/2021 06:05:41 - INFO - __main__ - Step 92998: {'lr': 0.00016174547531582346, 'samples': 17855616, 'steps': 92997, 'loss/train': 1.7489707469940186} 08/31/2021 06:05:42 - INFO - __main__ - Step 92999: {'lr': 0.00016174051025817144, 'samples': 17855808, 'steps': 92998, 'loss/train': 1.1845457553863525} 08/31/2021 06:05:43 - INFO - __main__ - Step 93000: {'lr': 0.00016173554524028782, 'samples': 17856000, 'steps': 92999, 'loss/train': 1.7226532697677612} 08/31/2021 06:05:43 - INFO - __main__ - Step 93001: {'lr': 0.0001617305802621748, 'samples': 17856192, 'steps': 93000, 'loss/train': 0.8668561577796936} 08/31/2021 06:05:44 - INFO - __main__ - Step 93002: {'lr': 0.0001617256153238347, 'samples': 17856384, 'steps': 93001, 'loss/train': 0.9405739307403564} 08/31/2021 06:05:44 - INFO - __main__ - Step 93003: {'lr': 0.0001617206504252696, 'samples': 17856576, 'steps': 93002, 'loss/train': 1.4271043539047241} 08/31/2021 06:05:45 - INFO - __main__ - Step 93004: {'lr': 0.00016171568556648178, 'samples': 17856768, 'steps': 93003, 'loss/train': 0.21158529818058014} 08/31/2021 06:05:46 - INFO - __main__ - Step 93005: {'lr': 0.00016171072074747353, 'samples': 17856960, 'steps': 93004, 'loss/train': 1.509198546409607} 08/31/2021 06:05:46 - INFO - __main__ - Step 93006: {'lr': 0.00016170575596824704, 'samples': 17857152, 'steps': 93005, 'loss/train': 1.0268524885177612} 08/31/2021 06:05:46 - INFO - __main__ - Step 93007: {'lr': 0.00016170079122880462, 'samples': 17857344, 'steps': 93006, 'loss/train': 1.13542902469635} 08/31/2021 06:05:47 - INFO - __main__ - Step 93008: {'lr': 0.00016169582652914843, 'samples': 17857536, 'steps': 93007, 'loss/train': 1.2157539129257202} 08/31/2021 06:05:48 - INFO - __main__ - Step 93009: {'lr': 0.00016169086186928076, 'samples': 17857728, 'steps': 93008, 'loss/train': 0.9065699577331543} 08/31/2021 06:05:49 - INFO - __main__ - Step 93010: {'lr': 0.0001616858972492038, 'samples': 17857920, 'steps': 93009, 'loss/train': 0.6244767308235168} 08/31/2021 06:05:49 - INFO - __main__ - Step 93011: {'lr': 0.00016168093266891983, 'samples': 17858112, 'steps': 93010, 'loss/train': 1.7111619710922241} 08/31/2021 06:05:50 - INFO - __main__ - Step 93012: {'lr': 0.00016167596812843106, 'samples': 17858304, 'steps': 93011, 'loss/train': 1.5167137384414673} 08/31/2021 06:05:50 - INFO - __main__ - Step 93013: {'lr': 0.00016167100362773974, 'samples': 17858496, 'steps': 93012, 'loss/train': 1.0837664604187012} 08/31/2021 06:05:52 - INFO - __main__ - Step 93014: {'lr': 0.0001616660391668481, 'samples': 17858688, 'steps': 93013, 'loss/train': 0.9968677759170532} 08/31/2021 06:05:52 - INFO - __main__ - Step 93015: {'lr': 0.0001616610747457584, 'samples': 17858880, 'steps': 93014, 'loss/train': 1.2228823900222778} 08/31/2021 06:05:52 - INFO - __main__ - Step 93016: {'lr': 0.00016165611036447292, 'samples': 17859072, 'steps': 93015, 'loss/train': 1.1245331764221191} 08/31/2021 06:05:53 - INFO - __main__ - Step 93017: {'lr': 0.00016165114602299373, 'samples': 17859264, 'steps': 93016, 'loss/train': 0.04775197431445122} 08/31/2021 06:05:53 - INFO - __main__ - Step 93018: {'lr': 0.00016164618172132323, 'samples': 17859456, 'steps': 93017, 'loss/train': 0.6913101673126221} 08/31/2021 06:05:55 - INFO - __main__ - Step 93019: {'lr': 0.00016164121745946354, 'samples': 17859648, 'steps': 93018, 'loss/train': 1.041459083557129} 08/31/2021 06:05:55 - INFO - __main__ - Step 93020: {'lr': 0.00016163625323741698, 'samples': 17859840, 'steps': 93019, 'loss/train': 1.4879261255264282} 08/31/2021 06:05:55 - INFO - __main__ - Step 93021: {'lr': 0.00016163128905518576, 'samples': 17860032, 'steps': 93020, 'loss/train': 1.1907708644866943} 08/31/2021 06:05:56 - INFO - __main__ - Step 93022: {'lr': 0.0001616263249127721, 'samples': 17860224, 'steps': 93021, 'loss/train': 1.6164790391921997} 08/31/2021 06:05:56 - INFO - __main__ - Step 93023: {'lr': 0.00016162136081017826, 'samples': 17860416, 'steps': 93022, 'loss/train': 1.1398261785507202} 08/31/2021 06:05:57 - INFO - __main__ - Step 93024: {'lr': 0.00016161639674740647, 'samples': 17860608, 'steps': 93023, 'loss/train': 0.9626582860946655} 08/31/2021 06:05:58 - INFO - __main__ - Step 93025: {'lr': 0.000161611432724459, 'samples': 17860800, 'steps': 93024, 'loss/train': 0.8099372982978821} 08/31/2021 06:05:59 - INFO - __main__ - Step 93026: {'lr': 0.000161606468741338, 'samples': 17860992, 'steps': 93025, 'loss/train': 1.2152094841003418} 08/31/2021 06:05:59 - INFO - __main__ - Step 93027: {'lr': 0.0001616015047980458, 'samples': 17861184, 'steps': 93026, 'loss/train': 1.2539305686950684} 08/31/2021 06:05:59 - INFO - __main__ - Step 93028: {'lr': 0.0001615965408945846, 'samples': 17861376, 'steps': 93027, 'loss/train': 0.7527851462364197} 08/31/2021 06:06:00 - INFO - __main__ - Step 93029: {'lr': 0.00016159157703095673, 'samples': 17861568, 'steps': 93028, 'loss/train': 0.948046863079071} 08/31/2021 06:06:01 - INFO - __main__ - Step 93030: {'lr': 0.0001615866132071642, 'samples': 17861760, 'steps': 93029, 'loss/train': 1.1524717807769775} 08/31/2021 06:06:02 - INFO - __main__ - Step 93031: {'lr': 0.0001615816494232094, 'samples': 17861952, 'steps': 93030, 'loss/train': 2.0586025714874268} 08/31/2021 06:06:02 - INFO - __main__ - Step 93032: {'lr': 0.00016157668567909456, 'samples': 17862144, 'steps': 93031, 'loss/train': 0.9216139316558838} 08/31/2021 06:06:02 - INFO - __main__ - Step 93033: {'lr': 0.0001615717219748219, 'samples': 17862336, 'steps': 93032, 'loss/train': 1.6198118925094604} 08/31/2021 06:06:03 - INFO - __main__ - Step 93034: {'lr': 0.00016156675831039362, 'samples': 17862528, 'steps': 93033, 'loss/train': 1.2900993824005127} 08/31/2021 06:06:04 - INFO - __main__ - Step 93035: {'lr': 0.000161561794685812, 'samples': 17862720, 'steps': 93034, 'loss/train': 0.9328334331512451} 08/31/2021 06:06:05 - INFO - __main__ - Step 93036: {'lr': 0.0001615568311010793, 'samples': 17862912, 'steps': 93035, 'loss/train': 1.0306307077407837} 08/31/2021 06:06:05 - INFO - __main__ - Step 93037: {'lr': 0.0001615518675561977, 'samples': 17863104, 'steps': 93036, 'loss/train': 1.2633910179138184} 08/31/2021 06:06:05 - INFO - __main__ - Step 93038: {'lr': 0.0001615469040511695, 'samples': 17863296, 'steps': 93037, 'loss/train': 1.1988104581832886} 08/31/2021 06:06:06 - INFO - __main__ - Step 93039: {'lr': 0.00016154194058599686, 'samples': 17863488, 'steps': 93038, 'loss/train': 1.278565764427185} 08/31/2021 06:06:08 - INFO - __main__ - Step 93040: {'lr': 0.00016153697716068212, 'samples': 17863680, 'steps': 93039, 'loss/train': 1.5025850534439087} 08/31/2021 06:06:09 - INFO - __main__ - Step 93041: {'lr': 0.0001615320137752274, 'samples': 17863872, 'steps': 93040, 'loss/train': 1.0538033246994019} 08/31/2021 06:06:09 - INFO - __main__ - Step 93042: {'lr': 0.00016152705042963498, 'samples': 17864064, 'steps': 93041, 'loss/train': 1.3143070936203003} 08/31/2021 06:06:09 - INFO - __main__ - Step 93043: {'lr': 0.00016152208712390723, 'samples': 17864256, 'steps': 93042, 'loss/train': 0.9754204750061035} 08/31/2021 06:06:10 - INFO - __main__ - Step 93044: {'lr': 0.00016151712385804615, 'samples': 17864448, 'steps': 93043, 'loss/train': 0.0795416310429573} 08/31/2021 06:06:10 - INFO - __main__ - Step 93045: {'lr': 0.0001615121606320541, 'samples': 17864640, 'steps': 93044, 'loss/train': 0.050294939428567886} 08/31/2021 06:06:12 - INFO - __main__ - Step 93046: {'lr': 0.0001615071974459333, 'samples': 17864832, 'steps': 93045, 'loss/train': 1.822937250137329} 08/31/2021 06:06:12 - INFO - __main__ - Step 93047: {'lr': 0.00016150223429968596, 'samples': 17865024, 'steps': 93046, 'loss/train': 0.24479609727859497} 08/31/2021 06:06:12 - INFO - __main__ - Step 93048: {'lr': 0.00016149727119331442, 'samples': 17865216, 'steps': 93047, 'loss/train': 0.20460468530654907} 08/31/2021 06:06:13 - INFO - __main__ - Step 93049: {'lr': 0.0001614923081268208, 'samples': 17865408, 'steps': 93048, 'loss/train': 1.2444967031478882} 08/31/2021 06:06:13 - INFO - __main__ - Step 93050: {'lr': 0.00016148734510020737, 'samples': 17865600, 'steps': 93049, 'loss/train': 1.291780710220337} 08/31/2021 06:06:13 - INFO - __main__ - Step 93051: {'lr': 0.00016148238211347637, 'samples': 17865792, 'steps': 93050, 'loss/train': 1.1680320501327515} 08/31/2021 06:06:15 - INFO - __main__ - Step 93052: {'lr': 0.00016147741916663008, 'samples': 17865984, 'steps': 93051, 'loss/train': 1.434735655784607} 08/31/2021 06:06:15 - INFO - __main__ - Step 93053: {'lr': 0.00016147245625967066, 'samples': 17866176, 'steps': 93052, 'loss/train': 1.4902530908584595} 08/31/2021 06:06:16 - INFO - __main__ - Step 93054: {'lr': 0.00016146749339260042, 'samples': 17866368, 'steps': 93053, 'loss/train': 0.2643001973628998} 08/31/2021 06:06:16 - INFO - __main__ - Step 93055: {'lr': 0.00016146253056542153, 'samples': 17866560, 'steps': 93054, 'loss/train': 0.8279063701629639} 08/31/2021 06:06:16 - INFO - __main__ - Step 93056: {'lr': 0.0001614575677781364, 'samples': 17866752, 'steps': 93055, 'loss/train': 1.4987411499023438} 08/31/2021 06:06:18 - INFO - __main__ - Step 93057: {'lr': 0.000161452605030747, 'samples': 17866944, 'steps': 93056, 'loss/train': 1.7042427062988281} 08/31/2021 06:06:18 - INFO - __main__ - Step 93058: {'lr': 0.0001614476423232557, 'samples': 17867136, 'steps': 93057, 'loss/train': 1.3713260889053345} 08/31/2021 06:06:19 - INFO - __main__ - Step 93059: {'lr': 0.00016144267965566473, 'samples': 17867328, 'steps': 93058, 'loss/train': 1.0303062200546265} 08/31/2021 06:06:19 - INFO - __main__ - Step 93060: {'lr': 0.00016143771702797628, 'samples': 17867520, 'steps': 93059, 'loss/train': 1.1806116104125977} 08/31/2021 06:06:19 - INFO - __main__ - Step 93061: {'lr': 0.00016143275444019267, 'samples': 17867712, 'steps': 93060, 'loss/train': 1.5750504732131958} 08/31/2021 06:06:21 - INFO - __main__ - Step 93062: {'lr': 0.00016142779189231608, 'samples': 17867904, 'steps': 93061, 'loss/train': 1.062494158744812} 08/31/2021 06:06:21 - INFO - __main__ - Step 93063: {'lr': 0.00016142282938434873, 'samples': 17868096, 'steps': 93062, 'loss/train': 1.0367504358291626} 08/31/2021 06:06:22 - INFO - __main__ - Step 93064: {'lr': 0.00016141786691629292, 'samples': 17868288, 'steps': 93063, 'loss/train': 1.0963925123214722} 08/31/2021 06:06:22 - INFO - __main__ - Step 93065: {'lr': 0.00016141290448815085, 'samples': 17868480, 'steps': 93064, 'loss/train': 1.6397148370742798} 08/31/2021 06:06:22 - INFO - __main__ - Step 93066: {'lr': 0.00016140794209992476, 'samples': 17868672, 'steps': 93065, 'loss/train': 0.9970700740814209} 08/31/2021 06:06:24 - INFO - __main__ - Step 93067: {'lr': 0.00016140297975161688, 'samples': 17868864, 'steps': 93066, 'loss/train': 1.5623416900634766} 08/31/2021 06:06:24 - INFO - __main__ - Step 93068: {'lr': 0.00016139801744322947, 'samples': 17869056, 'steps': 93067, 'loss/train': 0.9748929142951965} 08/31/2021 06:06:25 - INFO - __main__ - Step 93069: {'lr': 0.00016139305517476476, 'samples': 17869248, 'steps': 93068, 'loss/train': 1.5424294471740723} 08/31/2021 06:06:25 - INFO - __main__ - Step 93070: {'lr': 0.00016138809294622498, 'samples': 17869440, 'steps': 93069, 'loss/train': 1.541935682296753} 08/31/2021 06:06:25 - INFO - __main__ - Step 93071: {'lr': 0.00016138313075761233, 'samples': 17869632, 'steps': 93070, 'loss/train': 1.313523769378662} 08/31/2021 06:06:27 - INFO - __main__ - Step 93072: {'lr': 0.00016137816860892906, 'samples': 17869824, 'steps': 93071, 'loss/train': 1.2560886144638062} 08/31/2021 06:06:27 - INFO - __main__ - Step 93073: {'lr': 0.00016137320650017742, 'samples': 17870016, 'steps': 93072, 'loss/train': 1.3192822933197021} 08/31/2021 06:06:28 - INFO - __main__ - Step 93074: {'lr': 0.00016136824443135965, 'samples': 17870208, 'steps': 93073, 'loss/train': 1.3169132471084595} 08/31/2021 06:06:28 - INFO - __main__ - Step 93075: {'lr': 0.00016136328240247796, 'samples': 17870400, 'steps': 93074, 'loss/train': 1.1428419351577759} 08/31/2021 06:06:28 - INFO - __main__ - Step 93076: {'lr': 0.00016135832041353464, 'samples': 17870592, 'steps': 93075, 'loss/train': 1.0563578605651855} 08/31/2021 06:06:29 - INFO - __main__ - Step 93077: {'lr': 0.00016135335846453186, 'samples': 17870784, 'steps': 93076, 'loss/train': 0.8225031495094299} 08/31/2021 06:06:30 - INFO - __main__ - Step 93078: {'lr': 0.0001613483965554719, 'samples': 17870976, 'steps': 93077, 'loss/train': 1.1602857112884521} 08/31/2021 06:06:31 - INFO - __main__ - Step 93079: {'lr': 0.000161343434686357, 'samples': 17871168, 'steps': 93078, 'loss/train': 0.7654369473457336} 08/31/2021 06:06:31 - INFO - __main__ - Step 93080: {'lr': 0.00016133847285718943, 'samples': 17871360, 'steps': 93079, 'loss/train': 1.190126657485962} 08/31/2021 06:06:32 - INFO - __main__ - Step 93081: {'lr': 0.0001613335110679713, 'samples': 17871552, 'steps': 93080, 'loss/train': 1.0425817966461182} 08/31/2021 06:06:32 - INFO - __main__ - Step 93082: {'lr': 0.00016132854931870494, 'samples': 17871744, 'steps': 93081, 'loss/train': 0.9379702210426331} 08/31/2021 06:06:33 - INFO - __main__ - Step 93083: {'lr': 0.00016132358760939265, 'samples': 17871936, 'steps': 93082, 'loss/train': 0.0399482436478138} 08/31/2021 06:06:34 - INFO - __main__ - Step 93084: {'lr': 0.00016131862594003649, 'samples': 17872128, 'steps': 93083, 'loss/train': 1.262861967086792} 08/31/2021 06:06:34 - INFO - __main__ - Step 93085: {'lr': 0.00016131366431063876, 'samples': 17872320, 'steps': 93084, 'loss/train': 1.8327397108078003} 08/31/2021 06:06:35 - INFO - __main__ - Step 93086: {'lr': 0.0001613087027212018, 'samples': 17872512, 'steps': 93085, 'loss/train': 1.0715147256851196} 08/31/2021 06:06:35 - INFO - __main__ - Step 93087: {'lr': 0.0001613037411717277, 'samples': 17872704, 'steps': 93086, 'loss/train': 1.123667597770691} 08/31/2021 06:06:36 - INFO - __main__ - Step 93088: {'lr': 0.0001612987796622188, 'samples': 17872896, 'steps': 93087, 'loss/train': 1.7010481357574463} 08/31/2021 06:06:37 - INFO - __main__ - Step 93089: {'lr': 0.0001612938181926773, 'samples': 17873088, 'steps': 93088, 'loss/train': 1.79029381275177} 08/31/2021 06:06:37 - INFO - __main__ - Step 93090: {'lr': 0.00016128885676310544, 'samples': 17873280, 'steps': 93089, 'loss/train': 1.3717854022979736} 08/31/2021 06:06:38 - INFO - __main__ - Step 93091: {'lr': 0.00016128389537350553, 'samples': 17873472, 'steps': 93090, 'loss/train': 0.7387319207191467} 08/31/2021 06:06:38 - INFO - __main__ - Step 93092: {'lr': 0.0001612789340238796, 'samples': 17873664, 'steps': 93091, 'loss/train': 0.6633296608924866} 08/31/2021 06:06:41 - INFO - __main__ - Step 93093: {'lr': 0.00016127397271423007, 'samples': 17873856, 'steps': 93092, 'loss/train': 0.9048203825950623} 08/31/2021 06:06:41 - INFO - __main__ - Step 93094: {'lr': 0.00016126901144455913, 'samples': 17874048, 'steps': 93093, 'loss/train': 0.8885124325752258} 08/31/2021 06:06:41 - INFO - __main__ - Step 93095: {'lr': 0.00016126405021486896, 'samples': 17874240, 'steps': 93094, 'loss/train': 0.10792814195156097} 08/31/2021 06:06:42 - INFO - __main__ - Step 93096: {'lr': 0.00016125908902516186, 'samples': 17874432, 'steps': 93095, 'loss/train': 1.4395880699157715} 08/31/2021 06:06:42 - INFO - __main__ - Step 93097: {'lr': 0.0001612541278754401, 'samples': 17874624, 'steps': 93096, 'loss/train': 1.1655805110931396} 08/31/2021 06:06:44 - INFO - __main__ - Step 93098: {'lr': 0.00016124916676570582, 'samples': 17874816, 'steps': 93097, 'loss/train': 1.0896039009094238} 08/31/2021 06:06:44 - INFO - __main__ - Step 93099: {'lr': 0.00016124420569596127, 'samples': 17875008, 'steps': 93098, 'loss/train': 1.2389230728149414} 08/31/2021 06:06:44 - INFO - __main__ - Step 93100: {'lr': 0.00016123924466620874, 'samples': 17875200, 'steps': 93099, 'loss/train': 0.05701894313097} 08/31/2021 06:06:45 - INFO - __main__ - Step 93101: {'lr': 0.00016123428367645045, 'samples': 17875392, 'steps': 93100, 'loss/train': 1.3681035041809082} 08/31/2021 06:06:45 - INFO - __main__ - Step 93102: {'lr': 0.00016122932272668862, 'samples': 17875584, 'steps': 93101, 'loss/train': 1.2401443719863892} 08/31/2021 06:06:46 - INFO - __main__ - Step 93103: {'lr': 0.00016122436181692545, 'samples': 17875776, 'steps': 93102, 'loss/train': 1.4333009719848633} 08/31/2021 06:06:47 - INFO - __main__ - Step 93104: {'lr': 0.0001612194009471632, 'samples': 17875968, 'steps': 93103, 'loss/train': 1.7125883102416992} 08/31/2021 06:06:47 - INFO - __main__ - Step 93105: {'lr': 0.00016121444011740416, 'samples': 17876160, 'steps': 93104, 'loss/train': 1.0214951038360596} 08/31/2021 06:06:48 - INFO - __main__ - Step 93106: {'lr': 0.0001612094793276505, 'samples': 17876352, 'steps': 93105, 'loss/train': 0.2063782960176468} 08/31/2021 06:06:48 - INFO - __main__ - Step 93107: {'lr': 0.00016120451857790446, 'samples': 17876544, 'steps': 93106, 'loss/train': 1.2579008340835571} 08/31/2021 06:06:49 - INFO - __main__ - Step 93108: {'lr': 0.00016119955786816833, 'samples': 17876736, 'steps': 93107, 'loss/train': 0.9162527918815613} 08/31/2021 06:06:50 - INFO - __main__ - Step 93109: {'lr': 0.00016119459719844432, 'samples': 17876928, 'steps': 93108, 'loss/train': 1.2389991283416748} 08/31/2021 06:06:50 - INFO - __main__ - Step 93110: {'lr': 0.00016118963656873466, 'samples': 17877120, 'steps': 93109, 'loss/train': 1.7172600030899048} 08/31/2021 06:06:51 - INFO - __main__ - Step 93111: {'lr': 0.00016118467597904158, 'samples': 17877312, 'steps': 93110, 'loss/train': 0.6252900958061218} 08/31/2021 06:06:51 - INFO - __main__ - Step 93112: {'lr': 0.00016117971542936732, 'samples': 17877504, 'steps': 93111, 'loss/train': 0.7561182379722595} 08/31/2021 06:06:53 - INFO - __main__ - Step 93113: {'lr': 0.00016117475491971407, 'samples': 17877696, 'steps': 93112, 'loss/train': 1.249990701675415} 08/31/2021 06:06:53 - INFO - __main__ - Step 93114: {'lr': 0.00016116979445008413, 'samples': 17877888, 'steps': 93113, 'loss/train': 0.7028875350952148} 08/31/2021 06:06:53 - INFO - __main__ - Step 93115: {'lr': 0.00016116483402047965, 'samples': 17878080, 'steps': 93114, 'loss/train': 1.2284249067306519} 08/31/2021 06:06:54 - INFO - __main__ - Step 93116: {'lr': 0.00016115987363090296, 'samples': 17878272, 'steps': 93115, 'loss/train': 0.7137949466705322} 08/31/2021 06:06:54 - INFO - __main__ - Step 93117: {'lr': 0.0001611549132813563, 'samples': 17878464, 'steps': 93116, 'loss/train': 1.6874178647994995} 08/31/2021 06:06:54 - INFO - __main__ - Step 93118: {'lr': 0.00016114995297184182, 'samples': 17878656, 'steps': 93117, 'loss/train': 1.369198203086853} 08/31/2021 06:06:56 - INFO - __main__ - Step 93119: {'lr': 0.00016114499270236177, 'samples': 17878848, 'steps': 93118, 'loss/train': 0.56089186668396} 08/31/2021 06:06:57 - INFO - __main__ - Step 93120: {'lr': 0.00016114003247291847, 'samples': 17879040, 'steps': 93119, 'loss/train': 1.5757293701171875} 08/31/2021 06:06:57 - INFO - __main__ - Step 93121: {'lr': 0.0001611350722835141, 'samples': 17879232, 'steps': 93120, 'loss/train': 0.957963764667511} 08/31/2021 06:06:57 - INFO - __main__ - Step 93122: {'lr': 0.00016113011213415084, 'samples': 17879424, 'steps': 93121, 'loss/train': 1.3949110507965088} 08/31/2021 06:06:58 - INFO - __main__ - Step 93123: {'lr': 0.00016112515202483115, 'samples': 17879616, 'steps': 93122, 'loss/train': 1.1246228218078613} 08/31/2021 06:06:59 - INFO - __main__ - Step 93124: {'lr': 0.00016112019195555695, 'samples': 17879808, 'steps': 93123, 'loss/train': 1.5655441284179688} 08/31/2021 06:07:00 - INFO - __main__ - Step 93125: {'lr': 0.00016111523192633066, 'samples': 17880000, 'steps': 93124, 'loss/train': 2.127586603164673} 08/31/2021 06:07:00 - INFO - __main__ - Step 93126: {'lr': 0.00016111027193715444, 'samples': 17880192, 'steps': 93125, 'loss/train': 0.8325426578521729} 08/31/2021 06:07:00 - INFO - __main__ - Step 93127: {'lr': 0.00016110531198803055, 'samples': 17880384, 'steps': 93126, 'loss/train': 1.1728665828704834} 08/31/2021 06:07:01 - INFO - __main__ - Step 93128: {'lr': 0.00016110035207896127, 'samples': 17880576, 'steps': 93127, 'loss/train': 0.4046177864074707} 08/31/2021 06:07:03 - INFO - __main__ - Step 93129: {'lr': 0.00016109539220994878, 'samples': 17880768, 'steps': 93128, 'loss/train': 1.1955615282058716} 08/31/2021 06:07:03 - INFO - __main__ - Step 93130: {'lr': 0.00016109043238099534, 'samples': 17880960, 'steps': 93129, 'loss/train': 1.068825602531433} 08/31/2021 06:07:03 - INFO - __main__ - Step 93131: {'lr': 0.00016108547259210317, 'samples': 17881152, 'steps': 93130, 'loss/train': 1.2426505088806152} 08/31/2021 06:07:04 - INFO - __main__ - Step 93132: {'lr': 0.00016108051284327452, 'samples': 17881344, 'steps': 93131, 'loss/train': 1.1444069147109985} 08/31/2021 06:07:04 - INFO - __main__ - Step 93133: {'lr': 0.0001610755531345116, 'samples': 17881536, 'steps': 93132, 'loss/train': 1.1870722770690918} 08/31/2021 06:07:06 - INFO - __main__ - Step 93134: {'lr': 0.0001610705934658167, 'samples': 17881728, 'steps': 93133, 'loss/train': 0.07554202526807785} 08/31/2021 06:07:06 - INFO - __main__ - Step 93135: {'lr': 0.000161065633837192, 'samples': 17881920, 'steps': 93134, 'loss/train': 0.8111391067504883} 08/31/2021 06:07:06 - INFO - __main__ - Step 93136: {'lr': 0.00016106067424863973, 'samples': 17882112, 'steps': 93135, 'loss/train': 1.2823803424835205} 08/31/2021 06:07:07 - INFO - __main__ - Step 93137: {'lr': 0.0001610557147001623, 'samples': 17882304, 'steps': 93136, 'loss/train': 1.6554665565490723} 08/31/2021 06:07:07 - INFO - __main__ - Step 93138: {'lr': 0.00016105075519176165, 'samples': 17882496, 'steps': 93137, 'loss/train': 0.8264114260673523} 08/31/2021 06:07:08 - INFO - __main__ - Step 93139: {'lr': 0.0001610457957234402, 'samples': 17882688, 'steps': 93138, 'loss/train': 1.690678358078003} 08/31/2021 06:07:09 - INFO - __main__ - Step 93140: {'lr': 0.0001610408362952001, 'samples': 17882880, 'steps': 93139, 'loss/train': 1.888933539390564} 08/31/2021 06:07:09 - INFO - __main__ - Step 93141: {'lr': 0.00016103587690704363, 'samples': 17883072, 'steps': 93140, 'loss/train': 1.1841211318969727} 08/31/2021 06:07:10 - INFO - __main__ - Step 93142: {'lr': 0.00016103091755897302, 'samples': 17883264, 'steps': 93141, 'loss/train': 1.0515516996383667} 08/31/2021 06:07:10 - INFO - __main__ - Step 93143: {'lr': 0.00016102595825099054, 'samples': 17883456, 'steps': 93142, 'loss/train': 1.4224097728729248} 08/31/2021 06:07:12 - INFO - __main__ - Step 93144: {'lr': 0.00016102099898309836, 'samples': 17883648, 'steps': 93143, 'loss/train': 1.1449319124221802} 08/31/2021 06:07:12 - INFO - __main__ - Step 93145: {'lr': 0.00016101603975529873, 'samples': 17883840, 'steps': 93144, 'loss/train': 1.2650631666183472} 08/31/2021 06:07:13 - INFO - __main__ - Step 93146: {'lr': 0.00016101108056759396, 'samples': 17884032, 'steps': 93145, 'loss/train': 0.8494479060173035} 08/31/2021 06:07:13 - INFO - __main__ - Step 93147: {'lr': 0.00016100612141998615, 'samples': 17884224, 'steps': 93146, 'loss/train': 1.7525345087051392} 08/31/2021 06:07:13 - INFO - __main__ - Step 93148: {'lr': 0.00016100116231247764, 'samples': 17884416, 'steps': 93147, 'loss/train': 0.6406578421592712} 08/31/2021 06:07:14 - INFO - __main__ - Step 93149: {'lr': 0.00016099620324507065, 'samples': 17884608, 'steps': 93148, 'loss/train': 1.4122618436813354} 08/31/2021 06:07:15 - INFO - __main__ - Step 93150: {'lr': 0.0001609912442177675, 'samples': 17884800, 'steps': 93149, 'loss/train': 1.0594204664230347} 08/31/2021 06:07:16 - INFO - __main__ - Step 93151: {'lr': 0.00016098628523057018, 'samples': 17884992, 'steps': 93150, 'loss/train': 0.17124901711940765} 08/31/2021 06:07:16 - INFO - __main__ - Step 93152: {'lr': 0.00016098132628348112, 'samples': 17885184, 'steps': 93151, 'loss/train': 2.209906816482544} 08/31/2021 06:07:16 - INFO - __main__ - Step 93153: {'lr': 0.00016097636737650244, 'samples': 17885376, 'steps': 93152, 'loss/train': 1.444352626800537} 08/31/2021 06:07:17 - INFO - __main__ - Step 93154: {'lr': 0.00016097140850963648, 'samples': 17885568, 'steps': 93153, 'loss/train': 1.297467589378357} 08/31/2021 06:07:19 - INFO - __main__ - Step 93155: {'lr': 0.00016096644968288543, 'samples': 17885760, 'steps': 93154, 'loss/train': 1.5098055601119995} 08/31/2021 06:07:19 - INFO - __main__ - Step 93156: {'lr': 0.0001609614908962515, 'samples': 17885952, 'steps': 93155, 'loss/train': 1.1250159740447998} 08/31/2021 06:07:20 - INFO - __main__ - Step 93157: {'lr': 0.00016095653214973695, 'samples': 17886144, 'steps': 93156, 'loss/train': 1.552540898323059} 08/31/2021 06:07:20 - INFO - __main__ - Step 93158: {'lr': 0.00016095157344334405, 'samples': 17886336, 'steps': 93157, 'loss/train': 2.3342432975769043} 08/31/2021 06:07:20 - INFO - __main__ - Step 93159: {'lr': 0.00016094661477707495, 'samples': 17886528, 'steps': 93158, 'loss/train': 2.318483829498291} 08/31/2021 06:07:21 - INFO - __main__ - Step 93160: {'lr': 0.00016094165615093193, 'samples': 17886720, 'steps': 93159, 'loss/train': 1.258201003074646} 08/31/2021 06:07:22 - INFO - __main__ - Step 93161: {'lr': 0.00016093669756491724, 'samples': 17886912, 'steps': 93160, 'loss/train': 1.7943108081817627} 08/31/2021 06:07:23 - INFO - __main__ - Step 93162: {'lr': 0.00016093173901903312, 'samples': 17887104, 'steps': 93161, 'loss/train': 3.463319778442383} 08/31/2021 06:07:23 - INFO - __main__ - Step 93163: {'lr': 0.00016092678051328178, 'samples': 17887296, 'steps': 93162, 'loss/train': 1.1384408473968506} 08/31/2021 06:07:24 - INFO - __main__ - Step 93164: {'lr': 0.00016092182204766552, 'samples': 17887488, 'steps': 93163, 'loss/train': 1.439444661140442} 08/31/2021 06:07:24 - INFO - __main__ - Step 93165: {'lr': 0.00016091686362218648, 'samples': 17887680, 'steps': 93164, 'loss/train': 1.1125054359436035} 08/31/2021 06:07:26 - INFO - __main__ - Step 93166: {'lr': 0.00016091190523684687, 'samples': 17887872, 'steps': 93165, 'loss/train': 1.1119623184204102} 08/31/2021 06:07:26 - INFO - __main__ - Step 93167: {'lr': 0.000160906946891649, 'samples': 17888064, 'steps': 93166, 'loss/train': 0.8277662992477417} 08/31/2021 06:07:27 - INFO - __main__ - Step 93168: {'lr': 0.00016090198858659507, 'samples': 17888256, 'steps': 93167, 'loss/train': 1.431719422340393} 08/31/2021 06:07:27 - INFO - __main__ - Step 93169: {'lr': 0.00016089703032168734, 'samples': 17888448, 'steps': 93168, 'loss/train': 0.020314853638410568} 08/31/2021 06:07:27 - INFO - __main__ - Step 93170: {'lr': 0.00016089207209692805, 'samples': 17888640, 'steps': 93169, 'loss/train': 1.8399028778076172} 08/31/2021 06:07:28 - INFO - __main__ - Step 93171: {'lr': 0.00016088711391231938, 'samples': 17888832, 'steps': 93170, 'loss/train': 0.6523105502128601} 08/31/2021 06:07:29 - INFO - __main__ - Step 93172: {'lr': 0.00016088215576786364, 'samples': 17889024, 'steps': 93171, 'loss/train': 0.9186044335365295} 08/31/2021 06:07:30 - INFO - __main__ - Step 93173: {'lr': 0.000160877197663563, 'samples': 17889216, 'steps': 93172, 'loss/train': 1.0203317403793335} 08/31/2021 06:07:30 - INFO - __main__ - Step 93174: {'lr': 0.00016087223959941973, 'samples': 17889408, 'steps': 93173, 'loss/train': 1.1679184436798096} 08/31/2021 06:07:31 - INFO - __main__ - Step 93175: {'lr': 0.00016086728157543607, 'samples': 17889600, 'steps': 93174, 'loss/train': 0.538540244102478} 08/31/2021 06:07:31 - INFO - __main__ - Step 93176: {'lr': 0.0001608623235916142, 'samples': 17889792, 'steps': 93175, 'loss/train': 1.2999283075332642} 08/31/2021 06:07:31 - INFO - __main__ - Step 93177: {'lr': 0.0001608573656479565, 'samples': 17889984, 'steps': 93176, 'loss/train': 0.04189406335353851} 08/31/2021 06:07:33 - INFO - __main__ - Step 93178: {'lr': 0.00016085240774446502, 'samples': 17890176, 'steps': 93177, 'loss/train': 0.8909314870834351} 08/31/2021 06:07:33 - INFO - __main__ - Step 93179: {'lr': 0.00016084744988114206, 'samples': 17890368, 'steps': 93178, 'loss/train': 1.4544886350631714} 08/31/2021 06:07:34 - INFO - __main__ - Step 93180: {'lr': 0.00016084249205798983, 'samples': 17890560, 'steps': 93179, 'loss/train': 1.4745303392410278} 08/31/2021 06:07:34 - INFO - __main__ - Step 93181: {'lr': 0.00016083753427501064, 'samples': 17890752, 'steps': 93180, 'loss/train': 2.472407341003418} 08/31/2021 06:07:34 - INFO - __main__ - Step 93182: {'lr': 0.00016083257653220668, 'samples': 17890944, 'steps': 93181, 'loss/train': 0.7323713898658752} 08/31/2021 06:07:36 - INFO - __main__ - Step 93183: {'lr': 0.0001608276188295802, 'samples': 17891136, 'steps': 93182, 'loss/train': 1.2988477945327759} 08/31/2021 06:07:36 - INFO - __main__ - Step 93184: {'lr': 0.00016082266116713336, 'samples': 17891328, 'steps': 93183, 'loss/train': 1.154724359512329} 08/31/2021 06:07:37 - INFO - __main__ - Step 93185: {'lr': 0.00016081770354486847, 'samples': 17891520, 'steps': 93184, 'loss/train': 1.4599448442459106} 08/31/2021 06:07:37 - INFO - __main__ - Step 93186: {'lr': 0.00016081274596278777, 'samples': 17891712, 'steps': 93185, 'loss/train': 0.5670963525772095} 08/31/2021 06:07:37 - INFO - __main__ - Step 93187: {'lr': 0.00016080778842089347, 'samples': 17891904, 'steps': 93186, 'loss/train': 1.5697968006134033} 08/31/2021 06:07:39 - INFO - __main__ - Step 93188: {'lr': 0.0001608028309191878, 'samples': 17892096, 'steps': 93187, 'loss/train': 0.9129087924957275} 08/31/2021 06:07:39 - INFO - __main__ - Step 93189: {'lr': 0.00016079787345767298, 'samples': 17892288, 'steps': 93188, 'loss/train': 1.3059004545211792} 08/31/2021 06:07:40 - INFO - __main__ - Step 93190: {'lr': 0.00016079291603635128, 'samples': 17892480, 'steps': 93189, 'loss/train': 0.6859143972396851} 08/31/2021 06:07:40 - INFO - __main__ - Step 93191: {'lr': 0.000160787958655225, 'samples': 17892672, 'steps': 93190, 'loss/train': 1.7903138399124146} 08/31/2021 06:07:40 - INFO - __main__ - Step 93192: {'lr': 0.0001607830013142962, 'samples': 17892864, 'steps': 93191, 'loss/train': 0.779217004776001} 08/31/2021 06:07:42 - INFO - __main__ - Step 93193: {'lr': 0.00016077804401356722, 'samples': 17893056, 'steps': 93192, 'loss/train': 1.0141907930374146} 08/31/2021 06:07:42 - INFO - __main__ - Step 93194: {'lr': 0.00016077308675304026, 'samples': 17893248, 'steps': 93193, 'loss/train': 1.0838087797164917} 08/31/2021 06:07:43 - INFO - __main__ - Step 93195: {'lr': 0.00016076812953271758, 'samples': 17893440, 'steps': 93194, 'loss/train': 1.0252776145935059} 08/31/2021 06:07:43 - INFO - __main__ - Step 93196: {'lr': 0.00016076317235260137, 'samples': 17893632, 'steps': 93195, 'loss/train': 1.7396749258041382} 08/31/2021 06:07:43 - INFO - __main__ - Step 93197: {'lr': 0.00016075821521269393, 'samples': 17893824, 'steps': 93196, 'loss/train': 1.1727046966552734} 08/31/2021 06:07:45 - INFO - __main__ - Step 93198: {'lr': 0.00016075325811299747, 'samples': 17894016, 'steps': 93197, 'loss/train': 0.8768677711486816} 08/31/2021 06:07:45 - INFO - __main__ - Step 93199: {'lr': 0.00016074830105351418, 'samples': 17894208, 'steps': 93198, 'loss/train': 1.4933971166610718} 08/31/2021 06:07:46 - INFO - __main__ - Step 93200: {'lr': 0.00016074334403424635, 'samples': 17894400, 'steps': 93199, 'loss/train': 0.9181717038154602} 08/31/2021 06:07:46 - INFO - __main__ - Step 93201: {'lr': 0.00016073838705519617, 'samples': 17894592, 'steps': 93200, 'loss/train': 1.3201820850372314} 08/31/2021 06:07:46 - INFO - __main__ - Step 93202: {'lr': 0.00016073343011636593, 'samples': 17894784, 'steps': 93201, 'loss/train': 0.7889215350151062} 08/31/2021 06:07:47 - INFO - __main__ - Step 93203: {'lr': 0.00016072847321775785, 'samples': 17894976, 'steps': 93202, 'loss/train': 1.7701297998428345} 08/31/2021 06:07:49 - INFO - __main__ - Step 93204: {'lr': 0.00016072351635937416, 'samples': 17895168, 'steps': 93203, 'loss/train': 0.7151265740394592} 08/31/2021 06:07:49 - INFO - __main__ - Step 93205: {'lr': 0.000160718559541217, 'samples': 17895360, 'steps': 93204, 'loss/train': 0.818177342414856} 08/31/2021 06:07:50 - INFO - __main__ - Step 93206: {'lr': 0.00016071360276328874, 'samples': 17895552, 'steps': 93205, 'loss/train': 0.3998463749885559} 08/31/2021 06:07:50 - INFO - __main__ - Step 93207: {'lr': 0.0001607086460255915, 'samples': 17895744, 'steps': 93206, 'loss/train': 0.020125234499573708} 08/31/2021 06:07:50 - INFO - __main__ - Step 93208: {'lr': 0.00016070368932812756, 'samples': 17895936, 'steps': 93207, 'loss/train': 3.9988343715667725} 08/31/2021 06:07:51 - INFO - __main__ - Step 93209: {'lr': 0.00016069873267089918, 'samples': 17896128, 'steps': 93208, 'loss/train': 0.7712111473083496} 08/31/2021 06:07:53 - INFO - __main__ - Step 93210: {'lr': 0.00016069377605390856, 'samples': 17896320, 'steps': 93209, 'loss/train': 0.8825957179069519} 08/31/2021 06:07:53 - INFO - __main__ - Step 93211: {'lr': 0.00016068881947715796, 'samples': 17896512, 'steps': 93210, 'loss/train': 0.7111662030220032} 08/31/2021 06:07:54 - INFO - __main__ - Step 93212: {'lr': 0.00016068386294064964, 'samples': 17896704, 'steps': 93211, 'loss/train': 1.2813440561294556} 08/31/2021 06:07:54 - INFO - __main__ - Step 93213: {'lr': 0.0001606789064443857, 'samples': 17896896, 'steps': 93212, 'loss/train': 0.016861889511346817} 08/31/2021 06:07:54 - INFO - __main__ - Step 93214: {'lr': 0.0001606739499883686, 'samples': 17897088, 'steps': 93213, 'loss/train': 0.33839425444602966} 08/31/2021 06:07:55 - INFO - __main__ - Step 93215: {'lr': 0.00016066899357260035, 'samples': 17897280, 'steps': 93214, 'loss/train': 0.9338580965995789} 08/31/2021 06:07:56 - INFO - __main__ - Step 93216: {'lr': 0.00016066403719708328, 'samples': 17897472, 'steps': 93215, 'loss/train': 0.8636706471443176} 08/31/2021 06:07:56 - INFO - __main__ - Step 93217: {'lr': 0.0001606590808618196, 'samples': 17897664, 'steps': 93216, 'loss/train': 1.100251317024231} 08/31/2021 06:07:57 - INFO - __main__ - Step 93218: {'lr': 0.00016065412456681163, 'samples': 17897856, 'steps': 93217, 'loss/train': 1.4664061069488525} 08/31/2021 06:07:57 - INFO - __main__ - Step 93219: {'lr': 0.0001606491683120615, 'samples': 17898048, 'steps': 93218, 'loss/train': 1.2630850076675415} 08/31/2021 06:07:58 - INFO - __main__ - Step 93220: {'lr': 0.00016064421209757143, 'samples': 17898240, 'steps': 93219, 'loss/train': 1.7419108152389526} 08/31/2021 06:07:59 - INFO - __main__ - Step 93221: {'lr': 0.0001606392559233437, 'samples': 17898432, 'steps': 93220, 'loss/train': 1.1093170642852783} 08/31/2021 06:07:59 - INFO - __main__ - Step 93222: {'lr': 0.0001606342997893806, 'samples': 17898624, 'steps': 93221, 'loss/train': 1.449924349784851} 08/31/2021 06:08:00 - INFO - __main__ - Step 93223: {'lr': 0.00016062934369568427, 'samples': 17898816, 'steps': 93222, 'loss/train': 1.7515376806259155} 08/31/2021 06:08:00 - INFO - __main__ - Step 93224: {'lr': 0.00016062438764225694, 'samples': 17899008, 'steps': 93223, 'loss/train': 1.323652744293213} 08/31/2021 06:08:01 - INFO - __main__ - Step 93225: {'lr': 0.000160619431629101, 'samples': 17899200, 'steps': 93224, 'loss/train': 1.0176022052764893} 08/31/2021 06:08:02 - INFO - __main__ - Step 93226: {'lr': 0.00016061447565621852, 'samples': 17899392, 'steps': 93225, 'loss/train': 0.14240050315856934} 08/31/2021 06:08:03 - INFO - __main__ - Step 93227: {'lr': 0.0001606095197236117, 'samples': 17899584, 'steps': 93226, 'loss/train': 0.9770433306694031} 08/31/2021 06:08:03 - INFO - __main__ - Step 93228: {'lr': 0.00016060456383128291, 'samples': 17899776, 'steps': 93227, 'loss/train': 1.0284088850021362} 08/31/2021 06:08:03 - INFO - __main__ - Step 93229: {'lr': 0.00016059960797923432, 'samples': 17899968, 'steps': 93228, 'loss/train': 0.8191267251968384} 08/31/2021 06:08:04 - INFO - __main__ - Step 93230: {'lr': 0.00016059465216746816, 'samples': 17900160, 'steps': 93229, 'loss/train': 0.26565152406692505} 08/31/2021 06:08:05 - INFO - __main__ - Step 93231: {'lr': 0.00016058969639598668, 'samples': 17900352, 'steps': 93230, 'loss/train': 1.1726280450820923} 08/31/2021 06:08:06 - INFO - __main__ - Step 93232: {'lr': 0.0001605847406647921, 'samples': 17900544, 'steps': 93231, 'loss/train': 0.9232999086380005} 08/31/2021 06:08:06 - INFO - __main__ - Step 93233: {'lr': 0.00016057978497388664, 'samples': 17900736, 'steps': 93232, 'loss/train': 1.0766656398773193} 08/31/2021 06:08:07 - INFO - __main__ - Step 93234: {'lr': 0.00016057482932327257, 'samples': 17900928, 'steps': 93233, 'loss/train': 1.1638678312301636} 08/31/2021 06:08:07 - INFO - __main__ - Step 93235: {'lr': 0.00016056987371295209, 'samples': 17901120, 'steps': 93234, 'loss/train': 1.3657294511795044} 08/31/2021 06:08:07 - INFO - __main__ - Step 93236: {'lr': 0.00016056491814292752, 'samples': 17901312, 'steps': 93235, 'loss/train': 1.0088645219802856} 08/31/2021 06:08:09 - INFO - __main__ - Step 93237: {'lr': 0.0001605599626132009, 'samples': 17901504, 'steps': 93236, 'loss/train': 1.4579949378967285} 08/31/2021 06:08:09 - INFO - __main__ - Step 93238: {'lr': 0.00016055500712377463, 'samples': 17901696, 'steps': 93237, 'loss/train': 0.4599757194519043} 08/31/2021 06:08:10 - INFO - __main__ - Step 93239: {'lr': 0.00016055005167465089, 'samples': 17901888, 'steps': 93238, 'loss/train': 0.845689058303833} 08/31/2021 06:08:10 - INFO - __main__ - Step 93240: {'lr': 0.00016054509626583192, 'samples': 17902080, 'steps': 93239, 'loss/train': 1.1532223224639893} 08/31/2021 06:08:10 - INFO - __main__ - Step 93241: {'lr': 0.00016054014089731994, 'samples': 17902272, 'steps': 93240, 'loss/train': 0.03682957962155342} 08/31/2021 06:08:12 - INFO - __main__ - Step 93242: {'lr': 0.00016053518556911718, 'samples': 17902464, 'steps': 93241, 'loss/train': 0.9523086547851562} 08/31/2021 06:08:12 - INFO - __main__ - Step 93243: {'lr': 0.00016053023028122587, 'samples': 17902656, 'steps': 93242, 'loss/train': 0.6471880674362183} 08/31/2021 06:08:13 - INFO - __main__ - Step 93244: {'lr': 0.00016052527503364835, 'samples': 17902848, 'steps': 93243, 'loss/train': 1.5446343421936035} 08/31/2021 06:08:13 - INFO - __main__ - Step 93245: {'lr': 0.00016052031982638672, 'samples': 17903040, 'steps': 93244, 'loss/train': 0.31161725521087646} 08/31/2021 06:08:14 - INFO - __main__ - Step 93246: {'lr': 0.00016051536465944323, 'samples': 17903232, 'steps': 93245, 'loss/train': 0.7565855383872986} 08/31/2021 06:08:15 - INFO - __main__ - Step 93247: {'lr': 0.00016051040953282017, 'samples': 17903424, 'steps': 93246, 'loss/train': 1.356787085533142} 08/31/2021 06:08:15 - INFO - __main__ - Step 93248: {'lr': 0.00016050545444651972, 'samples': 17903616, 'steps': 93247, 'loss/train': 0.9984726309776306} 08/31/2021 06:08:16 - INFO - __main__ - Step 93249: {'lr': 0.00016050049940054408, 'samples': 17903808, 'steps': 93248, 'loss/train': 1.6349128484725952} 08/31/2021 06:08:16 - INFO - __main__ - Step 93250: {'lr': 0.0001604955443948956, 'samples': 17904000, 'steps': 93249, 'loss/train': 0.8721703886985779} 08/31/2021 06:08:17 - INFO - __main__ - Step 93251: {'lr': 0.00016049058942957639, 'samples': 17904192, 'steps': 93250, 'loss/train': 0.8275948762893677} 08/31/2021 06:08:18 - INFO - __main__ - Step 93252: {'lr': 0.00016048563450458874, 'samples': 17904384, 'steps': 93251, 'loss/train': 0.44333669543266296} 08/31/2021 06:08:18 - INFO - __main__ - Step 93253: {'lr': 0.00016048067961993494, 'samples': 17904576, 'steps': 93252, 'loss/train': 0.4240614175796509} 08/31/2021 06:08:19 - INFO - __main__ - Step 93254: {'lr': 0.0001604757247756171, 'samples': 17904768, 'steps': 93253, 'loss/train': 1.040388822555542} 08/31/2021 06:08:19 - INFO - __main__ - Step 93255: {'lr': 0.00016047076997163757, 'samples': 17904960, 'steps': 93254, 'loss/train': 1.439876914024353} 08/31/2021 06:08:19 - INFO - __main__ - Step 93256: {'lr': 0.00016046581520799853, 'samples': 17905152, 'steps': 93255, 'loss/train': 1.1977986097335815} 08/31/2021 06:08:22 - INFO - __main__ - Step 93257: {'lr': 0.00016046086048470215, 'samples': 17905344, 'steps': 93256, 'loss/train': 0.9343193173408508} 08/31/2021 06:08:22 - INFO - __main__ - Step 93258: {'lr': 0.00016045590580175087, 'samples': 17905536, 'steps': 93257, 'loss/train': 0.4357950985431671} 08/31/2021 06:08:23 - INFO - __main__ - Step 93259: {'lr': 0.00016045095115914667, 'samples': 17905728, 'steps': 93258, 'loss/train': 1.5916929244995117} 08/31/2021 06:08:23 - INFO - __main__ - Step 93260: {'lr': 0.0001604459965568919, 'samples': 17905920, 'steps': 93259, 'loss/train': 1.0768046379089355} 08/31/2021 06:08:23 - INFO - __main__ - Step 93261: {'lr': 0.00016044104199498878, 'samples': 17906112, 'steps': 93260, 'loss/train': 1.4552686214447021} 08/31/2021 06:08:25 - INFO - __main__ - Step 93262: {'lr': 0.0001604360874734395, 'samples': 17906304, 'steps': 93261, 'loss/train': 0.02977701649069786} 08/31/2021 06:08:25 - INFO - __main__ - Step 93263: {'lr': 0.0001604311329922464, 'samples': 17906496, 'steps': 93262, 'loss/train': 0.7639877200126648} 08/31/2021 06:08:26 - INFO - __main__ - Step 93264: {'lr': 0.0001604261785514116, 'samples': 17906688, 'steps': 93263, 'loss/train': 1.2850486040115356} 08/31/2021 06:08:26 - INFO - __main__ - Step 93265: {'lr': 0.0001604212241509374, 'samples': 17906880, 'steps': 93264, 'loss/train': 0.7664339542388916} 08/31/2021 06:08:26 - INFO - __main__ - Step 93266: {'lr': 0.00016041626979082602, 'samples': 17907072, 'steps': 93265, 'loss/train': 1.2076486349105835} 08/31/2021 06:08:28 - INFO - __main__ - Step 93267: {'lr': 0.00016041131547107969, 'samples': 17907264, 'steps': 93266, 'loss/train': 1.073287010192871} 08/31/2021 06:08:28 - INFO - __main__ - Step 93268: {'lr': 0.00016040636119170066, 'samples': 17907456, 'steps': 93267, 'loss/train': 1.3488261699676514} 08/31/2021 06:08:29 - INFO - __main__ - Step 93269: {'lr': 0.0001604014069526911, 'samples': 17907648, 'steps': 93268, 'loss/train': 0.427816778421402} 08/31/2021 06:08:29 - INFO - __main__ - Step 93270: {'lr': 0.00016039645275405328, 'samples': 17907840, 'steps': 93269, 'loss/train': 1.0737276077270508} 08/31/2021 06:08:29 - INFO - __main__ - Step 93271: {'lr': 0.00016039149859578956, 'samples': 17908032, 'steps': 93270, 'loss/train': 1.1113877296447754} 08/31/2021 06:08:30 - INFO - __main__ - Step 93272: {'lr': 0.00016038654447790197, 'samples': 17908224, 'steps': 93271, 'loss/train': 1.1380621194839478} 08/31/2021 06:08:32 - INFO - __main__ - Step 93273: {'lr': 0.00016038159040039277, 'samples': 17908416, 'steps': 93272, 'loss/train': 1.222652792930603} 08/31/2021 06:08:32 - INFO - __main__ - Step 93274: {'lr': 0.00016037663636326427, 'samples': 17908608, 'steps': 93273, 'loss/train': 0.7951551675796509} 08/31/2021 06:08:32 - INFO - __main__ - Step 93275: {'lr': 0.00016037168236651868, 'samples': 17908800, 'steps': 93274, 'loss/train': 0.8461892008781433} 08/31/2021 06:08:33 - INFO - __main__ - Step 93276: {'lr': 0.0001603667284101582, 'samples': 17908992, 'steps': 93275, 'loss/train': 1.0271275043487549} 08/31/2021 06:08:33 - INFO - __main__ - Step 93277: {'lr': 0.0001603617744941851, 'samples': 17909184, 'steps': 93276, 'loss/train': 1.0089987516403198} 08/31/2021 06:08:35 - INFO - __main__ - Step 93278: {'lr': 0.00016035682061860162, 'samples': 17909376, 'steps': 93277, 'loss/train': 0.038766488432884216} 08/31/2021 06:08:35 - INFO - __main__ - Step 93279: {'lr': 0.00016035186678340995, 'samples': 17909568, 'steps': 93278, 'loss/train': 1.482082486152649} 08/31/2021 06:08:35 - INFO - __main__ - Step 93280: {'lr': 0.00016034691298861238, 'samples': 17909760, 'steps': 93279, 'loss/train': 1.1211062669754028} 08/31/2021 06:08:36 - INFO - __main__ - Step 93281: {'lr': 0.00016034195923421104, 'samples': 17909952, 'steps': 93280, 'loss/train': 1.027567982673645} 08/31/2021 06:08:36 - INFO - __main__ - Step 93282: {'lr': 0.0001603370055202083, 'samples': 17910144, 'steps': 93281, 'loss/train': 0.5273157954216003} 08/31/2021 06:08:38 - INFO - __main__ - Step 93283: {'lr': 0.00016033205184660625, 'samples': 17910336, 'steps': 93282, 'loss/train': 0.6895043849945068} 08/31/2021 06:08:38 - INFO - __main__ - Step 93284: {'lr': 0.00016032709821340728, 'samples': 17910528, 'steps': 93283, 'loss/train': 1.0939193964004517} 08/31/2021 06:08:38 - INFO - __main__ - Step 93285: {'lr': 0.00016032214462061357, 'samples': 17910720, 'steps': 93284, 'loss/train': 1.2066148519515991} 08/31/2021 06:08:39 - INFO - __main__ - Step 93286: {'lr': 0.00016031719106822726, 'samples': 17910912, 'steps': 93285, 'loss/train': 0.2085082083940506} 08/31/2021 06:08:39 - INFO - __main__ - Step 93287: {'lr': 0.00016031223755625062, 'samples': 17911104, 'steps': 93286, 'loss/train': 1.0467171669006348} 08/31/2021 06:08:41 - INFO - __main__ - Step 93288: {'lr': 0.0001603072840846859, 'samples': 17911296, 'steps': 93287, 'loss/train': 1.155067801475525} 08/31/2021 06:08:41 - INFO - __main__ - Step 93289: {'lr': 0.00016030233065353534, 'samples': 17911488, 'steps': 93288, 'loss/train': 1.221687912940979} 08/31/2021 06:08:42 - INFO - __main__ - Step 93290: {'lr': 0.00016029737726280113, 'samples': 17911680, 'steps': 93289, 'loss/train': 0.919583797454834} 08/31/2021 06:08:42 - INFO - __main__ - Step 93291: {'lr': 0.0001602924239124856, 'samples': 17911872, 'steps': 93290, 'loss/train': 4.046106815338135} 08/31/2021 06:08:42 - INFO - __main__ - Step 93292: {'lr': 0.0001602874706025909, 'samples': 17912064, 'steps': 93291, 'loss/train': 0.31199702620506287} 08/31/2021 06:08:43 - INFO - __main__ - Step 93293: {'lr': 0.00016028251733311928, 'samples': 17912256, 'steps': 93292, 'loss/train': 1.1117918491363525} 08/31/2021 06:08:44 - INFO - __main__ - Step 93294: {'lr': 0.00016027756410407293, 'samples': 17912448, 'steps': 93293, 'loss/train': 1.1437782049179077} 08/31/2021 06:08:45 - INFO - __main__ - Step 93295: {'lr': 0.00016027261091545417, 'samples': 17912640, 'steps': 93294, 'loss/train': 0.3253858983516693} 08/31/2021 06:08:45 - INFO - __main__ - Step 93296: {'lr': 0.00016026765776726515, 'samples': 17912832, 'steps': 93295, 'loss/train': 0.5805505514144897} 08/31/2021 06:08:45 - INFO - __main__ - Step 93297: {'lr': 0.00016026270465950817, 'samples': 17913024, 'steps': 93296, 'loss/train': 1.0109457969665527} 08/31/2021 06:08:46 - INFO - __main__ - Step 93298: {'lr': 0.00016025775159218554, 'samples': 17913216, 'steps': 93297, 'loss/train': 0.23156042397022247} 08/31/2021 06:08:47 - INFO - __main__ - Step 93299: {'lr': 0.00016025279856529928, 'samples': 17913408, 'steps': 93298, 'loss/train': 1.2674603462219238} 08/31/2021 06:08:48 - INFO - __main__ - Step 93300: {'lr': 0.0001602478455788517, 'samples': 17913600, 'steps': 93299, 'loss/train': 1.7154290676116943} 08/31/2021 06:08:48 - INFO - __main__ - Step 93301: {'lr': 0.00016024289263284508, 'samples': 17913792, 'steps': 93300, 'loss/train': 0.6763744354248047} 08/31/2021 06:08:49 - INFO - __main__ - Step 93302: {'lr': 0.00016023793972728162, 'samples': 17913984, 'steps': 93301, 'loss/train': 1.4665664434432983} 08/31/2021 06:08:49 - INFO - __main__ - Step 93303: {'lr': 0.00016023298686216353, 'samples': 17914176, 'steps': 93302, 'loss/train': 1.4788979291915894} 08/31/2021 06:08:51 - INFO - __main__ - Step 93304: {'lr': 0.0001602280340374931, 'samples': 17914368, 'steps': 93303, 'loss/train': 1.772605299949646} 08/31/2021 06:08:51 - INFO - __main__ - Step 93305: {'lr': 0.00016022308125327253, 'samples': 17914560, 'steps': 93304, 'loss/train': 0.9356018304824829} 08/31/2021 06:08:51 - INFO - __main__ - Step 93306: {'lr': 0.00016021812850950407, 'samples': 17914752, 'steps': 93305, 'loss/train': 0.16870534420013428} 08/31/2021 06:08:52 - INFO - __main__ - Step 93307: {'lr': 0.00016021317580618987, 'samples': 17914944, 'steps': 93306, 'loss/train': 1.2883130311965942} 08/31/2021 06:08:52 - INFO - __main__ - Step 93308: {'lr': 0.0001602082231433323, 'samples': 17915136, 'steps': 93307, 'loss/train': 0.8735002875328064} 08/31/2021 06:08:54 - INFO - __main__ - Step 93309: {'lr': 0.0001602032705209335, 'samples': 17915328, 'steps': 93308, 'loss/train': 1.4966349601745605} 08/31/2021 06:08:54 - INFO - __main__ - Step 93310: {'lr': 0.0001601983179389957, 'samples': 17915520, 'steps': 93309, 'loss/train': 1.0811928510665894} 08/31/2021 06:08:54 - INFO - __main__ - Step 93311: {'lr': 0.00016019336539752118, 'samples': 17915712, 'steps': 93310, 'loss/train': 1.1003485918045044} 08/31/2021 06:08:55 - INFO - __main__ - Step 93312: {'lr': 0.00016018841289651222, 'samples': 17915904, 'steps': 93311, 'loss/train': 2.1776232719421387} 08/31/2021 06:08:55 - INFO - __main__ - Step 93313: {'lr': 0.0001601834604359709, 'samples': 17916096, 'steps': 93312, 'loss/train': 1.3277381658554077} 08/31/2021 06:08:57 - INFO - __main__ - Step 93314: {'lr': 0.0001601785080158995, 'samples': 17916288, 'steps': 93313, 'loss/train': 0.19101250171661377} 08/31/2021 06:08:58 - INFO - __main__ - Step 93315: {'lr': 0.00016017355563630032, 'samples': 17916480, 'steps': 93314, 'loss/train': 1.4994442462921143} 08/31/2021 06:08:58 - INFO - __main__ - Step 93316: {'lr': 0.0001601686032971755, 'samples': 17916672, 'steps': 93315, 'loss/train': 1.7865779399871826} 08/31/2021 06:08:58 - INFO - __main__ - Step 93317: {'lr': 0.00016016365099852736, 'samples': 17916864, 'steps': 93316, 'loss/train': 1.496598720550537} 08/31/2021 06:08:59 - INFO - __main__ - Step 93318: {'lr': 0.00016015869874035803, 'samples': 17917056, 'steps': 93317, 'loss/train': 1.156552791595459} 08/31/2021 06:08:59 - INFO - __main__ - Step 93319: {'lr': 0.0001601537465226699, 'samples': 17917248, 'steps': 93318, 'loss/train': 1.5489426851272583} 08/31/2021 06:09:01 - INFO - __main__ - Step 93320: {'lr': 0.00016014879434546504, 'samples': 17917440, 'steps': 93319, 'loss/train': 1.318467378616333} 08/31/2021 06:09:01 - INFO - __main__ - Step 93321: {'lr': 0.00016014384220874577, 'samples': 17917632, 'steps': 93320, 'loss/train': 1.7163348197937012} 08/31/2021 06:09:01 - INFO - __main__ - Step 93322: {'lr': 0.00016013889011251426, 'samples': 17917824, 'steps': 93321, 'loss/train': 0.958063006401062} 08/31/2021 06:09:02 - INFO - __main__ - Step 93323: {'lr': 0.00016013393805677285, 'samples': 17918016, 'steps': 93322, 'loss/train': 1.189638614654541} 08/31/2021 06:09:02 - INFO - __main__ - Step 93324: {'lr': 0.00016012898604152366, 'samples': 17918208, 'steps': 93323, 'loss/train': 1.137522578239441} 08/31/2021 06:09:04 - INFO - __main__ - Step 93325: {'lr': 0.00016012403406676903, 'samples': 17918400, 'steps': 93324, 'loss/train': 1.2215720415115356} 08/31/2021 06:09:04 - INFO - __main__ - Step 93326: {'lr': 0.00016011908213251107, 'samples': 17918592, 'steps': 93325, 'loss/train': 1.5583388805389404} 08/31/2021 06:09:05 - INFO - __main__ - Step 93327: {'lr': 0.00016011413023875204, 'samples': 17918784, 'steps': 93326, 'loss/train': 1.5619652271270752} 08/31/2021 06:09:05 - INFO - __main__ - Step 93328: {'lr': 0.00016010917838549422, 'samples': 17918976, 'steps': 93327, 'loss/train': 0.6313527226448059} 08/31/2021 06:09:05 - INFO - __main__ - Step 93329: {'lr': 0.0001601042265727398, 'samples': 17919168, 'steps': 93328, 'loss/train': 1.2574536800384521} 08/31/2021 06:09:07 - INFO - __main__ - Step 93330: {'lr': 0.000160099274800491, 'samples': 17919360, 'steps': 93329, 'loss/train': 1.1950653791427612} 08/31/2021 06:09:07 - INFO - __main__ - Step 93331: {'lr': 0.00016009432306875014, 'samples': 17919552, 'steps': 93330, 'loss/train': 2.299329996109009} 08/31/2021 06:09:08 - INFO - __main__ - Step 93332: {'lr': 0.00016008937137751935, 'samples': 17919744, 'steps': 93331, 'loss/train': 1.35124933719635} 08/31/2021 06:09:08 - INFO - __main__ - Step 93333: {'lr': 0.00016008441972680093, 'samples': 17919936, 'steps': 93332, 'loss/train': 0.16701790690422058} 08/31/2021 06:09:08 - INFO - __main__ - Step 93334: {'lr': 0.00016007946811659704, 'samples': 17920128, 'steps': 93333, 'loss/train': 0.8913236260414124} 08/31/2021 06:09:10 - INFO - __main__ - Step 93335: {'lr': 0.00016007451654691, 'samples': 17920320, 'steps': 93334, 'loss/train': 0.33418941497802734} 08/31/2021 06:09:11 - INFO - __main__ - Step 93336: {'lr': 0.00016006956501774195, 'samples': 17920512, 'steps': 93335, 'loss/train': 0.9415009021759033} 08/31/2021 06:09:11 - INFO - __main__ - Step 93337: {'lr': 0.00016006461352909522, 'samples': 17920704, 'steps': 93336, 'loss/train': 1.153184175491333} 08/31/2021 06:09:11 - INFO - __main__ - Step 93338: {'lr': 0.000160059662080972, 'samples': 17920896, 'steps': 93337, 'loss/train': 0.728762686252594} 08/31/2021 06:09:12 - INFO - __main__ - Step 93339: {'lr': 0.00016005471067337453, 'samples': 17921088, 'steps': 93338, 'loss/train': 1.248671293258667} 08/31/2021 06:09:13 - INFO - __main__ - Step 93340: {'lr': 0.00016004975930630495, 'samples': 17921280, 'steps': 93339, 'loss/train': 1.6965041160583496} 08/31/2021 06:09:14 - INFO - __main__ - Step 93341: {'lr': 0.00016004480797976556, 'samples': 17921472, 'steps': 93340, 'loss/train': 1.6827086210250854} 08/31/2021 06:09:14 - INFO - __main__ - Step 93342: {'lr': 0.00016003985669375858, 'samples': 17921664, 'steps': 93341, 'loss/train': 0.791117787361145} 08/31/2021 06:09:14 - INFO - __main__ - Step 93343: {'lr': 0.00016003490544828631, 'samples': 17921856, 'steps': 93342, 'loss/train': 1.4510067701339722} 08/31/2021 06:09:15 - INFO - __main__ - Step 93344: {'lr': 0.00016002995424335088, 'samples': 17922048, 'steps': 93343, 'loss/train': 0.9891752600669861} 08/31/2021 06:09:16 - INFO - __main__ - Step 93345: {'lr': 0.00016002500307895457, 'samples': 17922240, 'steps': 93344, 'loss/train': 1.3374629020690918} 08/31/2021 06:09:17 - INFO - __main__ - Step 93346: {'lr': 0.0001600200519550996, 'samples': 17922432, 'steps': 93345, 'loss/train': 1.0304481983184814} 08/31/2021 06:09:17 - INFO - __main__ - Step 93347: {'lr': 0.0001600151008717882, 'samples': 17922624, 'steps': 93346, 'loss/train': 1.0317859649658203} 08/31/2021 06:09:18 - INFO - __main__ - Step 93348: {'lr': 0.00016001014982902268, 'samples': 17922816, 'steps': 93347, 'loss/train': 0.65293288230896} 08/31/2021 06:09:18 - INFO - __main__ - Step 93349: {'lr': 0.00016000519882680513, 'samples': 17923008, 'steps': 93348, 'loss/train': 0.9344556927680969} 08/31/2021 06:09:20 - INFO - __main__ - Step 93350: {'lr': 0.00016000024786513782, 'samples': 17923200, 'steps': 93349, 'loss/train': 0.05456987023353577} 08/31/2021 06:09:20 - INFO - __main__ - Step 93351: {'lr': 0.00015999529694402307, 'samples': 17923392, 'steps': 93350, 'loss/train': 1.5344569683074951} 08/31/2021 06:09:20 - INFO - __main__ - Step 93352: {'lr': 0.0001599903460634631, 'samples': 17923584, 'steps': 93351, 'loss/train': 1.1996079683303833} 08/31/2021 06:09:21 - INFO - __main__ - Step 93353: {'lr': 0.00015998539522346, 'samples': 17923776, 'steps': 93352, 'loss/train': 1.3207124471664429} 08/31/2021 06:09:21 - INFO - __main__ - Step 93354: {'lr': 0.0001599804444240161, 'samples': 17923968, 'steps': 93353, 'loss/train': 0.060811493545770645} 08/31/2021 06:09:21 - INFO - __main__ - Step 93355: {'lr': 0.00015997549366513362, 'samples': 17924160, 'steps': 93354, 'loss/train': 1.4588570594787598} 08/31/2021 06:09:23 - INFO - __main__ - Step 93356: {'lr': 0.0001599705429468148, 'samples': 17924352, 'steps': 93355, 'loss/train': 1.2932289838790894} 08/31/2021 06:09:23 - INFO - __main__ - Step 93357: {'lr': 0.00015996559226906187, 'samples': 17924544, 'steps': 93356, 'loss/train': 0.9721563458442688} 08/31/2021 06:09:24 - INFO - __main__ - Step 93358: {'lr': 0.00015996064163187706, 'samples': 17924736, 'steps': 93357, 'loss/train': 0.8246678709983826} 08/31/2021 06:09:24 - INFO - __main__ - Step 93359: {'lr': 0.00015995569103526263, 'samples': 17924928, 'steps': 93358, 'loss/train': 1.5838502645492554} 08/31/2021 06:09:24 - INFO - __main__ - Step 93360: {'lr': 0.00015995074047922073, 'samples': 17925120, 'steps': 93359, 'loss/train': 1.4113792181015015} 08/31/2021 06:09:26 - INFO - __main__ - Step 93361: {'lr': 0.00015994578996375363, 'samples': 17925312, 'steps': 93360, 'loss/train': 1.161382794380188} 08/31/2021 06:09:26 - INFO - __main__ - Step 93362: {'lr': 0.00015994083948886356, 'samples': 17925504, 'steps': 93361, 'loss/train': 0.9909154176712036} 08/31/2021 06:09:27 - INFO - __main__ - Step 93363: {'lr': 0.00015993588905455282, 'samples': 17925696, 'steps': 93362, 'loss/train': 1.2127835750579834} 08/31/2021 06:09:27 - INFO - __main__ - Step 93364: {'lr': 0.00015993093866082354, 'samples': 17925888, 'steps': 93363, 'loss/train': 0.8228818774223328} 08/31/2021 06:09:28 - INFO - __main__ - Step 93365: {'lr': 0.00015992598830767802, 'samples': 17926080, 'steps': 93364, 'loss/train': 1.0436739921569824} 08/31/2021 06:09:30 - INFO - __main__ - Step 93366: {'lr': 0.00015992103799511843, 'samples': 17926272, 'steps': 93365, 'loss/train': 0.8716700077056885} 08/31/2021 06:09:30 - INFO - __main__ - Step 93367: {'lr': 0.000159916087723147, 'samples': 17926464, 'steps': 93366, 'loss/train': 1.3435815572738647} 08/31/2021 06:09:31 - INFO - __main__ - Step 93368: {'lr': 0.000159911137491766, 'samples': 17926656, 'steps': 93367, 'loss/train': 1.2039611339569092} 08/31/2021 06:09:31 - INFO - __main__ - Step 93369: {'lr': 0.00015990618730097768, 'samples': 17926848, 'steps': 93368, 'loss/train': 1.1304466724395752} 08/31/2021 06:09:31 - INFO - __main__ - Step 93370: {'lr': 0.00015990123715078428, 'samples': 17927040, 'steps': 93369, 'loss/train': 0.5783268809318542} 08/31/2021 06:09:32 - INFO - __main__ - Step 93371: {'lr': 0.00015989628704118794, 'samples': 17927232, 'steps': 93370, 'loss/train': 0.44106990098953247} 08/31/2021 06:09:34 - INFO - __main__ - Step 93372: {'lr': 0.00015989133697219093, 'samples': 17927424, 'steps': 93371, 'loss/train': 0.0381106436252594} 08/31/2021 06:09:34 - INFO - __main__ - Step 93373: {'lr': 0.00015988638694379553, 'samples': 17927616, 'steps': 93372, 'loss/train': 1.202406644821167} 08/31/2021 06:09:34 - INFO - __main__ - Step 93374: {'lr': 0.0001598814369560039, 'samples': 17927808, 'steps': 93373, 'loss/train': 1.0153695344924927} 08/31/2021 06:09:35 - INFO - __main__ - Step 93375: {'lr': 0.0001598764870088183, 'samples': 17928000, 'steps': 93374, 'loss/train': 0.8992131352424622} 08/31/2021 06:09:35 - INFO - __main__ - Step 93376: {'lr': 0.000159871537102241, 'samples': 17928192, 'steps': 93375, 'loss/train': 1.4639285802841187} 08/31/2021 06:09:36 - INFO - __main__ - Step 93377: {'lr': 0.00015986658723627417, 'samples': 17928384, 'steps': 93376, 'loss/train': 0.8674905300140381} 08/31/2021 06:09:37 - INFO - __main__ - Step 93378: {'lr': 0.00015986163741092005, 'samples': 17928576, 'steps': 93377, 'loss/train': 0.05189719423651695} 08/31/2021 06:09:38 - INFO - __main__ - Step 93379: {'lr': 0.00015985668762618095, 'samples': 17928768, 'steps': 93378, 'loss/train': 1.2329859733581543} 08/31/2021 06:09:38 - INFO - __main__ - Step 93380: {'lr': 0.00015985173788205897, 'samples': 17928960, 'steps': 93379, 'loss/train': 0.5389224886894226} 08/31/2021 06:09:38 - INFO - __main__ - Step 93381: {'lr': 0.0001598467881785565, 'samples': 17929152, 'steps': 93380, 'loss/train': 1.2585961818695068} 08/31/2021 06:09:39 - INFO - __main__ - Step 93382: {'lr': 0.00015984183851567557, 'samples': 17929344, 'steps': 93381, 'loss/train': 0.7823354005813599} 08/31/2021 06:09:40 - INFO - __main__ - Step 93383: {'lr': 0.00015983688889341857, 'samples': 17929536, 'steps': 93382, 'loss/train': 1.1803715229034424} 08/31/2021 06:09:41 - INFO - __main__ - Step 93384: {'lr': 0.00015983193931178762, 'samples': 17929728, 'steps': 93383, 'loss/train': 1.29645574092865} 08/31/2021 06:09:41 - INFO - __main__ - Step 93385: {'lr': 0.0001598269897707851, 'samples': 17929920, 'steps': 93384, 'loss/train': 1.347898244857788} 08/31/2021 06:09:41 - INFO - __main__ - Step 93386: {'lr': 0.00015982204027041306, 'samples': 17930112, 'steps': 93385, 'loss/train': 1.7769957780838013} 08/31/2021 06:09:42 - INFO - __main__ - Step 93387: {'lr': 0.00015981709081067382, 'samples': 17930304, 'steps': 93386, 'loss/train': 1.1856485605239868} 08/31/2021 06:09:44 - INFO - __main__ - Step 93388: {'lr': 0.00015981214139156963, 'samples': 17930496, 'steps': 93387, 'loss/train': 0.7612290978431702} 08/31/2021 06:09:44 - INFO - __main__ - Step 93389: {'lr': 0.00015980719201310272, 'samples': 17930688, 'steps': 93388, 'loss/train': 1.637911319732666} 08/31/2021 06:09:44 - INFO - __main__ - Step 93390: {'lr': 0.00015980224267527526, 'samples': 17930880, 'steps': 93389, 'loss/train': 5.671928405761719} 08/31/2021 06:09:45 - INFO - __main__ - Step 93391: {'lr': 0.00015979729337808955, 'samples': 17931072, 'steps': 93390, 'loss/train': 1.014951229095459} 08/31/2021 06:09:45 - INFO - __main__ - Step 93392: {'lr': 0.00015979234412154787, 'samples': 17931264, 'steps': 93391, 'loss/train': 1.0222575664520264} 08/31/2021 06:09:45 - INFO - __main__ - Step 93393: {'lr': 0.00015978739490565225, 'samples': 17931456, 'steps': 93392, 'loss/train': 0.48685601353645325} 08/31/2021 06:09:47 - INFO - __main__ - Step 93394: {'lr': 0.00015978244573040506, 'samples': 17931648, 'steps': 93393, 'loss/train': 1.1222889423370361} 08/31/2021 06:09:47 - INFO - __main__ - Step 93395: {'lr': 0.0001597774965958085, 'samples': 17931840, 'steps': 93394, 'loss/train': 1.7011487483978271} 08/31/2021 06:09:48 - INFO - __main__ - Step 93396: {'lr': 0.0001597725475018648, 'samples': 17932032, 'steps': 93395, 'loss/train': 1.3702702522277832} 08/31/2021 06:09:48 - INFO - __main__ - Step 93397: {'lr': 0.00015976759844857623, 'samples': 17932224, 'steps': 93396, 'loss/train': 0.6225467920303345} 08/31/2021 06:09:48 - INFO - __main__ - Step 93398: {'lr': 0.000159762649435945, 'samples': 17932416, 'steps': 93397, 'loss/train': 1.0992811918258667} 08/31/2021 06:09:50 - INFO - __main__ - Step 93399: {'lr': 0.00015975770046397326, 'samples': 17932608, 'steps': 93398, 'loss/train': 1.2041839361190796} 08/31/2021 06:09:51 - INFO - __main__ - Step 93400: {'lr': 0.00015975275153266334, 'samples': 17932800, 'steps': 93399, 'loss/train': 5.278476715087891} 08/31/2021 06:09:51 - INFO - __main__ - Step 93401: {'lr': 0.00015974780264201743, 'samples': 17932992, 'steps': 93400, 'loss/train': 1.4993733167648315} 08/31/2021 06:09:51 - INFO - __main__ - Step 93402: {'lr': 0.0001597428537920378, 'samples': 17933184, 'steps': 93401, 'loss/train': 0.5219538807868958} 08/31/2021 06:09:52 - INFO - __main__ - Step 93403: {'lr': 0.0001597379049827266, 'samples': 17933376, 'steps': 93402, 'loss/train': 0.04495802894234657} 08/31/2021 06:09:52 - INFO - __main__ - Step 93404: {'lr': 0.00015973295621408615, 'samples': 17933568, 'steps': 93403, 'loss/train': 0.021026568487286568} 08/31/2021 06:09:54 - INFO - __main__ - Step 93405: {'lr': 0.0001597280074861186, 'samples': 17933760, 'steps': 93404, 'loss/train': 1.3234680891036987} 08/31/2021 06:09:54 - INFO - __main__ - Step 93406: {'lr': 0.00015972305879882636, 'samples': 17933952, 'steps': 93405, 'loss/train': 0.07090459018945694} 08/31/2021 06:09:55 - INFO - __main__ - Step 93407: {'lr': 0.00015971811015221137, 'samples': 17934144, 'steps': 93406, 'loss/train': 1.0260552167892456} 08/31/2021 06:09:55 - INFO - __main__ - Step 93408: {'lr': 0.00015971316154627605, 'samples': 17934336, 'steps': 93407, 'loss/train': 0.4384724199771881} 08/31/2021 06:09:55 - INFO - __main__ - Step 93409: {'lr': 0.00015970821298102257, 'samples': 17934528, 'steps': 93408, 'loss/train': 0.041263647377491} 08/31/2021 06:09:57 - INFO - __main__ - Step 93410: {'lr': 0.00015970326445645315, 'samples': 17934720, 'steps': 93409, 'loss/train': 0.6234500408172607} 08/31/2021 06:09:57 - INFO - __main__ - Step 93411: {'lr': 0.00015969831597257005, 'samples': 17934912, 'steps': 93410, 'loss/train': 1.0353442430496216} 08/31/2021 06:09:58 - INFO - __main__ - Step 93412: {'lr': 0.0001596933675293755, 'samples': 17935104, 'steps': 93411, 'loss/train': 1.4516026973724365} 08/31/2021 06:09:58 - INFO - __main__ - Step 93413: {'lr': 0.00015968841912687175, 'samples': 17935296, 'steps': 93412, 'loss/train': 1.7690595388412476} 08/31/2021 06:09:58 - INFO - __main__ - Step 93414: {'lr': 0.000159683470765061, 'samples': 17935488, 'steps': 93413, 'loss/train': 0.9646214842796326} 08/31/2021 06:09:59 - INFO - __main__ - Step 93415: {'lr': 0.00015967852244394548, 'samples': 17935680, 'steps': 93414, 'loss/train': 1.5858913660049438} 08/31/2021 06:10:00 - INFO - __main__ - Step 93416: {'lr': 0.00015967357416352742, 'samples': 17935872, 'steps': 93415, 'loss/train': 0.7352783679962158} 08/31/2021 06:10:01 - INFO - __main__ - Step 93417: {'lr': 0.00015966862592380906, 'samples': 17936064, 'steps': 93416, 'loss/train': 0.8050405383110046} 08/31/2021 06:10:01 - INFO - __main__ - Step 93418: {'lr': 0.00015966367772479262, 'samples': 17936256, 'steps': 93417, 'loss/train': 0.9614372253417969} 08/31/2021 06:10:02 - INFO - __main__ - Step 93419: {'lr': 0.0001596587295664804, 'samples': 17936448, 'steps': 93418, 'loss/train': 1.029515266418457} 08/31/2021 06:10:02 - INFO - __main__ - Step 93420: {'lr': 0.00015965378144887455, 'samples': 17936640, 'steps': 93419, 'loss/train': 0.5827279686927795} 08/31/2021 06:10:04 - INFO - __main__ - Step 93421: {'lr': 0.00015964883337197722, 'samples': 17936832, 'steps': 93420, 'loss/train': 0.993341326713562} 08/31/2021 06:10:05 - INFO - __main__ - Step 93422: {'lr': 0.00015964388533579077, 'samples': 17937024, 'steps': 93421, 'loss/train': 0.04713982716202736} 08/31/2021 06:10:05 - INFO - __main__ - Step 93423: {'lr': 0.0001596389373403174, 'samples': 17937216, 'steps': 93422, 'loss/train': 0.0189021248370409} 08/31/2021 06:10:06 - INFO - __main__ - Step 93424: {'lr': 0.0001596339893855593, 'samples': 17937408, 'steps': 93423, 'loss/train': 1.1893129348754883} 08/31/2021 06:10:06 - INFO - __main__ - Step 93425: {'lr': 0.00015962904147151874, 'samples': 17937600, 'steps': 93424, 'loss/train': 1.158837914466858} 08/31/2021 06:10:06 - INFO - __main__ - Step 93426: {'lr': 0.00015962409359819796, 'samples': 17937792, 'steps': 93425, 'loss/train': 1.2430438995361328} 08/31/2021 06:10:08 - INFO - __main__ - Step 93427: {'lr': 0.00015961914576559917, 'samples': 17937984, 'steps': 93426, 'loss/train': 1.0270296335220337} 08/31/2021 06:10:08 - INFO - __main__ - Step 93428: {'lr': 0.00015961419797372455, 'samples': 17938176, 'steps': 93427, 'loss/train': 0.31955596804618835} 08/31/2021 06:10:09 - INFO - __main__ - Step 93429: {'lr': 0.00015960925022257645, 'samples': 17938368, 'steps': 93428, 'loss/train': 0.7356594204902649} 08/31/2021 06:10:09 - INFO - __main__ - Step 93430: {'lr': 0.00015960430251215697, 'samples': 17938560, 'steps': 93429, 'loss/train': 1.0508005619049072} 08/31/2021 06:10:10 - INFO - __main__ - Step 93431: {'lr': 0.0001595993548424684, 'samples': 17938752, 'steps': 93430, 'loss/train': 0.4395231306552887} 08/31/2021 06:10:11 - INFO - __main__ - Step 93432: {'lr': 0.000159594407213513, 'samples': 17938944, 'steps': 93431, 'loss/train': 0.9467533230781555} 08/31/2021 06:10:12 - INFO - __main__ - Step 93433: {'lr': 0.00015958945962529303, 'samples': 17939136, 'steps': 93432, 'loss/train': 1.6070706844329834} 08/31/2021 06:10:12 - INFO - __main__ - Step 93434: {'lr': 0.0001595845120778106, 'samples': 17939328, 'steps': 93433, 'loss/train': 1.0107651948928833} 08/31/2021 06:10:12 - INFO - __main__ - Step 93435: {'lr': 0.00015957956457106795, 'samples': 17939520, 'steps': 93434, 'loss/train': 1.6222591400146484} 08/31/2021 06:10:13 - INFO - __main__ - Step 93436: {'lr': 0.00015957461710506738, 'samples': 17939712, 'steps': 93435, 'loss/train': 1.2083916664123535} 08/31/2021 06:10:14 - INFO - __main__ - Step 93437: {'lr': 0.00015956966967981107, 'samples': 17939904, 'steps': 93436, 'loss/train': 1.6582947969436646} 08/31/2021 06:10:15 - INFO - __main__ - Step 93438: {'lr': 0.00015956472229530127, 'samples': 17940096, 'steps': 93437, 'loss/train': 1.2135155200958252} 08/31/2021 06:10:15 - INFO - __main__ - Step 93439: {'lr': 0.00015955977495154023, 'samples': 17940288, 'steps': 93438, 'loss/train': 1.4792180061340332} 08/31/2021 06:10:15 - INFO - __main__ - Step 93440: {'lr': 0.00015955482764853013, 'samples': 17940480, 'steps': 93439, 'loss/train': 0.9762659072875977} 08/31/2021 06:10:16 - INFO - __main__ - Step 93441: {'lr': 0.00015954988038627328, 'samples': 17940672, 'steps': 93440, 'loss/train': 1.5634267330169678} 08/31/2021 06:10:16 - INFO - __main__ - Step 93442: {'lr': 0.00015954493316477182, 'samples': 17940864, 'steps': 93441, 'loss/train': 1.3390071392059326} 08/31/2021 06:10:18 - INFO - __main__ - Step 93443: {'lr': 0.00015953998598402803, 'samples': 17941056, 'steps': 93442, 'loss/train': 1.670588493347168} 08/31/2021 06:10:18 - INFO - __main__ - Step 93444: {'lr': 0.00015953503884404412, 'samples': 17941248, 'steps': 93443, 'loss/train': 0.9092017412185669} 08/31/2021 06:10:19 - INFO - __main__ - Step 93445: {'lr': 0.0001595300917448223, 'samples': 17941440, 'steps': 93444, 'loss/train': 1.4908347129821777} 08/31/2021 06:10:19 - INFO - __main__ - Step 93446: {'lr': 0.00015952514468636498, 'samples': 17941632, 'steps': 93445, 'loss/train': 2.348825216293335} 08/31/2021 06:10:19 - INFO - __main__ - Step 93447: {'lr': 0.0001595201976686741, 'samples': 17941824, 'steps': 93446, 'loss/train': 1.6404238939285278} 08/31/2021 06:10:21 - INFO - __main__ - Step 93448: {'lr': 0.00015951525069175205, 'samples': 17942016, 'steps': 93447, 'loss/train': 0.9787067770957947} 08/31/2021 06:10:21 - INFO - __main__ - Step 93449: {'lr': 0.000159510303755601, 'samples': 17942208, 'steps': 93448, 'loss/train': 1.3792824745178223} 08/31/2021 06:10:22 - INFO - __main__ - Step 93450: {'lr': 0.00015950535686022323, 'samples': 17942400, 'steps': 93449, 'loss/train': 0.03557431697845459} 08/31/2021 06:10:22 - INFO - __main__ - Step 93451: {'lr': 0.00015950041000562093, 'samples': 17942592, 'steps': 93450, 'loss/train': 0.7018865346908569} 08/31/2021 06:10:22 - INFO - __main__ - Step 93452: {'lr': 0.00015949546319179636, 'samples': 17942784, 'steps': 93451, 'loss/train': 0.032540712505578995} 08/31/2021 06:10:24 - INFO - __main__ - Step 93453: {'lr': 0.00015949051641875173, 'samples': 17942976, 'steps': 93452, 'loss/train': 1.4560232162475586} 08/31/2021 06:10:24 - INFO - __main__ - Step 93454: {'lr': 0.0001594855696864893, 'samples': 17943168, 'steps': 93453, 'loss/train': 0.8096910119056702} 08/31/2021 06:10:25 - INFO - __main__ - Step 93455: {'lr': 0.00015948062299501125, 'samples': 17943360, 'steps': 93454, 'loss/train': 1.5838136672973633} 08/31/2021 06:10:25 - INFO - __main__ - Step 93456: {'lr': 0.00015947567634431984, 'samples': 17943552, 'steps': 93455, 'loss/train': 1.2012654542922974} 08/31/2021 06:10:25 - INFO - __main__ - Step 93457: {'lr': 0.00015947072973441728, 'samples': 17943744, 'steps': 93456, 'loss/train': 0.9152775406837463} 08/31/2021 06:10:27 - INFO - __main__ - Step 93458: {'lr': 0.00015946578316530585, 'samples': 17943936, 'steps': 93457, 'loss/train': 1.293197512626648} 08/31/2021 06:10:27 - INFO - __main__ - Step 93459: {'lr': 0.0001594608366369877, 'samples': 17944128, 'steps': 93458, 'loss/train': 1.7084070444107056} 08/31/2021 06:10:28 - INFO - __main__ - Step 93460: {'lr': 0.00015945589014946523, 'samples': 17944320, 'steps': 93459, 'loss/train': 0.29261574149131775} 08/31/2021 06:10:28 - INFO - __main__ - Step 93461: {'lr': 0.00015945094370274044, 'samples': 17944512, 'steps': 93460, 'loss/train': 1.8455696105957031} 08/31/2021 06:10:28 - INFO - __main__ - Step 93462: {'lr': 0.00015944599729681563, 'samples': 17944704, 'steps': 93461, 'loss/train': 5.742694854736328} 08/31/2021 06:10:29 - INFO - __main__ - Step 93463: {'lr': 0.0001594410509316931, 'samples': 17944896, 'steps': 93462, 'loss/train': 0.11789798736572266} 08/31/2021 06:10:30 - INFO - __main__ - Step 93464: {'lr': 0.000159436104607375, 'samples': 17945088, 'steps': 93463, 'loss/train': 1.173082709312439} 08/31/2021 06:10:31 - INFO - __main__ - Step 93465: {'lr': 0.0001594311583238636, 'samples': 17945280, 'steps': 93464, 'loss/train': 0.3255646526813507} 08/31/2021 06:10:31 - INFO - __main__ - Step 93466: {'lr': 0.00015942621208116112, 'samples': 17945472, 'steps': 93465, 'loss/train': 0.5970355272293091} 08/31/2021 06:10:31 - INFO - __main__ - Step 93467: {'lr': 0.0001594212658792698, 'samples': 17945664, 'steps': 93466, 'loss/train': 1.622712254524231} 08/31/2021 06:10:32 - INFO - __main__ - Step 93468: {'lr': 0.00015941631971819184, 'samples': 17945856, 'steps': 93467, 'loss/train': 1.2811250686645508} 08/31/2021 06:10:33 - INFO - __main__ - Step 93469: {'lr': 0.0001594113735979295, 'samples': 17946048, 'steps': 93468, 'loss/train': 0.6542872786521912} 08/31/2021 06:10:34 - INFO - __main__ - Step 93470: {'lr': 0.000159406427518485, 'samples': 17946240, 'steps': 93469, 'loss/train': 1.395048975944519} 08/31/2021 06:10:34 - INFO - __main__ - Step 93471: {'lr': 0.00015940148147986058, 'samples': 17946432, 'steps': 93470, 'loss/train': 1.5749061107635498} 08/31/2021 06:10:34 - INFO - __main__ - Step 93472: {'lr': 0.00015939653548205848, 'samples': 17946624, 'steps': 93471, 'loss/train': 1.4766703844070435} 08/31/2021 06:10:35 - INFO - __main__ - Step 93473: {'lr': 0.00015939158952508093, 'samples': 17946816, 'steps': 93472, 'loss/train': 1.5255298614501953} 08/31/2021 06:10:36 - INFO - __main__ - Step 93474: {'lr': 0.00015938664360893006, 'samples': 17947008, 'steps': 93473, 'loss/train': 1.3973907232284546} 08/31/2021 06:10:37 - INFO - __main__ - Step 93475: {'lr': 0.00015938169773360817, 'samples': 17947200, 'steps': 93474, 'loss/train': 1.3189038038253784} 08/31/2021 06:10:37 - INFO - __main__ - Step 93476: {'lr': 0.00015937675189911749, 'samples': 17947392, 'steps': 93475, 'loss/train': 1.584844946861267} 08/31/2021 06:10:38 - INFO - __main__ - Step 93477: {'lr': 0.00015937180610546027, 'samples': 17947584, 'steps': 93476, 'loss/train': 0.5856852531433105} 08/31/2021 06:10:38 - INFO - __main__ - Step 93478: {'lr': 0.0001593668603526387, 'samples': 17947776, 'steps': 93477, 'loss/train': 1.1925500631332397} 08/31/2021 06:10:40 - INFO - __main__ - Step 93479: {'lr': 0.00015936191464065502, 'samples': 17947968, 'steps': 93478, 'loss/train': 1.2043451070785522} 08/31/2021 06:10:41 - INFO - __main__ - Step 93480: {'lr': 0.00015935696896951146, 'samples': 17948160, 'steps': 93479, 'loss/train': 1.0784144401550293} 08/31/2021 06:10:41 - INFO - __main__ - Step 93481: {'lr': 0.00015935202333921026, 'samples': 17948352, 'steps': 93480, 'loss/train': 1.3002994060516357} 08/31/2021 06:10:41 - INFO - __main__ - Step 93482: {'lr': 0.00015934707774975363, 'samples': 17948544, 'steps': 93481, 'loss/train': 1.4360601902008057} 08/31/2021 06:10:42 - INFO - __main__ - Step 93483: {'lr': 0.00015934213220114386, 'samples': 17948736, 'steps': 93482, 'loss/train': 1.4004361629486084} 08/31/2021 06:10:43 - INFO - __main__ - Step 93484: {'lr': 0.0001593371866933831, 'samples': 17948928, 'steps': 93483, 'loss/train': 0.6928632855415344} 08/31/2021 06:10:44 - INFO - __main__ - Step 93485: {'lr': 0.00015933224122647354, 'samples': 17949120, 'steps': 93484, 'loss/train': 0.8474644422531128} 08/31/2021 06:10:44 - INFO - __main__ - Step 93486: {'lr': 0.0001593272958004176, 'samples': 17949312, 'steps': 93485, 'loss/train': 0.4908788204193115} 08/31/2021 06:10:44 - INFO - __main__ - Step 93487: {'lr': 0.0001593223504152173, 'samples': 17949504, 'steps': 93486, 'loss/train': 1.159867525100708} 08/31/2021 06:10:45 - INFO - __main__ - Step 93488: {'lr': 0.00015931740507087495, 'samples': 17949696, 'steps': 93487, 'loss/train': 1.2911722660064697} 08/31/2021 06:10:45 - INFO - __main__ - Step 93489: {'lr': 0.00015931245976739277, 'samples': 17949888, 'steps': 93488, 'loss/train': 1.630415439605713} 08/31/2021 06:10:47 - INFO - __main__ - Step 93490: {'lr': 0.00015930751450477299, 'samples': 17950080, 'steps': 93489, 'loss/train': 1.264613389968872} 08/31/2021 06:10:47 - INFO - __main__ - Step 93491: {'lr': 0.00015930256928301783, 'samples': 17950272, 'steps': 93490, 'loss/train': 0.932784378528595} 08/31/2021 06:10:47 - INFO - __main__ - Step 93492: {'lr': 0.00015929762410212957, 'samples': 17950464, 'steps': 93491, 'loss/train': 0.6905480027198792} 08/31/2021 06:10:48 - INFO - __main__ - Step 93493: {'lr': 0.00015929267896211042, 'samples': 17950656, 'steps': 93492, 'loss/train': 1.5350759029388428} 08/31/2021 06:10:48 - INFO - __main__ - Step 93494: {'lr': 0.00015928773386296257, 'samples': 17950848, 'steps': 93493, 'loss/train': 0.9653196334838867} 08/31/2021 06:10:50 - INFO - __main__ - Step 93495: {'lr': 0.00015928278880468827, 'samples': 17951040, 'steps': 93494, 'loss/train': 1.0491597652435303} 08/31/2021 06:10:50 - INFO - __main__ - Step 93496: {'lr': 0.00015927784378728975, 'samples': 17951232, 'steps': 93495, 'loss/train': 0.8169240355491638} 08/31/2021 06:10:51 - INFO - __main__ - Step 93497: {'lr': 0.00015927289881076924, 'samples': 17951424, 'steps': 93496, 'loss/train': 1.3680660724639893} 08/31/2021 06:10:51 - INFO - __main__ - Step 93498: {'lr': 0.0001592679538751289, 'samples': 17951616, 'steps': 93497, 'loss/train': 1.2982693910598755} 08/31/2021 06:10:51 - INFO - __main__ - Step 93499: {'lr': 0.00015926300898037104, 'samples': 17951808, 'steps': 93498, 'loss/train': 1.2382721900939941} 08/31/2021 06:10:53 - INFO - __main__ - Step 93500: {'lr': 0.00015925806412649796, 'samples': 17952000, 'steps': 93499, 'loss/train': 0.987006664276123} 08/31/2021 06:10:53 - INFO - __main__ - Step 93501: {'lr': 0.00015925311931351172, 'samples': 17952192, 'steps': 93500, 'loss/train': 0.9899635910987854} 08/31/2021 06:10:53 - INFO - __main__ - Step 93502: {'lr': 0.00015924817454141462, 'samples': 17952384, 'steps': 93501, 'loss/train': 0.6863428354263306} 08/31/2021 06:10:54 - INFO - __main__ - Step 93503: {'lr': 0.0001592432298102089, 'samples': 17952576, 'steps': 93502, 'loss/train': 1.535473346710205} 08/31/2021 06:10:54 - INFO - __main__ - Step 93504: {'lr': 0.0001592382851198968, 'samples': 17952768, 'steps': 93503, 'loss/train': 1.532615065574646} 08/31/2021 06:10:56 - INFO - __main__ - Step 93505: {'lr': 0.00015923334047048056, 'samples': 17952960, 'steps': 93504, 'loss/train': 1.4096918106079102} 08/31/2021 06:10:56 - INFO - __main__ - Step 93506: {'lr': 0.0001592283958619623, 'samples': 17953152, 'steps': 93505, 'loss/train': 1.1832170486450195} 08/31/2021 06:10:56 - INFO - __main__ - Step 93507: {'lr': 0.00015922345129434435, 'samples': 17953344, 'steps': 93506, 'loss/train': 1.1780691146850586} 08/31/2021 06:10:57 - INFO - __main__ - Step 93508: {'lr': 0.00015921850676762892, 'samples': 17953536, 'steps': 93507, 'loss/train': 1.5079160928726196} 08/31/2021 06:10:57 - INFO - __main__ - Step 93509: {'lr': 0.0001592135622818182, 'samples': 17953728, 'steps': 93508, 'loss/train': 1.1001638174057007} 08/31/2021 06:10:59 - INFO - __main__ - Step 93510: {'lr': 0.00015920861783691448, 'samples': 17953920, 'steps': 93509, 'loss/train': 1.113387107849121} 08/31/2021 06:10:59 - INFO - __main__ - Step 93511: {'lr': 0.00015920367343291993, 'samples': 17954112, 'steps': 93510, 'loss/train': 1.514309048652649} 08/31/2021 06:10:59 - INFO - __main__ - Step 93512: {'lr': 0.00015919872906983685, 'samples': 17954304, 'steps': 93511, 'loss/train': 1.2603789567947388} 08/31/2021 06:11:00 - INFO - __main__ - Step 93513: {'lr': 0.00015919378474766742, 'samples': 17954496, 'steps': 93512, 'loss/train': 1.7706191539764404} 08/31/2021 06:11:00 - INFO - __main__ - Step 93514: {'lr': 0.00015918884046641383, 'samples': 17954688, 'steps': 93513, 'loss/train': 1.0087004899978638} 08/31/2021 06:11:02 - INFO - __main__ - Step 93515: {'lr': 0.0001591838962260784, 'samples': 17954880, 'steps': 93514, 'loss/train': 0.9331165552139282} 08/31/2021 06:11:02 - INFO - __main__ - Step 93516: {'lr': 0.00015917895202666326, 'samples': 17955072, 'steps': 93515, 'loss/train': 1.0837541818618774} 08/31/2021 06:11:02 - INFO - __main__ - Step 93517: {'lr': 0.00015917400786817068, 'samples': 17955264, 'steps': 93516, 'loss/train': 1.1724408864974976} 08/31/2021 06:11:03 - INFO - __main__ - Step 93518: {'lr': 0.0001591690637506029, 'samples': 17955456, 'steps': 93517, 'loss/train': 1.1890360116958618} 08/31/2021 06:11:03 - INFO - __main__ - Step 93519: {'lr': 0.00015916411967396214, 'samples': 17955648, 'steps': 93518, 'loss/train': 1.4410849809646606} 08/31/2021 06:11:04 - INFO - __main__ - Step 93520: {'lr': 0.0001591591756382506, 'samples': 17955840, 'steps': 93519, 'loss/train': 1.2044402360916138} 08/31/2021 06:11:05 - INFO - __main__ - Step 93521: {'lr': 0.00015915423164347055, 'samples': 17956032, 'steps': 93520, 'loss/train': 1.1974281072616577} 08/31/2021 06:11:05 - INFO - __main__ - Step 93522: {'lr': 0.00015914928768962422, 'samples': 17956224, 'steps': 93521, 'loss/train': 0.8171408772468567} 08/31/2021 06:11:06 - INFO - __main__ - Step 93523: {'lr': 0.00015914434377671378, 'samples': 17956416, 'steps': 93522, 'loss/train': 0.5860333442687988} 08/31/2021 06:11:06 - INFO - __main__ - Step 93524: {'lr': 0.00015913939990474152, 'samples': 17956608, 'steps': 93523, 'loss/train': 1.1773154735565186} 08/31/2021 06:11:08 - INFO - __main__ - Step 93525: {'lr': 0.00015913445607370963, 'samples': 17956800, 'steps': 93524, 'loss/train': 1.2881104946136475} 08/31/2021 06:11:08 - INFO - __main__ - Step 93526: {'lr': 0.00015912951228362038, 'samples': 17956992, 'steps': 93525, 'loss/train': 1.5013142824172974} 08/31/2021 06:11:08 - INFO - __main__ - Step 93527: {'lr': 0.00015912456853447605, 'samples': 17957184, 'steps': 93526, 'loss/train': 0.8777068853378296} 08/31/2021 06:11:09 - INFO - __main__ - Step 93528: {'lr': 0.0001591196248262787, 'samples': 17957376, 'steps': 93527, 'loss/train': 0.9957514405250549} 08/31/2021 06:11:09 - INFO - __main__ - Step 93529: {'lr': 0.00015911468115903062, 'samples': 17957568, 'steps': 93528, 'loss/train': 0.9861114025115967} 08/31/2021 06:11:09 - INFO - __main__ - Step 93530: {'lr': 0.0001591097375327341, 'samples': 17957760, 'steps': 93529, 'loss/train': 0.6867761611938477} 08/31/2021 06:11:11 - INFO - __main__ - Step 93531: {'lr': 0.0001591047939473913, 'samples': 17957952, 'steps': 93530, 'loss/train': 1.386772632598877} 08/31/2021 06:11:12 - INFO - __main__ - Step 93532: {'lr': 0.00015909985040300447, 'samples': 17958144, 'steps': 93531, 'loss/train': 1.2887969017028809} 08/31/2021 06:11:12 - INFO - __main__ - Step 93533: {'lr': 0.00015909490689957587, 'samples': 17958336, 'steps': 93532, 'loss/train': 1.2609941959381104} 08/31/2021 06:11:13 - INFO - __main__ - Step 93534: {'lr': 0.0001590899634371077, 'samples': 17958528, 'steps': 93533, 'loss/train': 1.423486590385437} 08/31/2021 06:11:13 - INFO - __main__ - Step 93535: {'lr': 0.00015908502001560216, 'samples': 17958720, 'steps': 93534, 'loss/train': 0.025192176923155785} 08/31/2021 06:11:15 - INFO - __main__ - Step 93536: {'lr': 0.00015908007663506153, 'samples': 17958912, 'steps': 93535, 'loss/train': 1.0045760869979858} 08/31/2021 06:11:16 - INFO - __main__ - Step 93537: {'lr': 0.00015907513329548801, 'samples': 17959104, 'steps': 93536, 'loss/train': 1.5765018463134766} 08/31/2021 06:11:16 - INFO - __main__ - Step 93538: {'lr': 0.00015907018999688382, 'samples': 17959296, 'steps': 93537, 'loss/train': 1.202333688735962} 08/31/2021 06:11:16 - INFO - __main__ - Step 93539: {'lr': 0.00015906524673925125, 'samples': 17959488, 'steps': 93538, 'loss/train': 0.4095849096775055} 08/31/2021 06:11:17 - INFO - __main__ - Step 93540: {'lr': 0.00015906030352259254, 'samples': 17959680, 'steps': 93539, 'loss/train': 1.3858027458190918} 08/31/2021 06:11:17 - INFO - __main__ - Step 93541: {'lr': 0.00015905536034690977, 'samples': 17959872, 'steps': 93540, 'loss/train': 1.5812220573425293} 08/31/2021 06:11:18 - INFO - __main__ - Step 93542: {'lr': 0.0001590504172122052, 'samples': 17960064, 'steps': 93541, 'loss/train': 0.05588677525520325} 08/31/2021 06:11:19 - INFO - __main__ - Step 93543: {'lr': 0.00015904547411848115, 'samples': 17960256, 'steps': 93542, 'loss/train': 1.0457706451416016} 08/31/2021 06:11:19 - INFO - __main__ - Step 93544: {'lr': 0.0001590405310657398, 'samples': 17960448, 'steps': 93543, 'loss/train': 1.395614743232727} 08/31/2021 06:11:20 - INFO - __main__ - Step 93545: {'lr': 0.00015903558805398338, 'samples': 17960640, 'steps': 93544, 'loss/train': 1.0743873119354248} 08/31/2021 06:11:20 - INFO - __main__ - Step 93546: {'lr': 0.00015903064508321414, 'samples': 17960832, 'steps': 93545, 'loss/train': 1.0083343982696533} 08/31/2021 06:11:21 - INFO - __main__ - Step 93547: {'lr': 0.00015902570215343425, 'samples': 17961024, 'steps': 93546, 'loss/train': 1.3562341928482056} 08/31/2021 06:11:22 - INFO - __main__ - Step 93548: {'lr': 0.000159020759264646, 'samples': 17961216, 'steps': 93547, 'loss/train': 1.531903862953186} 08/31/2021 06:11:22 - INFO - __main__ - Step 93549: {'lr': 0.00015901581641685158, 'samples': 17961408, 'steps': 93548, 'loss/train': 1.7470674514770508} 08/31/2021 06:11:23 - INFO - __main__ - Step 93550: {'lr': 0.00015901087361005326, 'samples': 17961600, 'steps': 93549, 'loss/train': 1.9331861734390259} 08/31/2021 06:11:23 - INFO - __main__ - Step 93551: {'lr': 0.0001590059308442532, 'samples': 17961792, 'steps': 93550, 'loss/train': 1.485434889793396} 08/31/2021 06:11:25 - INFO - __main__ - Step 93552: {'lr': 0.00015900098811945368, 'samples': 17961984, 'steps': 93551, 'loss/train': 0.8257112503051758} 08/31/2021 06:11:25 - INFO - __main__ - Step 93553: {'lr': 0.0001589960454356569, 'samples': 17962176, 'steps': 93552, 'loss/train': 0.032412637025117874} 08/31/2021 06:11:25 - INFO - __main__ - Step 93554: {'lr': 0.0001589911027928652, 'samples': 17962368, 'steps': 93553, 'loss/train': 0.7463973164558411} 08/31/2021 06:11:26 - INFO - __main__ - Step 93555: {'lr': 0.00015898616019108065, 'samples': 17962560, 'steps': 93554, 'loss/train': 1.6662472486495972} 08/31/2021 06:11:26 - INFO - __main__ - Step 93556: {'lr': 0.00015898121763030547, 'samples': 17962752, 'steps': 93555, 'loss/train': 1.2470476627349854} 08/31/2021 06:11:26 - INFO - __main__ - Step 93557: {'lr': 0.00015897627511054198, 'samples': 17962944, 'steps': 93556, 'loss/train': 0.7031331062316895} 08/31/2021 06:11:29 - INFO - __main__ - Step 93558: {'lr': 0.00015897133263179236, 'samples': 17963136, 'steps': 93557, 'loss/train': 0.6069785952568054} 08/31/2021 06:11:29 - INFO - __main__ - Step 93559: {'lr': 0.00015896639019405884, 'samples': 17963328, 'steps': 93558, 'loss/train': 1.2992345094680786} 08/31/2021 06:11:29 - INFO - __main__ - Step 93560: {'lr': 0.00015896144779734366, 'samples': 17963520, 'steps': 93559, 'loss/train': 1.4949826002120972} 08/31/2021 06:11:30 - INFO - __main__ - Step 93561: {'lr': 0.0001589565054416491, 'samples': 17963712, 'steps': 93560, 'loss/train': 1.4620696306228638} 08/31/2021 06:11:30 - INFO - __main__ - Step 93562: {'lr': 0.0001589515631269773, 'samples': 17963904, 'steps': 93561, 'loss/train': 1.1422014236450195} 08/31/2021 06:11:31 - INFO - __main__ - Step 93563: {'lr': 0.0001589466208533305, 'samples': 17964096, 'steps': 93562, 'loss/train': 1.3536688089370728} 08/31/2021 06:11:32 - INFO - __main__ - Step 93564: {'lr': 0.00015894167862071098, 'samples': 17964288, 'steps': 93563, 'loss/train': 1.3584879636764526} 08/31/2021 06:11:33 - INFO - __main__ - Step 93565: {'lr': 0.00015893673642912093, 'samples': 17964480, 'steps': 93564, 'loss/train': 0.7759106755256653} 08/31/2021 06:11:33 - INFO - __main__ - Step 93566: {'lr': 0.00015893179427856259, 'samples': 17964672, 'steps': 93565, 'loss/train': 1.045677661895752} 08/31/2021 06:11:33 - INFO - __main__ - Step 93567: {'lr': 0.00015892685216903823, 'samples': 17964864, 'steps': 93566, 'loss/train': 1.1014302968978882} 08/31/2021 06:11:34 - INFO - __main__ - Step 93568: {'lr': 0.00015892191010054995, 'samples': 17965056, 'steps': 93567, 'loss/train': 1.5064517259597778} 08/31/2021 06:11:35 - INFO - __main__ - Step 93569: {'lr': 0.00015891696807310008, 'samples': 17965248, 'steps': 93568, 'loss/train': 1.3139898777008057} 08/31/2021 06:11:35 - INFO - __main__ - Step 93570: {'lr': 0.00015891202608669082, 'samples': 17965440, 'steps': 93569, 'loss/train': 1.0836361646652222} 08/31/2021 06:11:36 - INFO - __main__ - Step 93571: {'lr': 0.00015890708414132435, 'samples': 17965632, 'steps': 93570, 'loss/train': 1.1716861724853516} 08/31/2021 06:11:36 - INFO - __main__ - Step 93572: {'lr': 0.00015890214223700296, 'samples': 17965824, 'steps': 93571, 'loss/train': 1.2285363674163818} 08/31/2021 06:11:37 - INFO - __main__ - Step 93573: {'lr': 0.00015889720037372886, 'samples': 17966016, 'steps': 93572, 'loss/train': 1.415507435798645} 08/31/2021 06:11:38 - INFO - __main__ - Step 93574: {'lr': 0.00015889225855150429, 'samples': 17966208, 'steps': 93573, 'loss/train': 0.9646587371826172} 08/31/2021 06:11:38 - INFO - __main__ - Step 93575: {'lr': 0.00015888731677033148, 'samples': 17966400, 'steps': 93574, 'loss/train': 1.3221486806869507} 08/31/2021 06:11:39 - INFO - __main__ - Step 93576: {'lr': 0.0001588823750302126, 'samples': 17966592, 'steps': 93575, 'loss/train': 0.9955233931541443} 08/31/2021 06:11:39 - INFO - __main__ - Step 93577: {'lr': 0.0001588774333311499, 'samples': 17966784, 'steps': 93576, 'loss/train': 1.2842246294021606} 08/31/2021 06:11:40 - INFO - __main__ - Step 93578: {'lr': 0.00015887249167314567, 'samples': 17966976, 'steps': 93577, 'loss/train': 0.6167484521865845} 08/31/2021 06:11:41 - INFO - __main__ - Step 93579: {'lr': 0.00015886755005620207, 'samples': 17967168, 'steps': 93578, 'loss/train': 0.8314327001571655} 08/31/2021 06:11:41 - INFO - __main__ - Step 93580: {'lr': 0.00015886260848032134, 'samples': 17967360, 'steps': 93579, 'loss/train': 1.0831773281097412} 08/31/2021 06:11:42 - INFO - __main__ - Step 93581: {'lr': 0.0001588576669455058, 'samples': 17967552, 'steps': 93580, 'loss/train': 0.7915239334106445} 08/31/2021 06:11:42 - INFO - __main__ - Step 93582: {'lr': 0.0001588527254517575, 'samples': 17967744, 'steps': 93581, 'loss/train': 0.7460317015647888} 08/31/2021 06:11:43 - INFO - __main__ - Step 93583: {'lr': 0.00015884778399907878, 'samples': 17967936, 'steps': 93582, 'loss/train': 1.1439323425292969} 08/31/2021 06:11:43 - INFO - __main__ - Step 93584: {'lr': 0.00015884284258747185, 'samples': 17968128, 'steps': 93583, 'loss/train': 1.8308829069137573} 08/31/2021 06:11:45 - INFO - __main__ - Step 93585: {'lr': 0.00015883790121693885, 'samples': 17968320, 'steps': 93584, 'loss/train': 2.5879321098327637} 08/31/2021 06:11:46 - INFO - __main__ - Step 93586: {'lr': 0.00015883295988748213, 'samples': 17968512, 'steps': 93585, 'loss/train': 0.9313011765480042} 08/31/2021 06:11:46 - INFO - __main__ - Step 93587: {'lr': 0.00015882801859910388, 'samples': 17968704, 'steps': 93586, 'loss/train': 1.3524155616760254} 08/31/2021 06:11:46 - INFO - __main__ - Step 93588: {'lr': 0.00015882307735180635, 'samples': 17968896, 'steps': 93587, 'loss/train': 0.412840873003006} 08/31/2021 06:11:47 - INFO - __main__ - Step 93589: {'lr': 0.0001588181361455917, 'samples': 17969088, 'steps': 93588, 'loss/train': 1.7193814516067505} 08/31/2021 06:11:47 - INFO - __main__ - Step 93590: {'lr': 0.00015881319498046217, 'samples': 17969280, 'steps': 93589, 'loss/train': 1.738359808921814} 08/31/2021 06:11:49 - INFO - __main__ - Step 93591: {'lr': 0.00015880825385642004, 'samples': 17969472, 'steps': 93590, 'loss/train': 0.4694438874721527} 08/31/2021 06:11:49 - INFO - __main__ - Step 93592: {'lr': 0.0001588033127734675, 'samples': 17969664, 'steps': 93591, 'loss/train': 0.8960266709327698} 08/31/2021 06:11:49 - INFO - __main__ - Step 93593: {'lr': 0.00015879837173160677, 'samples': 17969856, 'steps': 93592, 'loss/train': 1.4270766973495483} 08/31/2021 06:11:50 - INFO - __main__ - Step 93594: {'lr': 0.0001587934307308402, 'samples': 17970048, 'steps': 93593, 'loss/train': 0.9556950926780701} 08/31/2021 06:11:50 - INFO - __main__ - Step 93595: {'lr': 0.00015878848977116979, 'samples': 17970240, 'steps': 93594, 'loss/train': 1.592839002609253} 08/31/2021 06:11:52 - INFO - __main__ - Step 93596: {'lr': 0.00015878354885259788, 'samples': 17970432, 'steps': 93595, 'loss/train': 2.0553958415985107} 08/31/2021 06:11:52 - INFO - __main__ - Step 93597: {'lr': 0.00015877860797512667, 'samples': 17970624, 'steps': 93596, 'loss/train': 1.3057153224945068} 08/31/2021 06:11:53 - INFO - __main__ - Step 93598: {'lr': 0.00015877366713875845, 'samples': 17970816, 'steps': 93597, 'loss/train': 1.3673877716064453} 08/31/2021 06:11:53 - INFO - __main__ - Step 93599: {'lr': 0.00015876872634349538, 'samples': 17971008, 'steps': 93598, 'loss/train': 2.3068647384643555} 08/31/2021 06:11:53 - INFO - __main__ - Step 93600: {'lr': 0.00015876378558933973, 'samples': 17971200, 'steps': 93599, 'loss/train': 1.2431085109710693} 08/31/2021 06:11:55 - INFO - __main__ - Step 93601: {'lr': 0.0001587588448762937, 'samples': 17971392, 'steps': 93600, 'loss/train': 1.5013021230697632} 08/31/2021 06:11:56 - INFO - __main__ - Step 93602: {'lr': 0.00015875390420435953, 'samples': 17971584, 'steps': 93601, 'loss/train': 1.1073033809661865} 08/31/2021 06:11:56 - INFO - __main__ - Step 93603: {'lr': 0.00015874896357353946, 'samples': 17971776, 'steps': 93602, 'loss/train': 0.5396893620491028} 08/31/2021 06:11:56 - INFO - __main__ - Step 93604: {'lr': 0.0001587440229838357, 'samples': 17971968, 'steps': 93603, 'loss/train': 1.4385968446731567} 08/31/2021 06:11:57 - INFO - __main__ - Step 93605: {'lr': 0.00015873908243525047, 'samples': 17972160, 'steps': 93604, 'loss/train': 0.8736380934715271} 08/31/2021 06:11:58 - INFO - __main__ - Step 93606: {'lr': 0.00015873414192778604, 'samples': 17972352, 'steps': 93605, 'loss/train': 1.1613744497299194} 08/31/2021 06:11:59 - INFO - __main__ - Step 93607: {'lr': 0.0001587292014614446, 'samples': 17972544, 'steps': 93606, 'loss/train': 0.9264675974845886} 08/31/2021 06:11:59 - INFO - __main__ - Step 93608: {'lr': 0.00015872426103622834, 'samples': 17972736, 'steps': 93607, 'loss/train': 0.16219083964824677} 08/31/2021 06:11:59 - INFO - __main__ - Step 93609: {'lr': 0.00015871932065213948, 'samples': 17972928, 'steps': 93608, 'loss/train': 1.3165130615234375} 08/31/2021 06:12:00 - INFO - __main__ - Step 93610: {'lr': 0.00015871438030918032, 'samples': 17973120, 'steps': 93609, 'loss/train': 1.017406702041626} 08/31/2021 06:12:01 - INFO - __main__ - Step 93611: {'lr': 0.00015870944000735305, 'samples': 17973312, 'steps': 93610, 'loss/train': 0.9503453969955444} 08/31/2021 06:12:01 - INFO - __main__ - Step 93612: {'lr': 0.00015870449974665987, 'samples': 17973504, 'steps': 93611, 'loss/train': 1.7108793258666992} 08/31/2021 06:12:02 - INFO - __main__ - Step 93613: {'lr': 0.00015869955952710308, 'samples': 17973696, 'steps': 93612, 'loss/train': 1.2776401042938232} 08/31/2021 06:12:02 - INFO - __main__ - Step 93614: {'lr': 0.0001586946193486848, 'samples': 17973888, 'steps': 93613, 'loss/train': 1.3172284364700317} 08/31/2021 06:12:03 - INFO - __main__ - Step 93615: {'lr': 0.00015868967921140736, 'samples': 17974080, 'steps': 93614, 'loss/train': 1.4941297769546509} 08/31/2021 06:12:04 - INFO - __main__ - Step 93616: {'lr': 0.00015868473911527292, 'samples': 17974272, 'steps': 93615, 'loss/train': 2.4594767093658447} 08/31/2021 06:12:05 - INFO - __main__ - Step 93617: {'lr': 0.0001586797990602838, 'samples': 17974464, 'steps': 93616, 'loss/train': 0.963939368724823} 08/31/2021 06:12:05 - INFO - __main__ - Step 93618: {'lr': 0.0001586748590464421, 'samples': 17974656, 'steps': 93617, 'loss/train': 1.3207260370254517} 08/31/2021 06:12:05 - INFO - __main__ - Step 93619: {'lr': 0.00015866991907375006, 'samples': 17974848, 'steps': 93618, 'loss/train': 1.0011858940124512} 08/31/2021 06:12:06 - INFO - __main__ - Step 93620: {'lr': 0.00015866497914220998, 'samples': 17975040, 'steps': 93619, 'loss/train': 0.7791850566864014} 08/31/2021 06:12:07 - INFO - __main__ - Step 93621: {'lr': 0.0001586600392518241, 'samples': 17975232, 'steps': 93620, 'loss/train': 0.8341751098632812} 08/31/2021 06:12:08 - INFO - __main__ - Step 93622: {'lr': 0.00015865509940259453, 'samples': 17975424, 'steps': 93621, 'loss/train': 1.5540574789047241} 08/31/2021 06:12:08 - INFO - __main__ - Step 93623: {'lr': 0.00015865015959452358, 'samples': 17975616, 'steps': 93622, 'loss/train': 1.4252772331237793} 08/31/2021 06:12:08 - INFO - __main__ - Step 93624: {'lr': 0.00015864521982761348, 'samples': 17975808, 'steps': 93623, 'loss/train': 0.835755467414856} 08/31/2021 06:12:09 - INFO - __main__ - Step 93625: {'lr': 0.00015864028010186638, 'samples': 17976000, 'steps': 93624, 'loss/train': 0.5882525444030762} 08/31/2021 06:12:10 - INFO - __main__ - Step 93626: {'lr': 0.0001586353404172846, 'samples': 17976192, 'steps': 93625, 'loss/train': 1.3001476526260376} 08/31/2021 06:12:11 - INFO - __main__ - Step 93627: {'lr': 0.0001586304007738703, 'samples': 17976384, 'steps': 93626, 'loss/train': 1.429051399230957} 08/31/2021 06:12:11 - INFO - __main__ - Step 93628: {'lr': 0.00015862546117162578, 'samples': 17976576, 'steps': 93627, 'loss/train': 0.9854305386543274} 08/31/2021 06:12:11 - INFO - __main__ - Step 93629: {'lr': 0.00015862052161055322, 'samples': 17976768, 'steps': 93628, 'loss/train': 1.2864353656768799} 08/31/2021 06:12:12 - INFO - __main__ - Step 93630: {'lr': 0.0001586155820906548, 'samples': 17976960, 'steps': 93629, 'loss/train': 0.9083409905433655} 08/31/2021 06:12:13 - INFO - __main__ - Step 93631: {'lr': 0.0001586106426119328, 'samples': 17977152, 'steps': 93630, 'loss/train': 1.0863758325576782} 08/31/2021 06:12:13 - INFO - __main__ - Step 93632: {'lr': 0.00015860570317438943, 'samples': 17977344, 'steps': 93631, 'loss/train': 1.7842358350753784} 08/31/2021 06:12:14 - INFO - __main__ - Step 93633: {'lr': 0.00015860076377802691, 'samples': 17977536, 'steps': 93632, 'loss/train': 1.0370973348617554} 08/31/2021 06:12:14 - INFO - __main__ - Step 93634: {'lr': 0.00015859582442284754, 'samples': 17977728, 'steps': 93633, 'loss/train': 1.6863305568695068} 08/31/2021 06:12:14 - INFO - __main__ - Step 93635: {'lr': 0.0001585908851088534, 'samples': 17977920, 'steps': 93634, 'loss/train': 0.8454755544662476} 08/31/2021 06:12:16 - INFO - __main__ - Step 93636: {'lr': 0.00015858594583604684, 'samples': 17978112, 'steps': 93635, 'loss/train': 1.1465356349945068} 08/31/2021 06:12:17 - INFO - __main__ - Step 93637: {'lr': 0.00015858100660443003, 'samples': 17978304, 'steps': 93636, 'loss/train': 1.347544550895691} 08/31/2021 06:12:17 - INFO - __main__ - Step 93638: {'lr': 0.0001585760674140052, 'samples': 17978496, 'steps': 93637, 'loss/train': 1.1805862188339233} 08/31/2021 06:12:17 - INFO - __main__ - Step 93639: {'lr': 0.00015857112826477463, 'samples': 17978688, 'steps': 93638, 'loss/train': 1.132975697517395} 08/31/2021 06:12:18 - INFO - __main__ - Step 93640: {'lr': 0.00015856618915674044, 'samples': 17978880, 'steps': 93639, 'loss/train': 1.0833176374435425} 08/31/2021 06:12:18 - INFO - __main__ - Step 93641: {'lr': 0.00015856125008990494, 'samples': 17979072, 'steps': 93640, 'loss/train': 1.9873679876327515} 08/31/2021 06:12:20 - INFO - __main__ - Step 93642: {'lr': 0.0001585563110642703, 'samples': 17979264, 'steps': 93641, 'loss/train': 0.855854332447052} 08/31/2021 06:12:21 - INFO - __main__ - Step 93643: {'lr': 0.0001585513720798388, 'samples': 17979456, 'steps': 93642, 'loss/train': 2.327544927597046} 08/31/2021 06:12:21 - INFO - __main__ - Step 93644: {'lr': 0.00015854643313661265, 'samples': 17979648, 'steps': 93643, 'loss/train': 1.2149592638015747} 08/31/2021 06:12:21 - INFO - __main__ - Step 93645: {'lr': 0.00015854149423459403, 'samples': 17979840, 'steps': 93644, 'loss/train': 0.876135528087616} 08/31/2021 06:12:22 - INFO - __main__ - Step 93646: {'lr': 0.0001585365553737852, 'samples': 17980032, 'steps': 93645, 'loss/train': 1.6985844373703003} 08/31/2021 06:12:23 - INFO - __main__ - Step 93647: {'lr': 0.00015853161655418843, 'samples': 17980224, 'steps': 93646, 'loss/train': 1.2131940126419067} 08/31/2021 06:12:24 - INFO - __main__ - Step 93648: {'lr': 0.00015852667777580592, 'samples': 17980416, 'steps': 93647, 'loss/train': 1.5981392860412598} 08/31/2021 06:12:24 - INFO - __main__ - Step 93649: {'lr': 0.00015852173903863986, 'samples': 17980608, 'steps': 93648, 'loss/train': 1.0122240781784058} 08/31/2021 06:12:24 - INFO - __main__ - Step 93650: {'lr': 0.0001585168003426925, 'samples': 17980800, 'steps': 93649, 'loss/train': 1.2916542291641235} 08/31/2021 06:12:25 - INFO - __main__ - Step 93651: {'lr': 0.00015851186168796606, 'samples': 17980992, 'steps': 93650, 'loss/train': 0.9108784794807434} 08/31/2021 06:12:25 - INFO - __main__ - Step 93652: {'lr': 0.00015850692307446272, 'samples': 17981184, 'steps': 93651, 'loss/train': 0.6094820499420166} 08/31/2021 06:12:27 - INFO - __main__ - Step 93653: {'lr': 0.00015850198450218474, 'samples': 17981376, 'steps': 93652, 'loss/train': 1.2347397804260254} 08/31/2021 06:12:27 - INFO - __main__ - Step 93654: {'lr': 0.00015849704597113438, 'samples': 17981568, 'steps': 93653, 'loss/train': 1.251924753189087} 08/31/2021 06:12:27 - INFO - __main__ - Step 93655: {'lr': 0.00015849210748131382, 'samples': 17981760, 'steps': 93654, 'loss/train': 1.3626478910446167} 08/31/2021 06:12:28 - INFO - __main__ - Step 93656: {'lr': 0.0001584871690327253, 'samples': 17981952, 'steps': 93655, 'loss/train': 1.3399204015731812} 08/31/2021 06:12:28 - INFO - __main__ - Step 93657: {'lr': 0.0001584822306253711, 'samples': 17982144, 'steps': 93656, 'loss/train': 1.2220827341079712} 08/31/2021 06:12:30 - INFO - __main__ - Step 93658: {'lr': 0.00015847729225925333, 'samples': 17982336, 'steps': 93657, 'loss/train': 1.338860034942627} 08/31/2021 06:12:30 - INFO - __main__ - Step 93659: {'lr': 0.00015847235393437435, 'samples': 17982528, 'steps': 93658, 'loss/train': 1.067164421081543} 08/31/2021 06:12:31 - INFO - __main__ - Step 93660: {'lr': 0.00015846741565073624, 'samples': 17982720, 'steps': 93659, 'loss/train': 0.3178102374076843} 08/31/2021 06:12:31 - INFO - __main__ - Step 93661: {'lr': 0.00015846247740834146, 'samples': 17982912, 'steps': 93660, 'loss/train': 1.152394413948059} 08/31/2021 06:12:31 - INFO - __main__ - Step 93662: {'lr': 0.00015845753920719198, 'samples': 17983104, 'steps': 93661, 'loss/train': 0.7645984292030334} 08/31/2021 06:12:32 - INFO - __main__ - Step 93663: {'lr': 0.00015845260104729007, 'samples': 17983296, 'steps': 93662, 'loss/train': 0.018731223419308662} 08/31/2021 06:12:33 - INFO - __main__ - Step 93664: {'lr': 0.00015844766292863802, 'samples': 17983488, 'steps': 93663, 'loss/train': 0.018175696954131126} 08/31/2021 06:12:34 - INFO - __main__ - Step 93665: {'lr': 0.00015844272485123807, 'samples': 17983680, 'steps': 93664, 'loss/train': 1.1308456659317017} 08/31/2021 06:12:34 - INFO - __main__ - Step 93666: {'lr': 0.00015843778681509234, 'samples': 17983872, 'steps': 93665, 'loss/train': 0.5808584094047546} 08/31/2021 06:12:34 - INFO - __main__ - Step 93667: {'lr': 0.0001584328488202032, 'samples': 17984064, 'steps': 93666, 'loss/train': 1.029619574546814} 08/31/2021 06:12:35 - INFO - __main__ - Step 93668: {'lr': 0.0001584279108665728, 'samples': 17984256, 'steps': 93667, 'loss/train': 1.7965542078018188} 08/31/2021 06:12:36 - INFO - __main__ - Step 93669: {'lr': 0.00015842297295420336, 'samples': 17984448, 'steps': 93668, 'loss/train': 1.506516456604004} 08/31/2021 06:12:37 - INFO - __main__ - Step 93670: {'lr': 0.0001584180350830971, 'samples': 17984640, 'steps': 93669, 'loss/train': 2.145983934402466} 08/31/2021 06:12:37 - INFO - __main__ - Step 93671: {'lr': 0.00015841309725325627, 'samples': 17984832, 'steps': 93670, 'loss/train': 1.1798456907272339} 08/31/2021 06:12:37 - INFO - __main__ - Step 93672: {'lr': 0.0001584081594646831, 'samples': 17985024, 'steps': 93671, 'loss/train': 1.3811589479446411} 08/31/2021 06:12:38 - INFO - __main__ - Step 93673: {'lr': 0.0001584032217173798, 'samples': 17985216, 'steps': 93672, 'loss/train': 1.0134471654891968} 08/31/2021 06:12:39 - INFO - __main__ - Step 93674: {'lr': 0.0001583982840113486, 'samples': 17985408, 'steps': 93673, 'loss/train': 0.7743900418281555} 08/31/2021 06:12:40 - INFO - __main__ - Step 93675: {'lr': 0.0001583933463465918, 'samples': 17985600, 'steps': 93674, 'loss/train': 1.7337327003479004} 08/31/2021 06:12:40 - INFO - __main__ - Step 93676: {'lr': 0.00015838840872311146, 'samples': 17985792, 'steps': 93675, 'loss/train': 1.5291035175323486} 08/31/2021 06:12:41 - INFO - __main__ - Step 93677: {'lr': 0.00015838347114090985, 'samples': 17985984, 'steps': 93676, 'loss/train': 1.1544811725616455} 08/31/2021 06:12:41 - INFO - __main__ - Step 93678: {'lr': 0.00015837853359998926, 'samples': 17986176, 'steps': 93677, 'loss/train': 0.5960312485694885} 08/31/2021 06:12:41 - INFO - __main__ - Step 93679: {'lr': 0.0001583735961003519, 'samples': 17986368, 'steps': 93678, 'loss/train': 0.7466101050376892} 08/31/2021 06:12:43 - INFO - __main__ - Step 93680: {'lr': 0.00015836865864199995, 'samples': 17986560, 'steps': 93679, 'loss/train': 1.0922483205795288} 08/31/2021 06:12:43 - INFO - __main__ - Step 93681: {'lr': 0.0001583637212249357, 'samples': 17986752, 'steps': 93680, 'loss/train': 1.0139988660812378} 08/31/2021 06:12:43 - INFO - __main__ - Step 93682: {'lr': 0.00015835878384916135, 'samples': 17986944, 'steps': 93681, 'loss/train': 1.3611828088760376} 08/31/2021 06:12:44 - INFO - __main__ - Step 93683: {'lr': 0.0001583538465146791, 'samples': 17987136, 'steps': 93682, 'loss/train': 0.7398980855941772} 08/31/2021 06:12:44 - INFO - __main__ - Step 93684: {'lr': 0.0001583489092214912, 'samples': 17987328, 'steps': 93683, 'loss/train': 0.9525290727615356} 08/31/2021 06:12:46 - INFO - __main__ - Step 93685: {'lr': 0.00015834397196959986, 'samples': 17987520, 'steps': 93684, 'loss/train': 1.0813124179840088} 08/31/2021 06:12:46 - INFO - __main__ - Step 93686: {'lr': 0.0001583390347590073, 'samples': 17987712, 'steps': 93685, 'loss/train': 1.3724044561386108} 08/31/2021 06:12:46 - INFO - __main__ - Step 93687: {'lr': 0.0001583340975897158, 'samples': 17987904, 'steps': 93686, 'loss/train': 1.4766737222671509} 08/31/2021 06:12:47 - INFO - __main__ - Step 93688: {'lr': 0.0001583291604617276, 'samples': 17988096, 'steps': 93687, 'loss/train': 1.2112882137298584} 08/31/2021 06:12:47 - INFO - __main__ - Step 93689: {'lr': 0.00015832422337504475, 'samples': 17988288, 'steps': 93688, 'loss/train': 1.2185535430908203} 08/31/2021 06:12:49 - INFO - __main__ - Step 93690: {'lr': 0.00015831928632966964, 'samples': 17988480, 'steps': 93689, 'loss/train': 1.0962584018707275} 08/31/2021 06:12:50 - INFO - __main__ - Step 93691: {'lr': 0.00015831434932560442, 'samples': 17988672, 'steps': 93690, 'loss/train': 1.276051640510559} 08/31/2021 06:12:50 - INFO - __main__ - Step 93692: {'lr': 0.00015830941236285134, 'samples': 17988864, 'steps': 93691, 'loss/train': 1.0489623546600342} 08/31/2021 06:12:50 - INFO - __main__ - Step 93693: {'lr': 0.00015830447544141262, 'samples': 17989056, 'steps': 93692, 'loss/train': 0.9979175329208374} 08/31/2021 06:12:51 - INFO - __main__ - Step 93694: {'lr': 0.00015829953856129052, 'samples': 17989248, 'steps': 93693, 'loss/train': 0.6863805651664734} 08/31/2021 06:12:51 - INFO - __main__ - Step 93695: {'lr': 0.00015829460172248723, 'samples': 17989440, 'steps': 93694, 'loss/train': 0.23089350759983063} 08/31/2021 06:12:53 - INFO - __main__ - Step 93696: {'lr': 0.0001582896649250049, 'samples': 17989632, 'steps': 93695, 'loss/train': 0.04419614374637604} 08/31/2021 06:12:54 - INFO - __main__ - Step 93697: {'lr': 0.00015828472816884593, 'samples': 17989824, 'steps': 93696, 'loss/train': 1.092850685119629} 08/31/2021 06:12:54 - INFO - __main__ - Step 93698: {'lr': 0.0001582797914540124, 'samples': 17990016, 'steps': 93697, 'loss/train': 0.7207590341567993} 08/31/2021 06:12:54 - INFO - __main__ - Step 93699: {'lr': 0.00015827485478050657, 'samples': 17990208, 'steps': 93698, 'loss/train': 0.7966042160987854} 08/31/2021 06:12:55 - INFO - __main__ - Step 93700: {'lr': 0.0001582699181483307, 'samples': 17990400, 'steps': 93699, 'loss/train': 0.030543586239218712} 08/31/2021 06:12:56 - INFO - __main__ - Step 93701: {'lr': 0.00015826498155748698, 'samples': 17990592, 'steps': 93700, 'loss/train': 0.7478623986244202} 08/31/2021 06:12:57 - INFO - __main__ - Step 93702: {'lr': 0.00015826004500797775, 'samples': 17990784, 'steps': 93701, 'loss/train': 0.5467161536216736} 08/31/2021 06:12:57 - INFO - __main__ - Step 93703: {'lr': 0.000158255108499805, 'samples': 17990976, 'steps': 93702, 'loss/train': 1.3760408163070679} 08/31/2021 06:12:57 - INFO - __main__ - Step 93704: {'lr': 0.0001582501720329711, 'samples': 17991168, 'steps': 93703, 'loss/train': 0.5308222770690918} 08/31/2021 06:12:58 - INFO - __main__ - Step 93705: {'lr': 0.00015824523560747827, 'samples': 17991360, 'steps': 93704, 'loss/train': 2.387446403503418} 08/31/2021 06:12:59 - INFO - __main__ - Step 93706: {'lr': 0.0001582402992233287, 'samples': 17991552, 'steps': 93705, 'loss/train': 1.3909724950790405} 08/31/2021 06:13:00 - INFO - __main__ - Step 93707: {'lr': 0.00015823536288052465, 'samples': 17991744, 'steps': 93706, 'loss/train': 1.1028857231140137} 08/31/2021 06:13:00 - INFO - __main__ - Step 93708: {'lr': 0.00015823042657906833, 'samples': 17991936, 'steps': 93707, 'loss/train': 1.5675069093704224} 08/31/2021 06:13:00 - INFO - __main__ - Step 93709: {'lr': 0.00015822549031896196, 'samples': 17992128, 'steps': 93708, 'loss/train': 0.8429660797119141} 08/31/2021 06:13:01 - INFO - __main__ - Step 93710: {'lr': 0.0001582205541002078, 'samples': 17992320, 'steps': 93709, 'loss/train': 1.1901650428771973} 08/31/2021 06:13:02 - INFO - __main__ - Step 93711: {'lr': 0.00015821561792280796, 'samples': 17992512, 'steps': 93710, 'loss/train': 0.882412850856781} 08/31/2021 06:13:03 - INFO - __main__ - Step 93712: {'lr': 0.0001582106817867648, 'samples': 17992704, 'steps': 93711, 'loss/train': 1.6472184658050537} 08/31/2021 06:13:03 - INFO - __main__ - Step 93713: {'lr': 0.0001582057456920805, 'samples': 17992896, 'steps': 93712, 'loss/train': 0.15603569149971008} 08/31/2021 06:13:04 - INFO - __main__ - Step 93714: {'lr': 0.00015820080963875727, 'samples': 17993088, 'steps': 93713, 'loss/train': 0.6134287118911743} 08/31/2021 06:13:04 - INFO - __main__ - Step 93715: {'lr': 0.00015819587362679745, 'samples': 17993280, 'steps': 93714, 'loss/train': 1.1718487739562988} 08/31/2021 06:13:04 - INFO - __main__ - Step 93716: {'lr': 0.000158190937656203, 'samples': 17993472, 'steps': 93715, 'loss/train': 0.6274308562278748} 08/31/2021 06:13:06 - INFO - __main__ - Step 93717: {'lr': 0.00015818600172697633, 'samples': 17993664, 'steps': 93716, 'loss/train': 0.7974156141281128} 08/31/2021 06:13:07 - INFO - __main__ - Step 93718: {'lr': 0.00015818106583911963, 'samples': 17993856, 'steps': 93717, 'loss/train': 0.07972376048564911} 08/31/2021 06:13:07 - INFO - __main__ - Step 93719: {'lr': 0.00015817612999263514, 'samples': 17994048, 'steps': 93718, 'loss/train': 1.419284701347351} 08/31/2021 06:13:07 - INFO - __main__ - Step 93720: {'lr': 0.00015817119418752503, 'samples': 17994240, 'steps': 93719, 'loss/train': 0.09131266176700592} 08/31/2021 06:13:08 - INFO - __main__ - Step 93721: {'lr': 0.0001581662584237916, 'samples': 17994432, 'steps': 93720, 'loss/train': 0.5253318548202515} 08/31/2021 06:13:09 - INFO - __main__ - Step 93722: {'lr': 0.000158161322701437, 'samples': 17994624, 'steps': 93721, 'loss/train': 0.8269578218460083} 08/31/2021 06:13:10 - INFO - __main__ - Step 93723: {'lr': 0.00015815638702046354, 'samples': 17994816, 'steps': 93722, 'loss/train': 1.490041732788086} 08/31/2021 06:13:10 - INFO - __main__ - Step 93724: {'lr': 0.00015815145138087336, 'samples': 17995008, 'steps': 93723, 'loss/train': 1.3964425325393677} 08/31/2021 06:13:10 - INFO - __main__ - Step 93725: {'lr': 0.00015814651578266873, 'samples': 17995200, 'steps': 93724, 'loss/train': 0.5936716198921204} 08/31/2021 06:13:11 - INFO - __main__ - Step 93726: {'lr': 0.00015814158022585184, 'samples': 17995392, 'steps': 93725, 'loss/train': 1.2864480018615723} 08/31/2021 06:13:12 - INFO - __main__ - Step 93727: {'lr': 0.00015813664471042498, 'samples': 17995584, 'steps': 93726, 'loss/train': 0.6549511551856995} 08/31/2021 06:13:13 - INFO - __main__ - Step 93728: {'lr': 0.00015813170923639042, 'samples': 17995776, 'steps': 93727, 'loss/train': 1.1654109954833984} 08/31/2021 06:13:13 - INFO - __main__ - Step 93729: {'lr': 0.00015812677380375019, 'samples': 17995968, 'steps': 93728, 'loss/train': 0.95784592628479} 08/31/2021 06:13:13 - INFO - __main__ - Step 93730: {'lr': 0.0001581218384125066, 'samples': 17996160, 'steps': 93729, 'loss/train': 2.0560221672058105} 08/31/2021 06:13:14 - INFO - __main__ - Step 93731: {'lr': 0.00015811690306266187, 'samples': 17996352, 'steps': 93730, 'loss/train': 1.0078089237213135} 08/31/2021 06:13:15 - INFO - __main__ - Step 93732: {'lr': 0.0001581119677542183, 'samples': 17996544, 'steps': 93731, 'loss/train': 0.9556013941764832} 08/31/2021 06:13:16 - INFO - __main__ - Step 93733: {'lr': 0.00015810703248717804, 'samples': 17996736, 'steps': 93732, 'loss/train': 1.3574234247207642} 08/31/2021 06:13:16 - INFO - __main__ - Step 93734: {'lr': 0.00015810209726154333, 'samples': 17996928, 'steps': 93733, 'loss/train': 1.515020728111267} 08/31/2021 06:13:16 - INFO - __main__ - Step 93735: {'lr': 0.00015809716207731639, 'samples': 17997120, 'steps': 93734, 'loss/train': 1.4572733640670776} 08/31/2021 06:13:17 - INFO - __main__ - Step 93736: {'lr': 0.00015809222693449943, 'samples': 17997312, 'steps': 93735, 'loss/train': 1.8532471656799316} 08/31/2021 06:13:18 - INFO - __main__ - Step 93737: {'lr': 0.00015808729183309472, 'samples': 17997504, 'steps': 93736, 'loss/train': 1.0251774787902832} 08/31/2021 06:13:19 - INFO - __main__ - Step 93738: {'lr': 0.00015808235677310448, 'samples': 17997696, 'steps': 93737, 'loss/train': 1.1241215467453003} 08/31/2021 06:13:19 - INFO - __main__ - Step 93739: {'lr': 0.0001580774217545309, 'samples': 17997888, 'steps': 93738, 'loss/train': 1.1565052270889282} 08/31/2021 06:13:19 - INFO - __main__ - Step 93740: {'lr': 0.00015807248677737618, 'samples': 17998080, 'steps': 93739, 'loss/train': 1.5917410850524902} 08/31/2021 06:13:20 - INFO - __main__ - Step 93741: {'lr': 0.00015806755184164268, 'samples': 17998272, 'steps': 93740, 'loss/train': 1.4937046766281128} 08/31/2021 06:13:21 - INFO - __main__ - Step 93742: {'lr': 0.0001580626169473325, 'samples': 17998464, 'steps': 93741, 'loss/train': 0.5699399709701538} 08/31/2021 06:13:22 - INFO - __main__ - Step 93743: {'lr': 0.0001580576820944478, 'samples': 17998656, 'steps': 93742, 'loss/train': 1.4162105321884155} 08/31/2021 06:13:22 - INFO - __main__ - Step 93744: {'lr': 0.00015805274728299096, 'samples': 17998848, 'steps': 93743, 'loss/train': 1.2958729267120361} 08/31/2021 06:13:22 - INFO - __main__ - Step 93745: {'lr': 0.00015804781251296408, 'samples': 17999040, 'steps': 93744, 'loss/train': 0.7108046412467957} 08/31/2021 06:13:23 - INFO - __main__ - Step 93746: {'lr': 0.00015804287778436947, 'samples': 17999232, 'steps': 93745, 'loss/train': 1.358054518699646} 08/31/2021 06:13:23 - INFO - __main__ - Step 93747: {'lr': 0.00015803794309720927, 'samples': 17999424, 'steps': 93746, 'loss/train': 0.7425488233566284} 08/31/2021 06:13:25 - INFO - __main__ - Step 93748: {'lr': 0.0001580330084514858, 'samples': 17999616, 'steps': 93747, 'loss/train': 1.2503598928451538} 08/31/2021 06:13:25 - INFO - __main__ - Step 93749: {'lr': 0.00015802807384720125, 'samples': 17999808, 'steps': 93748, 'loss/train': 1.6664438247680664} 08/31/2021 06:13:26 - INFO - __main__ - Step 93750: {'lr': 0.00015802313928435778, 'samples': 18000000, 'steps': 93749, 'loss/train': 0.8105935454368591} 08/31/2021 06:13:26 - INFO - __main__ - Step 93751: {'lr': 0.0001580182047629577, 'samples': 18000192, 'steps': 93750, 'loss/train': 1.4156931638717651} 08/31/2021 06:13:26 - INFO - __main__ - Step 93752: {'lr': 0.0001580132702830032, 'samples': 18000384, 'steps': 93751, 'loss/train': 1.3349334001541138} 08/31/2021 06:13:28 - INFO - __main__ - Step 93753: {'lr': 0.00015800833584449654, 'samples': 18000576, 'steps': 93752, 'loss/train': 1.3795894384384155} 08/31/2021 06:13:29 - INFO - __main__ - Step 93754: {'lr': 0.00015800340144743984, 'samples': 18000768, 'steps': 93753, 'loss/train': 0.07133051753044128} 08/31/2021 06:13:29 - INFO - __main__ - Step 93755: {'lr': 0.00015799846709183547, 'samples': 18000960, 'steps': 93754, 'loss/train': 0.14617682993412018} 08/31/2021 06:13:29 - INFO - __main__ - Step 93756: {'lr': 0.00015799353277768546, 'samples': 18001152, 'steps': 93755, 'loss/train': 0.7794240713119507} 08/31/2021 06:13:30 - INFO - __main__ - Step 93757: {'lr': 0.0001579885985049922, 'samples': 18001344, 'steps': 93756, 'loss/train': 1.4460029602050781} 08/31/2021 06:13:32 - INFO - __main__ - Step 93758: {'lr': 0.00015798366427375785, 'samples': 18001536, 'steps': 93757, 'loss/train': 1.3090826272964478} 08/31/2021 06:13:32 - INFO - __main__ - Step 93759: {'lr': 0.0001579787300839846, 'samples': 18001728, 'steps': 93758, 'loss/train': 0.02874067984521389} 08/31/2021 06:13:33 - INFO - __main__ - Step 93760: {'lr': 0.0001579737959356748, 'samples': 18001920, 'steps': 93759, 'loss/train': 0.05706647410988808} 08/31/2021 06:13:33 - INFO - __main__ - Step 93761: {'lr': 0.00015796886182883053, 'samples': 18002112, 'steps': 93760, 'loss/train': 1.4167193174362183} 08/31/2021 06:13:33 - INFO - __main__ - Step 93762: {'lr': 0.00015796392776345412, 'samples': 18002304, 'steps': 93761, 'loss/train': 1.256723165512085} 08/31/2021 06:13:34 - INFO - __main__ - Step 93763: {'lr': 0.0001579589937395477, 'samples': 18002496, 'steps': 93762, 'loss/train': 1.1486128568649292} 08/31/2021 06:13:35 - INFO - __main__ - Step 93764: {'lr': 0.0001579540597571135, 'samples': 18002688, 'steps': 93763, 'loss/train': 1.266448974609375} 08/31/2021 06:13:35 - INFO - __main__ - Step 93765: {'lr': 0.00015794912581615383, 'samples': 18002880, 'steps': 93764, 'loss/train': 1.4678008556365967} 08/31/2021 06:13:36 - INFO - __main__ - Step 93766: {'lr': 0.00015794419191667087, 'samples': 18003072, 'steps': 93765, 'loss/train': 1.1777528524398804} 08/31/2021 06:13:36 - INFO - __main__ - Step 93767: {'lr': 0.00015793925805866684, 'samples': 18003264, 'steps': 93766, 'loss/train': 1.4526478052139282} 08/31/2021 06:13:37 - INFO - __main__ - Step 93768: {'lr': 0.0001579343242421439, 'samples': 18003456, 'steps': 93767, 'loss/train': 1.742382287979126} 08/31/2021 06:13:38 - INFO - __main__ - Step 93769: {'lr': 0.0001579293904671044, 'samples': 18003648, 'steps': 93768, 'loss/train': 0.6612167954444885} 08/31/2021 06:13:39 - INFO - __main__ - Step 93770: {'lr': 0.0001579244567335505, 'samples': 18003840, 'steps': 93769, 'loss/train': 1.2910724878311157} 08/31/2021 06:13:39 - INFO - __main__ - Step 93771: {'lr': 0.00015791952304148438, 'samples': 18004032, 'steps': 93770, 'loss/train': 1.1496083736419678} 08/31/2021 06:13:39 - INFO - __main__ - Step 93772: {'lr': 0.0001579145893909083, 'samples': 18004224, 'steps': 93771, 'loss/train': 1.2289645671844482} 08/31/2021 06:13:40 - INFO - __main__ - Step 93773: {'lr': 0.00015790965578182456, 'samples': 18004416, 'steps': 93772, 'loss/train': 0.5794202089309692} 08/31/2021 06:13:40 - INFO - __main__ - Step 93774: {'lr': 0.00015790472221423525, 'samples': 18004608, 'steps': 93773, 'loss/train': 0.9784232378005981} 08/31/2021 06:13:42 - INFO - __main__ - Step 93775: {'lr': 0.00015789978868814265, 'samples': 18004800, 'steps': 93774, 'loss/train': 1.5997686386108398} 08/31/2021 06:13:42 - INFO - __main__ - Step 93776: {'lr': 0.00015789485520354896, 'samples': 18004992, 'steps': 93775, 'loss/train': 1.417463779449463} 08/31/2021 06:13:42 - INFO - __main__ - Step 93777: {'lr': 0.00015788992176045643, 'samples': 18005184, 'steps': 93776, 'loss/train': 1.4283877611160278} 08/31/2021 06:13:43 - INFO - __main__ - Step 93778: {'lr': 0.0001578849883588673, 'samples': 18005376, 'steps': 93777, 'loss/train': 0.9302576184272766} 08/31/2021 06:13:43 - INFO - __main__ - Step 93779: {'lr': 0.00015788005499878377, 'samples': 18005568, 'steps': 93778, 'loss/train': 0.1509140431880951} 08/31/2021 06:13:45 - INFO - __main__ - Step 93780: {'lr': 0.00015787512168020807, 'samples': 18005760, 'steps': 93779, 'loss/train': 1.3273347616195679} 08/31/2021 06:13:45 - INFO - __main__ - Step 93781: {'lr': 0.00015787018840314238, 'samples': 18005952, 'steps': 93780, 'loss/train': 0.9273046255111694} 08/31/2021 06:13:45 - INFO - __main__ - Step 93782: {'lr': 0.00015786525516758905, 'samples': 18006144, 'steps': 93781, 'loss/train': 1.6393893957138062} 08/31/2021 06:13:46 - INFO - __main__ - Step 93783: {'lr': 0.00015786032197355015, 'samples': 18006336, 'steps': 93782, 'loss/train': 1.3771837949752808} 08/31/2021 06:13:46 - INFO - __main__ - Step 93784: {'lr': 0.00015785538882102804, 'samples': 18006528, 'steps': 93783, 'loss/train': 0.6240729093551636} 08/31/2021 06:13:48 - INFO - __main__ - Step 93785: {'lr': 0.00015785045571002483, 'samples': 18006720, 'steps': 93784, 'loss/train': 1.396080732345581} 08/31/2021 06:13:48 - INFO - __main__ - Step 93786: {'lr': 0.00015784552264054273, 'samples': 18006912, 'steps': 93785, 'loss/train': 1.2579597234725952} 08/31/2021 06:13:49 - INFO - __main__ - Step 93787: {'lr': 0.000157840589612584, 'samples': 18007104, 'steps': 93786, 'loss/train': 1.7071239948272705} 08/31/2021 06:13:49 - INFO - __main__ - Step 93788: {'lr': 0.00015783565662615096, 'samples': 18007296, 'steps': 93787, 'loss/train': 1.0582720041275024} 08/31/2021 06:13:49 - INFO - __main__ - Step 93789: {'lr': 0.0001578307236812457, 'samples': 18007488, 'steps': 93788, 'loss/train': 0.8565037846565247} 08/31/2021 06:13:51 - INFO - __main__ - Step 93790: {'lr': 0.0001578257907778705, 'samples': 18007680, 'steps': 93789, 'loss/train': 0.03168879821896553} 08/31/2021 06:13:52 - INFO - __main__ - Step 93791: {'lr': 0.00015782085791602758, 'samples': 18007872, 'steps': 93790, 'loss/train': 1.1030184030532837} 08/31/2021 06:13:52 - INFO - __main__ - Step 93792: {'lr': 0.0001578159250957192, 'samples': 18008064, 'steps': 93791, 'loss/train': 0.7577894926071167} 08/31/2021 06:13:52 - INFO - __main__ - Step 93793: {'lr': 0.00015781099231694745, 'samples': 18008256, 'steps': 93792, 'loss/train': 0.016337696462869644} 08/31/2021 06:13:53 - INFO - __main__ - Step 93794: {'lr': 0.00015780605957971472, 'samples': 18008448, 'steps': 93793, 'loss/train': 0.016995815560221672} 08/31/2021 06:13:53 - INFO - __main__ - Step 93795: {'lr': 0.00015780112688402312, 'samples': 18008640, 'steps': 93794, 'loss/train': 1.3589699268341064} 08/31/2021 06:13:54 - INFO - __main__ - Step 93796: {'lr': 0.000157796194229875, 'samples': 18008832, 'steps': 93795, 'loss/train': 1.4497997760772705} 08/31/2021 06:13:55 - INFO - __main__ - Step 93797: {'lr': 0.00015779126161727245, 'samples': 18009024, 'steps': 93796, 'loss/train': 1.1274809837341309} 08/31/2021 06:13:55 - INFO - __main__ - Step 93798: {'lr': 0.0001577863290462177, 'samples': 18009216, 'steps': 93797, 'loss/train': 1.4609397649765015} 08/31/2021 06:13:56 - INFO - __main__ - Step 93799: {'lr': 0.000157781396516713, 'samples': 18009408, 'steps': 93798, 'loss/train': 1.1310445070266724} 08/31/2021 06:13:56 - INFO - __main__ - Step 93800: {'lr': 0.00015777646402876058, 'samples': 18009600, 'steps': 93799, 'loss/train': 0.23421946167945862} 08/31/2021 06:13:58 - INFO - __main__ - Step 93801: {'lr': 0.00015777153158236267, 'samples': 18009792, 'steps': 93800, 'loss/train': 1.2076473236083984} 08/31/2021 06:13:58 - INFO - __main__ - Step 93802: {'lr': 0.00015776659917752148, 'samples': 18009984, 'steps': 93801, 'loss/train': 1.26925790309906} 08/31/2021 06:13:59 - INFO - __main__ - Step 93803: {'lr': 0.00015776166681423927, 'samples': 18010176, 'steps': 93802, 'loss/train': 0.9457453489303589} 08/31/2021 06:13:59 - INFO - __main__ - Step 93804: {'lr': 0.00015775673449251816, 'samples': 18010368, 'steps': 93803, 'loss/train': 0.9240320920944214} 08/31/2021 06:13:59 - INFO - __main__ - Step 93805: {'lr': 0.00015775180221236048, 'samples': 18010560, 'steps': 93804, 'loss/train': 0.9493114352226257} 08/31/2021 06:14:01 - INFO - __main__ - Step 93806: {'lr': 0.0001577468699737684, 'samples': 18010752, 'steps': 93805, 'loss/train': 1.1334843635559082} 08/31/2021 06:14:02 - INFO - __main__ - Step 93807: {'lr': 0.0001577419377767442, 'samples': 18010944, 'steps': 93806, 'loss/train': 1.373408317565918} 08/31/2021 06:14:02 - INFO - __main__ - Step 93808: {'lr': 0.00015773700562129, 'samples': 18011136, 'steps': 93807, 'loss/train': 0.8935487866401672} 08/31/2021 06:14:03 - INFO - __main__ - Step 93809: {'lr': 0.00015773207350740825, 'samples': 18011328, 'steps': 93808, 'loss/train': 1.245800495147705} 08/31/2021 06:14:03 - INFO - __main__ - Step 93810: {'lr': 0.00015772714143510086, 'samples': 18011520, 'steps': 93809, 'loss/train': 1.3673486709594727} 08/31/2021 06:14:04 - INFO - __main__ - Step 93811: {'lr': 0.0001577222094043702, 'samples': 18011712, 'steps': 93810, 'loss/train': 0.3651045858860016} 08/31/2021 06:14:05 - INFO - __main__ - Step 93812: {'lr': 0.0001577172774152185, 'samples': 18011904, 'steps': 93811, 'loss/train': 1.3995925188064575} 08/31/2021 06:14:05 - INFO - __main__ - Step 93813: {'lr': 0.00015771234546764796, 'samples': 18012096, 'steps': 93812, 'loss/train': 1.191645622253418} 08/31/2021 06:14:06 - INFO - __main__ - Step 93814: {'lr': 0.0001577074135616608, 'samples': 18012288, 'steps': 93813, 'loss/train': 0.04132567718625069} 08/31/2021 06:14:06 - INFO - __main__ - Step 93815: {'lr': 0.00015770248169725927, 'samples': 18012480, 'steps': 93814, 'loss/train': 1.4868972301483154} 08/31/2021 06:14:07 - INFO - __main__ - Step 93816: {'lr': 0.00015769754987444556, 'samples': 18012672, 'steps': 93815, 'loss/train': 0.9884578585624695} 08/31/2021 06:14:08 - INFO - __main__ - Step 93817: {'lr': 0.00015769261809322194, 'samples': 18012864, 'steps': 93816, 'loss/train': 1.0586955547332764} 08/31/2021 06:14:08 - INFO - __main__ - Step 93818: {'lr': 0.0001576876863535906, 'samples': 18013056, 'steps': 93817, 'loss/train': 3.025338649749756} 08/31/2021 06:14:09 - INFO - __main__ - Step 93819: {'lr': 0.00015768275465555376, 'samples': 18013248, 'steps': 93818, 'loss/train': 0.830098032951355} 08/31/2021 06:14:09 - INFO - __main__ - Step 93820: {'lr': 0.00015767782299911366, 'samples': 18013440, 'steps': 93819, 'loss/train': 0.5152079463005066} 08/31/2021 06:14:09 - INFO - __main__ - Step 93821: {'lr': 0.00015767289138427247, 'samples': 18013632, 'steps': 93820, 'loss/train': 0.7344360947608948} 08/31/2021 06:14:11 - INFO - __main__ - Step 93822: {'lr': 0.00015766795981103247, 'samples': 18013824, 'steps': 93821, 'loss/train': 0.8650125861167908} 08/31/2021 06:14:11 - INFO - __main__ - Step 93823: {'lr': 0.00015766302827939594, 'samples': 18014016, 'steps': 93822, 'loss/train': 0.3569227457046509} 08/31/2021 06:14:12 - INFO - __main__ - Step 93824: {'lr': 0.00015765809678936496, 'samples': 18014208, 'steps': 93823, 'loss/train': 0.14570721983909607} 08/31/2021 06:14:12 - INFO - __main__ - Step 93825: {'lr': 0.00015765316534094181, 'samples': 18014400, 'steps': 93824, 'loss/train': 0.6863741874694824} 08/31/2021 06:14:13 - INFO - __main__ - Step 93826: {'lr': 0.0001576482339341287, 'samples': 18014592, 'steps': 93825, 'loss/train': 0.8951388597488403} 08/31/2021 06:14:14 - INFO - __main__ - Step 93827: {'lr': 0.0001576433025689279, 'samples': 18014784, 'steps': 93826, 'loss/train': 1.4926577806472778} 08/31/2021 06:14:15 - INFO - __main__ - Step 93828: {'lr': 0.00015763837124534158, 'samples': 18014976, 'steps': 93827, 'loss/train': 1.4058434963226318} 08/31/2021 06:14:15 - INFO - __main__ - Step 93829: {'lr': 0.00015763343996337198, 'samples': 18015168, 'steps': 93828, 'loss/train': 1.2736152410507202} 08/31/2021 06:14:15 - INFO - __main__ - Step 93830: {'lr': 0.00015762850872302135, 'samples': 18015360, 'steps': 93829, 'loss/train': 1.1387135982513428} 08/31/2021 06:14:16 - INFO - __main__ - Step 93831: {'lr': 0.00015762357752429186, 'samples': 18015552, 'steps': 93830, 'loss/train': 1.2059816122055054} 08/31/2021 06:14:17 - INFO - __main__ - Step 93832: {'lr': 0.00015761864636718576, 'samples': 18015744, 'steps': 93831, 'loss/train': 1.246033787727356} 08/31/2021 06:14:17 - INFO - __main__ - Step 93833: {'lr': 0.00015761371525170533, 'samples': 18015936, 'steps': 93832, 'loss/train': 1.1822208166122437} 08/31/2021 06:14:18 - INFO - __main__ - Step 93834: {'lr': 0.00015760878417785267, 'samples': 18016128, 'steps': 93833, 'loss/train': 1.8563568592071533} 08/31/2021 06:14:18 - INFO - __main__ - Step 93835: {'lr': 0.00015760385314563007, 'samples': 18016320, 'steps': 93834, 'loss/train': 1.1305814981460571} 08/31/2021 06:14:19 - INFO - __main__ - Step 93836: {'lr': 0.0001575989221550399, 'samples': 18016512, 'steps': 93835, 'loss/train': 1.3579354286193848} 08/31/2021 06:14:20 - INFO - __main__ - Step 93837: {'lr': 0.0001575939912060841, 'samples': 18016704, 'steps': 93836, 'loss/train': 1.205001950263977} 08/31/2021 06:14:21 - INFO - __main__ - Step 93838: {'lr': 0.000157589060298765, 'samples': 18016896, 'steps': 93837, 'loss/train': 1.2524349689483643} 08/31/2021 06:14:21 - INFO - __main__ - Step 93839: {'lr': 0.00015758412943308486, 'samples': 18017088, 'steps': 93838, 'loss/train': 1.1045219898223877} 08/31/2021 06:14:21 - INFO - __main__ - Step 93840: {'lr': 0.00015757919860904588, 'samples': 18017280, 'steps': 93839, 'loss/train': 0.9568340182304382} 08/31/2021 06:14:22 - INFO - __main__ - Step 93841: {'lr': 0.0001575742678266503, 'samples': 18017472, 'steps': 93840, 'loss/train': 1.4284982681274414} 08/31/2021 06:14:23 - INFO - __main__ - Step 93842: {'lr': 0.00015756933708590033, 'samples': 18017664, 'steps': 93841, 'loss/train': 0.97968989610672} 08/31/2021 06:14:24 - INFO - __main__ - Step 93843: {'lr': 0.00015756440638679817, 'samples': 18017856, 'steps': 93842, 'loss/train': 0.9504639506340027} 08/31/2021 06:14:24 - INFO - __main__ - Step 93844: {'lr': 0.0001575594757293461, 'samples': 18018048, 'steps': 93843, 'loss/train': 1.2072347402572632} 08/31/2021 06:14:24 - INFO - __main__ - Step 93845: {'lr': 0.00015755454511354625, 'samples': 18018240, 'steps': 93844, 'loss/train': 1.3997963666915894} 08/31/2021 06:14:25 - INFO - __main__ - Step 93846: {'lr': 0.0001575496145394009, 'samples': 18018432, 'steps': 93845, 'loss/train': 1.1653399467468262} 08/31/2021 06:14:25 - INFO - __main__ - Step 93847: {'lr': 0.0001575446840069123, 'samples': 18018624, 'steps': 93846, 'loss/train': 1.4712228775024414} 08/31/2021 06:14:27 - INFO - __main__ - Step 93848: {'lr': 0.00015753975351608262, 'samples': 18018816, 'steps': 93847, 'loss/train': 1.4055887460708618} 08/31/2021 06:14:27 - INFO - __main__ - Step 93849: {'lr': 0.00015753482306691424, 'samples': 18019008, 'steps': 93848, 'loss/train': 0.4238435924053192} 08/31/2021 06:14:28 - INFO - __main__ - Step 93850: {'lr': 0.0001575298926594091, 'samples': 18019200, 'steps': 93849, 'loss/train': 1.572007417678833} 08/31/2021 06:14:28 - INFO - __main__ - Step 93851: {'lr': 0.00015752496229356957, 'samples': 18019392, 'steps': 93850, 'loss/train': 0.9894062280654907} 08/31/2021 06:14:28 - INFO - __main__ - Step 93852: {'lr': 0.00015752003196939788, 'samples': 18019584, 'steps': 93851, 'loss/train': 0.03625176101922989} 08/31/2021 06:14:30 - INFO - __main__ - Step 93853: {'lr': 0.00015751510168689623, 'samples': 18019776, 'steps': 93852, 'loss/train': 1.6976629495620728} 08/31/2021 06:14:30 - INFO - __main__ - Step 93854: {'lr': 0.00015751017144606682, 'samples': 18019968, 'steps': 93853, 'loss/train': 0.8856787085533142} 08/31/2021 06:14:31 - INFO - __main__ - Step 93855: {'lr': 0.00015750524124691196, 'samples': 18020160, 'steps': 93854, 'loss/train': 0.944564700126648} 08/31/2021 06:14:31 - INFO - __main__ - Step 93856: {'lr': 0.00015750031108943373, 'samples': 18020352, 'steps': 93855, 'loss/train': 1.1770848035812378} 08/31/2021 06:14:31 - INFO - __main__ - Step 93857: {'lr': 0.00015749538097363454, 'samples': 18020544, 'steps': 93856, 'loss/train': 0.8379120230674744} 08/31/2021 06:14:33 - INFO - __main__ - Step 93858: {'lr': 0.0001574904508995164, 'samples': 18020736, 'steps': 93857, 'loss/train': 1.1905484199523926} 08/31/2021 06:14:34 - INFO - __main__ - Step 93859: {'lr': 0.00015748552086708169, 'samples': 18020928, 'steps': 93858, 'loss/train': 1.1083518266677856} 08/31/2021 06:14:34 - INFO - __main__ - Step 93860: {'lr': 0.00015748059087633255, 'samples': 18021120, 'steps': 93859, 'loss/train': 1.4277223348617554} 08/31/2021 06:14:34 - INFO - __main__ - Step 93861: {'lr': 0.00015747566092727126, 'samples': 18021312, 'steps': 93860, 'loss/train': 1.1995184421539307} 08/31/2021 06:14:35 - INFO - __main__ - Step 93862: {'lr': 0.00015747073101990002, 'samples': 18021504, 'steps': 93861, 'loss/train': 1.3306061029434204} 08/31/2021 06:14:36 - INFO - __main__ - Step 93863: {'lr': 0.00015746580115422106, 'samples': 18021696, 'steps': 93862, 'loss/train': 1.6207098960876465} 08/31/2021 06:14:37 - INFO - __main__ - Step 93864: {'lr': 0.00015746087133023656, 'samples': 18021888, 'steps': 93863, 'loss/train': 0.9382541179656982} 08/31/2021 06:14:37 - INFO - __main__ - Step 93865: {'lr': 0.00015745594154794874, 'samples': 18022080, 'steps': 93864, 'loss/train': 1.1752740144729614} 08/31/2021 06:14:37 - INFO - __main__ - Step 93866: {'lr': 0.00015745101180735983, 'samples': 18022272, 'steps': 93865, 'loss/train': 0.8488021492958069} 08/31/2021 06:14:38 - INFO - __main__ - Step 93867: {'lr': 0.0001574460821084721, 'samples': 18022464, 'steps': 93866, 'loss/train': 1.4756985902786255} 08/31/2021 06:14:39 - INFO - __main__ - Step 93868: {'lr': 0.0001574411524512877, 'samples': 18022656, 'steps': 93867, 'loss/train': 1.4717001914978027} 08/31/2021 06:14:40 - INFO - __main__ - Step 93869: {'lr': 0.0001574362228358089, 'samples': 18022848, 'steps': 93868, 'loss/train': 1.1092398166656494} 08/31/2021 06:14:40 - INFO - __main__ - Step 93870: {'lr': 0.00015743129326203792, 'samples': 18023040, 'steps': 93869, 'loss/train': 0.7510359287261963} 08/31/2021 06:14:40 - INFO - __main__ - Step 93871: {'lr': 0.00015742636372997694, 'samples': 18023232, 'steps': 93870, 'loss/train': 0.5481811165809631} 08/31/2021 06:14:41 - INFO - __main__ - Step 93872: {'lr': 0.00015742143423962823, 'samples': 18023424, 'steps': 93871, 'loss/train': 1.3878740072250366} 08/31/2021 06:14:42 - INFO - __main__ - Step 93873: {'lr': 0.000157416504790994, 'samples': 18023616, 'steps': 93872, 'loss/train': 1.3333699703216553} 08/31/2021 06:14:42 - INFO - __main__ - Step 93874: {'lr': 0.00015741157538407647, 'samples': 18023808, 'steps': 93873, 'loss/train': 0.9204732179641724} 08/31/2021 06:14:43 - INFO - __main__ - Step 93875: {'lr': 0.00015740664601887792, 'samples': 18024000, 'steps': 93874, 'loss/train': 1.402910590171814} 08/31/2021 06:14:43 - INFO - __main__ - Step 93876: {'lr': 0.00015740171669540047, 'samples': 18024192, 'steps': 93875, 'loss/train': 1.327793002128601} 08/31/2021 06:14:44 - INFO - __main__ - Step 93877: {'lr': 0.00015739678741364635, 'samples': 18024384, 'steps': 93876, 'loss/train': 1.1226866245269775} 08/31/2021 06:14:44 - INFO - __main__ - Step 93878: {'lr': 0.0001573918581736178, 'samples': 18024576, 'steps': 93877, 'loss/train': 0.9278714656829834} 08/31/2021 06:14:46 - INFO - __main__ - Step 93879: {'lr': 0.00015738692897531706, 'samples': 18024768, 'steps': 93878, 'loss/train': 0.6517120599746704} 08/31/2021 06:14:46 - INFO - __main__ - Step 93880: {'lr': 0.00015738199981874635, 'samples': 18024960, 'steps': 93879, 'loss/train': 0.3338717222213745} 08/31/2021 06:14:47 - INFO - __main__ - Step 93881: {'lr': 0.00015737707070390784, 'samples': 18025152, 'steps': 93880, 'loss/train': 1.7530641555786133} 08/31/2021 06:14:47 - INFO - __main__ - Step 93882: {'lr': 0.00015737214163080382, 'samples': 18025344, 'steps': 93881, 'loss/train': 1.76649808883667} 08/31/2021 06:14:47 - INFO - __main__ - Step 93883: {'lr': 0.00015736721259943648, 'samples': 18025536, 'steps': 93882, 'loss/train': 1.3844783306121826} 08/31/2021 06:14:48 - INFO - __main__ - Step 93884: {'lr': 0.00015736228360980803, 'samples': 18025728, 'steps': 93883, 'loss/train': 1.3625390529632568} 08/31/2021 06:14:49 - INFO - __main__ - Step 93885: {'lr': 0.00015735735466192074, 'samples': 18025920, 'steps': 93884, 'loss/train': 1.3610923290252686} 08/31/2021 06:14:50 - INFO - __main__ - Step 93886: {'lr': 0.00015735242575577683, 'samples': 18026112, 'steps': 93885, 'loss/train': 0.7355998158454895} 08/31/2021 06:14:50 - INFO - __main__ - Step 93887: {'lr': 0.00015734749689137842, 'samples': 18026304, 'steps': 93886, 'loss/train': 1.746832013130188} 08/31/2021 06:14:50 - INFO - __main__ - Step 93888: {'lr': 0.0001573425680687278, 'samples': 18026496, 'steps': 93887, 'loss/train': 0.9815201759338379} 08/31/2021 06:14:51 - INFO - __main__ - Step 93889: {'lr': 0.00015733763928782723, 'samples': 18026688, 'steps': 93888, 'loss/train': 1.0503427982330322} 08/31/2021 06:14:52 - INFO - __main__ - Step 93890: {'lr': 0.00015733271054867889, 'samples': 18026880, 'steps': 93889, 'loss/train': 1.143061637878418} 08/31/2021 06:14:52 - INFO - __main__ - Step 93891: {'lr': 0.000157327781851285, 'samples': 18027072, 'steps': 93890, 'loss/train': 1.261802077293396} 08/31/2021 06:14:53 - INFO - __main__ - Step 93892: {'lr': 0.00015732285319564773, 'samples': 18027264, 'steps': 93891, 'loss/train': 1.2851698398590088} 08/31/2021 06:14:53 - INFO - __main__ - Step 93893: {'lr': 0.00015731792458176938, 'samples': 18027456, 'steps': 93892, 'loss/train': 1.425775408744812} 08/31/2021 06:14:54 - INFO - __main__ - Step 93894: {'lr': 0.00015731299600965214, 'samples': 18027648, 'steps': 93893, 'loss/train': 1.1378673315048218} 08/31/2021 06:14:55 - INFO - __main__ - Step 93895: {'lr': 0.00015730806747929824, 'samples': 18027840, 'steps': 93894, 'loss/train': 0.6590859889984131} 08/31/2021 06:14:56 - INFO - __main__ - Step 93896: {'lr': 0.0001573031389907099, 'samples': 18028032, 'steps': 93895, 'loss/train': 0.8387634754180908} 08/31/2021 06:14:56 - INFO - __main__ - Step 93897: {'lr': 0.00015729821054388934, 'samples': 18028224, 'steps': 93896, 'loss/train': 0.8908076286315918} 08/31/2021 06:14:56 - INFO - __main__ - Step 93898: {'lr': 0.00015729328213883877, 'samples': 18028416, 'steps': 93897, 'loss/train': 1.233116865158081} 08/31/2021 06:14:57 - INFO - __main__ - Step 93899: {'lr': 0.0001572883537755604, 'samples': 18028608, 'steps': 93898, 'loss/train': 0.6418915390968323} 08/31/2021 06:14:58 - INFO - __main__ - Step 93900: {'lr': 0.00015728342545405648, 'samples': 18028800, 'steps': 93899, 'loss/train': 0.7104437947273254} 08/31/2021 06:14:59 - INFO - __main__ - Step 93901: {'lr': 0.00015727849717432922, 'samples': 18028992, 'steps': 93900, 'loss/train': 0.9087218046188354} 08/31/2021 06:14:59 - INFO - __main__ - Step 93902: {'lr': 0.00015727356893638082, 'samples': 18029184, 'steps': 93901, 'loss/train': 1.132394552230835} 08/31/2021 06:14:59 - INFO - __main__ - Step 93903: {'lr': 0.00015726864074021358, 'samples': 18029376, 'steps': 93902, 'loss/train': 0.8246236443519592} 08/31/2021 06:15:00 - INFO - __main__ - Step 93904: {'lr': 0.0001572637125858296, 'samples': 18029568, 'steps': 93903, 'loss/train': 0.8709865212440491} 08/31/2021 06:15:01 - INFO - __main__ - Step 93905: {'lr': 0.00015725878447323116, 'samples': 18029760, 'steps': 93904, 'loss/train': 1.47915780544281} 08/31/2021 06:15:02 - INFO - __main__ - Step 93906: {'lr': 0.0001572538564024205, 'samples': 18029952, 'steps': 93905, 'loss/train': 1.1972198486328125} 08/31/2021 06:15:02 - INFO - __main__ - Step 93907: {'lr': 0.0001572489283733998, 'samples': 18030144, 'steps': 93906, 'loss/train': 0.9102442264556885} 08/31/2021 06:15:02 - INFO - __main__ - Step 93908: {'lr': 0.00015724400038617136, 'samples': 18030336, 'steps': 93907, 'loss/train': 0.9344995021820068} 08/31/2021 06:15:03 - INFO - __main__ - Step 93909: {'lr': 0.0001572390724407373, 'samples': 18030528, 'steps': 93908, 'loss/train': 1.2711681127548218} 08/31/2021 06:15:04 - INFO - __main__ - Step 93910: {'lr': 0.00015723414453709986, 'samples': 18030720, 'steps': 93909, 'loss/train': 1.2160227298736572} 08/31/2021 06:15:05 - INFO - __main__ - Step 93911: {'lr': 0.0001572292166752613, 'samples': 18030912, 'steps': 93910, 'loss/train': 2.2795822620391846} 08/31/2021 06:15:05 - INFO - __main__ - Step 93912: {'lr': 0.00015722428885522384, 'samples': 18031104, 'steps': 93911, 'loss/train': 1.438546895980835} 08/31/2021 06:15:05 - INFO - __main__ - Step 93913: {'lr': 0.00015721936107698965, 'samples': 18031296, 'steps': 93912, 'loss/train': 0.8525093793869019} 08/31/2021 06:15:06 - INFO - __main__ - Step 93914: {'lr': 0.000157214433340561, 'samples': 18031488, 'steps': 93913, 'loss/train': 0.968966007232666} 08/31/2021 06:15:08 - INFO - __main__ - Step 93915: {'lr': 0.0001572095056459401, 'samples': 18031680, 'steps': 93914, 'loss/train': 1.2028626203536987} 08/31/2021 06:15:08 - INFO - __main__ - Step 93916: {'lr': 0.00015720457799312914, 'samples': 18031872, 'steps': 93915, 'loss/train': 2.010023355484009} 08/31/2021 06:15:08 - INFO - __main__ - Step 93917: {'lr': 0.00015719965038213043, 'samples': 18032064, 'steps': 93916, 'loss/train': 1.3726245164871216} 08/31/2021 06:15:09 - INFO - __main__ - Step 93918: {'lr': 0.00015719472281294612, 'samples': 18032256, 'steps': 93917, 'loss/train': 1.212628960609436} 08/31/2021 06:15:09 - INFO - __main__ - Step 93919: {'lr': 0.00015718979528557843, 'samples': 18032448, 'steps': 93918, 'loss/train': 1.098301887512207} 08/31/2021 06:15:11 - INFO - __main__ - Step 93920: {'lr': 0.00015718486780002955, 'samples': 18032640, 'steps': 93919, 'loss/train': 1.1912633180618286} 08/31/2021 06:15:11 - INFO - __main__ - Step 93921: {'lr': 0.00015717994035630174, 'samples': 18032832, 'steps': 93920, 'loss/train': 0.7242394089698792} 08/31/2021 06:15:11 - INFO - __main__ - Step 93922: {'lr': 0.0001571750129543972, 'samples': 18033024, 'steps': 93921, 'loss/train': 0.0474376305937767} 08/31/2021 06:15:12 - INFO - __main__ - Step 93923: {'lr': 0.00015717008559431816, 'samples': 18033216, 'steps': 93922, 'loss/train': 1.5576165914535522} 08/31/2021 06:15:12 - INFO - __main__ - Step 93924: {'lr': 0.00015716515827606688, 'samples': 18033408, 'steps': 93923, 'loss/train': 0.1353018879890442} 08/31/2021 06:15:12 - INFO - __main__ - Step 93925: {'lr': 0.00015716023099964554, 'samples': 18033600, 'steps': 93924, 'loss/train': 1.736870288848877} 08/31/2021 06:15:14 - INFO - __main__ - Step 93926: {'lr': 0.00015715530376505637, 'samples': 18033792, 'steps': 93925, 'loss/train': 1.598822832107544} 08/31/2021 06:15:14 - INFO - __main__ - Step 93927: {'lr': 0.00015715037657230158, 'samples': 18033984, 'steps': 93926, 'loss/train': 0.8543367981910706} 08/31/2021 06:15:15 - INFO - __main__ - Step 93928: {'lr': 0.0001571454494213834, 'samples': 18034176, 'steps': 93927, 'loss/train': 0.5755431652069092} 08/31/2021 06:15:15 - INFO - __main__ - Step 93929: {'lr': 0.00015714052231230403, 'samples': 18034368, 'steps': 93928, 'loss/train': 0.6441855430603027} 08/31/2021 06:15:15 - INFO - __main__ - Step 93930: {'lr': 0.0001571355952450658, 'samples': 18034560, 'steps': 93929, 'loss/train': 1.2078986167907715} 08/31/2021 06:15:17 - INFO - __main__ - Step 93931: {'lr': 0.00015713066821967082, 'samples': 18034752, 'steps': 93930, 'loss/train': 1.1278413534164429} 08/31/2021 06:15:17 - INFO - __main__ - Step 93932: {'lr': 0.0001571257412361212, 'samples': 18034944, 'steps': 93931, 'loss/train': 1.1167458295822144} 08/31/2021 06:15:18 - INFO - __main__ - Step 93933: {'lr': 0.00015712081429441937, 'samples': 18035136, 'steps': 93932, 'loss/train': 0.9890890717506409} 08/31/2021 06:15:18 - INFO - __main__ - Step 93934: {'lr': 0.00015711588739456749, 'samples': 18035328, 'steps': 93933, 'loss/train': 1.0627928972244263} 08/31/2021 06:15:18 - INFO - __main__ - Step 93935: {'lr': 0.0001571109605365677, 'samples': 18035520, 'steps': 93934, 'loss/train': 1.207956314086914} 08/31/2021 06:15:20 - INFO - __main__ - Step 93936: {'lr': 0.00015710603372042232, 'samples': 18035712, 'steps': 93935, 'loss/train': 1.3649406433105469} 08/31/2021 06:15:20 - INFO - __main__ - Step 93937: {'lr': 0.0001571011069461335, 'samples': 18035904, 'steps': 93936, 'loss/train': 1.4770208597183228} 08/31/2021 06:15:21 - INFO - __main__ - Step 93938: {'lr': 0.00015709618021370349, 'samples': 18036096, 'steps': 93937, 'loss/train': 0.8786147832870483} 08/31/2021 06:15:21 - INFO - __main__ - Step 93939: {'lr': 0.00015709125352313452, 'samples': 18036288, 'steps': 93938, 'loss/train': 0.7468423843383789} 08/31/2021 06:15:21 - INFO - __main__ - Step 93940: {'lr': 0.00015708632687442878, 'samples': 18036480, 'steps': 93939, 'loss/train': 1.3470832109451294} 08/31/2021 06:15:23 - INFO - __main__ - Step 93941: {'lr': 0.00015708140026758852, 'samples': 18036672, 'steps': 93940, 'loss/train': 1.0957355499267578} 08/31/2021 06:15:23 - INFO - __main__ - Step 93942: {'lr': 0.00015707647370261595, 'samples': 18036864, 'steps': 93941, 'loss/train': 1.2456756830215454} 08/31/2021 06:15:24 - INFO - __main__ - Step 93943: {'lr': 0.00015707154717951326, 'samples': 18037056, 'steps': 93942, 'loss/train': 0.527413010597229} 08/31/2021 06:15:24 - INFO - __main__ - Step 93944: {'lr': 0.00015706662069828284, 'samples': 18037248, 'steps': 93943, 'loss/train': 0.6508570313453674} 08/31/2021 06:15:24 - INFO - __main__ - Step 93945: {'lr': 0.00015706169425892664, 'samples': 18037440, 'steps': 93944, 'loss/train': 0.7323583960533142} 08/31/2021 06:15:27 - INFO - __main__ - Step 93946: {'lr': 0.00015705676786144702, 'samples': 18037632, 'steps': 93945, 'loss/train': 1.357094645500183} 08/31/2021 06:15:27 - INFO - __main__ - Step 93947: {'lr': 0.00015705184150584616, 'samples': 18037824, 'steps': 93946, 'loss/train': 1.5489563941955566} 08/31/2021 06:15:27 - INFO - __main__ - Step 93948: {'lr': 0.00015704691519212633, 'samples': 18038016, 'steps': 93947, 'loss/train': 1.1233710050582886} 08/31/2021 06:15:28 - INFO - __main__ - Step 93949: {'lr': 0.00015704198892028972, 'samples': 18038208, 'steps': 93948, 'loss/train': 0.6969537734985352} 08/31/2021 06:15:28 - INFO - __main__ - Step 93950: {'lr': 0.00015703706269033858, 'samples': 18038400, 'steps': 93949, 'loss/train': 0.7935917377471924} 08/31/2021 06:15:30 - INFO - __main__ - Step 93951: {'lr': 0.00015703213650227504, 'samples': 18038592, 'steps': 93950, 'loss/train': 1.0796037912368774} 08/31/2021 06:15:30 - INFO - __main__ - Step 93952: {'lr': 0.00015702721035610145, 'samples': 18038784, 'steps': 93951, 'loss/train': 1.063702940940857} 08/31/2021 06:15:30 - INFO - __main__ - Step 93953: {'lr': 0.00015702228425181993, 'samples': 18038976, 'steps': 93952, 'loss/train': 1.3049930334091187} 08/31/2021 06:15:31 - INFO - __main__ - Step 93954: {'lr': 0.00015701735818943275, 'samples': 18039168, 'steps': 93953, 'loss/train': 1.8285397291183472} 08/31/2021 06:15:31 - INFO - __main__ - Step 93955: {'lr': 0.00015701243216894212, 'samples': 18039360, 'steps': 93954, 'loss/train': 1.6559267044067383} 08/31/2021 06:15:31 - INFO - __main__ - Step 93956: {'lr': 0.00015700750619035024, 'samples': 18039552, 'steps': 93955, 'loss/train': 0.7833643555641174} 08/31/2021 06:15:33 - INFO - __main__ - Step 93957: {'lr': 0.00015700258025365944, 'samples': 18039744, 'steps': 93956, 'loss/train': 0.7954562306404114} 08/31/2021 06:15:34 - INFO - __main__ - Step 93958: {'lr': 0.00015699765435887175, 'samples': 18039936, 'steps': 93957, 'loss/train': 0.2022785097360611} 08/31/2021 06:15:34 - INFO - __main__ - Step 93959: {'lr': 0.00015699272850598945, 'samples': 18040128, 'steps': 93958, 'loss/train': 0.05444419011473656} 08/31/2021 06:15:34 - INFO - __main__ - Step 93960: {'lr': 0.00015698780269501485, 'samples': 18040320, 'steps': 93959, 'loss/train': 1.532674789428711} 08/31/2021 06:15:35 - INFO - __main__ - Step 93961: {'lr': 0.00015698287692595005, 'samples': 18040512, 'steps': 93960, 'loss/train': 1.5408345460891724} 08/31/2021 06:15:36 - INFO - __main__ - Step 93962: {'lr': 0.00015697795119879737, 'samples': 18040704, 'steps': 93961, 'loss/train': 1.425811529159546} 08/31/2021 06:15:36 - INFO - __main__ - Step 93963: {'lr': 0.00015697302551355896, 'samples': 18040896, 'steps': 93962, 'loss/train': 1.505088210105896} 08/31/2021 06:15:37 - INFO - __main__ - Step 93964: {'lr': 0.0001569680998702371, 'samples': 18041088, 'steps': 93963, 'loss/train': 1.3480809926986694} 08/31/2021 06:15:37 - INFO - __main__ - Step 93965: {'lr': 0.00015696317426883396, 'samples': 18041280, 'steps': 93964, 'loss/train': 0.44546496868133545} 08/31/2021 06:15:38 - INFO - __main__ - Step 93966: {'lr': 0.0001569582487093518, 'samples': 18041472, 'steps': 93965, 'loss/train': 1.6574528217315674} 08/31/2021 06:15:39 - INFO - __main__ - Step 93967: {'lr': 0.00015695332319179279, 'samples': 18041664, 'steps': 93966, 'loss/train': 1.3602931499481201} 08/31/2021 06:15:40 - INFO - __main__ - Step 93968: {'lr': 0.0001569483977161592, 'samples': 18041856, 'steps': 93967, 'loss/train': 0.7153401374816895} 08/31/2021 06:15:40 - INFO - __main__ - Step 93969: {'lr': 0.0001569434722824532, 'samples': 18042048, 'steps': 93968, 'loss/train': 1.178488850593567} 08/31/2021 06:15:40 - INFO - __main__ - Step 93970: {'lr': 0.00015693854689067716, 'samples': 18042240, 'steps': 93969, 'loss/train': 1.3858178853988647} 08/31/2021 06:15:41 - INFO - __main__ - Step 93971: {'lr': 0.00015693362154083307, 'samples': 18042432, 'steps': 93970, 'loss/train': 1.5236634016036987} 08/31/2021 06:15:42 - INFO - __main__ - Step 93972: {'lr': 0.00015692869623292326, 'samples': 18042624, 'steps': 93971, 'loss/train': 1.2200372219085693} 08/31/2021 06:15:43 - INFO - __main__ - Step 93973: {'lr': 0.00015692377096694992, 'samples': 18042816, 'steps': 93972, 'loss/train': 1.5234251022338867} 08/31/2021 06:15:43 - INFO - __main__ - Step 93974: {'lr': 0.00015691884574291532, 'samples': 18043008, 'steps': 93973, 'loss/train': 0.9340356588363647} 08/31/2021 06:15:43 - INFO - __main__ - Step 93975: {'lr': 0.00015691392056082162, 'samples': 18043200, 'steps': 93974, 'loss/train': 0.7885080575942993} 08/31/2021 06:15:44 - INFO - __main__ - Step 93976: {'lr': 0.0001569089954206711, 'samples': 18043392, 'steps': 93975, 'loss/train': 1.0632638931274414} 08/31/2021 06:15:45 - INFO - __main__ - Step 93977: {'lr': 0.00015690407032246595, 'samples': 18043584, 'steps': 93976, 'loss/train': 1.365370512008667} 08/31/2021 06:15:46 - INFO - __main__ - Step 93978: {'lr': 0.00015689914526620835, 'samples': 18043776, 'steps': 93977, 'loss/train': 1.2635191679000854} 08/31/2021 06:15:46 - INFO - __main__ - Step 93979: {'lr': 0.0001568942202519006, 'samples': 18043968, 'steps': 93978, 'loss/train': 0.9649736285209656} 08/31/2021 06:15:46 - INFO - __main__ - Step 93980: {'lr': 0.00015688929527954488, 'samples': 18044160, 'steps': 93979, 'loss/train': 1.1682049036026} 08/31/2021 06:15:47 - INFO - __main__ - Step 93981: {'lr': 0.00015688437034914337, 'samples': 18044352, 'steps': 93980, 'loss/train': 1.33124577999115} 08/31/2021 06:15:49 - INFO - __main__ - Step 93982: {'lr': 0.00015687944546069834, 'samples': 18044544, 'steps': 93981, 'loss/train': 0.9583380818367004} 08/31/2021 06:15:49 - INFO - __main__ - Step 93983: {'lr': 0.000156874520614212, 'samples': 18044736, 'steps': 93982, 'loss/train': 0.9267348051071167} 08/31/2021 06:15:50 - INFO - __main__ - Step 93984: {'lr': 0.00015686959580968668, 'samples': 18044928, 'steps': 93983, 'loss/train': 0.07276564091444016} 08/31/2021 06:15:50 - INFO - __main__ - Step 93985: {'lr': 0.00015686467104712438, 'samples': 18045120, 'steps': 93984, 'loss/train': 1.483906626701355} 08/31/2021 06:15:50 - INFO - __main__ - Step 93986: {'lr': 0.00015685974632652738, 'samples': 18045312, 'steps': 93985, 'loss/train': 1.2789137363433838} 08/31/2021 06:15:51 - INFO - __main__ - Step 93987: {'lr': 0.000156854821647898, 'samples': 18045504, 'steps': 93986, 'loss/train': 0.5231592059135437} 08/31/2021 06:15:52 - INFO - __main__ - Step 93988: {'lr': 0.00015684989701123837, 'samples': 18045696, 'steps': 93987, 'loss/train': 1.1245352029800415} 08/31/2021 06:15:53 - INFO - __main__ - Step 93989: {'lr': 0.00015684497241655072, 'samples': 18045888, 'steps': 93988, 'loss/train': 0.6019996404647827} 08/31/2021 06:15:53 - INFO - __main__ - Step 93990: {'lr': 0.00015684004786383732, 'samples': 18046080, 'steps': 93989, 'loss/train': 1.4956167936325073} 08/31/2021 06:15:53 - INFO - __main__ - Step 93991: {'lr': 0.00015683512335310036, 'samples': 18046272, 'steps': 93990, 'loss/train': 1.2064969539642334} 08/31/2021 06:15:54 - INFO - __main__ - Step 93992: {'lr': 0.00015683019888434202, 'samples': 18046464, 'steps': 93991, 'loss/train': 0.03597010299563408} 08/31/2021 06:15:55 - INFO - __main__ - Step 93993: {'lr': 0.00015682527445756456, 'samples': 18046656, 'steps': 93992, 'loss/train': 1.4002034664154053} 08/31/2021 06:15:56 - INFO - __main__ - Step 93994: {'lr': 0.00015682035007277023, 'samples': 18046848, 'steps': 93993, 'loss/train': 0.9341266751289368} 08/31/2021 06:15:56 - INFO - __main__ - Step 93995: {'lr': 0.0001568154257299612, 'samples': 18047040, 'steps': 93994, 'loss/train': 0.7031828165054321} 08/31/2021 06:15:57 - INFO - __main__ - Step 93996: {'lr': 0.00015681050142913965, 'samples': 18047232, 'steps': 93995, 'loss/train': 0.6937229037284851} 08/31/2021 06:15:57 - INFO - __main__ - Step 93997: {'lr': 0.00015680557717030803, 'samples': 18047424, 'steps': 93996, 'loss/train': 0.02001301571726799} 08/31/2021 06:15:57 - INFO - __main__ - Step 93998: {'lr': 0.00015680065295346825, 'samples': 18047616, 'steps': 93997, 'loss/train': 0.8392805457115173} 08/31/2021 06:15:59 - INFO - __main__ - Step 93999: {'lr': 0.00015679572877862265, 'samples': 18047808, 'steps': 93998, 'loss/train': 1.232938528060913} 08/31/2021 06:15:59 - INFO - __main__ - Step 94000: {'lr': 0.00015679080464577345, 'samples': 18048000, 'steps': 93999, 'loss/train': 1.6093549728393555} 08/31/2021 06:16:00 - INFO - __main__ - Step 94001: {'lr': 0.00015678588055492287, 'samples': 18048192, 'steps': 94000, 'loss/train': 1.2859671115875244} 08/31/2021 06:16:00 - INFO - __main__ - Step 94002: {'lr': 0.00015678095650607316, 'samples': 18048384, 'steps': 94001, 'loss/train': 1.441041111946106} 08/31/2021 06:16:00 - INFO - __main__ - Step 94003: {'lr': 0.0001567760324992265, 'samples': 18048576, 'steps': 94002, 'loss/train': 1.7795703411102295} 08/31/2021 06:16:01 - INFO - __main__ - Step 94004: {'lr': 0.00015677110853438509, 'samples': 18048768, 'steps': 94003, 'loss/train': 0.788340151309967} 08/31/2021 06:16:03 - INFO - __main__ - Step 94005: {'lr': 0.00015676618461155122, 'samples': 18048960, 'steps': 94004, 'loss/train': 1.1894766092300415} 08/31/2021 06:16:04 - INFO - __main__ - Step 94006: {'lr': 0.00015676126073072705, 'samples': 18049152, 'steps': 94005, 'loss/train': 1.116195559501648} 08/31/2021 06:16:04 - INFO - __main__ - Step 94007: {'lr': 0.0001567563368919148, 'samples': 18049344, 'steps': 94006, 'loss/train': 1.8283828496932983} 08/31/2021 06:16:04 - INFO - __main__ - Step 94008: {'lr': 0.00015675141309511677, 'samples': 18049536, 'steps': 94007, 'loss/train': 1.1635403633117676} 08/31/2021 06:16:05 - INFO - __main__ - Step 94009: {'lr': 0.0001567464893403351, 'samples': 18049728, 'steps': 94008, 'loss/train': 0.08282548189163208} 08/31/2021 06:16:06 - INFO - __main__ - Step 94010: {'lr': 0.00015674156562757202, 'samples': 18049920, 'steps': 94009, 'loss/train': 1.1053873300552368} 08/31/2021 06:16:06 - INFO - __main__ - Step 94011: {'lr': 0.0001567366419568298, 'samples': 18050112, 'steps': 94010, 'loss/train': 1.294260859489441} 08/31/2021 06:16:07 - INFO - __main__ - Step 94012: {'lr': 0.0001567317183281105, 'samples': 18050304, 'steps': 94011, 'loss/train': 1.6949478387832642} 08/31/2021 06:16:07 - INFO - __main__ - Step 94013: {'lr': 0.0001567267947414165, 'samples': 18050496, 'steps': 94012, 'loss/train': 0.9190523028373718} 08/31/2021 06:16:07 - INFO - __main__ - Step 94014: {'lr': 0.00015672187119674996, 'samples': 18050688, 'steps': 94013, 'loss/train': 1.317733645439148} 08/31/2021 06:16:09 - INFO - __main__ - Step 94015: {'lr': 0.0001567169476941131, 'samples': 18050880, 'steps': 94014, 'loss/train': 1.5182690620422363} 08/31/2021 06:16:09 - INFO - __main__ - Step 94016: {'lr': 0.00015671202423350814, 'samples': 18051072, 'steps': 94015, 'loss/train': 1.0275068283081055} 08/31/2021 06:16:10 - INFO - __main__ - Step 94017: {'lr': 0.0001567071008149373, 'samples': 18051264, 'steps': 94016, 'loss/train': 1.580678105354309} 08/31/2021 06:16:10 - INFO - __main__ - Step 94018: {'lr': 0.0001567021774384028, 'samples': 18051456, 'steps': 94017, 'loss/train': 1.1156134605407715} 08/31/2021 06:16:11 - INFO - __main__ - Step 94019: {'lr': 0.00015669725410390688, 'samples': 18051648, 'steps': 94018, 'loss/train': 1.6540030241012573} 08/31/2021 06:16:12 - INFO - __main__ - Step 94020: {'lr': 0.0001566923308114518, 'samples': 18051840, 'steps': 94019, 'loss/train': 1.1463831663131714} 08/31/2021 06:16:13 - INFO - __main__ - Step 94021: {'lr': 0.0001566874075610396, 'samples': 18052032, 'steps': 94020, 'loss/train': 0.6903653144836426} 08/31/2021 06:16:13 - INFO - __main__ - Step 94022: {'lr': 0.0001566824843526727, 'samples': 18052224, 'steps': 94021, 'loss/train': 2.3317697048187256} 08/31/2021 06:16:13 - INFO - __main__ - Step 94023: {'lr': 0.00015667756118635314, 'samples': 18052416, 'steps': 94022, 'loss/train': 0.908858597278595} 08/31/2021 06:16:14 - INFO - __main__ - Step 94024: {'lr': 0.00015667263806208335, 'samples': 18052608, 'steps': 94023, 'loss/train': 1.479919195175171} 08/31/2021 06:16:14 - INFO - __main__ - Step 94025: {'lr': 0.00015666771497986533, 'samples': 18052800, 'steps': 94024, 'loss/train': 1.5070855617523193} 08/31/2021 06:16:15 - INFO - __main__ - Step 94026: {'lr': 0.00015666279193970146, 'samples': 18052992, 'steps': 94025, 'loss/train': 5.478981018066406} 08/31/2021 06:16:16 - INFO - __main__ - Step 94027: {'lr': 0.00015665786894159385, 'samples': 18053184, 'steps': 94026, 'loss/train': 1.014453649520874} 08/31/2021 06:16:16 - INFO - __main__ - Step 94028: {'lr': 0.00015665294598554474, 'samples': 18053376, 'steps': 94027, 'loss/train': 0.8740664720535278} 08/31/2021 06:16:17 - INFO - __main__ - Step 94029: {'lr': 0.00015664802307155642, 'samples': 18053568, 'steps': 94028, 'loss/train': 0.9625178575515747} 08/31/2021 06:16:17 - INFO - __main__ - Step 94030: {'lr': 0.00015664310019963105, 'samples': 18053760, 'steps': 94029, 'loss/train': 1.3516082763671875} 08/31/2021 06:16:18 - INFO - __main__ - Step 94031: {'lr': 0.0001566381773697709, 'samples': 18053952, 'steps': 94030, 'loss/train': 1.6073662042617798} 08/31/2021 06:16:19 - INFO - __main__ - Step 94032: {'lr': 0.0001566332545819781, 'samples': 18054144, 'steps': 94031, 'loss/train': 1.0660327672958374} 08/31/2021 06:16:19 - INFO - __main__ - Step 94033: {'lr': 0.00015662833183625492, 'samples': 18054336, 'steps': 94032, 'loss/train': 0.8671882152557373} 08/31/2021 06:16:20 - INFO - __main__ - Step 94034: {'lr': 0.00015662340913260358, 'samples': 18054528, 'steps': 94033, 'loss/train': 1.5907248258590698} 08/31/2021 06:16:20 - INFO - __main__ - Step 94035: {'lr': 0.00015661848647102627, 'samples': 18054720, 'steps': 94034, 'loss/train': 0.8760409951210022} 08/31/2021 06:16:22 - INFO - __main__ - Step 94036: {'lr': 0.00015661356385152526, 'samples': 18054912, 'steps': 94035, 'loss/train': 0.9695798754692078} 08/31/2021 06:16:22 - INFO - __main__ - Step 94037: {'lr': 0.00015660864127410267, 'samples': 18055104, 'steps': 94036, 'loss/train': 1.040968656539917} 08/31/2021 06:16:22 - INFO - __main__ - Step 94038: {'lr': 0.0001566037187387609, 'samples': 18055296, 'steps': 94037, 'loss/train': 1.2673866748809814} 08/31/2021 06:16:23 - INFO - __main__ - Step 94039: {'lr': 0.000156598796245502, 'samples': 18055488, 'steps': 94038, 'loss/train': 0.6728128790855408} 08/31/2021 06:16:23 - INFO - __main__ - Step 94040: {'lr': 0.00015659387379432822, 'samples': 18055680, 'steps': 94039, 'loss/train': 1.2324122190475464} 08/31/2021 06:16:25 - INFO - __main__ - Step 94041: {'lr': 0.00015658895138524179, 'samples': 18055872, 'steps': 94040, 'loss/train': 0.9541370272636414} 08/31/2021 06:16:25 - INFO - __main__ - Step 94042: {'lr': 0.000156584029018245, 'samples': 18056064, 'steps': 94041, 'loss/train': 0.7482801675796509} 08/31/2021 06:16:26 - INFO - __main__ - Step 94043: {'lr': 0.00015657910669333996, 'samples': 18056256, 'steps': 94042, 'loss/train': 0.886588454246521} 08/31/2021 06:16:26 - INFO - __main__ - Step 94044: {'lr': 0.00015657418441052896, 'samples': 18056448, 'steps': 94043, 'loss/train': 1.1458321809768677} 08/31/2021 06:16:26 - INFO - __main__ - Step 94045: {'lr': 0.00015656926216981416, 'samples': 18056640, 'steps': 94044, 'loss/train': 1.4179480075836182} 08/31/2021 06:16:27 - INFO - __main__ - Step 94046: {'lr': 0.0001565643399711978, 'samples': 18056832, 'steps': 94045, 'loss/train': 0.08762761950492859} 08/31/2021 06:16:28 - INFO - __main__ - Step 94047: {'lr': 0.0001565594178146821, 'samples': 18057024, 'steps': 94046, 'loss/train': 0.06214309483766556} 08/31/2021 06:16:29 - INFO - __main__ - Step 94048: {'lr': 0.00015655449570026932, 'samples': 18057216, 'steps': 94047, 'loss/train': 1.1908824443817139} 08/31/2021 06:16:29 - INFO - __main__ - Step 94049: {'lr': 0.0001565495736279616, 'samples': 18057408, 'steps': 94048, 'loss/train': 0.1696501076221466} 08/31/2021 06:16:29 - INFO - __main__ - Step 94050: {'lr': 0.0001565446515977612, 'samples': 18057600, 'steps': 94049, 'loss/train': 1.5398916006088257} 08/31/2021 06:16:30 - INFO - __main__ - Step 94051: {'lr': 0.00015653972960967045, 'samples': 18057792, 'steps': 94050, 'loss/train': 1.262384057044983} 08/31/2021 06:16:30 - INFO - __main__ - Step 94052: {'lr': 0.00015653480766369135, 'samples': 18057984, 'steps': 94051, 'loss/train': 1.3627088069915771} 08/31/2021 06:16:32 - INFO - __main__ - Step 94053: {'lr': 0.0001565298857598263, 'samples': 18058176, 'steps': 94052, 'loss/train': 1.3981479406356812} 08/31/2021 06:16:32 - INFO - __main__ - Step 94054: {'lr': 0.00015652496389807736, 'samples': 18058368, 'steps': 94053, 'loss/train': 0.45051220059394836} 08/31/2021 06:16:32 - INFO - __main__ - Step 94055: {'lr': 0.00015652004207844687, 'samples': 18058560, 'steps': 94054, 'loss/train': 0.9174769520759583} 08/31/2021 06:16:33 - INFO - __main__ - Step 94056: {'lr': 0.00015651512030093697, 'samples': 18058752, 'steps': 94055, 'loss/train': 0.6173493266105652} 08/31/2021 06:16:33 - INFO - __main__ - Step 94057: {'lr': 0.00015651019856554994, 'samples': 18058944, 'steps': 94056, 'loss/train': 0.7656505107879639} 08/31/2021 06:16:35 - INFO - __main__ - Step 94058: {'lr': 0.00015650527687228793, 'samples': 18059136, 'steps': 94057, 'loss/train': 1.2782087326049805} 08/31/2021 06:16:35 - INFO - __main__ - Step 94059: {'lr': 0.00015650035522115326, 'samples': 18059328, 'steps': 94058, 'loss/train': 1.1489003896713257} 08/31/2021 06:16:35 - INFO - __main__ - Step 94060: {'lr': 0.00015649543361214804, 'samples': 18059520, 'steps': 94059, 'loss/train': 1.56424880027771} 08/31/2021 06:16:36 - INFO - __main__ - Step 94061: {'lr': 0.00015649051204527458, 'samples': 18059712, 'steps': 94060, 'loss/train': 1.3982398509979248} 08/31/2021 06:16:36 - INFO - __main__ - Step 94062: {'lr': 0.00015648559052053502, 'samples': 18059904, 'steps': 94061, 'loss/train': 0.932928204536438} 08/31/2021 06:16:38 - INFO - __main__ - Step 94063: {'lr': 0.00015648066903793163, 'samples': 18060096, 'steps': 94062, 'loss/train': 0.523012101650238} 08/31/2021 06:16:39 - INFO - __main__ - Step 94064: {'lr': 0.00015647574759746657, 'samples': 18060288, 'steps': 94063, 'loss/train': 0.44725731015205383} 08/31/2021 06:16:39 - INFO - __main__ - Step 94065: {'lr': 0.00015647082619914222, 'samples': 18060480, 'steps': 94064, 'loss/train': 1.667534351348877} 08/31/2021 06:16:39 - INFO - __main__ - Step 94066: {'lr': 0.0001564659048429606, 'samples': 18060672, 'steps': 94065, 'loss/train': 1.3147532939910889} 08/31/2021 06:16:40 - INFO - __main__ - Step 94067: {'lr': 0.00015646098352892394, 'samples': 18060864, 'steps': 94066, 'loss/train': 1.2891545295715332} 08/31/2021 06:16:41 - INFO - __main__ - Step 94068: {'lr': 0.00015645606225703454, 'samples': 18061056, 'steps': 94067, 'loss/train': 1.2005928754806519} 08/31/2021 06:16:42 - INFO - __main__ - Step 94069: {'lr': 0.0001564511410272946, 'samples': 18061248, 'steps': 94068, 'loss/train': 1.1557495594024658} 08/31/2021 06:16:42 - INFO - __main__ - Step 94070: {'lr': 0.00015644621983970636, 'samples': 18061440, 'steps': 94069, 'loss/train': 1.154829502105713} 08/31/2021 06:16:42 - INFO - __main__ - Step 94071: {'lr': 0.00015644129869427198, 'samples': 18061632, 'steps': 94070, 'loss/train': 0.9598216414451599} 08/31/2021 06:16:43 - INFO - __main__ - Step 94072: {'lr': 0.00015643637759099371, 'samples': 18061824, 'steps': 94071, 'loss/train': 1.2215614318847656} 08/31/2021 06:16:43 - INFO - __main__ - Step 94073: {'lr': 0.00015643145652987375, 'samples': 18062016, 'steps': 94072, 'loss/train': 0.9587391018867493} 08/31/2021 06:16:45 - INFO - __main__ - Step 94074: {'lr': 0.00015642653551091435, 'samples': 18062208, 'steps': 94073, 'loss/train': 1.3561056852340698} 08/31/2021 06:16:45 - INFO - __main__ - Step 94075: {'lr': 0.00015642161453411772, 'samples': 18062400, 'steps': 94074, 'loss/train': 2.287790060043335} 08/31/2021 06:16:46 - INFO - __main__ - Step 94076: {'lr': 0.00015641669359948605, 'samples': 18062592, 'steps': 94075, 'loss/train': 1.9158192873001099} 08/31/2021 06:16:46 - INFO - __main__ - Step 94077: {'lr': 0.00015641177270702157, 'samples': 18062784, 'steps': 94076, 'loss/train': 0.838623583316803} 08/31/2021 06:16:46 - INFO - __main__ - Step 94078: {'lr': 0.0001564068518567266, 'samples': 18062976, 'steps': 94077, 'loss/train': 1.1089218854904175} 08/31/2021 06:16:48 - INFO - __main__ - Step 94079: {'lr': 0.00015640193104860317, 'samples': 18063168, 'steps': 94078, 'loss/train': 1.0857492685317993} 08/31/2021 06:16:49 - INFO - __main__ - Step 94080: {'lr': 0.00015639701028265357, 'samples': 18063360, 'steps': 94079, 'loss/train': 0.5077550411224365} 08/31/2021 06:16:49 - INFO - __main__ - Step 94081: {'lr': 0.00015639208955888008, 'samples': 18063552, 'steps': 94080, 'loss/train': 0.8393121957778931} 08/31/2021 06:16:49 - INFO - __main__ - Step 94082: {'lr': 0.00015638716887728482, 'samples': 18063744, 'steps': 94081, 'loss/train': 0.7525778412818909} 08/31/2021 06:16:50 - INFO - __main__ - Step 94083: {'lr': 0.00015638224823787006, 'samples': 18063936, 'steps': 94082, 'loss/train': 1.106018304824829} 08/31/2021 06:16:52 - INFO - __main__ - Step 94084: {'lr': 0.00015637732764063806, 'samples': 18064128, 'steps': 94083, 'loss/train': 0.5665240287780762} 08/31/2021 06:16:53 - INFO - __main__ - Step 94085: {'lr': 0.00015637240708559093, 'samples': 18064320, 'steps': 94084, 'loss/train': 1.4689329862594604} 08/31/2021 06:16:53 - INFO - __main__ - Step 94086: {'lr': 0.00015636748657273098, 'samples': 18064512, 'steps': 94085, 'loss/train': 0.5936474800109863} 08/31/2021 06:16:54 - INFO - __main__ - Step 94087: {'lr': 0.0001563625661020604, 'samples': 18064704, 'steps': 94086, 'loss/train': 1.486279010772705} 08/31/2021 06:16:54 - INFO - __main__ - Step 94088: {'lr': 0.0001563576456735814, 'samples': 18064896, 'steps': 94087, 'loss/train': 1.1153160333633423} 08/31/2021 06:16:54 - INFO - __main__ - Step 94089: {'lr': 0.0001563527252872962, 'samples': 18065088, 'steps': 94088, 'loss/train': 1.7763243913650513} 08/31/2021 06:16:55 - INFO - __main__ - Step 94090: {'lr': 0.000156347804943207, 'samples': 18065280, 'steps': 94089, 'loss/train': 1.7760701179504395} 08/31/2021 06:16:55 - INFO - __main__ - Step 94091: {'lr': 0.00015634288464131614, 'samples': 18065472, 'steps': 94090, 'loss/train': 1.7771614789962769} 08/31/2021 06:16:57 - INFO - __main__ - Step 94092: {'lr': 0.00015633796438162565, 'samples': 18065664, 'steps': 94091, 'loss/train': 1.7694213390350342} 08/31/2021 06:16:57 - INFO - __main__ - Step 94093: {'lr': 0.0001563330441641378, 'samples': 18065856, 'steps': 94092, 'loss/train': 0.6856259703636169} 08/31/2021 06:16:58 - INFO - __main__ - Step 94094: {'lr': 0.00015632812398885487, 'samples': 18066048, 'steps': 94093, 'loss/train': 1.1396467685699463} 08/31/2021 06:16:58 - INFO - __main__ - Step 94095: {'lr': 0.00015632320385577903, 'samples': 18066240, 'steps': 94094, 'loss/train': 1.5297937393188477} 08/31/2021 06:16:58 - INFO - __main__ - Step 94096: {'lr': 0.00015631828376491246, 'samples': 18066432, 'steps': 94095, 'loss/train': 1.9029115438461304} 08/31/2021 06:17:00 - INFO - __main__ - Step 94097: {'lr': 0.0001563133637162575, 'samples': 18066624, 'steps': 94096, 'loss/train': 1.6471439599990845} 08/31/2021 06:17:00 - INFO - __main__ - Step 94098: {'lr': 0.00015630844370981623, 'samples': 18066816, 'steps': 94097, 'loss/train': 1.7749559879302979} 08/31/2021 06:17:01 - INFO - __main__ - Step 94099: {'lr': 0.00015630352374559098, 'samples': 18067008, 'steps': 94098, 'loss/train': 1.2397187948226929} 08/31/2021 06:17:01 - INFO - __main__ - Step 94100: {'lr': 0.00015629860382358388, 'samples': 18067200, 'steps': 94099, 'loss/train': 0.8990198969841003} 08/31/2021 06:17:01 - INFO - __main__ - Step 94101: {'lr': 0.0001562936839437972, 'samples': 18067392, 'steps': 94100, 'loss/train': 1.1375043392181396} 08/31/2021 06:17:03 - INFO - __main__ - Step 94102: {'lr': 0.00015628876410623315, 'samples': 18067584, 'steps': 94101, 'loss/train': 1.779197096824646} 08/31/2021 06:17:03 - INFO - __main__ - Step 94103: {'lr': 0.00015628384431089394, 'samples': 18067776, 'steps': 94102, 'loss/train': 1.1812857389450073} 08/31/2021 06:17:04 - INFO - __main__ - Step 94104: {'lr': 0.00015627892455778174, 'samples': 18067968, 'steps': 94103, 'loss/train': 0.8784602284431458} 08/31/2021 06:17:04 - INFO - __main__ - Step 94105: {'lr': 0.00015627400484689895, 'samples': 18068160, 'steps': 94104, 'loss/train': 1.4638091325759888} 08/31/2021 06:17:04 - INFO - __main__ - Step 94106: {'lr': 0.00015626908517824754, 'samples': 18068352, 'steps': 94105, 'loss/train': 1.496998906135559} 08/31/2021 06:17:06 - INFO - __main__ - Step 94107: {'lr': 0.00015626416555182982, 'samples': 18068544, 'steps': 94106, 'loss/train': 0.1530848890542984} 08/31/2021 06:17:06 - INFO - __main__ - Step 94108: {'lr': 0.000156259245967648, 'samples': 18068736, 'steps': 94107, 'loss/train': 0.9301477670669556} 08/31/2021 06:17:07 - INFO - __main__ - Step 94109: {'lr': 0.00015625432642570435, 'samples': 18068928, 'steps': 94108, 'loss/train': 2.1967945098876953} 08/31/2021 06:17:07 - INFO - __main__ - Step 94110: {'lr': 0.0001562494069260011, 'samples': 18069120, 'steps': 94109, 'loss/train': 1.5058460235595703} 08/31/2021 06:17:07 - INFO - __main__ - Step 94111: {'lr': 0.00015624448746854038, 'samples': 18069312, 'steps': 94110, 'loss/train': 0.6219431757926941} 08/31/2021 06:17:08 - INFO - __main__ - Step 94112: {'lr': 0.0001562395680533244, 'samples': 18069504, 'steps': 94111, 'loss/train': 1.2765522003173828} 08/31/2021 06:17:09 - INFO - __main__ - Step 94113: {'lr': 0.00015623464868035547, 'samples': 18069696, 'steps': 94112, 'loss/train': 1.2552247047424316} 08/31/2021 06:17:10 - INFO - __main__ - Step 94114: {'lr': 0.00015622972934963575, 'samples': 18069888, 'steps': 94113, 'loss/train': 1.441179633140564} 08/31/2021 06:17:10 - INFO - __main__ - Step 94115: {'lr': 0.00015622481006116748, 'samples': 18070080, 'steps': 94114, 'loss/train': 0.9270654916763306} 08/31/2021 06:17:10 - INFO - __main__ - Step 94116: {'lr': 0.00015621989081495287, 'samples': 18070272, 'steps': 94115, 'loss/train': 1.3475128412246704} 08/31/2021 06:17:11 - INFO - __main__ - Step 94117: {'lr': 0.0001562149716109941, 'samples': 18070464, 'steps': 94116, 'loss/train': 1.4476853609085083} 08/31/2021 06:17:13 - INFO - __main__ - Step 94118: {'lr': 0.00015621005244929355, 'samples': 18070656, 'steps': 94117, 'loss/train': 1.368288516998291} 08/31/2021 06:17:13 - INFO - __main__ - Step 94119: {'lr': 0.00015620513332985315, 'samples': 18070848, 'steps': 94118, 'loss/train': 0.7467924356460571} 08/31/2021 06:17:13 - INFO - __main__ - Step 94120: {'lr': 0.00015620021425267534, 'samples': 18071040, 'steps': 94119, 'loss/train': 0.35725417733192444} 08/31/2021 06:17:14 - INFO - __main__ - Step 94121: {'lr': 0.00015619529521776221, 'samples': 18071232, 'steps': 94120, 'loss/train': 0.18997378647327423} 08/31/2021 06:17:14 - INFO - __main__ - Step 94122: {'lr': 0.00015619037622511606, 'samples': 18071424, 'steps': 94121, 'loss/train': 1.1918541193008423} 08/31/2021 06:17:16 - INFO - __main__ - Step 94123: {'lr': 0.00015618545727473905, 'samples': 18071616, 'steps': 94122, 'loss/train': 1.4006506204605103} 08/31/2021 06:17:16 - INFO - __main__ - Step 94124: {'lr': 0.00015618053836663346, 'samples': 18071808, 'steps': 94123, 'loss/train': 0.7001181244850159} 08/31/2021 06:17:17 - INFO - __main__ - Step 94125: {'lr': 0.00015617561950080145, 'samples': 18072000, 'steps': 94124, 'loss/train': 0.07714451849460602} 08/31/2021 06:17:17 - INFO - __main__ - Step 94126: {'lr': 0.00015617070067724525, 'samples': 18072192, 'steps': 94125, 'loss/train': 1.5364091396331787} 08/31/2021 06:17:17 - INFO - __main__ - Step 94127: {'lr': 0.00015616578189596713, 'samples': 18072384, 'steps': 94126, 'loss/train': 1.3291813135147095} 08/31/2021 06:17:19 - INFO - __main__ - Step 94128: {'lr': 0.0001561608631569692, 'samples': 18072576, 'steps': 94127, 'loss/train': 1.029382586479187} 08/31/2021 06:17:20 - INFO - __main__ - Step 94129: {'lr': 0.00015615594446025376, 'samples': 18072768, 'steps': 94128, 'loss/train': 0.9625263810157776} 08/31/2021 06:17:20 - INFO - __main__ - Step 94130: {'lr': 0.00015615102580582302, 'samples': 18072960, 'steps': 94129, 'loss/train': 0.9874295592308044} 08/31/2021 06:17:20 - INFO - __main__ - Step 94131: {'lr': 0.0001561461071936792, 'samples': 18073152, 'steps': 94130, 'loss/train': 1.2348816394805908} 08/31/2021 06:17:21 - INFO - __main__ - Step 94132: {'lr': 0.00015614118862382456, 'samples': 18073344, 'steps': 94131, 'loss/train': 1.388765573501587} 08/31/2021 06:17:22 - INFO - __main__ - Step 94133: {'lr': 0.00015613627009626116, 'samples': 18073536, 'steps': 94132, 'loss/train': 0.5432755947113037} 08/31/2021 06:17:23 - INFO - __main__ - Step 94134: {'lr': 0.0001561313516109913, 'samples': 18073728, 'steps': 94133, 'loss/train': 0.8886851668357849} 08/31/2021 06:17:23 - INFO - __main__ - Step 94135: {'lr': 0.00015612643316801722, 'samples': 18073920, 'steps': 94134, 'loss/train': 0.16662639379501343} 08/31/2021 06:17:23 - INFO - __main__ - Step 94136: {'lr': 0.0001561215147673411, 'samples': 18074112, 'steps': 94135, 'loss/train': 1.3343462944030762} 08/31/2021 06:17:24 - INFO - __main__ - Step 94137: {'lr': 0.0001561165964089652, 'samples': 18074304, 'steps': 94136, 'loss/train': 1.0622093677520752} 08/31/2021 06:17:25 - INFO - __main__ - Step 94138: {'lr': 0.0001561116780928917, 'samples': 18074496, 'steps': 94137, 'loss/train': 1.6534093618392944} 08/31/2021 06:17:26 - INFO - __main__ - Step 94139: {'lr': 0.00015610675981912283, 'samples': 18074688, 'steps': 94138, 'loss/train': 0.8571233153343201} 08/31/2021 06:17:26 - INFO - __main__ - Step 94140: {'lr': 0.00015610184158766082, 'samples': 18074880, 'steps': 94139, 'loss/train': 0.9660701751708984} 08/31/2021 06:17:26 - INFO - __main__ - Step 94141: {'lr': 0.00015609692339850785, 'samples': 18075072, 'steps': 94140, 'loss/train': 1.4235503673553467} 08/31/2021 06:17:27 - INFO - __main__ - Step 94142: {'lr': 0.00015609200525166616, 'samples': 18075264, 'steps': 94141, 'loss/train': 1.4752963781356812} 08/31/2021 06:17:28 - INFO - __main__ - Step 94143: {'lr': 0.000156087087147138, 'samples': 18075456, 'steps': 94142, 'loss/train': 1.312512755393982} 08/31/2021 06:17:29 - INFO - __main__ - Step 94144: {'lr': 0.00015608216908492555, 'samples': 18075648, 'steps': 94143, 'loss/train': 1.3537795543670654} 08/31/2021 06:17:29 - INFO - __main__ - Step 94145: {'lr': 0.00015607725106503103, 'samples': 18075840, 'steps': 94144, 'loss/train': 2.015760660171509} 08/31/2021 06:17:29 - INFO - __main__ - Step 94146: {'lr': 0.00015607233308745662, 'samples': 18076032, 'steps': 94145, 'loss/train': 0.979049026966095} 08/31/2021 06:17:30 - INFO - __main__ - Step 94147: {'lr': 0.00015606741515220457, 'samples': 18076224, 'steps': 94146, 'loss/train': 2.0627822875976562} 08/31/2021 06:17:30 - INFO - __main__ - Step 94148: {'lr': 0.00015606249725927707, 'samples': 18076416, 'steps': 94147, 'loss/train': 0.901544988155365} 08/31/2021 06:17:32 - INFO - __main__ - Step 94149: {'lr': 0.00015605757940867637, 'samples': 18076608, 'steps': 94148, 'loss/train': 1.202897548675537} 08/31/2021 06:17:32 - INFO - __main__ - Step 94150: {'lr': 0.00015605266160040467, 'samples': 18076800, 'steps': 94149, 'loss/train': 1.4296807050704956} 08/31/2021 06:17:32 - INFO - __main__ - Step 94151: {'lr': 0.00015604774383446422, 'samples': 18076992, 'steps': 94150, 'loss/train': 1.3208205699920654} 08/31/2021 06:17:33 - INFO - __main__ - Step 94152: {'lr': 0.0001560428261108572, 'samples': 18077184, 'steps': 94151, 'loss/train': 1.189363956451416} 08/31/2021 06:17:33 - INFO - __main__ - Step 94153: {'lr': 0.00015603790842958582, 'samples': 18077376, 'steps': 94152, 'loss/train': 1.6059266328811646} 08/31/2021 06:17:35 - INFO - __main__ - Step 94154: {'lr': 0.0001560329907906523, 'samples': 18077568, 'steps': 94153, 'loss/train': 2.1940834522247314} 08/31/2021 06:17:35 - INFO - __main__ - Step 94155: {'lr': 0.00015602807319405892, 'samples': 18077760, 'steps': 94154, 'loss/train': 0.8849645853042603} 08/31/2021 06:17:35 - INFO - __main__ - Step 94156: {'lr': 0.0001560231556398078, 'samples': 18077952, 'steps': 94155, 'loss/train': 0.960627555847168} 08/31/2021 06:17:36 - INFO - __main__ - Step 94157: {'lr': 0.00015601823812790117, 'samples': 18078144, 'steps': 94156, 'loss/train': 1.1482163667678833} 08/31/2021 06:17:36 - INFO - __main__ - Step 94158: {'lr': 0.00015601332065834128, 'samples': 18078336, 'steps': 94157, 'loss/train': 5.784910678863525} 08/31/2021 06:17:38 - INFO - __main__ - Step 94159: {'lr': 0.0001560084032311304, 'samples': 18078528, 'steps': 94158, 'loss/train': 1.1379015445709229} 08/31/2021 06:17:38 - INFO - __main__ - Step 94160: {'lr': 0.00015600348584627068, 'samples': 18078720, 'steps': 94159, 'loss/train': 1.246097207069397} 08/31/2021 06:17:39 - INFO - __main__ - Step 94161: {'lr': 0.00015599856850376427, 'samples': 18078912, 'steps': 94160, 'loss/train': 0.9445534348487854} 08/31/2021 06:17:39 - INFO - __main__ - Step 94162: {'lr': 0.00015599365120361346, 'samples': 18079104, 'steps': 94161, 'loss/train': 1.3962886333465576} 08/31/2021 06:17:39 - INFO - __main__ - Step 94163: {'lr': 0.00015598873394582046, 'samples': 18079296, 'steps': 94162, 'loss/train': 0.4661487340927124} 08/31/2021 06:17:41 - INFO - __main__ - Step 94164: {'lr': 0.00015598381673038753, 'samples': 18079488, 'steps': 94163, 'loss/train': 0.8218596577644348} 08/31/2021 06:17:41 - INFO - __main__ - Step 94165: {'lr': 0.00015597889955731682, 'samples': 18079680, 'steps': 94164, 'loss/train': 1.0007935762405396} 08/31/2021 06:17:42 - INFO - __main__ - Step 94166: {'lr': 0.00015597398242661058, 'samples': 18079872, 'steps': 94165, 'loss/train': 1.0649322271347046} 08/31/2021 06:17:42 - INFO - __main__ - Step 94167: {'lr': 0.00015596906533827098, 'samples': 18080064, 'steps': 94166, 'loss/train': 1.185230016708374} 08/31/2021 06:17:42 - INFO - __main__ - Step 94168: {'lr': 0.0001559641482923003, 'samples': 18080256, 'steps': 94167, 'loss/train': 2.2039923667907715} 08/31/2021 06:17:43 - INFO - __main__ - Step 94169: {'lr': 0.0001559592312887007, 'samples': 18080448, 'steps': 94168, 'loss/train': 1.216976523399353} 08/31/2021 06:17:45 - INFO - __main__ - Step 94170: {'lr': 0.00015595431432747443, 'samples': 18080640, 'steps': 94169, 'loss/train': 1.096153974533081} 08/31/2021 06:17:45 - INFO - __main__ - Step 94171: {'lr': 0.00015594939740862368, 'samples': 18080832, 'steps': 94170, 'loss/train': 1.4629372358322144} 08/31/2021 06:17:46 - INFO - __main__ - Step 94172: {'lr': 0.00015594448053215073, 'samples': 18081024, 'steps': 94171, 'loss/train': 1.5548672676086426} 08/31/2021 06:17:46 - INFO - __main__ - Step 94173: {'lr': 0.00015593956369805773, 'samples': 18081216, 'steps': 94172, 'loss/train': 0.15233711898326874} 08/31/2021 06:17:46 - INFO - __main__ - Step 94174: {'lr': 0.00015593464690634687, 'samples': 18081408, 'steps': 94173, 'loss/train': 1.4492602348327637} 08/31/2021 06:17:48 - INFO - __main__ - Step 94175: {'lr': 0.00015592973015702042, 'samples': 18081600, 'steps': 94174, 'loss/train': 1.6208184957504272} 08/31/2021 06:17:48 - INFO - __main__ - Step 94176: {'lr': 0.00015592481345008064, 'samples': 18081792, 'steps': 94175, 'loss/train': 1.1907697916030884} 08/31/2021 06:17:49 - INFO - __main__ - Step 94177: {'lr': 0.00015591989678552962, 'samples': 18081984, 'steps': 94176, 'loss/train': 1.5571225881576538} 08/31/2021 06:17:49 - INFO - __main__ - Step 94178: {'lr': 0.00015591498016336966, 'samples': 18082176, 'steps': 94177, 'loss/train': 1.4194741249084473} 08/31/2021 06:17:49 - INFO - __main__ - Step 94179: {'lr': 0.00015591006358360294, 'samples': 18082368, 'steps': 94178, 'loss/train': 0.9771440029144287} 08/31/2021 06:17:51 - INFO - __main__ - Step 94180: {'lr': 0.0001559051470462317, 'samples': 18082560, 'steps': 94179, 'loss/train': 1.2577680349349976} 08/31/2021 06:17:51 - INFO - __main__ - Step 94181: {'lr': 0.00015590023055125817, 'samples': 18082752, 'steps': 94180, 'loss/train': 1.0414825677871704} 08/31/2021 06:17:52 - INFO - __main__ - Step 94182: {'lr': 0.0001558953140986845, 'samples': 18082944, 'steps': 94181, 'loss/train': 1.2931252717971802} 08/31/2021 06:17:52 - INFO - __main__ - Step 94183: {'lr': 0.00015589039768851298, 'samples': 18083136, 'steps': 94182, 'loss/train': 1.2995688915252686} 08/31/2021 06:17:52 - INFO - __main__ - Step 94184: {'lr': 0.00015588548132074582, 'samples': 18083328, 'steps': 94183, 'loss/train': 0.9850038290023804} 08/31/2021 06:17:54 - INFO - __main__ - Step 94185: {'lr': 0.00015588056499538517, 'samples': 18083520, 'steps': 94184, 'loss/train': 0.5874431729316711} 08/31/2021 06:17:54 - INFO - __main__ - Step 94186: {'lr': 0.00015587564871243333, 'samples': 18083712, 'steps': 94185, 'loss/train': 1.2887567281723022} 08/31/2021 06:17:55 - INFO - __main__ - Step 94187: {'lr': 0.0001558707324718925, 'samples': 18083904, 'steps': 94186, 'loss/train': 0.8787146806716919} 08/31/2021 06:17:55 - INFO - __main__ - Step 94188: {'lr': 0.00015586581627376482, 'samples': 18084096, 'steps': 94187, 'loss/train': 0.7100610136985779} 08/31/2021 06:17:55 - INFO - __main__ - Step 94189: {'lr': 0.00015586090011805254, 'samples': 18084288, 'steps': 94188, 'loss/train': 1.443636178970337} 08/31/2021 06:17:57 - INFO - __main__ - Step 94190: {'lr': 0.00015585598400475788, 'samples': 18084480, 'steps': 94189, 'loss/train': 0.4176374077796936} 08/31/2021 06:17:57 - INFO - __main__ - Step 94191: {'lr': 0.00015585106793388303, 'samples': 18084672, 'steps': 94190, 'loss/train': 1.730666160583496} 08/31/2021 06:17:58 - INFO - __main__ - Step 94192: {'lr': 0.00015584615190543028, 'samples': 18084864, 'steps': 94191, 'loss/train': 1.7226159572601318} 08/31/2021 06:17:58 - INFO - __main__ - Step 94193: {'lr': 0.00015584123591940179, 'samples': 18085056, 'steps': 94192, 'loss/train': 1.4289389848709106} 08/31/2021 06:17:58 - INFO - __main__ - Step 94194: {'lr': 0.00015583631997579978, 'samples': 18085248, 'steps': 94193, 'loss/train': 1.465842604637146} 08/31/2021 06:18:00 - INFO - __main__ - Step 94195: {'lr': 0.00015583140407462648, 'samples': 18085440, 'steps': 94194, 'loss/train': 1.4112629890441895} 08/31/2021 06:18:00 - INFO - __main__ - Step 94196: {'lr': 0.00015582648821588408, 'samples': 18085632, 'steps': 94195, 'loss/train': 1.5375221967697144} 08/31/2021 06:18:01 - INFO - __main__ - Step 94197: {'lr': 0.0001558215723995748, 'samples': 18085824, 'steps': 94196, 'loss/train': 0.9716324210166931} 08/31/2021 06:18:01 - INFO - __main__ - Step 94198: {'lr': 0.00015581665662570092, 'samples': 18086016, 'steps': 94197, 'loss/train': 0.7882241010665894} 08/31/2021 06:18:01 - INFO - __main__ - Step 94199: {'lr': 0.00015581174089426464, 'samples': 18086208, 'steps': 94198, 'loss/train': 0.7119746804237366} 08/31/2021 06:18:03 - INFO - __main__ - Step 94200: {'lr': 0.00015580682520526806, 'samples': 18086400, 'steps': 94199, 'loss/train': 1.3922252655029297} 08/31/2021 06:18:04 - INFO - __main__ - Step 94201: {'lr': 0.00015580190955871348, 'samples': 18086592, 'steps': 94200, 'loss/train': 1.1456831693649292} 08/31/2021 06:18:04 - INFO - __main__ - Step 94202: {'lr': 0.00015579699395460312, 'samples': 18086784, 'steps': 94201, 'loss/train': 0.6759202480316162} 08/31/2021 06:18:04 - INFO - __main__ - Step 94203: {'lr': 0.00015579207839293917, 'samples': 18086976, 'steps': 94202, 'loss/train': 1.0435733795166016} 08/31/2021 06:18:05 - INFO - __main__ - Step 94204: {'lr': 0.00015578716287372384, 'samples': 18087168, 'steps': 94203, 'loss/train': 1.1824069023132324} 08/31/2021 06:18:05 - INFO - __main__ - Step 94205: {'lr': 0.00015578224739695937, 'samples': 18087360, 'steps': 94204, 'loss/train': 1.084783911705017} 08/31/2021 06:18:06 - INFO - __main__ - Step 94206: {'lr': 0.00015577733196264795, 'samples': 18087552, 'steps': 94205, 'loss/train': 0.05130432918667793} 08/31/2021 06:18:07 - INFO - __main__ - Step 94207: {'lr': 0.00015577241657079184, 'samples': 18087744, 'steps': 94206, 'loss/train': 0.04352452978491783} 08/31/2021 06:18:07 - INFO - __main__ - Step 94208: {'lr': 0.0001557675012213932, 'samples': 18087936, 'steps': 94207, 'loss/train': 0.5331090688705444} 08/31/2021 06:18:08 - INFO - __main__ - Step 94209: {'lr': 0.00015576258591445431, 'samples': 18088128, 'steps': 94208, 'loss/train': 1.3371931314468384} 08/31/2021 06:18:08 - INFO - __main__ - Step 94210: {'lr': 0.00015575767064997728, 'samples': 18088320, 'steps': 94209, 'loss/train': 0.8578996658325195} 08/31/2021 06:18:10 - INFO - __main__ - Step 94211: {'lr': 0.00015575275542796443, 'samples': 18088512, 'steps': 94210, 'loss/train': 0.16541697084903717} 08/31/2021 06:18:10 - INFO - __main__ - Step 94212: {'lr': 0.00015574784024841804, 'samples': 18088704, 'steps': 94211, 'loss/train': 1.1394991874694824} 08/31/2021 06:18:10 - INFO - __main__ - Step 94213: {'lr': 0.00015574292511134007, 'samples': 18088896, 'steps': 94212, 'loss/train': 0.9788016676902771} 08/31/2021 06:18:11 - INFO - __main__ - Step 94214: {'lr': 0.00015573801001673293, 'samples': 18089088, 'steps': 94213, 'loss/train': 1.2205607891082764} 08/31/2021 06:18:11 - INFO - __main__ - Step 94215: {'lr': 0.00015573309496459881, 'samples': 18089280, 'steps': 94214, 'loss/train': 1.1580227613449097} 08/31/2021 06:18:13 - INFO - __main__ - Step 94216: {'lr': 0.00015572817995493986, 'samples': 18089472, 'steps': 94215, 'loss/train': 4.1659393310546875} 08/31/2021 06:18:13 - INFO - __main__ - Step 94217: {'lr': 0.00015572326498775835, 'samples': 18089664, 'steps': 94216, 'loss/train': 1.1859071254730225} 08/31/2021 06:18:13 - INFO - __main__ - Step 94218: {'lr': 0.00015571835006305645, 'samples': 18089856, 'steps': 94217, 'loss/train': 1.2531278133392334} 08/31/2021 06:18:14 - INFO - __main__ - Step 94219: {'lr': 0.00015571343518083647, 'samples': 18090048, 'steps': 94218, 'loss/train': 1.388136863708496} 08/31/2021 06:18:14 - INFO - __main__ - Step 94220: {'lr': 0.0001557085203411005, 'samples': 18090240, 'steps': 94219, 'loss/train': 0.9315336346626282} 08/31/2021 06:18:16 - INFO - __main__ - Step 94221: {'lr': 0.00015570360554385089, 'samples': 18090432, 'steps': 94220, 'loss/train': 1.7456780672073364} 08/31/2021 06:18:17 - INFO - __main__ - Step 94222: {'lr': 0.0001556986907890897, 'samples': 18090624, 'steps': 94221, 'loss/train': 1.1817559003829956} 08/31/2021 06:18:17 - INFO - __main__ - Step 94223: {'lr': 0.00015569377607681928, 'samples': 18090816, 'steps': 94222, 'loss/train': 1.3622084856033325} 08/31/2021 06:18:17 - INFO - __main__ - Step 94224: {'lr': 0.00015568886140704174, 'samples': 18091008, 'steps': 94223, 'loss/train': 1.536946415901184} 08/31/2021 06:18:18 - INFO - __main__ - Step 94225: {'lr': 0.00015568394677975938, 'samples': 18091200, 'steps': 94224, 'loss/train': 1.036156415939331} 08/31/2021 06:18:18 - INFO - __main__ - Step 94226: {'lr': 0.00015567903219497448, 'samples': 18091392, 'steps': 94225, 'loss/train': 1.194503903388977} 08/31/2021 06:18:20 - INFO - __main__ - Step 94227: {'lr': 0.00015567411765268904, 'samples': 18091584, 'steps': 94226, 'loss/train': 1.4011422395706177} 08/31/2021 06:18:20 - INFO - __main__ - Step 94228: {'lr': 0.0001556692031529054, 'samples': 18091776, 'steps': 94227, 'loss/train': 0.5559911131858826} 08/31/2021 06:18:21 - INFO - __main__ - Step 94229: {'lr': 0.00015566428869562575, 'samples': 18091968, 'steps': 94228, 'loss/train': 1.3461171388626099} 08/31/2021 06:18:21 - INFO - __main__ - Step 94230: {'lr': 0.00015565937428085232, 'samples': 18092160, 'steps': 94229, 'loss/train': 0.153316468000412} 08/31/2021 06:18:21 - INFO - __main__ - Step 94231: {'lr': 0.00015565445990858729, 'samples': 18092352, 'steps': 94230, 'loss/train': 1.2487822771072388} 08/31/2021 06:18:23 - INFO - __main__ - Step 94232: {'lr': 0.00015564954557883292, 'samples': 18092544, 'steps': 94231, 'loss/train': 1.3432376384735107} 08/31/2021 06:18:24 - INFO - __main__ - Step 94233: {'lr': 0.00015564463129159146, 'samples': 18092736, 'steps': 94232, 'loss/train': 1.5292549133300781} 08/31/2021 06:18:24 - INFO - __main__ - Step 94234: {'lr': 0.00015563971704686503, 'samples': 18092928, 'steps': 94233, 'loss/train': 1.5757734775543213} 08/31/2021 06:18:24 - INFO - __main__ - Step 94235: {'lr': 0.00015563480284465586, 'samples': 18093120, 'steps': 94234, 'loss/train': 1.3666845560073853} 08/31/2021 06:18:25 - INFO - __main__ - Step 94236: {'lr': 0.00015562988868496626, 'samples': 18093312, 'steps': 94235, 'loss/train': 0.985465943813324} 08/31/2021 06:18:26 - INFO - __main__ - Step 94237: {'lr': 0.00015562497456779833, 'samples': 18093504, 'steps': 94236, 'loss/train': 0.6574523448944092} 08/31/2021 06:18:27 - INFO - __main__ - Step 94238: {'lr': 0.00015562006049315433, 'samples': 18093696, 'steps': 94237, 'loss/train': 0.9195581078529358} 08/31/2021 06:18:27 - INFO - __main__ - Step 94239: {'lr': 0.00015561514646103658, 'samples': 18093888, 'steps': 94238, 'loss/train': 1.3281108140945435} 08/31/2021 06:18:27 - INFO - __main__ - Step 94240: {'lr': 0.0001556102324714471, 'samples': 18094080, 'steps': 94239, 'loss/train': 0.9793795347213745} 08/31/2021 06:18:28 - INFO - __main__ - Step 94241: {'lr': 0.0001556053185243882, 'samples': 18094272, 'steps': 94240, 'loss/train': 1.6442900896072388} 08/31/2021 06:18:29 - INFO - __main__ - Step 94242: {'lr': 0.00015560040461986204, 'samples': 18094464, 'steps': 94241, 'loss/train': 0.6309212446212769} 08/31/2021 06:18:30 - INFO - __main__ - Step 94243: {'lr': 0.00015559549075787094, 'samples': 18094656, 'steps': 94242, 'loss/train': 1.3377257585525513} 08/31/2021 06:18:30 - INFO - __main__ - Step 94244: {'lr': 0.000155590576938417, 'samples': 18094848, 'steps': 94243, 'loss/train': 0.9809268712997437} 08/31/2021 06:18:30 - INFO - __main__ - Step 94245: {'lr': 0.00015558566316150251, 'samples': 18095040, 'steps': 94244, 'loss/train': 1.40181565284729} 08/31/2021 06:18:31 - INFO - __main__ - Step 94246: {'lr': 0.0001555807494271297, 'samples': 18095232, 'steps': 94245, 'loss/train': 1.7627713680267334} 08/31/2021 06:18:32 - INFO - __main__ - Step 94247: {'lr': 0.0001555758357353007, 'samples': 18095424, 'steps': 94246, 'loss/train': 1.2879854440689087} 08/31/2021 06:18:32 - INFO - __main__ - Step 94248: {'lr': 0.00015557092208601781, 'samples': 18095616, 'steps': 94247, 'loss/train': 0.8358944654464722} 08/31/2021 06:18:33 - INFO - __main__ - Step 94249: {'lr': 0.0001555660084792832, 'samples': 18095808, 'steps': 94248, 'loss/train': 1.1896337270736694} 08/31/2021 06:18:33 - INFO - __main__ - Step 94250: {'lr': 0.00015556109491509908, 'samples': 18096000, 'steps': 94249, 'loss/train': 0.2921907901763916} 08/31/2021 06:18:34 - INFO - __main__ - Step 94251: {'lr': 0.00015555618139346763, 'samples': 18096192, 'steps': 94250, 'loss/train': 1.3258657455444336} 08/31/2021 06:18:35 - INFO - __main__ - Step 94252: {'lr': 0.00015555126791439114, 'samples': 18096384, 'steps': 94251, 'loss/train': 1.0703723430633545} 08/31/2021 06:18:35 - INFO - __main__ - Step 94253: {'lr': 0.00015554635447787192, 'samples': 18096576, 'steps': 94252, 'loss/train': 1.4212627410888672} 08/31/2021 06:18:36 - INFO - __main__ - Step 94254: {'lr': 0.00015554144108391192, 'samples': 18096768, 'steps': 94253, 'loss/train': 1.3791571855545044} 08/31/2021 06:18:36 - INFO - __main__ - Step 94255: {'lr': 0.0001555365277325135, 'samples': 18096960, 'steps': 94254, 'loss/train': 0.40501585602760315} 08/31/2021 06:18:37 - INFO - __main__ - Step 94256: {'lr': 0.00015553161442367886, 'samples': 18097152, 'steps': 94255, 'loss/train': 1.2655842304229736} 08/31/2021 06:18:37 - INFO - __main__ - Step 94257: {'lr': 0.00015552670115741022, 'samples': 18097344, 'steps': 94256, 'loss/train': 1.6567491292953491} 08/31/2021 06:18:38 - INFO - __main__ - Step 94258: {'lr': 0.0001555217879337098, 'samples': 18097536, 'steps': 94257, 'loss/train': 1.6131508350372314} 08/31/2021 06:18:39 - INFO - __main__ - Step 94259: {'lr': 0.00015551687475257977, 'samples': 18097728, 'steps': 94258, 'loss/train': 0.9113365411758423} 08/31/2021 06:18:39 - INFO - __main__ - Step 94260: {'lr': 0.00015551196161402243, 'samples': 18097920, 'steps': 94259, 'loss/train': 1.0285720825195312} 08/31/2021 06:18:40 - INFO - __main__ - Step 94261: {'lr': 0.00015550704851803991, 'samples': 18098112, 'steps': 94260, 'loss/train': 1.1923604011535645} 08/31/2021 06:18:40 - INFO - __main__ - Step 94262: {'lr': 0.00015550213546463443, 'samples': 18098304, 'steps': 94261, 'loss/train': 0.03963946923613548} 08/31/2021 06:18:41 - INFO - __main__ - Step 94263: {'lr': 0.00015549722245380827, 'samples': 18098496, 'steps': 94262, 'loss/train': 1.1634725332260132} 08/31/2021 06:18:42 - INFO - __main__ - Step 94264: {'lr': 0.00015549230948556358, 'samples': 18098688, 'steps': 94263, 'loss/train': 0.728005051612854} 08/31/2021 06:18:42 - INFO - __main__ - Step 94265: {'lr': 0.00015548739655990262, 'samples': 18098880, 'steps': 94264, 'loss/train': 1.406978726387024} 08/31/2021 06:18:43 - INFO - __main__ - Step 94266: {'lr': 0.00015548248367682767, 'samples': 18099072, 'steps': 94265, 'loss/train': 1.8371213674545288} 08/31/2021 06:18:43 - INFO - __main__ - Step 94267: {'lr': 0.0001554775708363408, 'samples': 18099264, 'steps': 94266, 'loss/train': 1.4099947214126587} 08/31/2021 06:18:44 - INFO - __main__ - Step 94268: {'lr': 0.00015547265803844421, 'samples': 18099456, 'steps': 94267, 'loss/train': 0.45237094163894653} 08/31/2021 06:18:45 - INFO - __main__ - Step 94269: {'lr': 0.0001554677452831402, 'samples': 18099648, 'steps': 94268, 'loss/train': 1.261700987815857} 08/31/2021 06:18:45 - INFO - __main__ - Step 94270: {'lr': 0.00015546283257043098, 'samples': 18099840, 'steps': 94269, 'loss/train': 1.4896596670150757} 08/31/2021 06:18:46 - INFO - __main__ - Step 94271: {'lr': 0.00015545791990031872, 'samples': 18100032, 'steps': 94270, 'loss/train': 0.03118208423256874} 08/31/2021 06:18:46 - INFO - __main__ - Step 94272: {'lr': 0.0001554530072728057, 'samples': 18100224, 'steps': 94271, 'loss/train': 0.7480906844139099} 08/31/2021 06:18:48 - INFO - __main__ - Step 94273: {'lr': 0.00015544809468789406, 'samples': 18100416, 'steps': 94272, 'loss/train': 1.4424232244491577} 08/31/2021 06:18:48 - INFO - __main__ - Step 94274: {'lr': 0.00015544318214558606, 'samples': 18100608, 'steps': 94273, 'loss/train': 0.03704536333680153} 08/31/2021 06:18:48 - INFO - __main__ - Step 94275: {'lr': 0.00015543826964588392, 'samples': 18100800, 'steps': 94274, 'loss/train': 1.1558959484100342} 08/31/2021 06:18:49 - INFO - __main__ - Step 94276: {'lr': 0.00015543335718878982, 'samples': 18100992, 'steps': 94275, 'loss/train': 1.7658376693725586} 08/31/2021 06:18:49 - INFO - __main__ - Step 94277: {'lr': 0.000155428444774306, 'samples': 18101184, 'steps': 94276, 'loss/train': 0.688883364200592} 08/31/2021 06:18:52 - INFO - __main__ - Step 94278: {'lr': 0.00015542353240243474, 'samples': 18101376, 'steps': 94277, 'loss/train': 0.6022616624832153} 08/31/2021 06:18:52 - INFO - __main__ - Step 94279: {'lr': 0.00015541862007317807, 'samples': 18101568, 'steps': 94278, 'loss/train': 1.3146828413009644} 08/31/2021 06:18:53 - INFO - __main__ - Step 94280: {'lr': 0.00015541370778653841, 'samples': 18101760, 'steps': 94279, 'loss/train': 0.4329131245613098} 08/31/2021 06:18:53 - INFO - __main__ - Step 94281: {'lr': 0.0001554087955425178, 'samples': 18101952, 'steps': 94280, 'loss/train': 0.9229162931442261} 08/31/2021 06:18:53 - INFO - __main__ - Step 94282: {'lr': 0.00015540388334111852, 'samples': 18102144, 'steps': 94281, 'loss/train': 1.3927316665649414} 08/31/2021 06:18:54 - INFO - __main__ - Step 94283: {'lr': 0.0001553989711823428, 'samples': 18102336, 'steps': 94282, 'loss/train': 1.0278637409210205} 08/31/2021 06:18:54 - INFO - __main__ - Step 94284: {'lr': 0.00015539405906619282, 'samples': 18102528, 'steps': 94283, 'loss/train': 5.767477989196777} 08/31/2021 06:18:55 - INFO - __main__ - Step 94285: {'lr': 0.00015538914699267088, 'samples': 18102720, 'steps': 94284, 'loss/train': 5.764154434204102} 08/31/2021 06:18:56 - INFO - __main__ - Step 94286: {'lr': 0.00015538423496177907, 'samples': 18102912, 'steps': 94285, 'loss/train': 1.7386853694915771} 08/31/2021 06:18:56 - INFO - __main__ - Step 94287: {'lr': 0.0001553793229735197, 'samples': 18103104, 'steps': 94286, 'loss/train': 1.3912872076034546} 08/31/2021 06:18:57 - INFO - __main__ - Step 94288: {'lr': 0.00015537441102789491, 'samples': 18103296, 'steps': 94287, 'loss/train': 1.147147297859192} 08/31/2021 06:18:57 - INFO - __main__ - Step 94289: {'lr': 0.00015536949912490702, 'samples': 18103488, 'steps': 94288, 'loss/train': 0.4503575265407562} 08/31/2021 06:18:58 - INFO - __main__ - Step 94290: {'lr': 0.00015536458726455812, 'samples': 18103680, 'steps': 94289, 'loss/train': 1.3706519603729248} 08/31/2021 06:18:59 - INFO - __main__ - Step 94291: {'lr': 0.00015535967544685048, 'samples': 18103872, 'steps': 94290, 'loss/train': 0.6241317391395569} 08/31/2021 06:18:59 - INFO - __main__ - Step 94292: {'lr': 0.0001553547636717863, 'samples': 18104064, 'steps': 94291, 'loss/train': 1.5399929285049438} 08/31/2021 06:19:00 - INFO - __main__ - Step 94293: {'lr': 0.0001553498519393679, 'samples': 18104256, 'steps': 94292, 'loss/train': 1.1316312551498413} 08/31/2021 06:19:00 - INFO - __main__ - Step 94294: {'lr': 0.00015534494024959728, 'samples': 18104448, 'steps': 94293, 'loss/train': 1.1605703830718994} 08/31/2021 06:19:02 - INFO - __main__ - Step 94295: {'lr': 0.00015534002860247682, 'samples': 18104640, 'steps': 94294, 'loss/train': 1.2535344362258911} 08/31/2021 06:19:02 - INFO - __main__ - Step 94296: {'lr': 0.00015533511699800868, 'samples': 18104832, 'steps': 94295, 'loss/train': 1.092376947402954} 08/31/2021 06:19:02 - INFO - __main__ - Step 94297: {'lr': 0.00015533020543619504, 'samples': 18105024, 'steps': 94296, 'loss/train': 1.3814637660980225} 08/31/2021 06:19:03 - INFO - __main__ - Step 94298: {'lr': 0.00015532529391703814, 'samples': 18105216, 'steps': 94297, 'loss/train': 1.5469659566879272} 08/31/2021 06:19:03 - INFO - __main__ - Step 94299: {'lr': 0.00015532038244054025, 'samples': 18105408, 'steps': 94298, 'loss/train': 0.995728075504303} 08/31/2021 06:19:03 - INFO - __main__ - Step 94300: {'lr': 0.00015531547100670356, 'samples': 18105600, 'steps': 94299, 'loss/train': 1.006205439567566} 08/31/2021 06:19:05 - INFO - __main__ - Step 94301: {'lr': 0.0001553105596155302, 'samples': 18105792, 'steps': 94300, 'loss/train': 2.081083059310913} 08/31/2021 06:19:05 - INFO - __main__ - Step 94302: {'lr': 0.00015530564826702245, 'samples': 18105984, 'steps': 94301, 'loss/train': 0.47472625970840454} 08/31/2021 06:19:06 - INFO - __main__ - Step 94303: {'lr': 0.00015530073696118252, 'samples': 18106176, 'steps': 94302, 'loss/train': 1.2009732723236084} 08/31/2021 06:19:06 - INFO - __main__ - Step 94304: {'lr': 0.0001552958256980126, 'samples': 18106368, 'steps': 94303, 'loss/train': 1.1730166673660278} 08/31/2021 06:19:06 - INFO - __main__ - Step 94305: {'lr': 0.00015529091447751494, 'samples': 18106560, 'steps': 94304, 'loss/train': 1.2081040143966675} 08/31/2021 06:19:08 - INFO - __main__ - Step 94306: {'lr': 0.00015528600329969171, 'samples': 18106752, 'steps': 94305, 'loss/train': 0.8779717683792114} 08/31/2021 06:19:08 - INFO - __main__ - Step 94307: {'lr': 0.00015528109216454523, 'samples': 18106944, 'steps': 94306, 'loss/train': 1.2972230911254883} 08/31/2021 06:19:08 - INFO - __main__ - Step 94308: {'lr': 0.00015527618107207756, 'samples': 18107136, 'steps': 94307, 'loss/train': 1.4471906423568726} 08/31/2021 06:19:09 - INFO - __main__ - Step 94309: {'lr': 0.00015527127002229097, 'samples': 18107328, 'steps': 94308, 'loss/train': 0.7386991381645203} 08/31/2021 06:19:09 - INFO - __main__ - Step 94310: {'lr': 0.0001552663590151877, 'samples': 18107520, 'steps': 94309, 'loss/train': 1.5476582050323486} 08/31/2021 06:19:11 - INFO - __main__ - Step 94311: {'lr': 0.00015526144805076998, 'samples': 18107712, 'steps': 94310, 'loss/train': 1.4965146780014038} 08/31/2021 06:19:11 - INFO - __main__ - Step 94312: {'lr': 0.00015525653712903994, 'samples': 18107904, 'steps': 94311, 'loss/train': 0.9527521729469299} 08/31/2021 06:19:11 - INFO - __main__ - Step 94313: {'lr': 0.00015525162624999985, 'samples': 18108096, 'steps': 94312, 'loss/train': 1.3717560768127441} 08/31/2021 06:19:12 - INFO - __main__ - Step 94314: {'lr': 0.00015524671541365193, 'samples': 18108288, 'steps': 94313, 'loss/train': 0.5977160334587097} 08/31/2021 06:19:12 - INFO - __main__ - Step 94315: {'lr': 0.00015524180461999837, 'samples': 18108480, 'steps': 94314, 'loss/train': 1.1124616861343384} 08/31/2021 06:19:14 - INFO - __main__ - Step 94316: {'lr': 0.0001552368938690414, 'samples': 18108672, 'steps': 94315, 'loss/train': 1.2064611911773682} 08/31/2021 06:19:14 - INFO - __main__ - Step 94317: {'lr': 0.00015523198316078318, 'samples': 18108864, 'steps': 94316, 'loss/train': 1.8129054307937622} 08/31/2021 06:19:14 - INFO - __main__ - Step 94318: {'lr': 0.000155227072495226, 'samples': 18109056, 'steps': 94317, 'loss/train': 0.9994035363197327} 08/31/2021 06:19:15 - INFO - __main__ - Step 94319: {'lr': 0.00015522216187237203, 'samples': 18109248, 'steps': 94318, 'loss/train': 1.4945614337921143} 08/31/2021 06:19:15 - INFO - __main__ - Step 94320: {'lr': 0.00015521725129222352, 'samples': 18109440, 'steps': 94319, 'loss/train': 1.2950413227081299} 08/31/2021 06:19:17 - INFO - __main__ - Step 94321: {'lr': 0.00015521234075478263, 'samples': 18109632, 'steps': 94320, 'loss/train': 1.0660988092422485} 08/31/2021 06:19:17 - INFO - __main__ - Step 94322: {'lr': 0.0001552074302600517, 'samples': 18109824, 'steps': 94321, 'loss/train': 0.5172632336616516} 08/31/2021 06:19:17 - INFO - __main__ - Step 94323: {'lr': 0.00015520251980803267, 'samples': 18110016, 'steps': 94322, 'loss/train': 1.2564221620559692} 08/31/2021 06:19:18 - INFO - __main__ - Step 94324: {'lr': 0.00015519760939872802, 'samples': 18110208, 'steps': 94323, 'loss/train': 1.8058841228485107} 08/31/2021 06:19:18 - INFO - __main__ - Step 94325: {'lr': 0.00015519269903213983, 'samples': 18110400, 'steps': 94324, 'loss/train': 1.5176079273223877} 08/31/2021 06:19:19 - INFO - __main__ - Step 94326: {'lr': 0.00015518778870827031, 'samples': 18110592, 'steps': 94325, 'loss/train': 1.591139793395996} 08/31/2021 06:19:20 - INFO - __main__ - Step 94327: {'lr': 0.00015518287842712178, 'samples': 18110784, 'steps': 94326, 'loss/train': 1.0118803977966309} 08/31/2021 06:19:20 - INFO - __main__ - Step 94328: {'lr': 0.00015517796818869634, 'samples': 18110976, 'steps': 94327, 'loss/train': 0.3213197588920593} 08/31/2021 06:19:21 - INFO - __main__ - Step 94329: {'lr': 0.00015517305799299624, 'samples': 18111168, 'steps': 94328, 'loss/train': 1.7979099750518799} 08/31/2021 06:19:21 - INFO - __main__ - Step 94330: {'lr': 0.0001551681478400237, 'samples': 18111360, 'steps': 94329, 'loss/train': 0.9889757037162781} 08/31/2021 06:19:23 - INFO - __main__ - Step 94331: {'lr': 0.00015516323772978097, 'samples': 18111552, 'steps': 94330, 'loss/train': 0.8302938938140869} 08/31/2021 06:19:24 - INFO - __main__ - Step 94332: {'lr': 0.00015515832766227017, 'samples': 18111744, 'steps': 94331, 'loss/train': 1.6271429061889648} 08/31/2021 06:19:24 - INFO - __main__ - Step 94333: {'lr': 0.00015515341763749368, 'samples': 18111936, 'steps': 94332, 'loss/train': 1.5150460004806519} 08/31/2021 06:19:24 - INFO - __main__ - Step 94334: {'lr': 0.0001551485076554535, 'samples': 18112128, 'steps': 94333, 'loss/train': 1.1029078960418701} 08/31/2021 06:19:25 - INFO - __main__ - Step 94335: {'lr': 0.00015514359771615194, 'samples': 18112320, 'steps': 94334, 'loss/train': 1.641058087348938} 08/31/2021 06:19:26 - INFO - __main__ - Step 94336: {'lr': 0.00015513868781959122, 'samples': 18112512, 'steps': 94335, 'loss/train': 1.2243412733078003} 08/31/2021 06:19:26 - INFO - __main__ - Step 94337: {'lr': 0.00015513377796577354, 'samples': 18112704, 'steps': 94336, 'loss/train': 0.190346360206604} 08/31/2021 06:19:27 - INFO - __main__ - Step 94338: {'lr': 0.00015512886815470113, 'samples': 18112896, 'steps': 94337, 'loss/train': 0.12983083724975586} 08/31/2021 06:19:27 - INFO - __main__ - Step 94339: {'lr': 0.00015512395838637616, 'samples': 18113088, 'steps': 94338, 'loss/train': 0.8337358832359314} 08/31/2021 06:19:27 - INFO - __main__ - Step 94340: {'lr': 0.00015511904866080084, 'samples': 18113280, 'steps': 94339, 'loss/train': 1.42217218875885} 08/31/2021 06:19:29 - INFO - __main__ - Step 94341: {'lr': 0.0001551141389779775, 'samples': 18113472, 'steps': 94340, 'loss/train': 0.89664226770401} 08/31/2021 06:19:29 - INFO - __main__ - Step 94342: {'lr': 0.00015510922933790818, 'samples': 18113664, 'steps': 94341, 'loss/train': 1.3558506965637207} 08/31/2021 06:19:30 - INFO - __main__ - Step 94343: {'lr': 0.00015510431974059523, 'samples': 18113856, 'steps': 94342, 'loss/train': 0.623163640499115} 08/31/2021 06:19:30 - INFO - __main__ - Step 94344: {'lr': 0.0001550994101860408, 'samples': 18114048, 'steps': 94343, 'loss/train': 1.7245423793792725} 08/31/2021 06:19:31 - INFO - __main__ - Step 94345: {'lr': 0.0001550945006742471, 'samples': 18114240, 'steps': 94344, 'loss/train': 1.0837363004684448} 08/31/2021 06:19:31 - INFO - __main__ - Step 94346: {'lr': 0.00015508959120521634, 'samples': 18114432, 'steps': 94345, 'loss/train': 0.5216077566146851} 08/31/2021 06:19:32 - INFO - __main__ - Step 94347: {'lr': 0.00015508468177895086, 'samples': 18114624, 'steps': 94346, 'loss/train': 1.579377293586731} 08/31/2021 06:19:33 - INFO - __main__ - Step 94348: {'lr': 0.0001550797723954527, 'samples': 18114816, 'steps': 94347, 'loss/train': 1.168376088142395} 08/31/2021 06:19:33 - INFO - __main__ - Step 94349: {'lr': 0.00015507486305472407, 'samples': 18115008, 'steps': 94348, 'loss/train': 0.9928193092346191} 08/31/2021 06:19:34 - INFO - __main__ - Step 94350: {'lr': 0.00015506995375676725, 'samples': 18115200, 'steps': 94349, 'loss/train': 0.984617292881012} 08/31/2021 06:19:34 - INFO - __main__ - Step 94351: {'lr': 0.00015506504450158446, 'samples': 18115392, 'steps': 94350, 'loss/train': 0.044617827981710434} 08/31/2021 06:19:36 - INFO - __main__ - Step 94352: {'lr': 0.0001550601352891779, 'samples': 18115584, 'steps': 94351, 'loss/train': 1.9868887662887573} 08/31/2021 06:19:36 - INFO - __main__ - Step 94353: {'lr': 0.00015505522611954976, 'samples': 18115776, 'steps': 94352, 'loss/train': 0.36535248160362244} 08/31/2021 06:19:36 - INFO - __main__ - Step 94354: {'lr': 0.00015505031699270227, 'samples': 18115968, 'steps': 94353, 'loss/train': 1.1977392435073853} 08/31/2021 06:19:37 - INFO - __main__ - Step 94355: {'lr': 0.00015504540790863764, 'samples': 18116160, 'steps': 94354, 'loss/train': 0.18026837706565857} 08/31/2021 06:19:37 - INFO - __main__ - Step 94356: {'lr': 0.0001550404988673581, 'samples': 18116352, 'steps': 94355, 'loss/train': 0.3816075026988983} 08/31/2021 06:19:39 - INFO - __main__ - Step 94357: {'lr': 0.00015503558986886584, 'samples': 18116544, 'steps': 94356, 'loss/train': 2.8526344299316406} 08/31/2021 06:19:39 - INFO - __main__ - Step 94358: {'lr': 0.00015503068091316308, 'samples': 18116736, 'steps': 94357, 'loss/train': 0.01882302202284336} 08/31/2021 06:19:40 - INFO - __main__ - Step 94359: {'lr': 0.00015502577200025204, 'samples': 18116928, 'steps': 94358, 'loss/train': 0.01745252124965191} 08/31/2021 06:19:40 - INFO - __main__ - Step 94360: {'lr': 0.00015502086313013504, 'samples': 18117120, 'steps': 94359, 'loss/train': 1.4962801933288574} 08/31/2021 06:19:40 - INFO - __main__ - Step 94361: {'lr': 0.000155015954302814, 'samples': 18117312, 'steps': 94360, 'loss/train': 0.9686358571052551} 08/31/2021 06:19:41 - INFO - __main__ - Step 94362: {'lr': 0.00015501104551829138, 'samples': 18117504, 'steps': 94361, 'loss/train': 1.3782411813735962} 08/31/2021 06:19:41 - INFO - __main__ - Step 94363: {'lr': 0.00015500613677656928, 'samples': 18117696, 'steps': 94362, 'loss/train': 1.0865024328231812} 08/31/2021 06:19:43 - INFO - __main__ - Step 94364: {'lr': 0.00015500122807764994, 'samples': 18117888, 'steps': 94363, 'loss/train': 0.1842295378446579} 08/31/2021 06:19:43 - INFO - __main__ - Step 94365: {'lr': 0.00015499631942153557, 'samples': 18118080, 'steps': 94364, 'loss/train': 0.8028274774551392} 08/31/2021 06:19:43 - INFO - __main__ - Step 94366: {'lr': 0.00015499141080822844, 'samples': 18118272, 'steps': 94365, 'loss/train': 1.0351669788360596} 08/31/2021 06:19:44 - INFO - __main__ - Step 94367: {'lr': 0.0001549865022377307, 'samples': 18118464, 'steps': 94366, 'loss/train': 0.29272764921188354} 08/31/2021 06:19:44 - INFO - __main__ - Step 94368: {'lr': 0.00015498159371004456, 'samples': 18118656, 'steps': 94367, 'loss/train': 1.2411634922027588} 08/31/2021 06:19:46 - INFO - __main__ - Step 94369: {'lr': 0.00015497668522517229, 'samples': 18118848, 'steps': 94368, 'loss/train': 1.4048770666122437} 08/31/2021 06:19:46 - INFO - __main__ - Step 94370: {'lr': 0.000154971776783116, 'samples': 18119040, 'steps': 94369, 'loss/train': 1.3752882480621338} 08/31/2021 06:19:47 - INFO - __main__ - Step 94371: {'lr': 0.00015496686838387797, 'samples': 18119232, 'steps': 94370, 'loss/train': 0.11696247011423111} 08/31/2021 06:19:47 - INFO - __main__ - Step 94372: {'lr': 0.00015496196002746042, 'samples': 18119424, 'steps': 94371, 'loss/train': 1.2088427543640137} 08/31/2021 06:19:47 - INFO - __main__ - Step 94373: {'lr': 0.00015495705171386553, 'samples': 18119616, 'steps': 94372, 'loss/train': 1.1005959510803223} 08/31/2021 06:19:49 - INFO - __main__ - Step 94374: {'lr': 0.00015495214344309565, 'samples': 18119808, 'steps': 94373, 'loss/train': 1.2685989141464233} 08/31/2021 06:19:49 - INFO - __main__ - Step 94375: {'lr': 0.00015494723521515278, 'samples': 18120000, 'steps': 94374, 'loss/train': 1.6407370567321777} 08/31/2021 06:19:49 - INFO - __main__ - Step 94376: {'lr': 0.00015494232703003918, 'samples': 18120192, 'steps': 94375, 'loss/train': 0.17693278193473816} 08/31/2021 06:19:50 - INFO - __main__ - Step 94377: {'lr': 0.00015493741888775715, 'samples': 18120384, 'steps': 94376, 'loss/train': 1.5495059490203857} 08/31/2021 06:19:50 - INFO - __main__ - Step 94378: {'lr': 0.00015493251078830877, 'samples': 18120576, 'steps': 94377, 'loss/train': 1.4172183275222778} 08/31/2021 06:19:52 - INFO - __main__ - Step 94379: {'lr': 0.00015492760273169644, 'samples': 18120768, 'steps': 94378, 'loss/train': 1.233871340751648} 08/31/2021 06:19:52 - INFO - __main__ - Step 94380: {'lr': 0.00015492269471792218, 'samples': 18120960, 'steps': 94379, 'loss/train': 0.5474933385848999} 08/31/2021 06:19:53 - INFO - __main__ - Step 94381: {'lr': 0.0001549177867469883, 'samples': 18121152, 'steps': 94380, 'loss/train': 1.5058761835098267} 08/31/2021 06:19:53 - INFO - __main__ - Step 94382: {'lr': 0.00015491287881889705, 'samples': 18121344, 'steps': 94381, 'loss/train': 0.7278217077255249} 08/31/2021 06:19:53 - INFO - __main__ - Step 94383: {'lr': 0.00015490797093365054, 'samples': 18121536, 'steps': 94382, 'loss/train': 1.3337541818618774} 08/31/2021 06:19:55 - INFO - __main__ - Step 94384: {'lr': 0.00015490306309125102, 'samples': 18121728, 'steps': 94383, 'loss/train': 1.1565296649932861} 08/31/2021 06:19:56 - INFO - __main__ - Step 94385: {'lr': 0.00015489815529170077, 'samples': 18121920, 'steps': 94384, 'loss/train': 1.0098193883895874} 08/31/2021 06:19:56 - INFO - __main__ - Step 94386: {'lr': 0.00015489324753500188, 'samples': 18122112, 'steps': 94385, 'loss/train': 0.7654393315315247} 08/31/2021 06:19:56 - INFO - __main__ - Step 94387: {'lr': 0.00015488833982115675, 'samples': 18122304, 'steps': 94386, 'loss/train': 1.36204993724823} 08/31/2021 06:19:57 - INFO - __main__ - Step 94388: {'lr': 0.00015488343215016738, 'samples': 18122496, 'steps': 94387, 'loss/train': 1.3834599256515503} 08/31/2021 06:19:57 - INFO - __main__ - Step 94389: {'lr': 0.00015487852452203605, 'samples': 18122688, 'steps': 94388, 'loss/train': 1.2149133682250977} 08/31/2021 06:19:59 - INFO - __main__ - Step 94390: {'lr': 0.000154873616936765, 'samples': 18122880, 'steps': 94389, 'loss/train': 0.17000830173492432} 08/31/2021 06:19:59 - INFO - __main__ - Step 94391: {'lr': 0.00015486870939435644, 'samples': 18123072, 'steps': 94390, 'loss/train': 1.5529534816741943} 08/31/2021 06:20:00 - INFO - __main__ - Step 94392: {'lr': 0.00015486380189481253, 'samples': 18123264, 'steps': 94391, 'loss/train': 0.7895346283912659} 08/31/2021 06:20:00 - INFO - __main__ - Step 94393: {'lr': 0.00015485889443813555, 'samples': 18123456, 'steps': 94392, 'loss/train': 0.27702340483665466} 08/31/2021 06:20:00 - INFO - __main__ - Step 94394: {'lr': 0.0001548539870243277, 'samples': 18123648, 'steps': 94393, 'loss/train': 0.6294711232185364} 08/31/2021 06:20:03 - INFO - __main__ - Step 94395: {'lr': 0.00015484907965339118, 'samples': 18123840, 'steps': 94394, 'loss/train': 1.137162446975708} 08/31/2021 06:20:03 - INFO - __main__ - Step 94396: {'lr': 0.00015484417232532817, 'samples': 18124032, 'steps': 94395, 'loss/train': 1.274584412574768} 08/31/2021 06:20:04 - INFO - __main__ - Step 94397: {'lr': 0.0001548392650401409, 'samples': 18124224, 'steps': 94396, 'loss/train': 1.3281512260437012} 08/31/2021 06:20:04 - INFO - __main__ - Step 94398: {'lr': 0.0001548343577978316, 'samples': 18124416, 'steps': 94397, 'loss/train': 0.8452656865119934} 08/31/2021 06:20:04 - INFO - __main__ - Step 94399: {'lr': 0.00015482945059840247, 'samples': 18124608, 'steps': 94398, 'loss/train': 1.5098460912704468} 08/31/2021 06:20:05 - INFO - __main__ - Step 94400: {'lr': 0.00015482454344185575, 'samples': 18124800, 'steps': 94399, 'loss/train': 1.630408763885498} 08/31/2021 06:20:05 - INFO - __main__ - Step 94401: {'lr': 0.0001548196363281937, 'samples': 18124992, 'steps': 94400, 'loss/train': 0.945127546787262} 08/31/2021 06:20:07 - INFO - __main__ - Step 94402: {'lr': 0.00015481472925741834, 'samples': 18125184, 'steps': 94401, 'loss/train': 1.1933915615081787} 08/31/2021 06:20:07 - INFO - __main__ - Step 94403: {'lr': 0.000154809822229532, 'samples': 18125376, 'steps': 94402, 'loss/train': 1.277593970298767} 08/31/2021 06:20:07 - INFO - __main__ - Step 94404: {'lr': 0.00015480491524453687, 'samples': 18125568, 'steps': 94403, 'loss/train': 1.5514202117919922} 08/31/2021 06:20:08 - INFO - __main__ - Step 94405: {'lr': 0.00015480000830243523, 'samples': 18125760, 'steps': 94404, 'loss/train': 0.5029330849647522} 08/31/2021 06:20:08 - INFO - __main__ - Step 94406: {'lr': 0.00015479510140322918, 'samples': 18125952, 'steps': 94405, 'loss/train': 1.1171880960464478} 08/31/2021 06:20:09 - INFO - __main__ - Step 94407: {'lr': 0.000154790194546921, 'samples': 18126144, 'steps': 94406, 'loss/train': 0.6444429755210876} 08/31/2021 06:20:10 - INFO - __main__ - Step 94408: {'lr': 0.0001547852877335129, 'samples': 18126336, 'steps': 94407, 'loss/train': 0.8892685174942017} 08/31/2021 06:20:10 - INFO - __main__ - Step 94409: {'lr': 0.0001547803809630071, 'samples': 18126528, 'steps': 94408, 'loss/train': 1.0061415433883667} 08/31/2021 06:20:11 - INFO - __main__ - Step 94410: {'lr': 0.00015477547423540578, 'samples': 18126720, 'steps': 94409, 'loss/train': 1.1617544889450073} 08/31/2021 06:20:11 - INFO - __main__ - Step 94411: {'lr': 0.00015477056755071114, 'samples': 18126912, 'steps': 94410, 'loss/train': 1.717930793762207} 08/31/2021 06:20:12 - INFO - __main__ - Step 94412: {'lr': 0.00015476566090892542, 'samples': 18127104, 'steps': 94411, 'loss/train': 0.5548768043518066} 08/31/2021 06:20:13 - INFO - __main__ - Step 94413: {'lr': 0.00015476075431005088, 'samples': 18127296, 'steps': 94412, 'loss/train': 0.9473716020584106} 08/31/2021 06:20:13 - INFO - __main__ - Step 94414: {'lr': 0.00015475584775408968, 'samples': 18127488, 'steps': 94413, 'loss/train': 1.4046911001205444} 08/31/2021 06:20:14 - INFO - __main__ - Step 94415: {'lr': 0.00015475094124104398, 'samples': 18127680, 'steps': 94414, 'loss/train': 1.3824392557144165} 08/31/2021 06:20:14 - INFO - __main__ - Step 94416: {'lr': 0.00015474603477091603, 'samples': 18127872, 'steps': 94415, 'loss/train': 0.39118245244026184} 08/31/2021 06:20:14 - INFO - __main__ - Step 94417: {'lr': 0.00015474112834370802, 'samples': 18128064, 'steps': 94416, 'loss/train': 0.8251573443412781} 08/31/2021 06:20:17 - INFO - __main__ - Step 94418: {'lr': 0.0001547362219594222, 'samples': 18128256, 'steps': 94417, 'loss/train': 0.5232747197151184} 08/31/2021 06:20:17 - INFO - __main__ - Step 94419: {'lr': 0.00015473131561806081, 'samples': 18128448, 'steps': 94418, 'loss/train': 1.1917500495910645} 08/31/2021 06:20:18 - INFO - __main__ - Step 94420: {'lr': 0.00015472640931962599, 'samples': 18128640, 'steps': 94419, 'loss/train': 0.2858414351940155} 08/31/2021 06:20:18 - INFO - __main__ - Step 94421: {'lr': 0.00015472150306411998, 'samples': 18128832, 'steps': 94420, 'loss/train': 0.25877252221107483} 08/31/2021 06:20:18 - INFO - __main__ - Step 94422: {'lr': 0.000154716596851545, 'samples': 18129024, 'steps': 94421, 'loss/train': 0.727226197719574} 08/31/2021 06:20:19 - INFO - __main__ - Step 94423: {'lr': 0.00015471169068190328, 'samples': 18129216, 'steps': 94422, 'loss/train': 2.1976959705352783} 08/31/2021 06:20:19 - INFO - __main__ - Step 94424: {'lr': 0.00015470678455519694, 'samples': 18129408, 'steps': 94423, 'loss/train': 1.205863118171692} 08/31/2021 06:20:21 - INFO - __main__ - Step 94425: {'lr': 0.00015470187847142829, 'samples': 18129600, 'steps': 94424, 'loss/train': 0.851832389831543} 08/31/2021 06:20:21 - INFO - __main__ - Step 94426: {'lr': 0.0001546969724305995, 'samples': 18129792, 'steps': 94425, 'loss/train': 0.9751107096672058} 08/31/2021 06:20:21 - INFO - __main__ - Step 94427: {'lr': 0.00015469206643271274, 'samples': 18129984, 'steps': 94426, 'loss/train': 1.4558377265930176} 08/31/2021 06:20:22 - INFO - __main__ - Step 94428: {'lr': 0.00015468716047777035, 'samples': 18130176, 'steps': 94427, 'loss/train': 0.925898015499115} 08/31/2021 06:20:22 - INFO - __main__ - Step 94429: {'lr': 0.0001546822545657744, 'samples': 18130368, 'steps': 94428, 'loss/train': 2.046121597290039} 08/31/2021 06:20:24 - INFO - __main__ - Step 94430: {'lr': 0.00015467734869672716, 'samples': 18130560, 'steps': 94429, 'loss/train': 1.3091118335723877} 08/31/2021 06:20:24 - INFO - __main__ - Step 94431: {'lr': 0.0001546724428706308, 'samples': 18130752, 'steps': 94430, 'loss/train': 0.8520321846008301} 08/31/2021 06:20:25 - INFO - __main__ - Step 94432: {'lr': 0.0001546675370874876, 'samples': 18130944, 'steps': 94431, 'loss/train': 1.4783804416656494} 08/31/2021 06:20:25 - INFO - __main__ - Step 94433: {'lr': 0.00015466263134729973, 'samples': 18131136, 'steps': 94432, 'loss/train': 0.42820480465888977} 08/31/2021 06:20:25 - INFO - __main__ - Step 94434: {'lr': 0.00015465772565006946, 'samples': 18131328, 'steps': 94433, 'loss/train': 1.258957862854004} 08/31/2021 06:20:27 - INFO - __main__ - Step 94435: {'lr': 0.0001546528199957989, 'samples': 18131520, 'steps': 94434, 'loss/train': 0.8600627779960632} 08/31/2021 06:20:28 - INFO - __main__ - Step 94436: {'lr': 0.00015464791438449032, 'samples': 18131712, 'steps': 94435, 'loss/train': 1.5899982452392578} 08/31/2021 06:20:28 - INFO - __main__ - Step 94437: {'lr': 0.0001546430088161459, 'samples': 18131904, 'steps': 94436, 'loss/train': 0.7349923849105835} 08/31/2021 06:20:28 - INFO - __main__ - Step 94438: {'lr': 0.00015463810329076789, 'samples': 18132096, 'steps': 94437, 'loss/train': 1.4841561317443848} 08/31/2021 06:20:29 - INFO - __main__ - Step 94439: {'lr': 0.00015463319780835845, 'samples': 18132288, 'steps': 94438, 'loss/train': 1.6341286897659302} 08/31/2021 06:20:30 - INFO - __main__ - Step 94440: {'lr': 0.00015462829236891984, 'samples': 18132480, 'steps': 94439, 'loss/train': 0.04408464580774307} 08/31/2021 06:20:30 - INFO - __main__ - Step 94441: {'lr': 0.00015462338697245427, 'samples': 18132672, 'steps': 94440, 'loss/train': 1.0276212692260742} 08/31/2021 06:20:31 - INFO - __main__ - Step 94442: {'lr': 0.00015461848161896392, 'samples': 18132864, 'steps': 94441, 'loss/train': 1.3421720266342163} 08/31/2021 06:20:31 - INFO - __main__ - Step 94443: {'lr': 0.00015461357630845097, 'samples': 18133056, 'steps': 94442, 'loss/train': 1.2051609754562378} 08/31/2021 06:20:31 - INFO - __main__ - Step 94444: {'lr': 0.0001546086710409177, 'samples': 18133248, 'steps': 94443, 'loss/train': 1.2890607118606567} 08/31/2021 06:20:32 - INFO - __main__ - Step 94445: {'lr': 0.00015460376581636633, 'samples': 18133440, 'steps': 94444, 'loss/train': 0.8750384449958801} 08/31/2021 06:20:34 - INFO - __main__ - Step 94446: {'lr': 0.000154598860634799, 'samples': 18133632, 'steps': 94445, 'loss/train': 1.8307253122329712} 08/31/2021 06:20:34 - INFO - __main__ - Step 94447: {'lr': 0.00015459395549621792, 'samples': 18133824, 'steps': 94446, 'loss/train': 1.8521502017974854} 08/31/2021 06:20:35 - INFO - __main__ - Step 94448: {'lr': 0.00015458905040062536, 'samples': 18134016, 'steps': 94447, 'loss/train': 1.2312421798706055} 08/31/2021 06:20:35 - INFO - __main__ - Step 94449: {'lr': 0.00015458414534802348, 'samples': 18134208, 'steps': 94448, 'loss/train': 0.9266657829284668} 08/31/2021 06:20:36 - INFO - __main__ - Step 94450: {'lr': 0.00015457924033841452, 'samples': 18134400, 'steps': 94449, 'loss/train': 1.3643800020217896} 08/31/2021 06:20:37 - INFO - __main__ - Step 94451: {'lr': 0.00015457433537180068, 'samples': 18134592, 'steps': 94450, 'loss/train': 1.2355303764343262} 08/31/2021 06:20:38 - INFO - __main__ - Step 94452: {'lr': 0.00015456943044818417, 'samples': 18134784, 'steps': 94451, 'loss/train': 1.2992072105407715} 08/31/2021 06:20:38 - INFO - __main__ - Step 94453: {'lr': 0.00015456452556756722, 'samples': 18134976, 'steps': 94452, 'loss/train': 1.3880752325057983} 08/31/2021 06:20:38 - INFO - __main__ - Step 94454: {'lr': 0.00015455962072995205, 'samples': 18135168, 'steps': 94453, 'loss/train': 0.3647903501987457} 08/31/2021 06:20:39 - INFO - __main__ - Step 94455: {'lr': 0.00015455471593534082, 'samples': 18135360, 'steps': 94454, 'loss/train': 0.8458422422409058} 08/31/2021 06:20:41 - INFO - __main__ - Step 94456: {'lr': 0.0001545498111837358, 'samples': 18135552, 'steps': 94455, 'loss/train': 5.491004943847656} 08/31/2021 06:20:41 - INFO - __main__ - Step 94457: {'lr': 0.00015454490647513907, 'samples': 18135744, 'steps': 94456, 'loss/train': 1.220663070678711} 08/31/2021 06:20:42 - INFO - __main__ - Step 94458: {'lr': 0.00015454000180955296, 'samples': 18135936, 'steps': 94457, 'loss/train': 1.2080588340759277} 08/31/2021 06:20:42 - INFO - __main__ - Step 94459: {'lr': 0.00015453509718697968, 'samples': 18136128, 'steps': 94458, 'loss/train': 1.5156160593032837} 08/31/2021 06:20:42 - INFO - __main__ - Step 94460: {'lr': 0.0001545301926074214, 'samples': 18136320, 'steps': 94459, 'loss/train': 1.5822793245315552} 08/31/2021 06:20:43 - INFO - __main__ - Step 94461: {'lr': 0.0001545252880708803, 'samples': 18136512, 'steps': 94460, 'loss/train': 0.047565482556819916} 08/31/2021 06:20:44 - INFO - __main__ - Step 94462: {'lr': 0.0001545203835773587, 'samples': 18136704, 'steps': 94461, 'loss/train': 0.017339227721095085} 08/31/2021 06:20:45 - INFO - __main__ - Step 94463: {'lr': 0.0001545154791268587, 'samples': 18136896, 'steps': 94462, 'loss/train': 0.9545417428016663} 08/31/2021 06:20:45 - INFO - __main__ - Step 94464: {'lr': 0.00015451057471938258, 'samples': 18137088, 'steps': 94463, 'loss/train': 0.8611682057380676} 08/31/2021 06:20:45 - INFO - __main__ - Step 94465: {'lr': 0.00015450567035493246, 'samples': 18137280, 'steps': 94464, 'loss/train': 0.5820348262786865} 08/31/2021 06:20:46 - INFO - __main__ - Step 94466: {'lr': 0.00015450076603351065, 'samples': 18137472, 'steps': 94465, 'loss/train': 1.3019200563430786} 08/31/2021 06:20:46 - INFO - __main__ - Step 94467: {'lr': 0.00015449586175511932, 'samples': 18137664, 'steps': 94466, 'loss/train': 0.9719635248184204} 08/31/2021 06:20:48 - INFO - __main__ - Step 94468: {'lr': 0.00015449095751976077, 'samples': 18137856, 'steps': 94467, 'loss/train': 0.5761323571205139} 08/31/2021 06:20:48 - INFO - __main__ - Step 94469: {'lr': 0.00015448605332743707, 'samples': 18138048, 'steps': 94468, 'loss/train': 0.9815865159034729} 08/31/2021 06:20:48 - INFO - __main__ - Step 94470: {'lr': 0.00015448114917815042, 'samples': 18138240, 'steps': 94469, 'loss/train': 0.37951505184173584} 08/31/2021 06:20:49 - INFO - __main__ - Step 94471: {'lr': 0.00015447624507190314, 'samples': 18138432, 'steps': 94470, 'loss/train': 0.9344165325164795} 08/31/2021 06:20:49 - INFO - __main__ - Step 94472: {'lr': 0.00015447134100869737, 'samples': 18138624, 'steps': 94471, 'loss/train': 1.3683222532272339} 08/31/2021 06:20:51 - INFO - __main__ - Step 94473: {'lr': 0.00015446643698853533, 'samples': 18138816, 'steps': 94472, 'loss/train': 1.3292239904403687} 08/31/2021 06:20:51 - INFO - __main__ - Step 94474: {'lr': 0.00015446153301141923, 'samples': 18139008, 'steps': 94473, 'loss/train': 1.108133316040039} 08/31/2021 06:20:51 - INFO - __main__ - Step 94475: {'lr': 0.0001544566290773513, 'samples': 18139200, 'steps': 94474, 'loss/train': 1.3435677289962769} 08/31/2021 06:20:52 - INFO - __main__ - Step 94476: {'lr': 0.00015445172518633373, 'samples': 18139392, 'steps': 94475, 'loss/train': 0.7736257314682007} 08/31/2021 06:20:52 - INFO - __main__ - Step 94477: {'lr': 0.00015444682133836877, 'samples': 18139584, 'steps': 94476, 'loss/train': 1.375881314277649} 08/31/2021 06:20:53 - INFO - __main__ - Step 94478: {'lr': 0.00015444191753345856, 'samples': 18139776, 'steps': 94477, 'loss/train': 1.658385157585144} 08/31/2021 06:20:54 - INFO - __main__ - Step 94479: {'lr': 0.00015443701377160538, 'samples': 18139968, 'steps': 94478, 'loss/train': 1.4822088479995728} 08/31/2021 06:20:55 - INFO - __main__ - Step 94480: {'lr': 0.00015443211005281137, 'samples': 18140160, 'steps': 94479, 'loss/train': 0.6237173080444336} 08/31/2021 06:20:55 - INFO - __main__ - Step 94481: {'lr': 0.00015442720637707892, 'samples': 18140352, 'steps': 94480, 'loss/train': 1.4666845798492432} 08/31/2021 06:20:55 - INFO - __main__ - Step 94482: {'lr': 0.00015442230274441, 'samples': 18140544, 'steps': 94481, 'loss/train': 0.03793569281697273} 08/31/2021 06:20:56 - INFO - __main__ - Step 94483: {'lr': 0.00015441739915480685, 'samples': 18140736, 'steps': 94482, 'loss/train': 1.0614899396896362} 08/31/2021 06:20:58 - INFO - __main__ - Step 94484: {'lr': 0.0001544124956082718, 'samples': 18140928, 'steps': 94483, 'loss/train': 0.7423208355903625} 08/31/2021 06:20:58 - INFO - __main__ - Step 94485: {'lr': 0.00015440759210480698, 'samples': 18141120, 'steps': 94484, 'loss/train': 1.2705016136169434} 08/31/2021 06:20:59 - INFO - __main__ - Step 94486: {'lr': 0.00015440268864441465, 'samples': 18141312, 'steps': 94485, 'loss/train': 0.5680662989616394} 08/31/2021 06:20:59 - INFO - __main__ - Step 94487: {'lr': 0.00015439778522709696, 'samples': 18141504, 'steps': 94486, 'loss/train': 1.072373390197754} 08/31/2021 06:20:59 - INFO - __main__ - Step 94488: {'lr': 0.0001543928818528562, 'samples': 18141696, 'steps': 94487, 'loss/train': 1.2768855094909668} 08/31/2021 06:21:00 - INFO - __main__ - Step 94489: {'lr': 0.00015438797852169447, 'samples': 18141888, 'steps': 94488, 'loss/train': 0.6188348531723022} 08/31/2021 06:21:01 - INFO - __main__ - Step 94490: {'lr': 0.00015438307523361409, 'samples': 18142080, 'steps': 94489, 'loss/train': 0.8751370906829834} 08/31/2021 06:21:02 - INFO - __main__ - Step 94491: {'lr': 0.0001543781719886172, 'samples': 18142272, 'steps': 94490, 'loss/train': 1.7249665260314941} 08/31/2021 06:21:02 - INFO - __main__ - Step 94492: {'lr': 0.00015437326878670605, 'samples': 18142464, 'steps': 94491, 'loss/train': 1.4145017862319946} 08/31/2021 06:21:02 - INFO - __main__ - Step 94493: {'lr': 0.0001543683656278828, 'samples': 18142656, 'steps': 94492, 'loss/train': 0.992618203163147} 08/31/2021 06:21:03 - INFO - __main__ - Step 94494: {'lr': 0.0001543634625121497, 'samples': 18142848, 'steps': 94493, 'loss/train': 1.7058616876602173} 08/31/2021 06:21:04 - INFO - __main__ - Step 94495: {'lr': 0.00015435855943950904, 'samples': 18143040, 'steps': 94494, 'loss/train': 1.3825517892837524} 08/31/2021 06:21:04 - INFO - __main__ - Step 94496: {'lr': 0.00015435365640996285, 'samples': 18143232, 'steps': 94495, 'loss/train': 1.7584846019744873} 08/31/2021 06:21:05 - INFO - __main__ - Step 94497: {'lr': 0.00015434875342351342, 'samples': 18143424, 'steps': 94496, 'loss/train': 0.8934467434883118} 08/31/2021 06:21:05 - INFO - __main__ - Step 94498: {'lr': 0.00015434385048016298, 'samples': 18143616, 'steps': 94497, 'loss/train': 0.6286365389823914} 08/31/2021 06:21:06 - INFO - __main__ - Step 94499: {'lr': 0.00015433894757991374, 'samples': 18143808, 'steps': 94498, 'loss/train': 1.0410404205322266} 08/31/2021 06:21:07 - INFO - __main__ - Step 94500: {'lr': 0.00015433404472276786, 'samples': 18144000, 'steps': 94499, 'loss/train': 0.10526605695486069} 08/31/2021 06:21:08 - INFO - __main__ - Step 94501: {'lr': 0.00015432914190872756, 'samples': 18144192, 'steps': 94500, 'loss/train': 0.1155729815363884} 08/31/2021 06:21:08 - INFO - __main__ - Step 94502: {'lr': 0.00015432423913779513, 'samples': 18144384, 'steps': 94501, 'loss/train': 1.9848328828811646} 08/31/2021 06:21:09 - INFO - __main__ - Step 94503: {'lr': 0.0001543193364099727, 'samples': 18144576, 'steps': 94502, 'loss/train': 1.2835451364517212} 08/31/2021 06:21:09 - INFO - __main__ - Step 94504: {'lr': 0.0001543144337252625, 'samples': 18144768, 'steps': 94503, 'loss/train': 2.574028730392456} 08/31/2021 06:21:11 - INFO - __main__ - Step 94505: {'lr': 0.00015430953108366672, 'samples': 18144960, 'steps': 94504, 'loss/train': 1.2206978797912598} 08/31/2021 06:21:11 - INFO - __main__ - Step 94506: {'lr': 0.0001543046284851876, 'samples': 18145152, 'steps': 94505, 'loss/train': 0.635660707950592} 08/31/2021 06:21:11 - INFO - __main__ - Step 94507: {'lr': 0.00015429972592982734, 'samples': 18145344, 'steps': 94506, 'loss/train': 1.1422275304794312} 08/31/2021 06:21:12 - INFO - __main__ - Step 94508: {'lr': 0.00015429482341758826, 'samples': 18145536, 'steps': 94507, 'loss/train': 1.2279807329177856} 08/31/2021 06:21:12 - INFO - __main__ - Step 94509: {'lr': 0.00015428992094847232, 'samples': 18145728, 'steps': 94508, 'loss/train': 0.7484858632087708} 08/31/2021 06:21:12 - INFO - __main__ - Step 94510: {'lr': 0.0001542850185224819, 'samples': 18145920, 'steps': 94509, 'loss/train': 1.2292615175247192} 08/31/2021 06:21:15 - INFO - __main__ - Step 94511: {'lr': 0.00015428011613961918, 'samples': 18146112, 'steps': 94510, 'loss/train': 1.5562478303909302} 08/31/2021 06:21:15 - INFO - __main__ - Step 94512: {'lr': 0.00015427521379988635, 'samples': 18146304, 'steps': 94511, 'loss/train': 1.1303008794784546} 08/31/2021 06:21:16 - INFO - __main__ - Step 94513: {'lr': 0.00015427031150328562, 'samples': 18146496, 'steps': 94512, 'loss/train': 0.32649388909339905} 08/31/2021 06:21:16 - INFO - __main__ - Step 94514: {'lr': 0.00015426540924981923, 'samples': 18146688, 'steps': 94513, 'loss/train': 0.27717727422714233} 08/31/2021 06:21:16 - INFO - __main__ - Step 94515: {'lr': 0.00015426050703948934, 'samples': 18146880, 'steps': 94514, 'loss/train': 1.3378721475601196} 08/31/2021 06:21:17 - INFO - __main__ - Step 94516: {'lr': 0.00015425560487229822, 'samples': 18147072, 'steps': 94515, 'loss/train': 1.5928798913955688} 08/31/2021 06:21:18 - INFO - __main__ - Step 94517: {'lr': 0.00015425070274824803, 'samples': 18147264, 'steps': 94516, 'loss/train': 1.1388202905654907} 08/31/2021 06:21:19 - INFO - __main__ - Step 94518: {'lr': 0.000154245800667341, 'samples': 18147456, 'steps': 94517, 'loss/train': 1.5339239835739136} 08/31/2021 06:21:19 - INFO - __main__ - Step 94519: {'lr': 0.00015424089862957932, 'samples': 18147648, 'steps': 94518, 'loss/train': 1.6769694089889526} 08/31/2021 06:21:19 - INFO - __main__ - Step 94520: {'lr': 0.00015423599663496525, 'samples': 18147840, 'steps': 94519, 'loss/train': 2.988264322280884} 08/31/2021 06:21:20 - INFO - __main__ - Step 94521: {'lr': 0.00015423109468350093, 'samples': 18148032, 'steps': 94520, 'loss/train': 0.7045763731002808} 08/31/2021 06:21:21 - INFO - __main__ - Step 94522: {'lr': 0.0001542261927751887, 'samples': 18148224, 'steps': 94521, 'loss/train': 1.4913277626037598} 08/31/2021 06:21:22 - INFO - __main__ - Step 94523: {'lr': 0.00015422129091003056, 'samples': 18148416, 'steps': 94522, 'loss/train': 1.2731587886810303} 08/31/2021 06:21:22 - INFO - __main__ - Step 94524: {'lr': 0.00015421638908802887, 'samples': 18148608, 'steps': 94523, 'loss/train': 1.2336013317108154} 08/31/2021 06:21:23 - INFO - __main__ - Step 94525: {'lr': 0.00015421148730918578, 'samples': 18148800, 'steps': 94524, 'loss/train': 1.3117578029632568} 08/31/2021 06:21:23 - INFO - __main__ - Step 94526: {'lr': 0.0001542065855735035, 'samples': 18148992, 'steps': 94525, 'loss/train': 1.2245538234710693} 08/31/2021 06:21:23 - INFO - __main__ - Step 94527: {'lr': 0.00015420168388098426, 'samples': 18149184, 'steps': 94526, 'loss/train': 1.0376735925674438} 08/31/2021 06:21:25 - INFO - __main__ - Step 94528: {'lr': 0.00015419678223163027, 'samples': 18149376, 'steps': 94527, 'loss/train': 0.47597354650497437} 08/31/2021 06:21:25 - INFO - __main__ - Step 94529: {'lr': 0.00015419188062544374, 'samples': 18149568, 'steps': 94528, 'loss/train': 1.3981592655181885} 08/31/2021 06:21:26 - INFO - __main__ - Step 94530: {'lr': 0.00015418697906242684, 'samples': 18149760, 'steps': 94529, 'loss/train': 1.4597406387329102} 08/31/2021 06:21:26 - INFO - __main__ - Step 94531: {'lr': 0.00015418207754258183, 'samples': 18149952, 'steps': 94530, 'loss/train': 1.9866336584091187} 08/31/2021 06:21:26 - INFO - __main__ - Step 94532: {'lr': 0.00015417717606591093, 'samples': 18150144, 'steps': 94531, 'loss/train': 1.2751585245132446} 08/31/2021 06:21:28 - INFO - __main__ - Step 94533: {'lr': 0.00015417227463241626, 'samples': 18150336, 'steps': 94532, 'loss/train': 1.143000602722168} 08/31/2021 06:21:28 - INFO - __main__ - Step 94534: {'lr': 0.00015416737324210013, 'samples': 18150528, 'steps': 94533, 'loss/train': 1.651965618133545} 08/31/2021 06:21:29 - INFO - __main__ - Step 94535: {'lr': 0.00015416247189496473, 'samples': 18150720, 'steps': 94534, 'loss/train': 2.1283693313598633} 08/31/2021 06:21:29 - INFO - __main__ - Step 94536: {'lr': 0.00015415757059101222, 'samples': 18150912, 'steps': 94535, 'loss/train': 1.1830331087112427} 08/31/2021 06:21:29 - INFO - __main__ - Step 94537: {'lr': 0.0001541526693302448, 'samples': 18151104, 'steps': 94536, 'loss/train': 1.2796094417572021} 08/31/2021 06:21:31 - INFO - __main__ - Step 94538: {'lr': 0.00015414776811266471, 'samples': 18151296, 'steps': 94537, 'loss/train': 1.1247551441192627} 08/31/2021 06:21:32 - INFO - __main__ - Step 94539: {'lr': 0.00015414286693827414, 'samples': 18151488, 'steps': 94538, 'loss/train': 1.3532249927520752} 08/31/2021 06:21:32 - INFO - __main__ - Step 94540: {'lr': 0.00015413796580707534, 'samples': 18151680, 'steps': 94539, 'loss/train': 1.9109541177749634} 08/31/2021 06:21:32 - INFO - __main__ - Step 94541: {'lr': 0.00015413306471907047, 'samples': 18151872, 'steps': 94540, 'loss/train': 1.2984217405319214} 08/31/2021 06:21:33 - INFO - __main__ - Step 94542: {'lr': 0.0001541281636742618, 'samples': 18152064, 'steps': 94541, 'loss/train': 1.5767030715942383} 08/31/2021 06:21:34 - INFO - __main__ - Step 94543: {'lr': 0.00015412326267265147, 'samples': 18152256, 'steps': 94542, 'loss/train': 1.4723594188690186} 08/31/2021 06:21:35 - INFO - __main__ - Step 94544: {'lr': 0.0001541183617142417, 'samples': 18152448, 'steps': 94543, 'loss/train': 1.1219367980957031} 08/31/2021 06:21:35 - INFO - __main__ - Step 94545: {'lr': 0.00015411346079903477, 'samples': 18152640, 'steps': 94544, 'loss/train': 1.177596092224121} 08/31/2021 06:21:35 - INFO - __main__ - Step 94546: {'lr': 0.00015410855992703277, 'samples': 18152832, 'steps': 94545, 'loss/train': 0.9919869303703308} 08/31/2021 06:21:36 - INFO - __main__ - Step 94547: {'lr': 0.0001541036590982381, 'samples': 18153024, 'steps': 94546, 'loss/train': 1.207759976387024} 08/31/2021 06:21:36 - INFO - __main__ - Step 94548: {'lr': 0.00015409875831265274, 'samples': 18153216, 'steps': 94547, 'loss/train': 0.7362618446350098} 08/31/2021 06:21:38 - INFO - __main__ - Step 94549: {'lr': 0.00015409385757027906, 'samples': 18153408, 'steps': 94548, 'loss/train': 0.9518475532531738} 08/31/2021 06:21:38 - INFO - __main__ - Step 94550: {'lr': 0.00015408895687111913, 'samples': 18153600, 'steps': 94549, 'loss/train': 0.8225346803665161} 08/31/2021 06:21:38 - INFO - __main__ - Step 94551: {'lr': 0.00015408405621517528, 'samples': 18153792, 'steps': 94550, 'loss/train': 1.299406886100769} 08/31/2021 06:21:39 - INFO - __main__ - Step 94552: {'lr': 0.00015407915560244965, 'samples': 18153984, 'steps': 94551, 'loss/train': 0.974066436290741} 08/31/2021 06:21:39 - INFO - __main__ - Step 94553: {'lr': 0.00015407425503294447, 'samples': 18154176, 'steps': 94552, 'loss/train': 0.7820748686790466} 08/31/2021 06:21:41 - INFO - __main__ - Step 94554: {'lr': 0.000154069354506662, 'samples': 18154368, 'steps': 94553, 'loss/train': 1.2363266944885254} 08/31/2021 06:21:41 - INFO - __main__ - Step 94555: {'lr': 0.0001540644540236043, 'samples': 18154560, 'steps': 94554, 'loss/train': 1.1323875188827515} 08/31/2021 06:21:42 - INFO - __main__ - Step 94556: {'lr': 0.00015405955358377378, 'samples': 18154752, 'steps': 94555, 'loss/train': 1.0290002822875977} 08/31/2021 06:21:42 - INFO - __main__ - Step 94557: {'lr': 0.0001540546531871725, 'samples': 18154944, 'steps': 94556, 'loss/train': 0.6357244253158569} 08/31/2021 06:21:42 - INFO - __main__ - Step 94558: {'lr': 0.00015404975283380275, 'samples': 18155136, 'steps': 94557, 'loss/train': 1.397250771522522} 08/31/2021 06:21:44 - INFO - __main__ - Step 94559: {'lr': 0.00015404485252366664, 'samples': 18155328, 'steps': 94558, 'loss/train': 5.762502670288086} 08/31/2021 06:21:45 - INFO - __main__ - Step 94560: {'lr': 0.0001540399522567665, 'samples': 18155520, 'steps': 94559, 'loss/train': 1.048230528831482} 08/31/2021 06:21:45 - INFO - __main__ - Step 94561: {'lr': 0.00015403505203310443, 'samples': 18155712, 'steps': 94560, 'loss/train': 0.7170799374580383} 08/31/2021 06:21:46 - INFO - __main__ - Step 94562: {'lr': 0.00015403015185268273, 'samples': 18155904, 'steps': 94561, 'loss/train': 0.3217443525791168} 08/31/2021 06:21:46 - INFO - __main__ - Step 94563: {'lr': 0.00015402525171550352, 'samples': 18156096, 'steps': 94562, 'loss/train': 1.0575412511825562} 08/31/2021 06:21:47 - INFO - __main__ - Step 94564: {'lr': 0.00015402035162156907, 'samples': 18156288, 'steps': 94563, 'loss/train': 1.1297287940979004} 08/31/2021 06:21:48 - INFO - __main__ - Step 94565: {'lr': 0.00015401545157088154, 'samples': 18156480, 'steps': 94564, 'loss/train': 1.342254638671875} 08/31/2021 06:21:48 - INFO - __main__ - Step 94566: {'lr': 0.0001540105515634432, 'samples': 18156672, 'steps': 94565, 'loss/train': 0.9489301443099976} 08/31/2021 06:21:48 - INFO - __main__ - Step 94567: {'lr': 0.0001540056515992562, 'samples': 18156864, 'steps': 94566, 'loss/train': 0.16043779253959656} 08/31/2021 06:21:49 - INFO - __main__ - Step 94568: {'lr': 0.00015400075167832278, 'samples': 18157056, 'steps': 94567, 'loss/train': 0.9338669776916504} 08/31/2021 06:21:49 - INFO - __main__ - Step 94569: {'lr': 0.0001539958518006452, 'samples': 18157248, 'steps': 94568, 'loss/train': 0.8108214735984802} 08/31/2021 06:21:51 - INFO - __main__ - Step 94570: {'lr': 0.00015399095196622553, 'samples': 18157440, 'steps': 94569, 'loss/train': 1.9287688732147217} 08/31/2021 06:21:51 - INFO - __main__ - Step 94571: {'lr': 0.00015398605217506605, 'samples': 18157632, 'steps': 94570, 'loss/train': 1.075211763381958} 08/31/2021 06:21:52 - INFO - __main__ - Step 94572: {'lr': 0.000153981152427169, 'samples': 18157824, 'steps': 94571, 'loss/train': 0.9684939980506897} 08/31/2021 06:21:52 - INFO - __main__ - Step 94573: {'lr': 0.00015397625272253656, 'samples': 18158016, 'steps': 94572, 'loss/train': 0.6974063515663147} 08/31/2021 06:21:52 - INFO - __main__ - Step 94574: {'lr': 0.00015397135306117094, 'samples': 18158208, 'steps': 94573, 'loss/train': 0.03492346033453941} 08/31/2021 06:21:54 - INFO - __main__ - Step 94575: {'lr': 0.00015396645344307438, 'samples': 18158400, 'steps': 94574, 'loss/train': 0.3201112747192383} 08/31/2021 06:21:54 - INFO - __main__ - Step 94576: {'lr': 0.00015396155386824902, 'samples': 18158592, 'steps': 94575, 'loss/train': 1.0021038055419922} 08/31/2021 06:21:55 - INFO - __main__ - Step 94577: {'lr': 0.0001539566543366971, 'samples': 18158784, 'steps': 94576, 'loss/train': 1.3809928894042969} 08/31/2021 06:21:55 - INFO - __main__ - Step 94578: {'lr': 0.00015395175484842082, 'samples': 18158976, 'steps': 94577, 'loss/train': 0.8217946290969849} 08/31/2021 06:21:55 - INFO - __main__ - Step 94579: {'lr': 0.0001539468554034224, 'samples': 18159168, 'steps': 94578, 'loss/train': 1.6034865379333496} 08/31/2021 06:21:57 - INFO - __main__ - Step 94580: {'lr': 0.00015394195600170412, 'samples': 18159360, 'steps': 94579, 'loss/train': 1.0083247423171997} 08/31/2021 06:21:57 - INFO - __main__ - Step 94581: {'lr': 0.00015393705664326805, 'samples': 18159552, 'steps': 94580, 'loss/train': 1.4769569635391235} 08/31/2021 06:21:58 - INFO - __main__ - Step 94582: {'lr': 0.00015393215732811645, 'samples': 18159744, 'steps': 94581, 'loss/train': 1.251611590385437} 08/31/2021 06:21:58 - INFO - __main__ - Step 94583: {'lr': 0.00015392725805625152, 'samples': 18159936, 'steps': 94582, 'loss/train': 1.164703130722046} 08/31/2021 06:21:58 - INFO - __main__ - Step 94584: {'lr': 0.00015392235882767552, 'samples': 18160128, 'steps': 94583, 'loss/train': 1.5319204330444336} 08/31/2021 06:22:00 - INFO - __main__ - Step 94585: {'lr': 0.0001539174596423906, 'samples': 18160320, 'steps': 94584, 'loss/train': 1.2418314218521118} 08/31/2021 06:22:00 - INFO - __main__ - Step 94586: {'lr': 0.00015391256050039897, 'samples': 18160512, 'steps': 94585, 'loss/train': 1.0551904439926147} 08/31/2021 06:22:01 - INFO - __main__ - Step 94587: {'lr': 0.00015390766140170289, 'samples': 18160704, 'steps': 94586, 'loss/train': 1.2512028217315674} 08/31/2021 06:22:01 - INFO - __main__ - Step 94588: {'lr': 0.00015390276234630455, 'samples': 18160896, 'steps': 94587, 'loss/train': 1.2687885761260986} 08/31/2021 06:22:01 - INFO - __main__ - Step 94589: {'lr': 0.00015389786333420616, 'samples': 18161088, 'steps': 94588, 'loss/train': 0.7809399962425232} 08/31/2021 06:22:03 - INFO - __main__ - Step 94590: {'lr': 0.0001538929643654099, 'samples': 18161280, 'steps': 94589, 'loss/train': 1.3680024147033691} 08/31/2021 06:22:04 - INFO - __main__ - Step 94591: {'lr': 0.00015388806543991797, 'samples': 18161472, 'steps': 94590, 'loss/train': 0.0321684293448925} 08/31/2021 06:22:04 - INFO - __main__ - Step 94592: {'lr': 0.0001538831665577326, 'samples': 18161664, 'steps': 94591, 'loss/train': 1.3276400566101074} 08/31/2021 06:22:04 - INFO - __main__ - Step 94593: {'lr': 0.00015387826771885596, 'samples': 18161856, 'steps': 94592, 'loss/train': 1.4889236688613892} 08/31/2021 06:22:05 - INFO - __main__ - Step 94594: {'lr': 0.00015387336892329028, 'samples': 18162048, 'steps': 94593, 'loss/train': 1.3888312578201294} 08/31/2021 06:22:05 - INFO - __main__ - Step 94595: {'lr': 0.00015386847017103783, 'samples': 18162240, 'steps': 94594, 'loss/train': 0.7703807950019836} 08/31/2021 06:22:07 - INFO - __main__ - Step 94596: {'lr': 0.00015386357146210072, 'samples': 18162432, 'steps': 94595, 'loss/train': 1.5073152780532837} 08/31/2021 06:22:07 - INFO - __main__ - Step 94597: {'lr': 0.00015385867279648125, 'samples': 18162624, 'steps': 94596, 'loss/train': 1.2057056427001953} 08/31/2021 06:22:08 - INFO - __main__ - Step 94598: {'lr': 0.00015385377417418151, 'samples': 18162816, 'steps': 94597, 'loss/train': 0.9202063679695129} 08/31/2021 06:22:08 - INFO - __main__ - Step 94599: {'lr': 0.00015384887559520384, 'samples': 18163008, 'steps': 94598, 'loss/train': 0.2900925278663635} 08/31/2021 06:22:08 - INFO - __main__ - Step 94600: {'lr': 0.00015384397705955034, 'samples': 18163200, 'steps': 94599, 'loss/train': 1.701716423034668} 08/31/2021 06:22:10 - INFO - __main__ - Step 94601: {'lr': 0.00015383907856722327, 'samples': 18163392, 'steps': 94600, 'loss/train': 1.1367608308792114} 08/31/2021 06:22:10 - INFO - __main__ - Step 94602: {'lr': 0.00015383418011822493, 'samples': 18163584, 'steps': 94601, 'loss/train': 1.3270522356033325} 08/31/2021 06:22:10 - INFO - __main__ - Step 94603: {'lr': 0.00015382928171255733, 'samples': 18163776, 'steps': 94602, 'loss/train': 1.1669888496398926} 08/31/2021 06:22:11 - INFO - __main__ - Step 94604: {'lr': 0.00015382438335022276, 'samples': 18163968, 'steps': 94603, 'loss/train': 1.0206466913223267} 08/31/2021 06:22:11 - INFO - __main__ - Step 94605: {'lr': 0.00015381948503122346, 'samples': 18164160, 'steps': 94604, 'loss/train': 0.7293086647987366} 08/31/2021 06:22:13 - INFO - __main__ - Step 94606: {'lr': 0.0001538145867555616, 'samples': 18164352, 'steps': 94605, 'loss/train': 0.44267839193344116} 08/31/2021 06:22:14 - INFO - __main__ - Step 94607: {'lr': 0.0001538096885232394, 'samples': 18164544, 'steps': 94606, 'loss/train': 0.7052573561668396} 08/31/2021 06:22:14 - INFO - __main__ - Step 94608: {'lr': 0.00015380479033425906, 'samples': 18164736, 'steps': 94607, 'loss/train': 1.237632393836975} 08/31/2021 06:22:14 - INFO - __main__ - Step 94609: {'lr': 0.00015379989218862282, 'samples': 18164928, 'steps': 94608, 'loss/train': 0.3828366696834564} 08/31/2021 06:22:15 - INFO - __main__ - Step 94610: {'lr': 0.00015379499408633285, 'samples': 18165120, 'steps': 94609, 'loss/train': 1.170900583267212} 08/31/2021 06:22:16 - INFO - __main__ - Step 94611: {'lr': 0.00015379009602739136, 'samples': 18165312, 'steps': 94610, 'loss/train': 1.701061487197876} 08/31/2021 06:22:17 - INFO - __main__ - Step 94612: {'lr': 0.0001537851980118006, 'samples': 18165504, 'steps': 94611, 'loss/train': 1.1280027627944946} 08/31/2021 06:22:17 - INFO - __main__ - Step 94613: {'lr': 0.00015378030003956273, 'samples': 18165696, 'steps': 94612, 'loss/train': 1.3507453203201294} 08/31/2021 06:22:18 - INFO - __main__ - Step 94614: {'lr': 0.00015377540211067997, 'samples': 18165888, 'steps': 94613, 'loss/train': 1.3343201875686646} 08/31/2021 06:22:18 - INFO - __main__ - Step 94615: {'lr': 0.00015377050422515454, 'samples': 18166080, 'steps': 94614, 'loss/train': 0.4976934790611267} 08/31/2021 06:22:20 - INFO - __main__ - Step 94616: {'lr': 0.00015376560638298873, 'samples': 18166272, 'steps': 94615, 'loss/train': 0.9567571878433228} 08/31/2021 06:22:20 - INFO - __main__ - Step 94617: {'lr': 0.00015376070858418454, 'samples': 18166464, 'steps': 94616, 'loss/train': 0.33133018016815186} 08/31/2021 06:22:21 - INFO - __main__ - Step 94618: {'lr': 0.00015375581082874428, 'samples': 18166656, 'steps': 94617, 'loss/train': 1.094622015953064} 08/31/2021 06:22:21 - INFO - __main__ - Step 94619: {'lr': 0.00015375091311667022, 'samples': 18166848, 'steps': 94618, 'loss/train': 1.0809952020645142} 08/31/2021 06:22:21 - INFO - __main__ - Step 94620: {'lr': 0.00015374601544796446, 'samples': 18167040, 'steps': 94619, 'loss/train': 1.2975071668624878} 08/31/2021 06:22:22 - INFO - __main__ - Step 94621: {'lr': 0.00015374111782262927, 'samples': 18167232, 'steps': 94620, 'loss/train': 1.553877830505371} 08/31/2021 06:22:23 - INFO - __main__ - Step 94622: {'lr': 0.00015373622024066687, 'samples': 18167424, 'steps': 94621, 'loss/train': 1.3670860528945923} 08/31/2021 06:22:24 - INFO - __main__ - Step 94623: {'lr': 0.00015373132270207944, 'samples': 18167616, 'steps': 94622, 'loss/train': 1.2968577146530151} 08/31/2021 06:22:24 - INFO - __main__ - Step 94624: {'lr': 0.00015372642520686917, 'samples': 18167808, 'steps': 94623, 'loss/train': 0.03865769878029823} 08/31/2021 06:22:24 - INFO - __main__ - Step 94625: {'lr': 0.0001537215277550383, 'samples': 18168000, 'steps': 94624, 'loss/train': 1.1333974599838257} 08/31/2021 06:22:25 - INFO - __main__ - Step 94626: {'lr': 0.000153716630346589, 'samples': 18168192, 'steps': 94625, 'loss/train': 1.1712547540664673} 08/31/2021 06:22:26 - INFO - __main__ - Step 94627: {'lr': 0.00015371173298152352, 'samples': 18168384, 'steps': 94626, 'loss/train': 1.2080811262130737} 08/31/2021 06:22:27 - INFO - __main__ - Step 94628: {'lr': 0.00015370683565984407, 'samples': 18168576, 'steps': 94627, 'loss/train': 0.7196084260940552} 08/31/2021 06:22:27 - INFO - __main__ - Step 94629: {'lr': 0.00015370193838155292, 'samples': 18168768, 'steps': 94628, 'loss/train': 1.1793513298034668} 08/31/2021 06:22:27 - INFO - __main__ - Step 94630: {'lr': 0.00015369704114665206, 'samples': 18168960, 'steps': 94629, 'loss/train': 0.7012323141098022} 08/31/2021 06:22:28 - INFO - __main__ - Step 94631: {'lr': 0.00015369214395514387, 'samples': 18169152, 'steps': 94630, 'loss/train': 1.0868113040924072} 08/31/2021 06:22:29 - INFO - __main__ - Step 94632: {'lr': 0.0001536872468070305, 'samples': 18169344, 'steps': 94631, 'loss/train': 1.0271705389022827} 08/31/2021 06:22:30 - INFO - __main__ - Step 94633: {'lr': 0.00015368234970231415, 'samples': 18169536, 'steps': 94632, 'loss/train': 1.03450345993042} 08/31/2021 06:22:30 - INFO - __main__ - Step 94634: {'lr': 0.00015367745264099707, 'samples': 18169728, 'steps': 94633, 'loss/train': 1.085762858390808} 08/31/2021 06:22:30 - INFO - __main__ - Step 94635: {'lr': 0.00015367255562308141, 'samples': 18169920, 'steps': 94634, 'loss/train': 0.7965360879898071} 08/31/2021 06:22:31 - INFO - __main__ - Step 94636: {'lr': 0.00015366765864856946, 'samples': 18170112, 'steps': 94635, 'loss/train': 1.0783379077911377} 08/31/2021 06:22:32 - INFO - __main__ - Step 94637: {'lr': 0.00015366276171746335, 'samples': 18170304, 'steps': 94636, 'loss/train': 1.5407147407531738} 08/31/2021 06:22:33 - INFO - __main__ - Step 94638: {'lr': 0.0001536578648297653, 'samples': 18170496, 'steps': 94637, 'loss/train': 1.4449379444122314} 08/31/2021 06:22:33 - INFO - __main__ - Step 94639: {'lr': 0.00015365296798547755, 'samples': 18170688, 'steps': 94638, 'loss/train': 1.4505889415740967} 08/31/2021 06:22:33 - INFO - __main__ - Step 94640: {'lr': 0.00015364807118460228, 'samples': 18170880, 'steps': 94639, 'loss/train': 1.527889609336853} 08/31/2021 06:22:34 - INFO - __main__ - Step 94641: {'lr': 0.0001536431744271417, 'samples': 18171072, 'steps': 94640, 'loss/train': 1.0371358394622803} 08/31/2021 06:22:35 - INFO - __main__ - Step 94642: {'lr': 0.000153638277713098, 'samples': 18171264, 'steps': 94641, 'loss/train': 1.5760140419006348} 08/31/2021 06:22:36 - INFO - __main__ - Step 94643: {'lr': 0.00015363338104247353, 'samples': 18171456, 'steps': 94642, 'loss/train': 0.055913325399160385} 08/31/2021 06:22:36 - INFO - __main__ - Step 94644: {'lr': 0.00015362848441527027, 'samples': 18171648, 'steps': 94643, 'loss/train': 1.2184503078460693} 08/31/2021 06:22:36 - INFO - __main__ - Step 94645: {'lr': 0.00015362358783149055, 'samples': 18171840, 'steps': 94644, 'loss/train': 0.7964897155761719} 08/31/2021 06:22:37 - INFO - __main__ - Step 94646: {'lr': 0.00015361869129113654, 'samples': 18172032, 'steps': 94645, 'loss/train': 0.730657696723938} 08/31/2021 06:22:38 - INFO - __main__ - Step 94647: {'lr': 0.00015361379479421046, 'samples': 18172224, 'steps': 94646, 'loss/train': 1.5856431722640991} 08/31/2021 06:22:39 - INFO - __main__ - Step 94648: {'lr': 0.00015360889834071452, 'samples': 18172416, 'steps': 94647, 'loss/train': 1.6143929958343506} 08/31/2021 06:22:39 - INFO - __main__ - Step 94649: {'lr': 0.00015360400193065087, 'samples': 18172608, 'steps': 94648, 'loss/train': 0.3101271092891693} 08/31/2021 06:22:39 - INFO - __main__ - Step 94650: {'lr': 0.00015359910556402183, 'samples': 18172800, 'steps': 94649, 'loss/train': 1.0403732061386108} 08/31/2021 06:22:40 - INFO - __main__ - Step 94651: {'lr': 0.0001535942092408295, 'samples': 18172992, 'steps': 94650, 'loss/train': 0.9157037138938904} 08/31/2021 06:22:40 - INFO - __main__ - Step 94652: {'lr': 0.00015358931296107617, 'samples': 18173184, 'steps': 94651, 'loss/train': 2.118377685546875} 08/31/2021 06:22:42 - INFO - __main__ - Step 94653: {'lr': 0.00015358441672476398, 'samples': 18173376, 'steps': 94652, 'loss/train': 0.8461973667144775} 08/31/2021 06:22:42 - INFO - __main__ - Step 94654: {'lr': 0.0001535795205318952, 'samples': 18173568, 'steps': 94653, 'loss/train': 1.5027048587799072} 08/31/2021 06:22:42 - INFO - __main__ - Step 94655: {'lr': 0.00015357462438247196, 'samples': 18173760, 'steps': 94654, 'loss/train': 0.027296731248497963} 08/31/2021 06:22:43 - INFO - __main__ - Step 94656: {'lr': 0.0001535697282764966, 'samples': 18173952, 'steps': 94655, 'loss/train': 0.8566051125526428} 08/31/2021 06:22:43 - INFO - __main__ - Step 94657: {'lr': 0.00015356483221397118, 'samples': 18174144, 'steps': 94656, 'loss/train': 0.8543839454650879} 08/31/2021 06:22:45 - INFO - __main__ - Step 94658: {'lr': 0.00015355993619489794, 'samples': 18174336, 'steps': 94657, 'loss/train': 0.03317641466856003} 08/31/2021 06:22:45 - INFO - __main__ - Step 94659: {'lr': 0.00015355504021927912, 'samples': 18174528, 'steps': 94658, 'loss/train': 1.226500153541565} 08/31/2021 06:22:46 - INFO - __main__ - Step 94660: {'lr': 0.0001535501442871169, 'samples': 18174720, 'steps': 94659, 'loss/train': 1.5578174591064453} 08/31/2021 06:22:46 - INFO - __main__ - Step 94661: {'lr': 0.00015354524839841346, 'samples': 18174912, 'steps': 94660, 'loss/train': 0.055552300065755844} 08/31/2021 06:22:46 - INFO - __main__ - Step 94662: {'lr': 0.00015354035255317106, 'samples': 18175104, 'steps': 94661, 'loss/train': 1.9324103593826294} 08/31/2021 06:22:47 - INFO - __main__ - Step 94663: {'lr': 0.00015353545675139192, 'samples': 18175296, 'steps': 94662, 'loss/train': 0.018737783655524254} 08/31/2021 06:22:49 - INFO - __main__ - Step 94664: {'lr': 0.0001535305609930782, 'samples': 18175488, 'steps': 94663, 'loss/train': 1.1767098903656006} 08/31/2021 06:22:49 - INFO - __main__ - Step 94665: {'lr': 0.00015352566527823209, 'samples': 18175680, 'steps': 94664, 'loss/train': 1.0823297500610352} 08/31/2021 06:22:50 - INFO - __main__ - Step 94666: {'lr': 0.00015352076960685584, 'samples': 18175872, 'steps': 94665, 'loss/train': 0.8381038904190063} 08/31/2021 06:22:50 - INFO - __main__ - Step 94667: {'lr': 0.00015351587397895167, 'samples': 18176064, 'steps': 94666, 'loss/train': 1.266619086265564} 08/31/2021 06:22:50 - INFO - __main__ - Step 94668: {'lr': 0.00015351097839452177, 'samples': 18176256, 'steps': 94667, 'loss/train': 0.6242073178291321} 08/31/2021 06:22:52 - INFO - __main__ - Step 94669: {'lr': 0.0001535060828535683, 'samples': 18176448, 'steps': 94668, 'loss/train': 0.4737633466720581} 08/31/2021 06:22:53 - INFO - __main__ - Step 94670: {'lr': 0.0001535011873560936, 'samples': 18176640, 'steps': 94669, 'loss/train': 1.382537841796875} 08/31/2021 06:22:53 - INFO - __main__ - Step 94671: {'lr': 0.0001534962919020997, 'samples': 18176832, 'steps': 94670, 'loss/train': 0.5721393823623657} 08/31/2021 06:22:53 - INFO - __main__ - Step 94672: {'lr': 0.00015349139649158884, 'samples': 18177024, 'steps': 94671, 'loss/train': 1.210199236869812} 08/31/2021 06:22:54 - INFO - __main__ - Step 94673: {'lr': 0.0001534865011245633, 'samples': 18177216, 'steps': 94672, 'loss/train': 1.4789915084838867} 08/31/2021 06:22:55 - INFO - __main__ - Step 94674: {'lr': 0.00015348160580102525, 'samples': 18177408, 'steps': 94673, 'loss/train': 0.396424263715744} 08/31/2021 06:22:56 - INFO - __main__ - Step 94675: {'lr': 0.0001534767105209769, 'samples': 18177600, 'steps': 94674, 'loss/train': 0.7227330207824707} 08/31/2021 06:22:56 - INFO - __main__ - Step 94676: {'lr': 0.00015347181528442045, 'samples': 18177792, 'steps': 94675, 'loss/train': 0.8537058234214783} 08/31/2021 06:22:56 - INFO - __main__ - Step 94677: {'lr': 0.0001534669200913581, 'samples': 18177984, 'steps': 94676, 'loss/train': 1.4109435081481934} 08/31/2021 06:22:57 - INFO - __main__ - Step 94678: {'lr': 0.00015346202494179206, 'samples': 18178176, 'steps': 94677, 'loss/train': 0.9374886155128479} 08/31/2021 06:22:58 - INFO - __main__ - Step 94679: {'lr': 0.00015345712983572457, 'samples': 18178368, 'steps': 94678, 'loss/train': 1.3252477645874023} 08/31/2021 06:22:59 - INFO - __main__ - Step 94680: {'lr': 0.00015345223477315778, 'samples': 18178560, 'steps': 94679, 'loss/train': 1.130985975265503} 08/31/2021 06:22:59 - INFO - __main__ - Step 94681: {'lr': 0.00015344733975409397, 'samples': 18178752, 'steps': 94680, 'loss/train': 0.9055663347244263} 08/31/2021 06:22:59 - INFO - __main__ - Step 94682: {'lr': 0.00015344244477853532, 'samples': 18178944, 'steps': 94681, 'loss/train': 1.2587497234344482} 08/31/2021 06:23:00 - INFO - __main__ - Step 94683: {'lr': 0.00015343754984648396, 'samples': 18179136, 'steps': 94682, 'loss/train': 2.7846145629882812} 08/31/2021 06:23:01 - INFO - __main__ - Step 94684: {'lr': 0.0001534326549579422, 'samples': 18179328, 'steps': 94683, 'loss/train': 0.4772501289844513} 08/31/2021 06:23:02 - INFO - __main__ - Step 94685: {'lr': 0.0001534277601129121, 'samples': 18179520, 'steps': 94684, 'loss/train': 1.0929049253463745} 08/31/2021 06:23:02 - INFO - __main__ - Step 94686: {'lr': 0.00015342286531139603, 'samples': 18179712, 'steps': 94685, 'loss/train': 1.2762489318847656} 08/31/2021 06:23:03 - INFO - __main__ - Step 94687: {'lr': 0.0001534179705533961, 'samples': 18179904, 'steps': 94686, 'loss/train': 3.2995457649230957} 08/31/2021 06:23:03 - INFO - __main__ - Step 94688: {'lr': 0.00015341307583891455, 'samples': 18180096, 'steps': 94687, 'loss/train': 1.7225465774536133} 08/31/2021 06:23:03 - INFO - __main__ - Step 94689: {'lr': 0.00015340818116795358, 'samples': 18180288, 'steps': 94688, 'loss/train': 0.016602594405412674} 08/31/2021 06:23:04 - INFO - __main__ - Step 94690: {'lr': 0.0001534032865405154, 'samples': 18180480, 'steps': 94689, 'loss/train': 0.016680937260389328} 08/31/2021 06:23:05 - INFO - __main__ - Step 94691: {'lr': 0.00015339839195660217, 'samples': 18180672, 'steps': 94690, 'loss/train': 0.5022851824760437} 08/31/2021 06:23:06 - INFO - __main__ - Step 94692: {'lr': 0.00015339349741621622, 'samples': 18180864, 'steps': 94691, 'loss/train': 0.043358899652957916} 08/31/2021 06:23:06 - INFO - __main__ - Step 94693: {'lr': 0.0001533886029193596, 'samples': 18181056, 'steps': 94692, 'loss/train': 1.575783133506775} 08/31/2021 06:23:07 - INFO - __main__ - Step 94694: {'lr': 0.0001533837084660346, 'samples': 18181248, 'steps': 94693, 'loss/train': 0.8989641070365906} 08/31/2021 06:23:07 - INFO - __main__ - Step 94695: {'lr': 0.0001533788140562434, 'samples': 18181440, 'steps': 94694, 'loss/train': 1.6184592247009277} 08/31/2021 06:23:09 - INFO - __main__ - Step 94696: {'lr': 0.00015337391968998825, 'samples': 18181632, 'steps': 94695, 'loss/train': 1.0761624574661255} 08/31/2021 06:23:09 - INFO - __main__ - Step 94697: {'lr': 0.00015336902536727131, 'samples': 18181824, 'steps': 94696, 'loss/train': 1.4388972520828247} 08/31/2021 06:23:10 - INFO - __main__ - Step 94698: {'lr': 0.00015336413108809477, 'samples': 18182016, 'steps': 94697, 'loss/train': 0.9417607188224792} 08/31/2021 06:23:10 - INFO - __main__ - Step 94699: {'lr': 0.00015335923685246087, 'samples': 18182208, 'steps': 94698, 'loss/train': 1.0729292631149292} 08/31/2021 06:23:10 - INFO - __main__ - Step 94700: {'lr': 0.00015335434266037178, 'samples': 18182400, 'steps': 94699, 'loss/train': 1.2594058513641357} 08/31/2021 06:23:13 - INFO - __main__ - Step 94701: {'lr': 0.00015334944851182978, 'samples': 18182592, 'steps': 94700, 'loss/train': 0.24059957265853882} 08/31/2021 06:23:13 - INFO - __main__ - Step 94702: {'lr': 0.000153344554406837, 'samples': 18182784, 'steps': 94701, 'loss/train': 0.589301586151123} 08/31/2021 06:23:14 - INFO - __main__ - Step 94703: {'lr': 0.00015333966034539575, 'samples': 18182976, 'steps': 94702, 'loss/train': 1.6667184829711914} 08/31/2021 06:23:14 - INFO - __main__ - Step 94704: {'lr': 0.00015333476632750808, 'samples': 18183168, 'steps': 94703, 'loss/train': 1.7636617422103882} 08/31/2021 06:23:14 - INFO - __main__ - Step 94705: {'lr': 0.00015332987235317625, 'samples': 18183360, 'steps': 94704, 'loss/train': 1.7625950574874878} 08/31/2021 06:23:15 - INFO - __main__ - Step 94706: {'lr': 0.00015332497842240252, 'samples': 18183552, 'steps': 94705, 'loss/train': 1.7424042224884033} 08/31/2021 06:23:15 - INFO - __main__ - Step 94707: {'lr': 0.00015332008453518902, 'samples': 18183744, 'steps': 94706, 'loss/train': 0.9161399006843567} 08/31/2021 06:23:15 - INFO - __main__ - Step 94708: {'lr': 0.00015331519069153806, 'samples': 18183936, 'steps': 94707, 'loss/train': 0.060519687831401825} 08/31/2021 06:23:17 - INFO - __main__ - Step 94709: {'lr': 0.00015331029689145175, 'samples': 18184128, 'steps': 94708, 'loss/train': 1.5295813083648682} 08/31/2021 06:23:17 - INFO - __main__ - Step 94710: {'lr': 0.0001533054031349324, 'samples': 18184320, 'steps': 94709, 'loss/train': 0.37134379148483276} 08/31/2021 06:23:18 - INFO - __main__ - Step 94711: {'lr': 0.0001533005094219821, 'samples': 18184512, 'steps': 94710, 'loss/train': 1.592635989189148} 08/31/2021 06:23:18 - INFO - __main__ - Step 94712: {'lr': 0.00015329561575260303, 'samples': 18184704, 'steps': 94711, 'loss/train': 1.114161729812622} 08/31/2021 06:23:18 - INFO - __main__ - Step 94713: {'lr': 0.00015329072212679753, 'samples': 18184896, 'steps': 94712, 'loss/train': 0.9769057631492615} 08/31/2021 06:23:20 - INFO - __main__ - Step 94714: {'lr': 0.00015328582854456777, 'samples': 18185088, 'steps': 94713, 'loss/train': 1.5487991571426392} 08/31/2021 06:23:20 - INFO - __main__ - Step 94715: {'lr': 0.0001532809350059159, 'samples': 18185280, 'steps': 94714, 'loss/train': 1.3498938083648682} 08/31/2021 06:23:21 - INFO - __main__ - Step 94716: {'lr': 0.0001532760415108441, 'samples': 18185472, 'steps': 94715, 'loss/train': 0.8262282013893127} 08/31/2021 06:23:21 - INFO - __main__ - Step 94717: {'lr': 0.00015327114805935464, 'samples': 18185664, 'steps': 94716, 'loss/train': 1.337446928024292} 08/31/2021 06:23:21 - INFO - __main__ - Step 94718: {'lr': 0.0001532662546514497, 'samples': 18185856, 'steps': 94717, 'loss/train': 1.3463168144226074} 08/31/2021 06:23:23 - INFO - __main__ - Step 94719: {'lr': 0.00015326136128713153, 'samples': 18186048, 'steps': 94718, 'loss/train': 1.1733092069625854} 08/31/2021 06:23:24 - INFO - __main__ - Step 94720: {'lr': 0.00015325646796640225, 'samples': 18186240, 'steps': 94719, 'loss/train': 1.1121424436569214} 08/31/2021 06:23:24 - INFO - __main__ - Step 94721: {'lr': 0.00015325157468926414, 'samples': 18186432, 'steps': 94720, 'loss/train': 0.12105417996644974} 08/31/2021 06:23:24 - INFO - __main__ - Step 94722: {'lr': 0.00015324668145571936, 'samples': 18186624, 'steps': 94721, 'loss/train': 1.2489334344863892} 08/31/2021 06:23:25 - INFO - __main__ - Step 94723: {'lr': 0.0001532417882657702, 'samples': 18186816, 'steps': 94722, 'loss/train': 1.3051457405090332} 08/31/2021 06:23:27 - INFO - __main__ - Step 94724: {'lr': 0.00015323689511941875, 'samples': 18187008, 'steps': 94723, 'loss/train': 1.6343984603881836} 08/31/2021 06:23:27 - INFO - __main__ - Step 94725: {'lr': 0.00015323200201666732, 'samples': 18187200, 'steps': 94724, 'loss/train': 1.5511887073516846} 08/31/2021 06:23:28 - INFO - __main__ - Step 94726: {'lr': 0.00015322710895751795, 'samples': 18187392, 'steps': 94725, 'loss/train': 0.03963381424546242} 08/31/2021 06:23:28 - INFO - __main__ - Step 94727: {'lr': 0.000153222215941973, 'samples': 18187584, 'steps': 94726, 'loss/train': 1.215404748916626} 08/31/2021 06:23:28 - INFO - __main__ - Step 94728: {'lr': 0.00015321732297003462, 'samples': 18187776, 'steps': 94727, 'loss/train': 1.9595063924789429} 08/31/2021 06:23:30 - INFO - __main__ - Step 94729: {'lr': 0.00015321243004170506, 'samples': 18187968, 'steps': 94728, 'loss/train': 0.891904354095459} 08/31/2021 06:23:30 - INFO - __main__ - Step 94730: {'lr': 0.00015320753715698644, 'samples': 18188160, 'steps': 94729, 'loss/train': 1.9276083707809448} 08/31/2021 06:23:31 - INFO - __main__ - Step 94731: {'lr': 0.000153202644315881, 'samples': 18188352, 'steps': 94730, 'loss/train': 1.4237140417099} 08/31/2021 06:23:31 - INFO - __main__ - Step 94732: {'lr': 0.00015319775151839094, 'samples': 18188544, 'steps': 94731, 'loss/train': 0.4503234028816223} 08/31/2021 06:23:31 - INFO - __main__ - Step 94733: {'lr': 0.00015319285876451853, 'samples': 18188736, 'steps': 94732, 'loss/train': 0.7489237785339355} 08/31/2021 06:23:33 - INFO - __main__ - Step 94734: {'lr': 0.00015318796605426588, 'samples': 18188928, 'steps': 94733, 'loss/train': 1.0216535329818726} 08/31/2021 06:23:33 - INFO - __main__ - Step 94735: {'lr': 0.00015318307338763526, 'samples': 18189120, 'steps': 94734, 'loss/train': 0.899128258228302} 08/31/2021 06:23:34 - INFO - __main__ - Step 94736: {'lr': 0.00015317818076462887, 'samples': 18189312, 'steps': 94735, 'loss/train': 1.2215807437896729} 08/31/2021 06:23:34 - INFO - __main__ - Step 94737: {'lr': 0.000153173288185249, 'samples': 18189504, 'steps': 94736, 'loss/train': 0.8542295694351196} 08/31/2021 06:23:34 - INFO - __main__ - Step 94738: {'lr': 0.00015316839564949764, 'samples': 18189696, 'steps': 94737, 'loss/train': 1.223841905593872} 08/31/2021 06:23:36 - INFO - __main__ - Step 94739: {'lr': 0.0001531635031573771, 'samples': 18189888, 'steps': 94738, 'loss/train': 1.8200243711471558} 08/31/2021 06:23:36 - INFO - __main__ - Step 94740: {'lr': 0.0001531586107088896, 'samples': 18190080, 'steps': 94739, 'loss/train': 2.0698397159576416} 08/31/2021 06:23:37 - INFO - __main__ - Step 94741: {'lr': 0.0001531537183040373, 'samples': 18190272, 'steps': 94740, 'loss/train': 0.26783308386802673} 08/31/2021 06:23:37 - INFO - __main__ - Step 94742: {'lr': 0.00015314882594282247, 'samples': 18190464, 'steps': 94741, 'loss/train': 1.7390356063842773} 08/31/2021 06:23:37 - INFO - __main__ - Step 94743: {'lr': 0.0001531439336252473, 'samples': 18190656, 'steps': 94742, 'loss/train': 1.1852930784225464} 08/31/2021 06:23:39 - INFO - __main__ - Step 94744: {'lr': 0.00015313904135131395, 'samples': 18190848, 'steps': 94743, 'loss/train': 1.2083529233932495} 08/31/2021 06:23:40 - INFO - __main__ - Step 94745: {'lr': 0.00015313414912102464, 'samples': 18191040, 'steps': 94744, 'loss/train': 0.8508957028388977} 08/31/2021 06:23:40 - INFO - __main__ - Step 94746: {'lr': 0.00015312925693438162, 'samples': 18191232, 'steps': 94745, 'loss/train': 1.6898057460784912} 08/31/2021 06:23:40 - INFO - __main__ - Step 94747: {'lr': 0.00015312436479138705, 'samples': 18191424, 'steps': 94746, 'loss/train': 1.1729557514190674} 08/31/2021 06:23:41 - INFO - __main__ - Step 94748: {'lr': 0.00015311947269204315, 'samples': 18191616, 'steps': 94747, 'loss/train': 1.3871318101882935} 08/31/2021 06:23:41 - INFO - __main__ - Step 94749: {'lr': 0.00015311458063635213, 'samples': 18191808, 'steps': 94748, 'loss/train': 0.023816049098968506} 08/31/2021 06:23:43 - INFO - __main__ - Step 94750: {'lr': 0.0001531096886243163, 'samples': 18192000, 'steps': 94749, 'loss/train': 0.03467954322695732} 08/31/2021 06:23:43 - INFO - __main__ - Step 94751: {'lr': 0.0001531047966559376, 'samples': 18192192, 'steps': 94750, 'loss/train': 1.5589723587036133} 08/31/2021 06:23:43 - INFO - __main__ - Step 94752: {'lr': 0.00015309990473121843, 'samples': 18192384, 'steps': 94751, 'loss/train': 0.8803030848503113} 08/31/2021 06:23:44 - INFO - __main__ - Step 94753: {'lr': 0.00015309501285016091, 'samples': 18192576, 'steps': 94752, 'loss/train': 1.27250075340271} 08/31/2021 06:23:44 - INFO - __main__ - Step 94754: {'lr': 0.0001530901210127673, 'samples': 18192768, 'steps': 94753, 'loss/train': 1.620829701423645} 08/31/2021 06:23:45 - INFO - __main__ - Step 94755: {'lr': 0.0001530852292190398, 'samples': 18192960, 'steps': 94754, 'loss/train': 1.388218641281128} 08/31/2021 06:23:46 - INFO - __main__ - Step 94756: {'lr': 0.00015308033746898057, 'samples': 18193152, 'steps': 94755, 'loss/train': 1.330891728401184} 08/31/2021 06:23:46 - INFO - __main__ - Step 94757: {'lr': 0.00015307544576259187, 'samples': 18193344, 'steps': 94756, 'loss/train': 1.6682473421096802} 08/31/2021 06:23:47 - INFO - __main__ - Step 94758: {'lr': 0.00015307055409987587, 'samples': 18193536, 'steps': 94757, 'loss/train': 1.5343105792999268} 08/31/2021 06:23:47 - INFO - __main__ - Step 94759: {'lr': 0.00015306566248083476, 'samples': 18193728, 'steps': 94758, 'loss/train': 1.135699987411499} 08/31/2021 06:23:47 - INFO - __main__ - Step 94760: {'lr': 0.00015306077090547078, 'samples': 18193920, 'steps': 94759, 'loss/train': 0.6793033480644226} 08/31/2021 06:23:49 - INFO - __main__ - Step 94761: {'lr': 0.00015305587937378611, 'samples': 18194112, 'steps': 94760, 'loss/train': 0.907841145992279} 08/31/2021 06:23:50 - INFO - __main__ - Step 94762: {'lr': 0.000153050987885783, 'samples': 18194304, 'steps': 94761, 'loss/train': 1.2793080806732178} 08/31/2021 06:23:50 - INFO - __main__ - Step 94763: {'lr': 0.00015304609644146362, 'samples': 18194496, 'steps': 94762, 'loss/train': 0.01883738860487938} 08/31/2021 06:23:51 - INFO - __main__ - Step 94764: {'lr': 0.00015304120504083024, 'samples': 18194688, 'steps': 94763, 'loss/train': 0.017064735293388367} 08/31/2021 06:23:51 - INFO - __main__ - Step 94765: {'lr': 0.00015303631368388494, 'samples': 18194880, 'steps': 94764, 'loss/train': 1.6700044870376587} 08/31/2021 06:23:51 - INFO - __main__ - Step 94766: {'lr': 0.00015303142237062996, 'samples': 18195072, 'steps': 94765, 'loss/train': 0.04585232958197594} 08/31/2021 06:23:53 - INFO - __main__ - Step 94767: {'lr': 0.00015302653110106748, 'samples': 18195264, 'steps': 94766, 'loss/train': 1.4360806941986084} 08/31/2021 06:23:53 - INFO - __main__ - Step 94768: {'lr': 0.0001530216398751998, 'samples': 18195456, 'steps': 94767, 'loss/train': 1.4397870302200317} 08/31/2021 06:23:54 - INFO - __main__ - Step 94769: {'lr': 0.00015301674869302906, 'samples': 18195648, 'steps': 94768, 'loss/train': 0.03592107445001602} 08/31/2021 06:23:54 - INFO - __main__ - Step 94770: {'lr': 0.00015301185755455746, 'samples': 18195840, 'steps': 94769, 'loss/train': 1.2735956907272339} 08/31/2021 06:23:54 - INFO - __main__ - Step 94771: {'lr': 0.00015300696645978725, 'samples': 18196032, 'steps': 94770, 'loss/train': 0.1387006938457489} 08/31/2021 06:23:56 - INFO - __main__ - Step 94772: {'lr': 0.00015300207540872056, 'samples': 18196224, 'steps': 94771, 'loss/train': 1.5880576372146606} 08/31/2021 06:23:57 - INFO - __main__ - Step 94773: {'lr': 0.00015299718440135967, 'samples': 18196416, 'steps': 94772, 'loss/train': 0.04605219513177872} 08/31/2021 06:23:57 - INFO - __main__ - Step 94774: {'lr': 0.00015299229343770677, 'samples': 18196608, 'steps': 94773, 'loss/train': 0.07303453236818314} 08/31/2021 06:23:57 - INFO - __main__ - Step 94775: {'lr': 0.00015298740251776398, 'samples': 18196800, 'steps': 94774, 'loss/train': 0.989942193031311} 08/31/2021 06:23:58 - INFO - __main__ - Step 94776: {'lr': 0.00015298251164153366, 'samples': 18196992, 'steps': 94775, 'loss/train': 1.2388570308685303} 08/31/2021 06:23:58 - INFO - __main__ - Step 94777: {'lr': 0.00015297762080901799, 'samples': 18197184, 'steps': 94776, 'loss/train': 1.0573456287384033} 08/31/2021 06:24:00 - INFO - __main__ - Step 94778: {'lr': 0.00015297273002021897, 'samples': 18197376, 'steps': 94777, 'loss/train': 0.45198503136634827} 08/31/2021 06:24:01 - INFO - __main__ - Step 94779: {'lr': 0.00015296783927513897, 'samples': 18197568, 'steps': 94778, 'loss/train': 1.1501103639602661} 08/31/2021 06:24:01 - INFO - __main__ - Step 94780: {'lr': 0.00015296294857378016, 'samples': 18197760, 'steps': 94779, 'loss/train': 0.43888187408447266} 08/31/2021 06:24:02 - INFO - __main__ - Step 94781: {'lr': 0.00015295805791614475, 'samples': 18197952, 'steps': 94780, 'loss/train': 0.9700510501861572} 08/31/2021 06:24:02 - INFO - __main__ - Step 94782: {'lr': 0.00015295316730223494, 'samples': 18198144, 'steps': 94781, 'loss/train': 1.6367191076278687} 08/31/2021 06:24:04 - INFO - __main__ - Step 94783: {'lr': 0.0001529482767320529, 'samples': 18198336, 'steps': 94782, 'loss/train': 0.7879956364631653} 08/31/2021 06:24:04 - INFO - __main__ - Step 94784: {'lr': 0.00015294338620560095, 'samples': 18198528, 'steps': 94783, 'loss/train': 0.935644805431366} 08/31/2021 06:24:04 - INFO - __main__ - Step 94785: {'lr': 0.00015293849572288115, 'samples': 18198720, 'steps': 94784, 'loss/train': 1.607079029083252} 08/31/2021 06:24:05 - INFO - __main__ - Step 94786: {'lr': 0.00015293360528389577, 'samples': 18198912, 'steps': 94785, 'loss/train': 0.7216967940330505} 08/31/2021 06:24:05 - INFO - __main__ - Step 94787: {'lr': 0.00015292871488864702, 'samples': 18199104, 'steps': 94786, 'loss/train': 0.9964869618415833} 08/31/2021 06:24:05 - INFO - __main__ - Step 94788: {'lr': 0.0001529238245371371, 'samples': 18199296, 'steps': 94787, 'loss/train': 1.5425351858139038} 08/31/2021 06:24:07 - INFO - __main__ - Step 94789: {'lr': 0.0001529189342293682, 'samples': 18199488, 'steps': 94788, 'loss/train': 1.2597030401229858} 08/31/2021 06:24:07 - INFO - __main__ - Step 94790: {'lr': 0.00015291404396534252, 'samples': 18199680, 'steps': 94789, 'loss/train': 1.8426169157028198} 08/31/2021 06:24:08 - INFO - __main__ - Step 94791: {'lr': 0.0001529091537450624, 'samples': 18199872, 'steps': 94790, 'loss/train': 1.0079262256622314} 08/31/2021 06:24:08 - INFO - __main__ - Step 94792: {'lr': 0.0001529042635685298, 'samples': 18200064, 'steps': 94791, 'loss/train': 1.043366551399231} 08/31/2021 06:24:08 - INFO - __main__ - Step 94793: {'lr': 0.00015289937343574705, 'samples': 18200256, 'steps': 94792, 'loss/train': 0.45166003704071045} 08/31/2021 06:24:10 - INFO - __main__ - Step 94794: {'lr': 0.00015289448334671632, 'samples': 18200448, 'steps': 94793, 'loss/train': 1.5691779851913452} 08/31/2021 06:24:10 - INFO - __main__ - Step 94795: {'lr': 0.00015288959330143987, 'samples': 18200640, 'steps': 94794, 'loss/train': 1.5660173892974854} 08/31/2021 06:24:11 - INFO - __main__ - Step 94796: {'lr': 0.00015288470329991984, 'samples': 18200832, 'steps': 94795, 'loss/train': 1.0587069988250732} 08/31/2021 06:24:11 - INFO - __main__ - Step 94797: {'lr': 0.00015287981334215851, 'samples': 18201024, 'steps': 94796, 'loss/train': 1.1508852243423462} 08/31/2021 06:24:11 - INFO - __main__ - Step 94798: {'lr': 0.00015287492342815797, 'samples': 18201216, 'steps': 94797, 'loss/train': 1.3613489866256714} 08/31/2021 06:24:13 - INFO - __main__ - Step 94799: {'lr': 0.00015287003355792054, 'samples': 18201408, 'steps': 94798, 'loss/train': 1.4381260871887207} 08/31/2021 06:24:13 - INFO - __main__ - Step 94800: {'lr': 0.00015286514373144837, 'samples': 18201600, 'steps': 94799, 'loss/train': 1.378699779510498} 08/31/2021 06:24:14 - INFO - __main__ - Step 94801: {'lr': 0.00015286025394874365, 'samples': 18201792, 'steps': 94800, 'loss/train': 1.5975501537322998} 08/31/2021 06:24:14 - INFO - __main__ - Step 94802: {'lr': 0.0001528553642098086, 'samples': 18201984, 'steps': 94801, 'loss/train': 0.6193406581878662} 08/31/2021 06:24:14 - INFO - __main__ - Step 94803: {'lr': 0.00015285047451464546, 'samples': 18202176, 'steps': 94802, 'loss/train': 0.9210160970687866} 08/31/2021 06:24:16 - INFO - __main__ - Step 94804: {'lr': 0.00015284558486325644, 'samples': 18202368, 'steps': 94803, 'loss/train': 1.3322396278381348} 08/31/2021 06:24:17 - INFO - __main__ - Step 94805: {'lr': 0.00015284069525564365, 'samples': 18202560, 'steps': 94804, 'loss/train': 1.3001012802124023} 08/31/2021 06:24:17 - INFO - __main__ - Step 94806: {'lr': 0.00015283580569180934, 'samples': 18202752, 'steps': 94805, 'loss/train': 1.3287293910980225} 08/31/2021 06:24:17 - INFO - __main__ - Step 94807: {'lr': 0.0001528309161717557, 'samples': 18202944, 'steps': 94806, 'loss/train': 1.2027918100357056} 08/31/2021 06:24:18 - INFO - __main__ - Step 94808: {'lr': 0.00015282602669548494, 'samples': 18203136, 'steps': 94807, 'loss/train': 0.8481674194335938} 08/31/2021 06:24:19 - INFO - __main__ - Step 94809: {'lr': 0.00015282113726299926, 'samples': 18203328, 'steps': 94808, 'loss/train': 1.4552173614501953} 08/31/2021 06:24:20 - INFO - __main__ - Step 94810: {'lr': 0.0001528162478743009, 'samples': 18203520, 'steps': 94809, 'loss/train': 0.6181998252868652} 08/31/2021 06:24:20 - INFO - __main__ - Step 94811: {'lr': 0.00015281135852939203, 'samples': 18203712, 'steps': 94810, 'loss/train': 0.7723973989486694} 08/31/2021 06:24:20 - INFO - __main__ - Step 94812: {'lr': 0.00015280646922827487, 'samples': 18203904, 'steps': 94811, 'loss/train': 1.281609058380127} 08/31/2021 06:24:21 - INFO - __main__ - Step 94813: {'lr': 0.00015280157997095162, 'samples': 18204096, 'steps': 94812, 'loss/train': 2.0069055557250977} 08/31/2021 06:24:23 - INFO - __main__ - Step 94814: {'lr': 0.00015279669075742448, 'samples': 18204288, 'steps': 94813, 'loss/train': 1.2371206283569336} 08/31/2021 06:24:23 - INFO - __main__ - Step 94815: {'lr': 0.00015279180158769566, 'samples': 18204480, 'steps': 94814, 'loss/train': 1.8178787231445312} 08/31/2021 06:24:23 - INFO - __main__ - Step 94816: {'lr': 0.00015278691246176738, 'samples': 18204672, 'steps': 94815, 'loss/train': 1.1902906894683838} 08/31/2021 06:24:24 - INFO - __main__ - Step 94817: {'lr': 0.0001527820233796418, 'samples': 18204864, 'steps': 94816, 'loss/train': 0.01517883688211441} 08/31/2021 06:24:24 - INFO - __main__ - Step 94818: {'lr': 0.00015277713434132113, 'samples': 18205056, 'steps': 94817, 'loss/train': 0.3665960431098938} 08/31/2021 06:24:24 - INFO - __main__ - Step 94819: {'lr': 0.00015277224534680756, 'samples': 18205248, 'steps': 94818, 'loss/train': 1.2726669311523438} 08/31/2021 06:24:25 - INFO - __main__ - Step 94820: {'lr': 0.00015276735639610335, 'samples': 18205440, 'steps': 94819, 'loss/train': 1.3407163619995117} 08/31/2021 06:24:26 - INFO - __main__ - Step 94821: {'lr': 0.00015276246748921064, 'samples': 18205632, 'steps': 94820, 'loss/train': 0.7610999941825867} 08/31/2021 06:24:27 - INFO - __main__ - Step 94822: {'lr': 0.00015275757862613166, 'samples': 18205824, 'steps': 94821, 'loss/train': 1.7499399185180664} 08/31/2021 06:24:27 - INFO - __main__ - Step 94823: {'lr': 0.00015275268980686864, 'samples': 18206016, 'steps': 94822, 'loss/train': 1.1182607412338257} 08/31/2021 06:24:27 - INFO - __main__ - Step 94824: {'lr': 0.0001527478010314237, 'samples': 18206208, 'steps': 94823, 'loss/train': 0.46373072266578674} 08/31/2021 06:24:28 - INFO - __main__ - Step 94825: {'lr': 0.00015274291229979914, 'samples': 18206400, 'steps': 94824, 'loss/train': 1.2490620613098145} 08/31/2021 06:24:29 - INFO - __main__ - Step 94826: {'lr': 0.00015273802361199712, 'samples': 18206592, 'steps': 94825, 'loss/train': 1.3455193042755127} 08/31/2021 06:24:30 - INFO - __main__ - Step 94827: {'lr': 0.00015273313496801992, 'samples': 18206784, 'steps': 94826, 'loss/train': 1.2085440158843994} 08/31/2021 06:24:30 - INFO - __main__ - Step 94828: {'lr': 0.00015272824636786958, 'samples': 18206976, 'steps': 94827, 'loss/train': 1.3657097816467285} 08/31/2021 06:24:30 - INFO - __main__ - Step 94829: {'lr': 0.00015272335781154838, 'samples': 18207168, 'steps': 94828, 'loss/train': 0.6690081357955933} 08/31/2021 06:24:31 - INFO - __main__ - Step 94830: {'lr': 0.00015271846929905858, 'samples': 18207360, 'steps': 94829, 'loss/train': 1.3572536706924438} 08/31/2021 06:24:33 - INFO - __main__ - Step 94831: {'lr': 0.00015271358083040237, 'samples': 18207552, 'steps': 94830, 'loss/train': 1.1104300022125244} 08/31/2021 06:24:33 - INFO - __main__ - Step 94832: {'lr': 0.0001527086924055819, 'samples': 18207744, 'steps': 94831, 'loss/train': 1.4459173679351807} 08/31/2021 06:24:34 - INFO - __main__ - Step 94833: {'lr': 0.00015270380402459933, 'samples': 18207936, 'steps': 94832, 'loss/train': 1.2447212934494019} 08/31/2021 06:24:34 - INFO - __main__ - Step 94834: {'lr': 0.00015269891568745698, 'samples': 18208128, 'steps': 94833, 'loss/train': 0.9802820682525635} 08/31/2021 06:24:34 - INFO - __main__ - Step 94835: {'lr': 0.00015269402739415694, 'samples': 18208320, 'steps': 94834, 'loss/train': 0.7575377821922302} 08/31/2021 06:24:36 - INFO - __main__ - Step 94836: {'lr': 0.0001526891391447015, 'samples': 18208512, 'steps': 94835, 'loss/train': 1.4940563440322876} 08/31/2021 06:24:37 - INFO - __main__ - Step 94837: {'lr': 0.00015268425093909287, 'samples': 18208704, 'steps': 94836, 'loss/train': 0.9766023755073547} 08/31/2021 06:24:37 - INFO - __main__ - Step 94838: {'lr': 0.00015267936277733318, 'samples': 18208896, 'steps': 94837, 'loss/train': 1.318843126296997} 08/31/2021 06:24:37 - INFO - __main__ - Step 94839: {'lr': 0.0001526744746594247, 'samples': 18209088, 'steps': 94838, 'loss/train': 0.9110986590385437} 08/31/2021 06:24:38 - INFO - __main__ - Step 94840: {'lr': 0.00015266958658536952, 'samples': 18209280, 'steps': 94839, 'loss/train': 1.629929542541504} 08/31/2021 06:24:38 - INFO - __main__ - Step 94841: {'lr': 0.00015266469855516998, 'samples': 18209472, 'steps': 94840, 'loss/train': 0.7589048743247986} 08/31/2021 06:24:40 - INFO - __main__ - Step 94842: {'lr': 0.0001526598105688282, 'samples': 18209664, 'steps': 94841, 'loss/train': 0.09089481085538864} 08/31/2021 06:24:40 - INFO - __main__ - Step 94843: {'lr': 0.00015265492262634645, 'samples': 18209856, 'steps': 94842, 'loss/train': 1.1475200653076172} 08/31/2021 06:24:40 - INFO - __main__ - Step 94844: {'lr': 0.00015265003472772688, 'samples': 18210048, 'steps': 94843, 'loss/train': 0.885500967502594} 08/31/2021 06:24:41 - INFO - __main__ - Step 94845: {'lr': 0.0001526451468729717, 'samples': 18210240, 'steps': 94844, 'loss/train': 1.4007024765014648} 08/31/2021 06:24:41 - INFO - __main__ - Step 94846: {'lr': 0.00015264025906208307, 'samples': 18210432, 'steps': 94845, 'loss/train': 1.3260470628738403} 08/31/2021 06:24:43 - INFO - __main__ - Step 94847: {'lr': 0.00015263537129506328, 'samples': 18210624, 'steps': 94846, 'loss/train': 1.2007559537887573} 08/31/2021 06:24:43 - INFO - __main__ - Step 94848: {'lr': 0.0001526304835719145, 'samples': 18210816, 'steps': 94847, 'loss/train': 1.3540252447128296} 08/31/2021 06:24:44 - INFO - __main__ - Step 94849: {'lr': 0.00015262559589263893, 'samples': 18211008, 'steps': 94848, 'loss/train': 0.8989319801330566} 08/31/2021 06:24:44 - INFO - __main__ - Step 94850: {'lr': 0.0001526207082572387, 'samples': 18211200, 'steps': 94849, 'loss/train': 0.7882407307624817} 08/31/2021 06:24:44 - INFO - __main__ - Step 94851: {'lr': 0.00015261582066571612, 'samples': 18211392, 'steps': 94850, 'loss/train': 1.296871304512024} 08/31/2021 06:24:45 - INFO - __main__ - Step 94852: {'lr': 0.00015261093311807333, 'samples': 18211584, 'steps': 94851, 'loss/train': 1.0043628215789795} 08/31/2021 06:24:46 - INFO - __main__ - Step 94853: {'lr': 0.00015260604561431255, 'samples': 18211776, 'steps': 94852, 'loss/train': 1.1706780195236206} 08/31/2021 06:24:47 - INFO - __main__ - Step 94854: {'lr': 0.00015260115815443598, 'samples': 18211968, 'steps': 94853, 'loss/train': 1.301734447479248} 08/31/2021 06:24:47 - INFO - __main__ - Step 94855: {'lr': 0.00015259627073844584, 'samples': 18212160, 'steps': 94854, 'loss/train': 1.0817043781280518} 08/31/2021 06:24:48 - INFO - __main__ - Step 94856: {'lr': 0.0001525913833663443, 'samples': 18212352, 'steps': 94855, 'loss/train': 0.8389433026313782} 08/31/2021 06:24:48 - INFO - __main__ - Step 94857: {'lr': 0.00015258649603813357, 'samples': 18212544, 'steps': 94856, 'loss/train': 0.67462158203125} 08/31/2021 06:24:49 - INFO - __main__ - Step 94858: {'lr': 0.00015258160875381593, 'samples': 18212736, 'steps': 94857, 'loss/train': 1.9524494409561157} 08/31/2021 06:24:50 - INFO - __main__ - Step 94859: {'lr': 0.00015257672151339352, 'samples': 18212928, 'steps': 94858, 'loss/train': 1.1613388061523438} 08/31/2021 06:24:50 - INFO - __main__ - Step 94860: {'lr': 0.00015257183431686847, 'samples': 18213120, 'steps': 94859, 'loss/train': 1.3998538255691528} 08/31/2021 06:24:51 - INFO - __main__ - Step 94861: {'lr': 0.00015256694716424306, 'samples': 18213312, 'steps': 94860, 'loss/train': 0.9493356943130493} 08/31/2021 06:24:51 - INFO - __main__ - Step 94862: {'lr': 0.00015256206005551947, 'samples': 18213504, 'steps': 94861, 'loss/train': 0.9462029933929443} 08/31/2021 06:24:53 - INFO - __main__ - Step 94863: {'lr': 0.00015255717299069994, 'samples': 18213696, 'steps': 94862, 'loss/train': 1.5034233331680298} 08/31/2021 06:24:53 - INFO - __main__ - Step 94864: {'lr': 0.0001525522859697866, 'samples': 18213888, 'steps': 94863, 'loss/train': 0.051463767886161804} 08/31/2021 06:24:53 - INFO - __main__ - Step 94865: {'lr': 0.00015254739899278171, 'samples': 18214080, 'steps': 94864, 'loss/train': 0.3295207619667053} 08/31/2021 06:24:54 - INFO - __main__ - Step 94866: {'lr': 0.0001525425120596875, 'samples': 18214272, 'steps': 94865, 'loss/train': 1.053735375404358} 08/31/2021 06:24:54 - INFO - __main__ - Step 94867: {'lr': 0.00015253762517050605, 'samples': 18214464, 'steps': 94866, 'loss/train': 1.2667522430419922} 08/31/2021 06:24:56 - INFO - __main__ - Step 94868: {'lr': 0.00015253273832523974, 'samples': 18214656, 'steps': 94867, 'loss/train': 0.7946726679801941} 08/31/2021 06:24:56 - INFO - __main__ - Step 94869: {'lr': 0.00015252785152389058, 'samples': 18214848, 'steps': 94868, 'loss/train': 1.0023149251937866} 08/31/2021 06:24:57 - INFO - __main__ - Step 94870: {'lr': 0.00015252296476646094, 'samples': 18215040, 'steps': 94869, 'loss/train': 1.392606258392334} 08/31/2021 06:24:57 - INFO - __main__ - Step 94871: {'lr': 0.000152518078052953, 'samples': 18215232, 'steps': 94870, 'loss/train': 0.9890748262405396} 08/31/2021 06:24:57 - INFO - __main__ - Step 94872: {'lr': 0.00015251319138336882, 'samples': 18215424, 'steps': 94871, 'loss/train': 0.9923700094223022} 08/31/2021 06:24:59 - INFO - __main__ - Step 94873: {'lr': 0.00015250830475771072, 'samples': 18215616, 'steps': 94872, 'loss/train': 0.24972251057624817} 08/31/2021 06:24:59 - INFO - __main__ - Step 94874: {'lr': 0.00015250341817598084, 'samples': 18215808, 'steps': 94873, 'loss/train': 1.0789903402328491} 08/31/2021 06:25:00 - INFO - __main__ - Step 94875: {'lr': 0.00015249853163818144, 'samples': 18216000, 'steps': 94874, 'loss/train': 0.7282647490501404} 08/31/2021 06:25:00 - INFO - __main__ - Step 94876: {'lr': 0.0001524936451443147, 'samples': 18216192, 'steps': 94875, 'loss/train': 1.1900440454483032} 08/31/2021 06:25:00 - INFO - __main__ - Step 94877: {'lr': 0.00015248875869438278, 'samples': 18216384, 'steps': 94876, 'loss/train': 1.3048361539840698} 08/31/2021 06:25:01 - INFO - __main__ - Step 94878: {'lr': 0.00015248387228838795, 'samples': 18216576, 'steps': 94877, 'loss/train': 1.0531973838806152} 08/31/2021 06:25:02 - INFO - __main__ - Step 94879: {'lr': 0.00015247898592633236, 'samples': 18216768, 'steps': 94878, 'loss/train': 1.3614602088928223} 08/31/2021 06:25:03 - INFO - __main__ - Step 94880: {'lr': 0.00015247409960821828, 'samples': 18216960, 'steps': 94879, 'loss/train': 1.28777015209198} 08/31/2021 06:25:03 - INFO - __main__ - Step 94881: {'lr': 0.00015246921333404785, 'samples': 18217152, 'steps': 94880, 'loss/train': 1.7397675514221191} 08/31/2021 06:25:03 - INFO - __main__ - Step 94882: {'lr': 0.00015246432710382324, 'samples': 18217344, 'steps': 94881, 'loss/train': 0.7739412188529968} 08/31/2021 06:25:04 - INFO - __main__ - Step 94883: {'lr': 0.00015245944091754675, 'samples': 18217536, 'steps': 94882, 'loss/train': 1.3675858974456787} 08/31/2021 06:25:05 - INFO - __main__ - Step 94884: {'lr': 0.00015245455477522053, 'samples': 18217728, 'steps': 94883, 'loss/train': 1.3428376913070679} 08/31/2021 06:25:06 - INFO - __main__ - Step 94885: {'lr': 0.00015244966867684683, 'samples': 18217920, 'steps': 94884, 'loss/train': 3.1890387535095215} 08/31/2021 06:25:06 - INFO - __main__ - Step 94886: {'lr': 0.00015244478262242775, 'samples': 18218112, 'steps': 94885, 'loss/train': 0.0578356571495533} 08/31/2021 06:25:06 - INFO - __main__ - Step 94887: {'lr': 0.00015243989661196556, 'samples': 18218304, 'steps': 94886, 'loss/train': 1.484437108039856} 08/31/2021 06:25:07 - INFO - __main__ - Step 94888: {'lr': 0.0001524350106454624, 'samples': 18218496, 'steps': 94887, 'loss/train': 1.5331742763519287} 08/31/2021 06:25:09 - INFO - __main__ - Step 94889: {'lr': 0.00015243012472292055, 'samples': 18218688, 'steps': 94888, 'loss/train': 1.319157600402832} 08/31/2021 06:25:09 - INFO - __main__ - Step 94890: {'lr': 0.00015242523884434218, 'samples': 18218880, 'steps': 94889, 'loss/train': 0.36515235900878906} 08/31/2021 06:25:10 - INFO - __main__ - Step 94891: {'lr': 0.00015242035300972945, 'samples': 18219072, 'steps': 94890, 'loss/train': 0.46877390146255493} 08/31/2021 06:25:10 - INFO - __main__ - Step 94892: {'lr': 0.00015241546721908467, 'samples': 18219264, 'steps': 94891, 'loss/train': 1.617020606994629} 08/31/2021 06:25:10 - INFO - __main__ - Step 94893: {'lr': 0.00015241058147240995, 'samples': 18219456, 'steps': 94892, 'loss/train': 0.6503520607948303} 08/31/2021 06:25:12 - INFO - __main__ - Step 94894: {'lr': 0.0001524056957697075, 'samples': 18219648, 'steps': 94893, 'loss/train': 1.461377739906311} 08/31/2021 06:25:12 - INFO - __main__ - Step 94895: {'lr': 0.00015240081011097954, 'samples': 18219840, 'steps': 94894, 'loss/train': 1.4338229894638062} 08/31/2021 06:25:13 - INFO - __main__ - Step 94896: {'lr': 0.00015239592449622824, 'samples': 18220032, 'steps': 94895, 'loss/train': 0.9824725985527039} 08/31/2021 06:25:13 - INFO - __main__ - Step 94897: {'lr': 0.0001523910389254559, 'samples': 18220224, 'steps': 94896, 'loss/train': 1.5319007635116577} 08/31/2021 06:25:14 - INFO - __main__ - Step 94898: {'lr': 0.00015238615339866472, 'samples': 18220416, 'steps': 94897, 'loss/train': 1.086488127708435} 08/31/2021 06:25:15 - INFO - __main__ - Step 94899: {'lr': 0.00015238126791585673, 'samples': 18220608, 'steps': 94898, 'loss/train': 0.4405345320701599} 08/31/2021 06:25:16 - INFO - __main__ - Step 94900: {'lr': 0.00015237638247703422, 'samples': 18220800, 'steps': 94899, 'loss/train': 0.880560040473938} 08/31/2021 06:25:16 - INFO - __main__ - Step 94901: {'lr': 0.0001523714970821994, 'samples': 18220992, 'steps': 94900, 'loss/train': 1.1982256174087524} 08/31/2021 06:25:17 - INFO - __main__ - Step 94902: {'lr': 0.00015236661173135453, 'samples': 18221184, 'steps': 94901, 'loss/train': 1.0486304759979248} 08/31/2021 06:25:17 - INFO - __main__ - Step 94903: {'lr': 0.0001523617264245017, 'samples': 18221376, 'steps': 94902, 'loss/train': 1.5528888702392578} 08/31/2021 06:25:19 - INFO - __main__ - Step 94904: {'lr': 0.0001523568411616432, 'samples': 18221568, 'steps': 94903, 'loss/train': 0.559154212474823} 08/31/2021 06:25:19 - INFO - __main__ - Step 94905: {'lr': 0.0001523519559427812, 'samples': 18221760, 'steps': 94904, 'loss/train': 0.6041433215141296} 08/31/2021 06:25:19 - INFO - __main__ - Step 94906: {'lr': 0.00015234707076791786, 'samples': 18221952, 'steps': 94905, 'loss/train': 0.7038237452507019} 08/31/2021 06:25:20 - INFO - __main__ - Step 94907: {'lr': 0.00015234218563705548, 'samples': 18222144, 'steps': 94906, 'loss/train': 0.8121737837791443} 08/31/2021 06:25:20 - INFO - __main__ - Step 94908: {'lr': 0.00015233730055019617, 'samples': 18222336, 'steps': 94907, 'loss/train': 1.1116304397583008} 08/31/2021 06:25:20 - INFO - __main__ - Step 94909: {'lr': 0.0001523324155073422, 'samples': 18222528, 'steps': 94908, 'loss/train': 1.7484489679336548} 08/31/2021 06:25:22 - INFO - __main__ - Step 94910: {'lr': 0.0001523275305084957, 'samples': 18222720, 'steps': 94909, 'loss/train': 1.4115849733352661} 08/31/2021 06:25:23 - INFO - __main__ - Step 94911: {'lr': 0.00015232264555365893, 'samples': 18222912, 'steps': 94910, 'loss/train': 0.4068971872329712} 08/31/2021 06:25:23 - INFO - __main__ - Step 94912: {'lr': 0.00015231776064283419, 'samples': 18223104, 'steps': 94911, 'loss/train': 1.1475980281829834} 08/31/2021 06:25:23 - INFO - __main__ - Step 94913: {'lr': 0.00015231287577602344, 'samples': 18223296, 'steps': 94912, 'loss/train': 0.3628794550895691} 08/31/2021 06:25:24 - INFO - __main__ - Step 94914: {'lr': 0.00015230799095322894, 'samples': 18223488, 'steps': 94913, 'loss/train': 0.9224643707275391} 08/31/2021 06:25:25 - INFO - __main__ - Step 94915: {'lr': 0.00015230310617445303, 'samples': 18223680, 'steps': 94914, 'loss/train': 0.6660122275352478} 08/31/2021 06:25:25 - INFO - __main__ - Step 94916: {'lr': 0.00015229822143969778, 'samples': 18223872, 'steps': 94915, 'loss/train': 1.0580763816833496} 08/31/2021 06:25:26 - INFO - __main__ - Step 94917: {'lr': 0.0001522933367489655, 'samples': 18224064, 'steps': 94916, 'loss/train': 1.2115646600723267} 08/31/2021 06:25:26 - INFO - __main__ - Step 94918: {'lr': 0.0001522884521022583, 'samples': 18224256, 'steps': 94917, 'loss/train': 0.9677482843399048} 08/31/2021 06:25:27 - INFO - __main__ - Step 94919: {'lr': 0.0001522835674995784, 'samples': 18224448, 'steps': 94918, 'loss/train': 0.46123865246772766} 08/31/2021 06:25:28 - INFO - __main__ - Step 94920: {'lr': 0.00015227868294092806, 'samples': 18224640, 'steps': 94919, 'loss/train': 0.8012036085128784} 08/31/2021 06:25:28 - INFO - __main__ - Step 94921: {'lr': 0.00015227379842630939, 'samples': 18224832, 'steps': 94920, 'loss/train': 1.4300607442855835} 08/31/2021 06:25:29 - INFO - __main__ - Step 94922: {'lr': 0.0001522689139557247, 'samples': 18225024, 'steps': 94921, 'loss/train': 1.108616590499878} 08/31/2021 06:25:29 - INFO - __main__ - Step 94923: {'lr': 0.00015226402952917605, 'samples': 18225216, 'steps': 94922, 'loss/train': 1.4341390132904053} 08/31/2021 06:25:29 - INFO - __main__ - Step 94924: {'lr': 0.00015225914514666578, 'samples': 18225408, 'steps': 94923, 'loss/train': 1.0770517587661743} 08/31/2021 06:25:31 - INFO - __main__ - Step 94925: {'lr': 0.00015225426080819614, 'samples': 18225600, 'steps': 94924, 'loss/train': 1.5284321308135986} 08/31/2021 06:25:31 - INFO - __main__ - Step 94926: {'lr': 0.00015224937651376908, 'samples': 18225792, 'steps': 94925, 'loss/train': 0.8622894287109375} 08/31/2021 06:25:32 - INFO - __main__ - Step 94927: {'lr': 0.00015224449226338696, 'samples': 18225984, 'steps': 94926, 'loss/train': 1.5993280410766602} 08/31/2021 06:25:32 - INFO - __main__ - Step 94928: {'lr': 0.00015223960805705195, 'samples': 18226176, 'steps': 94927, 'loss/train': 1.5996336936950684} 08/31/2021 06:25:33 - INFO - __main__ - Step 94929: {'lr': 0.0001522347238947663, 'samples': 18226368, 'steps': 94928, 'loss/train': 0.27709874510765076} 08/31/2021 06:25:33 - INFO - __main__ - Step 94930: {'lr': 0.00015222983977653215, 'samples': 18226560, 'steps': 94929, 'loss/train': 1.3512866497039795} 08/31/2021 06:25:35 - INFO - __main__ - Step 94931: {'lr': 0.00015222495570235174, 'samples': 18226752, 'steps': 94930, 'loss/train': 1.6281085014343262} 08/31/2021 06:25:35 - INFO - __main__ - Step 94932: {'lr': 0.0001522200716722272, 'samples': 18226944, 'steps': 94931, 'loss/train': 2.0791525840759277} 08/31/2021 06:25:36 - INFO - __main__ - Step 94933: {'lr': 0.00015221518768616084, 'samples': 18227136, 'steps': 94932, 'loss/train': 0.025279222056269646} 08/31/2021 06:25:36 - INFO - __main__ - Step 94934: {'lr': 0.00015221030374415478, 'samples': 18227328, 'steps': 94933, 'loss/train': 0.018227320164442062} 08/31/2021 06:25:36 - INFO - __main__ - Step 94935: {'lr': 0.00015220541984621127, 'samples': 18227520, 'steps': 94934, 'loss/train': 0.016728278249502182} 08/31/2021 06:25:37 - INFO - __main__ - Step 94936: {'lr': 0.0001522005359923325, 'samples': 18227712, 'steps': 94935, 'loss/train': 0.3646407723426819} 08/31/2021 06:25:38 - INFO - __main__ - Step 94937: {'lr': 0.00015219565218252062, 'samples': 18227904, 'steps': 94936, 'loss/train': 0.9196386933326721} 08/31/2021 06:25:39 - INFO - __main__ - Step 94938: {'lr': 0.000152190768416778, 'samples': 18228096, 'steps': 94937, 'loss/train': 1.5930010080337524} 08/31/2021 06:25:39 - INFO - __main__ - Step 94939: {'lr': 0.0001521858846951066, 'samples': 18228288, 'steps': 94938, 'loss/train': 0.5061541199684143} 08/31/2021 06:25:39 - INFO - __main__ - Step 94940: {'lr': 0.00015218100101750876, 'samples': 18228480, 'steps': 94939, 'loss/train': 0.28869104385375977} 08/31/2021 06:25:40 - INFO - __main__ - Step 94941: {'lr': 0.00015217611738398663, 'samples': 18228672, 'steps': 94940, 'loss/train': 1.972499966621399} 08/31/2021 06:25:42 - INFO - __main__ - Step 94942: {'lr': 0.0001521712337945424, 'samples': 18228864, 'steps': 94941, 'loss/train': 1.2001125812530518} 08/31/2021 06:25:42 - INFO - __main__ - Step 94943: {'lr': 0.00015216635024917834, 'samples': 18229056, 'steps': 94942, 'loss/train': 1.3603612184524536} 08/31/2021 06:25:43 - INFO - __main__ - Step 94944: {'lr': 0.0001521614667478966, 'samples': 18229248, 'steps': 94943, 'loss/train': 1.0689431428909302} 08/31/2021 06:25:43 - INFO - __main__ - Step 94945: {'lr': 0.0001521565832906994, 'samples': 18229440, 'steps': 94944, 'loss/train': 0.7572740316390991} 08/31/2021 06:25:43 - INFO - __main__ - Step 94946: {'lr': 0.00015215169987758894, 'samples': 18229632, 'steps': 94945, 'loss/train': 1.3706624507904053} 08/31/2021 06:25:44 - INFO - __main__ - Step 94947: {'lr': 0.00015214681650856739, 'samples': 18229824, 'steps': 94946, 'loss/train': 1.3080943822860718} 08/31/2021 06:25:46 - INFO - __main__ - Step 94948: {'lr': 0.000152141933183637, 'samples': 18230016, 'steps': 94947, 'loss/train': 1.1190744638442993} 08/31/2021 06:25:46 - INFO - __main__ - Step 94949: {'lr': 0.0001521370499027999, 'samples': 18230208, 'steps': 94948, 'loss/train': 1.2107840776443481} 08/31/2021 06:25:47 - INFO - __main__ - Step 94950: {'lr': 0.00015213216666605845, 'samples': 18230400, 'steps': 94949, 'loss/train': 0.9904088377952576} 08/31/2021 06:25:47 - INFO - __main__ - Step 94951: {'lr': 0.00015212728347341464, 'samples': 18230592, 'steps': 94950, 'loss/train': 1.2308207750320435} 08/31/2021 06:25:47 - INFO - __main__ - Step 94952: {'lr': 0.00015212240032487086, 'samples': 18230784, 'steps': 94951, 'loss/train': 1.2202136516571045} 08/31/2021 06:25:48 - INFO - __main__ - Step 94953: {'lr': 0.0001521175172204291, 'samples': 18230976, 'steps': 94952, 'loss/train': 1.4577301740646362} 08/31/2021 06:25:49 - INFO - __main__ - Step 94954: {'lr': 0.00015211263416009175, 'samples': 18231168, 'steps': 94953, 'loss/train': 1.0282222032546997} 08/31/2021 06:25:50 - INFO - __main__ - Step 94955: {'lr': 0.00015210775114386088, 'samples': 18231360, 'steps': 94954, 'loss/train': 1.7478739023208618} 08/31/2021 06:25:50 - INFO - __main__ - Step 94956: {'lr': 0.00015210286817173875, 'samples': 18231552, 'steps': 94955, 'loss/train': 0.29507380723953247} 08/31/2021 06:25:50 - INFO - __main__ - Step 94957: {'lr': 0.00015209798524372758, 'samples': 18231744, 'steps': 94956, 'loss/train': 1.4988181591033936} 08/31/2021 06:25:51 - INFO - __main__ - Step 94958: {'lr': 0.00015209310235982955, 'samples': 18231936, 'steps': 94957, 'loss/train': 0.6712117791175842} 08/31/2021 06:25:52 - INFO - __main__ - Step 94959: {'lr': 0.00015208821952004685, 'samples': 18232128, 'steps': 94958, 'loss/train': 1.5348387956619263} 08/31/2021 06:25:53 - INFO - __main__ - Step 94960: {'lr': 0.00015208333672438168, 'samples': 18232320, 'steps': 94959, 'loss/train': 2.5926408767700195} 08/31/2021 06:25:53 - INFO - __main__ - Step 94961: {'lr': 0.00015207845397283628, 'samples': 18232512, 'steps': 94960, 'loss/train': 0.88946533203125} 08/31/2021 06:25:53 - INFO - __main__ - Step 94962: {'lr': 0.00015207357126541281, 'samples': 18232704, 'steps': 94961, 'loss/train': 0.9929870367050171} 08/31/2021 06:25:54 - INFO - __main__ - Step 94963: {'lr': 0.00015206868860211345, 'samples': 18232896, 'steps': 94962, 'loss/train': 0.596460223197937} 08/31/2021 06:25:55 - INFO - __main__ - Step 94964: {'lr': 0.00015206380598294046, 'samples': 18233088, 'steps': 94963, 'loss/train': 0.2707999348640442} 08/31/2021 06:25:56 - INFO - __main__ - Step 94965: {'lr': 0.00015205892340789602, 'samples': 18233280, 'steps': 94964, 'loss/train': 0.5679212808609009} 08/31/2021 06:25:56 - INFO - __main__ - Step 94966: {'lr': 0.00015205404087698226, 'samples': 18233472, 'steps': 94965, 'loss/train': 1.0762089490890503} 08/31/2021 06:25:56 - INFO - __main__ - Step 94967: {'lr': 0.00015204915839020147, 'samples': 18233664, 'steps': 94966, 'loss/train': 1.2937674522399902} 08/31/2021 06:25:57 - INFO - __main__ - Step 94968: {'lr': 0.00015204427594755582, 'samples': 18233856, 'steps': 94967, 'loss/train': 0.7361130118370056} 08/31/2021 06:25:58 - INFO - __main__ - Step 94969: {'lr': 0.00015203939354904746, 'samples': 18234048, 'steps': 94968, 'loss/train': 0.7839331030845642} 08/31/2021 06:25:59 - INFO - __main__ - Step 94970: {'lr': 0.0001520345111946787, 'samples': 18234240, 'steps': 94969, 'loss/train': 2.9002935886383057} 08/31/2021 06:25:59 - INFO - __main__ - Step 94971: {'lr': 0.00015202962888445165, 'samples': 18234432, 'steps': 94970, 'loss/train': 0.9635030031204224} 08/31/2021 06:26:00 - INFO - __main__ - Step 94972: {'lr': 0.00015202474661836856, 'samples': 18234624, 'steps': 94971, 'loss/train': 0.6992368102073669} 08/31/2021 06:26:00 - INFO - __main__ - Step 94973: {'lr': 0.0001520198643964316, 'samples': 18234816, 'steps': 94972, 'loss/train': 0.6931453943252563} 08/31/2021 06:26:00 - INFO - __main__ - Step 94974: {'lr': 0.00015201498221864297, 'samples': 18235008, 'steps': 94973, 'loss/train': 0.5150843262672424} 08/31/2021 06:26:02 - INFO - __main__ - Step 94975: {'lr': 0.00015201010008500488, 'samples': 18235200, 'steps': 94974, 'loss/train': 1.3616493940353394} 08/31/2021 06:26:03 - INFO - __main__ - Step 94976: {'lr': 0.00015200521799551948, 'samples': 18235392, 'steps': 94975, 'loss/train': 0.7162086963653564} 08/31/2021 06:26:03 - INFO - __main__ - Step 94977: {'lr': 0.0001520003359501891, 'samples': 18235584, 'steps': 94976, 'loss/train': 0.7868983149528503} 08/31/2021 06:26:03 - INFO - __main__ - Step 94978: {'lr': 0.00015199545394901576, 'samples': 18235776, 'steps': 94977, 'loss/train': 1.0809261798858643} 08/31/2021 06:26:04 - INFO - __main__ - Step 94979: {'lr': 0.00015199057199200187, 'samples': 18235968, 'steps': 94978, 'loss/train': 1.48184072971344} 08/31/2021 06:26:06 - INFO - __main__ - Step 94980: {'lr': 0.00015198569007914944, 'samples': 18236160, 'steps': 94979, 'loss/train': 0.5227452516555786} 08/31/2021 06:26:06 - INFO - __main__ - Step 94981: {'lr': 0.00015198080821046076, 'samples': 18236352, 'steps': 94980, 'loss/train': 1.237851858139038} 08/31/2021 06:26:07 - INFO - __main__ - Step 94982: {'lr': 0.000151975926385938, 'samples': 18236544, 'steps': 94981, 'loss/train': 1.5332419872283936} 08/31/2021 06:26:07 - INFO - __main__ - Step 94983: {'lr': 0.00015197104460558345, 'samples': 18236736, 'steps': 94982, 'loss/train': 1.3830705881118774} 08/31/2021 06:26:07 - INFO - __main__ - Step 94984: {'lr': 0.0001519661628693992, 'samples': 18236928, 'steps': 94983, 'loss/train': 0.9368762969970703} 08/31/2021 06:26:08 - INFO - __main__ - Step 94985: {'lr': 0.0001519612811773874, 'samples': 18237120, 'steps': 94984, 'loss/train': 1.7326565980911255} 08/31/2021 06:26:08 - INFO - __main__ - Step 94986: {'lr': 0.00015195639952955041, 'samples': 18237312, 'steps': 94985, 'loss/train': 1.368809700012207} 08/31/2021 06:26:10 - INFO - __main__ - Step 94987: {'lr': 0.00015195151792589035, 'samples': 18237504, 'steps': 94986, 'loss/train': 1.1255162954330444} 08/31/2021 06:26:10 - INFO - __main__ - Step 94988: {'lr': 0.00015194663636640938, 'samples': 18237696, 'steps': 94987, 'loss/train': 1.2609392404556274} 08/31/2021 06:26:10 - INFO - __main__ - Step 94989: {'lr': 0.0001519417548511098, 'samples': 18237888, 'steps': 94988, 'loss/train': 0.9993146061897278} 08/31/2021 06:26:11 - INFO - __main__ - Step 94990: {'lr': 0.00015193687337999368, 'samples': 18238080, 'steps': 94989, 'loss/train': 1.2303082942962646} 08/31/2021 06:26:11 - INFO - __main__ - Step 94991: {'lr': 0.00015193199195306334, 'samples': 18238272, 'steps': 94990, 'loss/train': 1.3919596672058105} 08/31/2021 06:26:12 - INFO - __main__ - Step 94992: {'lr': 0.000151927110570321, 'samples': 18238464, 'steps': 94991, 'loss/train': 0.4504370391368866} 08/31/2021 06:26:13 - INFO - __main__ - Step 94993: {'lr': 0.00015192222923176869, 'samples': 18238656, 'steps': 94992, 'loss/train': 0.8493242859840393} 08/31/2021 06:26:13 - INFO - __main__ - Step 94994: {'lr': 0.0001519173479374088, 'samples': 18238848, 'steps': 94993, 'loss/train': 1.341725468635559} 08/31/2021 06:26:14 - INFO - __main__ - Step 94995: {'lr': 0.00015191246668724335, 'samples': 18239040, 'steps': 94994, 'loss/train': 1.1359872817993164} 08/31/2021 06:26:14 - INFO - __main__ - Step 94996: {'lr': 0.00015190758548127464, 'samples': 18239232, 'steps': 94995, 'loss/train': 1.2811170816421509} 08/31/2021 06:26:16 - INFO - __main__ - Step 94997: {'lr': 0.00015190270431950488, 'samples': 18239424, 'steps': 94996, 'loss/train': 1.3686885833740234} 08/31/2021 06:26:16 - INFO - __main__ - Step 94998: {'lr': 0.00015189782320193624, 'samples': 18239616, 'steps': 94997, 'loss/train': 1.4339511394500732} 08/31/2021 06:26:17 - INFO - __main__ - Step 94999: {'lr': 0.00015189294212857095, 'samples': 18239808, 'steps': 94998, 'loss/train': 0.059744592756032944} 08/31/2021 06:26:17 - INFO - __main__ - Step 95000: {'lr': 0.00015188806109941113, 'samples': 18240000, 'steps': 94999, 'loss/train': 0.30027759075164795} 08/31/2021 06:26:17 - INFO - __main__ - Step 95001: {'lr': 0.00015188318011445906, 'samples': 18240192, 'steps': 95000, 'loss/train': 1.0939452648162842} 08/31/2021 06:26:18 - INFO - __main__ - Step 95002: {'lr': 0.00015187829917371693, 'samples': 18240384, 'steps': 95001, 'loss/train': 0.019338907673954964} 08/31/2021 06:26:20 - INFO - __main__ - Step 95003: {'lr': 0.00015187341827718694, 'samples': 18240576, 'steps': 95002, 'loss/train': 0.06557648628950119} 08/31/2021 06:26:20 - INFO - __main__ - Step 95004: {'lr': 0.00015186853742487122, 'samples': 18240768, 'steps': 95003, 'loss/train': 0.8449533581733704} 08/31/2021 06:26:21 - INFO - __main__ - Step 95005: {'lr': 0.00015186365661677207, 'samples': 18240960, 'steps': 95004, 'loss/train': 0.25387683510780334} 08/31/2021 06:26:21 - INFO - __main__ - Step 95006: {'lr': 0.0001518587758528917, 'samples': 18241152, 'steps': 95005, 'loss/train': 1.8089929819107056} 08/31/2021 06:26:21 - INFO - __main__ - Step 95007: {'lr': 0.00015185389513323218, 'samples': 18241344, 'steps': 95006, 'loss/train': 1.2375410795211792} 08/31/2021 06:26:23 - INFO - __main__ - Step 95008: {'lr': 0.00015184901445779582, 'samples': 18241536, 'steps': 95007, 'loss/train': 0.8121448755264282} 08/31/2021 06:26:23 - INFO - __main__ - Step 95009: {'lr': 0.0001518441338265847, 'samples': 18241728, 'steps': 95008, 'loss/train': 1.2479770183563232} 08/31/2021 06:26:23 - INFO - __main__ - Step 95010: {'lr': 0.00015183925323960113, 'samples': 18241920, 'steps': 95009, 'loss/train': 1.8614426851272583} 08/31/2021 06:26:24 - INFO - __main__ - Step 95011: {'lr': 0.0001518343726968473, 'samples': 18242112, 'steps': 95010, 'loss/train': 1.2630261182785034} 08/31/2021 06:26:24 - INFO - __main__ - Step 95012: {'lr': 0.00015182949219832536, 'samples': 18242304, 'steps': 95011, 'loss/train': 0.8722225427627563} 08/31/2021 06:26:26 - INFO - __main__ - Step 95013: {'lr': 0.00015182461174403756, 'samples': 18242496, 'steps': 95012, 'loss/train': 1.02739679813385} 08/31/2021 06:26:27 - INFO - __main__ - Step 95014: {'lr': 0.00015181973133398605, 'samples': 18242688, 'steps': 95013, 'loss/train': 0.9890322089195251} 08/31/2021 06:26:27 - INFO - __main__ - Step 95015: {'lr': 0.00015181485096817305, 'samples': 18242880, 'steps': 95014, 'loss/train': 0.7633033990859985} 08/31/2021 06:26:27 - INFO - __main__ - Step 95016: {'lr': 0.00015180997064660078, 'samples': 18243072, 'steps': 95015, 'loss/train': 1.4435943365097046} 08/31/2021 06:26:28 - INFO - __main__ - Step 95017: {'lr': 0.00015180509036927142, 'samples': 18243264, 'steps': 95016, 'loss/train': 1.117884635925293} 08/31/2021 06:26:28 - INFO - __main__ - Step 95018: {'lr': 0.00015180021013618715, 'samples': 18243456, 'steps': 95017, 'loss/train': 1.4501843452453613} 08/31/2021 06:26:30 - INFO - __main__ - Step 95019: {'lr': 0.00015179532994735034, 'samples': 18243648, 'steps': 95018, 'loss/train': 1.1827322244644165} 08/31/2021 06:26:30 - INFO - __main__ - Step 95020: {'lr': 0.00015179044980276292, 'samples': 18243840, 'steps': 95019, 'loss/train': 0.736686110496521} 08/31/2021 06:26:30 - INFO - __main__ - Step 95021: {'lr': 0.00015178556970242717, 'samples': 18244032, 'steps': 95020, 'loss/train': 1.5315018892288208} 08/31/2021 06:26:31 - INFO - __main__ - Step 95022: {'lr': 0.00015178068964634536, 'samples': 18244224, 'steps': 95021, 'loss/train': 1.2203922271728516} 08/31/2021 06:26:31 - INFO - __main__ - Step 95023: {'lr': 0.00015177580963451965, 'samples': 18244416, 'steps': 95022, 'loss/train': 1.1639035940170288} 08/31/2021 06:26:32 - INFO - __main__ - Step 95024: {'lr': 0.00015177092966695225, 'samples': 18244608, 'steps': 95023, 'loss/train': 0.9466610550880432} 08/31/2021 06:26:33 - INFO - __main__ - Step 95025: {'lr': 0.00015176604974364533, 'samples': 18244800, 'steps': 95024, 'loss/train': 0.7393279671669006} 08/31/2021 06:26:33 - INFO - __main__ - Step 95026: {'lr': 0.00015176116986460116, 'samples': 18244992, 'steps': 95025, 'loss/train': 1.7487672567367554} 08/31/2021 06:26:34 - INFO - __main__ - Step 95027: {'lr': 0.00015175629002982184, 'samples': 18245184, 'steps': 95026, 'loss/train': 1.042631983757019} 08/31/2021 06:26:34 - INFO - __main__ - Step 95028: {'lr': 0.00015175141023930966, 'samples': 18245376, 'steps': 95027, 'loss/train': 1.3484052419662476} 08/31/2021 06:26:34 - INFO - __main__ - Step 95029: {'lr': 0.00015174653049306676, 'samples': 18245568, 'steps': 95028, 'loss/train': 0.49726060032844543} 08/31/2021 06:26:36 - INFO - __main__ - Step 95030: {'lr': 0.00015174165079109533, 'samples': 18245760, 'steps': 95029, 'loss/train': 0.6085231304168701} 08/31/2021 06:26:36 - INFO - __main__ - Step 95031: {'lr': 0.00015173677113339761, 'samples': 18245952, 'steps': 95030, 'loss/train': 1.0347704887390137} 08/31/2021 06:26:37 - INFO - __main__ - Step 95032: {'lr': 0.00015173189151997582, 'samples': 18246144, 'steps': 95031, 'loss/train': 1.4505196809768677} 08/31/2021 06:26:37 - INFO - __main__ - Step 95033: {'lr': 0.00015172701195083222, 'samples': 18246336, 'steps': 95032, 'loss/train': 1.4218908548355103} 08/31/2021 06:26:37 - INFO - __main__ - Step 95034: {'lr': 0.00015172213242596879, 'samples': 18246528, 'steps': 95033, 'loss/train': 1.4083921909332275} 08/31/2021 06:26:39 - INFO - __main__ - Step 95035: {'lr': 0.00015171725294538786, 'samples': 18246720, 'steps': 95034, 'loss/train': 1.35342538356781} 08/31/2021 06:26:39 - INFO - __main__ - Step 95036: {'lr': 0.00015171237350909158, 'samples': 18246912, 'steps': 95035, 'loss/train': 1.0126897096633911} 08/31/2021 06:26:40 - INFO - __main__ - Step 95037: {'lr': 0.00015170749411708224, 'samples': 18247104, 'steps': 95036, 'loss/train': 1.0373473167419434} 08/31/2021 06:26:40 - INFO - __main__ - Step 95038: {'lr': 0.00015170261476936194, 'samples': 18247296, 'steps': 95037, 'loss/train': 1.850600242614746} 08/31/2021 06:26:40 - INFO - __main__ - Step 95039: {'lr': 0.00015169773546593295, 'samples': 18247488, 'steps': 95038, 'loss/train': 1.1743659973144531} 08/31/2021 06:26:42 - INFO - __main__ - Step 95040: {'lr': 0.00015169285620679745, 'samples': 18247680, 'steps': 95039, 'loss/train': 0.6365709900856018} 08/31/2021 06:26:42 - INFO - __main__ - Step 95041: {'lr': 0.00015168797699195764, 'samples': 18247872, 'steps': 95040, 'loss/train': 1.119735836982727} 08/31/2021 06:26:43 - INFO - __main__ - Step 95042: {'lr': 0.00015168309782141569, 'samples': 18248064, 'steps': 95041, 'loss/train': 1.6159107685089111} 08/31/2021 06:26:43 - INFO - __main__ - Step 95043: {'lr': 0.00015167821869517382, 'samples': 18248256, 'steps': 95042, 'loss/train': 1.5948725938796997} 08/31/2021 06:26:43 - INFO - __main__ - Step 95044: {'lr': 0.00015167333961323425, 'samples': 18248448, 'steps': 95043, 'loss/train': 1.0260493755340576} 08/31/2021 06:26:45 - INFO - __main__ - Step 95045: {'lr': 0.00015166846057559913, 'samples': 18248640, 'steps': 95044, 'loss/train': 1.7871254682540894} 08/31/2021 06:26:46 - INFO - __main__ - Step 95046: {'lr': 0.00015166358158227077, 'samples': 18248832, 'steps': 95045, 'loss/train': 1.469797968864441} 08/31/2021 06:26:46 - INFO - __main__ - Step 95047: {'lr': 0.00015165870263325121, 'samples': 18249024, 'steps': 95046, 'loss/train': 1.0614168643951416} 08/31/2021 06:26:46 - INFO - __main__ - Step 95048: {'lr': 0.00015165382372854273, 'samples': 18249216, 'steps': 95047, 'loss/train': 0.7523884773254395} 08/31/2021 06:26:47 - INFO - __main__ - Step 95049: {'lr': 0.0001516489448681475, 'samples': 18249408, 'steps': 95048, 'loss/train': 0.87937331199646} 08/31/2021 06:26:48 - INFO - __main__ - Step 95050: {'lr': 0.00015164406605206777, 'samples': 18249600, 'steps': 95049, 'loss/train': 0.05876798555254936} 08/31/2021 06:26:49 - INFO - __main__ - Step 95051: {'lr': 0.00015163918728030565, 'samples': 18249792, 'steps': 95050, 'loss/train': 1.4462001323699951} 08/31/2021 06:26:49 - INFO - __main__ - Step 95052: {'lr': 0.00015163430855286343, 'samples': 18249984, 'steps': 95051, 'loss/train': 1.6049752235412598} 08/31/2021 06:26:50 - INFO - __main__ - Step 95053: {'lr': 0.00015162942986974326, 'samples': 18250176, 'steps': 95052, 'loss/train': 0.13199901580810547} 08/31/2021 06:26:50 - INFO - __main__ - Step 95054: {'lr': 0.00015162455123094736, 'samples': 18250368, 'steps': 95053, 'loss/train': 1.5982604026794434} 08/31/2021 06:26:50 - INFO - __main__ - Step 95055: {'lr': 0.0001516196726364779, 'samples': 18250560, 'steps': 95054, 'loss/train': 1.1598460674285889} 08/31/2021 06:26:52 - INFO - __main__ - Step 95056: {'lr': 0.00015161479408633713, 'samples': 18250752, 'steps': 95055, 'loss/train': 1.503164529800415} 08/31/2021 06:26:53 - INFO - __main__ - Step 95057: {'lr': 0.00015160991558052722, 'samples': 18250944, 'steps': 95056, 'loss/train': 0.1674950271844864} 08/31/2021 06:26:53 - INFO - __main__ - Step 95058: {'lr': 0.00015160503711905032, 'samples': 18251136, 'steps': 95057, 'loss/train': 1.0555278062820435} 08/31/2021 06:26:54 - INFO - __main__ - Step 95059: {'lr': 0.0001516001587019088, 'samples': 18251328, 'steps': 95058, 'loss/train': 0.042906276881694794} 08/31/2021 06:26:54 - INFO - __main__ - Step 95060: {'lr': 0.00015159528032910463, 'samples': 18251520, 'steps': 95059, 'loss/train': 1.2860605716705322} 08/31/2021 06:26:56 - INFO - __main__ - Step 95061: {'lr': 0.0001515904020006401, 'samples': 18251712, 'steps': 95060, 'loss/train': 1.1646454334259033} 08/31/2021 06:26:56 - INFO - __main__ - Step 95062: {'lr': 0.00015158552371651743, 'samples': 18251904, 'steps': 95061, 'loss/train': 1.570906639099121} 08/31/2021 06:26:56 - INFO - __main__ - Step 95063: {'lr': 0.00015158064547673877, 'samples': 18252096, 'steps': 95062, 'loss/train': 1.2358815670013428} 08/31/2021 06:26:57 - INFO - __main__ - Step 95064: {'lr': 0.0001515757672813064, 'samples': 18252288, 'steps': 95063, 'loss/train': 1.3062790632247925} 08/31/2021 06:26:57 - INFO - __main__ - Step 95065: {'lr': 0.00015157088913022242, 'samples': 18252480, 'steps': 95064, 'loss/train': 1.8022379875183105} 08/31/2021 06:26:58 - INFO - __main__ - Step 95066: {'lr': 0.00015156601102348912, 'samples': 18252672, 'steps': 95065, 'loss/train': 0.74410480260849} 08/31/2021 06:26:59 - INFO - __main__ - Step 95067: {'lr': 0.00015156113296110866, 'samples': 18252864, 'steps': 95066, 'loss/train': 1.2682722806930542} 08/31/2021 06:27:00 - INFO - __main__ - Step 95068: {'lr': 0.00015155625494308323, 'samples': 18253056, 'steps': 95067, 'loss/train': 1.3312116861343384} 08/31/2021 06:27:00 - INFO - __main__ - Step 95069: {'lr': 0.000151551376969415, 'samples': 18253248, 'steps': 95068, 'loss/train': 0.9082761406898499} 08/31/2021 06:27:00 - INFO - __main__ - Step 95070: {'lr': 0.00015154649904010624, 'samples': 18253440, 'steps': 95069, 'loss/train': 1.1721792221069336} 08/31/2021 06:27:01 - INFO - __main__ - Step 95071: {'lr': 0.00015154162115515907, 'samples': 18253632, 'steps': 95070, 'loss/train': 1.1034975051879883} 08/31/2021 06:27:02 - INFO - __main__ - Step 95072: {'lr': 0.00015153674331457574, 'samples': 18253824, 'steps': 95071, 'loss/train': 1.7276735305786133} 08/31/2021 06:27:03 - INFO - __main__ - Step 95073: {'lr': 0.00015153186551835856, 'samples': 18254016, 'steps': 95072, 'loss/train': 1.0217341184616089} 08/31/2021 06:27:03 - INFO - __main__ - Step 95074: {'lr': 0.00015152698776650948, 'samples': 18254208, 'steps': 95073, 'loss/train': 0.606885552406311} 08/31/2021 06:27:03 - INFO - __main__ - Step 95075: {'lr': 0.00015152211005903084, 'samples': 18254400, 'steps': 95074, 'loss/train': 1.1358191967010498} 08/31/2021 06:27:04 - INFO - __main__ - Step 95076: {'lr': 0.00015151723239592476, 'samples': 18254592, 'steps': 95075, 'loss/train': 0.7698326110839844} 08/31/2021 06:27:04 - INFO - __main__ - Step 95077: {'lr': 0.00015151235477719354, 'samples': 18254784, 'steps': 95076, 'loss/train': 2.1362369060516357} 08/31/2021 06:27:06 - INFO - __main__ - Step 95078: {'lr': 0.00015150747720283934, 'samples': 18254976, 'steps': 95077, 'loss/train': 1.4606441259384155} 08/31/2021 06:27:06 - INFO - __main__ - Step 95079: {'lr': 0.00015150259967286434, 'samples': 18255168, 'steps': 95078, 'loss/train': 1.2551168203353882} 08/31/2021 06:27:06 - INFO - __main__ - Step 95080: {'lr': 0.00015149772218727074, 'samples': 18255360, 'steps': 95079, 'loss/train': 1.097704291343689} 08/31/2021 06:27:07 - INFO - __main__ - Step 95081: {'lr': 0.00015149284474606073, 'samples': 18255552, 'steps': 95080, 'loss/train': 1.3918288946151733} 08/31/2021 06:27:07 - INFO - __main__ - Step 95082: {'lr': 0.00015148796734923656, 'samples': 18255744, 'steps': 95081, 'loss/train': 1.3043413162231445} 08/31/2021 06:27:09 - INFO - __main__ - Step 95083: {'lr': 0.00015148308999680038, 'samples': 18255936, 'steps': 95082, 'loss/train': 1.289328932762146} 08/31/2021 06:27:09 - INFO - __main__ - Step 95084: {'lr': 0.00015147821268875444, 'samples': 18256128, 'steps': 95083, 'loss/train': 0.2716228663921356} 08/31/2021 06:27:09 - INFO - __main__ - Step 95085: {'lr': 0.0001514733354251009, 'samples': 18256320, 'steps': 95084, 'loss/train': 0.8955122828483582} 08/31/2021 06:27:10 - INFO - __main__ - Step 95086: {'lr': 0.00015146845820584193, 'samples': 18256512, 'steps': 95085, 'loss/train': 0.6180307865142822} 08/31/2021 06:27:10 - INFO - __main__ - Step 95087: {'lr': 0.00015146358103097974, 'samples': 18256704, 'steps': 95086, 'loss/train': 1.003472924232483} 08/31/2021 06:27:12 - INFO - __main__ - Step 95088: {'lr': 0.00015145870390051653, 'samples': 18256896, 'steps': 95087, 'loss/train': 1.6494711637496948} 08/31/2021 06:27:12 - INFO - __main__ - Step 95089: {'lr': 0.0001514538268144545, 'samples': 18257088, 'steps': 95088, 'loss/train': 1.8084392547607422} 08/31/2021 06:27:13 - INFO - __main__ - Step 95090: {'lr': 0.00015144894977279588, 'samples': 18257280, 'steps': 95089, 'loss/train': 0.6006883382797241} 08/31/2021 06:27:13 - INFO - __main__ - Step 95091: {'lr': 0.00015144407277554282, 'samples': 18257472, 'steps': 95090, 'loss/train': 1.002094030380249} 08/31/2021 06:27:13 - INFO - __main__ - Step 95092: {'lr': 0.00015143919582269756, 'samples': 18257664, 'steps': 95091, 'loss/train': 1.697567105293274} 08/31/2021 06:27:15 - INFO - __main__ - Step 95093: {'lr': 0.00015143431891426223, 'samples': 18257856, 'steps': 95092, 'loss/train': 0.6913539171218872} 08/31/2021 06:27:15 - INFO - __main__ - Step 95094: {'lr': 0.00015142944205023912, 'samples': 18258048, 'steps': 95093, 'loss/train': 0.8878151774406433} 08/31/2021 06:27:16 - INFO - __main__ - Step 95095: {'lr': 0.0001514245652306304, 'samples': 18258240, 'steps': 95094, 'loss/train': 0.8068997859954834} 08/31/2021 06:27:16 - INFO - __main__ - Step 95096: {'lr': 0.00015141968845543824, 'samples': 18258432, 'steps': 95095, 'loss/train': 1.309606671333313} 08/31/2021 06:27:16 - INFO - __main__ - Step 95097: {'lr': 0.00015141481172466483, 'samples': 18258624, 'steps': 95096, 'loss/train': 0.7152243852615356} 08/31/2021 06:27:18 - INFO - __main__ - Step 95098: {'lr': 0.0001514099350383124, 'samples': 18258816, 'steps': 95097, 'loss/train': 1.3583133220672607} 08/31/2021 06:27:18 - INFO - __main__ - Step 95099: {'lr': 0.0001514050583963831, 'samples': 18259008, 'steps': 95098, 'loss/train': 1.1704837083816528} 08/31/2021 06:27:19 - INFO - __main__ - Step 95100: {'lr': 0.00015140018179887925, 'samples': 18259200, 'steps': 95099, 'loss/train': 0.17631195485591888} 08/31/2021 06:27:19 - INFO - __main__ - Step 95101: {'lr': 0.00015139530524580286, 'samples': 18259392, 'steps': 95100, 'loss/train': 0.11227105557918549} 08/31/2021 06:27:20 - INFO - __main__ - Step 95102: {'lr': 0.00015139042873715624, 'samples': 18259584, 'steps': 95101, 'loss/train': 0.9964969754219055} 08/31/2021 06:27:20 - INFO - __main__ - Step 95103: {'lr': 0.0001513855522729416, 'samples': 18259776, 'steps': 95102, 'loss/train': 0.6646439433097839} 08/31/2021 06:27:20 - INFO - __main__ - Step 95104: {'lr': 0.00015138067585316107, 'samples': 18259968, 'steps': 95103, 'loss/train': 0.6064831018447876} 08/31/2021 06:27:22 - INFO - __main__ - Step 95105: {'lr': 0.0001513757994778169, 'samples': 18260160, 'steps': 95104, 'loss/train': 1.7538124322891235} 08/31/2021 06:27:22 - INFO - __main__ - Step 95106: {'lr': 0.0001513709231469113, 'samples': 18260352, 'steps': 95105, 'loss/train': 1.6857504844665527} 08/31/2021 06:27:23 - INFO - __main__ - Step 95107: {'lr': 0.00015136604686044643, 'samples': 18260544, 'steps': 95106, 'loss/train': 1.2526320219039917} 08/31/2021 06:27:23 - INFO - __main__ - Step 95108: {'lr': 0.00015136117061842448, 'samples': 18260736, 'steps': 95107, 'loss/train': 1.1446281671524048} 08/31/2021 06:27:23 - INFO - __main__ - Step 95109: {'lr': 0.00015135629442084768, 'samples': 18260928, 'steps': 95108, 'loss/train': 1.758297085762024} 08/31/2021 06:27:25 - INFO - __main__ - Step 95110: {'lr': 0.0001513514182677182, 'samples': 18261120, 'steps': 95109, 'loss/train': 1.473426342010498} 08/31/2021 06:27:25 - INFO - __main__ - Step 95111: {'lr': 0.00015134654215903824, 'samples': 18261312, 'steps': 95110, 'loss/train': 1.4421947002410889} 08/31/2021 06:27:26 - INFO - __main__ - Step 95112: {'lr': 0.00015134166609481002, 'samples': 18261504, 'steps': 95111, 'loss/train': 1.447835087776184} 08/31/2021 06:27:26 - INFO - __main__ - Step 95113: {'lr': 0.00015133679007503577, 'samples': 18261696, 'steps': 95112, 'loss/train': 0.7539915442466736} 08/31/2021 06:27:26 - INFO - __main__ - Step 95114: {'lr': 0.0001513319140997176, 'samples': 18261888, 'steps': 95113, 'loss/train': 0.6922706365585327} 08/31/2021 06:27:28 - INFO - __main__ - Step 95115: {'lr': 0.00015132703816885768, 'samples': 18262080, 'steps': 95114, 'loss/train': 1.4959863424301147} 08/31/2021 06:27:29 - INFO - __main__ - Step 95116: {'lr': 0.00015132216228245834, 'samples': 18262272, 'steps': 95115, 'loss/train': 0.4750242233276367} 08/31/2021 06:27:30 - INFO - __main__ - Step 95117: {'lr': 0.00015131728644052173, 'samples': 18262464, 'steps': 95116, 'loss/train': 1.8914793729782104} 08/31/2021 06:27:30 - INFO - __main__ - Step 95118: {'lr': 0.00015131241064305002, 'samples': 18262656, 'steps': 95117, 'loss/train': 1.1035343408584595} 08/31/2021 06:27:30 - INFO - __main__ - Step 95119: {'lr': 0.0001513075348900454, 'samples': 18262848, 'steps': 95118, 'loss/train': 0.7225146293640137} 08/31/2021 06:27:32 - INFO - __main__ - Step 95120: {'lr': 0.00015130265918151004, 'samples': 18263040, 'steps': 95119, 'loss/train': 1.5622014999389648} 08/31/2021 06:27:32 - INFO - __main__ - Step 95121: {'lr': 0.0001512977835174462, 'samples': 18263232, 'steps': 95120, 'loss/train': 1.0448150634765625} 08/31/2021 06:27:33 - INFO - __main__ - Step 95122: {'lr': 0.0001512929078978561, 'samples': 18263424, 'steps': 95121, 'loss/train': 0.8534607887268066} 08/31/2021 06:27:33 - INFO - __main__ - Step 95123: {'lr': 0.00015128803232274186, 'samples': 18263616, 'steps': 95122, 'loss/train': 0.8182896971702576} 08/31/2021 06:27:33 - INFO - __main__ - Step 95124: {'lr': 0.0001512831567921057, 'samples': 18263808, 'steps': 95123, 'loss/train': 1.111001968383789} 08/31/2021 06:27:35 - INFO - __main__ - Step 95125: {'lr': 0.00015127828130594983, 'samples': 18264000, 'steps': 95124, 'loss/train': 1.3767828941345215} 08/31/2021 06:27:36 - INFO - __main__ - Step 95126: {'lr': 0.00015127340586427646, 'samples': 18264192, 'steps': 95125, 'loss/train': 1.9147857427597046} 08/31/2021 06:27:36 - INFO - __main__ - Step 95127: {'lr': 0.00015126853046708777, 'samples': 18264384, 'steps': 95126, 'loss/train': 1.6660298109054565} 08/31/2021 06:27:36 - INFO - __main__ - Step 95128: {'lr': 0.000151263655114386, 'samples': 18264576, 'steps': 95127, 'loss/train': 1.4872523546218872} 08/31/2021 06:27:37 - INFO - __main__ - Step 95129: {'lr': 0.00015125877980617326, 'samples': 18264768, 'steps': 95128, 'loss/train': 0.9856261014938354} 08/31/2021 06:27:37 - INFO - __main__ - Step 95130: {'lr': 0.00015125390454245177, 'samples': 18264960, 'steps': 95129, 'loss/train': 0.9714124798774719} 08/31/2021 06:27:38 - INFO - __main__ - Step 95131: {'lr': 0.00015124902932322376, 'samples': 18265152, 'steps': 95130, 'loss/train': 1.333583950996399} 08/31/2021 06:27:39 - INFO - __main__ - Step 95132: {'lr': 0.00015124415414849142, 'samples': 18265344, 'steps': 95131, 'loss/train': 1.111316442489624} 08/31/2021 06:27:39 - INFO - __main__ - Step 95133: {'lr': 0.0001512392790182569, 'samples': 18265536, 'steps': 95132, 'loss/train': 0.8797767162322998} 08/31/2021 06:27:40 - INFO - __main__ - Step 95134: {'lr': 0.00015123440393252248, 'samples': 18265728, 'steps': 95133, 'loss/train': 1.6392738819122314} 08/31/2021 06:27:40 - INFO - __main__ - Step 95135: {'lr': 0.00015122952889129029, 'samples': 18265920, 'steps': 95134, 'loss/train': 0.2891256511211395} 08/31/2021 06:27:41 - INFO - __main__ - Step 95136: {'lr': 0.00015122465389456256, 'samples': 18266112, 'steps': 95135, 'loss/train': 0.7667285203933716} 08/31/2021 06:27:42 - INFO - __main__ - Step 95137: {'lr': 0.00015121977894234145, 'samples': 18266304, 'steps': 95136, 'loss/train': 1.3402608633041382} 08/31/2021 06:27:42 - INFO - __main__ - Step 95138: {'lr': 0.00015121490403462924, 'samples': 18266496, 'steps': 95137, 'loss/train': 0.9015316367149353} 08/31/2021 06:27:43 - INFO - __main__ - Step 95139: {'lr': 0.000151210029171428, 'samples': 18266688, 'steps': 95138, 'loss/train': 1.561807632446289} 08/31/2021 06:27:43 - INFO - __main__ - Step 95140: {'lr': 0.00015120515435274018, 'samples': 18266880, 'steps': 95139, 'loss/train': 0.8278112411499023} 08/31/2021 06:27:45 - INFO - __main__ - Step 95141: {'lr': 0.00015120027957856764, 'samples': 18267072, 'steps': 95140, 'loss/train': 1.4549508094787598} 08/31/2021 06:27:45 - INFO - __main__ - Step 95142: {'lr': 0.0001511954048489127, 'samples': 18267264, 'steps': 95141, 'loss/train': 1.2149320840835571} 08/31/2021 06:27:46 - INFO - __main__ - Step 95143: {'lr': 0.00015119053016377765, 'samples': 18267456, 'steps': 95142, 'loss/train': 1.739427924156189} 08/31/2021 06:27:46 - INFO - __main__ - Step 95144: {'lr': 0.0001511856555231646, 'samples': 18267648, 'steps': 95143, 'loss/train': 1.5927716493606567} 08/31/2021 06:27:46 - INFO - __main__ - Step 95145: {'lr': 0.00015118078092707577, 'samples': 18267840, 'steps': 95144, 'loss/train': 0.023278813809156418} 08/31/2021 06:27:47 - INFO - __main__ - Step 95146: {'lr': 0.00015117590637551333, 'samples': 18268032, 'steps': 95145, 'loss/train': 1.3713338375091553} 08/31/2021 06:27:48 - INFO - __main__ - Step 95147: {'lr': 0.00015117103186847953, 'samples': 18268224, 'steps': 95146, 'loss/train': 0.9619539976119995} 08/31/2021 06:27:49 - INFO - __main__ - Step 95148: {'lr': 0.00015116615740597654, 'samples': 18268416, 'steps': 95147, 'loss/train': 1.1390212774276733} 08/31/2021 06:27:49 - INFO - __main__ - Step 95149: {'lr': 0.00015116128298800653, 'samples': 18268608, 'steps': 95148, 'loss/train': 1.303755283355713} 08/31/2021 06:27:49 - INFO - __main__ - Step 95150: {'lr': 0.00015115640861457176, 'samples': 18268800, 'steps': 95149, 'loss/train': 1.4777277708053589} 08/31/2021 06:27:50 - INFO - __main__ - Step 95151: {'lr': 0.00015115153428567435, 'samples': 18268992, 'steps': 95150, 'loss/train': 0.5514496564865112} 08/31/2021 06:27:51 - INFO - __main__ - Step 95152: {'lr': 0.00015114666000131652, 'samples': 18269184, 'steps': 95151, 'loss/train': 1.4117095470428467} 08/31/2021 06:27:52 - INFO - __main__ - Step 95153: {'lr': 0.0001511417857615005, 'samples': 18269376, 'steps': 95152, 'loss/train': 1.464296579360962} 08/31/2021 06:27:52 - INFO - __main__ - Step 95154: {'lr': 0.00015113691156622857, 'samples': 18269568, 'steps': 95153, 'loss/train': 1.3284577131271362} 08/31/2021 06:27:52 - INFO - __main__ - Step 95155: {'lr': 0.00015113203741550275, 'samples': 18269760, 'steps': 95154, 'loss/train': 1.4946268796920776} 08/31/2021 06:27:53 - INFO - __main__ - Step 95156: {'lr': 0.00015112716330932524, 'samples': 18269952, 'steps': 95155, 'loss/train': 1.2656611204147339} 08/31/2021 06:27:54 - INFO - __main__ - Step 95157: {'lr': 0.0001511222892476984, 'samples': 18270144, 'steps': 95156, 'loss/train': 1.3081614971160889} 08/31/2021 06:27:55 - INFO - __main__ - Step 95158: {'lr': 0.00015111741523062423, 'samples': 18270336, 'steps': 95157, 'loss/train': 0.6933846473693848} 08/31/2021 06:27:55 - INFO - __main__ - Step 95159: {'lr': 0.00015111254125810508, 'samples': 18270528, 'steps': 95158, 'loss/train': 0.7546186447143555} 08/31/2021 06:27:55 - INFO - __main__ - Step 95160: {'lr': 0.0001511076673301431, 'samples': 18270720, 'steps': 95159, 'loss/train': 1.4826420545578003} 08/31/2021 06:27:56 - INFO - __main__ - Step 95161: {'lr': 0.00015110279344674043, 'samples': 18270912, 'steps': 95160, 'loss/train': 1.4843791723251343} 08/31/2021 06:27:56 - INFO - __main__ - Step 95162: {'lr': 0.00015109791960789937, 'samples': 18271104, 'steps': 95161, 'loss/train': 1.6457836627960205} 08/31/2021 06:27:58 - INFO - __main__ - Step 95163: {'lr': 0.00015109304581362203, 'samples': 18271296, 'steps': 95162, 'loss/train': 1.3338003158569336} 08/31/2021 06:27:58 - INFO - __main__ - Step 95164: {'lr': 0.0001510881720639107, 'samples': 18271488, 'steps': 95163, 'loss/train': 0.5379081964492798} 08/31/2021 06:27:58 - INFO - __main__ - Step 95165: {'lr': 0.00015108329835876745, 'samples': 18271680, 'steps': 95164, 'loss/train': 1.2839831113815308} 08/31/2021 06:27:59 - INFO - __main__ - Step 95166: {'lr': 0.00015107842469819452, 'samples': 18271872, 'steps': 95165, 'loss/train': 1.4290434122085571} 08/31/2021 06:27:59 - INFO - __main__ - Step 95167: {'lr': 0.00015107355108219425, 'samples': 18272064, 'steps': 95166, 'loss/train': 0.9247078895568848} 08/31/2021 06:28:01 - INFO - __main__ - Step 95168: {'lr': 0.00015106867751076865, 'samples': 18272256, 'steps': 95167, 'loss/train': 1.0398356914520264} 08/31/2021 06:28:02 - INFO - __main__ - Step 95169: {'lr': 0.0001510638039839199, 'samples': 18272448, 'steps': 95168, 'loss/train': 0.1290113925933838} 08/31/2021 06:28:02 - INFO - __main__ - Step 95170: {'lr': 0.00015105893050165034, 'samples': 18272640, 'steps': 95169, 'loss/train': 0.9987427592277527} 08/31/2021 06:28:02 - INFO - __main__ - Step 95171: {'lr': 0.00015105405706396208, 'samples': 18272832, 'steps': 95170, 'loss/train': 1.747723937034607} 08/31/2021 06:28:03 - INFO - __main__ - Step 95172: {'lr': 0.00015104918367085736, 'samples': 18273024, 'steps': 95171, 'loss/train': 1.6289191246032715} 08/31/2021 06:28:04 - INFO - __main__ - Step 95173: {'lr': 0.00015104431032233827, 'samples': 18273216, 'steps': 95172, 'loss/train': 1.373146653175354} 08/31/2021 06:28:05 - INFO - __main__ - Step 95174: {'lr': 0.00015103943701840717, 'samples': 18273408, 'steps': 95173, 'loss/train': 1.0705293416976929} 08/31/2021 06:28:05 - INFO - __main__ - Step 95175: {'lr': 0.00015103456375906613, 'samples': 18273600, 'steps': 95174, 'loss/train': 1.109922170639038} 08/31/2021 06:28:05 - INFO - __main__ - Step 95176: {'lr': 0.00015102969054431743, 'samples': 18273792, 'steps': 95175, 'loss/train': 0.5293883681297302} 08/31/2021 06:28:06 - INFO - __main__ - Step 95177: {'lr': 0.00015102481737416318, 'samples': 18273984, 'steps': 95176, 'loss/train': 1.2273223400115967} 08/31/2021 06:28:07 - INFO - __main__ - Step 95178: {'lr': 0.00015101994424860564, 'samples': 18274176, 'steps': 95177, 'loss/train': 1.0761774778366089} 08/31/2021 06:28:08 - INFO - __main__ - Step 95179: {'lr': 0.00015101507116764695, 'samples': 18274368, 'steps': 95178, 'loss/train': 1.305659532546997} 08/31/2021 06:28:08 - INFO - __main__ - Step 95180: {'lr': 0.00015101019813128948, 'samples': 18274560, 'steps': 95179, 'loss/train': 1.3751384019851685} 08/31/2021 06:28:08 - INFO - __main__ - Step 95181: {'lr': 0.00015100532513953518, 'samples': 18274752, 'steps': 95180, 'loss/train': 1.3995305299758911} 08/31/2021 06:28:09 - INFO - __main__ - Step 95182: {'lr': 0.00015100045219238636, 'samples': 18274944, 'steps': 95181, 'loss/train': 0.30079084634780884} 08/31/2021 06:28:10 - INFO - __main__ - Step 95183: {'lr': 0.0001509955792898452, 'samples': 18275136, 'steps': 95182, 'loss/train': 1.413853406906128} 08/31/2021 06:28:10 - INFO - __main__ - Step 95184: {'lr': 0.00015099070643191393, 'samples': 18275328, 'steps': 95183, 'loss/train': 1.3056795597076416} 08/31/2021 06:28:11 - INFO - __main__ - Step 95185: {'lr': 0.0001509858336185947, 'samples': 18275520, 'steps': 95184, 'loss/train': 0.9282928109169006} 08/31/2021 06:28:11 - INFO - __main__ - Step 95186: {'lr': 0.0001509809608498897, 'samples': 18275712, 'steps': 95185, 'loss/train': 1.4059346914291382} 08/31/2021 06:28:12 - INFO - __main__ - Step 95187: {'lr': 0.00015097608812580116, 'samples': 18275904, 'steps': 95186, 'loss/train': 1.4894839525222778} 08/31/2021 06:28:13 - INFO - __main__ - Step 95188: {'lr': 0.0001509712154463313, 'samples': 18276096, 'steps': 95187, 'loss/train': 0.36982089281082153} 08/31/2021 06:28:14 - INFO - __main__ - Step 95189: {'lr': 0.00015096634281148224, 'samples': 18276288, 'steps': 95188, 'loss/train': 0.5573070645332336} 08/31/2021 06:28:14 - INFO - __main__ - Step 95190: {'lr': 0.0001509614702212562, 'samples': 18276480, 'steps': 95189, 'loss/train': 0.9971718788146973} 08/31/2021 06:28:14 - INFO - __main__ - Step 95191: {'lr': 0.00015095659767565546, 'samples': 18276672, 'steps': 95190, 'loss/train': 1.082746148109436} 08/31/2021 06:28:15 - INFO - __main__ - Step 95192: {'lr': 0.00015095172517468213, 'samples': 18276864, 'steps': 95191, 'loss/train': 0.6444589495658875} 08/31/2021 06:28:16 - INFO - __main__ - Step 95193: {'lr': 0.0001509468527183384, 'samples': 18277056, 'steps': 95192, 'loss/train': 0.9309276938438416} 08/31/2021 06:28:17 - INFO - __main__ - Step 95194: {'lr': 0.00015094198030662662, 'samples': 18277248, 'steps': 95193, 'loss/train': 1.6434876918792725} 08/31/2021 06:28:17 - INFO - __main__ - Step 95195: {'lr': 0.00015093710793954873, 'samples': 18277440, 'steps': 95194, 'loss/train': 1.3362338542938232} 08/31/2021 06:28:17 - INFO - __main__ - Step 95196: {'lr': 0.00015093223561710707, 'samples': 18277632, 'steps': 95195, 'loss/train': 1.2084274291992188} 08/31/2021 06:28:18 - INFO - __main__ - Step 95197: {'lr': 0.0001509273633393038, 'samples': 18277824, 'steps': 95196, 'loss/train': 1.113473892211914} 08/31/2021 06:28:18 - INFO - __main__ - Step 95198: {'lr': 0.00015092249110614114, 'samples': 18278016, 'steps': 95197, 'loss/train': 0.3427813649177551} 08/31/2021 06:28:19 - INFO - __main__ - Step 95199: {'lr': 0.0001509176189176213, 'samples': 18278208, 'steps': 95198, 'loss/train': 0.8062198162078857} 08/31/2021 06:28:20 - INFO - __main__ - Step 95200: {'lr': 0.0001509127467737464, 'samples': 18278400, 'steps': 95199, 'loss/train': 1.2028108835220337} 08/31/2021 06:28:20 - INFO - __main__ - Step 95201: {'lr': 0.00015090787467451872, 'samples': 18278592, 'steps': 95200, 'loss/train': 1.0642518997192383} 08/31/2021 06:28:21 - INFO - __main__ - Step 95202: {'lr': 0.00015090300261994043, 'samples': 18278784, 'steps': 95201, 'loss/train': 1.3107112646102905} 08/31/2021 06:28:21 - INFO - __main__ - Step 95203: {'lr': 0.00015089813061001367, 'samples': 18278976, 'steps': 95202, 'loss/train': 1.1312488317489624} 08/31/2021 06:28:22 - INFO - __main__ - Step 95204: {'lr': 0.00015089325864474075, 'samples': 18279168, 'steps': 95203, 'loss/train': 1.0805820226669312} 08/31/2021 06:28:23 - INFO - __main__ - Step 95205: {'lr': 0.00015088838672412376, 'samples': 18279360, 'steps': 95204, 'loss/train': 0.8816820979118347} 08/31/2021 06:28:23 - INFO - __main__ - Step 95206: {'lr': 0.00015088351484816493, 'samples': 18279552, 'steps': 95205, 'loss/train': 1.2989412546157837} 08/31/2021 06:28:23 - INFO - __main__ - Step 95207: {'lr': 0.00015087864301686657, 'samples': 18279744, 'steps': 95206, 'loss/train': 1.3835196495056152} 08/31/2021 06:28:24 - INFO - __main__ - Step 95208: {'lr': 0.00015087377123023066, 'samples': 18279936, 'steps': 95207, 'loss/train': 1.335362195968628} 08/31/2021 06:28:25 - INFO - __main__ - Step 95209: {'lr': 0.0001508688994882595, 'samples': 18280128, 'steps': 95208, 'loss/train': 1.2493540048599243} 08/31/2021 06:28:26 - INFO - __main__ - Step 95210: {'lr': 0.00015086402779095528, 'samples': 18280320, 'steps': 95209, 'loss/train': 1.3644636869430542} 08/31/2021 06:28:26 - INFO - __main__ - Step 95211: {'lr': 0.00015085915613832022, 'samples': 18280512, 'steps': 95210, 'loss/train': 0.8971989750862122} 08/31/2021 06:28:26 - INFO - __main__ - Step 95212: {'lr': 0.00015085428453035646, 'samples': 18280704, 'steps': 95211, 'loss/train': 1.1516544818878174} 08/31/2021 06:28:27 - INFO - __main__ - Step 95213: {'lr': 0.00015084941296706624, 'samples': 18280896, 'steps': 95212, 'loss/train': 0.7213677167892456} 08/31/2021 06:28:28 - INFO - __main__ - Step 95214: {'lr': 0.00015084454144845177, 'samples': 18281088, 'steps': 95213, 'loss/train': 0.5698078274726868} 08/31/2021 06:28:29 - INFO - __main__ - Step 95215: {'lr': 0.0001508396699745152, 'samples': 18281280, 'steps': 95214, 'loss/train': 0.9879644513130188} 08/31/2021 06:28:29 - INFO - __main__ - Step 95216: {'lr': 0.00015083479854525875, 'samples': 18281472, 'steps': 95215, 'loss/train': 1.2410717010498047} 08/31/2021 06:28:30 - INFO - __main__ - Step 95217: {'lr': 0.0001508299271606846, 'samples': 18281664, 'steps': 95216, 'loss/train': 1.3132661581039429} 08/31/2021 06:28:30 - INFO - __main__ - Step 95218: {'lr': 0.00015082505582079497, 'samples': 18281856, 'steps': 95217, 'loss/train': 1.2803304195404053} 08/31/2021 06:28:32 - INFO - __main__ - Step 95219: {'lr': 0.00015082018452559207, 'samples': 18282048, 'steps': 95218, 'loss/train': 1.210827112197876} 08/31/2021 06:28:33 - INFO - __main__ - Step 95220: {'lr': 0.00015081531327507802, 'samples': 18282240, 'steps': 95219, 'loss/train': 0.03548803552985191} 08/31/2021 06:28:33 - INFO - __main__ - Step 95221: {'lr': 0.00015081044206925512, 'samples': 18282432, 'steps': 95220, 'loss/train': 1.319951057434082} 08/31/2021 06:28:34 - INFO - __main__ - Step 95222: {'lr': 0.00015080557090812547, 'samples': 18282624, 'steps': 95221, 'loss/train': 0.9630402326583862} 08/31/2021 06:28:34 - INFO - __main__ - Step 95223: {'lr': 0.00015080069979169126, 'samples': 18282816, 'steps': 95222, 'loss/train': 1.2093037366867065} 08/31/2021 06:28:36 - INFO - __main__ - Step 95224: {'lr': 0.00015079582871995473, 'samples': 18283008, 'steps': 95223, 'loss/train': 1.4827340841293335} 08/31/2021 06:28:36 - INFO - __main__ - Step 95225: {'lr': 0.0001507909576929181, 'samples': 18283200, 'steps': 95224, 'loss/train': 0.9867389798164368} 08/31/2021 06:28:36 - INFO - __main__ - Step 95226: {'lr': 0.00015078608671058349, 'samples': 18283392, 'steps': 95225, 'loss/train': 0.9244527816772461} 08/31/2021 06:28:37 - INFO - __main__ - Step 95227: {'lr': 0.00015078121577295317, 'samples': 18283584, 'steps': 95226, 'loss/train': 1.134292483329773} 08/31/2021 06:28:37 - INFO - __main__ - Step 95228: {'lr': 0.00015077634488002927, 'samples': 18283776, 'steps': 95227, 'loss/train': 1.458004117012024} 08/31/2021 06:28:39 - INFO - __main__ - Step 95229: {'lr': 0.00015077147403181408, 'samples': 18283968, 'steps': 95228, 'loss/train': 0.2465471476316452} 08/31/2021 06:28:39 - INFO - __main__ - Step 95230: {'lr': 0.00015076660322830974, 'samples': 18284160, 'steps': 95229, 'loss/train': 1.0284476280212402} 08/31/2021 06:28:39 - INFO - __main__ - Step 95231: {'lr': 0.00015076173246951838, 'samples': 18284352, 'steps': 95230, 'loss/train': 2.103930950164795} 08/31/2021 06:28:40 - INFO - __main__ - Step 95232: {'lr': 0.00015075686175544228, 'samples': 18284544, 'steps': 95231, 'loss/train': 0.9730995297431946} 08/31/2021 06:28:40 - INFO - __main__ - Step 95233: {'lr': 0.00015075199108608356, 'samples': 18284736, 'steps': 95232, 'loss/train': 1.1058727502822876} 08/31/2021 06:28:42 - INFO - __main__ - Step 95234: {'lr': 0.00015074712046144457, 'samples': 18284928, 'steps': 95233, 'loss/train': 0.9718363285064697} 08/31/2021 06:28:42 - INFO - __main__ - Step 95235: {'lr': 0.0001507422498815273, 'samples': 18285120, 'steps': 95234, 'loss/train': 0.5569808483123779} 08/31/2021 06:28:43 - INFO - __main__ - Step 95236: {'lr': 0.0001507373793463341, 'samples': 18285312, 'steps': 95235, 'loss/train': 0.6772685050964355} 08/31/2021 06:28:43 - INFO - __main__ - Step 95237: {'lr': 0.00015073250885586702, 'samples': 18285504, 'steps': 95236, 'loss/train': 1.0335015058517456} 08/31/2021 06:28:43 - INFO - __main__ - Step 95238: {'lr': 0.00015072763841012841, 'samples': 18285696, 'steps': 95237, 'loss/train': 0.9447404742240906} 08/31/2021 06:28:44 - INFO - __main__ - Step 95239: {'lr': 0.00015072276800912035, 'samples': 18285888, 'steps': 95238, 'loss/train': 1.327397108078003} 08/31/2021 06:28:45 - INFO - __main__ - Step 95240: {'lr': 0.0001507178976528451, 'samples': 18286080, 'steps': 95239, 'loss/train': 0.6578044295310974} 08/31/2021 06:28:46 - INFO - __main__ - Step 95241: {'lr': 0.00015071302734130488, 'samples': 18286272, 'steps': 95240, 'loss/train': 0.8573218584060669} 08/31/2021 06:28:46 - INFO - __main__ - Step 95242: {'lr': 0.0001507081570745018, 'samples': 18286464, 'steps': 95241, 'loss/train': 1.8223892450332642} 08/31/2021 06:28:46 - INFO - __main__ - Step 95243: {'lr': 0.00015070328685243807, 'samples': 18286656, 'steps': 95242, 'loss/train': 1.3529860973358154} 08/31/2021 06:28:47 - INFO - __main__ - Step 95244: {'lr': 0.0001506984166751159, 'samples': 18286848, 'steps': 95243, 'loss/train': 1.5127708911895752} 08/31/2021 06:28:48 - INFO - __main__ - Step 95245: {'lr': 0.00015069354654253752, 'samples': 18287040, 'steps': 95244, 'loss/train': 1.094072699546814} 08/31/2021 06:28:49 - INFO - __main__ - Step 95246: {'lr': 0.00015068867645470508, 'samples': 18287232, 'steps': 95245, 'loss/train': 1.334610104560852} 08/31/2021 06:28:49 - INFO - __main__ - Step 95247: {'lr': 0.00015068380641162084, 'samples': 18287424, 'steps': 95246, 'loss/train': 1.163761854171753} 08/31/2021 06:28:49 - INFO - __main__ - Step 95248: {'lr': 0.00015067893641328693, 'samples': 18287616, 'steps': 95247, 'loss/train': 1.0834614038467407} 08/31/2021 06:28:50 - INFO - __main__ - Step 95249: {'lr': 0.0001506740664597055, 'samples': 18287808, 'steps': 95248, 'loss/train': 0.9550975561141968} 08/31/2021 06:28:51 - INFO - __main__ - Step 95250: {'lr': 0.00015066919655087885, 'samples': 18288000, 'steps': 95249, 'loss/train': 1.9410144090652466} 08/31/2021 06:28:52 - INFO - __main__ - Step 95251: {'lr': 0.00015066432668680915, 'samples': 18288192, 'steps': 95250, 'loss/train': 0.23161399364471436} 08/31/2021 06:28:52 - INFO - __main__ - Step 95252: {'lr': 0.00015065945686749854, 'samples': 18288384, 'steps': 95251, 'loss/train': 1.5704319477081299} 08/31/2021 06:28:53 - INFO - __main__ - Step 95253: {'lr': 0.00015065458709294922, 'samples': 18288576, 'steps': 95252, 'loss/train': 1.3678466081619263} 08/31/2021 06:28:53 - INFO - __main__ - Step 95254: {'lr': 0.0001506497173631634, 'samples': 18288768, 'steps': 95253, 'loss/train': 0.6739415526390076} 08/31/2021 06:28:54 - INFO - __main__ - Step 95255: {'lr': 0.00015064484767814335, 'samples': 18288960, 'steps': 95254, 'loss/train': 0.609207808971405} 08/31/2021 06:28:55 - INFO - __main__ - Step 95256: {'lr': 0.00015063997803789115, 'samples': 18289152, 'steps': 95255, 'loss/train': 1.3436336517333984} 08/31/2021 06:28:55 - INFO - __main__ - Step 95257: {'lr': 0.00015063510844240903, 'samples': 18289344, 'steps': 95256, 'loss/train': 1.2677232027053833} 08/31/2021 06:28:56 - INFO - __main__ - Step 95258: {'lr': 0.00015063023889169924, 'samples': 18289536, 'steps': 95257, 'loss/train': 1.481637716293335} 08/31/2021 06:28:56 - INFO - __main__ - Step 95259: {'lr': 0.00015062536938576388, 'samples': 18289728, 'steps': 95258, 'loss/train': 0.6868726015090942} 08/31/2021 06:28:58 - INFO - __main__ - Step 95260: {'lr': 0.00015062049992460526, 'samples': 18289920, 'steps': 95259, 'loss/train': 1.2682554721832275} 08/31/2021 06:28:58 - INFO - __main__ - Step 95261: {'lr': 0.0001506156305082255, 'samples': 18290112, 'steps': 95260, 'loss/train': 0.7588173151016235} 08/31/2021 06:28:59 - INFO - __main__ - Step 95262: {'lr': 0.00015061076113662684, 'samples': 18290304, 'steps': 95261, 'loss/train': 1.1641992330551147} 08/31/2021 06:28:59 - INFO - __main__ - Step 95263: {'lr': 0.00015060589180981138, 'samples': 18290496, 'steps': 95262, 'loss/train': 1.3495029211044312} 08/31/2021 06:28:59 - INFO - __main__ - Step 95264: {'lr': 0.00015060102252778136, 'samples': 18290688, 'steps': 95263, 'loss/train': 0.25654518604278564} 08/31/2021 06:29:00 - INFO - __main__ - Step 95265: {'lr': 0.000150596153290539, 'samples': 18290880, 'steps': 95264, 'loss/train': 0.037072956562042236} 08/31/2021 06:29:01 - INFO - __main__ - Step 95266: {'lr': 0.00015059128409808641, 'samples': 18291072, 'steps': 95265, 'loss/train': 1.4748992919921875} 08/31/2021 06:29:02 - INFO - __main__ - Step 95267: {'lr': 0.00015058641495042596, 'samples': 18291264, 'steps': 95266, 'loss/train': 1.0511301755905151} 08/31/2021 06:29:02 - INFO - __main__ - Step 95268: {'lr': 0.00015058154584755967, 'samples': 18291456, 'steps': 95267, 'loss/train': 0.6688958406448364} 08/31/2021 06:29:02 - INFO - __main__ - Step 95269: {'lr': 0.00015057667678948982, 'samples': 18291648, 'steps': 95268, 'loss/train': 1.3300621509552002} 08/31/2021 06:29:03 - INFO - __main__ - Step 95270: {'lr': 0.0001505718077762186, 'samples': 18291840, 'steps': 95269, 'loss/train': 0.7480103373527527} 08/31/2021 06:29:05 - INFO - __main__ - Step 95271: {'lr': 0.00015056693880774816, 'samples': 18292032, 'steps': 95270, 'loss/train': 1.0103152990341187} 08/31/2021 06:29:06 - INFO - __main__ - Step 95272: {'lr': 0.00015056206988408075, 'samples': 18292224, 'steps': 95271, 'loss/train': 1.630338430404663} 08/31/2021 06:29:06 - INFO - __main__ - Step 95273: {'lr': 0.00015055720100521852, 'samples': 18292416, 'steps': 95272, 'loss/train': 1.245577335357666} 08/31/2021 06:29:06 - INFO - __main__ - Step 95274: {'lr': 0.00015055233217116368, 'samples': 18292608, 'steps': 95273, 'loss/train': 0.13817408680915833} 08/31/2021 06:29:07 - INFO - __main__ - Step 95275: {'lr': 0.00015054746338191854, 'samples': 18292800, 'steps': 95274, 'loss/train': 1.2892194986343384} 08/31/2021 06:29:08 - INFO - __main__ - Step 95276: {'lr': 0.00015054259463748507, 'samples': 18292992, 'steps': 95275, 'loss/train': 0.16286998987197876} 08/31/2021 06:29:09 - INFO - __main__ - Step 95277: {'lr': 0.00015053772593786558, 'samples': 18293184, 'steps': 95276, 'loss/train': 0.8186547756195068} 08/31/2021 06:29:09 - INFO - __main__ - Step 95278: {'lr': 0.00015053285728306224, 'samples': 18293376, 'steps': 95277, 'loss/train': 0.7429742813110352} 08/31/2021 06:29:09 - INFO - __main__ - Step 95279: {'lr': 0.00015052798867307726, 'samples': 18293568, 'steps': 95278, 'loss/train': 0.9464095234870911} 08/31/2021 06:29:10 - INFO - __main__ - Step 95280: {'lr': 0.00015052312010791285, 'samples': 18293760, 'steps': 95279, 'loss/train': 1.5169063806533813} 08/31/2021 06:29:11 - INFO - __main__ - Step 95281: {'lr': 0.00015051825158757115, 'samples': 18293952, 'steps': 95280, 'loss/train': 1.2708666324615479} 08/31/2021 06:29:12 - INFO - __main__ - Step 95282: {'lr': 0.00015051338311205444, 'samples': 18294144, 'steps': 95281, 'loss/train': 1.244374394416809} 08/31/2021 06:29:12 - INFO - __main__ - Step 95283: {'lr': 0.00015050851468136485, 'samples': 18294336, 'steps': 95282, 'loss/train': 1.6143101453781128} 08/31/2021 06:29:12 - INFO - __main__ - Step 95284: {'lr': 0.00015050364629550455, 'samples': 18294528, 'steps': 95283, 'loss/train': 1.2124871015548706} 08/31/2021 06:29:13 - INFO - __main__ - Step 95285: {'lr': 0.00015049877795447582, 'samples': 18294720, 'steps': 95284, 'loss/train': 1.850335955619812} 08/31/2021 06:29:13 - INFO - __main__ - Step 95286: {'lr': 0.0001504939096582808, 'samples': 18294912, 'steps': 95285, 'loss/train': 1.5295430421829224} 08/31/2021 06:29:15 - INFO - __main__ - Step 95287: {'lr': 0.00015048904140692166, 'samples': 18295104, 'steps': 95286, 'loss/train': 1.5818105936050415} 08/31/2021 06:29:16 - INFO - __main__ - Step 95288: {'lr': 0.00015048417320040076, 'samples': 18295296, 'steps': 95287, 'loss/train': 1.5699422359466553} 08/31/2021 06:29:16 - INFO - __main__ - Step 95289: {'lr': 0.00015047930503872003, 'samples': 18295488, 'steps': 95288, 'loss/train': 1.0443674325942993} 08/31/2021 06:29:16 - INFO - __main__ - Step 95290: {'lr': 0.00015047443692188178, 'samples': 18295680, 'steps': 95289, 'loss/train': 0.05528728663921356} 08/31/2021 06:29:17 - INFO - __main__ - Step 95291: {'lr': 0.00015046956884988823, 'samples': 18295872, 'steps': 95290, 'loss/train': 1.517308235168457} 08/31/2021 06:29:18 - INFO - __main__ - Step 95292: {'lr': 0.00015046470082274156, 'samples': 18296064, 'steps': 95291, 'loss/train': 1.2705512046813965} 08/31/2021 06:29:19 - INFO - __main__ - Step 95293: {'lr': 0.00015045983284044397, 'samples': 18296256, 'steps': 95292, 'loss/train': 1.2745693922042847} 08/31/2021 06:29:19 - INFO - __main__ - Step 95294: {'lr': 0.0001504549649029976, 'samples': 18296448, 'steps': 95293, 'loss/train': 1.2570345401763916} 08/31/2021 06:29:19 - INFO - __main__ - Step 95295: {'lr': 0.00015045009701040473, 'samples': 18296640, 'steps': 95294, 'loss/train': 0.053363051265478134} 08/31/2021 06:29:20 - INFO - __main__ - Step 95296: {'lr': 0.00015044522916266747, 'samples': 18296832, 'steps': 95295, 'loss/train': 1.3123499155044556} 08/31/2021 06:29:21 - INFO - __main__ - Step 95297: {'lr': 0.0001504403613597881, 'samples': 18297024, 'steps': 95296, 'loss/train': 0.17997774481773376} 08/31/2021 06:29:22 - INFO - __main__ - Step 95298: {'lr': 0.00015043549360176873, 'samples': 18297216, 'steps': 95297, 'loss/train': 0.11566224694252014} 08/31/2021 06:29:22 - INFO - __main__ - Step 95299: {'lr': 0.00015043062588861162, 'samples': 18297408, 'steps': 95298, 'loss/train': 0.642688512802124} 08/31/2021 06:29:22 - INFO - __main__ - Step 95300: {'lr': 0.0001504257582203189, 'samples': 18297600, 'steps': 95299, 'loss/train': 1.0958101749420166} 08/31/2021 06:29:23 - INFO - __main__ - Step 95301: {'lr': 0.0001504208905968929, 'samples': 18297792, 'steps': 95300, 'loss/train': 1.3547053337097168} 08/31/2021 06:29:24 - INFO - __main__ - Step 95302: {'lr': 0.00015041602301833561, 'samples': 18297984, 'steps': 95301, 'loss/train': 1.2762635946273804} 08/31/2021 06:29:25 - INFO - __main__ - Step 95303: {'lr': 0.00015041115548464936, 'samples': 18298176, 'steps': 95302, 'loss/train': 0.7485890984535217} 08/31/2021 06:29:25 - INFO - __main__ - Step 95304: {'lr': 0.00015040628799583628, 'samples': 18298368, 'steps': 95303, 'loss/train': 1.042152762413025} 08/31/2021 06:29:25 - INFO - __main__ - Step 95305: {'lr': 0.0001504014205518986, 'samples': 18298560, 'steps': 95304, 'loss/train': 1.1457879543304443} 08/31/2021 06:29:26 - INFO - __main__ - Step 95306: {'lr': 0.00015039655315283852, 'samples': 18298752, 'steps': 95305, 'loss/train': 0.9041433334350586} 08/31/2021 06:29:26 - INFO - __main__ - Step 95307: {'lr': 0.00015039168579865817, 'samples': 18298944, 'steps': 95306, 'loss/train': 1.0004431009292603} 08/31/2021 06:29:28 - INFO - __main__ - Step 95308: {'lr': 0.0001503868184893598, 'samples': 18299136, 'steps': 95307, 'loss/train': 0.7242890000343323} 08/31/2021 06:29:28 - INFO - __main__ - Step 95309: {'lr': 0.00015038195122494562, 'samples': 18299328, 'steps': 95308, 'loss/train': 1.374976634979248} 08/31/2021 06:29:28 - INFO - __main__ - Step 95310: {'lr': 0.00015037708400541776, 'samples': 18299520, 'steps': 95309, 'loss/train': 1.8298709392547607} 08/31/2021 06:29:29 - INFO - __main__ - Step 95311: {'lr': 0.0001503722168307785, 'samples': 18299712, 'steps': 95310, 'loss/train': 0.02771802619099617} 08/31/2021 06:29:29 - INFO - __main__ - Step 95312: {'lr': 0.00015036734970102995, 'samples': 18299904, 'steps': 95311, 'loss/train': 1.06707763671875} 08/31/2021 06:29:31 - INFO - __main__ - Step 95313: {'lr': 0.00015036248261617434, 'samples': 18300096, 'steps': 95312, 'loss/train': 1.1969704627990723} 08/31/2021 06:29:31 - INFO - __main__ - Step 95314: {'lr': 0.00015035761557621386, 'samples': 18300288, 'steps': 95313, 'loss/train': 1.459311842918396} 08/31/2021 06:29:31 - INFO - __main__ - Step 95315: {'lr': 0.0001503527485811508, 'samples': 18300480, 'steps': 95314, 'loss/train': 1.2732391357421875} 08/31/2021 06:29:32 - INFO - __main__ - Step 95316: {'lr': 0.0001503478816309871, 'samples': 18300672, 'steps': 95315, 'loss/train': 1.3944522142410278} 08/31/2021 06:29:32 - INFO - __main__ - Step 95317: {'lr': 0.00015034301472572516, 'samples': 18300864, 'steps': 95316, 'loss/train': 1.5580644607543945} 08/31/2021 06:29:34 - INFO - __main__ - Step 95318: {'lr': 0.00015033814786536714, 'samples': 18301056, 'steps': 95317, 'loss/train': 1.7695600986480713} 08/31/2021 06:29:34 - INFO - __main__ - Step 95319: {'lr': 0.00015033328104991516, 'samples': 18301248, 'steps': 95318, 'loss/train': 1.2019321918487549} 08/31/2021 06:29:34 - INFO - __main__ - Step 95320: {'lr': 0.0001503284142793715, 'samples': 18301440, 'steps': 95319, 'loss/train': 0.7340556979179382} 08/31/2021 06:29:35 - INFO - __main__ - Step 95321: {'lr': 0.00015032354755373833, 'samples': 18301632, 'steps': 95320, 'loss/train': 0.14612922072410583} 08/31/2021 06:29:35 - INFO - __main__ - Step 95322: {'lr': 0.0001503186808730178, 'samples': 18301824, 'steps': 95321, 'loss/train': 1.3123486042022705} 08/31/2021 06:29:37 - INFO - __main__ - Step 95323: {'lr': 0.00015031381423721217, 'samples': 18302016, 'steps': 95322, 'loss/train': 1.2907989025115967} 08/31/2021 06:29:37 - INFO - __main__ - Step 95324: {'lr': 0.00015030894764632357, 'samples': 18302208, 'steps': 95323, 'loss/train': 1.4013984203338623} 08/31/2021 06:29:37 - INFO - __main__ - Step 95325: {'lr': 0.00015030408110035422, 'samples': 18302400, 'steps': 95324, 'loss/train': 0.49894431233406067} 08/31/2021 06:29:38 - INFO - __main__ - Step 95326: {'lr': 0.00015029921459930632, 'samples': 18302592, 'steps': 95325, 'loss/train': 1.1557371616363525} 08/31/2021 06:29:38 - INFO - __main__ - Step 95327: {'lr': 0.00015029434814318204, 'samples': 18302784, 'steps': 95326, 'loss/train': 1.163883924484253} 08/31/2021 06:29:40 - INFO - __main__ - Step 95328: {'lr': 0.00015028948173198371, 'samples': 18302976, 'steps': 95327, 'loss/train': 1.14159095287323} 08/31/2021 06:29:41 - INFO - __main__ - Step 95329: {'lr': 0.0001502846153657133, 'samples': 18303168, 'steps': 95328, 'loss/train': 0.9003618359565735} 08/31/2021 06:29:41 - INFO - __main__ - Step 95330: {'lr': 0.0001502797490443731, 'samples': 18303360, 'steps': 95329, 'loss/train': 1.14313542842865} 08/31/2021 06:29:42 - INFO - __main__ - Step 95331: {'lr': 0.00015027488276796527, 'samples': 18303552, 'steps': 95330, 'loss/train': 1.1732159852981567} 08/31/2021 06:29:42 - INFO - __main__ - Step 95332: {'lr': 0.00015027001653649207, 'samples': 18303744, 'steps': 95331, 'loss/train': 1.5680537223815918} 08/31/2021 06:29:44 - INFO - __main__ - Step 95333: {'lr': 0.0001502651503499557, 'samples': 18303936, 'steps': 95332, 'loss/train': 0.8547631502151489} 08/31/2021 06:29:44 - INFO - __main__ - Step 95334: {'lr': 0.00015026028420835825, 'samples': 18304128, 'steps': 95333, 'loss/train': 0.8535672426223755} 08/31/2021 06:29:45 - INFO - __main__ - Step 95335: {'lr': 0.00015025541811170202, 'samples': 18304320, 'steps': 95334, 'loss/train': 0.13899481296539307} 08/31/2021 06:29:45 - INFO - __main__ - Step 95336: {'lr': 0.0001502505520599891, 'samples': 18304512, 'steps': 95335, 'loss/train': 1.0321681499481201} 08/31/2021 06:29:45 - INFO - __main__ - Step 95337: {'lr': 0.0001502456860532218, 'samples': 18304704, 'steps': 95336, 'loss/train': 1.1880260705947876} 08/31/2021 06:29:46 - INFO - __main__ - Step 95338: {'lr': 0.00015024082009140226, 'samples': 18304896, 'steps': 95337, 'loss/train': 1.3602513074874878} 08/31/2021 06:29:47 - INFO - __main__ - Step 95339: {'lr': 0.00015023595417453263, 'samples': 18305088, 'steps': 95338, 'loss/train': 2.111999034881592} 08/31/2021 06:29:48 - INFO - __main__ - Step 95340: {'lr': 0.00015023108830261516, 'samples': 18305280, 'steps': 95339, 'loss/train': 1.9402457475662231} 08/31/2021 06:29:48 - INFO - __main__ - Step 95341: {'lr': 0.00015022622247565202, 'samples': 18305472, 'steps': 95340, 'loss/train': 1.351367712020874} 08/31/2021 06:29:48 - INFO - __main__ - Step 95342: {'lr': 0.0001502213566936455, 'samples': 18305664, 'steps': 95341, 'loss/train': 0.46557918190956116} 08/31/2021 06:29:49 - INFO - __main__ - Step 95343: {'lr': 0.00015021649095659761, 'samples': 18305856, 'steps': 95342, 'loss/train': 0.9030143618583679} 08/31/2021 06:29:50 - INFO - __main__ - Step 95344: {'lr': 0.0001502116252645106, 'samples': 18306048, 'steps': 95343, 'loss/train': 1.4697864055633545} 08/31/2021 06:29:50 - INFO - __main__ - Step 95345: {'lr': 0.0001502067596173867, 'samples': 18306240, 'steps': 95344, 'loss/train': 1.472805142402649} 08/31/2021 06:29:51 - INFO - __main__ - Step 95346: {'lr': 0.00015020189401522812, 'samples': 18306432, 'steps': 95345, 'loss/train': 1.2056968212127686} 08/31/2021 06:29:51 - INFO - __main__ - Step 95347: {'lr': 0.000150197028458037, 'samples': 18306624, 'steps': 95346, 'loss/train': 1.7332158088684082} 08/31/2021 06:29:52 - INFO - __main__ - Step 95348: {'lr': 0.0001501921629458156, 'samples': 18306816, 'steps': 95347, 'loss/train': 0.9178408980369568} 08/31/2021 06:29:53 - INFO - __main__ - Step 95349: {'lr': 0.000150187297478566, 'samples': 18307008, 'steps': 95348, 'loss/train': 1.282181739807129} 08/31/2021 06:29:53 - INFO - __main__ - Step 95350: {'lr': 0.00015018243205629054, 'samples': 18307200, 'steps': 95349, 'loss/train': 1.4809460639953613} 08/31/2021 06:29:54 - INFO - __main__ - Step 95351: {'lr': 0.00015017756667899128, 'samples': 18307392, 'steps': 95350, 'loss/train': 0.3536505103111267} 08/31/2021 06:29:54 - INFO - __main__ - Step 95352: {'lr': 0.0001501727013466705, 'samples': 18307584, 'steps': 95351, 'loss/train': 0.21218495070934296} 08/31/2021 06:29:54 - INFO - __main__ - Step 95353: {'lr': 0.0001501678360593304, 'samples': 18307776, 'steps': 95352, 'loss/train': 1.0501821041107178} 08/31/2021 06:29:56 - INFO - __main__ - Step 95354: {'lr': 0.00015016297081697308, 'samples': 18307968, 'steps': 95353, 'loss/train': 0.9714865684509277} 08/31/2021 06:29:56 - INFO - __main__ - Step 95355: {'lr': 0.00015015810561960086, 'samples': 18308160, 'steps': 95354, 'loss/train': 1.0348050594329834} 08/31/2021 06:29:57 - INFO - __main__ - Step 95356: {'lr': 0.00015015324046721576, 'samples': 18308352, 'steps': 95355, 'loss/train': 1.4511959552764893} 08/31/2021 06:29:57 - INFO - __main__ - Step 95357: {'lr': 0.0001501483753598201, 'samples': 18308544, 'steps': 95356, 'loss/train': 1.180548906326294} 08/31/2021 06:29:58 - INFO - __main__ - Step 95358: {'lr': 0.00015014351029741602, 'samples': 18308736, 'steps': 95357, 'loss/train': 1.1228302717208862} 08/31/2021 06:29:59 - INFO - __main__ - Step 95359: {'lr': 0.00015013864528000577, 'samples': 18308928, 'steps': 95358, 'loss/train': 1.049786925315857} 08/31/2021 06:29:59 - INFO - __main__ - Step 95360: {'lr': 0.00015013378030759146, 'samples': 18309120, 'steps': 95359, 'loss/train': 1.5186707973480225} 08/31/2021 06:30:00 - INFO - __main__ - Step 95361: {'lr': 0.00015012891538017536, 'samples': 18309312, 'steps': 95360, 'loss/train': 0.3747347295284271} 08/31/2021 06:30:00 - INFO - __main__ - Step 95362: {'lr': 0.00015012405049775963, 'samples': 18309504, 'steps': 95361, 'loss/train': 0.08550223708152771} 08/31/2021 06:30:00 - INFO - __main__ - Step 95363: {'lr': 0.00015011918566034643, 'samples': 18309696, 'steps': 95362, 'loss/train': 0.889359176158905} 08/31/2021 06:30:01 - INFO - __main__ - Step 95364: {'lr': 0.0001501143208679381, 'samples': 18309888, 'steps': 95363, 'loss/train': 1.0355284214019775} 08/31/2021 06:30:02 - INFO - __main__ - Step 95365: {'lr': 0.00015010945612053657, 'samples': 18310080, 'steps': 95364, 'loss/train': 1.427273154258728} 08/31/2021 06:30:03 - INFO - __main__ - Step 95366: {'lr': 0.00015010459141814425, 'samples': 18310272, 'steps': 95365, 'loss/train': 1.3993072509765625} 08/31/2021 06:30:03 - INFO - __main__ - Step 95367: {'lr': 0.00015009972676076322, 'samples': 18310464, 'steps': 95366, 'loss/train': 1.230095386505127} 08/31/2021 06:30:03 - INFO - __main__ - Step 95368: {'lr': 0.00015009486214839573, 'samples': 18310656, 'steps': 95367, 'loss/train': 1.052979826927185} 08/31/2021 06:30:04 - INFO - __main__ - Step 95369: {'lr': 0.00015008999758104404, 'samples': 18310848, 'steps': 95368, 'loss/train': 0.840857207775116} 08/31/2021 06:30:05 - INFO - __main__ - Step 95370: {'lr': 0.00015008513305871012, 'samples': 18311040, 'steps': 95369, 'loss/train': 0.7151879072189331} 08/31/2021 06:30:06 - INFO - __main__ - Step 95371: {'lr': 0.00015008026858139638, 'samples': 18311232, 'steps': 95370, 'loss/train': 1.1634154319763184} 08/31/2021 06:30:06 - INFO - __main__ - Step 95372: {'lr': 0.0001500754041491049, 'samples': 18311424, 'steps': 95371, 'loss/train': 0.8829538822174072} 08/31/2021 06:30:06 - INFO - __main__ - Step 95373: {'lr': 0.00015007053976183788, 'samples': 18311616, 'steps': 95372, 'loss/train': 1.3149564266204834} 08/31/2021 06:30:07 - INFO - __main__ - Step 95374: {'lr': 0.00015006567541959754, 'samples': 18311808, 'steps': 95373, 'loss/train': 1.0163418054580688} 08/31/2021 06:30:08 - INFO - __main__ - Step 95375: {'lr': 0.00015006081112238612, 'samples': 18312000, 'steps': 95374, 'loss/train': 0.9424931406974792} 08/31/2021 06:30:09 - INFO - __main__ - Step 95376: {'lr': 0.00015005594687020574, 'samples': 18312192, 'steps': 95375, 'loss/train': 1.1472917795181274} 08/31/2021 06:30:09 - INFO - __main__ - Step 95377: {'lr': 0.00015005108266305856, 'samples': 18312384, 'steps': 95376, 'loss/train': 0.9978615045547485} 08/31/2021 06:30:09 - INFO - __main__ - Step 95378: {'lr': 0.00015004621850094686, 'samples': 18312576, 'steps': 95377, 'loss/train': 0.9346179366111755} 08/31/2021 06:30:10 - INFO - __main__ - Step 95379: {'lr': 0.00015004135438387276, 'samples': 18312768, 'steps': 95378, 'loss/train': 1.6180191040039062} 08/31/2021 06:30:12 - INFO - __main__ - Step 95380: {'lr': 0.00015003649031183848, 'samples': 18312960, 'steps': 95379, 'loss/train': 1.2008113861083984} 08/31/2021 06:30:12 - INFO - __main__ - Step 95381: {'lr': 0.00015003162628484624, 'samples': 18313152, 'steps': 95380, 'loss/train': 1.27222740650177} 08/31/2021 06:30:13 - INFO - __main__ - Step 95382: {'lr': 0.00015002676230289826, 'samples': 18313344, 'steps': 95381, 'loss/train': 1.5516060590744019} 08/31/2021 06:30:13 - INFO - __main__ - Step 95383: {'lr': 0.00015002189836599658, 'samples': 18313536, 'steps': 95382, 'loss/train': 1.3870996236801147} 08/31/2021 06:30:13 - INFO - __main__ - Step 95384: {'lr': 0.00015001703447414352, 'samples': 18313728, 'steps': 95383, 'loss/train': 0.9484192132949829} 08/31/2021 06:30:14 - INFO - __main__ - Step 95385: {'lr': 0.00015001217062734124, 'samples': 18313920, 'steps': 95384, 'loss/train': 1.0827823877334595} 08/31/2021 06:30:15 - INFO - __main__ - Step 95386: {'lr': 0.000150007306825592, 'samples': 18314112, 'steps': 95385, 'loss/train': 0.7969435453414917} 08/31/2021 06:30:16 - INFO - __main__ - Step 95387: {'lr': 0.0001500024430688979, 'samples': 18314304, 'steps': 95386, 'loss/train': 0.05100255459547043} 08/31/2021 06:30:16 - INFO - __main__ - Step 95388: {'lr': 0.00014999757935726108, 'samples': 18314496, 'steps': 95387, 'loss/train': 1.4235106706619263} 08/31/2021 06:30:16 - INFO - __main__ - Step 95389: {'lr': 0.00014999271569068385, 'samples': 18314688, 'steps': 95388, 'loss/train': 1.1362992525100708} 08/31/2021 06:30:17 - INFO - __main__ - Step 95390: {'lr': 0.00014998785206916834, 'samples': 18314880, 'steps': 95389, 'loss/train': 0.6305090188980103} 08/31/2021 06:30:18 - INFO - __main__ - Step 95391: {'lr': 0.0001499829884927168, 'samples': 18315072, 'steps': 95390, 'loss/train': 1.0618715286254883} 08/31/2021 06:30:19 - INFO - __main__ - Step 95392: {'lr': 0.00014997812496133134, 'samples': 18315264, 'steps': 95391, 'loss/train': 0.16599850356578827} 08/31/2021 06:30:19 - INFO - __main__ - Step 95393: {'lr': 0.00014997326147501422, 'samples': 18315456, 'steps': 95392, 'loss/train': 0.8271806836128235} 08/31/2021 06:30:19 - INFO - __main__ - Step 95394: {'lr': 0.00014996839803376762, 'samples': 18315648, 'steps': 95393, 'loss/train': 1.2243739366531372} 08/31/2021 06:30:20 - INFO - __main__ - Step 95395: {'lr': 0.00014996353463759366, 'samples': 18315840, 'steps': 95394, 'loss/train': 1.2611151933670044} 08/31/2021 06:30:21 - INFO - __main__ - Step 95396: {'lr': 0.00014995867128649466, 'samples': 18316032, 'steps': 95395, 'loss/train': 0.21245944499969482} 08/31/2021 06:30:22 - INFO - __main__ - Step 95397: {'lr': 0.00014995380798047276, 'samples': 18316224, 'steps': 95396, 'loss/train': 1.271763801574707} 08/31/2021 06:30:22 - INFO - __main__ - Step 95398: {'lr': 0.00014994894471953007, 'samples': 18316416, 'steps': 95397, 'loss/train': 1.0720118284225464} 08/31/2021 06:30:23 - INFO - __main__ - Step 95399: {'lr': 0.00014994408150366883, 'samples': 18316608, 'steps': 95398, 'loss/train': 0.8607426881790161} 08/31/2021 06:30:23 - INFO - __main__ - Step 95400: {'lr': 0.00014993921833289127, 'samples': 18316800, 'steps': 95399, 'loss/train': 1.3946583271026611} 08/31/2021 06:30:23 - INFO - __main__ - Step 95401: {'lr': 0.00014993435520719954, 'samples': 18316992, 'steps': 95400, 'loss/train': 1.2523407936096191} 08/31/2021 06:30:25 - INFO - __main__ - Step 95402: {'lr': 0.00014992949212659586, 'samples': 18317184, 'steps': 95401, 'loss/train': 0.8453008532524109} 08/31/2021 06:30:25 - INFO - __main__ - Step 95403: {'lr': 0.00014992462909108235, 'samples': 18317376, 'steps': 95402, 'loss/train': 0.16325265169143677} 08/31/2021 06:30:26 - INFO - __main__ - Step 95404: {'lr': 0.0001499197661006613, 'samples': 18317568, 'steps': 95403, 'loss/train': 1.175154209136963} 08/31/2021 06:30:26 - INFO - __main__ - Step 95405: {'lr': 0.00014991490315533485, 'samples': 18317760, 'steps': 95404, 'loss/train': 0.954908549785614} 08/31/2021 06:30:26 - INFO - __main__ - Step 95406: {'lr': 0.00014991004025510522, 'samples': 18317952, 'steps': 95405, 'loss/train': 1.6169408559799194} 08/31/2021 06:30:28 - INFO - __main__ - Step 95407: {'lr': 0.00014990517739997455, 'samples': 18318144, 'steps': 95406, 'loss/train': 1.6164443492889404} 08/31/2021 06:30:28 - INFO - __main__ - Step 95408: {'lr': 0.00014990031458994506, 'samples': 18318336, 'steps': 95407, 'loss/train': 1.0747660398483276} 08/31/2021 06:30:29 - INFO - __main__ - Step 95409: {'lr': 0.0001498954518250191, 'samples': 18318528, 'steps': 95408, 'loss/train': 0.35362905263900757} 08/31/2021 06:30:29 - INFO - __main__ - Step 95410: {'lr': 0.00014989058910519856, 'samples': 18318720, 'steps': 95409, 'loss/train': 0.4995351731777191} 08/31/2021 06:30:29 - INFO - __main__ - Step 95411: {'lr': 0.0001498857264304858, 'samples': 18318912, 'steps': 95410, 'loss/train': 1.137885570526123} 08/31/2021 06:30:31 - INFO - __main__ - Step 95412: {'lr': 0.00014988086380088295, 'samples': 18319104, 'steps': 95411, 'loss/train': 1.4767274856567383} 08/31/2021 06:30:31 - INFO - __main__ - Step 95413: {'lr': 0.0001498760012163923, 'samples': 18319296, 'steps': 95412, 'loss/train': 1.4600645303726196} 08/31/2021 06:30:32 - INFO - __main__ - Step 95414: {'lr': 0.0001498711386770159, 'samples': 18319488, 'steps': 95413, 'loss/train': 1.7874834537506104} 08/31/2021 06:30:32 - INFO - __main__ - Step 95415: {'lr': 0.00014986627618275605, 'samples': 18319680, 'steps': 95414, 'loss/train': 2.3281233310699463} 08/31/2021 06:30:32 - INFO - __main__ - Step 95416: {'lr': 0.00014986141373361496, 'samples': 18319872, 'steps': 95415, 'loss/train': 0.8213973045349121} 08/31/2021 06:30:34 - INFO - __main__ - Step 95417: {'lr': 0.00014985655132959469, 'samples': 18320064, 'steps': 95416, 'loss/train': 0.8237175941467285} 08/31/2021 06:30:34 - INFO - __main__ - Step 95418: {'lr': 0.00014985168897069758, 'samples': 18320256, 'steps': 95417, 'loss/train': 1.0141568183898926} 08/31/2021 06:30:35 - INFO - __main__ - Step 95419: {'lr': 0.00014984682665692572, 'samples': 18320448, 'steps': 95418, 'loss/train': 1.117730975151062} 08/31/2021 06:30:35 - INFO - __main__ - Step 95420: {'lr': 0.00014984196438828134, 'samples': 18320640, 'steps': 95419, 'loss/train': 1.149919867515564} 08/31/2021 06:30:35 - INFO - __main__ - Step 95421: {'lr': 0.00014983710216476663, 'samples': 18320832, 'steps': 95420, 'loss/train': 0.1587366759777069} 08/31/2021 06:30:37 - INFO - __main__ - Step 95422: {'lr': 0.00014983223998638384, 'samples': 18321024, 'steps': 95421, 'loss/train': 1.4669349193572998} 08/31/2021 06:30:38 - INFO - __main__ - Step 95423: {'lr': 0.00014982737785313504, 'samples': 18321216, 'steps': 95422, 'loss/train': 1.0142273902893066} 08/31/2021 06:30:38 - INFO - __main__ - Step 95424: {'lr': 0.0001498225157650225, 'samples': 18321408, 'steps': 95423, 'loss/train': 1.6943027973175049} 08/31/2021 06:30:39 - INFO - __main__ - Step 95425: {'lr': 0.00014981765372204834, 'samples': 18321600, 'steps': 95424, 'loss/train': 1.4452896118164062} 08/31/2021 06:30:39 - INFO - __main__ - Step 95426: {'lr': 0.00014981279172421482, 'samples': 18321792, 'steps': 95425, 'loss/train': 0.01804918795824051} 08/31/2021 06:30:39 - INFO - __main__ - Step 95427: {'lr': 0.00014980792977152408, 'samples': 18321984, 'steps': 95426, 'loss/train': 1.3549031019210815} 08/31/2021 06:30:40 - INFO - __main__ - Step 95428: {'lr': 0.00014980306786397838, 'samples': 18322176, 'steps': 95427, 'loss/train': 1.2465238571166992} 08/31/2021 06:30:41 - INFO - __main__ - Step 95429: {'lr': 0.00014979820600157984, 'samples': 18322368, 'steps': 95428, 'loss/train': 1.6538598537445068} 08/31/2021 06:30:42 - INFO - __main__ - Step 95430: {'lr': 0.00014979334418433073, 'samples': 18322560, 'steps': 95429, 'loss/train': 0.7551625967025757} 08/31/2021 06:30:42 - INFO - __main__ - Step 95431: {'lr': 0.00014978848241223314, 'samples': 18322752, 'steps': 95430, 'loss/train': 0.2291892021894455} 08/31/2021 06:30:42 - INFO - __main__ - Step 95432: {'lr': 0.00014978362068528934, 'samples': 18322944, 'steps': 95431, 'loss/train': 0.04666120931506157} 08/31/2021 06:30:43 - INFO - __main__ - Step 95433: {'lr': 0.0001497787590035015, 'samples': 18323136, 'steps': 95432, 'loss/train': 1.7396302223205566} 08/31/2021 06:30:45 - INFO - __main__ - Step 95434: {'lr': 0.0001497738973668718, 'samples': 18323328, 'steps': 95433, 'loss/train': 1.1620759963989258} 08/31/2021 06:30:45 - INFO - __main__ - Step 95435: {'lr': 0.0001497690357754024, 'samples': 18323520, 'steps': 95434, 'loss/train': 1.8954648971557617} 08/31/2021 06:30:46 - INFO - __main__ - Step 95436: {'lr': 0.00014976417422909565, 'samples': 18323712, 'steps': 95435, 'loss/train': 0.9306353330612183} 08/31/2021 06:30:46 - INFO - __main__ - Step 95437: {'lr': 0.00014975931272795355, 'samples': 18323904, 'steps': 95436, 'loss/train': 0.931131899356842} 08/31/2021 06:30:46 - INFO - __main__ - Step 95438: {'lr': 0.00014975445127197833, 'samples': 18324096, 'steps': 95437, 'loss/train': 1.0891432762145996} 08/31/2021 06:30:48 - INFO - __main__ - Step 95439: {'lr': 0.00014974958986117221, 'samples': 18324288, 'steps': 95438, 'loss/train': 0.30257365107536316} 08/31/2021 06:30:48 - INFO - __main__ - Step 95440: {'lr': 0.00014974472849553735, 'samples': 18324480, 'steps': 95439, 'loss/train': 1.0260961055755615} 08/31/2021 06:30:49 - INFO - __main__ - Step 95441: {'lr': 0.000149739867175076, 'samples': 18324672, 'steps': 95440, 'loss/train': 1.026295781135559} 08/31/2021 06:30:49 - INFO - __main__ - Step 95442: {'lr': 0.00014973500589979033, 'samples': 18324864, 'steps': 95441, 'loss/train': 0.3689501881599426} 08/31/2021 06:30:49 - INFO - __main__ - Step 95443: {'lr': 0.0001497301446696825, 'samples': 18325056, 'steps': 95442, 'loss/train': 1.106239676475525} 08/31/2021 06:30:51 - INFO - __main__ - Step 95444: {'lr': 0.0001497252834847547, 'samples': 18325248, 'steps': 95443, 'loss/train': 0.9580696225166321} 08/31/2021 06:30:51 - INFO - __main__ - Step 95445: {'lr': 0.00014972042234500917, 'samples': 18325440, 'steps': 95444, 'loss/train': 0.7002933025360107} 08/31/2021 06:30:52 - INFO - __main__ - Step 95446: {'lr': 0.00014971556125044805, 'samples': 18325632, 'steps': 95445, 'loss/train': 0.5401299595832825} 08/31/2021 06:30:52 - INFO - __main__ - Step 95447: {'lr': 0.00014971070020107358, 'samples': 18325824, 'steps': 95446, 'loss/train': 0.9851008057594299} 08/31/2021 06:30:52 - INFO - __main__ - Step 95448: {'lr': 0.0001497058391968879, 'samples': 18326016, 'steps': 95447, 'loss/train': 1.7196221351623535} 08/31/2021 06:30:54 - INFO - __main__ - Step 95449: {'lr': 0.0001497009782378933, 'samples': 18326208, 'steps': 95448, 'loss/train': 1.0238988399505615} 08/31/2021 06:30:54 - INFO - __main__ - Step 95450: {'lr': 0.00014969611732409182, 'samples': 18326400, 'steps': 95449, 'loss/train': 0.9982655048370361} 08/31/2021 06:30:55 - INFO - __main__ - Step 95451: {'lr': 0.0001496912564554857, 'samples': 18326592, 'steps': 95450, 'loss/train': 1.2026073932647705} 08/31/2021 06:30:55 - INFO - __main__ - Step 95452: {'lr': 0.0001496863956320772, 'samples': 18326784, 'steps': 95451, 'loss/train': 1.1544907093048096} 08/31/2021 06:30:55 - INFO - __main__ - Step 95453: {'lr': 0.00014968153485386842, 'samples': 18326976, 'steps': 95452, 'loss/train': 0.7616146802902222} 08/31/2021 06:30:57 - INFO - __main__ - Step 95454: {'lr': 0.0001496766741208616, 'samples': 18327168, 'steps': 95453, 'loss/train': 1.8892621994018555} 08/31/2021 06:30:57 - INFO - __main__ - Step 95455: {'lr': 0.0001496718134330589, 'samples': 18327360, 'steps': 95454, 'loss/train': 1.039654016494751} 08/31/2021 06:30:58 - INFO - __main__ - Step 95456: {'lr': 0.0001496669527904626, 'samples': 18327552, 'steps': 95455, 'loss/train': 1.7670215368270874} 08/31/2021 06:30:58 - INFO - __main__ - Step 95457: {'lr': 0.00014966209219307474, 'samples': 18327744, 'steps': 95456, 'loss/train': 0.8175068497657776} 08/31/2021 06:30:58 - INFO - __main__ - Step 95458: {'lr': 0.00014965723164089766, 'samples': 18327936, 'steps': 95457, 'loss/train': 1.4779471158981323} 08/31/2021 06:30:59 - INFO - __main__ - Step 95459: {'lr': 0.00014965237113393346, 'samples': 18328128, 'steps': 95458, 'loss/train': 1.0756487846374512} 08/31/2021 06:31:00 - INFO - __main__ - Step 95460: {'lr': 0.00014964751067218435, 'samples': 18328320, 'steps': 95459, 'loss/train': 1.1039552688598633} 08/31/2021 06:31:01 - INFO - __main__ - Step 95461: {'lr': 0.0001496426502556525, 'samples': 18328512, 'steps': 95460, 'loss/train': 1.3391332626342773} 08/31/2021 06:31:01 - INFO - __main__ - Step 95462: {'lr': 0.0001496377898843402, 'samples': 18328704, 'steps': 95461, 'loss/train': 1.5711963176727295} 08/31/2021 06:31:01 - INFO - __main__ - Step 95463: {'lr': 0.0001496329295582496, 'samples': 18328896, 'steps': 95462, 'loss/train': 1.4466667175292969} 08/31/2021 06:31:02 - INFO - __main__ - Step 95464: {'lr': 0.00014962806927738272, 'samples': 18329088, 'steps': 95463, 'loss/train': 1.159924864768982} 08/31/2021 06:31:03 - INFO - __main__ - Step 95465: {'lr': 0.00014962320904174194, 'samples': 18329280, 'steps': 95464, 'loss/train': 0.9642931818962097} 08/31/2021 06:31:04 - INFO - __main__ - Step 95466: {'lr': 0.00014961834885132938, 'samples': 18329472, 'steps': 95465, 'loss/train': 1.3490337133407593} 08/31/2021 06:31:04 - INFO - __main__ - Step 95467: {'lr': 0.00014961348870614724, 'samples': 18329664, 'steps': 95466, 'loss/train': 1.0794012546539307} 08/31/2021 06:31:05 - INFO - __main__ - Step 95468: {'lr': 0.00014960862860619772, 'samples': 18329856, 'steps': 95467, 'loss/train': 1.2652168273925781} 08/31/2021 06:31:05 - INFO - __main__ - Step 95469: {'lr': 0.000149603768551483, 'samples': 18330048, 'steps': 95468, 'loss/train': 1.0625905990600586} 08/31/2021 06:31:07 - INFO - __main__ - Step 95470: {'lr': 0.00014959890854200525, 'samples': 18330240, 'steps': 95469, 'loss/train': 0.038186460733413696} 08/31/2021 06:31:07 - INFO - __main__ - Step 95471: {'lr': 0.00014959404857776672, 'samples': 18330432, 'steps': 95470, 'loss/train': 1.1669913530349731} 08/31/2021 06:31:07 - INFO - __main__ - Step 95472: {'lr': 0.00014958918865876954, 'samples': 18330624, 'steps': 95471, 'loss/train': 0.32779020071029663} 08/31/2021 06:31:08 - INFO - __main__ - Step 95473: {'lr': 0.00014958432878501595, 'samples': 18330816, 'steps': 95472, 'loss/train': 1.0890891551971436} 08/31/2021 06:31:08 - INFO - __main__ - Step 95474: {'lr': 0.00014957946895650807, 'samples': 18331008, 'steps': 95473, 'loss/train': 2.289961099624634} 08/31/2021 06:31:10 - INFO - __main__ - Step 95475: {'lr': 0.00014957460917324817, 'samples': 18331200, 'steps': 95474, 'loss/train': 1.7830148935317993} 08/31/2021 06:31:10 - INFO - __main__ - Step 95476: {'lr': 0.00014956974943523845, 'samples': 18331392, 'steps': 95475, 'loss/train': 1.1172488927841187} 08/31/2021 06:31:10 - INFO - __main__ - Step 95477: {'lr': 0.000149564889742481, 'samples': 18331584, 'steps': 95476, 'loss/train': 0.9021380543708801} 08/31/2021 06:31:11 - INFO - __main__ - Step 95478: {'lr': 0.00014956003009497805, 'samples': 18331776, 'steps': 95477, 'loss/train': 1.63791823387146} 08/31/2021 06:31:11 - INFO - __main__ - Step 95479: {'lr': 0.00014955517049273175, 'samples': 18331968, 'steps': 95478, 'loss/train': 1.1675959825515747} 08/31/2021 06:31:11 - INFO - __main__ - Step 95480: {'lr': 0.0001495503109357444, 'samples': 18332160, 'steps': 95479, 'loss/train': 1.501918911933899} 08/31/2021 06:31:13 - INFO - __main__ - Step 95481: {'lr': 0.00014954545142401813, 'samples': 18332352, 'steps': 95480, 'loss/train': 0.8198354244232178} 08/31/2021 06:31:14 - INFO - __main__ - Step 95482: {'lr': 0.0001495405919575551, 'samples': 18332544, 'steps': 95481, 'loss/train': 1.384542465209961} 08/31/2021 06:31:14 - INFO - __main__ - Step 95483: {'lr': 0.00014953573253635754, 'samples': 18332736, 'steps': 95482, 'loss/train': 1.151570439338684} 08/31/2021 06:31:14 - INFO - __main__ - Step 95484: {'lr': 0.00014953087316042766, 'samples': 18332928, 'steps': 95483, 'loss/train': 1.1257028579711914} 08/31/2021 06:31:15 - INFO - __main__ - Step 95485: {'lr': 0.00014952601382976758, 'samples': 18333120, 'steps': 95484, 'loss/train': 0.7111820578575134} 08/31/2021 06:31:17 - INFO - __main__ - Step 95486: {'lr': 0.00014952115454437953, 'samples': 18333312, 'steps': 95485, 'loss/train': 1.8103251457214355} 08/31/2021 06:31:17 - INFO - __main__ - Step 95487: {'lr': 0.00014951629530426572, 'samples': 18333504, 'steps': 95486, 'loss/train': 1.2971851825714111} 08/31/2021 06:31:18 - INFO - __main__ - Step 95488: {'lr': 0.00014951143610942837, 'samples': 18333696, 'steps': 95487, 'loss/train': 0.5989497303962708} 08/31/2021 06:31:18 - INFO - __main__ - Step 95489: {'lr': 0.00014950657695986952, 'samples': 18333888, 'steps': 95488, 'loss/train': 1.3528976440429688} 08/31/2021 06:31:19 - INFO - __main__ - Step 95490: {'lr': 0.00014950171785559153, 'samples': 18334080, 'steps': 95489, 'loss/train': 0.03304048255085945} 08/31/2021 06:31:20 - INFO - __main__ - Step 95491: {'lr': 0.00014949685879659647, 'samples': 18334272, 'steps': 95490, 'loss/train': 0.9755744934082031} 08/31/2021 06:31:21 - INFO - __main__ - Step 95492: {'lr': 0.00014949199978288657, 'samples': 18334464, 'steps': 95491, 'loss/train': 1.110749363899231} 08/31/2021 06:31:21 - INFO - __main__ - Step 95493: {'lr': 0.00014948714081446405, 'samples': 18334656, 'steps': 95492, 'loss/train': 1.1755976676940918} 08/31/2021 06:31:21 - INFO - __main__ - Step 95494: {'lr': 0.00014948228189133107, 'samples': 18334848, 'steps': 95493, 'loss/train': 1.0477713346481323} 08/31/2021 06:31:22 - INFO - __main__ - Step 95495: {'lr': 0.00014947742301348976, 'samples': 18335040, 'steps': 95494, 'loss/train': 0.8130986094474792} 08/31/2021 06:31:23 - INFO - __main__ - Step 95496: {'lr': 0.00014947256418094244, 'samples': 18335232, 'steps': 95495, 'loss/train': 0.9538718461990356} 08/31/2021 06:31:24 - INFO - __main__ - Step 95497: {'lr': 0.0001494677053936912, 'samples': 18335424, 'steps': 95496, 'loss/train': 1.2502366304397583} 08/31/2021 06:31:24 - INFO - __main__ - Step 95498: {'lr': 0.00014946284665173833, 'samples': 18335616, 'steps': 95497, 'loss/train': 0.8546008467674255} 08/31/2021 06:31:24 - INFO - __main__ - Step 95499: {'lr': 0.00014945798795508585, 'samples': 18335808, 'steps': 95498, 'loss/train': 1.0573828220367432} 08/31/2021 06:31:25 - INFO - __main__ - Step 95500: {'lr': 0.00014945312930373611, 'samples': 18336000, 'steps': 95499, 'loss/train': 1.546708583831787} 08/31/2021 06:31:25 - INFO - __main__ - Step 95501: {'lr': 0.00014944827069769123, 'samples': 18336192, 'steps': 95500, 'loss/train': 2.0411267280578613} 08/31/2021 06:31:27 - INFO - __main__ - Step 95502: {'lr': 0.0001494434121369534, 'samples': 18336384, 'steps': 95501, 'loss/train': 1.0189584493637085} 08/31/2021 06:31:27 - INFO - __main__ - Step 95503: {'lr': 0.00014943855362152485, 'samples': 18336576, 'steps': 95502, 'loss/train': 0.9225981831550598} 08/31/2021 06:31:27 - INFO - __main__ - Step 95504: {'lr': 0.00014943369515140771, 'samples': 18336768, 'steps': 95503, 'loss/train': 0.9109910726547241} 08/31/2021 06:31:28 - INFO - __main__ - Step 95505: {'lr': 0.0001494288367266042, 'samples': 18336960, 'steps': 95504, 'loss/train': 1.6725804805755615} 08/31/2021 06:31:28 - INFO - __main__ - Step 95506: {'lr': 0.00014942397834711646, 'samples': 18337152, 'steps': 95505, 'loss/train': 0.8734650015830994} 08/31/2021 06:31:30 - INFO - __main__ - Step 95507: {'lr': 0.0001494191200129467, 'samples': 18337344, 'steps': 95506, 'loss/train': 1.206551432609558} 08/31/2021 06:31:30 - INFO - __main__ - Step 95508: {'lr': 0.00014941426172409723, 'samples': 18337536, 'steps': 95507, 'loss/train': 1.3960556983947754} 08/31/2021 06:31:30 - INFO - __main__ - Step 95509: {'lr': 0.00014940940348057014, 'samples': 18337728, 'steps': 95508, 'loss/train': 1.3934921026229858} 08/31/2021 06:31:31 - INFO - __main__ - Step 95510: {'lr': 0.00014940454528236758, 'samples': 18337920, 'steps': 95509, 'loss/train': 1.5563843250274658} 08/31/2021 06:31:31 - INFO - __main__ - Step 95511: {'lr': 0.00014939968712949174, 'samples': 18338112, 'steps': 95510, 'loss/train': 1.0674155950546265} 08/31/2021 06:31:33 - INFO - __main__ - Step 95512: {'lr': 0.0001493948290219449, 'samples': 18338304, 'steps': 95511, 'loss/train': 1.2684656381607056} 08/31/2021 06:31:33 - INFO - __main__ - Step 95513: {'lr': 0.00014938997095972917, 'samples': 18338496, 'steps': 95512, 'loss/train': 0.48798662424087524} 08/31/2021 06:31:33 - INFO - __main__ - Step 95514: {'lr': 0.0001493851129428468, 'samples': 18338688, 'steps': 95513, 'loss/train': 0.9620428681373596} 08/31/2021 06:31:34 - INFO - __main__ - Step 95515: {'lr': 0.0001493802549712999, 'samples': 18338880, 'steps': 95514, 'loss/train': 0.6099022030830383} 08/31/2021 06:31:34 - INFO - __main__ - Step 95516: {'lr': 0.00014937539704509072, 'samples': 18339072, 'steps': 95515, 'loss/train': 1.3788816928863525} 08/31/2021 06:31:36 - INFO - __main__ - Step 95517: {'lr': 0.0001493705391642215, 'samples': 18339264, 'steps': 95516, 'loss/train': 1.0465149879455566} 08/31/2021 06:31:37 - INFO - __main__ - Step 95518: {'lr': 0.0001493656813286943, 'samples': 18339456, 'steps': 95517, 'loss/train': 0.9958316087722778} 08/31/2021 06:31:37 - INFO - __main__ - Step 95519: {'lr': 0.00014936082353851139, 'samples': 18339648, 'steps': 95518, 'loss/train': 1.9192999601364136} 08/31/2021 06:31:38 - INFO - __main__ - Step 95520: {'lr': 0.00014935596579367493, 'samples': 18339840, 'steps': 95519, 'loss/train': 1.0589829683303833} 08/31/2021 06:31:38 - INFO - __main__ - Step 95521: {'lr': 0.00014935110809418713, 'samples': 18340032, 'steps': 95520, 'loss/train': 0.8367999792098999} 08/31/2021 06:31:38 - INFO - __main__ - Step 95522: {'lr': 0.00014934625044005014, 'samples': 18340224, 'steps': 95521, 'loss/train': 1.5388327836990356} 08/31/2021 06:31:40 - INFO - __main__ - Step 95523: {'lr': 0.00014934139283126618, 'samples': 18340416, 'steps': 95522, 'loss/train': 1.407058835029602} 08/31/2021 06:31:40 - INFO - __main__ - Step 95524: {'lr': 0.00014933653526783748, 'samples': 18340608, 'steps': 95523, 'loss/train': 3.495948553085327} 08/31/2021 06:31:41 - INFO - __main__ - Step 95525: {'lr': 0.00014933167774976614, 'samples': 18340800, 'steps': 95524, 'loss/train': 1.589296817779541} 08/31/2021 06:31:41 - INFO - __main__ - Step 95526: {'lr': 0.00014932682027705437, 'samples': 18340992, 'steps': 95525, 'loss/train': 1.148659348487854} 08/31/2021 06:31:41 - INFO - __main__ - Step 95527: {'lr': 0.0001493219628497044, 'samples': 18341184, 'steps': 95526, 'loss/train': 0.9994359612464905} 08/31/2021 06:31:42 - INFO - __main__ - Step 95528: {'lr': 0.00014931710546771843, 'samples': 18341376, 'steps': 95527, 'loss/train': 1.1750432252883911} 08/31/2021 06:31:43 - INFO - __main__ - Step 95529: {'lr': 0.0001493122481310986, 'samples': 18341568, 'steps': 95528, 'loss/train': 1.5016846656799316} 08/31/2021 06:31:44 - INFO - __main__ - Step 95530: {'lr': 0.00014930739083984714, 'samples': 18341760, 'steps': 95529, 'loss/train': 1.608810305595398} 08/31/2021 06:31:44 - INFO - __main__ - Step 95531: {'lr': 0.00014930253359396627, 'samples': 18341952, 'steps': 95530, 'loss/train': 0.03754620626568794} 08/31/2021 06:31:45 - INFO - __main__ - Step 95532: {'lr': 0.00014929767639345804, 'samples': 18342144, 'steps': 95531, 'loss/train': 1.0244578123092651} 08/31/2021 06:31:45 - INFO - __main__ - Step 95533: {'lr': 0.00014929281923832473, 'samples': 18342336, 'steps': 95532, 'loss/train': 0.9597463011741638} 08/31/2021 06:31:47 - INFO - __main__ - Step 95534: {'lr': 0.00014928796212856848, 'samples': 18342528, 'steps': 95533, 'loss/train': 1.1883478164672852} 08/31/2021 06:31:47 - INFO - __main__ - Step 95535: {'lr': 0.00014928310506419156, 'samples': 18342720, 'steps': 95534, 'loss/train': 1.079297423362732} 08/31/2021 06:31:47 - INFO - __main__ - Step 95536: {'lr': 0.00014927824804519612, 'samples': 18342912, 'steps': 95535, 'loss/train': 0.9392183423042297} 08/31/2021 06:31:48 - INFO - __main__ - Step 95537: {'lr': 0.00014927339107158436, 'samples': 18343104, 'steps': 95536, 'loss/train': 1.0724061727523804} 08/31/2021 06:31:48 - INFO - __main__ - Step 95538: {'lr': 0.00014926853414335846, 'samples': 18343296, 'steps': 95537, 'loss/train': 0.037856243550777435} 08/31/2021 06:31:50 - INFO - __main__ - Step 95539: {'lr': 0.00014926367726052057, 'samples': 18343488, 'steps': 95538, 'loss/train': 1.1738033294677734} 08/31/2021 06:31:51 - INFO - __main__ - Step 95540: {'lr': 0.00014925882042307292, 'samples': 18343680, 'steps': 95539, 'loss/train': 0.752336323261261} 08/31/2021 06:31:51 - INFO - __main__ - Step 95541: {'lr': 0.00014925396363101772, 'samples': 18343872, 'steps': 95540, 'loss/train': 1.6395421028137207} 08/31/2021 06:31:51 - INFO - __main__ - Step 95542: {'lr': 0.0001492491068843571, 'samples': 18344064, 'steps': 95541, 'loss/train': 1.1920835971832275} 08/31/2021 06:31:52 - INFO - __main__ - Step 95543: {'lr': 0.0001492442501830934, 'samples': 18344256, 'steps': 95542, 'loss/train': 1.677049160003662} 08/31/2021 06:31:52 - INFO - __main__ - Step 95544: {'lr': 0.00014923939352722853, 'samples': 18344448, 'steps': 95543, 'loss/train': 1.1337579488754272} 08/31/2021 06:31:54 - INFO - __main__ - Step 95545: {'lr': 0.00014923453691676492, 'samples': 18344640, 'steps': 95544, 'loss/train': 1.405644416809082} 08/31/2021 06:31:54 - INFO - __main__ - Step 95546: {'lr': 0.0001492296803517046, 'samples': 18344832, 'steps': 95545, 'loss/train': 1.4526598453521729} 08/31/2021 06:31:55 - INFO - __main__ - Step 95547: {'lr': 0.00014922482383204988, 'samples': 18345024, 'steps': 95546, 'loss/train': 1.3716211318969727} 08/31/2021 06:31:55 - INFO - __main__ - Step 95548: {'lr': 0.00014921996735780285, 'samples': 18345216, 'steps': 95547, 'loss/train': 1.0577651262283325} 08/31/2021 06:31:55 - INFO - __main__ - Step 95549: {'lr': 0.0001492151109289658, 'samples': 18345408, 'steps': 95548, 'loss/train': 0.7790650129318237} 08/31/2021 06:31:57 - INFO - __main__ - Step 95550: {'lr': 0.00014921025454554083, 'samples': 18345600, 'steps': 95549, 'loss/train': 1.3449712991714478} 08/31/2021 06:31:58 - INFO - __main__ - Step 95551: {'lr': 0.00014920539820753017, 'samples': 18345792, 'steps': 95550, 'loss/train': 1.5971850156784058} 08/31/2021 06:31:58 - INFO - __main__ - Step 95552: {'lr': 0.00014920054191493604, 'samples': 18345984, 'steps': 95551, 'loss/train': 1.0205161571502686} 08/31/2021 06:31:58 - INFO - __main__ - Step 95553: {'lr': 0.00014919568566776055, 'samples': 18346176, 'steps': 95552, 'loss/train': 0.7512012720108032} 08/31/2021 06:31:59 - INFO - __main__ - Step 95554: {'lr': 0.00014919082946600592, 'samples': 18346368, 'steps': 95553, 'loss/train': 1.3373051881790161} 08/31/2021 06:32:00 - INFO - __main__ - Step 95555: {'lr': 0.00014918597330967437, 'samples': 18346560, 'steps': 95554, 'loss/train': 0.23765172064304352} 08/31/2021 06:32:01 - INFO - __main__ - Step 95556: {'lr': 0.00014918111719876807, 'samples': 18346752, 'steps': 95555, 'loss/train': 1.3019160032272339} 08/31/2021 06:32:01 - INFO - __main__ - Step 95557: {'lr': 0.0001491762611332893, 'samples': 18346944, 'steps': 95556, 'loss/train': 1.3448134660720825} 08/31/2021 06:32:01 - INFO - __main__ - Step 95558: {'lr': 0.00014917140511324002, 'samples': 18347136, 'steps': 95557, 'loss/train': 1.2884351015090942} 08/31/2021 06:32:02 - INFO - __main__ - Step 95559: {'lr': 0.0001491665491386226, 'samples': 18347328, 'steps': 95558, 'loss/train': 1.30308198928833} 08/31/2021 06:32:03 - INFO - __main__ - Step 95560: {'lr': 0.00014916169320943913, 'samples': 18347520, 'steps': 95559, 'loss/train': 0.03632253780961037} 08/31/2021 06:32:04 - INFO - __main__ - Step 95561: {'lr': 0.00014915683732569186, 'samples': 18347712, 'steps': 95560, 'loss/train': 0.6902087926864624} 08/31/2021 06:32:04 - INFO - __main__ - Step 95562: {'lr': 0.00014915198148738297, 'samples': 18347904, 'steps': 95561, 'loss/train': 1.6689040660858154} 08/31/2021 06:32:05 - INFO - __main__ - Step 95563: {'lr': 0.00014914712569451464, 'samples': 18348096, 'steps': 95562, 'loss/train': 1.7054970264434814} 08/31/2021 06:32:05 - INFO - __main__ - Step 95564: {'lr': 0.00014914226994708907, 'samples': 18348288, 'steps': 95563, 'loss/train': 1.6947910785675049} 08/31/2021 06:32:07 - INFO - __main__ - Step 95565: {'lr': 0.0001491374142451084, 'samples': 18348480, 'steps': 95564, 'loss/train': 0.02430807054042816} 08/31/2021 06:32:07 - INFO - __main__ - Step 95566: {'lr': 0.00014913255858857487, 'samples': 18348672, 'steps': 95565, 'loss/train': 0.8056641221046448} 08/31/2021 06:32:07 - INFO - __main__ - Step 95567: {'lr': 0.00014912770297749068, 'samples': 18348864, 'steps': 95566, 'loss/train': 1.6650627851486206} 08/31/2021 06:32:08 - INFO - __main__ - Step 95568: {'lr': 0.00014912284741185798, 'samples': 18349056, 'steps': 95567, 'loss/train': 1.257384181022644} 08/31/2021 06:32:08 - INFO - __main__ - Step 95569: {'lr': 0.00014911799189167897, 'samples': 18349248, 'steps': 95568, 'loss/train': 0.6725737452507019} 08/31/2021 06:32:10 - INFO - __main__ - Step 95570: {'lr': 0.0001491131364169559, 'samples': 18349440, 'steps': 95569, 'loss/train': 1.2113415002822876} 08/31/2021 06:32:10 - INFO - __main__ - Step 95571: {'lr': 0.00014910828098769083, 'samples': 18349632, 'steps': 95570, 'loss/train': 1.8626775741577148} 08/31/2021 06:32:10 - INFO - __main__ - Step 95572: {'lr': 0.00014910342560388602, 'samples': 18349824, 'steps': 95571, 'loss/train': 1.9518574476242065} 08/31/2021 06:32:11 - INFO - __main__ - Step 95573: {'lr': 0.0001490985702655436, 'samples': 18350016, 'steps': 95572, 'loss/train': 1.5228739976882935} 08/31/2021 06:32:11 - INFO - __main__ - Step 95574: {'lr': 0.00014909371497266583, 'samples': 18350208, 'steps': 95573, 'loss/train': 1.404320478439331} 08/31/2021 06:32:11 - INFO - __main__ - Step 95575: {'lr': 0.0001490888597252549, 'samples': 18350400, 'steps': 95574, 'loss/train': 0.6652339100837708} 08/31/2021 06:32:13 - INFO - __main__ - Step 95576: {'lr': 0.00014908400452331294, 'samples': 18350592, 'steps': 95575, 'loss/train': 1.3756122589111328} 08/31/2021 06:32:14 - INFO - __main__ - Step 95577: {'lr': 0.0001490791493668422, 'samples': 18350784, 'steps': 95576, 'loss/train': 1.073848009109497} 08/31/2021 06:32:14 - INFO - __main__ - Step 95578: {'lr': 0.00014907429425584483, 'samples': 18350976, 'steps': 95577, 'loss/train': 0.030286021530628204} 08/31/2021 06:32:14 - INFO - __main__ - Step 95579: {'lr': 0.00014906943919032302, 'samples': 18351168, 'steps': 95578, 'loss/train': 1.1025279760360718} 08/31/2021 06:32:15 - INFO - __main__ - Step 95580: {'lr': 0.00014906458417027896, 'samples': 18351360, 'steps': 95579, 'loss/train': 1.120193362236023} 08/31/2021 06:32:16 - INFO - __main__ - Step 95581: {'lr': 0.00014905972919571485, 'samples': 18351552, 'steps': 95580, 'loss/train': 1.1955755949020386} 08/31/2021 06:32:17 - INFO - __main__ - Step 95582: {'lr': 0.00014905487426663283, 'samples': 18351744, 'steps': 95581, 'loss/train': 0.9822276830673218} 08/31/2021 06:32:17 - INFO - __main__ - Step 95583: {'lr': 0.0001490500193830352, 'samples': 18351936, 'steps': 95582, 'loss/train': 1.0706844329833984} 08/31/2021 06:32:17 - INFO - __main__ - Step 95584: {'lr': 0.00014904516454492412, 'samples': 18352128, 'steps': 95583, 'loss/train': 1.1201112270355225} 08/31/2021 06:32:18 - INFO - __main__ - Step 95585: {'lr': 0.00014904030975230166, 'samples': 18352320, 'steps': 95584, 'loss/train': 0.04467323049902916} 08/31/2021 06:32:19 - INFO - __main__ - Step 95586: {'lr': 0.00014903545500517004, 'samples': 18352512, 'steps': 95585, 'loss/train': 1.7260929346084595} 08/31/2021 06:32:20 - INFO - __main__ - Step 95587: {'lr': 0.0001490306003035315, 'samples': 18352704, 'steps': 95586, 'loss/train': 1.510584831237793} 08/31/2021 06:32:20 - INFO - __main__ - Step 95588: {'lr': 0.00014902574564738824, 'samples': 18352896, 'steps': 95587, 'loss/train': 1.2047268152236938} 08/31/2021 06:32:20 - INFO - __main__ - Step 95589: {'lr': 0.0001490208910367424, 'samples': 18353088, 'steps': 95588, 'loss/train': 0.5390464067459106} 08/31/2021 06:32:21 - INFO - __main__ - Step 95590: {'lr': 0.00014901603647159617, 'samples': 18353280, 'steps': 95589, 'loss/train': 1.0781124830245972} 08/31/2021 06:32:22 - INFO - __main__ - Step 95591: {'lr': 0.0001490111819519518, 'samples': 18353472, 'steps': 95590, 'loss/train': 1.0232446193695068} 08/31/2021 06:32:23 - INFO - __main__ - Step 95592: {'lr': 0.0001490063274778114, 'samples': 18353664, 'steps': 95591, 'loss/train': 1.0280886888504028} 08/31/2021 06:32:23 - INFO - __main__ - Step 95593: {'lr': 0.0001490014730491772, 'samples': 18353856, 'steps': 95592, 'loss/train': 0.4358271062374115} 08/31/2021 06:32:23 - INFO - __main__ - Step 95594: {'lr': 0.00014899661866605137, 'samples': 18354048, 'steps': 95593, 'loss/train': 1.2686268091201782} 08/31/2021 06:32:24 - INFO - __main__ - Step 95595: {'lr': 0.0001489917643284361, 'samples': 18354240, 'steps': 95594, 'loss/train': 0.8107527494430542} 08/31/2021 06:32:26 - INFO - __main__ - Step 95596: {'lr': 0.0001489869100363336, 'samples': 18354432, 'steps': 95595, 'loss/train': 1.3216699361801147} 08/31/2021 06:32:26 - INFO - __main__ - Step 95597: {'lr': 0.00014898205578974617, 'samples': 18354624, 'steps': 95596, 'loss/train': 0.7229213118553162} 08/31/2021 06:32:27 - INFO - __main__ - Step 95598: {'lr': 0.0001489772015886757, 'samples': 18354816, 'steps': 95597, 'loss/train': 0.9953370094299316} 08/31/2021 06:32:27 - INFO - __main__ - Step 95599: {'lr': 0.0001489723474331246, 'samples': 18355008, 'steps': 95598, 'loss/train': 0.8173203468322754} 08/31/2021 06:32:28 - INFO - __main__ - Step 95600: {'lr': 0.00014896749332309495, 'samples': 18355200, 'steps': 95599, 'loss/train': 1.5002890825271606} 08/31/2021 06:32:28 - INFO - __main__ - Step 95601: {'lr': 0.00014896263925858903, 'samples': 18355392, 'steps': 95600, 'loss/train': 0.9031016230583191} 08/31/2021 06:32:30 - INFO - __main__ - Step 95602: {'lr': 0.00014895778523960895, 'samples': 18355584, 'steps': 95601, 'loss/train': 1.339957356452942} 08/31/2021 06:32:30 - INFO - __main__ - Step 95603: {'lr': 0.00014895293126615696, 'samples': 18355776, 'steps': 95602, 'loss/train': 1.2103723287582397} 08/31/2021 06:32:30 - INFO - __main__ - Step 95604: {'lr': 0.00014894807733823522, 'samples': 18355968, 'steps': 95603, 'loss/train': 0.27118784189224243} 08/31/2021 06:32:31 - INFO - __main__ - Step 95605: {'lr': 0.0001489432234558459, 'samples': 18356160, 'steps': 95604, 'loss/train': 1.2120903730392456} 08/31/2021 06:32:31 - INFO - __main__ - Step 95606: {'lr': 0.00014893836961899122, 'samples': 18356352, 'steps': 95605, 'loss/train': 1.3883253335952759} 08/31/2021 06:32:33 - INFO - __main__ - Step 95607: {'lr': 0.00014893351582767335, 'samples': 18356544, 'steps': 95606, 'loss/train': 1.0377432107925415} 08/31/2021 06:32:33 - INFO - __main__ - Step 95608: {'lr': 0.00014892866208189448, 'samples': 18356736, 'steps': 95607, 'loss/train': 0.769459068775177} 08/31/2021 06:32:33 - INFO - __main__ - Step 95609: {'lr': 0.00014892380838165678, 'samples': 18356928, 'steps': 95608, 'loss/train': 0.2998178005218506} 08/31/2021 06:32:34 - INFO - __main__ - Step 95610: {'lr': 0.00014891895472696244, 'samples': 18357120, 'steps': 95609, 'loss/train': 1.8722572326660156} 08/31/2021 06:32:34 - INFO - __main__ - Step 95611: {'lr': 0.0001489141011178138, 'samples': 18357312, 'steps': 95610, 'loss/train': 0.8991073966026306} 08/31/2021 06:32:36 - INFO - __main__ - Step 95612: {'lr': 0.00014890924755421277, 'samples': 18357504, 'steps': 95611, 'loss/train': 1.1448675394058228} 08/31/2021 06:32:36 - INFO - __main__ - Step 95613: {'lr': 0.00014890439403616171, 'samples': 18357696, 'steps': 95612, 'loss/train': 1.1075421571731567} 08/31/2021 06:32:36 - INFO - __main__ - Step 95614: {'lr': 0.00014889954056366273, 'samples': 18357888, 'steps': 95613, 'loss/train': 0.9697750210762024} 08/31/2021 06:32:37 - INFO - __main__ - Step 95615: {'lr': 0.0001488946871367181, 'samples': 18358080, 'steps': 95614, 'loss/train': 1.4135819673538208} 08/31/2021 06:32:37 - INFO - __main__ - Step 95616: {'lr': 0.00014888983375532994, 'samples': 18358272, 'steps': 95615, 'loss/train': 1.1726945638656616} 08/31/2021 06:32:39 - INFO - __main__ - Step 95617: {'lr': 0.00014888498041950045, 'samples': 18358464, 'steps': 95616, 'loss/train': 1.1249141693115234} 08/31/2021 06:32:39 - INFO - __main__ - Step 95618: {'lr': 0.00014888012712923186, 'samples': 18358656, 'steps': 95617, 'loss/train': 1.1298762559890747} 08/31/2021 06:32:40 - INFO - __main__ - Step 95619: {'lr': 0.00014887527388452628, 'samples': 18358848, 'steps': 95618, 'loss/train': 0.9787375926971436} 08/31/2021 06:32:40 - INFO - __main__ - Step 95620: {'lr': 0.00014887042068538597, 'samples': 18359040, 'steps': 95619, 'loss/train': 0.7055665850639343} 08/31/2021 06:32:40 - INFO - __main__ - Step 95621: {'lr': 0.00014886556753181308, 'samples': 18359232, 'steps': 95620, 'loss/train': 4.4787821769714355} 08/31/2021 06:32:41 - INFO - __main__ - Step 95622: {'lr': 0.00014886071442380986, 'samples': 18359424, 'steps': 95621, 'loss/train': 1.1723122596740723} 08/31/2021 06:32:42 - INFO - __main__ - Step 95623: {'lr': 0.00014885586136137842, 'samples': 18359616, 'steps': 95622, 'loss/train': 1.493640422821045} 08/31/2021 06:32:43 - INFO - __main__ - Step 95624: {'lr': 0.00014885100834452099, 'samples': 18359808, 'steps': 95623, 'loss/train': 1.1753677129745483} 08/31/2021 06:32:43 - INFO - __main__ - Step 95625: {'lr': 0.00014884615537323964, 'samples': 18360000, 'steps': 95624, 'loss/train': 0.23772184550762177} 08/31/2021 06:32:43 - INFO - __main__ - Step 95626: {'lr': 0.0001488413024475367, 'samples': 18360192, 'steps': 95625, 'loss/train': 1.5219017267227173} 08/31/2021 06:32:44 - INFO - __main__ - Step 95627: {'lr': 0.00014883644956741428, 'samples': 18360384, 'steps': 95626, 'loss/train': 1.21884024143219} 08/31/2021 06:32:45 - INFO - __main__ - Step 95628: {'lr': 0.00014883159673287463, 'samples': 18360576, 'steps': 95627, 'loss/train': 1.0245347023010254} 08/31/2021 06:32:46 - INFO - __main__ - Step 95629: {'lr': 0.00014882674394391988, 'samples': 18360768, 'steps': 95628, 'loss/train': 1.0525288581848145} 08/31/2021 06:32:46 - INFO - __main__ - Step 95630: {'lr': 0.00014882189120055226, 'samples': 18360960, 'steps': 95629, 'loss/train': 1.1020058393478394} 08/31/2021 06:32:46 - INFO - __main__ - Step 95631: {'lr': 0.00014881703850277392, 'samples': 18361152, 'steps': 95630, 'loss/train': 0.7168383002281189} 08/31/2021 06:32:47 - INFO - __main__ - Step 95632: {'lr': 0.00014881218585058707, 'samples': 18361344, 'steps': 95631, 'loss/train': 0.9400380849838257} 08/31/2021 06:32:48 - INFO - __main__ - Step 95633: {'lr': 0.00014880733324399394, 'samples': 18361536, 'steps': 95632, 'loss/train': 2.143404006958008} 08/31/2021 06:32:49 - INFO - __main__ - Step 95634: {'lr': 0.00014880248068299657, 'samples': 18361728, 'steps': 95633, 'loss/train': 1.0800808668136597} 08/31/2021 06:32:49 - INFO - __main__ - Step 95635: {'lr': 0.00014879762816759728, 'samples': 18361920, 'steps': 95634, 'loss/train': 1.372678518295288} 08/31/2021 06:32:49 - INFO - __main__ - Step 95636: {'lr': 0.0001487927756977982, 'samples': 18362112, 'steps': 95635, 'loss/train': 1.2184741497039795} 08/31/2021 06:32:50 - INFO - __main__ - Step 95637: {'lr': 0.00014878792327360156, 'samples': 18362304, 'steps': 95636, 'loss/train': 1.3284144401550293} 08/31/2021 06:32:51 - INFO - __main__ - Step 95638: {'lr': 0.00014878307089500952, 'samples': 18362496, 'steps': 95637, 'loss/train': 1.7135851383209229} 08/31/2021 06:32:52 - INFO - __main__ - Step 95639: {'lr': 0.0001487782185620243, 'samples': 18362688, 'steps': 95638, 'loss/train': 0.8327696323394775} 08/31/2021 06:32:52 - INFO - __main__ - Step 95640: {'lr': 0.000148773366274648, 'samples': 18362880, 'steps': 95639, 'loss/train': 0.8723026514053345} 08/31/2021 06:32:52 - INFO - __main__ - Step 95641: {'lr': 0.00014876851403288282, 'samples': 18363072, 'steps': 95640, 'loss/train': 1.7435293197631836} 08/31/2021 06:32:53 - INFO - __main__ - Step 95642: {'lr': 0.00014876366183673106, 'samples': 18363264, 'steps': 95641, 'loss/train': 2.5042154788970947} 08/31/2021 06:32:54 - INFO - __main__ - Step 95643: {'lr': 0.0001487588096861948, 'samples': 18363456, 'steps': 95642, 'loss/train': 1.1735726594924927} 08/31/2021 06:32:55 - INFO - __main__ - Step 95644: {'lr': 0.0001487539575812763, 'samples': 18363648, 'steps': 95643, 'loss/train': 0.75102299451828} 08/31/2021 06:32:55 - INFO - __main__ - Step 95645: {'lr': 0.00014874910552197768, 'samples': 18363840, 'steps': 95644, 'loss/train': 0.8126972913742065} 08/31/2021 06:32:55 - INFO - __main__ - Step 95646: {'lr': 0.00014874425350830113, 'samples': 18364032, 'steps': 95645, 'loss/train': 1.1514129638671875} 08/31/2021 06:32:56 - INFO - __main__ - Step 95647: {'lr': 0.00014873940154024883, 'samples': 18364224, 'steps': 95646, 'loss/train': 2.7996151447296143} 08/31/2021 06:32:56 - INFO - __main__ - Step 95648: {'lr': 0.00014873454961782304, 'samples': 18364416, 'steps': 95647, 'loss/train': 1.0262244939804077} 08/31/2021 06:32:58 - INFO - __main__ - Step 95649: {'lr': 0.00014872969774102588, 'samples': 18364608, 'steps': 95648, 'loss/train': 1.2184557914733887} 08/31/2021 06:32:59 - INFO - __main__ - Step 95650: {'lr': 0.00014872484590985956, 'samples': 18364800, 'steps': 95649, 'loss/train': 0.8929154872894287} 08/31/2021 06:32:59 - INFO - __main__ - Step 95651: {'lr': 0.0001487199941243263, 'samples': 18364992, 'steps': 95650, 'loss/train': 0.9095070958137512} 08/31/2021 06:33:00 - INFO - __main__ - Step 95652: {'lr': 0.0001487151423844282, 'samples': 18365184, 'steps': 95651, 'loss/train': 1.0305495262145996} 08/31/2021 06:33:00 - INFO - __main__ - Step 95653: {'lr': 0.0001487102906901675, 'samples': 18365376, 'steps': 95652, 'loss/train': 1.372849941253662} 08/31/2021 06:33:02 - INFO - __main__ - Step 95654: {'lr': 0.00014870543904154637, 'samples': 18365568, 'steps': 95653, 'loss/train': 1.576798677444458} 08/31/2021 06:33:02 - INFO - __main__ - Step 95655: {'lr': 0.00014870058743856706, 'samples': 18365760, 'steps': 95654, 'loss/train': 1.3637709617614746} 08/31/2021 06:33:02 - INFO - __main__ - Step 95656: {'lr': 0.0001486957358812317, 'samples': 18365952, 'steps': 95655, 'loss/train': 1.3039813041687012} 08/31/2021 06:33:03 - INFO - __main__ - Step 95657: {'lr': 0.00014869088436954243, 'samples': 18366144, 'steps': 95656, 'loss/train': 1.141339898109436} 08/31/2021 06:33:03 - INFO - __main__ - Step 95658: {'lr': 0.00014868603290350146, 'samples': 18366336, 'steps': 95657, 'loss/train': 0.4120793044567108} 08/31/2021 06:33:05 - INFO - __main__ - Step 95659: {'lr': 0.00014868118148311105, 'samples': 18366528, 'steps': 95658, 'loss/train': 1.1843314170837402} 08/31/2021 06:33:05 - INFO - __main__ - Step 95660: {'lr': 0.00014867633010837335, 'samples': 18366720, 'steps': 95659, 'loss/train': 1.456518292427063} 08/31/2021 06:33:06 - INFO - __main__ - Step 95661: {'lr': 0.00014867147877929048, 'samples': 18366912, 'steps': 95660, 'loss/train': 1.3418362140655518} 08/31/2021 06:33:06 - INFO - __main__ - Step 95662: {'lr': 0.0001486666274958647, 'samples': 18367104, 'steps': 95661, 'loss/train': 1.6478185653686523} 08/31/2021 06:33:06 - INFO - __main__ - Step 95663: {'lr': 0.00014866177625809818, 'samples': 18367296, 'steps': 95662, 'loss/train': 1.525752067565918} 08/31/2021 06:33:08 - INFO - __main__ - Step 95664: {'lr': 0.00014865692506599312, 'samples': 18367488, 'steps': 95663, 'loss/train': 1.3867254257202148} 08/31/2021 06:33:09 - INFO - __main__ - Step 95665: {'lr': 0.0001486520739195517, 'samples': 18367680, 'steps': 95664, 'loss/train': 1.5578073263168335} 08/31/2021 06:33:09 - INFO - __main__ - Step 95666: {'lr': 0.00014864722281877609, 'samples': 18367872, 'steps': 95665, 'loss/train': 1.2862263917922974} 08/31/2021 06:33:09 - INFO - __main__ - Step 95667: {'lr': 0.0001486423717636684, 'samples': 18368064, 'steps': 95666, 'loss/train': 1.3635348081588745} 08/31/2021 06:33:10 - INFO - __main__ - Step 95668: {'lr': 0.00014863752075423094, 'samples': 18368256, 'steps': 95667, 'loss/train': 1.5046583414077759} 08/31/2021 06:33:10 - INFO - __main__ - Step 95669: {'lr': 0.00014863266979046582, 'samples': 18368448, 'steps': 95668, 'loss/train': 1.7755920886993408} 08/31/2021 06:33:12 - INFO - __main__ - Step 95670: {'lr': 0.00014862781887237532, 'samples': 18368640, 'steps': 95669, 'loss/train': 0.020013801753520966} 08/31/2021 06:33:12 - INFO - __main__ - Step 95671: {'lr': 0.0001486229679999615, 'samples': 18368832, 'steps': 95670, 'loss/train': 0.7665825486183167} 08/31/2021 06:33:12 - INFO - __main__ - Step 95672: {'lr': 0.0001486181171732266, 'samples': 18369024, 'steps': 95671, 'loss/train': 0.7315759062767029} 08/31/2021 06:33:13 - INFO - __main__ - Step 95673: {'lr': 0.00014861326639217283, 'samples': 18369216, 'steps': 95672, 'loss/train': 0.7942467331886292} 08/31/2021 06:33:13 - INFO - __main__ - Step 95674: {'lr': 0.00014860841565680235, 'samples': 18369408, 'steps': 95673, 'loss/train': 1.6201014518737793} 08/31/2021 06:33:13 - INFO - __main__ - Step 95675: {'lr': 0.0001486035649671174, 'samples': 18369600, 'steps': 95674, 'loss/train': 1.1730879545211792} 08/31/2021 06:33:15 - INFO - __main__ - Step 95676: {'lr': 0.00014859871432312005, 'samples': 18369792, 'steps': 95675, 'loss/train': 0.590910017490387} 08/31/2021 06:33:15 - INFO - __main__ - Step 95677: {'lr': 0.0001485938637248126, 'samples': 18369984, 'steps': 95676, 'loss/train': 0.09638071805238724} 08/31/2021 06:33:16 - INFO - __main__ - Step 95678: {'lr': 0.00014858901317219727, 'samples': 18370176, 'steps': 95677, 'loss/train': 1.0221409797668457} 08/31/2021 06:33:16 - INFO - __main__ - Step 95679: {'lr': 0.00014858416266527608, 'samples': 18370368, 'steps': 95678, 'loss/train': 0.7343573570251465} 08/31/2021 06:33:16 - INFO - __main__ - Step 95680: {'lr': 0.0001485793122040513, 'samples': 18370560, 'steps': 95679, 'loss/train': 0.5987794995307922} 08/31/2021 06:33:18 - INFO - __main__ - Step 95681: {'lr': 0.0001485744617885251, 'samples': 18370752, 'steps': 95680, 'loss/train': 0.906184196472168} 08/31/2021 06:33:18 - INFO - __main__ - Step 95682: {'lr': 0.00014856961141869967, 'samples': 18370944, 'steps': 95681, 'loss/train': 1.0294774770736694} 08/31/2021 06:33:19 - INFO - __main__ - Step 95683: {'lr': 0.00014856476109457726, 'samples': 18371136, 'steps': 95682, 'loss/train': 1.2361162900924683} 08/31/2021 06:33:19 - INFO - __main__ - Step 95684: {'lr': 0.00014855991081616, 'samples': 18371328, 'steps': 95683, 'loss/train': 1.4303916692733765} 08/31/2021 06:33:19 - INFO - __main__ - Step 95685: {'lr': 0.00014855506058345002, 'samples': 18371520, 'steps': 95684, 'loss/train': 1.3891814947128296} 08/31/2021 06:33:21 - INFO - __main__ - Step 95686: {'lr': 0.00014855021039644962, 'samples': 18371712, 'steps': 95685, 'loss/train': 2.008589506149292} 08/31/2021 06:33:22 - INFO - __main__ - Step 95687: {'lr': 0.00014854536025516092, 'samples': 18371904, 'steps': 95686, 'loss/train': 1.461867094039917} 08/31/2021 06:33:22 - INFO - __main__ - Step 95688: {'lr': 0.00014854051015958608, 'samples': 18372096, 'steps': 95687, 'loss/train': 1.1212371587753296} 08/31/2021 06:33:22 - INFO - __main__ - Step 95689: {'lr': 0.00014853566010972736, 'samples': 18372288, 'steps': 95688, 'loss/train': 1.068069577217102} 08/31/2021 06:33:23 - INFO - __main__ - Step 95690: {'lr': 0.00014853081010558688, 'samples': 18372480, 'steps': 95689, 'loss/train': 1.124505639076233} 08/31/2021 06:33:24 - INFO - __main__ - Step 95691: {'lr': 0.00014852596014716695, 'samples': 18372672, 'steps': 95690, 'loss/train': 0.9148510098457336} 08/31/2021 06:33:25 - INFO - __main__ - Step 95692: {'lr': 0.00014852111023446957, 'samples': 18372864, 'steps': 95691, 'loss/train': 1.0352985858917236} 08/31/2021 06:33:25 - INFO - __main__ - Step 95693: {'lr': 0.000148516260367497, 'samples': 18373056, 'steps': 95692, 'loss/train': 1.171322226524353} 08/31/2021 06:33:25 - INFO - __main__ - Step 95694: {'lr': 0.00014851141054625144, 'samples': 18373248, 'steps': 95693, 'loss/train': 0.9485490918159485} 08/31/2021 06:33:26 - INFO - __main__ - Step 95695: {'lr': 0.0001485065607707351, 'samples': 18373440, 'steps': 95694, 'loss/train': 5.420644283294678} 08/31/2021 06:33:26 - INFO - __main__ - Step 95696: {'lr': 0.00014850171104095012, 'samples': 18373632, 'steps': 95695, 'loss/train': 0.8298525214195251} 08/31/2021 06:33:28 - INFO - __main__ - Step 95697: {'lr': 0.0001484968613568987, 'samples': 18373824, 'steps': 95696, 'loss/train': 1.043707013130188} 08/31/2021 06:33:28 - INFO - __main__ - Step 95698: {'lr': 0.00014849201171858301, 'samples': 18374016, 'steps': 95697, 'loss/train': 0.6953727006912231} 08/31/2021 06:33:28 - INFO - __main__ - Step 95699: {'lr': 0.00014848716212600526, 'samples': 18374208, 'steps': 95698, 'loss/train': 1.473447561264038} 08/31/2021 06:33:29 - INFO - __main__ - Step 95700: {'lr': 0.00014848231257916767, 'samples': 18374400, 'steps': 95699, 'loss/train': 0.706809937953949} 08/31/2021 06:33:29 - INFO - __main__ - Step 95701: {'lr': 0.00014847746307807233, 'samples': 18374592, 'steps': 95700, 'loss/train': 1.0358400344848633} 08/31/2021 06:33:31 - INFO - __main__ - Step 95702: {'lr': 0.0001484726136227215, 'samples': 18374784, 'steps': 95701, 'loss/train': 1.2181732654571533} 08/31/2021 06:33:31 - INFO - __main__ - Step 95703: {'lr': 0.00014846776421311738, 'samples': 18374976, 'steps': 95702, 'loss/train': 0.9946113228797913} 08/31/2021 06:33:32 - INFO - __main__ - Step 95704: {'lr': 0.00014846291484926205, 'samples': 18375168, 'steps': 95703, 'loss/train': 1.9540339708328247} 08/31/2021 06:33:32 - INFO - __main__ - Step 95705: {'lr': 0.0001484580655311579, 'samples': 18375360, 'steps': 95704, 'loss/train': 1.2925996780395508} 08/31/2021 06:33:32 - INFO - __main__ - Step 95706: {'lr': 0.00014845321625880687, 'samples': 18375552, 'steps': 95705, 'loss/train': 1.3133635520935059} 08/31/2021 06:33:34 - INFO - __main__ - Step 95707: {'lr': 0.00014844836703221126, 'samples': 18375744, 'steps': 95706, 'loss/train': 0.6572436094284058} 08/31/2021 06:33:35 - INFO - __main__ - Step 95708: {'lr': 0.00014844351785137325, 'samples': 18375936, 'steps': 95707, 'loss/train': 1.1583616733551025} 08/31/2021 06:33:35 - INFO - __main__ - Step 95709: {'lr': 0.00014843866871629502, 'samples': 18376128, 'steps': 95708, 'loss/train': 1.2522214651107788} 08/31/2021 06:33:35 - INFO - __main__ - Step 95710: {'lr': 0.00014843381962697876, 'samples': 18376320, 'steps': 95709, 'loss/train': 1.3269109725952148} 08/31/2021 06:33:36 - INFO - __main__ - Step 95711: {'lr': 0.00014842897058342663, 'samples': 18376512, 'steps': 95710, 'loss/train': 0.5131421685218811} 08/31/2021 06:33:37 - INFO - __main__ - Step 95712: {'lr': 0.0001484241215856409, 'samples': 18376704, 'steps': 95711, 'loss/train': 1.8602769374847412} 08/31/2021 06:33:38 - INFO - __main__ - Step 95713: {'lr': 0.00014841927263362366, 'samples': 18376896, 'steps': 95712, 'loss/train': 0.027275361120700836} 08/31/2021 06:33:38 - INFO - __main__ - Step 95714: {'lr': 0.0001484144237273771, 'samples': 18377088, 'steps': 95713, 'loss/train': 0.49399206042289734} 08/31/2021 06:33:39 - INFO - __main__ - Step 95715: {'lr': 0.00014840957486690346, 'samples': 18377280, 'steps': 95714, 'loss/train': 1.492231845855713} 08/31/2021 06:33:39 - INFO - __main__ - Step 95716: {'lr': 0.0001484047260522049, 'samples': 18377472, 'steps': 95715, 'loss/train': 1.491487979888916} 08/31/2021 06:33:41 - INFO - __main__ - Step 95717: {'lr': 0.00014839987728328357, 'samples': 18377664, 'steps': 95716, 'loss/train': 1.0071898698806763} 08/31/2021 06:33:41 - INFO - __main__ - Step 95718: {'lr': 0.00014839502856014183, 'samples': 18377856, 'steps': 95717, 'loss/train': 1.017519474029541} 08/31/2021 06:33:41 - INFO - __main__ - Step 95719: {'lr': 0.0001483901798827816, 'samples': 18378048, 'steps': 95718, 'loss/train': 1.290697455406189} 08/31/2021 06:33:42 - INFO - __main__ - Step 95720: {'lr': 0.00014838533125120521, 'samples': 18378240, 'steps': 95719, 'loss/train': 0.9920392036437988} 08/31/2021 06:33:42 - INFO - __main__ - Step 95721: {'lr': 0.0001483804826654148, 'samples': 18378432, 'steps': 95720, 'loss/train': 1.1146165132522583} 08/31/2021 06:33:44 - INFO - __main__ - Step 95722: {'lr': 0.0001483756341254126, 'samples': 18378624, 'steps': 95721, 'loss/train': 1.6686347723007202} 08/31/2021 06:33:44 - INFO - __main__ - Step 95723: {'lr': 0.00014837078563120074, 'samples': 18378816, 'steps': 95722, 'loss/train': 0.9598656892776489} 08/31/2021 06:33:44 - INFO - __main__ - Step 95724: {'lr': 0.00014836593718278146, 'samples': 18379008, 'steps': 95723, 'loss/train': 0.6460806727409363} 08/31/2021 06:33:45 - INFO - __main__ - Step 95725: {'lr': 0.0001483610887801569, 'samples': 18379200, 'steps': 95724, 'loss/train': 1.1564027070999146} 08/31/2021 06:33:45 - INFO - __main__ - Step 95726: {'lr': 0.0001483562404233293, 'samples': 18379392, 'steps': 95725, 'loss/train': 0.02451496198773384} 08/31/2021 06:33:45 - INFO - __main__ - Step 95727: {'lr': 0.00014835139211230076, 'samples': 18379584, 'steps': 95726, 'loss/train': 0.783251166343689} 08/31/2021 06:33:47 - INFO - __main__ - Step 95728: {'lr': 0.00014834654384707351, 'samples': 18379776, 'steps': 95727, 'loss/train': 0.8379067778587341} 08/31/2021 06:33:48 - INFO - __main__ - Step 95729: {'lr': 0.0001483416956276498, 'samples': 18379968, 'steps': 95728, 'loss/train': 1.2536888122558594} 08/31/2021 06:33:48 - INFO - __main__ - Step 95730: {'lr': 0.0001483368474540317, 'samples': 18380160, 'steps': 95729, 'loss/train': 0.025603706017136574} 08/31/2021 06:33:48 - INFO - __main__ - Step 95731: {'lr': 0.0001483319993262215, 'samples': 18380352, 'steps': 95730, 'loss/train': 0.03563975915312767} 08/31/2021 06:33:49 - INFO - __main__ - Step 95732: {'lr': 0.00014832715124422138, 'samples': 18380544, 'steps': 95731, 'loss/train': 0.7949602007865906} 08/31/2021 06:33:51 - INFO - __main__ - Step 95733: {'lr': 0.0001483223032080334, 'samples': 18380736, 'steps': 95732, 'loss/train': 0.5722035765647888} 08/31/2021 06:33:51 - INFO - __main__ - Step 95734: {'lr': 0.00014831745521765981, 'samples': 18380928, 'steps': 95733, 'loss/train': 0.6832880973815918} 08/31/2021 06:33:52 - INFO - __main__ - Step 95735: {'lr': 0.00014831260727310284, 'samples': 18381120, 'steps': 95734, 'loss/train': 1.0400567054748535} 08/31/2021 06:33:52 - INFO - __main__ - Step 95736: {'lr': 0.0001483077593743646, 'samples': 18381312, 'steps': 95735, 'loss/train': 1.7029938697814941} 08/31/2021 06:33:52 - INFO - __main__ - Step 95737: {'lr': 0.0001483029115214473, 'samples': 18381504, 'steps': 95736, 'loss/train': 1.1397731304168701} 08/31/2021 06:33:53 - INFO - __main__ - Step 95738: {'lr': 0.0001482980637143532, 'samples': 18381696, 'steps': 95737, 'loss/train': 1.0587822198867798} 08/31/2021 06:33:53 - INFO - __main__ - Step 95739: {'lr': 0.00014829321595308438, 'samples': 18381888, 'steps': 95738, 'loss/train': 0.018977772444486618} 08/31/2021 06:33:55 - INFO - __main__ - Step 95740: {'lr': 0.00014828836823764307, 'samples': 18382080, 'steps': 95739, 'loss/train': 0.10388006269931793} 08/31/2021 06:33:55 - INFO - __main__ - Step 95741: {'lr': 0.00014828352056803145, 'samples': 18382272, 'steps': 95740, 'loss/train': 1.5328779220581055} 08/31/2021 06:33:55 - INFO - __main__ - Step 95742: {'lr': 0.00014827867294425173, 'samples': 18382464, 'steps': 95741, 'loss/train': 0.808021068572998} 08/31/2021 06:33:56 - INFO - __main__ - Step 95743: {'lr': 0.00014827382536630607, 'samples': 18382656, 'steps': 95742, 'loss/train': 0.6696256399154663} 08/31/2021 06:33:56 - INFO - __main__ - Step 95744: {'lr': 0.00014826897783419663, 'samples': 18382848, 'steps': 95743, 'loss/train': 1.2861465215682983} 08/31/2021 06:33:58 - INFO - __main__ - Step 95745: {'lr': 0.00014826413034792573, 'samples': 18383040, 'steps': 95744, 'loss/train': 1.2044909000396729} 08/31/2021 06:33:58 - INFO - __main__ - Step 95746: {'lr': 0.00014825928290749534, 'samples': 18383232, 'steps': 95745, 'loss/train': 0.1635487824678421} 08/31/2021 06:33:58 - INFO - __main__ - Step 95747: {'lr': 0.00014825443551290775, 'samples': 18383424, 'steps': 95746, 'loss/train': 2.510240316390991} 08/31/2021 06:33:59 - INFO - __main__ - Step 95748: {'lr': 0.00014824958816416517, 'samples': 18383616, 'steps': 95747, 'loss/train': 1.0054126977920532} 08/31/2021 06:33:59 - INFO - __main__ - Step 95749: {'lr': 0.00014824474086126972, 'samples': 18383808, 'steps': 95748, 'loss/train': 0.8991132974624634} 08/31/2021 06:34:01 - INFO - __main__ - Step 95750: {'lr': 0.00014823989360422362, 'samples': 18384000, 'steps': 95749, 'loss/train': 0.49917319416999817} 08/31/2021 06:34:01 - INFO - __main__ - Step 95751: {'lr': 0.00014823504639302905, 'samples': 18384192, 'steps': 95750, 'loss/train': 0.8723515272140503} 08/31/2021 06:34:01 - INFO - __main__ - Step 95752: {'lr': 0.0001482301992276882, 'samples': 18384384, 'steps': 95751, 'loss/train': 1.608994483947754} 08/31/2021 06:34:02 - INFO - __main__ - Step 95753: {'lr': 0.00014822535210820326, 'samples': 18384576, 'steps': 95752, 'loss/train': 0.7565979957580566} 08/31/2021 06:34:02 - INFO - __main__ - Step 95754: {'lr': 0.0001482205050345764, 'samples': 18384768, 'steps': 95753, 'loss/train': 1.6456881761550903} 08/31/2021 06:34:04 - INFO - __main__ - Step 95755: {'lr': 0.00014821565800680984, 'samples': 18384960, 'steps': 95754, 'loss/train': 0.9907920956611633} 08/31/2021 06:34:04 - INFO - __main__ - Step 95756: {'lr': 0.00014821081102490575, 'samples': 18385152, 'steps': 95755, 'loss/train': 1.3732454776763916} 08/31/2021 06:34:04 - INFO - __main__ - Step 95757: {'lr': 0.00014820596408886627, 'samples': 18385344, 'steps': 95756, 'loss/train': 1.0177243947982788} 08/31/2021 06:34:05 - INFO - __main__ - Step 95758: {'lr': 0.00014820111719869358, 'samples': 18385536, 'steps': 95757, 'loss/train': 1.5261064767837524} 08/31/2021 06:34:05 - INFO - __main__ - Step 95759: {'lr': 0.00014819627035439, 'samples': 18385728, 'steps': 95758, 'loss/train': 0.9923175573348999} 08/31/2021 06:34:07 - INFO - __main__ - Step 95760: {'lr': 0.0001481914235559575, 'samples': 18385920, 'steps': 95759, 'loss/train': 1.26310133934021} 08/31/2021 06:34:08 - INFO - __main__ - Step 95761: {'lr': 0.0001481865768033984, 'samples': 18386112, 'steps': 95760, 'loss/train': 0.21143697202205658} 08/31/2021 06:34:08 - INFO - __main__ - Step 95762: {'lr': 0.00014818173009671485, 'samples': 18386304, 'steps': 95761, 'loss/train': 1.4208767414093018} 08/31/2021 06:34:09 - INFO - __main__ - Step 95763: {'lr': 0.00014817688343590903, 'samples': 18386496, 'steps': 95762, 'loss/train': 2.0860891342163086} 08/31/2021 06:34:09 - INFO - __main__ - Step 95764: {'lr': 0.00014817203682098318, 'samples': 18386688, 'steps': 95763, 'loss/train': 0.9950948357582092} 08/31/2021 06:34:10 - INFO - __main__ - Step 95765: {'lr': 0.00014816719025193939, 'samples': 18386880, 'steps': 95764, 'loss/train': 0.798660933971405} 08/31/2021 06:34:11 - INFO - __main__ - Step 95766: {'lr': 0.0001481623437287799, 'samples': 18387072, 'steps': 95765, 'loss/train': 1.8667653799057007} 08/31/2021 06:34:11 - INFO - __main__ - Step 95767: {'lr': 0.00014815749725150695, 'samples': 18387264, 'steps': 95766, 'loss/train': 1.4190880060195923} 08/31/2021 06:34:12 - INFO - __main__ - Step 95768: {'lr': 0.00014815265082012265, 'samples': 18387456, 'steps': 95767, 'loss/train': 1.1733925342559814} 08/31/2021 06:34:12 - INFO - __main__ - Step 95769: {'lr': 0.00014814780443462913, 'samples': 18387648, 'steps': 95768, 'loss/train': 0.85313481092453} 08/31/2021 06:34:14 - INFO - __main__ - Step 95770: {'lr': 0.00014814295809502864, 'samples': 18387840, 'steps': 95769, 'loss/train': 1.287460207939148} 08/31/2021 06:34:14 - INFO - __main__ - Step 95771: {'lr': 0.0001481381118013234, 'samples': 18388032, 'steps': 95770, 'loss/train': 0.07682032883167267} 08/31/2021 06:34:15 - INFO - __main__ - Step 95772: {'lr': 0.0001481332655535156, 'samples': 18388224, 'steps': 95771, 'loss/train': 1.1197757720947266} 08/31/2021 06:34:15 - INFO - __main__ - Step 95773: {'lr': 0.00014812841935160731, 'samples': 18388416, 'steps': 95772, 'loss/train': 0.35079464316368103} 08/31/2021 06:34:15 - INFO - __main__ - Step 95774: {'lr': 0.00014812357319560077, 'samples': 18388608, 'steps': 95773, 'loss/train': 1.1467556953430176} 08/31/2021 06:34:17 - INFO - __main__ - Step 95775: {'lr': 0.00014811872708549823, 'samples': 18388800, 'steps': 95774, 'loss/train': 1.0485488176345825} 08/31/2021 06:34:17 - INFO - __main__ - Step 95776: {'lr': 0.00014811388102130177, 'samples': 18388992, 'steps': 95775, 'loss/train': 1.2799005508422852} 08/31/2021 06:34:17 - INFO - __main__ - Step 95777: {'lr': 0.00014810903500301365, 'samples': 18389184, 'steps': 95776, 'loss/train': 1.511191487312317} 08/31/2021 06:34:18 - INFO - __main__ - Step 95778: {'lr': 0.00014810418903063604, 'samples': 18389376, 'steps': 95777, 'loss/train': 1.2795439958572388} 08/31/2021 06:34:18 - INFO - __main__ - Step 95779: {'lr': 0.00014809934310417108, 'samples': 18389568, 'steps': 95778, 'loss/train': 1.2084462642669678} 08/31/2021 06:34:20 - INFO - __main__ - Step 95780: {'lr': 0.000148094497223621, 'samples': 18389760, 'steps': 95779, 'loss/train': 1.5945450067520142} 08/31/2021 06:34:20 - INFO - __main__ - Step 95781: {'lr': 0.00014808965138898795, 'samples': 18389952, 'steps': 95780, 'loss/train': 1.2685059309005737} 08/31/2021 06:34:21 - INFO - __main__ - Step 95782: {'lr': 0.00014808480560027414, 'samples': 18390144, 'steps': 95781, 'loss/train': 0.7629892230033875} 08/31/2021 06:34:21 - INFO - __main__ - Step 95783: {'lr': 0.00014807995985748174, 'samples': 18390336, 'steps': 95782, 'loss/train': 0.04510067030787468} 08/31/2021 06:34:21 - INFO - __main__ - Step 95784: {'lr': 0.0001480751141606129, 'samples': 18390528, 'steps': 95783, 'loss/train': 1.4025458097457886} 08/31/2021 06:34:22 - INFO - __main__ - Step 95785: {'lr': 0.00014807026850966994, 'samples': 18390720, 'steps': 95784, 'loss/train': 1.3210647106170654} 08/31/2021 06:34:23 - INFO - __main__ - Step 95786: {'lr': 0.0001480654229046549, 'samples': 18390912, 'steps': 95785, 'loss/train': 0.9654977917671204} 08/31/2021 06:34:24 - INFO - __main__ - Step 95787: {'lr': 0.00014806057734557, 'samples': 18391104, 'steps': 95786, 'loss/train': 0.6116585731506348} 08/31/2021 06:34:24 - INFO - __main__ - Step 95788: {'lr': 0.00014805573183241738, 'samples': 18391296, 'steps': 95787, 'loss/train': 0.7209625244140625} 08/31/2021 06:34:25 - INFO - __main__ - Step 95789: {'lr': 0.00014805088636519938, 'samples': 18391488, 'steps': 95788, 'loss/train': 1.1709203720092773} 08/31/2021 06:34:25 - INFO - __main__ - Step 95790: {'lr': 0.00014804604094391803, 'samples': 18391680, 'steps': 95789, 'loss/train': 1.2122340202331543} 08/31/2021 06:34:26 - INFO - __main__ - Step 95791: {'lr': 0.00014804119556857554, 'samples': 18391872, 'steps': 95790, 'loss/train': 1.675599217414856} 08/31/2021 06:34:27 - INFO - __main__ - Step 95792: {'lr': 0.0001480363502391741, 'samples': 18392064, 'steps': 95791, 'loss/train': 0.863523542881012} 08/31/2021 06:34:27 - INFO - __main__ - Step 95793: {'lr': 0.00014803150495571593, 'samples': 18392256, 'steps': 95792, 'loss/train': 0.742881715297699} 08/31/2021 06:34:28 - INFO - __main__ - Step 95794: {'lr': 0.00014802665971820318, 'samples': 18392448, 'steps': 95793, 'loss/train': 1.1671355962753296} 08/31/2021 06:34:28 - INFO - __main__ - Step 95795: {'lr': 0.00014802181452663803, 'samples': 18392640, 'steps': 95794, 'loss/train': 1.1516822576522827} 08/31/2021 06:34:29 - INFO - __main__ - Step 95796: {'lr': 0.00014801696938102272, 'samples': 18392832, 'steps': 95795, 'loss/train': 1.0017229318618774} 08/31/2021 06:34:30 - INFO - __main__ - Step 95797: {'lr': 0.00014801212428135934, 'samples': 18393024, 'steps': 95796, 'loss/train': 1.6209381818771362} 08/31/2021 06:34:30 - INFO - __main__ - Step 95798: {'lr': 0.00014800727922765016, 'samples': 18393216, 'steps': 95797, 'loss/train': 1.0037426948547363} 08/31/2021 06:34:31 - INFO - __main__ - Step 95799: {'lr': 0.00014800243421989734, 'samples': 18393408, 'steps': 95798, 'loss/train': 1.2541414499282837} 08/31/2021 06:34:31 - INFO - __main__ - Step 95800: {'lr': 0.00014799758925810309, 'samples': 18393600, 'steps': 95799, 'loss/train': 1.3029882907867432} 08/31/2021 06:34:33 - INFO - __main__ - Step 95801: {'lr': 0.0001479927443422695, 'samples': 18393792, 'steps': 95800, 'loss/train': 1.0926103591918945} 08/31/2021 06:34:33 - INFO - __main__ - Step 95802: {'lr': 0.00014798789947239878, 'samples': 18393984, 'steps': 95801, 'loss/train': 1.5265345573425293} 08/31/2021 06:34:33 - INFO - __main__ - Step 95803: {'lr': 0.00014798305464849316, 'samples': 18394176, 'steps': 95802, 'loss/train': 0.036796871572732925} 08/31/2021 06:34:34 - INFO - __main__ - Step 95804: {'lr': 0.00014797820987055477, 'samples': 18394368, 'steps': 95803, 'loss/train': 1.2198749780654907} 08/31/2021 06:34:34 - INFO - __main__ - Step 95805: {'lr': 0.00014797336513858584, 'samples': 18394560, 'steps': 95804, 'loss/train': 1.1081534624099731} 08/31/2021 06:34:36 - INFO - __main__ - Step 95806: {'lr': 0.00014796852045258855, 'samples': 18394752, 'steps': 95805, 'loss/train': 1.33468759059906} 08/31/2021 06:34:36 - INFO - __main__ - Step 95807: {'lr': 0.00014796367581256507, 'samples': 18394944, 'steps': 95806, 'loss/train': 1.0533126592636108} 08/31/2021 06:34:36 - INFO - __main__ - Step 95808: {'lr': 0.00014795883121851755, 'samples': 18395136, 'steps': 95807, 'loss/train': 1.0475643873214722} 08/31/2021 06:34:37 - INFO - __main__ - Step 95809: {'lr': 0.00014795398667044824, 'samples': 18395328, 'steps': 95808, 'loss/train': 0.9405770301818848} 08/31/2021 06:34:37 - INFO - __main__ - Step 95810: {'lr': 0.00014794914216835928, 'samples': 18395520, 'steps': 95809, 'loss/train': 0.12304714322090149} 08/31/2021 06:34:39 - INFO - __main__ - Step 95811: {'lr': 0.00014794429771225289, 'samples': 18395712, 'steps': 95810, 'loss/train': 1.483185052871704} 08/31/2021 06:34:40 - INFO - __main__ - Step 95812: {'lr': 0.00014793945330213127, 'samples': 18395904, 'steps': 95811, 'loss/train': 0.9795758724212646} 08/31/2021 06:34:40 - INFO - __main__ - Step 95813: {'lr': 0.00014793460893799647, 'samples': 18396096, 'steps': 95812, 'loss/train': 0.2537054717540741} 08/31/2021 06:34:40 - INFO - __main__ - Step 95814: {'lr': 0.0001479297646198508, 'samples': 18396288, 'steps': 95813, 'loss/train': 1.4996147155761719} 08/31/2021 06:34:41 - INFO - __main__ - Step 95815: {'lr': 0.00014792492034769637, 'samples': 18396480, 'steps': 95814, 'loss/train': 0.4063628315925598} 08/31/2021 06:34:42 - INFO - __main__ - Step 95816: {'lr': 0.0001479200761215354, 'samples': 18396672, 'steps': 95815, 'loss/train': 1.3986304998397827} 08/31/2021 06:34:43 - INFO - __main__ - Step 95817: {'lr': 0.00014791523194137006, 'samples': 18396864, 'steps': 95816, 'loss/train': 1.1354085206985474} 08/31/2021 06:34:43 - INFO - __main__ - Step 95818: {'lr': 0.00014791038780720257, 'samples': 18397056, 'steps': 95817, 'loss/train': 0.6008878946304321} 08/31/2021 06:34:43 - INFO - __main__ - Step 95819: {'lr': 0.00014790554371903503, 'samples': 18397248, 'steps': 95818, 'loss/train': 0.2519949972629547} 08/31/2021 06:34:44 - INFO - __main__ - Step 95820: {'lr': 0.00014790069967686974, 'samples': 18397440, 'steps': 95819, 'loss/train': 1.2448439598083496} 08/31/2021 06:34:44 - INFO - __main__ - Step 95821: {'lr': 0.0001478958556807088, 'samples': 18397632, 'steps': 95820, 'loss/train': 0.9405775666236877} 08/31/2021 06:34:46 - INFO - __main__ - Step 95822: {'lr': 0.0001478910117305544, 'samples': 18397824, 'steps': 95821, 'loss/train': 1.0907104015350342} 08/31/2021 06:34:46 - INFO - __main__ - Step 95823: {'lr': 0.00014788616782640874, 'samples': 18398016, 'steps': 95822, 'loss/train': 0.14597027003765106} 08/31/2021 06:34:46 - INFO - __main__ - Step 95824: {'lr': 0.00014788132396827396, 'samples': 18398208, 'steps': 95823, 'loss/train': 1.589691162109375} 08/31/2021 06:34:47 - INFO - __main__ - Step 95825: {'lr': 0.00014787648015615235, 'samples': 18398400, 'steps': 95824, 'loss/train': 0.8824578523635864} 08/31/2021 06:34:47 - INFO - __main__ - Step 95826: {'lr': 0.00014787163639004607, 'samples': 18398592, 'steps': 95825, 'loss/train': 1.437381625175476} 08/31/2021 06:34:49 - INFO - __main__ - Step 95827: {'lr': 0.00014786679266995718, 'samples': 18398784, 'steps': 95826, 'loss/train': 0.18627217411994934} 08/31/2021 06:34:49 - INFO - __main__ - Step 95828: {'lr': 0.00014786194899588792, 'samples': 18398976, 'steps': 95827, 'loss/train': 1.1140819787979126} 08/31/2021 06:34:49 - INFO - __main__ - Step 95829: {'lr': 0.0001478571053678405, 'samples': 18399168, 'steps': 95828, 'loss/train': 1.2628147602081299} 08/31/2021 06:34:50 - INFO - __main__ - Step 95830: {'lr': 0.00014785226178581708, 'samples': 18399360, 'steps': 95829, 'loss/train': 1.0914499759674072} 08/31/2021 06:34:50 - INFO - __main__ - Step 95831: {'lr': 0.00014784741824981986, 'samples': 18399552, 'steps': 95830, 'loss/train': 0.7951732277870178} 08/31/2021 06:34:52 - INFO - __main__ - Step 95832: {'lr': 0.000147842574759851, 'samples': 18399744, 'steps': 95831, 'loss/train': 0.21949456632137299} 08/31/2021 06:34:52 - INFO - __main__ - Step 95833: {'lr': 0.00014783773131591278, 'samples': 18399936, 'steps': 95832, 'loss/train': 0.9568665623664856} 08/31/2021 06:34:52 - INFO - __main__ - Step 95834: {'lr': 0.00014783288791800722, 'samples': 18400128, 'steps': 95833, 'loss/train': 0.7449648380279541} 08/31/2021 06:34:53 - INFO - __main__ - Step 95835: {'lr': 0.0001478280445661366, 'samples': 18400320, 'steps': 95834, 'loss/train': 0.6032648086547852} 08/31/2021 06:34:53 - INFO - __main__ - Step 95836: {'lr': 0.0001478232012603031, 'samples': 18400512, 'steps': 95835, 'loss/train': 0.8676719069480896} 08/31/2021 06:34:55 - INFO - __main__ - Step 95837: {'lr': 0.00014781835800050888, 'samples': 18400704, 'steps': 95836, 'loss/train': 1.1032277345657349} 08/31/2021 06:34:55 - INFO - __main__ - Step 95838: {'lr': 0.00014781351478675614, 'samples': 18400896, 'steps': 95837, 'loss/train': 0.32865163683891296} 08/31/2021 06:34:56 - INFO - __main__ - Step 95839: {'lr': 0.00014780867161904717, 'samples': 18401088, 'steps': 95838, 'loss/train': 0.8177255988121033} 08/31/2021 06:34:56 - INFO - __main__ - Step 95840: {'lr': 0.00014780382849738388, 'samples': 18401280, 'steps': 95839, 'loss/train': 0.7370837926864624} 08/31/2021 06:34:56 - INFO - __main__ - Step 95841: {'lr': 0.00014779898542176864, 'samples': 18401472, 'steps': 95840, 'loss/train': 0.0369386188685894} 08/31/2021 06:34:58 - INFO - __main__ - Step 95842: {'lr': 0.00014779414239220363, 'samples': 18401664, 'steps': 95841, 'loss/train': 1.3697739839553833} 08/31/2021 06:34:58 - INFO - __main__ - Step 95843: {'lr': 0.00014778929940869096, 'samples': 18401856, 'steps': 95842, 'loss/train': 1.3811920881271362} 08/31/2021 06:34:59 - INFO - __main__ - Step 95844: {'lr': 0.00014778445647123284, 'samples': 18402048, 'steps': 95843, 'loss/train': 1.0868580341339111} 08/31/2021 06:34:59 - INFO - __main__ - Step 95845: {'lr': 0.00014777961357983148, 'samples': 18402240, 'steps': 95844, 'loss/train': 0.6506235003471375} 08/31/2021 06:35:00 - INFO - __main__ - Step 95846: {'lr': 0.00014777477073448907, 'samples': 18402432, 'steps': 95845, 'loss/train': 1.857537031173706} 08/31/2021 06:35:01 - INFO - __main__ - Step 95847: {'lr': 0.00014776992793520777, 'samples': 18402624, 'steps': 95846, 'loss/train': 0.6370205283164978} 08/31/2021 06:35:02 - INFO - __main__ - Step 95848: {'lr': 0.00014776508518198978, 'samples': 18402816, 'steps': 95847, 'loss/train': 1.2473384141921997} 08/31/2021 06:35:02 - INFO - __main__ - Step 95849: {'lr': 0.00014776024247483725, 'samples': 18403008, 'steps': 95848, 'loss/train': 1.3308336734771729} 08/31/2021 06:35:02 - INFO - __main__ - Step 95850: {'lr': 0.00014775539981375235, 'samples': 18403200, 'steps': 95849, 'loss/train': 1.6571325063705444} 08/31/2021 06:35:03 - INFO - __main__ - Step 95851: {'lr': 0.0001477505571987373, 'samples': 18403392, 'steps': 95850, 'loss/train': 1.8780813217163086} 08/31/2021 06:35:03 - INFO - __main__ - Step 95852: {'lr': 0.0001477457146297943, 'samples': 18403584, 'steps': 95851, 'loss/train': 1.4081473350524902} 08/31/2021 06:35:05 - INFO - __main__ - Step 95853: {'lr': 0.00014774087210692557, 'samples': 18403776, 'steps': 95852, 'loss/train': 0.2935781180858612} 08/31/2021 06:35:05 - INFO - __main__ - Step 95854: {'lr': 0.00014773602963013316, 'samples': 18403968, 'steps': 95853, 'loss/train': 1.9554510116577148} 08/31/2021 06:35:06 - INFO - __main__ - Step 95855: {'lr': 0.00014773118719941928, 'samples': 18404160, 'steps': 95854, 'loss/train': 1.5831021070480347} 08/31/2021 06:35:06 - INFO - __main__ - Step 95856: {'lr': 0.00014772634481478617, 'samples': 18404352, 'steps': 95855, 'loss/train': 1.0864145755767822} 08/31/2021 06:35:06 - INFO - __main__ - Step 95857: {'lr': 0.00014772150247623598, 'samples': 18404544, 'steps': 95856, 'loss/train': 2.242908000946045} 08/31/2021 06:35:07 - INFO - __main__ - Step 95858: {'lr': 0.0001477166601837709, 'samples': 18404736, 'steps': 95857, 'loss/train': 1.263730525970459} 08/31/2021 06:35:08 - INFO - __main__ - Step 95859: {'lr': 0.00014771181793739313, 'samples': 18404928, 'steps': 95858, 'loss/train': 1.7887353897094727} 08/31/2021 06:35:09 - INFO - __main__ - Step 95860: {'lr': 0.00014770697573710485, 'samples': 18405120, 'steps': 95859, 'loss/train': 0.7742652893066406} 08/31/2021 06:35:09 - INFO - __main__ - Step 95861: {'lr': 0.00014770213358290818, 'samples': 18405312, 'steps': 95860, 'loss/train': 2.858520030975342} 08/31/2021 06:35:09 - INFO - __main__ - Step 95862: {'lr': 0.00014769729147480538, 'samples': 18405504, 'steps': 95861, 'loss/train': 1.369283676147461} 08/31/2021 06:35:10 - INFO - __main__ - Step 95863: {'lr': 0.00014769244941279858, 'samples': 18405696, 'steps': 95862, 'loss/train': 1.3343068361282349} 08/31/2021 06:35:11 - INFO - __main__ - Step 95864: {'lr': 0.00014768760739689002, 'samples': 18405888, 'steps': 95863, 'loss/train': 1.3372032642364502} 08/31/2021 06:35:12 - INFO - __main__ - Step 95865: {'lr': 0.00014768276542708182, 'samples': 18406080, 'steps': 95864, 'loss/train': 1.5930944681167603} 08/31/2021 06:35:12 - INFO - __main__ - Step 95866: {'lr': 0.0001476779235033763, 'samples': 18406272, 'steps': 95865, 'loss/train': 1.643459439277649} 08/31/2021 06:35:13 - INFO - __main__ - Step 95867: {'lr': 0.00014767308162577541, 'samples': 18406464, 'steps': 95866, 'loss/train': 1.3249566555023193} 08/31/2021 06:35:13 - INFO - __main__ - Step 95868: {'lr': 0.00014766823979428146, 'samples': 18406656, 'steps': 95867, 'loss/train': 1.1023378372192383} 08/31/2021 06:35:15 - INFO - __main__ - Step 95869: {'lr': 0.00014766339800889665, 'samples': 18406848, 'steps': 95868, 'loss/train': 1.6426993608474731} 08/31/2021 06:35:15 - INFO - __main__ - Step 95870: {'lr': 0.0001476585562696231, 'samples': 18407040, 'steps': 95869, 'loss/train': 1.4647557735443115} 08/31/2021 06:35:16 - INFO - __main__ - Step 95871: {'lr': 0.00014765371457646303, 'samples': 18407232, 'steps': 95870, 'loss/train': 1.1830812692642212} 08/31/2021 06:35:16 - INFO - __main__ - Step 95872: {'lr': 0.00014764887292941864, 'samples': 18407424, 'steps': 95871, 'loss/train': 0.5585058331489563} 08/31/2021 06:35:17 - INFO - __main__ - Step 95873: {'lr': 0.00014764403132849204, 'samples': 18407616, 'steps': 95872, 'loss/train': 1.451277494430542} 08/31/2021 06:35:17 - INFO - __main__ - Step 95874: {'lr': 0.0001476391897736855, 'samples': 18407808, 'steps': 95873, 'loss/train': 1.037137746810913} 08/31/2021 06:35:19 - INFO - __main__ - Step 95875: {'lr': 0.00014763434826500115, 'samples': 18408000, 'steps': 95874, 'loss/train': 1.3761086463928223} 08/31/2021 06:35:19 - INFO - __main__ - Step 95876: {'lr': 0.0001476295068024412, 'samples': 18408192, 'steps': 95875, 'loss/train': 0.8947231769561768} 08/31/2021 06:35:19 - INFO - __main__ - Step 95877: {'lr': 0.00014762466538600777, 'samples': 18408384, 'steps': 95876, 'loss/train': 0.03483790531754494} 08/31/2021 06:35:20 - INFO - __main__ - Step 95878: {'lr': 0.00014761982401570312, 'samples': 18408576, 'steps': 95877, 'loss/train': 1.327616810798645} 08/31/2021 06:35:20 - INFO - __main__ - Step 95879: {'lr': 0.0001476149826915294, 'samples': 18408768, 'steps': 95878, 'loss/train': 1.7332472801208496} 08/31/2021 06:35:22 - INFO - __main__ - Step 95880: {'lr': 0.0001476101414134889, 'samples': 18408960, 'steps': 95879, 'loss/train': 1.4645342826843262} 08/31/2021 06:35:22 - INFO - __main__ - Step 95881: {'lr': 0.0001476053001815836, 'samples': 18409152, 'steps': 95880, 'loss/train': 0.10315897315740585} 08/31/2021 06:35:23 - INFO - __main__ - Step 95882: {'lr': 0.0001476004589958157, 'samples': 18409344, 'steps': 95881, 'loss/train': 0.8346534967422485} 08/31/2021 06:35:23 - INFO - __main__ - Step 95883: {'lr': 0.0001475956178561875, 'samples': 18409536, 'steps': 95882, 'loss/train': 1.2174450159072876} 08/31/2021 06:35:23 - INFO - __main__ - Step 95884: {'lr': 0.00014759077676270113, 'samples': 18409728, 'steps': 95883, 'loss/train': 1.2159698009490967} 08/31/2021 06:35:25 - INFO - __main__ - Step 95885: {'lr': 0.00014758593571535878, 'samples': 18409920, 'steps': 95884, 'loss/train': 0.03550989553332329} 08/31/2021 06:35:25 - INFO - __main__ - Step 95886: {'lr': 0.00014758109471416263, 'samples': 18410112, 'steps': 95885, 'loss/train': 0.6746588945388794} 08/31/2021 06:35:26 - INFO - __main__ - Step 95887: {'lr': 0.00014757625375911486, 'samples': 18410304, 'steps': 95886, 'loss/train': 0.4867177903652191} 08/31/2021 06:35:26 - INFO - __main__ - Step 95888: {'lr': 0.00014757141285021762, 'samples': 18410496, 'steps': 95887, 'loss/train': 1.5320500135421753} 08/31/2021 06:35:26 - INFO - __main__ - Step 95889: {'lr': 0.00014756657198747314, 'samples': 18410688, 'steps': 95888, 'loss/train': 0.9499347805976868} 08/31/2021 06:35:28 - INFO - __main__ - Step 95890: {'lr': 0.0001475617311708836, 'samples': 18410880, 'steps': 95889, 'loss/train': 1.364880084991455} 08/31/2021 06:35:28 - INFO - __main__ - Step 95891: {'lr': 0.00014755689040045117, 'samples': 18411072, 'steps': 95890, 'loss/train': 1.6615673303604126} 08/31/2021 06:35:29 - INFO - __main__ - Step 95892: {'lr': 0.00014755204967617803, 'samples': 18411264, 'steps': 95891, 'loss/train': 0.6097245216369629} 08/31/2021 06:35:29 - INFO - __main__ - Step 95893: {'lr': 0.00014754720899806637, 'samples': 18411456, 'steps': 95892, 'loss/train': 0.8558831810951233} 08/31/2021 06:35:29 - INFO - __main__ - Step 95894: {'lr': 0.0001475423683661183, 'samples': 18411648, 'steps': 95893, 'loss/train': 0.816281259059906} 08/31/2021 06:35:31 - INFO - __main__ - Step 95895: {'lr': 0.00014753752778033608, 'samples': 18411840, 'steps': 95894, 'loss/train': 1.0105299949645996} 08/31/2021 06:35:32 - INFO - __main__ - Step 95896: {'lr': 0.00014753268724072187, 'samples': 18412032, 'steps': 95895, 'loss/train': 1.0105493068695068} 08/31/2021 06:35:32 - INFO - __main__ - Step 95897: {'lr': 0.00014752784674727784, 'samples': 18412224, 'steps': 95896, 'loss/train': 0.9803844094276428} 08/31/2021 06:35:32 - INFO - __main__ - Step 95898: {'lr': 0.00014752300630000616, 'samples': 18412416, 'steps': 95897, 'loss/train': 1.2787457704544067} 08/31/2021 06:35:33 - INFO - __main__ - Step 95899: {'lr': 0.00014751816589890908, 'samples': 18412608, 'steps': 95898, 'loss/train': 0.9224196076393127} 08/31/2021 06:35:33 - INFO - __main__ - Step 95900: {'lr': 0.0001475133255439887, 'samples': 18412800, 'steps': 95899, 'loss/train': 2.38076114654541} 08/31/2021 06:35:35 - INFO - __main__ - Step 95901: {'lr': 0.00014750848523524724, 'samples': 18412992, 'steps': 95900, 'loss/train': 1.0113697052001953} 08/31/2021 06:35:35 - INFO - __main__ - Step 95902: {'lr': 0.0001475036449726869, 'samples': 18413184, 'steps': 95901, 'loss/train': 0.874566376209259} 08/31/2021 06:35:35 - INFO - __main__ - Step 95903: {'lr': 0.00014749880475630983, 'samples': 18413376, 'steps': 95902, 'loss/train': 1.6525461673736572} 08/31/2021 06:35:36 - INFO - __main__ - Step 95904: {'lr': 0.00014749396458611818, 'samples': 18413568, 'steps': 95903, 'loss/train': 0.9704763889312744} 08/31/2021 06:35:36 - INFO - __main__ - Step 95905: {'lr': 0.00014748912446211422, 'samples': 18413760, 'steps': 95904, 'loss/train': 1.471342921257019} 08/31/2021 06:35:38 - INFO - __main__ - Step 95906: {'lr': 0.0001474842843843001, 'samples': 18413952, 'steps': 95905, 'loss/train': 1.374483346939087} 08/31/2021 06:35:38 - INFO - __main__ - Step 95907: {'lr': 0.0001474794443526779, 'samples': 18414144, 'steps': 95906, 'loss/train': 1.4526026248931885} 08/31/2021 06:35:39 - INFO - __main__ - Step 95908: {'lr': 0.0001474746043672499, 'samples': 18414336, 'steps': 95907, 'loss/train': 0.027473686262965202} 08/31/2021 06:35:39 - INFO - __main__ - Step 95909: {'lr': 0.0001474697644280183, 'samples': 18414528, 'steps': 95908, 'loss/train': 1.1438361406326294} 08/31/2021 06:35:39 - INFO - __main__ - Step 95910: {'lr': 0.0001474649245349852, 'samples': 18414720, 'steps': 95909, 'loss/train': 0.9433062076568604} 08/31/2021 06:35:41 - INFO - __main__ - Step 95911: {'lr': 0.0001474600846881528, 'samples': 18414912, 'steps': 95910, 'loss/train': 0.624643087387085} 08/31/2021 06:35:41 - INFO - __main__ - Step 95912: {'lr': 0.00014745524488752343, 'samples': 18415104, 'steps': 95911, 'loss/train': 0.19179914891719818} 08/31/2021 06:35:42 - INFO - __main__ - Step 95913: {'lr': 0.00014745040513309903, 'samples': 18415296, 'steps': 95912, 'loss/train': 0.23592498898506165} 08/31/2021 06:35:42 - INFO - __main__ - Step 95914: {'lr': 0.00014744556542488192, 'samples': 18415488, 'steps': 95913, 'loss/train': 1.8767009973526} 08/31/2021 06:35:42 - INFO - __main__ - Step 95915: {'lr': 0.00014744072576287426, 'samples': 18415680, 'steps': 95914, 'loss/train': 0.925619900226593} 08/31/2021 06:35:44 - INFO - __main__ - Step 95916: {'lr': 0.0001474358861470782, 'samples': 18415872, 'steps': 95915, 'loss/train': 1.3744423389434814} 08/31/2021 06:35:44 - INFO - __main__ - Step 95917: {'lr': 0.00014743104657749596, 'samples': 18416064, 'steps': 95916, 'loss/train': 1.3909374475479126} 08/31/2021 06:35:45 - INFO - __main__ - Step 95918: {'lr': 0.00014742620705412974, 'samples': 18416256, 'steps': 95917, 'loss/train': 1.4794468879699707} 08/31/2021 06:35:45 - INFO - __main__ - Step 95919: {'lr': 0.00014742136757698164, 'samples': 18416448, 'steps': 95918, 'loss/train': 1.2178095579147339} 08/31/2021 06:35:45 - INFO - __main__ - Step 95920: {'lr': 0.00014741652814605395, 'samples': 18416640, 'steps': 95919, 'loss/train': 1.3553037643432617} 08/31/2021 06:35:47 - INFO - __main__ - Step 95921: {'lr': 0.00014741168876134875, 'samples': 18416832, 'steps': 95920, 'loss/train': 0.8118409514427185} 08/31/2021 06:35:48 - INFO - __main__ - Step 95922: {'lr': 0.00014740684942286824, 'samples': 18417024, 'steps': 95921, 'loss/train': 1.4345052242279053} 08/31/2021 06:35:48 - INFO - __main__ - Step 95923: {'lr': 0.00014740201013061473, 'samples': 18417216, 'steps': 95922, 'loss/train': 1.0765146017074585} 08/31/2021 06:35:49 - INFO - __main__ - Step 95924: {'lr': 0.00014739717088459018, 'samples': 18417408, 'steps': 95923, 'loss/train': 1.3796663284301758} 08/31/2021 06:35:49 - INFO - __main__ - Step 95925: {'lr': 0.00014739233168479688, 'samples': 18417600, 'steps': 95924, 'loss/train': 1.239289402961731} 08/31/2021 06:35:51 - INFO - __main__ - Step 95926: {'lr': 0.00014738749253123706, 'samples': 18417792, 'steps': 95925, 'loss/train': 1.1835660934448242} 08/31/2021 06:35:51 - INFO - __main__ - Step 95927: {'lr': 0.00014738265342391282, 'samples': 18417984, 'steps': 95926, 'loss/train': 0.8611743450164795} 08/31/2021 06:35:51 - INFO - __main__ - Step 95928: {'lr': 0.00014737781436282638, 'samples': 18418176, 'steps': 95927, 'loss/train': 0.5733428001403809} 08/31/2021 06:35:52 - INFO - __main__ - Step 95929: {'lr': 0.0001473729753479799, 'samples': 18418368, 'steps': 95928, 'loss/train': 1.2955645322799683} 08/31/2021 06:35:52 - INFO - __main__ - Step 95930: {'lr': 0.00014736813637937558, 'samples': 18418560, 'steps': 95929, 'loss/train': 1.4656001329421997} 08/31/2021 06:35:52 - INFO - __main__ - Step 95931: {'lr': 0.0001473632974570156, 'samples': 18418752, 'steps': 95930, 'loss/train': 0.7887412905693054} 08/31/2021 06:35:54 - INFO - __main__ - Step 95932: {'lr': 0.00014735845858090214, 'samples': 18418944, 'steps': 95931, 'loss/train': 0.9673280119895935} 08/31/2021 06:35:54 - INFO - __main__ - Step 95933: {'lr': 0.00014735361975103743, 'samples': 18419136, 'steps': 95932, 'loss/train': 1.1786601543426514} 08/31/2021 06:35:55 - INFO - __main__ - Step 95934: {'lr': 0.00014734878096742357, 'samples': 18419328, 'steps': 95933, 'loss/train': 0.6586493849754333} 08/31/2021 06:35:55 - INFO - __main__ - Step 95935: {'lr': 0.00014734394223006272, 'samples': 18419520, 'steps': 95934, 'loss/train': 1.6581968069076538} 08/31/2021 06:35:55 - INFO - __main__ - Step 95936: {'lr': 0.00014733910353895713, 'samples': 18419712, 'steps': 95935, 'loss/train': 1.355138897895813} 08/31/2021 06:35:57 - INFO - __main__ - Step 95937: {'lr': 0.00014733426489410895, 'samples': 18419904, 'steps': 95936, 'loss/train': 1.4523829221725464} 08/31/2021 06:35:58 - INFO - __main__ - Step 95938: {'lr': 0.00014732942629552034, 'samples': 18420096, 'steps': 95937, 'loss/train': 1.720503568649292} 08/31/2021 06:35:58 - INFO - __main__ - Step 95939: {'lr': 0.00014732458774319352, 'samples': 18420288, 'steps': 95938, 'loss/train': 1.6470433473587036} 08/31/2021 06:35:58 - INFO - __main__ - Step 95940: {'lr': 0.00014731974923713065, 'samples': 18420480, 'steps': 95939, 'loss/train': 0.017244691029191017} 08/31/2021 06:35:59 - INFO - __main__ - Step 95941: {'lr': 0.00014731491077733396, 'samples': 18420672, 'steps': 95940, 'loss/train': 0.8205433487892151} 08/31/2021 06:35:59 - INFO - __main__ - Step 95942: {'lr': 0.00014731007236380554, 'samples': 18420864, 'steps': 95941, 'loss/train': 1.107843041419983} 08/31/2021 06:36:01 - INFO - __main__ - Step 95943: {'lr': 0.00014730523399654762, 'samples': 18421056, 'steps': 95942, 'loss/train': 1.240586519241333} 08/31/2021 06:36:01 - INFO - __main__ - Step 95944: {'lr': 0.00014730039567556239, 'samples': 18421248, 'steps': 95943, 'loss/train': 1.1398974657058716} 08/31/2021 06:36:01 - INFO - __main__ - Step 95945: {'lr': 0.000147295557400852, 'samples': 18421440, 'steps': 95944, 'loss/train': 1.2540074586868286} 08/31/2021 06:36:02 - INFO - __main__ - Step 95946: {'lr': 0.00014729071917241865, 'samples': 18421632, 'steps': 95945, 'loss/train': 0.27508744597435} 08/31/2021 06:36:02 - INFO - __main__ - Step 95947: {'lr': 0.00014728588099026464, 'samples': 18421824, 'steps': 95946, 'loss/train': 0.9595944285392761} 08/31/2021 06:36:04 - INFO - __main__ - Step 95948: {'lr': 0.0001472810428543919, 'samples': 18422016, 'steps': 95947, 'loss/train': 1.12002694606781} 08/31/2021 06:36:04 - INFO - __main__ - Step 95949: {'lr': 0.00014727620476480275, 'samples': 18422208, 'steps': 95948, 'loss/train': 1.4988045692443848} 08/31/2021 06:36:05 - INFO - __main__ - Step 95950: {'lr': 0.00014727136672149937, 'samples': 18422400, 'steps': 95949, 'loss/train': 1.3285081386566162} 08/31/2021 06:36:05 - INFO - __main__ - Step 95951: {'lr': 0.00014726652872448394, 'samples': 18422592, 'steps': 95950, 'loss/train': 0.5442917346954346} 08/31/2021 06:36:05 - INFO - __main__ - Step 95952: {'lr': 0.00014726169077375857, 'samples': 18422784, 'steps': 95951, 'loss/train': 1.4951305389404297} 08/31/2021 06:36:07 - INFO - __main__ - Step 95953: {'lr': 0.00014725685286932555, 'samples': 18422976, 'steps': 95952, 'loss/train': 1.0698124170303345} 08/31/2021 06:36:07 - INFO - __main__ - Step 95954: {'lr': 0.00014725201501118696, 'samples': 18423168, 'steps': 95953, 'loss/train': 0.8547141551971436} 08/31/2021 06:36:07 - INFO - __main__ - Step 95955: {'lr': 0.00014724717719934505, 'samples': 18423360, 'steps': 95954, 'loss/train': 1.1575318574905396} 08/31/2021 06:36:08 - INFO - __main__ - Step 95956: {'lr': 0.00014724233943380199, 'samples': 18423552, 'steps': 95955, 'loss/train': 1.155849575996399} 08/31/2021 06:36:08 - INFO - __main__ - Step 95957: {'lr': 0.00014723750171455994, 'samples': 18423744, 'steps': 95956, 'loss/train': 0.8170459270477295} 08/31/2021 06:36:10 - INFO - __main__ - Step 95958: {'lr': 0.00014723266404162105, 'samples': 18423936, 'steps': 95957, 'loss/train': 1.7480393648147583} 08/31/2021 06:36:10 - INFO - __main__ - Step 95959: {'lr': 0.00014722782641498757, 'samples': 18424128, 'steps': 95958, 'loss/train': 1.0109533071517944} 08/31/2021 06:36:10 - INFO - __main__ - Step 95960: {'lr': 0.00014722298883466177, 'samples': 18424320, 'steps': 95959, 'loss/train': 0.9893866777420044} 08/31/2021 06:36:11 - INFO - __main__ - Step 95961: {'lr': 0.00014721815130064555, 'samples': 18424512, 'steps': 95960, 'loss/train': 0.5902500748634338} 08/31/2021 06:36:11 - INFO - __main__ - Step 95962: {'lr': 0.00014721331381294128, 'samples': 18424704, 'steps': 95961, 'loss/train': 1.1575320959091187} 08/31/2021 06:36:13 - INFO - __main__ - Step 95963: {'lr': 0.0001472084763715511, 'samples': 18424896, 'steps': 95962, 'loss/train': 1.0881373882293701} 08/31/2021 06:36:13 - INFO - __main__ - Step 95964: {'lr': 0.00014720363897647722, 'samples': 18425088, 'steps': 95963, 'loss/train': 1.1582568883895874} 08/31/2021 06:36:14 - INFO - __main__ - Step 95965: {'lr': 0.00014719880162772175, 'samples': 18425280, 'steps': 95964, 'loss/train': 1.315569519996643} 08/31/2021 06:36:14 - INFO - __main__ - Step 95966: {'lr': 0.0001471939643252869, 'samples': 18425472, 'steps': 95965, 'loss/train': 0.7712947130203247} 08/31/2021 06:36:14 - INFO - __main__ - Step 95967: {'lr': 0.00014718912706917491, 'samples': 18425664, 'steps': 95966, 'loss/train': 0.8080324530601501} 08/31/2021 06:36:16 - INFO - __main__ - Step 95968: {'lr': 0.0001471842898593879, 'samples': 18425856, 'steps': 95967, 'loss/train': 0.9415997266769409} 08/31/2021 06:36:16 - INFO - __main__ - Step 95969: {'lr': 0.00014717945269592802, 'samples': 18426048, 'steps': 95968, 'loss/train': 1.3242671489715576} 08/31/2021 06:36:16 - INFO - __main__ - Step 95970: {'lr': 0.00014717461557879757, 'samples': 18426240, 'steps': 95969, 'loss/train': 1.3069411516189575} 08/31/2021 06:36:17 - INFO - __main__ - Step 95971: {'lr': 0.0001471697785079986, 'samples': 18426432, 'steps': 95970, 'loss/train': 1.0990270376205444} 08/31/2021 06:36:17 - INFO - __main__ - Step 95972: {'lr': 0.00014716494148353336, 'samples': 18426624, 'steps': 95971, 'loss/train': 1.2664470672607422} 08/31/2021 06:36:17 - INFO - __main__ - Step 95973: {'lr': 0.000147160104505404, 'samples': 18426816, 'steps': 95972, 'loss/train': 0.8441196084022522} 08/31/2021 06:36:20 - INFO - __main__ - Step 95974: {'lr': 0.0001471552675736128, 'samples': 18427008, 'steps': 95973, 'loss/train': 0.20025920867919922} 08/31/2021 06:36:20 - INFO - __main__ - Step 95975: {'lr': 0.00014715043068816176, 'samples': 18427200, 'steps': 95974, 'loss/train': 0.8064374327659607} 08/31/2021 06:36:20 - INFO - __main__ - Step 95976: {'lr': 0.00014714559384905316, 'samples': 18427392, 'steps': 95975, 'loss/train': 0.7329667210578918} 08/31/2021 06:36:21 - INFO - __main__ - Step 95977: {'lr': 0.00014714075705628916, 'samples': 18427584, 'steps': 95976, 'loss/train': 0.4266168773174286} 08/31/2021 06:36:21 - INFO - __main__ - Step 95978: {'lr': 0.00014713592030987194, 'samples': 18427776, 'steps': 95977, 'loss/train': 1.2691365480422974} 08/31/2021 06:36:23 - INFO - __main__ - Step 95979: {'lr': 0.0001471310836098037, 'samples': 18427968, 'steps': 95978, 'loss/train': 1.4396257400512695} 08/31/2021 06:36:23 - INFO - __main__ - Step 95980: {'lr': 0.0001471262469560866, 'samples': 18428160, 'steps': 95979, 'loss/train': 0.1507042497396469} 08/31/2021 06:36:24 - INFO - __main__ - Step 95981: {'lr': 0.0001471214103487228, 'samples': 18428352, 'steps': 95980, 'loss/train': 1.2802385091781616} 08/31/2021 06:36:24 - INFO - __main__ - Step 95982: {'lr': 0.00014711657378771453, 'samples': 18428544, 'steps': 95981, 'loss/train': 1.3233903646469116} 08/31/2021 06:36:25 - INFO - __main__ - Step 95983: {'lr': 0.00014711173727306395, 'samples': 18428736, 'steps': 95982, 'loss/train': 1.3483552932739258} 08/31/2021 06:36:25 - INFO - __main__ - Step 95984: {'lr': 0.00014710690080477323, 'samples': 18428928, 'steps': 95983, 'loss/train': 0.016146937385201454} 08/31/2021 06:36:27 - INFO - __main__ - Step 95985: {'lr': 0.00014710206438284457, 'samples': 18429120, 'steps': 95984, 'loss/train': 0.9698509573936462} 08/31/2021 06:36:27 - INFO - __main__ - Step 95986: {'lr': 0.00014709722800728008, 'samples': 18429312, 'steps': 95985, 'loss/train': 0.11798591911792755} 08/31/2021 06:36:28 - INFO - __main__ - Step 95987: {'lr': 0.00014709239167808215, 'samples': 18429504, 'steps': 95986, 'loss/train': 0.8195245265960693} 08/31/2021 06:36:28 - INFO - __main__ - Step 95988: {'lr': 0.00014708755539525267, 'samples': 18429696, 'steps': 95987, 'loss/train': 0.3714436888694763} 08/31/2021 06:36:28 - INFO - __main__ - Step 95989: {'lr': 0.00014708271915879394, 'samples': 18429888, 'steps': 95988, 'loss/train': 1.6871330738067627} 08/31/2021 06:36:30 - INFO - __main__ - Step 95990: {'lr': 0.00014707788296870817, 'samples': 18430080, 'steps': 95989, 'loss/train': 1.7080601453781128} 08/31/2021 06:36:30 - INFO - __main__ - Step 95991: {'lr': 0.0001470730468249975, 'samples': 18430272, 'steps': 95990, 'loss/train': 1.15751051902771} 08/31/2021 06:36:31 - INFO - __main__ - Step 95992: {'lr': 0.00014706821072766417, 'samples': 18430464, 'steps': 95991, 'loss/train': 1.0632572174072266} 08/31/2021 06:36:31 - INFO - __main__ - Step 95993: {'lr': 0.00014706337467671027, 'samples': 18430656, 'steps': 95992, 'loss/train': 1.5308886766433716} 08/31/2021 06:36:31 - INFO - __main__ - Step 95994: {'lr': 0.00014705853867213802, 'samples': 18430848, 'steps': 95993, 'loss/train': 0.7521924376487732} 08/31/2021 06:36:33 - INFO - __main__ - Step 95995: {'lr': 0.00014705370271394963, 'samples': 18431040, 'steps': 95994, 'loss/train': 1.5092793703079224} 08/31/2021 06:36:33 - INFO - __main__ - Step 95996: {'lr': 0.00014704886680214725, 'samples': 18431232, 'steps': 95995, 'loss/train': 1.2224690914154053} 08/31/2021 06:36:34 - INFO - __main__ - Step 95997: {'lr': 0.00014704403093673308, 'samples': 18431424, 'steps': 95996, 'loss/train': 1.3353161811828613} 08/31/2021 06:36:34 - INFO - __main__ - Step 95998: {'lr': 0.00014703919511770925, 'samples': 18431616, 'steps': 95997, 'loss/train': 0.8609025478363037} 08/31/2021 06:36:34 - INFO - __main__ - Step 95999: {'lr': 0.00014703435934507796, 'samples': 18431808, 'steps': 95998, 'loss/train': 0.3198530673980713} 08/31/2021 06:36:36 - INFO - __main__ - Step 96000: {'lr': 0.00014702952361884142, 'samples': 18432000, 'steps': 95999, 'loss/train': 1.349602222442627} 08/31/2021 06:36:36 - INFO - __main__ - Step 96001: {'lr': 0.00014702468793900187, 'samples': 18432192, 'steps': 96000, 'loss/train': 1.1099801063537598} 08/31/2021 06:36:37 - INFO - __main__ - Step 96002: {'lr': 0.00014701985230556133, 'samples': 18432384, 'steps': 96001, 'loss/train': 0.9833934903144836} 08/31/2021 06:36:37 - INFO - __main__ - Step 96003: {'lr': 0.00014701501671852206, 'samples': 18432576, 'steps': 96002, 'loss/train': 0.8582797646522522} 08/31/2021 06:36:37 - INFO - __main__ - Step 96004: {'lr': 0.00014701018117788621, 'samples': 18432768, 'steps': 96003, 'loss/train': 0.7895305156707764} 08/31/2021 06:36:38 - INFO - __main__ - Step 96005: {'lr': 0.00014700534568365598, 'samples': 18432960, 'steps': 96004, 'loss/train': 1.0244804620742798} 08/31/2021 06:36:39 - INFO - __main__ - Step 96006: {'lr': 0.0001470005102358336, 'samples': 18433152, 'steps': 96005, 'loss/train': 1.0577796697616577} 08/31/2021 06:36:40 - INFO - __main__ - Step 96007: {'lr': 0.00014699567483442117, 'samples': 18433344, 'steps': 96006, 'loss/train': 1.2023701667785645} 08/31/2021 06:36:40 - INFO - __main__ - Step 96008: {'lr': 0.00014699083947942087, 'samples': 18433536, 'steps': 96007, 'loss/train': 0.1232496127486229} 08/31/2021 06:36:40 - INFO - __main__ - Step 96009: {'lr': 0.00014698600417083495, 'samples': 18433728, 'steps': 96008, 'loss/train': 1.3162459135055542} 08/31/2021 06:36:41 - INFO - __main__ - Step 96010: {'lr': 0.00014698116890866553, 'samples': 18433920, 'steps': 96009, 'loss/train': 1.8930991888046265} 08/31/2021 06:36:42 - INFO - __main__ - Step 96011: {'lr': 0.0001469763336929148, 'samples': 18434112, 'steps': 96010, 'loss/train': 1.2034350633621216} 08/31/2021 06:36:43 - INFO - __main__ - Step 96012: {'lr': 0.00014697149852358493, 'samples': 18434304, 'steps': 96011, 'loss/train': 1.399067997932434} 08/31/2021 06:36:43 - INFO - __main__ - Step 96013: {'lr': 0.00014696666340067817, 'samples': 18434496, 'steps': 96012, 'loss/train': 0.8474541306495667} 08/31/2021 06:36:44 - INFO - __main__ - Step 96014: {'lr': 0.0001469618283241967, 'samples': 18434688, 'steps': 96013, 'loss/train': 1.5007461309432983} 08/31/2021 06:36:44 - INFO - __main__ - Step 96015: {'lr': 0.00014695699329414253, 'samples': 18434880, 'steps': 96014, 'loss/train': 0.8683497905731201} 08/31/2021 06:36:45 - INFO - __main__ - Step 96016: {'lr': 0.00014695215831051796, 'samples': 18435072, 'steps': 96015, 'loss/train': 0.8925692439079285} 08/31/2021 06:36:46 - INFO - __main__ - Step 96017: {'lr': 0.00014694732337332516, 'samples': 18435264, 'steps': 96016, 'loss/train': 1.3559743165969849} 08/31/2021 06:36:46 - INFO - __main__ - Step 96018: {'lr': 0.0001469424884825663, 'samples': 18435456, 'steps': 96017, 'loss/train': 0.1724921464920044} 08/31/2021 06:36:47 - INFO - __main__ - Step 96019: {'lr': 0.00014693765363824358, 'samples': 18435648, 'steps': 96018, 'loss/train': 0.04062803462147713} 08/31/2021 06:36:47 - INFO - __main__ - Step 96020: {'lr': 0.00014693281884035916, 'samples': 18435840, 'steps': 96019, 'loss/train': 1.0883255004882812} 08/31/2021 06:36:49 - INFO - __main__ - Step 96021: {'lr': 0.0001469279840889152, 'samples': 18436032, 'steps': 96020, 'loss/train': 1.046568512916565} 08/31/2021 06:36:49 - INFO - __main__ - Step 96022: {'lr': 0.00014692314938391393, 'samples': 18436224, 'steps': 96021, 'loss/train': 1.223276138305664} 08/31/2021 06:36:49 - INFO - __main__ - Step 96023: {'lr': 0.0001469183147253575, 'samples': 18436416, 'steps': 96022, 'loss/train': 1.0823934078216553} 08/31/2021 06:36:50 - INFO - __main__ - Step 96024: {'lr': 0.00014691348011324808, 'samples': 18436608, 'steps': 96023, 'loss/train': 1.885027289390564} 08/31/2021 06:36:50 - INFO - __main__ - Step 96025: {'lr': 0.00014690864554758786, 'samples': 18436800, 'steps': 96024, 'loss/train': 1.318460464477539} 08/31/2021 06:36:51 - INFO - __main__ - Step 96026: {'lr': 0.00014690381102837902, 'samples': 18436992, 'steps': 96025, 'loss/train': 0.03048867918550968} 08/31/2021 06:36:52 - INFO - __main__ - Step 96027: {'lr': 0.00014689897655562376, 'samples': 18437184, 'steps': 96026, 'loss/train': 1.4441584348678589} 08/31/2021 06:36:53 - INFO - __main__ - Step 96028: {'lr': 0.00014689414212932416, 'samples': 18437376, 'steps': 96027, 'loss/train': 0.9884072542190552} 08/31/2021 06:36:53 - INFO - __main__ - Step 96029: {'lr': 0.0001468893077494825, 'samples': 18437568, 'steps': 96028, 'loss/train': 1.1612619161605835} 08/31/2021 06:36:53 - INFO - __main__ - Step 96030: {'lr': 0.00014688447341610096, 'samples': 18437760, 'steps': 96029, 'loss/train': 0.03752513602375984} 08/31/2021 06:36:54 - INFO - __main__ - Step 96031: {'lr': 0.00014687963912918161, 'samples': 18437952, 'steps': 96030, 'loss/train': 1.1000733375549316} 08/31/2021 06:36:56 - INFO - __main__ - Step 96032: {'lr': 0.00014687480488872673, 'samples': 18438144, 'steps': 96031, 'loss/train': 1.1580866575241089} 08/31/2021 06:36:56 - INFO - __main__ - Step 96033: {'lr': 0.00014686997069473848, 'samples': 18438336, 'steps': 96032, 'loss/train': 1.0801082849502563} 08/31/2021 06:36:57 - INFO - __main__ - Step 96034: {'lr': 0.00014686513654721902, 'samples': 18438528, 'steps': 96033, 'loss/train': 1.4212144613265991} 08/31/2021 06:36:57 - INFO - __main__ - Step 96035: {'lr': 0.00014686030244617055, 'samples': 18438720, 'steps': 96034, 'loss/train': 0.6116804480552673} 08/31/2021 06:36:57 - INFO - __main__ - Step 96036: {'lr': 0.0001468554683915953, 'samples': 18438912, 'steps': 96035, 'loss/train': 0.8802850246429443} 08/31/2021 06:36:59 - INFO - __main__ - Step 96037: {'lr': 0.0001468506343834953, 'samples': 18439104, 'steps': 96036, 'loss/train': 1.0557631254196167} 08/31/2021 06:37:00 - INFO - __main__ - Step 96038: {'lr': 0.00014684580042187285, 'samples': 18439296, 'steps': 96037, 'loss/train': 0.28383418917655945} 08/31/2021 06:37:00 - INFO - __main__ - Step 96039: {'lr': 0.00014684096650673006, 'samples': 18439488, 'steps': 96038, 'loss/train': 0.7419792413711548} 08/31/2021 06:37:00 - INFO - __main__ - Step 96040: {'lr': 0.00014683613263806914, 'samples': 18439680, 'steps': 96039, 'loss/train': 1.1453860998153687} 08/31/2021 06:37:01 - INFO - __main__ - Step 96041: {'lr': 0.00014683129881589232, 'samples': 18439872, 'steps': 96040, 'loss/train': 1.369388461112976} 08/31/2021 06:37:01 - INFO - __main__ - Step 96042: {'lr': 0.0001468264650402017, 'samples': 18440064, 'steps': 96041, 'loss/train': 1.03036367893219} 08/31/2021 06:37:03 - INFO - __main__ - Step 96043: {'lr': 0.00014682163131099946, 'samples': 18440256, 'steps': 96042, 'loss/train': 1.1102912425994873} 08/31/2021 06:37:03 - INFO - __main__ - Step 96044: {'lr': 0.00014681679762828777, 'samples': 18440448, 'steps': 96043, 'loss/train': 1.1118872165679932} 08/31/2021 06:37:03 - INFO - __main__ - Step 96045: {'lr': 0.0001468119639920689, 'samples': 18440640, 'steps': 96044, 'loss/train': 1.3093721866607666} 08/31/2021 06:37:04 - INFO - __main__ - Step 96046: {'lr': 0.00014680713040234495, 'samples': 18440832, 'steps': 96045, 'loss/train': 0.88897705078125} 08/31/2021 06:37:04 - INFO - __main__ - Step 96047: {'lr': 0.00014680229685911812, 'samples': 18441024, 'steps': 96046, 'loss/train': 0.9997936487197876} 08/31/2021 06:37:06 - INFO - __main__ - Step 96048: {'lr': 0.00014679746336239058, 'samples': 18441216, 'steps': 96047, 'loss/train': 0.745381236076355} 08/31/2021 06:37:06 - INFO - __main__ - Step 96049: {'lr': 0.0001467926299121645, 'samples': 18441408, 'steps': 96048, 'loss/train': 0.14924409985542297} 08/31/2021 06:37:07 - INFO - __main__ - Step 96050: {'lr': 0.00014678779650844205, 'samples': 18441600, 'steps': 96049, 'loss/train': 0.49971476197242737} 08/31/2021 06:37:07 - INFO - __main__ - Step 96051: {'lr': 0.00014678296315122545, 'samples': 18441792, 'steps': 96050, 'loss/train': 1.0193636417388916} 08/31/2021 06:37:07 - INFO - __main__ - Step 96052: {'lr': 0.00014677812984051683, 'samples': 18441984, 'steps': 96051, 'loss/train': 4.0991411209106445} 08/31/2021 06:37:09 - INFO - __main__ - Step 96053: {'lr': 0.0001467732965763184, 'samples': 18442176, 'steps': 96052, 'loss/train': 1.77615225315094} 08/31/2021 06:37:09 - INFO - __main__ - Step 96054: {'lr': 0.00014676846335863242, 'samples': 18442368, 'steps': 96053, 'loss/train': 1.3764901161193848} 08/31/2021 06:37:10 - INFO - __main__ - Step 96055: {'lr': 0.00014676363018746087, 'samples': 18442560, 'steps': 96054, 'loss/train': 0.33764609694480896} 08/31/2021 06:37:10 - INFO - __main__ - Step 96056: {'lr': 0.00014675879706280606, 'samples': 18442752, 'steps': 96055, 'loss/train': 1.1545466184616089} 08/31/2021 06:37:10 - INFO - __main__ - Step 96057: {'lr': 0.00014675396398467015, 'samples': 18442944, 'steps': 96056, 'loss/train': 0.5263362526893616} 08/31/2021 06:37:11 - INFO - __main__ - Step 96058: {'lr': 0.00014674913095305537, 'samples': 18443136, 'steps': 96057, 'loss/train': 0.9516515731811523} 08/31/2021 06:37:12 - INFO - __main__ - Step 96059: {'lr': 0.00014674429796796373, 'samples': 18443328, 'steps': 96058, 'loss/train': 5.753109455108643} 08/31/2021 06:37:13 - INFO - __main__ - Step 96060: {'lr': 0.00014673946502939756, 'samples': 18443520, 'steps': 96059, 'loss/train': 0.0636991485953331} 08/31/2021 06:37:13 - INFO - __main__ - Step 96061: {'lr': 0.00014673463213735899, 'samples': 18443712, 'steps': 96060, 'loss/train': 0.8535920977592468} 08/31/2021 06:37:13 - INFO - __main__ - Step 96062: {'lr': 0.00014672979929185022, 'samples': 18443904, 'steps': 96061, 'loss/train': 1.334969162940979} 08/31/2021 06:37:14 - INFO - __main__ - Step 96063: {'lr': 0.00014672496649287338, 'samples': 18444096, 'steps': 96062, 'loss/train': 1.3047962188720703} 08/31/2021 06:37:14 - INFO - __main__ - Step 96064: {'lr': 0.00014672013374043068, 'samples': 18444288, 'steps': 96063, 'loss/train': 1.2775954008102417} 08/31/2021 06:37:16 - INFO - __main__ - Step 96065: {'lr': 0.0001467153010345243, 'samples': 18444480, 'steps': 96064, 'loss/train': 1.1337487697601318} 08/31/2021 06:37:16 - INFO - __main__ - Step 96066: {'lr': 0.00014671046837515646, 'samples': 18444672, 'steps': 96065, 'loss/train': 0.27309921383857727} 08/31/2021 06:37:16 - INFO - __main__ - Step 96067: {'lr': 0.00014670563576232921, 'samples': 18444864, 'steps': 96066, 'loss/train': 0.9318625926971436} 08/31/2021 06:37:17 - INFO - __main__ - Step 96068: {'lr': 0.0001467008031960449, 'samples': 18445056, 'steps': 96067, 'loss/train': 0.6660805344581604} 08/31/2021 06:37:17 - INFO - __main__ - Step 96069: {'lr': 0.00014669597067630557, 'samples': 18445248, 'steps': 96068, 'loss/train': 1.90623939037323} 08/31/2021 06:37:19 - INFO - __main__ - Step 96070: {'lr': 0.00014669113820311343, 'samples': 18445440, 'steps': 96069, 'loss/train': 1.5392836332321167} 08/31/2021 06:37:19 - INFO - __main__ - Step 96071: {'lr': 0.0001466863057764707, 'samples': 18445632, 'steps': 96070, 'loss/train': 0.7503848671913147} 08/31/2021 06:37:20 - INFO - __main__ - Step 96072: {'lr': 0.00014668147339637946, 'samples': 18445824, 'steps': 96071, 'loss/train': 1.0261189937591553} 08/31/2021 06:37:20 - INFO - __main__ - Step 96073: {'lr': 0.00014667664106284201, 'samples': 18446016, 'steps': 96072, 'loss/train': 1.9649971723556519} 08/31/2021 06:37:20 - INFO - __main__ - Step 96074: {'lr': 0.00014667180877586043, 'samples': 18446208, 'steps': 96073, 'loss/train': 0.9668461680412292} 08/31/2021 06:37:21 - INFO - __main__ - Step 96075: {'lr': 0.00014666697653543693, 'samples': 18446400, 'steps': 96074, 'loss/train': 2.375458002090454} 08/31/2021 06:37:22 - INFO - __main__ - Step 96076: {'lr': 0.00014666214434157373, 'samples': 18446592, 'steps': 96075, 'loss/train': 1.1918582916259766} 08/31/2021 06:37:23 - INFO - __main__ - Step 96077: {'lr': 0.00014665731219427297, 'samples': 18446784, 'steps': 96076, 'loss/train': 1.0723583698272705} 08/31/2021 06:37:23 - INFO - __main__ - Step 96078: {'lr': 0.00014665248009353683, 'samples': 18446976, 'steps': 96077, 'loss/train': 1.26497483253479} 08/31/2021 06:37:23 - INFO - __main__ - Step 96079: {'lr': 0.00014664764803936747, 'samples': 18447168, 'steps': 96078, 'loss/train': 1.1036455631256104} 08/31/2021 06:37:24 - INFO - __main__ - Step 96080: {'lr': 0.0001466428160317671, 'samples': 18447360, 'steps': 96079, 'loss/train': 1.5185339450836182} 08/31/2021 06:37:25 - INFO - __main__ - Step 96081: {'lr': 0.00014663798407073798, 'samples': 18447552, 'steps': 96080, 'loss/train': 1.4837290048599243} 08/31/2021 06:37:26 - INFO - __main__ - Step 96082: {'lr': 0.00014663315215628208, 'samples': 18447744, 'steps': 96081, 'loss/train': 1.9234110116958618} 08/31/2021 06:37:26 - INFO - __main__ - Step 96083: {'lr': 0.00014662832028840167, 'samples': 18447936, 'steps': 96082, 'loss/train': 0.9675164818763733} 08/31/2021 06:37:26 - INFO - __main__ - Step 96084: {'lr': 0.00014662348846709899, 'samples': 18448128, 'steps': 96083, 'loss/train': 1.2248376607894897} 08/31/2021 06:37:27 - INFO - __main__ - Step 96085: {'lr': 0.00014661865669237615, 'samples': 18448320, 'steps': 96084, 'loss/train': 0.2056812196969986} 08/31/2021 06:37:28 - INFO - __main__ - Step 96086: {'lr': 0.00014661382496423533, 'samples': 18448512, 'steps': 96085, 'loss/train': 1.0998541116714478} 08/31/2021 06:37:29 - INFO - __main__ - Step 96087: {'lr': 0.00014660899328267874, 'samples': 18448704, 'steps': 96086, 'loss/train': 1.047334909439087} 08/31/2021 06:37:29 - INFO - __main__ - Step 96088: {'lr': 0.00014660416164770856, 'samples': 18448896, 'steps': 96087, 'loss/train': 1.2486636638641357} 08/31/2021 06:37:29 - INFO - __main__ - Step 96089: {'lr': 0.0001465993300593269, 'samples': 18449088, 'steps': 96088, 'loss/train': 1.07906973361969} 08/31/2021 06:37:30 - INFO - __main__ - Step 96090: {'lr': 0.00014659449851753603, 'samples': 18449280, 'steps': 96089, 'loss/train': 1.141206979751587} 08/31/2021 06:37:32 - INFO - __main__ - Step 96091: {'lr': 0.00014658966702233808, 'samples': 18449472, 'steps': 96090, 'loss/train': 1.5830525159835815} 08/31/2021 06:37:32 - INFO - __main__ - Step 96092: {'lr': 0.00014658483557373523, 'samples': 18449664, 'steps': 96091, 'loss/train': 1.1185351610183716} 08/31/2021 06:37:33 - INFO - __main__ - Step 96093: {'lr': 0.00014658000417172964, 'samples': 18449856, 'steps': 96092, 'loss/train': 1.2389028072357178} 08/31/2021 06:37:33 - INFO - __main__ - Step 96094: {'lr': 0.0001465751728163235, 'samples': 18450048, 'steps': 96093, 'loss/train': 1.2443370819091797} 08/31/2021 06:37:33 - INFO - __main__ - Step 96095: {'lr': 0.00014657034150751912, 'samples': 18450240, 'steps': 96094, 'loss/train': 1.5350559949874878} 08/31/2021 06:37:35 - INFO - __main__ - Step 96096: {'lr': 0.00014656551024531844, 'samples': 18450432, 'steps': 96095, 'loss/train': 1.324217677116394} 08/31/2021 06:37:35 - INFO - __main__ - Step 96097: {'lr': 0.00014656067902972376, 'samples': 18450624, 'steps': 96096, 'loss/train': 0.7586590051651001} 08/31/2021 06:37:36 - INFO - __main__ - Step 96098: {'lr': 0.0001465558478607372, 'samples': 18450816, 'steps': 96097, 'loss/train': 0.9907231330871582} 08/31/2021 06:37:36 - INFO - __main__ - Step 96099: {'lr': 0.000146551016738361, 'samples': 18451008, 'steps': 96098, 'loss/train': 1.8065860271453857} 08/31/2021 06:37:36 - INFO - __main__ - Step 96100: {'lr': 0.0001465461856625973, 'samples': 18451200, 'steps': 96099, 'loss/train': 0.8645588159561157} 08/31/2021 06:37:37 - INFO - __main__ - Step 96101: {'lr': 0.00014654135463344832, 'samples': 18451392, 'steps': 96100, 'loss/train': 0.5485498905181885} 08/31/2021 06:37:38 - INFO - __main__ - Step 96102: {'lr': 0.00014653652365091618, 'samples': 18451584, 'steps': 96101, 'loss/train': 1.155211329460144} 08/31/2021 06:37:39 - INFO - __main__ - Step 96103: {'lr': 0.0001465316927150031, 'samples': 18451776, 'steps': 96102, 'loss/train': 1.2352948188781738} 08/31/2021 06:37:39 - INFO - __main__ - Step 96104: {'lr': 0.00014652686182571126, 'samples': 18451968, 'steps': 96103, 'loss/train': 1.7322016954421997} 08/31/2021 06:37:39 - INFO - __main__ - Step 96105: {'lr': 0.0001465220309830428, 'samples': 18452160, 'steps': 96104, 'loss/train': 0.3111693859100342} 08/31/2021 06:37:40 - INFO - __main__ - Step 96106: {'lr': 0.00014651720018699993, 'samples': 18452352, 'steps': 96105, 'loss/train': 1.4358023405075073} 08/31/2021 06:37:41 - INFO - __main__ - Step 96107: {'lr': 0.00014651236943758478, 'samples': 18452544, 'steps': 96106, 'loss/train': 0.9486852884292603} 08/31/2021 06:37:42 - INFO - __main__ - Step 96108: {'lr': 0.00014650753873479968, 'samples': 18452736, 'steps': 96107, 'loss/train': 1.3971104621887207} 08/31/2021 06:37:42 - INFO - __main__ - Step 96109: {'lr': 0.0001465027080786466, 'samples': 18452928, 'steps': 96108, 'loss/train': 0.8647588491439819} 08/31/2021 06:37:42 - INFO - __main__ - Step 96110: {'lr': 0.00014649787746912778, 'samples': 18453120, 'steps': 96109, 'loss/train': 1.3872829675674438} 08/31/2021 06:37:43 - INFO - __main__ - Step 96111: {'lr': 0.00014649304690624544, 'samples': 18453312, 'steps': 96110, 'loss/train': 1.217340111732483} 08/31/2021 06:37:44 - INFO - __main__ - Step 96112: {'lr': 0.00014648821639000174, 'samples': 18453504, 'steps': 96111, 'loss/train': 0.9357565641403198} 08/31/2021 06:37:45 - INFO - __main__ - Step 96113: {'lr': 0.00014648338592039884, 'samples': 18453696, 'steps': 96112, 'loss/train': 0.6055468916893005} 08/31/2021 06:37:45 - INFO - __main__ - Step 96114: {'lr': 0.00014647855549743892, 'samples': 18453888, 'steps': 96113, 'loss/train': 1.4577844142913818} 08/31/2021 06:37:45 - INFO - __main__ - Step 96115: {'lr': 0.00014647372512112416, 'samples': 18454080, 'steps': 96114, 'loss/train': 1.5397789478302002} 08/31/2021 06:37:46 - INFO - __main__ - Step 96116: {'lr': 0.00014646889479145674, 'samples': 18454272, 'steps': 96115, 'loss/train': 0.6574559211730957} 08/31/2021 06:37:47 - INFO - __main__ - Step 96117: {'lr': 0.00014646406450843886, 'samples': 18454464, 'steps': 96116, 'loss/train': 1.6596295833587646} 08/31/2021 06:37:47 - INFO - __main__ - Step 96118: {'lr': 0.0001464592342720727, 'samples': 18454656, 'steps': 96117, 'loss/train': 1.4023699760437012} 08/31/2021 06:37:48 - INFO - __main__ - Step 96119: {'lr': 0.00014645440408236036, 'samples': 18454848, 'steps': 96118, 'loss/train': 1.783632755279541} 08/31/2021 06:37:48 - INFO - __main__ - Step 96120: {'lr': 0.0001464495739393041, 'samples': 18455040, 'steps': 96119, 'loss/train': 1.1231566667556763} 08/31/2021 06:37:49 - INFO - __main__ - Step 96121: {'lr': 0.00014644474384290605, 'samples': 18455232, 'steps': 96120, 'loss/train': 0.297191858291626} 08/31/2021 06:37:50 - INFO - __main__ - Step 96122: {'lr': 0.0001464399137931685, 'samples': 18455424, 'steps': 96121, 'loss/train': 1.2533069849014282} 08/31/2021 06:37:50 - INFO - __main__ - Step 96123: {'lr': 0.0001464350837900934, 'samples': 18455616, 'steps': 96122, 'loss/train': 1.0172839164733887} 08/31/2021 06:37:51 - INFO - __main__ - Step 96124: {'lr': 0.00014643025383368307, 'samples': 18455808, 'steps': 96123, 'loss/train': 1.398776650428772} 08/31/2021 06:37:51 - INFO - __main__ - Step 96125: {'lr': 0.0001464254239239397, 'samples': 18456000, 'steps': 96124, 'loss/train': 0.9257622957229614} 08/31/2021 06:37:52 - INFO - __main__ - Step 96126: {'lr': 0.00014642059406086544, 'samples': 18456192, 'steps': 96125, 'loss/train': 1.4323182106018066} 08/31/2021 06:37:53 - INFO - __main__ - Step 96127: {'lr': 0.00014641576424446242, 'samples': 18456384, 'steps': 96126, 'loss/train': 1.6677627563476562} 08/31/2021 06:37:54 - INFO - __main__ - Step 96128: {'lr': 0.00014641093447473287, 'samples': 18456576, 'steps': 96127, 'loss/train': 1.210496187210083} 08/31/2021 06:37:54 - INFO - __main__ - Step 96129: {'lr': 0.00014640610475167898, 'samples': 18456768, 'steps': 96128, 'loss/train': 1.6448259353637695} 08/31/2021 06:37:54 - INFO - __main__ - Step 96130: {'lr': 0.00014640127507530286, 'samples': 18456960, 'steps': 96129, 'loss/train': 1.3995975255966187} 08/31/2021 06:37:55 - INFO - __main__ - Step 96131: {'lr': 0.00014639644544560675, 'samples': 18457152, 'steps': 96130, 'loss/train': 0.7322454452514648} 08/31/2021 06:37:55 - INFO - __main__ - Step 96132: {'lr': 0.0001463916158625928, 'samples': 18457344, 'steps': 96131, 'loss/train': 0.8682517409324646} 08/31/2021 06:37:57 - INFO - __main__ - Step 96133: {'lr': 0.0001463867863262632, 'samples': 18457536, 'steps': 96132, 'loss/train': 1.4031903743743896} 08/31/2021 06:37:57 - INFO - __main__ - Step 96134: {'lr': 0.0001463819568366201, 'samples': 18457728, 'steps': 96133, 'loss/train': 1.3684836626052856} 08/31/2021 06:37:57 - INFO - __main__ - Step 96135: {'lr': 0.00014637712739366582, 'samples': 18457920, 'steps': 96134, 'loss/train': 0.723039984703064} 08/31/2021 06:37:58 - INFO - __main__ - Step 96136: {'lr': 0.00014637229799740225, 'samples': 18458112, 'steps': 96135, 'loss/train': 1.1440714597702026} 08/31/2021 06:37:58 - INFO - __main__ - Step 96137: {'lr': 0.00014636746864783178, 'samples': 18458304, 'steps': 96136, 'loss/train': 0.1588311791419983} 08/31/2021 06:38:00 - INFO - __main__ - Step 96138: {'lr': 0.00014636263934495654, 'samples': 18458496, 'steps': 96137, 'loss/train': 0.9174940586090088} 08/31/2021 06:38:01 - INFO - __main__ - Step 96139: {'lr': 0.00014635781008877862, 'samples': 18458688, 'steps': 96138, 'loss/train': 1.134350061416626} 08/31/2021 06:38:01 - INFO - __main__ - Step 96140: {'lr': 0.00014635298087930032, 'samples': 18458880, 'steps': 96139, 'loss/train': 0.928435742855072} 08/31/2021 06:38:01 - INFO - __main__ - Step 96141: {'lr': 0.00014634815171652376, 'samples': 18459072, 'steps': 96140, 'loss/train': 1.7034738063812256} 08/31/2021 06:38:02 - INFO - __main__ - Step 96142: {'lr': 0.00014634332260045113, 'samples': 18459264, 'steps': 96141, 'loss/train': 1.3542758226394653} 08/31/2021 06:38:04 - INFO - __main__ - Step 96143: {'lr': 0.00014633849353108458, 'samples': 18459456, 'steps': 96142, 'loss/train': 0.9697626829147339} 08/31/2021 06:38:04 - INFO - __main__ - Step 96144: {'lr': 0.00014633366450842632, 'samples': 18459648, 'steps': 96143, 'loss/train': 0.7159223556518555} 08/31/2021 06:38:04 - INFO - __main__ - Step 96145: {'lr': 0.00014632883553247853, 'samples': 18459840, 'steps': 96144, 'loss/train': 0.4714328944683075} 08/31/2021 06:38:05 - INFO - __main__ - Step 96146: {'lr': 0.00014632400660324335, 'samples': 18460032, 'steps': 96145, 'loss/train': 2.0503082275390625} 08/31/2021 06:38:05 - INFO - __main__ - Step 96147: {'lr': 0.00014631917772072296, 'samples': 18460224, 'steps': 96146, 'loss/train': 0.22005005180835724} 08/31/2021 06:38:06 - INFO - __main__ - Step 96148: {'lr': 0.0001463143488849197, 'samples': 18460416, 'steps': 96147, 'loss/train': 0.9253833889961243} 08/31/2021 06:38:07 - INFO - __main__ - Step 96149: {'lr': 0.00014630952009583542, 'samples': 18460608, 'steps': 96148, 'loss/train': 0.07135600596666336} 08/31/2021 06:38:08 - INFO - __main__ - Step 96150: {'lr': 0.00014630469135347253, 'samples': 18460800, 'steps': 96149, 'loss/train': 0.8290702104568481} 08/31/2021 06:38:08 - INFO - __main__ - Step 96151: {'lr': 0.0001462998626578331, 'samples': 18460992, 'steps': 96150, 'loss/train': 1.0239113569259644} 08/31/2021 06:38:09 - INFO - __main__ - Step 96152: {'lr': 0.00014629503400891936, 'samples': 18461184, 'steps': 96151, 'loss/train': 0.020245488733053207} 08/31/2021 06:38:09 - INFO - __main__ - Step 96153: {'lr': 0.0001462902054067335, 'samples': 18461376, 'steps': 96152, 'loss/train': 0.7809863090515137} 08/31/2021 06:38:09 - INFO - __main__ - Step 96154: {'lr': 0.00014628537685127765, 'samples': 18461568, 'steps': 96153, 'loss/train': 0.9039298892021179} 08/31/2021 06:38:11 - INFO - __main__ - Step 96155: {'lr': 0.00014628054834255402, 'samples': 18461760, 'steps': 96154, 'loss/train': 0.36696186661720276} 08/31/2021 06:38:11 - INFO - __main__ - Step 96156: {'lr': 0.0001462757198805648, 'samples': 18461952, 'steps': 96155, 'loss/train': 0.8395249247550964} 08/31/2021 06:38:12 - INFO - __main__ - Step 96157: {'lr': 0.00014627089146531207, 'samples': 18462144, 'steps': 96156, 'loss/train': 2.1035115718841553} 08/31/2021 06:38:12 - INFO - __main__ - Step 96158: {'lr': 0.00014626606309679812, 'samples': 18462336, 'steps': 96157, 'loss/train': 0.9743198156356812} 08/31/2021 06:38:12 - INFO - __main__ - Step 96159: {'lr': 0.00014626123477502517, 'samples': 18462528, 'steps': 96158, 'loss/train': 1.0650761127471924} 08/31/2021 06:38:14 - INFO - __main__ - Step 96160: {'lr': 0.00014625640649999522, 'samples': 18462720, 'steps': 96159, 'loss/train': 0.9188827872276306} 08/31/2021 06:38:14 - INFO - __main__ - Step 96161: {'lr': 0.00014625157827171054, 'samples': 18462912, 'steps': 96160, 'loss/train': 0.9631311893463135} 08/31/2021 06:38:15 - INFO - __main__ - Step 96162: {'lr': 0.00014624675009017332, 'samples': 18463104, 'steps': 96161, 'loss/train': 1.8554682731628418} 08/31/2021 06:38:15 - INFO - __main__ - Step 96163: {'lr': 0.00014624192195538568, 'samples': 18463296, 'steps': 96162, 'loss/train': 0.9351009130477905} 08/31/2021 06:38:15 - INFO - __main__ - Step 96164: {'lr': 0.00014623709386734984, 'samples': 18463488, 'steps': 96163, 'loss/train': 0.1890821009874344} 08/31/2021 06:38:17 - INFO - __main__ - Step 96165: {'lr': 0.00014623226582606796, 'samples': 18463680, 'steps': 96164, 'loss/train': 0.5857014656066895} 08/31/2021 06:38:17 - INFO - __main__ - Step 96166: {'lr': 0.0001462274378315422, 'samples': 18463872, 'steps': 96165, 'loss/train': 1.310825228691101} 08/31/2021 06:38:18 - INFO - __main__ - Step 96167: {'lr': 0.00014622260988377477, 'samples': 18464064, 'steps': 96166, 'loss/train': 1.0615217685699463} 08/31/2021 06:38:18 - INFO - __main__ - Step 96168: {'lr': 0.00014621778198276787, 'samples': 18464256, 'steps': 96167, 'loss/train': 1.7803415060043335} 08/31/2021 06:38:18 - INFO - __main__ - Step 96169: {'lr': 0.0001462129541285236, 'samples': 18464448, 'steps': 96168, 'loss/train': 1.4598928689956665} 08/31/2021 06:38:20 - INFO - __main__ - Step 96170: {'lr': 0.0001462081263210442, 'samples': 18464640, 'steps': 96169, 'loss/train': 1.7516891956329346} 08/31/2021 06:38:21 - INFO - __main__ - Step 96171: {'lr': 0.00014620329856033175, 'samples': 18464832, 'steps': 96170, 'loss/train': 1.750167965888977} 08/31/2021 06:38:21 - INFO - __main__ - Step 96172: {'lr': 0.00014619847084638854, 'samples': 18465024, 'steps': 96171, 'loss/train': 0.052175041288137436} 08/31/2021 06:38:22 - INFO - __main__ - Step 96173: {'lr': 0.00014619364317921667, 'samples': 18465216, 'steps': 96172, 'loss/train': 1.6027766466140747} 08/31/2021 06:38:22 - INFO - __main__ - Step 96174: {'lr': 0.00014618881555881837, 'samples': 18465408, 'steps': 96173, 'loss/train': 1.1963965892791748} 08/31/2021 06:38:22 - INFO - __main__ - Step 96175: {'lr': 0.00014618398798519583, 'samples': 18465600, 'steps': 96174, 'loss/train': 0.016732508316636086} 08/31/2021 06:38:23 - INFO - __main__ - Step 96176: {'lr': 0.00014617916045835114, 'samples': 18465792, 'steps': 96175, 'loss/train': 0.015626948326826096} 08/31/2021 06:38:24 - INFO - __main__ - Step 96177: {'lr': 0.0001461743329782865, 'samples': 18465984, 'steps': 96176, 'loss/train': 0.39935383200645447} 08/31/2021 06:38:25 - INFO - __main__ - Step 96178: {'lr': 0.00014616950554500414, 'samples': 18466176, 'steps': 96177, 'loss/train': 1.5581797361373901} 08/31/2021 06:38:25 - INFO - __main__ - Step 96179: {'lr': 0.00014616467815850614, 'samples': 18466368, 'steps': 96178, 'loss/train': 0.06322317570447922} 08/31/2021 06:38:25 - INFO - __main__ - Step 96180: {'lr': 0.00014615985081879477, 'samples': 18466560, 'steps': 96179, 'loss/train': 0.6338975429534912} 08/31/2021 06:38:26 - INFO - __main__ - Step 96181: {'lr': 0.0001461550235258722, 'samples': 18466752, 'steps': 96180, 'loss/train': 1.497671127319336} 08/31/2021 06:38:27 - INFO - __main__ - Step 96182: {'lr': 0.00014615019627974054, 'samples': 18466944, 'steps': 96181, 'loss/train': 1.5744549036026} 08/31/2021 06:38:28 - INFO - __main__ - Step 96183: {'lr': 0.000146145369080402, 'samples': 18467136, 'steps': 96182, 'loss/train': 1.204583764076233} 08/31/2021 06:38:28 - INFO - __main__ - Step 96184: {'lr': 0.00014614054192785874, 'samples': 18467328, 'steps': 96183, 'loss/train': 1.363812804222107} 08/31/2021 06:38:28 - INFO - __main__ - Step 96185: {'lr': 0.00014613571482211297, 'samples': 18467520, 'steps': 96184, 'loss/train': 0.026242824271321297} 08/31/2021 06:38:29 - INFO - __main__ - Step 96186: {'lr': 0.00014613088776316684, 'samples': 18467712, 'steps': 96185, 'loss/train': 1.497455358505249} 08/31/2021 06:38:30 - INFO - __main__ - Step 96187: {'lr': 0.00014612606075102252, 'samples': 18467904, 'steps': 96186, 'loss/train': 0.8946971893310547} 08/31/2021 06:38:31 - INFO - __main__ - Step 96188: {'lr': 0.00014612123378568217, 'samples': 18468096, 'steps': 96187, 'loss/train': 1.1089404821395874} 08/31/2021 06:38:31 - INFO - __main__ - Step 96189: {'lr': 0.00014611640686714805, 'samples': 18468288, 'steps': 96188, 'loss/train': 1.4452825784683228} 08/31/2021 06:38:31 - INFO - __main__ - Step 96190: {'lr': 0.00014611157999542228, 'samples': 18468480, 'steps': 96189, 'loss/train': 1.0604840517044067} 08/31/2021 06:38:32 - INFO - __main__ - Step 96191: {'lr': 0.000146106753170507, 'samples': 18468672, 'steps': 96190, 'loss/train': 1.4411914348602295} 08/31/2021 06:38:32 - INFO - __main__ - Step 96192: {'lr': 0.00014610192639240443, 'samples': 18468864, 'steps': 96191, 'loss/train': 1.1247835159301758} 08/31/2021 06:38:34 - INFO - __main__ - Step 96193: {'lr': 0.00014609709966111666, 'samples': 18469056, 'steps': 96192, 'loss/train': 1.1377722024917603} 08/31/2021 06:38:34 - INFO - __main__ - Step 96194: {'lr': 0.00014609227297664602, 'samples': 18469248, 'steps': 96193, 'loss/train': 0.8000820279121399} 08/31/2021 06:38:34 - INFO - __main__ - Step 96195: {'lr': 0.00014608744633899453, 'samples': 18469440, 'steps': 96194, 'loss/train': 1.9709008932113647} 08/31/2021 06:38:35 - INFO - __main__ - Step 96196: {'lr': 0.00014608261974816445, 'samples': 18469632, 'steps': 96195, 'loss/train': 1.4203158617019653} 08/31/2021 06:38:35 - INFO - __main__ - Step 96197: {'lr': 0.00014607779320415795, 'samples': 18469824, 'steps': 96196, 'loss/train': 1.8641550540924072} 08/31/2021 06:38:37 - INFO - __main__ - Step 96198: {'lr': 0.00014607296670697718, 'samples': 18470016, 'steps': 96197, 'loss/train': 1.3603923320770264} 08/31/2021 06:38:38 - INFO - __main__ - Step 96199: {'lr': 0.00014606814025662436, 'samples': 18470208, 'steps': 96198, 'loss/train': 1.0139391422271729} 08/31/2021 06:38:38 - INFO - __main__ - Step 96200: {'lr': 0.0001460633138531016, 'samples': 18470400, 'steps': 96199, 'loss/train': 1.1819133758544922} 08/31/2021 06:38:38 - INFO - __main__ - Step 96201: {'lr': 0.0001460584874964111, 'samples': 18470592, 'steps': 96200, 'loss/train': 1.895321011543274} 08/31/2021 06:38:39 - INFO - __main__ - Step 96202: {'lr': 0.0001460536611865551, 'samples': 18470784, 'steps': 96201, 'loss/train': 1.1414915323257446} 08/31/2021 06:38:41 - INFO - __main__ - Step 96203: {'lr': 0.0001460488349235357, 'samples': 18470976, 'steps': 96202, 'loss/train': 1.4577420949935913} 08/31/2021 06:38:41 - INFO - __main__ - Step 96204: {'lr': 0.00014604400870735508, 'samples': 18471168, 'steps': 96203, 'loss/train': 0.09180320054292679} 08/31/2021 06:38:41 - INFO - __main__ - Step 96205: {'lr': 0.0001460391825380154, 'samples': 18471360, 'steps': 96204, 'loss/train': 1.5880860090255737} 08/31/2021 06:38:42 - INFO - __main__ - Step 96206: {'lr': 0.0001460343564155189, 'samples': 18471552, 'steps': 96205, 'loss/train': 1.0898611545562744} 08/31/2021 06:38:42 - INFO - __main__ - Step 96207: {'lr': 0.00014602953033986766, 'samples': 18471744, 'steps': 96206, 'loss/train': 1.5243327617645264} 08/31/2021 06:38:42 - INFO - __main__ - Step 96208: {'lr': 0.00014602470431106392, 'samples': 18471936, 'steps': 96207, 'loss/train': 0.8291990160942078} 08/31/2021 06:38:44 - INFO - __main__ - Step 96209: {'lr': 0.00014601987832910988, 'samples': 18472128, 'steps': 96208, 'loss/train': 1.0208977460861206} 08/31/2021 06:38:45 - INFO - __main__ - Step 96210: {'lr': 0.00014601505239400763, 'samples': 18472320, 'steps': 96209, 'loss/train': 0.9803305864334106} 08/31/2021 06:38:45 - INFO - __main__ - Step 96211: {'lr': 0.00014601022650575943, 'samples': 18472512, 'steps': 96210, 'loss/train': 1.577696681022644} 08/31/2021 06:38:45 - INFO - __main__ - Step 96212: {'lr': 0.0001460054006643674, 'samples': 18472704, 'steps': 96211, 'loss/train': 1.5156254768371582} 08/31/2021 06:38:46 - INFO - __main__ - Step 96213: {'lr': 0.00014600057486983373, 'samples': 18472896, 'steps': 96212, 'loss/train': 1.5680447816848755} 08/31/2021 06:38:47 - INFO - __main__ - Step 96214: {'lr': 0.00014599574912216063, 'samples': 18473088, 'steps': 96213, 'loss/train': 1.3257542848587036} 08/31/2021 06:38:48 - INFO - __main__ - Step 96215: {'lr': 0.00014599092342135018, 'samples': 18473280, 'steps': 96214, 'loss/train': 0.5425242185592651} 08/31/2021 06:38:48 - INFO - __main__ - Step 96216: {'lr': 0.00014598609776740474, 'samples': 18473472, 'steps': 96215, 'loss/train': 1.023545742034912} 08/31/2021 06:38:48 - INFO - __main__ - Step 96217: {'lr': 0.00014598127216032628, 'samples': 18473664, 'steps': 96216, 'loss/train': 1.1007229089736938} 08/31/2021 06:38:49 - INFO - __main__ - Step 96218: {'lr': 0.00014597644660011705, 'samples': 18473856, 'steps': 96217, 'loss/train': 0.6493818759918213} 08/31/2021 06:38:50 - INFO - __main__ - Step 96219: {'lr': 0.0001459716210867792, 'samples': 18474048, 'steps': 96218, 'loss/train': 1.0470054149627686} 08/31/2021 06:38:51 - INFO - __main__ - Step 96220: {'lr': 0.00014596679562031494, 'samples': 18474240, 'steps': 96219, 'loss/train': 1.376570224761963} 08/31/2021 06:38:51 - INFO - __main__ - Step 96221: {'lr': 0.0001459619702007264, 'samples': 18474432, 'steps': 96220, 'loss/train': 0.771737277507782} 08/31/2021 06:38:51 - INFO - __main__ - Step 96222: {'lr': 0.00014595714482801587, 'samples': 18474624, 'steps': 96221, 'loss/train': 1.2539572715759277} 08/31/2021 06:38:52 - INFO - __main__ - Step 96223: {'lr': 0.0001459523195021854, 'samples': 18474816, 'steps': 96222, 'loss/train': 1.1359412670135498} 08/31/2021 06:38:53 - INFO - __main__ - Step 96224: {'lr': 0.0001459474942232372, 'samples': 18475008, 'steps': 96223, 'loss/train': 0.9288005232810974} 08/31/2021 06:38:54 - INFO - __main__ - Step 96225: {'lr': 0.00014594266899117347, 'samples': 18475200, 'steps': 96224, 'loss/train': 0.9577907919883728} 08/31/2021 06:38:54 - INFO - __main__ - Step 96226: {'lr': 0.00014593784380599638, 'samples': 18475392, 'steps': 96225, 'loss/train': 0.6971433758735657} 08/31/2021 06:38:54 - INFO - __main__ - Step 96227: {'lr': 0.0001459330186677082, 'samples': 18475584, 'steps': 96226, 'loss/train': 1.4742531776428223} 08/31/2021 06:38:55 - INFO - __main__ - Step 96228: {'lr': 0.00014592819357631088, 'samples': 18475776, 'steps': 96227, 'loss/train': 0.7408217191696167} 08/31/2021 06:38:56 - INFO - __main__ - Step 96229: {'lr': 0.00014592336853180672, 'samples': 18475968, 'steps': 96228, 'loss/train': 1.0366967916488647} 08/31/2021 06:38:57 - INFO - __main__ - Step 96230: {'lr': 0.00014591854353419786, 'samples': 18476160, 'steps': 96229, 'loss/train': 1.0335954427719116} 08/31/2021 06:38:57 - INFO - __main__ - Step 96231: {'lr': 0.0001459137185834865, 'samples': 18476352, 'steps': 96230, 'loss/train': 1.274666428565979} 08/31/2021 06:38:58 - INFO - __main__ - Step 96232: {'lr': 0.00014590889367967482, 'samples': 18476544, 'steps': 96231, 'loss/train': 1.1079967021942139} 08/31/2021 06:38:58 - INFO - __main__ - Step 96233: {'lr': 0.00014590406882276504, 'samples': 18476736, 'steps': 96232, 'loss/train': 1.158400535583496} 08/31/2021 06:38:58 - INFO - __main__ - Step 96234: {'lr': 0.0001458992440127592, 'samples': 18476928, 'steps': 96233, 'loss/train': 0.9737454652786255} 08/31/2021 06:39:00 - INFO - __main__ - Step 96235: {'lr': 0.00014589441924965958, 'samples': 18477120, 'steps': 96234, 'loss/train': 1.9711413383483887} 08/31/2021 06:39:00 - INFO - __main__ - Step 96236: {'lr': 0.00014588959453346834, 'samples': 18477312, 'steps': 96235, 'loss/train': 1.4600412845611572} 08/31/2021 06:39:01 - INFO - __main__ - Step 96237: {'lr': 0.00014588476986418774, 'samples': 18477504, 'steps': 96236, 'loss/train': 1.4354289770126343} 08/31/2021 06:39:01 - INFO - __main__ - Step 96238: {'lr': 0.00014587994524181976, 'samples': 18477696, 'steps': 96237, 'loss/train': 1.4096755981445312} 08/31/2021 06:39:01 - INFO - __main__ - Step 96239: {'lr': 0.00014587512066636666, 'samples': 18477888, 'steps': 96238, 'loss/train': 0.9926196932792664} 08/31/2021 06:39:03 - INFO - __main__ - Step 96240: {'lr': 0.00014587029613783063, 'samples': 18478080, 'steps': 96239, 'loss/train': 1.6718289852142334} 08/31/2021 06:39:03 - INFO - __main__ - Step 96241: {'lr': 0.00014586547165621383, 'samples': 18478272, 'steps': 96240, 'loss/train': 1.2684438228607178} 08/31/2021 06:39:03 - INFO - __main__ - Step 96242: {'lr': 0.00014586064722151842, 'samples': 18478464, 'steps': 96241, 'loss/train': 1.4427820444107056} 08/31/2021 06:39:04 - INFO - __main__ - Step 96243: {'lr': 0.00014585582283374666, 'samples': 18478656, 'steps': 96242, 'loss/train': 0.970063328742981} 08/31/2021 06:39:04 - INFO - __main__ - Step 96244: {'lr': 0.0001458509984929006, 'samples': 18478848, 'steps': 96243, 'loss/train': 1.0904265642166138} 08/31/2021 06:39:06 - INFO - __main__ - Step 96245: {'lr': 0.0001458461741989825, 'samples': 18479040, 'steps': 96244, 'loss/train': 1.0135436058044434} 08/31/2021 06:39:06 - INFO - __main__ - Step 96246: {'lr': 0.0001458413499519945, 'samples': 18479232, 'steps': 96245, 'loss/train': 1.6322095394134521} 08/31/2021 06:39:06 - INFO - __main__ - Step 96247: {'lr': 0.00014583652575193877, 'samples': 18479424, 'steps': 96246, 'loss/train': 0.6143170595169067} 08/31/2021 06:39:07 - INFO - __main__ - Step 96248: {'lr': 0.00014583170159881758, 'samples': 18479616, 'steps': 96247, 'loss/train': 2.3994288444519043} 08/31/2021 06:39:07 - INFO - __main__ - Step 96249: {'lr': 0.00014582687749263297, 'samples': 18479808, 'steps': 96248, 'loss/train': 1.0424555540084839} 08/31/2021 06:39:09 - INFO - __main__ - Step 96250: {'lr': 0.00014582205343338712, 'samples': 18480000, 'steps': 96249, 'loss/train': 1.6522561311721802} 08/31/2021 06:39:10 - INFO - __main__ - Step 96251: {'lr': 0.00014581722942108227, 'samples': 18480192, 'steps': 96250, 'loss/train': 1.340059518814087} 08/31/2021 06:39:10 - INFO - __main__ - Step 96252: {'lr': 0.00014581240545572056, 'samples': 18480384, 'steps': 96251, 'loss/train': 1.5433372259140015} 08/31/2021 06:39:10 - INFO - __main__ - Step 96253: {'lr': 0.00014580758153730417, 'samples': 18480576, 'steps': 96252, 'loss/train': 1.553223729133606} 08/31/2021 06:39:11 - INFO - __main__ - Step 96254: {'lr': 0.0001458027576658353, 'samples': 18480768, 'steps': 96253, 'loss/train': 1.074208378791809} 08/31/2021 06:39:13 - INFO - __main__ - Step 96255: {'lr': 0.00014579793384131607, 'samples': 18480960, 'steps': 96254, 'loss/train': 1.513020634651184} 08/31/2021 06:39:13 - INFO - __main__ - Step 96256: {'lr': 0.0001457931100637487, 'samples': 18481152, 'steps': 96255, 'loss/train': 1.369976282119751} 08/31/2021 06:39:14 - INFO - __main__ - Step 96257: {'lr': 0.00014578828633313528, 'samples': 18481344, 'steps': 96256, 'loss/train': 1.3554977178573608} 08/31/2021 06:39:14 - INFO - __main__ - Step 96258: {'lr': 0.0001457834626494781, 'samples': 18481536, 'steps': 96257, 'loss/train': 1.2575852870941162} 08/31/2021 06:39:14 - INFO - __main__ - Step 96259: {'lr': 0.00014577863901277943, 'samples': 18481728, 'steps': 96258, 'loss/train': 0.28453329205513} 08/31/2021 06:39:15 - INFO - __main__ - Step 96260: {'lr': 0.00014577381542304113, 'samples': 18481920, 'steps': 96259, 'loss/train': 0.01695213094353676} 08/31/2021 06:39:15 - INFO - __main__ - Step 96261: {'lr': 0.0001457689918802656, 'samples': 18482112, 'steps': 96260, 'loss/train': 1.1533992290496826} 08/31/2021 06:39:16 - INFO - __main__ - Step 96262: {'lr': 0.0001457641683844549, 'samples': 18482304, 'steps': 96261, 'loss/train': 0.1673988550901413} 08/31/2021 06:39:17 - INFO - __main__ - Step 96263: {'lr': 0.00014575934493561127, 'samples': 18482496, 'steps': 96262, 'loss/train': 0.9002057313919067} 08/31/2021 06:39:17 - INFO - __main__ - Step 96264: {'lr': 0.00014575452153373688, 'samples': 18482688, 'steps': 96263, 'loss/train': 1.111714482307434} 08/31/2021 06:39:18 - INFO - __main__ - Step 96265: {'lr': 0.0001457496981788339, 'samples': 18482880, 'steps': 96264, 'loss/train': 0.9177592396736145} 08/31/2021 06:39:18 - INFO - __main__ - Step 96266: {'lr': 0.0001457448748709045, 'samples': 18483072, 'steps': 96265, 'loss/train': 0.518993079662323} 08/31/2021 06:39:19 - INFO - __main__ - Step 96267: {'lr': 0.00014574005160995082, 'samples': 18483264, 'steps': 96266, 'loss/train': 5.431366443634033} 08/31/2021 06:39:20 - INFO - __main__ - Step 96268: {'lr': 0.0001457352283959751, 'samples': 18483456, 'steps': 96267, 'loss/train': 1.1619385480880737} 08/31/2021 06:39:20 - INFO - __main__ - Step 96269: {'lr': 0.00014573040522897944, 'samples': 18483648, 'steps': 96268, 'loss/train': 1.6041375398635864} 08/31/2021 06:39:20 - INFO - __main__ - Step 96270: {'lr': 0.0001457255821089662, 'samples': 18483840, 'steps': 96269, 'loss/train': 1.4932875633239746} 08/31/2021 06:39:21 - INFO - __main__ - Step 96271: {'lr': 0.00014572075903593727, 'samples': 18484032, 'steps': 96270, 'loss/train': 1.471190333366394} 08/31/2021 06:39:22 - INFO - __main__ - Step 96272: {'lr': 0.00014571593600989495, 'samples': 18484224, 'steps': 96271, 'loss/train': 1.482348084449768} 08/31/2021 06:39:23 - INFO - __main__ - Step 96273: {'lr': 0.00014571111303084144, 'samples': 18484416, 'steps': 96272, 'loss/train': 0.9211733937263489} 08/31/2021 06:39:23 - INFO - __main__ - Step 96274: {'lr': 0.0001457062900987789, 'samples': 18484608, 'steps': 96273, 'loss/train': 1.0731853246688843} 08/31/2021 06:39:23 - INFO - __main__ - Step 96275: {'lr': 0.00014570146721370946, 'samples': 18484800, 'steps': 96274, 'loss/train': 1.0934782028198242} 08/31/2021 06:39:24 - INFO - __main__ - Step 96276: {'lr': 0.00014569664437563535, 'samples': 18484992, 'steps': 96275, 'loss/train': 1.7682751417160034} 08/31/2021 06:39:26 - INFO - __main__ - Step 96277: {'lr': 0.00014569182158455873, 'samples': 18485184, 'steps': 96276, 'loss/train': 0.6615596413612366} 08/31/2021 06:39:26 - INFO - __main__ - Step 96278: {'lr': 0.00014568699884048175, 'samples': 18485376, 'steps': 96277, 'loss/train': 1.212204098701477} 08/31/2021 06:39:26 - INFO - __main__ - Step 96279: {'lr': 0.00014568217614340662, 'samples': 18485568, 'steps': 96278, 'loss/train': 0.6447852253913879} 08/31/2021 06:39:27 - INFO - __main__ - Step 96280: {'lr': 0.00014567735349333547, 'samples': 18485760, 'steps': 96279, 'loss/train': 0.8947270512580872} 08/31/2021 06:39:27 - INFO - __main__ - Step 96281: {'lr': 0.0001456725308902705, 'samples': 18485952, 'steps': 96280, 'loss/train': 0.05857066065073013} 08/31/2021 06:39:29 - INFO - __main__ - Step 96282: {'lr': 0.0001456677083342139, 'samples': 18486144, 'steps': 96281, 'loss/train': 1.1134356260299683} 08/31/2021 06:39:29 - INFO - __main__ - Step 96283: {'lr': 0.0001456628858251679, 'samples': 18486336, 'steps': 96282, 'loss/train': 0.3103831708431244} 08/31/2021 06:39:30 - INFO - __main__ - Step 96284: {'lr': 0.00014565806336313446, 'samples': 18486528, 'steps': 96283, 'loss/train': 0.14205652475357056} 08/31/2021 06:39:30 - INFO - __main__ - Step 96285: {'lr': 0.00014565324094811593, 'samples': 18486720, 'steps': 96284, 'loss/train': 0.7130700349807739} 08/31/2021 06:39:30 - INFO - __main__ - Step 96286: {'lr': 0.00014564841858011446, 'samples': 18486912, 'steps': 96285, 'loss/train': 0.7651422023773193} 08/31/2021 06:39:33 - INFO - __main__ - Step 96287: {'lr': 0.00014564359625913217, 'samples': 18487104, 'steps': 96286, 'loss/train': 1.409956693649292} 08/31/2021 06:39:33 - INFO - __main__ - Step 96288: {'lr': 0.00014563877398517127, 'samples': 18487296, 'steps': 96287, 'loss/train': 0.7965775728225708} 08/31/2021 06:39:34 - INFO - __main__ - Step 96289: {'lr': 0.00014563395175823393, 'samples': 18487488, 'steps': 96288, 'loss/train': 1.124233603477478} 08/31/2021 06:39:34 - INFO - __main__ - Step 96290: {'lr': 0.0001456291295783223, 'samples': 18487680, 'steps': 96289, 'loss/train': 0.57718425989151} 08/31/2021 06:39:34 - INFO - __main__ - Step 96291: {'lr': 0.00014562430744543861, 'samples': 18487872, 'steps': 96290, 'loss/train': 1.58738112449646} 08/31/2021 06:39:35 - INFO - __main__ - Step 96292: {'lr': 0.00014561948535958498, 'samples': 18488064, 'steps': 96291, 'loss/train': 0.6605281233787537} 08/31/2021 06:39:36 - INFO - __main__ - Step 96293: {'lr': 0.00014561466332076362, 'samples': 18488256, 'steps': 96292, 'loss/train': 0.3813512623310089} 08/31/2021 06:39:37 - INFO - __main__ - Step 96294: {'lr': 0.00014560984132897664, 'samples': 18488448, 'steps': 96293, 'loss/train': 0.4295157194137573} 08/31/2021 06:39:38 - INFO - __main__ - Step 96295: {'lr': 0.00014560501938422628, 'samples': 18488640, 'steps': 96294, 'loss/train': 0.814062774181366} 08/31/2021 06:39:38 - INFO - __main__ - Step 96296: {'lr': 0.00014560019748651476, 'samples': 18488832, 'steps': 96295, 'loss/train': 1.535862922668457} 08/31/2021 06:39:38 - INFO - __main__ - Step 96297: {'lr': 0.00014559537563584412, 'samples': 18489024, 'steps': 96296, 'loss/train': 0.919605553150177} 08/31/2021 06:39:39 - INFO - __main__ - Step 96298: {'lr': 0.0001455905538322166, 'samples': 18489216, 'steps': 96297, 'loss/train': 1.0970889329910278} 08/31/2021 06:39:40 - INFO - __main__ - Step 96299: {'lr': 0.0001455857320756343, 'samples': 18489408, 'steps': 96298, 'loss/train': 0.47369617223739624} 08/31/2021 06:39:41 - INFO - __main__ - Step 96300: {'lr': 0.0001455809103660995, 'samples': 18489600, 'steps': 96299, 'loss/train': 1.1267645359039307} 08/31/2021 06:39:41 - INFO - __main__ - Step 96301: {'lr': 0.00014557608870361432, 'samples': 18489792, 'steps': 96300, 'loss/train': 1.2309824228286743} 08/31/2021 06:39:41 - INFO - __main__ - Step 96302: {'lr': 0.00014557126708818096, 'samples': 18489984, 'steps': 96301, 'loss/train': 1.3566261529922485} 08/31/2021 06:39:42 - INFO - __main__ - Step 96303: {'lr': 0.00014556644551980157, 'samples': 18490176, 'steps': 96302, 'loss/train': 0.9990600347518921} 08/31/2021 06:39:43 - INFO - __main__ - Step 96304: {'lr': 0.00014556162399847832, 'samples': 18490368, 'steps': 96303, 'loss/train': 0.5522448420524597} 08/31/2021 06:39:44 - INFO - __main__ - Step 96305: {'lr': 0.0001455568025242134, 'samples': 18490560, 'steps': 96304, 'loss/train': 1.4327536821365356} 08/31/2021 06:39:44 - INFO - __main__ - Step 96306: {'lr': 0.00014555198109700898, 'samples': 18490752, 'steps': 96305, 'loss/train': 1.444364309310913} 08/31/2021 06:39:44 - INFO - __main__ - Step 96307: {'lr': 0.00014554715971686722, 'samples': 18490944, 'steps': 96306, 'loss/train': 0.47533276677131653} 08/31/2021 06:39:45 - INFO - __main__ - Step 96308: {'lr': 0.00014554233838379028, 'samples': 18491136, 'steps': 96307, 'loss/train': 1.3499643802642822} 08/31/2021 06:39:47 - INFO - __main__ - Step 96309: {'lr': 0.00014553751709778037, 'samples': 18491328, 'steps': 96308, 'loss/train': 1.3267356157302856} 08/31/2021 06:39:47 - INFO - __main__ - Step 96310: {'lr': 0.00014553269585883974, 'samples': 18491520, 'steps': 96309, 'loss/train': 1.4946445226669312} 08/31/2021 06:39:48 - INFO - __main__ - Step 96311: {'lr': 0.00014552787466697037, 'samples': 18491712, 'steps': 96310, 'loss/train': 0.9783613681793213} 08/31/2021 06:39:48 - INFO - __main__ - Step 96312: {'lr': 0.0001455230535221745, 'samples': 18491904, 'steps': 96311, 'loss/train': 0.9258230328559875} 08/31/2021 06:39:48 - INFO - __main__ - Step 96313: {'lr': 0.00014551823242445436, 'samples': 18492096, 'steps': 96312, 'loss/train': 0.8785537481307983} 08/31/2021 06:39:50 - INFO - __main__ - Step 96314: {'lr': 0.00014551341137381208, 'samples': 18492288, 'steps': 96313, 'loss/train': 1.3441991806030273} 08/31/2021 06:39:50 - INFO - __main__ - Step 96315: {'lr': 0.00014550859037024981, 'samples': 18492480, 'steps': 96314, 'loss/train': 1.3358465433120728} 08/31/2021 06:39:51 - INFO - __main__ - Step 96316: {'lr': 0.00014550376941376984, 'samples': 18492672, 'steps': 96315, 'loss/train': 1.0215684175491333} 08/31/2021 06:39:51 - INFO - __main__ - Step 96317: {'lr': 0.0001454989485043742, 'samples': 18492864, 'steps': 96316, 'loss/train': 1.2991305589675903} 08/31/2021 06:39:51 - INFO - __main__ - Step 96318: {'lr': 0.00014549412764206513, 'samples': 18493056, 'steps': 96317, 'loss/train': 1.2405503988265991} 08/31/2021 06:39:53 - INFO - __main__ - Step 96319: {'lr': 0.0001454893068268448, 'samples': 18493248, 'steps': 96318, 'loss/train': 0.9758899211883545} 08/31/2021 06:39:53 - INFO - __main__ - Step 96320: {'lr': 0.00014548448605871536, 'samples': 18493440, 'steps': 96319, 'loss/train': 1.2064220905303955} 08/31/2021 06:39:54 - INFO - __main__ - Step 96321: {'lr': 0.00014547966533767903, 'samples': 18493632, 'steps': 96320, 'loss/train': 0.5160839557647705} 08/31/2021 06:39:54 - INFO - __main__ - Step 96322: {'lr': 0.00014547484466373792, 'samples': 18493824, 'steps': 96321, 'loss/train': 0.7675943374633789} 08/31/2021 06:39:54 - INFO - __main__ - Step 96323: {'lr': 0.00014547002403689436, 'samples': 18494016, 'steps': 96322, 'loss/train': 1.1352169513702393} 08/31/2021 06:39:55 - INFO - __main__ - Step 96324: {'lr': 0.00014546520345715025, 'samples': 18494208, 'steps': 96323, 'loss/train': 1.4027026891708374} 08/31/2021 06:39:56 - INFO - __main__ - Step 96325: {'lr': 0.00014546038292450792, 'samples': 18494400, 'steps': 96324, 'loss/train': 1.0695104598999023} 08/31/2021 06:39:57 - INFO - __main__ - Step 96326: {'lr': 0.00014545556243896957, 'samples': 18494592, 'steps': 96325, 'loss/train': 1.5640861988067627} 08/31/2021 06:39:57 - INFO - __main__ - Step 96327: {'lr': 0.00014545074200053728, 'samples': 18494784, 'steps': 96326, 'loss/train': 0.48662298917770386} 08/31/2021 06:39:58 - INFO - __main__ - Step 96328: {'lr': 0.0001454459216092133, 'samples': 18494976, 'steps': 96327, 'loss/train': 0.18251918256282806} 08/31/2021 06:39:58 - INFO - __main__ - Step 96329: {'lr': 0.00014544110126499975, 'samples': 18495168, 'steps': 96328, 'loss/train': 0.32175591588020325} 08/31/2021 06:40:00 - INFO - __main__ - Step 96330: {'lr': 0.00014543628096789886, 'samples': 18495360, 'steps': 96329, 'loss/train': 1.3884150981903076} 08/31/2021 06:40:00 - INFO - __main__ - Step 96331: {'lr': 0.00014543146071791275, 'samples': 18495552, 'steps': 96330, 'loss/train': 0.31375840306282043} 08/31/2021 06:40:00 - INFO - __main__ - Step 96332: {'lr': 0.0001454266405150436, 'samples': 18495744, 'steps': 96331, 'loss/train': 0.21584570407867432} 08/31/2021 06:40:01 - INFO - __main__ - Step 96333: {'lr': 0.00014542182035929364, 'samples': 18495936, 'steps': 96332, 'loss/train': 0.8214980363845825} 08/31/2021 06:40:01 - INFO - __main__ - Step 96334: {'lr': 0.00014541700025066495, 'samples': 18496128, 'steps': 96333, 'loss/train': 0.030123021453619003} 08/31/2021 06:40:03 - INFO - __main__ - Step 96335: {'lr': 0.00014541218018915975, 'samples': 18496320, 'steps': 96334, 'loss/train': 0.6474719047546387} 08/31/2021 06:40:03 - INFO - __main__ - Step 96336: {'lr': 0.0001454073601747802, 'samples': 18496512, 'steps': 96335, 'loss/train': 0.9324410557746887} 08/31/2021 06:40:03 - INFO - __main__ - Step 96337: {'lr': 0.00014540254020752857, 'samples': 18496704, 'steps': 96336, 'loss/train': 1.7824712991714478} 08/31/2021 06:40:04 - INFO - __main__ - Step 96338: {'lr': 0.00014539772028740689, 'samples': 18496896, 'steps': 96337, 'loss/train': 1.115123987197876} 08/31/2021 06:40:04 - INFO - __main__ - Step 96339: {'lr': 0.00014539290041441736, 'samples': 18497088, 'steps': 96338, 'loss/train': 0.8977028727531433} 08/31/2021 06:40:06 - INFO - __main__ - Step 96340: {'lr': 0.00014538808058856217, 'samples': 18497280, 'steps': 96339, 'loss/train': 1.3324828147888184} 08/31/2021 06:40:06 - INFO - __main__ - Step 96341: {'lr': 0.0001453832608098435, 'samples': 18497472, 'steps': 96340, 'loss/train': 1.2505428791046143} 08/31/2021 06:40:07 - INFO - __main__ - Step 96342: {'lr': 0.0001453784410782635, 'samples': 18497664, 'steps': 96341, 'loss/train': 0.195723295211792} 08/31/2021 06:40:07 - INFO - __main__ - Step 96343: {'lr': 0.00014537362139382438, 'samples': 18497856, 'steps': 96342, 'loss/train': 1.603096842765808} 08/31/2021 06:40:07 - INFO - __main__ - Step 96344: {'lr': 0.00014536880175652827, 'samples': 18498048, 'steps': 96343, 'loss/train': 0.4415269196033478} 08/31/2021 06:40:09 - INFO - __main__ - Step 96345: {'lr': 0.0001453639821663774, 'samples': 18498240, 'steps': 96344, 'loss/train': 1.3505609035491943} 08/31/2021 06:40:09 - INFO - __main__ - Step 96346: {'lr': 0.0001453591626233739, 'samples': 18498432, 'steps': 96345, 'loss/train': 1.7501417398452759} 08/31/2021 06:40:09 - INFO - __main__ - Step 96347: {'lr': 0.00014535434312751993, 'samples': 18498624, 'steps': 96346, 'loss/train': 0.20759375393390656} 08/31/2021 06:40:10 - INFO - __main__ - Step 96348: {'lr': 0.00014534952367881764, 'samples': 18498816, 'steps': 96347, 'loss/train': 1.3575986623764038} 08/31/2021 06:40:10 - INFO - __main__ - Step 96349: {'lr': 0.0001453447042772693, 'samples': 18499008, 'steps': 96348, 'loss/train': 1.2907123565673828} 08/31/2021 06:40:12 - INFO - __main__ - Step 96350: {'lr': 0.0001453398849228771, 'samples': 18499200, 'steps': 96349, 'loss/train': 1.1128191947937012} 08/31/2021 06:40:12 - INFO - __main__ - Step 96351: {'lr': 0.00014533506561564306, 'samples': 18499392, 'steps': 96350, 'loss/train': 4.5072526931762695} 08/31/2021 06:40:13 - INFO - __main__ - Step 96352: {'lr': 0.0001453302463555694, 'samples': 18499584, 'steps': 96351, 'loss/train': 3.8935582637786865} 08/31/2021 06:40:13 - INFO - __main__ - Step 96353: {'lr': 0.0001453254271426583, 'samples': 18499776, 'steps': 96352, 'loss/train': 1.6529327630996704} 08/31/2021 06:40:13 - INFO - __main__ - Step 96354: {'lr': 0.00014532060797691195, 'samples': 18499968, 'steps': 96353, 'loss/train': 1.1388963460922241} 08/31/2021 06:40:14 - INFO - __main__ - Step 96355: {'lr': 0.00014531578885833255, 'samples': 18500160, 'steps': 96354, 'loss/train': 1.3964173793792725} 08/31/2021 06:40:15 - INFO - __main__ - Step 96356: {'lr': 0.0001453109697869222, 'samples': 18500352, 'steps': 96355, 'loss/train': 1.333149790763855} 08/31/2021 06:40:16 - INFO - __main__ - Step 96357: {'lr': 0.00014530615076268317, 'samples': 18500544, 'steps': 96356, 'loss/train': 3.192753314971924} 08/31/2021 06:40:16 - INFO - __main__ - Step 96358: {'lr': 0.0001453013317856175, 'samples': 18500736, 'steps': 96357, 'loss/train': 0.984138011932373} 08/31/2021 06:40:16 - INFO - __main__ - Step 96359: {'lr': 0.00014529651285572748, 'samples': 18500928, 'steps': 96358, 'loss/train': 1.2412718534469604} 08/31/2021 06:40:17 - INFO - __main__ - Step 96360: {'lr': 0.00014529169397301523, 'samples': 18501120, 'steps': 96359, 'loss/train': 1.121962547302246} 08/31/2021 06:40:18 - INFO - __main__ - Step 96361: {'lr': 0.00014528687513748294, 'samples': 18501312, 'steps': 96360, 'loss/train': 0.6466999650001526} 08/31/2021 06:40:19 - INFO - __main__ - Step 96362: {'lr': 0.0001452820563491327, 'samples': 18501504, 'steps': 96361, 'loss/train': 1.4958207607269287} 08/31/2021 06:40:19 - INFO - __main__ - Step 96363: {'lr': 0.00014527723760796686, 'samples': 18501696, 'steps': 96362, 'loss/train': 0.47631391882896423} 08/31/2021 06:40:19 - INFO - __main__ - Step 96364: {'lr': 0.0001452724189139875, 'samples': 18501888, 'steps': 96363, 'loss/train': 0.6971684694290161} 08/31/2021 06:40:20 - INFO - __main__ - Step 96365: {'lr': 0.0001452676002671967, 'samples': 18502080, 'steps': 96364, 'loss/train': 1.3193436861038208} 08/31/2021 06:40:22 - INFO - __main__ - Step 96366: {'lr': 0.00014526278166759668, 'samples': 18502272, 'steps': 96365, 'loss/train': 1.7253131866455078} 08/31/2021 06:40:22 - INFO - __main__ - Step 96367: {'lr': 0.00014525796311518966, 'samples': 18502464, 'steps': 96366, 'loss/train': 1.3273687362670898} 08/31/2021 06:40:23 - INFO - __main__ - Step 96368: {'lr': 0.00014525314460997777, 'samples': 18502656, 'steps': 96367, 'loss/train': 1.3512158393859863} 08/31/2021 06:40:23 - INFO - __main__ - Step 96369: {'lr': 0.00014524832615196321, 'samples': 18502848, 'steps': 96368, 'loss/train': 0.31403374671936035} 08/31/2021 06:40:23 - INFO - __main__ - Step 96370: {'lr': 0.00014524350774114815, 'samples': 18503040, 'steps': 96369, 'loss/train': 0.9299317002296448} 08/31/2021 06:40:25 - INFO - __main__ - Step 96371: {'lr': 0.0001452386893775347, 'samples': 18503232, 'steps': 96370, 'loss/train': 0.9955225586891174} 08/31/2021 06:40:25 - INFO - __main__ - Step 96372: {'lr': 0.00014523387106112512, 'samples': 18503424, 'steps': 96371, 'loss/train': 0.9980319142341614} 08/31/2021 06:40:26 - INFO - __main__ - Step 96373: {'lr': 0.00014522905279192152, 'samples': 18503616, 'steps': 96372, 'loss/train': 1.5781035423278809} 08/31/2021 06:40:26 - INFO - __main__ - Step 96374: {'lr': 0.00014522423456992612, 'samples': 18503808, 'steps': 96373, 'loss/train': 1.3383437395095825} 08/31/2021 06:40:26 - INFO - __main__ - Step 96375: {'lr': 0.00014521941639514103, 'samples': 18504000, 'steps': 96374, 'loss/train': 1.2594348192214966} 08/31/2021 06:40:28 - INFO - __main__ - Step 96376: {'lr': 0.00014521459826756847, 'samples': 18504192, 'steps': 96375, 'loss/train': 0.6747732758522034} 08/31/2021 06:40:28 - INFO - __main__ - Step 96377: {'lr': 0.0001452097801872107, 'samples': 18504384, 'steps': 96376, 'loss/train': 1.068603277206421} 08/31/2021 06:40:29 - INFO - __main__ - Step 96378: {'lr': 0.0001452049621540697, 'samples': 18504576, 'steps': 96377, 'loss/train': 0.9878383278846741} 08/31/2021 06:40:29 - INFO - __main__ - Step 96379: {'lr': 0.0001452001441681477, 'samples': 18504768, 'steps': 96378, 'loss/train': 0.7187274098396301} 08/31/2021 06:40:29 - INFO - __main__ - Step 96380: {'lr': 0.0001451953262294469, 'samples': 18504960, 'steps': 96379, 'loss/train': 1.415840744972229} 08/31/2021 06:40:30 - INFO - __main__ - Step 96381: {'lr': 0.0001451905083379695, 'samples': 18505152, 'steps': 96380, 'loss/train': 1.1818186044692993} 08/31/2021 06:40:31 - INFO - __main__ - Step 96382: {'lr': 0.00014518569049371758, 'samples': 18505344, 'steps': 96381, 'loss/train': 1.235533595085144} 08/31/2021 06:40:32 - INFO - __main__ - Step 96383: {'lr': 0.00014518087269669338, 'samples': 18505536, 'steps': 96382, 'loss/train': 1.1103447675704956} 08/31/2021 06:40:32 - INFO - __main__ - Step 96384: {'lr': 0.00014517605494689912, 'samples': 18505728, 'steps': 96383, 'loss/train': 1.348720669746399} 08/31/2021 06:40:32 - INFO - __main__ - Step 96385: {'lr': 0.00014517123724433687, 'samples': 18505920, 'steps': 96384, 'loss/train': 1.0924721956253052} 08/31/2021 06:40:33 - INFO - __main__ - Step 96386: {'lr': 0.00014516641958900884, 'samples': 18506112, 'steps': 96385, 'loss/train': 1.239772081375122} 08/31/2021 06:40:34 - INFO - __main__ - Step 96387: {'lr': 0.00014516160198091722, 'samples': 18506304, 'steps': 96386, 'loss/train': 0.5502846240997314} 08/31/2021 06:40:35 - INFO - __main__ - Step 96388: {'lr': 0.00014515678442006416, 'samples': 18506496, 'steps': 96387, 'loss/train': 1.4464579820632935} 08/31/2021 06:40:35 - INFO - __main__ - Step 96389: {'lr': 0.00014515196690645182, 'samples': 18506688, 'steps': 96388, 'loss/train': 1.3351315259933472} 08/31/2021 06:40:35 - INFO - __main__ - Step 96390: {'lr': 0.0001451471494400825, 'samples': 18506880, 'steps': 96389, 'loss/train': 0.6362497806549072} 08/31/2021 06:40:36 - INFO - __main__ - Step 96391: {'lr': 0.00014514233202095816, 'samples': 18507072, 'steps': 96390, 'loss/train': 0.6676924824714661} 08/31/2021 06:40:37 - INFO - __main__ - Step 96392: {'lr': 0.0001451375146490811, 'samples': 18507264, 'steps': 96391, 'loss/train': 0.7405581474304199} 08/31/2021 06:40:38 - INFO - __main__ - Step 96393: {'lr': 0.00014513269732445338, 'samples': 18507456, 'steps': 96392, 'loss/train': 0.9731442332267761} 08/31/2021 06:40:38 - INFO - __main__ - Step 96394: {'lr': 0.00014512788004707733, 'samples': 18507648, 'steps': 96393, 'loss/train': 1.2621420621871948} 08/31/2021 06:40:38 - INFO - __main__ - Step 96395: {'lr': 0.00014512306281695497, 'samples': 18507840, 'steps': 96394, 'loss/train': 1.337965726852417} 08/31/2021 06:40:39 - INFO - __main__ - Step 96396: {'lr': 0.0001451182456340886, 'samples': 18508032, 'steps': 96395, 'loss/train': 1.4848551750183105} 08/31/2021 06:40:40 - INFO - __main__ - Step 96397: {'lr': 0.0001451134284984803, 'samples': 18508224, 'steps': 96396, 'loss/train': 0.6957414150238037} 08/31/2021 06:40:41 - INFO - __main__ - Step 96398: {'lr': 0.00014510861141013226, 'samples': 18508416, 'steps': 96397, 'loss/train': 0.9602775573730469} 08/31/2021 06:40:41 - INFO - __main__ - Step 96399: {'lr': 0.00014510379436904664, 'samples': 18508608, 'steps': 96398, 'loss/train': 1.177664041519165} 08/31/2021 06:40:41 - INFO - __main__ - Step 96400: {'lr': 0.00014509897737522567, 'samples': 18508800, 'steps': 96399, 'loss/train': 1.1421362161636353} 08/31/2021 06:40:42 - INFO - __main__ - Step 96401: {'lr': 0.00014509416042867148, 'samples': 18508992, 'steps': 96400, 'loss/train': 1.108508586883545} 08/31/2021 06:40:42 - INFO - __main__ - Step 96402: {'lr': 0.00014508934352938625, 'samples': 18509184, 'steps': 96401, 'loss/train': 1.3656471967697144} 08/31/2021 06:40:44 - INFO - __main__ - Step 96403: {'lr': 0.00014508452667737212, 'samples': 18509376, 'steps': 96402, 'loss/train': 0.7935662269592285} 08/31/2021 06:40:44 - INFO - __main__ - Step 96404: {'lr': 0.00014507970987263138, 'samples': 18509568, 'steps': 96403, 'loss/train': 0.9253779053688049} 08/31/2021 06:40:44 - INFO - __main__ - Step 96405: {'lr': 0.00014507489311516602, 'samples': 18509760, 'steps': 96404, 'loss/train': 1.4055705070495605} 08/31/2021 06:40:45 - INFO - __main__ - Step 96406: {'lr': 0.00014507007640497828, 'samples': 18509952, 'steps': 96405, 'loss/train': 1.5116320848464966} 08/31/2021 06:40:45 - INFO - __main__ - Step 96407: {'lr': 0.00014506525974207035, 'samples': 18510144, 'steps': 96406, 'loss/train': 0.777008593082428} 08/31/2021 06:40:47 - INFO - __main__ - Step 96408: {'lr': 0.00014506044312644442, 'samples': 18510336, 'steps': 96407, 'loss/train': 5.018985271453857} 08/31/2021 06:40:47 - INFO - __main__ - Step 96409: {'lr': 0.00014505562655810263, 'samples': 18510528, 'steps': 96408, 'loss/train': 1.2292749881744385} 08/31/2021 06:40:48 - INFO - __main__ - Step 96410: {'lr': 0.00014505081003704712, 'samples': 18510720, 'steps': 96409, 'loss/train': 1.1620136499404907} 08/31/2021 06:40:48 - INFO - __main__ - Step 96411: {'lr': 0.00014504599356328013, 'samples': 18510912, 'steps': 96410, 'loss/train': 1.226747989654541} 08/31/2021 06:40:48 - INFO - __main__ - Step 96412: {'lr': 0.00014504117713680376, 'samples': 18511104, 'steps': 96411, 'loss/train': 1.3855684995651245} 08/31/2021 06:40:50 - INFO - __main__ - Step 96413: {'lr': 0.00014503636075762025, 'samples': 18511296, 'steps': 96412, 'loss/train': 1.0377391576766968} 08/31/2021 06:40:50 - INFO - __main__ - Step 96414: {'lr': 0.00014503154442573174, 'samples': 18511488, 'steps': 96413, 'loss/train': 0.703389048576355} 08/31/2021 06:40:51 - INFO - __main__ - Step 96415: {'lr': 0.00014502672814114038, 'samples': 18511680, 'steps': 96414, 'loss/train': 0.11675567179918289} 08/31/2021 06:40:51 - INFO - __main__ - Step 96416: {'lr': 0.00014502191190384834, 'samples': 18511872, 'steps': 96415, 'loss/train': 1.8068205118179321} 08/31/2021 06:40:51 - INFO - __main__ - Step 96417: {'lr': 0.0001450170957138579, 'samples': 18512064, 'steps': 96416, 'loss/train': 1.7567837238311768} 08/31/2021 06:40:52 - INFO - __main__ - Step 96418: {'lr': 0.0001450122795711711, 'samples': 18512256, 'steps': 96417, 'loss/train': 1.176469087600708} 08/31/2021 06:40:54 - INFO - __main__ - Step 96419: {'lr': 0.00014500746347579008, 'samples': 18512448, 'steps': 96418, 'loss/train': 0.14098750054836273} 08/31/2021 06:40:54 - INFO - __main__ - Step 96420: {'lr': 0.00014500264742771713, 'samples': 18512640, 'steps': 96419, 'loss/train': 0.061307135969400406} 08/31/2021 06:40:55 - INFO - __main__ - Step 96421: {'lr': 0.00014499783142695434, 'samples': 18512832, 'steps': 96420, 'loss/train': 0.8625728487968445} 08/31/2021 06:40:55 - INFO - __main__ - Step 96422: {'lr': 0.0001449930154735039, 'samples': 18513024, 'steps': 96421, 'loss/train': 1.5580013990402222} 08/31/2021 06:40:55 - INFO - __main__ - Step 96423: {'lr': 0.00014498819956736798, 'samples': 18513216, 'steps': 96422, 'loss/train': 0.758382260799408} 08/31/2021 06:40:57 - INFO - __main__ - Step 96424: {'lr': 0.00014498338370854877, 'samples': 18513408, 'steps': 96423, 'loss/train': 1.0069499015808105} 08/31/2021 06:40:57 - INFO - __main__ - Step 96425: {'lr': 0.00014497856789704843, 'samples': 18513600, 'steps': 96424, 'loss/train': 1.6022388935089111} 08/31/2021 06:40:58 - INFO - __main__ - Step 96426: {'lr': 0.00014497375213286912, 'samples': 18513792, 'steps': 96425, 'loss/train': 1.3569196462631226} 08/31/2021 06:40:58 - INFO - __main__ - Step 96427: {'lr': 0.00014496893641601302, 'samples': 18513984, 'steps': 96426, 'loss/train': 1.8186877965927124} 08/31/2021 06:40:58 - INFO - __main__ - Step 96428: {'lr': 0.0001449641207464823, 'samples': 18514176, 'steps': 96427, 'loss/train': 1.5529028177261353} 08/31/2021 06:41:00 - INFO - __main__ - Step 96429: {'lr': 0.00014495930512427912, 'samples': 18514368, 'steps': 96428, 'loss/train': 0.265691876411438} 08/31/2021 06:41:00 - INFO - __main__ - Step 96430: {'lr': 0.00014495448954940566, 'samples': 18514560, 'steps': 96429, 'loss/train': 1.021236777305603} 08/31/2021 06:41:01 - INFO - __main__ - Step 96431: {'lr': 0.0001449496740218642, 'samples': 18514752, 'steps': 96430, 'loss/train': 1.1236845254898071} 08/31/2021 06:41:01 - INFO - __main__ - Step 96432: {'lr': 0.00014494485854165667, 'samples': 18514944, 'steps': 96431, 'loss/train': 1.8557336330413818} 08/31/2021 06:41:01 - INFO - __main__ - Step 96433: {'lr': 0.0001449400431087854, 'samples': 18515136, 'steps': 96432, 'loss/train': 1.6843904256820679} 08/31/2021 06:41:03 - INFO - __main__ - Step 96434: {'lr': 0.00014493522772325248, 'samples': 18515328, 'steps': 96433, 'loss/train': 0.560496985912323} 08/31/2021 06:41:04 - INFO - __main__ - Step 96435: {'lr': 0.00014493041238506016, 'samples': 18515520, 'steps': 96434, 'loss/train': 1.0426467657089233} 08/31/2021 06:41:04 - INFO - __main__ - Step 96436: {'lr': 0.00014492559709421054, 'samples': 18515712, 'steps': 96435, 'loss/train': 2.2890570163726807} 08/31/2021 06:41:04 - INFO - __main__ - Step 96437: {'lr': 0.00014492078185070583, 'samples': 18515904, 'steps': 96436, 'loss/train': 0.35207101702690125} 08/31/2021 06:41:05 - INFO - __main__ - Step 96438: {'lr': 0.00014491596665454825, 'samples': 18516096, 'steps': 96437, 'loss/train': 0.7135747075080872} 08/31/2021 06:41:05 - INFO - __main__ - Step 96439: {'lr': 0.00014491115150573985, 'samples': 18516288, 'steps': 96438, 'loss/train': 1.0944864749908447} 08/31/2021 06:41:06 - INFO - __main__ - Step 96440: {'lr': 0.00014490633640428291, 'samples': 18516480, 'steps': 96439, 'loss/train': 0.7258082628250122} 08/31/2021 06:41:07 - INFO - __main__ - Step 96441: {'lr': 0.00014490152135017954, 'samples': 18516672, 'steps': 96440, 'loss/train': 1.434946060180664} 08/31/2021 06:41:07 - INFO - __main__ - Step 96442: {'lr': 0.0001448967063434319, 'samples': 18516864, 'steps': 96441, 'loss/train': 0.7426838874816895} 08/31/2021 06:41:07 - INFO - __main__ - Step 96443: {'lr': 0.00014489189138404217, 'samples': 18517056, 'steps': 96442, 'loss/train': 0.908612072467804} 08/31/2021 06:41:08 - INFO - __main__ - Step 96444: {'lr': 0.00014488707647201268, 'samples': 18517248, 'steps': 96443, 'loss/train': 1.6481070518493652} 08/31/2021 06:41:09 - INFO - __main__ - Step 96445: {'lr': 0.00014488226160734536, 'samples': 18517440, 'steps': 96444, 'loss/train': 1.1599502563476562} 08/31/2021 06:41:10 - INFO - __main__ - Step 96446: {'lr': 0.00014487744679004242, 'samples': 18517632, 'steps': 96445, 'loss/train': 1.0341567993164062} 08/31/2021 06:41:10 - INFO - __main__ - Step 96447: {'lr': 0.00014487263202010608, 'samples': 18517824, 'steps': 96446, 'loss/train': 0.17781563103199005} 08/31/2021 06:41:10 - INFO - __main__ - Step 96448: {'lr': 0.00014486781729753856, 'samples': 18518016, 'steps': 96447, 'loss/train': 1.1310983896255493} 08/31/2021 06:41:11 - INFO - __main__ - Step 96449: {'lr': 0.00014486300262234192, 'samples': 18518208, 'steps': 96448, 'loss/train': 1.7020021677017212} 08/31/2021 06:41:12 - INFO - __main__ - Step 96450: {'lr': 0.00014485818799451843, 'samples': 18518400, 'steps': 96449, 'loss/train': 0.6599424481391907} 08/31/2021 06:41:13 - INFO - __main__ - Step 96451: {'lr': 0.00014485337341407024, 'samples': 18518592, 'steps': 96450, 'loss/train': 2.618983268737793} 08/31/2021 06:41:13 - INFO - __main__ - Step 96452: {'lr': 0.00014484855888099947, 'samples': 18518784, 'steps': 96451, 'loss/train': 1.4444506168365479} 08/31/2021 06:41:13 - INFO - __main__ - Step 96453: {'lr': 0.00014484374439530827, 'samples': 18518976, 'steps': 96452, 'loss/train': 1.127005934715271} 08/31/2021 06:41:14 - INFO - __main__ - Step 96454: {'lr': 0.0001448389299569989, 'samples': 18519168, 'steps': 96453, 'loss/train': 1.035273551940918} 08/31/2021 06:41:15 - INFO - __main__ - Step 96455: {'lr': 0.00014483411556607352, 'samples': 18519360, 'steps': 96454, 'loss/train': 1.3073585033416748} 08/31/2021 06:41:16 - INFO - __main__ - Step 96456: {'lr': 0.00014482930122253419, 'samples': 18519552, 'steps': 96455, 'loss/train': 0.1091395765542984} 08/31/2021 06:41:16 - INFO - __main__ - Step 96457: {'lr': 0.0001448244869263832, 'samples': 18519744, 'steps': 96456, 'loss/train': 1.528476357460022} 08/31/2021 06:41:16 - INFO - __main__ - Step 96458: {'lr': 0.00014481967267762275, 'samples': 18519936, 'steps': 96457, 'loss/train': 1.4593474864959717} 08/31/2021 06:41:17 - INFO - __main__ - Step 96459: {'lr': 0.00014481485847625487, 'samples': 18520128, 'steps': 96458, 'loss/train': 1.3282496929168701} 08/31/2021 06:41:18 - INFO - __main__ - Step 96460: {'lr': 0.00014481004432228176, 'samples': 18520320, 'steps': 96459, 'loss/train': 1.7288169860839844} 08/31/2021 06:41:19 - INFO - __main__ - Step 96461: {'lr': 0.00014480523021570562, 'samples': 18520512, 'steps': 96460, 'loss/train': 1.166582465171814} 08/31/2021 06:41:19 - INFO - __main__ - Step 96462: {'lr': 0.00014480041615652864, 'samples': 18520704, 'steps': 96461, 'loss/train': 1.134511947631836} 08/31/2021 06:41:19 - INFO - __main__ - Step 96463: {'lr': 0.00014479560214475295, 'samples': 18520896, 'steps': 96462, 'loss/train': 0.3551977872848511} 08/31/2021 06:41:20 - INFO - __main__ - Step 96464: {'lr': 0.00014479078818038077, 'samples': 18521088, 'steps': 96463, 'loss/train': 1.0829728841781616} 08/31/2021 06:41:21 - INFO - __main__ - Step 96465: {'lr': 0.00014478597426341422, 'samples': 18521280, 'steps': 96464, 'loss/train': 1.4559714794158936} 08/31/2021 06:41:22 - INFO - __main__ - Step 96466: {'lr': 0.00014478116039385547, 'samples': 18521472, 'steps': 96465, 'loss/train': 1.1549535989761353} 08/31/2021 06:41:22 - INFO - __main__ - Step 96467: {'lr': 0.00014477634657170671, 'samples': 18521664, 'steps': 96466, 'loss/train': 1.114042043685913} 08/31/2021 06:41:22 - INFO - __main__ - Step 96468: {'lr': 0.00014477153279697012, 'samples': 18521856, 'steps': 96467, 'loss/train': 1.0268158912658691} 08/31/2021 06:41:23 - INFO - __main__ - Step 96469: {'lr': 0.00014476671906964782, 'samples': 18522048, 'steps': 96468, 'loss/train': 0.022917743772268295} 08/31/2021 06:41:23 - INFO - __main__ - Step 96470: {'lr': 0.00014476190538974205, 'samples': 18522240, 'steps': 96469, 'loss/train': 1.365394949913025} 08/31/2021 06:41:25 - INFO - __main__ - Step 96471: {'lr': 0.00014475709175725506, 'samples': 18522432, 'steps': 96470, 'loss/train': 1.0052279233932495} 08/31/2021 06:41:26 - INFO - __main__ - Step 96472: {'lr': 0.00014475227817218873, 'samples': 18522624, 'steps': 96471, 'loss/train': 0.6645991206169128} 08/31/2021 06:41:26 - INFO - __main__ - Step 96473: {'lr': 0.00014474746463454547, 'samples': 18522816, 'steps': 96472, 'loss/train': 1.1344345808029175} 08/31/2021 06:41:27 - INFO - __main__ - Step 96474: {'lr': 0.00014474265114432732, 'samples': 18523008, 'steps': 96473, 'loss/train': 0.6111900210380554} 08/31/2021 06:41:27 - INFO - __main__ - Step 96475: {'lr': 0.00014473783770153654, 'samples': 18523200, 'steps': 96474, 'loss/train': 0.7661778926849365} 08/31/2021 06:41:29 - INFO - __main__ - Step 96476: {'lr': 0.00014473302430617523, 'samples': 18523392, 'steps': 96475, 'loss/train': 1.3856089115142822} 08/31/2021 06:41:29 - INFO - __main__ - Step 96477: {'lr': 0.00014472821095824566, 'samples': 18523584, 'steps': 96476, 'loss/train': 1.1221282482147217} 08/31/2021 06:41:30 - INFO - __main__ - Step 96478: {'lr': 0.00014472339765774989, 'samples': 18523776, 'steps': 96477, 'loss/train': 0.6060962677001953} 08/31/2021 06:41:30 - INFO - __main__ - Step 96479: {'lr': 0.00014471858440469015, 'samples': 18523968, 'steps': 96478, 'loss/train': 1.000827670097351} 08/31/2021 06:41:30 - INFO - __main__ - Step 96480: {'lr': 0.0001447137711990686, 'samples': 18524160, 'steps': 96479, 'loss/train': 0.8522257208824158} 08/31/2021 06:41:32 - INFO - __main__ - Step 96481: {'lr': 0.00014470895804088736, 'samples': 18524352, 'steps': 96480, 'loss/train': 0.26926639676094055} 08/31/2021 06:41:33 - INFO - __main__ - Step 96482: {'lr': 0.00014470414493014867, 'samples': 18524544, 'steps': 96481, 'loss/train': 1.017570972442627} 08/31/2021 06:41:33 - INFO - __main__ - Step 96483: {'lr': 0.00014469933186685464, 'samples': 18524736, 'steps': 96482, 'loss/train': 0.06923730671405792} 08/31/2021 06:41:33 - INFO - __main__ - Step 96484: {'lr': 0.0001446945188510076, 'samples': 18524928, 'steps': 96483, 'loss/train': 0.6139786839485168} 08/31/2021 06:41:34 - INFO - __main__ - Step 96485: {'lr': 0.00014468970588260945, 'samples': 18525120, 'steps': 96484, 'loss/train': 1.889369010925293} 08/31/2021 06:41:35 - INFO - __main__ - Step 96486: {'lr': 0.00014468489296166255, 'samples': 18525312, 'steps': 96485, 'loss/train': 1.3679401874542236} 08/31/2021 06:41:36 - INFO - __main__ - Step 96487: {'lr': 0.00014468008008816896, 'samples': 18525504, 'steps': 96486, 'loss/train': 1.6178725957870483} 08/31/2021 06:41:36 - INFO - __main__ - Step 96488: {'lr': 0.00014467526726213092, 'samples': 18525696, 'steps': 96487, 'loss/train': 1.27727210521698} 08/31/2021 06:41:37 - INFO - __main__ - Step 96489: {'lr': 0.00014467045448355057, 'samples': 18525888, 'steps': 96488, 'loss/train': 1.423551082611084} 08/31/2021 06:41:37 - INFO - __main__ - Step 96490: {'lr': 0.00014466564175243007, 'samples': 18526080, 'steps': 96489, 'loss/train': 1.3181599378585815} 08/31/2021 06:41:38 - INFO - __main__ - Step 96491: {'lr': 0.00014466082906877166, 'samples': 18526272, 'steps': 96490, 'loss/train': 1.499491572380066} 08/31/2021 06:41:39 - INFO - __main__ - Step 96492: {'lr': 0.00014465601643257742, 'samples': 18526464, 'steps': 96491, 'loss/train': 0.8285044431686401} 08/31/2021 06:41:39 - INFO - __main__ - Step 96493: {'lr': 0.00014465120384384955, 'samples': 18526656, 'steps': 96492, 'loss/train': 1.4055564403533936} 08/31/2021 06:41:40 - INFO - __main__ - Step 96494: {'lr': 0.00014464639130259022, 'samples': 18526848, 'steps': 96493, 'loss/train': 1.2461533546447754} 08/31/2021 06:41:40 - INFO - __main__ - Step 96495: {'lr': 0.0001446415788088017, 'samples': 18527040, 'steps': 96494, 'loss/train': 1.3206102848052979} 08/31/2021 06:41:42 - INFO - __main__ - Step 96496: {'lr': 0.000144636766362486, 'samples': 18527232, 'steps': 96495, 'loss/train': 0.954975962638855} 08/31/2021 06:41:42 - INFO - __main__ - Step 96497: {'lr': 0.00014463195396364532, 'samples': 18527424, 'steps': 96496, 'loss/train': 1.099875569343567} 08/31/2021 06:41:43 - INFO - __main__ - Step 96498: {'lr': 0.00014462714161228186, 'samples': 18527616, 'steps': 96497, 'loss/train': 0.37804609537124634} 08/31/2021 06:41:43 - INFO - __main__ - Step 96499: {'lr': 0.00014462232930839776, 'samples': 18527808, 'steps': 96498, 'loss/train': 0.13095802068710327} 08/31/2021 06:41:44 - INFO - __main__ - Step 96500: {'lr': 0.00014461751705199523, 'samples': 18528000, 'steps': 96499, 'loss/train': 0.8294084072113037} 08/31/2021 06:41:45 - INFO - __main__ - Step 96501: {'lr': 0.00014461270484307642, 'samples': 18528192, 'steps': 96500, 'loss/train': 0.9558694958686829} 08/31/2021 06:41:46 - INFO - __main__ - Step 96502: {'lr': 0.0001446078926816435, 'samples': 18528384, 'steps': 96501, 'loss/train': 1.6286424398422241} 08/31/2021 06:41:46 - INFO - __main__ - Step 96503: {'lr': 0.0001446030805676986, 'samples': 18528576, 'steps': 96502, 'loss/train': 1.5683956146240234} 08/31/2021 06:41:46 - INFO - __main__ - Step 96504: {'lr': 0.00014459826850124396, 'samples': 18528768, 'steps': 96503, 'loss/train': 0.9484328627586365} 08/31/2021 06:41:47 - INFO - __main__ - Step 96505: {'lr': 0.00014459345648228173, 'samples': 18528960, 'steps': 96504, 'loss/train': 1.632859468460083} 08/31/2021 06:41:47 - INFO - __main__ - Step 96506: {'lr': 0.00014458864451081415, 'samples': 18529152, 'steps': 96505, 'loss/train': 1.2129483222961426} 08/31/2021 06:41:48 - INFO - __main__ - Step 96507: {'lr': 0.00014458383258684321, 'samples': 18529344, 'steps': 96506, 'loss/train': 0.02532871440052986} 08/31/2021 06:41:49 - INFO - __main__ - Step 96508: {'lr': 0.00014457902071037115, 'samples': 18529536, 'steps': 96507, 'loss/train': 0.8747509121894836} 08/31/2021 06:41:49 - INFO - __main__ - Step 96509: {'lr': 0.00014457420888140015, 'samples': 18529728, 'steps': 96508, 'loss/train': 1.1223528385162354} 08/31/2021 06:41:50 - INFO - __main__ - Step 96510: {'lr': 0.00014456939709993238, 'samples': 18529920, 'steps': 96509, 'loss/train': 0.6942667961120605} 08/31/2021 06:41:50 - INFO - __main__ - Step 96511: {'lr': 0.00014456458536597005, 'samples': 18530112, 'steps': 96510, 'loss/train': 0.790287435054779} 08/31/2021 06:41:52 - INFO - __main__ - Step 96512: {'lr': 0.00014455977367951528, 'samples': 18530304, 'steps': 96511, 'loss/train': 1.2694121599197388} 08/31/2021 06:41:52 - INFO - __main__ - Step 96513: {'lr': 0.00014455496204057023, 'samples': 18530496, 'steps': 96512, 'loss/train': 1.1235644817352295} 08/31/2021 06:41:53 - INFO - __main__ - Step 96514: {'lr': 0.0001445501504491371, 'samples': 18530688, 'steps': 96513, 'loss/train': 0.9142189025878906} 08/31/2021 06:41:53 - INFO - __main__ - Step 96515: {'lr': 0.00014454533890521804, 'samples': 18530880, 'steps': 96514, 'loss/train': 0.37898680567741394} 08/31/2021 06:41:53 - INFO - __main__ - Step 96516: {'lr': 0.00014454052740881524, 'samples': 18531072, 'steps': 96515, 'loss/train': 1.482269287109375} 08/31/2021 06:41:54 - INFO - __main__ - Step 96517: {'lr': 0.00014453571595993093, 'samples': 18531264, 'steps': 96516, 'loss/train': 0.13917618989944458} 08/31/2021 06:41:55 - INFO - __main__ - Step 96518: {'lr': 0.0001445309045585671, 'samples': 18531456, 'steps': 96517, 'loss/train': 1.612808108329773} 08/31/2021 06:41:56 - INFO - __main__ - Step 96519: {'lr': 0.00014452609320472602, 'samples': 18531648, 'steps': 96518, 'loss/train': 0.9727070927619934} 08/31/2021 06:41:56 - INFO - __main__ - Step 96520: {'lr': 0.00014452128189840986, 'samples': 18531840, 'steps': 96519, 'loss/train': 1.083290934562683} 08/31/2021 06:41:57 - INFO - __main__ - Step 96521: {'lr': 0.00014451647063962075, 'samples': 18532032, 'steps': 96520, 'loss/train': 1.5253069400787354} 08/31/2021 06:41:57 - INFO - __main__ - Step 96522: {'lr': 0.00014451165942836093, 'samples': 18532224, 'steps': 96521, 'loss/train': 1.0714291334152222} 08/31/2021 06:41:59 - INFO - __main__ - Step 96523: {'lr': 0.0001445068482646325, 'samples': 18532416, 'steps': 96522, 'loss/train': 0.8496609926223755} 08/31/2021 06:42:00 - INFO - __main__ - Step 96524: {'lr': 0.0001445020371484377, 'samples': 18532608, 'steps': 96523, 'loss/train': 1.3065385818481445} 08/31/2021 06:42:00 - INFO - __main__ - Step 96525: {'lr': 0.00014449722607977862, 'samples': 18532800, 'steps': 96524, 'loss/train': 1.1307008266448975} 08/31/2021 06:42:00 - INFO - __main__ - Step 96526: {'lr': 0.00014449241505865745, 'samples': 18532992, 'steps': 96525, 'loss/train': 1.514106273651123} 08/31/2021 06:42:01 - INFO - __main__ - Step 96527: {'lr': 0.00014448760408507642, 'samples': 18533184, 'steps': 96526, 'loss/train': 1.7515090703964233} 08/31/2021 06:42:02 - INFO - __main__ - Step 96528: {'lr': 0.0001444827931590377, 'samples': 18533376, 'steps': 96527, 'loss/train': 1.4589101076126099} 08/31/2021 06:42:03 - INFO - __main__ - Step 96529: {'lr': 0.00014447798228054331, 'samples': 18533568, 'steps': 96528, 'loss/train': 1.4624660015106201} 08/31/2021 06:42:03 - INFO - __main__ - Step 96530: {'lr': 0.00014447317144959554, 'samples': 18533760, 'steps': 96529, 'loss/train': 1.0117710828781128} 08/31/2021 06:42:04 - INFO - __main__ - Step 96531: {'lr': 0.0001444683606661965, 'samples': 18533952, 'steps': 96530, 'loss/train': 1.3436863422393799} 08/31/2021 06:42:04 - INFO - __main__ - Step 96532: {'lr': 0.00014446354993034844, 'samples': 18534144, 'steps': 96531, 'loss/train': 0.8776280283927917} 08/31/2021 06:42:06 - INFO - __main__ - Step 96533: {'lr': 0.00014445873924205343, 'samples': 18534336, 'steps': 96532, 'loss/train': 1.315457820892334} 08/31/2021 06:42:07 - INFO - __main__ - Step 96534: {'lr': 0.0001444539286013137, 'samples': 18534528, 'steps': 96533, 'loss/train': 0.23564913868904114} 08/31/2021 06:42:07 - INFO - __main__ - Step 96535: {'lr': 0.00014444911800813137, 'samples': 18534720, 'steps': 96534, 'loss/train': 1.369267463684082} 08/31/2021 06:42:07 - INFO - __main__ - Step 96536: {'lr': 0.00014444430746250866, 'samples': 18534912, 'steps': 96535, 'loss/train': 0.7210734486579895} 08/31/2021 06:42:08 - INFO - __main__ - Step 96537: {'lr': 0.00014443949696444776, 'samples': 18535104, 'steps': 96536, 'loss/train': 1.2297708988189697} 08/31/2021 06:42:08 - INFO - __main__ - Step 96538: {'lr': 0.00014443468651395073, 'samples': 18535296, 'steps': 96537, 'loss/train': 0.6621119379997253} 08/31/2021 06:42:09 - INFO - __main__ - Step 96539: {'lr': 0.00014442987611101992, 'samples': 18535488, 'steps': 96538, 'loss/train': 0.09344235807657242} 08/31/2021 06:42:10 - INFO - __main__ - Step 96540: {'lr': 0.0001444250657556573, 'samples': 18535680, 'steps': 96539, 'loss/train': 0.5526249408721924} 08/31/2021 06:42:10 - INFO - __main__ - Step 96541: {'lr': 0.00014442025544786507, 'samples': 18535872, 'steps': 96540, 'loss/train': 1.3224269151687622} 08/31/2021 06:42:11 - INFO - __main__ - Step 96542: {'lr': 0.0001444154451876455, 'samples': 18536064, 'steps': 96541, 'loss/train': 1.544386386871338} 08/31/2021 06:42:11 - INFO - __main__ - Step 96543: {'lr': 0.00014441063497500067, 'samples': 18536256, 'steps': 96542, 'loss/train': 0.9713169932365417} 08/31/2021 06:42:11 - INFO - __main__ - Step 96544: {'lr': 0.00014440582480993274, 'samples': 18536448, 'steps': 96543, 'loss/train': 1.331491470336914} 08/31/2021 06:42:13 - INFO - __main__ - Step 96545: {'lr': 0.000144401014692444, 'samples': 18536640, 'steps': 96544, 'loss/train': 0.8480978608131409} 08/31/2021 06:42:13 - INFO - __main__ - Step 96546: {'lr': 0.0001443962046225365, 'samples': 18536832, 'steps': 96545, 'loss/train': 1.087708830833435} 08/31/2021 06:42:14 - INFO - __main__ - Step 96547: {'lr': 0.00014439139460021243, 'samples': 18537024, 'steps': 96546, 'loss/train': 0.8281641602516174} 08/31/2021 06:42:14 - INFO - __main__ - Step 96548: {'lr': 0.00014438658462547394, 'samples': 18537216, 'steps': 96547, 'loss/train': 1.0319507122039795} 08/31/2021 06:42:14 - INFO - __main__ - Step 96549: {'lr': 0.00014438177469832324, 'samples': 18537408, 'steps': 96548, 'loss/train': 1.1847760677337646} 08/31/2021 06:42:16 - INFO - __main__ - Step 96550: {'lr': 0.00014437696481876252, 'samples': 18537600, 'steps': 96549, 'loss/train': 1.0829285383224487} 08/31/2021 06:42:16 - INFO - __main__ - Step 96551: {'lr': 0.0001443721549867939, 'samples': 18537792, 'steps': 96550, 'loss/train': 1.0441672801971436} 08/31/2021 06:42:17 - INFO - __main__ - Step 96552: {'lr': 0.0001443673452024196, 'samples': 18537984, 'steps': 96551, 'loss/train': 1.0692793130874634} 08/31/2021 06:42:17 - INFO - __main__ - Step 96553: {'lr': 0.0001443625354656417, 'samples': 18538176, 'steps': 96552, 'loss/train': 1.6055582761764526} 08/31/2021 06:42:17 - INFO - __main__ - Step 96554: {'lr': 0.00014435772577646243, 'samples': 18538368, 'steps': 96553, 'loss/train': 1.1467968225479126} 08/31/2021 06:42:19 - INFO - __main__ - Step 96555: {'lr': 0.0001443529161348839, 'samples': 18538560, 'steps': 96554, 'loss/train': 0.9919145703315735} 08/31/2021 06:42:19 - INFO - __main__ - Step 96556: {'lr': 0.00014434810654090835, 'samples': 18538752, 'steps': 96555, 'loss/train': 0.3228151202201843} 08/31/2021 06:42:20 - INFO - __main__ - Step 96557: {'lr': 0.00014434329699453786, 'samples': 18538944, 'steps': 96556, 'loss/train': 1.1127768754959106} 08/31/2021 06:42:20 - INFO - __main__ - Step 96558: {'lr': 0.0001443384874957747, 'samples': 18539136, 'steps': 96557, 'loss/train': 0.9724307060241699} 08/31/2021 06:42:20 - INFO - __main__ - Step 96559: {'lr': 0.00014433367804462095, 'samples': 18539328, 'steps': 96558, 'loss/train': 1.2905281782150269} 08/31/2021 06:42:22 - INFO - __main__ - Step 96560: {'lr': 0.00014432886864107884, 'samples': 18539520, 'steps': 96559, 'loss/train': 0.9501805305480957} 08/31/2021 06:42:22 - INFO - __main__ - Step 96561: {'lr': 0.0001443240592851505, 'samples': 18539712, 'steps': 96560, 'loss/train': 1.3281601667404175} 08/31/2021 06:42:23 - INFO - __main__ - Step 96562: {'lr': 0.0001443192499768381, 'samples': 18539904, 'steps': 96561, 'loss/train': 1.875609040260315} 08/31/2021 06:42:23 - INFO - __main__ - Step 96563: {'lr': 0.00014431444071614382, 'samples': 18540096, 'steps': 96562, 'loss/train': 1.7135275602340698} 08/31/2021 06:42:24 - INFO - __main__ - Step 96564: {'lr': 0.00014430963150306982, 'samples': 18540288, 'steps': 96563, 'loss/train': 1.0908002853393555} 08/31/2021 06:42:25 - INFO - __main__ - Step 96565: {'lr': 0.00014430482233761838, 'samples': 18540480, 'steps': 96564, 'loss/train': 1.5741450786590576} 08/31/2021 06:42:26 - INFO - __main__ - Step 96566: {'lr': 0.00014430001321979148, 'samples': 18540672, 'steps': 96565, 'loss/train': 1.0580579042434692} 08/31/2021 06:42:26 - INFO - __main__ - Step 96567: {'lr': 0.0001442952041495913, 'samples': 18540864, 'steps': 96566, 'loss/train': 1.926263689994812} 08/31/2021 06:42:26 - INFO - __main__ - Step 96568: {'lr': 0.0001442903951270201, 'samples': 18541056, 'steps': 96567, 'loss/train': 0.21679867804050446} 08/31/2021 06:42:27 - INFO - __main__ - Step 96569: {'lr': 0.00014428558615208004, 'samples': 18541248, 'steps': 96568, 'loss/train': 0.9423088431358337} 08/31/2021 06:42:29 - INFO - __main__ - Step 96570: {'lr': 0.00014428077722477322, 'samples': 18541440, 'steps': 96569, 'loss/train': 0.8609635233879089} 08/31/2021 06:42:29 - INFO - __main__ - Step 96571: {'lr': 0.0001442759683451019, 'samples': 18541632, 'steps': 96570, 'loss/train': 0.8311423659324646} 08/31/2021 06:42:29 - INFO - __main__ - Step 96572: {'lr': 0.0001442711595130682, 'samples': 18541824, 'steps': 96571, 'loss/train': 0.7541409134864807} 08/31/2021 06:42:30 - INFO - __main__ - Step 96573: {'lr': 0.00014426635072867423, 'samples': 18542016, 'steps': 96572, 'loss/train': 0.7843645811080933} 08/31/2021 06:42:30 - INFO - __main__ - Step 96574: {'lr': 0.0001442615419919222, 'samples': 18542208, 'steps': 96573, 'loss/train': 1.6471277475357056} 08/31/2021 06:42:30 - INFO - __main__ - Step 96575: {'lr': 0.00014425673330281435, 'samples': 18542400, 'steps': 96574, 'loss/train': 1.3896845579147339} 08/31/2021 06:42:33 - INFO - __main__ - Step 96576: {'lr': 0.00014425192466135275, 'samples': 18542592, 'steps': 96575, 'loss/train': 0.018876563757658005} 08/31/2021 06:42:33 - INFO - __main__ - Step 96577: {'lr': 0.00014424711606753963, 'samples': 18542784, 'steps': 96576, 'loss/train': 1.1203441619873047} 08/31/2021 06:42:33 - INFO - __main__ - Step 96578: {'lr': 0.0001442423075213771, 'samples': 18542976, 'steps': 96577, 'loss/train': 0.6133044958114624} 08/31/2021 06:42:34 - INFO - __main__ - Step 96579: {'lr': 0.00014423749902286746, 'samples': 18543168, 'steps': 96578, 'loss/train': 0.37875187397003174} 08/31/2021 06:42:34 - INFO - __main__ - Step 96580: {'lr': 0.00014423269057201266, 'samples': 18543360, 'steps': 96579, 'loss/train': 1.1427587270736694} 08/31/2021 06:42:34 - INFO - __main__ - Step 96581: {'lr': 0.000144227882168815, 'samples': 18543552, 'steps': 96580, 'loss/train': 1.3044637441635132} 08/31/2021 06:42:36 - INFO - __main__ - Step 96582: {'lr': 0.0001442230738132766, 'samples': 18543744, 'steps': 96581, 'loss/train': 1.1838189363479614} 08/31/2021 06:42:36 - INFO - __main__ - Step 96583: {'lr': 0.00014421826550539967, 'samples': 18543936, 'steps': 96582, 'loss/train': 1.4045312404632568} 08/31/2021 06:42:37 - INFO - __main__ - Step 96584: {'lr': 0.00014421345724518637, 'samples': 18544128, 'steps': 96583, 'loss/train': 0.6737760305404663} 08/31/2021 06:42:37 - INFO - __main__ - Step 96585: {'lr': 0.00014420864903263883, 'samples': 18544320, 'steps': 96584, 'loss/train': 0.9762819409370422} 08/31/2021 06:42:37 - INFO - __main__ - Step 96586: {'lr': 0.00014420384086775924, 'samples': 18544512, 'steps': 96585, 'loss/train': 1.114437222480774} 08/31/2021 06:42:39 - INFO - __main__ - Step 96587: {'lr': 0.0001441990327505498, 'samples': 18544704, 'steps': 96586, 'loss/train': 0.0889100655913353} 08/31/2021 06:42:39 - INFO - __main__ - Step 96588: {'lr': 0.0001441942246810126, 'samples': 18544896, 'steps': 96587, 'loss/train': 0.9024701714515686} 08/31/2021 06:42:40 - INFO - __main__ - Step 96589: {'lr': 0.00014418941665914986, 'samples': 18545088, 'steps': 96588, 'loss/train': 1.3491334915161133} 08/31/2021 06:42:40 - INFO - __main__ - Step 96590: {'lr': 0.00014418460868496376, 'samples': 18545280, 'steps': 96589, 'loss/train': 1.5427302122116089} 08/31/2021 06:42:40 - INFO - __main__ - Step 96591: {'lr': 0.0001441798007584564, 'samples': 18545472, 'steps': 96590, 'loss/train': 1.2163488864898682} 08/31/2021 06:42:42 - INFO - __main__ - Step 96592: {'lr': 0.00014417499287963014, 'samples': 18545664, 'steps': 96591, 'loss/train': 0.8415699005126953} 08/31/2021 06:42:42 - INFO - __main__ - Step 96593: {'lr': 0.00014417018504848684, 'samples': 18545856, 'steps': 96592, 'loss/train': 0.6197473406791687} 08/31/2021 06:42:43 - INFO - __main__ - Step 96594: {'lr': 0.00014416537726502887, 'samples': 18546048, 'steps': 96593, 'loss/train': 1.00821053981781} 08/31/2021 06:42:43 - INFO - __main__ - Step 96595: {'lr': 0.0001441605695292583, 'samples': 18546240, 'steps': 96594, 'loss/train': 1.6541255712509155} 08/31/2021 06:42:43 - INFO - __main__ - Step 96596: {'lr': 0.00014415576184117741, 'samples': 18546432, 'steps': 96595, 'loss/train': 1.367439866065979} 08/31/2021 06:42:45 - INFO - __main__ - Step 96597: {'lr': 0.00014415095420078822, 'samples': 18546624, 'steps': 96596, 'loss/train': 1.3699309825897217} 08/31/2021 06:42:45 - INFO - __main__ - Step 96598: {'lr': 0.00014414614660809304, 'samples': 18546816, 'steps': 96597, 'loss/train': 0.9384691119194031} 08/31/2021 06:42:46 - INFO - __main__ - Step 96599: {'lr': 0.00014414133906309395, 'samples': 18547008, 'steps': 96598, 'loss/train': 1.4670435190200806} 08/31/2021 06:42:46 - INFO - __main__ - Step 96600: {'lr': 0.00014413653156579315, 'samples': 18547200, 'steps': 96599, 'loss/train': 1.2437783479690552} 08/31/2021 06:42:46 - INFO - __main__ - Step 96601: {'lr': 0.0001441317241161928, 'samples': 18547392, 'steps': 96600, 'loss/train': 1.2760285139083862} 08/31/2021 06:42:47 - INFO - __main__ - Step 96602: {'lr': 0.000144126916714295, 'samples': 18547584, 'steps': 96601, 'loss/train': 1.4339927434921265} 08/31/2021 06:42:48 - INFO - __main__ - Step 96603: {'lr': 0.00014412210936010206, 'samples': 18547776, 'steps': 96602, 'loss/train': 1.2089991569519043} 08/31/2021 06:42:49 - INFO - __main__ - Step 96604: {'lr': 0.000144117302053616, 'samples': 18547968, 'steps': 96603, 'loss/train': 1.4658721685409546} 08/31/2021 06:42:49 - INFO - __main__ - Step 96605: {'lr': 0.00014411249479483909, 'samples': 18548160, 'steps': 96604, 'loss/train': 0.7082664370536804} 08/31/2021 06:42:50 - INFO - __main__ - Step 96606: {'lr': 0.00014410768758377356, 'samples': 18548352, 'steps': 96605, 'loss/train': 0.46421414613723755} 08/31/2021 06:42:50 - INFO - __main__ - Step 96607: {'lr': 0.00014410288042042137, 'samples': 18548544, 'steps': 96606, 'loss/train': 1.7608020305633545} 08/31/2021 06:42:51 - INFO - __main__ - Step 96608: {'lr': 0.00014409807330478474, 'samples': 18548736, 'steps': 96607, 'loss/train': 0.5165377855300903} 08/31/2021 06:42:52 - INFO - __main__ - Step 96609: {'lr': 0.00014409326623686592, 'samples': 18548928, 'steps': 96608, 'loss/train': 0.929338812828064} 08/31/2021 06:42:52 - INFO - __main__ - Step 96610: {'lr': 0.00014408845921666706, 'samples': 18549120, 'steps': 96609, 'loss/train': 0.8358507752418518} 08/31/2021 06:42:53 - INFO - __main__ - Step 96611: {'lr': 0.00014408365224419028, 'samples': 18549312, 'steps': 96610, 'loss/train': 1.0485769510269165} 08/31/2021 06:42:53 - INFO - __main__ - Step 96612: {'lr': 0.00014407884531943778, 'samples': 18549504, 'steps': 96611, 'loss/train': 1.624670147895813} 08/31/2021 06:42:54 - INFO - __main__ - Step 96613: {'lr': 0.00014407403844241172, 'samples': 18549696, 'steps': 96612, 'loss/train': 0.930191695690155} 08/31/2021 06:42:55 - INFO - __main__ - Step 96614: {'lr': 0.00014406923161311425, 'samples': 18549888, 'steps': 96613, 'loss/train': 1.0684326887130737} 08/31/2021 06:42:55 - INFO - __main__ - Step 96615: {'lr': 0.00014406442483154755, 'samples': 18550080, 'steps': 96614, 'loss/train': 1.3410500288009644} 08/31/2021 06:42:56 - INFO - __main__ - Step 96616: {'lr': 0.00014405961809771378, 'samples': 18550272, 'steps': 96615, 'loss/train': 0.7661535143852234} 08/31/2021 06:42:56 - INFO - __main__ - Step 96617: {'lr': 0.00014405481141161513, 'samples': 18550464, 'steps': 96616, 'loss/train': 1.031618595123291} 08/31/2021 06:42:58 - INFO - __main__ - Step 96618: {'lr': 0.00014405000477325376, 'samples': 18550656, 'steps': 96617, 'loss/train': 1.1333286762237549} 08/31/2021 06:42:58 - INFO - __main__ - Step 96619: {'lr': 0.0001440451981826319, 'samples': 18550848, 'steps': 96618, 'loss/train': 0.03429407253861427} 08/31/2021 06:42:58 - INFO - __main__ - Step 96620: {'lr': 0.00014404039163975156, 'samples': 18551040, 'steps': 96619, 'loss/train': 0.05366617441177368} 08/31/2021 06:42:59 - INFO - __main__ - Step 96621: {'lr': 0.00014403558514461496, 'samples': 18551232, 'steps': 96620, 'loss/train': 0.8673336505889893} 08/31/2021 06:42:59 - INFO - __main__ - Step 96622: {'lr': 0.0001440307786972243, 'samples': 18551424, 'steps': 96621, 'loss/train': 1.1005465984344482} 08/31/2021 06:42:59 - INFO - __main__ - Step 96623: {'lr': 0.00014402597229758174, 'samples': 18551616, 'steps': 96622, 'loss/train': 0.5723440051078796} 08/31/2021 06:43:01 - INFO - __main__ - Step 96624: {'lr': 0.00014402116594568944, 'samples': 18551808, 'steps': 96623, 'loss/train': 1.4759875535964966} 08/31/2021 06:43:01 - INFO - __main__ - Step 96625: {'lr': 0.00014401635964154954, 'samples': 18552000, 'steps': 96624, 'loss/train': 0.9019255638122559} 08/31/2021 06:43:02 - INFO - __main__ - Step 96626: {'lr': 0.00014401155338516426, 'samples': 18552192, 'steps': 96625, 'loss/train': 1.4542956352233887} 08/31/2021 06:43:02 - INFO - __main__ - Step 96627: {'lr': 0.00014400674717653572, 'samples': 18552384, 'steps': 96626, 'loss/train': 1.7714552879333496} 08/31/2021 06:43:02 - INFO - __main__ - Step 96628: {'lr': 0.00014400194101566612, 'samples': 18552576, 'steps': 96627, 'loss/train': 1.3112571239471436} 08/31/2021 06:43:04 - INFO - __main__ - Step 96629: {'lr': 0.00014399713490255761, 'samples': 18552768, 'steps': 96628, 'loss/train': 1.2871534824371338} 08/31/2021 06:43:05 - INFO - __main__ - Step 96630: {'lr': 0.00014399232883721236, 'samples': 18552960, 'steps': 96629, 'loss/train': 1.2036865949630737} 08/31/2021 06:43:05 - INFO - __main__ - Step 96631: {'lr': 0.00014398752281963255, 'samples': 18553152, 'steps': 96630, 'loss/train': 1.3657869100570679} 08/31/2021 06:43:05 - INFO - __main__ - Step 96632: {'lr': 0.0001439827168498204, 'samples': 18553344, 'steps': 96631, 'loss/train': 1.0683283805847168} 08/31/2021 06:43:06 - INFO - __main__ - Step 96633: {'lr': 0.0001439779109277779, 'samples': 18553536, 'steps': 96632, 'loss/train': 0.8248661160469055} 08/31/2021 06:43:08 - INFO - __main__ - Step 96634: {'lr': 0.0001439731050535073, 'samples': 18553728, 'steps': 96633, 'loss/train': 1.6967874765396118} 08/31/2021 06:43:09 - INFO - __main__ - Step 96635: {'lr': 0.00014396829922701083, 'samples': 18553920, 'steps': 96634, 'loss/train': 0.11587411165237427} 08/31/2021 06:43:09 - INFO - __main__ - Step 96636: {'lr': 0.00014396349344829057, 'samples': 18554112, 'steps': 96635, 'loss/train': 1.1850155591964722} 08/31/2021 06:43:09 - INFO - __main__ - Step 96637: {'lr': 0.00014395868771734872, 'samples': 18554304, 'steps': 96636, 'loss/train': 0.9276177287101746} 08/31/2021 06:43:10 - INFO - __main__ - Step 96638: {'lr': 0.00014395388203418746, 'samples': 18554496, 'steps': 96637, 'loss/train': 0.44573742151260376} 08/31/2021 06:43:12 - INFO - __main__ - Step 96639: {'lr': 0.00014394907639880895, 'samples': 18554688, 'steps': 96638, 'loss/train': 1.259790301322937} 08/31/2021 06:43:12 - INFO - __main__ - Step 96640: {'lr': 0.00014394427081121537, 'samples': 18554880, 'steps': 96639, 'loss/train': 1.2777936458587646} 08/31/2021 06:43:12 - INFO - __main__ - Step 96641: {'lr': 0.00014393946527140882, 'samples': 18555072, 'steps': 96640, 'loss/train': 0.016640232875943184} 08/31/2021 06:43:13 - INFO - __main__ - Step 96642: {'lr': 0.00014393465977939152, 'samples': 18555264, 'steps': 96641, 'loss/train': 1.2609680891036987} 08/31/2021 06:43:13 - INFO - __main__ - Step 96643: {'lr': 0.00014392985433516565, 'samples': 18555456, 'steps': 96642, 'loss/train': 0.5000331997871399} 08/31/2021 06:43:13 - INFO - __main__ - Step 96644: {'lr': 0.00014392504893873334, 'samples': 18555648, 'steps': 96643, 'loss/train': 1.2070561647415161} 08/31/2021 06:43:15 - INFO - __main__ - Step 96645: {'lr': 0.00014392024359009676, 'samples': 18555840, 'steps': 96644, 'loss/train': 1.3603062629699707} 08/31/2021 06:43:16 - INFO - __main__ - Step 96646: {'lr': 0.00014391543828925818, 'samples': 18556032, 'steps': 96645, 'loss/train': 1.0986965894699097} 08/31/2021 06:43:16 - INFO - __main__ - Step 96647: {'lr': 0.0001439106330362196, 'samples': 18556224, 'steps': 96646, 'loss/train': 1.1960405111312866} 08/31/2021 06:43:16 - INFO - __main__ - Step 96648: {'lr': 0.0001439058278309832, 'samples': 18556416, 'steps': 96647, 'loss/train': 0.745080292224884} 08/31/2021 06:43:17 - INFO - __main__ - Step 96649: {'lr': 0.00014390102267355123, 'samples': 18556608, 'steps': 96648, 'loss/train': 1.029473900794983} 08/31/2021 06:43:18 - INFO - __main__ - Step 96650: {'lr': 0.00014389621756392585, 'samples': 18556800, 'steps': 96649, 'loss/train': 1.043235421180725} 08/31/2021 06:43:19 - INFO - __main__ - Step 96651: {'lr': 0.00014389141250210913, 'samples': 18556992, 'steps': 96650, 'loss/train': 1.3367884159088135} 08/31/2021 06:43:19 - INFO - __main__ - Step 96652: {'lr': 0.00014388660748810333, 'samples': 18557184, 'steps': 96651, 'loss/train': 0.9121207594871521} 08/31/2021 06:43:19 - INFO - __main__ - Step 96653: {'lr': 0.0001438818025219106, 'samples': 18557376, 'steps': 96652, 'loss/train': 0.6835231781005859} 08/31/2021 06:43:20 - INFO - __main__ - Step 96654: {'lr': 0.00014387699760353307, 'samples': 18557568, 'steps': 96653, 'loss/train': 1.4197958707809448} 08/31/2021 06:43:20 - INFO - __main__ - Step 96655: {'lr': 0.00014387219273297297, 'samples': 18557760, 'steps': 96654, 'loss/train': 1.4687221050262451} 08/31/2021 06:43:22 - INFO - __main__ - Step 96656: {'lr': 0.0001438673879102324, 'samples': 18557952, 'steps': 96655, 'loss/train': 1.4048717021942139} 08/31/2021 06:43:22 - INFO - __main__ - Step 96657: {'lr': 0.00014386258313531353, 'samples': 18558144, 'steps': 96656, 'loss/train': 0.7122014760971069} 08/31/2021 06:43:22 - INFO - __main__ - Step 96658: {'lr': 0.00014385777840821853, 'samples': 18558336, 'steps': 96657, 'loss/train': 1.421080470085144} 08/31/2021 06:43:23 - INFO - __main__ - Step 96659: {'lr': 0.00014385297372894972, 'samples': 18558528, 'steps': 96658, 'loss/train': 1.2328393459320068} 08/31/2021 06:43:23 - INFO - __main__ - Step 96660: {'lr': 0.00014384816909750897, 'samples': 18558720, 'steps': 96659, 'loss/train': 1.2586076259613037} 08/31/2021 06:43:25 - INFO - __main__ - Step 96661: {'lr': 0.00014384336451389864, 'samples': 18558912, 'steps': 96660, 'loss/train': 1.0512683391571045} 08/31/2021 06:43:25 - INFO - __main__ - Step 96662: {'lr': 0.00014383855997812084, 'samples': 18559104, 'steps': 96661, 'loss/train': 0.9856039881706238} 08/31/2021 06:43:25 - INFO - __main__ - Step 96663: {'lr': 0.00014383375549017774, 'samples': 18559296, 'steps': 96662, 'loss/train': 1.2353135347366333} 08/31/2021 06:43:26 - INFO - __main__ - Step 96664: {'lr': 0.00014382895105007155, 'samples': 18559488, 'steps': 96663, 'loss/train': 1.8335280418395996} 08/31/2021 06:43:26 - INFO - __main__ - Step 96665: {'lr': 0.00014382414665780436, 'samples': 18559680, 'steps': 96664, 'loss/train': 0.9308651089668274} 08/31/2021 06:43:28 - INFO - __main__ - Step 96666: {'lr': 0.00014381934231337835, 'samples': 18559872, 'steps': 96665, 'loss/train': 1.4001613855361938} 08/31/2021 06:43:28 - INFO - __main__ - Step 96667: {'lr': 0.00014381453801679572, 'samples': 18560064, 'steps': 96666, 'loss/train': 1.280354380607605} 08/31/2021 06:43:28 - INFO - __main__ - Step 96668: {'lr': 0.00014380973376805866, 'samples': 18560256, 'steps': 96667, 'loss/train': 0.7418614029884338} 08/31/2021 06:43:29 - INFO - __main__ - Step 96669: {'lr': 0.00014380492956716926, 'samples': 18560448, 'steps': 96668, 'loss/train': 1.040845274925232} 08/31/2021 06:43:29 - INFO - __main__ - Step 96670: {'lr': 0.00014380012541412974, 'samples': 18560640, 'steps': 96669, 'loss/train': 0.9217097759246826} 08/31/2021 06:43:31 - INFO - __main__ - Step 96671: {'lr': 0.00014379532130894224, 'samples': 18560832, 'steps': 96670, 'loss/train': 0.3961760103702545} 08/31/2021 06:43:31 - INFO - __main__ - Step 96672: {'lr': 0.0001437905172516089, 'samples': 18561024, 'steps': 96671, 'loss/train': 0.8793443441390991} 08/31/2021 06:43:31 - INFO - __main__ - Step 96673: {'lr': 0.00014378571324213203, 'samples': 18561216, 'steps': 96672, 'loss/train': 1.3977998495101929} 08/31/2021 06:43:32 - INFO - __main__ - Step 96674: {'lr': 0.0001437809092805136, 'samples': 18561408, 'steps': 96673, 'loss/train': 1.1969585418701172} 08/31/2021 06:43:32 - INFO - __main__ - Step 96675: {'lr': 0.00014377610536675585, 'samples': 18561600, 'steps': 96674, 'loss/train': 0.8700608611106873} 08/31/2021 06:43:33 - INFO - __main__ - Step 96676: {'lr': 0.00014377130150086093, 'samples': 18561792, 'steps': 96675, 'loss/train': 0.6953405737876892} 08/31/2021 06:43:34 - INFO - __main__ - Step 96677: {'lr': 0.00014376649768283101, 'samples': 18561984, 'steps': 96676, 'loss/train': 1.7489771842956543} 08/31/2021 06:43:34 - INFO - __main__ - Step 96678: {'lr': 0.0001437616939126683, 'samples': 18562176, 'steps': 96677, 'loss/train': 1.6967103481292725} 08/31/2021 06:43:35 - INFO - __main__ - Step 96679: {'lr': 0.0001437568901903749, 'samples': 18562368, 'steps': 96678, 'loss/train': 0.9981000423431396} 08/31/2021 06:43:35 - INFO - __main__ - Step 96680: {'lr': 0.00014375208651595304, 'samples': 18562560, 'steps': 96679, 'loss/train': 1.062977910041809} 08/31/2021 06:43:36 - INFO - __main__ - Step 96681: {'lr': 0.0001437472828894048, 'samples': 18562752, 'steps': 96680, 'loss/train': 1.3429765701293945} 08/31/2021 06:43:37 - INFO - __main__ - Step 96682: {'lr': 0.00014374247931073244, 'samples': 18562944, 'steps': 96681, 'loss/train': 0.8645380139350891} 08/31/2021 06:43:37 - INFO - __main__ - Step 96683: {'lr': 0.00014373767577993807, 'samples': 18563136, 'steps': 96682, 'loss/train': 1.1887251138687134} 08/31/2021 06:43:38 - INFO - __main__ - Step 96684: {'lr': 0.00014373287229702388, 'samples': 18563328, 'steps': 96683, 'loss/train': 1.5440608263015747} 08/31/2021 06:43:38 - INFO - __main__ - Step 96685: {'lr': 0.00014372806886199196, 'samples': 18563520, 'steps': 96684, 'loss/train': 1.0574592351913452} 08/31/2021 06:43:40 - INFO - __main__ - Step 96686: {'lr': 0.00014372326547484472, 'samples': 18563712, 'steps': 96685, 'loss/train': 0.7085200548171997} 08/31/2021 06:43:41 - INFO - __main__ - Step 96687: {'lr': 0.00014371846213558396, 'samples': 18563904, 'steps': 96686, 'loss/train': 1.219497561454773} 08/31/2021 06:43:41 - INFO - __main__ - Step 96688: {'lr': 0.00014371365884421205, 'samples': 18564096, 'steps': 96687, 'loss/train': 0.7920130491256714} 08/31/2021 06:43:41 - INFO - __main__ - Step 96689: {'lr': 0.0001437088556007311, 'samples': 18564288, 'steps': 96688, 'loss/train': 1.06020987033844} 08/31/2021 06:43:42 - INFO - __main__ - Step 96690: {'lr': 0.00014370405240514333, 'samples': 18564480, 'steps': 96689, 'loss/train': 1.5721334218978882} 08/31/2021 06:43:42 - INFO - __main__ - Step 96691: {'lr': 0.00014369924925745087, 'samples': 18564672, 'steps': 96690, 'loss/train': 1.1154741048812866} 08/31/2021 06:43:44 - INFO - __main__ - Step 96692: {'lr': 0.0001436944461576559, 'samples': 18564864, 'steps': 96691, 'loss/train': 1.4491397142410278} 08/31/2021 06:43:44 - INFO - __main__ - Step 96693: {'lr': 0.00014368964310576055, 'samples': 18565056, 'steps': 96692, 'loss/train': 1.4881330728530884} 08/31/2021 06:43:44 - INFO - __main__ - Step 96694: {'lr': 0.00014368484010176703, 'samples': 18565248, 'steps': 96693, 'loss/train': 1.0501368045806885} 08/31/2021 06:43:45 - INFO - __main__ - Step 96695: {'lr': 0.00014368003714567746, 'samples': 18565440, 'steps': 96694, 'loss/train': 1.1364729404449463} 08/31/2021 06:43:45 - INFO - __main__ - Step 96696: {'lr': 0.00014367523423749402, 'samples': 18565632, 'steps': 96695, 'loss/train': 0.9718388915061951} 08/31/2021 06:43:47 - INFO - __main__ - Step 96697: {'lr': 0.00014367043137721887, 'samples': 18565824, 'steps': 96696, 'loss/train': 1.2713497877120972} 08/31/2021 06:43:47 - INFO - __main__ - Step 96698: {'lr': 0.0001436656285648542, 'samples': 18566016, 'steps': 96697, 'loss/train': 1.3812062740325928} 08/31/2021 06:43:47 - INFO - __main__ - Step 96699: {'lr': 0.00014366082580040214, 'samples': 18566208, 'steps': 96698, 'loss/train': 1.160968542098999} 08/31/2021 06:43:48 - INFO - __main__ - Step 96700: {'lr': 0.000143656023083865, 'samples': 18566400, 'steps': 96699, 'loss/train': 1.1890877485275269} 08/31/2021 06:43:48 - INFO - __main__ - Step 96701: {'lr': 0.0001436512204152447, 'samples': 18566592, 'steps': 96700, 'loss/train': 1.4620985984802246} 08/31/2021 06:43:50 - INFO - __main__ - Step 96702: {'lr': 0.00014364641779454352, 'samples': 18566784, 'steps': 96701, 'loss/train': 1.3583402633666992} 08/31/2021 06:43:50 - INFO - __main__ - Step 96703: {'lr': 0.00014364161522176363, 'samples': 18566976, 'steps': 96702, 'loss/train': 0.8017528653144836} 08/31/2021 06:43:50 - INFO - __main__ - Step 96704: {'lr': 0.0001436368126969072, 'samples': 18567168, 'steps': 96703, 'loss/train': 0.855571985244751} 08/31/2021 06:43:51 - INFO - __main__ - Step 96705: {'lr': 0.00014363201021997635, 'samples': 18567360, 'steps': 96704, 'loss/train': 1.3672194480895996} 08/31/2021 06:43:51 - INFO - __main__ - Step 96706: {'lr': 0.00014362720779097327, 'samples': 18567552, 'steps': 96705, 'loss/train': 0.6687718033790588} 08/31/2021 06:43:53 - INFO - __main__ - Step 96707: {'lr': 0.0001436224054099002, 'samples': 18567744, 'steps': 96706, 'loss/train': 1.454481840133667} 08/31/2021 06:43:53 - INFO - __main__ - Step 96708: {'lr': 0.00014361760307675915, 'samples': 18567936, 'steps': 96707, 'loss/train': 1.2785892486572266} 08/31/2021 06:43:54 - INFO - __main__ - Step 96709: {'lr': 0.00014361280079155237, 'samples': 18568128, 'steps': 96708, 'loss/train': 0.7721450924873352} 08/31/2021 06:43:54 - INFO - __main__ - Step 96710: {'lr': 0.00014360799855428206, 'samples': 18568320, 'steps': 96709, 'loss/train': 1.7127457857131958} 08/31/2021 06:43:54 - INFO - __main__ - Step 96711: {'lr': 0.00014360319636495033, 'samples': 18568512, 'steps': 96710, 'loss/train': 0.8072982430458069} 08/31/2021 06:43:56 - INFO - __main__ - Step 96712: {'lr': 0.00014359839422355936, 'samples': 18568704, 'steps': 96711, 'loss/train': 1.4018574953079224} 08/31/2021 06:43:56 - INFO - __main__ - Step 96713: {'lr': 0.00014359359213011143, 'samples': 18568896, 'steps': 96712, 'loss/train': 1.740746259689331} 08/31/2021 06:43:57 - INFO - __main__ - Step 96714: {'lr': 0.00014358879008460846, 'samples': 18569088, 'steps': 96713, 'loss/train': 1.2660642862319946} 08/31/2021 06:43:57 - INFO - __main__ - Step 96715: {'lr': 0.0001435839880870527, 'samples': 18569280, 'steps': 96714, 'loss/train': 1.6931027173995972} 08/31/2021 06:43:57 - INFO - __main__ - Step 96716: {'lr': 0.00014357918613744643, 'samples': 18569472, 'steps': 96715, 'loss/train': 1.1159987449645996} 08/31/2021 06:43:59 - INFO - __main__ - Step 96717: {'lr': 0.0001435743842357917, 'samples': 18569664, 'steps': 96716, 'loss/train': 1.8253026008605957} 08/31/2021 06:44:00 - INFO - __main__ - Step 96718: {'lr': 0.0001435695823820907, 'samples': 18569856, 'steps': 96717, 'loss/train': 1.6105209589004517} 08/31/2021 06:44:00 - INFO - __main__ - Step 96719: {'lr': 0.0001435647805763456, 'samples': 18570048, 'steps': 96718, 'loss/train': 1.0744380950927734} 08/31/2021 06:44:00 - INFO - __main__ - Step 96720: {'lr': 0.0001435599788185586, 'samples': 18570240, 'steps': 96719, 'loss/train': 1.1922036409378052} 08/31/2021 06:44:01 - INFO - __main__ - Step 96721: {'lr': 0.00014355517710873183, 'samples': 18570432, 'steps': 96720, 'loss/train': 0.819907009601593} 08/31/2021 06:44:01 - INFO - __main__ - Step 96722: {'lr': 0.00014355037544686744, 'samples': 18570624, 'steps': 96721, 'loss/train': 1.005292534828186} 08/31/2021 06:44:02 - INFO - __main__ - Step 96723: {'lr': 0.0001435455738329676, 'samples': 18570816, 'steps': 96722, 'loss/train': 1.18827223777771} 08/31/2021 06:44:03 - INFO - __main__ - Step 96724: {'lr': 0.0001435407722670345, 'samples': 18571008, 'steps': 96723, 'loss/train': 1.1286494731903076} 08/31/2021 06:44:03 - INFO - __main__ - Step 96725: {'lr': 0.00014353597074907027, 'samples': 18571200, 'steps': 96724, 'loss/train': 1.2900034189224243} 08/31/2021 06:44:03 - INFO - __main__ - Step 96726: {'lr': 0.00014353116927907708, 'samples': 18571392, 'steps': 96725, 'loss/train': 0.9935600757598877} 08/31/2021 06:44:04 - INFO - __main__ - Step 96727: {'lr': 0.00014352636785705723, 'samples': 18571584, 'steps': 96726, 'loss/train': 0.7948653697967529} 08/31/2021 06:44:05 - INFO - __main__ - Step 96728: {'lr': 0.00014352156648301262, 'samples': 18571776, 'steps': 96727, 'loss/train': 1.3137320280075073} 08/31/2021 06:44:06 - INFO - __main__ - Step 96729: {'lr': 0.0001435167651569456, 'samples': 18571968, 'steps': 96728, 'loss/train': 0.9911015033721924} 08/31/2021 06:44:06 - INFO - __main__ - Step 96730: {'lr': 0.00014351196387885824, 'samples': 18572160, 'steps': 96729, 'loss/train': 1.053792953491211} 08/31/2021 06:44:06 - INFO - __main__ - Step 96731: {'lr': 0.00014350716264875275, 'samples': 18572352, 'steps': 96730, 'loss/train': 0.9499380588531494} 08/31/2021 06:44:07 - INFO - __main__ - Step 96732: {'lr': 0.0001435023614666313, 'samples': 18572544, 'steps': 96731, 'loss/train': 0.8619197607040405} 08/31/2021 06:44:08 - INFO - __main__ - Step 96733: {'lr': 0.00014349756033249606, 'samples': 18572736, 'steps': 96732, 'loss/train': 1.2481598854064941} 08/31/2021 06:44:09 - INFO - __main__ - Step 96734: {'lr': 0.00014349275924634914, 'samples': 18572928, 'steps': 96733, 'loss/train': 0.7441053986549377} 08/31/2021 06:44:09 - INFO - __main__ - Step 96735: {'lr': 0.00014348795820819278, 'samples': 18573120, 'steps': 96734, 'loss/train': 1.2978779077529907} 08/31/2021 06:44:10 - INFO - __main__ - Step 96736: {'lr': 0.00014348315721802906, 'samples': 18573312, 'steps': 96735, 'loss/train': 1.718599796295166} 08/31/2021 06:44:10 - INFO - __main__ - Step 96737: {'lr': 0.0001434783562758602, 'samples': 18573504, 'steps': 96736, 'loss/train': 0.8733668923377991} 08/31/2021 06:44:12 - INFO - __main__ - Step 96738: {'lr': 0.00014347355538168837, 'samples': 18573696, 'steps': 96737, 'loss/train': 1.087062954902649} 08/31/2021 06:44:12 - INFO - __main__ - Step 96739: {'lr': 0.00014346875453551567, 'samples': 18573888, 'steps': 96738, 'loss/train': 1.4335209131240845} 08/31/2021 06:44:12 - INFO - __main__ - Step 96740: {'lr': 0.00014346395373734445, 'samples': 18574080, 'steps': 96739, 'loss/train': 1.0356978178024292} 08/31/2021 06:44:13 - INFO - __main__ - Step 96741: {'lr': 0.0001434591529871766, 'samples': 18574272, 'steps': 96740, 'loss/train': 1.3795156478881836} 08/31/2021 06:44:13 - INFO - __main__ - Step 96742: {'lr': 0.00014345435228501442, 'samples': 18574464, 'steps': 96741, 'loss/train': 1.2422229051589966} 08/31/2021 06:44:14 - INFO - __main__ - Step 96743: {'lr': 0.00014344955163086008, 'samples': 18574656, 'steps': 96742, 'loss/train': 0.6251217722892761} 08/31/2021 06:44:16 - INFO - __main__ - Step 96744: {'lr': 0.0001434447510247157, 'samples': 18574848, 'steps': 96743, 'loss/train': 0.9463390707969666} 08/31/2021 06:44:16 - INFO - __main__ - Step 96745: {'lr': 0.00014343995046658348, 'samples': 18575040, 'steps': 96744, 'loss/train': 0.12798111140727997} 08/31/2021 06:44:16 - INFO - __main__ - Step 96746: {'lr': 0.0001434351499564656, 'samples': 18575232, 'steps': 96745, 'loss/train': 1.0038666725158691} 08/31/2021 06:44:17 - INFO - __main__ - Step 96747: {'lr': 0.00014343034949436417, 'samples': 18575424, 'steps': 96746, 'loss/train': 0.7428969144821167} 08/31/2021 06:44:17 - INFO - __main__ - Step 96748: {'lr': 0.00014342554908028138, 'samples': 18575616, 'steps': 96747, 'loss/train': 1.3566405773162842} 08/31/2021 06:44:19 - INFO - __main__ - Step 96749: {'lr': 0.0001434207487142194, 'samples': 18575808, 'steps': 96748, 'loss/train': 1.1446188688278198} 08/31/2021 06:44:19 - INFO - __main__ - Step 96750: {'lr': 0.0001434159483961804, 'samples': 18576000, 'steps': 96749, 'loss/train': 1.1909323930740356} 08/31/2021 06:44:19 - INFO - __main__ - Step 96751: {'lr': 0.0001434111481261665, 'samples': 18576192, 'steps': 96750, 'loss/train': 0.8579829335212708} 08/31/2021 06:44:20 - INFO - __main__ - Step 96752: {'lr': 0.0001434063479041799, 'samples': 18576384, 'steps': 96751, 'loss/train': 0.7578479051589966} 08/31/2021 06:44:20 - INFO - __main__ - Step 96753: {'lr': 0.00014340154773022284, 'samples': 18576576, 'steps': 96752, 'loss/train': 0.08185013383626938} 08/31/2021 06:44:22 - INFO - __main__ - Step 96754: {'lr': 0.00014339674760429732, 'samples': 18576768, 'steps': 96753, 'loss/train': 0.13207510113716125} 08/31/2021 06:44:22 - INFO - __main__ - Step 96755: {'lr': 0.0001433919475264056, 'samples': 18576960, 'steps': 96754, 'loss/train': 0.7440239191055298} 08/31/2021 06:44:23 - INFO - __main__ - Step 96756: {'lr': 0.0001433871474965498, 'samples': 18577152, 'steps': 96755, 'loss/train': 1.1306650638580322} 08/31/2021 06:44:23 - INFO - __main__ - Step 96757: {'lr': 0.0001433823475147321, 'samples': 18577344, 'steps': 96756, 'loss/train': 1.1050786972045898} 08/31/2021 06:44:23 - INFO - __main__ - Step 96758: {'lr': 0.00014337754758095468, 'samples': 18577536, 'steps': 96757, 'loss/train': 0.6185306906700134} 08/31/2021 06:44:25 - INFO - __main__ - Step 96759: {'lr': 0.00014337274769521969, 'samples': 18577728, 'steps': 96758, 'loss/train': 0.8958358764648438} 08/31/2021 06:44:25 - INFO - __main__ - Step 96760: {'lr': 0.0001433679478575293, 'samples': 18577920, 'steps': 96759, 'loss/train': 1.445382833480835} 08/31/2021 06:44:26 - INFO - __main__ - Step 96761: {'lr': 0.00014336314806788565, 'samples': 18578112, 'steps': 96760, 'loss/train': 1.1623412370681763} 08/31/2021 06:44:26 - INFO - __main__ - Step 96762: {'lr': 0.0001433583483262909, 'samples': 18578304, 'steps': 96761, 'loss/train': 0.9152078628540039} 08/31/2021 06:44:26 - INFO - __main__ - Step 96763: {'lr': 0.00014335354863274729, 'samples': 18578496, 'steps': 96762, 'loss/train': 0.37776222825050354} 08/31/2021 06:44:28 - INFO - __main__ - Step 96764: {'lr': 0.000143348748987257, 'samples': 18578688, 'steps': 96763, 'loss/train': 1.179848074913025} 08/31/2021 06:44:29 - INFO - __main__ - Step 96765: {'lr': 0.00014334394938982203, 'samples': 18578880, 'steps': 96764, 'loss/train': 1.1515213251113892} 08/31/2021 06:44:29 - INFO - __main__ - Step 96766: {'lr': 0.0001433391498404446, 'samples': 18579072, 'steps': 96765, 'loss/train': 1.188004493713379} 08/31/2021 06:44:30 - INFO - __main__ - Step 96767: {'lr': 0.0001433343503391269, 'samples': 18579264, 'steps': 96766, 'loss/train': 1.4613839387893677} 08/31/2021 06:44:30 - INFO - __main__ - Step 96768: {'lr': 0.00014332955088587114, 'samples': 18579456, 'steps': 96767, 'loss/train': 1.0716197490692139} 08/31/2021 06:44:30 - INFO - __main__ - Step 96769: {'lr': 0.00014332475148067943, 'samples': 18579648, 'steps': 96768, 'loss/train': 0.6120595932006836} 08/31/2021 06:44:32 - INFO - __main__ - Step 96770: {'lr': 0.00014331995212355392, 'samples': 18579840, 'steps': 96769, 'loss/train': 0.8498466610908508} 08/31/2021 06:44:33 - INFO - __main__ - Step 96771: {'lr': 0.00014331515281449682, 'samples': 18580032, 'steps': 96770, 'loss/train': 1.016719102859497} 08/31/2021 06:44:33 - INFO - __main__ - Step 96772: {'lr': 0.0001433103535535102, 'samples': 18580224, 'steps': 96771, 'loss/train': 1.0721570253372192} 08/31/2021 06:44:33 - INFO - __main__ - Step 96773: {'lr': 0.00014330555434059633, 'samples': 18580416, 'steps': 96772, 'loss/train': 0.9373630881309509} 08/31/2021 06:44:34 - INFO - __main__ - Step 96774: {'lr': 0.00014330075517575736, 'samples': 18580608, 'steps': 96773, 'loss/train': 1.2616465091705322} 08/31/2021 06:44:34 - INFO - __main__ - Step 96775: {'lr': 0.00014329595605899547, 'samples': 18580800, 'steps': 96774, 'loss/train': 0.6691596508026123} 08/31/2021 06:44:36 - INFO - __main__ - Step 96776: {'lr': 0.00014329115699031274, 'samples': 18580992, 'steps': 96775, 'loss/train': 0.13573941588401794} 08/31/2021 06:44:36 - INFO - __main__ - Step 96777: {'lr': 0.0001432863579697113, 'samples': 18581184, 'steps': 96776, 'loss/train': 1.399859070777893} 08/31/2021 06:44:36 - INFO - __main__ - Step 96778: {'lr': 0.0001432815589971934, 'samples': 18581376, 'steps': 96777, 'loss/train': 1.036489486694336} 08/31/2021 06:44:37 - INFO - __main__ - Step 96779: {'lr': 0.00014327676007276123, 'samples': 18581568, 'steps': 96778, 'loss/train': 0.6461042165756226} 08/31/2021 06:44:37 - INFO - __main__ - Step 96780: {'lr': 0.00014327196119641686, 'samples': 18581760, 'steps': 96779, 'loss/train': 1.3281251192092896} 08/31/2021 06:44:39 - INFO - __main__ - Step 96781: {'lr': 0.00014326716236816252, 'samples': 18581952, 'steps': 96780, 'loss/train': 1.180436611175537} 08/31/2021 06:44:39 - INFO - __main__ - Step 96782: {'lr': 0.00014326236358800032, 'samples': 18582144, 'steps': 96781, 'loss/train': 1.7790542840957642} 08/31/2021 06:44:39 - INFO - __main__ - Step 96783: {'lr': 0.00014325756485593247, 'samples': 18582336, 'steps': 96782, 'loss/train': 1.1829320192337036} 08/31/2021 06:44:40 - INFO - __main__ - Step 96784: {'lr': 0.0001432527661719611, 'samples': 18582528, 'steps': 96783, 'loss/train': 0.9844227433204651} 08/31/2021 06:44:40 - INFO - __main__ - Step 96785: {'lr': 0.0001432479675360884, 'samples': 18582720, 'steps': 96784, 'loss/train': 0.8179687857627869} 08/31/2021 06:44:42 - INFO - __main__ - Step 96786: {'lr': 0.00014324316894831664, 'samples': 18582912, 'steps': 96785, 'loss/train': 0.3405288755893707} 08/31/2021 06:44:42 - INFO - __main__ - Step 96787: {'lr': 0.00014323837040864772, 'samples': 18583104, 'steps': 96786, 'loss/train': 0.32320436835289} 08/31/2021 06:44:43 - INFO - __main__ - Step 96788: {'lr': 0.00014323357191708397, 'samples': 18583296, 'steps': 96787, 'loss/train': 0.05400138720870018} 08/31/2021 06:44:43 - INFO - __main__ - Step 96789: {'lr': 0.0001432287734736275, 'samples': 18583488, 'steps': 96788, 'loss/train': 1.3551993370056152} 08/31/2021 06:44:43 - INFO - __main__ - Step 96790: {'lr': 0.0001432239750782805, 'samples': 18583680, 'steps': 96789, 'loss/train': 1.109026312828064} 08/31/2021 06:44:45 - INFO - __main__ - Step 96791: {'lr': 0.00014321917673104518, 'samples': 18583872, 'steps': 96790, 'loss/train': 2.0380313396453857} 08/31/2021 06:44:46 - INFO - __main__ - Step 96792: {'lr': 0.0001432143784319236, 'samples': 18584064, 'steps': 96791, 'loss/train': 1.4205080270767212} 08/31/2021 06:44:46 - INFO - __main__ - Step 96793: {'lr': 0.00014320958018091797, 'samples': 18584256, 'steps': 96792, 'loss/train': 1.2894691228866577} 08/31/2021 06:44:46 - INFO - __main__ - Step 96794: {'lr': 0.0001432047819780305, 'samples': 18584448, 'steps': 96793, 'loss/train': 0.9620645046234131} 08/31/2021 06:44:47 - INFO - __main__ - Step 96795: {'lr': 0.00014319998382326328, 'samples': 18584640, 'steps': 96794, 'loss/train': 0.059085913002491} 08/31/2021 06:44:47 - INFO - __main__ - Step 96796: {'lr': 0.0001431951857166185, 'samples': 18584832, 'steps': 96795, 'loss/train': 0.7814733982086182} 08/31/2021 06:44:49 - INFO - __main__ - Step 96797: {'lr': 0.00014319038765809837, 'samples': 18585024, 'steps': 96796, 'loss/train': 1.2906767129898071} 08/31/2021 06:44:49 - INFO - __main__ - Step 96798: {'lr': 0.00014318558964770498, 'samples': 18585216, 'steps': 96797, 'loss/train': 1.0425978899002075} 08/31/2021 06:44:50 - INFO - __main__ - Step 96799: {'lr': 0.00014318079168544048, 'samples': 18585408, 'steps': 96798, 'loss/train': 1.5355799198150635} 08/31/2021 06:44:50 - INFO - __main__ - Step 96800: {'lr': 0.00014317599377130708, 'samples': 18585600, 'steps': 96799, 'loss/train': 0.37562793493270874} 08/31/2021 06:44:51 - INFO - __main__ - Step 96801: {'lr': 0.0001431711959053069, 'samples': 18585792, 'steps': 96800, 'loss/train': 1.1753005981445312} 08/31/2021 06:44:52 - INFO - __main__ - Step 96802: {'lr': 0.0001431663980874422, 'samples': 18585984, 'steps': 96801, 'loss/train': 0.9622477889060974} 08/31/2021 06:44:52 - INFO - __main__ - Step 96803: {'lr': 0.00014316160031771502, 'samples': 18586176, 'steps': 96802, 'loss/train': 1.5108397006988525} 08/31/2021 06:44:53 - INFO - __main__ - Step 96804: {'lr': 0.00014315680259612758, 'samples': 18586368, 'steps': 96803, 'loss/train': 1.29005765914917} 08/31/2021 06:44:53 - INFO - __main__ - Step 96805: {'lr': 0.00014315200492268201, 'samples': 18586560, 'steps': 96804, 'loss/train': 1.5410754680633545} 08/31/2021 06:44:53 - INFO - __main__ - Step 96806: {'lr': 0.00014314720729738053, 'samples': 18586752, 'steps': 96805, 'loss/train': 1.0174543857574463} 08/31/2021 06:44:55 - INFO - __main__ - Step 96807: {'lr': 0.00014314240972022527, 'samples': 18586944, 'steps': 96806, 'loss/train': 2.2878243923187256} 08/31/2021 06:44:56 - INFO - __main__ - Step 96808: {'lr': 0.00014313761219121848, 'samples': 18587136, 'steps': 96807, 'loss/train': 0.09274396300315857} 08/31/2021 06:44:56 - INFO - __main__ - Step 96809: {'lr': 0.00014313281471036216, 'samples': 18587328, 'steps': 96808, 'loss/train': 1.0700273513793945} 08/31/2021 06:44:56 - INFO - __main__ - Step 96810: {'lr': 0.00014312801727765851, 'samples': 18587520, 'steps': 96809, 'loss/train': 0.8340388536453247} 08/31/2021 06:44:57 - INFO - __main__ - Step 96811: {'lr': 0.00014312321989310973, 'samples': 18587712, 'steps': 96810, 'loss/train': 0.29728493094444275} 08/31/2021 06:44:58 - INFO - __main__ - Step 96812: {'lr': 0.00014311842255671796, 'samples': 18587904, 'steps': 96811, 'loss/train': 1.397322654724121} 08/31/2021 06:44:59 - INFO - __main__ - Step 96813: {'lr': 0.00014311362526848542, 'samples': 18588096, 'steps': 96812, 'loss/train': 0.019137045368552208} 08/31/2021 06:44:59 - INFO - __main__ - Step 96814: {'lr': 0.00014310882802841425, 'samples': 18588288, 'steps': 96813, 'loss/train': 1.0723260641098022} 08/31/2021 06:45:00 - INFO - __main__ - Step 96815: {'lr': 0.00014310403083650654, 'samples': 18588480, 'steps': 96814, 'loss/train': 1.4015512466430664} 08/31/2021 06:45:00 - INFO - __main__ - Step 96816: {'lr': 0.00014309923369276454, 'samples': 18588672, 'steps': 96815, 'loss/train': 0.11173549294471741} 08/31/2021 06:45:00 - INFO - __main__ - Step 96817: {'lr': 0.00014309443659719034, 'samples': 18588864, 'steps': 96816, 'loss/train': 1.6304292678833008} 08/31/2021 06:45:02 - INFO - __main__ - Step 96818: {'lr': 0.00014308963954978615, 'samples': 18589056, 'steps': 96817, 'loss/train': 1.0372172594070435} 08/31/2021 06:45:02 - INFO - __main__ - Step 96819: {'lr': 0.00014308484255055415, 'samples': 18589248, 'steps': 96818, 'loss/train': 0.8495625853538513} 08/31/2021 06:45:03 - INFO - __main__ - Step 96820: {'lr': 0.00014308004559949645, 'samples': 18589440, 'steps': 96819, 'loss/train': 0.756263017654419} 08/31/2021 06:45:03 - INFO - __main__ - Step 96821: {'lr': 0.00014307524869661533, 'samples': 18589632, 'steps': 96820, 'loss/train': 1.0000981092453003} 08/31/2021 06:45:03 - INFO - __main__ - Step 96822: {'lr': 0.00014307045184191276, 'samples': 18589824, 'steps': 96821, 'loss/train': 0.794292151927948} 08/31/2021 06:45:05 - INFO - __main__ - Step 96823: {'lr': 0.00014306565503539097, 'samples': 18590016, 'steps': 96822, 'loss/train': 0.6259718537330627} 08/31/2021 06:45:05 - INFO - __main__ - Step 96824: {'lr': 0.0001430608582770522, 'samples': 18590208, 'steps': 96823, 'loss/train': 1.0098707675933838} 08/31/2021 06:45:06 - INFO - __main__ - Step 96825: {'lr': 0.0001430560615668985, 'samples': 18590400, 'steps': 96824, 'loss/train': 1.5334950685501099} 08/31/2021 06:45:06 - INFO - __main__ - Step 96826: {'lr': 0.00014305126490493208, 'samples': 18590592, 'steps': 96825, 'loss/train': 0.3376632332801819} 08/31/2021 06:45:06 - INFO - __main__ - Step 96827: {'lr': 0.00014304646829115515, 'samples': 18590784, 'steps': 96826, 'loss/train': 0.03322833031415939} 08/31/2021 06:45:08 - INFO - __main__ - Step 96828: {'lr': 0.0001430416717255698, 'samples': 18590976, 'steps': 96827, 'loss/train': 1.1704143285751343} 08/31/2021 06:45:08 - INFO - __main__ - Step 96829: {'lr': 0.00014303687520817826, 'samples': 18591168, 'steps': 96828, 'loss/train': 1.3557287454605103} 08/31/2021 06:45:09 - INFO - __main__ - Step 96830: {'lr': 0.00014303207873898261, 'samples': 18591360, 'steps': 96829, 'loss/train': 1.4521141052246094} 08/31/2021 06:45:09 - INFO - __main__ - Step 96831: {'lr': 0.0001430272823179851, 'samples': 18591552, 'steps': 96830, 'loss/train': 1.5529743432998657} 08/31/2021 06:45:09 - INFO - __main__ - Step 96832: {'lr': 0.0001430224859451878, 'samples': 18591744, 'steps': 96831, 'loss/train': 1.415655255317688} 08/31/2021 06:45:10 - INFO - __main__ - Step 96833: {'lr': 0.00014301768962059295, 'samples': 18591936, 'steps': 96832, 'loss/train': 1.086722731590271} 08/31/2021 06:45:12 - INFO - __main__ - Step 96834: {'lr': 0.00014301289334420276, 'samples': 18592128, 'steps': 96833, 'loss/train': 0.403438001871109} 08/31/2021 06:45:12 - INFO - __main__ - Step 96835: {'lr': 0.00014300809711601922, 'samples': 18592320, 'steps': 96834, 'loss/train': 5.78272008895874} 08/31/2021 06:45:12 - INFO - __main__ - Step 96836: {'lr': 0.00014300330093604458, 'samples': 18592512, 'steps': 96835, 'loss/train': 1.2851178646087646} 08/31/2021 06:45:13 - INFO - __main__ - Step 96837: {'lr': 0.000142998504804281, 'samples': 18592704, 'steps': 96836, 'loss/train': 1.4584039449691772} 08/31/2021 06:45:13 - INFO - __main__ - Step 96838: {'lr': 0.00014299370872073065, 'samples': 18592896, 'steps': 96837, 'loss/train': 1.3527218103408813} 08/31/2021 06:45:13 - INFO - __main__ - Step 96839: {'lr': 0.00014298891268539566, 'samples': 18593088, 'steps': 96838, 'loss/train': 0.9486315846443176} 08/31/2021 06:45:15 - INFO - __main__ - Step 96840: {'lr': 0.00014298411669827826, 'samples': 18593280, 'steps': 96839, 'loss/train': 1.4777474403381348} 08/31/2021 06:45:15 - INFO - __main__ - Step 96841: {'lr': 0.00014297932075938054, 'samples': 18593472, 'steps': 96840, 'loss/train': 1.3304370641708374} 08/31/2021 06:45:16 - INFO - __main__ - Step 96842: {'lr': 0.00014297452486870465, 'samples': 18593664, 'steps': 96841, 'loss/train': 0.5244483351707458} 08/31/2021 06:45:16 - INFO - __main__ - Step 96843: {'lr': 0.00014296972902625284, 'samples': 18593856, 'steps': 96842, 'loss/train': 1.23155677318573} 08/31/2021 06:45:17 - INFO - __main__ - Step 96844: {'lr': 0.0001429649332320272, 'samples': 18594048, 'steps': 96843, 'loss/train': 1.3063530921936035} 08/31/2021 06:45:18 - INFO - __main__ - Step 96845: {'lr': 0.0001429601374860299, 'samples': 18594240, 'steps': 96844, 'loss/train': 1.437713623046875} 08/31/2021 06:45:19 - INFO - __main__ - Step 96846: {'lr': 0.00014295534178826314, 'samples': 18594432, 'steps': 96845, 'loss/train': 1.4633804559707642} 08/31/2021 06:45:19 - INFO - __main__ - Step 96847: {'lr': 0.00014295054613872903, 'samples': 18594624, 'steps': 96846, 'loss/train': 1.2572957277297974} 08/31/2021 06:45:19 - INFO - __main__ - Step 96848: {'lr': 0.00014294575053742985, 'samples': 18594816, 'steps': 96847, 'loss/train': 2.116811752319336} 08/31/2021 06:45:20 - INFO - __main__ - Step 96849: {'lr': 0.00014294095498436756, 'samples': 18595008, 'steps': 96848, 'loss/train': 1.7898764610290527} 08/31/2021 06:45:21 - INFO - __main__ - Step 96850: {'lr': 0.00014293615947954443, 'samples': 18595200, 'steps': 96849, 'loss/train': 1.0574373006820679} 08/31/2021 06:45:22 - INFO - __main__ - Step 96851: {'lr': 0.0001429313640229626, 'samples': 18595392, 'steps': 96850, 'loss/train': 0.04132675379514694} 08/31/2021 06:45:22 - INFO - __main__ - Step 96852: {'lr': 0.00014292656861462428, 'samples': 18595584, 'steps': 96851, 'loss/train': 0.15774917602539062} 08/31/2021 06:45:23 - INFO - __main__ - Step 96853: {'lr': 0.00014292177325453157, 'samples': 18595776, 'steps': 96852, 'loss/train': 0.3156624436378479} 08/31/2021 06:45:23 - INFO - __main__ - Step 96854: {'lr': 0.00014291697794268667, 'samples': 18595968, 'steps': 96853, 'loss/train': 0.8095567226409912} 08/31/2021 06:45:25 - INFO - __main__ - Step 96855: {'lr': 0.0001429121826790917, 'samples': 18596160, 'steps': 96854, 'loss/train': 1.1362433433532715} 08/31/2021 06:45:25 - INFO - __main__ - Step 96856: {'lr': 0.00014290738746374886, 'samples': 18596352, 'steps': 96855, 'loss/train': 0.993026614189148} 08/31/2021 06:45:26 - INFO - __main__ - Step 96857: {'lr': 0.0001429025922966603, 'samples': 18596544, 'steps': 96856, 'loss/train': 1.3114901781082153} 08/31/2021 06:45:26 - INFO - __main__ - Step 96858: {'lr': 0.00014289779717782818, 'samples': 18596736, 'steps': 96857, 'loss/train': 1.0040192604064941} 08/31/2021 06:45:26 - INFO - __main__ - Step 96859: {'lr': 0.0001428930021072547, 'samples': 18596928, 'steps': 96858, 'loss/train': 1.4290761947631836} 08/31/2021 06:45:27 - INFO - __main__ - Step 96860: {'lr': 0.00014288820708494195, 'samples': 18597120, 'steps': 96859, 'loss/train': 0.3359902799129486} 08/31/2021 06:45:28 - INFO - __main__ - Step 96861: {'lr': 0.00014288341211089219, 'samples': 18597312, 'steps': 96860, 'loss/train': 0.7197900414466858} 08/31/2021 06:45:29 - INFO - __main__ - Step 96862: {'lr': 0.00014287861718510745, 'samples': 18597504, 'steps': 96861, 'loss/train': 1.173689842224121} 08/31/2021 06:45:29 - INFO - __main__ - Step 96863: {'lr': 0.00014287382230758995, 'samples': 18597696, 'steps': 96862, 'loss/train': 1.4535186290740967} 08/31/2021 06:45:29 - INFO - __main__ - Step 96864: {'lr': 0.00014286902747834182, 'samples': 18597888, 'steps': 96863, 'loss/train': 1.035046100616455} 08/31/2021 06:45:30 - INFO - __main__ - Step 96865: {'lr': 0.00014286423269736526, 'samples': 18598080, 'steps': 96864, 'loss/train': 1.1379555463790894} 08/31/2021 06:45:31 - INFO - __main__ - Step 96866: {'lr': 0.00014285943796466243, 'samples': 18598272, 'steps': 96865, 'loss/train': 1.3542557954788208} 08/31/2021 06:45:32 - INFO - __main__ - Step 96867: {'lr': 0.00014285464328023551, 'samples': 18598464, 'steps': 96866, 'loss/train': 1.63749361038208} 08/31/2021 06:45:32 - INFO - __main__ - Step 96868: {'lr': 0.00014284984864408663, 'samples': 18598656, 'steps': 96867, 'loss/train': 1.4719107151031494} 08/31/2021 06:45:32 - INFO - __main__ - Step 96869: {'lr': 0.00014284505405621795, 'samples': 18598848, 'steps': 96868, 'loss/train': 0.5935290455818176} 08/31/2021 06:45:33 - INFO - __main__ - Step 96870: {'lr': 0.0001428402595166316, 'samples': 18599040, 'steps': 96869, 'loss/train': 0.9679000973701477} 08/31/2021 06:45:34 - INFO - __main__ - Step 96871: {'lr': 0.00014283546502532983, 'samples': 18599232, 'steps': 96870, 'loss/train': 1.3673111200332642} 08/31/2021 06:45:35 - INFO - __main__ - Step 96872: {'lr': 0.00014283067058231468, 'samples': 18599424, 'steps': 96871, 'loss/train': 1.2480947971343994} 08/31/2021 06:45:35 - INFO - __main__ - Step 96873: {'lr': 0.00014282587618758843, 'samples': 18599616, 'steps': 96872, 'loss/train': 1.266038179397583} 08/31/2021 06:45:35 - INFO - __main__ - Step 96874: {'lr': 0.00014282108184115316, 'samples': 18599808, 'steps': 96873, 'loss/train': 0.8640566468238831} 08/31/2021 06:45:36 - INFO - __main__ - Step 96875: {'lr': 0.0001428162875430112, 'samples': 18600000, 'steps': 96874, 'loss/train': 0.19316591322422028} 08/31/2021 06:45:37 - INFO - __main__ - Step 96876: {'lr': 0.0001428114932931644, 'samples': 18600192, 'steps': 96875, 'loss/train': 0.8076790571212769} 08/31/2021 06:45:38 - INFO - __main__ - Step 96877: {'lr': 0.00014280669909161515, 'samples': 18600384, 'steps': 96876, 'loss/train': 0.7771775722503662} 08/31/2021 06:45:38 - INFO - __main__ - Step 96878: {'lr': 0.00014280190493836552, 'samples': 18600576, 'steps': 96877, 'loss/train': 1.0281847715377808} 08/31/2021 06:45:38 - INFO - __main__ - Step 96879: {'lr': 0.00014279711083341767, 'samples': 18600768, 'steps': 96878, 'loss/train': 0.1448027491569519} 08/31/2021 06:45:39 - INFO - __main__ - Step 96880: {'lr': 0.00014279231677677385, 'samples': 18600960, 'steps': 96879, 'loss/train': 1.8681070804595947} 08/31/2021 06:45:40 - INFO - __main__ - Step 96881: {'lr': 0.00014278752276843608, 'samples': 18601152, 'steps': 96880, 'loss/train': 0.968786895275116} 08/31/2021 06:45:41 - INFO - __main__ - Step 96882: {'lr': 0.00014278272880840668, 'samples': 18601344, 'steps': 96881, 'loss/train': 0.8196998238563538} 08/31/2021 06:45:41 - INFO - __main__ - Step 96883: {'lr': 0.00014277793489668767, 'samples': 18601536, 'steps': 96882, 'loss/train': 1.4094825983047485} 08/31/2021 06:45:41 - INFO - __main__ - Step 96884: {'lr': 0.00014277314103328128, 'samples': 18601728, 'steps': 96883, 'loss/train': 0.7742933630943298} 08/31/2021 06:45:42 - INFO - __main__ - Step 96885: {'lr': 0.00014276834721818968, 'samples': 18601920, 'steps': 96884, 'loss/train': 1.3037725687026978} 08/31/2021 06:45:43 - INFO - __main__ - Step 96886: {'lr': 0.000142763553451415, 'samples': 18602112, 'steps': 96885, 'loss/train': 0.8875266909599304} 08/31/2021 06:45:44 - INFO - __main__ - Step 96887: {'lr': 0.00014275875973295937, 'samples': 18602304, 'steps': 96886, 'loss/train': 0.04699799045920372} 08/31/2021 06:45:44 - INFO - __main__ - Step 96888: {'lr': 0.00014275396606282513, 'samples': 18602496, 'steps': 96887, 'loss/train': 1.7200069427490234} 08/31/2021 06:45:44 - INFO - __main__ - Step 96889: {'lr': 0.0001427491724410142, 'samples': 18602688, 'steps': 96888, 'loss/train': 0.7409180402755737} 08/31/2021 06:45:45 - INFO - __main__ - Step 96890: {'lr': 0.00014274437886752884, 'samples': 18602880, 'steps': 96889, 'loss/train': 0.6533226370811462} 08/31/2021 06:45:46 - INFO - __main__ - Step 96891: {'lr': 0.00014273958534237116, 'samples': 18603072, 'steps': 96890, 'loss/train': 1.448262095451355} 08/31/2021 06:45:47 - INFO - __main__ - Step 96892: {'lr': 0.0001427347918655434, 'samples': 18603264, 'steps': 96891, 'loss/train': 0.8809977173805237} 08/31/2021 06:45:47 - INFO - __main__ - Step 96893: {'lr': 0.00014272999843704771, 'samples': 18603456, 'steps': 96892, 'loss/train': 1.1340404748916626} 08/31/2021 06:45:47 - INFO - __main__ - Step 96894: {'lr': 0.0001427252050568862, 'samples': 18603648, 'steps': 96893, 'loss/train': 0.8113649487495422} 08/31/2021 06:45:48 - INFO - __main__ - Step 96895: {'lr': 0.00014272041172506107, 'samples': 18603840, 'steps': 96894, 'loss/train': 0.9812653064727783} 08/31/2021 06:45:50 - INFO - __main__ - Step 96896: {'lr': 0.00014271561844157445, 'samples': 18604032, 'steps': 96895, 'loss/train': 1.4630669355392456} 08/31/2021 06:45:50 - INFO - __main__ - Step 96897: {'lr': 0.00014271082520642852, 'samples': 18604224, 'steps': 96896, 'loss/train': 1.1123095750808716} 08/31/2021 06:45:51 - INFO - __main__ - Step 96898: {'lr': 0.00014270603201962546, 'samples': 18604416, 'steps': 96897, 'loss/train': 0.25733622908592224} 08/31/2021 06:45:51 - INFO - __main__ - Step 96899: {'lr': 0.00014270123888116738, 'samples': 18604608, 'steps': 96898, 'loss/train': 1.3532360792160034} 08/31/2021 06:45:51 - INFO - __main__ - Step 96900: {'lr': 0.00014269644579105646, 'samples': 18604800, 'steps': 96899, 'loss/train': 1.3559670448303223} 08/31/2021 06:45:52 - INFO - __main__ - Step 96901: {'lr': 0.00014269165274929496, 'samples': 18604992, 'steps': 96900, 'loss/train': 0.47744816541671753} 08/31/2021 06:45:54 - INFO - __main__ - Step 96902: {'lr': 0.0001426868597558849, 'samples': 18605184, 'steps': 96901, 'loss/train': 1.2055869102478027} 08/31/2021 06:45:54 - INFO - __main__ - Step 96903: {'lr': 0.00014268206681082842, 'samples': 18605376, 'steps': 96902, 'loss/train': 0.05412515625357628} 08/31/2021 06:45:54 - INFO - __main__ - Step 96904: {'lr': 0.00014267727391412778, 'samples': 18605568, 'steps': 96903, 'loss/train': 1.3072243928909302} 08/31/2021 06:45:55 - INFO - __main__ - Step 96905: {'lr': 0.00014267248106578513, 'samples': 18605760, 'steps': 96904, 'loss/train': 1.415990948677063} 08/31/2021 06:45:55 - INFO - __main__ - Step 96906: {'lr': 0.00014266768826580255, 'samples': 18605952, 'steps': 96905, 'loss/train': 0.7787221074104309} 08/31/2021 06:45:57 - INFO - __main__ - Step 96907: {'lr': 0.00014266289551418226, 'samples': 18606144, 'steps': 96906, 'loss/train': 0.4804087281227112} 08/31/2021 06:45:57 - INFO - __main__ - Step 96908: {'lr': 0.00014265810281092645, 'samples': 18606336, 'steps': 96907, 'loss/train': 0.9762008786201477} 08/31/2021 06:45:57 - INFO - __main__ - Step 96909: {'lr': 0.0001426533101560372, 'samples': 18606528, 'steps': 96908, 'loss/train': 1.3543320894241333} 08/31/2021 06:45:58 - INFO - __main__ - Step 96910: {'lr': 0.00014264851754951675, 'samples': 18606720, 'steps': 96909, 'loss/train': 1.457216739654541} 08/31/2021 06:45:58 - INFO - __main__ - Step 96911: {'lr': 0.0001426437249913672, 'samples': 18606912, 'steps': 96910, 'loss/train': 3.126108407974243} 08/31/2021 06:46:00 - INFO - __main__ - Step 96912: {'lr': 0.00014263893248159078, 'samples': 18607104, 'steps': 96911, 'loss/train': 0.13595792651176453} 08/31/2021 06:46:00 - INFO - __main__ - Step 96913: {'lr': 0.00014263414002018955, 'samples': 18607296, 'steps': 96912, 'loss/train': 0.8682147264480591} 08/31/2021 06:46:00 - INFO - __main__ - Step 96914: {'lr': 0.0001426293476071657, 'samples': 18607488, 'steps': 96913, 'loss/train': 1.1937220096588135} 08/31/2021 06:46:01 - INFO - __main__ - Step 96915: {'lr': 0.00014262455524252155, 'samples': 18607680, 'steps': 96914, 'loss/train': 0.5193722248077393} 08/31/2021 06:46:01 - INFO - __main__ - Step 96916: {'lr': 0.000142619762926259, 'samples': 18607872, 'steps': 96915, 'loss/train': 1.315343976020813} 08/31/2021 06:46:03 - INFO - __main__ - Step 96917: {'lr': 0.0001426149706583803, 'samples': 18608064, 'steps': 96916, 'loss/train': 1.1505475044250488} 08/31/2021 06:46:03 - INFO - __main__ - Step 96918: {'lr': 0.00014261017843888768, 'samples': 18608256, 'steps': 96917, 'loss/train': 1.9838743209838867} 08/31/2021 06:46:03 - INFO - __main__ - Step 96919: {'lr': 0.00014260538626778324, 'samples': 18608448, 'steps': 96918, 'loss/train': 1.209079384803772} 08/31/2021 06:46:04 - INFO - __main__ - Step 96920: {'lr': 0.0001426005941450692, 'samples': 18608640, 'steps': 96919, 'loss/train': 0.8940463066101074} 08/31/2021 06:46:04 - INFO - __main__ - Step 96921: {'lr': 0.00014259580207074763, 'samples': 18608832, 'steps': 96920, 'loss/train': 1.2076810598373413} 08/31/2021 06:46:06 - INFO - __main__ - Step 96922: {'lr': 0.00014259101004482073, 'samples': 18609024, 'steps': 96921, 'loss/train': 1.3443689346313477} 08/31/2021 06:46:06 - INFO - __main__ - Step 96923: {'lr': 0.00014258621806729067, 'samples': 18609216, 'steps': 96922, 'loss/train': 1.0353108644485474} 08/31/2021 06:46:06 - INFO - __main__ - Step 96924: {'lr': 0.0001425814261381596, 'samples': 18609408, 'steps': 96923, 'loss/train': 2.015859603881836} 08/31/2021 06:46:07 - INFO - __main__ - Step 96925: {'lr': 0.0001425766342574297, 'samples': 18609600, 'steps': 96924, 'loss/train': 1.8067394495010376} 08/31/2021 06:46:07 - INFO - __main__ - Step 96926: {'lr': 0.0001425718424251031, 'samples': 18609792, 'steps': 96925, 'loss/train': 0.6180989146232605} 08/31/2021 06:46:09 - INFO - __main__ - Step 96927: {'lr': 0.00014256705064118197, 'samples': 18609984, 'steps': 96926, 'loss/train': 1.5047725439071655} 08/31/2021 06:46:09 - INFO - __main__ - Step 96928: {'lr': 0.00014256225890566857, 'samples': 18610176, 'steps': 96927, 'loss/train': 1.0148946046829224} 08/31/2021 06:46:09 - INFO - __main__ - Step 96929: {'lr': 0.00014255746721856486, 'samples': 18610368, 'steps': 96928, 'loss/train': 0.7681695222854614} 08/31/2021 06:46:10 - INFO - __main__ - Step 96930: {'lr': 0.00014255267557987308, 'samples': 18610560, 'steps': 96929, 'loss/train': 1.0778424739837646} 08/31/2021 06:46:10 - INFO - __main__ - Step 96931: {'lr': 0.00014254788398959542, 'samples': 18610752, 'steps': 96930, 'loss/train': 2.1400718688964844} 08/31/2021 06:46:12 - INFO - __main__ - Step 96932: {'lr': 0.00014254309244773403, 'samples': 18610944, 'steps': 96931, 'loss/train': 0.8440712094306946} 08/31/2021 06:46:13 - INFO - __main__ - Step 96933: {'lr': 0.00014253830095429108, 'samples': 18611136, 'steps': 96932, 'loss/train': 0.870620608329773} 08/31/2021 06:46:13 - INFO - __main__ - Step 96934: {'lr': 0.00014253350950926868, 'samples': 18611328, 'steps': 96933, 'loss/train': 1.2050117254257202} 08/31/2021 06:46:13 - INFO - __main__ - Step 96935: {'lr': 0.00014252871811266905, 'samples': 18611520, 'steps': 96934, 'loss/train': 1.2065670490264893} 08/31/2021 06:46:14 - INFO - __main__ - Step 96936: {'lr': 0.0001425239267644943, 'samples': 18611712, 'steps': 96935, 'loss/train': 0.026798535138368607} 08/31/2021 06:46:14 - INFO - __main__ - Step 96937: {'lr': 0.0001425191354647466, 'samples': 18611904, 'steps': 96936, 'loss/train': 0.018023712560534477} 08/31/2021 06:46:14 - INFO - __main__ - Step 96938: {'lr': 0.00014251434421342816, 'samples': 18612096, 'steps': 96937, 'loss/train': 2.0517466068267822} 08/31/2021 06:46:16 - INFO - __main__ - Step 96939: {'lr': 0.0001425095530105411, 'samples': 18612288, 'steps': 96938, 'loss/train': 1.4480258226394653} 08/31/2021 06:46:16 - INFO - __main__ - Step 96940: {'lr': 0.00014250476185608752, 'samples': 18612480, 'steps': 96939, 'loss/train': 0.5874694585800171} 08/31/2021 06:46:17 - INFO - __main__ - Step 96941: {'lr': 0.00014249997075006966, 'samples': 18612672, 'steps': 96940, 'loss/train': 1.0258952379226685} 08/31/2021 06:46:17 - INFO - __main__ - Step 96942: {'lr': 0.00014249517969248975, 'samples': 18612864, 'steps': 96941, 'loss/train': 1.2094136476516724} 08/31/2021 06:46:17 - INFO - __main__ - Step 96943: {'lr': 0.0001424903886833498, 'samples': 18613056, 'steps': 96942, 'loss/train': 1.1000005006790161} 08/31/2021 06:46:19 - INFO - __main__ - Step 96944: {'lr': 0.00014248559772265195, 'samples': 18613248, 'steps': 96943, 'loss/train': 1.5422371625900269} 08/31/2021 06:46:19 - INFO - __main__ - Step 96945: {'lr': 0.0001424808068103985, 'samples': 18613440, 'steps': 96944, 'loss/train': 0.03717811033129692} 08/31/2021 06:46:20 - INFO - __main__ - Step 96946: {'lr': 0.00014247601594659148, 'samples': 18613632, 'steps': 96945, 'loss/train': 1.5280698537826538} 08/31/2021 06:46:20 - INFO - __main__ - Step 96947: {'lr': 0.00014247122513123315, 'samples': 18613824, 'steps': 96946, 'loss/train': 0.619288444519043} 08/31/2021 06:46:20 - INFO - __main__ - Step 96948: {'lr': 0.0001424664343643256, 'samples': 18614016, 'steps': 96947, 'loss/train': 0.693261981010437} 08/31/2021 06:46:22 - INFO - __main__ - Step 96949: {'lr': 0.00014246164364587103, 'samples': 18614208, 'steps': 96948, 'loss/train': 1.157747745513916} 08/31/2021 06:46:22 - INFO - __main__ - Step 96950: {'lr': 0.00014245685297587158, 'samples': 18614400, 'steps': 96949, 'loss/train': 1.4997398853302002} 08/31/2021 06:46:23 - INFO - __main__ - Step 96951: {'lr': 0.00014245206235432938, 'samples': 18614592, 'steps': 96950, 'loss/train': 1.1260162591934204} 08/31/2021 06:46:23 - INFO - __main__ - Step 96952: {'lr': 0.00014244727178124668, 'samples': 18614784, 'steps': 96951, 'loss/train': 0.8858009576797485} 08/31/2021 06:46:23 - INFO - __main__ - Step 96953: {'lr': 0.00014244248125662556, 'samples': 18614976, 'steps': 96952, 'loss/train': 1.360235571861267} 08/31/2021 06:46:26 - INFO - __main__ - Step 96954: {'lr': 0.0001424376907804682, 'samples': 18615168, 'steps': 96953, 'loss/train': 1.1489813327789307} 08/31/2021 06:46:26 - INFO - __main__ - Step 96955: {'lr': 0.00014243290035277685, 'samples': 18615360, 'steps': 96954, 'loss/train': 1.1874171495437622} 08/31/2021 06:46:26 - INFO - __main__ - Step 96956: {'lr': 0.00014242810997355346, 'samples': 18615552, 'steps': 96955, 'loss/train': 0.33956485986709595} 08/31/2021 06:46:27 - INFO - __main__ - Step 96957: {'lr': 0.00014242331964280032, 'samples': 18615744, 'steps': 96956, 'loss/train': 1.2466892004013062} 08/31/2021 06:46:27 - INFO - __main__ - Step 96958: {'lr': 0.0001424185293605196, 'samples': 18615936, 'steps': 96957, 'loss/train': 0.8240618705749512} 08/31/2021 06:46:27 - INFO - __main__ - Step 96959: {'lr': 0.00014241373912671337, 'samples': 18616128, 'steps': 96958, 'loss/train': 1.5968852043151855} 08/31/2021 06:46:29 - INFO - __main__ - Step 96960: {'lr': 0.0001424089489413839, 'samples': 18616320, 'steps': 96959, 'loss/train': 1.2407833337783813} 08/31/2021 06:46:29 - INFO - __main__ - Step 96961: {'lr': 0.00014240415880453324, 'samples': 18616512, 'steps': 96960, 'loss/train': 0.5202881097793579} 08/31/2021 06:46:30 - INFO - __main__ - Step 96962: {'lr': 0.00014239936871616367, 'samples': 18616704, 'steps': 96961, 'loss/train': 1.1667293310165405} 08/31/2021 06:46:30 - INFO - __main__ - Step 96963: {'lr': 0.00014239457867627726, 'samples': 18616896, 'steps': 96962, 'loss/train': 0.35861948132514954} 08/31/2021 06:46:30 - INFO - __main__ - Step 96964: {'lr': 0.00014238978868487618, 'samples': 18617088, 'steps': 96963, 'loss/train': 0.7805758118629456} 08/31/2021 06:46:32 - INFO - __main__ - Step 96965: {'lr': 0.0001423849987419626, 'samples': 18617280, 'steps': 96964, 'loss/train': 1.5859352350234985} 08/31/2021 06:46:32 - INFO - __main__ - Step 96966: {'lr': 0.00014238020884753868, 'samples': 18617472, 'steps': 96965, 'loss/train': 1.0731971263885498} 08/31/2021 06:46:33 - INFO - __main__ - Step 96967: {'lr': 0.0001423754190016066, 'samples': 18617664, 'steps': 96966, 'loss/train': 1.25876784324646} 08/31/2021 06:46:33 - INFO - __main__ - Step 96968: {'lr': 0.00014237062920416848, 'samples': 18617856, 'steps': 96967, 'loss/train': 1.2414711713790894} 08/31/2021 06:46:34 - INFO - __main__ - Step 96969: {'lr': 0.0001423658394552266, 'samples': 18618048, 'steps': 96968, 'loss/train': 2.156747817993164} 08/31/2021 06:46:35 - INFO - __main__ - Step 96970: {'lr': 0.00014236104975478292, 'samples': 18618240, 'steps': 96969, 'loss/train': 0.500935971736908} 08/31/2021 06:46:35 - INFO - __main__ - Step 96971: {'lr': 0.00014235626010283963, 'samples': 18618432, 'steps': 96970, 'loss/train': 1.02800714969635} 08/31/2021 06:46:36 - INFO - __main__ - Step 96972: {'lr': 0.000142351470499399, 'samples': 18618624, 'steps': 96971, 'loss/train': 1.1170763969421387} 08/31/2021 06:46:36 - INFO - __main__ - Step 96973: {'lr': 0.00014234668094446315, 'samples': 18618816, 'steps': 96972, 'loss/train': 1.20430588722229} 08/31/2021 06:46:36 - INFO - __main__ - Step 96974: {'lr': 0.00014234189143803421, 'samples': 18619008, 'steps': 96973, 'loss/train': 1.3899855613708496} 08/31/2021 06:46:38 - INFO - __main__ - Step 96975: {'lr': 0.00014233710198011435, 'samples': 18619200, 'steps': 96974, 'loss/train': 1.5046532154083252} 08/31/2021 06:46:38 - INFO - __main__ - Step 96976: {'lr': 0.00014233231257070573, 'samples': 18619392, 'steps': 96975, 'loss/train': 1.4876823425292969} 08/31/2021 06:46:39 - INFO - __main__ - Step 96977: {'lr': 0.00014232752320981053, 'samples': 18619584, 'steps': 96976, 'loss/train': 1.1668375730514526} 08/31/2021 06:46:39 - INFO - __main__ - Step 96978: {'lr': 0.00014232273389743085, 'samples': 18619776, 'steps': 96977, 'loss/train': 0.3883419334888458} 08/31/2021 06:46:40 - INFO - __main__ - Step 96979: {'lr': 0.0001423179446335689, 'samples': 18619968, 'steps': 96978, 'loss/train': 1.319286584854126} 08/31/2021 06:46:40 - INFO - __main__ - Step 96980: {'lr': 0.00014231315541822682, 'samples': 18620160, 'steps': 96979, 'loss/train': 1.942209243774414} 08/31/2021 06:46:41 - INFO - __main__ - Step 96981: {'lr': 0.00014230836625140676, 'samples': 18620352, 'steps': 96980, 'loss/train': 0.6951689720153809} 08/31/2021 06:46:42 - INFO - __main__ - Step 96982: {'lr': 0.00014230357713311098, 'samples': 18620544, 'steps': 96981, 'loss/train': 1.122607946395874} 08/31/2021 06:46:43 - INFO - __main__ - Step 96983: {'lr': 0.00014229878806334148, 'samples': 18620736, 'steps': 96982, 'loss/train': 0.7777488231658936} 08/31/2021 06:46:43 - INFO - __main__ - Step 96984: {'lr': 0.00014229399904210047, 'samples': 18620928, 'steps': 96983, 'loss/train': 0.4663466215133667} 08/31/2021 06:46:43 - INFO - __main__ - Step 96985: {'lr': 0.0001422892100693901, 'samples': 18621120, 'steps': 96984, 'loss/train': 0.9672496914863586} 08/31/2021 06:46:45 - INFO - __main__ - Step 96986: {'lr': 0.00014228442114521262, 'samples': 18621312, 'steps': 96985, 'loss/train': 1.6893128156661987} 08/31/2021 06:46:45 - INFO - __main__ - Step 96987: {'lr': 0.00014227963226957004, 'samples': 18621504, 'steps': 96986, 'loss/train': 1.7246989011764526} 08/31/2021 06:46:46 - INFO - __main__ - Step 96988: {'lr': 0.00014227484344246465, 'samples': 18621696, 'steps': 96987, 'loss/train': 1.280910611152649} 08/31/2021 06:46:46 - INFO - __main__ - Step 96989: {'lr': 0.00014227005466389852, 'samples': 18621888, 'steps': 96988, 'loss/train': 1.02302086353302} 08/31/2021 06:46:46 - INFO - __main__ - Step 96990: {'lr': 0.00014226526593387383, 'samples': 18622080, 'steps': 96989, 'loss/train': 1.5178771018981934} 08/31/2021 06:46:48 - INFO - __main__ - Step 96991: {'lr': 0.00014226047725239278, 'samples': 18622272, 'steps': 96990, 'loss/train': 2.1691722869873047} 08/31/2021 06:46:48 - INFO - __main__ - Step 96992: {'lr': 0.00014225568861945748, 'samples': 18622464, 'steps': 96991, 'loss/train': 1.017364501953125} 08/31/2021 06:46:49 - INFO - __main__ - Step 96993: {'lr': 0.00014225090003507014, 'samples': 18622656, 'steps': 96992, 'loss/train': 0.2451218217611313} 08/31/2021 06:46:49 - INFO - __main__ - Step 96994: {'lr': 0.00014224611149923284, 'samples': 18622848, 'steps': 96993, 'loss/train': 1.0078305006027222} 08/31/2021 06:46:49 - INFO - __main__ - Step 96995: {'lr': 0.00014224132301194776, 'samples': 18623040, 'steps': 96994, 'loss/train': 1.1418284177780151} 08/31/2021 06:46:51 - INFO - __main__ - Step 96996: {'lr': 0.00014223653457321722, 'samples': 18623232, 'steps': 96995, 'loss/train': 0.6174687743186951} 08/31/2021 06:46:51 - INFO - __main__ - Step 96997: {'lr': 0.00014223174618304313, 'samples': 18623424, 'steps': 96996, 'loss/train': 1.5352572202682495} 08/31/2021 06:46:52 - INFO - __main__ - Step 96998: {'lr': 0.00014222695784142775, 'samples': 18623616, 'steps': 96997, 'loss/train': 1.386254072189331} 08/31/2021 06:46:52 - INFO - __main__ - Step 96999: {'lr': 0.00014222216954837323, 'samples': 18623808, 'steps': 96998, 'loss/train': 0.6247411966323853} 08/31/2021 06:46:52 - INFO - __main__ - Step 97000: {'lr': 0.00014221738130388174, 'samples': 18624000, 'steps': 96999, 'loss/train': 1.4990907907485962} 08/31/2021 06:46:54 - INFO - __main__ - Step 97001: {'lr': 0.00014221259310795542, 'samples': 18624192, 'steps': 97000, 'loss/train': 0.8507382869720459} 08/31/2021 06:46:55 - INFO - __main__ - Step 97002: {'lr': 0.00014220780496059646, 'samples': 18624384, 'steps': 97001, 'loss/train': 1.0698802471160889} 08/31/2021 06:46:55 - INFO - __main__ - Step 97003: {'lr': 0.000142203016861807, 'samples': 18624576, 'steps': 97002, 'loss/train': 0.9746133685112} 08/31/2021 06:46:55 - INFO - __main__ - Step 97004: {'lr': 0.0001421982288115892, 'samples': 18624768, 'steps': 97003, 'loss/train': 1.608370065689087} 08/31/2021 06:46:56 - INFO - __main__ - Step 97005: {'lr': 0.0001421934408099452, 'samples': 18624960, 'steps': 97004, 'loss/train': 0.25171026587486267} 08/31/2021 06:46:58 - INFO - __main__ - Step 97006: {'lr': 0.0001421886528568772, 'samples': 18625152, 'steps': 97005, 'loss/train': 0.8477907180786133} 08/31/2021 06:46:58 - INFO - __main__ - Step 97007: {'lr': 0.00014218386495238727, 'samples': 18625344, 'steps': 97006, 'loss/train': 1.969077706336975} 08/31/2021 06:46:58 - INFO - __main__ - Step 97008: {'lr': 0.0001421790770964777, 'samples': 18625536, 'steps': 97007, 'loss/train': 1.614274024963379} 08/31/2021 06:46:59 - INFO - __main__ - Step 97009: {'lr': 0.00014217428928915064, 'samples': 18625728, 'steps': 97008, 'loss/train': 1.5648529529571533} 08/31/2021 06:46:59 - INFO - __main__ - Step 97010: {'lr': 0.0001421695015304081, 'samples': 18625920, 'steps': 97009, 'loss/train': 1.4235243797302246} 08/31/2021 06:46:59 - INFO - __main__ - Step 97011: {'lr': 0.00014216471382025225, 'samples': 18626112, 'steps': 97010, 'loss/train': 1.7396819591522217} 08/31/2021 06:47:01 - INFO - __main__ - Step 97012: {'lr': 0.00014215992615868538, 'samples': 18626304, 'steps': 97011, 'loss/train': 1.0326851606369019} 08/31/2021 06:47:01 - INFO - __main__ - Step 97013: {'lr': 0.00014215513854570958, 'samples': 18626496, 'steps': 97012, 'loss/train': 1.1199514865875244} 08/31/2021 06:47:02 - INFO - __main__ - Step 97014: {'lr': 0.000142150350981327, 'samples': 18626688, 'steps': 97013, 'loss/train': 1.226627230644226} 08/31/2021 06:47:02 - INFO - __main__ - Step 97015: {'lr': 0.0001421455634655398, 'samples': 18626880, 'steps': 97014, 'loss/train': 0.9001978039741516} 08/31/2021 06:47:02 - INFO - __main__ - Step 97016: {'lr': 0.00014214077599835018, 'samples': 18627072, 'steps': 97015, 'loss/train': 0.4369393587112427} 08/31/2021 06:47:04 - INFO - __main__ - Step 97017: {'lr': 0.00014213598857976023, 'samples': 18627264, 'steps': 97016, 'loss/train': 0.9747196435928345} 08/31/2021 06:47:04 - INFO - __main__ - Step 97018: {'lr': 0.00014213120120977214, 'samples': 18627456, 'steps': 97017, 'loss/train': 1.384846568107605} 08/31/2021 06:47:05 - INFO - __main__ - Step 97019: {'lr': 0.00014212641388838807, 'samples': 18627648, 'steps': 97018, 'loss/train': 1.0207688808441162} 08/31/2021 06:47:05 - INFO - __main__ - Step 97020: {'lr': 0.00014212162661561017, 'samples': 18627840, 'steps': 97019, 'loss/train': 1.1491918563842773} 08/31/2021 06:47:05 - INFO - __main__ - Step 97021: {'lr': 0.0001421168393914406, 'samples': 18628032, 'steps': 97020, 'loss/train': 1.3672080039978027} 08/31/2021 06:47:08 - INFO - __main__ - Step 97022: {'lr': 0.00014211205221588164, 'samples': 18628224, 'steps': 97021, 'loss/train': 1.4512444734573364} 08/31/2021 06:47:08 - INFO - __main__ - Step 97023: {'lr': 0.0001421072650889352, 'samples': 18628416, 'steps': 97022, 'loss/train': 0.871440589427948} 08/31/2021 06:47:09 - INFO - __main__ - Step 97024: {'lr': 0.00014210247801060355, 'samples': 18628608, 'steps': 97023, 'loss/train': 0.8274819850921631} 08/31/2021 06:47:09 - INFO - __main__ - Step 97025: {'lr': 0.00014209769098088887, 'samples': 18628800, 'steps': 97024, 'loss/train': 1.5809985399246216} 08/31/2021 06:47:09 - INFO - __main__ - Step 97026: {'lr': 0.00014209290399979334, 'samples': 18628992, 'steps': 97025, 'loss/train': 1.79579758644104} 08/31/2021 06:47:10 - INFO - __main__ - Step 97027: {'lr': 0.00014208811706731907, 'samples': 18629184, 'steps': 97026, 'loss/train': 0.624485969543457} 08/31/2021 06:47:11 - INFO - __main__ - Step 97028: {'lr': 0.0001420833301834682, 'samples': 18629376, 'steps': 97027, 'loss/train': 0.0891222432255745} 08/31/2021 06:47:12 - INFO - __main__ - Step 97029: {'lr': 0.00014207854334824294, 'samples': 18629568, 'steps': 97028, 'loss/train': 0.5265454053878784} 08/31/2021 06:47:12 - INFO - __main__ - Step 97030: {'lr': 0.00014207375656164538, 'samples': 18629760, 'steps': 97029, 'loss/train': 1.5711063146591187} 08/31/2021 06:47:12 - INFO - __main__ - Step 97031: {'lr': 0.0001420689698236778, 'samples': 18629952, 'steps': 97030, 'loss/train': 1.1277141571044922} 08/31/2021 06:47:13 - INFO - __main__ - Step 97032: {'lr': 0.00014206418313434218, 'samples': 18630144, 'steps': 97031, 'loss/train': 1.6313310861587524} 08/31/2021 06:47:14 - INFO - __main__ - Step 97033: {'lr': 0.00014205939649364094, 'samples': 18630336, 'steps': 97032, 'loss/train': 1.4402117729187012} 08/31/2021 06:47:15 - INFO - __main__ - Step 97034: {'lr': 0.00014205460990157596, 'samples': 18630528, 'steps': 97033, 'loss/train': 1.3407756090164185} 08/31/2021 06:47:15 - INFO - __main__ - Step 97035: {'lr': 0.00014204982335814948, 'samples': 18630720, 'steps': 97034, 'loss/train': 0.021390043199062347} 08/31/2021 06:47:16 - INFO - __main__ - Step 97036: {'lr': 0.00014204503686336372, 'samples': 18630912, 'steps': 97035, 'loss/train': 0.015212150290608406} 08/31/2021 06:47:16 - INFO - __main__ - Step 97037: {'lr': 0.0001420402504172208, 'samples': 18631104, 'steps': 97036, 'loss/train': 1.4220856428146362} 08/31/2021 06:47:16 - INFO - __main__ - Step 97038: {'lr': 0.00014203546401972284, 'samples': 18631296, 'steps': 97037, 'loss/train': 1.0326082706451416} 08/31/2021 06:47:17 - INFO - __main__ - Step 97039: {'lr': 0.00014203067767087208, 'samples': 18631488, 'steps': 97038, 'loss/train': 1.0161612033843994} 08/31/2021 06:47:19 - INFO - __main__ - Step 97040: {'lr': 0.00014202589137067058, 'samples': 18631680, 'steps': 97039, 'loss/train': 1.4236634969711304} 08/31/2021 06:47:19 - INFO - __main__ - Step 97041: {'lr': 0.0001420211051191206, 'samples': 18631872, 'steps': 97040, 'loss/train': 0.016798438504338264} 08/31/2021 06:47:19 - INFO - __main__ - Step 97042: {'lr': 0.00014201631891622418, 'samples': 18632064, 'steps': 97041, 'loss/train': 1.008452296257019} 08/31/2021 06:47:20 - INFO - __main__ - Step 97043: {'lr': 0.00014201153276198358, 'samples': 18632256, 'steps': 97042, 'loss/train': 1.0426095724105835} 08/31/2021 06:47:20 - INFO - __main__ - Step 97044: {'lr': 0.000142006746656401, 'samples': 18632448, 'steps': 97043, 'loss/train': 1.5939483642578125} 08/31/2021 06:47:20 - INFO - __main__ - Step 97045: {'lr': 0.00014200196059947846, 'samples': 18632640, 'steps': 97044, 'loss/train': 1.3978374004364014} 08/31/2021 06:47:22 - INFO - __main__ - Step 97046: {'lr': 0.00014199717459121813, 'samples': 18632832, 'steps': 97045, 'loss/train': 1.1475293636322021} 08/31/2021 06:47:23 - INFO - __main__ - Step 97047: {'lr': 0.00014199238863162224, 'samples': 18633024, 'steps': 97046, 'loss/train': 0.8313316702842712} 08/31/2021 06:47:23 - INFO - __main__ - Step 97048: {'lr': 0.00014198760272069285, 'samples': 18633216, 'steps': 97047, 'loss/train': 0.12925244867801666} 08/31/2021 06:47:23 - INFO - __main__ - Step 97049: {'lr': 0.00014198281685843224, 'samples': 18633408, 'steps': 97048, 'loss/train': 0.16717250645160675} 08/31/2021 06:47:24 - INFO - __main__ - Step 97050: {'lr': 0.00014197803104484247, 'samples': 18633600, 'steps': 97049, 'loss/train': 0.7730396389961243} 08/31/2021 06:47:25 - INFO - __main__ - Step 97051: {'lr': 0.00014197324527992576, 'samples': 18633792, 'steps': 97050, 'loss/train': 1.3722541332244873} 08/31/2021 06:47:26 - INFO - __main__ - Step 97052: {'lr': 0.0001419684595636842, 'samples': 18633984, 'steps': 97051, 'loss/train': 0.7985732555389404} 08/31/2021 06:47:26 - INFO - __main__ - Step 97053: {'lr': 0.00014196367389612003, 'samples': 18634176, 'steps': 97052, 'loss/train': 1.329866647720337} 08/31/2021 06:47:26 - INFO - __main__ - Step 97054: {'lr': 0.00014195888827723535, 'samples': 18634368, 'steps': 97053, 'loss/train': 0.688152015209198} 08/31/2021 06:47:27 - INFO - __main__ - Step 97055: {'lr': 0.0001419541027070324, 'samples': 18634560, 'steps': 97054, 'loss/train': 0.6481419801712036} 08/31/2021 06:47:28 - INFO - __main__ - Step 97056: {'lr': 0.00014194931718551317, 'samples': 18634752, 'steps': 97055, 'loss/train': 1.2769914865493774} 08/31/2021 06:47:29 - INFO - __main__ - Step 97057: {'lr': 0.00014194453171267996, 'samples': 18634944, 'steps': 97056, 'loss/train': 1.6246135234832764} 08/31/2021 06:47:29 - INFO - __main__ - Step 97058: {'lr': 0.00014193974628853482, 'samples': 18635136, 'steps': 97057, 'loss/train': 1.9707362651824951} 08/31/2021 06:47:29 - INFO - __main__ - Step 97059: {'lr': 0.00014193496091307998, 'samples': 18635328, 'steps': 97058, 'loss/train': 0.9345506429672241} 08/31/2021 06:47:30 - INFO - __main__ - Step 97060: {'lr': 0.0001419301755863176, 'samples': 18635520, 'steps': 97059, 'loss/train': 1.738848090171814} 08/31/2021 06:47:31 - INFO - __main__ - Step 97061: {'lr': 0.00014192539030824977, 'samples': 18635712, 'steps': 97060, 'loss/train': 1.5027320384979248} 08/31/2021 06:47:32 - INFO - __main__ - Step 97062: {'lr': 0.0001419206050788787, 'samples': 18635904, 'steps': 97061, 'loss/train': 1.1205874681472778} 08/31/2021 06:47:32 - INFO - __main__ - Step 97063: {'lr': 0.00014191581989820656, 'samples': 18636096, 'steps': 97062, 'loss/train': 0.15524935722351074} 08/31/2021 06:47:32 - INFO - __main__ - Step 97064: {'lr': 0.0001419110347662355, 'samples': 18636288, 'steps': 97063, 'loss/train': 1.8555519580841064} 08/31/2021 06:47:33 - INFO - __main__ - Step 97065: {'lr': 0.00014190624968296765, 'samples': 18636480, 'steps': 97064, 'loss/train': 1.2867714166641235} 08/31/2021 06:47:35 - INFO - __main__ - Step 97066: {'lr': 0.00014190146464840525, 'samples': 18636672, 'steps': 97065, 'loss/train': 0.8186080455780029} 08/31/2021 06:47:35 - INFO - __main__ - Step 97067: {'lr': 0.00014189667966255033, 'samples': 18636864, 'steps': 97066, 'loss/train': 1.2121566534042358} 08/31/2021 06:47:36 - INFO - __main__ - Step 97068: {'lr': 0.00014189189472540504, 'samples': 18637056, 'steps': 97067, 'loss/train': 0.781786322593689} 08/31/2021 06:47:36 - INFO - __main__ - Step 97069: {'lr': 0.00014188710983697162, 'samples': 18637248, 'steps': 97068, 'loss/train': 0.0727865993976593} 08/31/2021 06:47:36 - INFO - __main__ - Step 97070: {'lr': 0.0001418823249972522, 'samples': 18637440, 'steps': 97069, 'loss/train': 1.0750291347503662} 08/31/2021 06:47:37 - INFO - __main__ - Step 97071: {'lr': 0.00014187754020624893, 'samples': 18637632, 'steps': 97070, 'loss/train': 0.7571585774421692} 08/31/2021 06:47:38 - INFO - __main__ - Step 97072: {'lr': 0.000141872755463964, 'samples': 18637824, 'steps': 97071, 'loss/train': 0.9094876050949097} 08/31/2021 06:47:39 - INFO - __main__ - Step 97073: {'lr': 0.00014186797077039948, 'samples': 18638016, 'steps': 97072, 'loss/train': 0.8069265484809875} 08/31/2021 06:47:39 - INFO - __main__ - Step 97074: {'lr': 0.00014186318612555764, 'samples': 18638208, 'steps': 97073, 'loss/train': 1.0287487506866455} 08/31/2021 06:47:39 - INFO - __main__ - Step 97075: {'lr': 0.00014185840152944058, 'samples': 18638400, 'steps': 97074, 'loss/train': 1.079699993133545} 08/31/2021 06:47:40 - INFO - __main__ - Step 97076: {'lr': 0.00014185361698205052, 'samples': 18638592, 'steps': 97075, 'loss/train': 1.0330054759979248} 08/31/2021 06:47:41 - INFO - __main__ - Step 97077: {'lr': 0.00014184883248338946, 'samples': 18638784, 'steps': 97076, 'loss/train': 0.6367400884628296} 08/31/2021 06:47:42 - INFO - __main__ - Step 97078: {'lr': 0.00014184404803345963, 'samples': 18638976, 'steps': 97077, 'loss/train': 1.3967562913894653} 08/31/2021 06:47:42 - INFO - __main__ - Step 97079: {'lr': 0.00014183926363226323, 'samples': 18639168, 'steps': 97078, 'loss/train': 0.6802435517311096} 08/31/2021 06:47:42 - INFO - __main__ - Step 97080: {'lr': 0.0001418344792798024, 'samples': 18639360, 'steps': 97079, 'loss/train': 1.680348515510559} 08/31/2021 06:47:43 - INFO - __main__ - Step 97081: {'lr': 0.0001418296949760793, 'samples': 18639552, 'steps': 97080, 'loss/train': 1.3276162147521973} 08/31/2021 06:47:44 - INFO - __main__ - Step 97082: {'lr': 0.00014182491072109598, 'samples': 18639744, 'steps': 97081, 'loss/train': 0.36699092388153076} 08/31/2021 06:47:45 - INFO - __main__ - Step 97083: {'lr': 0.00014182012651485477, 'samples': 18639936, 'steps': 97082, 'loss/train': 0.8525152802467346} 08/31/2021 06:47:45 - INFO - __main__ - Step 97084: {'lr': 0.0001418153423573577, 'samples': 18640128, 'steps': 97083, 'loss/train': 0.8744995594024658} 08/31/2021 06:47:45 - INFO - __main__ - Step 97085: {'lr': 0.000141810558248607, 'samples': 18640320, 'steps': 97084, 'loss/train': 1.4158482551574707} 08/31/2021 06:47:46 - INFO - __main__ - Step 97086: {'lr': 0.0001418057741886048, 'samples': 18640512, 'steps': 97085, 'loss/train': 1.5040390491485596} 08/31/2021 06:47:47 - INFO - __main__ - Step 97087: {'lr': 0.0001418009901773532, 'samples': 18640704, 'steps': 97086, 'loss/train': 0.5745518803596497} 08/31/2021 06:47:48 - INFO - __main__ - Step 97088: {'lr': 0.00014179620621485446, 'samples': 18640896, 'steps': 97087, 'loss/train': 0.9939545392990112} 08/31/2021 06:47:48 - INFO - __main__ - Step 97089: {'lr': 0.00014179142230111064, 'samples': 18641088, 'steps': 97088, 'loss/train': 0.6497385501861572} 08/31/2021 06:47:49 - INFO - __main__ - Step 97090: {'lr': 0.00014178663843612404, 'samples': 18641280, 'steps': 97089, 'loss/train': 1.541619062423706} 08/31/2021 06:47:49 - INFO - __main__ - Step 97091: {'lr': 0.0001417818546198966, 'samples': 18641472, 'steps': 97090, 'loss/train': 1.479797124862671} 08/31/2021 06:47:49 - INFO - __main__ - Step 97092: {'lr': 0.0001417770708524306, 'samples': 18641664, 'steps': 97091, 'loss/train': 1.09062922000885} 08/31/2021 06:47:51 - INFO - __main__ - Step 97093: {'lr': 0.0001417722871337282, 'samples': 18641856, 'steps': 97092, 'loss/train': 1.9205979108810425} 08/31/2021 06:47:51 - INFO - __main__ - Step 97094: {'lr': 0.00014176750346379152, 'samples': 18642048, 'steps': 97093, 'loss/train': 0.9750161170959473} 08/31/2021 06:47:52 - INFO - __main__ - Step 97095: {'lr': 0.00014176271984262274, 'samples': 18642240, 'steps': 97094, 'loss/train': 1.5232633352279663} 08/31/2021 06:47:52 - INFO - __main__ - Step 97096: {'lr': 0.00014175793627022398, 'samples': 18642432, 'steps': 97095, 'loss/train': 0.7396429181098938} 08/31/2021 06:47:52 - INFO - __main__ - Step 97097: {'lr': 0.00014175315274659746, 'samples': 18642624, 'steps': 97096, 'loss/train': 1.3109211921691895} 08/31/2021 06:47:53 - INFO - __main__ - Step 97098: {'lr': 0.0001417483692717453, 'samples': 18642816, 'steps': 97097, 'loss/train': 1.5775036811828613} 08/31/2021 06:47:54 - INFO - __main__ - Step 97099: {'lr': 0.00014174358584566964, 'samples': 18643008, 'steps': 97098, 'loss/train': 1.0330780744552612} 08/31/2021 06:47:55 - INFO - __main__ - Step 97100: {'lr': 0.00014173880246837263, 'samples': 18643200, 'steps': 97099, 'loss/train': 0.9500693678855896} 08/31/2021 06:47:55 - INFO - __main__ - Step 97101: {'lr': 0.00014173401913985644, 'samples': 18643392, 'steps': 97100, 'loss/train': 1.5874338150024414} 08/31/2021 06:47:55 - INFO - __main__ - Step 97102: {'lr': 0.00014172923586012326, 'samples': 18643584, 'steps': 97101, 'loss/train': 1.08830726146698} 08/31/2021 06:47:56 - INFO - __main__ - Step 97103: {'lr': 0.00014172445262917532, 'samples': 18643776, 'steps': 97102, 'loss/train': 0.3547998070716858} 08/31/2021 06:47:57 - INFO - __main__ - Step 97104: {'lr': 0.0001417196694470146, 'samples': 18643968, 'steps': 97103, 'loss/train': 0.8396366238594055} 08/31/2021 06:47:58 - INFO - __main__ - Step 97105: {'lr': 0.00014171488631364328, 'samples': 18644160, 'steps': 97104, 'loss/train': 0.8439064025878906} 08/31/2021 06:47:58 - INFO - __main__ - Step 97106: {'lr': 0.00014171010322906356, 'samples': 18644352, 'steps': 97105, 'loss/train': 1.6163760423660278} 08/31/2021 06:47:59 - INFO - __main__ - Step 97107: {'lr': 0.0001417053201932776, 'samples': 18644544, 'steps': 97106, 'loss/train': 1.2641220092773438} 08/31/2021 06:47:59 - INFO - __main__ - Step 97108: {'lr': 0.00014170053720628757, 'samples': 18644736, 'steps': 97107, 'loss/train': 0.034206561744213104} 08/31/2021 06:48:00 - INFO - __main__ - Step 97109: {'lr': 0.00014169575426809558, 'samples': 18644928, 'steps': 97108, 'loss/train': 1.7907660007476807} 08/31/2021 06:48:01 - INFO - __main__ - Step 97110: {'lr': 0.00014169097137870383, 'samples': 18645120, 'steps': 97109, 'loss/train': 1.2525824308395386} 08/31/2021 06:48:01 - INFO - __main__ - Step 97111: {'lr': 0.00014168618853811443, 'samples': 18645312, 'steps': 97110, 'loss/train': 1.2917639017105103} 08/31/2021 06:48:02 - INFO - __main__ - Step 97112: {'lr': 0.0001416814057463296, 'samples': 18645504, 'steps': 97111, 'loss/train': 0.8655232787132263} 08/31/2021 06:48:02 - INFO - __main__ - Step 97113: {'lr': 0.00014167662300335144, 'samples': 18645696, 'steps': 97112, 'loss/train': 1.1512646675109863} 08/31/2021 06:48:02 - INFO - __main__ - Step 97114: {'lr': 0.00014167184030918213, 'samples': 18645888, 'steps': 97113, 'loss/train': 0.9906330704689026} 08/31/2021 06:48:04 - INFO - __main__ - Step 97115: {'lr': 0.00014166705766382383, 'samples': 18646080, 'steps': 97114, 'loss/train': 1.3784106969833374} 08/31/2021 06:48:04 - INFO - __main__ - Step 97116: {'lr': 0.00014166227506727863, 'samples': 18646272, 'steps': 97115, 'loss/train': 1.1966465711593628} 08/31/2021 06:48:05 - INFO - __main__ - Step 97117: {'lr': 0.00014165749251954888, 'samples': 18646464, 'steps': 97116, 'loss/train': 1.79700767993927} 08/31/2021 06:48:05 - INFO - __main__ - Step 97118: {'lr': 0.00014165271002063647, 'samples': 18646656, 'steps': 97117, 'loss/train': 1.5435136556625366} 08/31/2021 06:48:05 - INFO - __main__ - Step 97119: {'lr': 0.0001416479275705437, 'samples': 18646848, 'steps': 97118, 'loss/train': 1.65677809715271} 08/31/2021 06:48:08 - INFO - __main__ - Step 97120: {'lr': 0.00014164314516927268, 'samples': 18647040, 'steps': 97119, 'loss/train': 0.028907567262649536} 08/31/2021 06:48:08 - INFO - __main__ - Step 97121: {'lr': 0.00014163836281682563, 'samples': 18647232, 'steps': 97120, 'loss/train': 1.1368740797042847} 08/31/2021 06:48:09 - INFO - __main__ - Step 97122: {'lr': 0.00014163358051320462, 'samples': 18647424, 'steps': 97121, 'loss/train': 0.12337995320558548} 08/31/2021 06:48:09 - INFO - __main__ - Step 97123: {'lr': 0.00014162879825841185, 'samples': 18647616, 'steps': 97122, 'loss/train': 1.3547542095184326} 08/31/2021 06:48:09 - INFO - __main__ - Step 97124: {'lr': 0.00014162401605244946, 'samples': 18647808, 'steps': 97123, 'loss/train': 1.66285240650177} 08/31/2021 06:48:11 - INFO - __main__ - Step 97125: {'lr': 0.00014161923389531967, 'samples': 18648000, 'steps': 97124, 'loss/train': 0.9106276035308838} 08/31/2021 06:48:11 - INFO - __main__ - Step 97126: {'lr': 0.00014161445178702454, 'samples': 18648192, 'steps': 97125, 'loss/train': 1.298918604850769} 08/31/2021 06:48:12 - INFO - __main__ - Step 97127: {'lr': 0.00014160966972756624, 'samples': 18648384, 'steps': 97126, 'loss/train': 1.2919268608093262} 08/31/2021 06:48:12 - INFO - __main__ - Step 97128: {'lr': 0.000141604887716947, 'samples': 18648576, 'steps': 97127, 'loss/train': 0.9959275722503662} 08/31/2021 06:48:12 - INFO - __main__ - Step 97129: {'lr': 0.00014160010575516892, 'samples': 18648768, 'steps': 97128, 'loss/train': 1.0822914838790894} 08/31/2021 06:48:14 - INFO - __main__ - Step 97130: {'lr': 0.00014159532384223423, 'samples': 18648960, 'steps': 97129, 'loss/train': 0.8669250011444092} 08/31/2021 06:48:14 - INFO - __main__ - Step 97131: {'lr': 0.0001415905419781449, 'samples': 18649152, 'steps': 97130, 'loss/train': 1.1432180404663086} 08/31/2021 06:48:15 - INFO - __main__ - Step 97132: {'lr': 0.00014158576016290325, 'samples': 18649344, 'steps': 97131, 'loss/train': 0.31115493178367615} 08/31/2021 06:48:15 - INFO - __main__ - Step 97133: {'lr': 0.00014158097839651136, 'samples': 18649536, 'steps': 97132, 'loss/train': 1.4273731708526611} 08/31/2021 06:48:15 - INFO - __main__ - Step 97134: {'lr': 0.00014157619667897142, 'samples': 18649728, 'steps': 97133, 'loss/train': 1.277543067932129} 08/31/2021 06:48:16 - INFO - __main__ - Step 97135: {'lr': 0.00014157141501028553, 'samples': 18649920, 'steps': 97134, 'loss/train': 1.2172317504882812} 08/31/2021 06:48:17 - INFO - __main__ - Step 97136: {'lr': 0.00014156663339045595, 'samples': 18650112, 'steps': 97135, 'loss/train': 1.8353087902069092} 08/31/2021 06:48:18 - INFO - __main__ - Step 97137: {'lr': 0.00014156185181948472, 'samples': 18650304, 'steps': 97136, 'loss/train': 1.1656290292739868} 08/31/2021 06:48:18 - INFO - __main__ - Step 97138: {'lr': 0.00014155707029737407, 'samples': 18650496, 'steps': 97137, 'loss/train': 1.5382823944091797} 08/31/2021 06:48:18 - INFO - __main__ - Step 97139: {'lr': 0.00014155228882412613, 'samples': 18650688, 'steps': 97138, 'loss/train': 0.8123917579650879} 08/31/2021 06:48:19 - INFO - __main__ - Step 97140: {'lr': 0.00014154750739974305, 'samples': 18650880, 'steps': 97139, 'loss/train': 1.2678415775299072} 08/31/2021 06:48:21 - INFO - __main__ - Step 97141: {'lr': 0.000141542726024227, 'samples': 18651072, 'steps': 97140, 'loss/train': 1.5356327295303345} 08/31/2021 06:48:21 - INFO - __main__ - Step 97142: {'lr': 0.00014153794469758013, 'samples': 18651264, 'steps': 97141, 'loss/train': 0.4267776906490326} 08/31/2021 06:48:21 - INFO - __main__ - Step 97143: {'lr': 0.00014153316341980465, 'samples': 18651456, 'steps': 97142, 'loss/train': 1.7734787464141846} 08/31/2021 06:48:22 - INFO - __main__ - Step 97144: {'lr': 0.00014152838219090257, 'samples': 18651648, 'steps': 97143, 'loss/train': 1.3491953611373901} 08/31/2021 06:48:22 - INFO - __main__ - Step 97145: {'lr': 0.00014152360101087614, 'samples': 18651840, 'steps': 97144, 'loss/train': 0.9239640235900879} 08/31/2021 06:48:24 - INFO - __main__ - Step 97146: {'lr': 0.00014151881987972751, 'samples': 18652032, 'steps': 97145, 'loss/train': 1.2358993291854858} 08/31/2021 06:48:24 - INFO - __main__ - Step 97147: {'lr': 0.00014151403879745882, 'samples': 18652224, 'steps': 97146, 'loss/train': 1.665980339050293} 08/31/2021 06:48:24 - INFO - __main__ - Step 97148: {'lr': 0.0001415092577640722, 'samples': 18652416, 'steps': 97147, 'loss/train': 1.1548861265182495} 08/31/2021 06:48:25 - INFO - __main__ - Step 97149: {'lr': 0.00014150447677956988, 'samples': 18652608, 'steps': 97148, 'loss/train': 1.0682172775268555} 08/31/2021 06:48:25 - INFO - __main__ - Step 97150: {'lr': 0.00014149969584395394, 'samples': 18652800, 'steps': 97149, 'loss/train': 0.9133480787277222} 08/31/2021 06:48:27 - INFO - __main__ - Step 97151: {'lr': 0.00014149491495722656, 'samples': 18652992, 'steps': 97150, 'loss/train': 0.7554336786270142} 08/31/2021 06:48:27 - INFO - __main__ - Step 97152: {'lr': 0.0001414901341193899, 'samples': 18653184, 'steps': 97151, 'loss/train': 0.8037121295928955} 08/31/2021 06:48:28 - INFO - __main__ - Step 97153: {'lr': 0.00014148535333044612, 'samples': 18653376, 'steps': 97152, 'loss/train': 1.2341625690460205} 08/31/2021 06:48:28 - INFO - __main__ - Step 97154: {'lr': 0.00014148057259039736, 'samples': 18653568, 'steps': 97153, 'loss/train': 1.1541922092437744} 08/31/2021 06:48:28 - INFO - __main__ - Step 97155: {'lr': 0.0001414757918992458, 'samples': 18653760, 'steps': 97154, 'loss/train': 1.2078685760498047} 08/31/2021 06:48:29 - INFO - __main__ - Step 97156: {'lr': 0.00014147101125699355, 'samples': 18653952, 'steps': 97155, 'loss/train': 1.464938759803772} 08/31/2021 06:48:30 - INFO - __main__ - Step 97157: {'lr': 0.0001414662306636429, 'samples': 18654144, 'steps': 97156, 'loss/train': 0.45425230264663696} 08/31/2021 06:48:31 - INFO - __main__ - Step 97158: {'lr': 0.00014146145011919575, 'samples': 18654336, 'steps': 97157, 'loss/train': 0.9826258420944214} 08/31/2021 06:48:31 - INFO - __main__ - Step 97159: {'lr': 0.00014145666962365444, 'samples': 18654528, 'steps': 97158, 'loss/train': 1.125268816947937} 08/31/2021 06:48:31 - INFO - __main__ - Step 97160: {'lr': 0.00014145188917702106, 'samples': 18654720, 'steps': 97159, 'loss/train': 2.1417579650878906} 08/31/2021 06:48:33 - INFO - __main__ - Step 97161: {'lr': 0.0001414471087792978, 'samples': 18654912, 'steps': 97160, 'loss/train': 1.570792555809021} 08/31/2021 06:48:33 - INFO - __main__ - Step 97162: {'lr': 0.00014144232843048683, 'samples': 18655104, 'steps': 97161, 'loss/train': 0.5718932747840881} 08/31/2021 06:48:34 - INFO - __main__ - Step 97163: {'lr': 0.00014143754813059021, 'samples': 18655296, 'steps': 97162, 'loss/train': 0.3109131157398224} 08/31/2021 06:48:34 - INFO - __main__ - Step 97164: {'lr': 0.00014143276787961017, 'samples': 18655488, 'steps': 97163, 'loss/train': 1.5636423826217651} 08/31/2021 06:48:34 - INFO - __main__ - Step 97165: {'lr': 0.00014142798767754886, 'samples': 18655680, 'steps': 97164, 'loss/train': 1.24043607711792} 08/31/2021 06:48:35 - INFO - __main__ - Step 97166: {'lr': 0.00014142320752440842, 'samples': 18655872, 'steps': 97165, 'loss/train': 1.4984791278839111} 08/31/2021 06:48:36 - INFO - __main__ - Step 97167: {'lr': 0.00014141842742019102, 'samples': 18656064, 'steps': 97166, 'loss/train': 1.3395555019378662} 08/31/2021 06:48:37 - INFO - __main__ - Step 97168: {'lr': 0.00014141364736489878, 'samples': 18656256, 'steps': 97167, 'loss/train': 0.8083519339561462} 08/31/2021 06:48:37 - INFO - __main__ - Step 97169: {'lr': 0.00014140886735853386, 'samples': 18656448, 'steps': 97168, 'loss/train': 1.5100646018981934} 08/31/2021 06:48:37 - INFO - __main__ - Step 97170: {'lr': 0.0001414040874010986, 'samples': 18656640, 'steps': 97169, 'loss/train': 1.6225221157073975} 08/31/2021 06:48:38 - INFO - __main__ - Step 97171: {'lr': 0.00014139930749259484, 'samples': 18656832, 'steps': 97170, 'loss/train': 1.2038311958312988} 08/31/2021 06:48:40 - INFO - __main__ - Step 97172: {'lr': 0.00014139452763302485, 'samples': 18657024, 'steps': 97171, 'loss/train': 1.19761323928833} 08/31/2021 06:48:40 - INFO - __main__ - Step 97173: {'lr': 0.00014138974782239083, 'samples': 18657216, 'steps': 97172, 'loss/train': 0.906607985496521} 08/31/2021 06:48:41 - INFO - __main__ - Step 97174: {'lr': 0.0001413849680606949, 'samples': 18657408, 'steps': 97173, 'loss/train': 1.0689729452133179} 08/31/2021 06:48:41 - INFO - __main__ - Step 97175: {'lr': 0.00014138018834793925, 'samples': 18657600, 'steps': 97174, 'loss/train': 0.4574912190437317} 08/31/2021 06:48:41 - INFO - __main__ - Step 97176: {'lr': 0.00014137540868412602, 'samples': 18657792, 'steps': 97175, 'loss/train': 0.8254364132881165} 08/31/2021 06:48:43 - INFO - __main__ - Step 97177: {'lr': 0.00014137062906925733, 'samples': 18657984, 'steps': 97176, 'loss/train': 1.3392081260681152} 08/31/2021 06:48:43 - INFO - __main__ - Step 97178: {'lr': 0.00014136584950333536, 'samples': 18658176, 'steps': 97177, 'loss/train': 1.117923378944397} 08/31/2021 06:48:44 - INFO - __main__ - Step 97179: {'lr': 0.00014136106998636228, 'samples': 18658368, 'steps': 97178, 'loss/train': 1.2464147806167603} 08/31/2021 06:48:44 - INFO - __main__ - Step 97180: {'lr': 0.0001413562905183402, 'samples': 18658560, 'steps': 97179, 'loss/train': 1.0692322254180908} 08/31/2021 06:48:44 - INFO - __main__ - Step 97181: {'lr': 0.0001413515110992713, 'samples': 18658752, 'steps': 97180, 'loss/train': 0.7830687761306763} 08/31/2021 06:48:46 - INFO - __main__ - Step 97182: {'lr': 0.00014134673172915777, 'samples': 18658944, 'steps': 97181, 'loss/train': 2.1204094886779785} 08/31/2021 06:48:46 - INFO - __main__ - Step 97183: {'lr': 0.00014134195240800168, 'samples': 18659136, 'steps': 97182, 'loss/train': 1.7624861001968384} 08/31/2021 06:48:47 - INFO - __main__ - Step 97184: {'lr': 0.00014133717313580534, 'samples': 18659328, 'steps': 97183, 'loss/train': 1.3821213245391846} 08/31/2021 06:48:47 - INFO - __main__ - Step 97185: {'lr': 0.00014133239391257076, 'samples': 18659520, 'steps': 97184, 'loss/train': 1.1042617559432983} 08/31/2021 06:48:48 - INFO - __main__ - Step 97186: {'lr': 0.00014132761473830002, 'samples': 18659712, 'steps': 97185, 'loss/train': 0.06008995324373245} 08/31/2021 06:48:49 - INFO - __main__ - Step 97187: {'lr': 0.00014132283561299548, 'samples': 18659904, 'steps': 97186, 'loss/train': 1.2086998224258423} 08/31/2021 06:48:49 - INFO - __main__ - Step 97188: {'lr': 0.00014131805653665912, 'samples': 18660096, 'steps': 97187, 'loss/train': 1.3501676321029663} 08/31/2021 06:48:50 - INFO - __main__ - Step 97189: {'lr': 0.0001413132775092932, 'samples': 18660288, 'steps': 97188, 'loss/train': 1.2154878377914429} 08/31/2021 06:48:50 - INFO - __main__ - Step 97190: {'lr': 0.00014130849853089984, 'samples': 18660480, 'steps': 97189, 'loss/train': 1.1453137397766113} 08/31/2021 06:48:51 - INFO - __main__ - Step 97191: {'lr': 0.00014130371960148117, 'samples': 18660672, 'steps': 97190, 'loss/train': 0.6841074228286743} 08/31/2021 06:48:52 - INFO - __main__ - Step 97192: {'lr': 0.00014129894072103938, 'samples': 18660864, 'steps': 97191, 'loss/train': 0.8556108474731445} 08/31/2021 06:48:52 - INFO - __main__ - Step 97193: {'lr': 0.00014129416188957662, 'samples': 18661056, 'steps': 97192, 'loss/train': 1.3223215341567993} 08/31/2021 06:48:53 - INFO - __main__ - Step 97194: {'lr': 0.000141289383107095, 'samples': 18661248, 'steps': 97193, 'loss/train': 0.5334323644638062} 08/31/2021 06:48:53 - INFO - __main__ - Step 97195: {'lr': 0.00014128460437359675, 'samples': 18661440, 'steps': 97194, 'loss/train': 0.8156594038009644} 08/31/2021 06:48:53 - INFO - __main__ - Step 97196: {'lr': 0.00014127982568908393, 'samples': 18661632, 'steps': 97195, 'loss/train': 0.5007458329200745} 08/31/2021 06:48:54 - INFO - __main__ - Step 97197: {'lr': 0.0001412750470535589, 'samples': 18661824, 'steps': 97196, 'loss/train': 0.9282237887382507} 08/31/2021 06:48:56 - INFO - __main__ - Step 97198: {'lr': 0.00014127026846702352, 'samples': 18662016, 'steps': 97197, 'loss/train': 1.140044093132019} 08/31/2021 06:48:56 - INFO - __main__ - Step 97199: {'lr': 0.00014126548992948008, 'samples': 18662208, 'steps': 97198, 'loss/train': 1.2125704288482666} 08/31/2021 06:48:56 - INFO - __main__ - Step 97200: {'lr': 0.00014126071144093076, 'samples': 18662400, 'steps': 97199, 'loss/train': 0.9093201160430908} 08/31/2021 06:48:57 - INFO - __main__ - Step 97201: {'lr': 0.00014125593300137764, 'samples': 18662592, 'steps': 97200, 'loss/train': 1.3137544393539429} 08/31/2021 06:48:57 - INFO - __main__ - Step 97202: {'lr': 0.00014125115461082293, 'samples': 18662784, 'steps': 97201, 'loss/train': 1.336968183517456} 08/31/2021 06:48:57 - INFO - __main__ - Step 97203: {'lr': 0.00014124637626926882, 'samples': 18662976, 'steps': 97202, 'loss/train': 1.3259540796279907} 08/31/2021 06:48:59 - INFO - __main__ - Step 97204: {'lr': 0.00014124159797671736, 'samples': 18663168, 'steps': 97203, 'loss/train': 1.5049251317977905} 08/31/2021 06:48:59 - INFO - __main__ - Step 97205: {'lr': 0.0001412368197331708, 'samples': 18663360, 'steps': 97204, 'loss/train': 1.1874252557754517} 08/31/2021 06:49:00 - INFO - __main__ - Step 97206: {'lr': 0.00014123204153863124, 'samples': 18663552, 'steps': 97205, 'loss/train': 1.0609140396118164} 08/31/2021 06:49:00 - INFO - __main__ - Step 97207: {'lr': 0.00014122726339310082, 'samples': 18663744, 'steps': 97206, 'loss/train': 1.217552661895752} 08/31/2021 06:49:00 - INFO - __main__ - Step 97208: {'lr': 0.0001412224852965817, 'samples': 18663936, 'steps': 97207, 'loss/train': 1.1605249643325806} 08/31/2021 06:49:02 - INFO - __main__ - Step 97209: {'lr': 0.00014121770724907613, 'samples': 18664128, 'steps': 97208, 'loss/train': 0.5895033478736877} 08/31/2021 06:49:02 - INFO - __main__ - Step 97210: {'lr': 0.0001412129292505861, 'samples': 18664320, 'steps': 97209, 'loss/train': 0.976361870765686} 08/31/2021 06:49:03 - INFO - __main__ - Step 97211: {'lr': 0.00014120815130111398, 'samples': 18664512, 'steps': 97210, 'loss/train': 0.8271676301956177} 08/31/2021 06:49:03 - INFO - __main__ - Step 97212: {'lr': 0.0001412033734006617, 'samples': 18664704, 'steps': 97211, 'loss/train': 1.4302290678024292} 08/31/2021 06:49:03 - INFO - __main__ - Step 97213: {'lr': 0.00014119859554923147, 'samples': 18664896, 'steps': 97212, 'loss/train': 0.4975920021533966} 08/31/2021 06:49:05 - INFO - __main__ - Step 97214: {'lr': 0.00014119381774682548, 'samples': 18665088, 'steps': 97213, 'loss/train': 1.4840044975280762} 08/31/2021 06:49:05 - INFO - __main__ - Step 97215: {'lr': 0.0001411890399934459, 'samples': 18665280, 'steps': 97214, 'loss/train': 0.5969314575195312} 08/31/2021 06:49:06 - INFO - __main__ - Step 97216: {'lr': 0.00014118426228909486, 'samples': 18665472, 'steps': 97215, 'loss/train': 1.1246639490127563} 08/31/2021 06:49:06 - INFO - __main__ - Step 97217: {'lr': 0.0001411794846337745, 'samples': 18665664, 'steps': 97216, 'loss/train': 1.2506705522537231} 08/31/2021 06:49:06 - INFO - __main__ - Step 97218: {'lr': 0.00014117470702748697, 'samples': 18665856, 'steps': 97217, 'loss/train': 0.02354338765144348} 08/31/2021 06:49:08 - INFO - __main__ - Step 97219: {'lr': 0.00014116992947023444, 'samples': 18666048, 'steps': 97218, 'loss/train': 0.8973419070243835} 08/31/2021 06:49:09 - INFO - __main__ - Step 97220: {'lr': 0.0001411651519620191, 'samples': 18666240, 'steps': 97219, 'loss/train': 0.766959011554718} 08/31/2021 06:49:09 - INFO - __main__ - Step 97221: {'lr': 0.00014116037450284303, 'samples': 18666432, 'steps': 97220, 'loss/train': 0.9010717272758484} 08/31/2021 06:49:09 - INFO - __main__ - Step 97222: {'lr': 0.00014115559709270843, 'samples': 18666624, 'steps': 97221, 'loss/train': 0.7227452397346497} 08/31/2021 06:49:10 - INFO - __main__ - Step 97223: {'lr': 0.00014115081973161743, 'samples': 18666816, 'steps': 97222, 'loss/train': 0.7996641993522644} 08/31/2021 06:49:10 - INFO - __main__ - Step 97224: {'lr': 0.00014114604241957226, 'samples': 18667008, 'steps': 97223, 'loss/train': 0.028966769576072693} 08/31/2021 06:49:12 - INFO - __main__ - Step 97225: {'lr': 0.00014114126515657493, 'samples': 18667200, 'steps': 97224, 'loss/train': 2.013918876647949} 08/31/2021 06:49:12 - INFO - __main__ - Step 97226: {'lr': 0.00014113648794262767, 'samples': 18667392, 'steps': 97225, 'loss/train': 0.7560201287269592} 08/31/2021 06:49:13 - INFO - __main__ - Step 97227: {'lr': 0.00014113171077773267, 'samples': 18667584, 'steps': 97226, 'loss/train': 1.6009595394134521} 08/31/2021 06:49:13 - INFO - __main__ - Step 97228: {'lr': 0.00014112693366189196, 'samples': 18667776, 'steps': 97227, 'loss/train': 0.5983113050460815} 08/31/2021 06:49:13 - INFO - __main__ - Step 97229: {'lr': 0.00014112215659510782, 'samples': 18667968, 'steps': 97228, 'loss/train': 1.046415090560913} 08/31/2021 06:49:15 - INFO - __main__ - Step 97230: {'lr': 0.00014111737957738237, 'samples': 18668160, 'steps': 97229, 'loss/train': 0.2616778314113617} 08/31/2021 06:49:16 - INFO - __main__ - Step 97231: {'lr': 0.00014111260260871771, 'samples': 18668352, 'steps': 97230, 'loss/train': 1.352610468864441} 08/31/2021 06:49:16 - INFO - __main__ - Step 97232: {'lr': 0.00014110782568911605, 'samples': 18668544, 'steps': 97231, 'loss/train': 1.3411128520965576} 08/31/2021 06:49:16 - INFO - __main__ - Step 97233: {'lr': 0.00014110304881857956, 'samples': 18668736, 'steps': 97232, 'loss/train': 0.4931052327156067} 08/31/2021 06:49:17 - INFO - __main__ - Step 97234: {'lr': 0.00014109827199711028, 'samples': 18668928, 'steps': 97233, 'loss/train': 1.735377550125122} 08/31/2021 06:49:18 - INFO - __main__ - Step 97235: {'lr': 0.00014109349522471048, 'samples': 18669120, 'steps': 97234, 'loss/train': 0.7537398338317871} 08/31/2021 06:49:19 - INFO - __main__ - Step 97236: {'lr': 0.00014108871850138227, 'samples': 18669312, 'steps': 97235, 'loss/train': 0.8512526750564575} 08/31/2021 06:49:19 - INFO - __main__ - Step 97237: {'lr': 0.0001410839418271278, 'samples': 18669504, 'steps': 97236, 'loss/train': 1.3104020357131958} 08/31/2021 06:49:19 - INFO - __main__ - Step 97238: {'lr': 0.00014107916520194932, 'samples': 18669696, 'steps': 97237, 'loss/train': 0.9547712206840515} 08/31/2021 06:49:20 - INFO - __main__ - Step 97239: {'lr': 0.00014107438862584883, 'samples': 18669888, 'steps': 97238, 'loss/train': 0.796778678894043} 08/31/2021 06:49:21 - INFO - __main__ - Step 97240: {'lr': 0.00014106961209882845, 'samples': 18670080, 'steps': 97239, 'loss/train': 1.4843977689743042} 08/31/2021 06:49:22 - INFO - __main__ - Step 97241: {'lr': 0.0001410648356208905, 'samples': 18670272, 'steps': 97240, 'loss/train': 0.3215990364551544} 08/31/2021 06:49:22 - INFO - __main__ - Step 97242: {'lr': 0.00014106005919203702, 'samples': 18670464, 'steps': 97241, 'loss/train': 1.706813931465149} 08/31/2021 06:49:23 - INFO - __main__ - Step 97243: {'lr': 0.0001410552828122702, 'samples': 18670656, 'steps': 97242, 'loss/train': 0.9847044348716736} 08/31/2021 06:49:23 - INFO - __main__ - Step 97244: {'lr': 0.0001410505064815922, 'samples': 18670848, 'steps': 97243, 'loss/train': 1.3626375198364258} 08/31/2021 06:49:25 - INFO - __main__ - Step 97245: {'lr': 0.00014104573020000516, 'samples': 18671040, 'steps': 97244, 'loss/train': 0.9131843447685242} 08/31/2021 06:49:25 - INFO - __main__ - Step 97246: {'lr': 0.0001410409539675112, 'samples': 18671232, 'steps': 97245, 'loss/train': 1.8625861406326294} 08/31/2021 06:49:26 - INFO - __main__ - Step 97247: {'lr': 0.00014103617778411253, 'samples': 18671424, 'steps': 97246, 'loss/train': 0.13313864171504974} 08/31/2021 06:49:26 - INFO - __main__ - Step 97248: {'lr': 0.00014103140164981132, 'samples': 18671616, 'steps': 97247, 'loss/train': 1.2124239206314087} 08/31/2021 06:49:26 - INFO - __main__ - Step 97249: {'lr': 0.0001410266255646096, 'samples': 18671808, 'steps': 97248, 'loss/train': 1.3264390230178833} 08/31/2021 06:49:27 - INFO - __main__ - Step 97250: {'lr': 0.00014102184952850965, 'samples': 18672000, 'steps': 97249, 'loss/train': 1.4195855855941772} 08/31/2021 06:49:28 - INFO - __main__ - Step 97251: {'lr': 0.00014101707354151365, 'samples': 18672192, 'steps': 97250, 'loss/train': 0.8834394216537476} 08/31/2021 06:49:29 - INFO - __main__ - Step 97252: {'lr': 0.0001410122976036236, 'samples': 18672384, 'steps': 97251, 'loss/train': 0.8887166380882263} 08/31/2021 06:49:29 - INFO - __main__ - Step 97253: {'lr': 0.00014100752171484172, 'samples': 18672576, 'steps': 97252, 'loss/train': 1.0159436464309692} 08/31/2021 06:49:30 - INFO - __main__ - Step 97254: {'lr': 0.00014100274587517016, 'samples': 18672768, 'steps': 97253, 'loss/train': 2.498384714126587} 08/31/2021 06:49:30 - INFO - __main__ - Step 97255: {'lr': 0.00014099797008461108, 'samples': 18672960, 'steps': 97254, 'loss/train': 1.4158021211624146} 08/31/2021 06:49:32 - INFO - __main__ - Step 97256: {'lr': 0.00014099319434316665, 'samples': 18673152, 'steps': 97255, 'loss/train': 1.1817564964294434} 08/31/2021 06:49:32 - INFO - __main__ - Step 97257: {'lr': 0.00014098841865083897, 'samples': 18673344, 'steps': 97256, 'loss/train': 0.9991567730903625} 08/31/2021 06:49:32 - INFO - __main__ - Step 97258: {'lr': 0.00014098364300763026, 'samples': 18673536, 'steps': 97257, 'loss/train': 0.4548174738883972} 08/31/2021 06:49:33 - INFO - __main__ - Step 97259: {'lr': 0.0001409788674135426, 'samples': 18673728, 'steps': 97258, 'loss/train': 1.2757362127304077} 08/31/2021 06:49:33 - INFO - __main__ - Step 97260: {'lr': 0.00014097409186857824, 'samples': 18673920, 'steps': 97259, 'loss/train': 1.0172078609466553} 08/31/2021 06:49:35 - INFO - __main__ - Step 97261: {'lr': 0.00014096931637273922, 'samples': 18674112, 'steps': 97260, 'loss/train': 0.04738546162843704} 08/31/2021 06:49:35 - INFO - __main__ - Step 97262: {'lr': 0.00014096454092602775, 'samples': 18674304, 'steps': 97261, 'loss/train': 1.1690000295639038} 08/31/2021 06:49:36 - INFO - __main__ - Step 97263: {'lr': 0.000140959765528446, 'samples': 18674496, 'steps': 97262, 'loss/train': 1.2346805334091187} 08/31/2021 06:49:36 - INFO - __main__ - Step 97264: {'lr': 0.0001409549901799962, 'samples': 18674688, 'steps': 97263, 'loss/train': 0.8374868035316467} 08/31/2021 06:49:36 - INFO - __main__ - Step 97265: {'lr': 0.00014095021488068026, 'samples': 18674880, 'steps': 97264, 'loss/train': 1.0831491947174072} 08/31/2021 06:49:37 - INFO - __main__ - Step 97266: {'lr': 0.0001409454396305005, 'samples': 18675072, 'steps': 97265, 'loss/train': 0.8977838158607483} 08/31/2021 06:49:38 - INFO - __main__ - Step 97267: {'lr': 0.00014094066442945903, 'samples': 18675264, 'steps': 97266, 'loss/train': 1.183976650238037} 08/31/2021 06:49:39 - INFO - __main__ - Step 97268: {'lr': 0.00014093588927755802, 'samples': 18675456, 'steps': 97267, 'loss/train': 1.4251893758773804} 08/31/2021 06:49:39 - INFO - __main__ - Step 97269: {'lr': 0.0001409311141747996, 'samples': 18675648, 'steps': 97268, 'loss/train': 0.9956810474395752} 08/31/2021 06:49:39 - INFO - __main__ - Step 97270: {'lr': 0.00014092633912118595, 'samples': 18675840, 'steps': 97269, 'loss/train': 1.3599525690078735} 08/31/2021 06:49:40 - INFO - __main__ - Step 97271: {'lr': 0.0001409215641167192, 'samples': 18676032, 'steps': 97270, 'loss/train': 1.1506755352020264} 08/31/2021 06:49:41 - INFO - __main__ - Step 97272: {'lr': 0.00014091678916140153, 'samples': 18676224, 'steps': 97271, 'loss/train': 0.6821445822715759} 08/31/2021 06:49:42 - INFO - __main__ - Step 97273: {'lr': 0.00014091201425523505, 'samples': 18676416, 'steps': 97272, 'loss/train': 0.9070487022399902} 08/31/2021 06:49:42 - INFO - __main__ - Step 97274: {'lr': 0.00014090723939822196, 'samples': 18676608, 'steps': 97273, 'loss/train': 1.5023871660232544} 08/31/2021 06:49:42 - INFO - __main__ - Step 97275: {'lr': 0.00014090246459036435, 'samples': 18676800, 'steps': 97274, 'loss/train': 1.3155548572540283} 08/31/2021 06:49:43 - INFO - __main__ - Step 97276: {'lr': 0.00014089768983166444, 'samples': 18676992, 'steps': 97275, 'loss/train': 1.3309763669967651} 08/31/2021 06:49:44 - INFO - __main__ - Step 97277: {'lr': 0.0001408929151221243, 'samples': 18677184, 'steps': 97276, 'loss/train': 1.3224605321884155} 08/31/2021 06:49:45 - INFO - __main__ - Step 97278: {'lr': 0.00014088814046174628, 'samples': 18677376, 'steps': 97277, 'loss/train': 0.947833240032196} 08/31/2021 06:49:45 - INFO - __main__ - Step 97279: {'lr': 0.00014088336585053223, 'samples': 18677568, 'steps': 97278, 'loss/train': 1.4909716844558716} 08/31/2021 06:49:45 - INFO - __main__ - Step 97280: {'lr': 0.00014087859128848453, 'samples': 18677760, 'steps': 97279, 'loss/train': 1.6104843616485596} 08/31/2021 06:49:46 - INFO - __main__ - Step 97281: {'lr': 0.00014087381677560518, 'samples': 18677952, 'steps': 97280, 'loss/train': 1.4846627712249756} 08/31/2021 06:49:48 - INFO - __main__ - Step 97282: {'lr': 0.00014086904231189643, 'samples': 18678144, 'steps': 97281, 'loss/train': 1.281879186630249} 08/31/2021 06:49:48 - INFO - __main__ - Step 97283: {'lr': 0.0001408642678973604, 'samples': 18678336, 'steps': 97282, 'loss/train': 1.668168067932129} 08/31/2021 06:49:48 - INFO - __main__ - Step 97284: {'lr': 0.00014085949353199925, 'samples': 18678528, 'steps': 97283, 'loss/train': 0.8626554012298584} 08/31/2021 06:49:49 - INFO - __main__ - Step 97285: {'lr': 0.00014085471921581515, 'samples': 18678720, 'steps': 97284, 'loss/train': 0.8174747824668884} 08/31/2021 06:49:49 - INFO - __main__ - Step 97286: {'lr': 0.0001408499449488102, 'samples': 18678912, 'steps': 97285, 'loss/train': 0.8461136221885681} 08/31/2021 06:49:51 - INFO - __main__ - Step 97287: {'lr': 0.00014084517073098657, 'samples': 18679104, 'steps': 97286, 'loss/train': 1.0679694414138794} 08/31/2021 06:49:51 - INFO - __main__ - Step 97288: {'lr': 0.00014084039656234642, 'samples': 18679296, 'steps': 97287, 'loss/train': 1.5087515115737915} 08/31/2021 06:49:52 - INFO - __main__ - Step 97289: {'lr': 0.00014083562244289195, 'samples': 18679488, 'steps': 97288, 'loss/train': 0.7604408264160156} 08/31/2021 06:49:52 - INFO - __main__ - Step 97290: {'lr': 0.0001408308483726252, 'samples': 18679680, 'steps': 97289, 'loss/train': 0.8303909301757812} 08/31/2021 06:49:52 - INFO - __main__ - Step 97291: {'lr': 0.00014082607435154856, 'samples': 18679872, 'steps': 97290, 'loss/train': 0.8455714583396912} 08/31/2021 06:49:54 - INFO - __main__ - Step 97292: {'lr': 0.00014082130037966386, 'samples': 18680064, 'steps': 97291, 'loss/train': 0.7678682208061218} 08/31/2021 06:49:55 - INFO - __main__ - Step 97293: {'lr': 0.0001408165264569734, 'samples': 18680256, 'steps': 97292, 'loss/train': 0.5118140578269958} 08/31/2021 06:49:55 - INFO - __main__ - Step 97294: {'lr': 0.00014081175258347933, 'samples': 18680448, 'steps': 97293, 'loss/train': 1.3712520599365234} 08/31/2021 06:49:55 - INFO - __main__ - Step 97295: {'lr': 0.00014080697875918383, 'samples': 18680640, 'steps': 97294, 'loss/train': 1.482394814491272} 08/31/2021 06:49:56 - INFO - __main__ - Step 97296: {'lr': 0.00014080220498408896, 'samples': 18680832, 'steps': 97295, 'loss/train': 0.9754371047019958} 08/31/2021 06:49:56 - INFO - __main__ - Step 97297: {'lr': 0.000140797431258197, 'samples': 18681024, 'steps': 97296, 'loss/train': 1.24201238155365} 08/31/2021 06:49:56 - INFO - __main__ - Step 97298: {'lr': 0.00014079265758150999, 'samples': 18681216, 'steps': 97297, 'loss/train': 0.019660204648971558} 08/31/2021 06:49:58 - INFO - __main__ - Step 97299: {'lr': 0.00014078788395403014, 'samples': 18681408, 'steps': 97298, 'loss/train': 1.2330458164215088} 08/31/2021 06:49:58 - INFO - __main__ - Step 97300: {'lr': 0.0001407831103757596, 'samples': 18681600, 'steps': 97299, 'loss/train': 2.2967023849487305} 08/31/2021 06:49:59 - INFO - __main__ - Step 97301: {'lr': 0.00014077833684670045, 'samples': 18681792, 'steps': 97300, 'loss/train': 1.598179578781128} 08/31/2021 06:49:59 - INFO - __main__ - Step 97302: {'lr': 0.00014077356336685503, 'samples': 18681984, 'steps': 97301, 'loss/train': 0.765972375869751} 08/31/2021 06:50:00 - INFO - __main__ - Step 97303: {'lr': 0.00014076878993622526, 'samples': 18682176, 'steps': 97302, 'loss/train': 1.6235450506210327} 08/31/2021 06:50:01 - INFO - __main__ - Step 97304: {'lr': 0.00014076401655481336, 'samples': 18682368, 'steps': 97303, 'loss/train': 1.0436309576034546} 08/31/2021 06:50:01 - INFO - __main__ - Step 97305: {'lr': 0.00014075924322262155, 'samples': 18682560, 'steps': 97304, 'loss/train': 1.1511558294296265} 08/31/2021 06:50:02 - INFO - __main__ - Step 97306: {'lr': 0.0001407544699396519, 'samples': 18682752, 'steps': 97305, 'loss/train': 1.6138882637023926} 08/31/2021 06:50:02 - INFO - __main__ - Step 97307: {'lr': 0.00014074969670590663, 'samples': 18682944, 'steps': 97306, 'loss/train': 1.1066876649856567} 08/31/2021 06:50:03 - INFO - __main__ - Step 97308: {'lr': 0.00014074492352138786, 'samples': 18683136, 'steps': 97307, 'loss/train': 0.6299437284469604} 08/31/2021 06:50:05 - INFO - __main__ - Step 97309: {'lr': 0.0001407401503860977, 'samples': 18683328, 'steps': 97308, 'loss/train': 1.038818120956421} 08/31/2021 06:50:05 - INFO - __main__ - Step 97310: {'lr': 0.0001407353773000384, 'samples': 18683520, 'steps': 97309, 'loss/train': 0.13434579968452454} 08/31/2021 06:50:05 - INFO - __main__ - Step 97311: {'lr': 0.00014073060426321202, 'samples': 18683712, 'steps': 97310, 'loss/train': 1.2931334972381592} 08/31/2021 06:50:06 - INFO - __main__ - Step 97312: {'lr': 0.00014072583127562084, 'samples': 18683904, 'steps': 97311, 'loss/train': 1.4327430725097656} 08/31/2021 06:50:06 - INFO - __main__ - Step 97313: {'lr': 0.00014072105833726683, 'samples': 18684096, 'steps': 97312, 'loss/train': 0.32046014070510864} 08/31/2021 06:50:08 - INFO - __main__ - Step 97314: {'lr': 0.00014071628544815224, 'samples': 18684288, 'steps': 97313, 'loss/train': 1.6848409175872803} 08/31/2021 06:50:08 - INFO - __main__ - Step 97315: {'lr': 0.00014071151260827916, 'samples': 18684480, 'steps': 97314, 'loss/train': 0.9338322281837463} 08/31/2021 06:50:09 - INFO - __main__ - Step 97316: {'lr': 0.00014070673981764981, 'samples': 18684672, 'steps': 97315, 'loss/train': 0.9978773593902588} 08/31/2021 06:50:09 - INFO - __main__ - Step 97317: {'lr': 0.0001407019670762663, 'samples': 18684864, 'steps': 97316, 'loss/train': 1.2821335792541504} 08/31/2021 06:50:10 - INFO - __main__ - Step 97318: {'lr': 0.00014069719438413085, 'samples': 18685056, 'steps': 97317, 'loss/train': 0.01565813645720482} 08/31/2021 06:50:10 - INFO - __main__ - Step 97319: {'lr': 0.00014069242174124554, 'samples': 18685248, 'steps': 97318, 'loss/train': 1.6171690225601196} 08/31/2021 06:50:10 - INFO - __main__ - Step 97320: {'lr': 0.0001406876491476125, 'samples': 18685440, 'steps': 97319, 'loss/train': 1.1182612180709839} 08/31/2021 06:50:12 - INFO - __main__ - Step 97321: {'lr': 0.00014068287660323392, 'samples': 18685632, 'steps': 97320, 'loss/train': 0.9880237579345703} 08/31/2021 06:50:12 - INFO - __main__ - Step 97322: {'lr': 0.00014067810410811198, 'samples': 18685824, 'steps': 97321, 'loss/train': 1.173496961593628} 08/31/2021 06:50:12 - INFO - __main__ - Step 97323: {'lr': 0.0001406733316622489, 'samples': 18686016, 'steps': 97322, 'loss/train': 1.3179246187210083} 08/31/2021 06:50:13 - INFO - __main__ - Step 97324: {'lr': 0.00014066855926564659, 'samples': 18686208, 'steps': 97323, 'loss/train': 1.0592142343521118} 08/31/2021 06:50:13 - INFO - __main__ - Step 97325: {'lr': 0.0001406637869183074, 'samples': 18686400, 'steps': 97324, 'loss/train': 1.2010407447814941} 08/31/2021 06:50:15 - INFO - __main__ - Step 97326: {'lr': 0.00014065901462023336, 'samples': 18686592, 'steps': 97325, 'loss/train': 1.1924737691879272} 08/31/2021 06:50:15 - INFO - __main__ - Step 97327: {'lr': 0.0001406542423714267, 'samples': 18686784, 'steps': 97326, 'loss/train': 0.9715633988380432} 08/31/2021 06:50:16 - INFO - __main__ - Step 97328: {'lr': 0.00014064947017188956, 'samples': 18686976, 'steps': 97327, 'loss/train': 0.8499452471733093} 08/31/2021 06:50:16 - INFO - __main__ - Step 97329: {'lr': 0.0001406446980216241, 'samples': 18687168, 'steps': 97328, 'loss/train': 1.000552773475647} 08/31/2021 06:50:16 - INFO - __main__ - Step 97330: {'lr': 0.0001406399259206324, 'samples': 18687360, 'steps': 97329, 'loss/train': 1.4027642011642456} 08/31/2021 06:50:18 - INFO - __main__ - Step 97331: {'lr': 0.00014063515386891672, 'samples': 18687552, 'steps': 97330, 'loss/train': 0.6175758838653564} 08/31/2021 06:50:18 - INFO - __main__ - Step 97332: {'lr': 0.00014063038186647913, 'samples': 18687744, 'steps': 97331, 'loss/train': 4.9480133056640625} 08/31/2021 06:50:19 - INFO - __main__ - Step 97333: {'lr': 0.0001406256099133218, 'samples': 18687936, 'steps': 97332, 'loss/train': 1.300714135169983} 08/31/2021 06:50:19 - INFO - __main__ - Step 97334: {'lr': 0.00014062083800944698, 'samples': 18688128, 'steps': 97333, 'loss/train': 1.0815610885620117} 08/31/2021 06:50:19 - INFO - __main__ - Step 97335: {'lr': 0.00014061606615485661, 'samples': 18688320, 'steps': 97334, 'loss/train': 1.331461787223816} 08/31/2021 06:50:20 - INFO - __main__ - Step 97336: {'lr': 0.00014061129434955296, 'samples': 18688512, 'steps': 97335, 'loss/train': 0.06732726842164993} 08/31/2021 06:50:21 - INFO - __main__ - Step 97337: {'lr': 0.00014060652259353817, 'samples': 18688704, 'steps': 97336, 'loss/train': 1.27241051197052} 08/31/2021 06:50:22 - INFO - __main__ - Step 97338: {'lr': 0.00014060175088681441, 'samples': 18688896, 'steps': 97337, 'loss/train': 0.8498571515083313} 08/31/2021 06:50:22 - INFO - __main__ - Step 97339: {'lr': 0.0001405969792293838, 'samples': 18689088, 'steps': 97338, 'loss/train': 0.4657849967479706} 08/31/2021 06:50:22 - INFO - __main__ - Step 97340: {'lr': 0.00014059220762124852, 'samples': 18689280, 'steps': 97339, 'loss/train': 1.551831603050232} 08/31/2021 06:50:23 - INFO - __main__ - Step 97341: {'lr': 0.0001405874360624107, 'samples': 18689472, 'steps': 97340, 'loss/train': 1.0521124601364136} 08/31/2021 06:50:25 - INFO - __main__ - Step 97342: {'lr': 0.00014058266455287247, 'samples': 18689664, 'steps': 97341, 'loss/train': 1.9276872873306274} 08/31/2021 06:50:25 - INFO - __main__ - Step 97343: {'lr': 0.00014057789309263602, 'samples': 18689856, 'steps': 97342, 'loss/train': 0.6312562227249146} 08/31/2021 06:50:26 - INFO - __main__ - Step 97344: {'lr': 0.00014057312168170346, 'samples': 18690048, 'steps': 97343, 'loss/train': 1.123326063156128} 08/31/2021 06:50:26 - INFO - __main__ - Step 97345: {'lr': 0.00014056835032007708, 'samples': 18690240, 'steps': 97344, 'loss/train': 0.02756817266345024} 08/31/2021 06:50:26 - INFO - __main__ - Step 97346: {'lr': 0.00014056357900775886, 'samples': 18690432, 'steps': 97345, 'loss/train': 0.9230791330337524} 08/31/2021 06:50:28 - INFO - __main__ - Step 97347: {'lr': 0.00014055880774475093, 'samples': 18690624, 'steps': 97346, 'loss/train': 1.1086714267730713} 08/31/2021 06:50:28 - INFO - __main__ - Step 97348: {'lr': 0.00014055403653105553, 'samples': 18690816, 'steps': 97347, 'loss/train': 1.6121971607208252} 08/31/2021 06:50:29 - INFO - __main__ - Step 97349: {'lr': 0.0001405492653666748, 'samples': 18691008, 'steps': 97348, 'loss/train': 0.49336978793144226} 08/31/2021 06:50:29 - INFO - __main__ - Step 97350: {'lr': 0.0001405444942516109, 'samples': 18691200, 'steps': 97349, 'loss/train': 1.1554858684539795} 08/31/2021 06:50:29 - INFO - __main__ - Step 97351: {'lr': 0.00014053972318586595, 'samples': 18691392, 'steps': 97350, 'loss/train': 0.7618970274925232} 08/31/2021 06:50:31 - INFO - __main__ - Step 97352: {'lr': 0.00014053495216944208, 'samples': 18691584, 'steps': 97351, 'loss/train': 1.3807884454727173} 08/31/2021 06:50:31 - INFO - __main__ - Step 97353: {'lr': 0.0001405301812023415, 'samples': 18691776, 'steps': 97352, 'loss/train': 1.6285091638565063} 08/31/2021 06:50:32 - INFO - __main__ - Step 97354: {'lr': 0.00014052541028456635, 'samples': 18691968, 'steps': 97353, 'loss/train': 1.0406544208526611} 08/31/2021 06:50:32 - INFO - __main__ - Step 97355: {'lr': 0.00014052063941611876, 'samples': 18692160, 'steps': 97354, 'loss/train': 1.0076344013214111} 08/31/2021 06:50:33 - INFO - __main__ - Step 97356: {'lr': 0.00014051586859700082, 'samples': 18692352, 'steps': 97355, 'loss/train': 1.2885448932647705} 08/31/2021 06:50:35 - INFO - __main__ - Step 97357: {'lr': 0.0001405110978272148, 'samples': 18692544, 'steps': 97356, 'loss/train': 0.9964346289634705} 08/31/2021 06:50:35 - INFO - __main__ - Step 97358: {'lr': 0.00014050632710676275, 'samples': 18692736, 'steps': 97357, 'loss/train': 0.357993483543396} 08/31/2021 06:50:36 - INFO - __main__ - Step 97359: {'lr': 0.000140501556435647, 'samples': 18692928, 'steps': 97358, 'loss/train': 1.2125415802001953} 08/31/2021 06:50:36 - INFO - __main__ - Step 97360: {'lr': 0.00014049678581386942, 'samples': 18693120, 'steps': 97359, 'loss/train': 1.8967900276184082} 08/31/2021 06:50:36 - INFO - __main__ - Step 97361: {'lr': 0.00014049201524143234, 'samples': 18693312, 'steps': 97360, 'loss/train': 1.23812735080719} 08/31/2021 06:50:37 - INFO - __main__ - Step 97362: {'lr': 0.00014048724471833784, 'samples': 18693504, 'steps': 97361, 'loss/train': 1.6101689338684082} 08/31/2021 06:50:37 - INFO - __main__ - Step 97363: {'lr': 0.00014048247424458809, 'samples': 18693696, 'steps': 97362, 'loss/train': 1.7357927560806274} 08/31/2021 06:50:39 - INFO - __main__ - Step 97364: {'lr': 0.00014047770382018526, 'samples': 18693888, 'steps': 97363, 'loss/train': 0.8795987963676453} 08/31/2021 06:50:39 - INFO - __main__ - Step 97365: {'lr': 0.0001404729334451315, 'samples': 18694080, 'steps': 97364, 'loss/train': 2.0754761695861816} 08/31/2021 06:50:39 - INFO - __main__ - Step 97366: {'lr': 0.00014046816311942895, 'samples': 18694272, 'steps': 97365, 'loss/train': 1.354089379310608} 08/31/2021 06:50:40 - INFO - __main__ - Step 97367: {'lr': 0.00014046339284307975, 'samples': 18694464, 'steps': 97366, 'loss/train': 1.2172013521194458} 08/31/2021 06:50:40 - INFO - __main__ - Step 97368: {'lr': 0.00014045862261608604, 'samples': 18694656, 'steps': 97367, 'loss/train': 0.7054548859596252} 08/31/2021 06:50:42 - INFO - __main__ - Step 97369: {'lr': 0.00014045385243844998, 'samples': 18694848, 'steps': 97368, 'loss/train': 0.5666153430938721} 08/31/2021 06:50:42 - INFO - __main__ - Step 97370: {'lr': 0.00014044908231017372, 'samples': 18695040, 'steps': 97369, 'loss/train': 1.8207217454910278} 08/31/2021 06:50:43 - INFO - __main__ - Step 97371: {'lr': 0.00014044431223125941, 'samples': 18695232, 'steps': 97370, 'loss/train': 0.3557661771774292} 08/31/2021 06:50:43 - INFO - __main__ - Step 97372: {'lr': 0.00014043954220170935, 'samples': 18695424, 'steps': 97371, 'loss/train': 1.4188240766525269} 08/31/2021 06:50:43 - INFO - __main__ - Step 97373: {'lr': 0.0001404347722215254, 'samples': 18695616, 'steps': 97372, 'loss/train': 1.043563961982727} 08/31/2021 06:50:45 - INFO - __main__ - Step 97374: {'lr': 0.00014043000229070984, 'samples': 18695808, 'steps': 97373, 'loss/train': 1.1025210618972778} 08/31/2021 06:50:45 - INFO - __main__ - Step 97375: {'lr': 0.00014042523240926486, 'samples': 18696000, 'steps': 97374, 'loss/train': 0.9705355167388916} 08/31/2021 06:50:45 - INFO - __main__ - Step 97376: {'lr': 0.0001404204625771926, 'samples': 18696192, 'steps': 97375, 'loss/train': 0.8744102716445923} 08/31/2021 06:50:46 - INFO - __main__ - Step 97377: {'lr': 0.00014041569279449513, 'samples': 18696384, 'steps': 97376, 'loss/train': 1.5740370750427246} 08/31/2021 06:50:46 - INFO - __main__ - Step 97378: {'lr': 0.0001404109230611747, 'samples': 18696576, 'steps': 97377, 'loss/train': 1.0704059600830078} 08/31/2021 06:50:48 - INFO - __main__ - Step 97379: {'lr': 0.0001404061533772334, 'samples': 18696768, 'steps': 97378, 'loss/train': 0.8792445659637451} 08/31/2021 06:50:48 - INFO - __main__ - Step 97380: {'lr': 0.00014040138374267342, 'samples': 18696960, 'steps': 97379, 'loss/train': 0.976929247379303} 08/31/2021 06:50:49 - INFO - __main__ - Step 97381: {'lr': 0.00014039661415749682, 'samples': 18697152, 'steps': 97380, 'loss/train': 0.5529689192771912} 08/31/2021 06:50:49 - INFO - __main__ - Step 97382: {'lr': 0.0001403918446217059, 'samples': 18697344, 'steps': 97381, 'loss/train': 1.4296165704727173} 08/31/2021 06:50:49 - INFO - __main__ - Step 97383: {'lr': 0.00014038707513530267, 'samples': 18697536, 'steps': 97382, 'loss/train': 0.7372773885726929} 08/31/2021 06:50:50 - INFO - __main__ - Step 97384: {'lr': 0.00014038230569828937, 'samples': 18697728, 'steps': 97383, 'loss/train': 1.4025241136550903} 08/31/2021 06:50:51 - INFO - __main__ - Step 97385: {'lr': 0.00014037753631066815, 'samples': 18697920, 'steps': 97384, 'loss/train': 1.5729117393493652} 08/31/2021 06:50:52 - INFO - __main__ - Step 97386: {'lr': 0.00014037276697244106, 'samples': 18698112, 'steps': 97385, 'loss/train': 1.582082748413086} 08/31/2021 06:50:52 - INFO - __main__ - Step 97387: {'lr': 0.0001403679976836103, 'samples': 18698304, 'steps': 97386, 'loss/train': 1.1648176908493042} 08/31/2021 06:50:52 - INFO - __main__ - Step 97388: {'lr': 0.00014036322844417803, 'samples': 18698496, 'steps': 97387, 'loss/train': 0.5701935887336731} 08/31/2021 06:50:53 - INFO - __main__ - Step 97389: {'lr': 0.00014035845925414642, 'samples': 18698688, 'steps': 97388, 'loss/train': 1.1414424180984497} 08/31/2021 06:50:54 - INFO - __main__ - Step 97390: {'lr': 0.00014035369011351756, 'samples': 18698880, 'steps': 97389, 'loss/train': 1.0107671022415161} 08/31/2021 06:50:55 - INFO - __main__ - Step 97391: {'lr': 0.0001403489210222937, 'samples': 18699072, 'steps': 97390, 'loss/train': 2.262587070465088} 08/31/2021 06:50:55 - INFO - __main__ - Step 97392: {'lr': 0.00014034415198047685, 'samples': 18699264, 'steps': 97391, 'loss/train': 0.11741869151592255} 08/31/2021 06:50:56 - INFO - __main__ - Step 97393: {'lr': 0.00014033938298806925, 'samples': 18699456, 'steps': 97392, 'loss/train': 1.30916428565979} 08/31/2021 06:50:56 - INFO - __main__ - Step 97394: {'lr': 0.00014033461404507305, 'samples': 18699648, 'steps': 97393, 'loss/train': 0.943912148475647} 08/31/2021 06:50:58 - INFO - __main__ - Step 97395: {'lr': 0.0001403298451514904, 'samples': 18699840, 'steps': 97394, 'loss/train': 1.0489449501037598} 08/31/2021 06:50:58 - INFO - __main__ - Step 97396: {'lr': 0.0001403250763073234, 'samples': 18700032, 'steps': 97395, 'loss/train': 1.0305004119873047} 08/31/2021 06:50:59 - INFO - __main__ - Step 97397: {'lr': 0.0001403203075125742, 'samples': 18700224, 'steps': 97396, 'loss/train': 0.9777399301528931} 08/31/2021 06:50:59 - INFO - __main__ - Step 97398: {'lr': 0.000140315538767245, 'samples': 18700416, 'steps': 97397, 'loss/train': 0.9519603252410889} 08/31/2021 06:50:59 - INFO - __main__ - Step 97399: {'lr': 0.00014031077007133807, 'samples': 18700608, 'steps': 97398, 'loss/train': 0.9105738401412964} 08/31/2021 06:51:00 - INFO - __main__ - Step 97400: {'lr': 0.00014030600142485528, 'samples': 18700800, 'steps': 97399, 'loss/train': 0.9561859369277954} 08/31/2021 06:51:01 - INFO - __main__ - Step 97401: {'lr': 0.00014030123282779888, 'samples': 18700992, 'steps': 97400, 'loss/train': 1.4066706895828247} 08/31/2021 06:51:02 - INFO - __main__ - Step 97402: {'lr': 0.00014029646428017113, 'samples': 18701184, 'steps': 97401, 'loss/train': 0.48908761143684387} 08/31/2021 06:51:02 - INFO - __main__ - Step 97403: {'lr': 0.00014029169578197404, 'samples': 18701376, 'steps': 97402, 'loss/train': 0.20734989643096924} 08/31/2021 06:51:02 - INFO - __main__ - Step 97404: {'lr': 0.00014028692733320983, 'samples': 18701568, 'steps': 97403, 'loss/train': 0.6198925375938416} 08/31/2021 06:51:03 - INFO - __main__ - Step 97405: {'lr': 0.00014028215893388063, 'samples': 18701760, 'steps': 97404, 'loss/train': 1.1730360984802246} 08/31/2021 06:51:04 - INFO - __main__ - Step 97406: {'lr': 0.0001402773905839886, 'samples': 18701952, 'steps': 97405, 'loss/train': 0.604405403137207} 08/31/2021 06:51:05 - INFO - __main__ - Step 97407: {'lr': 0.0001402726222835359, 'samples': 18702144, 'steps': 97406, 'loss/train': 1.364751935005188} 08/31/2021 06:51:05 - INFO - __main__ - Step 97408: {'lr': 0.00014026785403252468, 'samples': 18702336, 'steps': 97407, 'loss/train': 1.0001531839370728} 08/31/2021 06:51:06 - INFO - __main__ - Step 97409: {'lr': 0.00014026308583095704, 'samples': 18702528, 'steps': 97408, 'loss/train': 1.0786597728729248} 08/31/2021 06:51:06 - INFO - __main__ - Step 97410: {'lr': 0.00014025831767883515, 'samples': 18702720, 'steps': 97409, 'loss/train': 1.1451719999313354} 08/31/2021 06:51:08 - INFO - __main__ - Step 97411: {'lr': 0.0001402535495761612, 'samples': 18702912, 'steps': 97410, 'loss/train': 1.3900501728057861} 08/31/2021 06:51:08 - INFO - __main__ - Step 97412: {'lr': 0.0001402487815229374, 'samples': 18703104, 'steps': 97411, 'loss/train': 1.10999596118927} 08/31/2021 06:51:08 - INFO - __main__ - Step 97413: {'lr': 0.0001402440135191657, 'samples': 18703296, 'steps': 97412, 'loss/train': 1.3064186573028564} 08/31/2021 06:51:09 - INFO - __main__ - Step 97414: {'lr': 0.00014023924556484836, 'samples': 18703488, 'steps': 97413, 'loss/train': 1.2534806728363037} 08/31/2021 06:51:09 - INFO - __main__ - Step 97415: {'lr': 0.00014023447765998748, 'samples': 18703680, 'steps': 97414, 'loss/train': 1.513184905052185} 08/31/2021 06:51:09 - INFO - __main__ - Step 97416: {'lr': 0.00014022970980458527, 'samples': 18703872, 'steps': 97415, 'loss/train': 1.241150140762329} 08/31/2021 06:51:11 - INFO - __main__ - Step 97417: {'lr': 0.00014022494199864387, 'samples': 18704064, 'steps': 97416, 'loss/train': 1.3964866399765015} 08/31/2021 06:51:11 - INFO - __main__ - Step 97418: {'lr': 0.00014022017424216544, 'samples': 18704256, 'steps': 97417, 'loss/train': 1.06961989402771} 08/31/2021 06:51:12 - INFO - __main__ - Step 97419: {'lr': 0.00014021540653515207, 'samples': 18704448, 'steps': 97418, 'loss/train': 1.3601223230361938} 08/31/2021 06:51:12 - INFO - __main__ - Step 97420: {'lr': 0.000140210638877606, 'samples': 18704640, 'steps': 97419, 'loss/train': 0.6716336607933044} 08/31/2021 06:51:12 - INFO - __main__ - Step 97421: {'lr': 0.00014020587126952928, 'samples': 18704832, 'steps': 97420, 'loss/train': 1.0491230487823486} 08/31/2021 06:51:14 - INFO - __main__ - Step 97422: {'lr': 0.0001402011037109241, 'samples': 18705024, 'steps': 97421, 'loss/train': 1.0507571697235107} 08/31/2021 06:51:14 - INFO - __main__ - Step 97423: {'lr': 0.0001401963362017926, 'samples': 18705216, 'steps': 97422, 'loss/train': 1.3818720579147339} 08/31/2021 06:51:15 - INFO - __main__ - Step 97424: {'lr': 0.00014019156874213695, 'samples': 18705408, 'steps': 97423, 'loss/train': 1.2852582931518555} 08/31/2021 06:51:15 - INFO - __main__ - Step 97425: {'lr': 0.00014018680133195927, 'samples': 18705600, 'steps': 97424, 'loss/train': 0.8214133381843567} 08/31/2021 06:51:15 - INFO - __main__ - Step 97426: {'lr': 0.00014018203397126185, 'samples': 18705792, 'steps': 97425, 'loss/train': 0.7509004473686218} 08/31/2021 06:51:17 - INFO - __main__ - Step 97427: {'lr': 0.0001401772666600466, 'samples': 18705984, 'steps': 97426, 'loss/train': 1.3853875398635864} 08/31/2021 06:51:17 - INFO - __main__ - Step 97428: {'lr': 0.0001401724993983158, 'samples': 18706176, 'steps': 97427, 'loss/train': 0.02649393118917942} 08/31/2021 06:51:18 - INFO - __main__ - Step 97429: {'lr': 0.0001401677321860715, 'samples': 18706368, 'steps': 97428, 'loss/train': 0.788628876209259} 08/31/2021 06:51:18 - INFO - __main__ - Step 97430: {'lr': 0.000140162965023316, 'samples': 18706560, 'steps': 97429, 'loss/train': 0.7603089809417725} 08/31/2021 06:51:18 - INFO - __main__ - Step 97431: {'lr': 0.00014015819791005137, 'samples': 18706752, 'steps': 97430, 'loss/train': 1.488219141960144} 08/31/2021 06:51:19 - INFO - __main__ - Step 97432: {'lr': 0.0001401534308462797, 'samples': 18706944, 'steps': 97431, 'loss/train': 0.5085647106170654} 08/31/2021 06:51:20 - INFO - __main__ - Step 97433: {'lr': 0.00014014866383200324, 'samples': 18707136, 'steps': 97432, 'loss/train': 2.2721002101898193} 08/31/2021 06:51:21 - INFO - __main__ - Step 97434: {'lr': 0.0001401438968672241, 'samples': 18707328, 'steps': 97433, 'loss/train': 1.6723442077636719} 08/31/2021 06:51:21 - INFO - __main__ - Step 97435: {'lr': 0.00014013912995194445, 'samples': 18707520, 'steps': 97434, 'loss/train': 0.7374874353408813} 08/31/2021 06:51:21 - INFO - __main__ - Step 97436: {'lr': 0.00014013436308616634, 'samples': 18707712, 'steps': 97435, 'loss/train': 1.3376604318618774} 08/31/2021 06:51:22 - INFO - __main__ - Step 97437: {'lr': 0.00014012959626989206, 'samples': 18707904, 'steps': 97436, 'loss/train': 0.9226334095001221} 08/31/2021 06:51:23 - INFO - __main__ - Step 97438: {'lr': 0.00014012482950312368, 'samples': 18708096, 'steps': 97437, 'loss/train': 1.2735588550567627} 08/31/2021 06:51:24 - INFO - __main__ - Step 97439: {'lr': 0.00014012006278586343, 'samples': 18708288, 'steps': 97438, 'loss/train': 1.196380376815796} 08/31/2021 06:51:24 - INFO - __main__ - Step 97440: {'lr': 0.0001401152961181133, 'samples': 18708480, 'steps': 97439, 'loss/train': 1.1876469850540161} 08/31/2021 06:51:24 - INFO - __main__ - Step 97441: {'lr': 0.0001401105294998755, 'samples': 18708672, 'steps': 97440, 'loss/train': 1.2063348293304443} 08/31/2021 06:51:25 - INFO - __main__ - Step 97442: {'lr': 0.00014010576293115222, 'samples': 18708864, 'steps': 97441, 'loss/train': 1.7553097009658813} 08/31/2021 06:51:26 - INFO - __main__ - Step 97443: {'lr': 0.00014010099641194556, 'samples': 18709056, 'steps': 97442, 'loss/train': 1.0856267213821411} 08/31/2021 06:51:27 - INFO - __main__ - Step 97444: {'lr': 0.00014009622994225773, 'samples': 18709248, 'steps': 97443, 'loss/train': 1.3089492321014404} 08/31/2021 06:51:27 - INFO - __main__ - Step 97445: {'lr': 0.00014009146352209084, 'samples': 18709440, 'steps': 97444, 'loss/train': 1.452183485031128} 08/31/2021 06:51:27 - INFO - __main__ - Step 97446: {'lr': 0.00014008669715144702, 'samples': 18709632, 'steps': 97445, 'loss/train': 0.7320536375045776} 08/31/2021 06:51:28 - INFO - __main__ - Step 97447: {'lr': 0.00014008193083032844, 'samples': 18709824, 'steps': 97446, 'loss/train': 1.2153111696243286} 08/31/2021 06:51:30 - INFO - __main__ - Step 97448: {'lr': 0.00014007716455873725, 'samples': 18710016, 'steps': 97447, 'loss/train': 1.0671582221984863} 08/31/2021 06:51:30 - INFO - __main__ - Step 97449: {'lr': 0.0001400723983366756, 'samples': 18710208, 'steps': 97448, 'loss/train': 1.4240777492523193} 08/31/2021 06:51:31 - INFO - __main__ - Step 97450: {'lr': 0.00014006763216414564, 'samples': 18710400, 'steps': 97449, 'loss/train': 1.037349820137024} 08/31/2021 06:51:31 - INFO - __main__ - Step 97451: {'lr': 0.0001400628660411495, 'samples': 18710592, 'steps': 97450, 'loss/train': 1.3312721252441406} 08/31/2021 06:51:31 - INFO - __main__ - Step 97452: {'lr': 0.00014005809996768935, 'samples': 18710784, 'steps': 97451, 'loss/train': 0.031908322125673294} 08/31/2021 06:51:33 - INFO - __main__ - Step 97453: {'lr': 0.0001400533339437674, 'samples': 18710976, 'steps': 97452, 'loss/train': 1.6097331047058105} 08/31/2021 06:51:34 - INFO - __main__ - Step 97454: {'lr': 0.00014004856796938565, 'samples': 18711168, 'steps': 97453, 'loss/train': 1.3864026069641113} 08/31/2021 06:51:34 - INFO - __main__ - Step 97455: {'lr': 0.00014004380204454627, 'samples': 18711360, 'steps': 97454, 'loss/train': 1.0669692754745483} 08/31/2021 06:51:34 - INFO - __main__ - Step 97456: {'lr': 0.00014003903616925152, 'samples': 18711552, 'steps': 97455, 'loss/train': 1.1787246465682983} 08/31/2021 06:51:35 - INFO - __main__ - Step 97457: {'lr': 0.00014003427034350342, 'samples': 18711744, 'steps': 97456, 'loss/train': 1.3956507444381714} 08/31/2021 06:51:36 - INFO - __main__ - Step 97458: {'lr': 0.0001400295045673042, 'samples': 18711936, 'steps': 97457, 'loss/train': 0.0291399247944355} 08/31/2021 06:51:37 - INFO - __main__ - Step 97459: {'lr': 0.00014002473884065601, 'samples': 18712128, 'steps': 97458, 'loss/train': 1.6755681037902832} 08/31/2021 06:51:37 - INFO - __main__ - Step 97460: {'lr': 0.00014001997316356095, 'samples': 18712320, 'steps': 97459, 'loss/train': 0.7870520353317261} 08/31/2021 06:51:37 - INFO - __main__ - Step 97461: {'lr': 0.0001400152075360212, 'samples': 18712512, 'steps': 97460, 'loss/train': 1.245167851448059} 08/31/2021 06:51:38 - INFO - __main__ - Step 97462: {'lr': 0.00014001044195803891, 'samples': 18712704, 'steps': 97461, 'loss/train': 1.779900074005127} 08/31/2021 06:51:40 - INFO - __main__ - Step 97463: {'lr': 0.00014000567642961622, 'samples': 18712896, 'steps': 97462, 'loss/train': 1.2091422080993652} 08/31/2021 06:51:40 - INFO - __main__ - Step 97464: {'lr': 0.0001400009109507553, 'samples': 18713088, 'steps': 97463, 'loss/train': 0.5015732049942017} 08/31/2021 06:51:41 - INFO - __main__ - Step 97465: {'lr': 0.00013999614552145823, 'samples': 18713280, 'steps': 97464, 'loss/train': 1.042346477508545} 08/31/2021 06:51:41 - INFO - __main__ - Step 97466: {'lr': 0.0001399913801417273, 'samples': 18713472, 'steps': 97465, 'loss/train': 0.04111626371741295} 08/31/2021 06:51:41 - INFO - __main__ - Step 97467: {'lr': 0.00013998661481156446, 'samples': 18713664, 'steps': 97466, 'loss/train': 1.2820110321044922} 08/31/2021 06:51:42 - INFO - __main__ - Step 97468: {'lr': 0.00013998184953097195, 'samples': 18713856, 'steps': 97467, 'loss/train': 1.2937042713165283} 08/31/2021 06:51:43 - INFO - __main__ - Step 97469: {'lr': 0.00013997708429995193, 'samples': 18714048, 'steps': 97468, 'loss/train': 1.181869387626648} 08/31/2021 06:51:44 - INFO - __main__ - Step 97470: {'lr': 0.00013997231911850656, 'samples': 18714240, 'steps': 97469, 'loss/train': 0.03750601038336754} 08/31/2021 06:51:44 - INFO - __main__ - Step 97471: {'lr': 0.00013996755398663793, 'samples': 18714432, 'steps': 97470, 'loss/train': 1.1407604217529297} 08/31/2021 06:51:44 - INFO - __main__ - Step 97472: {'lr': 0.00013996278890434825, 'samples': 18714624, 'steps': 97471, 'loss/train': 1.1664870977401733} 08/31/2021 06:51:45 - INFO - __main__ - Step 97473: {'lr': 0.00013995802387163964, 'samples': 18714816, 'steps': 97472, 'loss/train': 1.3906500339508057} 08/31/2021 06:51:46 - INFO - __main__ - Step 97474: {'lr': 0.0001399532588885142, 'samples': 18715008, 'steps': 97473, 'loss/train': 1.2855591773986816} 08/31/2021 06:51:47 - INFO - __main__ - Step 97475: {'lr': 0.00013994849395497415, 'samples': 18715200, 'steps': 97474, 'loss/train': 1.2011350393295288} 08/31/2021 06:51:47 - INFO - __main__ - Step 97476: {'lr': 0.00013994372907102167, 'samples': 18715392, 'steps': 97475, 'loss/train': 1.2468986511230469} 08/31/2021 06:51:47 - INFO - __main__ - Step 97477: {'lr': 0.00013993896423665874, 'samples': 18715584, 'steps': 97476, 'loss/train': 0.8704091906547546} 08/31/2021 06:51:48 - INFO - __main__ - Step 97478: {'lr': 0.00013993419945188768, 'samples': 18715776, 'steps': 97477, 'loss/train': 1.4218530654907227} 08/31/2021 06:51:50 - INFO - __main__ - Step 97479: {'lr': 0.00013992943471671055, 'samples': 18715968, 'steps': 97478, 'loss/train': 1.0742912292480469} 08/31/2021 06:51:50 - INFO - __main__ - Step 97480: {'lr': 0.00013992467003112963, 'samples': 18716160, 'steps': 97479, 'loss/train': 0.150120347738266} 08/31/2021 06:51:50 - INFO - __main__ - Step 97481: {'lr': 0.00013991990539514686, 'samples': 18716352, 'steps': 97480, 'loss/train': 0.02941700629889965} 08/31/2021 06:51:51 - INFO - __main__ - Step 97482: {'lr': 0.0001399151408087645, 'samples': 18716544, 'steps': 97481, 'loss/train': 1.368327021598816} 08/31/2021 06:51:51 - INFO - __main__ - Step 97483: {'lr': 0.00013991037627198463, 'samples': 18716736, 'steps': 97482, 'loss/train': 1.8859095573425293} 08/31/2021 06:51:51 - INFO - __main__ - Step 97484: {'lr': 0.00013990561178480948, 'samples': 18716928, 'steps': 97483, 'loss/train': 0.0273771770298481} 08/31/2021 06:51:53 - INFO - __main__ - Step 97485: {'lr': 0.00013990084734724116, 'samples': 18717120, 'steps': 97484, 'loss/train': 0.016803743317723274} 08/31/2021 06:51:53 - INFO - __main__ - Step 97486: {'lr': 0.0001398960829592818, 'samples': 18717312, 'steps': 97485, 'loss/train': 1.0673432350158691} 08/31/2021 06:51:54 - INFO - __main__ - Step 97487: {'lr': 0.00013989131862093357, 'samples': 18717504, 'steps': 97486, 'loss/train': 1.4372931718826294} 08/31/2021 06:51:54 - INFO - __main__ - Step 97488: {'lr': 0.0001398865543321986, 'samples': 18717696, 'steps': 97487, 'loss/train': 1.3543270826339722} 08/31/2021 06:51:54 - INFO - __main__ - Step 97489: {'lr': 0.0001398817900930791, 'samples': 18717888, 'steps': 97488, 'loss/train': 1.2848060131072998} 08/31/2021 06:51:56 - INFO - __main__ - Step 97490: {'lr': 0.0001398770259035771, 'samples': 18718080, 'steps': 97489, 'loss/train': 0.13896292448043823} 08/31/2021 06:51:56 - INFO - __main__ - Step 97491: {'lr': 0.00013987226176369487, 'samples': 18718272, 'steps': 97490, 'loss/train': 0.9473576545715332} 08/31/2021 06:51:57 - INFO - __main__ - Step 97492: {'lr': 0.00013986749767343448, 'samples': 18718464, 'steps': 97491, 'loss/train': 1.295639991760254} 08/31/2021 06:51:57 - INFO - __main__ - Step 97493: {'lr': 0.00013986273363279818, 'samples': 18718656, 'steps': 97492, 'loss/train': 1.7643930912017822} 08/31/2021 06:51:57 - INFO - __main__ - Step 97494: {'lr': 0.00013985796964178796, 'samples': 18718848, 'steps': 97493, 'loss/train': 1.283450722694397} 08/31/2021 06:51:59 - INFO - __main__ - Step 97495: {'lr': 0.000139853205700406, 'samples': 18719040, 'steps': 97494, 'loss/train': 1.272491455078125} 08/31/2021 06:51:59 - INFO - __main__ - Step 97496: {'lr': 0.00013984844180865453, 'samples': 18719232, 'steps': 97495, 'loss/train': 1.1058306694030762} 08/31/2021 06:52:00 - INFO - __main__ - Step 97497: {'lr': 0.00013984367796653562, 'samples': 18719424, 'steps': 97496, 'loss/train': 0.08564866334199905} 08/31/2021 06:52:00 - INFO - __main__ - Step 97498: {'lr': 0.00013983891417405147, 'samples': 18719616, 'steps': 97497, 'loss/train': 0.7912031412124634} 08/31/2021 06:52:00 - INFO - __main__ - Step 97499: {'lr': 0.00013983415043120423, 'samples': 18719808, 'steps': 97498, 'loss/train': 0.656093955039978} 08/31/2021 06:52:02 - INFO - __main__ - Step 97500: {'lr': 0.00013982938673799596, 'samples': 18720000, 'steps': 97499, 'loss/train': 1.1896227598190308} 08/31/2021 06:52:03 - INFO - __main__ - Step 97501: {'lr': 0.0001398246230944289, 'samples': 18720192, 'steps': 97500, 'loss/train': 1.0820424556732178} 08/31/2021 06:52:03 - INFO - __main__ - Step 97502: {'lr': 0.00013981985950050518, 'samples': 18720384, 'steps': 97501, 'loss/train': 0.7531193494796753} 08/31/2021 06:52:04 - INFO - __main__ - Step 97503: {'lr': 0.0001398150959562269, 'samples': 18720576, 'steps': 97502, 'loss/train': 1.4024221897125244} 08/31/2021 06:52:04 - INFO - __main__ - Step 97504: {'lr': 0.00013981033246159624, 'samples': 18720768, 'steps': 97503, 'loss/train': 1.2160968780517578} 08/31/2021 06:52:06 - INFO - __main__ - Step 97505: {'lr': 0.0001398055690166154, 'samples': 18720960, 'steps': 97504, 'loss/train': 1.3329992294311523} 08/31/2021 06:52:06 - INFO - __main__ - Step 97506: {'lr': 0.0001398008056212865, 'samples': 18721152, 'steps': 97505, 'loss/train': 1.3490841388702393} 08/31/2021 06:52:07 - INFO - __main__ - Step 97507: {'lr': 0.0001397960422756116, 'samples': 18721344, 'steps': 97506, 'loss/train': 1.5660220384597778} 08/31/2021 06:52:07 - INFO - __main__ - Step 97508: {'lr': 0.00013979127897959288, 'samples': 18721536, 'steps': 97507, 'loss/train': 1.418349266052246} 08/31/2021 06:52:07 - INFO - __main__ - Step 97509: {'lr': 0.0001397865157332325, 'samples': 18721728, 'steps': 97508, 'loss/train': 1.7847168445587158} 08/31/2021 06:52:08 - INFO - __main__ - Step 97510: {'lr': 0.00013978175253653264, 'samples': 18721920, 'steps': 97509, 'loss/train': 1.0822309255599976} 08/31/2021 06:52:10 - INFO - __main__ - Step 97511: {'lr': 0.0001397769893894954, 'samples': 18722112, 'steps': 97510, 'loss/train': 1.344345211982727} 08/31/2021 06:52:10 - INFO - __main__ - Step 97512: {'lr': 0.00013977222629212296, 'samples': 18722304, 'steps': 97511, 'loss/train': 0.9664269089698792} 08/31/2021 06:52:11 - INFO - __main__ - Step 97513: {'lr': 0.00013976746324441747, 'samples': 18722496, 'steps': 97512, 'loss/train': 0.3295220136642456} 08/31/2021 06:52:11 - INFO - __main__ - Step 97514: {'lr': 0.00013976270024638104, 'samples': 18722688, 'steps': 97513, 'loss/train': 0.0162852443754673} 08/31/2021 06:52:11 - INFO - __main__ - Step 97515: {'lr': 0.00013975793729801582, 'samples': 18722880, 'steps': 97514, 'loss/train': 0.014467664062976837} 08/31/2021 06:52:12 - INFO - __main__ - Step 97516: {'lr': 0.000139753174399324, 'samples': 18723072, 'steps': 97515, 'loss/train': 1.8388937711715698} 08/31/2021 06:52:13 - INFO - __main__ - Step 97517: {'lr': 0.0001397484115503077, 'samples': 18723264, 'steps': 97516, 'loss/train': 1.0403199195861816} 08/31/2021 06:52:14 - INFO - __main__ - Step 97518: {'lr': 0.00013974364875096905, 'samples': 18723456, 'steps': 97517, 'loss/train': 1.1695501804351807} 08/31/2021 06:52:14 - INFO - __main__ - Step 97519: {'lr': 0.00013973888600131022, 'samples': 18723648, 'steps': 97518, 'loss/train': 1.1708177328109741} 08/31/2021 06:52:14 - INFO - __main__ - Step 97520: {'lr': 0.00013973412330133345, 'samples': 18723840, 'steps': 97519, 'loss/train': 1.8812892436981201} 08/31/2021 06:52:15 - INFO - __main__ - Step 97521: {'lr': 0.00013972936065104064, 'samples': 18724032, 'steps': 97520, 'loss/train': 1.1532236337661743} 08/31/2021 06:52:16 - INFO - __main__ - Step 97522: {'lr': 0.00013972459805043413, 'samples': 18724224, 'steps': 97521, 'loss/train': 1.3426382541656494} 08/31/2021 06:52:17 - INFO - __main__ - Step 97523: {'lr': 0.000139719835499516, 'samples': 18724416, 'steps': 97522, 'loss/train': 1.8778345584869385} 08/31/2021 06:52:17 - INFO - __main__ - Step 97524: {'lr': 0.0001397150729982884, 'samples': 18724608, 'steps': 97523, 'loss/train': 1.379143476486206} 08/31/2021 06:52:18 - INFO - __main__ - Step 97525: {'lr': 0.0001397103105467535, 'samples': 18724800, 'steps': 97524, 'loss/train': 1.5747647285461426} 08/31/2021 06:52:18 - INFO - __main__ - Step 97526: {'lr': 0.00013970554814491344, 'samples': 18724992, 'steps': 97525, 'loss/train': 0.8261036276817322} 08/31/2021 06:52:18 - INFO - __main__ - Step 97527: {'lr': 0.00013970078579277032, 'samples': 18725184, 'steps': 97526, 'loss/train': 1.1621326208114624} 08/31/2021 06:52:20 - INFO - __main__ - Step 97528: {'lr': 0.00013969602349032633, 'samples': 18725376, 'steps': 97527, 'loss/train': 1.3568514585494995} 08/31/2021 06:52:21 - INFO - __main__ - Step 97529: {'lr': 0.00013969126123758362, 'samples': 18725568, 'steps': 97528, 'loss/train': 1.5732407569885254} 08/31/2021 06:52:21 - INFO - __main__ - Step 97530: {'lr': 0.00013968649903454435, 'samples': 18725760, 'steps': 97529, 'loss/train': 1.539645791053772} 08/31/2021 06:52:21 - INFO - __main__ - Step 97531: {'lr': 0.00013968173688121062, 'samples': 18725952, 'steps': 97530, 'loss/train': 0.46799954771995544} 08/31/2021 06:52:22 - INFO - __main__ - Step 97532: {'lr': 0.00013967697477758461, 'samples': 18726144, 'steps': 97531, 'loss/train': 0.8097679018974304} 08/31/2021 06:52:23 - INFO - __main__ - Step 97533: {'lr': 0.00013967221272366854, 'samples': 18726336, 'steps': 97532, 'loss/train': 0.033711861819028854} 08/31/2021 06:52:24 - INFO - __main__ - Step 97534: {'lr': 0.00013966745071946439, 'samples': 18726528, 'steps': 97533, 'loss/train': 1.4530551433563232} 08/31/2021 06:52:24 - INFO - __main__ - Step 97535: {'lr': 0.00013966268876497434, 'samples': 18726720, 'steps': 97534, 'loss/train': 1.2971190214157104} 08/31/2021 06:52:25 - INFO - __main__ - Step 97536: {'lr': 0.00013965792686020063, 'samples': 18726912, 'steps': 97535, 'loss/train': 0.7080249190330505} 08/31/2021 06:52:25 - INFO - __main__ - Step 97537: {'lr': 0.00013965316500514532, 'samples': 18727104, 'steps': 97536, 'loss/train': 0.5637668967247009} 08/31/2021 06:52:27 - INFO - __main__ - Step 97538: {'lr': 0.0001396484031998106, 'samples': 18727296, 'steps': 97537, 'loss/train': 1.3900514841079712} 08/31/2021 06:52:27 - INFO - __main__ - Step 97539: {'lr': 0.0001396436414441986, 'samples': 18727488, 'steps': 97538, 'loss/train': 0.815171480178833} 08/31/2021 06:52:27 - INFO - __main__ - Step 97540: {'lr': 0.00013963887973831153, 'samples': 18727680, 'steps': 97539, 'loss/train': 1.2635846138000488} 08/31/2021 06:52:28 - INFO - __main__ - Step 97541: {'lr': 0.0001396341180821514, 'samples': 18727872, 'steps': 97540, 'loss/train': 1.3517860174179077} 08/31/2021 06:52:28 - INFO - __main__ - Step 97542: {'lr': 0.00013962935647572044, 'samples': 18728064, 'steps': 97541, 'loss/train': 0.508669912815094} 08/31/2021 06:52:30 - INFO - __main__ - Step 97543: {'lr': 0.00013962459491902084, 'samples': 18728256, 'steps': 97542, 'loss/train': 1.2449157238006592} 08/31/2021 06:52:30 - INFO - __main__ - Step 97544: {'lr': 0.00013961983341205465, 'samples': 18728448, 'steps': 97543, 'loss/train': 0.7041391134262085} 08/31/2021 06:52:31 - INFO - __main__ - Step 97545: {'lr': 0.0001396150719548241, 'samples': 18728640, 'steps': 97544, 'loss/train': 1.5566017627716064} 08/31/2021 06:52:31 - INFO - __main__ - Step 97546: {'lr': 0.00013961031054733126, 'samples': 18728832, 'steps': 97545, 'loss/train': 1.2003324031829834} 08/31/2021 06:52:31 - INFO - __main__ - Step 97547: {'lr': 0.00013960554918957842, 'samples': 18729024, 'steps': 97546, 'loss/train': 0.41519415378570557} 08/31/2021 06:52:32 - INFO - __main__ - Step 97548: {'lr': 0.00013960078788156753, 'samples': 18729216, 'steps': 97547, 'loss/train': 0.9391587376594543} 08/31/2021 06:52:33 - INFO - __main__ - Step 97549: {'lr': 0.00013959602662330078, 'samples': 18729408, 'steps': 97548, 'loss/train': 1.09037184715271} 08/31/2021 06:52:34 - INFO - __main__ - Step 97550: {'lr': 0.0001395912654147804, 'samples': 18729600, 'steps': 97549, 'loss/train': 1.209672451019287} 08/31/2021 06:52:34 - INFO - __main__ - Step 97551: {'lr': 0.0001395865042560085, 'samples': 18729792, 'steps': 97550, 'loss/train': 0.7827520966529846} 08/31/2021 06:52:35 - INFO - __main__ - Step 97552: {'lr': 0.00013958174314698718, 'samples': 18729984, 'steps': 97551, 'loss/train': 1.0275810956954956} 08/31/2021 06:52:35 - INFO - __main__ - Step 97553: {'lr': 0.00013957698208771864, 'samples': 18730176, 'steps': 97552, 'loss/train': 1.190460205078125} 08/31/2021 06:52:36 - INFO - __main__ - Step 97554: {'lr': 0.000139572221078205, 'samples': 18730368, 'steps': 97553, 'loss/train': 1.7927215099334717} 08/31/2021 06:52:37 - INFO - __main__ - Step 97555: {'lr': 0.00013956746011844842, 'samples': 18730560, 'steps': 97554, 'loss/train': 1.219691276550293} 08/31/2021 06:52:37 - INFO - __main__ - Step 97556: {'lr': 0.00013956269920845104, 'samples': 18730752, 'steps': 97555, 'loss/train': 1.4044474363327026} 08/31/2021 06:52:37 - INFO - __main__ - Step 97557: {'lr': 0.000139557938348215, 'samples': 18730944, 'steps': 97556, 'loss/train': 0.8399431109428406} 08/31/2021 06:52:38 - INFO - __main__ - Step 97558: {'lr': 0.00013955317753774243, 'samples': 18731136, 'steps': 97557, 'loss/train': 1.5754634141921997} 08/31/2021 06:52:40 - INFO - __main__ - Step 97559: {'lr': 0.00013954841677703565, 'samples': 18731328, 'steps': 97558, 'loss/train': 1.4063475131988525} 08/31/2021 06:52:40 - INFO - __main__ - Step 97560: {'lr': 0.00013954365606609647, 'samples': 18731520, 'steps': 97559, 'loss/train': 0.3172362744808197} 08/31/2021 06:52:41 - INFO - __main__ - Step 97561: {'lr': 0.0001395388954049273, 'samples': 18731712, 'steps': 97560, 'loss/train': 0.21759621798992157} 08/31/2021 06:52:41 - INFO - __main__ - Step 97562: {'lr': 0.00013953413479353015, 'samples': 18731904, 'steps': 97561, 'loss/train': 1.8575384616851807} 08/31/2021 06:52:41 - INFO - __main__ - Step 97563: {'lr': 0.0001395293742319072, 'samples': 18732096, 'steps': 97562, 'loss/train': 1.8133410215377808} 08/31/2021 06:52:43 - INFO - __main__ - Step 97564: {'lr': 0.00013952461372006064, 'samples': 18732288, 'steps': 97563, 'loss/train': 1.2526441812515259} 08/31/2021 06:52:43 - INFO - __main__ - Step 97565: {'lr': 0.00013951985325799259, 'samples': 18732480, 'steps': 97564, 'loss/train': 1.0263575315475464} 08/31/2021 06:52:44 - INFO - __main__ - Step 97566: {'lr': 0.00013951509284570516, 'samples': 18732672, 'steps': 97565, 'loss/train': 0.49625861644744873} 08/31/2021 06:52:44 - INFO - __main__ - Step 97567: {'lr': 0.00013951033248320056, 'samples': 18732864, 'steps': 97566, 'loss/train': 1.1984443664550781} 08/31/2021 06:52:44 - INFO - __main__ - Step 97568: {'lr': 0.0001395055721704809, 'samples': 18733056, 'steps': 97567, 'loss/train': 1.3429123163223267} 08/31/2021 06:52:46 - INFO - __main__ - Step 97569: {'lr': 0.00013950081190754828, 'samples': 18733248, 'steps': 97568, 'loss/train': 1.5182385444641113} 08/31/2021 06:52:46 - INFO - __main__ - Step 97570: {'lr': 0.000139496051694405, 'samples': 18733440, 'steps': 97569, 'loss/train': 1.2317242622375488} 08/31/2021 06:52:47 - INFO - __main__ - Step 97571: {'lr': 0.000139491291531053, 'samples': 18733632, 'steps': 97570, 'loss/train': 0.7106318473815918} 08/31/2021 06:52:47 - INFO - __main__ - Step 97572: {'lr': 0.0001394865314174945, 'samples': 18733824, 'steps': 97571, 'loss/train': 1.6811907291412354} 08/31/2021 06:52:47 - INFO - __main__ - Step 97573: {'lr': 0.0001394817713537317, 'samples': 18734016, 'steps': 97572, 'loss/train': 2.1113858222961426} 08/31/2021 06:52:49 - INFO - __main__ - Step 97574: {'lr': 0.0001394770113397667, 'samples': 18734208, 'steps': 97573, 'loss/train': 0.45177164673805237} 08/31/2021 06:52:50 - INFO - __main__ - Step 97575: {'lr': 0.00013947225137560164, 'samples': 18734400, 'steps': 97574, 'loss/train': 1.0263841152191162} 08/31/2021 06:52:50 - INFO - __main__ - Step 97576: {'lr': 0.0001394674914612387, 'samples': 18734592, 'steps': 97575, 'loss/train': 1.0837531089782715} 08/31/2021 06:52:50 - INFO - __main__ - Step 97577: {'lr': 0.00013946273159668, 'samples': 18734784, 'steps': 97576, 'loss/train': 0.9265400767326355} 08/31/2021 06:52:51 - INFO - __main__ - Step 97578: {'lr': 0.00013945797178192766, 'samples': 18734976, 'steps': 97577, 'loss/train': 0.031317684799432755} 08/31/2021 06:52:51 - INFO - __main__ - Step 97579: {'lr': 0.00013945321201698385, 'samples': 18735168, 'steps': 97578, 'loss/train': 0.1578989177942276} 08/31/2021 06:52:53 - INFO - __main__ - Step 97580: {'lr': 0.00013944845230185078, 'samples': 18735360, 'steps': 97579, 'loss/train': 1.33429753780365} 08/31/2021 06:52:53 - INFO - __main__ - Step 97581: {'lr': 0.00013944369263653057, 'samples': 18735552, 'steps': 97580, 'loss/train': 1.533647060394287} 08/31/2021 06:52:54 - INFO - __main__ - Step 97582: {'lr': 0.00013943893302102522, 'samples': 18735744, 'steps': 97581, 'loss/train': 1.1411535739898682} 08/31/2021 06:52:54 - INFO - __main__ - Step 97583: {'lr': 0.00013943417345533703, 'samples': 18735936, 'steps': 97582, 'loss/train': 0.8943918943405151} 08/31/2021 06:52:54 - INFO - __main__ - Step 97584: {'lr': 0.00013942941393946807, 'samples': 18736128, 'steps': 97583, 'loss/train': 0.5642243027687073} 08/31/2021 06:52:56 - INFO - __main__ - Step 97585: {'lr': 0.0001394246544734205, 'samples': 18736320, 'steps': 97584, 'loss/train': 1.6836594343185425} 08/31/2021 06:52:56 - INFO - __main__ - Step 97586: {'lr': 0.0001394198950571965, 'samples': 18736512, 'steps': 97585, 'loss/train': 0.7453308701515198} 08/31/2021 06:52:57 - INFO - __main__ - Step 97587: {'lr': 0.00013941513569079816, 'samples': 18736704, 'steps': 97586, 'loss/train': 1.0312883853912354} 08/31/2021 06:52:57 - INFO - __main__ - Step 97588: {'lr': 0.00013941037637422765, 'samples': 18736896, 'steps': 97587, 'loss/train': 1.3001996278762817} 08/31/2021 06:52:57 - INFO - __main__ - Step 97589: {'lr': 0.00013940561710748715, 'samples': 18737088, 'steps': 97588, 'loss/train': 1.2961211204528809} 08/31/2021 06:52:58 - INFO - __main__ - Step 97590: {'lr': 0.00013940085789057875, 'samples': 18737280, 'steps': 97589, 'loss/train': 1.1955962181091309} 08/31/2021 06:52:59 - INFO - __main__ - Step 97591: {'lr': 0.00013939609872350462, 'samples': 18737472, 'steps': 97590, 'loss/train': 1.2051669359207153} 08/31/2021 06:53:00 - INFO - __main__ - Step 97592: {'lr': 0.00013939133960626698, 'samples': 18737664, 'steps': 97591, 'loss/train': 1.3041479587554932} 08/31/2021 06:53:00 - INFO - __main__ - Step 97593: {'lr': 0.00013938658053886782, 'samples': 18737856, 'steps': 97592, 'loss/train': 1.5469448566436768} 08/31/2021 06:53:00 - INFO - __main__ - Step 97594: {'lr': 0.00013938182152130937, 'samples': 18738048, 'steps': 97593, 'loss/train': 0.9192095994949341} 08/31/2021 06:53:01 - INFO - __main__ - Step 97595: {'lr': 0.00013937706255359378, 'samples': 18738240, 'steps': 97594, 'loss/train': 1.4843825101852417} 08/31/2021 06:53:02 - INFO - __main__ - Step 97596: {'lr': 0.0001393723036357231, 'samples': 18738432, 'steps': 97595, 'loss/train': 1.5690397024154663} 08/31/2021 06:53:03 - INFO - __main__ - Step 97597: {'lr': 0.00013936754476769964, 'samples': 18738624, 'steps': 97596, 'loss/train': 1.3012034893035889} 08/31/2021 06:53:03 - INFO - __main__ - Step 97598: {'lr': 0.00013936278594952543, 'samples': 18738816, 'steps': 97597, 'loss/train': 1.1554343700408936} 08/31/2021 06:53:03 - INFO - __main__ - Step 97599: {'lr': 0.00013935802718120262, 'samples': 18739008, 'steps': 97598, 'loss/train': 1.2824627161026} 08/31/2021 06:53:04 - INFO - __main__ - Step 97600: {'lr': 0.00013935326846273337, 'samples': 18739200, 'steps': 97599, 'loss/train': 1.4327998161315918} 08/31/2021 06:53:05 - INFO - __main__ - Step 97601: {'lr': 0.0001393485097941199, 'samples': 18739392, 'steps': 97600, 'loss/train': 1.0207302570343018} 08/31/2021 06:53:06 - INFO - __main__ - Step 97602: {'lr': 0.0001393437511753642, 'samples': 18739584, 'steps': 97601, 'loss/train': 0.6300545334815979} 08/31/2021 06:53:06 - INFO - __main__ - Step 97603: {'lr': 0.00013933899260646864, 'samples': 18739776, 'steps': 97602, 'loss/train': 1.557440161705017} 08/31/2021 06:53:06 - INFO - __main__ - Step 97604: {'lr': 0.0001393342340874351, 'samples': 18739968, 'steps': 97603, 'loss/train': 0.03696886822581291} 08/31/2021 06:53:07 - INFO - __main__ - Step 97605: {'lr': 0.00013932947561826588, 'samples': 18740160, 'steps': 97604, 'loss/train': 0.7872570157051086} 08/31/2021 06:53:09 - INFO - __main__ - Step 97606: {'lr': 0.00013932471719896306, 'samples': 18740352, 'steps': 97605, 'loss/train': 1.2624166011810303} 08/31/2021 06:53:09 - INFO - __main__ - Step 97607: {'lr': 0.00013931995882952882, 'samples': 18740544, 'steps': 97606, 'loss/train': 1.164880394935608} 08/31/2021 06:53:10 - INFO - __main__ - Step 97608: {'lr': 0.0001393152005099653, 'samples': 18740736, 'steps': 97607, 'loss/train': 0.07259541004896164} 08/31/2021 06:53:10 - INFO - __main__ - Step 97609: {'lr': 0.00013931044224027467, 'samples': 18740928, 'steps': 97608, 'loss/train': 0.2742314636707306} 08/31/2021 06:53:10 - INFO - __main__ - Step 97610: {'lr': 0.000139305684020459, 'samples': 18741120, 'steps': 97609, 'loss/train': 1.6086063385009766} 08/31/2021 06:53:13 - INFO - __main__ - Step 97611: {'lr': 0.00013930092585052052, 'samples': 18741312, 'steps': 97610, 'loss/train': 0.6157779097557068} 08/31/2021 06:53:13 - INFO - __main__ - Step 97612: {'lr': 0.00013929616773046135, 'samples': 18741504, 'steps': 97611, 'loss/train': 1.7820258140563965} 08/31/2021 06:53:14 - INFO - __main__ - Step 97613: {'lr': 0.00013929140966028355, 'samples': 18741696, 'steps': 97612, 'loss/train': 0.8602588772773743} 08/31/2021 06:53:14 - INFO - __main__ - Step 97614: {'lr': 0.0001392866516399895, 'samples': 18741888, 'steps': 97613, 'loss/train': 0.014856034889817238} 08/31/2021 06:53:14 - INFO - __main__ - Step 97615: {'lr': 0.00013928189366958101, 'samples': 18742080, 'steps': 97614, 'loss/train': 0.7576903104782104} 08/31/2021 06:53:15 - INFO - __main__ - Step 97616: {'lr': 0.00013927713574906042, 'samples': 18742272, 'steps': 97615, 'loss/train': 1.4341623783111572} 08/31/2021 06:53:16 - INFO - __main__ - Step 97617: {'lr': 0.00013927237787842987, 'samples': 18742464, 'steps': 97616, 'loss/train': 1.285928726196289} 08/31/2021 06:53:17 - INFO - __main__ - Step 97618: {'lr': 0.00013926762005769144, 'samples': 18742656, 'steps': 97617, 'loss/train': 1.0470346212387085} 08/31/2021 06:53:17 - INFO - __main__ - Step 97619: {'lr': 0.00013926286228684734, 'samples': 18742848, 'steps': 97618, 'loss/train': 0.19429562985897064} 08/31/2021 06:53:17 - INFO - __main__ - Step 97620: {'lr': 0.00013925810456589968, 'samples': 18743040, 'steps': 97619, 'loss/train': 1.1300079822540283} 08/31/2021 06:53:18 - INFO - __main__ - Step 97621: {'lr': 0.00013925334689485062, 'samples': 18743232, 'steps': 97620, 'loss/train': 0.6351122856140137} 08/31/2021 06:53:19 - INFO - __main__ - Step 97622: {'lr': 0.00013924858927370225, 'samples': 18743424, 'steps': 97621, 'loss/train': 1.3460350036621094} 08/31/2021 06:53:20 - INFO - __main__ - Step 97623: {'lr': 0.0001392438317024568, 'samples': 18743616, 'steps': 97622, 'loss/train': 1.4623976945877075} 08/31/2021 06:53:20 - INFO - __main__ - Step 97624: {'lr': 0.00013923907418111637, 'samples': 18743808, 'steps': 97623, 'loss/train': 1.0440319776535034} 08/31/2021 06:53:20 - INFO - __main__ - Step 97625: {'lr': 0.00013923431670968307, 'samples': 18744000, 'steps': 97624, 'loss/train': 1.2690694332122803} 08/31/2021 06:53:21 - INFO - __main__ - Step 97626: {'lr': 0.00013922955928815913, 'samples': 18744192, 'steps': 97625, 'loss/train': 1.1743528842926025} 08/31/2021 06:53:22 - INFO - __main__ - Step 97627: {'lr': 0.0001392248019165467, 'samples': 18744384, 'steps': 97626, 'loss/train': 1.372482180595398} 08/31/2021 06:53:23 - INFO - __main__ - Step 97628: {'lr': 0.00013922004459484774, 'samples': 18744576, 'steps': 97627, 'loss/train': 0.7585979104042053} 08/31/2021 06:53:23 - INFO - __main__ - Step 97629: {'lr': 0.00013921528732306455, 'samples': 18744768, 'steps': 97628, 'loss/train': 0.961385190486908} 08/31/2021 06:53:23 - INFO - __main__ - Step 97630: {'lr': 0.00013921053010119928, 'samples': 18744960, 'steps': 97629, 'loss/train': 1.3935775756835938} 08/31/2021 06:53:24 - INFO - __main__ - Step 97631: {'lr': 0.00013920577292925396, 'samples': 18745152, 'steps': 97630, 'loss/train': 0.9386054277420044} 08/31/2021 06:53:25 - INFO - __main__ - Step 97632: {'lr': 0.0001392010158072309, 'samples': 18745344, 'steps': 97631, 'loss/train': 0.9412724375724792} 08/31/2021 06:53:26 - INFO - __main__ - Step 97633: {'lr': 0.00013919625873513205, 'samples': 18745536, 'steps': 97632, 'loss/train': 1.2573379278182983} 08/31/2021 06:53:26 - INFO - __main__ - Step 97634: {'lr': 0.00013919150171295971, 'samples': 18745728, 'steps': 97633, 'loss/train': 0.5463159084320068} 08/31/2021 06:53:27 - INFO - __main__ - Step 97635: {'lr': 0.00013918674474071597, 'samples': 18745920, 'steps': 97634, 'loss/train': 1.1684556007385254} 08/31/2021 06:53:27 - INFO - __main__ - Step 97636: {'lr': 0.00013918198781840297, 'samples': 18746112, 'steps': 97635, 'loss/train': 0.15228131413459778} 08/31/2021 06:53:27 - INFO - __main__ - Step 97637: {'lr': 0.00013917723094602287, 'samples': 18746304, 'steps': 97636, 'loss/train': 1.324122667312622} 08/31/2021 06:53:29 - INFO - __main__ - Step 97638: {'lr': 0.00013917247412357776, 'samples': 18746496, 'steps': 97637, 'loss/train': 5.772827625274658} 08/31/2021 06:53:29 - INFO - __main__ - Step 97639: {'lr': 0.00013916771735106987, 'samples': 18746688, 'steps': 97638, 'loss/train': 1.445906400680542} 08/31/2021 06:53:30 - INFO - __main__ - Step 97640: {'lr': 0.00013916296062850125, 'samples': 18746880, 'steps': 97639, 'loss/train': 1.0206884145736694} 08/31/2021 06:53:30 - INFO - __main__ - Step 97641: {'lr': 0.00013915820395587423, 'samples': 18747072, 'steps': 97640, 'loss/train': 0.5611047744750977} 08/31/2021 06:53:30 - INFO - __main__ - Step 97642: {'lr': 0.00013915344733319069, 'samples': 18747264, 'steps': 97641, 'loss/train': 1.4660279750823975} 08/31/2021 06:53:32 - INFO - __main__ - Step 97643: {'lr': 0.0001391486907604529, 'samples': 18747456, 'steps': 97642, 'loss/train': 0.9195386171340942} 08/31/2021 06:53:33 - INFO - __main__ - Step 97644: {'lr': 0.000139143934237663, 'samples': 18747648, 'steps': 97643, 'loss/train': 1.4590280055999756} 08/31/2021 06:53:33 - INFO - __main__ - Step 97645: {'lr': 0.00013913917776482316, 'samples': 18747840, 'steps': 97644, 'loss/train': 1.4889341592788696} 08/31/2021 06:53:33 - INFO - __main__ - Step 97646: {'lr': 0.00013913442134193545, 'samples': 18748032, 'steps': 97645, 'loss/train': 1.1503760814666748} 08/31/2021 06:53:34 - INFO - __main__ - Step 97647: {'lr': 0.00013912966496900208, 'samples': 18748224, 'steps': 97646, 'loss/train': 1.3534141778945923} 08/31/2021 06:53:34 - INFO - __main__ - Step 97648: {'lr': 0.00013912490864602517, 'samples': 18748416, 'steps': 97647, 'loss/train': 1.4595859050750732} 08/31/2021 06:53:36 - INFO - __main__ - Step 97649: {'lr': 0.00013912015237300688, 'samples': 18748608, 'steps': 97648, 'loss/train': 1.671081781387329} 08/31/2021 06:53:36 - INFO - __main__ - Step 97650: {'lr': 0.0001391153961499493, 'samples': 18748800, 'steps': 97649, 'loss/train': 0.9167097210884094} 08/31/2021 06:53:36 - INFO - __main__ - Step 97651: {'lr': 0.00013911063997685465, 'samples': 18748992, 'steps': 97650, 'loss/train': 0.1587981879711151} 08/31/2021 06:53:37 - INFO - __main__ - Step 97652: {'lr': 0.00013910588385372504, 'samples': 18749184, 'steps': 97651, 'loss/train': 1.546136736869812} 08/31/2021 06:53:37 - INFO - __main__ - Step 97653: {'lr': 0.00013910112778056256, 'samples': 18749376, 'steps': 97652, 'loss/train': 1.384310245513916} 08/31/2021 06:53:39 - INFO - __main__ - Step 97654: {'lr': 0.00013909637175736956, 'samples': 18749568, 'steps': 97653, 'loss/train': 0.04428679496049881} 08/31/2021 06:53:39 - INFO - __main__ - Step 97655: {'lr': 0.00013909161578414786, 'samples': 18749760, 'steps': 97654, 'loss/train': 0.7394151091575623} 08/31/2021 06:53:40 - INFO - __main__ - Step 97656: {'lr': 0.0001390868598608998, 'samples': 18749952, 'steps': 97655, 'loss/train': 0.9641868472099304} 08/31/2021 06:53:40 - INFO - __main__ - Step 97657: {'lr': 0.0001390821039876275, 'samples': 18750144, 'steps': 97656, 'loss/train': 1.5453636646270752} 08/31/2021 06:53:40 - INFO - __main__ - Step 97658: {'lr': 0.0001390773481643331, 'samples': 18750336, 'steps': 97657, 'loss/train': 0.6656479239463806} 08/31/2021 06:53:41 - INFO - __main__ - Step 97659: {'lr': 0.0001390725923910187, 'samples': 18750528, 'steps': 97658, 'loss/train': 1.2871137857437134} 08/31/2021 06:53:42 - INFO - __main__ - Step 97660: {'lr': 0.00013906783666768648, 'samples': 18750720, 'steps': 97659, 'loss/train': 1.4042673110961914} 08/31/2021 06:53:43 - INFO - __main__ - Step 97661: {'lr': 0.00013906308099433863, 'samples': 18750912, 'steps': 97660, 'loss/train': 1.128169059753418} 08/31/2021 06:53:43 - INFO - __main__ - Step 97662: {'lr': 0.0001390583253709772, 'samples': 18751104, 'steps': 97661, 'loss/train': 0.9472292065620422} 08/31/2021 06:53:44 - INFO - __main__ - Step 97663: {'lr': 0.00013905356979760438, 'samples': 18751296, 'steps': 97662, 'loss/train': 1.0518563985824585} 08/31/2021 06:53:44 - INFO - __main__ - Step 97664: {'lr': 0.0001390488142742223, 'samples': 18751488, 'steps': 97663, 'loss/train': 0.44829925894737244} 08/31/2021 06:53:45 - INFO - __main__ - Step 97665: {'lr': 0.00013904405880083316, 'samples': 18751680, 'steps': 97664, 'loss/train': 0.4754858911037445} 08/31/2021 06:53:46 - INFO - __main__ - Step 97666: {'lr': 0.000139039303377439, 'samples': 18751872, 'steps': 97665, 'loss/train': 0.8978282809257507} 08/31/2021 06:53:46 - INFO - __main__ - Step 97667: {'lr': 0.00013903454800404203, 'samples': 18752064, 'steps': 97666, 'loss/train': 1.056471347808838} 08/31/2021 06:53:47 - INFO - __main__ - Step 97668: {'lr': 0.0001390297926806445, 'samples': 18752256, 'steps': 97667, 'loss/train': 0.6428348422050476} 08/31/2021 06:53:47 - INFO - __main__ - Step 97669: {'lr': 0.0001390250374072483, 'samples': 18752448, 'steps': 97668, 'loss/train': 0.8847025632858276} 08/31/2021 06:53:49 - INFO - __main__ - Step 97670: {'lr': 0.00013902028218385577, 'samples': 18752640, 'steps': 97669, 'loss/train': 0.1326296180486679} 08/31/2021 06:53:49 - INFO - __main__ - Step 97671: {'lr': 0.00013901552701046894, 'samples': 18752832, 'steps': 97670, 'loss/train': 0.8432947397232056} 08/31/2021 06:53:50 - INFO - __main__ - Step 97672: {'lr': 0.00013901077188708998, 'samples': 18753024, 'steps': 97671, 'loss/train': 1.473740816116333} 08/31/2021 06:53:50 - INFO - __main__ - Step 97673: {'lr': 0.0001390060168137211, 'samples': 18753216, 'steps': 97672, 'loss/train': 1.1646394729614258} 08/31/2021 06:53:50 - INFO - __main__ - Step 97674: {'lr': 0.00013900126179036438, 'samples': 18753408, 'steps': 97673, 'loss/train': 0.9183560609817505} 08/31/2021 06:53:52 - INFO - __main__ - Step 97675: {'lr': 0.00013899650681702198, 'samples': 18753600, 'steps': 97674, 'loss/train': 0.8586871027946472} 08/31/2021 06:53:53 - INFO - __main__ - Step 97676: {'lr': 0.00013899175189369603, 'samples': 18753792, 'steps': 97675, 'loss/train': 0.42828795313835144} 08/31/2021 06:53:53 - INFO - __main__ - Step 97677: {'lr': 0.0001389869970203887, 'samples': 18753984, 'steps': 97676, 'loss/train': 0.5768201947212219} 08/31/2021 06:53:53 - INFO - __main__ - Step 97678: {'lr': 0.0001389822421971021, 'samples': 18754176, 'steps': 97677, 'loss/train': 1.4135162830352783} 08/31/2021 06:53:54 - INFO - __main__ - Step 97679: {'lr': 0.0001389774874238384, 'samples': 18754368, 'steps': 97678, 'loss/train': 1.8099250793457031} 08/31/2021 06:53:55 - INFO - __main__ - Step 97680: {'lr': 0.00013897273270059975, 'samples': 18754560, 'steps': 97679, 'loss/train': 0.22394365072250366} 08/31/2021 06:53:56 - INFO - __main__ - Step 97681: {'lr': 0.0001389679780273883, 'samples': 18754752, 'steps': 97680, 'loss/train': 1.3907262086868286} 08/31/2021 06:53:56 - INFO - __main__ - Step 97682: {'lr': 0.00013896322340420614, 'samples': 18754944, 'steps': 97681, 'loss/train': 0.9354373216629028} 08/31/2021 06:53:56 - INFO - __main__ - Step 97683: {'lr': 0.0001389584688310554, 'samples': 18755136, 'steps': 97682, 'loss/train': 0.7794594764709473} 08/31/2021 06:53:57 - INFO - __main__ - Step 97684: {'lr': 0.0001389537143079383, 'samples': 18755328, 'steps': 97683, 'loss/train': 1.656326413154602} 08/31/2021 06:53:57 - INFO - __main__ - Step 97685: {'lr': 0.0001389489598348569, 'samples': 18755520, 'steps': 97684, 'loss/train': 1.072802186012268} 08/31/2021 06:53:59 - INFO - __main__ - Step 97686: {'lr': 0.0001389442054118134, 'samples': 18755712, 'steps': 97685, 'loss/train': 1.4678914546966553} 08/31/2021 06:53:59 - INFO - __main__ - Step 97687: {'lr': 0.00013893945103880996, 'samples': 18755904, 'steps': 97686, 'loss/train': 1.510437250137329} 08/31/2021 06:54:00 - INFO - __main__ - Step 97688: {'lr': 0.00013893469671584862, 'samples': 18756096, 'steps': 97687, 'loss/train': 1.1749451160430908} 08/31/2021 06:54:00 - INFO - __main__ - Step 97689: {'lr': 0.00013892994244293168, 'samples': 18756288, 'steps': 97688, 'loss/train': 1.3661314249038696} 08/31/2021 06:54:00 - INFO - __main__ - Step 97690: {'lr': 0.00013892518822006112, 'samples': 18756480, 'steps': 97689, 'loss/train': 1.5327280759811401} 08/31/2021 06:54:02 - INFO - __main__ - Step 97691: {'lr': 0.0001389204340472392, 'samples': 18756672, 'steps': 97690, 'loss/train': 1.2128663063049316} 08/31/2021 06:54:02 - INFO - __main__ - Step 97692: {'lr': 0.00013891567992446797, 'samples': 18756864, 'steps': 97691, 'loss/train': 0.6468807458877563} 08/31/2021 06:54:03 - INFO - __main__ - Step 97693: {'lr': 0.00013891092585174966, 'samples': 18757056, 'steps': 97692, 'loss/train': 0.7763208746910095} 08/31/2021 06:54:03 - INFO - __main__ - Step 97694: {'lr': 0.0001389061718290864, 'samples': 18757248, 'steps': 97693, 'loss/train': 1.3321106433868408} 08/31/2021 06:54:03 - INFO - __main__ - Step 97695: {'lr': 0.00013890141785648032, 'samples': 18757440, 'steps': 97694, 'loss/train': 1.027971863746643} 08/31/2021 06:54:05 - INFO - __main__ - Step 97696: {'lr': 0.00013889666393393353, 'samples': 18757632, 'steps': 97695, 'loss/train': 1.0658155679702759} 08/31/2021 06:54:05 - INFO - __main__ - Step 97697: {'lr': 0.00013889191006144814, 'samples': 18757824, 'steps': 97696, 'loss/train': 1.2794243097305298} 08/31/2021 06:54:06 - INFO - __main__ - Step 97698: {'lr': 0.00013888715623902633, 'samples': 18758016, 'steps': 97697, 'loss/train': 1.0002516508102417} 08/31/2021 06:54:06 - INFO - __main__ - Step 97699: {'lr': 0.00013888240246667026, 'samples': 18758208, 'steps': 97698, 'loss/train': 0.9303688406944275} 08/31/2021 06:54:06 - INFO - __main__ - Step 97700: {'lr': 0.00013887764874438214, 'samples': 18758400, 'steps': 97699, 'loss/train': 1.3736759424209595} 08/31/2021 06:54:08 - INFO - __main__ - Step 97701: {'lr': 0.00013887289507216394, 'samples': 18758592, 'steps': 97700, 'loss/train': 1.1403731107711792} 08/31/2021 06:54:08 - INFO - __main__ - Step 97702: {'lr': 0.00013886814145001796, 'samples': 18758784, 'steps': 97701, 'loss/train': 1.128007173538208} 08/31/2021 06:54:09 - INFO - __main__ - Step 97703: {'lr': 0.00013886338787794626, 'samples': 18758976, 'steps': 97702, 'loss/train': 1.0648292303085327} 08/31/2021 06:54:09 - INFO - __main__ - Step 97704: {'lr': 0.00013885863435595096, 'samples': 18759168, 'steps': 97703, 'loss/train': 1.6563620567321777} 08/31/2021 06:54:09 - INFO - __main__ - Step 97705: {'lr': 0.00013885388088403434, 'samples': 18759360, 'steps': 97704, 'loss/train': 1.3159780502319336} 08/31/2021 06:54:11 - INFO - __main__ - Step 97706: {'lr': 0.00013884912746219835, 'samples': 18759552, 'steps': 97705, 'loss/train': 1.6459598541259766} 08/31/2021 06:54:11 - INFO - __main__ - Step 97707: {'lr': 0.00013884437409044528, 'samples': 18759744, 'steps': 97706, 'loss/train': 1.0295315980911255} 08/31/2021 06:54:12 - INFO - __main__ - Step 97708: {'lr': 0.00013883962076877731, 'samples': 18759936, 'steps': 97707, 'loss/train': 0.20290425419807434} 08/31/2021 06:54:12 - INFO - __main__ - Step 97709: {'lr': 0.0001388348674971964, 'samples': 18760128, 'steps': 97708, 'loss/train': 1.027890682220459} 08/31/2021 06:54:13 - INFO - __main__ - Step 97710: {'lr': 0.00013883011427570478, 'samples': 18760320, 'steps': 97709, 'loss/train': 1.1067928075790405} 08/31/2021 06:54:14 - INFO - __main__ - Step 97711: {'lr': 0.00013882536110430458, 'samples': 18760512, 'steps': 97710, 'loss/train': 0.6216490268707275} 08/31/2021 06:54:15 - INFO - __main__ - Step 97712: {'lr': 0.00013882060798299796, 'samples': 18760704, 'steps': 97711, 'loss/train': 1.1019866466522217} 08/31/2021 06:54:15 - INFO - __main__ - Step 97713: {'lr': 0.00013881585491178707, 'samples': 18760896, 'steps': 97712, 'loss/train': 1.3326668739318848} 08/31/2021 06:54:15 - INFO - __main__ - Step 97714: {'lr': 0.00013881110189067404, 'samples': 18761088, 'steps': 97713, 'loss/train': 0.960745096206665} 08/31/2021 06:54:16 - INFO - __main__ - Step 97715: {'lr': 0.00013880634891966099, 'samples': 18761280, 'steps': 97714, 'loss/train': 1.7315795421600342} 08/31/2021 06:54:16 - INFO - __main__ - Step 97716: {'lr': 0.00013880159599875008, 'samples': 18761472, 'steps': 97715, 'loss/train': 1.4298615455627441} 08/31/2021 06:54:18 - INFO - __main__ - Step 97717: {'lr': 0.0001387968431279435, 'samples': 18761664, 'steps': 97716, 'loss/train': 1.1588643789291382} 08/31/2021 06:54:18 - INFO - __main__ - Step 97718: {'lr': 0.00013879209030724331, 'samples': 18761856, 'steps': 97717, 'loss/train': 1.189727783203125} 08/31/2021 06:54:18 - INFO - __main__ - Step 97719: {'lr': 0.0001387873375366517, 'samples': 18762048, 'steps': 97718, 'loss/train': 1.038447380065918} 08/31/2021 06:54:19 - INFO - __main__ - Step 97720: {'lr': 0.00013878258481617078, 'samples': 18762240, 'steps': 97719, 'loss/train': 1.145986795425415} 08/31/2021 06:54:19 - INFO - __main__ - Step 97721: {'lr': 0.00013877783214580276, 'samples': 18762432, 'steps': 97720, 'loss/train': 1.2624365091323853} 08/31/2021 06:54:21 - INFO - __main__ - Step 97722: {'lr': 0.0001387730795255498, 'samples': 18762624, 'steps': 97721, 'loss/train': 1.1630510091781616} 08/31/2021 06:54:22 - INFO - __main__ - Step 97723: {'lr': 0.00013876832695541386, 'samples': 18762816, 'steps': 97722, 'loss/train': 1.0547375679016113} 08/31/2021 06:54:22 - INFO - __main__ - Step 97724: {'lr': 0.00013876357443539722, 'samples': 18763008, 'steps': 97723, 'loss/train': 1.352134108543396} 08/31/2021 06:54:22 - INFO - __main__ - Step 97725: {'lr': 0.00013875882196550199, 'samples': 18763200, 'steps': 97724, 'loss/train': 1.2767229080200195} 08/31/2021 06:54:23 - INFO - __main__ - Step 97726: {'lr': 0.00013875406954573033, 'samples': 18763392, 'steps': 97725, 'loss/train': 1.6422086954116821} 08/31/2021 06:54:23 - INFO - __main__ - Step 97727: {'lr': 0.00013874931717608436, 'samples': 18763584, 'steps': 97726, 'loss/train': 1.2320739030838013} 08/31/2021 06:54:25 - INFO - __main__ - Step 97728: {'lr': 0.00013874456485656622, 'samples': 18763776, 'steps': 97727, 'loss/train': 1.0158438682556152} 08/31/2021 06:54:25 - INFO - __main__ - Step 97729: {'lr': 0.00013873981258717805, 'samples': 18763968, 'steps': 97728, 'loss/train': 1.8082863092422485} 08/31/2021 06:54:25 - INFO - __main__ - Step 97730: {'lr': 0.00013873506036792205, 'samples': 18764160, 'steps': 97729, 'loss/train': 1.932920217514038} 08/31/2021 06:54:26 - INFO - __main__ - Step 97731: {'lr': 0.00013873030819880027, 'samples': 18764352, 'steps': 97730, 'loss/train': 1.354712724685669} 08/31/2021 06:54:26 - INFO - __main__ - Step 97732: {'lr': 0.0001387255560798149, 'samples': 18764544, 'steps': 97731, 'loss/train': 0.8436786532402039} 08/31/2021 06:54:28 - INFO - __main__ - Step 97733: {'lr': 0.0001387208040109681, 'samples': 18764736, 'steps': 97732, 'loss/train': 1.0242440700531006} 08/31/2021 06:54:28 - INFO - __main__ - Step 97734: {'lr': 0.000138716051992262, 'samples': 18764928, 'steps': 97733, 'loss/train': 1.5689270496368408} 08/31/2021 06:54:28 - INFO - __main__ - Step 97735: {'lr': 0.0001387113000236988, 'samples': 18765120, 'steps': 97734, 'loss/train': 0.64021235704422} 08/31/2021 06:54:29 - INFO - __main__ - Step 97736: {'lr': 0.0001387065481052805, 'samples': 18765312, 'steps': 97735, 'loss/train': 0.1455928236246109} 08/31/2021 06:54:29 - INFO - __main__ - Step 97737: {'lr': 0.00013870179623700927, 'samples': 18765504, 'steps': 97736, 'loss/train': 1.2255101203918457} 08/31/2021 06:54:31 - INFO - __main__ - Step 97738: {'lr': 0.00013869704441888731, 'samples': 18765696, 'steps': 97737, 'loss/train': 0.8982796669006348} 08/31/2021 06:54:31 - INFO - __main__ - Step 97739: {'lr': 0.00013869229265091676, 'samples': 18765888, 'steps': 97738, 'loss/train': 1.2269699573516846} 08/31/2021 06:54:32 - INFO - __main__ - Step 97740: {'lr': 0.00013868754093309974, 'samples': 18766080, 'steps': 97739, 'loss/train': 1.1017898321151733} 08/31/2021 06:54:32 - INFO - __main__ - Step 97741: {'lr': 0.00013868278926543838, 'samples': 18766272, 'steps': 97740, 'loss/train': 1.8855713605880737} 08/31/2021 06:54:32 - INFO - __main__ - Step 97742: {'lr': 0.00013867803764793486, 'samples': 18766464, 'steps': 97741, 'loss/train': 0.2912074625492096} 08/31/2021 06:54:33 - INFO - __main__ - Step 97743: {'lr': 0.00013867328608059126, 'samples': 18766656, 'steps': 97742, 'loss/train': 1.692962408065796} 08/31/2021 06:54:34 - INFO - __main__ - Step 97744: {'lr': 0.0001386685345634098, 'samples': 18766848, 'steps': 97743, 'loss/train': 1.4566199779510498} 08/31/2021 06:54:35 - INFO - __main__ - Step 97745: {'lr': 0.00013866378309639258, 'samples': 18767040, 'steps': 97744, 'loss/train': 1.4056885242462158} 08/31/2021 06:54:35 - INFO - __main__ - Step 97746: {'lr': 0.0001386590316795417, 'samples': 18767232, 'steps': 97745, 'loss/train': 1.2473738193511963} 08/31/2021 06:54:35 - INFO - __main__ - Step 97747: {'lr': 0.0001386542803128594, 'samples': 18767424, 'steps': 97746, 'loss/train': 0.796715497970581} 08/31/2021 06:54:36 - INFO - __main__ - Step 97748: {'lr': 0.00013864952899634783, 'samples': 18767616, 'steps': 97747, 'loss/train': 0.6236863136291504} 08/31/2021 06:54:37 - INFO - __main__ - Step 97749: {'lr': 0.00013864477773000897, 'samples': 18767808, 'steps': 97748, 'loss/train': 1.5751103162765503} 08/31/2021 06:54:38 - INFO - __main__ - Step 97750: {'lr': 0.00013864002651384506, 'samples': 18768000, 'steps': 97749, 'loss/train': 1.4631153345108032} 08/31/2021 06:54:38 - INFO - __main__ - Step 97751: {'lr': 0.00013863527534785822, 'samples': 18768192, 'steps': 97750, 'loss/train': 1.257948875427246} 08/31/2021 06:54:38 - INFO - __main__ - Step 97752: {'lr': 0.00013863052423205064, 'samples': 18768384, 'steps': 97751, 'loss/train': 0.41774505376815796} 08/31/2021 06:54:39 - INFO - __main__ - Step 97753: {'lr': 0.00013862577316642438, 'samples': 18768576, 'steps': 97752, 'loss/train': 0.9500185251235962} 08/31/2021 06:54:41 - INFO - __main__ - Step 97754: {'lr': 0.00013862102215098166, 'samples': 18768768, 'steps': 97753, 'loss/train': 1.3206818103790283} 08/31/2021 06:54:41 - INFO - __main__ - Step 97755: {'lr': 0.00013861627118572455, 'samples': 18768960, 'steps': 97754, 'loss/train': 1.1052716970443726} 08/31/2021 06:54:41 - INFO - __main__ - Step 97756: {'lr': 0.00013861152027065527, 'samples': 18769152, 'steps': 97755, 'loss/train': 0.01678125374019146} 08/31/2021 06:54:42 - INFO - __main__ - Step 97757: {'lr': 0.00013860676940577593, 'samples': 18769344, 'steps': 97756, 'loss/train': 0.01708853431046009} 08/31/2021 06:54:42 - INFO - __main__ - Step 97758: {'lr': 0.00013860201859108861, 'samples': 18769536, 'steps': 97757, 'loss/train': 1.534600019454956} 08/31/2021 06:54:42 - INFO - __main__ - Step 97759: {'lr': 0.00013859726782659555, 'samples': 18769728, 'steps': 97758, 'loss/train': 0.9388341307640076} 08/31/2021 06:54:44 - INFO - __main__ - Step 97760: {'lr': 0.0001385925171122988, 'samples': 18769920, 'steps': 97759, 'loss/train': 0.4156738221645355} 08/31/2021 06:54:45 - INFO - __main__ - Step 97761: {'lr': 0.00013858776644820058, 'samples': 18770112, 'steps': 97760, 'loss/train': 1.6471670866012573} 08/31/2021 06:54:45 - INFO - __main__ - Step 97762: {'lr': 0.0001385830158343031, 'samples': 18770304, 'steps': 97761, 'loss/train': 0.2859603464603424} 08/31/2021 06:54:45 - INFO - __main__ - Step 97763: {'lr': 0.00013857826527060823, 'samples': 18770496, 'steps': 97762, 'loss/train': 1.4301897287368774} 08/31/2021 06:54:46 - INFO - __main__ - Step 97764: {'lr': 0.00013857351475711832, 'samples': 18770688, 'steps': 97763, 'loss/train': 0.7953904271125793} 08/31/2021 06:54:46 - INFO - __main__ - Step 97765: {'lr': 0.00013856876429383546, 'samples': 18770880, 'steps': 97764, 'loss/train': 1.2398300170898438} 08/31/2021 06:54:48 - INFO - __main__ - Step 97766: {'lr': 0.00013856401388076184, 'samples': 18771072, 'steps': 97765, 'loss/train': 1.6602859497070312} 08/31/2021 06:54:48 - INFO - __main__ - Step 97767: {'lr': 0.0001385592635178995, 'samples': 18771264, 'steps': 97766, 'loss/train': 0.9635849595069885} 08/31/2021 06:54:49 - INFO - __main__ - Step 97768: {'lr': 0.00013855451320525064, 'samples': 18771456, 'steps': 97767, 'loss/train': 0.666904091835022} 08/31/2021 06:54:49 - INFO - __main__ - Step 97769: {'lr': 0.0001385497629428174, 'samples': 18771648, 'steps': 97768, 'loss/train': 0.029116369783878326} 08/31/2021 06:54:49 - INFO - __main__ - Step 97770: {'lr': 0.00013854501273060193, 'samples': 18771840, 'steps': 97769, 'loss/train': 0.0684661939740181} 08/31/2021 06:54:50 - INFO - __main__ - Step 97771: {'lr': 0.00013854026256860635, 'samples': 18772032, 'steps': 97770, 'loss/train': 0.9570353627204895} 08/31/2021 06:54:51 - INFO - __main__ - Step 97772: {'lr': 0.00013853551245683282, 'samples': 18772224, 'steps': 97771, 'loss/train': 1.4355125427246094} 08/31/2021 06:54:52 - INFO - __main__ - Step 97773: {'lr': 0.00013853076239528345, 'samples': 18772416, 'steps': 97772, 'loss/train': 0.927247941493988} 08/31/2021 06:54:52 - INFO - __main__ - Step 97774: {'lr': 0.0001385260123839604, 'samples': 18772608, 'steps': 97773, 'loss/train': 1.3488333225250244} 08/31/2021 06:54:52 - INFO - __main__ - Step 97775: {'lr': 0.00013852126242286592, 'samples': 18772800, 'steps': 97774, 'loss/train': 0.9712384343147278} 08/31/2021 06:54:53 - INFO - __main__ - Step 97776: {'lr': 0.00013851651251200193, 'samples': 18772992, 'steps': 97775, 'loss/train': 1.330136775970459} 08/31/2021 06:54:55 - INFO - __main__ - Step 97777: {'lr': 0.00013851176265137067, 'samples': 18773184, 'steps': 97776, 'loss/train': 0.8001686334609985} 08/31/2021 06:54:56 - INFO - __main__ - Step 97778: {'lr': 0.0001385070128409743, 'samples': 18773376, 'steps': 97777, 'loss/train': 1.5486570596694946} 08/31/2021 06:54:56 - INFO - __main__ - Step 97779: {'lr': 0.00013850226308081498, 'samples': 18773568, 'steps': 97778, 'loss/train': 1.1668031215667725} 08/31/2021 06:54:56 - INFO - __main__ - Step 97780: {'lr': 0.00013849751337089477, 'samples': 18773760, 'steps': 97779, 'loss/train': 0.9134542346000671} 08/31/2021 06:54:57 - INFO - __main__ - Step 97781: {'lr': 0.0001384927637112159, 'samples': 18773952, 'steps': 97780, 'loss/train': 1.8064899444580078} 08/31/2021 06:54:58 - INFO - __main__ - Step 97782: {'lr': 0.0001384880141017804, 'samples': 18774144, 'steps': 97781, 'loss/train': 0.39911243319511414} 08/31/2021 06:54:59 - INFO - __main__ - Step 97783: {'lr': 0.0001384832645425906, 'samples': 18774336, 'steps': 97782, 'loss/train': 2.1817173957824707} 08/31/2021 06:54:59 - INFO - __main__ - Step 97784: {'lr': 0.00013847851503364842, 'samples': 18774528, 'steps': 97783, 'loss/train': 1.0833096504211426} 08/31/2021 06:54:59 - INFO - __main__ - Step 97785: {'lr': 0.00013847376557495612, 'samples': 18774720, 'steps': 97784, 'loss/train': 1.4330775737762451} 08/31/2021 06:55:00 - INFO - __main__ - Step 97786: {'lr': 0.00013846901616651583, 'samples': 18774912, 'steps': 97785, 'loss/train': 1.4178298711776733} 08/31/2021 06:55:00 - INFO - __main__ - Step 97787: {'lr': 0.0001384642668083297, 'samples': 18775104, 'steps': 97786, 'loss/train': 1.017378330230713} 08/31/2021 06:55:02 - INFO - __main__ - Step 97788: {'lr': 0.0001384595175003998, 'samples': 18775296, 'steps': 97787, 'loss/train': 0.2638110816478729} 08/31/2021 06:55:02 - INFO - __main__ - Step 97789: {'lr': 0.00013845476824272845, 'samples': 18775488, 'steps': 97788, 'loss/train': 1.7392696142196655} 08/31/2021 06:55:03 - INFO - __main__ - Step 97790: {'lr': 0.00013845001903531757, 'samples': 18775680, 'steps': 97789, 'loss/train': 0.9972221851348877} 08/31/2021 06:55:03 - INFO - __main__ - Step 97791: {'lr': 0.0001384452698781694, 'samples': 18775872, 'steps': 97790, 'loss/train': 0.7903093695640564} 08/31/2021 06:55:03 - INFO - __main__ - Step 97792: {'lr': 0.00013844052077128605, 'samples': 18776064, 'steps': 97791, 'loss/train': 1.5318875312805176} 08/31/2021 06:55:05 - INFO - __main__ - Step 97793: {'lr': 0.00013843577171466966, 'samples': 18776256, 'steps': 97792, 'loss/train': 0.7099236845970154} 08/31/2021 06:55:06 - INFO - __main__ - Step 97794: {'lr': 0.00013843102270832242, 'samples': 18776448, 'steps': 97793, 'loss/train': 1.303564190864563} 08/31/2021 06:55:06 - INFO - __main__ - Step 97795: {'lr': 0.00013842627375224644, 'samples': 18776640, 'steps': 97794, 'loss/train': 1.0307998657226562} 08/31/2021 06:55:06 - INFO - __main__ - Step 97796: {'lr': 0.00013842152484644385, 'samples': 18776832, 'steps': 97795, 'loss/train': 0.6445849537849426} 08/31/2021 06:55:07 - INFO - __main__ - Step 97797: {'lr': 0.0001384167759909168, 'samples': 18777024, 'steps': 97796, 'loss/train': 1.1947698593139648} 08/31/2021 06:55:07 - INFO - __main__ - Step 97798: {'lr': 0.00013841202718566743, 'samples': 18777216, 'steps': 97797, 'loss/train': 1.5217922925949097} 08/31/2021 06:55:09 - INFO - __main__ - Step 97799: {'lr': 0.00013840727843069788, 'samples': 18777408, 'steps': 97798, 'loss/train': 0.06741482019424438} 08/31/2021 06:55:09 - INFO - __main__ - Step 97800: {'lr': 0.00013840252972601027, 'samples': 18777600, 'steps': 97799, 'loss/train': 1.1703563928604126} 08/31/2021 06:55:09 - INFO - __main__ - Step 97801: {'lr': 0.0001383977810716068, 'samples': 18777792, 'steps': 97800, 'loss/train': 1.5954419374465942} 08/31/2021 06:55:10 - INFO - __main__ - Step 97802: {'lr': 0.00013839303246748964, 'samples': 18777984, 'steps': 97801, 'loss/train': 1.4948437213897705} 08/31/2021 06:55:10 - INFO - __main__ - Step 97803: {'lr': 0.00013838828391366076, 'samples': 18778176, 'steps': 97802, 'loss/train': 0.4774205982685089} 08/31/2021 06:55:12 - INFO - __main__ - Step 97804: {'lr': 0.00013838353541012239, 'samples': 18778368, 'steps': 97803, 'loss/train': 1.673612356185913} 08/31/2021 06:55:12 - INFO - __main__ - Step 97805: {'lr': 0.00013837878695687668, 'samples': 18778560, 'steps': 97804, 'loss/train': 1.2220889329910278} 08/31/2021 06:55:12 - INFO - __main__ - Step 97806: {'lr': 0.00013837403855392579, 'samples': 18778752, 'steps': 97805, 'loss/train': 1.297913908958435} 08/31/2021 06:55:13 - INFO - __main__ - Step 97807: {'lr': 0.0001383692902012718, 'samples': 18778944, 'steps': 97806, 'loss/train': 0.8313316702842712} 08/31/2021 06:55:13 - INFO - __main__ - Step 97808: {'lr': 0.00013836454189891689, 'samples': 18779136, 'steps': 97807, 'loss/train': 0.8304889798164368} 08/31/2021 06:55:15 - INFO - __main__ - Step 97809: {'lr': 0.0001383597936468632, 'samples': 18779328, 'steps': 97808, 'loss/train': 1.4927191734313965} 08/31/2021 06:55:15 - INFO - __main__ - Step 97810: {'lr': 0.00013835504544511284, 'samples': 18779520, 'steps': 97809, 'loss/train': 1.5784215927124023} 08/31/2021 06:55:16 - INFO - __main__ - Step 97811: {'lr': 0.00013835029729366804, 'samples': 18779712, 'steps': 97810, 'loss/train': 0.7913862466812134} 08/31/2021 06:55:16 - INFO - __main__ - Step 97812: {'lr': 0.00013834554919253084, 'samples': 18779904, 'steps': 97811, 'loss/train': 1.0810331106185913} 08/31/2021 06:55:16 - INFO - __main__ - Step 97813: {'lr': 0.00013834080114170339, 'samples': 18780096, 'steps': 97812, 'loss/train': 0.7964252233505249} 08/31/2021 06:55:18 - INFO - __main__ - Step 97814: {'lr': 0.00013833605314118785, 'samples': 18780288, 'steps': 97813, 'loss/train': 0.2479502409696579} 08/31/2021 06:55:18 - INFO - __main__ - Step 97815: {'lr': 0.00013833130519098642, 'samples': 18780480, 'steps': 97814, 'loss/train': 0.8132341504096985} 08/31/2021 06:55:19 - INFO - __main__ - Step 97816: {'lr': 0.0001383265572911012, 'samples': 18780672, 'steps': 97815, 'loss/train': 0.903587818145752} 08/31/2021 06:55:19 - INFO - __main__ - Step 97817: {'lr': 0.00013832180944153429, 'samples': 18780864, 'steps': 97816, 'loss/train': 1.0302082300186157} 08/31/2021 06:55:19 - INFO - __main__ - Step 97818: {'lr': 0.0001383170616422878, 'samples': 18781056, 'steps': 97817, 'loss/train': 0.315372496843338} 08/31/2021 06:55:21 - INFO - __main__ - Step 97819: {'lr': 0.00013831231389336394, 'samples': 18781248, 'steps': 97818, 'loss/train': 0.21954697370529175} 08/31/2021 06:55:21 - INFO - __main__ - Step 97820: {'lr': 0.00013830756619476482, 'samples': 18781440, 'steps': 97819, 'loss/train': 1.2331669330596924} 08/31/2021 06:55:22 - INFO - __main__ - Step 97821: {'lr': 0.00013830281854649258, 'samples': 18781632, 'steps': 97820, 'loss/train': 1.4881423711776733} 08/31/2021 06:55:22 - INFO - __main__ - Step 97822: {'lr': 0.00013829807094854936, 'samples': 18781824, 'steps': 97821, 'loss/train': 1.1835192441940308} 08/31/2021 06:55:22 - INFO - __main__ - Step 97823: {'lr': 0.00013829332340093732, 'samples': 18782016, 'steps': 97822, 'loss/train': 1.6328028440475464} 08/31/2021 06:55:24 - INFO - __main__ - Step 97824: {'lr': 0.00013828857590365856, 'samples': 18782208, 'steps': 97823, 'loss/train': 0.8669919371604919} 08/31/2021 06:55:25 - INFO - __main__ - Step 97825: {'lr': 0.0001382838284567153, 'samples': 18782400, 'steps': 97824, 'loss/train': 1.2320644855499268} 08/31/2021 06:55:25 - INFO - __main__ - Step 97826: {'lr': 0.00013827908106010955, 'samples': 18782592, 'steps': 97825, 'loss/train': 1.0332525968551636} 08/31/2021 06:55:25 - INFO - __main__ - Step 97827: {'lr': 0.00013827433371384356, 'samples': 18782784, 'steps': 97826, 'loss/train': 0.991710364818573} 08/31/2021 06:55:26 - INFO - __main__ - Step 97828: {'lr': 0.00013826958641791957, 'samples': 18782976, 'steps': 97827, 'loss/train': 0.9129717946052551} 08/31/2021 06:55:26 - INFO - __main__ - Step 97829: {'lr': 0.00013826483917233945, 'samples': 18783168, 'steps': 97828, 'loss/train': 0.016958557069301605} 08/31/2021 06:55:28 - INFO - __main__ - Step 97830: {'lr': 0.00013826009197710542, 'samples': 18783360, 'steps': 97829, 'loss/train': 0.08277088403701782} 08/31/2021 06:55:28 - INFO - __main__ - Step 97831: {'lr': 0.00013825534483221974, 'samples': 18783552, 'steps': 97830, 'loss/train': 1.3371580839157104} 08/31/2021 06:55:28 - INFO - __main__ - Step 97832: {'lr': 0.00013825059773768444, 'samples': 18783744, 'steps': 97831, 'loss/train': 1.1753273010253906} 08/31/2021 06:55:29 - INFO - __main__ - Step 97833: {'lr': 0.0001382458506935017, 'samples': 18783936, 'steps': 97832, 'loss/train': 1.5042698383331299} 08/31/2021 06:55:29 - INFO - __main__ - Step 97834: {'lr': 0.00013824110369967365, 'samples': 18784128, 'steps': 97833, 'loss/train': 1.3893789052963257} 08/31/2021 06:55:30 - INFO - __main__ - Step 97835: {'lr': 0.00013823635675620243, 'samples': 18784320, 'steps': 97834, 'loss/train': 1.1768689155578613} 08/31/2021 06:55:32 - INFO - __main__ - Step 97836: {'lr': 0.00013823160986309023, 'samples': 18784512, 'steps': 97835, 'loss/train': 1.1350470781326294} 08/31/2021 06:55:32 - INFO - __main__ - Step 97837: {'lr': 0.0001382268630203391, 'samples': 18784704, 'steps': 97836, 'loss/train': 0.7466709613800049} 08/31/2021 06:55:33 - INFO - __main__ - Step 97838: {'lr': 0.00013822211622795122, 'samples': 18784896, 'steps': 97837, 'loss/train': 1.042819857597351} 08/31/2021 06:55:33 - INFO - __main__ - Step 97839: {'lr': 0.00013821736948592883, 'samples': 18785088, 'steps': 97838, 'loss/train': 0.024858981370925903} 08/31/2021 06:55:33 - INFO - __main__ - Step 97840: {'lr': 0.00013821262279427389, 'samples': 18785280, 'steps': 97839, 'loss/train': 1.3315708637237549} 08/31/2021 06:55:35 - INFO - __main__ - Step 97841: {'lr': 0.0001382078761529886, 'samples': 18785472, 'steps': 97840, 'loss/train': 1.0293110609054565} 08/31/2021 06:55:35 - INFO - __main__ - Step 97842: {'lr': 0.00013820312956207512, 'samples': 18785664, 'steps': 97841, 'loss/train': 1.0605366230010986} 08/31/2021 06:55:36 - INFO - __main__ - Step 97843: {'lr': 0.0001381983830215356, 'samples': 18785856, 'steps': 97842, 'loss/train': 1.1004531383514404} 08/31/2021 06:55:36 - INFO - __main__ - Step 97844: {'lr': 0.00013819363653137212, 'samples': 18786048, 'steps': 97843, 'loss/train': 1.3241311311721802} 08/31/2021 06:55:36 - INFO - __main__ - Step 97845: {'lr': 0.00013818889009158691, 'samples': 18786240, 'steps': 97844, 'loss/train': 1.1302356719970703} 08/31/2021 06:55:38 - INFO - __main__ - Step 97846: {'lr': 0.000138184143702182, 'samples': 18786432, 'steps': 97845, 'loss/train': 1.345402717590332} 08/31/2021 06:55:38 - INFO - __main__ - Step 97847: {'lr': 0.00013817939736315965, 'samples': 18786624, 'steps': 97846, 'loss/train': 1.2969602346420288} 08/31/2021 06:55:39 - INFO - __main__ - Step 97848: {'lr': 0.00013817465107452193, 'samples': 18786816, 'steps': 97847, 'loss/train': 0.15052825212478638} 08/31/2021 06:55:39 - INFO - __main__ - Step 97849: {'lr': 0.00013816990483627098, 'samples': 18787008, 'steps': 97848, 'loss/train': 1.3171931505203247} 08/31/2021 06:55:39 - INFO - __main__ - Step 97850: {'lr': 0.00013816515864840904, 'samples': 18787200, 'steps': 97849, 'loss/train': 1.2289447784423828} 08/31/2021 06:55:41 - INFO - __main__ - Step 97851: {'lr': 0.00013816041251093805, 'samples': 18787392, 'steps': 97850, 'loss/train': 1.3636115789413452} 08/31/2021 06:55:41 - INFO - __main__ - Step 97852: {'lr': 0.00013815566642386026, 'samples': 18787584, 'steps': 97851, 'loss/train': 1.8460640907287598} 08/31/2021 06:55:42 - INFO - __main__ - Step 97853: {'lr': 0.0001381509203871778, 'samples': 18787776, 'steps': 97852, 'loss/train': 1.0018742084503174} 08/31/2021 06:55:42 - INFO - __main__ - Step 97854: {'lr': 0.0001381461744008928, 'samples': 18787968, 'steps': 97853, 'loss/train': 0.9908674955368042} 08/31/2021 06:55:42 - INFO - __main__ - Step 97855: {'lr': 0.00013814142846500744, 'samples': 18788160, 'steps': 97854, 'loss/train': 1.225137710571289} 08/31/2021 06:55:44 - INFO - __main__ - Step 97856: {'lr': 0.00013813668257952377, 'samples': 18788352, 'steps': 97855, 'loss/train': 0.92122882604599} 08/31/2021 06:55:44 - INFO - __main__ - Step 97857: {'lr': 0.00013813193674444403, 'samples': 18788544, 'steps': 97856, 'loss/train': 1.3662476539611816} 08/31/2021 06:55:45 - INFO - __main__ - Step 97858: {'lr': 0.00013812719095977028, 'samples': 18788736, 'steps': 97857, 'loss/train': 1.007347822189331} 08/31/2021 06:55:45 - INFO - __main__ - Step 97859: {'lr': 0.0001381224452255047, 'samples': 18788928, 'steps': 97858, 'loss/train': 1.1842644214630127} 08/31/2021 06:55:45 - INFO - __main__ - Step 97860: {'lr': 0.00013811769954164943, 'samples': 18789120, 'steps': 97859, 'loss/train': 1.333915114402771} 08/31/2021 06:55:47 - INFO - __main__ - Step 97861: {'lr': 0.0001381129539082067, 'samples': 18789312, 'steps': 97860, 'loss/train': 1.121636152267456} 08/31/2021 06:55:47 - INFO - __main__ - Step 97862: {'lr': 0.00013810820832517846, 'samples': 18789504, 'steps': 97861, 'loss/train': 0.8755151629447937} 08/31/2021 06:55:48 - INFO - __main__ - Step 97863: {'lr': 0.00013810346279256693, 'samples': 18789696, 'steps': 97862, 'loss/train': 0.9308801889419556} 08/31/2021 06:55:48 - INFO - __main__ - Step 97864: {'lr': 0.0001380987173103742, 'samples': 18789888, 'steps': 97863, 'loss/train': 1.9994462728500366} 08/31/2021 06:55:48 - INFO - __main__ - Step 97865: {'lr': 0.00013809397187860255, 'samples': 18790080, 'steps': 97864, 'loss/train': 0.8714383840560913} 08/31/2021 06:55:50 - INFO - __main__ - Step 97866: {'lr': 0.00013808922649725396, 'samples': 18790272, 'steps': 97865, 'loss/train': 0.6149237155914307} 08/31/2021 06:55:51 - INFO - __main__ - Step 97867: {'lr': 0.00013808448116633064, 'samples': 18790464, 'steps': 97866, 'loss/train': 1.5102053880691528} 08/31/2021 06:55:51 - INFO - __main__ - Step 97868: {'lr': 0.0001380797358858348, 'samples': 18790656, 'steps': 97867, 'loss/train': 0.8724989891052246} 08/31/2021 06:55:51 - INFO - __main__ - Step 97869: {'lr': 0.00013807499065576843, 'samples': 18790848, 'steps': 97868, 'loss/train': 0.09791877865791321} 08/31/2021 06:55:52 - INFO - __main__ - Step 97870: {'lr': 0.00013807024547613376, 'samples': 18791040, 'steps': 97869, 'loss/train': 1.4174063205718994} 08/31/2021 06:55:53 - INFO - __main__ - Step 97871: {'lr': 0.0001380655003469329, 'samples': 18791232, 'steps': 97870, 'loss/train': 0.723612904548645} 08/31/2021 06:55:54 - INFO - __main__ - Step 97872: {'lr': 0.00013806075526816815, 'samples': 18791424, 'steps': 97871, 'loss/train': 1.5550264120101929} 08/31/2021 06:55:54 - INFO - __main__ - Step 97873: {'lr': 0.00013805601023984132, 'samples': 18791616, 'steps': 97872, 'loss/train': 1.0854381322860718} 08/31/2021 06:55:54 - INFO - __main__ - Step 97874: {'lr': 0.00013805126526195477, 'samples': 18791808, 'steps': 97873, 'loss/train': 0.9801772236824036} 08/31/2021 06:55:55 - INFO - __main__ - Step 97875: {'lr': 0.0001380465203345106, 'samples': 18792000, 'steps': 97874, 'loss/train': 1.0561814308166504} 08/31/2021 06:55:56 - INFO - __main__ - Step 97876: {'lr': 0.0001380417754575109, 'samples': 18792192, 'steps': 97875, 'loss/train': 1.072278618812561} 08/31/2021 06:55:57 - INFO - __main__ - Step 97877: {'lr': 0.00013803703063095787, 'samples': 18792384, 'steps': 97876, 'loss/train': 0.9338046908378601} 08/31/2021 06:55:57 - INFO - __main__ - Step 97878: {'lr': 0.00013803228585485363, 'samples': 18792576, 'steps': 97877, 'loss/train': 0.6920312643051147} 08/31/2021 06:55:57 - INFO - __main__ - Step 97879: {'lr': 0.0001380275411292003, 'samples': 18792768, 'steps': 97878, 'loss/train': 1.3005434274673462} 08/31/2021 06:55:58 - INFO - __main__ - Step 97880: {'lr': 0.00013802279645400007, 'samples': 18792960, 'steps': 97879, 'loss/train': 0.744078516960144} 08/31/2021 06:55:59 - INFO - __main__ - Step 97881: {'lr': 0.000138018051829255, 'samples': 18793152, 'steps': 97880, 'loss/train': 1.03825843334198} 08/31/2021 06:56:00 - INFO - __main__ - Step 97882: {'lr': 0.0001380133072549673, 'samples': 18793344, 'steps': 97881, 'loss/train': 1.2859580516815186} 08/31/2021 06:56:00 - INFO - __main__ - Step 97883: {'lr': 0.00013800856273113915, 'samples': 18793536, 'steps': 97882, 'loss/train': 1.4304877519607544} 08/31/2021 06:56:01 - INFO - __main__ - Step 97884: {'lr': 0.00013800381825777253, 'samples': 18793728, 'steps': 97883, 'loss/train': 0.9655038714408875} 08/31/2021 06:56:01 - INFO - __main__ - Step 97885: {'lr': 0.00013799907383486965, 'samples': 18793920, 'steps': 97884, 'loss/train': 0.615882396697998} 08/31/2021 06:56:03 - INFO - __main__ - Step 97886: {'lr': 0.00013799432946243266, 'samples': 18794112, 'steps': 97885, 'loss/train': 1.4759149551391602} 08/31/2021 06:56:04 - INFO - __main__ - Step 97887: {'lr': 0.0001379895851404637, 'samples': 18794304, 'steps': 97886, 'loss/train': 0.7714624404907227} 08/31/2021 06:56:04 - INFO - __main__ - Step 97888: {'lr': 0.0001379848408689649, 'samples': 18794496, 'steps': 97887, 'loss/train': 0.03386050462722778} 08/31/2021 06:56:04 - INFO - __main__ - Step 97889: {'lr': 0.0001379800966479384, 'samples': 18794688, 'steps': 97888, 'loss/train': 1.3352229595184326} 08/31/2021 06:56:05 - INFO - __main__ - Step 97890: {'lr': 0.00013797535247738634, 'samples': 18794880, 'steps': 97889, 'loss/train': 1.3830136060714722} 08/31/2021 06:56:06 - INFO - __main__ - Step 97891: {'lr': 0.00013797060835731088, 'samples': 18795072, 'steps': 97890, 'loss/train': 1.2248228788375854} 08/31/2021 06:56:06 - INFO - __main__ - Step 97892: {'lr': 0.00013796586428771414, 'samples': 18795264, 'steps': 97891, 'loss/train': 1.9919769763946533} 08/31/2021 06:56:07 - INFO - __main__ - Step 97893: {'lr': 0.0001379611202685982, 'samples': 18795456, 'steps': 97892, 'loss/train': 0.3468325734138489} 08/31/2021 06:56:07 - INFO - __main__ - Step 97894: {'lr': 0.00013795637629996526, 'samples': 18795648, 'steps': 97893, 'loss/train': 0.9769589900970459} 08/31/2021 06:56:08 - INFO - __main__ - Step 97895: {'lr': 0.0001379516323818175, 'samples': 18795840, 'steps': 97894, 'loss/train': 0.910408079624176} 08/31/2021 06:56:08 - INFO - __main__ - Step 97896: {'lr': 0.00013794688851415706, 'samples': 18796032, 'steps': 97895, 'loss/train': 1.264803171157837} 08/31/2021 06:56:09 - INFO - __main__ - Step 97897: {'lr': 0.00013794214469698595, 'samples': 18796224, 'steps': 97896, 'loss/train': 1.4084162712097168} 08/31/2021 06:56:10 - INFO - __main__ - Step 97898: {'lr': 0.00013793740093030637, 'samples': 18796416, 'steps': 97897, 'loss/train': 1.4216676950454712} 08/31/2021 06:56:10 - INFO - __main__ - Step 97899: {'lr': 0.00013793265721412045, 'samples': 18796608, 'steps': 97898, 'loss/train': 1.4018347263336182} 08/31/2021 06:56:11 - INFO - __main__ - Step 97900: {'lr': 0.00013792791354843038, 'samples': 18796800, 'steps': 97899, 'loss/train': 1.1672550439834595} 08/31/2021 06:56:11 - INFO - __main__ - Step 97901: {'lr': 0.00013792316993323822, 'samples': 18796992, 'steps': 97900, 'loss/train': 2.8077144622802734} 08/31/2021 06:56:13 - INFO - __main__ - Step 97902: {'lr': 0.00013791842636854619, 'samples': 18797184, 'steps': 97901, 'loss/train': 1.7340288162231445} 08/31/2021 06:56:13 - INFO - __main__ - Step 97903: {'lr': 0.00013791368285435637, 'samples': 18797376, 'steps': 97902, 'loss/train': 0.04662507772445679} 08/31/2021 06:56:14 - INFO - __main__ - Step 97904: {'lr': 0.00013790893939067092, 'samples': 18797568, 'steps': 97903, 'loss/train': 0.06458146870136261} 08/31/2021 06:56:14 - INFO - __main__ - Step 97905: {'lr': 0.000137904195977492, 'samples': 18797760, 'steps': 97904, 'loss/train': 1.139090657234192} 08/31/2021 06:56:15 - INFO - __main__ - Step 97906: {'lr': 0.00013789945261482168, 'samples': 18797952, 'steps': 97905, 'loss/train': 1.3856987953186035} 08/31/2021 06:56:15 - INFO - __main__ - Step 97907: {'lr': 0.00013789470930266213, 'samples': 18798144, 'steps': 97906, 'loss/train': 1.731161117553711} 08/31/2021 06:56:16 - INFO - __main__ - Step 97908: {'lr': 0.0001378899660410155, 'samples': 18798336, 'steps': 97907, 'loss/train': 0.8233199715614319} 08/31/2021 06:56:17 - INFO - __main__ - Step 97909: {'lr': 0.0001378852228298839, 'samples': 18798528, 'steps': 97908, 'loss/train': 0.7572405338287354} 08/31/2021 06:56:17 - INFO - __main__ - Step 97910: {'lr': 0.00013788047966926964, 'samples': 18798720, 'steps': 97909, 'loss/train': 1.5510104894638062} 08/31/2021 06:56:18 - INFO - __main__ - Step 97911: {'lr': 0.0001378757365591746, 'samples': 18798912, 'steps': 97910, 'loss/train': 1.2955173254013062} 08/31/2021 06:56:18 - INFO - __main__ - Step 97912: {'lr': 0.000137870993499601, 'samples': 18799104, 'steps': 97911, 'loss/train': 0.7691969275474548} 08/31/2021 06:56:19 - INFO - __main__ - Step 97913: {'lr': 0.00013786625049055102, 'samples': 18799296, 'steps': 97912, 'loss/train': 1.3296022415161133} 08/31/2021 06:56:20 - INFO - __main__ - Step 97914: {'lr': 0.00013786150753202674, 'samples': 18799488, 'steps': 97913, 'loss/train': 1.696388602256775} 08/31/2021 06:56:20 - INFO - __main__ - Step 97915: {'lr': 0.00013785676462403038, 'samples': 18799680, 'steps': 97914, 'loss/train': 1.0559499263763428} 08/31/2021 06:56:21 - INFO - __main__ - Step 97916: {'lr': 0.00013785202176656402, 'samples': 18799872, 'steps': 97915, 'loss/train': 0.749920666217804} 08/31/2021 06:56:21 - INFO - __main__ - Step 97917: {'lr': 0.00013784727895962978, 'samples': 18800064, 'steps': 97916, 'loss/train': 1.3237110376358032} 08/31/2021 06:56:21 - INFO - __main__ - Step 97918: {'lr': 0.00013784253620322985, 'samples': 18800256, 'steps': 97917, 'loss/train': 1.2099096775054932} 08/31/2021 06:56:23 - INFO - __main__ - Step 97919: {'lr': 0.00013783779349736637, 'samples': 18800448, 'steps': 97918, 'loss/train': 1.0560452938079834} 08/31/2021 06:56:23 - INFO - __main__ - Step 97920: {'lr': 0.0001378330508420414, 'samples': 18800640, 'steps': 97919, 'loss/train': 0.9197412729263306} 08/31/2021 06:56:24 - INFO - __main__ - Step 97921: {'lr': 0.0001378283082372571, 'samples': 18800832, 'steps': 97920, 'loss/train': 1.6341229677200317} 08/31/2021 06:56:24 - INFO - __main__ - Step 97922: {'lr': 0.0001378235656830157, 'samples': 18801024, 'steps': 97921, 'loss/train': 1.2516146898269653} 08/31/2021 06:56:24 - INFO - __main__ - Step 97923: {'lr': 0.0001378188231793194, 'samples': 18801216, 'steps': 97922, 'loss/train': 1.011675238609314} 08/31/2021 06:56:26 - INFO - __main__ - Step 97924: {'lr': 0.00013781408072617002, 'samples': 18801408, 'steps': 97923, 'loss/train': 1.245365023612976} 08/31/2021 06:56:26 - INFO - __main__ - Step 97925: {'lr': 0.0001378093383235699, 'samples': 18801600, 'steps': 97924, 'loss/train': 1.264560341835022} 08/31/2021 06:56:27 - INFO - __main__ - Step 97926: {'lr': 0.00013780459597152118, 'samples': 18801792, 'steps': 97925, 'loss/train': 1.4073034524917603} 08/31/2021 06:56:27 - INFO - __main__ - Step 97927: {'lr': 0.00013779985367002597, 'samples': 18801984, 'steps': 97926, 'loss/train': 1.366646409034729} 08/31/2021 06:56:27 - INFO - __main__ - Step 97928: {'lr': 0.00013779511141908643, 'samples': 18802176, 'steps': 97927, 'loss/train': 0.49298593401908875} 08/31/2021 06:56:29 - INFO - __main__ - Step 97929: {'lr': 0.0001377903692187047, 'samples': 18802368, 'steps': 97928, 'loss/train': 1.3228720426559448} 08/31/2021 06:56:29 - INFO - __main__ - Step 97930: {'lr': 0.00013778562706888287, 'samples': 18802560, 'steps': 97929, 'loss/train': 0.7319233417510986} 08/31/2021 06:56:30 - INFO - __main__ - Step 97931: {'lr': 0.0001377808849696231, 'samples': 18802752, 'steps': 97930, 'loss/train': 1.26496422290802} 08/31/2021 06:56:30 - INFO - __main__ - Step 97932: {'lr': 0.00013777614292092752, 'samples': 18802944, 'steps': 97931, 'loss/train': 1.1321120262145996} 08/31/2021 06:56:30 - INFO - __main__ - Step 97933: {'lr': 0.0001377714009227983, 'samples': 18803136, 'steps': 97932, 'loss/train': 1.5504090785980225} 08/31/2021 06:56:32 - INFO - __main__ - Step 97934: {'lr': 0.00013776665897523755, 'samples': 18803328, 'steps': 97933, 'loss/train': 1.5240941047668457} 08/31/2021 06:56:33 - INFO - __main__ - Step 97935: {'lr': 0.00013776191707824743, 'samples': 18803520, 'steps': 97934, 'loss/train': 1.8613935708999634} 08/31/2021 06:56:33 - INFO - __main__ - Step 97936: {'lr': 0.00013775717523183, 'samples': 18803712, 'steps': 97935, 'loss/train': 1.4433988332748413} 08/31/2021 06:56:33 - INFO - __main__ - Step 97937: {'lr': 0.00013775243343598761, 'samples': 18803904, 'steps': 97936, 'loss/train': 0.26993560791015625} 08/31/2021 06:56:34 - INFO - __main__ - Step 97938: {'lr': 0.00013774769169072216, 'samples': 18804096, 'steps': 97937, 'loss/train': 1.0020250082015991} 08/31/2021 06:56:34 - INFO - __main__ - Step 97939: {'lr': 0.00013774294999603583, 'samples': 18804288, 'steps': 97938, 'loss/train': 1.2508772611618042} 08/31/2021 06:56:35 - INFO - __main__ - Step 97940: {'lr': 0.0001377382083519308, 'samples': 18804480, 'steps': 97939, 'loss/train': 0.6089497208595276} 08/31/2021 06:56:36 - INFO - __main__ - Step 97941: {'lr': 0.0001377334667584092, 'samples': 18804672, 'steps': 97940, 'loss/train': 1.3440909385681152} 08/31/2021 06:56:36 - INFO - __main__ - Step 97942: {'lr': 0.00013772872521547314, 'samples': 18804864, 'steps': 97941, 'loss/train': 0.2609036862850189} 08/31/2021 06:56:37 - INFO - __main__ - Step 97943: {'lr': 0.00013772398372312485, 'samples': 18805056, 'steps': 97942, 'loss/train': 4.060750961303711} 08/31/2021 06:56:37 - INFO - __main__ - Step 97944: {'lr': 0.00013771924228136634, 'samples': 18805248, 'steps': 97943, 'loss/train': 0.8566257357597351} 08/31/2021 06:56:39 - INFO - __main__ - Step 97945: {'lr': 0.00013771450089019983, 'samples': 18805440, 'steps': 97944, 'loss/train': 1.3462185859680176} 08/31/2021 06:56:40 - INFO - __main__ - Step 97946: {'lr': 0.00013770975954962745, 'samples': 18805632, 'steps': 97945, 'loss/train': 0.7304900884628296} 08/31/2021 06:56:40 - INFO - __main__ - Step 97947: {'lr': 0.0001377050182596513, 'samples': 18805824, 'steps': 97946, 'loss/train': 1.6677902936935425} 08/31/2021 06:56:40 - INFO - __main__ - Step 97948: {'lr': 0.00013770027702027351, 'samples': 18806016, 'steps': 97947, 'loss/train': 1.026213526725769} 08/31/2021 06:56:41 - INFO - __main__ - Step 97949: {'lr': 0.0001376955358314963, 'samples': 18806208, 'steps': 97948, 'loss/train': 0.054202694445848465} 08/31/2021 06:56:42 - INFO - __main__ - Step 97950: {'lr': 0.0001376907946933218, 'samples': 18806400, 'steps': 97949, 'loss/train': 1.3498880863189697} 08/31/2021 06:56:43 - INFO - __main__ - Step 97951: {'lr': 0.000137686053605752, 'samples': 18806592, 'steps': 97950, 'loss/train': 1.6419333219528198} 08/31/2021 06:56:43 - INFO - __main__ - Step 97952: {'lr': 0.00013768131256878917, 'samples': 18806784, 'steps': 97951, 'loss/train': 1.006381630897522} 08/31/2021 06:56:43 - INFO - __main__ - Step 97953: {'lr': 0.00013767657158243534, 'samples': 18806976, 'steps': 97952, 'loss/train': 0.07243992388248444} 08/31/2021 06:56:44 - INFO - __main__ - Step 97954: {'lr': 0.00013767183064669278, 'samples': 18807168, 'steps': 97953, 'loss/train': 1.4635010957717896} 08/31/2021 06:56:45 - INFO - __main__ - Step 97955: {'lr': 0.00013766708976156356, 'samples': 18807360, 'steps': 97954, 'loss/train': 1.2778534889221191} 08/31/2021 06:56:46 - INFO - __main__ - Step 97956: {'lr': 0.00013766234892704975, 'samples': 18807552, 'steps': 97955, 'loss/train': 1.3668419122695923} 08/31/2021 06:56:46 - INFO - __main__ - Step 97957: {'lr': 0.0001376576081431536, 'samples': 18807744, 'steps': 97956, 'loss/train': 0.7706286311149597} 08/31/2021 06:56:46 - INFO - __main__ - Step 97958: {'lr': 0.0001376528674098772, 'samples': 18807936, 'steps': 97957, 'loss/train': 1.03083336353302} 08/31/2021 06:56:47 - INFO - __main__ - Step 97959: {'lr': 0.0001376481267272227, 'samples': 18808128, 'steps': 97958, 'loss/train': 1.2708930969238281} 08/31/2021 06:56:48 - INFO - __main__ - Step 97960: {'lr': 0.00013764338609519218, 'samples': 18808320, 'steps': 97959, 'loss/train': 0.7448723316192627} 08/31/2021 06:56:49 - INFO - __main__ - Step 97961: {'lr': 0.00013763864551378786, 'samples': 18808512, 'steps': 97960, 'loss/train': 1.1608326435089111} 08/31/2021 06:56:49 - INFO - __main__ - Step 97962: {'lr': 0.00013763390498301178, 'samples': 18808704, 'steps': 97961, 'loss/train': 0.802852988243103} 08/31/2021 06:56:49 - INFO - __main__ - Step 97963: {'lr': 0.00013762916450286617, 'samples': 18808896, 'steps': 97962, 'loss/train': 0.19196727871894836} 08/31/2021 06:56:50 - INFO - __main__ - Step 97964: {'lr': 0.00013762442407335318, 'samples': 18809088, 'steps': 97963, 'loss/train': 1.2516454458236694} 08/31/2021 06:56:50 - INFO - __main__ - Step 97965: {'lr': 0.00013761968369447483, 'samples': 18809280, 'steps': 97964, 'loss/train': 1.9723937511444092} 08/31/2021 06:56:52 - INFO - __main__ - Step 97966: {'lr': 0.00013761494336623332, 'samples': 18809472, 'steps': 97965, 'loss/train': 1.459261417388916} 08/31/2021 06:56:52 - INFO - __main__ - Step 97967: {'lr': 0.00013761020308863077, 'samples': 18809664, 'steps': 97966, 'loss/train': 0.7515660524368286} 08/31/2021 06:56:53 - INFO - __main__ - Step 97968: {'lr': 0.0001376054628616693, 'samples': 18809856, 'steps': 97967, 'loss/train': 0.4886728823184967} 08/31/2021 06:56:53 - INFO - __main__ - Step 97969: {'lr': 0.0001376007226853511, 'samples': 18810048, 'steps': 97968, 'loss/train': 0.4576430320739746} 08/31/2021 06:56:53 - INFO - __main__ - Step 97970: {'lr': 0.0001375959825596783, 'samples': 18810240, 'steps': 97969, 'loss/train': 1.3065135478973389} 08/31/2021 06:56:55 - INFO - __main__ - Step 97971: {'lr': 0.000137591242484653, 'samples': 18810432, 'steps': 97970, 'loss/train': 1.2206236124038696} 08/31/2021 06:56:55 - INFO - __main__ - Step 97972: {'lr': 0.00013758650246027733, 'samples': 18810624, 'steps': 97971, 'loss/train': 1.5033934116363525} 08/31/2021 06:56:56 - INFO - __main__ - Step 97973: {'lr': 0.00013758176248655345, 'samples': 18810816, 'steps': 97972, 'loss/train': 0.797675371170044} 08/31/2021 06:56:56 - INFO - __main__ - Step 97974: {'lr': 0.00013757702256348353, 'samples': 18811008, 'steps': 97973, 'loss/train': 0.7827005982398987} 08/31/2021 06:56:56 - INFO - __main__ - Step 97975: {'lr': 0.00013757228269106964, 'samples': 18811200, 'steps': 97974, 'loss/train': 1.8071597814559937} 08/31/2021 06:56:58 - INFO - __main__ - Step 97976: {'lr': 0.00013756754286931393, 'samples': 18811392, 'steps': 97975, 'loss/train': 1.6636967658996582} 08/31/2021 06:56:58 - INFO - __main__ - Step 97977: {'lr': 0.00013756280309821869, 'samples': 18811584, 'steps': 97976, 'loss/train': 1.2422759532928467} 08/31/2021 06:56:59 - INFO - __main__ - Step 97978: {'lr': 0.00013755806337778582, 'samples': 18811776, 'steps': 97977, 'loss/train': 1.1359283924102783} 08/31/2021 06:56:59 - INFO - __main__ - Step 97979: {'lr': 0.0001375533237080175, 'samples': 18811968, 'steps': 97978, 'loss/train': 1.0044264793395996} 08/31/2021 06:56:59 - INFO - __main__ - Step 97980: {'lr': 0.00013754858408891596, 'samples': 18812160, 'steps': 97979, 'loss/train': 1.1550475358963013} 08/31/2021 06:57:01 - INFO - __main__ - Step 97981: {'lr': 0.00013754384452048328, 'samples': 18812352, 'steps': 97980, 'loss/train': 0.5480064153671265} 08/31/2021 06:57:02 - INFO - __main__ - Step 97982: {'lr': 0.0001375391050027216, 'samples': 18812544, 'steps': 97981, 'loss/train': 0.5996320247650146} 08/31/2021 06:57:02 - INFO - __main__ - Step 97983: {'lr': 0.0001375343655356331, 'samples': 18812736, 'steps': 97982, 'loss/train': 1.2269484996795654} 08/31/2021 06:57:02 - INFO - __main__ - Step 97984: {'lr': 0.00013752962611921982, 'samples': 18812928, 'steps': 97983, 'loss/train': 0.7082117199897766} 08/31/2021 06:57:03 - INFO - __main__ - Step 97985: {'lr': 0.00013752488675348402, 'samples': 18813120, 'steps': 97984, 'loss/train': 1.483682632446289} 08/31/2021 06:57:03 - INFO - __main__ - Step 97986: {'lr': 0.00013752014743842773, 'samples': 18813312, 'steps': 97985, 'loss/train': 0.015951495617628098} 08/31/2021 06:57:05 - INFO - __main__ - Step 97987: {'lr': 0.00013751540817405312, 'samples': 18813504, 'steps': 97986, 'loss/train': 1.6413661241531372} 08/31/2021 06:57:05 - INFO - __main__ - Step 97988: {'lr': 0.00013751066896036234, 'samples': 18813696, 'steps': 97987, 'loss/train': 1.0098623037338257} 08/31/2021 06:57:05 - INFO - __main__ - Step 97989: {'lr': 0.00013750592979735752, 'samples': 18813888, 'steps': 97988, 'loss/train': 0.20410774648189545} 08/31/2021 06:57:06 - INFO - __main__ - Step 97990: {'lr': 0.0001375011906850409, 'samples': 18814080, 'steps': 97989, 'loss/train': 1.074769377708435} 08/31/2021 06:57:06 - INFO - __main__ - Step 97991: {'lr': 0.0001374964516234144, 'samples': 18814272, 'steps': 97990, 'loss/train': 1.1234556436538696} 08/31/2021 06:57:06 - INFO - __main__ - Step 97992: {'lr': 0.00013749171261248026, 'samples': 18814464, 'steps': 97991, 'loss/train': 0.98863685131073} 08/31/2021 06:57:09 - INFO - __main__ - Step 97993: {'lr': 0.0001374869736522406, 'samples': 18814656, 'steps': 97992, 'loss/train': 0.1834014356136322} 08/31/2021 06:57:09 - INFO - __main__ - Step 97994: {'lr': 0.0001374822347426976, 'samples': 18814848, 'steps': 97993, 'loss/train': 0.7191120982170105} 08/31/2021 06:57:09 - INFO - __main__ - Step 97995: {'lr': 0.00013747749588385335, 'samples': 18815040, 'steps': 97994, 'loss/train': 1.2192928791046143} 08/31/2021 06:57:10 - INFO - __main__ - Step 97996: {'lr': 0.00013747275707571, 'samples': 18815232, 'steps': 97995, 'loss/train': 0.016584619879722595} 08/31/2021 06:57:10 - INFO - __main__ - Step 97997: {'lr': 0.00013746801831826974, 'samples': 18815424, 'steps': 97996, 'loss/train': 0.017032494768500328} 08/31/2021 06:57:10 - INFO - __main__ - Step 97998: {'lr': 0.00013746327961153463, 'samples': 18815616, 'steps': 97997, 'loss/train': 0.4574880599975586} 08/31/2021 06:57:12 - INFO - __main__ - Step 97999: {'lr': 0.00013745854095550681, 'samples': 18815808, 'steps': 97998, 'loss/train': 0.9769824743270874} 08/31/2021 06:57:13 - INFO - __main__ - Step 98000: {'lr': 0.00013745380235018846, 'samples': 18816000, 'steps': 97999, 'loss/train': 1.3809747695922852} 08/31/2021 06:57:13 - INFO - __main__ - Step 98001: {'lr': 0.00013744906379558163, 'samples': 18816192, 'steps': 98000, 'loss/train': 1.3465579748153687} 08/31/2021 06:57:14 - INFO - __main__ - Step 98002: {'lr': 0.0001374443252916886, 'samples': 18816384, 'steps': 98001, 'loss/train': 1.588599681854248} 08/31/2021 06:57:14 - INFO - __main__ - Step 98003: {'lr': 0.00013743958683851138, 'samples': 18816576, 'steps': 98002, 'loss/train': 1.2959110736846924} 08/31/2021 06:57:16 - INFO - __main__ - Step 98004: {'lr': 0.00013743484843605226, 'samples': 18816768, 'steps': 98003, 'loss/train': 1.3156248331069946} 08/31/2021 06:57:16 - INFO - __main__ - Step 98005: {'lr': 0.0001374301100843131, 'samples': 18816960, 'steps': 98004, 'loss/train': 0.5529717803001404} 08/31/2021 06:57:16 - INFO - __main__ - Step 98006: {'lr': 0.00013742537178329628, 'samples': 18817152, 'steps': 98005, 'loss/train': 1.1301124095916748} 08/31/2021 06:57:17 - INFO - __main__ - Step 98007: {'lr': 0.0001374206335330038, 'samples': 18817344, 'steps': 98006, 'loss/train': 0.9013334512710571} 08/31/2021 06:57:17 - INFO - __main__ - Step 98008: {'lr': 0.00013741589533343784, 'samples': 18817536, 'steps': 98007, 'loss/train': 1.0213202238082886} 08/31/2021 06:57:18 - INFO - __main__ - Step 98009: {'lr': 0.00013741115718460056, 'samples': 18817728, 'steps': 98008, 'loss/train': 0.893230676651001} 08/31/2021 06:57:19 - INFO - __main__ - Step 98010: {'lr': 0.0001374064190864941, 'samples': 18817920, 'steps': 98009, 'loss/train': 1.068037748336792} 08/31/2021 06:57:19 - INFO - __main__ - Step 98011: {'lr': 0.00013740168103912055, 'samples': 18818112, 'steps': 98010, 'loss/train': 0.8561079502105713} 08/31/2021 06:57:20 - INFO - __main__ - Step 98012: {'lr': 0.00013739694304248202, 'samples': 18818304, 'steps': 98011, 'loss/train': 1.1748861074447632} 08/31/2021 06:57:20 - INFO - __main__ - Step 98013: {'lr': 0.00013739220509658074, 'samples': 18818496, 'steps': 98012, 'loss/train': 1.299248456954956} 08/31/2021 06:57:22 - INFO - __main__ - Step 98014: {'lr': 0.0001373874672014188, 'samples': 18818688, 'steps': 98013, 'loss/train': 1.5559407472610474} 08/31/2021 06:57:22 - INFO - __main__ - Step 98015: {'lr': 0.0001373827293569983, 'samples': 18818880, 'steps': 98014, 'loss/train': 0.8511201739311218} 08/31/2021 06:57:22 - INFO - __main__ - Step 98016: {'lr': 0.00013737799156332144, 'samples': 18819072, 'steps': 98015, 'loss/train': 1.1042728424072266} 08/31/2021 06:57:23 - INFO - __main__ - Step 98017: {'lr': 0.00013737325382039037, 'samples': 18819264, 'steps': 98016, 'loss/train': 1.055877447128296} 08/31/2021 06:57:23 - INFO - __main__ - Step 98018: {'lr': 0.0001373685161282071, 'samples': 18819456, 'steps': 98017, 'loss/train': 1.4188237190246582} 08/31/2021 06:57:24 - INFO - __main__ - Step 98019: {'lr': 0.00013736377848677384, 'samples': 18819648, 'steps': 98018, 'loss/train': 1.0885212421417236} 08/31/2021 06:57:25 - INFO - __main__ - Step 98020: {'lr': 0.00013735904089609273, 'samples': 18819840, 'steps': 98019, 'loss/train': 0.4709036648273468} 08/31/2021 06:57:25 - INFO - __main__ - Step 98021: {'lr': 0.00013735430335616588, 'samples': 18820032, 'steps': 98020, 'loss/train': 1.126331090927124} 08/31/2021 06:57:26 - INFO - __main__ - Step 98022: {'lr': 0.00013734956586699542, 'samples': 18820224, 'steps': 98021, 'loss/train': 1.5575581789016724} 08/31/2021 06:57:26 - INFO - __main__ - Step 98023: {'lr': 0.00013734482842858356, 'samples': 18820416, 'steps': 98022, 'loss/train': 1.5417897701263428} 08/31/2021 06:57:26 - INFO - __main__ - Step 98024: {'lr': 0.00013734009104093237, 'samples': 18820608, 'steps': 98023, 'loss/train': 0.42042219638824463} 08/31/2021 06:57:28 - INFO - __main__ - Step 98025: {'lr': 0.00013733535370404399, 'samples': 18820800, 'steps': 98024, 'loss/train': 1.6470797061920166} 08/31/2021 06:57:29 - INFO - __main__ - Step 98026: {'lr': 0.00013733061641792055, 'samples': 18820992, 'steps': 98025, 'loss/train': 0.06124444305896759} 08/31/2021 06:57:29 - INFO - __main__ - Step 98027: {'lr': 0.0001373258791825642, 'samples': 18821184, 'steps': 98026, 'loss/train': 1.366117238998413} 08/31/2021 06:57:29 - INFO - __main__ - Step 98028: {'lr': 0.00013732114199797708, 'samples': 18821376, 'steps': 98027, 'loss/train': 0.04233568161725998} 08/31/2021 06:57:30 - INFO - __main__ - Step 98029: {'lr': 0.0001373164048641613, 'samples': 18821568, 'steps': 98028, 'loss/train': 1.9526448249816895} 08/31/2021 06:57:31 - INFO - __main__ - Step 98030: {'lr': 0.00013731166778111904, 'samples': 18821760, 'steps': 98029, 'loss/train': 0.5754132270812988} 08/31/2021 06:57:32 - INFO - __main__ - Step 98031: {'lr': 0.00013730693074885246, 'samples': 18821952, 'steps': 98030, 'loss/train': 0.9066572785377502} 08/31/2021 06:57:32 - INFO - __main__ - Step 98032: {'lr': 0.00013730219376736357, 'samples': 18822144, 'steps': 98031, 'loss/train': 0.9711709022521973} 08/31/2021 06:57:32 - INFO - __main__ - Step 98033: {'lr': 0.00013729745683665456, 'samples': 18822336, 'steps': 98032, 'loss/train': 1.342151165008545} 08/31/2021 06:57:34 - INFO - __main__ - Step 98034: {'lr': 0.0001372927199567276, 'samples': 18822528, 'steps': 98033, 'loss/train': 1.7255436182022095} 08/31/2021 06:57:35 - INFO - __main__ - Step 98035: {'lr': 0.00013728798312758478, 'samples': 18822720, 'steps': 98034, 'loss/train': 1.1110163927078247} 08/31/2021 06:57:36 - INFO - __main__ - Step 98036: {'lr': 0.00013728324634922824, 'samples': 18822912, 'steps': 98035, 'loss/train': 1.0107853412628174} 08/31/2021 06:57:36 - INFO - __main__ - Step 98037: {'lr': 0.00013727850962166015, 'samples': 18823104, 'steps': 98036, 'loss/train': 0.7972879409790039} 08/31/2021 06:57:36 - INFO - __main__ - Step 98038: {'lr': 0.00013727377294488262, 'samples': 18823296, 'steps': 98037, 'loss/train': 1.4443567991256714} 08/31/2021 06:57:37 - INFO - __main__ - Step 98039: {'lr': 0.0001372690363188978, 'samples': 18823488, 'steps': 98038, 'loss/train': 1.4440526962280273} 08/31/2021 06:57:38 - INFO - __main__ - Step 98040: {'lr': 0.0001372642997437078, 'samples': 18823680, 'steps': 98039, 'loss/train': 1.1133524179458618} 08/31/2021 06:57:39 - INFO - __main__ - Step 98041: {'lr': 0.00013725956321931475, 'samples': 18823872, 'steps': 98040, 'loss/train': 1.3960089683532715} 08/31/2021 06:57:39 - INFO - __main__ - Step 98042: {'lr': 0.00013725482674572083, 'samples': 18824064, 'steps': 98041, 'loss/train': 0.8754889369010925} 08/31/2021 06:57:40 - INFO - __main__ - Step 98043: {'lr': 0.00013725009032292812, 'samples': 18824256, 'steps': 98042, 'loss/train': 1.0962673425674438} 08/31/2021 06:57:40 - INFO - __main__ - Step 98044: {'lr': 0.0001372453539509389, 'samples': 18824448, 'steps': 98043, 'loss/train': 0.9282240867614746} 08/31/2021 06:57:41 - INFO - __main__ - Step 98045: {'lr': 0.0001372406176297551, 'samples': 18824640, 'steps': 98044, 'loss/train': 0.43241357803344727} 08/31/2021 06:57:42 - INFO - __main__ - Step 98046: {'lr': 0.00013723588135937888, 'samples': 18824832, 'steps': 98045, 'loss/train': 1.599999189376831} 08/31/2021 06:57:42 - INFO - __main__ - Step 98047: {'lr': 0.0001372311451398125, 'samples': 18825024, 'steps': 98046, 'loss/train': 1.2667851448059082} 08/31/2021 06:57:42 - INFO - __main__ - Step 98048: {'lr': 0.00013722640897105798, 'samples': 18825216, 'steps': 98047, 'loss/train': 0.8069878816604614} 08/31/2021 06:57:43 - INFO - __main__ - Step 98049: {'lr': 0.0001372216728531175, 'samples': 18825408, 'steps': 98048, 'loss/train': 1.0023283958435059} 08/31/2021 06:57:45 - INFO - __main__ - Step 98050: {'lr': 0.00013721693678599324, 'samples': 18825600, 'steps': 98049, 'loss/train': 1.17341148853302} 08/31/2021 06:57:46 - INFO - __main__ - Step 98051: {'lr': 0.00013721220076968723, 'samples': 18825792, 'steps': 98050, 'loss/train': 1.118937611579895} 08/31/2021 06:57:46 - INFO - __main__ - Step 98052: {'lr': 0.0001372074648042017, 'samples': 18825984, 'steps': 98051, 'loss/train': 1.3153047561645508} 08/31/2021 06:57:46 - INFO - __main__ - Step 98053: {'lr': 0.0001372027288895387, 'samples': 18826176, 'steps': 98052, 'loss/train': 0.08676420897245407} 08/31/2021 06:57:47 - INFO - __main__ - Step 98054: {'lr': 0.00013719799302570047, 'samples': 18826368, 'steps': 98053, 'loss/train': 1.2979862689971924} 08/31/2021 06:57:48 - INFO - __main__ - Step 98055: {'lr': 0.00013719325721268905, 'samples': 18826560, 'steps': 98054, 'loss/train': 1.5547820329666138} 08/31/2021 06:57:49 - INFO - __main__ - Step 98056: {'lr': 0.0001371885214505066, 'samples': 18826752, 'steps': 98055, 'loss/train': 1.7997190952301025} 08/31/2021 06:57:49 - INFO - __main__ - Step 98057: {'lr': 0.0001371837857391553, 'samples': 18826944, 'steps': 98056, 'loss/train': 1.8211406469345093} 08/31/2021 06:57:49 - INFO - __main__ - Step 98058: {'lr': 0.00013717905007863728, 'samples': 18827136, 'steps': 98057, 'loss/train': 1.0204914808273315} 08/31/2021 06:57:50 - INFO - __main__ - Step 98059: {'lr': 0.00013717431446895462, 'samples': 18827328, 'steps': 98058, 'loss/train': 1.4647772312164307} 08/31/2021 06:57:50 - INFO - __main__ - Step 98060: {'lr': 0.0001371695789101094, 'samples': 18827520, 'steps': 98059, 'loss/train': 1.1924494504928589} 08/31/2021 06:57:52 - INFO - __main__ - Step 98061: {'lr': 0.00013716484340210388, 'samples': 18827712, 'steps': 98060, 'loss/train': 0.9857768416404724} 08/31/2021 06:57:52 - INFO - __main__ - Step 98062: {'lr': 0.00013716010794494012, 'samples': 18827904, 'steps': 98061, 'loss/train': 0.84523606300354} 08/31/2021 06:57:53 - INFO - __main__ - Step 98063: {'lr': 0.00013715537253862026, 'samples': 18828096, 'steps': 98062, 'loss/train': 1.051289439201355} 08/31/2021 06:57:53 - INFO - __main__ - Step 98064: {'lr': 0.00013715063718314647, 'samples': 18828288, 'steps': 98063, 'loss/train': 1.225024700164795} 08/31/2021 06:57:53 - INFO - __main__ - Step 98065: {'lr': 0.00013714590187852087, 'samples': 18828480, 'steps': 98064, 'loss/train': 0.9811025857925415} 08/31/2021 06:57:55 - INFO - __main__ - Step 98066: {'lr': 0.00013714116662474554, 'samples': 18828672, 'steps': 98065, 'loss/train': 1.0935912132263184} 08/31/2021 06:57:55 - INFO - __main__ - Step 98067: {'lr': 0.0001371364314218227, 'samples': 18828864, 'steps': 98066, 'loss/train': 1.17349374294281} 08/31/2021 06:57:56 - INFO - __main__ - Step 98068: {'lr': 0.00013713169626975442, 'samples': 18829056, 'steps': 98067, 'loss/train': 1.3385330438613892} 08/31/2021 06:57:56 - INFO - __main__ - Step 98069: {'lr': 0.00013712696116854287, 'samples': 18829248, 'steps': 98068, 'loss/train': 1.2484627962112427} 08/31/2021 06:57:56 - INFO - __main__ - Step 98070: {'lr': 0.00013712222611819016, 'samples': 18829440, 'steps': 98069, 'loss/train': 1.1534923315048218} 08/31/2021 06:57:58 - INFO - __main__ - Step 98071: {'lr': 0.00013711749111869855, 'samples': 18829632, 'steps': 98070, 'loss/train': 1.297038197517395} 08/31/2021 06:57:58 - INFO - __main__ - Step 98072: {'lr': 0.00013711275617006994, 'samples': 18829824, 'steps': 98071, 'loss/train': 1.7550474405288696} 08/31/2021 06:57:59 - INFO - __main__ - Step 98073: {'lr': 0.0001371080212723066, 'samples': 18830016, 'steps': 98072, 'loss/train': 1.0643037557601929} 08/31/2021 06:57:59 - INFO - __main__ - Step 98074: {'lr': 0.00013710328642541062, 'samples': 18830208, 'steps': 98073, 'loss/train': 0.8604505062103271} 08/31/2021 06:57:59 - INFO - __main__ - Step 98075: {'lr': 0.00013709855162938417, 'samples': 18830400, 'steps': 98074, 'loss/train': 1.5527633428573608} 08/31/2021 06:58:01 - INFO - __main__ - Step 98076: {'lr': 0.00013709381688422934, 'samples': 18830592, 'steps': 98075, 'loss/train': 0.9977322816848755} 08/31/2021 06:58:02 - INFO - __main__ - Step 98077: {'lr': 0.00013708908218994833, 'samples': 18830784, 'steps': 98076, 'loss/train': 1.6771682500839233} 08/31/2021 06:58:02 - INFO - __main__ - Step 98078: {'lr': 0.00013708434754654324, 'samples': 18830976, 'steps': 98077, 'loss/train': 0.6748462319374084} 08/31/2021 06:58:02 - INFO - __main__ - Step 98079: {'lr': 0.00013707961295401618, 'samples': 18831168, 'steps': 98078, 'loss/train': 0.15909138321876526} 08/31/2021 06:58:03 - INFO - __main__ - Step 98080: {'lr': 0.00013707487841236931, 'samples': 18831360, 'steps': 98079, 'loss/train': 1.0942316055297852} 08/31/2021 06:58:03 - INFO - __main__ - Step 98081: {'lr': 0.00013707014392160476, 'samples': 18831552, 'steps': 98080, 'loss/train': 1.0861319303512573} 08/31/2021 06:58:05 - INFO - __main__ - Step 98082: {'lr': 0.00013706540948172467, 'samples': 18831744, 'steps': 98081, 'loss/train': 1.3505487442016602} 08/31/2021 06:58:05 - INFO - __main__ - Step 98083: {'lr': 0.0001370606750927311, 'samples': 18831936, 'steps': 98082, 'loss/train': 1.6506545543670654} 08/31/2021 06:58:06 - INFO - __main__ - Step 98084: {'lr': 0.00013705594075462635, 'samples': 18832128, 'steps': 98083, 'loss/train': 0.646242082118988} 08/31/2021 06:58:06 - INFO - __main__ - Step 98085: {'lr': 0.0001370512064674125, 'samples': 18832320, 'steps': 98084, 'loss/train': 1.300437569618225} 08/31/2021 06:58:06 - INFO - __main__ - Step 98086: {'lr': 0.0001370464722310915, 'samples': 18832512, 'steps': 98085, 'loss/train': 0.037690646946430206} 08/31/2021 06:58:08 - INFO - __main__ - Step 98087: {'lr': 0.00013704173804566567, 'samples': 18832704, 'steps': 98086, 'loss/train': 1.656369924545288} 08/31/2021 06:58:09 - INFO - __main__ - Step 98088: {'lr': 0.00013703700391113708, 'samples': 18832896, 'steps': 98087, 'loss/train': 1.0082776546478271} 08/31/2021 06:58:09 - INFO - __main__ - Step 98089: {'lr': 0.00013703226982750784, 'samples': 18833088, 'steps': 98088, 'loss/train': 1.1088694334030151} 08/31/2021 06:58:09 - INFO - __main__ - Step 98090: {'lr': 0.00013702753579478017, 'samples': 18833280, 'steps': 98089, 'loss/train': 1.214916706085205} 08/31/2021 06:58:10 - INFO - __main__ - Step 98091: {'lr': 0.0001370228018129561, 'samples': 18833472, 'steps': 98090, 'loss/train': 0.49125444889068604} 08/31/2021 06:58:10 - INFO - __main__ - Step 98092: {'lr': 0.00013701806788203786, 'samples': 18833664, 'steps': 98091, 'loss/train': 1.3589272499084473} 08/31/2021 06:58:12 - INFO - __main__ - Step 98093: {'lr': 0.0001370133340020275, 'samples': 18833856, 'steps': 98092, 'loss/train': 2.4086878299713135} 08/31/2021 06:58:12 - INFO - __main__ - Step 98094: {'lr': 0.00013700860017292716, 'samples': 18834048, 'steps': 98093, 'loss/train': 1.6481389999389648} 08/31/2021 06:58:12 - INFO - __main__ - Step 98095: {'lr': 0.00013700386639473906, 'samples': 18834240, 'steps': 98094, 'loss/train': 0.44665074348449707} 08/31/2021 06:58:13 - INFO - __main__ - Step 98096: {'lr': 0.0001369991326674652, 'samples': 18834432, 'steps': 98095, 'loss/train': 1.46884286403656} 08/31/2021 06:58:13 - INFO - __main__ - Step 98097: {'lr': 0.00013699439899110799, 'samples': 18834624, 'steps': 98096, 'loss/train': 1.524661898612976} 08/31/2021 06:58:15 - INFO - __main__ - Step 98098: {'lr': 0.0001369896653656692, 'samples': 18834816, 'steps': 98097, 'loss/train': 0.953040361404419} 08/31/2021 06:58:15 - INFO - __main__ - Step 98099: {'lr': 0.00013698493179115112, 'samples': 18835008, 'steps': 98098, 'loss/train': 1.060011863708496} 08/31/2021 06:58:15 - INFO - __main__ - Step 98100: {'lr': 0.0001369801982675559, 'samples': 18835200, 'steps': 98099, 'loss/train': 0.7622781991958618} 08/31/2021 06:58:16 - INFO - __main__ - Step 98101: {'lr': 0.00013697546479488564, 'samples': 18835392, 'steps': 98100, 'loss/train': 0.9694507718086243} 08/31/2021 06:58:16 - INFO - __main__ - Step 98102: {'lr': 0.00013697073137314253, 'samples': 18835584, 'steps': 98101, 'loss/train': 1.061760663986206} 08/31/2021 06:58:18 - INFO - __main__ - Step 98103: {'lr': 0.0001369659980023286, 'samples': 18835776, 'steps': 98102, 'loss/train': 1.0570261478424072} 08/31/2021 06:58:18 - INFO - __main__ - Step 98104: {'lr': 0.00013696126468244613, 'samples': 18835968, 'steps': 98103, 'loss/train': 0.26595422625541687} 08/31/2021 06:58:19 - INFO - __main__ - Step 98105: {'lr': 0.00013695653141349712, 'samples': 18836160, 'steps': 98104, 'loss/train': 0.8035968542098999} 08/31/2021 06:58:19 - INFO - __main__ - Step 98106: {'lr': 0.00013695179819548376, 'samples': 18836352, 'steps': 98105, 'loss/train': 1.1416726112365723} 08/31/2021 06:58:19 - INFO - __main__ - Step 98107: {'lr': 0.00013694706502840814, 'samples': 18836544, 'steps': 98106, 'loss/train': 1.719985842704773} 08/31/2021 06:58:21 - INFO - __main__ - Step 98108: {'lr': 0.00013694233191227257, 'samples': 18836736, 'steps': 98107, 'loss/train': 0.3123528063297272} 08/31/2021 06:58:22 - INFO - __main__ - Step 98109: {'lr': 0.00013693759884707895, 'samples': 18836928, 'steps': 98108, 'loss/train': 0.7942598462104797} 08/31/2021 06:58:22 - INFO - __main__ - Step 98110: {'lr': 0.0001369328658328295, 'samples': 18837120, 'steps': 98109, 'loss/train': 1.078116774559021} 08/31/2021 06:58:22 - INFO - __main__ - Step 98111: {'lr': 0.00013692813286952634, 'samples': 18837312, 'steps': 98110, 'loss/train': 0.5493465662002563} 08/31/2021 06:58:23 - INFO - __main__ - Step 98112: {'lr': 0.00013692339995717163, 'samples': 18837504, 'steps': 98111, 'loss/train': 0.7757496237754822} 08/31/2021 06:58:24 - INFO - __main__ - Step 98113: {'lr': 0.00013691866709576744, 'samples': 18837696, 'steps': 98112, 'loss/train': 0.09607160091400146} 08/31/2021 06:58:25 - INFO - __main__ - Step 98114: {'lr': 0.000136913934285316, 'samples': 18837888, 'steps': 98113, 'loss/train': 1.5969345569610596} 08/31/2021 06:58:25 - INFO - __main__ - Step 98115: {'lr': 0.0001369092015258194, 'samples': 18838080, 'steps': 98114, 'loss/train': 1.5168700218200684} 08/31/2021 06:58:25 - INFO - __main__ - Step 98116: {'lr': 0.00013690446881727976, 'samples': 18838272, 'steps': 98115, 'loss/train': 0.8245359063148499} 08/31/2021 06:58:26 - INFO - __main__ - Step 98117: {'lr': 0.00013689973615969923, 'samples': 18838464, 'steps': 98116, 'loss/train': 1.2968426942825317} 08/31/2021 06:58:27 - INFO - __main__ - Step 98118: {'lr': 0.00013689500355307995, 'samples': 18838656, 'steps': 98117, 'loss/train': 0.7793142795562744} 08/31/2021 06:58:28 - INFO - __main__ - Step 98119: {'lr': 0.00013689027099742407, 'samples': 18838848, 'steps': 98118, 'loss/train': 1.0955839157104492} 08/31/2021 06:58:28 - INFO - __main__ - Step 98120: {'lr': 0.00013688553849273364, 'samples': 18839040, 'steps': 98119, 'loss/train': 1.1207914352416992} 08/31/2021 06:58:28 - INFO - __main__ - Step 98121: {'lr': 0.00013688080603901082, 'samples': 18839232, 'steps': 98120, 'loss/train': 0.11555320024490356} 08/31/2021 06:58:29 - INFO - __main__ - Step 98122: {'lr': 0.00013687607363625779, 'samples': 18839424, 'steps': 98121, 'loss/train': 1.589195728302002} 08/31/2021 06:58:30 - INFO - __main__ - Step 98123: {'lr': 0.00013687134128447664, 'samples': 18839616, 'steps': 98122, 'loss/train': 1.1274338960647583} 08/31/2021 06:58:31 - INFO - __main__ - Step 98124: {'lr': 0.0001368666089836695, 'samples': 18839808, 'steps': 98123, 'loss/train': 1.3786284923553467} 08/31/2021 06:58:31 - INFO - __main__ - Step 98125: {'lr': 0.00013686187673383855, 'samples': 18840000, 'steps': 98124, 'loss/train': 1.47793447971344} 08/31/2021 06:58:32 - INFO - __main__ - Step 98126: {'lr': 0.0001368571445349859, 'samples': 18840192, 'steps': 98125, 'loss/train': 0.28695181012153625} 08/31/2021 06:58:32 - INFO - __main__ - Step 98127: {'lr': 0.00013685241238711366, 'samples': 18840384, 'steps': 98126, 'loss/train': 0.03454546257853508} 08/31/2021 06:58:33 - INFO - __main__ - Step 98128: {'lr': 0.00013684768029022392, 'samples': 18840576, 'steps': 98127, 'loss/train': 1.600717306137085} 08/31/2021 06:58:34 - INFO - __main__ - Step 98129: {'lr': 0.00013684294824431895, 'samples': 18840768, 'steps': 98128, 'loss/train': 1.5505367517471313} 08/31/2021 06:58:34 - INFO - __main__ - Step 98130: {'lr': 0.00013683821624940087, 'samples': 18840960, 'steps': 98129, 'loss/train': 1.3810689449310303} 08/31/2021 06:58:35 - INFO - __main__ - Step 98131: {'lr': 0.00013683348430547164, 'samples': 18841152, 'steps': 98130, 'loss/train': 1.070893406867981} 08/31/2021 06:58:35 - INFO - __main__ - Step 98132: {'lr': 0.0001368287524125335, 'samples': 18841344, 'steps': 98131, 'loss/train': 1.3386459350585938} 08/31/2021 06:58:35 - INFO - __main__ - Step 98133: {'lr': 0.00013682402057058857, 'samples': 18841536, 'steps': 98132, 'loss/train': 0.46927809715270996} 08/31/2021 06:58:37 - INFO - __main__ - Step 98134: {'lr': 0.000136819288779639, 'samples': 18841728, 'steps': 98133, 'loss/train': 1.4167718887329102} 08/31/2021 06:58:37 - INFO - __main__ - Step 98135: {'lr': 0.00013681455703968691, 'samples': 18841920, 'steps': 98134, 'loss/train': 1.0244220495224} 08/31/2021 06:58:38 - INFO - __main__ - Step 98136: {'lr': 0.00013680982535073445, 'samples': 18842112, 'steps': 98135, 'loss/train': 1.2059887647628784} 08/31/2021 06:58:38 - INFO - __main__ - Step 98137: {'lr': 0.00013680509371278372, 'samples': 18842304, 'steps': 98136, 'loss/train': 1.4231359958648682} 08/31/2021 06:58:38 - INFO - __main__ - Step 98138: {'lr': 0.00013680036212583688, 'samples': 18842496, 'steps': 98137, 'loss/train': 0.9406764507293701} 08/31/2021 06:58:40 - INFO - __main__ - Step 98139: {'lr': 0.00013679563058989602, 'samples': 18842688, 'steps': 98138, 'loss/train': 1.0463848114013672} 08/31/2021 06:58:40 - INFO - __main__ - Step 98140: {'lr': 0.00013679089910496344, 'samples': 18842880, 'steps': 98139, 'loss/train': 0.921140730381012} 08/31/2021 06:58:41 - INFO - __main__ - Step 98141: {'lr': 0.00013678616767104102, 'samples': 18843072, 'steps': 98140, 'loss/train': 1.1273201704025269} 08/31/2021 06:58:41 - INFO - __main__ - Step 98142: {'lr': 0.000136781436288131, 'samples': 18843264, 'steps': 98141, 'loss/train': 0.6987063884735107} 08/31/2021 06:58:41 - INFO - __main__ - Step 98143: {'lr': 0.0001367767049562355, 'samples': 18843456, 'steps': 98142, 'loss/train': 0.7244958281517029} 08/31/2021 06:58:43 - INFO - __main__ - Step 98144: {'lr': 0.0001367719736753567, 'samples': 18843648, 'steps': 98143, 'loss/train': 0.82405024766922} 08/31/2021 06:58:44 - INFO - __main__ - Step 98145: {'lr': 0.00013676724244549672, 'samples': 18843840, 'steps': 98144, 'loss/train': 0.06297007203102112} 08/31/2021 06:58:44 - INFO - __main__ - Step 98146: {'lr': 0.0001367625112666576, 'samples': 18844032, 'steps': 98145, 'loss/train': 0.6943821310997009} 08/31/2021 06:58:44 - INFO - __main__ - Step 98147: {'lr': 0.0001367577801388416, 'samples': 18844224, 'steps': 98146, 'loss/train': 0.9602606296539307} 08/31/2021 06:58:45 - INFO - __main__ - Step 98148: {'lr': 0.0001367530490620508, 'samples': 18844416, 'steps': 98147, 'loss/train': 0.02220722660422325} 08/31/2021 06:58:47 - INFO - __main__ - Step 98149: {'lr': 0.0001367483180362873, 'samples': 18844608, 'steps': 98148, 'loss/train': 1.6574242115020752} 08/31/2021 06:58:48 - INFO - __main__ - Step 98150: {'lr': 0.00013674358706155328, 'samples': 18844800, 'steps': 98149, 'loss/train': 0.11011993139982224} 08/31/2021 06:58:48 - INFO - __main__ - Step 98151: {'lr': 0.00013673885613785087, 'samples': 18844992, 'steps': 98150, 'loss/train': 0.942832887172699} 08/31/2021 06:58:48 - INFO - __main__ - Step 98152: {'lr': 0.00013673412526518224, 'samples': 18845184, 'steps': 98151, 'loss/train': 1.2527774572372437} 08/31/2021 06:58:49 - INFO - __main__ - Step 98153: {'lr': 0.00013672939444354937, 'samples': 18845376, 'steps': 98152, 'loss/train': 1.7305817604064941} 08/31/2021 06:58:49 - INFO - __main__ - Step 98154: {'lr': 0.0001367246636729545, 'samples': 18845568, 'steps': 98153, 'loss/train': 1.7320088148117065} 08/31/2021 06:58:49 - INFO - __main__ - Step 98155: {'lr': 0.00013671993295339977, 'samples': 18845760, 'steps': 98154, 'loss/train': 0.915016770362854} 08/31/2021 06:58:51 - INFO - __main__ - Step 98156: {'lr': 0.00013671520228488725, 'samples': 18845952, 'steps': 98155, 'loss/train': 0.7992319464683533} 08/31/2021 06:58:51 - INFO - __main__ - Step 98157: {'lr': 0.00013671047166741916, 'samples': 18846144, 'steps': 98156, 'loss/train': 0.8220946788787842} 08/31/2021 06:58:52 - INFO - __main__ - Step 98158: {'lr': 0.00013670574110099753, 'samples': 18846336, 'steps': 98157, 'loss/train': 0.9219307899475098} 08/31/2021 06:58:52 - INFO - __main__ - Step 98159: {'lr': 0.00013670101058562459, 'samples': 18846528, 'steps': 98158, 'loss/train': 0.899580717086792} 08/31/2021 06:58:53 - INFO - __main__ - Step 98160: {'lr': 0.0001366962801213024, 'samples': 18846720, 'steps': 98159, 'loss/train': 5.746903896331787} 08/31/2021 06:58:53 - INFO - __main__ - Step 98161: {'lr': 0.00013669154970803312, 'samples': 18846912, 'steps': 98160, 'loss/train': 1.4315431118011475} 08/31/2021 06:58:55 - INFO - __main__ - Step 98162: {'lr': 0.00013668681934581888, 'samples': 18847104, 'steps': 98161, 'loss/train': 1.0753166675567627} 08/31/2021 06:58:55 - INFO - __main__ - Step 98163: {'lr': 0.00013668208903466184, 'samples': 18847296, 'steps': 98162, 'loss/train': 1.310341238975525} 08/31/2021 06:58:56 - INFO - __main__ - Step 98164: {'lr': 0.00013667735877456405, 'samples': 18847488, 'steps': 98163, 'loss/train': 0.49637630581855774} 08/31/2021 06:58:56 - INFO - __main__ - Step 98165: {'lr': 0.00013667262856552784, 'samples': 18847680, 'steps': 98164, 'loss/train': 1.4258826971054077} 08/31/2021 06:58:56 - INFO - __main__ - Step 98166: {'lr': 0.00013666789840755507, 'samples': 18847872, 'steps': 98165, 'loss/train': 1.4245103597640991} 08/31/2021 06:58:58 - INFO - __main__ - Step 98167: {'lr': 0.000136663168300648, 'samples': 18848064, 'steps': 98166, 'loss/train': 0.7795150279998779} 08/31/2021 06:58:59 - INFO - __main__ - Step 98168: {'lr': 0.00013665843824480877, 'samples': 18848256, 'steps': 98167, 'loss/train': 0.3287044167518616} 08/31/2021 06:58:59 - INFO - __main__ - Step 98169: {'lr': 0.00013665370824003949, 'samples': 18848448, 'steps': 98168, 'loss/train': 1.2124732732772827} 08/31/2021 06:58:59 - INFO - __main__ - Step 98170: {'lr': 0.0001366489782863423, 'samples': 18848640, 'steps': 98169, 'loss/train': 0.6718682646751404} 08/31/2021 06:59:00 - INFO - __main__ - Step 98171: {'lr': 0.0001366442483837193, 'samples': 18848832, 'steps': 98170, 'loss/train': 0.7632813453674316} 08/31/2021 06:59:01 - INFO - __main__ - Step 98172: {'lr': 0.00013663951853217272, 'samples': 18849024, 'steps': 98171, 'loss/train': 0.9395601153373718} 08/31/2021 06:59:02 - INFO - __main__ - Step 98173: {'lr': 0.00013663478873170458, 'samples': 18849216, 'steps': 98172, 'loss/train': 1.4842385053634644} 08/31/2021 06:59:02 - INFO - __main__ - Step 98174: {'lr': 0.00013663005898231708, 'samples': 18849408, 'steps': 98173, 'loss/train': 1.587589979171753} 08/31/2021 06:59:02 - INFO - __main__ - Step 98175: {'lr': 0.00013662532928401228, 'samples': 18849600, 'steps': 98174, 'loss/train': 1.1217042207717896} 08/31/2021 06:59:03 - INFO - __main__ - Step 98176: {'lr': 0.00013662059963679237, 'samples': 18849792, 'steps': 98175, 'loss/train': 0.8967667818069458} 08/31/2021 06:59:04 - INFO - __main__ - Step 98177: {'lr': 0.0001366158700406595, 'samples': 18849984, 'steps': 98176, 'loss/train': 1.6349306106567383} 08/31/2021 06:59:05 - INFO - __main__ - Step 98178: {'lr': 0.00013661114049561574, 'samples': 18850176, 'steps': 98177, 'loss/train': 1.304612636566162} 08/31/2021 06:59:05 - INFO - __main__ - Step 98179: {'lr': 0.00013660641100166337, 'samples': 18850368, 'steps': 98178, 'loss/train': 0.8503315448760986} 08/31/2021 06:59:05 - INFO - __main__ - Step 98180: {'lr': 0.0001366016815588043, 'samples': 18850560, 'steps': 98179, 'loss/train': 1.064125657081604} 08/31/2021 06:59:06 - INFO - __main__ - Step 98181: {'lr': 0.00013659695216704075, 'samples': 18850752, 'steps': 98180, 'loss/train': 0.5552390813827515} 08/31/2021 06:59:07 - INFO - __main__ - Step 98182: {'lr': 0.00013659222282637483, 'samples': 18850944, 'steps': 98181, 'loss/train': 1.7865898609161377} 08/31/2021 06:59:08 - INFO - __main__ - Step 98183: {'lr': 0.00013658749353680878, 'samples': 18851136, 'steps': 98182, 'loss/train': 0.9229851961135864} 08/31/2021 06:59:08 - INFO - __main__ - Step 98184: {'lr': 0.00013658276429834459, 'samples': 18851328, 'steps': 98183, 'loss/train': 1.1307157278060913} 08/31/2021 06:59:08 - INFO - __main__ - Step 98185: {'lr': 0.00013657803511098448, 'samples': 18851520, 'steps': 98184, 'loss/train': 0.9061827063560486} 08/31/2021 06:59:09 - INFO - __main__ - Step 98186: {'lr': 0.0001365733059747306, 'samples': 18851712, 'steps': 98185, 'loss/train': 1.5935949087142944} 08/31/2021 06:59:09 - INFO - __main__ - Step 98187: {'lr': 0.00013656857688958498, 'samples': 18851904, 'steps': 98186, 'loss/train': 0.8762882351875305} 08/31/2021 06:59:11 - INFO - __main__ - Step 98188: {'lr': 0.00013656384785554985, 'samples': 18852096, 'steps': 98187, 'loss/train': 1.1108629703521729} 08/31/2021 06:59:11 - INFO - __main__ - Step 98189: {'lr': 0.00013655911887262728, 'samples': 18852288, 'steps': 98188, 'loss/train': 1.2993175983428955} 08/31/2021 06:59:12 - INFO - __main__ - Step 98190: {'lr': 0.00013655438994081943, 'samples': 18852480, 'steps': 98189, 'loss/train': 0.7277984023094177} 08/31/2021 06:59:12 - INFO - __main__ - Step 98191: {'lr': 0.0001365496610601284, 'samples': 18852672, 'steps': 98190, 'loss/train': 1.60127854347229} 08/31/2021 06:59:12 - INFO - __main__ - Step 98192: {'lr': 0.00013654493223055645, 'samples': 18852864, 'steps': 98191, 'loss/train': 1.6123688220977783} 08/31/2021 06:59:14 - INFO - __main__ - Step 98193: {'lr': 0.0001365402034521055, 'samples': 18853056, 'steps': 98192, 'loss/train': 1.3801219463348389} 08/31/2021 06:59:14 - INFO - __main__ - Step 98194: {'lr': 0.0001365354747247778, 'samples': 18853248, 'steps': 98193, 'loss/train': 0.7896041870117188} 08/31/2021 06:59:14 - INFO - __main__ - Step 98195: {'lr': 0.00013653074604857542, 'samples': 18853440, 'steps': 98194, 'loss/train': 1.4645227193832397} 08/31/2021 06:59:15 - INFO - __main__ - Step 98196: {'lr': 0.00013652601742350056, 'samples': 18853632, 'steps': 98195, 'loss/train': 0.7877668738365173} 08/31/2021 06:59:15 - INFO - __main__ - Step 98197: {'lr': 0.00013652128884955537, 'samples': 18853824, 'steps': 98196, 'loss/train': 0.8376044631004333} 08/31/2021 06:59:17 - INFO - __main__ - Step 98198: {'lr': 0.0001365165603267419, 'samples': 18854016, 'steps': 98197, 'loss/train': 1.3108056783676147} 08/31/2021 06:59:17 - INFO - __main__ - Step 98199: {'lr': 0.0001365118318550623, 'samples': 18854208, 'steps': 98198, 'loss/train': 0.9761171936988831} 08/31/2021 06:59:18 - INFO - __main__ - Step 98200: {'lr': 0.00013650710343451872, 'samples': 18854400, 'steps': 98199, 'loss/train': 1.1992464065551758} 08/31/2021 06:59:18 - INFO - __main__ - Step 98201: {'lr': 0.00013650237506511331, 'samples': 18854592, 'steps': 98200, 'loss/train': 0.9277355670928955} 08/31/2021 06:59:18 - INFO - __main__ - Step 98202: {'lr': 0.00013649764674684818, 'samples': 18854784, 'steps': 98201, 'loss/train': 0.57517409324646} 08/31/2021 06:59:21 - INFO - __main__ - Step 98203: {'lr': 0.00013649291847972546, 'samples': 18854976, 'steps': 98202, 'loss/train': 1.1911702156066895} 08/31/2021 06:59:21 - INFO - __main__ - Step 98204: {'lr': 0.00013648819026374726, 'samples': 18855168, 'steps': 98203, 'loss/train': 1.0807855129241943} 08/31/2021 06:59:21 - INFO - __main__ - Step 98205: {'lr': 0.00013648346209891573, 'samples': 18855360, 'steps': 98204, 'loss/train': 0.7647618055343628} 08/31/2021 06:59:22 - INFO - __main__ - Step 98206: {'lr': 0.00013647873398523312, 'samples': 18855552, 'steps': 98205, 'loss/train': 0.6361600160598755} 08/31/2021 06:59:22 - INFO - __main__ - Step 98207: {'lr': 0.00013647400592270133, 'samples': 18855744, 'steps': 98206, 'loss/train': 0.23087260127067566} 08/31/2021 06:59:22 - INFO - __main__ - Step 98208: {'lr': 0.0001364692779113226, 'samples': 18855936, 'steps': 98207, 'loss/train': 0.19107551872730255} 08/31/2021 06:59:24 - INFO - __main__ - Step 98209: {'lr': 0.00013646454995109905, 'samples': 18856128, 'steps': 98208, 'loss/train': 0.13949459791183472} 08/31/2021 06:59:25 - INFO - __main__ - Step 98210: {'lr': 0.00013645982204203282, 'samples': 18856320, 'steps': 98209, 'loss/train': 1.3507237434387207} 08/31/2021 06:59:25 - INFO - __main__ - Step 98211: {'lr': 0.00013645509418412608, 'samples': 18856512, 'steps': 98210, 'loss/train': 0.9734386801719666} 08/31/2021 06:59:25 - INFO - __main__ - Step 98212: {'lr': 0.0001364503663773809, 'samples': 18856704, 'steps': 98211, 'loss/train': 0.1352631002664566} 08/31/2021 06:59:26 - INFO - __main__ - Step 98213: {'lr': 0.00013644563862179942, 'samples': 18856896, 'steps': 98212, 'loss/train': 0.28979727625846863} 08/31/2021 06:59:26 - INFO - __main__ - Step 98214: {'lr': 0.0001364409109173838, 'samples': 18857088, 'steps': 98213, 'loss/train': 0.27834534645080566} 08/31/2021 06:59:28 - INFO - __main__ - Step 98215: {'lr': 0.00013643618326413616, 'samples': 18857280, 'steps': 98214, 'loss/train': 0.9913523197174072} 08/31/2021 06:59:29 - INFO - __main__ - Step 98216: {'lr': 0.0001364314556620586, 'samples': 18857472, 'steps': 98215, 'loss/train': 0.805168092250824} 08/31/2021 06:59:29 - INFO - __main__ - Step 98217: {'lr': 0.00013642672811115328, 'samples': 18857664, 'steps': 98216, 'loss/train': 0.625852644443512} 08/31/2021 06:59:30 - INFO - __main__ - Step 98218: {'lr': 0.00013642200061142235, 'samples': 18857856, 'steps': 98217, 'loss/train': 1.4583326578140259} 08/31/2021 06:59:30 - INFO - __main__ - Step 98219: {'lr': 0.00013641727316286798, 'samples': 18858048, 'steps': 98218, 'loss/train': 1.0341745615005493} 08/31/2021 06:59:30 - INFO - __main__ - Step 98220: {'lr': 0.00013641254576549213, 'samples': 18858240, 'steps': 98219, 'loss/train': 1.187707543373108} 08/31/2021 06:59:32 - INFO - __main__ - Step 98221: {'lr': 0.00013640781841929705, 'samples': 18858432, 'steps': 98220, 'loss/train': 1.2034850120544434} 08/31/2021 06:59:32 - INFO - __main__ - Step 98222: {'lr': 0.00013640309112428488, 'samples': 18858624, 'steps': 98221, 'loss/train': 0.0313684344291687} 08/31/2021 06:59:33 - INFO - __main__ - Step 98223: {'lr': 0.00013639836388045767, 'samples': 18858816, 'steps': 98222, 'loss/train': 0.5122442841529846} 08/31/2021 06:59:33 - INFO - __main__ - Step 98224: {'lr': 0.00013639363668781765, 'samples': 18859008, 'steps': 98223, 'loss/train': 0.9126080274581909} 08/31/2021 06:59:33 - INFO - __main__ - Step 98225: {'lr': 0.0001363889095463669, 'samples': 18859200, 'steps': 98224, 'loss/train': 0.651676595211029} 08/31/2021 06:59:34 - INFO - __main__ - Step 98226: {'lr': 0.00013638418245610751, 'samples': 18859392, 'steps': 98225, 'loss/train': 0.7194797992706299} 08/31/2021 06:59:35 - INFO - __main__ - Step 98227: {'lr': 0.00013637945541704173, 'samples': 18859584, 'steps': 98226, 'loss/train': 1.6915596723556519} 08/31/2021 06:59:36 - INFO - __main__ - Step 98228: {'lr': 0.00013637472842917153, 'samples': 18859776, 'steps': 98227, 'loss/train': 1.4049407243728638} 08/31/2021 06:59:36 - INFO - __main__ - Step 98229: {'lr': 0.00013637000149249918, 'samples': 18859968, 'steps': 98228, 'loss/train': 1.4424631595611572} 08/31/2021 06:59:36 - INFO - __main__ - Step 98230: {'lr': 0.00013636527460702673, 'samples': 18860160, 'steps': 98229, 'loss/train': 1.2955454587936401} 08/31/2021 06:59:37 - INFO - __main__ - Step 98231: {'lr': 0.00013636054777275636, 'samples': 18860352, 'steps': 98230, 'loss/train': 0.38346588611602783} 08/31/2021 06:59:38 - INFO - __main__ - Step 98232: {'lr': 0.00013635582098969024, 'samples': 18860544, 'steps': 98231, 'loss/train': 0.9990407824516296} 08/31/2021 06:59:39 - INFO - __main__ - Step 98233: {'lr': 0.00013635109425783035, 'samples': 18860736, 'steps': 98232, 'loss/train': 0.7333075404167175} 08/31/2021 06:59:39 - INFO - __main__ - Step 98234: {'lr': 0.0001363463675771789, 'samples': 18860928, 'steps': 98233, 'loss/train': 1.5176786184310913} 08/31/2021 06:59:39 - INFO - __main__ - Step 98235: {'lr': 0.00013634164094773805, 'samples': 18861120, 'steps': 98234, 'loss/train': 1.2463197708129883} 08/31/2021 06:59:40 - INFO - __main__ - Step 98236: {'lr': 0.00013633691436950985, 'samples': 18861312, 'steps': 98235, 'loss/train': 1.5470094680786133} 08/31/2021 06:59:42 - INFO - __main__ - Step 98237: {'lr': 0.00013633218784249652, 'samples': 18861504, 'steps': 98236, 'loss/train': 0.7986912727355957} 08/31/2021 06:59:42 - INFO - __main__ - Step 98238: {'lr': 0.00013632746136670016, 'samples': 18861696, 'steps': 98237, 'loss/train': 1.2135337591171265} 08/31/2021 06:59:42 - INFO - __main__ - Step 98239: {'lr': 0.00013632273494212287, 'samples': 18861888, 'steps': 98238, 'loss/train': 1.6649624109268188} 08/31/2021 06:59:43 - INFO - __main__ - Step 98240: {'lr': 0.0001363180085687668, 'samples': 18862080, 'steps': 98239, 'loss/train': 1.0999040603637695} 08/31/2021 06:59:43 - INFO - __main__ - Step 98241: {'lr': 0.00013631328224663407, 'samples': 18862272, 'steps': 98240, 'loss/train': 1.5463699102401733} 08/31/2021 06:59:43 - INFO - __main__ - Step 98242: {'lr': 0.00013630855597572683, 'samples': 18862464, 'steps': 98241, 'loss/train': 1.2736058235168457} 08/31/2021 06:59:46 - INFO - __main__ - Step 98243: {'lr': 0.0001363038297560472, 'samples': 18862656, 'steps': 98242, 'loss/train': 1.4256287813186646} 08/31/2021 06:59:46 - INFO - __main__ - Step 98244: {'lr': 0.00013629910358759734, 'samples': 18862848, 'steps': 98243, 'loss/train': 1.029792070388794} 08/31/2021 06:59:46 - INFO - __main__ - Step 98245: {'lr': 0.00013629437747037933, 'samples': 18863040, 'steps': 98244, 'loss/train': 0.024284644052386284} 08/31/2021 06:59:47 - INFO - __main__ - Step 98246: {'lr': 0.00013628965140439543, 'samples': 18863232, 'steps': 98245, 'loss/train': 0.018188247457146645} 08/31/2021 06:59:47 - INFO - __main__ - Step 98247: {'lr': 0.00013628492538964753, 'samples': 18863424, 'steps': 98246, 'loss/train': 1.35826575756073} 08/31/2021 06:59:47 - INFO - __main__ - Step 98248: {'lr': 0.0001362801994261379, 'samples': 18863616, 'steps': 98247, 'loss/train': 4.340117454528809} 08/31/2021 06:59:50 - INFO - __main__ - Step 98249: {'lr': 0.00013627547351386865, 'samples': 18863808, 'steps': 98248, 'loss/train': 1.167434573173523} 08/31/2021 06:59:50 - INFO - __main__ - Step 98250: {'lr': 0.00013627074765284192, 'samples': 18864000, 'steps': 98249, 'loss/train': 0.7995387315750122} 08/31/2021 06:59:50 - INFO - __main__ - Step 98251: {'lr': 0.00013626602184305987, 'samples': 18864192, 'steps': 98250, 'loss/train': 0.7619916200637817} 08/31/2021 06:59:51 - INFO - __main__ - Step 98252: {'lr': 0.00013626129608452454, 'samples': 18864384, 'steps': 98251, 'loss/train': 0.9371215105056763} 08/31/2021 06:59:51 - INFO - __main__ - Step 98253: {'lr': 0.00013625657037723816, 'samples': 18864576, 'steps': 98252, 'loss/train': 0.018155522644519806} 08/31/2021 06:59:51 - INFO - __main__ - Step 98254: {'lr': 0.00013625184472120278, 'samples': 18864768, 'steps': 98253, 'loss/train': 0.5526999831199646} 08/31/2021 06:59:53 - INFO - __main__ - Step 98255: {'lr': 0.00013624711911642057, 'samples': 18864960, 'steps': 98254, 'loss/train': 0.5363374352455139} 08/31/2021 06:59:54 - INFO - __main__ - Step 98256: {'lr': 0.0001362423935628937, 'samples': 18865152, 'steps': 98255, 'loss/train': 0.4615935981273651} 08/31/2021 06:59:54 - INFO - __main__ - Step 98257: {'lr': 0.0001362376680606242, 'samples': 18865344, 'steps': 98256, 'loss/train': 1.6871705055236816} 08/31/2021 06:59:54 - INFO - __main__ - Step 98258: {'lr': 0.00013623294260961427, 'samples': 18865536, 'steps': 98257, 'loss/train': 1.0276018381118774} 08/31/2021 06:59:55 - INFO - __main__ - Step 98259: {'lr': 0.00013622821720986613, 'samples': 18865728, 'steps': 98258, 'loss/train': 0.21315225958824158} 08/31/2021 06:59:56 - INFO - __main__ - Step 98260: {'lr': 0.00013622349186138166, 'samples': 18865920, 'steps': 98259, 'loss/train': 0.864101231098175} 08/31/2021 06:59:57 - INFO - __main__ - Step 98261: {'lr': 0.00013621876656416316, 'samples': 18866112, 'steps': 98260, 'loss/train': 1.3627747297286987} 08/31/2021 06:59:57 - INFO - __main__ - Step 98262: {'lr': 0.00013621404131821275, 'samples': 18866304, 'steps': 98261, 'loss/train': 0.9602535367012024} 08/31/2021 06:59:57 - INFO - __main__ - Step 98263: {'lr': 0.0001362093161235325, 'samples': 18866496, 'steps': 98262, 'loss/train': 0.6863746643066406} 08/31/2021 06:59:58 - INFO - __main__ - Step 98264: {'lr': 0.00013620459098012458, 'samples': 18866688, 'steps': 98263, 'loss/train': 1.4934190511703491} 08/31/2021 06:59:59 - INFO - __main__ - Step 98265: {'lr': 0.0001361998658879911, 'samples': 18866880, 'steps': 98264, 'loss/train': 0.9510440230369568} 08/31/2021 07:00:00 - INFO - __main__ - Step 98266: {'lr': 0.00013619514084713426, 'samples': 18867072, 'steps': 98265, 'loss/train': 1.0609033107757568} 08/31/2021 07:00:00 - INFO - __main__ - Step 98267: {'lr': 0.00013619041585755608, 'samples': 18867264, 'steps': 98266, 'loss/train': 1.4681223630905151} 08/31/2021 07:00:00 - INFO - __main__ - Step 98268: {'lr': 0.00013618569091925875, 'samples': 18867456, 'steps': 98267, 'loss/train': 0.7332401275634766} 08/31/2021 07:00:01 - INFO - __main__ - Step 98269: {'lr': 0.00013618096603224442, 'samples': 18867648, 'steps': 98268, 'loss/train': 0.6424439549446106} 08/31/2021 07:00:03 - INFO - __main__ - Step 98270: {'lr': 0.00013617624119651516, 'samples': 18867840, 'steps': 98269, 'loss/train': 0.06756855547428131} 08/31/2021 07:00:04 - INFO - __main__ - Step 98271: {'lr': 0.00013617151641207316, 'samples': 18868032, 'steps': 98270, 'loss/train': 1.2275327444076538} 08/31/2021 07:00:04 - INFO - __main__ - Step 98272: {'lr': 0.00013616679167892048, 'samples': 18868224, 'steps': 98271, 'loss/train': 1.1395319700241089} 08/31/2021 07:00:04 - INFO - __main__ - Step 98273: {'lr': 0.00013616206699705943, 'samples': 18868416, 'steps': 98272, 'loss/train': 0.15566802024841309} 08/31/2021 07:00:05 - INFO - __main__ - Step 98274: {'lr': 0.00013615734236649188, 'samples': 18868608, 'steps': 98273, 'loss/train': 1.2779242992401123} 08/31/2021 07:00:07 - INFO - __main__ - Step 98275: {'lr': 0.00013615261778722007, 'samples': 18868800, 'steps': 98274, 'loss/train': 0.06686249375343323} 08/31/2021 07:00:07 - INFO - __main__ - Step 98276: {'lr': 0.00013614789325924615, 'samples': 18868992, 'steps': 98275, 'loss/train': 0.631263792514801} 08/31/2021 07:00:07 - INFO - __main__ - Step 98277: {'lr': 0.0001361431687825722, 'samples': 18869184, 'steps': 98276, 'loss/train': 1.674951195716858} 08/31/2021 07:00:08 - INFO - __main__ - Step 98278: {'lr': 0.0001361384443572004, 'samples': 18869376, 'steps': 98277, 'loss/train': 1.2851542234420776} 08/31/2021 07:00:08 - INFO - __main__ - Step 98279: {'lr': 0.00013613371998313285, 'samples': 18869568, 'steps': 98278, 'loss/train': 1.013748049736023} 08/31/2021 07:00:09 - INFO - __main__ - Step 98280: {'lr': 0.0001361289956603717, 'samples': 18869760, 'steps': 98279, 'loss/train': 1.1987274885177612} 08/31/2021 07:00:10 - INFO - __main__ - Step 98281: {'lr': 0.00013612427138891907, 'samples': 18869952, 'steps': 98280, 'loss/train': 1.7064926624298096} 08/31/2021 07:00:11 - INFO - __main__ - Step 98282: {'lr': 0.00013611954716877706, 'samples': 18870144, 'steps': 98281, 'loss/train': 0.5042060613632202} 08/31/2021 07:00:11 - INFO - __main__ - Step 98283: {'lr': 0.00013611482299994787, 'samples': 18870336, 'steps': 98282, 'loss/train': 1.375766396522522} 08/31/2021 07:00:11 - INFO - __main__ - Step 98284: {'lr': 0.00013611009888243354, 'samples': 18870528, 'steps': 98283, 'loss/train': 0.9726049304008484} 08/31/2021 07:00:12 - INFO - __main__ - Step 98285: {'lr': 0.00013610537481623626, 'samples': 18870720, 'steps': 98284, 'loss/train': 0.9769461750984192} 08/31/2021 07:00:13 - INFO - __main__ - Step 98286: {'lr': 0.00013610065080135825, 'samples': 18870912, 'steps': 98285, 'loss/train': 1.2466354370117188} 08/31/2021 07:00:14 - INFO - __main__ - Step 98287: {'lr': 0.00013609592683780142, 'samples': 18871104, 'steps': 98286, 'loss/train': 1.1671955585479736} 08/31/2021 07:00:14 - INFO - __main__ - Step 98288: {'lr': 0.000136091202925568, 'samples': 18871296, 'steps': 98287, 'loss/train': 1.0340036153793335} 08/31/2021 07:00:14 - INFO - __main__ - Step 98289: {'lr': 0.00013608647906466015, 'samples': 18871488, 'steps': 98288, 'loss/train': 1.3821982145309448} 08/31/2021 07:00:15 - INFO - __main__ - Step 98290: {'lr': 0.00013608175525507994, 'samples': 18871680, 'steps': 98289, 'loss/train': 0.8783309459686279} 08/31/2021 07:00:16 - INFO - __main__ - Step 98291: {'lr': 0.00013607703149682955, 'samples': 18871872, 'steps': 98290, 'loss/train': 1.0131193399429321} 08/31/2021 07:00:17 - INFO - __main__ - Step 98292: {'lr': 0.0001360723077899111, 'samples': 18872064, 'steps': 98291, 'loss/train': 0.8632020354270935} 08/31/2021 07:00:17 - INFO - __main__ - Step 98293: {'lr': 0.00013606758413432668, 'samples': 18872256, 'steps': 98292, 'loss/train': 0.999121367931366} 08/31/2021 07:00:17 - INFO - __main__ - Step 98294: {'lr': 0.00013606286053007848, 'samples': 18872448, 'steps': 98293, 'loss/train': 1.2198877334594727} 08/31/2021 07:00:18 - INFO - __main__ - Step 98295: {'lr': 0.0001360581369771686, 'samples': 18872640, 'steps': 98294, 'loss/train': 1.4780588150024414} 08/31/2021 07:00:20 - INFO - __main__ - Step 98296: {'lr': 0.00013605341347559916, 'samples': 18872832, 'steps': 98295, 'loss/train': 1.2291538715362549} 08/31/2021 07:00:20 - INFO - __main__ - Step 98297: {'lr': 0.00013604869002537229, 'samples': 18873024, 'steps': 98296, 'loss/train': 1.3270421028137207} 08/31/2021 07:00:21 - INFO - __main__ - Step 98298: {'lr': 0.0001360439666264901, 'samples': 18873216, 'steps': 98297, 'loss/train': 1.6655758619308472} 08/31/2021 07:00:21 - INFO - __main__ - Step 98299: {'lr': 0.00013603924327895478, 'samples': 18873408, 'steps': 98298, 'loss/train': 1.8236806392669678} 08/31/2021 07:00:21 - INFO - __main__ - Step 98300: {'lr': 0.0001360345199827685, 'samples': 18873600, 'steps': 98299, 'loss/train': 0.28717952966690063} 08/31/2021 07:00:23 - INFO - __main__ - Step 98301: {'lr': 0.0001360297967379332, 'samples': 18873792, 'steps': 98300, 'loss/train': 0.14958365261554718} 08/31/2021 07:00:23 - INFO - __main__ - Step 98302: {'lr': 0.00013602507354445111, 'samples': 18873984, 'steps': 98301, 'loss/train': 0.5760176777839661} 08/31/2021 07:00:23 - INFO - __main__ - Step 98303: {'lr': 0.00013602035040232439, 'samples': 18874176, 'steps': 98302, 'loss/train': 1.239507794380188} 08/31/2021 07:00:24 - INFO - __main__ - Step 98304: {'lr': 0.00013601562731155512, 'samples': 18874368, 'steps': 98303, 'loss/train': 1.0268182754516602} 08/31/2021 07:00:24 - INFO - __main__ - Step 98305: {'lr': 0.00013601090427214547, 'samples': 18874560, 'steps': 98304, 'loss/train': 1.0713167190551758} 08/31/2021 07:00:24 - INFO - __main__ - Step 98306: {'lr': 0.0001360061812840975, 'samples': 18874752, 'steps': 98305, 'loss/train': 1.3238118886947632} 08/31/2021 07:00:26 - INFO - __main__ - Step 98307: {'lr': 0.00013600145834741342, 'samples': 18874944, 'steps': 98306, 'loss/train': 0.3518293797969818} 08/31/2021 07:00:27 - INFO - __main__ - Step 98308: {'lr': 0.00013599673546209535, 'samples': 18875136, 'steps': 98307, 'loss/train': 1.4642865657806396} 08/31/2021 07:00:27 - INFO - __main__ - Step 98309: {'lr': 0.00013599201262814534, 'samples': 18875328, 'steps': 98308, 'loss/train': 0.07436562329530716} 08/31/2021 07:00:27 - INFO - __main__ - Step 98310: {'lr': 0.00013598728984556558, 'samples': 18875520, 'steps': 98309, 'loss/train': 1.2002990245819092} 08/31/2021 07:00:28 - INFO - __main__ - Step 98311: {'lr': 0.0001359825671143582, 'samples': 18875712, 'steps': 98310, 'loss/train': 1.4003163576126099} 08/31/2021 07:00:29 - INFO - __main__ - Step 98312: {'lr': 0.00013597784443452533, 'samples': 18875904, 'steps': 98311, 'loss/train': 0.7878897786140442} 08/31/2021 07:00:30 - INFO - __main__ - Step 98313: {'lr': 0.00013597312180606917, 'samples': 18876096, 'steps': 98312, 'loss/train': 1.0007507801055908} 08/31/2021 07:00:30 - INFO - __main__ - Step 98314: {'lr': 0.00013596839922899165, 'samples': 18876288, 'steps': 98313, 'loss/train': 0.17161919176578522} 08/31/2021 07:00:31 - INFO - __main__ - Step 98315: {'lr': 0.000135963676703295, 'samples': 18876480, 'steps': 98314, 'loss/train': 0.9437064528465271} 08/31/2021 07:00:31 - INFO - __main__ - Step 98316: {'lr': 0.0001359589542289814, 'samples': 18876672, 'steps': 98315, 'loss/train': 0.3477555215358734} 08/31/2021 07:00:32 - INFO - __main__ - Step 98317: {'lr': 0.00013595423180605293, 'samples': 18876864, 'steps': 98316, 'loss/train': 0.817925214767456} 08/31/2021 07:00:33 - INFO - __main__ - Step 98318: {'lr': 0.0001359495094345117, 'samples': 18877056, 'steps': 98317, 'loss/train': 1.4331198930740356} 08/31/2021 07:00:33 - INFO - __main__ - Step 98319: {'lr': 0.00013594478711435987, 'samples': 18877248, 'steps': 98318, 'loss/train': 1.3976854085922241} 08/31/2021 07:00:34 - INFO - __main__ - Step 98320: {'lr': 0.00013594006484559957, 'samples': 18877440, 'steps': 98319, 'loss/train': 0.7853626608848572} 08/31/2021 07:00:34 - INFO - __main__ - Step 98321: {'lr': 0.00013593534262823287, 'samples': 18877632, 'steps': 98320, 'loss/train': 0.700370192527771} 08/31/2021 07:00:36 - INFO - __main__ - Step 98322: {'lr': 0.000135930620462262, 'samples': 18877824, 'steps': 98321, 'loss/train': 1.2216819524765015} 08/31/2021 07:00:36 - INFO - __main__ - Step 98323: {'lr': 0.000135925898347689, 'samples': 18878016, 'steps': 98322, 'loss/train': 1.1632310152053833} 08/31/2021 07:00:36 - INFO - __main__ - Step 98324: {'lr': 0.00013592117628451607, 'samples': 18878208, 'steps': 98323, 'loss/train': 1.0103609561920166} 08/31/2021 07:00:37 - INFO - __main__ - Step 98325: {'lr': 0.00013591645427274524, 'samples': 18878400, 'steps': 98324, 'loss/train': 0.5667015314102173} 08/31/2021 07:00:37 - INFO - __main__ - Step 98326: {'lr': 0.00013591173231237874, 'samples': 18878592, 'steps': 98325, 'loss/train': 1.266100525856018} 08/31/2021 07:00:39 - INFO - __main__ - Step 98327: {'lr': 0.00013590701040341874, 'samples': 18878784, 'steps': 98326, 'loss/train': 1.1841922998428345} 08/31/2021 07:00:39 - INFO - __main__ - Step 98328: {'lr': 0.00013590228854586716, 'samples': 18878976, 'steps': 98327, 'loss/train': 1.1487804651260376} 08/31/2021 07:00:40 - INFO - __main__ - Step 98329: {'lr': 0.00013589756673972628, 'samples': 18879168, 'steps': 98328, 'loss/train': 1.2106212377548218} 08/31/2021 07:00:40 - INFO - __main__ - Step 98330: {'lr': 0.00013589284498499818, 'samples': 18879360, 'steps': 98329, 'loss/train': 0.6759989857673645} 08/31/2021 07:00:41 - INFO - __main__ - Step 98331: {'lr': 0.000135888123281685, 'samples': 18879552, 'steps': 98330, 'loss/train': 1.6125633716583252} 08/31/2021 07:00:41 - INFO - __main__ - Step 98332: {'lr': 0.0001358834016297889, 'samples': 18879744, 'steps': 98331, 'loss/train': 0.052230287343263626} 08/31/2021 07:00:42 - INFO - __main__ - Step 98333: {'lr': 0.00013587868002931192, 'samples': 18879936, 'steps': 98332, 'loss/train': 1.340161919593811} 08/31/2021 07:00:43 - INFO - __main__ - Step 98334: {'lr': 0.0001358739584802563, 'samples': 18880128, 'steps': 98333, 'loss/train': 0.846270740032196} 08/31/2021 07:00:43 - INFO - __main__ - Step 98335: {'lr': 0.0001358692369826241, 'samples': 18880320, 'steps': 98334, 'loss/train': 0.9211127758026123} 08/31/2021 07:00:43 - INFO - __main__ - Step 98336: {'lr': 0.00013586451553641743, 'samples': 18880512, 'steps': 98335, 'loss/train': 1.245052456855774} 08/31/2021 07:00:44 - INFO - __main__ - Step 98337: {'lr': 0.00013585979414163846, 'samples': 18880704, 'steps': 98336, 'loss/train': 1.8590106964111328} 08/31/2021 07:00:45 - INFO - __main__ - Step 98338: {'lr': 0.00013585507279828933, 'samples': 18880896, 'steps': 98337, 'loss/train': 0.3581724464893341} 08/31/2021 07:00:46 - INFO - __main__ - Step 98339: {'lr': 0.00013585035150637215, 'samples': 18881088, 'steps': 98338, 'loss/train': 1.0733245611190796} 08/31/2021 07:00:46 - INFO - __main__ - Step 98340: {'lr': 0.0001358456302658891, 'samples': 18881280, 'steps': 98339, 'loss/train': 2.0989251136779785} 08/31/2021 07:00:46 - INFO - __main__ - Step 98341: {'lr': 0.00013584090907684215, 'samples': 18881472, 'steps': 98340, 'loss/train': 1.2661899328231812} 08/31/2021 07:00:47 - INFO - __main__ - Step 98342: {'lr': 0.00013583618793923358, 'samples': 18881664, 'steps': 98341, 'loss/train': 0.2042795568704605} 08/31/2021 07:00:48 - INFO - __main__ - Step 98343: {'lr': 0.00013583146685306542, 'samples': 18881856, 'steps': 98342, 'loss/train': 1.4297702312469482} 08/31/2021 07:00:49 - INFO - __main__ - Step 98344: {'lr': 0.0001358267458183398, 'samples': 18882048, 'steps': 98343, 'loss/train': 1.0755411386489868} 08/31/2021 07:00:49 - INFO - __main__ - Step 98345: {'lr': 0.00013582202483505896, 'samples': 18882240, 'steps': 98344, 'loss/train': 0.8919167518615723} 08/31/2021 07:00:49 - INFO - __main__ - Step 98346: {'lr': 0.00013581730390322495, 'samples': 18882432, 'steps': 98345, 'loss/train': 0.9518182277679443} 08/31/2021 07:00:50 - INFO - __main__ - Step 98347: {'lr': 0.00013581258302283985, 'samples': 18882624, 'steps': 98346, 'loss/train': 0.4088720977306366} 08/31/2021 07:00:51 - INFO - __main__ - Step 98348: {'lr': 0.00013580786219390587, 'samples': 18882816, 'steps': 98347, 'loss/train': 1.7669575214385986} 08/31/2021 07:00:52 - INFO - __main__ - Step 98349: {'lr': 0.00013580314141642508, 'samples': 18883008, 'steps': 98348, 'loss/train': 1.5743821859359741} 08/31/2021 07:00:52 - INFO - __main__ - Step 98350: {'lr': 0.00013579842069039966, 'samples': 18883200, 'steps': 98349, 'loss/train': 1.1016716957092285} 08/31/2021 07:00:52 - INFO - __main__ - Step 98351: {'lr': 0.0001357937000158317, 'samples': 18883392, 'steps': 98350, 'loss/train': 1.1347507238388062} 08/31/2021 07:00:53 - INFO - __main__ - Step 98352: {'lr': 0.00013578897939272333, 'samples': 18883584, 'steps': 98351, 'loss/train': 1.034494161605835} 08/31/2021 07:00:54 - INFO - __main__ - Step 98353: {'lr': 0.0001357842588210768, 'samples': 18883776, 'steps': 98352, 'loss/train': 1.073229193687439} 08/31/2021 07:00:55 - INFO - __main__ - Step 98354: {'lr': 0.000135779538300894, 'samples': 18883968, 'steps': 98353, 'loss/train': 1.0001146793365479} 08/31/2021 07:00:55 - INFO - __main__ - Step 98355: {'lr': 0.00013577481783217722, 'samples': 18884160, 'steps': 98354, 'loss/train': 1.4182301759719849} 08/31/2021 07:00:55 - INFO - __main__ - Step 98356: {'lr': 0.00013577009741492848, 'samples': 18884352, 'steps': 98355, 'loss/train': 0.850542426109314} 08/31/2021 07:00:56 - INFO - __main__ - Step 98357: {'lr': 0.00013576537704915003, 'samples': 18884544, 'steps': 98356, 'loss/train': 0.9032773375511169} 08/31/2021 07:00:57 - INFO - __main__ - Step 98358: {'lr': 0.0001357606567348439, 'samples': 18884736, 'steps': 98357, 'loss/train': 1.0846861600875854} 08/31/2021 07:00:58 - INFO - __main__ - Step 98359: {'lr': 0.00013575593647201226, 'samples': 18884928, 'steps': 98358, 'loss/train': 1.1696521043777466} 08/31/2021 07:00:58 - INFO - __main__ - Step 98360: {'lr': 0.00013575121626065723, 'samples': 18885120, 'steps': 98359, 'loss/train': 0.6686661839485168} 08/31/2021 07:00:59 - INFO - __main__ - Step 98361: {'lr': 0.00013574649610078096, 'samples': 18885312, 'steps': 98360, 'loss/train': 1.0450360774993896} 08/31/2021 07:00:59 - INFO - __main__ - Step 98362: {'lr': 0.00013574177599238554, 'samples': 18885504, 'steps': 98361, 'loss/train': 1.5035032033920288} 08/31/2021 07:00:59 - INFO - __main__ - Step 98363: {'lr': 0.00013573705593547314, 'samples': 18885696, 'steps': 98362, 'loss/train': 1.396562933921814} 08/31/2021 07:01:01 - INFO - __main__ - Step 98364: {'lr': 0.0001357323359300458, 'samples': 18885888, 'steps': 98363, 'loss/train': 1.6044222116470337} 08/31/2021 07:01:02 - INFO - __main__ - Step 98365: {'lr': 0.00013572761597610577, 'samples': 18886080, 'steps': 98364, 'loss/train': 1.383721947669983} 08/31/2021 07:01:02 - INFO - __main__ - Step 98366: {'lr': 0.00013572289607365518, 'samples': 18886272, 'steps': 98365, 'loss/train': 0.4871332049369812} 08/31/2021 07:01:02 - INFO - __main__ - Step 98367: {'lr': 0.000135718176222696, 'samples': 18886464, 'steps': 98366, 'loss/train': 0.9616862535476685} 08/31/2021 07:01:03 - INFO - __main__ - Step 98368: {'lr': 0.00013571345642323043, 'samples': 18886656, 'steps': 98367, 'loss/train': 1.0901414155960083} 08/31/2021 07:01:04 - INFO - __main__ - Step 98369: {'lr': 0.00013570873667526062, 'samples': 18886848, 'steps': 98368, 'loss/train': 0.9220381379127502} 08/31/2021 07:01:05 - INFO - __main__ - Step 98370: {'lr': 0.0001357040169787887, 'samples': 18887040, 'steps': 98369, 'loss/train': 1.4394944906234741} 08/31/2021 07:01:05 - INFO - __main__ - Step 98371: {'lr': 0.00013569929733381678, 'samples': 18887232, 'steps': 98370, 'loss/train': 0.7831174731254578} 08/31/2021 07:01:05 - INFO - __main__ - Step 98372: {'lr': 0.000135694577740347, 'samples': 18887424, 'steps': 98371, 'loss/train': 1.1419576406478882} 08/31/2021 07:01:06 - INFO - __main__ - Step 98373: {'lr': 0.00013568985819838148, 'samples': 18887616, 'steps': 98372, 'loss/train': 1.177843451499939} 08/31/2021 07:01:07 - INFO - __main__ - Step 98374: {'lr': 0.00013568513870792232, 'samples': 18887808, 'steps': 98373, 'loss/train': 0.7745641469955444} 08/31/2021 07:01:08 - INFO - __main__ - Step 98375: {'lr': 0.00013568041926897168, 'samples': 18888000, 'steps': 98374, 'loss/train': 1.1620337963104248} 08/31/2021 07:01:08 - INFO - __main__ - Step 98376: {'lr': 0.00013567569988153172, 'samples': 18888192, 'steps': 98375, 'loss/train': 1.6872884035110474} 08/31/2021 07:01:08 - INFO - __main__ - Step 98377: {'lr': 0.00013567098054560457, 'samples': 18888384, 'steps': 98376, 'loss/train': 0.6430014371871948} 08/31/2021 07:01:09 - INFO - __main__ - Step 98378: {'lr': 0.00013566626126119226, 'samples': 18888576, 'steps': 98377, 'loss/train': 1.1793787479400635} 08/31/2021 07:01:10 - INFO - __main__ - Step 98379: {'lr': 0.00013566154202829695, 'samples': 18888768, 'steps': 98378, 'loss/train': 1.0407792329788208} 08/31/2021 07:01:11 - INFO - __main__ - Step 98380: {'lr': 0.00013565682284692076, 'samples': 18888960, 'steps': 98379, 'loss/train': 1.1720188856124878} 08/31/2021 07:01:11 - INFO - __main__ - Step 98381: {'lr': 0.00013565210371706588, 'samples': 18889152, 'steps': 98380, 'loss/train': 1.077965497970581} 08/31/2021 07:01:12 - INFO - __main__ - Step 98382: {'lr': 0.00013564738463873438, 'samples': 18889344, 'steps': 98381, 'loss/train': 1.419891119003296} 08/31/2021 07:01:12 - INFO - __main__ - Step 98383: {'lr': 0.0001356426656119284, 'samples': 18889536, 'steps': 98382, 'loss/train': 4.277944087982178} 08/31/2021 07:01:12 - INFO - __main__ - Step 98384: {'lr': 0.00013563794663665007, 'samples': 18889728, 'steps': 98383, 'loss/train': 1.2023937702178955} 08/31/2021 07:01:14 - INFO - __main__ - Step 98385: {'lr': 0.0001356332277129015, 'samples': 18889920, 'steps': 98384, 'loss/train': 1.3469434976577759} 08/31/2021 07:01:14 - INFO - __main__ - Step 98386: {'lr': 0.00013562850884068486, 'samples': 18890112, 'steps': 98385, 'loss/train': 1.7840651273727417} 08/31/2021 07:01:15 - INFO - __main__ - Step 98387: {'lr': 0.00013562379002000235, 'samples': 18890304, 'steps': 98386, 'loss/train': 0.536411464214325} 08/31/2021 07:01:15 - INFO - __main__ - Step 98388: {'lr': 0.00013561907125085587, 'samples': 18890496, 'steps': 98387, 'loss/train': 1.579813003540039} 08/31/2021 07:01:15 - INFO - __main__ - Step 98389: {'lr': 0.00013561435253324773, 'samples': 18890688, 'steps': 98388, 'loss/train': 1.2798984050750732} 08/31/2021 07:01:17 - INFO - __main__ - Step 98390: {'lr': 0.00013560963386717996, 'samples': 18890880, 'steps': 98389, 'loss/train': 0.6176514029502869} 08/31/2021 07:01:17 - INFO - __main__ - Step 98391: {'lr': 0.00013560491525265467, 'samples': 18891072, 'steps': 98390, 'loss/train': 0.8543745875358582} 08/31/2021 07:01:18 - INFO - __main__ - Step 98392: {'lr': 0.0001356001966896741, 'samples': 18891264, 'steps': 98391, 'loss/train': 1.2390140295028687} 08/31/2021 07:01:18 - INFO - __main__ - Step 98393: {'lr': 0.0001355954781782403, 'samples': 18891456, 'steps': 98392, 'loss/train': 1.5005896091461182} 08/31/2021 07:01:18 - INFO - __main__ - Step 98394: {'lr': 0.00013559075971835544, 'samples': 18891648, 'steps': 98393, 'loss/train': 0.9448142647743225} 08/31/2021 07:01:20 - INFO - __main__ - Step 98395: {'lr': 0.0001355860413100216, 'samples': 18891840, 'steps': 98394, 'loss/train': 0.9612072706222534} 08/31/2021 07:01:20 - INFO - __main__ - Step 98396: {'lr': 0.0001355813229532409, 'samples': 18892032, 'steps': 98395, 'loss/train': 1.1405476331710815} 08/31/2021 07:01:21 - INFO - __main__ - Step 98397: {'lr': 0.0001355766046480155, 'samples': 18892224, 'steps': 98396, 'loss/train': 1.2551411390304565} 08/31/2021 07:01:21 - INFO - __main__ - Step 98398: {'lr': 0.00013557188639434764, 'samples': 18892416, 'steps': 98397, 'loss/train': 1.5087863206863403} 08/31/2021 07:01:21 - INFO - __main__ - Step 98399: {'lr': 0.00013556716819223923, 'samples': 18892608, 'steps': 98398, 'loss/train': 1.1481159925460815} 08/31/2021 07:01:22 - INFO - __main__ - Step 98400: {'lr': 0.00013556245004169246, 'samples': 18892800, 'steps': 98399, 'loss/train': 0.35642072558403015} 08/31/2021 07:01:24 - INFO - __main__ - Step 98401: {'lr': 0.00013555773194270948, 'samples': 18892992, 'steps': 98400, 'loss/train': 1.031781554222107} 08/31/2021 07:01:24 - INFO - __main__ - Step 98402: {'lr': 0.00013555301389529245, 'samples': 18893184, 'steps': 98401, 'loss/train': 1.1043394804000854} 08/31/2021 07:01:25 - INFO - __main__ - Step 98403: {'lr': 0.00013554829589944344, 'samples': 18893376, 'steps': 98402, 'loss/train': 0.035463836044073105} 08/31/2021 07:01:25 - INFO - __main__ - Step 98404: {'lr': 0.00013554357795516462, 'samples': 18893568, 'steps': 98403, 'loss/train': 0.5044965744018555} 08/31/2021 07:01:25 - INFO - __main__ - Step 98405: {'lr': 0.0001355388600624581, 'samples': 18893760, 'steps': 98404, 'loss/train': 1.3892552852630615} 08/31/2021 07:01:27 - INFO - __main__ - Step 98406: {'lr': 0.00013553414222132598, 'samples': 18893952, 'steps': 98405, 'loss/train': 0.12066002190113068} 08/31/2021 07:01:28 - INFO - __main__ - Step 98407: {'lr': 0.00013552942443177042, 'samples': 18894144, 'steps': 98406, 'loss/train': 1.4843641519546509} 08/31/2021 07:01:28 - INFO - __main__ - Step 98408: {'lr': 0.00013552470669379353, 'samples': 18894336, 'steps': 98407, 'loss/train': 1.4044743776321411} 08/31/2021 07:01:28 - INFO - __main__ - Step 98409: {'lr': 0.00013551998900739753, 'samples': 18894528, 'steps': 98408, 'loss/train': 1.3860722780227661} 08/31/2021 07:01:29 - INFO - __main__ - Step 98410: {'lr': 0.0001355152713725844, 'samples': 18894720, 'steps': 98409, 'loss/train': 1.428444743156433} 08/31/2021 07:01:30 - INFO - __main__ - Step 98411: {'lr': 0.0001355105537893563, 'samples': 18894912, 'steps': 98410, 'loss/train': 1.2057956457138062} 08/31/2021 07:01:31 - INFO - __main__ - Step 98412: {'lr': 0.00013550583625771535, 'samples': 18895104, 'steps': 98411, 'loss/train': 1.691049337387085} 08/31/2021 07:01:31 - INFO - __main__ - Step 98413: {'lr': 0.00013550111877766373, 'samples': 18895296, 'steps': 98412, 'loss/train': 1.4710605144500732} 08/31/2021 07:01:32 - INFO - __main__ - Step 98414: {'lr': 0.00013549640134920355, 'samples': 18895488, 'steps': 98413, 'loss/train': 0.015756091102957726} 08/31/2021 07:01:32 - INFO - __main__ - Step 98415: {'lr': 0.00013549168397233692, 'samples': 18895680, 'steps': 98414, 'loss/train': 1.1101524829864502} 08/31/2021 07:01:32 - INFO - __main__ - Step 98416: {'lr': 0.00013548696664706595, 'samples': 18895872, 'steps': 98415, 'loss/train': 1.2326786518096924} 08/31/2021 07:01:34 - INFO - __main__ - Step 98417: {'lr': 0.00013548224937339276, 'samples': 18896064, 'steps': 98416, 'loss/train': 0.9202932119369507} 08/31/2021 07:01:34 - INFO - __main__ - Step 98418: {'lr': 0.00013547753215131954, 'samples': 18896256, 'steps': 98417, 'loss/train': 0.10192430764436722} 08/31/2021 07:01:35 - INFO - __main__ - Step 98419: {'lr': 0.0001354728149808484, 'samples': 18896448, 'steps': 98418, 'loss/train': 1.4095447063446045} 08/31/2021 07:01:35 - INFO - __main__ - Step 98420: {'lr': 0.00013546809786198137, 'samples': 18896640, 'steps': 98419, 'loss/train': 1.611836552619934} 08/31/2021 07:01:35 - INFO - __main__ - Step 98421: {'lr': 0.00013546338079472082, 'samples': 18896832, 'steps': 98420, 'loss/train': 1.2855658531188965} 08/31/2021 07:01:38 - INFO - __main__ - Step 98422: {'lr': 0.00013545866377906858, 'samples': 18897024, 'steps': 98421, 'loss/train': 1.1406725645065308} 08/31/2021 07:01:38 - INFO - __main__ - Step 98423: {'lr': 0.00013545394681502689, 'samples': 18897216, 'steps': 98422, 'loss/train': 1.650492787361145} 08/31/2021 07:01:38 - INFO - __main__ - Step 98424: {'lr': 0.0001354492299025979, 'samples': 18897408, 'steps': 98423, 'loss/train': 1.64796781539917} 08/31/2021 07:01:39 - INFO - __main__ - Step 98425: {'lr': 0.0001354445130417837, 'samples': 18897600, 'steps': 98424, 'loss/train': 0.7640275955200195} 08/31/2021 07:01:39 - INFO - __main__ - Step 98426: {'lr': 0.00013543979623258646, 'samples': 18897792, 'steps': 98425, 'loss/train': 1.0168697834014893} 08/31/2021 07:01:41 - INFO - __main__ - Step 98427: {'lr': 0.00013543507947500825, 'samples': 18897984, 'steps': 98426, 'loss/train': 0.02959529682993889} 08/31/2021 07:01:41 - INFO - __main__ - Step 98428: {'lr': 0.00013543036276905123, 'samples': 18898176, 'steps': 98427, 'loss/train': 1.356474757194519} 08/31/2021 07:01:42 - INFO - __main__ - Step 98429: {'lr': 0.00013542564611471753, 'samples': 18898368, 'steps': 98428, 'loss/train': 0.7127218246459961} 08/31/2021 07:01:42 - INFO - __main__ - Step 98430: {'lr': 0.00013542092951200927, 'samples': 18898560, 'steps': 98429, 'loss/train': 0.43507060408592224} 08/31/2021 07:01:42 - INFO - __main__ - Step 98431: {'lr': 0.00013541621296092856, 'samples': 18898752, 'steps': 98430, 'loss/train': 0.2911485433578491} 08/31/2021 07:01:43 - INFO - __main__ - Step 98432: {'lr': 0.00013541149646147755, 'samples': 18898944, 'steps': 98431, 'loss/train': 1.6517037153244019} 08/31/2021 07:01:44 - INFO - __main__ - Step 98433: {'lr': 0.00013540678001365837, 'samples': 18899136, 'steps': 98432, 'loss/train': 1.3665183782577515} 08/31/2021 07:01:45 - INFO - __main__ - Step 98434: {'lr': 0.00013540206361747318, 'samples': 18899328, 'steps': 98433, 'loss/train': 1.7159991264343262} 08/31/2021 07:01:45 - INFO - __main__ - Step 98435: {'lr': 0.00013539734727292398, 'samples': 18899520, 'steps': 98434, 'loss/train': 1.0110620260238647} 08/31/2021 07:01:45 - INFO - __main__ - Step 98436: {'lr': 0.00013539263098001294, 'samples': 18899712, 'steps': 98435, 'loss/train': 0.7370926737785339} 08/31/2021 07:01:46 - INFO - __main__ - Step 98437: {'lr': 0.00013538791473874224, 'samples': 18899904, 'steps': 98436, 'loss/train': 1.4725069999694824} 08/31/2021 07:01:47 - INFO - __main__ - Step 98438: {'lr': 0.00013538319854911396, 'samples': 18900096, 'steps': 98437, 'loss/train': 1.2590090036392212} 08/31/2021 07:01:48 - INFO - __main__ - Step 98439: {'lr': 0.00013537848241113027, 'samples': 18900288, 'steps': 98438, 'loss/train': 0.8521704077720642} 08/31/2021 07:01:48 - INFO - __main__ - Step 98440: {'lr': 0.00013537376632479325, 'samples': 18900480, 'steps': 98439, 'loss/train': 1.1217259168624878} 08/31/2021 07:01:48 - INFO - __main__ - Step 98441: {'lr': 0.00013536905029010505, 'samples': 18900672, 'steps': 98440, 'loss/train': 1.094312310218811} 08/31/2021 07:01:49 - INFO - __main__ - Step 98442: {'lr': 0.00013536433430706775, 'samples': 18900864, 'steps': 98441, 'loss/train': 2.01471209526062} 08/31/2021 07:01:51 - INFO - __main__ - Step 98443: {'lr': 0.00013535961837568355, 'samples': 18901056, 'steps': 98442, 'loss/train': 1.3373167514801025} 08/31/2021 07:01:51 - INFO - __main__ - Step 98444: {'lr': 0.0001353549024959545, 'samples': 18901248, 'steps': 98443, 'loss/train': 1.1940284967422485} 08/31/2021 07:01:51 - INFO - __main__ - Step 98445: {'lr': 0.0001353501866678828, 'samples': 18901440, 'steps': 98444, 'loss/train': 1.4754756689071655} 08/31/2021 07:01:52 - INFO - __main__ - Step 98446: {'lr': 0.00013534547089147052, 'samples': 18901632, 'steps': 98445, 'loss/train': 1.376744270324707} 08/31/2021 07:01:52 - INFO - __main__ - Step 98447: {'lr': 0.0001353407551667198, 'samples': 18901824, 'steps': 98446, 'loss/train': 1.5623738765716553} 08/31/2021 07:01:53 - INFO - __main__ - Step 98448: {'lr': 0.00013533603949363287, 'samples': 18902016, 'steps': 98447, 'loss/train': 1.2584941387176514} 08/31/2021 07:01:54 - INFO - __main__ - Step 98449: {'lr': 0.00013533132387221166, 'samples': 18902208, 'steps': 98448, 'loss/train': 0.9446009397506714} 08/31/2021 07:01:54 - INFO - __main__ - Step 98450: {'lr': 0.0001353266083024584, 'samples': 18902400, 'steps': 98449, 'loss/train': 0.18235237896442413} 08/31/2021 07:01:55 - INFO - __main__ - Step 98451: {'lr': 0.00013532189278437517, 'samples': 18902592, 'steps': 98450, 'loss/train': 0.8291205763816833} 08/31/2021 07:01:55 - INFO - __main__ - Step 98452: {'lr': 0.00013531717731796414, 'samples': 18902784, 'steps': 98451, 'loss/train': 1.0848171710968018} 08/31/2021 07:01:57 - INFO - __main__ - Step 98453: {'lr': 0.00013531246190322743, 'samples': 18902976, 'steps': 98452, 'loss/train': 1.23374342918396} 08/31/2021 07:01:57 - INFO - __main__ - Step 98454: {'lr': 0.00013530774654016715, 'samples': 18903168, 'steps': 98453, 'loss/train': 1.1646199226379395} 08/31/2021 07:01:57 - INFO - __main__ - Step 98455: {'lr': 0.0001353030312287854, 'samples': 18903360, 'steps': 98454, 'loss/train': 0.5169075727462769} 08/31/2021 07:01:58 - INFO - __main__ - Step 98456: {'lr': 0.00013529831596908434, 'samples': 18903552, 'steps': 98455, 'loss/train': 0.7729511857032776} 08/31/2021 07:01:58 - INFO - __main__ - Step 98457: {'lr': 0.00013529360076106612, 'samples': 18903744, 'steps': 98456, 'loss/train': 0.7978063821792603} 08/31/2021 07:02:00 - INFO - __main__ - Step 98458: {'lr': 0.00013528888560473281, 'samples': 18903936, 'steps': 98457, 'loss/train': 1.178340196609497} 08/31/2021 07:02:00 - INFO - __main__ - Step 98459: {'lr': 0.00013528417050008657, 'samples': 18904128, 'steps': 98458, 'loss/train': 0.5171639323234558} 08/31/2021 07:02:00 - INFO - __main__ - Step 98460: {'lr': 0.0001352794554471295, 'samples': 18904320, 'steps': 98459, 'loss/train': 0.9917483925819397} 08/31/2021 07:02:01 - INFO - __main__ - Step 98461: {'lr': 0.00013527474044586386, 'samples': 18904512, 'steps': 98460, 'loss/train': 1.2180266380310059} 08/31/2021 07:02:01 - INFO - __main__ - Step 98462: {'lr': 0.00013527002549629152, 'samples': 18904704, 'steps': 98461, 'loss/train': 1.3339051008224487} 08/31/2021 07:02:01 - INFO - __main__ - Step 98463: {'lr': 0.00013526531059841477, 'samples': 18904896, 'steps': 98462, 'loss/train': 0.556273877620697} 08/31/2021 07:02:03 - INFO - __main__ - Step 98464: {'lr': 0.0001352605957522357, 'samples': 18905088, 'steps': 98463, 'loss/train': 1.3639874458312988} 08/31/2021 07:02:03 - INFO - __main__ - Step 98465: {'lr': 0.0001352558809577564, 'samples': 18905280, 'steps': 98464, 'loss/train': 1.2623136043548584} 08/31/2021 07:02:04 - INFO - __main__ - Step 98466: {'lr': 0.00013525116621497903, 'samples': 18905472, 'steps': 98465, 'loss/train': 0.9416714906692505} 08/31/2021 07:02:04 - INFO - __main__ - Step 98467: {'lr': 0.00013524645152390575, 'samples': 18905664, 'steps': 98466, 'loss/train': 1.4226388931274414} 08/31/2021 07:02:04 - INFO - __main__ - Step 98468: {'lr': 0.0001352417368845386, 'samples': 18905856, 'steps': 98467, 'loss/train': 1.081242561340332} 08/31/2021 07:02:06 - INFO - __main__ - Step 98469: {'lr': 0.00013523702229687978, 'samples': 18906048, 'steps': 98468, 'loss/train': 0.12108878791332245} 08/31/2021 07:02:06 - INFO - __main__ - Step 98470: {'lr': 0.00013523230776093143, 'samples': 18906240, 'steps': 98469, 'loss/train': 1.331705927848816} 08/31/2021 07:02:07 - INFO - __main__ - Step 98471: {'lr': 0.0001352275932766956, 'samples': 18906432, 'steps': 98470, 'loss/train': 1.0161126852035522} 08/31/2021 07:02:07 - INFO - __main__ - Step 98472: {'lr': 0.0001352228788441744, 'samples': 18906624, 'steps': 98471, 'loss/train': 1.1163052320480347} 08/31/2021 07:02:07 - INFO - __main__ - Step 98473: {'lr': 0.00013521816446337005, 'samples': 18906816, 'steps': 98472, 'loss/train': 1.0065795183181763} 08/31/2021 07:02:09 - INFO - __main__ - Step 98474: {'lr': 0.0001352134501342847, 'samples': 18907008, 'steps': 98473, 'loss/train': 0.8962015509605408} 08/31/2021 07:02:10 - INFO - __main__ - Step 98475: {'lr': 0.00013520873585692032, 'samples': 18907200, 'steps': 98474, 'loss/train': 1.5404560565948486} 08/31/2021 07:02:10 - INFO - __main__ - Step 98476: {'lr': 0.00013520402163127909, 'samples': 18907392, 'steps': 98475, 'loss/train': 1.0260937213897705} 08/31/2021 07:02:11 - INFO - __main__ - Step 98477: {'lr': 0.00013519930745736316, 'samples': 18907584, 'steps': 98476, 'loss/train': 1.0492298603057861} 08/31/2021 07:02:11 - INFO - __main__ - Step 98478: {'lr': 0.00013519459333517466, 'samples': 18907776, 'steps': 98477, 'loss/train': 0.7770772576332092} 08/31/2021 07:02:12 - INFO - __main__ - Step 98479: {'lr': 0.00013518987926471572, 'samples': 18907968, 'steps': 98478, 'loss/train': 1.36525297164917} 08/31/2021 07:02:13 - INFO - __main__ - Step 98480: {'lr': 0.00013518516524598843, 'samples': 18908160, 'steps': 98479, 'loss/train': 1.0137859582901} 08/31/2021 07:02:13 - INFO - __main__ - Step 98481: {'lr': 0.00013518045127899493, 'samples': 18908352, 'steps': 98480, 'loss/train': 1.006483554840088} 08/31/2021 07:02:14 - INFO - __main__ - Step 98482: {'lr': 0.00013517573736373734, 'samples': 18908544, 'steps': 98481, 'loss/train': 1.3417227268218994} 08/31/2021 07:02:14 - INFO - __main__ - Step 98483: {'lr': 0.00013517102350021781, 'samples': 18908736, 'steps': 98482, 'loss/train': 1.3187386989593506} 08/31/2021 07:02:15 - INFO - __main__ - Step 98484: {'lr': 0.00013516630968843843, 'samples': 18908928, 'steps': 98483, 'loss/train': 0.7442179322242737} 08/31/2021 07:02:16 - INFO - __main__ - Step 98485: {'lr': 0.00013516159592840131, 'samples': 18909120, 'steps': 98484, 'loss/train': 0.9051899909973145} 08/31/2021 07:02:16 - INFO - __main__ - Step 98486: {'lr': 0.0001351568822201087, 'samples': 18909312, 'steps': 98485, 'loss/train': 0.9738529920578003} 08/31/2021 07:02:17 - INFO - __main__ - Step 98487: {'lr': 0.00013515216856356256, 'samples': 18909504, 'steps': 98486, 'loss/train': 0.581830620765686} 08/31/2021 07:02:17 - INFO - __main__ - Step 98488: {'lr': 0.00013514745495876515, 'samples': 18909696, 'steps': 98487, 'loss/train': 0.6167622804641724} 08/31/2021 07:02:18 - INFO - __main__ - Step 98489: {'lr': 0.00013514274140571846, 'samples': 18909888, 'steps': 98488, 'loss/train': 0.02776803821325302} 08/31/2021 07:02:19 - INFO - __main__ - Step 98490: {'lr': 0.0001351380279044247, 'samples': 18910080, 'steps': 98489, 'loss/train': 0.7584244608879089} 08/31/2021 07:02:19 - INFO - __main__ - Step 98491: {'lr': 0.00013513331445488594, 'samples': 18910272, 'steps': 98490, 'loss/train': 1.3199862241744995} 08/31/2021 07:02:20 - INFO - __main__ - Step 98492: {'lr': 0.00013512860105710433, 'samples': 18910464, 'steps': 98491, 'loss/train': 0.16600434482097626} 08/31/2021 07:02:20 - INFO - __main__ - Step 98493: {'lr': 0.00013512388771108204, 'samples': 18910656, 'steps': 98492, 'loss/train': 1.5111210346221924} 08/31/2021 07:02:22 - INFO - __main__ - Step 98494: {'lr': 0.0001351191744168211, 'samples': 18910848, 'steps': 98493, 'loss/train': 0.6363020539283752} 08/31/2021 07:02:22 - INFO - __main__ - Step 98495: {'lr': 0.00013511446117432375, 'samples': 18911040, 'steps': 98494, 'loss/train': 1.143800139427185} 08/31/2021 07:02:23 - INFO - __main__ - Step 98496: {'lr': 0.00013510974798359199, 'samples': 18911232, 'steps': 98495, 'loss/train': 0.7675520181655884} 08/31/2021 07:02:23 - INFO - __main__ - Step 98497: {'lr': 0.00013510503484462805, 'samples': 18911424, 'steps': 98496, 'loss/train': 1.2488129138946533} 08/31/2021 07:02:23 - INFO - __main__ - Step 98498: {'lr': 0.000135100321757434, 'samples': 18911616, 'steps': 98497, 'loss/train': 0.6396152377128601} 08/31/2021 07:02:24 - INFO - __main__ - Step 98499: {'lr': 0.00013509560872201193, 'samples': 18911808, 'steps': 98498, 'loss/train': 0.7608988881111145} 08/31/2021 07:02:25 - INFO - __main__ - Step 98500: {'lr': 0.00013509089573836405, 'samples': 18912000, 'steps': 98499, 'loss/train': 0.6426641345024109} 08/31/2021 07:02:26 - INFO - __main__ - Step 98501: {'lr': 0.00013508618280649255, 'samples': 18912192, 'steps': 98500, 'loss/train': 1.714858055114746} 08/31/2021 07:02:26 - INFO - __main__ - Step 98502: {'lr': 0.0001350814699263993, 'samples': 18912384, 'steps': 98501, 'loss/train': 1.425253987312317} 08/31/2021 07:02:26 - INFO - __main__ - Step 98503: {'lr': 0.0001350767570980866, 'samples': 18912576, 'steps': 98502, 'loss/train': 1.156772494316101} 08/31/2021 07:02:27 - INFO - __main__ - Step 98504: {'lr': 0.0001350720443215565, 'samples': 18912768, 'steps': 98503, 'loss/train': 0.1197449341416359} 08/31/2021 07:02:29 - INFO - __main__ - Step 98505: {'lr': 0.00013506733159681123, 'samples': 18912960, 'steps': 98504, 'loss/train': 0.9445346593856812} 08/31/2021 07:02:29 - INFO - __main__ - Step 98506: {'lr': 0.0001350626189238528, 'samples': 18913152, 'steps': 98505, 'loss/train': 1.0255820751190186} 08/31/2021 07:02:30 - INFO - __main__ - Step 98507: {'lr': 0.00013505790630268338, 'samples': 18913344, 'steps': 98506, 'loss/train': 0.7068762183189392} 08/31/2021 07:02:30 - INFO - __main__ - Step 98508: {'lr': 0.0001350531937333051, 'samples': 18913536, 'steps': 98507, 'loss/train': 0.25761231780052185} 08/31/2021 07:02:30 - INFO - __main__ - Step 98509: {'lr': 0.00013504848121572005, 'samples': 18913728, 'steps': 98508, 'loss/train': 0.0665283277630806} 08/31/2021 07:02:32 - INFO - __main__ - Step 98510: {'lr': 0.00013504376874993044, 'samples': 18913920, 'steps': 98509, 'loss/train': 1.4210057258605957} 08/31/2021 07:02:32 - INFO - __main__ - Step 98511: {'lr': 0.00013503905633593827, 'samples': 18914112, 'steps': 98510, 'loss/train': 0.9550495147705078} 08/31/2021 07:02:33 - INFO - __main__ - Step 98512: {'lr': 0.00013503434397374578, 'samples': 18914304, 'steps': 98511, 'loss/train': 1.7931832075119019} 08/31/2021 07:02:33 - INFO - __main__ - Step 98513: {'lr': 0.00013502963166335503, 'samples': 18914496, 'steps': 98512, 'loss/train': 1.6938389539718628} 08/31/2021 07:02:33 - INFO - __main__ - Step 98514: {'lr': 0.00013502491940476814, 'samples': 18914688, 'steps': 98513, 'loss/train': 1.098267674446106} 08/31/2021 07:02:34 - INFO - __main__ - Step 98515: {'lr': 0.00013502020719798736, 'samples': 18914880, 'steps': 98514, 'loss/train': 0.7277714014053345} 08/31/2021 07:02:35 - INFO - __main__ - Step 98516: {'lr': 0.00013501549504301458, 'samples': 18915072, 'steps': 98515, 'loss/train': 1.1430529356002808} 08/31/2021 07:02:36 - INFO - __main__ - Step 98517: {'lr': 0.00013501078293985205, 'samples': 18915264, 'steps': 98516, 'loss/train': 1.3971909284591675} 08/31/2021 07:02:36 - INFO - __main__ - Step 98518: {'lr': 0.0001350060708885019, 'samples': 18915456, 'steps': 98517, 'loss/train': 0.955497145652771} 08/31/2021 07:02:36 - INFO - __main__ - Step 98519: {'lr': 0.00013500135888896622, 'samples': 18915648, 'steps': 98518, 'loss/train': 1.1411980390548706} 08/31/2021 07:02:37 - INFO - __main__ - Step 98520: {'lr': 0.0001349966469412472, 'samples': 18915840, 'steps': 98519, 'loss/train': 0.5759050250053406} 08/31/2021 07:02:38 - INFO - __main__ - Step 98521: {'lr': 0.00013499193504534684, 'samples': 18916032, 'steps': 98520, 'loss/train': 1.1687417030334473} 08/31/2021 07:02:39 - INFO - __main__ - Step 98522: {'lr': 0.00013498722320126738, 'samples': 18916224, 'steps': 98521, 'loss/train': 0.8013662695884705} 08/31/2021 07:02:39 - INFO - __main__ - Step 98523: {'lr': 0.0001349825114090109, 'samples': 18916416, 'steps': 98522, 'loss/train': 0.8727291226387024} 08/31/2021 07:02:39 - INFO - __main__ - Step 98524: {'lr': 0.00013497779966857953, 'samples': 18916608, 'steps': 98523, 'loss/train': 0.6403539180755615} 08/31/2021 07:02:40 - INFO - __main__ - Step 98525: {'lr': 0.0001349730879799754, 'samples': 18916800, 'steps': 98524, 'loss/train': 1.0354562997817993} 08/31/2021 07:02:41 - INFO - __main__ - Step 98526: {'lr': 0.00013496837634320062, 'samples': 18916992, 'steps': 98525, 'loss/train': 1.382743239402771} 08/31/2021 07:02:42 - INFO - __main__ - Step 98527: {'lr': 0.0001349636647582573, 'samples': 18917184, 'steps': 98526, 'loss/train': 0.9597851037979126} 08/31/2021 07:02:42 - INFO - __main__ - Step 98528: {'lr': 0.00013495895322514768, 'samples': 18917376, 'steps': 98527, 'loss/train': 1.2472668886184692} 08/31/2021 07:02:42 - INFO - __main__ - Step 98529: {'lr': 0.00013495424174387365, 'samples': 18917568, 'steps': 98528, 'loss/train': 1.2679306268692017} 08/31/2021 07:02:43 - INFO - __main__ - Step 98530: {'lr': 0.00013494953031443753, 'samples': 18917760, 'steps': 98529, 'loss/train': 1.5122385025024414} 08/31/2021 07:02:45 - INFO - __main__ - Step 98531: {'lr': 0.00013494481893684134, 'samples': 18917952, 'steps': 98530, 'loss/train': 1.3175617456436157} 08/31/2021 07:02:45 - INFO - __main__ - Step 98532: {'lr': 0.00013494010761108726, 'samples': 18918144, 'steps': 98531, 'loss/train': 0.8540804386138916} 08/31/2021 07:02:46 - INFO - __main__ - Step 98533: {'lr': 0.00013493539633717736, 'samples': 18918336, 'steps': 98532, 'loss/train': 0.637411892414093} 08/31/2021 07:02:46 - INFO - __main__ - Step 98534: {'lr': 0.0001349306851151138, 'samples': 18918528, 'steps': 98533, 'loss/train': 1.2501769065856934} 08/31/2021 07:02:46 - INFO - __main__ - Step 98535: {'lr': 0.0001349259739448987, 'samples': 18918720, 'steps': 98534, 'loss/train': 1.5837314128875732} 08/31/2021 07:02:47 - INFO - __main__ - Step 98536: {'lr': 0.0001349212628265342, 'samples': 18918912, 'steps': 98535, 'loss/train': 1.082192063331604} 08/31/2021 07:02:48 - INFO - __main__ - Step 98537: {'lr': 0.0001349165517600224, 'samples': 18919104, 'steps': 98536, 'loss/train': 1.3909883499145508} 08/31/2021 07:02:49 - INFO - __main__ - Step 98538: {'lr': 0.0001349118407453654, 'samples': 18919296, 'steps': 98537, 'loss/train': 1.13450026512146} 08/31/2021 07:02:49 - INFO - __main__ - Step 98539: {'lr': 0.00013490712978256537, 'samples': 18919488, 'steps': 98538, 'loss/train': 0.6625091433525085} 08/31/2021 07:02:49 - INFO - __main__ - Step 98540: {'lr': 0.0001349024188716244, 'samples': 18919680, 'steps': 98539, 'loss/train': 1.5690443515777588} 08/31/2021 07:02:50 - INFO - __main__ - Step 98541: {'lr': 0.00013489770801254465, 'samples': 18919872, 'steps': 98540, 'loss/train': 1.3639873266220093} 08/31/2021 07:02:51 - INFO - __main__ - Step 98542: {'lr': 0.00013489299720532828, 'samples': 18920064, 'steps': 98541, 'loss/train': 1.8344813585281372} 08/31/2021 07:02:52 - INFO - __main__ - Step 98543: {'lr': 0.00013488828644997724, 'samples': 18920256, 'steps': 98542, 'loss/train': 1.0752767324447632} 08/31/2021 07:02:52 - INFO - __main__ - Step 98544: {'lr': 0.0001348835757464938, 'samples': 18920448, 'steps': 98543, 'loss/train': 0.7742763757705688} 08/31/2021 07:02:52 - INFO - __main__ - Step 98545: {'lr': 0.00013487886509488001, 'samples': 18920640, 'steps': 98544, 'loss/train': 0.5909773111343384} 08/31/2021 07:02:53 - INFO - __main__ - Step 98546: {'lr': 0.00013487415449513806, 'samples': 18920832, 'steps': 98545, 'loss/train': 1.201603889465332} 08/31/2021 07:02:54 - INFO - __main__ - Step 98547: {'lr': 0.00013486944394727003, 'samples': 18921024, 'steps': 98546, 'loss/train': 0.9951362013816833} 08/31/2021 07:02:55 - INFO - __main__ - Step 98548: {'lr': 0.00013486473345127804, 'samples': 18921216, 'steps': 98547, 'loss/train': 1.1520881652832031} 08/31/2021 07:02:55 - INFO - __main__ - Step 98549: {'lr': 0.00013486002300716423, 'samples': 18921408, 'steps': 98548, 'loss/train': 1.5378577709197998} 08/31/2021 07:02:55 - INFO - __main__ - Step 98550: {'lr': 0.00013485531261493074, 'samples': 18921600, 'steps': 98549, 'loss/train': 0.3730226457118988} 08/31/2021 07:02:56 - INFO - __main__ - Step 98551: {'lr': 0.00013485060227457965, 'samples': 18921792, 'steps': 98550, 'loss/train': 1.0438427925109863} 08/31/2021 07:02:56 - INFO - __main__ - Step 98552: {'lr': 0.00013484589198611306, 'samples': 18921984, 'steps': 98551, 'loss/train': 0.775438129901886} 08/31/2021 07:02:58 - INFO - __main__ - Step 98553: {'lr': 0.00013484118174953322, 'samples': 18922176, 'steps': 98552, 'loss/train': 1.6071923971176147} 08/31/2021 07:02:58 - INFO - __main__ - Step 98554: {'lr': 0.00013483647156484213, 'samples': 18922368, 'steps': 98553, 'loss/train': 1.2856807708740234} 08/31/2021 07:02:58 - INFO - __main__ - Step 98555: {'lr': 0.000134831761432042, 'samples': 18922560, 'steps': 98554, 'loss/train': 1.5408543348312378} 08/31/2021 07:02:59 - INFO - __main__ - Step 98556: {'lr': 0.00013482705135113487, 'samples': 18922752, 'steps': 98555, 'loss/train': 1.2106292247772217} 08/31/2021 07:02:59 - INFO - __main__ - Step 98557: {'lr': 0.00013482234132212287, 'samples': 18922944, 'steps': 98556, 'loss/train': 0.6863553524017334} 08/31/2021 07:03:00 - INFO - __main__ - Step 98558: {'lr': 0.00013481763134500814, 'samples': 18923136, 'steps': 98557, 'loss/train': 1.3818320035934448} 08/31/2021 07:03:01 - INFO - __main__ - Step 98559: {'lr': 0.00013481292141979278, 'samples': 18923328, 'steps': 98558, 'loss/train': 0.951027512550354} 08/31/2021 07:03:01 - INFO - __main__ - Step 98560: {'lr': 0.000134808211546479, 'samples': 18923520, 'steps': 98559, 'loss/train': 1.0352686643600464} 08/31/2021 07:03:02 - INFO - __main__ - Step 98561: {'lr': 0.00013480350172506884, 'samples': 18923712, 'steps': 98560, 'loss/train': 1.3879483938217163} 08/31/2021 07:03:02 - INFO - __main__ - Step 98562: {'lr': 0.00013479879195556443, 'samples': 18923904, 'steps': 98561, 'loss/train': 1.4989758729934692} 08/31/2021 07:03:04 - INFO - __main__ - Step 98563: {'lr': 0.0001347940822379679, 'samples': 18924096, 'steps': 98562, 'loss/train': 1.3807249069213867} 08/31/2021 07:03:04 - INFO - __main__ - Step 98564: {'lr': 0.00013478937257228142, 'samples': 18924288, 'steps': 98563, 'loss/train': 1.2031257152557373} 08/31/2021 07:03:04 - INFO - __main__ - Step 98565: {'lr': 0.00013478466295850704, 'samples': 18924480, 'steps': 98564, 'loss/train': 2.0429491996765137} 08/31/2021 07:03:05 - INFO - __main__ - Step 98566: {'lr': 0.00013477995339664689, 'samples': 18924672, 'steps': 98565, 'loss/train': 1.141391634941101} 08/31/2021 07:03:05 - INFO - __main__ - Step 98567: {'lr': 0.00013477524388670316, 'samples': 18924864, 'steps': 98566, 'loss/train': 0.9681693315505981} 08/31/2021 07:03:07 - INFO - __main__ - Step 98568: {'lr': 0.0001347705344286779, 'samples': 18925056, 'steps': 98567, 'loss/train': 1.7991195917129517} 08/31/2021 07:03:07 - INFO - __main__ - Step 98569: {'lr': 0.00013476582502257336, 'samples': 18925248, 'steps': 98568, 'loss/train': 0.9089970588684082} 08/31/2021 07:03:08 - INFO - __main__ - Step 98570: {'lr': 0.00013476111566839148, 'samples': 18925440, 'steps': 98569, 'loss/train': 1.6520580053329468} 08/31/2021 07:03:08 - INFO - __main__ - Step 98571: {'lr': 0.00013475640636613446, 'samples': 18925632, 'steps': 98570, 'loss/train': 0.9566720724105835} 08/31/2021 07:03:08 - INFO - __main__ - Step 98572: {'lr': 0.0001347516971158044, 'samples': 18925824, 'steps': 98571, 'loss/train': 1.2454723119735718} 08/31/2021 07:03:10 - INFO - __main__ - Step 98573: {'lr': 0.00013474698791740347, 'samples': 18926016, 'steps': 98572, 'loss/train': 1.799878478050232} 08/31/2021 07:03:10 - INFO - __main__ - Step 98574: {'lr': 0.00013474227877093375, 'samples': 18926208, 'steps': 98573, 'loss/train': 0.9621990919113159} 08/31/2021 07:03:11 - INFO - __main__ - Step 98575: {'lr': 0.0001347375696763974, 'samples': 18926400, 'steps': 98574, 'loss/train': 1.7876056432724} 08/31/2021 07:03:11 - INFO - __main__ - Step 98576: {'lr': 0.00013473286063379653, 'samples': 18926592, 'steps': 98575, 'loss/train': 1.3404808044433594} 08/31/2021 07:03:12 - INFO - __main__ - Step 98577: {'lr': 0.00013472815164313325, 'samples': 18926784, 'steps': 98576, 'loss/train': 1.3639888763427734} 08/31/2021 07:03:12 - INFO - __main__ - Step 98578: {'lr': 0.00013472344270440965, 'samples': 18926976, 'steps': 98577, 'loss/train': 1.4039629697799683} 08/31/2021 07:03:14 - INFO - __main__ - Step 98579: {'lr': 0.0001347187338176279, 'samples': 18927168, 'steps': 98578, 'loss/train': 1.3552837371826172} 08/31/2021 07:03:15 - INFO - __main__ - Step 98580: {'lr': 0.0001347140249827901, 'samples': 18927360, 'steps': 98579, 'loss/train': 1.3352903127670288} 08/31/2021 07:03:15 - INFO - __main__ - Step 98581: {'lr': 0.00013470931619989846, 'samples': 18927552, 'steps': 98580, 'loss/train': 1.292927861213684} 08/31/2021 07:03:15 - INFO - __main__ - Step 98582: {'lr': 0.00013470460746895505, 'samples': 18927744, 'steps': 98581, 'loss/train': 1.252244234085083} 08/31/2021 07:03:16 - INFO - __main__ - Step 98583: {'lr': 0.00013469989878996187, 'samples': 18927936, 'steps': 98582, 'loss/train': 0.017468726262450218} 08/31/2021 07:03:16 - INFO - __main__ - Step 98584: {'lr': 0.00013469519016292113, 'samples': 18928128, 'steps': 98583, 'loss/train': 1.2464100122451782} 08/31/2021 07:03:18 - INFO - __main__ - Step 98585: {'lr': 0.000134690481587835, 'samples': 18928320, 'steps': 98584, 'loss/train': 1.6444098949432373} 08/31/2021 07:03:19 - INFO - __main__ - Step 98586: {'lr': 0.00013468577306470554, 'samples': 18928512, 'steps': 98585, 'loss/train': 0.9105275273323059} 08/31/2021 07:03:19 - INFO - __main__ - Step 98587: {'lr': 0.0001346810645935349, 'samples': 18928704, 'steps': 98586, 'loss/train': 0.09855267405509949} 08/31/2021 07:03:19 - INFO - __main__ - Step 98588: {'lr': 0.00013467635617432516, 'samples': 18928896, 'steps': 98587, 'loss/train': 1.1447365283966064} 08/31/2021 07:03:20 - INFO - __main__ - Step 98589: {'lr': 0.00013467164780707849, 'samples': 18929088, 'steps': 98588, 'loss/train': 1.4174696207046509} 08/31/2021 07:03:20 - INFO - __main__ - Step 98590: {'lr': 0.000134666939491797, 'samples': 18929280, 'steps': 98589, 'loss/train': 1.0083327293395996} 08/31/2021 07:03:21 - INFO - __main__ - Step 98591: {'lr': 0.0001346622312284828, 'samples': 18929472, 'steps': 98590, 'loss/train': 0.7126942276954651} 08/31/2021 07:03:22 - INFO - __main__ - Step 98592: {'lr': 0.00013465752301713806, 'samples': 18929664, 'steps': 98591, 'loss/train': 1.4775434732437134} 08/31/2021 07:03:22 - INFO - __main__ - Step 98593: {'lr': 0.0001346528148577648, 'samples': 18929856, 'steps': 98592, 'loss/train': 1.3770806789398193} 08/31/2021 07:03:23 - INFO - __main__ - Step 98594: {'lr': 0.00013464810675036526, 'samples': 18930048, 'steps': 98593, 'loss/train': 1.4771956205368042} 08/31/2021 07:03:23 - INFO - __main__ - Step 98595: {'lr': 0.00013464339869494155, 'samples': 18930240, 'steps': 98594, 'loss/train': 1.2860839366912842} 08/31/2021 07:03:24 - INFO - __main__ - Step 98596: {'lr': 0.00013463869069149566, 'samples': 18930432, 'steps': 98595, 'loss/train': 1.3371326923370361} 08/31/2021 07:03:25 - INFO - __main__ - Step 98597: {'lr': 0.0001346339827400298, 'samples': 18930624, 'steps': 98596, 'loss/train': 0.6480088233947754} 08/31/2021 07:03:25 - INFO - __main__ - Step 98598: {'lr': 0.0001346292748405461, 'samples': 18930816, 'steps': 98597, 'loss/train': 0.8516897559165955} 08/31/2021 07:03:26 - INFO - __main__ - Step 98599: {'lr': 0.00013462456699304666, 'samples': 18931008, 'steps': 98598, 'loss/train': 1.2671287059783936} 08/31/2021 07:03:26 - INFO - __main__ - Step 98600: {'lr': 0.00013461985919753362, 'samples': 18931200, 'steps': 98599, 'loss/train': 0.8396509885787964} 08/31/2021 07:03:27 - INFO - __main__ - Step 98601: {'lr': 0.00013461515145400907, 'samples': 18931392, 'steps': 98600, 'loss/train': 0.5831122398376465} 08/31/2021 07:03:28 - INFO - __main__ - Step 98602: {'lr': 0.00013461044376247516, 'samples': 18931584, 'steps': 98601, 'loss/train': 1.3217957019805908} 08/31/2021 07:03:28 - INFO - __main__ - Step 98603: {'lr': 0.000134605736122934, 'samples': 18931776, 'steps': 98602, 'loss/train': 1.046900987625122} 08/31/2021 07:03:29 - INFO - __main__ - Step 98604: {'lr': 0.0001346010285353877, 'samples': 18931968, 'steps': 98603, 'loss/train': 0.6398093700408936} 08/31/2021 07:03:29 - INFO - __main__ - Step 98605: {'lr': 0.00013459632099983843, 'samples': 18932160, 'steps': 98604, 'loss/train': 0.8759077787399292} 08/31/2021 07:03:31 - INFO - __main__ - Step 98606: {'lr': 0.00013459161351628827, 'samples': 18932352, 'steps': 98605, 'loss/train': 1.1658415794372559} 08/31/2021 07:03:32 - INFO - __main__ - Step 98607: {'lr': 0.00013458690608473934, 'samples': 18932544, 'steps': 98606, 'loss/train': 1.1978496313095093} 08/31/2021 07:03:32 - INFO - __main__ - Step 98608: {'lr': 0.00013458219870519377, 'samples': 18932736, 'steps': 98607, 'loss/train': 1.2669801712036133} 08/31/2021 07:03:32 - INFO - __main__ - Step 98609: {'lr': 0.0001345774913776538, 'samples': 18932928, 'steps': 98608, 'loss/train': 0.6538188457489014} 08/31/2021 07:03:33 - INFO - __main__ - Step 98610: {'lr': 0.0001345727841021213, 'samples': 18933120, 'steps': 98609, 'loss/train': 1.5380669832229614} 08/31/2021 07:03:33 - INFO - __main__ - Step 98611: {'lr': 0.00013456807687859852, 'samples': 18933312, 'steps': 98610, 'loss/train': 1.1135817766189575} 08/31/2021 07:03:35 - INFO - __main__ - Step 98612: {'lr': 0.0001345633697070876, 'samples': 18933504, 'steps': 98611, 'loss/train': 0.013906270265579224} 08/31/2021 07:03:35 - INFO - __main__ - Step 98613: {'lr': 0.00013455866258759065, 'samples': 18933696, 'steps': 98612, 'loss/train': 0.6740007400512695} 08/31/2021 07:03:35 - INFO - __main__ - Step 98614: {'lr': 0.00013455395552010977, 'samples': 18933888, 'steps': 98613, 'loss/train': 1.1808993816375732} 08/31/2021 07:03:36 - INFO - __main__ - Step 98615: {'lr': 0.00013454924850464712, 'samples': 18934080, 'steps': 98614, 'loss/train': 1.720341444015503} 08/31/2021 07:03:36 - INFO - __main__ - Step 98616: {'lr': 0.00013454454154120476, 'samples': 18934272, 'steps': 98615, 'loss/train': 1.4307249784469604} 08/31/2021 07:03:38 - INFO - __main__ - Step 98617: {'lr': 0.00013453983462978486, 'samples': 18934464, 'steps': 98616, 'loss/train': 0.5073376893997192} 08/31/2021 07:03:38 - INFO - __main__ - Step 98618: {'lr': 0.00013453512777038954, 'samples': 18934656, 'steps': 98617, 'loss/train': 1.514291763305664} 08/31/2021 07:03:38 - INFO - __main__ - Step 98619: {'lr': 0.0001345304209630209, 'samples': 18934848, 'steps': 98618, 'loss/train': 1.096260905265808} 08/31/2021 07:03:39 - INFO - __main__ - Step 98620: {'lr': 0.00013452571420768106, 'samples': 18935040, 'steps': 98619, 'loss/train': 1.397420883178711} 08/31/2021 07:03:39 - INFO - __main__ - Step 98621: {'lr': 0.00013452100750437217, 'samples': 18935232, 'steps': 98620, 'loss/train': 0.8457335829734802} 08/31/2021 07:03:39 - INFO - __main__ - Step 98622: {'lr': 0.00013451630085309647, 'samples': 18935424, 'steps': 98621, 'loss/train': 0.235523983836174} 08/31/2021 07:03:41 - INFO - __main__ - Step 98623: {'lr': 0.00013451159425385579, 'samples': 18935616, 'steps': 98622, 'loss/train': 0.4909980893135071} 08/31/2021 07:03:41 - INFO - __main__ - Step 98624: {'lr': 0.00013450688770665244, 'samples': 18935808, 'steps': 98623, 'loss/train': 1.372141718864441} 08/31/2021 07:03:42 - INFO - __main__ - Step 98625: {'lr': 0.00013450218121148844, 'samples': 18936000, 'steps': 98624, 'loss/train': 1.9006690979003906} 08/31/2021 07:03:42 - INFO - __main__ - Step 98626: {'lr': 0.00013449747476836603, 'samples': 18936192, 'steps': 98625, 'loss/train': 1.4613455533981323} 08/31/2021 07:03:42 - INFO - __main__ - Step 98627: {'lr': 0.00013449276837728725, 'samples': 18936384, 'steps': 98626, 'loss/train': 1.2254095077514648} 08/31/2021 07:03:44 - INFO - __main__ - Step 98628: {'lr': 0.00013448806203825424, 'samples': 18936576, 'steps': 98627, 'loss/train': 1.246549367904663} 08/31/2021 07:03:45 - INFO - __main__ - Step 98629: {'lr': 0.00013448335575126915, 'samples': 18936768, 'steps': 98628, 'loss/train': 1.2088689804077148} 08/31/2021 07:03:45 - INFO - __main__ - Step 98630: {'lr': 0.0001344786495163341, 'samples': 18936960, 'steps': 98629, 'loss/train': 1.2673604488372803} 08/31/2021 07:03:45 - INFO - __main__ - Step 98631: {'lr': 0.00013447394333345115, 'samples': 18937152, 'steps': 98630, 'loss/train': 1.3608155250549316} 08/31/2021 07:03:46 - INFO - __main__ - Step 98632: {'lr': 0.00013446923720262244, 'samples': 18937344, 'steps': 98631, 'loss/train': 0.10609562695026398} 08/31/2021 07:03:47 - INFO - __main__ - Step 98633: {'lr': 0.00013446453112385016, 'samples': 18937536, 'steps': 98632, 'loss/train': 0.6845930814743042} 08/31/2021 07:03:48 - INFO - __main__ - Step 98634: {'lr': 0.00013445982509713644, 'samples': 18937728, 'steps': 98633, 'loss/train': 1.7668492794036865} 08/31/2021 07:03:48 - INFO - __main__ - Step 98635: {'lr': 0.00013445511912248327, 'samples': 18937920, 'steps': 98634, 'loss/train': 0.7498371601104736} 08/31/2021 07:03:48 - INFO - __main__ - Step 98636: {'lr': 0.00013445041319989283, 'samples': 18938112, 'steps': 98635, 'loss/train': 1.166848063468933} 08/31/2021 07:03:49 - INFO - __main__ - Step 98637: {'lr': 0.00013444570732936721, 'samples': 18938304, 'steps': 98636, 'loss/train': 1.0068392753601074} 08/31/2021 07:03:52 - INFO - __main__ - Step 98638: {'lr': 0.00013444100151090865, 'samples': 18938496, 'steps': 98637, 'loss/train': 0.23676857352256775} 08/31/2021 07:03:52 - INFO - __main__ - Step 98639: {'lr': 0.00013443629574451916, 'samples': 18938688, 'steps': 98638, 'loss/train': 1.7296651601791382} 08/31/2021 07:03:52 - INFO - __main__ - Step 98640: {'lr': 0.00013443159003020087, 'samples': 18938880, 'steps': 98639, 'loss/train': 1.1588490009307861} 08/31/2021 07:03:53 - INFO - __main__ - Step 98641: {'lr': 0.00013442688436795592, 'samples': 18939072, 'steps': 98640, 'loss/train': 1.2882046699523926} 08/31/2021 07:03:53 - INFO - __main__ - Step 98642: {'lr': 0.00013442217875778644, 'samples': 18939264, 'steps': 98641, 'loss/train': 0.9835715293884277} 08/31/2021 07:03:53 - INFO - __main__ - Step 98643: {'lr': 0.00013441747319969455, 'samples': 18939456, 'steps': 98642, 'loss/train': 1.5295599699020386} 08/31/2021 07:03:55 - INFO - __main__ - Step 98644: {'lr': 0.00013441276769368237, 'samples': 18939648, 'steps': 98643, 'loss/train': 0.900200366973877} 08/31/2021 07:03:55 - INFO - __main__ - Step 98645: {'lr': 0.0001344080622397521, 'samples': 18939840, 'steps': 98644, 'loss/train': 1.2724615335464478} 08/31/2021 07:03:56 - INFO - __main__ - Step 98646: {'lr': 0.00013440335683790567, 'samples': 18940032, 'steps': 98645, 'loss/train': 1.5757174491882324} 08/31/2021 07:03:56 - INFO - __main__ - Step 98647: {'lr': 0.00013439865148814534, 'samples': 18940224, 'steps': 98646, 'loss/train': 1.1877894401550293} 08/31/2021 07:03:57 - INFO - __main__ - Step 98648: {'lr': 0.00013439394619047315, 'samples': 18940416, 'steps': 98647, 'loss/train': 1.1980476379394531} 08/31/2021 07:03:58 - INFO - __main__ - Step 98649: {'lr': 0.0001343892409448913, 'samples': 18940608, 'steps': 98648, 'loss/train': 1.1288080215454102} 08/31/2021 07:03:59 - INFO - __main__ - Step 98650: {'lr': 0.00013438453575140183, 'samples': 18940800, 'steps': 98649, 'loss/train': 1.357492208480835} 08/31/2021 07:03:59 - INFO - __main__ - Step 98651: {'lr': 0.00013437983061000694, 'samples': 18940992, 'steps': 98650, 'loss/train': 0.35888659954071045} 08/31/2021 07:03:59 - INFO - __main__ - Step 98652: {'lr': 0.00013437512552070868, 'samples': 18941184, 'steps': 98651, 'loss/train': 1.1539767980575562} 08/31/2021 07:04:00 - INFO - __main__ - Step 98653: {'lr': 0.00013437042048350923, 'samples': 18941376, 'steps': 98652, 'loss/train': 1.3152360916137695} 08/31/2021 07:04:00 - INFO - __main__ - Step 98654: {'lr': 0.00013436571549841071, 'samples': 18941568, 'steps': 98653, 'loss/train': 1.0068109035491943} 08/31/2021 07:04:01 - INFO - __main__ - Step 98655: {'lr': 0.00013436101056541516, 'samples': 18941760, 'steps': 98654, 'loss/train': 1.470740795135498} 08/31/2021 07:04:02 - INFO - __main__ - Step 98656: {'lr': 0.0001343563056845249, 'samples': 18941952, 'steps': 98655, 'loss/train': 2.446986675262451} 08/31/2021 07:04:02 - INFO - __main__ - Step 98657: {'lr': 0.00013435160085574176, 'samples': 18942144, 'steps': 98656, 'loss/train': 0.9941042065620422} 08/31/2021 07:04:03 - INFO - __main__ - Step 98658: {'lr': 0.00013434689607906802, 'samples': 18942336, 'steps': 98657, 'loss/train': 1.1848958730697632} 08/31/2021 07:04:03 - INFO - __main__ - Step 98659: {'lr': 0.0001343421913545058, 'samples': 18942528, 'steps': 98658, 'loss/train': 1.6295199394226074} 08/31/2021 07:04:05 - INFO - __main__ - Step 98660: {'lr': 0.0001343374866820572, 'samples': 18942720, 'steps': 98659, 'loss/train': 1.131701946258545} 08/31/2021 07:04:05 - INFO - __main__ - Step 98661: {'lr': 0.00013433278206172433, 'samples': 18942912, 'steps': 98660, 'loss/train': 0.802072286605835} 08/31/2021 07:04:05 - INFO - __main__ - Step 98662: {'lr': 0.00013432807749350935, 'samples': 18943104, 'steps': 98661, 'loss/train': 1.4284353256225586} 08/31/2021 07:04:06 - INFO - __main__ - Step 98663: {'lr': 0.00013432337297741436, 'samples': 18943296, 'steps': 98662, 'loss/train': 2.326469659805298} 08/31/2021 07:04:06 - INFO - __main__ - Step 98664: {'lr': 0.00013431866851344143, 'samples': 18943488, 'steps': 98663, 'loss/train': 0.6523790955543518} 08/31/2021 07:04:08 - INFO - __main__ - Step 98665: {'lr': 0.00013431396410159275, 'samples': 18943680, 'steps': 98664, 'loss/train': 0.6098090410232544} 08/31/2021 07:04:08 - INFO - __main__ - Step 98666: {'lr': 0.00013430925974187042, 'samples': 18943872, 'steps': 98665, 'loss/train': 1.4860295057296753} 08/31/2021 07:04:08 - INFO - __main__ - Step 98667: {'lr': 0.0001343045554342766, 'samples': 18944064, 'steps': 98666, 'loss/train': 1.4283753633499146} 08/31/2021 07:04:09 - INFO - __main__ - Step 98668: {'lr': 0.00013429985117881333, 'samples': 18944256, 'steps': 98667, 'loss/train': 0.9300184845924377} 08/31/2021 07:04:09 - INFO - __main__ - Step 98669: {'lr': 0.00013429514697548274, 'samples': 18944448, 'steps': 98668, 'loss/train': 1.0475178956985474} 08/31/2021 07:04:10 - INFO - __main__ - Step 98670: {'lr': 0.00013429044282428694, 'samples': 18944640, 'steps': 98669, 'loss/train': 0.6708595156669617} 08/31/2021 07:04:11 - INFO - __main__ - Step 98671: {'lr': 0.0001342857387252281, 'samples': 18944832, 'steps': 98670, 'loss/train': 1.1643351316452026} 08/31/2021 07:04:11 - INFO - __main__ - Step 98672: {'lr': 0.00013428103467830833, 'samples': 18945024, 'steps': 98671, 'loss/train': 0.9462478756904602} 08/31/2021 07:04:12 - INFO - __main__ - Step 98673: {'lr': 0.00013427633068352973, 'samples': 18945216, 'steps': 98672, 'loss/train': 1.0705866813659668} 08/31/2021 07:04:12 - INFO - __main__ - Step 98674: {'lr': 0.00013427162674089444, 'samples': 18945408, 'steps': 98673, 'loss/train': 0.8820722699165344} 08/31/2021 07:04:12 - INFO - __main__ - Step 98675: {'lr': 0.00013426692285040454, 'samples': 18945600, 'steps': 98674, 'loss/train': 1.1043120622634888} 08/31/2021 07:04:14 - INFO - __main__ - Step 98676: {'lr': 0.0001342622190120622, 'samples': 18945792, 'steps': 98675, 'loss/train': 1.5497503280639648} 08/31/2021 07:04:14 - INFO - __main__ - Step 98677: {'lr': 0.00013425751522586955, 'samples': 18945984, 'steps': 98676, 'loss/train': 0.8380981087684631} 08/31/2021 07:04:15 - INFO - __main__ - Step 98678: {'lr': 0.00013425281149182872, 'samples': 18946176, 'steps': 98677, 'loss/train': 1.6007047891616821} 08/31/2021 07:04:15 - INFO - __main__ - Step 98679: {'lr': 0.00013424810780994173, 'samples': 18946368, 'steps': 98678, 'loss/train': 0.8252430558204651} 08/31/2021 07:04:15 - INFO - __main__ - Step 98680: {'lr': 0.00013424340418021074, 'samples': 18946560, 'steps': 98679, 'loss/train': 1.3054912090301514} 08/31/2021 07:04:17 - INFO - __main__ - Step 98681: {'lr': 0.00013423870060263787, 'samples': 18946752, 'steps': 98680, 'loss/train': 1.2435073852539062} 08/31/2021 07:04:17 - INFO - __main__ - Step 98682: {'lr': 0.00013423399707722527, 'samples': 18946944, 'steps': 98681, 'loss/train': 1.5023553371429443} 08/31/2021 07:04:18 - INFO - __main__ - Step 98683: {'lr': 0.00013422929360397507, 'samples': 18947136, 'steps': 98682, 'loss/train': 1.1376436948776245} 08/31/2021 07:04:18 - INFO - __main__ - Step 98684: {'lr': 0.00013422459018288936, 'samples': 18947328, 'steps': 98683, 'loss/train': 0.7313824892044067} 08/31/2021 07:04:18 - INFO - __main__ - Step 98685: {'lr': 0.00013421988681397022, 'samples': 18947520, 'steps': 98684, 'loss/train': 0.8719971776008606} 08/31/2021 07:04:20 - INFO - __main__ - Step 98686: {'lr': 0.00013421518349721983, 'samples': 18947712, 'steps': 98685, 'loss/train': 0.8951671719551086} 08/31/2021 07:04:20 - INFO - __main__ - Step 98687: {'lr': 0.00013421048023264028, 'samples': 18947904, 'steps': 98686, 'loss/train': 0.8605912327766418} 08/31/2021 07:04:21 - INFO - __main__ - Step 98688: {'lr': 0.00013420577702023373, 'samples': 18948096, 'steps': 98687, 'loss/train': 1.5124200582504272} 08/31/2021 07:04:21 - INFO - __main__ - Step 98689: {'lr': 0.00013420107386000226, 'samples': 18948288, 'steps': 98688, 'loss/train': 1.219067931175232} 08/31/2021 07:04:21 - INFO - __main__ - Step 98690: {'lr': 0.0001341963707519481, 'samples': 18948480, 'steps': 98689, 'loss/train': 1.104477047920227} 08/31/2021 07:04:23 - INFO - __main__ - Step 98691: {'lr': 0.00013419166769607316, 'samples': 18948672, 'steps': 98690, 'loss/train': 0.9591729044914246} 08/31/2021 07:04:24 - INFO - __main__ - Step 98692: {'lr': 0.00013418696469237967, 'samples': 18948864, 'steps': 98691, 'loss/train': 1.1058452129364014} 08/31/2021 07:04:24 - INFO - __main__ - Step 98693: {'lr': 0.00013418226174086975, 'samples': 18949056, 'steps': 98692, 'loss/train': 1.45004141330719} 08/31/2021 07:04:25 - INFO - __main__ - Step 98694: {'lr': 0.00013417755884154552, 'samples': 18949248, 'steps': 98693, 'loss/train': 1.235135555267334} 08/31/2021 07:04:25 - INFO - __main__ - Step 98695: {'lr': 0.0001341728559944091, 'samples': 18949440, 'steps': 98694, 'loss/train': 1.064846396446228} 08/31/2021 07:04:25 - INFO - __main__ - Step 98696: {'lr': 0.00013416815319946258, 'samples': 18949632, 'steps': 98695, 'loss/train': 0.6073023080825806} 08/31/2021 07:04:27 - INFO - __main__ - Step 98697: {'lr': 0.00013416345045670814, 'samples': 18949824, 'steps': 98696, 'loss/train': 1.132477045059204} 08/31/2021 07:04:28 - INFO - __main__ - Step 98698: {'lr': 0.00013415874776614783, 'samples': 18950016, 'steps': 98697, 'loss/train': 0.01914091967046261} 08/31/2021 07:04:28 - INFO - __main__ - Step 98699: {'lr': 0.00013415404512778382, 'samples': 18950208, 'steps': 98698, 'loss/train': 1.316327691078186} 08/31/2021 07:04:28 - INFO - __main__ - Step 98700: {'lr': 0.0001341493425416182, 'samples': 18950400, 'steps': 98699, 'loss/train': 1.8391128778457642} 08/31/2021 07:04:29 - INFO - __main__ - Step 98701: {'lr': 0.0001341446400076531, 'samples': 18950592, 'steps': 98700, 'loss/train': 1.2094151973724365} 08/31/2021 07:04:29 - INFO - __main__ - Step 98702: {'lr': 0.00013413993752589063, 'samples': 18950784, 'steps': 98701, 'loss/train': 1.2402691841125488} 08/31/2021 07:04:31 - INFO - __main__ - Step 98703: {'lr': 0.00013413523509633301, 'samples': 18950976, 'steps': 98702, 'loss/train': 0.532869279384613} 08/31/2021 07:04:31 - INFO - __main__ - Step 98704: {'lr': 0.00013413053271898217, 'samples': 18951168, 'steps': 98703, 'loss/train': 1.4646064043045044} 08/31/2021 07:04:31 - INFO - __main__ - Step 98705: {'lr': 0.00013412583039384035, 'samples': 18951360, 'steps': 98704, 'loss/train': 0.5509979128837585} 08/31/2021 07:04:32 - INFO - __main__ - Step 98706: {'lr': 0.0001341211281209096, 'samples': 18951552, 'steps': 98705, 'loss/train': 1.3719319105148315} 08/31/2021 07:04:32 - INFO - __main__ - Step 98707: {'lr': 0.00013411642590019214, 'samples': 18951744, 'steps': 98706, 'loss/train': 0.7627738118171692} 08/31/2021 07:04:34 - INFO - __main__ - Step 98708: {'lr': 0.00013411172373168997, 'samples': 18951936, 'steps': 98707, 'loss/train': 1.5284297466278076} 08/31/2021 07:04:34 - INFO - __main__ - Step 98709: {'lr': 0.00013410702161540528, 'samples': 18952128, 'steps': 98708, 'loss/train': 1.7487456798553467} 08/31/2021 07:04:34 - INFO - __main__ - Step 98710: {'lr': 0.00013410231955134023, 'samples': 18952320, 'steps': 98709, 'loss/train': 0.6627320647239685} 08/31/2021 07:04:35 - INFO - __main__ - Step 98711: {'lr': 0.00013409761753949685, 'samples': 18952512, 'steps': 98710, 'loss/train': 1.0620828866958618} 08/31/2021 07:04:35 - INFO - __main__ - Step 98712: {'lr': 0.00013409291557987726, 'samples': 18952704, 'steps': 98711, 'loss/train': 1.0256617069244385} 08/31/2021 07:04:37 - INFO - __main__ - Step 98713: {'lr': 0.00013408821367248363, 'samples': 18952896, 'steps': 98712, 'loss/train': 0.6903265714645386} 08/31/2021 07:04:37 - INFO - __main__ - Step 98714: {'lr': 0.00013408351181731808, 'samples': 18953088, 'steps': 98713, 'loss/train': 1.0246965885162354} 08/31/2021 07:04:37 - INFO - __main__ - Step 98715: {'lr': 0.00013407881001438273, 'samples': 18953280, 'steps': 98714, 'loss/train': 1.3214046955108643} 08/31/2021 07:04:38 - INFO - __main__ - Step 98716: {'lr': 0.00013407410826367976, 'samples': 18953472, 'steps': 98715, 'loss/train': 0.7747198343276978} 08/31/2021 07:04:38 - INFO - __main__ - Step 98717: {'lr': 0.0001340694065652111, 'samples': 18953664, 'steps': 98716, 'loss/train': 0.8502606749534607} 08/31/2021 07:04:40 - INFO - __main__ - Step 98718: {'lr': 0.000134064704918979, 'samples': 18953856, 'steps': 98717, 'loss/train': 0.9125277400016785} 08/31/2021 07:04:40 - INFO - __main__ - Step 98719: {'lr': 0.00013406000332498552, 'samples': 18954048, 'steps': 98718, 'loss/train': 1.246095061302185} 08/31/2021 07:04:40 - INFO - __main__ - Step 98720: {'lr': 0.00013405530178323282, 'samples': 18954240, 'steps': 98719, 'loss/train': 1.0061511993408203} 08/31/2021 07:04:41 - INFO - __main__ - Step 98721: {'lr': 0.00013405060029372307, 'samples': 18954432, 'steps': 98720, 'loss/train': 1.2722002267837524} 08/31/2021 07:04:41 - INFO - __main__ - Step 98722: {'lr': 0.00013404589885645827, 'samples': 18954624, 'steps': 98721, 'loss/train': 0.7586686015129089} 08/31/2021 07:04:42 - INFO - __main__ - Step 98723: {'lr': 0.00013404119747144062, 'samples': 18954816, 'steps': 98722, 'loss/train': 1.4944953918457031} 08/31/2021 07:04:43 - INFO - __main__ - Step 98724: {'lr': 0.0001340364961386722, 'samples': 18955008, 'steps': 98723, 'loss/train': 1.6667335033416748} 08/31/2021 07:04:43 - INFO - __main__ - Step 98725: {'lr': 0.00013403179485815513, 'samples': 18955200, 'steps': 98724, 'loss/train': 0.4113411605358124} 08/31/2021 07:04:44 - INFO - __main__ - Step 98726: {'lr': 0.0001340270936298916, 'samples': 18955392, 'steps': 98725, 'loss/train': 1.4091087579727173} 08/31/2021 07:04:44 - INFO - __main__ - Step 98727: {'lr': 0.00013402239245388365, 'samples': 18955584, 'steps': 98726, 'loss/train': 1.2060186862945557} 08/31/2021 07:04:46 - INFO - __main__ - Step 98728: {'lr': 0.0001340176913301334, 'samples': 18955776, 'steps': 98727, 'loss/train': 0.9491299986839294} 08/31/2021 07:04:46 - INFO - __main__ - Step 98729: {'lr': 0.000134012990258643, 'samples': 18955968, 'steps': 98728, 'loss/train': 1.1493122577667236} 08/31/2021 07:04:47 - INFO - __main__ - Step 98730: {'lr': 0.00013400828923941467, 'samples': 18956160, 'steps': 98729, 'loss/train': 0.014312605373561382} 08/31/2021 07:04:47 - INFO - __main__ - Step 98731: {'lr': 0.00013400358827245028, 'samples': 18956352, 'steps': 98730, 'loss/train': 1.5784587860107422} 08/31/2021 07:04:47 - INFO - __main__ - Step 98732: {'lr': 0.0001339988873577521, 'samples': 18956544, 'steps': 98731, 'loss/train': 1.2668671607971191} 08/31/2021 07:04:48 - INFO - __main__ - Step 98733: {'lr': 0.00013399418649532224, 'samples': 18956736, 'steps': 98732, 'loss/train': 1.4235106706619263} 08/31/2021 07:04:49 - INFO - __main__ - Step 98734: {'lr': 0.00013398948568516284, 'samples': 18956928, 'steps': 98733, 'loss/train': 1.0964012145996094} 08/31/2021 07:04:50 - INFO - __main__ - Step 98735: {'lr': 0.00013398478492727595, 'samples': 18957120, 'steps': 98734, 'loss/train': 0.9610104560852051} 08/31/2021 07:04:50 - INFO - __main__ - Step 98736: {'lr': 0.00013398008422166373, 'samples': 18957312, 'steps': 98735, 'loss/train': 0.22261251509189606} 08/31/2021 07:04:50 - INFO - __main__ - Step 98737: {'lr': 0.00013397538356832827, 'samples': 18957504, 'steps': 98736, 'loss/train': 1.1352072954177856} 08/31/2021 07:04:51 - INFO - __main__ - Step 98738: {'lr': 0.00013397068296727173, 'samples': 18957696, 'steps': 98737, 'loss/train': 2.21064829826355} 08/31/2021 07:04:51 - INFO - __main__ - Step 98739: {'lr': 0.0001339659824184962, 'samples': 18957888, 'steps': 98738, 'loss/train': 1.3497000932693481} 08/31/2021 07:04:53 - INFO - __main__ - Step 98740: {'lr': 0.00013396128192200385, 'samples': 18958080, 'steps': 98739, 'loss/train': 1.1738941669464111} 08/31/2021 07:04:53 - INFO - __main__ - Step 98741: {'lr': 0.0001339565814777967, 'samples': 18958272, 'steps': 98740, 'loss/train': 0.5455629229545593} 08/31/2021 07:04:54 - INFO - __main__ - Step 98742: {'lr': 0.00013395188108587697, 'samples': 18958464, 'steps': 98741, 'loss/train': 0.9296185970306396} 08/31/2021 07:04:54 - INFO - __main__ - Step 98743: {'lr': 0.00013394718074624684, 'samples': 18958656, 'steps': 98742, 'loss/train': 1.2218776941299438} 08/31/2021 07:04:54 - INFO - __main__ - Step 98744: {'lr': 0.00013394248045890816, 'samples': 18958848, 'steps': 98743, 'loss/train': 0.9173516631126404} 08/31/2021 07:04:56 - INFO - __main__ - Step 98745: {'lr': 0.00013393778022386326, 'samples': 18959040, 'steps': 98744, 'loss/train': 0.9096903204917908} 08/31/2021 07:04:56 - INFO - __main__ - Step 98746: {'lr': 0.0001339330800411142, 'samples': 18959232, 'steps': 98745, 'loss/train': 1.2853330373764038} 08/31/2021 07:04:57 - INFO - __main__ - Step 98747: {'lr': 0.00013392837991066308, 'samples': 18959424, 'steps': 98746, 'loss/train': 1.2321679592132568} 08/31/2021 07:04:57 - INFO - __main__ - Step 98748: {'lr': 0.00013392367983251205, 'samples': 18959616, 'steps': 98747, 'loss/train': 1.2988293170928955} 08/31/2021 07:04:57 - INFO - __main__ - Step 98749: {'lr': 0.00013391897980666323, 'samples': 18959808, 'steps': 98748, 'loss/train': 0.5878225564956665} 08/31/2021 07:04:59 - INFO - __main__ - Step 98750: {'lr': 0.0001339142798331187, 'samples': 18960000, 'steps': 98749, 'loss/train': 0.295879602432251} 08/31/2021 07:05:00 - INFO - __main__ - Step 98751: {'lr': 0.00013390957991188062, 'samples': 18960192, 'steps': 98750, 'loss/train': 1.5320647954940796} 08/31/2021 07:05:00 - INFO - __main__ - Step 98752: {'lr': 0.0001339048800429511, 'samples': 18960384, 'steps': 98751, 'loss/train': 1.2546055316925049} 08/31/2021 07:05:01 - INFO - __main__ - Step 98753: {'lr': 0.00013390018022633223, 'samples': 18960576, 'steps': 98752, 'loss/train': 1.090251088142395} 08/31/2021 07:05:01 - INFO - __main__ - Step 98754: {'lr': 0.00013389548046202615, 'samples': 18960768, 'steps': 98753, 'loss/train': 1.128432273864746} 08/31/2021 07:05:03 - INFO - __main__ - Step 98755: {'lr': 0.000133890780750035, 'samples': 18960960, 'steps': 98754, 'loss/train': 1.1646496057510376} 08/31/2021 07:05:03 - INFO - __main__ - Step 98756: {'lr': 0.00013388608109036085, 'samples': 18961152, 'steps': 98755, 'loss/train': 2.246176242828369} 08/31/2021 07:05:04 - INFO - __main__ - Step 98757: {'lr': 0.00013388138148300594, 'samples': 18961344, 'steps': 98756, 'loss/train': 1.3218677043914795} 08/31/2021 07:05:04 - INFO - __main__ - Step 98758: {'lr': 0.0001338766819279722, 'samples': 18961536, 'steps': 98757, 'loss/train': 0.7469286918640137} 08/31/2021 07:05:04 - INFO - __main__ - Step 98759: {'lr': 0.00013387198242526183, 'samples': 18961728, 'steps': 98758, 'loss/train': 1.094513177871704} 08/31/2021 07:05:06 - INFO - __main__ - Step 98760: {'lr': 0.00013386728297487693, 'samples': 18961920, 'steps': 98759, 'loss/train': 0.8485645651817322} 08/31/2021 07:05:06 - INFO - __main__ - Step 98761: {'lr': 0.00013386258357681968, 'samples': 18962112, 'steps': 98760, 'loss/train': 1.2519090175628662} 08/31/2021 07:05:07 - INFO - __main__ - Step 98762: {'lr': 0.00013385788423109213, 'samples': 18962304, 'steps': 98761, 'loss/train': 0.9433420300483704} 08/31/2021 07:05:07 - INFO - __main__ - Step 98763: {'lr': 0.00013385318493769644, 'samples': 18962496, 'steps': 98762, 'loss/train': 1.0645519495010376} 08/31/2021 07:05:08 - INFO - __main__ - Step 98764: {'lr': 0.0001338484856966347, 'samples': 18962688, 'steps': 98763, 'loss/train': 1.841583013534546} 08/31/2021 07:05:09 - INFO - __main__ - Step 98765: {'lr': 0.00013384378650790907, 'samples': 18962880, 'steps': 98764, 'loss/train': 0.02855861186981201} 08/31/2021 07:05:09 - INFO - __main__ - Step 98766: {'lr': 0.00013383908737152163, 'samples': 18963072, 'steps': 98765, 'loss/train': 0.5105165243148804} 08/31/2021 07:05:10 - INFO - __main__ - Step 98767: {'lr': 0.00013383438828747446, 'samples': 18963264, 'steps': 98766, 'loss/train': 1.4960356950759888} 08/31/2021 07:05:10 - INFO - __main__ - Step 98768: {'lr': 0.00013382968925576978, 'samples': 18963456, 'steps': 98767, 'loss/train': 1.6599570512771606} 08/31/2021 07:05:11 - INFO - __main__ - Step 98769: {'lr': 0.0001338249902764096, 'samples': 18963648, 'steps': 98768, 'loss/train': 0.9287291765213013} 08/31/2021 07:05:11 - INFO - __main__ - Step 98770: {'lr': 0.0001338202913493962, 'samples': 18963840, 'steps': 98769, 'loss/train': 1.8549396991729736} 08/31/2021 07:05:13 - INFO - __main__ - Step 98771: {'lr': 0.0001338155924747315, 'samples': 18964032, 'steps': 98770, 'loss/train': 1.5987226963043213} 08/31/2021 07:05:13 - INFO - __main__ - Step 98772: {'lr': 0.00013381089365241769, 'samples': 18964224, 'steps': 98771, 'loss/train': 0.47904232144355774} 08/31/2021 07:05:13 - INFO - __main__ - Step 98773: {'lr': 0.00013380619488245692, 'samples': 18964416, 'steps': 98772, 'loss/train': 0.8040108680725098} 08/31/2021 07:05:14 - INFO - __main__ - Step 98774: {'lr': 0.00013380149616485127, 'samples': 18964608, 'steps': 98773, 'loss/train': 1.3144289255142212} 08/31/2021 07:05:14 - INFO - __main__ - Step 98775: {'lr': 0.00013379679749960286, 'samples': 18964800, 'steps': 98774, 'loss/train': 0.4812942147254944} 08/31/2021 07:05:16 - INFO - __main__ - Step 98776: {'lr': 0.00013379209888671385, 'samples': 18964992, 'steps': 98775, 'loss/train': 0.7406139969825745} 08/31/2021 07:05:16 - INFO - __main__ - Step 98777: {'lr': 0.00013378740032618627, 'samples': 18965184, 'steps': 98776, 'loss/train': 1.0608938932418823} 08/31/2021 07:05:17 - INFO - __main__ - Step 98778: {'lr': 0.00013378270181802233, 'samples': 18965376, 'steps': 98777, 'loss/train': 0.9783658385276794} 08/31/2021 07:05:17 - INFO - __main__ - Step 98779: {'lr': 0.00013377800336222413, 'samples': 18965568, 'steps': 98778, 'loss/train': 1.0204317569732666} 08/31/2021 07:05:17 - INFO - __main__ - Step 98780: {'lr': 0.00013377330495879374, 'samples': 18965760, 'steps': 98779, 'loss/train': 0.9214433431625366} 08/31/2021 07:05:19 - INFO - __main__ - Step 98781: {'lr': 0.00013376860660773332, 'samples': 18965952, 'steps': 98780, 'loss/train': 1.0086041688919067} 08/31/2021 07:05:19 - INFO - __main__ - Step 98782: {'lr': 0.00013376390830904496, 'samples': 18966144, 'steps': 98781, 'loss/train': 0.9963797330856323} 08/31/2021 07:05:20 - INFO - __main__ - Step 98783: {'lr': 0.0001337592100627308, 'samples': 18966336, 'steps': 98782, 'loss/train': 1.7442395687103271} 08/31/2021 07:05:20 - INFO - __main__ - Step 98784: {'lr': 0.00013375451186879307, 'samples': 18966528, 'steps': 98783, 'loss/train': 1.3481700420379639} 08/31/2021 07:05:20 - INFO - __main__ - Step 98785: {'lr': 0.0001337498137272336, 'samples': 18966720, 'steps': 98784, 'loss/train': 1.142989993095398} 08/31/2021 07:05:22 - INFO - __main__ - Step 98786: {'lr': 0.00013374511563805472, 'samples': 18966912, 'steps': 98785, 'loss/train': 1.0298124551773071} 08/31/2021 07:05:22 - INFO - __main__ - Step 98787: {'lr': 0.00013374041760125848, 'samples': 18967104, 'steps': 98786, 'loss/train': 0.9570989608764648} 08/31/2021 07:05:23 - INFO - __main__ - Step 98788: {'lr': 0.00013373571961684702, 'samples': 18967296, 'steps': 98787, 'loss/train': 0.8958974480628967} 08/31/2021 07:05:23 - INFO - __main__ - Step 98789: {'lr': 0.00013373102168482245, 'samples': 18967488, 'steps': 98788, 'loss/train': 1.3634769916534424} 08/31/2021 07:05:23 - INFO - __main__ - Step 98790: {'lr': 0.0001337263238051869, 'samples': 18967680, 'steps': 98789, 'loss/train': 1.627397060394287} 08/31/2021 07:05:25 - INFO - __main__ - Step 98791: {'lr': 0.00013372162597794247, 'samples': 18967872, 'steps': 98790, 'loss/train': 0.44567713141441345} 08/31/2021 07:05:25 - INFO - __main__ - Step 98792: {'lr': 0.00013371692820309124, 'samples': 18968064, 'steps': 98791, 'loss/train': 0.972441554069519} 08/31/2021 07:05:26 - INFO - __main__ - Step 98793: {'lr': 0.00013371223048063541, 'samples': 18968256, 'steps': 98792, 'loss/train': 0.8169844150543213} 08/31/2021 07:05:26 - INFO - __main__ - Step 98794: {'lr': 0.00013370753281057704, 'samples': 18968448, 'steps': 98793, 'loss/train': 1.1179478168487549} 08/31/2021 07:05:26 - INFO - __main__ - Step 98795: {'lr': 0.00013370283519291827, 'samples': 18968640, 'steps': 98794, 'loss/train': 0.8010036945343018} 08/31/2021 07:05:28 - INFO - __main__ - Step 98796: {'lr': 0.00013369813762766119, 'samples': 18968832, 'steps': 98795, 'loss/train': 1.5250365734100342} 08/31/2021 07:05:28 - INFO - __main__ - Step 98797: {'lr': 0.00013369344011480806, 'samples': 18969024, 'steps': 98796, 'loss/train': 1.2170636653900146} 08/31/2021 07:05:29 - INFO - __main__ - Step 98798: {'lr': 0.00013368874265436075, 'samples': 18969216, 'steps': 98797, 'loss/train': 1.4374922513961792} 08/31/2021 07:05:29 - INFO - __main__ - Step 98799: {'lr': 0.0001336840452463215, 'samples': 18969408, 'steps': 98798, 'loss/train': 1.1627689599990845} 08/31/2021 07:05:29 - INFO - __main__ - Step 98800: {'lr': 0.00013367934789069246, 'samples': 18969600, 'steps': 98799, 'loss/train': 0.8277335166931152} 08/31/2021 07:05:30 - INFO - __main__ - Step 98801: {'lr': 0.00013367465058747565, 'samples': 18969792, 'steps': 98800, 'loss/train': 0.14597590267658234} 08/31/2021 07:05:32 - INFO - __main__ - Step 98802: {'lr': 0.0001336699533366733, 'samples': 18969984, 'steps': 98801, 'loss/train': 0.9410943388938904} 08/31/2021 07:05:33 - INFO - __main__ - Step 98803: {'lr': 0.00013366525613828746, 'samples': 18970176, 'steps': 98802, 'loss/train': 1.0947264432907104} 08/31/2021 07:05:33 - INFO - __main__ - Step 98804: {'lr': 0.00013366055899232025, 'samples': 18970368, 'steps': 98803, 'loss/train': 0.5958264470100403} 08/31/2021 07:05:33 - INFO - __main__ - Step 98805: {'lr': 0.00013365586189877378, 'samples': 18970560, 'steps': 98804, 'loss/train': 1.5124396085739136} 08/31/2021 07:05:34 - INFO - __main__ - Step 98806: {'lr': 0.00013365116485765022, 'samples': 18970752, 'steps': 98805, 'loss/train': 1.305275797843933} 08/31/2021 07:05:35 - INFO - __main__ - Step 98807: {'lr': 0.00013364646786895163, 'samples': 18970944, 'steps': 98806, 'loss/train': 0.7153275609016418} 08/31/2021 07:05:35 - INFO - __main__ - Step 98808: {'lr': 0.00013364177093268015, 'samples': 18971136, 'steps': 98807, 'loss/train': 1.3800173997879028} 08/31/2021 07:05:36 - INFO - __main__ - Step 98809: {'lr': 0.0001336370740488379, 'samples': 18971328, 'steps': 98808, 'loss/train': 0.5887880921363831} 08/31/2021 07:05:36 - INFO - __main__ - Step 98810: {'lr': 0.00013363237721742696, 'samples': 18971520, 'steps': 98809, 'loss/train': 1.3446577787399292} 08/31/2021 07:05:37 - INFO - __main__ - Step 98811: {'lr': 0.00013362768043844958, 'samples': 18971712, 'steps': 98810, 'loss/train': 1.0597620010375977} 08/31/2021 07:05:38 - INFO - __main__ - Step 98812: {'lr': 0.0001336229837119077, 'samples': 18971904, 'steps': 98811, 'loss/train': 1.5710036754608154} 08/31/2021 07:05:39 - INFO - __main__ - Step 98813: {'lr': 0.0001336182870378035, 'samples': 18972096, 'steps': 98812, 'loss/train': 0.7078202366828918} 08/31/2021 07:05:39 - INFO - __main__ - Step 98814: {'lr': 0.0001336135904161391, 'samples': 18972288, 'steps': 98813, 'loss/train': 1.45558762550354} 08/31/2021 07:05:39 - INFO - __main__ - Step 98815: {'lr': 0.0001336088938469166, 'samples': 18972480, 'steps': 98814, 'loss/train': 0.8801798820495605} 08/31/2021 07:05:40 - INFO - __main__ - Step 98816: {'lr': 0.00013360419733013818, 'samples': 18972672, 'steps': 98815, 'loss/train': 0.8240532279014587} 08/31/2021 07:05:41 - INFO - __main__ - Step 98817: {'lr': 0.0001335995008658059, 'samples': 18972864, 'steps': 98816, 'loss/train': 1.6434834003448486} 08/31/2021 07:05:42 - INFO - __main__ - Step 98818: {'lr': 0.00013359480445392186, 'samples': 18973056, 'steps': 98817, 'loss/train': 1.673188328742981} 08/31/2021 07:05:42 - INFO - __main__ - Step 98819: {'lr': 0.00013359010809448825, 'samples': 18973248, 'steps': 98818, 'loss/train': 0.887004017829895} 08/31/2021 07:05:42 - INFO - __main__ - Step 98820: {'lr': 0.00013358541178750712, 'samples': 18973440, 'steps': 98819, 'loss/train': 1.439517855644226} 08/31/2021 07:05:43 - INFO - __main__ - Step 98821: {'lr': 0.00013358071553298055, 'samples': 18973632, 'steps': 98820, 'loss/train': 5.740662574768066} 08/31/2021 07:05:43 - INFO - __main__ - Step 98822: {'lr': 0.00013357601933091078, 'samples': 18973824, 'steps': 98821, 'loss/train': 1.1917176246643066} 08/31/2021 07:05:44 - INFO - __main__ - Step 98823: {'lr': 0.00013357132318129984, 'samples': 18974016, 'steps': 98822, 'loss/train': 1.6763508319854736} 08/31/2021 07:05:45 - INFO - __main__ - Step 98824: {'lr': 0.00013356662708414996, 'samples': 18974208, 'steps': 98823, 'loss/train': 1.0317280292510986} 08/31/2021 07:05:45 - INFO - __main__ - Step 98825: {'lr': 0.00013356193103946306, 'samples': 18974400, 'steps': 98824, 'loss/train': 0.6051830053329468} 08/31/2021 07:05:46 - INFO - __main__ - Step 98826: {'lr': 0.00013355723504724138, 'samples': 18974592, 'steps': 98825, 'loss/train': 1.6655398607254028} 08/31/2021 07:05:46 - INFO - __main__ - Step 98827: {'lr': 0.000133552539107487, 'samples': 18974784, 'steps': 98826, 'loss/train': 0.9554566144943237} 08/31/2021 07:05:47 - INFO - __main__ - Step 98828: {'lr': 0.00013354784322020202, 'samples': 18974976, 'steps': 98827, 'loss/train': 0.430431604385376} 08/31/2021 07:05:48 - INFO - __main__ - Step 98829: {'lr': 0.00013354314738538863, 'samples': 18975168, 'steps': 98828, 'loss/train': 1.1879175901412964} 08/31/2021 07:05:48 - INFO - __main__ - Step 98830: {'lr': 0.0001335384516030489, 'samples': 18975360, 'steps': 98829, 'loss/train': 0.6200684309005737} 08/31/2021 07:05:49 - INFO - __main__ - Step 98831: {'lr': 0.00013353375587318492, 'samples': 18975552, 'steps': 98830, 'loss/train': 0.7350080609321594} 08/31/2021 07:05:49 - INFO - __main__ - Step 98832: {'lr': 0.00013352906019579885, 'samples': 18975744, 'steps': 98831, 'loss/train': 1.333078145980835} 08/31/2021 07:05:50 - INFO - __main__ - Step 98833: {'lr': 0.00013352436457089278, 'samples': 18975936, 'steps': 98832, 'loss/train': 1.1744606494903564} 08/31/2021 07:05:51 - INFO - __main__ - Step 98834: {'lr': 0.00013351966899846884, 'samples': 18976128, 'steps': 98833, 'loss/train': 1.4248113632202148} 08/31/2021 07:05:51 - INFO - __main__ - Step 98835: {'lr': 0.00013351497347852912, 'samples': 18976320, 'steps': 98834, 'loss/train': 1.4909323453903198} 08/31/2021 07:05:52 - INFO - __main__ - Step 98836: {'lr': 0.0001335102780110758, 'samples': 18976512, 'steps': 98835, 'loss/train': 0.9493858218193054} 08/31/2021 07:05:52 - INFO - __main__ - Step 98837: {'lr': 0.00013350558259611102, 'samples': 18976704, 'steps': 98836, 'loss/train': 1.5092273950576782} 08/31/2021 07:05:53 - INFO - __main__ - Step 98838: {'lr': 0.00013350088723363668, 'samples': 18976896, 'steps': 98837, 'loss/train': 1.7988694906234741} 08/31/2021 07:05:54 - INFO - __main__ - Step 98839: {'lr': 0.00013349619192365512, 'samples': 18977088, 'steps': 98838, 'loss/train': 1.1473536491394043} 08/31/2021 07:05:54 - INFO - __main__ - Step 98840: {'lr': 0.00013349149666616833, 'samples': 18977280, 'steps': 98839, 'loss/train': 1.5647478103637695} 08/31/2021 07:05:55 - INFO - __main__ - Step 98841: {'lr': 0.0001334868014611785, 'samples': 18977472, 'steps': 98840, 'loss/train': 1.155071496963501} 08/31/2021 07:05:55 - INFO - __main__ - Step 98842: {'lr': 0.00013348210630868772, 'samples': 18977664, 'steps': 98841, 'loss/train': 1.321251392364502} 08/31/2021 07:05:55 - INFO - __main__ - Step 98843: {'lr': 0.0001334774112086981, 'samples': 18977856, 'steps': 98842, 'loss/train': 0.9022576808929443} 08/31/2021 07:05:57 - INFO - __main__ - Step 98844: {'lr': 0.00013347271616121175, 'samples': 18978048, 'steps': 98843, 'loss/train': 2.2125608921051025} 08/31/2021 07:05:57 - INFO - __main__ - Step 98845: {'lr': 0.0001334680211662308, 'samples': 18978240, 'steps': 98844, 'loss/train': 1.2102500200271606} 08/31/2021 07:05:57 - INFO - __main__ - Step 98846: {'lr': 0.00013346332622375735, 'samples': 18978432, 'steps': 98845, 'loss/train': 0.5791769027709961} 08/31/2021 07:05:58 - INFO - __main__ - Step 98847: {'lr': 0.00013345863133379355, 'samples': 18978624, 'steps': 98846, 'loss/train': 0.6887972354888916} 08/31/2021 07:05:58 - INFO - __main__ - Step 98848: {'lr': 0.0001334539364963415, 'samples': 18978816, 'steps': 98847, 'loss/train': 0.8600751757621765} 08/31/2021 07:06:00 - INFO - __main__ - Step 98849: {'lr': 0.00013344924171140326, 'samples': 18979008, 'steps': 98848, 'loss/train': 0.38840940594673157} 08/31/2021 07:06:00 - INFO - __main__ - Step 98850: {'lr': 0.00013344454697898108, 'samples': 18979200, 'steps': 98849, 'loss/train': 0.9258813261985779} 08/31/2021 07:06:00 - INFO - __main__ - Step 98851: {'lr': 0.00013343985229907703, 'samples': 18979392, 'steps': 98850, 'loss/train': 1.574149489402771} 08/31/2021 07:06:01 - INFO - __main__ - Step 98852: {'lr': 0.00013343515767169306, 'samples': 18979584, 'steps': 98851, 'loss/train': 1.7474168539047241} 08/31/2021 07:06:01 - INFO - __main__ - Step 98853: {'lr': 0.00013343046309683145, 'samples': 18979776, 'steps': 98852, 'loss/train': 0.2492651492357254} 08/31/2021 07:06:03 - INFO - __main__ - Step 98854: {'lr': 0.00013342576857449423, 'samples': 18979968, 'steps': 98853, 'loss/train': 0.5337806344032288} 08/31/2021 07:06:03 - INFO - __main__ - Step 98855: {'lr': 0.0001334210741046836, 'samples': 18980160, 'steps': 98854, 'loss/train': 1.318331003189087} 08/31/2021 07:06:03 - INFO - __main__ - Step 98856: {'lr': 0.0001334163796874016, 'samples': 18980352, 'steps': 98855, 'loss/train': 1.0635579824447632} 08/31/2021 07:06:04 - INFO - __main__ - Step 98857: {'lr': 0.00013341168532265044, 'samples': 18980544, 'steps': 98856, 'loss/train': 0.9566988348960876} 08/31/2021 07:06:04 - INFO - __main__ - Step 98858: {'lr': 0.00013340699101043214, 'samples': 18980736, 'steps': 98857, 'loss/train': 0.9985548853874207} 08/31/2021 07:06:06 - INFO - __main__ - Step 98859: {'lr': 0.00013340229675074883, 'samples': 18980928, 'steps': 98858, 'loss/train': 0.8071998357772827} 08/31/2021 07:06:07 - INFO - __main__ - Step 98860: {'lr': 0.00013339760254360268, 'samples': 18981120, 'steps': 98859, 'loss/train': 2.1696529388427734} 08/31/2021 07:06:07 - INFO - __main__ - Step 98861: {'lr': 0.00013339290838899575, 'samples': 18981312, 'steps': 98860, 'loss/train': 1.711277961730957} 08/31/2021 07:06:07 - INFO - __main__ - Step 98862: {'lr': 0.0001333882142869302, 'samples': 18981504, 'steps': 98861, 'loss/train': 1.324466586112976} 08/31/2021 07:06:08 - INFO - __main__ - Step 98863: {'lr': 0.0001333835202374081, 'samples': 18981696, 'steps': 98862, 'loss/train': 2.1764612197875977} 08/31/2021 07:06:09 - INFO - __main__ - Step 98864: {'lr': 0.00013337882624043167, 'samples': 18981888, 'steps': 98863, 'loss/train': 1.2853710651397705} 08/31/2021 07:06:10 - INFO - __main__ - Step 98865: {'lr': 0.0001333741322960029, 'samples': 18982080, 'steps': 98864, 'loss/train': 1.3473680019378662} 08/31/2021 07:06:10 - INFO - __main__ - Step 98866: {'lr': 0.00013336943840412392, 'samples': 18982272, 'steps': 98865, 'loss/train': 1.7571603059768677} 08/31/2021 07:06:10 - INFO - __main__ - Step 98867: {'lr': 0.00013336474456479685, 'samples': 18982464, 'steps': 98866, 'loss/train': 1.4488977193832397} 08/31/2021 07:06:11 - INFO - __main__ - Step 98868: {'lr': 0.00013336005077802383, 'samples': 18982656, 'steps': 98867, 'loss/train': 0.8534328937530518} 08/31/2021 07:06:11 - INFO - __main__ - Step 98869: {'lr': 0.00013335535704380697, 'samples': 18982848, 'steps': 98868, 'loss/train': 1.9855878353118896} 08/31/2021 07:06:13 - INFO - __main__ - Step 98870: {'lr': 0.0001333506633621484, 'samples': 18983040, 'steps': 98869, 'loss/train': 1.2976559400558472} 08/31/2021 07:06:13 - INFO - __main__ - Step 98871: {'lr': 0.00013334596973305025, 'samples': 18983232, 'steps': 98870, 'loss/train': 0.8058921098709106} 08/31/2021 07:06:13 - INFO - __main__ - Step 98872: {'lr': 0.00013334127615651452, 'samples': 18983424, 'steps': 98871, 'loss/train': 1.7926398515701294} 08/31/2021 07:06:14 - INFO - __main__ - Step 98873: {'lr': 0.00013333658263254351, 'samples': 18983616, 'steps': 98872, 'loss/train': 1.5915162563323975} 08/31/2021 07:06:14 - INFO - __main__ - Step 98874: {'lr': 0.00013333188916113918, 'samples': 18983808, 'steps': 98873, 'loss/train': 0.034803684800863266} 08/31/2021 07:06:16 - INFO - __main__ - Step 98875: {'lr': 0.0001333271957423037, 'samples': 18984000, 'steps': 98874, 'loss/train': 0.5700968503952026} 08/31/2021 07:06:16 - INFO - __main__ - Step 98876: {'lr': 0.00013332250237603921, 'samples': 18984192, 'steps': 98875, 'loss/train': 1.4309628009796143} 08/31/2021 07:06:17 - INFO - __main__ - Step 98877: {'lr': 0.00013331780906234775, 'samples': 18984384, 'steps': 98876, 'loss/train': 1.0472694635391235} 08/31/2021 07:06:17 - INFO - __main__ - Step 98878: {'lr': 0.00013331311580123162, 'samples': 18984576, 'steps': 98877, 'loss/train': 1.135661244392395} 08/31/2021 07:06:17 - INFO - __main__ - Step 98879: {'lr': 0.00013330842259269272, 'samples': 18984768, 'steps': 98878, 'loss/train': 1.1205148696899414} 08/31/2021 07:06:19 - INFO - __main__ - Step 98880: {'lr': 0.00013330372943673322, 'samples': 18984960, 'steps': 98879, 'loss/train': 0.9067323803901672} 08/31/2021 07:06:19 - INFO - __main__ - Step 98881: {'lr': 0.00013329903633335527, 'samples': 18985152, 'steps': 98880, 'loss/train': 0.9683869481086731} 08/31/2021 07:06:20 - INFO - __main__ - Step 98882: {'lr': 0.00013329434328256096, 'samples': 18985344, 'steps': 98881, 'loss/train': 1.8174670934677124} 08/31/2021 07:06:20 - INFO - __main__ - Step 98883: {'lr': 0.0001332896502843524, 'samples': 18985536, 'steps': 98882, 'loss/train': 0.9407746195793152} 08/31/2021 07:06:20 - INFO - __main__ - Step 98884: {'lr': 0.00013328495733873176, 'samples': 18985728, 'steps': 98883, 'loss/train': 0.624552845954895} 08/31/2021 07:06:22 - INFO - __main__ - Step 98885: {'lr': 0.00013328026444570112, 'samples': 18985920, 'steps': 98884, 'loss/train': 0.9196513295173645} 08/31/2021 07:06:22 - INFO - __main__ - Step 98886: {'lr': 0.00013327557160526255, 'samples': 18986112, 'steps': 98885, 'loss/train': 1.2943141460418701} 08/31/2021 07:06:23 - INFO - __main__ - Step 98887: {'lr': 0.00013327087881741823, 'samples': 18986304, 'steps': 98886, 'loss/train': 1.3671152591705322} 08/31/2021 07:06:23 - INFO - __main__ - Step 98888: {'lr': 0.00013326618608217028, 'samples': 18986496, 'steps': 98887, 'loss/train': 1.3003387451171875} 08/31/2021 07:06:24 - INFO - __main__ - Step 98889: {'lr': 0.00013326149339952075, 'samples': 18986688, 'steps': 98888, 'loss/train': 1.098178744316101} 08/31/2021 07:06:25 - INFO - __main__ - Step 98890: {'lr': 0.00013325680076947178, 'samples': 18986880, 'steps': 98889, 'loss/train': 0.5462380647659302} 08/31/2021 07:06:25 - INFO - __main__ - Step 98891: {'lr': 0.0001332521081920256, 'samples': 18987072, 'steps': 98890, 'loss/train': 1.2730062007904053} 08/31/2021 07:06:26 - INFO - __main__ - Step 98892: {'lr': 0.00013324741566718415, 'samples': 18987264, 'steps': 98891, 'loss/train': 1.3058243989944458} 08/31/2021 07:06:26 - INFO - __main__ - Step 98893: {'lr': 0.0001332427231949496, 'samples': 18987456, 'steps': 98892, 'loss/train': 1.3063162565231323} 08/31/2021 07:06:26 - INFO - __main__ - Step 98894: {'lr': 0.00013323803077532406, 'samples': 18987648, 'steps': 98893, 'loss/train': 1.4762040376663208} 08/31/2021 07:06:27 - INFO - __main__ - Step 98895: {'lr': 0.00013323333840830967, 'samples': 18987840, 'steps': 98894, 'loss/train': 1.257189393043518} 08/31/2021 07:06:28 - INFO - __main__ - Step 98896: {'lr': 0.00013322864609390856, 'samples': 18988032, 'steps': 98895, 'loss/train': 0.3494618535041809} 08/31/2021 07:06:29 - INFO - __main__ - Step 98897: {'lr': 0.00013322395383212276, 'samples': 18988224, 'steps': 98896, 'loss/train': 1.1701586246490479} 08/31/2021 07:06:29 - INFO - __main__ - Step 98898: {'lr': 0.00013321926162295451, 'samples': 18988416, 'steps': 98897, 'loss/train': 0.691460132598877} 08/31/2021 07:06:29 - INFO - __main__ - Step 98899: {'lr': 0.00013321456946640582, 'samples': 18988608, 'steps': 98898, 'loss/train': 1.0420576333999634} 08/31/2021 07:06:31 - INFO - __main__ - Step 98900: {'lr': 0.00013320987736247886, 'samples': 18988800, 'steps': 98899, 'loss/train': 1.0892349481582642} 08/31/2021 07:06:32 - INFO - __main__ - Step 98901: {'lr': 0.0001332051853111757, 'samples': 18988992, 'steps': 98900, 'loss/train': 0.9577414989471436} 08/31/2021 07:06:32 - INFO - __main__ - Step 98902: {'lr': 0.0001332004933124985, 'samples': 18989184, 'steps': 98901, 'loss/train': 0.0176435187458992} 08/31/2021 07:06:32 - INFO - __main__ - Step 98903: {'lr': 0.00013319580136644948, 'samples': 18989376, 'steps': 98902, 'loss/train': 1.6489789485931396} 08/31/2021 07:06:33 - INFO - __main__ - Step 98904: {'lr': 0.00013319110947303047, 'samples': 18989568, 'steps': 98903, 'loss/train': 0.28718939423561096} 08/31/2021 07:06:33 - INFO - __main__ - Step 98905: {'lr': 0.00013318641763224382, 'samples': 18989760, 'steps': 98904, 'loss/train': 1.5397838354110718} 08/31/2021 07:06:35 - INFO - __main__ - Step 98906: {'lr': 0.0001331817258440915, 'samples': 18989952, 'steps': 98905, 'loss/train': 1.4720392227172852} 08/31/2021 07:06:36 - INFO - __main__ - Step 98907: {'lr': 0.00013317703410857572, 'samples': 18990144, 'steps': 98906, 'loss/train': 0.9132537841796875} 08/31/2021 07:06:36 - INFO - __main__ - Step 98908: {'lr': 0.0001331723424256986, 'samples': 18990336, 'steps': 98907, 'loss/train': 0.7073020935058594} 08/31/2021 07:06:37 - INFO - __main__ - Step 98909: {'lr': 0.00013316765079546218, 'samples': 18990528, 'steps': 98908, 'loss/train': 1.0889102220535278} 08/31/2021 07:06:37 - INFO - __main__ - Step 98910: {'lr': 0.00013316295921786858, 'samples': 18990720, 'steps': 98909, 'loss/train': 1.7280986309051514} 08/31/2021 07:06:37 - INFO - __main__ - Step 98911: {'lr': 0.00013315826769292, 'samples': 18990912, 'steps': 98910, 'loss/train': 1.6933821439743042} 08/31/2021 07:06:38 - INFO - __main__ - Step 98912: {'lr': 0.0001331535762206185, 'samples': 18991104, 'steps': 98911, 'loss/train': 1.6906275749206543} 08/31/2021 07:06:40 - INFO - __main__ - Step 98913: {'lr': 0.00013314888480096617, 'samples': 18991296, 'steps': 98912, 'loss/train': 1.0932635068893433} 08/31/2021 07:06:40 - INFO - __main__ - Step 98914: {'lr': 0.00013314419343396527, 'samples': 18991488, 'steps': 98913, 'loss/train': 1.2345716953277588} 08/31/2021 07:06:41 - INFO - __main__ - Step 98915: {'lr': 0.00013313950211961767, 'samples': 18991680, 'steps': 98914, 'loss/train': 1.105489730834961} 08/31/2021 07:06:41 - INFO - __main__ - Step 98916: {'lr': 0.00013313481085792565, 'samples': 18991872, 'steps': 98915, 'loss/train': 1.5287530422210693} 08/31/2021 07:06:41 - INFO - __main__ - Step 98917: {'lr': 0.00013313011964889124, 'samples': 18992064, 'steps': 98916, 'loss/train': 0.4979943037033081} 08/31/2021 07:06:42 - INFO - __main__ - Step 98918: {'lr': 0.00013312542849251664, 'samples': 18992256, 'steps': 98917, 'loss/train': 1.3120943307876587} 08/31/2021 07:06:43 - INFO - __main__ - Step 98919: {'lr': 0.00013312073738880388, 'samples': 18992448, 'steps': 98918, 'loss/train': 1.293453335762024} 08/31/2021 07:06:44 - INFO - __main__ - Step 98920: {'lr': 0.0001331160463377551, 'samples': 18992640, 'steps': 98919, 'loss/train': 1.2020410299301147} 08/31/2021 07:06:44 - INFO - __main__ - Step 98921: {'lr': 0.00013311135533937248, 'samples': 18992832, 'steps': 98920, 'loss/train': 1.1888993978500366} 08/31/2021 07:06:44 - INFO - __main__ - Step 98922: {'lr': 0.000133106664393658, 'samples': 18993024, 'steps': 98921, 'loss/train': 0.5725383758544922} 08/31/2021 07:06:45 - INFO - __main__ - Step 98923: {'lr': 0.00013310197350061391, 'samples': 18993216, 'steps': 98922, 'loss/train': 0.3401493430137634} 08/31/2021 07:06:46 - INFO - __main__ - Step 98924: {'lr': 0.00013309728266024223, 'samples': 18993408, 'steps': 98923, 'loss/train': 1.0657273530960083} 08/31/2021 07:06:47 - INFO - __main__ - Step 98925: {'lr': 0.00013309259187254524, 'samples': 18993600, 'steps': 98924, 'loss/train': 1.557182788848877} 08/31/2021 07:06:47 - INFO - __main__ - Step 98926: {'lr': 0.00013308790113752484, 'samples': 18993792, 'steps': 98925, 'loss/train': 1.1525990962982178} 08/31/2021 07:06:47 - INFO - __main__ - Step 98927: {'lr': 0.00013308321045518321, 'samples': 18993984, 'steps': 98926, 'loss/train': 1.0392314195632935} 08/31/2021 07:06:48 - INFO - __main__ - Step 98928: {'lr': 0.0001330785198255225, 'samples': 18994176, 'steps': 98927, 'loss/train': 0.5318811535835266} 08/31/2021 07:06:49 - INFO - __main__ - Step 98929: {'lr': 0.00013307382924854477, 'samples': 18994368, 'steps': 98928, 'loss/train': 1.7256889343261719} 08/31/2021 07:06:50 - INFO - __main__ - Step 98930: {'lr': 0.00013306913872425217, 'samples': 18994560, 'steps': 98929, 'loss/train': 0.10253210365772247} 08/31/2021 07:06:50 - INFO - __main__ - Step 98931: {'lr': 0.00013306444825264682, 'samples': 18994752, 'steps': 98930, 'loss/train': 1.385252833366394} 08/31/2021 07:06:50 - INFO - __main__ - Step 98932: {'lr': 0.00013305975783373082, 'samples': 18994944, 'steps': 98931, 'loss/train': 0.06728701293468475} 08/31/2021 07:06:51 - INFO - __main__ - Step 98933: {'lr': 0.0001330550674675063, 'samples': 18995136, 'steps': 98932, 'loss/train': 1.4377400875091553} 08/31/2021 07:06:52 - INFO - __main__ - Step 98934: {'lr': 0.00013305037715397535, 'samples': 18995328, 'steps': 98933, 'loss/train': 1.5359573364257812} 08/31/2021 07:06:53 - INFO - __main__ - Step 98935: {'lr': 0.00013304568689314012, 'samples': 18995520, 'steps': 98934, 'loss/train': 1.056151270866394} 08/31/2021 07:06:53 - INFO - __main__ - Step 98936: {'lr': 0.0001330409966850028, 'samples': 18995712, 'steps': 98935, 'loss/train': 1.1648279428482056} 08/31/2021 07:06:53 - INFO - __main__ - Step 98937: {'lr': 0.00013303630652956527, 'samples': 18995904, 'steps': 98936, 'loss/train': 0.8110671639442444} 08/31/2021 07:06:54 - INFO - __main__ - Step 98938: {'lr': 0.00013303161642682978, 'samples': 18996096, 'steps': 98937, 'loss/train': 1.5708369016647339} 08/31/2021 07:06:56 - INFO - __main__ - Step 98939: {'lr': 0.00013302692637679847, 'samples': 18996288, 'steps': 98938, 'loss/train': 0.914010763168335} 08/31/2021 07:06:56 - INFO - __main__ - Step 98940: {'lr': 0.0001330222363794734, 'samples': 18996480, 'steps': 98939, 'loss/train': 1.1940912008285522} 08/31/2021 07:06:56 - INFO - __main__ - Step 98941: {'lr': 0.0001330175464348567, 'samples': 18996672, 'steps': 98940, 'loss/train': 1.2550569772720337} 08/31/2021 07:06:57 - INFO - __main__ - Step 98942: {'lr': 0.00013301285654295048, 'samples': 18996864, 'steps': 98941, 'loss/train': 0.05113668367266655} 08/31/2021 07:06:57 - INFO - __main__ - Step 98943: {'lr': 0.00013300816670375686, 'samples': 18997056, 'steps': 98942, 'loss/train': 0.972484290599823} 08/31/2021 07:06:59 - INFO - __main__ - Step 98944: {'lr': 0.000133003476917278, 'samples': 18997248, 'steps': 98943, 'loss/train': 1.2863521575927734} 08/31/2021 07:06:59 - INFO - __main__ - Step 98945: {'lr': 0.00013299878718351594, 'samples': 18997440, 'steps': 98944, 'loss/train': 1.092260718345642} 08/31/2021 07:06:59 - INFO - __main__ - Step 98946: {'lr': 0.00013299409750247283, 'samples': 18997632, 'steps': 98945, 'loss/train': 1.6860302686691284} 08/31/2021 07:07:00 - INFO - __main__ - Step 98947: {'lr': 0.00013298940787415087, 'samples': 18997824, 'steps': 98946, 'loss/train': 4.220773220062256} 08/31/2021 07:07:00 - INFO - __main__ - Step 98948: {'lr': 0.00013298471829855196, 'samples': 18998016, 'steps': 98947, 'loss/train': 0.7613404989242554} 08/31/2021 07:07:02 - INFO - __main__ - Step 98949: {'lr': 0.00013298002877567834, 'samples': 18998208, 'steps': 98948, 'loss/train': 1.3239738941192627} 08/31/2021 07:07:02 - INFO - __main__ - Step 98950: {'lr': 0.00013297533930553212, 'samples': 18998400, 'steps': 98949, 'loss/train': 1.1349589824676514} 08/31/2021 07:07:02 - INFO - __main__ - Step 98951: {'lr': 0.0001329706498881154, 'samples': 18998592, 'steps': 98950, 'loss/train': 1.2292612791061401} 08/31/2021 07:07:03 - INFO - __main__ - Step 98952: {'lr': 0.0001329659605234303, 'samples': 18998784, 'steps': 98951, 'loss/train': 1.300552248954773} 08/31/2021 07:07:03 - INFO - __main__ - Step 98953: {'lr': 0.00013296127121147894, 'samples': 18998976, 'steps': 98952, 'loss/train': 1.4193480014801025} 08/31/2021 07:07:05 - INFO - __main__ - Step 98954: {'lr': 0.0001329565819522634, 'samples': 18999168, 'steps': 98953, 'loss/train': 0.9593196511268616} 08/31/2021 07:07:05 - INFO - __main__ - Step 98955: {'lr': 0.00013295189274578585, 'samples': 18999360, 'steps': 98954, 'loss/train': 2.9699363708496094} 08/31/2021 07:07:05 - INFO - __main__ - Step 98956: {'lr': 0.00013294720359204837, 'samples': 18999552, 'steps': 98955, 'loss/train': 1.8552675247192383} 08/31/2021 07:07:06 - INFO - __main__ - Step 98957: {'lr': 0.00013294251449105305, 'samples': 18999744, 'steps': 98956, 'loss/train': 1.1270825862884521} 08/31/2021 07:07:06 - INFO - __main__ - Step 98958: {'lr': 0.00013293782544280213, 'samples': 18999936, 'steps': 98957, 'loss/train': 1.182310938835144} 08/31/2021 07:07:06 - INFO - __main__ - Step 98959: {'lr': 0.00013293313644729753, 'samples': 19000128, 'steps': 98958, 'loss/train': 0.9414702653884888} 08/31/2021 07:07:08 - INFO - __main__ - Step 98960: {'lr': 0.00013292844750454144, 'samples': 19000320, 'steps': 98959, 'loss/train': 0.8025766015052795} 08/31/2021 07:07:08 - INFO - __main__ - Step 98961: {'lr': 0.00013292375861453598, 'samples': 19000512, 'steps': 98960, 'loss/train': 1.1245203018188477} 08/31/2021 07:07:09 - INFO - __main__ - Step 98962: {'lr': 0.0001329190697772833, 'samples': 19000704, 'steps': 98961, 'loss/train': 1.6862096786499023} 08/31/2021 07:07:09 - INFO - __main__ - Step 98963: {'lr': 0.00013291438099278548, 'samples': 19000896, 'steps': 98962, 'loss/train': 0.507331132888794} 08/31/2021 07:07:09 - INFO - __main__ - Step 98964: {'lr': 0.00013290969226104461, 'samples': 19001088, 'steps': 98963, 'loss/train': 1.6491492986679077} 08/31/2021 07:07:11 - INFO - __main__ - Step 98965: {'lr': 0.00013290500358206282, 'samples': 19001280, 'steps': 98964, 'loss/train': 1.196678638458252} 08/31/2021 07:07:11 - INFO - __main__ - Step 98966: {'lr': 0.00013290031495584225, 'samples': 19001472, 'steps': 98965, 'loss/train': 1.0704562664031982} 08/31/2021 07:07:12 - INFO - __main__ - Step 98967: {'lr': 0.000132895626382385, 'samples': 19001664, 'steps': 98966, 'loss/train': 1.0832104682922363} 08/31/2021 07:07:12 - INFO - __main__ - Step 98968: {'lr': 0.00013289093786169316, 'samples': 19001856, 'steps': 98967, 'loss/train': 1.17779541015625} 08/31/2021 07:07:13 - INFO - __main__ - Step 98969: {'lr': 0.00013288624939376882, 'samples': 19002048, 'steps': 98968, 'loss/train': 0.9515359997749329} 08/31/2021 07:07:14 - INFO - __main__ - Step 98970: {'lr': 0.00013288156097861415, 'samples': 19002240, 'steps': 98969, 'loss/train': 1.1054896116256714} 08/31/2021 07:07:15 - INFO - __main__ - Step 98971: {'lr': 0.00013287687261623126, 'samples': 19002432, 'steps': 98970, 'loss/train': 1.394749402999878} 08/31/2021 07:07:15 - INFO - __main__ - Step 98972: {'lr': 0.00013287218430662234, 'samples': 19002624, 'steps': 98971, 'loss/train': 0.36257457733154297} 08/31/2021 07:07:16 - INFO - __main__ - Step 98973: {'lr': 0.00013286749604978933, 'samples': 19002816, 'steps': 98972, 'loss/train': 1.1069178581237793} 08/31/2021 07:07:16 - INFO - __main__ - Step 98974: {'lr': 0.00013286280784573435, 'samples': 19003008, 'steps': 98973, 'loss/train': 1.1489604711532593} 08/31/2021 07:07:18 - INFO - __main__ - Step 98975: {'lr': 0.00013285811969445966, 'samples': 19003200, 'steps': 98974, 'loss/train': 1.21534264087677} 08/31/2021 07:07:18 - INFO - __main__ - Step 98976: {'lr': 0.00013285343159596724, 'samples': 19003392, 'steps': 98975, 'loss/train': 1.5529181957244873} 08/31/2021 07:07:18 - INFO - __main__ - Step 98977: {'lr': 0.00013284874355025929, 'samples': 19003584, 'steps': 98976, 'loss/train': 1.2921463251113892} 08/31/2021 07:07:19 - INFO - __main__ - Step 98978: {'lr': 0.00013284405555733785, 'samples': 19003776, 'steps': 98977, 'loss/train': 1.3905950784683228} 08/31/2021 07:07:19 - INFO - __main__ - Step 98979: {'lr': 0.0001328393676172051, 'samples': 19003968, 'steps': 98978, 'loss/train': 0.6594128608703613} 08/31/2021 07:07:20 - INFO - __main__ - Step 98980: {'lr': 0.0001328346797298631, 'samples': 19004160, 'steps': 98979, 'loss/train': 1.0215569734573364} 08/31/2021 07:07:21 - INFO - __main__ - Step 98981: {'lr': 0.000132829991895314, 'samples': 19004352, 'steps': 98980, 'loss/train': 1.9259480237960815} 08/31/2021 07:07:22 - INFO - __main__ - Step 98982: {'lr': 0.0001328253041135599, 'samples': 19004544, 'steps': 98981, 'loss/train': 1.0197185277938843} 08/31/2021 07:07:22 - INFO - __main__ - Step 98983: {'lr': 0.0001328206163846029, 'samples': 19004736, 'steps': 98982, 'loss/train': 0.6290191411972046} 08/31/2021 07:07:22 - INFO - __main__ - Step 98984: {'lr': 0.00013281592870844513, 'samples': 19004928, 'steps': 98983, 'loss/train': 1.2856066226959229} 08/31/2021 07:07:23 - INFO - __main__ - Step 98985: {'lr': 0.0001328112410850888, 'samples': 19005120, 'steps': 98984, 'loss/train': 0.4978942573070526} 08/31/2021 07:07:24 - INFO - __main__ - Step 98986: {'lr': 0.0001328065535145358, 'samples': 19005312, 'steps': 98985, 'loss/train': 1.1591300964355469} 08/31/2021 07:07:25 - INFO - __main__ - Step 98987: {'lr': 0.00013280186599678838, 'samples': 19005504, 'steps': 98986, 'loss/train': 1.3982030153274536} 08/31/2021 07:07:25 - INFO - __main__ - Step 98988: {'lr': 0.0001327971785318486, 'samples': 19005696, 'steps': 98987, 'loss/train': 1.1953643560409546} 08/31/2021 07:07:25 - INFO - __main__ - Step 98989: {'lr': 0.00013279249111971864, 'samples': 19005888, 'steps': 98988, 'loss/train': 0.4888012409210205} 08/31/2021 07:07:26 - INFO - __main__ - Step 98990: {'lr': 0.00013278780376040056, 'samples': 19006080, 'steps': 98989, 'loss/train': 1.4845209121704102} 08/31/2021 07:07:27 - INFO - __main__ - Step 98991: {'lr': 0.00013278311645389645, 'samples': 19006272, 'steps': 98990, 'loss/train': 1.201758623123169} 08/31/2021 07:07:28 - INFO - __main__ - Step 98992: {'lr': 0.00013277842920020853, 'samples': 19006464, 'steps': 98991, 'loss/train': 1.4685313701629639} 08/31/2021 07:07:28 - INFO - __main__ - Step 98993: {'lr': 0.00013277374199933877, 'samples': 19006656, 'steps': 98992, 'loss/train': 0.8829256296157837} 08/31/2021 07:07:29 - INFO - __main__ - Step 98994: {'lr': 0.00013276905485128942, 'samples': 19006848, 'steps': 98993, 'loss/train': 1.2979415655136108} 08/31/2021 07:07:29 - INFO - __main__ - Step 98995: {'lr': 0.00013276436775606248, 'samples': 19007040, 'steps': 98994, 'loss/train': 1.474064588546753} 08/31/2021 07:07:31 - INFO - __main__ - Step 98996: {'lr': 0.00013275968071366012, 'samples': 19007232, 'steps': 98995, 'loss/train': 1.6449906826019287} 08/31/2021 07:07:31 - INFO - __main__ - Step 98997: {'lr': 0.00013275499372408445, 'samples': 19007424, 'steps': 98996, 'loss/train': 1.7669854164123535} 08/31/2021 07:07:32 - INFO - __main__ - Step 98998: {'lr': 0.00013275030678733753, 'samples': 19007616, 'steps': 98997, 'loss/train': 1.0954813957214355} 08/31/2021 07:07:32 - INFO - __main__ - Step 98999: {'lr': 0.00013274561990342165, 'samples': 19007808, 'steps': 98998, 'loss/train': 0.9737954139709473} 08/31/2021 07:07:32 - INFO - __main__ - Step 99000: {'lr': 0.00013274093307233867, 'samples': 19008000, 'steps': 98999, 'loss/train': 1.3408088684082031} 08/31/2021 07:07:33 - INFO - __main__ - Step 99001: {'lr': 0.0001327362462940908, 'samples': 19008192, 'steps': 99000, 'loss/train': 1.1867133378982544} 08/31/2021 07:07:33 - INFO - __main__ - Step 99002: {'lr': 0.0001327315595686802, 'samples': 19008384, 'steps': 99001, 'loss/train': 0.042121995240449905} 08/31/2021 07:07:35 - INFO - __main__ - Step 99003: {'lr': 0.00013272687289610897, 'samples': 19008576, 'steps': 99002, 'loss/train': 2.1389620304107666} 08/31/2021 07:07:35 - INFO - __main__ - Step 99004: {'lr': 0.00013272218627637916, 'samples': 19008768, 'steps': 99003, 'loss/train': 1.3614702224731445} 08/31/2021 07:07:35 - INFO - __main__ - Step 99005: {'lr': 0.00013271749970949294, 'samples': 19008960, 'steps': 99004, 'loss/train': 1.058853268623352} 08/31/2021 07:07:36 - INFO - __main__ - Step 99006: {'lr': 0.00013271281319545235, 'samples': 19009152, 'steps': 99005, 'loss/train': 0.335468590259552} 08/31/2021 07:07:36 - INFO - __main__ - Step 99007: {'lr': 0.00013270812673425963, 'samples': 19009344, 'steps': 99006, 'loss/train': 0.8177433609962463} 08/31/2021 07:07:36 - INFO - __main__ - Step 99008: {'lr': 0.0001327034403259168, 'samples': 19009536, 'steps': 99007, 'loss/train': 1.4002116918563843} 08/31/2021 07:07:38 - INFO - __main__ - Step 99009: {'lr': 0.00013269875397042596, 'samples': 19009728, 'steps': 99008, 'loss/train': 1.4777487516403198} 08/31/2021 07:07:38 - INFO - __main__ - Step 99010: {'lr': 0.0001326940676677893, 'samples': 19009920, 'steps': 99009, 'loss/train': 0.8528442978858948} 08/31/2021 07:07:39 - INFO - __main__ - Step 99011: {'lr': 0.00013268938141800885, 'samples': 19010112, 'steps': 99010, 'loss/train': 1.5257247686386108} 08/31/2021 07:07:39 - INFO - __main__ - Step 99012: {'lr': 0.00013268469522108685, 'samples': 19010304, 'steps': 99011, 'loss/train': 2.2001821994781494} 08/31/2021 07:07:39 - INFO - __main__ - Step 99013: {'lr': 0.00013268000907702525, 'samples': 19010496, 'steps': 99012, 'loss/train': 1.1379238367080688} 08/31/2021 07:07:42 - INFO - __main__ - Step 99014: {'lr': 0.0001326753229858262, 'samples': 19010688, 'steps': 99013, 'loss/train': 0.3368343114852905} 08/31/2021 07:07:43 - INFO - __main__ - Step 99015: {'lr': 0.0001326706369474918, 'samples': 19010880, 'steps': 99014, 'loss/train': 0.7784285545349121} 08/31/2021 07:07:43 - INFO - __main__ - Step 99016: {'lr': 0.0001326659509620243, 'samples': 19011072, 'steps': 99015, 'loss/train': 0.8499690294265747} 08/31/2021 07:07:43 - INFO - __main__ - Step 99017: {'lr': 0.00013266126502942563, 'samples': 19011264, 'steps': 99016, 'loss/train': 0.7375344038009644} 08/31/2021 07:07:44 - INFO - __main__ - Step 99018: {'lr': 0.00013265657914969802, 'samples': 19011456, 'steps': 99017, 'loss/train': 0.650026261806488} 08/31/2021 07:07:44 - INFO - __main__ - Step 99019: {'lr': 0.00013265189332284353, 'samples': 19011648, 'steps': 99018, 'loss/train': 1.0050495862960815} 08/31/2021 07:07:44 - INFO - __main__ - Step 99020: {'lr': 0.00013264720754886428, 'samples': 19011840, 'steps': 99019, 'loss/train': 0.6890770792961121} 08/31/2021 07:07:45 - INFO - __main__ - Step 99021: {'lr': 0.0001326425218277624, 'samples': 19012032, 'steps': 99020, 'loss/train': 1.148639440536499} 08/31/2021 07:07:46 - INFO - __main__ - Step 99022: {'lr': 0.00013263783615954, 'samples': 19012224, 'steps': 99021, 'loss/train': 1.6758129596710205} 08/31/2021 07:07:47 - INFO - __main__ - Step 99023: {'lr': 0.00013263315054419918, 'samples': 19012416, 'steps': 99022, 'loss/train': 0.7371653914451599} 08/31/2021 07:07:47 - INFO - __main__ - Step 99024: {'lr': 0.00013262846498174203, 'samples': 19012608, 'steps': 99023, 'loss/train': 0.7385165691375732} 08/31/2021 07:07:48 - INFO - __main__ - Step 99025: {'lr': 0.00013262377947217068, 'samples': 19012800, 'steps': 99024, 'loss/train': 1.4450067281723022} 08/31/2021 07:07:48 - INFO - __main__ - Step 99026: {'lr': 0.00013261909401548737, 'samples': 19012992, 'steps': 99025, 'loss/train': 1.241576910018921} 08/31/2021 07:07:50 - INFO - __main__ - Step 99027: {'lr': 0.00013261440861169393, 'samples': 19013184, 'steps': 99026, 'loss/train': 1.001333236694336} 08/31/2021 07:07:50 - INFO - __main__ - Step 99028: {'lr': 0.00013260972326079268, 'samples': 19013376, 'steps': 99027, 'loss/train': 1.5589609146118164} 08/31/2021 07:07:51 - INFO - __main__ - Step 99029: {'lr': 0.00013260503796278566, 'samples': 19013568, 'steps': 99028, 'loss/train': 0.025956284254789352} 08/31/2021 07:07:51 - INFO - __main__ - Step 99030: {'lr': 0.000132600352717675, 'samples': 19013760, 'steps': 99029, 'loss/train': 0.7750658988952637} 08/31/2021 07:07:52 - INFO - __main__ - Step 99031: {'lr': 0.0001325956675254628, 'samples': 19013952, 'steps': 99030, 'loss/train': 1.2861328125} 08/31/2021 07:07:53 - INFO - __main__ - Step 99032: {'lr': 0.0001325909823861512, 'samples': 19014144, 'steps': 99031, 'loss/train': 0.32887184619903564} 08/31/2021 07:07:54 - INFO - __main__ - Step 99033: {'lr': 0.0001325862972997423, 'samples': 19014336, 'steps': 99032, 'loss/train': 1.3786472082138062} 08/31/2021 07:07:54 - INFO - __main__ - Step 99034: {'lr': 0.00013258161226623817, 'samples': 19014528, 'steps': 99033, 'loss/train': 1.2088876962661743} 08/31/2021 07:07:54 - INFO - __main__ - Step 99035: {'lr': 0.00013257692728564096, 'samples': 19014720, 'steps': 99034, 'loss/train': 1.3534603118896484} 08/31/2021 07:07:55 - INFO - __main__ - Step 99036: {'lr': 0.0001325722423579528, 'samples': 19014912, 'steps': 99035, 'loss/train': 1.0865557193756104} 08/31/2021 07:07:56 - INFO - __main__ - Step 99037: {'lr': 0.00013256755748317575, 'samples': 19015104, 'steps': 99036, 'loss/train': 1.281903862953186} 08/31/2021 07:07:56 - INFO - __main__ - Step 99038: {'lr': 0.00013256287266131194, 'samples': 19015296, 'steps': 99037, 'loss/train': 1.4301044940948486} 08/31/2021 07:07:57 - INFO - __main__ - Step 99039: {'lr': 0.00013255818789236363, 'samples': 19015488, 'steps': 99038, 'loss/train': 1.2523196935653687} 08/31/2021 07:07:57 - INFO - __main__ - Step 99040: {'lr': 0.00013255350317633265, 'samples': 19015680, 'steps': 99039, 'loss/train': 1.3401750326156616} 08/31/2021 07:07:57 - INFO - __main__ - Step 99041: {'lr': 0.00013254881851322125, 'samples': 19015872, 'steps': 99040, 'loss/train': 1.050942063331604} 08/31/2021 07:07:59 - INFO - __main__ - Step 99042: {'lr': 0.00013254413390303155, 'samples': 19016064, 'steps': 99041, 'loss/train': 0.9614322185516357} 08/31/2021 07:08:00 - INFO - __main__ - Step 99043: {'lr': 0.00013253944934576566, 'samples': 19016256, 'steps': 99042, 'loss/train': 1.0345629453659058} 08/31/2021 07:08:00 - INFO - __main__ - Step 99044: {'lr': 0.00013253476484142567, 'samples': 19016448, 'steps': 99043, 'loss/train': 0.8537014722824097} 08/31/2021 07:08:01 - INFO - __main__ - Step 99045: {'lr': 0.00013253008039001372, 'samples': 19016640, 'steps': 99044, 'loss/train': 1.4908521175384521} 08/31/2021 07:08:01 - INFO - __main__ - Step 99046: {'lr': 0.00013252539599153187, 'samples': 19016832, 'steps': 99045, 'loss/train': 0.026215676218271255} 08/31/2021 07:08:01 - INFO - __main__ - Step 99047: {'lr': 0.00013252071164598228, 'samples': 19017024, 'steps': 99046, 'loss/train': 1.3221784830093384} 08/31/2021 07:08:03 - INFO - __main__ - Step 99048: {'lr': 0.00013251602735336705, 'samples': 19017216, 'steps': 99047, 'loss/train': 0.6725783348083496} 08/31/2021 07:08:03 - INFO - __main__ - Step 99049: {'lr': 0.0001325113431136883, 'samples': 19017408, 'steps': 99048, 'loss/train': 1.2461943626403809} 08/31/2021 07:08:04 - INFO - __main__ - Step 99050: {'lr': 0.00013250665892694812, 'samples': 19017600, 'steps': 99049, 'loss/train': 1.3558965921401978} 08/31/2021 07:08:04 - INFO - __main__ - Step 99051: {'lr': 0.00013250197479314858, 'samples': 19017792, 'steps': 99050, 'loss/train': 1.056509256362915} 08/31/2021 07:08:04 - INFO - __main__ - Step 99052: {'lr': 0.0001324972907122919, 'samples': 19017984, 'steps': 99051, 'loss/train': 0.9174265265464783} 08/31/2021 07:08:06 - INFO - __main__ - Step 99053: {'lr': 0.00013249260668438017, 'samples': 19018176, 'steps': 99052, 'loss/train': 1.5122127532958984} 08/31/2021 07:08:06 - INFO - __main__ - Step 99054: {'lr': 0.0001324879227094154, 'samples': 19018368, 'steps': 99053, 'loss/train': 0.9678950905799866} 08/31/2021 07:08:07 - INFO - __main__ - Step 99055: {'lr': 0.00013248323878739974, 'samples': 19018560, 'steps': 99054, 'loss/train': 1.000740647315979} 08/31/2021 07:08:07 - INFO - __main__ - Step 99056: {'lr': 0.00013247855491833532, 'samples': 19018752, 'steps': 99055, 'loss/train': 1.4197388887405396} 08/31/2021 07:08:07 - INFO - __main__ - Step 99057: {'lr': 0.00013247387110222427, 'samples': 19018944, 'steps': 99056, 'loss/train': 1.3970787525177002} 08/31/2021 07:08:09 - INFO - __main__ - Step 99058: {'lr': 0.00013246918733906865, 'samples': 19019136, 'steps': 99057, 'loss/train': 0.9946750998497009} 08/31/2021 07:08:09 - INFO - __main__ - Step 99059: {'lr': 0.00013246450362887065, 'samples': 19019328, 'steps': 99058, 'loss/train': 0.6367583274841309} 08/31/2021 07:08:09 - INFO - __main__ - Step 99060: {'lr': 0.00013245981997163226, 'samples': 19019520, 'steps': 99059, 'loss/train': 0.85209721326828} 08/31/2021 07:08:10 - INFO - __main__ - Step 99061: {'lr': 0.0001324551363673557, 'samples': 19019712, 'steps': 99060, 'loss/train': 1.1158865690231323} 08/31/2021 07:08:10 - INFO - __main__ - Step 99062: {'lr': 0.00013245045281604304, 'samples': 19019904, 'steps': 99061, 'loss/train': 1.3625757694244385} 08/31/2021 07:08:12 - INFO - __main__ - Step 99063: {'lr': 0.0001324457693176964, 'samples': 19020096, 'steps': 99062, 'loss/train': 0.994879424571991} 08/31/2021 07:08:12 - INFO - __main__ - Step 99064: {'lr': 0.00013244108587231784, 'samples': 19020288, 'steps': 99063, 'loss/train': 0.774165153503418} 08/31/2021 07:08:13 - INFO - __main__ - Step 99065: {'lr': 0.00013243640247990958, 'samples': 19020480, 'steps': 99064, 'loss/train': 1.3900823593139648} 08/31/2021 07:08:13 - INFO - __main__ - Step 99066: {'lr': 0.00013243171914047373, 'samples': 19020672, 'steps': 99065, 'loss/train': 0.6101256608963013} 08/31/2021 07:08:13 - INFO - __main__ - Step 99067: {'lr': 0.00013242703585401223, 'samples': 19020864, 'steps': 99066, 'loss/train': 1.7043410539627075} 08/31/2021 07:08:15 - INFO - __main__ - Step 99068: {'lr': 0.0001324223526205273, 'samples': 19021056, 'steps': 99067, 'loss/train': 1.1222351789474487} 08/31/2021 07:08:16 - INFO - __main__ - Step 99069: {'lr': 0.00013241766944002104, 'samples': 19021248, 'steps': 99068, 'loss/train': 1.0254411697387695} 08/31/2021 07:08:16 - INFO - __main__ - Step 99070: {'lr': 0.00013241298631249554, 'samples': 19021440, 'steps': 99069, 'loss/train': 1.1208770275115967} 08/31/2021 07:08:16 - INFO - __main__ - Step 99071: {'lr': 0.00013240830323795296, 'samples': 19021632, 'steps': 99070, 'loss/train': 1.594979166984558} 08/31/2021 07:08:17 - INFO - __main__ - Step 99072: {'lr': 0.0001324036202163954, 'samples': 19021824, 'steps': 99071, 'loss/train': 0.016494179144501686} 08/31/2021 07:08:17 - INFO - __main__ - Step 99073: {'lr': 0.0001323989372478249, 'samples': 19022016, 'steps': 99072, 'loss/train': 1.01035737991333} 08/31/2021 07:08:19 - INFO - __main__ - Step 99074: {'lr': 0.00013239425433224367, 'samples': 19022208, 'steps': 99073, 'loss/train': 1.1886639595031738} 08/31/2021 07:08:19 - INFO - __main__ - Step 99075: {'lr': 0.00013238957146965378, 'samples': 19022400, 'steps': 99074, 'loss/train': 1.3736799955368042} 08/31/2021 07:08:19 - INFO - __main__ - Step 99076: {'lr': 0.00013238488866005734, 'samples': 19022592, 'steps': 99075, 'loss/train': 0.9506051540374756} 08/31/2021 07:08:20 - INFO - __main__ - Step 99077: {'lr': 0.0001323802059034564, 'samples': 19022784, 'steps': 99076, 'loss/train': 0.7376305460929871} 08/31/2021 07:08:20 - INFO - __main__ - Step 99078: {'lr': 0.00013237552319985316, 'samples': 19022976, 'steps': 99077, 'loss/train': 1.1242468357086182} 08/31/2021 07:08:20 - INFO - __main__ - Step 99079: {'lr': 0.0001323708405492498, 'samples': 19023168, 'steps': 99078, 'loss/train': 1.069548487663269} 08/31/2021 07:08:23 - INFO - __main__ - Step 99080: {'lr': 0.00013236615795164818, 'samples': 19023360, 'steps': 99079, 'loss/train': 1.1348838806152344} 08/31/2021 07:08:23 - INFO - __main__ - Step 99081: {'lr': 0.00013236147540705062, 'samples': 19023552, 'steps': 99080, 'loss/train': 0.3952120542526245} 08/31/2021 07:08:23 - INFO - __main__ - Step 99082: {'lr': 0.00013235679291545913, 'samples': 19023744, 'steps': 99081, 'loss/train': 1.6920651197433472} 08/31/2021 07:08:24 - INFO - __main__ - Step 99083: {'lr': 0.00013235211047687585, 'samples': 19023936, 'steps': 99082, 'loss/train': 1.5684672594070435} 08/31/2021 07:08:24 - INFO - __main__ - Step 99084: {'lr': 0.0001323474280913029, 'samples': 19024128, 'steps': 99083, 'loss/train': 5.146883487701416} 08/31/2021 07:08:26 - INFO - __main__ - Step 99085: {'lr': 0.00013234274575874239, 'samples': 19024320, 'steps': 99084, 'loss/train': 1.1795341968536377} 08/31/2021 07:08:26 - INFO - __main__ - Step 99086: {'lr': 0.00013233806347919642, 'samples': 19024512, 'steps': 99085, 'loss/train': 0.5859531164169312} 08/31/2021 07:08:26 - INFO - __main__ - Step 99087: {'lr': 0.00013233338125266707, 'samples': 19024704, 'steps': 99086, 'loss/train': 1.0165234804153442} 08/31/2021 07:08:27 - INFO - __main__ - Step 99088: {'lr': 0.0001323286990791565, 'samples': 19024896, 'steps': 99087, 'loss/train': 1.299514651298523} 08/31/2021 07:08:27 - INFO - __main__ - Step 99089: {'lr': 0.00013232401695866685, 'samples': 19025088, 'steps': 99088, 'loss/train': 1.26094651222229} 08/31/2021 07:08:29 - INFO - __main__ - Step 99090: {'lr': 0.00013231933489120013, 'samples': 19025280, 'steps': 99089, 'loss/train': 1.6035274267196655} 08/31/2021 07:08:29 - INFO - __main__ - Step 99091: {'lr': 0.00013231465287675854, 'samples': 19025472, 'steps': 99090, 'loss/train': 1.029578447341919} 08/31/2021 07:08:29 - INFO - __main__ - Step 99092: {'lr': 0.00013230997091534413, 'samples': 19025664, 'steps': 99091, 'loss/train': 0.5540829300880432} 08/31/2021 07:08:30 - INFO - __main__ - Step 99093: {'lr': 0.0001323052890069591, 'samples': 19025856, 'steps': 99092, 'loss/train': 1.0646048784255981} 08/31/2021 07:08:30 - INFO - __main__ - Step 99094: {'lr': 0.00013230060715160543, 'samples': 19026048, 'steps': 99093, 'loss/train': 1.0428569316864014} 08/31/2021 07:08:30 - INFO - __main__ - Step 99095: {'lr': 0.0001322959253492853, 'samples': 19026240, 'steps': 99094, 'loss/train': 1.0099499225616455} 08/31/2021 07:08:32 - INFO - __main__ - Step 99096: {'lr': 0.00013229124360000078, 'samples': 19026432, 'steps': 99095, 'loss/train': 1.1163055896759033} 08/31/2021 07:08:32 - INFO - __main__ - Step 99097: {'lr': 0.00013228656190375404, 'samples': 19026624, 'steps': 99096, 'loss/train': 0.8562244772911072} 08/31/2021 07:08:33 - INFO - __main__ - Step 99098: {'lr': 0.00013228188026054711, 'samples': 19026816, 'steps': 99097, 'loss/train': 0.16118714213371277} 08/31/2021 07:08:33 - INFO - __main__ - Step 99099: {'lr': 0.00013227719867038218, 'samples': 19027008, 'steps': 99098, 'loss/train': 1.3255246877670288} 08/31/2021 07:08:33 - INFO - __main__ - Step 99100: {'lr': 0.00013227251713326133, 'samples': 19027200, 'steps': 99099, 'loss/train': 1.2468825578689575} 08/31/2021 07:08:35 - INFO - __main__ - Step 99101: {'lr': 0.00013226783564918666, 'samples': 19027392, 'steps': 99100, 'loss/train': 0.9836601614952087} 08/31/2021 07:08:36 - INFO - __main__ - Step 99102: {'lr': 0.0001322631542181603, 'samples': 19027584, 'steps': 99101, 'loss/train': 1.0963410139083862} 08/31/2021 07:08:36 - INFO - __main__ - Step 99103: {'lr': 0.00013225847284018433, 'samples': 19027776, 'steps': 99102, 'loss/train': 0.8287703394889832} 08/31/2021 07:08:37 - INFO - __main__ - Step 99104: {'lr': 0.0001322537915152609, 'samples': 19027968, 'steps': 99103, 'loss/train': 0.8394757509231567} 08/31/2021 07:08:37 - INFO - __main__ - Step 99105: {'lr': 0.00013224911024339205, 'samples': 19028160, 'steps': 99104, 'loss/train': 0.01706126518547535} 08/31/2021 07:08:37 - INFO - __main__ - Step 99106: {'lr': 0.00013224442902458005, 'samples': 19028352, 'steps': 99105, 'loss/train': 1.2147080898284912} 08/31/2021 07:08:39 - INFO - __main__ - Step 99107: {'lr': 0.00013223974785882682, 'samples': 19028544, 'steps': 99106, 'loss/train': 1.222204566001892} 08/31/2021 07:08:39 - INFO - __main__ - Step 99108: {'lr': 0.0001322350667461345, 'samples': 19028736, 'steps': 99107, 'loss/train': 0.9362818598747253} 08/31/2021 07:08:40 - INFO - __main__ - Step 99109: {'lr': 0.0001322303856865053, 'samples': 19028928, 'steps': 99108, 'loss/train': 0.17144444584846497} 08/31/2021 07:08:40 - INFO - __main__ - Step 99110: {'lr': 0.00013222570467994122, 'samples': 19029120, 'steps': 99109, 'loss/train': 1.1688522100448608} 08/31/2021 07:08:40 - INFO - __main__ - Step 99111: {'lr': 0.00013222102372644447, 'samples': 19029312, 'steps': 99110, 'loss/train': 1.3600871562957764} 08/31/2021 07:08:42 - INFO - __main__ - Step 99112: {'lr': 0.00013221634282601706, 'samples': 19029504, 'steps': 99111, 'loss/train': 0.6399683356285095} 08/31/2021 07:08:43 - INFO - __main__ - Step 99113: {'lr': 0.00013221166197866112, 'samples': 19029696, 'steps': 99112, 'loss/train': 1.37736976146698} 08/31/2021 07:08:43 - INFO - __main__ - Step 99114: {'lr': 0.00013220698118437884, 'samples': 19029888, 'steps': 99113, 'loss/train': 0.5534118413925171} 08/31/2021 07:08:44 - INFO - __main__ - Step 99115: {'lr': 0.00013220230044317229, 'samples': 19030080, 'steps': 99114, 'loss/train': 0.016178902238607407} 08/31/2021 07:08:44 - INFO - __main__ - Step 99116: {'lr': 0.00013219761975504356, 'samples': 19030272, 'steps': 99115, 'loss/train': 0.14470194280147552} 08/31/2021 07:08:44 - INFO - __main__ - Step 99117: {'lr': 0.00013219293911999474, 'samples': 19030464, 'steps': 99116, 'loss/train': 1.7837870121002197} 08/31/2021 07:08:46 - INFO - __main__ - Step 99118: {'lr': 0.00013218825853802797, 'samples': 19030656, 'steps': 99117, 'loss/train': 1.06902277469635} 08/31/2021 07:08:46 - INFO - __main__ - Step 99119: {'lr': 0.00013218357800914534, 'samples': 19030848, 'steps': 99118, 'loss/train': 1.245350956916809} 08/31/2021 07:08:47 - INFO - __main__ - Step 99120: {'lr': 0.0001321788975333491, 'samples': 19031040, 'steps': 99119, 'loss/train': 0.3980371356010437} 08/31/2021 07:08:47 - INFO - __main__ - Step 99121: {'lr': 0.0001321742171106411, 'samples': 19031232, 'steps': 99120, 'loss/train': 0.8677605986595154} 08/31/2021 07:08:47 - INFO - __main__ - Step 99122: {'lr': 0.0001321695367410236, 'samples': 19031424, 'steps': 99121, 'loss/train': 1.5355875492095947} 08/31/2021 07:08:49 - INFO - __main__ - Step 99123: {'lr': 0.00013216485642449872, 'samples': 19031616, 'steps': 99122, 'loss/train': 1.1335093975067139} 08/31/2021 07:08:49 - INFO - __main__ - Step 99124: {'lr': 0.0001321601761610685, 'samples': 19031808, 'steps': 99123, 'loss/train': 1.384162187576294} 08/31/2021 07:08:50 - INFO - __main__ - Step 99125: {'lr': 0.00013215549595073505, 'samples': 19032000, 'steps': 99124, 'loss/train': 1.4014360904693604} 08/31/2021 07:08:50 - INFO - __main__ - Step 99126: {'lr': 0.00013215081579350058, 'samples': 19032192, 'steps': 99125, 'loss/train': 1.0882052183151245} 08/31/2021 07:08:50 - INFO - __main__ - Step 99127: {'lr': 0.0001321461356893671, 'samples': 19032384, 'steps': 99126, 'loss/train': 1.2676037549972534} 08/31/2021 07:08:51 - INFO - __main__ - Step 99128: {'lr': 0.0001321414556383368, 'samples': 19032576, 'steps': 99127, 'loss/train': 1.6432504653930664} 08/31/2021 07:08:52 - INFO - __main__ - Step 99129: {'lr': 0.0001321367756404117, 'samples': 19032768, 'steps': 99128, 'loss/train': 0.8878993391990662} 08/31/2021 07:08:53 - INFO - __main__ - Step 99130: {'lr': 0.00013213209569559392, 'samples': 19032960, 'steps': 99129, 'loss/train': 1.045379400253296} 08/31/2021 07:08:53 - INFO - __main__ - Step 99131: {'lr': 0.00013212741580388566, 'samples': 19033152, 'steps': 99130, 'loss/train': 1.4208850860595703} 08/31/2021 07:08:53 - INFO - __main__ - Step 99132: {'lr': 0.00013212273596528894, 'samples': 19033344, 'steps': 99131, 'loss/train': 1.389335036277771} 08/31/2021 07:08:54 - INFO - __main__ - Step 99133: {'lr': 0.00013211805617980598, 'samples': 19033536, 'steps': 99132, 'loss/train': 0.968667209148407} 08/31/2021 07:08:56 - INFO - __main__ - Step 99134: {'lr': 0.0001321133764474387, 'samples': 19033728, 'steps': 99133, 'loss/train': 1.3021321296691895} 08/31/2021 07:08:56 - INFO - __main__ - Step 99135: {'lr': 0.00013210869676818935, 'samples': 19033920, 'steps': 99134, 'loss/train': 1.5939249992370605} 08/31/2021 07:08:57 - INFO - __main__ - Step 99136: {'lr': 0.00013210401714205998, 'samples': 19034112, 'steps': 99135, 'loss/train': 1.4554932117462158} 08/31/2021 07:08:57 - INFO - __main__ - Step 99137: {'lr': 0.00013209933756905273, 'samples': 19034304, 'steps': 99136, 'loss/train': 0.8588480353355408} 08/31/2021 07:08:57 - INFO - __main__ - Step 99138: {'lr': 0.0001320946580491697, 'samples': 19034496, 'steps': 99137, 'loss/train': 1.5657925605773926} 08/31/2021 07:08:59 - INFO - __main__ - Step 99139: {'lr': 0.000132089978582413, 'samples': 19034688, 'steps': 99138, 'loss/train': 0.8182023167610168} 08/31/2021 07:09:00 - INFO - __main__ - Step 99140: {'lr': 0.00013208529916878474, 'samples': 19034880, 'steps': 99139, 'loss/train': 0.7543695569038391} 08/31/2021 07:09:00 - INFO - __main__ - Step 99141: {'lr': 0.000132080619808287, 'samples': 19035072, 'steps': 99140, 'loss/train': 0.9747579097747803} 08/31/2021 07:09:01 - INFO - __main__ - Step 99142: {'lr': 0.00013207594050092193, 'samples': 19035264, 'steps': 99141, 'loss/train': 0.9509510397911072} 08/31/2021 07:09:01 - INFO - __main__ - Step 99143: {'lr': 0.00013207126124669161, 'samples': 19035456, 'steps': 99142, 'loss/train': 0.8542981743812561} 08/31/2021 07:09:02 - INFO - __main__ - Step 99144: {'lr': 0.00013206658204559818, 'samples': 19035648, 'steps': 99143, 'loss/train': 0.48714199662208557} 08/31/2021 07:09:03 - INFO - __main__ - Step 99145: {'lr': 0.0001320619028976437, 'samples': 19035840, 'steps': 99144, 'loss/train': 1.4559147357940674} 08/31/2021 07:09:03 - INFO - __main__ - Step 99146: {'lr': 0.00013205722380283034, 'samples': 19036032, 'steps': 99145, 'loss/train': 1.4433492422103882} 08/31/2021 07:09:03 - INFO - __main__ - Step 99147: {'lr': 0.00013205254476116024, 'samples': 19036224, 'steps': 99146, 'loss/train': 0.21481503546237946} 08/31/2021 07:09:04 - INFO - __main__ - Step 99148: {'lr': 0.00013204786577263538, 'samples': 19036416, 'steps': 99147, 'loss/train': 0.9785574078559875} 08/31/2021 07:09:05 - INFO - __main__ - Step 99149: {'lr': 0.00013204318683725791, 'samples': 19036608, 'steps': 99148, 'loss/train': 0.8471981883049011} 08/31/2021 07:09:06 - INFO - __main__ - Step 99150: {'lr': 0.00013203850795502997, 'samples': 19036800, 'steps': 99149, 'loss/train': 1.305340051651001} 08/31/2021 07:09:06 - INFO - __main__ - Step 99151: {'lr': 0.00013203382912595362, 'samples': 19036992, 'steps': 99150, 'loss/train': 1.5203044414520264} 08/31/2021 07:09:06 - INFO - __main__ - Step 99152: {'lr': 0.00013202915035003104, 'samples': 19037184, 'steps': 99151, 'loss/train': 0.9061627388000488} 08/31/2021 07:09:07 - INFO - __main__ - Step 99153: {'lr': 0.00013202447162726432, 'samples': 19037376, 'steps': 99152, 'loss/train': 0.7811323404312134} 08/31/2021 07:09:08 - INFO - __main__ - Step 99154: {'lr': 0.00013201979295765555, 'samples': 19037568, 'steps': 99153, 'loss/train': 1.5543279647827148} 08/31/2021 07:09:09 - INFO - __main__ - Step 99155: {'lr': 0.00013201511434120683, 'samples': 19037760, 'steps': 99154, 'loss/train': 1.132110834121704} 08/31/2021 07:09:09 - INFO - __main__ - Step 99156: {'lr': 0.00013201043577792026, 'samples': 19037952, 'steps': 99155, 'loss/train': 1.3000235557556152} 08/31/2021 07:09:09 - INFO - __main__ - Step 99157: {'lr': 0.00013200575726779798, 'samples': 19038144, 'steps': 99156, 'loss/train': 0.6155915856361389} 08/31/2021 07:09:10 - INFO - __main__ - Step 99158: {'lr': 0.0001320010788108421, 'samples': 19038336, 'steps': 99157, 'loss/train': 0.9919824004173279} 08/31/2021 07:09:11 - INFO - __main__ - Step 99159: {'lr': 0.00013199640040705468, 'samples': 19038528, 'steps': 99158, 'loss/train': 1.9871164560317993} 08/31/2021 07:09:12 - INFO - __main__ - Step 99160: {'lr': 0.000131991722056438, 'samples': 19038720, 'steps': 99159, 'loss/train': 1.0688954591751099} 08/31/2021 07:09:12 - INFO - __main__ - Step 99161: {'lr': 0.0001319870437589939, 'samples': 19038912, 'steps': 99160, 'loss/train': 1.0269453525543213} 08/31/2021 07:09:13 - INFO - __main__ - Step 99162: {'lr': 0.00013198236551472463, 'samples': 19039104, 'steps': 99161, 'loss/train': 1.1117641925811768} 08/31/2021 07:09:13 - INFO - __main__ - Step 99163: {'lr': 0.0001319776873236323, 'samples': 19039296, 'steps': 99162, 'loss/train': 0.43845298886299133} 08/31/2021 07:09:15 - INFO - __main__ - Step 99164: {'lr': 0.00013197300918571896, 'samples': 19039488, 'steps': 99163, 'loss/train': 1.5052787065505981} 08/31/2021 07:09:15 - INFO - __main__ - Step 99165: {'lr': 0.00013196833110098676, 'samples': 19039680, 'steps': 99164, 'loss/train': 1.0236634016036987} 08/31/2021 07:09:15 - INFO - __main__ - Step 99166: {'lr': 0.00013196365306943785, 'samples': 19039872, 'steps': 99165, 'loss/train': 0.5988667607307434} 08/31/2021 07:09:16 - INFO - __main__ - Step 99167: {'lr': 0.0001319589750910743, 'samples': 19040064, 'steps': 99166, 'loss/train': 0.46316421031951904} 08/31/2021 07:09:16 - INFO - __main__ - Step 99168: {'lr': 0.0001319542971658982, 'samples': 19040256, 'steps': 99167, 'loss/train': 0.8605539202690125} 08/31/2021 07:09:18 - INFO - __main__ - Step 99169: {'lr': 0.00013194961929391166, 'samples': 19040448, 'steps': 99168, 'loss/train': 1.7704304456710815} 08/31/2021 07:09:18 - INFO - __main__ - Step 99170: {'lr': 0.00013194494147511683, 'samples': 19040640, 'steps': 99169, 'loss/train': 0.0723864957690239} 08/31/2021 07:09:18 - INFO - __main__ - Step 99171: {'lr': 0.00013194026370951572, 'samples': 19040832, 'steps': 99170, 'loss/train': 1.8142942190170288} 08/31/2021 07:09:19 - INFO - __main__ - Step 99172: {'lr': 0.00013193558599711066, 'samples': 19041024, 'steps': 99171, 'loss/train': 1.085079550743103} 08/31/2021 07:09:19 - INFO - __main__ - Step 99173: {'lr': 0.0001319309083379035, 'samples': 19041216, 'steps': 99172, 'loss/train': 1.1688774824142456} 08/31/2021 07:09:19 - INFO - __main__ - Step 99174: {'lr': 0.00013192623073189644, 'samples': 19041408, 'steps': 99173, 'loss/train': 1.6215767860412598} 08/31/2021 07:09:21 - INFO - __main__ - Step 99175: {'lr': 0.0001319215531790916, 'samples': 19041600, 'steps': 99174, 'loss/train': 1.279434323310852} 08/31/2021 07:09:22 - INFO - __main__ - Step 99176: {'lr': 0.0001319168756794911, 'samples': 19041792, 'steps': 99175, 'loss/train': 1.191717267036438} 08/31/2021 07:09:22 - INFO - __main__ - Step 99177: {'lr': 0.00013191219823309702, 'samples': 19041984, 'steps': 99176, 'loss/train': 1.345211386680603} 08/31/2021 07:09:22 - INFO - __main__ - Step 99178: {'lr': 0.00013190752083991147, 'samples': 19042176, 'steps': 99177, 'loss/train': 1.2300841808319092} 08/31/2021 07:09:23 - INFO - __main__ - Step 99179: {'lr': 0.00013190284349993658, 'samples': 19042368, 'steps': 99178, 'loss/train': 1.6887935400009155} 08/31/2021 07:09:24 - INFO - __main__ - Step 99180: {'lr': 0.00013189816621317447, 'samples': 19042560, 'steps': 99179, 'loss/train': 1.3093469142913818} 08/31/2021 07:09:25 - INFO - __main__ - Step 99181: {'lr': 0.00013189348897962722, 'samples': 19042752, 'steps': 99180, 'loss/train': 0.6592271327972412} 08/31/2021 07:09:25 - INFO - __main__ - Step 99182: {'lr': 0.0001318888117992969, 'samples': 19042944, 'steps': 99181, 'loss/train': 2.28124737739563} 08/31/2021 07:09:25 - INFO - __main__ - Step 99183: {'lr': 0.00013188413467218578, 'samples': 19043136, 'steps': 99182, 'loss/train': 1.0713458061218262} 08/31/2021 07:09:26 - INFO - __main__ - Step 99184: {'lr': 0.00013187945759829576, 'samples': 19043328, 'steps': 99183, 'loss/train': 1.4675191640853882} 08/31/2021 07:09:27 - INFO - __main__ - Step 99185: {'lr': 0.00013187478057762901, 'samples': 19043520, 'steps': 99184, 'loss/train': 1.5151028633117676} 08/31/2021 07:09:28 - INFO - __main__ - Step 99186: {'lr': 0.0001318701036101877, 'samples': 19043712, 'steps': 99185, 'loss/train': 1.2400968074798584} 08/31/2021 07:09:28 - INFO - __main__ - Step 99187: {'lr': 0.00013186542669597385, 'samples': 19043904, 'steps': 99186, 'loss/train': 1.0482087135314941} 08/31/2021 07:09:28 - INFO - __main__ - Step 99188: {'lr': 0.00013186074983498965, 'samples': 19044096, 'steps': 99187, 'loss/train': 1.3094367980957031} 08/31/2021 07:09:29 - INFO - __main__ - Step 99189: {'lr': 0.00013185607302723716, 'samples': 19044288, 'steps': 99188, 'loss/train': 0.44138285517692566} 08/31/2021 07:09:31 - INFO - __main__ - Step 99190: {'lr': 0.0001318513962727185, 'samples': 19044480, 'steps': 99189, 'loss/train': 0.5387550592422485} 08/31/2021 07:09:32 - INFO - __main__ - Step 99191: {'lr': 0.0001318467195714358, 'samples': 19044672, 'steps': 99190, 'loss/train': 1.2714028358459473} 08/31/2021 07:09:32 - INFO - __main__ - Step 99192: {'lr': 0.0001318420429233911, 'samples': 19044864, 'steps': 99191, 'loss/train': 1.4206815958023071} 08/31/2021 07:09:33 - INFO - __main__ - Step 99193: {'lr': 0.00013183736632858657, 'samples': 19045056, 'steps': 99192, 'loss/train': 1.4400155544281006} 08/31/2021 07:09:33 - INFO - __main__ - Step 99194: {'lr': 0.0001318326897870244, 'samples': 19045248, 'steps': 99193, 'loss/train': 1.1163750886917114} 08/31/2021 07:09:33 - INFO - __main__ - Step 99195: {'lr': 0.00013182801329870652, 'samples': 19045440, 'steps': 99194, 'loss/train': 1.2548344135284424} 08/31/2021 07:09:34 - INFO - __main__ - Step 99196: {'lr': 0.00013182333686363506, 'samples': 19045632, 'steps': 99195, 'loss/train': 0.016966260969638824} 08/31/2021 07:09:35 - INFO - __main__ - Step 99197: {'lr': 0.00013181866048181225, 'samples': 19045824, 'steps': 99196, 'loss/train': 1.0763863325119019} 08/31/2021 07:09:36 - INFO - __main__ - Step 99198: {'lr': 0.0001318139841532401, 'samples': 19046016, 'steps': 99197, 'loss/train': 1.1939433813095093} 08/31/2021 07:09:36 - INFO - __main__ - Step 99199: {'lr': 0.00013180930787792073, 'samples': 19046208, 'steps': 99198, 'loss/train': 1.3395854234695435} 08/31/2021 07:09:36 - INFO - __main__ - Step 99200: {'lr': 0.00013180463165585627, 'samples': 19046400, 'steps': 99199, 'loss/train': 1.4980738162994385} 08/31/2021 07:09:37 - INFO - __main__ - Step 99201: {'lr': 0.00013179995548704882, 'samples': 19046592, 'steps': 99200, 'loss/train': 1.2835177183151245} 08/31/2021 07:09:38 - INFO - __main__ - Step 99202: {'lr': 0.0001317952793715005, 'samples': 19046784, 'steps': 99201, 'loss/train': 1.3056211471557617} 08/31/2021 07:09:39 - INFO - __main__ - Step 99203: {'lr': 0.0001317906033092134, 'samples': 19046976, 'steps': 99202, 'loss/train': 1.683671236038208} 08/31/2021 07:09:39 - INFO - __main__ - Step 99204: {'lr': 0.0001317859273001896, 'samples': 19047168, 'steps': 99203, 'loss/train': 1.5559123754501343} 08/31/2021 07:09:40 - INFO - __main__ - Step 99205: {'lr': 0.00013178125134443136, 'samples': 19047360, 'steps': 99204, 'loss/train': 1.1471638679504395} 08/31/2021 07:09:40 - INFO - __main__ - Step 99206: {'lr': 0.00013177657544194055, 'samples': 19047552, 'steps': 99205, 'loss/train': 1.0761497020721436} 08/31/2021 07:09:41 - INFO - __main__ - Step 99207: {'lr': 0.0001317718995927194, 'samples': 19047744, 'steps': 99206, 'loss/train': 1.399702787399292} 08/31/2021 07:09:42 - INFO - __main__ - Step 99208: {'lr': 0.00013176722379677004, 'samples': 19047936, 'steps': 99207, 'loss/train': 0.974609375} 08/31/2021 07:09:42 - INFO - __main__ - Step 99209: {'lr': 0.0001317625480540945, 'samples': 19048128, 'steps': 99208, 'loss/train': 0.95445716381073} 08/31/2021 07:09:43 - INFO - __main__ - Step 99210: {'lr': 0.00013175787236469495, 'samples': 19048320, 'steps': 99209, 'loss/train': 1.8762110471725464} 08/31/2021 07:09:43 - INFO - __main__ - Step 99211: {'lr': 0.00013175319672857348, 'samples': 19048512, 'steps': 99210, 'loss/train': 0.8951983451843262} 08/31/2021 07:09:44 - INFO - __main__ - Step 99212: {'lr': 0.00013174852114573215, 'samples': 19048704, 'steps': 99211, 'loss/train': 1.117104411125183} 08/31/2021 07:09:45 - INFO - __main__ - Step 99213: {'lr': 0.0001317438456161732, 'samples': 19048896, 'steps': 99212, 'loss/train': 1.0123358964920044} 08/31/2021 07:09:45 - INFO - __main__ - Step 99214: {'lr': 0.00013173917013989856, 'samples': 19049088, 'steps': 99213, 'loss/train': 0.19867922365665436} 08/31/2021 07:09:46 - INFO - __main__ - Step 99215: {'lr': 0.00013173449471691058, 'samples': 19049280, 'steps': 99214, 'loss/train': 1.8228766918182373} 08/31/2021 07:09:46 - INFO - __main__ - Step 99216: {'lr': 0.0001317298193472111, 'samples': 19049472, 'steps': 99215, 'loss/train': 0.2916373014450073} 08/31/2021 07:09:47 - INFO - __main__ - Step 99217: {'lr': 0.00013172514403080233, 'samples': 19049664, 'steps': 99216, 'loss/train': 1.2199194431304932} 08/31/2021 07:09:48 - INFO - __main__ - Step 99218: {'lr': 0.0001317204687676864, 'samples': 19049856, 'steps': 99217, 'loss/train': 0.8286017179489136} 08/31/2021 07:09:48 - INFO - __main__ - Step 99219: {'lr': 0.00013171579355786538, 'samples': 19050048, 'steps': 99218, 'loss/train': 1.6212525367736816} 08/31/2021 07:09:49 - INFO - __main__ - Step 99220: {'lr': 0.00013171111840134142, 'samples': 19050240, 'steps': 99219, 'loss/train': 1.4328168630599976} 08/31/2021 07:09:49 - INFO - __main__ - Step 99221: {'lr': 0.0001317064432981166, 'samples': 19050432, 'steps': 99220, 'loss/train': 0.7234498262405396} 08/31/2021 07:09:51 - INFO - __main__ - Step 99222: {'lr': 0.00013170176824819303, 'samples': 19050624, 'steps': 99221, 'loss/train': 0.5664961338043213} 08/31/2021 07:09:51 - INFO - __main__ - Step 99223: {'lr': 0.0001316970932515728, 'samples': 19050816, 'steps': 99222, 'loss/train': 2.304934501647949} 08/31/2021 07:09:51 - INFO - __main__ - Step 99224: {'lr': 0.00013169241830825803, 'samples': 19051008, 'steps': 99223, 'loss/train': 0.27001670002937317} 08/31/2021 07:09:52 - INFO - __main__ - Step 99225: {'lr': 0.00013168774341825086, 'samples': 19051200, 'steps': 99224, 'loss/train': 1.193464994430542} 08/31/2021 07:09:52 - INFO - __main__ - Step 99226: {'lr': 0.00013168306858155334, 'samples': 19051392, 'steps': 99225, 'loss/train': 1.477455973625183} 08/31/2021 07:09:54 - INFO - __main__ - Step 99227: {'lr': 0.0001316783937981677, 'samples': 19051584, 'steps': 99226, 'loss/train': 1.8530144691467285} 08/31/2021 07:09:54 - INFO - __main__ - Step 99228: {'lr': 0.00013167371906809588, 'samples': 19051776, 'steps': 99227, 'loss/train': 1.172791600227356} 08/31/2021 07:09:54 - INFO - __main__ - Step 99229: {'lr': 0.00013166904439134005, 'samples': 19051968, 'steps': 99228, 'loss/train': 1.0198153257369995} 08/31/2021 07:09:55 - INFO - __main__ - Step 99230: {'lr': 0.0001316643697679023, 'samples': 19052160, 'steps': 99229, 'loss/train': 0.6575351357460022} 08/31/2021 07:09:55 - INFO - __main__ - Step 99231: {'lr': 0.00013165969519778482, 'samples': 19052352, 'steps': 99230, 'loss/train': 1.2796422243118286} 08/31/2021 07:09:57 - INFO - __main__ - Step 99232: {'lr': 0.00013165502068098958, 'samples': 19052544, 'steps': 99231, 'loss/train': 1.7080035209655762} 08/31/2021 07:09:58 - INFO - __main__ - Step 99233: {'lr': 0.00013165034621751882, 'samples': 19052736, 'steps': 99232, 'loss/train': 0.6197007298469543} 08/31/2021 07:09:58 - INFO - __main__ - Step 99234: {'lr': 0.00013164567180737452, 'samples': 19052928, 'steps': 99233, 'loss/train': 1.4831074476242065} 08/31/2021 07:09:59 - INFO - __main__ - Step 99235: {'lr': 0.0001316409974505589, 'samples': 19053120, 'steps': 99234, 'loss/train': 2.1522481441497803} 08/31/2021 07:09:59 - INFO - __main__ - Step 99236: {'lr': 0.000131636323147074, 'samples': 19053312, 'steps': 99235, 'loss/train': 2.4469101428985596} 08/31/2021 07:09:59 - INFO - __main__ - Step 99237: {'lr': 0.00013163164889692198, 'samples': 19053504, 'steps': 99236, 'loss/train': 1.5166736841201782} 08/31/2021 07:10:01 - INFO - __main__ - Step 99238: {'lr': 0.0001316269747001049, 'samples': 19053696, 'steps': 99237, 'loss/train': 1.6985551118850708} 08/31/2021 07:10:01 - INFO - __main__ - Step 99239: {'lr': 0.00013162230055662488, 'samples': 19053888, 'steps': 99238, 'loss/train': 1.2150598764419556} 08/31/2021 07:10:02 - INFO - __main__ - Step 99240: {'lr': 0.00013161762646648402, 'samples': 19054080, 'steps': 99239, 'loss/train': 1.295936942100525} 08/31/2021 07:10:02 - INFO - __main__ - Step 99241: {'lr': 0.00013161295242968452, 'samples': 19054272, 'steps': 99240, 'loss/train': 0.5353776812553406} 08/31/2021 07:10:02 - INFO - __main__ - Step 99242: {'lr': 0.0001316082784462283, 'samples': 19054464, 'steps': 99241, 'loss/train': 0.5352637767791748} 08/31/2021 07:10:04 - INFO - __main__ - Step 99243: {'lr': 0.00013160360451611758, 'samples': 19054656, 'steps': 99242, 'loss/train': 1.1663626432418823} 08/31/2021 07:10:05 - INFO - __main__ - Step 99244: {'lr': 0.00013159893063935442, 'samples': 19054848, 'steps': 99243, 'loss/train': 1.3102140426635742} 08/31/2021 07:10:05 - INFO - __main__ - Step 99245: {'lr': 0.00013159425681594098, 'samples': 19055040, 'steps': 99244, 'loss/train': 0.8870473504066467} 08/31/2021 07:10:06 - INFO - __main__ - Step 99246: {'lr': 0.0001315895830458793, 'samples': 19055232, 'steps': 99245, 'loss/train': 0.5621102452278137} 08/31/2021 07:10:06 - INFO - __main__ - Step 99247: {'lr': 0.0001315849093291716, 'samples': 19055424, 'steps': 99246, 'loss/train': 1.258809208869934} 08/31/2021 07:10:08 - INFO - __main__ - Step 99248: {'lr': 0.00013158023566581988, 'samples': 19055616, 'steps': 99247, 'loss/train': 0.49273374676704407} 08/31/2021 07:10:08 - INFO - __main__ - Step 99249: {'lr': 0.00013157556205582626, 'samples': 19055808, 'steps': 99248, 'loss/train': 0.5155194997787476} 08/31/2021 07:10:08 - INFO - __main__ - Step 99250: {'lr': 0.00013157088849919286, 'samples': 19056000, 'steps': 99249, 'loss/train': 1.4089381694793701} 08/31/2021 07:10:09 - INFO - __main__ - Step 99251: {'lr': 0.00013156621499592182, 'samples': 19056192, 'steps': 99250, 'loss/train': 1.534696340560913} 08/31/2021 07:10:09 - INFO - __main__ - Step 99252: {'lr': 0.00013156154154601518, 'samples': 19056384, 'steps': 99251, 'loss/train': 2.7436888217926025} 08/31/2021 07:10:09 - INFO - __main__ - Step 99253: {'lr': 0.0001315568681494751, 'samples': 19056576, 'steps': 99252, 'loss/train': 0.8982190489768982} 08/31/2021 07:10:11 - INFO - __main__ - Step 99254: {'lr': 0.00013155219480630377, 'samples': 19056768, 'steps': 99253, 'loss/train': 0.9432326555252075} 08/31/2021 07:10:11 - INFO - __main__ - Step 99255: {'lr': 0.00013154752151650308, 'samples': 19056960, 'steps': 99254, 'loss/train': 1.225927472114563} 08/31/2021 07:10:12 - INFO - __main__ - Step 99256: {'lr': 0.0001315428482800753, 'samples': 19057152, 'steps': 99255, 'loss/train': 1.3528636693954468} 08/31/2021 07:10:12 - INFO - __main__ - Step 99257: {'lr': 0.00013153817509702244, 'samples': 19057344, 'steps': 99256, 'loss/train': 0.9980130791664124} 08/31/2021 07:10:12 - INFO - __main__ - Step 99258: {'lr': 0.00013153350196734665, 'samples': 19057536, 'steps': 99257, 'loss/train': 1.0974221229553223} 08/31/2021 07:10:14 - INFO - __main__ - Step 99259: {'lr': 0.00013152882889105007, 'samples': 19057728, 'steps': 99258, 'loss/train': 1.0353138446807861} 08/31/2021 07:10:14 - INFO - __main__ - Step 99260: {'lr': 0.00013152415586813472, 'samples': 19057920, 'steps': 99259, 'loss/train': 1.139345407485962} 08/31/2021 07:10:15 - INFO - __main__ - Step 99261: {'lr': 0.00013151948289860278, 'samples': 19058112, 'steps': 99260, 'loss/train': 0.29997748136520386} 08/31/2021 07:10:15 - INFO - __main__ - Step 99262: {'lr': 0.00013151480998245633, 'samples': 19058304, 'steps': 99261, 'loss/train': 0.9677925109863281} 08/31/2021 07:10:15 - INFO - __main__ - Step 99263: {'lr': 0.00013151013711969748, 'samples': 19058496, 'steps': 99262, 'loss/train': 1.1194076538085938} 08/31/2021 07:10:17 - INFO - __main__ - Step 99264: {'lr': 0.00013150546431032833, 'samples': 19058688, 'steps': 99263, 'loss/train': 1.3644468784332275} 08/31/2021 07:10:17 - INFO - __main__ - Step 99265: {'lr': 0.000131500791554351, 'samples': 19058880, 'steps': 99264, 'loss/train': 0.1397073119878769} 08/31/2021 07:10:18 - INFO - __main__ - Step 99266: {'lr': 0.0001314961188517676, 'samples': 19059072, 'steps': 99265, 'loss/train': 1.3266972303390503} 08/31/2021 07:10:18 - INFO - __main__ - Step 99267: {'lr': 0.0001314914462025802, 'samples': 19059264, 'steps': 99266, 'loss/train': 0.9380638003349304} 08/31/2021 07:10:18 - INFO - __main__ - Step 99268: {'lr': 0.000131486773606791, 'samples': 19059456, 'steps': 99267, 'loss/train': 0.6561790704727173} 08/31/2021 07:10:20 - INFO - __main__ - Step 99269: {'lr': 0.00013148210106440195, 'samples': 19059648, 'steps': 99268, 'loss/train': 1.8065484762191772} 08/31/2021 07:10:20 - INFO - __main__ - Step 99270: {'lr': 0.00013147742857541524, 'samples': 19059840, 'steps': 99269, 'loss/train': 1.2407103776931763} 08/31/2021 07:10:21 - INFO - __main__ - Step 99271: {'lr': 0.000131472756139833, 'samples': 19060032, 'steps': 99270, 'loss/train': 1.1386014223098755} 08/31/2021 07:10:21 - INFO - __main__ - Step 99272: {'lr': 0.00013146808375765729, 'samples': 19060224, 'steps': 99271, 'loss/train': 0.6915973424911499} 08/31/2021 07:10:21 - INFO - __main__ - Step 99273: {'lr': 0.0001314634114288902, 'samples': 19060416, 'steps': 99272, 'loss/train': 1.5556299686431885} 08/31/2021 07:10:23 - INFO - __main__ - Step 99274: {'lr': 0.0001314587391535339, 'samples': 19060608, 'steps': 99273, 'loss/train': 0.6231270432472229} 08/31/2021 07:10:23 - INFO - __main__ - Step 99275: {'lr': 0.00013145406693159046, 'samples': 19060800, 'steps': 99274, 'loss/train': 1.316165804862976} 08/31/2021 07:10:24 - INFO - __main__ - Step 99276: {'lr': 0.00013144939476306198, 'samples': 19060992, 'steps': 99275, 'loss/train': 1.0774222612380981} 08/31/2021 07:10:24 - INFO - __main__ - Step 99277: {'lr': 0.00013144472264795058, 'samples': 19061184, 'steps': 99276, 'loss/train': 1.2171076536178589} 08/31/2021 07:10:24 - INFO - __main__ - Step 99278: {'lr': 0.00013144005058625836, 'samples': 19061376, 'steps': 99277, 'loss/train': 1.1050642728805542} 08/31/2021 07:10:26 - INFO - __main__ - Step 99279: {'lr': 0.0001314353785779874, 'samples': 19061568, 'steps': 99278, 'loss/train': 1.4746289253234863} 08/31/2021 07:10:26 - INFO - __main__ - Step 99280: {'lr': 0.00013143070662313986, 'samples': 19061760, 'steps': 99279, 'loss/train': 1.0434459447860718} 08/31/2021 07:10:27 - INFO - __main__ - Step 99281: {'lr': 0.00013142603472171788, 'samples': 19061952, 'steps': 99280, 'loss/train': 0.7376382350921631} 08/31/2021 07:10:27 - INFO - __main__ - Step 99282: {'lr': 0.00013142136287372342, 'samples': 19062144, 'steps': 99281, 'loss/train': 1.116980791091919} 08/31/2021 07:10:27 - INFO - __main__ - Step 99283: {'lr': 0.0001314166910791587, 'samples': 19062336, 'steps': 99282, 'loss/train': 0.35951635241508484} 08/31/2021 07:10:29 - INFO - __main__ - Step 99284: {'lr': 0.00013141201933802575, 'samples': 19062528, 'steps': 99283, 'loss/train': 0.8181207180023193} 08/31/2021 07:10:29 - INFO - __main__ - Step 99285: {'lr': 0.00013140734765032668, 'samples': 19062720, 'steps': 99284, 'loss/train': 0.7081024050712585} 08/31/2021 07:10:30 - INFO - __main__ - Step 99286: {'lr': 0.0001314026760160637, 'samples': 19062912, 'steps': 99285, 'loss/train': 0.38147756457328796} 08/31/2021 07:10:30 - INFO - __main__ - Step 99287: {'lr': 0.00013139800443523882, 'samples': 19063104, 'steps': 99286, 'loss/train': 1.2045220136642456} 08/31/2021 07:10:30 - INFO - __main__ - Step 99288: {'lr': 0.00013139333290785416, 'samples': 19063296, 'steps': 99287, 'loss/train': 1.51215660572052} 08/31/2021 07:10:32 - INFO - __main__ - Step 99289: {'lr': 0.00013138866143391182, 'samples': 19063488, 'steps': 99288, 'loss/train': 1.0804357528686523} 08/31/2021 07:10:32 - INFO - __main__ - Step 99290: {'lr': 0.00013138399001341394, 'samples': 19063680, 'steps': 99289, 'loss/train': 1.4445252418518066} 08/31/2021 07:10:33 - INFO - __main__ - Step 99291: {'lr': 0.0001313793186463626, 'samples': 19063872, 'steps': 99290, 'loss/train': 1.1901203393936157} 08/31/2021 07:10:33 - INFO - __main__ - Step 99292: {'lr': 0.0001313746473327599, 'samples': 19064064, 'steps': 99291, 'loss/train': 0.1689896285533905} 08/31/2021 07:10:33 - INFO - __main__ - Step 99293: {'lr': 0.00013136997607260796, 'samples': 19064256, 'steps': 99292, 'loss/train': 1.7179454565048218} 08/31/2021 07:10:35 - INFO - __main__ - Step 99294: {'lr': 0.00013136530486590887, 'samples': 19064448, 'steps': 99293, 'loss/train': 0.4605514109134674} 08/31/2021 07:10:36 - INFO - __main__ - Step 99295: {'lr': 0.00013136063371266485, 'samples': 19064640, 'steps': 99294, 'loss/train': 1.971096396446228} 08/31/2021 07:10:36 - INFO - __main__ - Step 99296: {'lr': 0.0001313559626128778, 'samples': 19064832, 'steps': 99295, 'loss/train': 0.8353366255760193} 08/31/2021 07:10:36 - INFO - __main__ - Step 99297: {'lr': 0.0001313512915665499, 'samples': 19065024, 'steps': 99296, 'loss/train': 0.5340226292610168} 08/31/2021 07:10:37 - INFO - __main__ - Step 99298: {'lr': 0.0001313466205736833, 'samples': 19065216, 'steps': 99297, 'loss/train': 1.0679277181625366} 08/31/2021 07:10:37 - INFO - __main__ - Step 99299: {'lr': 0.00013134194963428008, 'samples': 19065408, 'steps': 99298, 'loss/train': 0.03657685965299606} 08/31/2021 07:10:39 - INFO - __main__ - Step 99300: {'lr': 0.00013133727874834237, 'samples': 19065600, 'steps': 99299, 'loss/train': 0.016392022371292114} 08/31/2021 07:10:40 - INFO - __main__ - Step 99301: {'lr': 0.0001313326079158722, 'samples': 19065792, 'steps': 99300, 'loss/train': 1.2094123363494873} 08/31/2021 07:10:40 - INFO - __main__ - Step 99302: {'lr': 0.00013132793713687178, 'samples': 19065984, 'steps': 99301, 'loss/train': 1.3689563274383545} 08/31/2021 07:10:40 - INFO - __main__ - Step 99303: {'lr': 0.00013132326641134313, 'samples': 19066176, 'steps': 99302, 'loss/train': 1.1527035236358643} 08/31/2021 07:10:41 - INFO - __main__ - Step 99304: {'lr': 0.0001313185957392884, 'samples': 19066368, 'steps': 99303, 'loss/train': 1.2873156070709229} 08/31/2021 07:10:42 - INFO - __main__ - Step 99305: {'lr': 0.00013131392512070967, 'samples': 19066560, 'steps': 99304, 'loss/train': 1.4547243118286133} 08/31/2021 07:10:43 - INFO - __main__ - Step 99306: {'lr': 0.00013130925455560904, 'samples': 19066752, 'steps': 99305, 'loss/train': 1.5451202392578125} 08/31/2021 07:10:43 - INFO - __main__ - Step 99307: {'lr': 0.00013130458404398866, 'samples': 19066944, 'steps': 99306, 'loss/train': 1.0157791376113892} 08/31/2021 07:10:44 - INFO - __main__ - Step 99308: {'lr': 0.00013129991358585064, 'samples': 19067136, 'steps': 99307, 'loss/train': 1.0599452257156372} 08/31/2021 07:10:44 - INFO - __main__ - Step 99309: {'lr': 0.00013129524318119702, 'samples': 19067328, 'steps': 99308, 'loss/train': 0.7313417196273804} 08/31/2021 07:10:45 - INFO - __main__ - Step 99310: {'lr': 0.00013129057283002988, 'samples': 19067520, 'steps': 99309, 'loss/train': 1.3018856048583984} 08/31/2021 07:10:46 - INFO - __main__ - Step 99311: {'lr': 0.0001312859025323514, 'samples': 19067712, 'steps': 99310, 'loss/train': 1.7982081174850464} 08/31/2021 07:10:46 - INFO - __main__ - Step 99312: {'lr': 0.00013128123228816366, 'samples': 19067904, 'steps': 99311, 'loss/train': 1.1535886526107788} 08/31/2021 07:10:47 - INFO - __main__ - Step 99313: {'lr': 0.00013127656209746874, 'samples': 19068096, 'steps': 99312, 'loss/train': 0.7324860692024231} 08/31/2021 07:10:47 - INFO - __main__ - Step 99314: {'lr': 0.00013127189196026883, 'samples': 19068288, 'steps': 99313, 'loss/train': 1.0429298877716064} 08/31/2021 07:10:48 - INFO - __main__ - Step 99315: {'lr': 0.00013126722187656594, 'samples': 19068480, 'steps': 99314, 'loss/train': 0.9441620111465454} 08/31/2021 07:10:49 - INFO - __main__ - Step 99316: {'lr': 0.0001312625518463622, 'samples': 19068672, 'steps': 99315, 'loss/train': 1.4815887212753296} 08/31/2021 07:10:49 - INFO - __main__ - Step 99317: {'lr': 0.0001312578818696597, 'samples': 19068864, 'steps': 99316, 'loss/train': 1.2572933435440063} 08/31/2021 07:10:50 - INFO - __main__ - Step 99318: {'lr': 0.0001312532119464606, 'samples': 19069056, 'steps': 99317, 'loss/train': 0.664878249168396} 08/31/2021 07:10:50 - INFO - __main__ - Step 99319: {'lr': 0.00013124854207676695, 'samples': 19069248, 'steps': 99318, 'loss/train': 1.2330983877182007} 08/31/2021 07:10:50 - INFO - __main__ - Step 99320: {'lr': 0.0001312438722605809, 'samples': 19069440, 'steps': 99319, 'loss/train': 0.715277373790741} 08/31/2021 07:10:52 - INFO - __main__ - Step 99321: {'lr': 0.0001312392024979046, 'samples': 19069632, 'steps': 99320, 'loss/train': 0.9595337510108948} 08/31/2021 07:10:52 - INFO - __main__ - Step 99322: {'lr': 0.00013123453278874, 'samples': 19069824, 'steps': 99321, 'loss/train': 1.7058987617492676} 08/31/2021 07:10:53 - INFO - __main__ - Step 99323: {'lr': 0.0001312298631330893, 'samples': 19070016, 'steps': 99322, 'loss/train': 0.48591840267181396} 08/31/2021 07:10:53 - INFO - __main__ - Step 99324: {'lr': 0.00013122519353095459, 'samples': 19070208, 'steps': 99323, 'loss/train': 1.4282763004302979} 08/31/2021 07:10:53 - INFO - __main__ - Step 99325: {'lr': 0.00013122052398233794, 'samples': 19070400, 'steps': 99324, 'loss/train': 1.2329087257385254} 08/31/2021 07:10:55 - INFO - __main__ - Step 99326: {'lr': 0.0001312158544872415, 'samples': 19070592, 'steps': 99325, 'loss/train': 0.9990717768669128} 08/31/2021 07:10:55 - INFO - __main__ - Step 99327: {'lr': 0.00013121118504566738, 'samples': 19070784, 'steps': 99326, 'loss/train': 1.0685057640075684} 08/31/2021 07:10:56 - INFO - __main__ - Step 99328: {'lr': 0.00013120651565761766, 'samples': 19070976, 'steps': 99327, 'loss/train': 1.2550054788589478} 08/31/2021 07:10:56 - INFO - __main__ - Step 99329: {'lr': 0.00013120184632309446, 'samples': 19071168, 'steps': 99328, 'loss/train': 1.3627957105636597} 08/31/2021 07:10:56 - INFO - __main__ - Step 99330: {'lr': 0.00013119717704209986, 'samples': 19071360, 'steps': 99329, 'loss/train': 1.224023699760437} 08/31/2021 07:10:58 - INFO - __main__ - Step 99331: {'lr': 0.000131192507814636, 'samples': 19071552, 'steps': 99330, 'loss/train': 1.4548317193984985} 08/31/2021 07:10:58 - INFO - __main__ - Step 99332: {'lr': 0.00013118783864070493, 'samples': 19071744, 'steps': 99331, 'loss/train': 0.8785534501075745} 08/31/2021 07:10:59 - INFO - __main__ - Step 99333: {'lr': 0.00013118316952030878, 'samples': 19071936, 'steps': 99332, 'loss/train': 1.1311161518096924} 08/31/2021 07:10:59 - INFO - __main__ - Step 99334: {'lr': 0.0001311785004534497, 'samples': 19072128, 'steps': 99333, 'loss/train': 1.060951828956604} 08/31/2021 07:11:00 - INFO - __main__ - Step 99335: {'lr': 0.00013117383144012985, 'samples': 19072320, 'steps': 99334, 'loss/train': 1.18971586227417} 08/31/2021 07:11:01 - INFO - __main__ - Step 99336: {'lr': 0.0001311691624803511, 'samples': 19072512, 'steps': 99335, 'loss/train': 0.9916255474090576} 08/31/2021 07:11:02 - INFO - __main__ - Step 99337: {'lr': 0.00013116449357411574, 'samples': 19072704, 'steps': 99336, 'loss/train': 1.51210355758667} 08/31/2021 07:11:02 - INFO - __main__ - Step 99338: {'lr': 0.0001311598247214258, 'samples': 19072896, 'steps': 99337, 'loss/train': 1.7875310182571411} 08/31/2021 07:11:02 - INFO - __main__ - Step 99339: {'lr': 0.0001311551559222834, 'samples': 19073088, 'steps': 99338, 'loss/train': 1.4992469549179077} 08/31/2021 07:11:03 - INFO - __main__ - Step 99340: {'lr': 0.00013115048717669063, 'samples': 19073280, 'steps': 99339, 'loss/train': 0.3211067020893097} 08/31/2021 07:11:04 - INFO - __main__ - Step 99341: {'lr': 0.00013114581848464968, 'samples': 19073472, 'steps': 99340, 'loss/train': 1.137550711631775} 08/31/2021 07:11:05 - INFO - __main__ - Step 99342: {'lr': 0.00013114114984616256, 'samples': 19073664, 'steps': 99341, 'loss/train': 1.3863582611083984} 08/31/2021 07:11:05 - INFO - __main__ - Step 99343: {'lr': 0.0001311364812612314, 'samples': 19073856, 'steps': 99342, 'loss/train': 0.6707139611244202} 08/31/2021 07:11:05 - INFO - __main__ - Step 99344: {'lr': 0.00013113181272985834, 'samples': 19074048, 'steps': 99343, 'loss/train': 1.4087954759597778} 08/31/2021 07:11:06 - INFO - __main__ - Step 99345: {'lr': 0.00013112714425204543, 'samples': 19074240, 'steps': 99344, 'loss/train': 0.41571399569511414} 08/31/2021 07:11:06 - INFO - __main__ - Step 99346: {'lr': 0.00013112247582779476, 'samples': 19074432, 'steps': 99345, 'loss/train': 1.9266259670257568} 08/31/2021 07:11:08 - INFO - __main__ - Step 99347: {'lr': 0.00013111780745710849, 'samples': 19074624, 'steps': 99346, 'loss/train': 0.4608350098133087} 08/31/2021 07:11:08 - INFO - __main__ - Step 99348: {'lr': 0.0001311131391399888, 'samples': 19074816, 'steps': 99347, 'loss/train': 1.492354393005371} 08/31/2021 07:11:08 - INFO - __main__ - Step 99349: {'lr': 0.00013110847087643762, 'samples': 19075008, 'steps': 99348, 'loss/train': 1.3841056823730469} 08/31/2021 07:11:09 - INFO - __main__ - Step 99350: {'lr': 0.0001311038026664571, 'samples': 19075200, 'steps': 99349, 'loss/train': 1.3366286754608154} 08/31/2021 07:11:09 - INFO - __main__ - Step 99351: {'lr': 0.0001310991345100494, 'samples': 19075392, 'steps': 99350, 'loss/train': 0.9442206621170044} 08/31/2021 07:11:11 - INFO - __main__ - Step 99352: {'lr': 0.00013109446640721656, 'samples': 19075584, 'steps': 99351, 'loss/train': 0.6594754457473755} 08/31/2021 07:11:12 - INFO - __main__ - Step 99353: {'lr': 0.00013108979835796075, 'samples': 19075776, 'steps': 99352, 'loss/train': 1.4766285419464111} 08/31/2021 07:11:12 - INFO - __main__ - Step 99354: {'lr': 0.00013108513036228403, 'samples': 19075968, 'steps': 99353, 'loss/train': 0.2716865837574005} 08/31/2021 07:11:12 - INFO - __main__ - Step 99355: {'lr': 0.0001310804624201885, 'samples': 19076160, 'steps': 99354, 'loss/train': 0.8918721675872803} 08/31/2021 07:11:13 - INFO - __main__ - Step 99356: {'lr': 0.00013107579453167632, 'samples': 19076352, 'steps': 99355, 'loss/train': 1.1378694772720337} 08/31/2021 07:11:15 - INFO - __main__ - Step 99357: {'lr': 0.0001310711266967495, 'samples': 19076544, 'steps': 99356, 'loss/train': 1.384843111038208} 08/31/2021 07:11:15 - INFO - __main__ - Step 99358: {'lr': 0.00013106645891541025, 'samples': 19076736, 'steps': 99357, 'loss/train': 0.7783317565917969} 08/31/2021 07:11:15 - INFO - __main__ - Step 99359: {'lr': 0.00013106179118766058, 'samples': 19076928, 'steps': 99358, 'loss/train': 0.5000618696212769} 08/31/2021 07:11:16 - INFO - __main__ - Step 99360: {'lr': 0.00013105712351350264, 'samples': 19077120, 'steps': 99359, 'loss/train': 1.005301594734192} 08/31/2021 07:11:16 - INFO - __main__ - Step 99361: {'lr': 0.00013105245589293852, 'samples': 19077312, 'steps': 99360, 'loss/train': 1.1487520933151245} 08/31/2021 07:11:17 - INFO - __main__ - Step 99362: {'lr': 0.00013104778832597041, 'samples': 19077504, 'steps': 99361, 'loss/train': 0.015237490646541119} 08/31/2021 07:11:18 - INFO - __main__ - Step 99363: {'lr': 0.00013104312081260028, 'samples': 19077696, 'steps': 99362, 'loss/train': 1.5990073680877686} 08/31/2021 07:11:18 - INFO - __main__ - Step 99364: {'lr': 0.00013103845335283023, 'samples': 19077888, 'steps': 99363, 'loss/train': 0.4955701529979706} 08/31/2021 07:11:19 - INFO - __main__ - Step 99365: {'lr': 0.00013103378594666245, 'samples': 19078080, 'steps': 99364, 'loss/train': 0.6694334149360657} 08/31/2021 07:11:19 - INFO - __main__ - Step 99366: {'lr': 0.000131029118594099, 'samples': 19078272, 'steps': 99365, 'loss/train': 1.288565754890442} 08/31/2021 07:11:20 - INFO - __main__ - Step 99367: {'lr': 0.000131024451295142, 'samples': 19078464, 'steps': 99366, 'loss/train': 1.607283115386963} 08/31/2021 07:11:21 - INFO - __main__ - Step 99368: {'lr': 0.00013101978404979353, 'samples': 19078656, 'steps': 99367, 'loss/train': 0.8701597452163696} 08/31/2021 07:11:21 - INFO - __main__ - Step 99369: {'lr': 0.00013101511685805574, 'samples': 19078848, 'steps': 99368, 'loss/train': 0.7606099843978882} 08/31/2021 07:11:22 - INFO - __main__ - Step 99370: {'lr': 0.0001310104497199307, 'samples': 19079040, 'steps': 99369, 'loss/train': 1.243194580078125} 08/31/2021 07:11:22 - INFO - __main__ - Step 99371: {'lr': 0.0001310057826354205, 'samples': 19079232, 'steps': 99370, 'loss/train': 1.3422386646270752} 08/31/2021 07:11:22 - INFO - __main__ - Step 99372: {'lr': 0.00013100111560452725, 'samples': 19079424, 'steps': 99371, 'loss/train': 1.4116050004959106} 08/31/2021 07:11:23 - INFO - __main__ - Step 99373: {'lr': 0.00013099644862725308, 'samples': 19079616, 'steps': 99372, 'loss/train': 0.9463654160499573} 08/31/2021 07:11:25 - INFO - __main__ - Step 99374: {'lr': 0.00013099178170360005, 'samples': 19079808, 'steps': 99373, 'loss/train': 1.200413703918457} 08/31/2021 07:11:25 - INFO - __main__ - Step 99375: {'lr': 0.00013098711483357039, 'samples': 19080000, 'steps': 99374, 'loss/train': 1.087787389755249} 08/31/2021 07:11:26 - INFO - __main__ - Step 99376: {'lr': 0.000130982448017166, 'samples': 19080192, 'steps': 99375, 'loss/train': 0.8636965155601501} 08/31/2021 07:11:26 - INFO - __main__ - Step 99377: {'lr': 0.00013097778125438915, 'samples': 19080384, 'steps': 99376, 'loss/train': 0.6059216856956482} 08/31/2021 07:11:26 - INFO - __main__ - Step 99378: {'lr': 0.0001309731145452418, 'samples': 19080576, 'steps': 99377, 'loss/train': 0.8980503082275391} 08/31/2021 07:11:28 - INFO - __main__ - Step 99379: {'lr': 0.00013096844788972612, 'samples': 19080768, 'steps': 99378, 'loss/train': 1.55452299118042} 08/31/2021 07:11:28 - INFO - __main__ - Step 99380: {'lr': 0.00013096378128784426, 'samples': 19080960, 'steps': 99379, 'loss/train': 1.2854681015014648} 08/31/2021 07:11:29 - INFO - __main__ - Step 99381: {'lr': 0.00013095911473959827, 'samples': 19081152, 'steps': 99380, 'loss/train': 0.6461917161941528} 08/31/2021 07:11:29 - INFO - __main__ - Step 99382: {'lr': 0.00013095444824499025, 'samples': 19081344, 'steps': 99381, 'loss/train': 1.4253910779953003} 08/31/2021 07:11:30 - INFO - __main__ - Step 99383: {'lr': 0.00013094978180402234, 'samples': 19081536, 'steps': 99382, 'loss/train': 0.5643200278282166} 08/31/2021 07:11:30 - INFO - __main__ - Step 99384: {'lr': 0.00013094511541669661, 'samples': 19081728, 'steps': 99383, 'loss/train': 0.7754808068275452} 08/31/2021 07:11:31 - INFO - __main__ - Step 99385: {'lr': 0.0001309404490830152, 'samples': 19081920, 'steps': 99384, 'loss/train': 0.667856752872467} 08/31/2021 07:11:32 - INFO - __main__ - Step 99386: {'lr': 0.00013093578280298017, 'samples': 19082112, 'steps': 99385, 'loss/train': 1.0502954721450806} 08/31/2021 07:11:32 - INFO - __main__ - Step 99387: {'lr': 0.00013093111657659363, 'samples': 19082304, 'steps': 99386, 'loss/train': 1.4086533784866333} 08/31/2021 07:11:33 - INFO - __main__ - Step 99388: {'lr': 0.0001309264504038577, 'samples': 19082496, 'steps': 99387, 'loss/train': 1.4205958843231201} 08/31/2021 07:11:33 - INFO - __main__ - Step 99389: {'lr': 0.0001309217842847746, 'samples': 19082688, 'steps': 99388, 'loss/train': 1.1939064264297485} 08/31/2021 07:11:35 - INFO - __main__ - Step 99390: {'lr': 0.00013091711821934616, 'samples': 19082880, 'steps': 99389, 'loss/train': 1.2245782613754272} 08/31/2021 07:11:35 - INFO - __main__ - Step 99391: {'lr': 0.00013091245220757465, 'samples': 19083072, 'steps': 99390, 'loss/train': 1.1769698858261108} 08/31/2021 07:11:35 - INFO - __main__ - Step 99392: {'lr': 0.00013090778624946211, 'samples': 19083264, 'steps': 99391, 'loss/train': 0.0867220088839531} 08/31/2021 07:11:36 - INFO - __main__ - Step 99393: {'lr': 0.00013090312034501073, 'samples': 19083456, 'steps': 99392, 'loss/train': 1.4370814561843872} 08/31/2021 07:11:36 - INFO - __main__ - Step 99394: {'lr': 0.00013089845449422256, 'samples': 19083648, 'steps': 99393, 'loss/train': 1.1278769969940186} 08/31/2021 07:11:38 - INFO - __main__ - Step 99395: {'lr': 0.00013089378869709972, 'samples': 19083840, 'steps': 99394, 'loss/train': 1.2324234247207642} 08/31/2021 07:11:38 - INFO - __main__ - Step 99396: {'lr': 0.00013088912295364428, 'samples': 19084032, 'steps': 99395, 'loss/train': 0.9319562911987305} 08/31/2021 07:11:39 - INFO - __main__ - Step 99397: {'lr': 0.00013088445726385837, 'samples': 19084224, 'steps': 99396, 'loss/train': 0.970470130443573} 08/31/2021 07:11:39 - INFO - __main__ - Step 99398: {'lr': 0.00013087979162774407, 'samples': 19084416, 'steps': 99397, 'loss/train': 0.021863777190446854} 08/31/2021 07:11:39 - INFO - __main__ - Step 99399: {'lr': 0.00013087512604530353, 'samples': 19084608, 'steps': 99398, 'loss/train': 0.8703310489654541} 08/31/2021 07:11:40 - INFO - __main__ - Step 99400: {'lr': 0.00013087046051653877, 'samples': 19084800, 'steps': 99399, 'loss/train': 0.6078135967254639} 08/31/2021 07:11:41 - INFO - __main__ - Step 99401: {'lr': 0.00013086579504145203, 'samples': 19084992, 'steps': 99400, 'loss/train': 0.47721755504608154} 08/31/2021 07:11:42 - INFO - __main__ - Step 99402: {'lr': 0.00013086112962004535, 'samples': 19085184, 'steps': 99401, 'loss/train': 1.2842637300491333} 08/31/2021 07:11:42 - INFO - __main__ - Step 99403: {'lr': 0.00013085646425232072, 'samples': 19085376, 'steps': 99402, 'loss/train': 1.3920722007751465} 08/31/2021 07:11:42 - INFO - __main__ - Step 99404: {'lr': 0.00013085179893828033, 'samples': 19085568, 'steps': 99403, 'loss/train': 1.253801703453064} 08/31/2021 07:11:43 - INFO - __main__ - Step 99405: {'lr': 0.00013084713367792628, 'samples': 19085760, 'steps': 99404, 'loss/train': 0.9639249444007874} 08/31/2021 07:11:44 - INFO - __main__ - Step 99406: {'lr': 0.0001308424684712607, 'samples': 19085952, 'steps': 99405, 'loss/train': 1.313557505607605} 08/31/2021 07:11:45 - INFO - __main__ - Step 99407: {'lr': 0.00013083780331828564, 'samples': 19086144, 'steps': 99406, 'loss/train': 0.4941728711128235} 08/31/2021 07:11:45 - INFO - __main__ - Step 99408: {'lr': 0.00013083313821900323, 'samples': 19086336, 'steps': 99407, 'loss/train': 1.4967026710510254} 08/31/2021 07:11:45 - INFO - __main__ - Step 99409: {'lr': 0.00013082847317341556, 'samples': 19086528, 'steps': 99408, 'loss/train': 0.9140313267707825} 08/31/2021 07:11:46 - INFO - __main__ - Step 99410: {'lr': 0.00013082380818152476, 'samples': 19086720, 'steps': 99409, 'loss/train': 0.414366215467453} 08/31/2021 07:11:48 - INFO - __main__ - Step 99411: {'lr': 0.0001308191432433329, 'samples': 19086912, 'steps': 99410, 'loss/train': 1.4210171699523926} 08/31/2021 07:11:49 - INFO - __main__ - Step 99412: {'lr': 0.00013081447835884208, 'samples': 19087104, 'steps': 99411, 'loss/train': 1.0086346864700317} 08/31/2021 07:11:49 - INFO - __main__ - Step 99413: {'lr': 0.00013080981352805445, 'samples': 19087296, 'steps': 99412, 'loss/train': 1.4850164651870728} 08/31/2021 07:11:49 - INFO - __main__ - Step 99414: {'lr': 0.00013080514875097208, 'samples': 19087488, 'steps': 99413, 'loss/train': 1.305564284324646} 08/31/2021 07:11:50 - INFO - __main__ - Step 99415: {'lr': 0.00013080048402759704, 'samples': 19087680, 'steps': 99414, 'loss/train': 0.7674810886383057} 08/31/2021 07:11:50 - INFO - __main__ - Step 99416: {'lr': 0.00013079581935793158, 'samples': 19087872, 'steps': 99415, 'loss/train': 0.40644362568855286} 08/31/2021 07:11:51 - INFO - __main__ - Step 99417: {'lr': 0.0001307911547419776, 'samples': 19088064, 'steps': 99416, 'loss/train': 1.607681155204773} 08/31/2021 07:11:52 - INFO - __main__ - Step 99418: {'lr': 0.00013078649017973727, 'samples': 19088256, 'steps': 99417, 'loss/train': 0.9117563366889954} 08/31/2021 07:11:52 - INFO - __main__ - Step 99419: {'lr': 0.0001307818256712127, 'samples': 19088448, 'steps': 99418, 'loss/train': 0.8980532884597778} 08/31/2021 07:11:52 - INFO - __main__ - Step 99420: {'lr': 0.00013077716121640597, 'samples': 19088640, 'steps': 99419, 'loss/train': 0.5420974493026733} 08/31/2021 07:11:53 - INFO - __main__ - Step 99421: {'lr': 0.00013077249681531927, 'samples': 19088832, 'steps': 99420, 'loss/train': 1.747511863708496} 08/31/2021 07:11:54 - INFO - __main__ - Step 99422: {'lr': 0.00013076783246795463, 'samples': 19089024, 'steps': 99421, 'loss/train': 1.005297064781189} 08/31/2021 07:11:55 - INFO - __main__ - Step 99423: {'lr': 0.00013076316817431415, 'samples': 19089216, 'steps': 99422, 'loss/train': 1.28118896484375} 08/31/2021 07:11:55 - INFO - __main__ - Step 99424: {'lr': 0.00013075850393439996, 'samples': 19089408, 'steps': 99423, 'loss/train': 1.6340925693511963} 08/31/2021 07:11:56 - INFO - __main__ - Step 99425: {'lr': 0.00013075383974821413, 'samples': 19089600, 'steps': 99424, 'loss/train': 0.3761058747768402} 08/31/2021 07:11:56 - INFO - __main__ - Step 99426: {'lr': 0.00013074917561575877, 'samples': 19089792, 'steps': 99425, 'loss/train': 0.1502372771501541} 08/31/2021 07:11:58 - INFO - __main__ - Step 99427: {'lr': 0.00013074451153703603, 'samples': 19089984, 'steps': 99426, 'loss/train': 0.6323882341384888} 08/31/2021 07:11:58 - INFO - __main__ - Step 99428: {'lr': 0.00013073984751204795, 'samples': 19090176, 'steps': 99427, 'loss/train': 0.9616451859474182} 08/31/2021 07:11:58 - INFO - __main__ - Step 99429: {'lr': 0.00013073518354079678, 'samples': 19090368, 'steps': 99428, 'loss/train': 0.9089288115501404} 08/31/2021 07:11:59 - INFO - __main__ - Step 99430: {'lr': 0.00013073051962328436, 'samples': 19090560, 'steps': 99429, 'loss/train': 0.8319503664970398} 08/31/2021 07:11:59 - INFO - __main__ - Step 99431: {'lr': 0.00013072585575951297, 'samples': 19090752, 'steps': 99430, 'loss/train': 1.111331582069397} 08/31/2021 07:12:01 - INFO - __main__ - Step 99432: {'lr': 0.0001307211919494846, 'samples': 19090944, 'steps': 99431, 'loss/train': 1.3340895175933838} 08/31/2021 07:12:01 - INFO - __main__ - Step 99433: {'lr': 0.00013071652819320146, 'samples': 19091136, 'steps': 99432, 'loss/train': 1.46607506275177} 08/31/2021 07:12:02 - INFO - __main__ - Step 99434: {'lr': 0.00013071186449066562, 'samples': 19091328, 'steps': 99433, 'loss/train': 0.8317039012908936} 08/31/2021 07:12:02 - INFO - __main__ - Step 99435: {'lr': 0.0001307072008418792, 'samples': 19091520, 'steps': 99434, 'loss/train': 0.9539635181427002} 08/31/2021 07:12:02 - INFO - __main__ - Step 99436: {'lr': 0.00013070253724684422, 'samples': 19091712, 'steps': 99435, 'loss/train': 1.4498120546340942} 08/31/2021 07:12:04 - INFO - __main__ - Step 99437: {'lr': 0.00013069787370556285, 'samples': 19091904, 'steps': 99436, 'loss/train': 0.22186492383480072} 08/31/2021 07:12:04 - INFO - __main__ - Step 99438: {'lr': 0.00013069321021803718, 'samples': 19092096, 'steps': 99437, 'loss/train': 0.9277826547622681} 08/31/2021 07:12:05 - INFO - __main__ - Step 99439: {'lr': 0.00013068854678426934, 'samples': 19092288, 'steps': 99438, 'loss/train': 1.2690050601959229} 08/31/2021 07:12:05 - INFO - __main__ - Step 99440: {'lr': 0.00013068388340426135, 'samples': 19092480, 'steps': 99439, 'loss/train': 1.3512064218521118} 08/31/2021 07:12:05 - INFO - __main__ - Step 99441: {'lr': 0.00013067922007801546, 'samples': 19092672, 'steps': 99440, 'loss/train': 1.0919777154922485} 08/31/2021 07:12:07 - INFO - __main__ - Step 99442: {'lr': 0.00013067455680553362, 'samples': 19092864, 'steps': 99441, 'loss/train': 1.2800071239471436} 08/31/2021 07:12:07 - INFO - __main__ - Step 99443: {'lr': 0.00013066989358681796, 'samples': 19093056, 'steps': 99442, 'loss/train': 0.912172794342041} 08/31/2021 07:12:08 - INFO - __main__ - Step 99444: {'lr': 0.0001306652304218706, 'samples': 19093248, 'steps': 99443, 'loss/train': 0.8822678923606873} 08/31/2021 07:12:08 - INFO - __main__ - Step 99445: {'lr': 0.00013066056731069365, 'samples': 19093440, 'steps': 99444, 'loss/train': 1.4388420581817627} 08/31/2021 07:12:08 - INFO - __main__ - Step 99446: {'lr': 0.00013065590425328922, 'samples': 19093632, 'steps': 99445, 'loss/train': 1.2790590524673462} 08/31/2021 07:12:09 - INFO - __main__ - Step 99447: {'lr': 0.00013065124124965938, 'samples': 19093824, 'steps': 99446, 'loss/train': 0.5778968334197998} 08/31/2021 07:12:10 - INFO - __main__ - Step 99448: {'lr': 0.00013064657829980626, 'samples': 19094016, 'steps': 99447, 'loss/train': 1.2593326568603516} 08/31/2021 07:12:11 - INFO - __main__ - Step 99449: {'lr': 0.00013064191540373193, 'samples': 19094208, 'steps': 99448, 'loss/train': 0.48302584886550903} 08/31/2021 07:12:11 - INFO - __main__ - Step 99450: {'lr': 0.00013063725256143852, 'samples': 19094400, 'steps': 99449, 'loss/train': 1.1725431680679321} 08/31/2021 07:12:11 - INFO - __main__ - Step 99451: {'lr': 0.00013063258977292813, 'samples': 19094592, 'steps': 99450, 'loss/train': 0.5926135778427124} 08/31/2021 07:12:12 - INFO - __main__ - Step 99452: {'lr': 0.00013062792703820292, 'samples': 19094784, 'steps': 99451, 'loss/train': 1.1241225004196167} 08/31/2021 07:12:13 - INFO - __main__ - Step 99453: {'lr': 0.00013062326435726485, 'samples': 19094976, 'steps': 99452, 'loss/train': 1.2117639780044556} 08/31/2021 07:12:14 - INFO - __main__ - Step 99454: {'lr': 0.0001306186017301161, 'samples': 19095168, 'steps': 99453, 'loss/train': 1.3020058870315552} 08/31/2021 07:12:14 - INFO - __main__ - Step 99455: {'lr': 0.00013061393915675878, 'samples': 19095360, 'steps': 99454, 'loss/train': 0.7677657008171082} 08/31/2021 07:12:14 - INFO - __main__ - Step 99456: {'lr': 0.00013060927663719496, 'samples': 19095552, 'steps': 99455, 'loss/train': 0.8584614992141724} 08/31/2021 07:12:15 - INFO - __main__ - Step 99457: {'lr': 0.00013060461417142678, 'samples': 19095744, 'steps': 99456, 'loss/train': 0.988497257232666} 08/31/2021 07:12:17 - INFO - __main__ - Step 99458: {'lr': 0.00013059995175945628, 'samples': 19095936, 'steps': 99457, 'loss/train': 1.4502815008163452} 08/31/2021 07:12:17 - INFO - __main__ - Step 99459: {'lr': 0.00013059528940128563, 'samples': 19096128, 'steps': 99458, 'loss/train': 1.3031067848205566} 08/31/2021 07:12:17 - INFO - __main__ - Step 99460: {'lr': 0.00013059062709691688, 'samples': 19096320, 'steps': 99459, 'loss/train': 0.9030387997627258} 08/31/2021 07:12:18 - INFO - __main__ - Step 99461: {'lr': 0.00013058596484635216, 'samples': 19096512, 'steps': 99460, 'loss/train': 1.1794071197509766} 08/31/2021 07:12:18 - INFO - __main__ - Step 99462: {'lr': 0.00013058130264959365, 'samples': 19096704, 'steps': 99461, 'loss/train': 1.1620503664016724} 08/31/2021 07:12:20 - INFO - __main__ - Step 99463: {'lr': 0.00013057664050664325, 'samples': 19096896, 'steps': 99462, 'loss/train': 0.1248817890882492} 08/31/2021 07:12:21 - INFO - __main__ - Step 99464: {'lr': 0.00013057197841750322, 'samples': 19097088, 'steps': 99463, 'loss/train': 1.592934250831604} 08/31/2021 07:12:21 - INFO - __main__ - Step 99465: {'lr': 0.00013056731638217556, 'samples': 19097280, 'steps': 99464, 'loss/train': 1.389295220375061} 08/31/2021 07:12:21 - INFO - __main__ - Step 99466: {'lr': 0.00013056265440066246, 'samples': 19097472, 'steps': 99465, 'loss/train': 0.44157636165618896} 08/31/2021 07:12:22 - INFO - __main__ - Step 99467: {'lr': 0.00013055799247296598, 'samples': 19097664, 'steps': 99466, 'loss/train': 1.1834931373596191} 08/31/2021 07:12:23 - INFO - __main__ - Step 99468: {'lr': 0.00013055333059908822, 'samples': 19097856, 'steps': 99467, 'loss/train': 0.8069680333137512} 08/31/2021 07:12:24 - INFO - __main__ - Step 99469: {'lr': 0.00013054866877903128, 'samples': 19098048, 'steps': 99468, 'loss/train': 1.2550591230392456} 08/31/2021 07:12:24 - INFO - __main__ - Step 99470: {'lr': 0.0001305440070127973, 'samples': 19098240, 'steps': 99469, 'loss/train': 1.1723634004592896} 08/31/2021 07:12:25 - INFO - __main__ - Step 99471: {'lr': 0.0001305393453003883, 'samples': 19098432, 'steps': 99470, 'loss/train': 1.4778488874435425} 08/31/2021 07:12:25 - INFO - __main__ - Step 99472: {'lr': 0.00013053468364180646, 'samples': 19098624, 'steps': 99471, 'loss/train': 1.1695184707641602} 08/31/2021 07:12:26 - INFO - __main__ - Step 99473: {'lr': 0.00013053002203705394, 'samples': 19098816, 'steps': 99472, 'loss/train': 1.177320122718811} 08/31/2021 07:12:27 - INFO - __main__ - Step 99474: {'lr': 0.00013052536048613263, 'samples': 19099008, 'steps': 99473, 'loss/train': 1.201941967010498} 08/31/2021 07:12:27 - INFO - __main__ - Step 99475: {'lr': 0.00013052069898904478, 'samples': 19099200, 'steps': 99474, 'loss/train': 0.48553910851478577} 08/31/2021 07:12:28 - INFO - __main__ - Step 99476: {'lr': 0.00013051603754579244, 'samples': 19099392, 'steps': 99475, 'loss/train': 1.8679534196853638} 08/31/2021 07:12:28 - INFO - __main__ - Step 99477: {'lr': 0.00013051137615637773, 'samples': 19099584, 'steps': 99476, 'loss/train': 1.0247477293014526} 08/31/2021 07:12:28 - INFO - __main__ - Step 99478: {'lr': 0.00013050671482080277, 'samples': 19099776, 'steps': 99477, 'loss/train': 0.9032413363456726} 08/31/2021 07:12:30 - INFO - __main__ - Step 99479: {'lr': 0.00013050205353906964, 'samples': 19099968, 'steps': 99478, 'loss/train': 0.9390671253204346} 08/31/2021 07:12:30 - INFO - __main__ - Step 99480: {'lr': 0.0001304973923111804, 'samples': 19100160, 'steps': 99479, 'loss/train': 0.5236740112304688} 08/31/2021 07:12:31 - INFO - __main__ - Step 99481: {'lr': 0.00013049273113713723, 'samples': 19100352, 'steps': 99480, 'loss/train': 0.17375415563583374} 08/31/2021 07:12:31 - INFO - __main__ - Step 99482: {'lr': 0.00013048807001694217, 'samples': 19100544, 'steps': 99481, 'loss/train': 1.162845253944397} 08/31/2021 07:12:31 - INFO - __main__ - Step 99483: {'lr': 0.00013048340895059735, 'samples': 19100736, 'steps': 99482, 'loss/train': 0.8447892665863037} 08/31/2021 07:12:33 - INFO - __main__ - Step 99484: {'lr': 0.00013047874793810493, 'samples': 19100928, 'steps': 99483, 'loss/train': 1.1345524787902832} 08/31/2021 07:12:34 - INFO - __main__ - Step 99485: {'lr': 0.0001304740869794669, 'samples': 19101120, 'steps': 99484, 'loss/train': 0.5583141446113586} 08/31/2021 07:12:34 - INFO - __main__ - Step 99486: {'lr': 0.00013046942607468538, 'samples': 19101312, 'steps': 99485, 'loss/train': 1.5438131093978882} 08/31/2021 07:12:34 - INFO - __main__ - Step 99487: {'lr': 0.0001304647652237625, 'samples': 19101504, 'steps': 99486, 'loss/train': 0.7014273405075073} 08/31/2021 07:12:35 - INFO - __main__ - Step 99488: {'lr': 0.0001304601044267003, 'samples': 19101696, 'steps': 99487, 'loss/train': 1.4251670837402344} 08/31/2021 07:12:36 - INFO - __main__ - Step 99489: {'lr': 0.000130455443683501, 'samples': 19101888, 'steps': 99488, 'loss/train': 1.3194259405136108} 08/31/2021 07:12:37 - INFO - __main__ - Step 99490: {'lr': 0.00013045078299416657, 'samples': 19102080, 'steps': 99489, 'loss/train': 1.038906216621399} 08/31/2021 07:12:37 - INFO - __main__ - Step 99491: {'lr': 0.00013044612235869923, 'samples': 19102272, 'steps': 99490, 'loss/train': 1.65194833278656} 08/31/2021 07:12:38 - INFO - __main__ - Step 99492: {'lr': 0.00013044146177710098, 'samples': 19102464, 'steps': 99491, 'loss/train': 1.0317810773849487} 08/31/2021 07:12:38 - INFO - __main__ - Step 99493: {'lr': 0.00013043680124937397, 'samples': 19102656, 'steps': 99492, 'loss/train': 1.0115275382995605} 08/31/2021 07:12:39 - INFO - __main__ - Step 99494: {'lr': 0.00013043214077552035, 'samples': 19102848, 'steps': 99493, 'loss/train': 1.628556489944458} 08/31/2021 07:12:40 - INFO - __main__ - Step 99495: {'lr': 0.0001304274803555421, 'samples': 19103040, 'steps': 99494, 'loss/train': 0.9229342937469482} 08/31/2021 07:12:40 - INFO - __main__ - Step 99496: {'lr': 0.0001304228199894415, 'samples': 19103232, 'steps': 99495, 'loss/train': 1.1400425434112549} 08/31/2021 07:12:40 - INFO - __main__ - Step 99497: {'lr': 0.00013041815967722043, 'samples': 19103424, 'steps': 99496, 'loss/train': 1.2099665403366089} 08/31/2021 07:12:41 - INFO - __main__ - Step 99498: {'lr': 0.0001304134994188811, 'samples': 19103616, 'steps': 99497, 'loss/train': 1.0942022800445557} 08/31/2021 07:12:43 - INFO - __main__ - Step 99499: {'lr': 0.0001304088392144256, 'samples': 19103808, 'steps': 99498, 'loss/train': 1.0345399379730225} 08/31/2021 07:12:43 - INFO - __main__ - Step 99500: {'lr': 0.00013040417906385598, 'samples': 19104000, 'steps': 99499, 'loss/train': 0.9736818671226501} 08/31/2021 07:12:44 - INFO - __main__ - Step 99501: {'lr': 0.00013039951896717445, 'samples': 19104192, 'steps': 99500, 'loss/train': 1.0448771715164185} 08/31/2021 07:12:44 - INFO - __main__ - Step 99502: {'lr': 0.00013039485892438305, 'samples': 19104384, 'steps': 99501, 'loss/train': 0.06286333501338959} 08/31/2021 07:12:44 - INFO - __main__ - Step 99503: {'lr': 0.00013039019893548387, 'samples': 19104576, 'steps': 99502, 'loss/train': 0.6299185156822205} 08/31/2021 07:12:46 - INFO - __main__ - Step 99504: {'lr': 0.000130385539000479, 'samples': 19104768, 'steps': 99503, 'loss/train': 1.8145979642868042} 08/31/2021 07:12:46 - INFO - __main__ - Step 99505: {'lr': 0.00013038087911937057, 'samples': 19104960, 'steps': 99504, 'loss/train': 0.9145816564559937} 08/31/2021 07:12:46 - INFO - __main__ - Step 99506: {'lr': 0.0001303762192921607, 'samples': 19105152, 'steps': 99505, 'loss/train': 1.0548427104949951} 08/31/2021 07:12:47 - INFO - __main__ - Step 99507: {'lr': 0.00013037155951885145, 'samples': 19105344, 'steps': 99506, 'loss/train': 1.202152967453003} 08/31/2021 07:12:47 - INFO - __main__ - Step 99508: {'lr': 0.00013036689979944492, 'samples': 19105536, 'steps': 99507, 'loss/train': 0.5178483128547668} 08/31/2021 07:12:49 - INFO - __main__ - Step 99509: {'lr': 0.00013036224013394322, 'samples': 19105728, 'steps': 99508, 'loss/train': 0.7879159450531006} 08/31/2021 07:12:49 - INFO - __main__ - Step 99510: {'lr': 0.00013035758052234853, 'samples': 19105920, 'steps': 99509, 'loss/train': 1.3085436820983887} 08/31/2021 07:12:49 - INFO - __main__ - Step 99511: {'lr': 0.00013035292096466277, 'samples': 19106112, 'steps': 99510, 'loss/train': 0.7097960114479065} 08/31/2021 07:12:50 - INFO - __main__ - Step 99512: {'lr': 0.0001303482614608882, 'samples': 19106304, 'steps': 99511, 'loss/train': 1.2931476831436157} 08/31/2021 07:12:50 - INFO - __main__ - Step 99513: {'lr': 0.0001303436020110268, 'samples': 19106496, 'steps': 99512, 'loss/train': 1.3560634851455688} 08/31/2021 07:12:52 - INFO - __main__ - Step 99514: {'lr': 0.00013033894261508071, 'samples': 19106688, 'steps': 99513, 'loss/train': 1.5077800750732422} 08/31/2021 07:12:52 - INFO - __main__ - Step 99515: {'lr': 0.00013033428327305209, 'samples': 19106880, 'steps': 99514, 'loss/train': 1.0002048015594482} 08/31/2021 07:12:53 - INFO - __main__ - Step 99516: {'lr': 0.00013032962398494297, 'samples': 19107072, 'steps': 99515, 'loss/train': 0.9601036310195923} 08/31/2021 07:12:53 - INFO - __main__ - Step 99517: {'lr': 0.0001303249647507555, 'samples': 19107264, 'steps': 99516, 'loss/train': 0.8936942219734192} 08/31/2021 07:12:53 - INFO - __main__ - Step 99518: {'lr': 0.00013032030557049172, 'samples': 19107456, 'steps': 99517, 'loss/train': 0.9931618571281433} 08/31/2021 07:12:54 - INFO - __main__ - Step 99519: {'lr': 0.00013031564644415378, 'samples': 19107648, 'steps': 99518, 'loss/train': 0.6515316367149353} 08/31/2021 07:12:56 - INFO - __main__ - Step 99520: {'lr': 0.00013031098737174374, 'samples': 19107840, 'steps': 99519, 'loss/train': 1.4394840002059937} 08/31/2021 07:12:56 - INFO - __main__ - Step 99521: {'lr': 0.00013030632835326378, 'samples': 19108032, 'steps': 99520, 'loss/train': 1.1312730312347412} 08/31/2021 07:12:57 - INFO - __main__ - Step 99522: {'lr': 0.0001303016693887159, 'samples': 19108224, 'steps': 99521, 'loss/train': 1.1223585605621338} 08/31/2021 07:12:57 - INFO - __main__ - Step 99523: {'lr': 0.00013029701047810233, 'samples': 19108416, 'steps': 99522, 'loss/train': 1.0634465217590332} 08/31/2021 07:12:57 - INFO - __main__ - Step 99524: {'lr': 0.000130292351621425, 'samples': 19108608, 'steps': 99523, 'loss/train': 1.5577493906021118} 08/31/2021 07:12:59 - INFO - __main__ - Step 99525: {'lr': 0.00013028769281868608, 'samples': 19108800, 'steps': 99524, 'loss/train': 1.4926127195358276} 08/31/2021 07:12:59 - INFO - __main__ - Step 99526: {'lr': 0.00013028303406988767, 'samples': 19108992, 'steps': 99525, 'loss/train': 0.8288177251815796} 08/31/2021 07:13:00 - INFO - __main__ - Step 99527: {'lr': 0.0001302783753750319, 'samples': 19109184, 'steps': 99526, 'loss/train': 0.9305577874183655} 08/31/2021 07:13:00 - INFO - __main__ - Step 99528: {'lr': 0.00013027371673412087, 'samples': 19109376, 'steps': 99527, 'loss/train': 1.405616283416748} 08/31/2021 07:13:00 - INFO - __main__ - Step 99529: {'lr': 0.00013026905814715663, 'samples': 19109568, 'steps': 99528, 'loss/train': 1.3539550304412842} 08/31/2021 07:13:02 - INFO - __main__ - Step 99530: {'lr': 0.00013026439961414128, 'samples': 19109760, 'steps': 99529, 'loss/train': 1.6893415451049805} 08/31/2021 07:13:02 - INFO - __main__ - Step 99531: {'lr': 0.00013025974113507695, 'samples': 19109952, 'steps': 99530, 'loss/train': 1.6947230100631714} 08/31/2021 07:13:02 - INFO - __main__ - Step 99532: {'lr': 0.00013025508270996574, 'samples': 19110144, 'steps': 99531, 'loss/train': 1.7025150060653687} 08/31/2021 07:13:03 - INFO - __main__ - Step 99533: {'lr': 0.00013025042433880977, 'samples': 19110336, 'steps': 99532, 'loss/train': 0.45846349000930786} 08/31/2021 07:13:03 - INFO - __main__ - Step 99534: {'lr': 0.0001302457660216111, 'samples': 19110528, 'steps': 99533, 'loss/train': 0.976446807384491} 08/31/2021 07:13:05 - INFO - __main__ - Step 99535: {'lr': 0.0001302411077583718, 'samples': 19110720, 'steps': 99534, 'loss/train': 1.1983317136764526} 08/31/2021 07:13:05 - INFO - __main__ - Step 99536: {'lr': 0.00013023644954909404, 'samples': 19110912, 'steps': 99535, 'loss/train': 1.5886656045913696} 08/31/2021 07:13:06 - INFO - __main__ - Step 99537: {'lr': 0.00013023179139377998, 'samples': 19111104, 'steps': 99536, 'loss/train': 1.2359024286270142} 08/31/2021 07:13:06 - INFO - __main__ - Step 99538: {'lr': 0.00013022713329243152, 'samples': 19111296, 'steps': 99537, 'loss/train': 0.7664893865585327} 08/31/2021 07:13:06 - INFO - __main__ - Step 99539: {'lr': 0.0001302224752450509, 'samples': 19111488, 'steps': 99538, 'loss/train': 1.693583607673645} 08/31/2021 07:13:08 - INFO - __main__ - Step 99540: {'lr': 0.00013021781725164016, 'samples': 19111680, 'steps': 99539, 'loss/train': 0.975797712802887} 08/31/2021 07:13:09 - INFO - __main__ - Step 99541: {'lr': 0.00013021315931220143, 'samples': 19111872, 'steps': 99540, 'loss/train': 1.2180489301681519} 08/31/2021 07:13:09 - INFO - __main__ - Step 99542: {'lr': 0.00013020850142673679, 'samples': 19112064, 'steps': 99541, 'loss/train': 1.6531702280044556} 08/31/2021 07:13:09 - INFO - __main__ - Step 99543: {'lr': 0.00013020384359524833, 'samples': 19112256, 'steps': 99542, 'loss/train': 0.5229354500770569} 08/31/2021 07:13:10 - INFO - __main__ - Step 99544: {'lr': 0.0001301991858177382, 'samples': 19112448, 'steps': 99543, 'loss/train': 1.3001126050949097} 08/31/2021 07:13:10 - INFO - __main__ - Step 99545: {'lr': 0.0001301945280942085, 'samples': 19112640, 'steps': 99544, 'loss/train': 1.2956953048706055} 08/31/2021 07:13:11 - INFO - __main__ - Step 99546: {'lr': 0.00013018987042466123, 'samples': 19112832, 'steps': 99545, 'loss/train': 0.9875297546386719} 08/31/2021 07:13:12 - INFO - __main__ - Step 99547: {'lr': 0.00013018521280909863, 'samples': 19113024, 'steps': 99546, 'loss/train': 0.9678457379341125} 08/31/2021 07:13:12 - INFO - __main__ - Step 99548: {'lr': 0.00013018055524752266, 'samples': 19113216, 'steps': 99547, 'loss/train': 1.46924889087677} 08/31/2021 07:13:13 - INFO - __main__ - Step 99549: {'lr': 0.00013017589773993548, 'samples': 19113408, 'steps': 99548, 'loss/train': 1.395107626914978} 08/31/2021 07:13:13 - INFO - __main__ - Step 99550: {'lr': 0.00013017124028633933, 'samples': 19113600, 'steps': 99549, 'loss/train': 1.0853939056396484} 08/31/2021 07:13:15 - INFO - __main__ - Step 99551: {'lr': 0.00013016658288673606, 'samples': 19113792, 'steps': 99550, 'loss/train': 1.1646835803985596} 08/31/2021 07:13:15 - INFO - __main__ - Step 99552: {'lr': 0.00013016192554112787, 'samples': 19113984, 'steps': 99551, 'loss/train': 1.030179738998413} 08/31/2021 07:13:16 - INFO - __main__ - Step 99553: {'lr': 0.0001301572682495169, 'samples': 19114176, 'steps': 99552, 'loss/train': 1.2108606100082397} 08/31/2021 07:13:16 - INFO - __main__ - Step 99554: {'lr': 0.00013015261101190519, 'samples': 19114368, 'steps': 99553, 'loss/train': 0.662564754486084} 08/31/2021 07:13:16 - INFO - __main__ - Step 99555: {'lr': 0.00013014795382829486, 'samples': 19114560, 'steps': 99554, 'loss/train': 2.979017496109009} 08/31/2021 07:13:17 - INFO - __main__ - Step 99556: {'lr': 0.00013014329669868802, 'samples': 19114752, 'steps': 99555, 'loss/train': 0.4000747799873352} 08/31/2021 07:13:17 - INFO - __main__ - Step 99557: {'lr': 0.00013013863962308675, 'samples': 19114944, 'steps': 99556, 'loss/train': 0.04347065091133118} 08/31/2021 07:13:18 - INFO - __main__ - Step 99558: {'lr': 0.00013013398260149317, 'samples': 19115136, 'steps': 99557, 'loss/train': 1.2132995128631592} 08/31/2021 07:13:19 - INFO - __main__ - Step 99559: {'lr': 0.00013012932563390934, 'samples': 19115328, 'steps': 99558, 'loss/train': 1.236556887626648} 08/31/2021 07:13:19 - INFO - __main__ - Step 99560: {'lr': 0.0001301246687203374, 'samples': 19115520, 'steps': 99559, 'loss/train': 1.505846619606018} 08/31/2021 07:13:20 - INFO - __main__ - Step 99561: {'lr': 0.00013012001186077946, 'samples': 19115712, 'steps': 99560, 'loss/train': 1.4155253171920776} 08/31/2021 07:13:20 - INFO - __main__ - Step 99562: {'lr': 0.00013011535505523758, 'samples': 19115904, 'steps': 99561, 'loss/train': 0.859171450138092} 08/31/2021 07:13:22 - INFO - __main__ - Step 99563: {'lr': 0.00013011069830371397, 'samples': 19116096, 'steps': 99562, 'loss/train': 1.5488930940628052} 08/31/2021 07:13:22 - INFO - __main__ - Step 99564: {'lr': 0.00013010604160621053, 'samples': 19116288, 'steps': 99563, 'loss/train': 1.4356147050857544} 08/31/2021 07:13:22 - INFO - __main__ - Step 99565: {'lr': 0.00013010138496272945, 'samples': 19116480, 'steps': 99564, 'loss/train': 1.119185447692871} 08/31/2021 07:13:23 - INFO - __main__ - Step 99566: {'lr': 0.00013009672837327287, 'samples': 19116672, 'steps': 99565, 'loss/train': 1.5445102453231812} 08/31/2021 07:13:23 - INFO - __main__ - Step 99567: {'lr': 0.00013009207183784278, 'samples': 19116864, 'steps': 99566, 'loss/train': 0.9082179069519043} 08/31/2021 07:13:25 - INFO - __main__ - Step 99568: {'lr': 0.0001300874153564414, 'samples': 19117056, 'steps': 99567, 'loss/train': 1.2719429731369019} 08/31/2021 07:13:25 - INFO - __main__ - Step 99569: {'lr': 0.0001300827589290708, 'samples': 19117248, 'steps': 99568, 'loss/train': 0.9412938952445984} 08/31/2021 07:13:26 - INFO - __main__ - Step 99570: {'lr': 0.00013007810255573303, 'samples': 19117440, 'steps': 99569, 'loss/train': 1.1251927614212036} 08/31/2021 07:13:26 - INFO - __main__ - Step 99571: {'lr': 0.00013007344623643019, 'samples': 19117632, 'steps': 99570, 'loss/train': 0.3540344536304474} 08/31/2021 07:13:26 - INFO - __main__ - Step 99572: {'lr': 0.00013006878997116444, 'samples': 19117824, 'steps': 99571, 'loss/train': 1.3239595890045166} 08/31/2021 07:13:28 - INFO - __main__ - Step 99573: {'lr': 0.00013006413375993785, 'samples': 19118016, 'steps': 99572, 'loss/train': 0.7476842999458313} 08/31/2021 07:13:29 - INFO - __main__ - Step 99574: {'lr': 0.0001300594776027525, 'samples': 19118208, 'steps': 99573, 'loss/train': 1.307913064956665} 08/31/2021 07:13:29 - INFO - __main__ - Step 99575: {'lr': 0.0001300548214996105, 'samples': 19118400, 'steps': 99574, 'loss/train': 1.4971308708190918} 08/31/2021 07:13:29 - INFO - __main__ - Step 99576: {'lr': 0.00013005016545051396, 'samples': 19118592, 'steps': 99575, 'loss/train': 1.5774048566818237} 08/31/2021 07:13:30 - INFO - __main__ - Step 99577: {'lr': 0.00013004550945546503, 'samples': 19118784, 'steps': 99576, 'loss/train': 1.8767083883285522} 08/31/2021 07:13:31 - INFO - __main__ - Step 99578: {'lr': 0.00013004085351446564, 'samples': 19118976, 'steps': 99577, 'loss/train': 2.6896860599517822} 08/31/2021 07:13:32 - INFO - __main__ - Step 99579: {'lr': 0.00013003619762751804, 'samples': 19119168, 'steps': 99578, 'loss/train': 1.3381445407867432} 08/31/2021 07:13:32 - INFO - __main__ - Step 99580: {'lr': 0.00013003154179462424, 'samples': 19119360, 'steps': 99579, 'loss/train': 1.1296045780181885} 08/31/2021 07:13:33 - INFO - __main__ - Step 99581: {'lr': 0.0001300268860157864, 'samples': 19119552, 'steps': 99580, 'loss/train': 0.8775065541267395} 08/31/2021 07:13:33 - INFO - __main__ - Step 99582: {'lr': 0.00013002223029100657, 'samples': 19119744, 'steps': 99581, 'loss/train': 1.3370813131332397} 08/31/2021 07:13:33 - INFO - __main__ - Step 99583: {'lr': 0.00013001757462028688, 'samples': 19119936, 'steps': 99582, 'loss/train': 2.530108690261841} 08/31/2021 07:13:35 - INFO - __main__ - Step 99584: {'lr': 0.00013001291900362945, 'samples': 19120128, 'steps': 99583, 'loss/train': 0.8433623313903809} 08/31/2021 07:13:36 - INFO - __main__ - Step 99585: {'lr': 0.00013000826344103627, 'samples': 19120320, 'steps': 99584, 'loss/train': 1.2726413011550903} 08/31/2021 07:13:36 - INFO - __main__ - Step 99586: {'lr': 0.0001300036079325096, 'samples': 19120512, 'steps': 99585, 'loss/train': 0.09673666208982468} 08/31/2021 07:13:36 - INFO - __main__ - Step 99587: {'lr': 0.00012999895247805138, 'samples': 19120704, 'steps': 99586, 'loss/train': 0.20737893879413605} 08/31/2021 07:13:37 - INFO - __main__ - Step 99588: {'lr': 0.00012999429707766382, 'samples': 19120896, 'steps': 99587, 'loss/train': 0.9518918991088867} 08/31/2021 07:13:37 - INFO - __main__ - Step 99589: {'lr': 0.00012998964173134897, 'samples': 19121088, 'steps': 99588, 'loss/train': 1.7410601377487183} 08/31/2021 07:13:39 - INFO - __main__ - Step 99590: {'lr': 0.00012998498643910906, 'samples': 19121280, 'steps': 99589, 'loss/train': 1.1900306940078735} 08/31/2021 07:13:39 - INFO - __main__ - Step 99591: {'lr': 0.00012998033120094593, 'samples': 19121472, 'steps': 99590, 'loss/train': 2.13830828666687} 08/31/2021 07:13:40 - INFO - __main__ - Step 99592: {'lr': 0.00012997567601686182, 'samples': 19121664, 'steps': 99591, 'loss/train': 1.1598066091537476} 08/31/2021 07:13:40 - INFO - __main__ - Step 99593: {'lr': 0.00012997102088685883, 'samples': 19121856, 'steps': 99592, 'loss/train': 1.301230549812317} 08/31/2021 07:13:40 - INFO - __main__ - Step 99594: {'lr': 0.00012996636581093904, 'samples': 19122048, 'steps': 99593, 'loss/train': 1.240021824836731} 08/31/2021 07:13:42 - INFO - __main__ - Step 99595: {'lr': 0.00012996171078910457, 'samples': 19122240, 'steps': 99594, 'loss/train': 0.12408119440078735} 08/31/2021 07:13:42 - INFO - __main__ - Step 99596: {'lr': 0.00012995705582135748, 'samples': 19122432, 'steps': 99595, 'loss/train': 1.4355113506317139} 08/31/2021 07:13:43 - INFO - __main__ - Step 99597: {'lr': 0.00012995240090769988, 'samples': 19122624, 'steps': 99596, 'loss/train': 0.5184643268585205} 08/31/2021 07:13:43 - INFO - __main__ - Step 99598: {'lr': 0.00012994774604813386, 'samples': 19122816, 'steps': 99597, 'loss/train': 1.215983271598816} 08/31/2021 07:13:43 - INFO - __main__ - Step 99599: {'lr': 0.00012994309124266158, 'samples': 19123008, 'steps': 99598, 'loss/train': 0.7565485835075378} 08/31/2021 07:13:44 - INFO - __main__ - Step 99600: {'lr': 0.00012993843649128505, 'samples': 19123200, 'steps': 99599, 'loss/train': 1.109330177307129} 08/31/2021 07:13:45 - INFO - __main__ - Step 99601: {'lr': 0.00012993378179400645, 'samples': 19123392, 'steps': 99600, 'loss/train': 0.561823308467865} 08/31/2021 07:13:46 - INFO - __main__ - Step 99602: {'lr': 0.0001299291271508278, 'samples': 19123584, 'steps': 99601, 'loss/train': 1.0702913999557495} 08/31/2021 07:13:46 - INFO - __main__ - Step 99603: {'lr': 0.00012992447256175124, 'samples': 19123776, 'steps': 99602, 'loss/train': 1.1164512634277344} 08/31/2021 07:13:46 - INFO - __main__ - Step 99604: {'lr': 0.00012991981802677898, 'samples': 19123968, 'steps': 99603, 'loss/train': 1.1584635972976685} 08/31/2021 07:13:47 - INFO - __main__ - Step 99605: {'lr': 0.00012991516354591287, 'samples': 19124160, 'steps': 99604, 'loss/train': 1.4313695430755615} 08/31/2021 07:13:48 - INFO - __main__ - Step 99606: {'lr': 0.00012991050911915513, 'samples': 19124352, 'steps': 99605, 'loss/train': 0.9766532778739929} 08/31/2021 07:13:49 - INFO - __main__ - Step 99607: {'lr': 0.0001299058547465079, 'samples': 19124544, 'steps': 99606, 'loss/train': 1.205605149269104} 08/31/2021 07:13:49 - INFO - __main__ - Step 99608: {'lr': 0.0001299012004279732, 'samples': 19124736, 'steps': 99607, 'loss/train': 1.0999791622161865} 08/31/2021 07:13:50 - INFO - __main__ - Step 99609: {'lr': 0.00012989654616355316, 'samples': 19124928, 'steps': 99608, 'loss/train': 1.1079577207565308} 08/31/2021 07:13:50 - INFO - __main__ - Step 99610: {'lr': 0.00012989189195324993, 'samples': 19125120, 'steps': 99609, 'loss/train': 1.2780635356903076} 08/31/2021 07:13:52 - INFO - __main__ - Step 99611: {'lr': 0.00012988723779706554, 'samples': 19125312, 'steps': 99610, 'loss/train': 1.4705301523208618} 08/31/2021 07:13:52 - INFO - __main__ - Step 99612: {'lr': 0.0001298825836950021, 'samples': 19125504, 'steps': 99611, 'loss/train': 0.05081605911254883} 08/31/2021 07:13:52 - INFO - __main__ - Step 99613: {'lr': 0.00012987792964706175, 'samples': 19125696, 'steps': 99612, 'loss/train': 1.1713088750839233} 08/31/2021 07:13:53 - INFO - __main__ - Step 99614: {'lr': 0.0001298732756532465, 'samples': 19125888, 'steps': 99613, 'loss/train': 1.043382167816162} 08/31/2021 07:13:53 - INFO - __main__ - Step 99615: {'lr': 0.0001298686217135585, 'samples': 19126080, 'steps': 99614, 'loss/train': 1.468504786491394} 08/31/2021 07:13:55 - INFO - __main__ - Step 99616: {'lr': 0.00012986396782799987, 'samples': 19126272, 'steps': 99615, 'loss/train': 1.521830439567566} 08/31/2021 07:13:55 - INFO - __main__ - Step 99617: {'lr': 0.00012985931399657277, 'samples': 19126464, 'steps': 99616, 'loss/train': 1.0613820552825928} 08/31/2021 07:13:55 - INFO - __main__ - Step 99618: {'lr': 0.00012985466021927912, 'samples': 19126656, 'steps': 99617, 'loss/train': 0.9138532876968384} 08/31/2021 07:13:56 - INFO - __main__ - Step 99619: {'lr': 0.00012985000649612112, 'samples': 19126848, 'steps': 99618, 'loss/train': 0.8903195261955261} 08/31/2021 07:13:56 - INFO - __main__ - Step 99620: {'lr': 0.0001298453528271008, 'samples': 19127040, 'steps': 99619, 'loss/train': 1.6260021924972534} 08/31/2021 07:13:58 - INFO - __main__ - Step 99621: {'lr': 0.00012984069921222037, 'samples': 19127232, 'steps': 99620, 'loss/train': 0.08464352041482925} 08/31/2021 07:13:58 - INFO - __main__ - Step 99622: {'lr': 0.00012983604565148182, 'samples': 19127424, 'steps': 99621, 'loss/train': 4.820627689361572} 08/31/2021 07:13:58 - INFO - __main__ - Step 99623: {'lr': 0.00012983139214488732, 'samples': 19127616, 'steps': 99622, 'loss/train': 0.7793408632278442} 08/31/2021 07:13:59 - INFO - __main__ - Step 99624: {'lr': 0.00012982673869243894, 'samples': 19127808, 'steps': 99623, 'loss/train': 1.1585643291473389} 08/31/2021 07:13:59 - INFO - __main__ - Step 99625: {'lr': 0.00012982208529413875, 'samples': 19128000, 'steps': 99624, 'loss/train': 1.5212286710739136} 08/31/2021 07:14:01 - INFO - __main__ - Step 99626: {'lr': 0.00012981743194998891, 'samples': 19128192, 'steps': 99625, 'loss/train': 0.6945102214813232} 08/31/2021 07:14:01 - INFO - __main__ - Step 99627: {'lr': 0.00012981277865999145, 'samples': 19128384, 'steps': 99626, 'loss/train': 1.4430903196334839} 08/31/2021 07:14:01 - INFO - __main__ - Step 99628: {'lr': 0.0001298081254241485, 'samples': 19128576, 'steps': 99627, 'loss/train': 0.0661759078502655} 08/31/2021 07:14:02 - INFO - __main__ - Step 99629: {'lr': 0.0001298034722424622, 'samples': 19128768, 'steps': 99628, 'loss/train': 1.2501877546310425} 08/31/2021 07:14:02 - INFO - __main__ - Step 99630: {'lr': 0.00012979881911493455, 'samples': 19128960, 'steps': 99629, 'loss/train': 1.0696507692337036} 08/31/2021 07:14:04 - INFO - __main__ - Step 99631: {'lr': 0.0001297941660415678, 'samples': 19129152, 'steps': 99630, 'loss/train': 0.03545232489705086} 08/31/2021 07:14:05 - INFO - __main__ - Step 99632: {'lr': 0.00012978951302236385, 'samples': 19129344, 'steps': 99631, 'loss/train': 0.7050430178642273} 08/31/2021 07:14:05 - INFO - __main__ - Step 99633: {'lr': 0.00012978486005732492, 'samples': 19129536, 'steps': 99632, 'loss/train': 1.280219316482544} 08/31/2021 07:14:05 - INFO - __main__ - Step 99634: {'lr': 0.00012978020714645306, 'samples': 19129728, 'steps': 99633, 'loss/train': 1.2977290153503418} 08/31/2021 07:14:06 - INFO - __main__ - Step 99635: {'lr': 0.00012977555428975035, 'samples': 19129920, 'steps': 99634, 'loss/train': 0.7946133613586426} 08/31/2021 07:14:06 - INFO - __main__ - Step 99636: {'lr': 0.00012977090148721897, 'samples': 19130112, 'steps': 99635, 'loss/train': 0.9551418423652649} 08/31/2021 07:14:08 - INFO - __main__ - Step 99637: {'lr': 0.00012976624873886096, 'samples': 19130304, 'steps': 99636, 'loss/train': 1.7239423990249634} 08/31/2021 07:14:08 - INFO - __main__ - Step 99638: {'lr': 0.00012976159604467837, 'samples': 19130496, 'steps': 99637, 'loss/train': 0.6911917924880981} 08/31/2021 07:14:08 - INFO - __main__ - Step 99639: {'lr': 0.00012975694340467341, 'samples': 19130688, 'steps': 99638, 'loss/train': 0.7603223919868469} 08/31/2021 07:14:09 - INFO - __main__ - Step 99640: {'lr': 0.0001297522908188481, 'samples': 19130880, 'steps': 99639, 'loss/train': 1.9311933517456055} 08/31/2021 07:14:09 - INFO - __main__ - Step 99641: {'lr': 0.00012974763828720455, 'samples': 19131072, 'steps': 99640, 'loss/train': 1.1290900707244873} 08/31/2021 07:14:11 - INFO - __main__ - Step 99642: {'lr': 0.00012974298580974484, 'samples': 19131264, 'steps': 99641, 'loss/train': 1.2645047903060913} 08/31/2021 07:14:11 - INFO - __main__ - Step 99643: {'lr': 0.00012973833338647108, 'samples': 19131456, 'steps': 99642, 'loss/train': 1.284048080444336} 08/31/2021 07:14:12 - INFO - __main__ - Step 99644: {'lr': 0.0001297336810173855, 'samples': 19131648, 'steps': 99643, 'loss/train': 0.8337318301200867} 08/31/2021 07:14:12 - INFO - __main__ - Step 99645: {'lr': 0.00012972902870248996, 'samples': 19131840, 'steps': 99644, 'loss/train': 1.0973684787750244} 08/31/2021 07:14:12 - INFO - __main__ - Step 99646: {'lr': 0.00012972437644178666, 'samples': 19132032, 'steps': 99645, 'loss/train': 0.9603807926177979} 08/31/2021 07:14:14 - INFO - __main__ - Step 99647: {'lr': 0.0001297197242352777, 'samples': 19132224, 'steps': 99646, 'loss/train': 0.8542397022247314} 08/31/2021 07:14:14 - INFO - __main__ - Step 99648: {'lr': 0.00012971507208296517, 'samples': 19132416, 'steps': 99647, 'loss/train': 1.4806257486343384} 08/31/2021 07:14:15 - INFO - __main__ - Step 99649: {'lr': 0.0001297104199848512, 'samples': 19132608, 'steps': 99648, 'loss/train': 0.7157195806503296} 08/31/2021 07:14:15 - INFO - __main__ - Step 99650: {'lr': 0.00012970576794093784, 'samples': 19132800, 'steps': 99649, 'loss/train': 0.5841606259346008} 08/31/2021 07:14:15 - INFO - __main__ - Step 99651: {'lr': 0.0001297011159512272, 'samples': 19132992, 'steps': 99650, 'loss/train': 0.749714195728302} 08/31/2021 07:14:17 - INFO - __main__ - Step 99652: {'lr': 0.00012969646401572138, 'samples': 19133184, 'steps': 99651, 'loss/train': 1.019858479499817} 08/31/2021 07:14:17 - INFO - __main__ - Step 99653: {'lr': 0.00012969181213442249, 'samples': 19133376, 'steps': 99652, 'loss/train': 1.092071771621704} 08/31/2021 07:14:18 - INFO - __main__ - Step 99654: {'lr': 0.00012968716030733261, 'samples': 19133568, 'steps': 99653, 'loss/train': 1.0770000219345093} 08/31/2021 07:14:18 - INFO - __main__ - Step 99655: {'lr': 0.00012968250853445383, 'samples': 19133760, 'steps': 99654, 'loss/train': 1.3979840278625488} 08/31/2021 07:14:18 - INFO - __main__ - Step 99656: {'lr': 0.00012967785681578824, 'samples': 19133952, 'steps': 99655, 'loss/train': 0.2889506220817566} 08/31/2021 07:14:20 - INFO - __main__ - Step 99657: {'lr': 0.00012967320515133796, 'samples': 19134144, 'steps': 99656, 'loss/train': 1.5606462955474854} 08/31/2021 07:14:20 - INFO - __main__ - Step 99658: {'lr': 0.00012966855354110517, 'samples': 19134336, 'steps': 99657, 'loss/train': 0.5338023900985718} 08/31/2021 07:14:21 - INFO - __main__ - Step 99659: {'lr': 0.0001296639019850918, 'samples': 19134528, 'steps': 99658, 'loss/train': 0.306400865316391} 08/31/2021 07:14:21 - INFO - __main__ - Step 99660: {'lr': 0.00012965925048330002, 'samples': 19134720, 'steps': 99659, 'loss/train': 1.6021440029144287} 08/31/2021 07:14:21 - INFO - __main__ - Step 99661: {'lr': 0.0001296545990357319, 'samples': 19134912, 'steps': 99660, 'loss/train': 0.6377342939376831} 08/31/2021 07:14:22 - INFO - __main__ - Step 99662: {'lr': 0.00012964994764238957, 'samples': 19135104, 'steps': 99661, 'loss/train': 1.1166720390319824} 08/31/2021 07:14:23 - INFO - __main__ - Step 99663: {'lr': 0.00012964529630327514, 'samples': 19135296, 'steps': 99662, 'loss/train': 1.4568078517913818} 08/31/2021 07:14:24 - INFO - __main__ - Step 99664: {'lr': 0.00012964064501839068, 'samples': 19135488, 'steps': 99663, 'loss/train': 1.1533958911895752} 08/31/2021 07:14:24 - INFO - __main__ - Step 99665: {'lr': 0.00012963599378773826, 'samples': 19135680, 'steps': 99664, 'loss/train': 1.2826858758926392} 08/31/2021 07:14:24 - INFO - __main__ - Step 99666: {'lr': 0.00012963134261132002, 'samples': 19135872, 'steps': 99665, 'loss/train': 1.2066097259521484} 08/31/2021 07:14:25 - INFO - __main__ - Step 99667: {'lr': 0.00012962669148913804, 'samples': 19136064, 'steps': 99666, 'loss/train': 0.8995120525360107} 08/31/2021 07:14:26 - INFO - __main__ - Step 99668: {'lr': 0.0001296220404211944, 'samples': 19136256, 'steps': 99667, 'loss/train': 1.12932288646698} 08/31/2021 07:14:27 - INFO - __main__ - Step 99669: {'lr': 0.00012961738940749123, 'samples': 19136448, 'steps': 99668, 'loss/train': 0.41285786032676697} 08/31/2021 07:14:27 - INFO - __main__ - Step 99670: {'lr': 0.00012961273844803057, 'samples': 19136640, 'steps': 99669, 'loss/train': 1.3590203523635864} 08/31/2021 07:14:27 - INFO - __main__ - Step 99671: {'lr': 0.00012960808754281468, 'samples': 19136832, 'steps': 99670, 'loss/train': 1.4157620668411255} 08/31/2021 07:14:28 - INFO - __main__ - Step 99672: {'lr': 0.00012960343669184544, 'samples': 19137024, 'steps': 99671, 'loss/train': 0.7983701229095459} 08/31/2021 07:14:30 - INFO - __main__ - Step 99673: {'lr': 0.00012959878589512502, 'samples': 19137216, 'steps': 99672, 'loss/train': 1.3195240497589111} 08/31/2021 07:14:31 - INFO - __main__ - Step 99674: {'lr': 0.00012959413515265553, 'samples': 19137408, 'steps': 99673, 'loss/train': 1.3937166929244995} 08/31/2021 07:14:31 - INFO - __main__ - Step 99675: {'lr': 0.00012958948446443907, 'samples': 19137600, 'steps': 99674, 'loss/train': 1.108956217765808} 08/31/2021 07:14:31 - INFO - __main__ - Step 99676: {'lr': 0.00012958483383047773, 'samples': 19137792, 'steps': 99675, 'loss/train': 0.8705493211746216} 08/31/2021 07:14:32 - INFO - __main__ - Step 99677: {'lr': 0.0001295801832507736, 'samples': 19137984, 'steps': 99676, 'loss/train': 1.5274312496185303} 08/31/2021 07:14:32 - INFO - __main__ - Step 99678: {'lr': 0.0001295755327253288, 'samples': 19138176, 'steps': 99677, 'loss/train': 1.2439104318618774} 08/31/2021 07:14:34 - INFO - __main__ - Step 99679: {'lr': 0.00012957088225414539, 'samples': 19138368, 'steps': 99678, 'loss/train': 1.6665349006652832} 08/31/2021 07:14:34 - INFO - __main__ - Step 99680: {'lr': 0.00012956623183722543, 'samples': 19138560, 'steps': 99679, 'loss/train': 1.4911706447601318} 08/31/2021 07:14:34 - INFO - __main__ - Step 99681: {'lr': 0.00012956158147457115, 'samples': 19138752, 'steps': 99680, 'loss/train': 0.662963330745697} 08/31/2021 07:14:35 - INFO - __main__ - Step 99682: {'lr': 0.00012955693116618451, 'samples': 19138944, 'steps': 99681, 'loss/train': 0.2801252603530884} 08/31/2021 07:14:35 - INFO - __main__ - Step 99683: {'lr': 0.0001295522809120677, 'samples': 19139136, 'steps': 99682, 'loss/train': 1.3715310096740723} 08/31/2021 07:14:36 - INFO - __main__ - Step 99684: {'lr': 0.00012954763071222286, 'samples': 19139328, 'steps': 99683, 'loss/train': 0.9406057596206665} 08/31/2021 07:14:37 - INFO - __main__ - Step 99685: {'lr': 0.00012954298056665187, 'samples': 19139520, 'steps': 99684, 'loss/train': 0.9800447225570679} 08/31/2021 07:14:38 - INFO - __main__ - Step 99686: {'lr': 0.000129538330475357, 'samples': 19139712, 'steps': 99685, 'loss/train': 0.2871890962123871} 08/31/2021 07:14:38 - INFO - __main__ - Step 99687: {'lr': 0.00012953368043834023, 'samples': 19139904, 'steps': 99686, 'loss/train': 1.8917887210845947} 08/31/2021 07:14:39 - INFO - __main__ - Step 99688: {'lr': 0.0001295290304556038, 'samples': 19140096, 'steps': 99687, 'loss/train': 0.955401599407196} 08/31/2021 07:14:39 - INFO - __main__ - Step 99689: {'lr': 0.00012952438052714972, 'samples': 19140288, 'steps': 99688, 'loss/train': 1.415424108505249} 08/31/2021 07:14:41 - INFO - __main__ - Step 99690: {'lr': 0.00012951973065298007, 'samples': 19140480, 'steps': 99689, 'loss/train': 1.0640079975128174} 08/31/2021 07:14:41 - INFO - __main__ - Step 99691: {'lr': 0.00012951508083309697, 'samples': 19140672, 'steps': 99690, 'loss/train': 1.6655712127685547} 08/31/2021 07:14:41 - INFO - __main__ - Step 99692: {'lr': 0.00012951043106750252, 'samples': 19140864, 'steps': 99691, 'loss/train': 0.540099561214447} 08/31/2021 07:14:42 - INFO - __main__ - Step 99693: {'lr': 0.00012950578135619882, 'samples': 19141056, 'steps': 99692, 'loss/train': 1.510315179824829} 08/31/2021 07:14:42 - INFO - __main__ - Step 99694: {'lr': 0.00012950113169918792, 'samples': 19141248, 'steps': 99693, 'loss/train': 1.198548436164856} 08/31/2021 07:14:44 - INFO - __main__ - Step 99695: {'lr': 0.000129496482096472, 'samples': 19141440, 'steps': 99694, 'loss/train': 1.5482265949249268} 08/31/2021 07:14:44 - INFO - __main__ - Step 99696: {'lr': 0.0001294918325480531, 'samples': 19141632, 'steps': 99695, 'loss/train': 0.11231572180986404} 08/31/2021 07:14:45 - INFO - __main__ - Step 99697: {'lr': 0.00012948718305393327, 'samples': 19141824, 'steps': 99696, 'loss/train': 1.352632761001587} 08/31/2021 07:14:45 - INFO - __main__ - Step 99698: {'lr': 0.0001294825336141148, 'samples': 19142016, 'steps': 99697, 'loss/train': 0.8837792277336121} 08/31/2021 07:14:45 - INFO - __main__ - Step 99699: {'lr': 0.00012947788422859951, 'samples': 19142208, 'steps': 99698, 'loss/train': 0.9892621636390686} 08/31/2021 07:14:47 - INFO - __main__ - Step 99700: {'lr': 0.00012947323489738966, 'samples': 19142400, 'steps': 99699, 'loss/train': 0.9027585387229919} 08/31/2021 07:14:48 - INFO - __main__ - Step 99701: {'lr': 0.0001294685856204873, 'samples': 19142592, 'steps': 99700, 'loss/train': 1.420314908027649} 08/31/2021 07:14:48 - INFO - __main__ - Step 99702: {'lr': 0.00012946393639789452, 'samples': 19142784, 'steps': 99701, 'loss/train': 1.5884275436401367} 08/31/2021 07:14:48 - INFO - __main__ - Step 99703: {'lr': 0.00012945928722961347, 'samples': 19142976, 'steps': 99702, 'loss/train': 0.9694648385047913} 08/31/2021 07:14:49 - INFO - __main__ - Step 99704: {'lr': 0.00012945463811564616, 'samples': 19143168, 'steps': 99703, 'loss/train': 0.9285093545913696} 08/31/2021 07:14:51 - INFO - __main__ - Step 99705: {'lr': 0.00012944998905599475, 'samples': 19143360, 'steps': 99704, 'loss/train': 1.4236687421798706} 08/31/2021 07:14:51 - INFO - __main__ - Step 99706: {'lr': 0.00012944534005066133, 'samples': 19143552, 'steps': 99705, 'loss/train': 1.5184483528137207} 08/31/2021 07:14:51 - INFO - __main__ - Step 99707: {'lr': 0.00012944069109964795, 'samples': 19143744, 'steps': 99706, 'loss/train': 0.7075099945068359} 08/31/2021 07:14:52 - INFO - __main__ - Step 99708: {'lr': 0.00012943604220295673, 'samples': 19143936, 'steps': 99707, 'loss/train': 1.2405861616134644} 08/31/2021 07:14:52 - INFO - __main__ - Step 99709: {'lr': 0.0001294313933605899, 'samples': 19144128, 'steps': 99708, 'loss/train': 1.2022591829299927} 08/31/2021 07:14:52 - INFO - __main__ - Step 99710: {'lr': 0.0001294267445725493, 'samples': 19144320, 'steps': 99709, 'loss/train': 1.181591510772705} 08/31/2021 07:14:54 - INFO - __main__ - Step 99711: {'lr': 0.00012942209583883716, 'samples': 19144512, 'steps': 99710, 'loss/train': 1.413183569908142} 08/31/2021 07:14:55 - INFO - __main__ - Step 99712: {'lr': 0.00012941744715945557, 'samples': 19144704, 'steps': 99711, 'loss/train': 0.0516643263399601} 08/31/2021 07:14:55 - INFO - __main__ - Step 99713: {'lr': 0.0001294127985344066, 'samples': 19144896, 'steps': 99712, 'loss/train': 0.7360002994537354} 08/31/2021 07:14:56 - INFO - __main__ - Step 99714: {'lr': 0.0001294081499636924, 'samples': 19145088, 'steps': 99713, 'loss/train': 0.5496819615364075} 08/31/2021 07:14:56 - INFO - __main__ - Step 99715: {'lr': 0.00012940350144731495, 'samples': 19145280, 'steps': 99714, 'loss/train': 1.2937709093093872} 08/31/2021 07:14:56 - INFO - __main__ - Step 99716: {'lr': 0.00012939885298527648, 'samples': 19145472, 'steps': 99715, 'loss/train': 0.8286815285682678} 08/31/2021 07:14:58 - INFO - __main__ - Step 99717: {'lr': 0.000129394204577579, 'samples': 19145664, 'steps': 99716, 'loss/train': 0.8622777462005615} 08/31/2021 07:14:59 - INFO - __main__ - Step 99718: {'lr': 0.00012938955622422466, 'samples': 19145856, 'steps': 99717, 'loss/train': 1.2766664028167725} 08/31/2021 07:14:59 - INFO - __main__ - Step 99719: {'lr': 0.0001293849079252155, 'samples': 19146048, 'steps': 99718, 'loss/train': 1.492601752281189} 08/31/2021 07:14:59 - INFO - __main__ - Step 99720: {'lr': 0.00012938025968055376, 'samples': 19146240, 'steps': 99719, 'loss/train': 0.5506030321121216} 08/31/2021 07:15:00 - INFO - __main__ - Step 99721: {'lr': 0.0001293756114902413, 'samples': 19146432, 'steps': 99720, 'loss/train': 0.03289417177438736} 08/31/2021 07:15:01 - INFO - __main__ - Step 99722: {'lr': 0.00012937096335428034, 'samples': 19146624, 'steps': 99721, 'loss/train': 1.1476877927780151} 08/31/2021 07:15:02 - INFO - __main__ - Step 99723: {'lr': 0.00012936631527267294, 'samples': 19146816, 'steps': 99722, 'loss/train': 0.8253213763237} 08/31/2021 07:15:02 - INFO - __main__ - Step 99724: {'lr': 0.00012936166724542123, 'samples': 19147008, 'steps': 99723, 'loss/train': 1.3726866245269775} 08/31/2021 07:15:02 - INFO - __main__ - Step 99725: {'lr': 0.0001293570192725273, 'samples': 19147200, 'steps': 99724, 'loss/train': 0.5917758941650391} 08/31/2021 07:15:03 - INFO - __main__ - Step 99726: {'lr': 0.00012935237135399321, 'samples': 19147392, 'steps': 99725, 'loss/train': 0.9359443783760071} 08/31/2021 07:15:05 - INFO - __main__ - Step 99727: {'lr': 0.0001293477234898211, 'samples': 19147584, 'steps': 99726, 'loss/train': 1.6280314922332764} 08/31/2021 07:15:05 - INFO - __main__ - Step 99728: {'lr': 0.00012934307568001304, 'samples': 19147776, 'steps': 99727, 'loss/train': 1.2358285188674927} 08/31/2021 07:15:05 - INFO - __main__ - Step 99729: {'lr': 0.00012933842792457113, 'samples': 19147968, 'steps': 99728, 'loss/train': 1.3761990070343018} 08/31/2021 07:15:06 - INFO - __main__ - Step 99730: {'lr': 0.00012933378022349747, 'samples': 19148160, 'steps': 99729, 'loss/train': 0.7566720843315125} 08/31/2021 07:15:06 - INFO - __main__ - Step 99731: {'lr': 0.00012932913257679424, 'samples': 19148352, 'steps': 99730, 'loss/train': 1.4455283880233765} 08/31/2021 07:15:08 - INFO - __main__ - Step 99732: {'lr': 0.0001293244849844633, 'samples': 19148544, 'steps': 99731, 'loss/train': 1.1134769916534424} 08/31/2021 07:15:08 - INFO - __main__ - Step 99733: {'lr': 0.00012931983744650694, 'samples': 19148736, 'steps': 99732, 'loss/train': 1.6085562705993652} 08/31/2021 07:15:09 - INFO - __main__ - Step 99734: {'lr': 0.0001293151899629272, 'samples': 19148928, 'steps': 99733, 'loss/train': 0.0484735444188118} 08/31/2021 07:15:09 - INFO - __main__ - Step 99735: {'lr': 0.00012931054253372616, 'samples': 19149120, 'steps': 99734, 'loss/train': 1.0350905656814575} 08/31/2021 07:15:09 - INFO - __main__ - Step 99736: {'lr': 0.0001293058951589059, 'samples': 19149312, 'steps': 99735, 'loss/train': 0.9524511098861694} 08/31/2021 07:15:10 - INFO - __main__ - Step 99737: {'lr': 0.0001293012478384686, 'samples': 19149504, 'steps': 99736, 'loss/train': 0.018745386973023415} 08/31/2021 07:15:10 - INFO - __main__ - Step 99738: {'lr': 0.00012929660057241622, 'samples': 19149696, 'steps': 99737, 'loss/train': 1.2153863906860352} 08/31/2021 07:15:12 - INFO - __main__ - Step 99739: {'lr': 0.00012929195336075099, 'samples': 19149888, 'steps': 99738, 'loss/train': 1.6042721271514893} 08/31/2021 07:15:13 - INFO - __main__ - Step 99740: {'lr': 0.00012928730620347489, 'samples': 19150080, 'steps': 99739, 'loss/train': 0.13051451742649078} 08/31/2021 07:15:13 - INFO - __main__ - Step 99741: {'lr': 0.00012928265910059012, 'samples': 19150272, 'steps': 99740, 'loss/train': 0.37278950214385986} 08/31/2021 07:15:13 - INFO - __main__ - Step 99742: {'lr': 0.00012927801205209877, 'samples': 19150464, 'steps': 99741, 'loss/train': 1.319118857383728} 08/31/2021 07:15:14 - INFO - __main__ - Step 99743: {'lr': 0.00012927336505800282, 'samples': 19150656, 'steps': 99742, 'loss/train': 1.121779441833496} 08/31/2021 07:15:16 - INFO - __main__ - Step 99744: {'lr': 0.00012926871811830444, 'samples': 19150848, 'steps': 99743, 'loss/train': 1.477781891822815} 08/31/2021 07:15:16 - INFO - __main__ - Step 99745: {'lr': 0.00012926407123300571, 'samples': 19151040, 'steps': 99744, 'loss/train': 1.6991541385650635} 08/31/2021 07:15:16 - INFO - __main__ - Step 99746: {'lr': 0.0001292594244021087, 'samples': 19151232, 'steps': 99745, 'loss/train': 1.0459914207458496} 08/31/2021 07:15:17 - INFO - __main__ - Step 99747: {'lr': 0.00012925477762561554, 'samples': 19151424, 'steps': 99746, 'loss/train': 3.7194106578826904} 08/31/2021 07:15:17 - INFO - __main__ - Step 99748: {'lr': 0.00012925013090352833, 'samples': 19151616, 'steps': 99747, 'loss/train': 1.0323878526687622} 08/31/2021 07:15:17 - INFO - __main__ - Step 99749: {'lr': 0.00012924548423584912, 'samples': 19151808, 'steps': 99748, 'loss/train': 1.0454261302947998} 08/31/2021 07:15:19 - INFO - __main__ - Step 99750: {'lr': 0.00012924083762258005, 'samples': 19152000, 'steps': 99749, 'loss/train': 0.8786013126373291} 08/31/2021 07:15:19 - INFO - __main__ - Step 99751: {'lr': 0.00012923619106372319, 'samples': 19152192, 'steps': 99750, 'loss/train': 0.9722951054573059} 08/31/2021 07:15:20 - INFO - __main__ - Step 99752: {'lr': 0.00012923154455928064, 'samples': 19152384, 'steps': 99751, 'loss/train': 2.129549264907837} 08/31/2021 07:15:20 - INFO - __main__ - Step 99753: {'lr': 0.00012922689810925458, 'samples': 19152576, 'steps': 99752, 'loss/train': 1.4468586444854736} 08/31/2021 07:15:20 - INFO - __main__ - Step 99754: {'lr': 0.00012922225171364693, 'samples': 19152768, 'steps': 99753, 'loss/train': 0.23749083280563354} 08/31/2021 07:15:22 - INFO - __main__ - Step 99755: {'lr': 0.00012921760537245986, 'samples': 19152960, 'steps': 99754, 'loss/train': 0.9223119616508484} 08/31/2021 07:15:22 - INFO - __main__ - Step 99756: {'lr': 0.00012921295908569546, 'samples': 19153152, 'steps': 99755, 'loss/train': 0.6924178004264832} 08/31/2021 07:15:23 - INFO - __main__ - Step 99757: {'lr': 0.0001292083128533559, 'samples': 19153344, 'steps': 99756, 'loss/train': 1.1857362985610962} 08/31/2021 07:15:23 - INFO - __main__ - Step 99758: {'lr': 0.00012920366667544314, 'samples': 19153536, 'steps': 99757, 'loss/train': 1.5979639291763306} 08/31/2021 07:15:23 - INFO - __main__ - Step 99759: {'lr': 0.00012919902055195937, 'samples': 19153728, 'steps': 99758, 'loss/train': 1.190401554107666} 08/31/2021 07:15:25 - INFO - __main__ - Step 99760: {'lr': 0.00012919437448290666, 'samples': 19153920, 'steps': 99759, 'loss/train': 0.9571189284324646} 08/31/2021 07:15:26 - INFO - __main__ - Step 99761: {'lr': 0.00012918972846828712, 'samples': 19154112, 'steps': 99760, 'loss/train': 1.0619359016418457} 08/31/2021 07:15:26 - INFO - __main__ - Step 99762: {'lr': 0.00012918508250810278, 'samples': 19154304, 'steps': 99761, 'loss/train': 0.9935026168823242} 08/31/2021 07:15:26 - INFO - __main__ - Step 99763: {'lr': 0.0001291804366023558, 'samples': 19154496, 'steps': 99762, 'loss/train': 1.6271003484725952} 08/31/2021 07:15:27 - INFO - __main__ - Step 99764: {'lr': 0.00012917579075104825, 'samples': 19154688, 'steps': 99763, 'loss/train': 1.060632348060608} 08/31/2021 07:15:27 - INFO - __main__ - Step 99765: {'lr': 0.00012917114495418237, 'samples': 19154880, 'steps': 99764, 'loss/train': 1.0512316226959229} 08/31/2021 07:15:28 - INFO - __main__ - Step 99766: {'lr': 0.00012916649921175993, 'samples': 19155072, 'steps': 99765, 'loss/train': 1.315406084060669} 08/31/2021 07:15:29 - INFO - __main__ - Step 99767: {'lr': 0.00012916185352378323, 'samples': 19155264, 'steps': 99766, 'loss/train': 1.233123540878296} 08/31/2021 07:15:29 - INFO - __main__ - Step 99768: {'lr': 0.00012915720789025438, 'samples': 19155456, 'steps': 99767, 'loss/train': 1.3519643545150757} 08/31/2021 07:15:30 - INFO - __main__ - Step 99769: {'lr': 0.00012915256231117532, 'samples': 19155648, 'steps': 99768, 'loss/train': 1.336204171180725} 08/31/2021 07:15:30 - INFO - __main__ - Step 99770: {'lr': 0.00012914791678654834, 'samples': 19155840, 'steps': 99769, 'loss/train': 0.7153515815734863} 08/31/2021 07:15:32 - INFO - __main__ - Step 99771: {'lr': 0.00012914327131637542, 'samples': 19156032, 'steps': 99770, 'loss/train': 1.5008268356323242} 08/31/2021 07:15:32 - INFO - __main__ - Step 99772: {'lr': 0.0001291386259006587, 'samples': 19156224, 'steps': 99771, 'loss/train': 0.9999924302101135} 08/31/2021 07:15:32 - INFO - __main__ - Step 99773: {'lr': 0.00012913398053940024, 'samples': 19156416, 'steps': 99772, 'loss/train': 0.9470640420913696} 08/31/2021 07:15:33 - INFO - __main__ - Step 99774: {'lr': 0.0001291293352326021, 'samples': 19156608, 'steps': 99773, 'loss/train': 1.1740467548370361} 08/31/2021 07:15:33 - INFO - __main__ - Step 99775: {'lr': 0.00012912468998026644, 'samples': 19156800, 'steps': 99774, 'loss/train': 1.1830607652664185} 08/31/2021 07:15:35 - INFO - __main__ - Step 99776: {'lr': 0.00012912004478239536, 'samples': 19156992, 'steps': 99775, 'loss/train': 1.1689373254776} 08/31/2021 07:15:35 - INFO - __main__ - Step 99777: {'lr': 0.00012911539963899089, 'samples': 19157184, 'steps': 99776, 'loss/train': 0.8574010133743286} 08/31/2021 07:15:35 - INFO - __main__ - Step 99778: {'lr': 0.00012911075455005516, 'samples': 19157376, 'steps': 99777, 'loss/train': 0.19273683428764343} 08/31/2021 07:15:36 - INFO - __main__ - Step 99779: {'lr': 0.00012910610951559037, 'samples': 19157568, 'steps': 99778, 'loss/train': 1.4435946941375732} 08/31/2021 07:15:36 - INFO - __main__ - Step 99780: {'lr': 0.0001291014645355984, 'samples': 19157760, 'steps': 99779, 'loss/train': 0.9129658937454224} 08/31/2021 07:15:38 - INFO - __main__ - Step 99781: {'lr': 0.00012909681961008142, 'samples': 19157952, 'steps': 99780, 'loss/train': 1.1094648838043213} 08/31/2021 07:15:38 - INFO - __main__ - Step 99782: {'lr': 0.00012909217473904157, 'samples': 19158144, 'steps': 99781, 'loss/train': 0.9093625545501709} 08/31/2021 07:15:39 - INFO - __main__ - Step 99783: {'lr': 0.00012908752992248093, 'samples': 19158336, 'steps': 99782, 'loss/train': 1.4207136631011963} 08/31/2021 07:15:39 - INFO - __main__ - Step 99784: {'lr': 0.00012908288516040155, 'samples': 19158528, 'steps': 99783, 'loss/train': 0.906629204750061} 08/31/2021 07:15:39 - INFO - __main__ - Step 99785: {'lr': 0.0001290782404528056, 'samples': 19158720, 'steps': 99784, 'loss/train': 1.7121936082839966} 08/31/2021 07:15:41 - INFO - __main__ - Step 99786: {'lr': 0.0001290735957996951, 'samples': 19158912, 'steps': 99785, 'loss/train': 1.5821951627731323} 08/31/2021 07:15:41 - INFO - __main__ - Step 99787: {'lr': 0.0001290689512010722, 'samples': 19159104, 'steps': 99786, 'loss/train': 1.2557322978973389} 08/31/2021 07:15:42 - INFO - __main__ - Step 99788: {'lr': 0.0001290643066569389, 'samples': 19159296, 'steps': 99787, 'loss/train': 1.6525087356567383} 08/31/2021 07:15:42 - INFO - __main__ - Step 99789: {'lr': 0.00012905966216729742, 'samples': 19159488, 'steps': 99788, 'loss/train': 1.121001958847046} 08/31/2021 07:15:42 - INFO - __main__ - Step 99790: {'lr': 0.00012905501773214978, 'samples': 19159680, 'steps': 99789, 'loss/train': 0.8364229798316956} 08/31/2021 07:15:44 - INFO - __main__ - Step 99791: {'lr': 0.00012905037335149804, 'samples': 19159872, 'steps': 99790, 'loss/train': 1.1975345611572266} 08/31/2021 07:15:45 - INFO - __main__ - Step 99792: {'lr': 0.0001290457290253445, 'samples': 19160064, 'steps': 99791, 'loss/train': 1.3745696544647217} 08/31/2021 07:15:45 - INFO - __main__ - Step 99793: {'lr': 0.00012904108475369095, 'samples': 19160256, 'steps': 99792, 'loss/train': 0.3250822424888611} 08/31/2021 07:15:45 - INFO - __main__ - Step 99794: {'lr': 0.0001290364405365396, 'samples': 19160448, 'steps': 99793, 'loss/train': 0.7902237772941589} 08/31/2021 07:15:46 - INFO - __main__ - Step 99795: {'lr': 0.00012903179637389263, 'samples': 19160640, 'steps': 99794, 'loss/train': 0.9707430601119995} 08/31/2021 07:15:46 - INFO - __main__ - Step 99796: {'lr': 0.00012902715226575202, 'samples': 19160832, 'steps': 99795, 'loss/train': 1.213683009147644} 08/31/2021 07:15:49 - INFO - __main__ - Step 99797: {'lr': 0.00012902250821211992, 'samples': 19161024, 'steps': 99796, 'loss/train': 0.5130658745765686} 08/31/2021 07:15:49 - INFO - __main__ - Step 99798: {'lr': 0.00012901786421299838, 'samples': 19161216, 'steps': 99797, 'loss/train': 0.8744195103645325} 08/31/2021 07:15:50 - INFO - __main__ - Step 99799: {'lr': 0.00012901322026838958, 'samples': 19161408, 'steps': 99798, 'loss/train': 0.3483252227306366} 08/31/2021 07:15:50 - INFO - __main__ - Step 99800: {'lr': 0.0001290085763782955, 'samples': 19161600, 'steps': 99799, 'loss/train': 0.31826382875442505} 08/31/2021 07:15:50 - INFO - __main__ - Step 99801: {'lr': 0.0001290039325427183, 'samples': 19161792, 'steps': 99800, 'loss/train': 1.4952428340911865} 08/31/2021 07:15:51 - INFO - __main__ - Step 99802: {'lr': 0.0001289992887616601, 'samples': 19161984, 'steps': 99801, 'loss/train': 0.9281591773033142} 08/31/2021 07:15:52 - INFO - __main__ - Step 99803: {'lr': 0.00012899464503512292, 'samples': 19162176, 'steps': 99802, 'loss/train': 0.9649723768234253} 08/31/2021 07:15:53 - INFO - __main__ - Step 99804: {'lr': 0.0001289900013631089, 'samples': 19162368, 'steps': 99803, 'loss/train': 1.390377163887024} 08/31/2021 07:15:53 - INFO - __main__ - Step 99805: {'lr': 0.0001289853577456202, 'samples': 19162560, 'steps': 99804, 'loss/train': 1.38633131980896} 08/31/2021 07:15:53 - INFO - __main__ - Step 99806: {'lr': 0.00012898071418265876, 'samples': 19162752, 'steps': 99805, 'loss/train': 1.4396247863769531} 08/31/2021 07:15:54 - INFO - __main__ - Step 99807: {'lr': 0.0001289760706742267, 'samples': 19162944, 'steps': 99806, 'loss/train': 1.210745930671692} 08/31/2021 07:15:55 - INFO - __main__ - Step 99808: {'lr': 0.00012897142722032617, 'samples': 19163136, 'steps': 99807, 'loss/train': 1.0445449352264404} 08/31/2021 07:15:56 - INFO - __main__ - Step 99809: {'lr': 0.00012896678382095928, 'samples': 19163328, 'steps': 99808, 'loss/train': 0.847602128982544} 08/31/2021 07:15:56 - INFO - __main__ - Step 99810: {'lr': 0.00012896214047612806, 'samples': 19163520, 'steps': 99809, 'loss/train': 1.5043926239013672} 08/31/2021 07:15:57 - INFO - __main__ - Step 99811: {'lr': 0.00012895749718583462, 'samples': 19163712, 'steps': 99810, 'loss/train': 1.1048015356063843} 08/31/2021 07:15:57 - INFO - __main__ - Step 99812: {'lr': 0.0001289528539500811, 'samples': 19163904, 'steps': 99811, 'loss/train': 0.9958586096763611} 08/31/2021 07:15:58 - INFO - __main__ - Step 99813: {'lr': 0.00012894821076886955, 'samples': 19164096, 'steps': 99812, 'loss/train': 0.6855944395065308} 08/31/2021 07:15:59 - INFO - __main__ - Step 99814: {'lr': 0.00012894356764220206, 'samples': 19164288, 'steps': 99813, 'loss/train': 0.4649219810962677} 08/31/2021 07:15:59 - INFO - __main__ - Step 99815: {'lr': 0.00012893892457008072, 'samples': 19164480, 'steps': 99814, 'loss/train': 0.6298910975456238} 08/31/2021 07:16:00 - INFO - __main__ - Step 99816: {'lr': 0.00012893428155250764, 'samples': 19164672, 'steps': 99815, 'loss/train': 1.1233069896697998} 08/31/2021 07:16:00 - INFO - __main__ - Step 99817: {'lr': 0.0001289296385894849, 'samples': 19164864, 'steps': 99816, 'loss/train': 1.015171766281128} 08/31/2021 07:16:01 - INFO - __main__ - Step 99818: {'lr': 0.0001289249956810146, 'samples': 19165056, 'steps': 99817, 'loss/train': 1.9306260347366333} 08/31/2021 07:16:02 - INFO - __main__ - Step 99819: {'lr': 0.0001289203528270989, 'samples': 19165248, 'steps': 99818, 'loss/train': 0.7519629597663879} 08/31/2021 07:16:02 - INFO - __main__ - Step 99820: {'lr': 0.00012891571002773976, 'samples': 19165440, 'steps': 99819, 'loss/train': 1.5254971981048584} 08/31/2021 07:16:03 - INFO - __main__ - Step 99821: {'lr': 0.00012891106728293934, 'samples': 19165632, 'steps': 99820, 'loss/train': 1.095857858657837} 08/31/2021 07:16:03 - INFO - __main__ - Step 99822: {'lr': 0.00012890642459269968, 'samples': 19165824, 'steps': 99821, 'loss/train': 1.4253133535385132} 08/31/2021 07:16:03 - INFO - __main__ - Step 99823: {'lr': 0.00012890178195702295, 'samples': 19166016, 'steps': 99822, 'loss/train': 1.4973033666610718} 08/31/2021 07:16:05 - INFO - __main__ - Step 99824: {'lr': 0.00012889713937591123, 'samples': 19166208, 'steps': 99823, 'loss/train': 1.356478214263916} 08/31/2021 07:16:05 - INFO - __main__ - Step 99825: {'lr': 0.00012889249684936655, 'samples': 19166400, 'steps': 99824, 'loss/train': 1.4915390014648438} 08/31/2021 07:16:06 - INFO - __main__ - Step 99826: {'lr': 0.00012888785437739102, 'samples': 19166592, 'steps': 99825, 'loss/train': 1.3350651264190674} 08/31/2021 07:16:06 - INFO - __main__ - Step 99827: {'lr': 0.0001288832119599868, 'samples': 19166784, 'steps': 99826, 'loss/train': 1.179060459136963} 08/31/2021 07:16:06 - INFO - __main__ - Step 99828: {'lr': 0.00012887856959715595, 'samples': 19166976, 'steps': 99827, 'loss/train': 0.7607772946357727} 08/31/2021 07:16:08 - INFO - __main__ - Step 99829: {'lr': 0.00012887392728890053, 'samples': 19167168, 'steps': 99828, 'loss/train': 1.3415483236312866} 08/31/2021 07:16:08 - INFO - __main__ - Step 99830: {'lr': 0.0001288692850352226, 'samples': 19167360, 'steps': 99829, 'loss/train': 1.3040478229522705} 08/31/2021 07:16:09 - INFO - __main__ - Step 99831: {'lr': 0.00012886464283612436, 'samples': 19167552, 'steps': 99830, 'loss/train': 1.0074961185455322} 08/31/2021 07:16:09 - INFO - __main__ - Step 99832: {'lr': 0.0001288600006916079, 'samples': 19167744, 'steps': 99831, 'loss/train': 1.2074856758117676} 08/31/2021 07:16:09 - INFO - __main__ - Step 99833: {'lr': 0.0001288553586016752, 'samples': 19167936, 'steps': 99832, 'loss/train': 0.5192385315895081} 08/31/2021 07:16:11 - INFO - __main__ - Step 99834: {'lr': 0.0001288507165663284, 'samples': 19168128, 'steps': 99833, 'loss/train': 2.074260711669922} 08/31/2021 07:16:11 - INFO - __main__ - Step 99835: {'lr': 0.00012884607458556958, 'samples': 19168320, 'steps': 99834, 'loss/train': 1.146958589553833} 08/31/2021 07:16:12 - INFO - __main__ - Step 99836: {'lr': 0.00012884143265940086, 'samples': 19168512, 'steps': 99835, 'loss/train': 1.894443154335022} 08/31/2021 07:16:12 - INFO - __main__ - Step 99837: {'lr': 0.00012883679078782429, 'samples': 19168704, 'steps': 99836, 'loss/train': 0.031816281378269196} 08/31/2021 07:16:12 - INFO - __main__ - Step 99838: {'lr': 0.00012883214897084204, 'samples': 19168896, 'steps': 99837, 'loss/train': 1.0457298755645752} 08/31/2021 07:16:14 - INFO - __main__ - Step 99839: {'lr': 0.0001288275072084561, 'samples': 19169088, 'steps': 99838, 'loss/train': 1.2489672899246216} 08/31/2021 07:16:15 - INFO - __main__ - Step 99840: {'lr': 0.00012882286550066865, 'samples': 19169280, 'steps': 99839, 'loss/train': 1.4276260137557983} 08/31/2021 07:16:15 - INFO - __main__ - Step 99841: {'lr': 0.00012881822384748176, 'samples': 19169472, 'steps': 99840, 'loss/train': 0.1904870867729187} 08/31/2021 07:16:15 - INFO - __main__ - Step 99842: {'lr': 0.0001288135822488975, 'samples': 19169664, 'steps': 99841, 'loss/train': 1.2054307460784912} 08/31/2021 07:16:16 - INFO - __main__ - Step 99843: {'lr': 0.00012880894070491794, 'samples': 19169856, 'steps': 99842, 'loss/train': 0.43108898401260376} 08/31/2021 07:16:17 - INFO - __main__ - Step 99844: {'lr': 0.0001288042992155452, 'samples': 19170048, 'steps': 99843, 'loss/train': 1.052039623260498} 08/31/2021 07:16:18 - INFO - __main__ - Step 99845: {'lr': 0.0001287996577807814, 'samples': 19170240, 'steps': 99844, 'loss/train': 1.5944792032241821} 08/31/2021 07:16:18 - INFO - __main__ - Step 99846: {'lr': 0.0001287950164006287, 'samples': 19170432, 'steps': 99845, 'loss/train': 1.418282389640808} 08/31/2021 07:16:18 - INFO - __main__ - Step 99847: {'lr': 0.000128790375075089, 'samples': 19170624, 'steps': 99846, 'loss/train': 1.18960440158844} 08/31/2021 07:16:19 - INFO - __main__ - Step 99848: {'lr': 0.00012878573380416448, 'samples': 19170816, 'steps': 99847, 'loss/train': 1.0152307748794556} 08/31/2021 07:16:20 - INFO - __main__ - Step 99849: {'lr': 0.00012878109258785726, 'samples': 19171008, 'steps': 99848, 'loss/train': 1.017449975013733} 08/31/2021 07:16:21 - INFO - __main__ - Step 99850: {'lr': 0.00012877645142616936, 'samples': 19171200, 'steps': 99849, 'loss/train': 1.3132927417755127} 08/31/2021 07:16:21 - INFO - __main__ - Step 99851: {'lr': 0.00012877181031910296, 'samples': 19171392, 'steps': 99850, 'loss/train': 1.5006849765777588} 08/31/2021 07:16:22 - INFO - __main__ - Step 99852: {'lr': 0.0001287671692666601, 'samples': 19171584, 'steps': 99851, 'loss/train': 0.9170181155204773} 08/31/2021 07:16:22 - INFO - __main__ - Step 99853: {'lr': 0.00012876252826884288, 'samples': 19171776, 'steps': 99852, 'loss/train': 1.5497363805770874} 08/31/2021 07:16:24 - INFO - __main__ - Step 99854: {'lr': 0.00012875788732565337, 'samples': 19171968, 'steps': 99853, 'loss/train': 0.9734504222869873} 08/31/2021 07:16:24 - INFO - __main__ - Step 99855: {'lr': 0.00012875324643709375, 'samples': 19172160, 'steps': 99854, 'loss/train': 0.9509963989257812} 08/31/2021 07:16:25 - INFO - __main__ - Step 99856: {'lr': 0.00012874860560316598, 'samples': 19172352, 'steps': 99855, 'loss/train': 1.00780189037323} 08/31/2021 07:16:25 - INFO - __main__ - Step 99857: {'lr': 0.00012874396482387223, 'samples': 19172544, 'steps': 99856, 'loss/train': 0.5061560869216919} 08/31/2021 07:16:25 - INFO - __main__ - Step 99858: {'lr': 0.0001287393240992146, 'samples': 19172736, 'steps': 99857, 'loss/train': 1.0702587366104126} 08/31/2021 07:16:26 - INFO - __main__ - Step 99859: {'lr': 0.00012873468342919527, 'samples': 19172928, 'steps': 99858, 'loss/train': 1.1403279304504395} 08/31/2021 07:16:27 - INFO - __main__ - Step 99860: {'lr': 0.0001287300428138161, 'samples': 19173120, 'steps': 99859, 'loss/train': 1.4694273471832275} 08/31/2021 07:16:28 - INFO - __main__ - Step 99861: {'lr': 0.00012872540225307926, 'samples': 19173312, 'steps': 99860, 'loss/train': 1.4380625486373901} 08/31/2021 07:16:28 - INFO - __main__ - Step 99862: {'lr': 0.00012872076174698694, 'samples': 19173504, 'steps': 99861, 'loss/train': 1.1255768537521362} 08/31/2021 07:16:28 - INFO - __main__ - Step 99863: {'lr': 0.00012871612129554118, 'samples': 19173696, 'steps': 99862, 'loss/train': 1.3827921152114868} 08/31/2021 07:16:29 - INFO - __main__ - Step 99864: {'lr': 0.00012871148089874403, 'samples': 19173888, 'steps': 99863, 'loss/train': 1.1296747922897339} 08/31/2021 07:16:30 - INFO - __main__ - Step 99865: {'lr': 0.00012870684055659766, 'samples': 19174080, 'steps': 99864, 'loss/train': 1.52472984790802} 08/31/2021 07:16:31 - INFO - __main__ - Step 99866: {'lr': 0.00012870220026910405, 'samples': 19174272, 'steps': 99865, 'loss/train': 0.9906420111656189} 08/31/2021 07:16:31 - INFO - __main__ - Step 99867: {'lr': 0.0001286975600362654, 'samples': 19174464, 'steps': 99866, 'loss/train': 0.5261450409889221} 08/31/2021 07:16:31 - INFO - __main__ - Step 99868: {'lr': 0.00012869291985808374, 'samples': 19174656, 'steps': 99867, 'loss/train': 1.3498917818069458} 08/31/2021 07:16:32 - INFO - __main__ - Step 99869: {'lr': 0.0001286882797345612, 'samples': 19174848, 'steps': 99868, 'loss/train': 1.029515266418457} 08/31/2021 07:16:33 - INFO - __main__ - Step 99870: {'lr': 0.00012868363966569984, 'samples': 19175040, 'steps': 99869, 'loss/train': 0.732782781124115} 08/31/2021 07:16:34 - INFO - __main__ - Step 99871: {'lr': 0.00012867899965150176, 'samples': 19175232, 'steps': 99870, 'loss/train': 0.7804431915283203} 08/31/2021 07:16:34 - INFO - __main__ - Step 99872: {'lr': 0.00012867435969196903, 'samples': 19175424, 'steps': 99871, 'loss/train': 1.1355459690093994} 08/31/2021 07:16:35 - INFO - __main__ - Step 99873: {'lr': 0.0001286697197871039, 'samples': 19175616, 'steps': 99872, 'loss/train': 1.1857284307479858} 08/31/2021 07:16:35 - INFO - __main__ - Step 99874: {'lr': 0.00012866507993690817, 'samples': 19175808, 'steps': 99873, 'loss/train': 1.6328585147857666} 08/31/2021 07:16:36 - INFO - __main__ - Step 99875: {'lr': 0.00012866044014138412, 'samples': 19176000, 'steps': 99874, 'loss/train': 2.2941439151763916} 08/31/2021 07:16:37 - INFO - __main__ - Step 99876: {'lr': 0.0001286558004005338, 'samples': 19176192, 'steps': 99875, 'loss/train': 1.7447972297668457} 08/31/2021 07:16:37 - INFO - __main__ - Step 99877: {'lr': 0.00012865116071435927, 'samples': 19176384, 'steps': 99876, 'loss/train': 1.299224615097046} 08/31/2021 07:16:38 - INFO - __main__ - Step 99878: {'lr': 0.00012864652108286273, 'samples': 19176576, 'steps': 99877, 'loss/train': 1.6977314949035645} 08/31/2021 07:16:38 - INFO - __main__ - Step 99879: {'lr': 0.00012864188150604614, 'samples': 19176768, 'steps': 99878, 'loss/train': 1.4524519443511963} 08/31/2021 07:16:40 - INFO - __main__ - Step 99880: {'lr': 0.00012863724198391164, 'samples': 19176960, 'steps': 99879, 'loss/train': 1.025600552558899} 08/31/2021 07:16:40 - INFO - __main__ - Step 99881: {'lr': 0.00012863260251646136, 'samples': 19177152, 'steps': 99880, 'loss/train': 1.3240265846252441} 08/31/2021 07:16:40 - INFO - __main__ - Step 99882: {'lr': 0.00012862796310369735, 'samples': 19177344, 'steps': 99881, 'loss/train': 1.2855066061019897} 08/31/2021 07:16:41 - INFO - __main__ - Step 99883: {'lr': 0.0001286233237456217, 'samples': 19177536, 'steps': 99882, 'loss/train': 0.8876783847808838} 08/31/2021 07:16:41 - INFO - __main__ - Step 99884: {'lr': 0.00012861868444223644, 'samples': 19177728, 'steps': 99883, 'loss/train': 1.0569016933441162} 08/31/2021 07:16:41 - INFO - __main__ - Step 99885: {'lr': 0.0001286140451935438, 'samples': 19177920, 'steps': 99884, 'loss/train': 1.8107062578201294} 08/31/2021 07:16:43 - INFO - __main__ - Step 99886: {'lr': 0.0001286094059995459, 'samples': 19178112, 'steps': 99885, 'loss/train': 0.7273181676864624} 08/31/2021 07:16:44 - INFO - __main__ - Step 99887: {'lr': 0.00012860476686024465, 'samples': 19178304, 'steps': 99886, 'loss/train': 1.674269437789917} 08/31/2021 07:16:44 - INFO - __main__ - Step 99888: {'lr': 0.00012860012777564218, 'samples': 19178496, 'steps': 99887, 'loss/train': 1.7365111112594604} 08/31/2021 07:16:44 - INFO - __main__ - Step 99889: {'lr': 0.0001285954887457406, 'samples': 19178688, 'steps': 99888, 'loss/train': 1.2942849397659302} 08/31/2021 07:16:45 - INFO - __main__ - Step 99890: {'lr': 0.00012859084977054203, 'samples': 19178880, 'steps': 99889, 'loss/train': 0.23843614757061005} 08/31/2021 07:16:46 - INFO - __main__ - Step 99891: {'lr': 0.00012858621085004858, 'samples': 19179072, 'steps': 99890, 'loss/train': 0.8406660556793213} 08/31/2021 07:16:47 - INFO - __main__ - Step 99892: {'lr': 0.0001285815719842623, 'samples': 19179264, 'steps': 99891, 'loss/train': 1.0128321647644043} 08/31/2021 07:16:47 - INFO - __main__ - Step 99893: {'lr': 0.00012857693317318527, 'samples': 19179456, 'steps': 99892, 'loss/train': 0.7121506333351135} 08/31/2021 07:16:47 - INFO - __main__ - Step 99894: {'lr': 0.00012857229441681962, 'samples': 19179648, 'steps': 99893, 'loss/train': 0.7789650559425354} 08/31/2021 07:16:48 - INFO - __main__ - Step 99895: {'lr': 0.00012856765571516744, 'samples': 19179840, 'steps': 99894, 'loss/train': 0.8446537852287292} 08/31/2021 07:16:49 - INFO - __main__ - Step 99896: {'lr': 0.00012856301706823075, 'samples': 19180032, 'steps': 99895, 'loss/train': 0.9298411011695862} 08/31/2021 07:16:50 - INFO - __main__ - Step 99897: {'lr': 0.0001285583784760117, 'samples': 19180224, 'steps': 99896, 'loss/train': 1.0460224151611328} 08/31/2021 07:16:50 - INFO - __main__ - Step 99898: {'lr': 0.00012855373993851237, 'samples': 19180416, 'steps': 99897, 'loss/train': 0.8311014771461487} 08/31/2021 07:16:50 - INFO - __main__ - Step 99899: {'lr': 0.0001285491014557349, 'samples': 19180608, 'steps': 99898, 'loss/train': 1.0459132194519043} 08/31/2021 07:16:51 - INFO - __main__ - Step 99900: {'lr': 0.00012854446302768138, 'samples': 19180800, 'steps': 99899, 'loss/train': 1.1728571653366089} 08/31/2021 07:16:52 - INFO - __main__ - Step 99901: {'lr': 0.00012853982465435375, 'samples': 19180992, 'steps': 99900, 'loss/train': 1.2617440223693848} 08/31/2021 07:16:53 - INFO - __main__ - Step 99902: {'lr': 0.00012853518633575421, 'samples': 19181184, 'steps': 99901, 'loss/train': 1.7181352376937866} 08/31/2021 07:16:53 - INFO - __main__ - Step 99903: {'lr': 0.00012853054807188488, 'samples': 19181376, 'steps': 99902, 'loss/train': 1.1400911808013916} 08/31/2021 07:16:53 - INFO - __main__ - Step 99904: {'lr': 0.00012852590986274777, 'samples': 19181568, 'steps': 99903, 'loss/train': 0.946768581867218} 08/31/2021 07:16:54 - INFO - __main__ - Step 99905: {'lr': 0.00012852127170834504, 'samples': 19181760, 'steps': 99904, 'loss/train': 1.2345316410064697} 08/31/2021 07:16:56 - INFO - __main__ - Step 99906: {'lr': 0.00012851663360867872, 'samples': 19181952, 'steps': 99905, 'loss/train': 0.4658118784427643} 08/31/2021 07:16:56 - INFO - __main__ - Step 99907: {'lr': 0.00012851199556375095, 'samples': 19182144, 'steps': 99906, 'loss/train': 1.5224534273147583} 08/31/2021 07:16:56 - INFO - __main__ - Step 99908: {'lr': 0.0001285073575735638, 'samples': 19182336, 'steps': 99907, 'loss/train': 1.0168066024780273} 08/31/2021 07:16:57 - INFO - __main__ - Step 99909: {'lr': 0.00012850271963811932, 'samples': 19182528, 'steps': 99908, 'loss/train': 0.6184437870979309} 08/31/2021 07:16:57 - INFO - __main__ - Step 99910: {'lr': 0.0001284980817574197, 'samples': 19182720, 'steps': 99909, 'loss/train': 1.4810179471969604} 08/31/2021 07:16:59 - INFO - __main__ - Step 99911: {'lr': 0.00012849344393146695, 'samples': 19182912, 'steps': 99910, 'loss/train': 1.2365630865097046} 08/31/2021 07:17:00 - INFO - __main__ - Step 99912: {'lr': 0.00012848880616026315, 'samples': 19183104, 'steps': 99911, 'loss/train': 1.6065949201583862} 08/31/2021 07:17:00 - INFO - __main__ - Step 99913: {'lr': 0.00012848416844381055, 'samples': 19183296, 'steps': 99912, 'loss/train': 1.3306889533996582} 08/31/2021 07:17:00 - INFO - __main__ - Step 99914: {'lr': 0.000128479530782111, 'samples': 19183488, 'steps': 99913, 'loss/train': 0.7230981588363647} 08/31/2021 07:17:01 - INFO - __main__ - Step 99915: {'lr': 0.0001284748931751667, 'samples': 19183680, 'steps': 99914, 'loss/train': 0.6087337732315063} 08/31/2021 07:17:01 - INFO - __main__ - Step 99916: {'lr': 0.0001284702556229797, 'samples': 19183872, 'steps': 99915, 'loss/train': 1.21946120262146} 08/31/2021 07:17:03 - INFO - __main__ - Step 99917: {'lr': 0.00012846561812555218, 'samples': 19184064, 'steps': 99916, 'loss/train': 1.0358043909072876} 08/31/2021 07:17:03 - INFO - __main__ - Step 99918: {'lr': 0.00012846098068288614, 'samples': 19184256, 'steps': 99917, 'loss/train': 0.8506391048431396} 08/31/2021 07:17:04 - INFO - __main__ - Step 99919: {'lr': 0.00012845634329498374, 'samples': 19184448, 'steps': 99918, 'loss/train': 0.9699780941009521} 08/31/2021 07:17:04 - INFO - __main__ - Step 99920: {'lr': 0.00012845170596184703, 'samples': 19184640, 'steps': 99919, 'loss/train': 0.6223047375679016} 08/31/2021 07:17:04 - INFO - __main__ - Step 99921: {'lr': 0.0001284470686834781, 'samples': 19184832, 'steps': 99920, 'loss/train': 1.6857198476791382} 08/31/2021 07:17:06 - INFO - __main__ - Step 99922: {'lr': 0.00012844243145987902, 'samples': 19185024, 'steps': 99921, 'loss/train': 0.981339693069458} 08/31/2021 07:17:06 - INFO - __main__ - Step 99923: {'lr': 0.00012843779429105192, 'samples': 19185216, 'steps': 99922, 'loss/train': 0.916754424571991} 08/31/2021 07:17:07 - INFO - __main__ - Step 99924: {'lr': 0.00012843315717699888, 'samples': 19185408, 'steps': 99923, 'loss/train': 0.867360532283783} 08/31/2021 07:17:07 - INFO - __main__ - Step 99925: {'lr': 0.000128428520117722, 'samples': 19185600, 'steps': 99924, 'loss/train': 0.8300249576568604} 08/31/2021 07:17:07 - INFO - __main__ - Step 99926: {'lr': 0.00012842388311322346, 'samples': 19185792, 'steps': 99925, 'loss/train': 0.03204462304711342} 08/31/2021 07:17:09 - INFO - __main__ - Step 99927: {'lr': 0.00012841924616350509, 'samples': 19185984, 'steps': 99926, 'loss/train': 0.828811764717102} 08/31/2021 07:17:09 - INFO - __main__ - Step 99928: {'lr': 0.00012841460926856917, 'samples': 19186176, 'steps': 99927, 'loss/train': 1.0376509428024292} 08/31/2021 07:17:10 - INFO - __main__ - Step 99929: {'lr': 0.00012840997242841772, 'samples': 19186368, 'steps': 99928, 'loss/train': 1.3632588386535645} 08/31/2021 07:17:10 - INFO - __main__ - Step 99930: {'lr': 0.0001284053356430529, 'samples': 19186560, 'steps': 99929, 'loss/train': 0.8020740151405334} 08/31/2021 07:17:10 - INFO - __main__ - Step 99931: {'lr': 0.00012840069891247675, 'samples': 19186752, 'steps': 99930, 'loss/train': 1.555260419845581} 08/31/2021 07:17:12 - INFO - __main__ - Step 99932: {'lr': 0.00012839606223669135, 'samples': 19186944, 'steps': 99931, 'loss/train': 1.7278995513916016} 08/31/2021 07:17:12 - INFO - __main__ - Step 99933: {'lr': 0.00012839142561569882, 'samples': 19187136, 'steps': 99932, 'loss/train': 1.2291111946105957} 08/31/2021 07:17:13 - INFO - __main__ - Step 99934: {'lr': 0.00012838678904950125, 'samples': 19187328, 'steps': 99933, 'loss/train': 0.8996776342391968} 08/31/2021 07:17:13 - INFO - __main__ - Step 99935: {'lr': 0.00012838215253810069, 'samples': 19187520, 'steps': 99934, 'loss/train': 0.7975789308547974} 08/31/2021 07:17:13 - INFO - __main__ - Step 99936: {'lr': 0.00012837751608149925, 'samples': 19187712, 'steps': 99935, 'loss/train': 1.1297985315322876} 08/31/2021 07:17:15 - INFO - __main__ - Step 99937: {'lr': 0.00012837287967969904, 'samples': 19187904, 'steps': 99936, 'loss/train': 1.1087121963500977} 08/31/2021 07:17:15 - INFO - __main__ - Step 99938: {'lr': 0.00012836824333270215, 'samples': 19188096, 'steps': 99937, 'loss/train': 1.3419957160949707} 08/31/2021 07:17:16 - INFO - __main__ - Step 99939: {'lr': 0.00012836360704051065, 'samples': 19188288, 'steps': 99938, 'loss/train': 1.3205569982528687} 08/31/2021 07:17:16 - INFO - __main__ - Step 99940: {'lr': 0.00012835897080312668, 'samples': 19188480, 'steps': 99939, 'loss/train': 1.317103624343872} 08/31/2021 07:17:16 - INFO - __main__ - Step 99941: {'lr': 0.00012835433462055223, 'samples': 19188672, 'steps': 99940, 'loss/train': 0.9932810664176941} 08/31/2021 07:17:18 - INFO - __main__ - Step 99942: {'lr': 0.00012834969849278945, 'samples': 19188864, 'steps': 99941, 'loss/train': 1.1751561164855957} 08/31/2021 07:17:18 - INFO - __main__ - Step 99943: {'lr': 0.0001283450624198404, 'samples': 19189056, 'steps': 99942, 'loss/train': 1.4693529605865479} 08/31/2021 07:17:19 - INFO - __main__ - Step 99944: {'lr': 0.0001283404264017072, 'samples': 19189248, 'steps': 99943, 'loss/train': 1.0346901416778564} 08/31/2021 07:17:19 - INFO - __main__ - Step 99945: {'lr': 0.0001283357904383919, 'samples': 19189440, 'steps': 99944, 'loss/train': 1.1849530935287476} 08/31/2021 07:17:19 - INFO - __main__ - Step 99946: {'lr': 0.0001283311545298966, 'samples': 19189632, 'steps': 99945, 'loss/train': 1.1943457126617432} 08/31/2021 07:17:20 - INFO - __main__ - Step 99947: {'lr': 0.00012832651867622345, 'samples': 19189824, 'steps': 99946, 'loss/train': 1.394416332244873} 08/31/2021 07:17:22 - INFO - __main__ - Step 99948: {'lr': 0.00012832188287737446, 'samples': 19190016, 'steps': 99947, 'loss/train': 1.4617518186569214} 08/31/2021 07:17:22 - INFO - __main__ - Step 99949: {'lr': 0.00012831724713335179, 'samples': 19190208, 'steps': 99948, 'loss/train': 0.03128162771463394} 08/31/2021 07:17:23 - INFO - __main__ - Step 99950: {'lr': 0.00012831261144415746, 'samples': 19190400, 'steps': 99949, 'loss/train': 0.023062849417328835} 08/31/2021 07:17:23 - INFO - __main__ - Step 99951: {'lr': 0.0001283079758097936, 'samples': 19190592, 'steps': 99950, 'loss/train': 0.01833854243159294} 08/31/2021 07:17:23 - INFO - __main__ - Step 99952: {'lr': 0.00012830334023026228, 'samples': 19190784, 'steps': 99951, 'loss/train': 1.065147876739502} 08/31/2021 07:17:24 - INFO - __main__ - Step 99953: {'lr': 0.0001282987047055657, 'samples': 19190976, 'steps': 99952, 'loss/train': 0.7828344702720642} 08/31/2021 07:17:25 - INFO - __main__ - Step 99954: {'lr': 0.00012829406923570575, 'samples': 19191168, 'steps': 99953, 'loss/train': 1.0992377996444702} 08/31/2021 07:17:26 - INFO - __main__ - Step 99955: {'lr': 0.00012828943382068458, 'samples': 19191360, 'steps': 99954, 'loss/train': 0.018069829791784286} 08/31/2021 07:17:26 - INFO - __main__ - Step 99956: {'lr': 0.00012828479846050436, 'samples': 19191552, 'steps': 99955, 'loss/train': 0.9866687059402466} 08/31/2021 07:17:27 - INFO - __main__ - Step 99957: {'lr': 0.0001282801631551671, 'samples': 19191744, 'steps': 99956, 'loss/train': 1.5266263484954834} 08/31/2021 07:17:27 - INFO - __main__ - Step 99958: {'lr': 0.00012827552790467496, 'samples': 19191936, 'steps': 99957, 'loss/train': 1.4432053565979004} 08/31/2021 07:17:27 - INFO - __main__ - Step 99959: {'lr': 0.00012827089270902998, 'samples': 19192128, 'steps': 99958, 'loss/train': 0.9058359265327454} 08/31/2021 07:17:29 - INFO - __main__ - Step 99960: {'lr': 0.00012826625756823425, 'samples': 19192320, 'steps': 99959, 'loss/train': 1.5297600030899048} 08/31/2021 07:17:29 - INFO - __main__ - Step 99961: {'lr': 0.00012826162248228985, 'samples': 19192512, 'steps': 99960, 'loss/train': 0.2183658480644226} 08/31/2021 07:17:30 - INFO - __main__ - Step 99962: {'lr': 0.0001282569874511989, 'samples': 19192704, 'steps': 99961, 'loss/train': 0.9781127572059631} 08/31/2021 07:17:30 - INFO - __main__ - Step 99963: {'lr': 0.00012825235247496347, 'samples': 19192896, 'steps': 99962, 'loss/train': 0.8731555342674255} 08/31/2021 07:17:30 - INFO - __main__ - Step 99964: {'lr': 0.00012824771755358565, 'samples': 19193088, 'steps': 99963, 'loss/train': 1.6792149543762207} 08/31/2021 07:17:33 - INFO - __main__ - Step 99965: {'lr': 0.00012824308268706753, 'samples': 19193280, 'steps': 99964, 'loss/train': 1.321476697921753} 08/31/2021 07:17:33 - INFO - __main__ - Step 99966: {'lr': 0.00012823844787541116, 'samples': 19193472, 'steps': 99965, 'loss/train': 1.1992918252944946} 08/31/2021 07:17:33 - INFO - __main__ - Step 99967: {'lr': 0.00012823381311861883, 'samples': 19193664, 'steps': 99966, 'loss/train': 1.381905198097229} 08/31/2021 07:17:34 - INFO - __main__ - Step 99968: {'lr': 0.00012822917841669233, 'samples': 19193856, 'steps': 99967, 'loss/train': 0.7839632034301758} 08/31/2021 07:17:34 - INFO - __main__ - Step 99969: {'lr': 0.0001282245437696339, 'samples': 19194048, 'steps': 99968, 'loss/train': 0.5214457511901855} 08/31/2021 07:17:36 - INFO - __main__ - Step 99970: {'lr': 0.00012821990917744557, 'samples': 19194240, 'steps': 99969, 'loss/train': 1.0228511095046997} 08/31/2021 07:17:36 - INFO - __main__ - Step 99971: {'lr': 0.0001282152746401295, 'samples': 19194432, 'steps': 99970, 'loss/train': 1.7080423831939697} 08/31/2021 07:17:36 - INFO - __main__ - Step 99972: {'lr': 0.00012821064015768776, 'samples': 19194624, 'steps': 99971, 'loss/train': 0.6207467317581177} 08/31/2021 07:17:37 - INFO - __main__ - Step 99973: {'lr': 0.00012820600573012242, 'samples': 19194816, 'steps': 99972, 'loss/train': 1.4313119649887085} 08/31/2021 07:17:37 - INFO - __main__ - Step 99974: {'lr': 0.0001282013713574356, 'samples': 19195008, 'steps': 99973, 'loss/train': 1.1238466501235962} 08/31/2021 07:17:39 - INFO - __main__ - Step 99975: {'lr': 0.0001281967370396293, 'samples': 19195200, 'steps': 99974, 'loss/train': 0.9578401446342468} 08/31/2021 07:17:39 - INFO - __main__ - Step 99976: {'lr': 0.0001281921027767057, 'samples': 19195392, 'steps': 99975, 'loss/train': 1.1759147644042969} 08/31/2021 07:17:40 - INFO - __main__ - Step 99977: {'lr': 0.00012818746856866687, 'samples': 19195584, 'steps': 99976, 'loss/train': 0.5577530860900879} 08/31/2021 07:17:40 - INFO - __main__ - Step 99978: {'lr': 0.00012818283441551497, 'samples': 19195776, 'steps': 99977, 'loss/train': 1.4807103872299194} 08/31/2021 07:17:40 - INFO - __main__ - Step 99979: {'lr': 0.0001281782003172519, 'samples': 19195968, 'steps': 99978, 'loss/train': 0.7207238674163818} 08/31/2021 07:17:42 - INFO - __main__ - Step 99980: {'lr': 0.00012817356627387987, 'samples': 19196160, 'steps': 99979, 'loss/train': 0.14353665709495544} 08/31/2021 07:17:42 - INFO - __main__ - Step 99981: {'lr': 0.00012816893228540096, 'samples': 19196352, 'steps': 99980, 'loss/train': 1.0824509859085083} 08/31/2021 07:17:43 - INFO - __main__ - Step 99982: {'lr': 0.00012816429835181727, 'samples': 19196544, 'steps': 99981, 'loss/train': 0.3874960243701935} 08/31/2021 07:17:43 - INFO - __main__ - Step 99983: {'lr': 0.00012815966447313082, 'samples': 19196736, 'steps': 99982, 'loss/train': 1.4651522636413574} 08/31/2021 07:17:43 - INFO - __main__ - Step 99984: {'lr': 0.00012815503064934376, 'samples': 19196928, 'steps': 99983, 'loss/train': 0.9843025207519531} 08/31/2021 07:17:44 - INFO - __main__ - Step 99985: {'lr': 0.00012815039688045816, 'samples': 19197120, 'steps': 99984, 'loss/train': 1.2773369550704956} 08/31/2021 07:17:45 - INFO - __main__ - Step 99986: {'lr': 0.00012814576316647611, 'samples': 19197312, 'steps': 99985, 'loss/train': 0.9121506810188293} 08/31/2021 07:17:46 - INFO - __main__ - Step 99987: {'lr': 0.0001281411295073997, 'samples': 19197504, 'steps': 99986, 'loss/train': 1.307643175125122} 08/31/2021 07:17:46 - INFO - __main__ - Step 99988: {'lr': 0.00012813649590323102, 'samples': 19197696, 'steps': 99987, 'loss/train': 1.558752179145813} 08/31/2021 07:17:46 - INFO - __main__ - Step 99989: {'lr': 0.00012813186235397224, 'samples': 19197888, 'steps': 99988, 'loss/train': 1.0699830055236816} 08/31/2021 07:17:47 - INFO - __main__ - Step 99990: {'lr': 0.0001281272288596253, 'samples': 19198080, 'steps': 99989, 'loss/train': 1.0952857732772827} 08/31/2021 07:17:48 - INFO - __main__ - Step 99991: {'lr': 0.00012812259542019234, 'samples': 19198272, 'steps': 99990, 'loss/train': 1.1834948062896729} 08/31/2021 07:17:48 - INFO - __main__ - Step 99992: {'lr': 0.00012811796203567543, 'samples': 19198464, 'steps': 99991, 'loss/train': 1.1330357789993286} 08/31/2021 07:17:49 - INFO - __main__ - Step 99993: {'lr': 0.00012811332870607667, 'samples': 19198656, 'steps': 99992, 'loss/train': 1.2952488660812378} 08/31/2021 07:17:49 - INFO - __main__ - Step 99994: {'lr': 0.0001281086954313982, 'samples': 19198848, 'steps': 99993, 'loss/train': 1.1997745037078857} 08/31/2021 07:17:49 - INFO - __main__ - Step 99995: {'lr': 0.00012810406221164207, 'samples': 19199040, 'steps': 99994, 'loss/train': 1.2197797298431396} 08/31/2021 07:17:51 - INFO - __main__ - Step 99996: {'lr': 0.00012809942904681038, 'samples': 19199232, 'steps': 99995, 'loss/train': 1.164495825767517} 08/31/2021 07:17:51 - INFO - __main__ - Step 99997: {'lr': 0.00012809479593690518, 'samples': 19199424, 'steps': 99996, 'loss/train': 0.4638856053352356} 08/31/2021 07:17:52 - INFO - __main__ - Step 99998: {'lr': 0.0001280901628819286, 'samples': 19199616, 'steps': 99997, 'loss/train': 0.6257897019386292} 08/31/2021 07:17:52 - INFO - __main__ - Step 99999: {'lr': 0.0001280855298818827, 'samples': 19199808, 'steps': 99998, 'loss/train': 0.04992919787764549} 08/31/2021 07:17:52 - INFO - __main__ - Step 100000: {'lr': 0.00012808089693676966, 'samples': 19200000, 'steps': 99999, 'loss/train': 0.8388455510139465} 08/31/2021 07:17:54 - INFO - __main__ - Step 100001: {'lr': 0.00012807626404659142, 'samples': 19200192, 'steps': 100000, 'loss/train': 0.8297622799873352} 08/31/2021 07:17:55 - INFO - __main__ - Step 100002: {'lr': 0.00012807163121135012, 'samples': 19200384, 'steps': 100001, 'loss/train': 1.610054850578308} 08/31/2021 07:17:55 - INFO - __main__ - Step 100003: {'lr': 0.00012806699843104786, 'samples': 19200576, 'steps': 100002, 'loss/train': 1.0744518041610718} 08/31/2021 07:17:56 - INFO - __main__ - Step 100004: {'lr': 0.00012806236570568676, 'samples': 19200768, 'steps': 100003, 'loss/train': 0.7389559745788574} 08/31/2021 07:17:56 - INFO - __main__ - Step 100005: {'lr': 0.00012805773303526885, 'samples': 19200960, 'steps': 100004, 'loss/train': 1.6486589908599854} 08/31/2021 07:17:56 - INFO - __main__ - Step 100006: {'lr': 0.00012805310041979622, 'samples': 19201152, 'steps': 100005, 'loss/train': 1.3973579406738281} 08/31/2021 07:17:58 - INFO - __main__ - Step 100007: {'lr': 0.000128048467859271, 'samples': 19201344, 'steps': 100006, 'loss/train': 0.0624818429350853} 08/31/2021 07:17:59 - INFO - __main__ - Step 100008: {'lr': 0.00012804383535369528, 'samples': 19201536, 'steps': 100007, 'loss/train': 1.4767897129058838} 08/31/2021 07:17:59 - INFO - __main__ - Step 100009: {'lr': 0.00012803920290307112, 'samples': 19201728, 'steps': 100008, 'loss/train': 0.01617346704006195} 08/31/2021 07:17:59 - INFO - __main__ - Step 100010: {'lr': 0.00012803457050740059, 'samples': 19201920, 'steps': 100009, 'loss/train': 1.3802217245101929} 08/31/2021 07:18:00 - INFO - __main__ - Step 100011: {'lr': 0.0001280299381666859, 'samples': 19202112, 'steps': 100010, 'loss/train': 0.8215788006782532} 08/31/2021 07:18:00 - INFO - __main__ - Step 100012: {'lr': 0.00012802530588092897, 'samples': 19202304, 'steps': 100011, 'loss/train': 0.14743342995643616} 08/31/2021 07:18:02 - INFO - __main__ - Step 100013: {'lr': 0.00012802067365013192, 'samples': 19202496, 'steps': 100012, 'loss/train': 0.8087685108184814} 08/31/2021 07:18:02 - INFO - __main__ - Step 100014: {'lr': 0.0001280160414742969, 'samples': 19202688, 'steps': 100013, 'loss/train': 0.9044237732887268} 08/31/2021 07:18:02 - INFO - __main__ - Step 100015: {'lr': 0.00012801140935342594, 'samples': 19202880, 'steps': 100014, 'loss/train': 1.1913001537322998} 08/31/2021 07:18:03 - INFO - __main__ - Step 100016: {'lr': 0.0001280067772875212, 'samples': 19203072, 'steps': 100015, 'loss/train': 1.0761910676956177} 08/31/2021 07:18:03 - INFO - __main__ - Step 100017: {'lr': 0.00012800214527658468, 'samples': 19203264, 'steps': 100016, 'loss/train': 1.4888547658920288} 08/31/2021 07:18:05 - INFO - __main__ - Step 100018: {'lr': 0.00012799751332061854, 'samples': 19203456, 'steps': 100017, 'loss/train': 1.284159779548645} 08/31/2021 07:18:06 - INFO - __main__ - Step 100019: {'lr': 0.00012799288141962485, 'samples': 19203648, 'steps': 100018, 'loss/train': 0.950201690196991} 08/31/2021 07:18:06 - INFO - __main__ - Step 100020: {'lr': 0.00012798824957360565, 'samples': 19203840, 'steps': 100019, 'loss/train': 1.1910277605056763} 08/31/2021 07:18:06 - INFO - __main__ - Step 100021: {'lr': 0.00012798361778256306, 'samples': 19204032, 'steps': 100020, 'loss/train': 0.06317026913166046} 08/31/2021 07:18:07 - INFO - __main__ - Step 100022: {'lr': 0.00012797898604649928, 'samples': 19204224, 'steps': 100021, 'loss/train': 0.1152782291173935} 08/31/2021 07:18:09 - INFO - __main__ - Step 100023: {'lr': 0.00012797435436541618, 'samples': 19204416, 'steps': 100022, 'loss/train': 0.03280811011791229} 08/31/2021 07:18:09 - INFO - __main__ - Step 100024: {'lr': 0.00012796972273931595, 'samples': 19204608, 'steps': 100023, 'loss/train': 0.6337260007858276} 08/31/2021 07:18:10 - INFO - __main__ - Step 100025: {'lr': 0.00012796509116820071, 'samples': 19204800, 'steps': 100024, 'loss/train': 0.9945670366287231} 08/31/2021 07:18:10 - INFO - __main__ - Step 100026: {'lr': 0.00012796045965207247, 'samples': 19204992, 'steps': 100025, 'loss/train': 0.16036680340766907} 08/31/2021 07:18:10 - INFO - __main__ - Step 100027: {'lr': 0.00012795582819093344, 'samples': 19205184, 'steps': 100026, 'loss/train': 1.5391786098480225} 08/31/2021 07:18:12 - INFO - __main__ - Step 100028: {'lr': 0.00012795119678478555, 'samples': 19205376, 'steps': 100027, 'loss/train': 0.9435558915138245} 08/31/2021 07:18:12 - INFO - __main__ - Step 100029: {'lr': 0.00012794656543363103, 'samples': 19205568, 'steps': 100028, 'loss/train': 0.03699221834540367} 08/31/2021 07:18:13 - INFO - __main__ - Step 100030: {'lr': 0.00012794193413747184, 'samples': 19205760, 'steps': 100029, 'loss/train': 1.553835391998291} 08/31/2021 07:18:13 - INFO - __main__ - Step 100031: {'lr': 0.00012793730289631017, 'samples': 19205952, 'steps': 100030, 'loss/train': 1.1380586624145508} 08/31/2021 07:18:13 - INFO - __main__ - Step 100032: {'lr': 0.00012793267171014807, 'samples': 19206144, 'steps': 100031, 'loss/train': 1.6915019750595093} 08/31/2021 07:18:15 - INFO - __main__ - Step 100033: {'lr': 0.00012792804057898762, 'samples': 19206336, 'steps': 100032, 'loss/train': 0.738391101360321} 08/31/2021 07:18:16 - INFO - __main__ - Step 100034: {'lr': 0.00012792340950283098, 'samples': 19206528, 'steps': 100033, 'loss/train': 0.9859848022460938} 08/31/2021 07:18:16 - INFO - __main__ - Step 100035: {'lr': 0.00012791877848168014, 'samples': 19206720, 'steps': 100034, 'loss/train': 1.367610216140747} 08/31/2021 07:18:16 - INFO - __main__ - Step 100036: {'lr': 0.00012791414751553716, 'samples': 19206912, 'steps': 100035, 'loss/train': 1.0869853496551514} 08/31/2021 07:18:17 - INFO - __main__ - Step 100037: {'lr': 0.0001279095166044042, 'samples': 19207104, 'steps': 100036, 'loss/train': 1.27237069606781} 08/31/2021 07:18:17 - INFO - __main__ - Step 100038: {'lr': 0.00012790488574828329, 'samples': 19207296, 'steps': 100037, 'loss/train': 1.821224570274353} 08/31/2021 07:18:18 - INFO - __main__ - Step 100039: {'lr': 0.00012790025494717662, 'samples': 19207488, 'steps': 100038, 'loss/train': 1.06119966506958} 08/31/2021 07:18:19 - INFO - __main__ - Step 100040: {'lr': 0.00012789562420108616, 'samples': 19207680, 'steps': 100039, 'loss/train': 1.0717287063598633} 08/31/2021 07:18:19 - INFO - __main__ - Step 100041: {'lr': 0.00012789099351001408, 'samples': 19207872, 'steps': 100040, 'loss/train': 0.7530016303062439} 08/31/2021 07:18:20 - INFO - __main__ - Step 100042: {'lr': 0.00012788636287396242, 'samples': 19208064, 'steps': 100041, 'loss/train': 1.15794837474823} 08/31/2021 07:18:20 - INFO - __main__ - Step 100043: {'lr': 0.00012788173229293326, 'samples': 19208256, 'steps': 100042, 'loss/train': 1.8301312923431396} 08/31/2021 07:18:21 - INFO - __main__ - Step 100044: {'lr': 0.00012787710176692874, 'samples': 19208448, 'steps': 100043, 'loss/train': 1.7191431522369385} 08/31/2021 07:18:22 - INFO - __main__ - Step 100045: {'lr': 0.00012787247129595087, 'samples': 19208640, 'steps': 100044, 'loss/train': 1.6222670078277588} 08/31/2021 07:18:22 - INFO - __main__ - Step 100046: {'lr': 0.00012786784088000182, 'samples': 19208832, 'steps': 100045, 'loss/train': 0.9282597303390503} 08/31/2021 07:18:23 - INFO - __main__ - Step 100047: {'lr': 0.00012786321051908372, 'samples': 19209024, 'steps': 100046, 'loss/train': 0.4395543038845062} 08/31/2021 07:18:23 - INFO - __main__ - Step 100048: {'lr': 0.00012785858021319846, 'samples': 19209216, 'steps': 100047, 'loss/train': 1.4412375688552856} 08/31/2021 07:18:24 - INFO - __main__ - Step 100049: {'lr': 0.00012785394996234827, 'samples': 19209408, 'steps': 100048, 'loss/train': 1.7192729711532593} 08/31/2021 07:18:25 - INFO - __main__ - Step 100050: {'lr': 0.0001278493197665352, 'samples': 19209600, 'steps': 100049, 'loss/train': 1.206614375114441} 08/31/2021 07:18:25 - INFO - __main__ - Step 100051: {'lr': 0.00012784468962576134, 'samples': 19209792, 'steps': 100050, 'loss/train': 1.5381686687469482} 08/31/2021 07:18:26 - INFO - __main__ - Step 100052: {'lr': 0.00012784005954002875, 'samples': 19209984, 'steps': 100051, 'loss/train': 1.0418622493743896} 08/31/2021 07:18:26 - INFO - __main__ - Step 100053: {'lr': 0.00012783542950933958, 'samples': 19210176, 'steps': 100052, 'loss/train': 1.1821805238723755} 08/31/2021 07:18:27 - INFO - __main__ - Step 100054: {'lr': 0.00012783079953369587, 'samples': 19210368, 'steps': 100053, 'loss/train': 0.8265933394432068} 08/31/2021 07:18:28 - INFO - __main__ - Step 100055: {'lr': 0.0001278261696130997, 'samples': 19210560, 'steps': 100054, 'loss/train': 1.5039130449295044} 08/31/2021 07:18:28 - INFO - __main__ - Step 100056: {'lr': 0.00012782153974755318, 'samples': 19210752, 'steps': 100055, 'loss/train': 0.7528966069221497} 08/31/2021 07:18:29 - INFO - __main__ - Step 100057: {'lr': 0.00012781690993705843, 'samples': 19210944, 'steps': 100056, 'loss/train': 1.4948208332061768} 08/31/2021 07:18:29 - INFO - __main__ - Step 100058: {'lr': 0.00012781228018161745, 'samples': 19211136, 'steps': 100057, 'loss/train': 1.1337366104125977} 08/31/2021 07:18:31 - INFO - __main__ - Step 100059: {'lr': 0.00012780765048123235, 'samples': 19211328, 'steps': 100058, 'loss/train': 1.0596610307693481} 08/31/2021 07:18:31 - INFO - __main__ - Step 100060: {'lr': 0.00012780302083590528, 'samples': 19211520, 'steps': 100059, 'loss/train': 1.7190272808074951} 08/31/2021 07:18:31 - INFO - __main__ - Step 100061: {'lr': 0.00012779839124563836, 'samples': 19211712, 'steps': 100060, 'loss/train': 1.4839978218078613} 08/31/2021 07:18:32 - INFO - __main__ - Step 100062: {'lr': 0.00012779376171043348, 'samples': 19211904, 'steps': 100061, 'loss/train': 0.46398356556892395} 08/31/2021 07:18:32 - INFO - __main__ - Step 100063: {'lr': 0.00012778913223029294, 'samples': 19212096, 'steps': 100062, 'loss/train': 1.6899479627609253} 08/31/2021 07:18:33 - INFO - __main__ - Step 100064: {'lr': 0.00012778450280521864, 'samples': 19212288, 'steps': 100063, 'loss/train': 1.131710171699524} 08/31/2021 07:18:34 - INFO - __main__ - Step 100065: {'lr': 0.00012777987343521278, 'samples': 19212480, 'steps': 100064, 'loss/train': 1.1551865339279175} 08/31/2021 07:18:34 - INFO - __main__ - Step 100066: {'lr': 0.0001277752441202774, 'samples': 19212672, 'steps': 100065, 'loss/train': 1.1101667881011963} 08/31/2021 07:18:35 - INFO - __main__ - Step 100067: {'lr': 0.00012777061486041468, 'samples': 19212864, 'steps': 100066, 'loss/train': 0.9883649945259094} 08/31/2021 07:18:35 - INFO - __main__ - Step 100068: {'lr': 0.00012776598565562657, 'samples': 19213056, 'steps': 100067, 'loss/train': 0.8981395959854126} 08/31/2021 07:18:37 - INFO - __main__ - Step 100069: {'lr': 0.00012776135650591526, 'samples': 19213248, 'steps': 100068, 'loss/train': 0.8779296875} 08/31/2021 07:18:37 - INFO - __main__ - Step 100070: {'lr': 0.00012775672741128274, 'samples': 19213440, 'steps': 100069, 'loss/train': 1.4905309677124023} 08/31/2021 07:18:37 - INFO - __main__ - Step 100071: {'lr': 0.00012775209837173122, 'samples': 19213632, 'steps': 100070, 'loss/train': 1.4487751722335815} 08/31/2021 07:18:38 - INFO - __main__ - Step 100072: {'lr': 0.00012774746938726267, 'samples': 19213824, 'steps': 100071, 'loss/train': 1.2300535440444946} 08/31/2021 07:18:38 - INFO - __main__ - Step 100073: {'lr': 0.00012774284045787926, 'samples': 19214016, 'steps': 100072, 'loss/train': 1.1830400228500366} 08/31/2021 07:18:38 - INFO - __main__ - Step 100074: {'lr': 0.0001277382115835831, 'samples': 19214208, 'steps': 100073, 'loss/train': 1.3940585851669312} 08/31/2021 07:18:40 - INFO - __main__ - Step 100075: {'lr': 0.00012773358276437614, 'samples': 19214400, 'steps': 100074, 'loss/train': 0.9490925073623657} 08/31/2021 07:18:41 - INFO - __main__ - Step 100076: {'lr': 0.0001277289540002605, 'samples': 19214592, 'steps': 100075, 'loss/train': 1.0710279941558838} 08/31/2021 07:18:41 - INFO - __main__ - Step 100077: {'lr': 0.0001277243252912384, 'samples': 19214784, 'steps': 100076, 'loss/train': 1.404097318649292} 08/31/2021 07:18:42 - INFO - __main__ - Step 100078: {'lr': 0.00012771969663731176, 'samples': 19214976, 'steps': 100077, 'loss/train': 1.1682885885238647} 08/31/2021 07:18:42 - INFO - __main__ - Step 100079: {'lr': 0.00012771506803848276, 'samples': 19215168, 'steps': 100078, 'loss/train': 0.8981820344924927} 08/31/2021 07:18:43 - INFO - __main__ - Step 100080: {'lr': 0.00012771043949475345, 'samples': 19215360, 'steps': 100079, 'loss/train': 1.2929283380508423} 08/31/2021 07:18:44 - INFO - __main__ - Step 100081: {'lr': 0.00012770581100612593, 'samples': 19215552, 'steps': 100080, 'loss/train': 1.163359522819519} 08/31/2021 07:18:44 - INFO - __main__ - Step 100082: {'lr': 0.00012770118257260228, 'samples': 19215744, 'steps': 100081, 'loss/train': 5.503803730010986} 08/31/2021 07:18:45 - INFO - __main__ - Step 100083: {'lr': 0.0001276965541941846, 'samples': 19215936, 'steps': 100082, 'loss/train': 1.1561752557754517} 08/31/2021 07:18:45 - INFO - __main__ - Step 100084: {'lr': 0.00012769192587087496, 'samples': 19216128, 'steps': 100083, 'loss/train': 1.1697947978973389} 08/31/2021 07:18:46 - INFO - __main__ - Step 100085: {'lr': 0.00012768729760267547, 'samples': 19216320, 'steps': 100084, 'loss/train': 1.2080821990966797} 08/31/2021 07:18:47 - INFO - __main__ - Step 100086: {'lr': 0.00012768266938958817, 'samples': 19216512, 'steps': 100085, 'loss/train': 1.3803424835205078} 08/31/2021 07:18:47 - INFO - __main__ - Step 100087: {'lr': 0.0001276780412316152, 'samples': 19216704, 'steps': 100086, 'loss/train': 1.3494642972946167} 08/31/2021 07:18:48 - INFO - __main__ - Step 100088: {'lr': 0.00012767341312875868, 'samples': 19216896, 'steps': 100087, 'loss/train': 1.2034871578216553} 08/31/2021 07:18:48 - INFO - __main__ - Step 100089: {'lr': 0.0001276687850810206, 'samples': 19217088, 'steps': 100088, 'loss/train': 1.0200155973434448} 08/31/2021 07:18:50 - INFO - __main__ - Step 100090: {'lr': 0.000127664157088403, 'samples': 19217280, 'steps': 100089, 'loss/train': 1.2904821634292603} 08/31/2021 07:18:50 - INFO - __main__ - Step 100091: {'lr': 0.00012765952915090806, 'samples': 19217472, 'steps': 100090, 'loss/train': 1.2537987232208252} 08/31/2021 07:18:50 - INFO - __main__ - Step 100092: {'lr': 0.00012765490126853788, 'samples': 19217664, 'steps': 100091, 'loss/train': 0.8148485422134399} 08/31/2021 07:18:51 - INFO - __main__ - Step 100093: {'lr': 0.0001276502734412945, 'samples': 19217856, 'steps': 100092, 'loss/train': 0.6869409084320068} 08/31/2021 07:18:51 - INFO - __main__ - Step 100094: {'lr': 0.00012764564566918003, 'samples': 19218048, 'steps': 100093, 'loss/train': 1.9744625091552734} 08/31/2021 07:18:52 - INFO - __main__ - Step 100095: {'lr': 0.0001276410179521965, 'samples': 19218240, 'steps': 100094, 'loss/train': 1.74240243434906} 08/31/2021 07:18:53 - INFO - __main__ - Step 100096: {'lr': 0.00012763639029034609, 'samples': 19218432, 'steps': 100095, 'loss/train': 0.9269503355026245} 08/31/2021 07:18:53 - INFO - __main__ - Step 100097: {'lr': 0.0001276317626836308, 'samples': 19218624, 'steps': 100096, 'loss/train': 0.7897220253944397} 08/31/2021 07:18:54 - INFO - __main__ - Step 100098: {'lr': 0.00012762713513205277, 'samples': 19218816, 'steps': 100097, 'loss/train': 1.2939720153808594} 08/31/2021 07:18:54 - INFO - __main__ - Step 100099: {'lr': 0.00012762250763561405, 'samples': 19219008, 'steps': 100098, 'loss/train': 2.131370782852173} 08/31/2021 07:18:55 - INFO - __main__ - Step 100100: {'lr': 0.00012761788019431675, 'samples': 19219200, 'steps': 100099, 'loss/train': 1.1637259721755981} 08/31/2021 07:18:56 - INFO - __main__ - Step 100101: {'lr': 0.00012761325280816305, 'samples': 19219392, 'steps': 100100, 'loss/train': 1.3834149837493896} 08/31/2021 07:18:57 - INFO - __main__ - Step 100102: {'lr': 0.0001276086254771548, 'samples': 19219584, 'steps': 100101, 'loss/train': 0.7720890641212463} 08/31/2021 07:18:57 - INFO - __main__ - Step 100103: {'lr': 0.00012760399820129425, 'samples': 19219776, 'steps': 100102, 'loss/train': 1.8471969366073608} 08/31/2021 07:18:57 - INFO - __main__ - Step 100104: {'lr': 0.00012759937098058343, 'samples': 19219968, 'steps': 100103, 'loss/train': 0.8374856114387512} 08/31/2021 07:18:58 - INFO - __main__ - Step 100105: {'lr': 0.00012759474381502444, 'samples': 19220160, 'steps': 100104, 'loss/train': 0.9107193946838379} 08/31/2021 07:18:59 - INFO - __main__ - Step 100106: {'lr': 0.0001275901167046194, 'samples': 19220352, 'steps': 100105, 'loss/train': 1.3900163173675537} 08/31/2021 07:19:00 - INFO - __main__ - Step 100107: {'lr': 0.00012758548964937033, 'samples': 19220544, 'steps': 100106, 'loss/train': 0.8470945358276367} 08/31/2021 07:19:00 - INFO - __main__ - Step 100108: {'lr': 0.00012758086264927937, 'samples': 19220736, 'steps': 100107, 'loss/train': 0.3511739671230316} 08/31/2021 07:19:00 - INFO - __main__ - Step 100109: {'lr': 0.00012757623570434858, 'samples': 19220928, 'steps': 100108, 'loss/train': 0.9898549914360046} 08/31/2021 07:19:01 - INFO - __main__ - Step 100110: {'lr': 0.00012757160881458004, 'samples': 19221120, 'steps': 100109, 'loss/train': 1.2871081829071045} 08/31/2021 07:19:02 - INFO - __main__ - Step 100111: {'lr': 0.00012756698197997584, 'samples': 19221312, 'steps': 100110, 'loss/train': 1.2006279230117798} 08/31/2021 07:19:03 - INFO - __main__ - Step 100112: {'lr': 0.0001275623552005381, 'samples': 19221504, 'steps': 100111, 'loss/train': 1.1593341827392578} 08/31/2021 07:19:03 - INFO - __main__ - Step 100113: {'lr': 0.00012755772847626885, 'samples': 19221696, 'steps': 100112, 'loss/train': 0.7573296427726746} 08/31/2021 07:19:03 - INFO - __main__ - Step 100114: {'lr': 0.0001275531018071702, 'samples': 19221888, 'steps': 100113, 'loss/train': 1.1544703245162964} 08/31/2021 07:19:04 - INFO - __main__ - Step 100115: {'lr': 0.00012754847519324432, 'samples': 19222080, 'steps': 100114, 'loss/train': 1.125351071357727} 08/31/2021 07:19:05 - INFO - __main__ - Step 100116: {'lr': 0.00012754384863449314, 'samples': 19222272, 'steps': 100115, 'loss/train': 0.8295948505401611} 08/31/2021 07:19:06 - INFO - __main__ - Step 100117: {'lr': 0.00012753922213091877, 'samples': 19222464, 'steps': 100116, 'loss/train': 0.9101735353469849} 08/31/2021 07:19:06 - INFO - __main__ - Step 100118: {'lr': 0.00012753459568252338, 'samples': 19222656, 'steps': 100117, 'loss/train': 0.8727255463600159} 08/31/2021 07:19:06 - INFO - __main__ - Step 100119: {'lr': 0.00012752996928930898, 'samples': 19222848, 'steps': 100118, 'loss/train': 1.368880033493042} 08/31/2021 07:19:07 - INFO - __main__ - Step 100120: {'lr': 0.00012752534295127772, 'samples': 19223040, 'steps': 100119, 'loss/train': 1.163401484489441} 08/31/2021 07:19:08 - INFO - __main__ - Step 100121: {'lr': 0.00012752071666843163, 'samples': 19223232, 'steps': 100120, 'loss/train': 1.1615384817123413} 08/31/2021 07:19:08 - INFO - __main__ - Step 100122: {'lr': 0.00012751609044077278, 'samples': 19223424, 'steps': 100121, 'loss/train': 0.9600424766540527} 08/31/2021 07:19:09 - INFO - __main__ - Step 100123: {'lr': 0.00012751146426830335, 'samples': 19223616, 'steps': 100122, 'loss/train': 1.2993184328079224} 08/31/2021 07:19:09 - INFO - __main__ - Step 100124: {'lr': 0.0001275068381510253, 'samples': 19223808, 'steps': 100123, 'loss/train': 1.159179925918579} 08/31/2021 07:19:10 - INFO - __main__ - Step 100125: {'lr': 0.00012750221208894085, 'samples': 19224000, 'steps': 100124, 'loss/train': 1.099105954170227} 08/31/2021 07:19:12 - INFO - __main__ - Step 100126: {'lr': 0.00012749758608205197, 'samples': 19224192, 'steps': 100125, 'loss/train': 1.0037752389907837} 08/31/2021 07:19:13 - INFO - __main__ - Step 100127: {'lr': 0.0001274929601303608, 'samples': 19224384, 'steps': 100126, 'loss/train': 0.5879133939743042} 08/31/2021 07:19:13 - INFO - __main__ - Step 100128: {'lr': 0.00012748833423386951, 'samples': 19224576, 'steps': 100127, 'loss/train': 1.5079455375671387} 08/31/2021 07:19:13 - INFO - __main__ - Step 100129: {'lr': 0.00012748370839258, 'samples': 19224768, 'steps': 100128, 'loss/train': 0.04987144470214844} 08/31/2021 07:19:14 - INFO - __main__ - Step 100130: {'lr': 0.0001274790826064944, 'samples': 19224960, 'steps': 100129, 'loss/train': 1.6652880907058716} 08/31/2021 07:19:15 - INFO - __main__ - Step 100131: {'lr': 0.00012747445687561487, 'samples': 19225152, 'steps': 100130, 'loss/train': 0.5893763303756714} 08/31/2021 07:19:16 - INFO - __main__ - Step 100132: {'lr': 0.00012746983119994344, 'samples': 19225344, 'steps': 100131, 'loss/train': 1.3362069129943848} 08/31/2021 07:19:16 - INFO - __main__ - Step 100133: {'lr': 0.0001274652055794822, 'samples': 19225536, 'steps': 100132, 'loss/train': 1.403755784034729} 08/31/2021 07:19:16 - INFO - __main__ - Step 100134: {'lr': 0.0001274605800142333, 'samples': 19225728, 'steps': 100133, 'loss/train': 1.2554956674575806} 08/31/2021 07:19:17 - INFO - __main__ - Step 100135: {'lr': 0.00012745595450419872, 'samples': 19225920, 'steps': 100134, 'loss/train': 0.8797351717948914} 08/31/2021 07:19:18 - INFO - __main__ - Step 100136: {'lr': 0.00012745132904938062, 'samples': 19226112, 'steps': 100135, 'loss/train': 1.3714925050735474} 08/31/2021 07:19:19 - INFO - __main__ - Step 100137: {'lr': 0.00012744670364978105, 'samples': 19226304, 'steps': 100136, 'loss/train': 1.7238035202026367} 08/31/2021 07:19:19 - INFO - __main__ - Step 100138: {'lr': 0.00012744207830540214, 'samples': 19226496, 'steps': 100137, 'loss/train': 0.8919591307640076} 08/31/2021 07:19:19 - INFO - __main__ - Step 100139: {'lr': 0.0001274374530162459, 'samples': 19226688, 'steps': 100138, 'loss/train': 1.1213719844818115} 08/31/2021 07:19:20 - INFO - __main__ - Step 100140: {'lr': 0.00012743282778231445, 'samples': 19226880, 'steps': 100139, 'loss/train': 2.1528961658477783} 08/31/2021 07:19:22 - INFO - __main__ - Step 100141: {'lr': 0.0001274282026036099, 'samples': 19227072, 'steps': 100140, 'loss/train': 0.45975908637046814} 08/31/2021 07:19:22 - INFO - __main__ - Step 100142: {'lr': 0.0001274235774801344, 'samples': 19227264, 'steps': 100141, 'loss/train': 0.6194334626197815} 08/31/2021 07:19:22 - INFO - __main__ - Step 100143: {'lr': 0.00012741895241188982, 'samples': 19227456, 'steps': 100142, 'loss/train': 1.167024850845337} 08/31/2021 07:19:23 - INFO - __main__ - Step 100144: {'lr': 0.00012741432739887842, 'samples': 19227648, 'steps': 100143, 'loss/train': 1.6326309442520142} 08/31/2021 07:19:23 - INFO - __main__ - Step 100145: {'lr': 0.0001274097024411022, 'samples': 19227840, 'steps': 100144, 'loss/train': 0.01616877317428589} 08/31/2021 07:19:23 - INFO - __main__ - Step 100146: {'lr': 0.00012740507753856327, 'samples': 19228032, 'steps': 100145, 'loss/train': 0.3228659927845001} 08/31/2021 07:19:24 - INFO - __main__ - Step 100147: {'lr': 0.00012740045269126374, 'samples': 19228224, 'steps': 100146, 'loss/train': 1.2335397005081177} 08/31/2021 07:19:25 - INFO - __main__ - Step 100148: {'lr': 0.00012739582789920566, 'samples': 19228416, 'steps': 100147, 'loss/train': 1.3220566511154175} 08/31/2021 07:19:26 - INFO - __main__ - Step 100149: {'lr': 0.00012739120316239113, 'samples': 19228608, 'steps': 100148, 'loss/train': 1.770614743232727} 08/31/2021 07:19:26 - INFO - __main__ - Step 100150: {'lr': 0.00012738657848082225, 'samples': 19228800, 'steps': 100149, 'loss/train': 0.9645708203315735} 08/31/2021 07:19:26 - INFO - __main__ - Step 100151: {'lr': 0.0001273819538545011, 'samples': 19228992, 'steps': 100150, 'loss/train': 1.5357457399368286} 08/31/2021 07:19:27 - INFO - __main__ - Step 100152: {'lr': 0.00012737732928342968, 'samples': 19229184, 'steps': 100151, 'loss/train': 1.3378159999847412} 08/31/2021 07:19:28 - INFO - __main__ - Step 100153: {'lr': 0.0001273727047676102, 'samples': 19229376, 'steps': 100152, 'loss/train': 1.0850270986557007} 08/31/2021 07:19:29 - INFO - __main__ - Step 100154: {'lr': 0.00012736808030704467, 'samples': 19229568, 'steps': 100153, 'loss/train': 0.7673694491386414} 08/31/2021 07:19:29 - INFO - __main__ - Step 100155: {'lr': 0.00012736345590173525, 'samples': 19229760, 'steps': 100154, 'loss/train': 1.1614646911621094} 08/31/2021 07:19:29 - INFO - __main__ - Step 100156: {'lr': 0.00012735883155168392, 'samples': 19229952, 'steps': 100155, 'loss/train': 1.075524926185608} 08/31/2021 07:19:30 - INFO - __main__ - Step 100157: {'lr': 0.00012735420725689281, 'samples': 19230144, 'steps': 100156, 'loss/train': 1.4226762056350708} 08/31/2021 07:19:31 - INFO - __main__ - Step 100158: {'lr': 0.00012734958301736398, 'samples': 19230336, 'steps': 100157, 'loss/train': 1.11351478099823} 08/31/2021 07:19:32 - INFO - __main__ - Step 100159: {'lr': 0.00012734495883309955, 'samples': 19230528, 'steps': 100158, 'loss/train': 2.5880892276763916} 08/31/2021 07:19:32 - INFO - __main__ - Step 100160: {'lr': 0.00012734033470410155, 'samples': 19230720, 'steps': 100159, 'loss/train': 1.3037569522857666} 08/31/2021 07:19:32 - INFO - __main__ - Step 100161: {'lr': 0.00012733571063037213, 'samples': 19230912, 'steps': 100160, 'loss/train': 0.3112882375717163} 08/31/2021 07:19:33 - INFO - __main__ - Step 100162: {'lr': 0.0001273310866119134, 'samples': 19231104, 'steps': 100161, 'loss/train': 0.7819522023200989} 08/31/2021 07:19:34 - INFO - __main__ - Step 100163: {'lr': 0.00012732646264872733, 'samples': 19231296, 'steps': 100162, 'loss/train': 0.7197356224060059} 08/31/2021 07:19:35 - INFO - __main__ - Step 100164: {'lr': 0.00012732183874081604, 'samples': 19231488, 'steps': 100163, 'loss/train': 1.0743674039840698} 08/31/2021 07:19:35 - INFO - __main__ - Step 100165: {'lr': 0.00012731721488818169, 'samples': 19231680, 'steps': 100164, 'loss/train': 1.0277336835861206} 08/31/2021 07:19:35 - INFO - __main__ - Step 100166: {'lr': 0.00012731259109082627, 'samples': 19231872, 'steps': 100165, 'loss/train': 0.5140492916107178} 08/31/2021 07:19:36 - INFO - __main__ - Step 100167: {'lr': 0.00012730796734875194, 'samples': 19232064, 'steps': 100166, 'loss/train': 1.0638015270233154} 08/31/2021 07:19:37 - INFO - __main__ - Step 100168: {'lr': 0.0001273033436619608, 'samples': 19232256, 'steps': 100167, 'loss/train': 1.358141303062439} 08/31/2021 07:19:38 - INFO - __main__ - Step 100169: {'lr': 0.0001272987200304548, 'samples': 19232448, 'steps': 100168, 'loss/train': 0.7664006948471069} 08/31/2021 07:19:38 - INFO - __main__ - Step 100170: {'lr': 0.0001272940964542361, 'samples': 19232640, 'steps': 100169, 'loss/train': 1.25361168384552} 08/31/2021 07:19:38 - INFO - __main__ - Step 100171: {'lr': 0.00012728947293330685, 'samples': 19232832, 'steps': 100170, 'loss/train': 1.4564878940582275} 08/31/2021 07:19:39 - INFO - __main__ - Step 100172: {'lr': 0.000127284849467669, 'samples': 19233024, 'steps': 100171, 'loss/train': 1.364309310913086} 08/31/2021 07:19:40 - INFO - __main__ - Step 100173: {'lr': 0.0001272802260573247, 'samples': 19233216, 'steps': 100172, 'loss/train': 1.312368631362915} 08/31/2021 07:19:41 - INFO - __main__ - Step 100174: {'lr': 0.00012727560270227607, 'samples': 19233408, 'steps': 100173, 'loss/train': 1.492784023284912} 08/31/2021 07:19:41 - INFO - __main__ - Step 100175: {'lr': 0.00012727097940252514, 'samples': 19233600, 'steps': 100174, 'loss/train': 1.1128677129745483} 08/31/2021 07:19:41 - INFO - __main__ - Step 100176: {'lr': 0.00012726635615807402, 'samples': 19233792, 'steps': 100175, 'loss/train': 0.5087065100669861} 08/31/2021 07:19:42 - INFO - __main__ - Step 100177: {'lr': 0.0001272617329689248, 'samples': 19233984, 'steps': 100176, 'loss/train': 0.9378015995025635} 08/31/2021 07:19:44 - INFO - __main__ - Step 100178: {'lr': 0.00012725710983507954, 'samples': 19234176, 'steps': 100177, 'loss/train': 1.4775190353393555} 08/31/2021 07:19:44 - INFO - __main__ - Step 100179: {'lr': 0.0001272524867565403, 'samples': 19234368, 'steps': 100178, 'loss/train': 0.9167503714561462} 08/31/2021 07:19:44 - INFO - __main__ - Step 100180: {'lr': 0.00012724786373330922, 'samples': 19234560, 'steps': 100179, 'loss/train': 3.1646223068237305} 08/31/2021 07:19:45 - INFO - __main__ - Step 100181: {'lr': 0.00012724324076538837, 'samples': 19234752, 'steps': 100180, 'loss/train': 1.4015246629714966} 08/31/2021 07:19:45 - INFO - __main__ - Step 100182: {'lr': 0.0001272386178527799, 'samples': 19234944, 'steps': 100181, 'loss/train': 0.1072600856423378} 08/31/2021 07:19:47 - INFO - __main__ - Step 100183: {'lr': 0.00012723399499548575, 'samples': 19235136, 'steps': 100182, 'loss/train': 1.3519110679626465} 08/31/2021 07:19:48 - INFO - __main__ - Step 100184: {'lr': 0.00012722937219350803, 'samples': 19235328, 'steps': 100183, 'loss/train': 1.2518815994262695} 08/31/2021 07:19:48 - INFO - __main__ - Step 100185: {'lr': 0.00012722474944684887, 'samples': 19235520, 'steps': 100184, 'loss/train': 1.303746223449707} 08/31/2021 07:19:48 - INFO - __main__ - Step 100186: {'lr': 0.00012722012675551038, 'samples': 19235712, 'steps': 100185, 'loss/train': 0.05180337652564049} 08/31/2021 07:19:49 - INFO - __main__ - Step 100187: {'lr': 0.00012721550411949457, 'samples': 19235904, 'steps': 100186, 'loss/train': 1.7592464685440063} 08/31/2021 07:19:50 - INFO - __main__ - Step 100188: {'lr': 0.00012721088153880357, 'samples': 19236096, 'steps': 100187, 'loss/train': 1.0861870050430298} 08/31/2021 07:19:51 - INFO - __main__ - Step 100189: {'lr': 0.0001272062590134394, 'samples': 19236288, 'steps': 100188, 'loss/train': 0.5125572681427002} 08/31/2021 07:19:51 - INFO - __main__ - Step 100190: {'lr': 0.00012720163654340424, 'samples': 19236480, 'steps': 100189, 'loss/train': 0.07558512687683105} 08/31/2021 07:19:52 - INFO - __main__ - Step 100191: {'lr': 0.00012719701412870014, 'samples': 19236672, 'steps': 100190, 'loss/train': 0.36975669860839844} 08/31/2021 07:19:52 - INFO - __main__ - Step 100192: {'lr': 0.00012719239176932917, 'samples': 19236864, 'steps': 100191, 'loss/train': 1.008338451385498} 08/31/2021 07:19:54 - INFO - __main__ - Step 100193: {'lr': 0.00012718776946529336, 'samples': 19237056, 'steps': 100192, 'loss/train': 1.1451363563537598} 08/31/2021 07:19:54 - INFO - __main__ - Step 100194: {'lr': 0.0001271831472165949, 'samples': 19237248, 'steps': 100193, 'loss/train': 1.0558427572250366} 08/31/2021 07:19:54 - INFO - __main__ - Step 100195: {'lr': 0.0001271785250232359, 'samples': 19237440, 'steps': 100194, 'loss/train': 2.023343324661255} 08/31/2021 07:19:55 - INFO - __main__ - Step 100196: {'lr': 0.0001271739028852183, 'samples': 19237632, 'steps': 100195, 'loss/train': 0.5594295263290405} 08/31/2021 07:19:55 - INFO - __main__ - Step 100197: {'lr': 0.0001271692808025442, 'samples': 19237824, 'steps': 100196, 'loss/train': 1.1416568756103516} 08/31/2021 07:19:56 - INFO - __main__ - Step 100198: {'lr': 0.00012716465877521572, 'samples': 19238016, 'steps': 100197, 'loss/train': 1.0539038181304932} 08/31/2021 07:19:57 - INFO - __main__ - Step 100199: {'lr': 0.000127160036803235, 'samples': 19238208, 'steps': 100198, 'loss/train': 1.252834677696228} 08/31/2021 07:19:57 - INFO - __main__ - Step 100200: {'lr': 0.00012715541488660405, 'samples': 19238400, 'steps': 100199, 'loss/train': 1.2155804634094238} 08/31/2021 07:19:58 - INFO - __main__ - Step 100201: {'lr': 0.00012715079302532496, 'samples': 19238592, 'steps': 100200, 'loss/train': 1.0668160915374756} 08/31/2021 07:19:58 - INFO - __main__ - Step 100202: {'lr': 0.00012714617121939982, 'samples': 19238784, 'steps': 100201, 'loss/train': 1.1732121706008911} 08/31/2021 07:20:00 - INFO - __main__ - Step 100203: {'lr': 0.00012714154946883073, 'samples': 19238976, 'steps': 100202, 'loss/train': 0.9527013897895813} 08/31/2021 07:20:00 - INFO - __main__ - Step 100204: {'lr': 0.00012713692777361973, 'samples': 19239168, 'steps': 100203, 'loss/train': 1.259201169013977} 08/31/2021 07:20:00 - INFO - __main__ - Step 100205: {'lr': 0.00012713230613376896, 'samples': 19239360, 'steps': 100204, 'loss/train': 1.461673617362976} 08/31/2021 07:20:01 - INFO - __main__ - Step 100206: {'lr': 0.0001271276845492805, 'samples': 19239552, 'steps': 100205, 'loss/train': 1.500192403793335} 08/31/2021 07:20:01 - INFO - __main__ - Step 100207: {'lr': 0.0001271230630201564, 'samples': 19239744, 'steps': 100206, 'loss/train': 1.5808682441711426} 08/31/2021 07:20:01 - INFO - __main__ - Step 100208: {'lr': 0.00012711844154639874, 'samples': 19239936, 'steps': 100207, 'loss/train': 1.117234230041504} 08/31/2021 07:20:03 - INFO - __main__ - Step 100209: {'lr': 0.0001271138201280097, 'samples': 19240128, 'steps': 100208, 'loss/train': 1.2059816122055054} 08/31/2021 07:20:03 - INFO - __main__ - Step 100210: {'lr': 0.0001271091987649912, 'samples': 19240320, 'steps': 100209, 'loss/train': 1.0504714250564575} 08/31/2021 07:20:04 - INFO - __main__ - Step 100211: {'lr': 0.0001271045774573454, 'samples': 19240512, 'steps': 100210, 'loss/train': 0.6036858558654785} 08/31/2021 07:20:04 - INFO - __main__ - Step 100212: {'lr': 0.00012709995620507436, 'samples': 19240704, 'steps': 100211, 'loss/train': 1.7164416313171387} 08/31/2021 07:20:04 - INFO - __main__ - Step 100213: {'lr': 0.00012709533500818022, 'samples': 19240896, 'steps': 100212, 'loss/train': 1.5696581602096558} 08/31/2021 07:20:06 - INFO - __main__ - Step 100214: {'lr': 0.00012709071386666498, 'samples': 19241088, 'steps': 100213, 'loss/train': 1.1502233743667603} 08/31/2021 07:20:07 - INFO - __main__ - Step 100215: {'lr': 0.00012708609278053079, 'samples': 19241280, 'steps': 100214, 'loss/train': 1.2522252798080444} 08/31/2021 07:20:07 - INFO - __main__ - Step 100216: {'lr': 0.00012708147174977976, 'samples': 19241472, 'steps': 100215, 'loss/train': 1.275410771369934} 08/31/2021 07:20:07 - INFO - __main__ - Step 100217: {'lr': 0.00012707685077441384, 'samples': 19241664, 'steps': 100216, 'loss/train': 1.1529306173324585} 08/31/2021 07:20:08 - INFO - __main__ - Step 100218: {'lr': 0.00012707222985443523, 'samples': 19241856, 'steps': 100217, 'loss/train': 0.04831381514668465} 08/31/2021 07:20:09 - INFO - __main__ - Step 100219: {'lr': 0.000127067608989846, 'samples': 19242048, 'steps': 100218, 'loss/train': 0.7728003263473511} 08/31/2021 07:20:10 - INFO - __main__ - Step 100220: {'lr': 0.00012706298818064815, 'samples': 19242240, 'steps': 100219, 'loss/train': 2.043827533721924} 08/31/2021 07:20:10 - INFO - __main__ - Step 100221: {'lr': 0.00012705836742684385, 'samples': 19242432, 'steps': 100220, 'loss/train': 1.5234042406082153} 08/31/2021 07:20:10 - INFO - __main__ - Step 100222: {'lr': 0.0001270537467284353, 'samples': 19242624, 'steps': 100221, 'loss/train': 1.3794293403625488} 08/31/2021 07:20:11 - INFO - __main__ - Step 100223: {'lr': 0.00012704912608542423, 'samples': 19242816, 'steps': 100222, 'loss/train': 0.9851841926574707} 08/31/2021 07:20:12 - INFO - __main__ - Step 100224: {'lr': 0.000127044505497813, 'samples': 19243008, 'steps': 100223, 'loss/train': 0.7900869250297546} 08/31/2021 07:20:13 - INFO - __main__ - Step 100225: {'lr': 0.0001270398849656036, 'samples': 19243200, 'steps': 100224, 'loss/train': 1.63540518283844} 08/31/2021 07:20:13 - INFO - __main__ - Step 100226: {'lr': 0.00012703526448879816, 'samples': 19243392, 'steps': 100225, 'loss/train': 0.8214966058731079} 08/31/2021 07:20:13 - INFO - __main__ - Step 100227: {'lr': 0.0001270306440673987, 'samples': 19243584, 'steps': 100226, 'loss/train': 1.2991559505462646} 08/31/2021 07:20:14 - INFO - __main__ - Step 100228: {'lr': 0.00012702602370140735, 'samples': 19243776, 'steps': 100227, 'loss/train': 0.6832723021507263} 08/31/2021 07:20:16 - INFO - __main__ - Step 100229: {'lr': 0.00012702140339082617, 'samples': 19243968, 'steps': 100228, 'loss/train': 0.6873255968093872} 08/31/2021 07:20:16 - INFO - __main__ - Step 100230: {'lr': 0.00012701678313565724, 'samples': 19244160, 'steps': 100229, 'loss/train': 0.7773661017417908} 08/31/2021 07:20:17 - INFO - __main__ - Step 100231: {'lr': 0.00012701216293590264, 'samples': 19244352, 'steps': 100230, 'loss/train': 1.0638296604156494} 08/31/2021 07:20:17 - INFO - __main__ - Step 100232: {'lr': 0.0001270075427915645, 'samples': 19244544, 'steps': 100231, 'loss/train': 1.3199596405029297} 08/31/2021 07:20:17 - INFO - __main__ - Step 100233: {'lr': 0.00012700292270264481, 'samples': 19244736, 'steps': 100232, 'loss/train': 1.2387566566467285} 08/31/2021 07:20:18 - INFO - __main__ - Step 100234: {'lr': 0.00012699830266914576, 'samples': 19244928, 'steps': 100233, 'loss/train': 0.7549978494644165} 08/31/2021 07:20:18 - INFO - __main__ - Step 100235: {'lr': 0.00012699368269106933, 'samples': 19245120, 'steps': 100234, 'loss/train': 0.024142872542142868} 08/31/2021 07:20:20 - INFO - __main__ - Step 100236: {'lr': 0.00012698906276841776, 'samples': 19245312, 'steps': 100235, 'loss/train': 0.05021390691399574} 08/31/2021 07:20:20 - INFO - __main__ - Step 100237: {'lr': 0.00012698444290119292, 'samples': 19245504, 'steps': 100236, 'loss/train': 0.3531807065010071} 08/31/2021 07:20:21 - INFO - __main__ - Step 100238: {'lr': 0.00012697982308939703, 'samples': 19245696, 'steps': 100237, 'loss/train': 0.8300862908363342} 08/31/2021 07:20:21 - INFO - __main__ - Step 100239: {'lr': 0.00012697520333303212, 'samples': 19245888, 'steps': 100238, 'loss/train': 0.9146879315376282} 08/31/2021 07:20:21 - INFO - __main__ - Step 100240: {'lr': 0.00012697058363210026, 'samples': 19246080, 'steps': 100239, 'loss/train': 1.6305756568908691} 08/31/2021 07:20:23 - INFO - __main__ - Step 100241: {'lr': 0.00012696596398660356, 'samples': 19246272, 'steps': 100240, 'loss/train': 1.1569668054580688} 08/31/2021 07:20:24 - INFO - __main__ - Step 100242: {'lr': 0.0001269613443965441, 'samples': 19246464, 'steps': 100241, 'loss/train': 0.803654670715332} 08/31/2021 07:20:24 - INFO - __main__ - Step 100243: {'lr': 0.00012695672486192397, 'samples': 19246656, 'steps': 100242, 'loss/train': 1.4102288484573364} 08/31/2021 07:20:24 - INFO - __main__ - Step 100244: {'lr': 0.00012695210538274525, 'samples': 19246848, 'steps': 100243, 'loss/train': 1.1629586219787598} 08/31/2021 07:20:25 - INFO - __main__ - Step 100245: {'lr': 0.00012694748595901001, 'samples': 19247040, 'steps': 100244, 'loss/train': 1.5876291990280151} 08/31/2021 07:20:26 - INFO - __main__ - Step 100246: {'lr': 0.0001269428665907203, 'samples': 19247232, 'steps': 100245, 'loss/train': 0.032179102301597595} 08/31/2021 07:20:27 - INFO - __main__ - Step 100247: {'lr': 0.00012693824727787837, 'samples': 19247424, 'steps': 100246, 'loss/train': 1.0770121812820435} 08/31/2021 07:20:27 - INFO - __main__ - Step 100248: {'lr': 0.00012693362802048606, 'samples': 19247616, 'steps': 100247, 'loss/train': 0.8539549112319946} 08/31/2021 07:20:27 - INFO - __main__ - Step 100249: {'lr': 0.00012692900881854552, 'samples': 19247808, 'steps': 100248, 'loss/train': 1.647426724433899} 08/31/2021 07:20:28 - INFO - __main__ - Step 100250: {'lr': 0.00012692438967205894, 'samples': 19248000, 'steps': 100249, 'loss/train': 1.2220628261566162} 08/31/2021 07:20:29 - INFO - __main__ - Step 100251: {'lr': 0.00012691977058102826, 'samples': 19248192, 'steps': 100250, 'loss/train': 1.5475761890411377} 08/31/2021 07:20:30 - INFO - __main__ - Step 100252: {'lr': 0.0001269151515454557, 'samples': 19248384, 'steps': 100251, 'loss/train': 1.4981423616409302} 08/31/2021 07:20:30 - INFO - __main__ - Step 100253: {'lr': 0.00012691053256534324, 'samples': 19248576, 'steps': 100252, 'loss/train': 0.9992868900299072} 08/31/2021 07:20:30 - INFO - __main__ - Step 100254: {'lr': 0.000126905913640693, 'samples': 19248768, 'steps': 100253, 'loss/train': 1.9263638257980347} 08/31/2021 07:20:31 - INFO - __main__ - Step 100255: {'lr': 0.00012690129477150702, 'samples': 19248960, 'steps': 100254, 'loss/train': 1.4719892740249634} 08/31/2021 07:20:32 - INFO - __main__ - Step 100256: {'lr': 0.00012689667595778745, 'samples': 19249152, 'steps': 100255, 'loss/train': 1.5462082624435425} 08/31/2021 07:20:33 - INFO - __main__ - Step 100257: {'lr': 0.00012689205719953634, 'samples': 19249344, 'steps': 100256, 'loss/train': 2.025225877761841} 08/31/2021 07:20:33 - INFO - __main__ - Step 100258: {'lr': 0.00012688743849675584, 'samples': 19249536, 'steps': 100257, 'loss/train': 1.1654777526855469} 08/31/2021 07:20:33 - INFO - __main__ - Step 100259: {'lr': 0.0001268828198494479, 'samples': 19249728, 'steps': 100258, 'loss/train': 1.2335429191589355} 08/31/2021 07:20:34 - INFO - __main__ - Step 100260: {'lr': 0.00012687820125761466, 'samples': 19249920, 'steps': 100259, 'loss/train': 0.761099636554718} 08/31/2021 07:20:34 - INFO - __main__ - Step 100261: {'lr': 0.00012687358272125819, 'samples': 19250112, 'steps': 100260, 'loss/train': 1.6281839609146118} 08/31/2021 07:20:36 - INFO - __main__ - Step 100262: {'lr': 0.00012686896424038058, 'samples': 19250304, 'steps': 100261, 'loss/train': 1.5048556327819824} 08/31/2021 07:20:36 - INFO - __main__ - Step 100263: {'lr': 0.0001268643458149839, 'samples': 19250496, 'steps': 100262, 'loss/train': 1.2511775493621826} 08/31/2021 07:20:37 - INFO - __main__ - Step 100264: {'lr': 0.00012685972744507027, 'samples': 19250688, 'steps': 100263, 'loss/train': 1.036303997039795} 08/31/2021 07:20:37 - INFO - __main__ - Step 100265: {'lr': 0.00012685510913064174, 'samples': 19250880, 'steps': 100264, 'loss/train': 1.1976258754730225} 08/31/2021 07:20:37 - INFO - __main__ - Step 100266: {'lr': 0.00012685049087170043, 'samples': 19251072, 'steps': 100265, 'loss/train': 0.5641679763793945} 08/31/2021 07:20:40 - INFO - __main__ - Step 100267: {'lr': 0.00012684587266824832, 'samples': 19251264, 'steps': 100266, 'loss/train': 1.7264000177383423} 08/31/2021 07:20:40 - INFO - __main__ - Step 100268: {'lr': 0.00012684125452028762, 'samples': 19251456, 'steps': 100267, 'loss/train': 0.37342339754104614} 08/31/2021 07:20:41 - INFO - __main__ - Step 100269: {'lr': 0.0001268366364278204, 'samples': 19251648, 'steps': 100268, 'loss/train': 0.32200706005096436} 08/31/2021 07:20:41 - INFO - __main__ - Step 100270: {'lr': 0.0001268320183908486, 'samples': 19251840, 'steps': 100269, 'loss/train': 0.3010866940021515} 08/31/2021 07:20:41 - INFO - __main__ - Step 100271: {'lr': 0.00012682740040937442, 'samples': 19252032, 'steps': 100270, 'loss/train': 0.27907559275627136} 08/31/2021 07:20:42 - INFO - __main__ - Step 100272: {'lr': 0.0001268227824833999, 'samples': 19252224, 'steps': 100271, 'loss/train': 0.8296771049499512} 08/31/2021 07:20:42 - INFO - __main__ - Step 100273: {'lr': 0.00012681816461292713, 'samples': 19252416, 'steps': 100272, 'loss/train': 1.7761313915252686} 08/31/2021 07:20:44 - INFO - __main__ - Step 100274: {'lr': 0.0001268135467979582, 'samples': 19252608, 'steps': 100273, 'loss/train': 1.3394538164138794} 08/31/2021 07:20:44 - INFO - __main__ - Step 100275: {'lr': 0.0001268089290384952, 'samples': 19252800, 'steps': 100274, 'loss/train': 0.024731798097491264} 08/31/2021 07:20:44 - INFO - __main__ - Step 100276: {'lr': 0.00012680431133454018, 'samples': 19252992, 'steps': 100275, 'loss/train': 1.5137803554534912} 08/31/2021 07:20:45 - INFO - __main__ - Step 100277: {'lr': 0.00012679969368609522, 'samples': 19253184, 'steps': 100276, 'loss/train': 1.2323942184448242} 08/31/2021 07:20:45 - INFO - __main__ - Step 100278: {'lr': 0.00012679507609316242, 'samples': 19253376, 'steps': 100277, 'loss/train': 0.991345226764679} 08/31/2021 07:20:47 - INFO - __main__ - Step 100279: {'lr': 0.00012679045855574388, 'samples': 19253568, 'steps': 100278, 'loss/train': 1.7605178356170654} 08/31/2021 07:20:47 - INFO - __main__ - Step 100280: {'lr': 0.00012678584107384178, 'samples': 19253760, 'steps': 100279, 'loss/train': 1.1513725519180298} 08/31/2021 07:20:48 - INFO - __main__ - Step 100281: {'lr': 0.0001267812236474579, 'samples': 19253952, 'steps': 100280, 'loss/train': 1.0807132720947266} 08/31/2021 07:20:48 - INFO - __main__ - Step 100282: {'lr': 0.00012677660627659457, 'samples': 19254144, 'steps': 100281, 'loss/train': 0.9494248032569885} 08/31/2021 07:20:48 - INFO - __main__ - Step 100283: {'lr': 0.0001267719889612538, 'samples': 19254336, 'steps': 100282, 'loss/train': 0.8829890489578247} 08/31/2021 07:20:50 - INFO - __main__ - Step 100284: {'lr': 0.00012676737170143763, 'samples': 19254528, 'steps': 100283, 'loss/train': 1.564279556274414} 08/31/2021 07:20:50 - INFO - __main__ - Step 100285: {'lr': 0.00012676275449714818, 'samples': 19254720, 'steps': 100284, 'loss/train': 1.5849984884262085} 08/31/2021 07:20:51 - INFO - __main__ - Step 100286: {'lr': 0.00012675813734838755, 'samples': 19254912, 'steps': 100285, 'loss/train': 0.8118892908096313} 08/31/2021 07:20:51 - INFO - __main__ - Step 100287: {'lr': 0.00012675352025515779, 'samples': 19255104, 'steps': 100286, 'loss/train': 1.196958065032959} 08/31/2021 07:20:51 - INFO - __main__ - Step 100288: {'lr': 0.00012674890321746102, 'samples': 19255296, 'steps': 100287, 'loss/train': 1.7640018463134766} 08/31/2021 07:20:54 - INFO - __main__ - Step 100289: {'lr': 0.00012674428623529928, 'samples': 19255488, 'steps': 100288, 'loss/train': 0.9396986961364746} 08/31/2021 07:20:54 - INFO - __main__ - Step 100290: {'lr': 0.00012673966930867476, 'samples': 19255680, 'steps': 100289, 'loss/train': 1.3067916631698608} 08/31/2021 07:20:54 - INFO - __main__ - Step 100291: {'lr': 0.00012673505243758932, 'samples': 19255872, 'steps': 100290, 'loss/train': 2.345221757888794} 08/31/2021 07:20:55 - INFO - __main__ - Step 100292: {'lr': 0.0001267304356220452, 'samples': 19256064, 'steps': 100291, 'loss/train': 1.0613733530044556} 08/31/2021 07:20:55 - INFO - __main__ - Step 100293: {'lr': 0.00012672581886204442, 'samples': 19256256, 'steps': 100292, 'loss/train': 1.0028091669082642} 08/31/2021 07:20:56 - INFO - __main__ - Step 100294: {'lr': 0.00012672120215758909, 'samples': 19256448, 'steps': 100293, 'loss/train': 0.974739134311676} 08/31/2021 07:20:57 - INFO - __main__ - Step 100295: {'lr': 0.00012671658550868128, 'samples': 19256640, 'steps': 100294, 'loss/train': 0.9512900710105896} 08/31/2021 07:20:58 - INFO - __main__ - Step 100296: {'lr': 0.00012671196891532308, 'samples': 19256832, 'steps': 100295, 'loss/train': 1.1763527393341064} 08/31/2021 07:20:58 - INFO - __main__ - Step 100297: {'lr': 0.00012670735237751656, 'samples': 19257024, 'steps': 100296, 'loss/train': 0.34997573494911194} 08/31/2021 07:20:58 - INFO - __main__ - Step 100298: {'lr': 0.00012670273589526383, 'samples': 19257216, 'steps': 100297, 'loss/train': 1.4202643632888794} 08/31/2021 07:20:59 - INFO - __main__ - Step 100299: {'lr': 0.00012669811946856691, 'samples': 19257408, 'steps': 100298, 'loss/train': 1.533759355545044} 08/31/2021 07:21:00 - INFO - __main__ - Step 100300: {'lr': 0.0001266935030974279, 'samples': 19257600, 'steps': 100299, 'loss/train': 1.3395212888717651} 08/31/2021 07:21:01 - INFO - __main__ - Step 100301: {'lr': 0.00012668888678184892, 'samples': 19257792, 'steps': 100300, 'loss/train': 1.225488543510437} 08/31/2021 07:21:01 - INFO - __main__ - Step 100302: {'lr': 0.00012668427052183208, 'samples': 19257984, 'steps': 100301, 'loss/train': 1.3476694822311401} 08/31/2021 07:21:01 - INFO - __main__ - Step 100303: {'lr': 0.00012667965431737942, 'samples': 19258176, 'steps': 100302, 'loss/train': 1.817333459854126} 08/31/2021 07:21:02 - INFO - __main__ - Step 100304: {'lr': 0.00012667503816849295, 'samples': 19258368, 'steps': 100303, 'loss/train': 1.3029149770736694} 08/31/2021 07:21:04 - INFO - __main__ - Step 100305: {'lr': 0.00012667042207517476, 'samples': 19258560, 'steps': 100304, 'loss/train': 1.0688612461090088} 08/31/2021 07:21:04 - INFO - __main__ - Step 100306: {'lr': 0.000126665806037427, 'samples': 19258752, 'steps': 100305, 'loss/train': 0.7835975885391235} 08/31/2021 07:21:04 - INFO - __main__ - Step 100307: {'lr': 0.00012666119005525173, 'samples': 19258944, 'steps': 100306, 'loss/train': 0.9757846593856812} 08/31/2021 07:21:05 - INFO - __main__ - Step 100308: {'lr': 0.00012665657412865106, 'samples': 19259136, 'steps': 100307, 'loss/train': 1.3405735492706299} 08/31/2021 07:21:05 - INFO - __main__ - Step 100309: {'lr': 0.00012665195825762698, 'samples': 19259328, 'steps': 100308, 'loss/train': 1.1504147052764893} 08/31/2021 07:21:05 - INFO - __main__ - Step 100310: {'lr': 0.00012664734244218165, 'samples': 19259520, 'steps': 100309, 'loss/train': 1.2693592309951782} 08/31/2021 07:21:07 - INFO - __main__ - Step 100311: {'lr': 0.0001266427266823171, 'samples': 19259712, 'steps': 100310, 'loss/train': 0.028958134353160858} 08/31/2021 07:21:07 - INFO - __main__ - Step 100312: {'lr': 0.00012663811097803545, 'samples': 19259904, 'steps': 100311, 'loss/train': 0.9966191053390503} 08/31/2021 07:21:08 - INFO - __main__ - Step 100313: {'lr': 0.00012663349532933876, 'samples': 19260096, 'steps': 100312, 'loss/train': 0.9900615811347961} 08/31/2021 07:21:08 - INFO - __main__ - Step 100314: {'lr': 0.00012662887973622914, 'samples': 19260288, 'steps': 100313, 'loss/train': 0.9206687808036804} 08/31/2021 07:21:08 - INFO - __main__ - Step 100315: {'lr': 0.00012662426419870863, 'samples': 19260480, 'steps': 100314, 'loss/train': 1.5986089706420898} 08/31/2021 07:21:10 - INFO - __main__ - Step 100316: {'lr': 0.0001266196487167794, 'samples': 19260672, 'steps': 100315, 'loss/train': 1.4030041694641113} 08/31/2021 07:21:10 - INFO - __main__ - Step 100317: {'lr': 0.00012661503329044338, 'samples': 19260864, 'steps': 100316, 'loss/train': 1.725233554840088} 08/31/2021 07:21:11 - INFO - __main__ - Step 100318: {'lr': 0.00012661041791970268, 'samples': 19261056, 'steps': 100317, 'loss/train': 0.9725667834281921} 08/31/2021 07:21:11 - INFO - __main__ - Step 100319: {'lr': 0.00012660580260455946, 'samples': 19261248, 'steps': 100318, 'loss/train': 0.5526949763298035} 08/31/2021 07:21:11 - INFO - __main__ - Step 100320: {'lr': 0.00012660118734501575, 'samples': 19261440, 'steps': 100319, 'loss/train': 0.721118688583374} 08/31/2021 07:21:13 - INFO - __main__ - Step 100321: {'lr': 0.00012659657214107365, 'samples': 19261632, 'steps': 100320, 'loss/train': 1.596856713294983} 08/31/2021 07:21:13 - INFO - __main__ - Step 100322: {'lr': 0.00012659195699273523, 'samples': 19261824, 'steps': 100321, 'loss/train': 1.4379109144210815} 08/31/2021 07:21:14 - INFO - __main__ - Step 100323: {'lr': 0.00012658734190000253, 'samples': 19262016, 'steps': 100322, 'loss/train': 1.3657608032226562} 08/31/2021 07:21:14 - INFO - __main__ - Step 100324: {'lr': 0.00012658272686287772, 'samples': 19262208, 'steps': 100323, 'loss/train': 0.6136654615402222} 08/31/2021 07:21:14 - INFO - __main__ - Step 100325: {'lr': 0.0001265781118813628, 'samples': 19262400, 'steps': 100324, 'loss/train': 0.7147376537322998} 08/31/2021 07:21:16 - INFO - __main__ - Step 100326: {'lr': 0.00012657349695545988, 'samples': 19262592, 'steps': 100325, 'loss/train': 0.8189196586608887} 08/31/2021 07:21:17 - INFO - __main__ - Step 100327: {'lr': 0.00012656888208517107, 'samples': 19262784, 'steps': 100326, 'loss/train': 0.04832777753472328} 08/31/2021 07:21:17 - INFO - __main__ - Step 100328: {'lr': 0.0001265642672704984, 'samples': 19262976, 'steps': 100327, 'loss/train': 1.5765661001205444} 08/31/2021 07:21:17 - INFO - __main__ - Step 100329: {'lr': 0.00012655965251144396, 'samples': 19263168, 'steps': 100328, 'loss/train': 0.525155782699585} 08/31/2021 07:21:18 - INFO - __main__ - Step 100330: {'lr': 0.0001265550378080099, 'samples': 19263360, 'steps': 100329, 'loss/train': 2.2005629539489746} 08/31/2021 07:21:20 - INFO - __main__ - Step 100331: {'lr': 0.00012655042316019822, 'samples': 19263552, 'steps': 100330, 'loss/train': 0.8729051351547241} 08/31/2021 07:21:20 - INFO - __main__ - Step 100332: {'lr': 0.00012654580856801096, 'samples': 19263744, 'steps': 100331, 'loss/train': 1.3780211210250854} 08/31/2021 07:21:21 - INFO - __main__ - Step 100333: {'lr': 0.00012654119403145026, 'samples': 19263936, 'steps': 100332, 'loss/train': 0.017298107966780663} 08/31/2021 07:21:21 - INFO - __main__ - Step 100334: {'lr': 0.00012653657955051818, 'samples': 19264128, 'steps': 100333, 'loss/train': 0.6246251463890076} 08/31/2021 07:21:21 - INFO - __main__ - Step 100335: {'lr': 0.00012653196512521682, 'samples': 19264320, 'steps': 100334, 'loss/train': 0.0627736896276474} 08/31/2021 07:21:22 - INFO - __main__ - Step 100336: {'lr': 0.00012652735075554825, 'samples': 19264512, 'steps': 100335, 'loss/train': 0.8594437837600708} 08/31/2021 07:21:23 - INFO - __main__ - Step 100337: {'lr': 0.00012652273644151457, 'samples': 19264704, 'steps': 100336, 'loss/train': 1.010487675666809} 08/31/2021 07:21:24 - INFO - __main__ - Step 100338: {'lr': 0.00012651812218311781, 'samples': 19264896, 'steps': 100337, 'loss/train': 0.42141464352607727} 08/31/2021 07:21:24 - INFO - __main__ - Step 100339: {'lr': 0.0001265135079803601, 'samples': 19265088, 'steps': 100338, 'loss/train': 0.895580530166626} 08/31/2021 07:21:24 - INFO - __main__ - Step 100340: {'lr': 0.00012650889383324348, 'samples': 19265280, 'steps': 100339, 'loss/train': 1.2016961574554443} 08/31/2021 07:21:25 - INFO - __main__ - Step 100341: {'lr': 0.00012650427974177005, 'samples': 19265472, 'steps': 100340, 'loss/train': 1.1215876340866089} 08/31/2021 07:21:26 - INFO - __main__ - Step 100342: {'lr': 0.0001264996657059419, 'samples': 19265664, 'steps': 100341, 'loss/train': 0.9970541000366211} 08/31/2021 07:21:27 - INFO - __main__ - Step 100343: {'lr': 0.0001264950517257612, 'samples': 19265856, 'steps': 100342, 'loss/train': 1.9003682136535645} 08/31/2021 07:21:27 - INFO - __main__ - Step 100344: {'lr': 0.00012649043780122983, 'samples': 19266048, 'steps': 100343, 'loss/train': 1.5350310802459717} 08/31/2021 07:21:27 - INFO - __main__ - Step 100345: {'lr': 0.0001264858239323499, 'samples': 19266240, 'steps': 100344, 'loss/train': 1.1676973104476929} 08/31/2021 07:21:28 - INFO - __main__ - Step 100346: {'lr': 0.0001264812101191236, 'samples': 19266432, 'steps': 100345, 'loss/train': 0.10233143717050552} 08/31/2021 07:21:28 - INFO - __main__ - Step 100347: {'lr': 0.00012647659636155298, 'samples': 19266624, 'steps': 100346, 'loss/train': 0.47105672955513} 08/31/2021 07:21:30 - INFO - __main__ - Step 100348: {'lr': 0.0001264719826596401, 'samples': 19266816, 'steps': 100347, 'loss/train': 1.6885381937026978} 08/31/2021 07:21:30 - INFO - __main__ - Step 100349: {'lr': 0.00012646736901338702, 'samples': 19267008, 'steps': 100348, 'loss/train': 1.2230641841888428} 08/31/2021 07:21:31 - INFO - __main__ - Step 100350: {'lr': 0.0001264627554227958, 'samples': 19267200, 'steps': 100349, 'loss/train': 1.2264083623886108} 08/31/2021 07:21:31 - INFO - __main__ - Step 100351: {'lr': 0.0001264581418878686, 'samples': 19267392, 'steps': 100350, 'loss/train': 1.7446573972702026} 08/31/2021 07:21:31 - INFO - __main__ - Step 100352: {'lr': 0.00012645352840860743, 'samples': 19267584, 'steps': 100351, 'loss/train': 1.9131678342819214} 08/31/2021 07:21:33 - INFO - __main__ - Step 100353: {'lr': 0.00012644891498501444, 'samples': 19267776, 'steps': 100352, 'loss/train': 1.332550287246704} 08/31/2021 07:21:34 - INFO - __main__ - Step 100354: {'lr': 0.00012644430161709162, 'samples': 19267968, 'steps': 100353, 'loss/train': 1.0559029579162598} 08/31/2021 07:21:34 - INFO - __main__ - Step 100355: {'lr': 0.0001264396883048411, 'samples': 19268160, 'steps': 100354, 'loss/train': 0.03556877002120018} 08/31/2021 07:21:34 - INFO - __main__ - Step 100356: {'lr': 0.00012643507504826496, 'samples': 19268352, 'steps': 100355, 'loss/train': 1.3860753774642944} 08/31/2021 07:21:35 - INFO - __main__ - Step 100357: {'lr': 0.00012643046184736533, 'samples': 19268544, 'steps': 100356, 'loss/train': 1.6048858165740967} 08/31/2021 07:21:36 - INFO - __main__ - Step 100358: {'lr': 0.00012642584870214418, 'samples': 19268736, 'steps': 100357, 'loss/train': 1.3707376718521118} 08/31/2021 07:21:37 - INFO - __main__ - Step 100359: {'lr': 0.0001264212356126036, 'samples': 19268928, 'steps': 100358, 'loss/train': 1.310282588005066} 08/31/2021 07:21:37 - INFO - __main__ - Step 100360: {'lr': 0.00012641662257874574, 'samples': 19269120, 'steps': 100359, 'loss/train': 1.3626033067703247} 08/31/2021 07:21:37 - INFO - __main__ - Step 100361: {'lr': 0.0001264120096005726, 'samples': 19269312, 'steps': 100360, 'loss/train': 1.1304056644439697} 08/31/2021 07:21:38 - INFO - __main__ - Step 100362: {'lr': 0.0001264073966780863, 'samples': 19269504, 'steps': 100361, 'loss/train': 1.3733187913894653} 08/31/2021 07:21:39 - INFO - __main__ - Step 100363: {'lr': 0.00012640278381128895, 'samples': 19269696, 'steps': 100362, 'loss/train': 1.1359443664550781} 08/31/2021 07:21:40 - INFO - __main__ - Step 100364: {'lr': 0.0001263981710001826, 'samples': 19269888, 'steps': 100363, 'loss/train': 1.0140193700790405} 08/31/2021 07:21:40 - INFO - __main__ - Step 100365: {'lr': 0.00012639355824476935, 'samples': 19270080, 'steps': 100364, 'loss/train': 1.1942631006240845} 08/31/2021 07:21:40 - INFO - __main__ - Step 100366: {'lr': 0.0001263889455450512, 'samples': 19270272, 'steps': 100365, 'loss/train': 0.868809163570404} 08/31/2021 07:21:41 - INFO - __main__ - Step 100367: {'lr': 0.00012638433290103028, 'samples': 19270464, 'steps': 100366, 'loss/train': 1.166144609451294} 08/31/2021 07:21:42 - INFO - __main__ - Step 100368: {'lr': 0.00012637972031270874, 'samples': 19270656, 'steps': 100367, 'loss/train': 1.0124648809432983} 08/31/2021 07:21:43 - INFO - __main__ - Step 100369: {'lr': 0.00012637510778008853, 'samples': 19270848, 'steps': 100368, 'loss/train': 0.7000548839569092} 08/31/2021 07:21:43 - INFO - __main__ - Step 100370: {'lr': 0.0001263704953031719, 'samples': 19271040, 'steps': 100369, 'loss/train': 1.450197696685791} 08/31/2021 07:21:43 - INFO - __main__ - Step 100371: {'lr': 0.0001263658828819607, 'samples': 19271232, 'steps': 100370, 'loss/train': 1.2610359191894531} 08/31/2021 07:21:44 - INFO - __main__ - Step 100372: {'lr': 0.00012636127051645718, 'samples': 19271424, 'steps': 100371, 'loss/train': 0.8412570953369141} 08/31/2021 07:21:45 - INFO - __main__ - Step 100373: {'lr': 0.00012635665820666332, 'samples': 19271616, 'steps': 100372, 'loss/train': 0.5954692959785461} 08/31/2021 07:21:46 - INFO - __main__ - Step 100374: {'lr': 0.00012635204595258127, 'samples': 19271808, 'steps': 100373, 'loss/train': 0.5354041457176208} 08/31/2021 07:21:46 - INFO - __main__ - Step 100375: {'lr': 0.00012634743375421306, 'samples': 19272000, 'steps': 100374, 'loss/train': 0.5214121341705322} 08/31/2021 07:21:46 - INFO - __main__ - Step 100376: {'lr': 0.0001263428216115608, 'samples': 19272192, 'steps': 100375, 'loss/train': 1.787928581237793} 08/31/2021 07:21:47 - INFO - __main__ - Step 100377: {'lr': 0.00012633820952462655, 'samples': 19272384, 'steps': 100376, 'loss/train': 1.3171442747116089} 08/31/2021 07:21:48 - INFO - __main__ - Step 100378: {'lr': 0.0001263335974934124, 'samples': 19272576, 'steps': 100377, 'loss/train': 2.444467306137085} 08/31/2021 07:21:49 - INFO - __main__ - Step 100379: {'lr': 0.0001263289855179204, 'samples': 19272768, 'steps': 100378, 'loss/train': 0.9052068591117859} 08/31/2021 07:21:49 - INFO - __main__ - Step 100380: {'lr': 0.0001263243735981527, 'samples': 19272960, 'steps': 100379, 'loss/train': 0.9804367423057556} 08/31/2021 07:21:49 - INFO - __main__ - Step 100381: {'lr': 0.00012631976173411126, 'samples': 19273152, 'steps': 100380, 'loss/train': 0.9920803308486938} 08/31/2021 07:21:50 - INFO - __main__ - Step 100382: {'lr': 0.00012631514992579828, 'samples': 19273344, 'steps': 100381, 'loss/train': 1.2218327522277832} 08/31/2021 07:21:51 - INFO - __main__ - Step 100383: {'lr': 0.00012631053817321574, 'samples': 19273536, 'steps': 100382, 'loss/train': 1.315305471420288} 08/31/2021 07:21:52 - INFO - __main__ - Step 100384: {'lr': 0.0001263059264763659, 'samples': 19273728, 'steps': 100383, 'loss/train': 1.0948022603988647} 08/31/2021 07:21:52 - INFO - __main__ - Step 100385: {'lr': 0.00012630131483525058, 'samples': 19273920, 'steps': 100384, 'loss/train': 0.8505386114120483} 08/31/2021 07:21:52 - INFO - __main__ - Step 100386: {'lr': 0.00012629670324987202, 'samples': 19274112, 'steps': 100385, 'loss/train': 1.2939658164978027} 08/31/2021 07:21:53 - INFO - __main__ - Step 100387: {'lr': 0.0001262920917202322, 'samples': 19274304, 'steps': 100386, 'loss/train': 1.2911159992218018} 08/31/2021 07:21:54 - INFO - __main__ - Step 100388: {'lr': 0.0001262874802463333, 'samples': 19274496, 'steps': 100387, 'loss/train': 0.89754718542099} 08/31/2021 07:21:55 - INFO - __main__ - Step 100389: {'lr': 0.00012628286882817737, 'samples': 19274688, 'steps': 100388, 'loss/train': 0.9343141317367554} 08/31/2021 07:21:55 - INFO - __main__ - Step 100390: {'lr': 0.0001262782574657664, 'samples': 19274880, 'steps': 100389, 'loss/train': 0.8164887428283691} 08/31/2021 07:21:55 - INFO - __main__ - Step 100391: {'lr': 0.00012627364615910259, 'samples': 19275072, 'steps': 100390, 'loss/train': 0.9216713309288025} 08/31/2021 07:21:56 - INFO - __main__ - Step 100392: {'lr': 0.00012626903490818792, 'samples': 19275264, 'steps': 100391, 'loss/train': 1.1301122903823853} 08/31/2021 07:21:56 - INFO - __main__ - Step 100393: {'lr': 0.00012626442371302456, 'samples': 19275456, 'steps': 100392, 'loss/train': 0.9068832993507385} 08/31/2021 07:21:58 - INFO - __main__ - Step 100394: {'lr': 0.00012625981257361453, 'samples': 19275648, 'steps': 100393, 'loss/train': 0.6890780329704285} 08/31/2021 07:21:58 - INFO - __main__ - Step 100395: {'lr': 0.0001262552014899599, 'samples': 19275840, 'steps': 100394, 'loss/train': 0.9390223622322083} 08/31/2021 07:21:59 - INFO - __main__ - Step 100396: {'lr': 0.00012625059046206277, 'samples': 19276032, 'steps': 100395, 'loss/train': 0.2811412811279297} 08/31/2021 07:21:59 - INFO - __main__ - Step 100397: {'lr': 0.00012624597948992532, 'samples': 19276224, 'steps': 100396, 'loss/train': 1.3429710865020752} 08/31/2021 07:22:00 - INFO - __main__ - Step 100398: {'lr': 0.00012624136857354945, 'samples': 19276416, 'steps': 100397, 'loss/train': 1.39130437374115} 08/31/2021 07:22:02 - INFO - __main__ - Step 100399: {'lr': 0.00012623675771293726, 'samples': 19276608, 'steps': 100398, 'loss/train': 1.0149272680282593} 08/31/2021 07:22:02 - INFO - __main__ - Step 100400: {'lr': 0.00012623214690809094, 'samples': 19276800, 'steps': 100399, 'loss/train': 0.1327429562807083} 08/31/2021 07:22:03 - INFO - __main__ - Step 100401: {'lr': 0.00012622753615901245, 'samples': 19276992, 'steps': 100400, 'loss/train': 0.5622549057006836} 08/31/2021 07:22:03 - INFO - __main__ - Step 100402: {'lr': 0.00012622292546570393, 'samples': 19277184, 'steps': 100401, 'loss/train': 1.018294095993042} 08/31/2021 07:22:03 - INFO - __main__ - Step 100403: {'lr': 0.00012621831482816749, 'samples': 19277376, 'steps': 100402, 'loss/train': 1.4907715320587158} 08/31/2021 07:22:05 - INFO - __main__ - Step 100404: {'lr': 0.0001262137042464051, 'samples': 19277568, 'steps': 100403, 'loss/train': 0.5980422496795654} 08/31/2021 07:22:05 - INFO - __main__ - Step 100405: {'lr': 0.00012620909372041894, 'samples': 19277760, 'steps': 100404, 'loss/train': 1.5873974561691284} 08/31/2021 07:22:06 - INFO - __main__ - Step 100406: {'lr': 0.00012620448325021105, 'samples': 19277952, 'steps': 100405, 'loss/train': 0.3894239068031311} 08/31/2021 07:22:06 - INFO - __main__ - Step 100407: {'lr': 0.0001261998728357835, 'samples': 19278144, 'steps': 100406, 'loss/train': 1.0558533668518066} 08/31/2021 07:22:06 - INFO - __main__ - Step 100408: {'lr': 0.00012619526247713842, 'samples': 19278336, 'steps': 100407, 'loss/train': 0.8275063633918762} 08/31/2021 07:22:07 - INFO - __main__ - Step 100409: {'lr': 0.0001261906521742778, 'samples': 19278528, 'steps': 100408, 'loss/train': 0.8457481265068054} 08/31/2021 07:22:08 - INFO - __main__ - Step 100410: {'lr': 0.0001261860419272039, 'samples': 19278720, 'steps': 100409, 'loss/train': 1.5522133111953735} 08/31/2021 07:22:09 - INFO - __main__ - Step 100411: {'lr': 0.0001261814317359185, 'samples': 19278912, 'steps': 100410, 'loss/train': 1.3016854524612427} 08/31/2021 07:22:09 - INFO - __main__ - Step 100412: {'lr': 0.00012617682160042388, 'samples': 19279104, 'steps': 100411, 'loss/train': 1.309647798538208} 08/31/2021 07:22:09 - INFO - __main__ - Step 100413: {'lr': 0.00012617221152072205, 'samples': 19279296, 'steps': 100412, 'loss/train': 1.53251051902771} 08/31/2021 07:22:10 - INFO - __main__ - Step 100414: {'lr': 0.00012616760149681517, 'samples': 19279488, 'steps': 100413, 'loss/train': 1.3187543153762817} 08/31/2021 07:22:11 - INFO - __main__ - Step 100415: {'lr': 0.0001261629915287052, 'samples': 19279680, 'steps': 100414, 'loss/train': 1.506401538848877} 08/31/2021 07:22:11 - INFO - __main__ - Step 100416: {'lr': 0.0001261583816163943, 'samples': 19279872, 'steps': 100415, 'loss/train': 1.8387587070465088} 08/31/2021 07:22:12 - INFO - __main__ - Step 100417: {'lr': 0.00012615377175988448, 'samples': 19280064, 'steps': 100416, 'loss/train': 1.1413323879241943} 08/31/2021 07:22:12 - INFO - __main__ - Step 100418: {'lr': 0.0001261491619591779, 'samples': 19280256, 'steps': 100417, 'loss/train': 1.1824110746383667} 08/31/2021 07:22:13 - INFO - __main__ - Step 100419: {'lr': 0.0001261445522142766, 'samples': 19280448, 'steps': 100418, 'loss/train': 0.9907718896865845} 08/31/2021 07:22:14 - INFO - __main__ - Step 100420: {'lr': 0.00012613994252518262, 'samples': 19280640, 'steps': 100419, 'loss/train': 1.1912744045257568} 08/31/2021 07:22:15 - INFO - __main__ - Step 100421: {'lr': 0.0001261353328918981, 'samples': 19280832, 'steps': 100420, 'loss/train': 0.3559425175189972} 08/31/2021 07:22:15 - INFO - __main__ - Step 100422: {'lr': 0.00012613072331442508, 'samples': 19281024, 'steps': 100421, 'loss/train': 0.9297517538070679} 08/31/2021 07:22:15 - INFO - __main__ - Step 100423: {'lr': 0.0001261261137927656, 'samples': 19281216, 'steps': 100422, 'loss/train': 0.8387694358825684} 08/31/2021 07:22:16 - INFO - __main__ - Step 100424: {'lr': 0.00012612150432692195, 'samples': 19281408, 'steps': 100423, 'loss/train': 1.3425233364105225} 08/31/2021 07:22:17 - INFO - __main__ - Step 100425: {'lr': 0.00012611689491689594, 'samples': 19281600, 'steps': 100424, 'loss/train': 1.1732330322265625} 08/31/2021 07:22:18 - INFO - __main__ - Step 100426: {'lr': 0.00012611228556268973, 'samples': 19281792, 'steps': 100425, 'loss/train': 0.9238210320472717} 08/31/2021 07:22:18 - INFO - __main__ - Step 100427: {'lr': 0.00012610767626430536, 'samples': 19281984, 'steps': 100426, 'loss/train': 0.8877953886985779} 08/31/2021 07:22:18 - INFO - __main__ - Step 100428: {'lr': 0.000126103067021745, 'samples': 19282176, 'steps': 100427, 'loss/train': 1.1921610832214355} 08/31/2021 07:22:19 - INFO - __main__ - Step 100429: {'lr': 0.0001260984578350107, 'samples': 19282368, 'steps': 100428, 'loss/train': 1.2358815670013428} 08/31/2021 07:22:20 - INFO - __main__ - Step 100430: {'lr': 0.0001260938487041045, 'samples': 19282560, 'steps': 100429, 'loss/train': 1.11981999874115} 08/31/2021 07:22:21 - INFO - __main__ - Step 100431: {'lr': 0.00012608923962902853, 'samples': 19282752, 'steps': 100430, 'loss/train': 1.191864013671875} 08/31/2021 07:22:21 - INFO - __main__ - Step 100432: {'lr': 0.00012608463060978482, 'samples': 19282944, 'steps': 100431, 'loss/train': 1.0797998905181885} 08/31/2021 07:22:21 - INFO - __main__ - Step 100433: {'lr': 0.00012608002164637543, 'samples': 19283136, 'steps': 100432, 'loss/train': 1.1021018028259277} 08/31/2021 07:22:22 - INFO - __main__ - Step 100434: {'lr': 0.00012607541273880251, 'samples': 19283328, 'steps': 100433, 'loss/train': 0.5609205365180969} 08/31/2021 07:22:23 - INFO - __main__ - Step 100435: {'lr': 0.0001260708038870681, 'samples': 19283520, 'steps': 100434, 'loss/train': 2.3339219093322754} 08/31/2021 07:22:24 - INFO - __main__ - Step 100436: {'lr': 0.00012606619509117424, 'samples': 19283712, 'steps': 100435, 'loss/train': 1.122658610343933} 08/31/2021 07:22:24 - INFO - __main__ - Step 100437: {'lr': 0.00012606158635112316, 'samples': 19283904, 'steps': 100436, 'loss/train': 1.287429928779602} 08/31/2021 07:22:24 - INFO - __main__ - Step 100438: {'lr': 0.0001260569776669167, 'samples': 19284096, 'steps': 100437, 'loss/train': 1.6144814491271973} 08/31/2021 07:22:25 - INFO - __main__ - Step 100439: {'lr': 0.0001260523690385571, 'samples': 19284288, 'steps': 100438, 'loss/train': 1.0565426349639893} 08/31/2021 07:22:25 - INFO - __main__ - Step 100440: {'lr': 0.00012604776046604634, 'samples': 19284480, 'steps': 100439, 'loss/train': 1.3410708904266357} 08/31/2021 07:22:27 - INFO - __main__ - Step 100441: {'lr': 0.00012604315194938658, 'samples': 19284672, 'steps': 100440, 'loss/train': 1.9481427669525146} 08/31/2021 07:22:28 - INFO - __main__ - Step 100442: {'lr': 0.00012603854348857985, 'samples': 19284864, 'steps': 100441, 'loss/train': 1.5418757200241089} 08/31/2021 07:22:28 - INFO - __main__ - Step 100443: {'lr': 0.00012603393508362824, 'samples': 19285056, 'steps': 100442, 'loss/train': 0.5755658745765686} 08/31/2021 07:22:28 - INFO - __main__ - Step 100444: {'lr': 0.00012602932673453382, 'samples': 19285248, 'steps': 100443, 'loss/train': 0.8463659286499023} 08/31/2021 07:22:29 - INFO - __main__ - Step 100445: {'lr': 0.00012602471844129867, 'samples': 19285440, 'steps': 100444, 'loss/train': 1.3793131113052368} 08/31/2021 07:22:30 - INFO - __main__ - Step 100446: {'lr': 0.0001260201102039249, 'samples': 19285632, 'steps': 100445, 'loss/train': 1.113417387008667} 08/31/2021 07:22:31 - INFO - __main__ - Step 100447: {'lr': 0.00012601550202241452, 'samples': 19285824, 'steps': 100446, 'loss/train': 0.6749491691589355} 08/31/2021 07:22:31 - INFO - __main__ - Step 100448: {'lr': 0.00012601089389676964, 'samples': 19286016, 'steps': 100447, 'loss/train': 1.1672502756118774} 08/31/2021 07:22:31 - INFO - __main__ - Step 100449: {'lr': 0.00012600628582699235, 'samples': 19286208, 'steps': 100448, 'loss/train': 1.4735043048858643} 08/31/2021 07:22:32 - INFO - __main__ - Step 100450: {'lr': 0.00012600167781308473, 'samples': 19286400, 'steps': 100449, 'loss/train': 0.2229299247264862} 08/31/2021 07:22:34 - INFO - __main__ - Step 100451: {'lr': 0.00012599706985504892, 'samples': 19286592, 'steps': 100450, 'loss/train': 1.2771327495574951} 08/31/2021 07:22:34 - INFO - __main__ - Step 100452: {'lr': 0.00012599246195288681, 'samples': 19286784, 'steps': 100451, 'loss/train': 1.1390273571014404} 08/31/2021 07:22:35 - INFO - __main__ - Step 100453: {'lr': 0.00012598785410660056, 'samples': 19286976, 'steps': 100452, 'loss/train': 0.9521041512489319} 08/31/2021 07:22:35 - INFO - __main__ - Step 100454: {'lr': 0.00012598324631619235, 'samples': 19287168, 'steps': 100453, 'loss/train': 1.4999395608901978} 08/31/2021 07:22:35 - INFO - __main__ - Step 100455: {'lr': 0.00012597863858166412, 'samples': 19287360, 'steps': 100454, 'loss/train': 1.2896324396133423} 08/31/2021 07:22:37 - INFO - __main__ - Step 100456: {'lr': 0.00012597403090301802, 'samples': 19287552, 'steps': 100455, 'loss/train': 0.050744958221912384} 08/31/2021 07:22:37 - INFO - __main__ - Step 100457: {'lr': 0.00012596942328025606, 'samples': 19287744, 'steps': 100456, 'loss/train': 0.3305818736553192} 08/31/2021 07:22:38 - INFO - __main__ - Step 100458: {'lr': 0.00012596481571338042, 'samples': 19287936, 'steps': 100457, 'loss/train': 0.7901273369789124} 08/31/2021 07:22:38 - INFO - __main__ - Step 100459: {'lr': 0.00012596020820239312, 'samples': 19288128, 'steps': 100458, 'loss/train': 1.3144724369049072} 08/31/2021 07:22:38 - INFO - __main__ - Step 100460: {'lr': 0.00012595560074729622, 'samples': 19288320, 'steps': 100459, 'loss/train': 1.1372729539871216} 08/31/2021 07:22:40 - INFO - __main__ - Step 100461: {'lr': 0.0001259509933480918, 'samples': 19288512, 'steps': 100460, 'loss/train': 1.1569288969039917} 08/31/2021 07:22:40 - INFO - __main__ - Step 100462: {'lr': 0.00012594638600478197, 'samples': 19288704, 'steps': 100461, 'loss/train': 1.052534818649292} 08/31/2021 07:22:41 - INFO - __main__ - Step 100463: {'lr': 0.0001259417787173688, 'samples': 19288896, 'steps': 100462, 'loss/train': 1.0972254276275635} 08/31/2021 07:22:41 - INFO - __main__ - Step 100464: {'lr': 0.00012593717148585436, 'samples': 19289088, 'steps': 100463, 'loss/train': 1.5551462173461914} 08/31/2021 07:22:41 - INFO - __main__ - Step 100465: {'lr': 0.0001259325643102407, 'samples': 19289280, 'steps': 100464, 'loss/train': 1.1251134872436523} 08/31/2021 07:22:42 - INFO - __main__ - Step 100466: {'lr': 0.0001259279571905299, 'samples': 19289472, 'steps': 100465, 'loss/train': 1.2585104703903198} 08/31/2021 07:22:43 - INFO - __main__ - Step 100467: {'lr': 0.00012592335012672403, 'samples': 19289664, 'steps': 100466, 'loss/train': 1.3721657991409302} 08/31/2021 07:22:44 - INFO - __main__ - Step 100468: {'lr': 0.0001259187431188252, 'samples': 19289856, 'steps': 100467, 'loss/train': 1.6572179794311523} 08/31/2021 07:22:44 - INFO - __main__ - Step 100469: {'lr': 0.00012591413616683548, 'samples': 19290048, 'steps': 100468, 'loss/train': 1.0247231721878052} 08/31/2021 07:22:45 - INFO - __main__ - Step 100470: {'lr': 0.00012590952927075692, 'samples': 19290240, 'steps': 100469, 'loss/train': 1.006393313407898} 08/31/2021 07:22:45 - INFO - __main__ - Step 100471: {'lr': 0.0001259049224305916, 'samples': 19290432, 'steps': 100470, 'loss/train': 1.4087833166122437} 08/31/2021 07:22:46 - INFO - __main__ - Step 100472: {'lr': 0.00012590031564634164, 'samples': 19290624, 'steps': 100471, 'loss/train': 1.4844024181365967} 08/31/2021 07:22:47 - INFO - __main__ - Step 100473: {'lr': 0.00012589570891800907, 'samples': 19290816, 'steps': 100472, 'loss/train': 0.9836045503616333} 08/31/2021 07:22:47 - INFO - __main__ - Step 100474: {'lr': 0.00012589110224559593, 'samples': 19291008, 'steps': 100473, 'loss/train': 1.2800769805908203} 08/31/2021 07:22:48 - INFO - __main__ - Step 100475: {'lr': 0.0001258864956291044, 'samples': 19291200, 'steps': 100474, 'loss/train': 1.19801926612854} 08/31/2021 07:22:48 - INFO - __main__ - Step 100476: {'lr': 0.00012588188906853648, 'samples': 19291392, 'steps': 100475, 'loss/train': 1.3819770812988281} 08/31/2021 07:22:50 - INFO - __main__ - Step 100477: {'lr': 0.00012587728256389425, 'samples': 19291584, 'steps': 100476, 'loss/train': 0.9700078368186951} 08/31/2021 07:22:50 - INFO - __main__ - Step 100478: {'lr': 0.00012587267611517995, 'samples': 19291776, 'steps': 100477, 'loss/train': 0.7726835012435913} 08/31/2021 07:22:50 - INFO - __main__ - Step 100479: {'lr': 0.00012586806972239535, 'samples': 19291968, 'steps': 100478, 'loss/train': 3.1754207611083984} 08/31/2021 07:22:51 - INFO - __main__ - Step 100480: {'lr': 0.00012586346338554273, 'samples': 19292160, 'steps': 100479, 'loss/train': 1.2260503768920898} 08/31/2021 07:22:51 - INFO - __main__ - Step 100481: {'lr': 0.00012585885710462408, 'samples': 19292352, 'steps': 100480, 'loss/train': 1.2341395616531372} 08/31/2021 07:22:52 - INFO - __main__ - Step 100482: {'lr': 0.00012585425087964153, 'samples': 19292544, 'steps': 100481, 'loss/train': 1.1160396337509155} 08/31/2021 07:22:53 - INFO - __main__ - Step 100483: {'lr': 0.00012584964471059712, 'samples': 19292736, 'steps': 100482, 'loss/train': 0.5059953331947327} 08/31/2021 07:22:53 - INFO - __main__ - Step 100484: {'lr': 0.00012584503859749296, 'samples': 19292928, 'steps': 100483, 'loss/train': 1.184385061264038} 08/31/2021 07:22:54 - INFO - __main__ - Step 100485: {'lr': 0.0001258404325403311, 'samples': 19293120, 'steps': 100484, 'loss/train': 0.9114646911621094} 08/31/2021 07:22:54 - INFO - __main__ - Step 100486: {'lr': 0.00012583582653911369, 'samples': 19293312, 'steps': 100485, 'loss/train': 1.0275335311889648} 08/31/2021 07:22:54 - INFO - __main__ - Step 100487: {'lr': 0.00012583122059384267, 'samples': 19293504, 'steps': 100486, 'loss/train': 1.455222249031067} 08/31/2021 07:22:56 - INFO - __main__ - Step 100488: {'lr': 0.00012582661470452022, 'samples': 19293696, 'steps': 100487, 'loss/train': 1.2056145668029785} 08/31/2021 07:22:57 - INFO - __main__ - Step 100489: {'lr': 0.00012582200887114835, 'samples': 19293888, 'steps': 100488, 'loss/train': 1.953246831893921} 08/31/2021 07:22:57 - INFO - __main__ - Step 100490: {'lr': 0.00012581740309372918, 'samples': 19294080, 'steps': 100489, 'loss/train': 2.1339523792266846} 08/31/2021 07:22:57 - INFO - __main__ - Step 100491: {'lr': 0.00012581279737226486, 'samples': 19294272, 'steps': 100490, 'loss/train': 0.5258262157440186} 08/31/2021 07:22:58 - INFO - __main__ - Step 100492: {'lr': 0.0001258081917067573, 'samples': 19294464, 'steps': 100491, 'loss/train': 0.017004750669002533} 08/31/2021 07:22:58 - INFO - __main__ - Step 100493: {'lr': 0.00012580358609720865, 'samples': 19294656, 'steps': 100492, 'loss/train': 0.015985148027539253} 08/31/2021 07:23:00 - INFO - __main__ - Step 100494: {'lr': 0.00012579898054362098, 'samples': 19294848, 'steps': 100493, 'loss/train': 0.040430158376693726} 08/31/2021 07:23:00 - INFO - __main__ - Step 100495: {'lr': 0.00012579437504599638, 'samples': 19295040, 'steps': 100494, 'loss/train': 1.3859331607818604} 08/31/2021 07:23:01 - INFO - __main__ - Step 100496: {'lr': 0.00012578976960433692, 'samples': 19295232, 'steps': 100495, 'loss/train': 1.4673341512680054} 08/31/2021 07:23:01 - INFO - __main__ - Step 100497: {'lr': 0.00012578516421864465, 'samples': 19295424, 'steps': 100496, 'loss/train': 1.3636276721954346} 08/31/2021 07:23:01 - INFO - __main__ - Step 100498: {'lr': 0.0001257805588889217, 'samples': 19295616, 'steps': 100497, 'loss/train': 1.5362522602081299} 08/31/2021 07:23:03 - INFO - __main__ - Step 100499: {'lr': 0.00012577595361517007, 'samples': 19295808, 'steps': 100498, 'loss/train': 0.041218437254428864} 08/31/2021 07:23:03 - INFO - __main__ - Step 100500: {'lr': 0.0001257713483973919, 'samples': 19296000, 'steps': 100499, 'loss/train': 1.6562608480453491} 08/31/2021 07:23:04 - INFO - __main__ - Step 100501: {'lr': 0.00012576674323558929, 'samples': 19296192, 'steps': 100500, 'loss/train': 1.172236680984497} 08/31/2021 07:23:04 - INFO - __main__ - Step 100502: {'lr': 0.00012576213812976424, 'samples': 19296384, 'steps': 100501, 'loss/train': 1.1201053857803345} 08/31/2021 07:23:04 - INFO - __main__ - Step 100503: {'lr': 0.00012575753307991883, 'samples': 19296576, 'steps': 100502, 'loss/train': 1.5956021547317505} 08/31/2021 07:23:06 - INFO - __main__ - Step 100504: {'lr': 0.00012575292808605516, 'samples': 19296768, 'steps': 100503, 'loss/train': 0.9594897627830505} 08/31/2021 07:23:07 - INFO - __main__ - Step 100505: {'lr': 0.00012574832314817542, 'samples': 19296960, 'steps': 100504, 'loss/train': 1.1261991262435913} 08/31/2021 07:23:07 - INFO - __main__ - Step 100506: {'lr': 0.00012574371826628146, 'samples': 19297152, 'steps': 100505, 'loss/train': 0.968102753162384} 08/31/2021 07:23:08 - INFO - __main__ - Step 100507: {'lr': 0.00012573911344037546, 'samples': 19297344, 'steps': 100506, 'loss/train': 1.9543383121490479} 08/31/2021 07:23:08 - INFO - __main__ - Step 100508: {'lr': 0.0001257345086704595, 'samples': 19297536, 'steps': 100507, 'loss/train': 1.5118111371994019} 08/31/2021 07:23:10 - INFO - __main__ - Step 100509: {'lr': 0.00012572990395653567, 'samples': 19297728, 'steps': 100508, 'loss/train': 1.1013023853302002} 08/31/2021 07:23:10 - INFO - __main__ - Step 100510: {'lr': 0.00012572529929860598, 'samples': 19297920, 'steps': 100509, 'loss/train': 0.19255580008029938} 08/31/2021 07:23:11 - INFO - __main__ - Step 100511: {'lr': 0.00012572069469667257, 'samples': 19298112, 'steps': 100510, 'loss/train': 1.5407661199569702} 08/31/2021 07:23:11 - INFO - __main__ - Step 100512: {'lr': 0.00012571609015073754, 'samples': 19298304, 'steps': 100511, 'loss/train': 0.07813314348459244} 08/31/2021 07:23:12 - INFO - __main__ - Step 100513: {'lr': 0.00012571148566080286, 'samples': 19298496, 'steps': 100512, 'loss/train': 0.7128002643585205} 08/31/2021 07:23:12 - INFO - __main__ - Step 100514: {'lr': 0.00012570688122687075, 'samples': 19298688, 'steps': 100513, 'loss/train': 1.1066315174102783} 08/31/2021 07:23:13 - INFO - __main__ - Step 100515: {'lr': 0.00012570227684894315, 'samples': 19298880, 'steps': 100514, 'loss/train': 0.9077932238578796} 08/31/2021 07:23:14 - INFO - __main__ - Step 100516: {'lr': 0.00012569767252702227, 'samples': 19299072, 'steps': 100515, 'loss/train': 1.4494693279266357} 08/31/2021 07:23:14 - INFO - __main__ - Step 100517: {'lr': 0.00012569306826111003, 'samples': 19299264, 'steps': 100516, 'loss/train': 1.4219415187835693} 08/31/2021 07:23:14 - INFO - __main__ - Step 100518: {'lr': 0.00012568846405120853, 'samples': 19299456, 'steps': 100517, 'loss/train': 1.3821388483047485} 08/31/2021 07:23:15 - INFO - __main__ - Step 100519: {'lr': 0.00012568385989731996, 'samples': 19299648, 'steps': 100518, 'loss/train': 0.8682149052619934} 08/31/2021 07:23:16 - INFO - __main__ - Step 100520: {'lr': 0.00012567925579944628, 'samples': 19299840, 'steps': 100519, 'loss/train': 1.0336930751800537} 08/31/2021 07:23:17 - INFO - __main__ - Step 100521: {'lr': 0.0001256746517575896, 'samples': 19300032, 'steps': 100520, 'loss/train': 1.2564697265625} 08/31/2021 07:23:17 - INFO - __main__ - Step 100522: {'lr': 0.00012567004777175203, 'samples': 19300224, 'steps': 100521, 'loss/train': 0.4537471532821655} 08/31/2021 07:23:17 - INFO - __main__ - Step 100523: {'lr': 0.00012566544384193563, 'samples': 19300416, 'steps': 100522, 'loss/train': 0.7364866733551025} 08/31/2021 07:23:18 - INFO - __main__ - Step 100524: {'lr': 0.00012566083996814242, 'samples': 19300608, 'steps': 100523, 'loss/train': 0.9279020428657532} 08/31/2021 07:23:19 - INFO - __main__ - Step 100525: {'lr': 0.00012565623615037451, 'samples': 19300800, 'steps': 100524, 'loss/train': 0.8243870735168457} 08/31/2021 07:23:20 - INFO - __main__ - Step 100526: {'lr': 0.00012565163238863403, 'samples': 19300992, 'steps': 100525, 'loss/train': 1.1502315998077393} 08/31/2021 07:23:20 - INFO - __main__ - Step 100527: {'lr': 0.00012564702868292311, 'samples': 19301184, 'steps': 100526, 'loss/train': 1.504940390586853} 08/31/2021 07:23:20 - INFO - __main__ - Step 100528: {'lr': 0.00012564242503324357, 'samples': 19301376, 'steps': 100527, 'loss/train': 0.5797358751296997} 08/31/2021 07:23:21 - INFO - __main__ - Step 100529: {'lr': 0.0001256378214395977, 'samples': 19301568, 'steps': 100528, 'loss/train': 0.8718259334564209} 08/31/2021 07:23:23 - INFO - __main__ - Step 100530: {'lr': 0.00012563321790198746, 'samples': 19301760, 'steps': 100529, 'loss/train': 1.1162090301513672} 08/31/2021 07:23:23 - INFO - __main__ - Step 100531: {'lr': 0.00012562861442041496, 'samples': 19301952, 'steps': 100530, 'loss/train': 0.028471458703279495} 08/31/2021 07:23:23 - INFO - __main__ - Step 100532: {'lr': 0.0001256240109948823, 'samples': 19302144, 'steps': 100531, 'loss/train': 0.7997885346412659} 08/31/2021 07:23:24 - INFO - __main__ - Step 100533: {'lr': 0.00012561940762539155, 'samples': 19302336, 'steps': 100532, 'loss/train': 0.016757046803832054} 08/31/2021 07:23:24 - INFO - __main__ - Step 100534: {'lr': 0.00012561480431194479, 'samples': 19302528, 'steps': 100533, 'loss/train': 0.016570139676332474} 08/31/2021 07:23:24 - INFO - __main__ - Step 100535: {'lr': 0.00012561020105454406, 'samples': 19302720, 'steps': 100534, 'loss/train': 2.107757329940796} 08/31/2021 07:23:26 - INFO - __main__ - Step 100536: {'lr': 0.00012560559785319145, 'samples': 19302912, 'steps': 100535, 'loss/train': 1.1788825988769531} 08/31/2021 07:23:27 - INFO - __main__ - Step 100537: {'lr': 0.00012560099470788915, 'samples': 19303104, 'steps': 100536, 'loss/train': 0.973484218120575} 08/31/2021 07:23:27 - INFO - __main__ - Step 100538: {'lr': 0.000125596391618639, 'samples': 19303296, 'steps': 100537, 'loss/train': 0.8075686693191528} 08/31/2021 07:23:27 - INFO - __main__ - Step 100539: {'lr': 0.00012559178858544324, 'samples': 19303488, 'steps': 100538, 'loss/train': 1.0508757829666138} 08/31/2021 07:23:28 - INFO - __main__ - Step 100540: {'lr': 0.00012558718560830388, 'samples': 19303680, 'steps': 100539, 'loss/train': 0.9422228336334229} 08/31/2021 07:23:28 - INFO - __main__ - Step 100541: {'lr': 0.000125582582687223, 'samples': 19303872, 'steps': 100540, 'loss/train': 0.5863433480262756} 08/31/2021 07:23:30 - INFO - __main__ - Step 100542: {'lr': 0.0001255779798222027, 'samples': 19304064, 'steps': 100541, 'loss/train': 1.4076498746871948} 08/31/2021 07:23:31 - INFO - __main__ - Step 100543: {'lr': 0.00012557337701324503, 'samples': 19304256, 'steps': 100542, 'loss/train': 1.7558982372283936} 08/31/2021 07:23:31 - INFO - __main__ - Step 100544: {'lr': 0.0001255687742603521, 'samples': 19304448, 'steps': 100543, 'loss/train': 1.7652969360351562} 08/31/2021 07:23:31 - INFO - __main__ - Step 100545: {'lr': 0.00012556417156352597, 'samples': 19304640, 'steps': 100544, 'loss/train': 0.7443817257881165} 08/31/2021 07:23:32 - INFO - __main__ - Step 100546: {'lr': 0.00012555956892276865, 'samples': 19304832, 'steps': 100545, 'loss/train': 1.6425057649612427} 08/31/2021 07:23:32 - INFO - __main__ - Step 100547: {'lr': 0.0001255549663380823, 'samples': 19305024, 'steps': 100546, 'loss/train': 1.5577247142791748} 08/31/2021 07:23:34 - INFO - __main__ - Step 100548: {'lr': 0.00012555036380946906, 'samples': 19305216, 'steps': 100547, 'loss/train': 1.0784372091293335} 08/31/2021 07:23:34 - INFO - __main__ - Step 100549: {'lr': 0.0001255457613369308, 'samples': 19305408, 'steps': 100548, 'loss/train': 0.43473753333091736} 08/31/2021 07:23:34 - INFO - __main__ - Step 100550: {'lr': 0.00012554115892046973, 'samples': 19305600, 'steps': 100549, 'loss/train': 1.5214297771453857} 08/31/2021 07:23:35 - INFO - __main__ - Step 100551: {'lr': 0.00012553655656008782, 'samples': 19305792, 'steps': 100550, 'loss/train': 1.469770908355713} 08/31/2021 07:23:35 - INFO - __main__ - Step 100552: {'lr': 0.00012553195425578728, 'samples': 19305984, 'steps': 100551, 'loss/train': 0.02269388921558857} 08/31/2021 07:23:35 - INFO - __main__ - Step 100553: {'lr': 0.00012552735200757013, 'samples': 19306176, 'steps': 100552, 'loss/train': 0.769383430480957} 08/31/2021 07:23:37 - INFO - __main__ - Step 100554: {'lr': 0.00012552274981543843, 'samples': 19306368, 'steps': 100553, 'loss/train': 1.7701539993286133} 08/31/2021 07:23:37 - INFO - __main__ - Step 100555: {'lr': 0.00012551814767939424, 'samples': 19306560, 'steps': 100554, 'loss/train': 1.4271544218063354} 08/31/2021 07:23:38 - INFO - __main__ - Step 100556: {'lr': 0.00012551354559943963, 'samples': 19306752, 'steps': 100555, 'loss/train': 0.46423977613449097} 08/31/2021 07:23:38 - INFO - __main__ - Step 100557: {'lr': 0.00012550894357557673, 'samples': 19306944, 'steps': 100556, 'loss/train': 1.3346176147460938} 08/31/2021 07:23:38 - INFO - __main__ - Step 100558: {'lr': 0.00012550434160780755, 'samples': 19307136, 'steps': 100557, 'loss/train': 1.2457993030548096} 08/31/2021 07:23:40 - INFO - __main__ - Step 100559: {'lr': 0.0001254997396961343, 'samples': 19307328, 'steps': 100558, 'loss/train': 0.5925033688545227} 08/31/2021 07:23:41 - INFO - __main__ - Step 100560: {'lr': 0.0001254951378405589, 'samples': 19307520, 'steps': 100559, 'loss/train': 1.0549814701080322} 08/31/2021 07:23:41 - INFO - __main__ - Step 100561: {'lr': 0.0001254905360410834, 'samples': 19307712, 'steps': 100560, 'loss/train': 1.0567662715911865} 08/31/2021 07:23:41 - INFO - __main__ - Step 100562: {'lr': 0.00012548593429770997, 'samples': 19307904, 'steps': 100561, 'loss/train': 0.9739788770675659} 08/31/2021 07:23:42 - INFO - __main__ - Step 100563: {'lr': 0.00012548133261044064, 'samples': 19308096, 'steps': 100562, 'loss/train': 1.1192193031311035} 08/31/2021 07:23:42 - INFO - __main__ - Step 100564: {'lr': 0.00012547673097927753, 'samples': 19308288, 'steps': 100563, 'loss/train': 1.0870436429977417} 08/31/2021 07:23:45 - INFO - __main__ - Step 100565: {'lr': 0.00012547212940422264, 'samples': 19308480, 'steps': 100564, 'loss/train': 0.6616799831390381} 08/31/2021 07:23:45 - INFO - __main__ - Step 100566: {'lr': 0.00012546752788527814, 'samples': 19308672, 'steps': 100565, 'loss/train': 0.017494939267635345} 08/31/2021 07:23:45 - INFO - __main__ - Step 100567: {'lr': 0.000125462926422446, 'samples': 19308864, 'steps': 100566, 'loss/train': 1.3327279090881348} 08/31/2021 07:23:46 - INFO - __main__ - Step 100568: {'lr': 0.0001254583250157284, 'samples': 19309056, 'steps': 100567, 'loss/train': 1.177987813949585} 08/31/2021 07:23:46 - INFO - __main__ - Step 100569: {'lr': 0.0001254537236651273, 'samples': 19309248, 'steps': 100568, 'loss/train': 1.4152957201004028} 08/31/2021 07:23:46 - INFO - __main__ - Step 100570: {'lr': 0.00012544912237064486, 'samples': 19309440, 'steps': 100569, 'loss/train': 1.047195553779602} 08/31/2021 07:23:48 - INFO - __main__ - Step 100571: {'lr': 0.00012544452113228313, 'samples': 19309632, 'steps': 100570, 'loss/train': 1.22641122341156} 08/31/2021 07:23:48 - INFO - __main__ - Step 100572: {'lr': 0.0001254399199500443, 'samples': 19309824, 'steps': 100571, 'loss/train': 1.2997373342514038} 08/31/2021 07:23:49 - INFO - __main__ - Step 100573: {'lr': 0.00012543531882393017, 'samples': 19310016, 'steps': 100572, 'loss/train': 1.0068638324737549} 08/31/2021 07:23:49 - INFO - __main__ - Step 100574: {'lr': 0.00012543071775394297, 'samples': 19310208, 'steps': 100573, 'loss/train': 1.2601211071014404} 08/31/2021 07:23:49 - INFO - __main__ - Step 100575: {'lr': 0.00012542611674008476, 'samples': 19310400, 'steps': 100574, 'loss/train': 0.9454554319381714} 08/31/2021 07:23:51 - INFO - __main__ - Step 100576: {'lr': 0.00012542151578235762, 'samples': 19310592, 'steps': 100575, 'loss/train': 1.376473069190979} 08/31/2021 07:23:51 - INFO - __main__ - Step 100577: {'lr': 0.00012541691488076367, 'samples': 19310784, 'steps': 100576, 'loss/train': 1.4831664562225342} 08/31/2021 07:23:52 - INFO - __main__ - Step 100578: {'lr': 0.0001254123140353049, 'samples': 19310976, 'steps': 100577, 'loss/train': 0.5738304257392883} 08/31/2021 07:23:52 - INFO - __main__ - Step 100579: {'lr': 0.00012540771324598345, 'samples': 19311168, 'steps': 100578, 'loss/train': 1.0328141450881958} 08/31/2021 07:23:52 - INFO - __main__ - Step 100580: {'lr': 0.0001254031125128013, 'samples': 19311360, 'steps': 100579, 'loss/train': 1.2959908246994019} 08/31/2021 07:23:54 - INFO - __main__ - Step 100581: {'lr': 0.00012539851183576063, 'samples': 19311552, 'steps': 100580, 'loss/train': 0.7848300933837891} 08/31/2021 07:23:54 - INFO - __main__ - Step 100582: {'lr': 0.00012539391121486342, 'samples': 19311744, 'steps': 100581, 'loss/train': 1.2382159233093262} 08/31/2021 07:23:55 - INFO - __main__ - Step 100583: {'lr': 0.00012538931065011186, 'samples': 19311936, 'steps': 100582, 'loss/train': 0.03419925272464752} 08/31/2021 07:23:55 - INFO - __main__ - Step 100584: {'lr': 0.00012538471014150794, 'samples': 19312128, 'steps': 100583, 'loss/train': 0.8856621384620667} 08/31/2021 07:23:55 - INFO - __main__ - Step 100585: {'lr': 0.00012538010968905382, 'samples': 19312320, 'steps': 100584, 'loss/train': 1.0943317413330078} 08/31/2021 07:23:57 - INFO - __main__ - Step 100586: {'lr': 0.0001253755092927514, 'samples': 19312512, 'steps': 100585, 'loss/train': 1.3507574796676636} 08/31/2021 07:23:57 - INFO - __main__ - Step 100587: {'lr': 0.00012537090895260283, 'samples': 19312704, 'steps': 100586, 'loss/train': 1.7081174850463867} 08/31/2021 07:23:58 - INFO - __main__ - Step 100588: {'lr': 0.00012536630866861028, 'samples': 19312896, 'steps': 100587, 'loss/train': 1.4108270406723022} 08/31/2021 07:23:58 - INFO - __main__ - Step 100589: {'lr': 0.00012536170844077568, 'samples': 19313088, 'steps': 100588, 'loss/train': 0.9527762532234192} 08/31/2021 07:23:58 - INFO - __main__ - Step 100590: {'lr': 0.0001253571082691012, 'samples': 19313280, 'steps': 100589, 'loss/train': 1.0270664691925049} 08/31/2021 07:24:00 - INFO - __main__ - Step 100591: {'lr': 0.00012535250815358888, 'samples': 19313472, 'steps': 100590, 'loss/train': 1.085062861442566} 08/31/2021 07:24:00 - INFO - __main__ - Step 100592: {'lr': 0.0001253479080942408, 'samples': 19313664, 'steps': 100591, 'loss/train': 1.6275925636291504} 08/31/2021 07:24:01 - INFO - __main__ - Step 100593: {'lr': 0.00012534330809105902, 'samples': 19313856, 'steps': 100592, 'loss/train': 0.9518206119537354} 08/31/2021 07:24:01 - INFO - __main__ - Step 100594: {'lr': 0.00012533870814404564, 'samples': 19314048, 'steps': 100593, 'loss/train': 0.7116111516952515} 08/31/2021 07:24:01 - INFO - __main__ - Step 100595: {'lr': 0.00012533410825320268, 'samples': 19314240, 'steps': 100594, 'loss/train': 1.1954803466796875} 08/31/2021 07:24:03 - INFO - __main__ - Step 100596: {'lr': 0.00012532950841853227, 'samples': 19314432, 'steps': 100595, 'loss/train': 1.4166789054870605} 08/31/2021 07:24:03 - INFO - __main__ - Step 100597: {'lr': 0.00012532490864003646, 'samples': 19314624, 'steps': 100596, 'loss/train': 1.549458622932434} 08/31/2021 07:24:04 - INFO - __main__ - Step 100598: {'lr': 0.0001253203089177173, 'samples': 19314816, 'steps': 100597, 'loss/train': 1.0453635454177856} 08/31/2021 07:24:04 - INFO - __main__ - Step 100599: {'lr': 0.000125315709251577, 'samples': 19315008, 'steps': 100598, 'loss/train': 1.060383915901184} 08/31/2021 07:24:04 - INFO - __main__ - Step 100600: {'lr': 0.00012531110964161742, 'samples': 19315200, 'steps': 100599, 'loss/train': 1.6825839281082153} 08/31/2021 07:24:05 - INFO - __main__ - Step 100601: {'lr': 0.00012530651008784075, 'samples': 19315392, 'steps': 100600, 'loss/train': 0.565371036529541} 08/31/2021 07:24:06 - INFO - __main__ - Step 100602: {'lr': 0.00012530191059024904, 'samples': 19315584, 'steps': 100601, 'loss/train': 1.115952491760254} 08/31/2021 07:24:07 - INFO - __main__ - Step 100603: {'lr': 0.00012529731114884436, 'samples': 19315776, 'steps': 100602, 'loss/train': 1.238531231880188} 08/31/2021 07:24:07 - INFO - __main__ - Step 100604: {'lr': 0.00012529271176362874, 'samples': 19315968, 'steps': 100603, 'loss/train': 1.5644689798355103} 08/31/2021 07:24:07 - INFO - __main__ - Step 100605: {'lr': 0.00012528811243460436, 'samples': 19316160, 'steps': 100604, 'loss/train': 1.2376446723937988} 08/31/2021 07:24:08 - INFO - __main__ - Step 100606: {'lr': 0.0001252835131617732, 'samples': 19316352, 'steps': 100605, 'loss/train': 1.2174780368804932} 08/31/2021 07:24:10 - INFO - __main__ - Step 100607: {'lr': 0.00012527891394513736, 'samples': 19316544, 'steps': 100606, 'loss/train': 1.1041960716247559} 08/31/2021 07:24:10 - INFO - __main__ - Step 100608: {'lr': 0.0001252743147846989, 'samples': 19316736, 'steps': 100607, 'loss/train': 1.152555227279663} 08/31/2021 07:24:11 - INFO - __main__ - Step 100609: {'lr': 0.00012526971568045997, 'samples': 19316928, 'steps': 100608, 'loss/train': 1.3006724119186401} 08/31/2021 07:24:11 - INFO - __main__ - Step 100610: {'lr': 0.00012526511663242258, 'samples': 19317120, 'steps': 100609, 'loss/train': 1.1490497589111328} 08/31/2021 07:24:11 - INFO - __main__ - Step 100611: {'lr': 0.00012526051764058876, 'samples': 19317312, 'steps': 100610, 'loss/train': 1.1704741716384888} 08/31/2021 07:24:12 - INFO - __main__ - Step 100612: {'lr': 0.00012525591870496072, 'samples': 19317504, 'steps': 100611, 'loss/train': 1.5396374464035034} 08/31/2021 07:24:13 - INFO - __main__ - Step 100613: {'lr': 0.00012525131982554037, 'samples': 19317696, 'steps': 100612, 'loss/train': 0.12324971705675125} 08/31/2021 07:24:14 - INFO - __main__ - Step 100614: {'lr': 0.0001252467210023298, 'samples': 19317888, 'steps': 100613, 'loss/train': 1.3903776407241821} 08/31/2021 07:24:14 - INFO - __main__ - Step 100615: {'lr': 0.00012524212223533122, 'samples': 19318080, 'steps': 100614, 'loss/train': 0.8457449674606323} 08/31/2021 07:24:15 - INFO - __main__ - Step 100616: {'lr': 0.00012523752352454654, 'samples': 19318272, 'steps': 100615, 'loss/train': 0.49227067828178406} 08/31/2021 07:24:15 - INFO - __main__ - Step 100617: {'lr': 0.00012523292486997794, 'samples': 19318464, 'steps': 100616, 'loss/train': 0.6247328519821167} 08/31/2021 07:24:17 - INFO - __main__ - Step 100618: {'lr': 0.00012522832627162743, 'samples': 19318656, 'steps': 100617, 'loss/train': 0.11970742046833038} 08/31/2021 07:24:17 - INFO - __main__ - Step 100619: {'lr': 0.00012522372772949715, 'samples': 19318848, 'steps': 100618, 'loss/train': 1.3933298587799072} 08/31/2021 07:24:18 - INFO - __main__ - Step 100620: {'lr': 0.00012521912924358912, 'samples': 19319040, 'steps': 100619, 'loss/train': 1.059743881225586} 08/31/2021 07:24:18 - INFO - __main__ - Step 100621: {'lr': 0.0001252145308139054, 'samples': 19319232, 'steps': 100620, 'loss/train': 0.07392776757478714} 08/31/2021 07:24:18 - INFO - __main__ - Step 100622: {'lr': 0.0001252099324404481, 'samples': 19319424, 'steps': 100621, 'loss/train': 1.7069892883300781} 08/31/2021 07:24:20 - INFO - __main__ - Step 100623: {'lr': 0.0001252053341232193, 'samples': 19319616, 'steps': 100622, 'loss/train': 1.5705482959747314} 08/31/2021 07:24:20 - INFO - __main__ - Step 100624: {'lr': 0.00012520073586222102, 'samples': 19319808, 'steps': 100623, 'loss/train': 1.0159369707107544} 08/31/2021 07:24:21 - INFO - __main__ - Step 100625: {'lr': 0.00012519613765745542, 'samples': 19320000, 'steps': 100624, 'loss/train': 1.191800594329834} 08/31/2021 07:24:21 - INFO - __main__ - Step 100626: {'lr': 0.00012519153950892454, 'samples': 19320192, 'steps': 100625, 'loss/train': 1.2210668325424194} 08/31/2021 07:24:21 - INFO - __main__ - Step 100627: {'lr': 0.00012518694141663036, 'samples': 19320384, 'steps': 100626, 'loss/train': 1.4013123512268066} 08/31/2021 07:24:23 - INFO - __main__ - Step 100628: {'lr': 0.00012518234338057503, 'samples': 19320576, 'steps': 100627, 'loss/train': 0.3274479806423187} 08/31/2021 07:24:23 - INFO - __main__ - Step 100629: {'lr': 0.0001251777454007606, 'samples': 19320768, 'steps': 100628, 'loss/train': 0.407479465007782} 08/31/2021 07:24:24 - INFO - __main__ - Step 100630: {'lr': 0.00012517314747718914, 'samples': 19320960, 'steps': 100629, 'loss/train': 1.5556674003601074} 08/31/2021 07:24:24 - INFO - __main__ - Step 100631: {'lr': 0.00012516854960986274, 'samples': 19321152, 'steps': 100630, 'loss/train': 0.9850348830223083} 08/31/2021 07:24:24 - INFO - __main__ - Step 100632: {'lr': 0.00012516395179878347, 'samples': 19321344, 'steps': 100631, 'loss/train': 1.030499815940857} 08/31/2021 07:24:26 - INFO - __main__ - Step 100633: {'lr': 0.0001251593540439534, 'samples': 19321536, 'steps': 100632, 'loss/train': 0.3568057119846344} 08/31/2021 07:24:26 - INFO - __main__ - Step 100634: {'lr': 0.0001251547563453746, 'samples': 19321728, 'steps': 100633, 'loss/train': 0.07062038779258728} 08/31/2021 07:24:27 - INFO - __main__ - Step 100635: {'lr': 0.00012515015870304914, 'samples': 19321920, 'steps': 100634, 'loss/train': 0.9183659553527832} 08/31/2021 07:24:27 - INFO - __main__ - Step 100636: {'lr': 0.00012514556111697906, 'samples': 19322112, 'steps': 100635, 'loss/train': 1.6471142768859863} 08/31/2021 07:24:28 - INFO - __main__ - Step 100637: {'lr': 0.00012514096358716648, 'samples': 19322304, 'steps': 100636, 'loss/train': 1.046697974205017} 08/31/2021 07:24:29 - INFO - __main__ - Step 100638: {'lr': 0.00012513636611361347, 'samples': 19322496, 'steps': 100637, 'loss/train': 1.3184185028076172} 08/31/2021 07:24:29 - INFO - __main__ - Step 100639: {'lr': 0.0001251317686963222, 'samples': 19322688, 'steps': 100638, 'loss/train': 0.5431467294692993} 08/31/2021 07:24:30 - INFO - __main__ - Step 100640: {'lr': 0.0001251271713352945, 'samples': 19322880, 'steps': 100639, 'loss/train': 0.9169621467590332} 08/31/2021 07:24:30 - INFO - __main__ - Step 100641: {'lr': 0.00012512257403053255, 'samples': 19323072, 'steps': 100640, 'loss/train': 0.9291008710861206} 08/31/2021 07:24:31 - INFO - __main__ - Step 100642: {'lr': 0.0001251179767820385, 'samples': 19323264, 'steps': 100641, 'loss/train': 1.1616030931472778} 08/31/2021 07:24:32 - INFO - __main__ - Step 100643: {'lr': 0.00012511337958981433, 'samples': 19323456, 'steps': 100642, 'loss/train': 1.4421842098236084} 08/31/2021 07:24:32 - INFO - __main__ - Step 100644: {'lr': 0.00012510878245386214, 'samples': 19323648, 'steps': 100643, 'loss/train': 1.0806102752685547} 08/31/2021 07:24:33 - INFO - __main__ - Step 100645: {'lr': 0.000125104185374184, 'samples': 19323840, 'steps': 100644, 'loss/train': 1.2861627340316772} 08/31/2021 07:24:33 - INFO - __main__ - Step 100646: {'lr': 0.000125099588350782, 'samples': 19324032, 'steps': 100645, 'loss/train': 1.2272660732269287} 08/31/2021 07:24:33 - INFO - __main__ - Step 100647: {'lr': 0.0001250949913836582, 'samples': 19324224, 'steps': 100646, 'loss/train': 1.5968414545059204} 08/31/2021 07:24:35 - INFO - __main__ - Step 100648: {'lr': 0.00012509039447281467, 'samples': 19324416, 'steps': 100647, 'loss/train': 0.6691514849662781} 08/31/2021 07:24:35 - INFO - __main__ - Step 100649: {'lr': 0.0001250857976182535, 'samples': 19324608, 'steps': 100648, 'loss/train': 0.9986521005630493} 08/31/2021 07:24:36 - INFO - __main__ - Step 100650: {'lr': 0.0001250812008199767, 'samples': 19324800, 'steps': 100649, 'loss/train': 1.0541576147079468} 08/31/2021 07:24:36 - INFO - __main__ - Step 100651: {'lr': 0.0001250766040779864, 'samples': 19324992, 'steps': 100650, 'loss/train': 1.4492970705032349} 08/31/2021 07:24:36 - INFO - __main__ - Step 100652: {'lr': 0.00012507200739228475, 'samples': 19325184, 'steps': 100651, 'loss/train': 1.2157236337661743} 08/31/2021 07:24:38 - INFO - __main__ - Step 100653: {'lr': 0.00012506741076287364, 'samples': 19325376, 'steps': 100652, 'loss/train': 1.1970380544662476} 08/31/2021 07:24:39 - INFO - __main__ - Step 100654: {'lr': 0.00012506281418975522, 'samples': 19325568, 'steps': 100653, 'loss/train': 1.2014929056167603} 08/31/2021 07:24:39 - INFO - __main__ - Step 100655: {'lr': 0.00012505821767293157, 'samples': 19325760, 'steps': 100654, 'loss/train': 0.015598895028233528} 08/31/2021 07:24:40 - INFO - __main__ - Step 100656: {'lr': 0.00012505362121240476, 'samples': 19325952, 'steps': 100655, 'loss/train': 1.2302333116531372} 08/31/2021 07:24:40 - INFO - __main__ - Step 100657: {'lr': 0.00012504902480817688, 'samples': 19326144, 'steps': 100656, 'loss/train': 0.7617394328117371} 08/31/2021 07:24:40 - INFO - __main__ - Step 100658: {'lr': 0.00012504442846024994, 'samples': 19326336, 'steps': 100657, 'loss/train': 1.2130846977233887} 08/31/2021 07:24:42 - INFO - __main__ - Step 100659: {'lr': 0.00012503983216862607, 'samples': 19326528, 'steps': 100658, 'loss/train': 1.148032784461975} 08/31/2021 07:24:42 - INFO - __main__ - Step 100660: {'lr': 0.00012503523593330733, 'samples': 19326720, 'steps': 100659, 'loss/train': 1.4441031217575073} 08/31/2021 07:24:43 - INFO - __main__ - Step 100661: {'lr': 0.00012503063975429578, 'samples': 19326912, 'steps': 100660, 'loss/train': 1.405781626701355} 08/31/2021 07:24:43 - INFO - __main__ - Step 100662: {'lr': 0.0001250260436315935, 'samples': 19327104, 'steps': 100661, 'loss/train': 0.35061290860176086} 08/31/2021 07:24:44 - INFO - __main__ - Step 100663: {'lr': 0.00012502144756520255, 'samples': 19327296, 'steps': 100662, 'loss/train': 0.7855449318885803} 08/31/2021 07:24:44 - INFO - __main__ - Step 100664: {'lr': 0.00012501685155512498, 'samples': 19327488, 'steps': 100663, 'loss/train': 0.023645445704460144} 08/31/2021 07:24:45 - INFO - __main__ - Step 100665: {'lr': 0.0001250122556013629, 'samples': 19327680, 'steps': 100664, 'loss/train': 1.7653210163116455} 08/31/2021 07:24:46 - INFO - __main__ - Step 100666: {'lr': 0.00012500765970391853, 'samples': 19327872, 'steps': 100665, 'loss/train': 0.912299394607544} 08/31/2021 07:24:46 - INFO - __main__ - Step 100667: {'lr': 0.0001250030638627936, 'samples': 19328064, 'steps': 100666, 'loss/train': 1.302156686782837} 08/31/2021 07:24:47 - INFO - __main__ - Step 100668: {'lr': 0.00012499846807799043, 'samples': 19328256, 'steps': 100667, 'loss/train': 1.2640900611877441} 08/31/2021 07:24:47 - INFO - __main__ - Step 100669: {'lr': 0.00012499387234951096, 'samples': 19328448, 'steps': 100668, 'loss/train': 1.619794249534607} 08/31/2021 07:24:49 - INFO - __main__ - Step 100670: {'lr': 0.00012498927667735734, 'samples': 19328640, 'steps': 100669, 'loss/train': 1.0667097568511963} 08/31/2021 07:24:49 - INFO - __main__ - Step 100671: {'lr': 0.00012498468106153166, 'samples': 19328832, 'steps': 100670, 'loss/train': 1.3428094387054443} 08/31/2021 07:24:50 - INFO - __main__ - Step 100672: {'lr': 0.0001249800855020359, 'samples': 19329024, 'steps': 100671, 'loss/train': 0.9524711966514587} 08/31/2021 07:24:50 - INFO - __main__ - Step 100673: {'lr': 0.00012497548999887222, 'samples': 19329216, 'steps': 100672, 'loss/train': 1.0046732425689697} 08/31/2021 07:24:50 - INFO - __main__ - Step 100674: {'lr': 0.00012497089455204265, 'samples': 19329408, 'steps': 100673, 'loss/train': 1.2376924753189087} 08/31/2021 07:24:53 - INFO - __main__ - Step 100675: {'lr': 0.00012496629916154925, 'samples': 19329600, 'steps': 100674, 'loss/train': 0.17763054370880127} 08/31/2021 07:24:53 - INFO - __main__ - Step 100676: {'lr': 0.00012496170382739414, 'samples': 19329792, 'steps': 100675, 'loss/train': 1.4974027872085571} 08/31/2021 07:24:53 - INFO - __main__ - Step 100677: {'lr': 0.00012495710854957932, 'samples': 19329984, 'steps': 100676, 'loss/train': 1.201414942741394} 08/31/2021 07:24:54 - INFO - __main__ - Step 100678: {'lr': 0.0001249525133281069, 'samples': 19330176, 'steps': 100677, 'loss/train': 1.3249905109405518} 08/31/2021 07:24:54 - INFO - __main__ - Step 100679: {'lr': 0.00012494791816297906, 'samples': 19330368, 'steps': 100678, 'loss/train': 1.3291196823120117} 08/31/2021 07:24:54 - INFO - __main__ - Step 100680: {'lr': 0.00012494332305419765, 'samples': 19330560, 'steps': 100679, 'loss/train': 1.4966431856155396} 08/31/2021 07:24:56 - INFO - __main__ - Step 100681: {'lr': 0.00012493872800176486, 'samples': 19330752, 'steps': 100680, 'loss/train': 0.8470578193664551} 08/31/2021 07:24:56 - INFO - __main__ - Step 100682: {'lr': 0.00012493413300568274, 'samples': 19330944, 'steps': 100681, 'loss/train': 0.8838624954223633} 08/31/2021 07:24:57 - INFO - __main__ - Step 100683: {'lr': 0.0001249295380659534, 'samples': 19331136, 'steps': 100682, 'loss/train': 1.3083444833755493} 08/31/2021 07:24:57 - INFO - __main__ - Step 100684: {'lr': 0.00012492494318257883, 'samples': 19331328, 'steps': 100683, 'loss/train': 1.3294153213500977} 08/31/2021 07:24:58 - INFO - __main__ - Step 100685: {'lr': 0.00012492034835556118, 'samples': 19331520, 'steps': 100684, 'loss/train': 1.2289726734161377} 08/31/2021 07:24:59 - INFO - __main__ - Step 100686: {'lr': 0.00012491575358490248, 'samples': 19331712, 'steps': 100685, 'loss/train': 1.411431074142456} 08/31/2021 07:24:59 - INFO - __main__ - Step 100687: {'lr': 0.00012491115887060483, 'samples': 19331904, 'steps': 100686, 'loss/train': 1.3597184419631958} 08/31/2021 07:25:00 - INFO - __main__ - Step 100688: {'lr': 0.00012490656421267028, 'samples': 19332096, 'steps': 100687, 'loss/train': 1.1689536571502686} 08/31/2021 07:25:00 - INFO - __main__ - Step 100689: {'lr': 0.00012490196961110087, 'samples': 19332288, 'steps': 100688, 'loss/train': 1.3461499214172363} 08/31/2021 07:25:00 - INFO - __main__ - Step 100690: {'lr': 0.00012489737506589873, 'samples': 19332480, 'steps': 100689, 'loss/train': 0.20621521770954132} 08/31/2021 07:25:02 - INFO - __main__ - Step 100691: {'lr': 0.0001248927805770659, 'samples': 19332672, 'steps': 100690, 'loss/train': 1.1929622888565063} 08/31/2021 07:25:03 - INFO - __main__ - Step 100692: {'lr': 0.00012488818614460445, 'samples': 19332864, 'steps': 100691, 'loss/train': 1.1068248748779297} 08/31/2021 07:25:03 - INFO - __main__ - Step 100693: {'lr': 0.00012488359176851654, 'samples': 19333056, 'steps': 100692, 'loss/train': 0.9324474334716797} 08/31/2021 07:25:03 - INFO - __main__ - Step 100694: {'lr': 0.00012487899744880406, 'samples': 19333248, 'steps': 100693, 'loss/train': 1.5994806289672852} 08/31/2021 07:25:04 - INFO - __main__ - Step 100695: {'lr': 0.0001248744031854692, 'samples': 19333440, 'steps': 100694, 'loss/train': 0.8826206922531128} 08/31/2021 07:25:05 - INFO - __main__ - Step 100696: {'lr': 0.00012486980897851398, 'samples': 19333632, 'steps': 100695, 'loss/train': 0.9988768100738525} 08/31/2021 07:25:06 - INFO - __main__ - Step 100697: {'lr': 0.00012486521482794048, 'samples': 19333824, 'steps': 100696, 'loss/train': 0.908353865146637} 08/31/2021 07:25:06 - INFO - __main__ - Step 100698: {'lr': 0.0001248606207337508, 'samples': 19334016, 'steps': 100697, 'loss/train': 1.262795329093933} 08/31/2021 07:25:07 - INFO - __main__ - Step 100699: {'lr': 0.00012485602669594698, 'samples': 19334208, 'steps': 100698, 'loss/train': 0.21028149127960205} 08/31/2021 07:25:07 - INFO - __main__ - Step 100700: {'lr': 0.0001248514327145311, 'samples': 19334400, 'steps': 100699, 'loss/train': 0.04317111149430275} 08/31/2021 07:25:09 - INFO - __main__ - Step 100701: {'lr': 0.00012484683878950526, 'samples': 19334592, 'steps': 100700, 'loss/train': 0.7493926882743835} 08/31/2021 07:25:09 - INFO - __main__ - Step 100702: {'lr': 0.0001248422449208715, 'samples': 19334784, 'steps': 100701, 'loss/train': 1.2076146602630615} 08/31/2021 07:25:09 - INFO - __main__ - Step 100703: {'lr': 0.00012483765110863187, 'samples': 19334976, 'steps': 100702, 'loss/train': 1.0959519147872925} 08/31/2021 07:25:10 - INFO - __main__ - Step 100704: {'lr': 0.00012483305735278846, 'samples': 19335168, 'steps': 100703, 'loss/train': 0.9619711637496948} 08/31/2021 07:25:10 - INFO - __main__ - Step 100705: {'lr': 0.00012482846365334337, 'samples': 19335360, 'steps': 100704, 'loss/train': 0.5795369148254395} 08/31/2021 07:25:10 - INFO - __main__ - Step 100706: {'lr': 0.00012482387001029873, 'samples': 19335552, 'steps': 100705, 'loss/train': 1.1941142082214355} 08/31/2021 07:25:12 - INFO - __main__ - Step 100707: {'lr': 0.00012481927642365642, 'samples': 19335744, 'steps': 100706, 'loss/train': 1.1885788440704346} 08/31/2021 07:25:12 - INFO - __main__ - Step 100708: {'lr': 0.00012481468289341863, 'samples': 19335936, 'steps': 100707, 'loss/train': 1.3457551002502441} 08/31/2021 07:25:13 - INFO - __main__ - Step 100709: {'lr': 0.00012481008941958737, 'samples': 19336128, 'steps': 100708, 'loss/train': 1.5248832702636719} 08/31/2021 07:25:13 - INFO - __main__ - Step 100710: {'lr': 0.0001248054960021648, 'samples': 19336320, 'steps': 100709, 'loss/train': 1.400115728378296} 08/31/2021 07:25:13 - INFO - __main__ - Step 100711: {'lr': 0.00012480090264115293, 'samples': 19336512, 'steps': 100710, 'loss/train': 0.7549226880073547} 08/31/2021 07:25:15 - INFO - __main__ - Step 100712: {'lr': 0.0001247963093365538, 'samples': 19336704, 'steps': 100711, 'loss/train': 0.49771326780319214} 08/31/2021 07:25:15 - INFO - __main__ - Step 100713: {'lr': 0.00012479171608836958, 'samples': 19336896, 'steps': 100712, 'loss/train': 0.45183345675468445} 08/31/2021 07:25:16 - INFO - __main__ - Step 100714: {'lr': 0.00012478712289660225, 'samples': 19337088, 'steps': 100713, 'loss/train': 0.8755108714103699} 08/31/2021 07:25:16 - INFO - __main__ - Step 100715: {'lr': 0.00012478252976125392, 'samples': 19337280, 'steps': 100714, 'loss/train': 0.9827967882156372} 08/31/2021 07:25:16 - INFO - __main__ - Step 100716: {'lr': 0.00012477793668232666, 'samples': 19337472, 'steps': 100715, 'loss/train': 1.198737382888794} 08/31/2021 07:25:18 - INFO - __main__ - Step 100717: {'lr': 0.00012477334365982248, 'samples': 19337664, 'steps': 100716, 'loss/train': 0.8507248163223267} 08/31/2021 07:25:18 - INFO - __main__ - Step 100718: {'lr': 0.00012476875069374356, 'samples': 19337856, 'steps': 100717, 'loss/train': 0.23118779063224792} 08/31/2021 07:25:19 - INFO - __main__ - Step 100719: {'lr': 0.00012476415778409186, 'samples': 19338048, 'steps': 100718, 'loss/train': 1.2769187688827515} 08/31/2021 07:25:19 - INFO - __main__ - Step 100720: {'lr': 0.0001247595649308696, 'samples': 19338240, 'steps': 100719, 'loss/train': 1.0000818967819214} 08/31/2021 07:25:19 - INFO - __main__ - Step 100721: {'lr': 0.0001247549721340787, 'samples': 19338432, 'steps': 100720, 'loss/train': 2.2588376998901367} 08/31/2021 07:25:21 - INFO - __main__ - Step 100722: {'lr': 0.00012475037939372124, 'samples': 19338624, 'steps': 100721, 'loss/train': 1.1345120668411255} 08/31/2021 07:25:21 - INFO - __main__ - Step 100723: {'lr': 0.00012474578670979933, 'samples': 19338816, 'steps': 100722, 'loss/train': 0.9935561418533325} 08/31/2021 07:25:22 - INFO - __main__ - Step 100724: {'lr': 0.00012474119408231504, 'samples': 19339008, 'steps': 100723, 'loss/train': 1.2452529668807983} 08/31/2021 07:25:22 - INFO - __main__ - Step 100725: {'lr': 0.00012473660151127042, 'samples': 19339200, 'steps': 100724, 'loss/train': 1.0939842462539673} 08/31/2021 07:25:22 - INFO - __main__ - Step 100726: {'lr': 0.00012473200899666757, 'samples': 19339392, 'steps': 100725, 'loss/train': 0.44679197669029236} 08/31/2021 07:25:24 - INFO - __main__ - Step 100727: {'lr': 0.00012472741653850856, 'samples': 19339584, 'steps': 100726, 'loss/train': 1.1512770652770996} 08/31/2021 07:25:25 - INFO - __main__ - Step 100728: {'lr': 0.0001247228241367954, 'samples': 19339776, 'steps': 100727, 'loss/train': 0.9851679801940918} 08/31/2021 07:25:25 - INFO - __main__ - Step 100729: {'lr': 0.0001247182317915302, 'samples': 19339968, 'steps': 100728, 'loss/train': 1.3210049867630005} 08/31/2021 07:25:26 - INFO - __main__ - Step 100730: {'lr': 0.0001247136395027151, 'samples': 19340160, 'steps': 100729, 'loss/train': 1.5579458475112915} 08/31/2021 07:25:26 - INFO - __main__ - Step 100731: {'lr': 0.00012470904727035205, 'samples': 19340352, 'steps': 100730, 'loss/train': 1.2041001319885254} 08/31/2021 07:25:28 - INFO - __main__ - Step 100732: {'lr': 0.00012470445509444317, 'samples': 19340544, 'steps': 100731, 'loss/train': 1.3221124410629272} 08/31/2021 07:25:28 - INFO - __main__ - Step 100733: {'lr': 0.00012469986297499063, 'samples': 19340736, 'steps': 100732, 'loss/train': 0.02572927623987198} 08/31/2021 07:25:29 - INFO - __main__ - Step 100734: {'lr': 0.0001246952709119963, 'samples': 19340928, 'steps': 100733, 'loss/train': 0.015501495450735092} 08/31/2021 07:25:29 - INFO - __main__ - Step 100735: {'lr': 0.00012469067890546234, 'samples': 19341120, 'steps': 100734, 'loss/train': 1.739631175994873} 08/31/2021 07:25:30 - INFO - __main__ - Step 100736: {'lr': 0.00012468608695539085, 'samples': 19341312, 'steps': 100735, 'loss/train': 0.795937180519104} 08/31/2021 07:25:30 - INFO - __main__ - Step 100737: {'lr': 0.00012468149506178385, 'samples': 19341504, 'steps': 100736, 'loss/train': 1.1633342504501343} 08/31/2021 07:25:31 - INFO - __main__ - Step 100738: {'lr': 0.00012467690322464349, 'samples': 19341696, 'steps': 100737, 'loss/train': 1.3172446489334106} 08/31/2021 07:25:32 - INFO - __main__ - Step 100739: {'lr': 0.00012467231144397173, 'samples': 19341888, 'steps': 100738, 'loss/train': 0.9381430745124817} 08/31/2021 07:25:32 - INFO - __main__ - Step 100740: {'lr': 0.0001246677197197707, 'samples': 19342080, 'steps': 100739, 'loss/train': 1.0489944219589233} 08/31/2021 07:25:33 - INFO - __main__ - Step 100741: {'lr': 0.00012466312805204248, 'samples': 19342272, 'steps': 100740, 'loss/train': 1.1999911069869995} 08/31/2021 07:25:33 - INFO - __main__ - Step 100742: {'lr': 0.0001246585364407891, 'samples': 19342464, 'steps': 100741, 'loss/train': 1.107398271560669} 08/31/2021 07:25:34 - INFO - __main__ - Step 100743: {'lr': 0.00012465394488601265, 'samples': 19342656, 'steps': 100742, 'loss/train': 1.1541444063186646} 08/31/2021 07:25:35 - INFO - __main__ - Step 100744: {'lr': 0.00012464935338771517, 'samples': 19342848, 'steps': 100743, 'loss/train': 1.1635518074035645} 08/31/2021 07:25:35 - INFO - __main__ - Step 100745: {'lr': 0.00012464476194589883, 'samples': 19343040, 'steps': 100744, 'loss/train': 1.1577147245407104} 08/31/2021 07:25:36 - INFO - __main__ - Step 100746: {'lr': 0.00012464017056056556, 'samples': 19343232, 'steps': 100745, 'loss/train': 1.0084080696105957} 08/31/2021 07:25:36 - INFO - __main__ - Step 100747: {'lr': 0.00012463557923171763, 'samples': 19343424, 'steps': 100746, 'loss/train': 1.518538475036621} 08/31/2021 07:25:36 - INFO - __main__ - Step 100748: {'lr': 0.00012463098795935688, 'samples': 19343616, 'steps': 100747, 'loss/train': 0.19987569749355316} 08/31/2021 07:25:38 - INFO - __main__ - Step 100749: {'lr': 0.00012462639674348545, 'samples': 19343808, 'steps': 100748, 'loss/train': 1.2147432565689087} 08/31/2021 07:25:38 - INFO - __main__ - Step 100750: {'lr': 0.00012462180558410544, 'samples': 19344000, 'steps': 100749, 'loss/train': 0.9861595630645752} 08/31/2021 07:25:39 - INFO - __main__ - Step 100751: {'lr': 0.0001246172144812189, 'samples': 19344192, 'steps': 100750, 'loss/train': 0.405523419380188} 08/31/2021 07:25:39 - INFO - __main__ - Step 100752: {'lr': 0.0001246126234348279, 'samples': 19344384, 'steps': 100751, 'loss/train': 0.4764644503593445} 08/31/2021 07:25:39 - INFO - __main__ - Step 100753: {'lr': 0.00012460803244493455, 'samples': 19344576, 'steps': 100752, 'loss/train': 0.6272745728492737} 08/31/2021 07:25:41 - INFO - __main__ - Step 100754: {'lr': 0.00012460344151154088, 'samples': 19344768, 'steps': 100753, 'loss/train': 1.1711905002593994} 08/31/2021 07:25:42 - INFO - __main__ - Step 100755: {'lr': 0.00012459885063464894, 'samples': 19344960, 'steps': 100754, 'loss/train': 0.03624805063009262} 08/31/2021 07:25:42 - INFO - __main__ - Step 100756: {'lr': 0.00012459425981426085, 'samples': 19345152, 'steps': 100755, 'loss/train': 1.0997103452682495} 08/31/2021 07:25:42 - INFO - __main__ - Step 100757: {'lr': 0.00012458966905037864, 'samples': 19345344, 'steps': 100756, 'loss/train': 2.365952491760254} 08/31/2021 07:25:43 - INFO - __main__ - Step 100758: {'lr': 0.00012458507834300437, 'samples': 19345536, 'steps': 100757, 'loss/train': 0.9455625414848328} 08/31/2021 07:25:44 - INFO - __main__ - Step 100759: {'lr': 0.00012458048769214015, 'samples': 19345728, 'steps': 100758, 'loss/train': 1.8199928998947144} 08/31/2021 07:25:45 - INFO - __main__ - Step 100760: {'lr': 0.00012457589709778812, 'samples': 19345920, 'steps': 100759, 'loss/train': 2.5121278762817383} 08/31/2021 07:25:45 - INFO - __main__ - Step 100761: {'lr': 0.00012457130655995017, 'samples': 19346112, 'steps': 100760, 'loss/train': 1.3642964363098145} 08/31/2021 07:25:45 - INFO - __main__ - Step 100762: {'lr': 0.00012456671607862844, 'samples': 19346304, 'steps': 100761, 'loss/train': 1.0358842611312866} 08/31/2021 07:25:46 - INFO - __main__ - Step 100763: {'lr': 0.00012456212565382498, 'samples': 19346496, 'steps': 100762, 'loss/train': 1.146067500114441} 08/31/2021 07:25:46 - INFO - __main__ - Step 100764: {'lr': 0.00012455753528554196, 'samples': 19346688, 'steps': 100763, 'loss/train': 1.6569607257843018} 08/31/2021 07:25:48 - INFO - __main__ - Step 100765: {'lr': 0.00012455294497378132, 'samples': 19346880, 'steps': 100764, 'loss/train': 1.0349419116973877} 08/31/2021 07:25:48 - INFO - __main__ - Step 100766: {'lr': 0.00012454835471854521, 'samples': 19347072, 'steps': 100765, 'loss/train': 1.911851167678833} 08/31/2021 07:25:48 - INFO - __main__ - Step 100767: {'lr': 0.00012454376451983567, 'samples': 19347264, 'steps': 100766, 'loss/train': 1.382925271987915} 08/31/2021 07:25:49 - INFO - __main__ - Step 100768: {'lr': 0.0001245391743776548, 'samples': 19347456, 'steps': 100767, 'loss/train': 1.124830961227417} 08/31/2021 07:25:49 - INFO - __main__ - Step 100769: {'lr': 0.00012453458429200463, 'samples': 19347648, 'steps': 100768, 'loss/train': 1.3674296140670776} 08/31/2021 07:25:51 - INFO - __main__ - Step 100770: {'lr': 0.00012452999426288723, 'samples': 19347840, 'steps': 100769, 'loss/train': 1.4872897863388062} 08/31/2021 07:25:51 - INFO - __main__ - Step 100771: {'lr': 0.0001245254042903047, 'samples': 19348032, 'steps': 100770, 'loss/train': 0.03519666567444801} 08/31/2021 07:25:51 - INFO - __main__ - Step 100772: {'lr': 0.00012452081437425906, 'samples': 19348224, 'steps': 100771, 'loss/train': 1.215185284614563} 08/31/2021 07:25:52 - INFO - __main__ - Step 100773: {'lr': 0.0001245162245147525, 'samples': 19348416, 'steps': 100772, 'loss/train': 1.4903883934020996} 08/31/2021 07:25:52 - INFO - __main__ - Step 100774: {'lr': 0.0001245116347117869, 'samples': 19348608, 'steps': 100773, 'loss/train': 1.143738031387329} 08/31/2021 07:25:54 - INFO - __main__ - Step 100775: {'lr': 0.0001245070449653644, 'samples': 19348800, 'steps': 100774, 'loss/train': 1.0289627313613892} 08/31/2021 07:25:54 - INFO - __main__ - Step 100776: {'lr': 0.00012450245527548715, 'samples': 19348992, 'steps': 100775, 'loss/train': 1.3089314699172974} 08/31/2021 07:25:55 - INFO - __main__ - Step 100777: {'lr': 0.00012449786564215713, 'samples': 19349184, 'steps': 100776, 'loss/train': 1.1439474821090698} 08/31/2021 07:25:55 - INFO - __main__ - Step 100778: {'lr': 0.0001244932760653764, 'samples': 19349376, 'steps': 100777, 'loss/train': 1.1462358236312866} 08/31/2021 07:25:55 - INFO - __main__ - Step 100779: {'lr': 0.0001244886865451471, 'samples': 19349568, 'steps': 100778, 'loss/train': 0.9992877840995789} 08/31/2021 07:25:57 - INFO - __main__ - Step 100780: {'lr': 0.00012448409708147126, 'samples': 19349760, 'steps': 100779, 'loss/train': 1.4187545776367188} 08/31/2021 07:25:57 - INFO - __main__ - Step 100781: {'lr': 0.00012447950767435092, 'samples': 19349952, 'steps': 100780, 'loss/train': 0.49077942967414856} 08/31/2021 07:25:58 - INFO - __main__ - Step 100782: {'lr': 0.0001244749183237882, 'samples': 19350144, 'steps': 100781, 'loss/train': 1.2302645444869995} 08/31/2021 07:25:58 - INFO - __main__ - Step 100783: {'lr': 0.00012447032902978517, 'samples': 19350336, 'steps': 100782, 'loss/train': 1.244992971420288} 08/31/2021 07:25:58 - INFO - __main__ - Step 100784: {'lr': 0.00012446573979234393, 'samples': 19350528, 'steps': 100783, 'loss/train': 0.8038694858551025} 08/31/2021 07:26:00 - INFO - __main__ - Step 100785: {'lr': 0.0001244611506114664, 'samples': 19350720, 'steps': 100784, 'loss/train': 1.2022398710250854} 08/31/2021 07:26:01 - INFO - __main__ - Step 100786: {'lr': 0.00012445656148715476, 'samples': 19350912, 'steps': 100785, 'loss/train': 0.7957320213317871} 08/31/2021 07:26:01 - INFO - __main__ - Step 100787: {'lr': 0.00012445197241941103, 'samples': 19351104, 'steps': 100786, 'loss/train': 0.7929695248603821} 08/31/2021 07:26:01 - INFO - __main__ - Step 100788: {'lr': 0.0001244473834082373, 'samples': 19351296, 'steps': 100787, 'loss/train': 0.8021140694618225} 08/31/2021 07:26:02 - INFO - __main__ - Step 100789: {'lr': 0.00012444279445363566, 'samples': 19351488, 'steps': 100788, 'loss/train': 1.0035039186477661} 08/31/2021 07:26:03 - INFO - __main__ - Step 100790: {'lr': 0.00012443820555560817, 'samples': 19351680, 'steps': 100789, 'loss/train': 1.9231503009796143} 08/31/2021 07:26:04 - INFO - __main__ - Step 100791: {'lr': 0.00012443361671415687, 'samples': 19351872, 'steps': 100790, 'loss/train': 1.0500719547271729} 08/31/2021 07:26:04 - INFO - __main__ - Step 100792: {'lr': 0.00012442902792928384, 'samples': 19352064, 'steps': 100791, 'loss/train': 2.702029228210449} 08/31/2021 07:26:04 - INFO - __main__ - Step 100793: {'lr': 0.00012442443920099118, 'samples': 19352256, 'steps': 100792, 'loss/train': 1.2235578298568726} 08/31/2021 07:26:05 - INFO - __main__ - Step 100794: {'lr': 0.0001244198505292809, 'samples': 19352448, 'steps': 100793, 'loss/train': 1.303404450416565} 08/31/2021 07:26:05 - INFO - __main__ - Step 100795: {'lr': 0.0001244152619141552, 'samples': 19352640, 'steps': 100794, 'loss/train': 1.252638578414917} 08/31/2021 07:26:07 - INFO - __main__ - Step 100796: {'lr': 0.00012441067335561596, 'samples': 19352832, 'steps': 100795, 'loss/train': 1.2895500659942627} 08/31/2021 07:26:07 - INFO - __main__ - Step 100797: {'lr': 0.0001244060848536653, 'samples': 19353024, 'steps': 100796, 'loss/train': 1.0479463338851929} 08/31/2021 07:26:08 - INFO - __main__ - Step 100798: {'lr': 0.00012440149640830536, 'samples': 19353216, 'steps': 100797, 'loss/train': 1.3127553462982178} 08/31/2021 07:26:08 - INFO - __main__ - Step 100799: {'lr': 0.00012439690801953815, 'samples': 19353408, 'steps': 100798, 'loss/train': 0.660880446434021} 08/31/2021 07:26:08 - INFO - __main__ - Step 100800: {'lr': 0.00012439231968736574, 'samples': 19353600, 'steps': 100799, 'loss/train': 1.0675227642059326} 08/31/2021 07:26:10 - INFO - __main__ - Step 100801: {'lr': 0.00012438773141179024, 'samples': 19353792, 'steps': 100800, 'loss/train': 0.7810311317443848} 08/31/2021 07:26:11 - INFO - __main__ - Step 100802: {'lr': 0.0001243831431928137, 'samples': 19353984, 'steps': 100801, 'loss/train': 1.3126306533813477} 08/31/2021 07:26:11 - INFO - __main__ - Step 100803: {'lr': 0.00012437855503043813, 'samples': 19354176, 'steps': 100802, 'loss/train': 0.38915494084358215} 08/31/2021 07:26:11 - INFO - __main__ - Step 100804: {'lr': 0.00012437396692466568, 'samples': 19354368, 'steps': 100803, 'loss/train': 0.622521698474884} 08/31/2021 07:26:12 - INFO - __main__ - Step 100805: {'lr': 0.00012436937887549837, 'samples': 19354560, 'steps': 100804, 'loss/train': 0.6441142559051514} 08/31/2021 07:26:13 - INFO - __main__ - Step 100806: {'lr': 0.0001243647908829384, 'samples': 19354752, 'steps': 100805, 'loss/train': 1.0685697793960571} 08/31/2021 07:26:13 - INFO - __main__ - Step 100807: {'lr': 0.00012436020294698757, 'samples': 19354944, 'steps': 100806, 'loss/train': 1.4610215425491333} 08/31/2021 07:26:14 - INFO - __main__ - Step 100808: {'lr': 0.00012435561506764814, 'samples': 19355136, 'steps': 100807, 'loss/train': 1.8037383556365967} 08/31/2021 07:26:14 - INFO - __main__ - Step 100809: {'lr': 0.00012435102724492211, 'samples': 19355328, 'steps': 100808, 'loss/train': 1.9762094020843506} 08/31/2021 07:26:15 - INFO - __main__ - Step 100810: {'lr': 0.00012434643947881158, 'samples': 19355520, 'steps': 100809, 'loss/train': 0.4004576504230499} 08/31/2021 07:26:16 - INFO - __main__ - Step 100811: {'lr': 0.00012434185176931858, 'samples': 19355712, 'steps': 100810, 'loss/train': 1.0527206659317017} 08/31/2021 07:26:17 - INFO - __main__ - Step 100812: {'lr': 0.0001243372641164452, 'samples': 19355904, 'steps': 100811, 'loss/train': 1.4291194677352905} 08/31/2021 07:26:17 - INFO - __main__ - Step 100813: {'lr': 0.00012433267652019357, 'samples': 19356096, 'steps': 100812, 'loss/train': 0.3750877380371094} 08/31/2021 07:26:17 - INFO - __main__ - Step 100814: {'lr': 0.00012432808898056567, 'samples': 19356288, 'steps': 100813, 'loss/train': 0.27405619621276855} 08/31/2021 07:26:18 - INFO - __main__ - Step 100815: {'lr': 0.00012432350149756355, 'samples': 19356480, 'steps': 100814, 'loss/train': 1.1065804958343506} 08/31/2021 07:26:18 - INFO - __main__ - Step 100816: {'lr': 0.00012431891407118937, 'samples': 19356672, 'steps': 100815, 'loss/train': 1.2537806034088135} 08/31/2021 07:26:20 - INFO - __main__ - Step 100817: {'lr': 0.0001243143267014452, 'samples': 19356864, 'steps': 100816, 'loss/train': 0.9668084979057312} 08/31/2021 07:26:20 - INFO - __main__ - Step 100818: {'lr': 0.00012430973938833302, 'samples': 19357056, 'steps': 100817, 'loss/train': 0.8250771760940552} 08/31/2021 07:26:20 - INFO - __main__ - Step 100819: {'lr': 0.0001243051521318549, 'samples': 19357248, 'steps': 100818, 'loss/train': 1.271384835243225} 08/31/2021 07:26:21 - INFO - __main__ - Step 100820: {'lr': 0.0001243005649320129, 'samples': 19357440, 'steps': 100819, 'loss/train': 1.5400714874267578} 08/31/2021 07:26:21 - INFO - __main__ - Step 100821: {'lr': 0.0001242959777888092, 'samples': 19357632, 'steps': 100820, 'loss/train': 1.4740991592407227} 08/31/2021 07:26:22 - INFO - __main__ - Step 100822: {'lr': 0.00012429139070224574, 'samples': 19357824, 'steps': 100821, 'loss/train': 1.0009665489196777} 08/31/2021 07:26:23 - INFO - __main__ - Step 100823: {'lr': 0.00012428680367232464, 'samples': 19358016, 'steps': 100822, 'loss/train': 1.9644290208816528} 08/31/2021 07:26:23 - INFO - __main__ - Step 100824: {'lr': 0.000124282216699048, 'samples': 19358208, 'steps': 100823, 'loss/train': 1.5970282554626465} 08/31/2021 07:26:24 - INFO - __main__ - Step 100825: {'lr': 0.00012427762978241781, 'samples': 19358400, 'steps': 100824, 'loss/train': 0.8454954028129578} 08/31/2021 07:26:24 - INFO - __main__ - Step 100826: {'lr': 0.00012427304292243622, 'samples': 19358592, 'steps': 100825, 'loss/train': 1.112184762954712} 08/31/2021 07:26:26 - INFO - __main__ - Step 100827: {'lr': 0.00012426845611910524, 'samples': 19358784, 'steps': 100826, 'loss/train': 0.49603375792503357} 08/31/2021 07:26:26 - INFO - __main__ - Step 100828: {'lr': 0.00012426386937242705, 'samples': 19358976, 'steps': 100827, 'loss/train': 1.6147983074188232} 08/31/2021 07:26:26 - INFO - __main__ - Step 100829: {'lr': 0.00012425928268240352, 'samples': 19359168, 'steps': 100828, 'loss/train': 0.8282032608985901} 08/31/2021 07:26:27 - INFO - __main__ - Step 100830: {'lr': 0.00012425469604903681, 'samples': 19359360, 'steps': 100829, 'loss/train': 1.1599459648132324} 08/31/2021 07:26:27 - INFO - __main__ - Step 100831: {'lr': 0.000124250109472329, 'samples': 19359552, 'steps': 100830, 'loss/train': 1.42081618309021} 08/31/2021 07:26:29 - INFO - __main__ - Step 100832: {'lr': 0.00012424552295228216, 'samples': 19359744, 'steps': 100831, 'loss/train': 1.0929621458053589} 08/31/2021 07:26:29 - INFO - __main__ - Step 100833: {'lr': 0.00012424093648889833, 'samples': 19359936, 'steps': 100832, 'loss/train': 1.2578884363174438} 08/31/2021 07:26:30 - INFO - __main__ - Step 100834: {'lr': 0.00012423635008217962, 'samples': 19360128, 'steps': 100833, 'loss/train': 0.01634957082569599} 08/31/2021 07:26:30 - INFO - __main__ - Step 100835: {'lr': 0.00012423176373212806, 'samples': 19360320, 'steps': 100834, 'loss/train': 0.8410822153091431} 08/31/2021 07:26:31 - INFO - __main__ - Step 100836: {'lr': 0.0001242271774387457, 'samples': 19360512, 'steps': 100835, 'loss/train': 0.9587385058403015} 08/31/2021 07:26:31 - INFO - __main__ - Step 100837: {'lr': 0.00012422259120203465, 'samples': 19360704, 'steps': 100836, 'loss/train': 0.5182278156280518} 08/31/2021 07:26:33 - INFO - __main__ - Step 100838: {'lr': 0.00012421800502199697, 'samples': 19360896, 'steps': 100837, 'loss/train': 1.3560786247253418} 08/31/2021 07:26:34 - INFO - __main__ - Step 100839: {'lr': 0.00012421341889863472, 'samples': 19361088, 'steps': 100838, 'loss/train': 0.7158544659614563} 08/31/2021 07:26:34 - INFO - __main__ - Step 100840: {'lr': 0.00012420883283194994, 'samples': 19361280, 'steps': 100839, 'loss/train': 0.810695469379425} 08/31/2021 07:26:34 - INFO - __main__ - Step 100841: {'lr': 0.00012420424682194485, 'samples': 19361472, 'steps': 100840, 'loss/train': 0.45926231145858765} 08/31/2021 07:26:35 - INFO - __main__ - Step 100842: {'lr': 0.00012419966086862124, 'samples': 19361664, 'steps': 100841, 'loss/train': 1.2310094833374023} 08/31/2021 07:26:36 - INFO - __main__ - Step 100843: {'lr': 0.00012419507497198138, 'samples': 19361856, 'steps': 100842, 'loss/train': 1.3853250741958618} 08/31/2021 07:26:37 - INFO - __main__ - Step 100844: {'lr': 0.00012419048913202724, 'samples': 19362048, 'steps': 100843, 'loss/train': 1.4809973239898682} 08/31/2021 07:26:37 - INFO - __main__ - Step 100845: {'lr': 0.00012418590334876094, 'samples': 19362240, 'steps': 100844, 'loss/train': 1.1637825965881348} 08/31/2021 07:26:37 - INFO - __main__ - Step 100846: {'lr': 0.0001241813176221845, 'samples': 19362432, 'steps': 100845, 'loss/train': 1.452117919921875} 08/31/2021 07:26:38 - INFO - __main__ - Step 100847: {'lr': 0.00012417673195230002, 'samples': 19362624, 'steps': 100846, 'loss/train': 1.1493210792541504} 08/31/2021 07:26:39 - INFO - __main__ - Step 100848: {'lr': 0.00012417214633910962, 'samples': 19362816, 'steps': 100847, 'loss/train': 1.115431308746338} 08/31/2021 07:26:39 - INFO - __main__ - Step 100849: {'lr': 0.00012416756078261526, 'samples': 19363008, 'steps': 100848, 'loss/train': 1.3806040287017822} 08/31/2021 07:26:40 - INFO - __main__ - Step 100850: {'lr': 0.00012416297528281906, 'samples': 19363200, 'steps': 100849, 'loss/train': 0.8873185515403748} 08/31/2021 07:26:40 - INFO - __main__ - Step 100851: {'lr': 0.00012415838983972308, 'samples': 19363392, 'steps': 100850, 'loss/train': 1.1574382781982422} 08/31/2021 07:26:41 - INFO - __main__ - Step 100852: {'lr': 0.00012415380445332942, 'samples': 19363584, 'steps': 100851, 'loss/train': 1.0520479679107666} 08/31/2021 07:26:41 - INFO - __main__ - Step 100853: {'lr': 0.00012414921912364007, 'samples': 19363776, 'steps': 100852, 'loss/train': 1.4411875009536743} 08/31/2021 07:26:42 - INFO - __main__ - Step 100854: {'lr': 0.00012414463385065723, 'samples': 19363968, 'steps': 100853, 'loss/train': 0.889809787273407} 08/31/2021 07:26:43 - INFO - __main__ - Step 100855: {'lr': 0.00012414004863438283, 'samples': 19364160, 'steps': 100854, 'loss/train': 1.9560775756835938} 08/31/2021 07:26:43 - INFO - __main__ - Step 100856: {'lr': 0.00012413546347481895, 'samples': 19364352, 'steps': 100855, 'loss/train': 2.8346307277679443} 08/31/2021 07:26:44 - INFO - __main__ - Step 100857: {'lr': 0.00012413087837196768, 'samples': 19364544, 'steps': 100856, 'loss/train': 0.778918445110321} 08/31/2021 07:26:44 - INFO - __main__ - Step 100858: {'lr': 0.0001241262933258311, 'samples': 19364736, 'steps': 100857, 'loss/train': 0.39573806524276733} 08/31/2021 07:26:46 - INFO - __main__ - Step 100859: {'lr': 0.0001241217083364113, 'samples': 19364928, 'steps': 100858, 'loss/train': 0.5418578386306763} 08/31/2021 07:26:46 - INFO - __main__ - Step 100860: {'lr': 0.0001241171234037103, 'samples': 19365120, 'steps': 100859, 'loss/train': 1.1850016117095947} 08/31/2021 07:26:47 - INFO - __main__ - Step 100861: {'lr': 0.00012411253852773017, 'samples': 19365312, 'steps': 100860, 'loss/train': 1.0989638566970825} 08/31/2021 07:26:47 - INFO - __main__ - Step 100862: {'lr': 0.000124107953708473, 'samples': 19365504, 'steps': 100861, 'loss/train': 2.0231637954711914} 08/31/2021 07:26:47 - INFO - __main__ - Step 100863: {'lr': 0.00012410336894594083, 'samples': 19365696, 'steps': 100862, 'loss/train': 1.2197489738464355} 08/31/2021 07:26:49 - INFO - __main__ - Step 100864: {'lr': 0.00012409878424013573, 'samples': 19365888, 'steps': 100863, 'loss/train': 0.963477373123169} 08/31/2021 07:26:49 - INFO - __main__ - Step 100865: {'lr': 0.0001240941995910598, 'samples': 19366080, 'steps': 100864, 'loss/train': 0.33550354838371277} 08/31/2021 07:26:50 - INFO - __main__ - Step 100866: {'lr': 0.00012408961499871506, 'samples': 19366272, 'steps': 100865, 'loss/train': 1.1121615171432495} 08/31/2021 07:26:50 - INFO - __main__ - Step 100867: {'lr': 0.00012408503046310363, 'samples': 19366464, 'steps': 100866, 'loss/train': 0.9370144009590149} 08/31/2021 07:26:50 - INFO - __main__ - Step 100868: {'lr': 0.0001240804459842276, 'samples': 19366656, 'steps': 100867, 'loss/train': 1.2054909467697144} 08/31/2021 07:26:52 - INFO - __main__ - Step 100869: {'lr': 0.00012407586156208892, 'samples': 19366848, 'steps': 100868, 'loss/train': 0.6464783549308777} 08/31/2021 07:26:52 - INFO - __main__ - Step 100870: {'lr': 0.00012407127719668969, 'samples': 19367040, 'steps': 100869, 'loss/train': 1.200994849205017} 08/31/2021 07:26:53 - INFO - __main__ - Step 100871: {'lr': 0.00012406669288803199, 'samples': 19367232, 'steps': 100870, 'loss/train': 1.38463294506073} 08/31/2021 07:26:53 - INFO - __main__ - Step 100872: {'lr': 0.0001240621086361179, 'samples': 19367424, 'steps': 100871, 'loss/train': 1.3724638223648071} 08/31/2021 07:26:53 - INFO - __main__ - Step 100873: {'lr': 0.0001240575244409495, 'samples': 19367616, 'steps': 100872, 'loss/train': 1.2310458421707153} 08/31/2021 07:26:55 - INFO - __main__ - Step 100874: {'lr': 0.0001240529403025288, 'samples': 19367808, 'steps': 100873, 'loss/train': 0.6162384748458862} 08/31/2021 07:26:55 - INFO - __main__ - Step 100875: {'lr': 0.00012404835622085793, 'samples': 19368000, 'steps': 100874, 'loss/train': 0.7230374813079834} 08/31/2021 07:26:56 - INFO - __main__ - Step 100876: {'lr': 0.00012404377219593892, 'samples': 19368192, 'steps': 100875, 'loss/train': 0.5788853764533997} 08/31/2021 07:26:56 - INFO - __main__ - Step 100877: {'lr': 0.00012403918822777386, 'samples': 19368384, 'steps': 100876, 'loss/train': 1.096013069152832} 08/31/2021 07:26:56 - INFO - __main__ - Step 100878: {'lr': 0.00012403460431636477, 'samples': 19368576, 'steps': 100877, 'loss/train': 0.992752730846405} 08/31/2021 07:26:57 - INFO - __main__ - Step 100879: {'lr': 0.00012403002046171377, 'samples': 19368768, 'steps': 100878, 'loss/train': 0.6318140029907227} 08/31/2021 07:26:58 - INFO - __main__ - Step 100880: {'lr': 0.00012402543666382288, 'samples': 19368960, 'steps': 100879, 'loss/train': 0.9550764560699463} 08/31/2021 07:26:59 - INFO - __main__ - Step 100881: {'lr': 0.00012402085292269427, 'samples': 19369152, 'steps': 100880, 'loss/train': 0.6567683815956116} 08/31/2021 07:26:59 - INFO - __main__ - Step 100882: {'lr': 0.00012401626923832983, 'samples': 19369344, 'steps': 100881, 'loss/train': 0.5988680720329285} 08/31/2021 07:27:00 - INFO - __main__ - Step 100883: {'lr': 0.00012401168561073175, 'samples': 19369536, 'steps': 100882, 'loss/train': 1.2922388315200806} 08/31/2021 07:27:00 - INFO - __main__ - Step 100884: {'lr': 0.00012400710203990203, 'samples': 19369728, 'steps': 100883, 'loss/train': 5.356098651885986} 08/31/2021 07:27:01 - INFO - __main__ - Step 100885: {'lr': 0.00012400251852584277, 'samples': 19369920, 'steps': 100884, 'loss/train': 1.2486354112625122} 08/31/2021 07:27:02 - INFO - __main__ - Step 100886: {'lr': 0.00012399793506855602, 'samples': 19370112, 'steps': 100885, 'loss/train': 0.7648338079452515} 08/31/2021 07:27:02 - INFO - __main__ - Step 100887: {'lr': 0.00012399335166804386, 'samples': 19370304, 'steps': 100886, 'loss/train': 0.9884029030799866} 08/31/2021 07:27:03 - INFO - __main__ - Step 100888: {'lr': 0.00012398876832430837, 'samples': 19370496, 'steps': 100887, 'loss/train': 1.1523903608322144} 08/31/2021 07:27:03 - INFO - __main__ - Step 100889: {'lr': 0.0001239841850373516, 'samples': 19370688, 'steps': 100888, 'loss/train': 1.3252218961715698} 08/31/2021 07:27:03 - INFO - __main__ - Step 100890: {'lr': 0.00012397960180717557, 'samples': 19370880, 'steps': 100889, 'loss/train': 1.2319954633712769} 08/31/2021 07:27:06 - INFO - __main__ - Step 100891: {'lr': 0.00012397501863378244, 'samples': 19371072, 'steps': 100890, 'loss/train': 1.5936384201049805} 08/31/2021 07:27:06 - INFO - __main__ - Step 100892: {'lr': 0.00012397043551717418, 'samples': 19371264, 'steps': 100891, 'loss/train': 1.3606820106506348} 08/31/2021 07:27:06 - INFO - __main__ - Step 100893: {'lr': 0.0001239658524573529, 'samples': 19371456, 'steps': 100892, 'loss/train': 1.013109564781189} 08/31/2021 07:27:07 - INFO - __main__ - Step 100894: {'lr': 0.0001239612694543208, 'samples': 19371648, 'steps': 100893, 'loss/train': 0.060915522277355194} 08/31/2021 07:27:07 - INFO - __main__ - Step 100895: {'lr': 0.00012395668650807968, 'samples': 19371840, 'steps': 100894, 'loss/train': 1.1782466173171997} 08/31/2021 07:27:09 - INFO - __main__ - Step 100896: {'lr': 0.00012395210361863172, 'samples': 19372032, 'steps': 100895, 'loss/train': 1.2601392269134521} 08/31/2021 07:27:09 - INFO - __main__ - Step 100897: {'lr': 0.00012394752078597902, 'samples': 19372224, 'steps': 100896, 'loss/train': 1.2345640659332275} 08/31/2021 07:27:09 - INFO - __main__ - Step 100898: {'lr': 0.0001239429380101236, 'samples': 19372416, 'steps': 100897, 'loss/train': 1.3499751091003418} 08/31/2021 07:27:10 - INFO - __main__ - Step 100899: {'lr': 0.00012393835529106757, 'samples': 19372608, 'steps': 100898, 'loss/train': 0.9021561741828918} 08/31/2021 07:27:10 - INFO - __main__ - Step 100900: {'lr': 0.00012393377262881296, 'samples': 19372800, 'steps': 100899, 'loss/train': 1.2656290531158447} 08/31/2021 07:27:11 - INFO - __main__ - Step 100901: {'lr': 0.00012392919002336184, 'samples': 19372992, 'steps': 100900, 'loss/train': 0.6676000952720642} 08/31/2021 07:27:12 - INFO - __main__ - Step 100902: {'lr': 0.00012392460747471628, 'samples': 19373184, 'steps': 100901, 'loss/train': 1.1529649496078491} 08/31/2021 07:27:12 - INFO - __main__ - Step 100903: {'lr': 0.00012392002498287836, 'samples': 19373376, 'steps': 100902, 'loss/train': 1.3550227880477905} 08/31/2021 07:27:13 - INFO - __main__ - Step 100904: {'lr': 0.0001239154425478501, 'samples': 19373568, 'steps': 100903, 'loss/train': 1.2079434394836426} 08/31/2021 07:27:13 - INFO - __main__ - Step 100905: {'lr': 0.00012391086016963365, 'samples': 19373760, 'steps': 100904, 'loss/train': 1.0456671714782715} 08/31/2021 07:27:14 - INFO - __main__ - Step 100906: {'lr': 0.00012390627784823098, 'samples': 19373952, 'steps': 100905, 'loss/train': 0.4250079393386841} 08/31/2021 07:27:15 - INFO - __main__ - Step 100907: {'lr': 0.00012390169558364422, 'samples': 19374144, 'steps': 100906, 'loss/train': 1.2977715730667114} 08/31/2021 07:27:15 - INFO - __main__ - Step 100908: {'lr': 0.0001238971133758755, 'samples': 19374336, 'steps': 100907, 'loss/train': 0.8876873850822449} 08/31/2021 07:27:16 - INFO - __main__ - Step 100909: {'lr': 0.0001238925312249267, 'samples': 19374528, 'steps': 100908, 'loss/train': 2.3940742015838623} 08/31/2021 07:27:16 - INFO - __main__ - Step 100910: {'lr': 0.00012388794913079996, 'samples': 19374720, 'steps': 100909, 'loss/train': 0.30429667234420776} 08/31/2021 07:27:18 - INFO - __main__ - Step 100911: {'lr': 0.00012388336709349737, 'samples': 19374912, 'steps': 100910, 'loss/train': 1.138485312461853} 08/31/2021 07:27:18 - INFO - __main__ - Step 100912: {'lr': 0.000123878785113021, 'samples': 19375104, 'steps': 100911, 'loss/train': 0.990445077419281} 08/31/2021 07:27:18 - INFO - __main__ - Step 100913: {'lr': 0.0001238742031893729, 'samples': 19375296, 'steps': 100912, 'loss/train': 0.9129601716995239} 08/31/2021 07:27:19 - INFO - __main__ - Step 100914: {'lr': 0.00012386962132255515, 'samples': 19375488, 'steps': 100913, 'loss/train': 0.9082217216491699} 08/31/2021 07:27:19 - INFO - __main__ - Step 100915: {'lr': 0.00012386503951256978, 'samples': 19375680, 'steps': 100914, 'loss/train': 1.3996118307113647} 08/31/2021 07:27:20 - INFO - __main__ - Step 100916: {'lr': 0.0001238604577594189, 'samples': 19375872, 'steps': 100915, 'loss/train': 2.36234450340271} 08/31/2021 07:27:21 - INFO - __main__ - Step 100917: {'lr': 0.00012385587606310452, 'samples': 19376064, 'steps': 100916, 'loss/train': 0.03793129324913025} 08/31/2021 07:27:21 - INFO - __main__ - Step 100918: {'lr': 0.00012385129442362878, 'samples': 19376256, 'steps': 100917, 'loss/train': 1.089276909828186} 08/31/2021 07:27:22 - INFO - __main__ - Step 100919: {'lr': 0.00012384671284099366, 'samples': 19376448, 'steps': 100918, 'loss/train': 1.5065094232559204} 08/31/2021 07:27:22 - INFO - __main__ - Step 100920: {'lr': 0.0001238421313152013, 'samples': 19376640, 'steps': 100919, 'loss/train': 0.9015535116195679} 08/31/2021 07:27:24 - INFO - __main__ - Step 100921: {'lr': 0.00012383754984625377, 'samples': 19376832, 'steps': 100920, 'loss/train': 0.734326958656311} 08/31/2021 07:27:24 - INFO - __main__ - Step 100922: {'lr': 0.00012383296843415304, 'samples': 19377024, 'steps': 100921, 'loss/train': 1.3054183721542358} 08/31/2021 07:27:25 - INFO - __main__ - Step 100923: {'lr': 0.0001238283870789012, 'samples': 19377216, 'steps': 100922, 'loss/train': 1.0761206150054932} 08/31/2021 07:27:25 - INFO - __main__ - Step 100924: {'lr': 0.00012382380578050036, 'samples': 19377408, 'steps': 100923, 'loss/train': 1.036180019378662} 08/31/2021 07:27:25 - INFO - __main__ - Step 100925: {'lr': 0.0001238192245389526, 'samples': 19377600, 'steps': 100924, 'loss/train': 1.2059166431427002} 08/31/2021 07:27:27 - INFO - __main__ - Step 100926: {'lr': 0.0001238146433542599, 'samples': 19377792, 'steps': 100925, 'loss/train': 1.219902515411377} 08/31/2021 07:27:27 - INFO - __main__ - Step 100927: {'lr': 0.0001238100622264244, 'samples': 19377984, 'steps': 100926, 'loss/train': 0.48723599314689636} 08/31/2021 07:27:28 - INFO - __main__ - Step 100928: {'lr': 0.00012380548115544814, 'samples': 19378176, 'steps': 100927, 'loss/train': 1.1040207147598267} 08/31/2021 07:27:28 - INFO - __main__ - Step 100929: {'lr': 0.00012380090014133316, 'samples': 19378368, 'steps': 100928, 'loss/train': 1.3726599216461182} 08/31/2021 07:27:29 - INFO - __main__ - Step 100930: {'lr': 0.00012379631918408156, 'samples': 19378560, 'steps': 100929, 'loss/train': 1.507658839225769} 08/31/2021 07:27:30 - INFO - __main__ - Step 100931: {'lr': 0.00012379173828369538, 'samples': 19378752, 'steps': 100930, 'loss/train': 0.4294075667858124} 08/31/2021 07:27:30 - INFO - __main__ - Step 100932: {'lr': 0.0001237871574401767, 'samples': 19378944, 'steps': 100931, 'loss/train': 0.877061128616333} 08/31/2021 07:27:31 - INFO - __main__ - Step 100933: {'lr': 0.0001237825766535276, 'samples': 19379136, 'steps': 100932, 'loss/train': 1.4014699459075928} 08/31/2021 07:27:31 - INFO - __main__ - Step 100934: {'lr': 0.00012377799592375012, 'samples': 19379328, 'steps': 100933, 'loss/train': 1.260118007659912} 08/31/2021 07:27:31 - INFO - __main__ - Step 100935: {'lr': 0.0001237734152508464, 'samples': 19379520, 'steps': 100934, 'loss/train': 1.2487530708312988} 08/31/2021 07:27:33 - INFO - __main__ - Step 100936: {'lr': 0.00012376883463481833, 'samples': 19379712, 'steps': 100935, 'loss/train': 0.7333464622497559} 08/31/2021 07:27:33 - INFO - __main__ - Step 100937: {'lr': 0.00012376425407566811, 'samples': 19379904, 'steps': 100936, 'loss/train': 1.309653878211975} 08/31/2021 07:27:34 - INFO - __main__ - Step 100938: {'lr': 0.00012375967357339775, 'samples': 19380096, 'steps': 100937, 'loss/train': 1.2222740650177002} 08/31/2021 07:27:34 - INFO - __main__ - Step 100939: {'lr': 0.00012375509312800934, 'samples': 19380288, 'steps': 100938, 'loss/train': 0.9607834219932556} 08/31/2021 07:27:34 - INFO - __main__ - Step 100940: {'lr': 0.0001237505127395049, 'samples': 19380480, 'steps': 100939, 'loss/train': 1.10877525806427} 08/31/2021 07:27:36 - INFO - __main__ - Step 100941: {'lr': 0.00012374593240788658, 'samples': 19380672, 'steps': 100940, 'loss/train': 1.4840259552001953} 08/31/2021 07:27:37 - INFO - __main__ - Step 100942: {'lr': 0.00012374135213315637, 'samples': 19380864, 'steps': 100941, 'loss/train': 0.4555549621582031} 08/31/2021 07:27:37 - INFO - __main__ - Step 100943: {'lr': 0.00012373677191531638, 'samples': 19381056, 'steps': 100942, 'loss/train': 0.9420198798179626} 08/31/2021 07:27:37 - INFO - __main__ - Step 100944: {'lr': 0.0001237321917543686, 'samples': 19381248, 'steps': 100943, 'loss/train': 1.5678825378417969} 08/31/2021 07:27:38 - INFO - __main__ - Step 100945: {'lr': 0.0001237276116503152, 'samples': 19381440, 'steps': 100944, 'loss/train': 0.061361342668533325} 08/31/2021 07:27:40 - INFO - __main__ - Step 100946: {'lr': 0.00012372303160315817, 'samples': 19381632, 'steps': 100945, 'loss/train': 0.6879174113273621} 08/31/2021 07:27:40 - INFO - __main__ - Step 100947: {'lr': 0.0001237184516128996, 'samples': 19381824, 'steps': 100946, 'loss/train': 1.0136088132858276} 08/31/2021 07:27:40 - INFO - __main__ - Step 100948: {'lr': 0.00012371387167954166, 'samples': 19382016, 'steps': 100947, 'loss/train': 0.7030196189880371} 08/31/2021 07:27:41 - INFO - __main__ - Step 100949: {'lr': 0.00012370929180308617, 'samples': 19382208, 'steps': 100948, 'loss/train': 1.1126495599746704} 08/31/2021 07:27:41 - INFO - __main__ - Step 100950: {'lr': 0.00012370471198353534, 'samples': 19382400, 'steps': 100949, 'loss/train': 1.2530651092529297} 08/31/2021 07:27:43 - INFO - __main__ - Step 100951: {'lr': 0.00012370013222089122, 'samples': 19382592, 'steps': 100950, 'loss/train': 0.1075361892580986} 08/31/2021 07:27:43 - INFO - __main__ - Step 100952: {'lr': 0.0001236955525151559, 'samples': 19382784, 'steps': 100951, 'loss/train': 1.1919888257980347} 08/31/2021 07:27:44 - INFO - __main__ - Step 100953: {'lr': 0.00012369097286633136, 'samples': 19382976, 'steps': 100952, 'loss/train': 1.0575090646743774} 08/31/2021 07:27:44 - INFO - __main__ - Step 100954: {'lr': 0.00012368639327441975, 'samples': 19383168, 'steps': 100953, 'loss/train': 1.062398910522461} 08/31/2021 07:27:44 - INFO - __main__ - Step 100955: {'lr': 0.0001236818137394231, 'samples': 19383360, 'steps': 100954, 'loss/train': 1.246273398399353} 08/31/2021 07:27:45 - INFO - __main__ - Step 100956: {'lr': 0.00012367723426134344, 'samples': 19383552, 'steps': 100955, 'loss/train': 0.4119336009025574} 08/31/2021 07:27:46 - INFO - __main__ - Step 100957: {'lr': 0.00012367265484018288, 'samples': 19383744, 'steps': 100956, 'loss/train': 1.2995171546936035} 08/31/2021 07:27:47 - INFO - __main__ - Step 100958: {'lr': 0.00012366807547594354, 'samples': 19383936, 'steps': 100957, 'loss/train': 1.2231171131134033} 08/31/2021 07:27:47 - INFO - __main__ - Step 100959: {'lr': 0.00012366349616862735, 'samples': 19384128, 'steps': 100958, 'loss/train': 1.1719645261764526} 08/31/2021 07:27:47 - INFO - __main__ - Step 100960: {'lr': 0.00012365891691823645, 'samples': 19384320, 'steps': 100959, 'loss/train': 0.03033527545630932} 08/31/2021 07:27:48 - INFO - __main__ - Step 100961: {'lr': 0.00012365433772477288, 'samples': 19384512, 'steps': 100960, 'loss/train': 1.749696135520935} 08/31/2021 07:27:49 - INFO - __main__ - Step 100962: {'lr': 0.00012364975858823884, 'samples': 19384704, 'steps': 100961, 'loss/train': 0.45037564635276794} 08/31/2021 07:27:50 - INFO - __main__ - Step 100963: {'lr': 0.00012364517950863615, 'samples': 19384896, 'steps': 100962, 'loss/train': 1.0962271690368652} 08/31/2021 07:27:50 - INFO - __main__ - Step 100964: {'lr': 0.000123640600485967, 'samples': 19385088, 'steps': 100963, 'loss/train': 1.1296806335449219} 08/31/2021 07:27:51 - INFO - __main__ - Step 100965: {'lr': 0.00012363602152023348, 'samples': 19385280, 'steps': 100964, 'loss/train': 0.5591887831687927} 08/31/2021 07:27:51 - INFO - __main__ - Step 100966: {'lr': 0.00012363144261143757, 'samples': 19385472, 'steps': 100965, 'loss/train': 1.0964202880859375} 08/31/2021 07:27:53 - INFO - __main__ - Step 100967: {'lr': 0.0001236268637595814, 'samples': 19385664, 'steps': 100966, 'loss/train': 1.3215088844299316} 08/31/2021 07:27:53 - INFO - __main__ - Step 100968: {'lr': 0.00012362228496466703, 'samples': 19385856, 'steps': 100967, 'loss/train': 0.6869611144065857} 08/31/2021 07:27:54 - INFO - __main__ - Step 100969: {'lr': 0.0001236177062266965, 'samples': 19386048, 'steps': 100968, 'loss/train': 1.1261928081512451} 08/31/2021 07:27:54 - INFO - __main__ - Step 100970: {'lr': 0.00012361312754567187, 'samples': 19386240, 'steps': 100969, 'loss/train': 0.01798630692064762} 08/31/2021 07:27:54 - INFO - __main__ - Step 100971: {'lr': 0.00012360854892159523, 'samples': 19386432, 'steps': 100970, 'loss/train': 0.01403286773711443} 08/31/2021 07:27:55 - INFO - __main__ - Step 100972: {'lr': 0.0001236039703544686, 'samples': 19386624, 'steps': 100971, 'loss/train': 0.5245627164840698} 08/31/2021 07:27:56 - INFO - __main__ - Step 100973: {'lr': 0.0001235993918442941, 'samples': 19386816, 'steps': 100972, 'loss/train': 1.661704182624817} 08/31/2021 07:27:57 - INFO - __main__ - Step 100974: {'lr': 0.00012359481339107377, 'samples': 19387008, 'steps': 100973, 'loss/train': 1.0661252737045288} 08/31/2021 07:27:57 - INFO - __main__ - Step 100975: {'lr': 0.00012359023499480972, 'samples': 19387200, 'steps': 100974, 'loss/train': 1.154654860496521} 08/31/2021 07:27:57 - INFO - __main__ - Step 100976: {'lr': 0.0001235856566555039, 'samples': 19387392, 'steps': 100975, 'loss/train': 0.945034921169281} 08/31/2021 07:27:58 - INFO - __main__ - Step 100977: {'lr': 0.0001235810783731584, 'samples': 19387584, 'steps': 100976, 'loss/train': 0.7148399949073792} 08/31/2021 07:27:59 - INFO - __main__ - Step 100978: {'lr': 0.00012357650014777535, 'samples': 19387776, 'steps': 100977, 'loss/train': 0.7809057235717773} 08/31/2021 07:28:00 - INFO - __main__ - Step 100979: {'lr': 0.00012357192197935677, 'samples': 19387968, 'steps': 100978, 'loss/train': 0.4579121172428131} 08/31/2021 07:28:00 - INFO - __main__ - Step 100980: {'lr': 0.0001235673438679047, 'samples': 19388160, 'steps': 100979, 'loss/train': 0.6078177690505981} 08/31/2021 07:28:00 - INFO - __main__ - Step 100981: {'lr': 0.00012356276581342127, 'samples': 19388352, 'steps': 100980, 'loss/train': 0.6966748833656311} 08/31/2021 07:28:01 - INFO - __main__ - Step 100982: {'lr': 0.0001235581878159085, 'samples': 19388544, 'steps': 100981, 'loss/train': 1.3758691549301147} 08/31/2021 07:28:02 - INFO - __main__ - Step 100983: {'lr': 0.00012355360987536846, 'samples': 19388736, 'steps': 100982, 'loss/train': 1.3983886241912842} 08/31/2021 07:28:03 - INFO - __main__ - Step 100984: {'lr': 0.0001235490319918032, 'samples': 19388928, 'steps': 100983, 'loss/train': 1.7293542623519897} 08/31/2021 07:28:03 - INFO - __main__ - Step 100985: {'lr': 0.0001235444541652148, 'samples': 19389120, 'steps': 100984, 'loss/train': 1.3907934427261353} 08/31/2021 07:28:04 - INFO - __main__ - Step 100986: {'lr': 0.00012353987639560532, 'samples': 19389312, 'steps': 100985, 'loss/train': 0.849755585193634} 08/31/2021 07:28:04 - INFO - __main__ - Step 100987: {'lr': 0.00012353529868297685, 'samples': 19389504, 'steps': 100986, 'loss/train': 1.1213456392288208} 08/31/2021 07:28:04 - INFO - __main__ - Step 100988: {'lr': 0.00012353072102733138, 'samples': 19389696, 'steps': 100987, 'loss/train': 0.054942574352025986} 08/31/2021 07:28:06 - INFO - __main__ - Step 100989: {'lr': 0.00012352614342867114, 'samples': 19389888, 'steps': 100988, 'loss/train': 0.8534911274909973} 08/31/2021 07:28:06 - INFO - __main__ - Step 100990: {'lr': 0.00012352156588699796, 'samples': 19390080, 'steps': 100989, 'loss/train': 0.9454047679901123} 08/31/2021 07:28:07 - INFO - __main__ - Step 100991: {'lr': 0.000123516988402314, 'samples': 19390272, 'steps': 100990, 'loss/train': 0.39109712839126587} 08/31/2021 07:28:07 - INFO - __main__ - Step 100992: {'lr': 0.00012351241097462132, 'samples': 19390464, 'steps': 100991, 'loss/train': 1.5304925441741943} 08/31/2021 07:28:07 - INFO - __main__ - Step 100993: {'lr': 0.000123507833603922, 'samples': 19390656, 'steps': 100992, 'loss/train': 1.282875657081604} 08/31/2021 07:28:09 - INFO - __main__ - Step 100994: {'lr': 0.00012350325629021815, 'samples': 19390848, 'steps': 100993, 'loss/train': 0.9634736776351929} 08/31/2021 07:28:09 - INFO - __main__ - Step 100995: {'lr': 0.00012349867903351173, 'samples': 19391040, 'steps': 100994, 'loss/train': 0.9981614351272583} 08/31/2021 07:28:10 - INFO - __main__ - Step 100996: {'lr': 0.00012349410183380488, 'samples': 19391232, 'steps': 100995, 'loss/train': 1.24323308467865} 08/31/2021 07:28:10 - INFO - __main__ - Step 100997: {'lr': 0.0001234895246910996, 'samples': 19391424, 'steps': 100996, 'loss/train': 1.2585254907608032} 08/31/2021 07:28:10 - INFO - __main__ - Step 100998: {'lr': 0.00012348494760539802, 'samples': 19391616, 'steps': 100997, 'loss/train': 0.727639377117157} 08/31/2021 07:28:13 - INFO - __main__ - Step 100999: {'lr': 0.00012348037057670217, 'samples': 19391808, 'steps': 100998, 'loss/train': 0.1871088147163391} 08/31/2021 07:28:13 - INFO - __main__ - Step 101000: {'lr': 0.0001234757936050141, 'samples': 19392000, 'steps': 100999, 'loss/train': 0.7410372495651245} 08/31/2021 07:28:13 - INFO - __main__ - Step 101001: {'lr': 0.0001234712166903359, 'samples': 19392192, 'steps': 101000, 'loss/train': 1.274217128753662} 08/31/2021 07:28:14 - INFO - __main__ - Step 101002: {'lr': 0.0001234666398326697, 'samples': 19392384, 'steps': 101001, 'loss/train': 0.015438989736139774} 08/31/2021 07:28:14 - INFO - __main__ - Step 101003: {'lr': 0.0001234620630320174, 'samples': 19392576, 'steps': 101002, 'loss/train': 1.088982343673706} 08/31/2021 07:28:15 - INFO - __main__ - Step 101004: {'lr': 0.00012345748628838114, 'samples': 19392768, 'steps': 101003, 'loss/train': 0.5974991321563721} 08/31/2021 07:28:16 - INFO - __main__ - Step 101005: {'lr': 0.00012345290960176294, 'samples': 19392960, 'steps': 101004, 'loss/train': 1.0137461423873901} 08/31/2021 07:28:17 - INFO - __main__ - Step 101006: {'lr': 0.00012344833297216496, 'samples': 19393152, 'steps': 101005, 'loss/train': 2.4483354091644287} 08/31/2021 07:28:17 - INFO - __main__ - Step 101007: {'lr': 0.0001234437563995892, 'samples': 19393344, 'steps': 101006, 'loss/train': 0.37758561968803406} 08/31/2021 07:28:17 - INFO - __main__ - Step 101008: {'lr': 0.0001234391798840377, 'samples': 19393536, 'steps': 101007, 'loss/train': 1.1453807353973389} 08/31/2021 07:28:18 - INFO - __main__ - Step 101009: {'lr': 0.00012343460342551259, 'samples': 19393728, 'steps': 101008, 'loss/train': 1.0472379922866821} 08/31/2021 07:28:19 - INFO - __main__ - Step 101010: {'lr': 0.00012343002702401584, 'samples': 19393920, 'steps': 101009, 'loss/train': 0.9767241477966309} 08/31/2021 07:28:20 - INFO - __main__ - Step 101011: {'lr': 0.00012342545067954965, 'samples': 19394112, 'steps': 101010, 'loss/train': 1.2072327136993408} 08/31/2021 07:28:20 - INFO - __main__ - Step 101012: {'lr': 0.0001234208743921159, 'samples': 19394304, 'steps': 101011, 'loss/train': 0.9996216297149658} 08/31/2021 07:28:20 - INFO - __main__ - Step 101013: {'lr': 0.0001234162981617168, 'samples': 19394496, 'steps': 101012, 'loss/train': 0.5823945999145508} 08/31/2021 07:28:21 - INFO - __main__ - Step 101014: {'lr': 0.00012341172198835438, 'samples': 19394688, 'steps': 101013, 'loss/train': 1.01802659034729} 08/31/2021 07:28:22 - INFO - __main__ - Step 101015: {'lr': 0.00012340714587203078, 'samples': 19394880, 'steps': 101014, 'loss/train': 0.997427761554718} 08/31/2021 07:28:23 - INFO - __main__ - Step 101016: {'lr': 0.00012340256981274787, 'samples': 19395072, 'steps': 101015, 'loss/train': 1.1984589099884033} 08/31/2021 07:28:23 - INFO - __main__ - Step 101017: {'lr': 0.0001233979938105078, 'samples': 19395264, 'steps': 101016, 'loss/train': 1.072455883026123} 08/31/2021 07:28:23 - INFO - __main__ - Step 101018: {'lr': 0.0001233934178653126, 'samples': 19395456, 'steps': 101017, 'loss/train': 0.874440610408783} 08/31/2021 07:28:24 - INFO - __main__ - Step 101019: {'lr': 0.00012338884197716441, 'samples': 19395648, 'steps': 101018, 'loss/train': 1.029476523399353} 08/31/2021 07:28:25 - INFO - __main__ - Step 101020: {'lr': 0.00012338426614606527, 'samples': 19395840, 'steps': 101019, 'loss/train': 1.154707431793213} 08/31/2021 07:28:26 - INFO - __main__ - Step 101021: {'lr': 0.0001233796903720172, 'samples': 19396032, 'steps': 101020, 'loss/train': 1.3896071910858154} 08/31/2021 07:28:26 - INFO - __main__ - Step 101022: {'lr': 0.0001233751146550223, 'samples': 19396224, 'steps': 101021, 'loss/train': 1.053342342376709} 08/31/2021 07:28:26 - INFO - __main__ - Step 101023: {'lr': 0.0001233705389950826, 'samples': 19396416, 'steps': 101022, 'loss/train': 1.5775744915008545} 08/31/2021 07:28:27 - INFO - __main__ - Step 101024: {'lr': 0.0001233659633922002, 'samples': 19396608, 'steps': 101023, 'loss/train': 2.271249771118164} 08/31/2021 07:28:28 - INFO - __main__ - Step 101025: {'lr': 0.00012336138784637714, 'samples': 19396800, 'steps': 101024, 'loss/train': 0.6166203618049622} 08/31/2021 07:28:29 - INFO - __main__ - Step 101026: {'lr': 0.00012335681235761548, 'samples': 19396992, 'steps': 101025, 'loss/train': 1.182600975036621} 08/31/2021 07:28:29 - INFO - __main__ - Step 101027: {'lr': 0.0001233522369259173, 'samples': 19397184, 'steps': 101026, 'loss/train': 1.121616244316101} 08/31/2021 07:28:30 - INFO - __main__ - Step 101028: {'lr': 0.00012334766155128462, 'samples': 19397376, 'steps': 101027, 'loss/train': 1.098909616470337} 08/31/2021 07:28:30 - INFO - __main__ - Step 101029: {'lr': 0.00012334308623371964, 'samples': 19397568, 'steps': 101028, 'loss/train': 0.03511198237538338} 08/31/2021 07:28:30 - INFO - __main__ - Step 101030: {'lr': 0.00012333851097322423, 'samples': 19397760, 'steps': 101029, 'loss/train': 1.0267434120178223} 08/31/2021 07:28:32 - INFO - __main__ - Step 101031: {'lr': 0.0001233339357698005, 'samples': 19397952, 'steps': 101030, 'loss/train': 1.201441764831543} 08/31/2021 07:28:32 - INFO - __main__ - Step 101032: {'lr': 0.00012332936062345057, 'samples': 19398144, 'steps': 101031, 'loss/train': 1.0320885181427002} 08/31/2021 07:28:33 - INFO - __main__ - Step 101033: {'lr': 0.00012332478553417648, 'samples': 19398336, 'steps': 101032, 'loss/train': 1.168994665145874} 08/31/2021 07:28:33 - INFO - __main__ - Step 101034: {'lr': 0.00012332021050198027, 'samples': 19398528, 'steps': 101033, 'loss/train': 1.5921990871429443} 08/31/2021 07:28:33 - INFO - __main__ - Step 101035: {'lr': 0.00012331563552686403, 'samples': 19398720, 'steps': 101034, 'loss/train': 0.7263823747634888} 08/31/2021 07:28:35 - INFO - __main__ - Step 101036: {'lr': 0.0001233110606088298, 'samples': 19398912, 'steps': 101035, 'loss/train': 1.2343883514404297} 08/31/2021 07:28:36 - INFO - __main__ - Step 101037: {'lr': 0.00012330648574787964, 'samples': 19399104, 'steps': 101036, 'loss/train': 1.5284571647644043} 08/31/2021 07:28:36 - INFO - __main__ - Step 101038: {'lr': 0.00012330191094401567, 'samples': 19399296, 'steps': 101037, 'loss/train': 0.7776716351509094} 08/31/2021 07:28:36 - INFO - __main__ - Step 101039: {'lr': 0.00012329733619723986, 'samples': 19399488, 'steps': 101038, 'loss/train': 1.2882100343704224} 08/31/2021 07:28:37 - INFO - __main__ - Step 101040: {'lr': 0.0001232927615075543, 'samples': 19399680, 'steps': 101039, 'loss/train': 1.1697943210601807} 08/31/2021 07:28:38 - INFO - __main__ - Step 101041: {'lr': 0.0001232881868749611, 'samples': 19399872, 'steps': 101040, 'loss/train': 1.4649347066879272} 08/31/2021 07:28:39 - INFO - __main__ - Step 101042: {'lr': 0.0001232836122994624, 'samples': 19400064, 'steps': 101041, 'loss/train': 1.3327786922454834} 08/31/2021 07:28:39 - INFO - __main__ - Step 101043: {'lr': 0.00012327903778106, 'samples': 19400256, 'steps': 101042, 'loss/train': 0.829323410987854} 08/31/2021 07:28:39 - INFO - __main__ - Step 101044: {'lr': 0.00012327446331975616, 'samples': 19400448, 'steps': 101043, 'loss/train': 0.927006721496582} 08/31/2021 07:28:40 - INFO - __main__ - Step 101045: {'lr': 0.0001232698889155529, 'samples': 19400640, 'steps': 101044, 'loss/train': 0.15722361207008362} 08/31/2021 07:28:41 - INFO - __main__ - Step 101046: {'lr': 0.0001232653145684522, 'samples': 19400832, 'steps': 101045, 'loss/train': 1.3472180366516113} 08/31/2021 07:28:42 - INFO - __main__ - Step 101047: {'lr': 0.00012326074027845625, 'samples': 19401024, 'steps': 101046, 'loss/train': 0.7547399401664734} 08/31/2021 07:28:42 - INFO - __main__ - Step 101048: {'lr': 0.00012325616604556705, 'samples': 19401216, 'steps': 101047, 'loss/train': 1.0169779062271118} 08/31/2021 07:28:42 - INFO - __main__ - Step 101049: {'lr': 0.00012325159186978666, 'samples': 19401408, 'steps': 101048, 'loss/train': 1.0394915342330933} 08/31/2021 07:28:43 - INFO - __main__ - Step 101050: {'lr': 0.00012324701775111714, 'samples': 19401600, 'steps': 101049, 'loss/train': 1.307293176651001} 08/31/2021 07:28:44 - INFO - __main__ - Step 101051: {'lr': 0.00012324244368956057, 'samples': 19401792, 'steps': 101050, 'loss/train': 1.2679920196533203} 08/31/2021 07:28:45 - INFO - __main__ - Step 101052: {'lr': 0.00012323786968511898, 'samples': 19401984, 'steps': 101051, 'loss/train': 1.1458590030670166} 08/31/2021 07:28:45 - INFO - __main__ - Step 101053: {'lr': 0.00012323329573779454, 'samples': 19402176, 'steps': 101052, 'loss/train': 1.079854130744934} 08/31/2021 07:28:46 - INFO - __main__ - Step 101054: {'lr': 0.00012322872184758916, 'samples': 19402368, 'steps': 101053, 'loss/train': 0.8762382864952087} 08/31/2021 07:28:46 - INFO - __main__ - Step 101055: {'lr': 0.00012322414801450493, 'samples': 19402560, 'steps': 101054, 'loss/train': 1.064357876777649} 08/31/2021 07:28:46 - INFO - __main__ - Step 101056: {'lr': 0.00012321957423854396, 'samples': 19402752, 'steps': 101055, 'loss/train': 0.03376274183392525} 08/31/2021 07:28:49 - INFO - __main__ - Step 101057: {'lr': 0.0001232150005197083, 'samples': 19402944, 'steps': 101056, 'loss/train': 0.3541387915611267} 08/31/2021 07:28:49 - INFO - __main__ - Step 101058: {'lr': 0.000123210426858, 'samples': 19403136, 'steps': 101057, 'loss/train': 0.32879188656806946} 08/31/2021 07:28:49 - INFO - __main__ - Step 101059: {'lr': 0.0001232058532534211, 'samples': 19403328, 'steps': 101058, 'loss/train': 0.8540230989456177} 08/31/2021 07:28:50 - INFO - __main__ - Step 101060: {'lr': 0.00012320127970597372, 'samples': 19403520, 'steps': 101059, 'loss/train': 1.5063180923461914} 08/31/2021 07:28:50 - INFO - __main__ - Step 101061: {'lr': 0.00012319670621565988, 'samples': 19403712, 'steps': 101060, 'loss/train': 1.4534579515457153} 08/31/2021 07:28:51 - INFO - __main__ - Step 101062: {'lr': 0.00012319213278248162, 'samples': 19403904, 'steps': 101061, 'loss/train': 1.6238635778427124} 08/31/2021 07:28:52 - INFO - __main__ - Step 101063: {'lr': 0.00012318755940644106, 'samples': 19404096, 'steps': 101062, 'loss/train': 0.932535707950592} 08/31/2021 07:28:52 - INFO - __main__ - Step 101064: {'lr': 0.00012318298608754032, 'samples': 19404288, 'steps': 101063, 'loss/train': 0.6429392695426941} 08/31/2021 07:28:53 - INFO - __main__ - Step 101065: {'lr': 0.00012317841282578123, 'samples': 19404480, 'steps': 101064, 'loss/train': 0.8014376163482666} 08/31/2021 07:28:53 - INFO - __main__ - Step 101066: {'lr': 0.00012317383962116604, 'samples': 19404672, 'steps': 101065, 'loss/train': 0.646342396736145} 08/31/2021 07:28:54 - INFO - __main__ - Step 101067: {'lr': 0.00012316926647369675, 'samples': 19404864, 'steps': 101066, 'loss/train': 1.0388814210891724} 08/31/2021 07:28:55 - INFO - __main__ - Step 101068: {'lr': 0.00012316469338337544, 'samples': 19405056, 'steps': 101067, 'loss/train': 1.5597381591796875} 08/31/2021 07:28:55 - INFO - __main__ - Step 101069: {'lr': 0.00012316012035020415, 'samples': 19405248, 'steps': 101068, 'loss/train': 1.141764521598816} 08/31/2021 07:28:56 - INFO - __main__ - Step 101070: {'lr': 0.00012315554737418494, 'samples': 19405440, 'steps': 101069, 'loss/train': 1.3971025943756104} 08/31/2021 07:28:56 - INFO - __main__ - Step 101071: {'lr': 0.0001231509744553199, 'samples': 19405632, 'steps': 101070, 'loss/train': 1.265699028968811} 08/31/2021 07:28:57 - INFO - __main__ - Step 101072: {'lr': 0.00012314640159361107, 'samples': 19405824, 'steps': 101071, 'loss/train': 1.289044737815857} 08/31/2021 07:28:58 - INFO - __main__ - Step 101073: {'lr': 0.00012314182878906053, 'samples': 19406016, 'steps': 101072, 'loss/train': 1.1259489059448242} 08/31/2021 07:28:58 - INFO - __main__ - Step 101074: {'lr': 0.0001231372560416703, 'samples': 19406208, 'steps': 101073, 'loss/train': 1.0356582403182983} 08/31/2021 07:28:59 - INFO - __main__ - Step 101075: {'lr': 0.00012313268335144257, 'samples': 19406400, 'steps': 101074, 'loss/train': 1.5147771835327148} 08/31/2021 07:28:59 - INFO - __main__ - Step 101076: {'lr': 0.0001231281107183792, 'samples': 19406592, 'steps': 101075, 'loss/train': 1.2471140623092651} 08/31/2021 07:29:00 - INFO - __main__ - Step 101077: {'lr': 0.00012312353814248234, 'samples': 19406784, 'steps': 101076, 'loss/train': 1.3476086854934692} 08/31/2021 07:29:01 - INFO - __main__ - Step 101078: {'lr': 0.00012311896562375405, 'samples': 19406976, 'steps': 101077, 'loss/train': 1.5292656421661377} 08/31/2021 07:29:01 - INFO - __main__ - Step 101079: {'lr': 0.00012311439316219642, 'samples': 19407168, 'steps': 101078, 'loss/train': 1.2068418264389038} 08/31/2021 07:29:02 - INFO - __main__ - Step 101080: {'lr': 0.00012310982075781148, 'samples': 19407360, 'steps': 101079, 'loss/train': 1.7519891262054443} 08/31/2021 07:29:02 - INFO - __main__ - Step 101081: {'lr': 0.0001231052484106013, 'samples': 19407552, 'steps': 101080, 'loss/train': 1.209014892578125} 08/31/2021 07:29:04 - INFO - __main__ - Step 101082: {'lr': 0.0001231006761205679, 'samples': 19407744, 'steps': 101081, 'loss/train': 1.3961081504821777} 08/31/2021 07:29:04 - INFO - __main__ - Step 101083: {'lr': 0.0001230961038877134, 'samples': 19407936, 'steps': 101082, 'loss/train': 1.0716780424118042} 08/31/2021 07:29:04 - INFO - __main__ - Step 101084: {'lr': 0.00012309153171203985, 'samples': 19408128, 'steps': 101083, 'loss/train': 1.0460225343704224} 08/31/2021 07:29:05 - INFO - __main__ - Step 101085: {'lr': 0.0001230869595935493, 'samples': 19408320, 'steps': 101084, 'loss/train': 1.3982762098312378} 08/31/2021 07:29:05 - INFO - __main__ - Step 101086: {'lr': 0.00012308238753224387, 'samples': 19408512, 'steps': 101085, 'loss/train': 1.422070026397705} 08/31/2021 07:29:05 - INFO - __main__ - Step 101087: {'lr': 0.0001230778155281255, 'samples': 19408704, 'steps': 101086, 'loss/train': 1.3017586469650269} 08/31/2021 07:29:07 - INFO - __main__ - Step 101088: {'lr': 0.00012307324358119628, 'samples': 19408896, 'steps': 101087, 'loss/train': 0.6428318619728088} 08/31/2021 07:29:07 - INFO - __main__ - Step 101089: {'lr': 0.0001230686716914583, 'samples': 19409088, 'steps': 101088, 'loss/train': 0.3832978904247284} 08/31/2021 07:29:08 - INFO - __main__ - Step 101090: {'lr': 0.00012306409985891363, 'samples': 19409280, 'steps': 101089, 'loss/train': 1.3919206857681274} 08/31/2021 07:29:08 - INFO - __main__ - Step 101091: {'lr': 0.00012305952808356433, 'samples': 19409472, 'steps': 101090, 'loss/train': 0.913593053817749} 08/31/2021 07:29:08 - INFO - __main__ - Step 101092: {'lr': 0.00012305495636541242, 'samples': 19409664, 'steps': 101091, 'loss/train': 1.513794183731079} 08/31/2021 07:29:10 - INFO - __main__ - Step 101093: {'lr': 0.00012305038470446, 'samples': 19409856, 'steps': 101092, 'loss/train': 0.6673634648323059} 08/31/2021 07:29:10 - INFO - __main__ - Step 101094: {'lr': 0.00012304581310070912, 'samples': 19410048, 'steps': 101093, 'loss/train': 1.3907558917999268} 08/31/2021 07:29:11 - INFO - __main__ - Step 101095: {'lr': 0.00012304124155416182, 'samples': 19410240, 'steps': 101094, 'loss/train': 1.070164680480957} 08/31/2021 07:29:11 - INFO - __main__ - Step 101096: {'lr': 0.0001230366700648202, 'samples': 19410432, 'steps': 101095, 'loss/train': 0.8415691256523132} 08/31/2021 07:29:11 - INFO - __main__ - Step 101097: {'lr': 0.00012303209863268638, 'samples': 19410624, 'steps': 101096, 'loss/train': 1.2168388366699219} 08/31/2021 07:29:13 - INFO - __main__ - Step 101098: {'lr': 0.00012302752725776224, 'samples': 19410816, 'steps': 101097, 'loss/train': 2.2728705406188965} 08/31/2021 07:29:13 - INFO - __main__ - Step 101099: {'lr': 0.00012302295594004997, 'samples': 19411008, 'steps': 101098, 'loss/train': 1.0643810033798218} 08/31/2021 07:29:14 - INFO - __main__ - Step 101100: {'lr': 0.00012301838467955155, 'samples': 19411200, 'steps': 101099, 'loss/train': 1.0724337100982666} 08/31/2021 07:29:14 - INFO - __main__ - Step 101101: {'lr': 0.00012301381347626912, 'samples': 19411392, 'steps': 101100, 'loss/train': 0.5685582160949707} 08/31/2021 07:29:15 - INFO - __main__ - Step 101102: {'lr': 0.0001230092423302047, 'samples': 19411584, 'steps': 101101, 'loss/train': 1.235297679901123} 08/31/2021 07:29:16 - INFO - __main__ - Step 101103: {'lr': 0.00012300467124136034, 'samples': 19411776, 'steps': 101102, 'loss/train': 1.3841930627822876} 08/31/2021 07:29:17 - INFO - __main__ - Step 101104: {'lr': 0.0001230001002097381, 'samples': 19411968, 'steps': 101103, 'loss/train': 1.2055734395980835} 08/31/2021 07:29:17 - INFO - __main__ - Step 101105: {'lr': 0.0001229955292353401, 'samples': 19412160, 'steps': 101104, 'loss/train': 1.1976107358932495} 08/31/2021 07:29:18 - INFO - __main__ - Step 101106: {'lr': 0.00012299095831816835, 'samples': 19412352, 'steps': 101105, 'loss/train': 0.8678342700004578} 08/31/2021 07:29:18 - INFO - __main__ - Step 101107: {'lr': 0.00012298638745822488, 'samples': 19412544, 'steps': 101106, 'loss/train': 0.811130702495575} 08/31/2021 07:29:18 - INFO - __main__ - Step 101108: {'lr': 0.0001229818166555118, 'samples': 19412736, 'steps': 101107, 'loss/train': 2.7078635692596436} 08/31/2021 07:29:20 - INFO - __main__ - Step 101109: {'lr': 0.0001229772459100312, 'samples': 19412928, 'steps': 101108, 'loss/train': 2.7323789596557617} 08/31/2021 07:29:21 - INFO - __main__ - Step 101110: {'lr': 0.00012297267522178512, 'samples': 19413120, 'steps': 101109, 'loss/train': 0.8182257413864136} 08/31/2021 07:29:21 - INFO - __main__ - Step 101111: {'lr': 0.0001229681045907755, 'samples': 19413312, 'steps': 101110, 'loss/train': 0.8599892258644104} 08/31/2021 07:29:21 - INFO - __main__ - Step 101112: {'lr': 0.00012296353401700452, 'samples': 19413504, 'steps': 101111, 'loss/train': 1.177427887916565} 08/31/2021 07:29:22 - INFO - __main__ - Step 101113: {'lr': 0.00012295896350047423, 'samples': 19413696, 'steps': 101112, 'loss/train': 1.5501954555511475} 08/31/2021 07:29:24 - INFO - __main__ - Step 101114: {'lr': 0.00012295439304118664, 'samples': 19413888, 'steps': 101113, 'loss/train': 1.6124167442321777} 08/31/2021 07:29:24 - INFO - __main__ - Step 101115: {'lr': 0.00012294982263914383, 'samples': 19414080, 'steps': 101114, 'loss/train': 1.662298560142517} 08/31/2021 07:29:24 - INFO - __main__ - Step 101116: {'lr': 0.00012294525229434788, 'samples': 19414272, 'steps': 101115, 'loss/train': 1.5556106567382812} 08/31/2021 07:29:25 - INFO - __main__ - Step 101117: {'lr': 0.00012294068200680087, 'samples': 19414464, 'steps': 101116, 'loss/train': 0.48683154582977295} 08/31/2021 07:29:25 - INFO - __main__ - Step 101118: {'lr': 0.0001229361117765048, 'samples': 19414656, 'steps': 101117, 'loss/train': 1.047224521636963} 08/31/2021 07:29:27 - INFO - __main__ - Step 101119: {'lr': 0.00012293154160346174, 'samples': 19414848, 'steps': 101118, 'loss/train': 1.7093240022659302} 08/31/2021 07:29:27 - INFO - __main__ - Step 101120: {'lr': 0.0001229269714876738, 'samples': 19415040, 'steps': 101119, 'loss/train': 0.9180815815925598} 08/31/2021 07:29:27 - INFO - __main__ - Step 101121: {'lr': 0.000122922401429143, 'samples': 19415232, 'steps': 101120, 'loss/train': 1.0674833059310913} 08/31/2021 07:29:28 - INFO - __main__ - Step 101122: {'lr': 0.00012291783142787138, 'samples': 19415424, 'steps': 101121, 'loss/train': 0.6338594555854797} 08/31/2021 07:29:28 - INFO - __main__ - Step 101123: {'lr': 0.00012291326148386114, 'samples': 19415616, 'steps': 101122, 'loss/train': 0.7017533779144287} 08/31/2021 07:29:30 - INFO - __main__ - Step 101124: {'lr': 0.00012290869159711413, 'samples': 19415808, 'steps': 101123, 'loss/train': 1.4236592054367065} 08/31/2021 07:29:30 - INFO - __main__ - Step 101125: {'lr': 0.0001229041217676325, 'samples': 19416000, 'steps': 101124, 'loss/train': 1.5890883207321167} 08/31/2021 07:29:30 - INFO - __main__ - Step 101126: {'lr': 0.0001228995519954183, 'samples': 19416192, 'steps': 101125, 'loss/train': 1.6158771514892578} 08/31/2021 07:29:31 - INFO - __main__ - Step 101127: {'lr': 0.00012289498228047361, 'samples': 19416384, 'steps': 101126, 'loss/train': 1.0000274181365967} 08/31/2021 07:29:31 - INFO - __main__ - Step 101128: {'lr': 0.00012289041262280047, 'samples': 19416576, 'steps': 101127, 'loss/train': 1.6521092653274536} 08/31/2021 07:29:31 - INFO - __main__ - Step 101129: {'lr': 0.00012288584302240098, 'samples': 19416768, 'steps': 101128, 'loss/train': 0.7422467470169067} 08/31/2021 07:29:34 - INFO - __main__ - Step 101130: {'lr': 0.00012288127347927712, 'samples': 19416960, 'steps': 101129, 'loss/train': 0.8737890124320984} 08/31/2021 07:29:34 - INFO - __main__ - Step 101131: {'lr': 0.00012287670399343102, 'samples': 19417152, 'steps': 101130, 'loss/train': 0.16181538999080658} 08/31/2021 07:29:34 - INFO - __main__ - Step 101132: {'lr': 0.0001228721345648647, 'samples': 19417344, 'steps': 101131, 'loss/train': 1.5083502531051636} 08/31/2021 07:29:35 - INFO - __main__ - Step 101133: {'lr': 0.00012286756519358028, 'samples': 19417536, 'steps': 101132, 'loss/train': 1.2231305837631226} 08/31/2021 07:29:35 - INFO - __main__ - Step 101134: {'lr': 0.00012286299587957973, 'samples': 19417728, 'steps': 101133, 'loss/train': 0.9664493799209595} 08/31/2021 07:29:37 - INFO - __main__ - Step 101135: {'lr': 0.00012285842662286518, 'samples': 19417920, 'steps': 101134, 'loss/train': 1.0324015617370605} 08/31/2021 07:29:37 - INFO - __main__ - Step 101136: {'lr': 0.00012285385742343875, 'samples': 19418112, 'steps': 101135, 'loss/train': 1.1901581287384033} 08/31/2021 07:29:37 - INFO - __main__ - Step 101137: {'lr': 0.0001228492882813023, 'samples': 19418304, 'steps': 101136, 'loss/train': 1.3502144813537598} 08/31/2021 07:29:38 - INFO - __main__ - Step 101138: {'lr': 0.000122844719196458, 'samples': 19418496, 'steps': 101137, 'loss/train': 0.8902196884155273} 08/31/2021 07:29:39 - INFO - __main__ - Step 101139: {'lr': 0.0001228401501689079, 'samples': 19418688, 'steps': 101138, 'loss/train': 0.35307061672210693} 08/31/2021 07:29:40 - INFO - __main__ - Step 101140: {'lr': 0.0001228355811986541, 'samples': 19418880, 'steps': 101139, 'loss/train': 1.1260689496994019} 08/31/2021 07:29:40 - INFO - __main__ - Step 101141: {'lr': 0.00012283101228569859, 'samples': 19419072, 'steps': 101140, 'loss/train': 1.1501625776290894} 08/31/2021 07:29:40 - INFO - __main__ - Step 101142: {'lr': 0.00012282644343004348, 'samples': 19419264, 'steps': 101141, 'loss/train': 0.9527280330657959} 08/31/2021 07:29:41 - INFO - __main__ - Step 101143: {'lr': 0.0001228218746316908, 'samples': 19419456, 'steps': 101142, 'loss/train': 1.325979232788086} 08/31/2021 07:29:42 - INFO - __main__ - Step 101144: {'lr': 0.00012281730589064262, 'samples': 19419648, 'steps': 101143, 'loss/train': 0.9690097570419312} 08/31/2021 07:29:43 - INFO - __main__ - Step 101145: {'lr': 0.00012281273720690102, 'samples': 19419840, 'steps': 101144, 'loss/train': 0.826564610004425} 08/31/2021 07:29:43 - INFO - __main__ - Step 101146: {'lr': 0.00012280816858046802, 'samples': 19420032, 'steps': 101145, 'loss/train': 1.4154269695281982} 08/31/2021 07:29:43 - INFO - __main__ - Step 101147: {'lr': 0.00012280360001134573, 'samples': 19420224, 'steps': 101146, 'loss/train': 0.5699229836463928} 08/31/2021 07:29:44 - INFO - __main__ - Step 101148: {'lr': 0.00012279903149953615, 'samples': 19420416, 'steps': 101147, 'loss/train': 1.0847053527832031} 08/31/2021 07:29:44 - INFO - __main__ - Step 101149: {'lr': 0.00012279446304504135, 'samples': 19420608, 'steps': 101148, 'loss/train': 1.7760357856750488} 08/31/2021 07:29:46 - INFO - __main__ - Step 101150: {'lr': 0.00012278989464786352, 'samples': 19420800, 'steps': 101149, 'loss/train': 1.5024688243865967} 08/31/2021 07:29:46 - INFO - __main__ - Step 101151: {'lr': 0.00012278532630800447, 'samples': 19420992, 'steps': 101150, 'loss/train': 1.5158641338348389} 08/31/2021 07:29:47 - INFO - __main__ - Step 101152: {'lr': 0.00012278075802546647, 'samples': 19421184, 'steps': 101151, 'loss/train': 1.236954689025879} 08/31/2021 07:29:47 - INFO - __main__ - Step 101153: {'lr': 0.0001227761898002514, 'samples': 19421376, 'steps': 101152, 'loss/train': 1.195316195487976} 08/31/2021 07:29:47 - INFO - __main__ - Step 101154: {'lr': 0.00012277162163236148, 'samples': 19421568, 'steps': 101153, 'loss/train': 0.6355584859848022} 08/31/2021 07:29:49 - INFO - __main__ - Step 101155: {'lr': 0.00012276705352179867, 'samples': 19421760, 'steps': 101154, 'loss/train': 0.45281538367271423} 08/31/2021 07:29:50 - INFO - __main__ - Step 101156: {'lr': 0.0001227624854685651, 'samples': 19421952, 'steps': 101155, 'loss/train': 1.3216010332107544} 08/31/2021 07:29:50 - INFO - __main__ - Step 101157: {'lr': 0.00012275791747266273, 'samples': 19422144, 'steps': 101156, 'loss/train': 0.6759527325630188} 08/31/2021 07:29:50 - INFO - __main__ - Step 101158: {'lr': 0.00012275334953409372, 'samples': 19422336, 'steps': 101157, 'loss/train': 0.9977884292602539} 08/31/2021 07:29:51 - INFO - __main__ - Step 101159: {'lr': 0.0001227487816528601, 'samples': 19422528, 'steps': 101158, 'loss/train': 2.5206778049468994} 08/31/2021 07:29:51 - INFO - __main__ - Step 101160: {'lr': 0.00012274421382896388, 'samples': 19422720, 'steps': 101159, 'loss/train': 1.7960909605026245} 08/31/2021 07:29:53 - INFO - __main__ - Step 101161: {'lr': 0.00012273964606240718, 'samples': 19422912, 'steps': 101160, 'loss/train': 0.44675537943840027} 08/31/2021 07:29:54 - INFO - __main__ - Step 101162: {'lr': 0.00012273507835319203, 'samples': 19423104, 'steps': 101161, 'loss/train': 1.2263199090957642} 08/31/2021 07:29:54 - INFO - __main__ - Step 101163: {'lr': 0.00012273051070132057, 'samples': 19423296, 'steps': 101162, 'loss/train': 1.2680723667144775} 08/31/2021 07:29:54 - INFO - __main__ - Step 101164: {'lr': 0.0001227259431067947, 'samples': 19423488, 'steps': 101163, 'loss/train': 0.7783894538879395} 08/31/2021 07:29:55 - INFO - __main__ - Step 101165: {'lr': 0.00012272137556961654, 'samples': 19423680, 'steps': 101164, 'loss/train': 0.6668043732643127} 08/31/2021 07:29:56 - INFO - __main__ - Step 101166: {'lr': 0.00012271680808978815, 'samples': 19423872, 'steps': 101165, 'loss/train': 1.298357367515564} 08/31/2021 07:29:57 - INFO - __main__ - Step 101167: {'lr': 0.00012271224066731163, 'samples': 19424064, 'steps': 101166, 'loss/train': 1.6299405097961426} 08/31/2021 07:29:57 - INFO - __main__ - Step 101168: {'lr': 0.00012270767330218902, 'samples': 19424256, 'steps': 101167, 'loss/train': 1.3337390422821045} 08/31/2021 07:29:57 - INFO - __main__ - Step 101169: {'lr': 0.00012270310599442233, 'samples': 19424448, 'steps': 101168, 'loss/train': 1.8946843147277832} 08/31/2021 07:29:58 - INFO - __main__ - Step 101170: {'lr': 0.00012269853874401367, 'samples': 19424640, 'steps': 101169, 'loss/train': 1.5816361904144287} 08/31/2021 07:29:59 - INFO - __main__ - Step 101171: {'lr': 0.00012269397155096508, 'samples': 19424832, 'steps': 101170, 'loss/train': 1.7842049598693848} 08/31/2021 07:30:00 - INFO - __main__ - Step 101172: {'lr': 0.00012268940441527865, 'samples': 19425024, 'steps': 101171, 'loss/train': 0.9957925081253052} 08/31/2021 07:30:00 - INFO - __main__ - Step 101173: {'lr': 0.0001226848373369564, 'samples': 19425216, 'steps': 101172, 'loss/train': 0.46110448241233826} 08/31/2021 07:30:00 - INFO - __main__ - Step 101174: {'lr': 0.00012268027031600036, 'samples': 19425408, 'steps': 101173, 'loss/train': 1.3438169956207275} 08/31/2021 07:30:01 - INFO - __main__ - Step 101175: {'lr': 0.00012267570335241268, 'samples': 19425600, 'steps': 101174, 'loss/train': 1.1768605709075928} 08/31/2021 07:30:02 - INFO - __main__ - Step 101176: {'lr': 0.00012267113644619536, 'samples': 19425792, 'steps': 101175, 'loss/train': 1.6990028619766235} 08/31/2021 07:30:03 - INFO - __main__ - Step 101177: {'lr': 0.0001226665695973505, 'samples': 19425984, 'steps': 101176, 'loss/train': 1.3909077644348145} 08/31/2021 07:30:03 - INFO - __main__ - Step 101178: {'lr': 0.0001226620028058801, 'samples': 19426176, 'steps': 101177, 'loss/train': 0.08403807133436203} 08/31/2021 07:30:03 - INFO - __main__ - Step 101179: {'lr': 0.00012265743607178616, 'samples': 19426368, 'steps': 101178, 'loss/train': 1.341868281364441} 08/31/2021 07:30:04 - INFO - __main__ - Step 101180: {'lr': 0.00012265286939507086, 'samples': 19426560, 'steps': 101179, 'loss/train': 0.9096772074699402} 08/31/2021 07:30:05 - INFO - __main__ - Step 101181: {'lr': 0.00012264830277573623, 'samples': 19426752, 'steps': 101180, 'loss/train': 0.9521566033363342} 08/31/2021 07:30:06 - INFO - __main__ - Step 101182: {'lr': 0.00012264373621378424, 'samples': 19426944, 'steps': 101181, 'loss/train': 0.8301417827606201} 08/31/2021 07:30:06 - INFO - __main__ - Step 101183: {'lr': 0.00012263916970921707, 'samples': 19427136, 'steps': 101182, 'loss/train': 1.4685180187225342} 08/31/2021 07:30:07 - INFO - __main__ - Step 101184: {'lr': 0.0001226346032620367, 'samples': 19427328, 'steps': 101183, 'loss/train': 1.2202767133712769} 08/31/2021 07:30:07 - INFO - __main__ - Step 101185: {'lr': 0.00012263003687224526, 'samples': 19427520, 'steps': 101184, 'loss/train': 0.996803343296051} 08/31/2021 07:30:09 - INFO - __main__ - Step 101186: {'lr': 0.0001226254705398447, 'samples': 19427712, 'steps': 101185, 'loss/train': 0.2753470242023468} 08/31/2021 07:30:09 - INFO - __main__ - Step 101187: {'lr': 0.00012262090426483718, 'samples': 19427904, 'steps': 101186, 'loss/train': 0.9174317121505737} 08/31/2021 07:30:09 - INFO - __main__ - Step 101188: {'lr': 0.0001226163380472247, 'samples': 19428096, 'steps': 101187, 'loss/train': 1.5633236169815063} 08/31/2021 07:30:10 - INFO - __main__ - Step 101189: {'lr': 0.00012261177188700932, 'samples': 19428288, 'steps': 101188, 'loss/train': 1.408023715019226} 08/31/2021 07:30:10 - INFO - __main__ - Step 101190: {'lr': 0.0001226072057841932, 'samples': 19428480, 'steps': 101189, 'loss/train': 0.914196789264679} 08/31/2021 07:30:10 - INFO - __main__ - Step 101191: {'lr': 0.00012260263973877826, 'samples': 19428672, 'steps': 101190, 'loss/train': 1.7171396017074585} 08/31/2021 07:30:12 - INFO - __main__ - Step 101192: {'lr': 0.00012259807375076656, 'samples': 19428864, 'steps': 101191, 'loss/train': 0.38681724667549133} 08/31/2021 07:30:13 - INFO - __main__ - Step 101193: {'lr': 0.00012259350782016021, 'samples': 19429056, 'steps': 101192, 'loss/train': 1.3290035724639893} 08/31/2021 07:30:13 - INFO - __main__ - Step 101194: {'lr': 0.00012258894194696127, 'samples': 19429248, 'steps': 101193, 'loss/train': 0.40362924337387085} 08/31/2021 07:30:13 - INFO - __main__ - Step 101195: {'lr': 0.0001225843761311718, 'samples': 19429440, 'steps': 101194, 'loss/train': 1.1312536001205444} 08/31/2021 07:30:14 - INFO - __main__ - Step 101196: {'lr': 0.00012257981037279382, 'samples': 19429632, 'steps': 101195, 'loss/train': 0.8713805079460144} 08/31/2021 07:30:15 - INFO - __main__ - Step 101197: {'lr': 0.0001225752446718294, 'samples': 19429824, 'steps': 101196, 'loss/train': 1.4401203393936157} 08/31/2021 07:30:16 - INFO - __main__ - Step 101198: {'lr': 0.0001225706790282806, 'samples': 19430016, 'steps': 101197, 'loss/train': 1.0894865989685059} 08/31/2021 07:30:16 - INFO - __main__ - Step 101199: {'lr': 0.00012256611344214956, 'samples': 19430208, 'steps': 101198, 'loss/train': 0.8663557171821594} 08/31/2021 07:30:16 - INFO - __main__ - Step 101200: {'lr': 0.00012256154791343818, 'samples': 19430400, 'steps': 101199, 'loss/train': 0.9273255467414856} 08/31/2021 07:30:17 - INFO - __main__ - Step 101201: {'lr': 0.00012255698244214864, 'samples': 19430592, 'steps': 101200, 'loss/train': 0.885271430015564} 08/31/2021 07:30:18 - INFO - __main__ - Step 101202: {'lr': 0.00012255241702828295, 'samples': 19430784, 'steps': 101201, 'loss/train': 0.25002485513687134} 08/31/2021 07:30:19 - INFO - __main__ - Step 101203: {'lr': 0.0001225478516718432, 'samples': 19430976, 'steps': 101202, 'loss/train': 0.7602146863937378} 08/31/2021 07:30:19 - INFO - __main__ - Step 101204: {'lr': 0.00012254328637283148, 'samples': 19431168, 'steps': 101203, 'loss/train': 0.2820691764354706} 08/31/2021 07:30:19 - INFO - __main__ - Step 101205: {'lr': 0.0001225387211312497, 'samples': 19431360, 'steps': 101204, 'loss/train': 1.4644520282745361} 08/31/2021 07:30:20 - INFO - __main__ - Step 101206: {'lr': 0.0001225341559471, 'samples': 19431552, 'steps': 101205, 'loss/train': 0.9752139449119568} 08/31/2021 07:30:21 - INFO - __main__ - Step 101207: {'lr': 0.00012252959082038444, 'samples': 19431744, 'steps': 101206, 'loss/train': 1.364993691444397} 08/31/2021 07:30:22 - INFO - __main__ - Step 101208: {'lr': 0.00012252502575110512, 'samples': 19431936, 'steps': 101207, 'loss/train': 0.9309571385383606} 08/31/2021 07:30:22 - INFO - __main__ - Step 101209: {'lr': 0.000122520460739264, 'samples': 19432128, 'steps': 101208, 'loss/train': 0.8780586123466492} 08/31/2021 07:30:23 - INFO - __main__ - Step 101210: {'lr': 0.0001225158957848632, 'samples': 19432320, 'steps': 101209, 'loss/train': 2.0875589847564697} 08/31/2021 07:30:23 - INFO - __main__ - Step 101211: {'lr': 0.0001225113308879048, 'samples': 19432512, 'steps': 101210, 'loss/train': 1.5581449270248413} 08/31/2021 07:30:24 - INFO - __main__ - Step 101212: {'lr': 0.00012250676604839083, 'samples': 19432704, 'steps': 101211, 'loss/train': 1.27802574634552} 08/31/2021 07:30:25 - INFO - __main__ - Step 101213: {'lr': 0.00012250220126632332, 'samples': 19432896, 'steps': 101212, 'loss/train': 0.6200952529907227} 08/31/2021 07:30:25 - INFO - __main__ - Step 101214: {'lr': 0.00012249763654170436, 'samples': 19433088, 'steps': 101213, 'loss/train': 0.7023029327392578} 08/31/2021 07:30:26 - INFO - __main__ - Step 101215: {'lr': 0.00012249307187453605, 'samples': 19433280, 'steps': 101214, 'loss/train': 0.9094130992889404} 08/31/2021 07:30:26 - INFO - __main__ - Step 101216: {'lr': 0.00012248850726482034, 'samples': 19433472, 'steps': 101215, 'loss/train': 1.2047889232635498} 08/31/2021 07:30:28 - INFO - __main__ - Step 101217: {'lr': 0.0001224839427125594, 'samples': 19433664, 'steps': 101216, 'loss/train': 1.4915590286254883} 08/31/2021 07:30:28 - INFO - __main__ - Step 101218: {'lr': 0.0001224793782177552, 'samples': 19433856, 'steps': 101217, 'loss/train': 1.5063891410827637} 08/31/2021 07:30:29 - INFO - __main__ - Step 101219: {'lr': 0.00012247481378040978, 'samples': 19434048, 'steps': 101218, 'loss/train': 1.1771984100341797} 08/31/2021 07:30:29 - INFO - __main__ - Step 101220: {'lr': 0.00012247024940052525, 'samples': 19434240, 'steps': 101219, 'loss/train': 1.1870847940444946} 08/31/2021 07:30:29 - INFO - __main__ - Step 101221: {'lr': 0.0001224656850781037, 'samples': 19434432, 'steps': 101220, 'loss/train': 0.9396051168441772} 08/31/2021 07:30:30 - INFO - __main__ - Step 101222: {'lr': 0.0001224611208131471, 'samples': 19434624, 'steps': 101221, 'loss/train': 1.0770277976989746} 08/31/2021 07:30:31 - INFO - __main__ - Step 101223: {'lr': 0.00012245655660565754, 'samples': 19434816, 'steps': 101222, 'loss/train': 0.9647417068481445} 08/31/2021 07:30:32 - INFO - __main__ - Step 101224: {'lr': 0.00012245199245563713, 'samples': 19435008, 'steps': 101223, 'loss/train': 1.5083231925964355} 08/31/2021 07:30:32 - INFO - __main__ - Step 101225: {'lr': 0.00012244742836308787, 'samples': 19435200, 'steps': 101224, 'loss/train': 1.1088796854019165} 08/31/2021 07:30:33 - INFO - __main__ - Step 101226: {'lr': 0.00012244286432801184, 'samples': 19435392, 'steps': 101225, 'loss/train': 1.3645037412643433} 08/31/2021 07:30:33 - INFO - __main__ - Step 101227: {'lr': 0.00012243830035041104, 'samples': 19435584, 'steps': 101226, 'loss/train': 1.5164635181427002} 08/31/2021 07:30:34 - INFO - __main__ - Step 101228: {'lr': 0.0001224337364302876, 'samples': 19435776, 'steps': 101227, 'loss/train': 1.2424079179763794} 08/31/2021 07:30:35 - INFO - __main__ - Step 101229: {'lr': 0.00012242917256764354, 'samples': 19435968, 'steps': 101228, 'loss/train': 1.0052980184555054} 08/31/2021 07:30:35 - INFO - __main__ - Step 101230: {'lr': 0.00012242460876248095, 'samples': 19436160, 'steps': 101229, 'loss/train': 1.3354990482330322} 08/31/2021 07:30:35 - INFO - __main__ - Step 101231: {'lr': 0.00012242004501480198, 'samples': 19436352, 'steps': 101230, 'loss/train': 1.1600927114486694} 08/31/2021 07:30:36 - INFO - __main__ - Step 101232: {'lr': 0.0001224154813246084, 'samples': 19436544, 'steps': 101231, 'loss/train': 1.4511252641677856} 08/31/2021 07:30:37 - INFO - __main__ - Step 101233: {'lr': 0.0001224109176919025, 'samples': 19436736, 'steps': 101232, 'loss/train': 1.1148539781570435} 08/31/2021 07:30:38 - INFO - __main__ - Step 101234: {'lr': 0.00012240635411668623, 'samples': 19436928, 'steps': 101233, 'loss/train': 1.0495017766952515} 08/31/2021 07:30:38 - INFO - __main__ - Step 101235: {'lr': 0.00012240179059896171, 'samples': 19437120, 'steps': 101234, 'loss/train': 1.4920082092285156} 08/31/2021 07:30:39 - INFO - __main__ - Step 101236: {'lr': 0.000122397227138731, 'samples': 19437312, 'steps': 101235, 'loss/train': 0.746233344078064} 08/31/2021 07:30:39 - INFO - __main__ - Step 101237: {'lr': 0.00012239266373599607, 'samples': 19437504, 'steps': 101236, 'loss/train': 0.9501714706420898} 08/31/2021 07:30:40 - INFO - __main__ - Step 101238: {'lr': 0.0001223881003907591, 'samples': 19437696, 'steps': 101237, 'loss/train': 0.5478942394256592} 08/31/2021 07:30:41 - INFO - __main__ - Step 101239: {'lr': 0.00012238353710302202, 'samples': 19437888, 'steps': 101238, 'loss/train': 1.4532233476638794} 08/31/2021 07:30:41 - INFO - __main__ - Step 101240: {'lr': 0.000122378973872787, 'samples': 19438080, 'steps': 101239, 'loss/train': 0.43660998344421387} 08/31/2021 07:30:42 - INFO - __main__ - Step 101241: {'lr': 0.00012237441070005604, 'samples': 19438272, 'steps': 101240, 'loss/train': 1.2687056064605713} 08/31/2021 07:30:42 - INFO - __main__ - Step 101242: {'lr': 0.00012236984758483117, 'samples': 19438464, 'steps': 101241, 'loss/train': 0.1434238702058792} 08/31/2021 07:30:42 - INFO - __main__ - Step 101243: {'lr': 0.00012236528452711447, 'samples': 19438656, 'steps': 101242, 'loss/train': 1.187946081161499} 08/31/2021 07:30:44 - INFO - __main__ - Step 101244: {'lr': 0.00012236072152690814, 'samples': 19438848, 'steps': 101243, 'loss/train': 0.6088303327560425} 08/31/2021 07:30:45 - INFO - __main__ - Step 101245: {'lr': 0.000122356158584214, 'samples': 19439040, 'steps': 101244, 'loss/train': 0.7937678098678589} 08/31/2021 07:30:45 - INFO - __main__ - Step 101246: {'lr': 0.00012235159569903416, 'samples': 19439232, 'steps': 101245, 'loss/train': 1.0582844018936157} 08/31/2021 07:30:45 - INFO - __main__ - Step 101247: {'lr': 0.00012234703287137077, 'samples': 19439424, 'steps': 101246, 'loss/train': 0.12084166705608368} 08/31/2021 07:30:46 - INFO - __main__ - Step 101248: {'lr': 0.00012234247010122583, 'samples': 19439616, 'steps': 101247, 'loss/train': 1.1909563541412354} 08/31/2021 07:30:47 - INFO - __main__ - Step 101249: {'lr': 0.0001223379073886014, 'samples': 19439808, 'steps': 101248, 'loss/train': 1.2456660270690918} 08/31/2021 07:30:48 - INFO - __main__ - Step 101250: {'lr': 0.00012233334473349953, 'samples': 19440000, 'steps': 101249, 'loss/train': 1.1606230735778809} 08/31/2021 07:30:48 - INFO - __main__ - Step 101251: {'lr': 0.00012232878213592227, 'samples': 19440192, 'steps': 101250, 'loss/train': 1.151384711265564} 08/31/2021 07:30:48 - INFO - __main__ - Step 101252: {'lr': 0.0001223242195958717, 'samples': 19440384, 'steps': 101251, 'loss/train': 1.442710518836975} 08/31/2021 07:30:49 - INFO - __main__ - Step 101253: {'lr': 0.0001223196571133499, 'samples': 19440576, 'steps': 101252, 'loss/train': 0.8536520004272461} 08/31/2021 07:30:50 - INFO - __main__ - Step 101254: {'lr': 0.00012231509468835886, 'samples': 19440768, 'steps': 101253, 'loss/train': 1.3621952533721924} 08/31/2021 07:30:51 - INFO - __main__ - Step 101255: {'lr': 0.00012231053232090067, 'samples': 19440960, 'steps': 101254, 'loss/train': 0.7737142443656921} 08/31/2021 07:30:51 - INFO - __main__ - Step 101256: {'lr': 0.00012230597001097737, 'samples': 19441152, 'steps': 101255, 'loss/train': 1.2122604846954346} 08/31/2021 07:30:51 - INFO - __main__ - Step 101257: {'lr': 0.00012230140775859117, 'samples': 19441344, 'steps': 101256, 'loss/train': 1.0660163164138794} 08/31/2021 07:30:52 - INFO - __main__ - Step 101258: {'lr': 0.00012229684556374384, 'samples': 19441536, 'steps': 101257, 'loss/train': 1.7831530570983887} 08/31/2021 07:30:53 - INFO - __main__ - Step 101259: {'lr': 0.00012229228342643762, 'samples': 19441728, 'steps': 101258, 'loss/train': 1.3647229671478271} 08/31/2021 07:30:54 - INFO - __main__ - Step 101260: {'lr': 0.0001222877213466745, 'samples': 19441920, 'steps': 101259, 'loss/train': 0.30038100481033325} 08/31/2021 07:30:54 - INFO - __main__ - Step 101261: {'lr': 0.0001222831593244566, 'samples': 19442112, 'steps': 101260, 'loss/train': 0.6503936052322388} 08/31/2021 07:30:54 - INFO - __main__ - Step 101262: {'lr': 0.00012227859735978587, 'samples': 19442304, 'steps': 101261, 'loss/train': 0.6862180233001709} 08/31/2021 07:30:55 - INFO - __main__ - Step 101263: {'lr': 0.0001222740354526645, 'samples': 19442496, 'steps': 101262, 'loss/train': 0.6589425206184387} 08/31/2021 07:30:56 - INFO - __main__ - Step 101264: {'lr': 0.00012226947360309442, 'samples': 19442688, 'steps': 101263, 'loss/train': 0.6576816439628601} 08/31/2021 07:30:57 - INFO - __main__ - Step 101265: {'lr': 0.0001222649118110778, 'samples': 19442880, 'steps': 101264, 'loss/train': 1.1408530473709106} 08/31/2021 07:30:57 - INFO - __main__ - Step 101266: {'lr': 0.0001222603500766166, 'samples': 19443072, 'steps': 101265, 'loss/train': 0.4011925458908081} 08/31/2021 07:30:57 - INFO - __main__ - Step 101267: {'lr': 0.00012225578839971293, 'samples': 19443264, 'steps': 101266, 'loss/train': 0.2619223892688751} 08/31/2021 07:30:58 - INFO - __main__ - Step 101268: {'lr': 0.00012225122678036885, 'samples': 19443456, 'steps': 101267, 'loss/train': 1.1563005447387695} 08/31/2021 07:31:00 - INFO - __main__ - Step 101269: {'lr': 0.00012224666521858636, 'samples': 19443648, 'steps': 101268, 'loss/train': 1.1731139421463013} 08/31/2021 07:31:00 - INFO - __main__ - Step 101270: {'lr': 0.00012224210371436755, 'samples': 19443840, 'steps': 101269, 'loss/train': 0.49811235070228577} 08/31/2021 07:31:01 - INFO - __main__ - Step 101271: {'lr': 0.00012223754226771462, 'samples': 19444032, 'steps': 101270, 'loss/train': 1.2277352809906006} 08/31/2021 07:31:01 - INFO - __main__ - Step 101272: {'lr': 0.00012223298087862936, 'samples': 19444224, 'steps': 101271, 'loss/train': 0.9179261922836304} 08/31/2021 07:31:01 - INFO - __main__ - Step 101273: {'lr': 0.00012222841954711395, 'samples': 19444416, 'steps': 101272, 'loss/train': 0.9762556552886963} 08/31/2021 07:31:02 - INFO - __main__ - Step 101274: {'lr': 0.00012222385827317041, 'samples': 19444608, 'steps': 101273, 'loss/train': 1.5897374153137207} 08/31/2021 07:31:03 - INFO - __main__ - Step 101275: {'lr': 0.00012221929705680086, 'samples': 19444800, 'steps': 101274, 'loss/train': 0.8509877324104309} 08/31/2021 07:31:04 - INFO - __main__ - Step 101276: {'lr': 0.00012221473589800732, 'samples': 19444992, 'steps': 101275, 'loss/train': 0.7243250608444214} 08/31/2021 07:31:04 - INFO - __main__ - Step 101277: {'lr': 0.00012221017479679182, 'samples': 19445184, 'steps': 101276, 'loss/train': 0.06131669506430626} 08/31/2021 07:31:05 - INFO - __main__ - Step 101278: {'lr': 0.0001222056137531565, 'samples': 19445376, 'steps': 101277, 'loss/train': 0.2583184838294983} 08/31/2021 07:31:05 - INFO - __main__ - Step 101279: {'lr': 0.00012220105276710333, 'samples': 19445568, 'steps': 101278, 'loss/train': 1.1096527576446533} 08/31/2021 07:31:06 - INFO - __main__ - Step 101280: {'lr': 0.0001221964918386344, 'samples': 19445760, 'steps': 101279, 'loss/train': 1.1560038328170776} 08/31/2021 07:31:07 - INFO - __main__ - Step 101281: {'lr': 0.0001221919309677517, 'samples': 19445952, 'steps': 101280, 'loss/train': 1.4265692234039307} 08/31/2021 07:31:07 - INFO - __main__ - Step 101282: {'lr': 0.0001221873701544574, 'samples': 19446144, 'steps': 101281, 'loss/train': 0.9284528493881226} 08/31/2021 07:31:08 - INFO - __main__ - Step 101283: {'lr': 0.0001221828093987535, 'samples': 19446336, 'steps': 101282, 'loss/train': 1.1360090970993042} 08/31/2021 07:31:08 - INFO - __main__ - Step 101284: {'lr': 0.00012217824870064216, 'samples': 19446528, 'steps': 101283, 'loss/train': 1.3780319690704346} 08/31/2021 07:31:08 - INFO - __main__ - Step 101285: {'lr': 0.0001221736880601252, 'samples': 19446720, 'steps': 101284, 'loss/train': 1.6678253412246704} 08/31/2021 07:31:10 - INFO - __main__ - Step 101286: {'lr': 0.00012216912747720483, 'samples': 19446912, 'steps': 101285, 'loss/train': 1.0666905641555786} 08/31/2021 07:31:10 - INFO - __main__ - Step 101287: {'lr': 0.00012216456695188306, 'samples': 19447104, 'steps': 101286, 'loss/train': 1.1109200716018677} 08/31/2021 07:31:11 - INFO - __main__ - Step 101288: {'lr': 0.00012216000648416199, 'samples': 19447296, 'steps': 101287, 'loss/train': 1.3430629968643188} 08/31/2021 07:31:11 - INFO - __main__ - Step 101289: {'lr': 0.0001221554460740436, 'samples': 19447488, 'steps': 101288, 'loss/train': 1.9337934255599976} 08/31/2021 07:31:11 - INFO - __main__ - Step 101290: {'lr': 0.00012215088572153002, 'samples': 19447680, 'steps': 101289, 'loss/train': 1.3810856342315674} 08/31/2021 07:31:13 - INFO - __main__ - Step 101291: {'lr': 0.0001221463254266233, 'samples': 19447872, 'steps': 101290, 'loss/train': 1.1727665662765503} 08/31/2021 07:31:13 - INFO - __main__ - Step 101292: {'lr': 0.00012214176518932543, 'samples': 19448064, 'steps': 101291, 'loss/train': 0.9889326095581055} 08/31/2021 07:31:14 - INFO - __main__ - Step 101293: {'lr': 0.00012213720500963855, 'samples': 19448256, 'steps': 101292, 'loss/train': 0.8196161985397339} 08/31/2021 07:31:14 - INFO - __main__ - Step 101294: {'lr': 0.00012213264488756466, 'samples': 19448448, 'steps': 101293, 'loss/train': 1.2873237133026123} 08/31/2021 07:31:14 - INFO - __main__ - Step 101295: {'lr': 0.0001221280848231058, 'samples': 19448640, 'steps': 101294, 'loss/train': 1.5838737487792969} 08/31/2021 07:31:16 - INFO - __main__ - Step 101296: {'lr': 0.00012212352481626407, 'samples': 19448832, 'steps': 101295, 'loss/train': 1.2500122785568237} 08/31/2021 07:31:16 - INFO - __main__ - Step 101297: {'lr': 0.00012211896486704151, 'samples': 19449024, 'steps': 101296, 'loss/train': 1.1488057374954224} 08/31/2021 07:31:17 - INFO - __main__ - Step 101298: {'lr': 0.00012211440497544027, 'samples': 19449216, 'steps': 101297, 'loss/train': 1.2831721305847168} 08/31/2021 07:31:17 - INFO - __main__ - Step 101299: {'lr': 0.0001221098451414622, 'samples': 19449408, 'steps': 101298, 'loss/train': 1.4089442491531372} 08/31/2021 07:31:17 - INFO - __main__ - Step 101300: {'lr': 0.00012210528536510948, 'samples': 19449600, 'steps': 101299, 'loss/train': 1.0165268182754517} 08/31/2021 07:31:19 - INFO - __main__ - Step 101301: {'lr': 0.0001221007256463841, 'samples': 19449792, 'steps': 101300, 'loss/train': 1.2791496515274048} 08/31/2021 07:31:20 - INFO - __main__ - Step 101302: {'lr': 0.0001220961659852882, 'samples': 19449984, 'steps': 101301, 'loss/train': 1.486127495765686} 08/31/2021 07:31:20 - INFO - __main__ - Step 101303: {'lr': 0.00012209160638182378, 'samples': 19450176, 'steps': 101302, 'loss/train': 1.4168143272399902} 08/31/2021 07:31:21 - INFO - __main__ - Step 101304: {'lr': 0.00012208704683599293, 'samples': 19450368, 'steps': 101303, 'loss/train': 1.0799517631530762} 08/31/2021 07:31:21 - INFO - __main__ - Step 101305: {'lr': 0.00012208248734779767, 'samples': 19450560, 'steps': 101304, 'loss/train': 1.62314772605896} 08/31/2021 07:31:23 - INFO - __main__ - Step 101306: {'lr': 0.00012207792791724004, 'samples': 19450752, 'steps': 101305, 'loss/train': 0.48025715351104736} 08/31/2021 07:31:24 - INFO - __main__ - Step 101307: {'lr': 0.00012207336854432217, 'samples': 19450944, 'steps': 101306, 'loss/train': 0.045035891234874725} 08/31/2021 07:31:24 - INFO - __main__ - Step 101308: {'lr': 0.00012206880922904603, 'samples': 19451136, 'steps': 101307, 'loss/train': 1.536628246307373} 08/31/2021 07:31:24 - INFO - __main__ - Step 101309: {'lr': 0.00012206424997141371, 'samples': 19451328, 'steps': 101308, 'loss/train': 1.5361418724060059} 08/31/2021 07:31:25 - INFO - __main__ - Step 101310: {'lr': 0.00012205969077142729, 'samples': 19451520, 'steps': 101309, 'loss/train': 0.8043996691703796} 08/31/2021 07:31:25 - INFO - __main__ - Step 101311: {'lr': 0.00012205513162908888, 'samples': 19451712, 'steps': 101310, 'loss/train': 1.1571457386016846} 08/31/2021 07:31:25 - INFO - __main__ - Step 101312: {'lr': 0.00012205057254440036, 'samples': 19451904, 'steps': 101311, 'loss/train': 2.6886494159698486} 08/31/2021 07:31:26 - INFO - __main__ - Step 101313: {'lr': 0.00012204601351736385, 'samples': 19452096, 'steps': 101312, 'loss/train': 2.7112700939178467} 08/31/2021 07:31:27 - INFO - __main__ - Step 101314: {'lr': 0.00012204145454798147, 'samples': 19452288, 'steps': 101313, 'loss/train': 1.8399022817611694} 08/31/2021 07:31:28 - INFO - __main__ - Step 101315: {'lr': 0.00012203689563625522, 'samples': 19452480, 'steps': 101314, 'loss/train': 1.1668068170547485} 08/31/2021 07:31:28 - INFO - __main__ - Step 101316: {'lr': 0.00012203233678218717, 'samples': 19452672, 'steps': 101315, 'loss/train': 1.2560397386550903} 08/31/2021 07:31:28 - INFO - __main__ - Step 101317: {'lr': 0.00012202777798577938, 'samples': 19452864, 'steps': 101316, 'loss/train': 1.4099085330963135} 08/31/2021 07:31:29 - INFO - __main__ - Step 101318: {'lr': 0.00012202321924703388, 'samples': 19453056, 'steps': 101317, 'loss/train': 1.491847038269043} 08/31/2021 07:31:30 - INFO - __main__ - Step 101319: {'lr': 0.00012201866056595279, 'samples': 19453248, 'steps': 101318, 'loss/train': 0.9706310629844666} 08/31/2021 07:31:31 - INFO - __main__ - Step 101320: {'lr': 0.00012201410194253806, 'samples': 19453440, 'steps': 101319, 'loss/train': 1.5874602794647217} 08/31/2021 07:31:31 - INFO - __main__ - Step 101321: {'lr': 0.00012200954337679185, 'samples': 19453632, 'steps': 101320, 'loss/train': 1.263085126876831} 08/31/2021 07:31:31 - INFO - __main__ - Step 101322: {'lr': 0.00012200498486871622, 'samples': 19453824, 'steps': 101321, 'loss/train': 1.2202476263046265} 08/31/2021 07:31:32 - INFO - __main__ - Step 101323: {'lr': 0.0001220004264183131, 'samples': 19454016, 'steps': 101322, 'loss/train': 1.0293388366699219} 08/31/2021 07:31:33 - INFO - __main__ - Step 101324: {'lr': 0.0001219958680255846, 'samples': 19454208, 'steps': 101323, 'loss/train': 0.782431960105896} 08/31/2021 07:31:34 - INFO - __main__ - Step 101325: {'lr': 0.0001219913096905328, 'samples': 19454400, 'steps': 101324, 'loss/train': 1.2267005443572998} 08/31/2021 07:31:34 - INFO - __main__ - Step 101326: {'lr': 0.0001219867514131597, 'samples': 19454592, 'steps': 101325, 'loss/train': 0.6287528872489929} 08/31/2021 07:31:34 - INFO - __main__ - Step 101327: {'lr': 0.00012198219319346743, 'samples': 19454784, 'steps': 101326, 'loss/train': 1.2707300186157227} 08/31/2021 07:31:35 - INFO - __main__ - Step 101328: {'lr': 0.000121977635031458, 'samples': 19454976, 'steps': 101327, 'loss/train': 1.5761637687683105} 08/31/2021 07:31:36 - INFO - __main__ - Step 101329: {'lr': 0.00012197307692713347, 'samples': 19455168, 'steps': 101328, 'loss/train': 1.0884796380996704} 08/31/2021 07:31:37 - INFO - __main__ - Step 101330: {'lr': 0.00012196851888049592, 'samples': 19455360, 'steps': 101329, 'loss/train': 1.303161859512329} 08/31/2021 07:31:37 - INFO - __main__ - Step 101331: {'lr': 0.00012196396089154734, 'samples': 19455552, 'steps': 101330, 'loss/train': 0.8257454633712769} 08/31/2021 07:31:38 - INFO - __main__ - Step 101332: {'lr': 0.00012195940296028984, 'samples': 19455744, 'steps': 101331, 'loss/train': 0.38467299938201904} 08/31/2021 07:31:38 - INFO - __main__ - Step 101333: {'lr': 0.00012195484508672558, 'samples': 19455936, 'steps': 101332, 'loss/train': 1.1860147714614868} 08/31/2021 07:31:39 - INFO - __main__ - Step 101334: {'lr': 0.00012195028727085636, 'samples': 19456128, 'steps': 101333, 'loss/train': 1.374892234802246} 08/31/2021 07:31:40 - INFO - __main__ - Step 101335: {'lr': 0.00012194572951268438, 'samples': 19456320, 'steps': 101334, 'loss/train': 0.9368864893913269} 08/31/2021 07:31:40 - INFO - __main__ - Step 101336: {'lr': 0.00012194117181221168, 'samples': 19456512, 'steps': 101335, 'loss/train': 1.7300047874450684} 08/31/2021 07:31:41 - INFO - __main__ - Step 101337: {'lr': 0.0001219366141694403, 'samples': 19456704, 'steps': 101336, 'loss/train': 1.176271677017212} 08/31/2021 07:31:41 - INFO - __main__ - Step 101338: {'lr': 0.00012193205658437232, 'samples': 19456896, 'steps': 101337, 'loss/train': 1.131476879119873} 08/31/2021 07:31:43 - INFO - __main__ - Step 101339: {'lr': 0.00012192749905700976, 'samples': 19457088, 'steps': 101338, 'loss/train': 2.3890063762664795} 08/31/2021 07:31:43 - INFO - __main__ - Step 101340: {'lr': 0.0001219229415873547, 'samples': 19457280, 'steps': 101339, 'loss/train': 1.1649458408355713} 08/31/2021 07:31:43 - INFO - __main__ - Step 101341: {'lr': 0.00012191838417540921, 'samples': 19457472, 'steps': 101340, 'loss/train': 1.3450897932052612} 08/31/2021 07:31:44 - INFO - __main__ - Step 101342: {'lr': 0.0001219138268211753, 'samples': 19457664, 'steps': 101341, 'loss/train': 1.6551501750946045} 08/31/2021 07:31:44 - INFO - __main__ - Step 101343: {'lr': 0.00012190926952465504, 'samples': 19457856, 'steps': 101342, 'loss/train': 1.1020373106002808} 08/31/2021 07:31:46 - INFO - __main__ - Step 101344: {'lr': 0.00012190471228585057, 'samples': 19458048, 'steps': 101343, 'loss/train': 1.273442029953003} 08/31/2021 07:31:46 - INFO - __main__ - Step 101345: {'lr': 0.0001219001551047638, 'samples': 19458240, 'steps': 101344, 'loss/train': 1.302808165550232} 08/31/2021 07:31:46 - INFO - __main__ - Step 101346: {'lr': 0.00012189559798139682, 'samples': 19458432, 'steps': 101345, 'loss/train': 1.208802580833435} 08/31/2021 07:31:47 - INFO - __main__ - Step 101347: {'lr': 0.0001218910409157517, 'samples': 19458624, 'steps': 101346, 'loss/train': 1.4496538639068604} 08/31/2021 07:31:47 - INFO - __main__ - Step 101348: {'lr': 0.00012188648390783049, 'samples': 19458816, 'steps': 101347, 'loss/train': 1.5218706130981445} 08/31/2021 07:31:49 - INFO - __main__ - Step 101349: {'lr': 0.00012188192695763528, 'samples': 19459008, 'steps': 101348, 'loss/train': 0.7686771154403687} 08/31/2021 07:31:49 - INFO - __main__ - Step 101350: {'lr': 0.00012187737006516811, 'samples': 19459200, 'steps': 101349, 'loss/train': 0.8962917327880859} 08/31/2021 07:31:49 - INFO - __main__ - Step 101351: {'lr': 0.00012187281323043098, 'samples': 19459392, 'steps': 101350, 'loss/train': 1.5603818893432617} 08/31/2021 07:31:50 - INFO - __main__ - Step 101352: {'lr': 0.000121868256453426, 'samples': 19459584, 'steps': 101351, 'loss/train': 1.7933205366134644} 08/31/2021 07:31:50 - INFO - __main__ - Step 101353: {'lr': 0.00012186369973415523, 'samples': 19459776, 'steps': 101352, 'loss/train': 1.4646782875061035} 08/31/2021 07:31:52 - INFO - __main__ - Step 101354: {'lr': 0.00012185914307262066, 'samples': 19459968, 'steps': 101353, 'loss/train': 1.9210889339447021} 08/31/2021 07:31:53 - INFO - __main__ - Step 101355: {'lr': 0.00012185458646882453, 'samples': 19460160, 'steps': 101354, 'loss/train': 1.0109187364578247} 08/31/2021 07:31:53 - INFO - __main__ - Step 101356: {'lr': 0.00012185002992276859, 'samples': 19460352, 'steps': 101355, 'loss/train': 1.4516024589538574} 08/31/2021 07:31:53 - INFO - __main__ - Step 101357: {'lr': 0.0001218454734344551, 'samples': 19460544, 'steps': 101356, 'loss/train': 1.2201099395751953} 08/31/2021 07:31:54 - INFO - __main__ - Step 101358: {'lr': 0.00012184091700388603, 'samples': 19460736, 'steps': 101357, 'loss/train': 0.7469978332519531} 08/31/2021 07:31:54 - INFO - __main__ - Step 101359: {'lr': 0.00012183636063106345, 'samples': 19460928, 'steps': 101358, 'loss/train': 1.061379075050354} 08/31/2021 07:31:56 - INFO - __main__ - Step 101360: {'lr': 0.00012183180431598947, 'samples': 19461120, 'steps': 101359, 'loss/train': 1.1787077188491821} 08/31/2021 07:31:56 - INFO - __main__ - Step 101361: {'lr': 0.00012182724805866607, 'samples': 19461312, 'steps': 101360, 'loss/train': 0.8259553909301758} 08/31/2021 07:31:57 - INFO - __main__ - Step 101362: {'lr': 0.00012182269185909536, 'samples': 19461504, 'steps': 101361, 'loss/train': 0.06989458203315735} 08/31/2021 07:31:57 - INFO - __main__ - Step 101363: {'lr': 0.00012181813571727937, 'samples': 19461696, 'steps': 101362, 'loss/train': 0.9465081691741943} 08/31/2021 07:31:57 - INFO - __main__ - Step 101364: {'lr': 0.00012181357963322012, 'samples': 19461888, 'steps': 101363, 'loss/train': 1.1104917526245117} 08/31/2021 07:31:58 - INFO - __main__ - Step 101365: {'lr': 0.00012180902360691982, 'samples': 19462080, 'steps': 101364, 'loss/train': 0.023060226812958717} 08/31/2021 07:31:59 - INFO - __main__ - Step 101366: {'lr': 0.00012180446763838026, 'samples': 19462272, 'steps': 101365, 'loss/train': 0.04946412146091461} 08/31/2021 07:32:00 - INFO - __main__ - Step 101367: {'lr': 0.00012179991172760366, 'samples': 19462464, 'steps': 101366, 'loss/train': 1.1019333600997925} 08/31/2021 07:32:00 - INFO - __main__ - Step 101368: {'lr': 0.00012179535587459204, 'samples': 19462656, 'steps': 101367, 'loss/train': 1.4800595045089722} 08/31/2021 07:32:00 - INFO - __main__ - Step 101369: {'lr': 0.00012179080007934746, 'samples': 19462848, 'steps': 101368, 'loss/train': 1.2707420587539673} 08/31/2021 07:32:01 - INFO - __main__ - Step 101370: {'lr': 0.00012178624434187193, 'samples': 19463040, 'steps': 101369, 'loss/train': 1.0212018489837646} 08/31/2021 07:32:02 - INFO - __main__ - Step 101371: {'lr': 0.00012178168866216757, 'samples': 19463232, 'steps': 101370, 'loss/train': 0.5502579212188721} 08/31/2021 07:32:03 - INFO - __main__ - Step 101372: {'lr': 0.0001217771330402364, 'samples': 19463424, 'steps': 101371, 'loss/train': 2.0762176513671875} 08/31/2021 07:32:03 - INFO - __main__ - Step 101373: {'lr': 0.00012177257747608048, 'samples': 19463616, 'steps': 101372, 'loss/train': 0.9138540625572205} 08/31/2021 07:32:03 - INFO - __main__ - Step 101374: {'lr': 0.00012176802196970186, 'samples': 19463808, 'steps': 101373, 'loss/train': 1.1078120470046997} 08/31/2021 07:32:04 - INFO - __main__ - Step 101375: {'lr': 0.00012176346652110257, 'samples': 19464000, 'steps': 101374, 'loss/train': 0.8589619994163513} 08/31/2021 07:32:05 - INFO - __main__ - Step 101376: {'lr': 0.0001217589111302847, 'samples': 19464192, 'steps': 101375, 'loss/train': 1.2294319868087769} 08/31/2021 07:32:06 - INFO - __main__ - Step 101377: {'lr': 0.00012175435579725028, 'samples': 19464384, 'steps': 101376, 'loss/train': 0.5916227102279663} 08/31/2021 07:32:06 - INFO - __main__ - Step 101378: {'lr': 0.00012174980052200146, 'samples': 19464576, 'steps': 101377, 'loss/train': 0.03489207103848457} 08/31/2021 07:32:07 - INFO - __main__ - Step 101379: {'lr': 0.00012174524530454012, 'samples': 19464768, 'steps': 101378, 'loss/train': 0.721900224685669} 08/31/2021 07:32:07 - INFO - __main__ - Step 101380: {'lr': 0.00012174069014486839, 'samples': 19464960, 'steps': 101379, 'loss/train': 1.3339579105377197} 08/31/2021 07:32:09 - INFO - __main__ - Step 101381: {'lr': 0.00012173613504298831, 'samples': 19465152, 'steps': 101380, 'loss/train': 1.4543073177337646} 08/31/2021 07:32:09 - INFO - __main__ - Step 101382: {'lr': 0.00012173157999890194, 'samples': 19465344, 'steps': 101381, 'loss/train': 1.1170014142990112} 08/31/2021 07:32:10 - INFO - __main__ - Step 101383: {'lr': 0.00012172702501261138, 'samples': 19465536, 'steps': 101382, 'loss/train': 0.6411260962486267} 08/31/2021 07:32:10 - INFO - __main__ - Step 101384: {'lr': 0.0001217224700841186, 'samples': 19465728, 'steps': 101383, 'loss/train': 0.08607368171215057} 08/31/2021 07:32:10 - INFO - __main__ - Step 101385: {'lr': 0.00012171791521342573, 'samples': 19465920, 'steps': 101384, 'loss/train': 1.259034514427185} 08/31/2021 07:32:11 - INFO - __main__ - Step 101386: {'lr': 0.00012171336040053477, 'samples': 19466112, 'steps': 101385, 'loss/train': 1.6233757734298706} 08/31/2021 07:32:12 - INFO - __main__ - Step 101387: {'lr': 0.00012170880564544778, 'samples': 19466304, 'steps': 101386, 'loss/train': 0.8699265718460083} 08/31/2021 07:32:13 - INFO - __main__ - Step 101388: {'lr': 0.00012170425094816687, 'samples': 19466496, 'steps': 101387, 'loss/train': 1.0410057306289673} 08/31/2021 07:32:13 - INFO - __main__ - Step 101389: {'lr': 0.00012169969630869399, 'samples': 19466688, 'steps': 101388, 'loss/train': 1.3235036134719849} 08/31/2021 07:32:13 - INFO - __main__ - Step 101390: {'lr': 0.00012169514172703128, 'samples': 19466880, 'steps': 101389, 'loss/train': 1.653022289276123} 08/31/2021 07:32:14 - INFO - __main__ - Step 101391: {'lr': 0.00012169058720318074, 'samples': 19467072, 'steps': 101390, 'loss/train': 1.1030998229980469} 08/31/2021 07:32:15 - INFO - __main__ - Step 101392: {'lr': 0.00012168603273714454, 'samples': 19467264, 'steps': 101391, 'loss/train': 1.021690011024475} 08/31/2021 07:32:16 - INFO - __main__ - Step 101393: {'lr': 0.00012168147832892457, 'samples': 19467456, 'steps': 101392, 'loss/train': 1.0007106065750122} 08/31/2021 07:32:16 - INFO - __main__ - Step 101394: {'lr': 0.0001216769239785229, 'samples': 19467648, 'steps': 101393, 'loss/train': 0.6496148705482483} 08/31/2021 07:32:16 - INFO - __main__ - Step 101395: {'lr': 0.00012167236968594165, 'samples': 19467840, 'steps': 101394, 'loss/train': 0.3947880268096924} 08/31/2021 07:32:17 - INFO - __main__ - Step 101396: {'lr': 0.00012166781545118286, 'samples': 19468032, 'steps': 101395, 'loss/train': 1.1031583547592163} 08/31/2021 07:32:18 - INFO - __main__ - Step 101397: {'lr': 0.00012166326127424854, 'samples': 19468224, 'steps': 101396, 'loss/train': 0.8801388740539551} 08/31/2021 07:32:19 - INFO - __main__ - Step 101398: {'lr': 0.00012165870715514079, 'samples': 19468416, 'steps': 101397, 'loss/train': 1.2554513216018677} 08/31/2021 07:32:19 - INFO - __main__ - Step 101399: {'lr': 0.00012165415309386166, 'samples': 19468608, 'steps': 101398, 'loss/train': 1.1365833282470703} 08/31/2021 07:32:19 - INFO - __main__ - Step 101400: {'lr': 0.00012164959909041318, 'samples': 19468800, 'steps': 101399, 'loss/train': 0.29728764295578003} 08/31/2021 07:32:20 - INFO - __main__ - Step 101401: {'lr': 0.00012164504514479741, 'samples': 19468992, 'steps': 101400, 'loss/train': 1.0587464570999146} 08/31/2021 07:32:21 - INFO - __main__ - Step 101402: {'lr': 0.0001216404912570164, 'samples': 19469184, 'steps': 101401, 'loss/train': 0.8088469505310059} 08/31/2021 07:32:22 - INFO - __main__ - Step 101403: {'lr': 0.00012163593742707222, 'samples': 19469376, 'steps': 101402, 'loss/train': 0.40226665139198303} 08/31/2021 07:32:22 - INFO - __main__ - Step 101404: {'lr': 0.00012163138365496687, 'samples': 19469568, 'steps': 101403, 'loss/train': 1.0924620628356934} 08/31/2021 07:32:23 - INFO - __main__ - Step 101405: {'lr': 0.00012162682994070257, 'samples': 19469760, 'steps': 101404, 'loss/train': 1.111368179321289} 08/31/2021 07:32:23 - INFO - __main__ - Step 101406: {'lr': 0.0001216222762842811, 'samples': 19469952, 'steps': 101405, 'loss/train': 1.3889946937561035} 08/31/2021 07:32:24 - INFO - __main__ - Step 101407: {'lr': 0.00012161772268570471, 'samples': 19470144, 'steps': 101406, 'loss/train': 1.4555531740188599} 08/31/2021 07:32:25 - INFO - __main__ - Step 101408: {'lr': 0.00012161316914497533, 'samples': 19470336, 'steps': 101407, 'loss/train': 1.1459991931915283} 08/31/2021 07:32:25 - INFO - __main__ - Step 101409: {'lr': 0.00012160861566209511, 'samples': 19470528, 'steps': 101408, 'loss/train': 1.2008429765701294} 08/31/2021 07:32:25 - INFO - __main__ - Step 101410: {'lr': 0.00012160406223706608, 'samples': 19470720, 'steps': 101409, 'loss/train': 1.3472027778625488} 08/31/2021 07:32:26 - INFO - __main__ - Step 101411: {'lr': 0.00012159950886989024, 'samples': 19470912, 'steps': 101410, 'loss/train': 0.8128551840782166} 08/31/2021 07:32:28 - INFO - __main__ - Step 101412: {'lr': 0.0001215949555605697, 'samples': 19471104, 'steps': 101411, 'loss/train': 1.540539264678955} 08/31/2021 07:32:28 - INFO - __main__ - Step 101413: {'lr': 0.00012159040230910651, 'samples': 19471296, 'steps': 101412, 'loss/train': 1.5324115753173828} 08/31/2021 07:32:29 - INFO - __main__ - Step 101414: {'lr': 0.00012158584911550269, 'samples': 19471488, 'steps': 101413, 'loss/train': 0.5912073850631714} 08/31/2021 07:32:29 - INFO - __main__ - Step 101415: {'lr': 0.00012158129597976029, 'samples': 19471680, 'steps': 101414, 'loss/train': 1.4652835130691528} 08/31/2021 07:32:29 - INFO - __main__ - Step 101416: {'lr': 0.0001215767429018814, 'samples': 19471872, 'steps': 101415, 'loss/train': 1.4227761030197144} 08/31/2021 07:32:31 - INFO - __main__ - Step 101417: {'lr': 0.00012157218988186802, 'samples': 19472064, 'steps': 101416, 'loss/train': 0.8804949522018433} 08/31/2021 07:32:31 - INFO - __main__ - Step 101418: {'lr': 0.00012156763691972226, 'samples': 19472256, 'steps': 101417, 'loss/train': 1.375320553779602} 08/31/2021 07:32:32 - INFO - __main__ - Step 101419: {'lr': 0.00012156308401544621, 'samples': 19472448, 'steps': 101418, 'loss/train': 0.8104120492935181} 08/31/2021 07:32:32 - INFO - __main__ - Step 101420: {'lr': 0.00012155853116904178, 'samples': 19472640, 'steps': 101419, 'loss/train': 1.2262729406356812} 08/31/2021 07:32:32 - INFO - __main__ - Step 101421: {'lr': 0.00012155397838051108, 'samples': 19472832, 'steps': 101420, 'loss/train': 1.0585664510726929} 08/31/2021 07:32:34 - INFO - __main__ - Step 101422: {'lr': 0.00012154942564985617, 'samples': 19473024, 'steps': 101421, 'loss/train': 1.4085793495178223} 08/31/2021 07:32:34 - INFO - __main__ - Step 101423: {'lr': 0.00012154487297707911, 'samples': 19473216, 'steps': 101422, 'loss/train': 1.1589694023132324} 08/31/2021 07:32:35 - INFO - __main__ - Step 101424: {'lr': 0.00012154032036218196, 'samples': 19473408, 'steps': 101423, 'loss/train': 1.2180495262145996} 08/31/2021 07:32:35 - INFO - __main__ - Step 101425: {'lr': 0.00012153576780516673, 'samples': 19473600, 'steps': 101424, 'loss/train': 0.440495103597641} 08/31/2021 07:32:35 - INFO - __main__ - Step 101426: {'lr': 0.00012153121530603553, 'samples': 19473792, 'steps': 101425, 'loss/train': 0.24100832641124725} 08/31/2021 07:32:37 - INFO - __main__ - Step 101427: {'lr': 0.00012152666286479039, 'samples': 19473984, 'steps': 101426, 'loss/train': 1.3483645915985107} 08/31/2021 07:32:37 - INFO - __main__ - Step 101428: {'lr': 0.00012152211048143333, 'samples': 19474176, 'steps': 101427, 'loss/train': 1.276616096496582} 08/31/2021 07:32:38 - INFO - __main__ - Step 101429: {'lr': 0.00012151755815596643, 'samples': 19474368, 'steps': 101428, 'loss/train': 1.5656383037567139} 08/31/2021 07:32:38 - INFO - __main__ - Step 101430: {'lr': 0.00012151300588839173, 'samples': 19474560, 'steps': 101429, 'loss/train': 1.3898673057556152} 08/31/2021 07:32:38 - INFO - __main__ - Step 101431: {'lr': 0.0001215084536787113, 'samples': 19474752, 'steps': 101430, 'loss/train': 2.402778148651123} 08/31/2021 07:32:40 - INFO - __main__ - Step 101432: {'lr': 0.00012150390152692728, 'samples': 19474944, 'steps': 101431, 'loss/train': 1.2192628383636475} 08/31/2021 07:32:40 - INFO - __main__ - Step 101433: {'lr': 0.0001214993494330415, 'samples': 19475136, 'steps': 101432, 'loss/train': 1.0767066478729248} 08/31/2021 07:32:41 - INFO - __main__ - Step 101434: {'lr': 0.00012149479739705613, 'samples': 19475328, 'steps': 101433, 'loss/train': 0.6962353587150574} 08/31/2021 07:32:41 - INFO - __main__ - Step 101435: {'lr': 0.00012149024541897325, 'samples': 19475520, 'steps': 101434, 'loss/train': 1.833289623260498} 08/31/2021 07:32:41 - INFO - __main__ - Step 101436: {'lr': 0.00012148569349879484, 'samples': 19475712, 'steps': 101435, 'loss/train': 1.0301144123077393} 08/31/2021 07:32:44 - INFO - __main__ - Step 101437: {'lr': 0.00012148114163652305, 'samples': 19475904, 'steps': 101436, 'loss/train': 0.8748747706413269} 08/31/2021 07:32:44 - INFO - __main__ - Step 101438: {'lr': 0.00012147658983215984, 'samples': 19476096, 'steps': 101437, 'loss/train': 0.5788360238075256} 08/31/2021 07:32:44 - INFO - __main__ - Step 101439: {'lr': 0.00012147203808570728, 'samples': 19476288, 'steps': 101438, 'loss/train': 1.6837116479873657} 08/31/2021 07:32:45 - INFO - __main__ - Step 101440: {'lr': 0.00012146748639716745, 'samples': 19476480, 'steps': 101439, 'loss/train': 0.2334281951189041} 08/31/2021 07:32:45 - INFO - __main__ - Step 101441: {'lr': 0.0001214629347665424, 'samples': 19476672, 'steps': 101440, 'loss/train': 1.1980429887771606} 08/31/2021 07:32:45 - INFO - __main__ - Step 101442: {'lr': 0.00012145838319383418, 'samples': 19476864, 'steps': 101441, 'loss/train': 1.0214545726776123} 08/31/2021 07:32:46 - INFO - __main__ - Step 101443: {'lr': 0.00012145383167904481, 'samples': 19477056, 'steps': 101442, 'loss/train': 1.7615246772766113} 08/31/2021 07:32:47 - INFO - __main__ - Step 101444: {'lr': 0.00012144928022217635, 'samples': 19477248, 'steps': 101443, 'loss/train': 1.751789927482605} 08/31/2021 07:32:48 - INFO - __main__ - Step 101445: {'lr': 0.00012144472882323088, 'samples': 19477440, 'steps': 101444, 'loss/train': 1.6329903602600098} 08/31/2021 07:32:48 - INFO - __main__ - Step 101446: {'lr': 0.0001214401774822105, 'samples': 19477632, 'steps': 101445, 'loss/train': 1.289408802986145} 08/31/2021 07:32:49 - INFO - __main__ - Step 101447: {'lr': 0.0001214356261991171, 'samples': 19477824, 'steps': 101446, 'loss/train': 1.43438720703125} 08/31/2021 07:32:49 - INFO - __main__ - Step 101448: {'lr': 0.00012143107497395286, 'samples': 19478016, 'steps': 101447, 'loss/train': 0.7696179747581482} 08/31/2021 07:32:49 - INFO - __main__ - Step 101449: {'lr': 0.00012142652380671976, 'samples': 19478208, 'steps': 101448, 'loss/train': 1.2872881889343262} 08/31/2021 07:32:51 - INFO - __main__ - Step 101450: {'lr': 0.00012142197269741989, 'samples': 19478400, 'steps': 101449, 'loss/train': 1.4398432970046997} 08/31/2021 07:32:51 - INFO - __main__ - Step 101451: {'lr': 0.00012141742164605532, 'samples': 19478592, 'steps': 101450, 'loss/train': 0.7921017408370972} 08/31/2021 07:32:52 - INFO - __main__ - Step 101452: {'lr': 0.00012141287065262805, 'samples': 19478784, 'steps': 101451, 'loss/train': 0.8848704099655151} 08/31/2021 07:32:52 - INFO - __main__ - Step 101453: {'lr': 0.00012140831971714017, 'samples': 19478976, 'steps': 101452, 'loss/train': 1.538116455078125} 08/31/2021 07:32:52 - INFO - __main__ - Step 101454: {'lr': 0.00012140376883959369, 'samples': 19479168, 'steps': 101453, 'loss/train': 0.5858311653137207} 08/31/2021 07:32:54 - INFO - __main__ - Step 101455: {'lr': 0.00012139921801999071, 'samples': 19479360, 'steps': 101454, 'loss/train': 1.3717854022979736} 08/31/2021 07:32:54 - INFO - __main__ - Step 101456: {'lr': 0.00012139466725833326, 'samples': 19479552, 'steps': 101455, 'loss/train': 0.8068404793739319} 08/31/2021 07:32:55 - INFO - __main__ - Step 101457: {'lr': 0.00012139011655462338, 'samples': 19479744, 'steps': 101456, 'loss/train': 1.2593779563903809} 08/31/2021 07:32:55 - INFO - __main__ - Step 101458: {'lr': 0.00012138556590886312, 'samples': 19479936, 'steps': 101457, 'loss/train': 0.9203198552131653} 08/31/2021 07:32:55 - INFO - __main__ - Step 101459: {'lr': 0.00012138101532105467, 'samples': 19480128, 'steps': 101458, 'loss/train': 1.2893418073654175} 08/31/2021 07:32:57 - INFO - __main__ - Step 101460: {'lr': 0.00012137646479119982, 'samples': 19480320, 'steps': 101459, 'loss/train': 1.240096926689148} 08/31/2021 07:32:57 - INFO - __main__ - Step 101461: {'lr': 0.00012137191431930075, 'samples': 19480512, 'steps': 101460, 'loss/train': 1.5397090911865234} 08/31/2021 07:32:58 - INFO - __main__ - Step 101462: {'lr': 0.00012136736390535952, 'samples': 19480704, 'steps': 101461, 'loss/train': 0.9815245270729065} 08/31/2021 07:32:58 - INFO - __main__ - Step 101463: {'lr': 0.00012136281354937817, 'samples': 19480896, 'steps': 101462, 'loss/train': 1.565774917602539} 08/31/2021 07:32:58 - INFO - __main__ - Step 101464: {'lr': 0.00012135826325135877, 'samples': 19481088, 'steps': 101463, 'loss/train': 1.599395751953125} 08/31/2021 07:33:00 - INFO - __main__ - Step 101465: {'lr': 0.00012135371301130332, 'samples': 19481280, 'steps': 101464, 'loss/train': 1.1775562763214111} 08/31/2021 07:33:01 - INFO - __main__ - Step 101466: {'lr': 0.00012134916282921393, 'samples': 19481472, 'steps': 101465, 'loss/train': 0.6230964064598083} 08/31/2021 07:33:01 - INFO - __main__ - Step 101467: {'lr': 0.00012134461270509259, 'samples': 19481664, 'steps': 101466, 'loss/train': 1.3320143222808838} 08/31/2021 07:33:01 - INFO - __main__ - Step 101468: {'lr': 0.0001213400626389414, 'samples': 19481856, 'steps': 101467, 'loss/train': 1.0753026008605957} 08/31/2021 07:33:02 - INFO - __main__ - Step 101469: {'lr': 0.0001213355126307624, 'samples': 19482048, 'steps': 101468, 'loss/train': 1.1488593816757202} 08/31/2021 07:33:03 - INFO - __main__ - Step 101470: {'lr': 0.00012133096268055763, 'samples': 19482240, 'steps': 101469, 'loss/train': 1.3091137409210205} 08/31/2021 07:33:04 - INFO - __main__ - Step 101471: {'lr': 0.00012132641278832915, 'samples': 19482432, 'steps': 101470, 'loss/train': 0.02727317065000534} 08/31/2021 07:33:04 - INFO - __main__ - Step 101472: {'lr': 0.00012132186295407899, 'samples': 19482624, 'steps': 101471, 'loss/train': 1.2165465354919434} 08/31/2021 07:33:05 - INFO - __main__ - Step 101473: {'lr': 0.0001213173131778093, 'samples': 19482816, 'steps': 101472, 'loss/train': 1.1200995445251465} 08/31/2021 07:33:05 - INFO - __main__ - Step 101474: {'lr': 0.00012131276345952197, 'samples': 19483008, 'steps': 101473, 'loss/train': 1.674053430557251} 08/31/2021 07:33:07 - INFO - __main__ - Step 101475: {'lr': 0.0001213082137992191, 'samples': 19483200, 'steps': 101474, 'loss/train': 1.7790136337280273} 08/31/2021 07:33:07 - INFO - __main__ - Step 101476: {'lr': 0.00012130366419690277, 'samples': 19483392, 'steps': 101475, 'loss/train': 0.6888386607170105} 08/31/2021 07:33:07 - INFO - __main__ - Step 101477: {'lr': 0.00012129911465257504, 'samples': 19483584, 'steps': 101476, 'loss/train': 1.451303243637085} 08/31/2021 07:33:08 - INFO - __main__ - Step 101478: {'lr': 0.00012129456516623791, 'samples': 19483776, 'steps': 101477, 'loss/train': 0.33189815282821655} 08/31/2021 07:33:08 - INFO - __main__ - Step 101479: {'lr': 0.0001212900157378935, 'samples': 19483968, 'steps': 101478, 'loss/train': 1.6108542680740356} 08/31/2021 07:33:09 - INFO - __main__ - Step 101480: {'lr': 0.00012128546636754379, 'samples': 19484160, 'steps': 101479, 'loss/train': 0.34554848074913025} 08/31/2021 07:33:10 - INFO - __main__ - Step 101481: {'lr': 0.00012128091705519086, 'samples': 19484352, 'steps': 101480, 'loss/train': 1.086796760559082} 08/31/2021 07:33:10 - INFO - __main__ - Step 101482: {'lr': 0.0001212763678008368, 'samples': 19484544, 'steps': 101481, 'loss/train': 1.2166748046875} 08/31/2021 07:33:11 - INFO - __main__ - Step 101483: {'lr': 0.00012127181860448361, 'samples': 19484736, 'steps': 101482, 'loss/train': 0.07418504357337952} 08/31/2021 07:33:11 - INFO - __main__ - Step 101484: {'lr': 0.00012126726946613334, 'samples': 19484928, 'steps': 101483, 'loss/train': 1.2365131378173828} 08/31/2021 07:33:13 - INFO - __main__ - Step 101485: {'lr': 0.00012126272038578806, 'samples': 19485120, 'steps': 101484, 'loss/train': 0.9423051476478577} 08/31/2021 07:33:13 - INFO - __main__ - Step 101486: {'lr': 0.00012125817136344992, 'samples': 19485312, 'steps': 101485, 'loss/train': 0.6070348024368286} 08/31/2021 07:33:13 - INFO - __main__ - Step 101487: {'lr': 0.00012125362239912071, 'samples': 19485504, 'steps': 101486, 'loss/train': 1.0194491147994995} 08/31/2021 07:33:14 - INFO - __main__ - Step 101488: {'lr': 0.00012124907349280268, 'samples': 19485696, 'steps': 101487, 'loss/train': 0.9031763076782227} 08/31/2021 07:33:14 - INFO - __main__ - Step 101489: {'lr': 0.00012124452464449784, 'samples': 19485888, 'steps': 101488, 'loss/train': 0.5268224477767944} 08/31/2021 07:33:15 - INFO - __main__ - Step 101490: {'lr': 0.0001212399758542082, 'samples': 19486080, 'steps': 101489, 'loss/train': 0.8884082436561584} 08/31/2021 07:33:16 - INFO - __main__ - Step 101491: {'lr': 0.00012123542712193586, 'samples': 19486272, 'steps': 101490, 'loss/train': 1.0726765394210815} 08/31/2021 07:33:16 - INFO - __main__ - Step 101492: {'lr': 0.00012123087844768283, 'samples': 19486464, 'steps': 101491, 'loss/train': 1.1338621377944946} 08/31/2021 07:33:17 - INFO - __main__ - Step 101493: {'lr': 0.00012122632983145118, 'samples': 19486656, 'steps': 101492, 'loss/train': 0.6227396726608276} 08/31/2021 07:33:17 - INFO - __main__ - Step 101494: {'lr': 0.00012122178127324298, 'samples': 19486848, 'steps': 101493, 'loss/train': 1.0429059267044067} 08/31/2021 07:33:19 - INFO - __main__ - Step 101495: {'lr': 0.00012121723277306024, 'samples': 19487040, 'steps': 101494, 'loss/train': 0.433111310005188} 08/31/2021 07:33:19 - INFO - __main__ - Step 101496: {'lr': 0.00012121268433090504, 'samples': 19487232, 'steps': 101495, 'loss/train': 0.732810378074646} 08/31/2021 07:33:19 - INFO - __main__ - Step 101497: {'lr': 0.00012120813594677942, 'samples': 19487424, 'steps': 101496, 'loss/train': 0.7505481839179993} 08/31/2021 07:33:20 - INFO - __main__ - Step 101498: {'lr': 0.00012120358762068543, 'samples': 19487616, 'steps': 101497, 'loss/train': 0.3526025116443634} 08/31/2021 07:33:20 - INFO - __main__ - Step 101499: {'lr': 0.00012119903935262508, 'samples': 19487808, 'steps': 101498, 'loss/train': 0.5981515645980835} 08/31/2021 07:33:20 - INFO - __main__ - Step 101500: {'lr': 0.0001211944911426006, 'samples': 19488000, 'steps': 101499, 'loss/train': 1.1016857624053955} 08/31/2021 07:33:22 - INFO - __main__ - Step 101501: {'lr': 0.00012118994299061376, 'samples': 19488192, 'steps': 101500, 'loss/train': 0.9749114513397217} 08/31/2021 07:33:23 - INFO - __main__ - Step 101502: {'lr': 0.00012118539489666674, 'samples': 19488384, 'steps': 101501, 'loss/train': 0.07316675037145615} 08/31/2021 07:33:23 - INFO - __main__ - Step 101503: {'lr': 0.00012118084686076164, 'samples': 19488576, 'steps': 101502, 'loss/train': 1.2201552391052246} 08/31/2021 07:33:23 - INFO - __main__ - Step 101504: {'lr': 0.00012117629888290044, 'samples': 19488768, 'steps': 101503, 'loss/train': 1.3285574913024902} 08/31/2021 07:33:24 - INFO - __main__ - Step 101505: {'lr': 0.0001211717509630852, 'samples': 19488960, 'steps': 101504, 'loss/train': 0.919383704662323} 08/31/2021 07:33:25 - INFO - __main__ - Step 101506: {'lr': 0.00012116720310131799, 'samples': 19489152, 'steps': 101505, 'loss/train': 1.7393839359283447} 08/31/2021 07:33:25 - INFO - __main__ - Step 101507: {'lr': 0.00012116265529760084, 'samples': 19489344, 'steps': 101506, 'loss/train': 0.9813694953918457} 08/31/2021 07:33:26 - INFO - __main__ - Step 101508: {'lr': 0.00012115810755193582, 'samples': 19489536, 'steps': 101507, 'loss/train': 1.2542258501052856} 08/31/2021 07:33:26 - INFO - __main__ - Step 101509: {'lr': 0.00012115355986432497, 'samples': 19489728, 'steps': 101508, 'loss/train': 0.7358566522598267} 08/31/2021 07:33:27 - INFO - __main__ - Step 101510: {'lr': 0.00012114901223477031, 'samples': 19489920, 'steps': 101509, 'loss/train': 1.033786654472351} 08/31/2021 07:33:28 - INFO - __main__ - Step 101511: {'lr': 0.00012114446466327394, 'samples': 19490112, 'steps': 101510, 'loss/train': 1.223771095275879} 08/31/2021 07:33:28 - INFO - __main__ - Step 101512: {'lr': 0.00012113991714983791, 'samples': 19490304, 'steps': 101511, 'loss/train': 0.7407032251358032} 08/31/2021 07:33:29 - INFO - __main__ - Step 101513: {'lr': 0.00012113536969446432, 'samples': 19490496, 'steps': 101512, 'loss/train': 0.945004940032959} 08/31/2021 07:33:29 - INFO - __main__ - Step 101514: {'lr': 0.00012113082229715502, 'samples': 19490688, 'steps': 101513, 'loss/train': 1.1832791566848755} 08/31/2021 07:33:29 - INFO - __main__ - Step 101515: {'lr': 0.00012112627495791222, 'samples': 19490880, 'steps': 101514, 'loss/train': 1.3714860677719116} 08/31/2021 07:33:31 - INFO - __main__ - Step 101516: {'lr': 0.00012112172767673793, 'samples': 19491072, 'steps': 101515, 'loss/train': 1.512179970741272} 08/31/2021 07:33:32 - INFO - __main__ - Step 101517: {'lr': 0.00012111718045363419, 'samples': 19491264, 'steps': 101516, 'loss/train': 1.3654316663742065} 08/31/2021 07:33:32 - INFO - __main__ - Step 101518: {'lr': 0.00012111263328860305, 'samples': 19491456, 'steps': 101517, 'loss/train': 1.1717746257781982} 08/31/2021 07:33:32 - INFO - __main__ - Step 101519: {'lr': 0.0001211080861816466, 'samples': 19491648, 'steps': 101518, 'loss/train': 1.5363686084747314} 08/31/2021 07:33:33 - INFO - __main__ - Step 101520: {'lr': 0.00012110353913276681, 'samples': 19491840, 'steps': 101519, 'loss/train': 1.5765341520309448} 08/31/2021 07:33:35 - INFO - __main__ - Step 101521: {'lr': 0.00012109899214196582, 'samples': 19492032, 'steps': 101520, 'loss/train': 0.7319559454917908} 08/31/2021 07:33:35 - INFO - __main__ - Step 101522: {'lr': 0.00012109444520924561, 'samples': 19492224, 'steps': 101521, 'loss/train': 0.8066271543502808} 08/31/2021 07:33:35 - INFO - __main__ - Step 101523: {'lr': 0.00012108989833460826, 'samples': 19492416, 'steps': 101522, 'loss/train': 0.7116113901138306} 08/31/2021 07:33:36 - INFO - __main__ - Step 101524: {'lr': 0.0001210853515180558, 'samples': 19492608, 'steps': 101523, 'loss/train': 1.8056797981262207} 08/31/2021 07:33:36 - INFO - __main__ - Step 101525: {'lr': 0.00012108080475959032, 'samples': 19492800, 'steps': 101524, 'loss/train': 0.9657330513000488} 08/31/2021 07:33:38 - INFO - __main__ - Step 101526: {'lr': 0.00012107625805921391, 'samples': 19492992, 'steps': 101525, 'loss/train': 1.6600513458251953} 08/31/2021 07:33:38 - INFO - __main__ - Step 101527: {'lr': 0.00012107171141692847, 'samples': 19493184, 'steps': 101526, 'loss/train': 1.1490018367767334} 08/31/2021 07:33:38 - INFO - __main__ - Step 101528: {'lr': 0.00012106716483273614, 'samples': 19493376, 'steps': 101527, 'loss/train': 1.8046904802322388} 08/31/2021 07:33:39 - INFO - __main__ - Step 101529: {'lr': 0.00012106261830663892, 'samples': 19493568, 'steps': 101528, 'loss/train': 0.15891499817371368} 08/31/2021 07:33:39 - INFO - __main__ - Step 101530: {'lr': 0.0001210580718386389, 'samples': 19493760, 'steps': 101529, 'loss/train': 1.6728200912475586} 08/31/2021 07:33:40 - INFO - __main__ - Step 101531: {'lr': 0.00012105352542873815, 'samples': 19493952, 'steps': 101530, 'loss/train': 0.8769270181655884} 08/31/2021 07:33:41 - INFO - __main__ - Step 101532: {'lr': 0.00012104897907693869, 'samples': 19494144, 'steps': 101531, 'loss/train': 1.0135278701782227} 08/31/2021 07:33:42 - INFO - __main__ - Step 101533: {'lr': 0.00012104443278324254, 'samples': 19494336, 'steps': 101532, 'loss/train': 1.2730488777160645} 08/31/2021 07:33:42 - INFO - __main__ - Step 101534: {'lr': 0.0001210398865476518, 'samples': 19494528, 'steps': 101533, 'loss/train': 1.2693873643875122} 08/31/2021 07:33:42 - INFO - __main__ - Step 101535: {'lr': 0.0001210353403701685, 'samples': 19494720, 'steps': 101534, 'loss/train': 0.7429710626602173} 08/31/2021 07:33:43 - INFO - __main__ - Step 101536: {'lr': 0.00012103079425079466, 'samples': 19494912, 'steps': 101535, 'loss/train': 1.662930965423584} 08/31/2021 07:33:44 - INFO - __main__ - Step 101537: {'lr': 0.00012102624818953239, 'samples': 19495104, 'steps': 101536, 'loss/train': 0.13690443336963654} 08/31/2021 07:33:45 - INFO - __main__ - Step 101538: {'lr': 0.00012102170218638367, 'samples': 19495296, 'steps': 101537, 'loss/train': 1.3164552450180054} 08/31/2021 07:33:45 - INFO - __main__ - Step 101539: {'lr': 0.0001210171562413506, 'samples': 19495488, 'steps': 101538, 'loss/train': 0.9357736706733704} 08/31/2021 07:33:45 - INFO - __main__ - Step 101540: {'lr': 0.00012101261035443531, 'samples': 19495680, 'steps': 101539, 'loss/train': 0.8137335181236267} 08/31/2021 07:33:46 - INFO - __main__ - Step 101541: {'lr': 0.00012100806452563965, 'samples': 19495872, 'steps': 101540, 'loss/train': 1.2990537881851196} 08/31/2021 07:33:47 - INFO - __main__ - Step 101542: {'lr': 0.00012100351875496573, 'samples': 19496064, 'steps': 101541, 'loss/train': 2.0235414505004883} 08/31/2021 07:33:48 - INFO - __main__ - Step 101543: {'lr': 0.00012099897304241567, 'samples': 19496256, 'steps': 101542, 'loss/train': 0.5239053964614868} 08/31/2021 07:33:48 - INFO - __main__ - Step 101544: {'lr': 0.0001209944273879915, 'samples': 19496448, 'steps': 101543, 'loss/train': 1.4153486490249634} 08/31/2021 07:33:48 - INFO - __main__ - Step 101545: {'lr': 0.00012098988179169521, 'samples': 19496640, 'steps': 101544, 'loss/train': 1.060839056968689} 08/31/2021 07:33:49 - INFO - __main__ - Step 101546: {'lr': 0.0001209853362535289, 'samples': 19496832, 'steps': 101545, 'loss/train': 1.1725749969482422} 08/31/2021 07:33:49 - INFO - __main__ - Step 101547: {'lr': 0.00012098079077349462, 'samples': 19497024, 'steps': 101546, 'loss/train': 1.438166618347168} 08/31/2021 07:33:51 - INFO - __main__ - Step 101548: {'lr': 0.00012097624535159438, 'samples': 19497216, 'steps': 101547, 'loss/train': 1.3853427171707153} 08/31/2021 07:33:51 - INFO - __main__ - Step 101549: {'lr': 0.00012097169998783025, 'samples': 19497408, 'steps': 101548, 'loss/train': 1.387844204902649} 08/31/2021 07:33:51 - INFO - __main__ - Step 101550: {'lr': 0.00012096715468220431, 'samples': 19497600, 'steps': 101549, 'loss/train': 1.1523120403289795} 08/31/2021 07:33:52 - INFO - __main__ - Step 101551: {'lr': 0.00012096260943471856, 'samples': 19497792, 'steps': 101550, 'loss/train': 1.9888839721679688} 08/31/2021 07:33:52 - INFO - __main__ - Step 101552: {'lr': 0.00012095806424537508, 'samples': 19497984, 'steps': 101551, 'loss/train': 1.3116703033447266} 08/31/2021 07:33:54 - INFO - __main__ - Step 101553: {'lr': 0.00012095351911417598, 'samples': 19498176, 'steps': 101552, 'loss/train': 1.2812066078186035} 08/31/2021 07:33:54 - INFO - __main__ - Step 101554: {'lr': 0.00012094897404112317, 'samples': 19498368, 'steps': 101553, 'loss/train': 1.8486460447311401} 08/31/2021 07:33:55 - INFO - __main__ - Step 101555: {'lr': 0.00012094442902621874, 'samples': 19498560, 'steps': 101554, 'loss/train': 1.2223427295684814} 08/31/2021 07:33:55 - INFO - __main__ - Step 101556: {'lr': 0.00012093988406946477, 'samples': 19498752, 'steps': 101555, 'loss/train': 1.1859406232833862} 08/31/2021 07:33:55 - INFO - __main__ - Step 101557: {'lr': 0.00012093533917086328, 'samples': 19498944, 'steps': 101556, 'loss/train': 1.5938620567321777} 08/31/2021 07:33:57 - INFO - __main__ - Step 101558: {'lr': 0.00012093079433041634, 'samples': 19499136, 'steps': 101557, 'loss/train': 1.0458115339279175} 08/31/2021 07:33:57 - INFO - __main__ - Step 101559: {'lr': 0.000120926249548126, 'samples': 19499328, 'steps': 101558, 'loss/train': 1.6203885078430176} 08/31/2021 07:33:58 - INFO - __main__ - Step 101560: {'lr': 0.00012092170482399431, 'samples': 19499520, 'steps': 101559, 'loss/train': 1.3227005004882812} 08/31/2021 07:33:58 - INFO - __main__ - Step 101561: {'lr': 0.00012091716015802329, 'samples': 19499712, 'steps': 101560, 'loss/train': 0.24403731524944305} 08/31/2021 07:33:58 - INFO - __main__ - Step 101562: {'lr': 0.00012091261555021499, 'samples': 19499904, 'steps': 101561, 'loss/train': 2.4169158935546875} 08/31/2021 07:34:00 - INFO - __main__ - Step 101563: {'lr': 0.0001209080710005715, 'samples': 19500096, 'steps': 101562, 'loss/train': 1.1665221452713013} 08/31/2021 07:34:01 - INFO - __main__ - Step 101564: {'lr': 0.00012090352650909483, 'samples': 19500288, 'steps': 101563, 'loss/train': 1.5080280303955078} 08/31/2021 07:34:01 - INFO - __main__ - Step 101565: {'lr': 0.00012089898207578706, 'samples': 19500480, 'steps': 101564, 'loss/train': 0.988430380821228} 08/31/2021 07:34:01 - INFO - __main__ - Step 101566: {'lr': 0.0001208944377006502, 'samples': 19500672, 'steps': 101565, 'loss/train': 1.0194929838180542} 08/31/2021 07:34:02 - INFO - __main__ - Step 101567: {'lr': 0.00012088989338368639, 'samples': 19500864, 'steps': 101566, 'loss/train': 0.0833066776394844} 08/31/2021 07:34:03 - INFO - __main__ - Step 101568: {'lr': 0.00012088534912489754, 'samples': 19501056, 'steps': 101567, 'loss/train': 1.0477676391601562} 08/31/2021 07:34:04 - INFO - __main__ - Step 101569: {'lr': 0.00012088080492428575, 'samples': 19501248, 'steps': 101568, 'loss/train': 1.4289209842681885} 08/31/2021 07:34:04 - INFO - __main__ - Step 101570: {'lr': 0.00012087626078185307, 'samples': 19501440, 'steps': 101569, 'loss/train': 1.0518640279769897} 08/31/2021 07:34:05 - INFO - __main__ - Step 101571: {'lr': 0.00012087171669760155, 'samples': 19501632, 'steps': 101570, 'loss/train': 0.8832936882972717} 08/31/2021 07:34:05 - INFO - __main__ - Step 101572: {'lr': 0.00012086717267153325, 'samples': 19501824, 'steps': 101571, 'loss/train': 1.267886757850647} 08/31/2021 07:34:07 - INFO - __main__ - Step 101573: {'lr': 0.0001208626287036502, 'samples': 19502016, 'steps': 101572, 'loss/train': 0.6471459269523621} 08/31/2021 07:34:07 - INFO - __main__ - Step 101574: {'lr': 0.00012085808479395446, 'samples': 19502208, 'steps': 101573, 'loss/train': 0.1273936927318573} 08/31/2021 07:34:08 - INFO - __main__ - Step 101575: {'lr': 0.00012085354094244808, 'samples': 19502400, 'steps': 101574, 'loss/train': 1.640493392944336} 08/31/2021 07:34:08 - INFO - __main__ - Step 101576: {'lr': 0.00012084899714913311, 'samples': 19502592, 'steps': 101575, 'loss/train': 1.2987542152404785} 08/31/2021 07:34:08 - INFO - __main__ - Step 101577: {'lr': 0.00012084445341401157, 'samples': 19502784, 'steps': 101576, 'loss/train': 1.2577764987945557} 08/31/2021 07:34:09 - INFO - __main__ - Step 101578: {'lr': 0.00012083990973708554, 'samples': 19502976, 'steps': 101577, 'loss/train': 1.0198622941970825} 08/31/2021 07:34:10 - INFO - __main__ - Step 101579: {'lr': 0.00012083536611835704, 'samples': 19503168, 'steps': 101578, 'loss/train': 0.6581168174743652} 08/31/2021 07:34:11 - INFO - __main__ - Step 101580: {'lr': 0.00012083082255782824, 'samples': 19503360, 'steps': 101579, 'loss/train': 0.9142572283744812} 08/31/2021 07:34:11 - INFO - __main__ - Step 101581: {'lr': 0.00012082627905550098, 'samples': 19503552, 'steps': 101580, 'loss/train': 0.911212682723999} 08/31/2021 07:34:11 - INFO - __main__ - Step 101582: {'lr': 0.00012082173561137741, 'samples': 19503744, 'steps': 101581, 'loss/train': 0.5667144060134888} 08/31/2021 07:34:12 - INFO - __main__ - Step 101583: {'lr': 0.00012081719222545955, 'samples': 19503936, 'steps': 101582, 'loss/train': 1.8798104524612427} 08/31/2021 07:34:13 - INFO - __main__ - Step 101584: {'lr': 0.00012081264889774948, 'samples': 19504128, 'steps': 101583, 'loss/train': 1.205127477645874} 08/31/2021 07:34:14 - INFO - __main__ - Step 101585: {'lr': 0.00012080810562824926, 'samples': 19504320, 'steps': 101584, 'loss/train': 0.03903837129473686} 08/31/2021 07:34:14 - INFO - __main__ - Step 101586: {'lr': 0.00012080356241696089, 'samples': 19504512, 'steps': 101585, 'loss/train': 1.3389384746551514} 08/31/2021 07:34:14 - INFO - __main__ - Step 101587: {'lr': 0.00012079901926388645, 'samples': 19504704, 'steps': 101586, 'loss/train': 0.4412395656108856} 08/31/2021 07:34:15 - INFO - __main__ - Step 101588: {'lr': 0.00012079447616902798, 'samples': 19504896, 'steps': 101587, 'loss/train': 1.1719839572906494} 08/31/2021 07:34:17 - INFO - __main__ - Step 101589: {'lr': 0.0001207899331323875, 'samples': 19505088, 'steps': 101588, 'loss/train': 1.2060860395431519} 08/31/2021 07:34:17 - INFO - __main__ - Step 101590: {'lr': 0.0001207853901539671, 'samples': 19505280, 'steps': 101589, 'loss/train': 5.7471795082092285} 08/31/2021 07:34:17 - INFO - __main__ - Step 101591: {'lr': 0.00012078084723376892, 'samples': 19505472, 'steps': 101590, 'loss/train': 0.7560542821884155} 08/31/2021 07:34:18 - INFO - __main__ - Step 101592: {'lr': 0.00012077630437179479, 'samples': 19505664, 'steps': 101591, 'loss/train': 0.691511332988739} 08/31/2021 07:34:18 - INFO - __main__ - Step 101593: {'lr': 0.00012077176156804687, 'samples': 19505856, 'steps': 101592, 'loss/train': 0.04162390157580376} 08/31/2021 07:34:18 - INFO - __main__ - Step 101594: {'lr': 0.0001207672188225272, 'samples': 19506048, 'steps': 101593, 'loss/train': 1.2973718643188477} 08/31/2021 07:34:20 - INFO - __main__ - Step 101595: {'lr': 0.00012076267613523781, 'samples': 19506240, 'steps': 101594, 'loss/train': 1.4273288249969482} 08/31/2021 07:34:21 - INFO - __main__ - Step 101596: {'lr': 0.00012075813350618079, 'samples': 19506432, 'steps': 101595, 'loss/train': 1.0828216075897217} 08/31/2021 07:34:21 - INFO - __main__ - Step 101597: {'lr': 0.00012075359093535812, 'samples': 19506624, 'steps': 101596, 'loss/train': 0.9950786232948303} 08/31/2021 07:34:21 - INFO - __main__ - Step 101598: {'lr': 0.00012074904842277193, 'samples': 19506816, 'steps': 101597, 'loss/train': 1.2203223705291748} 08/31/2021 07:34:22 - INFO - __main__ - Step 101599: {'lr': 0.0001207445059684242, 'samples': 19507008, 'steps': 101598, 'loss/train': 0.7147961258888245} 08/31/2021 07:34:22 - INFO - __main__ - Step 101600: {'lr': 0.00012073996357231701, 'samples': 19507200, 'steps': 101599, 'loss/train': 0.46297144889831543} 08/31/2021 07:34:24 - INFO - __main__ - Step 101601: {'lr': 0.00012073542123445239, 'samples': 19507392, 'steps': 101600, 'loss/train': 1.1045252084732056} 08/31/2021 07:34:25 - INFO - __main__ - Step 101602: {'lr': 0.0001207308789548325, 'samples': 19507584, 'steps': 101601, 'loss/train': 0.02626633644104004} 08/31/2021 07:34:25 - INFO - __main__ - Step 101603: {'lr': 0.00012072633673345917, 'samples': 19507776, 'steps': 101602, 'loss/train': 1.0228288173675537} 08/31/2021 07:34:25 - INFO - __main__ - Step 101604: {'lr': 0.00012072179457033458, 'samples': 19507968, 'steps': 101603, 'loss/train': 1.1462690830230713} 08/31/2021 07:34:26 - INFO - __main__ - Step 101605: {'lr': 0.00012071725246546073, 'samples': 19508160, 'steps': 101604, 'loss/train': 1.2830348014831543} 08/31/2021 07:34:27 - INFO - __main__ - Step 101606: {'lr': 0.00012071271041883971, 'samples': 19508352, 'steps': 101605, 'loss/train': 0.4158967435359955} 08/31/2021 07:34:28 - INFO - __main__ - Step 101607: {'lr': 0.00012070816843047356, 'samples': 19508544, 'steps': 101606, 'loss/train': 1.80980384349823} 08/31/2021 07:34:28 - INFO - __main__ - Step 101608: {'lr': 0.0001207036265003643, 'samples': 19508736, 'steps': 101607, 'loss/train': 1.2968727350234985} 08/31/2021 07:34:28 - INFO - __main__ - Step 101609: {'lr': 0.00012069908462851394, 'samples': 19508928, 'steps': 101608, 'loss/train': 1.357539176940918} 08/31/2021 07:34:29 - INFO - __main__ - Step 101610: {'lr': 0.00012069454281492465, 'samples': 19509120, 'steps': 101609, 'loss/train': 1.067460536956787} 08/31/2021 07:34:30 - INFO - __main__ - Step 101611: {'lr': 0.00012069000105959837, 'samples': 19509312, 'steps': 101610, 'loss/train': 1.2850596904754639} 08/31/2021 07:34:31 - INFO - __main__ - Step 101612: {'lr': 0.00012068545936253728, 'samples': 19509504, 'steps': 101611, 'loss/train': 0.42226678133010864} 08/31/2021 07:34:31 - INFO - __main__ - Step 101613: {'lr': 0.00012068091772374323, 'samples': 19509696, 'steps': 101612, 'loss/train': 0.99335777759552} 08/31/2021 07:34:31 - INFO - __main__ - Step 101614: {'lr': 0.00012067637614321839, 'samples': 19509888, 'steps': 101613, 'loss/train': 1.2321429252624512} 08/31/2021 07:34:32 - INFO - __main__ - Step 101615: {'lr': 0.00012067183462096473, 'samples': 19510080, 'steps': 101614, 'loss/train': 0.5503644347190857} 08/31/2021 07:34:32 - INFO - __main__ - Step 101616: {'lr': 0.00012066729315698438, 'samples': 19510272, 'steps': 101615, 'loss/train': 0.9607608318328857} 08/31/2021 07:34:34 - INFO - __main__ - Step 101617: {'lr': 0.00012066275175127935, 'samples': 19510464, 'steps': 101616, 'loss/train': 0.6913027763366699} 08/31/2021 07:34:34 - INFO - __main__ - Step 101618: {'lr': 0.00012065821040385169, 'samples': 19510656, 'steps': 101617, 'loss/train': 0.9123680591583252} 08/31/2021 07:34:34 - INFO - __main__ - Step 101619: {'lr': 0.00012065366911470343, 'samples': 19510848, 'steps': 101618, 'loss/train': 1.1737897396087646} 08/31/2021 07:34:35 - INFO - __main__ - Step 101620: {'lr': 0.00012064912788383663, 'samples': 19511040, 'steps': 101619, 'loss/train': 1.4597508907318115} 08/31/2021 07:34:35 - INFO - __main__ - Step 101621: {'lr': 0.00012064458671125336, 'samples': 19511232, 'steps': 101620, 'loss/train': 1.3318768739700317} 08/31/2021 07:34:37 - INFO - __main__ - Step 101622: {'lr': 0.00012064004559695562, 'samples': 19511424, 'steps': 101621, 'loss/train': 0.8486092686653137} 08/31/2021 07:34:37 - INFO - __main__ - Step 101623: {'lr': 0.00012063550454094558, 'samples': 19511616, 'steps': 101622, 'loss/train': 1.469586730003357} 08/31/2021 07:34:37 - INFO - __main__ - Step 101624: {'lr': 0.00012063096354322508, 'samples': 19511808, 'steps': 101623, 'loss/train': 1.5114787817001343} 08/31/2021 07:34:38 - INFO - __main__ - Step 101625: {'lr': 0.0001206264226037963, 'samples': 19512000, 'steps': 101624, 'loss/train': 1.3802493810653687} 08/31/2021 07:34:38 - INFO - __main__ - Step 101626: {'lr': 0.00012062188172266123, 'samples': 19512192, 'steps': 101625, 'loss/train': 1.0297690629959106} 08/31/2021 07:34:40 - INFO - __main__ - Step 101627: {'lr': 0.00012061734089982196, 'samples': 19512384, 'steps': 101626, 'loss/train': 0.9032306671142578} 08/31/2021 07:34:41 - INFO - __main__ - Step 101628: {'lr': 0.00012061280013528053, 'samples': 19512576, 'steps': 101627, 'loss/train': 0.18880318105220795} 08/31/2021 07:34:41 - INFO - __main__ - Step 101629: {'lr': 0.00012060825942903894, 'samples': 19512768, 'steps': 101628, 'loss/train': 1.0431604385375977} 08/31/2021 07:34:41 - INFO - __main__ - Step 101630: {'lr': 0.0001206037187810993, 'samples': 19512960, 'steps': 101629, 'loss/train': 0.4788409173488617} 08/31/2021 07:34:42 - INFO - __main__ - Step 101631: {'lr': 0.00012059917819146362, 'samples': 19513152, 'steps': 101630, 'loss/train': 0.5871433019638062} 08/31/2021 07:34:43 - INFO - __main__ - Step 101632: {'lr': 0.00012059463766013396, 'samples': 19513344, 'steps': 101631, 'loss/train': 1.381627082824707} 08/31/2021 07:34:44 - INFO - __main__ - Step 101633: {'lr': 0.00012059009718711233, 'samples': 19513536, 'steps': 101632, 'loss/train': 1.2896732091903687} 08/31/2021 07:34:44 - INFO - __main__ - Step 101634: {'lr': 0.00012058555677240093, 'samples': 19513728, 'steps': 101633, 'loss/train': 1.726658582687378} 08/31/2021 07:34:44 - INFO - __main__ - Step 101635: {'lr': 0.00012058101641600158, 'samples': 19513920, 'steps': 101634, 'loss/train': 1.0337892770767212} 08/31/2021 07:34:45 - INFO - __main__ - Step 101636: {'lr': 0.00012057647611791645, 'samples': 19514112, 'steps': 101635, 'loss/train': 1.5681012868881226} 08/31/2021 07:34:45 - INFO - __main__ - Step 101637: {'lr': 0.00012057193587814752, 'samples': 19514304, 'steps': 101636, 'loss/train': 0.6418308615684509} 08/31/2021 07:34:46 - INFO - __main__ - Step 101638: {'lr': 0.00012056739569669688, 'samples': 19514496, 'steps': 101637, 'loss/train': 1.1581690311431885} 08/31/2021 07:34:47 - INFO - __main__ - Step 101639: {'lr': 0.00012056285557356661, 'samples': 19514688, 'steps': 101638, 'loss/train': 1.544374704360962} 08/31/2021 07:34:47 - INFO - __main__ - Step 101640: {'lr': 0.0001205583155087587, 'samples': 19514880, 'steps': 101639, 'loss/train': 1.5077801942825317} 08/31/2021 07:34:48 - INFO - __main__ - Step 101641: {'lr': 0.00012055377550227523, 'samples': 19515072, 'steps': 101640, 'loss/train': 1.420950174331665} 08/31/2021 07:34:48 - INFO - __main__ - Step 101642: {'lr': 0.0001205492355541182, 'samples': 19515264, 'steps': 101641, 'loss/train': 1.0885170698165894} 08/31/2021 07:34:50 - INFO - __main__ - Step 101643: {'lr': 0.00012054469566428971, 'samples': 19515456, 'steps': 101642, 'loss/train': 1.008658766746521} 08/31/2021 07:34:50 - INFO - __main__ - Step 101644: {'lr': 0.00012054015583279179, 'samples': 19515648, 'steps': 101643, 'loss/train': 0.5444469451904297} 08/31/2021 07:34:50 - INFO - __main__ - Step 101645: {'lr': 0.00012053561605962646, 'samples': 19515840, 'steps': 101644, 'loss/train': 1.2426154613494873} 08/31/2021 07:34:51 - INFO - __main__ - Step 101646: {'lr': 0.00012053107634479579, 'samples': 19516032, 'steps': 101645, 'loss/train': 0.10642832517623901} 08/31/2021 07:34:51 - INFO - __main__ - Step 101647: {'lr': 0.0001205265366883019, 'samples': 19516224, 'steps': 101646, 'loss/train': 1.0505237579345703} 08/31/2021 07:34:53 - INFO - __main__ - Step 101648: {'lr': 0.00012052199709014669, 'samples': 19516416, 'steps': 101647, 'loss/train': 1.7835711240768433} 08/31/2021 07:34:53 - INFO - __main__ - Step 101649: {'lr': 0.00012051745755033224, 'samples': 19516608, 'steps': 101648, 'loss/train': 0.8006229996681213} 08/31/2021 07:34:53 - INFO - __main__ - Step 101650: {'lr': 0.00012051291806886067, 'samples': 19516800, 'steps': 101649, 'loss/train': 1.0081242322921753} 08/31/2021 07:34:54 - INFO - __main__ - Step 101651: {'lr': 0.00012050837864573394, 'samples': 19516992, 'steps': 101650, 'loss/train': 1.4092888832092285} 08/31/2021 07:34:54 - INFO - __main__ - Step 101652: {'lr': 0.00012050383928095415, 'samples': 19517184, 'steps': 101651, 'loss/train': 2.4368321895599365} 08/31/2021 07:34:56 - INFO - __main__ - Step 101653: {'lr': 0.00012049929997452333, 'samples': 19517376, 'steps': 101652, 'loss/train': 1.715415596961975} 08/31/2021 07:34:56 - INFO - __main__ - Step 101654: {'lr': 0.00012049476072644352, 'samples': 19517568, 'steps': 101653, 'loss/train': 0.8448714017868042} 08/31/2021 07:34:57 - INFO - __main__ - Step 101655: {'lr': 0.00012049022153671677, 'samples': 19517760, 'steps': 101654, 'loss/train': 0.14023476839065552} 08/31/2021 07:34:57 - INFO - __main__ - Step 101656: {'lr': 0.00012048568240534513, 'samples': 19517952, 'steps': 101655, 'loss/train': 1.3104727268218994} 08/31/2021 07:34:57 - INFO - __main__ - Step 101657: {'lr': 0.00012048114333233065, 'samples': 19518144, 'steps': 101656, 'loss/train': 1.526383399963379} 08/31/2021 07:34:59 - INFO - __main__ - Step 101658: {'lr': 0.00012047660431767537, 'samples': 19518336, 'steps': 101657, 'loss/train': 1.7185251712799072} 08/31/2021 07:34:59 - INFO - __main__ - Step 101659: {'lr': 0.00012047206536138133, 'samples': 19518528, 'steps': 101658, 'loss/train': 1.535981297492981} 08/31/2021 07:35:00 - INFO - __main__ - Step 101660: {'lr': 0.00012046752646345058, 'samples': 19518720, 'steps': 101659, 'loss/train': 0.8477292060852051} 08/31/2021 07:35:00 - INFO - __main__ - Step 101661: {'lr': 0.00012046298762388527, 'samples': 19518912, 'steps': 101660, 'loss/train': 5.733696460723877} 08/31/2021 07:35:00 - INFO - __main__ - Step 101662: {'lr': 0.00012045844884268722, 'samples': 19519104, 'steps': 101661, 'loss/train': 1.218291997909546} 08/31/2021 07:35:01 - INFO - __main__ - Step 101663: {'lr': 0.00012045391011985862, 'samples': 19519296, 'steps': 101662, 'loss/train': 0.1351786106824875} 08/31/2021 07:35:02 - INFO - __main__ - Step 101664: {'lr': 0.00012044937145540147, 'samples': 19519488, 'steps': 101663, 'loss/train': 1.2114959955215454} 08/31/2021 07:35:03 - INFO - __main__ - Step 101665: {'lr': 0.00012044483284931785, 'samples': 19519680, 'steps': 101664, 'loss/train': 1.3292138576507568} 08/31/2021 07:35:03 - INFO - __main__ - Step 101666: {'lr': 0.00012044029430160977, 'samples': 19519872, 'steps': 101665, 'loss/train': 1.5851069688796997} 08/31/2021 07:35:03 - INFO - __main__ - Step 101667: {'lr': 0.00012043575581227928, 'samples': 19520064, 'steps': 101666, 'loss/train': 1.239612102508545} 08/31/2021 07:35:04 - INFO - __main__ - Step 101668: {'lr': 0.00012043121738132847, 'samples': 19520256, 'steps': 101667, 'loss/train': 1.0991815328598022} 08/31/2021 07:35:05 - INFO - __main__ - Step 101669: {'lr': 0.00012042667900875934, 'samples': 19520448, 'steps': 101668, 'loss/train': 1.1686698198318481} 08/31/2021 07:35:06 - INFO - __main__ - Step 101670: {'lr': 0.00012042214069457397, 'samples': 19520640, 'steps': 101669, 'loss/train': 1.418835997581482} 08/31/2021 07:35:06 - INFO - __main__ - Step 101671: {'lr': 0.00012041760243877436, 'samples': 19520832, 'steps': 101670, 'loss/train': 1.7897922992706299} 08/31/2021 07:35:06 - INFO - __main__ - Step 101672: {'lr': 0.00012041306424136258, 'samples': 19521024, 'steps': 101671, 'loss/train': 0.6747955679893494} 08/31/2021 07:35:07 - INFO - __main__ - Step 101673: {'lr': 0.00012040852610234068, 'samples': 19521216, 'steps': 101672, 'loss/train': 0.8184670209884644} 08/31/2021 07:35:08 - INFO - __main__ - Step 101674: {'lr': 0.0001204039880217108, 'samples': 19521408, 'steps': 101673, 'loss/train': 1.2109789848327637} 08/31/2021 07:35:08 - INFO - __main__ - Step 101675: {'lr': 0.00012039944999947477, 'samples': 19521600, 'steps': 101674, 'loss/train': 1.148738980293274} 08/31/2021 07:35:09 - INFO - __main__ - Step 101676: {'lr': 0.00012039491203563477, 'samples': 19521792, 'steps': 101675, 'loss/train': 1.618710994720459} 08/31/2021 07:35:09 - INFO - __main__ - Step 101677: {'lr': 0.00012039037413019283, 'samples': 19521984, 'steps': 101676, 'loss/train': 0.5546750426292419} 08/31/2021 07:35:09 - INFO - __main__ - Step 101678: {'lr': 0.00012038583628315097, 'samples': 19522176, 'steps': 101677, 'loss/train': 0.6931491494178772} 08/31/2021 07:35:11 - INFO - __main__ - Step 101679: {'lr': 0.00012038129849451124, 'samples': 19522368, 'steps': 101678, 'loss/train': 1.604479193687439} 08/31/2021 07:35:12 - INFO - __main__ - Step 101680: {'lr': 0.0001203767607642757, 'samples': 19522560, 'steps': 101679, 'loss/train': 1.1396666765213013} 08/31/2021 07:35:12 - INFO - __main__ - Step 101681: {'lr': 0.00012037222309244642, 'samples': 19522752, 'steps': 101680, 'loss/train': 0.023107927292585373} 08/31/2021 07:35:12 - INFO - __main__ - Step 101682: {'lr': 0.00012036768547902538, 'samples': 19522944, 'steps': 101681, 'loss/train': 0.052147842943668365} 08/31/2021 07:35:13 - INFO - __main__ - Step 101683: {'lr': 0.00012036314792401467, 'samples': 19523136, 'steps': 101682, 'loss/train': 1.1451282501220703} 08/31/2021 07:35:13 - INFO - __main__ - Step 101684: {'lr': 0.00012035861042741635, 'samples': 19523328, 'steps': 101683, 'loss/train': 1.254586935043335} 08/31/2021 07:35:15 - INFO - __main__ - Step 101685: {'lr': 0.00012035407298923242, 'samples': 19523520, 'steps': 101684, 'loss/train': 1.504679799079895} 08/31/2021 07:35:16 - INFO - __main__ - Step 101686: {'lr': 0.00012034953560946497, 'samples': 19523712, 'steps': 101685, 'loss/train': 0.9975141882896423} 08/31/2021 07:35:16 - INFO - __main__ - Step 101687: {'lr': 0.00012034499828811599, 'samples': 19523904, 'steps': 101686, 'loss/train': 1.1400806903839111} 08/31/2021 07:35:16 - INFO - __main__ - Step 101688: {'lr': 0.00012034046102518765, 'samples': 19524096, 'steps': 101687, 'loss/train': 0.7654421329498291} 08/31/2021 07:35:17 - INFO - __main__ - Step 101689: {'lr': 0.00012033592382068178, 'samples': 19524288, 'steps': 101688, 'loss/train': 0.4719488322734833} 08/31/2021 07:35:18 - INFO - __main__ - Step 101690: {'lr': 0.00012033138667460058, 'samples': 19524480, 'steps': 101689, 'loss/train': 1.4906376600265503} 08/31/2021 07:35:19 - INFO - __main__ - Step 101691: {'lr': 0.00012032684958694604, 'samples': 19524672, 'steps': 101690, 'loss/train': 0.031326718628406525} 08/31/2021 07:35:19 - INFO - __main__ - Step 101692: {'lr': 0.00012032231255772022, 'samples': 19524864, 'steps': 101691, 'loss/train': 0.7556763291358948} 08/31/2021 07:35:19 - INFO - __main__ - Step 101693: {'lr': 0.00012031777558692516, 'samples': 19525056, 'steps': 101692, 'loss/train': 1.0128254890441895} 08/31/2021 07:35:20 - INFO - __main__ - Step 101694: {'lr': 0.00012031323867456293, 'samples': 19525248, 'steps': 101693, 'loss/train': 1.1887261867523193} 08/31/2021 07:35:21 - INFO - __main__ - Step 101695: {'lr': 0.00012030870182063556, 'samples': 19525440, 'steps': 101694, 'loss/train': 1.0954691171646118} 08/31/2021 07:35:22 - INFO - __main__ - Step 101696: {'lr': 0.00012030416502514504, 'samples': 19525632, 'steps': 101695, 'loss/train': 1.04832923412323} 08/31/2021 07:35:22 - INFO - __main__ - Step 101697: {'lr': 0.00012029962828809352, 'samples': 19525824, 'steps': 101696, 'loss/train': 1.7008486986160278} 08/31/2021 07:35:23 - INFO - __main__ - Step 101698: {'lr': 0.00012029509160948294, 'samples': 19526016, 'steps': 101697, 'loss/train': 0.3727898597717285} 08/31/2021 07:35:23 - INFO - __main__ - Step 101699: {'lr': 0.0001202905549893154, 'samples': 19526208, 'steps': 101698, 'loss/train': 0.41736066341400146} 08/31/2021 07:35:23 - INFO - __main__ - Step 101700: {'lr': 0.00012028601842759295, 'samples': 19526400, 'steps': 101699, 'loss/train': 0.5204687714576721} 08/31/2021 07:35:25 - INFO - __main__ - Step 101701: {'lr': 0.00012028148192431771, 'samples': 19526592, 'steps': 101700, 'loss/train': 1.4638152122497559} 08/31/2021 07:35:25 - INFO - __main__ - Step 101702: {'lr': 0.00012027694547949153, 'samples': 19526784, 'steps': 101701, 'loss/train': 1.130101203918457} 08/31/2021 07:35:26 - INFO - __main__ - Step 101703: {'lr': 0.00012027240909311656, 'samples': 19526976, 'steps': 101702, 'loss/train': 0.7580312490463257} 08/31/2021 07:35:26 - INFO - __main__ - Step 101704: {'lr': 0.00012026787276519485, 'samples': 19527168, 'steps': 101703, 'loss/train': 0.03904798626899719} 08/31/2021 07:35:26 - INFO - __main__ - Step 101705: {'lr': 0.0001202633364957284, 'samples': 19527360, 'steps': 101704, 'loss/train': 0.6132375001907349} 08/31/2021 07:35:28 - INFO - __main__ - Step 101706: {'lr': 0.00012025880028471934, 'samples': 19527552, 'steps': 101705, 'loss/train': 1.6233891248703003} 08/31/2021 07:35:28 - INFO - __main__ - Step 101707: {'lr': 0.00012025426413216963, 'samples': 19527744, 'steps': 101706, 'loss/train': 1.1355944871902466} 08/31/2021 07:35:29 - INFO - __main__ - Step 101708: {'lr': 0.00012024972803808135, 'samples': 19527936, 'steps': 101707, 'loss/train': 0.7391155958175659} 08/31/2021 07:35:29 - INFO - __main__ - Step 101709: {'lr': 0.00012024519200245653, 'samples': 19528128, 'steps': 101708, 'loss/train': 1.1682273149490356} 08/31/2021 07:35:29 - INFO - __main__ - Step 101710: {'lr': 0.00012024065602529724, 'samples': 19528320, 'steps': 101709, 'loss/train': 1.6603089570999146} 08/31/2021 07:35:31 - INFO - __main__ - Step 101711: {'lr': 0.00012023612010660551, 'samples': 19528512, 'steps': 101710, 'loss/train': 1.2018970251083374} 08/31/2021 07:35:31 - INFO - __main__ - Step 101712: {'lr': 0.00012023158424638339, 'samples': 19528704, 'steps': 101711, 'loss/train': 1.4767082929611206} 08/31/2021 07:35:32 - INFO - __main__ - Step 101713: {'lr': 0.0001202270484446329, 'samples': 19528896, 'steps': 101712, 'loss/train': 1.2394402027130127} 08/31/2021 07:35:32 - INFO - __main__ - Step 101714: {'lr': 0.00012022251270135609, 'samples': 19529088, 'steps': 101713, 'loss/train': 1.107418417930603} 08/31/2021 07:35:32 - INFO - __main__ - Step 101715: {'lr': 0.00012021797701655512, 'samples': 19529280, 'steps': 101714, 'loss/train': 1.5302244424819946} 08/31/2021 07:35:34 - INFO - __main__ - Step 101716: {'lr': 0.00012021344139023186, 'samples': 19529472, 'steps': 101715, 'loss/train': 0.9160192012786865} 08/31/2021 07:35:34 - INFO - __main__ - Step 101717: {'lr': 0.00012020890582238838, 'samples': 19529664, 'steps': 101716, 'loss/train': 1.3963829278945923} 08/31/2021 07:35:35 - INFO - __main__ - Step 101718: {'lr': 0.00012020437031302677, 'samples': 19529856, 'steps': 101717, 'loss/train': 1.1565805673599243} 08/31/2021 07:35:35 - INFO - __main__ - Step 101719: {'lr': 0.00012019983486214908, 'samples': 19530048, 'steps': 101718, 'loss/train': 1.05953848361969} 08/31/2021 07:35:35 - INFO - __main__ - Step 101720: {'lr': 0.00012019529946975733, 'samples': 19530240, 'steps': 101719, 'loss/train': 0.8725329637527466} 08/31/2021 07:35:37 - INFO - __main__ - Step 101721: {'lr': 0.00012019076413585359, 'samples': 19530432, 'steps': 101720, 'loss/train': 1.2990894317626953} 08/31/2021 07:35:37 - INFO - __main__ - Step 101722: {'lr': 0.00012018622886043987, 'samples': 19530624, 'steps': 101721, 'loss/train': 0.7445432543754578} 08/31/2021 07:35:38 - INFO - __main__ - Step 101723: {'lr': 0.00012018169364351824, 'samples': 19530816, 'steps': 101722, 'loss/train': 1.524727463722229} 08/31/2021 07:35:38 - INFO - __main__ - Step 101724: {'lr': 0.00012017715848509076, 'samples': 19531008, 'steps': 101723, 'loss/train': 1.8921316862106323} 08/31/2021 07:35:38 - INFO - __main__ - Step 101725: {'lr': 0.00012017262338515941, 'samples': 19531200, 'steps': 101724, 'loss/train': 0.9328914880752563} 08/31/2021 07:35:40 - INFO - __main__ - Step 101726: {'lr': 0.0001201680883437263, 'samples': 19531392, 'steps': 101725, 'loss/train': 1.1827635765075684} 08/31/2021 07:35:40 - INFO - __main__ - Step 101727: {'lr': 0.00012016355336079343, 'samples': 19531584, 'steps': 101726, 'loss/train': 1.2244782447814941} 08/31/2021 07:35:41 - INFO - __main__ - Step 101728: {'lr': 0.00012015901843636295, 'samples': 19531776, 'steps': 101727, 'loss/train': 1.2698811292648315} 08/31/2021 07:35:41 - INFO - __main__ - Step 101729: {'lr': 0.00012015448357043673, 'samples': 19531968, 'steps': 101728, 'loss/train': 1.1409521102905273} 08/31/2021 07:35:41 - INFO - __main__ - Step 101730: {'lr': 0.00012014994876301691, 'samples': 19532160, 'steps': 101729, 'loss/train': 1.3895142078399658} 08/31/2021 07:35:43 - INFO - __main__ - Step 101731: {'lr': 0.0001201454140141055, 'samples': 19532352, 'steps': 101730, 'loss/train': 1.204322099685669} 08/31/2021 07:35:43 - INFO - __main__ - Step 101732: {'lr': 0.00012014087932370457, 'samples': 19532544, 'steps': 101731, 'loss/train': 1.0810163021087646} 08/31/2021 07:35:44 - INFO - __main__ - Step 101733: {'lr': 0.00012013634469181614, 'samples': 19532736, 'steps': 101732, 'loss/train': 1.3459726572036743} 08/31/2021 07:35:44 - INFO - __main__ - Step 101734: {'lr': 0.00012013181011844229, 'samples': 19532928, 'steps': 101733, 'loss/train': 1.0404443740844727} 08/31/2021 07:35:44 - INFO - __main__ - Step 101735: {'lr': 0.00012012727560358502, 'samples': 19533120, 'steps': 101734, 'loss/train': 0.6877654790878296} 08/31/2021 07:35:45 - INFO - __main__ - Step 101736: {'lr': 0.00012012274114724641, 'samples': 19533312, 'steps': 101735, 'loss/train': 0.588363528251648} 08/31/2021 07:35:47 - INFO - __main__ - Step 101737: {'lr': 0.0001201182067494285, 'samples': 19533504, 'steps': 101736, 'loss/train': 0.2580851912498474} 08/31/2021 07:35:47 - INFO - __main__ - Step 101738: {'lr': 0.00012011367241013329, 'samples': 19533696, 'steps': 101737, 'loss/train': 0.8942738175392151} 08/31/2021 07:35:48 - INFO - __main__ - Step 101739: {'lr': 0.00012010913812936289, 'samples': 19533888, 'steps': 101738, 'loss/train': 1.2674223184585571} 08/31/2021 07:35:48 - INFO - __main__ - Step 101740: {'lr': 0.00012010460390711927, 'samples': 19534080, 'steps': 101739, 'loss/train': 0.7053371667861938} 08/31/2021 07:35:48 - INFO - __main__ - Step 101741: {'lr': 0.00012010006974340454, 'samples': 19534272, 'steps': 101740, 'loss/train': 1.6184111833572388} 08/31/2021 07:35:50 - INFO - __main__ - Step 101742: {'lr': 0.00012009553563822081, 'samples': 19534464, 'steps': 101741, 'loss/train': 1.4624416828155518} 08/31/2021 07:35:50 - INFO - __main__ - Step 101743: {'lr': 0.00012009100159156993, 'samples': 19534656, 'steps': 101742, 'loss/train': 1.129699468612671} 08/31/2021 07:35:51 - INFO - __main__ - Step 101744: {'lr': 0.00012008646760345405, 'samples': 19534848, 'steps': 101743, 'loss/train': 0.488018661737442} 08/31/2021 07:35:51 - INFO - __main__ - Step 101745: {'lr': 0.00012008193367387518, 'samples': 19535040, 'steps': 101744, 'loss/train': 1.2323334217071533} 08/31/2021 07:35:51 - INFO - __main__ - Step 101746: {'lr': 0.00012007739980283539, 'samples': 19535232, 'steps': 101745, 'loss/train': 0.6270249485969543} 08/31/2021 07:35:53 - INFO - __main__ - Step 101747: {'lr': 0.0001200728659903367, 'samples': 19535424, 'steps': 101746, 'loss/train': 1.397699236869812} 08/31/2021 07:35:54 - INFO - __main__ - Step 101748: {'lr': 0.00012006833223638122, 'samples': 19535616, 'steps': 101747, 'loss/train': 1.0773454904556274} 08/31/2021 07:35:54 - INFO - __main__ - Step 101749: {'lr': 0.0001200637985409709, 'samples': 19535808, 'steps': 101748, 'loss/train': 1.5291740894317627} 08/31/2021 07:35:54 - INFO - __main__ - Step 101750: {'lr': 0.00012005926490410784, 'samples': 19536000, 'steps': 101749, 'loss/train': 0.031833454966545105} 08/31/2021 07:35:55 - INFO - __main__ - Step 101751: {'lr': 0.00012005473132579409, 'samples': 19536192, 'steps': 101750, 'loss/train': 1.3222233057022095} 08/31/2021 07:35:56 - INFO - __main__ - Step 101752: {'lr': 0.00012005019780603166, 'samples': 19536384, 'steps': 101751, 'loss/train': 0.4669724106788635} 08/31/2021 07:35:57 - INFO - __main__ - Step 101753: {'lr': 0.00012004566434482261, 'samples': 19536576, 'steps': 101752, 'loss/train': 1.1656200885772705} 08/31/2021 07:35:57 - INFO - __main__ - Step 101754: {'lr': 0.00012004113094216898, 'samples': 19536768, 'steps': 101753, 'loss/train': 0.04105202108621597} 08/31/2021 07:35:58 - INFO - __main__ - Step 101755: {'lr': 0.00012003659759807289, 'samples': 19536960, 'steps': 101754, 'loss/train': 1.2775418758392334} 08/31/2021 07:35:58 - INFO - __main__ - Step 101756: {'lr': 0.00012003206431253622, 'samples': 19537152, 'steps': 101755, 'loss/train': 1.6642541885375977} 08/31/2021 07:35:59 - INFO - __main__ - Step 101757: {'lr': 0.00012002753108556108, 'samples': 19537344, 'steps': 101756, 'loss/train': 1.1199285984039307} 08/31/2021 07:36:00 - INFO - __main__ - Step 101758: {'lr': 0.00012002299791714955, 'samples': 19537536, 'steps': 101757, 'loss/train': 1.4607362747192383} 08/31/2021 07:36:00 - INFO - __main__ - Step 101759: {'lr': 0.00012001846480730366, 'samples': 19537728, 'steps': 101758, 'loss/train': 1.1840813159942627} 08/31/2021 07:36:01 - INFO - __main__ - Step 101760: {'lr': 0.00012001393175602543, 'samples': 19537920, 'steps': 101759, 'loss/train': 1.7357537746429443} 08/31/2021 07:36:01 - INFO - __main__ - Step 101761: {'lr': 0.0001200093987633169, 'samples': 19538112, 'steps': 101760, 'loss/train': 1.3147786855697632} 08/31/2021 07:36:03 - INFO - __main__ - Step 101762: {'lr': 0.00012000486582918013, 'samples': 19538304, 'steps': 101761, 'loss/train': 0.9615361094474792} 08/31/2021 07:36:03 - INFO - __main__ - Step 101763: {'lr': 0.00012000033295361721, 'samples': 19538496, 'steps': 101762, 'loss/train': 1.1680750846862793} 08/31/2021 07:36:03 - INFO - __main__ - Step 101764: {'lr': 0.00011999580013663008, 'samples': 19538688, 'steps': 101763, 'loss/train': 1.0020687580108643} 08/31/2021 07:36:04 - INFO - __main__ - Step 101765: {'lr': 0.00011999126737822085, 'samples': 19538880, 'steps': 101764, 'loss/train': 1.1504392623901367} 08/31/2021 07:36:04 - INFO - __main__ - Step 101766: {'lr': 0.00011998673467839155, 'samples': 19539072, 'steps': 101765, 'loss/train': 0.7428621649742126} 08/31/2021 07:36:05 - INFO - __main__ - Step 101767: {'lr': 0.00011998220203714425, 'samples': 19539264, 'steps': 101766, 'loss/train': 1.4634759426116943} 08/31/2021 07:36:06 - INFO - __main__ - Step 101768: {'lr': 0.00011997766945448102, 'samples': 19539456, 'steps': 101767, 'loss/train': 1.486343502998352} 08/31/2021 07:36:06 - INFO - __main__ - Step 101769: {'lr': 0.00011997313693040377, 'samples': 19539648, 'steps': 101768, 'loss/train': 1.9981980323791504} 08/31/2021 07:36:07 - INFO - __main__ - Step 101770: {'lr': 0.00011996860446491462, 'samples': 19539840, 'steps': 101769, 'loss/train': 0.22206038236618042} 08/31/2021 07:36:07 - INFO - __main__ - Step 101771: {'lr': 0.0001199640720580156, 'samples': 19540032, 'steps': 101770, 'loss/train': 0.7229089736938477} 08/31/2021 07:36:09 - INFO - __main__ - Step 101772: {'lr': 0.00011995953970970878, 'samples': 19540224, 'steps': 101771, 'loss/train': 0.9934617280960083} 08/31/2021 07:36:09 - INFO - __main__ - Step 101773: {'lr': 0.00011995500741999615, 'samples': 19540416, 'steps': 101772, 'loss/train': 0.6982331871986389} 08/31/2021 07:36:09 - INFO - __main__ - Step 101774: {'lr': 0.00011995047518887981, 'samples': 19540608, 'steps': 101773, 'loss/train': 0.46969717741012573} 08/31/2021 07:36:10 - INFO - __main__ - Step 101775: {'lr': 0.00011994594301636178, 'samples': 19540800, 'steps': 101774, 'loss/train': 1.2733113765716553} 08/31/2021 07:36:10 - INFO - __main__ - Step 101776: {'lr': 0.00011994141090244409, 'samples': 19540992, 'steps': 101775, 'loss/train': 0.8176148533821106} 08/31/2021 07:36:11 - INFO - __main__ - Step 101777: {'lr': 0.0001199368788471288, 'samples': 19541184, 'steps': 101776, 'loss/train': 0.9608219265937805} 08/31/2021 07:36:12 - INFO - __main__ - Step 101778: {'lr': 0.00011993234685041795, 'samples': 19541376, 'steps': 101777, 'loss/train': 0.8425820469856262} 08/31/2021 07:36:12 - INFO - __main__ - Step 101779: {'lr': 0.00011992781491231358, 'samples': 19541568, 'steps': 101778, 'loss/train': 0.8872432112693787} 08/31/2021 07:36:13 - INFO - __main__ - Step 101780: {'lr': 0.00011992328303281772, 'samples': 19541760, 'steps': 101779, 'loss/train': 1.0164079666137695} 08/31/2021 07:36:13 - INFO - __main__ - Step 101781: {'lr': 0.00011991875121193241, 'samples': 19541952, 'steps': 101780, 'loss/train': 0.9875656962394714} 08/31/2021 07:36:13 - INFO - __main__ - Step 101782: {'lr': 0.00011991421944965982, 'samples': 19542144, 'steps': 101781, 'loss/train': 1.143882393836975} 08/31/2021 07:36:15 - INFO - __main__ - Step 101783: {'lr': 0.00011990968774600178, 'samples': 19542336, 'steps': 101782, 'loss/train': 1.138259768486023} 08/31/2021 07:36:15 - INFO - __main__ - Step 101784: {'lr': 0.00011990515610096042, 'samples': 19542528, 'steps': 101783, 'loss/train': 1.0879567861557007} 08/31/2021 07:36:16 - INFO - __main__ - Step 101785: {'lr': 0.00011990062451453778, 'samples': 19542720, 'steps': 101784, 'loss/train': 1.1791664361953735} 08/31/2021 07:36:16 - INFO - __main__ - Step 101786: {'lr': 0.00011989609298673592, 'samples': 19542912, 'steps': 101785, 'loss/train': 0.2146679013967514} 08/31/2021 07:36:16 - INFO - __main__ - Step 101787: {'lr': 0.00011989156151755689, 'samples': 19543104, 'steps': 101786, 'loss/train': 0.9884822964668274} 08/31/2021 07:36:18 - INFO - __main__ - Step 101788: {'lr': 0.00011988703010700269, 'samples': 19543296, 'steps': 101787, 'loss/train': 0.820283055305481} 08/31/2021 07:36:19 - INFO - __main__ - Step 101789: {'lr': 0.0001198824987550754, 'samples': 19543488, 'steps': 101788, 'loss/train': 1.1499149799346924} 08/31/2021 07:36:19 - INFO - __main__ - Step 101790: {'lr': 0.00011987796746177704, 'samples': 19543680, 'steps': 101789, 'loss/train': 1.1362484693527222} 08/31/2021 07:36:19 - INFO - __main__ - Step 101791: {'lr': 0.00011987343622710966, 'samples': 19543872, 'steps': 101790, 'loss/train': 1.2439619302749634} 08/31/2021 07:36:20 - INFO - __main__ - Step 101792: {'lr': 0.00011986890505107531, 'samples': 19544064, 'steps': 101791, 'loss/train': 0.04069872200489044} 08/31/2021 07:36:20 - INFO - __main__ - Step 101793: {'lr': 0.00011986437393367602, 'samples': 19544256, 'steps': 101792, 'loss/train': 0.04550565034151077} 08/31/2021 07:36:22 - INFO - __main__ - Step 101794: {'lr': 0.00011985984287491383, 'samples': 19544448, 'steps': 101793, 'loss/train': 0.964624285697937} 08/31/2021 07:36:23 - INFO - __main__ - Step 101795: {'lr': 0.0001198553118747909, 'samples': 19544640, 'steps': 101794, 'loss/train': 1.341532826423645} 08/31/2021 07:36:23 - INFO - __main__ - Step 101796: {'lr': 0.00011985078093330904, 'samples': 19544832, 'steps': 101795, 'loss/train': 0.6258386373519897} 08/31/2021 07:36:23 - INFO - __main__ - Step 101797: {'lr': 0.00011984625005047042, 'samples': 19545024, 'steps': 101796, 'loss/train': 0.3887024521827698} 08/31/2021 07:36:24 - INFO - __main__ - Step 101798: {'lr': 0.00011984171922627707, 'samples': 19545216, 'steps': 101797, 'loss/train': 1.1444092988967896} 08/31/2021 07:36:25 - INFO - __main__ - Step 101799: {'lr': 0.00011983718846073103, 'samples': 19545408, 'steps': 101798, 'loss/train': 1.5743343830108643} 08/31/2021 07:36:26 - INFO - __main__ - Step 101800: {'lr': 0.00011983265775383434, 'samples': 19545600, 'steps': 101799, 'loss/train': 1.1305897235870361} 08/31/2021 07:36:26 - INFO - __main__ - Step 101801: {'lr': 0.00011982812710558905, 'samples': 19545792, 'steps': 101800, 'loss/train': 0.08833718299865723} 08/31/2021 07:36:27 - INFO - __main__ - Step 101802: {'lr': 0.0001198235965159972, 'samples': 19545984, 'steps': 101801, 'loss/train': 0.8112149238586426} 08/31/2021 07:36:27 - INFO - __main__ - Step 101803: {'lr': 0.00011981906598506084, 'samples': 19546176, 'steps': 101802, 'loss/train': 1.4985417127609253} 08/31/2021 07:36:28 - INFO - __main__ - Step 101804: {'lr': 0.00011981453551278199, 'samples': 19546368, 'steps': 101803, 'loss/train': 1.2465969324111938} 08/31/2021 07:36:29 - INFO - __main__ - Step 101805: {'lr': 0.0001198100050991627, 'samples': 19546560, 'steps': 101804, 'loss/train': 1.2840193510055542} 08/31/2021 07:36:29 - INFO - __main__ - Step 101806: {'lr': 0.000119805474744205, 'samples': 19546752, 'steps': 101805, 'loss/train': 1.7172293663024902} 08/31/2021 07:36:30 - INFO - __main__ - Step 101807: {'lr': 0.00011980094444791095, 'samples': 19546944, 'steps': 101806, 'loss/train': 1.6799023151397705} 08/31/2021 07:36:30 - INFO - __main__ - Step 101808: {'lr': 0.00011979641421028261, 'samples': 19547136, 'steps': 101807, 'loss/train': 0.6412171125411987} 08/31/2021 07:36:32 - INFO - __main__ - Step 101809: {'lr': 0.00011979188403132207, 'samples': 19547328, 'steps': 101808, 'loss/train': 1.1134737730026245} 08/31/2021 07:36:32 - INFO - __main__ - Step 101810: {'lr': 0.00011978735391103122, 'samples': 19547520, 'steps': 101809, 'loss/train': 1.4133079051971436} 08/31/2021 07:36:32 - INFO - __main__ - Step 101811: {'lr': 0.00011978282384941214, 'samples': 19547712, 'steps': 101810, 'loss/train': 0.9458695650100708} 08/31/2021 07:36:33 - INFO - __main__ - Step 101812: {'lr': 0.00011977829384646694, 'samples': 19547904, 'steps': 101811, 'loss/train': 1.5958133935928345} 08/31/2021 07:36:33 - INFO - __main__ - Step 101813: {'lr': 0.00011977376390219764, 'samples': 19548096, 'steps': 101812, 'loss/train': 0.813469648361206} 08/31/2021 07:36:33 - INFO - __main__ - Step 101814: {'lr': 0.00011976923401660625, 'samples': 19548288, 'steps': 101813, 'loss/train': 1.676626205444336} 08/31/2021 07:36:35 - INFO - __main__ - Step 101815: {'lr': 0.00011976470418969485, 'samples': 19548480, 'steps': 101814, 'loss/train': 0.32229161262512207} 08/31/2021 07:36:36 - INFO - __main__ - Step 101816: {'lr': 0.00011976017442146545, 'samples': 19548672, 'steps': 101815, 'loss/train': 0.36683329939842224} 08/31/2021 07:36:36 - INFO - __main__ - Step 101817: {'lr': 0.0001197556447119201, 'samples': 19548864, 'steps': 101816, 'loss/train': 1.3823310136795044} 08/31/2021 07:36:37 - INFO - __main__ - Step 101818: {'lr': 0.00011975111506106087, 'samples': 19549056, 'steps': 101817, 'loss/train': 0.9989871382713318} 08/31/2021 07:36:37 - INFO - __main__ - Step 101819: {'lr': 0.00011974658546888977, 'samples': 19549248, 'steps': 101818, 'loss/train': 0.750559389591217} 08/31/2021 07:36:38 - INFO - __main__ - Step 101820: {'lr': 0.00011974205593540884, 'samples': 19549440, 'steps': 101819, 'loss/train': 1.5654600858688354} 08/31/2021 07:36:39 - INFO - __main__ - Step 101821: {'lr': 0.00011973752646062014, 'samples': 19549632, 'steps': 101820, 'loss/train': 1.066489338874817} 08/31/2021 07:36:39 - INFO - __main__ - Step 101822: {'lr': 0.00011973299704452581, 'samples': 19549824, 'steps': 101821, 'loss/train': 1.1675504446029663} 08/31/2021 07:36:40 - INFO - __main__ - Step 101823: {'lr': 0.00011972846768712764, 'samples': 19550016, 'steps': 101822, 'loss/train': 1.3536454439163208} 08/31/2021 07:36:40 - INFO - __main__ - Step 101824: {'lr': 0.00011972393838842785, 'samples': 19550208, 'steps': 101823, 'loss/train': 1.437849998474121} 08/31/2021 07:36:40 - INFO - __main__ - Step 101825: {'lr': 0.00011971940914842843, 'samples': 19550400, 'steps': 101824, 'loss/train': 1.3064666986465454} 08/31/2021 07:36:42 - INFO - __main__ - Step 101826: {'lr': 0.00011971487996713146, 'samples': 19550592, 'steps': 101825, 'loss/train': 2.7134954929351807} 08/31/2021 07:36:42 - INFO - __main__ - Step 101827: {'lr': 0.0001197103508445389, 'samples': 19550784, 'steps': 101826, 'loss/train': 1.4025382995605469} 08/31/2021 07:36:43 - INFO - __main__ - Step 101828: {'lr': 0.00011970582178065289, 'samples': 19550976, 'steps': 101827, 'loss/train': 1.4365936517715454} 08/31/2021 07:36:43 - INFO - __main__ - Step 101829: {'lr': 0.00011970129277547542, 'samples': 19551168, 'steps': 101828, 'loss/train': 1.3447604179382324} 08/31/2021 07:36:43 - INFO - __main__ - Step 101830: {'lr': 0.00011969676382900852, 'samples': 19551360, 'steps': 101829, 'loss/train': 0.7315950989723206} 08/31/2021 07:36:45 - INFO - __main__ - Step 101831: {'lr': 0.00011969223494125425, 'samples': 19551552, 'steps': 101830, 'loss/train': 1.5577137470245361} 08/31/2021 07:36:45 - INFO - __main__ - Step 101832: {'lr': 0.00011968770611221466, 'samples': 19551744, 'steps': 101831, 'loss/train': 1.005232810974121} 08/31/2021 07:36:46 - INFO - __main__ - Step 101833: {'lr': 0.0001196831773418918, 'samples': 19551936, 'steps': 101832, 'loss/train': 1.3543695211410522} 08/31/2021 07:36:46 - INFO - __main__ - Step 101834: {'lr': 0.00011967864863028765, 'samples': 19552128, 'steps': 101833, 'loss/train': 0.9161190986633301} 08/31/2021 07:36:46 - INFO - __main__ - Step 101835: {'lr': 0.00011967411997740429, 'samples': 19552320, 'steps': 101834, 'loss/train': 0.7434133887290955} 08/31/2021 07:36:48 - INFO - __main__ - Step 101836: {'lr': 0.00011966959138324387, 'samples': 19552512, 'steps': 101835, 'loss/train': 0.3166797459125519} 08/31/2021 07:36:48 - INFO - __main__ - Step 101837: {'lr': 0.00011966506284780823, 'samples': 19552704, 'steps': 101836, 'loss/train': 1.6064200401306152} 08/31/2021 07:36:49 - INFO - __main__ - Step 101838: {'lr': 0.0001196605343710995, 'samples': 19552896, 'steps': 101837, 'loss/train': 1.1222525835037231} 08/31/2021 07:36:49 - INFO - __main__ - Step 101839: {'lr': 0.00011965600595311973, 'samples': 19553088, 'steps': 101838, 'loss/train': 1.0783799886703491} 08/31/2021 07:36:49 - INFO - __main__ - Step 101840: {'lr': 0.00011965147759387093, 'samples': 19553280, 'steps': 101839, 'loss/train': 1.419423222541809} 08/31/2021 07:36:51 - INFO - __main__ - Step 101841: {'lr': 0.00011964694929335517, 'samples': 19553472, 'steps': 101840, 'loss/train': 1.1689882278442383} 08/31/2021 07:36:51 - INFO - __main__ - Step 101842: {'lr': 0.0001196424210515745, 'samples': 19553664, 'steps': 101841, 'loss/train': 0.4398871064186096} 08/31/2021 07:36:52 - INFO - __main__ - Step 101843: {'lr': 0.00011963789286853093, 'samples': 19553856, 'steps': 101842, 'loss/train': 1.5545480251312256} 08/31/2021 07:36:52 - INFO - __main__ - Step 101844: {'lr': 0.0001196333647442265, 'samples': 19554048, 'steps': 101843, 'loss/train': 1.5330102443695068} 08/31/2021 07:36:52 - INFO - __main__ - Step 101845: {'lr': 0.00011962883667866328, 'samples': 19554240, 'steps': 101844, 'loss/train': 0.666790246963501} 08/31/2021 07:36:53 - INFO - __main__ - Step 101846: {'lr': 0.00011962430867184329, 'samples': 19554432, 'steps': 101845, 'loss/train': 0.9670796990394592} 08/31/2021 07:36:55 - INFO - __main__ - Step 101847: {'lr': 0.00011961978072376859, 'samples': 19554624, 'steps': 101846, 'loss/train': 1.208627700805664} 08/31/2021 07:36:56 - INFO - __main__ - Step 101848: {'lr': 0.0001196152528344413, 'samples': 19554816, 'steps': 101847, 'loss/train': 1.0138139724731445} 08/31/2021 07:36:56 - INFO - __main__ - Step 101849: {'lr': 0.00011961072500386325, 'samples': 19555008, 'steps': 101848, 'loss/train': 0.8144997954368591} 08/31/2021 07:36:56 - INFO - __main__ - Step 101850: {'lr': 0.00011960619723203662, 'samples': 19555200, 'steps': 101849, 'loss/train': 0.8016435503959656} 08/31/2021 07:36:57 - INFO - __main__ - Step 101851: {'lr': 0.00011960166951896339, 'samples': 19555392, 'steps': 101850, 'loss/train': 0.029232554137706757} 08/31/2021 07:36:58 - INFO - __main__ - Step 101852: {'lr': 0.00011959714186464566, 'samples': 19555584, 'steps': 101851, 'loss/train': 0.16572506725788116} 08/31/2021 07:36:59 - INFO - __main__ - Step 101853: {'lr': 0.00011959261426908544, 'samples': 19555776, 'steps': 101852, 'loss/train': 1.2063926458358765} 08/31/2021 07:36:59 - INFO - __main__ - Step 101854: {'lr': 0.00011958808673228477, 'samples': 19555968, 'steps': 101853, 'loss/train': 0.449612557888031} 08/31/2021 07:37:00 - INFO - __main__ - Step 101855: {'lr': 0.0001195835592542457, 'samples': 19556160, 'steps': 101854, 'loss/train': 1.4171371459960938} 08/31/2021 07:37:00 - INFO - __main__ - Step 101856: {'lr': 0.00011957903183497026, 'samples': 19556352, 'steps': 101855, 'loss/train': 1.582789421081543} 08/31/2021 07:37:01 - INFO - __main__ - Step 101857: {'lr': 0.0001195745044744605, 'samples': 19556544, 'steps': 101856, 'loss/train': 1.3010153770446777} 08/31/2021 07:37:02 - INFO - __main__ - Step 101858: {'lr': 0.00011956997717271848, 'samples': 19556736, 'steps': 101857, 'loss/train': 0.9452726244926453} 08/31/2021 07:37:02 - INFO - __main__ - Step 101859: {'lr': 0.00011956544992974628, 'samples': 19556928, 'steps': 101858, 'loss/train': 1.0692058801651} 08/31/2021 07:37:03 - INFO - __main__ - Step 101860: {'lr': 0.00011956092274554579, 'samples': 19557120, 'steps': 101859, 'loss/train': 1.0057729482650757} 08/31/2021 07:37:03 - INFO - __main__ - Step 101861: {'lr': 0.00011955639562011914, 'samples': 19557312, 'steps': 101860, 'loss/train': 0.17599503695964813} 08/31/2021 07:37:04 - INFO - __main__ - Step 101862: {'lr': 0.00011955186855346836, 'samples': 19557504, 'steps': 101861, 'loss/train': 0.7957687973976135} 08/31/2021 07:37:05 - INFO - __main__ - Step 101863: {'lr': 0.00011954734154559549, 'samples': 19557696, 'steps': 101862, 'loss/train': 1.2521781921386719} 08/31/2021 07:37:05 - INFO - __main__ - Step 101864: {'lr': 0.00011954281459650257, 'samples': 19557888, 'steps': 101863, 'loss/train': 1.2889056205749512} 08/31/2021 07:37:06 - INFO - __main__ - Step 101865: {'lr': 0.00011953828770619165, 'samples': 19558080, 'steps': 101864, 'loss/train': 0.8274602890014648} 08/31/2021 07:37:06 - INFO - __main__ - Step 101866: {'lr': 0.00011953376087466478, 'samples': 19558272, 'steps': 101865, 'loss/train': 1.0070264339447021} 08/31/2021 07:37:07 - INFO - __main__ - Step 101867: {'lr': 0.00011952923410192399, 'samples': 19558464, 'steps': 101866, 'loss/train': 1.3254059553146362} 08/31/2021 07:37:08 - INFO - __main__ - Step 101868: {'lr': 0.00011952470738797128, 'samples': 19558656, 'steps': 101867, 'loss/train': 0.7881344556808472} 08/31/2021 07:37:08 - INFO - __main__ - Step 101869: {'lr': 0.00011952018073280873, 'samples': 19558848, 'steps': 101868, 'loss/train': 1.5274543762207031} 08/31/2021 07:37:09 - INFO - __main__ - Step 101870: {'lr': 0.0001195156541364385, 'samples': 19559040, 'steps': 101869, 'loss/train': 1.064880609512329} 08/31/2021 07:37:09 - INFO - __main__ - Step 101871: {'lr': 0.00011951112759886237, 'samples': 19559232, 'steps': 101870, 'loss/train': 0.6002642512321472} 08/31/2021 07:37:10 - INFO - __main__ - Step 101872: {'lr': 0.00011950660112008255, 'samples': 19559424, 'steps': 101871, 'loss/train': 1.0321801900863647} 08/31/2021 07:37:11 - INFO - __main__ - Step 101873: {'lr': 0.00011950207470010103, 'samples': 19559616, 'steps': 101872, 'loss/train': 0.7628198862075806} 08/31/2021 07:37:11 - INFO - __main__ - Step 101874: {'lr': 0.00011949754833891981, 'samples': 19559808, 'steps': 101873, 'loss/train': 1.1791030168533325} 08/31/2021 07:37:12 - INFO - __main__ - Step 101875: {'lr': 0.00011949302203654105, 'samples': 19560000, 'steps': 101874, 'loss/train': 1.254225254058838} 08/31/2021 07:37:12 - INFO - __main__ - Step 101876: {'lr': 0.00011948849579296669, 'samples': 19560192, 'steps': 101875, 'loss/train': 1.4287163019180298} 08/31/2021 07:37:13 - INFO - __main__ - Step 101877: {'lr': 0.00011948396960819879, 'samples': 19560384, 'steps': 101876, 'loss/train': 1.141016960144043} 08/31/2021 07:37:14 - INFO - __main__ - Step 101878: {'lr': 0.00011947944348223944, 'samples': 19560576, 'steps': 101877, 'loss/train': 0.9054498076438904} 08/31/2021 07:37:14 - INFO - __main__ - Step 101879: {'lr': 0.00011947491741509059, 'samples': 19560768, 'steps': 101878, 'loss/train': 1.1686080694198608} 08/31/2021 07:37:15 - INFO - __main__ - Step 101880: {'lr': 0.00011947039140675436, 'samples': 19560960, 'steps': 101879, 'loss/train': 1.3726481199264526} 08/31/2021 07:37:15 - INFO - __main__ - Step 101881: {'lr': 0.00011946586545723284, 'samples': 19561152, 'steps': 101880, 'loss/train': 1.0781656503677368} 08/31/2021 07:37:16 - INFO - __main__ - Step 101882: {'lr': 0.00011946133956652788, 'samples': 19561344, 'steps': 101881, 'loss/train': 0.8813005089759827} 08/31/2021 07:37:17 - INFO - __main__ - Step 101883: {'lr': 0.00011945681373464166, 'samples': 19561536, 'steps': 101882, 'loss/train': 0.9161784052848816} 08/31/2021 07:37:17 - INFO - __main__ - Step 101884: {'lr': 0.00011945228796157614, 'samples': 19561728, 'steps': 101883, 'loss/train': 0.9746947288513184} 08/31/2021 07:37:18 - INFO - __main__ - Step 101885: {'lr': 0.00011944776224733345, 'samples': 19561920, 'steps': 101884, 'loss/train': 0.4681336283683777} 08/31/2021 07:37:18 - INFO - __main__ - Step 101886: {'lr': 0.00011944323659191556, 'samples': 19562112, 'steps': 101885, 'loss/train': 0.9414152503013611} 08/31/2021 07:37:18 - INFO - __main__ - Step 101887: {'lr': 0.00011943871099532455, 'samples': 19562304, 'steps': 101886, 'loss/train': 1.2755566835403442} 08/31/2021 07:37:20 - INFO - __main__ - Step 101888: {'lr': 0.0001194341854575624, 'samples': 19562496, 'steps': 101887, 'loss/train': 1.5627098083496094} 08/31/2021 07:37:20 - INFO - __main__ - Step 101889: {'lr': 0.00011942965997863123, 'samples': 19562688, 'steps': 101888, 'loss/train': 1.0239843130111694} 08/31/2021 07:37:21 - INFO - __main__ - Step 101890: {'lr': 0.00011942513455853305, 'samples': 19562880, 'steps': 101889, 'loss/train': 1.289617896080017} 08/31/2021 07:37:21 - INFO - __main__ - Step 101891: {'lr': 0.00011942060919726985, 'samples': 19563072, 'steps': 101890, 'loss/train': 0.1227954775094986} 08/31/2021 07:37:21 - INFO - __main__ - Step 101892: {'lr': 0.00011941608389484381, 'samples': 19563264, 'steps': 101891, 'loss/train': 1.9497361183166504} 08/31/2021 07:37:23 - INFO - __main__ - Step 101893: {'lr': 0.0001194115586512568, 'samples': 19563456, 'steps': 101892, 'loss/train': 1.4323210716247559} 08/31/2021 07:37:23 - INFO - __main__ - Step 101894: {'lr': 0.00011940703346651091, 'samples': 19563648, 'steps': 101893, 'loss/train': 1.7373088598251343} 08/31/2021 07:37:24 - INFO - __main__ - Step 101895: {'lr': 0.00011940250834060821, 'samples': 19563840, 'steps': 101894, 'loss/train': 0.9150209426879883} 08/31/2021 07:37:24 - INFO - __main__ - Step 101896: {'lr': 0.0001193979832735507, 'samples': 19564032, 'steps': 101895, 'loss/train': 1.4116333723068237} 08/31/2021 07:37:24 - INFO - __main__ - Step 101897: {'lr': 0.00011939345826534046, 'samples': 19564224, 'steps': 101896, 'loss/train': 1.4184556007385254} 08/31/2021 07:37:26 - INFO - __main__ - Step 101898: {'lr': 0.00011938893331597953, 'samples': 19564416, 'steps': 101897, 'loss/train': 1.8559037446975708} 08/31/2021 07:37:27 - INFO - __main__ - Step 101899: {'lr': 0.00011938440842546991, 'samples': 19564608, 'steps': 101898, 'loss/train': 1.001936435699463} 08/31/2021 07:37:27 - INFO - __main__ - Step 101900: {'lr': 0.00011937988359381363, 'samples': 19564800, 'steps': 101899, 'loss/train': 0.9874993562698364} 08/31/2021 07:37:28 - INFO - __main__ - Step 101901: {'lr': 0.00011937535882101281, 'samples': 19564992, 'steps': 101900, 'loss/train': 0.9433104395866394} 08/31/2021 07:37:28 - INFO - __main__ - Step 101902: {'lr': 0.00011937083410706942, 'samples': 19565184, 'steps': 101901, 'loss/train': 1.4475809335708618} 08/31/2021 07:37:29 - INFO - __main__ - Step 101903: {'lr': 0.0001193663094519856, 'samples': 19565376, 'steps': 101902, 'loss/train': 1.2724635601043701} 08/31/2021 07:37:30 - INFO - __main__ - Step 101904: {'lr': 0.00011936178485576321, 'samples': 19565568, 'steps': 101903, 'loss/train': 1.251541018486023} 08/31/2021 07:37:30 - INFO - __main__ - Step 101905: {'lr': 0.00011935726031840441, 'samples': 19565760, 'steps': 101904, 'loss/train': 0.4848887026309967} 08/31/2021 07:37:31 - INFO - __main__ - Step 101906: {'lr': 0.00011935273583991118, 'samples': 19565952, 'steps': 101905, 'loss/train': 1.0919172763824463} 08/31/2021 07:37:31 - INFO - __main__ - Step 101907: {'lr': 0.0001193482114202856, 'samples': 19566144, 'steps': 101906, 'loss/train': 1.1335978507995605} 08/31/2021 07:37:33 - INFO - __main__ - Step 101908: {'lr': 0.00011934368705952972, 'samples': 19566336, 'steps': 101907, 'loss/train': 1.3675241470336914} 08/31/2021 07:37:33 - INFO - __main__ - Step 101909: {'lr': 0.00011933916275764553, 'samples': 19566528, 'steps': 101908, 'loss/train': 0.9032924771308899} 08/31/2021 07:37:33 - INFO - __main__ - Step 101910: {'lr': 0.0001193346385146351, 'samples': 19566720, 'steps': 101909, 'loss/train': 0.2541126012802124} 08/31/2021 07:37:34 - INFO - __main__ - Step 101911: {'lr': 0.00011933011433050051, 'samples': 19566912, 'steps': 101910, 'loss/train': 1.6070866584777832} 08/31/2021 07:37:34 - INFO - __main__ - Step 101912: {'lr': 0.0001193255902052437, 'samples': 19567104, 'steps': 101911, 'loss/train': 0.6116580963134766} 08/31/2021 07:37:34 - INFO - __main__ - Step 101913: {'lr': 0.00011932106613886678, 'samples': 19567296, 'steps': 101912, 'loss/train': 1.2091001272201538} 08/31/2021 07:37:36 - INFO - __main__ - Step 101914: {'lr': 0.00011931654213137177, 'samples': 19567488, 'steps': 101913, 'loss/train': 1.1120291948318481} 08/31/2021 07:37:36 - INFO - __main__ - Step 101915: {'lr': 0.00011931201818276072, 'samples': 19567680, 'steps': 101914, 'loss/train': 0.6813705563545227} 08/31/2021 07:37:37 - INFO - __main__ - Step 101916: {'lr': 0.00011930749429303576, 'samples': 19567872, 'steps': 101915, 'loss/train': 0.973353922367096} 08/31/2021 07:37:37 - INFO - __main__ - Step 101917: {'lr': 0.00011930297046219871, 'samples': 19568064, 'steps': 101916, 'loss/train': 0.9496330618858337} 08/31/2021 07:37:37 - INFO - __main__ - Step 101918: {'lr': 0.00011929844669025172, 'samples': 19568256, 'steps': 101917, 'loss/train': 0.826167106628418} 08/31/2021 07:37:39 - INFO - __main__ - Step 101919: {'lr': 0.00011929392297719685, 'samples': 19568448, 'steps': 101918, 'loss/train': 0.9577308297157288} 08/31/2021 07:37:40 - INFO - __main__ - Step 101920: {'lr': 0.00011928939932303612, 'samples': 19568640, 'steps': 101919, 'loss/train': 0.7959800362586975} 08/31/2021 07:37:40 - INFO - __main__ - Step 101921: {'lr': 0.00011928487572777158, 'samples': 19568832, 'steps': 101920, 'loss/train': 0.8600114583969116} 08/31/2021 07:37:41 - INFO - __main__ - Step 101922: {'lr': 0.00011928035219140523, 'samples': 19569024, 'steps': 101921, 'loss/train': 0.037047673016786575} 08/31/2021 07:37:41 - INFO - __main__ - Step 101923: {'lr': 0.00011927582871393916, 'samples': 19569216, 'steps': 101922, 'loss/train': 1.0062159299850464} 08/31/2021 07:37:43 - INFO - __main__ - Step 101924: {'lr': 0.00011927130529537538, 'samples': 19569408, 'steps': 101923, 'loss/train': 0.6935502886772156} 08/31/2021 07:37:43 - INFO - __main__ - Step 101925: {'lr': 0.00011926678193571592, 'samples': 19569600, 'steps': 101924, 'loss/train': 0.11541688442230225} 08/31/2021 07:37:44 - INFO - __main__ - Step 101926: {'lr': 0.00011926225863496285, 'samples': 19569792, 'steps': 101925, 'loss/train': 1.394673466682434} 08/31/2021 07:37:44 - INFO - __main__ - Step 101927: {'lr': 0.00011925773539311816, 'samples': 19569984, 'steps': 101926, 'loss/train': 0.7199193835258484} 08/31/2021 07:37:44 - INFO - __main__ - Step 101928: {'lr': 0.00011925321221018396, 'samples': 19570176, 'steps': 101927, 'loss/train': 0.5570936799049377} 08/31/2021 07:37:46 - INFO - __main__ - Step 101929: {'lr': 0.00011924868908616222, 'samples': 19570368, 'steps': 101928, 'loss/train': 1.3484402894973755} 08/31/2021 07:37:46 - INFO - __main__ - Step 101930: {'lr': 0.00011924416602105508, 'samples': 19570560, 'steps': 101929, 'loss/train': 1.2130367755889893} 08/31/2021 07:37:47 - INFO - __main__ - Step 101931: {'lr': 0.00011923964301486442, 'samples': 19570752, 'steps': 101930, 'loss/train': 0.676175594329834} 08/31/2021 07:37:47 - INFO - __main__ - Step 101932: {'lr': 0.00011923512006759238, 'samples': 19570944, 'steps': 101931, 'loss/train': 1.2905724048614502} 08/31/2021 07:37:47 - INFO - __main__ - Step 101933: {'lr': 0.00011923059717924095, 'samples': 19571136, 'steps': 101932, 'loss/train': 1.91047203540802} 08/31/2021 07:37:48 - INFO - __main__ - Step 101934: {'lr': 0.0001192260743498122, 'samples': 19571328, 'steps': 101933, 'loss/train': 0.611297070980072} 08/31/2021 07:37:49 - INFO - __main__ - Step 101935: {'lr': 0.00011922155157930816, 'samples': 19571520, 'steps': 101934, 'loss/train': 1.6605281829833984} 08/31/2021 07:37:50 - INFO - __main__ - Step 101936: {'lr': 0.00011921702886773089, 'samples': 19571712, 'steps': 101935, 'loss/train': 1.1638939380645752} 08/31/2021 07:37:50 - INFO - __main__ - Step 101937: {'lr': 0.0001192125062150824, 'samples': 19571904, 'steps': 101936, 'loss/train': 1.2288395166397095} 08/31/2021 07:37:51 - INFO - __main__ - Step 101938: {'lr': 0.00011920798362136472, 'samples': 19572096, 'steps': 101937, 'loss/train': 1.4301509857177734} 08/31/2021 07:37:51 - INFO - __main__ - Step 101939: {'lr': 0.00011920346108657992, 'samples': 19572288, 'steps': 101938, 'loss/train': 1.2524826526641846} 08/31/2021 07:37:52 - INFO - __main__ - Step 101940: {'lr': 0.00011919893861073003, 'samples': 19572480, 'steps': 101939, 'loss/train': 1.7352874279022217} 08/31/2021 07:37:53 - INFO - __main__ - Step 101941: {'lr': 0.00011919441619381708, 'samples': 19572672, 'steps': 101940, 'loss/train': 0.4791563153266907} 08/31/2021 07:37:53 - INFO - __main__ - Step 101942: {'lr': 0.00011918989383584308, 'samples': 19572864, 'steps': 101941, 'loss/train': 1.2807728052139282} 08/31/2021 07:37:54 - INFO - __main__ - Step 101943: {'lr': 0.00011918537153681022, 'samples': 19573056, 'steps': 101942, 'loss/train': 0.9421918988227844} 08/31/2021 07:37:54 - INFO - __main__ - Step 101944: {'lr': 0.00011918084929672029, 'samples': 19573248, 'steps': 101943, 'loss/train': 1.2774271965026855} 08/31/2021 07:37:56 - INFO - __main__ - Step 101945: {'lr': 0.00011917632711557547, 'samples': 19573440, 'steps': 101944, 'loss/train': 1.3000602722167969} 08/31/2021 07:37:56 - INFO - __main__ - Step 101946: {'lr': 0.0001191718049933778, 'samples': 19573632, 'steps': 101945, 'loss/train': 0.015683922916650772} 08/31/2021 07:37:57 - INFO - __main__ - Step 101947: {'lr': 0.00011916728293012927, 'samples': 19573824, 'steps': 101946, 'loss/train': 1.1667133569717407} 08/31/2021 07:37:57 - INFO - __main__ - Step 101948: {'lr': 0.00011916276092583191, 'samples': 19574016, 'steps': 101947, 'loss/train': 0.07763542979955673} 08/31/2021 07:37:57 - INFO - __main__ - Step 101949: {'lr': 0.00011915823898048784, 'samples': 19574208, 'steps': 101948, 'loss/train': 0.05898617208003998} 08/31/2021 07:37:58 - INFO - __main__ - Step 101950: {'lr': 0.00011915371709409903, 'samples': 19574400, 'steps': 101949, 'loss/train': 0.8875890970230103} 08/31/2021 07:38:00 - INFO - __main__ - Step 101951: {'lr': 0.00011914919526666753, 'samples': 19574592, 'steps': 101950, 'loss/train': 0.9284489154815674} 08/31/2021 07:38:00 - INFO - __main__ - Step 101952: {'lr': 0.00011914467349819542, 'samples': 19574784, 'steps': 101951, 'loss/train': 1.2763739824295044} 08/31/2021 07:38:01 - INFO - __main__ - Step 101953: {'lr': 0.00011914015178868468, 'samples': 19574976, 'steps': 101952, 'loss/train': 1.323026180267334} 08/31/2021 07:38:01 - INFO - __main__ - Step 101954: {'lr': 0.00011913563013813735, 'samples': 19575168, 'steps': 101953, 'loss/train': 0.6880312561988831} 08/31/2021 07:38:01 - INFO - __main__ - Step 101955: {'lr': 0.00011913110854655549, 'samples': 19575360, 'steps': 101954, 'loss/train': 0.5918450951576233} 08/31/2021 07:38:03 - INFO - __main__ - Step 101956: {'lr': 0.00011912658701394113, 'samples': 19575552, 'steps': 101955, 'loss/train': 0.20933429896831512} 08/31/2021 07:38:04 - INFO - __main__ - Step 101957: {'lr': 0.00011912206554029645, 'samples': 19575744, 'steps': 101956, 'loss/train': 1.0501102209091187} 08/31/2021 07:38:04 - INFO - __main__ - Step 101958: {'lr': 0.0001191175441256232, 'samples': 19575936, 'steps': 101957, 'loss/train': 1.2773123979568481} 08/31/2021 07:38:05 - INFO - __main__ - Step 101959: {'lr': 0.00011911302276992358, 'samples': 19576128, 'steps': 101958, 'loss/train': 1.0572246313095093} 08/31/2021 07:38:05 - INFO - __main__ - Step 101960: {'lr': 0.00011910850147319962, 'samples': 19576320, 'steps': 101959, 'loss/train': 0.7359774708747864} 08/31/2021 07:38:07 - INFO - __main__ - Step 101961: {'lr': 0.00011910398023545336, 'samples': 19576512, 'steps': 101960, 'loss/train': 1.0663259029388428} 08/31/2021 07:38:07 - INFO - __main__ - Step 101962: {'lr': 0.00011909945905668682, 'samples': 19576704, 'steps': 101961, 'loss/train': 1.5741603374481201} 08/31/2021 07:38:07 - INFO - __main__ - Step 101963: {'lr': 0.00011909493793690201, 'samples': 19576896, 'steps': 101962, 'loss/train': 0.8224965333938599} 08/31/2021 07:38:08 - INFO - __main__ - Step 101964: {'lr': 0.00011909041687610104, 'samples': 19577088, 'steps': 101963, 'loss/train': 0.6301760077476501} 08/31/2021 07:38:08 - INFO - __main__ - Step 101965: {'lr': 0.00011908589587428589, 'samples': 19577280, 'steps': 101964, 'loss/train': 0.8702564835548401} 08/31/2021 07:38:08 - INFO - __main__ - Step 101966: {'lr': 0.00011908137493145862, 'samples': 19577472, 'steps': 101965, 'loss/train': 0.61788409948349} 08/31/2021 07:38:10 - INFO - __main__ - Step 101967: {'lr': 0.00011907685404762128, 'samples': 19577664, 'steps': 101966, 'loss/train': 0.0514795146882534} 08/31/2021 07:38:11 - INFO - __main__ - Step 101968: {'lr': 0.00011907233322277586, 'samples': 19577856, 'steps': 101967, 'loss/train': 1.350290060043335} 08/31/2021 07:38:11 - INFO - __main__ - Step 101969: {'lr': 0.00011906781245692444, 'samples': 19578048, 'steps': 101968, 'loss/train': 1.051469326019287} 08/31/2021 07:38:12 - INFO - __main__ - Step 101970: {'lr': 0.00011906329175006914, 'samples': 19578240, 'steps': 101969, 'loss/train': 0.08108965307474136} 08/31/2021 07:38:12 - INFO - __main__ - Step 101971: {'lr': 0.00011905877110221181, 'samples': 19578432, 'steps': 101970, 'loss/train': 0.1688804179430008} 08/31/2021 07:38:14 - INFO - __main__ - Step 101972: {'lr': 0.00011905425051335456, 'samples': 19578624, 'steps': 101971, 'loss/train': 0.7694299817085266} 08/31/2021 07:38:14 - INFO - __main__ - Step 101973: {'lr': 0.00011904972998349945, 'samples': 19578816, 'steps': 101972, 'loss/train': 1.3586955070495605} 08/31/2021 07:38:14 - INFO - __main__ - Step 101974: {'lr': 0.00011904520951264852, 'samples': 19579008, 'steps': 101973, 'loss/train': 1.664488434791565} 08/31/2021 07:38:15 - INFO - __main__ - Step 101975: {'lr': 0.00011904068910080379, 'samples': 19579200, 'steps': 101974, 'loss/train': 1.6537431478500366} 08/31/2021 07:38:15 - INFO - __main__ - Step 101976: {'lr': 0.0001190361687479673, 'samples': 19579392, 'steps': 101975, 'loss/train': 1.2180429697036743} 08/31/2021 07:38:16 - INFO - __main__ - Step 101977: {'lr': 0.00011903164845414111, 'samples': 19579584, 'steps': 101976, 'loss/train': 1.0174568891525269} 08/31/2021 07:38:17 - INFO - __main__ - Step 101978: {'lr': 0.0001190271282193272, 'samples': 19579776, 'steps': 101977, 'loss/train': 1.29668128490448} 08/31/2021 07:38:17 - INFO - __main__ - Step 101979: {'lr': 0.00011902260804352769, 'samples': 19579968, 'steps': 101978, 'loss/train': 1.5157408714294434} 08/31/2021 07:38:18 - INFO - __main__ - Step 101980: {'lr': 0.00011901808792674457, 'samples': 19580160, 'steps': 101979, 'loss/train': 1.1899563074111938} 08/31/2021 07:38:18 - INFO - __main__ - Step 101981: {'lr': 0.00011901356786897985, 'samples': 19580352, 'steps': 101980, 'loss/train': 1.0989189147949219} 08/31/2021 07:38:20 - INFO - __main__ - Step 101982: {'lr': 0.00011900904787023562, 'samples': 19580544, 'steps': 101981, 'loss/train': 1.2159123420715332} 08/31/2021 07:38:20 - INFO - __main__ - Step 101983: {'lr': 0.00011900452793051387, 'samples': 19580736, 'steps': 101982, 'loss/train': 1.760990023612976} 08/31/2021 07:38:20 - INFO - __main__ - Step 101984: {'lr': 0.00011900000804981676, 'samples': 19580928, 'steps': 101983, 'loss/train': 1.1692445278167725} 08/31/2021 07:38:21 - INFO - __main__ - Step 101985: {'lr': 0.00011899548822814613, 'samples': 19581120, 'steps': 101984, 'loss/train': 1.0173044204711914} 08/31/2021 07:38:21 - INFO - __main__ - Step 101986: {'lr': 0.00011899096846550412, 'samples': 19581312, 'steps': 101985, 'loss/train': 1.4070183038711548} 08/31/2021 07:38:23 - INFO - __main__ - Step 101987: {'lr': 0.00011898644876189275, 'samples': 19581504, 'steps': 101986, 'loss/train': 0.6743320226669312} 08/31/2021 07:38:23 - INFO - __main__ - Step 101988: {'lr': 0.00011898192911731407, 'samples': 19581696, 'steps': 101987, 'loss/train': 0.9675386548042297} 08/31/2021 07:38:23 - INFO - __main__ - Step 101989: {'lr': 0.0001189774095317701, 'samples': 19581888, 'steps': 101988, 'loss/train': 1.3068853616714478} 08/31/2021 07:38:24 - INFO - __main__ - Step 101990: {'lr': 0.0001189728900052629, 'samples': 19582080, 'steps': 101989, 'loss/train': 1.4415392875671387} 08/31/2021 07:38:24 - INFO - __main__ - Step 101991: {'lr': 0.00011896837053779447, 'samples': 19582272, 'steps': 101990, 'loss/train': 1.1156014204025269} 08/31/2021 07:38:24 - INFO - __main__ - Step 101992: {'lr': 0.00011896385112936689, 'samples': 19582464, 'steps': 101991, 'loss/train': 0.27391767501831055} 08/31/2021 07:38:26 - INFO - __main__ - Step 101993: {'lr': 0.00011895933177998219, 'samples': 19582656, 'steps': 101992, 'loss/train': 0.5746101140975952} 08/31/2021 07:38:27 - INFO - __main__ - Step 101994: {'lr': 0.00011895481248964238, 'samples': 19582848, 'steps': 101993, 'loss/train': 0.7537217736244202} 08/31/2021 07:38:27 - INFO - __main__ - Step 101995: {'lr': 0.0001189502932583495, 'samples': 19583040, 'steps': 101994, 'loss/train': 1.874815583229065} 08/31/2021 07:38:27 - INFO - __main__ - Step 101996: {'lr': 0.0001189457740861056, 'samples': 19583232, 'steps': 101995, 'loss/train': 1.0166712999343872} 08/31/2021 07:38:28 - INFO - __main__ - Step 101997: {'lr': 0.0001189412549729128, 'samples': 19583424, 'steps': 101996, 'loss/train': 1.4758758544921875} 08/31/2021 07:38:29 - INFO - __main__ - Step 101998: {'lr': 0.00011893673591877297, 'samples': 19583616, 'steps': 101997, 'loss/train': 0.7908099293708801} 08/31/2021 07:38:30 - INFO - __main__ - Step 101999: {'lr': 0.00011893221692368822, 'samples': 19583808, 'steps': 101998, 'loss/train': 0.8867291212081909} 08/31/2021 07:38:30 - INFO - __main__ - Step 102000: {'lr': 0.0001189276979876606, 'samples': 19584000, 'steps': 101999, 'loss/train': 0.6525214910507202} 08/31/2021 07:38:31 - INFO - __main__ - Step 102001: {'lr': 0.00011892317911069211, 'samples': 19584192, 'steps': 102000, 'loss/train': 1.3691209554672241} 08/31/2021 07:38:31 - INFO - __main__ - Step 102002: {'lr': 0.00011891866029278483, 'samples': 19584384, 'steps': 102001, 'loss/train': 0.6075790524482727} 08/31/2021 07:38:33 - INFO - __main__ - Step 102003: {'lr': 0.00011891414153394078, 'samples': 19584576, 'steps': 102002, 'loss/train': 1.4283134937286377} 08/31/2021 07:38:33 - INFO - __main__ - Step 102004: {'lr': 0.00011890962283416198, 'samples': 19584768, 'steps': 102003, 'loss/train': 1.2224438190460205} 08/31/2021 07:38:34 - INFO - __main__ - Step 102005: {'lr': 0.00011890510419345049, 'samples': 19584960, 'steps': 102004, 'loss/train': 1.4514403343200684} 08/31/2021 07:38:34 - INFO - __main__ - Step 102006: {'lr': 0.00011890058561180836, 'samples': 19585152, 'steps': 102005, 'loss/train': 0.029614634811878204} 08/31/2021 07:38:34 - INFO - __main__ - Step 102007: {'lr': 0.00011889606708923759, 'samples': 19585344, 'steps': 102006, 'loss/train': 1.3734990358352661} 08/31/2021 07:38:35 - INFO - __main__ - Step 102008: {'lr': 0.0001188915486257402, 'samples': 19585536, 'steps': 102007, 'loss/train': 0.08327855914831161} 08/31/2021 07:38:37 - INFO - __main__ - Step 102009: {'lr': 0.00011888703022131827, 'samples': 19585728, 'steps': 102008, 'loss/train': 0.5021024942398071} 08/31/2021 07:38:37 - INFO - __main__ - Step 102010: {'lr': 0.00011888251187597393, 'samples': 19585920, 'steps': 102009, 'loss/train': 1.6140341758728027} 08/31/2021 07:38:38 - INFO - __main__ - Step 102011: {'lr': 0.00011887799358970902, 'samples': 19586112, 'steps': 102010, 'loss/train': 5.706700801849365} 08/31/2021 07:38:38 - INFO - __main__ - Step 102012: {'lr': 0.00011887347536252565, 'samples': 19586304, 'steps': 102011, 'loss/train': 1.3543208837509155} 08/31/2021 07:38:39 - INFO - __main__ - Step 102013: {'lr': 0.00011886895719442587, 'samples': 19586496, 'steps': 102012, 'loss/train': 1.2631746530532837} 08/31/2021 07:38:39 - INFO - __main__ - Step 102014: {'lr': 0.0001188644390854117, 'samples': 19586688, 'steps': 102013, 'loss/train': 0.017637373879551888} 08/31/2021 07:38:39 - INFO - __main__ - Step 102015: {'lr': 0.0001188599210354852, 'samples': 19586880, 'steps': 102014, 'loss/train': 1.5056143999099731} 08/31/2021 07:38:41 - INFO - __main__ - Step 102016: {'lr': 0.0001188554030446484, 'samples': 19587072, 'steps': 102015, 'loss/train': 1.0709084272384644} 08/31/2021 07:38:41 - INFO - __main__ - Step 102017: {'lr': 0.00011885088511290332, 'samples': 19587264, 'steps': 102016, 'loss/train': 1.1801300048828125} 08/31/2021 07:38:42 - INFO - __main__ - Step 102018: {'lr': 0.00011884636724025202, 'samples': 19587456, 'steps': 102017, 'loss/train': 0.6582010388374329} 08/31/2021 07:38:42 - INFO - __main__ - Step 102019: {'lr': 0.00011884184942669651, 'samples': 19587648, 'steps': 102018, 'loss/train': 1.7585289478302002} 08/31/2021 07:38:42 - INFO - __main__ - Step 102020: {'lr': 0.00011883733167223887, 'samples': 19587840, 'steps': 102019, 'loss/train': 1.4595251083374023} 08/31/2021 07:38:44 - INFO - __main__ - Step 102021: {'lr': 0.00011883281397688109, 'samples': 19588032, 'steps': 102020, 'loss/train': 1.4452036619186401} 08/31/2021 07:38:44 - INFO - __main__ - Step 102022: {'lr': 0.0001188282963406252, 'samples': 19588224, 'steps': 102021, 'loss/train': 0.4036887586116791} 08/31/2021 07:38:45 - INFO - __main__ - Step 102023: {'lr': 0.00011882377876347327, 'samples': 19588416, 'steps': 102022, 'loss/train': 0.97346431016922} 08/31/2021 07:38:45 - INFO - __main__ - Step 102024: {'lr': 0.0001188192612454274, 'samples': 19588608, 'steps': 102023, 'loss/train': 1.60884690284729} 08/31/2021 07:38:45 - INFO - __main__ - Step 102025: {'lr': 0.00011881474378648949, 'samples': 19588800, 'steps': 102024, 'loss/train': 1.141629934310913} 08/31/2021 07:38:46 - INFO - __main__ - Step 102026: {'lr': 0.00011881022638666158, 'samples': 19588992, 'steps': 102025, 'loss/train': 1.148844838142395} 08/31/2021 07:38:47 - INFO - __main__ - Step 102027: {'lr': 0.00011880570904594582, 'samples': 19589184, 'steps': 102026, 'loss/train': 0.6358899474143982} 08/31/2021 07:38:48 - INFO - __main__ - Step 102028: {'lr': 0.00011880119176434411, 'samples': 19589376, 'steps': 102027, 'loss/train': 1.0486083030700684} 08/31/2021 07:38:48 - INFO - __main__ - Step 102029: {'lr': 0.0001187966745418586, 'samples': 19589568, 'steps': 102028, 'loss/train': 0.6756696701049805} 08/31/2021 07:38:48 - INFO - __main__ - Step 102030: {'lr': 0.00011879215737849131, 'samples': 19589760, 'steps': 102029, 'loss/train': 1.7918691635131836} 08/31/2021 07:38:49 - INFO - __main__ - Step 102031: {'lr': 0.00011878764027424421, 'samples': 19589952, 'steps': 102030, 'loss/train': 1.1029574871063232} 08/31/2021 07:38:50 - INFO - __main__ - Step 102032: {'lr': 0.00011878312322911938, 'samples': 19590144, 'steps': 102031, 'loss/train': 1.1668881177902222} 08/31/2021 07:38:51 - INFO - __main__ - Step 102033: {'lr': 0.00011877860624311886, 'samples': 19590336, 'steps': 102032, 'loss/train': 1.4711824655532837} 08/31/2021 07:38:51 - INFO - __main__ - Step 102034: {'lr': 0.00011877408931624467, 'samples': 19590528, 'steps': 102033, 'loss/train': 0.7328134775161743} 08/31/2021 07:38:52 - INFO - __main__ - Step 102035: {'lr': 0.00011876957244849884, 'samples': 19590720, 'steps': 102034, 'loss/train': 1.0625429153442383} 08/31/2021 07:38:52 - INFO - __main__ - Step 102036: {'lr': 0.00011876505563988344, 'samples': 19590912, 'steps': 102035, 'loss/train': 0.41459736227989197} 08/31/2021 07:38:53 - INFO - __main__ - Step 102037: {'lr': 0.00011876053889040056, 'samples': 19591104, 'steps': 102036, 'loss/train': 1.2836765050888062} 08/31/2021 07:38:54 - INFO - __main__ - Step 102038: {'lr': 0.00011875602220005204, 'samples': 19591296, 'steps': 102037, 'loss/train': 1.2645187377929688} 08/31/2021 07:38:54 - INFO - __main__ - Step 102039: {'lr': 0.00011875150556884006, 'samples': 19591488, 'steps': 102038, 'loss/train': 1.5943396091461182} 08/31/2021 07:38:55 - INFO - __main__ - Step 102040: {'lr': 0.00011874698899676665, 'samples': 19591680, 'steps': 102039, 'loss/train': 0.06212270259857178} 08/31/2021 07:38:55 - INFO - __main__ - Step 102041: {'lr': 0.00011874247248383376, 'samples': 19591872, 'steps': 102040, 'loss/train': 1.5123398303985596} 08/31/2021 07:38:56 - INFO - __main__ - Step 102042: {'lr': 0.00011873795603004353, 'samples': 19592064, 'steps': 102041, 'loss/train': 0.8245259523391724} 08/31/2021 07:38:57 - INFO - __main__ - Step 102043: {'lr': 0.00011873343963539795, 'samples': 19592256, 'steps': 102042, 'loss/train': 1.4684809446334839} 08/31/2021 07:38:57 - INFO - __main__ - Step 102044: {'lr': 0.00011872892329989904, 'samples': 19592448, 'steps': 102043, 'loss/train': 1.422234058380127} 08/31/2021 07:38:58 - INFO - __main__ - Step 102045: {'lr': 0.00011872440702354887, 'samples': 19592640, 'steps': 102044, 'loss/train': 0.6349273920059204} 08/31/2021 07:38:58 - INFO - __main__ - Step 102046: {'lr': 0.00011871989080634943, 'samples': 19592832, 'steps': 102045, 'loss/train': 1.4136853218078613} 08/31/2021 07:38:59 - INFO - __main__ - Step 102047: {'lr': 0.00011871537464830278, 'samples': 19593024, 'steps': 102046, 'loss/train': 1.4057037830352783} 08/31/2021 07:39:00 - INFO - __main__ - Step 102048: {'lr': 0.00011871085854941099, 'samples': 19593216, 'steps': 102047, 'loss/train': 1.9728368520736694} 08/31/2021 07:39:00 - INFO - __main__ - Step 102049: {'lr': 0.00011870634250967604, 'samples': 19593408, 'steps': 102048, 'loss/train': 0.31588804721832275} 08/31/2021 07:39:01 - INFO - __main__ - Step 102050: {'lr': 0.0001187018265291, 'samples': 19593600, 'steps': 102049, 'loss/train': 0.8814945816993713} 08/31/2021 07:39:01 - INFO - __main__ - Step 102051: {'lr': 0.00011869731060768496, 'samples': 19593792, 'steps': 102050, 'loss/train': 0.7025154829025269} 08/31/2021 07:39:03 - INFO - __main__ - Step 102052: {'lr': 0.00011869279474543282, 'samples': 19593984, 'steps': 102051, 'loss/train': 0.9506757259368896} 08/31/2021 07:39:03 - INFO - __main__ - Step 102053: {'lr': 0.00011868827894234566, 'samples': 19594176, 'steps': 102052, 'loss/train': 0.9054686427116394} 08/31/2021 07:39:04 - INFO - __main__ - Step 102054: {'lr': 0.00011868376319842552, 'samples': 19594368, 'steps': 102053, 'loss/train': 1.2787929773330688} 08/31/2021 07:39:04 - INFO - __main__ - Step 102055: {'lr': 0.00011867924751367448, 'samples': 19594560, 'steps': 102054, 'loss/train': 1.3851529359817505} 08/31/2021 07:39:04 - INFO - __main__ - Step 102056: {'lr': 0.00011867473188809455, 'samples': 19594752, 'steps': 102055, 'loss/train': 0.05422217771410942} 08/31/2021 07:39:05 - INFO - __main__ - Step 102057: {'lr': 0.00011867021632168774, 'samples': 19594944, 'steps': 102056, 'loss/train': 1.4654712677001953} 08/31/2021 07:39:06 - INFO - __main__ - Step 102058: {'lr': 0.0001186657008144561, 'samples': 19595136, 'steps': 102057, 'loss/train': 0.21900364756584167} 08/31/2021 07:39:07 - INFO - __main__ - Step 102059: {'lr': 0.00011866118536640169, 'samples': 19595328, 'steps': 102058, 'loss/train': 1.2239633798599243} 08/31/2021 07:39:07 - INFO - __main__ - Step 102060: {'lr': 0.0001186566699775265, 'samples': 19595520, 'steps': 102059, 'loss/train': 0.9906067252159119} 08/31/2021 07:39:08 - INFO - __main__ - Step 102061: {'lr': 0.0001186521546478326, 'samples': 19595712, 'steps': 102060, 'loss/train': 1.834280014038086} 08/31/2021 07:39:08 - INFO - __main__ - Step 102062: {'lr': 0.00011864763937732203, 'samples': 19595904, 'steps': 102061, 'loss/train': 0.7306866645812988} 08/31/2021 07:39:10 - INFO - __main__ - Step 102063: {'lr': 0.00011864312416599679, 'samples': 19596096, 'steps': 102062, 'loss/train': 1.1184829473495483} 08/31/2021 07:39:11 - INFO - __main__ - Step 102064: {'lr': 0.00011863860901385901, 'samples': 19596288, 'steps': 102063, 'loss/train': 0.06701188534498215} 08/31/2021 07:39:11 - INFO - __main__ - Step 102065: {'lr': 0.00011863409392091056, 'samples': 19596480, 'steps': 102064, 'loss/train': 1.2761932611465454} 08/31/2021 07:39:11 - INFO - __main__ - Step 102066: {'lr': 0.00011862957888715359, 'samples': 19596672, 'steps': 102065, 'loss/train': 1.0541471242904663} 08/31/2021 07:39:12 - INFO - __main__ - Step 102067: {'lr': 0.00011862506391259006, 'samples': 19596864, 'steps': 102066, 'loss/train': 1.3511079549789429} 08/31/2021 07:39:13 - INFO - __main__ - Step 102068: {'lr': 0.00011862054899722207, 'samples': 19597056, 'steps': 102067, 'loss/train': 1.1949126720428467} 08/31/2021 07:39:14 - INFO - __main__ - Step 102069: {'lr': 0.00011861603414105163, 'samples': 19597248, 'steps': 102068, 'loss/train': 1.2624019384384155} 08/31/2021 07:39:14 - INFO - __main__ - Step 102070: {'lr': 0.0001186115193440808, 'samples': 19597440, 'steps': 102069, 'loss/train': 0.7560875415802002} 08/31/2021 07:39:14 - INFO - __main__ - Step 102071: {'lr': 0.00011860700460631155, 'samples': 19597632, 'steps': 102070, 'loss/train': 1.568544864654541} 08/31/2021 07:39:15 - INFO - __main__ - Step 102072: {'lr': 0.000118602489927746, 'samples': 19597824, 'steps': 102071, 'loss/train': 1.1178569793701172} 08/31/2021 07:39:16 - INFO - __main__ - Step 102073: {'lr': 0.00011859797530838611, 'samples': 19598016, 'steps': 102072, 'loss/train': 1.4052516222000122} 08/31/2021 07:39:17 - INFO - __main__ - Step 102074: {'lr': 0.00011859346074823397, 'samples': 19598208, 'steps': 102073, 'loss/train': 1.3311779499053955} 08/31/2021 07:39:17 - INFO - __main__ - Step 102075: {'lr': 0.00011858894624729155, 'samples': 19598400, 'steps': 102074, 'loss/train': 0.7030099034309387} 08/31/2021 07:39:18 - INFO - __main__ - Step 102076: {'lr': 0.00011858443180556094, 'samples': 19598592, 'steps': 102075, 'loss/train': 1.320266604423523} 08/31/2021 07:39:18 - INFO - __main__ - Step 102077: {'lr': 0.00011857991742304417, 'samples': 19598784, 'steps': 102076, 'loss/train': 1.4747958183288574} 08/31/2021 07:39:19 - INFO - __main__ - Step 102078: {'lr': 0.00011857540309974335, 'samples': 19598976, 'steps': 102077, 'loss/train': 0.33246707916259766} 08/31/2021 07:39:20 - INFO - __main__ - Step 102079: {'lr': 0.00011857088883566033, 'samples': 19599168, 'steps': 102078, 'loss/train': 1.3457626104354858} 08/31/2021 07:39:20 - INFO - __main__ - Step 102080: {'lr': 0.00011856637463079723, 'samples': 19599360, 'steps': 102079, 'loss/train': 0.9518728852272034} 08/31/2021 07:39:20 - INFO - __main__ - Step 102081: {'lr': 0.0001185618604851561, 'samples': 19599552, 'steps': 102080, 'loss/train': 1.4246602058410645} 08/31/2021 07:39:21 - INFO - __main__ - Step 102082: {'lr': 0.00011855734639873897, 'samples': 19599744, 'steps': 102081, 'loss/train': 1.2146670818328857} 08/31/2021 07:39:22 - INFO - __main__ - Step 102083: {'lr': 0.00011855283237154788, 'samples': 19599936, 'steps': 102082, 'loss/train': 1.5624632835388184} 08/31/2021 07:39:23 - INFO - __main__ - Step 102084: {'lr': 0.00011854831840358485, 'samples': 19600128, 'steps': 102083, 'loss/train': 1.1295087337493896} 08/31/2021 07:39:23 - INFO - __main__ - Step 102085: {'lr': 0.00011854380449485191, 'samples': 19600320, 'steps': 102084, 'loss/train': 2.6382107734680176} 08/31/2021 07:39:23 - INFO - __main__ - Step 102086: {'lr': 0.0001185392906453511, 'samples': 19600512, 'steps': 102085, 'loss/train': 1.3953191041946411} 08/31/2021 07:39:24 - INFO - __main__ - Step 102087: {'lr': 0.00011853477685508445, 'samples': 19600704, 'steps': 102086, 'loss/train': 0.7035936117172241} 08/31/2021 07:39:25 - INFO - __main__ - Step 102088: {'lr': 0.00011853026312405404, 'samples': 19600896, 'steps': 102087, 'loss/train': 0.1762804239988327} 08/31/2021 07:39:26 - INFO - __main__ - Step 102089: {'lr': 0.00011852574945226183, 'samples': 19601088, 'steps': 102088, 'loss/train': 1.5796515941619873} 08/31/2021 07:39:26 - INFO - __main__ - Step 102090: {'lr': 0.00011852123583970992, 'samples': 19601280, 'steps': 102089, 'loss/train': 0.7186498641967773} 08/31/2021 07:39:26 - INFO - __main__ - Step 102091: {'lr': 0.00011851672228640037, 'samples': 19601472, 'steps': 102090, 'loss/train': 1.5689775943756104} 08/31/2021 07:39:27 - INFO - __main__ - Step 102092: {'lr': 0.0001185122087923351, 'samples': 19601664, 'steps': 102091, 'loss/train': 1.040037989616394} 08/31/2021 07:39:27 - INFO - __main__ - Step 102093: {'lr': 0.00011850769535751615, 'samples': 19601856, 'steps': 102092, 'loss/train': 0.9264912605285645} 08/31/2021 07:39:29 - INFO - __main__ - Step 102094: {'lr': 0.00011850318198194565, 'samples': 19602048, 'steps': 102093, 'loss/train': 1.0606625080108643} 08/31/2021 07:39:29 - INFO - __main__ - Step 102095: {'lr': 0.00011849866866562556, 'samples': 19602240, 'steps': 102094, 'loss/train': 1.2953839302062988} 08/31/2021 07:39:30 - INFO - __main__ - Step 102096: {'lr': 0.00011849415540855795, 'samples': 19602432, 'steps': 102095, 'loss/train': 1.1835700273513794} 08/31/2021 07:39:30 - INFO - __main__ - Step 102097: {'lr': 0.00011848964221074485, 'samples': 19602624, 'steps': 102096, 'loss/train': 1.7977880239486694} 08/31/2021 07:39:31 - INFO - __main__ - Step 102098: {'lr': 0.00011848512907218828, 'samples': 19602816, 'steps': 102097, 'loss/train': 0.5050445199012756} 08/31/2021 07:39:31 - INFO - __main__ - Step 102099: {'lr': 0.00011848061599289029, 'samples': 19603008, 'steps': 102098, 'loss/train': 0.021590204909443855} 08/31/2021 07:39:32 - INFO - __main__ - Step 102100: {'lr': 0.00011847610297285288, 'samples': 19603200, 'steps': 102099, 'loss/train': 0.015440492890775204} 08/31/2021 07:39:33 - INFO - __main__ - Step 102101: {'lr': 0.00011847159001207813, 'samples': 19603392, 'steps': 102100, 'loss/train': 0.5566750764846802} 08/31/2021 07:39:33 - INFO - __main__ - Step 102102: {'lr': 0.00011846707711056806, 'samples': 19603584, 'steps': 102101, 'loss/train': 1.2545387744903564} 08/31/2021 07:39:34 - INFO - __main__ - Step 102103: {'lr': 0.00011846256426832466, 'samples': 19603776, 'steps': 102102, 'loss/train': 1.1783963441848755} 08/31/2021 07:39:34 - INFO - __main__ - Step 102104: {'lr': 0.00011845805148535005, 'samples': 19603968, 'steps': 102103, 'loss/train': 1.4868220090866089} 08/31/2021 07:39:35 - INFO - __main__ - Step 102105: {'lr': 0.00011845353876164627, 'samples': 19604160, 'steps': 102104, 'loss/train': 1.2016186714172363} 08/31/2021 07:39:36 - INFO - __main__ - Step 102106: {'lr': 0.0001184490260972152, 'samples': 19604352, 'steps': 102105, 'loss/train': 0.9036823511123657} 08/31/2021 07:39:36 - INFO - __main__ - Step 102107: {'lr': 0.00011844451349205898, 'samples': 19604544, 'steps': 102106, 'loss/train': 1.1896113157272339} 08/31/2021 07:39:37 - INFO - __main__ - Step 102108: {'lr': 0.00011844000094617963, 'samples': 19604736, 'steps': 102107, 'loss/train': 1.2582581043243408} 08/31/2021 07:39:37 - INFO - __main__ - Step 102109: {'lr': 0.0001184354884595792, 'samples': 19604928, 'steps': 102108, 'loss/train': 0.8510369658470154} 08/31/2021 07:39:38 - INFO - __main__ - Step 102110: {'lr': 0.0001184309760322597, 'samples': 19605120, 'steps': 102109, 'loss/train': 1.0329842567443848} 08/31/2021 07:39:39 - INFO - __main__ - Step 102111: {'lr': 0.00011842646366422317, 'samples': 19605312, 'steps': 102110, 'loss/train': 2.10732364654541} 08/31/2021 07:39:39 - INFO - __main__ - Step 102112: {'lr': 0.00011842195135547162, 'samples': 19605504, 'steps': 102111, 'loss/train': 1.105647087097168} 08/31/2021 07:39:40 - INFO - __main__ - Step 102113: {'lr': 0.00011841743910600713, 'samples': 19605696, 'steps': 102112, 'loss/train': 1.0247678756713867} 08/31/2021 07:39:40 - INFO - __main__ - Step 102114: {'lr': 0.00011841292691583172, 'samples': 19605888, 'steps': 102113, 'loss/train': 0.688653826713562} 08/31/2021 07:39:42 - INFO - __main__ - Step 102115: {'lr': 0.0001184084147849474, 'samples': 19606080, 'steps': 102114, 'loss/train': 0.9004619121551514} 08/31/2021 07:39:42 - INFO - __main__ - Step 102116: {'lr': 0.00011840390271335624, 'samples': 19606272, 'steps': 102115, 'loss/train': 1.305626392364502} 08/31/2021 07:39:43 - INFO - __main__ - Step 102117: {'lr': 0.00011839939070106032, 'samples': 19606464, 'steps': 102116, 'loss/train': 1.1491916179656982} 08/31/2021 07:39:43 - INFO - __main__ - Step 102118: {'lr': 0.00011839487874806152, 'samples': 19606656, 'steps': 102117, 'loss/train': 0.9665786027908325} 08/31/2021 07:39:43 - INFO - __main__ - Step 102119: {'lr': 0.00011839036685436198, 'samples': 19606848, 'steps': 102118, 'loss/train': 0.4049566686153412} 08/31/2021 07:39:46 - INFO - __main__ - Step 102120: {'lr': 0.00011838585501996366, 'samples': 19607040, 'steps': 102119, 'loss/train': 0.9531047344207764} 08/31/2021 07:39:46 - INFO - __main__ - Step 102121: {'lr': 0.00011838134324486869, 'samples': 19607232, 'steps': 102120, 'loss/train': 0.8750478625297546} 08/31/2021 07:39:47 - INFO - __main__ - Step 102122: {'lr': 0.00011837683152907902, 'samples': 19607424, 'steps': 102121, 'loss/train': 1.1378587484359741} 08/31/2021 07:39:47 - INFO - __main__ - Step 102123: {'lr': 0.00011837231987259672, 'samples': 19607616, 'steps': 102122, 'loss/train': 1.2409840822219849} 08/31/2021 07:39:47 - INFO - __main__ - Step 102124: {'lr': 0.00011836780827542385, 'samples': 19607808, 'steps': 102123, 'loss/train': 0.6080643534660339} 08/31/2021 07:39:48 - INFO - __main__ - Step 102125: {'lr': 0.00011836329673756238, 'samples': 19608000, 'steps': 102124, 'loss/train': 1.1644787788391113} 08/31/2021 07:39:49 - INFO - __main__ - Step 102126: {'lr': 0.00011835878525901442, 'samples': 19608192, 'steps': 102125, 'loss/train': 1.3026357889175415} 08/31/2021 07:39:50 - INFO - __main__ - Step 102127: {'lr': 0.00011835427383978192, 'samples': 19608384, 'steps': 102126, 'loss/train': 0.9809686541557312} 08/31/2021 07:39:50 - INFO - __main__ - Step 102128: {'lr': 0.00011834976247986706, 'samples': 19608576, 'steps': 102127, 'loss/train': 1.0720123052597046} 08/31/2021 07:39:51 - INFO - __main__ - Step 102129: {'lr': 0.0001183452511792717, 'samples': 19608768, 'steps': 102128, 'loss/train': 1.19172203540802} 08/31/2021 07:39:51 - INFO - __main__ - Step 102130: {'lr': 0.0001183407399379979, 'samples': 19608960, 'steps': 102129, 'loss/train': 1.1377924680709839} 08/31/2021 07:39:52 - INFO - __main__ - Step 102131: {'lr': 0.00011833622875604774, 'samples': 19609152, 'steps': 102130, 'loss/train': 0.5541213154792786} 08/31/2021 07:39:53 - INFO - __main__ - Step 102132: {'lr': 0.00011833171763342324, 'samples': 19609344, 'steps': 102131, 'loss/train': 1.136548638343811} 08/31/2021 07:39:53 - INFO - __main__ - Step 102133: {'lr': 0.00011832720657012644, 'samples': 19609536, 'steps': 102132, 'loss/train': 1.152867317199707} 08/31/2021 07:39:54 - INFO - __main__ - Step 102134: {'lr': 0.00011832269556615938, 'samples': 19609728, 'steps': 102133, 'loss/train': 0.9366738796234131} 08/31/2021 07:39:54 - INFO - __main__ - Step 102135: {'lr': 0.00011831818462152408, 'samples': 19609920, 'steps': 102134, 'loss/train': 1.113004207611084} 08/31/2021 07:39:55 - INFO - __main__ - Step 102136: {'lr': 0.00011831367373622256, 'samples': 19610112, 'steps': 102135, 'loss/train': 1.4099581241607666} 08/31/2021 07:39:56 - INFO - __main__ - Step 102137: {'lr': 0.00011830916291025687, 'samples': 19610304, 'steps': 102136, 'loss/train': 0.5884583592414856} 08/31/2021 07:39:56 - INFO - __main__ - Step 102138: {'lr': 0.00011830465214362907, 'samples': 19610496, 'steps': 102137, 'loss/train': 1.0640650987625122} 08/31/2021 07:39:57 - INFO - __main__ - Step 102139: {'lr': 0.00011830014143634121, 'samples': 19610688, 'steps': 102138, 'loss/train': 1.0928455591201782} 08/31/2021 07:39:57 - INFO - __main__ - Step 102140: {'lr': 0.0001182956307883952, 'samples': 19610880, 'steps': 102139, 'loss/train': 0.9700819849967957} 08/31/2021 07:39:59 - INFO - __main__ - Step 102141: {'lr': 0.00011829112019979316, 'samples': 19611072, 'steps': 102140, 'loss/train': 1.2926474809646606} 08/31/2021 07:39:59 - INFO - __main__ - Step 102142: {'lr': 0.00011828660967053709, 'samples': 19611264, 'steps': 102141, 'loss/train': 1.2289320230484009} 08/31/2021 07:40:00 - INFO - __main__ - Step 102143: {'lr': 0.00011828209920062905, 'samples': 19611456, 'steps': 102142, 'loss/train': 1.5291860103607178} 08/31/2021 07:40:00 - INFO - __main__ - Step 102144: {'lr': 0.00011827758879007105, 'samples': 19611648, 'steps': 102143, 'loss/train': 1.1119788885116577} 08/31/2021 07:40:00 - INFO - __main__ - Step 102145: {'lr': 0.00011827307843886514, 'samples': 19611840, 'steps': 102144, 'loss/train': 1.1342796087265015} 08/31/2021 07:40:01 - INFO - __main__ - Step 102146: {'lr': 0.00011826856814701336, 'samples': 19612032, 'steps': 102145, 'loss/train': 0.01639346405863762} 08/31/2021 07:40:02 - INFO - __main__ - Step 102147: {'lr': 0.00011826405791451772, 'samples': 19612224, 'steps': 102146, 'loss/train': 0.016278229653835297} 08/31/2021 07:40:03 - INFO - __main__ - Step 102148: {'lr': 0.00011825954774138025, 'samples': 19612416, 'steps': 102147, 'loss/train': 1.5582823753356934} 08/31/2021 07:40:03 - INFO - __main__ - Step 102149: {'lr': 0.00011825503762760303, 'samples': 19612608, 'steps': 102148, 'loss/train': 1.4190009832382202} 08/31/2021 07:40:04 - INFO - __main__ - Step 102150: {'lr': 0.00011825052757318813, 'samples': 19612800, 'steps': 102149, 'loss/train': 1.2128982543945312} 08/31/2021 07:40:04 - INFO - __main__ - Step 102151: {'lr': 0.00011824601757813741, 'samples': 19612992, 'steps': 102150, 'loss/train': 1.309056043624878} 08/31/2021 07:40:04 - INFO - __main__ - Step 102152: {'lr': 0.00011824150764245301, 'samples': 19613184, 'steps': 102151, 'loss/train': 1.2766475677490234} 08/31/2021 07:40:06 - INFO - __main__ - Step 102153: {'lr': 0.00011823699776613698, 'samples': 19613376, 'steps': 102152, 'loss/train': 0.48005202412605286} 08/31/2021 07:40:07 - INFO - __main__ - Step 102154: {'lr': 0.00011823248794919128, 'samples': 19613568, 'steps': 102153, 'loss/train': 0.4474647343158722} 08/31/2021 07:40:07 - INFO - __main__ - Step 102155: {'lr': 0.00011822797819161802, 'samples': 19613760, 'steps': 102154, 'loss/train': 0.5355979800224304} 08/31/2021 07:40:08 - INFO - __main__ - Step 102156: {'lr': 0.00011822346849341917, 'samples': 19613952, 'steps': 102155, 'loss/train': 0.9410123825073242} 08/31/2021 07:40:08 - INFO - __main__ - Step 102157: {'lr': 0.0001182189588545968, 'samples': 19614144, 'steps': 102156, 'loss/train': 0.7146899104118347} 08/31/2021 07:40:08 - INFO - __main__ - Step 102158: {'lr': 0.00011821444927515296, 'samples': 19614336, 'steps': 102157, 'loss/train': 0.9845948815345764} 08/31/2021 07:40:10 - INFO - __main__ - Step 102159: {'lr': 0.00011820993975508962, 'samples': 19614528, 'steps': 102158, 'loss/train': 1.9103949069976807} 08/31/2021 07:40:10 - INFO - __main__ - Step 102160: {'lr': 0.00011820543029440887, 'samples': 19614720, 'steps': 102159, 'loss/train': 1.2701270580291748} 08/31/2021 07:40:11 - INFO - __main__ - Step 102161: {'lr': 0.0001182009208931128, 'samples': 19614912, 'steps': 102160, 'loss/train': 1.0455454587936401} 08/31/2021 07:40:11 - INFO - __main__ - Step 102162: {'lr': 0.00011819641155120328, 'samples': 19615104, 'steps': 102161, 'loss/train': 1.0709137916564941} 08/31/2021 07:40:11 - INFO - __main__ - Step 102163: {'lr': 0.00011819190226868242, 'samples': 19615296, 'steps': 102162, 'loss/train': 1.2764718532562256} 08/31/2021 07:40:13 - INFO - __main__ - Step 102164: {'lr': 0.00011818739304555227, 'samples': 19615488, 'steps': 102163, 'loss/train': 0.7684187293052673} 08/31/2021 07:40:13 - INFO - __main__ - Step 102165: {'lr': 0.0001181828838818148, 'samples': 19615680, 'steps': 102164, 'loss/train': 1.170680046081543} 08/31/2021 07:40:14 - INFO - __main__ - Step 102166: {'lr': 0.00011817837477747212, 'samples': 19615872, 'steps': 102165, 'loss/train': 0.5399566292762756} 08/31/2021 07:40:14 - INFO - __main__ - Step 102167: {'lr': 0.00011817386573252623, 'samples': 19616064, 'steps': 102166, 'loss/train': 1.134397029876709} 08/31/2021 07:40:14 - INFO - __main__ - Step 102168: {'lr': 0.00011816935674697918, 'samples': 19616256, 'steps': 102167, 'loss/train': 1.3769054412841797} 08/31/2021 07:40:16 - INFO - __main__ - Step 102169: {'lr': 0.00011816484782083295, 'samples': 19616448, 'steps': 102168, 'loss/train': 0.7507781386375427} 08/31/2021 07:40:17 - INFO - __main__ - Step 102170: {'lr': 0.00011816033895408962, 'samples': 19616640, 'steps': 102169, 'loss/train': 1.1590380668640137} 08/31/2021 07:40:17 - INFO - __main__ - Step 102171: {'lr': 0.00011815583014675121, 'samples': 19616832, 'steps': 102170, 'loss/train': 0.9372797012329102} 08/31/2021 07:40:17 - INFO - __main__ - Step 102172: {'lr': 0.00011815132139881984, 'samples': 19617024, 'steps': 102171, 'loss/train': 0.7678989768028259} 08/31/2021 07:40:18 - INFO - __main__ - Step 102173: {'lr': 0.00011814681271029734, 'samples': 19617216, 'steps': 102172, 'loss/train': 0.1265108585357666} 08/31/2021 07:40:20 - INFO - __main__ - Step 102174: {'lr': 0.00011814230408118587, 'samples': 19617408, 'steps': 102173, 'loss/train': 1.1101032495498657} 08/31/2021 07:40:20 - INFO - __main__ - Step 102175: {'lr': 0.00011813779551148745, 'samples': 19617600, 'steps': 102174, 'loss/train': 2.3282599449157715} 08/31/2021 07:40:21 - INFO - __main__ - Step 102176: {'lr': 0.0001181332870012041, 'samples': 19617792, 'steps': 102175, 'loss/train': 0.5012416839599609} 08/31/2021 07:40:21 - INFO - __main__ - Step 102177: {'lr': 0.00011812877855033782, 'samples': 19617984, 'steps': 102176, 'loss/train': 1.2817672491073608} 08/31/2021 07:40:21 - INFO - __main__ - Step 102178: {'lr': 0.00011812427015889071, 'samples': 19618176, 'steps': 102177, 'loss/train': 1.3961992263793945} 08/31/2021 07:40:23 - INFO - __main__ - Step 102179: {'lr': 0.00011811976182686479, 'samples': 19618368, 'steps': 102178, 'loss/train': 1.1775751113891602} 08/31/2021 07:40:23 - INFO - __main__ - Step 102180: {'lr': 0.00011811525355426204, 'samples': 19618560, 'steps': 102179, 'loss/train': 1.1711256504058838} 08/31/2021 07:40:24 - INFO - __main__ - Step 102181: {'lr': 0.00011811074534108451, 'samples': 19618752, 'steps': 102180, 'loss/train': 1.4764479398727417} 08/31/2021 07:40:24 - INFO - __main__ - Step 102182: {'lr': 0.00011810623718733426, 'samples': 19618944, 'steps': 102181, 'loss/train': 1.2155513763427734} 08/31/2021 07:40:24 - INFO - __main__ - Step 102183: {'lr': 0.00011810172909301331, 'samples': 19619136, 'steps': 102182, 'loss/train': 1.1674824953079224} 08/31/2021 07:40:25 - INFO - __main__ - Step 102184: {'lr': 0.00011809722105812367, 'samples': 19619328, 'steps': 102183, 'loss/train': 0.965765118598938} 08/31/2021 07:40:26 - INFO - __main__ - Step 102185: {'lr': 0.0001180927130826675, 'samples': 19619520, 'steps': 102184, 'loss/train': 0.18828889727592468} 08/31/2021 07:40:27 - INFO - __main__ - Step 102186: {'lr': 0.00011808820516664662, 'samples': 19619712, 'steps': 102185, 'loss/train': 0.9830746054649353} 08/31/2021 07:40:27 - INFO - __main__ - Step 102187: {'lr': 0.00011808369731006315, 'samples': 19619904, 'steps': 102186, 'loss/train': 1.0998280048370361} 08/31/2021 07:40:27 - INFO - __main__ - Step 102188: {'lr': 0.00011807918951291916, 'samples': 19620096, 'steps': 102187, 'loss/train': 1.5641145706176758} 08/31/2021 07:40:28 - INFO - __main__ - Step 102189: {'lr': 0.0001180746817752166, 'samples': 19620288, 'steps': 102188, 'loss/train': 0.9882229566574097} 08/31/2021 07:40:29 - INFO - __main__ - Step 102190: {'lr': 0.00011807017409695758, 'samples': 19620480, 'steps': 102189, 'loss/train': 0.9962482452392578} 08/31/2021 07:40:30 - INFO - __main__ - Step 102191: {'lr': 0.00011806566647814412, 'samples': 19620672, 'steps': 102190, 'loss/train': 1.5939021110534668} 08/31/2021 07:40:30 - INFO - __main__ - Step 102192: {'lr': 0.00011806115891877822, 'samples': 19620864, 'steps': 102191, 'loss/train': 1.2606745958328247} 08/31/2021 07:40:30 - INFO - __main__ - Step 102193: {'lr': 0.00011805665141886191, 'samples': 19621056, 'steps': 102192, 'loss/train': 1.6123844385147095} 08/31/2021 07:40:31 - INFO - __main__ - Step 102194: {'lr': 0.00011805214397839725, 'samples': 19621248, 'steps': 102193, 'loss/train': 1.0321247577667236} 08/31/2021 07:40:32 - INFO - __main__ - Step 102195: {'lr': 0.00011804763659738626, 'samples': 19621440, 'steps': 102194, 'loss/train': 0.11438997834920883} 08/31/2021 07:40:33 - INFO - __main__ - Step 102196: {'lr': 0.00011804312927583097, 'samples': 19621632, 'steps': 102195, 'loss/train': 1.4935306310653687} 08/31/2021 07:40:33 - INFO - __main__ - Step 102197: {'lr': 0.00011803862201373342, 'samples': 19621824, 'steps': 102196, 'loss/train': 1.8916347026824951} 08/31/2021 07:40:33 - INFO - __main__ - Step 102198: {'lr': 0.00011803411481109561, 'samples': 19622016, 'steps': 102197, 'loss/train': 1.258516550064087} 08/31/2021 07:40:34 - INFO - __main__ - Step 102199: {'lr': 0.0001180296076679197, 'samples': 19622208, 'steps': 102198, 'loss/train': 1.1515392065048218} 08/31/2021 07:40:35 - INFO - __main__ - Step 102200: {'lr': 0.00011802510058420752, 'samples': 19622400, 'steps': 102199, 'loss/train': 1.046830415725708} 08/31/2021 07:40:36 - INFO - __main__ - Step 102201: {'lr': 0.00011802059355996118, 'samples': 19622592, 'steps': 102200, 'loss/train': 1.3340336084365845} 08/31/2021 07:40:36 - INFO - __main__ - Step 102202: {'lr': 0.0001180160865951827, 'samples': 19622784, 'steps': 102201, 'loss/train': 0.489393949508667} 08/31/2021 07:40:37 - INFO - __main__ - Step 102203: {'lr': 0.00011801157968987417, 'samples': 19622976, 'steps': 102202, 'loss/train': 1.3689252138137817} 08/31/2021 07:40:37 - INFO - __main__ - Step 102204: {'lr': 0.00011800707284403759, 'samples': 19623168, 'steps': 102203, 'loss/train': 0.6473280787467957} 08/31/2021 07:40:37 - INFO - __main__ - Step 102205: {'lr': 0.00011800256605767498, 'samples': 19623360, 'steps': 102204, 'loss/train': 1.2541550397872925} 08/31/2021 07:40:39 - INFO - __main__ - Step 102206: {'lr': 0.00011799805933078836, 'samples': 19623552, 'steps': 102205, 'loss/train': 1.5701327323913574} 08/31/2021 07:40:39 - INFO - __main__ - Step 102207: {'lr': 0.0001179935526633798, 'samples': 19623744, 'steps': 102206, 'loss/train': 1.0843461751937866} 08/31/2021 07:40:39 - INFO - __main__ - Step 102208: {'lr': 0.0001179890460554513, 'samples': 19623936, 'steps': 102207, 'loss/train': 1.4223543405532837} 08/31/2021 07:40:40 - INFO - __main__ - Step 102209: {'lr': 0.00011798453950700488, 'samples': 19624128, 'steps': 102208, 'loss/train': 1.3659956455230713} 08/31/2021 07:40:40 - INFO - __main__ - Step 102210: {'lr': 0.00011798003301804261, 'samples': 19624320, 'steps': 102209, 'loss/train': 0.7263427972793579} 08/31/2021 07:40:42 - INFO - __main__ - Step 102211: {'lr': 0.0001179755265885665, 'samples': 19624512, 'steps': 102210, 'loss/train': 0.9532144665718079} 08/31/2021 07:40:43 - INFO - __main__ - Step 102212: {'lr': 0.00011797102021857867, 'samples': 19624704, 'steps': 102211, 'loss/train': 1.1081511974334717} 08/31/2021 07:40:43 - INFO - __main__ - Step 102213: {'lr': 0.00011796651390808097, 'samples': 19624896, 'steps': 102212, 'loss/train': 1.4169635772705078} 08/31/2021 07:40:44 - INFO - __main__ - Step 102214: {'lr': 0.00011796200765707551, 'samples': 19625088, 'steps': 102213, 'loss/train': 1.4203691482543945} 08/31/2021 07:40:44 - INFO - __main__ - Step 102215: {'lr': 0.00011795750146556433, 'samples': 19625280, 'steps': 102214, 'loss/train': 0.06682638823986053} 08/31/2021 07:40:44 - INFO - __main__ - Step 102216: {'lr': 0.00011795299533354948, 'samples': 19625472, 'steps': 102215, 'loss/train': 0.01838657259941101} 08/31/2021 07:40:45 - INFO - __main__ - Step 102217: {'lr': 0.00011794848926103296, 'samples': 19625664, 'steps': 102216, 'loss/train': 0.014995717443525791} 08/31/2021 07:40:46 - INFO - __main__ - Step 102218: {'lr': 0.00011794398324801684, 'samples': 19625856, 'steps': 102217, 'loss/train': 0.8879470825195312} 08/31/2021 07:40:47 - INFO - __main__ - Step 102219: {'lr': 0.00011793947729450311, 'samples': 19626048, 'steps': 102218, 'loss/train': 1.3685864210128784} 08/31/2021 07:40:47 - INFO - __main__ - Step 102220: {'lr': 0.00011793497140049377, 'samples': 19626240, 'steps': 102219, 'loss/train': 1.315830111503601} 08/31/2021 07:40:47 - INFO - __main__ - Step 102221: {'lr': 0.00011793046556599094, 'samples': 19626432, 'steps': 102220, 'loss/train': 1.2330348491668701} 08/31/2021 07:40:48 - INFO - __main__ - Step 102222: {'lr': 0.0001179259597909966, 'samples': 19626624, 'steps': 102221, 'loss/train': 1.2000319957733154} 08/31/2021 07:40:49 - INFO - __main__ - Step 102223: {'lr': 0.00011792145407551277, 'samples': 19626816, 'steps': 102222, 'loss/train': 1.4003098011016846} 08/31/2021 07:40:50 - INFO - __main__ - Step 102224: {'lr': 0.00011791694841954151, 'samples': 19627008, 'steps': 102223, 'loss/train': 1.1589832305908203} 08/31/2021 07:40:50 - INFO - __main__ - Step 102225: {'lr': 0.00011791244282308483, 'samples': 19627200, 'steps': 102224, 'loss/train': 1.1040596961975098} 08/31/2021 07:40:50 - INFO - __main__ - Step 102226: {'lr': 0.00011790793728614485, 'samples': 19627392, 'steps': 102225, 'loss/train': 1.3641561269760132} 08/31/2021 07:40:51 - INFO - __main__ - Step 102227: {'lr': 0.00011790343180872342, 'samples': 19627584, 'steps': 102226, 'loss/train': 1.846192717552185} 08/31/2021 07:40:51 - INFO - __main__ - Step 102228: {'lr': 0.0001178989263908227, 'samples': 19627776, 'steps': 102227, 'loss/train': 2.134948968887329} 08/31/2021 07:40:53 - INFO - __main__ - Step 102229: {'lr': 0.00011789442103244466, 'samples': 19627968, 'steps': 102228, 'loss/train': 0.807033896446228} 08/31/2021 07:40:53 - INFO - __main__ - Step 102230: {'lr': 0.00011788991573359134, 'samples': 19628160, 'steps': 102229, 'loss/train': 0.8946169018745422} 08/31/2021 07:40:54 - INFO - __main__ - Step 102231: {'lr': 0.0001178854104942648, 'samples': 19628352, 'steps': 102230, 'loss/train': 1.445412278175354} 08/31/2021 07:40:54 - INFO - __main__ - Step 102232: {'lr': 0.00011788090531446704, 'samples': 19628544, 'steps': 102231, 'loss/train': 0.08001932501792908} 08/31/2021 07:40:54 - INFO - __main__ - Step 102233: {'lr': 0.00011787640019420012, 'samples': 19628736, 'steps': 102232, 'loss/train': 1.1264854669570923} 08/31/2021 07:40:56 - INFO - __main__ - Step 102234: {'lr': 0.00011787189513346607, 'samples': 19628928, 'steps': 102233, 'loss/train': 1.1252868175506592} 08/31/2021 07:40:57 - INFO - __main__ - Step 102235: {'lr': 0.00011786739013226688, 'samples': 19629120, 'steps': 102234, 'loss/train': 1.123004674911499} 08/31/2021 07:40:57 - INFO - __main__ - Step 102236: {'lr': 0.00011786288519060462, 'samples': 19629312, 'steps': 102235, 'loss/train': 1.311522364616394} 08/31/2021 07:40:58 - INFO - __main__ - Step 102237: {'lr': 0.00011785838030848132, 'samples': 19629504, 'steps': 102236, 'loss/train': 1.0581035614013672} 08/31/2021 07:40:58 - INFO - __main__ - Step 102238: {'lr': 0.00011785387548589896, 'samples': 19629696, 'steps': 102237, 'loss/train': 1.2706327438354492} 08/31/2021 07:40:58 - INFO - __main__ - Step 102239: {'lr': 0.00011784937072285972, 'samples': 19629888, 'steps': 102238, 'loss/train': 2.1677160263061523} 08/31/2021 07:41:00 - INFO - __main__ - Step 102240: {'lr': 0.00011784486601936542, 'samples': 19630080, 'steps': 102239, 'loss/train': 1.7065259218215942} 08/31/2021 07:41:00 - INFO - __main__ - Step 102241: {'lr': 0.00011784036137541818, 'samples': 19630272, 'steps': 102240, 'loss/train': 0.7215387225151062} 08/31/2021 07:41:01 - INFO - __main__ - Step 102242: {'lr': 0.00011783585679102002, 'samples': 19630464, 'steps': 102241, 'loss/train': 0.10225090384483337} 08/31/2021 07:41:01 - INFO - __main__ - Step 102243: {'lr': 0.00011783135226617301, 'samples': 19630656, 'steps': 102242, 'loss/train': 1.2098565101623535} 08/31/2021 07:41:01 - INFO - __main__ - Step 102244: {'lr': 0.00011782684780087912, 'samples': 19630848, 'steps': 102243, 'loss/train': 0.5435097217559814} 08/31/2021 07:41:03 - INFO - __main__ - Step 102245: {'lr': 0.00011782234339514045, 'samples': 19631040, 'steps': 102244, 'loss/train': 1.068113923072815} 08/31/2021 07:41:04 - INFO - __main__ - Step 102246: {'lr': 0.00011781783904895896, 'samples': 19631232, 'steps': 102245, 'loss/train': 1.2818659543991089} 08/31/2021 07:41:04 - INFO - __main__ - Step 102247: {'lr': 0.00011781333476233674, 'samples': 19631424, 'steps': 102246, 'loss/train': 0.112056665122509} 08/31/2021 07:41:04 - INFO - __main__ - Step 102248: {'lr': 0.00011780883053527577, 'samples': 19631616, 'steps': 102247, 'loss/train': 1.3252533674240112} 08/31/2021 07:41:05 - INFO - __main__ - Step 102249: {'lr': 0.0001178043263677781, 'samples': 19631808, 'steps': 102248, 'loss/train': 0.836444079875946} 08/31/2021 07:41:06 - INFO - __main__ - Step 102250: {'lr': 0.00011779982225984578, 'samples': 19632000, 'steps': 102249, 'loss/train': 1.0734986066818237} 08/31/2021 07:41:07 - INFO - __main__ - Step 102251: {'lr': 0.00011779531821148081, 'samples': 19632192, 'steps': 102250, 'loss/train': 0.8631531596183777} 08/31/2021 07:41:07 - INFO - __main__ - Step 102252: {'lr': 0.00011779081422268531, 'samples': 19632384, 'steps': 102251, 'loss/train': 1.3593378067016602} 08/31/2021 07:41:07 - INFO - __main__ - Step 102253: {'lr': 0.00011778631029346115, 'samples': 19632576, 'steps': 102252, 'loss/train': 1.650553584098816} 08/31/2021 07:41:08 - INFO - __main__ - Step 102254: {'lr': 0.00011778180642381045, 'samples': 19632768, 'steps': 102253, 'loss/train': 1.738925576210022} 08/31/2021 07:41:09 - INFO - __main__ - Step 102255: {'lr': 0.0001177773026137352, 'samples': 19632960, 'steps': 102254, 'loss/train': 1.3692771196365356} 08/31/2021 07:41:10 - INFO - __main__ - Step 102256: {'lr': 0.00011777279886323747, 'samples': 19633152, 'steps': 102255, 'loss/train': 1.3365637063980103} 08/31/2021 07:41:10 - INFO - __main__ - Step 102257: {'lr': 0.0001177682951723193, 'samples': 19633344, 'steps': 102256, 'loss/train': 1.3576749563217163} 08/31/2021 07:41:10 - INFO - __main__ - Step 102258: {'lr': 0.00011776379154098265, 'samples': 19633536, 'steps': 102257, 'loss/train': 1.336775779724121} 08/31/2021 07:41:11 - INFO - __main__ - Step 102259: {'lr': 0.00011775928796922963, 'samples': 19633728, 'steps': 102258, 'loss/train': 1.1117064952850342} 08/31/2021 07:41:11 - INFO - __main__ - Step 102260: {'lr': 0.00011775478445706223, 'samples': 19633920, 'steps': 102259, 'loss/train': 0.7990821003913879} 08/31/2021 07:41:13 - INFO - __main__ - Step 102261: {'lr': 0.00011775028100448246, 'samples': 19634112, 'steps': 102260, 'loss/train': 1.3265211582183838} 08/31/2021 07:41:13 - INFO - __main__ - Step 102262: {'lr': 0.00011774577761149241, 'samples': 19634304, 'steps': 102261, 'loss/train': 1.4661625623703003} 08/31/2021 07:41:13 - INFO - __main__ - Step 102263: {'lr': 0.00011774127427809403, 'samples': 19634496, 'steps': 102262, 'loss/train': 0.8016442060470581} 08/31/2021 07:41:14 - INFO - __main__ - Step 102264: {'lr': 0.00011773677100428942, 'samples': 19634688, 'steps': 102263, 'loss/train': 1.4709811210632324} 08/31/2021 07:41:14 - INFO - __main__ - Step 102265: {'lr': 0.00011773226779008056, 'samples': 19634880, 'steps': 102264, 'loss/train': 0.8763440847396851} 08/31/2021 07:41:16 - INFO - __main__ - Step 102266: {'lr': 0.00011772776463546961, 'samples': 19635072, 'steps': 102265, 'loss/train': 1.2709547281265259} 08/31/2021 07:41:16 - INFO - __main__ - Step 102267: {'lr': 0.0001177232615404584, 'samples': 19635264, 'steps': 102266, 'loss/train': 1.6355677843093872} 08/31/2021 07:41:17 - INFO - __main__ - Step 102268: {'lr': 0.00011771875850504904, 'samples': 19635456, 'steps': 102267, 'loss/train': 1.669840693473816} 08/31/2021 07:41:17 - INFO - __main__ - Step 102269: {'lr': 0.00011771425552924356, 'samples': 19635648, 'steps': 102268, 'loss/train': 0.4738331735134125} 08/31/2021 07:41:17 - INFO - __main__ - Step 102270: {'lr': 0.00011770975261304401, 'samples': 19635840, 'steps': 102269, 'loss/train': 1.1082336902618408} 08/31/2021 07:41:19 - INFO - __main__ - Step 102271: {'lr': 0.00011770524975645239, 'samples': 19636032, 'steps': 102270, 'loss/train': 2.3222007751464844} 08/31/2021 07:41:19 - INFO - __main__ - Step 102272: {'lr': 0.00011770074695947072, 'samples': 19636224, 'steps': 102271, 'loss/train': 1.0634253025054932} 08/31/2021 07:41:20 - INFO - __main__ - Step 102273: {'lr': 0.0001176962442221011, 'samples': 19636416, 'steps': 102272, 'loss/train': 1.3536415100097656} 08/31/2021 07:41:20 - INFO - __main__ - Step 102274: {'lr': 0.00011769174154434548, 'samples': 19636608, 'steps': 102273, 'loss/train': 1.3189499378204346} 08/31/2021 07:41:20 - INFO - __main__ - Step 102275: {'lr': 0.00011768723892620591, 'samples': 19636800, 'steps': 102274, 'loss/train': 0.942736804485321} 08/31/2021 07:41:22 - INFO - __main__ - Step 102276: {'lr': 0.00011768273636768446, 'samples': 19636992, 'steps': 102275, 'loss/train': 1.174930214881897} 08/31/2021 07:41:23 - INFO - __main__ - Step 102277: {'lr': 0.00011767823386878312, 'samples': 19637184, 'steps': 102276, 'loss/train': 3.5597262382507324} 08/31/2021 07:41:23 - INFO - __main__ - Step 102278: {'lr': 0.00011767373142950392, 'samples': 19637376, 'steps': 102277, 'loss/train': 0.794888436794281} 08/31/2021 07:41:23 - INFO - __main__ - Step 102279: {'lr': 0.00011766922904984898, 'samples': 19637568, 'steps': 102278, 'loss/train': 1.2287883758544922} 08/31/2021 07:41:24 - INFO - __main__ - Step 102280: {'lr': 0.00011766472672982015, 'samples': 19637760, 'steps': 102279, 'loss/train': 1.2169432640075684} 08/31/2021 07:41:24 - INFO - __main__ - Step 102281: {'lr': 0.00011766022446941957, 'samples': 19637952, 'steps': 102280, 'loss/train': 0.23287925124168396} 08/31/2021 07:41:26 - INFO - __main__ - Step 102282: {'lr': 0.00011765572226864924, 'samples': 19638144, 'steps': 102281, 'loss/train': 0.507131814956665} 08/31/2021 07:41:26 - INFO - __main__ - Step 102283: {'lr': 0.0001176512201275112, 'samples': 19638336, 'steps': 102282, 'loss/train': 1.3512630462646484} 08/31/2021 07:41:26 - INFO - __main__ - Step 102284: {'lr': 0.00011764671804600746, 'samples': 19638528, 'steps': 102283, 'loss/train': 1.0696964263916016} 08/31/2021 07:41:27 - INFO - __main__ - Step 102285: {'lr': 0.0001176422160241401, 'samples': 19638720, 'steps': 102284, 'loss/train': 0.8745241165161133} 08/31/2021 07:41:27 - INFO - __main__ - Step 102286: {'lr': 0.0001176377140619111, 'samples': 19638912, 'steps': 102285, 'loss/train': 0.5995098352432251} 08/31/2021 07:41:29 - INFO - __main__ - Step 102287: {'lr': 0.00011763321215932249, 'samples': 19639104, 'steps': 102286, 'loss/train': 1.2168376445770264} 08/31/2021 07:41:30 - INFO - __main__ - Step 102288: {'lr': 0.00011762871031637631, 'samples': 19639296, 'steps': 102287, 'loss/train': 0.7170840501785278} 08/31/2021 07:41:30 - INFO - __main__ - Step 102289: {'lr': 0.00011762420853307462, 'samples': 19639488, 'steps': 102288, 'loss/train': 1.1523572206497192} 08/31/2021 07:41:30 - INFO - __main__ - Step 102290: {'lr': 0.00011761970680941941, 'samples': 19639680, 'steps': 102289, 'loss/train': 0.8553473353385925} 08/31/2021 07:41:31 - INFO - __main__ - Step 102291: {'lr': 0.0001176152051454127, 'samples': 19639872, 'steps': 102290, 'loss/train': 0.9553813934326172} 08/31/2021 07:41:32 - INFO - __main__ - Step 102292: {'lr': 0.00011761070354105654, 'samples': 19640064, 'steps': 102291, 'loss/train': 1.4124040603637695} 08/31/2021 07:41:33 - INFO - __main__ - Step 102293: {'lr': 0.00011760620199635307, 'samples': 19640256, 'steps': 102292, 'loss/train': 1.680817723274231} 08/31/2021 07:41:33 - INFO - __main__ - Step 102294: {'lr': 0.00011760170051130409, 'samples': 19640448, 'steps': 102293, 'loss/train': 1.3625471591949463} 08/31/2021 07:41:34 - INFO - __main__ - Step 102295: {'lr': 0.00011759719908591174, 'samples': 19640640, 'steps': 102294, 'loss/train': 1.3822962045669556} 08/31/2021 07:41:34 - INFO - __main__ - Step 102296: {'lr': 0.00011759269772017806, 'samples': 19640832, 'steps': 102295, 'loss/train': 0.35426944494247437} 08/31/2021 07:41:35 - INFO - __main__ - Step 102297: {'lr': 0.00011758819641410506, 'samples': 19641024, 'steps': 102296, 'loss/train': 0.9992993474006653} 08/31/2021 07:41:36 - INFO - __main__ - Step 102298: {'lr': 0.00011758369516769476, 'samples': 19641216, 'steps': 102297, 'loss/train': 1.0816410779953003} 08/31/2021 07:41:36 - INFO - __main__ - Step 102299: {'lr': 0.00011757919398094924, 'samples': 19641408, 'steps': 102298, 'loss/train': 0.7703390717506409} 08/31/2021 07:41:37 - INFO - __main__ - Step 102300: {'lr': 0.00011757469285387046, 'samples': 19641600, 'steps': 102299, 'loss/train': 1.5100009441375732} 08/31/2021 07:41:37 - INFO - __main__ - Step 102301: {'lr': 0.0001175701917864605, 'samples': 19641792, 'steps': 102300, 'loss/train': 0.9503892064094543} 08/31/2021 07:41:38 - INFO - __main__ - Step 102302: {'lr': 0.00011756569077872136, 'samples': 19641984, 'steps': 102301, 'loss/train': 1.2431458234786987} 08/31/2021 07:41:39 - INFO - __main__ - Step 102303: {'lr': 0.00011756118983065506, 'samples': 19642176, 'steps': 102302, 'loss/train': 0.0389440692961216} 08/31/2021 07:41:39 - INFO - __main__ - Step 102304: {'lr': 0.00011755668894226368, 'samples': 19642368, 'steps': 102303, 'loss/train': 1.339013695716858} 08/31/2021 07:41:40 - INFO - __main__ - Step 102305: {'lr': 0.00011755218811354918, 'samples': 19642560, 'steps': 102304, 'loss/train': 0.7803480625152588} 08/31/2021 07:41:40 - INFO - __main__ - Step 102306: {'lr': 0.00011754768734451373, 'samples': 19642752, 'steps': 102305, 'loss/train': 0.797426700592041} 08/31/2021 07:41:42 - INFO - __main__ - Step 102307: {'lr': 0.00011754318663515915, 'samples': 19642944, 'steps': 102306, 'loss/train': 0.947338342666626} 08/31/2021 07:41:42 - INFO - __main__ - Step 102308: {'lr': 0.00011753868598548756, 'samples': 19643136, 'steps': 102307, 'loss/train': 1.0535049438476562} 08/31/2021 07:41:42 - INFO - __main__ - Step 102309: {'lr': 0.00011753418539550101, 'samples': 19643328, 'steps': 102308, 'loss/train': 0.022563055157661438} 08/31/2021 07:41:43 - INFO - __main__ - Step 102310: {'lr': 0.00011752968486520149, 'samples': 19643520, 'steps': 102309, 'loss/train': 1.5088797807693481} 08/31/2021 07:41:43 - INFO - __main__ - Step 102311: {'lr': 0.00011752518439459106, 'samples': 19643712, 'steps': 102310, 'loss/train': 1.502281665802002} 08/31/2021 07:41:43 - INFO - __main__ - Step 102312: {'lr': 0.00011752068398367174, 'samples': 19643904, 'steps': 102311, 'loss/train': 1.4914990663528442} 08/31/2021 07:41:45 - INFO - __main__ - Step 102313: {'lr': 0.00011751618363244557, 'samples': 19644096, 'steps': 102312, 'loss/train': 1.3660997152328491} 08/31/2021 07:41:45 - INFO - __main__ - Step 102314: {'lr': 0.00011751168334091455, 'samples': 19644288, 'steps': 102313, 'loss/train': 0.49551692605018616} 08/31/2021 07:41:46 - INFO - __main__ - Step 102315: {'lr': 0.00011750718310908071, 'samples': 19644480, 'steps': 102314, 'loss/train': 0.1682036966085434} 08/31/2021 07:41:46 - INFO - __main__ - Step 102316: {'lr': 0.0001175026829369461, 'samples': 19644672, 'steps': 102315, 'loss/train': 1.0722614526748657} 08/31/2021 07:41:46 - INFO - __main__ - Step 102317: {'lr': 0.00011749818282451275, 'samples': 19644864, 'steps': 102316, 'loss/train': 1.058375597000122} 08/31/2021 07:41:48 - INFO - __main__ - Step 102318: {'lr': 0.00011749368277178266, 'samples': 19645056, 'steps': 102317, 'loss/train': 0.3215196132659912} 08/31/2021 07:41:48 - INFO - __main__ - Step 102319: {'lr': 0.00011748918277875787, 'samples': 19645248, 'steps': 102318, 'loss/train': 0.6978884935379028} 08/31/2021 07:41:49 - INFO - __main__ - Step 102320: {'lr': 0.0001174846828454405, 'samples': 19645440, 'steps': 102319, 'loss/train': 1.2578434944152832} 08/31/2021 07:41:49 - INFO - __main__ - Step 102321: {'lr': 0.00011748018297183238, 'samples': 19645632, 'steps': 102320, 'loss/train': 1.1938332319259644} 08/31/2021 07:41:49 - INFO - __main__ - Step 102322: {'lr': 0.00011747568315793567, 'samples': 19645824, 'steps': 102321, 'loss/train': 1.0901250839233398} 08/31/2021 07:41:51 - INFO - __main__ - Step 102323: {'lr': 0.00011747118340375238, 'samples': 19646016, 'steps': 102322, 'loss/train': 1.4457041025161743} 08/31/2021 07:41:52 - INFO - __main__ - Step 102324: {'lr': 0.00011746668370928452, 'samples': 19646208, 'steps': 102323, 'loss/train': 0.08491788059473038} 08/31/2021 07:41:52 - INFO - __main__ - Step 102325: {'lr': 0.0001174621840745341, 'samples': 19646400, 'steps': 102324, 'loss/train': 1.0580565929412842} 08/31/2021 07:41:52 - INFO - __main__ - Step 102326: {'lr': 0.0001174576844995032, 'samples': 19646592, 'steps': 102325, 'loss/train': 0.4266042113304138} 08/31/2021 07:41:53 - INFO - __main__ - Step 102327: {'lr': 0.00011745318498419383, 'samples': 19646784, 'steps': 102326, 'loss/train': 0.927969753742218} 08/31/2021 07:41:54 - INFO - __main__ - Step 102328: {'lr': 0.00011744868552860799, 'samples': 19646976, 'steps': 102327, 'loss/train': 0.33023637533187866} 08/31/2021 07:41:55 - INFO - __main__ - Step 102329: {'lr': 0.00011744418613274773, 'samples': 19647168, 'steps': 102328, 'loss/train': 1.1078118085861206} 08/31/2021 07:41:55 - INFO - __main__ - Step 102330: {'lr': 0.00011743968679661507, 'samples': 19647360, 'steps': 102329, 'loss/train': 1.2525793313980103} 08/31/2021 07:41:56 - INFO - __main__ - Step 102331: {'lr': 0.00011743518752021206, 'samples': 19647552, 'steps': 102330, 'loss/train': 1.423476219177246} 08/31/2021 07:41:56 - INFO - __main__ - Step 102332: {'lr': 0.0001174306883035407, 'samples': 19647744, 'steps': 102331, 'loss/train': 0.6329155564308167} 08/31/2021 07:41:58 - INFO - __main__ - Step 102333: {'lr': 0.00011742618914660311, 'samples': 19647936, 'steps': 102332, 'loss/train': 1.218291997909546} 08/31/2021 07:41:58 - INFO - __main__ - Step 102334: {'lr': 0.00011742169004940115, 'samples': 19648128, 'steps': 102333, 'loss/train': 0.7609556913375854} 08/31/2021 07:41:58 - INFO - __main__ - Step 102335: {'lr': 0.00011741719101193693, 'samples': 19648320, 'steps': 102334, 'loss/train': 1.4190921783447266} 08/31/2021 07:41:59 - INFO - __main__ - Step 102336: {'lr': 0.00011741269203421248, 'samples': 19648512, 'steps': 102335, 'loss/train': 0.9892703294754028} 08/31/2021 07:41:59 - INFO - __main__ - Step 102337: {'lr': 0.00011740819311622983, 'samples': 19648704, 'steps': 102336, 'loss/train': 1.3465925455093384} 08/31/2021 07:41:59 - INFO - __main__ - Step 102338: {'lr': 0.000117403694257991, 'samples': 19648896, 'steps': 102337, 'loss/train': 1.3023918867111206} 08/31/2021 07:42:01 - INFO - __main__ - Step 102339: {'lr': 0.00011739919545949801, 'samples': 19649088, 'steps': 102338, 'loss/train': 0.7343723177909851} 08/31/2021 07:42:02 - INFO - __main__ - Step 102340: {'lr': 0.0001173946967207529, 'samples': 19649280, 'steps': 102339, 'loss/train': 0.6331624388694763} 08/31/2021 07:42:02 - INFO - __main__ - Step 102341: {'lr': 0.00011739019804175769, 'samples': 19649472, 'steps': 102340, 'loss/train': 0.02520127408206463} 08/31/2021 07:42:03 - INFO - __main__ - Step 102342: {'lr': 0.00011738569942251443, 'samples': 19649664, 'steps': 102341, 'loss/train': 1.3364768028259277} 08/31/2021 07:42:03 - INFO - __main__ - Step 102343: {'lr': 0.00011738120086302509, 'samples': 19649856, 'steps': 102342, 'loss/train': 1.261439561843872} 08/31/2021 07:42:05 - INFO - __main__ - Step 102344: {'lr': 0.00011737670236329176, 'samples': 19650048, 'steps': 102343, 'loss/train': 0.7983510494232178} 08/31/2021 07:42:05 - INFO - __main__ - Step 102345: {'lr': 0.00011737220392331644, 'samples': 19650240, 'steps': 102344, 'loss/train': 0.9695695042610168} 08/31/2021 07:42:05 - INFO - __main__ - Step 102346: {'lr': 0.00011736770554310117, 'samples': 19650432, 'steps': 102345, 'loss/train': 0.6908962726593018} 08/31/2021 07:42:06 - INFO - __main__ - Step 102347: {'lr': 0.00011736320722264804, 'samples': 19650624, 'steps': 102346, 'loss/train': 1.173563838005066} 08/31/2021 07:42:06 - INFO - __main__ - Step 102348: {'lr': 0.0001173587089619589, 'samples': 19650816, 'steps': 102347, 'loss/train': 0.7747337222099304} 08/31/2021 07:42:07 - INFO - __main__ - Step 102349: {'lr': 0.00011735421076103589, 'samples': 19651008, 'steps': 102348, 'loss/train': 1.1861820220947266} 08/31/2021 07:42:08 - INFO - __main__ - Step 102350: {'lr': 0.00011734971261988104, 'samples': 19651200, 'steps': 102349, 'loss/train': 0.4289950430393219} 08/31/2021 07:42:08 - INFO - __main__ - Step 102351: {'lr': 0.00011734521453849634, 'samples': 19651392, 'steps': 102350, 'loss/train': 0.20840367674827576} 08/31/2021 07:42:09 - INFO - __main__ - Step 102352: {'lr': 0.00011734071651688385, 'samples': 19651584, 'steps': 102351, 'loss/train': 1.4170585870742798} 08/31/2021 07:42:09 - INFO - __main__ - Step 102353: {'lr': 0.00011733621855504559, 'samples': 19651776, 'steps': 102352, 'loss/train': 1.3308602571487427} 08/31/2021 07:42:10 - INFO - __main__ - Step 102354: {'lr': 0.00011733172065298358, 'samples': 19651968, 'steps': 102353, 'loss/train': 0.08344083279371262} 08/31/2021 07:42:11 - INFO - __main__ - Step 102355: {'lr': 0.00011732722281069985, 'samples': 19652160, 'steps': 102354, 'loss/train': 0.4188515245914459} 08/31/2021 07:42:11 - INFO - __main__ - Step 102356: {'lr': 0.00011732272502819644, 'samples': 19652352, 'steps': 102355, 'loss/train': 0.28787171840667725} 08/31/2021 07:42:12 - INFO - __main__ - Step 102357: {'lr': 0.00011731822730547534, 'samples': 19652544, 'steps': 102356, 'loss/train': 1.4396100044250488} 08/31/2021 07:42:12 - INFO - __main__ - Step 102358: {'lr': 0.00011731372964253861, 'samples': 19652736, 'steps': 102357, 'loss/train': 2.2108230590820312} 08/31/2021 07:42:13 - INFO - __main__ - Step 102359: {'lr': 0.00011730923203938826, 'samples': 19652928, 'steps': 102358, 'loss/train': 0.8981300592422485} 08/31/2021 07:42:14 - INFO - __main__ - Step 102360: {'lr': 0.0001173047344960264, 'samples': 19653120, 'steps': 102359, 'loss/train': 1.3408383131027222} 08/31/2021 07:42:14 - INFO - __main__ - Step 102361: {'lr': 0.00011730023701245493, 'samples': 19653312, 'steps': 102360, 'loss/train': 1.5323679447174072} 08/31/2021 07:42:15 - INFO - __main__ - Step 102362: {'lr': 0.0001172957395886759, 'samples': 19653504, 'steps': 102361, 'loss/train': 0.8102272152900696} 08/31/2021 07:42:15 - INFO - __main__ - Step 102363: {'lr': 0.00011729124222469134, 'samples': 19653696, 'steps': 102362, 'loss/train': 0.5412476062774658} 08/31/2021 07:42:16 - INFO - __main__ - Step 102364: {'lr': 0.00011728674492050333, 'samples': 19653888, 'steps': 102363, 'loss/train': 0.9640061855316162} 08/31/2021 07:42:17 - INFO - __main__ - Step 102365: {'lr': 0.00011728224767611386, 'samples': 19654080, 'steps': 102364, 'loss/train': 1.007182240486145} 08/31/2021 07:42:17 - INFO - __main__ - Step 102366: {'lr': 0.00011727775049152495, 'samples': 19654272, 'steps': 102365, 'loss/train': 1.5960040092468262} 08/31/2021 07:42:18 - INFO - __main__ - Step 102367: {'lr': 0.00011727325336673864, 'samples': 19654464, 'steps': 102366, 'loss/train': 1.2190369367599487} 08/31/2021 07:42:18 - INFO - __main__ - Step 102368: {'lr': 0.00011726875630175696, 'samples': 19654656, 'steps': 102367, 'loss/train': 1.6903659105300903} 08/31/2021 07:42:20 - INFO - __main__ - Step 102369: {'lr': 0.00011726425929658193, 'samples': 19654848, 'steps': 102368, 'loss/train': 0.8056348562240601} 08/31/2021 07:42:20 - INFO - __main__ - Step 102370: {'lr': 0.00011725976235121557, 'samples': 19655040, 'steps': 102369, 'loss/train': 1.4467337131500244} 08/31/2021 07:42:20 - INFO - __main__ - Step 102371: {'lr': 0.00011725526546565993, 'samples': 19655232, 'steps': 102370, 'loss/train': 0.8660365343093872} 08/31/2021 07:42:21 - INFO - __main__ - Step 102372: {'lr': 0.00011725076863991699, 'samples': 19655424, 'steps': 102371, 'loss/train': 1.3761767148971558} 08/31/2021 07:42:21 - INFO - __main__ - Step 102373: {'lr': 0.00011724627187398892, 'samples': 19655616, 'steps': 102372, 'loss/train': 1.4174879789352417} 08/31/2021 07:42:22 - INFO - __main__ - Step 102374: {'lr': 0.00011724177516787754, 'samples': 19655808, 'steps': 102373, 'loss/train': 1.3538779020309448} 08/31/2021 07:42:23 - INFO - __main__ - Step 102375: {'lr': 0.00011723727852158495, 'samples': 19656000, 'steps': 102374, 'loss/train': 1.246534824371338} 08/31/2021 07:42:23 - INFO - __main__ - Step 102376: {'lr': 0.00011723278193511322, 'samples': 19656192, 'steps': 102375, 'loss/train': 1.2634598016738892} 08/31/2021 07:42:24 - INFO - __main__ - Step 102377: {'lr': 0.00011722828540846434, 'samples': 19656384, 'steps': 102376, 'loss/train': 1.5203737020492554} 08/31/2021 07:42:24 - INFO - __main__ - Step 102378: {'lr': 0.00011722378894164031, 'samples': 19656576, 'steps': 102377, 'loss/train': 1.405561923980713} 08/31/2021 07:42:26 - INFO - __main__ - Step 102379: {'lr': 0.00011721929253464323, 'samples': 19656768, 'steps': 102378, 'loss/train': 0.31710073351860046} 08/31/2021 07:42:26 - INFO - __main__ - Step 102380: {'lr': 0.00011721479618747507, 'samples': 19656960, 'steps': 102379, 'loss/train': 0.5983393788337708} 08/31/2021 07:42:27 - INFO - __main__ - Step 102381: {'lr': 0.0001172102999001379, 'samples': 19657152, 'steps': 102380, 'loss/train': 1.1380833387374878} 08/31/2021 07:42:27 - INFO - __main__ - Step 102382: {'lr': 0.0001172058036726337, 'samples': 19657344, 'steps': 102381, 'loss/train': 1.5110979080200195} 08/31/2021 07:42:27 - INFO - __main__ - Step 102383: {'lr': 0.00011720130750496452, 'samples': 19657536, 'steps': 102382, 'loss/train': 0.04910941421985626} 08/31/2021 07:42:29 - INFO - __main__ - Step 102384: {'lr': 0.00011719681139713237, 'samples': 19657728, 'steps': 102383, 'loss/train': 0.9725580811500549} 08/31/2021 07:42:29 - INFO - __main__ - Step 102385: {'lr': 0.00011719231534913932, 'samples': 19657920, 'steps': 102384, 'loss/train': 1.4142217636108398} 08/31/2021 07:42:30 - INFO - __main__ - Step 102386: {'lr': 0.00011718781936098744, 'samples': 19658112, 'steps': 102385, 'loss/train': 1.4970678091049194} 08/31/2021 07:42:30 - INFO - __main__ - Step 102387: {'lr': 0.00011718332343267857, 'samples': 19658304, 'steps': 102386, 'loss/train': 0.257293164730072} 08/31/2021 07:42:30 - INFO - __main__ - Step 102388: {'lr': 0.00011717882756421485, 'samples': 19658496, 'steps': 102387, 'loss/train': 1.3254281282424927} 08/31/2021 07:42:31 - INFO - __main__ - Step 102389: {'lr': 0.00011717433175559831, 'samples': 19658688, 'steps': 102388, 'loss/train': 0.5523635149002075} 08/31/2021 07:42:32 - INFO - __main__ - Step 102390: {'lr': 0.00011716983600683096, 'samples': 19658880, 'steps': 102389, 'loss/train': 0.7919734716415405} 08/31/2021 07:42:33 - INFO - __main__ - Step 102391: {'lr': 0.00011716534031791485, 'samples': 19659072, 'steps': 102390, 'loss/train': 1.3449995517730713} 08/31/2021 07:42:33 - INFO - __main__ - Step 102392: {'lr': 0.00011716084468885197, 'samples': 19659264, 'steps': 102391, 'loss/train': 1.1846877336502075} 08/31/2021 07:42:33 - INFO - __main__ - Step 102393: {'lr': 0.00011715634911964434, 'samples': 19659456, 'steps': 102392, 'loss/train': 1.1713947057724} 08/31/2021 07:42:34 - INFO - __main__ - Step 102394: {'lr': 0.00011715185361029404, 'samples': 19659648, 'steps': 102393, 'loss/train': 0.8780636787414551} 08/31/2021 07:42:36 - INFO - __main__ - Step 102395: {'lr': 0.00011714735816080308, 'samples': 19659840, 'steps': 102394, 'loss/train': 0.1119748204946518} 08/31/2021 07:42:37 - INFO - __main__ - Step 102396: {'lr': 0.00011714286277117344, 'samples': 19660032, 'steps': 102395, 'loss/train': 0.9278119206428528} 08/31/2021 07:42:37 - INFO - __main__ - Step 102397: {'lr': 0.00011713836744140727, 'samples': 19660224, 'steps': 102396, 'loss/train': 0.5051430463790894} 08/31/2021 07:42:37 - INFO - __main__ - Step 102398: {'lr': 0.00011713387217150642, 'samples': 19660416, 'steps': 102397, 'loss/train': 1.0693871974945068} 08/31/2021 07:42:38 - INFO - __main__ - Step 102399: {'lr': 0.00011712937696147299, 'samples': 19660608, 'steps': 102398, 'loss/train': 0.17410939931869507} 08/31/2021 07:42:39 - INFO - __main__ - Step 102400: {'lr': 0.00011712488181130903, 'samples': 19660800, 'steps': 102399, 'loss/train': 0.4597470760345459} 08/31/2021 07:42:40 - INFO - __main__ - Step 102401: {'lr': 0.00011712038672101654, 'samples': 19660992, 'steps': 102400, 'loss/train': 1.2276209592819214} 08/31/2021 07:42:40 - INFO - __main__ - Step 102402: {'lr': 0.00011711589169059756, 'samples': 19661184, 'steps': 102401, 'loss/train': 1.4235634803771973} 08/31/2021 07:42:41 - INFO - __main__ - Step 102403: {'lr': 0.00011711139672005408, 'samples': 19661376, 'steps': 102402, 'loss/train': 1.1638814210891724} 08/31/2021 07:42:41 - INFO - __main__ - Step 102404: {'lr': 0.00011710690180938818, 'samples': 19661568, 'steps': 102403, 'loss/train': 0.1084807813167572} 08/31/2021 07:42:43 - INFO - __main__ - Step 102405: {'lr': 0.00011710240695860183, 'samples': 19661760, 'steps': 102404, 'loss/train': 1.2231035232543945} 08/31/2021 07:42:43 - INFO - __main__ - Step 102406: {'lr': 0.00011709791216769711, 'samples': 19661952, 'steps': 102405, 'loss/train': 0.9849667549133301} 08/31/2021 07:42:43 - INFO - __main__ - Step 102407: {'lr': 0.000117093417436676, 'samples': 19662144, 'steps': 102406, 'loss/train': 1.56538987159729} 08/31/2021 07:42:44 - INFO - __main__ - Step 102408: {'lr': 0.00011708892276554067, 'samples': 19662336, 'steps': 102407, 'loss/train': 1.0260677337646484} 08/31/2021 07:42:44 - INFO - __main__ - Step 102409: {'lr': 0.00011708442815429291, 'samples': 19662528, 'steps': 102408, 'loss/train': 0.6093288660049438} 08/31/2021 07:42:44 - INFO - __main__ - Step 102410: {'lr': 0.00011707993360293486, 'samples': 19662720, 'steps': 102409, 'loss/train': 1.0089061260223389} 08/31/2021 07:42:46 - INFO - __main__ - Step 102411: {'lr': 0.00011707543911146854, 'samples': 19662912, 'steps': 102410, 'loss/train': 0.2866598069667816} 08/31/2021 07:42:46 - INFO - __main__ - Step 102412: {'lr': 0.00011707094467989598, 'samples': 19663104, 'steps': 102411, 'loss/train': 0.5885066986083984} 08/31/2021 07:42:47 - INFO - __main__ - Step 102413: {'lr': 0.00011706645030821919, 'samples': 19663296, 'steps': 102412, 'loss/train': 1.8192411661148071} 08/31/2021 07:42:47 - INFO - __main__ - Step 102414: {'lr': 0.00011706195599644021, 'samples': 19663488, 'steps': 102413, 'loss/train': 1.130923867225647} 08/31/2021 07:42:47 - INFO - __main__ - Step 102415: {'lr': 0.00011705746174456106, 'samples': 19663680, 'steps': 102414, 'loss/train': 0.7840981483459473} 08/31/2021 07:42:49 - INFO - __main__ - Step 102416: {'lr': 0.00011705296755258376, 'samples': 19663872, 'steps': 102415, 'loss/train': 0.811585009098053} 08/31/2021 07:42:50 - INFO - __main__ - Step 102417: {'lr': 0.00011704847342051036, 'samples': 19664064, 'steps': 102416, 'loss/train': 1.5457533597946167} 08/31/2021 07:42:50 - INFO - __main__ - Step 102418: {'lr': 0.00011704397934834284, 'samples': 19664256, 'steps': 102417, 'loss/train': 1.8305449485778809} 08/31/2021 07:42:50 - INFO - __main__ - Step 102419: {'lr': 0.00011703948533608339, 'samples': 19664448, 'steps': 102418, 'loss/train': 1.1519792079925537} 08/31/2021 07:42:51 - INFO - __main__ - Step 102420: {'lr': 0.00011703499138373375, 'samples': 19664640, 'steps': 102419, 'loss/train': 1.1157273054122925} 08/31/2021 07:42:52 - INFO - __main__ - Step 102421: {'lr': 0.00011703049749129613, 'samples': 19664832, 'steps': 102420, 'loss/train': 0.09434758126735687} 08/31/2021 07:42:53 - INFO - __main__ - Step 102422: {'lr': 0.0001170260036587725, 'samples': 19665024, 'steps': 102421, 'loss/train': 1.462384581565857} 08/31/2021 07:42:53 - INFO - __main__ - Step 102423: {'lr': 0.0001170215098861649, 'samples': 19665216, 'steps': 102422, 'loss/train': 1.472336769104004} 08/31/2021 07:42:53 - INFO - __main__ - Step 102424: {'lr': 0.00011701701617347535, 'samples': 19665408, 'steps': 102423, 'loss/train': 1.1804503202438354} 08/31/2021 07:42:54 - INFO - __main__ - Step 102425: {'lr': 0.00011701252252070587, 'samples': 19665600, 'steps': 102424, 'loss/train': 1.114054560661316} 08/31/2021 07:42:55 - INFO - __main__ - Step 102426: {'lr': 0.00011700802892785852, 'samples': 19665792, 'steps': 102425, 'loss/train': 0.9694872498512268} 08/31/2021 07:42:56 - INFO - __main__ - Step 102427: {'lr': 0.0001170035353949353, 'samples': 19665984, 'steps': 102426, 'loss/train': 1.4860697984695435} 08/31/2021 07:42:56 - INFO - __main__ - Step 102428: {'lr': 0.00011699904192193822, 'samples': 19666176, 'steps': 102427, 'loss/train': 1.5392858982086182} 08/31/2021 07:42:56 - INFO - __main__ - Step 102429: {'lr': 0.00011699454850886935, 'samples': 19666368, 'steps': 102428, 'loss/train': 1.6791350841522217} 08/31/2021 07:42:57 - INFO - __main__ - Step 102430: {'lr': 0.00011699005515573075, 'samples': 19666560, 'steps': 102429, 'loss/train': 1.5518577098846436} 08/31/2021 07:42:57 - INFO - __main__ - Step 102431: {'lr': 0.00011698556186252429, 'samples': 19666752, 'steps': 102430, 'loss/train': 0.4427405893802643} 08/31/2021 07:42:59 - INFO - __main__ - Step 102432: {'lr': 0.00011698106862925206, 'samples': 19666944, 'steps': 102431, 'loss/train': 1.8368427753448486} 08/31/2021 07:42:59 - INFO - __main__ - Step 102433: {'lr': 0.00011697657545591614, 'samples': 19667136, 'steps': 102432, 'loss/train': 1.1857070922851562} 08/31/2021 07:42:59 - INFO - __main__ - Step 102434: {'lr': 0.00011697208234251852, 'samples': 19667328, 'steps': 102433, 'loss/train': 0.8072631359100342} 08/31/2021 07:43:00 - INFO - __main__ - Step 102435: {'lr': 0.00011696758928906123, 'samples': 19667520, 'steps': 102434, 'loss/train': 0.657738447189331} 08/31/2021 07:43:00 - INFO - __main__ - Step 102436: {'lr': 0.00011696309629554627, 'samples': 19667712, 'steps': 102435, 'loss/train': 1.0464574098587036} 08/31/2021 07:43:02 - INFO - __main__ - Step 102437: {'lr': 0.0001169586033619757, 'samples': 19667904, 'steps': 102436, 'loss/train': 1.2441805601119995} 08/31/2021 07:43:02 - INFO - __main__ - Step 102438: {'lr': 0.00011695411048835153, 'samples': 19668096, 'steps': 102437, 'loss/train': 1.731823205947876} 08/31/2021 07:43:02 - INFO - __main__ - Step 102439: {'lr': 0.00011694961767467576, 'samples': 19668288, 'steps': 102438, 'loss/train': 1.236121416091919} 08/31/2021 07:43:03 - INFO - __main__ - Step 102440: {'lr': 0.00011694512492095047, 'samples': 19668480, 'steps': 102439, 'loss/train': 0.8934429287910461} 08/31/2021 07:43:03 - INFO - __main__ - Step 102441: {'lr': 0.00011694063222717774, 'samples': 19668672, 'steps': 102440, 'loss/train': 1.0332175493240356} 08/31/2021 07:43:05 - INFO - __main__ - Step 102442: {'lr': 0.00011693613959335942, 'samples': 19668864, 'steps': 102441, 'loss/train': 0.8793565034866333} 08/31/2021 07:43:06 - INFO - __main__ - Step 102443: {'lr': 0.00011693164701949763, 'samples': 19669056, 'steps': 102442, 'loss/train': 1.1771490573883057} 08/31/2021 07:43:06 - INFO - __main__ - Step 102444: {'lr': 0.00011692715450559435, 'samples': 19669248, 'steps': 102443, 'loss/train': 1.0158499479293823} 08/31/2021 07:43:06 - INFO - __main__ - Step 102445: {'lr': 0.00011692266205165166, 'samples': 19669440, 'steps': 102444, 'loss/train': 0.01621103845536709} 08/31/2021 07:43:07 - INFO - __main__ - Step 102446: {'lr': 0.00011691816965767157, 'samples': 19669632, 'steps': 102445, 'loss/train': 0.37086743116378784} 08/31/2021 07:43:07 - INFO - __main__ - Step 102447: {'lr': 0.0001169136773236561, 'samples': 19669824, 'steps': 102446, 'loss/train': 0.8906146287918091} 08/31/2021 07:43:09 - INFO - __main__ - Step 102448: {'lr': 0.00011690918504960726, 'samples': 19670016, 'steps': 102447, 'loss/train': 1.6597976684570312} 08/31/2021 07:43:10 - INFO - __main__ - Step 102449: {'lr': 0.00011690469283552713, 'samples': 19670208, 'steps': 102448, 'loss/train': 0.5850132703781128} 08/31/2021 07:43:10 - INFO - __main__ - Step 102450: {'lr': 0.00011690020068141766, 'samples': 19670400, 'steps': 102449, 'loss/train': 1.2567462921142578} 08/31/2021 07:43:10 - INFO - __main__ - Step 102451: {'lr': 0.00011689570858728088, 'samples': 19670592, 'steps': 102450, 'loss/train': 1.1866278648376465} 08/31/2021 07:43:11 - INFO - __main__ - Step 102452: {'lr': 0.00011689121655311888, 'samples': 19670784, 'steps': 102451, 'loss/train': 1.2232611179351807} 08/31/2021 07:43:12 - INFO - __main__ - Step 102453: {'lr': 0.00011688672457893363, 'samples': 19670976, 'steps': 102452, 'loss/train': 0.9788064360618591} 08/31/2021 07:43:12 - INFO - __main__ - Step 102454: {'lr': 0.00011688223266472726, 'samples': 19671168, 'steps': 102453, 'loss/train': 1.2409846782684326} 08/31/2021 07:43:13 - INFO - __main__ - Step 102455: {'lr': 0.00011687774081050159, 'samples': 19671360, 'steps': 102454, 'loss/train': 1.0488736629486084} 08/31/2021 07:43:13 - INFO - __main__ - Step 102456: {'lr': 0.00011687324901625879, 'samples': 19671552, 'steps': 102455, 'loss/train': 1.5804874897003174} 08/31/2021 07:43:13 - INFO - __main__ - Step 102457: {'lr': 0.00011686875728200083, 'samples': 19671744, 'steps': 102456, 'loss/train': 0.8128859996795654} 08/31/2021 07:43:15 - INFO - __main__ - Step 102458: {'lr': 0.00011686426560772975, 'samples': 19671936, 'steps': 102457, 'loss/train': 0.691148579120636} 08/31/2021 07:43:16 - INFO - __main__ - Step 102459: {'lr': 0.00011685977399344758, 'samples': 19672128, 'steps': 102458, 'loss/train': 0.5882441401481628} 08/31/2021 07:43:16 - INFO - __main__ - Step 102460: {'lr': 0.00011685528243915635, 'samples': 19672320, 'steps': 102459, 'loss/train': 1.1633669137954712} 08/31/2021 07:43:16 - INFO - __main__ - Step 102461: {'lr': 0.00011685079094485807, 'samples': 19672512, 'steps': 102460, 'loss/train': 1.0511947870254517} 08/31/2021 07:43:17 - INFO - __main__ - Step 102462: {'lr': 0.00011684629951055478, 'samples': 19672704, 'steps': 102461, 'loss/train': 0.6128777265548706} 08/31/2021 07:43:18 - INFO - __main__ - Step 102463: {'lr': 0.00011684180813624847, 'samples': 19672896, 'steps': 102462, 'loss/train': 0.639450192451477} 08/31/2021 07:43:19 - INFO - __main__ - Step 102464: {'lr': 0.0001168373168219412, 'samples': 19673088, 'steps': 102463, 'loss/train': 0.49736571311950684} 08/31/2021 07:43:19 - INFO - __main__ - Step 102465: {'lr': 0.000116832825567635, 'samples': 19673280, 'steps': 102464, 'loss/train': 0.8523269295692444} 08/31/2021 07:43:19 - INFO - __main__ - Step 102466: {'lr': 0.00011682833437333185, 'samples': 19673472, 'steps': 102465, 'loss/train': 1.5401464700698853} 08/31/2021 07:43:20 - INFO - __main__ - Step 102467: {'lr': 0.0001168238432390338, 'samples': 19673664, 'steps': 102466, 'loss/train': 0.07178909331560135} 08/31/2021 07:43:21 - INFO - __main__ - Step 102468: {'lr': 0.00011681935216474296, 'samples': 19673856, 'steps': 102467, 'loss/train': 0.9361916184425354} 08/31/2021 07:43:22 - INFO - __main__ - Step 102469: {'lr': 0.00011681486115046117, 'samples': 19674048, 'steps': 102468, 'loss/train': 0.8190920948982239} 08/31/2021 07:43:22 - INFO - __main__ - Step 102470: {'lr': 0.00011681037019619056, 'samples': 19674240, 'steps': 102469, 'loss/train': 1.2162302732467651} 08/31/2021 07:43:22 - INFO - __main__ - Step 102471: {'lr': 0.00011680587930193315, 'samples': 19674432, 'steps': 102470, 'loss/train': 1.6963609457015991} 08/31/2021 07:43:23 - INFO - __main__ - Step 102472: {'lr': 0.00011680138846769093, 'samples': 19674624, 'steps': 102471, 'loss/train': 1.0304129123687744} 08/31/2021 07:43:23 - INFO - __main__ - Step 102473: {'lr': 0.00011679689769346596, 'samples': 19674816, 'steps': 102472, 'loss/train': 1.3489798307418823} 08/31/2021 07:43:25 - INFO - __main__ - Step 102474: {'lr': 0.00011679240697926027, 'samples': 19675008, 'steps': 102473, 'loss/train': 1.059310793876648} 08/31/2021 07:43:25 - INFO - __main__ - Step 102475: {'lr': 0.00011678791632507585, 'samples': 19675200, 'steps': 102474, 'loss/train': 1.692676067352295} 08/31/2021 07:43:26 - INFO - __main__ - Step 102476: {'lr': 0.00011678342573091474, 'samples': 19675392, 'steps': 102475, 'loss/train': 0.685514509677887} 08/31/2021 07:43:26 - INFO - __main__ - Step 102477: {'lr': 0.00011677893519677896, 'samples': 19675584, 'steps': 102476, 'loss/train': 1.7797552347183228} 08/31/2021 07:43:27 - INFO - __main__ - Step 102478: {'lr': 0.00011677444472267054, 'samples': 19675776, 'steps': 102477, 'loss/train': 1.0810514688491821} 08/31/2021 07:43:28 - INFO - __main__ - Step 102479: {'lr': 0.00011676995430859149, 'samples': 19675968, 'steps': 102478, 'loss/train': 0.9777151942253113} 08/31/2021 07:43:29 - INFO - __main__ - Step 102480: {'lr': 0.00011676546395454385, 'samples': 19676160, 'steps': 102479, 'loss/train': 1.4167225360870361} 08/31/2021 07:43:29 - INFO - __main__ - Step 102481: {'lr': 0.00011676097366052974, 'samples': 19676352, 'steps': 102480, 'loss/train': 1.2490180730819702} 08/31/2021 07:43:29 - INFO - __main__ - Step 102482: {'lr': 0.00011675648342655095, 'samples': 19676544, 'steps': 102481, 'loss/train': 1.1045703887939453} 08/31/2021 07:43:30 - INFO - __main__ - Step 102483: {'lr': 0.00011675199325260968, 'samples': 19676736, 'steps': 102482, 'loss/train': 1.7393107414245605} 08/31/2021 07:43:31 - INFO - __main__ - Step 102484: {'lr': 0.00011674750313870789, 'samples': 19676928, 'steps': 102483, 'loss/train': 0.1648765653371811} 08/31/2021 07:43:32 - INFO - __main__ - Step 102485: {'lr': 0.00011674301308484761, 'samples': 19677120, 'steps': 102484, 'loss/train': 1.5384507179260254} 08/31/2021 07:43:32 - INFO - __main__ - Step 102486: {'lr': 0.00011673852309103086, 'samples': 19677312, 'steps': 102485, 'loss/train': 0.17024339735507965} 08/31/2021 07:43:32 - INFO - __main__ - Step 102487: {'lr': 0.00011673403315725969, 'samples': 19677504, 'steps': 102486, 'loss/train': 0.2251347452402115} 08/31/2021 07:43:33 - INFO - __main__ - Step 102488: {'lr': 0.0001167295432835361, 'samples': 19677696, 'steps': 102487, 'loss/train': 0.8705334067344666} 08/31/2021 07:43:34 - INFO - __main__ - Step 102489: {'lr': 0.00011672505346986214, 'samples': 19677888, 'steps': 102488, 'loss/train': 1.2029677629470825} 08/31/2021 07:43:35 - INFO - __main__ - Step 102490: {'lr': 0.00011672056371623982, 'samples': 19678080, 'steps': 102489, 'loss/train': 1.0819262266159058} 08/31/2021 07:43:35 - INFO - __main__ - Step 102491: {'lr': 0.00011671607402267112, 'samples': 19678272, 'steps': 102490, 'loss/train': 0.22703580558300018} 08/31/2021 07:43:35 - INFO - __main__ - Step 102492: {'lr': 0.00011671158438915813, 'samples': 19678464, 'steps': 102491, 'loss/train': 0.847062885761261} 08/31/2021 07:43:36 - INFO - __main__ - Step 102493: {'lr': 0.00011670709481570285, 'samples': 19678656, 'steps': 102492, 'loss/train': 1.2718236446380615} 08/31/2021 07:43:37 - INFO - __main__ - Step 102494: {'lr': 0.00011670260530230736, 'samples': 19678848, 'steps': 102493, 'loss/train': 1.21174156665802} 08/31/2021 07:43:38 - INFO - __main__ - Step 102495: {'lr': 0.00011669811584897355, 'samples': 19679040, 'steps': 102494, 'loss/train': 0.4952957332134247} 08/31/2021 07:43:38 - INFO - __main__ - Step 102496: {'lr': 0.0001166936264557035, 'samples': 19679232, 'steps': 102495, 'loss/train': 1.6930330991744995} 08/31/2021 07:43:38 - INFO - __main__ - Step 102497: {'lr': 0.00011668913712249923, 'samples': 19679424, 'steps': 102496, 'loss/train': 1.1400229930877686} 08/31/2021 07:43:39 - INFO - __main__ - Step 102498: {'lr': 0.0001166846478493628, 'samples': 19679616, 'steps': 102497, 'loss/train': 1.1178096532821655} 08/31/2021 07:43:40 - INFO - __main__ - Step 102499: {'lr': 0.00011668015863629623, 'samples': 19679808, 'steps': 102498, 'loss/train': 0.8718501329421997} 08/31/2021 07:43:41 - INFO - __main__ - Step 102500: {'lr': 0.0001166756694833015, 'samples': 19680000, 'steps': 102499, 'loss/train': 1.0376214981079102} 08/31/2021 07:43:41 - INFO - __main__ - Step 102501: {'lr': 0.00011667118039038063, 'samples': 19680192, 'steps': 102500, 'loss/train': 0.8285325169563293} 08/31/2021 07:43:42 - INFO - __main__ - Step 102502: {'lr': 0.00011666669135753571, 'samples': 19680384, 'steps': 102501, 'loss/train': 0.39744001626968384} 08/31/2021 07:43:42 - INFO - __main__ - Step 102503: {'lr': 0.00011666220238476871, 'samples': 19680576, 'steps': 102502, 'loss/train': 0.027520235627889633} 08/31/2021 07:43:44 - INFO - __main__ - Step 102504: {'lr': 0.00011665771347208164, 'samples': 19680768, 'steps': 102503, 'loss/train': 0.7418518662452698} 08/31/2021 07:43:44 - INFO - __main__ - Step 102505: {'lr': 0.00011665322461947658, 'samples': 19680960, 'steps': 102504, 'loss/train': 0.9297959208488464} 08/31/2021 07:43:45 - INFO - __main__ - Step 102506: {'lr': 0.0001166487358269555, 'samples': 19681152, 'steps': 102505, 'loss/train': 1.1205161809921265} 08/31/2021 07:43:45 - INFO - __main__ - Step 102507: {'lr': 0.00011664424709452045, 'samples': 19681344, 'steps': 102506, 'loss/train': 1.3890172243118286} 08/31/2021 07:43:45 - INFO - __main__ - Step 102508: {'lr': 0.00011663975842217353, 'samples': 19681536, 'steps': 102507, 'loss/train': 0.9958083033561707} 08/31/2021 07:43:46 - INFO - __main__ - Step 102509: {'lr': 0.0001166352698099166, 'samples': 19681728, 'steps': 102508, 'loss/train': 1.0955942869186401} 08/31/2021 07:43:47 - INFO - __main__ - Step 102510: {'lr': 0.00011663078125775173, 'samples': 19681920, 'steps': 102509, 'loss/train': 1.1466138362884521} 08/31/2021 07:43:48 - INFO - __main__ - Step 102511: {'lr': 0.00011662629276568099, 'samples': 19682112, 'steps': 102510, 'loss/train': 0.9742377400398254} 08/31/2021 07:43:48 - INFO - __main__ - Step 102512: {'lr': 0.00011662180433370639, 'samples': 19682304, 'steps': 102511, 'loss/train': 1.227194905281067} 08/31/2021 07:43:48 - INFO - __main__ - Step 102513: {'lr': 0.00011661731596182995, 'samples': 19682496, 'steps': 102512, 'loss/train': 1.4082099199295044} 08/31/2021 07:43:49 - INFO - __main__ - Step 102514: {'lr': 0.00011661282765005368, 'samples': 19682688, 'steps': 102513, 'loss/train': 0.5762169361114502} 08/31/2021 07:43:51 - INFO - __main__ - Step 102515: {'lr': 0.00011660833939837962, 'samples': 19682880, 'steps': 102514, 'loss/train': 1.4331775903701782} 08/31/2021 07:43:51 - INFO - __main__ - Step 102516: {'lr': 0.00011660385120680977, 'samples': 19683072, 'steps': 102515, 'loss/train': 1.1362690925598145} 08/31/2021 07:43:52 - INFO - __main__ - Step 102517: {'lr': 0.00011659936307534615, 'samples': 19683264, 'steps': 102516, 'loss/train': 1.2889868021011353} 08/31/2021 07:43:52 - INFO - __main__ - Step 102518: {'lr': 0.00011659487500399083, 'samples': 19683456, 'steps': 102517, 'loss/train': 1.7966469526290894} 08/31/2021 07:43:52 - INFO - __main__ - Step 102519: {'lr': 0.0001165903869927458, 'samples': 19683648, 'steps': 102518, 'loss/train': 5.7508649826049805} 08/31/2021 07:43:53 - INFO - __main__ - Step 102520: {'lr': 0.00011658589904161307, 'samples': 19683840, 'steps': 102519, 'loss/train': 5.712170124053955} 08/31/2021 07:43:54 - INFO - __main__ - Step 102521: {'lr': 0.00011658141115059479, 'samples': 19684032, 'steps': 102520, 'loss/train': 0.997898280620575} 08/31/2021 07:43:55 - INFO - __main__ - Step 102522: {'lr': 0.00011657692331969275, 'samples': 19684224, 'steps': 102521, 'loss/train': 1.3020944595336914} 08/31/2021 07:43:55 - INFO - __main__ - Step 102523: {'lr': 0.0001165724355489091, 'samples': 19684416, 'steps': 102522, 'loss/train': 1.5286130905151367} 08/31/2021 07:43:56 - INFO - __main__ - Step 102524: {'lr': 0.00011656794783824584, 'samples': 19684608, 'steps': 102523, 'loss/train': 0.9640877842903137} 08/31/2021 07:43:56 - INFO - __main__ - Step 102525: {'lr': 0.000116563460187705, 'samples': 19684800, 'steps': 102524, 'loss/train': 0.3056177794933319} 08/31/2021 07:43:56 - INFO - __main__ - Step 102526: {'lr': 0.00011655897259728863, 'samples': 19684992, 'steps': 102525, 'loss/train': 0.15920710563659668} 08/31/2021 07:43:58 - INFO - __main__ - Step 102527: {'lr': 0.0001165544850669987, 'samples': 19685184, 'steps': 102526, 'loss/train': 0.09307707846164703} 08/31/2021 07:43:59 - INFO - __main__ - Step 102528: {'lr': 0.00011654999759683729, 'samples': 19685376, 'steps': 102527, 'loss/train': 0.8386534452438354} 08/31/2021 07:43:59 - INFO - __main__ - Step 102529: {'lr': 0.00011654551018680637, 'samples': 19685568, 'steps': 102528, 'loss/train': 0.5914297699928284} 08/31/2021 07:44:00 - INFO - __main__ - Step 102530: {'lr': 0.00011654102283690798, 'samples': 19685760, 'steps': 102529, 'loss/train': 1.0466994047164917} 08/31/2021 07:44:00 - INFO - __main__ - Step 102531: {'lr': 0.00011653653554714416, 'samples': 19685952, 'steps': 102530, 'loss/train': 1.2232857942581177} 08/31/2021 07:44:02 - INFO - __main__ - Step 102532: {'lr': 0.00011653204831751693, 'samples': 19686144, 'steps': 102531, 'loss/train': 0.14840157330036163} 08/31/2021 07:44:02 - INFO - __main__ - Step 102533: {'lr': 0.00011652756114802829, 'samples': 19686336, 'steps': 102532, 'loss/train': 1.0124433040618896} 08/31/2021 07:44:03 - INFO - __main__ - Step 102534: {'lr': 0.00011652307403868027, 'samples': 19686528, 'steps': 102533, 'loss/train': 1.0508122444152832} 08/31/2021 07:44:03 - INFO - __main__ - Step 102535: {'lr': 0.00011651858698947496, 'samples': 19686720, 'steps': 102534, 'loss/train': 1.3735888004302979} 08/31/2021 07:44:03 - INFO - __main__ - Step 102536: {'lr': 0.00011651410000041423, 'samples': 19686912, 'steps': 102535, 'loss/train': 0.8133484721183777} 08/31/2021 07:44:04 - INFO - __main__ - Step 102537: {'lr': 0.00011650961307150021, 'samples': 19687104, 'steps': 102536, 'loss/train': 0.7593972086906433} 08/31/2021 07:44:05 - INFO - __main__ - Step 102538: {'lr': 0.0001165051262027349, 'samples': 19687296, 'steps': 102537, 'loss/train': 0.01826912723481655} 08/31/2021 07:44:06 - INFO - __main__ - Step 102539: {'lr': 0.00011650063939412032, 'samples': 19687488, 'steps': 102538, 'loss/train': 1.3437341451644897} 08/31/2021 07:44:06 - INFO - __main__ - Step 102540: {'lr': 0.00011649615264565846, 'samples': 19687680, 'steps': 102539, 'loss/train': 1.1886409521102905} 08/31/2021 07:44:06 - INFO - __main__ - Step 102541: {'lr': 0.00011649166595735139, 'samples': 19687872, 'steps': 102540, 'loss/train': 1.1154847145080566} 08/31/2021 07:44:07 - INFO - __main__ - Step 102542: {'lr': 0.00011648717932920113, 'samples': 19688064, 'steps': 102541, 'loss/train': 0.9650161862373352} 08/31/2021 07:44:07 - INFO - __main__ - Step 102543: {'lr': 0.00011648269276120969, 'samples': 19688256, 'steps': 102542, 'loss/train': 0.6415955424308777} 08/31/2021 07:44:09 - INFO - __main__ - Step 102544: {'lr': 0.00011647820625337905, 'samples': 19688448, 'steps': 102543, 'loss/train': 0.9523547291755676} 08/31/2021 07:44:09 - INFO - __main__ - Step 102545: {'lr': 0.00011647371980571131, 'samples': 19688640, 'steps': 102544, 'loss/train': 1.3828163146972656} 08/31/2021 07:44:09 - INFO - __main__ - Step 102546: {'lr': 0.00011646923341820843, 'samples': 19688832, 'steps': 102545, 'loss/train': 0.9863747954368591} 08/31/2021 07:44:10 - INFO - __main__ - Step 102547: {'lr': 0.00011646474709087246, 'samples': 19689024, 'steps': 102546, 'loss/train': 1.1406069993972778} 08/31/2021 07:44:10 - INFO - __main__ - Step 102548: {'lr': 0.00011646026082370551, 'samples': 19689216, 'steps': 102547, 'loss/train': 0.5554343461990356} 08/31/2021 07:44:12 - INFO - __main__ - Step 102549: {'lr': 0.0001164557746167094, 'samples': 19689408, 'steps': 102548, 'loss/train': 1.3194293975830078} 08/31/2021 07:44:12 - INFO - __main__ - Step 102550: {'lr': 0.00011645128846988626, 'samples': 19689600, 'steps': 102549, 'loss/train': 1.467248558998108} 08/31/2021 07:44:12 - INFO - __main__ - Step 102551: {'lr': 0.00011644680238323813, 'samples': 19689792, 'steps': 102550, 'loss/train': 1.181603193283081} 08/31/2021 07:44:13 - INFO - __main__ - Step 102552: {'lr': 0.00011644231635676698, 'samples': 19689984, 'steps': 102551, 'loss/train': 0.7047680616378784} 08/31/2021 07:44:13 - INFO - __main__ - Step 102553: {'lr': 0.00011643783039047487, 'samples': 19690176, 'steps': 102552, 'loss/train': 1.2589877843856812} 08/31/2021 07:44:15 - INFO - __main__ - Step 102554: {'lr': 0.00011643334448436382, 'samples': 19690368, 'steps': 102553, 'loss/train': 1.4884651899337769} 08/31/2021 07:44:16 - INFO - __main__ - Step 102555: {'lr': 0.00011642885863843586, 'samples': 19690560, 'steps': 102554, 'loss/train': 0.8124693632125854} 08/31/2021 07:44:16 - INFO - __main__ - Step 102556: {'lr': 0.00011642437285269297, 'samples': 19690752, 'steps': 102555, 'loss/train': 0.7019651532173157} 08/31/2021 07:44:16 - INFO - __main__ - Step 102557: {'lr': 0.0001164198871271372, 'samples': 19690944, 'steps': 102556, 'loss/train': 1.1316003799438477} 08/31/2021 07:44:17 - INFO - __main__ - Step 102558: {'lr': 0.00011641540146177057, 'samples': 19691136, 'steps': 102557, 'loss/train': 1.4693259000778198} 08/31/2021 07:44:19 - INFO - __main__ - Step 102559: {'lr': 0.0001164109158565951, 'samples': 19691328, 'steps': 102558, 'loss/train': 1.343479037284851} 08/31/2021 07:44:19 - INFO - __main__ - Step 102560: {'lr': 0.0001164064303116128, 'samples': 19691520, 'steps': 102559, 'loss/train': 1.5133001804351807} 08/31/2021 07:44:19 - INFO - __main__ - Step 102561: {'lr': 0.00011640194482682573, 'samples': 19691712, 'steps': 102560, 'loss/train': 1.3341474533081055} 08/31/2021 07:44:20 - INFO - __main__ - Step 102562: {'lr': 0.00011639745940223596, 'samples': 19691904, 'steps': 102561, 'loss/train': 0.8138205409049988} 08/31/2021 07:44:20 - INFO - __main__ - Step 102563: {'lr': 0.00011639297403784533, 'samples': 19692096, 'steps': 102562, 'loss/train': 1.7312184572219849} 08/31/2021 07:44:20 - INFO - __main__ - Step 102564: {'lr': 0.00011638848873365596, 'samples': 19692288, 'steps': 102563, 'loss/train': 1.7306208610534668} 08/31/2021 07:44:22 - INFO - __main__ - Step 102565: {'lr': 0.0001163840034896699, 'samples': 19692480, 'steps': 102564, 'loss/train': 1.3236569166183472} 08/31/2021 07:44:23 - INFO - __main__ - Step 102566: {'lr': 0.00011637951830588914, 'samples': 19692672, 'steps': 102565, 'loss/train': 1.3096596002578735} 08/31/2021 07:44:23 - INFO - __main__ - Step 102567: {'lr': 0.00011637503318231568, 'samples': 19692864, 'steps': 102566, 'loss/train': 0.5003764629364014} 08/31/2021 07:44:23 - INFO - __main__ - Step 102568: {'lr': 0.00011637054811895159, 'samples': 19693056, 'steps': 102567, 'loss/train': 1.4589160680770874} 08/31/2021 07:44:24 - INFO - __main__ - Step 102569: {'lr': 0.00011636606311579886, 'samples': 19693248, 'steps': 102568, 'loss/train': 1.0909911394119263} 08/31/2021 07:44:26 - INFO - __main__ - Step 102570: {'lr': 0.00011636157817285953, 'samples': 19693440, 'steps': 102569, 'loss/train': 0.07793951034545898} 08/31/2021 07:44:26 - INFO - __main__ - Step 102571: {'lr': 0.00011635709329013561, 'samples': 19693632, 'steps': 102570, 'loss/train': 1.152114987373352} 08/31/2021 07:44:26 - INFO - __main__ - Step 102572: {'lr': 0.00011635260846762913, 'samples': 19693824, 'steps': 102571, 'loss/train': 1.0574005842208862} 08/31/2021 07:44:27 - INFO - __main__ - Step 102573: {'lr': 0.00011634812370534209, 'samples': 19694016, 'steps': 102572, 'loss/train': 1.0202956199645996} 08/31/2021 07:44:27 - INFO - __main__ - Step 102574: {'lr': 0.00011634363900327652, 'samples': 19694208, 'steps': 102573, 'loss/train': 2.576860189437866} 08/31/2021 07:44:27 - INFO - __main__ - Step 102575: {'lr': 0.00011633915436143452, 'samples': 19694400, 'steps': 102574, 'loss/train': 0.8830051422119141} 08/31/2021 07:44:30 - INFO - __main__ - Step 102576: {'lr': 0.00011633466977981797, 'samples': 19694592, 'steps': 102575, 'loss/train': 0.14139820635318756} 08/31/2021 07:44:31 - INFO - __main__ - Step 102577: {'lr': 0.00011633018525842895, 'samples': 19694784, 'steps': 102576, 'loss/train': 1.2578874826431274} 08/31/2021 07:44:31 - INFO - __main__ - Step 102578: {'lr': 0.00011632570079726948, 'samples': 19694976, 'steps': 102577, 'loss/train': 1.0656245946884155} 08/31/2021 07:44:31 - INFO - __main__ - Step 102579: {'lr': 0.0001163212163963416, 'samples': 19695168, 'steps': 102578, 'loss/train': 0.8511412143707275} 08/31/2021 07:44:32 - INFO - __main__ - Step 102580: {'lr': 0.0001163167320556473, 'samples': 19695360, 'steps': 102579, 'loss/train': 1.371519923210144} 08/31/2021 07:44:32 - INFO - __main__ - Step 102581: {'lr': 0.00011631224777518861, 'samples': 19695552, 'steps': 102580, 'loss/train': 0.34096628427505493} 08/31/2021 07:44:32 - INFO - __main__ - Step 102582: {'lr': 0.00011630776355496758, 'samples': 19695744, 'steps': 102581, 'loss/train': 0.3017582893371582} 08/31/2021 07:44:33 - INFO - __main__ - Step 102583: {'lr': 0.00011630327939498622, 'samples': 19695936, 'steps': 102582, 'loss/train': 0.28930801153182983} 08/31/2021 07:44:34 - INFO - __main__ - Step 102584: {'lr': 0.0001162987952952465, 'samples': 19696128, 'steps': 102583, 'loss/train': 0.2604629397392273} 08/31/2021 07:44:35 - INFO - __main__ - Step 102585: {'lr': 0.00011629431125575051, 'samples': 19696320, 'steps': 102584, 'loss/train': 1.4528720378875732} 08/31/2021 07:44:35 - INFO - __main__ - Step 102586: {'lr': 0.00011628982727650023, 'samples': 19696512, 'steps': 102585, 'loss/train': 1.2844812870025635} 08/31/2021 07:44:35 - INFO - __main__ - Step 102587: {'lr': 0.00011628534335749768, 'samples': 19696704, 'steps': 102586, 'loss/train': 1.1072289943695068} 08/31/2021 07:44:36 - INFO - __main__ - Step 102588: {'lr': 0.00011628085949874493, 'samples': 19696896, 'steps': 102587, 'loss/train': 1.319175362586975} 08/31/2021 07:44:37 - INFO - __main__ - Step 102589: {'lr': 0.00011627637570024402, 'samples': 19697088, 'steps': 102588, 'loss/train': 1.5696452856063843} 08/31/2021 07:44:38 - INFO - __main__ - Step 102590: {'lr': 0.00011627189196199683, 'samples': 19697280, 'steps': 102589, 'loss/train': 1.6666285991668701} 08/31/2021 07:44:38 - INFO - __main__ - Step 102591: {'lr': 0.00011626740828400544, 'samples': 19697472, 'steps': 102590, 'loss/train': 1.5892847776412964} 08/31/2021 07:44:38 - INFO - __main__ - Step 102592: {'lr': 0.00011626292466627192, 'samples': 19697664, 'steps': 102591, 'loss/train': 0.31011220812797546} 08/31/2021 07:44:39 - INFO - __main__ - Step 102593: {'lr': 0.00011625844110879823, 'samples': 19697856, 'steps': 102592, 'loss/train': 1.1070010662078857} 08/31/2021 07:44:40 - INFO - __main__ - Step 102594: {'lr': 0.00011625395761158646, 'samples': 19698048, 'steps': 102593, 'loss/train': 0.8336900472640991} 08/31/2021 07:44:41 - INFO - __main__ - Step 102595: {'lr': 0.00011624947417463858, 'samples': 19698240, 'steps': 102594, 'loss/train': 1.5710731744766235} 08/31/2021 07:44:41 - INFO - __main__ - Step 102596: {'lr': 0.00011624499079795661, 'samples': 19698432, 'steps': 102595, 'loss/train': 1.5549927949905396} 08/31/2021 07:44:41 - INFO - __main__ - Step 102597: {'lr': 0.00011624050748154261, 'samples': 19698624, 'steps': 102596, 'loss/train': 0.7340179681777954} 08/31/2021 07:44:42 - INFO - __main__ - Step 102598: {'lr': 0.00011623602422539856, 'samples': 19698816, 'steps': 102597, 'loss/train': 0.6252428889274597} 08/31/2021 07:44:44 - INFO - __main__ - Step 102599: {'lr': 0.00011623154102952648, 'samples': 19699008, 'steps': 102598, 'loss/train': 1.276282548904419} 08/31/2021 07:44:44 - INFO - __main__ - Step 102600: {'lr': 0.0001162270578939284, 'samples': 19699200, 'steps': 102599, 'loss/train': 0.2603258490562439} 08/31/2021 07:44:44 - INFO - __main__ - Step 102601: {'lr': 0.00011622257481860637, 'samples': 19699392, 'steps': 102600, 'loss/train': 0.88315749168396} 08/31/2021 07:44:45 - INFO - __main__ - Step 102602: {'lr': 0.00011621809180356246, 'samples': 19699584, 'steps': 102601, 'loss/train': 0.9429758787155151} 08/31/2021 07:44:45 - INFO - __main__ - Step 102603: {'lr': 0.00011621360884879853, 'samples': 19699776, 'steps': 102602, 'loss/train': 0.24810439348220825} 08/31/2021 07:44:45 - INFO - __main__ - Step 102604: {'lr': 0.00011620912595431668, 'samples': 19699968, 'steps': 102603, 'loss/train': 0.914836585521698} 08/31/2021 07:44:47 - INFO - __main__ - Step 102605: {'lr': 0.00011620464312011894, 'samples': 19700160, 'steps': 102604, 'loss/train': 1.5597639083862305} 08/31/2021 07:44:47 - INFO - __main__ - Step 102606: {'lr': 0.0001162001603462073, 'samples': 19700352, 'steps': 102605, 'loss/train': 0.5990623235702515} 08/31/2021 07:44:48 - INFO - __main__ - Step 102607: {'lr': 0.00011619567763258382, 'samples': 19700544, 'steps': 102606, 'loss/train': 0.6666663289070129} 08/31/2021 07:44:48 - INFO - __main__ - Step 102608: {'lr': 0.00011619119497925049, 'samples': 19700736, 'steps': 102607, 'loss/train': 0.7570028305053711} 08/31/2021 07:44:48 - INFO - __main__ - Step 102609: {'lr': 0.00011618671238620936, 'samples': 19700928, 'steps': 102608, 'loss/train': 0.774237871170044} 08/31/2021 07:44:50 - INFO - __main__ - Step 102610: {'lr': 0.00011618222985346244, 'samples': 19701120, 'steps': 102609, 'loss/train': 0.871292233467102} 08/31/2021 07:44:50 - INFO - __main__ - Step 102611: {'lr': 0.00011617774738101172, 'samples': 19701312, 'steps': 102610, 'loss/train': 1.0740978717803955} 08/31/2021 07:44:51 - INFO - __main__ - Step 102612: {'lr': 0.00011617326496885925, 'samples': 19701504, 'steps': 102611, 'loss/train': 0.9117563366889954} 08/31/2021 07:44:51 - INFO - __main__ - Step 102613: {'lr': 0.00011616878261700702, 'samples': 19701696, 'steps': 102612, 'loss/train': 1.0929373502731323} 08/31/2021 07:44:51 - INFO - __main__ - Step 102614: {'lr': 0.00011616430032545711, 'samples': 19701888, 'steps': 102613, 'loss/train': 0.8522975444793701} 08/31/2021 07:44:54 - INFO - __main__ - Step 102615: {'lr': 0.00011615981809421158, 'samples': 19702080, 'steps': 102614, 'loss/train': 1.5841490030288696} 08/31/2021 07:44:54 - INFO - __main__ - Step 102616: {'lr': 0.00011615533592327226, 'samples': 19702272, 'steps': 102615, 'loss/train': 1.180142879486084} 08/31/2021 07:44:54 - INFO - __main__ - Step 102617: {'lr': 0.00011615085381264132, 'samples': 19702464, 'steps': 102616, 'loss/train': 1.091709017753601} 08/31/2021 07:44:55 - INFO - __main__ - Step 102618: {'lr': 0.00011614637176232071, 'samples': 19702656, 'steps': 102617, 'loss/train': 1.675344467163086} 08/31/2021 07:44:55 - INFO - __main__ - Step 102619: {'lr': 0.00011614188977231247, 'samples': 19702848, 'steps': 102618, 'loss/train': 1.8464545011520386} 08/31/2021 07:44:57 - INFO - __main__ - Step 102620: {'lr': 0.00011613740784261865, 'samples': 19703040, 'steps': 102619, 'loss/train': 1.0026675462722778} 08/31/2021 07:44:57 - INFO - __main__ - Step 102621: {'lr': 0.00011613292597324123, 'samples': 19703232, 'steps': 102620, 'loss/train': 0.9609147310256958} 08/31/2021 07:44:58 - INFO - __main__ - Step 102622: {'lr': 0.00011612844416418228, 'samples': 19703424, 'steps': 102621, 'loss/train': 1.4907573461532593} 08/31/2021 07:44:58 - INFO - __main__ - Step 102623: {'lr': 0.00011612396241544377, 'samples': 19703616, 'steps': 102622, 'loss/train': 1.1574163436889648} 08/31/2021 07:44:59 - INFO - __main__ - Step 102624: {'lr': 0.00011611948072702772, 'samples': 19703808, 'steps': 102623, 'loss/train': 0.7891780734062195} 08/31/2021 07:45:00 - INFO - __main__ - Step 102625: {'lr': 0.00011611499909893616, 'samples': 19704000, 'steps': 102624, 'loss/train': 1.2784978151321411} 08/31/2021 07:45:01 - INFO - __main__ - Step 102626: {'lr': 0.00011611051753117115, 'samples': 19704192, 'steps': 102625, 'loss/train': 0.29129040241241455} 08/31/2021 07:45:01 - INFO - __main__ - Step 102627: {'lr': 0.00011610603602373466, 'samples': 19704384, 'steps': 102626, 'loss/train': 1.7861688137054443} 08/31/2021 07:45:01 - INFO - __main__ - Step 102628: {'lr': 0.00011610155457662871, 'samples': 19704576, 'steps': 102627, 'loss/train': 1.2692137956619263} 08/31/2021 07:45:02 - INFO - __main__ - Step 102629: {'lr': 0.00011609707318985546, 'samples': 19704768, 'steps': 102628, 'loss/train': 1.1697168350219727} 08/31/2021 07:45:02 - INFO - __main__ - Step 102630: {'lr': 0.00011609259186341667, 'samples': 19704960, 'steps': 102629, 'loss/train': 0.9854292869567871} 08/31/2021 07:45:04 - INFO - __main__ - Step 102631: {'lr': 0.00011608811059731453, 'samples': 19705152, 'steps': 102630, 'loss/train': 1.6015572547912598} 08/31/2021 07:45:04 - INFO - __main__ - Step 102632: {'lr': 0.00011608362939155098, 'samples': 19705344, 'steps': 102631, 'loss/train': 1.6250879764556885} 08/31/2021 07:45:04 - INFO - __main__ - Step 102633: {'lr': 0.00011607914824612811, 'samples': 19705536, 'steps': 102632, 'loss/train': 0.8276107907295227} 08/31/2021 07:45:05 - INFO - __main__ - Step 102634: {'lr': 0.00011607466716104792, 'samples': 19705728, 'steps': 102633, 'loss/train': 1.4338537454605103} 08/31/2021 07:45:05 - INFO - __main__ - Step 102635: {'lr': 0.0001160701861363124, 'samples': 19705920, 'steps': 102634, 'loss/train': 0.9674796462059021} 08/31/2021 07:45:07 - INFO - __main__ - Step 102636: {'lr': 0.00011606570517192357, 'samples': 19706112, 'steps': 102635, 'loss/train': 0.3202551007270813} 08/31/2021 07:45:07 - INFO - __main__ - Step 102637: {'lr': 0.00011606122426788349, 'samples': 19706304, 'steps': 102636, 'loss/train': 1.2369623184204102} 08/31/2021 07:45:08 - INFO - __main__ - Step 102638: {'lr': 0.00011605674342419414, 'samples': 19706496, 'steps': 102637, 'loss/train': 0.9016428589820862} 08/31/2021 07:45:08 - INFO - __main__ - Step 102639: {'lr': 0.00011605226264085758, 'samples': 19706688, 'steps': 102638, 'loss/train': 1.4003058671951294} 08/31/2021 07:45:08 - INFO - __main__ - Step 102640: {'lr': 0.00011604778191787579, 'samples': 19706880, 'steps': 102639, 'loss/train': 0.03594831004738808} 08/31/2021 07:45:10 - INFO - __main__ - Step 102641: {'lr': 0.00011604330125525078, 'samples': 19707072, 'steps': 102640, 'loss/train': 1.1242016553878784} 08/31/2021 07:45:11 - INFO - __main__ - Step 102642: {'lr': 0.00011603882065298471, 'samples': 19707264, 'steps': 102641, 'loss/train': 1.0887538194656372} 08/31/2021 07:45:11 - INFO - __main__ - Step 102643: {'lr': 0.00011603434011107939, 'samples': 19707456, 'steps': 102642, 'loss/train': 0.7473770380020142} 08/31/2021 07:45:11 - INFO - __main__ - Step 102644: {'lr': 0.00011602985962953692, 'samples': 19707648, 'steps': 102643, 'loss/train': 1.0115914344787598} 08/31/2021 07:45:12 - INFO - __main__ - Step 102645: {'lr': 0.00011602537920835932, 'samples': 19707840, 'steps': 102644, 'loss/train': 0.04294288158416748} 08/31/2021 07:45:12 - INFO - __main__ - Step 102646: {'lr': 0.00011602089884754863, 'samples': 19708032, 'steps': 102645, 'loss/train': 0.019646055996418} 08/31/2021 07:45:13 - INFO - __main__ - Step 102647: {'lr': 0.00011601641854710684, 'samples': 19708224, 'steps': 102646, 'loss/train': 1.50381600856781} 08/31/2021 07:45:14 - INFO - __main__ - Step 102648: {'lr': 0.00011601193830703602, 'samples': 19708416, 'steps': 102647, 'loss/train': 1.280247449874878} 08/31/2021 07:45:14 - INFO - __main__ - Step 102649: {'lr': 0.00011600745812733812, 'samples': 19708608, 'steps': 102648, 'loss/train': 0.853737473487854} 08/31/2021 07:45:15 - INFO - __main__ - Step 102650: {'lr': 0.00011600297800801521, 'samples': 19708800, 'steps': 102649, 'loss/train': 1.2302263975143433} 08/31/2021 07:45:15 - INFO - __main__ - Step 102651: {'lr': 0.00011599849794906928, 'samples': 19708992, 'steps': 102650, 'loss/train': 0.6194763779640198} 08/31/2021 07:45:17 - INFO - __main__ - Step 102652: {'lr': 0.00011599401795050235, 'samples': 19709184, 'steps': 102651, 'loss/train': 0.421208918094635} 08/31/2021 07:45:17 - INFO - __main__ - Step 102653: {'lr': 0.00011598953801231646, 'samples': 19709376, 'steps': 102652, 'loss/train': 0.7472138404846191} 08/31/2021 07:45:17 - INFO - __main__ - Step 102654: {'lr': 0.0001159850581345136, 'samples': 19709568, 'steps': 102653, 'loss/train': 1.3680893182754517} 08/31/2021 07:45:18 - INFO - __main__ - Step 102655: {'lr': 0.00011598057831709591, 'samples': 19709760, 'steps': 102654, 'loss/train': 0.020981835201382637} 08/31/2021 07:45:18 - INFO - __main__ - Step 102656: {'lr': 0.00011597609856006522, 'samples': 19709952, 'steps': 102655, 'loss/train': 1.294303297996521} 08/31/2021 07:45:20 - INFO - __main__ - Step 102657: {'lr': 0.0001159716188634236, 'samples': 19710144, 'steps': 102656, 'loss/train': 1.0357083082199097} 08/31/2021 07:45:20 - INFO - __main__ - Step 102658: {'lr': 0.00011596713922717314, 'samples': 19710336, 'steps': 102657, 'loss/train': 1.1219184398651123} 08/31/2021 07:45:20 - INFO - __main__ - Step 102659: {'lr': 0.0001159626596513158, 'samples': 19710528, 'steps': 102658, 'loss/train': 0.9792618751525879} 08/31/2021 07:45:21 - INFO - __main__ - Step 102660: {'lr': 0.00011595818013585362, 'samples': 19710720, 'steps': 102659, 'loss/train': 0.9301964044570923} 08/31/2021 07:45:21 - INFO - __main__ - Step 102661: {'lr': 0.00011595370068078861, 'samples': 19710912, 'steps': 102660, 'loss/train': 0.8660966753959656} 08/31/2021 07:45:23 - INFO - __main__ - Step 102662: {'lr': 0.00011594922128612282, 'samples': 19711104, 'steps': 102661, 'loss/train': 0.8839181661605835} 08/31/2021 07:45:23 - INFO - __main__ - Step 102663: {'lr': 0.00011594474195185823, 'samples': 19711296, 'steps': 102662, 'loss/train': 1.2167140245437622} 08/31/2021 07:45:23 - INFO - __main__ - Step 102664: {'lr': 0.00011594026267799684, 'samples': 19711488, 'steps': 102663, 'loss/train': 1.2112692594528198} 08/31/2021 07:45:24 - INFO - __main__ - Step 102665: {'lr': 0.00011593578346454073, 'samples': 19711680, 'steps': 102664, 'loss/train': 0.913783609867096} 08/31/2021 07:45:24 - INFO - __main__ - Step 102666: {'lr': 0.00011593130431149199, 'samples': 19711872, 'steps': 102665, 'loss/train': 0.8406625390052795} 08/31/2021 07:45:26 - INFO - __main__ - Step 102667: {'lr': 0.00011592682521885243, 'samples': 19712064, 'steps': 102666, 'loss/train': 0.6156542301177979} 08/31/2021 07:45:27 - INFO - __main__ - Step 102668: {'lr': 0.00011592234618662415, 'samples': 19712256, 'steps': 102667, 'loss/train': 0.9285765886306763} 08/31/2021 07:45:27 - INFO - __main__ - Step 102669: {'lr': 0.00011591786721480921, 'samples': 19712448, 'steps': 102668, 'loss/train': 0.4752539396286011} 08/31/2021 07:45:27 - INFO - __main__ - Step 102670: {'lr': 0.00011591338830340961, 'samples': 19712640, 'steps': 102669, 'loss/train': 1.2002155780792236} 08/31/2021 07:45:28 - INFO - __main__ - Step 102671: {'lr': 0.00011590890945242738, 'samples': 19712832, 'steps': 102670, 'loss/train': 0.5518791079521179} 08/31/2021 07:45:28 - INFO - __main__ - Step 102672: {'lr': 0.00011590443066186451, 'samples': 19713024, 'steps': 102671, 'loss/train': 1.1277652978897095} 08/31/2021 07:45:30 - INFO - __main__ - Step 102673: {'lr': 0.00011589995193172303, 'samples': 19713216, 'steps': 102672, 'loss/train': 1.4911576509475708} 08/31/2021 07:45:30 - INFO - __main__ - Step 102674: {'lr': 0.00011589547326200497, 'samples': 19713408, 'steps': 102673, 'loss/train': 1.5030301809310913} 08/31/2021 07:45:30 - INFO - __main__ - Step 102675: {'lr': 0.00011589099465271233, 'samples': 19713600, 'steps': 102674, 'loss/train': 0.8167790770530701} 08/31/2021 07:45:31 - INFO - __main__ - Step 102676: {'lr': 0.00011588651610384715, 'samples': 19713792, 'steps': 102675, 'loss/train': 0.8149600028991699} 08/31/2021 07:45:31 - INFO - __main__ - Step 102677: {'lr': 0.00011588203761541154, 'samples': 19713984, 'steps': 102676, 'loss/train': 1.4141632318496704} 08/31/2021 07:45:33 - INFO - __main__ - Step 102678: {'lr': 0.0001158775591874073, 'samples': 19714176, 'steps': 102677, 'loss/train': 1.0489557981491089} 08/31/2021 07:45:33 - INFO - __main__ - Step 102679: {'lr': 0.00011587308081983657, 'samples': 19714368, 'steps': 102678, 'loss/train': 1.0807468891143799} 08/31/2021 07:45:33 - INFO - __main__ - Step 102680: {'lr': 0.00011586860251270137, 'samples': 19714560, 'steps': 102679, 'loss/train': 1.052866816520691} 08/31/2021 07:45:34 - INFO - __main__ - Step 102681: {'lr': 0.00011586412426600371, 'samples': 19714752, 'steps': 102680, 'loss/train': 1.1800588369369507} 08/31/2021 07:45:34 - INFO - __main__ - Step 102682: {'lr': 0.00011585964607974559, 'samples': 19714944, 'steps': 102681, 'loss/train': 1.0975910425186157} 08/31/2021 07:45:36 - INFO - __main__ - Step 102683: {'lr': 0.00011585516795392905, 'samples': 19715136, 'steps': 102682, 'loss/train': 1.4223906993865967} 08/31/2021 07:45:36 - INFO - __main__ - Step 102684: {'lr': 0.0001158506898885561, 'samples': 19715328, 'steps': 102683, 'loss/train': 0.8338748216629028} 08/31/2021 07:45:37 - INFO - __main__ - Step 102685: {'lr': 0.00011584621188362875, 'samples': 19715520, 'steps': 102684, 'loss/train': 4.414675712585449} 08/31/2021 07:45:37 - INFO - __main__ - Step 102686: {'lr': 0.00011584173393914904, 'samples': 19715712, 'steps': 102685, 'loss/train': 0.997051477432251} 08/31/2021 07:45:37 - INFO - __main__ - Step 102687: {'lr': 0.00011583725605511908, 'samples': 19715904, 'steps': 102686, 'loss/train': 0.903117835521698} 08/31/2021 07:45:39 - INFO - __main__ - Step 102688: {'lr': 0.00011583277823154068, 'samples': 19716096, 'steps': 102687, 'loss/train': 1.4330395460128784} 08/31/2021 07:45:39 - INFO - __main__ - Step 102689: {'lr': 0.00011582830046841594, 'samples': 19716288, 'steps': 102688, 'loss/train': 0.5274356603622437} 08/31/2021 07:45:40 - INFO - __main__ - Step 102690: {'lr': 0.00011582382276574691, 'samples': 19716480, 'steps': 102689, 'loss/train': 0.9391019344329834} 08/31/2021 07:45:40 - INFO - __main__ - Step 102691: {'lr': 0.0001158193451235356, 'samples': 19716672, 'steps': 102690, 'loss/train': 1.599886178970337} 08/31/2021 07:45:40 - INFO - __main__ - Step 102692: {'lr': 0.00011581486754178403, 'samples': 19716864, 'steps': 102691, 'loss/train': 1.3840285539627075} 08/31/2021 07:45:42 - INFO - __main__ - Step 102693: {'lr': 0.00011581039002049418, 'samples': 19717056, 'steps': 102692, 'loss/train': 1.2134242057800293} 08/31/2021 07:45:42 - INFO - __main__ - Step 102694: {'lr': 0.00011580591255966812, 'samples': 19717248, 'steps': 102693, 'loss/train': 1.1503126621246338} 08/31/2021 07:45:43 - INFO - __main__ - Step 102695: {'lr': 0.00011580143515930785, 'samples': 19717440, 'steps': 102694, 'loss/train': 1.340241551399231} 08/31/2021 07:45:43 - INFO - __main__ - Step 102696: {'lr': 0.00011579695781941538, 'samples': 19717632, 'steps': 102695, 'loss/train': 1.3996398448944092} 08/31/2021 07:45:43 - INFO - __main__ - Step 102697: {'lr': 0.00011579248053999272, 'samples': 19717824, 'steps': 102696, 'loss/train': 1.4202162027359009} 08/31/2021 07:45:45 - INFO - __main__ - Step 102698: {'lr': 0.000115788003321042, 'samples': 19718016, 'steps': 102697, 'loss/train': 0.02704414539039135} 08/31/2021 07:45:45 - INFO - __main__ - Step 102699: {'lr': 0.00011578352616256501, 'samples': 19718208, 'steps': 102698, 'loss/train': 1.4066147804260254} 08/31/2021 07:45:46 - INFO - __main__ - Step 102700: {'lr': 0.00011577904906456394, 'samples': 19718400, 'steps': 102699, 'loss/train': 0.8422622680664062} 08/31/2021 07:45:46 - INFO - __main__ - Step 102701: {'lr': 0.00011577457202704073, 'samples': 19718592, 'steps': 102700, 'loss/train': 1.2470839023590088} 08/31/2021 07:45:46 - INFO - __main__ - Step 102702: {'lr': 0.00011577009504999744, 'samples': 19718784, 'steps': 102701, 'loss/train': 1.6072760820388794} 08/31/2021 07:45:47 - INFO - __main__ - Step 102703: {'lr': 0.00011576561813343605, 'samples': 19718976, 'steps': 102702, 'loss/train': 1.2614762783050537} 08/31/2021 07:45:48 - INFO - __main__ - Step 102704: {'lr': 0.00011576114127735862, 'samples': 19719168, 'steps': 102703, 'loss/train': 1.0105259418487549} 08/31/2021 07:45:48 - INFO - __main__ - Step 102705: {'lr': 0.00011575666448176717, 'samples': 19719360, 'steps': 102704, 'loss/train': 1.4833585023880005} 08/31/2021 07:45:49 - INFO - __main__ - Step 102706: {'lr': 0.00011575218774666366, 'samples': 19719552, 'steps': 102705, 'loss/train': 1.3027764558792114} 08/31/2021 07:45:49 - INFO - __main__ - Step 102707: {'lr': 0.00011574771107205015, 'samples': 19719744, 'steps': 102706, 'loss/train': 1.5876599550247192} 08/31/2021 07:45:50 - INFO - __main__ - Step 102708: {'lr': 0.00011574323445792866, 'samples': 19719936, 'steps': 102707, 'loss/train': 1.1452161073684692} 08/31/2021 07:45:51 - INFO - __main__ - Step 102709: {'lr': 0.00011573875790430119, 'samples': 19720128, 'steps': 102708, 'loss/train': 0.7328912019729614} 08/31/2021 07:45:51 - INFO - __main__ - Step 102710: {'lr': 0.00011573428141116987, 'samples': 19720320, 'steps': 102709, 'loss/train': 1.3263506889343262} 08/31/2021 07:45:52 - INFO - __main__ - Step 102711: {'lr': 0.0001157298049785365, 'samples': 19720512, 'steps': 102710, 'loss/train': 1.5227993726730347} 08/31/2021 07:45:52 - INFO - __main__ - Step 102712: {'lr': 0.00011572532860640322, 'samples': 19720704, 'steps': 102711, 'loss/train': 1.1970309019088745} 08/31/2021 07:45:53 - INFO - __main__ - Step 102713: {'lr': 0.00011572085229477203, 'samples': 19720896, 'steps': 102712, 'loss/train': 0.9831252694129944} 08/31/2021 07:45:54 - INFO - __main__ - Step 102714: {'lr': 0.00011571637604364493, 'samples': 19721088, 'steps': 102713, 'loss/train': 0.138050839304924} 08/31/2021 07:45:54 - INFO - __main__ - Step 102715: {'lr': 0.000115711899853024, 'samples': 19721280, 'steps': 102714, 'loss/train': 1.3331048488616943} 08/31/2021 07:45:55 - INFO - __main__ - Step 102716: {'lr': 0.00011570742372291118, 'samples': 19721472, 'steps': 102715, 'loss/train': 1.5111709833145142} 08/31/2021 07:45:55 - INFO - __main__ - Step 102717: {'lr': 0.00011570294765330855, 'samples': 19721664, 'steps': 102716, 'loss/train': 0.897118330001831} 08/31/2021 07:45:56 - INFO - __main__ - Step 102718: {'lr': 0.0001156984716442181, 'samples': 19721856, 'steps': 102717, 'loss/train': 0.658606231212616} 08/31/2021 07:45:57 - INFO - __main__ - Step 102719: {'lr': 0.00011569399569564181, 'samples': 19722048, 'steps': 102718, 'loss/train': 1.2868728637695312} 08/31/2021 07:45:57 - INFO - __main__ - Step 102720: {'lr': 0.00011568951980758177, 'samples': 19722240, 'steps': 102719, 'loss/train': 0.9539962410926819} 08/31/2021 07:45:58 - INFO - __main__ - Step 102721: {'lr': 0.00011568504398003996, 'samples': 19722432, 'steps': 102720, 'loss/train': 0.8932653665542603} 08/31/2021 07:45:58 - INFO - __main__ - Step 102722: {'lr': 0.00011568056821301836, 'samples': 19722624, 'steps': 102721, 'loss/train': 1.2826231718063354} 08/31/2021 07:45:58 - INFO - __main__ - Step 102723: {'lr': 0.00011567609250651914, 'samples': 19722816, 'steps': 102722, 'loss/train': 1.2056409120559692} 08/31/2021 07:46:00 - INFO - __main__ - Step 102724: {'lr': 0.00011567161686054411, 'samples': 19723008, 'steps': 102723, 'loss/train': 0.9222179651260376} 08/31/2021 07:46:01 - INFO - __main__ - Step 102725: {'lr': 0.0001156671412750954, 'samples': 19723200, 'steps': 102724, 'loss/train': 0.7343999743461609} 08/31/2021 07:46:01 - INFO - __main__ - Step 102726: {'lr': 0.00011566266575017495, 'samples': 19723392, 'steps': 102725, 'loss/train': 0.7412059903144836} 08/31/2021 07:46:02 - INFO - __main__ - Step 102727: {'lr': 0.00011565819028578486, 'samples': 19723584, 'steps': 102726, 'loss/train': 0.9112852215766907} 08/31/2021 07:46:02 - INFO - __main__ - Step 102728: {'lr': 0.0001156537148819271, 'samples': 19723776, 'steps': 102727, 'loss/train': 1.510016679763794} 08/31/2021 07:46:03 - INFO - __main__ - Step 102729: {'lr': 0.00011564923953860373, 'samples': 19723968, 'steps': 102728, 'loss/train': 0.20890727639198303} 08/31/2021 07:46:04 - INFO - __main__ - Step 102730: {'lr': 0.00011564476425581675, 'samples': 19724160, 'steps': 102729, 'loss/train': 1.1031841039657593} 08/31/2021 07:46:04 - INFO - __main__ - Step 102731: {'lr': 0.00011564028903356813, 'samples': 19724352, 'steps': 102730, 'loss/train': 0.5326605439186096} 08/31/2021 07:46:05 - INFO - __main__ - Step 102732: {'lr': 0.00011563581387185992, 'samples': 19724544, 'steps': 102731, 'loss/train': 1.0407761335372925} 08/31/2021 07:46:05 - INFO - __main__ - Step 102733: {'lr': 0.00011563133877069415, 'samples': 19724736, 'steps': 102732, 'loss/train': 0.6054432392120361} 08/31/2021 07:46:05 - INFO - __main__ - Step 102734: {'lr': 0.00011562686373007284, 'samples': 19724928, 'steps': 102733, 'loss/train': 1.3375273942947388} 08/31/2021 07:46:07 - INFO - __main__ - Step 102735: {'lr': 0.00011562238874999797, 'samples': 19725120, 'steps': 102734, 'loss/train': 0.7930502891540527} 08/31/2021 07:46:07 - INFO - __main__ - Step 102736: {'lr': 0.00011561791383047168, 'samples': 19725312, 'steps': 102735, 'loss/train': 1.5468634366989136} 08/31/2021 07:46:08 - INFO - __main__ - Step 102737: {'lr': 0.00011561343897149581, 'samples': 19725504, 'steps': 102736, 'loss/train': 0.9110869765281677} 08/31/2021 07:46:08 - INFO - __main__ - Step 102738: {'lr': 0.00011560896417307243, 'samples': 19725696, 'steps': 102737, 'loss/train': 0.7624320983886719} 08/31/2021 07:46:08 - INFO - __main__ - Step 102739: {'lr': 0.00011560448943520357, 'samples': 19725888, 'steps': 102738, 'loss/train': 1.3529667854309082} 08/31/2021 07:46:10 - INFO - __main__ - Step 102740: {'lr': 0.00011560001475789128, 'samples': 19726080, 'steps': 102739, 'loss/train': 0.9008795619010925} 08/31/2021 07:46:11 - INFO - __main__ - Step 102741: {'lr': 0.00011559554014113751, 'samples': 19726272, 'steps': 102740, 'loss/train': 1.6337803602218628} 08/31/2021 07:46:11 - INFO - __main__ - Step 102742: {'lr': 0.00011559106558494433, 'samples': 19726464, 'steps': 102741, 'loss/train': 1.281930923461914} 08/31/2021 07:46:11 - INFO - __main__ - Step 102743: {'lr': 0.00011558659108931377, 'samples': 19726656, 'steps': 102742, 'loss/train': 0.40166813135147095} 08/31/2021 07:46:12 - INFO - __main__ - Step 102744: {'lr': 0.0001155821166542478, 'samples': 19726848, 'steps': 102743, 'loss/train': 0.17778268456459045} 08/31/2021 07:46:13 - INFO - __main__ - Step 102745: {'lr': 0.00011557764227974845, 'samples': 19727040, 'steps': 102744, 'loss/train': 1.5406590700149536} 08/31/2021 07:46:14 - INFO - __main__ - Step 102746: {'lr': 0.00011557316796581774, 'samples': 19727232, 'steps': 102745, 'loss/train': 1.6266531944274902} 08/31/2021 07:46:14 - INFO - __main__ - Step 102747: {'lr': 0.0001155686937124577, 'samples': 19727424, 'steps': 102746, 'loss/train': 1.1056147813796997} 08/31/2021 07:46:15 - INFO - __main__ - Step 102748: {'lr': 0.00011556421951967031, 'samples': 19727616, 'steps': 102747, 'loss/train': 0.9449421763420105} 08/31/2021 07:46:15 - INFO - __main__ - Step 102749: {'lr': 0.00011555974538745762, 'samples': 19727808, 'steps': 102748, 'loss/train': 0.0446288175880909} 08/31/2021 07:46:16 - INFO - __main__ - Step 102750: {'lr': 0.00011555527131582173, 'samples': 19728000, 'steps': 102749, 'loss/train': 1.0171147584915161} 08/31/2021 07:46:17 - INFO - __main__ - Step 102751: {'lr': 0.00011555079730476448, 'samples': 19728192, 'steps': 102750, 'loss/train': 0.9280477166175842} 08/31/2021 07:46:17 - INFO - __main__ - Step 102752: {'lr': 0.00011554632335428795, 'samples': 19728384, 'steps': 102751, 'loss/train': 1.1976633071899414} 08/31/2021 07:46:17 - INFO - __main__ - Step 102753: {'lr': 0.00011554184946439417, 'samples': 19728576, 'steps': 102752, 'loss/train': 1.0998754501342773} 08/31/2021 07:46:18 - INFO - __main__ - Step 102754: {'lr': 0.00011553737563508515, 'samples': 19728768, 'steps': 102753, 'loss/train': 1.5553038120269775} 08/31/2021 07:46:18 - INFO - __main__ - Step 102755: {'lr': 0.00011553290186636293, 'samples': 19728960, 'steps': 102754, 'loss/train': 1.3600691556930542} 08/31/2021 07:46:20 - INFO - __main__ - Step 102756: {'lr': 0.00011552842815822947, 'samples': 19729152, 'steps': 102755, 'loss/train': 1.0429643392562866} 08/31/2021 07:46:20 - INFO - __main__ - Step 102757: {'lr': 0.00011552395451068686, 'samples': 19729344, 'steps': 102756, 'loss/train': 1.097299575805664} 08/31/2021 07:46:21 - INFO - __main__ - Step 102758: {'lr': 0.0001155194809237371, 'samples': 19729536, 'steps': 102757, 'loss/train': 0.14334258437156677} 08/31/2021 07:46:21 - INFO - __main__ - Step 102759: {'lr': 0.00011551500739738217, 'samples': 19729728, 'steps': 102758, 'loss/train': 0.8727156519889832} 08/31/2021 07:46:21 - INFO - __main__ - Step 102760: {'lr': 0.00011551053393162409, 'samples': 19729920, 'steps': 102759, 'loss/train': 0.8786572813987732} 08/31/2021 07:46:23 - INFO - __main__ - Step 102761: {'lr': 0.00011550606052646489, 'samples': 19730112, 'steps': 102760, 'loss/train': 1.2600830793380737} 08/31/2021 07:46:24 - INFO - __main__ - Step 102762: {'lr': 0.00011550158718190659, 'samples': 19730304, 'steps': 102761, 'loss/train': 1.528556227684021} 08/31/2021 07:46:24 - INFO - __main__ - Step 102763: {'lr': 0.00011549711389795129, 'samples': 19730496, 'steps': 102762, 'loss/train': 1.5240628719329834} 08/31/2021 07:46:25 - INFO - __main__ - Step 102764: {'lr': 0.00011549264067460083, 'samples': 19730688, 'steps': 102763, 'loss/train': 1.3872193098068237} 08/31/2021 07:46:25 - INFO - __main__ - Step 102765: {'lr': 0.00011548816751185731, 'samples': 19730880, 'steps': 102764, 'loss/train': 0.872299313545227} 08/31/2021 07:46:26 - INFO - __main__ - Step 102766: {'lr': 0.00011548369440972272, 'samples': 19731072, 'steps': 102765, 'loss/train': 0.40251848101615906} 08/31/2021 07:46:27 - INFO - __main__ - Step 102767: {'lr': 0.00011547922136819913, 'samples': 19731264, 'steps': 102766, 'loss/train': 0.9727261066436768} 08/31/2021 07:46:27 - INFO - __main__ - Step 102768: {'lr': 0.00011547474838728853, 'samples': 19731456, 'steps': 102767, 'loss/train': 0.7540887594223022} 08/31/2021 07:46:28 - INFO - __main__ - Step 102769: {'lr': 0.00011547027546699293, 'samples': 19731648, 'steps': 102768, 'loss/train': 0.7169140577316284} 08/31/2021 07:46:28 - INFO - __main__ - Step 102770: {'lr': 0.00011546580260731432, 'samples': 19731840, 'steps': 102769, 'loss/train': 1.404588222503662} 08/31/2021 07:46:29 - INFO - __main__ - Step 102771: {'lr': 0.00011546132980825477, 'samples': 19732032, 'steps': 102770, 'loss/train': 0.7092716097831726} 08/31/2021 07:46:30 - INFO - __main__ - Step 102772: {'lr': 0.00011545685706981627, 'samples': 19732224, 'steps': 102771, 'loss/train': 0.16401752829551697} 08/31/2021 07:46:30 - INFO - __main__ - Step 102773: {'lr': 0.00011545238439200082, 'samples': 19732416, 'steps': 102772, 'loss/train': 1.5727808475494385} 08/31/2021 07:46:31 - INFO - __main__ - Step 102774: {'lr': 0.00011544791177481046, 'samples': 19732608, 'steps': 102773, 'loss/train': 0.8838624358177185} 08/31/2021 07:46:31 - INFO - __main__ - Step 102775: {'lr': 0.00011544343921824718, 'samples': 19732800, 'steps': 102774, 'loss/train': 1.348691463470459} 08/31/2021 07:46:32 - INFO - __main__ - Step 102776: {'lr': 0.00011543896672231301, 'samples': 19732992, 'steps': 102775, 'loss/train': 0.268671452999115} 08/31/2021 07:46:33 - INFO - __main__ - Step 102777: {'lr': 0.00011543449428701008, 'samples': 19733184, 'steps': 102776, 'loss/train': 1.3529433012008667} 08/31/2021 07:46:33 - INFO - __main__ - Step 102778: {'lr': 0.0001154300219123402, 'samples': 19733376, 'steps': 102777, 'loss/train': 1.4879858493804932} 08/31/2021 07:46:34 - INFO - __main__ - Step 102779: {'lr': 0.00011542554959830545, 'samples': 19733568, 'steps': 102778, 'loss/train': 1.1060115098953247} 08/31/2021 07:46:34 - INFO - __main__ - Step 102780: {'lr': 0.0001154210773449079, 'samples': 19733760, 'steps': 102779, 'loss/train': 1.3062334060668945} 08/31/2021 07:46:35 - INFO - __main__ - Step 102781: {'lr': 0.0001154166051521495, 'samples': 19733952, 'steps': 102780, 'loss/train': 1.3811923265457153} 08/31/2021 07:46:36 - INFO - __main__ - Step 102782: {'lr': 0.00011541213302003231, 'samples': 19734144, 'steps': 102781, 'loss/train': 1.944803237915039} 08/31/2021 07:46:36 - INFO - __main__ - Step 102783: {'lr': 0.00011540766094855834, 'samples': 19734336, 'steps': 102782, 'loss/train': 1.952254295349121} 08/31/2021 07:46:37 - INFO - __main__ - Step 102784: {'lr': 0.0001154031889377296, 'samples': 19734528, 'steps': 102783, 'loss/train': 1.051505208015442} 08/31/2021 07:46:37 - INFO - __main__ - Step 102785: {'lr': 0.00011539871698754814, 'samples': 19734720, 'steps': 102784, 'loss/train': 1.2476913928985596} 08/31/2021 07:46:38 - INFO - __main__ - Step 102786: {'lr': 0.00011539424509801591, 'samples': 19734912, 'steps': 102785, 'loss/train': 1.407280683517456} 08/31/2021 07:46:39 - INFO - __main__ - Step 102787: {'lr': 0.00011538977326913494, 'samples': 19735104, 'steps': 102786, 'loss/train': 0.9707581996917725} 08/31/2021 07:46:39 - INFO - __main__ - Step 102788: {'lr': 0.00011538530150090728, 'samples': 19735296, 'steps': 102787, 'loss/train': 1.4803928136825562} 08/31/2021 07:46:40 - INFO - __main__ - Step 102789: {'lr': 0.00011538082979333495, 'samples': 19735488, 'steps': 102788, 'loss/train': 1.2531484365463257} 08/31/2021 07:46:40 - INFO - __main__ - Step 102790: {'lr': 0.00011537635814642, 'samples': 19735680, 'steps': 102789, 'loss/train': 1.9668656587600708} 08/31/2021 07:46:41 - INFO - __main__ - Step 102791: {'lr': 0.00011537188656016432, 'samples': 19735872, 'steps': 102790, 'loss/train': 1.3735023736953735} 08/31/2021 07:46:42 - INFO - __main__ - Step 102792: {'lr': 0.00011536741503456997, 'samples': 19736064, 'steps': 102791, 'loss/train': 1.280170202255249} 08/31/2021 07:46:42 - INFO - __main__ - Step 102793: {'lr': 0.00011536294356963898, 'samples': 19736256, 'steps': 102792, 'loss/train': 1.1350855827331543} 08/31/2021 07:46:43 - INFO - __main__ - Step 102794: {'lr': 0.00011535847216537337, 'samples': 19736448, 'steps': 102793, 'loss/train': 1.0120824575424194} 08/31/2021 07:46:43 - INFO - __main__ - Step 102795: {'lr': 0.00011535400082177516, 'samples': 19736640, 'steps': 102794, 'loss/train': 0.839663565158844} 08/31/2021 07:46:43 - INFO - __main__ - Step 102796: {'lr': 0.00011534952953884636, 'samples': 19736832, 'steps': 102795, 'loss/train': 1.5036609172821045} 08/31/2021 07:46:45 - INFO - __main__ - Step 102797: {'lr': 0.00011534505831658899, 'samples': 19737024, 'steps': 102796, 'loss/train': 1.165733814239502} 08/31/2021 07:46:45 - INFO - __main__ - Step 102798: {'lr': 0.00011534058715500507, 'samples': 19737216, 'steps': 102797, 'loss/train': 1.3785873651504517} 08/31/2021 07:46:46 - INFO - __main__ - Step 102799: {'lr': 0.00011533611605409658, 'samples': 19737408, 'steps': 102798, 'loss/train': 1.0887889862060547} 08/31/2021 07:46:46 - INFO - __main__ - Step 102800: {'lr': 0.00011533164501386556, 'samples': 19737600, 'steps': 102799, 'loss/train': 0.9400983452796936} 08/31/2021 07:46:47 - INFO - __main__ - Step 102801: {'lr': 0.00011532717403431403, 'samples': 19737792, 'steps': 102800, 'loss/train': 0.8857008218765259} 08/31/2021 07:46:48 - INFO - __main__ - Step 102802: {'lr': 0.00011532270311544399, 'samples': 19737984, 'steps': 102801, 'loss/train': 1.1067546606063843} 08/31/2021 07:46:48 - INFO - __main__ - Step 102803: {'lr': 0.00011531823225725749, 'samples': 19738176, 'steps': 102802, 'loss/train': 1.4234943389892578} 08/31/2021 07:46:49 - INFO - __main__ - Step 102804: {'lr': 0.00011531376145975659, 'samples': 19738368, 'steps': 102803, 'loss/train': 1.7966381311416626} 08/31/2021 07:46:49 - INFO - __main__ - Step 102805: {'lr': 0.00011530929072294313, 'samples': 19738560, 'steps': 102804, 'loss/train': 0.6260969638824463} 08/31/2021 07:46:50 - INFO - __main__ - Step 102806: {'lr': 0.00011530482004681922, 'samples': 19738752, 'steps': 102805, 'loss/train': 1.2601628303527832} 08/31/2021 07:46:51 - INFO - __main__ - Step 102807: {'lr': 0.0001153003494313869, 'samples': 19738944, 'steps': 102806, 'loss/train': 0.718834638595581} 08/31/2021 07:46:52 - INFO - __main__ - Step 102808: {'lr': 0.00011529587887664816, 'samples': 19739136, 'steps': 102807, 'loss/train': 0.040600672364234924} 08/31/2021 07:46:52 - INFO - __main__ - Step 102809: {'lr': 0.00011529140838260501, 'samples': 19739328, 'steps': 102808, 'loss/train': 0.9402570128440857} 08/31/2021 07:46:52 - INFO - __main__ - Step 102810: {'lr': 0.00011528693794925949, 'samples': 19739520, 'steps': 102809, 'loss/train': 1.3804481029510498} 08/31/2021 07:46:53 - INFO - __main__ - Step 102811: {'lr': 0.00011528246757661356, 'samples': 19739712, 'steps': 102810, 'loss/train': 1.0913790464401245} 08/31/2021 07:46:55 - INFO - __main__ - Step 102812: {'lr': 0.00011527799726466931, 'samples': 19739904, 'steps': 102811, 'loss/train': 1.1940810680389404} 08/31/2021 07:46:55 - INFO - __main__ - Step 102813: {'lr': 0.0001152735270134287, 'samples': 19740096, 'steps': 102812, 'loss/train': 1.4324032068252563} 08/31/2021 07:46:55 - INFO - __main__ - Step 102814: {'lr': 0.00011526905682289373, 'samples': 19740288, 'steps': 102813, 'loss/train': 0.017851337790489197} 08/31/2021 07:46:56 - INFO - __main__ - Step 102815: {'lr': 0.0001152645866930665, 'samples': 19740480, 'steps': 102814, 'loss/train': 1.168884515762329} 08/31/2021 07:46:56 - INFO - __main__ - Step 102816: {'lr': 0.00011526011662394895, 'samples': 19740672, 'steps': 102815, 'loss/train': 0.3584080636501312} 08/31/2021 07:46:56 - INFO - __main__ - Step 102817: {'lr': 0.0001152556466155432, 'samples': 19740864, 'steps': 102816, 'loss/train': 0.704035222530365} 08/31/2021 07:46:59 - INFO - __main__ - Step 102818: {'lr': 0.00011525117666785107, 'samples': 19741056, 'steps': 102817, 'loss/train': 1.5996407270431519} 08/31/2021 07:46:59 - INFO - __main__ - Step 102819: {'lr': 0.00011524670678087467, 'samples': 19741248, 'steps': 102818, 'loss/train': 0.8765345215797424} 08/31/2021 07:47:00 - INFO - __main__ - Step 102820: {'lr': 0.00011524223695461605, 'samples': 19741440, 'steps': 102819, 'loss/train': 0.7052137851715088} 08/31/2021 07:47:00 - INFO - __main__ - Step 102821: {'lr': 0.0001152377671890772, 'samples': 19741632, 'steps': 102820, 'loss/train': 0.9884483218193054} 08/31/2021 07:47:00 - INFO - __main__ - Step 102822: {'lr': 0.00011523329748426013, 'samples': 19741824, 'steps': 102821, 'loss/train': 1.2050632238388062} 08/31/2021 07:47:02 - INFO - __main__ - Step 102823: {'lr': 0.00011522882784016686, 'samples': 19742016, 'steps': 102822, 'loss/train': 1.3002499341964722} 08/31/2021 07:47:02 - INFO - __main__ - Step 102824: {'lr': 0.00011522435825679938, 'samples': 19742208, 'steps': 102823, 'loss/train': 0.32837405800819397} 08/31/2021 07:47:03 - INFO - __main__ - Step 102825: {'lr': 0.00011521988873415976, 'samples': 19742400, 'steps': 102824, 'loss/train': 1.0129859447479248} 08/31/2021 07:47:03 - INFO - __main__ - Step 102826: {'lr': 0.00011521541927224994, 'samples': 19742592, 'steps': 102825, 'loss/train': 1.5683037042617798} 08/31/2021 07:47:03 - INFO - __main__ - Step 102827: {'lr': 0.00011521094987107198, 'samples': 19742784, 'steps': 102826, 'loss/train': 1.3069467544555664} 08/31/2021 07:47:05 - INFO - __main__ - Step 102828: {'lr': 0.00011520648053062791, 'samples': 19742976, 'steps': 102827, 'loss/train': 0.42795783281326294} 08/31/2021 07:47:05 - INFO - __main__ - Step 102829: {'lr': 0.0001152020112509197, 'samples': 19743168, 'steps': 102828, 'loss/train': 1.4870357513427734} 08/31/2021 07:47:06 - INFO - __main__ - Step 102830: {'lr': 0.00011519754203194938, 'samples': 19743360, 'steps': 102829, 'loss/train': 1.7907726764678955} 08/31/2021 07:47:06 - INFO - __main__ - Step 102831: {'lr': 0.00011519307287371908, 'samples': 19743552, 'steps': 102830, 'loss/train': 1.1544429063796997} 08/31/2021 07:47:07 - INFO - __main__ - Step 102832: {'lr': 0.00011518860377623059, 'samples': 19743744, 'steps': 102831, 'loss/train': 1.4271024465560913} 08/31/2021 07:47:07 - INFO - __main__ - Step 102833: {'lr': 0.00011518413473948605, 'samples': 19743936, 'steps': 102832, 'loss/train': 0.6200354695320129} 08/31/2021 07:47:08 - INFO - __main__ - Step 102834: {'lr': 0.00011517966576348746, 'samples': 19744128, 'steps': 102833, 'loss/train': 0.565756618976593} 08/31/2021 07:47:09 - INFO - __main__ - Step 102835: {'lr': 0.0001151751968482368, 'samples': 19744320, 'steps': 102834, 'loss/train': 0.7563499808311462} 08/31/2021 07:47:09 - INFO - __main__ - Step 102836: {'lr': 0.00011517072799373615, 'samples': 19744512, 'steps': 102835, 'loss/train': 1.2776942253112793} 08/31/2021 07:47:09 - INFO - __main__ - Step 102837: {'lr': 0.00011516625919998747, 'samples': 19744704, 'steps': 102836, 'loss/train': 0.7564741373062134} 08/31/2021 07:47:10 - INFO - __main__ - Step 102838: {'lr': 0.0001151617904669928, 'samples': 19744896, 'steps': 102837, 'loss/train': 1.2763930559158325} 08/31/2021 07:47:11 - INFO - __main__ - Step 102839: {'lr': 0.00011515732179475416, 'samples': 19745088, 'steps': 102838, 'loss/train': 0.8021659255027771} 08/31/2021 07:47:12 - INFO - __main__ - Step 102840: {'lr': 0.00011515285318327354, 'samples': 19745280, 'steps': 102839, 'loss/train': 1.4564577341079712} 08/31/2021 07:47:12 - INFO - __main__ - Step 102841: {'lr': 0.00011514838463255294, 'samples': 19745472, 'steps': 102840, 'loss/train': 1.6300595998764038} 08/31/2021 07:47:12 - INFO - __main__ - Step 102842: {'lr': 0.00011514391614259442, 'samples': 19745664, 'steps': 102841, 'loss/train': 1.1922427415847778} 08/31/2021 07:47:13 - INFO - __main__ - Step 102843: {'lr': 0.00011513944771339999, 'samples': 19745856, 'steps': 102842, 'loss/train': 1.6018904447555542} 08/31/2021 07:47:15 - INFO - __main__ - Step 102844: {'lr': 0.0001151349793449717, 'samples': 19746048, 'steps': 102843, 'loss/train': 1.219494342803955} 08/31/2021 07:47:15 - INFO - __main__ - Step 102845: {'lr': 0.00011513051103731143, 'samples': 19746240, 'steps': 102844, 'loss/train': 1.4552843570709229} 08/31/2021 07:47:16 - INFO - __main__ - Step 102846: {'lr': 0.00011512604279042127, 'samples': 19746432, 'steps': 102845, 'loss/train': 0.877316415309906} 08/31/2021 07:47:16 - INFO - __main__ - Step 102847: {'lr': 0.00011512157460430322, 'samples': 19746624, 'steps': 102846, 'loss/train': 1.4918769598007202} 08/31/2021 07:47:16 - INFO - __main__ - Step 102848: {'lr': 0.00011511710647895935, 'samples': 19746816, 'steps': 102847, 'loss/train': 1.2931417226791382} 08/31/2021 07:47:17 - INFO - __main__ - Step 102849: {'lr': 0.0001151126384143916, 'samples': 19747008, 'steps': 102848, 'loss/train': 0.015423234552145004} 08/31/2021 07:47:18 - INFO - __main__ - Step 102850: {'lr': 0.00011510817041060201, 'samples': 19747200, 'steps': 102849, 'loss/train': 1.041518211364746} 08/31/2021 07:47:19 - INFO - __main__ - Step 102851: {'lr': 0.00011510370246759258, 'samples': 19747392, 'steps': 102850, 'loss/train': 1.1540096998214722} 08/31/2021 07:47:19 - INFO - __main__ - Step 102852: {'lr': 0.00011509923458536536, 'samples': 19747584, 'steps': 102851, 'loss/train': 1.243377923965454} 08/31/2021 07:47:19 - INFO - __main__ - Step 102853: {'lr': 0.00011509476676392235, 'samples': 19747776, 'steps': 102852, 'loss/train': 1.3916066884994507} 08/31/2021 07:47:20 - INFO - __main__ - Step 102854: {'lr': 0.00011509029900326556, 'samples': 19747968, 'steps': 102853, 'loss/train': 1.3654239177703857} 08/31/2021 07:47:20 - INFO - __main__ - Step 102855: {'lr': 0.00011508583130339701, 'samples': 19748160, 'steps': 102854, 'loss/train': 0.3766365945339203} 08/31/2021 07:47:21 - INFO - __main__ - Step 102856: {'lr': 0.00011508136366431868, 'samples': 19748352, 'steps': 102855, 'loss/train': 1.340623140335083} 08/31/2021 07:47:22 - INFO - __main__ - Step 102857: {'lr': 0.0001150768960860327, 'samples': 19748544, 'steps': 102856, 'loss/train': 1.2268459796905518} 08/31/2021 07:47:22 - INFO - __main__ - Step 102858: {'lr': 0.00011507242856854088, 'samples': 19748736, 'steps': 102857, 'loss/train': 1.264603853225708} 08/31/2021 07:47:22 - INFO - __main__ - Step 102859: {'lr': 0.00011506796111184537, 'samples': 19748928, 'steps': 102858, 'loss/train': 0.6470721960067749} 08/31/2021 07:47:23 - INFO - __main__ - Step 102860: {'lr': 0.00011506349371594815, 'samples': 19749120, 'steps': 102859, 'loss/train': 1.233963966369629} 08/31/2021 07:47:24 - INFO - __main__ - Step 102861: {'lr': 0.00011505902638085122, 'samples': 19749312, 'steps': 102860, 'loss/train': 1.2024288177490234} 08/31/2021 07:47:25 - INFO - __main__ - Step 102862: {'lr': 0.00011505455910655663, 'samples': 19749504, 'steps': 102861, 'loss/train': 1.5874807834625244} 08/31/2021 07:47:25 - INFO - __main__ - Step 102863: {'lr': 0.00011505009189306636, 'samples': 19749696, 'steps': 102862, 'loss/train': 1.6875795125961304} 08/31/2021 07:47:25 - INFO - __main__ - Step 102864: {'lr': 0.00011504562474038244, 'samples': 19749888, 'steps': 102863, 'loss/train': 1.0064899921417236} 08/31/2021 07:47:26 - INFO - __main__ - Step 102865: {'lr': 0.00011504115764850689, 'samples': 19750080, 'steps': 102864, 'loss/train': 1.4508142471313477} 08/31/2021 07:47:27 - INFO - __main__ - Step 102866: {'lr': 0.00011503669061744171, 'samples': 19750272, 'steps': 102865, 'loss/train': 1.1471055746078491} 08/31/2021 07:47:28 - INFO - __main__ - Step 102867: {'lr': 0.00011503222364718891, 'samples': 19750464, 'steps': 102866, 'loss/train': 1.3607895374298096} 08/31/2021 07:47:28 - INFO - __main__ - Step 102868: {'lr': 0.00011502775673775049, 'samples': 19750656, 'steps': 102867, 'loss/train': 0.14282061159610748} 08/31/2021 07:47:28 - INFO - __main__ - Step 102869: {'lr': 0.0001150232898891285, 'samples': 19750848, 'steps': 102868, 'loss/train': 1.477405309677124} 08/31/2021 07:47:29 - INFO - __main__ - Step 102870: {'lr': 0.00011501882310132492, 'samples': 19751040, 'steps': 102869, 'loss/train': 1.4567729234695435} 08/31/2021 07:47:31 - INFO - __main__ - Step 102871: {'lr': 0.00011501435637434188, 'samples': 19751232, 'steps': 102870, 'loss/train': 1.297889232635498} 08/31/2021 07:47:31 - INFO - __main__ - Step 102872: {'lr': 0.00011500988970818119, 'samples': 19751424, 'steps': 102871, 'loss/train': 1.4394465684890747} 08/31/2021 07:47:32 - INFO - __main__ - Step 102873: {'lr': 0.00011500542310284496, 'samples': 19751616, 'steps': 102872, 'loss/train': 1.85306715965271} 08/31/2021 07:47:32 - INFO - __main__ - Step 102874: {'lr': 0.0001150009565583352, 'samples': 19751808, 'steps': 102873, 'loss/train': 1.1274795532226562} 08/31/2021 07:47:32 - INFO - __main__ - Step 102875: {'lr': 0.00011499649007465394, 'samples': 19752000, 'steps': 102874, 'loss/train': 1.0809924602508545} 08/31/2021 07:47:34 - INFO - __main__ - Step 102876: {'lr': 0.00011499202365180317, 'samples': 19752192, 'steps': 102875, 'loss/train': 1.6152147054672241} 08/31/2021 07:47:34 - INFO - __main__ - Step 102877: {'lr': 0.0001149875572897849, 'samples': 19752384, 'steps': 102876, 'loss/train': 1.0003843307495117} 08/31/2021 07:47:35 - INFO - __main__ - Step 102878: {'lr': 0.00011498309098860115, 'samples': 19752576, 'steps': 102877, 'loss/train': 1.1612006425857544} 08/31/2021 07:47:35 - INFO - __main__ - Step 102879: {'lr': 0.00011497862474825397, 'samples': 19752768, 'steps': 102878, 'loss/train': 0.836056113243103} 08/31/2021 07:47:35 - INFO - __main__ - Step 102880: {'lr': 0.00011497415856874532, 'samples': 19752960, 'steps': 102879, 'loss/train': 0.9933675527572632} 08/31/2021 07:47:37 - INFO - __main__ - Step 102881: {'lr': 0.00011496969245007721, 'samples': 19753152, 'steps': 102880, 'loss/train': 1.2713602781295776} 08/31/2021 07:47:37 - INFO - __main__ - Step 102882: {'lr': 0.00011496522639225171, 'samples': 19753344, 'steps': 102881, 'loss/train': 0.8066943883895874} 08/31/2021 07:47:38 - INFO - __main__ - Step 102883: {'lr': 0.00011496076039527075, 'samples': 19753536, 'steps': 102882, 'loss/train': 0.8361757397651672} 08/31/2021 07:47:38 - INFO - __main__ - Step 102884: {'lr': 0.00011495629445913652, 'samples': 19753728, 'steps': 102883, 'loss/train': 0.3194490075111389} 08/31/2021 07:47:38 - INFO - __main__ - Step 102885: {'lr': 0.00011495182858385081, 'samples': 19753920, 'steps': 102884, 'loss/train': 1.217405080795288} 08/31/2021 07:47:40 - INFO - __main__ - Step 102886: {'lr': 0.0001149473627694157, 'samples': 19754112, 'steps': 102885, 'loss/train': 0.060075607150793076} 08/31/2021 07:47:40 - INFO - __main__ - Step 102887: {'lr': 0.00011494289701583322, 'samples': 19754304, 'steps': 102886, 'loss/train': 0.6021156311035156} 08/31/2021 07:47:41 - INFO - __main__ - Step 102888: {'lr': 0.00011493843132310541, 'samples': 19754496, 'steps': 102887, 'loss/train': 1.2388476133346558} 08/31/2021 07:47:41 - INFO - __main__ - Step 102889: {'lr': 0.00011493396569123423, 'samples': 19754688, 'steps': 102888, 'loss/train': 1.3468079566955566} 08/31/2021 07:47:41 - INFO - __main__ - Step 102890: {'lr': 0.00011492950012022174, 'samples': 19754880, 'steps': 102889, 'loss/train': 1.2724082469940186} 08/31/2021 07:47:43 - INFO - __main__ - Step 102891: {'lr': 0.00011492503461006993, 'samples': 19755072, 'steps': 102890, 'loss/train': 1.0837688446044922} 08/31/2021 07:47:43 - INFO - __main__ - Step 102892: {'lr': 0.0001149205691607808, 'samples': 19755264, 'steps': 102891, 'loss/train': 0.08107797801494598} 08/31/2021 07:47:44 - INFO - __main__ - Step 102893: {'lr': 0.0001149161037723564, 'samples': 19755456, 'steps': 102892, 'loss/train': 1.0982024669647217} 08/31/2021 07:47:44 - INFO - __main__ - Step 102894: {'lr': 0.00011491163844479871, 'samples': 19755648, 'steps': 102893, 'loss/train': 0.8745922446250916} 08/31/2021 07:47:44 - INFO - __main__ - Step 102895: {'lr': 0.00011490717317810975, 'samples': 19755840, 'steps': 102894, 'loss/train': 1.0455458164215088} 08/31/2021 07:47:46 - INFO - __main__ - Step 102896: {'lr': 0.00011490270797229154, 'samples': 19756032, 'steps': 102895, 'loss/train': 1.115440011024475} 08/31/2021 07:47:46 - INFO - __main__ - Step 102897: {'lr': 0.00011489824282734609, 'samples': 19756224, 'steps': 102896, 'loss/train': 0.800042450428009} 08/31/2021 07:47:47 - INFO - __main__ - Step 102898: {'lr': 0.00011489377774327548, 'samples': 19756416, 'steps': 102897, 'loss/train': 0.6245821118354797} 08/31/2021 07:47:47 - INFO - __main__ - Step 102899: {'lr': 0.00011488931272008158, 'samples': 19756608, 'steps': 102898, 'loss/train': 1.022200584411621} 08/31/2021 07:47:47 - INFO - __main__ - Step 102900: {'lr': 0.00011488484775776645, 'samples': 19756800, 'steps': 102899, 'loss/train': 1.0167863368988037} 08/31/2021 07:47:49 - INFO - __main__ - Step 102901: {'lr': 0.00011488038285633213, 'samples': 19756992, 'steps': 102900, 'loss/train': 1.5347872972488403} 08/31/2021 07:47:50 - INFO - __main__ - Step 102902: {'lr': 0.00011487591801578062, 'samples': 19757184, 'steps': 102901, 'loss/train': 0.7438292503356934} 08/31/2021 07:47:50 - INFO - __main__ - Step 102903: {'lr': 0.00011487145323611396, 'samples': 19757376, 'steps': 102902, 'loss/train': 1.7011622190475464} 08/31/2021 07:47:50 - INFO - __main__ - Step 102904: {'lr': 0.0001148669885173341, 'samples': 19757568, 'steps': 102903, 'loss/train': 1.3864587545394897} 08/31/2021 07:47:51 - INFO - __main__ - Step 102905: {'lr': 0.0001148625238594431, 'samples': 19757760, 'steps': 102904, 'loss/train': 0.6965579986572266} 08/31/2021 07:47:52 - INFO - __main__ - Step 102906: {'lr': 0.00011485805926244297, 'samples': 19757952, 'steps': 102905, 'loss/train': 0.06060969457030296} 08/31/2021 07:47:53 - INFO - __main__ - Step 102907: {'lr': 0.00011485359472633572, 'samples': 19758144, 'steps': 102906, 'loss/train': 1.2910891771316528} 08/31/2021 07:47:53 - INFO - __main__ - Step 102908: {'lr': 0.00011484913025112333, 'samples': 19758336, 'steps': 102907, 'loss/train': 0.6551135182380676} 08/31/2021 07:47:53 - INFO - __main__ - Step 102909: {'lr': 0.00011484466583680786, 'samples': 19758528, 'steps': 102908, 'loss/train': 1.2784135341644287} 08/31/2021 07:47:54 - INFO - __main__ - Step 102910: {'lr': 0.00011484020148339131, 'samples': 19758720, 'steps': 102909, 'loss/train': 1.4534574747085571} 08/31/2021 07:47:55 - INFO - __main__ - Step 102911: {'lr': 0.00011483573719087573, 'samples': 19758912, 'steps': 102910, 'loss/train': 1.3709819316864014} 08/31/2021 07:47:56 - INFO - __main__ - Step 102912: {'lr': 0.00011483127295926302, 'samples': 19759104, 'steps': 102911, 'loss/train': 1.0565295219421387} 08/31/2021 07:47:56 - INFO - __main__ - Step 102913: {'lr': 0.00011482680878855525, 'samples': 19759296, 'steps': 102912, 'loss/train': 1.3267908096313477} 08/31/2021 07:47:56 - INFO - __main__ - Step 102914: {'lr': 0.00011482234467875444, 'samples': 19759488, 'steps': 102913, 'loss/train': 0.8524420857429504} 08/31/2021 07:47:57 - INFO - __main__ - Step 102915: {'lr': 0.00011481788062986257, 'samples': 19759680, 'steps': 102914, 'loss/train': 2.123868703842163} 08/31/2021 07:47:57 - INFO - __main__ - Step 102916: {'lr': 0.0001148134166418817, 'samples': 19759872, 'steps': 102915, 'loss/train': 0.9422054886817932} 08/31/2021 07:47:59 - INFO - __main__ - Step 102917: {'lr': 0.00011480895271481381, 'samples': 19760064, 'steps': 102916, 'loss/train': 0.6853470206260681} 08/31/2021 07:48:00 - INFO - __main__ - Step 102918: {'lr': 0.0001148044888486609, 'samples': 19760256, 'steps': 102917, 'loss/train': 0.7039289474487305} 08/31/2021 07:48:00 - INFO - __main__ - Step 102919: {'lr': 0.00011480002504342504, 'samples': 19760448, 'steps': 102918, 'loss/train': 0.01520248968154192} 08/31/2021 07:48:00 - INFO - __main__ - Step 102920: {'lr': 0.00011479556129910817, 'samples': 19760640, 'steps': 102919, 'loss/train': 0.8634268045425415} 08/31/2021 07:48:01 - INFO - __main__ - Step 102921: {'lr': 0.00011479109761571235, 'samples': 19760832, 'steps': 102920, 'loss/train': 1.5924248695373535} 08/31/2021 07:48:01 - INFO - __main__ - Step 102922: {'lr': 0.00011478663399323958, 'samples': 19761024, 'steps': 102921, 'loss/train': 1.4289991855621338} 08/31/2021 07:48:03 - INFO - __main__ - Step 102923: {'lr': 0.00011478217043169195, 'samples': 19761216, 'steps': 102922, 'loss/train': 1.0761531591415405} 08/31/2021 07:48:04 - INFO - __main__ - Step 102924: {'lr': 0.00011477770693107129, 'samples': 19761408, 'steps': 102923, 'loss/train': 1.001878023147583} 08/31/2021 07:48:04 - INFO - __main__ - Step 102925: {'lr': 0.00011477324349137971, 'samples': 19761600, 'steps': 102924, 'loss/train': 1.6407976150512695} 08/31/2021 07:48:04 - INFO - __main__ - Step 102926: {'lr': 0.00011476878011261923, 'samples': 19761792, 'steps': 102925, 'loss/train': 1.2192037105560303} 08/31/2021 07:48:05 - INFO - __main__ - Step 102927: {'lr': 0.00011476431679479186, 'samples': 19761984, 'steps': 102926, 'loss/train': 1.2368186712265015} 08/31/2021 07:48:06 - INFO - __main__ - Step 102928: {'lr': 0.00011475985353789958, 'samples': 19762176, 'steps': 102927, 'loss/train': 1.2578810453414917} 08/31/2021 07:48:07 - INFO - __main__ - Step 102929: {'lr': 0.00011475539034194443, 'samples': 19762368, 'steps': 102928, 'loss/train': 1.604103684425354} 08/31/2021 07:48:07 - INFO - __main__ - Step 102930: {'lr': 0.0001147509272069284, 'samples': 19762560, 'steps': 102929, 'loss/train': 1.14344322681427} 08/31/2021 07:48:07 - INFO - __main__ - Step 102931: {'lr': 0.00011474646413285353, 'samples': 19762752, 'steps': 102930, 'loss/train': 0.036984577775001526} 08/31/2021 07:48:08 - INFO - __main__ - Step 102932: {'lr': 0.00011474200111972182, 'samples': 19762944, 'steps': 102931, 'loss/train': 1.279111385345459} 08/31/2021 07:48:09 - INFO - __main__ - Step 102933: {'lr': 0.00011473753816753527, 'samples': 19763136, 'steps': 102932, 'loss/train': 0.7021978497505188} 08/31/2021 07:48:10 - INFO - __main__ - Step 102934: {'lr': 0.00011473307527629601, 'samples': 19763328, 'steps': 102933, 'loss/train': 1.322527527809143} 08/31/2021 07:48:10 - INFO - __main__ - Step 102935: {'lr': 0.00011472861244600582, 'samples': 19763520, 'steps': 102934, 'loss/train': 1.3112314939498901} 08/31/2021 07:48:10 - INFO - __main__ - Step 102936: {'lr': 0.00011472414967666683, 'samples': 19763712, 'steps': 102935, 'loss/train': 0.5954946875572205} 08/31/2021 07:48:11 - INFO - __main__ - Step 102937: {'lr': 0.00011471968696828106, 'samples': 19763904, 'steps': 102936, 'loss/train': 1.3935356140136719} 08/31/2021 07:48:12 - INFO - __main__ - Step 102938: {'lr': 0.00011471522432085053, 'samples': 19764096, 'steps': 102937, 'loss/train': 1.5978431701660156} 08/31/2021 07:48:13 - INFO - __main__ - Step 102939: {'lr': 0.0001147107617343772, 'samples': 19764288, 'steps': 102938, 'loss/train': 1.3261198997497559} 08/31/2021 07:48:13 - INFO - __main__ - Step 102940: {'lr': 0.00011470629920886314, 'samples': 19764480, 'steps': 102939, 'loss/train': 0.6870683431625366} 08/31/2021 07:48:13 - INFO - __main__ - Step 102941: {'lr': 0.00011470183674431031, 'samples': 19764672, 'steps': 102940, 'loss/train': 0.8653033971786499} 08/31/2021 07:48:14 - INFO - __main__ - Step 102942: {'lr': 0.00011469737434072075, 'samples': 19764864, 'steps': 102941, 'loss/train': 0.8503947257995605} 08/31/2021 07:48:15 - INFO - __main__ - Step 102943: {'lr': 0.00011469291199809647, 'samples': 19765056, 'steps': 102942, 'loss/train': 0.7018950581550598} 08/31/2021 07:48:16 - INFO - __main__ - Step 102944: {'lr': 0.00011468844971643949, 'samples': 19765248, 'steps': 102943, 'loss/train': 1.0777511596679688} 08/31/2021 07:48:16 - INFO - __main__ - Step 102945: {'lr': 0.00011468398749575188, 'samples': 19765440, 'steps': 102944, 'loss/train': 0.9652733206748962} 08/31/2021 07:48:16 - INFO - __main__ - Step 102946: {'lr': 0.00011467952533603549, 'samples': 19765632, 'steps': 102945, 'loss/train': 1.1246271133422852} 08/31/2021 07:48:17 - INFO - __main__ - Step 102947: {'lr': 0.00011467506323729243, 'samples': 19765824, 'steps': 102946, 'loss/train': 0.9875687956809998} 08/31/2021 07:48:19 - INFO - __main__ - Step 102948: {'lr': 0.00011467060119952469, 'samples': 19766016, 'steps': 102947, 'loss/train': 0.8466693162918091} 08/31/2021 07:48:19 - INFO - __main__ - Step 102949: {'lr': 0.00011466613922273428, 'samples': 19766208, 'steps': 102948, 'loss/train': 1.2161518335342407} 08/31/2021 07:48:19 - INFO - __main__ - Step 102950: {'lr': 0.00011466167730692323, 'samples': 19766400, 'steps': 102949, 'loss/train': 0.016517069190740585} 08/31/2021 07:48:20 - INFO - __main__ - Step 102951: {'lr': 0.00011465721545209354, 'samples': 19766592, 'steps': 102950, 'loss/train': 1.7179794311523438} 08/31/2021 07:48:20 - INFO - __main__ - Step 102952: {'lr': 0.0001146527536582472, 'samples': 19766784, 'steps': 102951, 'loss/train': 1.5126292705535889} 08/31/2021 07:48:20 - INFO - __main__ - Step 102953: {'lr': 0.00011464829192538625, 'samples': 19766976, 'steps': 102952, 'loss/train': 1.0161540508270264} 08/31/2021 07:48:22 - INFO - __main__ - Step 102954: {'lr': 0.00011464383025351272, 'samples': 19767168, 'steps': 102953, 'loss/train': 1.021998643875122} 08/31/2021 07:48:22 - INFO - __main__ - Step 102955: {'lr': 0.00011463936864262856, 'samples': 19767360, 'steps': 102954, 'loss/train': 1.1985770463943481} 08/31/2021 07:48:23 - INFO - __main__ - Step 102956: {'lr': 0.00011463490709273591, 'samples': 19767552, 'steps': 102955, 'loss/train': 1.1931545734405518} 08/31/2021 07:48:23 - INFO - __main__ - Step 102957: {'lr': 0.00011463044560383659, 'samples': 19767744, 'steps': 102956, 'loss/train': 1.5618610382080078} 08/31/2021 07:48:23 - INFO - __main__ - Step 102958: {'lr': 0.0001146259841759327, 'samples': 19767936, 'steps': 102957, 'loss/train': 1.0014697313308716} 08/31/2021 07:48:24 - INFO - __main__ - Step 102959: {'lr': 0.00011462152280902627, 'samples': 19768128, 'steps': 102958, 'loss/train': 0.6504828929901123} 08/31/2021 07:48:25 - INFO - __main__ - Step 102960: {'lr': 0.00011461706150311927, 'samples': 19768320, 'steps': 102959, 'loss/train': 1.711073875427246} 08/31/2021 07:48:26 - INFO - __main__ - Step 102961: {'lr': 0.00011461260025821373, 'samples': 19768512, 'steps': 102960, 'loss/train': 1.3955481052398682} 08/31/2021 07:48:26 - INFO - __main__ - Step 102962: {'lr': 0.00011460813907431169, 'samples': 19768704, 'steps': 102961, 'loss/train': 0.7641656398773193} 08/31/2021 07:48:26 - INFO - __main__ - Step 102963: {'lr': 0.00011460367795141513, 'samples': 19768896, 'steps': 102962, 'loss/train': 1.4231196641921997} 08/31/2021 07:48:27 - INFO - __main__ - Step 102964: {'lr': 0.00011459921688952604, 'samples': 19769088, 'steps': 102963, 'loss/train': 0.5536224842071533} 08/31/2021 07:48:29 - INFO - __main__ - Step 102965: {'lr': 0.00011459475588864646, 'samples': 19769280, 'steps': 102964, 'loss/train': 1.2411967515945435} 08/31/2021 07:48:29 - INFO - __main__ - Step 102966: {'lr': 0.0001145902949487784, 'samples': 19769472, 'steps': 102965, 'loss/train': 0.9231042861938477} 08/31/2021 07:48:30 - INFO - __main__ - Step 102967: {'lr': 0.00011458583406992396, 'samples': 19769664, 'steps': 102966, 'loss/train': 0.9330569505691528} 08/31/2021 07:48:30 - INFO - __main__ - Step 102968: {'lr': 0.00011458137325208495, 'samples': 19769856, 'steps': 102967, 'loss/train': 0.6548598408699036} 08/31/2021 07:48:30 - INFO - __main__ - Step 102969: {'lr': 0.00011457691249526351, 'samples': 19770048, 'steps': 102968, 'loss/train': 0.7803599834442139} 08/31/2021 07:48:32 - INFO - __main__ - Step 102970: {'lr': 0.0001145724517994616, 'samples': 19770240, 'steps': 102969, 'loss/train': 1.01943838596344} 08/31/2021 07:48:32 - INFO - __main__ - Step 102971: {'lr': 0.00011456799116468126, 'samples': 19770432, 'steps': 102970, 'loss/train': 2.6550815105438232} 08/31/2021 07:48:33 - INFO - __main__ - Step 102972: {'lr': 0.00011456353059092448, 'samples': 19770624, 'steps': 102971, 'loss/train': 1.5653271675109863} 08/31/2021 07:48:33 - INFO - __main__ - Step 102973: {'lr': 0.0001145590700781933, 'samples': 19770816, 'steps': 102972, 'loss/train': 1.2792445421218872} 08/31/2021 07:48:33 - INFO - __main__ - Step 102974: {'lr': 0.0001145546096264897, 'samples': 19771008, 'steps': 102973, 'loss/train': 1.4324183464050293} 08/31/2021 07:48:34 - INFO - __main__ - Step 102975: {'lr': 0.00011455014923581571, 'samples': 19771200, 'steps': 102974, 'loss/train': 1.6541874408721924} 08/31/2021 07:48:35 - INFO - __main__ - Step 102976: {'lr': 0.00011454568890617334, 'samples': 19771392, 'steps': 102975, 'loss/train': 1.5096803903579712} 08/31/2021 07:48:36 - INFO - __main__ - Step 102977: {'lr': 0.00011454122863756458, 'samples': 19771584, 'steps': 102976, 'loss/train': 0.3427775204181671} 08/31/2021 07:48:36 - INFO - __main__ - Step 102978: {'lr': 0.00011453676842999156, 'samples': 19771776, 'steps': 102977, 'loss/train': 1.2362662553787231} 08/31/2021 07:48:36 - INFO - __main__ - Step 102979: {'lr': 0.00011453230828345606, 'samples': 19771968, 'steps': 102978, 'loss/train': 1.1835039854049683} 08/31/2021 07:48:37 - INFO - __main__ - Step 102980: {'lr': 0.00011452784819796026, 'samples': 19772160, 'steps': 102979, 'loss/train': 1.5385537147521973} 08/31/2021 07:48:39 - INFO - __main__ - Step 102981: {'lr': 0.00011452338817350608, 'samples': 19772352, 'steps': 102980, 'loss/train': 1.3311318159103394} 08/31/2021 07:48:40 - INFO - __main__ - Step 102982: {'lr': 0.00011451892821009557, 'samples': 19772544, 'steps': 102981, 'loss/train': 1.4301540851593018} 08/31/2021 07:48:40 - INFO - __main__ - Step 102983: {'lr': 0.00011451446830773076, 'samples': 19772736, 'steps': 102982, 'loss/train': 0.8287355303764343} 08/31/2021 07:48:40 - INFO - __main__ - Step 102984: {'lr': 0.00011451000846641363, 'samples': 19772928, 'steps': 102983, 'loss/train': 1.603290319442749} 08/31/2021 07:48:41 - INFO - __main__ - Step 102985: {'lr': 0.00011450554868614622, 'samples': 19773120, 'steps': 102984, 'loss/train': 1.0545421838760376} 08/31/2021 07:48:42 - INFO - __main__ - Step 102986: {'lr': 0.00011450108896693048, 'samples': 19773312, 'steps': 102985, 'loss/train': 1.376555323600769} 08/31/2021 07:48:43 - INFO - __main__ - Step 102987: {'lr': 0.00011449662930876848, 'samples': 19773504, 'steps': 102986, 'loss/train': 1.0158147811889648} 08/31/2021 07:48:43 - INFO - __main__ - Step 102988: {'lr': 0.0001144921697116622, 'samples': 19773696, 'steps': 102987, 'loss/train': 0.9945064187049866} 08/31/2021 07:48:43 - INFO - __main__ - Step 102989: {'lr': 0.00011448771017561369, 'samples': 19773888, 'steps': 102988, 'loss/train': 1.2292072772979736} 08/31/2021 07:48:44 - INFO - __main__ - Step 102990: {'lr': 0.0001144832507006249, 'samples': 19774080, 'steps': 102989, 'loss/train': 1.319274663925171} 08/31/2021 07:48:45 - INFO - __main__ - Step 102991: {'lr': 0.00011447879128669787, 'samples': 19774272, 'steps': 102990, 'loss/train': 0.6450743079185486} 08/31/2021 07:48:46 - INFO - __main__ - Step 102992: {'lr': 0.0001144743319338347, 'samples': 19774464, 'steps': 102991, 'loss/train': 0.6075178980827332} 08/31/2021 07:48:46 - INFO - __main__ - Step 102993: {'lr': 0.00011446987264203721, 'samples': 19774656, 'steps': 102992, 'loss/train': 1.2179808616638184} 08/31/2021 07:48:46 - INFO - __main__ - Step 102994: {'lr': 0.00011446541341130748, 'samples': 19774848, 'steps': 102993, 'loss/train': 0.4942600727081299} 08/31/2021 07:48:47 - INFO - __main__ - Step 102995: {'lr': 0.00011446095424164757, 'samples': 19775040, 'steps': 102994, 'loss/train': 0.6583268642425537} 08/31/2021 07:48:48 - INFO - __main__ - Step 102996: {'lr': 0.00011445649513305945, 'samples': 19775232, 'steps': 102995, 'loss/train': 0.9841436147689819} 08/31/2021 07:48:49 - INFO - __main__ - Step 102997: {'lr': 0.00011445203608554516, 'samples': 19775424, 'steps': 102996, 'loss/train': 1.6059064865112305} 08/31/2021 07:48:49 - INFO - __main__ - Step 102998: {'lr': 0.00011444757709910666, 'samples': 19775616, 'steps': 102997, 'loss/train': 1.9868892431259155} 08/31/2021 07:48:49 - INFO - __main__ - Step 102999: {'lr': 0.00011444311817374603, 'samples': 19775808, 'steps': 102998, 'loss/train': 1.1228289604187012} 08/31/2021 07:48:50 - INFO - __main__ - Step 103000: {'lr': 0.00011443865930946521, 'samples': 19776000, 'steps': 102999, 'loss/train': 0.8160231113433838} 08/31/2021 07:48:51 - INFO - __main__ - Step 103001: {'lr': 0.00011443420050626624, 'samples': 19776192, 'steps': 103000, 'loss/train': 0.9101318120956421} 08/31/2021 07:48:52 - INFO - __main__ - Step 103002: {'lr': 0.00011442974176415113, 'samples': 19776384, 'steps': 103001, 'loss/train': 0.7848303914070129} 08/31/2021 07:48:52 - INFO - __main__ - Step 103003: {'lr': 0.00011442528308312192, 'samples': 19776576, 'steps': 103002, 'loss/train': 1.1957274675369263} 08/31/2021 07:48:52 - INFO - __main__ - Step 103004: {'lr': 0.00011442082446318055, 'samples': 19776768, 'steps': 103003, 'loss/train': 0.9076095223426819} 08/31/2021 07:48:53 - INFO - __main__ - Step 103005: {'lr': 0.00011441636590432916, 'samples': 19776960, 'steps': 103004, 'loss/train': 1.230119228363037} 08/31/2021 07:48:54 - INFO - __main__ - Step 103006: {'lr': 0.00011441190740656956, 'samples': 19777152, 'steps': 103005, 'loss/train': 1.4565153121948242} 08/31/2021 07:48:55 - INFO - __main__ - Step 103007: {'lr': 0.00011440744896990387, 'samples': 19777344, 'steps': 103006, 'loss/train': 1.473261833190918} 08/31/2021 07:48:55 - INFO - __main__ - Step 103008: {'lr': 0.00011440299059433412, 'samples': 19777536, 'steps': 103007, 'loss/train': 0.5379543900489807} 08/31/2021 07:48:56 - INFO - __main__ - Step 103009: {'lr': 0.00011439853227986227, 'samples': 19777728, 'steps': 103008, 'loss/train': 0.6259070634841919} 08/31/2021 07:48:56 - INFO - __main__ - Step 103010: {'lr': 0.00011439407402649036, 'samples': 19777920, 'steps': 103009, 'loss/train': 0.9405578374862671} 08/31/2021 07:48:56 - INFO - __main__ - Step 103011: {'lr': 0.00011438961583422036, 'samples': 19778112, 'steps': 103010, 'loss/train': 1.234266996383667} 08/31/2021 07:48:58 - INFO - __main__ - Step 103012: {'lr': 0.00011438515770305432, 'samples': 19778304, 'steps': 103011, 'loss/train': 1.1620748043060303} 08/31/2021 07:48:58 - INFO - __main__ - Step 103013: {'lr': 0.00011438069963299425, 'samples': 19778496, 'steps': 103012, 'loss/train': 1.1439658403396606} 08/31/2021 07:48:59 - INFO - __main__ - Step 103014: {'lr': 0.00011437624162404212, 'samples': 19778688, 'steps': 103013, 'loss/train': 0.057403843849897385} 08/31/2021 07:48:59 - INFO - __main__ - Step 103015: {'lr': 0.00011437178367619996, 'samples': 19778880, 'steps': 103014, 'loss/train': 1.2356582880020142} 08/31/2021 07:49:00 - INFO - __main__ - Step 103016: {'lr': 0.00011436732578946982, 'samples': 19779072, 'steps': 103015, 'loss/train': 1.144582748413086} 08/31/2021 07:49:01 - INFO - __main__ - Step 103017: {'lr': 0.00011436286796385362, 'samples': 19779264, 'steps': 103016, 'loss/train': 1.0509963035583496} 08/31/2021 07:49:02 - INFO - __main__ - Step 103018: {'lr': 0.00011435841019935345, 'samples': 19779456, 'steps': 103017, 'loss/train': 1.0946733951568604} 08/31/2021 07:49:02 - INFO - __main__ - Step 103019: {'lr': 0.00011435395249597139, 'samples': 19779648, 'steps': 103018, 'loss/train': 1.2128715515136719} 08/31/2021 07:49:02 - INFO - __main__ - Step 103020: {'lr': 0.00011434949485370921, 'samples': 19779840, 'steps': 103019, 'loss/train': 0.5044548511505127} 08/31/2021 07:49:03 - INFO - __main__ - Step 103021: {'lr': 0.0001143450372725691, 'samples': 19780032, 'steps': 103020, 'loss/train': 0.7169390916824341} 08/31/2021 07:49:04 - INFO - __main__ - Step 103022: {'lr': 0.00011434057975255299, 'samples': 19780224, 'steps': 103021, 'loss/train': 2.054319143295288} 08/31/2021 07:49:05 - INFO - __main__ - Step 103023: {'lr': 0.00011433612229366295, 'samples': 19780416, 'steps': 103022, 'loss/train': 1.3806686401367188} 08/31/2021 07:49:05 - INFO - __main__ - Step 103024: {'lr': 0.00011433166489590094, 'samples': 19780608, 'steps': 103023, 'loss/train': 0.749598503112793} 08/31/2021 07:49:05 - INFO - __main__ - Step 103025: {'lr': 0.00011432720755926898, 'samples': 19780800, 'steps': 103024, 'loss/train': 0.020514003932476044} 08/31/2021 07:49:06 - INFO - __main__ - Step 103026: {'lr': 0.00011432275028376912, 'samples': 19780992, 'steps': 103025, 'loss/train': 1.4468200206756592} 08/31/2021 07:49:07 - INFO - __main__ - Step 103027: {'lr': 0.00011431829306940331, 'samples': 19781184, 'steps': 103026, 'loss/train': 0.7357423901557922} 08/31/2021 07:49:08 - INFO - __main__ - Step 103028: {'lr': 0.00011431383591617359, 'samples': 19781376, 'steps': 103027, 'loss/train': 1.3027558326721191} 08/31/2021 07:49:08 - INFO - __main__ - Step 103029: {'lr': 0.00011430937882408196, 'samples': 19781568, 'steps': 103028, 'loss/train': 0.93926602602005} 08/31/2021 07:49:08 - INFO - __main__ - Step 103030: {'lr': 0.00011430492179313043, 'samples': 19781760, 'steps': 103029, 'loss/train': 1.2415775060653687} 08/31/2021 07:49:09 - INFO - __main__ - Step 103031: {'lr': 0.00011430046482332101, 'samples': 19781952, 'steps': 103030, 'loss/train': 0.027686510235071182} 08/31/2021 07:49:09 - INFO - __main__ - Step 103032: {'lr': 0.0001142960079146558, 'samples': 19782144, 'steps': 103031, 'loss/train': 1.0189586877822876} 08/31/2021 07:49:11 - INFO - __main__ - Step 103033: {'lr': 0.00011429155106713662, 'samples': 19782336, 'steps': 103032, 'loss/train': 0.815425455570221} 08/31/2021 07:49:12 - INFO - __main__ - Step 103034: {'lr': 0.00011428709428076555, 'samples': 19782528, 'steps': 103033, 'loss/train': 0.9748965501785278} 08/31/2021 07:49:12 - INFO - __main__ - Step 103035: {'lr': 0.00011428263755554465, 'samples': 19782720, 'steps': 103034, 'loss/train': 0.7012942433357239} 08/31/2021 07:49:12 - INFO - __main__ - Step 103036: {'lr': 0.0001142781808914759, 'samples': 19782912, 'steps': 103035, 'loss/train': 1.546762228012085} 08/31/2021 07:49:13 - INFO - __main__ - Step 103037: {'lr': 0.0001142737242885613, 'samples': 19783104, 'steps': 103036, 'loss/train': 0.07098890095949173} 08/31/2021 07:49:14 - INFO - __main__ - Step 103038: {'lr': 0.00011426926774680288, 'samples': 19783296, 'steps': 103037, 'loss/train': 1.4286918640136719} 08/31/2021 07:49:15 - INFO - __main__ - Step 103039: {'lr': 0.00011426481126620262, 'samples': 19783488, 'steps': 103038, 'loss/train': 1.3131808042526245} 08/31/2021 07:49:15 - INFO - __main__ - Step 103040: {'lr': 0.00011426035484676254, 'samples': 19783680, 'steps': 103039, 'loss/train': 1.171387791633606} 08/31/2021 07:49:16 - INFO - __main__ - Step 103041: {'lr': 0.00011425589848848463, 'samples': 19783872, 'steps': 103040, 'loss/train': 0.9503030180931091} 08/31/2021 07:49:16 - INFO - __main__ - Step 103042: {'lr': 0.00011425144219137096, 'samples': 19784064, 'steps': 103041, 'loss/train': 0.867376446723938} 08/31/2021 07:49:18 - INFO - __main__ - Step 103043: {'lr': 0.00011424698595542346, 'samples': 19784256, 'steps': 103042, 'loss/train': 1.2828692197799683} 08/31/2021 07:49:18 - INFO - __main__ - Step 103044: {'lr': 0.0001142425297806442, 'samples': 19784448, 'steps': 103043, 'loss/train': 0.5934759378433228} 08/31/2021 07:49:19 - INFO - __main__ - Step 103045: {'lr': 0.00011423807366703515, 'samples': 19784640, 'steps': 103044, 'loss/train': 1.2847199440002441} 08/31/2021 07:49:19 - INFO - __main__ - Step 103046: {'lr': 0.00011423361761459841, 'samples': 19784832, 'steps': 103045, 'loss/train': 1.739162802696228} 08/31/2021 07:49:19 - INFO - __main__ - Step 103047: {'lr': 0.00011422916162333583, 'samples': 19785024, 'steps': 103046, 'loss/train': 1.4524414539337158} 08/31/2021 07:49:20 - INFO - __main__ - Step 103048: {'lr': 0.00011422470569324949, 'samples': 19785216, 'steps': 103047, 'loss/train': 0.1735684722661972} 08/31/2021 07:49:21 - INFO - __main__ - Step 103049: {'lr': 0.0001142202498243414, 'samples': 19785408, 'steps': 103048, 'loss/train': 1.2329187393188477} 08/31/2021 07:49:22 - INFO - __main__ - Step 103050: {'lr': 0.00011421579401661356, 'samples': 19785600, 'steps': 103049, 'loss/train': 0.930299699306488} 08/31/2021 07:49:22 - INFO - __main__ - Step 103051: {'lr': 0.00011421133827006802, 'samples': 19785792, 'steps': 103050, 'loss/train': 0.8296559453010559} 08/31/2021 07:49:23 - INFO - __main__ - Step 103052: {'lr': 0.00011420688258470672, 'samples': 19785984, 'steps': 103051, 'loss/train': 0.9697974920272827} 08/31/2021 07:49:23 - INFO - __main__ - Step 103053: {'lr': 0.00011420242696053174, 'samples': 19786176, 'steps': 103052, 'loss/train': 1.5190684795379639} 08/31/2021 07:49:23 - INFO - __main__ - Step 103054: {'lr': 0.00011419797139754501, 'samples': 19786368, 'steps': 103053, 'loss/train': 0.7760647535324097} 08/31/2021 07:49:25 - INFO - __main__ - Step 103055: {'lr': 0.00011419351589574862, 'samples': 19786560, 'steps': 103054, 'loss/train': 0.9735894799232483} 08/31/2021 07:49:25 - INFO - __main__ - Step 103056: {'lr': 0.00011418906045514449, 'samples': 19786752, 'steps': 103055, 'loss/train': 1.4639681577682495} 08/31/2021 07:49:26 - INFO - __main__ - Step 103057: {'lr': 0.00011418460507573469, 'samples': 19786944, 'steps': 103056, 'loss/train': 1.3963603973388672} 08/31/2021 07:49:26 - INFO - __main__ - Step 103058: {'lr': 0.00011418014975752122, 'samples': 19787136, 'steps': 103057, 'loss/train': 1.3646281957626343} 08/31/2021 07:49:27 - INFO - __main__ - Step 103059: {'lr': 0.00011417569450050619, 'samples': 19787328, 'steps': 103058, 'loss/train': 1.1782102584838867} 08/31/2021 07:49:28 - INFO - __main__ - Step 103060: {'lr': 0.00011417123930469137, 'samples': 19787520, 'steps': 103059, 'loss/train': 1.17402184009552} 08/31/2021 07:49:29 - INFO - __main__ - Step 103061: {'lr': 0.00011416678417007892, 'samples': 19787712, 'steps': 103060, 'loss/train': 1.7153735160827637} 08/31/2021 07:49:29 - INFO - __main__ - Step 103062: {'lr': 0.0001141623290966708, 'samples': 19787904, 'steps': 103061, 'loss/train': 0.11068594455718994} 08/31/2021 07:49:29 - INFO - __main__ - Step 103063: {'lr': 0.00011415787408446904, 'samples': 19788096, 'steps': 103062, 'loss/train': 0.6983914971351624} 08/31/2021 07:49:30 - INFO - __main__ - Step 103064: {'lr': 0.00011415341913347565, 'samples': 19788288, 'steps': 103063, 'loss/train': 1.084524393081665} 08/31/2021 07:49:31 - INFO - __main__ - Step 103065: {'lr': 0.00011414896424369264, 'samples': 19788480, 'steps': 103064, 'loss/train': 0.46894124150276184} 08/31/2021 07:49:32 - INFO - __main__ - Step 103066: {'lr': 0.000114144509415122, 'samples': 19788672, 'steps': 103065, 'loss/train': 0.7503259778022766} 08/31/2021 07:49:32 - INFO - __main__ - Step 103067: {'lr': 0.00011414005464776578, 'samples': 19788864, 'steps': 103066, 'loss/train': 2.0172512531280518} 08/31/2021 07:49:32 - INFO - __main__ - Step 103068: {'lr': 0.00011413559994162592, 'samples': 19789056, 'steps': 103067, 'loss/train': 0.4172382354736328} 08/31/2021 07:49:33 - INFO - __main__ - Step 103069: {'lr': 0.00011413114529670446, 'samples': 19789248, 'steps': 103068, 'loss/train': 1.1531482934951782} 08/31/2021 07:49:34 - INFO - __main__ - Step 103070: {'lr': 0.00011412669071300343, 'samples': 19789440, 'steps': 103069, 'loss/train': 1.4354934692382812} 08/31/2021 07:49:35 - INFO - __main__ - Step 103071: {'lr': 0.00011412223619052481, 'samples': 19789632, 'steps': 103070, 'loss/train': 1.5334827899932861} 08/31/2021 07:49:35 - INFO - __main__ - Step 103072: {'lr': 0.0001141177817292706, 'samples': 19789824, 'steps': 103071, 'loss/train': 0.711826741695404} 08/31/2021 07:49:35 - INFO - __main__ - Step 103073: {'lr': 0.00011411332732924293, 'samples': 19790016, 'steps': 103072, 'loss/train': 1.5735758543014526} 08/31/2021 07:49:36 - INFO - __main__ - Step 103074: {'lr': 0.00011410887299044359, 'samples': 19790208, 'steps': 103073, 'loss/train': 1.587536334991455} 08/31/2021 07:49:37 - INFO - __main__ - Step 103075: {'lr': 0.00011410441871287472, 'samples': 19790400, 'steps': 103074, 'loss/train': 1.3110610246658325} 08/31/2021 07:49:38 - INFO - __main__ - Step 103076: {'lr': 0.00011409996449653828, 'samples': 19790592, 'steps': 103075, 'loss/train': 1.9000658988952637} 08/31/2021 07:49:38 - INFO - __main__ - Step 103077: {'lr': 0.0001140955103414363, 'samples': 19790784, 'steps': 103076, 'loss/train': 1.0341843366622925} 08/31/2021 07:49:38 - INFO - __main__ - Step 103078: {'lr': 0.0001140910562475708, 'samples': 19790976, 'steps': 103077, 'loss/train': 0.8032108545303345} 08/31/2021 07:49:39 - INFO - __main__ - Step 103079: {'lr': 0.00011408660221494377, 'samples': 19791168, 'steps': 103078, 'loss/train': 0.8719102740287781} 08/31/2021 07:49:40 - INFO - __main__ - Step 103080: {'lr': 0.0001140821482435572, 'samples': 19791360, 'steps': 103079, 'loss/train': 1.6663750410079956} 08/31/2021 07:49:41 - INFO - __main__ - Step 103081: {'lr': 0.00011407769433341314, 'samples': 19791552, 'steps': 103080, 'loss/train': 0.8722819685935974} 08/31/2021 07:49:41 - INFO - __main__ - Step 103082: {'lr': 0.00011407324048451356, 'samples': 19791744, 'steps': 103081, 'loss/train': 0.8285781145095825} 08/31/2021 07:49:41 - INFO - __main__ - Step 103083: {'lr': 0.00011406878669686047, 'samples': 19791936, 'steps': 103082, 'loss/train': 1.2354656457901} 08/31/2021 07:49:42 - INFO - __main__ - Step 103084: {'lr': 0.0001140643329704559, 'samples': 19792128, 'steps': 103083, 'loss/train': 0.8452224731445312} 08/31/2021 07:49:42 - INFO - __main__ - Step 103085: {'lr': 0.00011405987930530184, 'samples': 19792320, 'steps': 103084, 'loss/train': 0.7961551547050476} 08/31/2021 07:49:44 - INFO - __main__ - Step 103086: {'lr': 0.0001140554257014004, 'samples': 19792512, 'steps': 103085, 'loss/train': 1.2057509422302246} 08/31/2021 07:49:45 - INFO - __main__ - Step 103087: {'lr': 0.00011405097215875341, 'samples': 19792704, 'steps': 103086, 'loss/train': 1.1733423471450806} 08/31/2021 07:49:45 - INFO - __main__ - Step 103088: {'lr': 0.00011404651867736293, 'samples': 19792896, 'steps': 103087, 'loss/train': 1.1359573602676392} 08/31/2021 07:49:45 - INFO - __main__ - Step 103089: {'lr': 0.00011404206525723102, 'samples': 19793088, 'steps': 103088, 'loss/train': 1.0433318614959717} 08/31/2021 07:49:46 - INFO - __main__ - Step 103090: {'lr': 0.00011403761189835962, 'samples': 19793280, 'steps': 103089, 'loss/train': 1.2028073072433472} 08/31/2021 07:49:47 - INFO - __main__ - Step 103091: {'lr': 0.00011403315860075078, 'samples': 19793472, 'steps': 103090, 'loss/train': 1.222922444343567} 08/31/2021 07:49:48 - INFO - __main__ - Step 103092: {'lr': 0.00011402870536440652, 'samples': 19793664, 'steps': 103091, 'loss/train': 1.2949196100234985} 08/31/2021 07:49:48 - INFO - __main__ - Step 103093: {'lr': 0.00011402425218932883, 'samples': 19793856, 'steps': 103092, 'loss/train': 1.5762770175933838} 08/31/2021 07:49:48 - INFO - __main__ - Step 103094: {'lr': 0.00011401979907551968, 'samples': 19794048, 'steps': 103093, 'loss/train': 1.236182451248169} 08/31/2021 07:49:49 - INFO - __main__ - Step 103095: {'lr': 0.00011401534602298114, 'samples': 19794240, 'steps': 103094, 'loss/train': 0.8767582178115845} 08/31/2021 07:49:50 - INFO - __main__ - Step 103096: {'lr': 0.00011401089303171516, 'samples': 19794432, 'steps': 103095, 'loss/train': 0.6427907347679138} 08/31/2021 07:49:51 - INFO - __main__ - Step 103097: {'lr': 0.00011400644010172381, 'samples': 19794624, 'steps': 103096, 'loss/train': 0.9935689568519592} 08/31/2021 07:49:51 - INFO - __main__ - Step 103098: {'lr': 0.00011400198723300903, 'samples': 19794816, 'steps': 103097, 'loss/train': 0.7606958746910095} 08/31/2021 07:49:51 - INFO - __main__ - Step 103099: {'lr': 0.00011399753442557298, 'samples': 19795008, 'steps': 103098, 'loss/train': 1.4038485288619995} 08/31/2021 07:49:52 - INFO - __main__ - Step 103100: {'lr': 0.00011399308167941741, 'samples': 19795200, 'steps': 103099, 'loss/train': 0.4852368235588074} 08/31/2021 07:49:53 - INFO - __main__ - Step 103101: {'lr': 0.00011398862899454449, 'samples': 19795392, 'steps': 103100, 'loss/train': 1.692582607269287} 08/31/2021 07:49:54 - INFO - __main__ - Step 103102: {'lr': 0.00011398417637095618, 'samples': 19795584, 'steps': 103101, 'loss/train': 1.0432783365249634} 08/31/2021 07:49:54 - INFO - __main__ - Step 103103: {'lr': 0.0001139797238086545, 'samples': 19795776, 'steps': 103102, 'loss/train': 1.0072978734970093} 08/31/2021 07:49:55 - INFO - __main__ - Step 103104: {'lr': 0.00011397527130764147, 'samples': 19795968, 'steps': 103103, 'loss/train': 1.7835536003112793} 08/31/2021 07:49:55 - INFO - __main__ - Step 103105: {'lr': 0.00011397081886791908, 'samples': 19796160, 'steps': 103104, 'loss/train': 1.2917276620864868} 08/31/2021 07:49:55 - INFO - __main__ - Step 103106: {'lr': 0.00011396636648948932, 'samples': 19796352, 'steps': 103105, 'loss/train': 1.0356570482254028} 08/31/2021 07:49:57 - INFO - __main__ - Step 103107: {'lr': 0.00011396191417235425, 'samples': 19796544, 'steps': 103106, 'loss/train': 0.04559139162302017} 08/31/2021 07:49:57 - INFO - __main__ - Step 103108: {'lr': 0.00011395746191651581, 'samples': 19796736, 'steps': 103107, 'loss/train': 1.1418797969818115} 08/31/2021 07:49:58 - INFO - __main__ - Step 103109: {'lr': 0.00011395300972197606, 'samples': 19796928, 'steps': 103108, 'loss/train': 1.5554733276367188} 08/31/2021 07:49:58 - INFO - __main__ - Step 103110: {'lr': 0.00011394855758873696, 'samples': 19797120, 'steps': 103109, 'loss/train': 1.0986348390579224} 08/31/2021 07:49:58 - INFO - __main__ - Step 103111: {'lr': 0.00011394410551680057, 'samples': 19797312, 'steps': 103110, 'loss/train': 1.2844491004943848} 08/31/2021 07:50:00 - INFO - __main__ - Step 103112: {'lr': 0.00011393965350616887, 'samples': 19797504, 'steps': 103111, 'loss/train': 1.7884583473205566} 08/31/2021 07:50:01 - INFO - __main__ - Step 103113: {'lr': 0.00011393520155684391, 'samples': 19797696, 'steps': 103112, 'loss/train': 0.8151888847351074} 08/31/2021 07:50:01 - INFO - __main__ - Step 103114: {'lr': 0.0001139307496688276, 'samples': 19797888, 'steps': 103113, 'loss/train': 1.0197993516921997} 08/31/2021 07:50:01 - INFO - __main__ - Step 103115: {'lr': 0.00011392629784212197, 'samples': 19798080, 'steps': 103114, 'loss/train': 1.1856931447982788} 08/31/2021 07:50:02 - INFO - __main__ - Step 103116: {'lr': 0.00011392184607672906, 'samples': 19798272, 'steps': 103115, 'loss/train': 0.017266925424337387} 08/31/2021 07:50:02 - INFO - __main__ - Step 103117: {'lr': 0.00011391739437265086, 'samples': 19798464, 'steps': 103116, 'loss/train': 1.388851523399353} 08/31/2021 07:50:04 - INFO - __main__ - Step 103118: {'lr': 0.0001139129427298894, 'samples': 19798656, 'steps': 103117, 'loss/train': 1.2434931993484497} 08/31/2021 07:50:04 - INFO - __main__ - Step 103119: {'lr': 0.00011390849114844664, 'samples': 19798848, 'steps': 103118, 'loss/train': 1.315948724746704} 08/31/2021 07:50:04 - INFO - __main__ - Step 103120: {'lr': 0.00011390403962832466, 'samples': 19799040, 'steps': 103119, 'loss/train': 1.5677226781845093} 08/31/2021 07:50:05 - INFO - __main__ - Step 103121: {'lr': 0.00011389958816952536, 'samples': 19799232, 'steps': 103120, 'loss/train': 1.281481146812439} 08/31/2021 07:50:05 - INFO - __main__ - Step 103122: {'lr': 0.00011389513677205084, 'samples': 19799424, 'steps': 103121, 'loss/train': 0.796940803527832} 08/31/2021 07:50:07 - INFO - __main__ - Step 103123: {'lr': 0.00011389068543590309, 'samples': 19799616, 'steps': 103122, 'loss/train': 1.6819267272949219} 08/31/2021 07:50:07 - INFO - __main__ - Step 103124: {'lr': 0.00011388623416108406, 'samples': 19799808, 'steps': 103123, 'loss/train': 1.3889405727386475} 08/31/2021 07:50:08 - INFO - __main__ - Step 103125: {'lr': 0.0001138817829475958, 'samples': 19800000, 'steps': 103124, 'loss/train': 0.9907286763191223} 08/31/2021 07:50:08 - INFO - __main__ - Step 103126: {'lr': 0.00011387733179544041, 'samples': 19800192, 'steps': 103125, 'loss/train': 0.01533495169132948} 08/31/2021 07:50:08 - INFO - __main__ - Step 103127: {'lr': 0.0001138728807046197, 'samples': 19800384, 'steps': 103126, 'loss/train': 1.3696541786193848} 08/31/2021 07:50:09 - INFO - __main__ - Step 103128: {'lr': 0.00011386842967513578, 'samples': 19800576, 'steps': 103127, 'loss/train': 1.6885591745376587} 08/31/2021 07:50:10 - INFO - __main__ - Step 103129: {'lr': 0.00011386397870699062, 'samples': 19800768, 'steps': 103128, 'loss/train': 1.6005311012268066} 08/31/2021 07:50:11 - INFO - __main__ - Step 103130: {'lr': 0.00011385952780018627, 'samples': 19800960, 'steps': 103129, 'loss/train': 1.4117517471313477} 08/31/2021 07:50:11 - INFO - __main__ - Step 103131: {'lr': 0.00011385507695472468, 'samples': 19801152, 'steps': 103130, 'loss/train': 1.0835163593292236} 08/31/2021 07:50:11 - INFO - __main__ - Step 103132: {'lr': 0.00011385062617060793, 'samples': 19801344, 'steps': 103131, 'loss/train': 1.0325669050216675} 08/31/2021 07:50:12 - INFO - __main__ - Step 103133: {'lr': 0.00011384617544783799, 'samples': 19801536, 'steps': 103132, 'loss/train': 0.3893069624900818} 08/31/2021 07:50:14 - INFO - __main__ - Step 103134: {'lr': 0.00011384172478641686, 'samples': 19801728, 'steps': 103133, 'loss/train': 1.1826452016830444} 08/31/2021 07:50:15 - INFO - __main__ - Step 103135: {'lr': 0.00011383727418634653, 'samples': 19801920, 'steps': 103134, 'loss/train': 1.2535285949707031} 08/31/2021 07:50:15 - INFO - __main__ - Step 103136: {'lr': 0.00011383282364762904, 'samples': 19802112, 'steps': 103135, 'loss/train': 1.6567659378051758} 08/31/2021 07:50:15 - INFO - __main__ - Step 103137: {'lr': 0.00011382837317026637, 'samples': 19802304, 'steps': 103136, 'loss/train': 1.7456068992614746} 08/31/2021 07:50:16 - INFO - __main__ - Step 103138: {'lr': 0.00011382392275426052, 'samples': 19802496, 'steps': 103137, 'loss/train': 1.769305944442749} 08/31/2021 07:50:16 - INFO - __main__ - Step 103139: {'lr': 0.00011381947239961352, 'samples': 19802688, 'steps': 103138, 'loss/train': 1.7773842811584473} 08/31/2021 07:50:16 - INFO - __main__ - Step 103140: {'lr': 0.00011381502210632746, 'samples': 19802880, 'steps': 103139, 'loss/train': 1.1451799869537354} 08/31/2021 07:50:18 - INFO - __main__ - Step 103141: {'lr': 0.00011381057187440416, 'samples': 19803072, 'steps': 103140, 'loss/train': 1.6251858472824097} 08/31/2021 07:50:19 - INFO - __main__ - Step 103142: {'lr': 0.00011380612170384572, 'samples': 19803264, 'steps': 103141, 'loss/train': 0.5795865654945374} 08/31/2021 07:50:19 - INFO - __main__ - Step 103143: {'lr': 0.00011380167159465413, 'samples': 19803456, 'steps': 103142, 'loss/train': 0.639456033706665} 08/31/2021 07:50:19 - INFO - __main__ - Step 103144: {'lr': 0.0001137972215468314, 'samples': 19803648, 'steps': 103143, 'loss/train': 1.380344033241272} 08/31/2021 07:50:20 - INFO - __main__ - Step 103145: {'lr': 0.00011379277156037954, 'samples': 19803840, 'steps': 103144, 'loss/train': 0.9035762548446655} 08/31/2021 07:50:22 - INFO - __main__ - Step 103146: {'lr': 0.00011378832163530056, 'samples': 19804032, 'steps': 103145, 'loss/train': 1.3242989778518677} 08/31/2021 07:50:22 - INFO - __main__ - Step 103147: {'lr': 0.00011378387177159646, 'samples': 19804224, 'steps': 103146, 'loss/train': 0.7390807271003723} 08/31/2021 07:50:23 - INFO - __main__ - Step 103148: {'lr': 0.00011377942196926924, 'samples': 19804416, 'steps': 103147, 'loss/train': 1.3450982570648193} 08/31/2021 07:50:23 - INFO - __main__ - Step 103149: {'lr': 0.00011377497222832092, 'samples': 19804608, 'steps': 103148, 'loss/train': 1.3340363502502441} 08/31/2021 07:50:23 - INFO - __main__ - Step 103150: {'lr': 0.0001137705225487535, 'samples': 19804800, 'steps': 103149, 'loss/train': 1.5038671493530273} 08/31/2021 07:50:26 - INFO - __main__ - Step 103151: {'lr': 0.00011376607293056898, 'samples': 19804992, 'steps': 103150, 'loss/train': 0.9917954802513123} 08/31/2021 07:50:26 - INFO - __main__ - Step 103152: {'lr': 0.00011376162337376936, 'samples': 19805184, 'steps': 103151, 'loss/train': 1.4361491203308105} 08/31/2021 07:50:26 - INFO - __main__ - Step 103153: {'lr': 0.00011375717387835674, 'samples': 19805376, 'steps': 103152, 'loss/train': 1.3863941431045532} 08/31/2021 07:50:27 - INFO - __main__ - Step 103154: {'lr': 0.00011375272444433294, 'samples': 19805568, 'steps': 103153, 'loss/train': 1.1532419919967651} 08/31/2021 07:50:27 - INFO - __main__ - Step 103155: {'lr': 0.00011374827507170005, 'samples': 19805760, 'steps': 103154, 'loss/train': 0.562231183052063} 08/31/2021 07:50:27 - INFO - __main__ - Step 103156: {'lr': 0.0001137438257604601, 'samples': 19805952, 'steps': 103155, 'loss/train': 0.01623363234102726} 08/31/2021 07:50:28 - INFO - __main__ - Step 103157: {'lr': 0.00011373937651061509, 'samples': 19806144, 'steps': 103156, 'loss/train': 0.015171683393418789} 08/31/2021 07:50:29 - INFO - __main__ - Step 103158: {'lr': 0.000113734927322167, 'samples': 19806336, 'steps': 103157, 'loss/train': 0.9028975963592529} 08/31/2021 07:50:30 - INFO - __main__ - Step 103159: {'lr': 0.00011373047819511783, 'samples': 19806528, 'steps': 103158, 'loss/train': 0.7255801558494568} 08/31/2021 07:50:30 - INFO - __main__ - Step 103160: {'lr': 0.00011372602912946964, 'samples': 19806720, 'steps': 103159, 'loss/train': 1.4244524240493774} 08/31/2021 07:50:31 - INFO - __main__ - Step 103161: {'lr': 0.00011372158012522438, 'samples': 19806912, 'steps': 103160, 'loss/train': 1.4014835357666016} 08/31/2021 07:50:31 - INFO - __main__ - Step 103162: {'lr': 0.00011371713118238408, 'samples': 19807104, 'steps': 103161, 'loss/train': 1.2314075231552124} 08/31/2021 07:50:33 - INFO - __main__ - Step 103163: {'lr': 0.00011371268230095075, 'samples': 19807296, 'steps': 103162, 'loss/train': 1.166285514831543} 08/31/2021 07:50:33 - INFO - __main__ - Step 103164: {'lr': 0.00011370823348092635, 'samples': 19807488, 'steps': 103163, 'loss/train': 1.1039981842041016} 08/31/2021 07:50:33 - INFO - __main__ - Step 103165: {'lr': 0.00011370378472231293, 'samples': 19807680, 'steps': 103164, 'loss/train': 0.8490579128265381} 08/31/2021 07:50:34 - INFO - __main__ - Step 103166: {'lr': 0.00011369933602511248, 'samples': 19807872, 'steps': 103165, 'loss/train': 0.7152259349822998} 08/31/2021 07:50:34 - INFO - __main__ - Step 103167: {'lr': 0.00011369488738932713, 'samples': 19808064, 'steps': 103166, 'loss/train': 1.1835861206054688} 08/31/2021 07:50:34 - INFO - __main__ - Step 103168: {'lr': 0.00011369043881495863, 'samples': 19808256, 'steps': 103167, 'loss/train': 0.7224677205085754} 08/31/2021 07:50:36 - INFO - __main__ - Step 103169: {'lr': 0.00011368599030200913, 'samples': 19808448, 'steps': 103168, 'loss/train': 1.342576265335083} 08/31/2021 07:50:37 - INFO - __main__ - Step 103170: {'lr': 0.0001136815418504806, 'samples': 19808640, 'steps': 103169, 'loss/train': 0.5258198976516724} 08/31/2021 07:50:37 - INFO - __main__ - Step 103171: {'lr': 0.00011367709346037508, 'samples': 19808832, 'steps': 103170, 'loss/train': 1.9353625774383545} 08/31/2021 07:50:37 - INFO - __main__ - Step 103172: {'lr': 0.00011367264513169456, 'samples': 19809024, 'steps': 103171, 'loss/train': 1.188541054725647} 08/31/2021 07:50:38 - INFO - __main__ - Step 103173: {'lr': 0.00011366819686444105, 'samples': 19809216, 'steps': 103172, 'loss/train': 1.526586890220642} 08/31/2021 07:50:39 - INFO - __main__ - Step 103174: {'lr': 0.00011366374865861653, 'samples': 19809408, 'steps': 103173, 'loss/train': 2.1701581478118896} 08/31/2021 07:50:40 - INFO - __main__ - Step 103175: {'lr': 0.00011365930051422305, 'samples': 19809600, 'steps': 103174, 'loss/train': 0.21536609530448914} 08/31/2021 07:50:40 - INFO - __main__ - Step 103176: {'lr': 0.00011365485243126256, 'samples': 19809792, 'steps': 103175, 'loss/train': 0.6973598003387451} 08/31/2021 07:50:40 - INFO - __main__ - Step 103177: {'lr': 0.00011365040440973709, 'samples': 19809984, 'steps': 103176, 'loss/train': 1.1359515190124512} 08/31/2021 07:50:41 - INFO - __main__ - Step 103178: {'lr': 0.00011364595644964865, 'samples': 19810176, 'steps': 103177, 'loss/train': 1.078758716583252} 08/31/2021 07:50:42 - INFO - __main__ - Step 103179: {'lr': 0.00011364150855099922, 'samples': 19810368, 'steps': 103178, 'loss/train': 0.054410405457019806} 08/31/2021 07:50:43 - INFO - __main__ - Step 103180: {'lr': 0.00011363706071379092, 'samples': 19810560, 'steps': 103179, 'loss/train': 1.3979026079177856} 08/31/2021 07:50:43 - INFO - __main__ - Step 103181: {'lr': 0.00011363261293802557, 'samples': 19810752, 'steps': 103180, 'loss/train': 1.4100744724273682} 08/31/2021 07:50:43 - INFO - __main__ - Step 103182: {'lr': 0.00011362816522370529, 'samples': 19810944, 'steps': 103181, 'loss/train': 0.2953925132751465} 08/31/2021 07:50:44 - INFO - __main__ - Step 103183: {'lr': 0.00011362371757083201, 'samples': 19811136, 'steps': 103182, 'loss/train': 1.5846126079559326} 08/31/2021 07:50:45 - INFO - __main__ - Step 103184: {'lr': 0.0001136192699794078, 'samples': 19811328, 'steps': 103183, 'loss/train': 1.2847208976745605} 08/31/2021 07:50:46 - INFO - __main__ - Step 103185: {'lr': 0.00011361482244943463, 'samples': 19811520, 'steps': 103184, 'loss/train': 0.5931851267814636} 08/31/2021 07:50:46 - INFO - __main__ - Step 103186: {'lr': 0.00011361037498091453, 'samples': 19811712, 'steps': 103185, 'loss/train': 0.9248389601707458} 08/31/2021 07:50:46 - INFO - __main__ - Step 103187: {'lr': 0.0001136059275738495, 'samples': 19811904, 'steps': 103186, 'loss/train': 1.3743131160736084} 08/31/2021 07:50:47 - INFO - __main__ - Step 103188: {'lr': 0.00011360148022824152, 'samples': 19812096, 'steps': 103187, 'loss/train': 0.8543387055397034} 08/31/2021 07:50:47 - INFO - __main__ - Step 103189: {'lr': 0.0001135970329440926, 'samples': 19812288, 'steps': 103188, 'loss/train': 1.2793270349502563} 08/31/2021 07:50:49 - INFO - __main__ - Step 103190: {'lr': 0.00011359258572140477, 'samples': 19812480, 'steps': 103189, 'loss/train': 1.7243282794952393} 08/31/2021 07:50:49 - INFO - __main__ - Step 103191: {'lr': 0.00011358813856018, 'samples': 19812672, 'steps': 103190, 'loss/train': 0.5319922566413879} 08/31/2021 07:50:49 - INFO - __main__ - Step 103192: {'lr': 0.00011358369146042042, 'samples': 19812864, 'steps': 103191, 'loss/train': 1.6609702110290527} 08/31/2021 07:50:50 - INFO - __main__ - Step 103193: {'lr': 0.0001135792444221278, 'samples': 19813056, 'steps': 103192, 'loss/train': 1.1546564102172852} 08/31/2021 07:50:50 - INFO - __main__ - Step 103194: {'lr': 0.00011357479744530427, 'samples': 19813248, 'steps': 103193, 'loss/train': 1.935894250869751} 08/31/2021 07:50:52 - INFO - __main__ - Step 103195: {'lr': 0.00011357035052995188, 'samples': 19813440, 'steps': 103194, 'loss/train': 1.0080795288085938} 08/31/2021 07:50:52 - INFO - __main__ - Step 103196: {'lr': 0.00011356590367607253, 'samples': 19813632, 'steps': 103195, 'loss/train': 1.3583985567092896} 08/31/2021 07:50:52 - INFO - __main__ - Step 103197: {'lr': 0.00011356145688366831, 'samples': 19813824, 'steps': 103196, 'loss/train': 1.2485445737838745} 08/31/2021 07:50:53 - INFO - __main__ - Step 103198: {'lr': 0.00011355701015274117, 'samples': 19814016, 'steps': 103197, 'loss/train': 0.3724300265312195} 08/31/2021 07:50:53 - INFO - __main__ - Step 103199: {'lr': 0.00011355256348329315, 'samples': 19814208, 'steps': 103198, 'loss/train': 1.7832136154174805} 08/31/2021 07:50:55 - INFO - __main__ - Step 103200: {'lr': 0.00011354811687532626, 'samples': 19814400, 'steps': 103199, 'loss/train': 1.1602777242660522} 08/31/2021 07:50:56 - INFO - __main__ - Step 103201: {'lr': 0.00011354367032884244, 'samples': 19814592, 'steps': 103200, 'loss/train': 1.4273217916488647} 08/31/2021 07:50:56 - INFO - __main__ - Step 103202: {'lr': 0.00011353922384384377, 'samples': 19814784, 'steps': 103201, 'loss/train': 0.026298411190509796} 08/31/2021 07:50:57 - INFO - __main__ - Step 103203: {'lr': 0.00011353477742033231, 'samples': 19814976, 'steps': 103202, 'loss/train': 1.249007225036621} 08/31/2021 07:50:57 - INFO - __main__ - Step 103204: {'lr': 0.00011353033105830987, 'samples': 19815168, 'steps': 103203, 'loss/train': 0.794483482837677} 08/31/2021 07:50:58 - INFO - __main__ - Step 103205: {'lr': 0.00011352588475777856, 'samples': 19815360, 'steps': 103204, 'loss/train': 1.1805912256240845} 08/31/2021 07:50:59 - INFO - __main__ - Step 103206: {'lr': 0.00011352143851874036, 'samples': 19815552, 'steps': 103205, 'loss/train': 0.5595102906227112} 08/31/2021 07:50:59 - INFO - __main__ - Step 103207: {'lr': 0.00011351699234119734, 'samples': 19815744, 'steps': 103206, 'loss/train': 1.1707268953323364} 08/31/2021 07:51:00 - INFO - __main__ - Step 103208: {'lr': 0.00011351254622515142, 'samples': 19815936, 'steps': 103207, 'loss/train': 0.6626666784286499} 08/31/2021 07:51:00 - INFO - __main__ - Step 103209: {'lr': 0.00011350810017060464, 'samples': 19816128, 'steps': 103208, 'loss/train': 1.6899062395095825} 08/31/2021 07:51:01 - INFO - __main__ - Step 103210: {'lr': 0.00011350365417755901, 'samples': 19816320, 'steps': 103209, 'loss/train': 0.5566109418869019} 08/31/2021 07:51:02 - INFO - __main__ - Step 103211: {'lr': 0.00011349920824601653, 'samples': 19816512, 'steps': 103210, 'loss/train': 0.4609620273113251} 08/31/2021 07:51:02 - INFO - __main__ - Step 103212: {'lr': 0.00011349476237597922, 'samples': 19816704, 'steps': 103211, 'loss/train': 0.9410513043403625} 08/31/2021 07:51:03 - INFO - __main__ - Step 103213: {'lr': 0.00011349031656744904, 'samples': 19816896, 'steps': 103212, 'loss/train': 1.5982071161270142} 08/31/2021 07:51:03 - INFO - __main__ - Step 103214: {'lr': 0.00011348587082042811, 'samples': 19817088, 'steps': 103213, 'loss/train': 1.3225412368774414} 08/31/2021 07:51:05 - INFO - __main__ - Step 103215: {'lr': 0.00011348142513491824, 'samples': 19817280, 'steps': 103214, 'loss/train': 1.340444803237915} 08/31/2021 07:51:05 - INFO - __main__ - Step 103216: {'lr': 0.00011347697951092156, 'samples': 19817472, 'steps': 103215, 'loss/train': 0.9756584763526917} 08/31/2021 07:51:06 - INFO - __main__ - Step 103217: {'lr': 0.00011347253394844004, 'samples': 19817664, 'steps': 103216, 'loss/train': 0.16707120835781097} 08/31/2021 07:51:06 - INFO - __main__ - Step 103218: {'lr': 0.00011346808844747567, 'samples': 19817856, 'steps': 103217, 'loss/train': 0.8254596590995789} 08/31/2021 07:51:06 - INFO - __main__ - Step 103219: {'lr': 0.0001134636430080305, 'samples': 19818048, 'steps': 103218, 'loss/train': 1.3625415563583374} 08/31/2021 07:51:07 - INFO - __main__ - Step 103220: {'lr': 0.00011345919763010648, 'samples': 19818240, 'steps': 103219, 'loss/train': 1.5200717449188232} 08/31/2021 07:51:08 - INFO - __main__ - Step 103221: {'lr': 0.00011345475231370564, 'samples': 19818432, 'steps': 103220, 'loss/train': 0.9977383613586426} 08/31/2021 07:51:09 - INFO - __main__ - Step 103222: {'lr': 0.00011345030705883, 'samples': 19818624, 'steps': 103221, 'loss/train': 0.9850178360939026} 08/31/2021 07:51:09 - INFO - __main__ - Step 103223: {'lr': 0.00011344586186548153, 'samples': 19818816, 'steps': 103222, 'loss/train': 1.5447347164154053} 08/31/2021 07:51:10 - INFO - __main__ - Step 103224: {'lr': 0.00011344141673366227, 'samples': 19819008, 'steps': 103223, 'loss/train': 1.3225950002670288} 08/31/2021 07:51:10 - INFO - __main__ - Step 103225: {'lr': 0.00011343697166337425, 'samples': 19819200, 'steps': 103224, 'loss/train': 1.3002936840057373} 08/31/2021 07:51:10 - INFO - __main__ - Step 103226: {'lr': 0.00011343252665461936, 'samples': 19819392, 'steps': 103225, 'loss/train': 1.0784753561019897} 08/31/2021 07:51:12 - INFO - __main__ - Step 103227: {'lr': 0.00011342808170739966, 'samples': 19819584, 'steps': 103226, 'loss/train': 0.9109216928482056} 08/31/2021 07:51:12 - INFO - __main__ - Step 103228: {'lr': 0.00011342363682171716, 'samples': 19819776, 'steps': 103227, 'loss/train': 1.006446361541748} 08/31/2021 07:51:13 - INFO - __main__ - Step 103229: {'lr': 0.00011341919199757387, 'samples': 19819968, 'steps': 103228, 'loss/train': 0.09764053672552109} 08/31/2021 07:51:13 - INFO - __main__ - Step 103230: {'lr': 0.00011341474723497178, 'samples': 19820160, 'steps': 103229, 'loss/train': 0.1317274570465088} 08/31/2021 07:51:13 - INFO - __main__ - Step 103231: {'lr': 0.00011341030253391288, 'samples': 19820352, 'steps': 103230, 'loss/train': 1.56969153881073} 08/31/2021 07:51:15 - INFO - __main__ - Step 103232: {'lr': 0.0001134058578943992, 'samples': 19820544, 'steps': 103231, 'loss/train': 1.0987919569015503} 08/31/2021 07:51:15 - INFO - __main__ - Step 103233: {'lr': 0.00011340141331643275, 'samples': 19820736, 'steps': 103232, 'loss/train': 1.1224582195281982} 08/31/2021 07:51:16 - INFO - __main__ - Step 103234: {'lr': 0.00011339696880001548, 'samples': 19820928, 'steps': 103233, 'loss/train': 1.0899044275283813} 08/31/2021 07:51:16 - INFO - __main__ - Step 103235: {'lr': 0.00011339252434514947, 'samples': 19821120, 'steps': 103234, 'loss/train': 0.8515387773513794} 08/31/2021 07:51:16 - INFO - __main__ - Step 103236: {'lr': 0.00011338807995183676, 'samples': 19821312, 'steps': 103235, 'loss/train': 1.7437602281570435} 08/31/2021 07:51:18 - INFO - __main__ - Step 103237: {'lr': 0.00011338363562007916, 'samples': 19821504, 'steps': 103236, 'loss/train': 1.757574439048767} 08/31/2021 07:51:18 - INFO - __main__ - Step 103238: {'lr': 0.00011337919134987881, 'samples': 19821696, 'steps': 103237, 'loss/train': 1.163340449333191} 08/31/2021 07:51:19 - INFO - __main__ - Step 103239: {'lr': 0.00011337474714123766, 'samples': 19821888, 'steps': 103238, 'loss/train': 1.6050533056259155} 08/31/2021 07:51:19 - INFO - __main__ - Step 103240: {'lr': 0.00011337030299415777, 'samples': 19822080, 'steps': 103239, 'loss/train': 0.39137348532676697} 08/31/2021 07:51:19 - INFO - __main__ - Step 103241: {'lr': 0.00011336585890864109, 'samples': 19822272, 'steps': 103240, 'loss/train': 0.9831041097640991} 08/31/2021 07:51:21 - INFO - __main__ - Step 103242: {'lr': 0.00011336141488468967, 'samples': 19822464, 'steps': 103241, 'loss/train': 1.2211482524871826} 08/31/2021 07:51:22 - INFO - __main__ - Step 103243: {'lr': 0.00011335697092230546, 'samples': 19822656, 'steps': 103242, 'loss/train': 1.1994810104370117} 08/31/2021 07:51:22 - INFO - __main__ - Step 103244: {'lr': 0.00011335252702149052, 'samples': 19822848, 'steps': 103243, 'loss/train': 1.2042994499206543} 08/31/2021 07:51:23 - INFO - __main__ - Step 103245: {'lr': 0.00011334808318224679, 'samples': 19823040, 'steps': 103244, 'loss/train': 1.3406739234924316} 08/31/2021 07:51:23 - INFO - __main__ - Step 103246: {'lr': 0.00011334363940457634, 'samples': 19823232, 'steps': 103245, 'loss/train': 1.0565332174301147} 08/31/2021 07:51:23 - INFO - __main__ - Step 103247: {'lr': 0.00011333919568848123, 'samples': 19823424, 'steps': 103246, 'loss/train': 1.1246808767318726} 08/31/2021 07:51:24 - INFO - __main__ - Step 103248: {'lr': 0.00011333475203396323, 'samples': 19823616, 'steps': 103247, 'loss/train': 1.3302104473114014} 08/31/2021 07:51:25 - INFO - __main__ - Step 103249: {'lr': 0.00011333030844102451, 'samples': 19823808, 'steps': 103248, 'loss/train': 0.3743899166584015} 08/31/2021 07:51:26 - INFO - __main__ - Step 103250: {'lr': 0.00011332586490966707, 'samples': 19824000, 'steps': 103249, 'loss/train': 0.2844642698764801} 08/31/2021 07:51:26 - INFO - __main__ - Step 103251: {'lr': 0.00011332142143989285, 'samples': 19824192, 'steps': 103250, 'loss/train': 1.1622436046600342} 08/31/2021 07:51:26 - INFO - __main__ - Step 103252: {'lr': 0.00011331697803170391, 'samples': 19824384, 'steps': 103251, 'loss/train': 0.8319507241249084} 08/31/2021 07:51:27 - INFO - __main__ - Step 103253: {'lr': 0.00011331253468510223, 'samples': 19824576, 'steps': 103252, 'loss/train': 0.3971894383430481} 08/31/2021 07:51:28 - INFO - __main__ - Step 103254: {'lr': 0.0001133080914000898, 'samples': 19824768, 'steps': 103253, 'loss/train': 0.7891254425048828} 08/31/2021 07:51:29 - INFO - __main__ - Step 103255: {'lr': 0.00011330364817666864, 'samples': 19824960, 'steps': 103254, 'loss/train': 1.4145121574401855} 08/31/2021 07:51:29 - INFO - __main__ - Step 103256: {'lr': 0.00011329920501484073, 'samples': 19825152, 'steps': 103255, 'loss/train': 1.1525882482528687} 08/31/2021 07:51:29 - INFO - __main__ - Step 103257: {'lr': 0.00011329476191460811, 'samples': 19825344, 'steps': 103256, 'loss/train': 0.9045448899269104} 08/31/2021 07:51:30 - INFO - __main__ - Step 103258: {'lr': 0.00011329031887597274, 'samples': 19825536, 'steps': 103257, 'loss/train': 1.6390411853790283} 08/31/2021 07:51:32 - INFO - __main__ - Step 103259: {'lr': 0.00011328587589893666, 'samples': 19825728, 'steps': 103258, 'loss/train': 1.3377236127853394} 08/31/2021 07:51:32 - INFO - __main__ - Step 103260: {'lr': 0.00011328143298350185, 'samples': 19825920, 'steps': 103259, 'loss/train': 1.7549407482147217} 08/31/2021 07:51:33 - INFO - __main__ - Step 103261: {'lr': 0.00011327699012967041, 'samples': 19826112, 'steps': 103260, 'loss/train': 0.127635657787323} 08/31/2021 07:51:33 - INFO - __main__ - Step 103262: {'lr': 0.00011327254733744416, 'samples': 19826304, 'steps': 103261, 'loss/train': 1.646756887435913} 08/31/2021 07:51:33 - INFO - __main__ - Step 103263: {'lr': 0.00011326810460682518, 'samples': 19826496, 'steps': 103262, 'loss/train': 1.300894021987915} 08/31/2021 07:51:35 - INFO - __main__ - Step 103264: {'lr': 0.0001132636619378155, 'samples': 19826688, 'steps': 103263, 'loss/train': 1.1824872493743896} 08/31/2021 07:51:36 - INFO - __main__ - Step 103265: {'lr': 0.0001132592193304171, 'samples': 19826880, 'steps': 103264, 'loss/train': 1.1824342012405396} 08/31/2021 07:51:36 - INFO - __main__ - Step 103266: {'lr': 0.00011325477678463198, 'samples': 19827072, 'steps': 103265, 'loss/train': 1.2468894720077515} 08/31/2021 07:51:36 - INFO - __main__ - Step 103267: {'lr': 0.00011325033430046214, 'samples': 19827264, 'steps': 103266, 'loss/train': 2.376939535140991} 08/31/2021 07:51:37 - INFO - __main__ - Step 103268: {'lr': 0.0001132458918779096, 'samples': 19827456, 'steps': 103267, 'loss/train': 0.647485077381134} 08/31/2021 07:51:37 - INFO - __main__ - Step 103269: {'lr': 0.00011324144951697634, 'samples': 19827648, 'steps': 103268, 'loss/train': 1.3475590944290161} 08/31/2021 07:51:38 - INFO - __main__ - Step 103270: {'lr': 0.00011323700721766439, 'samples': 19827840, 'steps': 103269, 'loss/train': 0.38873544335365295} 08/31/2021 07:51:39 - INFO - __main__ - Step 103271: {'lr': 0.00011323256497997572, 'samples': 19828032, 'steps': 103270, 'loss/train': 1.4918532371520996} 08/31/2021 07:51:39 - INFO - __main__ - Step 103272: {'lr': 0.00011322812280391234, 'samples': 19828224, 'steps': 103271, 'loss/train': 0.12295208871364594} 08/31/2021 07:51:40 - INFO - __main__ - Step 103273: {'lr': 0.00011322368068947627, 'samples': 19828416, 'steps': 103272, 'loss/train': 0.7548835277557373} 08/31/2021 07:51:40 - INFO - __main__ - Step 103274: {'lr': 0.0001132192386366696, 'samples': 19828608, 'steps': 103273, 'loss/train': 0.6791359782218933} 08/31/2021 07:51:42 - INFO - __main__ - Step 103275: {'lr': 0.00011321479664549414, 'samples': 19828800, 'steps': 103274, 'loss/train': 1.3943955898284912} 08/31/2021 07:51:42 - INFO - __main__ - Step 103276: {'lr': 0.00011321035471595195, 'samples': 19828992, 'steps': 103275, 'loss/train': 0.607895016670227} 08/31/2021 07:51:42 - INFO - __main__ - Step 103277: {'lr': 0.00011320591284804508, 'samples': 19829184, 'steps': 103276, 'loss/train': 1.5363948345184326} 08/31/2021 07:51:43 - INFO - __main__ - Step 103278: {'lr': 0.00011320147104177553, 'samples': 19829376, 'steps': 103277, 'loss/train': 1.1775329113006592} 08/31/2021 07:51:43 - INFO - __main__ - Step 103279: {'lr': 0.00011319702929714526, 'samples': 19829568, 'steps': 103278, 'loss/train': 0.581076443195343} 08/31/2021 07:51:44 - INFO - __main__ - Step 103280: {'lr': 0.00011319258761415632, 'samples': 19829760, 'steps': 103279, 'loss/train': 1.2765729427337646} 08/31/2021 07:51:45 - INFO - __main__ - Step 103281: {'lr': 0.00011318814599281068, 'samples': 19829952, 'steps': 103280, 'loss/train': 1.5352129936218262} 08/31/2021 07:51:45 - INFO - __main__ - Step 103282: {'lr': 0.00011318370443311036, 'samples': 19830144, 'steps': 103281, 'loss/train': 1.0290640592575073} 08/31/2021 07:51:46 - INFO - __main__ - Step 103283: {'lr': 0.00011317926293505732, 'samples': 19830336, 'steps': 103282, 'loss/train': 1.24081289768219} 08/31/2021 07:51:46 - INFO - __main__ - Step 103284: {'lr': 0.00011317482149865363, 'samples': 19830528, 'steps': 103283, 'loss/train': 1.519904375076294} 08/31/2021 07:51:48 - INFO - __main__ - Step 103285: {'lr': 0.00011317038012390124, 'samples': 19830720, 'steps': 103284, 'loss/train': 1.0478392839431763} 08/31/2021 07:51:48 - INFO - __main__ - Step 103286: {'lr': 0.00011316593881080215, 'samples': 19830912, 'steps': 103285, 'loss/train': 1.3864728212356567} 08/31/2021 07:51:48 - INFO - __main__ - Step 103287: {'lr': 0.00011316149755935839, 'samples': 19831104, 'steps': 103286, 'loss/train': 0.027226172387599945} 08/31/2021 07:51:49 - INFO - __main__ - Step 103288: {'lr': 0.00011315705636957204, 'samples': 19831296, 'steps': 103287, 'loss/train': 0.6916993856430054} 08/31/2021 07:51:49 - INFO - __main__ - Step 103289: {'lr': 0.00011315261524144491, 'samples': 19831488, 'steps': 103288, 'loss/train': 1.5533825159072876} 08/31/2021 07:51:50 - INFO - __main__ - Step 103290: {'lr': 0.00011314817417497911, 'samples': 19831680, 'steps': 103289, 'loss/train': 1.035072684288025} 08/31/2021 07:51:51 - INFO - __main__ - Step 103291: {'lr': 0.00011314373317017663, 'samples': 19831872, 'steps': 103290, 'loss/train': 0.05715174227952957} 08/31/2021 07:51:51 - INFO - __main__ - Step 103292: {'lr': 0.00011313929222703947, 'samples': 19832064, 'steps': 103291, 'loss/train': 0.9538436532020569} 08/31/2021 07:51:52 - INFO - __main__ - Step 103293: {'lr': 0.00011313485134556963, 'samples': 19832256, 'steps': 103292, 'loss/train': 1.296364426612854} 08/31/2021 07:51:52 - INFO - __main__ - Step 103294: {'lr': 0.00011313041052576911, 'samples': 19832448, 'steps': 103293, 'loss/train': 1.0006338357925415} 08/31/2021 07:51:52 - INFO - __main__ - Step 103295: {'lr': 0.00011312596976763991, 'samples': 19832640, 'steps': 103294, 'loss/train': 0.1645939201116562} 08/31/2021 07:51:54 - INFO - __main__ - Step 103296: {'lr': 0.00011312152907118406, 'samples': 19832832, 'steps': 103295, 'loss/train': 1.1010971069335938} 08/31/2021 07:51:54 - INFO - __main__ - Step 103297: {'lr': 0.00011311708843640353, 'samples': 19833024, 'steps': 103296, 'loss/train': 1.2612013816833496} 08/31/2021 07:51:55 - INFO - __main__ - Step 103298: {'lr': 0.00011311264786330033, 'samples': 19833216, 'steps': 103297, 'loss/train': 0.8912965655326843} 08/31/2021 07:51:55 - INFO - __main__ - Step 103299: {'lr': 0.00011310820735187643, 'samples': 19833408, 'steps': 103298, 'loss/train': 1.5425695180892944} 08/31/2021 07:51:56 - INFO - __main__ - Step 103300: {'lr': 0.0001131037669021339, 'samples': 19833600, 'steps': 103299, 'loss/train': 0.6251587271690369} 08/31/2021 07:51:57 - INFO - __main__ - Step 103301: {'lr': 0.00011309932651407475, 'samples': 19833792, 'steps': 103300, 'loss/train': 1.957216501235962} 08/31/2021 07:51:57 - INFO - __main__ - Step 103302: {'lr': 0.00011309488618770086, 'samples': 19833984, 'steps': 103301, 'loss/train': 0.5670649409294128} 08/31/2021 07:51:58 - INFO - __main__ - Step 103303: {'lr': 0.00011309044592301432, 'samples': 19834176, 'steps': 103302, 'loss/train': 2.8463327884674072} 08/31/2021 07:51:58 - INFO - __main__ - Step 103304: {'lr': 0.00011308600572001709, 'samples': 19834368, 'steps': 103303, 'loss/train': 1.0817015171051025} 08/31/2021 07:51:59 - INFO - __main__ - Step 103305: {'lr': 0.00011308156557871118, 'samples': 19834560, 'steps': 103304, 'loss/train': 0.9797886610031128} 08/31/2021 07:52:00 - INFO - __main__ - Step 103306: {'lr': 0.00011307712549909865, 'samples': 19834752, 'steps': 103305, 'loss/train': 1.4255030155181885} 08/31/2021 07:52:00 - INFO - __main__ - Step 103307: {'lr': 0.00011307268548118141, 'samples': 19834944, 'steps': 103306, 'loss/train': 1.102942943572998} 08/31/2021 07:52:01 - INFO - __main__ - Step 103308: {'lr': 0.00011306824552496154, 'samples': 19835136, 'steps': 103307, 'loss/train': 1.570037841796875} 08/31/2021 07:52:01 - INFO - __main__ - Step 103309: {'lr': 0.00011306380563044096, 'samples': 19835328, 'steps': 103308, 'loss/train': 1.3100268840789795} 08/31/2021 07:52:01 - INFO - __main__ - Step 103310: {'lr': 0.00011305936579762174, 'samples': 19835520, 'steps': 103309, 'loss/train': 1.5149327516555786} 08/31/2021 07:52:04 - INFO - __main__ - Step 103311: {'lr': 0.00011305492602650589, 'samples': 19835712, 'steps': 103310, 'loss/train': 0.5023385286331177} 08/31/2021 07:52:04 - INFO - __main__ - Step 103312: {'lr': 0.00011305048631709533, 'samples': 19835904, 'steps': 103311, 'loss/train': 1.4421119689941406} 08/31/2021 07:52:05 - INFO - __main__ - Step 103313: {'lr': 0.00011304604666939213, 'samples': 19836096, 'steps': 103312, 'loss/train': 1.844990611076355} 08/31/2021 07:52:05 - INFO - __main__ - Step 103314: {'lr': 0.00011304160708339825, 'samples': 19836288, 'steps': 103313, 'loss/train': 1.3610025644302368} 08/31/2021 07:52:05 - INFO - __main__ - Step 103315: {'lr': 0.00011303716755911583, 'samples': 19836480, 'steps': 103314, 'loss/train': 1.028191328048706} 08/31/2021 07:52:06 - INFO - __main__ - Step 103316: {'lr': 0.00011303272809654663, 'samples': 19836672, 'steps': 103315, 'loss/train': 0.9596469402313232} 08/31/2021 07:52:07 - INFO - __main__ - Step 103317: {'lr': 0.00011302828869569279, 'samples': 19836864, 'steps': 103316, 'loss/train': 1.0387526750564575} 08/31/2021 07:52:08 - INFO - __main__ - Step 103318: {'lr': 0.00011302384935655627, 'samples': 19837056, 'steps': 103317, 'loss/train': 1.0284879207611084} 08/31/2021 07:52:08 - INFO - __main__ - Step 103319: {'lr': 0.0001130194100791391, 'samples': 19837248, 'steps': 103318, 'loss/train': 1.2586909532546997} 08/31/2021 07:52:08 - INFO - __main__ - Step 103320: {'lr': 0.00011301497086344325, 'samples': 19837440, 'steps': 103319, 'loss/train': 0.6280498504638672} 08/31/2021 07:52:09 - INFO - __main__ - Step 103321: {'lr': 0.00011301053170947078, 'samples': 19837632, 'steps': 103320, 'loss/train': 1.40207839012146} 08/31/2021 07:52:10 - INFO - __main__ - Step 103322: {'lr': 0.00011300609261722363, 'samples': 19837824, 'steps': 103321, 'loss/train': 0.04173928499221802} 08/31/2021 07:52:11 - INFO - __main__ - Step 103323: {'lr': 0.00011300165358670381, 'samples': 19838016, 'steps': 103322, 'loss/train': 1.0249675512313843} 08/31/2021 07:52:11 - INFO - __main__ - Step 103324: {'lr': 0.00011299721461791334, 'samples': 19838208, 'steps': 103323, 'loss/train': 1.1685822010040283} 08/31/2021 07:52:11 - INFO - __main__ - Step 103325: {'lr': 0.00011299277571085423, 'samples': 19838400, 'steps': 103324, 'loss/train': 1.2596633434295654} 08/31/2021 07:52:12 - INFO - __main__ - Step 103326: {'lr': 0.00011298833686552843, 'samples': 19838592, 'steps': 103325, 'loss/train': 0.629024088382721} 08/31/2021 07:52:13 - INFO - __main__ - Step 103327: {'lr': 0.00011298389808193798, 'samples': 19838784, 'steps': 103326, 'loss/train': 1.2018506526947021} 08/31/2021 07:52:14 - INFO - __main__ - Step 103328: {'lr': 0.00011297945936008497, 'samples': 19838976, 'steps': 103327, 'loss/train': 1.0861839056015015} 08/31/2021 07:52:14 - INFO - __main__ - Step 103329: {'lr': 0.0001129750206999712, 'samples': 19839168, 'steps': 103328, 'loss/train': 1.1125026941299438} 08/31/2021 07:52:15 - INFO - __main__ - Step 103330: {'lr': 0.00011297058210159877, 'samples': 19839360, 'steps': 103329, 'loss/train': 1.9269264936447144} 08/31/2021 07:52:15 - INFO - __main__ - Step 103331: {'lr': 0.0001129661435649697, 'samples': 19839552, 'steps': 103330, 'loss/train': 1.6095908880233765} 08/31/2021 07:52:15 - INFO - __main__ - Step 103332: {'lr': 0.00011296170509008596, 'samples': 19839744, 'steps': 103331, 'loss/train': 1.4186441898345947} 08/31/2021 07:52:17 - INFO - __main__ - Step 103333: {'lr': 0.00011295726667694955, 'samples': 19839936, 'steps': 103332, 'loss/train': 0.42496541142463684} 08/31/2021 07:52:17 - INFO - __main__ - Step 103334: {'lr': 0.0001129528283255625, 'samples': 19840128, 'steps': 103333, 'loss/train': 0.1415705531835556} 08/31/2021 07:52:18 - INFO - __main__ - Step 103335: {'lr': 0.0001129483900359268, 'samples': 19840320, 'steps': 103334, 'loss/train': 1.6920970678329468} 08/31/2021 07:52:18 - INFO - __main__ - Step 103336: {'lr': 0.00011294395180804443, 'samples': 19840512, 'steps': 103335, 'loss/train': 1.882409691810608} 08/31/2021 07:52:18 - INFO - __main__ - Step 103337: {'lr': 0.00011293951364191738, 'samples': 19840704, 'steps': 103336, 'loss/train': 0.6240132451057434} 08/31/2021 07:52:20 - INFO - __main__ - Step 103338: {'lr': 0.00011293507553754767, 'samples': 19840896, 'steps': 103337, 'loss/train': 1.0723743438720703} 08/31/2021 07:52:20 - INFO - __main__ - Step 103339: {'lr': 0.00011293063749493731, 'samples': 19841088, 'steps': 103338, 'loss/train': 0.6302104592323303} 08/31/2021 07:52:20 - INFO - __main__ - Step 103340: {'lr': 0.00011292619951408831, 'samples': 19841280, 'steps': 103339, 'loss/train': 1.2803232669830322} 08/31/2021 07:52:21 - INFO - __main__ - Step 103341: {'lr': 0.00011292176159500272, 'samples': 19841472, 'steps': 103340, 'loss/train': 1.1234123706817627} 08/31/2021 07:52:21 - INFO - __main__ - Step 103342: {'lr': 0.00011291732373768238, 'samples': 19841664, 'steps': 103341, 'loss/train': 0.840133786201477} 08/31/2021 07:52:23 - INFO - __main__ - Step 103343: {'lr': 0.0001129128859421294, 'samples': 19841856, 'steps': 103342, 'loss/train': 0.11441129446029663} 08/31/2021 07:52:23 - INFO - __main__ - Step 103344: {'lr': 0.00011290844820834572, 'samples': 19842048, 'steps': 103343, 'loss/train': 1.5401997566223145} 08/31/2021 07:52:23 - INFO - __main__ - Step 103345: {'lr': 0.00011290401053633339, 'samples': 19842240, 'steps': 103344, 'loss/train': 1.5007858276367188} 08/31/2021 07:52:24 - INFO - __main__ - Step 103346: {'lr': 0.00011289957292609443, 'samples': 19842432, 'steps': 103345, 'loss/train': 0.970757007598877} 08/31/2021 07:52:24 - INFO - __main__ - Step 103347: {'lr': 0.00011289513537763077, 'samples': 19842624, 'steps': 103346, 'loss/train': 0.9142011404037476} 08/31/2021 07:52:25 - INFO - __main__ - Step 103348: {'lr': 0.00011289069789094444, 'samples': 19842816, 'steps': 103347, 'loss/train': 0.9987598061561584} 08/31/2021 07:52:26 - INFO - __main__ - Step 103349: {'lr': 0.00011288626046603748, 'samples': 19843008, 'steps': 103348, 'loss/train': 0.9994597434997559} 08/31/2021 07:52:27 - INFO - __main__ - Step 103350: {'lr': 0.00011288182310291184, 'samples': 19843200, 'steps': 103349, 'loss/train': 0.053763508796691895} 08/31/2021 07:52:27 - INFO - __main__ - Step 103351: {'lr': 0.00011287738580156953, 'samples': 19843392, 'steps': 103350, 'loss/train': 1.2006425857543945} 08/31/2021 07:52:28 - INFO - __main__ - Step 103352: {'lr': 0.00011287294856201255, 'samples': 19843584, 'steps': 103351, 'loss/train': 0.6540609002113342} 08/31/2021 07:52:28 - INFO - __main__ - Step 103353: {'lr': 0.00011286851138424293, 'samples': 19843776, 'steps': 103352, 'loss/train': 1.0734355449676514} 08/31/2021 07:52:30 - INFO - __main__ - Step 103354: {'lr': 0.00011286407426826262, 'samples': 19843968, 'steps': 103353, 'loss/train': 0.04022965580224991} 08/31/2021 07:52:30 - INFO - __main__ - Step 103355: {'lr': 0.00011285963721407371, 'samples': 19844160, 'steps': 103354, 'loss/train': 1.5757509469985962} 08/31/2021 07:52:31 - INFO - __main__ - Step 103356: {'lr': 0.00011285520022167808, 'samples': 19844352, 'steps': 103355, 'loss/train': 0.4900566339492798} 08/31/2021 07:52:31 - INFO - __main__ - Step 103357: {'lr': 0.00011285076329107777, 'samples': 19844544, 'steps': 103356, 'loss/train': 0.8250307440757751} 08/31/2021 07:52:31 - INFO - __main__ - Step 103358: {'lr': 0.0001128463264222748, 'samples': 19844736, 'steps': 103357, 'loss/train': 0.256268709897995} 08/31/2021 07:52:32 - INFO - __main__ - Step 103359: {'lr': 0.00011284188961527114, 'samples': 19844928, 'steps': 103358, 'loss/train': 0.03803873062133789} 08/31/2021 07:52:33 - INFO - __main__ - Step 103360: {'lr': 0.0001128374528700688, 'samples': 19845120, 'steps': 103359, 'loss/train': 0.04554343223571777} 08/31/2021 07:52:34 - INFO - __main__ - Step 103361: {'lr': 0.0001128330161866698, 'samples': 19845312, 'steps': 103360, 'loss/train': 0.9826399087905884} 08/31/2021 07:52:34 - INFO - __main__ - Step 103362: {'lr': 0.00011282857956507615, 'samples': 19845504, 'steps': 103361, 'loss/train': 1.364778995513916} 08/31/2021 07:52:34 - INFO - __main__ - Step 103363: {'lr': 0.00011282414300528978, 'samples': 19845696, 'steps': 103362, 'loss/train': 1.341951847076416} 08/31/2021 07:52:35 - INFO - __main__ - Step 103364: {'lr': 0.00011281970650731277, 'samples': 19845888, 'steps': 103363, 'loss/train': 1.6193574666976929} 08/31/2021 07:52:37 - INFO - __main__ - Step 103365: {'lr': 0.00011281527007114706, 'samples': 19846080, 'steps': 103364, 'loss/train': 1.5072367191314697} 08/31/2021 07:52:37 - INFO - __main__ - Step 103366: {'lr': 0.00011281083369679468, 'samples': 19846272, 'steps': 103365, 'loss/train': 0.586295485496521} 08/31/2021 07:52:38 - INFO - __main__ - Step 103367: {'lr': 0.00011280639738425762, 'samples': 19846464, 'steps': 103366, 'loss/train': 1.1396125555038452} 08/31/2021 07:52:38 - INFO - __main__ - Step 103368: {'lr': 0.000112801961133538, 'samples': 19846656, 'steps': 103367, 'loss/train': 0.864645779132843} 08/31/2021 07:52:38 - INFO - __main__ - Step 103369: {'lr': 0.00011279752494463757, 'samples': 19846848, 'steps': 103368, 'loss/train': 1.3883990049362183} 08/31/2021 07:52:40 - INFO - __main__ - Step 103370: {'lr': 0.00011279308881755845, 'samples': 19847040, 'steps': 103369, 'loss/train': 0.8525276184082031} 08/31/2021 07:52:40 - INFO - __main__ - Step 103371: {'lr': 0.00011278865275230268, 'samples': 19847232, 'steps': 103370, 'loss/train': 1.2397868633270264} 08/31/2021 07:52:41 - INFO - __main__ - Step 103372: {'lr': 0.00011278421674887221, 'samples': 19847424, 'steps': 103371, 'loss/train': 1.167093276977539} 08/31/2021 07:52:41 - INFO - __main__ - Step 103373: {'lr': 0.00011277978080726906, 'samples': 19847616, 'steps': 103372, 'loss/train': 0.9305601119995117} 08/31/2021 07:52:41 - INFO - __main__ - Step 103374: {'lr': 0.00011277534492749522, 'samples': 19847808, 'steps': 103373, 'loss/train': 0.8697303533554077} 08/31/2021 07:52:43 - INFO - __main__ - Step 103375: {'lr': 0.0001127709091095527, 'samples': 19848000, 'steps': 103374, 'loss/train': 0.136363223195076} 08/31/2021 07:52:43 - INFO - __main__ - Step 103376: {'lr': 0.00011276647335344348, 'samples': 19848192, 'steps': 103375, 'loss/train': 1.2025279998779297} 08/31/2021 07:52:44 - INFO - __main__ - Step 103377: {'lr': 0.0001127620376591696, 'samples': 19848384, 'steps': 103376, 'loss/train': 0.6873274445533752} 08/31/2021 07:52:44 - INFO - __main__ - Step 103378: {'lr': 0.000112757602026733, 'samples': 19848576, 'steps': 103377, 'loss/train': 0.050203803926706314} 08/31/2021 07:52:44 - INFO - __main__ - Step 103379: {'lr': 0.00011275316645613571, 'samples': 19848768, 'steps': 103378, 'loss/train': 0.9851334095001221} 08/31/2021 07:52:45 - INFO - __main__ - Step 103380: {'lr': 0.0001127487309473797, 'samples': 19848960, 'steps': 103379, 'loss/train': 1.9023194313049316} 08/31/2021 07:52:47 - INFO - __main__ - Step 103381: {'lr': 0.00011274429550046702, 'samples': 19849152, 'steps': 103380, 'loss/train': 1.1106367111206055} 08/31/2021 07:52:47 - INFO - __main__ - Step 103382: {'lr': 0.00011273986011539974, 'samples': 19849344, 'steps': 103381, 'loss/train': 1.467158317565918} 08/31/2021 07:52:48 - INFO - __main__ - Step 103383: {'lr': 0.00011273542479217966, 'samples': 19849536, 'steps': 103382, 'loss/train': 1.5888367891311646} 08/31/2021 07:52:48 - INFO - __main__ - Step 103384: {'lr': 0.00011273098953080887, 'samples': 19849728, 'steps': 103383, 'loss/train': 0.3181135356426239} 08/31/2021 07:52:48 - INFO - __main__ - Step 103385: {'lr': 0.0001127265543312894, 'samples': 19849920, 'steps': 103384, 'loss/train': 0.6971626877784729} 08/31/2021 07:52:50 - INFO - __main__ - Step 103386: {'lr': 0.00011272211919362322, 'samples': 19850112, 'steps': 103385, 'loss/train': 1.4617596864700317} 08/31/2021 07:52:51 - INFO - __main__ - Step 103387: {'lr': 0.00011271768411781232, 'samples': 19850304, 'steps': 103386, 'loss/train': 1.1249661445617676} 08/31/2021 07:52:51 - INFO - __main__ - Step 103388: {'lr': 0.00011271324910385875, 'samples': 19850496, 'steps': 103387, 'loss/train': 2.114011526107788} 08/31/2021 07:52:51 - INFO - __main__ - Step 103389: {'lr': 0.00011270881415176443, 'samples': 19850688, 'steps': 103388, 'loss/train': 1.0633143186569214} 08/31/2021 07:52:52 - INFO - __main__ - Step 103390: {'lr': 0.0001127043792615314, 'samples': 19850880, 'steps': 103389, 'loss/train': 1.2579782009124756} 08/31/2021 07:52:52 - INFO - __main__ - Step 103391: {'lr': 0.0001126999444331617, 'samples': 19851072, 'steps': 103390, 'loss/train': 0.4753819406032562} 08/31/2021 07:52:53 - INFO - __main__ - Step 103392: {'lr': 0.00011269550966665726, 'samples': 19851264, 'steps': 103391, 'loss/train': 1.9134471416473389} 08/31/2021 07:52:54 - INFO - __main__ - Step 103393: {'lr': 0.00011269107496202008, 'samples': 19851456, 'steps': 103392, 'loss/train': 1.2830312252044678} 08/31/2021 07:52:54 - INFO - __main__ - Step 103394: {'lr': 0.00011268664031925221, 'samples': 19851648, 'steps': 103393, 'loss/train': 1.0495551824569702} 08/31/2021 07:52:55 - INFO - __main__ - Step 103395: {'lr': 0.00011268220573835572, 'samples': 19851840, 'steps': 103394, 'loss/train': 1.6671051979064941} 08/31/2021 07:52:55 - INFO - __main__ - Step 103396: {'lr': 0.00011267777121933239, 'samples': 19852032, 'steps': 103395, 'loss/train': 1.6772464513778687} 08/31/2021 07:52:57 - INFO - __main__ - Step 103397: {'lr': 0.00011267333676218437, 'samples': 19852224, 'steps': 103396, 'loss/train': 1.1561633348464966} 08/31/2021 07:52:57 - INFO - __main__ - Step 103398: {'lr': 0.0001126689023669136, 'samples': 19852416, 'steps': 103397, 'loss/train': 1.6642276048660278} 08/31/2021 07:52:57 - INFO - __main__ - Step 103399: {'lr': 0.00011266446803352213, 'samples': 19852608, 'steps': 103398, 'loss/train': 1.9387798309326172} 08/31/2021 07:52:58 - INFO - __main__ - Step 103400: {'lr': 0.0001126600337620119, 'samples': 19852800, 'steps': 103399, 'loss/train': 1.3376514911651611} 08/31/2021 07:52:58 - INFO - __main__ - Step 103401: {'lr': 0.00011265559955238496, 'samples': 19852992, 'steps': 103400, 'loss/train': 1.5332553386688232} 08/31/2021 07:53:00 - INFO - __main__ - Step 103402: {'lr': 0.00011265116540464329, 'samples': 19853184, 'steps': 103401, 'loss/train': 1.3881964683532715} 08/31/2021 07:53:00 - INFO - __main__ - Step 103403: {'lr': 0.00011264673131878886, 'samples': 19853376, 'steps': 103402, 'loss/train': 1.2745797634124756} 08/31/2021 07:53:01 - INFO - __main__ - Step 103404: {'lr': 0.00011264229729482372, 'samples': 19853568, 'steps': 103403, 'loss/train': 0.7641554474830627} 08/31/2021 07:53:01 - INFO - __main__ - Step 103405: {'lr': 0.00011263786333274984, 'samples': 19853760, 'steps': 103404, 'loss/train': 1.432836890220642} 08/31/2021 07:53:01 - INFO - __main__ - Step 103406: {'lr': 0.0001126334294325692, 'samples': 19853952, 'steps': 103405, 'loss/train': 1.3425456285476685} 08/31/2021 07:53:03 - INFO - __main__ - Step 103407: {'lr': 0.00011262899559428383, 'samples': 19854144, 'steps': 103406, 'loss/train': 0.6257226467132568} 08/31/2021 07:53:04 - INFO - __main__ - Step 103408: {'lr': 0.00011262456181789571, 'samples': 19854336, 'steps': 103407, 'loss/train': 1.1177059412002563} 08/31/2021 07:53:04 - INFO - __main__ - Step 103409: {'lr': 0.00011262012810340694, 'samples': 19854528, 'steps': 103408, 'loss/train': 0.472185879945755} 08/31/2021 07:53:04 - INFO - __main__ - Step 103410: {'lr': 0.00011261569445081932, 'samples': 19854720, 'steps': 103409, 'loss/train': 1.1441658735275269} 08/31/2021 07:53:05 - INFO - __main__ - Step 103411: {'lr': 0.00011261126086013496, 'samples': 19854912, 'steps': 103410, 'loss/train': 1.0588301420211792} 08/31/2021 07:53:05 - INFO - __main__ - Step 103412: {'lr': 0.00011260682733135582, 'samples': 19855104, 'steps': 103411, 'loss/train': 0.7075667977333069} 08/31/2021 07:53:06 - INFO - __main__ - Step 103413: {'lr': 0.00011260239386448396, 'samples': 19855296, 'steps': 103412, 'loss/train': 1.7873399257659912} 08/31/2021 07:53:07 - INFO - __main__ - Step 103414: {'lr': 0.00011259796045952134, 'samples': 19855488, 'steps': 103413, 'loss/train': 1.7878203392028809} 08/31/2021 07:53:08 - INFO - __main__ - Step 103415: {'lr': 0.00011259352711646992, 'samples': 19855680, 'steps': 103414, 'loss/train': 1.164563775062561} 08/31/2021 07:53:08 - INFO - __main__ - Step 103416: {'lr': 0.00011258909383533177, 'samples': 19855872, 'steps': 103415, 'loss/train': 1.1523995399475098} 08/31/2021 07:53:08 - INFO - __main__ - Step 103417: {'lr': 0.00011258466061610883, 'samples': 19856064, 'steps': 103416, 'loss/train': 0.9999387264251709} 08/31/2021 07:53:09 - INFO - __main__ - Step 103418: {'lr': 0.00011258022745880315, 'samples': 19856256, 'steps': 103417, 'loss/train': 0.42262914776802063} 08/31/2021 07:53:09 - INFO - __main__ - Step 103419: {'lr': 0.00011257579436341666, 'samples': 19856448, 'steps': 103418, 'loss/train': 1.1383755207061768} 08/31/2021 07:53:11 - INFO - __main__ - Step 103420: {'lr': 0.00011257136132995144, 'samples': 19856640, 'steps': 103419, 'loss/train': 1.7157148122787476} 08/31/2021 07:53:12 - INFO - __main__ - Step 103421: {'lr': 0.00011256692835840943, 'samples': 19856832, 'steps': 103420, 'loss/train': 1.5713883638381958} 08/31/2021 07:53:12 - INFO - __main__ - Step 103422: {'lr': 0.00011256249544879271, 'samples': 19857024, 'steps': 103421, 'loss/train': 0.6687493920326233} 08/31/2021 07:53:13 - INFO - __main__ - Step 103423: {'lr': 0.00011255806260110315, 'samples': 19857216, 'steps': 103422, 'loss/train': 1.776906967163086} 08/31/2021 07:53:13 - INFO - __main__ - Step 103424: {'lr': 0.00011255362981534279, 'samples': 19857408, 'steps': 103423, 'loss/train': 1.3741000890731812} 08/31/2021 07:53:15 - INFO - __main__ - Step 103425: {'lr': 0.00011254919709151365, 'samples': 19857600, 'steps': 103424, 'loss/train': 1.448397159576416} 08/31/2021 07:53:15 - INFO - __main__ - Step 103426: {'lr': 0.0001125447644296177, 'samples': 19857792, 'steps': 103425, 'loss/train': 1.326753854751587} 08/31/2021 07:53:15 - INFO - __main__ - Step 103427: {'lr': 0.00011254033182965698, 'samples': 19857984, 'steps': 103426, 'loss/train': 1.3236416578292847} 08/31/2021 07:53:16 - INFO - __main__ - Step 103428: {'lr': 0.00011253589929163346, 'samples': 19858176, 'steps': 103427, 'loss/train': 0.6573923230171204} 08/31/2021 07:53:16 - INFO - __main__ - Step 103429: {'lr': 0.00011253146681554913, 'samples': 19858368, 'steps': 103428, 'loss/train': 1.1211411952972412} 08/31/2021 07:53:17 - INFO - __main__ - Step 103430: {'lr': 0.00011252703440140602, 'samples': 19858560, 'steps': 103429, 'loss/train': 1.6497682332992554} 08/31/2021 07:53:18 - INFO - __main__ - Step 103431: {'lr': 0.00011252260204920608, 'samples': 19858752, 'steps': 103430, 'loss/train': 0.17520536482334137} 08/31/2021 07:53:19 - INFO - __main__ - Step 103432: {'lr': 0.00011251816975895137, 'samples': 19858944, 'steps': 103431, 'loss/train': 1.3719180822372437} 08/31/2021 07:53:19 - INFO - __main__ - Step 103433: {'lr': 0.00011251373753064384, 'samples': 19859136, 'steps': 103432, 'loss/train': 1.500784158706665} 08/31/2021 07:53:19 - INFO - __main__ - Step 103434: {'lr': 0.00011250930536428547, 'samples': 19859328, 'steps': 103433, 'loss/train': 0.8592292666435242} 08/31/2021 07:53:20 - INFO - __main__ - Step 103435: {'lr': 0.00011250487325987831, 'samples': 19859520, 'steps': 103434, 'loss/train': 0.9007093906402588} 08/31/2021 07:53:21 - INFO - __main__ - Step 103436: {'lr': 0.00011250044121742442, 'samples': 19859712, 'steps': 103435, 'loss/train': 1.3107861280441284} 08/31/2021 07:53:21 - INFO - __main__ - Step 103437: {'lr': 0.00011249600923692562, 'samples': 19859904, 'steps': 103436, 'loss/train': 1.1389484405517578} 08/31/2021 07:53:22 - INFO - __main__ - Step 103438: {'lr': 0.000112491577318384, 'samples': 19860096, 'steps': 103437, 'loss/train': 1.340753197669983} 08/31/2021 07:53:22 - INFO - __main__ - Step 103439: {'lr': 0.00011248714546180155, 'samples': 19860288, 'steps': 103438, 'loss/train': 0.632353663444519} 08/31/2021 07:53:23 - INFO - __main__ - Step 103440: {'lr': 0.00011248271366718027, 'samples': 19860480, 'steps': 103439, 'loss/train': 1.3603163957595825} 08/31/2021 07:53:24 - INFO - __main__ - Step 103441: {'lr': 0.00011247828193452215, 'samples': 19860672, 'steps': 103440, 'loss/train': 0.6148167848587036} 08/31/2021 07:53:25 - INFO - __main__ - Step 103442: {'lr': 0.0001124738502638292, 'samples': 19860864, 'steps': 103441, 'loss/train': 1.1706960201263428} 08/31/2021 07:53:25 - INFO - __main__ - Step 103443: {'lr': 0.0001124694186551034, 'samples': 19861056, 'steps': 103442, 'loss/train': 0.11119561642408371} 08/31/2021 07:53:26 - INFO - __main__ - Step 103444: {'lr': 0.00011246498710834679, 'samples': 19861248, 'steps': 103443, 'loss/train': 0.05405803024768829} 08/31/2021 07:53:26 - INFO - __main__ - Step 103445: {'lr': 0.00011246055562356131, 'samples': 19861440, 'steps': 103444, 'loss/train': 1.5297960042953491} 08/31/2021 07:53:26 - INFO - __main__ - Step 103446: {'lr': 0.00011245612420074896, 'samples': 19861632, 'steps': 103445, 'loss/train': 1.0510838031768799} 08/31/2021 07:53:28 - INFO - __main__ - Step 103447: {'lr': 0.0001124516928399118, 'samples': 19861824, 'steps': 103446, 'loss/train': 1.2411441802978516} 08/31/2021 07:53:28 - INFO - __main__ - Step 103448: {'lr': 0.00011244726154105179, 'samples': 19862016, 'steps': 103447, 'loss/train': 0.4976387023925781} 08/31/2021 07:53:29 - INFO - __main__ - Step 103449: {'lr': 0.00011244283030417096, 'samples': 19862208, 'steps': 103448, 'loss/train': 0.7446251511573792} 08/31/2021 07:53:29 - INFO - __main__ - Step 103450: {'lr': 0.00011243839912927123, 'samples': 19862400, 'steps': 103449, 'loss/train': 0.9682085514068604} 08/31/2021 07:53:29 - INFO - __main__ - Step 103451: {'lr': 0.00011243396801635461, 'samples': 19862592, 'steps': 103450, 'loss/train': 0.9303199052810669} 08/31/2021 07:53:31 - INFO - __main__ - Step 103452: {'lr': 0.0001124295369654231, 'samples': 19862784, 'steps': 103451, 'loss/train': 0.892289936542511} 08/31/2021 07:53:31 - INFO - __main__ - Step 103453: {'lr': 0.00011242510597647875, 'samples': 19862976, 'steps': 103452, 'loss/train': 1.4416918754577637} 08/31/2021 07:53:32 - INFO - __main__ - Step 103454: {'lr': 0.00011242067504952352, 'samples': 19863168, 'steps': 103453, 'loss/train': 1.197341799736023} 08/31/2021 07:53:32 - INFO - __main__ - Step 103455: {'lr': 0.0001124162441845594, 'samples': 19863360, 'steps': 103454, 'loss/train': 1.417234182357788} 08/31/2021 07:53:32 - INFO - __main__ - Step 103456: {'lr': 0.0001124118133815884, 'samples': 19863552, 'steps': 103455, 'loss/train': 1.500541090965271} 08/31/2021 07:53:34 - INFO - __main__ - Step 103457: {'lr': 0.00011240738264061251, 'samples': 19863744, 'steps': 103456, 'loss/train': 0.04522736370563507} 08/31/2021 07:53:34 - INFO - __main__ - Step 103458: {'lr': 0.00011240295196163375, 'samples': 19863936, 'steps': 103457, 'loss/train': 1.4323779344558716} 08/31/2021 07:53:35 - INFO - __main__ - Step 103459: {'lr': 0.00011239852134465408, 'samples': 19864128, 'steps': 103458, 'loss/train': 1.2001254558563232} 08/31/2021 07:53:35 - INFO - __main__ - Step 103460: {'lr': 0.00011239409078967552, 'samples': 19864320, 'steps': 103459, 'loss/train': 0.5921819806098938} 08/31/2021 07:53:35 - INFO - __main__ - Step 103461: {'lr': 0.00011238966029670014, 'samples': 19864512, 'steps': 103460, 'loss/train': 0.09733568131923676} 08/31/2021 07:53:36 - INFO - __main__ - Step 103462: {'lr': 0.00011238522986572977, 'samples': 19864704, 'steps': 103461, 'loss/train': 1.188731074333191} 08/31/2021 07:53:37 - INFO - __main__ - Step 103463: {'lr': 0.0001123807994967665, 'samples': 19864896, 'steps': 103462, 'loss/train': 1.2730928659439087} 08/31/2021 07:53:38 - INFO - __main__ - Step 103464: {'lr': 0.00011237636918981232, 'samples': 19865088, 'steps': 103463, 'loss/train': 0.9069377183914185} 08/31/2021 07:53:38 - INFO - __main__ - Step 103465: {'lr': 0.00011237193894486919, 'samples': 19865280, 'steps': 103464, 'loss/train': 0.2709962725639343} 08/31/2021 07:53:38 - INFO - __main__ - Step 103466: {'lr': 0.00011236750876193918, 'samples': 19865472, 'steps': 103465, 'loss/train': 1.1195248365402222} 08/31/2021 07:53:39 - INFO - __main__ - Step 103467: {'lr': 0.00011236307864102424, 'samples': 19865664, 'steps': 103466, 'loss/train': 0.9639461040496826} 08/31/2021 07:53:40 - INFO - __main__ - Step 103468: {'lr': 0.00011235864858212636, 'samples': 19865856, 'steps': 103467, 'loss/train': 1.23145592212677} 08/31/2021 07:53:41 - INFO - __main__ - Step 103469: {'lr': 0.00011235421858524755, 'samples': 19866048, 'steps': 103468, 'loss/train': 1.0897510051727295} 08/31/2021 07:53:41 - INFO - __main__ - Step 103470: {'lr': 0.0001123497886503898, 'samples': 19866240, 'steps': 103469, 'loss/train': 0.49050572514533997} 08/31/2021 07:53:41 - INFO - __main__ - Step 103471: {'lr': 0.00011234535877755515, 'samples': 19866432, 'steps': 103470, 'loss/train': 0.21475686132907867} 08/31/2021 07:53:42 - INFO - __main__ - Step 103472: {'lr': 0.00011234092896674561, 'samples': 19866624, 'steps': 103471, 'loss/train': 0.9112575650215149} 08/31/2021 07:53:43 - INFO - __main__ - Step 103473: {'lr': 0.00011233649921796305, 'samples': 19866816, 'steps': 103472, 'loss/train': 1.370247483253479} 08/31/2021 07:53:44 - INFO - __main__ - Step 103474: {'lr': 0.0001123320695312095, 'samples': 19867008, 'steps': 103473, 'loss/train': 1.4191771745681763} 08/31/2021 07:53:44 - INFO - __main__ - Step 103475: {'lr': 0.00011232763990648704, 'samples': 19867200, 'steps': 103474, 'loss/train': 1.7544511556625366} 08/31/2021 07:53:44 - INFO - __main__ - Step 103476: {'lr': 0.00011232321034379761, 'samples': 19867392, 'steps': 103475, 'loss/train': 1.4774221181869507} 08/31/2021 07:53:45 - INFO - __main__ - Step 103477: {'lr': 0.0001123187808431432, 'samples': 19867584, 'steps': 103476, 'loss/train': 1.2517914772033691} 08/31/2021 07:53:47 - INFO - __main__ - Step 103478: {'lr': 0.00011231435140452583, 'samples': 19867776, 'steps': 103477, 'loss/train': 1.0452029705047607} 08/31/2021 07:53:47 - INFO - __main__ - Step 103479: {'lr': 0.00011230992202794752, 'samples': 19867968, 'steps': 103478, 'loss/train': 1.24252450466156} 08/31/2021 07:53:48 - INFO - __main__ - Step 103480: {'lr': 0.0001123054927134102, 'samples': 19868160, 'steps': 103479, 'loss/train': 0.9056673645973206} 08/31/2021 07:53:48 - INFO - __main__ - Step 103481: {'lr': 0.00011230106346091589, 'samples': 19868352, 'steps': 103480, 'loss/train': 1.0912528038024902} 08/31/2021 07:53:48 - INFO - __main__ - Step 103482: {'lr': 0.00011229663427046663, 'samples': 19868544, 'steps': 103481, 'loss/train': 0.9879567623138428} 08/31/2021 07:53:50 - INFO - __main__ - Step 103483: {'lr': 0.00011229220514206446, 'samples': 19868736, 'steps': 103482, 'loss/train': 1.173966884613037} 08/31/2021 07:53:51 - INFO - __main__ - Step 103484: {'lr': 0.0001122877760757112, 'samples': 19868928, 'steps': 103483, 'loss/train': 1.2679705619812012} 08/31/2021 07:53:51 - INFO - __main__ - Step 103485: {'lr': 0.00011228334707140898, 'samples': 19869120, 'steps': 103484, 'loss/train': 0.7860333919525146} 08/31/2021 07:53:51 - INFO - __main__ - Step 103486: {'lr': 0.00011227891812915969, 'samples': 19869312, 'steps': 103485, 'loss/train': 1.1125569343566895} 08/31/2021 07:53:52 - INFO - __main__ - Step 103487: {'lr': 0.00011227448924896544, 'samples': 19869504, 'steps': 103486, 'loss/train': 1.6019318103790283} 08/31/2021 07:53:53 - INFO - __main__ - Step 103488: {'lr': 0.00011227006043082818, 'samples': 19869696, 'steps': 103487, 'loss/train': 0.032710231840610504} 08/31/2021 07:53:53 - INFO - __main__ - Step 103489: {'lr': 0.0001122656316747499, 'samples': 19869888, 'steps': 103488, 'loss/train': 0.9871717691421509} 08/31/2021 07:53:54 - INFO - __main__ - Step 103490: {'lr': 0.00011226120298073258, 'samples': 19870080, 'steps': 103489, 'loss/train': 1.5229367017745972} 08/31/2021 07:53:54 - INFO - __main__ - Step 103491: {'lr': 0.00011225677434877826, 'samples': 19870272, 'steps': 103490, 'loss/train': 1.1629281044006348} 08/31/2021 07:53:55 - INFO - __main__ - Step 103492: {'lr': 0.0001122523457788889, 'samples': 19870464, 'steps': 103491, 'loss/train': 0.8692485690116882} 08/31/2021 07:53:55 - INFO - __main__ - Step 103493: {'lr': 0.0001122479172710665, 'samples': 19870656, 'steps': 103492, 'loss/train': 1.5656452178955078} 08/31/2021 07:53:56 - INFO - __main__ - Step 103494: {'lr': 0.00011224348882531318, 'samples': 19870848, 'steps': 103493, 'loss/train': 1.3779666423797607} 08/31/2021 07:53:57 - INFO - __main__ - Step 103495: {'lr': 0.00011223906044163074, 'samples': 19871040, 'steps': 103494, 'loss/train': 1.460146188735962} 08/31/2021 07:53:57 - INFO - __main__ - Step 103496: {'lr': 0.00011223463212002121, 'samples': 19871232, 'steps': 103495, 'loss/train': 1.487711787223816} 08/31/2021 07:53:57 - INFO - __main__ - Step 103497: {'lr': 0.00011223020386048665, 'samples': 19871424, 'steps': 103496, 'loss/train': 0.5225017070770264} 08/31/2021 07:53:58 - INFO - __main__ - Step 103498: {'lr': 0.00011222577566302902, 'samples': 19871616, 'steps': 103497, 'loss/train': 1.322960376739502} 08/31/2021 07:53:59 - INFO - __main__ - Step 103499: {'lr': 0.00011222134752765034, 'samples': 19871808, 'steps': 103498, 'loss/train': 1.3810596466064453} 08/31/2021 07:54:00 - INFO - __main__ - Step 103500: {'lr': 0.00011221691945435262, 'samples': 19872000, 'steps': 103499, 'loss/train': 1.5979183912277222} 08/31/2021 07:54:00 - INFO - __main__ - Step 103501: {'lr': 0.00011221249144313777, 'samples': 19872192, 'steps': 103500, 'loss/train': 1.3811736106872559} 08/31/2021 07:54:01 - INFO - __main__ - Step 103502: {'lr': 0.00011220806349400788, 'samples': 19872384, 'steps': 103501, 'loss/train': 0.6729941964149475} 08/31/2021 07:54:01 - INFO - __main__ - Step 103503: {'lr': 0.00011220363560696492, 'samples': 19872576, 'steps': 103502, 'loss/train': 1.4121819734573364} 08/31/2021 07:54:03 - INFO - __main__ - Step 103504: {'lr': 0.00011219920778201088, 'samples': 19872768, 'steps': 103503, 'loss/train': 0.6292234063148499} 08/31/2021 07:54:03 - INFO - __main__ - Step 103505: {'lr': 0.00011219478001914781, 'samples': 19872960, 'steps': 103504, 'loss/train': 0.2841945290565491} 08/31/2021 07:54:03 - INFO - __main__ - Step 103506: {'lr': 0.00011219035231837759, 'samples': 19873152, 'steps': 103505, 'loss/train': 0.8492419123649597} 08/31/2021 07:54:04 - INFO - __main__ - Step 103507: {'lr': 0.00011218592467970226, 'samples': 19873344, 'steps': 103506, 'loss/train': 1.307983636856079} 08/31/2021 07:54:04 - INFO - __main__ - Step 103508: {'lr': 0.0001121814971031238, 'samples': 19873536, 'steps': 103507, 'loss/train': 1.5050883293151855} 08/31/2021 07:54:05 - INFO - __main__ - Step 103509: {'lr': 0.00011217706958864426, 'samples': 19873728, 'steps': 103508, 'loss/train': 1.0359307527542114} 08/31/2021 07:54:06 - INFO - __main__ - Step 103510: {'lr': 0.0001121726421362656, 'samples': 19873920, 'steps': 103509, 'loss/train': 1.1536670923233032} 08/31/2021 07:54:06 - INFO - __main__ - Step 103511: {'lr': 0.00011216821474598982, 'samples': 19874112, 'steps': 103510, 'loss/train': 1.258154273033142} 08/31/2021 07:54:07 - INFO - __main__ - Step 103512: {'lr': 0.00011216378741781891, 'samples': 19874304, 'steps': 103511, 'loss/train': 1.6271679401397705} 08/31/2021 07:54:07 - INFO - __main__ - Step 103513: {'lr': 0.00011215936015175488, 'samples': 19874496, 'steps': 103512, 'loss/train': 1.3886827230453491} 08/31/2021 07:54:09 - INFO - __main__ - Step 103514: {'lr': 0.00011215493294779969, 'samples': 19874688, 'steps': 103513, 'loss/train': 1.4479175806045532} 08/31/2021 07:54:09 - INFO - __main__ - Step 103515: {'lr': 0.00011215050580595538, 'samples': 19874880, 'steps': 103514, 'loss/train': 1.2888892889022827} 08/31/2021 07:54:09 - INFO - __main__ - Step 103516: {'lr': 0.000112146078726224, 'samples': 19875072, 'steps': 103515, 'loss/train': 1.1552543640136719} 08/31/2021 07:54:10 - INFO - __main__ - Step 103517: {'lr': 0.0001121416517086074, 'samples': 19875264, 'steps': 103516, 'loss/train': 0.850182056427002} 08/31/2021 07:54:10 - INFO - __main__ - Step 103518: {'lr': 0.00011213722475310765, 'samples': 19875456, 'steps': 103517, 'loss/train': 0.3030627965927124} 08/31/2021 07:54:12 - INFO - __main__ - Step 103519: {'lr': 0.00011213279785972672, 'samples': 19875648, 'steps': 103518, 'loss/train': 0.6775755882263184} 08/31/2021 07:54:12 - INFO - __main__ - Step 103520: {'lr': 0.00011212837102846663, 'samples': 19875840, 'steps': 103519, 'loss/train': 0.1289987862110138} 08/31/2021 07:54:13 - INFO - __main__ - Step 103521: {'lr': 0.00011212394425932938, 'samples': 19876032, 'steps': 103520, 'loss/train': 0.24704903364181519} 08/31/2021 07:54:13 - INFO - __main__ - Step 103522: {'lr': 0.00011211951755231692, 'samples': 19876224, 'steps': 103521, 'loss/train': 0.9278753399848938} 08/31/2021 07:54:13 - INFO - __main__ - Step 103523: {'lr': 0.0001121150909074313, 'samples': 19876416, 'steps': 103522, 'loss/train': 0.8183149099349976} 08/31/2021 07:54:14 - INFO - __main__ - Step 103524: {'lr': 0.00011211066432467448, 'samples': 19876608, 'steps': 103523, 'loss/train': 1.2431066036224365} 08/31/2021 07:54:15 - INFO - __main__ - Step 103525: {'lr': 0.0001121062378040485, 'samples': 19876800, 'steps': 103524, 'loss/train': 0.7299224734306335} 08/31/2021 07:54:16 - INFO - __main__ - Step 103526: {'lr': 0.0001121018113455553, 'samples': 19876992, 'steps': 103525, 'loss/train': 1.198306679725647} 08/31/2021 07:54:16 - INFO - __main__ - Step 103527: {'lr': 0.00011209738494919689, 'samples': 19877184, 'steps': 103526, 'loss/train': 0.11463401466608047} 08/31/2021 07:54:16 - INFO - __main__ - Step 103528: {'lr': 0.00011209295861497529, 'samples': 19877376, 'steps': 103527, 'loss/train': 0.030900048092007637} 08/31/2021 07:54:17 - INFO - __main__ - Step 103529: {'lr': 0.00011208853234289245, 'samples': 19877568, 'steps': 103528, 'loss/train': 1.0643222332000732} 08/31/2021 07:54:19 - INFO - __main__ - Step 103530: {'lr': 0.00011208410613295047, 'samples': 19877760, 'steps': 103529, 'loss/train': 1.6215726137161255} 08/31/2021 07:54:19 - INFO - __main__ - Step 103531: {'lr': 0.0001120796799851512, 'samples': 19877952, 'steps': 103530, 'loss/train': 1.3834271430969238} 08/31/2021 07:54:19 - INFO - __main__ - Step 103532: {'lr': 0.00011207525389949671, 'samples': 19878144, 'steps': 103531, 'loss/train': 0.8581879734992981} 08/31/2021 07:54:20 - INFO - __main__ - Step 103533: {'lr': 0.00011207082787598896, 'samples': 19878336, 'steps': 103532, 'loss/train': 1.1450321674346924} 08/31/2021 07:54:20 - INFO - __main__ - Step 103534: {'lr': 0.00011206640191462996, 'samples': 19878528, 'steps': 103533, 'loss/train': 1.3352458477020264} 08/31/2021 07:54:22 - INFO - __main__ - Step 103535: {'lr': 0.00011206197601542173, 'samples': 19878720, 'steps': 103534, 'loss/train': 0.15915194153785706} 08/31/2021 07:54:22 - INFO - __main__ - Step 103536: {'lr': 0.00011205755017836625, 'samples': 19878912, 'steps': 103535, 'loss/train': 0.026366587728261948} 08/31/2021 07:54:23 - INFO - __main__ - Step 103537: {'lr': 0.0001120531244034655, 'samples': 19879104, 'steps': 103536, 'loss/train': 0.9660996198654175} 08/31/2021 07:54:23 - INFO - __main__ - Step 103538: {'lr': 0.00011204869869072146, 'samples': 19879296, 'steps': 103537, 'loss/train': 1.4508519172668457} 08/31/2021 07:54:23 - INFO - __main__ - Step 103539: {'lr': 0.00011204427304013617, 'samples': 19879488, 'steps': 103538, 'loss/train': 1.2896894216537476} 08/31/2021 07:54:25 - INFO - __main__ - Step 103540: {'lr': 0.00011203984745171159, 'samples': 19879680, 'steps': 103539, 'loss/train': 1.6012823581695557} 08/31/2021 07:54:25 - INFO - __main__ - Step 103541: {'lr': 0.00011203542192544975, 'samples': 19879872, 'steps': 103540, 'loss/train': 0.595230221748352} 08/31/2021 07:54:26 - INFO - __main__ - Step 103542: {'lr': 0.0001120309964613526, 'samples': 19880064, 'steps': 103541, 'loss/train': 1.5672062635421753} 08/31/2021 07:54:26 - INFO - __main__ - Step 103543: {'lr': 0.00011202657105942224, 'samples': 19880256, 'steps': 103542, 'loss/train': 1.756510615348816} 08/31/2021 07:54:26 - INFO - __main__ - Step 103544: {'lr': 0.00011202214571966049, 'samples': 19880448, 'steps': 103543, 'loss/train': 1.4316705465316772} 08/31/2021 07:54:28 - INFO - __main__ - Step 103545: {'lr': 0.00011201772044206945, 'samples': 19880640, 'steps': 103544, 'loss/train': 1.4424049854278564} 08/31/2021 07:54:28 - INFO - __main__ - Step 103546: {'lr': 0.00011201329522665107, 'samples': 19880832, 'steps': 103545, 'loss/train': 1.2569031715393066} 08/31/2021 07:54:29 - INFO - __main__ - Step 103547: {'lr': 0.00011200887007340741, 'samples': 19881024, 'steps': 103546, 'loss/train': 1.423149824142456} 08/31/2021 07:54:29 - INFO - __main__ - Step 103548: {'lr': 0.00011200444498234038, 'samples': 19881216, 'steps': 103547, 'loss/train': 1.280379056930542} 08/31/2021 07:54:29 - INFO - __main__ - Step 103549: {'lr': 0.00011200001995345204, 'samples': 19881408, 'steps': 103548, 'loss/train': 0.8747661113739014} 08/31/2021 07:54:31 - INFO - __main__ - Step 103550: {'lr': 0.00011199559498674436, 'samples': 19881600, 'steps': 103549, 'loss/train': 1.2337663173675537} 08/31/2021 07:54:31 - INFO - __main__ - Step 103551: {'lr': 0.00011199117008221932, 'samples': 19881792, 'steps': 103550, 'loss/train': 1.2738096714019775} 08/31/2021 07:54:32 - INFO - __main__ - Step 103552: {'lr': 0.00011198674523987896, 'samples': 19881984, 'steps': 103551, 'loss/train': 1.1555482149124146} 08/31/2021 07:54:32 - INFO - __main__ - Step 103553: {'lr': 0.00011198232045972523, 'samples': 19882176, 'steps': 103552, 'loss/train': 1.9961564540863037} 08/31/2021 07:54:32 - INFO - __main__ - Step 103554: {'lr': 0.00011197789574176012, 'samples': 19882368, 'steps': 103553, 'loss/train': 2.400904417037964} 08/31/2021 07:54:34 - INFO - __main__ - Step 103555: {'lr': 0.00011197347108598566, 'samples': 19882560, 'steps': 103554, 'loss/train': 1.1839922666549683} 08/31/2021 07:54:34 - INFO - __main__ - Step 103556: {'lr': 0.0001119690464924038, 'samples': 19882752, 'steps': 103555, 'loss/train': 1.1834429502487183} 08/31/2021 07:54:35 - INFO - __main__ - Step 103557: {'lr': 0.00011196462196101667, 'samples': 19882944, 'steps': 103556, 'loss/train': 1.1751723289489746} 08/31/2021 07:54:35 - INFO - __main__ - Step 103558: {'lr': 0.00011196019749182607, 'samples': 19883136, 'steps': 103557, 'loss/train': 0.9316601753234863} 08/31/2021 07:54:35 - INFO - __main__ - Step 103559: {'lr': 0.00011195577308483405, 'samples': 19883328, 'steps': 103558, 'loss/train': 1.140350580215454} 08/31/2021 07:54:37 - INFO - __main__ - Step 103560: {'lr': 0.00011195134874004265, 'samples': 19883520, 'steps': 103559, 'loss/train': 1.1434682607650757} 08/31/2021 07:54:37 - INFO - __main__ - Step 103561: {'lr': 0.0001119469244574538, 'samples': 19883712, 'steps': 103560, 'loss/train': 0.42836108803749084} 08/31/2021 07:54:38 - INFO - __main__ - Step 103562: {'lr': 0.00011194250023706959, 'samples': 19883904, 'steps': 103561, 'loss/train': 1.1248056888580322} 08/31/2021 07:54:38 - INFO - __main__ - Step 103563: {'lr': 0.00011193807607889192, 'samples': 19884096, 'steps': 103562, 'loss/train': 1.2118191719055176} 08/31/2021 07:54:38 - INFO - __main__ - Step 103564: {'lr': 0.00011193365198292285, 'samples': 19884288, 'steps': 103563, 'loss/train': 1.6429160833358765} 08/31/2021 07:54:40 - INFO - __main__ - Step 103565: {'lr': 0.00011192922794916432, 'samples': 19884480, 'steps': 103564, 'loss/train': 1.1484066247940063} 08/31/2021 07:54:41 - INFO - __main__ - Step 103566: {'lr': 0.00011192480397761836, 'samples': 19884672, 'steps': 103565, 'loss/train': 1.0281298160552979} 08/31/2021 07:54:41 - INFO - __main__ - Step 103567: {'lr': 0.00011192038006828698, 'samples': 19884864, 'steps': 103566, 'loss/train': 1.416115641593933} 08/31/2021 07:54:41 - INFO - __main__ - Step 103568: {'lr': 0.0001119159562211721, 'samples': 19885056, 'steps': 103567, 'loss/train': 1.122248649597168} 08/31/2021 07:54:42 - INFO - __main__ - Step 103569: {'lr': 0.00011191153243627578, 'samples': 19885248, 'steps': 103568, 'loss/train': 0.35702162981033325} 08/31/2021 07:54:42 - INFO - __main__ - Step 103570: {'lr': 0.0001119071087136001, 'samples': 19885440, 'steps': 103569, 'loss/train': 1.0167450904846191} 08/31/2021 07:54:44 - INFO - __main__ - Step 103571: {'lr': 0.00011190268505314682, 'samples': 19885632, 'steps': 103570, 'loss/train': 1.0169775485992432} 08/31/2021 07:54:44 - INFO - __main__ - Step 103572: {'lr': 0.0001118982614549181, 'samples': 19885824, 'steps': 103571, 'loss/train': 0.517902672290802} 08/31/2021 07:54:45 - INFO - __main__ - Step 103573: {'lr': 0.00011189383791891586, 'samples': 19886016, 'steps': 103572, 'loss/train': 1.25039541721344} 08/31/2021 07:54:45 - INFO - __main__ - Step 103574: {'lr': 0.00011188941444514214, 'samples': 19886208, 'steps': 103573, 'loss/train': 1.3698418140411377} 08/31/2021 07:54:45 - INFO - __main__ - Step 103575: {'lr': 0.00011188499103359892, 'samples': 19886400, 'steps': 103574, 'loss/train': 1.11335289478302} 08/31/2021 07:54:47 - INFO - __main__ - Step 103576: {'lr': 0.00011188056768428817, 'samples': 19886592, 'steps': 103575, 'loss/train': 0.741727352142334} 08/31/2021 07:54:47 - INFO - __main__ - Step 103577: {'lr': 0.00011187614439721194, 'samples': 19886784, 'steps': 103576, 'loss/train': 0.5335412621498108} 08/31/2021 07:54:48 - INFO - __main__ - Step 103578: {'lr': 0.00011187172117237216, 'samples': 19886976, 'steps': 103577, 'loss/train': 1.7538098096847534} 08/31/2021 07:54:48 - INFO - __main__ - Step 103579: {'lr': 0.00011186729800977085, 'samples': 19887168, 'steps': 103578, 'loss/train': 1.0364693403244019} 08/31/2021 07:54:48 - INFO - __main__ - Step 103580: {'lr': 0.00011186287490941002, 'samples': 19887360, 'steps': 103579, 'loss/train': 0.1991368681192398} 08/31/2021 07:54:50 - INFO - __main__ - Step 103581: {'lr': 0.00011185845187129164, 'samples': 19887552, 'steps': 103580, 'loss/train': 0.033080440014600754} 08/31/2021 07:54:51 - INFO - __main__ - Step 103582: {'lr': 0.0001118540288954177, 'samples': 19887744, 'steps': 103581, 'loss/train': 1.1759867668151855} 08/31/2021 07:54:51 - INFO - __main__ - Step 103583: {'lr': 0.00011184960598179033, 'samples': 19887936, 'steps': 103582, 'loss/train': 1.0654240846633911} 08/31/2021 07:54:52 - INFO - __main__ - Step 103584: {'lr': 0.00011184518313041128, 'samples': 19888128, 'steps': 103583, 'loss/train': 0.37697556614875793} 08/31/2021 07:54:52 - INFO - __main__ - Step 103585: {'lr': 0.00011184076034128265, 'samples': 19888320, 'steps': 103584, 'loss/train': 1.2683025598526} 08/31/2021 07:54:54 - INFO - __main__ - Step 103586: {'lr': 0.00011183633761440645, 'samples': 19888512, 'steps': 103585, 'loss/train': 1.186093807220459} 08/31/2021 07:54:54 - INFO - __main__ - Step 103587: {'lr': 0.00011183191494978467, 'samples': 19888704, 'steps': 103586, 'loss/train': 0.16010670363903046} 08/31/2021 07:54:54 - INFO - __main__ - Step 103588: {'lr': 0.00011182749234741929, 'samples': 19888896, 'steps': 103587, 'loss/train': 1.4329044818878174} 08/31/2021 07:54:55 - INFO - __main__ - Step 103589: {'lr': 0.0001118230698073123, 'samples': 19889088, 'steps': 103588, 'loss/train': 1.191300392150879} 08/31/2021 07:54:55 - INFO - __main__ - Step 103590: {'lr': 0.00011181864732946573, 'samples': 19889280, 'steps': 103589, 'loss/train': 0.999716579914093} 08/31/2021 07:54:57 - INFO - __main__ - Step 103591: {'lr': 0.00011181422491388152, 'samples': 19889472, 'steps': 103590, 'loss/train': 1.1432054042816162} 08/31/2021 07:54:57 - INFO - __main__ - Step 103592: {'lr': 0.0001118098025605617, 'samples': 19889664, 'steps': 103591, 'loss/train': 0.9029049277305603} 08/31/2021 07:54:57 - INFO - __main__ - Step 103593: {'lr': 0.00011180538026950826, 'samples': 19889856, 'steps': 103592, 'loss/train': 0.05632699653506279} 08/31/2021 07:54:58 - INFO - __main__ - Step 103594: {'lr': 0.00011180095804072315, 'samples': 19890048, 'steps': 103593, 'loss/train': 1.4450457096099854} 08/31/2021 07:54:58 - INFO - __main__ - Step 103595: {'lr': 0.00011179653587420844, 'samples': 19890240, 'steps': 103594, 'loss/train': 1.1573996543884277} 08/31/2021 07:55:00 - INFO - __main__ - Step 103596: {'lr': 0.00011179211376996604, 'samples': 19890432, 'steps': 103595, 'loss/train': 1.099231481552124} 08/31/2021 07:55:00 - INFO - __main__ - Step 103597: {'lr': 0.0001117876917279981, 'samples': 19890624, 'steps': 103596, 'loss/train': 1.2292193174362183} 08/31/2021 07:55:00 - INFO - __main__ - Step 103598: {'lr': 0.00011178326974830638, 'samples': 19890816, 'steps': 103597, 'loss/train': 0.6027976274490356} 08/31/2021 07:55:01 - INFO - __main__ - Step 103599: {'lr': 0.00011177884783089299, 'samples': 19891008, 'steps': 103598, 'loss/train': 1.4428197145462036} 08/31/2021 07:55:01 - INFO - __main__ - Step 103600: {'lr': 0.00011177442597575993, 'samples': 19891200, 'steps': 103599, 'loss/train': 1.428324818611145} 08/31/2021 07:55:03 - INFO - __main__ - Step 103601: {'lr': 0.00011177000418290917, 'samples': 19891392, 'steps': 103600, 'loss/train': 0.5374991297721863} 08/31/2021 07:55:03 - INFO - __main__ - Step 103602: {'lr': 0.00011176558245234273, 'samples': 19891584, 'steps': 103601, 'loss/train': 1.0395855903625488} 08/31/2021 07:55:04 - INFO - __main__ - Step 103603: {'lr': 0.00011176116078406257, 'samples': 19891776, 'steps': 103602, 'loss/train': 0.7520251274108887} 08/31/2021 07:55:04 - INFO - __main__ - Step 103604: {'lr': 0.0001117567391780707, 'samples': 19891968, 'steps': 103603, 'loss/train': 1.1186904907226562} 08/31/2021 07:55:04 - INFO - __main__ - Step 103605: {'lr': 0.00011175231763436911, 'samples': 19892160, 'steps': 103604, 'loss/train': 0.9549963474273682} 08/31/2021 07:55:05 - INFO - __main__ - Step 103606: {'lr': 0.0001117478961529598, 'samples': 19892352, 'steps': 103605, 'loss/train': 1.087336778640747} 08/31/2021 07:55:06 - INFO - __main__ - Step 103607: {'lr': 0.00011174347473384474, 'samples': 19892544, 'steps': 103606, 'loss/train': 0.060835689306259155} 08/31/2021 07:55:07 - INFO - __main__ - Step 103608: {'lr': 0.00011173905337702594, 'samples': 19892736, 'steps': 103607, 'loss/train': 0.6227801442146301} 08/31/2021 07:55:07 - INFO - __main__ - Step 103609: {'lr': 0.0001117346320825054, 'samples': 19892928, 'steps': 103608, 'loss/train': 1.4867304563522339} 08/31/2021 07:55:07 - INFO - __main__ - Step 103610: {'lr': 0.00011173021085028518, 'samples': 19893120, 'steps': 103609, 'loss/train': 1.7655088901519775} 08/31/2021 07:55:08 - INFO - __main__ - Step 103611: {'lr': 0.00011172578968036712, 'samples': 19893312, 'steps': 103610, 'loss/train': 0.03314831107854843} 08/31/2021 07:55:09 - INFO - __main__ - Step 103612: {'lr': 0.00011172136857275325, 'samples': 19893504, 'steps': 103611, 'loss/train': 0.952876091003418} 08/31/2021 07:55:10 - INFO - __main__ - Step 103613: {'lr': 0.00011171694752744562, 'samples': 19893696, 'steps': 103612, 'loss/train': 0.8262567520141602} 08/31/2021 07:55:10 - INFO - __main__ - Step 103614: {'lr': 0.00011171252654444622, 'samples': 19893888, 'steps': 103613, 'loss/train': 0.055787891149520874} 08/31/2021 07:55:11 - INFO - __main__ - Step 103615: {'lr': 0.000111708105623757, 'samples': 19894080, 'steps': 103614, 'loss/train': 1.0932472944259644} 08/31/2021 07:55:11 - INFO - __main__ - Step 103616: {'lr': 0.00011170368476537998, 'samples': 19894272, 'steps': 103615, 'loss/train': 0.17583966255187988} 08/31/2021 07:55:13 - INFO - __main__ - Step 103617: {'lr': 0.00011169926396931712, 'samples': 19894464, 'steps': 103616, 'loss/train': 1.2654728889465332} 08/31/2021 07:55:13 - INFO - __main__ - Step 103618: {'lr': 0.00011169484323557047, 'samples': 19894656, 'steps': 103617, 'loss/train': 1.6556732654571533} 08/31/2021 07:55:14 - INFO - __main__ - Step 103619: {'lr': 0.00011169042256414197, 'samples': 19894848, 'steps': 103618, 'loss/train': 0.1960604190826416} 08/31/2021 07:55:14 - INFO - __main__ - Step 103620: {'lr': 0.00011168600195503364, 'samples': 19895040, 'steps': 103619, 'loss/train': 0.10260579735040665} 08/31/2021 07:55:14 - INFO - __main__ - Step 103621: {'lr': 0.00011168158140824746, 'samples': 19895232, 'steps': 103620, 'loss/train': 1.3307380676269531} 08/31/2021 07:55:16 - INFO - __main__ - Step 103622: {'lr': 0.00011167716092378544, 'samples': 19895424, 'steps': 103621, 'loss/train': 0.7331464290618896} 08/31/2021 07:55:17 - INFO - __main__ - Step 103623: {'lr': 0.00011167274050164955, 'samples': 19895616, 'steps': 103622, 'loss/train': 0.44012802839279175} 08/31/2021 07:55:17 - INFO - __main__ - Step 103624: {'lr': 0.00011166832014184186, 'samples': 19895808, 'steps': 103623, 'loss/train': 0.10116718709468842} 08/31/2021 07:55:17 - INFO - __main__ - Step 103625: {'lr': 0.00011166389984436423, 'samples': 19896000, 'steps': 103624, 'loss/train': 1.247071623802185} 08/31/2021 07:55:18 - INFO - __main__ - Step 103626: {'lr': 0.00011165947960921868, 'samples': 19896192, 'steps': 103625, 'loss/train': 1.2324745655059814} 08/31/2021 07:55:19 - INFO - __main__ - Step 103627: {'lr': 0.00011165505943640725, 'samples': 19896384, 'steps': 103626, 'loss/train': 0.025256779044866562} 08/31/2021 07:55:20 - INFO - __main__ - Step 103628: {'lr': 0.00011165063932593192, 'samples': 19896576, 'steps': 103627, 'loss/train': 1.1174771785736084} 08/31/2021 07:55:20 - INFO - __main__ - Step 103629: {'lr': 0.00011164621927779467, 'samples': 19896768, 'steps': 103628, 'loss/train': 0.7709673047065735} 08/31/2021 07:55:20 - INFO - __main__ - Step 103630: {'lr': 0.0001116417992919975, 'samples': 19896960, 'steps': 103629, 'loss/train': 1.1445246934890747} 08/31/2021 07:55:21 - INFO - __main__ - Step 103631: {'lr': 0.0001116373793685424, 'samples': 19897152, 'steps': 103630, 'loss/train': 0.028443127870559692} 08/31/2021 07:55:22 - INFO - __main__ - Step 103632: {'lr': 0.00011163295950743139, 'samples': 19897344, 'steps': 103631, 'loss/train': 1.3365614414215088} 08/31/2021 07:55:23 - INFO - __main__ - Step 103633: {'lr': 0.00011162853970866637, 'samples': 19897536, 'steps': 103632, 'loss/train': 0.9879570007324219} 08/31/2021 07:55:23 - INFO - __main__ - Step 103634: {'lr': 0.00011162411997224945, 'samples': 19897728, 'steps': 103633, 'loss/train': 0.9249162673950195} 08/31/2021 07:55:23 - INFO - __main__ - Step 103635: {'lr': 0.00011161970029818255, 'samples': 19897920, 'steps': 103634, 'loss/train': 1.5248947143554688} 08/31/2021 07:55:24 - INFO - __main__ - Step 103636: {'lr': 0.00011161528068646767, 'samples': 19898112, 'steps': 103635, 'loss/train': 1.123947262763977} 08/31/2021 07:55:26 - INFO - __main__ - Step 103637: {'lr': 0.00011161086113710692, 'samples': 19898304, 'steps': 103636, 'loss/train': 1.253689169883728} 08/31/2021 07:55:26 - INFO - __main__ - Step 103638: {'lr': 0.00011160644165010206, 'samples': 19898496, 'steps': 103637, 'loss/train': 1.4107106924057007} 08/31/2021 07:55:27 - INFO - __main__ - Step 103639: {'lr': 0.0001116020222254552, 'samples': 19898688, 'steps': 103638, 'loss/train': 1.2562835216522217} 08/31/2021 07:55:27 - INFO - __main__ - Step 103640: {'lr': 0.00011159760286316836, 'samples': 19898880, 'steps': 103639, 'loss/train': 0.3292219042778015} 08/31/2021 07:55:27 - INFO - __main__ - Step 103641: {'lr': 0.00011159318356324349, 'samples': 19899072, 'steps': 103640, 'loss/train': 0.7802824378013611} 08/31/2021 07:55:28 - INFO - __main__ - Step 103642: {'lr': 0.0001115887643256826, 'samples': 19899264, 'steps': 103641, 'loss/train': 1.6077755689620972} 08/31/2021 07:55:30 - INFO - __main__ - Step 103643: {'lr': 0.00011158434515048768, 'samples': 19899456, 'steps': 103642, 'loss/train': 1.1578514575958252} 08/31/2021 07:55:31 - INFO - __main__ - Step 103644: {'lr': 0.00011157992603766073, 'samples': 19899648, 'steps': 103643, 'loss/train': 1.235709547996521} 08/31/2021 07:55:31 - INFO - __main__ - Step 103645: {'lr': 0.0001115755069872037, 'samples': 19899840, 'steps': 103644, 'loss/train': 1.1279321908950806} 08/31/2021 07:55:31 - INFO - __main__ - Step 103646: {'lr': 0.00011157108799911863, 'samples': 19900032, 'steps': 103645, 'loss/train': 0.30017438530921936} 08/31/2021 07:55:32 - INFO - __main__ - Step 103647: {'lr': 0.00011156666907340749, 'samples': 19900224, 'steps': 103646, 'loss/train': 0.3159826695919037} 08/31/2021 07:55:32 - INFO - __main__ - Step 103648: {'lr': 0.00011156225021007227, 'samples': 19900416, 'steps': 103647, 'loss/train': 1.3176041841506958} 08/31/2021 07:55:34 - INFO - __main__ - Step 103649: {'lr': 0.00011155783140911496, 'samples': 19900608, 'steps': 103648, 'loss/train': 1.2508463859558105} 08/31/2021 07:55:34 - INFO - __main__ - Step 103650: {'lr': 0.00011155341267053756, 'samples': 19900800, 'steps': 103649, 'loss/train': 0.5672750473022461} 08/31/2021 07:55:34 - INFO - __main__ - Step 103651: {'lr': 0.00011154899399434215, 'samples': 19900992, 'steps': 103650, 'loss/train': 0.8846773505210876} 08/31/2021 07:55:35 - INFO - __main__ - Step 103652: {'lr': 0.00011154457538053054, 'samples': 19901184, 'steps': 103651, 'loss/train': 0.4851069748401642} 08/31/2021 07:55:35 - INFO - __main__ - Step 103653: {'lr': 0.00011154015682910479, 'samples': 19901376, 'steps': 103652, 'loss/train': 1.2398706674575806} 08/31/2021 07:55:37 - INFO - __main__ - Step 103654: {'lr': 0.00011153573834006691, 'samples': 19901568, 'steps': 103653, 'loss/train': 1.5168814659118652} 08/31/2021 07:55:37 - INFO - __main__ - Step 103655: {'lr': 0.00011153131991341889, 'samples': 19901760, 'steps': 103654, 'loss/train': 0.4785196781158447} 08/31/2021 07:55:37 - INFO - __main__ - Step 103656: {'lr': 0.00011152690154916273, 'samples': 19901952, 'steps': 103655, 'loss/train': 0.41433385014533997} 08/31/2021 07:55:38 - INFO - __main__ - Step 103657: {'lr': 0.0001115224832473004, 'samples': 19902144, 'steps': 103656, 'loss/train': 1.165194034576416} 08/31/2021 07:55:38 - INFO - __main__ - Step 103658: {'lr': 0.00011151806500783393, 'samples': 19902336, 'steps': 103657, 'loss/train': 0.9956315755844116} 08/31/2021 07:55:40 - INFO - __main__ - Step 103659: {'lr': 0.00011151364683076526, 'samples': 19902528, 'steps': 103658, 'loss/train': 0.8877595663070679} 08/31/2021 07:55:40 - INFO - __main__ - Step 103660: {'lr': 0.00011150922871609639, 'samples': 19902720, 'steps': 103659, 'loss/train': 1.2949750423431396} 08/31/2021 07:55:40 - INFO - __main__ - Step 103661: {'lr': 0.00011150481066382937, 'samples': 19902912, 'steps': 103660, 'loss/train': 1.603350281715393} 08/31/2021 07:55:41 - INFO - __main__ - Step 103662: {'lr': 0.00011150039267396611, 'samples': 19903104, 'steps': 103661, 'loss/train': 1.1156070232391357} 08/31/2021 07:55:41 - INFO - __main__ - Step 103663: {'lr': 0.00011149597474650864, 'samples': 19903296, 'steps': 103662, 'loss/train': 1.3124847412109375} 08/31/2021 07:55:43 - INFO - __main__ - Step 103664: {'lr': 0.00011149155688145904, 'samples': 19903488, 'steps': 103663, 'loss/train': 2.1129586696624756} 08/31/2021 07:55:43 - INFO - __main__ - Step 103665: {'lr': 0.00011148713907881914, 'samples': 19903680, 'steps': 103664, 'loss/train': 1.01936674118042} 08/31/2021 07:55:43 - INFO - __main__ - Step 103666: {'lr': 0.00011148272133859096, 'samples': 19903872, 'steps': 103665, 'loss/train': 0.6678959727287292} 08/31/2021 07:55:44 - INFO - __main__ - Step 103667: {'lr': 0.00011147830366077654, 'samples': 19904064, 'steps': 103666, 'loss/train': 0.9012476801872253} 08/31/2021 07:55:44 - INFO - __main__ - Step 103668: {'lr': 0.00011147388604537786, 'samples': 19904256, 'steps': 103667, 'loss/train': 0.7295585870742798} 08/31/2021 07:55:44 - INFO - __main__ - Step 103669: {'lr': 0.00011146946849239692, 'samples': 19904448, 'steps': 103668, 'loss/train': 0.9640259742736816} 08/31/2021 07:55:46 - INFO - __main__ - Step 103670: {'lr': 0.00011146505100183568, 'samples': 19904640, 'steps': 103669, 'loss/train': 1.5597782135009766} 08/31/2021 07:55:46 - INFO - __main__ - Step 103671: {'lr': 0.00011146063357369619, 'samples': 19904832, 'steps': 103670, 'loss/train': 1.5255593061447144} 08/31/2021 07:55:47 - INFO - __main__ - Step 103672: {'lr': 0.00011145621620798035, 'samples': 19905024, 'steps': 103671, 'loss/train': 1.259563684463501} 08/31/2021 07:55:47 - INFO - __main__ - Step 103673: {'lr': 0.00011145179890469023, 'samples': 19905216, 'steps': 103672, 'loss/train': 0.9486218094825745} 08/31/2021 07:55:48 - INFO - __main__ - Step 103674: {'lr': 0.00011144738166382779, 'samples': 19905408, 'steps': 103673, 'loss/train': 1.1774377822875977} 08/31/2021 07:55:49 - INFO - __main__ - Step 103675: {'lr': 0.00011144296448539501, 'samples': 19905600, 'steps': 103674, 'loss/train': 0.046388886868953705} 08/31/2021 07:55:50 - INFO - __main__ - Step 103676: {'lr': 0.00011143854736939391, 'samples': 19905792, 'steps': 103675, 'loss/train': 1.01982843875885} 08/31/2021 07:55:50 - INFO - __main__ - Step 103677: {'lr': 0.00011143413031582644, 'samples': 19905984, 'steps': 103676, 'loss/train': 1.085915446281433} 08/31/2021 07:55:51 - INFO - __main__ - Step 103678: {'lr': 0.0001114297133246947, 'samples': 19906176, 'steps': 103677, 'loss/train': 0.019402984529733658} 08/31/2021 07:55:51 - INFO - __main__ - Step 103679: {'lr': 0.00011142529639600051, 'samples': 19906368, 'steps': 103678, 'loss/train': 0.9275330901145935} 08/31/2021 07:55:51 - INFO - __main__ - Step 103680: {'lr': 0.00011142087952974598, 'samples': 19906560, 'steps': 103679, 'loss/train': 2.1655433177948} 08/31/2021 07:55:53 - INFO - __main__ - Step 103681: {'lr': 0.00011141646272593303, 'samples': 19906752, 'steps': 103680, 'loss/train': 1.5619903802871704} 08/31/2021 07:55:53 - INFO - __main__ - Step 103682: {'lr': 0.00011141204598456367, 'samples': 19906944, 'steps': 103681, 'loss/train': 0.9147385358810425} 08/31/2021 07:55:54 - INFO - __main__ - Step 103683: {'lr': 0.00011140762930563995, 'samples': 19907136, 'steps': 103682, 'loss/train': 1.2406271696090698} 08/31/2021 07:55:54 - INFO - __main__ - Step 103684: {'lr': 0.00011140321268916376, 'samples': 19907328, 'steps': 103683, 'loss/train': 1.4565362930297852} 08/31/2021 07:55:54 - INFO - __main__ - Step 103685: {'lr': 0.00011139879613513718, 'samples': 19907520, 'steps': 103684, 'loss/train': 3.029939889907837} 08/31/2021 07:55:56 - INFO - __main__ - Step 103686: {'lr': 0.00011139437964356214, 'samples': 19907712, 'steps': 103685, 'loss/train': 1.1653982400894165} 08/31/2021 07:55:56 - INFO - __main__ - Step 103687: {'lr': 0.00011138996321444068, 'samples': 19907904, 'steps': 103686, 'loss/train': 1.2709239721298218} 08/31/2021 07:55:57 - INFO - __main__ - Step 103688: {'lr': 0.00011138554684777475, 'samples': 19908096, 'steps': 103687, 'loss/train': 0.6293612718582153} 08/31/2021 07:55:57 - INFO - __main__ - Step 103689: {'lr': 0.00011138113054356632, 'samples': 19908288, 'steps': 103688, 'loss/train': 1.346228003501892} 08/31/2021 07:55:57 - INFO - __main__ - Step 103690: {'lr': 0.00011137671430181746, 'samples': 19908480, 'steps': 103689, 'loss/train': 1.3085306882858276} 08/31/2021 07:56:00 - INFO - __main__ - Step 103691: {'lr': 0.00011137229812253019, 'samples': 19908672, 'steps': 103690, 'loss/train': 1.0364404916763306} 08/31/2021 07:56:00 - INFO - __main__ - Step 103692: {'lr': 0.00011136788200570632, 'samples': 19908864, 'steps': 103691, 'loss/train': 0.5743703246116638} 08/31/2021 07:56:00 - INFO - __main__ - Step 103693: {'lr': 0.00011136346595134796, 'samples': 19909056, 'steps': 103692, 'loss/train': 0.7891236543655396} 08/31/2021 07:56:01 - INFO - __main__ - Step 103694: {'lr': 0.00011135904995945709, 'samples': 19909248, 'steps': 103693, 'loss/train': 5.734269142150879} 08/31/2021 07:56:01 - INFO - __main__ - Step 103695: {'lr': 0.00011135463403003567, 'samples': 19909440, 'steps': 103694, 'loss/train': 0.7168192267417908} 08/31/2021 07:56:01 - INFO - __main__ - Step 103696: {'lr': 0.00011135021816308574, 'samples': 19909632, 'steps': 103695, 'loss/train': 0.46392112970352173} 08/31/2021 07:56:03 - INFO - __main__ - Step 103697: {'lr': 0.00011134580235860925, 'samples': 19909824, 'steps': 103696, 'loss/train': 1.503993272781372} 08/31/2021 07:56:04 - INFO - __main__ - Step 103698: {'lr': 0.0001113413866166082, 'samples': 19910016, 'steps': 103697, 'loss/train': 0.6749073266983032} 08/31/2021 07:56:04 - INFO - __main__ - Step 103699: {'lr': 0.00011133697093708456, 'samples': 19910208, 'steps': 103698, 'loss/train': 0.9477936625480652} 08/31/2021 07:56:04 - INFO - __main__ - Step 103700: {'lr': 0.00011133255532004036, 'samples': 19910400, 'steps': 103699, 'loss/train': 2.0673015117645264} 08/31/2021 07:56:05 - INFO - __main__ - Step 103701: {'lr': 0.0001113281397654776, 'samples': 19910592, 'steps': 103700, 'loss/train': 0.834253191947937} 08/31/2021 07:56:05 - INFO - __main__ - Step 103702: {'lr': 0.0001113237242733982, 'samples': 19910784, 'steps': 103701, 'loss/train': 1.0421171188354492} 08/31/2021 07:56:06 - INFO - __main__ - Step 103703: {'lr': 0.0001113193088438042, 'samples': 19910976, 'steps': 103702, 'loss/train': 1.5098204612731934} 08/31/2021 07:56:07 - INFO - __main__ - Step 103704: {'lr': 0.00011131489347669768, 'samples': 19911168, 'steps': 103703, 'loss/train': 1.3041677474975586} 08/31/2021 07:56:07 - INFO - __main__ - Step 103705: {'lr': 0.00011131047817208043, 'samples': 19911360, 'steps': 103704, 'loss/train': 0.7100335955619812} 08/31/2021 07:56:08 - INFO - __main__ - Step 103706: {'lr': 0.00011130606292995451, 'samples': 19911552, 'steps': 103705, 'loss/train': 0.6225258111953735} 08/31/2021 07:56:08 - INFO - __main__ - Step 103707: {'lr': 0.00011130164775032198, 'samples': 19911744, 'steps': 103706, 'loss/train': 1.3059192895889282} 08/31/2021 07:56:10 - INFO - __main__ - Step 103708: {'lr': 0.00011129723263318479, 'samples': 19911936, 'steps': 103707, 'loss/train': 1.0894806385040283} 08/31/2021 07:56:10 - INFO - __main__ - Step 103709: {'lr': 0.0001112928175785449, 'samples': 19912128, 'steps': 103708, 'loss/train': 0.6609763503074646} 08/31/2021 07:56:10 - INFO - __main__ - Step 103710: {'lr': 0.00011128840258640433, 'samples': 19912320, 'steps': 103709, 'loss/train': 0.4165011942386627} 08/31/2021 07:56:11 - INFO - __main__ - Step 103711: {'lr': 0.00011128398765676509, 'samples': 19912512, 'steps': 103710, 'loss/train': 1.4667307138442993} 08/31/2021 07:56:11 - INFO - __main__ - Step 103712: {'lr': 0.00011127957278962911, 'samples': 19912704, 'steps': 103711, 'loss/train': 1.2122448682785034} 08/31/2021 07:56:13 - INFO - __main__ - Step 103713: {'lr': 0.00011127515798499844, 'samples': 19912896, 'steps': 103712, 'loss/train': 0.9932926297187805} 08/31/2021 07:56:13 - INFO - __main__ - Step 103714: {'lr': 0.00011127074324287504, 'samples': 19913088, 'steps': 103713, 'loss/train': 0.6881841421127319} 08/31/2021 07:56:13 - INFO - __main__ - Step 103715: {'lr': 0.00011126632856326088, 'samples': 19913280, 'steps': 103714, 'loss/train': 0.31371092796325684} 08/31/2021 07:56:14 - INFO - __main__ - Step 103716: {'lr': 0.000111261913946158, 'samples': 19913472, 'steps': 103715, 'loss/train': 1.2052251100540161} 08/31/2021 07:56:14 - INFO - __main__ - Step 103717: {'lr': 0.00011125749939156835, 'samples': 19913664, 'steps': 103716, 'loss/train': 1.7560704946517944} 08/31/2021 07:56:16 - INFO - __main__ - Step 103718: {'lr': 0.00011125308489949401, 'samples': 19913856, 'steps': 103717, 'loss/train': 1.2619943618774414} 08/31/2021 07:56:16 - INFO - __main__ - Step 103719: {'lr': 0.0001112486704699368, 'samples': 19914048, 'steps': 103718, 'loss/train': 0.6680779457092285} 08/31/2021 07:56:17 - INFO - __main__ - Step 103720: {'lr': 0.00011124425610289881, 'samples': 19914240, 'steps': 103719, 'loss/train': 1.3596782684326172} 08/31/2021 07:56:17 - INFO - __main__ - Step 103721: {'lr': 0.000111239841798382, 'samples': 19914432, 'steps': 103720, 'loss/train': 1.2546875476837158} 08/31/2021 07:56:17 - INFO - __main__ - Step 103722: {'lr': 0.00011123542755638841, 'samples': 19914624, 'steps': 103721, 'loss/train': 0.6546391248703003} 08/31/2021 07:56:18 - INFO - __main__ - Step 103723: {'lr': 0.00011123101337691995, 'samples': 19914816, 'steps': 103722, 'loss/train': 0.7878504395484924} 08/31/2021 07:56:19 - INFO - __main__ - Step 103724: {'lr': 0.00011122659925997868, 'samples': 19915008, 'steps': 103723, 'loss/train': 0.9078142046928406} 08/31/2021 07:56:20 - INFO - __main__ - Step 103725: {'lr': 0.00011122218520556657, 'samples': 19915200, 'steps': 103724, 'loss/train': 1.484755039215088} 08/31/2021 07:56:20 - INFO - __main__ - Step 103726: {'lr': 0.0001112177712136856, 'samples': 19915392, 'steps': 103725, 'loss/train': 0.9645933508872986} 08/31/2021 07:56:20 - INFO - __main__ - Step 103727: {'lr': 0.00011121335728433776, 'samples': 19915584, 'steps': 103726, 'loss/train': 1.3353701829910278} 08/31/2021 07:56:21 - INFO - __main__ - Step 103728: {'lr': 0.00011120894341752502, 'samples': 19915776, 'steps': 103727, 'loss/train': 0.6179356575012207} 08/31/2021 07:56:22 - INFO - __main__ - Step 103729: {'lr': 0.00011120452961324939, 'samples': 19915968, 'steps': 103728, 'loss/train': 1.2219396829605103} 08/31/2021 07:56:23 - INFO - __main__ - Step 103730: {'lr': 0.00011120011587151297, 'samples': 19916160, 'steps': 103729, 'loss/train': 1.139223575592041} 08/31/2021 07:56:23 - INFO - __main__ - Step 103731: {'lr': 0.00011119570219231754, 'samples': 19916352, 'steps': 103730, 'loss/train': 1.007759928703308} 08/31/2021 07:56:23 - INFO - __main__ - Step 103732: {'lr': 0.00011119128857566518, 'samples': 19916544, 'steps': 103731, 'loss/train': 1.4672608375549316} 08/31/2021 07:56:24 - INFO - __main__ - Step 103733: {'lr': 0.00011118687502155789, 'samples': 19916736, 'steps': 103732, 'loss/train': 1.226230263710022} 08/31/2021 07:56:26 - INFO - __main__ - Step 103734: {'lr': 0.00011118246152999764, 'samples': 19916928, 'steps': 103733, 'loss/train': 0.9689670205116272} 08/31/2021 07:56:26 - INFO - __main__ - Step 103735: {'lr': 0.00011117804810098642, 'samples': 19917120, 'steps': 103734, 'loss/train': 1.0868338346481323} 08/31/2021 07:56:26 - INFO - __main__ - Step 103736: {'lr': 0.00011117363473452624, 'samples': 19917312, 'steps': 103735, 'loss/train': 2.096287488937378} 08/31/2021 07:56:27 - INFO - __main__ - Step 103737: {'lr': 0.00011116922143061911, 'samples': 19917504, 'steps': 103736, 'loss/train': 0.8159136772155762} 08/31/2021 07:56:27 - INFO - __main__ - Step 103738: {'lr': 0.00011116480818926694, 'samples': 19917696, 'steps': 103737, 'loss/train': 0.8552383780479431} 08/31/2021 07:56:29 - INFO - __main__ - Step 103739: {'lr': 0.00011116039501047179, 'samples': 19917888, 'steps': 103738, 'loss/train': 1.3206491470336914} 08/31/2021 07:56:29 - INFO - __main__ - Step 103740: {'lr': 0.00011115598189423563, 'samples': 19918080, 'steps': 103739, 'loss/train': 1.37600839138031} 08/31/2021 07:56:29 - INFO - __main__ - Step 103741: {'lr': 0.00011115156884056052, 'samples': 19918272, 'steps': 103740, 'loss/train': 0.48411232233047485} 08/31/2021 07:56:30 - INFO - __main__ - Step 103742: {'lr': 0.00011114715584944827, 'samples': 19918464, 'steps': 103741, 'loss/train': 1.277787685394287} 08/31/2021 07:56:30 - INFO - __main__ - Step 103743: {'lr': 0.00011114274292090099, 'samples': 19918656, 'steps': 103742, 'loss/train': 1.052668571472168} 08/31/2021 07:56:32 - INFO - __main__ - Step 103744: {'lr': 0.00011113833005492063, 'samples': 19918848, 'steps': 103743, 'loss/train': 1.5229297876358032} 08/31/2021 07:56:32 - INFO - __main__ - Step 103745: {'lr': 0.0001111339172515092, 'samples': 19919040, 'steps': 103744, 'loss/train': 1.5149245262145996} 08/31/2021 07:56:32 - INFO - __main__ - Step 103746: {'lr': 0.00011112950451066869, 'samples': 19919232, 'steps': 103745, 'loss/train': 1.4280656576156616} 08/31/2021 07:56:33 - INFO - __main__ - Step 103747: {'lr': 0.00011112509183240108, 'samples': 19919424, 'steps': 103746, 'loss/train': 1.5538512468338013} 08/31/2021 07:56:33 - INFO - __main__ - Step 103748: {'lr': 0.00011112067921670834, 'samples': 19919616, 'steps': 103747, 'loss/train': 1.6765271425247192} 08/31/2021 07:56:35 - INFO - __main__ - Step 103749: {'lr': 0.0001111162666635925, 'samples': 19919808, 'steps': 103748, 'loss/train': 1.6261087656021118} 08/31/2021 07:56:36 - INFO - __main__ - Step 103750: {'lr': 0.00011111185417305553, 'samples': 19920000, 'steps': 103749, 'loss/train': 1.2728848457336426} 08/31/2021 07:56:36 - INFO - __main__ - Step 103751: {'lr': 0.00011110744174509952, 'samples': 19920192, 'steps': 103750, 'loss/train': 1.0776625871658325} 08/31/2021 07:56:36 - INFO - __main__ - Step 103752: {'lr': 0.00011110302937972624, 'samples': 19920384, 'steps': 103751, 'loss/train': 0.9715216159820557} 08/31/2021 07:56:37 - INFO - __main__ - Step 103753: {'lr': 0.0001110986170769378, 'samples': 19920576, 'steps': 103752, 'loss/train': 1.225649356842041} 08/31/2021 07:56:37 - INFO - __main__ - Step 103754: {'lr': 0.00011109420483673616, 'samples': 19920768, 'steps': 103753, 'loss/train': 1.2235033512115479} 08/31/2021 07:56:39 - INFO - __main__ - Step 103755: {'lr': 0.00011108979265912336, 'samples': 19920960, 'steps': 103754, 'loss/train': 0.6402405500411987} 08/31/2021 07:56:39 - INFO - __main__ - Step 103756: {'lr': 0.00011108538054410133, 'samples': 19921152, 'steps': 103755, 'loss/train': 1.189773440361023} 08/31/2021 07:56:39 - INFO - __main__ - Step 103757: {'lr': 0.0001110809684916721, 'samples': 19921344, 'steps': 103756, 'loss/train': 1.4551513195037842} 08/31/2021 07:56:40 - INFO - __main__ - Step 103758: {'lr': 0.00011107655650183762, 'samples': 19921536, 'steps': 103757, 'loss/train': 0.8731600046157837} 08/31/2021 07:56:40 - INFO - __main__ - Step 103759: {'lr': 0.00011107214457459991, 'samples': 19921728, 'steps': 103758, 'loss/train': 0.030942566692829132} 08/31/2021 07:56:42 - INFO - __main__ - Step 103760: {'lr': 0.00011106773270996095, 'samples': 19921920, 'steps': 103759, 'loss/train': 1.0843391418457031} 08/31/2021 07:56:42 - INFO - __main__ - Step 103761: {'lr': 0.00011106332090792273, 'samples': 19922112, 'steps': 103760, 'loss/train': 1.505993127822876} 08/31/2021 07:56:42 - INFO - __main__ - Step 103762: {'lr': 0.00011105890916848735, 'samples': 19922304, 'steps': 103761, 'loss/train': 1.5422354936599731} 08/31/2021 07:56:43 - INFO - __main__ - Step 103763: {'lr': 0.00011105449749165655, 'samples': 19922496, 'steps': 103762, 'loss/train': 1.5007883310317993} 08/31/2021 07:56:43 - INFO - __main__ - Step 103764: {'lr': 0.00011105008587743246, 'samples': 19922688, 'steps': 103763, 'loss/train': 1.6287171840667725} 08/31/2021 07:56:45 - INFO - __main__ - Step 103765: {'lr': 0.00011104567432581709, 'samples': 19922880, 'steps': 103764, 'loss/train': 1.1947065591812134} 08/31/2021 07:56:45 - INFO - __main__ - Step 103766: {'lr': 0.00011104126283681234, 'samples': 19923072, 'steps': 103765, 'loss/train': 1.283312439918518} 08/31/2021 07:56:46 - INFO - __main__ - Step 103767: {'lr': 0.00011103685141042027, 'samples': 19923264, 'steps': 103766, 'loss/train': 1.2773330211639404} 08/31/2021 07:56:46 - INFO - __main__ - Step 103768: {'lr': 0.00011103244004664287, 'samples': 19923456, 'steps': 103767, 'loss/train': 0.9612957835197449} 08/31/2021 07:56:46 - INFO - __main__ - Step 103769: {'lr': 0.00011102802874548209, 'samples': 19923648, 'steps': 103768, 'loss/train': 0.39912310242652893} 08/31/2021 07:56:48 - INFO - __main__ - Step 103770: {'lr': 0.00011102361750693996, 'samples': 19923840, 'steps': 103769, 'loss/train': 1.361642837524414} 08/31/2021 07:56:49 - INFO - __main__ - Step 103771: {'lr': 0.00011101920633101842, 'samples': 19924032, 'steps': 103770, 'loss/train': 1.090664267539978} 08/31/2021 07:56:49 - INFO - __main__ - Step 103772: {'lr': 0.00011101479521771948, 'samples': 19924224, 'steps': 103771, 'loss/train': 0.9372139573097229} 08/31/2021 07:56:49 - INFO - __main__ - Step 103773: {'lr': 0.00011101038416704523, 'samples': 19924416, 'steps': 103772, 'loss/train': 0.02602362632751465} 08/31/2021 07:56:50 - INFO - __main__ - Step 103774: {'lr': 0.00011100597317899747, 'samples': 19924608, 'steps': 103773, 'loss/train': 0.09040386229753494} 08/31/2021 07:56:50 - INFO - __main__ - Step 103775: {'lr': 0.00011100156225357827, 'samples': 19924800, 'steps': 103774, 'loss/train': 0.42071983218193054} 08/31/2021 07:56:52 - INFO - __main__ - Step 103776: {'lr': 0.00011099715139078962, 'samples': 19924992, 'steps': 103775, 'loss/train': 0.09167429059743881} 08/31/2021 07:56:52 - INFO - __main__ - Step 103777: {'lr': 0.0001109927405906335, 'samples': 19925184, 'steps': 103776, 'loss/train': 1.1629817485809326} 08/31/2021 07:56:53 - INFO - __main__ - Step 103778: {'lr': 0.00011098832985311191, 'samples': 19925376, 'steps': 103777, 'loss/train': 0.7653327584266663} 08/31/2021 07:56:53 - INFO - __main__ - Step 103779: {'lr': 0.00011098391917822684, 'samples': 19925568, 'steps': 103778, 'loss/train': 0.8357661366462708} 08/31/2021 07:56:53 - INFO - __main__ - Step 103780: {'lr': 0.00011097950856598024, 'samples': 19925760, 'steps': 103779, 'loss/train': 0.957642138004303} 08/31/2021 07:56:55 - INFO - __main__ - Step 103781: {'lr': 0.00011097509801637418, 'samples': 19925952, 'steps': 103780, 'loss/train': 0.02628931775689125} 08/31/2021 07:56:55 - INFO - __main__ - Step 103782: {'lr': 0.00011097068752941056, 'samples': 19926144, 'steps': 103781, 'loss/train': 1.446332335472107} 08/31/2021 07:56:56 - INFO - __main__ - Step 103783: {'lr': 0.00011096627710509142, 'samples': 19926336, 'steps': 103782, 'loss/train': 1.1888254880905151} 08/31/2021 07:56:56 - INFO - __main__ - Step 103784: {'lr': 0.0001109618667434187, 'samples': 19926528, 'steps': 103783, 'loss/train': 0.5549772381782532} 08/31/2021 07:56:56 - INFO - __main__ - Step 103785: {'lr': 0.00011095745644439453, 'samples': 19926720, 'steps': 103784, 'loss/train': 1.2301931381225586} 08/31/2021 07:56:58 - INFO - __main__ - Step 103786: {'lr': 0.00011095304620802072, 'samples': 19926912, 'steps': 103785, 'loss/train': 1.1263866424560547} 08/31/2021 07:56:58 - INFO - __main__ - Step 103787: {'lr': 0.00011094863603429928, 'samples': 19927104, 'steps': 103786, 'loss/train': 1.362353801727295} 08/31/2021 07:56:58 - INFO - __main__ - Step 103788: {'lr': 0.00011094422592323224, 'samples': 19927296, 'steps': 103787, 'loss/train': 0.9856191873550415} 08/31/2021 07:56:59 - INFO - __main__ - Step 103789: {'lr': 0.00011093981587482163, 'samples': 19927488, 'steps': 103788, 'loss/train': 1.3475322723388672} 08/31/2021 07:56:59 - INFO - __main__ - Step 103790: {'lr': 0.00011093540588906936, 'samples': 19927680, 'steps': 103789, 'loss/train': 1.0730518102645874} 08/31/2021 07:57:01 - INFO - __main__ - Step 103791: {'lr': 0.00011093099596597744, 'samples': 19927872, 'steps': 103790, 'loss/train': 0.17763064801692963} 08/31/2021 07:57:02 - INFO - __main__ - Step 103792: {'lr': 0.0001109265861055479, 'samples': 19928064, 'steps': 103791, 'loss/train': 0.581875741481781} 08/31/2021 07:57:02 - INFO - __main__ - Step 103793: {'lr': 0.00011092217630778267, 'samples': 19928256, 'steps': 103792, 'loss/train': 1.1135797500610352} 08/31/2021 07:57:02 - INFO - __main__ - Step 103794: {'lr': 0.00011091776657268377, 'samples': 19928448, 'steps': 103793, 'loss/train': 1.55893075466156} 08/31/2021 07:57:03 - INFO - __main__ - Step 103795: {'lr': 0.00011091335690025317, 'samples': 19928640, 'steps': 103794, 'loss/train': 0.9521303176879883} 08/31/2021 07:57:03 - INFO - __main__ - Step 103796: {'lr': 0.00011090894729049286, 'samples': 19928832, 'steps': 103795, 'loss/train': 0.8542739152908325} 08/31/2021 07:57:05 - INFO - __main__ - Step 103797: {'lr': 0.00011090453774340484, 'samples': 19929024, 'steps': 103796, 'loss/train': 0.9203824996948242} 08/31/2021 07:57:05 - INFO - __main__ - Step 103798: {'lr': 0.0001109001282589911, 'samples': 19929216, 'steps': 103797, 'loss/train': 1.0484235286712646} 08/31/2021 07:57:05 - INFO - __main__ - Step 103799: {'lr': 0.00011089571883725369, 'samples': 19929408, 'steps': 103798, 'loss/train': 0.8636024594306946} 08/31/2021 07:57:06 - INFO - __main__ - Step 103800: {'lr': 0.00011089130947819445, 'samples': 19929600, 'steps': 103799, 'loss/train': 1.3173927068710327} 08/31/2021 07:57:06 - INFO - __main__ - Step 103801: {'lr': 0.00011088690018181544, 'samples': 19929792, 'steps': 103800, 'loss/train': 2.261248826980591} 08/31/2021 07:57:08 - INFO - __main__ - Step 103802: {'lr': 0.00011088249094811861, 'samples': 19929984, 'steps': 103801, 'loss/train': 0.6912263631820679} 08/31/2021 07:57:09 - INFO - __main__ - Step 103803: {'lr': 0.00011087808177710603, 'samples': 19930176, 'steps': 103802, 'loss/train': 1.0321674346923828} 08/31/2021 07:57:09 - INFO - __main__ - Step 103804: {'lr': 0.00011087367266877963, 'samples': 19930368, 'steps': 103803, 'loss/train': 1.4369269609451294} 08/31/2021 07:57:09 - INFO - __main__ - Step 103805: {'lr': 0.00011086926362314137, 'samples': 19930560, 'steps': 103804, 'loss/train': 1.2107630968093872} 08/31/2021 07:57:10 - INFO - __main__ - Step 103806: {'lr': 0.0001108648546401933, 'samples': 19930752, 'steps': 103805, 'loss/train': 0.42621320486068726} 08/31/2021 07:57:11 - INFO - __main__ - Step 103807: {'lr': 0.00011086044571993739, 'samples': 19930944, 'steps': 103806, 'loss/train': 0.9924352169036865} 08/31/2021 07:57:12 - INFO - __main__ - Step 103808: {'lr': 0.00011085603686237558, 'samples': 19931136, 'steps': 103807, 'loss/train': 0.8222121000289917} 08/31/2021 07:57:12 - INFO - __main__ - Step 103809: {'lr': 0.00011085162806750992, 'samples': 19931328, 'steps': 103808, 'loss/train': 0.6042539477348328} 08/31/2021 07:57:12 - INFO - __main__ - Step 103810: {'lr': 0.00011084721933534236, 'samples': 19931520, 'steps': 103809, 'loss/train': 1.2125848531723022} 08/31/2021 07:57:13 - INFO - __main__ - Step 103811: {'lr': 0.0001108428106658749, 'samples': 19931712, 'steps': 103810, 'loss/train': 1.1617860794067383} 08/31/2021 07:57:14 - INFO - __main__ - Step 103812: {'lr': 0.00011083840205910964, 'samples': 19931904, 'steps': 103811, 'loss/train': 0.6010311245918274} 08/31/2021 07:57:15 - INFO - __main__ - Step 103813: {'lr': 0.00011083399351504834, 'samples': 19932096, 'steps': 103812, 'loss/train': 1.2438596487045288} 08/31/2021 07:57:15 - INFO - __main__ - Step 103814: {'lr': 0.00011082958503369306, 'samples': 19932288, 'steps': 103813, 'loss/train': 0.31194376945495605} 08/31/2021 07:57:16 - INFO - __main__ - Step 103815: {'lr': 0.00011082517661504584, 'samples': 19932480, 'steps': 103814, 'loss/train': 1.6600558757781982} 08/31/2021 07:57:16 - INFO - __main__ - Step 103816: {'lr': 0.00011082076825910867, 'samples': 19932672, 'steps': 103815, 'loss/train': 0.959213137626648} 08/31/2021 07:57:16 - INFO - __main__ - Step 103817: {'lr': 0.0001108163599658835, 'samples': 19932864, 'steps': 103816, 'loss/train': 1.1638453006744385} 08/31/2021 07:57:18 - INFO - __main__ - Step 103818: {'lr': 0.00011081195173537231, 'samples': 19933056, 'steps': 103817, 'loss/train': 1.2612370252609253} 08/31/2021 07:57:18 - INFO - __main__ - Step 103819: {'lr': 0.00011080754356757714, 'samples': 19933248, 'steps': 103818, 'loss/train': 1.4711486101150513} 08/31/2021 07:57:19 - INFO - __main__ - Step 103820: {'lr': 0.00011080313546249993, 'samples': 19933440, 'steps': 103819, 'loss/train': 1.4235130548477173} 08/31/2021 07:57:19 - INFO - __main__ - Step 103821: {'lr': 0.00011079872742014268, 'samples': 19933632, 'steps': 103820, 'loss/train': 0.8170410394668579} 08/31/2021 07:57:19 - INFO - __main__ - Step 103822: {'lr': 0.00011079431944050738, 'samples': 19933824, 'steps': 103821, 'loss/train': 0.24830396473407745} 08/31/2021 07:57:21 - INFO - __main__ - Step 103823: {'lr': 0.000110789911523596, 'samples': 19934016, 'steps': 103822, 'loss/train': 1.0204917192459106} 08/31/2021 07:57:21 - INFO - __main__ - Step 103824: {'lr': 0.00011078550366941053, 'samples': 19934208, 'steps': 103823, 'loss/train': 1.2720582485198975} 08/31/2021 07:57:22 - INFO - __main__ - Step 103825: {'lr': 0.0001107810958779531, 'samples': 19934400, 'steps': 103824, 'loss/train': 0.9664533734321594} 08/31/2021 07:57:22 - INFO - __main__ - Step 103826: {'lr': 0.00011077668814922543, 'samples': 19934592, 'steps': 103825, 'loss/train': 0.8588270545005798} 08/31/2021 07:57:22 - INFO - __main__ - Step 103827: {'lr': 0.00011077228048322962, 'samples': 19934784, 'steps': 103826, 'loss/train': 1.1771708726882935} 08/31/2021 07:57:24 - INFO - __main__ - Step 103828: {'lr': 0.0001107678728799677, 'samples': 19934976, 'steps': 103827, 'loss/train': 1.2088357210159302} 08/31/2021 07:57:25 - INFO - __main__ - Step 103829: {'lr': 0.00011076346533944162, 'samples': 19935168, 'steps': 103828, 'loss/train': 1.153882622718811} 08/31/2021 07:57:25 - INFO - __main__ - Step 103830: {'lr': 0.00011075905786165339, 'samples': 19935360, 'steps': 103829, 'loss/train': 1.4750980138778687} 08/31/2021 07:57:25 - INFO - __main__ - Step 103831: {'lr': 0.00011075465044660496, 'samples': 19935552, 'steps': 103830, 'loss/train': 1.02236807346344} 08/31/2021 07:57:26 - INFO - __main__ - Step 103832: {'lr': 0.00011075024309429835, 'samples': 19935744, 'steps': 103831, 'loss/train': 0.9933954477310181} 08/31/2021 07:57:27 - INFO - __main__ - Step 103833: {'lr': 0.00011074583580473552, 'samples': 19935936, 'steps': 103832, 'loss/train': 0.9924665689468384} 08/31/2021 07:57:27 - INFO - __main__ - Step 103834: {'lr': 0.00011074142857791846, 'samples': 19936128, 'steps': 103833, 'loss/train': 0.3958439826965332} 08/31/2021 07:57:28 - INFO - __main__ - Step 103835: {'lr': 0.0001107370214138492, 'samples': 19936320, 'steps': 103834, 'loss/train': 0.15646645426750183} 08/31/2021 07:57:28 - INFO - __main__ - Step 103836: {'lr': 0.00011073261431252965, 'samples': 19936512, 'steps': 103835, 'loss/train': 0.18097464740276337} 08/31/2021 07:57:29 - INFO - __main__ - Step 103837: {'lr': 0.00011072820727396186, 'samples': 19936704, 'steps': 103836, 'loss/train': 1.6742583513259888} 08/31/2021 07:57:30 - INFO - __main__ - Step 103838: {'lr': 0.00011072380029814777, 'samples': 19936896, 'steps': 103837, 'loss/train': 1.3121283054351807} 08/31/2021 07:57:31 - INFO - __main__ - Step 103839: {'lr': 0.00011071939338508949, 'samples': 19937088, 'steps': 103838, 'loss/train': 0.9452996253967285} 08/31/2021 07:57:31 - INFO - __main__ - Step 103840: {'lr': 0.00011071498653478881, 'samples': 19937280, 'steps': 103839, 'loss/train': 1.181705355644226} 08/31/2021 07:57:31 - INFO - __main__ - Step 103841: {'lr': 0.00011071057974724782, 'samples': 19937472, 'steps': 103840, 'loss/train': 1.7030855417251587} 08/31/2021 07:57:32 - INFO - __main__ - Step 103842: {'lr': 0.00011070617302246847, 'samples': 19937664, 'steps': 103841, 'loss/train': 0.21277424693107605} 08/31/2021 07:57:33 - INFO - __main__ - Step 103843: {'lr': 0.00011070176636045278, 'samples': 19937856, 'steps': 103842, 'loss/train': 2.9792258739471436} 08/31/2021 07:57:33 - INFO - __main__ - Step 103844: {'lr': 0.00011069735976120274, 'samples': 19938048, 'steps': 103843, 'loss/train': 1.3553638458251953} 08/31/2021 07:57:34 - INFO - __main__ - Step 103845: {'lr': 0.00011069295322472028, 'samples': 19938240, 'steps': 103844, 'loss/train': 0.6234962344169617} 08/31/2021 07:57:34 - INFO - __main__ - Step 103846: {'lr': 0.00011068854675100745, 'samples': 19938432, 'steps': 103845, 'loss/train': 1.8702095746994019} 08/31/2021 07:57:35 - INFO - __main__ - Step 103847: {'lr': 0.00011068414034006621, 'samples': 19938624, 'steps': 103846, 'loss/train': 0.9376929998397827} 08/31/2021 07:57:37 - INFO - __main__ - Step 103848: {'lr': 0.00011067973399189857, 'samples': 19938816, 'steps': 103847, 'loss/train': 1.8633509874343872} 08/31/2021 07:57:37 - INFO - __main__ - Step 103849: {'lr': 0.00011067532770650646, 'samples': 19939008, 'steps': 103848, 'loss/train': 1.363998532295227} 08/31/2021 07:57:37 - INFO - __main__ - Step 103850: {'lr': 0.0001106709214838919, 'samples': 19939200, 'steps': 103849, 'loss/train': 0.5046257376670837} 08/31/2021 07:57:38 - INFO - __main__ - Step 103851: {'lr': 0.00011066651532405689, 'samples': 19939392, 'steps': 103850, 'loss/train': 0.35216808319091797} 08/31/2021 07:57:38 - INFO - __main__ - Step 103852: {'lr': 0.00011066210922700348, 'samples': 19939584, 'steps': 103851, 'loss/train': 1.0893301963806152} 08/31/2021 07:57:39 - INFO - __main__ - Step 103853: {'lr': 0.00011065770319273346, 'samples': 19939776, 'steps': 103852, 'loss/train': 0.7077786922454834} 08/31/2021 07:57:40 - INFO - __main__ - Step 103854: {'lr': 0.00011065329722124898, 'samples': 19939968, 'steps': 103853, 'loss/train': 1.200325846672058} 08/31/2021 07:57:41 - INFO - __main__ - Step 103855: {'lr': 0.00011064889131255192, 'samples': 19940160, 'steps': 103854, 'loss/train': 1.3133143186569214} 08/31/2021 07:57:42 - INFO - __main__ - Step 103856: {'lr': 0.00011064448546664435, 'samples': 19940352, 'steps': 103855, 'loss/train': 0.9146718382835388} 08/31/2021 07:57:42 - INFO - __main__ - Step 103857: {'lr': 0.0001106400796835282, 'samples': 19940544, 'steps': 103856, 'loss/train': 1.3823434114456177} 08/31/2021 07:57:42 - INFO - __main__ - Step 103858: {'lr': 0.0001106356739632055, 'samples': 19940736, 'steps': 103857, 'loss/train': 0.7188156247138977} 08/31/2021 07:57:43 - INFO - __main__ - Step 103859: {'lr': 0.00011063126830567824, 'samples': 19940928, 'steps': 103858, 'loss/train': 1.2121906280517578} 08/31/2021 07:57:44 - INFO - __main__ - Step 103860: {'lr': 0.00011062686271094836, 'samples': 19941120, 'steps': 103859, 'loss/train': 1.2145600318908691} 08/31/2021 07:57:45 - INFO - __main__ - Step 103861: {'lr': 0.00011062245717901784, 'samples': 19941312, 'steps': 103860, 'loss/train': 1.171522617340088} 08/31/2021 07:57:45 - INFO - __main__ - Step 103862: {'lr': 0.0001106180517098887, 'samples': 19941504, 'steps': 103861, 'loss/train': 1.3891578912734985} 08/31/2021 07:57:45 - INFO - __main__ - Step 103863: {'lr': 0.00011061364630356293, 'samples': 19941696, 'steps': 103862, 'loss/train': 1.1718900203704834} 08/31/2021 07:57:46 - INFO - __main__ - Step 103864: {'lr': 0.00011060924096004248, 'samples': 19941888, 'steps': 103863, 'loss/train': 0.023952241986989975} 08/31/2021 07:57:47 - INFO - __main__ - Step 103865: {'lr': 0.00011060483567932938, 'samples': 19942080, 'steps': 103864, 'loss/train': 0.866555392742157} 08/31/2021 07:57:48 - INFO - __main__ - Step 103866: {'lr': 0.00011060043046142568, 'samples': 19942272, 'steps': 103865, 'loss/train': 2.159756660461426} 08/31/2021 07:57:48 - INFO - __main__ - Step 103867: {'lr': 0.00011059602530633317, 'samples': 19942464, 'steps': 103866, 'loss/train': 1.1219121217727661} 08/31/2021 07:57:48 - INFO - __main__ - Step 103868: {'lr': 0.00011059162021405394, 'samples': 19942656, 'steps': 103867, 'loss/train': 2.1746513843536377} 08/31/2021 07:57:49 - INFO - __main__ - Step 103869: {'lr': 0.00011058721518458997, 'samples': 19942848, 'steps': 103868, 'loss/train': 0.9445266723632812} 08/31/2021 07:57:50 - INFO - __main__ - Step 103870: {'lr': 0.00011058281021794325, 'samples': 19943040, 'steps': 103869, 'loss/train': 0.9344762563705444} 08/31/2021 07:57:51 - INFO - __main__ - Step 103871: {'lr': 0.00011057840531411578, 'samples': 19943232, 'steps': 103870, 'loss/train': 1.9120237827301025} 08/31/2021 07:57:51 - INFO - __main__ - Step 103872: {'lr': 0.00011057400047310954, 'samples': 19943424, 'steps': 103871, 'loss/train': 1.3680646419525146} 08/31/2021 07:57:51 - INFO - __main__ - Step 103873: {'lr': 0.00011056959569492647, 'samples': 19943616, 'steps': 103872, 'loss/train': 1.1298469305038452} 08/31/2021 07:57:52 - INFO - __main__ - Step 103874: {'lr': 0.00011056519097956861, 'samples': 19943808, 'steps': 103873, 'loss/train': 0.6537736058235168} 08/31/2021 07:57:53 - INFO - __main__ - Step 103875: {'lr': 0.00011056078632703789, 'samples': 19944000, 'steps': 103874, 'loss/train': 0.9944978356361389} 08/31/2021 07:57:54 - INFO - __main__ - Step 103876: {'lr': 0.00011055638173733637, 'samples': 19944192, 'steps': 103875, 'loss/train': 1.6120456457138062} 08/31/2021 07:57:54 - INFO - __main__ - Step 103877: {'lr': 0.00011055197721046598, 'samples': 19944384, 'steps': 103876, 'loss/train': 1.2137269973754883} 08/31/2021 07:57:54 - INFO - __main__ - Step 103878: {'lr': 0.0001105475727464287, 'samples': 19944576, 'steps': 103877, 'loss/train': 0.728225827217102} 08/31/2021 07:57:55 - INFO - __main__ - Step 103879: {'lr': 0.00011054316834522665, 'samples': 19944768, 'steps': 103878, 'loss/train': 1.6511733531951904} 08/31/2021 07:57:56 - INFO - __main__ - Step 103880: {'lr': 0.00011053876400686158, 'samples': 19944960, 'steps': 103879, 'loss/train': 1.490509271621704} 08/31/2021 07:57:57 - INFO - __main__ - Step 103881: {'lr': 0.0001105343597313356, 'samples': 19945152, 'steps': 103880, 'loss/train': 1.1468544006347656} 08/31/2021 07:57:57 - INFO - __main__ - Step 103882: {'lr': 0.00011052995551865069, 'samples': 19945344, 'steps': 103881, 'loss/train': 0.3537570536136627} 08/31/2021 07:57:58 - INFO - __main__ - Step 103883: {'lr': 0.00011052555136880885, 'samples': 19945536, 'steps': 103882, 'loss/train': 1.1088751554489136} 08/31/2021 07:57:58 - INFO - __main__ - Step 103884: {'lr': 0.00011052114728181201, 'samples': 19945728, 'steps': 103883, 'loss/train': 0.9740763306617737} 08/31/2021 07:57:58 - INFO - __main__ - Step 103885: {'lr': 0.0001105167432576622, 'samples': 19945920, 'steps': 103884, 'loss/train': 1.4315829277038574} 08/31/2021 07:58:00 - INFO - __main__ - Step 103886: {'lr': 0.0001105123392963614, 'samples': 19946112, 'steps': 103885, 'loss/train': 0.9420982003211975} 08/31/2021 07:58:00 - INFO - __main__ - Step 103887: {'lr': 0.00011050793539791157, 'samples': 19946304, 'steps': 103886, 'loss/train': 0.7916200757026672} 08/31/2021 07:58:01 - INFO - __main__ - Step 103888: {'lr': 0.00011050353156231474, 'samples': 19946496, 'steps': 103887, 'loss/train': 0.8583735227584839} 08/31/2021 07:58:01 - INFO - __main__ - Step 103889: {'lr': 0.00011049912778957283, 'samples': 19946688, 'steps': 103888, 'loss/train': 1.156554937362671} 08/31/2021 07:58:01 - INFO - __main__ - Step 103890: {'lr': 0.00011049472407968788, 'samples': 19946880, 'steps': 103889, 'loss/train': 0.7889857888221741} 08/31/2021 07:58:03 - INFO - __main__ - Step 103891: {'lr': 0.00011049032043266186, 'samples': 19947072, 'steps': 103890, 'loss/train': 0.812947690486908} 08/31/2021 07:58:04 - INFO - __main__ - Step 103892: {'lr': 0.00011048591684849677, 'samples': 19947264, 'steps': 103891, 'loss/train': 1.264509916305542} 08/31/2021 07:58:04 - INFO - __main__ - Step 103893: {'lr': 0.00011048151332719461, 'samples': 19947456, 'steps': 103892, 'loss/train': 1.6175960302352905} 08/31/2021 07:58:04 - INFO - __main__ - Step 103894: {'lr': 0.00011047710986875729, 'samples': 19947648, 'steps': 103893, 'loss/train': 1.1165094375610352} 08/31/2021 07:58:05 - INFO - __main__ - Step 103895: {'lr': 0.0001104727064731868, 'samples': 19947840, 'steps': 103894, 'loss/train': 1.3912910223007202} 08/31/2021 07:58:06 - INFO - __main__ - Step 103896: {'lr': 0.00011046830314048514, 'samples': 19948032, 'steps': 103895, 'loss/train': 1.6665334701538086} 08/31/2021 07:58:07 - INFO - __main__ - Step 103897: {'lr': 0.00011046389987065433, 'samples': 19948224, 'steps': 103896, 'loss/train': 1.620702862739563} 08/31/2021 07:58:07 - INFO - __main__ - Step 103898: {'lr': 0.00011045949666369634, 'samples': 19948416, 'steps': 103897, 'loss/train': 0.9216617941856384} 08/31/2021 07:58:07 - INFO - __main__ - Step 103899: {'lr': 0.00011045509351961314, 'samples': 19948608, 'steps': 103898, 'loss/train': 1.0185381174087524} 08/31/2021 07:58:08 - INFO - __main__ - Step 103900: {'lr': 0.00011045069043840673, 'samples': 19948800, 'steps': 103899, 'loss/train': 1.0095850229263306} 08/31/2021 07:58:08 - INFO - __main__ - Step 103901: {'lr': 0.00011044628742007909, 'samples': 19948992, 'steps': 103900, 'loss/train': 1.0296231508255005} 08/31/2021 07:58:10 - INFO - __main__ - Step 103902: {'lr': 0.00011044188446463218, 'samples': 19949184, 'steps': 103901, 'loss/train': 0.6883531212806702} 08/31/2021 07:58:10 - INFO - __main__ - Step 103903: {'lr': 0.00011043748157206802, 'samples': 19949376, 'steps': 103902, 'loss/train': 1.1474854946136475} 08/31/2021 07:58:10 - INFO - __main__ - Step 103904: {'lr': 0.00011043307874238856, 'samples': 19949568, 'steps': 103903, 'loss/train': 2.212127208709717} 08/31/2021 07:58:11 - INFO - __main__ - Step 103905: {'lr': 0.0001104286759755958, 'samples': 19949760, 'steps': 103904, 'loss/train': 1.241202712059021} 08/31/2021 07:58:11 - INFO - __main__ - Step 103906: {'lr': 0.00011042427327169183, 'samples': 19949952, 'steps': 103905, 'loss/train': 0.897288978099823} 08/31/2021 07:58:13 - INFO - __main__ - Step 103907: {'lr': 0.00011041987063067843, 'samples': 19950144, 'steps': 103906, 'loss/train': 0.02655400149524212} 08/31/2021 07:58:14 - INFO - __main__ - Step 103908: {'lr': 0.0001104154680525577, 'samples': 19950336, 'steps': 103907, 'loss/train': 1.2207083702087402} 08/31/2021 07:58:14 - INFO - __main__ - Step 103909: {'lr': 0.00011041106553733157, 'samples': 19950528, 'steps': 103908, 'loss/train': 1.0494681596755981} 08/31/2021 07:58:15 - INFO - __main__ - Step 103910: {'lr': 0.00011040666308500211, 'samples': 19950720, 'steps': 103909, 'loss/train': 0.10171832144260406} 08/31/2021 07:58:15 - INFO - __main__ - Step 103911: {'lr': 0.00011040226069557121, 'samples': 19950912, 'steps': 103910, 'loss/train': 0.9136308431625366} 08/31/2021 07:58:16 - INFO - __main__ - Step 103912: {'lr': 0.0001103978583690409, 'samples': 19951104, 'steps': 103911, 'loss/train': 1.1221940517425537} 08/31/2021 07:58:17 - INFO - __main__ - Step 103913: {'lr': 0.00011039345610541317, 'samples': 19951296, 'steps': 103912, 'loss/train': 0.6975702047348022} 08/31/2021 07:58:17 - INFO - __main__ - Step 103914: {'lr': 0.00011038905390469, 'samples': 19951488, 'steps': 103913, 'loss/train': 0.22587424516677856} 08/31/2021 07:58:17 - INFO - __main__ - Step 103915: {'lr': 0.00011038465176687337, 'samples': 19951680, 'steps': 103914, 'loss/train': 1.059319019317627} 08/31/2021 07:58:18 - INFO - __main__ - Step 103916: {'lr': 0.00011038024969196528, 'samples': 19951872, 'steps': 103915, 'loss/train': 0.48540279269218445} 08/31/2021 07:58:20 - INFO - __main__ - Step 103917: {'lr': 0.00011037584767996767, 'samples': 19952064, 'steps': 103916, 'loss/train': 0.6662756204605103} 08/31/2021 07:58:20 - INFO - __main__ - Step 103918: {'lr': 0.00011037144573088253, 'samples': 19952256, 'steps': 103917, 'loss/train': 1.1110432147979736} 08/31/2021 07:58:20 - INFO - __main__ - Step 103919: {'lr': 0.00011036704384471189, 'samples': 19952448, 'steps': 103918, 'loss/train': 1.126396894454956} 08/31/2021 07:58:21 - INFO - __main__ - Step 103920: {'lr': 0.00011036264202145779, 'samples': 19952640, 'steps': 103919, 'loss/train': 1.817020058631897} 08/31/2021 07:58:21 - INFO - __main__ - Step 103921: {'lr': 0.00011035824026112204, 'samples': 19952832, 'steps': 103920, 'loss/train': 0.01621810719370842} 08/31/2021 07:58:21 - INFO - __main__ - Step 103922: {'lr': 0.0001103538385637067, 'samples': 19953024, 'steps': 103921, 'loss/train': 0.016989417374134064} 08/31/2021 07:58:23 - INFO - __main__ - Step 103923: {'lr': 0.00011034943692921378, 'samples': 19953216, 'steps': 103922, 'loss/train': 1.0209543704986572} 08/31/2021 07:58:23 - INFO - __main__ - Step 103924: {'lr': 0.00011034503535764525, 'samples': 19953408, 'steps': 103923, 'loss/train': 0.13306251168251038} 08/31/2021 07:58:24 - INFO - __main__ - Step 103925: {'lr': 0.00011034063384900309, 'samples': 19953600, 'steps': 103924, 'loss/train': 1.1024177074432373} 08/31/2021 07:58:24 - INFO - __main__ - Step 103926: {'lr': 0.00011033623240328928, 'samples': 19953792, 'steps': 103925, 'loss/train': 1.5880951881408691} 08/31/2021 07:58:25 - INFO - __main__ - Step 103927: {'lr': 0.00011033183102050581, 'samples': 19953984, 'steps': 103926, 'loss/train': 1.099786400794983} 08/31/2021 07:58:26 - INFO - __main__ - Step 103928: {'lr': 0.00011032742970065466, 'samples': 19954176, 'steps': 103927, 'loss/train': 0.8861891627311707} 08/31/2021 07:58:26 - INFO - __main__ - Step 103929: {'lr': 0.00011032302844373781, 'samples': 19954368, 'steps': 103928, 'loss/train': 1.0507311820983887} 08/31/2021 07:58:27 - INFO - __main__ - Step 103930: {'lr': 0.00011031862724975724, 'samples': 19954560, 'steps': 103929, 'loss/train': 2.0865724086761475} 08/31/2021 07:58:27 - INFO - __main__ - Step 103931: {'lr': 0.00011031422611871497, 'samples': 19954752, 'steps': 103930, 'loss/train': 1.058713674545288} 08/31/2021 07:58:27 - INFO - __main__ - Step 103932: {'lr': 0.00011030982505061293, 'samples': 19954944, 'steps': 103931, 'loss/train': 0.848630964756012} 08/31/2021 07:58:29 - INFO - __main__ - Step 103933: {'lr': 0.00011030542404545325, 'samples': 19955136, 'steps': 103932, 'loss/train': 1.3450331687927246} 08/31/2021 07:58:30 - INFO - __main__ - Step 103934: {'lr': 0.00011030102310323767, 'samples': 19955328, 'steps': 103933, 'loss/train': 0.6758243441581726} 08/31/2021 07:58:30 - INFO - __main__ - Step 103935: {'lr': 0.0001102966222239683, 'samples': 19955520, 'steps': 103934, 'loss/train': 1.9098881483078003} 08/31/2021 07:58:30 - INFO - __main__ - Step 103936: {'lr': 0.0001102922214076471, 'samples': 19955712, 'steps': 103935, 'loss/train': 0.7419423460960388} 08/31/2021 07:58:31 - INFO - __main__ - Step 103937: {'lr': 0.00011028782065427608, 'samples': 19955904, 'steps': 103936, 'loss/train': 2.3951919078826904} 08/31/2021 07:58:32 - INFO - __main__ - Step 103938: {'lr': 0.00011028341996385724, 'samples': 19956096, 'steps': 103937, 'loss/train': 1.277425765991211} 08/31/2021 07:58:33 - INFO - __main__ - Step 103939: {'lr': 0.0001102790193363925, 'samples': 19956288, 'steps': 103938, 'loss/train': 1.2308502197265625} 08/31/2021 07:58:33 - INFO - __main__ - Step 103940: {'lr': 0.00011027461877188388, 'samples': 19956480, 'steps': 103939, 'loss/train': 1.7226297855377197} 08/31/2021 07:58:33 - INFO - __main__ - Step 103941: {'lr': 0.00011027021827033337, 'samples': 19956672, 'steps': 103940, 'loss/train': 1.1391640901565552} 08/31/2021 07:58:34 - INFO - __main__ - Step 103942: {'lr': 0.00011026581783174298, 'samples': 19956864, 'steps': 103941, 'loss/train': 0.7893560528755188} 08/31/2021 07:58:34 - INFO - __main__ - Step 103943: {'lr': 0.00011026141745611459, 'samples': 19957056, 'steps': 103942, 'loss/train': 1.7811659574508667} 08/31/2021 07:58:36 - INFO - __main__ - Step 103944: {'lr': 0.0001102570171434503, 'samples': 19957248, 'steps': 103943, 'loss/train': 1.247570276260376} 08/31/2021 07:58:36 - INFO - __main__ - Step 103945: {'lr': 0.00011025261689375201, 'samples': 19957440, 'steps': 103944, 'loss/train': 2.2426092624664307} 08/31/2021 07:58:36 - INFO - __main__ - Step 103946: {'lr': 0.00011024821670702184, 'samples': 19957632, 'steps': 103945, 'loss/train': 1.1947335004806519} 08/31/2021 07:58:37 - INFO - __main__ - Step 103947: {'lr': 0.00011024381658326158, 'samples': 19957824, 'steps': 103946, 'loss/train': 1.0877206325531006} 08/31/2021 07:58:37 - INFO - __main__ - Step 103948: {'lr': 0.00011023941652247329, 'samples': 19958016, 'steps': 103947, 'loss/train': 1.067050576210022} 08/31/2021 07:58:39 - INFO - __main__ - Step 103949: {'lr': 0.00011023501652465895, 'samples': 19958208, 'steps': 103948, 'loss/train': 1.2328743934631348} 08/31/2021 07:58:39 - INFO - __main__ - Step 103950: {'lr': 0.00011023061658982059, 'samples': 19958400, 'steps': 103949, 'loss/train': 0.02557509019970894} 08/31/2021 07:58:40 - INFO - __main__ - Step 103951: {'lr': 0.00011022621671796013, 'samples': 19958592, 'steps': 103950, 'loss/train': 1.586539387702942} 08/31/2021 07:58:40 - INFO - __main__ - Step 103952: {'lr': 0.0001102218169090796, 'samples': 19958784, 'steps': 103951, 'loss/train': 1.5726412534713745} 08/31/2021 07:58:40 - INFO - __main__ - Step 103953: {'lr': 0.00011021741716318093, 'samples': 19958976, 'steps': 103952, 'loss/train': 0.8888742327690125} 08/31/2021 07:58:42 - INFO - __main__ - Step 103954: {'lr': 0.00011021301748026616, 'samples': 19959168, 'steps': 103953, 'loss/train': 0.9658700823783875} 08/31/2021 07:58:43 - INFO - __main__ - Step 103955: {'lr': 0.00011020861786033723, 'samples': 19959360, 'steps': 103954, 'loss/train': 1.3966320753097534} 08/31/2021 07:58:43 - INFO - __main__ - Step 103956: {'lr': 0.00011020421830339617, 'samples': 19959552, 'steps': 103955, 'loss/train': 1.942691445350647} 08/31/2021 07:58:43 - INFO - __main__ - Step 103957: {'lr': 0.00011019981880944491, 'samples': 19959744, 'steps': 103956, 'loss/train': 1.0805062055587769} 08/31/2021 07:58:44 - INFO - __main__ - Step 103958: {'lr': 0.00011019541937848546, 'samples': 19959936, 'steps': 103957, 'loss/train': 1.095350742340088} 08/31/2021 07:58:44 - INFO - __main__ - Step 103959: {'lr': 0.00011019102001051979, 'samples': 19960128, 'steps': 103958, 'loss/train': 0.6865413188934326} 08/31/2021 07:58:46 - INFO - __main__ - Step 103960: {'lr': 0.00011018662070554999, 'samples': 19960320, 'steps': 103959, 'loss/train': 0.13792645931243896} 08/31/2021 07:58:46 - INFO - __main__ - Step 103961: {'lr': 0.00011018222146357785, 'samples': 19960512, 'steps': 103960, 'loss/train': 1.3832826614379883} 08/31/2021 07:58:46 - INFO - __main__ - Step 103962: {'lr': 0.00011017782228460544, 'samples': 19960704, 'steps': 103961, 'loss/train': 0.9211254715919495} 08/31/2021 07:58:47 - INFO - __main__ - Step 103963: {'lr': 0.00011017342316863474, 'samples': 19960896, 'steps': 103962, 'loss/train': 0.7109171152114868} 08/31/2021 07:58:47 - INFO - __main__ - Step 103964: {'lr': 0.00011016902411566774, 'samples': 19961088, 'steps': 103963, 'loss/train': 1.1415799856185913} 08/31/2021 07:58:49 - INFO - __main__ - Step 103965: {'lr': 0.0001101646251257064, 'samples': 19961280, 'steps': 103964, 'loss/train': 0.15317505598068237} 08/31/2021 07:58:50 - INFO - __main__ - Step 103966: {'lr': 0.00011016022619875276, 'samples': 19961472, 'steps': 103965, 'loss/train': 1.1878015995025635} 08/31/2021 07:58:50 - INFO - __main__ - Step 103967: {'lr': 0.00011015582733480875, 'samples': 19961664, 'steps': 103966, 'loss/train': 1.4306169748306274} 08/31/2021 07:58:51 - INFO - __main__ - Step 103968: {'lr': 0.00011015142853387636, 'samples': 19961856, 'steps': 103967, 'loss/train': 1.4536592960357666} 08/31/2021 07:58:51 - INFO - __main__ - Step 103969: {'lr': 0.00011014702979595759, 'samples': 19962048, 'steps': 103968, 'loss/train': 1.409221887588501} 08/31/2021 07:58:52 - INFO - __main__ - Step 103970: {'lr': 0.00011014263112105441, 'samples': 19962240, 'steps': 103969, 'loss/train': 1.3131816387176514} 08/31/2021 07:58:53 - INFO - __main__ - Step 103971: {'lr': 0.0001101382325091688, 'samples': 19962432, 'steps': 103970, 'loss/train': 1.102254867553711} 08/31/2021 07:58:53 - INFO - __main__ - Step 103972: {'lr': 0.00011013383396030271, 'samples': 19962624, 'steps': 103971, 'loss/train': 1.8780990839004517} 08/31/2021 07:58:54 - INFO - __main__ - Step 103973: {'lr': 0.00011012943547445828, 'samples': 19962816, 'steps': 103972, 'loss/train': 1.499772310256958} 08/31/2021 07:58:54 - INFO - __main__ - Step 103974: {'lr': 0.00011012503705163729, 'samples': 19963008, 'steps': 103973, 'loss/train': 1.2184967994689941} 08/31/2021 07:58:56 - INFO - __main__ - Step 103975: {'lr': 0.00011012063869184177, 'samples': 19963200, 'steps': 103974, 'loss/train': 1.2895798683166504} 08/31/2021 07:58:56 - INFO - __main__ - Step 103976: {'lr': 0.00011011624039507376, 'samples': 19963392, 'steps': 103975, 'loss/train': 0.027140870690345764} 08/31/2021 07:58:57 - INFO - __main__ - Step 103977: {'lr': 0.00011011184216133518, 'samples': 19963584, 'steps': 103976, 'loss/train': 0.015309431590139866} 08/31/2021 07:58:57 - INFO - __main__ - Step 103978: {'lr': 0.00011010744399062808, 'samples': 19963776, 'steps': 103977, 'loss/train': 1.394222617149353} 08/31/2021 07:58:57 - INFO - __main__ - Step 103979: {'lr': 0.00011010304588295439, 'samples': 19963968, 'steps': 103978, 'loss/train': 1.1841259002685547} 08/31/2021 07:58:58 - INFO - __main__ - Step 103980: {'lr': 0.0001100986478383161, 'samples': 19964160, 'steps': 103979, 'loss/train': 1.3981984853744507} 08/31/2021 07:58:59 - INFO - __main__ - Step 103981: {'lr': 0.00011009424985671521, 'samples': 19964352, 'steps': 103980, 'loss/train': 0.4471179246902466} 08/31/2021 07:59:00 - INFO - __main__ - Step 103982: {'lr': 0.00011008985193815371, 'samples': 19964544, 'steps': 103981, 'loss/train': 1.1501718759536743} 08/31/2021 07:59:00 - INFO - __main__ - Step 103983: {'lr': 0.00011008545408263354, 'samples': 19964736, 'steps': 103982, 'loss/train': 0.993286669254303} 08/31/2021 07:59:00 - INFO - __main__ - Step 103984: {'lr': 0.00011008105629015672, 'samples': 19964928, 'steps': 103983, 'loss/train': 0.9113123416900635} 08/31/2021 07:59:01 - INFO - __main__ - Step 103985: {'lr': 0.00011007665856072521, 'samples': 19965120, 'steps': 103984, 'loss/train': 1.079293966293335} 08/31/2021 07:59:01 - INFO - __main__ - Step 103986: {'lr': 0.000110072260894341, 'samples': 19965312, 'steps': 103985, 'loss/train': 2.1858508586883545} 08/31/2021 07:59:03 - INFO - __main__ - Step 103987: {'lr': 0.00011006786329100615, 'samples': 19965504, 'steps': 103986, 'loss/train': 1.4245140552520752} 08/31/2021 07:59:03 - INFO - __main__ - Step 103988: {'lr': 0.00011006346575072249, 'samples': 19965696, 'steps': 103987, 'loss/train': 0.5404672622680664} 08/31/2021 07:59:03 - INFO - __main__ - Step 103989: {'lr': 0.00011005906827349204, 'samples': 19965888, 'steps': 103988, 'loss/train': 0.7784343361854553} 08/31/2021 07:59:04 - INFO - __main__ - Step 103990: {'lr': 0.00011005467085931683, 'samples': 19966080, 'steps': 103989, 'loss/train': 0.881203293800354} 08/31/2021 07:59:04 - INFO - __main__ - Step 103991: {'lr': 0.00011005027350819886, 'samples': 19966272, 'steps': 103990, 'loss/train': 0.8822658061981201} 08/31/2021 07:59:06 - INFO - __main__ - Step 103992: {'lr': 0.00011004587622014003, 'samples': 19966464, 'steps': 103991, 'loss/train': 1.1107524633407593} 08/31/2021 07:59:06 - INFO - __main__ - Step 103993: {'lr': 0.00011004147899514239, 'samples': 19966656, 'steps': 103992, 'loss/train': 0.9397068023681641} 08/31/2021 07:59:07 - INFO - __main__ - Step 103994: {'lr': 0.0001100370818332079, 'samples': 19966848, 'steps': 103993, 'loss/train': 1.2919217348098755} 08/31/2021 07:59:07 - INFO - __main__ - Step 103995: {'lr': 0.00011003268473433853, 'samples': 19967040, 'steps': 103994, 'loss/train': 0.1719575971364975} 08/31/2021 07:59:07 - INFO - __main__ - Step 103996: {'lr': 0.00011002828769853628, 'samples': 19967232, 'steps': 103995, 'loss/train': 1.3338285684585571} 08/31/2021 07:59:09 - INFO - __main__ - Step 103997: {'lr': 0.00011002389072580313, 'samples': 19967424, 'steps': 103996, 'loss/train': 0.6975773572921753} 08/31/2021 07:59:09 - INFO - __main__ - Step 103998: {'lr': 0.00011001949381614115, 'samples': 19967616, 'steps': 103997, 'loss/train': 0.8829681277275085} 08/31/2021 07:59:10 - INFO - __main__ - Step 103999: {'lr': 0.00011001509696955211, 'samples': 19967808, 'steps': 103998, 'loss/train': 0.6314629912376404} 08/31/2021 07:59:10 - INFO - __main__ - Step 104000: {'lr': 0.00011001070018603815, 'samples': 19968000, 'steps': 103999, 'loss/train': 0.460904598236084} 08/31/2021 07:59:10 - INFO - __main__ - Step 104001: {'lr': 0.00011000630346560118, 'samples': 19968192, 'steps': 104000, 'loss/train': 1.3066576719284058} 08/31/2021 07:59:12 - INFO - __main__ - Step 104002: {'lr': 0.0001100019068082432, 'samples': 19968384, 'steps': 104001, 'loss/train': 1.0025854110717773} 08/31/2021 07:59:12 - INFO - __main__ - Step 104003: {'lr': 0.00010999751021396621, 'samples': 19968576, 'steps': 104002, 'loss/train': 1.076770544052124} 08/31/2021 07:59:12 - INFO - __main__ - Step 104004: {'lr': 0.00010999311368277218, 'samples': 19968768, 'steps': 104003, 'loss/train': 0.1330661028623581} 08/31/2021 07:59:13 - INFO - __main__ - Step 104005: {'lr': 0.00010998871721466311, 'samples': 19968960, 'steps': 104004, 'loss/train': 1.266283392906189} 08/31/2021 07:59:13 - INFO - __main__ - Step 104006: {'lr': 0.00010998432080964093, 'samples': 19969152, 'steps': 104005, 'loss/train': 0.5966111421585083} 08/31/2021 07:59:13 - INFO - __main__ - Step 104007: {'lr': 0.00010997992446770769, 'samples': 19969344, 'steps': 104006, 'loss/train': 0.9257500767707825} 08/31/2021 07:59:15 - INFO - __main__ - Step 104008: {'lr': 0.0001099755281888653, 'samples': 19969536, 'steps': 104007, 'loss/train': 1.616864800453186} 08/31/2021 07:59:16 - INFO - __main__ - Step 104009: {'lr': 0.0001099711319731159, 'samples': 19969728, 'steps': 104008, 'loss/train': 1.2825498580932617} 08/31/2021 07:59:16 - INFO - __main__ - Step 104010: {'lr': 0.00010996673582046124, 'samples': 19969920, 'steps': 104009, 'loss/train': 0.038393784314394} 08/31/2021 07:59:16 - INFO - __main__ - Step 104011: {'lr': 0.00010996233973090342, 'samples': 19970112, 'steps': 104010, 'loss/train': 1.1317776441574097} 08/31/2021 07:59:17 - INFO - __main__ - Step 104012: {'lr': 0.0001099579437044444, 'samples': 19970304, 'steps': 104011, 'loss/train': 1.2603415250778198} 08/31/2021 07:59:18 - INFO - __main__ - Step 104013: {'lr': 0.00010995354774108615, 'samples': 19970496, 'steps': 104012, 'loss/train': 0.07364638894796371} 08/31/2021 07:59:19 - INFO - __main__ - Step 104014: {'lr': 0.00010994915184083071, 'samples': 19970688, 'steps': 104013, 'loss/train': 1.170803427696228} 08/31/2021 07:59:19 - INFO - __main__ - Step 104015: {'lr': 0.00010994475600367998, 'samples': 19970880, 'steps': 104014, 'loss/train': 1.2204183340072632} 08/31/2021 07:59:20 - INFO - __main__ - Step 104016: {'lr': 0.00010994036022963602, 'samples': 19971072, 'steps': 104015, 'loss/train': 1.4724262952804565} 08/31/2021 07:59:20 - INFO - __main__ - Step 104017: {'lr': 0.00010993596451870074, 'samples': 19971264, 'steps': 104016, 'loss/train': 0.7921647429466248} 08/31/2021 07:59:22 - INFO - __main__ - Step 104018: {'lr': 0.00010993156887087619, 'samples': 19971456, 'steps': 104017, 'loss/train': 1.2479619979858398} 08/31/2021 07:59:22 - INFO - __main__ - Step 104019: {'lr': 0.00010992717328616427, 'samples': 19971648, 'steps': 104018, 'loss/train': 0.661708414554596} 08/31/2021 07:59:23 - INFO - __main__ - Step 104020: {'lr': 0.00010992277776456713, 'samples': 19971840, 'steps': 104019, 'loss/train': 2.3777594566345215} 08/31/2021 07:59:23 - INFO - __main__ - Step 104021: {'lr': 0.0001099183823060865, 'samples': 19972032, 'steps': 104020, 'loss/train': 0.7332015633583069} 08/31/2021 07:59:23 - INFO - __main__ - Step 104022: {'lr': 0.00010991398691072452, 'samples': 19972224, 'steps': 104021, 'loss/train': 1.0295244455337524} 08/31/2021 07:59:24 - INFO - __main__ - Step 104023: {'lr': 0.00010990959157848312, 'samples': 19972416, 'steps': 104022, 'loss/train': 1.2435979843139648} 08/31/2021 07:59:26 - INFO - __main__ - Step 104024: {'lr': 0.0001099051963093643, 'samples': 19972608, 'steps': 104023, 'loss/train': 1.01216459274292} 08/31/2021 07:59:26 - INFO - __main__ - Step 104025: {'lr': 0.00010990080110337003, 'samples': 19972800, 'steps': 104024, 'loss/train': 0.5797045826911926} 08/31/2021 07:59:27 - INFO - __main__ - Step 104026: {'lr': 0.0001098964059605023, 'samples': 19972992, 'steps': 104025, 'loss/train': 0.2790169417858124} 08/31/2021 07:59:27 - INFO - __main__ - Step 104027: {'lr': 0.00010989201088076308, 'samples': 19973184, 'steps': 104026, 'loss/train': 0.9822050929069519} 08/31/2021 07:59:27 - INFO - __main__ - Step 104028: {'lr': 0.00010988761586415438, 'samples': 19973376, 'steps': 104027, 'loss/train': 0.1067906990647316} 08/31/2021 07:59:28 - INFO - __main__ - Step 104029: {'lr': 0.00010988322091067816, 'samples': 19973568, 'steps': 104028, 'loss/train': 1.9949396848678589} 08/31/2021 07:59:29 - INFO - __main__ - Step 104030: {'lr': 0.00010987882602033635, 'samples': 19973760, 'steps': 104029, 'loss/train': 1.8899563550949097} 08/31/2021 07:59:30 - INFO - __main__ - Step 104031: {'lr': 0.00010987443119313111, 'samples': 19973952, 'steps': 104030, 'loss/train': 1.434897780418396} 08/31/2021 07:59:30 - INFO - __main__ - Step 104032: {'lr': 0.00010987003642906421, 'samples': 19974144, 'steps': 104031, 'loss/train': 1.4085291624069214} 08/31/2021 07:59:30 - INFO - __main__ - Step 104033: {'lr': 0.00010986564172813768, 'samples': 19974336, 'steps': 104032, 'loss/train': 0.49712106585502625} 08/31/2021 07:59:31 - INFO - __main__ - Step 104034: {'lr': 0.00010986124709035356, 'samples': 19974528, 'steps': 104033, 'loss/train': 0.5291520953178406} 08/31/2021 07:59:32 - INFO - __main__ - Step 104035: {'lr': 0.00010985685251571376, 'samples': 19974720, 'steps': 104034, 'loss/train': 1.608048439025879} 08/31/2021 07:59:33 - INFO - __main__ - Step 104036: {'lr': 0.00010985245800422033, 'samples': 19974912, 'steps': 104035, 'loss/train': 1.2413805723190308} 08/31/2021 07:59:33 - INFO - __main__ - Step 104037: {'lr': 0.0001098480635558752, 'samples': 19975104, 'steps': 104036, 'loss/train': 1.7728180885314941} 08/31/2021 07:59:33 - INFO - __main__ - Step 104038: {'lr': 0.0001098436691706804, 'samples': 19975296, 'steps': 104037, 'loss/train': 0.8928073644638062} 08/31/2021 07:59:34 - INFO - __main__ - Step 104039: {'lr': 0.00010983927484863784, 'samples': 19975488, 'steps': 104038, 'loss/train': 1.3793718814849854} 08/31/2021 07:59:35 - INFO - __main__ - Step 104040: {'lr': 0.00010983488058974955, 'samples': 19975680, 'steps': 104039, 'loss/train': 1.1986380815505981} 08/31/2021 07:59:36 - INFO - __main__ - Step 104041: {'lr': 0.00010983048639401752, 'samples': 19975872, 'steps': 104040, 'loss/train': 0.19695758819580078} 08/31/2021 07:59:36 - INFO - __main__ - Step 104042: {'lr': 0.0001098260922614438, 'samples': 19976064, 'steps': 104041, 'loss/train': 1.0234415531158447} 08/31/2021 07:59:36 - INFO - __main__ - Step 104043: {'lr': 0.00010982169819203017, 'samples': 19976256, 'steps': 104042, 'loss/train': 1.1981706619262695} 08/31/2021 07:59:37 - INFO - __main__ - Step 104044: {'lr': 0.00010981730418577873, 'samples': 19976448, 'steps': 104043, 'loss/train': 0.22485613822937012} 08/31/2021 07:59:37 - INFO - __main__ - Step 104045: {'lr': 0.00010981291024269144, 'samples': 19976640, 'steps': 104044, 'loss/train': 0.7614938616752625} 08/31/2021 07:59:39 - INFO - __main__ - Step 104046: {'lr': 0.00010980851636277031, 'samples': 19976832, 'steps': 104045, 'loss/train': 0.9890492558479309} 08/31/2021 07:59:39 - INFO - __main__ - Step 104047: {'lr': 0.00010980412254601729, 'samples': 19977024, 'steps': 104046, 'loss/train': 0.22345376014709473} 08/31/2021 07:59:39 - INFO - __main__ - Step 104048: {'lr': 0.00010979972879243436, 'samples': 19977216, 'steps': 104047, 'loss/train': 0.6700292825698853} 08/31/2021 07:59:40 - INFO - __main__ - Step 104049: {'lr': 0.0001097953351020235, 'samples': 19977408, 'steps': 104048, 'loss/train': 1.4822659492492676} 08/31/2021 07:59:40 - INFO - __main__ - Step 104050: {'lr': 0.00010979094147478671, 'samples': 19977600, 'steps': 104049, 'loss/train': 1.1727582216262817} 08/31/2021 07:59:41 - INFO - __main__ - Step 104051: {'lr': 0.00010978654791072598, 'samples': 19977792, 'steps': 104050, 'loss/train': 0.9044354557991028} 08/31/2021 07:59:42 - INFO - __main__ - Step 104052: {'lr': 0.00010978215440984324, 'samples': 19977984, 'steps': 104051, 'loss/train': 1.021725058555603} 08/31/2021 07:59:42 - INFO - __main__ - Step 104053: {'lr': 0.00010977776097214051, 'samples': 19978176, 'steps': 104052, 'loss/train': 0.5211241841316223} 08/31/2021 07:59:43 - INFO - __main__ - Step 104054: {'lr': 0.00010977336759761986, 'samples': 19978368, 'steps': 104053, 'loss/train': 1.2572828531265259} 08/31/2021 07:59:43 - INFO - __main__ - Step 104055: {'lr': 0.00010976897428628305, 'samples': 19978560, 'steps': 104054, 'loss/train': 1.0070699453353882} 08/31/2021 07:59:45 - INFO - __main__ - Step 104056: {'lr': 0.00010976458103813219, 'samples': 19978752, 'steps': 104055, 'loss/train': 0.7507715821266174} 08/31/2021 07:59:45 - INFO - __main__ - Step 104057: {'lr': 0.00010976018785316924, 'samples': 19978944, 'steps': 104056, 'loss/train': 1.6761183738708496} 08/31/2021 07:59:45 - INFO - __main__ - Step 104058: {'lr': 0.00010975579473139618, 'samples': 19979136, 'steps': 104057, 'loss/train': 1.3320658206939697} 08/31/2021 07:59:46 - INFO - __main__ - Step 104059: {'lr': 0.000109751401672815, 'samples': 19979328, 'steps': 104058, 'loss/train': 0.6471942067146301} 08/31/2021 07:59:46 - INFO - __main__ - Step 104060: {'lr': 0.00010974700867742768, 'samples': 19979520, 'steps': 104059, 'loss/train': 0.7722434401512146} 08/31/2021 07:59:48 - INFO - __main__ - Step 104061: {'lr': 0.00010974261574523619, 'samples': 19979712, 'steps': 104060, 'loss/train': 0.7646737098693848} 08/31/2021 07:59:48 - INFO - __main__ - Step 104062: {'lr': 0.00010973822287624253, 'samples': 19979904, 'steps': 104061, 'loss/train': 0.7443246841430664} 08/31/2021 07:59:48 - INFO - __main__ - Step 104063: {'lr': 0.00010973383007044863, 'samples': 19980096, 'steps': 104062, 'loss/train': 1.6791740655899048} 08/31/2021 07:59:49 - INFO - __main__ - Step 104064: {'lr': 0.00010972943732785654, 'samples': 19980288, 'steps': 104063, 'loss/train': 1.8115311861038208} 08/31/2021 07:59:49 - INFO - __main__ - Step 104065: {'lr': 0.00010972504464846816, 'samples': 19980480, 'steps': 104064, 'loss/train': 1.65694260597229} 08/31/2021 07:59:51 - INFO - __main__ - Step 104066: {'lr': 0.00010972065203228555, 'samples': 19980672, 'steps': 104065, 'loss/train': 0.8595975637435913} 08/31/2021 07:59:51 - INFO - __main__ - Step 104067: {'lr': 0.00010971625947931068, 'samples': 19980864, 'steps': 104066, 'loss/train': 1.452256202697754} 08/31/2021 07:59:52 - INFO - __main__ - Step 104068: {'lr': 0.00010971186698954547, 'samples': 19981056, 'steps': 104067, 'loss/train': 1.2228745222091675} 08/31/2021 07:59:52 - INFO - __main__ - Step 104069: {'lr': 0.0001097074745629919, 'samples': 19981248, 'steps': 104068, 'loss/train': 1.4797250032424927} 08/31/2021 07:59:52 - INFO - __main__ - Step 104070: {'lr': 0.000109703082199652, 'samples': 19981440, 'steps': 104069, 'loss/train': 0.992195188999176} 08/31/2021 07:59:54 - INFO - __main__ - Step 104071: {'lr': 0.00010969868989952769, 'samples': 19981632, 'steps': 104070, 'loss/train': 0.9355828166007996} 08/31/2021 07:59:55 - INFO - __main__ - Step 104072: {'lr': 0.00010969429766262102, 'samples': 19981824, 'steps': 104071, 'loss/train': 1.4435456991195679} 08/31/2021 07:59:55 - INFO - __main__ - Step 104073: {'lr': 0.0001096899054889339, 'samples': 19982016, 'steps': 104072, 'loss/train': 1.3640942573547363} 08/31/2021 07:59:55 - INFO - __main__ - Step 104074: {'lr': 0.00010968551337846838, 'samples': 19982208, 'steps': 104073, 'loss/train': 0.719005823135376} 08/31/2021 07:59:56 - INFO - __main__ - Step 104075: {'lr': 0.00010968112133122638, 'samples': 19982400, 'steps': 104074, 'loss/train': 0.6738285422325134} 08/31/2021 07:59:57 - INFO - __main__ - Step 104076: {'lr': 0.0001096767293472099, 'samples': 19982592, 'steps': 104075, 'loss/train': 1.2597682476043701} 08/31/2021 07:59:58 - INFO - __main__ - Step 104077: {'lr': 0.00010967233742642094, 'samples': 19982784, 'steps': 104076, 'loss/train': 0.9854483604431152} 08/31/2021 07:59:58 - INFO - __main__ - Step 104078: {'lr': 0.00010966794556886142, 'samples': 19982976, 'steps': 104077, 'loss/train': 0.21288591623306274} 08/31/2021 07:59:58 - INFO - __main__ - Step 104079: {'lr': 0.00010966355377453341, 'samples': 19983168, 'steps': 104078, 'loss/train': 1.4425872564315796} 08/31/2021 07:59:59 - INFO - __main__ - Step 104080: {'lr': 0.00010965916204343878, 'samples': 19983360, 'steps': 104079, 'loss/train': 1.7061398029327393} 08/31/2021 08:00:00 - INFO - __main__ - Step 104081: {'lr': 0.00010965477037557973, 'samples': 19983552, 'steps': 104080, 'loss/train': 0.9059672951698303} 08/31/2021 08:00:01 - INFO - __main__ - Step 104082: {'lr': 0.00010965037877095793, 'samples': 19983744, 'steps': 104081, 'loss/train': 1.1355209350585938} 08/31/2021 08:00:01 - INFO - __main__ - Step 104083: {'lr': 0.0001096459872295755, 'samples': 19983936, 'steps': 104082, 'loss/train': 0.8500956892967224} 08/31/2021 08:00:01 - INFO - __main__ - Step 104084: {'lr': 0.00010964159575143445, 'samples': 19984128, 'steps': 104083, 'loss/train': 0.34681570529937744} 08/31/2021 08:00:02 - INFO - __main__ - Step 104085: {'lr': 0.00010963720433653671, 'samples': 19984320, 'steps': 104084, 'loss/train': 1.3799419403076172} 08/31/2021 08:00:02 - INFO - __main__ - Step 104086: {'lr': 0.00010963281298488428, 'samples': 19984512, 'steps': 104085, 'loss/train': 0.4859790503978729} 08/31/2021 08:00:03 - INFO - __main__ - Step 104087: {'lr': 0.00010962842169647916, 'samples': 19984704, 'steps': 104086, 'loss/train': 1.0148539543151855} 08/31/2021 08:00:04 - INFO - __main__ - Step 104088: {'lr': 0.0001096240304713233, 'samples': 19984896, 'steps': 104087, 'loss/train': 1.6814751625061035} 08/31/2021 08:00:04 - INFO - __main__ - Step 104089: {'lr': 0.00010961963930941867, 'samples': 19985088, 'steps': 104088, 'loss/train': 1.3483527898788452} 08/31/2021 08:00:05 - INFO - __main__ - Step 104090: {'lr': 0.00010961524821076726, 'samples': 19985280, 'steps': 104089, 'loss/train': 1.3044553995132446} 08/31/2021 08:00:05 - INFO - __main__ - Step 104091: {'lr': 0.00010961085717537109, 'samples': 19985472, 'steps': 104090, 'loss/train': 1.5084881782531738} 08/31/2021 08:00:07 - INFO - __main__ - Step 104092: {'lr': 0.00010960646620323209, 'samples': 19985664, 'steps': 104091, 'loss/train': 1.0185397863388062} 08/31/2021 08:00:08 - INFO - __main__ - Step 104093: {'lr': 0.00010960207529435223, 'samples': 19985856, 'steps': 104092, 'loss/train': 0.5845171809196472} 08/31/2021 08:00:08 - INFO - __main__ - Step 104094: {'lr': 0.00010959768444873361, 'samples': 19986048, 'steps': 104093, 'loss/train': 0.6094076037406921} 08/31/2021 08:00:08 - INFO - __main__ - Step 104095: {'lr': 0.00010959329366637802, 'samples': 19986240, 'steps': 104094, 'loss/train': 0.814298152923584} 08/31/2021 08:00:09 - INFO - __main__ - Step 104096: {'lr': 0.00010958890294728752, 'samples': 19986432, 'steps': 104095, 'loss/train': 1.4391388893127441} 08/31/2021 08:00:09 - INFO - __main__ - Step 104097: {'lr': 0.00010958451229146408, 'samples': 19986624, 'steps': 104096, 'loss/train': 1.272160291671753} 08/31/2021 08:00:10 - INFO - __main__ - Step 104098: {'lr': 0.00010958012169890972, 'samples': 19986816, 'steps': 104097, 'loss/train': 1.1962890625} 08/31/2021 08:00:11 - INFO - __main__ - Step 104099: {'lr': 0.00010957573116962636, 'samples': 19987008, 'steps': 104098, 'loss/train': 1.5467476844787598} 08/31/2021 08:00:11 - INFO - __main__ - Step 104100: {'lr': 0.00010957134070361602, 'samples': 19987200, 'steps': 104099, 'loss/train': 0.34656962752342224} 08/31/2021 08:00:12 - INFO - __main__ - Step 104101: {'lr': 0.00010956695030088069, 'samples': 19987392, 'steps': 104100, 'loss/train': 0.8790134787559509} 08/31/2021 08:00:12 - INFO - __main__ - Step 104102: {'lr': 0.00010956255996142227, 'samples': 19987584, 'steps': 104101, 'loss/train': 1.1802940368652344} 08/31/2021 08:00:13 - INFO - __main__ - Step 104103: {'lr': 0.00010955816968524285, 'samples': 19987776, 'steps': 104102, 'loss/train': 0.2752212882041931} 08/31/2021 08:00:14 - INFO - __main__ - Step 104104: {'lr': 0.00010955377947234432, 'samples': 19987968, 'steps': 104103, 'loss/train': 0.877297043800354} 08/31/2021 08:00:14 - INFO - __main__ - Step 104105: {'lr': 0.00010954938932272871, 'samples': 19988160, 'steps': 104104, 'loss/train': 0.8599981069564819} 08/31/2021 08:00:15 - INFO - __main__ - Step 104106: {'lr': 0.00010954499923639796, 'samples': 19988352, 'steps': 104105, 'loss/train': 1.1355818510055542} 08/31/2021 08:00:15 - INFO - __main__ - Step 104107: {'lr': 0.00010954060921335409, 'samples': 19988544, 'steps': 104106, 'loss/train': 1.0117958784103394} 08/31/2021 08:00:17 - INFO - __main__ - Step 104108: {'lr': 0.00010953621925359914, 'samples': 19988736, 'steps': 104107, 'loss/train': 0.6284607648849487} 08/31/2021 08:00:18 - INFO - __main__ - Step 104109: {'lr': 0.00010953182935713488, 'samples': 19988928, 'steps': 104108, 'loss/train': 0.9543494582176208} 08/31/2021 08:00:18 - INFO - __main__ - Step 104110: {'lr': 0.00010952743952396343, 'samples': 19989120, 'steps': 104109, 'loss/train': 2.979402542114258} 08/31/2021 08:00:18 - INFO - __main__ - Step 104111: {'lr': 0.00010952304975408676, 'samples': 19989312, 'steps': 104110, 'loss/train': 0.052142977714538574} 08/31/2021 08:00:19 - INFO - __main__ - Step 104112: {'lr': 0.00010951866004750682, 'samples': 19989504, 'steps': 104111, 'loss/train': 0.6941607594490051} 08/31/2021 08:00:20 - INFO - __main__ - Step 104113: {'lr': 0.00010951427040422563, 'samples': 19989696, 'steps': 104112, 'loss/train': 1.3816182613372803} 08/31/2021 08:00:21 - INFO - __main__ - Step 104114: {'lr': 0.0001095098808242451, 'samples': 19989888, 'steps': 104113, 'loss/train': 0.41793662309646606} 08/31/2021 08:00:21 - INFO - __main__ - Step 104115: {'lr': 0.00010950549130756726, 'samples': 19990080, 'steps': 104114, 'loss/train': 0.28204116225242615} 08/31/2021 08:00:21 - INFO - __main__ - Step 104116: {'lr': 0.0001095011018541941, 'samples': 19990272, 'steps': 104115, 'loss/train': 0.9202042818069458} 08/31/2021 08:00:22 - INFO - __main__ - Step 104117: {'lr': 0.00010949671246412757, 'samples': 19990464, 'steps': 104116, 'loss/train': 0.778965413570404} 08/31/2021 08:00:23 - INFO - __main__ - Step 104118: {'lr': 0.00010949232313736965, 'samples': 19990656, 'steps': 104117, 'loss/train': 2.1589174270629883} 08/31/2021 08:00:24 - INFO - __main__ - Step 104119: {'lr': 0.0001094879338739223, 'samples': 19990848, 'steps': 104118, 'loss/train': 0.7349445223808289} 08/31/2021 08:00:24 - INFO - __main__ - Step 104120: {'lr': 0.00010948354467378754, 'samples': 19991040, 'steps': 104119, 'loss/train': 1.2311820983886719} 08/31/2021 08:00:24 - INFO - __main__ - Step 104121: {'lr': 0.0001094791555369674, 'samples': 19991232, 'steps': 104120, 'loss/train': 0.9504224061965942} 08/31/2021 08:00:25 - INFO - __main__ - Step 104122: {'lr': 0.00010947476646346374, 'samples': 19991424, 'steps': 104121, 'loss/train': 0.7799720168113708} 08/31/2021 08:00:25 - INFO - __main__ - Step 104123: {'lr': 0.00010947037745327853, 'samples': 19991616, 'steps': 104122, 'loss/train': 2.169063091278076} 08/31/2021 08:00:26 - INFO - __main__ - Step 104124: {'lr': 0.00010946598850641385, 'samples': 19991808, 'steps': 104123, 'loss/train': 1.456480860710144} 08/31/2021 08:00:27 - INFO - __main__ - Step 104125: {'lr': 0.00010946159962287158, 'samples': 19992000, 'steps': 104124, 'loss/train': 0.9917334914207458} 08/31/2021 08:00:27 - INFO - __main__ - Step 104126: {'lr': 0.00010945721080265375, 'samples': 19992192, 'steps': 104125, 'loss/train': 1.5419713258743286} 08/31/2021 08:00:28 - INFO - __main__ - Step 104127: {'lr': 0.00010945282204576235, 'samples': 19992384, 'steps': 104126, 'loss/train': 0.920435905456543} 08/31/2021 08:00:28 - INFO - __main__ - Step 104128: {'lr': 0.00010944843335219934, 'samples': 19992576, 'steps': 104127, 'loss/train': 0.7533044219017029} 08/31/2021 08:00:30 - INFO - __main__ - Step 104129: {'lr': 0.00010944404472196667, 'samples': 19992768, 'steps': 104128, 'loss/train': 1.0967391729354858} 08/31/2021 08:00:31 - INFO - __main__ - Step 104130: {'lr': 0.00010943965615506638, 'samples': 19992960, 'steps': 104129, 'loss/train': 1.2192250490188599} 08/31/2021 08:00:31 - INFO - __main__ - Step 104131: {'lr': 0.00010943526765150038, 'samples': 19993152, 'steps': 104130, 'loss/train': 0.3314967751502991} 08/31/2021 08:00:32 - INFO - __main__ - Step 104132: {'lr': 0.00010943087921127071, 'samples': 19993344, 'steps': 104131, 'loss/train': 0.5332444906234741} 08/31/2021 08:00:32 - INFO - __main__ - Step 104133: {'lr': 0.0001094264908343793, 'samples': 19993536, 'steps': 104132, 'loss/train': 1.3777565956115723} 08/31/2021 08:00:34 - INFO - __main__ - Step 104134: {'lr': 0.00010942210252082815, 'samples': 19993728, 'steps': 104133, 'loss/train': 0.03094273805618286} 08/31/2021 08:00:34 - INFO - __main__ - Step 104135: {'lr': 0.00010941771427061931, 'samples': 19993920, 'steps': 104134, 'loss/train': 1.4976446628570557} 08/31/2021 08:00:34 - INFO - __main__ - Step 104136: {'lr': 0.0001094133260837546, 'samples': 19994112, 'steps': 104135, 'loss/train': 1.444387674331665} 08/31/2021 08:00:35 - INFO - __main__ - Step 104137: {'lr': 0.00010940893796023607, 'samples': 19994304, 'steps': 104136, 'loss/train': 0.8678277730941772} 08/31/2021 08:00:35 - INFO - __main__ - Step 104138: {'lr': 0.00010940454990006571, 'samples': 19994496, 'steps': 104137, 'loss/train': 1.6423481702804565} 08/31/2021 08:00:37 - INFO - __main__ - Step 104139: {'lr': 0.00010940016190324548, 'samples': 19994688, 'steps': 104138, 'loss/train': 0.7874184250831604} 08/31/2021 08:00:37 - INFO - __main__ - Step 104140: {'lr': 0.00010939577396977738, 'samples': 19994880, 'steps': 104139, 'loss/train': 1.3881169557571411} 08/31/2021 08:00:37 - INFO - __main__ - Step 104141: {'lr': 0.00010939138609966337, 'samples': 19995072, 'steps': 104140, 'loss/train': 1.2081528902053833} 08/31/2021 08:00:38 - INFO - __main__ - Step 104142: {'lr': 0.00010938699829290541, 'samples': 19995264, 'steps': 104141, 'loss/train': 0.9343920946121216} 08/31/2021 08:00:38 - INFO - __main__ - Step 104143: {'lr': 0.00010938261054950552, 'samples': 19995456, 'steps': 104142, 'loss/train': 1.0186879634857178} 08/31/2021 08:00:40 - INFO - __main__ - Step 104144: {'lr': 0.00010937822286946566, 'samples': 19995648, 'steps': 104143, 'loss/train': 1.3065389394760132} 08/31/2021 08:00:40 - INFO - __main__ - Step 104145: {'lr': 0.00010937383525278779, 'samples': 19995840, 'steps': 104144, 'loss/train': 1.2766016721725464} 08/31/2021 08:00:40 - INFO - __main__ - Step 104146: {'lr': 0.0001093694476994739, 'samples': 19996032, 'steps': 104145, 'loss/train': 0.1269041895866394} 08/31/2021 08:00:41 - INFO - __main__ - Step 104147: {'lr': 0.000109365060209526, 'samples': 19996224, 'steps': 104146, 'loss/train': 0.637507975101471} 08/31/2021 08:00:41 - INFO - __main__ - Step 104148: {'lr': 0.00010936067278294609, 'samples': 19996416, 'steps': 104147, 'loss/train': 1.5107672214508057} 08/31/2021 08:00:43 - INFO - __main__ - Step 104149: {'lr': 0.000109356285419736, 'samples': 19996608, 'steps': 104148, 'loss/train': 1.052331566810608} 08/31/2021 08:00:43 - INFO - __main__ - Step 104150: {'lr': 0.00010935189811989782, 'samples': 19996800, 'steps': 104149, 'loss/train': 0.8226367831230164} 08/31/2021 08:00:43 - INFO - __main__ - Step 104151: {'lr': 0.00010934751088343348, 'samples': 19996992, 'steps': 104150, 'loss/train': 1.0376255512237549} 08/31/2021 08:00:44 - INFO - __main__ - Step 104152: {'lr': 0.00010934312371034499, 'samples': 19997184, 'steps': 104151, 'loss/train': 1.6691625118255615} 08/31/2021 08:00:44 - INFO - __main__ - Step 104153: {'lr': 0.00010933873660063432, 'samples': 19997376, 'steps': 104152, 'loss/train': 1.2314215898513794} 08/31/2021 08:00:46 - INFO - __main__ - Step 104154: {'lr': 0.00010933434955430344, 'samples': 19997568, 'steps': 104153, 'loss/train': 1.195868730545044} 08/31/2021 08:00:46 - INFO - __main__ - Step 104155: {'lr': 0.00010932996257135433, 'samples': 19997760, 'steps': 104154, 'loss/train': 0.6368772387504578} 08/31/2021 08:00:46 - INFO - __main__ - Step 104156: {'lr': 0.000109325575651789, 'samples': 19997952, 'steps': 104155, 'loss/train': 1.0484222173690796} 08/31/2021 08:00:47 - INFO - __main__ - Step 104157: {'lr': 0.00010932118879560935, 'samples': 19998144, 'steps': 104156, 'loss/train': 1.1639212369918823} 08/31/2021 08:00:47 - INFO - __main__ - Step 104158: {'lr': 0.00010931680200281741, 'samples': 19998336, 'steps': 104157, 'loss/train': 0.5001857876777649} 08/31/2021 08:00:49 - INFO - __main__ - Step 104159: {'lr': 0.00010931241527341518, 'samples': 19998528, 'steps': 104158, 'loss/train': 0.6832075119018555} 08/31/2021 08:00:49 - INFO - __main__ - Step 104160: {'lr': 0.00010930802860740458, 'samples': 19998720, 'steps': 104159, 'loss/train': 1.2022671699523926} 08/31/2021 08:00:49 - INFO - __main__ - Step 104161: {'lr': 0.0001093036420047876, 'samples': 19998912, 'steps': 104160, 'loss/train': 1.6013538837432861} 08/31/2021 08:00:50 - INFO - __main__ - Step 104162: {'lr': 0.00010929925546556636, 'samples': 19999104, 'steps': 104161, 'loss/train': 0.5044681429862976} 08/31/2021 08:00:50 - INFO - __main__ - Step 104163: {'lr': 0.00010929486898974255, 'samples': 19999296, 'steps': 104162, 'loss/train': 0.05426203832030296} 08/31/2021 08:00:51 - INFO - __main__ - Step 104164: {'lr': 0.00010929048257731836, 'samples': 19999488, 'steps': 104163, 'loss/train': 1.3345099687576294} 08/31/2021 08:00:52 - INFO - __main__ - Step 104165: {'lr': 0.00010928609622829566, 'samples': 19999680, 'steps': 104164, 'loss/train': 1.3814464807510376} 08/31/2021 08:00:52 - INFO - __main__ - Step 104166: {'lr': 0.0001092817099426765, 'samples': 19999872, 'steps': 104165, 'loss/train': 1.1468209028244019} 08/31/2021 08:00:53 - INFO - __main__ - Step 104167: {'lr': 0.00010927732372046283, 'samples': 20000064, 'steps': 104166, 'loss/train': 0.5721499919891357} 08/31/2021 08:00:53 - INFO - __main__ - Step 104168: {'lr': 0.00010927293756165663, 'samples': 20000256, 'steps': 104167, 'loss/train': 1.4532920122146606} 08/31/2021 08:00:53 - INFO - __main__ - Step 104169: {'lr': 0.00010926855146625986, 'samples': 20000448, 'steps': 104168, 'loss/train': 1.2328624725341797} 08/31/2021 08:00:55 - INFO - __main__ - Step 104170: {'lr': 0.00010926416543427453, 'samples': 20000640, 'steps': 104169, 'loss/train': 1.1610395908355713} 08/31/2021 08:00:55 - INFO - __main__ - Step 104171: {'lr': 0.00010925977946570256, 'samples': 20000832, 'steps': 104170, 'loss/train': 1.0742908716201782} 08/31/2021 08:00:56 - INFO - __main__ - Step 104172: {'lr': 0.000109255393560546, 'samples': 20001024, 'steps': 104171, 'loss/train': 1.4804630279541016} 08/31/2021 08:00:56 - INFO - __main__ - Step 104173: {'lr': 0.00010925100771880678, 'samples': 20001216, 'steps': 104172, 'loss/train': 0.8701015114784241} 08/31/2021 08:00:56 - INFO - __main__ - Step 104174: {'lr': 0.00010924662194048687, 'samples': 20001408, 'steps': 104173, 'loss/train': 0.23597665131092072} 08/31/2021 08:00:58 - INFO - __main__ - Step 104175: {'lr': 0.00010924223622558835, 'samples': 20001600, 'steps': 104174, 'loss/train': 1.0345615148544312} 08/31/2021 08:00:58 - INFO - __main__ - Step 104176: {'lr': 0.00010923785057411304, 'samples': 20001792, 'steps': 104175, 'loss/train': 1.0800665616989136} 08/31/2021 08:00:59 - INFO - __main__ - Step 104177: {'lr': 0.00010923346498606296, 'samples': 20001984, 'steps': 104176, 'loss/train': 1.3221566677093506} 08/31/2021 08:00:59 - INFO - __main__ - Step 104178: {'lr': 0.0001092290794614401, 'samples': 20002176, 'steps': 104177, 'loss/train': 1.4313803911209106} 08/31/2021 08:00:59 - INFO - __main__ - Step 104179: {'lr': 0.00010922469400024645, 'samples': 20002368, 'steps': 104178, 'loss/train': 1.243634819984436} 08/31/2021 08:01:01 - INFO - __main__ - Step 104180: {'lr': 0.000109220308602484, 'samples': 20002560, 'steps': 104179, 'loss/train': 0.8511803150177002} 08/31/2021 08:01:02 - INFO - __main__ - Step 104181: {'lr': 0.00010921592326815468, 'samples': 20002752, 'steps': 104180, 'loss/train': 1.6961876153945923} 08/31/2021 08:01:02 - INFO - __main__ - Step 104182: {'lr': 0.00010921153799726052, 'samples': 20002944, 'steps': 104181, 'loss/train': 1.9480754137039185} 08/31/2021 08:01:03 - INFO - __main__ - Step 104183: {'lr': 0.00010920715278980345, 'samples': 20003136, 'steps': 104182, 'loss/train': 1.1165783405303955} 08/31/2021 08:01:03 - INFO - __main__ - Step 104184: {'lr': 0.00010920276764578545, 'samples': 20003328, 'steps': 104183, 'loss/train': 1.0943800210952759} 08/31/2021 08:01:04 - INFO - __main__ - Step 104185: {'lr': 0.00010919838256520856, 'samples': 20003520, 'steps': 104184, 'loss/train': 0.9905229210853577} 08/31/2021 08:01:05 - INFO - __main__ - Step 104186: {'lr': 0.00010919399754807466, 'samples': 20003712, 'steps': 104185, 'loss/train': 1.3382554054260254} 08/31/2021 08:01:05 - INFO - __main__ - Step 104187: {'lr': 0.00010918961259438578, 'samples': 20003904, 'steps': 104186, 'loss/train': 1.160109043121338} 08/31/2021 08:01:06 - INFO - __main__ - Step 104188: {'lr': 0.00010918522770414398, 'samples': 20004096, 'steps': 104187, 'loss/train': 1.165528655052185} 08/31/2021 08:01:06 - INFO - __main__ - Step 104189: {'lr': 0.00010918084287735108, 'samples': 20004288, 'steps': 104188, 'loss/train': 0.8930889964103699} 08/31/2021 08:01:08 - INFO - __main__ - Step 104190: {'lr': 0.00010917645811400909, 'samples': 20004480, 'steps': 104189, 'loss/train': 0.771878719329834} 08/31/2021 08:01:08 - INFO - __main__ - Step 104191: {'lr': 0.00010917207341412003, 'samples': 20004672, 'steps': 104190, 'loss/train': 0.29425275325775146} 08/31/2021 08:01:09 - INFO - __main__ - Step 104192: {'lr': 0.00010916768877768585, 'samples': 20004864, 'steps': 104191, 'loss/train': 1.5347275733947754} 08/31/2021 08:01:09 - INFO - __main__ - Step 104193: {'lr': 0.00010916330420470854, 'samples': 20005056, 'steps': 104192, 'loss/train': 0.6981988549232483} 08/31/2021 08:01:09 - INFO - __main__ - Step 104194: {'lr': 0.00010915891969519007, 'samples': 20005248, 'steps': 104193, 'loss/train': 1.3242323398590088} 08/31/2021 08:01:10 - INFO - __main__ - Step 104195: {'lr': 0.00010915453524913243, 'samples': 20005440, 'steps': 104194, 'loss/train': 0.49290552735328674} 08/31/2021 08:01:11 - INFO - __main__ - Step 104196: {'lr': 0.00010915015086653756, 'samples': 20005632, 'steps': 104195, 'loss/train': 1.0119181871414185} 08/31/2021 08:01:12 - INFO - __main__ - Step 104197: {'lr': 0.00010914576654740748, 'samples': 20005824, 'steps': 104196, 'loss/train': 1.0623843669891357} 08/31/2021 08:01:12 - INFO - __main__ - Step 104198: {'lr': 0.00010914138229174414, 'samples': 20006016, 'steps': 104197, 'loss/train': 0.9330307841300964} 08/31/2021 08:01:12 - INFO - __main__ - Step 104199: {'lr': 0.00010913699809954952, 'samples': 20006208, 'steps': 104198, 'loss/train': 0.9249323010444641} 08/31/2021 08:01:13 - INFO - __main__ - Step 104200: {'lr': 0.00010913261397082558, 'samples': 20006400, 'steps': 104199, 'loss/train': 1.0858567953109741} 08/31/2021 08:01:14 - INFO - __main__ - Step 104201: {'lr': 0.0001091282299055743, 'samples': 20006592, 'steps': 104200, 'loss/train': 0.6688423156738281} 08/31/2021 08:01:14 - INFO - __main__ - Step 104202: {'lr': 0.00010912384590379779, 'samples': 20006784, 'steps': 104201, 'loss/train': 0.9637935161590576} 08/31/2021 08:01:15 - INFO - __main__ - Step 104203: {'lr': 0.0001091194619654978, 'samples': 20006976, 'steps': 104202, 'loss/train': 0.9395329356193542} 08/31/2021 08:01:15 - INFO - __main__ - Step 104204: {'lr': 0.00010911507809067642, 'samples': 20007168, 'steps': 104203, 'loss/train': 1.4696296453475952} 08/31/2021 08:01:16 - INFO - __main__ - Step 104205: {'lr': 0.00010911069427933559, 'samples': 20007360, 'steps': 104204, 'loss/train': 0.9841011166572571} 08/31/2021 08:01:17 - INFO - __main__ - Step 104206: {'lr': 0.00010910631053147729, 'samples': 20007552, 'steps': 104205, 'loss/train': 0.9671657681465149} 08/31/2021 08:01:17 - INFO - __main__ - Step 104207: {'lr': 0.00010910192684710354, 'samples': 20007744, 'steps': 104206, 'loss/train': 0.882346510887146} 08/31/2021 08:01:18 - INFO - __main__ - Step 104208: {'lr': 0.00010909754322621629, 'samples': 20007936, 'steps': 104207, 'loss/train': 1.2980331182479858} 08/31/2021 08:01:18 - INFO - __main__ - Step 104209: {'lr': 0.0001090931596688175, 'samples': 20008128, 'steps': 104208, 'loss/train': 1.4185463190078735} 08/31/2021 08:01:18 - INFO - __main__ - Step 104210: {'lr': 0.00010908877617490917, 'samples': 20008320, 'steps': 104209, 'loss/train': 0.7632114291191101} 08/31/2021 08:01:20 - INFO - __main__ - Step 104211: {'lr': 0.00010908439274449325, 'samples': 20008512, 'steps': 104210, 'loss/train': 1.0003254413604736} 08/31/2021 08:01:20 - INFO - __main__ - Step 104212: {'lr': 0.00010908000937757174, 'samples': 20008704, 'steps': 104211, 'loss/train': 0.15677805244922638} 08/31/2021 08:01:21 - INFO - __main__ - Step 104213: {'lr': 0.0001090756260741466, 'samples': 20008896, 'steps': 104212, 'loss/train': 0.3510969579219818} 08/31/2021 08:01:21 - INFO - __main__ - Step 104214: {'lr': 0.00010907124283421981, 'samples': 20009088, 'steps': 104213, 'loss/train': 1.43925142288208} 08/31/2021 08:01:21 - INFO - __main__ - Step 104215: {'lr': 0.00010906685965779343, 'samples': 20009280, 'steps': 104214, 'loss/train': 0.6025188565254211} 08/31/2021 08:01:23 - INFO - __main__ - Step 104216: {'lr': 0.00010906247654486926, 'samples': 20009472, 'steps': 104215, 'loss/train': 1.046383261680603} 08/31/2021 08:01:23 - INFO - __main__ - Step 104217: {'lr': 0.00010905809349544935, 'samples': 20009664, 'steps': 104216, 'loss/train': 1.2548856735229492} 08/31/2021 08:01:24 - INFO - __main__ - Step 104218: {'lr': 0.00010905371050953569, 'samples': 20009856, 'steps': 104217, 'loss/train': 0.1338912844657898} 08/31/2021 08:01:24 - INFO - __main__ - Step 104219: {'lr': 0.00010904932758713027, 'samples': 20010048, 'steps': 104218, 'loss/train': 1.2184077501296997} 08/31/2021 08:01:24 - INFO - __main__ - Step 104220: {'lr': 0.00010904494472823504, 'samples': 20010240, 'steps': 104219, 'loss/train': 1.21293044090271} 08/31/2021 08:01:26 - INFO - __main__ - Step 104221: {'lr': 0.000109040561932852, 'samples': 20010432, 'steps': 104220, 'loss/train': 0.967292308807373} 08/31/2021 08:01:26 - INFO - __main__ - Step 104222: {'lr': 0.00010903617920098308, 'samples': 20010624, 'steps': 104221, 'loss/train': 1.5062929391860962} 08/31/2021 08:01:27 - INFO - __main__ - Step 104223: {'lr': 0.00010903179653263029, 'samples': 20010816, 'steps': 104222, 'loss/train': 1.0879461765289307} 08/31/2021 08:01:27 - INFO - __main__ - Step 104224: {'lr': 0.00010902741392779562, 'samples': 20011008, 'steps': 104223, 'loss/train': 1.497548222541809} 08/31/2021 08:01:28 - INFO - __main__ - Step 104225: {'lr': 0.00010902303138648098, 'samples': 20011200, 'steps': 104224, 'loss/train': 1.1736739873886108} 08/31/2021 08:01:29 - INFO - __main__ - Step 104226: {'lr': 0.00010901864890868843, 'samples': 20011392, 'steps': 104225, 'loss/train': 0.8236013054847717} 08/31/2021 08:01:30 - INFO - __main__ - Step 104227: {'lr': 0.00010901426649441987, 'samples': 20011584, 'steps': 104226, 'loss/train': 1.19740891456604} 08/31/2021 08:01:30 - INFO - __main__ - Step 104228: {'lr': 0.00010900988414367732, 'samples': 20011776, 'steps': 104227, 'loss/train': 0.43896687030792236} 08/31/2021 08:01:30 - INFO - __main__ - Step 104229: {'lr': 0.00010900550185646283, 'samples': 20011968, 'steps': 104228, 'loss/train': 1.1228125095367432} 08/31/2021 08:01:31 - INFO - __main__ - Step 104230: {'lr': 0.00010900111963277817, 'samples': 20012160, 'steps': 104229, 'loss/train': 0.41706693172454834} 08/31/2021 08:01:31 - INFO - __main__ - Step 104231: {'lr': 0.00010899673747262545, 'samples': 20012352, 'steps': 104230, 'loss/train': 1.2477983236312866} 08/31/2021 08:01:33 - INFO - __main__ - Step 104232: {'lr': 0.00010899235537600663, 'samples': 20012544, 'steps': 104231, 'loss/train': 0.8561280369758606} 08/31/2021 08:01:34 - INFO - __main__ - Step 104233: {'lr': 0.00010898797334292368, 'samples': 20012736, 'steps': 104232, 'loss/train': 1.2503776550292969} 08/31/2021 08:01:34 - INFO - __main__ - Step 104234: {'lr': 0.00010898359137337857, 'samples': 20012928, 'steps': 104233, 'loss/train': 0.022170301526784897} 08/31/2021 08:01:34 - INFO - __main__ - Step 104235: {'lr': 0.00010897920946737327, 'samples': 20013120, 'steps': 104234, 'loss/train': 1.183053970336914} 08/31/2021 08:01:35 - INFO - __main__ - Step 104236: {'lr': 0.00010897482762490978, 'samples': 20013312, 'steps': 104235, 'loss/train': 1.4410555362701416} 08/31/2021 08:01:36 - INFO - __main__ - Step 104237: {'lr': 0.00010897044584599003, 'samples': 20013504, 'steps': 104236, 'loss/train': 1.5367151498794556} 08/31/2021 08:01:37 - INFO - __main__ - Step 104238: {'lr': 0.00010896606413061605, 'samples': 20013696, 'steps': 104237, 'loss/train': 1.8535836935043335} 08/31/2021 08:01:37 - INFO - __main__ - Step 104239: {'lr': 0.00010896168247878977, 'samples': 20013888, 'steps': 104238, 'loss/train': 1.1149710416793823} 08/31/2021 08:01:37 - INFO - __main__ - Step 104240: {'lr': 0.00010895730089051317, 'samples': 20014080, 'steps': 104239, 'loss/train': 1.3414677381515503} 08/31/2021 08:01:38 - INFO - __main__ - Step 104241: {'lr': 0.00010895291936578825, 'samples': 20014272, 'steps': 104240, 'loss/train': 0.6860696077346802} 08/31/2021 08:01:39 - INFO - __main__ - Step 104242: {'lr': 0.00010894853790461706, 'samples': 20014464, 'steps': 104241, 'loss/train': 1.0764594078063965} 08/31/2021 08:01:40 - INFO - __main__ - Step 104243: {'lr': 0.00010894415650700138, 'samples': 20014656, 'steps': 104242, 'loss/train': 1.0567210912704468} 08/31/2021 08:01:40 - INFO - __main__ - Step 104244: {'lr': 0.00010893977517294329, 'samples': 20014848, 'steps': 104243, 'loss/train': 5.8225483894348145} 08/31/2021 08:01:41 - INFO - __main__ - Step 104245: {'lr': 0.00010893539390244475, 'samples': 20015040, 'steps': 104244, 'loss/train': 0.03545185551047325} 08/31/2021 08:01:41 - INFO - __main__ - Step 104246: {'lr': 0.00010893101269550776, 'samples': 20015232, 'steps': 104245, 'loss/train': 1.0784111022949219} 08/31/2021 08:01:41 - INFO - __main__ - Step 104247: {'lr': 0.00010892663155213429, 'samples': 20015424, 'steps': 104246, 'loss/train': 1.465700626373291} 08/31/2021 08:01:43 - INFO - __main__ - Step 104248: {'lr': 0.0001089222504723263, 'samples': 20015616, 'steps': 104247, 'loss/train': 0.6818866729736328} 08/31/2021 08:01:43 - INFO - __main__ - Step 104249: {'lr': 0.00010891786945608573, 'samples': 20015808, 'steps': 104248, 'loss/train': 1.485130786895752} 08/31/2021 08:01:44 - INFO - __main__ - Step 104250: {'lr': 0.00010891348850341462, 'samples': 20016000, 'steps': 104249, 'loss/train': 0.047852471470832825} 08/31/2021 08:01:44 - INFO - __main__ - Step 104251: {'lr': 0.00010890910761431492, 'samples': 20016192, 'steps': 104250, 'loss/train': 1.2044471502304077} 08/31/2021 08:01:44 - INFO - __main__ - Step 104252: {'lr': 0.00010890472678878858, 'samples': 20016384, 'steps': 104251, 'loss/train': 1.37453293800354} 08/31/2021 08:01:46 - INFO - __main__ - Step 104253: {'lr': 0.0001089003460268376, 'samples': 20016576, 'steps': 104252, 'loss/train': 1.720788598060608} 08/31/2021 08:01:46 - INFO - __main__ - Step 104254: {'lr': 0.00010889596532846397, 'samples': 20016768, 'steps': 104253, 'loss/train': 1.1797659397125244} 08/31/2021 08:01:47 - INFO - __main__ - Step 104255: {'lr': 0.0001088915846936696, 'samples': 20016960, 'steps': 104254, 'loss/train': 1.1345343589782715} 08/31/2021 08:01:47 - INFO - __main__ - Step 104256: {'lr': 0.00010888720412245661, 'samples': 20017152, 'steps': 104255, 'loss/train': 1.5476206541061401} 08/31/2021 08:01:47 - INFO - __main__ - Step 104257: {'lr': 0.00010888282361482679, 'samples': 20017344, 'steps': 104256, 'loss/train': 1.031874179840088} 08/31/2021 08:01:48 - INFO - __main__ - Step 104258: {'lr': 0.00010887844317078219, 'samples': 20017536, 'steps': 104257, 'loss/train': 0.45948371291160583} 08/31/2021 08:01:49 - INFO - __main__ - Step 104259: {'lr': 0.00010887406279032478, 'samples': 20017728, 'steps': 104258, 'loss/train': 1.1339665651321411} 08/31/2021 08:01:50 - INFO - __main__ - Step 104260: {'lr': 0.00010886968247345655, 'samples': 20017920, 'steps': 104259, 'loss/train': 1.7409969568252563} 08/31/2021 08:01:50 - INFO - __main__ - Step 104261: {'lr': 0.00010886530222017943, 'samples': 20018112, 'steps': 104260, 'loss/train': 1.1991263628005981} 08/31/2021 08:01:50 - INFO - __main__ - Step 104262: {'lr': 0.00010886092203049546, 'samples': 20018304, 'steps': 104261, 'loss/train': 1.378542423248291} 08/31/2021 08:01:51 - INFO - __main__ - Step 104263: {'lr': 0.00010885654190440658, 'samples': 20018496, 'steps': 104262, 'loss/train': 1.1333458423614502} 08/31/2021 08:01:52 - INFO - __main__ - Step 104264: {'lr': 0.00010885216184191474, 'samples': 20018688, 'steps': 104263, 'loss/train': 0.8615468740463257} 08/31/2021 08:01:53 - INFO - __main__ - Step 104265: {'lr': 0.00010884778184302196, 'samples': 20018880, 'steps': 104264, 'loss/train': 1.564740777015686} 08/31/2021 08:01:53 - INFO - __main__ - Step 104266: {'lr': 0.00010884340190773017, 'samples': 20019072, 'steps': 104265, 'loss/train': 0.8609736561775208} 08/31/2021 08:01:53 - INFO - __main__ - Step 104267: {'lr': 0.00010883902203604148, 'samples': 20019264, 'steps': 104266, 'loss/train': 1.0299136638641357} 08/31/2021 08:01:54 - INFO - __main__ - Step 104268: {'lr': 0.00010883464222795766, 'samples': 20019456, 'steps': 104267, 'loss/train': 1.3336783647537231} 08/31/2021 08:01:55 - INFO - __main__ - Step 104269: {'lr': 0.00010883026248348076, 'samples': 20019648, 'steps': 104268, 'loss/train': 1.3305418491363525} 08/31/2021 08:01:56 - INFO - __main__ - Step 104270: {'lr': 0.00010882588280261277, 'samples': 20019840, 'steps': 104269, 'loss/train': 1.0421745777130127} 08/31/2021 08:01:56 - INFO - __main__ - Step 104271: {'lr': 0.00010882150318535564, 'samples': 20020032, 'steps': 104270, 'loss/train': 1.6584817171096802} 08/31/2021 08:01:56 - INFO - __main__ - Step 104272: {'lr': 0.0001088171236317114, 'samples': 20020224, 'steps': 104271, 'loss/train': 1.1799620389938354} 08/31/2021 08:01:57 - INFO - __main__ - Step 104273: {'lr': 0.00010881274414168194, 'samples': 20020416, 'steps': 104272, 'loss/train': 0.7333314418792725} 08/31/2021 08:01:58 - INFO - __main__ - Step 104274: {'lr': 0.0001088083647152693, 'samples': 20020608, 'steps': 104273, 'loss/train': 1.2432045936584473} 08/31/2021 08:01:59 - INFO - __main__ - Step 104275: {'lr': 0.00010880398535247543, 'samples': 20020800, 'steps': 104274, 'loss/train': 1.1103107929229736} 08/31/2021 08:01:59 - INFO - __main__ - Step 104276: {'lr': 0.0001087996060533023, 'samples': 20020992, 'steps': 104275, 'loss/train': 1.6548680067062378} 08/31/2021 08:01:59 - INFO - __main__ - Step 104277: {'lr': 0.00010879522681775192, 'samples': 20021184, 'steps': 104276, 'loss/train': 1.2457772493362427} 08/31/2021 08:02:00 - INFO - __main__ - Step 104278: {'lr': 0.00010879084764582629, 'samples': 20021376, 'steps': 104277, 'loss/train': 0.730384886264801} 08/31/2021 08:02:00 - INFO - __main__ - Step 104279: {'lr': 0.00010878646853752724, 'samples': 20021568, 'steps': 104278, 'loss/train': 1.1377203464508057} 08/31/2021 08:02:01 - INFO - __main__ - Step 104280: {'lr': 0.00010878208949285684, 'samples': 20021760, 'steps': 104279, 'loss/train': 1.2597585916519165} 08/31/2021 08:02:02 - INFO - __main__ - Step 104281: {'lr': 0.00010877771051181703, 'samples': 20021952, 'steps': 104280, 'loss/train': 1.6158487796783447} 08/31/2021 08:02:02 - INFO - __main__ - Step 104282: {'lr': 0.00010877333159440983, 'samples': 20022144, 'steps': 104281, 'loss/train': 1.3568098545074463} 08/31/2021 08:02:03 - INFO - __main__ - Step 104283: {'lr': 0.00010876895274063717, 'samples': 20022336, 'steps': 104282, 'loss/train': 1.313965916633606} 08/31/2021 08:02:03 - INFO - __main__ - Step 104284: {'lr': 0.00010876457395050105, 'samples': 20022528, 'steps': 104283, 'loss/train': 0.5865679979324341} 08/31/2021 08:02:05 - INFO - __main__ - Step 104285: {'lr': 0.00010876019522400344, 'samples': 20022720, 'steps': 104284, 'loss/train': 1.332023024559021} 08/31/2021 08:02:05 - INFO - __main__ - Step 104286: {'lr': 0.00010875581656114628, 'samples': 20022912, 'steps': 104285, 'loss/train': 0.7495536208152771} 08/31/2021 08:02:06 - INFO - __main__ - Step 104287: {'lr': 0.0001087514379619316, 'samples': 20023104, 'steps': 104286, 'loss/train': 1.102513313293457} 08/31/2021 08:02:06 - INFO - __main__ - Step 104288: {'lr': 0.00010874705942636131, 'samples': 20023296, 'steps': 104287, 'loss/train': 0.7481996417045593} 08/31/2021 08:02:07 - INFO - __main__ - Step 104289: {'lr': 0.00010874268095443754, 'samples': 20023488, 'steps': 104288, 'loss/train': 0.4483107924461365} 08/31/2021 08:02:08 - INFO - __main__ - Step 104290: {'lr': 0.00010873830254616202, 'samples': 20023680, 'steps': 104289, 'loss/train': 0.12825369834899902} 08/31/2021 08:02:08 - INFO - __main__ - Step 104291: {'lr': 0.00010873392420153685, 'samples': 20023872, 'steps': 104290, 'loss/train': 1.7675577402114868} 08/31/2021 08:02:09 - INFO - __main__ - Step 104292: {'lr': 0.000108729545920564, 'samples': 20024064, 'steps': 104291, 'loss/train': 1.1939949989318848} 08/31/2021 08:02:09 - INFO - __main__ - Step 104293: {'lr': 0.00010872516770324544, 'samples': 20024256, 'steps': 104292, 'loss/train': 1.8088196516036987} 08/31/2021 08:02:10 - INFO - __main__ - Step 104294: {'lr': 0.00010872078954958315, 'samples': 20024448, 'steps': 104293, 'loss/train': 1.2622100114822388} 08/31/2021 08:02:11 - INFO - __main__ - Step 104295: {'lr': 0.00010871641145957906, 'samples': 20024640, 'steps': 104294, 'loss/train': 0.7786862254142761} 08/31/2021 08:02:11 - INFO - __main__ - Step 104296: {'lr': 0.00010871203343323518, 'samples': 20024832, 'steps': 104295, 'loss/train': 0.46661171317100525} 08/31/2021 08:02:12 - INFO - __main__ - Step 104297: {'lr': 0.0001087076554705535, 'samples': 20025024, 'steps': 104296, 'loss/train': 1.117024302482605} 08/31/2021 08:02:12 - INFO - __main__ - Step 104298: {'lr': 0.00010870327757153595, 'samples': 20025216, 'steps': 104297, 'loss/train': 0.6041065454483032} 08/31/2021 08:02:13 - INFO - __main__ - Step 104299: {'lr': 0.00010869889973618452, 'samples': 20025408, 'steps': 104298, 'loss/train': 0.8494076132774353} 08/31/2021 08:02:14 - INFO - __main__ - Step 104300: {'lr': 0.0001086945219645013, 'samples': 20025600, 'steps': 104299, 'loss/train': 1.454743504524231} 08/31/2021 08:02:15 - INFO - __main__ - Step 104301: {'lr': 0.00010869014425648804, 'samples': 20025792, 'steps': 104300, 'loss/train': 0.5275313258171082} 08/31/2021 08:02:15 - INFO - __main__ - Step 104302: {'lr': 0.00010868576661214683, 'samples': 20025984, 'steps': 104301, 'loss/train': 1.4052228927612305} 08/31/2021 08:02:15 - INFO - __main__ - Step 104303: {'lr': 0.00010868138903147961, 'samples': 20026176, 'steps': 104302, 'loss/train': 0.8359745144844055} 08/31/2021 08:02:16 - INFO - __main__ - Step 104304: {'lr': 0.00010867701151448842, 'samples': 20026368, 'steps': 104303, 'loss/train': 1.1952425241470337} 08/31/2021 08:02:16 - INFO - __main__ - Step 104305: {'lr': 0.00010867263406117514, 'samples': 20026560, 'steps': 104304, 'loss/train': 1.342445969581604} 08/31/2021 08:02:18 - INFO - __main__ - Step 104306: {'lr': 0.00010866825667154182, 'samples': 20026752, 'steps': 104305, 'loss/train': 1.3365180492401123} 08/31/2021 08:02:18 - INFO - __main__ - Step 104307: {'lr': 0.00010866387934559039, 'samples': 20026944, 'steps': 104306, 'loss/train': 1.1479591131210327} 08/31/2021 08:02:18 - INFO - __main__ - Step 104308: {'lr': 0.00010865950208332284, 'samples': 20027136, 'steps': 104307, 'loss/train': 0.9957082271575928} 08/31/2021 08:02:19 - INFO - __main__ - Step 104309: {'lr': 0.00010865512488474113, 'samples': 20027328, 'steps': 104308, 'loss/train': 1.2761178016662598} 08/31/2021 08:02:19 - INFO - __main__ - Step 104310: {'lr': 0.00010865074774984723, 'samples': 20027520, 'steps': 104309, 'loss/train': 1.2406514883041382} 08/31/2021 08:02:21 - INFO - __main__ - Step 104311: {'lr': 0.00010864637067864325, 'samples': 20027712, 'steps': 104310, 'loss/train': 0.9935246109962463} 08/31/2021 08:02:21 - INFO - __main__ - Step 104312: {'lr': 0.00010864199367113092, 'samples': 20027904, 'steps': 104311, 'loss/train': 1.253017544746399} 08/31/2021 08:02:21 - INFO - __main__ - Step 104313: {'lr': 0.00010863761672731231, 'samples': 20028096, 'steps': 104312, 'loss/train': 0.7763842940330505} 08/31/2021 08:02:22 - INFO - __main__ - Step 104314: {'lr': 0.00010863323984718945, 'samples': 20028288, 'steps': 104313, 'loss/train': 1.3147318363189697} 08/31/2021 08:02:22 - INFO - __main__ - Step 104315: {'lr': 0.00010862886303076425, 'samples': 20028480, 'steps': 104314, 'loss/train': 0.8756992220878601} 08/31/2021 08:02:24 - INFO - __main__ - Step 104316: {'lr': 0.00010862448627803869, 'samples': 20028672, 'steps': 104315, 'loss/train': 1.0870708227157593} 08/31/2021 08:02:24 - INFO - __main__ - Step 104317: {'lr': 0.00010862010958901474, 'samples': 20028864, 'steps': 104316, 'loss/train': 1.0893902778625488} 08/31/2021 08:02:25 - INFO - __main__ - Step 104318: {'lr': 0.00010861573296369442, 'samples': 20029056, 'steps': 104317, 'loss/train': 1.28543221950531} 08/31/2021 08:02:25 - INFO - __main__ - Step 104319: {'lr': 0.00010861135640207966, 'samples': 20029248, 'steps': 104318, 'loss/train': 1.445030927658081} 08/31/2021 08:02:25 - INFO - __main__ - Step 104320: {'lr': 0.00010860697990417245, 'samples': 20029440, 'steps': 104319, 'loss/train': 0.01796572655439377} 08/31/2021 08:02:26 - INFO - __main__ - Step 104321: {'lr': 0.00010860260346997474, 'samples': 20029632, 'steps': 104320, 'loss/train': 0.37620818614959717} 08/31/2021 08:02:27 - INFO - __main__ - Step 104322: {'lr': 0.00010859822709948853, 'samples': 20029824, 'steps': 104321, 'loss/train': 0.9536052346229553} 08/31/2021 08:02:28 - INFO - __main__ - Step 104323: {'lr': 0.00010859385079271586, 'samples': 20030016, 'steps': 104322, 'loss/train': 1.2062228918075562} 08/31/2021 08:02:28 - INFO - __main__ - Step 104324: {'lr': 0.00010858947454965853, 'samples': 20030208, 'steps': 104323, 'loss/train': 1.2960015535354614} 08/31/2021 08:02:29 - INFO - __main__ - Step 104325: {'lr': 0.0001085850983703186, 'samples': 20030400, 'steps': 104324, 'loss/train': 0.39174968004226685} 08/31/2021 08:02:29 - INFO - __main__ - Step 104326: {'lr': 0.00010858072225469803, 'samples': 20030592, 'steps': 104325, 'loss/train': 1.452306866645813} 08/31/2021 08:02:29 - INFO - __main__ - Step 104327: {'lr': 0.0001085763462027988, 'samples': 20030784, 'steps': 104326, 'loss/train': 1.0849337577819824} 08/31/2021 08:02:31 - INFO - __main__ - Step 104328: {'lr': 0.00010857197021462292, 'samples': 20030976, 'steps': 104327, 'loss/train': 0.9538805484771729} 08/31/2021 08:02:31 - INFO - __main__ - Step 104329: {'lr': 0.0001085675942901723, 'samples': 20031168, 'steps': 104328, 'loss/train': 1.1629655361175537} 08/31/2021 08:02:32 - INFO - __main__ - Step 104330: {'lr': 0.00010856321842944894, 'samples': 20031360, 'steps': 104329, 'loss/train': 0.9765387773513794} 08/31/2021 08:02:32 - INFO - __main__ - Step 104331: {'lr': 0.00010855884263245483, 'samples': 20031552, 'steps': 104330, 'loss/train': 1.0514730215072632} 08/31/2021 08:02:34 - INFO - __main__ - Step 104332: {'lr': 0.00010855446689919191, 'samples': 20031744, 'steps': 104331, 'loss/train': 1.1408883333206177} 08/31/2021 08:02:34 - INFO - __main__ - Step 104333: {'lr': 0.00010855009122966217, 'samples': 20031936, 'steps': 104332, 'loss/train': 1.9902368783950806} 08/31/2021 08:02:34 - INFO - __main__ - Step 104334: {'lr': 0.00010854571562386756, 'samples': 20032128, 'steps': 104333, 'loss/train': 1.2181308269500732} 08/31/2021 08:02:35 - INFO - __main__ - Step 104335: {'lr': 0.00010854134008181007, 'samples': 20032320, 'steps': 104334, 'loss/train': 1.0793300867080688} 08/31/2021 08:02:35 - INFO - __main__ - Step 104336: {'lr': 0.00010853696460349177, 'samples': 20032512, 'steps': 104335, 'loss/train': 0.3611939549446106} 08/31/2021 08:02:35 - INFO - __main__ - Step 104337: {'lr': 0.00010853258918891445, 'samples': 20032704, 'steps': 104336, 'loss/train': 1.0347288846969604} 08/31/2021 08:02:37 - INFO - __main__ - Step 104338: {'lr': 0.00010852821383808015, 'samples': 20032896, 'steps': 104337, 'loss/train': 1.5473384857177734} 08/31/2021 08:02:37 - INFO - __main__ - Step 104339: {'lr': 0.00010852383855099086, 'samples': 20033088, 'steps': 104338, 'loss/train': 1.0050020217895508} 08/31/2021 08:02:38 - INFO - __main__ - Step 104340: {'lr': 0.00010851946332764853, 'samples': 20033280, 'steps': 104339, 'loss/train': 1.1237211227416992} 08/31/2021 08:02:38 - INFO - __main__ - Step 104341: {'lr': 0.00010851508816805516, 'samples': 20033472, 'steps': 104340, 'loss/train': 1.036097764968872} 08/31/2021 08:02:38 - INFO - __main__ - Step 104342: {'lr': 0.00010851071307221272, 'samples': 20033664, 'steps': 104341, 'loss/train': 1.5515506267547607} 08/31/2021 08:02:41 - INFO - __main__ - Step 104343: {'lr': 0.00010850633804012314, 'samples': 20033856, 'steps': 104342, 'loss/train': 1.4524621963500977} 08/31/2021 08:02:41 - INFO - __main__ - Step 104344: {'lr': 0.00010850196307178844, 'samples': 20034048, 'steps': 104343, 'loss/train': 1.3150659799575806} 08/31/2021 08:02:42 - INFO - __main__ - Step 104345: {'lr': 0.00010849758816721056, 'samples': 20034240, 'steps': 104344, 'loss/train': 0.015435438603162766} 08/31/2021 08:02:42 - INFO - __main__ - Step 104346: {'lr': 0.00010849321332639151, 'samples': 20034432, 'steps': 104345, 'loss/train': 1.5368115901947021} 08/31/2021 08:02:42 - INFO - __main__ - Step 104347: {'lr': 0.0001084888385493332, 'samples': 20034624, 'steps': 104346, 'loss/train': 0.014270042069256306} 08/31/2021 08:02:43 - INFO - __main__ - Step 104348: {'lr': 0.00010848446383603767, 'samples': 20034816, 'steps': 104347, 'loss/train': 1.625446081161499} 08/31/2021 08:02:43 - INFO - __main__ - Step 104349: {'lr': 0.00010848008918650682, 'samples': 20035008, 'steps': 104348, 'loss/train': 1.272879958152771} 08/31/2021 08:02:45 - INFO - __main__ - Step 104350: {'lr': 0.00010847571460074276, 'samples': 20035200, 'steps': 104349, 'loss/train': 1.7026585340499878} 08/31/2021 08:02:45 - INFO - __main__ - Step 104351: {'lr': 0.0001084713400787473, 'samples': 20035392, 'steps': 104350, 'loss/train': 1.2103087902069092} 08/31/2021 08:02:45 - INFO - __main__ - Step 104352: {'lr': 0.00010846696562052241, 'samples': 20035584, 'steps': 104351, 'loss/train': 1.5148591995239258} 08/31/2021 08:02:46 - INFO - __main__ - Step 104353: {'lr': 0.00010846259122607016, 'samples': 20035776, 'steps': 104352, 'loss/train': 1.2955151796340942} 08/31/2021 08:02:46 - INFO - __main__ - Step 104354: {'lr': 0.00010845821689539249, 'samples': 20035968, 'steps': 104353, 'loss/train': 0.7139571309089661} 08/31/2021 08:02:48 - INFO - __main__ - Step 104355: {'lr': 0.00010845384262849134, 'samples': 20036160, 'steps': 104354, 'loss/train': 0.9857474565505981} 08/31/2021 08:02:48 - INFO - __main__ - Step 104356: {'lr': 0.00010844946842536873, 'samples': 20036352, 'steps': 104355, 'loss/train': 1.3283944129943848} 08/31/2021 08:02:49 - INFO - __main__ - Step 104357: {'lr': 0.00010844509428602659, 'samples': 20036544, 'steps': 104356, 'loss/train': 1.3511565923690796} 08/31/2021 08:02:49 - INFO - __main__ - Step 104358: {'lr': 0.00010844072021046692, 'samples': 20036736, 'steps': 104357, 'loss/train': 0.9285714030265808} 08/31/2021 08:02:49 - INFO - __main__ - Step 104359: {'lr': 0.00010843634619869167, 'samples': 20036928, 'steps': 104358, 'loss/train': 1.3600823879241943} 08/31/2021 08:02:51 - INFO - __main__ - Step 104360: {'lr': 0.0001084319722507028, 'samples': 20037120, 'steps': 104359, 'loss/train': 1.5284191370010376} 08/31/2021 08:02:52 - INFO - __main__ - Step 104361: {'lr': 0.00010842759836650231, 'samples': 20037312, 'steps': 104360, 'loss/train': 0.4548897445201874} 08/31/2021 08:02:52 - INFO - __main__ - Step 104362: {'lr': 0.00010842322454609216, 'samples': 20037504, 'steps': 104361, 'loss/train': 1.3596723079681396} 08/31/2021 08:02:52 - INFO - __main__ - Step 104363: {'lr': 0.00010841885078947441, 'samples': 20037696, 'steps': 104362, 'loss/train': 1.0639692544937134} 08/31/2021 08:02:53 - INFO - __main__ - Step 104364: {'lr': 0.00010841447709665086, 'samples': 20037888, 'steps': 104363, 'loss/train': 0.6310824155807495} 08/31/2021 08:02:54 - INFO - __main__ - Step 104365: {'lr': 0.00010841010346762356, 'samples': 20038080, 'steps': 104364, 'loss/train': 1.2155629396438599} 08/31/2021 08:02:55 - INFO - __main__ - Step 104366: {'lr': 0.00010840572990239447, 'samples': 20038272, 'steps': 104365, 'loss/train': 1.4544464349746704} 08/31/2021 08:02:55 - INFO - __main__ - Step 104367: {'lr': 0.00010840135640096558, 'samples': 20038464, 'steps': 104366, 'loss/train': 1.0188581943511963} 08/31/2021 08:02:55 - INFO - __main__ - Step 104368: {'lr': 0.00010839698296333885, 'samples': 20038656, 'steps': 104367, 'loss/train': 1.41841721534729} 08/31/2021 08:02:56 - INFO - __main__ - Step 104369: {'lr': 0.00010839260958951628, 'samples': 20038848, 'steps': 104368, 'loss/train': 1.435529112815857} 08/31/2021 08:02:57 - INFO - __main__ - Step 104370: {'lr': 0.00010838823627949978, 'samples': 20039040, 'steps': 104369, 'loss/train': 1.4524978399276733} 08/31/2021 08:02:58 - INFO - __main__ - Step 104371: {'lr': 0.00010838386303329137, 'samples': 20039232, 'steps': 104370, 'loss/train': 1.4407768249511719} 08/31/2021 08:02:58 - INFO - __main__ - Step 104372: {'lr': 0.00010837948985089299, 'samples': 20039424, 'steps': 104371, 'loss/train': 1.021733283996582} 08/31/2021 08:02:58 - INFO - __main__ - Step 104373: {'lr': 0.00010837511673230666, 'samples': 20039616, 'steps': 104372, 'loss/train': 1.1457853317260742} 08/31/2021 08:02:59 - INFO - __main__ - Step 104374: {'lr': 0.0001083707436775343, 'samples': 20039808, 'steps': 104373, 'loss/train': 1.035945177078247} 08/31/2021 08:03:00 - INFO - __main__ - Step 104375: {'lr': 0.00010836637068657787, 'samples': 20040000, 'steps': 104374, 'loss/train': 0.9893151521682739} 08/31/2021 08:03:00 - INFO - __main__ - Step 104376: {'lr': 0.00010836199775943942, 'samples': 20040192, 'steps': 104375, 'loss/train': 1.523581624031067} 08/31/2021 08:03:01 - INFO - __main__ - Step 104377: {'lr': 0.00010835762489612091, 'samples': 20040384, 'steps': 104376, 'loss/train': 0.8361201286315918} 08/31/2021 08:03:01 - INFO - __main__ - Step 104378: {'lr': 0.00010835325209662423, 'samples': 20040576, 'steps': 104377, 'loss/train': 1.328720211982727} 08/31/2021 08:03:02 - INFO - __main__ - Step 104379: {'lr': 0.00010834887936095134, 'samples': 20040768, 'steps': 104378, 'loss/train': 1.1323941946029663} 08/31/2021 08:03:02 - INFO - __main__ - Step 104380: {'lr': 0.00010834450668910428, 'samples': 20040960, 'steps': 104379, 'loss/train': 1.4101953506469727} 08/31/2021 08:03:04 - INFO - __main__ - Step 104381: {'lr': 0.000108340134081085, 'samples': 20041152, 'steps': 104380, 'loss/train': 0.8169834613800049} 08/31/2021 08:03:04 - INFO - __main__ - Step 104382: {'lr': 0.00010833576153689547, 'samples': 20041344, 'steps': 104381, 'loss/train': 1.1597418785095215} 08/31/2021 08:03:05 - INFO - __main__ - Step 104383: {'lr': 0.00010833138905653767, 'samples': 20041536, 'steps': 104382, 'loss/train': 0.913008451461792} 08/31/2021 08:03:05 - INFO - __main__ - Step 104384: {'lr': 0.00010832701664001354, 'samples': 20041728, 'steps': 104383, 'loss/train': 1.2532789707183838} 08/31/2021 08:03:05 - INFO - __main__ - Step 104385: {'lr': 0.00010832264428732508, 'samples': 20041920, 'steps': 104384, 'loss/train': 1.6066054105758667} 08/31/2021 08:03:07 - INFO - __main__ - Step 104386: {'lr': 0.00010831827199847424, 'samples': 20042112, 'steps': 104385, 'loss/train': 2.0591046810150146} 08/31/2021 08:03:07 - INFO - __main__ - Step 104387: {'lr': 0.000108313899773463, 'samples': 20042304, 'steps': 104386, 'loss/train': 1.0307536125183105} 08/31/2021 08:03:08 - INFO - __main__ - Step 104388: {'lr': 0.00010830952761229334, 'samples': 20042496, 'steps': 104387, 'loss/train': 1.057883858680725} 08/31/2021 08:03:08 - INFO - __main__ - Step 104389: {'lr': 0.00010830515551496722, 'samples': 20042688, 'steps': 104388, 'loss/train': 0.8468753099441528} 08/31/2021 08:03:08 - INFO - __main__ - Step 104390: {'lr': 0.0001083007834814867, 'samples': 20042880, 'steps': 104389, 'loss/train': 1.1109611988067627} 08/31/2021 08:03:10 - INFO - __main__ - Step 104391: {'lr': 0.00010829641151185357, 'samples': 20043072, 'steps': 104390, 'loss/train': 1.8418816328048706} 08/31/2021 08:03:10 - INFO - __main__ - Step 104392: {'lr': 0.0001082920396060699, 'samples': 20043264, 'steps': 104391, 'loss/train': 1.5261727571487427} 08/31/2021 08:03:11 - INFO - __main__ - Step 104393: {'lr': 0.00010828766776413762, 'samples': 20043456, 'steps': 104392, 'loss/train': 0.6599792242050171} 08/31/2021 08:03:11 - INFO - __main__ - Step 104394: {'lr': 0.00010828329598605876, 'samples': 20043648, 'steps': 104393, 'loss/train': 1.3374820947647095} 08/31/2021 08:03:11 - INFO - __main__ - Step 104395: {'lr': 0.00010827892427183525, 'samples': 20043840, 'steps': 104394, 'loss/train': 1.6539791822433472} 08/31/2021 08:03:12 - INFO - __main__ - Step 104396: {'lr': 0.00010827455262146907, 'samples': 20044032, 'steps': 104395, 'loss/train': 1.0646864175796509} 08/31/2021 08:03:14 - INFO - __main__ - Step 104397: {'lr': 0.0001082701810349622, 'samples': 20044224, 'steps': 104396, 'loss/train': 1.2400615215301514} 08/31/2021 08:03:14 - INFO - __main__ - Step 104398: {'lr': 0.0001082658095123166, 'samples': 20044416, 'steps': 104397, 'loss/train': 1.2150068283081055} 08/31/2021 08:03:15 - INFO - __main__ - Step 104399: {'lr': 0.00010826143805353423, 'samples': 20044608, 'steps': 104398, 'loss/train': 1.0619193315505981} 08/31/2021 08:03:15 - INFO - __main__ - Step 104400: {'lr': 0.00010825706665861707, 'samples': 20044800, 'steps': 104399, 'loss/train': 1.1928907632827759} 08/31/2021 08:03:15 - INFO - __main__ - Step 104401: {'lr': 0.00010825269532756707, 'samples': 20044992, 'steps': 104400, 'loss/train': 0.9103001356124878} 08/31/2021 08:03:17 - INFO - __main__ - Step 104402: {'lr': 0.00010824832406038623, 'samples': 20045184, 'steps': 104401, 'loss/train': 0.8814652562141418} 08/31/2021 08:03:17 - INFO - __main__ - Step 104403: {'lr': 0.00010824395285707653, 'samples': 20045376, 'steps': 104402, 'loss/train': 1.263675332069397} 08/31/2021 08:03:18 - INFO - __main__ - Step 104404: {'lr': 0.00010823958171763998, 'samples': 20045568, 'steps': 104403, 'loss/train': 0.9074292778968811} 08/31/2021 08:03:18 - INFO - __main__ - Step 104405: {'lr': 0.00010823521064207839, 'samples': 20045760, 'steps': 104404, 'loss/train': 1.1750075817108154} 08/31/2021 08:03:18 - INFO - __main__ - Step 104406: {'lr': 0.00010823083963039384, 'samples': 20045952, 'steps': 104405, 'loss/train': 1.8499526977539062} 08/31/2021 08:03:20 - INFO - __main__ - Step 104407: {'lr': 0.00010822646868258831, 'samples': 20046144, 'steps': 104406, 'loss/train': 1.4421637058258057} 08/31/2021 08:03:21 - INFO - __main__ - Step 104408: {'lr': 0.00010822209779866371, 'samples': 20046336, 'steps': 104407, 'loss/train': 1.0452871322631836} 08/31/2021 08:03:21 - INFO - __main__ - Step 104409: {'lr': 0.00010821772697862206, 'samples': 20046528, 'steps': 104408, 'loss/train': 0.14994937181472778} 08/31/2021 08:03:21 - INFO - __main__ - Step 104410: {'lr': 0.0001082133562224653, 'samples': 20046720, 'steps': 104409, 'loss/train': 1.049034595489502} 08/31/2021 08:03:22 - INFO - __main__ - Step 104411: {'lr': 0.00010820898553019545, 'samples': 20046912, 'steps': 104410, 'loss/train': 1.3680700063705444} 08/31/2021 08:03:22 - INFO - __main__ - Step 104412: {'lr': 0.00010820461490181441, 'samples': 20047104, 'steps': 104411, 'loss/train': 1.3265591859817505} 08/31/2021 08:03:24 - INFO - __main__ - Step 104413: {'lr': 0.0001082002443373242, 'samples': 20047296, 'steps': 104412, 'loss/train': 1.195838451385498} 08/31/2021 08:03:24 - INFO - __main__ - Step 104414: {'lr': 0.00010819587383672678, 'samples': 20047488, 'steps': 104413, 'loss/train': 1.0989298820495605} 08/31/2021 08:03:25 - INFO - __main__ - Step 104415: {'lr': 0.0001081915034000241, 'samples': 20047680, 'steps': 104414, 'loss/train': 0.733390748500824} 08/31/2021 08:03:25 - INFO - __main__ - Step 104416: {'lr': 0.0001081871330272181, 'samples': 20047872, 'steps': 104415, 'loss/train': 1.3031482696533203} 08/31/2021 08:03:25 - INFO - __main__ - Step 104417: {'lr': 0.00010818276271831093, 'samples': 20048064, 'steps': 104416, 'loss/train': 0.06029035896062851} 08/31/2021 08:03:27 - INFO - __main__ - Step 104418: {'lr': 0.00010817839247330432, 'samples': 20048256, 'steps': 104417, 'loss/train': 0.6051499247550964} 08/31/2021 08:03:27 - INFO - __main__ - Step 104419: {'lr': 0.00010817402229220032, 'samples': 20048448, 'steps': 104418, 'loss/train': 1.6196955442428589} 08/31/2021 08:03:28 - INFO - __main__ - Step 104420: {'lr': 0.00010816965217500093, 'samples': 20048640, 'steps': 104419, 'loss/train': 0.9316592216491699} 08/31/2021 08:03:28 - INFO - __main__ - Step 104421: {'lr': 0.00010816528212170812, 'samples': 20048832, 'steps': 104420, 'loss/train': 1.2953218221664429} 08/31/2021 08:03:28 - INFO - __main__ - Step 104422: {'lr': 0.00010816091213232385, 'samples': 20049024, 'steps': 104421, 'loss/train': 1.294671893119812} 08/31/2021 08:03:30 - INFO - __main__ - Step 104423: {'lr': 0.00010815654220685006, 'samples': 20049216, 'steps': 104422, 'loss/train': 1.0423383712768555} 08/31/2021 08:03:30 - INFO - __main__ - Step 104424: {'lr': 0.00010815217234528873, 'samples': 20049408, 'steps': 104423, 'loss/train': 0.6951054930686951} 08/31/2021 08:03:31 - INFO - __main__ - Step 104425: {'lr': 0.00010814780254764186, 'samples': 20049600, 'steps': 104424, 'loss/train': 1.9297553300857544} 08/31/2021 08:03:31 - INFO - __main__ - Step 104426: {'lr': 0.00010814343281391143, 'samples': 20049792, 'steps': 104425, 'loss/train': 1.254754662513733} 08/31/2021 08:03:31 - INFO - __main__ - Step 104427: {'lr': 0.00010813906314409933, 'samples': 20049984, 'steps': 104426, 'loss/train': 1.4836337566375732} 08/31/2021 08:03:33 - INFO - __main__ - Step 104428: {'lr': 0.0001081346935382076, 'samples': 20050176, 'steps': 104427, 'loss/train': 0.9310618042945862} 08/31/2021 08:03:34 - INFO - __main__ - Step 104429: {'lr': 0.0001081303239962382, 'samples': 20050368, 'steps': 104428, 'loss/train': 1.3204272985458374} 08/31/2021 08:03:34 - INFO - __main__ - Step 104430: {'lr': 0.00010812595451819315, 'samples': 20050560, 'steps': 104429, 'loss/train': 1.5565259456634521} 08/31/2021 08:03:34 - INFO - __main__ - Step 104431: {'lr': 0.0001081215851040743, 'samples': 20050752, 'steps': 104430, 'loss/train': 0.03714314103126526} 08/31/2021 08:03:35 - INFO - __main__ - Step 104432: {'lr': 0.00010811721575388364, 'samples': 20050944, 'steps': 104431, 'loss/train': 1.4244199991226196} 08/31/2021 08:03:36 - INFO - __main__ - Step 104433: {'lr': 0.0001081128464676232, 'samples': 20051136, 'steps': 104432, 'loss/train': 1.3729808330535889} 08/31/2021 08:03:36 - INFO - __main__ - Step 104434: {'lr': 0.00010810847724529491, 'samples': 20051328, 'steps': 104433, 'loss/train': 1.0948024988174438} 08/31/2021 08:03:37 - INFO - __main__ - Step 104435: {'lr': 0.00010810410808690076, 'samples': 20051520, 'steps': 104434, 'loss/train': 1.1162762641906738} 08/31/2021 08:03:37 - INFO - __main__ - Step 104436: {'lr': 0.00010809973899244269, 'samples': 20051712, 'steps': 104435, 'loss/train': 1.2312233448028564} 08/31/2021 08:03:38 - INFO - __main__ - Step 104437: {'lr': 0.00010809536996192271, 'samples': 20051904, 'steps': 104436, 'loss/train': 0.2374889850616455} 08/31/2021 08:03:39 - INFO - __main__ - Step 104438: {'lr': 0.00010809100099534274, 'samples': 20052096, 'steps': 104437, 'loss/train': 1.0924909114837646} 08/31/2021 08:03:40 - INFO - __main__ - Step 104439: {'lr': 0.0001080866320927048, 'samples': 20052288, 'steps': 104438, 'loss/train': 1.5007307529449463} 08/31/2021 08:03:40 - INFO - __main__ - Step 104440: {'lr': 0.00010808226325401082, 'samples': 20052480, 'steps': 104439, 'loss/train': 1.3476861715316772} 08/31/2021 08:03:40 - INFO - __main__ - Step 104441: {'lr': 0.00010807789447926281, 'samples': 20052672, 'steps': 104440, 'loss/train': 0.030584564432501793} 08/31/2021 08:03:41 - INFO - __main__ - Step 104442: {'lr': 0.00010807352576846268, 'samples': 20052864, 'steps': 104441, 'loss/train': 1.2162587642669678} 08/31/2021 08:03:41 - INFO - __main__ - Step 104443: {'lr': 0.00010806915712161244, 'samples': 20053056, 'steps': 104442, 'loss/train': 5.784353733062744} 08/31/2021 08:03:43 - INFO - __main__ - Step 104444: {'lr': 0.00010806478853871413, 'samples': 20053248, 'steps': 104443, 'loss/train': 1.0228818655014038} 08/31/2021 08:03:43 - INFO - __main__ - Step 104445: {'lr': 0.00010806042001976954, 'samples': 20053440, 'steps': 104444, 'loss/train': 1.324083685874939} 08/31/2021 08:03:43 - INFO - __main__ - Step 104446: {'lr': 0.00010805605156478076, 'samples': 20053632, 'steps': 104445, 'loss/train': 1.2937071323394775} 08/31/2021 08:03:44 - INFO - __main__ - Step 104447: {'lr': 0.00010805168317374972, 'samples': 20053824, 'steps': 104446, 'loss/train': 1.331533670425415} 08/31/2021 08:03:44 - INFO - __main__ - Step 104448: {'lr': 0.0001080473148466784, 'samples': 20054016, 'steps': 104447, 'loss/train': 1.0548697710037231} 08/31/2021 08:03:45 - INFO - __main__ - Step 104449: {'lr': 0.00010804294658356875, 'samples': 20054208, 'steps': 104448, 'loss/train': 1.7064030170440674} 08/31/2021 08:03:46 - INFO - __main__ - Step 104450: {'lr': 0.00010803857838442279, 'samples': 20054400, 'steps': 104449, 'loss/train': 1.2293751239776611} 08/31/2021 08:03:46 - INFO - __main__ - Step 104451: {'lr': 0.00010803421024924246, 'samples': 20054592, 'steps': 104450, 'loss/train': 1.7388584613800049} 08/31/2021 08:03:47 - INFO - __main__ - Step 104452: {'lr': 0.00010802984217802968, 'samples': 20054784, 'steps': 104451, 'loss/train': 1.215920090675354} 08/31/2021 08:03:47 - INFO - __main__ - Step 104453: {'lr': 0.00010802547417078651, 'samples': 20054976, 'steps': 104452, 'loss/train': 1.7493537664413452} 08/31/2021 08:03:49 - INFO - __main__ - Step 104454: {'lr': 0.00010802110622751485, 'samples': 20055168, 'steps': 104453, 'loss/train': 1.0171843767166138} 08/31/2021 08:03:50 - INFO - __main__ - Step 104455: {'lr': 0.00010801673834821668, 'samples': 20055360, 'steps': 104454, 'loss/train': 0.7855429649353027} 08/31/2021 08:03:50 - INFO - __main__ - Step 104456: {'lr': 0.00010801237053289398, 'samples': 20055552, 'steps': 104455, 'loss/train': 1.193865180015564} 08/31/2021 08:03:51 - INFO - __main__ - Step 104457: {'lr': 0.00010800800278154882, 'samples': 20055744, 'steps': 104456, 'loss/train': 1.2304810285568237} 08/31/2021 08:03:51 - INFO - __main__ - Step 104458: {'lr': 0.00010800363509418296, 'samples': 20055936, 'steps': 104457, 'loss/train': 1.0248245000839233} 08/31/2021 08:03:51 - INFO - __main__ - Step 104459: {'lr': 0.00010799926747079847, 'samples': 20056128, 'steps': 104458, 'loss/train': 1.2227973937988281} 08/31/2021 08:03:53 - INFO - __main__ - Step 104460: {'lr': 0.00010799489991139732, 'samples': 20056320, 'steps': 104459, 'loss/train': 0.8643730878829956} 08/31/2021 08:03:54 - INFO - __main__ - Step 104461: {'lr': 0.00010799053241598147, 'samples': 20056512, 'steps': 104460, 'loss/train': 0.8941879272460938} 08/31/2021 08:03:54 - INFO - __main__ - Step 104462: {'lr': 0.00010798616498455291, 'samples': 20056704, 'steps': 104461, 'loss/train': 0.9701585173606873} 08/31/2021 08:03:55 - INFO - __main__ - Step 104463: {'lr': 0.0001079817976171136, 'samples': 20056896, 'steps': 104462, 'loss/train': 0.6930187344551086} 08/31/2021 08:03:55 - INFO - __main__ - Step 104464: {'lr': 0.00010797743031366546, 'samples': 20057088, 'steps': 104463, 'loss/train': 0.02251790650188923} 08/31/2021 08:03:55 - INFO - __main__ - Step 104465: {'lr': 0.00010797306307421053, 'samples': 20057280, 'steps': 104464, 'loss/train': 0.05279465764760971} 08/31/2021 08:03:57 - INFO - __main__ - Step 104466: {'lr': 0.00010796869589875077, 'samples': 20057472, 'steps': 104465, 'loss/train': 1.3960996866226196} 08/31/2021 08:03:58 - INFO - __main__ - Step 104467: {'lr': 0.0001079643287872881, 'samples': 20057664, 'steps': 104466, 'loss/train': 0.06265833228826523} 08/31/2021 08:03:58 - INFO - __main__ - Step 104468: {'lr': 0.0001079599617398245, 'samples': 20057856, 'steps': 104467, 'loss/train': 0.09249033033847809} 08/31/2021 08:03:58 - INFO - __main__ - Step 104469: {'lr': 0.00010795559475636196, 'samples': 20058048, 'steps': 104468, 'loss/train': 2.169793128967285} 08/31/2021 08:03:59 - INFO - __main__ - Step 104470: {'lr': 0.00010795122783690242, 'samples': 20058240, 'steps': 104469, 'loss/train': 1.6816859245300293} 08/31/2021 08:03:59 - INFO - __main__ - Step 104471: {'lr': 0.00010794686098144799, 'samples': 20058432, 'steps': 104470, 'loss/train': 1.0477409362792969} 08/31/2021 08:04:01 - INFO - __main__ - Step 104472: {'lr': 0.00010794249419000038, 'samples': 20058624, 'steps': 104471, 'loss/train': 1.3475059270858765} 08/31/2021 08:04:01 - INFO - __main__ - Step 104473: {'lr': 0.00010793812746256171, 'samples': 20058816, 'steps': 104472, 'loss/train': 1.701497197151184} 08/31/2021 08:04:02 - INFO - __main__ - Step 104474: {'lr': 0.00010793376079913395, 'samples': 20059008, 'steps': 104473, 'loss/train': 0.7407916784286499} 08/31/2021 08:04:02 - INFO - __main__ - Step 104475: {'lr': 0.000107929394199719, 'samples': 20059200, 'steps': 104474, 'loss/train': 0.4885394275188446} 08/31/2021 08:04:02 - INFO - __main__ - Step 104476: {'lr': 0.00010792502766431891, 'samples': 20059392, 'steps': 104475, 'loss/train': 0.8336019515991211} 08/31/2021 08:04:04 - INFO - __main__ - Step 104477: {'lr': 0.00010792066119293559, 'samples': 20059584, 'steps': 104476, 'loss/train': 0.5304927229881287} 08/31/2021 08:04:04 - INFO - __main__ - Step 104478: {'lr': 0.00010791629478557105, 'samples': 20059776, 'steps': 104477, 'loss/train': 1.19675874710083} 08/31/2021 08:04:05 - INFO - __main__ - Step 104479: {'lr': 0.00010791192844222722, 'samples': 20059968, 'steps': 104478, 'loss/train': 1.1773605346679688} 08/31/2021 08:04:05 - INFO - __main__ - Step 104480: {'lr': 0.00010790756216290606, 'samples': 20060160, 'steps': 104479, 'loss/train': 1.5096771717071533} 08/31/2021 08:04:06 - INFO - __main__ - Step 104481: {'lr': 0.00010790319594760958, 'samples': 20060352, 'steps': 104480, 'loss/train': 1.2078269720077515} 08/31/2021 08:04:07 - INFO - __main__ - Step 104482: {'lr': 0.00010789882979633974, 'samples': 20060544, 'steps': 104481, 'loss/train': 1.5615143775939941} 08/31/2021 08:04:08 - INFO - __main__ - Step 104483: {'lr': 0.0001078944637090985, 'samples': 20060736, 'steps': 104482, 'loss/train': 1.073015809059143} 08/31/2021 08:04:08 - INFO - __main__ - Step 104484: {'lr': 0.0001078900976858879, 'samples': 20060928, 'steps': 104483, 'loss/train': 0.641765296459198} 08/31/2021 08:04:08 - INFO - __main__ - Step 104485: {'lr': 0.00010788573172670973, 'samples': 20061120, 'steps': 104484, 'loss/train': 0.9834431409835815} 08/31/2021 08:04:09 - INFO - __main__ - Step 104486: {'lr': 0.00010788136583156604, 'samples': 20061312, 'steps': 104485, 'loss/train': 1.3778536319732666} 08/31/2021 08:04:09 - INFO - __main__ - Step 104487: {'lr': 0.00010787700000045886, 'samples': 20061504, 'steps': 104486, 'loss/train': 1.7285436391830444} 08/31/2021 08:04:11 - INFO - __main__ - Step 104488: {'lr': 0.00010787263423339008, 'samples': 20061696, 'steps': 104487, 'loss/train': 1.8484793901443481} 08/31/2021 08:04:11 - INFO - __main__ - Step 104489: {'lr': 0.00010786826853036169, 'samples': 20061888, 'steps': 104488, 'loss/train': 1.483098030090332} 08/31/2021 08:04:12 - INFO - __main__ - Step 104490: {'lr': 0.00010786390289137569, 'samples': 20062080, 'steps': 104489, 'loss/train': 1.1446243524551392} 08/31/2021 08:04:12 - INFO - __main__ - Step 104491: {'lr': 0.000107859537316434, 'samples': 20062272, 'steps': 104490, 'loss/train': 0.014389042742550373} 08/31/2021 08:04:12 - INFO - __main__ - Step 104492: {'lr': 0.00010785517180553864, 'samples': 20062464, 'steps': 104491, 'loss/train': 0.6298662424087524} 08/31/2021 08:04:13 - INFO - __main__ - Step 104493: {'lr': 0.00010785080635869152, 'samples': 20062656, 'steps': 104492, 'loss/train': 0.9994999170303345} 08/31/2021 08:04:14 - INFO - __main__ - Step 104494: {'lr': 0.00010784644097589463, 'samples': 20062848, 'steps': 104493, 'loss/train': 1.4632960557937622} 08/31/2021 08:04:15 - INFO - __main__ - Step 104495: {'lr': 0.00010784207565714995, 'samples': 20063040, 'steps': 104494, 'loss/train': 1.4936941862106323} 08/31/2021 08:04:15 - INFO - __main__ - Step 104496: {'lr': 0.00010783771040245944, 'samples': 20063232, 'steps': 104495, 'loss/train': 0.09050046652555466} 08/31/2021 08:04:16 - INFO - __main__ - Step 104497: {'lr': 0.00010783334521182505, 'samples': 20063424, 'steps': 104496, 'loss/train': 0.9980858564376831} 08/31/2021 08:04:16 - INFO - __main__ - Step 104498: {'lr': 0.00010782898008524885, 'samples': 20063616, 'steps': 104497, 'loss/train': 0.22799573838710785} 08/31/2021 08:04:17 - INFO - __main__ - Step 104499: {'lr': 0.00010782461502273267, 'samples': 20063808, 'steps': 104498, 'loss/train': 0.7820613980293274} 08/31/2021 08:04:18 - INFO - __main__ - Step 104500: {'lr': 0.00010782025002427848, 'samples': 20064000, 'steps': 104499, 'loss/train': 1.0393059253692627} 08/31/2021 08:04:18 - INFO - __main__ - Step 104501: {'lr': 0.0001078158850898883, 'samples': 20064192, 'steps': 104500, 'loss/train': 1.5033518075942993} 08/31/2021 08:04:19 - INFO - __main__ - Step 104502: {'lr': 0.00010781152021956408, 'samples': 20064384, 'steps': 104501, 'loss/train': 0.97944176197052} 08/31/2021 08:04:19 - INFO - __main__ - Step 104503: {'lr': 0.00010780715541330783, 'samples': 20064576, 'steps': 104502, 'loss/train': 1.500643253326416} 08/31/2021 08:04:21 - INFO - __main__ - Step 104504: {'lr': 0.00010780279067112145, 'samples': 20064768, 'steps': 104503, 'loss/train': 1.0282241106033325} 08/31/2021 08:04:21 - INFO - __main__ - Step 104505: {'lr': 0.00010779842599300696, 'samples': 20064960, 'steps': 104504, 'loss/train': 0.7776840925216675} 08/31/2021 08:04:22 - INFO - __main__ - Step 104506: {'lr': 0.00010779406137896627, 'samples': 20065152, 'steps': 104505, 'loss/train': 1.4798444509506226} 08/31/2021 08:04:22 - INFO - __main__ - Step 104507: {'lr': 0.00010778969682900141, 'samples': 20065344, 'steps': 104506, 'loss/train': 0.5772438049316406} 08/31/2021 08:04:22 - INFO - __main__ - Step 104508: {'lr': 0.00010778533234311433, 'samples': 20065536, 'steps': 104507, 'loss/train': 1.0472975969314575} 08/31/2021 08:04:23 - INFO - __main__ - Step 104509: {'lr': 0.00010778096792130695, 'samples': 20065728, 'steps': 104508, 'loss/train': 0.6092252731323242} 08/31/2021 08:04:23 - INFO - __main__ - Step 104510: {'lr': 0.0001077766035635813, 'samples': 20065920, 'steps': 104509, 'loss/train': 0.4656361937522888} 08/31/2021 08:04:25 - INFO - __main__ - Step 104511: {'lr': 0.0001077722392699394, 'samples': 20066112, 'steps': 104510, 'loss/train': 1.1661752462387085} 08/31/2021 08:04:25 - INFO - __main__ - Step 104512: {'lr': 0.00010776787504038305, 'samples': 20066304, 'steps': 104511, 'loss/train': 0.04143400490283966} 08/31/2021 08:04:26 - INFO - __main__ - Step 104513: {'lr': 0.00010776351087491426, 'samples': 20066496, 'steps': 104512, 'loss/train': 0.7126590609550476} 08/31/2021 08:04:26 - INFO - __main__ - Step 104514: {'lr': 0.00010775914677353507, 'samples': 20066688, 'steps': 104513, 'loss/train': 0.895695686340332} 08/31/2021 08:04:26 - INFO - __main__ - Step 104515: {'lr': 0.00010775478273624743, 'samples': 20066880, 'steps': 104514, 'loss/train': 1.4931379556655884} 08/31/2021 08:04:28 - INFO - __main__ - Step 104516: {'lr': 0.00010775041876305328, 'samples': 20067072, 'steps': 104515, 'loss/train': 1.2084861993789673} 08/31/2021 08:04:29 - INFO - __main__ - Step 104517: {'lr': 0.00010774605485395458, 'samples': 20067264, 'steps': 104516, 'loss/train': 1.4896782636642456} 08/31/2021 08:04:29 - INFO - __main__ - Step 104518: {'lr': 0.00010774169100895332, 'samples': 20067456, 'steps': 104517, 'loss/train': 0.20414525270462036} 08/31/2021 08:04:30 - INFO - __main__ - Step 104519: {'lr': 0.00010773732722805146, 'samples': 20067648, 'steps': 104518, 'loss/train': 1.4545546770095825} 08/31/2021 08:04:30 - INFO - __main__ - Step 104520: {'lr': 0.00010773296351125095, 'samples': 20067840, 'steps': 104519, 'loss/train': 2.247368097305298} 08/31/2021 08:04:32 - INFO - __main__ - Step 104521: {'lr': 0.00010772859985855379, 'samples': 20068032, 'steps': 104520, 'loss/train': 0.8320226073265076} 08/31/2021 08:04:32 - INFO - __main__ - Step 104522: {'lr': 0.00010772423626996192, 'samples': 20068224, 'steps': 104521, 'loss/train': 1.5350579023361206} 08/31/2021 08:04:32 - INFO - __main__ - Step 104523: {'lr': 0.00010771987274547732, 'samples': 20068416, 'steps': 104522, 'loss/train': 0.8041763305664062} 08/31/2021 08:04:33 - INFO - __main__ - Step 104524: {'lr': 0.00010771550928510196, 'samples': 20068608, 'steps': 104523, 'loss/train': 0.814879298210144} 08/31/2021 08:04:33 - INFO - __main__ - Step 104525: {'lr': 0.00010771114588883787, 'samples': 20068800, 'steps': 104524, 'loss/train': 1.5745877027511597} 08/31/2021 08:04:33 - INFO - __main__ - Step 104526: {'lr': 0.00010770678255668684, 'samples': 20068992, 'steps': 104525, 'loss/train': 0.9694482088088989} 08/31/2021 08:04:35 - INFO - __main__ - Step 104527: {'lr': 0.00010770241928865097, 'samples': 20069184, 'steps': 104526, 'loss/train': 1.3065396547317505} 08/31/2021 08:04:36 - INFO - __main__ - Step 104528: {'lr': 0.00010769805608473218, 'samples': 20069376, 'steps': 104527, 'loss/train': 0.815649151802063} 08/31/2021 08:04:36 - INFO - __main__ - Step 104529: {'lr': 0.00010769369294493245, 'samples': 20069568, 'steps': 104528, 'loss/train': 0.9915851950645447} 08/31/2021 08:04:36 - INFO - __main__ - Step 104530: {'lr': 0.00010768932986925373, 'samples': 20069760, 'steps': 104529, 'loss/train': 1.3303602933883667} 08/31/2021 08:04:37 - INFO - __main__ - Step 104531: {'lr': 0.00010768496685769802, 'samples': 20069952, 'steps': 104530, 'loss/train': 0.017187627032399178} 08/31/2021 08:04:38 - INFO - __main__ - Step 104532: {'lr': 0.00010768060391026727, 'samples': 20070144, 'steps': 104531, 'loss/train': 0.9177713990211487} 08/31/2021 08:04:39 - INFO - __main__ - Step 104533: {'lr': 0.0001076762410269634, 'samples': 20070336, 'steps': 104532, 'loss/train': 0.16952422261238098} 08/31/2021 08:04:39 - INFO - __main__ - Step 104534: {'lr': 0.00010767187820778848, 'samples': 20070528, 'steps': 104533, 'loss/train': 1.1552261114120483} 08/31/2021 08:04:39 - INFO - __main__ - Step 104535: {'lr': 0.0001076675154527444, 'samples': 20070720, 'steps': 104534, 'loss/train': 0.8159119486808777} 08/31/2021 08:04:40 - INFO - __main__ - Step 104536: {'lr': 0.00010766315276183323, 'samples': 20070912, 'steps': 104535, 'loss/train': 1.6227320432662964} 08/31/2021 08:04:40 - INFO - __main__ - Step 104537: {'lr': 0.00010765879013505673, 'samples': 20071104, 'steps': 104536, 'loss/train': 0.5254586935043335} 08/31/2021 08:04:42 - INFO - __main__ - Step 104538: {'lr': 0.000107654427572417, 'samples': 20071296, 'steps': 104537, 'loss/train': 1.1332038640975952} 08/31/2021 08:04:42 - INFO - __main__ - Step 104539: {'lr': 0.00010765006507391601, 'samples': 20071488, 'steps': 104538, 'loss/train': 0.5247661471366882} 08/31/2021 08:04:43 - INFO - __main__ - Step 104540: {'lr': 0.00010764570263955567, 'samples': 20071680, 'steps': 104539, 'loss/train': 1.0600221157073975} 08/31/2021 08:04:43 - INFO - __main__ - Step 104541: {'lr': 0.000107641340269338, 'samples': 20071872, 'steps': 104540, 'loss/train': 1.1430710554122925} 08/31/2021 08:04:43 - INFO - __main__ - Step 104542: {'lr': 0.00010763697796326493, 'samples': 20072064, 'steps': 104541, 'loss/train': 1.1467337608337402} 08/31/2021 08:04:45 - INFO - __main__ - Step 104543: {'lr': 0.00010763261572133845, 'samples': 20072256, 'steps': 104542, 'loss/train': 1.1853269338607788} 08/31/2021 08:04:45 - INFO - __main__ - Step 104544: {'lr': 0.00010762825354356054, 'samples': 20072448, 'steps': 104543, 'loss/train': 1.1177455186843872} 08/31/2021 08:04:46 - INFO - __main__ - Step 104545: {'lr': 0.00010762389142993312, 'samples': 20072640, 'steps': 104544, 'loss/train': 1.3116600513458252} 08/31/2021 08:04:46 - INFO - __main__ - Step 104546: {'lr': 0.00010761952938045816, 'samples': 20072832, 'steps': 104545, 'loss/train': 1.1077669858932495} 08/31/2021 08:04:46 - INFO - __main__ - Step 104547: {'lr': 0.00010761516739513777, 'samples': 20073024, 'steps': 104546, 'loss/train': 1.0929042100906372} 08/31/2021 08:04:48 - INFO - __main__ - Step 104548: {'lr': 0.00010761080547397367, 'samples': 20073216, 'steps': 104547, 'loss/train': 1.2518433332443237} 08/31/2021 08:04:48 - INFO - __main__ - Step 104549: {'lr': 0.00010760644361696795, 'samples': 20073408, 'steps': 104548, 'loss/train': 1.4887983798980713} 08/31/2021 08:04:49 - INFO - __main__ - Step 104550: {'lr': 0.00010760208182412257, 'samples': 20073600, 'steps': 104549, 'loss/train': 0.8652244210243225} 08/31/2021 08:04:49 - INFO - __main__ - Step 104551: {'lr': 0.0001075977200954395, 'samples': 20073792, 'steps': 104550, 'loss/train': 1.444751501083374} 08/31/2021 08:04:49 - INFO - __main__ - Step 104552: {'lr': 0.00010759335843092068, 'samples': 20073984, 'steps': 104551, 'loss/train': 0.7507429122924805} 08/31/2021 08:04:51 - INFO - __main__ - Step 104553: {'lr': 0.00010758899683056811, 'samples': 20074176, 'steps': 104552, 'loss/train': 1.3043897151947021} 08/31/2021 08:04:51 - INFO - __main__ - Step 104554: {'lr': 0.00010758463529438376, 'samples': 20074368, 'steps': 104553, 'loss/train': 0.9317770004272461} 08/31/2021 08:04:52 - INFO - __main__ - Step 104555: {'lr': 0.00010758027382236953, 'samples': 20074560, 'steps': 104554, 'loss/train': 0.9059991836547852} 08/31/2021 08:04:52 - INFO - __main__ - Step 104556: {'lr': 0.00010757591241452749, 'samples': 20074752, 'steps': 104555, 'loss/train': 1.2000700235366821} 08/31/2021 08:04:52 - INFO - __main__ - Step 104557: {'lr': 0.00010757155107085951, 'samples': 20074944, 'steps': 104556, 'loss/train': 0.7252821922302246} 08/31/2021 08:04:54 - INFO - __main__ - Step 104558: {'lr': 0.00010756718979136768, 'samples': 20075136, 'steps': 104557, 'loss/train': 0.21762479841709137} 08/31/2021 08:04:54 - INFO - __main__ - Step 104559: {'lr': 0.0001075628285760538, 'samples': 20075328, 'steps': 104558, 'loss/train': 1.7156147956848145} 08/31/2021 08:04:55 - INFO - __main__ - Step 104560: {'lr': 0.0001075584674249199, 'samples': 20075520, 'steps': 104559, 'loss/train': 0.2892569899559021} 08/31/2021 08:04:55 - INFO - __main__ - Step 104561: {'lr': 0.00010755410633796797, 'samples': 20075712, 'steps': 104560, 'loss/train': 1.6067363023757935} 08/31/2021 08:04:55 - INFO - __main__ - Step 104562: {'lr': 0.00010754974531519995, 'samples': 20075904, 'steps': 104561, 'loss/train': 0.7394968867301941} 08/31/2021 08:04:57 - INFO - __main__ - Step 104563: {'lr': 0.00010754538435661781, 'samples': 20076096, 'steps': 104562, 'loss/train': 1.1136362552642822} 08/31/2021 08:04:58 - INFO - __main__ - Step 104564: {'lr': 0.00010754102346222353, 'samples': 20076288, 'steps': 104563, 'loss/train': 1.3241016864776611} 08/31/2021 08:04:58 - INFO - __main__ - Step 104565: {'lr': 0.00010753666263201906, 'samples': 20076480, 'steps': 104564, 'loss/train': 0.8167480230331421} 08/31/2021 08:04:59 - INFO - __main__ - Step 104566: {'lr': 0.00010753230186600638, 'samples': 20076672, 'steps': 104565, 'loss/train': 0.4793672561645508} 08/31/2021 08:04:59 - INFO - __main__ - Step 104567: {'lr': 0.00010752794116418745, 'samples': 20076864, 'steps': 104566, 'loss/train': 1.606521487236023} 08/31/2021 08:04:59 - INFO - __main__ - Step 104568: {'lr': 0.00010752358052656422, 'samples': 20077056, 'steps': 104567, 'loss/train': 1.0524157285690308} 08/31/2021 08:05:01 - INFO - __main__ - Step 104569: {'lr': 0.00010751921995313876, 'samples': 20077248, 'steps': 104568, 'loss/train': 1.4549187421798706} 08/31/2021 08:05:02 - INFO - __main__ - Step 104570: {'lr': 0.00010751485944391288, 'samples': 20077440, 'steps': 104569, 'loss/train': 1.4777249097824097} 08/31/2021 08:05:02 - INFO - __main__ - Step 104571: {'lr': 0.00010751049899888856, 'samples': 20077632, 'steps': 104570, 'loss/train': 1.7868447303771973} 08/31/2021 08:05:02 - INFO - __main__ - Step 104572: {'lr': 0.00010750613861806783, 'samples': 20077824, 'steps': 104571, 'loss/train': 0.9960811734199524} 08/31/2021 08:05:03 - INFO - __main__ - Step 104573: {'lr': 0.00010750177830145264, 'samples': 20078016, 'steps': 104572, 'loss/train': 0.9786851406097412} 08/31/2021 08:05:03 - INFO - __main__ - Step 104574: {'lr': 0.00010749741804904494, 'samples': 20078208, 'steps': 104573, 'loss/train': 1.1850024461746216} 08/31/2021 08:05:05 - INFO - __main__ - Step 104575: {'lr': 0.00010749305786084671, 'samples': 20078400, 'steps': 104574, 'loss/train': 1.442749261856079} 08/31/2021 08:05:05 - INFO - __main__ - Step 104576: {'lr': 0.0001074886977368599, 'samples': 20078592, 'steps': 104575, 'loss/train': 0.42224010825157166} 08/31/2021 08:05:05 - INFO - __main__ - Step 104577: {'lr': 0.00010748433767708649, 'samples': 20078784, 'steps': 104576, 'loss/train': 0.6404814720153809} 08/31/2021 08:05:06 - INFO - __main__ - Step 104578: {'lr': 0.00010747997768152845, 'samples': 20078976, 'steps': 104577, 'loss/train': 0.6454488039016724} 08/31/2021 08:05:06 - INFO - __main__ - Step 104579: {'lr': 0.00010747561775018771, 'samples': 20079168, 'steps': 104578, 'loss/train': 0.9087527990341187} 08/31/2021 08:05:07 - INFO - __main__ - Step 104580: {'lr': 0.00010747125788306636, 'samples': 20079360, 'steps': 104579, 'loss/train': 0.6778385639190674} 08/31/2021 08:05:08 - INFO - __main__ - Step 104581: {'lr': 0.00010746689808016619, 'samples': 20079552, 'steps': 104580, 'loss/train': 0.8183732032775879} 08/31/2021 08:05:09 - INFO - __main__ - Step 104582: {'lr': 0.0001074625383414892, 'samples': 20079744, 'steps': 104581, 'loss/train': 1.2751672267913818} 08/31/2021 08:05:09 - INFO - __main__ - Step 104583: {'lr': 0.00010745817866703741, 'samples': 20079936, 'steps': 104582, 'loss/train': 0.840452253818512} 08/31/2021 08:05:09 - INFO - __main__ - Step 104584: {'lr': 0.00010745381905681276, 'samples': 20080128, 'steps': 104583, 'loss/train': 1.4502180814743042} 08/31/2021 08:05:10 - INFO - __main__ - Step 104585: {'lr': 0.00010744945951081722, 'samples': 20080320, 'steps': 104584, 'loss/train': 0.6578668355941772} 08/31/2021 08:05:11 - INFO - __main__ - Step 104586: {'lr': 0.00010744510002905278, 'samples': 20080512, 'steps': 104585, 'loss/train': 1.3774999380111694} 08/31/2021 08:05:12 - INFO - __main__ - Step 104587: {'lr': 0.00010744074061152134, 'samples': 20080704, 'steps': 104586, 'loss/train': 1.5681235790252686} 08/31/2021 08:05:12 - INFO - __main__ - Step 104588: {'lr': 0.00010743638125822491, 'samples': 20080896, 'steps': 104587, 'loss/train': 0.9958345890045166} 08/31/2021 08:05:13 - INFO - __main__ - Step 104589: {'lr': 0.00010743202196916546, 'samples': 20081088, 'steps': 104588, 'loss/train': 1.83180832862854} 08/31/2021 08:05:13 - INFO - __main__ - Step 104590: {'lr': 0.00010742766274434493, 'samples': 20081280, 'steps': 104589, 'loss/train': 1.420768141746521} 08/31/2021 08:05:14 - INFO - __main__ - Step 104591: {'lr': 0.00010742330358376531, 'samples': 20081472, 'steps': 104590, 'loss/train': 1.2599663734436035} 08/31/2021 08:05:15 - INFO - __main__ - Step 104592: {'lr': 0.00010741894448742865, 'samples': 20081664, 'steps': 104591, 'loss/train': 0.778070867061615} 08/31/2021 08:05:15 - INFO - __main__ - Step 104593: {'lr': 0.00010741458545533669, 'samples': 20081856, 'steps': 104592, 'loss/train': 0.3866858184337616} 08/31/2021 08:05:16 - INFO - __main__ - Step 104594: {'lr': 0.00010741022648749153, 'samples': 20082048, 'steps': 104593, 'loss/train': 0.8583776950836182} 08/31/2021 08:05:16 - INFO - __main__ - Step 104595: {'lr': 0.00010740586758389511, 'samples': 20082240, 'steps': 104594, 'loss/train': 1.0223582983016968} 08/31/2021 08:05:17 - INFO - __main__ - Step 104596: {'lr': 0.00010740150874454943, 'samples': 20082432, 'steps': 104595, 'loss/train': 1.4794758558273315} 08/31/2021 08:05:18 - INFO - __main__ - Step 104597: {'lr': 0.0001073971499694564, 'samples': 20082624, 'steps': 104596, 'loss/train': 0.785749077796936} 08/31/2021 08:05:18 - INFO - __main__ - Step 104598: {'lr': 0.00010739279125861807, 'samples': 20082816, 'steps': 104597, 'loss/train': 1.1907985210418701} 08/31/2021 08:05:18 - INFO - __main__ - Step 104599: {'lr': 0.00010738843261203629, 'samples': 20083008, 'steps': 104598, 'loss/train': 1.0932233333587646} 08/31/2021 08:05:19 - INFO - __main__ - Step 104600: {'lr': 0.00010738407402971309, 'samples': 20083200, 'steps': 104599, 'loss/train': 1.284151554107666} 08/31/2021 08:05:21 - INFO - __main__ - Step 104601: {'lr': 0.00010737971551165043, 'samples': 20083392, 'steps': 104600, 'loss/train': 0.4280872642993927} 08/31/2021 08:05:21 - INFO - __main__ - Step 104602: {'lr': 0.00010737535705785028, 'samples': 20083584, 'steps': 104601, 'loss/train': 1.3411235809326172} 08/31/2021 08:05:21 - INFO - __main__ - Step 104603: {'lr': 0.0001073709986683146, 'samples': 20083776, 'steps': 104602, 'loss/train': 0.6915375590324402} 08/31/2021 08:05:22 - INFO - __main__ - Step 104604: {'lr': 0.00010736664034304533, 'samples': 20083968, 'steps': 104603, 'loss/train': 0.040562789887189865} 08/31/2021 08:05:22 - INFO - __main__ - Step 104605: {'lr': 0.00010736228208204454, 'samples': 20084160, 'steps': 104604, 'loss/train': 0.6886308789253235} 08/31/2021 08:05:24 - INFO - __main__ - Step 104606: {'lr': 0.00010735792388531405, 'samples': 20084352, 'steps': 104605, 'loss/train': 0.31506839394569397} 08/31/2021 08:05:24 - INFO - __main__ - Step 104607: {'lr': 0.00010735356575285585, 'samples': 20084544, 'steps': 104606, 'loss/train': 0.8057672381401062} 08/31/2021 08:05:24 - INFO - __main__ - Step 104608: {'lr': 0.0001073492076846719, 'samples': 20084736, 'steps': 104607, 'loss/train': 0.8371543288230896} 08/31/2021 08:05:25 - INFO - __main__ - Step 104609: {'lr': 0.00010734484968076425, 'samples': 20084928, 'steps': 104608, 'loss/train': 0.8772906064987183} 08/31/2021 08:05:25 - INFO - __main__ - Step 104610: {'lr': 0.00010734049174113478, 'samples': 20085120, 'steps': 104609, 'loss/train': 1.1142268180847168} 08/31/2021 08:05:25 - INFO - __main__ - Step 104611: {'lr': 0.0001073361338657855, 'samples': 20085312, 'steps': 104610, 'loss/train': 1.3836413621902466} 08/31/2021 08:05:27 - INFO - __main__ - Step 104612: {'lr': 0.00010733177605471834, 'samples': 20085504, 'steps': 104611, 'loss/train': 1.3660213947296143} 08/31/2021 08:05:27 - INFO - __main__ - Step 104613: {'lr': 0.0001073274183079353, 'samples': 20085696, 'steps': 104612, 'loss/train': 0.6181337833404541} 08/31/2021 08:05:28 - INFO - __main__ - Step 104614: {'lr': 0.0001073230606254383, 'samples': 20085888, 'steps': 104613, 'loss/train': 1.6117327213287354} 08/31/2021 08:05:28 - INFO - __main__ - Step 104615: {'lr': 0.00010731870300722934, 'samples': 20086080, 'steps': 104614, 'loss/train': 1.31644868850708} 08/31/2021 08:05:29 - INFO - __main__ - Step 104616: {'lr': 0.00010731434545331036, 'samples': 20086272, 'steps': 104615, 'loss/train': 1.5225818157196045} 08/31/2021 08:05:30 - INFO - __main__ - Step 104617: {'lr': 0.00010730998796368336, 'samples': 20086464, 'steps': 104616, 'loss/train': 1.5084329843521118} 08/31/2021 08:05:30 - INFO - __main__ - Step 104618: {'lr': 0.00010730563053835024, 'samples': 20086656, 'steps': 104617, 'loss/train': 1.0215961933135986} 08/31/2021 08:05:31 - INFO - __main__ - Step 104619: {'lr': 0.00010730127317731311, 'samples': 20086848, 'steps': 104618, 'loss/train': 1.136569619178772} 08/31/2021 08:05:31 - INFO - __main__ - Step 104620: {'lr': 0.00010729691588057374, 'samples': 20087040, 'steps': 104619, 'loss/train': 1.6266149282455444} 08/31/2021 08:05:31 - INFO - __main__ - Step 104621: {'lr': 0.0001072925586481342, 'samples': 20087232, 'steps': 104620, 'loss/train': 1.6280410289764404} 08/31/2021 08:05:33 - INFO - __main__ - Step 104622: {'lr': 0.00010728820147999638, 'samples': 20087424, 'steps': 104621, 'loss/train': 1.7494375705718994} 08/31/2021 08:05:34 - INFO - __main__ - Step 104623: {'lr': 0.00010728384437616234, 'samples': 20087616, 'steps': 104622, 'loss/train': 1.6766670942306519} 08/31/2021 08:05:34 - INFO - __main__ - Step 104624: {'lr': 0.00010727948733663398, 'samples': 20087808, 'steps': 104623, 'loss/train': 0.42706671357154846} 08/31/2021 08:05:35 - INFO - __main__ - Step 104625: {'lr': 0.00010727513036141327, 'samples': 20088000, 'steps': 104624, 'loss/train': 1.2859952449798584} 08/31/2021 08:05:35 - INFO - __main__ - Step 104626: {'lr': 0.00010727077345050218, 'samples': 20088192, 'steps': 104625, 'loss/train': 1.2277498245239258} 08/31/2021 08:05:37 - INFO - __main__ - Step 104627: {'lr': 0.00010726641660390269, 'samples': 20088384, 'steps': 104626, 'loss/train': 1.5614454746246338} 08/31/2021 08:05:37 - INFO - __main__ - Step 104628: {'lr': 0.00010726205982161674, 'samples': 20088576, 'steps': 104627, 'loss/train': 1.5616031885147095} 08/31/2021 08:05:37 - INFO - __main__ - Step 104629: {'lr': 0.00010725770310364633, 'samples': 20088768, 'steps': 104628, 'loss/train': 0.30848491191864014} 08/31/2021 08:05:38 - INFO - __main__ - Step 104630: {'lr': 0.00010725334644999338, 'samples': 20088960, 'steps': 104629, 'loss/train': 1.1610645055770874} 08/31/2021 08:05:38 - INFO - __main__ - Step 104631: {'lr': 0.00010724898986065987, 'samples': 20089152, 'steps': 104630, 'loss/train': 1.0940582752227783} 08/31/2021 08:05:40 - INFO - __main__ - Step 104632: {'lr': 0.00010724463333564785, 'samples': 20089344, 'steps': 104631, 'loss/train': 1.3839807510375977} 08/31/2021 08:05:40 - INFO - __main__ - Step 104633: {'lr': 0.0001072402768749591, 'samples': 20089536, 'steps': 104632, 'loss/train': 1.399775505065918} 08/31/2021 08:05:40 - INFO - __main__ - Step 104634: {'lr': 0.00010723592047859567, 'samples': 20089728, 'steps': 104633, 'loss/train': 1.128339409828186} 08/31/2021 08:05:41 - INFO - __main__ - Step 104635: {'lr': 0.00010723156414655955, 'samples': 20089920, 'steps': 104634, 'loss/train': 0.9100589752197266} 08/31/2021 08:05:41 - INFO - __main__ - Step 104636: {'lr': 0.00010722720787885268, 'samples': 20090112, 'steps': 104635, 'loss/train': 0.8551604151725769} 08/31/2021 08:05:43 - INFO - __main__ - Step 104637: {'lr': 0.00010722285167547702, 'samples': 20090304, 'steps': 104636, 'loss/train': 1.3462188243865967} 08/31/2021 08:05:43 - INFO - __main__ - Step 104638: {'lr': 0.00010721849553643456, 'samples': 20090496, 'steps': 104637, 'loss/train': 1.2184492349624634} 08/31/2021 08:05:43 - INFO - __main__ - Step 104639: {'lr': 0.00010721413946172722, 'samples': 20090688, 'steps': 104638, 'loss/train': 0.874984622001648} 08/31/2021 08:05:44 - INFO - __main__ - Step 104640: {'lr': 0.00010720978345135698, 'samples': 20090880, 'steps': 104639, 'loss/train': 0.45984378457069397} 08/31/2021 08:05:44 - INFO - __main__ - Step 104641: {'lr': 0.00010720542750532583, 'samples': 20091072, 'steps': 104640, 'loss/train': 0.7600849270820618} 08/31/2021 08:05:46 - INFO - __main__ - Step 104642: {'lr': 0.00010720107162363571, 'samples': 20091264, 'steps': 104641, 'loss/train': 1.2870688438415527} 08/31/2021 08:05:46 - INFO - __main__ - Step 104643: {'lr': 0.00010719671580628856, 'samples': 20091456, 'steps': 104642, 'loss/train': 1.4400041103363037} 08/31/2021 08:05:46 - INFO - __main__ - Step 104644: {'lr': 0.00010719236005328639, 'samples': 20091648, 'steps': 104643, 'loss/train': 1.3587274551391602} 08/31/2021 08:05:47 - INFO - __main__ - Step 104645: {'lr': 0.00010718800436463114, 'samples': 20091840, 'steps': 104644, 'loss/train': 1.4218971729278564} 08/31/2021 08:05:47 - INFO - __main__ - Step 104646: {'lr': 0.00010718364874032485, 'samples': 20092032, 'steps': 104645, 'loss/train': 1.0334742069244385} 08/31/2021 08:05:49 - INFO - __main__ - Step 104647: {'lr': 0.00010717929318036932, 'samples': 20092224, 'steps': 104646, 'loss/train': 1.3860721588134766} 08/31/2021 08:05:49 - INFO - __main__ - Step 104648: {'lr': 0.0001071749376847666, 'samples': 20092416, 'steps': 104647, 'loss/train': 1.6752277612686157} 08/31/2021 08:05:49 - INFO - __main__ - Step 104649: {'lr': 0.00010717058225351864, 'samples': 20092608, 'steps': 104648, 'loss/train': 1.8152559995651245} 08/31/2021 08:05:50 - INFO - __main__ - Step 104650: {'lr': 0.00010716622688662742, 'samples': 20092800, 'steps': 104649, 'loss/train': 2.7790141105651855} 08/31/2021 08:05:50 - INFO - __main__ - Step 104651: {'lr': 0.00010716187158409488, 'samples': 20092992, 'steps': 104650, 'loss/train': 1.1934382915496826} 08/31/2021 08:05:50 - INFO - __main__ - Step 104652: {'lr': 0.000107157516345923, 'samples': 20093184, 'steps': 104651, 'loss/train': 1.172540307044983} 08/31/2021 08:05:52 - INFO - __main__ - Step 104653: {'lr': 0.00010715316117211376, 'samples': 20093376, 'steps': 104652, 'loss/train': 0.5488795042037964} 08/31/2021 08:05:53 - INFO - __main__ - Step 104654: {'lr': 0.00010714880606266908, 'samples': 20093568, 'steps': 104653, 'loss/train': 0.6067644953727722} 08/31/2021 08:05:53 - INFO - __main__ - Step 104655: {'lr': 0.00010714445101759097, 'samples': 20093760, 'steps': 104654, 'loss/train': 0.4855556786060333} 08/31/2021 08:05:53 - INFO - __main__ - Step 104656: {'lr': 0.00010714009603688132, 'samples': 20093952, 'steps': 104655, 'loss/train': 0.8908176422119141} 08/31/2021 08:05:54 - INFO - __main__ - Step 104657: {'lr': 0.00010713574112054217, 'samples': 20094144, 'steps': 104656, 'loss/train': 1.0158628225326538} 08/31/2021 08:05:55 - INFO - __main__ - Step 104658: {'lr': 0.00010713138626857544, 'samples': 20094336, 'steps': 104657, 'loss/train': 1.4165582656860352} 08/31/2021 08:05:56 - INFO - __main__ - Step 104659: {'lr': 0.00010712703148098322, 'samples': 20094528, 'steps': 104658, 'loss/train': 1.0858608484268188} 08/31/2021 08:05:56 - INFO - __main__ - Step 104660: {'lr': 0.00010712267675776721, 'samples': 20094720, 'steps': 104659, 'loss/train': 1.2284562587738037} 08/31/2021 08:05:56 - INFO - __main__ - Step 104661: {'lr': 0.00010711832209892955, 'samples': 20094912, 'steps': 104660, 'loss/train': 0.4837993383407593} 08/31/2021 08:05:57 - INFO - __main__ - Step 104662: {'lr': 0.00010711396750447217, 'samples': 20095104, 'steps': 104661, 'loss/train': 1.3053741455078125} 08/31/2021 08:05:58 - INFO - __main__ - Step 104663: {'lr': 0.00010710961297439702, 'samples': 20095296, 'steps': 104662, 'loss/train': 1.3437933921813965} 08/31/2021 08:05:59 - INFO - __main__ - Step 104664: {'lr': 0.00010710525850870608, 'samples': 20095488, 'steps': 104663, 'loss/train': 1.116668462753296} 08/31/2021 08:05:59 - INFO - __main__ - Step 104665: {'lr': 0.00010710090410740133, 'samples': 20095680, 'steps': 104664, 'loss/train': 1.3328962326049805} 08/31/2021 08:05:59 - INFO - __main__ - Step 104666: {'lr': 0.00010709654977048469, 'samples': 20095872, 'steps': 104665, 'loss/train': 0.4560783803462982} 08/31/2021 08:06:00 - INFO - __main__ - Step 104667: {'lr': 0.00010709219549795812, 'samples': 20096064, 'steps': 104666, 'loss/train': 0.8458210825920105} 08/31/2021 08:06:00 - INFO - __main__ - Step 104668: {'lr': 0.00010708784128982363, 'samples': 20096256, 'steps': 104667, 'loss/train': 2.3995425701141357} 08/31/2021 08:06:02 - INFO - __main__ - Step 104669: {'lr': 0.00010708348714608312, 'samples': 20096448, 'steps': 104668, 'loss/train': 1.1793620586395264} 08/31/2021 08:06:02 - INFO - __main__ - Step 104670: {'lr': 0.00010707913306673861, 'samples': 20096640, 'steps': 104669, 'loss/train': 1.2418875694274902} 08/31/2021 08:06:02 - INFO - __main__ - Step 104671: {'lr': 0.00010707477905179206, 'samples': 20096832, 'steps': 104670, 'loss/train': 1.2804704904556274} 08/31/2021 08:06:03 - INFO - __main__ - Step 104672: {'lr': 0.00010707042510124545, 'samples': 20097024, 'steps': 104671, 'loss/train': 0.8672813177108765} 08/31/2021 08:06:03 - INFO - __main__ - Step 104673: {'lr': 0.00010706607121510065, 'samples': 20097216, 'steps': 104672, 'loss/train': 0.9805932641029358} 08/31/2021 08:06:06 - INFO - __main__ - Step 104674: {'lr': 0.00010706171739335965, 'samples': 20097408, 'steps': 104673, 'loss/train': 1.2085773944854736} 08/31/2021 08:06:07 - INFO - __main__ - Step 104675: {'lr': 0.00010705736363602445, 'samples': 20097600, 'steps': 104674, 'loss/train': 0.8384157419204712} 08/31/2021 08:06:07 - INFO - __main__ - Step 104676: {'lr': 0.00010705300994309697, 'samples': 20097792, 'steps': 104675, 'loss/train': 1.4883136749267578} 08/31/2021 08:06:07 - INFO - __main__ - Step 104677: {'lr': 0.00010704865631457922, 'samples': 20097984, 'steps': 104676, 'loss/train': 1.2647380828857422} 08/31/2021 08:06:08 - INFO - __main__ - Step 104678: {'lr': 0.00010704430275047314, 'samples': 20098176, 'steps': 104677, 'loss/train': 0.7933791279792786} 08/31/2021 08:06:08 - INFO - __main__ - Step 104679: {'lr': 0.00010703994925078067, 'samples': 20098368, 'steps': 104678, 'loss/train': 0.6468349695205688} 08/31/2021 08:06:08 - INFO - __main__ - Step 104680: {'lr': 0.00010703559581550382, 'samples': 20098560, 'steps': 104679, 'loss/train': 0.014687784016132355} 08/31/2021 08:06:10 - INFO - __main__ - Step 104681: {'lr': 0.00010703124244464452, 'samples': 20098752, 'steps': 104680, 'loss/train': 0.016435803845524788} 08/31/2021 08:06:10 - INFO - __main__ - Step 104682: {'lr': 0.00010702688913820471, 'samples': 20098944, 'steps': 104681, 'loss/train': 1.3177061080932617} 08/31/2021 08:06:11 - INFO - __main__ - Step 104683: {'lr': 0.0001070225358961864, 'samples': 20099136, 'steps': 104682, 'loss/train': 1.3245271444320679} 08/31/2021 08:06:11 - INFO - __main__ - Step 104684: {'lr': 0.00010701818271859154, 'samples': 20099328, 'steps': 104683, 'loss/train': 1.664434790611267} 08/31/2021 08:06:11 - INFO - __main__ - Step 104685: {'lr': 0.00010701382960542205, 'samples': 20099520, 'steps': 104684, 'loss/train': 0.9842556118965149} 08/31/2021 08:06:13 - INFO - __main__ - Step 104686: {'lr': 0.00010700947655668003, 'samples': 20099712, 'steps': 104685, 'loss/train': 1.3701225519180298} 08/31/2021 08:06:13 - INFO - __main__ - Step 104687: {'lr': 0.00010700512357236725, 'samples': 20099904, 'steps': 104686, 'loss/train': 0.7720368504524231} 08/31/2021 08:06:14 - INFO - __main__ - Step 104688: {'lr': 0.00010700077065248573, 'samples': 20100096, 'steps': 104687, 'loss/train': 1.4013941287994385} 08/31/2021 08:06:14 - INFO - __main__ - Step 104689: {'lr': 0.00010699641779703748, 'samples': 20100288, 'steps': 104688, 'loss/train': 1.2894346714019775} 08/31/2021 08:06:14 - INFO - __main__ - Step 104690: {'lr': 0.00010699206500602443, 'samples': 20100480, 'steps': 104689, 'loss/train': 1.16309654712677} 08/31/2021 08:06:16 - INFO - __main__ - Step 104691: {'lr': 0.00010698771227944857, 'samples': 20100672, 'steps': 104690, 'loss/train': 0.5061227083206177} 08/31/2021 08:06:17 - INFO - __main__ - Step 104692: {'lr': 0.00010698335961731179, 'samples': 20100864, 'steps': 104691, 'loss/train': 1.2587690353393555} 08/31/2021 08:06:17 - INFO - __main__ - Step 104693: {'lr': 0.00010697900701961614, 'samples': 20101056, 'steps': 104692, 'loss/train': 2.712162494659424} 08/31/2021 08:06:17 - INFO - __main__ - Step 104694: {'lr': 0.00010697465448636354, 'samples': 20101248, 'steps': 104693, 'loss/train': 1.0459258556365967} 08/31/2021 08:06:18 - INFO - __main__ - Step 104695: {'lr': 0.00010697030201755592, 'samples': 20101440, 'steps': 104694, 'loss/train': 1.3412067890167236} 08/31/2021 08:06:18 - INFO - __main__ - Step 104696: {'lr': 0.0001069659496131953, 'samples': 20101632, 'steps': 104695, 'loss/train': 1.6255849599838257} 08/31/2021 08:06:18 - INFO - __main__ - Step 104697: {'lr': 0.00010696159727328364, 'samples': 20101824, 'steps': 104696, 'loss/train': 1.209944248199463} 08/31/2021 08:06:20 - INFO - __main__ - Step 104698: {'lr': 0.00010695724499782284, 'samples': 20102016, 'steps': 104697, 'loss/train': 1.4174121618270874} 08/31/2021 08:06:21 - INFO - __main__ - Step 104699: {'lr': 0.00010695289278681499, 'samples': 20102208, 'steps': 104698, 'loss/train': 1.0264949798583984} 08/31/2021 08:06:21 - INFO - __main__ - Step 104700: {'lr': 0.00010694854064026191, 'samples': 20102400, 'steps': 104699, 'loss/train': 1.1537986993789673} 08/31/2021 08:06:21 - INFO - __main__ - Step 104701: {'lr': 0.00010694418855816557, 'samples': 20102592, 'steps': 104700, 'loss/train': 1.336484432220459} 08/31/2021 08:06:22 - INFO - __main__ - Step 104702: {'lr': 0.00010693983654052797, 'samples': 20102784, 'steps': 104701, 'loss/train': 0.9109624028205872} 08/31/2021 08:06:23 - INFO - __main__ - Step 104703: {'lr': 0.00010693548458735109, 'samples': 20102976, 'steps': 104702, 'loss/train': 1.4984904527664185} 08/31/2021 08:06:24 - INFO - __main__ - Step 104704: {'lr': 0.00010693113269863688, 'samples': 20103168, 'steps': 104703, 'loss/train': 1.113987684249878} 08/31/2021 08:06:24 - INFO - __main__ - Step 104705: {'lr': 0.00010692678087438729, 'samples': 20103360, 'steps': 104704, 'loss/train': 1.0838675498962402} 08/31/2021 08:06:25 - INFO - __main__ - Step 104706: {'lr': 0.00010692242911460426, 'samples': 20103552, 'steps': 104705, 'loss/train': 1.0990185737609863} 08/31/2021 08:06:25 - INFO - __main__ - Step 104707: {'lr': 0.0001069180774192898, 'samples': 20103744, 'steps': 104706, 'loss/train': 0.4871578514575958} 08/31/2021 08:06:26 - INFO - __main__ - Step 104708: {'lr': 0.00010691372578844582, 'samples': 20103936, 'steps': 104707, 'loss/train': 1.2271381616592407} 08/31/2021 08:06:27 - INFO - __main__ - Step 104709: {'lr': 0.00010690937422207434, 'samples': 20104128, 'steps': 104708, 'loss/train': 1.0468924045562744} 08/31/2021 08:06:27 - INFO - __main__ - Step 104710: {'lr': 0.00010690502272017727, 'samples': 20104320, 'steps': 104709, 'loss/train': 0.6744142770767212} 08/31/2021 08:06:28 - INFO - __main__ - Step 104711: {'lr': 0.0001069006712827566, 'samples': 20104512, 'steps': 104710, 'loss/train': 1.836534023284912} 08/31/2021 08:06:28 - INFO - __main__ - Step 104712: {'lr': 0.00010689631990981427, 'samples': 20104704, 'steps': 104711, 'loss/train': 0.9483121037483215} 08/31/2021 08:06:30 - INFO - __main__ - Step 104713: {'lr': 0.00010689196860135234, 'samples': 20104896, 'steps': 104712, 'loss/train': 0.5438528656959534} 08/31/2021 08:06:30 - INFO - __main__ - Step 104714: {'lr': 0.0001068876173573726, 'samples': 20105088, 'steps': 104713, 'loss/train': 1.355721354484558} 08/31/2021 08:06:31 - INFO - __main__ - Step 104715: {'lr': 0.00010688326617787705, 'samples': 20105280, 'steps': 104714, 'loss/train': 1.2106375694274902} 08/31/2021 08:06:31 - INFO - __main__ - Step 104716: {'lr': 0.00010687891506286773, 'samples': 20105472, 'steps': 104715, 'loss/train': 1.0706579685211182} 08/31/2021 08:06:31 - INFO - __main__ - Step 104717: {'lr': 0.00010687456401234657, 'samples': 20105664, 'steps': 104716, 'loss/train': 0.4973125755786896} 08/31/2021 08:06:32 - INFO - __main__ - Step 104718: {'lr': 0.0001068702130263155, 'samples': 20105856, 'steps': 104717, 'loss/train': 1.2610969543457031} 08/31/2021 08:06:33 - INFO - __main__ - Step 104719: {'lr': 0.00010686586210477652, 'samples': 20106048, 'steps': 104718, 'loss/train': 1.200582504272461} 08/31/2021 08:06:34 - INFO - __main__ - Step 104720: {'lr': 0.00010686151124773157, 'samples': 20106240, 'steps': 104719, 'loss/train': 0.949643075466156} 08/31/2021 08:06:34 - INFO - __main__ - Step 104721: {'lr': 0.00010685716045518263, 'samples': 20106432, 'steps': 104720, 'loss/train': 0.028738193213939667} 08/31/2021 08:06:34 - INFO - __main__ - Step 104722: {'lr': 0.0001068528097271316, 'samples': 20106624, 'steps': 104721, 'loss/train': 1.9410780668258667} 08/31/2021 08:06:35 - INFO - __main__ - Step 104723: {'lr': 0.00010684845906358052, 'samples': 20106816, 'steps': 104722, 'loss/train': 1.4228169918060303} 08/31/2021 08:06:36 - INFO - __main__ - Step 104724: {'lr': 0.0001068441084645313, 'samples': 20107008, 'steps': 104723, 'loss/train': 1.2424862384796143} 08/31/2021 08:06:37 - INFO - __main__ - Step 104725: {'lr': 0.00010683975792998593, 'samples': 20107200, 'steps': 104724, 'loss/train': 0.8180807828903198} 08/31/2021 08:06:37 - INFO - __main__ - Step 104726: {'lr': 0.00010683540745994644, 'samples': 20107392, 'steps': 104725, 'loss/train': 1.4393538236618042} 08/31/2021 08:06:38 - INFO - __main__ - Step 104727: {'lr': 0.00010683105705441463, 'samples': 20107584, 'steps': 104726, 'loss/train': 1.7899525165557861} 08/31/2021 08:06:38 - INFO - __main__ - Step 104728: {'lr': 0.0001068267067133925, 'samples': 20107776, 'steps': 104727, 'loss/train': 1.2041155099868774} 08/31/2021 08:06:40 - INFO - __main__ - Step 104729: {'lr': 0.00010682235643688207, 'samples': 20107968, 'steps': 104728, 'loss/train': 0.8407651782035828} 08/31/2021 08:06:40 - INFO - __main__ - Step 104730: {'lr': 0.00010681800622488528, 'samples': 20108160, 'steps': 104729, 'loss/train': 0.6425801515579224} 08/31/2021 08:06:40 - INFO - __main__ - Step 104731: {'lr': 0.00010681365607740407, 'samples': 20108352, 'steps': 104730, 'loss/train': 1.678697109222412} 08/31/2021 08:06:41 - INFO - __main__ - Step 104732: {'lr': 0.00010680930599444044, 'samples': 20108544, 'steps': 104731, 'loss/train': 0.9918367862701416} 08/31/2021 08:06:41 - INFO - __main__ - Step 104733: {'lr': 0.00010680495597599632, 'samples': 20108736, 'steps': 104732, 'loss/train': 0.7461940050125122} 08/31/2021 08:06:41 - INFO - __main__ - Step 104734: {'lr': 0.00010680060602207368, 'samples': 20108928, 'steps': 104733, 'loss/train': 0.4934621751308441} 08/31/2021 08:06:44 - INFO - __main__ - Step 104735: {'lr': 0.00010679625613267446, 'samples': 20109120, 'steps': 104734, 'loss/train': 1.4234830141067505} 08/31/2021 08:06:44 - INFO - __main__ - Step 104736: {'lr': 0.00010679190630780065, 'samples': 20109312, 'steps': 104735, 'loss/train': 0.9676803350448608} 08/31/2021 08:06:44 - INFO - __main__ - Step 104737: {'lr': 0.00010678755654745418, 'samples': 20109504, 'steps': 104736, 'loss/train': 1.619815707206726} 08/31/2021 08:06:45 - INFO - __main__ - Step 104738: {'lr': 0.00010678320685163707, 'samples': 20109696, 'steps': 104737, 'loss/train': 1.000343680381775} 08/31/2021 08:06:45 - INFO - __main__ - Step 104739: {'lr': 0.0001067788572203512, 'samples': 20109888, 'steps': 104738, 'loss/train': 1.1804893016815186} 08/31/2021 08:06:47 - INFO - __main__ - Step 104740: {'lr': 0.00010677450765359865, 'samples': 20110080, 'steps': 104739, 'loss/train': 0.6099144816398621} 08/31/2021 08:06:47 - INFO - __main__ - Step 104741: {'lr': 0.00010677015815138121, 'samples': 20110272, 'steps': 104740, 'loss/train': 1.0881679058074951} 08/31/2021 08:06:47 - INFO - __main__ - Step 104742: {'lr': 0.00010676580871370096, 'samples': 20110464, 'steps': 104741, 'loss/train': 1.5608134269714355} 08/31/2021 08:06:48 - INFO - __main__ - Step 104743: {'lr': 0.00010676145934055981, 'samples': 20110656, 'steps': 104742, 'loss/train': 0.5054184198379517} 08/31/2021 08:06:48 - INFO - __main__ - Step 104744: {'lr': 0.00010675711003195973, 'samples': 20110848, 'steps': 104743, 'loss/train': 1.2166274785995483} 08/31/2021 08:06:50 - INFO - __main__ - Step 104745: {'lr': 0.0001067527607879027, 'samples': 20111040, 'steps': 104744, 'loss/train': 1.0669907331466675} 08/31/2021 08:06:51 - INFO - __main__ - Step 104746: {'lr': 0.00010674841160839063, 'samples': 20111232, 'steps': 104745, 'loss/train': 1.4993078708648682} 08/31/2021 08:06:51 - INFO - __main__ - Step 104747: {'lr': 0.00010674406249342555, 'samples': 20111424, 'steps': 104746, 'loss/train': 1.1726562976837158} 08/31/2021 08:06:51 - INFO - __main__ - Step 104748: {'lr': 0.00010673971344300936, 'samples': 20111616, 'steps': 104747, 'loss/train': 0.9936128854751587} 08/31/2021 08:06:52 - INFO - __main__ - Step 104749: {'lr': 0.00010673536445714407, 'samples': 20111808, 'steps': 104748, 'loss/train': 1.8309544324874878} 08/31/2021 08:06:52 - INFO - __main__ - Step 104750: {'lr': 0.00010673101553583159, 'samples': 20112000, 'steps': 104749, 'loss/train': 0.11435264348983765} 08/31/2021 08:06:54 - INFO - __main__ - Step 104751: {'lr': 0.0001067266666790739, 'samples': 20112192, 'steps': 104750, 'loss/train': 0.8429388403892517} 08/31/2021 08:06:54 - INFO - __main__ - Step 104752: {'lr': 0.000106722317886873, 'samples': 20112384, 'steps': 104751, 'loss/train': 2.2253005504608154} 08/31/2021 08:06:54 - INFO - __main__ - Step 104753: {'lr': 0.00010671796915923087, 'samples': 20112576, 'steps': 104752, 'loss/train': 0.5280506014823914} 08/31/2021 08:06:55 - INFO - __main__ - Step 104754: {'lr': 0.00010671362049614933, 'samples': 20112768, 'steps': 104753, 'loss/train': 1.2840025424957275} 08/31/2021 08:06:55 - INFO - __main__ - Step 104755: {'lr': 0.00010670927189763044, 'samples': 20112960, 'steps': 104754, 'loss/train': 1.3586241006851196} 08/31/2021 08:06:55 - INFO - __main__ - Step 104756: {'lr': 0.00010670492336367613, 'samples': 20113152, 'steps': 104755, 'loss/train': 0.18751700222492218} 08/31/2021 08:06:57 - INFO - __main__ - Step 104757: {'lr': 0.00010670057489428836, 'samples': 20113344, 'steps': 104756, 'loss/train': 1.2267106771469116} 08/31/2021 08:06:57 - INFO - __main__ - Step 104758: {'lr': 0.00010669622648946912, 'samples': 20113536, 'steps': 104757, 'loss/train': 0.5976489782333374} 08/31/2021 08:06:58 - INFO - __main__ - Step 104759: {'lr': 0.00010669187814922032, 'samples': 20113728, 'steps': 104758, 'loss/train': 1.1871737241744995} 08/31/2021 08:06:58 - INFO - __main__ - Step 104760: {'lr': 0.00010668752987354397, 'samples': 20113920, 'steps': 104759, 'loss/train': 1.2529046535491943} 08/31/2021 08:06:59 - INFO - __main__ - Step 104761: {'lr': 0.00010668318166244197, 'samples': 20114112, 'steps': 104760, 'loss/train': 1.6314157247543335} 08/31/2021 08:07:00 - INFO - __main__ - Step 104762: {'lr': 0.00010667883351591637, 'samples': 20114304, 'steps': 104761, 'loss/train': 0.8082550764083862} 08/31/2021 08:07:01 - INFO - __main__ - Step 104763: {'lr': 0.00010667448543396904, 'samples': 20114496, 'steps': 104762, 'loss/train': 1.5150021314620972} 08/31/2021 08:07:01 - INFO - __main__ - Step 104764: {'lr': 0.000106670137416602, 'samples': 20114688, 'steps': 104763, 'loss/train': 1.5340009927749634} 08/31/2021 08:07:01 - INFO - __main__ - Step 104765: {'lr': 0.00010666578946381716, 'samples': 20114880, 'steps': 104764, 'loss/train': 1.2368122339248657} 08/31/2021 08:07:02 - INFO - __main__ - Step 104766: {'lr': 0.00010666144157561653, 'samples': 20115072, 'steps': 104765, 'loss/train': 1.1694329977035522} 08/31/2021 08:07:03 - INFO - __main__ - Step 104767: {'lr': 0.00010665709375200211, 'samples': 20115264, 'steps': 104766, 'loss/train': 0.9290387034416199} 08/31/2021 08:07:04 - INFO - __main__ - Step 104768: {'lr': 0.00010665274599297572, 'samples': 20115456, 'steps': 104767, 'loss/train': 1.617471694946289} 08/31/2021 08:07:04 - INFO - __main__ - Step 104769: {'lr': 0.0001066483982985394, 'samples': 20115648, 'steps': 104768, 'loss/train': 0.7444087862968445} 08/31/2021 08:07:04 - INFO - __main__ - Step 104770: {'lr': 0.00010664405066869506, 'samples': 20115840, 'steps': 104769, 'loss/train': 0.9651777148246765} 08/31/2021 08:07:05 - INFO - __main__ - Step 104771: {'lr': 0.00010663970310344474, 'samples': 20116032, 'steps': 104770, 'loss/train': 1.1177352666854858} 08/31/2021 08:07:05 - INFO - __main__ - Step 104772: {'lr': 0.00010663535560279031, 'samples': 20116224, 'steps': 104771, 'loss/train': 0.5853380560874939} 08/31/2021 08:07:07 - INFO - __main__ - Step 104773: {'lr': 0.00010663100816673383, 'samples': 20116416, 'steps': 104772, 'loss/train': 1.222687005996704} 08/31/2021 08:07:07 - INFO - __main__ - Step 104774: {'lr': 0.00010662666079527716, 'samples': 20116608, 'steps': 104773, 'loss/train': 1.237558126449585} 08/31/2021 08:07:07 - INFO - __main__ - Step 104775: {'lr': 0.00010662231348842232, 'samples': 20116800, 'steps': 104774, 'loss/train': 0.7748495936393738} 08/31/2021 08:07:08 - INFO - __main__ - Step 104776: {'lr': 0.00010661796624617126, 'samples': 20116992, 'steps': 104775, 'loss/train': 0.026720786467194557} 08/31/2021 08:07:08 - INFO - __main__ - Step 104777: {'lr': 0.00010661361906852592, 'samples': 20117184, 'steps': 104776, 'loss/train': 1.0222030878067017} 08/31/2021 08:07:10 - INFO - __main__ - Step 104778: {'lr': 0.00010660927195548828, 'samples': 20117376, 'steps': 104777, 'loss/train': 1.1741812229156494} 08/31/2021 08:07:10 - INFO - __main__ - Step 104779: {'lr': 0.00010660492490706031, 'samples': 20117568, 'steps': 104778, 'loss/train': 0.7616022825241089} 08/31/2021 08:07:11 - INFO - __main__ - Step 104780: {'lr': 0.00010660057792324401, 'samples': 20117760, 'steps': 104779, 'loss/train': 0.9361923336982727} 08/31/2021 08:07:11 - INFO - __main__ - Step 104781: {'lr': 0.0001065962310040412, 'samples': 20117952, 'steps': 104780, 'loss/train': 0.8635304570198059} 08/31/2021 08:07:11 - INFO - __main__ - Step 104782: {'lr': 0.0001065918841494539, 'samples': 20118144, 'steps': 104781, 'loss/train': 1.2751520872116089} 08/31/2021 08:07:13 - INFO - __main__ - Step 104783: {'lr': 0.0001065875373594841, 'samples': 20118336, 'steps': 104782, 'loss/train': 1.4465785026550293} 08/31/2021 08:07:13 - INFO - __main__ - Step 104784: {'lr': 0.00010658319063413372, 'samples': 20118528, 'steps': 104783, 'loss/train': 1.897141933441162} 08/31/2021 08:07:14 - INFO - __main__ - Step 104785: {'lr': 0.00010657884397340475, 'samples': 20118720, 'steps': 104784, 'loss/train': 1.7143726348876953} 08/31/2021 08:07:14 - INFO - __main__ - Step 104786: {'lr': 0.00010657449737729915, 'samples': 20118912, 'steps': 104785, 'loss/train': 1.4946027994155884} 08/31/2021 08:07:14 - INFO - __main__ - Step 104787: {'lr': 0.00010657015084581886, 'samples': 20119104, 'steps': 104786, 'loss/train': 1.0776851177215576} 08/31/2021 08:07:16 - INFO - __main__ - Step 104788: {'lr': 0.00010656580437896588, 'samples': 20119296, 'steps': 104787, 'loss/train': 1.1433900594711304} 08/31/2021 08:07:17 - INFO - __main__ - Step 104789: {'lr': 0.0001065614579767421, 'samples': 20119488, 'steps': 104788, 'loss/train': 1.208310604095459} 08/31/2021 08:07:17 - INFO - __main__ - Step 104790: {'lr': 0.00010655711163914952, 'samples': 20119680, 'steps': 104789, 'loss/train': 1.0713797807693481} 08/31/2021 08:07:18 - INFO - __main__ - Step 104791: {'lr': 0.0001065527653661901, 'samples': 20119872, 'steps': 104790, 'loss/train': 0.7158060669898987} 08/31/2021 08:07:18 - INFO - __main__ - Step 104792: {'lr': 0.00010654841915786579, 'samples': 20120064, 'steps': 104791, 'loss/train': 1.0336142778396606} 08/31/2021 08:07:19 - INFO - __main__ - Step 104793: {'lr': 0.00010654407301417862, 'samples': 20120256, 'steps': 104792, 'loss/train': 0.9139495491981506} 08/31/2021 08:07:20 - INFO - __main__ - Step 104794: {'lr': 0.0001065397269351304, 'samples': 20120448, 'steps': 104793, 'loss/train': 1.1449915170669556} 08/31/2021 08:07:20 - INFO - __main__ - Step 104795: {'lr': 0.00010653538092072316, 'samples': 20120640, 'steps': 104794, 'loss/train': 0.990200400352478} 08/31/2021 08:07:21 - INFO - __main__ - Step 104796: {'lr': 0.00010653103497095887, 'samples': 20120832, 'steps': 104795, 'loss/train': 0.34924542903900146} 08/31/2021 08:07:21 - INFO - __main__ - Step 104797: {'lr': 0.00010652668908583949, 'samples': 20121024, 'steps': 104796, 'loss/train': 1.3233609199523926} 08/31/2021 08:07:23 - INFO - __main__ - Step 104798: {'lr': 0.00010652234326536694, 'samples': 20121216, 'steps': 104797, 'loss/train': 0.8342812061309814} 08/31/2021 08:07:23 - INFO - __main__ - Step 104799: {'lr': 0.00010651799750954322, 'samples': 20121408, 'steps': 104798, 'loss/train': 1.28315007686615} 08/31/2021 08:07:23 - INFO - __main__ - Step 104800: {'lr': 0.0001065136518183703, 'samples': 20121600, 'steps': 104799, 'loss/train': 0.317850261926651} 08/31/2021 08:07:24 - INFO - __main__ - Step 104801: {'lr': 0.00010650930619185009, 'samples': 20121792, 'steps': 104800, 'loss/train': 1.3261210918426514} 08/31/2021 08:07:24 - INFO - __main__ - Step 104802: {'lr': 0.00010650496062998457, 'samples': 20121984, 'steps': 104801, 'loss/train': 1.3461804389953613} 08/31/2021 08:07:24 - INFO - __main__ - Step 104803: {'lr': 0.00010650061513277573, 'samples': 20122176, 'steps': 104802, 'loss/train': 0.9430283904075623} 08/31/2021 08:07:26 - INFO - __main__ - Step 104804: {'lr': 0.00010649626970022547, 'samples': 20122368, 'steps': 104803, 'loss/train': 1.4418925046920776} 08/31/2021 08:07:26 - INFO - __main__ - Step 104805: {'lr': 0.00010649192433233587, 'samples': 20122560, 'steps': 104804, 'loss/train': 1.6203604936599731} 08/31/2021 08:07:27 - INFO - __main__ - Step 104806: {'lr': 0.00010648757902910872, 'samples': 20122752, 'steps': 104805, 'loss/train': 1.2203450202941895} 08/31/2021 08:07:27 - INFO - __main__ - Step 104807: {'lr': 0.00010648323379054606, 'samples': 20122944, 'steps': 104806, 'loss/train': 0.7601943016052246} 08/31/2021 08:07:27 - INFO - __main__ - Step 104808: {'lr': 0.0001064788886166498, 'samples': 20123136, 'steps': 104807, 'loss/train': 0.8890836238861084} 08/31/2021 08:07:29 - INFO - __main__ - Step 104809: {'lr': 0.00010647454350742197, 'samples': 20123328, 'steps': 104808, 'loss/train': 0.8078678250312805} 08/31/2021 08:07:30 - INFO - __main__ - Step 104810: {'lr': 0.00010647019846286448, 'samples': 20123520, 'steps': 104809, 'loss/train': 0.9539797902107239} 08/31/2021 08:07:30 - INFO - __main__ - Step 104811: {'lr': 0.00010646585348297932, 'samples': 20123712, 'steps': 104810, 'loss/train': 0.8541688323020935} 08/31/2021 08:07:30 - INFO - __main__ - Step 104812: {'lr': 0.00010646150856776843, 'samples': 20123904, 'steps': 104811, 'loss/train': 0.6811293363571167} 08/31/2021 08:07:31 - INFO - __main__ - Step 104813: {'lr': 0.00010645716371723374, 'samples': 20124096, 'steps': 104812, 'loss/train': 0.11747559905052185} 08/31/2021 08:07:32 - INFO - __main__ - Step 104814: {'lr': 0.00010645281893137726, 'samples': 20124288, 'steps': 104813, 'loss/train': 1.2308413982391357} 08/31/2021 08:07:33 - INFO - __main__ - Step 104815: {'lr': 0.00010644847421020093, 'samples': 20124480, 'steps': 104814, 'loss/train': 0.7780659198760986} 08/31/2021 08:07:33 - INFO - __main__ - Step 104816: {'lr': 0.0001064441295537068, 'samples': 20124672, 'steps': 104815, 'loss/train': 1.074324369430542} 08/31/2021 08:07:34 - INFO - __main__ - Step 104817: {'lr': 0.00010643978496189663, 'samples': 20124864, 'steps': 104816, 'loss/train': 0.7426940202713013} 08/31/2021 08:07:34 - INFO - __main__ - Step 104818: {'lr': 0.00010643544043477247, 'samples': 20125056, 'steps': 104817, 'loss/train': 0.6460456252098083} 08/31/2021 08:07:36 - INFO - __main__ - Step 104819: {'lr': 0.00010643109597233628, 'samples': 20125248, 'steps': 104818, 'loss/train': 1.7479978799819946} 08/31/2021 08:07:36 - INFO - __main__ - Step 104820: {'lr': 0.00010642675157459003, 'samples': 20125440, 'steps': 104819, 'loss/train': 0.330098956823349} 08/31/2021 08:07:36 - INFO - __main__ - Step 104821: {'lr': 0.00010642240724153568, 'samples': 20125632, 'steps': 104820, 'loss/train': 0.7050631046295166} 08/31/2021 08:07:37 - INFO - __main__ - Step 104822: {'lr': 0.00010641806297317516, 'samples': 20125824, 'steps': 104821, 'loss/train': 1.0561884641647339} 08/31/2021 08:07:37 - INFO - __main__ - Step 104823: {'lr': 0.00010641371876951045, 'samples': 20126016, 'steps': 104822, 'loss/train': 0.8232138156890869} 08/31/2021 08:07:37 - INFO - __main__ - Step 104824: {'lr': 0.00010640937463054351, 'samples': 20126208, 'steps': 104823, 'loss/train': 0.37157219648361206} 08/31/2021 08:07:39 - INFO - __main__ - Step 104825: {'lr': 0.0001064050305562763, 'samples': 20126400, 'steps': 104824, 'loss/train': 1.1033601760864258} 08/31/2021 08:07:40 - INFO - __main__ - Step 104826: {'lr': 0.00010640068654671084, 'samples': 20126592, 'steps': 104825, 'loss/train': 1.1962854862213135} 08/31/2021 08:07:40 - INFO - __main__ - Step 104827: {'lr': 0.00010639634260184894, 'samples': 20126784, 'steps': 104826, 'loss/train': 0.6842201352119446} 08/31/2021 08:07:40 - INFO - __main__ - Step 104828: {'lr': 0.00010639199872169262, 'samples': 20126976, 'steps': 104827, 'loss/train': 0.9233607053756714} 08/31/2021 08:07:41 - INFO - __main__ - Step 104829: {'lr': 0.00010638765490624383, 'samples': 20127168, 'steps': 104828, 'loss/train': 1.120949625968933} 08/31/2021 08:07:43 - INFO - __main__ - Step 104830: {'lr': 0.00010638331115550459, 'samples': 20127360, 'steps': 104829, 'loss/train': 1.6259852647781372} 08/31/2021 08:07:43 - INFO - __main__ - Step 104831: {'lr': 0.00010637896746947678, 'samples': 20127552, 'steps': 104830, 'loss/train': 0.023234067484736443} 08/31/2021 08:07:43 - INFO - __main__ - Step 104832: {'lr': 0.0001063746238481624, 'samples': 20127744, 'steps': 104831, 'loss/train': 0.016724061220884323} 08/31/2021 08:07:44 - INFO - __main__ - Step 104833: {'lr': 0.0001063702802915634, 'samples': 20127936, 'steps': 104832, 'loss/train': 1.329260230064392} 08/31/2021 08:07:44 - INFO - __main__ - Step 104834: {'lr': 0.00010636593679968173, 'samples': 20128128, 'steps': 104833, 'loss/train': 1.1317695379257202} 08/31/2021 08:07:44 - INFO - __main__ - Step 104835: {'lr': 0.00010636159337251938, 'samples': 20128320, 'steps': 104834, 'loss/train': 0.7768670320510864} 08/31/2021 08:07:46 - INFO - __main__ - Step 104836: {'lr': 0.00010635725001007826, 'samples': 20128512, 'steps': 104835, 'loss/train': 0.9554364085197449} 08/31/2021 08:07:46 - INFO - __main__ - Step 104837: {'lr': 0.00010635290671236041, 'samples': 20128704, 'steps': 104836, 'loss/train': 1.924375295639038} 08/31/2021 08:07:47 - INFO - __main__ - Step 104838: {'lr': 0.00010634856347936766, 'samples': 20128896, 'steps': 104837, 'loss/train': 1.0298694372177124} 08/31/2021 08:07:47 - INFO - __main__ - Step 104839: {'lr': 0.00010634422031110205, 'samples': 20129088, 'steps': 104838, 'loss/train': 1.3221309185028076} 08/31/2021 08:07:47 - INFO - __main__ - Step 104840: {'lr': 0.0001063398772075655, 'samples': 20129280, 'steps': 104839, 'loss/train': 0.805147647857666} 08/31/2021 08:07:49 - INFO - __main__ - Step 104841: {'lr': 0.00010633553416875996, 'samples': 20129472, 'steps': 104840, 'loss/train': 0.5009288191795349} 08/31/2021 08:07:50 - INFO - __main__ - Step 104842: {'lr': 0.00010633119119468745, 'samples': 20129664, 'steps': 104841, 'loss/train': 0.5477420091629028} 08/31/2021 08:07:50 - INFO - __main__ - Step 104843: {'lr': 0.00010632684828534985, 'samples': 20129856, 'steps': 104842, 'loss/train': 1.6718692779541016} 08/31/2021 08:07:51 - INFO - __main__ - Step 104844: {'lr': 0.00010632250544074921, 'samples': 20130048, 'steps': 104843, 'loss/train': 1.3873441219329834} 08/31/2021 08:07:51 - INFO - __main__ - Step 104845: {'lr': 0.00010631816266088737, 'samples': 20130240, 'steps': 104844, 'loss/train': 1.4270943403244019} 08/31/2021 08:07:53 - INFO - __main__ - Step 104846: {'lr': 0.00010631381994576639, 'samples': 20130432, 'steps': 104845, 'loss/train': 0.7712404727935791} 08/31/2021 08:07:53 - INFO - __main__ - Step 104847: {'lr': 0.00010630947729538818, 'samples': 20130624, 'steps': 104846, 'loss/train': 0.8903262615203857} 08/31/2021 08:07:53 - INFO - __main__ - Step 104848: {'lr': 0.00010630513470975478, 'samples': 20130816, 'steps': 104847, 'loss/train': 1.773324966430664} 08/31/2021 08:07:54 - INFO - __main__ - Step 104849: {'lr': 0.00010630079218886798, 'samples': 20131008, 'steps': 104848, 'loss/train': 1.4998373985290527} 08/31/2021 08:07:54 - INFO - __main__ - Step 104850: {'lr': 0.00010629644973272984, 'samples': 20131200, 'steps': 104849, 'loss/train': 1.2852425575256348} 08/31/2021 08:07:56 - INFO - __main__ - Step 104851: {'lr': 0.00010629210734134228, 'samples': 20131392, 'steps': 104850, 'loss/train': 1.0999119281768799} 08/31/2021 08:07:56 - INFO - __main__ - Step 104852: {'lr': 0.0001062877650147073, 'samples': 20131584, 'steps': 104851, 'loss/train': 1.0284342765808105} 08/31/2021 08:07:57 - INFO - __main__ - Step 104853: {'lr': 0.00010628342275282682, 'samples': 20131776, 'steps': 104852, 'loss/train': 1.2938337326049805} 08/31/2021 08:07:57 - INFO - __main__ - Step 104854: {'lr': 0.00010627908055570282, 'samples': 20131968, 'steps': 104853, 'loss/train': 1.2842708826065063} 08/31/2021 08:07:57 - INFO - __main__ - Step 104855: {'lr': 0.00010627473842333724, 'samples': 20132160, 'steps': 104854, 'loss/train': 1.406572699546814} 08/31/2021 08:07:59 - INFO - __main__ - Step 104856: {'lr': 0.00010627039635573205, 'samples': 20132352, 'steps': 104855, 'loss/train': 1.4958237409591675} 08/31/2021 08:07:59 - INFO - __main__ - Step 104857: {'lr': 0.00010626605435288919, 'samples': 20132544, 'steps': 104856, 'loss/train': 1.7973403930664062} 08/31/2021 08:08:00 - INFO - __main__ - Step 104858: {'lr': 0.00010626171241481067, 'samples': 20132736, 'steps': 104857, 'loss/train': 0.15921396017074585} 08/31/2021 08:08:00 - INFO - __main__ - Step 104859: {'lr': 0.00010625737054149836, 'samples': 20132928, 'steps': 104858, 'loss/train': 1.6536095142364502} 08/31/2021 08:08:00 - INFO - __main__ - Step 104860: {'lr': 0.00010625302873295428, 'samples': 20133120, 'steps': 104859, 'loss/train': 2.0620439052581787} 08/31/2021 08:08:01 - INFO - __main__ - Step 104861: {'lr': 0.00010624868698918044, 'samples': 20133312, 'steps': 104860, 'loss/train': 0.7061291337013245} 08/31/2021 08:08:02 - INFO - __main__ - Step 104862: {'lr': 0.00010624434531017865, 'samples': 20133504, 'steps': 104861, 'loss/train': 1.2776459455490112} 08/31/2021 08:08:03 - INFO - __main__ - Step 104863: {'lr': 0.00010624000369595093, 'samples': 20133696, 'steps': 104862, 'loss/train': 0.18466101586818695} 08/31/2021 08:08:03 - INFO - __main__ - Step 104864: {'lr': 0.00010623566214649927, 'samples': 20133888, 'steps': 104863, 'loss/train': 1.343582034111023} 08/31/2021 08:08:03 - INFO - __main__ - Step 104865: {'lr': 0.00010623132066182559, 'samples': 20134080, 'steps': 104864, 'loss/train': 0.03122076950967312} 08/31/2021 08:08:04 - INFO - __main__ - Step 104866: {'lr': 0.00010622697924193184, 'samples': 20134272, 'steps': 104865, 'loss/train': 0.19612184166908264} 08/31/2021 08:08:06 - INFO - __main__ - Step 104867: {'lr': 0.00010622263788682001, 'samples': 20134464, 'steps': 104866, 'loss/train': 1.2045567035675049} 08/31/2021 08:08:06 - INFO - __main__ - Step 104868: {'lr': 0.00010621829659649204, 'samples': 20134656, 'steps': 104867, 'loss/train': 0.4125199615955353} 08/31/2021 08:08:06 - INFO - __main__ - Step 104869: {'lr': 0.00010621395537094988, 'samples': 20134848, 'steps': 104868, 'loss/train': 0.9653751254081726} 08/31/2021 08:08:07 - INFO - __main__ - Step 104870: {'lr': 0.00010620961421019551, 'samples': 20135040, 'steps': 104869, 'loss/train': 1.5011050701141357} 08/31/2021 08:08:07 - INFO - __main__ - Step 104871: {'lr': 0.00010620527311423083, 'samples': 20135232, 'steps': 104870, 'loss/train': 1.3342550992965698} 08/31/2021 08:08:09 - INFO - __main__ - Step 104872: {'lr': 0.00010620093208305789, 'samples': 20135424, 'steps': 104871, 'loss/train': 0.9591538906097412} 08/31/2021 08:08:09 - INFO - __main__ - Step 104873: {'lr': 0.00010619659111667857, 'samples': 20135616, 'steps': 104872, 'loss/train': 1.096541404724121} 08/31/2021 08:08:09 - INFO - __main__ - Step 104874: {'lr': 0.0001061922502150949, 'samples': 20135808, 'steps': 104873, 'loss/train': 1.2649098634719849} 08/31/2021 08:08:10 - INFO - __main__ - Step 104875: {'lr': 0.00010618790937830874, 'samples': 20136000, 'steps': 104874, 'loss/train': 0.7138583064079285} 08/31/2021 08:08:10 - INFO - __main__ - Step 104876: {'lr': 0.00010618356860632208, 'samples': 20136192, 'steps': 104875, 'loss/train': 1.0996893644332886} 08/31/2021 08:08:12 - INFO - __main__ - Step 104877: {'lr': 0.00010617922789913686, 'samples': 20136384, 'steps': 104876, 'loss/train': 1.0980757474899292} 08/31/2021 08:08:12 - INFO - __main__ - Step 104878: {'lr': 0.00010617488725675509, 'samples': 20136576, 'steps': 104877, 'loss/train': 0.7743045091629028} 08/31/2021 08:08:12 - INFO - __main__ - Step 104879: {'lr': 0.00010617054667917869, 'samples': 20136768, 'steps': 104878, 'loss/train': 1.3097976446151733} 08/31/2021 08:08:13 - INFO - __main__ - Step 104880: {'lr': 0.0001061662061664096, 'samples': 20136960, 'steps': 104879, 'loss/train': 0.7185203433036804} 08/31/2021 08:08:13 - INFO - __main__ - Step 104881: {'lr': 0.00010616186571844982, 'samples': 20137152, 'steps': 104880, 'loss/train': 1.2684086561203003} 08/31/2021 08:08:15 - INFO - __main__ - Step 104882: {'lr': 0.0001061575253353013, 'samples': 20137344, 'steps': 104881, 'loss/train': 0.7995501160621643} 08/31/2021 08:08:15 - INFO - __main__ - Step 104883: {'lr': 0.00010615318501696594, 'samples': 20137536, 'steps': 104882, 'loss/train': 0.9512080550193787} 08/31/2021 08:08:16 - INFO - __main__ - Step 104884: {'lr': 0.00010614884476344575, 'samples': 20137728, 'steps': 104883, 'loss/train': 0.8760464787483215} 08/31/2021 08:08:16 - INFO - __main__ - Step 104885: {'lr': 0.00010614450457474267, 'samples': 20137920, 'steps': 104884, 'loss/train': 1.5883407592773438} 08/31/2021 08:08:16 - INFO - __main__ - Step 104886: {'lr': 0.00010614016445085866, 'samples': 20138112, 'steps': 104885, 'loss/train': 1.189199686050415} 08/31/2021 08:08:17 - INFO - __main__ - Step 104887: {'lr': 0.00010613582439179567, 'samples': 20138304, 'steps': 104886, 'loss/train': 1.5797144174575806} 08/31/2021 08:08:18 - INFO - __main__ - Step 104888: {'lr': 0.00010613148439755576, 'samples': 20138496, 'steps': 104887, 'loss/train': 0.5508427023887634} 08/31/2021 08:08:19 - INFO - __main__ - Step 104889: {'lr': 0.00010612714446814068, 'samples': 20138688, 'steps': 104888, 'loss/train': 1.0893315076828003} 08/31/2021 08:08:19 - INFO - __main__ - Step 104890: {'lr': 0.00010612280460355247, 'samples': 20138880, 'steps': 104889, 'loss/train': 0.9943389296531677} 08/31/2021 08:08:19 - INFO - __main__ - Step 104891: {'lr': 0.00010611846480379314, 'samples': 20139072, 'steps': 104890, 'loss/train': 1.4807102680206299} 08/31/2021 08:08:20 - INFO - __main__ - Step 104892: {'lr': 0.00010611412506886459, 'samples': 20139264, 'steps': 104891, 'loss/train': 1.287441611289978} 08/31/2021 08:08:21 - INFO - __main__ - Step 104893: {'lr': 0.0001061097853987688, 'samples': 20139456, 'steps': 104892, 'loss/train': 1.3409900665283203} 08/31/2021 08:08:22 - INFO - __main__ - Step 104894: {'lr': 0.00010610544579350773, 'samples': 20139648, 'steps': 104893, 'loss/train': 0.8986031413078308} 08/31/2021 08:08:22 - INFO - __main__ - Step 104895: {'lr': 0.00010610110625308331, 'samples': 20139840, 'steps': 104894, 'loss/train': 1.286092758178711} 08/31/2021 08:08:22 - INFO - __main__ - Step 104896: {'lr': 0.00010609676677749752, 'samples': 20140032, 'steps': 104895, 'loss/train': 1.4021092653274536} 08/31/2021 08:08:23 - INFO - __main__ - Step 104897: {'lr': 0.00010609242736675231, 'samples': 20140224, 'steps': 104896, 'loss/train': 1.3714697360992432} 08/31/2021 08:08:25 - INFO - __main__ - Step 104898: {'lr': 0.00010608808802084963, 'samples': 20140416, 'steps': 104897, 'loss/train': 1.2991434335708618} 08/31/2021 08:08:25 - INFO - __main__ - Step 104899: {'lr': 0.00010608374873979143, 'samples': 20140608, 'steps': 104898, 'loss/train': 1.2082020044326782} 08/31/2021 08:08:25 - INFO - __main__ - Step 104900: {'lr': 0.00010607940952357966, 'samples': 20140800, 'steps': 104899, 'loss/train': 1.0508671998977661} 08/31/2021 08:08:26 - INFO - __main__ - Step 104901: {'lr': 0.0001060750703722164, 'samples': 20140992, 'steps': 104900, 'loss/train': 0.8902335166931152} 08/31/2021 08:08:26 - INFO - __main__ - Step 104902: {'lr': 0.00010607073128570339, 'samples': 20141184, 'steps': 104901, 'loss/train': 0.4789111614227295} 08/31/2021 08:08:28 - INFO - __main__ - Step 104903: {'lr': 0.00010606639226404268, 'samples': 20141376, 'steps': 104902, 'loss/train': 0.936044454574585} 08/31/2021 08:08:28 - INFO - __main__ - Step 104904: {'lr': 0.00010606205330723626, 'samples': 20141568, 'steps': 104903, 'loss/train': 1.5765713453292847} 08/31/2021 08:08:29 - INFO - __main__ - Step 104905: {'lr': 0.00010605771441528602, 'samples': 20141760, 'steps': 104904, 'loss/train': 1.3665622472763062} 08/31/2021 08:08:29 - INFO - __main__ - Step 104906: {'lr': 0.00010605337558819398, 'samples': 20141952, 'steps': 104905, 'loss/train': 1.1641533374786377} 08/31/2021 08:08:29 - INFO - __main__ - Step 104907: {'lr': 0.00010604903682596207, 'samples': 20142144, 'steps': 104906, 'loss/train': 1.9928507804870605} 08/31/2021 08:08:32 - INFO - __main__ - Step 104908: {'lr': 0.00010604469812859224, 'samples': 20142336, 'steps': 104907, 'loss/train': 0.9281948208808899} 08/31/2021 08:08:32 - INFO - __main__ - Step 104909: {'lr': 0.00010604035949608643, 'samples': 20142528, 'steps': 104908, 'loss/train': 1.3750513792037964} 08/31/2021 08:08:33 - INFO - __main__ - Step 104910: {'lr': 0.00010603602092844664, 'samples': 20142720, 'steps': 104909, 'loss/train': 0.7089974880218506} 08/31/2021 08:08:33 - INFO - __main__ - Step 104911: {'lr': 0.00010603168242567477, 'samples': 20142912, 'steps': 104910, 'loss/train': 0.7078320980072021} 08/31/2021 08:08:33 - INFO - __main__ - Step 104912: {'lr': 0.0001060273439877728, 'samples': 20143104, 'steps': 104911, 'loss/train': 0.739677369594574} 08/31/2021 08:08:34 - INFO - __main__ - Step 104913: {'lr': 0.0001060230056147427, 'samples': 20143296, 'steps': 104912, 'loss/train': 1.2531445026397705} 08/31/2021 08:08:34 - INFO - __main__ - Step 104914: {'lr': 0.00010601866730658652, 'samples': 20143488, 'steps': 104913, 'loss/train': 0.14937132596969604} 08/31/2021 08:08:35 - INFO - __main__ - Step 104915: {'lr': 0.00010601432906330599, 'samples': 20143680, 'steps': 104914, 'loss/train': 0.680777907371521} 08/31/2021 08:08:36 - INFO - __main__ - Step 104916: {'lr': 0.0001060099908849032, 'samples': 20143872, 'steps': 104915, 'loss/train': 1.5133785009384155} 08/31/2021 08:08:36 - INFO - __main__ - Step 104917: {'lr': 0.00010600565277138008, 'samples': 20144064, 'steps': 104916, 'loss/train': 1.4162280559539795} 08/31/2021 08:08:37 - INFO - __main__ - Step 104918: {'lr': 0.00010600131472273858, 'samples': 20144256, 'steps': 104917, 'loss/train': 0.9897408485412598} 08/31/2021 08:08:37 - INFO - __main__ - Step 104919: {'lr': 0.00010599697673898068, 'samples': 20144448, 'steps': 104918, 'loss/train': 1.1988532543182373} 08/31/2021 08:08:37 - INFO - __main__ - Step 104920: {'lr': 0.00010599263882010831, 'samples': 20144640, 'steps': 104919, 'loss/train': 1.4454706907272339} 08/31/2021 08:08:39 - INFO - __main__ - Step 104921: {'lr': 0.00010598830096612344, 'samples': 20144832, 'steps': 104920, 'loss/train': 1.5938173532485962} 08/31/2021 08:08:40 - INFO - __main__ - Step 104922: {'lr': 0.00010598396317702802, 'samples': 20145024, 'steps': 104921, 'loss/train': 1.3424756526947021} 08/31/2021 08:08:40 - INFO - __main__ - Step 104923: {'lr': 0.000105979625452824, 'samples': 20145216, 'steps': 104922, 'loss/train': 2.088754177093506} 08/31/2021 08:08:41 - INFO - __main__ - Step 104924: {'lr': 0.00010597528779351335, 'samples': 20145408, 'steps': 104923, 'loss/train': 1.224080204963684} 08/31/2021 08:08:41 - INFO - __main__ - Step 104925: {'lr': 0.000105970950199098, 'samples': 20145600, 'steps': 104924, 'loss/train': 2.0355722904205322} 08/31/2021 08:08:41 - INFO - __main__ - Step 104926: {'lr': 0.00010596661266957991, 'samples': 20145792, 'steps': 104925, 'loss/train': 1.0986859798431396} 08/31/2021 08:08:43 - INFO - __main__ - Step 104927: {'lr': 0.00010596227520496107, 'samples': 20145984, 'steps': 104926, 'loss/train': 1.0946565866470337} 08/31/2021 08:08:44 - INFO - __main__ - Step 104928: {'lr': 0.00010595793780524346, 'samples': 20146176, 'steps': 104927, 'loss/train': 1.409627079963684} 08/31/2021 08:08:44 - INFO - __main__ - Step 104929: {'lr': 0.00010595360047042893, 'samples': 20146368, 'steps': 104928, 'loss/train': 0.533854067325592} 08/31/2021 08:08:44 - INFO - __main__ - Step 104930: {'lr': 0.00010594926320051946, 'samples': 20146560, 'steps': 104929, 'loss/train': 1.50621497631073} 08/31/2021 08:08:45 - INFO - __main__ - Step 104931: {'lr': 0.00010594492599551703, 'samples': 20146752, 'steps': 104930, 'loss/train': 1.943846583366394} 08/31/2021 08:08:46 - INFO - __main__ - Step 104932: {'lr': 0.0001059405888554236, 'samples': 20146944, 'steps': 104931, 'loss/train': 1.784415602684021} 08/31/2021 08:08:47 - INFO - __main__ - Step 104933: {'lr': 0.0001059362517802411, 'samples': 20147136, 'steps': 104932, 'loss/train': 1.3410685062408447} 08/31/2021 08:08:47 - INFO - __main__ - Step 104934: {'lr': 0.00010593191476997152, 'samples': 20147328, 'steps': 104933, 'loss/train': 0.5061587691307068} 08/31/2021 08:08:47 - INFO - __main__ - Step 104935: {'lr': 0.00010592757782461679, 'samples': 20147520, 'steps': 104934, 'loss/train': 1.4741861820220947} 08/31/2021 08:08:48 - INFO - __main__ - Step 104936: {'lr': 0.00010592324094417888, 'samples': 20147712, 'steps': 104935, 'loss/train': 1.376375436782837} 08/31/2021 08:08:49 - INFO - __main__ - Step 104937: {'lr': 0.00010591890412865973, 'samples': 20147904, 'steps': 104936, 'loss/train': 1.5759577751159668} 08/31/2021 08:08:50 - INFO - __main__ - Step 104938: {'lr': 0.0001059145673780613, 'samples': 20148096, 'steps': 104937, 'loss/train': 0.5198733806610107} 08/31/2021 08:08:50 - INFO - __main__ - Step 104939: {'lr': 0.00010591023069238553, 'samples': 20148288, 'steps': 104938, 'loss/train': 0.9022155404090881} 08/31/2021 08:08:50 - INFO - __main__ - Step 104940: {'lr': 0.00010590589407163439, 'samples': 20148480, 'steps': 104939, 'loss/train': 1.5282379388809204} 08/31/2021 08:08:51 - INFO - __main__ - Step 104941: {'lr': 0.00010590155751580993, 'samples': 20148672, 'steps': 104940, 'loss/train': 1.4443044662475586} 08/31/2021 08:08:52 - INFO - __main__ - Step 104942: {'lr': 0.00010589722102491393, 'samples': 20148864, 'steps': 104941, 'loss/train': 1.8029767274856567} 08/31/2021 08:08:53 - INFO - __main__ - Step 104943: {'lr': 0.00010589288459894838, 'samples': 20149056, 'steps': 104942, 'loss/train': 0.4480433762073517} 08/31/2021 08:08:53 - INFO - __main__ - Step 104944: {'lr': 0.0001058885482379153, 'samples': 20149248, 'steps': 104943, 'loss/train': 1.6292096376419067} 08/31/2021 08:08:54 - INFO - __main__ - Step 104945: {'lr': 0.0001058842119418166, 'samples': 20149440, 'steps': 104944, 'loss/train': 1.510172963142395} 08/31/2021 08:08:54 - INFO - __main__ - Step 104946: {'lr': 0.00010587987571065427, 'samples': 20149632, 'steps': 104945, 'loss/train': 1.5246070623397827} 08/31/2021 08:08:56 - INFO - __main__ - Step 104947: {'lr': 0.00010587553954443021, 'samples': 20149824, 'steps': 104946, 'loss/train': 1.287803292274475} 08/31/2021 08:08:56 - INFO - __main__ - Step 104948: {'lr': 0.00010587120344314643, 'samples': 20150016, 'steps': 104947, 'loss/train': 1.2045594453811646} 08/31/2021 08:08:56 - INFO - __main__ - Step 104949: {'lr': 0.00010586686740680488, 'samples': 20150208, 'steps': 104948, 'loss/train': 1.0728036165237427} 08/31/2021 08:08:57 - INFO - __main__ - Step 104950: {'lr': 0.00010586253143540748, 'samples': 20150400, 'steps': 104949, 'loss/train': 0.21523191034793854} 08/31/2021 08:08:57 - INFO - __main__ - Step 104951: {'lr': 0.00010585819552895617, 'samples': 20150592, 'steps': 104950, 'loss/train': 1.2920119762420654} 08/31/2021 08:09:00 - INFO - __main__ - Step 104952: {'lr': 0.00010585385968745298, 'samples': 20150784, 'steps': 104951, 'loss/train': 1.223368763923645} 08/31/2021 08:09:00 - INFO - __main__ - Step 104953: {'lr': 0.00010584952391089981, 'samples': 20150976, 'steps': 104952, 'loss/train': 1.424492359161377} 08/31/2021 08:09:01 - INFO - __main__ - Step 104954: {'lr': 0.00010584518819929858, 'samples': 20151168, 'steps': 104953, 'loss/train': 1.3817585706710815} 08/31/2021 08:09:01 - INFO - __main__ - Step 104955: {'lr': 0.00010584085255265142, 'samples': 20151360, 'steps': 104954, 'loss/train': 0.8125301599502563} 08/31/2021 08:09:01 - INFO - __main__ - Step 104956: {'lr': 0.00010583651697096003, 'samples': 20151552, 'steps': 104955, 'loss/train': 0.02957320399582386} 08/31/2021 08:09:03 - INFO - __main__ - Step 104957: {'lr': 0.0001058321814542265, 'samples': 20151744, 'steps': 104956, 'loss/train': 1.297200322151184} 08/31/2021 08:09:03 - INFO - __main__ - Step 104958: {'lr': 0.00010582784600245273, 'samples': 20151936, 'steps': 104957, 'loss/train': 0.9908238649368286} 08/31/2021 08:09:04 - INFO - __main__ - Step 104959: {'lr': 0.00010582351061564075, 'samples': 20152128, 'steps': 104958, 'loss/train': 0.6114372611045837} 08/31/2021 08:09:04 - INFO - __main__ - Step 104960: {'lr': 0.00010581917529379242, 'samples': 20152320, 'steps': 104959, 'loss/train': 1.089606761932373} 08/31/2021 08:09:04 - INFO - __main__ - Step 104961: {'lr': 0.0001058148400369098, 'samples': 20152512, 'steps': 104960, 'loss/train': 0.5140676498413086} 08/31/2021 08:09:05 - INFO - __main__ - Step 104962: {'lr': 0.00010581050484499477, 'samples': 20152704, 'steps': 104961, 'loss/train': 1.5492761135101318} 08/31/2021 08:09:06 - INFO - __main__ - Step 104963: {'lr': 0.00010580616971804929, 'samples': 20152896, 'steps': 104962, 'loss/train': 1.2794146537780762} 08/31/2021 08:09:07 - INFO - __main__ - Step 104964: {'lr': 0.00010580183465607532, 'samples': 20153088, 'steps': 104963, 'loss/train': 1.3672140836715698} 08/31/2021 08:09:07 - INFO - __main__ - Step 104965: {'lr': 0.00010579749965907485, 'samples': 20153280, 'steps': 104964, 'loss/train': 0.9242538809776306} 08/31/2021 08:09:07 - INFO - __main__ - Step 104966: {'lr': 0.00010579316472704974, 'samples': 20153472, 'steps': 104965, 'loss/train': 1.4770108461380005} 08/31/2021 08:09:08 - INFO - __main__ - Step 104967: {'lr': 0.00010578882986000207, 'samples': 20153664, 'steps': 104966, 'loss/train': 1.2325197458267212} 08/31/2021 08:09:09 - INFO - __main__ - Step 104968: {'lr': 0.00010578449505793378, 'samples': 20153856, 'steps': 104967, 'loss/train': 1.0336030721664429} 08/31/2021 08:09:10 - INFO - __main__ - Step 104969: {'lr': 0.00010578016032084669, 'samples': 20154048, 'steps': 104968, 'loss/train': 1.3012276887893677} 08/31/2021 08:09:10 - INFO - __main__ - Step 104970: {'lr': 0.00010577582564874285, 'samples': 20154240, 'steps': 104969, 'loss/train': 1.2648682594299316} 08/31/2021 08:09:10 - INFO - __main__ - Step 104971: {'lr': 0.0001057714910416242, 'samples': 20154432, 'steps': 104970, 'loss/train': 0.17222872376441956} 08/31/2021 08:09:11 - INFO - __main__ - Step 104972: {'lr': 0.00010576715649949268, 'samples': 20154624, 'steps': 104971, 'loss/train': 0.8766909241676331} 08/31/2021 08:09:12 - INFO - __main__ - Step 104973: {'lr': 0.00010576282202235023, 'samples': 20154816, 'steps': 104972, 'loss/train': 0.9587438106536865} 08/31/2021 08:09:13 - INFO - __main__ - Step 104974: {'lr': 0.00010575848761019885, 'samples': 20155008, 'steps': 104973, 'loss/train': 0.7851959466934204} 08/31/2021 08:09:13 - INFO - __main__ - Step 104975: {'lr': 0.00010575415326304047, 'samples': 20155200, 'steps': 104974, 'loss/train': 0.7560685873031616} 08/31/2021 08:09:14 - INFO - __main__ - Step 104976: {'lr': 0.00010574981898087705, 'samples': 20155392, 'steps': 104975, 'loss/train': 1.4467991590499878} 08/31/2021 08:09:14 - INFO - __main__ - Step 104977: {'lr': 0.00010574548476371051, 'samples': 20155584, 'steps': 104976, 'loss/train': 1.656894326210022} 08/31/2021 08:09:15 - INFO - __main__ - Step 104978: {'lr': 0.00010574115061154285, 'samples': 20155776, 'steps': 104977, 'loss/train': 1.4369568824768066} 08/31/2021 08:09:16 - INFO - __main__ - Step 104979: {'lr': 0.000105736816524376, 'samples': 20155968, 'steps': 104978, 'loss/train': 1.5365879535675049} 08/31/2021 08:09:16 - INFO - __main__ - Step 104980: {'lr': 0.0001057324825022119, 'samples': 20156160, 'steps': 104979, 'loss/train': 1.3309271335601807} 08/31/2021 08:09:17 - INFO - __main__ - Step 104981: {'lr': 0.00010572814854505252, 'samples': 20156352, 'steps': 104980, 'loss/train': 0.9854734539985657} 08/31/2021 08:09:17 - INFO - __main__ - Step 104982: {'lr': 0.0001057238146528999, 'samples': 20156544, 'steps': 104981, 'loss/train': 0.5824598073959351} 08/31/2021 08:09:17 - INFO - __main__ - Step 104983: {'lr': 0.00010571948082575583, 'samples': 20156736, 'steps': 104982, 'loss/train': 1.0269999504089355} 08/31/2021 08:09:19 - INFO - __main__ - Step 104984: {'lr': 0.00010571514706362231, 'samples': 20156928, 'steps': 104983, 'loss/train': 1.8181307315826416} 08/31/2021 08:09:20 - INFO - __main__ - Step 104985: {'lr': 0.00010571081336650135, 'samples': 20157120, 'steps': 104984, 'loss/train': 1.215108871459961} 08/31/2021 08:09:20 - INFO - __main__ - Step 104986: {'lr': 0.00010570647973439485, 'samples': 20157312, 'steps': 104985, 'loss/train': 0.05214808136224747} 08/31/2021 08:09:20 - INFO - __main__ - Step 104987: {'lr': 0.00010570214616730478, 'samples': 20157504, 'steps': 104986, 'loss/train': 1.438924789428711} 08/31/2021 08:09:21 - INFO - __main__ - Step 104988: {'lr': 0.00010569781266523312, 'samples': 20157696, 'steps': 104987, 'loss/train': 0.6245241761207581} 08/31/2021 08:09:22 - INFO - __main__ - Step 104989: {'lr': 0.00010569347922818179, 'samples': 20157888, 'steps': 104988, 'loss/train': 1.0744789838790894} 08/31/2021 08:09:22 - INFO - __main__ - Step 104990: {'lr': 0.00010568914585615274, 'samples': 20158080, 'steps': 104989, 'loss/train': 0.35678523778915405} 08/31/2021 08:09:23 - INFO - __main__ - Step 104991: {'lr': 0.00010568481254914793, 'samples': 20158272, 'steps': 104990, 'loss/train': 1.2960723638534546} 08/31/2021 08:09:23 - INFO - __main__ - Step 104992: {'lr': 0.00010568047930716932, 'samples': 20158464, 'steps': 104991, 'loss/train': 0.9370571374893188} 08/31/2021 08:09:24 - INFO - __main__ - Step 104993: {'lr': 0.00010567614613021887, 'samples': 20158656, 'steps': 104992, 'loss/train': 1.6841130256652832} 08/31/2021 08:09:25 - INFO - __main__ - Step 104994: {'lr': 0.0001056718130182985, 'samples': 20158848, 'steps': 104993, 'loss/train': 1.3550522327423096} 08/31/2021 08:09:26 - INFO - __main__ - Step 104995: {'lr': 0.00010566747997141029, 'samples': 20159040, 'steps': 104994, 'loss/train': 1.1998811960220337} 08/31/2021 08:09:26 - INFO - __main__ - Step 104996: {'lr': 0.000105663146989556, 'samples': 20159232, 'steps': 104995, 'loss/train': 0.9839302897453308} 08/31/2021 08:09:26 - INFO - __main__ - Step 104997: {'lr': 0.00010565881407273767, 'samples': 20159424, 'steps': 104996, 'loss/train': 1.026582956314087} 08/31/2021 08:09:27 - INFO - __main__ - Step 104998: {'lr': 0.00010565448122095725, 'samples': 20159616, 'steps': 104997, 'loss/train': 0.46173954010009766} 08/31/2021 08:09:28 - INFO - __main__ - Step 104999: {'lr': 0.0001056501484342167, 'samples': 20159808, 'steps': 104998, 'loss/train': 0.03197352588176727} 08/31/2021 08:09:29 - INFO - __main__ - Step 105000: {'lr': 0.00010564581571251794, 'samples': 20160000, 'steps': 104999, 'loss/train': 0.7868649959564209} 08/31/2021 08:09:29 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 08:18:15 - INFO - __main__ - Step 105000: {'loss/eval': 1.020147442817688, 'perplexity': 2.773603677749634} 08/31/2021 08:18:15 - INFO - __main__ - Saving model checkpoint 08/31/2021 08:19:13 - INFO - __main__ - Step 105001: {'lr': 0.00010564148305586297, 'samples': 20160192, 'steps': 105000, 'loss/train': 1.2281724214553833} 08/31/2021 08:19:13 - INFO - __main__ - Step 105002: {'lr': 0.0001056371504642537, 'samples': 20160384, 'steps': 105001, 'loss/train': 0.8422194719314575} 08/31/2021 08:19:14 - INFO - __main__ - Step 105003: {'lr': 0.00010563281793769211, 'samples': 20160576, 'steps': 105002, 'loss/train': 0.8546005487442017} 08/31/2021 08:19:16 - INFO - __main__ - Step 105004: {'lr': 0.00010562848547618017, 'samples': 20160768, 'steps': 105003, 'loss/train': 1.066231369972229} 08/31/2021 08:19:16 - INFO - __main__ - Step 105005: {'lr': 0.00010562415307971979, 'samples': 20160960, 'steps': 105004, 'loss/train': 1.009142518043518} 08/31/2021 08:19:17 - INFO - __main__ - Step 105006: {'lr': 0.00010561982074831292, 'samples': 20161152, 'steps': 105005, 'loss/train': 0.6323432326316833} 08/31/2021 08:19:17 - INFO - __main__ - Step 105007: {'lr': 0.00010561548848196157, 'samples': 20161344, 'steps': 105006, 'loss/train': 1.0198276042938232} 08/31/2021 08:19:17 - INFO - __main__ - Step 105008: {'lr': 0.00010561115628066761, 'samples': 20161536, 'steps': 105007, 'loss/train': 0.9249420762062073} 08/31/2021 08:19:19 - INFO - __main__ - Step 105009: {'lr': 0.00010560682414443315, 'samples': 20161728, 'steps': 105008, 'loss/train': 0.5890960693359375} 08/31/2021 08:19:19 - INFO - __main__ - Step 105010: {'lr': 0.00010560249207325992, 'samples': 20161920, 'steps': 105009, 'loss/train': 1.170270562171936} 08/31/2021 08:19:20 - INFO - __main__ - Step 105011: {'lr': 0.00010559816006715, 'samples': 20162112, 'steps': 105010, 'loss/train': 0.7353661060333252} 08/31/2021 08:19:20 - INFO - __main__ - Step 105012: {'lr': 0.00010559382812610529, 'samples': 20162304, 'steps': 105011, 'loss/train': 1.7995141744613647} 08/31/2021 08:19:20 - INFO - __main__ - Step 105013: {'lr': 0.00010558949625012782, 'samples': 20162496, 'steps': 105012, 'loss/train': 1.1277936697006226} 08/31/2021 08:19:21 - INFO - __main__ - Step 105014: {'lr': 0.00010558516443921946, 'samples': 20162688, 'steps': 105013, 'loss/train': 1.2750567197799683} 08/31/2021 08:19:22 - INFO - __main__ - Step 105015: {'lr': 0.0001055808326933822, 'samples': 20162880, 'steps': 105014, 'loss/train': 0.6025093793869019} 08/31/2021 08:19:23 - INFO - __main__ - Step 105016: {'lr': 0.00010557650101261798, 'samples': 20163072, 'steps': 105015, 'loss/train': 1.3254072666168213} 08/31/2021 08:19:23 - INFO - __main__ - Step 105017: {'lr': 0.00010557216939692879, 'samples': 20163264, 'steps': 105016, 'loss/train': 1.5251851081848145} 08/31/2021 08:19:24 - INFO - __main__ - Step 105018: {'lr': 0.00010556783784631651, 'samples': 20163456, 'steps': 105017, 'loss/train': 0.3942871391773224} 08/31/2021 08:19:24 - INFO - __main__ - Step 105019: {'lr': 0.00010556350636078318, 'samples': 20163648, 'steps': 105018, 'loss/train': 1.4389894008636475} 08/31/2021 08:19:26 - INFO - __main__ - Step 105020: {'lr': 0.00010555917494033068, 'samples': 20163840, 'steps': 105019, 'loss/train': 0.9402697086334229} 08/31/2021 08:19:26 - INFO - __main__ - Step 105021: {'lr': 0.00010555484358496099, 'samples': 20164032, 'steps': 105020, 'loss/train': 0.7721148133277893} 08/31/2021 08:19:26 - INFO - __main__ - Step 105022: {'lr': 0.00010555051229467613, 'samples': 20164224, 'steps': 105021, 'loss/train': 1.1047570705413818} 08/31/2021 08:19:27 - INFO - __main__ - Step 105023: {'lr': 0.00010554618106947792, 'samples': 20164416, 'steps': 105022, 'loss/train': 1.2623248100280762} 08/31/2021 08:19:27 - INFO - __main__ - Step 105024: {'lr': 0.00010554184990936836, 'samples': 20164608, 'steps': 105023, 'loss/train': 1.251064419746399} 08/31/2021 08:19:29 - INFO - __main__ - Step 105025: {'lr': 0.00010553751881434942, 'samples': 20164800, 'steps': 105024, 'loss/train': 1.036949634552002} 08/31/2021 08:19:29 - INFO - __main__ - Step 105026: {'lr': 0.00010553318778442303, 'samples': 20164992, 'steps': 105025, 'loss/train': 1.218252182006836} 08/31/2021 08:19:30 - INFO - __main__ - Step 105027: {'lr': 0.00010552885681959119, 'samples': 20165184, 'steps': 105026, 'loss/train': 0.4216369390487671} 08/31/2021 08:19:30 - INFO - __main__ - Step 105028: {'lr': 0.00010552452591985579, 'samples': 20165376, 'steps': 105027, 'loss/train': 0.28346067667007446} 08/31/2021 08:19:30 - INFO - __main__ - Step 105029: {'lr': 0.00010552019508521879, 'samples': 20165568, 'steps': 105028, 'loss/train': 1.8195265531539917} 08/31/2021 08:19:31 - INFO - __main__ - Step 105030: {'lr': 0.00010551586431568219, 'samples': 20165760, 'steps': 105029, 'loss/train': 0.5119067430496216} 08/31/2021 08:19:32 - INFO - __main__ - Step 105031: {'lr': 0.00010551153361124791, 'samples': 20165952, 'steps': 105030, 'loss/train': 1.3380719423294067} 08/31/2021 08:19:33 - INFO - __main__ - Step 105032: {'lr': 0.00010550720297191787, 'samples': 20166144, 'steps': 105031, 'loss/train': 1.3595622777938843} 08/31/2021 08:19:33 - INFO - __main__ - Step 105033: {'lr': 0.0001055028723976941, 'samples': 20166336, 'steps': 105032, 'loss/train': 0.6478117108345032} 08/31/2021 08:19:33 - INFO - __main__ - Step 105034: {'lr': 0.0001054985418885785, 'samples': 20166528, 'steps': 105033, 'loss/train': 1.0857617855072021} 08/31/2021 08:19:34 - INFO - __main__ - Step 105035: {'lr': 0.0001054942114445731, 'samples': 20166720, 'steps': 105034, 'loss/train': 1.1866899728775024} 08/31/2021 08:19:35 - INFO - __main__ - Step 105036: {'lr': 0.00010548988106567969, 'samples': 20166912, 'steps': 105035, 'loss/train': 0.8426647782325745} 08/31/2021 08:19:36 - INFO - __main__ - Step 105037: {'lr': 0.0001054855507519003, 'samples': 20167104, 'steps': 105036, 'loss/train': 0.8056514859199524} 08/31/2021 08:19:36 - INFO - __main__ - Step 105038: {'lr': 0.00010548122050323691, 'samples': 20167296, 'steps': 105037, 'loss/train': 1.1083818674087524} 08/31/2021 08:19:36 - INFO - __main__ - Step 105039: {'lr': 0.00010547689031969146, 'samples': 20167488, 'steps': 105038, 'loss/train': 0.028775867074728012} 08/31/2021 08:19:37 - INFO - __main__ - Step 105040: {'lr': 0.00010547256020126589, 'samples': 20167680, 'steps': 105039, 'loss/train': 1.2353564500808716} 08/31/2021 08:19:38 - INFO - __main__ - Step 105041: {'lr': 0.00010546823014796214, 'samples': 20167872, 'steps': 105040, 'loss/train': 0.5273957252502441} 08/31/2021 08:19:39 - INFO - __main__ - Step 105042: {'lr': 0.00010546390015978217, 'samples': 20168064, 'steps': 105041, 'loss/train': 1.3008532524108887} 08/31/2021 08:19:39 - INFO - __main__ - Step 105043: {'lr': 0.00010545957023672795, 'samples': 20168256, 'steps': 105042, 'loss/train': 0.27147188782691956} 08/31/2021 08:19:39 - INFO - __main__ - Step 105044: {'lr': 0.00010545524037880142, 'samples': 20168448, 'steps': 105043, 'loss/train': 0.9647092223167419} 08/31/2021 08:19:40 - INFO - __main__ - Step 105045: {'lr': 0.00010545091058600451, 'samples': 20168640, 'steps': 105044, 'loss/train': 1.0454849004745483} 08/31/2021 08:19:41 - INFO - __main__ - Step 105046: {'lr': 0.00010544658085833919, 'samples': 20168832, 'steps': 105045, 'loss/train': 0.7609098553657532} 08/31/2021 08:19:42 - INFO - __main__ - Step 105047: {'lr': 0.00010544225119580741, 'samples': 20169024, 'steps': 105046, 'loss/train': 0.40301552414894104} 08/31/2021 08:19:42 - INFO - __main__ - Step 105048: {'lr': 0.00010543792159841115, 'samples': 20169216, 'steps': 105047, 'loss/train': 0.8032633066177368} 08/31/2021 08:19:43 - INFO - __main__ - Step 105049: {'lr': 0.00010543359206615242, 'samples': 20169408, 'steps': 105048, 'loss/train': 0.8497207164764404} 08/31/2021 08:19:43 - INFO - __main__ - Step 105050: {'lr': 0.00010542926259903296, 'samples': 20169600, 'steps': 105049, 'loss/train': 1.681134819984436} 08/31/2021 08:19:45 - INFO - __main__ - Step 105051: {'lr': 0.00010542493319705484, 'samples': 20169792, 'steps': 105050, 'loss/train': 1.0282788276672363} 08/31/2021 08:19:45 - INFO - __main__ - Step 105052: {'lr': 0.00010542060386022004, 'samples': 20169984, 'steps': 105051, 'loss/train': 1.0851260423660278} 08/31/2021 08:19:45 - INFO - __main__ - Step 105053: {'lr': 0.00010541627458853048, 'samples': 20170176, 'steps': 105052, 'loss/train': 1.0552949905395508} 08/31/2021 08:19:46 - INFO - __main__ - Step 105054: {'lr': 0.00010541194538198812, 'samples': 20170368, 'steps': 105053, 'loss/train': 1.5372302532196045} 08/31/2021 08:19:46 - INFO - __main__ - Step 105055: {'lr': 0.00010540761624059489, 'samples': 20170560, 'steps': 105054, 'loss/train': 1.3926950693130493} 08/31/2021 08:19:48 - INFO - __main__ - Step 105056: {'lr': 0.00010540328716435277, 'samples': 20170752, 'steps': 105055, 'loss/train': 0.6882191896438599} 08/31/2021 08:19:48 - INFO - __main__ - Step 105057: {'lr': 0.00010539895815326369, 'samples': 20170944, 'steps': 105056, 'loss/train': 1.3646029233932495} 08/31/2021 08:19:48 - INFO - __main__ - Step 105058: {'lr': 0.00010539462920732962, 'samples': 20171136, 'steps': 105057, 'loss/train': 0.43947476148605347} 08/31/2021 08:19:49 - INFO - __main__ - Step 105059: {'lr': 0.0001053903003265525, 'samples': 20171328, 'steps': 105058, 'loss/train': 0.41769811511039734} 08/31/2021 08:19:49 - INFO - __main__ - Step 105060: {'lr': 0.00010538597151093426, 'samples': 20171520, 'steps': 105059, 'loss/train': 1.158011555671692} 08/31/2021 08:19:50 - INFO - __main__ - Step 105061: {'lr': 0.00010538164276047688, 'samples': 20171712, 'steps': 105060, 'loss/train': 0.5763310790061951} 08/31/2021 08:19:52 - INFO - __main__ - Step 105062: {'lr': 0.00010537731407518238, 'samples': 20171904, 'steps': 105061, 'loss/train': 1.3739066123962402} 08/31/2021 08:19:52 - INFO - __main__ - Step 105063: {'lr': 0.00010537298545505256, 'samples': 20172096, 'steps': 105062, 'loss/train': 1.484243631362915} 08/31/2021 08:19:52 - INFO - __main__ - Step 105064: {'lr': 0.00010536865690008943, 'samples': 20172288, 'steps': 105063, 'loss/train': 1.2835320234298706} 08/31/2021 08:19:53 - INFO - __main__ - Step 105065: {'lr': 0.00010536432841029497, 'samples': 20172480, 'steps': 105064, 'loss/train': 0.7705671787261963} 08/31/2021 08:19:53 - INFO - __main__ - Step 105066: {'lr': 0.00010535999998567108, 'samples': 20172672, 'steps': 105065, 'loss/train': 1.3018571138381958} 08/31/2021 08:19:55 - INFO - __main__ - Step 105067: {'lr': 0.00010535567162621975, 'samples': 20172864, 'steps': 105066, 'loss/train': 0.9765710234642029} 08/31/2021 08:19:55 - INFO - __main__ - Step 105068: {'lr': 0.00010535134333194293, 'samples': 20173056, 'steps': 105067, 'loss/train': 1.098104476928711} 08/31/2021 08:19:56 - INFO - __main__ - Step 105069: {'lr': 0.00010534701510284258, 'samples': 20173248, 'steps': 105068, 'loss/train': 0.36772629618644714} 08/31/2021 08:19:56 - INFO - __main__ - Step 105070: {'lr': 0.0001053426869389206, 'samples': 20173440, 'steps': 105069, 'loss/train': 1.428608775138855} 08/31/2021 08:19:56 - INFO - __main__ - Step 105071: {'lr': 0.000105338358840179, 'samples': 20173632, 'steps': 105070, 'loss/train': 1.0516018867492676} 08/31/2021 08:19:58 - INFO - __main__ - Step 105072: {'lr': 0.00010533403080661968, 'samples': 20173824, 'steps': 105071, 'loss/train': 1.2410181760787964} 08/31/2021 08:19:58 - INFO - __main__ - Step 105073: {'lr': 0.00010532970283824472, 'samples': 20174016, 'steps': 105072, 'loss/train': 1.2692315578460693} 08/31/2021 08:19:58 - INFO - __main__ - Step 105074: {'lr': 0.00010532537493505587, 'samples': 20174208, 'steps': 105073, 'loss/train': 0.8522570729255676} 08/31/2021 08:19:59 - INFO - __main__ - Step 105075: {'lr': 0.00010532104709705517, 'samples': 20174400, 'steps': 105074, 'loss/train': 1.1089510917663574} 08/31/2021 08:19:59 - INFO - __main__ - Step 105076: {'lr': 0.00010531671932424458, 'samples': 20174592, 'steps': 105075, 'loss/train': 1.310166597366333} 08/31/2021 08:20:01 - INFO - __main__ - Step 105077: {'lr': 0.00010531239161662603, 'samples': 20174784, 'steps': 105076, 'loss/train': 1.3266538381576538} 08/31/2021 08:20:01 - INFO - __main__ - Step 105078: {'lr': 0.00010530806397420151, 'samples': 20174976, 'steps': 105077, 'loss/train': 1.293400764465332} 08/31/2021 08:20:01 - INFO - __main__ - Step 105079: {'lr': 0.0001053037363969729, 'samples': 20175168, 'steps': 105078, 'loss/train': 1.5355740785598755} 08/31/2021 08:20:02 - INFO - __main__ - Step 105080: {'lr': 0.00010529940888494224, 'samples': 20175360, 'steps': 105079, 'loss/train': 1.8637571334838867} 08/31/2021 08:20:02 - INFO - __main__ - Step 105081: {'lr': 0.00010529508143811142, 'samples': 20175552, 'steps': 105080, 'loss/train': 1.239051342010498} 08/31/2021 08:20:04 - INFO - __main__ - Step 105082: {'lr': 0.00010529075405648239, 'samples': 20175744, 'steps': 105081, 'loss/train': 1.3489995002746582} 08/31/2021 08:20:04 - INFO - __main__ - Step 105083: {'lr': 0.00010528642674005712, 'samples': 20175936, 'steps': 105082, 'loss/train': 0.3358563184738159} 08/31/2021 08:20:04 - INFO - __main__ - Step 105084: {'lr': 0.00010528209948883763, 'samples': 20176128, 'steps': 105083, 'loss/train': 0.1997682899236679} 08/31/2021 08:20:05 - INFO - __main__ - Step 105085: {'lr': 0.00010527777230282572, 'samples': 20176320, 'steps': 105084, 'loss/train': 0.44863060116767883} 08/31/2021 08:20:05 - INFO - __main__ - Step 105086: {'lr': 0.00010527344518202341, 'samples': 20176512, 'steps': 105085, 'loss/train': 1.1423715353012085} 08/31/2021 08:20:07 - INFO - __main__ - Step 105087: {'lr': 0.00010526911812643266, 'samples': 20176704, 'steps': 105086, 'loss/train': 0.6932131052017212} 08/31/2021 08:20:07 - INFO - __main__ - Step 105088: {'lr': 0.00010526479113605539, 'samples': 20176896, 'steps': 105087, 'loss/train': 1.0138479471206665} 08/31/2021 08:20:07 - INFO - __main__ - Step 105089: {'lr': 0.00010526046421089358, 'samples': 20177088, 'steps': 105088, 'loss/train': 2.1401243209838867} 08/31/2021 08:20:08 - INFO - __main__ - Step 105090: {'lr': 0.00010525613735094919, 'samples': 20177280, 'steps': 105089, 'loss/train': 1.3251301050186157} 08/31/2021 08:20:08 - INFO - __main__ - Step 105091: {'lr': 0.00010525181055622412, 'samples': 20177472, 'steps': 105090, 'loss/train': 1.2575043439865112} 08/31/2021 08:20:10 - INFO - __main__ - Step 105092: {'lr': 0.00010524748382672039, 'samples': 20177664, 'steps': 105091, 'loss/train': 0.5667254328727722} 08/31/2021 08:20:10 - INFO - __main__ - Step 105093: {'lr': 0.00010524315716243988, 'samples': 20177856, 'steps': 105092, 'loss/train': 1.4336004257202148} 08/31/2021 08:20:11 - INFO - __main__ - Step 105094: {'lr': 0.00010523883056338457, 'samples': 20178048, 'steps': 105093, 'loss/train': 0.7689983248710632} 08/31/2021 08:20:11 - INFO - __main__ - Step 105095: {'lr': 0.00010523450402955651, 'samples': 20178240, 'steps': 105094, 'loss/train': 5.826443195343018} 08/31/2021 08:20:11 - INFO - __main__ - Step 105096: {'lr': 0.00010523017756095745, 'samples': 20178432, 'steps': 105095, 'loss/train': 1.0556200742721558} 08/31/2021 08:20:12 - INFO - __main__ - Step 105097: {'lr': 0.00010522585115758945, 'samples': 20178624, 'steps': 105096, 'loss/train': 1.100460410118103} 08/31/2021 08:20:13 - INFO - __main__ - Step 105098: {'lr': 0.00010522152481945443, 'samples': 20178816, 'steps': 105097, 'loss/train': 1.800125241279602} 08/31/2021 08:20:14 - INFO - __main__ - Step 105099: {'lr': 0.00010521719854655437, 'samples': 20179008, 'steps': 105098, 'loss/train': 1.2409647703170776} 08/31/2021 08:20:14 - INFO - __main__ - Step 105100: {'lr': 0.00010521287233889121, 'samples': 20179200, 'steps': 105099, 'loss/train': 1.2482280731201172} 08/31/2021 08:20:14 - INFO - __main__ - Step 105101: {'lr': 0.00010520854619646689, 'samples': 20179392, 'steps': 105100, 'loss/train': 1.4607805013656616} 08/31/2021 08:20:15 - INFO - __main__ - Step 105102: {'lr': 0.00010520422011928337, 'samples': 20179584, 'steps': 105101, 'loss/train': 0.7154951095581055} 08/31/2021 08:20:16 - INFO - __main__ - Step 105103: {'lr': 0.0001051998941073426, 'samples': 20179776, 'steps': 105102, 'loss/train': 1.4795958995819092} 08/31/2021 08:20:17 - INFO - __main__ - Step 105104: {'lr': 0.00010519556816064649, 'samples': 20179968, 'steps': 105103, 'loss/train': 0.6420783996582031} 08/31/2021 08:20:17 - INFO - __main__ - Step 105105: {'lr': 0.00010519124227919705, 'samples': 20180160, 'steps': 105104, 'loss/train': 0.29131871461868286} 08/31/2021 08:20:17 - INFO - __main__ - Step 105106: {'lr': 0.00010518691646299628, 'samples': 20180352, 'steps': 105105, 'loss/train': 1.0334739685058594} 08/31/2021 08:20:18 - INFO - __main__ - Step 105107: {'lr': 0.00010518259071204597, 'samples': 20180544, 'steps': 105106, 'loss/train': 0.03255676105618477} 08/31/2021 08:20:19 - INFO - __main__ - Step 105108: {'lr': 0.00010517826502634815, 'samples': 20180736, 'steps': 105107, 'loss/train': 1.3994488716125488} 08/31/2021 08:20:20 - INFO - __main__ - Step 105109: {'lr': 0.00010517393940590475, 'samples': 20180928, 'steps': 105108, 'loss/train': 0.4036102294921875} 08/31/2021 08:20:20 - INFO - __main__ - Step 105110: {'lr': 0.00010516961385071777, 'samples': 20181120, 'steps': 105109, 'loss/train': 0.6757689118385315} 08/31/2021 08:20:20 - INFO - __main__ - Step 105111: {'lr': 0.00010516528836078912, 'samples': 20181312, 'steps': 105110, 'loss/train': 0.5109900236129761} 08/31/2021 08:20:21 - INFO - __main__ - Step 105112: {'lr': 0.00010516096293612074, 'samples': 20181504, 'steps': 105111, 'loss/train': 1.1669737100601196} 08/31/2021 08:20:22 - INFO - __main__ - Step 105113: {'lr': 0.00010515663757671459, 'samples': 20181696, 'steps': 105112, 'loss/train': 1.3345134258270264} 08/31/2021 08:20:23 - INFO - __main__ - Step 105114: {'lr': 0.00010515231228257263, 'samples': 20181888, 'steps': 105113, 'loss/train': 1.0090949535369873} 08/31/2021 08:20:23 - INFO - __main__ - Step 105115: {'lr': 0.00010514798705369682, 'samples': 20182080, 'steps': 105114, 'loss/train': 1.0281293392181396} 08/31/2021 08:20:23 - INFO - __main__ - Step 105116: {'lr': 0.00010514366189008909, 'samples': 20182272, 'steps': 105115, 'loss/train': 1.4257597923278809} 08/31/2021 08:20:24 - INFO - __main__ - Step 105117: {'lr': 0.00010513933679175147, 'samples': 20182464, 'steps': 105116, 'loss/train': 0.9182392954826355} 08/31/2021 08:20:26 - INFO - __main__ - Step 105118: {'lr': 0.00010513501175868573, 'samples': 20182656, 'steps': 105117, 'loss/train': 1.48539400100708} 08/31/2021 08:20:26 - INFO - __main__ - Step 105119: {'lr': 0.00010513068679089394, 'samples': 20182848, 'steps': 105118, 'loss/train': 0.42304569482803345} 08/31/2021 08:20:27 - INFO - __main__ - Step 105120: {'lr': 0.00010512636188837801, 'samples': 20183040, 'steps': 105119, 'loss/train': 1.0219361782073975} 08/31/2021 08:20:27 - INFO - __main__ - Step 105121: {'lr': 0.00010512203705113991, 'samples': 20183232, 'steps': 105120, 'loss/train': 1.0593644380569458} 08/31/2021 08:20:27 - INFO - __main__ - Step 105122: {'lr': 0.0001051177122791816, 'samples': 20183424, 'steps': 105121, 'loss/train': 1.1922255754470825} 08/31/2021 08:20:29 - INFO - __main__ - Step 105123: {'lr': 0.000105113387572505, 'samples': 20183616, 'steps': 105122, 'loss/train': 0.759606659412384} 08/31/2021 08:20:30 - INFO - __main__ - Step 105124: {'lr': 0.00010510906293111205, 'samples': 20183808, 'steps': 105123, 'loss/train': 1.415083885192871} 08/31/2021 08:20:30 - INFO - __main__ - Step 105125: {'lr': 0.00010510473835500476, 'samples': 20184000, 'steps': 105124, 'loss/train': 0.8164761662483215} 08/31/2021 08:20:30 - INFO - __main__ - Step 105126: {'lr': 0.000105100413844185, 'samples': 20184192, 'steps': 105125, 'loss/train': 0.6694581508636475} 08/31/2021 08:20:31 - INFO - __main__ - Step 105127: {'lr': 0.00010509608939865478, 'samples': 20184384, 'steps': 105126, 'loss/train': 0.3866545259952545} 08/31/2021 08:20:31 - INFO - __main__ - Step 105128: {'lr': 0.00010509176501841602, 'samples': 20184576, 'steps': 105127, 'loss/train': 1.36874520778656} 08/31/2021 08:20:32 - INFO - __main__ - Step 105129: {'lr': 0.00010508744070347071, 'samples': 20184768, 'steps': 105128, 'loss/train': 1.0839682817459106} 08/31/2021 08:20:33 - INFO - __main__ - Step 105130: {'lr': 0.00010508311645382083, 'samples': 20184960, 'steps': 105129, 'loss/train': 0.9136685729026794} 08/31/2021 08:20:33 - INFO - __main__ - Step 105131: {'lr': 0.00010507879226946814, 'samples': 20185152, 'steps': 105130, 'loss/train': 1.3527477979660034} 08/31/2021 08:20:34 - INFO - __main__ - Step 105132: {'lr': 0.00010507446815041475, 'samples': 20185344, 'steps': 105131, 'loss/train': 1.131778359413147} 08/31/2021 08:20:34 - INFO - __main__ - Step 105133: {'lr': 0.00010507014409666255, 'samples': 20185536, 'steps': 105132, 'loss/train': 0.6439208984375} 08/31/2021 08:20:36 - INFO - __main__ - Step 105134: {'lr': 0.0001050658201082135, 'samples': 20185728, 'steps': 105133, 'loss/train': 1.74103844165802} 08/31/2021 08:20:36 - INFO - __main__ - Step 105135: {'lr': 0.00010506149618506956, 'samples': 20185920, 'steps': 105134, 'loss/train': 0.07209568470716476} 08/31/2021 08:20:37 - INFO - __main__ - Step 105136: {'lr': 0.00010505717232723266, 'samples': 20186112, 'steps': 105135, 'loss/train': 0.9396089911460876} 08/31/2021 08:20:37 - INFO - __main__ - Step 105137: {'lr': 0.00010505284853470479, 'samples': 20186304, 'steps': 105136, 'loss/train': 2.087850332260132} 08/31/2021 08:20:37 - INFO - __main__ - Step 105138: {'lr': 0.00010504852480748786, 'samples': 20186496, 'steps': 105137, 'loss/train': 0.7928347587585449} 08/31/2021 08:20:39 - INFO - __main__ - Step 105139: {'lr': 0.00010504420114558382, 'samples': 20186688, 'steps': 105138, 'loss/train': 0.8925848007202148} 08/31/2021 08:20:39 - INFO - __main__ - Step 105140: {'lr': 0.00010503987754899463, 'samples': 20186880, 'steps': 105139, 'loss/train': 2.252793312072754} 08/31/2021 08:20:40 - INFO - __main__ - Step 105141: {'lr': 0.00010503555401772224, 'samples': 20187072, 'steps': 105140, 'loss/train': 1.829186201095581} 08/31/2021 08:20:40 - INFO - __main__ - Step 105142: {'lr': 0.00010503123055176861, 'samples': 20187264, 'steps': 105141, 'loss/train': 0.9065923690795898} 08/31/2021 08:20:40 - INFO - __main__ - Step 105143: {'lr': 0.00010502690715113572, 'samples': 20187456, 'steps': 105142, 'loss/train': 0.36279043555259705} 08/31/2021 08:20:42 - INFO - __main__ - Step 105144: {'lr': 0.00010502258381582541, 'samples': 20187648, 'steps': 105143, 'loss/train': 1.2718380689620972} 08/31/2021 08:20:42 - INFO - __main__ - Step 105145: {'lr': 0.00010501826054583968, 'samples': 20187840, 'steps': 105144, 'loss/train': 1.578251600265503} 08/31/2021 08:20:43 - INFO - __main__ - Step 105146: {'lr': 0.00010501393734118048, 'samples': 20188032, 'steps': 105145, 'loss/train': 1.3959945440292358} 08/31/2021 08:20:43 - INFO - __main__ - Step 105147: {'lr': 0.00010500961420184976, 'samples': 20188224, 'steps': 105146, 'loss/train': 1.0191783905029297} 08/31/2021 08:20:43 - INFO - __main__ - Step 105148: {'lr': 0.00010500529112784945, 'samples': 20188416, 'steps': 105147, 'loss/train': 1.2163500785827637} 08/31/2021 08:20:45 - INFO - __main__ - Step 105149: {'lr': 0.00010500096811918156, 'samples': 20188608, 'steps': 105148, 'loss/train': 1.171643614768982} 08/31/2021 08:20:45 - INFO - __main__ - Step 105150: {'lr': 0.00010499664517584798, 'samples': 20188800, 'steps': 105149, 'loss/train': 0.23028957843780518} 08/31/2021 08:20:46 - INFO - __main__ - Step 105151: {'lr': 0.00010499232229785067, 'samples': 20188992, 'steps': 105150, 'loss/train': 1.3155369758605957} 08/31/2021 08:20:46 - INFO - __main__ - Step 105152: {'lr': 0.00010498799948519158, 'samples': 20189184, 'steps': 105151, 'loss/train': 1.4330060482025146} 08/31/2021 08:20:46 - INFO - __main__ - Step 105153: {'lr': 0.00010498367673787266, 'samples': 20189376, 'steps': 105152, 'loss/train': 0.877869725227356} 08/31/2021 08:20:47 - INFO - __main__ - Step 105154: {'lr': 0.00010497935405589587, 'samples': 20189568, 'steps': 105153, 'loss/train': 0.8722127676010132} 08/31/2021 08:20:48 - INFO - __main__ - Step 105155: {'lr': 0.00010497503143926313, 'samples': 20189760, 'steps': 105154, 'loss/train': 1.2494999170303345} 08/31/2021 08:20:49 - INFO - __main__ - Step 105156: {'lr': 0.0001049707088879765, 'samples': 20189952, 'steps': 105155, 'loss/train': 1.192293405532837} 08/31/2021 08:20:49 - INFO - __main__ - Step 105157: {'lr': 0.00010496638640203774, 'samples': 20190144, 'steps': 105156, 'loss/train': 1.055669903755188} 08/31/2021 08:20:49 - INFO - __main__ - Step 105158: {'lr': 0.00010496206398144888, 'samples': 20190336, 'steps': 105157, 'loss/train': 1.1832785606384277} 08/31/2021 08:20:50 - INFO - __main__ - Step 105159: {'lr': 0.00010495774162621189, 'samples': 20190528, 'steps': 105158, 'loss/train': 1.2110540866851807} 08/31/2021 08:20:52 - INFO - __main__ - Step 105160: {'lr': 0.0001049534193363287, 'samples': 20190720, 'steps': 105159, 'loss/train': 1.0195015668869019} 08/31/2021 08:20:52 - INFO - __main__ - Step 105161: {'lr': 0.00010494909711180125, 'samples': 20190912, 'steps': 105160, 'loss/train': 0.06654872745275497} 08/31/2021 08:20:52 - INFO - __main__ - Step 105162: {'lr': 0.00010494477495263152, 'samples': 20191104, 'steps': 105161, 'loss/train': 0.15891778469085693} 08/31/2021 08:20:53 - INFO - __main__ - Step 105163: {'lr': 0.00010494045285882143, 'samples': 20191296, 'steps': 105162, 'loss/train': 0.7607253789901733} 08/31/2021 08:20:53 - INFO - __main__ - Step 105164: {'lr': 0.0001049361308303729, 'samples': 20191488, 'steps': 105163, 'loss/train': 0.791624128818512} 08/31/2021 08:20:53 - INFO - __main__ - Step 105165: {'lr': 0.00010493180886728796, 'samples': 20191680, 'steps': 105164, 'loss/train': 1.4964853525161743} 08/31/2021 08:20:55 - INFO - __main__ - Step 105166: {'lr': 0.00010492748696956846, 'samples': 20191872, 'steps': 105165, 'loss/train': 0.016793597489595413} 08/31/2021 08:20:56 - INFO - __main__ - Step 105167: {'lr': 0.00010492316513721645, 'samples': 20192064, 'steps': 105166, 'loss/train': 0.9282083511352539} 08/31/2021 08:20:56 - INFO - __main__ - Step 105168: {'lr': 0.00010491884337023377, 'samples': 20192256, 'steps': 105167, 'loss/train': 1.354393720626831} 08/31/2021 08:20:56 - INFO - __main__ - Step 105169: {'lr': 0.00010491452166862245, 'samples': 20192448, 'steps': 105168, 'loss/train': 1.3376737833023071} 08/31/2021 08:20:57 - INFO - __main__ - Step 105170: {'lr': 0.00010491020003238449, 'samples': 20192640, 'steps': 105169, 'loss/train': 0.8817601203918457} 08/31/2021 08:20:59 - INFO - __main__ - Step 105171: {'lr': 0.00010490587846152166, 'samples': 20192832, 'steps': 105170, 'loss/train': 1.0904200077056885} 08/31/2021 08:20:59 - INFO - __main__ - Step 105172: {'lr': 0.00010490155695603604, 'samples': 20193024, 'steps': 105171, 'loss/train': 0.43847206234931946} 08/31/2021 08:21:00 - INFO - __main__ - Step 105173: {'lr': 0.0001048972355159295, 'samples': 20193216, 'steps': 105172, 'loss/train': 1.374102234840393} 08/31/2021 08:21:00 - INFO - __main__ - Step 105174: {'lr': 0.00010489291414120403, 'samples': 20193408, 'steps': 105173, 'loss/train': 0.6380664706230164} 08/31/2021 08:21:00 - INFO - __main__ - Step 105175: {'lr': 0.00010488859283186158, 'samples': 20193600, 'steps': 105174, 'loss/train': 1.5922802686691284} 08/31/2021 08:21:01 - INFO - __main__ - Step 105176: {'lr': 0.00010488427158790408, 'samples': 20193792, 'steps': 105175, 'loss/train': 0.9388678073883057} 08/31/2021 08:21:02 - INFO - __main__ - Step 105177: {'lr': 0.00010487995040933352, 'samples': 20193984, 'steps': 105176, 'loss/train': 1.3367986679077148} 08/31/2021 08:21:03 - INFO - __main__ - Step 105178: {'lr': 0.0001048756292961518, 'samples': 20194176, 'steps': 105177, 'loss/train': 1.1996225118637085} 08/31/2021 08:21:03 - INFO - __main__ - Step 105179: {'lr': 0.00010487130824836086, 'samples': 20194368, 'steps': 105178, 'loss/train': 1.1591931581497192} 08/31/2021 08:21:03 - INFO - __main__ - Step 105180: {'lr': 0.00010486698726596269, 'samples': 20194560, 'steps': 105179, 'loss/train': 1.2558799982070923} 08/31/2021 08:21:04 - INFO - __main__ - Step 105181: {'lr': 0.00010486266634895922, 'samples': 20194752, 'steps': 105180, 'loss/train': 0.7643042206764221} 08/31/2021 08:21:06 - INFO - __main__ - Step 105182: {'lr': 0.00010485834549735237, 'samples': 20194944, 'steps': 105181, 'loss/train': 1.393633246421814} 08/31/2021 08:21:06 - INFO - __main__ - Step 105183: {'lr': 0.00010485402471114422, 'samples': 20195136, 'steps': 105182, 'loss/train': 1.060198187828064} 08/31/2021 08:21:06 - INFO - __main__ - Step 105184: {'lr': 0.0001048497039903365, 'samples': 20195328, 'steps': 105183, 'loss/train': 0.4292512834072113} 08/31/2021 08:21:07 - INFO - __main__ - Step 105185: {'lr': 0.00010484538333493127, 'samples': 20195520, 'steps': 105184, 'loss/train': 1.2470179796218872} 08/31/2021 08:21:07 - INFO - __main__ - Step 105186: {'lr': 0.00010484106274493049, 'samples': 20195712, 'steps': 105185, 'loss/train': 0.09315679222345352} 08/31/2021 08:21:09 - INFO - __main__ - Step 105187: {'lr': 0.00010483674222033607, 'samples': 20195904, 'steps': 105186, 'loss/train': 0.6680126786231995} 08/31/2021 08:21:10 - INFO - __main__ - Step 105188: {'lr': 0.00010483242176114996, 'samples': 20196096, 'steps': 105187, 'loss/train': 1.4061862230300903} 08/31/2021 08:21:10 - INFO - __main__ - Step 105189: {'lr': 0.00010482810136737414, 'samples': 20196288, 'steps': 105188, 'loss/train': 1.373706340789795} 08/31/2021 08:21:10 - INFO - __main__ - Step 105190: {'lr': 0.00010482378103901052, 'samples': 20196480, 'steps': 105189, 'loss/train': 1.9672446250915527} 08/31/2021 08:21:11 - INFO - __main__ - Step 105191: {'lr': 0.00010481946077606108, 'samples': 20196672, 'steps': 105190, 'loss/train': 1.4338356256484985} 08/31/2021 08:21:12 - INFO - __main__ - Step 105192: {'lr': 0.00010481514057852776, 'samples': 20196864, 'steps': 105191, 'loss/train': 0.917847216129303} 08/31/2021 08:21:12 - INFO - __main__ - Step 105193: {'lr': 0.00010481082044641249, 'samples': 20197056, 'steps': 105192, 'loss/train': 1.0236690044403076} 08/31/2021 08:21:13 - INFO - __main__ - Step 105194: {'lr': 0.00010480650037971723, 'samples': 20197248, 'steps': 105193, 'loss/train': 1.1673914194107056} 08/31/2021 08:21:13 - INFO - __main__ - Step 105195: {'lr': 0.00010480218037844389, 'samples': 20197440, 'steps': 105194, 'loss/train': 0.7326564788818359} 08/31/2021 08:21:14 - INFO - __main__ - Step 105196: {'lr': 0.00010479786044259449, 'samples': 20197632, 'steps': 105195, 'loss/train': 1.2135934829711914} 08/31/2021 08:21:14 - INFO - __main__ - Step 105197: {'lr': 0.000104793540572171, 'samples': 20197824, 'steps': 105196, 'loss/train': 1.3354657888412476} 08/31/2021 08:21:15 - INFO - __main__ - Step 105198: {'lr': 0.0001047892207671752, 'samples': 20198016, 'steps': 105197, 'loss/train': 0.8125900626182556} 08/31/2021 08:21:16 - INFO - __main__ - Step 105199: {'lr': 0.00010478490102760915, 'samples': 20198208, 'steps': 105198, 'loss/train': 1.1897683143615723} 08/31/2021 08:21:16 - INFO - __main__ - Step 105200: {'lr': 0.00010478058135347477, 'samples': 20198400, 'steps': 105199, 'loss/train': 1.9993062019348145} 08/31/2021 08:21:17 - INFO - __main__ - Step 105201: {'lr': 0.00010477626174477404, 'samples': 20198592, 'steps': 105200, 'loss/train': 0.9171655178070068} 08/31/2021 08:21:17 - INFO - __main__ - Step 105202: {'lr': 0.00010477194220150887, 'samples': 20198784, 'steps': 105201, 'loss/train': 1.2319529056549072} 08/31/2021 08:21:18 - INFO - __main__ - Step 105203: {'lr': 0.00010476762272368124, 'samples': 20198976, 'steps': 105202, 'loss/train': 0.9685291051864624} 08/31/2021 08:21:19 - INFO - __main__ - Step 105204: {'lr': 0.00010476330331129305, 'samples': 20199168, 'steps': 105203, 'loss/train': 0.8453961610794067} 08/31/2021 08:21:19 - INFO - __main__ - Step 105205: {'lr': 0.00010475898396434627, 'samples': 20199360, 'steps': 105204, 'loss/train': 1.2124049663543701} 08/31/2021 08:21:20 - INFO - __main__ - Step 105206: {'lr': 0.0001047546646828429, 'samples': 20199552, 'steps': 105205, 'loss/train': 1.9635862112045288} 08/31/2021 08:21:20 - INFO - __main__ - Step 105207: {'lr': 0.00010475034546678478, 'samples': 20199744, 'steps': 105206, 'loss/train': 1.3758102655410767} 08/31/2021 08:21:22 - INFO - __main__ - Step 105208: {'lr': 0.00010474602631617395, 'samples': 20199936, 'steps': 105207, 'loss/train': 1.1317193508148193} 08/31/2021 08:21:22 - INFO - __main__ - Step 105209: {'lr': 0.00010474170723101231, 'samples': 20200128, 'steps': 105208, 'loss/train': 0.7592847347259521} 08/31/2021 08:21:22 - INFO - __main__ - Step 105210: {'lr': 0.00010473738821130191, 'samples': 20200320, 'steps': 105209, 'loss/train': 1.4481873512268066} 08/31/2021 08:21:23 - INFO - __main__ - Step 105211: {'lr': 0.00010473306925704448, 'samples': 20200512, 'steps': 105210, 'loss/train': 1.433190107345581} 08/31/2021 08:21:23 - INFO - __main__ - Step 105212: {'lr': 0.00010472875036824211, 'samples': 20200704, 'steps': 105211, 'loss/train': 0.9453040957450867} 08/31/2021 08:21:25 - INFO - __main__ - Step 105213: {'lr': 0.00010472443154489675, 'samples': 20200896, 'steps': 105212, 'loss/train': 1.333503007888794} 08/31/2021 08:21:25 - INFO - __main__ - Step 105214: {'lr': 0.0001047201127870103, 'samples': 20201088, 'steps': 105213, 'loss/train': 0.8411892652511597} 08/31/2021 08:21:26 - INFO - __main__ - Step 105215: {'lr': 0.0001047157940945847, 'samples': 20201280, 'steps': 105214, 'loss/train': 0.5701859593391418} 08/31/2021 08:21:26 - INFO - __main__ - Step 105216: {'lr': 0.00010471147546762195, 'samples': 20201472, 'steps': 105215, 'loss/train': 0.8318484425544739} 08/31/2021 08:21:26 - INFO - __main__ - Step 105217: {'lr': 0.00010470715690612396, 'samples': 20201664, 'steps': 105216, 'loss/train': 1.7678966522216797} 08/31/2021 08:21:29 - INFO - __main__ - Step 105218: {'lr': 0.00010470283841009268, 'samples': 20201856, 'steps': 105217, 'loss/train': 0.9007284045219421} 08/31/2021 08:21:29 - INFO - __main__ - Step 105219: {'lr': 0.00010469851997953006, 'samples': 20202048, 'steps': 105218, 'loss/train': 0.7457420825958252} 08/31/2021 08:21:29 - INFO - __main__ - Step 105220: {'lr': 0.00010469420161443805, 'samples': 20202240, 'steps': 105219, 'loss/train': 0.551665186882019} 08/31/2021 08:21:30 - INFO - __main__ - Step 105221: {'lr': 0.00010468988331481857, 'samples': 20202432, 'steps': 105220, 'loss/train': 1.203680396080017} 08/31/2021 08:21:30 - INFO - __main__ - Step 105222: {'lr': 0.00010468556508067361, 'samples': 20202624, 'steps': 105221, 'loss/train': 1.2108632326126099} 08/31/2021 08:21:31 - INFO - __main__ - Step 105223: {'lr': 0.00010468124691200509, 'samples': 20202816, 'steps': 105222, 'loss/train': 1.2276703119277954} 08/31/2021 08:21:32 - INFO - __main__ - Step 105224: {'lr': 0.00010467692880881504, 'samples': 20203008, 'steps': 105223, 'loss/train': 0.9287087917327881} 08/31/2021 08:21:33 - INFO - __main__ - Step 105225: {'lr': 0.00010467261077110523, 'samples': 20203200, 'steps': 105224, 'loss/train': 0.10639603435993195} 08/31/2021 08:21:33 - INFO - __main__ - Step 105226: {'lr': 0.00010466829279887771, 'samples': 20203392, 'steps': 105225, 'loss/train': 1.3094931840896606} 08/31/2021 08:21:34 - INFO - __main__ - Step 105227: {'lr': 0.00010466397489213441, 'samples': 20203584, 'steps': 105226, 'loss/train': 1.287667989730835} 08/31/2021 08:21:34 - INFO - __main__ - Step 105228: {'lr': 0.00010465965705087726, 'samples': 20203776, 'steps': 105227, 'loss/train': 0.41305118799209595} 08/31/2021 08:21:36 - INFO - __main__ - Step 105229: {'lr': 0.00010465533927510826, 'samples': 20203968, 'steps': 105228, 'loss/train': 0.6233494877815247} 08/31/2021 08:21:36 - INFO - __main__ - Step 105230: {'lr': 0.0001046510215648293, 'samples': 20204160, 'steps': 105229, 'loss/train': 1.4044851064682007} 08/31/2021 08:21:36 - INFO - __main__ - Step 105231: {'lr': 0.00010464670392004236, 'samples': 20204352, 'steps': 105230, 'loss/train': 0.49480152130126953} 08/31/2021 08:21:37 - INFO - __main__ - Step 105232: {'lr': 0.00010464238634074938, 'samples': 20204544, 'steps': 105231, 'loss/train': 0.8115413188934326} 08/31/2021 08:21:37 - INFO - __main__ - Step 105233: {'lr': 0.00010463806882695229, 'samples': 20204736, 'steps': 105232, 'loss/train': 1.0465881824493408} 08/31/2021 08:21:39 - INFO - __main__ - Step 105234: {'lr': 0.00010463375137865302, 'samples': 20204928, 'steps': 105233, 'loss/train': 0.14869298040866852} 08/31/2021 08:21:39 - INFO - __main__ - Step 105235: {'lr': 0.00010462943399585357, 'samples': 20205120, 'steps': 105234, 'loss/train': 0.31197792291641235} 08/31/2021 08:21:40 - INFO - __main__ - Step 105236: {'lr': 0.00010462511667855581, 'samples': 20205312, 'steps': 105235, 'loss/train': 1.1766180992126465} 08/31/2021 08:21:40 - INFO - __main__ - Step 105237: {'lr': 0.00010462079942676186, 'samples': 20205504, 'steps': 105236, 'loss/train': 1.207515835762024} 08/31/2021 08:21:40 - INFO - __main__ - Step 105238: {'lr': 0.00010461648224047343, 'samples': 20205696, 'steps': 105237, 'loss/train': 1.2791060209274292} 08/31/2021 08:21:42 - INFO - __main__ - Step 105239: {'lr': 0.00010461216511969257, 'samples': 20205888, 'steps': 105238, 'loss/train': 1.3895187377929688} 08/31/2021 08:21:42 - INFO - __main__ - Step 105240: {'lr': 0.00010460784806442123, 'samples': 20206080, 'steps': 105239, 'loss/train': 1.1651573181152344} 08/31/2021 08:21:43 - INFO - __main__ - Step 105241: {'lr': 0.00010460353107466137, 'samples': 20206272, 'steps': 105240, 'loss/train': 1.1196703910827637} 08/31/2021 08:21:43 - INFO - __main__ - Step 105242: {'lr': 0.00010459921415041487, 'samples': 20206464, 'steps': 105241, 'loss/train': 1.4396823644638062} 08/31/2021 08:21:43 - INFO - __main__ - Step 105243: {'lr': 0.00010459489729168375, 'samples': 20206656, 'steps': 105242, 'loss/train': 1.437564730644226} 08/31/2021 08:21:45 - INFO - __main__ - Step 105244: {'lr': 0.00010459058049846992, 'samples': 20206848, 'steps': 105243, 'loss/train': 1.3628218173980713} 08/31/2021 08:21:45 - INFO - __main__ - Step 105245: {'lr': 0.00010458626377077531, 'samples': 20207040, 'steps': 105244, 'loss/train': 0.8966172933578491} 08/31/2021 08:21:46 - INFO - __main__ - Step 105246: {'lr': 0.00010458194710860192, 'samples': 20207232, 'steps': 105245, 'loss/train': 1.1146475076675415} 08/31/2021 08:21:46 - INFO - __main__ - Step 105247: {'lr': 0.00010457763051195165, 'samples': 20207424, 'steps': 105246, 'loss/train': 1.4465787410736084} 08/31/2021 08:21:47 - INFO - __main__ - Step 105248: {'lr': 0.00010457331398082645, 'samples': 20207616, 'steps': 105247, 'loss/train': 0.12176769971847534} 08/31/2021 08:21:48 - INFO - __main__ - Step 105249: {'lr': 0.00010456899751522827, 'samples': 20207808, 'steps': 105248, 'loss/train': 0.9268542528152466} 08/31/2021 08:21:48 - INFO - __main__ - Step 105250: {'lr': 0.00010456468111515905, 'samples': 20208000, 'steps': 105249, 'loss/train': 1.7674829959869385} 08/31/2021 08:21:49 - INFO - __main__ - Step 105251: {'lr': 0.00010456036478062083, 'samples': 20208192, 'steps': 105250, 'loss/train': 0.4246339797973633} 08/31/2021 08:21:49 - INFO - __main__ - Step 105252: {'lr': 0.0001045560485116154, 'samples': 20208384, 'steps': 105251, 'loss/train': 0.8284586071968079} 08/31/2021 08:21:49 - INFO - __main__ - Step 105253: {'lr': 0.00010455173230814474, 'samples': 20208576, 'steps': 105252, 'loss/train': 0.9121598601341248} 08/31/2021 08:21:51 - INFO - __main__ - Step 105254: {'lr': 0.00010454741617021086, 'samples': 20208768, 'steps': 105253, 'loss/train': 1.0161652565002441} 08/31/2021 08:21:51 - INFO - __main__ - Step 105255: {'lr': 0.00010454310009781565, 'samples': 20208960, 'steps': 105254, 'loss/train': 0.4689902365207672} 08/31/2021 08:21:52 - INFO - __main__ - Step 105256: {'lr': 0.00010453878409096107, 'samples': 20209152, 'steps': 105255, 'loss/train': 1.332301378250122} 08/31/2021 08:21:52 - INFO - __main__ - Step 105257: {'lr': 0.00010453446814964906, 'samples': 20209344, 'steps': 105256, 'loss/train': 5.737178325653076} 08/31/2021 08:21:53 - INFO - __main__ - Step 105258: {'lr': 0.0001045301522738816, 'samples': 20209536, 'steps': 105257, 'loss/train': 0.32987821102142334} 08/31/2021 08:21:53 - INFO - __main__ - Step 105259: {'lr': 0.00010452583646366059, 'samples': 20209728, 'steps': 105258, 'loss/train': 1.4486172199249268} 08/31/2021 08:21:54 - INFO - __main__ - Step 105260: {'lr': 0.00010452152071898799, 'samples': 20209920, 'steps': 105259, 'loss/train': 0.9146166443824768} 08/31/2021 08:21:55 - INFO - __main__ - Step 105261: {'lr': 0.00010451720503986576, 'samples': 20210112, 'steps': 105260, 'loss/train': 0.7891067266464233} 08/31/2021 08:21:55 - INFO - __main__ - Step 105262: {'lr': 0.00010451288942629583, 'samples': 20210304, 'steps': 105261, 'loss/train': 0.9845904111862183} 08/31/2021 08:21:56 - INFO - __main__ - Step 105263: {'lr': 0.00010450857387828014, 'samples': 20210496, 'steps': 105262, 'loss/train': 1.2344975471496582} 08/31/2021 08:21:56 - INFO - __main__ - Step 105264: {'lr': 0.00010450425839582073, 'samples': 20210688, 'steps': 105263, 'loss/train': 1.3834404945373535} 08/31/2021 08:21:57 - INFO - __main__ - Step 105265: {'lr': 0.00010449994297891937, 'samples': 20210880, 'steps': 105264, 'loss/train': 0.8812759518623352} 08/31/2021 08:21:58 - INFO - __main__ - Step 105266: {'lr': 0.0001044956276275781, 'samples': 20211072, 'steps': 105265, 'loss/train': 1.269688606262207} 08/31/2021 08:21:58 - INFO - __main__ - Step 105267: {'lr': 0.00010449131234179884, 'samples': 20211264, 'steps': 105266, 'loss/train': 0.7026260495185852} 08/31/2021 08:21:59 - INFO - __main__ - Step 105268: {'lr': 0.00010448699712158357, 'samples': 20211456, 'steps': 105267, 'loss/train': 0.777451753616333} 08/31/2021 08:21:59 - INFO - __main__ - Step 105269: {'lr': 0.0001044826819669342, 'samples': 20211648, 'steps': 105268, 'loss/train': 0.9646427035331726} 08/31/2021 08:22:01 - INFO - __main__ - Step 105270: {'lr': 0.0001044783668778527, 'samples': 20211840, 'steps': 105269, 'loss/train': 1.0591439008712769} 08/31/2021 08:22:01 - INFO - __main__ - Step 105271: {'lr': 0.00010447405185434097, 'samples': 20212032, 'steps': 105270, 'loss/train': 1.167189598083496} 08/31/2021 08:22:02 - INFO - __main__ - Step 105272: {'lr': 0.00010446973689640101, 'samples': 20212224, 'steps': 105271, 'loss/train': 1.278755784034729} 08/31/2021 08:22:02 - INFO - __main__ - Step 105273: {'lr': 0.00010446542200403475, 'samples': 20212416, 'steps': 105272, 'loss/train': 0.7671155333518982} 08/31/2021 08:22:02 - INFO - __main__ - Step 105274: {'lr': 0.0001044611071772441, 'samples': 20212608, 'steps': 105273, 'loss/train': 1.2611417770385742} 08/31/2021 08:22:05 - INFO - __main__ - Step 105275: {'lr': 0.00010445679241603107, 'samples': 20212800, 'steps': 105274, 'loss/train': 0.03251421079039574} 08/31/2021 08:22:05 - INFO - __main__ - Step 105276: {'lr': 0.00010445247772039754, 'samples': 20212992, 'steps': 105275, 'loss/train': 1.4051711559295654} 08/31/2021 08:22:06 - INFO - __main__ - Step 105277: {'lr': 0.00010444816309034555, 'samples': 20213184, 'steps': 105276, 'loss/train': 1.252321481704712} 08/31/2021 08:22:06 - INFO - __main__ - Step 105278: {'lr': 0.00010444384852587691, 'samples': 20213376, 'steps': 105277, 'loss/train': 0.9001662135124207} 08/31/2021 08:22:06 - INFO - __main__ - Step 105279: {'lr': 0.0001044395340269936, 'samples': 20213568, 'steps': 105278, 'loss/train': 0.8742414712905884} 08/31/2021 08:22:07 - INFO - __main__ - Step 105280: {'lr': 0.0001044352195936976, 'samples': 20213760, 'steps': 105279, 'loss/train': 0.9571483731269836} 08/31/2021 08:22:08 - INFO - __main__ - Step 105281: {'lr': 0.00010443090522599086, 'samples': 20213952, 'steps': 105280, 'loss/train': 0.05342013016343117} 08/31/2021 08:22:09 - INFO - __main__ - Step 105282: {'lr': 0.00010442659092387527, 'samples': 20214144, 'steps': 105281, 'loss/train': 1.3877315521240234} 08/31/2021 08:22:09 - INFO - __main__ - Step 105283: {'lr': 0.00010442227668735285, 'samples': 20214336, 'steps': 105282, 'loss/train': 0.9481426477432251} 08/31/2021 08:22:09 - INFO - __main__ - Step 105284: {'lr': 0.00010441796251642549, 'samples': 20214528, 'steps': 105283, 'loss/train': 0.6332029104232788} 08/31/2021 08:22:10 - INFO - __main__ - Step 105285: {'lr': 0.00010441364841109515, 'samples': 20214720, 'steps': 105284, 'loss/train': 0.7469627857208252} 08/31/2021 08:22:11 - INFO - __main__ - Step 105286: {'lr': 0.00010440933437136376, 'samples': 20214912, 'steps': 105285, 'loss/train': 1.5476266145706177} 08/31/2021 08:22:12 - INFO - __main__ - Step 105287: {'lr': 0.00010440502039723331, 'samples': 20215104, 'steps': 105286, 'loss/train': 0.8096064329147339} 08/31/2021 08:22:12 - INFO - __main__ - Step 105288: {'lr': 0.0001044007064887057, 'samples': 20215296, 'steps': 105287, 'loss/train': 0.8875748515129089} 08/31/2021 08:22:12 - INFO - __main__ - Step 105289: {'lr': 0.00010439639264578288, 'samples': 20215488, 'steps': 105288, 'loss/train': 0.3871237337589264} 08/31/2021 08:22:13 - INFO - __main__ - Step 105290: {'lr': 0.00010439207886846677, 'samples': 20215680, 'steps': 105289, 'loss/train': 1.2554463148117065} 08/31/2021 08:22:14 - INFO - __main__ - Step 105291: {'lr': 0.00010438776515675946, 'samples': 20215872, 'steps': 105290, 'loss/train': 2.051391124725342} 08/31/2021 08:22:15 - INFO - __main__ - Step 105292: {'lr': 0.0001043834515106627, 'samples': 20216064, 'steps': 105291, 'loss/train': 1.1735893487930298} 08/31/2021 08:22:15 - INFO - __main__ - Step 105293: {'lr': 0.00010437913793017851, 'samples': 20216256, 'steps': 105292, 'loss/train': 1.4033435583114624} 08/31/2021 08:22:15 - INFO - __main__ - Step 105294: {'lr': 0.0001043748244153088, 'samples': 20216448, 'steps': 105293, 'loss/train': 1.2502374649047852} 08/31/2021 08:22:16 - INFO - __main__ - Step 105295: {'lr': 0.00010437051096605556, 'samples': 20216640, 'steps': 105294, 'loss/train': 1.4067721366882324} 08/31/2021 08:22:17 - INFO - __main__ - Step 105296: {'lr': 0.00010436619758242072, 'samples': 20216832, 'steps': 105295, 'loss/train': 1.3348369598388672} 08/31/2021 08:22:18 - INFO - __main__ - Step 105297: {'lr': 0.00010436188426440623, 'samples': 20217024, 'steps': 105296, 'loss/train': 1.0590940713882446} 08/31/2021 08:22:18 - INFO - __main__ - Step 105298: {'lr': 0.00010435757101201404, 'samples': 20217216, 'steps': 105297, 'loss/train': 0.4090961515903473} 08/31/2021 08:22:18 - INFO - __main__ - Step 105299: {'lr': 0.00010435325782524608, 'samples': 20217408, 'steps': 105298, 'loss/train': 1.1333277225494385} 08/31/2021 08:22:19 - INFO - __main__ - Step 105300: {'lr': 0.00010434894470410428, 'samples': 20217600, 'steps': 105299, 'loss/train': 1.2282953262329102} 08/31/2021 08:22:20 - INFO - __main__ - Step 105301: {'lr': 0.0001043446316485906, 'samples': 20217792, 'steps': 105300, 'loss/train': 1.1808453798294067} 08/31/2021 08:22:21 - INFO - __main__ - Step 105302: {'lr': 0.00010434031865870697, 'samples': 20217984, 'steps': 105301, 'loss/train': 0.31605860590934753} 08/31/2021 08:22:21 - INFO - __main__ - Step 105303: {'lr': 0.00010433600573445538, 'samples': 20218176, 'steps': 105302, 'loss/train': 1.1154271364212036} 08/31/2021 08:22:22 - INFO - __main__ - Step 105304: {'lr': 0.0001043316928758378, 'samples': 20218368, 'steps': 105303, 'loss/train': 0.307627409696579} 08/31/2021 08:22:22 - INFO - __main__ - Step 105305: {'lr': 0.00010432738008285602, 'samples': 20218560, 'steps': 105304, 'loss/train': 0.9112704992294312} 08/31/2021 08:22:22 - INFO - __main__ - Step 105306: {'lr': 0.00010432306735551209, 'samples': 20218752, 'steps': 105305, 'loss/train': 1.4299336671829224} 08/31/2021 08:22:24 - INFO - __main__ - Step 105307: {'lr': 0.00010431875469380792, 'samples': 20218944, 'steps': 105306, 'loss/train': 1.2659945487976074} 08/31/2021 08:22:24 - INFO - __main__ - Step 105308: {'lr': 0.00010431444209774549, 'samples': 20219136, 'steps': 105307, 'loss/train': 1.0747166872024536} 08/31/2021 08:22:25 - INFO - __main__ - Step 105309: {'lr': 0.00010431012956732668, 'samples': 20219328, 'steps': 105308, 'loss/train': 1.2062938213348389} 08/31/2021 08:22:25 - INFO - __main__ - Step 105310: {'lr': 0.00010430581710255354, 'samples': 20219520, 'steps': 105309, 'loss/train': 1.2353129386901855} 08/31/2021 08:22:25 - INFO - __main__ - Step 105311: {'lr': 0.00010430150470342793, 'samples': 20219712, 'steps': 105310, 'loss/train': 1.146299958229065} 08/31/2021 08:22:27 - INFO - __main__ - Step 105312: {'lr': 0.0001042971923699518, 'samples': 20219904, 'steps': 105311, 'loss/train': 0.5596831440925598} 08/31/2021 08:22:27 - INFO - __main__ - Step 105313: {'lr': 0.00010429288010212712, 'samples': 20220096, 'steps': 105312, 'loss/train': 0.6665584444999695} 08/31/2021 08:22:28 - INFO - __main__ - Step 105314: {'lr': 0.00010428856789995581, 'samples': 20220288, 'steps': 105313, 'loss/train': 0.8134067058563232} 08/31/2021 08:22:28 - INFO - __main__ - Step 105315: {'lr': 0.00010428425576343981, 'samples': 20220480, 'steps': 105314, 'loss/train': 1.2716890573501587} 08/31/2021 08:22:28 - INFO - __main__ - Step 105316: {'lr': 0.00010427994369258109, 'samples': 20220672, 'steps': 105315, 'loss/train': 2.2146058082580566} 08/31/2021 08:22:30 - INFO - __main__ - Step 105317: {'lr': 0.00010427563168738157, 'samples': 20220864, 'steps': 105316, 'loss/train': 0.7957946062088013} 08/31/2021 08:22:30 - INFO - __main__ - Step 105318: {'lr': 0.00010427131974784332, 'samples': 20221056, 'steps': 105317, 'loss/train': 1.5135626792907715} 08/31/2021 08:22:31 - INFO - __main__ - Step 105319: {'lr': 0.00010426700787396806, 'samples': 20221248, 'steps': 105318, 'loss/train': 1.409425139427185} 08/31/2021 08:22:31 - INFO - __main__ - Step 105320: {'lr': 0.00010426269606575783, 'samples': 20221440, 'steps': 105319, 'loss/train': 0.6731960773468018} 08/31/2021 08:22:31 - INFO - __main__ - Step 105321: {'lr': 0.00010425838432321457, 'samples': 20221632, 'steps': 105320, 'loss/train': 1.1320732831954956} 08/31/2021 08:22:33 - INFO - __main__ - Step 105322: {'lr': 0.00010425407264634026, 'samples': 20221824, 'steps': 105321, 'loss/train': 1.3252352476119995} 08/31/2021 08:22:33 - INFO - __main__ - Step 105323: {'lr': 0.0001042497610351368, 'samples': 20222016, 'steps': 105322, 'loss/train': 1.1927019357681274} 08/31/2021 08:22:34 - INFO - __main__ - Step 105324: {'lr': 0.00010424544948960616, 'samples': 20222208, 'steps': 105323, 'loss/train': 0.34861570596694946} 08/31/2021 08:22:34 - INFO - __main__ - Step 105325: {'lr': 0.00010424113800975027, 'samples': 20222400, 'steps': 105324, 'loss/train': 1.3875787258148193} 08/31/2021 08:22:34 - INFO - __main__ - Step 105326: {'lr': 0.00010423682659557107, 'samples': 20222592, 'steps': 105325, 'loss/train': 1.272530198097229} 08/31/2021 08:22:36 - INFO - __main__ - Step 105327: {'lr': 0.0001042325152470705, 'samples': 20222784, 'steps': 105326, 'loss/train': 0.6332734227180481} 08/31/2021 08:22:37 - INFO - __main__ - Step 105328: {'lr': 0.00010422820396425051, 'samples': 20222976, 'steps': 105327, 'loss/train': 0.9678958058357239} 08/31/2021 08:22:37 - INFO - __main__ - Step 105329: {'lr': 0.00010422389274711305, 'samples': 20223168, 'steps': 105328, 'loss/train': 1.8105783462524414} 08/31/2021 08:22:38 - INFO - __main__ - Step 105330: {'lr': 0.00010421958159566006, 'samples': 20223360, 'steps': 105329, 'loss/train': 1.5530064105987549} 08/31/2021 08:22:38 - INFO - __main__ - Step 105331: {'lr': 0.00010421527050989354, 'samples': 20223552, 'steps': 105330, 'loss/train': 1.3736687898635864} 08/31/2021 08:22:40 - INFO - __main__ - Step 105332: {'lr': 0.0001042109594898153, 'samples': 20223744, 'steps': 105331, 'loss/train': 0.6189119219779968} 08/31/2021 08:22:40 - INFO - __main__ - Step 105333: {'lr': 0.00010420664853542736, 'samples': 20223936, 'steps': 105332, 'loss/train': 1.3635780811309814} 08/31/2021 08:22:41 - INFO - __main__ - Step 105334: {'lr': 0.00010420233764673162, 'samples': 20224128, 'steps': 105333, 'loss/train': 0.6664382219314575} 08/31/2021 08:22:41 - INFO - __main__ - Step 105335: {'lr': 0.00010419802682373008, 'samples': 20224320, 'steps': 105334, 'loss/train': 0.10275360941886902} 08/31/2021 08:22:41 - INFO - __main__ - Step 105336: {'lr': 0.00010419371606642467, 'samples': 20224512, 'steps': 105335, 'loss/train': 0.02814379520714283} 08/31/2021 08:22:42 - INFO - __main__ - Step 105337: {'lr': 0.0001041894053748173, 'samples': 20224704, 'steps': 105336, 'loss/train': 1.05650794506073} 08/31/2021 08:22:42 - INFO - __main__ - Step 105338: {'lr': 0.00010418509474890994, 'samples': 20224896, 'steps': 105337, 'loss/train': 0.01778442971408367} 08/31/2021 08:22:44 - INFO - __main__ - Step 105339: {'lr': 0.00010418078418870455, 'samples': 20225088, 'steps': 105338, 'loss/train': 0.9406306147575378} 08/31/2021 08:22:44 - INFO - __main__ - Step 105340: {'lr': 0.00010417647369420302, 'samples': 20225280, 'steps': 105339, 'loss/train': 1.065247893333435} 08/31/2021 08:22:44 - INFO - __main__ - Step 105341: {'lr': 0.00010417216326540732, 'samples': 20225472, 'steps': 105340, 'loss/train': 0.5851069092750549} 08/31/2021 08:22:45 - INFO - __main__ - Step 105342: {'lr': 0.00010416785290231951, 'samples': 20225664, 'steps': 105341, 'loss/train': 1.1041430234909058} 08/31/2021 08:22:45 - INFO - __main__ - Step 105343: {'lr': 0.0001041635426049413, 'samples': 20225856, 'steps': 105342, 'loss/train': 1.237876534461975} 08/31/2021 08:22:47 - INFO - __main__ - Step 105344: {'lr': 0.00010415923237327476, 'samples': 20226048, 'steps': 105343, 'loss/train': 1.0358295440673828} 08/31/2021 08:22:47 - INFO - __main__ - Step 105345: {'lr': 0.00010415492220732181, 'samples': 20226240, 'steps': 105344, 'loss/train': 0.8538624048233032} 08/31/2021 08:22:48 - INFO - __main__ - Step 105346: {'lr': 0.0001041506121070844, 'samples': 20226432, 'steps': 105345, 'loss/train': 0.9701250195503235} 08/31/2021 08:22:48 - INFO - __main__ - Step 105347: {'lr': 0.00010414630207256447, 'samples': 20226624, 'steps': 105346, 'loss/train': 0.014112964272499084} 08/31/2021 08:22:48 - INFO - __main__ - Step 105348: {'lr': 0.00010414199210376399, 'samples': 20226816, 'steps': 105347, 'loss/train': 0.7772605419158936} 08/31/2021 08:22:49 - INFO - __main__ - Step 105349: {'lr': 0.00010413768220068487, 'samples': 20227008, 'steps': 105348, 'loss/train': 0.9351430535316467} 08/31/2021 08:22:50 - INFO - __main__ - Step 105350: {'lr': 0.00010413337236332907, 'samples': 20227200, 'steps': 105349, 'loss/train': 0.8370217084884644} 08/31/2021 08:22:51 - INFO - __main__ - Step 105351: {'lr': 0.0001041290625916985, 'samples': 20227392, 'steps': 105350, 'loss/train': 3.738870859146118} 08/31/2021 08:22:51 - INFO - __main__ - Step 105352: {'lr': 0.00010412475288579512, 'samples': 20227584, 'steps': 105351, 'loss/train': 1.0826410055160522} 08/31/2021 08:22:52 - INFO - __main__ - Step 105353: {'lr': 0.00010412044324562098, 'samples': 20227776, 'steps': 105352, 'loss/train': 1.5355538129806519} 08/31/2021 08:22:52 - INFO - __main__ - Step 105354: {'lr': 0.00010411613367117781, 'samples': 20227968, 'steps': 105353, 'loss/train': 0.8807198405265808} 08/31/2021 08:22:54 - INFO - __main__ - Step 105355: {'lr': 0.00010411182416246768, 'samples': 20228160, 'steps': 105354, 'loss/train': 1.1570793390274048} 08/31/2021 08:22:54 - INFO - __main__ - Step 105356: {'lr': 0.00010410751471949248, 'samples': 20228352, 'steps': 105355, 'loss/train': 0.9328386783599854} 08/31/2021 08:22:55 - INFO - __main__ - Step 105357: {'lr': 0.0001041032053422542, 'samples': 20228544, 'steps': 105356, 'loss/train': 0.1714010238647461} 08/31/2021 08:22:55 - INFO - __main__ - Step 105358: {'lr': 0.00010409889603075478, 'samples': 20228736, 'steps': 105357, 'loss/train': 0.9548125267028809} 08/31/2021 08:22:55 - INFO - __main__ - Step 105359: {'lr': 0.00010409458678499615, 'samples': 20228928, 'steps': 105358, 'loss/train': 0.5104395151138306} 08/31/2021 08:22:57 - INFO - __main__ - Step 105360: {'lr': 0.00010409027760498021, 'samples': 20229120, 'steps': 105359, 'loss/train': 1.2499511241912842} 08/31/2021 08:22:57 - INFO - __main__ - Step 105361: {'lr': 0.00010408596849070898, 'samples': 20229312, 'steps': 105360, 'loss/train': 1.5432732105255127} 08/31/2021 08:22:58 - INFO - __main__ - Step 105362: {'lr': 0.00010408165944218431, 'samples': 20229504, 'steps': 105361, 'loss/train': 1.0043578147888184} 08/31/2021 08:22:58 - INFO - __main__ - Step 105363: {'lr': 0.00010407735045940825, 'samples': 20229696, 'steps': 105362, 'loss/train': 1.009913444519043} 08/31/2021 08:22:58 - INFO - __main__ - Step 105364: {'lr': 0.00010407304154238272, 'samples': 20229888, 'steps': 105363, 'loss/train': 1.4899643659591675} 08/31/2021 08:22:59 - INFO - __main__ - Step 105365: {'lr': 0.00010406873269110959, 'samples': 20230080, 'steps': 105364, 'loss/train': 0.9478417038917542} 08/31/2021 08:23:00 - INFO - __main__ - Step 105366: {'lr': 0.00010406442390559082, 'samples': 20230272, 'steps': 105365, 'loss/train': 1.1178042888641357} 08/31/2021 08:23:01 - INFO - __main__ - Step 105367: {'lr': 0.00010406011518582834, 'samples': 20230464, 'steps': 105366, 'loss/train': 1.8900272846221924} 08/31/2021 08:23:01 - INFO - __main__ - Step 105368: {'lr': 0.00010405580653182415, 'samples': 20230656, 'steps': 105367, 'loss/train': 0.5194541215896606} 08/31/2021 08:23:01 - INFO - __main__ - Step 105369: {'lr': 0.00010405149794358015, 'samples': 20230848, 'steps': 105368, 'loss/train': 1.1917425394058228} 08/31/2021 08:23:02 - INFO - __main__ - Step 105370: {'lr': 0.00010404718942109829, 'samples': 20231040, 'steps': 105369, 'loss/train': 1.4194493293762207} 08/31/2021 08:23:04 - INFO - __main__ - Step 105371: {'lr': 0.00010404288096438052, 'samples': 20231232, 'steps': 105370, 'loss/train': 0.7879176735877991} 08/31/2021 08:23:04 - INFO - __main__ - Step 105372: {'lr': 0.00010403857257342877, 'samples': 20231424, 'steps': 105371, 'loss/train': 1.2900422811508179} 08/31/2021 08:23:05 - INFO - __main__ - Step 105373: {'lr': 0.000104034264248245, 'samples': 20231616, 'steps': 105372, 'loss/train': 0.07219859212636948} 08/31/2021 08:23:05 - INFO - __main__ - Step 105374: {'lr': 0.00010402995598883111, 'samples': 20231808, 'steps': 105373, 'loss/train': 0.9268020987510681} 08/31/2021 08:23:05 - INFO - __main__ - Step 105375: {'lr': 0.00010402564779518919, 'samples': 20232000, 'steps': 105374, 'loss/train': 1.3261218070983887} 08/31/2021 08:23:07 - INFO - __main__ - Step 105376: {'lr': 0.00010402133966732098, 'samples': 20232192, 'steps': 105375, 'loss/train': 1.329608678817749} 08/31/2021 08:23:07 - INFO - __main__ - Step 105377: {'lr': 0.00010401703160522846, 'samples': 20232384, 'steps': 105376, 'loss/train': 1.4815560579299927} 08/31/2021 08:23:08 - INFO - __main__ - Step 105378: {'lr': 0.00010401272360891364, 'samples': 20232576, 'steps': 105377, 'loss/train': 1.3601067066192627} 08/31/2021 08:23:08 - INFO - __main__ - Step 105379: {'lr': 0.00010400841567837843, 'samples': 20232768, 'steps': 105378, 'loss/train': 0.8117528557777405} 08/31/2021 08:23:08 - INFO - __main__ - Step 105380: {'lr': 0.00010400410781362477, 'samples': 20232960, 'steps': 105379, 'loss/train': 1.4750171899795532} 08/31/2021 08:23:10 - INFO - __main__ - Step 105381: {'lr': 0.00010399980001465461, 'samples': 20233152, 'steps': 105380, 'loss/train': 0.9658573269844055} 08/31/2021 08:23:10 - INFO - __main__ - Step 105382: {'lr': 0.00010399549228146987, 'samples': 20233344, 'steps': 105381, 'loss/train': 1.4409233331680298} 08/31/2021 08:23:11 - INFO - __main__ - Step 105383: {'lr': 0.00010399118461407254, 'samples': 20233536, 'steps': 105382, 'loss/train': 0.7587305307388306} 08/31/2021 08:23:11 - INFO - __main__ - Step 105384: {'lr': 0.00010398687701246451, 'samples': 20233728, 'steps': 105383, 'loss/train': 0.6619294881820679} 08/31/2021 08:23:11 - INFO - __main__ - Step 105385: {'lr': 0.00010398256947664774, 'samples': 20233920, 'steps': 105384, 'loss/train': 1.9251883029937744} 08/31/2021 08:23:13 - INFO - __main__ - Step 105386: {'lr': 0.00010397826200662427, 'samples': 20234112, 'steps': 105385, 'loss/train': 1.1935971975326538} 08/31/2021 08:23:14 - INFO - __main__ - Step 105387: {'lr': 0.00010397395460239583, 'samples': 20234304, 'steps': 105386, 'loss/train': 0.6086632013320923} 08/31/2021 08:23:14 - INFO - __main__ - Step 105388: {'lr': 0.00010396964726396452, 'samples': 20234496, 'steps': 105387, 'loss/train': 0.3335244059562683} 08/31/2021 08:23:14 - INFO - __main__ - Step 105389: {'lr': 0.00010396533999133218, 'samples': 20234688, 'steps': 105388, 'loss/train': 0.8790905475616455} 08/31/2021 08:23:15 - INFO - __main__ - Step 105390: {'lr': 0.00010396103278450084, 'samples': 20234880, 'steps': 105389, 'loss/train': 0.9016445875167847} 08/31/2021 08:23:16 - INFO - __main__ - Step 105391: {'lr': 0.00010395672564347239, 'samples': 20235072, 'steps': 105390, 'loss/train': 1.216385006904602} 08/31/2021 08:23:17 - INFO - __main__ - Step 105392: {'lr': 0.00010395241856824877, 'samples': 20235264, 'steps': 105391, 'loss/train': 0.962901771068573} 08/31/2021 08:23:17 - INFO - __main__ - Step 105393: {'lr': 0.00010394811155883197, 'samples': 20235456, 'steps': 105392, 'loss/train': 1.2115111351013184} 08/31/2021 08:23:17 - INFO - __main__ - Step 105394: {'lr': 0.00010394380461522387, 'samples': 20235648, 'steps': 105393, 'loss/train': 1.4844475984573364} 08/31/2021 08:23:18 - INFO - __main__ - Step 105395: {'lr': 0.00010393949773742648, 'samples': 20235840, 'steps': 105394, 'loss/train': 1.325050950050354} 08/31/2021 08:23:19 - INFO - __main__ - Step 105396: {'lr': 0.00010393519092544165, 'samples': 20236032, 'steps': 105395, 'loss/train': 1.7191097736358643} 08/31/2021 08:23:20 - INFO - __main__ - Step 105397: {'lr': 0.00010393088417927137, 'samples': 20236224, 'steps': 105396, 'loss/train': 1.057712197303772} 08/31/2021 08:23:20 - INFO - __main__ - Step 105398: {'lr': 0.00010392657749891771, 'samples': 20236416, 'steps': 105397, 'loss/train': 1.3198649883270264} 08/31/2021 08:23:21 - INFO - __main__ - Step 105399: {'lr': 0.00010392227088438236, 'samples': 20236608, 'steps': 105398, 'loss/train': 1.6737525463104248} 08/31/2021 08:23:21 - INFO - __main__ - Step 105400: {'lr': 0.00010391796433566739, 'samples': 20236800, 'steps': 105399, 'loss/train': 1.2645106315612793} 08/31/2021 08:23:22 - INFO - __main__ - Step 105401: {'lr': 0.00010391365785277473, 'samples': 20236992, 'steps': 105400, 'loss/train': 1.0635541677474976} 08/31/2021 08:23:23 - INFO - __main__ - Step 105402: {'lr': 0.00010390935143570631, 'samples': 20237184, 'steps': 105401, 'loss/train': 1.388014793395996} 08/31/2021 08:23:23 - INFO - __main__ - Step 105403: {'lr': 0.0001039050450844641, 'samples': 20237376, 'steps': 105402, 'loss/train': 0.5384480357170105} 08/31/2021 08:23:23 - INFO - __main__ - Step 105404: {'lr': 0.00010390073879905002, 'samples': 20237568, 'steps': 105403, 'loss/train': 1.0287017822265625} 08/31/2021 08:23:24 - INFO - __main__ - Step 105405: {'lr': 0.00010389643257946602, 'samples': 20237760, 'steps': 105404, 'loss/train': 1.3486233949661255} 08/31/2021 08:23:26 - INFO - __main__ - Step 105406: {'lr': 0.000103892126425714, 'samples': 20237952, 'steps': 105405, 'loss/train': 1.1572858095169067} 08/31/2021 08:23:26 - INFO - __main__ - Step 105407: {'lr': 0.00010388782033779595, 'samples': 20238144, 'steps': 105406, 'loss/train': 1.191105842590332} 08/31/2021 08:23:26 - INFO - __main__ - Step 105408: {'lr': 0.0001038835143157138, 'samples': 20238336, 'steps': 105407, 'loss/train': 0.8015508055686951} 08/31/2021 08:23:27 - INFO - __main__ - Step 105409: {'lr': 0.00010387920835946949, 'samples': 20238528, 'steps': 105408, 'loss/train': 1.390981912612915} 08/31/2021 08:23:27 - INFO - __main__ - Step 105410: {'lr': 0.00010387490246906495, 'samples': 20238720, 'steps': 105409, 'loss/train': 0.7515566349029541} 08/31/2021 08:23:27 - INFO - __main__ - Step 105411: {'lr': 0.00010387059664450211, 'samples': 20238912, 'steps': 105410, 'loss/train': 1.0044705867767334} 08/31/2021 08:23:29 - INFO - __main__ - Step 105412: {'lr': 0.00010386629088578303, 'samples': 20239104, 'steps': 105411, 'loss/train': 0.20446082949638367} 08/31/2021 08:23:30 - INFO - __main__ - Step 105413: {'lr': 0.00010386198519290943, 'samples': 20239296, 'steps': 105412, 'loss/train': 1.2678329944610596} 08/31/2021 08:23:30 - INFO - __main__ - Step 105414: {'lr': 0.00010385767956588338, 'samples': 20239488, 'steps': 105413, 'loss/train': 0.11043532937765121} 08/31/2021 08:23:31 - INFO - __main__ - Step 105415: {'lr': 0.00010385337400470681, 'samples': 20239680, 'steps': 105414, 'loss/train': 1.3270403146743774} 08/31/2021 08:23:31 - INFO - __main__ - Step 105416: {'lr': 0.00010384906850938167, 'samples': 20239872, 'steps': 105415, 'loss/train': 0.8873847723007202} 08/31/2021 08:23:33 - INFO - __main__ - Step 105417: {'lr': 0.00010384476307990987, 'samples': 20240064, 'steps': 105416, 'loss/train': 1.4199939966201782} 08/31/2021 08:23:33 - INFO - __main__ - Step 105418: {'lr': 0.00010384045771629333, 'samples': 20240256, 'steps': 105417, 'loss/train': 1.14844810962677} 08/31/2021 08:23:33 - INFO - __main__ - Step 105419: {'lr': 0.00010383615241853405, 'samples': 20240448, 'steps': 105418, 'loss/train': 1.2174588441848755} 08/31/2021 08:23:34 - INFO - __main__ - Step 105420: {'lr': 0.00010383184718663397, 'samples': 20240640, 'steps': 105419, 'loss/train': 1.3271639347076416} 08/31/2021 08:23:34 - INFO - __main__ - Step 105421: {'lr': 0.00010382754202059497, 'samples': 20240832, 'steps': 105420, 'loss/train': 1.3336299657821655} 08/31/2021 08:23:36 - INFO - __main__ - Step 105422: {'lr': 0.00010382323692041903, 'samples': 20241024, 'steps': 105421, 'loss/train': 1.8545912504196167} 08/31/2021 08:23:36 - INFO - __main__ - Step 105423: {'lr': 0.0001038189318861081, 'samples': 20241216, 'steps': 105422, 'loss/train': 0.8936260342597961} 08/31/2021 08:23:36 - INFO - __main__ - Step 105424: {'lr': 0.00010381462691766411, 'samples': 20241408, 'steps': 105423, 'loss/train': 1.3408620357513428} 08/31/2021 08:23:37 - INFO - __main__ - Step 105425: {'lr': 0.00010381032201508906, 'samples': 20241600, 'steps': 105424, 'loss/train': 1.3686509132385254} 08/31/2021 08:23:37 - INFO - __main__ - Step 105426: {'lr': 0.00010380601717838472, 'samples': 20241792, 'steps': 105425, 'loss/train': 1.297418475151062} 08/31/2021 08:23:39 - INFO - __main__ - Step 105427: {'lr': 0.00010380171240755317, 'samples': 20241984, 'steps': 105426, 'loss/train': 0.7488637566566467} 08/31/2021 08:23:39 - INFO - __main__ - Step 105428: {'lr': 0.0001037974077025963, 'samples': 20242176, 'steps': 105427, 'loss/train': 1.1762160062789917} 08/31/2021 08:23:40 - INFO - __main__ - Step 105429: {'lr': 0.00010379310306351606, 'samples': 20242368, 'steps': 105428, 'loss/train': 1.3328648805618286} 08/31/2021 08:23:40 - INFO - __main__ - Step 105430: {'lr': 0.00010378879849031439, 'samples': 20242560, 'steps': 105429, 'loss/train': 0.9695454239845276} 08/31/2021 08:23:40 - INFO - __main__ - Step 105431: {'lr': 0.00010378449398299322, 'samples': 20242752, 'steps': 105430, 'loss/train': 0.38876211643218994} 08/31/2021 08:23:42 - INFO - __main__ - Step 105432: {'lr': 0.00010378018954155452, 'samples': 20242944, 'steps': 105431, 'loss/train': 1.2049940824508667} 08/31/2021 08:23:43 - INFO - __main__ - Step 105433: {'lr': 0.0001037758851660002, 'samples': 20243136, 'steps': 105432, 'loss/train': 1.2653642892837524} 08/31/2021 08:23:43 - INFO - __main__ - Step 105434: {'lr': 0.00010377158085633221, 'samples': 20243328, 'steps': 105433, 'loss/train': 0.8118320107460022} 08/31/2021 08:23:43 - INFO - __main__ - Step 105435: {'lr': 0.00010376727661255247, 'samples': 20243520, 'steps': 105434, 'loss/train': 0.8109714984893799} 08/31/2021 08:23:44 - INFO - __main__ - Step 105436: {'lr': 0.00010376297243466299, 'samples': 20243712, 'steps': 105435, 'loss/train': 1.3340599536895752} 08/31/2021 08:23:44 - INFO - __main__ - Step 105437: {'lr': 0.00010375866832266562, 'samples': 20243904, 'steps': 105436, 'loss/train': 0.13952849805355072} 08/31/2021 08:23:45 - INFO - __main__ - Step 105438: {'lr': 0.00010375436427656235, 'samples': 20244096, 'steps': 105437, 'loss/train': 1.7653017044067383} 08/31/2021 08:23:46 - INFO - __main__ - Step 105439: {'lr': 0.00010375006029635518, 'samples': 20244288, 'steps': 105438, 'loss/train': 0.9003090858459473} 08/31/2021 08:23:46 - INFO - __main__ - Step 105440: {'lr': 0.0001037457563820459, 'samples': 20244480, 'steps': 105439, 'loss/train': 1.2723987102508545} 08/31/2021 08:23:47 - INFO - __main__ - Step 105441: {'lr': 0.00010374145253363651, 'samples': 20244672, 'steps': 105440, 'loss/train': 0.910072386264801} 08/31/2021 08:23:47 - INFO - __main__ - Step 105442: {'lr': 0.00010373714875112897, 'samples': 20244864, 'steps': 105441, 'loss/train': 0.858017086982727} 08/31/2021 08:23:49 - INFO - __main__ - Step 105443: {'lr': 0.00010373284503452524, 'samples': 20245056, 'steps': 105442, 'loss/train': 0.9978110790252686} 08/31/2021 08:23:49 - INFO - __main__ - Step 105444: {'lr': 0.00010372854138382721, 'samples': 20245248, 'steps': 105443, 'loss/train': 2.7924211025238037} 08/31/2021 08:23:50 - INFO - __main__ - Step 105445: {'lr': 0.00010372423779903683, 'samples': 20245440, 'steps': 105444, 'loss/train': 0.8516626358032227} 08/31/2021 08:23:50 - INFO - __main__ - Step 105446: {'lr': 0.00010371993428015608, 'samples': 20245632, 'steps': 105445, 'loss/train': 0.47417396306991577} 08/31/2021 08:23:50 - INFO - __main__ - Step 105447: {'lr': 0.00010371563082718685, 'samples': 20245824, 'steps': 105446, 'loss/train': 0.7149452567100525} 08/31/2021 08:23:52 - INFO - __main__ - Step 105448: {'lr': 0.00010371132744013112, 'samples': 20246016, 'steps': 105447, 'loss/train': 1.743778944015503} 08/31/2021 08:23:52 - INFO - __main__ - Step 105449: {'lr': 0.0001037070241189908, 'samples': 20246208, 'steps': 105448, 'loss/train': 1.2623788118362427} 08/31/2021 08:23:53 - INFO - __main__ - Step 105450: {'lr': 0.00010370272086376784, 'samples': 20246400, 'steps': 105449, 'loss/train': 1.1438802480697632} 08/31/2021 08:23:53 - INFO - __main__ - Step 105451: {'lr': 0.00010369841767446414, 'samples': 20246592, 'steps': 105450, 'loss/train': 1.3961420059204102} 08/31/2021 08:23:53 - INFO - __main__ - Step 105452: {'lr': 0.0001036941145510818, 'samples': 20246784, 'steps': 105451, 'loss/train': 0.6873788237571716} 08/31/2021 08:23:54 - INFO - __main__ - Step 105453: {'lr': 0.00010368981149362256, 'samples': 20246976, 'steps': 105452, 'loss/train': 1.3036624193191528} 08/31/2021 08:23:55 - INFO - __main__ - Step 105454: {'lr': 0.00010368550850208841, 'samples': 20247168, 'steps': 105453, 'loss/train': 1.4992423057556152} 08/31/2021 08:23:56 - INFO - __main__ - Step 105455: {'lr': 0.0001036812055764813, 'samples': 20247360, 'steps': 105454, 'loss/train': 0.6945679187774658} 08/31/2021 08:23:56 - INFO - __main__ - Step 105456: {'lr': 0.00010367690271680319, 'samples': 20247552, 'steps': 105455, 'loss/train': 1.3470182418823242} 08/31/2021 08:23:56 - INFO - __main__ - Step 105457: {'lr': 0.00010367259992305602, 'samples': 20247744, 'steps': 105456, 'loss/train': 1.8517450094223022} 08/31/2021 08:23:57 - INFO - __main__ - Step 105458: {'lr': 0.00010366829719524173, 'samples': 20247936, 'steps': 105457, 'loss/train': 0.8485214710235596} 08/31/2021 08:23:58 - INFO - __main__ - Step 105459: {'lr': 0.00010366399453336223, 'samples': 20248128, 'steps': 105458, 'loss/train': 0.8486917018890381} 08/31/2021 08:23:59 - INFO - __main__ - Step 105460: {'lr': 0.00010365969193741948, 'samples': 20248320, 'steps': 105459, 'loss/train': 1.3333030939102173} 08/31/2021 08:23:59 - INFO - __main__ - Step 105461: {'lr': 0.0001036553894074154, 'samples': 20248512, 'steps': 105460, 'loss/train': 1.6383509635925293} 08/31/2021 08:23:59 - INFO - __main__ - Step 105462: {'lr': 0.00010365108694335196, 'samples': 20248704, 'steps': 105461, 'loss/train': 0.9701530337333679} 08/31/2021 08:24:00 - INFO - __main__ - Step 105463: {'lr': 0.00010364678454523107, 'samples': 20248896, 'steps': 105462, 'loss/train': 1.390127182006836} 08/31/2021 08:24:02 - INFO - __main__ - Step 105464: {'lr': 0.00010364248221305469, 'samples': 20249088, 'steps': 105463, 'loss/train': 1.2952468395233154} 08/31/2021 08:24:02 - INFO - __main__ - Step 105465: {'lr': 0.00010363817994682476, 'samples': 20249280, 'steps': 105464, 'loss/train': 1.044443130493164} 08/31/2021 08:24:02 - INFO - __main__ - Step 105466: {'lr': 0.00010363387774654326, 'samples': 20249472, 'steps': 105465, 'loss/train': 0.4441086947917938} 08/31/2021 08:24:03 - INFO - __main__ - Step 105467: {'lr': 0.00010362957561221204, 'samples': 20249664, 'steps': 105466, 'loss/train': 0.9686768651008606} 08/31/2021 08:24:03 - INFO - __main__ - Step 105468: {'lr': 0.00010362527354383302, 'samples': 20249856, 'steps': 105467, 'loss/train': 0.631248950958252} 08/31/2021 08:24:05 - INFO - __main__ - Step 105469: {'lr': 0.00010362097154140824, 'samples': 20250048, 'steps': 105468, 'loss/train': 1.2169225215911865} 08/31/2021 08:24:06 - INFO - __main__ - Step 105470: {'lr': 0.00010361666960493956, 'samples': 20250240, 'steps': 105469, 'loss/train': 1.1359539031982422} 08/31/2021 08:24:06 - INFO - __main__ - Step 105471: {'lr': 0.00010361236773442895, 'samples': 20250432, 'steps': 105470, 'loss/train': 0.9962088465690613} 08/31/2021 08:24:06 - INFO - __main__ - Step 105472: {'lr': 0.00010360806592987837, 'samples': 20250624, 'steps': 105471, 'loss/train': 0.064696304500103} 08/31/2021 08:24:07 - INFO - __main__ - Step 105473: {'lr': 0.00010360376419128972, 'samples': 20250816, 'steps': 105472, 'loss/train': 1.3377569913864136} 08/31/2021 08:24:08 - INFO - __main__ - Step 105474: {'lr': 0.00010359946251866495, 'samples': 20251008, 'steps': 105473, 'loss/train': 1.047925591468811} 08/31/2021 08:24:09 - INFO - __main__ - Step 105475: {'lr': 0.00010359516091200602, 'samples': 20251200, 'steps': 105474, 'loss/train': 0.7947340607643127} 08/31/2021 08:24:09 - INFO - __main__ - Step 105476: {'lr': 0.00010359085937131485, 'samples': 20251392, 'steps': 105475, 'loss/train': 0.6654545664787292} 08/31/2021 08:24:09 - INFO - __main__ - Step 105477: {'lr': 0.00010358655789659335, 'samples': 20251584, 'steps': 105476, 'loss/train': 1.1981343030929565} 08/31/2021 08:24:10 - INFO - __main__ - Step 105478: {'lr': 0.00010358225648784354, 'samples': 20251776, 'steps': 105477, 'loss/train': 0.11424863338470459} 08/31/2021 08:24:12 - INFO - __main__ - Step 105479: {'lr': 0.00010357795514506734, 'samples': 20251968, 'steps': 105478, 'loss/train': 0.5021644830703735} 08/31/2021 08:24:12 - INFO - __main__ - Step 105480: {'lr': 0.00010357365386826658, 'samples': 20252160, 'steps': 105479, 'loss/train': 2.234579563140869} 08/31/2021 08:24:12 - INFO - __main__ - Step 105481: {'lr': 0.0001035693526574433, 'samples': 20252352, 'steps': 105480, 'loss/train': 1.6026195287704468} 08/31/2021 08:24:13 - INFO - __main__ - Step 105482: {'lr': 0.0001035650515125994, 'samples': 20252544, 'steps': 105481, 'loss/train': 0.42323556542396545} 08/31/2021 08:24:13 - INFO - __main__ - Step 105483: {'lr': 0.0001035607504337368, 'samples': 20252736, 'steps': 105482, 'loss/train': 1.053091287612915} 08/31/2021 08:24:14 - INFO - __main__ - Step 105484: {'lr': 0.00010355644942085751, 'samples': 20252928, 'steps': 105483, 'loss/train': 1.1412593126296997} 08/31/2021 08:24:14 - INFO - __main__ - Step 105485: {'lr': 0.00010355214847396338, 'samples': 20253120, 'steps': 105484, 'loss/train': 0.03177674859762192} 08/31/2021 08:24:15 - INFO - __main__ - Step 105486: {'lr': 0.00010354784759305644, 'samples': 20253312, 'steps': 105485, 'loss/train': 0.057273585349321365} 08/31/2021 08:24:16 - INFO - __main__ - Step 105487: {'lr': 0.00010354354677813855, 'samples': 20253504, 'steps': 105486, 'loss/train': 0.8579213619232178} 08/31/2021 08:24:16 - INFO - __main__ - Step 105488: {'lr': 0.00010353924602921166, 'samples': 20253696, 'steps': 105487, 'loss/train': 0.44829174876213074} 08/31/2021 08:24:17 - INFO - __main__ - Step 105489: {'lr': 0.00010353494534627774, 'samples': 20253888, 'steps': 105488, 'loss/train': 1.3819928169250488} 08/31/2021 08:24:17 - INFO - __main__ - Step 105490: {'lr': 0.00010353064472933873, 'samples': 20254080, 'steps': 105489, 'loss/train': 1.4907039403915405} 08/31/2021 08:24:19 - INFO - __main__ - Step 105491: {'lr': 0.00010352634417839654, 'samples': 20254272, 'steps': 105490, 'loss/train': 1.0957483053207397} 08/31/2021 08:24:20 - INFO - __main__ - Step 105492: {'lr': 0.00010352204369345314, 'samples': 20254464, 'steps': 105491, 'loss/train': 1.2524681091308594} 08/31/2021 08:24:20 - INFO - __main__ - Step 105493: {'lr': 0.0001035177432745105, 'samples': 20254656, 'steps': 105492, 'loss/train': 0.7247156500816345} 08/31/2021 08:24:21 - INFO - __main__ - Step 105494: {'lr': 0.00010351344292157044, 'samples': 20254848, 'steps': 105493, 'loss/train': 0.8144748210906982} 08/31/2021 08:24:21 - INFO - __main__ - Step 105495: {'lr': 0.00010350914263463495, 'samples': 20255040, 'steps': 105494, 'loss/train': 0.29615068435668945} 08/31/2021 08:24:21 - INFO - __main__ - Step 105496: {'lr': 0.00010350484241370598, 'samples': 20255232, 'steps': 105495, 'loss/train': 0.2610336244106293} 08/31/2021 08:24:23 - INFO - __main__ - Step 105497: {'lr': 0.00010350054225878546, 'samples': 20255424, 'steps': 105496, 'loss/train': 0.27375081181526184} 08/31/2021 08:24:24 - INFO - __main__ - Step 105498: {'lr': 0.00010349624216987535, 'samples': 20255616, 'steps': 105497, 'loss/train': 0.6711174249649048} 08/31/2021 08:24:24 - INFO - __main__ - Step 105499: {'lr': 0.00010349194214697757, 'samples': 20255808, 'steps': 105498, 'loss/train': 1.354931116104126} 08/31/2021 08:24:25 - INFO - __main__ - Step 105500: {'lr': 0.00010348764219009408, 'samples': 20256000, 'steps': 105499, 'loss/train': 0.994879424571991} 08/31/2021 08:24:25 - INFO - __main__ - Step 105501: {'lr': 0.00010348334229922676, 'samples': 20256192, 'steps': 105500, 'loss/train': 0.33709678053855896} 08/31/2021 08:24:27 - INFO - __main__ - Step 105502: {'lr': 0.00010347904247437762, 'samples': 20256384, 'steps': 105501, 'loss/train': 1.2798352241516113} 08/31/2021 08:24:27 - INFO - __main__ - Step 105503: {'lr': 0.00010347474271554855, 'samples': 20256576, 'steps': 105502, 'loss/train': 0.624228298664093} 08/31/2021 08:24:27 - INFO - __main__ - Step 105504: {'lr': 0.00010347044302274147, 'samples': 20256768, 'steps': 105503, 'loss/train': 0.03041796386241913} 08/31/2021 08:24:28 - INFO - __main__ - Step 105505: {'lr': 0.00010346614339595839, 'samples': 20256960, 'steps': 105504, 'loss/train': 1.0586055517196655} 08/31/2021 08:24:28 - INFO - __main__ - Step 105506: {'lr': 0.00010346184383520126, 'samples': 20257152, 'steps': 105505, 'loss/train': 1.1066280603408813} 08/31/2021 08:24:29 - INFO - __main__ - Step 105507: {'lr': 0.00010345754434047189, 'samples': 20257344, 'steps': 105506, 'loss/train': 1.0961241722106934} 08/31/2021 08:24:30 - INFO - __main__ - Step 105508: {'lr': 0.0001034532449117723, 'samples': 20257536, 'steps': 105507, 'loss/train': 1.125349760055542} 08/31/2021 08:24:31 - INFO - __main__ - Step 105509: {'lr': 0.00010344894554910439, 'samples': 20257728, 'steps': 105508, 'loss/train': 1.4224060773849487} 08/31/2021 08:24:31 - INFO - __main__ - Step 105510: {'lr': 0.00010344464625247014, 'samples': 20257920, 'steps': 105509, 'loss/train': 1.0881906747817993} 08/31/2021 08:24:31 - INFO - __main__ - Step 105511: {'lr': 0.00010344034702187147, 'samples': 20258112, 'steps': 105510, 'loss/train': 0.5611541867256165} 08/31/2021 08:24:32 - INFO - __main__ - Step 105512: {'lr': 0.00010343604785731031, 'samples': 20258304, 'steps': 105511, 'loss/train': 0.04413183033466339} 08/31/2021 08:24:33 - INFO - __main__ - Step 105513: {'lr': 0.0001034317487587886, 'samples': 20258496, 'steps': 105512, 'loss/train': 1.2229321002960205} 08/31/2021 08:24:34 - INFO - __main__ - Step 105514: {'lr': 0.00010342744972630833, 'samples': 20258688, 'steps': 105513, 'loss/train': 0.813060998916626} 08/31/2021 08:24:34 - INFO - __main__ - Step 105515: {'lr': 0.00010342315075987133, 'samples': 20258880, 'steps': 105514, 'loss/train': 1.0177830457687378} 08/31/2021 08:24:34 - INFO - __main__ - Step 105516: {'lr': 0.00010341885185947964, 'samples': 20259072, 'steps': 105515, 'loss/train': 1.2367472648620605} 08/31/2021 08:24:35 - INFO - __main__ - Step 105517: {'lr': 0.00010341455302513511, 'samples': 20259264, 'steps': 105516, 'loss/train': 1.4078785181045532} 08/31/2021 08:24:36 - INFO - __main__ - Step 105518: {'lr': 0.00010341025425683976, 'samples': 20259456, 'steps': 105517, 'loss/train': 1.072892665863037} 08/31/2021 08:24:37 - INFO - __main__ - Step 105519: {'lr': 0.00010340595555459556, 'samples': 20259648, 'steps': 105518, 'loss/train': 1.272162914276123} 08/31/2021 08:24:37 - INFO - __main__ - Step 105520: {'lr': 0.00010340165691840428, 'samples': 20259840, 'steps': 105519, 'loss/train': 1.3801147937774658} 08/31/2021 08:24:38 - INFO - __main__ - Step 105521: {'lr': 0.00010339735834826797, 'samples': 20260032, 'steps': 105520, 'loss/train': 1.127531886100769} 08/31/2021 08:24:38 - INFO - __main__ - Step 105522: {'lr': 0.00010339305984418854, 'samples': 20260224, 'steps': 105521, 'loss/train': 1.5380784273147583} 08/31/2021 08:24:39 - INFO - __main__ - Step 105523: {'lr': 0.0001033887614061679, 'samples': 20260416, 'steps': 105522, 'loss/train': 0.07562309503555298} 08/31/2021 08:24:40 - INFO - __main__ - Step 105524: {'lr': 0.00010338446303420806, 'samples': 20260608, 'steps': 105523, 'loss/train': 1.0003492832183838} 08/31/2021 08:24:40 - INFO - __main__ - Step 105525: {'lr': 0.00010338016472831091, 'samples': 20260800, 'steps': 105524, 'loss/train': 0.593250036239624} 08/31/2021 08:24:41 - INFO - __main__ - Step 105526: {'lr': 0.00010337586648847841, 'samples': 20260992, 'steps': 105525, 'loss/train': 1.03286612033844} 08/31/2021 08:24:41 - INFO - __main__ - Step 105527: {'lr': 0.00010337156831471245, 'samples': 20261184, 'steps': 105526, 'loss/train': 1.3065718412399292} 08/31/2021 08:24:43 - INFO - __main__ - Step 105528: {'lr': 0.00010336727020701504, 'samples': 20261376, 'steps': 105527, 'loss/train': 1.1828532218933105} 08/31/2021 08:24:43 - INFO - __main__ - Step 105529: {'lr': 0.00010336297216538803, 'samples': 20261568, 'steps': 105528, 'loss/train': 1.1622304916381836} 08/31/2021 08:24:43 - INFO - __main__ - Step 105530: {'lr': 0.00010335867418983345, 'samples': 20261760, 'steps': 105529, 'loss/train': 0.8118917346000671} 08/31/2021 08:24:44 - INFO - __main__ - Step 105531: {'lr': 0.00010335437628035314, 'samples': 20261952, 'steps': 105530, 'loss/train': 1.4322091341018677} 08/31/2021 08:24:44 - INFO - __main__ - Step 105532: {'lr': 0.0001033500784369491, 'samples': 20262144, 'steps': 105531, 'loss/train': 0.028315268456935883} 08/31/2021 08:24:46 - INFO - __main__ - Step 105533: {'lr': 0.00010334578065962335, 'samples': 20262336, 'steps': 105532, 'loss/train': 1.5325103998184204} 08/31/2021 08:24:47 - INFO - __main__ - Step 105534: {'lr': 0.00010334148294837764, 'samples': 20262528, 'steps': 105533, 'loss/train': 0.8454746603965759} 08/31/2021 08:24:47 - INFO - __main__ - Step 105535: {'lr': 0.000103337185303214, 'samples': 20262720, 'steps': 105534, 'loss/train': 1.816338300704956} 08/31/2021 08:24:48 - INFO - __main__ - Step 105536: {'lr': 0.00010333288772413435, 'samples': 20262912, 'steps': 105535, 'loss/train': 1.551828145980835} 08/31/2021 08:24:48 - INFO - __main__ - Step 105537: {'lr': 0.00010332859021114063, 'samples': 20263104, 'steps': 105536, 'loss/train': 1.6448931694030762} 08/31/2021 08:24:48 - INFO - __main__ - Step 105538: {'lr': 0.0001033242927642348, 'samples': 20263296, 'steps': 105537, 'loss/train': 0.7351908087730408} 08/31/2021 08:24:49 - INFO - __main__ - Step 105539: {'lr': 0.00010331999538341877, 'samples': 20263488, 'steps': 105538, 'loss/train': 1.4371929168701172} 08/31/2021 08:24:50 - INFO - __main__ - Step 105540: {'lr': 0.0001033156980686945, 'samples': 20263680, 'steps': 105539, 'loss/train': 1.1796084642410278} 08/31/2021 08:24:51 - INFO - __main__ - Step 105541: {'lr': 0.00010331140082006391, 'samples': 20263872, 'steps': 105540, 'loss/train': 1.1620548963546753} 08/31/2021 08:24:51 - INFO - __main__ - Step 105542: {'lr': 0.00010330710363752893, 'samples': 20264064, 'steps': 105541, 'loss/train': 1.8553837537765503} 08/31/2021 08:24:51 - INFO - __main__ - Step 105543: {'lr': 0.0001033028065210915, 'samples': 20264256, 'steps': 105542, 'loss/train': 0.9820476174354553} 08/31/2021 08:24:52 - INFO - __main__ - Step 105544: {'lr': 0.00010329850947075359, 'samples': 20264448, 'steps': 105543, 'loss/train': 1.4752144813537598} 08/31/2021 08:24:53 - INFO - __main__ - Step 105545: {'lr': 0.00010329421248651707, 'samples': 20264640, 'steps': 105544, 'loss/train': 0.8937035202980042} 08/31/2021 08:24:54 - INFO - __main__ - Step 105546: {'lr': 0.00010328991556838401, 'samples': 20264832, 'steps': 105545, 'loss/train': 0.6761635541915894} 08/31/2021 08:24:54 - INFO - __main__ - Step 105547: {'lr': 0.0001032856187163562, 'samples': 20265024, 'steps': 105546, 'loss/train': 0.6191251277923584} 08/31/2021 08:24:54 - INFO - __main__ - Step 105548: {'lr': 0.0001032813219304356, 'samples': 20265216, 'steps': 105547, 'loss/train': 1.313103199005127} 08/31/2021 08:24:55 - INFO - __main__ - Step 105549: {'lr': 0.00010327702521062415, 'samples': 20265408, 'steps': 105548, 'loss/train': 1.1468636989593506} 08/31/2021 08:24:57 - INFO - __main__ - Step 105550: {'lr': 0.00010327272855692385, 'samples': 20265600, 'steps': 105549, 'loss/train': 1.0647144317626953} 08/31/2021 08:24:57 - INFO - __main__ - Step 105551: {'lr': 0.00010326843196933658, 'samples': 20265792, 'steps': 105550, 'loss/train': 1.1835016012191772} 08/31/2021 08:24:58 - INFO - __main__ - Step 105552: {'lr': 0.00010326413544786429, 'samples': 20265984, 'steps': 105551, 'loss/train': 1.1310874223709106} 08/31/2021 08:24:58 - INFO - __main__ - Step 105553: {'lr': 0.0001032598389925089, 'samples': 20266176, 'steps': 105552, 'loss/train': 0.7755479216575623} 08/31/2021 08:24:58 - INFO - __main__ - Step 105554: {'lr': 0.00010325554260327239, 'samples': 20266368, 'steps': 105553, 'loss/train': 1.1962592601776123} 08/31/2021 08:25:00 - INFO - __main__ - Step 105555: {'lr': 0.00010325124628015665, 'samples': 20266560, 'steps': 105554, 'loss/train': 1.2273423671722412} 08/31/2021 08:25:01 - INFO - __main__ - Step 105556: {'lr': 0.00010324695002316362, 'samples': 20266752, 'steps': 105555, 'loss/train': 0.2836887240409851} 08/31/2021 08:25:01 - INFO - __main__ - Step 105557: {'lr': 0.00010324265383229526, 'samples': 20266944, 'steps': 105556, 'loss/train': 1.6274477243423462} 08/31/2021 08:25:01 - INFO - __main__ - Step 105558: {'lr': 0.0001032383577075535, 'samples': 20267136, 'steps': 105557, 'loss/train': 0.19427752494812012} 08/31/2021 08:25:02 - INFO - __main__ - Step 105559: {'lr': 0.00010323406164894027, 'samples': 20267328, 'steps': 105558, 'loss/train': 1.2206965684890747} 08/31/2021 08:25:02 - INFO - __main__ - Step 105560: {'lr': 0.00010322976565645761, 'samples': 20267520, 'steps': 105559, 'loss/train': 1.2130402326583862} 08/31/2021 08:25:04 - INFO - __main__ - Step 105561: {'lr': 0.00010322546973010724, 'samples': 20267712, 'steps': 105560, 'loss/train': 1.21611487865448} 08/31/2021 08:25:04 - INFO - __main__ - Step 105562: {'lr': 0.00010322117386989122, 'samples': 20267904, 'steps': 105561, 'loss/train': 0.24035383760929108} 08/31/2021 08:25:04 - INFO - __main__ - Step 105563: {'lr': 0.00010321687807581148, 'samples': 20268096, 'steps': 105562, 'loss/train': 0.9241979718208313} 08/31/2021 08:25:05 - INFO - __main__ - Step 105564: {'lr': 0.00010321258234786996, 'samples': 20268288, 'steps': 105563, 'loss/train': 1.1481661796569824} 08/31/2021 08:25:05 - INFO - __main__ - Step 105565: {'lr': 0.00010320828668606855, 'samples': 20268480, 'steps': 105564, 'loss/train': 1.192222237586975} 08/31/2021 08:25:06 - INFO - __main__ - Step 105566: {'lr': 0.00010320399109040927, 'samples': 20268672, 'steps': 105565, 'loss/train': 1.2069846391677856} 08/31/2021 08:25:07 - INFO - __main__ - Step 105567: {'lr': 0.00010319969556089396, 'samples': 20268864, 'steps': 105566, 'loss/train': 0.7534160017967224} 08/31/2021 08:25:07 - INFO - __main__ - Step 105568: {'lr': 0.00010319540009752463, 'samples': 20269056, 'steps': 105567, 'loss/train': 1.2350369691848755} 08/31/2021 08:25:08 - INFO - __main__ - Step 105569: {'lr': 0.00010319110470030315, 'samples': 20269248, 'steps': 105568, 'loss/train': 0.45484763383865356} 08/31/2021 08:25:08 - INFO - __main__ - Step 105570: {'lr': 0.00010318680936923153, 'samples': 20269440, 'steps': 105569, 'loss/train': 1.2800524234771729} 08/31/2021 08:25:08 - INFO - __main__ - Step 105571: {'lr': 0.00010318251410431164, 'samples': 20269632, 'steps': 105570, 'loss/train': 1.4738558530807495} 08/31/2021 08:25:10 - INFO - __main__ - Step 105572: {'lr': 0.00010317821890554549, 'samples': 20269824, 'steps': 105571, 'loss/train': 0.8834466934204102} 08/31/2021 08:25:10 - INFO - __main__ - Step 105573: {'lr': 0.00010317392377293503, 'samples': 20270016, 'steps': 105572, 'loss/train': 1.3178707361221313} 08/31/2021 08:25:11 - INFO - __main__ - Step 105574: {'lr': 0.00010316962870648203, 'samples': 20270208, 'steps': 105573, 'loss/train': 0.9983810782432556} 08/31/2021 08:25:11 - INFO - __main__ - Step 105575: {'lr': 0.00010316533370618856, 'samples': 20270400, 'steps': 105574, 'loss/train': 0.6603397130966187} 08/31/2021 08:25:11 - INFO - __main__ - Step 105576: {'lr': 0.00010316103877205649, 'samples': 20270592, 'steps': 105575, 'loss/train': 1.005111575126648} 08/31/2021 08:25:13 - INFO - __main__ - Step 105577: {'lr': 0.0001031567439040878, 'samples': 20270784, 'steps': 105576, 'loss/train': 1.4776670932769775} 08/31/2021 08:25:13 - INFO - __main__ - Step 105578: {'lr': 0.00010315244910228445, 'samples': 20270976, 'steps': 105577, 'loss/train': 1.4446722269058228} 08/31/2021 08:25:14 - INFO - __main__ - Step 105579: {'lr': 0.00010314815436664828, 'samples': 20271168, 'steps': 105578, 'loss/train': 0.6292014122009277} 08/31/2021 08:25:14 - INFO - __main__ - Step 105580: {'lr': 0.00010314385969718135, 'samples': 20271360, 'steps': 105579, 'loss/train': 1.1393694877624512} 08/31/2021 08:25:14 - INFO - __main__ - Step 105581: {'lr': 0.0001031395650938855, 'samples': 20271552, 'steps': 105580, 'loss/train': 0.6525192260742188} 08/31/2021 08:25:16 - INFO - __main__ - Step 105582: {'lr': 0.0001031352705567627, 'samples': 20271744, 'steps': 105581, 'loss/train': 1.1635539531707764} 08/31/2021 08:25:16 - INFO - __main__ - Step 105583: {'lr': 0.00010313097608581487, 'samples': 20271936, 'steps': 105582, 'loss/train': 1.2155879735946655} 08/31/2021 08:25:17 - INFO - __main__ - Step 105584: {'lr': 0.00010312668168104397, 'samples': 20272128, 'steps': 105583, 'loss/train': 1.2543421983718872} 08/31/2021 08:25:17 - INFO - __main__ - Step 105585: {'lr': 0.00010312238734245192, 'samples': 20272320, 'steps': 105584, 'loss/train': 0.9381511807441711} 08/31/2021 08:25:17 - INFO - __main__ - Step 105586: {'lr': 0.00010311809307004063, 'samples': 20272512, 'steps': 105585, 'loss/train': 0.38637009263038635} 08/31/2021 08:25:19 - INFO - __main__ - Step 105587: {'lr': 0.00010311379886381216, 'samples': 20272704, 'steps': 105586, 'loss/train': 1.6446785926818848} 08/31/2021 08:25:20 - INFO - __main__ - Step 105588: {'lr': 0.00010310950472376829, 'samples': 20272896, 'steps': 105587, 'loss/train': 0.4780772924423218} 08/31/2021 08:25:20 - INFO - __main__ - Step 105589: {'lr': 0.00010310521064991096, 'samples': 20273088, 'steps': 105588, 'loss/train': 0.01954047754406929} 08/31/2021 08:25:20 - INFO - __main__ - Step 105590: {'lr': 0.0001031009166422422, 'samples': 20273280, 'steps': 105589, 'loss/train': 0.40314820408821106} 08/31/2021 08:25:21 - INFO - __main__ - Step 105591: {'lr': 0.0001030966227007639, 'samples': 20273472, 'steps': 105590, 'loss/train': 0.3867492973804474} 08/31/2021 08:25:21 - INFO - __main__ - Step 105592: {'lr': 0.00010309232882547795, 'samples': 20273664, 'steps': 105591, 'loss/train': 1.2158390283584595} 08/31/2021 08:25:23 - INFO - __main__ - Step 105593: {'lr': 0.00010308803501638636, 'samples': 20273856, 'steps': 105592, 'loss/train': 0.0250246599316597} 08/31/2021 08:25:24 - INFO - __main__ - Step 105594: {'lr': 0.00010308374127349104, 'samples': 20274048, 'steps': 105593, 'loss/train': 0.9133855104446411} 08/31/2021 08:25:24 - INFO - __main__ - Step 105595: {'lr': 0.00010307944759679392, 'samples': 20274240, 'steps': 105594, 'loss/train': 0.9084822535514832} 08/31/2021 08:25:24 - INFO - __main__ - Step 105596: {'lr': 0.00010307515398629691, 'samples': 20274432, 'steps': 105595, 'loss/train': 1.1618908643722534} 08/31/2021 08:25:25 - INFO - __main__ - Step 105597: {'lr': 0.00010307086044200198, 'samples': 20274624, 'steps': 105596, 'loss/train': 0.1300654411315918} 08/31/2021 08:25:26 - INFO - __main__ - Step 105598: {'lr': 0.00010306656696391106, 'samples': 20274816, 'steps': 105597, 'loss/train': 1.1492992639541626} 08/31/2021 08:25:27 - INFO - __main__ - Step 105599: {'lr': 0.00010306227355202608, 'samples': 20275008, 'steps': 105598, 'loss/train': 0.5430612564086914} 08/31/2021 08:25:27 - INFO - __main__ - Step 105600: {'lr': 0.00010305798020634904, 'samples': 20275200, 'steps': 105599, 'loss/train': 1.459140658378601} 08/31/2021 08:25:27 - INFO - __main__ - Step 105601: {'lr': 0.00010305368692688174, 'samples': 20275392, 'steps': 105600, 'loss/train': 1.490547776222229} 08/31/2021 08:25:28 - INFO - __main__ - Step 105602: {'lr': 0.00010304939371362618, 'samples': 20275584, 'steps': 105601, 'loss/train': 0.42966172099113464} 08/31/2021 08:25:29 - INFO - __main__ - Step 105603: {'lr': 0.00010304510056658428, 'samples': 20275776, 'steps': 105602, 'loss/train': 0.7190060615539551} 08/31/2021 08:25:30 - INFO - __main__ - Step 105604: {'lr': 0.000103040807485758, 'samples': 20275968, 'steps': 105603, 'loss/train': 1.5071601867675781} 08/31/2021 08:25:30 - INFO - __main__ - Step 105605: {'lr': 0.00010303651447114926, 'samples': 20276160, 'steps': 105604, 'loss/train': 1.128165602684021} 08/31/2021 08:25:30 - INFO - __main__ - Step 105606: {'lr': 0.00010303222152276001, 'samples': 20276352, 'steps': 105605, 'loss/train': 1.3312201499938965} 08/31/2021 08:25:31 - INFO - __main__ - Step 105607: {'lr': 0.00010302792864059216, 'samples': 20276544, 'steps': 105606, 'loss/train': 0.48840823769569397} 08/31/2021 08:25:33 - INFO - __main__ - Step 105608: {'lr': 0.00010302363582464766, 'samples': 20276736, 'steps': 105607, 'loss/train': 1.5393930673599243} 08/31/2021 08:25:33 - INFO - __main__ - Step 105609: {'lr': 0.00010301934307492844, 'samples': 20276928, 'steps': 105608, 'loss/train': 1.396823525428772} 08/31/2021 08:25:34 - INFO - __main__ - Step 105610: {'lr': 0.00010301505039143644, 'samples': 20277120, 'steps': 105609, 'loss/train': 0.5163642764091492} 08/31/2021 08:25:34 - INFO - __main__ - Step 105611: {'lr': 0.00010301075777417368, 'samples': 20277312, 'steps': 105610, 'loss/train': 0.8891454339027405} 08/31/2021 08:25:34 - INFO - __main__ - Step 105612: {'lr': 0.00010300646522314192, 'samples': 20277504, 'steps': 105611, 'loss/train': 0.4107256233692169} 08/31/2021 08:25:36 - INFO - __main__ - Step 105613: {'lr': 0.00010300217273834317, 'samples': 20277696, 'steps': 105612, 'loss/train': 1.1695830821990967} 08/31/2021 08:25:37 - INFO - __main__ - Step 105614: {'lr': 0.00010299788031977938, 'samples': 20277888, 'steps': 105613, 'loss/train': 0.2825806736946106} 08/31/2021 08:25:37 - INFO - __main__ - Step 105615: {'lr': 0.00010299358796745248, 'samples': 20278080, 'steps': 105614, 'loss/train': 1.6651782989501953} 08/31/2021 08:25:37 - INFO - __main__ - Step 105616: {'lr': 0.00010298929568136439, 'samples': 20278272, 'steps': 105615, 'loss/train': 1.3836705684661865} 08/31/2021 08:25:38 - INFO - __main__ - Step 105617: {'lr': 0.00010298500346151707, 'samples': 20278464, 'steps': 105616, 'loss/train': 1.0595192909240723} 08/31/2021 08:25:38 - INFO - __main__ - Step 105618: {'lr': 0.00010298071130791243, 'samples': 20278656, 'steps': 105617, 'loss/train': 0.41350632905960083} 08/31/2021 08:25:40 - INFO - __main__ - Step 105619: {'lr': 0.0001029764192205524, 'samples': 20278848, 'steps': 105618, 'loss/train': 0.9083815813064575} 08/31/2021 08:25:40 - INFO - __main__ - Step 105620: {'lr': 0.00010297212719943893, 'samples': 20279040, 'steps': 105619, 'loss/train': 1.047224760055542} 08/31/2021 08:25:40 - INFO - __main__ - Step 105621: {'lr': 0.00010296783524457395, 'samples': 20279232, 'steps': 105620, 'loss/train': 0.9818163514137268} 08/31/2021 08:25:41 - INFO - __main__ - Step 105622: {'lr': 0.0001029635433559595, 'samples': 20279424, 'steps': 105621, 'loss/train': 0.9732034802436829} 08/31/2021 08:25:41 - INFO - __main__ - Step 105623: {'lr': 0.00010295925153359731, 'samples': 20279616, 'steps': 105622, 'loss/train': 1.1777466535568237} 08/31/2021 08:25:42 - INFO - __main__ - Step 105624: {'lr': 0.00010295495977748942, 'samples': 20279808, 'steps': 105623, 'loss/train': 1.1354750394821167} 08/31/2021 08:25:43 - INFO - __main__ - Step 105625: {'lr': 0.00010295066808763775, 'samples': 20280000, 'steps': 105624, 'loss/train': 1.3179566860198975} 08/31/2021 08:25:43 - INFO - __main__ - Step 105626: {'lr': 0.00010294637646404422, 'samples': 20280192, 'steps': 105625, 'loss/train': 1.0217862129211426} 08/31/2021 08:25:44 - INFO - __main__ - Step 105627: {'lr': 0.0001029420849067108, 'samples': 20280384, 'steps': 105626, 'loss/train': 1.1278808116912842} 08/31/2021 08:25:44 - INFO - __main__ - Step 105628: {'lr': 0.00010293779341563942, 'samples': 20280576, 'steps': 105627, 'loss/train': 1.2691612243652344} 08/31/2021 08:25:46 - INFO - __main__ - Step 105629: {'lr': 0.00010293350199083198, 'samples': 20280768, 'steps': 105628, 'loss/train': 1.0095443725585938} 08/31/2021 08:25:46 - INFO - __main__ - Step 105630: {'lr': 0.00010292921063229046, 'samples': 20280960, 'steps': 105629, 'loss/train': 1.2287299633026123} 08/31/2021 08:25:46 - INFO - __main__ - Step 105631: {'lr': 0.00010292491934001674, 'samples': 20281152, 'steps': 105630, 'loss/train': 1.3334904909133911} 08/31/2021 08:25:47 - INFO - __main__ - Step 105632: {'lr': 0.00010292062811401281, 'samples': 20281344, 'steps': 105631, 'loss/train': 1.3974010944366455} 08/31/2021 08:25:47 - INFO - __main__ - Step 105633: {'lr': 0.00010291633695428066, 'samples': 20281536, 'steps': 105632, 'loss/train': 0.9972994327545166} 08/31/2021 08:25:47 - INFO - __main__ - Step 105634: {'lr': 0.00010291204586082204, 'samples': 20281728, 'steps': 105633, 'loss/train': 1.7368078231811523} 08/31/2021 08:25:49 - INFO - __main__ - Step 105635: {'lr': 0.00010290775483363899, 'samples': 20281920, 'steps': 105634, 'loss/train': 1.2998219728469849} 08/31/2021 08:25:49 - INFO - __main__ - Step 105636: {'lr': 0.00010290346387273341, 'samples': 20282112, 'steps': 105635, 'loss/train': 0.2301613688468933} 08/31/2021 08:25:50 - INFO - __main__ - Step 105637: {'lr': 0.00010289917297810728, 'samples': 20282304, 'steps': 105636, 'loss/train': 1.409660816192627} 08/31/2021 08:25:50 - INFO - __main__ - Step 105638: {'lr': 0.0001028948821497625, 'samples': 20282496, 'steps': 105637, 'loss/train': 0.8908960223197937} 08/31/2021 08:25:50 - INFO - __main__ - Step 105639: {'lr': 0.00010289059138770104, 'samples': 20282688, 'steps': 105638, 'loss/train': 1.9322177171707153} 08/31/2021 08:25:52 - INFO - __main__ - Step 105640: {'lr': 0.00010288630069192479, 'samples': 20282880, 'steps': 105639, 'loss/train': 1.2492393255233765} 08/31/2021 08:25:52 - INFO - __main__ - Step 105641: {'lr': 0.00010288201006243572, 'samples': 20283072, 'steps': 105640, 'loss/train': 0.8941012024879456} 08/31/2021 08:25:53 - INFO - __main__ - Step 105642: {'lr': 0.00010287771949923571, 'samples': 20283264, 'steps': 105641, 'loss/train': 0.661487340927124} 08/31/2021 08:25:53 - INFO - __main__ - Step 105643: {'lr': 0.00010287342900232676, 'samples': 20283456, 'steps': 105642, 'loss/train': 1.0815452337265015} 08/31/2021 08:25:53 - INFO - __main__ - Step 105644: {'lr': 0.00010286913857171088, 'samples': 20283648, 'steps': 105643, 'loss/train': 0.9511322379112244} 08/31/2021 08:25:55 - INFO - __main__ - Step 105645: {'lr': 0.00010286484820738975, 'samples': 20283840, 'steps': 105644, 'loss/train': 1.3684165477752686} 08/31/2021 08:25:55 - INFO - __main__ - Step 105646: {'lr': 0.00010286055790936549, 'samples': 20284032, 'steps': 105645, 'loss/train': 1.3372063636779785} 08/31/2021 08:25:56 - INFO - __main__ - Step 105647: {'lr': 0.00010285626767764, 'samples': 20284224, 'steps': 105646, 'loss/train': 1.3058143854141235} 08/31/2021 08:25:56 - INFO - __main__ - Step 105648: {'lr': 0.00010285197751221517, 'samples': 20284416, 'steps': 105647, 'loss/train': 0.8379442691802979} 08/31/2021 08:25:56 - INFO - __main__ - Step 105649: {'lr': 0.000102847687413093, 'samples': 20284608, 'steps': 105648, 'loss/train': 1.2797322273254395} 08/31/2021 08:25:58 - INFO - __main__ - Step 105650: {'lr': 0.00010284339738027538, 'samples': 20284800, 'steps': 105649, 'loss/train': 0.8757469058036804} 08/31/2021 08:25:59 - INFO - __main__ - Step 105651: {'lr': 0.00010283910741376427, 'samples': 20284992, 'steps': 105650, 'loss/train': 1.3960440158843994} 08/31/2021 08:25:59 - INFO - __main__ - Step 105652: {'lr': 0.00010283481751356155, 'samples': 20285184, 'steps': 105651, 'loss/train': 0.6243266463279724} 08/31/2021 08:25:59 - INFO - __main__ - Step 105653: {'lr': 0.00010283052767966922, 'samples': 20285376, 'steps': 105652, 'loss/train': 0.7027682662010193} 08/31/2021 08:26:00 - INFO - __main__ - Step 105654: {'lr': 0.00010282623791208917, 'samples': 20285568, 'steps': 105653, 'loss/train': 0.5618264675140381} 08/31/2021 08:26:01 - INFO - __main__ - Step 105655: {'lr': 0.00010282194821082344, 'samples': 20285760, 'steps': 105654, 'loss/train': 0.1368846893310547} 08/31/2021 08:26:02 - INFO - __main__ - Step 105656: {'lr': 0.00010281765857587377, 'samples': 20285952, 'steps': 105655, 'loss/train': 1.6610372066497803} 08/31/2021 08:26:02 - INFO - __main__ - Step 105657: {'lr': 0.0001028133690072422, 'samples': 20286144, 'steps': 105656, 'loss/train': 1.1369521617889404} 08/31/2021 08:26:02 - INFO - __main__ - Step 105658: {'lr': 0.00010280907950493066, 'samples': 20286336, 'steps': 105657, 'loss/train': 1.4037162065505981} 08/31/2021 08:26:03 - INFO - __main__ - Step 105659: {'lr': 0.00010280479006894108, 'samples': 20286528, 'steps': 105658, 'loss/train': 0.95011967420578} 08/31/2021 08:26:04 - INFO - __main__ - Step 105660: {'lr': 0.00010280050069927538, 'samples': 20286720, 'steps': 105659, 'loss/train': 0.7591801285743713} 08/31/2021 08:26:05 - INFO - __main__ - Step 105661: {'lr': 0.0001027962113959355, 'samples': 20286912, 'steps': 105660, 'loss/train': 0.03172913193702698} 08/31/2021 08:26:05 - INFO - __main__ - Step 105662: {'lr': 0.00010279192215892339, 'samples': 20287104, 'steps': 105661, 'loss/train': 1.105919599533081} 08/31/2021 08:26:05 - INFO - __main__ - Step 105663: {'lr': 0.00010278763298824096, 'samples': 20287296, 'steps': 105662, 'loss/train': 0.059861477464437485} 08/31/2021 08:26:06 - INFO - __main__ - Step 105664: {'lr': 0.00010278334388389016, 'samples': 20287488, 'steps': 105663, 'loss/train': 0.7677066922187805} 08/31/2021 08:26:06 - INFO - __main__ - Step 105665: {'lr': 0.00010277905484587288, 'samples': 20287680, 'steps': 105664, 'loss/train': 1.2620289325714111} 08/31/2021 08:26:08 - INFO - __main__ - Step 105666: {'lr': 0.00010277476587419112, 'samples': 20287872, 'steps': 105665, 'loss/train': 1.316501498222351} 08/31/2021 08:26:09 - INFO - __main__ - Step 105667: {'lr': 0.00010277047696884687, 'samples': 20288064, 'steps': 105666, 'loss/train': 1.0066204071044922} 08/31/2021 08:26:09 - INFO - __main__ - Step 105668: {'lr': 0.00010276618812984188, 'samples': 20288256, 'steps': 105667, 'loss/train': 0.8480851650238037} 08/31/2021 08:26:09 - INFO - __main__ - Step 105669: {'lr': 0.00010276189935717814, 'samples': 20288448, 'steps': 105668, 'loss/train': 0.39200201630592346} 08/31/2021 08:26:10 - INFO - __main__ - Step 105670: {'lr': 0.00010275761065085764, 'samples': 20288640, 'steps': 105669, 'loss/train': 1.306254267692566} 08/31/2021 08:26:11 - INFO - __main__ - Step 105671: {'lr': 0.00010275332201088231, 'samples': 20288832, 'steps': 105670, 'loss/train': 1.408262014389038} 08/31/2021 08:26:12 - INFO - __main__ - Step 105672: {'lr': 0.00010274903343725403, 'samples': 20289024, 'steps': 105671, 'loss/train': 1.068863868713379} 08/31/2021 08:26:12 - INFO - __main__ - Step 105673: {'lr': 0.00010274474492997477, 'samples': 20289216, 'steps': 105672, 'loss/train': 0.11155931651592255} 08/31/2021 08:26:13 - INFO - __main__ - Step 105674: {'lr': 0.00010274045648904646, 'samples': 20289408, 'steps': 105673, 'loss/train': 0.6137298941612244} 08/31/2021 08:26:13 - INFO - __main__ - Step 105675: {'lr': 0.00010273616811447103, 'samples': 20289600, 'steps': 105674, 'loss/train': 0.9100965857505798} 08/31/2021 08:26:14 - INFO - __main__ - Step 105676: {'lr': 0.0001027318798062504, 'samples': 20289792, 'steps': 105675, 'loss/train': 1.1179198026657104} 08/31/2021 08:26:15 - INFO - __main__ - Step 105677: {'lr': 0.00010272759156438651, 'samples': 20289984, 'steps': 105676, 'loss/train': 1.0831807851791382} 08/31/2021 08:26:15 - INFO - __main__ - Step 105678: {'lr': 0.0001027233033888813, 'samples': 20290176, 'steps': 105677, 'loss/train': 1.1127660274505615} 08/31/2021 08:26:15 - INFO - __main__ - Step 105679: {'lr': 0.00010271901527973671, 'samples': 20290368, 'steps': 105678, 'loss/train': 1.3903647661209106} 08/31/2021 08:26:16 - INFO - __main__ - Step 105680: {'lr': 0.00010271472723695466, 'samples': 20290560, 'steps': 105679, 'loss/train': 1.2290143966674805} 08/31/2021 08:26:18 - INFO - __main__ - Step 105681: {'lr': 0.00010271043926053716, 'samples': 20290752, 'steps': 105680, 'loss/train': 1.245816946029663} 08/31/2021 08:26:18 - INFO - __main__ - Step 105682: {'lr': 0.00010270615135048597, 'samples': 20290944, 'steps': 105681, 'loss/train': 1.2878086566925049} 08/31/2021 08:26:18 - INFO - __main__ - Step 105683: {'lr': 0.00010270186350680314, 'samples': 20291136, 'steps': 105682, 'loss/train': 1.1884783506393433} 08/31/2021 08:26:19 - INFO - __main__ - Step 105684: {'lr': 0.00010269757572949054, 'samples': 20291328, 'steps': 105683, 'loss/train': 0.41686928272247314} 08/31/2021 08:26:19 - INFO - __main__ - Step 105685: {'lr': 0.00010269328801855016, 'samples': 20291520, 'steps': 105684, 'loss/train': 1.2829393148422241} 08/31/2021 08:26:21 - INFO - __main__ - Step 105686: {'lr': 0.0001026890003739839, 'samples': 20291712, 'steps': 105685, 'loss/train': 0.8019644021987915} 08/31/2021 08:26:21 - INFO - __main__ - Step 105687: {'lr': 0.00010268471279579372, 'samples': 20291904, 'steps': 105686, 'loss/train': 1.3674958944320679} 08/31/2021 08:26:21 - INFO - __main__ - Step 105688: {'lr': 0.00010268042528398153, 'samples': 20292096, 'steps': 105687, 'loss/train': 1.481391191482544} 08/31/2021 08:26:22 - INFO - __main__ - Step 105689: {'lr': 0.00010267613783854925, 'samples': 20292288, 'steps': 105688, 'loss/train': 1.337081789970398} 08/31/2021 08:26:22 - INFO - __main__ - Step 105690: {'lr': 0.00010267185045949884, 'samples': 20292480, 'steps': 105689, 'loss/train': 0.3312702476978302} 08/31/2021 08:26:24 - INFO - __main__ - Step 105691: {'lr': 0.00010266756314683224, 'samples': 20292672, 'steps': 105690, 'loss/train': 1.0089030265808105} 08/31/2021 08:26:24 - INFO - __main__ - Step 105692: {'lr': 0.00010266327590055132, 'samples': 20292864, 'steps': 105691, 'loss/train': 0.754873514175415} 08/31/2021 08:26:24 - INFO - __main__ - Step 105693: {'lr': 0.0001026589887206581, 'samples': 20293056, 'steps': 105692, 'loss/train': 1.2074600458145142} 08/31/2021 08:26:25 - INFO - __main__ - Step 105694: {'lr': 0.00010265470160715453, 'samples': 20293248, 'steps': 105693, 'loss/train': 1.1931782960891724} 08/31/2021 08:26:25 - INFO - __main__ - Step 105695: {'lr': 0.0001026504145600424, 'samples': 20293440, 'steps': 105694, 'loss/train': 0.7435371279716492} 08/31/2021 08:26:25 - INFO - __main__ - Step 105696: {'lr': 0.00010264612757932371, 'samples': 20293632, 'steps': 105695, 'loss/train': 1.286536693572998} 08/31/2021 08:26:27 - INFO - __main__ - Step 105697: {'lr': 0.0001026418406650004, 'samples': 20293824, 'steps': 105696, 'loss/train': 0.8515684008598328} 08/31/2021 08:26:27 - INFO - __main__ - Step 105698: {'lr': 0.00010263755381707441, 'samples': 20294016, 'steps': 105697, 'loss/train': 1.0008734464645386} 08/31/2021 08:26:28 - INFO - __main__ - Step 105699: {'lr': 0.00010263326703554765, 'samples': 20294208, 'steps': 105698, 'loss/train': 0.3182515501976013} 08/31/2021 08:26:28 - INFO - __main__ - Step 105700: {'lr': 0.00010262898032042208, 'samples': 20294400, 'steps': 105699, 'loss/train': 1.443812370300293} 08/31/2021 08:26:29 - INFO - __main__ - Step 105701: {'lr': 0.00010262469367169963, 'samples': 20294592, 'steps': 105700, 'loss/train': 1.4050358533859253} 08/31/2021 08:26:30 - INFO - __main__ - Step 105702: {'lr': 0.0001026204070893822, 'samples': 20294784, 'steps': 105701, 'loss/train': 0.926609992980957} 08/31/2021 08:26:30 - INFO - __main__ - Step 105703: {'lr': 0.00010261612057347175, 'samples': 20294976, 'steps': 105702, 'loss/train': 0.40010926127433777} 08/31/2021 08:26:31 - INFO - __main__ - Step 105704: {'lr': 0.00010261183412397018, 'samples': 20295168, 'steps': 105703, 'loss/train': 1.6888636350631714} 08/31/2021 08:26:31 - INFO - __main__ - Step 105705: {'lr': 0.00010260754774087947, 'samples': 20295360, 'steps': 105704, 'loss/train': 0.9706432223320007} 08/31/2021 08:26:32 - INFO - __main__ - Step 105706: {'lr': 0.00010260326142420151, 'samples': 20295552, 'steps': 105705, 'loss/train': 1.625828742980957} 08/31/2021 08:26:34 - INFO - __main__ - Step 105707: {'lr': 0.00010259897517393826, 'samples': 20295744, 'steps': 105706, 'loss/train': 0.973706066608429} 08/31/2021 08:26:34 - INFO - __main__ - Step 105708: {'lr': 0.00010259468899009172, 'samples': 20295936, 'steps': 105707, 'loss/train': 0.9501315951347351} 08/31/2021 08:26:35 - INFO - __main__ - Step 105709: {'lr': 0.00010259040287266363, 'samples': 20296128, 'steps': 105708, 'loss/train': 0.9372137188911438} 08/31/2021 08:26:35 - INFO - __main__ - Step 105710: {'lr': 0.00010258611682165605, 'samples': 20296320, 'steps': 105709, 'loss/train': 1.0673784017562866} 08/31/2021 08:26:35 - INFO - __main__ - Step 105711: {'lr': 0.0001025818308370709, 'samples': 20296512, 'steps': 105710, 'loss/train': 0.7696548104286194} 08/31/2021 08:26:37 - INFO - __main__ - Step 105712: {'lr': 0.00010257754491891009, 'samples': 20296704, 'steps': 105711, 'loss/train': 1.5261746644973755} 08/31/2021 08:26:37 - INFO - __main__ - Step 105713: {'lr': 0.00010257325906717554, 'samples': 20296896, 'steps': 105712, 'loss/train': 0.9581429958343506} 08/31/2021 08:26:38 - INFO - __main__ - Step 105714: {'lr': 0.00010256897328186923, 'samples': 20297088, 'steps': 105713, 'loss/train': 1.1605243682861328} 08/31/2021 08:26:38 - INFO - __main__ - Step 105715: {'lr': 0.00010256468756299306, 'samples': 20297280, 'steps': 105714, 'loss/train': 0.19535744190216064} 08/31/2021 08:26:38 - INFO - __main__ - Step 105716: {'lr': 0.00010256040191054897, 'samples': 20297472, 'steps': 105715, 'loss/train': 0.11659673601388931} 08/31/2021 08:26:40 - INFO - __main__ - Step 105717: {'lr': 0.0001025561163245389, 'samples': 20297664, 'steps': 105716, 'loss/train': 2.171008348464966} 08/31/2021 08:26:40 - INFO - __main__ - Step 105718: {'lr': 0.00010255183080496474, 'samples': 20297856, 'steps': 105717, 'loss/train': 0.8383882641792297} 08/31/2021 08:26:41 - INFO - __main__ - Step 105719: {'lr': 0.00010254754535182848, 'samples': 20298048, 'steps': 105718, 'loss/train': 1.2521036863327026} 08/31/2021 08:26:41 - INFO - __main__ - Step 105720: {'lr': 0.000102543259965132, 'samples': 20298240, 'steps': 105719, 'loss/train': 0.859679102897644} 08/31/2021 08:26:41 - INFO - __main__ - Step 105721: {'lr': 0.00010253897464487735, 'samples': 20298432, 'steps': 105720, 'loss/train': 1.2435359954833984} 08/31/2021 08:26:42 - INFO - __main__ - Step 105722: {'lr': 0.00010253468939106628, 'samples': 20298624, 'steps': 105721, 'loss/train': 2.703948497772217} 08/31/2021 08:26:43 - INFO - __main__ - Step 105723: {'lr': 0.00010253040420370077, 'samples': 20298816, 'steps': 105722, 'loss/train': 0.1263357400894165} 08/31/2021 08:26:44 - INFO - __main__ - Step 105724: {'lr': 0.0001025261190827828, 'samples': 20299008, 'steps': 105723, 'loss/train': 1.2394647598266602} 08/31/2021 08:26:44 - INFO - __main__ - Step 105725: {'lr': 0.00010252183402831431, 'samples': 20299200, 'steps': 105724, 'loss/train': 0.02689882181584835} 08/31/2021 08:26:45 - INFO - __main__ - Step 105726: {'lr': 0.0001025175490402972, 'samples': 20299392, 'steps': 105725, 'loss/train': 0.5804492831230164} 08/31/2021 08:26:45 - INFO - __main__ - Step 105727: {'lr': 0.00010251326411873338, 'samples': 20299584, 'steps': 105726, 'loss/train': 0.10719870775938034} 08/31/2021 08:26:47 - INFO - __main__ - Step 105728: {'lr': 0.00010250897926362482, 'samples': 20299776, 'steps': 105727, 'loss/train': 1.361311912536621} 08/31/2021 08:26:47 - INFO - __main__ - Step 105729: {'lr': 0.00010250469447497345, 'samples': 20299968, 'steps': 105728, 'loss/train': 0.7777637839317322} 08/31/2021 08:26:48 - INFO - __main__ - Step 105730: {'lr': 0.00010250040975278118, 'samples': 20300160, 'steps': 105729, 'loss/train': 0.9424239993095398} 08/31/2021 08:26:48 - INFO - __main__ - Step 105731: {'lr': 0.00010249612509704995, 'samples': 20300352, 'steps': 105730, 'loss/train': 2.7528676986694336} 08/31/2021 08:26:48 - INFO - __main__ - Step 105732: {'lr': 0.00010249184050778168, 'samples': 20300544, 'steps': 105731, 'loss/train': 2.0010335445404053} 08/31/2021 08:26:50 - INFO - __main__ - Step 105733: {'lr': 0.00010248755598497834, 'samples': 20300736, 'steps': 105732, 'loss/train': 1.5081686973571777} 08/31/2021 08:26:51 - INFO - __main__ - Step 105734: {'lr': 0.00010248327152864179, 'samples': 20300928, 'steps': 105733, 'loss/train': 0.9227163791656494} 08/31/2021 08:26:51 - INFO - __main__ - Step 105735: {'lr': 0.00010247898713877413, 'samples': 20301120, 'steps': 105734, 'loss/train': 2.0529239177703857} 08/31/2021 08:26:51 - INFO - __main__ - Step 105736: {'lr': 0.00010247470281537704, 'samples': 20301312, 'steps': 105735, 'loss/train': 1.6074495315551758} 08/31/2021 08:26:52 - INFO - __main__ - Step 105737: {'lr': 0.00010247041855845257, 'samples': 20301504, 'steps': 105736, 'loss/train': 1.4791380167007446} 08/31/2021 08:26:52 - INFO - __main__ - Step 105738: {'lr': 0.00010246613436800268, 'samples': 20301696, 'steps': 105737, 'loss/train': 0.014949257485568523} 08/31/2021 08:26:54 - INFO - __main__ - Step 105739: {'lr': 0.00010246185024402927, 'samples': 20301888, 'steps': 105738, 'loss/train': 0.01577002741396427} 08/31/2021 08:26:54 - INFO - __main__ - Step 105740: {'lr': 0.00010245756618653426, 'samples': 20302080, 'steps': 105739, 'loss/train': 0.8778870701789856} 08/31/2021 08:26:54 - INFO - __main__ - Step 105741: {'lr': 0.00010245328219551961, 'samples': 20302272, 'steps': 105740, 'loss/train': 1.6193984746932983} 08/31/2021 08:26:55 - INFO - __main__ - Step 105742: {'lr': 0.00010244899827098721, 'samples': 20302464, 'steps': 105741, 'loss/train': 1.0790096521377563} 08/31/2021 08:26:55 - INFO - __main__ - Step 105743: {'lr': 0.00010244471441293904, 'samples': 20302656, 'steps': 105742, 'loss/train': 0.31515195965766907} 08/31/2021 08:26:57 - INFO - __main__ - Step 105744: {'lr': 0.00010244043062137698, 'samples': 20302848, 'steps': 105743, 'loss/train': 1.0895947217941284} 08/31/2021 08:26:57 - INFO - __main__ - Step 105745: {'lr': 0.00010243614689630302, 'samples': 20303040, 'steps': 105744, 'loss/train': 1.5433064699172974} 08/31/2021 08:26:58 - INFO - __main__ - Step 105746: {'lr': 0.00010243186323771903, 'samples': 20303232, 'steps': 105745, 'loss/train': 1.3008826971054077} 08/31/2021 08:26:58 - INFO - __main__ - Step 105747: {'lr': 0.00010242757964562696, 'samples': 20303424, 'steps': 105746, 'loss/train': 1.5757629871368408} 08/31/2021 08:26:58 - INFO - __main__ - Step 105748: {'lr': 0.00010242329612002885, 'samples': 20303616, 'steps': 105747, 'loss/train': 0.9913932681083679} 08/31/2021 08:27:00 - INFO - __main__ - Step 105749: {'lr': 0.00010241901266092644, 'samples': 20303808, 'steps': 105748, 'loss/train': 0.47606855630874634} 08/31/2021 08:27:00 - INFO - __main__ - Step 105750: {'lr': 0.00010241472926832171, 'samples': 20304000, 'steps': 105749, 'loss/train': 1.0824971199035645} 08/31/2021 08:27:01 - INFO - __main__ - Step 105751: {'lr': 0.00010241044594221666, 'samples': 20304192, 'steps': 105750, 'loss/train': 1.4187548160552979} 08/31/2021 08:27:01 - INFO - __main__ - Step 105752: {'lr': 0.00010240616268261318, 'samples': 20304384, 'steps': 105751, 'loss/train': 0.5569803714752197} 08/31/2021 08:27:01 - INFO - __main__ - Step 105753: {'lr': 0.00010240187948951318, 'samples': 20304576, 'steps': 105752, 'loss/train': 0.2320302426815033} 08/31/2021 08:27:03 - INFO - __main__ - Step 105754: {'lr': 0.00010239759636291864, 'samples': 20304768, 'steps': 105753, 'loss/train': 1.22904372215271} 08/31/2021 08:27:03 - INFO - __main__ - Step 105755: {'lr': 0.00010239331330283147, 'samples': 20304960, 'steps': 105754, 'loss/train': 0.9574843645095825} 08/31/2021 08:27:04 - INFO - __main__ - Step 105756: {'lr': 0.00010238903030925359, 'samples': 20305152, 'steps': 105755, 'loss/train': 0.851742148399353} 08/31/2021 08:27:04 - INFO - __main__ - Step 105757: {'lr': 0.00010238474738218696, 'samples': 20305344, 'steps': 105756, 'loss/train': 0.6889218688011169} 08/31/2021 08:27:04 - INFO - __main__ - Step 105758: {'lr': 0.00010238046452163343, 'samples': 20305536, 'steps': 105757, 'loss/train': 0.7933364510536194} 08/31/2021 08:27:07 - INFO - __main__ - Step 105759: {'lr': 0.00010237618172759502, 'samples': 20305728, 'steps': 105758, 'loss/train': 1.4966663122177124} 08/31/2021 08:27:07 - INFO - __main__ - Step 105760: {'lr': 0.00010237189900007363, 'samples': 20305920, 'steps': 105759, 'loss/train': 1.1410293579101562} 08/31/2021 08:27:08 - INFO - __main__ - Step 105761: {'lr': 0.00010236761633907124, 'samples': 20306112, 'steps': 105760, 'loss/train': 1.1415234804153442} 08/31/2021 08:27:08 - INFO - __main__ - Step 105762: {'lr': 0.00010236333374458967, 'samples': 20306304, 'steps': 105761, 'loss/train': 2.041999101638794} 08/31/2021 08:27:08 - INFO - __main__ - Step 105763: {'lr': 0.00010235905121663089, 'samples': 20306496, 'steps': 105762, 'loss/train': 1.3707237243652344} 08/31/2021 08:27:09 - INFO - __main__ - Step 105764: {'lr': 0.00010235476875519683, 'samples': 20306688, 'steps': 105763, 'loss/train': 1.097004771232605} 08/31/2021 08:27:10 - INFO - __main__ - Step 105765: {'lr': 0.00010235048636028945, 'samples': 20306880, 'steps': 105764, 'loss/train': 0.016621142625808716} 08/31/2021 08:27:11 - INFO - __main__ - Step 105766: {'lr': 0.00010234620403191067, 'samples': 20307072, 'steps': 105765, 'loss/train': 1.1437633037567139} 08/31/2021 08:27:11 - INFO - __main__ - Step 105767: {'lr': 0.00010234192177006241, 'samples': 20307264, 'steps': 105766, 'loss/train': 0.9816616177558899} 08/31/2021 08:27:11 - INFO - __main__ - Step 105768: {'lr': 0.00010233763957474656, 'samples': 20307456, 'steps': 105767, 'loss/train': 1.5639616250991821} 08/31/2021 08:27:12 - INFO - __main__ - Step 105769: {'lr': 0.00010233335744596514, 'samples': 20307648, 'steps': 105768, 'loss/train': 1.6569210290908813} 08/31/2021 08:27:12 - INFO - __main__ - Step 105770: {'lr': 0.00010232907538372002, 'samples': 20307840, 'steps': 105769, 'loss/train': 0.26002541184425354} 08/31/2021 08:27:14 - INFO - __main__ - Step 105771: {'lr': 0.00010232479338801312, 'samples': 20308032, 'steps': 105770, 'loss/train': 0.6714946627616882} 08/31/2021 08:27:14 - INFO - __main__ - Step 105772: {'lr': 0.00010232051145884641, 'samples': 20308224, 'steps': 105771, 'loss/train': 1.632441520690918} 08/31/2021 08:27:14 - INFO - __main__ - Step 105773: {'lr': 0.00010231622959622181, 'samples': 20308416, 'steps': 105772, 'loss/train': 1.7648078203201294} 08/31/2021 08:27:15 - INFO - __main__ - Step 105774: {'lr': 0.00010231194780014119, 'samples': 20308608, 'steps': 105773, 'loss/train': 0.12148479372262955} 08/31/2021 08:27:15 - INFO - __main__ - Step 105775: {'lr': 0.00010230766607060665, 'samples': 20308800, 'steps': 105774, 'loss/train': 1.5115177631378174} 08/31/2021 08:27:17 - INFO - __main__ - Step 105776: {'lr': 0.00010230338440761991, 'samples': 20308992, 'steps': 105775, 'loss/train': 0.9631041288375854} 08/31/2021 08:27:17 - INFO - __main__ - Step 105777: {'lr': 0.00010229910281118299, 'samples': 20309184, 'steps': 105776, 'loss/train': 0.7039385437965393} 08/31/2021 08:27:17 - INFO - __main__ - Step 105778: {'lr': 0.0001022948212812978, 'samples': 20309376, 'steps': 105777, 'loss/train': 1.1922528743743896} 08/31/2021 08:27:18 - INFO - __main__ - Step 105779: {'lr': 0.0001022905398179663, 'samples': 20309568, 'steps': 105778, 'loss/train': 1.029603123664856} 08/31/2021 08:27:18 - INFO - __main__ - Step 105780: {'lr': 0.00010228625842119039, 'samples': 20309760, 'steps': 105779, 'loss/train': 0.5903127789497375} 08/31/2021 08:27:20 - INFO - __main__ - Step 105781: {'lr': 0.00010228197709097201, 'samples': 20309952, 'steps': 105780, 'loss/train': 1.4522098302841187} 08/31/2021 08:27:20 - INFO - __main__ - Step 105782: {'lr': 0.00010227769582731308, 'samples': 20310144, 'steps': 105781, 'loss/train': 0.8774638175964355} 08/31/2021 08:27:20 - INFO - __main__ - Step 105783: {'lr': 0.00010227341463021555, 'samples': 20310336, 'steps': 105782, 'loss/train': 0.9279484748840332} 08/31/2021 08:27:21 - INFO - __main__ - Step 105784: {'lr': 0.00010226913349968137, 'samples': 20310528, 'steps': 105783, 'loss/train': 0.8334944248199463} 08/31/2021 08:27:21 - INFO - __main__ - Step 105785: {'lr': 0.0001022648524357124, 'samples': 20310720, 'steps': 105784, 'loss/train': 1.3706680536270142} 08/31/2021 08:27:23 - INFO - __main__ - Step 105786: {'lr': 0.00010226057143831064, 'samples': 20310912, 'steps': 105785, 'loss/train': 1.6810539960861206} 08/31/2021 08:27:23 - INFO - __main__ - Step 105787: {'lr': 0.00010225629050747796, 'samples': 20311104, 'steps': 105786, 'loss/train': 0.028815243393182755} 08/31/2021 08:27:24 - INFO - __main__ - Step 105788: {'lr': 0.00010225200964321644, 'samples': 20311296, 'steps': 105787, 'loss/train': 1.3350964784622192} 08/31/2021 08:27:24 - INFO - __main__ - Step 105789: {'lr': 0.00010224772884552774, 'samples': 20311488, 'steps': 105788, 'loss/train': 0.9453239440917969} 08/31/2021 08:27:24 - INFO - __main__ - Step 105790: {'lr': 0.00010224344811441397, 'samples': 20311680, 'steps': 105789, 'loss/train': 1.1483988761901855} 08/31/2021 08:27:26 - INFO - __main__ - Step 105791: {'lr': 0.00010223916744987702, 'samples': 20311872, 'steps': 105790, 'loss/train': 1.7988272905349731} 08/31/2021 08:27:26 - INFO - __main__ - Step 105792: {'lr': 0.00010223488685191882, 'samples': 20312064, 'steps': 105791, 'loss/train': 0.8397231698036194} 08/31/2021 08:27:27 - INFO - __main__ - Step 105793: {'lr': 0.00010223060632054129, 'samples': 20312256, 'steps': 105792, 'loss/train': 1.1149646043777466} 08/31/2021 08:27:27 - INFO - __main__ - Step 105794: {'lr': 0.00010222632585574638, 'samples': 20312448, 'steps': 105793, 'loss/train': 0.8159704804420471} 08/31/2021 08:27:27 - INFO - __main__ - Step 105795: {'lr': 0.000102222045457536, 'samples': 20312640, 'steps': 105794, 'loss/train': 1.2687913179397583} 08/31/2021 08:27:29 - INFO - __main__ - Step 105796: {'lr': 0.0001022177651259121, 'samples': 20312832, 'steps': 105795, 'loss/train': 1.10648775100708} 08/31/2021 08:27:29 - INFO - __main__ - Step 105797: {'lr': 0.00010221348486087659, 'samples': 20313024, 'steps': 105796, 'loss/train': 0.4647308588027954} 08/31/2021 08:27:30 - INFO - __main__ - Step 105798: {'lr': 0.00010220920466243138, 'samples': 20313216, 'steps': 105797, 'loss/train': 1.4773356914520264} 08/31/2021 08:27:30 - INFO - __main__ - Step 105799: {'lr': 0.00010220492453057845, 'samples': 20313408, 'steps': 105798, 'loss/train': 0.41161060333251953} 08/31/2021 08:27:30 - INFO - __main__ - Step 105800: {'lr': 0.00010220064446531968, 'samples': 20313600, 'steps': 105799, 'loss/train': 1.4612855911254883} 08/31/2021 08:27:32 - INFO - __main__ - Step 105801: {'lr': 0.00010219636446665703, 'samples': 20313792, 'steps': 105800, 'loss/train': 1.4233174324035645} 08/31/2021 08:27:32 - INFO - __main__ - Step 105802: {'lr': 0.0001021920845345925, 'samples': 20313984, 'steps': 105801, 'loss/train': 0.5379604697227478} 08/31/2021 08:27:33 - INFO - __main__ - Step 105803: {'lr': 0.00010218780466912785, 'samples': 20314176, 'steps': 105802, 'loss/train': 0.8775195479393005} 08/31/2021 08:27:33 - INFO - __main__ - Step 105804: {'lr': 0.00010218352487026511, 'samples': 20314368, 'steps': 105803, 'loss/train': 1.42264723777771} 08/31/2021 08:27:33 - INFO - __main__ - Step 105805: {'lr': 0.00010217924513800617, 'samples': 20314560, 'steps': 105804, 'loss/train': 0.45687806606292725} 08/31/2021 08:27:34 - INFO - __main__ - Step 105806: {'lr': 0.000102174965472353, 'samples': 20314752, 'steps': 105805, 'loss/train': 1.174752950668335} 08/31/2021 08:27:36 - INFO - __main__ - Step 105807: {'lr': 0.0001021706858733075, 'samples': 20314944, 'steps': 105806, 'loss/train': 0.2978276014328003} 08/31/2021 08:27:37 - INFO - __main__ - Step 105808: {'lr': 0.00010216640634087159, 'samples': 20315136, 'steps': 105807, 'loss/train': 0.7290779948234558} 08/31/2021 08:27:37 - INFO - __main__ - Step 105809: {'lr': 0.00010216212687504725, 'samples': 20315328, 'steps': 105808, 'loss/train': 1.6351035833358765} 08/31/2021 08:27:37 - INFO - __main__ - Step 105810: {'lr': 0.00010215784747583634, 'samples': 20315520, 'steps': 105809, 'loss/train': 1.0505865812301636} 08/31/2021 08:27:38 - INFO - __main__ - Step 105811: {'lr': 0.00010215356814324084, 'samples': 20315712, 'steps': 105810, 'loss/train': 1.0362316370010376} 08/31/2021 08:27:38 - INFO - __main__ - Step 105812: {'lr': 0.00010214928887726266, 'samples': 20315904, 'steps': 105811, 'loss/train': 0.7800830602645874} 08/31/2021 08:27:40 - INFO - __main__ - Step 105813: {'lr': 0.00010214500967790375, 'samples': 20316096, 'steps': 105812, 'loss/train': 0.058139074593782425} 08/31/2021 08:27:41 - INFO - __main__ - Step 105814: {'lr': 0.00010214073054516598, 'samples': 20316288, 'steps': 105813, 'loss/train': 1.3984251022338867} 08/31/2021 08:27:41 - INFO - __main__ - Step 105815: {'lr': 0.00010213645147905142, 'samples': 20316480, 'steps': 105814, 'loss/train': 1.167860507965088} 08/31/2021 08:27:41 - INFO - __main__ - Step 105816: {'lr': 0.0001021321724795618, 'samples': 20316672, 'steps': 105815, 'loss/train': 0.6360495090484619} 08/31/2021 08:27:42 - INFO - __main__ - Step 105817: {'lr': 0.00010212789354669916, 'samples': 20316864, 'steps': 105816, 'loss/train': 1.1539345979690552} 08/31/2021 08:27:43 - INFO - __main__ - Step 105818: {'lr': 0.0001021236146804654, 'samples': 20317056, 'steps': 105817, 'loss/train': 1.1049823760986328} 08/31/2021 08:27:44 - INFO - __main__ - Step 105819: {'lr': 0.00010211933588086245, 'samples': 20317248, 'steps': 105818, 'loss/train': 1.0179775953292847} 08/31/2021 08:27:44 - INFO - __main__ - Step 105820: {'lr': 0.00010211505714789223, 'samples': 20317440, 'steps': 105819, 'loss/train': 1.1937462091445923} 08/31/2021 08:27:44 - INFO - __main__ - Step 105821: {'lr': 0.00010211077848155672, 'samples': 20317632, 'steps': 105820, 'loss/train': 1.1100448369979858} 08/31/2021 08:27:45 - INFO - __main__ - Step 105822: {'lr': 0.0001021064998818578, 'samples': 20317824, 'steps': 105821, 'loss/train': 0.24499483406543732} 08/31/2021 08:27:46 - INFO - __main__ - Step 105823: {'lr': 0.0001021022213487974, 'samples': 20318016, 'steps': 105822, 'loss/train': 1.2536275386810303} 08/31/2021 08:27:47 - INFO - __main__ - Step 105824: {'lr': 0.00010209794288237745, 'samples': 20318208, 'steps': 105823, 'loss/train': 0.620628833770752} 08/31/2021 08:27:47 - INFO - __main__ - Step 105825: {'lr': 0.00010209366448259991, 'samples': 20318400, 'steps': 105824, 'loss/train': 1.288483738899231} 08/31/2021 08:27:47 - INFO - __main__ - Step 105826: {'lr': 0.00010208938614946667, 'samples': 20318592, 'steps': 105825, 'loss/train': 0.8805475234985352} 08/31/2021 08:27:48 - INFO - __main__ - Step 105827: {'lr': 0.00010208510788297965, 'samples': 20318784, 'steps': 105826, 'loss/train': 0.9814959168434143} 08/31/2021 08:27:49 - INFO - __main__ - Step 105828: {'lr': 0.0001020808296831408, 'samples': 20318976, 'steps': 105827, 'loss/train': 1.2649400234222412} 08/31/2021 08:27:49 - INFO - __main__ - Step 105829: {'lr': 0.00010207655154995216, 'samples': 20319168, 'steps': 105828, 'loss/train': 1.4192919731140137} 08/31/2021 08:27:50 - INFO - __main__ - Step 105830: {'lr': 0.00010207227348341545, 'samples': 20319360, 'steps': 105829, 'loss/train': 1.0578504800796509} 08/31/2021 08:27:50 - INFO - __main__ - Step 105831: {'lr': 0.00010206799548353268, 'samples': 20319552, 'steps': 105830, 'loss/train': 1.839617371559143} 08/31/2021 08:27:51 - INFO - __main__ - Step 105832: {'lr': 0.0001020637175503058, 'samples': 20319744, 'steps': 105831, 'loss/train': 1.0999948978424072} 08/31/2021 08:27:52 - INFO - __main__ - Step 105833: {'lr': 0.0001020594396837367, 'samples': 20319936, 'steps': 105832, 'loss/train': 0.9847355484962463} 08/31/2021 08:27:53 - INFO - __main__ - Step 105834: {'lr': 0.00010205516188382736, 'samples': 20320128, 'steps': 105833, 'loss/train': 1.410720705986023} 08/31/2021 08:27:53 - INFO - __main__ - Step 105835: {'lr': 0.00010205088415057967, 'samples': 20320320, 'steps': 105834, 'loss/train': 1.40143883228302} 08/31/2021 08:27:53 - INFO - __main__ - Step 105836: {'lr': 0.00010204660648399558, 'samples': 20320512, 'steps': 105835, 'loss/train': 1.6461174488067627} 08/31/2021 08:27:54 - INFO - __main__ - Step 105837: {'lr': 0.00010204232888407699, 'samples': 20320704, 'steps': 105836, 'loss/train': 2.24753999710083} 08/31/2021 08:27:55 - INFO - __main__ - Step 105838: {'lr': 0.00010203805135082586, 'samples': 20320896, 'steps': 105837, 'loss/train': 1.067722201347351} 08/31/2021 08:27:55 - INFO - __main__ - Step 105839: {'lr': 0.00010203377388424409, 'samples': 20321088, 'steps': 105838, 'loss/train': 1.5324249267578125} 08/31/2021 08:27:56 - INFO - __main__ - Step 105840: {'lr': 0.00010202949648433363, 'samples': 20321280, 'steps': 105839, 'loss/train': 0.4338209331035614} 08/31/2021 08:27:56 - INFO - __main__ - Step 105841: {'lr': 0.00010202521915109639, 'samples': 20321472, 'steps': 105840, 'loss/train': 0.8687264919281006} 08/31/2021 08:27:57 - INFO - __main__ - Step 105842: {'lr': 0.00010202094188453437, 'samples': 20321664, 'steps': 105841, 'loss/train': 1.1269968748092651} 08/31/2021 08:27:58 - INFO - __main__ - Step 105843: {'lr': 0.00010201666468464937, 'samples': 20321856, 'steps': 105842, 'loss/train': 1.2234523296356201} 08/31/2021 08:27:59 - INFO - __main__ - Step 105844: {'lr': 0.00010201238755144337, 'samples': 20322048, 'steps': 105843, 'loss/train': 1.1651917695999146} 08/31/2021 08:27:59 - INFO - __main__ - Step 105845: {'lr': 0.00010200811048491828, 'samples': 20322240, 'steps': 105844, 'loss/train': 1.1769098043441772} 08/31/2021 08:27:59 - INFO - __main__ - Step 105846: {'lr': 0.00010200383348507607, 'samples': 20322432, 'steps': 105845, 'loss/train': 0.914192259311676} 08/31/2021 08:28:00 - INFO - __main__ - Step 105847: {'lr': 0.00010199955655191867, 'samples': 20322624, 'steps': 105846, 'loss/train': 0.9095439314842224} 08/31/2021 08:28:00 - INFO - __main__ - Step 105848: {'lr': 0.00010199527968544797, 'samples': 20322816, 'steps': 105847, 'loss/train': 0.9583854675292969} 08/31/2021 08:28:01 - INFO - __main__ - Step 105849: {'lr': 0.0001019910028856659, 'samples': 20323008, 'steps': 105848, 'loss/train': 1.7139966487884521} 08/31/2021 08:28:02 - INFO - __main__ - Step 105850: {'lr': 0.00010198672615257443, 'samples': 20323200, 'steps': 105849, 'loss/train': 0.7677218914031982} 08/31/2021 08:28:02 - INFO - __main__ - Step 105851: {'lr': 0.00010198244948617544, 'samples': 20323392, 'steps': 105850, 'loss/train': 0.9656529426574707} 08/31/2021 08:28:03 - INFO - __main__ - Step 105852: {'lr': 0.00010197817288647085, 'samples': 20323584, 'steps': 105851, 'loss/train': 0.7761653661727905} 08/31/2021 08:28:03 - INFO - __main__ - Step 105853: {'lr': 0.00010197389635346263, 'samples': 20323776, 'steps': 105852, 'loss/train': 1.409069538116455} 08/31/2021 08:28:05 - INFO - __main__ - Step 105854: {'lr': 0.0001019696198871527, 'samples': 20323968, 'steps': 105853, 'loss/train': 1.0835645198822021} 08/31/2021 08:28:05 - INFO - __main__ - Step 105855: {'lr': 0.00010196534348754296, 'samples': 20324160, 'steps': 105854, 'loss/train': 1.1196845769882202} 08/31/2021 08:28:05 - INFO - __main__ - Step 105856: {'lr': 0.00010196106715463546, 'samples': 20324352, 'steps': 105855, 'loss/train': 1.0150002241134644} 08/31/2021 08:28:06 - INFO - __main__ - Step 105857: {'lr': 0.0001019567908884319, 'samples': 20324544, 'steps': 105856, 'loss/train': 1.2561067342758179} 08/31/2021 08:28:06 - INFO - __main__ - Step 105858: {'lr': 0.00010195251468893435, 'samples': 20324736, 'steps': 105857, 'loss/train': 0.040821727365255356} 08/31/2021 08:28:08 - INFO - __main__ - Step 105859: {'lr': 0.00010194823855614471, 'samples': 20324928, 'steps': 105858, 'loss/train': 0.42933064699172974} 08/31/2021 08:28:09 - INFO - __main__ - Step 105860: {'lr': 0.00010194396249006491, 'samples': 20325120, 'steps': 105859, 'loss/train': 0.05780196189880371} 08/31/2021 08:28:09 - INFO - __main__ - Step 105861: {'lr': 0.00010193968649069688, 'samples': 20325312, 'steps': 105860, 'loss/train': 1.5732296705245972} 08/31/2021 08:28:09 - INFO - __main__ - Step 105862: {'lr': 0.00010193541055804254, 'samples': 20325504, 'steps': 105861, 'loss/train': 0.5694838166236877} 08/31/2021 08:28:10 - INFO - __main__ - Step 105863: {'lr': 0.0001019311346921038, 'samples': 20325696, 'steps': 105862, 'loss/train': 1.154905915260315} 08/31/2021 08:28:12 - INFO - __main__ - Step 105864: {'lr': 0.00010192685889288261, 'samples': 20325888, 'steps': 105863, 'loss/train': 1.2234406471252441} 08/31/2021 08:28:12 - INFO - __main__ - Step 105865: {'lr': 0.00010192258316038091, 'samples': 20326080, 'steps': 105864, 'loss/train': 1.342454433441162} 08/31/2021 08:28:12 - INFO - __main__ - Step 105866: {'lr': 0.00010191830749460059, 'samples': 20326272, 'steps': 105865, 'loss/train': 0.6809442639350891} 08/31/2021 08:28:13 - INFO - __main__ - Step 105867: {'lr': 0.00010191403189554361, 'samples': 20326464, 'steps': 105866, 'loss/train': 1.4299641847610474} 08/31/2021 08:28:13 - INFO - __main__ - Step 105868: {'lr': 0.00010190975636321187, 'samples': 20326656, 'steps': 105867, 'loss/train': 1.065779685974121} 08/31/2021 08:28:14 - INFO - __main__ - Step 105869: {'lr': 0.00010190548089760743, 'samples': 20326848, 'steps': 105868, 'loss/train': 0.13165701925754547} 08/31/2021 08:28:15 - INFO - __main__ - Step 105870: {'lr': 0.00010190120549873198, 'samples': 20327040, 'steps': 105869, 'loss/train': 0.9324557781219482} 08/31/2021 08:28:16 - INFO - __main__ - Step 105871: {'lr': 0.00010189693016658755, 'samples': 20327232, 'steps': 105870, 'loss/train': 1.0006561279296875} 08/31/2021 08:28:16 - INFO - __main__ - Step 105872: {'lr': 0.00010189265490117607, 'samples': 20327424, 'steps': 105871, 'loss/train': 1.5631976127624512} 08/31/2021 08:28:16 - INFO - __main__ - Step 105873: {'lr': 0.0001018883797024995, 'samples': 20327616, 'steps': 105872, 'loss/train': 1.7638089656829834} 08/31/2021 08:28:17 - INFO - __main__ - Step 105874: {'lr': 0.00010188410457055975, 'samples': 20327808, 'steps': 105873, 'loss/train': 1.3548710346221924} 08/31/2021 08:28:18 - INFO - __main__ - Step 105875: {'lr': 0.00010187982950535873, 'samples': 20328000, 'steps': 105874, 'loss/train': 1.1661738157272339} 08/31/2021 08:28:19 - INFO - __main__ - Step 105876: {'lr': 0.00010187555450689836, 'samples': 20328192, 'steps': 105875, 'loss/train': 1.9316705465316772} 08/31/2021 08:28:19 - INFO - __main__ - Step 105877: {'lr': 0.00010187127957518058, 'samples': 20328384, 'steps': 105876, 'loss/train': 1.970819115638733} 08/31/2021 08:28:20 - INFO - __main__ - Step 105878: {'lr': 0.00010186700471020733, 'samples': 20328576, 'steps': 105877, 'loss/train': 0.7902805209159851} 08/31/2021 08:28:20 - INFO - __main__ - Step 105879: {'lr': 0.0001018627299119805, 'samples': 20328768, 'steps': 105878, 'loss/train': 1.0747745037078857} 08/31/2021 08:28:21 - INFO - __main__ - Step 105880: {'lr': 0.00010185845518050216, 'samples': 20328960, 'steps': 105879, 'loss/train': 0.46492183208465576} 08/31/2021 08:28:22 - INFO - __main__ - Step 105881: {'lr': 0.00010185418051577399, 'samples': 20329152, 'steps': 105880, 'loss/train': 0.4176916480064392} 08/31/2021 08:28:22 - INFO - __main__ - Step 105882: {'lr': 0.00010184990591779805, 'samples': 20329344, 'steps': 105881, 'loss/train': 1.5485703945159912} 08/31/2021 08:28:23 - INFO - __main__ - Step 105883: {'lr': 0.00010184563138657627, 'samples': 20329536, 'steps': 105882, 'loss/train': 1.236082911491394} 08/31/2021 08:28:23 - INFO - __main__ - Step 105884: {'lr': 0.00010184135692211055, 'samples': 20329728, 'steps': 105883, 'loss/train': 1.1052988767623901} 08/31/2021 08:28:25 - INFO - __main__ - Step 105885: {'lr': 0.00010183708252440282, 'samples': 20329920, 'steps': 105884, 'loss/train': 1.0678131580352783} 08/31/2021 08:28:25 - INFO - __main__ - Step 105886: {'lr': 0.00010183280819345503, 'samples': 20330112, 'steps': 105885, 'loss/train': 1.0478944778442383} 08/31/2021 08:28:26 - INFO - __main__ - Step 105887: {'lr': 0.00010182853392926909, 'samples': 20330304, 'steps': 105886, 'loss/train': 1.1536473035812378} 08/31/2021 08:28:26 - INFO - __main__ - Step 105888: {'lr': 0.00010182425973184692, 'samples': 20330496, 'steps': 105887, 'loss/train': 1.227690577507019} 08/31/2021 08:28:26 - INFO - __main__ - Step 105889: {'lr': 0.00010181998560119046, 'samples': 20330688, 'steps': 105888, 'loss/train': 1.148419976234436} 08/31/2021 08:28:28 - INFO - __main__ - Step 105890: {'lr': 0.00010181571153730163, 'samples': 20330880, 'steps': 105889, 'loss/train': 1.1142857074737549} 08/31/2021 08:28:28 - INFO - __main__ - Step 105891: {'lr': 0.00010181143754018243, 'samples': 20331072, 'steps': 105890, 'loss/train': 1.0141353607177734} 08/31/2021 08:28:29 - INFO - __main__ - Step 105892: {'lr': 0.00010180716360983463, 'samples': 20331264, 'steps': 105891, 'loss/train': 1.3615248203277588} 08/31/2021 08:28:29 - INFO - __main__ - Step 105893: {'lr': 0.00010180288974626023, 'samples': 20331456, 'steps': 105892, 'loss/train': 0.6123162508010864} 08/31/2021 08:28:29 - INFO - __main__ - Step 105894: {'lr': 0.00010179861594946116, 'samples': 20331648, 'steps': 105893, 'loss/train': 0.7138718962669373} 08/31/2021 08:28:31 - INFO - __main__ - Step 105895: {'lr': 0.00010179434221943935, 'samples': 20331840, 'steps': 105894, 'loss/train': 0.18136653304100037} 08/31/2021 08:28:31 - INFO - __main__ - Step 105896: {'lr': 0.00010179006855619672, 'samples': 20332032, 'steps': 105895, 'loss/train': 1.3744920492172241} 08/31/2021 08:28:32 - INFO - __main__ - Step 105897: {'lr': 0.0001017857949597352, 'samples': 20332224, 'steps': 105896, 'loss/train': 0.835102915763855} 08/31/2021 08:28:32 - INFO - __main__ - Step 105898: {'lr': 0.0001017815214300567, 'samples': 20332416, 'steps': 105897, 'loss/train': 0.04491141811013222} 08/31/2021 08:28:32 - INFO - __main__ - Step 105899: {'lr': 0.00010177724796716317, 'samples': 20332608, 'steps': 105898, 'loss/train': 0.509750247001648} 08/31/2021 08:28:34 - INFO - __main__ - Step 105900: {'lr': 0.00010177297457105656, 'samples': 20332800, 'steps': 105899, 'loss/train': 1.4845826625823975} 08/31/2021 08:28:34 - INFO - __main__ - Step 105901: {'lr': 0.00010176870124173878, 'samples': 20332992, 'steps': 105900, 'loss/train': 0.3400064706802368} 08/31/2021 08:28:35 - INFO - __main__ - Step 105902: {'lr': 0.0001017644279792117, 'samples': 20333184, 'steps': 105901, 'loss/train': 1.6660616397857666} 08/31/2021 08:28:35 - INFO - __main__ - Step 105903: {'lr': 0.00010176015478347728, 'samples': 20333376, 'steps': 105902, 'loss/train': 0.9504784345626831} 08/31/2021 08:28:35 - INFO - __main__ - Step 105904: {'lr': 0.00010175588165453741, 'samples': 20333568, 'steps': 105903, 'loss/train': 0.8233919143676758} 08/31/2021 08:28:37 - INFO - __main__ - Step 105905: {'lr': 0.00010175160859239407, 'samples': 20333760, 'steps': 105904, 'loss/train': 1.2819597721099854} 08/31/2021 08:28:38 - INFO - __main__ - Step 105906: {'lr': 0.00010174733559704919, 'samples': 20333952, 'steps': 105905, 'loss/train': 0.7360233068466187} 08/31/2021 08:28:38 - INFO - __main__ - Step 105907: {'lr': 0.00010174306266850464, 'samples': 20334144, 'steps': 105906, 'loss/train': 0.014915554784238338} 08/31/2021 08:28:39 - INFO - __main__ - Step 105908: {'lr': 0.00010173878980676241, 'samples': 20334336, 'steps': 105907, 'loss/train': 1.6216168403625488} 08/31/2021 08:28:39 - INFO - __main__ - Step 105909: {'lr': 0.00010173451701182437, 'samples': 20334528, 'steps': 105908, 'loss/train': 1.0955029726028442} 08/31/2021 08:28:39 - INFO - __main__ - Step 105910: {'lr': 0.00010173024428369245, 'samples': 20334720, 'steps': 105909, 'loss/train': 0.4718729853630066} 08/31/2021 08:28:40 - INFO - __main__ - Step 105911: {'lr': 0.00010172597162236863, 'samples': 20334912, 'steps': 105910, 'loss/train': 2.9141929149627686} 08/31/2021 08:28:40 - INFO - __main__ - Step 105912: {'lr': 0.00010172169902785488, 'samples': 20335104, 'steps': 105911, 'loss/train': 2.845102310180664} 08/31/2021 08:28:42 - INFO - __main__ - Step 105913: {'lr': 0.00010171742650015295, 'samples': 20335296, 'steps': 105912, 'loss/train': 1.3658545017242432} 08/31/2021 08:28:42 - INFO - __main__ - Step 105914: {'lr': 0.00010171315403926487, 'samples': 20335488, 'steps': 105913, 'loss/train': 1.1545339822769165} 08/31/2021 08:28:43 - INFO - __main__ - Step 105915: {'lr': 0.00010170888164519254, 'samples': 20335680, 'steps': 105914, 'loss/train': 1.1796385049819946} 08/31/2021 08:28:43 - INFO - __main__ - Step 105916: {'lr': 0.0001017046093179379, 'samples': 20335872, 'steps': 105915, 'loss/train': 1.6141855716705322} 08/31/2021 08:28:43 - INFO - __main__ - Step 105917: {'lr': 0.0001017003370575029, 'samples': 20336064, 'steps': 105916, 'loss/train': 0.7932843565940857} 08/31/2021 08:28:45 - INFO - __main__ - Step 105918: {'lr': 0.0001016960648638894, 'samples': 20336256, 'steps': 105917, 'loss/train': 0.9319802522659302} 08/31/2021 08:28:45 - INFO - __main__ - Step 105919: {'lr': 0.00010169179273709942, 'samples': 20336448, 'steps': 105918, 'loss/train': 1.4295625686645508} 08/31/2021 08:28:45 - INFO - __main__ - Step 105920: {'lr': 0.00010168752067713477, 'samples': 20336640, 'steps': 105919, 'loss/train': 1.2458573579788208} 08/31/2021 08:28:46 - INFO - __main__ - Step 105921: {'lr': 0.00010168324868399748, 'samples': 20336832, 'steps': 105920, 'loss/train': 1.0068027973175049} 08/31/2021 08:28:46 - INFO - __main__ - Step 105922: {'lr': 0.00010167897675768939, 'samples': 20337024, 'steps': 105921, 'loss/train': 1.3831347227096558} 08/31/2021 08:28:48 - INFO - __main__ - Step 105923: {'lr': 0.00010167470489821257, 'samples': 20337216, 'steps': 105922, 'loss/train': 1.2000303268432617} 08/31/2021 08:28:49 - INFO - __main__ - Step 105924: {'lr': 0.00010167043310556875, 'samples': 20337408, 'steps': 105923, 'loss/train': 1.1754508018493652} 08/31/2021 08:28:49 - INFO - __main__ - Step 105925: {'lr': 0.00010166616137975995, 'samples': 20337600, 'steps': 105924, 'loss/train': 1.2414637804031372} 08/31/2021 08:28:49 - INFO - __main__ - Step 105926: {'lr': 0.00010166188972078811, 'samples': 20337792, 'steps': 105925, 'loss/train': 1.002989649772644} 08/31/2021 08:28:50 - INFO - __main__ - Step 105927: {'lr': 0.00010165761812865509, 'samples': 20337984, 'steps': 105926, 'loss/train': 0.8144569993019104} 08/31/2021 08:28:51 - INFO - __main__ - Step 105928: {'lr': 0.00010165334660336287, 'samples': 20338176, 'steps': 105927, 'loss/train': 0.43418028950691223} 08/31/2021 08:28:52 - INFO - __main__ - Step 105929: {'lr': 0.00010164907514491337, 'samples': 20338368, 'steps': 105928, 'loss/train': 1.0027796030044556} 08/31/2021 08:28:52 - INFO - __main__ - Step 105930: {'lr': 0.0001016448037533085, 'samples': 20338560, 'steps': 105929, 'loss/train': 1.6501601934432983} 08/31/2021 08:28:52 - INFO - __main__ - Step 105931: {'lr': 0.0001016405324285502, 'samples': 20338752, 'steps': 105930, 'loss/train': 1.6280778646469116} 08/31/2021 08:28:53 - INFO - __main__ - Step 105932: {'lr': 0.0001016362611706404, 'samples': 20338944, 'steps': 105931, 'loss/train': 0.29861003160476685} 08/31/2021 08:28:54 - INFO - __main__ - Step 105933: {'lr': 0.00010163198997958101, 'samples': 20339136, 'steps': 105932, 'loss/train': 1.3045802116394043} 08/31/2021 08:28:55 - INFO - __main__ - Step 105934: {'lr': 0.00010162771885537392, 'samples': 20339328, 'steps': 105933, 'loss/train': 1.6871742010116577} 08/31/2021 08:28:55 - INFO - __main__ - Step 105935: {'lr': 0.00010162344779802113, 'samples': 20339520, 'steps': 105934, 'loss/train': 2.406541347503662} 08/31/2021 08:28:55 - INFO - __main__ - Step 105936: {'lr': 0.00010161917680752458, 'samples': 20339712, 'steps': 105935, 'loss/train': 0.2540208101272583} 08/31/2021 08:28:56 - INFO - __main__ - Step 105937: {'lr': 0.00010161490588388609, 'samples': 20339904, 'steps': 105936, 'loss/train': 1.261778473854065} 08/31/2021 08:28:57 - INFO - __main__ - Step 105938: {'lr': 0.0001016106350271076, 'samples': 20340096, 'steps': 105937, 'loss/train': 0.691156804561615} 08/31/2021 08:28:58 - INFO - __main__ - Step 105939: {'lr': 0.00010160636423719108, 'samples': 20340288, 'steps': 105938, 'loss/train': 1.2523516416549683} 08/31/2021 08:28:58 - INFO - __main__ - Step 105940: {'lr': 0.00010160209351413843, 'samples': 20340480, 'steps': 105939, 'loss/train': 0.945038914680481} 08/31/2021 08:28:58 - INFO - __main__ - Step 105941: {'lr': 0.0001015978228579516, 'samples': 20340672, 'steps': 105940, 'loss/train': 1.0896341800689697} 08/31/2021 08:28:59 - INFO - __main__ - Step 105942: {'lr': 0.0001015935522686325, 'samples': 20340864, 'steps': 105941, 'loss/train': 0.4041142761707306} 08/31/2021 08:28:59 - INFO - __main__ - Step 105943: {'lr': 0.00010158928174618307, 'samples': 20341056, 'steps': 105942, 'loss/train': 2.6844451427459717} 08/31/2021 08:29:01 - INFO - __main__ - Step 105944: {'lr': 0.00010158501129060521, 'samples': 20341248, 'steps': 105943, 'loss/train': 1.3049217462539673} 08/31/2021 08:29:02 - INFO - __main__ - Step 105945: {'lr': 0.00010158074090190084, 'samples': 20341440, 'steps': 105944, 'loss/train': 0.10351524502038956} 08/31/2021 08:29:02 - INFO - __main__ - Step 105946: {'lr': 0.00010157647058007192, 'samples': 20341632, 'steps': 105945, 'loss/train': 2.0285773277282715} 08/31/2021 08:29:03 - INFO - __main__ - Step 105947: {'lr': 0.00010157220032512033, 'samples': 20341824, 'steps': 105946, 'loss/train': 1.2245593070983887} 08/31/2021 08:29:03 - INFO - __main__ - Step 105948: {'lr': 0.00010156793013704802, 'samples': 20342016, 'steps': 105947, 'loss/train': 0.06700818240642548} 08/31/2021 08:29:03 - INFO - __main__ - Step 105949: {'lr': 0.0001015636600158569, 'samples': 20342208, 'steps': 105948, 'loss/train': 1.4658575057983398} 08/31/2021 08:29:04 - INFO - __main__ - Step 105950: {'lr': 0.00010155938996154904, 'samples': 20342400, 'steps': 105949, 'loss/train': 0.697708785533905} 08/31/2021 08:29:05 - INFO - __main__ - Step 105951: {'lr': 0.00010155511997412609, 'samples': 20342592, 'steps': 105950, 'loss/train': 0.5670025944709778} 08/31/2021 08:29:06 - INFO - __main__ - Step 105952: {'lr': 0.00010155085005359013, 'samples': 20342784, 'steps': 105951, 'loss/train': 0.940995991230011} 08/31/2021 08:29:06 - INFO - __main__ - Step 105953: {'lr': 0.00010154658019994306, 'samples': 20342976, 'steps': 105952, 'loss/train': 1.1719897985458374} 08/31/2021 08:29:06 - INFO - __main__ - Step 105954: {'lr': 0.00010154231041318681, 'samples': 20343168, 'steps': 105953, 'loss/train': 0.9386411309242249} 08/31/2021 08:29:07 - INFO - __main__ - Step 105955: {'lr': 0.00010153804069332332, 'samples': 20343360, 'steps': 105954, 'loss/train': 0.903531014919281} 08/31/2021 08:29:08 - INFO - __main__ - Step 105956: {'lr': 0.0001015337710403545, 'samples': 20343552, 'steps': 105955, 'loss/train': 1.0442962646484375} 08/31/2021 08:29:09 - INFO - __main__ - Step 105957: {'lr': 0.00010152950145428224, 'samples': 20343744, 'steps': 105956, 'loss/train': 1.234002947807312} 08/31/2021 08:29:09 - INFO - __main__ - Step 105958: {'lr': 0.00010152523193510852, 'samples': 20343936, 'steps': 105957, 'loss/train': 0.5667851567268372} 08/31/2021 08:29:09 - INFO - __main__ - Step 105959: {'lr': 0.00010152096248283524, 'samples': 20344128, 'steps': 105958, 'loss/train': 1.0565162897109985} 08/31/2021 08:29:10 - INFO - __main__ - Step 105960: {'lr': 0.0001015166930974643, 'samples': 20344320, 'steps': 105959, 'loss/train': 0.23158344626426697} 08/31/2021 08:29:11 - INFO - __main__ - Step 105961: {'lr': 0.00010151242377899769, 'samples': 20344512, 'steps': 105960, 'loss/train': 1.756416916847229} 08/31/2021 08:29:12 - INFO - __main__ - Step 105962: {'lr': 0.00010150815452743725, 'samples': 20344704, 'steps': 105961, 'loss/train': 1.6148878335952759} 08/31/2021 08:29:12 - INFO - __main__ - Step 105963: {'lr': 0.00010150388534278507, 'samples': 20344896, 'steps': 105962, 'loss/train': 0.7668377757072449} 08/31/2021 08:29:12 - INFO - __main__ - Step 105964: {'lr': 0.00010149961622504283, 'samples': 20345088, 'steps': 105963, 'loss/train': 1.595459222793579} 08/31/2021 08:29:13 - INFO - __main__ - Step 105965: {'lr': 0.00010149534717421257, 'samples': 20345280, 'steps': 105964, 'loss/train': 1.0742850303649902} 08/31/2021 08:29:14 - INFO - __main__ - Step 105966: {'lr': 0.00010149107819029623, 'samples': 20345472, 'steps': 105965, 'loss/train': 0.8017987012863159} 08/31/2021 08:29:15 - INFO - __main__ - Step 105967: {'lr': 0.0001014868092732957, 'samples': 20345664, 'steps': 105966, 'loss/train': 0.532289981842041} 08/31/2021 08:29:15 - INFO - __main__ - Step 105968: {'lr': 0.00010148254042321295, 'samples': 20345856, 'steps': 105967, 'loss/train': 1.571904182434082} 08/31/2021 08:29:16 - INFO - __main__ - Step 105969: {'lr': 0.00010147827164004986, 'samples': 20346048, 'steps': 105968, 'loss/train': 1.322590708732605} 08/31/2021 08:29:16 - INFO - __main__ - Step 105970: {'lr': 0.00010147400292380837, 'samples': 20346240, 'steps': 105969, 'loss/train': 1.4826105833053589} 08/31/2021 08:29:16 - INFO - __main__ - Step 105971: {'lr': 0.00010146973427449039, 'samples': 20346432, 'steps': 105970, 'loss/train': 0.9043594598770142} 08/31/2021 08:29:18 - INFO - __main__ - Step 105972: {'lr': 0.00010146546569209789, 'samples': 20346624, 'steps': 105971, 'loss/train': 0.8835033774375916} 08/31/2021 08:29:18 - INFO - __main__ - Step 105973: {'lr': 0.00010146119717663271, 'samples': 20346816, 'steps': 105972, 'loss/train': 1.53104829788208} 08/31/2021 08:29:19 - INFO - __main__ - Step 105974: {'lr': 0.00010145692872809687, 'samples': 20347008, 'steps': 105973, 'loss/train': 0.5940052270889282} 08/31/2021 08:29:19 - INFO - __main__ - Step 105975: {'lr': 0.00010145266034649223, 'samples': 20347200, 'steps': 105974, 'loss/train': 0.8558434844017029} 08/31/2021 08:29:19 - INFO - __main__ - Step 105976: {'lr': 0.00010144839203182071, 'samples': 20347392, 'steps': 105975, 'loss/train': 1.5744469165802002} 08/31/2021 08:29:21 - INFO - __main__ - Step 105977: {'lr': 0.00010144412378408436, 'samples': 20347584, 'steps': 105976, 'loss/train': 0.9732472896575928} 08/31/2021 08:29:22 - INFO - __main__ - Step 105978: {'lr': 0.00010143985560328489, 'samples': 20347776, 'steps': 105977, 'loss/train': 1.2990840673446655} 08/31/2021 08:29:22 - INFO - __main__ - Step 105979: {'lr': 0.00010143558748942433, 'samples': 20347968, 'steps': 105978, 'loss/train': 1.4575457572937012} 08/31/2021 08:29:23 - INFO - __main__ - Step 105980: {'lr': 0.00010143131944250463, 'samples': 20348160, 'steps': 105979, 'loss/train': 0.8659235239028931} 08/31/2021 08:29:23 - INFO - __main__ - Step 105981: {'lr': 0.00010142705146252764, 'samples': 20348352, 'steps': 105980, 'loss/train': 0.42158055305480957} 08/31/2021 08:29:24 - INFO - __main__ - Step 105982: {'lr': 0.00010142278354949538, 'samples': 20348544, 'steps': 105981, 'loss/train': 1.14264976978302} 08/31/2021 08:29:25 - INFO - __main__ - Step 105983: {'lr': 0.00010141851570340967, 'samples': 20348736, 'steps': 105982, 'loss/train': 0.9328215718269348} 08/31/2021 08:29:25 - INFO - __main__ - Step 105984: {'lr': 0.00010141424792427253, 'samples': 20348928, 'steps': 105983, 'loss/train': 1.275865077972412} 08/31/2021 08:29:26 - INFO - __main__ - Step 105985: {'lr': 0.0001014099802120858, 'samples': 20349120, 'steps': 105984, 'loss/train': 0.593533992767334} 08/31/2021 08:29:26 - INFO - __main__ - Step 105986: {'lr': 0.00010140571256685147, 'samples': 20349312, 'steps': 105985, 'loss/train': 0.9513514041900635} 08/31/2021 08:29:27 - INFO - __main__ - Step 105987: {'lr': 0.00010140144498857142, 'samples': 20349504, 'steps': 105986, 'loss/train': 1.2339164018630981} 08/31/2021 08:29:28 - INFO - __main__ - Step 105988: {'lr': 0.00010139717747724758, 'samples': 20349696, 'steps': 105987, 'loss/train': 1.1459558010101318} 08/31/2021 08:29:28 - INFO - __main__ - Step 105989: {'lr': 0.00010139291003288189, 'samples': 20349888, 'steps': 105988, 'loss/train': 1.341751217842102} 08/31/2021 08:29:29 - INFO - __main__ - Step 105990: {'lr': 0.00010138864265547635, 'samples': 20350080, 'steps': 105989, 'loss/train': 1.256232500076294} 08/31/2021 08:29:29 - INFO - __main__ - Step 105991: {'lr': 0.0001013843753450327, 'samples': 20350272, 'steps': 105990, 'loss/train': 2.669072389602661} 08/31/2021 08:29:30 - INFO - __main__ - Step 105992: {'lr': 0.00010138010810155296, 'samples': 20350464, 'steps': 105991, 'loss/train': 1.1601581573486328} 08/31/2021 08:29:31 - INFO - __main__ - Step 105993: {'lr': 0.00010137584092503905, 'samples': 20350656, 'steps': 105992, 'loss/train': 1.438899278640747} 08/31/2021 08:29:31 - INFO - __main__ - Step 105994: {'lr': 0.00010137157381549289, 'samples': 20350848, 'steps': 105993, 'loss/train': 1.3550945520401} 08/31/2021 08:29:32 - INFO - __main__ - Step 105995: {'lr': 0.00010136730677291639, 'samples': 20351040, 'steps': 105994, 'loss/train': 1.8988783359527588} 08/31/2021 08:29:32 - INFO - __main__ - Step 105996: {'lr': 0.00010136303979731151, 'samples': 20351232, 'steps': 105995, 'loss/train': 1.0856050252914429} 08/31/2021 08:29:33 - INFO - __main__ - Step 105997: {'lr': 0.00010135877288868014, 'samples': 20351424, 'steps': 105996, 'loss/train': 0.7624516487121582} 08/31/2021 08:29:34 - INFO - __main__ - Step 105998: {'lr': 0.00010135450604702424, 'samples': 20351616, 'steps': 105997, 'loss/train': 1.457175612449646} 08/31/2021 08:29:34 - INFO - __main__ - Step 105999: {'lr': 0.00010135023927234565, 'samples': 20351808, 'steps': 105998, 'loss/train': 1.0875897407531738} 08/31/2021 08:29:35 - INFO - __main__ - Step 106000: {'lr': 0.0001013459725646464, 'samples': 20352000, 'steps': 105999, 'loss/train': 1.1052793264389038} 08/31/2021 08:29:35 - INFO - __main__ - Step 106001: {'lr': 0.00010134170592392835, 'samples': 20352192, 'steps': 106000, 'loss/train': 1.5506471395492554} 08/31/2021 08:29:36 - INFO - __main__ - Step 106002: {'lr': 0.00010133743935019343, 'samples': 20352384, 'steps': 106001, 'loss/train': 1.6864479780197144} 08/31/2021 08:29:37 - INFO - __main__ - Step 106003: {'lr': 0.00010133317284344365, 'samples': 20352576, 'steps': 106002, 'loss/train': 1.3654860258102417} 08/31/2021 08:29:37 - INFO - __main__ - Step 106004: {'lr': 0.00010132890640368075, 'samples': 20352768, 'steps': 106003, 'loss/train': 1.569750189781189} 08/31/2021 08:29:38 - INFO - __main__ - Step 106005: {'lr': 0.00010132464003090677, 'samples': 20352960, 'steps': 106004, 'loss/train': 1.016880989074707} 08/31/2021 08:29:38 - INFO - __main__ - Step 106006: {'lr': 0.00010132037372512359, 'samples': 20353152, 'steps': 106005, 'loss/train': 1.2961968183517456} 08/31/2021 08:29:40 - INFO - __main__ - Step 106007: {'lr': 0.00010131610748633319, 'samples': 20353344, 'steps': 106006, 'loss/train': 1.131701111793518} 08/31/2021 08:29:40 - INFO - __main__ - Step 106008: {'lr': 0.00010131184131453741, 'samples': 20353536, 'steps': 106007, 'loss/train': 1.3171021938323975} 08/31/2021 08:29:40 - INFO - __main__ - Step 106009: {'lr': 0.00010130757520973826, 'samples': 20353728, 'steps': 106008, 'loss/train': 0.7268537878990173} 08/31/2021 08:29:41 - INFO - __main__ - Step 106010: {'lr': 0.00010130330917193762, 'samples': 20353920, 'steps': 106009, 'loss/train': 0.45797207951545715} 08/31/2021 08:29:41 - INFO - __main__ - Step 106011: {'lr': 0.00010129904320113739, 'samples': 20354112, 'steps': 106010, 'loss/train': 2.2111825942993164} 08/31/2021 08:29:41 - INFO - __main__ - Step 106012: {'lr': 0.00010129477729733951, 'samples': 20354304, 'steps': 106011, 'loss/train': 1.3777769804000854} 08/31/2021 08:29:43 - INFO - __main__ - Step 106013: {'lr': 0.00010129051146054594, 'samples': 20354496, 'steps': 106012, 'loss/train': 1.4199941158294678} 08/31/2021 08:29:43 - INFO - __main__ - Step 106014: {'lr': 0.00010128624569075856, 'samples': 20354688, 'steps': 106013, 'loss/train': 0.6301577091217041} 08/31/2021 08:29:44 - INFO - __main__ - Step 106015: {'lr': 0.00010128197998797931, 'samples': 20354880, 'steps': 106014, 'loss/train': 0.9005060791969299} 08/31/2021 08:29:44 - INFO - __main__ - Step 106016: {'lr': 0.00010127771435221009, 'samples': 20355072, 'steps': 106015, 'loss/train': 0.6761646866798401} 08/31/2021 08:29:45 - INFO - __main__ - Step 106017: {'lr': 0.00010127344878345294, 'samples': 20355264, 'steps': 106016, 'loss/train': 0.04342183470726013} 08/31/2021 08:29:46 - INFO - __main__ - Step 106018: {'lr': 0.00010126918328170959, 'samples': 20355456, 'steps': 106017, 'loss/train': 1.3053449392318726} 08/31/2021 08:29:47 - INFO - __main__ - Step 106019: {'lr': 0.00010126491784698202, 'samples': 20355648, 'steps': 106018, 'loss/train': 1.6854811906814575} 08/31/2021 08:29:47 - INFO - __main__ - Step 106020: {'lr': 0.00010126065247927222, 'samples': 20355840, 'steps': 106019, 'loss/train': 1.121501088142395} 08/31/2021 08:29:47 - INFO - __main__ - Step 106021: {'lr': 0.00010125638717858208, 'samples': 20356032, 'steps': 106020, 'loss/train': 1.3924068212509155} 08/31/2021 08:29:48 - INFO - __main__ - Step 106022: {'lr': 0.00010125212194491349, 'samples': 20356224, 'steps': 106021, 'loss/train': 0.8798534870147705} 08/31/2021 08:29:49 - INFO - __main__ - Step 106023: {'lr': 0.0001012478567782684, 'samples': 20356416, 'steps': 106022, 'loss/train': 1.0213900804519653} 08/31/2021 08:29:50 - INFO - __main__ - Step 106024: {'lr': 0.00010124359167864875, 'samples': 20356608, 'steps': 106023, 'loss/train': 0.276519238948822} 08/31/2021 08:29:50 - INFO - __main__ - Step 106025: {'lr': 0.00010123932664605642, 'samples': 20356800, 'steps': 106024, 'loss/train': 0.7261303067207336} 08/31/2021 08:29:50 - INFO - __main__ - Step 106026: {'lr': 0.00010123506168049334, 'samples': 20356992, 'steps': 106025, 'loss/train': 1.3989979028701782} 08/31/2021 08:29:51 - INFO - __main__ - Step 106027: {'lr': 0.00010123079678196149, 'samples': 20357184, 'steps': 106026, 'loss/train': 0.5811588168144226} 08/31/2021 08:29:52 - INFO - __main__ - Step 106028: {'lr': 0.00010122653195046272, 'samples': 20357376, 'steps': 106027, 'loss/train': 1.3984217643737793} 08/31/2021 08:29:53 - INFO - __main__ - Step 106029: {'lr': 0.00010122226718599901, 'samples': 20357568, 'steps': 106028, 'loss/train': 1.0645039081573486} 08/31/2021 08:29:53 - INFO - __main__ - Step 106030: {'lr': 0.0001012180024885723, 'samples': 20357760, 'steps': 106029, 'loss/train': 1.1358023881912231} 08/31/2021 08:29:53 - INFO - __main__ - Step 106031: {'lr': 0.00010121373785818439, 'samples': 20357952, 'steps': 106030, 'loss/train': 0.5555463433265686} 08/31/2021 08:29:54 - INFO - __main__ - Step 106032: {'lr': 0.00010120947329483727, 'samples': 20358144, 'steps': 106031, 'loss/train': 1.420164704322815} 08/31/2021 08:29:56 - INFO - __main__ - Step 106033: {'lr': 0.00010120520879853287, 'samples': 20358336, 'steps': 106032, 'loss/train': 0.4066040515899658} 08/31/2021 08:29:56 - INFO - __main__ - Step 106034: {'lr': 0.0001012009443692731, 'samples': 20358528, 'steps': 106033, 'loss/train': 1.116875410079956} 08/31/2021 08:29:57 - INFO - __main__ - Step 106035: {'lr': 0.0001011966800070599, 'samples': 20358720, 'steps': 106034, 'loss/train': 1.198990821838379} 08/31/2021 08:29:57 - INFO - __main__ - Step 106036: {'lr': 0.00010119241571189517, 'samples': 20358912, 'steps': 106035, 'loss/train': 1.364976167678833} 08/31/2021 08:29:57 - INFO - __main__ - Step 106037: {'lr': 0.00010118815148378082, 'samples': 20359104, 'steps': 106036, 'loss/train': 0.9980375170707703} 08/31/2021 08:29:59 - INFO - __main__ - Step 106038: {'lr': 0.00010118388732271882, 'samples': 20359296, 'steps': 106037, 'loss/train': 1.113005518913269} 08/31/2021 08:29:59 - INFO - __main__ - Step 106039: {'lr': 0.00010117962322871107, 'samples': 20359488, 'steps': 106038, 'loss/train': 1.283774733543396} 08/31/2021 08:30:00 - INFO - __main__ - Step 106040: {'lr': 0.00010117535920175946, 'samples': 20359680, 'steps': 106039, 'loss/train': 0.3154667913913727} 08/31/2021 08:30:00 - INFO - __main__ - Step 106041: {'lr': 0.00010117109524186596, 'samples': 20359872, 'steps': 106040, 'loss/train': 0.8084431886672974} 08/31/2021 08:30:00 - INFO - __main__ - Step 106042: {'lr': 0.00010116683134903246, 'samples': 20360064, 'steps': 106041, 'loss/train': 1.2364990711212158} 08/31/2021 08:30:02 - INFO - __main__ - Step 106043: {'lr': 0.0001011625675232609, 'samples': 20360256, 'steps': 106042, 'loss/train': 1.3341575860977173} 08/31/2021 08:30:02 - INFO - __main__ - Step 106044: {'lr': 0.00010115830376455326, 'samples': 20360448, 'steps': 106043, 'loss/train': 0.5199947357177734} 08/31/2021 08:30:03 - INFO - __main__ - Step 106045: {'lr': 0.00010115404007291131, 'samples': 20360640, 'steps': 106044, 'loss/train': 1.3387497663497925} 08/31/2021 08:30:03 - INFO - __main__ - Step 106046: {'lr': 0.00010114977644833707, 'samples': 20360832, 'steps': 106045, 'loss/train': 1.0332040786743164} 08/31/2021 08:30:04 - INFO - __main__ - Step 106047: {'lr': 0.0001011455128908324, 'samples': 20361024, 'steps': 106046, 'loss/train': 1.1453748941421509} 08/31/2021 08:30:04 - INFO - __main__ - Step 106048: {'lr': 0.00010114124940039931, 'samples': 20361216, 'steps': 106047, 'loss/train': 0.13303861021995544} 08/31/2021 08:30:05 - INFO - __main__ - Step 106049: {'lr': 0.00010113698597703965, 'samples': 20361408, 'steps': 106048, 'loss/train': 1.5595402717590332} 08/31/2021 08:30:06 - INFO - __main__ - Step 106050: {'lr': 0.00010113272262075537, 'samples': 20361600, 'steps': 106049, 'loss/train': 1.4838709831237793} 08/31/2021 08:30:06 - INFO - __main__ - Step 106051: {'lr': 0.00010112845933154841, 'samples': 20361792, 'steps': 106050, 'loss/train': 1.3259917497634888} 08/31/2021 08:30:07 - INFO - __main__ - Step 106052: {'lr': 0.00010112419610942064, 'samples': 20361984, 'steps': 106051, 'loss/train': 1.0002995729446411} 08/31/2021 08:30:07 - INFO - __main__ - Step 106053: {'lr': 0.00010111993295437403, 'samples': 20362176, 'steps': 106052, 'loss/train': 0.7860404253005981} 08/31/2021 08:30:08 - INFO - __main__ - Step 106054: {'lr': 0.00010111566986641047, 'samples': 20362368, 'steps': 106053, 'loss/train': 0.6888359189033508} 08/31/2021 08:30:09 - INFO - __main__ - Step 106055: {'lr': 0.00010111140684553192, 'samples': 20362560, 'steps': 106054, 'loss/train': 0.882591962814331} 08/31/2021 08:30:09 - INFO - __main__ - Step 106056: {'lr': 0.00010110714389174022, 'samples': 20362752, 'steps': 106055, 'loss/train': 1.0943180322647095} 08/31/2021 08:30:10 - INFO - __main__ - Step 106057: {'lr': 0.00010110288100503747, 'samples': 20362944, 'steps': 106056, 'loss/train': 1.3135225772857666} 08/31/2021 08:30:10 - INFO - __main__ - Step 106058: {'lr': 0.00010109861818542538, 'samples': 20363136, 'steps': 106057, 'loss/train': 0.030441517010331154} 08/31/2021 08:30:12 - INFO - __main__ - Step 106059: {'lr': 0.00010109435543290593, 'samples': 20363328, 'steps': 106058, 'loss/train': 1.432733178138733} 08/31/2021 08:30:12 - INFO - __main__ - Step 106060: {'lr': 0.00010109009274748108, 'samples': 20363520, 'steps': 106059, 'loss/train': 0.6535923480987549} 08/31/2021 08:30:12 - INFO - __main__ - Step 106061: {'lr': 0.00010108583012915274, 'samples': 20363712, 'steps': 106060, 'loss/train': 0.8481794595718384} 08/31/2021 08:30:13 - INFO - __main__ - Step 106062: {'lr': 0.0001010815675779228, 'samples': 20363904, 'steps': 106061, 'loss/train': 1.177118182182312} 08/31/2021 08:30:13 - INFO - __main__ - Step 106063: {'lr': 0.00010107730509379323, 'samples': 20364096, 'steps': 106062, 'loss/train': 0.7180401086807251} 08/31/2021 08:30:15 - INFO - __main__ - Step 106064: {'lr': 0.00010107304267676593, 'samples': 20364288, 'steps': 106063, 'loss/train': 1.0472242832183838} 08/31/2021 08:30:15 - INFO - __main__ - Step 106065: {'lr': 0.0001010687803268428, 'samples': 20364480, 'steps': 106064, 'loss/train': 0.8704371452331543} 08/31/2021 08:30:16 - INFO - __main__ - Step 106066: {'lr': 0.0001010645180440258, 'samples': 20364672, 'steps': 106065, 'loss/train': 0.17284467816352844} 08/31/2021 08:30:16 - INFO - __main__ - Step 106067: {'lr': 0.00010106025582831682, 'samples': 20364864, 'steps': 106066, 'loss/train': 0.463261216878891} 08/31/2021 08:30:16 - INFO - __main__ - Step 106068: {'lr': 0.0001010559936797178, 'samples': 20365056, 'steps': 106067, 'loss/train': 0.7450929284095764} 08/31/2021 08:30:18 - INFO - __main__ - Step 106069: {'lr': 0.00010105173159823064, 'samples': 20365248, 'steps': 106068, 'loss/train': 1.557459831237793} 08/31/2021 08:30:19 - INFO - __main__ - Step 106070: {'lr': 0.00010104746958385727, 'samples': 20365440, 'steps': 106069, 'loss/train': 1.6288601160049438} 08/31/2021 08:30:19 - INFO - __main__ - Step 106071: {'lr': 0.00010104320763659971, 'samples': 20365632, 'steps': 106070, 'loss/train': 1.6003588438034058} 08/31/2021 08:30:19 - INFO - __main__ - Step 106072: {'lr': 0.0001010389457564597, 'samples': 20365824, 'steps': 106071, 'loss/train': 1.436032772064209} 08/31/2021 08:30:20 - INFO - __main__ - Step 106073: {'lr': 0.00010103468394343923, 'samples': 20366016, 'steps': 106072, 'loss/train': 5.768657684326172} 08/31/2021 08:30:20 - INFO - __main__ - Step 106074: {'lr': 0.00010103042219754025, 'samples': 20366208, 'steps': 106073, 'loss/train': 5.720317363739014} 08/31/2021 08:30:20 - INFO - __main__ - Step 106075: {'lr': 0.00010102616051876465, 'samples': 20366400, 'steps': 106074, 'loss/train': 0.41105160117149353} 08/31/2021 08:30:22 - INFO - __main__ - Step 106076: {'lr': 0.00010102189890711436, 'samples': 20366592, 'steps': 106075, 'loss/train': 1.3341693878173828} 08/31/2021 08:30:22 - INFO - __main__ - Step 106077: {'lr': 0.00010101763736259129, 'samples': 20366784, 'steps': 106076, 'loss/train': 1.0360007286071777} 08/31/2021 08:30:23 - INFO - __main__ - Step 106078: {'lr': 0.00010101337588519737, 'samples': 20366976, 'steps': 106077, 'loss/train': 1.1773654222488403} 08/31/2021 08:30:23 - INFO - __main__ - Step 106079: {'lr': 0.00010100911447493454, 'samples': 20367168, 'steps': 106078, 'loss/train': 0.9014889001846313} 08/31/2021 08:30:23 - INFO - __main__ - Step 106080: {'lr': 0.00010100485313180474, 'samples': 20367360, 'steps': 106079, 'loss/train': 0.771958589553833} 08/31/2021 08:30:25 - INFO - __main__ - Step 106081: {'lr': 0.00010100059185580982, 'samples': 20367552, 'steps': 106080, 'loss/train': 1.2073627710342407} 08/31/2021 08:30:25 - INFO - __main__ - Step 106082: {'lr': 0.0001009963306469517, 'samples': 20367744, 'steps': 106081, 'loss/train': 1.4336237907409668} 08/31/2021 08:30:26 - INFO - __main__ - Step 106083: {'lr': 0.0001009920695052324, 'samples': 20367936, 'steps': 106082, 'loss/train': 1.0289233922958374} 08/31/2021 08:30:26 - INFO - __main__ - Step 106084: {'lr': 0.00010098780843065383, 'samples': 20368128, 'steps': 106083, 'loss/train': 0.9431576132774353} 08/31/2021 08:30:26 - INFO - __main__ - Step 106085: {'lr': 0.00010098354742321778, 'samples': 20368320, 'steps': 106084, 'loss/train': 0.9841139912605286} 08/31/2021 08:30:29 - INFO - __main__ - Step 106086: {'lr': 0.0001009792864829262, 'samples': 20368512, 'steps': 106085, 'loss/train': 1.2772902250289917} 08/31/2021 08:30:29 - INFO - __main__ - Step 106087: {'lr': 0.00010097502560978109, 'samples': 20368704, 'steps': 106086, 'loss/train': 1.2456531524658203} 08/31/2021 08:30:30 - INFO - __main__ - Step 106088: {'lr': 0.00010097076480378434, 'samples': 20368896, 'steps': 106087, 'loss/train': 1.0209572315216064} 08/31/2021 08:30:30 - INFO - __main__ - Step 106089: {'lr': 0.00010096650406493784, 'samples': 20369088, 'steps': 106088, 'loss/train': 0.24937793612480164} 08/31/2021 08:30:30 - INFO - __main__ - Step 106090: {'lr': 0.00010096224339324356, 'samples': 20369280, 'steps': 106089, 'loss/train': 0.7806217074394226} 08/31/2021 08:30:31 - INFO - __main__ - Step 106091: {'lr': 0.00010095798278870338, 'samples': 20369472, 'steps': 106090, 'loss/train': 1.4895524978637695} 08/31/2021 08:30:32 - INFO - __main__ - Step 106092: {'lr': 0.00010095372225131924, 'samples': 20369664, 'steps': 106091, 'loss/train': 1.1877189874649048} 08/31/2021 08:30:33 - INFO - __main__ - Step 106093: {'lr': 0.00010094946178109304, 'samples': 20369856, 'steps': 106092, 'loss/train': 1.169493556022644} 08/31/2021 08:30:33 - INFO - __main__ - Step 106094: {'lr': 0.00010094520137802671, 'samples': 20370048, 'steps': 106093, 'loss/train': 1.0628904104232788} 08/31/2021 08:30:33 - INFO - __main__ - Step 106095: {'lr': 0.00010094094104212218, 'samples': 20370240, 'steps': 106094, 'loss/train': 0.692791223526001} 08/31/2021 08:30:34 - INFO - __main__ - Step 106096: {'lr': 0.00010093668077338136, 'samples': 20370432, 'steps': 106095, 'loss/train': 1.6200989484786987} 08/31/2021 08:30:35 - INFO - __main__ - Step 106097: {'lr': 0.00010093242057180618, 'samples': 20370624, 'steps': 106096, 'loss/train': 1.156789779663086} 08/31/2021 08:30:36 - INFO - __main__ - Step 106098: {'lr': 0.00010092816043739863, 'samples': 20370816, 'steps': 106097, 'loss/train': 1.2744321823120117} 08/31/2021 08:30:36 - INFO - __main__ - Step 106099: {'lr': 0.00010092390037016048, 'samples': 20371008, 'steps': 106098, 'loss/train': 0.9922428727149963} 08/31/2021 08:30:36 - INFO - __main__ - Step 106100: {'lr': 0.00010091964037009369, 'samples': 20371200, 'steps': 106099, 'loss/train': 0.8383084535598755} 08/31/2021 08:30:37 - INFO - __main__ - Step 106101: {'lr': 0.00010091538043720022, 'samples': 20371392, 'steps': 106100, 'loss/train': 1.0146595239639282} 08/31/2021 08:30:37 - INFO - __main__ - Step 106102: {'lr': 0.000100911120571482, 'samples': 20371584, 'steps': 106101, 'loss/train': 1.5553364753723145} 08/31/2021 08:30:39 - INFO - __main__ - Step 106103: {'lr': 0.0001009068607729409, 'samples': 20371776, 'steps': 106102, 'loss/train': 0.6852903366088867} 08/31/2021 08:30:39 - INFO - __main__ - Step 106104: {'lr': 0.00010090260104157888, 'samples': 20371968, 'steps': 106103, 'loss/train': 1.2069926261901855} 08/31/2021 08:30:40 - INFO - __main__ - Step 106105: {'lr': 0.00010089834137739783, 'samples': 20372160, 'steps': 106104, 'loss/train': 1.7249717712402344} 08/31/2021 08:30:40 - INFO - __main__ - Step 106106: {'lr': 0.00010089408178039971, 'samples': 20372352, 'steps': 106105, 'loss/train': 1.0524928569793701} 08/31/2021 08:30:40 - INFO - __main__ - Step 106107: {'lr': 0.00010088982225058643, 'samples': 20372544, 'steps': 106106, 'loss/train': 1.6105300188064575} 08/31/2021 08:30:42 - INFO - __main__ - Step 106108: {'lr': 0.00010088556278795988, 'samples': 20372736, 'steps': 106107, 'loss/train': 1.2158867120742798} 08/31/2021 08:30:42 - INFO - __main__ - Step 106109: {'lr': 0.000100881303392522, 'samples': 20372928, 'steps': 106108, 'loss/train': 1.0343599319458008} 08/31/2021 08:30:43 - INFO - __main__ - Step 106110: {'lr': 0.00010087704406427467, 'samples': 20373120, 'steps': 106109, 'loss/train': 1.0172327756881714} 08/31/2021 08:30:43 - INFO - __main__ - Step 106111: {'lr': 0.00010087278480321996, 'samples': 20373312, 'steps': 106110, 'loss/train': 0.8144633173942566} 08/31/2021 08:30:43 - INFO - __main__ - Step 106112: {'lr': 0.00010086852560935958, 'samples': 20373504, 'steps': 106111, 'loss/train': 0.7426841855049133} 08/31/2021 08:30:45 - INFO - __main__ - Step 106113: {'lr': 0.00010086426648269553, 'samples': 20373696, 'steps': 106112, 'loss/train': 1.5847364664077759} 08/31/2021 08:30:45 - INFO - __main__ - Step 106114: {'lr': 0.00010086000742322976, 'samples': 20373888, 'steps': 106113, 'loss/train': 1.5936723947525024} 08/31/2021 08:30:46 - INFO - __main__ - Step 106115: {'lr': 0.00010085574843096414, 'samples': 20374080, 'steps': 106114, 'loss/train': 1.0621519088745117} 08/31/2021 08:30:46 - INFO - __main__ - Step 106116: {'lr': 0.00010085148950590064, 'samples': 20374272, 'steps': 106115, 'loss/train': 1.781938910484314} 08/31/2021 08:30:46 - INFO - __main__ - Step 106117: {'lr': 0.00010084723064804116, 'samples': 20374464, 'steps': 106116, 'loss/train': 0.9750658273696899} 08/31/2021 08:30:48 - INFO - __main__ - Step 106118: {'lr': 0.00010084297185738761, 'samples': 20374656, 'steps': 106117, 'loss/train': 1.3455324172973633} 08/31/2021 08:30:49 - INFO - __main__ - Step 106119: {'lr': 0.00010083871313394191, 'samples': 20374848, 'steps': 106118, 'loss/train': 1.0823553800582886} 08/31/2021 08:30:49 - INFO - __main__ - Step 106120: {'lr': 0.000100834454477706, 'samples': 20375040, 'steps': 106119, 'loss/train': 1.3368524312973022} 08/31/2021 08:30:49 - INFO - __main__ - Step 106121: {'lr': 0.00010083019588868178, 'samples': 20375232, 'steps': 106120, 'loss/train': 1.1984267234802246} 08/31/2021 08:30:50 - INFO - __main__ - Step 106122: {'lr': 0.00010082593736687115, 'samples': 20375424, 'steps': 106121, 'loss/train': 1.7989627122879028} 08/31/2021 08:30:50 - INFO - __main__ - Step 106123: {'lr': 0.00010082167891227609, 'samples': 20375616, 'steps': 106122, 'loss/train': 1.0448354482650757} 08/31/2021 08:30:51 - INFO - __main__ - Step 106124: {'lr': 0.00010081742052489845, 'samples': 20375808, 'steps': 106123, 'loss/train': 0.4452173709869385} 08/31/2021 08:30:52 - INFO - __main__ - Step 106125: {'lr': 0.00010081316220474027, 'samples': 20376000, 'steps': 106124, 'loss/train': 1.163490891456604} 08/31/2021 08:30:52 - INFO - __main__ - Step 106126: {'lr': 0.00010080890395180328, 'samples': 20376192, 'steps': 106125, 'loss/train': 2.206547498703003} 08/31/2021 08:30:53 - INFO - __main__ - Step 106127: {'lr': 0.00010080464576608952, 'samples': 20376384, 'steps': 106126, 'loss/train': 0.5233995914459229} 08/31/2021 08:30:53 - INFO - __main__ - Step 106128: {'lr': 0.00010080038764760085, 'samples': 20376576, 'steps': 106127, 'loss/train': 1.4231854677200317} 08/31/2021 08:30:55 - INFO - __main__ - Step 106129: {'lr': 0.00010079612959633926, 'samples': 20376768, 'steps': 106128, 'loss/train': 0.4322413206100464} 08/31/2021 08:30:55 - INFO - __main__ - Step 106130: {'lr': 0.0001007918716123066, 'samples': 20376960, 'steps': 106129, 'loss/train': 1.6177338361740112} 08/31/2021 08:30:55 - INFO - __main__ - Step 106131: {'lr': 0.00010078761369550485, 'samples': 20377152, 'steps': 106130, 'loss/train': 1.0103892087936401} 08/31/2021 08:30:56 - INFO - __main__ - Step 106132: {'lr': 0.0001007833558459359, 'samples': 20377344, 'steps': 106131, 'loss/train': 1.6678465604782104} 08/31/2021 08:30:56 - INFO - __main__ - Step 106133: {'lr': 0.00010077909806360164, 'samples': 20377536, 'steps': 106132, 'loss/train': 1.2508124113082886} 08/31/2021 08:30:58 - INFO - __main__ - Step 106134: {'lr': 0.00010077484034850403, 'samples': 20377728, 'steps': 106133, 'loss/train': 0.8539701700210571} 08/31/2021 08:30:58 - INFO - __main__ - Step 106135: {'lr': 0.00010077058270064496, 'samples': 20377920, 'steps': 106134, 'loss/train': 1.27801513671875} 08/31/2021 08:30:59 - INFO - __main__ - Step 106136: {'lr': 0.00010076632512002636, 'samples': 20378112, 'steps': 106135, 'loss/train': 1.5535578727722168} 08/31/2021 08:30:59 - INFO - __main__ - Step 106137: {'lr': 0.00010076206760665019, 'samples': 20378304, 'steps': 106136, 'loss/train': 1.8451788425445557} 08/31/2021 08:30:59 - INFO - __main__ - Step 106138: {'lr': 0.00010075781016051838, 'samples': 20378496, 'steps': 106137, 'loss/train': 0.6519547700881958} 08/31/2021 08:31:02 - INFO - __main__ - Step 106139: {'lr': 0.00010075355278163273, 'samples': 20378688, 'steps': 106138, 'loss/train': 1.1138997077941895} 08/31/2021 08:31:02 - INFO - __main__ - Step 106140: {'lr': 0.00010074929546999523, 'samples': 20378880, 'steps': 106139, 'loss/train': 0.91582190990448} 08/31/2021 08:31:03 - INFO - __main__ - Step 106141: {'lr': 0.00010074503822560776, 'samples': 20379072, 'steps': 106140, 'loss/train': 1.3259172439575195} 08/31/2021 08:31:03 - INFO - __main__ - Step 106142: {'lr': 0.00010074078104847232, 'samples': 20379264, 'steps': 106141, 'loss/train': 0.05015840753912926} 08/31/2021 08:31:03 - INFO - __main__ - Step 106143: {'lr': 0.00010073652393859076, 'samples': 20379456, 'steps': 106142, 'loss/train': 0.6782110333442688} 08/31/2021 08:31:05 - INFO - __main__ - Step 106144: {'lr': 0.00010073226689596502, 'samples': 20379648, 'steps': 106143, 'loss/train': 1.6104422807693481} 08/31/2021 08:31:05 - INFO - __main__ - Step 106145: {'lr': 0.00010072800992059699, 'samples': 20379840, 'steps': 106144, 'loss/train': 1.53786301612854} 08/31/2021 08:31:06 - INFO - __main__ - Step 106146: {'lr': 0.00010072375301248864, 'samples': 20380032, 'steps': 106145, 'loss/train': 1.3691173791885376} 08/31/2021 08:31:06 - INFO - __main__ - Step 106147: {'lr': 0.00010071949617164185, 'samples': 20380224, 'steps': 106146, 'loss/train': 0.3933824896812439} 08/31/2021 08:31:07 - INFO - __main__ - Step 106148: {'lr': 0.00010071523939805868, 'samples': 20380416, 'steps': 106147, 'loss/train': 0.2840355336666107} 08/31/2021 08:31:07 - INFO - __main__ - Step 106149: {'lr': 0.00010071098269174078, 'samples': 20380608, 'steps': 106148, 'loss/train': 1.630765676498413} 08/31/2021 08:31:08 - INFO - __main__ - Step 106150: {'lr': 0.00010070672605269024, 'samples': 20380800, 'steps': 106149, 'loss/train': 1.2508742809295654} 08/31/2021 08:31:09 - INFO - __main__ - Step 106151: {'lr': 0.00010070246948090894, 'samples': 20380992, 'steps': 106150, 'loss/train': 1.1334086656570435} 08/31/2021 08:31:09 - INFO - __main__ - Step 106152: {'lr': 0.00010069821297639881, 'samples': 20381184, 'steps': 106151, 'loss/train': 1.531406044960022} 08/31/2021 08:31:10 - INFO - __main__ - Step 106153: {'lr': 0.00010069395653916174, 'samples': 20381376, 'steps': 106152, 'loss/train': 0.5144498348236084} 08/31/2021 08:31:10 - INFO - __main__ - Step 106154: {'lr': 0.00010068970016919968, 'samples': 20381568, 'steps': 106153, 'loss/train': 1.5655722618103027} 08/31/2021 08:31:12 - INFO - __main__ - Step 106155: {'lr': 0.00010068544386651454, 'samples': 20381760, 'steps': 106154, 'loss/train': 0.19653105735778809} 08/31/2021 08:31:12 - INFO - __main__ - Step 106156: {'lr': 0.00010068118763110824, 'samples': 20381952, 'steps': 106155, 'loss/train': 1.373597264289856} 08/31/2021 08:31:12 - INFO - __main__ - Step 106157: {'lr': 0.00010067693146298268, 'samples': 20382144, 'steps': 106156, 'loss/train': 0.8454389572143555} 08/31/2021 08:31:13 - INFO - __main__ - Step 106158: {'lr': 0.00010067267536213978, 'samples': 20382336, 'steps': 106157, 'loss/train': 1.375908613204956} 08/31/2021 08:31:13 - INFO - __main__ - Step 106159: {'lr': 0.00010066841932858159, 'samples': 20382528, 'steps': 106158, 'loss/train': 1.4651439189910889} 08/31/2021 08:31:15 - INFO - __main__ - Step 106160: {'lr': 0.0001006641633623098, 'samples': 20382720, 'steps': 106159, 'loss/train': 1.8252266645431519} 08/31/2021 08:31:15 - INFO - __main__ - Step 106161: {'lr': 0.00010065990746332643, 'samples': 20382912, 'steps': 106160, 'loss/train': 1.5285080671310425} 08/31/2021 08:31:15 - INFO - __main__ - Step 106162: {'lr': 0.0001006556516316334, 'samples': 20383104, 'steps': 106161, 'loss/train': 0.43867015838623047} 08/31/2021 08:31:16 - INFO - __main__ - Step 106163: {'lr': 0.00010065139586723263, 'samples': 20383296, 'steps': 106162, 'loss/train': 0.12560948729515076} 08/31/2021 08:31:16 - INFO - __main__ - Step 106164: {'lr': 0.00010064714017012605, 'samples': 20383488, 'steps': 106163, 'loss/train': 1.0412427186965942} 08/31/2021 08:31:16 - INFO - __main__ - Step 106165: {'lr': 0.00010064288454031554, 'samples': 20383680, 'steps': 106164, 'loss/train': 0.7329241633415222} 08/31/2021 08:31:18 - INFO - __main__ - Step 106166: {'lr': 0.00010063862897780308, 'samples': 20383872, 'steps': 106165, 'loss/train': 1.0880595445632935} 08/31/2021 08:31:19 - INFO - __main__ - Step 106167: {'lr': 0.0001006343734825905, 'samples': 20384064, 'steps': 106166, 'loss/train': 0.9021614193916321} 08/31/2021 08:31:19 - INFO - __main__ - Step 106168: {'lr': 0.00010063011805467978, 'samples': 20384256, 'steps': 106167, 'loss/train': 1.1656957864761353} 08/31/2021 08:31:19 - INFO - __main__ - Step 106169: {'lr': 0.00010062586269407284, 'samples': 20384448, 'steps': 106168, 'loss/train': 1.3586196899414062} 08/31/2021 08:31:20 - INFO - __main__ - Step 106170: {'lr': 0.00010062160740077167, 'samples': 20384640, 'steps': 106169, 'loss/train': 1.1192137002944946} 08/31/2021 08:31:21 - INFO - __main__ - Step 106171: {'lr': 0.00010061735217477799, 'samples': 20384832, 'steps': 106170, 'loss/train': 0.8397552371025085} 08/31/2021 08:31:21 - INFO - __main__ - Step 106172: {'lr': 0.00010061309701609387, 'samples': 20385024, 'steps': 106171, 'loss/train': 0.7207592129707336} 08/31/2021 08:31:22 - INFO - __main__ - Step 106173: {'lr': 0.00010060884192472114, 'samples': 20385216, 'steps': 106172, 'loss/train': 1.372679352760315} 08/31/2021 08:31:22 - INFO - __main__ - Step 106174: {'lr': 0.00010060458690066176, 'samples': 20385408, 'steps': 106173, 'loss/train': 1.0631771087646484} 08/31/2021 08:31:22 - INFO - __main__ - Step 106175: {'lr': 0.00010060033194391768, 'samples': 20385600, 'steps': 106174, 'loss/train': 1.0456455945968628} 08/31/2021 08:31:24 - INFO - __main__ - Step 106176: {'lr': 0.00010059607705449076, 'samples': 20385792, 'steps': 106175, 'loss/train': 1.1248719692230225} 08/31/2021 08:31:24 - INFO - __main__ - Step 106177: {'lr': 0.00010059182223238294, 'samples': 20385984, 'steps': 106176, 'loss/train': 1.4320528507232666} 08/31/2021 08:31:25 - INFO - __main__ - Step 106178: {'lr': 0.00010058756747759614, 'samples': 20386176, 'steps': 106177, 'loss/train': 1.1505805253982544} 08/31/2021 08:31:25 - INFO - __main__ - Step 106179: {'lr': 0.0001005833127901323, 'samples': 20386368, 'steps': 106178, 'loss/train': 1.4694613218307495} 08/31/2021 08:31:25 - INFO - __main__ - Step 106180: {'lr': 0.0001005790581699933, 'samples': 20386560, 'steps': 106179, 'loss/train': 1.7419317960739136} 08/31/2021 08:31:27 - INFO - __main__ - Step 106181: {'lr': 0.00010057480361718116, 'samples': 20386752, 'steps': 106180, 'loss/train': 1.4064091444015503} 08/31/2021 08:31:28 - INFO - __main__ - Step 106182: {'lr': 0.00010057054913169761, 'samples': 20386944, 'steps': 106181, 'loss/train': 1.256070852279663} 08/31/2021 08:31:28 - INFO - __main__ - Step 106183: {'lr': 0.00010056629471354466, 'samples': 20387136, 'steps': 106182, 'loss/train': 0.8726018667221069} 08/31/2021 08:31:28 - INFO - __main__ - Step 106184: {'lr': 0.00010056204036272426, 'samples': 20387328, 'steps': 106183, 'loss/train': 1.4913897514343262} 08/31/2021 08:31:29 - INFO - __main__ - Step 106185: {'lr': 0.00010055778607923829, 'samples': 20387520, 'steps': 106184, 'loss/train': 1.6202378273010254} 08/31/2021 08:31:30 - INFO - __main__ - Step 106186: {'lr': 0.00010055353186308866, 'samples': 20387712, 'steps': 106185, 'loss/train': 0.4980842173099518} 08/31/2021 08:31:31 - INFO - __main__ - Step 106187: {'lr': 0.00010054927771427733, 'samples': 20387904, 'steps': 106186, 'loss/train': 1.2449418306350708} 08/31/2021 08:31:31 - INFO - __main__ - Step 106188: {'lr': 0.00010054502363280615, 'samples': 20388096, 'steps': 106187, 'loss/train': 1.9670426845550537} 08/31/2021 08:31:31 - INFO - __main__ - Step 106189: {'lr': 0.00010054076961867708, 'samples': 20388288, 'steps': 106188, 'loss/train': 0.9810535311698914} 08/31/2021 08:31:32 - INFO - __main__ - Step 106190: {'lr': 0.00010053651567189207, 'samples': 20388480, 'steps': 106189, 'loss/train': 1.0429413318634033} 08/31/2021 08:31:32 - INFO - __main__ - Step 106191: {'lr': 0.00010053226179245298, 'samples': 20388672, 'steps': 106190, 'loss/train': 1.399601936340332} 08/31/2021 08:31:34 - INFO - __main__ - Step 106192: {'lr': 0.00010052800798036182, 'samples': 20388864, 'steps': 106191, 'loss/train': 1.4131015539169312} 08/31/2021 08:31:35 - INFO - __main__ - Step 106193: {'lr': 0.00010052375423562038, 'samples': 20389056, 'steps': 106192, 'loss/train': 1.2040467262268066} 08/31/2021 08:31:35 - INFO - __main__ - Step 106194: {'lr': 0.00010051950055823058, 'samples': 20389248, 'steps': 106193, 'loss/train': 1.072699785232544} 08/31/2021 08:31:35 - INFO - __main__ - Step 106195: {'lr': 0.00010051524694819442, 'samples': 20389440, 'steps': 106194, 'loss/train': 1.1261866092681885} 08/31/2021 08:31:36 - INFO - __main__ - Step 106196: {'lr': 0.00010051099340551379, 'samples': 20389632, 'steps': 106195, 'loss/train': 1.3445250988006592} 08/31/2021 08:31:37 - INFO - __main__ - Step 106197: {'lr': 0.00010050673993019058, 'samples': 20389824, 'steps': 106196, 'loss/train': 1.0754331350326538} 08/31/2021 08:31:38 - INFO - __main__ - Step 106198: {'lr': 0.00010050248652222674, 'samples': 20390016, 'steps': 106197, 'loss/train': 1.4053938388824463} 08/31/2021 08:31:38 - INFO - __main__ - Step 106199: {'lr': 0.00010049823318162416, 'samples': 20390208, 'steps': 106198, 'loss/train': 0.9525148272514343} 08/31/2021 08:31:38 - INFO - __main__ - Step 106200: {'lr': 0.00010049397990838477, 'samples': 20390400, 'steps': 106199, 'loss/train': 1.7325141429901123} 08/31/2021 08:31:39 - INFO - __main__ - Step 106201: {'lr': 0.0001004897267025105, 'samples': 20390592, 'steps': 106200, 'loss/train': 1.5701336860656738} 08/31/2021 08:31:41 - INFO - __main__ - Step 106202: {'lr': 0.00010048547356400322, 'samples': 20390784, 'steps': 106201, 'loss/train': 1.3147612810134888} 08/31/2021 08:31:41 - INFO - __main__ - Step 106203: {'lr': 0.00010048122049286492, 'samples': 20390976, 'steps': 106202, 'loss/train': 1.4869375228881836} 08/31/2021 08:31:42 - INFO - __main__ - Step 106204: {'lr': 0.00010047696748909745, 'samples': 20391168, 'steps': 106203, 'loss/train': 0.5516825318336487} 08/31/2021 08:31:42 - INFO - __main__ - Step 106205: {'lr': 0.00010047271455270285, 'samples': 20391360, 'steps': 106204, 'loss/train': 3.1096158027648926} 08/31/2021 08:31:42 - INFO - __main__ - Step 106206: {'lr': 0.00010046846168368285, 'samples': 20391552, 'steps': 106205, 'loss/train': 0.037811823189258575} 08/31/2021 08:31:44 - INFO - __main__ - Step 106207: {'lr': 0.00010046420888203944, 'samples': 20391744, 'steps': 106206, 'loss/train': 1.285926103591919} 08/31/2021 08:31:44 - INFO - __main__ - Step 106208: {'lr': 0.00010045995614777456, 'samples': 20391936, 'steps': 106207, 'loss/train': 1.21792471408844} 08/31/2021 08:31:45 - INFO - __main__ - Step 106209: {'lr': 0.00010045570348089012, 'samples': 20392128, 'steps': 106208, 'loss/train': 1.5267009735107422} 08/31/2021 08:31:45 - INFO - __main__ - Step 106210: {'lr': 0.00010045145088138802, 'samples': 20392320, 'steps': 106209, 'loss/train': 1.0909016132354736} 08/31/2021 08:31:45 - INFO - __main__ - Step 106211: {'lr': 0.00010044719834927019, 'samples': 20392512, 'steps': 106210, 'loss/train': 0.024142982438206673} 08/31/2021 08:31:47 - INFO - __main__ - Step 106212: {'lr': 0.00010044294588453857, 'samples': 20392704, 'steps': 106211, 'loss/train': 1.1859617233276367} 08/31/2021 08:31:48 - INFO - __main__ - Step 106213: {'lr': 0.000100438693487195, 'samples': 20392896, 'steps': 106212, 'loss/train': 0.768837034702301} 08/31/2021 08:31:48 - INFO - __main__ - Step 106214: {'lr': 0.00010043444115724148, 'samples': 20393088, 'steps': 106213, 'loss/train': 1.1969318389892578} 08/31/2021 08:31:48 - INFO - __main__ - Step 106215: {'lr': 0.00010043018889467991, 'samples': 20393280, 'steps': 106214, 'loss/train': 1.3587764501571655} 08/31/2021 08:31:49 - INFO - __main__ - Step 106216: {'lr': 0.00010042593669951216, 'samples': 20393472, 'steps': 106215, 'loss/train': 1.7745915651321411} 08/31/2021 08:31:49 - INFO - __main__ - Step 106217: {'lr': 0.00010042168457174019, 'samples': 20393664, 'steps': 106216, 'loss/train': 1.0854060649871826} 08/31/2021 08:31:50 - INFO - __main__ - Step 106218: {'lr': 0.0001004174325113659, 'samples': 20393856, 'steps': 106217, 'loss/train': 0.6162081360816956} 08/31/2021 08:31:51 - INFO - __main__ - Step 106219: {'lr': 0.0001004131805183913, 'samples': 20394048, 'steps': 106218, 'loss/train': 1.034374475479126} 08/31/2021 08:31:51 - INFO - __main__ - Step 106220: {'lr': 0.00010040892859281811, 'samples': 20394240, 'steps': 106219, 'loss/train': 0.7763091325759888} 08/31/2021 08:31:52 - INFO - __main__ - Step 106221: {'lr': 0.00010040467673464834, 'samples': 20394432, 'steps': 106220, 'loss/train': 1.2045978307724} 08/31/2021 08:31:52 - INFO - __main__ - Step 106222: {'lr': 0.00010040042494388393, 'samples': 20394624, 'steps': 106221, 'loss/train': 0.9530177712440491} 08/31/2021 08:31:53 - INFO - __main__ - Step 106223: {'lr': 0.00010039617322052677, 'samples': 20394816, 'steps': 106222, 'loss/train': 0.8072147369384766} 08/31/2021 08:31:54 - INFO - __main__ - Step 106224: {'lr': 0.0001003919215645788, 'samples': 20395008, 'steps': 106223, 'loss/train': 1.0804392099380493} 08/31/2021 08:31:54 - INFO - __main__ - Step 106225: {'lr': 0.0001003876699760419, 'samples': 20395200, 'steps': 106224, 'loss/train': 1.4824031591415405} 08/31/2021 08:31:55 - INFO - __main__ - Step 106226: {'lr': 0.00010038341845491802, 'samples': 20395392, 'steps': 106225, 'loss/train': 1.2517240047454834} 08/31/2021 08:31:55 - INFO - __main__ - Step 106227: {'lr': 0.00010037916700120908, 'samples': 20395584, 'steps': 106226, 'loss/train': 1.5722843408584595} 08/31/2021 08:31:57 - INFO - __main__ - Step 106228: {'lr': 0.00010037491561491696, 'samples': 20395776, 'steps': 106227, 'loss/train': 1.5733709335327148} 08/31/2021 08:31:57 - INFO - __main__ - Step 106229: {'lr': 0.0001003706642960436, 'samples': 20395968, 'steps': 106228, 'loss/train': 1.3153338432312012} 08/31/2021 08:31:58 - INFO - __main__ - Step 106230: {'lr': 0.0001003664130445909, 'samples': 20396160, 'steps': 106229, 'loss/train': 1.415090560913086} 08/31/2021 08:31:58 - INFO - __main__ - Step 106231: {'lr': 0.0001003621618605608, 'samples': 20396352, 'steps': 106230, 'loss/train': 1.3609962463378906} 08/31/2021 08:31:58 - INFO - __main__ - Step 106232: {'lr': 0.00010035791074395528, 'samples': 20396544, 'steps': 106231, 'loss/train': 1.2259244918823242} 08/31/2021 08:32:00 - INFO - __main__ - Step 106233: {'lr': 0.00010035365969477608, 'samples': 20396736, 'steps': 106232, 'loss/train': 0.27430835366249084} 08/31/2021 08:32:00 - INFO - __main__ - Step 106234: {'lr': 0.00010034940871302523, 'samples': 20396928, 'steps': 106233, 'loss/train': 0.9098885655403137} 08/31/2021 08:32:01 - INFO - __main__ - Step 106235: {'lr': 0.00010034515779870462, 'samples': 20397120, 'steps': 106234, 'loss/train': 1.4352335929870605} 08/31/2021 08:32:01 - INFO - __main__ - Step 106236: {'lr': 0.00010034090695181616, 'samples': 20397312, 'steps': 106235, 'loss/train': 1.187251091003418} 08/31/2021 08:32:01 - INFO - __main__ - Step 106237: {'lr': 0.00010033665617236179, 'samples': 20397504, 'steps': 106236, 'loss/train': 0.9928209781646729} 08/31/2021 08:32:03 - INFO - __main__ - Step 106238: {'lr': 0.00010033240546034342, 'samples': 20397696, 'steps': 106237, 'loss/train': 0.7613252997398376} 08/31/2021 08:32:03 - INFO - __main__ - Step 106239: {'lr': 0.00010032815481576296, 'samples': 20397888, 'steps': 106238, 'loss/train': 0.12837745249271393} 08/31/2021 08:32:04 - INFO - __main__ - Step 106240: {'lr': 0.00010032390423862231, 'samples': 20398080, 'steps': 106239, 'loss/train': 1.3024009466171265} 08/31/2021 08:32:04 - INFO - __main__ - Step 106241: {'lr': 0.00010031965372892341, 'samples': 20398272, 'steps': 106240, 'loss/train': 1.5327675342559814} 08/31/2021 08:32:04 - INFO - __main__ - Step 106242: {'lr': 0.00010031540328666816, 'samples': 20398464, 'steps': 106241, 'loss/train': 1.0071004629135132} 08/31/2021 08:32:05 - INFO - __main__ - Step 106243: {'lr': 0.00010031115291185846, 'samples': 20398656, 'steps': 106242, 'loss/train': 1.8150707483291626} 08/31/2021 08:32:06 - INFO - __main__ - Step 106244: {'lr': 0.00010030690260449627, 'samples': 20398848, 'steps': 106243, 'loss/train': 1.0354686975479126} 08/31/2021 08:32:07 - INFO - __main__ - Step 106245: {'lr': 0.00010030265236458347, 'samples': 20399040, 'steps': 106244, 'loss/train': 1.5548334121704102} 08/31/2021 08:32:07 - INFO - __main__ - Step 106246: {'lr': 0.00010029840219212208, 'samples': 20399232, 'steps': 106245, 'loss/train': 0.4755750000476837} 08/31/2021 08:32:07 - INFO - __main__ - Step 106247: {'lr': 0.00010029415208711382, 'samples': 20399424, 'steps': 106246, 'loss/train': 1.4548426866531372} 08/31/2021 08:32:08 - INFO - __main__ - Step 106248: {'lr': 0.0001002899020495607, 'samples': 20399616, 'steps': 106247, 'loss/train': 1.1924099922180176} 08/31/2021 08:32:10 - INFO - __main__ - Step 106249: {'lr': 0.00010028565207946466, 'samples': 20399808, 'steps': 106248, 'loss/train': 1.4432953596115112} 08/31/2021 08:32:10 - INFO - __main__ - Step 106250: {'lr': 0.0001002814021768276, 'samples': 20400000, 'steps': 106249, 'loss/train': 1.7517919540405273} 08/31/2021 08:32:11 - INFO - __main__ - Step 106251: {'lr': 0.00010027715234165141, 'samples': 20400192, 'steps': 106250, 'loss/train': 1.1862454414367676} 08/31/2021 08:32:11 - INFO - __main__ - Step 106252: {'lr': 0.00010027290257393804, 'samples': 20400384, 'steps': 106251, 'loss/train': 1.2804350852966309} 08/31/2021 08:32:11 - INFO - __main__ - Step 106253: {'lr': 0.00010026865287368939, 'samples': 20400576, 'steps': 106252, 'loss/train': 1.010743498802185} 08/31/2021 08:32:13 - INFO - __main__ - Step 106254: {'lr': 0.00010026440324090735, 'samples': 20400768, 'steps': 106253, 'loss/train': 1.3232674598693848} 08/31/2021 08:32:13 - INFO - __main__ - Step 106255: {'lr': 0.00010026015367559388, 'samples': 20400960, 'steps': 106254, 'loss/train': 0.5793623924255371} 08/31/2021 08:32:14 - INFO - __main__ - Step 106256: {'lr': 0.00010025590417775085, 'samples': 20401152, 'steps': 106255, 'loss/train': 0.7231732606887817} 08/31/2021 08:32:14 - INFO - __main__ - Step 106257: {'lr': 0.00010025165474738024, 'samples': 20401344, 'steps': 106256, 'loss/train': 0.5198184251785278} 08/31/2021 08:32:14 - INFO - __main__ - Step 106258: {'lr': 0.0001002474053844839, 'samples': 20401536, 'steps': 106257, 'loss/train': 1.042908787727356} 08/31/2021 08:32:15 - INFO - __main__ - Step 106259: {'lr': 0.00010024315608906384, 'samples': 20401728, 'steps': 106258, 'loss/train': 1.3849694728851318} 08/31/2021 08:32:16 - INFO - __main__ - Step 106260: {'lr': 0.00010023890686112183, 'samples': 20401920, 'steps': 106259, 'loss/train': 1.2301419973373413} 08/31/2021 08:32:17 - INFO - __main__ - Step 106261: {'lr': 0.00010023465770065987, 'samples': 20402112, 'steps': 106260, 'loss/train': 1.3486442565917969} 08/31/2021 08:32:17 - INFO - __main__ - Step 106262: {'lr': 0.00010023040860767984, 'samples': 20402304, 'steps': 106261, 'loss/train': 0.6164008975028992} 08/31/2021 08:32:17 - INFO - __main__ - Step 106263: {'lr': 0.0001002261595821837, 'samples': 20402496, 'steps': 106262, 'loss/train': 0.11005334556102753} 08/31/2021 08:32:18 - INFO - __main__ - Step 106264: {'lr': 0.00010022191062417332, 'samples': 20402688, 'steps': 106263, 'loss/train': 1.5167911052703857} 08/31/2021 08:32:20 - INFO - __main__ - Step 106265: {'lr': 0.00010021766173365066, 'samples': 20402880, 'steps': 106264, 'loss/train': 0.7302648425102234} 08/31/2021 08:32:20 - INFO - __main__ - Step 106266: {'lr': 0.00010021341291061761, 'samples': 20403072, 'steps': 106265, 'loss/train': 0.7306133508682251} 08/31/2021 08:32:20 - INFO - __main__ - Step 106267: {'lr': 0.00010020916415507605, 'samples': 20403264, 'steps': 106266, 'loss/train': 1.148005485534668} 08/31/2021 08:32:21 - INFO - __main__ - Step 106268: {'lr': 0.00010020491546702795, 'samples': 20403456, 'steps': 106267, 'loss/train': 1.0319690704345703} 08/31/2021 08:32:21 - INFO - __main__ - Step 106269: {'lr': 0.00010020066684647522, 'samples': 20403648, 'steps': 106268, 'loss/train': 0.04026016220450401} 08/31/2021 08:32:23 - INFO - __main__ - Step 106270: {'lr': 0.00010019641829341975, 'samples': 20403840, 'steps': 106269, 'loss/train': 1.0775010585784912} 08/31/2021 08:32:23 - INFO - __main__ - Step 106271: {'lr': 0.00010019216980786344, 'samples': 20404032, 'steps': 106270, 'loss/train': 0.9400037527084351} 08/31/2021 08:32:23 - INFO - __main__ - Step 106272: {'lr': 0.00010018792138980834, 'samples': 20404224, 'steps': 106271, 'loss/train': 1.0757025480270386} 08/31/2021 08:32:24 - INFO - __main__ - Step 106273: {'lr': 0.00010018367303925616, 'samples': 20404416, 'steps': 106272, 'loss/train': 0.42397719621658325} 08/31/2021 08:32:24 - INFO - __main__ - Step 106274: {'lr': 0.00010017942475620889, 'samples': 20404608, 'steps': 106273, 'loss/train': 0.8646873831748962} 08/31/2021 08:32:26 - INFO - __main__ - Step 106275: {'lr': 0.00010017517654066846, 'samples': 20404800, 'steps': 106274, 'loss/train': 1.1918281316757202} 08/31/2021 08:32:26 - INFO - __main__ - Step 106276: {'lr': 0.00010017092839263677, 'samples': 20404992, 'steps': 106275, 'loss/train': 0.027585051953792572} 08/31/2021 08:32:26 - INFO - __main__ - Step 106277: {'lr': 0.0001001666803121158, 'samples': 20405184, 'steps': 106276, 'loss/train': 0.7174517512321472} 08/31/2021 08:32:27 - INFO - __main__ - Step 106278: {'lr': 0.00010016243229910738, 'samples': 20405376, 'steps': 106277, 'loss/train': 1.0969129800796509} 08/31/2021 08:32:27 - INFO - __main__ - Step 106279: {'lr': 0.00010015818435361346, 'samples': 20405568, 'steps': 106278, 'loss/train': 1.8709287643432617} 08/31/2021 08:32:29 - INFO - __main__ - Step 106280: {'lr': 0.00010015393647563592, 'samples': 20405760, 'steps': 106279, 'loss/train': 0.026167389005422592} 08/31/2021 08:32:29 - INFO - __main__ - Step 106281: {'lr': 0.00010014968866517673, 'samples': 20405952, 'steps': 106280, 'loss/train': 0.9675310254096985} 08/31/2021 08:32:30 - INFO - __main__ - Step 106282: {'lr': 0.00010014544092223779, 'samples': 20406144, 'steps': 106281, 'loss/train': 1.0340335369110107} 08/31/2021 08:32:30 - INFO - __main__ - Step 106283: {'lr': 0.000100141193246821, 'samples': 20406336, 'steps': 106282, 'loss/train': 1.1035183668136597} 08/31/2021 08:32:30 - INFO - __main__ - Step 106284: {'lr': 0.00010013694563892825, 'samples': 20406528, 'steps': 106283, 'loss/train': 0.837596595287323} 08/31/2021 08:32:31 - INFO - __main__ - Step 106285: {'lr': 0.00010013269809856148, 'samples': 20406720, 'steps': 106284, 'loss/train': 0.05485837534070015} 08/31/2021 08:32:32 - INFO - __main__ - Step 106286: {'lr': 0.00010012845062572273, 'samples': 20406912, 'steps': 106285, 'loss/train': 1.4430617094039917} 08/31/2021 08:32:33 - INFO - __main__ - Step 106287: {'lr': 0.00010012420322041369, 'samples': 20407104, 'steps': 106286, 'loss/train': 1.274416446685791} 08/31/2021 08:32:33 - INFO - __main__ - Step 106288: {'lr': 0.00010011995588263633, 'samples': 20407296, 'steps': 106287, 'loss/train': 1.2466448545455933} 08/31/2021 08:32:33 - INFO - __main__ - Step 106289: {'lr': 0.00010011570861239264, 'samples': 20407488, 'steps': 106288, 'loss/train': 0.4298645257949829} 08/31/2021 08:32:34 - INFO - __main__ - Step 106290: {'lr': 0.0001001114614096845, 'samples': 20407680, 'steps': 106289, 'loss/train': 1.266303539276123} 08/31/2021 08:32:35 - INFO - __main__ - Step 106291: {'lr': 0.0001001072142745138, 'samples': 20407872, 'steps': 106290, 'loss/train': 1.2601293325424194} 08/31/2021 08:32:36 - INFO - __main__ - Step 106292: {'lr': 0.0001001029672068825, 'samples': 20408064, 'steps': 106291, 'loss/train': 1.5268858671188354} 08/31/2021 08:32:36 - INFO - __main__ - Step 106293: {'lr': 0.00010009872020679248, 'samples': 20408256, 'steps': 106292, 'loss/train': 1.238985300064087} 08/31/2021 08:32:36 - INFO - __main__ - Step 106294: {'lr': 0.00010009447327424567, 'samples': 20408448, 'steps': 106293, 'loss/train': 0.8845602869987488} 08/31/2021 08:32:37 - INFO - __main__ - Step 106295: {'lr': 0.00010009022640924395, 'samples': 20408640, 'steps': 106294, 'loss/train': 0.8122714757919312} 08/31/2021 08:32:38 - INFO - __main__ - Step 106296: {'lr': 0.00010008597961178931, 'samples': 20408832, 'steps': 106295, 'loss/train': 1.0658596754074097} 08/31/2021 08:32:39 - INFO - __main__ - Step 106297: {'lr': 0.00010008173288188358, 'samples': 20409024, 'steps': 106296, 'loss/train': 1.0966979265213013} 08/31/2021 08:32:39 - INFO - __main__ - Step 106298: {'lr': 0.0001000774862195287, 'samples': 20409216, 'steps': 106297, 'loss/train': 1.2457056045532227} 08/31/2021 08:32:39 - INFO - __main__ - Step 106299: {'lr': 0.00010007323962472669, 'samples': 20409408, 'steps': 106298, 'loss/train': 1.5062313079833984} 08/31/2021 08:32:40 - INFO - __main__ - Step 106300: {'lr': 0.0001000689930974793, 'samples': 20409600, 'steps': 106299, 'loss/train': 0.8483542799949646} 08/31/2021 08:32:42 - INFO - __main__ - Step 106301: {'lr': 0.00010006474663778847, 'samples': 20409792, 'steps': 106300, 'loss/train': 1.0092599391937256} 08/31/2021 08:32:42 - INFO - __main__ - Step 106302: {'lr': 0.00010006050024565619, 'samples': 20409984, 'steps': 106301, 'loss/train': 1.154924750328064} 08/31/2021 08:32:43 - INFO - __main__ - Step 106303: {'lr': 0.0001000562539210843, 'samples': 20410176, 'steps': 106302, 'loss/train': 1.2181118726730347} 08/31/2021 08:32:43 - INFO - __main__ - Step 106304: {'lr': 0.00010005200766407476, 'samples': 20410368, 'steps': 106303, 'loss/train': 0.06132292374968529} 08/31/2021 08:32:43 - INFO - __main__ - Step 106305: {'lr': 0.00010004776147462946, 'samples': 20410560, 'steps': 106304, 'loss/train': 1.163674235343933} 08/31/2021 08:32:45 - INFO - __main__ - Step 106306: {'lr': 0.00010004351535275036, 'samples': 20410752, 'steps': 106305, 'loss/train': 0.9842481017112732} 08/31/2021 08:32:46 - INFO - __main__ - Step 106307: {'lr': 0.00010003926929843931, 'samples': 20410944, 'steps': 106306, 'loss/train': 1.8771032094955444} 08/31/2021 08:32:46 - INFO - __main__ - Step 106308: {'lr': 0.00010003502331169825, 'samples': 20411136, 'steps': 106307, 'loss/train': 0.7883379459381104} 08/31/2021 08:32:46 - INFO - __main__ - Step 106309: {'lr': 0.00010003077739252911, 'samples': 20411328, 'steps': 106308, 'loss/train': 0.2970670461654663} 08/31/2021 08:32:47 - INFO - __main__ - Step 106310: {'lr': 0.00010002653154093378, 'samples': 20411520, 'steps': 106309, 'loss/train': 1.3309670686721802} 08/31/2021 08:32:47 - INFO - __main__ - Step 106311: {'lr': 0.00010002228575691418, 'samples': 20411712, 'steps': 106310, 'loss/train': 0.5214956998825073} 08/31/2021 08:32:48 - INFO - __main__ - Step 106312: {'lr': 0.00010001804004047222, 'samples': 20411904, 'steps': 106311, 'loss/train': 1.0667327642440796} 08/31/2021 08:32:49 - INFO - __main__ - Step 106313: {'lr': 0.0001000137943916099, 'samples': 20412096, 'steps': 106312, 'loss/train': 0.9442289471626282} 08/31/2021 08:32:49 - INFO - __main__ - Step 106314: {'lr': 0.00010000954881032898, 'samples': 20412288, 'steps': 106313, 'loss/train': 1.0297906398773193} 08/31/2021 08:32:50 - INFO - __main__ - Step 106315: {'lr': 0.00010000530329663144, 'samples': 20412480, 'steps': 106314, 'loss/train': 0.6766101121902466} 08/31/2021 08:32:50 - INFO - __main__ - Step 106316: {'lr': 0.0001000010578505192, 'samples': 20412672, 'steps': 106315, 'loss/train': 1.0820354223251343} 08/31/2021 08:32:51 - INFO - __main__ - Step 106317: {'lr': 9.999681247199415e-05, 'samples': 20412864, 'steps': 106316, 'loss/train': 1.3712029457092285} 08/31/2021 08:32:52 - INFO - __main__ - Step 106318: {'lr': 9.999256716105823e-05, 'samples': 20413056, 'steps': 106317, 'loss/train': 1.014772653579712} 08/31/2021 08:32:52 - INFO - __main__ - Step 106319: {'lr': 9.998832191771334e-05, 'samples': 20413248, 'steps': 106318, 'loss/train': 0.46078047156333923} 08/31/2021 08:32:53 - INFO - __main__ - Step 106320: {'lr': 9.998407674196142e-05, 'samples': 20413440, 'steps': 106319, 'loss/train': 1.1374855041503906} 08/31/2021 08:32:53 - INFO - __main__ - Step 106321: {'lr': 9.997983163380434e-05, 'samples': 20413632, 'steps': 106320, 'loss/train': 1.042474389076233} 08/31/2021 08:32:55 - INFO - __main__ - Step 106322: {'lr': 9.997558659324402e-05, 'samples': 20413824, 'steps': 106321, 'loss/train': 1.5204486846923828} 08/31/2021 08:32:55 - INFO - __main__ - Step 106323: {'lr': 9.99713416202824e-05, 'samples': 20414016, 'steps': 106322, 'loss/train': 1.21371328830719} 08/31/2021 08:32:55 - INFO - __main__ - Step 106324: {'lr': 9.996709671492138e-05, 'samples': 20414208, 'steps': 106323, 'loss/train': 1.8082858324050903} 08/31/2021 08:32:56 - INFO - __main__ - Step 106325: {'lr': 9.996285187716286e-05, 'samples': 20414400, 'steps': 106324, 'loss/train': 1.2569622993469238} 08/31/2021 08:32:56 - INFO - __main__ - Step 106326: {'lr': 9.995860710700888e-05, 'samples': 20414592, 'steps': 106325, 'loss/train': 1.268198847770691} 08/31/2021 08:32:58 - INFO - __main__ - Step 106327: {'lr': 9.995436240446112e-05, 'samples': 20414784, 'steps': 106326, 'loss/train': 1.3409923315048218} 08/31/2021 08:32:58 - INFO - __main__ - Step 106328: {'lr': 9.995011776952162e-05, 'samples': 20414976, 'steps': 106327, 'loss/train': 0.7005583643913269} 08/31/2021 08:32:59 - INFO - __main__ - Step 106329: {'lr': 9.994587320219228e-05, 'samples': 20415168, 'steps': 106328, 'loss/train': 1.4907649755477905} 08/31/2021 08:32:59 - INFO - __main__ - Step 106330: {'lr': 9.9941628702475e-05, 'samples': 20415360, 'steps': 106329, 'loss/train': 0.6562418937683105} 08/31/2021 08:32:59 - INFO - __main__ - Step 106331: {'lr': 9.993738427037175e-05, 'samples': 20415552, 'steps': 106330, 'loss/train': 1.18358314037323} 08/31/2021 08:33:00 - INFO - __main__ - Step 106332: {'lr': 9.993313990588434e-05, 'samples': 20415744, 'steps': 106331, 'loss/train': 0.8635681867599487} 08/31/2021 08:33:02 - INFO - __main__ - Step 106333: {'lr': 9.992889560901478e-05, 'samples': 20415936, 'steps': 106332, 'loss/train': 1.318817138671875} 08/31/2021 08:33:02 - INFO - __main__ - Step 106334: {'lr': 9.992465137976495e-05, 'samples': 20416128, 'steps': 106333, 'loss/train': 0.9402587413787842} 08/31/2021 08:33:02 - INFO - __main__ - Step 106335: {'lr': 9.992040721813673e-05, 'samples': 20416320, 'steps': 106334, 'loss/train': 1.3223719596862793} 08/31/2021 08:33:03 - INFO - __main__ - Step 106336: {'lr': 9.991616312413206e-05, 'samples': 20416512, 'steps': 106335, 'loss/train': 0.8640462756156921} 08/31/2021 08:33:03 - INFO - __main__ - Step 106337: {'lr': 9.991191909775287e-05, 'samples': 20416704, 'steps': 106336, 'loss/train': 1.398064136505127} 08/31/2021 08:33:05 - INFO - __main__ - Step 106338: {'lr': 9.990767513900107e-05, 'samples': 20416896, 'steps': 106337, 'loss/train': 0.5686051845550537} 08/31/2021 08:33:05 - INFO - __main__ - Step 106339: {'lr': 9.990343124787851e-05, 'samples': 20417088, 'steps': 106338, 'loss/train': 1.5529146194458008} 08/31/2021 08:33:05 - INFO - __main__ - Step 106340: {'lr': 9.989918742438725e-05, 'samples': 20417280, 'steps': 106339, 'loss/train': 1.2211769819259644} 08/31/2021 08:33:06 - INFO - __main__ - Step 106341: {'lr': 9.989494366852902e-05, 'samples': 20417472, 'steps': 106340, 'loss/train': 1.28508460521698} 08/31/2021 08:33:06 - INFO - __main__ - Step 106342: {'lr': 9.989069998030581e-05, 'samples': 20417664, 'steps': 106341, 'loss/train': 0.044512789696455} 08/31/2021 08:33:08 - INFO - __main__ - Step 106343: {'lr': 9.988645635971954e-05, 'samples': 20417856, 'steps': 106342, 'loss/train': 1.70108163356781} 08/31/2021 08:33:08 - INFO - __main__ - Step 106344: {'lr': 9.988221280677213e-05, 'samples': 20418048, 'steps': 106343, 'loss/train': 0.7528117895126343} 08/31/2021 08:33:08 - INFO - __main__ - Step 106345: {'lr': 9.987796932146545e-05, 'samples': 20418240, 'steps': 106344, 'loss/train': 0.6892493367195129} 08/31/2021 08:33:09 - INFO - __main__ - Step 106346: {'lr': 9.987372590380145e-05, 'samples': 20418432, 'steps': 106345, 'loss/train': 1.1975963115692139} 08/31/2021 08:33:09 - INFO - __main__ - Step 106347: {'lr': 9.986948255378204e-05, 'samples': 20418624, 'steps': 106346, 'loss/train': 0.44663673639297485} 08/31/2021 08:33:11 - INFO - __main__ - Step 106348: {'lr': 9.986523927140909e-05, 'samples': 20418816, 'steps': 106347, 'loss/train': 0.6279676556587219} 08/31/2021 08:33:12 - INFO - __main__ - Step 106349: {'lr': 9.986099605668458e-05, 'samples': 20419008, 'steps': 106348, 'loss/train': 1.2213950157165527} 08/31/2021 08:33:12 - INFO - __main__ - Step 106350: {'lr': 9.985675290961038e-05, 'samples': 20419200, 'steps': 106349, 'loss/train': 0.8637761473655701} 08/31/2021 08:33:12 - INFO - __main__ - Step 106351: {'lr': 9.98525098301884e-05, 'samples': 20419392, 'steps': 106350, 'loss/train': 0.9564113020896912} 08/31/2021 08:33:13 - INFO - __main__ - Step 106352: {'lr': 9.984826681842057e-05, 'samples': 20419584, 'steps': 106351, 'loss/train': 0.953113317489624} 08/31/2021 08:33:13 - INFO - __main__ - Step 106353: {'lr': 9.98440238743089e-05, 'samples': 20419776, 'steps': 106352, 'loss/train': 0.8878160119056702} 08/31/2021 08:33:14 - INFO - __main__ - Step 106354: {'lr': 9.98397809978551e-05, 'samples': 20419968, 'steps': 106353, 'loss/train': 0.03224699944257736} 08/31/2021 08:33:15 - INFO - __main__ - Step 106355: {'lr': 9.983553818906116e-05, 'samples': 20420160, 'steps': 106354, 'loss/train': 1.2843761444091797} 08/31/2021 08:33:15 - INFO - __main__ - Step 106356: {'lr': 9.983129544792902e-05, 'samples': 20420352, 'steps': 106355, 'loss/train': 0.8984180092811584} 08/31/2021 08:33:16 - INFO - __main__ - Step 106357: {'lr': 9.982705277446057e-05, 'samples': 20420544, 'steps': 106356, 'loss/train': 1.538697361946106} 08/31/2021 08:33:16 - INFO - __main__ - Step 106358: {'lr': 9.982281016865777e-05, 'samples': 20420736, 'steps': 106357, 'loss/train': 1.3105138540267944} 08/31/2021 08:33:18 - INFO - __main__ - Step 106359: {'lr': 9.981856763052247e-05, 'samples': 20420928, 'steps': 106358, 'loss/train': 0.37781819701194763} 08/31/2021 08:33:18 - INFO - __main__ - Step 106360: {'lr': 9.981432516005658e-05, 'samples': 20421120, 'steps': 106359, 'loss/train': 1.5172053575515747} 08/31/2021 08:33:19 - INFO - __main__ - Step 106361: {'lr': 9.981008275726208e-05, 'samples': 20421312, 'steps': 106360, 'loss/train': 0.6610856652259827} 08/31/2021 08:33:19 - INFO - __main__ - Step 106362: {'lr': 9.980584042214083e-05, 'samples': 20421504, 'steps': 106361, 'loss/train': 1.1991908550262451} 08/31/2021 08:33:19 - INFO - __main__ - Step 106363: {'lr': 9.980159815469472e-05, 'samples': 20421696, 'steps': 106362, 'loss/train': 1.245524287223816} 08/31/2021 08:33:21 - INFO - __main__ - Step 106364: {'lr': 9.979735595492573e-05, 'samples': 20421888, 'steps': 106363, 'loss/train': 1.0047518014907837} 08/31/2021 08:33:22 - INFO - __main__ - Step 106365: {'lr': 9.97931138228357e-05, 'samples': 20422080, 'steps': 106364, 'loss/train': 1.1116758584976196} 08/31/2021 08:33:22 - INFO - __main__ - Step 106366: {'lr': 9.97888717584266e-05, 'samples': 20422272, 'steps': 106365, 'loss/train': 0.10290682315826416} 08/31/2021 08:33:23 - INFO - __main__ - Step 106367: {'lr': 9.978462976170041e-05, 'samples': 20422464, 'steps': 106366, 'loss/train': 0.8359252214431763} 08/31/2021 08:33:23 - INFO - __main__ - Step 106368: {'lr': 9.978038783265883e-05, 'samples': 20422656, 'steps': 106367, 'loss/train': 1.3363587856292725} 08/31/2021 08:33:25 - INFO - __main__ - Step 106369: {'lr': 9.977614597130391e-05, 'samples': 20422848, 'steps': 106368, 'loss/train': 0.038499243557453156} 08/31/2021 08:33:25 - INFO - __main__ - Step 106370: {'lr': 9.977190417763754e-05, 'samples': 20423040, 'steps': 106369, 'loss/train': 1.5807671546936035} 08/31/2021 08:33:25 - INFO - __main__ - Step 106371: {'lr': 9.976766245166164e-05, 'samples': 20423232, 'steps': 106370, 'loss/train': 1.5347530841827393} 08/31/2021 08:33:26 - INFO - __main__ - Step 106372: {'lr': 9.97634207933781e-05, 'samples': 20423424, 'steps': 106371, 'loss/train': 0.6545484662055969} 08/31/2021 08:33:26 - INFO - __main__ - Step 106373: {'lr': 9.975917920278884e-05, 'samples': 20423616, 'steps': 106372, 'loss/train': 0.9513847231864929} 08/31/2021 08:33:28 - INFO - __main__ - Step 106374: {'lr': 9.97549376798958e-05, 'samples': 20423808, 'steps': 106373, 'loss/train': 1.0701978206634521} 08/31/2021 08:33:28 - INFO - __main__ - Step 106375: {'lr': 9.975069622470084e-05, 'samples': 20424000, 'steps': 106374, 'loss/train': 1.0042660236358643} 08/31/2021 08:33:28 - INFO - __main__ - Step 106376: {'lr': 9.974645483720591e-05, 'samples': 20424192, 'steps': 106375, 'loss/train': 0.5563393235206604} 08/31/2021 08:33:29 - INFO - __main__ - Step 106377: {'lr': 9.974221351741289e-05, 'samples': 20424384, 'steps': 106376, 'loss/train': 1.2749873399734497} 08/31/2021 08:33:29 - INFO - __main__ - Step 106378: {'lr': 9.973797226532372e-05, 'samples': 20424576, 'steps': 106377, 'loss/train': 0.39280030131340027} 08/31/2021 08:33:31 - INFO - __main__ - Step 106379: {'lr': 9.973373108094031e-05, 'samples': 20424768, 'steps': 106378, 'loss/train': 0.09043616056442261} 08/31/2021 08:33:31 - INFO - __main__ - Step 106380: {'lr': 9.972948996426464e-05, 'samples': 20424960, 'steps': 106379, 'loss/train': 1.2354971170425415} 08/31/2021 08:33:32 - INFO - __main__ - Step 106381: {'lr': 9.972524891529847e-05, 'samples': 20425152, 'steps': 106380, 'loss/train': 1.247930645942688} 08/31/2021 08:33:32 - INFO - __main__ - Step 106382: {'lr': 9.972100793404377e-05, 'samples': 20425344, 'steps': 106381, 'loss/train': 0.9488747119903564} 08/31/2021 08:33:32 - INFO - __main__ - Step 106383: {'lr': 9.971676702050247e-05, 'samples': 20425536, 'steps': 106382, 'loss/train': 0.8630216717720032} 08/31/2021 08:33:34 - INFO - __main__ - Step 106384: {'lr': 9.97125261746765e-05, 'samples': 20425728, 'steps': 106383, 'loss/train': 0.4987500309944153} 08/31/2021 08:33:34 - INFO - __main__ - Step 106385: {'lr': 9.970828539656771e-05, 'samples': 20425920, 'steps': 106384, 'loss/train': 1.3897557258605957} 08/31/2021 08:33:35 - INFO - __main__ - Step 106386: {'lr': 9.970404468617805e-05, 'samples': 20426112, 'steps': 106385, 'loss/train': 1.1359217166900635} 08/31/2021 08:33:35 - INFO - __main__ - Step 106387: {'lr': 9.969980404350945e-05, 'samples': 20426304, 'steps': 106386, 'loss/train': 0.6727789044380188} 08/31/2021 08:33:35 - INFO - __main__ - Step 106388: {'lr': 9.969556346856379e-05, 'samples': 20426496, 'steps': 106387, 'loss/train': 1.0693598985671997} 08/31/2021 08:33:36 - INFO - __main__ - Step 106389: {'lr': 9.969132296134298e-05, 'samples': 20426688, 'steps': 106388, 'loss/train': 1.7614567279815674} 08/31/2021 08:33:37 - INFO - __main__ - Step 106390: {'lr': 9.968708252184894e-05, 'samples': 20426880, 'steps': 106389, 'loss/train': 0.4863155484199524} 08/31/2021 08:33:38 - INFO - __main__ - Step 106391: {'lr': 9.968284215008358e-05, 'samples': 20427072, 'steps': 106390, 'loss/train': 1.193121075630188} 08/31/2021 08:33:38 - INFO - __main__ - Step 106392: {'lr': 9.967860184604882e-05, 'samples': 20427264, 'steps': 106391, 'loss/train': 0.8778451085090637} 08/31/2021 08:33:38 - INFO - __main__ - Step 106393: {'lr': 9.967436160974666e-05, 'samples': 20427456, 'steps': 106392, 'loss/train': 1.787707805633545} 08/31/2021 08:33:39 - INFO - __main__ - Step 106394: {'lr': 9.967012144117882e-05, 'samples': 20427648, 'steps': 106393, 'loss/train': 1.434587836265564} 08/31/2021 08:33:40 - INFO - __main__ - Step 106395: {'lr': 9.966588134034729e-05, 'samples': 20427840, 'steps': 106394, 'loss/train': 0.7848215103149414} 08/31/2021 08:33:41 - INFO - __main__ - Step 106396: {'lr': 9.9661641307254e-05, 'samples': 20428032, 'steps': 106395, 'loss/train': 1.1009351015090942} 08/31/2021 08:33:41 - INFO - __main__ - Step 106397: {'lr': 9.965740134190087e-05, 'samples': 20428224, 'steps': 106396, 'loss/train': 4.229349613189697} 08/31/2021 08:33:42 - INFO - __main__ - Step 106398: {'lr': 9.96531614442898e-05, 'samples': 20428416, 'steps': 106397, 'loss/train': 0.39724457263946533} 08/31/2021 08:33:42 - INFO - __main__ - Step 106399: {'lr': 9.964892161442265e-05, 'samples': 20428608, 'steps': 106398, 'loss/train': 0.9009621143341064} 08/31/2021 08:33:43 - INFO - __main__ - Step 106400: {'lr': 9.964468185230141e-05, 'samples': 20428800, 'steps': 106399, 'loss/train': 0.1121455729007721} 08/31/2021 08:33:44 - INFO - __main__ - Step 106401: {'lr': 9.964044215792795e-05, 'samples': 20428992, 'steps': 106400, 'loss/train': 0.39849138259887695} 08/31/2021 08:33:44 - INFO - __main__ - Step 106402: {'lr': 9.963620253130418e-05, 'samples': 20429184, 'steps': 106401, 'loss/train': 1.2038391828536987} 08/31/2021 08:33:45 - INFO - __main__ - Step 106403: {'lr': 9.963196297243204e-05, 'samples': 20429376, 'steps': 106402, 'loss/train': 0.8565537333488464} 08/31/2021 08:33:45 - INFO - __main__ - Step 106404: {'lr': 9.962772348131338e-05, 'samples': 20429568, 'steps': 106403, 'loss/train': 1.0649638175964355} 08/31/2021 08:33:47 - INFO - __main__ - Step 106405: {'lr': 9.962348405795018e-05, 'samples': 20429760, 'steps': 106404, 'loss/train': 0.7853347063064575} 08/31/2021 08:33:47 - INFO - __main__ - Step 106406: {'lr': 9.96192447023444e-05, 'samples': 20429952, 'steps': 106405, 'loss/train': 1.4889311790466309} 08/31/2021 08:33:47 - INFO - __main__ - Step 106407: {'lr': 9.961500541449778e-05, 'samples': 20430144, 'steps': 106406, 'loss/train': 0.6221863627433777} 08/31/2021 08:33:48 - INFO - __main__ - Step 106408: {'lr': 9.961076619441231e-05, 'samples': 20430336, 'steps': 106407, 'loss/train': 1.4379099607467651} 08/31/2021 08:33:48 - INFO - __main__ - Step 106409: {'lr': 9.960652704208988e-05, 'samples': 20430528, 'steps': 106408, 'loss/train': 0.05354837700724602} 08/31/2021 08:33:48 - INFO - __main__ - Step 106410: {'lr': 9.960228795753248e-05, 'samples': 20430720, 'steps': 106409, 'loss/train': 1.220002293586731} 08/31/2021 08:33:50 - INFO - __main__ - Step 106411: {'lr': 9.959804894074195e-05, 'samples': 20430912, 'steps': 106410, 'loss/train': 1.140596628189087} 08/31/2021 08:33:51 - INFO - __main__ - Step 106412: {'lr': 9.959380999172021e-05, 'samples': 20431104, 'steps': 106411, 'loss/train': 0.3940414488315582} 08/31/2021 08:33:51 - INFO - __main__ - Step 106413: {'lr': 9.958957111046918e-05, 'samples': 20431296, 'steps': 106412, 'loss/train': 0.9381294250488281} 08/31/2021 08:33:51 - INFO - __main__ - Step 106414: {'lr': 9.958533229699076e-05, 'samples': 20431488, 'steps': 106413, 'loss/train': 0.5956626534461975} 08/31/2021 08:33:52 - INFO - __main__ - Step 106415: {'lr': 9.958109355128688e-05, 'samples': 20431680, 'steps': 106414, 'loss/train': 1.2361717224121094} 08/31/2021 08:33:53 - INFO - __main__ - Step 106416: {'lr': 9.957685487335946e-05, 'samples': 20431872, 'steps': 106415, 'loss/train': 1.2808083295822144} 08/31/2021 08:33:54 - INFO - __main__ - Step 106417: {'lr': 9.957261626321045e-05, 'samples': 20432064, 'steps': 106416, 'loss/train': 0.9173884391784668} 08/31/2021 08:33:54 - INFO - __main__ - Step 106418: {'lr': 9.956837772084159e-05, 'samples': 20432256, 'steps': 106417, 'loss/train': 0.7734465599060059} 08/31/2021 08:33:55 - INFO - __main__ - Step 106419: {'lr': 9.956413924625493e-05, 'samples': 20432448, 'steps': 106418, 'loss/train': 0.5258631706237793} 08/31/2021 08:33:55 - INFO - __main__ - Step 106420: {'lr': 9.955990083945235e-05, 'samples': 20432640, 'steps': 106419, 'loss/train': 0.43035635352134705} 08/31/2021 08:33:57 - INFO - __main__ - Step 106421: {'lr': 9.955566250043574e-05, 'samples': 20432832, 'steps': 106420, 'loss/train': 0.5074214935302734} 08/31/2021 08:33:58 - INFO - __main__ - Step 106422: {'lr': 9.955142422920704e-05, 'samples': 20433024, 'steps': 106421, 'loss/train': 1.5210071802139282} 08/31/2021 08:33:58 - INFO - __main__ - Step 106423: {'lr': 9.954718602576815e-05, 'samples': 20433216, 'steps': 106422, 'loss/train': 1.1672276258468628} 08/31/2021 08:33:58 - INFO - __main__ - Step 106424: {'lr': 9.954294789012094e-05, 'samples': 20433408, 'steps': 106423, 'loss/train': 0.6230200529098511} 08/31/2021 08:33:59 - INFO - __main__ - Step 106425: {'lr': 9.953870982226739e-05, 'samples': 20433600, 'steps': 106424, 'loss/train': 0.6328084468841553} 08/31/2021 08:33:59 - INFO - __main__ - Step 106426: {'lr': 9.953447182220937e-05, 'samples': 20433792, 'steps': 106425, 'loss/train': 3.6457901000976562} 08/31/2021 08:34:00 - INFO - __main__ - Step 106427: {'lr': 9.953023388994881e-05, 'samples': 20433984, 'steps': 106426, 'loss/train': 5.731656074523926} 08/31/2021 08:34:00 - INFO - __main__ - Step 106428: {'lr': 9.952599602548765e-05, 'samples': 20434176, 'steps': 106427, 'loss/train': 5.387825965881348} 08/31/2021 08:34:01 - INFO - __main__ - Step 106429: {'lr': 9.952175822882769e-05, 'samples': 20434368, 'steps': 106428, 'loss/train': 3.8055763244628906} 08/31/2021 08:34:02 - INFO - __main__ - Step 106430: {'lr': 9.951752049997093e-05, 'samples': 20434560, 'steps': 106429, 'loss/train': 1.1488226652145386} 08/31/2021 08:34:02 - INFO - __main__ - Step 106431: {'lr': 9.951328283891922e-05, 'samples': 20434752, 'steps': 106430, 'loss/train': 0.9012792110443115} 08/31/2021 08:34:03 - INFO - __main__ - Step 106432: {'lr': 9.95090452456745e-05, 'samples': 20434944, 'steps': 106431, 'loss/train': 1.216329574584961} 08/31/2021 08:34:03 - INFO - __main__ - Step 106433: {'lr': 9.95048077202387e-05, 'samples': 20435136, 'steps': 106432, 'loss/train': 0.48056623339653015} 08/31/2021 08:34:05 - INFO - __main__ - Step 106434: {'lr': 9.95005702626137e-05, 'samples': 20435328, 'steps': 106433, 'loss/train': 0.9972517490386963} 08/31/2021 08:34:05 - INFO - __main__ - Step 106435: {'lr': 9.949633287280144e-05, 'samples': 20435520, 'steps': 106434, 'loss/train': 0.3338925242424011} 08/31/2021 08:34:05 - INFO - __main__ - Step 106436: {'lr': 9.949209555080379e-05, 'samples': 20435712, 'steps': 106435, 'loss/train': 1.3210591077804565} 08/31/2021 08:34:06 - INFO - __main__ - Step 106437: {'lr': 9.948785829662269e-05, 'samples': 20435904, 'steps': 106436, 'loss/train': 1.429215431213379} 08/31/2021 08:34:06 - INFO - __main__ - Step 106438: {'lr': 9.948362111026002e-05, 'samples': 20436096, 'steps': 106437, 'loss/train': 1.5952142477035522} 08/31/2021 08:34:07 - INFO - __main__ - Step 106439: {'lr': 9.947938399171783e-05, 'samples': 20436288, 'steps': 106438, 'loss/train': 0.6310433149337769} 08/31/2021 08:34:08 - INFO - __main__ - Step 106440: {'lr': 9.947514694099777e-05, 'samples': 20436480, 'steps': 106439, 'loss/train': 1.576019287109375} 08/31/2021 08:34:08 - INFO - __main__ - Step 106441: {'lr': 9.947090995810193e-05, 'samples': 20436672, 'steps': 106440, 'loss/train': 1.3177837133407593} 08/31/2021 08:34:09 - INFO - __main__ - Step 106442: {'lr': 9.946667304303214e-05, 'samples': 20436864, 'steps': 106441, 'loss/train': 1.2818820476531982} 08/31/2021 08:34:09 - INFO - __main__ - Step 106443: {'lr': 9.946243619579038e-05, 'samples': 20437056, 'steps': 106442, 'loss/train': 2.031200647354126} 08/31/2021 08:34:10 - INFO - __main__ - Step 106444: {'lr': 9.945819941637852e-05, 'samples': 20437248, 'steps': 106443, 'loss/train': 1.319132924079895} 08/31/2021 08:34:11 - INFO - __main__ - Step 106445: {'lr': 9.945396270479845e-05, 'samples': 20437440, 'steps': 106444, 'loss/train': 1.3896379470825195} 08/31/2021 08:34:11 - INFO - __main__ - Step 106446: {'lr': 9.94497260610521e-05, 'samples': 20437632, 'steps': 106445, 'loss/train': 1.0649774074554443} 08/31/2021 08:34:12 - INFO - __main__ - Step 106447: {'lr': 9.94454894851414e-05, 'samples': 20437824, 'steps': 106446, 'loss/train': 1.3220993280410767} 08/31/2021 08:34:12 - INFO - __main__ - Step 106448: {'lr': 9.944125297706822e-05, 'samples': 20438016, 'steps': 106447, 'loss/train': 1.5773776769638062} 08/31/2021 08:34:12 - INFO - __main__ - Step 106449: {'lr': 9.943701653683449e-05, 'samples': 20438208, 'steps': 106448, 'loss/train': 0.6257185339927673} 08/31/2021 08:34:15 - INFO - __main__ - Step 106450: {'lr': 9.943278016444221e-05, 'samples': 20438400, 'steps': 106449, 'loss/train': 0.8363649845123291} 08/31/2021 08:34:15 - INFO - __main__ - Step 106451: {'lr': 9.942854385989311e-05, 'samples': 20438592, 'steps': 106450, 'loss/train': 6.048529148101807} 08/31/2021 08:34:16 - INFO - __main__ - Step 106452: {'lr': 9.942430762318919e-05, 'samples': 20438784, 'steps': 106451, 'loss/train': 1.093256950378418} 08/31/2021 08:34:16 - INFO - __main__ - Step 106453: {'lr': 9.942007145433235e-05, 'samples': 20438976, 'steps': 106452, 'loss/train': 2.33879017829895} 08/31/2021 08:34:17 - INFO - __main__ - Step 106454: {'lr': 9.941583535332451e-05, 'samples': 20439168, 'steps': 106453, 'loss/train': 1.0425647497177124} 08/31/2021 08:34:17 - INFO - __main__ - Step 106455: {'lr': 9.941159932016755e-05, 'samples': 20439360, 'steps': 106454, 'loss/train': 0.5747717618942261} 08/31/2021 08:34:18 - INFO - __main__ - Step 106456: {'lr': 9.940736335486341e-05, 'samples': 20439552, 'steps': 106455, 'loss/train': 0.5617252588272095} 08/31/2021 08:34:19 - INFO - __main__ - Step 106457: {'lr': 9.9403127457414e-05, 'samples': 20439744, 'steps': 106456, 'loss/train': 0.14412470161914825} 08/31/2021 08:34:19 - INFO - __main__ - Step 106458: {'lr': 9.93988916278212e-05, 'samples': 20439936, 'steps': 106457, 'loss/train': 0.6074172854423523} 08/31/2021 08:34:20 - INFO - __main__ - Step 106459: {'lr': 9.939465586608695e-05, 'samples': 20440128, 'steps': 106458, 'loss/train': 1.1553648710250854} 08/31/2021 08:34:20 - INFO - __main__ - Step 106460: {'lr': 9.939042017221314e-05, 'samples': 20440320, 'steps': 106459, 'loss/train': 2.3184587955474854} 08/31/2021 08:34:20 - INFO - __main__ - Step 106461: {'lr': 9.938618454620177e-05, 'samples': 20440512, 'steps': 106460, 'loss/train': 1.6085314750671387} 08/31/2021 08:34:22 - INFO - __main__ - Step 106462: {'lr': 9.938194898805455e-05, 'samples': 20440704, 'steps': 106461, 'loss/train': 1.7261931896209717} 08/31/2021 08:34:23 - INFO - __main__ - Step 106463: {'lr': 9.937771349777353e-05, 'samples': 20440896, 'steps': 106462, 'loss/train': 1.352246642112732} 08/31/2021 08:34:23 - INFO - __main__ - Step 106464: {'lr': 9.937347807536056e-05, 'samples': 20441088, 'steps': 106463, 'loss/train': 1.1619857549667358} 08/31/2021 08:34:23 - INFO - __main__ - Step 106465: {'lr': 9.936924272081762e-05, 'samples': 20441280, 'steps': 106464, 'loss/train': 0.022391123697161674} 08/31/2021 08:34:24 - INFO - __main__ - Step 106466: {'lr': 9.936500743414653e-05, 'samples': 20441472, 'steps': 106465, 'loss/train': 0.4027904272079468} 08/31/2021 08:34:24 - INFO - __main__ - Step 106467: {'lr': 9.936077221534928e-05, 'samples': 20441664, 'steps': 106466, 'loss/train': 1.5638537406921387} 08/31/2021 08:34:26 - INFO - __main__ - Step 106468: {'lr': 9.935653706442771e-05, 'samples': 20441856, 'steps': 106467, 'loss/train': 1.1240527629852295} 08/31/2021 08:34:26 - INFO - __main__ - Step 106469: {'lr': 9.935230198138378e-05, 'samples': 20442048, 'steps': 106468, 'loss/train': 0.9819787740707397} 08/31/2021 08:34:27 - INFO - __main__ - Step 106470: {'lr': 9.934806696621937e-05, 'samples': 20442240, 'steps': 106469, 'loss/train': 0.9124958515167236} 08/31/2021 08:34:27 - INFO - __main__ - Step 106471: {'lr': 9.93438320189364e-05, 'samples': 20442432, 'steps': 106470, 'loss/train': 0.4425491392612457} 08/31/2021 08:34:27 - INFO - __main__ - Step 106472: {'lr': 9.933959713953677e-05, 'samples': 20442624, 'steps': 106471, 'loss/train': 0.09410364925861359} 08/31/2021 08:34:29 - INFO - __main__ - Step 106473: {'lr': 9.93353623280224e-05, 'samples': 20442816, 'steps': 106472, 'loss/train': 1.178957462310791} 08/31/2021 08:34:30 - INFO - __main__ - Step 106474: {'lr': 9.933112758439528e-05, 'samples': 20443008, 'steps': 106473, 'loss/train': 0.9686446189880371} 08/31/2021 08:34:30 - INFO - __main__ - Step 106475: {'lr': 9.932689290865712e-05, 'samples': 20443200, 'steps': 106474, 'loss/train': 1.30351984500885} 08/31/2021 08:34:31 - INFO - __main__ - Step 106476: {'lr': 9.932265830080998e-05, 'samples': 20443392, 'steps': 106475, 'loss/train': 1.4824296236038208} 08/31/2021 08:34:31 - INFO - __main__ - Step 106477: {'lr': 9.931842376085567e-05, 'samples': 20443584, 'steps': 106476, 'loss/train': 1.0480976104736328} 08/31/2021 08:34:32 - INFO - __main__ - Step 106478: {'lr': 9.931418928879618e-05, 'samples': 20443776, 'steps': 106477, 'loss/train': 1.3646457195281982} 08/31/2021 08:34:33 - INFO - __main__ - Step 106479: {'lr': 9.930995488463341e-05, 'samples': 20443968, 'steps': 106478, 'loss/train': 1.1519526243209839} 08/31/2021 08:34:33 - INFO - __main__ - Step 106480: {'lr': 9.930572054836923e-05, 'samples': 20444160, 'steps': 106479, 'loss/train': 0.27700695395469666} 08/31/2021 08:34:34 - INFO - __main__ - Step 106481: {'lr': 9.930148628000556e-05, 'samples': 20444352, 'steps': 106480, 'loss/train': 2.0089292526245117} 08/31/2021 08:34:34 - INFO - __main__ - Step 106482: {'lr': 9.929725207954433e-05, 'samples': 20444544, 'steps': 106481, 'loss/train': 0.7452793717384338} 08/31/2021 08:34:36 - INFO - __main__ - Step 106483: {'lr': 9.929301794698742e-05, 'samples': 20444736, 'steps': 106482, 'loss/train': 1.4425132274627686} 08/31/2021 08:34:37 - INFO - __main__ - Step 106484: {'lr': 9.928878388233676e-05, 'samples': 20444928, 'steps': 106483, 'loss/train': 0.05790594965219498} 08/31/2021 08:34:37 - INFO - __main__ - Step 106485: {'lr': 9.928454988559423e-05, 'samples': 20445120, 'steps': 106484, 'loss/train': 0.08905353397130966} 08/31/2021 08:34:37 - INFO - __main__ - Step 106486: {'lr': 9.928031595676177e-05, 'samples': 20445312, 'steps': 106485, 'loss/train': 0.031680166721343994} 08/31/2021 08:34:38 - INFO - __main__ - Step 106487: {'lr': 9.927608209584126e-05, 'samples': 20445504, 'steps': 106486, 'loss/train': 0.8556455969810486} 08/31/2021 08:34:38 - INFO - __main__ - Step 106488: {'lr': 9.927184830283476e-05, 'samples': 20445696, 'steps': 106487, 'loss/train': 1.2920857667922974} 08/31/2021 08:34:40 - INFO - __main__ - Step 106489: {'lr': 9.926761457774389e-05, 'samples': 20445888, 'steps': 106488, 'loss/train': 0.6323469281196594} 08/31/2021 08:34:40 - INFO - __main__ - Step 106490: {'lr': 9.926338092057075e-05, 'samples': 20446080, 'steps': 106489, 'loss/train': 0.9891965389251709} 08/31/2021 08:34:40 - INFO - __main__ - Step 106491: {'lr': 9.92591473313172e-05, 'samples': 20446272, 'steps': 106490, 'loss/train': 1.2984215021133423} 08/31/2021 08:34:41 - INFO - __main__ - Step 106492: {'lr': 9.925491380998511e-05, 'samples': 20446464, 'steps': 106491, 'loss/train': 0.8434588313102722} 08/31/2021 08:34:41 - INFO - __main__ - Step 106493: {'lr': 9.925068035657647e-05, 'samples': 20446656, 'steps': 106492, 'loss/train': 1.2831617593765259} 08/31/2021 08:34:41 - INFO - __main__ - Step 106494: {'lr': 9.924644697109314e-05, 'samples': 20446848, 'steps': 106493, 'loss/train': 1.7612968683242798} 08/31/2021 08:34:43 - INFO - __main__ - Step 106495: {'lr': 9.924221365353702e-05, 'samples': 20447040, 'steps': 106494, 'loss/train': 1.5064847469329834} 08/31/2021 08:34:43 - INFO - __main__ - Step 106496: {'lr': 9.923798040391005e-05, 'samples': 20447232, 'steps': 106495, 'loss/train': 0.8696641325950623} 08/31/2021 08:34:44 - INFO - __main__ - Step 106497: {'lr': 9.923374722221409e-05, 'samples': 20447424, 'steps': 106496, 'loss/train': 0.9547936320304871} 08/31/2021 08:34:44 - INFO - __main__ - Step 106498: {'lr': 9.92295141084511e-05, 'samples': 20447616, 'steps': 106497, 'loss/train': 1.2308852672576904} 08/31/2021 08:34:44 - INFO - __main__ - Step 106499: {'lr': 9.922528106262296e-05, 'samples': 20447808, 'steps': 106498, 'loss/train': 1.2933210134506226} 08/31/2021 08:34:46 - INFO - __main__ - Step 106500: {'lr': 9.92210480847316e-05, 'samples': 20448000, 'steps': 106499, 'loss/train': 0.9766151905059814} 08/31/2021 08:34:46 - INFO - __main__ - Step 106501: {'lr': 9.921681517477899e-05, 'samples': 20448192, 'steps': 106500, 'loss/train': 0.7733757495880127} 08/31/2021 08:34:47 - INFO - __main__ - Step 106502: {'lr': 9.921258233276687e-05, 'samples': 20448384, 'steps': 106501, 'loss/train': 0.9134508371353149} 08/31/2021 08:34:47 - INFO - __main__ - Step 106503: {'lr': 9.92083495586972e-05, 'samples': 20448576, 'steps': 106502, 'loss/train': 1.4527747631072998} 08/31/2021 08:34:47 - INFO - __main__ - Step 106504: {'lr': 9.920411685257194e-05, 'samples': 20448768, 'steps': 106503, 'loss/train': 1.0987684726715088} 08/31/2021 08:34:49 - INFO - __main__ - Step 106505: {'lr': 9.9199884214393e-05, 'samples': 20448960, 'steps': 106504, 'loss/train': 0.8819124698638916} 08/31/2021 08:34:49 - INFO - __main__ - Step 106506: {'lr': 9.919565164416224e-05, 'samples': 20449152, 'steps': 106505, 'loss/train': 0.6912347674369812} 08/31/2021 08:34:50 - INFO - __main__ - Step 106507: {'lr': 9.91914191418816e-05, 'samples': 20449344, 'steps': 106506, 'loss/train': 1.2933293581008911} 08/31/2021 08:34:50 - INFO - __main__ - Step 106508: {'lr': 9.918718670755297e-05, 'samples': 20449536, 'steps': 106507, 'loss/train': 1.0696001052856445} 08/31/2021 08:34:50 - INFO - __main__ - Step 106509: {'lr': 9.91829543411783e-05, 'samples': 20449728, 'steps': 106508, 'loss/train': 1.312199592590332} 08/31/2021 08:34:52 - INFO - __main__ - Step 106510: {'lr': 9.917872204275944e-05, 'samples': 20449920, 'steps': 106509, 'loss/train': 1.0121757984161377} 08/31/2021 08:34:53 - INFO - __main__ - Step 106511: {'lr': 9.917448981229832e-05, 'samples': 20450112, 'steps': 106510, 'loss/train': 0.08971413969993591} 08/31/2021 08:34:53 - INFO - __main__ - Step 106512: {'lr': 9.917025764979684e-05, 'samples': 20450304, 'steps': 106511, 'loss/train': 1.1984758377075195} 08/31/2021 08:34:53 - INFO - __main__ - Step 106513: {'lr': 9.916602555525692e-05, 'samples': 20450496, 'steps': 106512, 'loss/train': 1.3840259313583374} 08/31/2021 08:34:54 - INFO - __main__ - Step 106514: {'lr': 9.916179352868054e-05, 'samples': 20450688, 'steps': 106513, 'loss/train': 1.2555431127548218} 08/31/2021 08:34:55 - INFO - __main__ - Step 106515: {'lr': 9.915756157006947e-05, 'samples': 20450880, 'steps': 106514, 'loss/train': 0.9241752624511719} 08/31/2021 08:34:56 - INFO - __main__ - Step 106516: {'lr': 9.915332967942564e-05, 'samples': 20451072, 'steps': 106515, 'loss/train': 0.6033097505569458} 08/31/2021 08:34:56 - INFO - __main__ - Step 106517: {'lr': 9.914909785675102e-05, 'samples': 20451264, 'steps': 106516, 'loss/train': 0.23016797006130219} 08/31/2021 08:34:56 - INFO - __main__ - Step 106518: {'lr': 9.914486610204749e-05, 'samples': 20451456, 'steps': 106517, 'loss/train': 0.5547255873680115} 08/31/2021 08:34:57 - INFO - __main__ - Step 106519: {'lr': 9.914063441531693e-05, 'samples': 20451648, 'steps': 106518, 'loss/train': 0.7967595458030701} 08/31/2021 08:34:58 - INFO - __main__ - Step 106520: {'lr': 9.913640279656128e-05, 'samples': 20451840, 'steps': 106519, 'loss/train': 1.524399757385254} 08/31/2021 08:34:59 - INFO - __main__ - Step 106521: {'lr': 9.913217124578245e-05, 'samples': 20452032, 'steps': 106520, 'loss/train': 1.115313172340393} 08/31/2021 08:34:59 - INFO - __main__ - Step 106522: {'lr': 9.912793976298235e-05, 'samples': 20452224, 'steps': 106521, 'loss/train': 1.1113485097885132} 08/31/2021 08:35:00 - INFO - __main__ - Step 106523: {'lr': 9.912370834816283e-05, 'samples': 20452416, 'steps': 106522, 'loss/train': 0.2558375597000122} 08/31/2021 08:35:00 - INFO - __main__ - Step 106524: {'lr': 9.911947700132587e-05, 'samples': 20452608, 'steps': 106523, 'loss/train': 0.59176105260849} 08/31/2021 08:35:00 - INFO - __main__ - Step 106525: {'lr': 9.911524572247332e-05, 'samples': 20452800, 'steps': 106524, 'loss/train': 0.5006262063980103} 08/31/2021 08:35:02 - INFO - __main__ - Step 106526: {'lr': 9.911101451160715e-05, 'samples': 20452992, 'steps': 106525, 'loss/train': 1.3276184797286987} 08/31/2021 08:35:03 - INFO - __main__ - Step 106527: {'lr': 9.910678336872919e-05, 'samples': 20453184, 'steps': 106526, 'loss/train': 1.0212500095367432} 08/31/2021 08:35:03 - INFO - __main__ - Step 106528: {'lr': 9.91025522938415e-05, 'samples': 20453376, 'steps': 106527, 'loss/train': 1.4206050634384155} 08/31/2021 08:35:03 - INFO - __main__ - Step 106529: {'lr': 9.909832128694577e-05, 'samples': 20453568, 'steps': 106528, 'loss/train': 1.4157977104187012} 08/31/2021 08:35:04 - INFO - __main__ - Step 106530: {'lr': 9.909409034804401e-05, 'samples': 20453760, 'steps': 106529, 'loss/train': 0.9235005974769592} 08/31/2021 08:35:05 - INFO - __main__ - Step 106531: {'lr': 9.908985947713814e-05, 'samples': 20453952, 'steps': 106530, 'loss/train': 1.224161148071289} 08/31/2021 08:35:06 - INFO - __main__ - Step 106532: {'lr': 9.908562867423002e-05, 'samples': 20454144, 'steps': 106531, 'loss/train': 0.6362735629081726} 08/31/2021 08:35:06 - INFO - __main__ - Step 106533: {'lr': 9.908139793932161e-05, 'samples': 20454336, 'steps': 106532, 'loss/train': 0.978369414806366} 08/31/2021 08:35:07 - INFO - __main__ - Step 106534: {'lr': 9.907716727241478e-05, 'samples': 20454528, 'steps': 106533, 'loss/train': 0.46998175978660583} 08/31/2021 08:35:07 - INFO - __main__ - Step 106535: {'lr': 9.907293667351148e-05, 'samples': 20454720, 'steps': 106534, 'loss/train': 0.9472569823265076} 08/31/2021 08:35:08 - INFO - __main__ - Step 106536: {'lr': 9.906870614261355e-05, 'samples': 20454912, 'steps': 106535, 'loss/train': 1.3601396083831787} 08/31/2021 08:35:09 - INFO - __main__ - Step 106537: {'lr': 9.906447567972293e-05, 'samples': 20455104, 'steps': 106536, 'loss/train': 1.4235756397247314} 08/31/2021 08:35:09 - INFO - __main__ - Step 106538: {'lr': 9.906024528484155e-05, 'samples': 20455296, 'steps': 106537, 'loss/train': 1.812826156616211} 08/31/2021 08:35:10 - INFO - __main__ - Step 106539: {'lr': 9.905601495797128e-05, 'samples': 20455488, 'steps': 106538, 'loss/train': 1.3212920427322388} 08/31/2021 08:35:10 - INFO - __main__ - Step 106540: {'lr': 9.905178469911405e-05, 'samples': 20455680, 'steps': 106539, 'loss/train': 1.3518236875534058} 08/31/2021 08:35:12 - INFO - __main__ - Step 106541: {'lr': 9.904755450827185e-05, 'samples': 20455872, 'steps': 106540, 'loss/train': 0.3625265955924988} 08/31/2021 08:35:12 - INFO - __main__ - Step 106542: {'lr': 9.904332438544638e-05, 'samples': 20456064, 'steps': 106541, 'loss/train': 1.4798510074615479} 08/31/2021 08:35:13 - INFO - __main__ - Step 106543: {'lr': 9.903909433063968e-05, 'samples': 20456256, 'steps': 106542, 'loss/train': 0.027513084933161736} 08/31/2021 08:35:13 - INFO - __main__ - Step 106544: {'lr': 9.903486434385364e-05, 'samples': 20456448, 'steps': 106543, 'loss/train': 0.016546977683901787} 08/31/2021 08:35:13 - INFO - __main__ - Step 106545: {'lr': 9.903063442509013e-05, 'samples': 20456640, 'steps': 106544, 'loss/train': 1.0375328063964844} 08/31/2021 08:35:14 - INFO - __main__ - Step 106546: {'lr': 9.902640457435111e-05, 'samples': 20456832, 'steps': 106545, 'loss/train': 1.78213632106781} 08/31/2021 08:35:14 - INFO - __main__ - Step 106547: {'lr': 9.902217479163847e-05, 'samples': 20457024, 'steps': 106546, 'loss/train': 0.9682788252830505} 08/31/2021 08:35:16 - INFO - __main__ - Step 106548: {'lr': 9.90179450769541e-05, 'samples': 20457216, 'steps': 106547, 'loss/train': 1.3639421463012695} 08/31/2021 08:35:16 - INFO - __main__ - Step 106549: {'lr': 9.90137154302999e-05, 'samples': 20457408, 'steps': 106548, 'loss/train': 0.02143639139831066} 08/31/2021 08:35:16 - INFO - __main__ - Step 106550: {'lr': 9.900948585167782e-05, 'samples': 20457600, 'steps': 106549, 'loss/train': 0.6885313987731934} 08/31/2021 08:35:17 - INFO - __main__ - Step 106551: {'lr': 9.90052563410897e-05, 'samples': 20457792, 'steps': 106550, 'loss/train': 0.8640162348747253} 08/31/2021 08:35:17 - INFO - __main__ - Step 106552: {'lr': 9.900102689853751e-05, 'samples': 20457984, 'steps': 106551, 'loss/train': 0.35630711913108826} 08/31/2021 08:35:19 - INFO - __main__ - Step 106553: {'lr': 9.89967975240231e-05, 'samples': 20458176, 'steps': 106552, 'loss/train': 1.1596604585647583} 08/31/2021 08:35:20 - INFO - __main__ - Step 106554: {'lr': 9.899256821754843e-05, 'samples': 20458368, 'steps': 106553, 'loss/train': 0.8805127143859863} 08/31/2021 08:35:20 - INFO - __main__ - Step 106555: {'lr': 9.898833897911547e-05, 'samples': 20458560, 'steps': 106554, 'loss/train': 0.01374222245067358} 08/31/2021 08:35:20 - INFO - __main__ - Step 106556: {'lr': 9.898410980872591e-05, 'samples': 20458752, 'steps': 106555, 'loss/train': 0.05045250058174133} 08/31/2021 08:35:21 - INFO - __main__ - Step 106557: {'lr': 9.897988070638181e-05, 'samples': 20458944, 'steps': 106556, 'loss/train': 1.0277256965637207} 08/31/2021 08:35:21 - INFO - __main__ - Step 106558: {'lr': 9.897565167208502e-05, 'samples': 20459136, 'steps': 106557, 'loss/train': 1.3863810300827026} 08/31/2021 08:35:22 - INFO - __main__ - Step 106559: {'lr': 9.897142270583751e-05, 'samples': 20459328, 'steps': 106558, 'loss/train': 1.1016541719436646} 08/31/2021 08:35:23 - INFO - __main__ - Step 106560: {'lr': 9.896719380764114e-05, 'samples': 20459520, 'steps': 106559, 'loss/train': 0.23912057280540466} 08/31/2021 08:35:23 - INFO - __main__ - Step 106561: {'lr': 9.896296497749779e-05, 'samples': 20459712, 'steps': 106560, 'loss/train': 1.3517801761627197} 08/31/2021 08:35:24 - INFO - __main__ - Step 106562: {'lr': 9.89587362154094e-05, 'samples': 20459904, 'steps': 106561, 'loss/train': 1.0175424814224243} 08/31/2021 08:35:24 - INFO - __main__ - Step 106563: {'lr': 9.895450752137788e-05, 'samples': 20460096, 'steps': 106562, 'loss/train': 1.258460521697998} 08/31/2021 08:35:26 - INFO - __main__ - Step 106564: {'lr': 9.895027889540515e-05, 'samples': 20460288, 'steps': 106563, 'loss/train': 1.238884687423706} 08/31/2021 08:35:26 - INFO - __main__ - Step 106565: {'lr': 9.894605033749307e-05, 'samples': 20460480, 'steps': 106564, 'loss/train': 0.9797247648239136} 08/31/2021 08:35:26 - INFO - __main__ - Step 106566: {'lr': 9.894182184764358e-05, 'samples': 20460672, 'steps': 106565, 'loss/train': 1.1793612241744995} 08/31/2021 08:35:27 - INFO - __main__ - Step 106567: {'lr': 9.893759342585856e-05, 'samples': 20460864, 'steps': 106566, 'loss/train': 1.310068964958191} 08/31/2021 08:35:27 - INFO - __main__ - Step 106568: {'lr': 9.893336507214004e-05, 'samples': 20461056, 'steps': 106567, 'loss/train': 0.758661687374115} 08/31/2021 08:35:27 - INFO - __main__ - Step 106569: {'lr': 9.892913678648972e-05, 'samples': 20461248, 'steps': 106568, 'loss/train': 0.041265204548835754} 08/31/2021 08:35:29 - INFO - __main__ - Step 106570: {'lr': 9.892490856890959e-05, 'samples': 20461440, 'steps': 106569, 'loss/train': 0.5827274918556213} 08/31/2021 08:35:29 - INFO - __main__ - Step 106571: {'lr': 9.892068041940155e-05, 'samples': 20461632, 'steps': 106570, 'loss/train': 1.2484445571899414} 08/31/2021 08:35:30 - INFO - __main__ - Step 106572: {'lr': 9.891645233796756e-05, 'samples': 20461824, 'steps': 106571, 'loss/train': 0.7127681970596313} 08/31/2021 08:35:30 - INFO - __main__ - Step 106573: {'lr': 9.891222432460947e-05, 'samples': 20462016, 'steps': 106572, 'loss/train': 1.1144007444381714} 08/31/2021 08:35:30 - INFO - __main__ - Step 106574: {'lr': 9.890799637932918e-05, 'samples': 20462208, 'steps': 106573, 'loss/train': 0.790219247341156} 08/31/2021 08:35:32 - INFO - __main__ - Step 106575: {'lr': 9.890376850212865e-05, 'samples': 20462400, 'steps': 106574, 'loss/train': 1.3726354837417603} 08/31/2021 08:35:33 - INFO - __main__ - Step 106576: {'lr': 9.889954069300971e-05, 'samples': 20462592, 'steps': 106575, 'loss/train': 0.04996999353170395} 08/31/2021 08:35:33 - INFO - __main__ - Step 106577: {'lr': 9.889531295197432e-05, 'samples': 20462784, 'steps': 106576, 'loss/train': 1.5195187330245972} 08/31/2021 08:35:33 - INFO - __main__ - Step 106578: {'lr': 9.889108527902437e-05, 'samples': 20462976, 'steps': 106577, 'loss/train': 0.8841964602470398} 08/31/2021 08:35:34 - INFO - __main__ - Step 106579: {'lr': 9.888685767416178e-05, 'samples': 20463168, 'steps': 106578, 'loss/train': 1.2197331190109253} 08/31/2021 08:35:36 - INFO - __main__ - Step 106580: {'lr': 9.888263013738843e-05, 'samples': 20463360, 'steps': 106579, 'loss/train': 1.4997198581695557} 08/31/2021 08:35:36 - INFO - __main__ - Step 106581: {'lr': 9.887840266870624e-05, 'samples': 20463552, 'steps': 106580, 'loss/train': 1.3502708673477173} 08/31/2021 08:35:37 - INFO - __main__ - Step 106582: {'lr': 9.88741752681172e-05, 'samples': 20463744, 'steps': 106581, 'loss/train': 0.7004910111427307} 08/31/2021 08:35:37 - INFO - __main__ - Step 106583: {'lr': 9.886994793562304e-05, 'samples': 20463936, 'steps': 106582, 'loss/train': 1.0055773258209229} 08/31/2021 08:35:37 - INFO - __main__ - Step 106584: {'lr': 9.886572067122574e-05, 'samples': 20464128, 'steps': 106583, 'loss/train': 0.3867133855819702} 08/31/2021 08:35:39 - INFO - __main__ - Step 106585: {'lr': 9.886149347492721e-05, 'samples': 20464320, 'steps': 106584, 'loss/train': 1.0475118160247803} 08/31/2021 08:35:39 - INFO - __main__ - Step 106586: {'lr': 9.885726634672937e-05, 'samples': 20464512, 'steps': 106585, 'loss/train': 1.6610668897628784} 08/31/2021 08:35:39 - INFO - __main__ - Step 106587: {'lr': 9.885303928663411e-05, 'samples': 20464704, 'steps': 106586, 'loss/train': 0.9903727769851685} 08/31/2021 08:35:40 - INFO - __main__ - Step 106588: {'lr': 9.884881229464332e-05, 'samples': 20464896, 'steps': 106587, 'loss/train': 1.049225091934204} 08/31/2021 08:35:40 - INFO - __main__ - Step 106589: {'lr': 9.884458537075894e-05, 'samples': 20465088, 'steps': 106588, 'loss/train': 0.9047696590423584} 08/31/2021 08:35:42 - INFO - __main__ - Step 106590: {'lr': 9.884035851498285e-05, 'samples': 20465280, 'steps': 106589, 'loss/train': 1.1184444427490234} 08/31/2021 08:35:42 - INFO - __main__ - Step 106591: {'lr': 9.883613172731698e-05, 'samples': 20465472, 'steps': 106590, 'loss/train': 0.9188616871833801} 08/31/2021 08:35:43 - INFO - __main__ - Step 106592: {'lr': 9.88319050077632e-05, 'samples': 20465664, 'steps': 106591, 'loss/train': 0.5570932030677795} 08/31/2021 08:35:43 - INFO - __main__ - Step 106593: {'lr': 9.882767835632342e-05, 'samples': 20465856, 'steps': 106592, 'loss/train': 0.6814382672309875} 08/31/2021 08:35:43 - INFO - __main__ - Step 106594: {'lr': 9.882345177299958e-05, 'samples': 20466048, 'steps': 106593, 'loss/train': 1.0957986116409302} 08/31/2021 08:35:45 - INFO - __main__ - Step 106595: {'lr': 9.881922525779364e-05, 'samples': 20466240, 'steps': 106594, 'loss/train': 1.7813136577606201} 08/31/2021 08:35:45 - INFO - __main__ - Step 106596: {'lr': 9.881499881070733e-05, 'samples': 20466432, 'steps': 106595, 'loss/train': 1.2328330278396606} 08/31/2021 08:35:46 - INFO - __main__ - Step 106597: {'lr': 9.881077243174266e-05, 'samples': 20466624, 'steps': 106596, 'loss/train': 0.9377177953720093} 08/31/2021 08:35:46 - INFO - __main__ - Step 106598: {'lr': 9.880654612090151e-05, 'samples': 20466816, 'steps': 106597, 'loss/train': 1.0200269222259521} 08/31/2021 08:35:46 - INFO - __main__ - Step 106599: {'lr': 9.880231987818581e-05, 'samples': 20467008, 'steps': 106598, 'loss/train': 0.9116693139076233} 08/31/2021 08:35:48 - INFO - __main__ - Step 106600: {'lr': 9.879809370359744e-05, 'samples': 20467200, 'steps': 106599, 'loss/train': 0.4428243637084961} 08/31/2021 08:35:49 - INFO - __main__ - Step 106601: {'lr': 9.879386759713833e-05, 'samples': 20467392, 'steps': 106600, 'loss/train': 1.0681976079940796} 08/31/2021 08:35:49 - INFO - __main__ - Step 106602: {'lr': 9.878964155881034e-05, 'samples': 20467584, 'steps': 106601, 'loss/train': 0.8559277057647705} 08/31/2021 08:35:49 - INFO - __main__ - Step 106603: {'lr': 9.878541558861543e-05, 'samples': 20467776, 'steps': 106602, 'loss/train': 0.9700613021850586} 08/31/2021 08:35:50 - INFO - __main__ - Step 106604: {'lr': 9.878118968655547e-05, 'samples': 20467968, 'steps': 106603, 'loss/train': 0.9791941046714783} 08/31/2021 08:35:50 - INFO - __main__ - Step 106605: {'lr': 9.877696385263238e-05, 'samples': 20468160, 'steps': 106604, 'loss/train': 1.1678842306137085} 08/31/2021 08:35:51 - INFO - __main__ - Step 106606: {'lr': 9.877273808684805e-05, 'samples': 20468352, 'steps': 106605, 'loss/train': 0.5161897540092468} 08/31/2021 08:35:52 - INFO - __main__ - Step 106607: {'lr': 9.876851238920439e-05, 'samples': 20468544, 'steps': 106606, 'loss/train': 0.9759429097175598} 08/31/2021 08:35:52 - INFO - __main__ - Step 106608: {'lr': 9.876428675970331e-05, 'samples': 20468736, 'steps': 106607, 'loss/train': 1.4587640762329102} 08/31/2021 08:35:53 - INFO - __main__ - Step 106609: {'lr': 9.87600611983468e-05, 'samples': 20468928, 'steps': 106608, 'loss/train': 1.1659175157546997} 08/31/2021 08:35:53 - INFO - __main__ - Step 106610: {'lr': 9.875583570513657e-05, 'samples': 20469120, 'steps': 106609, 'loss/train': 1.0716065168380737} 08/31/2021 08:35:55 - INFO - __main__ - Step 106611: {'lr': 9.875161028007465e-05, 'samples': 20469312, 'steps': 106610, 'loss/train': 0.9571855068206787} 08/31/2021 08:35:55 - INFO - __main__ - Step 106612: {'lr': 9.87473849231629e-05, 'samples': 20469504, 'steps': 106611, 'loss/train': 1.631066083908081} 08/31/2021 08:35:55 - INFO - __main__ - Step 106613: {'lr': 9.874315963440326e-05, 'samples': 20469696, 'steps': 106612, 'loss/train': 1.1737315654754639} 08/31/2021 08:35:56 - INFO - __main__ - Step 106614: {'lr': 9.873893441379759e-05, 'samples': 20469888, 'steps': 106613, 'loss/train': 0.40402042865753174} 08/31/2021 08:35:56 - INFO - __main__ - Step 106615: {'lr': 9.873470926134783e-05, 'samples': 20470080, 'steps': 106614, 'loss/train': 1.3544535636901855} 08/31/2021 08:35:58 - INFO - __main__ - Step 106616: {'lr': 9.873048417705591e-05, 'samples': 20470272, 'steps': 106615, 'loss/train': 1.4916739463806152} 08/31/2021 08:35:59 - INFO - __main__ - Step 106617: {'lr': 9.872625916092365e-05, 'samples': 20470464, 'steps': 106616, 'loss/train': 1.1282806396484375} 08/31/2021 08:35:59 - INFO - __main__ - Step 106618: {'lr': 9.872203421295304e-05, 'samples': 20470656, 'steps': 106617, 'loss/train': 1.260718584060669} 08/31/2021 08:35:59 - INFO - __main__ - Step 106619: {'lr': 9.871780933314595e-05, 'samples': 20470848, 'steps': 106618, 'loss/train': 1.3517131805419922} 08/31/2021 08:36:00 - INFO - __main__ - Step 106620: {'lr': 9.871358452150425e-05, 'samples': 20471040, 'steps': 106619, 'loss/train': 1.138325572013855} 08/31/2021 08:36:00 - INFO - __main__ - Step 106621: {'lr': 9.870935977802988e-05, 'samples': 20471232, 'steps': 106620, 'loss/train': 1.2402875423431396} 08/31/2021 08:36:02 - INFO - __main__ - Step 106622: {'lr': 9.870513510272486e-05, 'samples': 20471424, 'steps': 106621, 'loss/train': 1.342515230178833} 08/31/2021 08:36:02 - INFO - __main__ - Step 106623: {'lr': 9.870091049559086e-05, 'samples': 20471616, 'steps': 106622, 'loss/train': 0.5832355618476868} 08/31/2021 08:36:02 - INFO - __main__ - Step 106624: {'lr': 9.86966859566299e-05, 'samples': 20471808, 'steps': 106623, 'loss/train': 1.0541296005249023} 08/31/2021 08:36:03 - INFO - __main__ - Step 106625: {'lr': 9.869246148584385e-05, 'samples': 20472000, 'steps': 106624, 'loss/train': 1.312065601348877} 08/31/2021 08:36:03 - INFO - __main__ - Step 106626: {'lr': 9.868823708323468e-05, 'samples': 20472192, 'steps': 106625, 'loss/train': 1.0897235870361328} 08/31/2021 08:36:05 - INFO - __main__ - Step 106627: {'lr': 9.868401274880423e-05, 'samples': 20472384, 'steps': 106626, 'loss/train': 0.7864401936531067} 08/31/2021 08:36:05 - INFO - __main__ - Step 106628: {'lr': 9.867978848255443e-05, 'samples': 20472576, 'steps': 106627, 'loss/train': 1.54884934425354} 08/31/2021 08:36:05 - INFO - __main__ - Step 106629: {'lr': 9.86755642844872e-05, 'samples': 20472768, 'steps': 106628, 'loss/train': 1.0426608324050903} 08/31/2021 08:36:06 - INFO - __main__ - Step 106630: {'lr': 9.867134015460444e-05, 'samples': 20472960, 'steps': 106629, 'loss/train': 1.3594930171966553} 08/31/2021 08:36:06 - INFO - __main__ - Step 106631: {'lr': 9.866711609290801e-05, 'samples': 20473152, 'steps': 106630, 'loss/train': 0.1568768322467804} 08/31/2021 08:36:08 - INFO - __main__ - Step 106632: {'lr': 9.866289209939986e-05, 'samples': 20473344, 'steps': 106631, 'loss/train': 0.032871540635824203} 08/31/2021 08:36:08 - INFO - __main__ - Step 106633: {'lr': 9.865866817408184e-05, 'samples': 20473536, 'steps': 106632, 'loss/train': 1.7754801511764526} 08/31/2021 08:36:08 - INFO - __main__ - Step 106634: {'lr': 9.865444431695592e-05, 'samples': 20473728, 'steps': 106633, 'loss/train': 1.0787715911865234} 08/31/2021 08:36:09 - INFO - __main__ - Step 106635: {'lr': 9.865022052802405e-05, 'samples': 20473920, 'steps': 106634, 'loss/train': 1.1270374059677124} 08/31/2021 08:36:09 - INFO - __main__ - Step 106636: {'lr': 9.864599680728797e-05, 'samples': 20474112, 'steps': 106635, 'loss/train': 0.8257997632026672} 08/31/2021 08:36:12 - INFO - __main__ - Step 106637: {'lr': 9.864177315474967e-05, 'samples': 20474304, 'steps': 106636, 'loss/train': 2.6431593894958496} 08/31/2021 08:36:12 - INFO - __main__ - Step 106638: {'lr': 9.863754957041104e-05, 'samples': 20474496, 'steps': 106637, 'loss/train': 0.6682136654853821} 08/31/2021 08:36:13 - INFO - __main__ - Step 106639: {'lr': 9.863332605427402e-05, 'samples': 20474688, 'steps': 106638, 'loss/train': 0.8011758923530579} 08/31/2021 08:36:13 - INFO - __main__ - Step 106640: {'lr': 9.862910260634048e-05, 'samples': 20474880, 'steps': 106639, 'loss/train': 0.7778907418251038} 08/31/2021 08:36:13 - INFO - __main__ - Step 106641: {'lr': 9.862487922661232e-05, 'samples': 20475072, 'steps': 106640, 'loss/train': 1.0226514339447021} 08/31/2021 08:36:14 - INFO - __main__ - Step 106642: {'lr': 9.862065591509145e-05, 'samples': 20475264, 'steps': 106641, 'loss/train': 0.024768076837062836} 08/31/2021 08:36:16 - INFO - __main__ - Step 106643: {'lr': 9.861643267177977e-05, 'samples': 20475456, 'steps': 106642, 'loss/train': 0.04018788039684296} 08/31/2021 08:36:16 - INFO - __main__ - Step 106644: {'lr': 9.861220949667924e-05, 'samples': 20475648, 'steps': 106643, 'loss/train': 0.8645538091659546} 08/31/2021 08:36:16 - INFO - __main__ - Step 106645: {'lr': 9.860798638979165e-05, 'samples': 20475840, 'steps': 106644, 'loss/train': 1.2758333683013916} 08/31/2021 08:36:17 - INFO - __main__ - Step 106646: {'lr': 9.860376335111901e-05, 'samples': 20476032, 'steps': 106645, 'loss/train': 0.3134055733680725} 08/31/2021 08:36:17 - INFO - __main__ - Step 106647: {'lr': 9.859954038066316e-05, 'samples': 20476224, 'steps': 106646, 'loss/train': 1.0787291526794434} 08/31/2021 08:36:17 - INFO - __main__ - Step 106648: {'lr': 9.859531747842601e-05, 'samples': 20476416, 'steps': 106647, 'loss/train': 1.7909194231033325} 08/31/2021 08:36:19 - INFO - __main__ - Step 106649: {'lr': 9.859109464440957e-05, 'samples': 20476608, 'steps': 106648, 'loss/train': 1.1439169645309448} 08/31/2021 08:36:19 - INFO - __main__ - Step 106650: {'lr': 9.858687187861556e-05, 'samples': 20476800, 'steps': 106649, 'loss/train': 1.4156988859176636} 08/31/2021 08:36:20 - INFO - __main__ - Step 106651: {'lr': 9.858264918104595e-05, 'samples': 20476992, 'steps': 106650, 'loss/train': 0.3595336675643921} 08/31/2021 08:36:20 - INFO - __main__ - Step 106652: {'lr': 9.857842655170268e-05, 'samples': 20477184, 'steps': 106651, 'loss/train': 0.9943047165870667} 08/31/2021 08:36:20 - INFO - __main__ - Step 106653: {'lr': 9.857420399058764e-05, 'samples': 20477376, 'steps': 106652, 'loss/train': 1.1368998289108276} 08/31/2021 08:36:22 - INFO - __main__ - Step 106654: {'lr': 9.856998149770274e-05, 'samples': 20477568, 'steps': 106653, 'loss/train': 1.5043656826019287} 08/31/2021 08:36:22 - INFO - __main__ - Step 106655: {'lr': 9.856575907304985e-05, 'samples': 20477760, 'steps': 106654, 'loss/train': 1.061430811882019} 08/31/2021 08:36:23 - INFO - __main__ - Step 106656: {'lr': 9.856153671663088e-05, 'samples': 20477952, 'steps': 106655, 'loss/train': 0.44926589727401733} 08/31/2021 08:36:23 - INFO - __main__ - Step 106657: {'lr': 9.855731442844775e-05, 'samples': 20478144, 'steps': 106656, 'loss/train': 1.3838765621185303} 08/31/2021 08:36:24 - INFO - __main__ - Step 106658: {'lr': 9.855309220850237e-05, 'samples': 20478336, 'steps': 106657, 'loss/train': 1.523768424987793} 08/31/2021 08:36:25 - INFO - __main__ - Step 106659: {'lr': 9.854887005679663e-05, 'samples': 20478528, 'steps': 106658, 'loss/train': 0.805931806564331} 08/31/2021 08:36:26 - INFO - __main__ - Step 106660: {'lr': 9.854464797333243e-05, 'samples': 20478720, 'steps': 106659, 'loss/train': 0.6181793808937073} 08/31/2021 08:36:26 - INFO - __main__ - Step 106661: {'lr': 9.854042595811167e-05, 'samples': 20478912, 'steps': 106660, 'loss/train': 1.2613472938537598} 08/31/2021 08:36:26 - INFO - __main__ - Step 106662: {'lr': 9.853620401113636e-05, 'samples': 20479104, 'steps': 106661, 'loss/train': 0.7243856191635132} 08/31/2021 08:36:27 - INFO - __main__ - Step 106663: {'lr': 9.853198213240819e-05, 'samples': 20479296, 'steps': 106662, 'loss/train': 0.7897437810897827} 08/31/2021 08:36:29 - INFO - __main__ - Step 106664: {'lr': 9.852776032192917e-05, 'samples': 20479488, 'steps': 106663, 'loss/train': 0.7417866587638855} 08/31/2021 08:36:29 - INFO - __main__ - Step 106665: {'lr': 9.852353857970123e-05, 'samples': 20479680, 'steps': 106664, 'loss/train': 0.7734745740890503} 08/31/2021 08:36:30 - INFO - __main__ - Step 106666: {'lr': 9.851931690572621e-05, 'samples': 20479872, 'steps': 106665, 'loss/train': 0.7930748462677002} 08/31/2021 08:36:30 - INFO - __main__ - Step 106667: {'lr': 9.851509530000607e-05, 'samples': 20480064, 'steps': 106666, 'loss/train': 1.3196132183074951} 08/31/2021 08:36:30 - INFO - __main__ - Step 106668: {'lr': 9.85108737625427e-05, 'samples': 20480256, 'steps': 106667, 'loss/train': 0.020272135734558105} 08/31/2021 08:36:31 - INFO - __main__ - Step 106669: {'lr': 9.850665229333796e-05, 'samples': 20480448, 'steps': 106668, 'loss/train': 0.04018649086356163} 08/31/2021 08:36:32 - INFO - __main__ - Step 106670: {'lr': 9.850243089239383e-05, 'samples': 20480640, 'steps': 106669, 'loss/train': 1.1601611375808716} 08/31/2021 08:36:33 - INFO - __main__ - Step 106671: {'lr': 9.849820955971214e-05, 'samples': 20480832, 'steps': 106670, 'loss/train': 1.7348878383636475} 08/31/2021 08:36:33 - INFO - __main__ - Step 106672: {'lr': 9.849398829529482e-05, 'samples': 20481024, 'steps': 106671, 'loss/train': 1.1146785020828247} 08/31/2021 08:36:33 - INFO - __main__ - Step 106673: {'lr': 9.848976709914375e-05, 'samples': 20481216, 'steps': 106672, 'loss/train': 0.896639347076416} 08/31/2021 08:36:34 - INFO - __main__ - Step 106674: {'lr': 9.848554597126088e-05, 'samples': 20481408, 'steps': 106673, 'loss/train': 1.2957252264022827} 08/31/2021 08:36:35 - INFO - __main__ - Step 106675: {'lr': 9.848132491164819e-05, 'samples': 20481600, 'steps': 106674, 'loss/train': 0.7556629776954651} 08/31/2021 08:36:36 - INFO - __main__ - Step 106676: {'lr': 9.847710392030738e-05, 'samples': 20481792, 'steps': 106675, 'loss/train': 0.8994797468185425} 08/31/2021 08:36:36 - INFO - __main__ - Step 106677: {'lr': 9.847288299724042e-05, 'samples': 20481984, 'steps': 106676, 'loss/train': 1.3432037830352783} 08/31/2021 08:36:36 - INFO - __main__ - Step 106678: {'lr': 9.846866214244926e-05, 'samples': 20482176, 'steps': 106677, 'loss/train': 1.6585652828216553} 08/31/2021 08:36:37 - INFO - __main__ - Step 106679: {'lr': 9.846444135593576e-05, 'samples': 20482368, 'steps': 106678, 'loss/train': 1.9951106309890747} 08/31/2021 08:36:38 - INFO - __main__ - Step 106680: {'lr': 9.846022063770188e-05, 'samples': 20482560, 'steps': 106679, 'loss/train': 0.6962351202964783} 08/31/2021 08:36:39 - INFO - __main__ - Step 106681: {'lr': 9.845599998774946e-05, 'samples': 20482752, 'steps': 106680, 'loss/train': 0.8116294741630554} 08/31/2021 08:36:39 - INFO - __main__ - Step 106682: {'lr': 9.845177940608044e-05, 'samples': 20482944, 'steps': 106681, 'loss/train': 1.1928538084030151} 08/31/2021 08:36:39 - INFO - __main__ - Step 106683: {'lr': 9.844755889269672e-05, 'samples': 20483136, 'steps': 106682, 'loss/train': 1.5414453744888306} 08/31/2021 08:36:40 - INFO - __main__ - Step 106684: {'lr': 9.844333844760018e-05, 'samples': 20483328, 'steps': 106683, 'loss/train': 1.9208004474639893} 08/31/2021 08:36:40 - INFO - __main__ - Step 106685: {'lr': 9.843911807079272e-05, 'samples': 20483520, 'steps': 106684, 'loss/train': 1.3126285076141357} 08/31/2021 08:36:42 - INFO - __main__ - Step 106686: {'lr': 9.843489776227634e-05, 'samples': 20483712, 'steps': 106685, 'loss/train': 1.1918144226074219} 08/31/2021 08:36:42 - INFO - __main__ - Step 106687: {'lr': 9.843067752205279e-05, 'samples': 20483904, 'steps': 106686, 'loss/train': 1.2367993593215942} 08/31/2021 08:36:42 - INFO - __main__ - Step 106688: {'lr': 9.842645735012404e-05, 'samples': 20484096, 'steps': 106687, 'loss/train': 1.1305084228515625} 08/31/2021 08:36:43 - INFO - __main__ - Step 106689: {'lr': 9.8422237246492e-05, 'samples': 20484288, 'steps': 106688, 'loss/train': 0.5966020226478577} 08/31/2021 08:36:43 - INFO - __main__ - Step 106690: {'lr': 9.841801721115853e-05, 'samples': 20484480, 'steps': 106689, 'loss/train': 1.1407142877578735} 08/31/2021 08:36:45 - INFO - __main__ - Step 106691: {'lr': 9.841379724412556e-05, 'samples': 20484672, 'steps': 106690, 'loss/train': 0.15330642461776733} 08/31/2021 08:36:45 - INFO - __main__ - Step 106692: {'lr': 9.840957734539502e-05, 'samples': 20484864, 'steps': 106691, 'loss/train': 1.3311078548431396} 08/31/2021 08:36:46 - INFO - __main__ - Step 106693: {'lr': 9.840535751496876e-05, 'samples': 20485056, 'steps': 106692, 'loss/train': 2.1265251636505127} 08/31/2021 08:36:46 - INFO - __main__ - Step 106694: {'lr': 9.840113775284873e-05, 'samples': 20485248, 'steps': 106693, 'loss/train': 1.5110890865325928} 08/31/2021 08:36:46 - INFO - __main__ - Step 106695: {'lr': 9.839691805903678e-05, 'samples': 20485440, 'steps': 106694, 'loss/train': 0.7459655404090881} 08/31/2021 08:36:48 - INFO - __main__ - Step 106696: {'lr': 9.839269843353487e-05, 'samples': 20485632, 'steps': 106695, 'loss/train': 1.295630931854248} 08/31/2021 08:36:49 - INFO - __main__ - Step 106697: {'lr': 9.838847887634494e-05, 'samples': 20485824, 'steps': 106696, 'loss/train': 1.1354914903640747} 08/31/2021 08:36:49 - INFO - __main__ - Step 106698: {'lr': 9.838425938746875e-05, 'samples': 20486016, 'steps': 106697, 'loss/train': 1.2606762647628784} 08/31/2021 08:36:49 - INFO - __main__ - Step 106699: {'lr': 9.838003996690826e-05, 'samples': 20486208, 'steps': 106698, 'loss/train': 1.0671435594558716} 08/31/2021 08:36:50 - INFO - __main__ - Step 106700: {'lr': 9.837582061466538e-05, 'samples': 20486400, 'steps': 106699, 'loss/train': 1.247644066810608} 08/31/2021 08:36:51 - INFO - __main__ - Step 106701: {'lr': 9.837160133074202e-05, 'samples': 20486592, 'steps': 106700, 'loss/train': 0.592989444732666} 08/31/2021 08:36:52 - INFO - __main__ - Step 106702: {'lr': 9.836738211514007e-05, 'samples': 20486784, 'steps': 106701, 'loss/train': 1.187814712524414} 08/31/2021 08:36:52 - INFO - __main__ - Step 106703: {'lr': 9.836316296786146e-05, 'samples': 20486976, 'steps': 106702, 'loss/train': 0.9997162222862244} 08/31/2021 08:36:52 - INFO - __main__ - Step 106704: {'lr': 9.835894388890807e-05, 'samples': 20487168, 'steps': 106703, 'loss/train': 1.343563199043274} 08/31/2021 08:36:53 - INFO - __main__ - Step 106705: {'lr': 9.835472487828176e-05, 'samples': 20487360, 'steps': 106704, 'loss/train': 1.1917957067489624} 08/31/2021 08:36:54 - INFO - __main__ - Step 106706: {'lr': 9.835050593598452e-05, 'samples': 20487552, 'steps': 106705, 'loss/train': 1.2312119007110596} 08/31/2021 08:36:55 - INFO - __main__ - Step 106707: {'lr': 9.834628706201817e-05, 'samples': 20487744, 'steps': 106706, 'loss/train': 0.9456256031990051} 08/31/2021 08:36:55 - INFO - __main__ - Step 106708: {'lr': 9.834206825638473e-05, 'samples': 20487936, 'steps': 106707, 'loss/train': 1.0198482275009155} 08/31/2021 08:36:55 - INFO - __main__ - Step 106709: {'lr': 9.833784951908595e-05, 'samples': 20488128, 'steps': 106708, 'loss/train': 1.468306064605713} 08/31/2021 08:36:56 - INFO - __main__ - Step 106710: {'lr': 9.833363085012376e-05, 'samples': 20488320, 'steps': 106709, 'loss/train': 0.8699062466621399} 08/31/2021 08:36:57 - INFO - __main__ - Step 106711: {'lr': 9.832941224950012e-05, 'samples': 20488512, 'steps': 106710, 'loss/train': 1.5112814903259277} 08/31/2021 08:36:58 - INFO - __main__ - Step 106712: {'lr': 9.83251937172169e-05, 'samples': 20488704, 'steps': 106711, 'loss/train': 0.8262061476707458} 08/31/2021 08:36:58 - INFO - __main__ - Step 106713: {'lr': 9.832097525327601e-05, 'samples': 20488896, 'steps': 106712, 'loss/train': 1.353804349899292} 08/31/2021 08:36:58 - INFO - __main__ - Step 106714: {'lr': 9.831675685767935e-05, 'samples': 20489088, 'steps': 106713, 'loss/train': 0.37731316685676575} 08/31/2021 08:36:59 - INFO - __main__ - Step 106715: {'lr': 9.831253853042882e-05, 'samples': 20489280, 'steps': 106714, 'loss/train': 0.8016782402992249} 08/31/2021 08:36:59 - INFO - __main__ - Step 106716: {'lr': 9.830832027152631e-05, 'samples': 20489472, 'steps': 106715, 'loss/train': 1.060200572013855} 08/31/2021 08:37:01 - INFO - __main__ - Step 106717: {'lr': 9.830410208097373e-05, 'samples': 20489664, 'steps': 106716, 'loss/train': 0.6742435097694397} 08/31/2021 08:37:01 - INFO - __main__ - Step 106718: {'lr': 9.829988395877299e-05, 'samples': 20489856, 'steps': 106717, 'loss/train': 1.2319083213806152} 08/31/2021 08:37:02 - INFO - __main__ - Step 106719: {'lr': 9.829566590492606e-05, 'samples': 20490048, 'steps': 106718, 'loss/train': 1.0434662103652954} 08/31/2021 08:37:02 - INFO - __main__ - Step 106720: {'lr': 9.82914479194347e-05, 'samples': 20490240, 'steps': 106719, 'loss/train': 0.8506955504417419} 08/31/2021 08:37:02 - INFO - __main__ - Step 106721: {'lr': 9.828723000230083e-05, 'samples': 20490432, 'steps': 106720, 'loss/train': 0.07087195664644241} 08/31/2021 08:37:04 - INFO - __main__ - Step 106722: {'lr': 9.828301215352642e-05, 'samples': 20490624, 'steps': 106721, 'loss/train': 0.05341360718011856} 08/31/2021 08:37:04 - INFO - __main__ - Step 106723: {'lr': 9.827879437311335e-05, 'samples': 20490816, 'steps': 106722, 'loss/train': 1.1629959344863892} 08/31/2021 08:37:05 - INFO - __main__ - Step 106724: {'lr': 9.827457666106349e-05, 'samples': 20491008, 'steps': 106723, 'loss/train': 1.5939868688583374} 08/31/2021 08:37:05 - INFO - __main__ - Step 106725: {'lr': 9.82703590173788e-05, 'samples': 20491200, 'steps': 106724, 'loss/train': 1.4070196151733398} 08/31/2021 08:37:05 - INFO - __main__ - Step 106726: {'lr': 9.826614144206112e-05, 'samples': 20491392, 'steps': 106725, 'loss/train': 1.2197827100753784} 08/31/2021 08:37:07 - INFO - __main__ - Step 106727: {'lr': 9.826192393511235e-05, 'samples': 20491584, 'steps': 106726, 'loss/train': 1.1404953002929688} 08/31/2021 08:37:07 - INFO - __main__ - Step 106728: {'lr': 9.825770649653446e-05, 'samples': 20491776, 'steps': 106727, 'loss/train': 0.7025036215782166} 08/31/2021 08:37:08 - INFO - __main__ - Step 106729: {'lr': 9.825348912632928e-05, 'samples': 20491968, 'steps': 106728, 'loss/train': 0.9751273393630981} 08/31/2021 08:37:08 - INFO - __main__ - Step 106730: {'lr': 9.824927182449884e-05, 'samples': 20492160, 'steps': 106729, 'loss/train': 0.2725696563720703} 08/31/2021 08:37:09 - INFO - __main__ - Step 106731: {'lr': 9.824505459104485e-05, 'samples': 20492352, 'steps': 106730, 'loss/train': 0.9590908885002136} 08/31/2021 08:37:10 - INFO - __main__ - Step 106732: {'lr': 9.824083742596929e-05, 'samples': 20492544, 'steps': 106731, 'loss/train': 0.5652922987937927} 08/31/2021 08:37:11 - INFO - __main__ - Step 106733: {'lr': 9.823662032927404e-05, 'samples': 20492736, 'steps': 106732, 'loss/train': 0.9447895288467407} 08/31/2021 08:37:11 - INFO - __main__ - Step 106734: {'lr': 9.823240330096106e-05, 'samples': 20492928, 'steps': 106733, 'loss/train': 0.3747391402721405} 08/31/2021 08:37:11 - INFO - __main__ - Step 106735: {'lr': 9.822818634103223e-05, 'samples': 20493120, 'steps': 106734, 'loss/train': 0.0636717900633812} 08/31/2021 08:37:12 - INFO - __main__ - Step 106736: {'lr': 9.822396944948942e-05, 'samples': 20493312, 'steps': 106735, 'loss/train': 0.029142703860998154} 08/31/2021 08:37:13 - INFO - __main__ - Step 106737: {'lr': 9.821975262633453e-05, 'samples': 20493504, 'steps': 106736, 'loss/train': 0.19618593156337738} 08/31/2021 08:37:14 - INFO - __main__ - Step 106738: {'lr': 9.821553587156948e-05, 'samples': 20493696, 'steps': 106737, 'loss/train': 1.3368723392486572} 08/31/2021 08:37:14 - INFO - __main__ - Step 106739: {'lr': 9.821131918519619e-05, 'samples': 20493888, 'steps': 106738, 'loss/train': 0.8482885956764221} 08/31/2021 08:37:14 - INFO - __main__ - Step 106740: {'lr': 9.820710256721651e-05, 'samples': 20494080, 'steps': 106739, 'loss/train': 1.1563974618911743} 08/31/2021 08:37:15 - INFO - __main__ - Step 106741: {'lr': 9.820288601763238e-05, 'samples': 20494272, 'steps': 106740, 'loss/train': 1.1723097562789917} 08/31/2021 08:37:15 - INFO - __main__ - Step 106742: {'lr': 9.81986695364457e-05, 'samples': 20494464, 'steps': 106741, 'loss/train': 0.425678551197052} 08/31/2021 08:37:17 - INFO - __main__ - Step 106743: {'lr': 9.819445312365843e-05, 'samples': 20494656, 'steps': 106742, 'loss/train': 1.5337659120559692} 08/31/2021 08:37:18 - INFO - __main__ - Step 106744: {'lr': 9.819023677927233e-05, 'samples': 20494848, 'steps': 106743, 'loss/train': 0.8953853249549866} 08/31/2021 08:37:18 - INFO - __main__ - Step 106745: {'lr': 9.818602050328934e-05, 'samples': 20495040, 'steps': 106744, 'loss/train': 0.9477965235710144} 08/31/2021 08:37:18 - INFO - __main__ - Step 106746: {'lr': 9.818180429571141e-05, 'samples': 20495232, 'steps': 106745, 'loss/train': 1.243416428565979} 08/31/2021 08:37:19 - INFO - __main__ - Step 106747: {'lr': 9.81775881565404e-05, 'samples': 20495424, 'steps': 106746, 'loss/train': 1.1135811805725098} 08/31/2021 08:37:20 - INFO - __main__ - Step 106748: {'lr': 9.817337208577823e-05, 'samples': 20495616, 'steps': 106747, 'loss/train': 0.8012048006057739} 08/31/2021 08:37:21 - INFO - __main__ - Step 106749: {'lr': 9.81691560834268e-05, 'samples': 20495808, 'steps': 106748, 'loss/train': 0.8462074995040894} 08/31/2021 08:37:21 - INFO - __main__ - Step 106750: {'lr': 9.816494014948798e-05, 'samples': 20496000, 'steps': 106749, 'loss/train': 1.2549818754196167} 08/31/2021 08:37:21 - INFO - __main__ - Step 106751: {'lr': 9.816072428396375e-05, 'samples': 20496192, 'steps': 106750, 'loss/train': 0.7663068175315857} 08/31/2021 08:37:22 - INFO - __main__ - Step 106752: {'lr': 9.815650848685589e-05, 'samples': 20496384, 'steps': 106751, 'loss/train': 0.6331231594085693} 08/31/2021 08:37:24 - INFO - __main__ - Step 106753: {'lr': 9.815229275816643e-05, 'samples': 20496576, 'steps': 106752, 'loss/train': 0.41467535495758057} 08/31/2021 08:37:24 - INFO - __main__ - Step 106754: {'lr': 9.814807709789714e-05, 'samples': 20496768, 'steps': 106753, 'loss/train': 0.5442361235618591} 08/31/2021 08:37:24 - INFO - __main__ - Step 106755: {'lr': 9.814386150605001e-05, 'samples': 20496960, 'steps': 106754, 'loss/train': 0.24123458564281464} 08/31/2021 08:37:25 - INFO - __main__ - Step 106756: {'lr': 9.813964598262701e-05, 'samples': 20497152, 'steps': 106755, 'loss/train': 1.2373507022857666} 08/31/2021 08:37:25 - INFO - __main__ - Step 106757: {'lr': 9.813543052762986e-05, 'samples': 20497344, 'steps': 106756, 'loss/train': 1.3543254137039185} 08/31/2021 08:37:26 - INFO - __main__ - Step 106758: {'lr': 9.813121514106052e-05, 'samples': 20497536, 'steps': 106757, 'loss/train': 0.04124252870678902} 08/31/2021 08:37:27 - INFO - __main__ - Step 106759: {'lr': 9.812699982292092e-05, 'samples': 20497728, 'steps': 106758, 'loss/train': 1.3082698583602905} 08/31/2021 08:37:27 - INFO - __main__ - Step 106760: {'lr': 9.812278457321294e-05, 'samples': 20497920, 'steps': 106759, 'loss/train': 0.4723355770111084} 08/31/2021 08:37:28 - INFO - __main__ - Step 106761: {'lr': 9.81185693919385e-05, 'samples': 20498112, 'steps': 106760, 'loss/train': 0.9959558248519897} 08/31/2021 08:37:28 - INFO - __main__ - Step 106762: {'lr': 9.811435427909951e-05, 'samples': 20498304, 'steps': 106761, 'loss/train': 1.577839732170105} 08/31/2021 08:37:29 - INFO - __main__ - Step 106763: {'lr': 9.811013923469781e-05, 'samples': 20498496, 'steps': 106762, 'loss/train': 1.4757453203201294} 08/31/2021 08:37:30 - INFO - __main__ - Step 106764: {'lr': 9.810592425873535e-05, 'samples': 20498688, 'steps': 106763, 'loss/train': 0.6642885208129883} 08/31/2021 08:37:30 - INFO - __main__ - Step 106765: {'lr': 9.810170935121404e-05, 'samples': 20498880, 'steps': 106764, 'loss/train': 1.3592166900634766} 08/31/2021 08:37:31 - INFO - __main__ - Step 106766: {'lr': 9.809749451213573e-05, 'samples': 20499072, 'steps': 106765, 'loss/train': 1.5508289337158203} 08/31/2021 08:37:31 - INFO - __main__ - Step 106767: {'lr': 9.809327974150234e-05, 'samples': 20499264, 'steps': 106766, 'loss/train': 4.663733005523682} 08/31/2021 08:37:31 - INFO - __main__ - Step 106768: {'lr': 9.808906503931577e-05, 'samples': 20499456, 'steps': 106767, 'loss/train': 1.4414876699447632} 08/31/2021 08:37:33 - INFO - __main__ - Step 106769: {'lr': 9.808485040557797e-05, 'samples': 20499648, 'steps': 106768, 'loss/train': 1.5654354095458984} 08/31/2021 08:37:33 - INFO - __main__ - Step 106770: {'lr': 9.808063584029084e-05, 'samples': 20499840, 'steps': 106769, 'loss/train': 1.619712233543396} 08/31/2021 08:37:34 - INFO - __main__ - Step 106771: {'lr': 9.807642134345615e-05, 'samples': 20500032, 'steps': 106770, 'loss/train': 0.1506403237581253} 08/31/2021 08:37:34 - INFO - __main__ - Step 106772: {'lr': 9.807220691507587e-05, 'samples': 20500224, 'steps': 106771, 'loss/train': 0.6171824336051941} 08/31/2021 08:37:34 - INFO - __main__ - Step 106773: {'lr': 9.806799255515194e-05, 'samples': 20500416, 'steps': 106772, 'loss/train': 1.0684239864349365} 08/31/2021 08:37:36 - INFO - __main__ - Step 106774: {'lr': 9.80637782636862e-05, 'samples': 20500608, 'steps': 106773, 'loss/train': 0.578822135925293} 08/31/2021 08:37:36 - INFO - __main__ - Step 106775: {'lr': 9.80595640406806e-05, 'samples': 20500800, 'steps': 106774, 'loss/train': 1.3137813806533813} 08/31/2021 08:37:37 - INFO - __main__ - Step 106776: {'lr': 9.805534988613699e-05, 'samples': 20500992, 'steps': 106775, 'loss/train': 0.5000673532485962} 08/31/2021 08:37:37 - INFO - __main__ - Step 106777: {'lr': 9.805113580005732e-05, 'samples': 20501184, 'steps': 106776, 'loss/train': 0.8391203880310059} 08/31/2021 08:37:37 - INFO - __main__ - Step 106778: {'lr': 9.804692178244345e-05, 'samples': 20501376, 'steps': 106777, 'loss/train': 0.34590983390808105} 08/31/2021 08:37:39 - INFO - __main__ - Step 106779: {'lr': 9.804270783329727e-05, 'samples': 20501568, 'steps': 106778, 'loss/train': 0.8540314435958862} 08/31/2021 08:37:39 - INFO - __main__ - Step 106780: {'lr': 9.803849395262073e-05, 'samples': 20501760, 'steps': 106779, 'loss/train': 1.429695963859558} 08/31/2021 08:37:40 - INFO - __main__ - Step 106781: {'lr': 9.803428014041571e-05, 'samples': 20501952, 'steps': 106780, 'loss/train': 0.747103750705719} 08/31/2021 08:37:40 - INFO - __main__ - Step 106782: {'lr': 9.803006639668407e-05, 'samples': 20502144, 'steps': 106781, 'loss/train': 0.9566219449043274} 08/31/2021 08:37:40 - INFO - __main__ - Step 106783: {'lr': 9.802585272142784e-05, 'samples': 20502336, 'steps': 106782, 'loss/train': 0.993829607963562} 08/31/2021 08:37:41 - INFO - __main__ - Step 106784: {'lr': 9.802163911464873e-05, 'samples': 20502528, 'steps': 106783, 'loss/train': 1.3444478511810303} 08/31/2021 08:37:42 - INFO - __main__ - Step 106785: {'lr': 9.801742557634872e-05, 'samples': 20502720, 'steps': 106784, 'loss/train': 1.1075862646102905} 08/31/2021 08:37:43 - INFO - __main__ - Step 106786: {'lr': 9.801321210652973e-05, 'samples': 20502912, 'steps': 106785, 'loss/train': 2.0683786869049072} 08/31/2021 08:37:43 - INFO - __main__ - Step 106787: {'lr': 9.800899870519362e-05, 'samples': 20503104, 'steps': 106786, 'loss/train': 0.9470058679580688} 08/31/2021 08:37:43 - INFO - __main__ - Step 106788: {'lr': 9.800478537234231e-05, 'samples': 20503296, 'steps': 106787, 'loss/train': 0.7390244007110596} 08/31/2021 08:37:44 - INFO - __main__ - Step 106789: {'lr': 9.800057210797769e-05, 'samples': 20503488, 'steps': 106788, 'loss/train': 1.4527969360351562} 08/31/2021 08:37:45 - INFO - __main__ - Step 106790: {'lr': 9.799635891210167e-05, 'samples': 20503680, 'steps': 106789, 'loss/train': 0.997793436050415} 08/31/2021 08:37:46 - INFO - __main__ - Step 106791: {'lr': 9.799214578471616e-05, 'samples': 20503872, 'steps': 106790, 'loss/train': 1.297635793685913} 08/31/2021 08:37:46 - INFO - __main__ - Step 106792: {'lr': 9.798793272582305e-05, 'samples': 20504064, 'steps': 106791, 'loss/train': 1.2209190130233765} 08/31/2021 08:37:46 - INFO - __main__ - Step 106793: {'lr': 9.798371973542419e-05, 'samples': 20504256, 'steps': 106792, 'loss/train': 0.6508068442344666} 08/31/2021 08:37:47 - INFO - __main__ - Step 106794: {'lr': 9.797950681352155e-05, 'samples': 20504448, 'steps': 106793, 'loss/train': 1.1184874773025513} 08/31/2021 08:37:48 - INFO - __main__ - Step 106795: {'lr': 9.7975293960117e-05, 'samples': 20504640, 'steps': 106794, 'loss/train': 1.4378670454025269} 08/31/2021 08:37:48 - INFO - __main__ - Step 106796: {'lr': 9.797108117521244e-05, 'samples': 20504832, 'steps': 106795, 'loss/train': 0.6727332472801208} 08/31/2021 08:37:49 - INFO - __main__ - Step 106797: {'lr': 9.796686845880983e-05, 'samples': 20505024, 'steps': 106796, 'loss/train': 1.0096936225891113} 08/31/2021 08:37:49 - INFO - __main__ - Step 106798: {'lr': 9.796265581091096e-05, 'samples': 20505216, 'steps': 106797, 'loss/train': 0.8008363246917725} 08/31/2021 08:37:50 - INFO - __main__ - Step 106799: {'lr': 9.795844323151773e-05, 'samples': 20505408, 'steps': 106798, 'loss/train': 1.1569710969924927} 08/31/2021 08:37:52 - INFO - __main__ - Step 106800: {'lr': 9.795423072063208e-05, 'samples': 20505600, 'steps': 106799, 'loss/train': 1.0020129680633545} 08/31/2021 08:37:52 - INFO - __main__ - Step 106801: {'lr': 9.795001827825595e-05, 'samples': 20505792, 'steps': 106800, 'loss/train': 1.282206654548645} 08/31/2021 08:37:52 - INFO - __main__ - Step 106802: {'lr': 9.794580590439114e-05, 'samples': 20505984, 'steps': 106801, 'loss/train': 1.5437201261520386} 08/31/2021 08:37:53 - INFO - __main__ - Step 106803: {'lr': 9.794159359903965e-05, 'samples': 20506176, 'steps': 106802, 'loss/train': 1.317499041557312} 08/31/2021 08:37:53 - INFO - __main__ - Step 106804: {'lr': 9.793738136220329e-05, 'samples': 20506368, 'steps': 106803, 'loss/train': 0.44083747267723083} 08/31/2021 08:37:55 - INFO - __main__ - Step 106805: {'lr': 9.793316919388404e-05, 'samples': 20506560, 'steps': 106804, 'loss/train': 0.08436901867389679} 08/31/2021 08:37:55 - INFO - __main__ - Step 106806: {'lr': 9.792895709408373e-05, 'samples': 20506752, 'steps': 106805, 'loss/train': 0.6540743112564087} 08/31/2021 08:37:55 - INFO - __main__ - Step 106807: {'lr': 9.79247450628043e-05, 'samples': 20506944, 'steps': 106806, 'loss/train': 1.2816299200057983} 08/31/2021 08:37:56 - INFO - __main__ - Step 106808: {'lr': 9.792053310004761e-05, 'samples': 20507136, 'steps': 106807, 'loss/train': 1.110756754875183} 08/31/2021 08:37:56 - INFO - __main__ - Step 106809: {'lr': 9.791632120581558e-05, 'samples': 20507328, 'steps': 106808, 'loss/train': 1.0828652381896973} 08/31/2021 08:37:58 - INFO - __main__ - Step 106810: {'lr': 9.791210938011021e-05, 'samples': 20507520, 'steps': 106809, 'loss/train': 0.9383329153060913} 08/31/2021 08:37:58 - INFO - __main__ - Step 106811: {'lr': 9.790789762293323e-05, 'samples': 20507712, 'steps': 106810, 'loss/train': 1.1481456756591797} 08/31/2021 08:37:58 - INFO - __main__ - Step 106812: {'lr': 9.790368593428659e-05, 'samples': 20507904, 'steps': 106811, 'loss/train': 1.2796986103057861} 08/31/2021 08:37:59 - INFO - __main__ - Step 106813: {'lr': 9.78994743141722e-05, 'samples': 20508096, 'steps': 106812, 'loss/train': 1.383543610572815} 08/31/2021 08:37:59 - INFO - __main__ - Step 106814: {'lr': 9.789526276259194e-05, 'samples': 20508288, 'steps': 106813, 'loss/train': 1.024290919303894} 08/31/2021 08:38:01 - INFO - __main__ - Step 106815: {'lr': 9.789105127954775e-05, 'samples': 20508480, 'steps': 106814, 'loss/train': 1.0593347549438477} 08/31/2021 08:38:01 - INFO - __main__ - Step 106816: {'lr': 9.788683986504152e-05, 'samples': 20508672, 'steps': 106815, 'loss/train': 0.8948236703872681} 08/31/2021 08:38:02 - INFO - __main__ - Step 106817: {'lr': 9.788262851907512e-05, 'samples': 20508864, 'steps': 106816, 'loss/train': 0.6045704483985901} 08/31/2021 08:38:02 - INFO - __main__ - Step 106818: {'lr': 9.787841724165045e-05, 'samples': 20509056, 'steps': 106817, 'loss/train': 1.070888638496399} 08/31/2021 08:38:02 - INFO - __main__ - Step 106819: {'lr': 9.787420603276942e-05, 'samples': 20509248, 'steps': 106818, 'loss/train': 0.7051044702529907} 08/31/2021 08:38:03 - INFO - __main__ - Step 106820: {'lr': 9.786999489243392e-05, 'samples': 20509440, 'steps': 106819, 'loss/train': 1.8023854494094849} 08/31/2021 08:38:04 - INFO - __main__ - Step 106821: {'lr': 9.786578382064587e-05, 'samples': 20509632, 'steps': 106820, 'loss/train': 1.2773271799087524} 08/31/2021 08:38:05 - INFO - __main__ - Step 106822: {'lr': 9.786157281740712e-05, 'samples': 20509824, 'steps': 106821, 'loss/train': 1.348010778427124} 08/31/2021 08:38:05 - INFO - __main__ - Step 106823: {'lr': 9.785736188271963e-05, 'samples': 20510016, 'steps': 106822, 'loss/train': 0.9178051352500916} 08/31/2021 08:38:06 - INFO - __main__ - Step 106824: {'lr': 9.785315101658535e-05, 'samples': 20510208, 'steps': 106823, 'loss/train': 0.6911401748657227} 08/31/2021 08:38:06 - INFO - __main__ - Step 106825: {'lr': 9.784894021900598e-05, 'samples': 20510400, 'steps': 106824, 'loss/train': 0.07092837244272232} 08/31/2021 08:38:07 - INFO - __main__ - Step 106826: {'lr': 9.784472948998355e-05, 'samples': 20510592, 'steps': 106825, 'loss/train': 1.2943867444992065} 08/31/2021 08:38:08 - INFO - __main__ - Step 106827: {'lr': 9.784051882951994e-05, 'samples': 20510784, 'steps': 106826, 'loss/train': 1.3288010358810425} 08/31/2021 08:38:08 - INFO - __main__ - Step 106828: {'lr': 9.783630823761702e-05, 'samples': 20510976, 'steps': 106827, 'loss/train': 1.0096129179000854} 08/31/2021 08:38:09 - INFO - __main__ - Step 106829: {'lr': 9.783209771427673e-05, 'samples': 20511168, 'steps': 106828, 'loss/train': 1.4358853101730347} 08/31/2021 08:38:09 - INFO - __main__ - Step 106830: {'lr': 9.782788725950095e-05, 'samples': 20511360, 'steps': 106829, 'loss/train': 3.967703342437744} 08/31/2021 08:38:10 - INFO - __main__ - Step 106831: {'lr': 9.782367687329158e-05, 'samples': 20511552, 'steps': 106830, 'loss/train': 0.47122856974601746} 08/31/2021 08:38:11 - INFO - __main__ - Step 106832: {'lr': 9.78194665556505e-05, 'samples': 20511744, 'steps': 106831, 'loss/train': 1.293046236038208} 08/31/2021 08:38:11 - INFO - __main__ - Step 106833: {'lr': 9.781525630657964e-05, 'samples': 20511936, 'steps': 106832, 'loss/train': 1.373659372329712} 08/31/2021 08:38:11 - INFO - __main__ - Step 106834: {'lr': 9.781104612608085e-05, 'samples': 20512128, 'steps': 106833, 'loss/train': 1.1142903566360474} 08/31/2021 08:38:12 - INFO - __main__ - Step 106835: {'lr': 9.780683601415607e-05, 'samples': 20512320, 'steps': 106834, 'loss/train': 0.9802790880203247} 08/31/2021 08:38:13 - INFO - __main__ - Step 106836: {'lr': 9.780262597080717e-05, 'samples': 20512512, 'steps': 106835, 'loss/train': 0.4934469759464264} 08/31/2021 08:38:14 - INFO - __main__ - Step 106837: {'lr': 9.779841599603618e-05, 'samples': 20512704, 'steps': 106836, 'loss/train': 1.581258773803711} 08/31/2021 08:38:14 - INFO - __main__ - Step 106838: {'lr': 9.779420608984474e-05, 'samples': 20512896, 'steps': 106837, 'loss/train': 0.7141708135604858} 08/31/2021 08:38:15 - INFO - __main__ - Step 106839: {'lr': 9.778999625223489e-05, 'samples': 20513088, 'steps': 106838, 'loss/train': 1.0727012157440186} 08/31/2021 08:38:15 - INFO - __main__ - Step 106840: {'lr': 9.778578648320854e-05, 'samples': 20513280, 'steps': 106839, 'loss/train': 1.2353742122650146} 08/31/2021 08:38:16 - INFO - __main__ - Step 106841: {'lr': 9.778157678276756e-05, 'samples': 20513472, 'steps': 106840, 'loss/train': 1.7602035999298096} 08/31/2021 08:38:17 - INFO - __main__ - Step 106842: {'lr': 9.777736715091385e-05, 'samples': 20513664, 'steps': 106841, 'loss/train': 1.1515698432922363} 08/31/2021 08:38:17 - INFO - __main__ - Step 106843: {'lr': 9.777315758764932e-05, 'samples': 20513856, 'steps': 106842, 'loss/train': 0.5607684254646301} 08/31/2021 08:38:18 - INFO - __main__ - Step 106844: {'lr': 9.776894809297585e-05, 'samples': 20514048, 'steps': 106843, 'loss/train': 1.2256932258605957} 08/31/2021 08:38:18 - INFO - __main__ - Step 106845: {'lr': 9.776473866689533e-05, 'samples': 20514240, 'steps': 106844, 'loss/train': 1.4531985521316528} 08/31/2021 08:38:19 - INFO - __main__ - Step 106846: {'lr': 9.776052930940968e-05, 'samples': 20514432, 'steps': 106845, 'loss/train': 1.340491771697998} 08/31/2021 08:38:20 - INFO - __main__ - Step 106847: {'lr': 9.775632002052079e-05, 'samples': 20514624, 'steps': 106846, 'loss/train': 1.0402768850326538} 08/31/2021 08:38:20 - INFO - __main__ - Step 106848: {'lr': 9.775211080023056e-05, 'samples': 20514816, 'steps': 106847, 'loss/train': 0.9319148063659668} 08/31/2021 08:38:21 - INFO - __main__ - Step 106849: {'lr': 9.774790164854086e-05, 'samples': 20515008, 'steps': 106848, 'loss/train': 1.0768202543258667} 08/31/2021 08:38:21 - INFO - __main__ - Step 106850: {'lr': 9.77436925654536e-05, 'samples': 20515200, 'steps': 106849, 'loss/train': 1.3098541498184204} 08/31/2021 08:38:23 - INFO - __main__ - Step 106851: {'lr': 9.773948355097078e-05, 'samples': 20515392, 'steps': 106850, 'loss/train': 0.5962309837341309} 08/31/2021 08:38:24 - INFO - __main__ - Step 106852: {'lr': 9.773527460509413e-05, 'samples': 20515584, 'steps': 106851, 'loss/train': 0.7539719343185425} 08/31/2021 08:38:24 - INFO - __main__ - Step 106853: {'lr': 9.773106572782558e-05, 'samples': 20515776, 'steps': 106852, 'loss/train': 0.24367855489253998} 08/31/2021 08:38:24 - INFO - __main__ - Step 106854: {'lr': 9.77268569191671e-05, 'samples': 20515968, 'steps': 106853, 'loss/train': 0.06208156794309616} 08/31/2021 08:38:25 - INFO - __main__ - Step 106855: {'lr': 9.772264817912052e-05, 'samples': 20516160, 'steps': 106854, 'loss/train': 0.9132378101348877} 08/31/2021 08:38:26 - INFO - __main__ - Step 106856: {'lr': 9.77184395076878e-05, 'samples': 20516352, 'steps': 106855, 'loss/train': 1.7780581712722778} 08/31/2021 08:38:27 - INFO - __main__ - Step 106857: {'lr': 9.771423090487078e-05, 'samples': 20516544, 'steps': 106856, 'loss/train': 0.6855329275131226} 08/31/2021 08:38:27 - INFO - __main__ - Step 106858: {'lr': 9.771002237067137e-05, 'samples': 20516736, 'steps': 106857, 'loss/train': 1.0646851062774658} 08/31/2021 08:38:28 - INFO - __main__ - Step 106859: {'lr': 9.770581390509148e-05, 'samples': 20516928, 'steps': 106858, 'loss/train': 0.9350279569625854} 08/31/2021 08:38:28 - INFO - __main__ - Step 106860: {'lr': 9.770160550813298e-05, 'samples': 20517120, 'steps': 106859, 'loss/train': 0.9657089710235596} 08/31/2021 08:38:28 - INFO - __main__ - Step 106861: {'lr': 9.769739717979781e-05, 'samples': 20517312, 'steps': 106860, 'loss/train': 1.0729432106018066} 08/31/2021 08:38:30 - INFO - __main__ - Step 106862: {'lr': 9.769318892008785e-05, 'samples': 20517504, 'steps': 106861, 'loss/train': 1.3288902044296265} 08/31/2021 08:38:30 - INFO - __main__ - Step 106863: {'lr': 9.768898072900498e-05, 'samples': 20517696, 'steps': 106862, 'loss/train': 1.1952372789382935} 08/31/2021 08:38:30 - INFO - __main__ - Step 106864: {'lr': 9.768477260655117e-05, 'samples': 20517888, 'steps': 106863, 'loss/train': 1.4388465881347656} 08/31/2021 08:38:31 - INFO - __main__ - Step 106865: {'lr': 9.76805645527282e-05, 'samples': 20518080, 'steps': 106864, 'loss/train': 0.3445621430873871} 08/31/2021 08:38:31 - INFO - __main__ - Step 106866: {'lr': 9.7676356567538e-05, 'samples': 20518272, 'steps': 106865, 'loss/train': 0.46262818574905396} 08/31/2021 08:38:33 - INFO - __main__ - Step 106867: {'lr': 9.767214865098248e-05, 'samples': 20518464, 'steps': 106866, 'loss/train': 1.199238657951355} 08/31/2021 08:38:33 - INFO - __main__ - Step 106868: {'lr': 9.766794080306354e-05, 'samples': 20518656, 'steps': 106867, 'loss/train': 0.8428351879119873} 08/31/2021 08:38:34 - INFO - __main__ - Step 106869: {'lr': 9.766373302378309e-05, 'samples': 20518848, 'steps': 106868, 'loss/train': 0.5953788161277771} 08/31/2021 08:38:34 - INFO - __main__ - Step 106870: {'lr': 9.765952531314301e-05, 'samples': 20519040, 'steps': 106869, 'loss/train': 1.1773027181625366} 08/31/2021 08:38:34 - INFO - __main__ - Step 106871: {'lr': 9.76553176711452e-05, 'samples': 20519232, 'steps': 106870, 'loss/train': 1.2909168004989624} 08/31/2021 08:38:36 - INFO - __main__ - Step 106872: {'lr': 9.765111009779151e-05, 'samples': 20519424, 'steps': 106871, 'loss/train': 1.110777735710144} 08/31/2021 08:38:37 - INFO - __main__ - Step 106873: {'lr': 9.764690259308393e-05, 'samples': 20519616, 'steps': 106872, 'loss/train': 0.07058961689472198} 08/31/2021 08:38:37 - INFO - __main__ - Step 106874: {'lr': 9.764269515702425e-05, 'samples': 20519808, 'steps': 106873, 'loss/train': 1.630035400390625} 08/31/2021 08:38:37 - INFO - __main__ - Step 106875: {'lr': 9.763848778961449e-05, 'samples': 20520000, 'steps': 106874, 'loss/train': 0.11452638357877731} 08/31/2021 08:38:38 - INFO - __main__ - Step 106876: {'lr': 9.763428049085643e-05, 'samples': 20520192, 'steps': 106875, 'loss/train': 0.4363997280597687} 08/31/2021 08:38:39 - INFO - __main__ - Step 106877: {'lr': 9.76300732607521e-05, 'samples': 20520384, 'steps': 106876, 'loss/train': 1.1548073291778564} 08/31/2021 08:38:40 - INFO - __main__ - Step 106878: {'lr': 9.762586609930324e-05, 'samples': 20520576, 'steps': 106877, 'loss/train': 1.3623266220092773} 08/31/2021 08:38:40 - INFO - __main__ - Step 106879: {'lr': 9.762165900651179e-05, 'samples': 20520768, 'steps': 106878, 'loss/train': 1.2528738975524902} 08/31/2021 08:38:40 - INFO - __main__ - Step 106880: {'lr': 9.76174519823797e-05, 'samples': 20520960, 'steps': 106879, 'loss/train': 1.5902795791625977} 08/31/2021 08:38:41 - INFO - __main__ - Step 106881: {'lr': 9.76132450269088e-05, 'samples': 20521152, 'steps': 106880, 'loss/train': 1.0023045539855957} 08/31/2021 08:38:41 - INFO - __main__ - Step 106882: {'lr': 9.760903814010106e-05, 'samples': 20521344, 'steps': 106881, 'loss/train': 0.8530206084251404} 08/31/2021 08:38:42 - INFO - __main__ - Step 106883: {'lr': 9.76048313219583e-05, 'samples': 20521536, 'steps': 106882, 'loss/train': 0.6372188329696655} 08/31/2021 08:38:43 - INFO - __main__ - Step 106884: {'lr': 9.760062457248248e-05, 'samples': 20521728, 'steps': 106883, 'loss/train': 1.6849056482315063} 08/31/2021 08:38:43 - INFO - __main__ - Step 106885: {'lr': 9.759641789167545e-05, 'samples': 20521920, 'steps': 106884, 'loss/train': 0.9388592839241028} 08/31/2021 08:38:44 - INFO - __main__ - Step 106886: {'lr': 9.759221127953912e-05, 'samples': 20522112, 'steps': 106885, 'loss/train': 0.7094906568527222} 08/31/2021 08:38:44 - INFO - __main__ - Step 106887: {'lr': 9.758800473607537e-05, 'samples': 20522304, 'steps': 106886, 'loss/train': 1.006321907043457} 08/31/2021 08:38:45 - INFO - __main__ - Step 106888: {'lr': 9.758379826128616e-05, 'samples': 20522496, 'steps': 106887, 'loss/train': 0.7222561836242676} 08/31/2021 08:38:46 - INFO - __main__ - Step 106889: {'lr': 9.757959185517332e-05, 'samples': 20522688, 'steps': 106888, 'loss/train': 1.4675679206848145} 08/31/2021 08:38:46 - INFO - __main__ - Step 106890: {'lr': 9.757538551773876e-05, 'samples': 20522880, 'steps': 106889, 'loss/train': 1.8647010326385498} 08/31/2021 08:38:47 - INFO - __main__ - Step 106891: {'lr': 9.757117924898445e-05, 'samples': 20523072, 'steps': 106890, 'loss/train': 1.5876846313476562} 08/31/2021 08:38:47 - INFO - __main__ - Step 106892: {'lr': 9.756697304891215e-05, 'samples': 20523264, 'steps': 106891, 'loss/train': 1.3281447887420654} 08/31/2021 08:38:49 - INFO - __main__ - Step 106893: {'lr': 9.75627669175238e-05, 'samples': 20523456, 'steps': 106892, 'loss/train': 1.7101854085922241} 08/31/2021 08:38:49 - INFO - __main__ - Step 106894: {'lr': 9.755856085482134e-05, 'samples': 20523648, 'steps': 106893, 'loss/train': 0.03589869663119316} 08/31/2021 08:38:49 - INFO - __main__ - Step 106895: {'lr': 9.755435486080663e-05, 'samples': 20523840, 'steps': 106894, 'loss/train': 1.7980934381484985} 08/31/2021 08:38:50 - INFO - __main__ - Step 106896: {'lr': 9.755014893548156e-05, 'samples': 20524032, 'steps': 106895, 'loss/train': 1.0904245376586914} 08/31/2021 08:38:50 - INFO - __main__ - Step 106897: {'lr': 9.754594307884806e-05, 'samples': 20524224, 'steps': 106896, 'loss/train': 1.2726253271102905} 08/31/2021 08:38:52 - INFO - __main__ - Step 106898: {'lr': 9.754173729090798e-05, 'samples': 20524416, 'steps': 106897, 'loss/train': 2.0132899284362793} 08/31/2021 08:38:52 - INFO - __main__ - Step 106899: {'lr': 9.753753157166329e-05, 'samples': 20524608, 'steps': 106898, 'loss/train': 1.1229814291000366} 08/31/2021 08:38:53 - INFO - __main__ - Step 106900: {'lr': 9.753332592111577e-05, 'samples': 20524800, 'steps': 106899, 'loss/train': 0.4551236927509308} 08/31/2021 08:38:53 - INFO - __main__ - Step 106901: {'lr': 9.752912033926742e-05, 'samples': 20524992, 'steps': 106900, 'loss/train': 3.2362756729125977} 08/31/2021 08:38:53 - INFO - __main__ - Step 106902: {'lr': 9.752491482612011e-05, 'samples': 20525184, 'steps': 106901, 'loss/train': 1.1474862098693848} 08/31/2021 08:38:55 - INFO - __main__ - Step 106903: {'lr': 9.75207093816757e-05, 'samples': 20525376, 'steps': 106902, 'loss/train': 0.6954326033592224} 08/31/2021 08:38:55 - INFO - __main__ - Step 106904: {'lr': 9.751650400593621e-05, 'samples': 20525568, 'steps': 106903, 'loss/train': 0.5831822156906128} 08/31/2021 08:38:56 - INFO - __main__ - Step 106905: {'lr': 9.75122986989033e-05, 'samples': 20525760, 'steps': 106904, 'loss/train': 0.44446149468421936} 08/31/2021 08:38:56 - INFO - __main__ - Step 106906: {'lr': 9.750809346057904e-05, 'samples': 20525952, 'steps': 106905, 'loss/train': 1.9993748664855957} 08/31/2021 08:38:56 - INFO - __main__ - Step 106907: {'lr': 9.750388829096524e-05, 'samples': 20526144, 'steps': 106906, 'loss/train': 0.266975462436676} 08/31/2021 08:38:57 - INFO - __main__ - Step 106908: {'lr': 9.749968319006386e-05, 'samples': 20526336, 'steps': 106907, 'loss/train': 0.8465656042098999} 08/31/2021 08:38:59 - INFO - __main__ - Step 106909: {'lr': 9.749547815787677e-05, 'samples': 20526528, 'steps': 106908, 'loss/train': 1.069716215133667} 08/31/2021 08:38:59 - INFO - __main__ - Step 106910: {'lr': 9.749127319440588e-05, 'samples': 20526720, 'steps': 106909, 'loss/train': 1.0760483741760254} 08/31/2021 08:39:00 - INFO - __main__ - Step 106911: {'lr': 9.748706829965304e-05, 'samples': 20526912, 'steps': 106910, 'loss/train': 1.083074688911438} 08/31/2021 08:39:00 - INFO - __main__ - Step 106912: {'lr': 9.748286347362017e-05, 'samples': 20527104, 'steps': 106911, 'loss/train': 0.9359529614448547} 08/31/2021 08:39:00 - INFO - __main__ - Step 106913: {'lr': 9.747865871630918e-05, 'samples': 20527296, 'steps': 106912, 'loss/train': 1.6622862815856934} 08/31/2021 08:39:02 - INFO - __main__ - Step 106914: {'lr': 9.747445402772195e-05, 'samples': 20527488, 'steps': 106913, 'loss/train': 0.6369410157203674} 08/31/2021 08:39:02 - INFO - __main__ - Step 106915: {'lr': 9.74702494078604e-05, 'samples': 20527680, 'steps': 106914, 'loss/train': 1.371463656425476} 08/31/2021 08:39:03 - INFO - __main__ - Step 106916: {'lr': 9.746604485672638e-05, 'samples': 20527872, 'steps': 106915, 'loss/train': 1.1678634881973267} 08/31/2021 08:39:03 - INFO - __main__ - Step 106917: {'lr': 9.746184037432182e-05, 'samples': 20528064, 'steps': 106916, 'loss/train': 1.076380968093872} 08/31/2021 08:39:03 - INFO - __main__ - Step 106918: {'lr': 9.745763596064866e-05, 'samples': 20528256, 'steps': 106917, 'loss/train': 1.1891746520996094} 08/31/2021 08:39:05 - INFO - __main__ - Step 106919: {'lr': 9.745343161570869e-05, 'samples': 20528448, 'steps': 106918, 'loss/train': 1.0023642778396606} 08/31/2021 08:39:05 - INFO - __main__ - Step 106920: {'lr': 9.744922733950381e-05, 'samples': 20528640, 'steps': 106919, 'loss/train': 0.7142760753631592} 08/31/2021 08:39:06 - INFO - __main__ - Step 106921: {'lr': 9.744502313203596e-05, 'samples': 20528832, 'steps': 106920, 'loss/train': 1.3954877853393555} 08/31/2021 08:39:06 - INFO - __main__ - Step 106922: {'lr': 9.744081899330707e-05, 'samples': 20529024, 'steps': 106921, 'loss/train': 1.5744142532348633} 08/31/2021 08:39:06 - INFO - __main__ - Step 106923: {'lr': 9.743661492331895e-05, 'samples': 20529216, 'steps': 106922, 'loss/train': 0.9463986754417419} 08/31/2021 08:39:08 - INFO - __main__ - Step 106924: {'lr': 9.743241092207356e-05, 'samples': 20529408, 'steps': 106923, 'loss/train': 0.8846786618232727} 08/31/2021 08:39:09 - INFO - __main__ - Step 106925: {'lr': 9.742820698957274e-05, 'samples': 20529600, 'steps': 106924, 'loss/train': 1.3455100059509277} 08/31/2021 08:39:09 - INFO - __main__ - Step 106926: {'lr': 9.742400312581845e-05, 'samples': 20529792, 'steps': 106925, 'loss/train': 1.0282621383666992} 08/31/2021 08:39:09 - INFO - __main__ - Step 106927: {'lr': 9.741979933081251e-05, 'samples': 20529984, 'steps': 106926, 'loss/train': 1.4214341640472412} 08/31/2021 08:39:10 - INFO - __main__ - Step 106928: {'lr': 9.74155956045569e-05, 'samples': 20530176, 'steps': 106927, 'loss/train': 0.5774005055427551} 08/31/2021 08:39:11 - INFO - __main__ - Step 106929: {'lr': 9.741139194705345e-05, 'samples': 20530368, 'steps': 106928, 'loss/train': 0.492411345243454} 08/31/2021 08:39:12 - INFO - __main__ - Step 106930: {'lr': 9.740718835830406e-05, 'samples': 20530560, 'steps': 106929, 'loss/train': 1.2840811014175415} 08/31/2021 08:39:12 - INFO - __main__ - Step 106931: {'lr': 9.740298483831073e-05, 'samples': 20530752, 'steps': 106930, 'loss/train': 0.7387442588806152} 08/31/2021 08:39:12 - INFO - __main__ - Step 106932: {'lr': 9.739878138707517e-05, 'samples': 20530944, 'steps': 106931, 'loss/train': 1.2834641933441162} 08/31/2021 08:39:13 - INFO - __main__ - Step 106933: {'lr': 9.739457800459939e-05, 'samples': 20531136, 'steps': 106932, 'loss/train': 1.2609634399414062} 08/31/2021 08:39:14 - INFO - __main__ - Step 106934: {'lr': 9.739037469088524e-05, 'samples': 20531328, 'steps': 106933, 'loss/train': 1.3470765352249146} 08/31/2021 08:39:15 - INFO - __main__ - Step 106935: {'lr': 9.738617144593462e-05, 'samples': 20531520, 'steps': 106934, 'loss/train': 1.5340631008148193} 08/31/2021 08:39:15 - INFO - __main__ - Step 106936: {'lr': 9.738196826974946e-05, 'samples': 20531712, 'steps': 106935, 'loss/train': 1.2603424787521362} 08/31/2021 08:39:15 - INFO - __main__ - Step 106937: {'lr': 9.737776516233159e-05, 'samples': 20531904, 'steps': 106936, 'loss/train': 0.8525152206420898} 08/31/2021 08:39:16 - INFO - __main__ - Step 106938: {'lr': 9.737356212368297e-05, 'samples': 20532096, 'steps': 106937, 'loss/train': 1.5374913215637207} 08/31/2021 08:39:17 - INFO - __main__ - Step 106939: {'lr': 9.736935915380549e-05, 'samples': 20532288, 'steps': 106938, 'loss/train': 1.10094153881073} 08/31/2021 08:39:18 - INFO - __main__ - Step 106940: {'lr': 9.7365156252701e-05, 'samples': 20532480, 'steps': 106939, 'loss/train': 0.5107056498527527} 08/31/2021 08:39:18 - INFO - __main__ - Step 106941: {'lr': 9.736095342037141e-05, 'samples': 20532672, 'steps': 106940, 'loss/train': 0.9813194870948792} 08/31/2021 08:39:18 - INFO - __main__ - Step 106942: {'lr': 9.735675065681863e-05, 'samples': 20532864, 'steps': 106941, 'loss/train': 0.636378288269043} 08/31/2021 08:39:19 - INFO - __main__ - Step 106943: {'lr': 9.735254796204454e-05, 'samples': 20533056, 'steps': 106942, 'loss/train': 1.578966498374939} 08/31/2021 08:39:19 - INFO - __main__ - Step 106944: {'lr': 9.734834533605114e-05, 'samples': 20533248, 'steps': 106943, 'loss/train': 0.6368812918663025} 08/31/2021 08:39:21 - INFO - __main__ - Step 106945: {'lr': 9.73441427788401e-05, 'samples': 20533440, 'steps': 106944, 'loss/train': 1.0947614908218384} 08/31/2021 08:39:22 - INFO - __main__ - Step 106946: {'lr': 9.733994029041343e-05, 'samples': 20533632, 'steps': 106945, 'loss/train': 1.1165292263031006} 08/31/2021 08:39:22 - INFO - __main__ - Step 106947: {'lr': 9.733573787077307e-05, 'samples': 20533824, 'steps': 106946, 'loss/train': 2.8346939086914062} 08/31/2021 08:39:22 - INFO - __main__ - Step 106948: {'lr': 9.733153551992083e-05, 'samples': 20534016, 'steps': 106947, 'loss/train': 1.7135088443756104} 08/31/2021 08:39:23 - INFO - __main__ - Step 106949: {'lr': 9.732733323785867e-05, 'samples': 20534208, 'steps': 106948, 'loss/train': 0.08206751197576523} 08/31/2021 08:39:24 - INFO - __main__ - Step 106950: {'lr': 9.732313102458845e-05, 'samples': 20534400, 'steps': 106949, 'loss/train': 1.428564190864563} 08/31/2021 08:39:25 - INFO - __main__ - Step 106951: {'lr': 9.731892888011206e-05, 'samples': 20534592, 'steps': 106950, 'loss/train': 0.8824874758720398} 08/31/2021 08:39:25 - INFO - __main__ - Step 106952: {'lr': 9.731472680443143e-05, 'samples': 20534784, 'steps': 106951, 'loss/train': 1.6854184865951538} 08/31/2021 08:39:25 - INFO - __main__ - Step 106953: {'lr': 9.73105247975484e-05, 'samples': 20534976, 'steps': 106952, 'loss/train': 1.050886631011963} 08/31/2021 08:39:26 - INFO - __main__ - Step 106954: {'lr': 9.730632285946489e-05, 'samples': 20535168, 'steps': 106953, 'loss/train': 1.4860703945159912} 08/31/2021 08:39:27 - INFO - __main__ - Step 106955: {'lr': 9.73021209901829e-05, 'samples': 20535360, 'steps': 106954, 'loss/train': 0.40409067273139954} 08/31/2021 08:39:28 - INFO - __main__ - Step 106956: {'lr': 9.729791918970413e-05, 'samples': 20535552, 'steps': 106955, 'loss/train': 1.1785331964492798} 08/31/2021 08:39:28 - INFO - __main__ - Step 106957: {'lr': 9.729371745803056e-05, 'samples': 20535744, 'steps': 106956, 'loss/train': 1.743674635887146} 08/31/2021 08:39:28 - INFO - __main__ - Step 106958: {'lr': 9.728951579516409e-05, 'samples': 20535936, 'steps': 106957, 'loss/train': 1.5752408504486084} 08/31/2021 08:39:29 - INFO - __main__ - Step 106959: {'lr': 9.72853142011066e-05, 'samples': 20536128, 'steps': 106958, 'loss/train': 1.310632586479187} 08/31/2021 08:39:31 - INFO - __main__ - Step 106960: {'lr': 9.728111267585998e-05, 'samples': 20536320, 'steps': 106959, 'loss/train': 0.8194876909255981} 08/31/2021 08:39:31 - INFO - __main__ - Step 106961: {'lr': 9.727691121942614e-05, 'samples': 20536512, 'steps': 106960, 'loss/train': 1.039907455444336} 08/31/2021 08:39:32 - INFO - __main__ - Step 106962: {'lr': 9.727270983180697e-05, 'samples': 20536704, 'steps': 106961, 'loss/train': 1.602846622467041} 08/31/2021 08:39:32 - INFO - __main__ - Step 106963: {'lr': 9.726850851300436e-05, 'samples': 20536896, 'steps': 106962, 'loss/train': 1.2387562990188599} 08/31/2021 08:39:32 - INFO - __main__ - Step 106964: {'lr': 9.726430726302021e-05, 'samples': 20537088, 'steps': 106963, 'loss/train': 1.2749340534210205} 08/31/2021 08:39:34 - INFO - __main__ - Step 106965: {'lr': 9.72601060818564e-05, 'samples': 20537280, 'steps': 106964, 'loss/train': 0.7717134952545166} 08/31/2021 08:39:34 - INFO - __main__ - Step 106966: {'lr': 9.725590496951492e-05, 'samples': 20537472, 'steps': 106965, 'loss/train': 1.3102885484695435} 08/31/2021 08:39:35 - INFO - __main__ - Step 106967: {'lr': 9.72517039259975e-05, 'samples': 20537664, 'steps': 106966, 'loss/train': 1.0176221132278442} 08/31/2021 08:39:35 - INFO - __main__ - Step 106968: {'lr': 9.724750295130608e-05, 'samples': 20537856, 'steps': 106967, 'loss/train': 1.4586851596832275} 08/31/2021 08:39:35 - INFO - __main__ - Step 106969: {'lr': 9.724330204544258e-05, 'samples': 20538048, 'steps': 106968, 'loss/train': 0.571659505367279} 08/31/2021 08:39:36 - INFO - __main__ - Step 106970: {'lr': 9.72391012084089e-05, 'samples': 20538240, 'steps': 106969, 'loss/train': 1.0726484060287476} 08/31/2021 08:39:37 - INFO - __main__ - Step 106971: {'lr': 9.723490044020692e-05, 'samples': 20538432, 'steps': 106970, 'loss/train': 1.3977841138839722} 08/31/2021 08:39:38 - INFO - __main__ - Step 106972: {'lr': 9.723069974083853e-05, 'samples': 20538624, 'steps': 106971, 'loss/train': 1.3762272596359253} 08/31/2021 08:39:38 - INFO - __main__ - Step 106973: {'lr': 9.722649911030565e-05, 'samples': 20538816, 'steps': 106972, 'loss/train': 1.2901958227157593} 08/31/2021 08:39:39 - INFO - __main__ - Step 106974: {'lr': 9.722229854861015e-05, 'samples': 20539008, 'steps': 106973, 'loss/train': 0.9855589270591736} 08/31/2021 08:39:39 - INFO - __main__ - Step 106975: {'lr': 9.721809805575391e-05, 'samples': 20539200, 'steps': 106974, 'loss/train': 1.2459255456924438} 08/31/2021 08:39:40 - INFO - __main__ - Step 106976: {'lr': 9.721389763173891e-05, 'samples': 20539392, 'steps': 106975, 'loss/train': 0.2685299217700958} 08/31/2021 08:39:41 - INFO - __main__ - Step 106977: {'lr': 9.72096972765669e-05, 'samples': 20539584, 'steps': 106976, 'loss/train': 1.3277350664138794} 08/31/2021 08:39:41 - INFO - __main__ - Step 106978: {'lr': 9.720549699023984e-05, 'samples': 20539776, 'steps': 106977, 'loss/train': 0.7102240920066833} 08/31/2021 08:39:41 - INFO - __main__ - Step 106979: {'lr': 9.720129677275963e-05, 'samples': 20539968, 'steps': 106978, 'loss/train': 0.9176896810531616} 08/31/2021 08:39:42 - INFO - __main__ - Step 106980: {'lr': 9.719709662412818e-05, 'samples': 20540160, 'steps': 106979, 'loss/train': 1.3167784214019775} 08/31/2021 08:39:43 - INFO - __main__ - Step 106981: {'lr': 9.719289654434732e-05, 'samples': 20540352, 'steps': 106980, 'loss/train': 1.3465383052825928} 08/31/2021 08:39:44 - INFO - __main__ - Step 106982: {'lr': 9.7188696533419e-05, 'samples': 20540544, 'steps': 106981, 'loss/train': 0.1419816017150879} 08/31/2021 08:39:44 - INFO - __main__ - Step 106983: {'lr': 9.71844965913451e-05, 'samples': 20540736, 'steps': 106982, 'loss/train': 0.11288188397884369} 08/31/2021 08:39:45 - INFO - __main__ - Step 106984: {'lr': 9.71802967181275e-05, 'samples': 20540928, 'steps': 106983, 'loss/train': 0.9681414365768433} 08/31/2021 08:39:45 - INFO - __main__ - Step 106985: {'lr': 9.717609691376811e-05, 'samples': 20541120, 'steps': 106984, 'loss/train': 1.4405509233474731} 08/31/2021 08:39:47 - INFO - __main__ - Step 106986: {'lr': 9.717189717826879e-05, 'samples': 20541312, 'steps': 106985, 'loss/train': 0.3443043828010559} 08/31/2021 08:39:47 - INFO - __main__ - Step 106987: {'lr': 9.716769751163157e-05, 'samples': 20541504, 'steps': 106986, 'loss/train': 0.9963691830635071} 08/31/2021 08:39:48 - INFO - __main__ - Step 106988: {'lr': 9.716349791385811e-05, 'samples': 20541696, 'steps': 106987, 'loss/train': 0.09546788036823273} 08/31/2021 08:39:48 - INFO - __main__ - Step 106989: {'lr': 9.715929838495047e-05, 'samples': 20541888, 'steps': 106988, 'loss/train': 0.5497484803199768} 08/31/2021 08:39:48 - INFO - __main__ - Step 106990: {'lr': 9.715509892491045e-05, 'samples': 20542080, 'steps': 106989, 'loss/train': 0.5552133917808533} 08/31/2021 08:39:50 - INFO - __main__ - Step 106991: {'lr': 9.715089953373998e-05, 'samples': 20542272, 'steps': 106990, 'loss/train': 1.3325740098953247} 08/31/2021 08:39:51 - INFO - __main__ - Step 106992: {'lr': 9.714670021144097e-05, 'samples': 20542464, 'steps': 106991, 'loss/train': 0.07816500216722488} 08/31/2021 08:39:51 - INFO - __main__ - Step 106993: {'lr': 9.71425009580153e-05, 'samples': 20542656, 'steps': 106992, 'loss/train': 0.053954243659973145} 08/31/2021 08:39:52 - INFO - __main__ - Step 106994: {'lr': 9.713830177346486e-05, 'samples': 20542848, 'steps': 106993, 'loss/train': 0.04484350234270096} 08/31/2021 08:39:52 - INFO - __main__ - Step 106995: {'lr': 9.713410265779155e-05, 'samples': 20543040, 'steps': 106994, 'loss/train': 1.2789760828018188} 08/31/2021 08:39:52 - INFO - __main__ - Step 106996: {'lr': 9.712990361099725e-05, 'samples': 20543232, 'steps': 106995, 'loss/train': 1.0283681154251099} 08/31/2021 08:39:54 - INFO - __main__ - Step 106997: {'lr': 9.712570463308384e-05, 'samples': 20543424, 'steps': 106996, 'loss/train': 3.5707216262817383} 08/31/2021 08:39:54 - INFO - __main__ - Step 106998: {'lr': 9.712150572405331e-05, 'samples': 20543616, 'steps': 106997, 'loss/train': 0.9747381806373596} 08/31/2021 08:39:55 - INFO - __main__ - Step 106999: {'lr': 9.71173068839074e-05, 'samples': 20543808, 'steps': 106998, 'loss/train': 1.3306187391281128} 08/31/2021 08:39:55 - INFO - __main__ - Step 107000: {'lr': 9.71131081126481e-05, 'samples': 20544000, 'steps': 106999, 'loss/train': 0.8941397666931152} 08/31/2021 08:39:55 - INFO - __main__ - Step 107001: {'lr': 9.710890941027722e-05, 'samples': 20544192, 'steps': 107000, 'loss/train': 0.15458518266677856} 08/31/2021 08:39:57 - INFO - __main__ - Step 107002: {'lr': 9.710471077679675e-05, 'samples': 20544384, 'steps': 107001, 'loss/train': 1.5807979106903076} 08/31/2021 08:39:58 - INFO - __main__ - Step 107003: {'lr': 9.710051221220851e-05, 'samples': 20544576, 'steps': 107002, 'loss/train': 1.280315637588501} 08/31/2021 08:39:58 - INFO - __main__ - Step 107004: {'lr': 9.709631371651443e-05, 'samples': 20544768, 'steps': 107003, 'loss/train': 0.9158442616462708} 08/31/2021 08:39:58 - INFO - __main__ - Step 107005: {'lr': 9.70921152897164e-05, 'samples': 20544960, 'steps': 107004, 'loss/train': 1.8615602254867554} 08/31/2021 08:39:59 - INFO - __main__ - Step 107006: {'lr': 9.708791693181628e-05, 'samples': 20545152, 'steps': 107005, 'loss/train': 0.9847207069396973} 08/31/2021 08:39:59 - INFO - __main__ - Step 107007: {'lr': 9.708371864281601e-05, 'samples': 20545344, 'steps': 107006, 'loss/train': 1.537882924079895} 08/31/2021 08:40:01 - INFO - __main__ - Step 107008: {'lr': 9.707952042271745e-05, 'samples': 20545536, 'steps': 107007, 'loss/train': 0.9567146301269531} 08/31/2021 08:40:01 - INFO - __main__ - Step 107009: {'lr': 9.70753222715225e-05, 'samples': 20545728, 'steps': 107008, 'loss/train': 1.593084692955017} 08/31/2021 08:40:02 - INFO - __main__ - Step 107010: {'lr': 9.707112418923303e-05, 'samples': 20545920, 'steps': 107009, 'loss/train': 0.0751551166176796} 08/31/2021 08:40:02 - INFO - __main__ - Step 107011: {'lr': 9.706692617585097e-05, 'samples': 20546112, 'steps': 107010, 'loss/train': 0.883693516254425} 08/31/2021 08:40:02 - INFO - __main__ - Step 107012: {'lr': 9.706272823137829e-05, 'samples': 20546304, 'steps': 107011, 'loss/train': 1.0039536952972412} 08/31/2021 08:40:04 - INFO - __main__ - Step 107013: {'lr': 9.705853035581668e-05, 'samples': 20546496, 'steps': 107012, 'loss/train': 1.4406734704971313} 08/31/2021 08:40:04 - INFO - __main__ - Step 107014: {'lr': 9.705433254916814e-05, 'samples': 20546688, 'steps': 107013, 'loss/train': 0.8361368775367737} 08/31/2021 08:40:05 - INFO - __main__ - Step 107015: {'lr': 9.705013481143457e-05, 'samples': 20546880, 'steps': 107014, 'loss/train': 0.533431887626648} 08/31/2021 08:40:05 - INFO - __main__ - Step 107016: {'lr': 9.704593714261784e-05, 'samples': 20547072, 'steps': 107015, 'loss/train': 0.7838728427886963} 08/31/2021 08:40:05 - INFO - __main__ - Step 107017: {'lr': 9.704173954271984e-05, 'samples': 20547264, 'steps': 107016, 'loss/train': 1.0405229330062866} 08/31/2021 08:40:08 - INFO - __main__ - Step 107018: {'lr': 9.703754201174248e-05, 'samples': 20547456, 'steps': 107017, 'loss/train': 1.130838394165039} 08/31/2021 08:40:08 - INFO - __main__ - Step 107019: {'lr': 9.703334454968765e-05, 'samples': 20547648, 'steps': 107018, 'loss/train': 1.1398993730545044} 08/31/2021 08:40:09 - INFO - __main__ - Step 107020: {'lr': 9.702914715655723e-05, 'samples': 20547840, 'steps': 107019, 'loss/train': 1.3191230297088623} 08/31/2021 08:40:09 - INFO - __main__ - Step 107021: {'lr': 9.702494983235311e-05, 'samples': 20548032, 'steps': 107020, 'loss/train': 0.9789395332336426} 08/31/2021 08:40:09 - INFO - __main__ - Step 107022: {'lr': 9.702075257707718e-05, 'samples': 20548224, 'steps': 107021, 'loss/train': 0.588477611541748} 08/31/2021 08:40:11 - INFO - __main__ - Step 107023: {'lr': 9.701655539073134e-05, 'samples': 20548416, 'steps': 107022, 'loss/train': 1.4532082080841064} 08/31/2021 08:40:11 - INFO - __main__ - Step 107024: {'lr': 9.70123582733175e-05, 'samples': 20548608, 'steps': 107023, 'loss/train': 0.47406965494155884} 08/31/2021 08:40:12 - INFO - __main__ - Step 107025: {'lr': 9.70081612248376e-05, 'samples': 20548800, 'steps': 107024, 'loss/train': 1.3558894395828247} 08/31/2021 08:40:12 - INFO - __main__ - Step 107026: {'lr': 9.70039642452934e-05, 'samples': 20548992, 'steps': 107025, 'loss/train': 1.3581814765930176} 08/31/2021 08:40:12 - INFO - __main__ - Step 107027: {'lr': 9.699976733468682e-05, 'samples': 20549184, 'steps': 107026, 'loss/train': 1.6679987907409668} 08/31/2021 08:40:14 - INFO - __main__ - Step 107028: {'lr': 9.69955704930198e-05, 'samples': 20549376, 'steps': 107027, 'loss/train': 1.3090896606445312} 08/31/2021 08:40:14 - INFO - __main__ - Step 107029: {'lr': 9.69913737202942e-05, 'samples': 20549568, 'steps': 107028, 'loss/train': 1.1450022459030151} 08/31/2021 08:40:15 - INFO - __main__ - Step 107030: {'lr': 9.698717701651193e-05, 'samples': 20549760, 'steps': 107029, 'loss/train': 0.6298901438713074} 08/31/2021 08:40:15 - INFO - __main__ - Step 107031: {'lr': 9.698298038167492e-05, 'samples': 20549952, 'steps': 107030, 'loss/train': 2.1077659130096436} 08/31/2021 08:40:15 - INFO - __main__ - Step 107032: {'lr': 9.697878381578499e-05, 'samples': 20550144, 'steps': 107031, 'loss/train': 0.8962575793266296} 08/31/2021 08:40:16 - INFO - __main__ - Step 107033: {'lr': 9.697458731884404e-05, 'samples': 20550336, 'steps': 107032, 'loss/train': 0.7835466265678406} 08/31/2021 08:40:17 - INFO - __main__ - Step 107034: {'lr': 9.697039089085399e-05, 'samples': 20550528, 'steps': 107033, 'loss/train': 1.5482831001281738} 08/31/2021 08:40:18 - INFO - __main__ - Step 107035: {'lr': 9.696619453181671e-05, 'samples': 20550720, 'steps': 107034, 'loss/train': 1.2125719785690308} 08/31/2021 08:40:18 - INFO - __main__ - Step 107036: {'lr': 9.696199824173413e-05, 'samples': 20550912, 'steps': 107035, 'loss/train': 1.1099439859390259} 08/31/2021 08:40:18 - INFO - __main__ - Step 107037: {'lr': 9.695780202060809e-05, 'samples': 20551104, 'steps': 107036, 'loss/train': 0.053744103759527206} 08/31/2021 08:40:19 - INFO - __main__ - Step 107038: {'lr': 9.695360586844052e-05, 'samples': 20551296, 'steps': 107037, 'loss/train': 1.6483180522918701} 08/31/2021 08:40:20 - INFO - __main__ - Step 107039: {'lr': 9.694940978523337e-05, 'samples': 20551488, 'steps': 107038, 'loss/train': 1.911889672279358} 08/31/2021 08:40:21 - INFO - __main__ - Step 107040: {'lr': 9.694521377098837e-05, 'samples': 20551680, 'steps': 107039, 'loss/train': 1.8343334197998047} 08/31/2021 08:40:21 - INFO - __main__ - Step 107041: {'lr': 9.694101782570747e-05, 'samples': 20551872, 'steps': 107040, 'loss/train': 1.3765650987625122} 08/31/2021 08:40:21 - INFO - __main__ - Step 107042: {'lr': 9.69368219493926e-05, 'samples': 20552064, 'steps': 107041, 'loss/train': 1.0180646181106567} 08/31/2021 08:40:22 - INFO - __main__ - Step 107043: {'lr': 9.693262614204566e-05, 'samples': 20552256, 'steps': 107042, 'loss/train': 1.0874475240707397} 08/31/2021 08:40:23 - INFO - __main__ - Step 107044: {'lr': 9.69284304036685e-05, 'samples': 20552448, 'steps': 107043, 'loss/train': 1.4837943315505981} 08/31/2021 08:40:24 - INFO - __main__ - Step 107045: {'lr': 9.692423473426302e-05, 'samples': 20552640, 'steps': 107044, 'loss/train': 0.9339009523391724} 08/31/2021 08:40:24 - INFO - __main__ - Step 107046: {'lr': 9.692003913383113e-05, 'samples': 20552832, 'steps': 107045, 'loss/train': 1.4308961629867554} 08/31/2021 08:40:24 - INFO - __main__ - Step 107047: {'lr': 9.691584360237471e-05, 'samples': 20553024, 'steps': 107046, 'loss/train': 0.6045286059379578} 08/31/2021 08:40:25 - INFO - __main__ - Step 107048: {'lr': 9.691164813989564e-05, 'samples': 20553216, 'steps': 107047, 'loss/train': 0.7267823815345764} 08/31/2021 08:40:26 - INFO - __main__ - Step 107049: {'lr': 9.690745274639582e-05, 'samples': 20553408, 'steps': 107048, 'loss/train': 1.5308858156204224} 08/31/2021 08:40:27 - INFO - __main__ - Step 107050: {'lr': 9.690325742187714e-05, 'samples': 20553600, 'steps': 107049, 'loss/train': 1.5085744857788086} 08/31/2021 08:40:27 - INFO - __main__ - Step 107051: {'lr': 9.689906216634147e-05, 'samples': 20553792, 'steps': 107050, 'loss/train': 1.0256597995758057} 08/31/2021 08:40:27 - INFO - __main__ - Step 107052: {'lr': 9.689486697979083e-05, 'samples': 20553984, 'steps': 107051, 'loss/train': 1.3688173294067383} 08/31/2021 08:40:28 - INFO - __main__ - Step 107053: {'lr': 9.689067186222692e-05, 'samples': 20554176, 'steps': 107052, 'loss/train': 0.7678484320640564} 08/31/2021 08:40:29 - INFO - __main__ - Step 107054: {'lr': 9.68864768136517e-05, 'samples': 20554368, 'steps': 107053, 'loss/train': 1.1012458801269531} 08/31/2021 08:40:30 - INFO - __main__ - Step 107055: {'lr': 9.688228183406706e-05, 'samples': 20554560, 'steps': 107054, 'loss/train': 1.364890694618225} 08/31/2021 08:40:30 - INFO - __main__ - Step 107056: {'lr': 9.687808692347492e-05, 'samples': 20554752, 'steps': 107055, 'loss/train': 1.2127773761749268} 08/31/2021 08:40:30 - INFO - __main__ - Step 107057: {'lr': 9.687389208187714e-05, 'samples': 20554944, 'steps': 107056, 'loss/train': 1.4865508079528809} 08/31/2021 08:40:31 - INFO - __main__ - Step 107058: {'lr': 9.686969730927564e-05, 'samples': 20555136, 'steps': 107057, 'loss/train': 1.477526068687439} 08/31/2021 08:40:32 - INFO - __main__ - Step 107059: {'lr': 9.686550260567225e-05, 'samples': 20555328, 'steps': 107058, 'loss/train': 1.11470627784729} 08/31/2021 08:40:33 - INFO - __main__ - Step 107060: {'lr': 9.686130797106896e-05, 'samples': 20555520, 'steps': 107059, 'loss/train': 0.8494611978530884} 08/31/2021 08:40:33 - INFO - __main__ - Step 107061: {'lr': 9.685711340546755e-05, 'samples': 20555712, 'steps': 107060, 'loss/train': 1.38909113407135} 08/31/2021 08:40:33 - INFO - __main__ - Step 107062: {'lr': 9.685291890886999e-05, 'samples': 20555904, 'steps': 107061, 'loss/train': 1.419817328453064} 08/31/2021 08:40:34 - INFO - __main__ - Step 107063: {'lr': 9.684872448127813e-05, 'samples': 20556096, 'steps': 107062, 'loss/train': 0.13907544314861298} 08/31/2021 08:40:36 - INFO - __main__ - Step 107064: {'lr': 9.684453012269387e-05, 'samples': 20556288, 'steps': 107063, 'loss/train': 1.1689553260803223} 08/31/2021 08:40:36 - INFO - __main__ - Step 107065: {'lr': 9.68403358331191e-05, 'samples': 20556480, 'steps': 107064, 'loss/train': 1.10209059715271} 08/31/2021 08:40:36 - INFO - __main__ - Step 107066: {'lr': 9.68361416125558e-05, 'samples': 20556672, 'steps': 107065, 'loss/train': 1.4444580078125} 08/31/2021 08:40:37 - INFO - __main__ - Step 107067: {'lr': 9.683194746100571e-05, 'samples': 20556864, 'steps': 107066, 'loss/train': 0.8390801548957825} 08/31/2021 08:40:37 - INFO - __main__ - Step 107068: {'lr': 9.682775337847075e-05, 'samples': 20557056, 'steps': 107067, 'loss/train': 1.0799586772918701} 08/31/2021 08:40:37 - INFO - __main__ - Step 107069: {'lr': 9.682355936495285e-05, 'samples': 20557248, 'steps': 107068, 'loss/train': 0.38438743352890015} 08/31/2021 08:40:39 - INFO - __main__ - Step 107070: {'lr': 9.681936542045389e-05, 'samples': 20557440, 'steps': 107069, 'loss/train': 1.1095741987228394} 08/31/2021 08:40:40 - INFO - __main__ - Step 107071: {'lr': 9.681517154497576e-05, 'samples': 20557632, 'steps': 107070, 'loss/train': 1.4901906251907349} 08/31/2021 08:40:40 - INFO - __main__ - Step 107072: {'lr': 9.681097773852034e-05, 'samples': 20557824, 'steps': 107071, 'loss/train': 1.084364414215088} 08/31/2021 08:40:41 - INFO - __main__ - Step 107073: {'lr': 9.680678400108955e-05, 'samples': 20558016, 'steps': 107072, 'loss/train': 0.5735841989517212} 08/31/2021 08:40:41 - INFO - __main__ - Step 107074: {'lr': 9.680259033268524e-05, 'samples': 20558208, 'steps': 107073, 'loss/train': 1.2259560823440552} 08/31/2021 08:40:42 - INFO - __main__ - Step 107075: {'lr': 9.679839673330934e-05, 'samples': 20558400, 'steps': 107074, 'loss/train': 1.211562156677246} 08/31/2021 08:40:43 - INFO - __main__ - Step 107076: {'lr': 9.67942032029637e-05, 'samples': 20558592, 'steps': 107075, 'loss/train': 1.549920678138733} 08/31/2021 08:40:43 - INFO - __main__ - Step 107077: {'lr': 9.679000974165022e-05, 'samples': 20558784, 'steps': 107076, 'loss/train': 0.853145182132721} 08/31/2021 08:40:44 - INFO - __main__ - Step 107078: {'lr': 9.678581634937084e-05, 'samples': 20558976, 'steps': 107077, 'loss/train': 1.262402057647705} 08/31/2021 08:40:44 - INFO - __main__ - Step 107079: {'lr': 9.678162302612744e-05, 'samples': 20559168, 'steps': 107078, 'loss/train': 1.378458857536316} 08/31/2021 08:40:45 - INFO - __main__ - Step 107080: {'lr': 9.677742977192184e-05, 'samples': 20559360, 'steps': 107079, 'loss/train': 0.9363263249397278} 08/31/2021 08:40:46 - INFO - __main__ - Step 107081: {'lr': 9.677323658675594e-05, 'samples': 20559552, 'steps': 107080, 'loss/train': 1.7124199867248535} 08/31/2021 08:40:46 - INFO - __main__ - Step 107082: {'lr': 9.676904347063164e-05, 'samples': 20559744, 'steps': 107081, 'loss/train': 0.7488746047019958} 08/31/2021 08:40:47 - INFO - __main__ - Step 107083: {'lr': 9.676485042355087e-05, 'samples': 20559936, 'steps': 107082, 'loss/train': 0.568144679069519} 08/31/2021 08:40:47 - INFO - __main__ - Step 107084: {'lr': 9.676065744551548e-05, 'samples': 20560128, 'steps': 107083, 'loss/train': 1.0829335451126099} 08/31/2021 08:40:49 - INFO - __main__ - Step 107085: {'lr': 9.675646453652736e-05, 'samples': 20560320, 'steps': 107084, 'loss/train': 0.6088138818740845} 08/31/2021 08:40:49 - INFO - __main__ - Step 107086: {'lr': 9.675227169658846e-05, 'samples': 20560512, 'steps': 107085, 'loss/train': 1.2874608039855957} 08/31/2021 08:40:49 - INFO - __main__ - Step 107087: {'lr': 9.674807892570059e-05, 'samples': 20560704, 'steps': 107086, 'loss/train': 0.9656407833099365} 08/31/2021 08:40:50 - INFO - __main__ - Step 107088: {'lr': 9.674388622386565e-05, 'samples': 20560896, 'steps': 107087, 'loss/train': 0.9638950228691101} 08/31/2021 08:40:50 - INFO - __main__ - Step 107089: {'lr': 9.673969359108559e-05, 'samples': 20561088, 'steps': 107088, 'loss/train': 0.6008372902870178} 08/31/2021 08:40:52 - INFO - __main__ - Step 107090: {'lr': 9.673550102736223e-05, 'samples': 20561280, 'steps': 107089, 'loss/train': 1.2713996171951294} 08/31/2021 08:40:52 - INFO - __main__ - Step 107091: {'lr': 9.673130853269751e-05, 'samples': 20561472, 'steps': 107090, 'loss/train': 1.0946242809295654} 08/31/2021 08:40:53 - INFO - __main__ - Step 107092: {'lr': 9.672711610709328e-05, 'samples': 20561664, 'steps': 107091, 'loss/train': 0.7540306448936462} 08/31/2021 08:40:53 - INFO - __main__ - Step 107093: {'lr': 9.672292375055156e-05, 'samples': 20561856, 'steps': 107092, 'loss/train': 0.15247660875320435} 08/31/2021 08:40:53 - INFO - __main__ - Step 107094: {'lr': 9.6718731463074e-05, 'samples': 20562048, 'steps': 107093, 'loss/train': 0.9664754271507263} 08/31/2021 08:40:54 - INFO - __main__ - Step 107095: {'lr': 9.671453924466264e-05, 'samples': 20562240, 'steps': 107094, 'loss/train': 0.8903565406799316} 08/31/2021 08:40:56 - INFO - __main__ - Step 107096: {'lr': 9.671034709531934e-05, 'samples': 20562432, 'steps': 107095, 'loss/train': 0.02989821694791317} 08/31/2021 08:40:56 - INFO - __main__ - Step 107097: {'lr': 9.670615501504598e-05, 'samples': 20562624, 'steps': 107096, 'loss/train': 1.1011563539505005} 08/31/2021 08:40:56 - INFO - __main__ - Step 107098: {'lr': 9.670196300384445e-05, 'samples': 20562816, 'steps': 107097, 'loss/train': 1.1379780769348145} 08/31/2021 08:40:57 - INFO - __main__ - Step 107099: {'lr': 9.669777106171667e-05, 'samples': 20563008, 'steps': 107098, 'loss/train': 5.794408321380615} 08/31/2021 08:40:57 - INFO - __main__ - Step 107100: {'lr': 9.669357918866454e-05, 'samples': 20563200, 'steps': 107099, 'loss/train': 5.757033348083496} 08/31/2021 08:40:58 - INFO - __main__ - Step 107101: {'lr': 9.668938738468989e-05, 'samples': 20563392, 'steps': 107100, 'loss/train': 1.3282006978988647} 08/31/2021 08:40:59 - INFO - __main__ - Step 107102: {'lr': 9.668519564979461e-05, 'samples': 20563584, 'steps': 107101, 'loss/train': 1.4238348007202148} 08/31/2021 08:41:00 - INFO - __main__ - Step 107103: {'lr': 9.668100398398063e-05, 'samples': 20563776, 'steps': 107102, 'loss/train': 1.0394556522369385} 08/31/2021 08:41:00 - INFO - __main__ - Step 107104: {'lr': 9.667681238724985e-05, 'samples': 20563968, 'steps': 107103, 'loss/train': 1.5712271928787231} 08/31/2021 08:41:00 - INFO - __main__ - Step 107105: {'lr': 9.66726208596041e-05, 'samples': 20564160, 'steps': 107104, 'loss/train': 0.944447934627533} 08/31/2021 08:41:01 - INFO - __main__ - Step 107106: {'lr': 9.666842940104539e-05, 'samples': 20564352, 'steps': 107105, 'loss/train': 1.1378397941589355} 08/31/2021 08:41:02 - INFO - __main__ - Step 107107: {'lr': 9.666423801157545e-05, 'samples': 20564544, 'steps': 107106, 'loss/train': 0.23026791214942932} 08/31/2021 08:41:02 - INFO - __main__ - Step 107108: {'lr': 9.666004669119624e-05, 'samples': 20564736, 'steps': 107107, 'loss/train': 0.6176185011863708} 08/31/2021 08:41:03 - INFO - __main__ - Step 107109: {'lr': 9.665585543990965e-05, 'samples': 20564928, 'steps': 107108, 'loss/train': 1.7019106149673462} 08/31/2021 08:41:03 - INFO - __main__ - Step 107110: {'lr': 9.665166425771754e-05, 'samples': 20565120, 'steps': 107109, 'loss/train': 1.2803276777267456} 08/31/2021 08:41:04 - INFO - __main__ - Step 107111: {'lr': 9.664747314462186e-05, 'samples': 20565312, 'steps': 107110, 'loss/train': 1.1779149770736694} 08/31/2021 08:41:04 - INFO - __main__ - Step 107112: {'lr': 9.664328210062443e-05, 'samples': 20565504, 'steps': 107111, 'loss/train': 1.0545599460601807} 08/31/2021 08:41:05 - INFO - __main__ - Step 107113: {'lr': 9.663909112572716e-05, 'samples': 20565696, 'steps': 107112, 'loss/train': 1.314795732498169} 08/31/2021 08:41:06 - INFO - __main__ - Step 107114: {'lr': 9.663490021993199e-05, 'samples': 20565888, 'steps': 107113, 'loss/train': 0.1028975173830986} 08/31/2021 08:41:06 - INFO - __main__ - Step 107115: {'lr': 9.663070938324075e-05, 'samples': 20566080, 'steps': 107114, 'loss/train': 1.2484112977981567} 08/31/2021 08:41:07 - INFO - __main__ - Step 107116: {'lr': 9.662651861565532e-05, 'samples': 20566272, 'steps': 107115, 'loss/train': 0.5236048102378845} 08/31/2021 08:41:07 - INFO - __main__ - Step 107117: {'lr': 9.662232791717765e-05, 'samples': 20566464, 'steps': 107116, 'loss/train': 0.25137507915496826} 08/31/2021 08:41:08 - INFO - __main__ - Step 107118: {'lr': 9.661813728780958e-05, 'samples': 20566656, 'steps': 107117, 'loss/train': 1.1585631370544434} 08/31/2021 08:41:09 - INFO - __main__ - Step 107119: {'lr': 9.661394672755311e-05, 'samples': 20566848, 'steps': 107118, 'loss/train': 0.988869845867157} 08/31/2021 08:41:09 - INFO - __main__ - Step 107120: {'lr': 9.660975623640992e-05, 'samples': 20567040, 'steps': 107119, 'loss/train': 1.5273182392120361} 08/31/2021 08:41:10 - INFO - __main__ - Step 107121: {'lr': 9.660556581438202e-05, 'samples': 20567232, 'steps': 107120, 'loss/train': 0.34401002526283264} 08/31/2021 08:41:10 - INFO - __main__ - Step 107122: {'lr': 9.660137546147127e-05, 'samples': 20567424, 'steps': 107121, 'loss/train': 0.9642392992973328} 08/31/2021 08:41:12 - INFO - __main__ - Step 107123: {'lr': 9.65971851776796e-05, 'samples': 20567616, 'steps': 107122, 'loss/train': 0.8164193630218506} 08/31/2021 08:41:12 - INFO - __main__ - Step 107124: {'lr': 9.659299496300883e-05, 'samples': 20567808, 'steps': 107123, 'loss/train': 1.3768393993377686} 08/31/2021 08:41:13 - INFO - __main__ - Step 107125: {'lr': 9.658880481746093e-05, 'samples': 20568000, 'steps': 107124, 'loss/train': 0.9813694357872009} 08/31/2021 08:41:13 - INFO - __main__ - Step 107126: {'lr': 9.658461474103772e-05, 'samples': 20568192, 'steps': 107125, 'loss/train': 0.8677955865859985} 08/31/2021 08:41:13 - INFO - __main__ - Step 107127: {'lr': 9.658042473374113e-05, 'samples': 20568384, 'steps': 107126, 'loss/train': 1.1106339693069458} 08/31/2021 08:41:14 - INFO - __main__ - Step 107128: {'lr': 9.657623479557303e-05, 'samples': 20568576, 'steps': 107127, 'loss/train': 0.2970218062400818} 08/31/2021 08:41:15 - INFO - __main__ - Step 107129: {'lr': 9.657204492653532e-05, 'samples': 20568768, 'steps': 107128, 'loss/train': 0.5793025493621826} 08/31/2021 08:41:16 - INFO - __main__ - Step 107130: {'lr': 9.656785512662985e-05, 'samples': 20568960, 'steps': 107129, 'loss/train': 0.5285404920578003} 08/31/2021 08:41:16 - INFO - __main__ - Step 107131: {'lr': 9.656366539585856e-05, 'samples': 20569152, 'steps': 107130, 'loss/train': 0.09528309851884842} 08/31/2021 08:41:17 - INFO - __main__ - Step 107132: {'lr': 9.655947573422333e-05, 'samples': 20569344, 'steps': 107131, 'loss/train': 0.7052547335624695} 08/31/2021 08:41:17 - INFO - __main__ - Step 107133: {'lr': 9.655528614172609e-05, 'samples': 20569536, 'steps': 107132, 'loss/train': 1.158192753791809} 08/31/2021 08:41:18 - INFO - __main__ - Step 107134: {'lr': 9.655109661836861e-05, 'samples': 20569728, 'steps': 107133, 'loss/train': 1.9667556285858154} 08/31/2021 08:41:19 - INFO - __main__ - Step 107135: {'lr': 9.654690716415282e-05, 'samples': 20569920, 'steps': 107134, 'loss/train': 1.6077680587768555} 08/31/2021 08:41:19 - INFO - __main__ - Step 107136: {'lr': 9.654271777908061e-05, 'samples': 20570112, 'steps': 107135, 'loss/train': 0.9279983043670654} 08/31/2021 08:41:19 - INFO - __main__ - Step 107137: {'lr': 9.653852846315392e-05, 'samples': 20570304, 'steps': 107136, 'loss/train': 1.0198798179626465} 08/31/2021 08:41:20 - INFO - __main__ - Step 107138: {'lr': 9.653433921637459e-05, 'samples': 20570496, 'steps': 107137, 'loss/train': 1.2350208759307861} 08/31/2021 08:41:22 - INFO - __main__ - Step 107139: {'lr': 9.653015003874449e-05, 'samples': 20570688, 'steps': 107138, 'loss/train': 1.2473080158233643} 08/31/2021 08:41:22 - INFO - __main__ - Step 107140: {'lr': 9.652596093026555e-05, 'samples': 20570880, 'steps': 107139, 'loss/train': 1.993714690208435} 08/31/2021 08:41:22 - INFO - __main__ - Step 107141: {'lr': 9.652177189093967e-05, 'samples': 20571072, 'steps': 107140, 'loss/train': 1.0660074949264526} 08/31/2021 08:41:23 - INFO - __main__ - Step 107142: {'lr': 9.651758292076867e-05, 'samples': 20571264, 'steps': 107141, 'loss/train': 0.16340848803520203} 08/31/2021 08:41:23 - INFO - __main__ - Step 107143: {'lr': 9.65133940197545e-05, 'samples': 20571456, 'steps': 107142, 'loss/train': 1.298892617225647} 08/31/2021 08:41:23 - INFO - __main__ - Step 107144: {'lr': 9.650920518789904e-05, 'samples': 20571648, 'steps': 107143, 'loss/train': 1.4386520385742188} 08/31/2021 08:41:24 - INFO - __main__ - Step 107145: {'lr': 9.650501642520415e-05, 'samples': 20571840, 'steps': 107144, 'loss/train': 1.3695909976959229} 08/31/2021 08:41:25 - INFO - __main__ - Step 107146: {'lr': 9.650082773167182e-05, 'samples': 20572032, 'steps': 107145, 'loss/train': 1.309755563735962} 08/31/2021 08:41:26 - INFO - __main__ - Step 107147: {'lr': 9.649663910730377e-05, 'samples': 20572224, 'steps': 107146, 'loss/train': 1.412326693534851} 08/31/2021 08:41:26 - INFO - __main__ - Step 107148: {'lr': 9.649245055210196e-05, 'samples': 20572416, 'steps': 107147, 'loss/train': 0.4606505334377289} 08/31/2021 08:41:26 - INFO - __main__ - Step 107149: {'lr': 9.648826206606826e-05, 'samples': 20572608, 'steps': 107148, 'loss/train': 1.0031269788742065} 08/31/2021 08:41:27 - INFO - __main__ - Step 107150: {'lr': 9.648407364920461e-05, 'samples': 20572800, 'steps': 107149, 'loss/train': 1.162497639656067} 08/31/2021 08:41:28 - INFO - __main__ - Step 107151: {'lr': 9.647988530151285e-05, 'samples': 20572992, 'steps': 107150, 'loss/train': 1.206028699874878} 08/31/2021 08:41:29 - INFO - __main__ - Step 107152: {'lr': 9.647569702299489e-05, 'samples': 20573184, 'steps': 107151, 'loss/train': 0.5479369759559631} 08/31/2021 08:41:29 - INFO - __main__ - Step 107153: {'lr': 9.647150881365263e-05, 'samples': 20573376, 'steps': 107152, 'loss/train': 0.7711401581764221} 08/31/2021 08:41:29 - INFO - __main__ - Step 107154: {'lr': 9.64673206734879e-05, 'samples': 20573568, 'steps': 107153, 'loss/train': 0.7530151009559631} 08/31/2021 08:41:30 - INFO - __main__ - Step 107155: {'lr': 9.646313260250267e-05, 'samples': 20573760, 'steps': 107154, 'loss/train': 0.6694494485855103} 08/31/2021 08:41:31 - INFO - __main__ - Step 107156: {'lr': 9.645894460069876e-05, 'samples': 20573952, 'steps': 107155, 'loss/train': 1.6360586881637573} 08/31/2021 08:41:32 - INFO - __main__ - Step 107157: {'lr': 9.645475666807807e-05, 'samples': 20574144, 'steps': 107156, 'loss/train': 1.2881107330322266} 08/31/2021 08:41:32 - INFO - __main__ - Step 107158: {'lr': 9.64505688046425e-05, 'samples': 20574336, 'steps': 107157, 'loss/train': 0.5893133282661438} 08/31/2021 08:41:33 - INFO - __main__ - Step 107159: {'lr': 9.644638101039396e-05, 'samples': 20574528, 'steps': 107158, 'loss/train': 0.44986751675605774} 08/31/2021 08:41:33 - INFO - __main__ - Step 107160: {'lr': 9.644219328533438e-05, 'samples': 20574720, 'steps': 107159, 'loss/train': 1.553208351135254} 08/31/2021 08:41:34 - INFO - __main__ - Step 107161: {'lr': 9.643800562946551e-05, 'samples': 20574912, 'steps': 107160, 'loss/train': 1.4931449890136719} 08/31/2021 08:41:35 - INFO - __main__ - Step 107162: {'lr': 9.643381804278927e-05, 'samples': 20575104, 'steps': 107161, 'loss/train': 0.5139908790588379} 08/31/2021 08:41:35 - INFO - __main__ - Step 107163: {'lr': 9.642963052530759e-05, 'samples': 20575296, 'steps': 107162, 'loss/train': 0.3669644296169281} 08/31/2021 08:41:35 - INFO - __main__ - Step 107164: {'lr': 9.642544307702236e-05, 'samples': 20575488, 'steps': 107163, 'loss/train': 0.4945383071899414} 08/31/2021 08:41:36 - INFO - __main__ - Step 107165: {'lr': 9.642125569793547e-05, 'samples': 20575680, 'steps': 107164, 'loss/train': 1.6370012760162354} 08/31/2021 08:41:38 - INFO - __main__ - Step 107166: {'lr': 9.641706838804879e-05, 'samples': 20575872, 'steps': 107165, 'loss/train': 1.1399986743927002} 08/31/2021 08:41:38 - INFO - __main__ - Step 107167: {'lr': 9.641288114736418e-05, 'samples': 20576064, 'steps': 107166, 'loss/train': 0.8910755515098572} 08/31/2021 08:41:39 - INFO - __main__ - Step 107168: {'lr': 9.640869397588356e-05, 'samples': 20576256, 'steps': 107167, 'loss/train': 1.2577297687530518} 08/31/2021 08:41:39 - INFO - __main__ - Step 107169: {'lr': 9.640450687360882e-05, 'samples': 20576448, 'steps': 107168, 'loss/train': 1.3436425924301147} 08/31/2021 08:41:39 - INFO - __main__ - Step 107170: {'lr': 9.640031984054184e-05, 'samples': 20576640, 'steps': 107169, 'loss/train': 2.435749053955078} 08/31/2021 08:41:41 - INFO - __main__ - Step 107171: {'lr': 9.639613287668453e-05, 'samples': 20576832, 'steps': 107170, 'loss/train': 0.536205530166626} 08/31/2021 08:41:41 - INFO - __main__ - Step 107172: {'lr': 9.639194598203873e-05, 'samples': 20577024, 'steps': 107171, 'loss/train': 1.0525225400924683} 08/31/2021 08:41:42 - INFO - __main__ - Step 107173: {'lr': 9.638775915660644e-05, 'samples': 20577216, 'steps': 107172, 'loss/train': 1.7584991455078125} 08/31/2021 08:41:42 - INFO - __main__ - Step 107174: {'lr': 9.638357240038936e-05, 'samples': 20577408, 'steps': 107173, 'loss/train': 1.3939481973648071} 08/31/2021 08:41:42 - INFO - __main__ - Step 107175: {'lr': 9.637938571338947e-05, 'samples': 20577600, 'steps': 107174, 'loss/train': 0.5820891857147217} 08/31/2021 08:41:44 - INFO - __main__ - Step 107176: {'lr': 9.637519909560869e-05, 'samples': 20577792, 'steps': 107175, 'loss/train': 1.279363751411438} 08/31/2021 08:41:45 - INFO - __main__ - Step 107177: {'lr': 9.637101254704882e-05, 'samples': 20577984, 'steps': 107176, 'loss/train': 1.3050516843795776} 08/31/2021 08:41:45 - INFO - __main__ - Step 107178: {'lr': 9.636682606771185e-05, 'samples': 20578176, 'steps': 107177, 'loss/train': 0.6070922017097473} 08/31/2021 08:41:45 - INFO - __main__ - Step 107179: {'lr': 9.636263965759959e-05, 'samples': 20578368, 'steps': 107178, 'loss/train': 0.5989670157432556} 08/31/2021 08:41:46 - INFO - __main__ - Step 107180: {'lr': 9.635845331671397e-05, 'samples': 20578560, 'steps': 107179, 'loss/train': 0.9612488746643066} 08/31/2021 08:41:46 - INFO - __main__ - Step 107181: {'lr': 9.635426704505684e-05, 'samples': 20578752, 'steps': 107180, 'loss/train': 0.7017633318901062} 08/31/2021 08:41:48 - INFO - __main__ - Step 107182: {'lr': 9.635008084263014e-05, 'samples': 20578944, 'steps': 107181, 'loss/train': 0.7932401895523071} 08/31/2021 08:41:49 - INFO - __main__ - Step 107183: {'lr': 9.634589470943569e-05, 'samples': 20579136, 'steps': 107182, 'loss/train': 1.1449940204620361} 08/31/2021 08:41:49 - INFO - __main__ - Step 107184: {'lr': 9.634170864547542e-05, 'samples': 20579328, 'steps': 107183, 'loss/train': 0.8713076114654541} 08/31/2021 08:41:49 - INFO - __main__ - Step 107185: {'lr': 9.633752265075122e-05, 'samples': 20579520, 'steps': 107184, 'loss/train': 1.2968169450759888} 08/31/2021 08:41:50 - INFO - __main__ - Step 107186: {'lr': 9.633333672526493e-05, 'samples': 20579712, 'steps': 107185, 'loss/train': 0.4749062657356262} 08/31/2021 08:41:50 - INFO - __main__ - Step 107187: {'lr': 9.632915086901858e-05, 'samples': 20579904, 'steps': 107186, 'loss/train': 0.5676414370536804} 08/31/2021 08:41:52 - INFO - __main__ - Step 107188: {'lr': 9.632496508201382e-05, 'samples': 20580096, 'steps': 107187, 'loss/train': 0.07169056683778763} 08/31/2021 08:41:52 - INFO - __main__ - Step 107189: {'lr': 9.632077936425271e-05, 'samples': 20580288, 'steps': 107188, 'loss/train': 0.7228058576583862} 08/31/2021 08:41:52 - INFO - __main__ - Step 107190: {'lr': 9.631659371573706e-05, 'samples': 20580480, 'steps': 107189, 'loss/train': 1.0109436511993408} 08/31/2021 08:41:53 - INFO - __main__ - Step 107191: {'lr': 9.631240813646878e-05, 'samples': 20580672, 'steps': 107190, 'loss/train': 1.0616767406463623} 08/31/2021 08:41:53 - INFO - __main__ - Step 107192: {'lr': 9.630822262644976e-05, 'samples': 20580864, 'steps': 107191, 'loss/train': 1.4191056489944458} 08/31/2021 08:41:55 - INFO - __main__ - Step 107193: {'lr': 9.630403718568187e-05, 'samples': 20581056, 'steps': 107192, 'loss/train': 0.8730380535125732} 08/31/2021 08:41:56 - INFO - __main__ - Step 107194: {'lr': 9.629985181416703e-05, 'samples': 20581248, 'steps': 107193, 'loss/train': 0.9455018043518066} 08/31/2021 08:41:56 - INFO - __main__ - Step 107195: {'lr': 9.62956665119071e-05, 'samples': 20581440, 'steps': 107194, 'loss/train': 5.4532012939453125} 08/31/2021 08:41:56 - INFO - __main__ - Step 107196: {'lr': 9.629148127890397e-05, 'samples': 20581632, 'steps': 107195, 'loss/train': 0.8819096684455872} 08/31/2021 08:41:57 - INFO - __main__ - Step 107197: {'lr': 9.628729611515951e-05, 'samples': 20581824, 'steps': 107196, 'loss/train': 1.324592113494873} 08/31/2021 08:41:57 - INFO - __main__ - Step 107198: {'lr': 9.628311102067566e-05, 'samples': 20582016, 'steps': 107197, 'loss/train': 0.03942272067070007} 08/31/2021 08:41:57 - INFO - __main__ - Step 107199: {'lr': 9.627892599545424e-05, 'samples': 20582208, 'steps': 107198, 'loss/train': 1.2572606801986694} 08/31/2021 08:41:59 - INFO - __main__ - Step 107200: {'lr': 9.627474103949727e-05, 'samples': 20582400, 'steps': 107199, 'loss/train': 1.2848488092422485} 08/31/2021 08:41:59 - INFO - __main__ - Step 107201: {'lr': 9.627055615280641e-05, 'samples': 20582592, 'steps': 107200, 'loss/train': 0.9795254468917847} 08/31/2021 08:42:00 - INFO - __main__ - Step 107202: {'lr': 9.626637133538368e-05, 'samples': 20582784, 'steps': 107201, 'loss/train': 1.3104243278503418} 08/31/2021 08:42:00 - INFO - __main__ - Step 107203: {'lr': 9.626218658723096e-05, 'samples': 20582976, 'steps': 107202, 'loss/train': 1.2443649768829346} 08/31/2021 08:42:00 - INFO - __main__ - Step 107204: {'lr': 9.625800190835013e-05, 'samples': 20583168, 'steps': 107203, 'loss/train': 1.2416878938674927} 08/31/2021 08:42:02 - INFO - __main__ - Step 107205: {'lr': 9.625381729874308e-05, 'samples': 20583360, 'steps': 107204, 'loss/train': 1.135412573814392} 08/31/2021 08:42:02 - INFO - __main__ - Step 107206: {'lr': 9.624963275841167e-05, 'samples': 20583552, 'steps': 107205, 'loss/train': 0.7813754677772522} 08/31/2021 08:42:03 - INFO - __main__ - Step 107207: {'lr': 9.62454482873578e-05, 'samples': 20583744, 'steps': 107206, 'loss/train': 1.2428406476974487} 08/31/2021 08:42:03 - INFO - __main__ - Step 107208: {'lr': 9.624126388558335e-05, 'samples': 20583936, 'steps': 107207, 'loss/train': 1.4483143091201782} 08/31/2021 08:42:03 - INFO - __main__ - Step 107209: {'lr': 9.623707955309025e-05, 'samples': 20584128, 'steps': 107208, 'loss/train': 1.3107683658599854} 08/31/2021 08:42:05 - INFO - __main__ - Step 107210: {'lr': 9.62328952898803e-05, 'samples': 20584320, 'steps': 107209, 'loss/train': 1.5142841339111328} 08/31/2021 08:42:05 - INFO - __main__ - Step 107211: {'lr': 9.622871109595546e-05, 'samples': 20584512, 'steps': 107210, 'loss/train': 5.078926086425781} 08/31/2021 08:42:06 - INFO - __main__ - Step 107212: {'lr': 9.62245269713176e-05, 'samples': 20584704, 'steps': 107211, 'loss/train': 1.428531289100647} 08/31/2021 08:42:06 - INFO - __main__ - Step 107213: {'lr': 9.622034291596868e-05, 'samples': 20584896, 'steps': 107212, 'loss/train': 3.715669870376587} 08/31/2021 08:42:07 - INFO - __main__ - Step 107214: {'lr': 9.62161589299104e-05, 'samples': 20585088, 'steps': 107213, 'loss/train': 1.1030138731002808} 08/31/2021 08:42:08 - INFO - __main__ - Step 107215: {'lr': 9.621197501314474e-05, 'samples': 20585280, 'steps': 107214, 'loss/train': 0.963266909122467} 08/31/2021 08:42:08 - INFO - __main__ - Step 107216: {'lr': 9.62077911656736e-05, 'samples': 20585472, 'steps': 107215, 'loss/train': 1.366887092590332} 08/31/2021 08:42:09 - INFO - __main__ - Step 107217: {'lr': 9.620360738749886e-05, 'samples': 20585664, 'steps': 107216, 'loss/train': 1.0007401704788208} 08/31/2021 08:42:09 - INFO - __main__ - Step 107218: {'lr': 9.619942367862241e-05, 'samples': 20585856, 'steps': 107217, 'loss/train': 0.9622012972831726} 08/31/2021 08:42:09 - INFO - __main__ - Step 107219: {'lr': 9.619524003904612e-05, 'samples': 20586048, 'steps': 107218, 'loss/train': 0.8417533040046692} 08/31/2021 08:42:10 - INFO - __main__ - Step 107220: {'lr': 9.619105646877188e-05, 'samples': 20586240, 'steps': 107219, 'loss/train': 0.7380598783493042} 08/31/2021 08:42:11 - INFO - __main__ - Step 107221: {'lr': 9.618687296780157e-05, 'samples': 20586432, 'steps': 107220, 'loss/train': 1.5630913972854614} 08/31/2021 08:42:12 - INFO - __main__ - Step 107222: {'lr': 9.61826895361371e-05, 'samples': 20586624, 'steps': 107221, 'loss/train': 0.9447553157806396} 08/31/2021 08:42:12 - INFO - __main__ - Step 107223: {'lr': 9.617850617378041e-05, 'samples': 20586816, 'steps': 107222, 'loss/train': 1.0006879568099976} 08/31/2021 08:42:13 - INFO - __main__ - Step 107224: {'lr': 9.617432288073322e-05, 'samples': 20587008, 'steps': 107223, 'loss/train': 1.0387355089187622} 08/31/2021 08:42:15 - INFO - __main__ - Step 107225: {'lr': 9.61701396569975e-05, 'samples': 20587200, 'steps': 107224, 'loss/train': 1.6757526397705078} 08/31/2021 08:42:16 - INFO - __main__ - Step 107226: {'lr': 9.616595650257514e-05, 'samples': 20587392, 'steps': 107225, 'loss/train': 0.9061586856842041} 08/31/2021 08:42:16 - INFO - __main__ - Step 107227: {'lr': 9.616177341746807e-05, 'samples': 20587584, 'steps': 107226, 'loss/train': 0.9918128848075867} 08/31/2021 08:42:16 - INFO - __main__ - Step 107228: {'lr': 9.61575904016781e-05, 'samples': 20587776, 'steps': 107227, 'loss/train': 0.32333803176879883} 08/31/2021 08:42:17 - INFO - __main__ - Step 107229: {'lr': 9.615340745520712e-05, 'samples': 20587968, 'steps': 107228, 'loss/train': 1.0971202850341797} 08/31/2021 08:42:17 - INFO - __main__ - Step 107230: {'lr': 9.614922457805708e-05, 'samples': 20588160, 'steps': 107229, 'loss/train': 0.0925125926733017} 08/31/2021 08:42:18 - INFO - __main__ - Step 107231: {'lr': 9.614504177022981e-05, 'samples': 20588352, 'steps': 107230, 'loss/train': 1.1724426746368408} 08/31/2021 08:42:19 - INFO - __main__ - Step 107232: {'lr': 9.61408590317272e-05, 'samples': 20588544, 'steps': 107231, 'loss/train': 0.45313286781311035} 08/31/2021 08:42:19 - INFO - __main__ - Step 107233: {'lr': 9.613667636255116e-05, 'samples': 20588736, 'steps': 107232, 'loss/train': 1.4825084209442139} 08/31/2021 08:42:20 - INFO - __main__ - Step 107234: {'lr': 9.613249376270364e-05, 'samples': 20588928, 'steps': 107233, 'loss/train': 1.3429754972457886} 08/31/2021 08:42:20 - INFO - __main__ - Step 107235: {'lr': 9.612831123218638e-05, 'samples': 20589120, 'steps': 107234, 'loss/train': 0.7690558433532715} 08/31/2021 08:42:21 - INFO - __main__ - Step 107236: {'lr': 9.61241287710013e-05, 'samples': 20589312, 'steps': 107235, 'loss/train': 0.47171273827552795} 08/31/2021 08:42:22 - INFO - __main__ - Step 107237: {'lr': 9.61199463791503e-05, 'samples': 20589504, 'steps': 107236, 'loss/train': 1.2390319108963013} 08/31/2021 08:42:22 - INFO - __main__ - Step 107238: {'lr': 9.611576405663533e-05, 'samples': 20589696, 'steps': 107237, 'loss/train': 0.2880304455757141} 08/31/2021 08:42:23 - INFO - __main__ - Step 107239: {'lr': 9.61115818034582e-05, 'samples': 20589888, 'steps': 107238, 'loss/train': 0.9094682335853577} 08/31/2021 08:42:23 - INFO - __main__ - Step 107240: {'lr': 9.610739961962078e-05, 'samples': 20590080, 'steps': 107239, 'loss/train': 1.1790518760681152} 08/31/2021 08:42:25 - INFO - __main__ - Step 107241: {'lr': 9.610321750512502e-05, 'samples': 20590272, 'steps': 107240, 'loss/train': 1.4021332263946533} 08/31/2021 08:42:25 - INFO - __main__ - Step 107242: {'lr': 9.609903545997278e-05, 'samples': 20590464, 'steps': 107241, 'loss/train': 1.4083466529846191} 08/31/2021 08:42:25 - INFO - __main__ - Step 107243: {'lr': 9.609485348416594e-05, 'samples': 20590656, 'steps': 107242, 'loss/train': 1.6825512647628784} 08/31/2021 08:42:26 - INFO - __main__ - Step 107244: {'lr': 9.609067157770638e-05, 'samples': 20590848, 'steps': 107243, 'loss/train': 0.7668808102607727} 08/31/2021 08:42:26 - INFO - __main__ - Step 107245: {'lr': 9.608648974059606e-05, 'samples': 20591040, 'steps': 107244, 'loss/train': 0.6707156300544739} 08/31/2021 08:42:28 - INFO - __main__ - Step 107246: {'lr': 9.608230797283673e-05, 'samples': 20591232, 'steps': 107245, 'loss/train': 3.0085396766662598} 08/31/2021 08:42:28 - INFO - __main__ - Step 107247: {'lr': 9.607812627443032e-05, 'samples': 20591424, 'steps': 107246, 'loss/train': 1.3697211742401123} 08/31/2021 08:42:28 - INFO - __main__ - Step 107248: {'lr': 9.607394464537875e-05, 'samples': 20591616, 'steps': 107247, 'loss/train': 0.7796127796173096} 08/31/2021 08:42:29 - INFO - __main__ - Step 107249: {'lr': 9.606976308568385e-05, 'samples': 20591808, 'steps': 107248, 'loss/train': 0.961603581905365} 08/31/2021 08:42:29 - INFO - __main__ - Step 107250: {'lr': 9.606558159534756e-05, 'samples': 20592000, 'steps': 107249, 'loss/train': 1.321306586265564} 08/31/2021 08:42:30 - INFO - __main__ - Step 107251: {'lr': 9.606140017437176e-05, 'samples': 20592192, 'steps': 107250, 'loss/train': 1.0890456438064575} 08/31/2021 08:42:31 - INFO - __main__ - Step 107252: {'lr': 9.605721882275831e-05, 'samples': 20592384, 'steps': 107251, 'loss/train': 1.6886101961135864} 08/31/2021 08:42:31 - INFO - __main__ - Step 107253: {'lr': 9.60530375405091e-05, 'samples': 20592576, 'steps': 107252, 'loss/train': 1.8117555379867554} 08/31/2021 08:42:32 - INFO - __main__ - Step 107254: {'lr': 9.6048856327626e-05, 'samples': 20592768, 'steps': 107253, 'loss/train': 1.188651204109192} 08/31/2021 08:42:32 - INFO - __main__ - Step 107255: {'lr': 9.604467518411092e-05, 'samples': 20592960, 'steps': 107254, 'loss/train': 1.1840084791183472} 08/31/2021 08:42:32 - INFO - __main__ - Step 107256: {'lr': 9.604049410996582e-05, 'samples': 20593152, 'steps': 107255, 'loss/train': 1.6720829010009766} 08/31/2021 08:42:34 - INFO - __main__ - Step 107257: {'lr': 9.60363131051924e-05, 'samples': 20593344, 'steps': 107256, 'loss/train': 0.6101132035255432} 08/31/2021 08:42:34 - INFO - __main__ - Step 107258: {'lr': 9.603213216979268e-05, 'samples': 20593536, 'steps': 107257, 'loss/train': 1.4551705121994019} 08/31/2021 08:42:35 - INFO - __main__ - Step 107259: {'lr': 9.602795130376846e-05, 'samples': 20593728, 'steps': 107258, 'loss/train': 1.4112615585327148} 08/31/2021 08:42:35 - INFO - __main__ - Step 107260: {'lr': 9.602377050712169e-05, 'samples': 20593920, 'steps': 107259, 'loss/train': 1.248260498046875} 08/31/2021 08:42:35 - INFO - __main__ - Step 107261: {'lr': 9.601958977985423e-05, 'samples': 20594112, 'steps': 107260, 'loss/train': 1.4672082662582397} 08/31/2021 08:42:37 - INFO - __main__ - Step 107262: {'lr': 9.601540912196796e-05, 'samples': 20594304, 'steps': 107261, 'loss/train': 1.3421306610107422} 08/31/2021 08:42:37 - INFO - __main__ - Step 107263: {'lr': 9.601122853346478e-05, 'samples': 20594496, 'steps': 107262, 'loss/train': 1.248422384262085} 08/31/2021 08:42:38 - INFO - __main__ - Step 107264: {'lr': 9.600704801434657e-05, 'samples': 20594688, 'steps': 107263, 'loss/train': 1.339085578918457} 08/31/2021 08:42:38 - INFO - __main__ - Step 107265: {'lr': 9.600286756461521e-05, 'samples': 20594880, 'steps': 107264, 'loss/train': 0.8783632516860962} 08/31/2021 08:42:38 - INFO - __main__ - Step 107266: {'lr': 9.599868718427256e-05, 'samples': 20595072, 'steps': 107265, 'loss/train': 0.03352999687194824} 08/31/2021 08:42:40 - INFO - __main__ - Step 107267: {'lr': 9.599450687332062e-05, 'samples': 20595264, 'steps': 107266, 'loss/train': 0.9880793690681458} 08/31/2021 08:42:40 - INFO - __main__ - Step 107268: {'lr': 9.59903266317611e-05, 'samples': 20595456, 'steps': 107267, 'loss/train': 1.310739517211914} 08/31/2021 08:42:41 - INFO - __main__ - Step 107269: {'lr': 9.598614645959597e-05, 'samples': 20595648, 'steps': 107268, 'loss/train': 1.294625997543335} 08/31/2021 08:42:41 - INFO - __main__ - Step 107270: {'lr': 9.598196635682707e-05, 'samples': 20595840, 'steps': 107269, 'loss/train': 0.9673343896865845} 08/31/2021 08:42:41 - INFO - __main__ - Step 107271: {'lr': 9.597778632345636e-05, 'samples': 20596032, 'steps': 107270, 'loss/train': 0.9265564680099487} 08/31/2021 08:42:43 - INFO - __main__ - Step 107272: {'lr': 9.597360635948565e-05, 'samples': 20596224, 'steps': 107271, 'loss/train': 0.9860804677009583} 08/31/2021 08:42:44 - INFO - __main__ - Step 107273: {'lr': 9.596942646491688e-05, 'samples': 20596416, 'steps': 107272, 'loss/train': 0.4045785665512085} 08/31/2021 08:42:44 - INFO - __main__ - Step 107274: {'lr': 9.59652466397519e-05, 'samples': 20596608, 'steps': 107273, 'loss/train': 0.712661623954773} 08/31/2021 08:42:44 - INFO - __main__ - Step 107275: {'lr': 9.596106688399262e-05, 'samples': 20596800, 'steps': 107274, 'loss/train': 2.2469935417175293} 08/31/2021 08:42:45 - INFO - __main__ - Step 107276: {'lr': 9.595688719764087e-05, 'samples': 20596992, 'steps': 107275, 'loss/train': 0.9737388491630554} 08/31/2021 08:42:47 - INFO - __main__ - Step 107277: {'lr': 9.59527075806986e-05, 'samples': 20597184, 'steps': 107276, 'loss/train': 1.1349818706512451} 08/31/2021 08:42:47 - INFO - __main__ - Step 107278: {'lr': 9.594852803316764e-05, 'samples': 20597376, 'steps': 107277, 'loss/train': 1.3941233158111572} 08/31/2021 08:42:48 - INFO - __main__ - Step 107279: {'lr': 9.594434855504991e-05, 'samples': 20597568, 'steps': 107278, 'loss/train': 1.0390963554382324} 08/31/2021 08:42:48 - INFO - __main__ - Step 107280: {'lr': 9.594016914634728e-05, 'samples': 20597760, 'steps': 107279, 'loss/train': 1.5025290250778198} 08/31/2021 08:42:48 - INFO - __main__ - Step 107281: {'lr': 9.593598980706172e-05, 'samples': 20597952, 'steps': 107280, 'loss/train': 0.27165403962135315} 08/31/2021 08:42:50 - INFO - __main__ - Step 107282: {'lr': 9.593181053719494e-05, 'samples': 20598144, 'steps': 107281, 'loss/train': 1.3138757944107056} 08/31/2021 08:42:50 - INFO - __main__ - Step 107283: {'lr': 9.592763133674892e-05, 'samples': 20598336, 'steps': 107282, 'loss/train': 1.398629069328308} 08/31/2021 08:42:51 - INFO - __main__ - Step 107284: {'lr': 9.592345220572551e-05, 'samples': 20598528, 'steps': 107283, 'loss/train': 1.4508271217346191} 08/31/2021 08:42:51 - INFO - __main__ - Step 107285: {'lr': 9.591927314412663e-05, 'samples': 20598720, 'steps': 107284, 'loss/train': 1.2742226123809814} 08/31/2021 08:42:51 - INFO - __main__ - Step 107286: {'lr': 9.591509415195413e-05, 'samples': 20598912, 'steps': 107285, 'loss/train': 1.3535590171813965} 08/31/2021 08:42:52 - INFO - __main__ - Step 107287: {'lr': 9.591091522920992e-05, 'samples': 20599104, 'steps': 107286, 'loss/train': 0.9267523884773254} 08/31/2021 08:42:53 - INFO - __main__ - Step 107288: {'lr': 9.590673637589586e-05, 'samples': 20599296, 'steps': 107287, 'loss/train': 1.0657267570495605} 08/31/2021 08:42:54 - INFO - __main__ - Step 107289: {'lr': 9.590255759201388e-05, 'samples': 20599488, 'steps': 107288, 'loss/train': 1.77235746383667} 08/31/2021 08:42:54 - INFO - __main__ - Step 107290: {'lr': 9.58983788775658e-05, 'samples': 20599680, 'steps': 107289, 'loss/train': 0.9635431170463562} 08/31/2021 08:42:54 - INFO - __main__ - Step 107291: {'lr': 9.589420023255355e-05, 'samples': 20599872, 'steps': 107290, 'loss/train': 1.1824595928192139} 08/31/2021 08:42:55 - INFO - __main__ - Step 107292: {'lr': 9.589002165697899e-05, 'samples': 20600064, 'steps': 107291, 'loss/train': 1.1799203157424927} 08/31/2021 08:42:57 - INFO - __main__ - Step 107293: {'lr': 9.5885843150844e-05, 'samples': 20600256, 'steps': 107292, 'loss/train': 1.3572962284088135} 08/31/2021 08:42:57 - INFO - __main__ - Step 107294: {'lr': 9.588166471415058e-05, 'samples': 20600448, 'steps': 107293, 'loss/train': 0.48547399044036865} 08/31/2021 08:42:57 - INFO - __main__ - Step 107295: {'lr': 9.58774863469004e-05, 'samples': 20600640, 'steps': 107294, 'loss/train': 1.6551934480667114} 08/31/2021 08:42:58 - INFO - __main__ - Step 107296: {'lr': 9.587330804909544e-05, 'samples': 20600832, 'steps': 107295, 'loss/train': 0.9957321286201477} 08/31/2021 08:42:58 - INFO - __main__ - Step 107297: {'lr': 9.586912982073762e-05, 'samples': 20601024, 'steps': 107296, 'loss/train': 1.1334421634674072} 08/31/2021 08:43:00 - INFO - __main__ - Step 107298: {'lr': 9.586495166182877e-05, 'samples': 20601216, 'steps': 107297, 'loss/train': 0.08364541828632355} 08/31/2021 08:43:00 - INFO - __main__ - Step 107299: {'lr': 9.586077357237077e-05, 'samples': 20601408, 'steps': 107298, 'loss/train': 1.1724282503128052} 08/31/2021 08:43:01 - INFO - __main__ - Step 107300: {'lr': 9.585659555236556e-05, 'samples': 20601600, 'steps': 107299, 'loss/train': 1.1238033771514893} 08/31/2021 08:43:01 - INFO - __main__ - Step 107301: {'lr': 9.585241760181499e-05, 'samples': 20601792, 'steps': 107300, 'loss/train': 1.0486037731170654} 08/31/2021 08:43:01 - INFO - __main__ - Step 107302: {'lr': 9.584823972072093e-05, 'samples': 20601984, 'steps': 107301, 'loss/train': 1.411884069442749} 08/31/2021 08:43:04 - INFO - __main__ - Step 107303: {'lr': 9.584406190908527e-05, 'samples': 20602176, 'steps': 107302, 'loss/train': 1.0105680227279663} 08/31/2021 08:43:04 - INFO - __main__ - Step 107304: {'lr': 9.58398841669099e-05, 'samples': 20602368, 'steps': 107303, 'loss/train': 1.2736010551452637} 08/31/2021 08:43:05 - INFO - __main__ - Step 107305: {'lr': 9.58357064941967e-05, 'samples': 20602560, 'steps': 107304, 'loss/train': 1.0482486486434937} 08/31/2021 08:43:05 - INFO - __main__ - Step 107306: {'lr': 9.583152889094757e-05, 'samples': 20602752, 'steps': 107305, 'loss/train': 1.165856122970581} 08/31/2021 08:43:05 - INFO - __main__ - Step 107307: {'lr': 9.582735135716437e-05, 'samples': 20602944, 'steps': 107306, 'loss/train': 1.2008473873138428} 08/31/2021 08:43:06 - INFO - __main__ - Step 107308: {'lr': 9.582317389284903e-05, 'samples': 20603136, 'steps': 107307, 'loss/train': 1.3154873847961426} 08/31/2021 08:43:06 - INFO - __main__ - Step 107309: {'lr': 9.581899649800335e-05, 'samples': 20603328, 'steps': 107308, 'loss/train': 1.0447510480880737} 08/31/2021 08:43:06 - INFO - __main__ - Step 107310: {'lr': 9.581481917262924e-05, 'samples': 20603520, 'steps': 107309, 'loss/train': 0.3835475742816925} 08/31/2021 08:43:08 - INFO - __main__ - Step 107311: {'lr': 9.581064191672859e-05, 'samples': 20603712, 'steps': 107310, 'loss/train': 0.2833836078643799} 08/31/2021 08:43:08 - INFO - __main__ - Step 107312: {'lr': 9.580646473030327e-05, 'samples': 20603904, 'steps': 107311, 'loss/train': 0.595137894153595} 08/31/2021 08:43:09 - INFO - __main__ - Step 107313: {'lr': 9.580228761335519e-05, 'samples': 20604096, 'steps': 107312, 'loss/train': 0.03234380483627319} 08/31/2021 08:43:09 - INFO - __main__ - Step 107314: {'lr': 9.579811056588622e-05, 'samples': 20604288, 'steps': 107313, 'loss/train': 0.21907645463943481} 08/31/2021 08:43:09 - INFO - __main__ - Step 107315: {'lr': 9.579393358789825e-05, 'samples': 20604480, 'steps': 107314, 'loss/train': 1.350448489189148} 08/31/2021 08:43:11 - INFO - __main__ - Step 107316: {'lr': 9.578975667939316e-05, 'samples': 20604672, 'steps': 107315, 'loss/train': 1.2485840320587158} 08/31/2021 08:43:11 - INFO - __main__ - Step 107317: {'lr': 9.578557984037281e-05, 'samples': 20604864, 'steps': 107316, 'loss/train': 0.5573439598083496} 08/31/2021 08:43:12 - INFO - __main__ - Step 107318: {'lr': 9.57814030708391e-05, 'samples': 20605056, 'steps': 107317, 'loss/train': 1.2064385414123535} 08/31/2021 08:43:12 - INFO - __main__ - Step 107319: {'lr': 9.57772263707939e-05, 'samples': 20605248, 'steps': 107318, 'loss/train': 1.304779052734375} 08/31/2021 08:43:12 - INFO - __main__ - Step 107320: {'lr': 9.577304974023911e-05, 'samples': 20605440, 'steps': 107319, 'loss/train': 0.9300135970115662} 08/31/2021 08:43:14 - INFO - __main__ - Step 107321: {'lr': 9.57688731791767e-05, 'samples': 20605632, 'steps': 107320, 'loss/train': 0.8131571412086487} 08/31/2021 08:43:14 - INFO - __main__ - Step 107322: {'lr': 9.576469668760837e-05, 'samples': 20605824, 'steps': 107321, 'loss/train': 1.1780269145965576} 08/31/2021 08:43:15 - INFO - __main__ - Step 107323: {'lr': 9.576052026553609e-05, 'samples': 20606016, 'steps': 107322, 'loss/train': 1.1664308309555054} 08/31/2021 08:43:15 - INFO - __main__ - Step 107324: {'lr': 9.57563439129617e-05, 'samples': 20606208, 'steps': 107323, 'loss/train': 1.4496815204620361} 08/31/2021 08:43:15 - INFO - __main__ - Step 107325: {'lr': 9.575216762988717e-05, 'samples': 20606400, 'steps': 107324, 'loss/train': 0.6368297338485718} 08/31/2021 08:43:17 - INFO - __main__ - Step 107326: {'lr': 9.574799141631432e-05, 'samples': 20606592, 'steps': 107325, 'loss/train': 0.9126620888710022} 08/31/2021 08:43:17 - INFO - __main__ - Step 107327: {'lr': 9.574381527224501e-05, 'samples': 20606784, 'steps': 107326, 'loss/train': 1.0978838205337524} 08/31/2021 08:43:18 - INFO - __main__ - Step 107328: {'lr': 9.57396391976812e-05, 'samples': 20606976, 'steps': 107327, 'loss/train': 1.1348282098770142} 08/31/2021 08:43:18 - INFO - __main__ - Step 107329: {'lr': 9.573546319262472e-05, 'samples': 20607168, 'steps': 107328, 'loss/train': 2.1910758018493652} 08/31/2021 08:43:18 - INFO - __main__ - Step 107330: {'lr': 9.573128725707744e-05, 'samples': 20607360, 'steps': 107329, 'loss/train': 1.2085490226745605} 08/31/2021 08:43:20 - INFO - __main__ - Step 107331: {'lr': 9.572711139104129e-05, 'samples': 20607552, 'steps': 107330, 'loss/train': 1.2741326093673706} 08/31/2021 08:43:21 - INFO - __main__ - Step 107332: {'lr': 9.572293559451811e-05, 'samples': 20607744, 'steps': 107331, 'loss/train': 1.0526716709136963} 08/31/2021 08:43:21 - INFO - __main__ - Step 107333: {'lr': 9.57187598675098e-05, 'samples': 20607936, 'steps': 107332, 'loss/train': 0.9513636827468872} 08/31/2021 08:43:22 - INFO - __main__ - Step 107334: {'lr': 9.571458421001822e-05, 'samples': 20608128, 'steps': 107333, 'loss/train': 0.8872134685516357} 08/31/2021 08:43:22 - INFO - __main__ - Step 107335: {'lr': 9.571040862204536e-05, 'samples': 20608320, 'steps': 107334, 'loss/train': 0.6828175187110901} 08/31/2021 08:43:22 - INFO - __main__ - Step 107336: {'lr': 9.570623310359291e-05, 'samples': 20608512, 'steps': 107335, 'loss/train': 0.7011517286300659} 08/31/2021 08:43:24 - INFO - __main__ - Step 107337: {'lr': 9.570205765466289e-05, 'samples': 20608704, 'steps': 107336, 'loss/train': 0.9501222968101501} 08/31/2021 08:43:24 - INFO - __main__ - Step 107338: {'lr': 9.569788227525711e-05, 'samples': 20608896, 'steps': 107337, 'loss/train': 0.7900269031524658} 08/31/2021 08:43:25 - INFO - __main__ - Step 107339: {'lr': 9.56937069653775e-05, 'samples': 20609088, 'steps': 107338, 'loss/train': 1.290412187576294} 08/31/2021 08:43:25 - INFO - __main__ - Step 107340: {'lr': 9.568953172502589e-05, 'samples': 20609280, 'steps': 107339, 'loss/train': 1.4015758037567139} 08/31/2021 08:43:25 - INFO - __main__ - Step 107341: {'lr': 9.568535655420424e-05, 'samples': 20609472, 'steps': 107340, 'loss/train': 0.4660302400588989} 08/31/2021 08:43:27 - INFO - __main__ - Step 107342: {'lr': 9.568118145291437e-05, 'samples': 20609664, 'steps': 107341, 'loss/train': 1.1727491617202759} 08/31/2021 08:43:27 - INFO - __main__ - Step 107343: {'lr': 9.567700642115817e-05, 'samples': 20609856, 'steps': 107342, 'loss/train': 1.0116117000579834} 08/31/2021 08:43:28 - INFO - __main__ - Step 107344: {'lr': 9.567283145893754e-05, 'samples': 20610048, 'steps': 107343, 'loss/train': 4.450706481933594} 08/31/2021 08:43:28 - INFO - __main__ - Step 107345: {'lr': 9.566865656625435e-05, 'samples': 20610240, 'steps': 107344, 'loss/train': 1.3199193477630615} 08/31/2021 08:43:28 - INFO - __main__ - Step 107346: {'lr': 9.566448174311049e-05, 'samples': 20610432, 'steps': 107345, 'loss/train': 0.9825550317764282} 08/31/2021 08:43:29 - INFO - __main__ - Step 107347: {'lr': 9.56603069895078e-05, 'samples': 20610624, 'steps': 107346, 'loss/train': 0.5919831395149231} 08/31/2021 08:43:30 - INFO - __main__ - Step 107348: {'lr': 9.565613230544832e-05, 'samples': 20610816, 'steps': 107347, 'loss/train': 1.5709795951843262} 08/31/2021 08:43:31 - INFO - __main__ - Step 107349: {'lr': 9.565195769093371e-05, 'samples': 20611008, 'steps': 107348, 'loss/train': 1.1598668098449707} 08/31/2021 08:43:31 - INFO - __main__ - Step 107350: {'lr': 9.564778314596592e-05, 'samples': 20611200, 'steps': 107349, 'loss/train': 1.4842190742492676} 08/31/2021 08:43:32 - INFO - __main__ - Step 107351: {'lr': 9.564360867054689e-05, 'samples': 20611392, 'steps': 107350, 'loss/train': 1.899519920349121} 08/31/2021 08:43:32 - INFO - __main__ - Step 107352: {'lr': 9.563943426467844e-05, 'samples': 20611584, 'steps': 107351, 'loss/train': 0.18929995596408844} 08/31/2021 08:43:34 - INFO - __main__ - Step 107353: {'lr': 9.56352599283625e-05, 'samples': 20611776, 'steps': 107352, 'loss/train': 0.6425683498382568} 08/31/2021 08:43:34 - INFO - __main__ - Step 107354: {'lr': 9.563108566160092e-05, 'samples': 20611968, 'steps': 107353, 'loss/train': 1.1366915702819824} 08/31/2021 08:43:35 - INFO - __main__ - Step 107355: {'lr': 9.562691146439559e-05, 'samples': 20612160, 'steps': 107354, 'loss/train': 1.3246346712112427} 08/31/2021 08:43:35 - INFO - __main__ - Step 107356: {'lr': 9.56227373367484e-05, 'samples': 20612352, 'steps': 107355, 'loss/train': 1.2458680868148804} 08/31/2021 08:43:35 - INFO - __main__ - Step 107357: {'lr': 9.56185632786612e-05, 'samples': 20612544, 'steps': 107356, 'loss/train': 1.0268770456314087} 08/31/2021 08:43:37 - INFO - __main__ - Step 107358: {'lr': 9.561438929013592e-05, 'samples': 20612736, 'steps': 107357, 'loss/train': 1.1198707818984985} 08/31/2021 08:43:37 - INFO - __main__ - Step 107359: {'lr': 9.56102153711744e-05, 'samples': 20612928, 'steps': 107358, 'loss/train': 1.160618782043457} 08/31/2021 08:43:38 - INFO - __main__ - Step 107360: {'lr': 9.560604152177855e-05, 'samples': 20613120, 'steps': 107359, 'loss/train': 1.1395395994186401} 08/31/2021 08:43:38 - INFO - __main__ - Step 107361: {'lr': 9.560186774195028e-05, 'samples': 20613312, 'steps': 107360, 'loss/train': 0.7554022669792175} 08/31/2021 08:43:38 - INFO - __main__ - Step 107362: {'lr': 9.559769403169138e-05, 'samples': 20613504, 'steps': 107361, 'loss/train': 1.2932257652282715} 08/31/2021 08:43:40 - INFO - __main__ - Step 107363: {'lr': 9.559352039100377e-05, 'samples': 20613696, 'steps': 107362, 'loss/train': 1.6192712783813477} 08/31/2021 08:43:41 - INFO - __main__ - Step 107364: {'lr': 9.558934681988935e-05, 'samples': 20613888, 'steps': 107363, 'loss/train': 1.3372262716293335} 08/31/2021 08:43:41 - INFO - __main__ - Step 107365: {'lr': 9.558517331834996e-05, 'samples': 20614080, 'steps': 107364, 'loss/train': 0.8191419243812561} 08/31/2021 08:43:42 - INFO - __main__ - Step 107366: {'lr': 9.558099988638752e-05, 'samples': 20614272, 'steps': 107365, 'loss/train': 0.9353303909301758} 08/31/2021 08:43:42 - INFO - __main__ - Step 107367: {'lr': 9.55768265240039e-05, 'samples': 20614464, 'steps': 107366, 'loss/train': 1.171592354774475} 08/31/2021 08:43:42 - INFO - __main__ - Step 107368: {'lr': 9.557265323120096e-05, 'samples': 20614656, 'steps': 107367, 'loss/train': 1.6752102375030518} 08/31/2021 08:43:44 - INFO - __main__ - Step 107369: {'lr': 9.556848000798063e-05, 'samples': 20614848, 'steps': 107368, 'loss/train': 1.1450213193893433} 08/31/2021 08:43:44 - INFO - __main__ - Step 107370: {'lr': 9.556430685434474e-05, 'samples': 20615040, 'steps': 107369, 'loss/train': 1.1057909727096558} 08/31/2021 08:43:45 - INFO - __main__ - Step 107371: {'lr': 9.556013377029519e-05, 'samples': 20615232, 'steps': 107370, 'loss/train': 1.6778889894485474} 08/31/2021 08:43:45 - INFO - __main__ - Step 107372: {'lr': 9.555596075583386e-05, 'samples': 20615424, 'steps': 107371, 'loss/train': 0.38461753726005554} 08/31/2021 08:43:45 - INFO - __main__ - Step 107373: {'lr': 9.555178781096266e-05, 'samples': 20615616, 'steps': 107372, 'loss/train': 1.0894224643707275} 08/31/2021 08:43:47 - INFO - __main__ - Step 107374: {'lr': 9.55476149356834e-05, 'samples': 20615808, 'steps': 107373, 'loss/train': 0.8564246296882629} 08/31/2021 08:43:47 - INFO - __main__ - Step 107375: {'lr': 9.55434421299981e-05, 'samples': 20616000, 'steps': 107374, 'loss/train': 1.3914985656738281} 08/31/2021 08:43:48 - INFO - __main__ - Step 107376: {'lr': 9.553926939390847e-05, 'samples': 20616192, 'steps': 107375, 'loss/train': 0.6405320167541504} 08/31/2021 08:43:48 - INFO - __main__ - Step 107377: {'lr': 9.553509672741645e-05, 'samples': 20616384, 'steps': 107376, 'loss/train': 1.355663537979126} 08/31/2021 08:43:48 - INFO - __main__ - Step 107378: {'lr': 9.553092413052394e-05, 'samples': 20616576, 'steps': 107377, 'loss/train': 1.1427229642868042} 08/31/2021 08:43:50 - INFO - __main__ - Step 107379: {'lr': 9.552675160323282e-05, 'samples': 20616768, 'steps': 107378, 'loss/train': 0.6504741311073303} 08/31/2021 08:43:50 - INFO - __main__ - Step 107380: {'lr': 9.552257914554494e-05, 'samples': 20616960, 'steps': 107379, 'loss/train': 1.343231201171875} 08/31/2021 08:43:51 - INFO - __main__ - Step 107381: {'lr': 9.55184067574622e-05, 'samples': 20617152, 'steps': 107380, 'loss/train': 0.8204243183135986} 08/31/2021 08:43:51 - INFO - __main__ - Step 107382: {'lr': 9.551423443898649e-05, 'samples': 20617344, 'steps': 107381, 'loss/train': 0.9384047389030457} 08/31/2021 08:43:51 - INFO - __main__ - Step 107383: {'lr': 9.551006219011971e-05, 'samples': 20617536, 'steps': 107382, 'loss/train': 1.3311736583709717} 08/31/2021 08:43:53 - INFO - __main__ - Step 107384: {'lr': 9.550589001086369e-05, 'samples': 20617728, 'steps': 107383, 'loss/train': 0.6866693496704102} 08/31/2021 08:43:54 - INFO - __main__ - Step 107385: {'lr': 9.55017179012203e-05, 'samples': 20617920, 'steps': 107384, 'loss/train': 1.1223875284194946} 08/31/2021 08:43:54 - INFO - __main__ - Step 107386: {'lr': 9.54975458611915e-05, 'samples': 20618112, 'steps': 107385, 'loss/train': 0.7333303689956665} 08/31/2021 08:43:54 - INFO - __main__ - Step 107387: {'lr': 9.549337389077908e-05, 'samples': 20618304, 'steps': 107386, 'loss/train': 1.0771892070770264} 08/31/2021 08:43:55 - INFO - __main__ - Step 107388: {'lr': 9.548920198998509e-05, 'samples': 20618496, 'steps': 107387, 'loss/train': 1.5209027528762817} 08/31/2021 08:43:55 - INFO - __main__ - Step 107389: {'lr': 9.548503015881118e-05, 'samples': 20618688, 'steps': 107388, 'loss/train': 1.3974581956863403} 08/31/2021 08:43:57 - INFO - __main__ - Step 107390: {'lr': 9.548085839725931e-05, 'samples': 20618880, 'steps': 107389, 'loss/train': 0.2637239098548889} 08/31/2021 08:43:57 - INFO - __main__ - Step 107391: {'lr': 9.547668670533141e-05, 'samples': 20619072, 'steps': 107390, 'loss/train': 1.6286871433258057} 08/31/2021 08:43:58 - INFO - __main__ - Step 107392: {'lr': 9.547251508302931e-05, 'samples': 20619264, 'steps': 107391, 'loss/train': 1.0898357629776} 08/31/2021 08:43:58 - INFO - __main__ - Step 107393: {'lr': 9.546834353035491e-05, 'samples': 20619456, 'steps': 107392, 'loss/train': 1.0730427503585815} 08/31/2021 08:43:58 - INFO - __main__ - Step 107394: {'lr': 9.546417204731012e-05, 'samples': 20619648, 'steps': 107393, 'loss/train': 1.1966983079910278} 08/31/2021 08:44:00 - INFO - __main__ - Step 107395: {'lr': 9.546000063389675e-05, 'samples': 20619840, 'steps': 107394, 'loss/train': 1.1590131521224976} 08/31/2021 08:44:00 - INFO - __main__ - Step 107396: {'lr': 9.545582929011676e-05, 'samples': 20620032, 'steps': 107395, 'loss/train': 0.6423376202583313} 08/31/2021 08:44:01 - INFO - __main__ - Step 107397: {'lr': 9.545165801597194e-05, 'samples': 20620224, 'steps': 107396, 'loss/train': 0.7646444439888} 08/31/2021 08:44:01 - INFO - __main__ - Step 107398: {'lr': 9.544748681146425e-05, 'samples': 20620416, 'steps': 107397, 'loss/train': 1.2636222839355469} 08/31/2021 08:44:02 - INFO - __main__ - Step 107399: {'lr': 9.544331567659553e-05, 'samples': 20620608, 'steps': 107398, 'loss/train': 0.7914072275161743} 08/31/2021 08:44:03 - INFO - __main__ - Step 107400: {'lr': 9.543914461136769e-05, 'samples': 20620800, 'steps': 107399, 'loss/train': 1.1232253313064575} 08/31/2021 08:44:04 - INFO - __main__ - Step 107401: {'lr': 9.543497361578254e-05, 'samples': 20620992, 'steps': 107400, 'loss/train': 0.7216566205024719} 08/31/2021 08:44:04 - INFO - __main__ - Step 107402: {'lr': 9.543080268984211e-05, 'samples': 20621184, 'steps': 107401, 'loss/train': 0.5662425756454468} 08/31/2021 08:44:04 - INFO - __main__ - Step 107403: {'lr': 9.54266318335481e-05, 'samples': 20621376, 'steps': 107402, 'loss/train': 0.8352737426757812} 08/31/2021 08:44:05 - INFO - __main__ - Step 107404: {'lr': 9.542246104690247e-05, 'samples': 20621568, 'steps': 107403, 'loss/train': 1.3831017017364502} 08/31/2021 08:44:06 - INFO - __main__ - Step 107405: {'lr': 9.541829032990709e-05, 'samples': 20621760, 'steps': 107404, 'loss/train': 0.5613722801208496} 08/31/2021 08:44:07 - INFO - __main__ - Step 107406: {'lr': 9.541411968256383e-05, 'samples': 20621952, 'steps': 107405, 'loss/train': 0.42533281445503235} 08/31/2021 08:44:07 - INFO - __main__ - Step 107407: {'lr': 9.540994910487457e-05, 'samples': 20622144, 'steps': 107406, 'loss/train': 1.304123044013977} 08/31/2021 08:44:07 - INFO - __main__ - Step 107408: {'lr': 9.540577859684124e-05, 'samples': 20622336, 'steps': 107407, 'loss/train': 0.9469597339630127} 08/31/2021 08:44:08 - INFO - __main__ - Step 107409: {'lr': 9.540160815846566e-05, 'samples': 20622528, 'steps': 107408, 'loss/train': 0.7959844470024109} 08/31/2021 08:44:09 - INFO - __main__ - Step 107410: {'lr': 9.539743778974975e-05, 'samples': 20622720, 'steps': 107409, 'loss/train': 1.188163161277771} 08/31/2021 08:44:10 - INFO - __main__ - Step 107411: {'lr': 9.539326749069532e-05, 'samples': 20622912, 'steps': 107410, 'loss/train': 1.017207145690918} 08/31/2021 08:44:10 - INFO - __main__ - Step 107412: {'lr': 9.538909726130435e-05, 'samples': 20623104, 'steps': 107411, 'loss/train': 0.7600564360618591} 08/31/2021 08:44:11 - INFO - __main__ - Step 107413: {'lr': 9.538492710157865e-05, 'samples': 20623296, 'steps': 107412, 'loss/train': 1.7580455541610718} 08/31/2021 08:44:11 - INFO - __main__ - Step 107414: {'lr': 9.53807570115201e-05, 'samples': 20623488, 'steps': 107413, 'loss/train': 1.0994830131530762} 08/31/2021 08:44:12 - INFO - __main__ - Step 107415: {'lr': 9.537658699113069e-05, 'samples': 20623680, 'steps': 107414, 'loss/train': 1.1522247791290283} 08/31/2021 08:44:13 - INFO - __main__ - Step 107416: {'lr': 9.537241704041211e-05, 'samples': 20623872, 'steps': 107415, 'loss/train': 1.3526111841201782} 08/31/2021 08:44:13 - INFO - __main__ - Step 107417: {'lr': 9.536824715936635e-05, 'samples': 20624064, 'steps': 107416, 'loss/train': 0.8438138961791992} 08/31/2021 08:44:14 - INFO - __main__ - Step 107418: {'lr': 9.536407734799527e-05, 'samples': 20624256, 'steps': 107417, 'loss/train': 1.27318274974823} 08/31/2021 08:44:14 - INFO - __main__ - Step 107419: {'lr': 9.535990760630072e-05, 'samples': 20624448, 'steps': 107418, 'loss/train': 1.1418027877807617} 08/31/2021 08:44:16 - INFO - __main__ - Step 107420: {'lr': 9.535573793428465e-05, 'samples': 20624640, 'steps': 107419, 'loss/train': 0.4538024663925171} 08/31/2021 08:44:16 - INFO - __main__ - Step 107421: {'lr': 9.535156833194889e-05, 'samples': 20624832, 'steps': 107420, 'loss/train': 0.774732768535614} 08/31/2021 08:44:16 - INFO - __main__ - Step 107422: {'lr': 9.53473987992953e-05, 'samples': 20625024, 'steps': 107421, 'loss/train': 1.3404537439346313} 08/31/2021 08:44:17 - INFO - __main__ - Step 107423: {'lr': 9.534322933632581e-05, 'samples': 20625216, 'steps': 107422, 'loss/train': 0.9329372048377991} 08/31/2021 08:44:17 - INFO - __main__ - Step 107424: {'lr': 9.533905994304226e-05, 'samples': 20625408, 'steps': 107423, 'loss/train': 1.0599257946014404} 08/31/2021 08:44:17 - INFO - __main__ - Step 107425: {'lr': 9.533489061944655e-05, 'samples': 20625600, 'steps': 107424, 'loss/train': 1.194465160369873} 08/31/2021 08:44:19 - INFO - __main__ - Step 107426: {'lr': 9.533072136554058e-05, 'samples': 20625792, 'steps': 107425, 'loss/train': 0.6859608292579651} 08/31/2021 08:44:19 - INFO - __main__ - Step 107427: {'lr': 9.532655218132616e-05, 'samples': 20625984, 'steps': 107426, 'loss/train': 1.3196128606796265} 08/31/2021 08:44:20 - INFO - __main__ - Step 107428: {'lr': 9.532238306680521e-05, 'samples': 20626176, 'steps': 107427, 'loss/train': 1.177780270576477} 08/31/2021 08:44:20 - INFO - __main__ - Step 107429: {'lr': 9.531821402197972e-05, 'samples': 20626368, 'steps': 107428, 'loss/train': 1.3717046976089478} 08/31/2021 08:44:21 - INFO - __main__ - Step 107430: {'lr': 9.531404504685134e-05, 'samples': 20626560, 'steps': 107429, 'loss/train': 0.07111386954784393} 08/31/2021 08:44:23 - INFO - __main__ - Step 107431: {'lr': 9.530987614142209e-05, 'samples': 20626752, 'steps': 107430, 'loss/train': 1.0449360609054565} 08/31/2021 08:44:23 - INFO - __main__ - Step 107432: {'lr': 9.530570730569383e-05, 'samples': 20626944, 'steps': 107431, 'loss/train': 0.9042270183563232} 08/31/2021 08:44:23 - INFO - __main__ - Step 107433: {'lr': 9.530153853966841e-05, 'samples': 20627136, 'steps': 107432, 'loss/train': 0.8948994874954224} 08/31/2021 08:44:24 - INFO - __main__ - Step 107434: {'lr': 9.529736984334773e-05, 'samples': 20627328, 'steps': 107433, 'loss/train': 1.347769856452942} 08/31/2021 08:44:24 - INFO - __main__ - Step 107435: {'lr': 9.529320121673369e-05, 'samples': 20627520, 'steps': 107434, 'loss/train': 1.4477006196975708} 08/31/2021 08:44:26 - INFO - __main__ - Step 107436: {'lr': 9.52890326598281e-05, 'samples': 20627712, 'steps': 107435, 'loss/train': 0.7341331839561462} 08/31/2021 08:44:26 - INFO - __main__ - Step 107437: {'lr': 9.528486417263294e-05, 'samples': 20627904, 'steps': 107436, 'loss/train': 1.0504881143569946} 08/31/2021 08:44:26 - INFO - __main__ - Step 107438: {'lr': 9.528069575515e-05, 'samples': 20628096, 'steps': 107437, 'loss/train': 1.3428760766983032} 08/31/2021 08:44:27 - INFO - __main__ - Step 107439: {'lr': 9.527652740738118e-05, 'samples': 20628288, 'steps': 107438, 'loss/train': 1.6323901414871216} 08/31/2021 08:44:27 - INFO - __main__ - Step 107440: {'lr': 9.527235912932839e-05, 'samples': 20628480, 'steps': 107439, 'loss/train': 1.301985740661621} 08/31/2021 08:44:28 - INFO - __main__ - Step 107441: {'lr': 9.526819092099348e-05, 'samples': 20628672, 'steps': 107440, 'loss/train': 0.6316635012626648} 08/31/2021 08:44:30 - INFO - __main__ - Step 107442: {'lr': 9.526402278237842e-05, 'samples': 20628864, 'steps': 107441, 'loss/train': 1.814478874206543} 08/31/2021 08:44:30 - INFO - __main__ - Step 107443: {'lr': 9.525985471348491e-05, 'samples': 20629056, 'steps': 107442, 'loss/train': 0.9588897228240967} 08/31/2021 08:44:30 - INFO - __main__ - Step 107444: {'lr': 9.525568671431495e-05, 'samples': 20629248, 'steps': 107443, 'loss/train': 1.472604513168335} 08/31/2021 08:44:31 - INFO - __main__ - Step 107445: {'lr': 9.525151878487037e-05, 'samples': 20629440, 'steps': 107444, 'loss/train': 0.4928511083126068} 08/31/2021 08:44:31 - INFO - __main__ - Step 107446: {'lr': 9.524735092515308e-05, 'samples': 20629632, 'steps': 107445, 'loss/train': 1.445392370223999} 08/31/2021 08:44:33 - INFO - __main__ - Step 107447: {'lr': 9.524318313516495e-05, 'samples': 20629824, 'steps': 107446, 'loss/train': 1.2293301820755005} 08/31/2021 08:44:33 - INFO - __main__ - Step 107448: {'lr': 9.523901541490781e-05, 'samples': 20630016, 'steps': 107447, 'loss/train': 1.3568799495697021} 08/31/2021 08:44:34 - INFO - __main__ - Step 107449: {'lr': 9.523484776438363e-05, 'samples': 20630208, 'steps': 107448, 'loss/train': 0.6476321220397949} 08/31/2021 08:44:34 - INFO - __main__ - Step 107450: {'lr': 9.52306801835942e-05, 'samples': 20630400, 'steps': 107449, 'loss/train': 1.8054437637329102} 08/31/2021 08:44:34 - INFO - __main__ - Step 107451: {'lr': 9.522651267254148e-05, 'samples': 20630592, 'steps': 107450, 'loss/train': 1.1752350330352783} 08/31/2021 08:44:36 - INFO - __main__ - Step 107452: {'lr': 9.522234523122728e-05, 'samples': 20630784, 'steps': 107451, 'loss/train': 1.1914907693862915} 08/31/2021 08:44:36 - INFO - __main__ - Step 107453: {'lr': 9.52181778596535e-05, 'samples': 20630976, 'steps': 107452, 'loss/train': 0.7795267105102539} 08/31/2021 08:44:36 - INFO - __main__ - Step 107454: {'lr': 9.521401055782203e-05, 'samples': 20631168, 'steps': 107453, 'loss/train': 1.3432427644729614} 08/31/2021 08:44:37 - INFO - __main__ - Step 107455: {'lr': 9.520984332573474e-05, 'samples': 20631360, 'steps': 107454, 'loss/train': 1.902921438217163} 08/31/2021 08:44:37 - INFO - __main__ - Step 107456: {'lr': 9.52056761633936e-05, 'samples': 20631552, 'steps': 107455, 'loss/train': 0.9657325148582458} 08/31/2021 08:44:39 - INFO - __main__ - Step 107457: {'lr': 9.520150907080027e-05, 'samples': 20631744, 'steps': 107456, 'loss/train': 0.9696630835533142} 08/31/2021 08:44:39 - INFO - __main__ - Step 107458: {'lr': 9.51973420479568e-05, 'samples': 20631936, 'steps': 107457, 'loss/train': 0.9931274652481079} 08/31/2021 08:44:40 - INFO - __main__ - Step 107459: {'lr': 9.5193175094865e-05, 'samples': 20632128, 'steps': 107458, 'loss/train': 1.308805227279663} 08/31/2021 08:44:40 - INFO - __main__ - Step 107460: {'lr': 9.518900821152677e-05, 'samples': 20632320, 'steps': 107459, 'loss/train': 0.9586748480796814} 08/31/2021 08:44:40 - INFO - __main__ - Step 107461: {'lr': 9.518484139794396e-05, 'samples': 20632512, 'steps': 107460, 'loss/train': 1.2068425416946411} 08/31/2021 08:44:41 - INFO - __main__ - Step 107462: {'lr': 9.518067465411848e-05, 'samples': 20632704, 'steps': 107461, 'loss/train': 0.8583801984786987} 08/31/2021 08:44:42 - INFO - __main__ - Step 107463: {'lr': 9.51765079800522e-05, 'samples': 20632896, 'steps': 107462, 'loss/train': 0.6443690657615662} 08/31/2021 08:44:43 - INFO - __main__ - Step 107464: {'lr': 9.517234137574701e-05, 'samples': 20633088, 'steps': 107463, 'loss/train': 1.207588791847229} 08/31/2021 08:44:43 - INFO - __main__ - Step 107465: {'lr': 9.516817484120477e-05, 'samples': 20633280, 'steps': 107464, 'loss/train': 1.0017058849334717} 08/31/2021 08:44:43 - INFO - __main__ - Step 107466: {'lr': 9.516400837642736e-05, 'samples': 20633472, 'steps': 107465, 'loss/train': 1.0401620864868164} 08/31/2021 08:44:44 - INFO - __main__ - Step 107467: {'lr': 9.515984198141666e-05, 'samples': 20633664, 'steps': 107466, 'loss/train': 0.5200825929641724} 08/31/2021 08:44:45 - INFO - __main__ - Step 107468: {'lr': 9.515567565617453e-05, 'samples': 20633856, 'steps': 107467, 'loss/train': 1.658021330833435} 08/31/2021 08:44:46 - INFO - __main__ - Step 107469: {'lr': 9.515150940070297e-05, 'samples': 20634048, 'steps': 107468, 'loss/train': 1.1812560558319092} 08/31/2021 08:44:46 - INFO - __main__ - Step 107470: {'lr': 9.514734321500365e-05, 'samples': 20634240, 'steps': 107469, 'loss/train': 0.7467882037162781} 08/31/2021 08:44:46 - INFO - __main__ - Step 107471: {'lr': 9.514317709907857e-05, 'samples': 20634432, 'steps': 107470, 'loss/train': 1.4403185844421387} 08/31/2021 08:44:47 - INFO - __main__ - Step 107472: {'lr': 9.513901105292958e-05, 'samples': 20634624, 'steps': 107471, 'loss/train': 0.39557263255119324} 08/31/2021 08:44:48 - INFO - __main__ - Step 107473: {'lr': 9.513484507655854e-05, 'samples': 20634816, 'steps': 107472, 'loss/train': 1.363736867904663} 08/31/2021 08:44:49 - INFO - __main__ - Step 107474: {'lr': 9.513067916996734e-05, 'samples': 20635008, 'steps': 107473, 'loss/train': 1.0566542148590088} 08/31/2021 08:44:49 - INFO - __main__ - Step 107475: {'lr': 9.512651333315789e-05, 'samples': 20635200, 'steps': 107474, 'loss/train': 1.240404486656189} 08/31/2021 08:44:49 - INFO - __main__ - Step 107476: {'lr': 9.512234756613206e-05, 'samples': 20635392, 'steps': 107475, 'loss/train': 0.11762939393520355} 08/31/2021 08:44:50 - INFO - __main__ - Step 107477: {'lr': 9.511818186889168e-05, 'samples': 20635584, 'steps': 107476, 'loss/train': 1.6177470684051514} 08/31/2021 08:44:51 - INFO - __main__ - Step 107478: {'lr': 9.511401624143867e-05, 'samples': 20635776, 'steps': 107477, 'loss/train': 1.2039833068847656} 08/31/2021 08:44:52 - INFO - __main__ - Step 107479: {'lr': 9.51098506837749e-05, 'samples': 20635968, 'steps': 107478, 'loss/train': 0.8178271651268005} 08/31/2021 08:44:52 - INFO - __main__ - Step 107480: {'lr': 9.51056851959022e-05, 'samples': 20636160, 'steps': 107479, 'loss/train': 1.3930492401123047} 08/31/2021 08:44:53 - INFO - __main__ - Step 107481: {'lr': 9.510151977782264e-05, 'samples': 20636352, 'steps': 107480, 'loss/train': 0.5477792024612427} 08/31/2021 08:44:53 - INFO - __main__ - Step 107482: {'lr': 9.509735442953782e-05, 'samples': 20636544, 'steps': 107481, 'loss/train': 0.3661915957927704} 08/31/2021 08:44:54 - INFO - __main__ - Step 107483: {'lr': 9.509318915104976e-05, 'samples': 20636736, 'steps': 107482, 'loss/train': 0.29069939255714417} 08/31/2021 08:44:55 - INFO - __main__ - Step 107484: {'lr': 9.50890239423603e-05, 'samples': 20636928, 'steps': 107483, 'loss/train': 1.0856801271438599} 08/31/2021 08:44:55 - INFO - __main__ - Step 107485: {'lr': 9.508485880347132e-05, 'samples': 20637120, 'steps': 107484, 'loss/train': 1.460364580154419} 08/31/2021 08:44:56 - INFO - __main__ - Step 107486: {'lr': 9.508069373438475e-05, 'samples': 20637312, 'steps': 107485, 'loss/train': 1.2341421842575073} 08/31/2021 08:44:56 - INFO - __main__ - Step 107487: {'lr': 9.50765287351024e-05, 'samples': 20637504, 'steps': 107486, 'loss/train': 1.4198124408721924} 08/31/2021 08:44:58 - INFO - __main__ - Step 107488: {'lr': 9.50723638056262e-05, 'samples': 20637696, 'steps': 107487, 'loss/train': 0.5471900701522827} 08/31/2021 08:44:59 - INFO - __main__ - Step 107489: {'lr': 9.506819894595798e-05, 'samples': 20637888, 'steps': 107488, 'loss/train': 1.9890233278274536} 08/31/2021 08:44:59 - INFO - __main__ - Step 107490: {'lr': 9.506403415609966e-05, 'samples': 20638080, 'steps': 107489, 'loss/train': 1.990457534790039} 08/31/2021 08:44:59 - INFO - __main__ - Step 107491: {'lr': 9.505986943605307e-05, 'samples': 20638272, 'steps': 107490, 'loss/train': 1.187853217124939} 08/31/2021 08:45:00 - INFO - __main__ - Step 107492: {'lr': 9.50557047858202e-05, 'samples': 20638464, 'steps': 107491, 'loss/train': 1.3770676851272583} 08/31/2021 08:45:00 - INFO - __main__ - Step 107493: {'lr': 9.505154020540277e-05, 'samples': 20638656, 'steps': 107492, 'loss/train': 0.6046382188796997} 08/31/2021 08:45:02 - INFO - __main__ - Step 107494: {'lr': 9.504737569480273e-05, 'samples': 20638848, 'steps': 107493, 'loss/train': 0.8570234179496765} 08/31/2021 08:45:03 - INFO - __main__ - Step 107495: {'lr': 9.504321125402193e-05, 'samples': 20639040, 'steps': 107494, 'loss/train': 5.718972682952881} 08/31/2021 08:45:03 - INFO - __main__ - Step 107496: {'lr': 9.503904688306227e-05, 'samples': 20639232, 'steps': 107495, 'loss/train': 1.085023283958435} 08/31/2021 08:45:03 - INFO - __main__ - Step 107497: {'lr': 9.503488258192566e-05, 'samples': 20639424, 'steps': 107496, 'loss/train': 0.5484830141067505} 08/31/2021 08:45:04 - INFO - __main__ - Step 107498: {'lr': 9.503071835061391e-05, 'samples': 20639616, 'steps': 107497, 'loss/train': 1.2608343362808228} 08/31/2021 08:45:04 - INFO - __main__ - Step 107499: {'lr': 9.502655418912892e-05, 'samples': 20639808, 'steps': 107498, 'loss/train': 1.0522701740264893} 08/31/2021 08:45:06 - INFO - __main__ - Step 107500: {'lr': 9.50223900974726e-05, 'samples': 20640000, 'steps': 107499, 'loss/train': 0.8727893829345703} 08/31/2021 08:45:06 - INFO - __main__ - Step 107501: {'lr': 9.501822607564677e-05, 'samples': 20640192, 'steps': 107500, 'loss/train': 1.3417905569076538} 08/31/2021 08:45:06 - INFO - __main__ - Step 107502: {'lr': 9.501406212365334e-05, 'samples': 20640384, 'steps': 107501, 'loss/train': 1.081406831741333} 08/31/2021 08:45:07 - INFO - __main__ - Step 107503: {'lr': 9.500989824149428e-05, 'samples': 20640576, 'steps': 107502, 'loss/train': 1.7216979265213013} 08/31/2021 08:45:07 - INFO - __main__ - Step 107504: {'lr': 9.500573442917129e-05, 'samples': 20640768, 'steps': 107503, 'loss/train': 1.1382194757461548} 08/31/2021 08:45:09 - INFO - __main__ - Step 107505: {'lr': 9.500157068668632e-05, 'samples': 20640960, 'steps': 107504, 'loss/train': 2.795123815536499} 08/31/2021 08:45:09 - INFO - __main__ - Step 107506: {'lr': 9.499740701404124e-05, 'samples': 20641152, 'steps': 107505, 'loss/train': 1.0076067447662354} 08/31/2021 08:45:09 - INFO - __main__ - Step 107507: {'lr': 9.499324341123793e-05, 'samples': 20641344, 'steps': 107506, 'loss/train': 1.1296941041946411} 08/31/2021 08:45:10 - INFO - __main__ - Step 107508: {'lr': 9.498907987827829e-05, 'samples': 20641536, 'steps': 107507, 'loss/train': 1.592293620109558} 08/31/2021 08:45:10 - INFO - __main__ - Step 107509: {'lr': 9.498491641516418e-05, 'samples': 20641728, 'steps': 107508, 'loss/train': 1.4706817865371704} 08/31/2021 08:45:10 - INFO - __main__ - Step 107510: {'lr': 9.498075302189746e-05, 'samples': 20641920, 'steps': 107509, 'loss/train': 1.5882197618484497} 08/31/2021 08:45:12 - INFO - __main__ - Step 107511: {'lr': 9.497658969848002e-05, 'samples': 20642112, 'steps': 107510, 'loss/train': 1.590090036392212} 08/31/2021 08:45:12 - INFO - __main__ - Step 107512: {'lr': 9.497242644491375e-05, 'samples': 20642304, 'steps': 107511, 'loss/train': 0.48478591442108154} 08/31/2021 08:45:13 - INFO - __main__ - Step 107513: {'lr': 9.496826326120051e-05, 'samples': 20642496, 'steps': 107512, 'loss/train': 1.2984524965286255} 08/31/2021 08:45:13 - INFO - __main__ - Step 107514: {'lr': 9.496410014734228e-05, 'samples': 20642688, 'steps': 107513, 'loss/train': 0.9202203750610352} 08/31/2021 08:45:14 - INFO - __main__ - Step 107515: {'lr': 9.495993710334072e-05, 'samples': 20642880, 'steps': 107514, 'loss/train': 0.7383270859718323} 08/31/2021 08:45:15 - INFO - __main__ - Step 107516: {'lr': 9.495577412919781e-05, 'samples': 20643072, 'steps': 107515, 'loss/train': 1.2749875783920288} 08/31/2021 08:45:16 - INFO - __main__ - Step 107517: {'lr': 9.495161122491547e-05, 'samples': 20643264, 'steps': 107516, 'loss/train': 1.0570529699325562} 08/31/2021 08:45:16 - INFO - __main__ - Step 107518: {'lr': 9.494744839049552e-05, 'samples': 20643456, 'steps': 107517, 'loss/train': 1.7052749395370483} 08/31/2021 08:45:16 - INFO - __main__ - Step 107519: {'lr': 9.494328562593987e-05, 'samples': 20643648, 'steps': 107518, 'loss/train': 1.1968728303909302} 08/31/2021 08:45:17 - INFO - __main__ - Step 107520: {'lr': 9.493912293125038e-05, 'samples': 20643840, 'steps': 107519, 'loss/train': 1.5411704778671265} 08/31/2021 08:45:19 - INFO - __main__ - Step 107521: {'lr': 9.493496030642892e-05, 'samples': 20644032, 'steps': 107520, 'loss/train': 1.339186668395996} 08/31/2021 08:45:20 - INFO - __main__ - Step 107522: {'lr': 9.493079775147736e-05, 'samples': 20644224, 'steps': 107521, 'loss/train': 1.5354280471801758} 08/31/2021 08:45:20 - INFO - __main__ - Step 107523: {'lr': 9.492663526639761e-05, 'samples': 20644416, 'steps': 107522, 'loss/train': 1.2102717161178589} 08/31/2021 08:45:20 - INFO - __main__ - Step 107524: {'lr': 9.492247285119155e-05, 'samples': 20644608, 'steps': 107523, 'loss/train': 1.5657330751419067} 08/31/2021 08:45:21 - INFO - __main__ - Step 107525: {'lr': 9.491831050586108e-05, 'samples': 20644800, 'steps': 107524, 'loss/train': 1.1499691009521484} 08/31/2021 08:45:21 - INFO - __main__ - Step 107526: {'lr': 9.491414823040795e-05, 'samples': 20644992, 'steps': 107525, 'loss/train': 1.1832486391067505} 08/31/2021 08:45:21 - INFO - __main__ - Step 107527: {'lr': 9.490998602483411e-05, 'samples': 20645184, 'steps': 107526, 'loss/train': 2.4314141273498535} 08/31/2021 08:45:23 - INFO - __main__ - Step 107528: {'lr': 9.490582388914143e-05, 'samples': 20645376, 'steps': 107527, 'loss/train': 1.9959871768951416} 08/31/2021 08:45:23 - INFO - __main__ - Step 107529: {'lr': 9.490166182333182e-05, 'samples': 20645568, 'steps': 107528, 'loss/train': 0.5232628583908081} 08/31/2021 08:45:24 - INFO - __main__ - Step 107530: {'lr': 9.489749982740711e-05, 'samples': 20645760, 'steps': 107529, 'loss/train': 1.3290897607803345} 08/31/2021 08:45:24 - INFO - __main__ - Step 107531: {'lr': 9.489333790136917e-05, 'samples': 20645952, 'steps': 107530, 'loss/train': 1.2229487895965576} 08/31/2021 08:45:24 - INFO - __main__ - Step 107532: {'lr': 9.488917604521994e-05, 'samples': 20646144, 'steps': 107531, 'loss/train': 1.113869309425354} 08/31/2021 08:45:26 - INFO - __main__ - Step 107533: {'lr': 9.488501425896124e-05, 'samples': 20646336, 'steps': 107532, 'loss/train': 0.5480154156684875} 08/31/2021 08:45:26 - INFO - __main__ - Step 107534: {'lr': 9.488085254259494e-05, 'samples': 20646528, 'steps': 107533, 'loss/train': 1.0775012969970703} 08/31/2021 08:45:27 - INFO - __main__ - Step 107535: {'lr': 9.487669089612294e-05, 'samples': 20646720, 'steps': 107534, 'loss/train': 1.0314441919326782} 08/31/2021 08:45:27 - INFO - __main__ - Step 107536: {'lr': 9.48725293195472e-05, 'samples': 20646912, 'steps': 107535, 'loss/train': 0.8840481638908386} 08/31/2021 08:45:27 - INFO - __main__ - Step 107537: {'lr': 9.486836781286945e-05, 'samples': 20647104, 'steps': 107536, 'loss/train': 1.365445613861084} 08/31/2021 08:45:29 - INFO - __main__ - Step 107538: {'lr': 9.486420637609158e-05, 'samples': 20647296, 'steps': 107537, 'loss/train': 1.2995110750198364} 08/31/2021 08:45:30 - INFO - __main__ - Step 107539: {'lr': 9.486004500921552e-05, 'samples': 20647488, 'steps': 107538, 'loss/train': 1.1149640083312988} 08/31/2021 08:45:30 - INFO - __main__ - Step 107540: {'lr': 9.485588371224313e-05, 'samples': 20647680, 'steps': 107539, 'loss/train': 1.3796244859695435} 08/31/2021 08:45:31 - INFO - __main__ - Step 107541: {'lr': 9.485172248517626e-05, 'samples': 20647872, 'steps': 107540, 'loss/train': 0.020509440451860428} 08/31/2021 08:45:31 - INFO - __main__ - Step 107542: {'lr': 9.484756132801683e-05, 'samples': 20648064, 'steps': 107541, 'loss/train': 0.8703935742378235} 08/31/2021 08:45:31 - INFO - __main__ - Step 107543: {'lr': 9.48434002407667e-05, 'samples': 20648256, 'steps': 107542, 'loss/train': 0.019544528797268867} 08/31/2021 08:45:32 - INFO - __main__ - Step 107544: {'lr': 9.483923922342775e-05, 'samples': 20648448, 'steps': 107543, 'loss/train': 0.7411813735961914} 08/31/2021 08:45:33 - INFO - __main__ - Step 107545: {'lr': 9.483507827600182e-05, 'samples': 20648640, 'steps': 107544, 'loss/train': 1.4451349973678589} 08/31/2021 08:45:34 - INFO - __main__ - Step 107546: {'lr': 9.483091739849082e-05, 'samples': 20648832, 'steps': 107545, 'loss/train': 0.9080624580383301} 08/31/2021 08:45:34 - INFO - __main__ - Step 107547: {'lr': 9.482675659089663e-05, 'samples': 20649024, 'steps': 107546, 'loss/train': 0.9527475237846375} 08/31/2021 08:45:34 - INFO - __main__ - Step 107548: {'lr': 9.482259585322109e-05, 'samples': 20649216, 'steps': 107547, 'loss/train': 1.2639609575271606} 08/31/2021 08:45:35 - INFO - __main__ - Step 107549: {'lr': 9.48184351854661e-05, 'samples': 20649408, 'steps': 107548, 'loss/train': 1.6521615982055664} 08/31/2021 08:45:36 - INFO - __main__ - Step 107550: {'lr': 9.481427458763359e-05, 'samples': 20649600, 'steps': 107549, 'loss/train': 1.7504593133926392} 08/31/2021 08:45:37 - INFO - __main__ - Step 107551: {'lr': 9.481011405972531e-05, 'samples': 20649792, 'steps': 107550, 'loss/train': 1.2908775806427002} 08/31/2021 08:45:37 - INFO - __main__ - Step 107552: {'lr': 9.480595360174321e-05, 'samples': 20649984, 'steps': 107551, 'loss/train': 1.2853691577911377} 08/31/2021 08:45:37 - INFO - __main__ - Step 107553: {'lr': 9.480179321368912e-05, 'samples': 20650176, 'steps': 107552, 'loss/train': 1.7600566148757935} 08/31/2021 08:45:38 - INFO - __main__ - Step 107554: {'lr': 9.479763289556498e-05, 'samples': 20650368, 'steps': 107553, 'loss/train': 0.8650235533714294} 08/31/2021 08:45:38 - INFO - __main__ - Step 107555: {'lr': 9.479347264737261e-05, 'samples': 20650560, 'steps': 107554, 'loss/train': 0.7818946242332458} 08/31/2021 08:45:40 - INFO - __main__ - Step 107556: {'lr': 9.47893124691139e-05, 'samples': 20650752, 'steps': 107555, 'loss/train': 0.6344665884971619} 08/31/2021 08:45:41 - INFO - __main__ - Step 107557: {'lr': 9.478515236079077e-05, 'samples': 20650944, 'steps': 107556, 'loss/train': 1.039368987083435} 08/31/2021 08:45:41 - INFO - __main__ - Step 107558: {'lr': 9.478099232240503e-05, 'samples': 20651136, 'steps': 107557, 'loss/train': 1.261858582496643} 08/31/2021 08:45:41 - INFO - __main__ - Step 107559: {'lr': 9.477683235395856e-05, 'samples': 20651328, 'steps': 107558, 'loss/train': 0.8095993995666504} 08/31/2021 08:45:42 - INFO - __main__ - Step 107560: {'lr': 9.47726724554533e-05, 'samples': 20651520, 'steps': 107559, 'loss/train': 0.74733966588974} 08/31/2021 08:45:43 - INFO - __main__ - Step 107561: {'lr': 9.476851262689103e-05, 'samples': 20651712, 'steps': 107560, 'loss/train': 0.6549397110939026} 08/31/2021 08:45:44 - INFO - __main__ - Step 107562: {'lr': 9.476435286827371e-05, 'samples': 20651904, 'steps': 107561, 'loss/train': 1.3666887283325195} 08/31/2021 08:45:44 - INFO - __main__ - Step 107563: {'lr': 9.476019317960325e-05, 'samples': 20652096, 'steps': 107562, 'loss/train': 1.0220756530761719} 08/31/2021 08:45:44 - INFO - __main__ - Step 107564: {'lr': 9.475603356088135e-05, 'samples': 20652288, 'steps': 107563, 'loss/train': 0.7894126176834106} 08/31/2021 08:45:45 - INFO - __main__ - Step 107565: {'lr': 9.475187401211e-05, 'samples': 20652480, 'steps': 107564, 'loss/train': 1.803521752357483} 08/31/2021 08:45:46 - INFO - __main__ - Step 107566: {'lr': 9.474771453329106e-05, 'samples': 20652672, 'steps': 107565, 'loss/train': 1.3608325719833374} 08/31/2021 08:45:47 - INFO - __main__ - Step 107567: {'lr': 9.474355512442639e-05, 'samples': 20652864, 'steps': 107566, 'loss/train': 1.648926854133606} 08/31/2021 08:45:47 - INFO - __main__ - Step 107568: {'lr': 9.47393957855179e-05, 'samples': 20653056, 'steps': 107567, 'loss/train': 1.1858198642730713} 08/31/2021 08:45:48 - INFO - __main__ - Step 107569: {'lr': 9.473523651656743e-05, 'samples': 20653248, 'steps': 107568, 'loss/train': 1.3483766317367554} 08/31/2021 08:45:48 - INFO - __main__ - Step 107570: {'lr': 9.473107731757689e-05, 'samples': 20653440, 'steps': 107569, 'loss/train': 1.0845611095428467} 08/31/2021 08:45:48 - INFO - __main__ - Step 107571: {'lr': 9.472691818854809e-05, 'samples': 20653632, 'steps': 107570, 'loss/train': 1.3316395282745361} 08/31/2021 08:45:50 - INFO - __main__ - Step 107572: {'lr': 9.472275912948297e-05, 'samples': 20653824, 'steps': 107571, 'loss/train': 1.0005656480789185} 08/31/2021 08:45:51 - INFO - __main__ - Step 107573: {'lr': 9.471860014038336e-05, 'samples': 20654016, 'steps': 107572, 'loss/train': 1.4611053466796875} 08/31/2021 08:45:51 - INFO - __main__ - Step 107574: {'lr': 9.471444122125117e-05, 'samples': 20654208, 'steps': 107573, 'loss/train': 0.47391387820243835} 08/31/2021 08:45:51 - INFO - __main__ - Step 107575: {'lr': 9.471028237208826e-05, 'samples': 20654400, 'steps': 107574, 'loss/train': 1.0157564878463745} 08/31/2021 08:45:52 - INFO - __main__ - Step 107576: {'lr': 9.470612359289648e-05, 'samples': 20654592, 'steps': 107575, 'loss/train': 1.1902439594268799} 08/31/2021 08:45:53 - INFO - __main__ - Step 107577: {'lr': 9.470196488367785e-05, 'samples': 20654784, 'steps': 107576, 'loss/train': 0.5232098698616028} 08/31/2021 08:45:54 - INFO - __main__ - Step 107578: {'lr': 9.4697806244434e-05, 'samples': 20654976, 'steps': 107577, 'loss/train': 1.1653119325637817} 08/31/2021 08:45:54 - INFO - __main__ - Step 107579: {'lr': 9.469364767516691e-05, 'samples': 20655168, 'steps': 107578, 'loss/train': 0.8085770606994629} 08/31/2021 08:45:54 - INFO - __main__ - Step 107580: {'lr': 9.46894891758785e-05, 'samples': 20655360, 'steps': 107579, 'loss/train': 0.8858819603919983} 08/31/2021 08:45:55 - INFO - __main__ - Step 107581: {'lr': 9.46853307465706e-05, 'samples': 20655552, 'steps': 107580, 'loss/train': 0.9051340818405151} 08/31/2021 08:45:56 - INFO - __main__ - Step 107582: {'lr': 9.468117238724507e-05, 'samples': 20655744, 'steps': 107581, 'loss/train': 0.9377085566520691} 08/31/2021 08:45:57 - INFO - __main__ - Step 107583: {'lr': 9.467701409790384e-05, 'samples': 20655936, 'steps': 107582, 'loss/train': 1.1218143701553345} 08/31/2021 08:45:57 - INFO - __main__ - Step 107584: {'lr': 9.467285587854874e-05, 'samples': 20656128, 'steps': 107583, 'loss/train': 0.7825645804405212} 08/31/2021 08:45:58 - INFO - __main__ - Step 107585: {'lr': 9.466869772918162e-05, 'samples': 20656320, 'steps': 107584, 'loss/train': 1.231796383857727} 08/31/2021 08:45:58 - INFO - __main__ - Step 107586: {'lr': 9.466453964980443e-05, 'samples': 20656512, 'steps': 107585, 'loss/train': 1.231482982635498} 08/31/2021 08:45:59 - INFO - __main__ - Step 107587: {'lr': 9.466038164041898e-05, 'samples': 20656704, 'steps': 107586, 'loss/train': 1.8824658393859863} 08/31/2021 08:46:00 - INFO - __main__ - Step 107588: {'lr': 9.46562237010272e-05, 'samples': 20656896, 'steps': 107587, 'loss/train': 1.2260679006576538} 08/31/2021 08:46:00 - INFO - __main__ - Step 107589: {'lr': 9.465206583163088e-05, 'samples': 20657088, 'steps': 107588, 'loss/train': 1.1069746017456055} 08/31/2021 08:46:01 - INFO - __main__ - Step 107590: {'lr': 9.464790803223205e-05, 'samples': 20657280, 'steps': 107589, 'loss/train': 1.489072561264038} 08/31/2021 08:46:01 - INFO - __main__ - Step 107591: {'lr': 9.46437503028324e-05, 'samples': 20657472, 'steps': 107590, 'loss/train': 1.30763578414917} 08/31/2021 08:46:03 - INFO - __main__ - Step 107592: {'lr': 9.463959264343385e-05, 'samples': 20657664, 'steps': 107591, 'loss/train': 0.9082358479499817} 08/31/2021 08:46:03 - INFO - __main__ - Step 107593: {'lr': 9.463543505403834e-05, 'samples': 20657856, 'steps': 107592, 'loss/train': 1.2554852962493896} 08/31/2021 08:46:03 - INFO - __main__ - Step 107594: {'lr': 9.463127753464767e-05, 'samples': 20658048, 'steps': 107593, 'loss/train': 1.3976709842681885} 08/31/2021 08:46:04 - INFO - __main__ - Step 107595: {'lr': 9.462712008526378e-05, 'samples': 20658240, 'steps': 107594, 'loss/train': 1.1327584981918335} 08/31/2021 08:46:04 - INFO - __main__ - Step 107596: {'lr': 9.46229627058885e-05, 'samples': 20658432, 'steps': 107595, 'loss/train': 1.333005428314209} 08/31/2021 08:46:06 - INFO - __main__ - Step 107597: {'lr': 9.46188053965237e-05, 'samples': 20658624, 'steps': 107596, 'loss/train': 1.0485891103744507} 08/31/2021 08:46:06 - INFO - __main__ - Step 107598: {'lr': 9.46146481571713e-05, 'samples': 20658816, 'steps': 107597, 'loss/train': 0.8721388578414917} 08/31/2021 08:46:06 - INFO - __main__ - Step 107599: {'lr': 9.461049098783312e-05, 'samples': 20659008, 'steps': 107598, 'loss/train': 1.2869188785552979} 08/31/2021 08:46:07 - INFO - __main__ - Step 107600: {'lr': 9.460633388851106e-05, 'samples': 20659200, 'steps': 107599, 'loss/train': 1.217995285987854} 08/31/2021 08:46:07 - INFO - __main__ - Step 107601: {'lr': 9.460217685920697e-05, 'samples': 20659392, 'steps': 107600, 'loss/train': 1.77584707736969} 08/31/2021 08:46:07 - INFO - __main__ - Step 107602: {'lr': 9.459801989992275e-05, 'samples': 20659584, 'steps': 107601, 'loss/train': 1.2168447971343994} 08/31/2021 08:46:09 - INFO - __main__ - Step 107603: {'lr': 9.459386301066036e-05, 'samples': 20659776, 'steps': 107602, 'loss/train': 1.327474594116211} 08/31/2021 08:46:09 - INFO - __main__ - Step 107604: {'lr': 9.458970619142149e-05, 'samples': 20659968, 'steps': 107603, 'loss/train': 1.8143447637557983} 08/31/2021 08:46:10 - INFO - __main__ - Step 107605: {'lr': 9.45855494422081e-05, 'samples': 20660160, 'steps': 107604, 'loss/train': 1.2740287780761719} 08/31/2021 08:46:10 - INFO - __main__ - Step 107606: {'lr': 9.458139276302208e-05, 'samples': 20660352, 'steps': 107605, 'loss/train': 0.8991782665252686} 08/31/2021 08:46:12 - INFO - __main__ - Step 107607: {'lr': 9.457723615386526e-05, 'samples': 20660544, 'steps': 107606, 'loss/train': 1.6659724712371826} 08/31/2021 08:46:13 - INFO - __main__ - Step 107608: {'lr': 9.457307961473954e-05, 'samples': 20660736, 'steps': 107607, 'loss/train': 1.385733723640442} 08/31/2021 08:46:13 - INFO - __main__ - Step 107609: {'lr': 9.45689231456468e-05, 'samples': 20660928, 'steps': 107608, 'loss/train': 0.8224989175796509} 08/31/2021 08:46:13 - INFO - __main__ - Step 107610: {'lr': 9.45647667465889e-05, 'samples': 20661120, 'steps': 107609, 'loss/train': 1.0030674934387207} 08/31/2021 08:46:14 - INFO - __main__ - Step 107611: {'lr': 9.456061041756772e-05, 'samples': 20661312, 'steps': 107610, 'loss/train': 1.0051954984664917} 08/31/2021 08:46:14 - INFO - __main__ - Step 107612: {'lr': 9.455645415858514e-05, 'samples': 20661504, 'steps': 107611, 'loss/train': 1.1179673671722412} 08/31/2021 08:46:16 - INFO - __main__ - Step 107613: {'lr': 9.455229796964302e-05, 'samples': 20661696, 'steps': 107612, 'loss/train': 1.3334101438522339} 08/31/2021 08:46:16 - INFO - __main__ - Step 107614: {'lr': 9.454814185074323e-05, 'samples': 20661888, 'steps': 107613, 'loss/train': 5.815192222595215} 08/31/2021 08:46:17 - INFO - __main__ - Step 107615: {'lr': 9.454398580188764e-05, 'samples': 20662080, 'steps': 107614, 'loss/train': 0.663994550704956} 08/31/2021 08:46:17 - INFO - __main__ - Step 107616: {'lr': 9.453982982307816e-05, 'samples': 20662272, 'steps': 107615, 'loss/train': 0.9140866994857788} 08/31/2021 08:46:17 - INFO - __main__ - Step 107617: {'lr': 9.45356739143167e-05, 'samples': 20662464, 'steps': 107616, 'loss/train': 0.175772026181221} 08/31/2021 08:46:19 - INFO - __main__ - Step 107618: {'lr': 9.453151807560498e-05, 'samples': 20662656, 'steps': 107617, 'loss/train': 2.465609550476074} 08/31/2021 08:46:19 - INFO - __main__ - Step 107619: {'lr': 9.452736230694494e-05, 'samples': 20662848, 'steps': 107618, 'loss/train': 1.498498558998108} 08/31/2021 08:46:20 - INFO - __main__ - Step 107620: {'lr': 9.452320660833849e-05, 'samples': 20663040, 'steps': 107619, 'loss/train': 0.39475998282432556} 08/31/2021 08:46:20 - INFO - __main__ - Step 107621: {'lr': 9.45190509797875e-05, 'samples': 20663232, 'steps': 107620, 'loss/train': 1.5977816581726074} 08/31/2021 08:46:20 - INFO - __main__ - Step 107622: {'lr': 9.451489542129379e-05, 'samples': 20663424, 'steps': 107621, 'loss/train': 0.8922869563102722} 08/31/2021 08:46:22 - INFO - __main__ - Step 107623: {'lr': 9.45107399328593e-05, 'samples': 20663616, 'steps': 107622, 'loss/train': 1.4105455875396729} 08/31/2021 08:46:22 - INFO - __main__ - Step 107624: {'lr': 9.450658451448588e-05, 'samples': 20663808, 'steps': 107623, 'loss/train': 1.327336311340332} 08/31/2021 08:46:23 - INFO - __main__ - Step 107625: {'lr': 9.450242916617535e-05, 'samples': 20664000, 'steps': 107624, 'loss/train': 0.9168437719345093} 08/31/2021 08:46:23 - INFO - __main__ - Step 107626: {'lr': 9.449827388792967e-05, 'samples': 20664192, 'steps': 107625, 'loss/train': 0.960771381855011} 08/31/2021 08:46:23 - INFO - __main__ - Step 107627: {'lr': 9.449411867975063e-05, 'samples': 20664384, 'steps': 107626, 'loss/train': 1.5660290718078613} 08/31/2021 08:46:25 - INFO - __main__ - Step 107628: {'lr': 9.448996354164016e-05, 'samples': 20664576, 'steps': 107627, 'loss/train': 2.352597713470459} 08/31/2021 08:46:26 - INFO - __main__ - Step 107629: {'lr': 9.448580847360013e-05, 'samples': 20664768, 'steps': 107628, 'loss/train': 0.7644488215446472} 08/31/2021 08:46:26 - INFO - __main__ - Step 107630: {'lr': 9.448165347563244e-05, 'samples': 20664960, 'steps': 107629, 'loss/train': 0.7278079390525818} 08/31/2021 08:46:27 - INFO - __main__ - Step 107631: {'lr': 9.447749854773888e-05, 'samples': 20665152, 'steps': 107630, 'loss/train': 0.13042572140693665} 08/31/2021 08:46:27 - INFO - __main__ - Step 107632: {'lr': 9.447334368992133e-05, 'samples': 20665344, 'steps': 107631, 'loss/train': 1.665347933769226} 08/31/2021 08:46:28 - INFO - __main__ - Step 107633: {'lr': 9.44691889021817e-05, 'samples': 20665536, 'steps': 107632, 'loss/train': 0.8297322988510132} 08/31/2021 08:46:29 - INFO - __main__ - Step 107634: {'lr': 9.446503418452184e-05, 'samples': 20665728, 'steps': 107633, 'loss/train': 1.142409324645996} 08/31/2021 08:46:29 - INFO - __main__ - Step 107635: {'lr': 9.446087953694366e-05, 'samples': 20665920, 'steps': 107634, 'loss/train': 1.6092599630355835} 08/31/2021 08:46:29 - INFO - __main__ - Step 107636: {'lr': 9.445672495944899e-05, 'samples': 20666112, 'steps': 107635, 'loss/train': 1.4514343738555908} 08/31/2021 08:46:30 - INFO - __main__ - Step 107637: {'lr': 9.44525704520397e-05, 'samples': 20666304, 'steps': 107636, 'loss/train': 1.1375287771224976} 08/31/2021 08:46:31 - INFO - __main__ - Step 107638: {'lr': 9.444841601471771e-05, 'samples': 20666496, 'steps': 107637, 'loss/train': 1.3542051315307617} 08/31/2021 08:46:32 - INFO - __main__ - Step 107639: {'lr': 9.444426164748485e-05, 'samples': 20666688, 'steps': 107638, 'loss/train': 1.0265380144119263} 08/31/2021 08:46:32 - INFO - __main__ - Step 107640: {'lr': 9.444010735034304e-05, 'samples': 20666880, 'steps': 107639, 'loss/train': 1.1175023317337036} 08/31/2021 08:46:32 - INFO - __main__ - Step 107641: {'lr': 9.443595312329406e-05, 'samples': 20667072, 'steps': 107640, 'loss/train': 0.8010900020599365} 08/31/2021 08:46:33 - INFO - __main__ - Step 107642: {'lr': 9.443179896633988e-05, 'samples': 20667264, 'steps': 107641, 'loss/train': 0.9120587706565857} 08/31/2021 08:46:33 - INFO - __main__ - Step 107643: {'lr': 9.442764487948233e-05, 'samples': 20667456, 'steps': 107642, 'loss/train': 1.5131670236587524} 08/31/2021 08:46:35 - INFO - __main__ - Step 107644: {'lr': 9.442349086272334e-05, 'samples': 20667648, 'steps': 107643, 'loss/train': 1.0872924327850342} 08/31/2021 08:46:35 - INFO - __main__ - Step 107645: {'lr': 9.441933691606466e-05, 'samples': 20667840, 'steps': 107644, 'loss/train': 0.7296358346939087} 08/31/2021 08:46:35 - INFO - __main__ - Step 107646: {'lr': 9.441518303950822e-05, 'samples': 20668032, 'steps': 107645, 'loss/train': 1.1492197513580322} 08/31/2021 08:46:36 - INFO - __main__ - Step 107647: {'lr': 9.441102923305589e-05, 'samples': 20668224, 'steps': 107646, 'loss/train': 0.8436548709869385} 08/31/2021 08:46:36 - INFO - __main__ - Step 107648: {'lr': 9.440687549670957e-05, 'samples': 20668416, 'steps': 107647, 'loss/train': 1.388114333152771} 08/31/2021 08:46:38 - INFO - __main__ - Step 107649: {'lr': 9.440272183047111e-05, 'samples': 20668608, 'steps': 107648, 'loss/train': 1.512404441833496} 08/31/2021 08:46:38 - INFO - __main__ - Step 107650: {'lr': 9.439856823434236e-05, 'samples': 20668800, 'steps': 107649, 'loss/train': 0.9874385595321655} 08/31/2021 08:46:39 - INFO - __main__ - Step 107651: {'lr': 9.439441470832525e-05, 'samples': 20668992, 'steps': 107650, 'loss/train': 1.4650733470916748} 08/31/2021 08:46:39 - INFO - __main__ - Step 107652: {'lr': 9.439026125242156e-05, 'samples': 20669184, 'steps': 107651, 'loss/train': 0.5260549783706665} 08/31/2021 08:46:39 - INFO - __main__ - Step 107653: {'lr': 9.438610786663327e-05, 'samples': 20669376, 'steps': 107652, 'loss/train': 0.9609938263893127} 08/31/2021 08:46:41 - INFO - __main__ - Step 107654: {'lr': 9.438195455096216e-05, 'samples': 20669568, 'steps': 107653, 'loss/train': 1.4456266164779663} 08/31/2021 08:46:41 - INFO - __main__ - Step 107655: {'lr': 9.437780130541015e-05, 'samples': 20669760, 'steps': 107654, 'loss/train': 1.1317143440246582} 08/31/2021 08:46:42 - INFO - __main__ - Step 107656: {'lr': 9.437364812997912e-05, 'samples': 20669952, 'steps': 107655, 'loss/train': 1.8268024921417236} 08/31/2021 08:46:42 - INFO - __main__ - Step 107657: {'lr': 9.436949502467101e-05, 'samples': 20670144, 'steps': 107656, 'loss/train': 1.519318699836731} 08/31/2021 08:46:42 - INFO - __main__ - Step 107658: {'lr': 9.436534198948752e-05, 'samples': 20670336, 'steps': 107657, 'loss/train': 1.8164833784103394} 08/31/2021 08:46:45 - INFO - __main__ - Step 107659: {'lr': 9.436118902443059e-05, 'samples': 20670528, 'steps': 107658, 'loss/train': 1.2766573429107666} 08/31/2021 08:46:45 - INFO - __main__ - Step 107660: {'lr': 9.435703612950208e-05, 'samples': 20670720, 'steps': 107659, 'loss/train': 1.5453993082046509} 08/31/2021 08:46:46 - INFO - __main__ - Step 107661: {'lr': 9.435288330470392e-05, 'samples': 20670912, 'steps': 107660, 'loss/train': 1.0432324409484863} 08/31/2021 08:46:46 - INFO - __main__ - Step 107662: {'lr': 9.434873055003796e-05, 'samples': 20671104, 'steps': 107661, 'loss/train': 0.6803992986679077} 08/31/2021 08:46:46 - INFO - __main__ - Step 107663: {'lr': 9.434457786550605e-05, 'samples': 20671296, 'steps': 107662, 'loss/train': 0.9742295742034912} 08/31/2021 08:46:48 - INFO - __main__ - Step 107664: {'lr': 9.434042525111006e-05, 'samples': 20671488, 'steps': 107663, 'loss/train': 1.1439129114151} 08/31/2021 08:46:49 - INFO - __main__ - Step 107665: {'lr': 9.433627270685185e-05, 'samples': 20671680, 'steps': 107664, 'loss/train': 1.4106978178024292} 08/31/2021 08:46:49 - INFO - __main__ - Step 107666: {'lr': 9.433212023273336e-05, 'samples': 20671872, 'steps': 107665, 'loss/train': 1.2303518056869507} 08/31/2021 08:46:49 - INFO - __main__ - Step 107667: {'lr': 9.432796782875638e-05, 'samples': 20672064, 'steps': 107666, 'loss/train': 0.36974114179611206} 08/31/2021 08:46:50 - INFO - __main__ - Step 107668: {'lr': 9.432381549492284e-05, 'samples': 20672256, 'steps': 107667, 'loss/train': 1.3286123275756836} 08/31/2021 08:46:50 - INFO - __main__ - Step 107669: {'lr': 9.431966323123458e-05, 'samples': 20672448, 'steps': 107668, 'loss/train': 5.3520050048828125} 08/31/2021 08:46:50 - INFO - __main__ - Step 107670: {'lr': 9.431551103769348e-05, 'samples': 20672640, 'steps': 107669, 'loss/train': 0.9717222452163696} 08/31/2021 08:46:52 - INFO - __main__ - Step 107671: {'lr': 9.431135891430148e-05, 'samples': 20672832, 'steps': 107670, 'loss/train': 1.5227047204971313} 08/31/2021 08:46:52 - INFO - __main__ - Step 107672: {'lr': 9.430720686106031e-05, 'samples': 20673024, 'steps': 107671, 'loss/train': 1.7069329023361206} 08/31/2021 08:46:53 - INFO - __main__ - Step 107673: {'lr': 9.430305487797191e-05, 'samples': 20673216, 'steps': 107672, 'loss/train': 1.2501344680786133} 08/31/2021 08:46:53 - INFO - __main__ - Step 107674: {'lr': 9.429890296503815e-05, 'samples': 20673408, 'steps': 107673, 'loss/train': 0.9401653409004211} 08/31/2021 08:46:54 - INFO - __main__ - Step 107675: {'lr': 9.429475112226088e-05, 'samples': 20673600, 'steps': 107674, 'loss/train': 0.6797422170639038} 08/31/2021 08:46:55 - INFO - __main__ - Step 107676: {'lr': 9.429059934964201e-05, 'samples': 20673792, 'steps': 107675, 'loss/train': 0.38235974311828613} 08/31/2021 08:46:56 - INFO - __main__ - Step 107677: {'lr': 9.428644764718338e-05, 'samples': 20673984, 'steps': 107676, 'loss/train': 1.3110421895980835} 08/31/2021 08:46:56 - INFO - __main__ - Step 107678: {'lr': 9.428229601488691e-05, 'samples': 20674176, 'steps': 107677, 'loss/train': 1.3444782495498657} 08/31/2021 08:46:57 - INFO - __main__ - Step 107679: {'lr': 9.42781444527544e-05, 'samples': 20674368, 'steps': 107678, 'loss/train': 1.0640329122543335} 08/31/2021 08:46:57 - INFO - __main__ - Step 107680: {'lr': 9.427399296078775e-05, 'samples': 20674560, 'steps': 107679, 'loss/train': 0.991499125957489} 08/31/2021 08:46:58 - INFO - __main__ - Step 107681: {'lr': 9.426984153898887e-05, 'samples': 20674752, 'steps': 107680, 'loss/train': 0.05704557150602341} 08/31/2021 08:46:59 - INFO - __main__ - Step 107682: {'lr': 9.426569018735958e-05, 'samples': 20674944, 'steps': 107681, 'loss/train': 1.6790798902511597} 08/31/2021 08:46:59 - INFO - __main__ - Step 107683: {'lr': 9.426153890590175e-05, 'samples': 20675136, 'steps': 107682, 'loss/train': 1.0357136726379395} 08/31/2021 08:47:00 - INFO - __main__ - Step 107684: {'lr': 9.425738769461739e-05, 'samples': 20675328, 'steps': 107683, 'loss/train': 1.9330449104309082} 08/31/2021 08:47:00 - INFO - __main__ - Step 107685: {'lr': 9.425323655350813e-05, 'samples': 20675520, 'steps': 107684, 'loss/train': 0.7378239035606384} 08/31/2021 08:47:00 - INFO - __main__ - Step 107686: {'lr': 9.424908548257596e-05, 'samples': 20675712, 'steps': 107685, 'loss/train': 1.256769061088562} 08/31/2021 08:47:02 - INFO - __main__ - Step 107687: {'lr': 9.424493448182275e-05, 'samples': 20675904, 'steps': 107686, 'loss/train': 1.5943429470062256} 08/31/2021 08:47:02 - INFO - __main__ - Step 107688: {'lr': 9.424078355125038e-05, 'samples': 20676096, 'steps': 107687, 'loss/train': 1.0437735319137573} 08/31/2021 08:47:03 - INFO - __main__ - Step 107689: {'lr': 9.423663269086072e-05, 'samples': 20676288, 'steps': 107688, 'loss/train': 1.4787527322769165} 08/31/2021 08:47:03 - INFO - __main__ - Step 107690: {'lr': 9.423248190065561e-05, 'samples': 20676480, 'steps': 107689, 'loss/train': 1.1343556642532349} 08/31/2021 08:47:03 - INFO - __main__ - Step 107691: {'lr': 9.422833118063694e-05, 'samples': 20676672, 'steps': 107690, 'loss/train': 1.0072784423828125} 08/31/2021 08:47:05 - INFO - __main__ - Step 107692: {'lr': 9.422418053080658e-05, 'samples': 20676864, 'steps': 107691, 'loss/train': 1.4229565858840942} 08/31/2021 08:47:05 - INFO - __main__ - Step 107693: {'lr': 9.422002995116641e-05, 'samples': 20677056, 'steps': 107692, 'loss/train': 0.5312652587890625} 08/31/2021 08:47:06 - INFO - __main__ - Step 107694: {'lr': 9.421587944171828e-05, 'samples': 20677248, 'steps': 107693, 'loss/train': 1.3999598026275635} 08/31/2021 08:47:06 - INFO - __main__ - Step 107695: {'lr': 9.421172900246408e-05, 'samples': 20677440, 'steps': 107694, 'loss/train': 1.2772107124328613} 08/31/2021 08:47:06 - INFO - __main__ - Step 107696: {'lr': 9.420757863340568e-05, 'samples': 20677632, 'steps': 107695, 'loss/train': 0.1426583081483841} 08/31/2021 08:47:08 - INFO - __main__ - Step 107697: {'lr': 9.420342833454492e-05, 'samples': 20677824, 'steps': 107696, 'loss/train': 0.4725174009799957} 08/31/2021 08:47:08 - INFO - __main__ - Step 107698: {'lr': 9.41992781058838e-05, 'samples': 20678016, 'steps': 107697, 'loss/train': 0.9779374599456787} 08/31/2021 08:47:09 - INFO - __main__ - Step 107699: {'lr': 9.419512794742397e-05, 'samples': 20678208, 'steps': 107698, 'loss/train': 1.248079776763916} 08/31/2021 08:47:09 - INFO - __main__ - Step 107700: {'lr': 9.419097785916741e-05, 'samples': 20678400, 'steps': 107699, 'loss/train': 1.0784558057785034} 08/31/2021 08:47:09 - INFO - __main__ - Step 107701: {'lr': 9.418682784111601e-05, 'samples': 20678592, 'steps': 107700, 'loss/train': 1.6056169271469116} 08/31/2021 08:47:11 - INFO - __main__ - Step 107702: {'lr': 9.418267789327161e-05, 'samples': 20678784, 'steps': 107701, 'loss/train': 0.056700438261032104} 08/31/2021 08:47:12 - INFO - __main__ - Step 107703: {'lr': 9.417852801563612e-05, 'samples': 20678976, 'steps': 107702, 'loss/train': 0.22442539036273956} 08/31/2021 08:47:12 - INFO - __main__ - Step 107704: {'lr': 9.417437820821134e-05, 'samples': 20679168, 'steps': 107703, 'loss/train': 1.1333284378051758} 08/31/2021 08:47:12 - INFO - __main__ - Step 107705: {'lr': 9.417022847099921e-05, 'samples': 20679360, 'steps': 107704, 'loss/train': 1.2903940677642822} 08/31/2021 08:47:13 - INFO - __main__ - Step 107706: {'lr': 9.416607880400155e-05, 'samples': 20679552, 'steps': 107705, 'loss/train': 1.3171578645706177} 08/31/2021 08:47:13 - INFO - __main__ - Step 107707: {'lr': 9.416192920722025e-05, 'samples': 20679744, 'steps': 107706, 'loss/train': 1.595720648765564} 08/31/2021 08:47:15 - INFO - __main__ - Step 107708: {'lr': 9.41577796806572e-05, 'samples': 20679936, 'steps': 107707, 'loss/train': 0.9194750189781189} 08/31/2021 08:47:15 - INFO - __main__ - Step 107709: {'lr': 9.415363022431423e-05, 'samples': 20680128, 'steps': 107708, 'loss/train': 0.881084680557251} 08/31/2021 08:47:16 - INFO - __main__ - Step 107710: {'lr': 9.414948083819325e-05, 'samples': 20680320, 'steps': 107709, 'loss/train': 1.3621211051940918} 08/31/2021 08:47:16 - INFO - __main__ - Step 107711: {'lr': 9.414533152229617e-05, 'samples': 20680512, 'steps': 107710, 'loss/train': 1.3985596895217896} 08/31/2021 08:47:16 - INFO - __main__ - Step 107712: {'lr': 9.414118227662472e-05, 'samples': 20680704, 'steps': 107711, 'loss/train': 1.3300907611846924} 08/31/2021 08:47:18 - INFO - __main__ - Step 107713: {'lr': 9.413703310118085e-05, 'samples': 20680896, 'steps': 107712, 'loss/train': 0.33118167519569397} 08/31/2021 08:47:18 - INFO - __main__ - Step 107714: {'lr': 9.413288399596642e-05, 'samples': 20681088, 'steps': 107713, 'loss/train': 1.4824328422546387} 08/31/2021 08:47:19 - INFO - __main__ - Step 107715: {'lr': 9.412873496098334e-05, 'samples': 20681280, 'steps': 107714, 'loss/train': 1.3258929252624512} 08/31/2021 08:47:19 - INFO - __main__ - Step 107716: {'lr': 9.412458599623341e-05, 'samples': 20681472, 'steps': 107715, 'loss/train': 1.0019028186798096} 08/31/2021 08:47:19 - INFO - __main__ - Step 107717: {'lr': 9.412043710171855e-05, 'samples': 20681664, 'steps': 107716, 'loss/train': 1.201453447341919} 08/31/2021 08:47:21 - INFO - __main__ - Step 107718: {'lr': 9.411628827744062e-05, 'samples': 20681856, 'steps': 107717, 'loss/train': 1.086041808128357} 08/31/2021 08:47:22 - INFO - __main__ - Step 107719: {'lr': 9.411213952340147e-05, 'samples': 20682048, 'steps': 107718, 'loss/train': 1.409443736076355} 08/31/2021 08:47:22 - INFO - __main__ - Step 107720: {'lr': 9.4107990839603e-05, 'samples': 20682240, 'steps': 107719, 'loss/train': 1.5422863960266113} 08/31/2021 08:47:22 - INFO - __main__ - Step 107721: {'lr': 9.410384222604706e-05, 'samples': 20682432, 'steps': 107720, 'loss/train': 1.7478396892547607} 08/31/2021 08:47:23 - INFO - __main__ - Step 107722: {'lr': 9.409969368273552e-05, 'samples': 20682624, 'steps': 107721, 'loss/train': 0.8839545845985413} 08/31/2021 08:47:25 - INFO - __main__ - Step 107723: {'lr': 9.409554520967026e-05, 'samples': 20682816, 'steps': 107722, 'loss/train': 1.8169282674789429} 08/31/2021 08:47:25 - INFO - __main__ - Step 107724: {'lr': 9.409139680685322e-05, 'samples': 20683008, 'steps': 107723, 'loss/train': 0.7889143228530884} 08/31/2021 08:47:26 - INFO - __main__ - Step 107725: {'lr': 9.408724847428612e-05, 'samples': 20683200, 'steps': 107724, 'loss/train': 0.10767673701047897} 08/31/2021 08:47:26 - INFO - __main__ - Step 107726: {'lr': 9.40831002119709e-05, 'samples': 20683392, 'steps': 107725, 'loss/train': 0.8262044191360474} 08/31/2021 08:47:26 - INFO - __main__ - Step 107727: {'lr': 9.40789520199094e-05, 'samples': 20683584, 'steps': 107726, 'loss/train': 0.04380156099796295} 08/31/2021 08:47:28 - INFO - __main__ - Step 107728: {'lr': 9.407480389810356e-05, 'samples': 20683776, 'steps': 107727, 'loss/train': 0.698835015296936} 08/31/2021 08:47:28 - INFO - __main__ - Step 107729: {'lr': 9.407065584655516e-05, 'samples': 20683968, 'steps': 107728, 'loss/train': 0.8959972262382507} 08/31/2021 08:47:29 - INFO - __main__ - Step 107730: {'lr': 9.406650786526613e-05, 'samples': 20684160, 'steps': 107729, 'loss/train': 1.1828664541244507} 08/31/2021 08:47:29 - INFO - __main__ - Step 107731: {'lr': 9.406235995423834e-05, 'samples': 20684352, 'steps': 107730, 'loss/train': 1.8745307922363281} 08/31/2021 08:47:29 - INFO - __main__ - Step 107732: {'lr': 9.405821211347365e-05, 'samples': 20684544, 'steps': 107731, 'loss/train': 1.550337314605713} 08/31/2021 08:47:30 - INFO - __main__ - Step 107733: {'lr': 9.405406434297389e-05, 'samples': 20684736, 'steps': 107732, 'loss/train': 1.578768253326416} 08/31/2021 08:47:31 - INFO - __main__ - Step 107734: {'lr': 9.404991664274098e-05, 'samples': 20684928, 'steps': 107733, 'loss/train': 1.2076784372329712} 08/31/2021 08:47:32 - INFO - __main__ - Step 107735: {'lr': 9.404576901277678e-05, 'samples': 20685120, 'steps': 107734, 'loss/train': 0.8235082030296326} 08/31/2021 08:47:32 - INFO - __main__ - Step 107736: {'lr': 9.404162145308314e-05, 'samples': 20685312, 'steps': 107735, 'loss/train': 1.4618189334869385} 08/31/2021 08:47:32 - INFO - __main__ - Step 107737: {'lr': 9.403747396366197e-05, 'samples': 20685504, 'steps': 107736, 'loss/train': 1.3594331741333008} 08/31/2021 08:47:33 - INFO - __main__ - Step 107738: {'lr': 9.403332654451515e-05, 'samples': 20685696, 'steps': 107737, 'loss/train': 1.2924489974975586} 08/31/2021 08:47:34 - INFO - __main__ - Step 107739: {'lr': 9.402917919564444e-05, 'samples': 20685888, 'steps': 107738, 'loss/train': 0.8706616163253784} 08/31/2021 08:47:34 - INFO - __main__ - Step 107740: {'lr': 9.402503191705177e-05, 'samples': 20686080, 'steps': 107739, 'loss/train': 1.3134896755218506} 08/31/2021 08:47:35 - INFO - __main__ - Step 107741: {'lr': 9.402088470873902e-05, 'samples': 20686272, 'steps': 107740, 'loss/train': 0.9370191693305969} 08/31/2021 08:47:35 - INFO - __main__ - Step 107742: {'lr': 9.401673757070806e-05, 'samples': 20686464, 'steps': 107741, 'loss/train': 1.8390135765075684} 08/31/2021 08:47:36 - INFO - __main__ - Step 107743: {'lr': 9.401259050296073e-05, 'samples': 20686656, 'steps': 107742, 'loss/train': 1.3698525428771973} 08/31/2021 08:47:37 - INFO - __main__ - Step 107744: {'lr': 9.400844350549893e-05, 'samples': 20686848, 'steps': 107743, 'loss/train': 1.007261872291565} 08/31/2021 08:47:37 - INFO - __main__ - Step 107745: {'lr': 9.400429657832451e-05, 'samples': 20687040, 'steps': 107744, 'loss/train': 1.109729290008545} 08/31/2021 08:47:38 - INFO - __main__ - Step 107746: {'lr': 9.400014972143936e-05, 'samples': 20687232, 'steps': 107745, 'loss/train': 1.3889905214309692} 08/31/2021 08:47:38 - INFO - __main__ - Step 107747: {'lr': 9.399600293484533e-05, 'samples': 20687424, 'steps': 107746, 'loss/train': 0.9224821329116821} 08/31/2021 08:47:38 - INFO - __main__ - Step 107748: {'lr': 9.399185621854428e-05, 'samples': 20687616, 'steps': 107747, 'loss/train': 1.1273882389068604} 08/31/2021 08:47:40 - INFO - __main__ - Step 107749: {'lr': 9.39877095725381e-05, 'samples': 20687808, 'steps': 107748, 'loss/train': 1.3315887451171875} 08/31/2021 08:47:40 - INFO - __main__ - Step 107750: {'lr': 9.398356299682875e-05, 'samples': 20688000, 'steps': 107749, 'loss/train': 1.251086950302124} 08/31/2021 08:47:41 - INFO - __main__ - Step 107751: {'lr': 9.397941649141792e-05, 'samples': 20688192, 'steps': 107750, 'loss/train': 1.6158456802368164} 08/31/2021 08:47:41 - INFO - __main__ - Step 107752: {'lr': 9.397527005630754e-05, 'samples': 20688384, 'steps': 107751, 'loss/train': 1.6675785779953003} 08/31/2021 08:47:42 - INFO - __main__ - Step 107753: {'lr': 9.397112369149949e-05, 'samples': 20688576, 'steps': 107752, 'loss/train': 0.9063429236412048} 08/31/2021 08:47:43 - INFO - __main__ - Step 107754: {'lr': 9.396697739699567e-05, 'samples': 20688768, 'steps': 107753, 'loss/train': 0.8269808292388916} 08/31/2021 08:47:44 - INFO - __main__ - Step 107755: {'lr': 9.396283117279788e-05, 'samples': 20688960, 'steps': 107754, 'loss/train': 1.6895700693130493} 08/31/2021 08:47:44 - INFO - __main__ - Step 107756: {'lr': 9.395868501890806e-05, 'samples': 20689152, 'steps': 107755, 'loss/train': 1.1136441230773926} 08/31/2021 08:47:44 - INFO - __main__ - Step 107757: {'lr': 9.395453893532805e-05, 'samples': 20689344, 'steps': 107756, 'loss/train': 1.0913176536560059} 08/31/2021 08:47:45 - INFO - __main__ - Step 107758: {'lr': 9.39503929220597e-05, 'samples': 20689536, 'steps': 107757, 'loss/train': 1.4170200824737549} 08/31/2021 08:47:46 - INFO - __main__ - Step 107759: {'lr': 9.394624697910492e-05, 'samples': 20689728, 'steps': 107758, 'loss/train': 0.8984721899032593} 08/31/2021 08:47:46 - INFO - __main__ - Step 107760: {'lr': 9.394210110646553e-05, 'samples': 20689920, 'steps': 107759, 'loss/train': 0.2954542934894562} 08/31/2021 08:47:47 - INFO - __main__ - Step 107761: {'lr': 9.393795530414354e-05, 'samples': 20690112, 'steps': 107760, 'loss/train': 1.4695310592651367} 08/31/2021 08:47:47 - INFO - __main__ - Step 107762: {'lr': 9.393380957214056e-05, 'samples': 20690304, 'steps': 107761, 'loss/train': 1.1778640747070312} 08/31/2021 08:47:48 - INFO - __main__ - Step 107763: {'lr': 9.392966391045862e-05, 'samples': 20690496, 'steps': 107762, 'loss/train': 0.9056761860847473} 08/31/2021 08:47:49 - INFO - __main__ - Step 107764: {'lr': 9.39255183190996e-05, 'samples': 20690688, 'steps': 107763, 'loss/train': 0.9850396513938904} 08/31/2021 08:47:49 - INFO - __main__ - Step 107765: {'lr': 9.392137279806528e-05, 'samples': 20690880, 'steps': 107764, 'loss/train': 1.236459493637085} 08/31/2021 08:47:50 - INFO - __main__ - Step 107766: {'lr': 9.39172273473576e-05, 'samples': 20691072, 'steps': 107765, 'loss/train': 1.1762266159057617} 08/31/2021 08:47:50 - INFO - __main__ - Step 107767: {'lr': 9.391308196697843e-05, 'samples': 20691264, 'steps': 107766, 'loss/train': 0.7288626432418823} 08/31/2021 08:47:50 - INFO - __main__ - Step 107768: {'lr': 9.39089366569296e-05, 'samples': 20691456, 'steps': 107767, 'loss/train': 0.8448583483695984} 08/31/2021 08:47:53 - INFO - __main__ - Step 107769: {'lr': 9.3904791417213e-05, 'samples': 20691648, 'steps': 107768, 'loss/train': 0.919365644454956} 08/31/2021 08:47:53 - INFO - __main__ - Step 107770: {'lr': 9.390064624783048e-05, 'samples': 20691840, 'steps': 107769, 'loss/train': 1.0124634504318237} 08/31/2021 08:47:53 - INFO - __main__ - Step 107771: {'lr': 9.389650114878393e-05, 'samples': 20692032, 'steps': 107770, 'loss/train': 0.772358775138855} 08/31/2021 08:47:54 - INFO - __main__ - Step 107772: {'lr': 9.38923561200753e-05, 'samples': 20692224, 'steps': 107771, 'loss/train': 0.5229784846305847} 08/31/2021 08:47:54 - INFO - __main__ - Step 107773: {'lr': 9.388821116170626e-05, 'samples': 20692416, 'steps': 107772, 'loss/train': 0.16474802792072296} 08/31/2021 08:47:54 - INFO - __main__ - Step 107774: {'lr': 9.388406627367879e-05, 'samples': 20692608, 'steps': 107773, 'loss/train': 1.7164446115493774} 08/31/2021 08:47:56 - INFO - __main__ - Step 107775: {'lr': 9.387992145599477e-05, 'samples': 20692800, 'steps': 107774, 'loss/train': 1.1894460916519165} 08/31/2021 08:47:56 - INFO - __main__ - Step 107776: {'lr': 9.387577670865601e-05, 'samples': 20692992, 'steps': 107775, 'loss/train': 0.7201740145683289} 08/31/2021 08:47:57 - INFO - __main__ - Step 107777: {'lr': 9.387163203166445e-05, 'samples': 20693184, 'steps': 107776, 'loss/train': 1.4020196199417114} 08/31/2021 08:47:57 - INFO - __main__ - Step 107778: {'lr': 9.386748742502191e-05, 'samples': 20693376, 'steps': 107777, 'loss/train': 1.3928866386413574} 08/31/2021 08:47:57 - INFO - __main__ - Step 107779: {'lr': 9.386334288873027e-05, 'samples': 20693568, 'steps': 107778, 'loss/train': 1.0273032188415527} 08/31/2021 08:47:59 - INFO - __main__ - Step 107780: {'lr': 9.385919842279142e-05, 'samples': 20693760, 'steps': 107779, 'loss/train': 0.8638908267021179} 08/31/2021 08:47:59 - INFO - __main__ - Step 107781: {'lr': 9.385505402720718e-05, 'samples': 20693952, 'steps': 107780, 'loss/train': 0.4562666118144989} 08/31/2021 08:48:00 - INFO - __main__ - Step 107782: {'lr': 9.385090970197945e-05, 'samples': 20694144, 'steps': 107781, 'loss/train': 0.7733129858970642} 08/31/2021 08:48:00 - INFO - __main__ - Step 107783: {'lr': 9.384676544711018e-05, 'samples': 20694336, 'steps': 107782, 'loss/train': 1.205531120300293} 08/31/2021 08:48:00 - INFO - __main__ - Step 107784: {'lr': 9.384262126260107e-05, 'samples': 20694528, 'steps': 107783, 'loss/train': 0.8629662394523621} 08/31/2021 08:48:02 - INFO - __main__ - Step 107785: {'lr': 9.383847714845403e-05, 'samples': 20694720, 'steps': 107784, 'loss/train': 1.2607396841049194} 08/31/2021 08:48:02 - INFO - __main__ - Step 107786: {'lr': 9.383433310467099e-05, 'samples': 20694912, 'steps': 107785, 'loss/train': 1.3491828441619873} 08/31/2021 08:48:03 - INFO - __main__ - Step 107787: {'lr': 9.383018913125379e-05, 'samples': 20695104, 'steps': 107786, 'loss/train': 1.2158641815185547} 08/31/2021 08:48:03 - INFO - __main__ - Step 107788: {'lr': 9.382604522820429e-05, 'samples': 20695296, 'steps': 107787, 'loss/train': 1.0885872840881348} 08/31/2021 08:48:03 - INFO - __main__ - Step 107789: {'lr': 9.382190139552438e-05, 'samples': 20695488, 'steps': 107788, 'loss/train': 1.3837279081344604} 08/31/2021 08:48:05 - INFO - __main__ - Step 107790: {'lr': 9.38177576332159e-05, 'samples': 20695680, 'steps': 107789, 'loss/train': 0.5243405699729919} 08/31/2021 08:48:05 - INFO - __main__ - Step 107791: {'lr': 9.381361394128071e-05, 'samples': 20695872, 'steps': 107790, 'loss/train': 1.5268616676330566} 08/31/2021 08:48:06 - INFO - __main__ - Step 107792: {'lr': 9.380947031972073e-05, 'samples': 20696064, 'steps': 107791, 'loss/train': 0.7317495942115784} 08/31/2021 08:48:06 - INFO - __main__ - Step 107793: {'lr': 9.380532676853775e-05, 'samples': 20696256, 'steps': 107792, 'loss/train': 1.214015007019043} 08/31/2021 08:48:06 - INFO - __main__ - Step 107794: {'lr': 9.380118328773382e-05, 'samples': 20696448, 'steps': 107793, 'loss/train': 0.9991066455841064} 08/31/2021 08:48:08 - INFO - __main__ - Step 107795: {'lr': 9.379703987731053e-05, 'samples': 20696640, 'steps': 107794, 'loss/train': 1.459567904472351} 08/31/2021 08:48:09 - INFO - __main__ - Step 107796: {'lr': 9.37928965372699e-05, 'samples': 20696832, 'steps': 107795, 'loss/train': 1.039053201675415} 08/31/2021 08:48:09 - INFO - __main__ - Step 107797: {'lr': 9.37887532676138e-05, 'samples': 20697024, 'steps': 107796, 'loss/train': 0.5760068297386169} 08/31/2021 08:48:09 - INFO - __main__ - Step 107798: {'lr': 9.378461006834408e-05, 'samples': 20697216, 'steps': 107797, 'loss/train': 0.8526011109352112} 08/31/2021 08:48:10 - INFO - __main__ - Step 107799: {'lr': 9.378046693946257e-05, 'samples': 20697408, 'steps': 107798, 'loss/train': 1.583202838897705} 08/31/2021 08:48:11 - INFO - __main__ - Step 107800: {'lr': 9.377632388097119e-05, 'samples': 20697600, 'steps': 107799, 'loss/train': 0.8252288699150085} 08/31/2021 08:48:12 - INFO - __main__ - Step 107801: {'lr': 9.377218089287179e-05, 'samples': 20697792, 'steps': 107800, 'loss/train': 1.467714786529541} 08/31/2021 08:48:12 - INFO - __main__ - Step 107802: {'lr': 9.376803797516623e-05, 'samples': 20697984, 'steps': 107801, 'loss/train': 2.3061320781707764} 08/31/2021 08:48:12 - INFO - __main__ - Step 107803: {'lr': 9.376389512785638e-05, 'samples': 20698176, 'steps': 107802, 'loss/train': 1.254144310951233} 08/31/2021 08:48:13 - INFO - __main__ - Step 107804: {'lr': 9.375975235094411e-05, 'samples': 20698368, 'steps': 107803, 'loss/train': 0.5405426025390625} 08/31/2021 08:48:13 - INFO - __main__ - Step 107805: {'lr': 9.375560964443136e-05, 'samples': 20698560, 'steps': 107804, 'loss/train': 1.3722584247589111} 08/31/2021 08:48:14 - INFO - __main__ - Step 107806: {'lr': 9.375146700831985e-05, 'samples': 20698752, 'steps': 107805, 'loss/train': 1.1679391860961914} 08/31/2021 08:48:15 - INFO - __main__ - Step 107807: {'lr': 9.37473244426115e-05, 'samples': 20698944, 'steps': 107806, 'loss/train': 2.5800445079803467} 08/31/2021 08:48:15 - INFO - __main__ - Step 107808: {'lr': 9.374318194730821e-05, 'samples': 20699136, 'steps': 107807, 'loss/train': 1.4840285778045654} 08/31/2021 08:48:16 - INFO - __main__ - Step 107809: {'lr': 9.373903952241184e-05, 'samples': 20699328, 'steps': 107808, 'loss/train': 1.3140795230865479} 08/31/2021 08:48:16 - INFO - __main__ - Step 107810: {'lr': 9.373489716792422e-05, 'samples': 20699520, 'steps': 107809, 'loss/train': 1.5996415615081787} 08/31/2021 08:48:17 - INFO - __main__ - Step 107811: {'lr': 9.373075488384727e-05, 'samples': 20699712, 'steps': 107810, 'loss/train': 1.3944196701049805} 08/31/2021 08:48:18 - INFO - __main__ - Step 107812: {'lr': 9.372661267018282e-05, 'samples': 20699904, 'steps': 107811, 'loss/train': 0.06414306908845901} 08/31/2021 08:48:18 - INFO - __main__ - Step 107813: {'lr': 9.372247052693275e-05, 'samples': 20700096, 'steps': 107812, 'loss/train': 1.7628507614135742} 08/31/2021 08:48:19 - INFO - __main__ - Step 107814: {'lr': 9.371832845409892e-05, 'samples': 20700288, 'steps': 107813, 'loss/train': 2.1535215377807617} 08/31/2021 08:48:19 - INFO - __main__ - Step 107815: {'lr': 9.37141864516832e-05, 'samples': 20700480, 'steps': 107814, 'loss/train': 1.1392815113067627} 08/31/2021 08:48:21 - INFO - __main__ - Step 107816: {'lr': 9.371004451968745e-05, 'samples': 20700672, 'steps': 107815, 'loss/train': 1.6096389293670654} 08/31/2021 08:48:21 - INFO - __main__ - Step 107817: {'lr': 9.370590265811355e-05, 'samples': 20700864, 'steps': 107816, 'loss/train': 0.9401848912239075} 08/31/2021 08:48:21 - INFO - __main__ - Step 107818: {'lr': 9.370176086696336e-05, 'samples': 20701056, 'steps': 107817, 'loss/train': 1.3011225461959839} 08/31/2021 08:48:22 - INFO - __main__ - Step 107819: {'lr': 9.369761914623884e-05, 'samples': 20701248, 'steps': 107818, 'loss/train': 0.5792026519775391} 08/31/2021 08:48:22 - INFO - __main__ - Step 107820: {'lr': 9.369347749594164e-05, 'samples': 20701440, 'steps': 107819, 'loss/train': 0.2865196466445923} 08/31/2021 08:48:24 - INFO - __main__ - Step 107821: {'lr': 9.368933591607378e-05, 'samples': 20701632, 'steps': 107820, 'loss/train': 1.4656121730804443} 08/31/2021 08:48:24 - INFO - __main__ - Step 107822: {'lr': 9.368519440663709e-05, 'samples': 20701824, 'steps': 107821, 'loss/train': 0.8697898387908936} 08/31/2021 08:48:25 - INFO - __main__ - Step 107823: {'lr': 9.368105296763344e-05, 'samples': 20702016, 'steps': 107822, 'loss/train': 1.086666226387024} 08/31/2021 08:48:25 - INFO - __main__ - Step 107824: {'lr': 9.367691159906466e-05, 'samples': 20702208, 'steps': 107823, 'loss/train': 0.7178633213043213} 08/31/2021 08:48:25 - INFO - __main__ - Step 107825: {'lr': 9.367277030093268e-05, 'samples': 20702400, 'steps': 107824, 'loss/train': 1.0553125143051147} 08/31/2021 08:48:26 - INFO - __main__ - Step 107826: {'lr': 9.366862907323934e-05, 'samples': 20702592, 'steps': 107825, 'loss/train': 0.9694816470146179} 08/31/2021 08:48:28 - INFO - __main__ - Step 107827: {'lr': 9.36644879159865e-05, 'samples': 20702784, 'steps': 107826, 'loss/train': 0.09659680724143982} 08/31/2021 08:48:28 - INFO - __main__ - Step 107828: {'lr': 9.366034682917604e-05, 'samples': 20702976, 'steps': 107827, 'loss/train': 0.494510293006897} 08/31/2021 08:48:29 - INFO - __main__ - Step 107829: {'lr': 9.365620581280979e-05, 'samples': 20703168, 'steps': 107828, 'loss/train': 1.4670226573944092} 08/31/2021 08:48:29 - INFO - __main__ - Step 107830: {'lr': 9.365206486688965e-05, 'samples': 20703360, 'steps': 107829, 'loss/train': 1.513110876083374} 08/31/2021 08:48:29 - INFO - __main__ - Step 107831: {'lr': 9.36479239914175e-05, 'samples': 20703552, 'steps': 107830, 'loss/train': 1.3299955129623413} 08/31/2021 08:48:31 - INFO - __main__ - Step 107832: {'lr': 9.364378318639524e-05, 'samples': 20703744, 'steps': 107831, 'loss/train': 1.969864845275879} 08/31/2021 08:48:31 - INFO - __main__ - Step 107833: {'lr': 9.36396424518246e-05, 'samples': 20703936, 'steps': 107832, 'loss/train': 1.4462958574295044} 08/31/2021 08:48:32 - INFO - __main__ - Step 107834: {'lr': 9.363550178770754e-05, 'samples': 20704128, 'steps': 107833, 'loss/train': 0.8075213432312012} 08/31/2021 08:48:32 - INFO - __main__ - Step 107835: {'lr': 9.363136119404589e-05, 'samples': 20704320, 'steps': 107834, 'loss/train': 1.2254855632781982} 08/31/2021 08:48:32 - INFO - __main__ - Step 107836: {'lr': 9.362722067084156e-05, 'samples': 20704512, 'steps': 107835, 'loss/train': 1.238389015197754} 08/31/2021 08:48:34 - INFO - __main__ - Step 107837: {'lr': 9.362308021809637e-05, 'samples': 20704704, 'steps': 107836, 'loss/train': 1.0400406122207642} 08/31/2021 08:48:35 - INFO - __main__ - Step 107838: {'lr': 9.361893983581221e-05, 'samples': 20704896, 'steps': 107837, 'loss/train': 1.2224959135055542} 08/31/2021 08:48:35 - INFO - __main__ - Step 107839: {'lr': 9.361479952399093e-05, 'samples': 20705088, 'steps': 107838, 'loss/train': 1.4622020721435547} 08/31/2021 08:48:35 - INFO - __main__ - Step 107840: {'lr': 9.361065928263443e-05, 'samples': 20705280, 'steps': 107839, 'loss/train': 1.5158405303955078} 08/31/2021 08:48:36 - INFO - __main__ - Step 107841: {'lr': 9.360651911174455e-05, 'samples': 20705472, 'steps': 107840, 'loss/train': 0.9269044995307922} 08/31/2021 08:48:37 - INFO - __main__ - Step 107842: {'lr': 9.360237901132316e-05, 'samples': 20705664, 'steps': 107841, 'loss/train': 1.0850164890289307} 08/31/2021 08:48:38 - INFO - __main__ - Step 107843: {'lr': 9.359823898137212e-05, 'samples': 20705856, 'steps': 107842, 'loss/train': 1.1716654300689697} 08/31/2021 08:48:38 - INFO - __main__ - Step 107844: {'lr': 9.35940990218933e-05, 'samples': 20706048, 'steps': 107843, 'loss/train': 1.243765115737915} 08/31/2021 08:48:38 - INFO - __main__ - Step 107845: {'lr': 9.358995913288865e-05, 'samples': 20706240, 'steps': 107844, 'loss/train': 0.37880223989486694} 08/31/2021 08:48:39 - INFO - __main__ - Step 107846: {'lr': 9.358581931435987e-05, 'samples': 20706432, 'steps': 107845, 'loss/train': 1.048689365386963} 08/31/2021 08:48:40 - INFO - __main__ - Step 107847: {'lr': 9.358167956630889e-05, 'samples': 20706624, 'steps': 107846, 'loss/train': 1.0498987436294556} 08/31/2021 08:48:41 - INFO - __main__ - Step 107848: {'lr': 9.357753988873763e-05, 'samples': 20706816, 'steps': 107847, 'loss/train': 1.5488194227218628} 08/31/2021 08:48:41 - INFO - __main__ - Step 107849: {'lr': 9.357340028164787e-05, 'samples': 20707008, 'steps': 107848, 'loss/train': 1.76338529586792} 08/31/2021 08:48:42 - INFO - __main__ - Step 107850: {'lr': 9.356926074504155e-05, 'samples': 20707200, 'steps': 107849, 'loss/train': 1.2985339164733887} 08/31/2021 08:48:42 - INFO - __main__ - Step 107851: {'lr': 9.35651212789205e-05, 'samples': 20707392, 'steps': 107850, 'loss/train': 0.05123785510659218} 08/31/2021 08:48:43 - INFO - __main__ - Step 107852: {'lr': 9.35609818832866e-05, 'samples': 20707584, 'steps': 107851, 'loss/train': 1.364959478378296} 08/31/2021 08:48:44 - INFO - __main__ - Step 107853: {'lr': 9.35568425581417e-05, 'samples': 20707776, 'steps': 107852, 'loss/train': 1.5660630464553833} 08/31/2021 08:48:44 - INFO - __main__ - Step 107854: {'lr': 9.355270330348767e-05, 'samples': 20707968, 'steps': 107853, 'loss/train': 1.2035883665084839} 08/31/2021 08:48:45 - INFO - __main__ - Step 107855: {'lr': 9.354856411932639e-05, 'samples': 20708160, 'steps': 107854, 'loss/train': 0.7718247771263123} 08/31/2021 08:48:45 - INFO - __main__ - Step 107856: {'lr': 9.354442500565968e-05, 'samples': 20708352, 'steps': 107855, 'loss/train': 1.0299553871154785} 08/31/2021 08:48:45 - INFO - __main__ - Step 107857: {'lr': 9.354028596248948e-05, 'samples': 20708544, 'steps': 107856, 'loss/train': 0.6652044653892517} 08/31/2021 08:48:47 - INFO - __main__ - Step 107858: {'lr': 9.353614698981761e-05, 'samples': 20708736, 'steps': 107857, 'loss/train': 0.9664566516876221} 08/31/2021 08:48:48 - INFO - __main__ - Step 107859: {'lr': 9.3532008087646e-05, 'samples': 20708928, 'steps': 107858, 'loss/train': 0.03020261600613594} 08/31/2021 08:48:48 - INFO - __main__ - Step 107860: {'lr': 9.352786925597636e-05, 'samples': 20709120, 'steps': 107859, 'loss/train': 1.4558933973312378} 08/31/2021 08:48:48 - INFO - __main__ - Step 107861: {'lr': 9.352373049481067e-05, 'samples': 20709312, 'steps': 107860, 'loss/train': 1.2822175025939941} 08/31/2021 08:48:49 - INFO - __main__ - Step 107862: {'lr': 9.351959180415077e-05, 'samples': 20709504, 'steps': 107861, 'loss/train': 0.594023585319519} 08/31/2021 08:48:50 - INFO - __main__ - Step 107863: {'lr': 9.351545318399851e-05, 'samples': 20709696, 'steps': 107862, 'loss/train': 0.5600147843360901} 08/31/2021 08:48:51 - INFO - __main__ - Step 107864: {'lr': 9.351131463435581e-05, 'samples': 20709888, 'steps': 107863, 'loss/train': 0.911152720451355} 08/31/2021 08:48:51 - INFO - __main__ - Step 107865: {'lr': 9.350717615522444e-05, 'samples': 20710080, 'steps': 107864, 'loss/train': 0.33738383650779724} 08/31/2021 08:48:51 - INFO - __main__ - Step 107866: {'lr': 9.350303774660637e-05, 'samples': 20710272, 'steps': 107865, 'loss/train': 1.2186495065689087} 08/31/2021 08:48:52 - INFO - __main__ - Step 107867: {'lr': 9.34988994085034e-05, 'samples': 20710464, 'steps': 107866, 'loss/train': 1.0167064666748047} 08/31/2021 08:48:53 - INFO - __main__ - Step 107868: {'lr': 9.34947611409174e-05, 'samples': 20710656, 'steps': 107867, 'loss/train': 0.8011385798454285} 08/31/2021 08:48:54 - INFO - __main__ - Step 107869: {'lr': 9.349062294385027e-05, 'samples': 20710848, 'steps': 107868, 'loss/train': 1.7132511138916016} 08/31/2021 08:48:54 - INFO - __main__ - Step 107870: {'lr': 9.348648481730382e-05, 'samples': 20711040, 'steps': 107869, 'loss/train': 1.2275643348693848} 08/31/2021 08:48:54 - INFO - __main__ - Step 107871: {'lr': 9.348234676127998e-05, 'samples': 20711232, 'steps': 107870, 'loss/train': 1.276097297668457} 08/31/2021 08:48:55 - INFO - __main__ - Step 107872: {'lr': 9.347820877578064e-05, 'samples': 20711424, 'steps': 107871, 'loss/train': 1.2847880125045776} 08/31/2021 08:48:56 - INFO - __main__ - Step 107873: {'lr': 9.347407086080753e-05, 'samples': 20711616, 'steps': 107872, 'loss/train': 0.7249664068222046} 08/31/2021 08:48:57 - INFO - __main__ - Step 107874: {'lr': 9.346993301636256e-05, 'samples': 20711808, 'steps': 107873, 'loss/train': 0.744190514087677} 08/31/2021 08:48:57 - INFO - __main__ - Step 107875: {'lr': 9.346579524244767e-05, 'samples': 20712000, 'steps': 107874, 'loss/train': 0.7878009080886841} 08/31/2021 08:48:57 - INFO - __main__ - Step 107876: {'lr': 9.346165753906464e-05, 'samples': 20712192, 'steps': 107875, 'loss/train': 0.8875252604484558} 08/31/2021 08:48:58 - INFO - __main__ - Step 107877: {'lr': 9.345751990621537e-05, 'samples': 20712384, 'steps': 107876, 'loss/train': 1.1468157768249512} 08/31/2021 08:49:00 - INFO - __main__ - Step 107878: {'lr': 9.345338234390174e-05, 'samples': 20712576, 'steps': 107877, 'loss/train': 1.3685414791107178} 08/31/2021 08:49:00 - INFO - __main__ - Step 107879: {'lr': 9.344924485212561e-05, 'samples': 20712768, 'steps': 107878, 'loss/train': 1.3615666627883911} 08/31/2021 08:49:01 - INFO - __main__ - Step 107880: {'lr': 9.344510743088882e-05, 'samples': 20712960, 'steps': 107879, 'loss/train': 0.6508249044418335} 08/31/2021 08:49:01 - INFO - __main__ - Step 107881: {'lr': 9.344097008019326e-05, 'samples': 20713152, 'steps': 107880, 'loss/train': 1.5305792093276978} 08/31/2021 08:49:01 - INFO - __main__ - Step 107882: {'lr': 9.343683280004078e-05, 'samples': 20713344, 'steps': 107881, 'loss/train': 1.4259026050567627} 08/31/2021 08:49:02 - INFO - __main__ - Step 107883: {'lr': 9.343269559043324e-05, 'samples': 20713536, 'steps': 107882, 'loss/train': 2.237344980239868} 08/31/2021 08:49:03 - INFO - __main__ - Step 107884: {'lr': 9.342855845137252e-05, 'samples': 20713728, 'steps': 107883, 'loss/train': 1.2029072046279907} 08/31/2021 08:49:04 - INFO - __main__ - Step 107885: {'lr': 9.342442138286048e-05, 'samples': 20713920, 'steps': 107884, 'loss/train': 1.1455423831939697} 08/31/2021 08:49:04 - INFO - __main__ - Step 107886: {'lr': 9.342028438489905e-05, 'samples': 20714112, 'steps': 107885, 'loss/train': 0.5140069127082825} 08/31/2021 08:49:04 - INFO - __main__ - Step 107887: {'lr': 9.341614745748995e-05, 'samples': 20714304, 'steps': 107886, 'loss/train': 0.5196638107299805} 08/31/2021 08:49:05 - INFO - __main__ - Step 107888: {'lr': 9.34120106006351e-05, 'samples': 20714496, 'steps': 107887, 'loss/train': 1.266554355621338} 08/31/2021 08:49:07 - INFO - __main__ - Step 107889: {'lr': 9.340787381433638e-05, 'samples': 20714688, 'steps': 107888, 'loss/train': 1.385787844657898} 08/31/2021 08:49:07 - INFO - __main__ - Step 107890: {'lr': 9.340373709859567e-05, 'samples': 20714880, 'steps': 107889, 'loss/train': 0.0934094712138176} 08/31/2021 08:49:07 - INFO - __main__ - Step 107891: {'lr': 9.339960045341483e-05, 'samples': 20715072, 'steps': 107890, 'loss/train': 0.06828249990940094} 08/31/2021 08:49:08 - INFO - __main__ - Step 107892: {'lr': 9.339546387879568e-05, 'samples': 20715264, 'steps': 107891, 'loss/train': 0.8092866539955139} 08/31/2021 08:49:08 - INFO - __main__ - Step 107893: {'lr': 9.339132737474015e-05, 'samples': 20715456, 'steps': 107892, 'loss/train': 0.470276802778244} 08/31/2021 08:49:10 - INFO - __main__ - Step 107894: {'lr': 9.338719094125007e-05, 'samples': 20715648, 'steps': 107893, 'loss/train': 0.8193601369857788} 08/31/2021 08:49:10 - INFO - __main__ - Step 107895: {'lr': 9.33830545783273e-05, 'samples': 20715840, 'steps': 107894, 'loss/train': 0.7013453841209412} 08/31/2021 08:49:11 - INFO - __main__ - Step 107896: {'lr': 9.33789182859737e-05, 'samples': 20716032, 'steps': 107895, 'loss/train': 1.333148717880249} 08/31/2021 08:49:11 - INFO - __main__ - Step 107897: {'lr': 9.337478206419115e-05, 'samples': 20716224, 'steps': 107896, 'loss/train': 0.5705798864364624} 08/31/2021 08:49:11 - INFO - __main__ - Step 107898: {'lr': 9.33706459129815e-05, 'samples': 20716416, 'steps': 107897, 'loss/train': 1.279287338256836} 08/31/2021 08:49:13 - INFO - __main__ - Step 107899: {'lr': 9.336650983234671e-05, 'samples': 20716608, 'steps': 107898, 'loss/train': 0.09293182939291} 08/31/2021 08:49:13 - INFO - __main__ - Step 107900: {'lr': 9.336237382228846e-05, 'samples': 20716800, 'steps': 107899, 'loss/train': 1.0361387729644775} 08/31/2021 08:49:14 - INFO - __main__ - Step 107901: {'lr': 9.335823788280873e-05, 'samples': 20716992, 'steps': 107900, 'loss/train': 0.9461830258369446} 08/31/2021 08:49:14 - INFO - __main__ - Step 107902: {'lr': 9.335410201390934e-05, 'samples': 20717184, 'steps': 107901, 'loss/train': 1.1447081565856934} 08/31/2021 08:49:15 - INFO - __main__ - Step 107903: {'lr': 9.334996621559219e-05, 'samples': 20717376, 'steps': 107902, 'loss/train': 0.9186926484107971} 08/31/2021 08:49:16 - INFO - __main__ - Step 107904: {'lr': 9.33458304878591e-05, 'samples': 20717568, 'steps': 107903, 'loss/train': 1.622067928314209} 08/31/2021 08:49:17 - INFO - __main__ - Step 107905: {'lr': 9.334169483071201e-05, 'samples': 20717760, 'steps': 107904, 'loss/train': 0.8982301354408264} 08/31/2021 08:49:17 - INFO - __main__ - Step 107906: {'lr': 9.333755924415269e-05, 'samples': 20717952, 'steps': 107905, 'loss/train': 1.3048495054244995} 08/31/2021 08:49:17 - INFO - __main__ - Step 107907: {'lr': 9.333342372818307e-05, 'samples': 20718144, 'steps': 107906, 'loss/train': 1.1716967821121216} 08/31/2021 08:49:18 - INFO - __main__ - Step 107908: {'lr': 9.332928828280499e-05, 'samples': 20718336, 'steps': 107907, 'loss/train': 1.0692551136016846} 08/31/2021 08:49:19 - INFO - __main__ - Step 107909: {'lr': 9.332515290802029e-05, 'samples': 20718528, 'steps': 107908, 'loss/train': 0.9043654203414917} 08/31/2021 08:49:20 - INFO - __main__ - Step 107910: {'lr': 9.332101760383088e-05, 'samples': 20718720, 'steps': 107909, 'loss/train': 1.6061744689941406} 08/31/2021 08:49:20 - INFO - __main__ - Step 107911: {'lr': 9.331688237023861e-05, 'samples': 20718912, 'steps': 107910, 'loss/train': 1.5527416467666626} 08/31/2021 08:49:20 - INFO - __main__ - Step 107912: {'lr': 9.331274720724531e-05, 'samples': 20719104, 'steps': 107911, 'loss/train': 0.8544957041740417} 08/31/2021 08:49:21 - INFO - __main__ - Step 107913: {'lr': 9.330861211485298e-05, 'samples': 20719296, 'steps': 107912, 'loss/train': 1.6542693376541138} 08/31/2021 08:49:21 - INFO - __main__ - Step 107914: {'lr': 9.330447709306328e-05, 'samples': 20719488, 'steps': 107913, 'loss/train': 1.687711477279663} 08/31/2021 08:49:23 - INFO - __main__ - Step 107915: {'lr': 9.330034214187816e-05, 'samples': 20719680, 'steps': 107914, 'loss/train': 0.3705524802207947} 08/31/2021 08:49:23 - INFO - __main__ - Step 107916: {'lr': 9.329620726129948e-05, 'samples': 20719872, 'steps': 107915, 'loss/train': 1.405173897743225} 08/31/2021 08:49:23 - INFO - __main__ - Step 107917: {'lr': 9.329207245132912e-05, 'samples': 20720064, 'steps': 107916, 'loss/train': 1.1100999116897583} 08/31/2021 08:49:24 - INFO - __main__ - Step 107918: {'lr': 9.328793771196892e-05, 'samples': 20720256, 'steps': 107917, 'loss/train': 0.9398180842399597} 08/31/2021 08:49:24 - INFO - __main__ - Step 107919: {'lr': 9.328380304322078e-05, 'samples': 20720448, 'steps': 107918, 'loss/train': 1.1057183742523193} 08/31/2021 08:49:26 - INFO - __main__ - Step 107920: {'lr': 9.327966844508654e-05, 'samples': 20720640, 'steps': 107919, 'loss/train': 0.5519773960113525} 08/31/2021 08:49:26 - INFO - __main__ - Step 107921: {'lr': 9.327553391756804e-05, 'samples': 20720832, 'steps': 107920, 'loss/train': 1.2930192947387695} 08/31/2021 08:49:26 - INFO - __main__ - Step 107922: {'lr': 9.327139946066718e-05, 'samples': 20721024, 'steps': 107921, 'loss/train': 1.2550429105758667} 08/31/2021 08:49:27 - INFO - __main__ - Step 107923: {'lr': 9.32672650743858e-05, 'samples': 20721216, 'steps': 107922, 'loss/train': 1.4882266521453857} 08/31/2021 08:49:27 - INFO - __main__ - Step 107924: {'lr': 9.326313075872578e-05, 'samples': 20721408, 'steps': 107923, 'loss/train': 0.4173848628997803} 08/31/2021 08:49:29 - INFO - __main__ - Step 107925: {'lr': 9.325899651368897e-05, 'samples': 20721600, 'steps': 107924, 'loss/train': 1.3922368288040161} 08/31/2021 08:49:29 - INFO - __main__ - Step 107926: {'lr': 9.325486233927732e-05, 'samples': 20721792, 'steps': 107925, 'loss/train': 1.2947227954864502} 08/31/2021 08:49:29 - INFO - __main__ - Step 107927: {'lr': 9.325072823549256e-05, 'samples': 20721984, 'steps': 107926, 'loss/train': 0.834082305431366} 08/31/2021 08:49:30 - INFO - __main__ - Step 107928: {'lr': 9.324659420233655e-05, 'samples': 20722176, 'steps': 107927, 'loss/train': 1.1658803224563599} 08/31/2021 08:49:30 - INFO - __main__ - Step 107929: {'lr': 9.324246023981123e-05, 'samples': 20722368, 'steps': 107928, 'loss/train': 0.9723550081253052} 08/31/2021 08:49:32 - INFO - __main__ - Step 107930: {'lr': 9.323832634791846e-05, 'samples': 20722560, 'steps': 107929, 'loss/train': 1.0116815567016602} 08/31/2021 08:49:33 - INFO - __main__ - Step 107931: {'lr': 9.323419252666004e-05, 'samples': 20722752, 'steps': 107930, 'loss/train': 1.4044753313064575} 08/31/2021 08:49:33 - INFO - __main__ - Step 107932: {'lr': 9.323005877603791e-05, 'samples': 20722944, 'steps': 107931, 'loss/train': 1.1015211343765259} 08/31/2021 08:49:33 - INFO - __main__ - Step 107933: {'lr': 9.322592509605388e-05, 'samples': 20723136, 'steps': 107932, 'loss/train': 1.1996742486953735} 08/31/2021 08:49:34 - INFO - __main__ - Step 107934: {'lr': 9.322179148670981e-05, 'samples': 20723328, 'steps': 107933, 'loss/train': 0.28654998540878296} 08/31/2021 08:49:35 - INFO - __main__ - Step 107935: {'lr': 9.32176579480076e-05, 'samples': 20723520, 'steps': 107934, 'loss/train': 0.8760296106338501} 08/31/2021 08:49:36 - INFO - __main__ - Step 107936: {'lr': 9.32135244799491e-05, 'samples': 20723712, 'steps': 107935, 'loss/train': 1.1622841358184814} 08/31/2021 08:49:36 - INFO - __main__ - Step 107937: {'lr': 9.320939108253618e-05, 'samples': 20723904, 'steps': 107936, 'loss/train': 1.6438461542129517} 08/31/2021 08:49:36 - INFO - __main__ - Step 107938: {'lr': 9.320525775577065e-05, 'samples': 20724096, 'steps': 107937, 'loss/train': 1.3163005113601685} 08/31/2021 08:49:37 - INFO - __main__ - Step 107939: {'lr': 9.320112449965446e-05, 'samples': 20724288, 'steps': 107938, 'loss/train': 1.2454625368118286} 08/31/2021 08:49:39 - INFO - __main__ - Step 107940: {'lr': 9.319699131418946e-05, 'samples': 20724480, 'steps': 107939, 'loss/train': 1.0292152166366577} 08/31/2021 08:49:39 - INFO - __main__ - Step 107941: {'lr': 9.319285819937742e-05, 'samples': 20724672, 'steps': 107940, 'loss/train': 1.600354790687561} 08/31/2021 08:49:39 - INFO - __main__ - Step 107942: {'lr': 9.318872515522026e-05, 'samples': 20724864, 'steps': 107941, 'loss/train': 0.41159698367118835} 08/31/2021 08:49:40 - INFO - __main__ - Step 107943: {'lr': 9.318459218171982e-05, 'samples': 20725056, 'steps': 107942, 'loss/train': 1.3070001602172852} 08/31/2021 08:49:40 - INFO - __main__ - Step 107944: {'lr': 9.3180459278878e-05, 'samples': 20725248, 'steps': 107943, 'loss/train': 0.8010015487670898} 08/31/2021 08:49:42 - INFO - __main__ - Step 107945: {'lr': 9.317632644669662e-05, 'samples': 20725440, 'steps': 107944, 'loss/train': 1.1423439979553223} 08/31/2021 08:49:42 - INFO - __main__ - Step 107946: {'lr': 9.317219368517759e-05, 'samples': 20725632, 'steps': 107945, 'loss/train': 1.6558212041854858} 08/31/2021 08:49:42 - INFO - __main__ - Step 107947: {'lr': 9.316806099432276e-05, 'samples': 20725824, 'steps': 107946, 'loss/train': 1.8351900577545166} 08/31/2021 08:49:43 - INFO - __main__ - Step 107948: {'lr': 9.316392837413396e-05, 'samples': 20726016, 'steps': 107947, 'loss/train': 1.269007921218872} 08/31/2021 08:49:43 - INFO - __main__ - Step 107949: {'lr': 9.31597958246131e-05, 'samples': 20726208, 'steps': 107948, 'loss/train': 0.6315890550613403} 08/31/2021 08:49:43 - INFO - __main__ - Step 107950: {'lr': 9.315566334576197e-05, 'samples': 20726400, 'steps': 107949, 'loss/train': 0.54716557264328} 08/31/2021 08:49:45 - INFO - __main__ - Step 107951: {'lr': 9.315153093758249e-05, 'samples': 20726592, 'steps': 107950, 'loss/train': 0.04706646874547005} 08/31/2021 08:49:45 - INFO - __main__ - Step 107952: {'lr': 9.314739860007654e-05, 'samples': 20726784, 'steps': 107951, 'loss/train': 0.8142390251159668} 08/31/2021 08:49:46 - INFO - __main__ - Step 107953: {'lr': 9.314326633324602e-05, 'samples': 20726976, 'steps': 107952, 'loss/train': 1.019706130027771} 08/31/2021 08:49:46 - INFO - __main__ - Step 107954: {'lr': 9.313913413709266e-05, 'samples': 20727168, 'steps': 107953, 'loss/train': 0.029053449630737305} 08/31/2021 08:49:46 - INFO - __main__ - Step 107955: {'lr': 9.313500201161834e-05, 'samples': 20727360, 'steps': 107954, 'loss/train': 1.5364243984222412} 08/31/2021 08:49:48 - INFO - __main__ - Step 107956: {'lr': 9.313086995682501e-05, 'samples': 20727552, 'steps': 107955, 'loss/train': 0.7286567687988281} 08/31/2021 08:49:48 - INFO - __main__ - Step 107957: {'lr': 9.312673797271447e-05, 'samples': 20727744, 'steps': 107956, 'loss/train': 1.288769006729126} 08/31/2021 08:49:49 - INFO - __main__ - Step 107958: {'lr': 9.31226060592886e-05, 'samples': 20727936, 'steps': 107957, 'loss/train': 1.4163821935653687} 08/31/2021 08:49:49 - INFO - __main__ - Step 107959: {'lr': 9.311847421654926e-05, 'samples': 20728128, 'steps': 107958, 'loss/train': 1.077035903930664} 08/31/2021 08:49:50 - INFO - __main__ - Step 107960: {'lr': 9.311434244449831e-05, 'samples': 20728320, 'steps': 107959, 'loss/train': 1.2252087593078613} 08/31/2021 08:49:51 - INFO - __main__ - Step 107961: {'lr': 9.311021074313763e-05, 'samples': 20728512, 'steps': 107960, 'loss/train': 1.790932297706604} 08/31/2021 08:49:51 - INFO - __main__ - Step 107962: {'lr': 9.310607911246907e-05, 'samples': 20728704, 'steps': 107961, 'loss/train': 0.7683644890785217} 08/31/2021 08:49:52 - INFO - __main__ - Step 107963: {'lr': 9.310194755249449e-05, 'samples': 20728896, 'steps': 107962, 'loss/train': 1.3659043312072754} 08/31/2021 08:49:52 - INFO - __main__ - Step 107964: {'lr': 9.309781606321576e-05, 'samples': 20729088, 'steps': 107963, 'loss/train': 0.2578679621219635} 08/31/2021 08:49:52 - INFO - __main__ - Step 107965: {'lr': 9.309368464463473e-05, 'samples': 20729280, 'steps': 107964, 'loss/train': 0.9254921078681946} 08/31/2021 08:49:54 - INFO - __main__ - Step 107966: {'lr': 9.308955329675333e-05, 'samples': 20729472, 'steps': 107965, 'loss/train': 0.9764153957366943} 08/31/2021 08:49:55 - INFO - __main__ - Step 107967: {'lr': 9.30854220195733e-05, 'samples': 20729664, 'steps': 107966, 'loss/train': 1.843541145324707} 08/31/2021 08:49:55 - INFO - __main__ - Step 107968: {'lr': 9.308129081309652e-05, 'samples': 20729856, 'steps': 107967, 'loss/train': 0.822740375995636} 08/31/2021 08:49:55 - INFO - __main__ - Step 107969: {'lr': 9.307715967732491e-05, 'samples': 20730048, 'steps': 107968, 'loss/train': 0.11348571628332138} 08/31/2021 08:49:56 - INFO - __main__ - Step 107970: {'lr': 9.30730286122603e-05, 'samples': 20730240, 'steps': 107969, 'loss/train': 1.5903092622756958} 08/31/2021 08:49:57 - INFO - __main__ - Step 107971: {'lr': 9.306889761790458e-05, 'samples': 20730432, 'steps': 107970, 'loss/train': 1.4032684564590454} 08/31/2021 08:49:58 - INFO - __main__ - Step 107972: {'lr': 9.306476669425957e-05, 'samples': 20730624, 'steps': 107971, 'loss/train': 1.2942450046539307} 08/31/2021 08:49:58 - INFO - __main__ - Step 107973: {'lr': 9.306063584132717e-05, 'samples': 20730816, 'steps': 107972, 'loss/train': 0.931864857673645} 08/31/2021 08:49:58 - INFO - __main__ - Step 107974: {'lr': 9.305650505910922e-05, 'samples': 20731008, 'steps': 107973, 'loss/train': 1.6744049787521362} 08/31/2021 08:49:59 - INFO - __main__ - Step 107975: {'lr': 9.305237434760758e-05, 'samples': 20731200, 'steps': 107974, 'loss/train': 0.8523196578025818} 08/31/2021 08:49:59 - INFO - __main__ - Step 107976: {'lr': 9.304824370682414e-05, 'samples': 20731392, 'steps': 107975, 'loss/train': 1.4730018377304077} 08/31/2021 08:50:00 - INFO - __main__ - Step 107977: {'lr': 9.304411313676073e-05, 'samples': 20731584, 'steps': 107976, 'loss/train': 1.5157594680786133} 08/31/2021 08:50:01 - INFO - __main__ - Step 107978: {'lr': 9.303998263741923e-05, 'samples': 20731776, 'steps': 107977, 'loss/train': 1.1157255172729492} 08/31/2021 08:50:01 - INFO - __main__ - Step 107979: {'lr': 9.303585220880146e-05, 'samples': 20731968, 'steps': 107978, 'loss/train': 0.8583193421363831} 08/31/2021 08:50:01 - INFO - __main__ - Step 107980: {'lr': 9.303172185090941e-05, 'samples': 20732160, 'steps': 107979, 'loss/train': 1.3796651363372803} 08/31/2021 08:50:02 - INFO - __main__ - Step 107981: {'lr': 9.302759156374477e-05, 'samples': 20732352, 'steps': 107980, 'loss/train': 0.9369054436683655} 08/31/2021 08:50:03 - INFO - __main__ - Step 107982: {'lr': 9.30234613473095e-05, 'samples': 20732544, 'steps': 107981, 'loss/train': 1.0438655614852905} 08/31/2021 08:50:04 - INFO - __main__ - Step 107983: {'lr': 9.301933120160538e-05, 'samples': 20732736, 'steps': 107982, 'loss/train': 1.1810835599899292} 08/31/2021 08:50:04 - INFO - __main__ - Step 107984: {'lr': 9.301520112663437e-05, 'samples': 20732928, 'steps': 107983, 'loss/train': 1.3444160223007202} 08/31/2021 08:50:05 - INFO - __main__ - Step 107985: {'lr': 9.301107112239826e-05, 'samples': 20733120, 'steps': 107984, 'loss/train': 0.9078838229179382} 08/31/2021 08:50:05 - INFO - __main__ - Step 107986: {'lr': 9.300694118889896e-05, 'samples': 20733312, 'steps': 107985, 'loss/train': 1.1885769367218018} 08/31/2021 08:50:07 - INFO - __main__ - Step 107987: {'lr': 9.30028113261383e-05, 'samples': 20733504, 'steps': 107986, 'loss/train': 0.04047380015254021} 08/31/2021 08:50:08 - INFO - __main__ - Step 107988: {'lr': 9.299868153411814e-05, 'samples': 20733696, 'steps': 107987, 'loss/train': 1.5717118978500366} 08/31/2021 08:50:08 - INFO - __main__ - Step 107989: {'lr': 9.299455181284036e-05, 'samples': 20733888, 'steps': 107988, 'loss/train': 1.2796076536178589} 08/31/2021 08:50:09 - INFO - __main__ - Step 107990: {'lr': 9.299042216230682e-05, 'samples': 20734080, 'steps': 107989, 'loss/train': 1.0889464616775513} 08/31/2021 08:50:09 - INFO - __main__ - Step 107991: {'lr': 9.298629258251936e-05, 'samples': 20734272, 'steps': 107990, 'loss/train': 0.14452140033245087} 08/31/2021 08:50:09 - INFO - __main__ - Step 107992: {'lr': 9.298216307347988e-05, 'samples': 20734464, 'steps': 107991, 'loss/train': 1.5820964574813843} 08/31/2021 08:50:11 - INFO - __main__ - Step 107993: {'lr': 9.297803363519029e-05, 'samples': 20734656, 'steps': 107992, 'loss/train': 0.7947246432304382} 08/31/2021 08:50:11 - INFO - __main__ - Step 107994: {'lr': 9.297390426765226e-05, 'samples': 20734848, 'steps': 107993, 'loss/train': 1.3307762145996094} 08/31/2021 08:50:12 - INFO - __main__ - Step 107995: {'lr': 9.29697749708678e-05, 'samples': 20735040, 'steps': 107994, 'loss/train': 0.46623942255973816} 08/31/2021 08:50:12 - INFO - __main__ - Step 107996: {'lr': 9.296564574483873e-05, 'samples': 20735232, 'steps': 107995, 'loss/train': 1.4805090427398682} 08/31/2021 08:50:12 - INFO - __main__ - Step 107997: {'lr': 9.296151658956689e-05, 'samples': 20735424, 'steps': 107996, 'loss/train': 0.9162530303001404} 08/31/2021 08:50:14 - INFO - __main__ - Step 107998: {'lr': 9.295738750505419e-05, 'samples': 20735616, 'steps': 107997, 'loss/train': 0.7183054685592651} 08/31/2021 08:50:14 - INFO - __main__ - Step 107999: {'lr': 9.295325849130249e-05, 'samples': 20735808, 'steps': 107998, 'loss/train': 0.06238754466176033} 08/31/2021 08:50:15 - INFO - __main__ - Step 108000: {'lr': 9.294912954831359e-05, 'samples': 20736000, 'steps': 107999, 'loss/train': 1.1909373998641968} 08/31/2021 08:50:15 - INFO - __main__ - Step 108001: {'lr': 9.29450006760894e-05, 'samples': 20736192, 'steps': 108000, 'loss/train': 1.1259735822677612} 08/31/2021 08:50:15 - INFO - __main__ - Step 108002: {'lr': 9.294087187463176e-05, 'samples': 20736384, 'steps': 108001, 'loss/train': 0.75650954246521} 08/31/2021 08:50:17 - INFO - __main__ - Step 108003: {'lr': 9.293674314394258e-05, 'samples': 20736576, 'steps': 108002, 'loss/train': 0.9995419383049011} 08/31/2021 08:50:18 - INFO - __main__ - Step 108004: {'lr': 9.293261448402363e-05, 'samples': 20736768, 'steps': 108003, 'loss/train': 1.5002449750900269} 08/31/2021 08:50:18 - INFO - __main__ - Step 108005: {'lr': 9.292848589487684e-05, 'samples': 20736960, 'steps': 108004, 'loss/train': 0.7873072028160095} 08/31/2021 08:50:18 - INFO - __main__ - Step 108006: {'lr': 9.292435737650406e-05, 'samples': 20737152, 'steps': 108005, 'loss/train': 0.8349205851554871} 08/31/2021 08:50:19 - INFO - __main__ - Step 108007: {'lr': 9.292022892890723e-05, 'samples': 20737344, 'steps': 108006, 'loss/train': 0.9616420269012451} 08/31/2021 08:50:21 - INFO - __main__ - Step 108008: {'lr': 9.291610055208802e-05, 'samples': 20737536, 'steps': 108007, 'loss/train': 1.1503429412841797} 08/31/2021 08:50:21 - INFO - __main__ - Step 108009: {'lr': 9.291197224604839e-05, 'samples': 20737728, 'steps': 108008, 'loss/train': 1.2140333652496338} 08/31/2021 08:50:21 - INFO - __main__ - Step 108010: {'lr': 9.29078440107902e-05, 'samples': 20737920, 'steps': 108009, 'loss/train': 1.2954727411270142} 08/31/2021 08:50:22 - INFO - __main__ - Step 108011: {'lr': 9.290371584631532e-05, 'samples': 20738112, 'steps': 108010, 'loss/train': 0.7139278650283813} 08/31/2021 08:50:22 - INFO - __main__ - Step 108012: {'lr': 9.289958775262561e-05, 'samples': 20738304, 'steps': 108011, 'loss/train': 1.2183538675308228} 08/31/2021 08:50:22 - INFO - __main__ - Step 108013: {'lr': 9.28954597297229e-05, 'samples': 20738496, 'steps': 108012, 'loss/train': 1.4465656280517578} 08/31/2021 08:50:24 - INFO - __main__ - Step 108014: {'lr': 9.289133177760908e-05, 'samples': 20738688, 'steps': 108013, 'loss/train': 0.6118118166923523} 08/31/2021 08:50:24 - INFO - __main__ - Step 108015: {'lr': 9.2887203896286e-05, 'samples': 20738880, 'steps': 108014, 'loss/train': 1.6764758825302124} 08/31/2021 08:50:25 - INFO - __main__ - Step 108016: {'lr': 9.288307608575552e-05, 'samples': 20739072, 'steps': 108015, 'loss/train': 1.1459988355636597} 08/31/2021 08:50:25 - INFO - __main__ - Step 108017: {'lr': 9.287894834601951e-05, 'samples': 20739264, 'steps': 108016, 'loss/train': 1.170619010925293} 08/31/2021 08:50:25 - INFO - __main__ - Step 108018: {'lr': 9.287482067707983e-05, 'samples': 20739456, 'steps': 108017, 'loss/train': 0.8438692688941956} 08/31/2021 08:50:27 - INFO - __main__ - Step 108019: {'lr': 9.28706930789384e-05, 'samples': 20739648, 'steps': 108018, 'loss/train': 0.8628430962562561} 08/31/2021 08:50:27 - INFO - __main__ - Step 108020: {'lr': 9.286656555159692e-05, 'samples': 20739840, 'steps': 108019, 'loss/train': 1.3532332181930542} 08/31/2021 08:50:28 - INFO - __main__ - Step 108021: {'lr': 9.286243809505738e-05, 'samples': 20740032, 'steps': 108020, 'loss/train': 0.8872671127319336} 08/31/2021 08:50:28 - INFO - __main__ - Step 108022: {'lr': 9.285831070932155e-05, 'samples': 20740224, 'steps': 108021, 'loss/train': 0.6618024110794067} 08/31/2021 08:50:28 - INFO - __main__ - Step 108023: {'lr': 9.285418339439136e-05, 'samples': 20740416, 'steps': 108022, 'loss/train': 0.6733138561248779} 08/31/2021 08:50:30 - INFO - __main__ - Step 108024: {'lr': 9.285005615026865e-05, 'samples': 20740608, 'steps': 108023, 'loss/train': 1.2118993997573853} 08/31/2021 08:50:31 - INFO - __main__ - Step 108025: {'lr': 9.28459289769553e-05, 'samples': 20740800, 'steps': 108024, 'loss/train': 1.1906404495239258} 08/31/2021 08:50:31 - INFO - __main__ - Step 108026: {'lr': 9.284180187445312e-05, 'samples': 20740992, 'steps': 108025, 'loss/train': 0.7872807383537292} 08/31/2021 08:50:31 - INFO - __main__ - Step 108027: {'lr': 9.2837674842764e-05, 'samples': 20741184, 'steps': 108026, 'loss/train': 1.707274079322815} 08/31/2021 08:50:32 - INFO - __main__ - Step 108028: {'lr': 9.283354788188982e-05, 'samples': 20741376, 'steps': 108027, 'loss/train': 1.2540650367736816} 08/31/2021 08:50:32 - INFO - __main__ - Step 108029: {'lr': 9.282942099183242e-05, 'samples': 20741568, 'steps': 108028, 'loss/train': 1.8721414804458618} 08/31/2021 08:50:34 - INFO - __main__ - Step 108030: {'lr': 9.282529417259372e-05, 'samples': 20741760, 'steps': 108029, 'loss/train': 0.8369045853614807} 08/31/2021 08:50:34 - INFO - __main__ - Step 108031: {'lr': 9.282116742417543e-05, 'samples': 20741952, 'steps': 108030, 'loss/train': 1.6039831638336182} 08/31/2021 08:50:34 - INFO - __main__ - Step 108032: {'lr': 9.281704074657951e-05, 'samples': 20742144, 'steps': 108031, 'loss/train': 0.9567728638648987} 08/31/2021 08:50:35 - INFO - __main__ - Step 108033: {'lr': 9.28129141398078e-05, 'samples': 20742336, 'steps': 108032, 'loss/train': 1.6011251211166382} 08/31/2021 08:50:35 - INFO - __main__ - Step 108034: {'lr': 9.280878760386218e-05, 'samples': 20742528, 'steps': 108033, 'loss/train': 0.9109366536140442} 08/31/2021 08:50:37 - INFO - __main__ - Step 108035: {'lr': 9.280466113874447e-05, 'samples': 20742720, 'steps': 108034, 'loss/train': 1.4379431009292603} 08/31/2021 08:50:37 - INFO - __main__ - Step 108036: {'lr': 9.280053474445657e-05, 'samples': 20742912, 'steps': 108035, 'loss/train': 0.9185407161712646} 08/31/2021 08:50:38 - INFO - __main__ - Step 108037: {'lr': 9.279640842100035e-05, 'samples': 20743104, 'steps': 108036, 'loss/train': 0.6469335556030273} 08/31/2021 08:50:38 - INFO - __main__ - Step 108038: {'lr': 9.27922821683776e-05, 'samples': 20743296, 'steps': 108037, 'loss/train': 1.0880697965621948} 08/31/2021 08:50:38 - INFO - __main__ - Step 108039: {'lr': 9.278815598659024e-05, 'samples': 20743488, 'steps': 108038, 'loss/train': 1.3045501708984375} 08/31/2021 08:50:40 - INFO - __main__ - Step 108040: {'lr': 9.278402987564011e-05, 'samples': 20743680, 'steps': 108039, 'loss/train': 0.2648612856864929} 08/31/2021 08:50:41 - INFO - __main__ - Step 108041: {'lr': 9.277990383552914e-05, 'samples': 20743872, 'steps': 108040, 'loss/train': 1.0842446088790894} 08/31/2021 08:50:41 - INFO - __main__ - Step 108042: {'lr': 9.277577786625904e-05, 'samples': 20744064, 'steps': 108041, 'loss/train': 1.2825521230697632} 08/31/2021 08:50:41 - INFO - __main__ - Step 108043: {'lr': 9.277165196783177e-05, 'samples': 20744256, 'steps': 108042, 'loss/train': 1.137089729309082} 08/31/2021 08:50:42 - INFO - __main__ - Step 108044: {'lr': 9.276752614024914e-05, 'samples': 20744448, 'steps': 108043, 'loss/train': 0.653613269329071} 08/31/2021 08:50:43 - INFO - __main__ - Step 108045: {'lr': 9.276340038351305e-05, 'samples': 20744640, 'steps': 108044, 'loss/train': 0.6494199633598328} 08/31/2021 08:50:44 - INFO - __main__ - Step 108046: {'lr': 9.275927469762535e-05, 'samples': 20744832, 'steps': 108045, 'loss/train': 1.6633782386779785} 08/31/2021 08:50:44 - INFO - __main__ - Step 108047: {'lr': 9.27551490825879e-05, 'samples': 20745024, 'steps': 108046, 'loss/train': 1.3599340915679932} 08/31/2021 08:50:45 - INFO - __main__ - Step 108048: {'lr': 9.275102353840253e-05, 'samples': 20745216, 'steps': 108047, 'loss/train': 1.4801565408706665} 08/31/2021 08:50:45 - INFO - __main__ - Step 108049: {'lr': 9.274689806507114e-05, 'samples': 20745408, 'steps': 108048, 'loss/train': 0.506973385810852} 08/31/2021 08:50:46 - INFO - __main__ - Step 108050: {'lr': 9.274277266259557e-05, 'samples': 20745600, 'steps': 108049, 'loss/train': 1.266276240348816} 08/31/2021 08:50:47 - INFO - __main__ - Step 108051: {'lr': 9.273864733097775e-05, 'samples': 20745792, 'steps': 108050, 'loss/train': 1.0282782316207886} 08/31/2021 08:50:47 - INFO - __main__ - Step 108052: {'lr': 9.27345220702194e-05, 'samples': 20745984, 'steps': 108051, 'loss/train': 0.41314437985420227} 08/31/2021 08:50:48 - INFO - __main__ - Step 108053: {'lr': 9.273039688032244e-05, 'samples': 20746176, 'steps': 108052, 'loss/train': 0.5741205811500549} 08/31/2021 08:50:48 - INFO - __main__ - Step 108054: {'lr': 9.272627176128873e-05, 'samples': 20746368, 'steps': 108053, 'loss/train': 0.8120647668838501} 08/31/2021 08:50:49 - INFO - __main__ - Step 108055: {'lr': 9.272214671312015e-05, 'samples': 20746560, 'steps': 108054, 'loss/train': 1.1197038888931274} 08/31/2021 08:50:50 - INFO - __main__ - Step 108056: {'lr': 9.271802173581854e-05, 'samples': 20746752, 'steps': 108055, 'loss/train': 0.9983811378479004} 08/31/2021 08:50:50 - INFO - __main__ - Step 108057: {'lr': 9.271389682938574e-05, 'samples': 20746944, 'steps': 108056, 'loss/train': 1.2381510734558105} 08/31/2021 08:50:51 - INFO - __main__ - Step 108058: {'lr': 9.270977199382365e-05, 'samples': 20747136, 'steps': 108057, 'loss/train': 1.7712832689285278} 08/31/2021 08:50:51 - INFO - __main__ - Step 108059: {'lr': 9.270564722913413e-05, 'samples': 20747328, 'steps': 108058, 'loss/train': 1.0471794605255127} 08/31/2021 08:50:52 - INFO - __main__ - Step 108060: {'lr': 9.270152253531899e-05, 'samples': 20747520, 'steps': 108059, 'loss/train': 0.5062770247459412} 08/31/2021 08:50:53 - INFO - __main__ - Step 108061: {'lr': 9.269739791238013e-05, 'samples': 20747712, 'steps': 108060, 'loss/train': 1.2063143253326416} 08/31/2021 08:50:53 - INFO - __main__ - Step 108062: {'lr': 9.269327336031946e-05, 'samples': 20747904, 'steps': 108061, 'loss/train': 2.8160243034362793} 08/31/2021 08:50:54 - INFO - __main__ - Step 108063: {'lr': 9.26891488791387e-05, 'samples': 20748096, 'steps': 108062, 'loss/train': 1.1322611570358276} 08/31/2021 08:50:54 - INFO - __main__ - Step 108064: {'lr': 9.268502446883981e-05, 'samples': 20748288, 'steps': 108063, 'loss/train': 1.093564510345459} 08/31/2021 08:50:54 - INFO - __main__ - Step 108065: {'lr': 9.26809001294246e-05, 'samples': 20748480, 'steps': 108064, 'loss/train': 1.4409478902816772} 08/31/2021 08:50:56 - INFO - __main__ - Step 108066: {'lr': 9.267677586089493e-05, 'samples': 20748672, 'steps': 108065, 'loss/train': 1.396673560142517} 08/31/2021 08:50:57 - INFO - __main__ - Step 108067: {'lr': 9.26726516632527e-05, 'samples': 20748864, 'steps': 108066, 'loss/train': 1.2955596446990967} 08/31/2021 08:50:57 - INFO - __main__ - Step 108068: {'lr': 9.266852753649974e-05, 'samples': 20749056, 'steps': 108067, 'loss/train': 1.508488416671753} 08/31/2021 08:50:57 - INFO - __main__ - Step 108069: {'lr': 9.26644034806379e-05, 'samples': 20749248, 'steps': 108068, 'loss/train': 0.7254191040992737} 08/31/2021 08:50:58 - INFO - __main__ - Step 108070: {'lr': 9.266027949566908e-05, 'samples': 20749440, 'steps': 108069, 'loss/train': 0.03167993202805519} 08/31/2021 08:50:58 - INFO - __main__ - Step 108071: {'lr': 9.265615558159507e-05, 'samples': 20749632, 'steps': 108070, 'loss/train': 0.12427037954330444} 08/31/2021 08:50:59 - INFO - __main__ - Step 108072: {'lr': 9.26520317384178e-05, 'samples': 20749824, 'steps': 108071, 'loss/train': 1.4633082151412964} 08/31/2021 08:51:00 - INFO - __main__ - Step 108073: {'lr': 9.264790796613909e-05, 'samples': 20750016, 'steps': 108072, 'loss/train': 1.0952751636505127} 08/31/2021 08:51:00 - INFO - __main__ - Step 108074: {'lr': 9.26437842647609e-05, 'samples': 20750208, 'steps': 108073, 'loss/train': 1.1873711347579956} 08/31/2021 08:51:01 - INFO - __main__ - Step 108075: {'lr': 9.263966063428489e-05, 'samples': 20750400, 'steps': 108074, 'loss/train': 0.9926527142524719} 08/31/2021 08:51:01 - INFO - __main__ - Step 108076: {'lr': 9.2635537074713e-05, 'samples': 20750592, 'steps': 108075, 'loss/train': 0.45054736733436584} 08/31/2021 08:51:03 - INFO - __main__ - Step 108077: {'lr': 9.263141358604715e-05, 'samples': 20750784, 'steps': 108076, 'loss/train': 0.34057071805000305} 08/31/2021 08:51:03 - INFO - __main__ - Step 108078: {'lr': 9.262729016828914e-05, 'samples': 20750976, 'steps': 108077, 'loss/train': 0.7030280232429504} 08/31/2021 08:51:03 - INFO - __main__ - Step 108079: {'lr': 9.262316682144084e-05, 'samples': 20751168, 'steps': 108078, 'loss/train': 1.5311816930770874} 08/31/2021 08:51:04 - INFO - __main__ - Step 108080: {'lr': 9.261904354550413e-05, 'samples': 20751360, 'steps': 108079, 'loss/train': 1.2730793952941895} 08/31/2021 08:51:04 - INFO - __main__ - Step 108081: {'lr': 9.261492034048083e-05, 'samples': 20751552, 'steps': 108080, 'loss/train': 1.3321024179458618} 08/31/2021 08:51:06 - INFO - __main__ - Step 108082: {'lr': 9.261079720637284e-05, 'samples': 20751744, 'steps': 108081, 'loss/train': 1.22978675365448} 08/31/2021 08:51:07 - INFO - __main__ - Step 108083: {'lr': 9.260667414318197e-05, 'samples': 20751936, 'steps': 108082, 'loss/train': 1.0241857767105103} 08/31/2021 08:51:07 - INFO - __main__ - Step 108084: {'lr': 9.260255115091013e-05, 'samples': 20752128, 'steps': 108083, 'loss/train': 1.3356059789657593} 08/31/2021 08:51:07 - INFO - __main__ - Step 108085: {'lr': 9.259842822955914e-05, 'samples': 20752320, 'steps': 108084, 'loss/train': 1.7621325254440308} 08/31/2021 08:51:08 - INFO - __main__ - Step 108086: {'lr': 9.259430537913085e-05, 'samples': 20752512, 'steps': 108085, 'loss/train': 1.0650627613067627} 08/31/2021 08:51:08 - INFO - __main__ - Step 108087: {'lr': 9.259018259962727e-05, 'samples': 20752704, 'steps': 108086, 'loss/train': 0.07490114122629166} 08/31/2021 08:51:10 - INFO - __main__ - Step 108088: {'lr': 9.258605989104999e-05, 'samples': 20752896, 'steps': 108087, 'loss/train': 1.1999022960662842} 08/31/2021 08:51:11 - INFO - __main__ - Step 108089: {'lr': 9.258193725340103e-05, 'samples': 20753088, 'steps': 108088, 'loss/train': 1.5602881908416748} 08/31/2021 08:51:11 - INFO - __main__ - Step 108090: {'lr': 9.257781468668222e-05, 'samples': 20753280, 'steps': 108089, 'loss/train': 1.482665777206421} 08/31/2021 08:51:12 - INFO - __main__ - Step 108091: {'lr': 9.25736921908954e-05, 'samples': 20753472, 'steps': 108090, 'loss/train': 0.9434956312179565} 08/31/2021 08:51:12 - INFO - __main__ - Step 108092: {'lr': 9.256956976604244e-05, 'samples': 20753664, 'steps': 108091, 'loss/train': 1.0549821853637695} 08/31/2021 08:51:12 - INFO - __main__ - Step 108093: {'lr': 9.256544741212524e-05, 'samples': 20753856, 'steps': 108092, 'loss/train': 0.31501448154449463} 08/31/2021 08:51:13 - INFO - __main__ - Step 108094: {'lr': 9.256132512914558e-05, 'samples': 20754048, 'steps': 108093, 'loss/train': 0.25216442346572876} 08/31/2021 08:51:15 - INFO - __main__ - Step 108095: {'lr': 9.25572029171054e-05, 'samples': 20754240, 'steps': 108094, 'loss/train': 0.27349093556404114} 08/31/2021 08:51:16 - INFO - __main__ - Step 108096: {'lr': 9.255308077600647e-05, 'samples': 20754432, 'steps': 108095, 'loss/train': 1.156050682067871} 08/31/2021 08:51:16 - INFO - __main__ - Step 108097: {'lr': 9.254895870585073e-05, 'samples': 20754624, 'steps': 108096, 'loss/train': 1.6610502004623413} 08/31/2021 08:51:16 - INFO - __main__ - Step 108098: {'lr': 9.254483670663997e-05, 'samples': 20754816, 'steps': 108097, 'loss/train': 1.5401893854141235} 08/31/2021 08:51:17 - INFO - __main__ - Step 108099: {'lr': 9.254071477837609e-05, 'samples': 20755008, 'steps': 108098, 'loss/train': 1.2416446208953857} 08/31/2021 08:51:17 - INFO - __main__ - Step 108100: {'lr': 9.253659292106092e-05, 'samples': 20755200, 'steps': 108099, 'loss/train': 1.3059604167938232} 08/31/2021 08:51:19 - INFO - __main__ - Step 108101: {'lr': 9.253247113469646e-05, 'samples': 20755392, 'steps': 108100, 'loss/train': 1.067229151725769} 08/31/2021 08:51:19 - INFO - __main__ - Step 108102: {'lr': 9.252834941928431e-05, 'samples': 20755584, 'steps': 108101, 'loss/train': 0.5775083899497986} 08/31/2021 08:51:19 - INFO - __main__ - Step 108103: {'lr': 9.252422777482646e-05, 'samples': 20755776, 'steps': 108102, 'loss/train': 1.965337872505188} 08/31/2021 08:51:20 - INFO - __main__ - Step 108104: {'lr': 9.252010620132478e-05, 'samples': 20755968, 'steps': 108103, 'loss/train': 0.9111270308494568} 08/31/2021 08:51:20 - INFO - __main__ - Step 108105: {'lr': 9.251598469878111e-05, 'samples': 20756160, 'steps': 108104, 'loss/train': 0.583582878112793} 08/31/2021 08:51:22 - INFO - __main__ - Step 108106: {'lr': 9.251186326719729e-05, 'samples': 20756352, 'steps': 108105, 'loss/train': 0.9304945468902588} 08/31/2021 08:51:23 - INFO - __main__ - Step 108107: {'lr': 9.250774190657521e-05, 'samples': 20756544, 'steps': 108106, 'loss/train': 1.5538917779922485} 08/31/2021 08:51:23 - INFO - __main__ - Step 108108: {'lr': 9.25036206169167e-05, 'samples': 20756736, 'steps': 108107, 'loss/train': 1.6185643672943115} 08/31/2021 08:51:23 - INFO - __main__ - Step 108109: {'lr': 9.249949939822363e-05, 'samples': 20756928, 'steps': 108108, 'loss/train': 0.017290664836764336} 08/31/2021 08:51:24 - INFO - __main__ - Step 108110: {'lr': 9.249537825049786e-05, 'samples': 20757120, 'steps': 108109, 'loss/train': 0.016979772597551346} 08/31/2021 08:51:24 - INFO - __main__ - Step 108111: {'lr': 9.249125717374124e-05, 'samples': 20757312, 'steps': 108110, 'loss/train': 1.2955846786499023} 08/31/2021 08:51:25 - INFO - __main__ - Step 108112: {'lr': 9.248713616795562e-05, 'samples': 20757504, 'steps': 108111, 'loss/train': 1.0524705648422241} 08/31/2021 08:51:26 - INFO - __main__ - Step 108113: {'lr': 9.24830152331429e-05, 'samples': 20757696, 'steps': 108112, 'loss/train': 1.670881748199463} 08/31/2021 08:51:26 - INFO - __main__ - Step 108114: {'lr': 9.247889436930495e-05, 'samples': 20757888, 'steps': 108113, 'loss/train': 0.8638481497764587} 08/31/2021 08:51:27 - INFO - __main__ - Step 108115: {'lr': 9.247477357644351e-05, 'samples': 20758080, 'steps': 108114, 'loss/train': 1.1110460758209229} 08/31/2021 08:51:27 - INFO - __main__ - Step 108116: {'lr': 9.247065285456049e-05, 'samples': 20758272, 'steps': 108115, 'loss/train': 0.8299546837806702} 08/31/2021 08:51:27 - INFO - __main__ - Step 108117: {'lr': 9.246653220365778e-05, 'samples': 20758464, 'steps': 108116, 'loss/train': 1.8416175842285156} 08/31/2021 08:51:29 - INFO - __main__ - Step 108118: {'lr': 9.246241162373722e-05, 'samples': 20758656, 'steps': 108117, 'loss/train': 0.6021884679794312} 08/31/2021 08:51:29 - INFO - __main__ - Step 108119: {'lr': 9.245829111480067e-05, 'samples': 20758848, 'steps': 108118, 'loss/train': 1.1761680841445923} 08/31/2021 08:51:30 - INFO - __main__ - Step 108120: {'lr': 9.245417067684997e-05, 'samples': 20759040, 'steps': 108119, 'loss/train': 0.8257330060005188} 08/31/2021 08:51:30 - INFO - __main__ - Step 108121: {'lr': 9.245005030988699e-05, 'samples': 20759232, 'steps': 108120, 'loss/train': 0.9062073826789856} 08/31/2021 08:51:30 - INFO - __main__ - Step 108122: {'lr': 9.24459300139136e-05, 'samples': 20759424, 'steps': 108121, 'loss/train': 1.0434471368789673} 08/31/2021 08:51:32 - INFO - __main__ - Step 108123: {'lr': 9.244180978893163e-05, 'samples': 20759616, 'steps': 108122, 'loss/train': 1.1606284379959106} 08/31/2021 08:51:33 - INFO - __main__ - Step 108124: {'lr': 9.243768963494295e-05, 'samples': 20759808, 'steps': 108123, 'loss/train': 1.5544872283935547} 08/31/2021 08:51:33 - INFO - __main__ - Step 108125: {'lr': 9.243356955194943e-05, 'samples': 20760000, 'steps': 108124, 'loss/train': 0.7642537951469421} 08/31/2021 08:51:33 - INFO - __main__ - Step 108126: {'lr': 9.242944953995289e-05, 'samples': 20760192, 'steps': 108125, 'loss/train': 0.34194785356521606} 08/31/2021 08:51:34 - INFO - __main__ - Step 108127: {'lr': 9.242532959895522e-05, 'samples': 20760384, 'steps': 108126, 'loss/train': 1.0201454162597656} 08/31/2021 08:51:35 - INFO - __main__ - Step 108128: {'lr': 9.242120972895835e-05, 'samples': 20760576, 'steps': 108127, 'loss/train': 0.742986261844635} 08/31/2021 08:51:36 - INFO - __main__ - Step 108129: {'lr': 9.241708992996398e-05, 'samples': 20760768, 'steps': 108128, 'loss/train': 1.3297370672225952} 08/31/2021 08:51:36 - INFO - __main__ - Step 108130: {'lr': 9.241297020197401e-05, 'samples': 20760960, 'steps': 108129, 'loss/train': 2.285006284713745} 08/31/2021 08:51:36 - INFO - __main__ - Step 108131: {'lr': 9.240885054499034e-05, 'samples': 20761152, 'steps': 108130, 'loss/train': 1.0379682779312134} 08/31/2021 08:51:37 - INFO - __main__ - Step 108132: {'lr': 9.240473095901481e-05, 'samples': 20761344, 'steps': 108131, 'loss/train': 1.0383861064910889} 08/31/2021 08:51:38 - INFO - __main__ - Step 108133: {'lr': 9.240061144404926e-05, 'samples': 20761536, 'steps': 108132, 'loss/train': 0.5058023929595947} 08/31/2021 08:51:39 - INFO - __main__ - Step 108134: {'lr': 9.239649200009559e-05, 'samples': 20761728, 'steps': 108133, 'loss/train': 1.1419326066970825} 08/31/2021 08:51:39 - INFO - __main__ - Step 108135: {'lr': 9.23923726271556e-05, 'samples': 20761920, 'steps': 108134, 'loss/train': 0.777153730392456} 08/31/2021 08:51:39 - INFO - __main__ - Step 108136: {'lr': 9.23882533252312e-05, 'samples': 20762112, 'steps': 108135, 'loss/train': 1.425330400466919} 08/31/2021 08:51:40 - INFO - __main__ - Step 108137: {'lr': 9.238413409432423e-05, 'samples': 20762304, 'steps': 108136, 'loss/train': 0.7391394376754761} 08/31/2021 08:51:40 - INFO - __main__ - Step 108138: {'lr': 9.23800149344365e-05, 'samples': 20762496, 'steps': 108137, 'loss/train': 1.3791236877441406} 08/31/2021 08:51:42 - INFO - __main__ - Step 108139: {'lr': 9.237589584556994e-05, 'samples': 20762688, 'steps': 108138, 'loss/train': 0.6978230476379395} 08/31/2021 08:51:42 - INFO - __main__ - Step 108140: {'lr': 9.237177682772635e-05, 'samples': 20762880, 'steps': 108139, 'loss/train': 1.2162513732910156} 08/31/2021 08:51:42 - INFO - __main__ - Step 108141: {'lr': 9.236765788090767e-05, 'samples': 20763072, 'steps': 108140, 'loss/train': 1.7614705562591553} 08/31/2021 08:51:43 - INFO - __main__ - Step 108142: {'lr': 9.236353900511563e-05, 'samples': 20763264, 'steps': 108141, 'loss/train': 0.8551150560379028} 08/31/2021 08:51:43 - INFO - __main__ - Step 108143: {'lr': 9.235942020035215e-05, 'samples': 20763456, 'steps': 108142, 'loss/train': 1.544439673423767} 08/31/2021 08:51:45 - INFO - __main__ - Step 108144: {'lr': 9.235530146661908e-05, 'samples': 20763648, 'steps': 108143, 'loss/train': 1.5610053539276123} 08/31/2021 08:51:45 - INFO - __main__ - Step 108145: {'lr': 9.235118280391827e-05, 'samples': 20763840, 'steps': 108144, 'loss/train': 0.5537392497062683} 08/31/2021 08:51:45 - INFO - __main__ - Step 108146: {'lr': 9.234706421225158e-05, 'samples': 20764032, 'steps': 108145, 'loss/train': 1.2735447883605957} 08/31/2021 08:51:46 - INFO - __main__ - Step 108147: {'lr': 9.234294569162088e-05, 'samples': 20764224, 'steps': 108146, 'loss/train': 1.2000536918640137} 08/31/2021 08:51:46 - INFO - __main__ - Step 108148: {'lr': 9.233882724202802e-05, 'samples': 20764416, 'steps': 108147, 'loss/train': 1.1174616813659668} 08/31/2021 08:51:48 - INFO - __main__ - Step 108149: {'lr': 9.233470886347484e-05, 'samples': 20764608, 'steps': 108148, 'loss/train': 0.9998771548271179} 08/31/2021 08:51:48 - INFO - __main__ - Step 108150: {'lr': 9.233059055596321e-05, 'samples': 20764800, 'steps': 108149, 'loss/train': 1.0614959001541138} 08/31/2021 08:51:48 - INFO - __main__ - Step 108151: {'lr': 9.232647231949501e-05, 'samples': 20764992, 'steps': 108150, 'loss/train': 0.893125057220459} 08/31/2021 08:51:49 - INFO - __main__ - Step 108152: {'lr': 9.232235415407204e-05, 'samples': 20765184, 'steps': 108151, 'loss/train': 1.4130773544311523} 08/31/2021 08:51:49 - INFO - __main__ - Step 108153: {'lr': 9.23182360596962e-05, 'samples': 20765376, 'steps': 108152, 'loss/train': 1.235729694366455} 08/31/2021 08:51:51 - INFO - __main__ - Step 108154: {'lr': 9.23141180363693e-05, 'samples': 20765568, 'steps': 108153, 'loss/train': 1.1036858558654785} 08/31/2021 08:51:52 - INFO - __main__ - Step 108155: {'lr': 9.231000008409332e-05, 'samples': 20765760, 'steps': 108154, 'loss/train': 1.3101621866226196} 08/31/2021 08:51:52 - INFO - __main__ - Step 108156: {'lr': 9.230588220286995e-05, 'samples': 20765952, 'steps': 108155, 'loss/train': 1.3652257919311523} 08/31/2021 08:51:52 - INFO - __main__ - Step 108157: {'lr': 9.230176439270111e-05, 'samples': 20766144, 'steps': 108156, 'loss/train': 0.666738748550415} 08/31/2021 08:51:53 - INFO - __main__ - Step 108158: {'lr': 9.229764665358867e-05, 'samples': 20766336, 'steps': 108157, 'loss/train': 0.7786694765090942} 08/31/2021 08:51:54 - INFO - __main__ - Step 108159: {'lr': 9.229352898553447e-05, 'samples': 20766528, 'steps': 108158, 'loss/train': 0.9236804842948914} 08/31/2021 08:51:55 - INFO - __main__ - Step 108160: {'lr': 9.228941138854039e-05, 'samples': 20766720, 'steps': 108159, 'loss/train': 0.3390201926231384} 08/31/2021 08:51:55 - INFO - __main__ - Step 108161: {'lr': 9.228529386260823e-05, 'samples': 20766912, 'steps': 108160, 'loss/train': 0.6293671727180481} 08/31/2021 08:51:55 - INFO - __main__ - Step 108162: {'lr': 9.228117640773989e-05, 'samples': 20767104, 'steps': 108161, 'loss/train': 0.9399939775466919} 08/31/2021 08:51:56 - INFO - __main__ - Step 108163: {'lr': 9.227705902393724e-05, 'samples': 20767296, 'steps': 108162, 'loss/train': 1.5821491479873657} 08/31/2021 08:51:57 - INFO - __main__ - Step 108164: {'lr': 9.22729417112021e-05, 'samples': 20767488, 'steps': 108163, 'loss/train': 1.1565021276474} 08/31/2021 08:51:58 - INFO - __main__ - Step 108165: {'lr': 9.226882446953636e-05, 'samples': 20767680, 'steps': 108164, 'loss/train': 1.5249614715576172} 08/31/2021 08:51:58 - INFO - __main__ - Step 108166: {'lr': 9.226470729894182e-05, 'samples': 20767872, 'steps': 108165, 'loss/train': 1.3299129009246826} 08/31/2021 08:51:58 - INFO - __main__ - Step 108167: {'lr': 9.22605901994204e-05, 'samples': 20768064, 'steps': 108166, 'loss/train': 1.5577480792999268} 08/31/2021 08:51:59 - INFO - __main__ - Step 108168: {'lr': 9.225647317097399e-05, 'samples': 20768256, 'steps': 108167, 'loss/train': 1.5112876892089844} 08/31/2021 08:51:59 - INFO - __main__ - Step 108169: {'lr': 9.225235621360428e-05, 'samples': 20768448, 'steps': 108168, 'loss/train': 0.8389723300933838} 08/31/2021 08:52:01 - INFO - __main__ - Step 108170: {'lr': 9.224823932731325e-05, 'samples': 20768640, 'steps': 108169, 'loss/train': 1.2567038536071777} 08/31/2021 08:52:01 - INFO - __main__ - Step 108171: {'lr': 9.224412251210274e-05, 'samples': 20768832, 'steps': 108170, 'loss/train': 1.4185339212417603} 08/31/2021 08:52:02 - INFO - __main__ - Step 108172: {'lr': 9.224000576797456e-05, 'samples': 20769024, 'steps': 108171, 'loss/train': 0.9544657468795776} 08/31/2021 08:52:02 - INFO - __main__ - Step 108173: {'lr': 9.223588909493061e-05, 'samples': 20769216, 'steps': 108172, 'loss/train': 1.6177979707717896} 08/31/2021 08:52:02 - INFO - __main__ - Step 108174: {'lr': 9.223177249297274e-05, 'samples': 20769408, 'steps': 108173, 'loss/train': 1.0746467113494873} 08/31/2021 08:52:04 - INFO - __main__ - Step 108175: {'lr': 9.22276559621028e-05, 'samples': 20769600, 'steps': 108174, 'loss/train': 1.2925227880477905} 08/31/2021 08:52:05 - INFO - __main__ - Step 108176: {'lr': 9.222353950232265e-05, 'samples': 20769792, 'steps': 108175, 'loss/train': 1.3597239255905151} 08/31/2021 08:52:05 - INFO - __main__ - Step 108177: {'lr': 9.221942311363413e-05, 'samples': 20769984, 'steps': 108176, 'loss/train': 0.9371404051780701} 08/31/2021 08:52:05 - INFO - __main__ - Step 108178: {'lr': 9.221530679603909e-05, 'samples': 20770176, 'steps': 108177, 'loss/train': 1.212398648262024} 08/31/2021 08:52:06 - INFO - __main__ - Step 108179: {'lr': 9.221119054953942e-05, 'samples': 20770368, 'steps': 108178, 'loss/train': 0.9339491128921509} 08/31/2021 08:52:06 - INFO - __main__ - Step 108180: {'lr': 9.220707437413694e-05, 'samples': 20770560, 'steps': 108179, 'loss/train': 0.017787091434001923} 08/31/2021 08:52:08 - INFO - __main__ - Step 108181: {'lr': 9.220295826983352e-05, 'samples': 20770752, 'steps': 108180, 'loss/train': 0.0688202977180481} 08/31/2021 08:52:08 - INFO - __main__ - Step 108182: {'lr': 9.219884223663108e-05, 'samples': 20770944, 'steps': 108181, 'loss/train': 1.576974868774414} 08/31/2021 08:52:08 - INFO - __main__ - Step 108183: {'lr': 9.219472627453135e-05, 'samples': 20771136, 'steps': 108182, 'loss/train': 0.7594858407974243} 08/31/2021 08:52:09 - INFO - __main__ - Step 108184: {'lr': 9.219061038353623e-05, 'samples': 20771328, 'steps': 108183, 'loss/train': 0.9046703577041626} 08/31/2021 08:52:09 - INFO - __main__ - Step 108185: {'lr': 9.218649456364758e-05, 'samples': 20771520, 'steps': 108184, 'loss/train': 0.9443342685699463} 08/31/2021 08:52:11 - INFO - __main__ - Step 108186: {'lr': 9.218237881486727e-05, 'samples': 20771712, 'steps': 108185, 'loss/train': 1.259242296218872} 08/31/2021 08:52:11 - INFO - __main__ - Step 108187: {'lr': 9.217826313719716e-05, 'samples': 20771904, 'steps': 108186, 'loss/train': 0.13561159372329712} 08/31/2021 08:52:11 - INFO - __main__ - Step 108188: {'lr': 9.217414753063905e-05, 'samples': 20772096, 'steps': 108187, 'loss/train': 1.3412941694259644} 08/31/2021 08:52:12 - INFO - __main__ - Step 108189: {'lr': 9.217003199519486e-05, 'samples': 20772288, 'steps': 108188, 'loss/train': 1.2481895685195923} 08/31/2021 08:52:12 - INFO - __main__ - Step 108190: {'lr': 9.216591653086643e-05, 'samples': 20772480, 'steps': 108189, 'loss/train': 1.3747940063476562} 08/31/2021 08:52:14 - INFO - __main__ - Step 108191: {'lr': 9.216180113765556e-05, 'samples': 20772672, 'steps': 108190, 'loss/train': 1.1555067300796509} 08/31/2021 08:52:14 - INFO - __main__ - Step 108192: {'lr': 9.215768581556419e-05, 'samples': 20772864, 'steps': 108191, 'loss/train': 1.1795275211334229} 08/31/2021 08:52:15 - INFO - __main__ - Step 108193: {'lr': 9.215357056459412e-05, 'samples': 20773056, 'steps': 108192, 'loss/train': 1.0621923208236694} 08/31/2021 08:52:15 - INFO - __main__ - Step 108194: {'lr': 9.21494553847472e-05, 'samples': 20773248, 'steps': 108193, 'loss/train': 0.9957098364830017} 08/31/2021 08:52:15 - INFO - __main__ - Step 108195: {'lr': 9.21453402760254e-05, 'samples': 20773440, 'steps': 108194, 'loss/train': 0.4742867946624756} 08/31/2021 08:52:16 - INFO - __main__ - Step 108196: {'lr': 9.214122523843035e-05, 'samples': 20773632, 'steps': 108195, 'loss/train': 0.7629415988922119} 08/31/2021 08:52:17 - INFO - __main__ - Step 108197: {'lr': 9.213711027196409e-05, 'samples': 20773824, 'steps': 108196, 'loss/train': 0.018597479909658432} 08/31/2021 08:52:18 - INFO - __main__ - Step 108198: {'lr': 9.213299537662836e-05, 'samples': 20774016, 'steps': 108197, 'loss/train': 1.4444125890731812} 08/31/2021 08:52:18 - INFO - __main__ - Step 108199: {'lr': 9.21288805524251e-05, 'samples': 20774208, 'steps': 108198, 'loss/train': 1.4751101732254028} 08/31/2021 08:52:18 - INFO - __main__ - Step 108200: {'lr': 9.212476579935611e-05, 'samples': 20774400, 'steps': 108199, 'loss/train': 0.2932188808917999} 08/31/2021 08:52:19 - INFO - __main__ - Step 108201: {'lr': 9.212065111742326e-05, 'samples': 20774592, 'steps': 108200, 'loss/train': 0.03445475175976753} 08/31/2021 08:52:19 - INFO - __main__ - Step 108202: {'lr': 9.211653650662844e-05, 'samples': 20774784, 'steps': 108201, 'loss/train': 0.6726464033126831} 08/31/2021 08:52:21 - INFO - __main__ - Step 108203: {'lr': 9.211242196697345e-05, 'samples': 20774976, 'steps': 108202, 'loss/train': 0.9605728983879089} 08/31/2021 08:52:21 - INFO - __main__ - Step 108204: {'lr': 9.210830749846016e-05, 'samples': 20775168, 'steps': 108203, 'loss/train': 1.2217421531677246} 08/31/2021 08:52:22 - INFO - __main__ - Step 108205: {'lr': 9.210419310109044e-05, 'samples': 20775360, 'steps': 108204, 'loss/train': 0.9903507828712463} 08/31/2021 08:52:22 - INFO - __main__ - Step 108206: {'lr': 9.210007877486615e-05, 'samples': 20775552, 'steps': 108205, 'loss/train': 1.7907785177230835} 08/31/2021 08:52:22 - INFO - __main__ - Step 108207: {'lr': 9.20959645197891e-05, 'samples': 20775744, 'steps': 108206, 'loss/train': 0.2356945276260376} 08/31/2021 08:52:24 - INFO - __main__ - Step 108208: {'lr': 9.209185033586129e-05, 'samples': 20775936, 'steps': 108207, 'loss/train': 1.5009702444076538} 08/31/2021 08:52:25 - INFO - __main__ - Step 108209: {'lr': 9.208773622308433e-05, 'samples': 20776128, 'steps': 108208, 'loss/train': 1.437044382095337} 08/31/2021 08:52:25 - INFO - __main__ - Step 108210: {'lr': 9.208362218146021e-05, 'samples': 20776320, 'steps': 108209, 'loss/train': 0.8234527707099915} 08/31/2021 08:52:26 - INFO - __main__ - Step 108211: {'lr': 9.207950821099078e-05, 'samples': 20776512, 'steps': 108210, 'loss/train': 1.2101032733917236} 08/31/2021 08:52:26 - INFO - __main__ - Step 108212: {'lr': 9.207539431167792e-05, 'samples': 20776704, 'steps': 108211, 'loss/train': 0.5732751488685608} 08/31/2021 08:52:27 - INFO - __main__ - Step 108213: {'lr': 9.207128048352339e-05, 'samples': 20776896, 'steps': 108212, 'loss/train': 1.8318572044372559} 08/31/2021 08:52:28 - INFO - __main__ - Step 108214: {'lr': 9.206716672652915e-05, 'samples': 20777088, 'steps': 108213, 'loss/train': 1.2880406379699707} 08/31/2021 08:52:28 - INFO - __main__ - Step 108215: {'lr': 9.206305304069699e-05, 'samples': 20777280, 'steps': 108214, 'loss/train': 0.8813955187797546} 08/31/2021 08:52:29 - INFO - __main__ - Step 108216: {'lr': 9.205893942602878e-05, 'samples': 20777472, 'steps': 108215, 'loss/train': 0.4093852937221527} 08/31/2021 08:52:29 - INFO - __main__ - Step 108217: {'lr': 9.205482588252637e-05, 'samples': 20777664, 'steps': 108216, 'loss/train': 1.3227516412734985} 08/31/2021 08:52:31 - INFO - __main__ - Step 108218: {'lr': 9.205071241019164e-05, 'samples': 20777856, 'steps': 108217, 'loss/train': 0.6217944025993347} 08/31/2021 08:52:31 - INFO - __main__ - Step 108219: {'lr': 9.20465990090264e-05, 'samples': 20778048, 'steps': 108218, 'loss/train': 1.243157982826233} 08/31/2021 08:52:32 - INFO - __main__ - Step 108220: {'lr': 9.204248567903254e-05, 'samples': 20778240, 'steps': 108219, 'loss/train': 0.11337799578905106} 08/31/2021 08:52:32 - INFO - __main__ - Step 108221: {'lr': 9.203837242021187e-05, 'samples': 20778432, 'steps': 108220, 'loss/train': 1.2512041330337524} 08/31/2021 08:52:32 - INFO - __main__ - Step 108222: {'lr': 9.20342592325664e-05, 'samples': 20778624, 'steps': 108221, 'loss/train': 1.5189722776412964} 08/31/2021 08:52:33 - INFO - __main__ - Step 108223: {'lr': 9.203014611609772e-05, 'samples': 20778816, 'steps': 108222, 'loss/train': 1.1273329257965088} 08/31/2021 08:52:34 - INFO - __main__ - Step 108224: {'lr': 9.202603307080787e-05, 'samples': 20779008, 'steps': 108223, 'loss/train': 0.544284462928772} 08/31/2021 08:52:35 - INFO - __main__ - Step 108225: {'lr': 9.202192009669863e-05, 'samples': 20779200, 'steps': 108224, 'loss/train': 1.263524055480957} 08/31/2021 08:52:35 - INFO - __main__ - Step 108226: {'lr': 9.201780719377186e-05, 'samples': 20779392, 'steps': 108225, 'loss/train': 1.4281550645828247} 08/31/2021 08:52:36 - INFO - __main__ - Step 108227: {'lr': 9.201369436202944e-05, 'samples': 20779584, 'steps': 108226, 'loss/train': 1.3580127954483032} 08/31/2021 08:52:36 - INFO - __main__ - Step 108228: {'lr': 9.200958160147322e-05, 'samples': 20779776, 'steps': 108227, 'loss/train': 0.6948870420455933} 08/31/2021 08:52:38 - INFO - __main__ - Step 108229: {'lr': 9.200546891210504e-05, 'samples': 20779968, 'steps': 108228, 'loss/train': 1.2349834442138672} 08/31/2021 08:52:38 - INFO - __main__ - Step 108230: {'lr': 9.200135629392675e-05, 'samples': 20780160, 'steps': 108229, 'loss/train': 1.7031577825546265} 08/31/2021 08:52:38 - INFO - __main__ - Step 108231: {'lr': 9.199724374694021e-05, 'samples': 20780352, 'steps': 108230, 'loss/train': 0.9682494401931763} 08/31/2021 08:52:39 - INFO - __main__ - Step 108232: {'lr': 9.199313127114728e-05, 'samples': 20780544, 'steps': 108231, 'loss/train': 1.0748162269592285} 08/31/2021 08:52:39 - INFO - __main__ - Step 108233: {'lr': 9.198901886654982e-05, 'samples': 20780736, 'steps': 108232, 'loss/train': 0.026221157982945442} 08/31/2021 08:52:40 - INFO - __main__ - Step 108234: {'lr': 9.198490653314965e-05, 'samples': 20780928, 'steps': 108233, 'loss/train': 0.7681716680526733} 08/31/2021 08:52:41 - INFO - __main__ - Step 108235: {'lr': 9.198079427094872e-05, 'samples': 20781120, 'steps': 108234, 'loss/train': 1.2696406841278076} 08/31/2021 08:52:41 - INFO - __main__ - Step 108236: {'lr': 9.197668207994874e-05, 'samples': 20781312, 'steps': 108235, 'loss/train': 0.9823046922683716} 08/31/2021 08:52:42 - INFO - __main__ - Step 108237: {'lr': 9.197256996015163e-05, 'samples': 20781504, 'steps': 108236, 'loss/train': 1.5169620513916016} 08/31/2021 08:52:42 - INFO - __main__ - Step 108238: {'lr': 9.196845791155923e-05, 'samples': 20781696, 'steps': 108237, 'loss/train': 1.5201176404953003} 08/31/2021 08:52:43 - INFO - __main__ - Step 108239: {'lr': 9.196434593417341e-05, 'samples': 20781888, 'steps': 108238, 'loss/train': 0.8362079858779907} 08/31/2021 08:52:44 - INFO - __main__ - Step 108240: {'lr': 9.196023402799603e-05, 'samples': 20782080, 'steps': 108239, 'loss/train': 1.4293289184570312} 08/31/2021 08:52:44 - INFO - __main__ - Step 108241: {'lr': 9.19561221930289e-05, 'samples': 20782272, 'steps': 108240, 'loss/train': 1.484302282333374} 08/31/2021 08:52:45 - INFO - __main__ - Step 108242: {'lr': 9.195201042927393e-05, 'samples': 20782464, 'steps': 108241, 'loss/train': 1.3968604803085327} 08/31/2021 08:52:45 - INFO - __main__ - Step 108243: {'lr': 9.194789873673292e-05, 'samples': 20782656, 'steps': 108242, 'loss/train': 0.18750937283039093} 08/31/2021 08:52:46 - INFO - __main__ - Step 108244: {'lr': 9.194378711540776e-05, 'samples': 20782848, 'steps': 108243, 'loss/train': 1.3573739528656006} 08/31/2021 08:52:47 - INFO - __main__ - Step 108245: {'lr': 9.19396755653003e-05, 'samples': 20783040, 'steps': 108244, 'loss/train': 2.446141004562378} 08/31/2021 08:52:47 - INFO - __main__ - Step 108246: {'lr': 9.193556408641238e-05, 'samples': 20783232, 'steps': 108245, 'loss/train': 1.0798202753067017} 08/31/2021 08:52:48 - INFO - __main__ - Step 108247: {'lr': 9.193145267874583e-05, 'samples': 20783424, 'steps': 108246, 'loss/train': 1.0330449342727661} 08/31/2021 08:52:48 - INFO - __main__ - Step 108248: {'lr': 9.192734134230257e-05, 'samples': 20783616, 'steps': 108247, 'loss/train': 1.1665289402008057} 08/31/2021 08:52:48 - INFO - __main__ - Step 108249: {'lr': 9.192323007708448e-05, 'samples': 20783808, 'steps': 108248, 'loss/train': 1.3853315114974976} 08/31/2021 08:52:50 - INFO - __main__ - Step 108250: {'lr': 9.191911888309323e-05, 'samples': 20784000, 'steps': 108249, 'loss/train': 1.2026525735855103} 08/31/2021 08:52:51 - INFO - __main__ - Step 108251: {'lr': 9.191500776033082e-05, 'samples': 20784192, 'steps': 108250, 'loss/train': 1.442879319190979} 08/31/2021 08:52:51 - INFO - __main__ - Step 108252: {'lr': 9.191089670879907e-05, 'samples': 20784384, 'steps': 108251, 'loss/train': 1.4683858156204224} 08/31/2021 08:52:51 - INFO - __main__ - Step 108253: {'lr': 9.190678572849981e-05, 'samples': 20784576, 'steps': 108252, 'loss/train': 1.4073952436447144} 08/31/2021 08:52:52 - INFO - __main__ - Step 108254: {'lr': 9.19026748194349e-05, 'samples': 20784768, 'steps': 108253, 'loss/train': 0.8556252121925354} 08/31/2021 08:52:52 - INFO - __main__ - Step 108255: {'lr': 9.189856398160623e-05, 'samples': 20784960, 'steps': 108254, 'loss/train': 4.346175193786621} 08/31/2021 08:52:54 - INFO - __main__ - Step 108256: {'lr': 9.189445321501563e-05, 'samples': 20785152, 'steps': 108255, 'loss/train': 4.376315593719482} 08/31/2021 08:52:54 - INFO - __main__ - Step 108257: {'lr': 9.189034251966494e-05, 'samples': 20785344, 'steps': 108256, 'loss/train': 1.1910191774368286} 08/31/2021 08:52:54 - INFO - __main__ - Step 108258: {'lr': 9.188623189555603e-05, 'samples': 20785536, 'steps': 108257, 'loss/train': 1.0741150379180908} 08/31/2021 08:52:55 - INFO - __main__ - Step 108259: {'lr': 9.188212134269075e-05, 'samples': 20785728, 'steps': 108258, 'loss/train': 1.0845904350280762} 08/31/2021 08:52:55 - INFO - __main__ - Step 108260: {'lr': 9.187801086107092e-05, 'samples': 20785920, 'steps': 108259, 'loss/train': 0.5792633891105652} 08/31/2021 08:52:57 - INFO - __main__ - Step 108261: {'lr': 9.187390045069844e-05, 'samples': 20786112, 'steps': 108260, 'loss/train': 0.7499101161956787} 08/31/2021 08:52:58 - INFO - __main__ - Step 108262: {'lr': 9.18697901115752e-05, 'samples': 20786304, 'steps': 108261, 'loss/train': 1.2046655416488647} 08/31/2021 08:52:58 - INFO - __main__ - Step 108263: {'lr': 9.186567984370294e-05, 'samples': 20786496, 'steps': 108262, 'loss/train': 1.1246625185012817} 08/31/2021 08:52:58 - INFO - __main__ - Step 108264: {'lr': 9.186156964708357e-05, 'samples': 20786688, 'steps': 108263, 'loss/train': 0.7311848402023315} 08/31/2021 08:52:59 - INFO - __main__ - Step 108265: {'lr': 9.185745952171889e-05, 'samples': 20786880, 'steps': 108264, 'loss/train': 1.2963491678237915} 08/31/2021 08:53:00 - INFO - __main__ - Step 108266: {'lr': 9.185334946761084e-05, 'samples': 20787072, 'steps': 108265, 'loss/train': 0.9256336092948914} 08/31/2021 08:53:01 - INFO - __main__ - Step 108267: {'lr': 9.18492394847612e-05, 'samples': 20787264, 'steps': 108266, 'loss/train': 1.0062813758850098} 08/31/2021 08:53:01 - INFO - __main__ - Step 108268: {'lr': 9.184512957317187e-05, 'samples': 20787456, 'steps': 108267, 'loss/train': 1.2953883409500122} 08/31/2021 08:53:02 - INFO - __main__ - Step 108269: {'lr': 9.18410197328447e-05, 'samples': 20787648, 'steps': 108268, 'loss/train': 1.08655846118927} 08/31/2021 08:53:02 - INFO - __main__ - Step 108270: {'lr': 9.18369099637815e-05, 'samples': 20787840, 'steps': 108269, 'loss/train': 1.1913563013076782} 08/31/2021 08:53:04 - INFO - __main__ - Step 108271: {'lr': 9.183280026598415e-05, 'samples': 20788032, 'steps': 108270, 'loss/train': 0.025754308328032494} 08/31/2021 08:53:04 - INFO - __main__ - Step 108272: {'lr': 9.182869063945451e-05, 'samples': 20788224, 'steps': 108271, 'loss/train': 0.17758099734783173} 08/31/2021 08:53:05 - INFO - __main__ - Step 108273: {'lr': 9.182458108419441e-05, 'samples': 20788416, 'steps': 108272, 'loss/train': 0.04866969585418701} 08/31/2021 08:53:05 - INFO - __main__ - Step 108274: {'lr': 9.182047160020573e-05, 'samples': 20788608, 'steps': 108273, 'loss/train': 1.0269821882247925} 08/31/2021 08:53:05 - INFO - __main__ - Step 108275: {'lr': 9.181636218749029e-05, 'samples': 20788800, 'steps': 108274, 'loss/train': 1.1448955535888672} 08/31/2021 08:53:07 - INFO - __main__ - Step 108276: {'lr': 9.181225284605005e-05, 'samples': 20788992, 'steps': 108275, 'loss/train': 1.0868818759918213} 08/31/2021 08:53:08 - INFO - __main__ - Step 108277: {'lr': 9.180814357588668e-05, 'samples': 20789184, 'steps': 108276, 'loss/train': 1.1803689002990723} 08/31/2021 08:53:08 - INFO - __main__ - Step 108278: {'lr': 9.18040343770021e-05, 'samples': 20789376, 'steps': 108277, 'loss/train': 1.407547950744629} 08/31/2021 08:53:08 - INFO - __main__ - Step 108279: {'lr': 9.179992524939821e-05, 'samples': 20789568, 'steps': 108278, 'loss/train': 1.393271803855896} 08/31/2021 08:53:09 - INFO - __main__ - Step 108280: {'lr': 9.179581619307684e-05, 'samples': 20789760, 'steps': 108279, 'loss/train': 1.3215408325195312} 08/31/2021 08:53:09 - INFO - __main__ - Step 108281: {'lr': 9.179170720803981e-05, 'samples': 20789952, 'steps': 108280, 'loss/train': 1.5828076601028442} 08/31/2021 08:53:11 - INFO - __main__ - Step 108282: {'lr': 9.178759829428898e-05, 'samples': 20790144, 'steps': 108281, 'loss/train': 0.05103034898638725} 08/31/2021 08:53:11 - INFO - __main__ - Step 108283: {'lr': 9.178348945182624e-05, 'samples': 20790336, 'steps': 108282, 'loss/train': 0.14212697744369507} 08/31/2021 08:53:12 - INFO - __main__ - Step 108284: {'lr': 9.177938068065341e-05, 'samples': 20790528, 'steps': 108283, 'loss/train': 1.0677589178085327} 08/31/2021 08:53:12 - INFO - __main__ - Step 108285: {'lr': 9.177527198077237e-05, 'samples': 20790720, 'steps': 108284, 'loss/train': 1.43539559841156} 08/31/2021 08:53:12 - INFO - __main__ - Step 108286: {'lr': 9.177116335218494e-05, 'samples': 20790912, 'steps': 108285, 'loss/train': 0.7955344915390015} 08/31/2021 08:53:14 - INFO - __main__ - Step 108287: {'lr': 9.176705479489298e-05, 'samples': 20791104, 'steps': 108286, 'loss/train': 1.3339760303497314} 08/31/2021 08:53:14 - INFO - __main__ - Step 108288: {'lr': 9.176294630889842e-05, 'samples': 20791296, 'steps': 108287, 'loss/train': 0.8554761409759521} 08/31/2021 08:53:15 - INFO - __main__ - Step 108289: {'lr': 9.175883789420294e-05, 'samples': 20791488, 'steps': 108288, 'loss/train': 1.1003412008285522} 08/31/2021 08:53:15 - INFO - __main__ - Step 108290: {'lr': 9.175472955080852e-05, 'samples': 20791680, 'steps': 108289, 'loss/train': 0.8021849393844604} 08/31/2021 08:53:15 - INFO - __main__ - Step 108291: {'lr': 9.175062127871697e-05, 'samples': 20791872, 'steps': 108290, 'loss/train': 0.9662749171257019} 08/31/2021 08:53:16 - INFO - __main__ - Step 108292: {'lr': 9.174651307793014e-05, 'samples': 20792064, 'steps': 108291, 'loss/train': 1.0792628526687622} 08/31/2021 08:53:17 - INFO - __main__ - Step 108293: {'lr': 9.174240494844987e-05, 'samples': 20792256, 'steps': 108292, 'loss/train': 0.24021190404891968} 08/31/2021 08:53:18 - INFO - __main__ - Step 108294: {'lr': 9.173829689027805e-05, 'samples': 20792448, 'steps': 108293, 'loss/train': 0.48658621311187744} 08/31/2021 08:53:18 - INFO - __main__ - Step 108295: {'lr': 9.173418890341651e-05, 'samples': 20792640, 'steps': 108294, 'loss/train': 1.8055142164230347} 08/31/2021 08:53:18 - INFO - __main__ - Step 108296: {'lr': 9.173008098786712e-05, 'samples': 20792832, 'steps': 108295, 'loss/train': 0.9638709425926208} 08/31/2021 08:53:19 - INFO - __main__ - Step 108297: {'lr': 9.172597314363168e-05, 'samples': 20793024, 'steps': 108296, 'loss/train': 0.5822237133979797} 08/31/2021 08:53:20 - INFO - __main__ - Step 108298: {'lr': 9.172186537071217e-05, 'samples': 20793216, 'steps': 108297, 'loss/train': 0.8826703429222107} 08/31/2021 08:53:21 - INFO - __main__ - Step 108299: {'lr': 9.171775766911025e-05, 'samples': 20793408, 'steps': 108298, 'loss/train': 1.2136597633361816} 08/31/2021 08:53:21 - INFO - __main__ - Step 108300: {'lr': 9.17136500388279e-05, 'samples': 20793600, 'steps': 108299, 'loss/train': 1.019216537475586} 08/31/2021 08:53:21 - INFO - __main__ - Step 108301: {'lr': 9.170954247986691e-05, 'samples': 20793792, 'steps': 108300, 'loss/train': 1.2246779203414917} 08/31/2021 08:53:22 - INFO - __main__ - Step 108302: {'lr': 9.170543499222917e-05, 'samples': 20793984, 'steps': 108301, 'loss/train': 1.312106966972351} 08/31/2021 08:53:23 - INFO - __main__ - Step 108303: {'lr': 9.170132757591651e-05, 'samples': 20794176, 'steps': 108302, 'loss/train': 0.948315441608429} 08/31/2021 08:53:24 - INFO - __main__ - Step 108304: {'lr': 9.169722023093077e-05, 'samples': 20794368, 'steps': 108303, 'loss/train': 0.8200471997261047} 08/31/2021 08:53:24 - INFO - __main__ - Step 108305: {'lr': 9.169311295727387e-05, 'samples': 20794560, 'steps': 108304, 'loss/train': 1.2507092952728271} 08/31/2021 08:53:24 - INFO - __main__ - Step 108306: {'lr': 9.168900575494757e-05, 'samples': 20794752, 'steps': 108305, 'loss/train': 1.1403379440307617} 08/31/2021 08:53:25 - INFO - __main__ - Step 108307: {'lr': 9.168489862395377e-05, 'samples': 20794944, 'steps': 108306, 'loss/train': 1.5082465410232544} 08/31/2021 08:53:26 - INFO - __main__ - Step 108308: {'lr': 9.168079156429433e-05, 'samples': 20795136, 'steps': 108307, 'loss/train': 1.030645489692688} 08/31/2021 08:53:27 - INFO - __main__ - Step 108309: {'lr': 9.167668457597114e-05, 'samples': 20795328, 'steps': 108308, 'loss/train': 1.3604600429534912} 08/31/2021 08:53:27 - INFO - __main__ - Step 108310: {'lr': 9.16725776589859e-05, 'samples': 20795520, 'steps': 108309, 'loss/train': 0.6362448334693909} 08/31/2021 08:53:27 - INFO - __main__ - Step 108311: {'lr': 9.166847081334059e-05, 'samples': 20795712, 'steps': 108310, 'loss/train': 0.8243186473846436} 08/31/2021 08:53:28 - INFO - __main__ - Step 108312: {'lr': 9.1664364039037e-05, 'samples': 20795904, 'steps': 108311, 'loss/train': 1.6445032358169556} 08/31/2021 08:53:29 - INFO - __main__ - Step 108313: {'lr': 9.166025733607702e-05, 'samples': 20796096, 'steps': 108312, 'loss/train': 1.3242316246032715} 08/31/2021 08:53:30 - INFO - __main__ - Step 108314: {'lr': 9.165615070446248e-05, 'samples': 20796288, 'steps': 108313, 'loss/train': 1.5659406185150146} 08/31/2021 08:53:30 - INFO - __main__ - Step 108315: {'lr': 9.165204414419523e-05, 'samples': 20796480, 'steps': 108314, 'loss/train': 1.4813719987869263} 08/31/2021 08:53:31 - INFO - __main__ - Step 108316: {'lr': 9.164793765527712e-05, 'samples': 20796672, 'steps': 108315, 'loss/train': 1.2070900201797485} 08/31/2021 08:53:31 - INFO - __main__ - Step 108317: {'lr': 9.164383123771e-05, 'samples': 20796864, 'steps': 108316, 'loss/train': 0.6570805311203003} 08/31/2021 08:53:31 - INFO - __main__ - Step 108318: {'lr': 9.163972489149574e-05, 'samples': 20797056, 'steps': 108317, 'loss/train': 1.2665122747421265} 08/31/2021 08:53:33 - INFO - __main__ - Step 108319: {'lr': 9.163561861663619e-05, 'samples': 20797248, 'steps': 108318, 'loss/train': 0.03685281425714493} 08/31/2021 08:53:34 - INFO - __main__ - Step 108320: {'lr': 9.163151241313325e-05, 'samples': 20797440, 'steps': 108319, 'loss/train': 0.3211301565170288} 08/31/2021 08:53:34 - INFO - __main__ - Step 108321: {'lr': 9.162740628098862e-05, 'samples': 20797632, 'steps': 108320, 'loss/train': 1.2898502349853516} 08/31/2021 08:53:35 - INFO - __main__ - Step 108322: {'lr': 9.162330022020423e-05, 'samples': 20797824, 'steps': 108321, 'loss/train': 1.26219642162323} 08/31/2021 08:53:35 - INFO - __main__ - Step 108323: {'lr': 9.161919423078196e-05, 'samples': 20798016, 'steps': 108322, 'loss/train': 1.0248366594314575} 08/31/2021 08:53:35 - INFO - __main__ - Step 108324: {'lr': 9.161508831272364e-05, 'samples': 20798208, 'steps': 108323, 'loss/train': 0.7368125915527344} 08/31/2021 08:53:37 - INFO - __main__ - Step 108325: {'lr': 9.161098246603111e-05, 'samples': 20798400, 'steps': 108324, 'loss/train': 1.2559316158294678} 08/31/2021 08:53:37 - INFO - __main__ - Step 108326: {'lr': 9.160687669070623e-05, 'samples': 20798592, 'steps': 108325, 'loss/train': 1.0421377420425415} 08/31/2021 08:53:38 - INFO - __main__ - Step 108327: {'lr': 9.160277098675082e-05, 'samples': 20798784, 'steps': 108326, 'loss/train': 1.0439616441726685} 08/31/2021 08:53:38 - INFO - __main__ - Step 108328: {'lr': 9.159866535416678e-05, 'samples': 20798976, 'steps': 108327, 'loss/train': 1.1673411130905151} 08/31/2021 08:53:38 - INFO - __main__ - Step 108329: {'lr': 9.159455979295594e-05, 'samples': 20799168, 'steps': 108328, 'loss/train': 0.6638091802597046} 08/31/2021 08:53:40 - INFO - __main__ - Step 108330: {'lr': 9.159045430312013e-05, 'samples': 20799360, 'steps': 108329, 'loss/train': 0.8414220213890076} 08/31/2021 08:53:40 - INFO - __main__ - Step 108331: {'lr': 9.158634888466133e-05, 'samples': 20799552, 'steps': 108330, 'loss/train': 0.38820162415504456} 08/31/2021 08:53:41 - INFO - __main__ - Step 108332: {'lr': 9.158224353758115e-05, 'samples': 20799744, 'steps': 108331, 'loss/train': 0.9763069748878479} 08/31/2021 08:53:41 - INFO - __main__ - Step 108333: {'lr': 9.157813826188161e-05, 'samples': 20799936, 'steps': 108332, 'loss/train': 0.17748400568962097} 08/31/2021 08:53:41 - INFO - __main__ - Step 108334: {'lr': 9.157403305756451e-05, 'samples': 20800128, 'steps': 108333, 'loss/train': 1.494112253189087} 08/31/2021 08:53:43 - INFO - __main__ - Step 108335: {'lr': 9.156992792463167e-05, 'samples': 20800320, 'steps': 108334, 'loss/train': 1.0022305250167847} 08/31/2021 08:53:43 - INFO - __main__ - Step 108336: {'lr': 9.156582286308501e-05, 'samples': 20800512, 'steps': 108335, 'loss/train': 1.124377727508545} 08/31/2021 08:53:44 - INFO - __main__ - Step 108337: {'lr': 9.156171787292633e-05, 'samples': 20800704, 'steps': 108336, 'loss/train': 1.2298526763916016} 08/31/2021 08:53:44 - INFO - __main__ - Step 108338: {'lr': 9.155761295415751e-05, 'samples': 20800896, 'steps': 108337, 'loss/train': 1.0497866868972778} 08/31/2021 08:53:44 - INFO - __main__ - Step 108339: {'lr': 9.155350810678037e-05, 'samples': 20801088, 'steps': 108338, 'loss/train': 1.2809839248657227} 08/31/2021 08:53:46 - INFO - __main__ - Step 108340: {'lr': 9.154940333079678e-05, 'samples': 20801280, 'steps': 108339, 'loss/train': 0.9680335521697998} 08/31/2021 08:53:46 - INFO - __main__ - Step 108341: {'lr': 9.154529862620858e-05, 'samples': 20801472, 'steps': 108340, 'loss/train': 0.2787095904350281} 08/31/2021 08:53:47 - INFO - __main__ - Step 108342: {'lr': 9.154119399301764e-05, 'samples': 20801664, 'steps': 108341, 'loss/train': 1.1191339492797852} 08/31/2021 08:53:47 - INFO - __main__ - Step 108343: {'lr': 9.153708943122585e-05, 'samples': 20801856, 'steps': 108342, 'loss/train': 0.8882087469100952} 08/31/2021 08:53:47 - INFO - __main__ - Step 108344: {'lr': 9.153298494083492e-05, 'samples': 20802048, 'steps': 108343, 'loss/train': 2.9628820419311523} 08/31/2021 08:53:49 - INFO - __main__ - Step 108345: {'lr': 9.15288805218468e-05, 'samples': 20802240, 'steps': 108344, 'loss/train': 1.0843099355697632} 08/31/2021 08:53:49 - INFO - __main__ - Step 108346: {'lr': 9.152477617426333e-05, 'samples': 20802432, 'steps': 108345, 'loss/train': 1.242691159248352} 08/31/2021 08:53:50 - INFO - __main__ - Step 108347: {'lr': 9.152067189808633e-05, 'samples': 20802624, 'steps': 108346, 'loss/train': 0.8100740909576416} 08/31/2021 08:53:50 - INFO - __main__ - Step 108348: {'lr': 9.151656769331767e-05, 'samples': 20802816, 'steps': 108347, 'loss/train': 0.49435895681381226} 08/31/2021 08:53:50 - INFO - __main__ - Step 108349: {'lr': 9.15124635599592e-05, 'samples': 20803008, 'steps': 108348, 'loss/train': 1.2751272916793823} 08/31/2021 08:53:51 - INFO - __main__ - Step 108350: {'lr': 9.150835949801278e-05, 'samples': 20803200, 'steps': 108349, 'loss/train': 1.5036180019378662} 08/31/2021 08:53:52 - INFO - __main__ - Step 108351: {'lr': 9.150425550748023e-05, 'samples': 20803392, 'steps': 108350, 'loss/train': 1.4265128374099731} 08/31/2021 08:53:53 - INFO - __main__ - Step 108352: {'lr': 9.150015158836345e-05, 'samples': 20803584, 'steps': 108351, 'loss/train': 1.3105775117874146} 08/31/2021 08:53:53 - INFO - __main__ - Step 108353: {'lr': 9.149604774066422e-05, 'samples': 20803776, 'steps': 108352, 'loss/train': 0.9016819596290588} 08/31/2021 08:53:54 - INFO - __main__ - Step 108354: {'lr': 9.149194396438442e-05, 'samples': 20803968, 'steps': 108353, 'loss/train': 0.9177563786506653} 08/31/2021 08:53:54 - INFO - __main__ - Step 108355: {'lr': 9.148784025952594e-05, 'samples': 20804160, 'steps': 108354, 'loss/train': 0.94149249792099} 08/31/2021 08:53:55 - INFO - __main__ - Step 108356: {'lr': 9.148373662609067e-05, 'samples': 20804352, 'steps': 108355, 'loss/train': 1.5900354385375977} 08/31/2021 08:53:56 - INFO - __main__ - Step 108357: {'lr': 9.147963306408028e-05, 'samples': 20804544, 'steps': 108356, 'loss/train': 1.5671485662460327} 08/31/2021 08:53:56 - INFO - __main__ - Step 108358: {'lr': 9.147552957349672e-05, 'samples': 20804736, 'steps': 108357, 'loss/train': 1.8127371072769165} 08/31/2021 08:53:57 - INFO - __main__ - Step 108359: {'lr': 9.147142615434184e-05, 'samples': 20804928, 'steps': 108358, 'loss/train': 1.426079273223877} 08/31/2021 08:53:57 - INFO - __main__ - Step 108360: {'lr': 9.146732280661749e-05, 'samples': 20805120, 'steps': 108359, 'loss/train': 1.4327974319458008} 08/31/2021 08:53:58 - INFO - __main__ - Step 108361: {'lr': 9.146321953032555e-05, 'samples': 20805312, 'steps': 108360, 'loss/train': 0.6988500952720642} 08/31/2021 08:53:59 - INFO - __main__ - Step 108362: {'lr': 9.14591163254678e-05, 'samples': 20805504, 'steps': 108361, 'loss/train': 0.5535426139831543} 08/31/2021 08:53:59 - INFO - __main__ - Step 108363: {'lr': 9.145501319204613e-05, 'samples': 20805696, 'steps': 108362, 'loss/train': 1.5448862314224243} 08/31/2021 08:54:00 - INFO - __main__ - Step 108364: {'lr': 9.14509101300624e-05, 'samples': 20805888, 'steps': 108363, 'loss/train': 1.7536922693252563} 08/31/2021 08:54:00 - INFO - __main__ - Step 108365: {'lr': 9.144680713951845e-05, 'samples': 20806080, 'steps': 108364, 'loss/train': 0.5114242434501648} 08/31/2021 08:54:02 - INFO - __main__ - Step 108366: {'lr': 9.14427042204161e-05, 'samples': 20806272, 'steps': 108365, 'loss/train': 1.8568845987319946} 08/31/2021 08:54:02 - INFO - __main__ - Step 108367: {'lr': 9.143860137275723e-05, 'samples': 20806464, 'steps': 108366, 'loss/train': 1.9962159395217896} 08/31/2021 08:54:02 - INFO - __main__ - Step 108368: {'lr': 9.143449859654366e-05, 'samples': 20806656, 'steps': 108367, 'loss/train': 1.2664047479629517} 08/31/2021 08:54:03 - INFO - __main__ - Step 108369: {'lr': 9.143039589177728e-05, 'samples': 20806848, 'steps': 108368, 'loss/train': 1.0268774032592773} 08/31/2021 08:54:03 - INFO - __main__ - Step 108370: {'lr': 9.142629325846e-05, 'samples': 20807040, 'steps': 108369, 'loss/train': 0.9985572099685669} 08/31/2021 08:54:05 - INFO - __main__ - Step 108371: {'lr': 9.142219069659349e-05, 'samples': 20807232, 'steps': 108370, 'loss/train': 1.37344229221344} 08/31/2021 08:54:06 - INFO - __main__ - Step 108372: {'lr': 9.141808820617972e-05, 'samples': 20807424, 'steps': 108371, 'loss/train': 1.2155426740646362} 08/31/2021 08:54:06 - INFO - __main__ - Step 108373: {'lr': 9.141398578722049e-05, 'samples': 20807616, 'steps': 108372, 'loss/train': 0.953385055065155} 08/31/2021 08:54:06 - INFO - __main__ - Step 108374: {'lr': 9.140988343971768e-05, 'samples': 20807808, 'steps': 108373, 'loss/train': 1.235337734222412} 08/31/2021 08:54:07 - INFO - __main__ - Step 108375: {'lr': 9.140578116367312e-05, 'samples': 20808000, 'steps': 108374, 'loss/train': 1.002524733543396} 08/31/2021 08:54:08 - INFO - __main__ - Step 108376: {'lr': 9.140167895908866e-05, 'samples': 20808192, 'steps': 108375, 'loss/train': 1.0120868682861328} 08/31/2021 08:54:09 - INFO - __main__ - Step 108377: {'lr': 9.139757682596616e-05, 'samples': 20808384, 'steps': 108376, 'loss/train': 1.2807577848434448} 08/31/2021 08:54:09 - INFO - __main__ - Step 108378: {'lr': 9.139347476430748e-05, 'samples': 20808576, 'steps': 108377, 'loss/train': 1.473464846611023} 08/31/2021 08:54:09 - INFO - __main__ - Step 108379: {'lr': 9.138937277411446e-05, 'samples': 20808768, 'steps': 108378, 'loss/train': 1.2650202512741089} 08/31/2021 08:54:10 - INFO - __main__ - Step 108380: {'lr': 9.138527085538892e-05, 'samples': 20808960, 'steps': 108379, 'loss/train': 1.1950962543487549} 08/31/2021 08:54:11 - INFO - __main__ - Step 108381: {'lr': 9.138116900813274e-05, 'samples': 20809152, 'steps': 108380, 'loss/train': 1.0803719758987427} 08/31/2021 08:54:12 - INFO - __main__ - Step 108382: {'lr': 9.137706723234776e-05, 'samples': 20809344, 'steps': 108381, 'loss/train': 1.3883785009384155} 08/31/2021 08:54:12 - INFO - __main__ - Step 108383: {'lr': 9.137296552803589e-05, 'samples': 20809536, 'steps': 108382, 'loss/train': 0.9765095114707947} 08/31/2021 08:54:12 - INFO - __main__ - Step 108384: {'lr': 9.136886389519885e-05, 'samples': 20809728, 'steps': 108383, 'loss/train': 0.7607001066207886} 08/31/2021 08:54:13 - INFO - __main__ - Step 108385: {'lr': 9.136476233383853e-05, 'samples': 20809920, 'steps': 108384, 'loss/train': 0.15534894168376923} 08/31/2021 08:54:14 - INFO - __main__ - Step 108386: {'lr': 9.136066084395683e-05, 'samples': 20810112, 'steps': 108385, 'loss/train': 1.877864956855774} 08/31/2021 08:54:15 - INFO - __main__ - Step 108387: {'lr': 9.135655942555555e-05, 'samples': 20810304, 'steps': 108386, 'loss/train': 1.3635141849517822} 08/31/2021 08:54:15 - INFO - __main__ - Step 108388: {'lr': 9.135245807863658e-05, 'samples': 20810496, 'steps': 108387, 'loss/train': 0.8325202465057373} 08/31/2021 08:54:15 - INFO - __main__ - Step 108389: {'lr': 9.134835680320172e-05, 'samples': 20810688, 'steps': 108388, 'loss/train': 0.4530278742313385} 08/31/2021 08:54:16 - INFO - __main__ - Step 108390: {'lr': 9.134425559925283e-05, 'samples': 20810880, 'steps': 108389, 'loss/train': 1.2545489072799683} 08/31/2021 08:54:17 - INFO - __main__ - Step 108391: {'lr': 9.134015446679178e-05, 'samples': 20811072, 'steps': 108390, 'loss/train': 1.2420759201049805} 08/31/2021 08:54:18 - INFO - __main__ - Step 108392: {'lr': 9.133605340582044e-05, 'samples': 20811264, 'steps': 108391, 'loss/train': 0.7486011981964111} 08/31/2021 08:54:18 - INFO - __main__ - Step 108393: {'lr': 9.13319524163406e-05, 'samples': 20811456, 'steps': 108392, 'loss/train': 1.0029683113098145} 08/31/2021 08:54:18 - INFO - __main__ - Step 108394: {'lr': 9.132785149835413e-05, 'samples': 20811648, 'steps': 108393, 'loss/train': 0.9421591758728027} 08/31/2021 08:54:19 - INFO - __main__ - Step 108395: {'lr': 9.132375065186289e-05, 'samples': 20811840, 'steps': 108394, 'loss/train': 1.131788969039917} 08/31/2021 08:54:20 - INFO - __main__ - Step 108396: {'lr': 9.131964987686872e-05, 'samples': 20812032, 'steps': 108395, 'loss/train': 0.23772740364074707} 08/31/2021 08:54:21 - INFO - __main__ - Step 108397: {'lr': 9.131554917337354e-05, 'samples': 20812224, 'steps': 108396, 'loss/train': 0.7981311678886414} 08/31/2021 08:54:21 - INFO - __main__ - Step 108398: {'lr': 9.131144854137904e-05, 'samples': 20812416, 'steps': 108397, 'loss/train': 0.8591808080673218} 08/31/2021 08:54:22 - INFO - __main__ - Step 108399: {'lr': 9.130734798088716e-05, 'samples': 20812608, 'steps': 108398, 'loss/train': 1.3580665588378906} 08/31/2021 08:54:22 - INFO - __main__ - Step 108400: {'lr': 9.130324749189975e-05, 'samples': 20812800, 'steps': 108399, 'loss/train': 1.0773149728775024} 08/31/2021 08:54:23 - INFO - __main__ - Step 108401: {'lr': 9.129914707441864e-05, 'samples': 20812992, 'steps': 108400, 'loss/train': 1.0930895805358887} 08/31/2021 08:54:24 - INFO - __main__ - Step 108402: {'lr': 9.129504672844568e-05, 'samples': 20813184, 'steps': 108401, 'loss/train': 1.0877468585968018} 08/31/2021 08:54:24 - INFO - __main__ - Step 108403: {'lr': 9.129094645398272e-05, 'samples': 20813376, 'steps': 108402, 'loss/train': 0.9176636934280396} 08/31/2021 08:54:24 - INFO - __main__ - Step 108404: {'lr': 9.128684625103162e-05, 'samples': 20813568, 'steps': 108403, 'loss/train': 1.3884327411651611} 08/31/2021 08:54:25 - INFO - __main__ - Step 108405: {'lr': 9.128274611959422e-05, 'samples': 20813760, 'steps': 108404, 'loss/train': 1.6906418800354004} 08/31/2021 08:54:25 - INFO - __main__ - Step 108406: {'lr': 9.127864605967237e-05, 'samples': 20813952, 'steps': 108405, 'loss/train': 1.541995882987976} 08/31/2021 08:54:27 - INFO - __main__ - Step 108407: {'lr': 9.12745460712679e-05, 'samples': 20814144, 'steps': 108406, 'loss/train': 1.2297780513763428} 08/31/2021 08:54:27 - INFO - __main__ - Step 108408: {'lr': 9.127044615438268e-05, 'samples': 20814336, 'steps': 108407, 'loss/train': 1.7229335308074951} 08/31/2021 08:54:27 - INFO - __main__ - Step 108409: {'lr': 9.126634630901853e-05, 'samples': 20814528, 'steps': 108408, 'loss/train': 1.2332111597061157} 08/31/2021 08:54:28 - INFO - __main__ - Step 108410: {'lr': 9.126224653517743e-05, 'samples': 20814720, 'steps': 108409, 'loss/train': 1.1061655282974243} 08/31/2021 08:54:30 - INFO - __main__ - Step 108411: {'lr': 9.125814683286099e-05, 'samples': 20814912, 'steps': 108410, 'loss/train': 0.957314133644104} 08/31/2021 08:54:30 - INFO - __main__ - Step 108412: {'lr': 9.12540472020712e-05, 'samples': 20815104, 'steps': 108411, 'loss/train': 0.6667250990867615} 08/31/2021 08:54:30 - INFO - __main__ - Step 108413: {'lr': 9.124994764280989e-05, 'samples': 20815296, 'steps': 108412, 'loss/train': 1.129199504852295} 08/31/2021 08:54:31 - INFO - __main__ - Step 108414: {'lr': 9.124584815507888e-05, 'samples': 20815488, 'steps': 108413, 'loss/train': 0.5061348080635071} 08/31/2021 08:54:31 - INFO - __main__ - Step 108415: {'lr': 9.124174873888008e-05, 'samples': 20815680, 'steps': 108414, 'loss/train': 1.1401357650756836} 08/31/2021 08:54:31 - INFO - __main__ - Step 108416: {'lr': 9.123764939421528e-05, 'samples': 20815872, 'steps': 108415, 'loss/train': 1.8901420831680298} 08/31/2021 08:54:33 - INFO - __main__ - Step 108417: {'lr': 9.123355012108634e-05, 'samples': 20816064, 'steps': 108416, 'loss/train': 1.1118942499160767} 08/31/2021 08:54:33 - INFO - __main__ - Step 108418: {'lr': 9.12294509194951e-05, 'samples': 20816256, 'steps': 108417, 'loss/train': 1.1032003164291382} 08/31/2021 08:54:34 - INFO - __main__ - Step 108419: {'lr': 9.122535178944346e-05, 'samples': 20816448, 'steps': 108418, 'loss/train': 0.9553247094154358} 08/31/2021 08:54:34 - INFO - __main__ - Step 108420: {'lr': 9.122125273093321e-05, 'samples': 20816640, 'steps': 108419, 'loss/train': 1.1839460134506226} 08/31/2021 08:54:34 - INFO - __main__ - Step 108421: {'lr': 9.12171537439662e-05, 'samples': 20816832, 'steps': 108420, 'loss/train': 1.9577521085739136} 08/31/2021 08:54:37 - INFO - __main__ - Step 108422: {'lr': 9.121305482854427e-05, 'samples': 20817024, 'steps': 108421, 'loss/train': 1.4042130708694458} 08/31/2021 08:54:37 - INFO - __main__ - Step 108423: {'lr': 9.120895598466933e-05, 'samples': 20817216, 'steps': 108422, 'loss/train': 0.10934656113386154} 08/31/2021 08:54:37 - INFO - __main__ - Step 108424: {'lr': 9.120485721234325e-05, 'samples': 20817408, 'steps': 108423, 'loss/train': 0.0512799508869648} 08/31/2021 08:54:38 - INFO - __main__ - Step 108425: {'lr': 9.120075851156773e-05, 'samples': 20817600, 'steps': 108424, 'loss/train': 0.029499318450689316} 08/31/2021 08:54:38 - INFO - __main__ - Step 108426: {'lr': 9.119665988234472e-05, 'samples': 20817792, 'steps': 108425, 'loss/train': 1.0498054027557373} 08/31/2021 08:54:38 - INFO - __main__ - Step 108427: {'lr': 9.119256132467602e-05, 'samples': 20817984, 'steps': 108426, 'loss/train': 1.3390306234359741} 08/31/2021 08:54:40 - INFO - __main__ - Step 108428: {'lr': 9.118846283856349e-05, 'samples': 20818176, 'steps': 108427, 'loss/train': 1.70795738697052} 08/31/2021 08:54:41 - INFO - __main__ - Step 108429: {'lr': 9.118436442400898e-05, 'samples': 20818368, 'steps': 108428, 'loss/train': 1.043349027633667} 08/31/2021 08:54:41 - INFO - __main__ - Step 108430: {'lr': 9.118026608101438e-05, 'samples': 20818560, 'steps': 108429, 'loss/train': 1.3408117294311523} 08/31/2021 08:54:41 - INFO - __main__ - Step 108431: {'lr': 9.11761678095815e-05, 'samples': 20818752, 'steps': 108430, 'loss/train': 1.7427854537963867} 08/31/2021 08:54:42 - INFO - __main__ - Step 108432: {'lr': 9.117206960971216e-05, 'samples': 20818944, 'steps': 108431, 'loss/train': 1.1117116212844849} 08/31/2021 08:54:43 - INFO - __main__ - Step 108433: {'lr': 9.116797148140823e-05, 'samples': 20819136, 'steps': 108432, 'loss/train': 1.4892303943634033} 08/31/2021 08:54:44 - INFO - __main__ - Step 108434: {'lr': 9.116387342467161e-05, 'samples': 20819328, 'steps': 108433, 'loss/train': 0.631697416305542} 08/31/2021 08:54:44 - INFO - __main__ - Step 108435: {'lr': 9.115977543950404e-05, 'samples': 20819520, 'steps': 108434, 'loss/train': 0.13175298273563385} 08/31/2021 08:54:45 - INFO - __main__ - Step 108436: {'lr': 9.115567752590748e-05, 'samples': 20819712, 'steps': 108435, 'loss/train': 1.4234129190444946} 08/31/2021 08:54:45 - INFO - __main__ - Step 108437: {'lr': 9.115157968388376e-05, 'samples': 20819904, 'steps': 108436, 'loss/train': 0.037301205098629} 08/31/2021 08:54:47 - INFO - __main__ - Step 108438: {'lr': 9.114748191343464e-05, 'samples': 20820096, 'steps': 108437, 'loss/train': 0.47982877492904663} 08/31/2021 08:54:47 - INFO - __main__ - Step 108439: {'lr': 9.114338421456197e-05, 'samples': 20820288, 'steps': 108438, 'loss/train': 0.8757627010345459} 08/31/2021 08:54:47 - INFO - __main__ - Step 108440: {'lr': 9.113928658726767e-05, 'samples': 20820480, 'steps': 108439, 'loss/train': 0.9216955900192261} 08/31/2021 08:54:48 - INFO - __main__ - Step 108441: {'lr': 9.113518903155354e-05, 'samples': 20820672, 'steps': 108440, 'loss/train': 0.6795761585235596} 08/31/2021 08:54:48 - INFO - __main__ - Step 108442: {'lr': 9.113109154742146e-05, 'samples': 20820864, 'steps': 108441, 'loss/train': 0.8914387822151184} 08/31/2021 08:54:48 - INFO - __main__ - Step 108443: {'lr': 9.112699413487324e-05, 'samples': 20821056, 'steps': 108442, 'loss/train': 1.8553402423858643} 08/31/2021 08:54:50 - INFO - __main__ - Step 108444: {'lr': 9.112289679391075e-05, 'samples': 20821248, 'steps': 108443, 'loss/train': 0.9882615804672241} 08/31/2021 08:54:51 - INFO - __main__ - Step 108445: {'lr': 9.111879952453586e-05, 'samples': 20821440, 'steps': 108444, 'loss/train': 0.1643209010362625} 08/31/2021 08:54:51 - INFO - __main__ - Step 108446: {'lr': 9.111470232675034e-05, 'samples': 20821632, 'steps': 108445, 'loss/train': 1.176256775856018} 08/31/2021 08:54:51 - INFO - __main__ - Step 108447: {'lr': 9.11106052005561e-05, 'samples': 20821824, 'steps': 108446, 'loss/train': 1.0073950290679932} 08/31/2021 08:54:52 - INFO - __main__ - Step 108448: {'lr': 9.1106508145955e-05, 'samples': 20822016, 'steps': 108447, 'loss/train': 0.6856481432914734} 08/31/2021 08:54:54 - INFO - __main__ - Step 108449: {'lr': 9.110241116294882e-05, 'samples': 20822208, 'steps': 108448, 'loss/train': 1.5408371686935425} 08/31/2021 08:54:54 - INFO - __main__ - Step 108450: {'lr': 9.109831425153956e-05, 'samples': 20822400, 'steps': 108449, 'loss/train': 1.2581177949905396} 08/31/2021 08:54:55 - INFO - __main__ - Step 108451: {'lr': 9.109421741172883e-05, 'samples': 20822592, 'steps': 108450, 'loss/train': 0.05095824971795082} 08/31/2021 08:54:55 - INFO - __main__ - Step 108452: {'lr': 9.10901206435186e-05, 'samples': 20822784, 'steps': 108451, 'loss/train': 0.7360373735427856} 08/31/2021 08:54:55 - INFO - __main__ - Step 108453: {'lr': 9.108602394691071e-05, 'samples': 20822976, 'steps': 108452, 'loss/train': 1.0955047607421875} 08/31/2021 08:54:57 - INFO - __main__ - Step 108454: {'lr': 9.108192732190701e-05, 'samples': 20823168, 'steps': 108453, 'loss/train': 1.134702444076538} 08/31/2021 08:54:57 - INFO - __main__ - Step 108455: {'lr': 9.107783076850933e-05, 'samples': 20823360, 'steps': 108454, 'loss/train': 0.6099106669425964} 08/31/2021 08:54:58 - INFO - __main__ - Step 108456: {'lr': 9.107373428671955e-05, 'samples': 20823552, 'steps': 108455, 'loss/train': 0.2433386743068695} 08/31/2021 08:54:58 - INFO - __main__ - Step 108457: {'lr': 9.106963787653949e-05, 'samples': 20823744, 'steps': 108456, 'loss/train': 0.10509434342384338} 08/31/2021 08:54:58 - INFO - __main__ - Step 108458: {'lr': 9.106554153797097e-05, 'samples': 20823936, 'steps': 108457, 'loss/train': 0.6669867038726807} 08/31/2021 08:55:00 - INFO - __main__ - Step 108459: {'lr': 9.10614452710159e-05, 'samples': 20824128, 'steps': 108458, 'loss/train': 1.006445288658142} 08/31/2021 08:55:00 - INFO - __main__ - Step 108460: {'lr': 9.105734907567606e-05, 'samples': 20824320, 'steps': 108459, 'loss/train': 2.0049102306365967} 08/31/2021 08:55:01 - INFO - __main__ - Step 108461: {'lr': 9.105325295195335e-05, 'samples': 20824512, 'steps': 108460, 'loss/train': 1.2913392782211304} 08/31/2021 08:55:01 - INFO - __main__ - Step 108462: {'lr': 9.104915689984957e-05, 'samples': 20824704, 'steps': 108461, 'loss/train': 1.0497368574142456} 08/31/2021 08:55:01 - INFO - __main__ - Step 108463: {'lr': 9.104506091936659e-05, 'samples': 20824896, 'steps': 108462, 'loss/train': 1.3483076095581055} 08/31/2021 08:55:03 - INFO - __main__ - Step 108464: {'lr': 9.104096501050635e-05, 'samples': 20825088, 'steps': 108463, 'loss/train': 0.8419173359870911} 08/31/2021 08:55:04 - INFO - __main__ - Step 108465: {'lr': 9.103686917327053e-05, 'samples': 20825280, 'steps': 108464, 'loss/train': 0.5002732276916504} 08/31/2021 08:55:04 - INFO - __main__ - Step 108466: {'lr': 9.1032773407661e-05, 'samples': 20825472, 'steps': 108465, 'loss/train': 1.283994436264038} 08/31/2021 08:55:04 - INFO - __main__ - Step 108467: {'lr': 9.102867771367967e-05, 'samples': 20825664, 'steps': 108466, 'loss/train': 1.0338600873947144} 08/31/2021 08:55:05 - INFO - __main__ - Step 108468: {'lr': 9.102458209132839e-05, 'samples': 20825856, 'steps': 108467, 'loss/train': 1.2237441539764404} 08/31/2021 08:55:06 - INFO - __main__ - Step 108469: {'lr': 9.102048654060896e-05, 'samples': 20826048, 'steps': 108468, 'loss/train': 0.5083189606666565} 08/31/2021 08:55:07 - INFO - __main__ - Step 108470: {'lr': 9.101639106152324e-05, 'samples': 20826240, 'steps': 108469, 'loss/train': 1.3036609888076782} 08/31/2021 08:55:07 - INFO - __main__ - Step 108471: {'lr': 9.101229565407307e-05, 'samples': 20826432, 'steps': 108470, 'loss/train': 0.8203469514846802} 08/31/2021 08:55:08 - INFO - __main__ - Step 108472: {'lr': 9.100820031826032e-05, 'samples': 20826624, 'steps': 108471, 'loss/train': 0.14476865530014038} 08/31/2021 08:55:08 - INFO - __main__ - Step 108473: {'lr': 9.100410505408682e-05, 'samples': 20826816, 'steps': 108472, 'loss/train': 1.4713670015335083} 08/31/2021 08:55:08 - INFO - __main__ - Step 108474: {'lr': 9.100000986155443e-05, 'samples': 20827008, 'steps': 108473, 'loss/train': 0.7955964803695679} 08/31/2021 08:55:10 - INFO - __main__ - Step 108475: {'lr': 9.099591474066496e-05, 'samples': 20827200, 'steps': 108474, 'loss/train': 0.0239899680018425} 08/31/2021 08:55:10 - INFO - __main__ - Step 108476: {'lr': 9.099181969142029e-05, 'samples': 20827392, 'steps': 108475, 'loss/train': 1.755980134010315} 08/31/2021 08:55:10 - INFO - __main__ - Step 108477: {'lr': 9.098772471382233e-05, 'samples': 20827584, 'steps': 108476, 'loss/train': 0.6573270559310913} 08/31/2021 08:55:11 - INFO - __main__ - Step 108478: {'lr': 9.098362980787278e-05, 'samples': 20827776, 'steps': 108477, 'loss/train': 1.0868396759033203} 08/31/2021 08:55:11 - INFO - __main__ - Step 108479: {'lr': 9.097953497357354e-05, 'samples': 20827968, 'steps': 108478, 'loss/train': 1.4661123752593994} 08/31/2021 08:55:13 - INFO - __main__ - Step 108480: {'lr': 9.097544021092647e-05, 'samples': 20828160, 'steps': 108479, 'loss/train': 0.9293385744094849} 08/31/2021 08:55:14 - INFO - __main__ - Step 108481: {'lr': 9.097134551993342e-05, 'samples': 20828352, 'steps': 108480, 'loss/train': 1.0981009006500244} 08/31/2021 08:55:14 - INFO - __main__ - Step 108482: {'lr': 9.096725090059621e-05, 'samples': 20828544, 'steps': 108481, 'loss/train': 1.5293397903442383} 08/31/2021 08:55:14 - INFO - __main__ - Step 108483: {'lr': 9.096315635291671e-05, 'samples': 20828736, 'steps': 108482, 'loss/train': 0.5782113671302795} 08/31/2021 08:55:15 - INFO - __main__ - Step 108484: {'lr': 9.095906187689676e-05, 'samples': 20828928, 'steps': 108483, 'loss/train': 0.9408302903175354} 08/31/2021 08:55:17 - INFO - __main__ - Step 108485: {'lr': 9.09549674725382e-05, 'samples': 20829120, 'steps': 108484, 'loss/train': 0.6250643730163574} 08/31/2021 08:55:17 - INFO - __main__ - Step 108486: {'lr': 9.095087313984287e-05, 'samples': 20829312, 'steps': 108485, 'loss/train': 0.037012021988630295} 08/31/2021 08:55:17 - INFO - __main__ - Step 108487: {'lr': 9.094677887881264e-05, 'samples': 20829504, 'steps': 108486, 'loss/train': 1.0395492315292358} 08/31/2021 08:55:18 - INFO - __main__ - Step 108488: {'lr': 9.094268468944933e-05, 'samples': 20829696, 'steps': 108487, 'loss/train': 1.3105111122131348} 08/31/2021 08:55:18 - INFO - __main__ - Step 108489: {'lr': 9.093859057175479e-05, 'samples': 20829888, 'steps': 108488, 'loss/train': 1.1122158765792847} 08/31/2021 08:55:18 - INFO - __main__ - Step 108490: {'lr': 9.093449652573086e-05, 'samples': 20830080, 'steps': 108489, 'loss/train': 0.9950888752937317} 08/31/2021 08:55:20 - INFO - __main__ - Step 108491: {'lr': 9.093040255137949e-05, 'samples': 20830272, 'steps': 108490, 'loss/train': 0.9429182410240173} 08/31/2021 08:55:21 - INFO - __main__ - Step 108492: {'lr': 9.092630864870233e-05, 'samples': 20830464, 'steps': 108491, 'loss/train': 1.3656322956085205} 08/31/2021 08:55:21 - INFO - __main__ - Step 108493: {'lr': 9.092221481770133e-05, 'samples': 20830656, 'steps': 108492, 'loss/train': 1.4792672395706177} 08/31/2021 08:55:21 - INFO - __main__ - Step 108494: {'lr': 9.091812105837833e-05, 'samples': 20830848, 'steps': 108493, 'loss/train': 0.8548069000244141} 08/31/2021 08:55:22 - INFO - __main__ - Step 108495: {'lr': 9.091402737073514e-05, 'samples': 20831040, 'steps': 108494, 'loss/train': 0.8001048564910889} 08/31/2021 08:55:24 - INFO - __main__ - Step 108496: {'lr': 9.090993375477366e-05, 'samples': 20831232, 'steps': 108495, 'loss/train': 1.1199941635131836} 08/31/2021 08:55:24 - INFO - __main__ - Step 108497: {'lr': 9.09058402104957e-05, 'samples': 20831424, 'steps': 108496, 'loss/train': 1.427262306213379} 08/31/2021 08:55:25 - INFO - __main__ - Step 108498: {'lr': 9.090174673790311e-05, 'samples': 20831616, 'steps': 108497, 'loss/train': 1.0361160039901733} 08/31/2021 08:55:25 - INFO - __main__ - Step 108499: {'lr': 9.089765333699776e-05, 'samples': 20831808, 'steps': 108498, 'loss/train': 1.057201862335205} 08/31/2021 08:55:25 - INFO - __main__ - Step 108500: {'lr': 9.089356000778145e-05, 'samples': 20832000, 'steps': 108499, 'loss/train': 0.5519518256187439} 08/31/2021 08:55:26 - INFO - __main__ - Step 108501: {'lr': 9.088946675025606e-05, 'samples': 20832192, 'steps': 108500, 'loss/train': 0.9456202983856201} 08/31/2021 08:55:27 - INFO - __main__ - Step 108502: {'lr': 9.088537356442342e-05, 'samples': 20832384, 'steps': 108501, 'loss/train': 1.0512378215789795} 08/31/2021 08:55:28 - INFO - __main__ - Step 108503: {'lr': 9.088128045028535e-05, 'samples': 20832576, 'steps': 108502, 'loss/train': 0.9061411619186401} 08/31/2021 08:55:28 - INFO - __main__ - Step 108504: {'lr': 9.087718740784385e-05, 'samples': 20832768, 'steps': 108503, 'loss/train': 1.078945279121399} 08/31/2021 08:55:28 - INFO - __main__ - Step 108505: {'lr': 9.087309443710051e-05, 'samples': 20832960, 'steps': 108504, 'loss/train': 1.9144222736358643} 08/31/2021 08:55:29 - INFO - __main__ - Step 108506: {'lr': 9.08690015380573e-05, 'samples': 20833152, 'steps': 108505, 'loss/train': 1.1549656391143799} 08/31/2021 08:55:30 - INFO - __main__ - Step 108507: {'lr': 9.086490871071609e-05, 'samples': 20833344, 'steps': 108506, 'loss/train': 1.5477361679077148} 08/31/2021 08:55:31 - INFO - __main__ - Step 108508: {'lr': 9.086081595507867e-05, 'samples': 20833536, 'steps': 108507, 'loss/train': 0.06331747025251389} 08/31/2021 08:55:31 - INFO - __main__ - Step 108509: {'lr': 9.085672327114691e-05, 'samples': 20833728, 'steps': 108508, 'loss/train': 1.0385901927947998} 08/31/2021 08:55:31 - INFO - __main__ - Step 108510: {'lr': 9.085263065892268e-05, 'samples': 20833920, 'steps': 108509, 'loss/train': 0.9406969547271729} 08/31/2021 08:55:32 - INFO - __main__ - Step 108511: {'lr': 9.084853811840779e-05, 'samples': 20834112, 'steps': 108510, 'loss/train': 1.587815523147583} 08/31/2021 08:55:33 - INFO - __main__ - Step 108512: {'lr': 9.084444564960409e-05, 'samples': 20834304, 'steps': 108511, 'loss/train': 1.2286503314971924} 08/31/2021 08:55:34 - INFO - __main__ - Step 108513: {'lr': 9.084035325251341e-05, 'samples': 20834496, 'steps': 108512, 'loss/train': 1.4481470584869385} 08/31/2021 08:55:34 - INFO - __main__ - Step 108514: {'lr': 9.083626092713765e-05, 'samples': 20834688, 'steps': 108513, 'loss/train': 0.8556390404701233} 08/31/2021 08:55:34 - INFO - __main__ - Step 108515: {'lr': 9.083216867347857e-05, 'samples': 20834880, 'steps': 108514, 'loss/train': 0.2880999445915222} 08/31/2021 08:55:35 - INFO - __main__ - Step 108516: {'lr': 9.08280764915381e-05, 'samples': 20835072, 'steps': 108515, 'loss/train': 2.0689451694488525} 08/31/2021 08:55:35 - INFO - __main__ - Step 108517: {'lr': 9.0823984381318e-05, 'samples': 20835264, 'steps': 108516, 'loss/train': 0.8236048817634583} 08/31/2021 08:55:37 - INFO - __main__ - Step 108518: {'lr': 9.081989234282025e-05, 'samples': 20835456, 'steps': 108517, 'loss/train': 1.201019525527954} 08/31/2021 08:55:37 - INFO - __main__ - Step 108519: {'lr': 9.081580037604656e-05, 'samples': 20835648, 'steps': 108518, 'loss/train': 1.0465885400772095} 08/31/2021 08:55:37 - INFO - __main__ - Step 108520: {'lr': 9.081170848099876e-05, 'samples': 20835840, 'steps': 108519, 'loss/train': 1.524001955986023} 08/31/2021 08:55:38 - INFO - __main__ - Step 108521: {'lr': 9.080761665767878e-05, 'samples': 20836032, 'steps': 108520, 'loss/train': 1.796068549156189} 08/31/2021 08:55:38 - INFO - __main__ - Step 108522: {'lr': 9.080352490608842e-05, 'samples': 20836224, 'steps': 108521, 'loss/train': 1.7576627731323242} 08/31/2021 08:55:40 - INFO - __main__ - Step 108523: {'lr': 9.079943322622954e-05, 'samples': 20836416, 'steps': 108522, 'loss/train': 1.633036494255066} 08/31/2021 08:55:40 - INFO - __main__ - Step 108524: {'lr': 9.079534161810396e-05, 'samples': 20836608, 'steps': 108523, 'loss/train': 1.464066743850708} 08/31/2021 08:55:40 - INFO - __main__ - Step 108525: {'lr': 9.079125008171358e-05, 'samples': 20836800, 'steps': 108524, 'loss/train': 1.420060396194458} 08/31/2021 08:55:41 - INFO - __main__ - Step 108526: {'lr': 9.078715861706016e-05, 'samples': 20836992, 'steps': 108525, 'loss/train': 1.5440460443496704} 08/31/2021 08:55:41 - INFO - __main__ - Step 108527: {'lr': 9.078306722414562e-05, 'samples': 20837184, 'steps': 108526, 'loss/train': 0.30108240246772766} 08/31/2021 08:55:43 - INFO - __main__ - Step 108528: {'lr': 9.077897590297177e-05, 'samples': 20837376, 'steps': 108527, 'loss/train': 1.2247873544692993} 08/31/2021 08:55:43 - INFO - __main__ - Step 108529: {'lr': 9.077488465354044e-05, 'samples': 20837568, 'steps': 108528, 'loss/train': 1.0919156074523926} 08/31/2021 08:55:44 - INFO - __main__ - Step 108530: {'lr': 9.077079347585352e-05, 'samples': 20837760, 'steps': 108529, 'loss/train': 0.7044809460639954} 08/31/2021 08:55:44 - INFO - __main__ - Step 108531: {'lr': 9.076670236991289e-05, 'samples': 20837952, 'steps': 108530, 'loss/train': 1.629050850868225} 08/31/2021 08:55:44 - INFO - __main__ - Step 108532: {'lr': 9.076261133572026e-05, 'samples': 20838144, 'steps': 108531, 'loss/train': 1.1774810552597046} 08/31/2021 08:55:45 - INFO - __main__ - Step 108533: {'lr': 9.075852037327751e-05, 'samples': 20838336, 'steps': 108532, 'loss/train': 0.016880309209227562} 08/31/2021 08:55:47 - INFO - __main__ - Step 108534: {'lr': 9.075442948258653e-05, 'samples': 20838528, 'steps': 108533, 'loss/train': 0.016343453899025917} 08/31/2021 08:55:47 - INFO - __main__ - Step 108535: {'lr': 9.075033866364912e-05, 'samples': 20838720, 'steps': 108534, 'loss/train': 1.0392426252365112} 08/31/2021 08:55:48 - INFO - __main__ - Step 108536: {'lr': 9.074624791646718e-05, 'samples': 20838912, 'steps': 108535, 'loss/train': 1.1607825756072998} 08/31/2021 08:55:48 - INFO - __main__ - Step 108537: {'lr': 9.074215724104254e-05, 'samples': 20839104, 'steps': 108536, 'loss/train': 1.7281596660614014} 08/31/2021 08:55:48 - INFO - __main__ - Step 108538: {'lr': 9.0738066637377e-05, 'samples': 20839296, 'steps': 108537, 'loss/train': 0.6337355971336365} 08/31/2021 08:55:50 - INFO - __main__ - Step 108539: {'lr': 9.073397610547244e-05, 'samples': 20839488, 'steps': 108538, 'loss/train': 1.2772043943405151} 08/31/2021 08:55:50 - INFO - __main__ - Step 108540: {'lr': 9.072988564533066e-05, 'samples': 20839680, 'steps': 108539, 'loss/train': 1.1364188194274902} 08/31/2021 08:55:51 - INFO - __main__ - Step 108541: {'lr': 9.072579525695357e-05, 'samples': 20839872, 'steps': 108540, 'loss/train': 1.274750828742981} 08/31/2021 08:55:51 - INFO - __main__ - Step 108542: {'lr': 9.072170494034296e-05, 'samples': 20840064, 'steps': 108541, 'loss/train': 0.8199490308761597} 08/31/2021 08:55:51 - INFO - __main__ - Step 108543: {'lr': 9.071761469550071e-05, 'samples': 20840256, 'steps': 108542, 'loss/train': 1.1725753545761108} 08/31/2021 08:55:52 - INFO - __main__ - Step 108544: {'lr': 9.071352452242865e-05, 'samples': 20840448, 'steps': 108543, 'loss/train': 0.49146485328674316} 08/31/2021 08:55:53 - INFO - __main__ - Step 108545: {'lr': 9.070943442112867e-05, 'samples': 20840640, 'steps': 108544, 'loss/train': 1.4269554615020752} 08/31/2021 08:55:54 - INFO - __main__ - Step 108546: {'lr': 9.07053443916025e-05, 'samples': 20840832, 'steps': 108545, 'loss/train': 1.4069418907165527} 08/31/2021 08:55:54 - INFO - __main__ - Step 108547: {'lr': 9.070125443385205e-05, 'samples': 20841024, 'steps': 108546, 'loss/train': 0.8228004574775696} 08/31/2021 08:55:55 - INFO - __main__ - Step 108548: {'lr': 9.069716454787914e-05, 'samples': 20841216, 'steps': 108547, 'loss/train': 1.4384214878082275} 08/31/2021 08:55:55 - INFO - __main__ - Step 108549: {'lr': 9.069307473368562e-05, 'samples': 20841408, 'steps': 108548, 'loss/train': 0.10527560114860535} 08/31/2021 08:55:57 - INFO - __main__ - Step 108550: {'lr': 9.068898499127337e-05, 'samples': 20841600, 'steps': 108549, 'loss/train': 1.0534698963165283} 08/31/2021 08:55:57 - INFO - __main__ - Step 108551: {'lr': 9.068489532064419e-05, 'samples': 20841792, 'steps': 108550, 'loss/train': 1.0201528072357178} 08/31/2021 08:55:57 - INFO - __main__ - Step 108552: {'lr': 9.068080572179995e-05, 'samples': 20841984, 'steps': 108551, 'loss/train': 1.1149581670761108} 08/31/2021 08:55:58 - INFO - __main__ - Step 108553: {'lr': 9.067671619474247e-05, 'samples': 20842176, 'steps': 108552, 'loss/train': 1.2634737491607666} 08/31/2021 08:55:58 - INFO - __main__ - Step 108554: {'lr': 9.067262673947361e-05, 'samples': 20842368, 'steps': 108553, 'loss/train': 0.8019670248031616} 08/31/2021 08:56:00 - INFO - __main__ - Step 108555: {'lr': 9.06685373559952e-05, 'samples': 20842560, 'steps': 108554, 'loss/train': 0.48017430305480957} 08/31/2021 08:56:00 - INFO - __main__ - Step 108556: {'lr': 9.066444804430917e-05, 'samples': 20842752, 'steps': 108555, 'loss/train': 1.490080714225769} 08/31/2021 08:56:01 - INFO - __main__ - Step 108557: {'lr': 9.06603588044172e-05, 'samples': 20842944, 'steps': 108556, 'loss/train': 1.3107248544692993} 08/31/2021 08:56:01 - INFO - __main__ - Step 108558: {'lr': 9.06562696363212e-05, 'samples': 20843136, 'steps': 108557, 'loss/train': 0.3198666274547577} 08/31/2021 08:56:01 - INFO - __main__ - Step 108559: {'lr': 9.065218054002306e-05, 'samples': 20843328, 'steps': 108558, 'loss/train': 1.1093266010284424} 08/31/2021 08:56:03 - INFO - __main__ - Step 108560: {'lr': 9.064809151552456e-05, 'samples': 20843520, 'steps': 108559, 'loss/train': 0.8588522672653198} 08/31/2021 08:56:04 - INFO - __main__ - Step 108561: {'lr': 9.064400256282756e-05, 'samples': 20843712, 'steps': 108560, 'loss/train': 0.6916801333427429} 08/31/2021 08:56:04 - INFO - __main__ - Step 108562: {'lr': 9.063991368193394e-05, 'samples': 20843904, 'steps': 108561, 'loss/train': 0.014444665051996708} 08/31/2021 08:56:04 - INFO - __main__ - Step 108563: {'lr': 9.063582487284553e-05, 'samples': 20844096, 'steps': 108562, 'loss/train': 1.1344037055969238} 08/31/2021 08:56:05 - INFO - __main__ - Step 108564: {'lr': 9.06317361355641e-05, 'samples': 20844288, 'steps': 108563, 'loss/train': 0.6259686946868896} 08/31/2021 08:56:05 - INFO - __main__ - Step 108565: {'lr': 9.062764747009162e-05, 'samples': 20844480, 'steps': 108564, 'loss/train': 0.8595331311225891} 08/31/2021 08:56:07 - INFO - __main__ - Step 108566: {'lr': 9.062355887642981e-05, 'samples': 20844672, 'steps': 108565, 'loss/train': 2.47235369682312} 08/31/2021 08:56:07 - INFO - __main__ - Step 108567: {'lr': 9.061947035458068e-05, 'samples': 20844864, 'steps': 108566, 'loss/train': 1.2797021865844727} 08/31/2021 08:56:07 - INFO - __main__ - Step 108568: {'lr': 9.061538190454586e-05, 'samples': 20845056, 'steps': 108567, 'loss/train': 1.3490701913833618} 08/31/2021 08:56:08 - INFO - __main__ - Step 108569: {'lr': 9.06112935263273e-05, 'samples': 20845248, 'steps': 108568, 'loss/train': 0.14720407128334045} 08/31/2021 08:56:08 - INFO - __main__ - Step 108570: {'lr': 9.060720521992682e-05, 'samples': 20845440, 'steps': 108569, 'loss/train': 0.09255687892436981} 08/31/2021 08:56:10 - INFO - __main__ - Step 108571: {'lr': 9.060311698534627e-05, 'samples': 20845632, 'steps': 108570, 'loss/train': 1.3334003686904907} 08/31/2021 08:56:10 - INFO - __main__ - Step 108572: {'lr': 9.05990288225875e-05, 'samples': 20845824, 'steps': 108571, 'loss/train': 0.6342909932136536} 08/31/2021 08:56:10 - INFO - __main__ - Step 108573: {'lr': 9.059494073165236e-05, 'samples': 20846016, 'steps': 108572, 'loss/train': 0.7917737364768982} 08/31/2021 08:56:11 - INFO - __main__ - Step 108574: {'lr': 9.059085271254266e-05, 'samples': 20846208, 'steps': 108573, 'loss/train': 1.2119020223617554} 08/31/2021 08:56:11 - INFO - __main__ - Step 108575: {'lr': 9.058676476526029e-05, 'samples': 20846400, 'steps': 108574, 'loss/train': 1.0379536151885986} 08/31/2021 08:56:13 - INFO - __main__ - Step 108576: {'lr': 9.058267688980703e-05, 'samples': 20846592, 'steps': 108575, 'loss/train': 0.7336357235908508} 08/31/2021 08:56:13 - INFO - __main__ - Step 108577: {'lr': 9.057858908618477e-05, 'samples': 20846784, 'steps': 108576, 'loss/train': 0.3218242824077606} 08/31/2021 08:56:13 - INFO - __main__ - Step 108578: {'lr': 9.057450135439544e-05, 'samples': 20846976, 'steps': 108577, 'loss/train': 0.8997313976287842} 08/31/2021 08:56:14 - INFO - __main__ - Step 108579: {'lr': 9.057041369444066e-05, 'samples': 20847168, 'steps': 108578, 'loss/train': 0.8177857995033264} 08/31/2021 08:56:14 - INFO - __main__ - Step 108580: {'lr': 9.056632610632243e-05, 'samples': 20847360, 'steps': 108579, 'loss/train': 1.5978279113769531} 08/31/2021 08:56:16 - INFO - __main__ - Step 108581: {'lr': 9.056223859004253e-05, 'samples': 20847552, 'steps': 108580, 'loss/train': 0.09277145564556122} 08/31/2021 08:56:16 - INFO - __main__ - Step 108582: {'lr': 9.055815114560281e-05, 'samples': 20847744, 'steps': 108581, 'loss/train': 1.4415287971496582} 08/31/2021 08:56:16 - INFO - __main__ - Step 108583: {'lr': 9.055406377300515e-05, 'samples': 20847936, 'steps': 108582, 'loss/train': 0.31986674666404724} 08/31/2021 08:56:17 - INFO - __main__ - Step 108584: {'lr': 9.054997647225138e-05, 'samples': 20848128, 'steps': 108583, 'loss/train': 0.7979655861854553} 08/31/2021 08:56:17 - INFO - __main__ - Step 108585: {'lr': 9.054588924334332e-05, 'samples': 20848320, 'steps': 108584, 'loss/train': 1.5726009607315063} 08/31/2021 08:56:19 - INFO - __main__ - Step 108586: {'lr': 9.05418020862828e-05, 'samples': 20848512, 'steps': 108585, 'loss/train': 1.205473780632019} 08/31/2021 08:56:19 - INFO - __main__ - Step 108587: {'lr': 9.053771500107169e-05, 'samples': 20848704, 'steps': 108586, 'loss/train': 1.4899390935897827} 08/31/2021 08:56:20 - INFO - __main__ - Step 108588: {'lr': 9.053362798771184e-05, 'samples': 20848896, 'steps': 108587, 'loss/train': 1.459694743156433} 08/31/2021 08:56:20 - INFO - __main__ - Step 108589: {'lr': 9.052954104620517e-05, 'samples': 20849088, 'steps': 108588, 'loss/train': 0.06836548447608948} 08/31/2021 08:56:20 - INFO - __main__ - Step 108590: {'lr': 9.052545417655333e-05, 'samples': 20849280, 'steps': 108589, 'loss/train': 1.8759379386901855} 08/31/2021 08:56:21 - INFO - __main__ - Step 108591: {'lr': 9.052136737875824e-05, 'samples': 20849472, 'steps': 108590, 'loss/train': 0.14944174885749817} 08/31/2021 08:56:23 - INFO - __main__ - Step 108592: {'lr': 9.05172806528218e-05, 'samples': 20849664, 'steps': 108591, 'loss/train': 0.5254972577095032} 08/31/2021 08:56:23 - INFO - __main__ - Step 108593: {'lr': 9.051319399874577e-05, 'samples': 20849856, 'steps': 108592, 'loss/train': 0.4847237467765808} 08/31/2021 08:56:23 - INFO - __main__ - Step 108594: {'lr': 9.050910741653206e-05, 'samples': 20850048, 'steps': 108593, 'loss/train': 0.5793378949165344} 08/31/2021 08:56:24 - INFO - __main__ - Step 108595: {'lr': 9.050502090618248e-05, 'samples': 20850240, 'steps': 108594, 'loss/train': 0.7489916086196899} 08/31/2021 08:56:24 - INFO - __main__ - Step 108596: {'lr': 9.050093446769889e-05, 'samples': 20850432, 'steps': 108595, 'loss/train': 1.1497886180877686} 08/31/2021 08:56:26 - INFO - __main__ - Step 108597: {'lr': 9.04968481010831e-05, 'samples': 20850624, 'steps': 108596, 'loss/train': 1.062268614768982} 08/31/2021 08:56:27 - INFO - __main__ - Step 108598: {'lr': 9.049276180633698e-05, 'samples': 20850816, 'steps': 108597, 'loss/train': 0.9460775256156921} 08/31/2021 08:56:27 - INFO - __main__ - Step 108599: {'lr': 9.048867558346236e-05, 'samples': 20851008, 'steps': 108598, 'loss/train': 0.1896500587463379} 08/31/2021 08:56:27 - INFO - __main__ - Step 108600: {'lr': 9.048458943246116e-05, 'samples': 20851200, 'steps': 108599, 'loss/train': 1.157590627670288} 08/31/2021 08:56:28 - INFO - __main__ - Step 108601: {'lr': 9.048050335333505e-05, 'samples': 20851392, 'steps': 108600, 'loss/train': 1.3725296258926392} 08/31/2021 08:56:30 - INFO - __main__ - Step 108602: {'lr': 9.047641734608597e-05, 'samples': 20851584, 'steps': 108601, 'loss/train': 1.1593366861343384} 08/31/2021 08:56:30 - INFO - __main__ - Step 108603: {'lr': 9.047233141071576e-05, 'samples': 20851776, 'steps': 108602, 'loss/train': 0.16873866319656372} 08/31/2021 08:56:31 - INFO - __main__ - Step 108604: {'lr': 9.046824554722624e-05, 'samples': 20851968, 'steps': 108603, 'loss/train': 1.3796511888504028} 08/31/2021 08:56:31 - INFO - __main__ - Step 108605: {'lr': 9.046415975561928e-05, 'samples': 20852160, 'steps': 108604, 'loss/train': 1.245116114616394} 08/31/2021 08:56:31 - INFO - __main__ - Step 108606: {'lr': 9.04600740358967e-05, 'samples': 20852352, 'steps': 108605, 'loss/train': 1.5029540061950684} 08/31/2021 08:56:32 - INFO - __main__ - Step 108607: {'lr': 9.045598838806038e-05, 'samples': 20852544, 'steps': 108606, 'loss/train': 0.07368823140859604} 08/31/2021 08:56:33 - INFO - __main__ - Step 108608: {'lr': 9.04519028121121e-05, 'samples': 20852736, 'steps': 108607, 'loss/train': 0.40884631872177124} 08/31/2021 08:56:34 - INFO - __main__ - Step 108609: {'lr': 9.044781730805374e-05, 'samples': 20852928, 'steps': 108608, 'loss/train': 1.5830914974212646} 08/31/2021 08:56:34 - INFO - __main__ - Step 108610: {'lr': 9.044373187588711e-05, 'samples': 20853120, 'steps': 108609, 'loss/train': 0.6467254161834717} 08/31/2021 08:56:35 - INFO - __main__ - Step 108611: {'lr': 9.04396465156141e-05, 'samples': 20853312, 'steps': 108610, 'loss/train': 1.628493070602417} 08/31/2021 08:56:35 - INFO - __main__ - Step 108612: {'lr': 9.043556122723658e-05, 'samples': 20853504, 'steps': 108611, 'loss/train': 0.5988805294036865} 08/31/2021 08:56:37 - INFO - __main__ - Step 108613: {'lr': 9.04314760107563e-05, 'samples': 20853696, 'steps': 108612, 'loss/train': 1.048123836517334} 08/31/2021 08:56:37 - INFO - __main__ - Step 108614: {'lr': 9.042739086617507e-05, 'samples': 20853888, 'steps': 108613, 'loss/train': 0.9267345666885376} 08/31/2021 08:56:37 - INFO - __main__ - Step 108615: {'lr': 9.042330579349484e-05, 'samples': 20854080, 'steps': 108614, 'loss/train': 0.5927047729492188} 08/31/2021 08:56:38 - INFO - __main__ - Step 108616: {'lr': 9.041922079271739e-05, 'samples': 20854272, 'steps': 108615, 'loss/train': 1.2001017332077026} 08/31/2021 08:56:38 - INFO - __main__ - Step 108617: {'lr': 9.041513586384458e-05, 'samples': 20854464, 'steps': 108616, 'loss/train': 0.9643843173980713} 08/31/2021 08:56:40 - INFO - __main__ - Step 108618: {'lr': 9.041105100687824e-05, 'samples': 20854656, 'steps': 108617, 'loss/train': 1.1539496183395386} 08/31/2021 08:56:40 - INFO - __main__ - Step 108619: {'lr': 9.040696622182023e-05, 'samples': 20854848, 'steps': 108618, 'loss/train': 1.999328374862671} 08/31/2021 08:56:41 - INFO - __main__ - Step 108620: {'lr': 9.040288150867238e-05, 'samples': 20855040, 'steps': 108619, 'loss/train': 0.06319890916347504} 08/31/2021 08:56:41 - INFO - __main__ - Step 108621: {'lr': 9.039879686743652e-05, 'samples': 20855232, 'steps': 108620, 'loss/train': 0.8902134895324707} 08/31/2021 08:56:41 - INFO - __main__ - Step 108622: {'lr': 9.03947122981145e-05, 'samples': 20855424, 'steps': 108621, 'loss/train': 1.1671524047851562} 08/31/2021 08:56:42 - INFO - __main__ - Step 108623: {'lr': 9.039062780070817e-05, 'samples': 20855616, 'steps': 108622, 'loss/train': 1.7589231729507446} 08/31/2021 08:56:43 - INFO - __main__ - Step 108624: {'lr': 9.038654337521934e-05, 'samples': 20855808, 'steps': 108623, 'loss/train': 1.549576997756958} 08/31/2021 08:56:44 - INFO - __main__ - Step 108625: {'lr': 9.038245902164996e-05, 'samples': 20856000, 'steps': 108624, 'loss/train': 1.0958905220031738} 08/31/2021 08:56:44 - INFO - __main__ - Step 108626: {'lr': 9.03783747400017e-05, 'samples': 20856192, 'steps': 108625, 'loss/train': 1.3961987495422363} 08/31/2021 08:56:44 - INFO - __main__ - Step 108627: {'lr': 9.037429053027648e-05, 'samples': 20856384, 'steps': 108626, 'loss/train': 0.9274309873580933} 08/31/2021 08:56:45 - INFO - __main__ - Step 108628: {'lr': 9.037020639247614e-05, 'samples': 20856576, 'steps': 108627, 'loss/train': 1.1377758979797363} 08/31/2021 08:56:46 - INFO - __main__ - Step 108629: {'lr': 9.036612232660255e-05, 'samples': 20856768, 'steps': 108628, 'loss/train': 0.6310593485832214} 08/31/2021 08:56:47 - INFO - __main__ - Step 108630: {'lr': 9.03620383326575e-05, 'samples': 20856960, 'steps': 108629, 'loss/train': 1.35898756980896} 08/31/2021 08:56:47 - INFO - __main__ - Step 108631: {'lr': 9.035795441064285e-05, 'samples': 20857152, 'steps': 108630, 'loss/train': 0.67208331823349} 08/31/2021 08:56:47 - INFO - __main__ - Step 108632: {'lr': 9.035387056056044e-05, 'samples': 20857344, 'steps': 108631, 'loss/train': 1.1033107042312622} 08/31/2021 08:56:48 - INFO - __main__ - Step 108633: {'lr': 9.034978678241213e-05, 'samples': 20857536, 'steps': 108632, 'loss/train': 1.9093513488769531} 08/31/2021 08:56:49 - INFO - __main__ - Step 108634: {'lr': 9.034570307619972e-05, 'samples': 20857728, 'steps': 108633, 'loss/train': 1.5266637802124023} 08/31/2021 08:56:50 - INFO - __main__ - Step 108635: {'lr': 9.034161944192506e-05, 'samples': 20857920, 'steps': 108634, 'loss/train': 1.465925931930542} 08/31/2021 08:56:50 - INFO - __main__ - Step 108636: {'lr': 9.033753587959004e-05, 'samples': 20858112, 'steps': 108635, 'loss/train': 0.6485291719436646} 08/31/2021 08:56:51 - INFO - __main__ - Step 108637: {'lr': 9.033345238919643e-05, 'samples': 20858304, 'steps': 108636, 'loss/train': 1.1499450206756592} 08/31/2021 08:56:51 - INFO - __main__ - Step 108638: {'lr': 9.032936897074615e-05, 'samples': 20858496, 'steps': 108637, 'loss/train': 1.1249898672103882} 08/31/2021 08:56:52 - INFO - __main__ - Step 108639: {'lr': 9.032528562424103e-05, 'samples': 20858688, 'steps': 108638, 'loss/train': 1.3109511137008667} 08/31/2021 08:56:53 - INFO - __main__ - Step 108640: {'lr': 9.03212023496828e-05, 'samples': 20858880, 'steps': 108639, 'loss/train': 1.1496226787567139} 08/31/2021 08:56:53 - INFO - __main__ - Step 108641: {'lr': 9.031711914707339e-05, 'samples': 20859072, 'steps': 108640, 'loss/train': 1.070651650428772} 08/31/2021 08:56:53 - INFO - __main__ - Step 108642: {'lr': 9.031303601641461e-05, 'samples': 20859264, 'steps': 108641, 'loss/train': 1.175346851348877} 08/31/2021 08:56:54 - INFO - __main__ - Step 108643: {'lr': 9.03089529577083e-05, 'samples': 20859456, 'steps': 108642, 'loss/train': 1.3113807439804077} 08/31/2021 08:56:54 - INFO - __main__ - Step 108644: {'lr': 9.030486997095633e-05, 'samples': 20859648, 'steps': 108643, 'loss/train': 1.3926414251327515} 08/31/2021 08:56:56 - INFO - __main__ - Step 108645: {'lr': 9.030078705616049e-05, 'samples': 20859840, 'steps': 108644, 'loss/train': 0.9150943756103516} 08/31/2021 08:56:57 - INFO - __main__ - Step 108646: {'lr': 9.029670421332267e-05, 'samples': 20860032, 'steps': 108645, 'loss/train': 1.3940935134887695} 08/31/2021 08:56:57 - INFO - __main__ - Step 108647: {'lr': 9.029262144244471e-05, 'samples': 20860224, 'steps': 108646, 'loss/train': 1.2029114961624146} 08/31/2021 08:56:58 - INFO - __main__ - Step 108648: {'lr': 9.028853874352841e-05, 'samples': 20860416, 'steps': 108647, 'loss/train': 1.8819481134414673} 08/31/2021 08:56:58 - INFO - __main__ - Step 108649: {'lr': 9.028445611657563e-05, 'samples': 20860608, 'steps': 108648, 'loss/train': 0.7923023700714111} 08/31/2021 08:56:59 - INFO - __main__ - Step 108650: {'lr': 9.028037356158822e-05, 'samples': 20860800, 'steps': 108649, 'loss/train': 1.1377607583999634} 08/31/2021 08:57:00 - INFO - __main__ - Step 108651: {'lr': 9.0276291078568e-05, 'samples': 20860992, 'steps': 108650, 'loss/train': 1.4157074689865112} 08/31/2021 08:57:00 - INFO - __main__ - Step 108652: {'lr': 9.027220866751689e-05, 'samples': 20861184, 'steps': 108651, 'loss/train': 0.9857519268989563} 08/31/2021 08:57:01 - INFO - __main__ - Step 108653: {'lr': 9.026812632843661e-05, 'samples': 20861376, 'steps': 108652, 'loss/train': 0.9753545522689819} 08/31/2021 08:57:01 - INFO - __main__ - Step 108654: {'lr': 9.026404406132901e-05, 'samples': 20861568, 'steps': 108653, 'loss/train': 1.0662620067596436} 08/31/2021 08:57:02 - INFO - __main__ - Step 108655: {'lr': 9.0259961866196e-05, 'samples': 20861760, 'steps': 108654, 'loss/train': 1.4488033056259155} 08/31/2021 08:57:03 - INFO - __main__ - Step 108656: {'lr': 9.025587974303937e-05, 'samples': 20861952, 'steps': 108655, 'loss/train': 0.928264319896698} 08/31/2021 08:57:03 - INFO - __main__ - Step 108657: {'lr': 9.025179769186098e-05, 'samples': 20862144, 'steps': 108656, 'loss/train': 0.667210578918457} 08/31/2021 08:57:04 - INFO - __main__ - Step 108658: {'lr': 9.024771571266266e-05, 'samples': 20862336, 'steps': 108657, 'loss/train': 1.2909026145935059} 08/31/2021 08:57:04 - INFO - __main__ - Step 108659: {'lr': 9.024363380544626e-05, 'samples': 20862528, 'steps': 108658, 'loss/train': 1.534730076789856} 08/31/2021 08:57:05 - INFO - __main__ - Step 108660: {'lr': 9.023955197021361e-05, 'samples': 20862720, 'steps': 108659, 'loss/train': 1.7189165353775024} 08/31/2021 08:57:06 - INFO - __main__ - Step 108661: {'lr': 9.023547020696654e-05, 'samples': 20862912, 'steps': 108660, 'loss/train': 1.2605607509613037} 08/31/2021 08:57:06 - INFO - __main__ - Step 108662: {'lr': 9.023138851570692e-05, 'samples': 20863104, 'steps': 108661, 'loss/train': 0.04623100906610489} 08/31/2021 08:57:06 - INFO - __main__ - Step 108663: {'lr': 9.022730689643654e-05, 'samples': 20863296, 'steps': 108662, 'loss/train': 1.1629581451416016} 08/31/2021 08:57:07 - INFO - __main__ - Step 108664: {'lr': 9.022322534915731e-05, 'samples': 20863488, 'steps': 108663, 'loss/train': 1.0114233493804932} 08/31/2021 08:57:09 - INFO - __main__ - Step 108665: {'lr': 9.021914387387101e-05, 'samples': 20863680, 'steps': 108664, 'loss/train': 0.9269765019416809} 08/31/2021 08:57:09 - INFO - __main__ - Step 108666: {'lr': 9.021506247057959e-05, 'samples': 20863872, 'steps': 108665, 'loss/train': 1.2307041883468628} 08/31/2021 08:57:09 - INFO - __main__ - Step 108667: {'lr': 9.021098113928472e-05, 'samples': 20864064, 'steps': 108666, 'loss/train': 1.5279196500778198} 08/31/2021 08:57:10 - INFO - __main__ - Step 108668: {'lr': 9.020689987998828e-05, 'samples': 20864256, 'steps': 108667, 'loss/train': 1.4657142162322998} 08/31/2021 08:57:10 - INFO - __main__ - Step 108669: {'lr': 9.020281869269217e-05, 'samples': 20864448, 'steps': 108668, 'loss/train': 0.49225664138793945} 08/31/2021 08:57:10 - INFO - __main__ - Step 108670: {'lr': 9.019873757739821e-05, 'samples': 20864640, 'steps': 108669, 'loss/train': 0.4516506791114807} 08/31/2021 08:57:13 - INFO - __main__ - Step 108671: {'lr': 9.019465653410824e-05, 'samples': 20864832, 'steps': 108670, 'loss/train': 0.9195604920387268} 08/31/2021 08:57:13 - INFO - __main__ - Step 108672: {'lr': 9.019057556282406e-05, 'samples': 20865024, 'steps': 108671, 'loss/train': 1.1829205751419067} 08/31/2021 08:57:13 - INFO - __main__ - Step 108673: {'lr': 9.018649466354758e-05, 'samples': 20865216, 'steps': 108672, 'loss/train': 0.8596547245979309} 08/31/2021 08:57:14 - INFO - __main__ - Step 108674: {'lr': 9.018241383628056e-05, 'samples': 20865408, 'steps': 108673, 'loss/train': 1.4590767621994019} 08/31/2021 08:57:14 - INFO - __main__ - Step 108675: {'lr': 9.017833308102491e-05, 'samples': 20865600, 'steps': 108674, 'loss/train': 0.48935550451278687} 08/31/2021 08:57:14 - INFO - __main__ - Step 108676: {'lr': 9.017425239778242e-05, 'samples': 20865792, 'steps': 108675, 'loss/train': 0.46553412079811096} 08/31/2021 08:57:16 - INFO - __main__ - Step 108677: {'lr': 9.017017178655495e-05, 'samples': 20865984, 'steps': 108676, 'loss/train': 1.4423669576644897} 08/31/2021 08:57:17 - INFO - __main__ - Step 108678: {'lr': 9.016609124734435e-05, 'samples': 20866176, 'steps': 108677, 'loss/train': 1.2544101476669312} 08/31/2021 08:57:17 - INFO - __main__ - Step 108679: {'lr': 9.016201078015248e-05, 'samples': 20866368, 'steps': 108678, 'loss/train': 1.3575127124786377} 08/31/2021 08:57:17 - INFO - __main__ - Step 108680: {'lr': 9.01579303849811e-05, 'samples': 20866560, 'steps': 108679, 'loss/train': 1.7651325464248657} 08/31/2021 08:57:18 - INFO - __main__ - Step 108681: {'lr': 9.015385006183207e-05, 'samples': 20866752, 'steps': 108680, 'loss/train': 0.6844162940979004} 08/31/2021 08:57:19 - INFO - __main__ - Step 108682: {'lr': 9.014976981070727e-05, 'samples': 20866944, 'steps': 108681, 'loss/train': 1.403480052947998} 08/31/2021 08:57:20 - INFO - __main__ - Step 108683: {'lr': 9.014568963160849e-05, 'samples': 20867136, 'steps': 108682, 'loss/train': 1.1823768615722656} 08/31/2021 08:57:20 - INFO - __main__ - Step 108684: {'lr': 9.014160952453762e-05, 'samples': 20867328, 'steps': 108683, 'loss/train': 1.0226269960403442} 08/31/2021 08:57:20 - INFO - __main__ - Step 108685: {'lr': 9.013752948949647e-05, 'samples': 20867520, 'steps': 108684, 'loss/train': 1.3813737630844116} 08/31/2021 08:57:21 - INFO - __main__ - Step 108686: {'lr': 9.013344952648686e-05, 'samples': 20867712, 'steps': 108685, 'loss/train': 1.5223084688186646} 08/31/2021 08:57:21 - INFO - __main__ - Step 108687: {'lr': 9.01293696355107e-05, 'samples': 20867904, 'steps': 108686, 'loss/train': 1.1794326305389404} 08/31/2021 08:57:22 - INFO - __main__ - Step 108688: {'lr': 9.012528981656973e-05, 'samples': 20868096, 'steps': 108687, 'loss/train': 0.3822213113307953} 08/31/2021 08:57:23 - INFO - __main__ - Step 108689: {'lr': 9.012121006966583e-05, 'samples': 20868288, 'steps': 108688, 'loss/train': 1.3625857830047607} 08/31/2021 08:57:23 - INFO - __main__ - Step 108690: {'lr': 9.011713039480088e-05, 'samples': 20868480, 'steps': 108689, 'loss/train': 1.007445216178894} 08/31/2021 08:57:24 - INFO - __main__ - Step 108691: {'lr': 9.011305079197669e-05, 'samples': 20868672, 'steps': 108690, 'loss/train': 1.8416517972946167} 08/31/2021 08:57:24 - INFO - __main__ - Step 108692: {'lr': 9.010897126119517e-05, 'samples': 20868864, 'steps': 108691, 'loss/train': 1.1546388864517212} 08/31/2021 08:57:26 - INFO - __main__ - Step 108693: {'lr': 9.010489180245796e-05, 'samples': 20869056, 'steps': 108692, 'loss/train': 0.795015275478363} 08/31/2021 08:57:26 - INFO - __main__ - Step 108694: {'lr': 9.010081241576703e-05, 'samples': 20869248, 'steps': 108693, 'loss/train': 0.44757285714149475} 08/31/2021 08:57:26 - INFO - __main__ - Step 108695: {'lr': 9.009673310112424e-05, 'samples': 20869440, 'steps': 108694, 'loss/train': 0.7396942973136902} 08/31/2021 08:57:27 - INFO - __main__ - Step 108696: {'lr': 9.009265385853138e-05, 'samples': 20869632, 'steps': 108695, 'loss/train': 1.4342435598373413} 08/31/2021 08:57:27 - INFO - __main__ - Step 108697: {'lr': 9.008857468799028e-05, 'samples': 20869824, 'steps': 108696, 'loss/train': 1.0039137601852417} 08/31/2021 08:57:28 - INFO - __main__ - Step 108698: {'lr': 9.008449558950283e-05, 'samples': 20870016, 'steps': 108697, 'loss/train': 1.0202059745788574} 08/31/2021 08:57:29 - INFO - __main__ - Step 108699: {'lr': 9.008041656307081e-05, 'samples': 20870208, 'steps': 108698, 'loss/train': 0.9625111818313599} 08/31/2021 08:57:30 - INFO - __main__ - Step 108700: {'lr': 9.007633760869614e-05, 'samples': 20870400, 'steps': 108699, 'loss/train': 1.275126338005066} 08/31/2021 08:57:30 - INFO - __main__ - Step 108701: {'lr': 9.007225872638053e-05, 'samples': 20870592, 'steps': 108700, 'loss/train': 1.3739013671875} 08/31/2021 08:57:31 - INFO - __main__ - Step 108702: {'lr': 9.006817991612595e-05, 'samples': 20870784, 'steps': 108701, 'loss/train': 1.1162880659103394} 08/31/2021 08:57:31 - INFO - __main__ - Step 108703: {'lr': 9.006410117793415e-05, 'samples': 20870976, 'steps': 108702, 'loss/train': 1.1236110925674438} 08/31/2021 08:57:32 - INFO - __main__ - Step 108704: {'lr': 9.006002251180701e-05, 'samples': 20871168, 'steps': 108703, 'loss/train': 0.5299155712127686} 08/31/2021 08:57:33 - INFO - __main__ - Step 108705: {'lr': 9.005594391774635e-05, 'samples': 20871360, 'steps': 108704, 'loss/train': 0.25536292791366577} 08/31/2021 08:57:33 - INFO - __main__ - Step 108706: {'lr': 9.00518653957541e-05, 'samples': 20871552, 'steps': 108705, 'loss/train': 0.9177165031433105} 08/31/2021 08:57:34 - INFO - __main__ - Step 108707: {'lr': 9.004778694583193e-05, 'samples': 20871744, 'steps': 108706, 'loss/train': 1.483080267906189} 08/31/2021 08:57:34 - INFO - __main__ - Step 108708: {'lr': 9.004370856798177e-05, 'samples': 20871936, 'steps': 108707, 'loss/train': 0.9505636096000671} 08/31/2021 08:57:36 - INFO - __main__ - Step 108709: {'lr': 9.003963026220543e-05, 'samples': 20872128, 'steps': 108708, 'loss/train': 1.2239469289779663} 08/31/2021 08:57:36 - INFO - __main__ - Step 108710: {'lr': 9.003555202850478e-05, 'samples': 20872320, 'steps': 108709, 'loss/train': 0.7371538877487183} 08/31/2021 08:57:37 - INFO - __main__ - Step 108711: {'lr': 9.003147386688163e-05, 'samples': 20872512, 'steps': 108710, 'loss/train': 0.8325613737106323} 08/31/2021 08:57:37 - INFO - __main__ - Step 108712: {'lr': 9.002739577733782e-05, 'samples': 20872704, 'steps': 108711, 'loss/train': 0.7944112420082092} 08/31/2021 08:57:37 - INFO - __main__ - Step 108713: {'lr': 9.002331775987522e-05, 'samples': 20872896, 'steps': 108712, 'loss/train': 0.9163603782653809} 08/31/2021 08:57:38 - INFO - __main__ - Step 108714: {'lr': 9.00192398144956e-05, 'samples': 20873088, 'steps': 108713, 'loss/train': 1.4148627519607544} 08/31/2021 08:57:39 - INFO - __main__ - Step 108715: {'lr': 9.001516194120088e-05, 'samples': 20873280, 'steps': 108714, 'loss/train': 1.014499545097351} 08/31/2021 08:57:40 - INFO - __main__ - Step 108716: {'lr': 9.001108413999287e-05, 'samples': 20873472, 'steps': 108715, 'loss/train': 1.4919421672821045} 08/31/2021 08:57:40 - INFO - __main__ - Step 108717: {'lr': 9.000700641087336e-05, 'samples': 20873664, 'steps': 108716, 'loss/train': 0.6798527240753174} 08/31/2021 08:57:41 - INFO - __main__ - Step 108718: {'lr': 9.000292875384425e-05, 'samples': 20873856, 'steps': 108717, 'loss/train': 1.4887151718139648} 08/31/2021 08:57:41 - INFO - __main__ - Step 108719: {'lr': 8.999885116890744e-05, 'samples': 20874048, 'steps': 108718, 'loss/train': 0.9098027944564819} 08/31/2021 08:57:42 - INFO - __main__ - Step 108720: {'lr': 8.999477365606457e-05, 'samples': 20874240, 'steps': 108719, 'loss/train': 1.1999051570892334} 08/31/2021 08:57:43 - INFO - __main__ - Step 108721: {'lr': 8.999069621531761e-05, 'samples': 20874432, 'steps': 108720, 'loss/train': 0.9993131756782532} 08/31/2021 08:57:43 - INFO - __main__ - Step 108722: {'lr': 8.998661884666837e-05, 'samples': 20874624, 'steps': 108721, 'loss/train': 0.4290897250175476} 08/31/2021 08:57:44 - INFO - __main__ - Step 108723: {'lr': 8.998254155011868e-05, 'samples': 20874816, 'steps': 108722, 'loss/train': 0.3382652997970581} 08/31/2021 08:57:44 - INFO - __main__ - Step 108724: {'lr': 8.997846432567039e-05, 'samples': 20875008, 'steps': 108723, 'loss/train': 0.9587906002998352} 08/31/2021 08:57:44 - INFO - __main__ - Step 108725: {'lr': 8.997438717332532e-05, 'samples': 20875200, 'steps': 108724, 'loss/train': 1.0233933925628662} 08/31/2021 08:57:46 - INFO - __main__ - Step 108726: {'lr': 8.997031009308535e-05, 'samples': 20875392, 'steps': 108725, 'loss/train': 1.2602508068084717} 08/31/2021 08:57:46 - INFO - __main__ - Step 108727: {'lr': 8.996623308495227e-05, 'samples': 20875584, 'steps': 108726, 'loss/train': 1.615351676940918} 08/31/2021 08:57:47 - INFO - __main__ - Step 108728: {'lr': 8.996215614892794e-05, 'samples': 20875776, 'steps': 108727, 'loss/train': 0.024978796020150185} 08/31/2021 08:57:47 - INFO - __main__ - Step 108729: {'lr': 8.99580792850142e-05, 'samples': 20875968, 'steps': 108728, 'loss/train': 1.4906270503997803} 08/31/2021 08:57:47 - INFO - __main__ - Step 108730: {'lr': 8.995400249321287e-05, 'samples': 20876160, 'steps': 108729, 'loss/train': 1.934163212776184} 08/31/2021 08:57:49 - INFO - __main__ - Step 108731: {'lr': 8.994992577352582e-05, 'samples': 20876352, 'steps': 108730, 'loss/train': 0.7385546565055847} 08/31/2021 08:57:49 - INFO - __main__ - Step 108732: {'lr': 8.994584912595483e-05, 'samples': 20876544, 'steps': 108731, 'loss/train': 0.808712363243103} 08/31/2021 08:57:50 - INFO - __main__ - Step 108733: {'lr': 8.994177255050187e-05, 'samples': 20876736, 'steps': 108732, 'loss/train': 1.597229242324829} 08/31/2021 08:57:50 - INFO - __main__ - Step 108734: {'lr': 8.993769604716858e-05, 'samples': 20876928, 'steps': 108733, 'loss/train': 0.9970517754554749} 08/31/2021 08:57:50 - INFO - __main__ - Step 108735: {'lr': 8.993361961595691e-05, 'samples': 20877120, 'steps': 108734, 'loss/train': 1.0253314971923828} 08/31/2021 08:57:52 - INFO - __main__ - Step 108736: {'lr': 8.99295432568687e-05, 'samples': 20877312, 'steps': 108735, 'loss/train': 1.7446404695510864} 08/31/2021 08:57:53 - INFO - __main__ - Step 108737: {'lr': 8.992546696990575e-05, 'samples': 20877504, 'steps': 108736, 'loss/train': 0.9263041615486145} 08/31/2021 08:57:53 - INFO - __main__ - Step 108738: {'lr': 8.992139075506988e-05, 'samples': 20877696, 'steps': 108737, 'loss/train': 1.8043272495269775} 08/31/2021 08:57:53 - INFO - __main__ - Step 108739: {'lr': 8.991731461236302e-05, 'samples': 20877888, 'steps': 108738, 'loss/train': 0.924140989780426} 08/31/2021 08:57:54 - INFO - __main__ - Step 108740: {'lr': 8.99132385417869e-05, 'samples': 20878080, 'steps': 108739, 'loss/train': 1.4856395721435547} 08/31/2021 08:57:55 - INFO - __main__ - Step 108741: {'lr': 8.990916254334345e-05, 'samples': 20878272, 'steps': 108740, 'loss/train': 0.81736159324646} 08/31/2021 08:57:56 - INFO - __main__ - Step 108742: {'lr': 8.990508661703441e-05, 'samples': 20878464, 'steps': 108741, 'loss/train': 1.0897417068481445} 08/31/2021 08:57:56 - INFO - __main__ - Step 108743: {'lr': 8.990101076286169e-05, 'samples': 20878656, 'steps': 108742, 'loss/train': 1.1737405061721802} 08/31/2021 08:57:56 - INFO - __main__ - Step 108744: {'lr': 8.989693498082713e-05, 'samples': 20878848, 'steps': 108743, 'loss/train': 0.9217525720596313} 08/31/2021 08:57:57 - INFO - __main__ - Step 108745: {'lr': 8.98928592709325e-05, 'samples': 20879040, 'steps': 108744, 'loss/train': 1.127503514289856} 08/31/2021 08:57:58 - INFO - __main__ - Step 108746: {'lr': 8.98887836331798e-05, 'samples': 20879232, 'steps': 108745, 'loss/train': 1.114726185798645} 08/31/2021 08:57:59 - INFO - __main__ - Step 108747: {'lr': 8.988470806757062e-05, 'samples': 20879424, 'steps': 108746, 'loss/train': 0.8983207941055298} 08/31/2021 08:57:59 - INFO - __main__ - Step 108748: {'lr': 8.988063257410695e-05, 'samples': 20879616, 'steps': 108747, 'loss/train': 0.6033380627632141} 08/31/2021 08:58:00 - INFO - __main__ - Step 108749: {'lr': 8.987655715279058e-05, 'samples': 20879808, 'steps': 108748, 'loss/train': 1.4161933660507202} 08/31/2021 08:58:00 - INFO - __main__ - Step 108750: {'lr': 8.987248180362337e-05, 'samples': 20880000, 'steps': 108749, 'loss/train': 1.4184678792953491} 08/31/2021 08:58:03 - INFO - __main__ - Step 108751: {'lr': 8.986840652660714e-05, 'samples': 20880192, 'steps': 108750, 'loss/train': 1.4916231632232666} 08/31/2021 08:58:03 - INFO - __main__ - Step 108752: {'lr': 8.986433132174374e-05, 'samples': 20880384, 'steps': 108751, 'loss/train': 0.5367985963821411} 08/31/2021 08:58:03 - INFO - __main__ - Step 108753: {'lr': 8.986025618903499e-05, 'samples': 20880576, 'steps': 108752, 'loss/train': 1.1839141845703125} 08/31/2021 08:58:04 - INFO - __main__ - Step 108754: {'lr': 8.985618112848277e-05, 'samples': 20880768, 'steps': 108753, 'loss/train': 0.015716547146439552} 08/31/2021 08:58:04 - INFO - __main__ - Step 108755: {'lr': 8.985210614008884e-05, 'samples': 20880960, 'steps': 108754, 'loss/train': 0.2650851607322693} 08/31/2021 08:58:04 - INFO - __main__ - Step 108756: {'lr': 8.98480312238551e-05, 'samples': 20881152, 'steps': 108755, 'loss/train': 1.0516479015350342} 08/31/2021 08:58:06 - INFO - __main__ - Step 108757: {'lr': 8.984395637978338e-05, 'samples': 20881344, 'steps': 108756, 'loss/train': 1.1118286848068237} 08/31/2021 08:58:06 - INFO - __main__ - Step 108758: {'lr': 8.983988160787548e-05, 'samples': 20881536, 'steps': 108757, 'loss/train': 0.6845412254333496} 08/31/2021 08:58:07 - INFO - __main__ - Step 108759: {'lr': 8.983580690813328e-05, 'samples': 20881728, 'steps': 108758, 'loss/train': 1.3679943084716797} 08/31/2021 08:58:07 - INFO - __main__ - Step 108760: {'lr': 8.983173228055866e-05, 'samples': 20881920, 'steps': 108759, 'loss/train': 1.0259541273117065} 08/31/2021 08:58:07 - INFO - __main__ - Step 108761: {'lr': 8.98276577251533e-05, 'samples': 20882112, 'steps': 108760, 'loss/train': 1.4591398239135742} 08/31/2021 08:58:09 - INFO - __main__ - Step 108762: {'lr': 8.982358324191917e-05, 'samples': 20882304, 'steps': 108761, 'loss/train': 0.5297559499740601} 08/31/2021 08:58:09 - INFO - __main__ - Step 108763: {'lr': 8.981950883085801e-05, 'samples': 20882496, 'steps': 108762, 'loss/train': 0.3247704803943634} 08/31/2021 08:58:10 - INFO - __main__ - Step 108764: {'lr': 8.981543449197172e-05, 'samples': 20882688, 'steps': 108763, 'loss/train': 1.3199712038040161} 08/31/2021 08:58:10 - INFO - __main__ - Step 108765: {'lr': 8.981136022526215e-05, 'samples': 20882880, 'steps': 108764, 'loss/train': 0.8976152539253235} 08/31/2021 08:58:10 - INFO - __main__ - Step 108766: {'lr': 8.980728603073107e-05, 'samples': 20883072, 'steps': 108765, 'loss/train': 1.1229197978973389} 08/31/2021 08:58:12 - INFO - __main__ - Step 108767: {'lr': 8.980321190838039e-05, 'samples': 20883264, 'steps': 108766, 'loss/train': 1.4531294107437134} 08/31/2021 08:58:13 - INFO - __main__ - Step 108768: {'lr': 8.979913785821189e-05, 'samples': 20883456, 'steps': 108767, 'loss/train': 1.128035068511963} 08/31/2021 08:58:13 - INFO - __main__ - Step 108769: {'lr': 8.979506388022743e-05, 'samples': 20883648, 'steps': 108768, 'loss/train': 1.6725441217422485} 08/31/2021 08:58:13 - INFO - __main__ - Step 108770: {'lr': 8.979098997442883e-05, 'samples': 20883840, 'steps': 108769, 'loss/train': 1.4408423900604248} 08/31/2021 08:58:14 - INFO - __main__ - Step 108771: {'lr': 8.978691614081796e-05, 'samples': 20884032, 'steps': 108770, 'loss/train': 1.2430424690246582} 08/31/2021 08:58:14 - INFO - __main__ - Step 108772: {'lr': 8.978284237939663e-05, 'samples': 20884224, 'steps': 108771, 'loss/train': 1.2095904350280762} 08/31/2021 08:58:16 - INFO - __main__ - Step 108773: {'lr': 8.977876869016677e-05, 'samples': 20884416, 'steps': 108772, 'loss/train': 0.9632752537727356} 08/31/2021 08:58:16 - INFO - __main__ - Step 108774: {'lr': 8.977469507313002e-05, 'samples': 20884608, 'steps': 108773, 'loss/train': 1.1899397373199463} 08/31/2021 08:58:16 - INFO - __main__ - Step 108775: {'lr': 8.977062152828832e-05, 'samples': 20884800, 'steps': 108774, 'loss/train': 0.19106386601924896} 08/31/2021 08:58:17 - INFO - __main__ - Step 108776: {'lr': 8.976654805564352e-05, 'samples': 20884992, 'steps': 108775, 'loss/train': 0.9998701810836792} 08/31/2021 08:58:17 - INFO - __main__ - Step 108777: {'lr': 8.976247465519743e-05, 'samples': 20885184, 'steps': 108776, 'loss/train': 0.6591718196868896} 08/31/2021 08:58:19 - INFO - __main__ - Step 108778: {'lr': 8.97584013269519e-05, 'samples': 20885376, 'steps': 108777, 'loss/train': 0.9471878409385681} 08/31/2021 08:58:19 - INFO - __main__ - Step 108779: {'lr': 8.975432807090877e-05, 'samples': 20885568, 'steps': 108778, 'loss/train': 1.5963159799575806} 08/31/2021 08:58:19 - INFO - __main__ - Step 108780: {'lr': 8.975025488706986e-05, 'samples': 20885760, 'steps': 108779, 'loss/train': 1.3992576599121094} 08/31/2021 08:58:20 - INFO - __main__ - Step 108781: {'lr': 8.9746181775437e-05, 'samples': 20885952, 'steps': 108780, 'loss/train': 1.7008841037750244} 08/31/2021 08:58:20 - INFO - __main__ - Step 108782: {'lr': 8.974210873601205e-05, 'samples': 20886144, 'steps': 108781, 'loss/train': 0.4813818335533142} 08/31/2021 08:58:21 - INFO - __main__ - Step 108783: {'lr': 8.973803576879683e-05, 'samples': 20886336, 'steps': 108782, 'loss/train': 1.2902487516403198} 08/31/2021 08:58:22 - INFO - __main__ - Step 108784: {'lr': 8.973396287379318e-05, 'samples': 20886528, 'steps': 108783, 'loss/train': 1.6038029193878174} 08/31/2021 08:58:23 - INFO - __main__ - Step 108785: {'lr': 8.972989005100293e-05, 'samples': 20886720, 'steps': 108784, 'loss/train': 0.9668072462081909} 08/31/2021 08:58:23 - INFO - __main__ - Step 108786: {'lr': 8.972581730042792e-05, 'samples': 20886912, 'steps': 108785, 'loss/train': 1.1627378463745117} 08/31/2021 08:58:23 - INFO - __main__ - Step 108787: {'lr': 8.972174462207009e-05, 'samples': 20887104, 'steps': 108786, 'loss/train': 1.7288899421691895} 08/31/2021 08:58:24 - INFO - __main__ - Step 108788: {'lr': 8.971767201593106e-05, 'samples': 20887296, 'steps': 108787, 'loss/train': 1.5617179870605469} 08/31/2021 08:58:25 - INFO - __main__ - Step 108789: {'lr': 8.971359948201276e-05, 'samples': 20887488, 'steps': 108788, 'loss/train': 0.849992573261261} 08/31/2021 08:58:26 - INFO - __main__ - Step 108790: {'lr': 8.970952702031707e-05, 'samples': 20887680, 'steps': 108789, 'loss/train': 1.0062617063522339} 08/31/2021 08:58:26 - INFO - __main__ - Step 108791: {'lr': 8.970545463084578e-05, 'samples': 20887872, 'steps': 108790, 'loss/train': 0.905060887336731} 08/31/2021 08:58:26 - INFO - __main__ - Step 108792: {'lr': 8.970138231360075e-05, 'samples': 20888064, 'steps': 108791, 'loss/train': 0.7033385038375854} 08/31/2021 08:58:27 - INFO - __main__ - Step 108793: {'lr': 8.969731006858378e-05, 'samples': 20888256, 'steps': 108792, 'loss/train': 1.0452871322631836} 08/31/2021 08:58:28 - INFO - __main__ - Step 108794: {'lr': 8.969323789579675e-05, 'samples': 20888448, 'steps': 108793, 'loss/train': 1.7085050344467163} 08/31/2021 08:58:29 - INFO - __main__ - Step 108795: {'lr': 8.968916579524147e-05, 'samples': 20888640, 'steps': 108794, 'loss/train': 1.5167994499206543} 08/31/2021 08:58:29 - INFO - __main__ - Step 108796: {'lr': 8.968509376691977e-05, 'samples': 20888832, 'steps': 108795, 'loss/train': 0.8656372427940369} 08/31/2021 08:58:29 - INFO - __main__ - Step 108797: {'lr': 8.968102181083349e-05, 'samples': 20889024, 'steps': 108796, 'loss/train': 0.5955412983894348} 08/31/2021 08:58:30 - INFO - __main__ - Step 108798: {'lr': 8.967694992698447e-05, 'samples': 20889216, 'steps': 108797, 'loss/train': 0.9631354212760925} 08/31/2021 08:58:32 - INFO - __main__ - Step 108799: {'lr': 8.967287811537455e-05, 'samples': 20889408, 'steps': 108798, 'loss/train': 1.3745920658111572} 08/31/2021 08:58:33 - INFO - __main__ - Step 108800: {'lr': 8.966880637600564e-05, 'samples': 20889600, 'steps': 108799, 'loss/train': 1.1787420511245728} 08/31/2021 08:58:33 - INFO - __main__ - Step 108801: {'lr': 8.96647347088794e-05, 'samples': 20889792, 'steps': 108800, 'loss/train': 0.38520872592926025} 08/31/2021 08:58:33 - INFO - __main__ - Step 108802: {'lr': 8.966066311399776e-05, 'samples': 20889984, 'steps': 108801, 'loss/train': 0.8630877733230591} 08/31/2021 08:58:34 - INFO - __main__ - Step 108803: {'lr': 8.965659159136255e-05, 'samples': 20890176, 'steps': 108802, 'loss/train': 0.9758468866348267} 08/31/2021 08:58:34 - INFO - __main__ - Step 108804: {'lr': 8.965252014097561e-05, 'samples': 20890368, 'steps': 108803, 'loss/train': 0.6980400681495667} 08/31/2021 08:58:34 - INFO - __main__ - Step 108805: {'lr': 8.964844876283876e-05, 'samples': 20890560, 'steps': 108804, 'loss/train': 1.5219502449035645} 08/31/2021 08:58:36 - INFO - __main__ - Step 108806: {'lr': 8.964437745695386e-05, 'samples': 20890752, 'steps': 108805, 'loss/train': 1.0154072046279907} 08/31/2021 08:58:36 - INFO - __main__ - Step 108807: {'lr': 8.964030622332273e-05, 'samples': 20890944, 'steps': 108806, 'loss/train': 0.8408656716346741} 08/31/2021 08:58:37 - INFO - __main__ - Step 108808: {'lr': 8.963623506194718e-05, 'samples': 20891136, 'steps': 108807, 'loss/train': 2.1811416149139404} 08/31/2021 08:58:37 - INFO - __main__ - Step 108809: {'lr': 8.963216397282909e-05, 'samples': 20891328, 'steps': 108808, 'loss/train': 1.408144235610962} 08/31/2021 08:58:37 - INFO - __main__ - Step 108810: {'lr': 8.962809295597028e-05, 'samples': 20891520, 'steps': 108809, 'loss/train': 1.3097972869873047} 08/31/2021 08:58:40 - INFO - __main__ - Step 108811: {'lr': 8.962402201137254e-05, 'samples': 20891712, 'steps': 108810, 'loss/train': 1.3124200105667114} 08/31/2021 08:58:40 - INFO - __main__ - Step 108812: {'lr': 8.961995113903775e-05, 'samples': 20891904, 'steps': 108811, 'loss/train': 0.8359218239784241} 08/31/2021 08:58:41 - INFO - __main__ - Step 108813: {'lr': 8.961588033896784e-05, 'samples': 20892096, 'steps': 108812, 'loss/train': 1.1627225875854492} 08/31/2021 08:58:41 - INFO - __main__ - Step 108814: {'lr': 8.961180961116447e-05, 'samples': 20892288, 'steps': 108813, 'loss/train': 1.4309601783752441} 08/31/2021 08:58:41 - INFO - __main__ - Step 108815: {'lr': 8.960773895562951e-05, 'samples': 20892480, 'steps': 108814, 'loss/train': 1.227954387664795} 08/31/2021 08:58:42 - INFO - __main__ - Step 108816: {'lr': 8.960366837236483e-05, 'samples': 20892672, 'steps': 108815, 'loss/train': 0.9571413993835449} 08/31/2021 08:58:43 - INFO - __main__ - Step 108817: {'lr': 8.959959786137229e-05, 'samples': 20892864, 'steps': 108816, 'loss/train': 0.6813088059425354} 08/31/2021 08:58:44 - INFO - __main__ - Step 108818: {'lr': 8.959552742265367e-05, 'samples': 20893056, 'steps': 108817, 'loss/train': 1.0774688720703125} 08/31/2021 08:58:44 - INFO - __main__ - Step 108819: {'lr': 8.959145705621083e-05, 'samples': 20893248, 'steps': 108818, 'loss/train': 1.4527270793914795} 08/31/2021 08:58:44 - INFO - __main__ - Step 108820: {'lr': 8.958738676204562e-05, 'samples': 20893440, 'steps': 108819, 'loss/train': 1.3774878978729248} 08/31/2021 08:58:45 - INFO - __main__ - Step 108821: {'lr': 8.958331654015983e-05, 'samples': 20893632, 'steps': 108820, 'loss/train': 1.2229344844818115} 08/31/2021 08:58:46 - INFO - __main__ - Step 108822: {'lr': 8.957924639055534e-05, 'samples': 20893824, 'steps': 108821, 'loss/train': 0.8382067680358887} 08/31/2021 08:58:47 - INFO - __main__ - Step 108823: {'lr': 8.957517631323397e-05, 'samples': 20894016, 'steps': 108822, 'loss/train': 1.408797025680542} 08/31/2021 08:58:47 - INFO - __main__ - Step 108824: {'lr': 8.957110630819757e-05, 'samples': 20894208, 'steps': 108823, 'loss/train': 1.3047051429748535} 08/31/2021 08:58:47 - INFO - __main__ - Step 108825: {'lr': 8.9567036375448e-05, 'samples': 20894400, 'steps': 108824, 'loss/train': 1.6684317588806152} 08/31/2021 08:58:48 - INFO - __main__ - Step 108826: {'lr': 8.956296651498699e-05, 'samples': 20894592, 'steps': 108825, 'loss/train': 0.9723764061927795} 08/31/2021 08:58:49 - INFO - __main__ - Step 108827: {'lr': 8.955889672681642e-05, 'samples': 20894784, 'steps': 108826, 'loss/train': 1.0995436906814575} 08/31/2021 08:58:50 - INFO - __main__ - Step 108828: {'lr': 8.955482701093811e-05, 'samples': 20894976, 'steps': 108827, 'loss/train': 0.6152254939079285} 08/31/2021 08:58:50 - INFO - __main__ - Step 108829: {'lr': 8.955075736735397e-05, 'samples': 20895168, 'steps': 108828, 'loss/train': 1.7620797157287598} 08/31/2021 08:58:51 - INFO - __main__ - Step 108830: {'lr': 8.954668779606576e-05, 'samples': 20895360, 'steps': 108829, 'loss/train': 1.1329313516616821} 08/31/2021 08:58:51 - INFO - __main__ - Step 108831: {'lr': 8.954261829707533e-05, 'samples': 20895552, 'steps': 108830, 'loss/train': 0.06788700819015503} 08/31/2021 08:58:51 - INFO - __main__ - Step 108832: {'lr': 8.953854887038451e-05, 'samples': 20895744, 'steps': 108831, 'loss/train': 0.900385320186615} 08/31/2021 08:58:53 - INFO - __main__ - Step 108833: {'lr': 8.953447951599516e-05, 'samples': 20895936, 'steps': 108832, 'loss/train': 1.3063380718231201} 08/31/2021 08:58:54 - INFO - __main__ - Step 108834: {'lr': 8.953041023390912e-05, 'samples': 20896128, 'steps': 108833, 'loss/train': 1.2307380437850952} 08/31/2021 08:58:54 - INFO - __main__ - Step 108835: {'lr': 8.952634102412815e-05, 'samples': 20896320, 'steps': 108834, 'loss/train': 1.0610049962997437} 08/31/2021 08:58:54 - INFO - __main__ - Step 108836: {'lr': 8.952227188665426e-05, 'samples': 20896512, 'steps': 108835, 'loss/train': 0.7072449326515198} 08/31/2021 08:58:55 - INFO - __main__ - Step 108837: {'lr': 8.951820282148906e-05, 'samples': 20896704, 'steps': 108836, 'loss/train': 0.9332616329193115} 08/31/2021 08:58:56 - INFO - __main__ - Step 108838: {'lr': 8.951413382863449e-05, 'samples': 20896896, 'steps': 108837, 'loss/train': 1.3767606019973755} 08/31/2021 08:58:56 - INFO - __main__ - Step 108839: {'lr': 8.951006490809236e-05, 'samples': 20897088, 'steps': 108838, 'loss/train': 1.3115863800048828} 08/31/2021 08:58:57 - INFO - __main__ - Step 108840: {'lr': 8.95059960598645e-05, 'samples': 20897280, 'steps': 108839, 'loss/train': 1.278144359588623} 08/31/2021 08:58:57 - INFO - __main__ - Step 108841: {'lr': 8.950192728395281e-05, 'samples': 20897472, 'steps': 108840, 'loss/train': 1.1982927322387695} 08/31/2021 08:58:57 - INFO - __main__ - Step 108842: {'lr': 8.949785858035906e-05, 'samples': 20897664, 'steps': 108841, 'loss/train': 0.8026331067085266} 08/31/2021 08:58:59 - INFO - __main__ - Step 108843: {'lr': 8.949378994908509e-05, 'samples': 20897856, 'steps': 108842, 'loss/train': 0.7984132170677185} 08/31/2021 08:58:59 - INFO - __main__ - Step 108844: {'lr': 8.948972139013273e-05, 'samples': 20898048, 'steps': 108843, 'loss/train': 1.4259129762649536} 08/31/2021 08:59:00 - INFO - __main__ - Step 108845: {'lr': 8.948565290350383e-05, 'samples': 20898240, 'steps': 108844, 'loss/train': 1.4165009260177612} 08/31/2021 08:59:00 - INFO - __main__ - Step 108846: {'lr': 8.948158448920021e-05, 'samples': 20898432, 'steps': 108845, 'loss/train': 0.9842936396598816} 08/31/2021 08:59:00 - INFO - __main__ - Step 108847: {'lr': 8.947751614722382e-05, 'samples': 20898624, 'steps': 108846, 'loss/train': 1.542123556137085} 08/31/2021 08:59:02 - INFO - __main__ - Step 108848: {'lr': 8.94734478775763e-05, 'samples': 20898816, 'steps': 108847, 'loss/train': 0.8704677820205688} 08/31/2021 08:59:02 - INFO - __main__ - Step 108849: {'lr': 8.946937968025956e-05, 'samples': 20899008, 'steps': 108848, 'loss/train': 0.9109771847724915} 08/31/2021 08:59:03 - INFO - __main__ - Step 108850: {'lr': 8.946531155527543e-05, 'samples': 20899200, 'steps': 108849, 'loss/train': 1.3292337656021118} 08/31/2021 08:59:03 - INFO - __main__ - Step 108851: {'lr': 8.946124350262574e-05, 'samples': 20899392, 'steps': 108850, 'loss/train': 1.4981300830841064} 08/31/2021 08:59:03 - INFO - __main__ - Step 108852: {'lr': 8.945717552231236e-05, 'samples': 20899584, 'steps': 108851, 'loss/train': 1.2777864933013916} 08/31/2021 08:59:05 - INFO - __main__ - Step 108853: {'lr': 8.945310761433712e-05, 'samples': 20899776, 'steps': 108852, 'loss/train': 1.3942022323608398} 08/31/2021 08:59:05 - INFO - __main__ - Step 108854: {'lr': 8.944903977870178e-05, 'samples': 20899968, 'steps': 108853, 'loss/train': 1.4636175632476807} 08/31/2021 08:59:06 - INFO - __main__ - Step 108855: {'lr': 8.944497201540827e-05, 'samples': 20900160, 'steps': 108854, 'loss/train': 1.2808520793914795} 08/31/2021 08:59:06 - INFO - __main__ - Step 108856: {'lr': 8.944090432445837e-05, 'samples': 20900352, 'steps': 108855, 'loss/train': 1.0609432458877563} 08/31/2021 08:59:06 - INFO - __main__ - Step 108857: {'lr': 8.94368367058539e-05, 'samples': 20900544, 'steps': 108856, 'loss/train': 0.9117324352264404} 08/31/2021 08:59:08 - INFO - __main__ - Step 108858: {'lr': 8.94327691595968e-05, 'samples': 20900736, 'steps': 108857, 'loss/train': 0.7849223613739014} 08/31/2021 08:59:09 - INFO - __main__ - Step 108859: {'lr': 8.942870168568876e-05, 'samples': 20900928, 'steps': 108858, 'loss/train': 0.7499904632568359} 08/31/2021 08:59:09 - INFO - __main__ - Step 108860: {'lr': 8.942463428413164e-05, 'samples': 20901120, 'steps': 108859, 'loss/train': 1.3088855743408203} 08/31/2021 08:59:10 - INFO - __main__ - Step 108861: {'lr': 8.942056695492731e-05, 'samples': 20901312, 'steps': 108860, 'loss/train': 0.024483826011419296} 08/31/2021 08:59:10 - INFO - __main__ - Step 108862: {'lr': 8.94164996980776e-05, 'samples': 20901504, 'steps': 108861, 'loss/train': 1.3520958423614502} 08/31/2021 08:59:10 - INFO - __main__ - Step 108863: {'lr': 8.941243251358433e-05, 'samples': 20901696, 'steps': 108862, 'loss/train': 1.171278476715088} 08/31/2021 08:59:11 - INFO - __main__ - Step 108864: {'lr': 8.940836540144937e-05, 'samples': 20901888, 'steps': 108863, 'loss/train': 0.08830304443836212} 08/31/2021 08:59:11 - INFO - __main__ - Step 108865: {'lr': 8.940429836167449e-05, 'samples': 20902080, 'steps': 108864, 'loss/train': 0.053681328892707825} 08/31/2021 08:59:13 - INFO - __main__ - Step 108866: {'lr': 8.940023139426157e-05, 'samples': 20902272, 'steps': 108865, 'loss/train': 0.016618164256215096} 08/31/2021 08:59:14 - INFO - __main__ - Step 108867: {'lr': 8.93961644992124e-05, 'samples': 20902464, 'steps': 108866, 'loss/train': 2.2037465572357178} 08/31/2021 08:59:14 - INFO - __main__ - Step 108868: {'lr': 8.939209767652887e-05, 'samples': 20902656, 'steps': 108867, 'loss/train': 1.1170015335083008} 08/31/2021 08:59:14 - INFO - __main__ - Step 108869: {'lr': 8.938803092621284e-05, 'samples': 20902848, 'steps': 108868, 'loss/train': 1.1348098516464233} 08/31/2021 08:59:15 - INFO - __main__ - Step 108870: {'lr': 8.938396424826603e-05, 'samples': 20903040, 'steps': 108869, 'loss/train': 0.8730552196502686} 08/31/2021 08:59:16 - INFO - __main__ - Step 108871: {'lr': 8.937989764269031e-05, 'samples': 20903232, 'steps': 108870, 'loss/train': 1.27863609790802} 08/31/2021 08:59:17 - INFO - __main__ - Step 108872: {'lr': 8.937583110948755e-05, 'samples': 20903424, 'steps': 108871, 'loss/train': 1.2391345500946045} 08/31/2021 08:59:17 - INFO - __main__ - Step 108873: {'lr': 8.937176464865953e-05, 'samples': 20903616, 'steps': 108872, 'loss/train': 1.7267706394195557} 08/31/2021 08:59:17 - INFO - __main__ - Step 108874: {'lr': 8.936769826020813e-05, 'samples': 20903808, 'steps': 108873, 'loss/train': 2.066495895385742} 08/31/2021 08:59:18 - INFO - __main__ - Step 108875: {'lr': 8.936363194413516e-05, 'samples': 20904000, 'steps': 108874, 'loss/train': 1.5404599905014038} 08/31/2021 08:59:19 - INFO - __main__ - Step 108876: {'lr': 8.935956570044249e-05, 'samples': 20904192, 'steps': 108875, 'loss/train': 1.2717262506484985} 08/31/2021 08:59:20 - INFO - __main__ - Step 108877: {'lr': 8.935549952913189e-05, 'samples': 20904384, 'steps': 108876, 'loss/train': 1.6179074048995972} 08/31/2021 08:59:20 - INFO - __main__ - Step 108878: {'lr': 8.935143343020521e-05, 'samples': 20904576, 'steps': 108877, 'loss/train': 1.4266300201416016} 08/31/2021 08:59:20 - INFO - __main__ - Step 108879: {'lr': 8.934736740366433e-05, 'samples': 20904768, 'steps': 108878, 'loss/train': 1.179142951965332} 08/31/2021 08:59:21 - INFO - __main__ - Step 108880: {'lr': 8.934330144951103e-05, 'samples': 20904960, 'steps': 108879, 'loss/train': 1.3458154201507568} 08/31/2021 08:59:23 - INFO - __main__ - Step 108881: {'lr': 8.933923556774725e-05, 'samples': 20905152, 'steps': 108880, 'loss/train': 1.0694684982299805} 08/31/2021 08:59:23 - INFO - __main__ - Step 108882: {'lr': 8.933516975837463e-05, 'samples': 20905344, 'steps': 108881, 'loss/train': 0.8567676544189453} 08/31/2021 08:59:23 - INFO - __main__ - Step 108883: {'lr': 8.933110402139514e-05, 'samples': 20905536, 'steps': 108882, 'loss/train': 1.8148062229156494} 08/31/2021 08:59:24 - INFO - __main__ - Step 108884: {'lr': 8.932703835681052e-05, 'samples': 20905728, 'steps': 108883, 'loss/train': 1.0114177465438843} 08/31/2021 08:59:24 - INFO - __main__ - Step 108885: {'lr': 8.93229727646227e-05, 'samples': 20905920, 'steps': 108884, 'loss/train': 1.1088820695877075} 08/31/2021 08:59:24 - INFO - __main__ - Step 108886: {'lr': 8.931890724483346e-05, 'samples': 20906112, 'steps': 108885, 'loss/train': 1.519532322883606} 08/31/2021 08:59:26 - INFO - __main__ - Step 108887: {'lr': 8.931484179744465e-05, 'samples': 20906304, 'steps': 108886, 'loss/train': 1.732107162475586} 08/31/2021 08:59:27 - INFO - __main__ - Step 108888: {'lr': 8.931077642245808e-05, 'samples': 20906496, 'steps': 108887, 'loss/train': 1.1260453462600708} 08/31/2021 08:59:27 - INFO - __main__ - Step 108889: {'lr': 8.930671111987559e-05, 'samples': 20906688, 'steps': 108888, 'loss/train': 1.8538342714309692} 08/31/2021 08:59:28 - INFO - __main__ - Step 108890: {'lr': 8.930264588969903e-05, 'samples': 20906880, 'steps': 108889, 'loss/train': 1.2278493642807007} 08/31/2021 08:59:28 - INFO - __main__ - Step 108891: {'lr': 8.929858073193021e-05, 'samples': 20907072, 'steps': 108890, 'loss/train': 0.3460969924926758} 08/31/2021 08:59:28 - INFO - __main__ - Step 108892: {'lr': 8.929451564657095e-05, 'samples': 20907264, 'steps': 108891, 'loss/train': 0.03560056537389755} 08/31/2021 08:59:30 - INFO - __main__ - Step 108893: {'lr': 8.929045063362312e-05, 'samples': 20907456, 'steps': 108892, 'loss/train': 0.2746908366680145} 08/31/2021 08:59:30 - INFO - __main__ - Step 108894: {'lr': 8.928638569308862e-05, 'samples': 20907648, 'steps': 108893, 'loss/train': 1.144968032836914} 08/31/2021 08:59:31 - INFO - __main__ - Step 108895: {'lr': 8.928232082496912e-05, 'samples': 20907840, 'steps': 108894, 'loss/train': 1.2772157192230225} 08/31/2021 08:59:31 - INFO - __main__ - Step 108896: {'lr': 8.927825602926651e-05, 'samples': 20908032, 'steps': 108895, 'loss/train': 1.4944267272949219} 08/31/2021 08:59:31 - INFO - __main__ - Step 108897: {'lr': 8.927419130598264e-05, 'samples': 20908224, 'steps': 108896, 'loss/train': 1.185381531715393} 08/31/2021 08:59:33 - INFO - __main__ - Step 108898: {'lr': 8.927012665511933e-05, 'samples': 20908416, 'steps': 108897, 'loss/train': 0.8021140694618225} 08/31/2021 08:59:34 - INFO - __main__ - Step 108899: {'lr': 8.926606207667846e-05, 'samples': 20908608, 'steps': 108898, 'loss/train': 0.6130889654159546} 08/31/2021 08:59:34 - INFO - __main__ - Step 108900: {'lr': 8.926199757066178e-05, 'samples': 20908800, 'steps': 108899, 'loss/train': 1.5224517583847046} 08/31/2021 08:59:34 - INFO - __main__ - Step 108901: {'lr': 8.925793313707117e-05, 'samples': 20908992, 'steps': 108900, 'loss/train': 1.2809101343154907} 08/31/2021 08:59:35 - INFO - __main__ - Step 108902: {'lr': 8.925386877590847e-05, 'samples': 20909184, 'steps': 108901, 'loss/train': 1.2563742399215698} 08/31/2021 08:59:36 - INFO - __main__ - Step 108903: {'lr': 8.924980448717548e-05, 'samples': 20909376, 'steps': 108902, 'loss/train': 1.2216646671295166} 08/31/2021 08:59:37 - INFO - __main__ - Step 108904: {'lr': 8.924574027087406e-05, 'samples': 20909568, 'steps': 108903, 'loss/train': 1.1945393085479736} 08/31/2021 08:59:37 - INFO - __main__ - Step 108905: {'lr': 8.924167612700604e-05, 'samples': 20909760, 'steps': 108904, 'loss/train': 0.27808263897895813} 08/31/2021 08:59:37 - INFO - __main__ - Step 108906: {'lr': 8.92376120555732e-05, 'samples': 20909952, 'steps': 108905, 'loss/train': 1.360975980758667} 08/31/2021 08:59:38 - INFO - __main__ - Step 108907: {'lr': 8.923354805657746e-05, 'samples': 20910144, 'steps': 108906, 'loss/train': 1.3086094856262207} 08/31/2021 08:59:39 - INFO - __main__ - Step 108908: {'lr': 8.922948413002065e-05, 'samples': 20910336, 'steps': 108907, 'loss/train': 1.470322847366333} 08/31/2021 08:59:40 - INFO - __main__ - Step 108909: {'lr': 8.922542027590449e-05, 'samples': 20910528, 'steps': 108908, 'loss/train': 1.1837115287780762} 08/31/2021 08:59:40 - INFO - __main__ - Step 108910: {'lr': 8.922135649423088e-05, 'samples': 20910720, 'steps': 108909, 'loss/train': 0.20431163907051086} 08/31/2021 08:59:40 - INFO - __main__ - Step 108911: {'lr': 8.921729278500163e-05, 'samples': 20910912, 'steps': 108910, 'loss/train': 0.5541070699691772} 08/31/2021 08:59:41 - INFO - __main__ - Step 108912: {'lr': 8.921322914821859e-05, 'samples': 20911104, 'steps': 108911, 'loss/train': 1.003592610359192} 08/31/2021 08:59:41 - INFO - __main__ - Step 108913: {'lr': 8.920916558388359e-05, 'samples': 20911296, 'steps': 108912, 'loss/train': 1.1919150352478027} 08/31/2021 08:59:43 - INFO - __main__ - Step 108914: {'lr': 8.920510209199844e-05, 'samples': 20911488, 'steps': 108913, 'loss/train': 1.6479636430740356} 08/31/2021 08:59:43 - INFO - __main__ - Step 108915: {'lr': 8.920103867256502e-05, 'samples': 20911680, 'steps': 108914, 'loss/train': 1.3226302862167358} 08/31/2021 08:59:43 - INFO - __main__ - Step 108916: {'lr': 8.919697532558512e-05, 'samples': 20911872, 'steps': 108915, 'loss/train': 0.5744799375534058} 08/31/2021 08:59:44 - INFO - __main__ - Step 108917: {'lr': 8.91929120510606e-05, 'samples': 20912064, 'steps': 108916, 'loss/train': 1.0290842056274414} 08/31/2021 08:59:44 - INFO - __main__ - Step 108918: {'lr': 8.918884884899323e-05, 'samples': 20912256, 'steps': 108917, 'loss/train': 0.6251280903816223} 08/31/2021 08:59:46 - INFO - __main__ - Step 108919: {'lr': 8.91847857193849e-05, 'samples': 20912448, 'steps': 108918, 'loss/train': 1.4524340629577637} 08/31/2021 08:59:47 - INFO - __main__ - Step 108920: {'lr': 8.918072266223742e-05, 'samples': 20912640, 'steps': 108919, 'loss/train': 0.0205057542771101} 08/31/2021 08:59:47 - INFO - __main__ - Step 108921: {'lr': 8.917665967755272e-05, 'samples': 20912832, 'steps': 108920, 'loss/train': 1.5337246656417847} 08/31/2021 08:59:47 - INFO - __main__ - Step 108922: {'lr': 8.917259676533246e-05, 'samples': 20913024, 'steps': 108921, 'loss/train': 0.6092886328697205} 08/31/2021 08:59:48 - INFO - __main__ - Step 108923: {'lr': 8.916853392557852e-05, 'samples': 20913216, 'steps': 108922, 'loss/train': 1.2934820652008057} 08/31/2021 08:59:49 - INFO - __main__ - Step 108924: {'lr': 8.916447115829279e-05, 'samples': 20913408, 'steps': 108923, 'loss/train': 1.4080145359039307} 08/31/2021 08:59:50 - INFO - __main__ - Step 108925: {'lr': 8.916040846347707e-05, 'samples': 20913600, 'steps': 108924, 'loss/train': 0.6266003251075745} 08/31/2021 08:59:51 - INFO - __main__ - Step 108926: {'lr': 8.915634584113314e-05, 'samples': 20913792, 'steps': 108925, 'loss/train': 1.1483691930770874} 08/31/2021 08:59:51 - INFO - __main__ - Step 108927: {'lr': 8.91522832912629e-05, 'samples': 20913984, 'steps': 108926, 'loss/train': 1.5411723852157593} 08/31/2021 08:59:51 - INFO - __main__ - Step 108928: {'lr': 8.914822081386817e-05, 'samples': 20914176, 'steps': 108927, 'loss/train': 1.0790730714797974} 08/31/2021 08:59:52 - INFO - __main__ - Step 108929: {'lr': 8.914415840895076e-05, 'samples': 20914368, 'steps': 108928, 'loss/train': 1.0381885766983032} 08/31/2021 08:59:53 - INFO - __main__ - Step 108930: {'lr': 8.914009607651253e-05, 'samples': 20914560, 'steps': 108929, 'loss/train': 0.030961234122514725} 08/31/2021 08:59:54 - INFO - __main__ - Step 108931: {'lr': 8.913603381655528e-05, 'samples': 20914752, 'steps': 108930, 'loss/train': 1.3793059587478638} 08/31/2021 08:59:54 - INFO - __main__ - Step 108932: {'lr': 8.913197162908085e-05, 'samples': 20914944, 'steps': 108931, 'loss/train': 0.7745879888534546} 08/31/2021 08:59:54 - INFO - __main__ - Step 108933: {'lr': 8.912790951409105e-05, 'samples': 20915136, 'steps': 108932, 'loss/train': 0.5042415261268616} 08/31/2021 08:59:55 - INFO - __main__ - Step 108934: {'lr': 8.912384747158783e-05, 'samples': 20915328, 'steps': 108933, 'loss/train': 0.9113548994064331} 08/31/2021 08:59:56 - INFO - __main__ - Step 108935: {'lr': 8.911978550157284e-05, 'samples': 20915520, 'steps': 108934, 'loss/train': 1.0534864664077759} 08/31/2021 08:59:57 - INFO - __main__ - Step 108936: {'lr': 8.911572360404802e-05, 'samples': 20915712, 'steps': 108935, 'loss/train': 1.0732462406158447} 08/31/2021 08:59:57 - INFO - __main__ - Step 108937: {'lr': 8.911166177901514e-05, 'samples': 20915904, 'steps': 108936, 'loss/train': 0.6463776230812073} 08/31/2021 08:59:57 - INFO - __main__ - Step 108938: {'lr': 8.910760002647605e-05, 'samples': 20916096, 'steps': 108937, 'loss/train': 0.964496374130249} 08/31/2021 08:59:58 - INFO - __main__ - Step 108939: {'lr': 8.910353834643262e-05, 'samples': 20916288, 'steps': 108938, 'loss/train': 1.1391679048538208} 08/31/2021 08:59:59 - INFO - __main__ - Step 108940: {'lr': 8.909947673888666e-05, 'samples': 20916480, 'steps': 108939, 'loss/train': 1.1972980499267578} 08/31/2021 09:00:00 - INFO - __main__ - Step 108941: {'lr': 8.909541520383996e-05, 'samples': 20916672, 'steps': 108940, 'loss/train': 2.019324541091919} 08/31/2021 09:00:00 - INFO - __main__ - Step 108942: {'lr': 8.90913537412944e-05, 'samples': 20916864, 'steps': 108941, 'loss/train': 1.2142367362976074} 08/31/2021 09:00:00 - INFO - __main__ - Step 108943: {'lr': 8.908729235125179e-05, 'samples': 20917056, 'steps': 108942, 'loss/train': 0.4603906571865082} 08/31/2021 09:00:01 - INFO - __main__ - Step 108944: {'lr': 8.908323103371396e-05, 'samples': 20917248, 'steps': 108943, 'loss/train': 1.1870008707046509} 08/31/2021 09:00:02 - INFO - __main__ - Step 108945: {'lr': 8.907916978868278e-05, 'samples': 20917440, 'steps': 108944, 'loss/train': 1.2969402074813843} 08/31/2021 09:00:03 - INFO - __main__ - Step 108946: {'lr': 8.907510861616e-05, 'samples': 20917632, 'steps': 108945, 'loss/train': 0.9425232410430908} 08/31/2021 09:00:03 - INFO - __main__ - Step 108947: {'lr': 8.90710475161475e-05, 'samples': 20917824, 'steps': 108946, 'loss/train': 1.309138298034668} 08/31/2021 09:00:03 - INFO - __main__ - Step 108948: {'lr': 8.906698648864719e-05, 'samples': 20918016, 'steps': 108947, 'loss/train': 1.0077166557312012} 08/31/2021 09:00:04 - INFO - __main__ - Step 108949: {'lr': 8.906292553366072e-05, 'samples': 20918208, 'steps': 108948, 'loss/train': 1.3742092847824097} 08/31/2021 09:00:05 - INFO - __main__ - Step 108950: {'lr': 8.905886465119003e-05, 'samples': 20918400, 'steps': 108949, 'loss/train': 1.0259530544281006} 08/31/2021 09:00:06 - INFO - __main__ - Step 108951: {'lr': 8.905480384123693e-05, 'samples': 20918592, 'steps': 108950, 'loss/train': 2.6474263668060303} 08/31/2021 09:00:06 - INFO - __main__ - Step 108952: {'lr': 8.905074310380323e-05, 'samples': 20918784, 'steps': 108951, 'loss/train': 0.9011325240135193} 08/31/2021 09:00:07 - INFO - __main__ - Step 108953: {'lr': 8.90466824388908e-05, 'samples': 20918976, 'steps': 108952, 'loss/train': 1.574777364730835} 08/31/2021 09:00:07 - INFO - __main__ - Step 108954: {'lr': 8.904262184650148e-05, 'samples': 20919168, 'steps': 108953, 'loss/train': 1.239075779914856} 08/31/2021 09:00:07 - INFO - __main__ - Step 108955: {'lr': 8.903856132663701e-05, 'samples': 20919360, 'steps': 108954, 'loss/train': 0.33842456340789795} 08/31/2021 09:00:09 - INFO - __main__ - Step 108956: {'lr': 8.903450087929931e-05, 'samples': 20919552, 'steps': 108955, 'loss/train': 0.3634588122367859} 08/31/2021 09:00:09 - INFO - __main__ - Step 108957: {'lr': 8.903044050449019e-05, 'samples': 20919744, 'steps': 108956, 'loss/train': 1.1628930568695068} 08/31/2021 09:00:10 - INFO - __main__ - Step 108958: {'lr': 8.902638020221145e-05, 'samples': 20919936, 'steps': 108957, 'loss/train': 0.7023959159851074} 08/31/2021 09:00:10 - INFO - __main__ - Step 108959: {'lr': 8.902231997246496e-05, 'samples': 20920128, 'steps': 108958, 'loss/train': 1.221039056777954} 08/31/2021 09:00:10 - INFO - __main__ - Step 108960: {'lr': 8.901825981525252e-05, 'samples': 20920320, 'steps': 108959, 'loss/train': 1.638770341873169} 08/31/2021 09:00:12 - INFO - __main__ - Step 108961: {'lr': 8.901419973057603e-05, 'samples': 20920512, 'steps': 108960, 'loss/train': 0.8890554904937744} 08/31/2021 09:00:12 - INFO - __main__ - Step 108962: {'lr': 8.901013971843722e-05, 'samples': 20920704, 'steps': 108961, 'loss/train': 1.307104468345642} 08/31/2021 09:00:12 - INFO - __main__ - Step 108963: {'lr': 8.900607977883792e-05, 'samples': 20920896, 'steps': 108962, 'loss/train': 1.0929218530654907} 08/31/2021 09:00:13 - INFO - __main__ - Step 108964: {'lr': 8.900201991178e-05, 'samples': 20921088, 'steps': 108963, 'loss/train': 1.2926992177963257} 08/31/2021 09:00:13 - INFO - __main__ - Step 108965: {'lr': 8.89979601172653e-05, 'samples': 20921280, 'steps': 108964, 'loss/train': 1.1304049491882324} 08/31/2021 09:00:15 - INFO - __main__ - Step 108966: {'lr': 8.899390039529561e-05, 'samples': 20921472, 'steps': 108965, 'loss/train': 1.2284339666366577} 08/31/2021 09:00:15 - INFO - __main__ - Step 108967: {'lr': 8.898984074587282e-05, 'samples': 20921664, 'steps': 108966, 'loss/train': 0.9265618920326233} 08/31/2021 09:00:16 - INFO - __main__ - Step 108968: {'lr': 8.89857811689987e-05, 'samples': 20921856, 'steps': 108967, 'loss/train': 0.8221815228462219} 08/31/2021 09:00:16 - INFO - __main__ - Step 108969: {'lr': 8.89817216646751e-05, 'samples': 20922048, 'steps': 108968, 'loss/train': 0.11666624248027802} 08/31/2021 09:00:16 - INFO - __main__ - Step 108970: {'lr': 8.897766223290385e-05, 'samples': 20922240, 'steps': 108969, 'loss/train': 1.4386613368988037} 08/31/2021 09:00:17 - INFO - __main__ - Step 108971: {'lr': 8.897360287368681e-05, 'samples': 20922432, 'steps': 108970, 'loss/train': 0.9835116267204285} 08/31/2021 09:00:18 - INFO - __main__ - Step 108972: {'lr': 8.896954358702574e-05, 'samples': 20922624, 'steps': 108971, 'loss/train': 1.1885801553726196} 08/31/2021 09:00:18 - INFO - __main__ - Step 108973: {'lr': 8.896548437292254e-05, 'samples': 20922816, 'steps': 108972, 'loss/train': 1.539350986480713} 08/31/2021 09:00:19 - INFO - __main__ - Step 108974: {'lr': 8.896142523137899e-05, 'samples': 20923008, 'steps': 108973, 'loss/train': 1.0701088905334473} 08/31/2021 09:00:19 - INFO - __main__ - Step 108975: {'lr': 8.895736616239703e-05, 'samples': 20923200, 'steps': 108974, 'loss/train': 0.7154566049575806} 08/31/2021 09:00:20 - INFO - __main__ - Step 108976: {'lr': 8.89533071659783e-05, 'samples': 20923392, 'steps': 108975, 'loss/train': 0.8944734930992126} 08/31/2021 09:00:22 - INFO - __main__ - Step 108977: {'lr': 8.894924824212475e-05, 'samples': 20923584, 'steps': 108976, 'loss/train': 0.7820467948913574} 08/31/2021 09:00:22 - INFO - __main__ - Step 108978: {'lr': 8.894518939083815e-05, 'samples': 20923776, 'steps': 108977, 'loss/train': 0.839404284954071} 08/31/2021 09:00:23 - INFO - __main__ - Step 108979: {'lr': 8.894113061212039e-05, 'samples': 20923968, 'steps': 108978, 'loss/train': 0.5989570021629333} 08/31/2021 09:00:23 - INFO - __main__ - Step 108980: {'lr': 8.893707190597325e-05, 'samples': 20924160, 'steps': 108979, 'loss/train': 1.1090022325515747} 08/31/2021 09:00:23 - INFO - __main__ - Step 108981: {'lr': 8.893301327239859e-05, 'samples': 20924352, 'steps': 108980, 'loss/train': 0.5609883666038513} 08/31/2021 09:00:25 - INFO - __main__ - Step 108982: {'lr': 8.892895471139822e-05, 'samples': 20924544, 'steps': 108981, 'loss/train': 0.6018509864807129} 08/31/2021 09:00:25 - INFO - __main__ - Step 108983: {'lr': 8.892489622297397e-05, 'samples': 20924736, 'steps': 108982, 'loss/train': 0.026574771851301193} 08/31/2021 09:00:26 - INFO - __main__ - Step 108984: {'lr': 8.89208378071277e-05, 'samples': 20924928, 'steps': 108983, 'loss/train': 1.037451148033142} 08/31/2021 09:00:26 - INFO - __main__ - Step 108985: {'lr': 8.891677946386123e-05, 'samples': 20925120, 'steps': 108984, 'loss/train': 1.6651583909988403} 08/31/2021 09:00:26 - INFO - __main__ - Step 108986: {'lr': 8.891272119317634e-05, 'samples': 20925312, 'steps': 108985, 'loss/train': 1.8141553401947021} 08/31/2021 09:00:28 - INFO - __main__ - Step 108987: {'lr': 8.89086629950749e-05, 'samples': 20925504, 'steps': 108986, 'loss/train': 0.154721200466156} 08/31/2021 09:00:29 - INFO - __main__ - Step 108988: {'lr': 8.890460486955882e-05, 'samples': 20925696, 'steps': 108987, 'loss/train': 0.3215935528278351} 08/31/2021 09:00:29 - INFO - __main__ - Step 108989: {'lr': 8.890054681662976e-05, 'samples': 20925888, 'steps': 108988, 'loss/train': 1.0719841718673706} 08/31/2021 09:00:29 - INFO - __main__ - Step 108990: {'lr': 8.889648883628961e-05, 'samples': 20926080, 'steps': 108989, 'loss/train': 1.3545464277267456} 08/31/2021 09:00:30 - INFO - __main__ - Step 108991: {'lr': 8.889243092854021e-05, 'samples': 20926272, 'steps': 108990, 'loss/train': 1.3218673467636108} 08/31/2021 09:00:31 - INFO - __main__ - Step 108992: {'lr': 8.888837309338344e-05, 'samples': 20926464, 'steps': 108991, 'loss/train': 0.4805091321468353} 08/31/2021 09:00:31 - INFO - __main__ - Step 108993: {'lr': 8.888431533082104e-05, 'samples': 20926656, 'steps': 108992, 'loss/train': 0.8990511298179626} 08/31/2021 09:00:32 - INFO - __main__ - Step 108994: {'lr': 8.888025764085489e-05, 'samples': 20926848, 'steps': 108993, 'loss/train': 1.8059059381484985} 08/31/2021 09:00:32 - INFO - __main__ - Step 108995: {'lr': 8.887620002348681e-05, 'samples': 20927040, 'steps': 108994, 'loss/train': 1.4892398118972778} 08/31/2021 09:00:33 - INFO - __main__ - Step 108996: {'lr': 8.887214247871864e-05, 'samples': 20927232, 'steps': 108995, 'loss/train': 0.4968765377998352} 08/31/2021 09:00:34 - INFO - __main__ - Step 108997: {'lr': 8.886808500655219e-05, 'samples': 20927424, 'steps': 108996, 'loss/train': 0.754946768283844} 08/31/2021 09:00:35 - INFO - __main__ - Step 108998: {'lr': 8.886402760698931e-05, 'samples': 20927616, 'steps': 108997, 'loss/train': 1.0000470876693726} 08/31/2021 09:00:35 - INFO - __main__ - Step 108999: {'lr': 8.885997028003179e-05, 'samples': 20927808, 'steps': 108998, 'loss/train': 0.7539471387863159} 08/31/2021 09:00:35 - INFO - __main__ - Step 109000: {'lr': 8.885591302568147e-05, 'samples': 20928000, 'steps': 108999, 'loss/train': 0.05879274010658264} 08/31/2021 09:00:36 - INFO - __main__ - Step 109001: {'lr': 8.88518558439402e-05, 'samples': 20928192, 'steps': 109000, 'loss/train': 0.9486022591590881} 08/31/2021 09:00:37 - INFO - __main__ - Step 109002: {'lr': 8.884779873480991e-05, 'samples': 20928384, 'steps': 109001, 'loss/train': 1.0017995834350586} 08/31/2021 09:00:38 - INFO - __main__ - Step 109003: {'lr': 8.884374169829221e-05, 'samples': 20928576, 'steps': 109002, 'loss/train': 1.4072967767715454} 08/31/2021 09:00:38 - INFO - __main__ - Step 109004: {'lr': 8.883968473438903e-05, 'samples': 20928768, 'steps': 109003, 'loss/train': 1.3196192979812622} 08/31/2021 09:00:38 - INFO - __main__ - Step 109005: {'lr': 8.88356278431022e-05, 'samples': 20928960, 'steps': 109004, 'loss/train': 1.161914587020874} 08/31/2021 09:00:39 - INFO - __main__ - Step 109006: {'lr': 8.883157102443354e-05, 'samples': 20929152, 'steps': 109005, 'loss/train': 2.0097572803497314} 08/31/2021 09:00:39 - INFO - __main__ - Step 109007: {'lr': 8.88275142783849e-05, 'samples': 20929344, 'steps': 109006, 'loss/train': 1.107763648033142} 08/31/2021 09:00:41 - INFO - __main__ - Step 109008: {'lr': 8.88234576049581e-05, 'samples': 20929536, 'steps': 109007, 'loss/train': 0.9140473008155823} 08/31/2021 09:00:41 - INFO - __main__ - Step 109009: {'lr': 8.881940100415495e-05, 'samples': 20929728, 'steps': 109008, 'loss/train': 1.247394323348999} 08/31/2021 09:00:42 - INFO - __main__ - Step 109010: {'lr': 8.881534447597731e-05, 'samples': 20929920, 'steps': 109009, 'loss/train': 1.496502161026001} 08/31/2021 09:00:42 - INFO - __main__ - Step 109011: {'lr': 8.881128802042695e-05, 'samples': 20930112, 'steps': 109010, 'loss/train': 1.7696480751037598} 08/31/2021 09:00:42 - INFO - __main__ - Step 109012: {'lr': 8.880723163750579e-05, 'samples': 20930304, 'steps': 109011, 'loss/train': 0.6062515377998352} 08/31/2021 09:00:44 - INFO - __main__ - Step 109013: {'lr': 8.880317532721558e-05, 'samples': 20930496, 'steps': 109012, 'loss/train': 1.1806474924087524} 08/31/2021 09:00:44 - INFO - __main__ - Step 109014: {'lr': 8.879911908955815e-05, 'samples': 20930688, 'steps': 109013, 'loss/train': 1.144115924835205} 08/31/2021 09:00:45 - INFO - __main__ - Step 109015: {'lr': 8.879506292453546e-05, 'samples': 20930880, 'steps': 109014, 'loss/train': 1.7117233276367188} 08/31/2021 09:00:45 - INFO - __main__ - Step 109016: {'lr': 8.879100683214913e-05, 'samples': 20931072, 'steps': 109015, 'loss/train': 1.034560203552246} 08/31/2021 09:00:45 - INFO - __main__ - Step 109017: {'lr': 8.87869508124011e-05, 'samples': 20931264, 'steps': 109016, 'loss/train': 0.9755954146385193} 08/31/2021 09:00:47 - INFO - __main__ - Step 109018: {'lr': 8.878289486529317e-05, 'samples': 20931456, 'steps': 109017, 'loss/train': 1.335561752319336} 08/31/2021 09:00:47 - INFO - __main__ - Step 109019: {'lr': 8.877883899082717e-05, 'samples': 20931648, 'steps': 109018, 'loss/train': 0.6837214231491089} 08/31/2021 09:00:48 - INFO - __main__ - Step 109020: {'lr': 8.877478318900494e-05, 'samples': 20931840, 'steps': 109019, 'loss/train': 0.629725992679596} 08/31/2021 09:00:48 - INFO - __main__ - Step 109021: {'lr': 8.877072745982834e-05, 'samples': 20932032, 'steps': 109020, 'loss/train': 1.1806882619857788} 08/31/2021 09:00:48 - INFO - __main__ - Step 109022: {'lr': 8.876667180329912e-05, 'samples': 20932224, 'steps': 109021, 'loss/train': 0.63785719871521} 08/31/2021 09:00:50 - INFO - __main__ - Step 109023: {'lr': 8.876261621941916e-05, 'samples': 20932416, 'steps': 109022, 'loss/train': 2.085789918899536} 08/31/2021 09:00:50 - INFO - __main__ - Step 109024: {'lr': 8.87585607081903e-05, 'samples': 20932608, 'steps': 109023, 'loss/train': 1.2427409887313843} 08/31/2021 09:00:51 - INFO - __main__ - Step 109025: {'lr': 8.875450526961431e-05, 'samples': 20932800, 'steps': 109024, 'loss/train': 1.437042236328125} 08/31/2021 09:00:51 - INFO - __main__ - Step 109026: {'lr': 8.875044990369308e-05, 'samples': 20932992, 'steps': 109025, 'loss/train': 0.026333021000027657} 08/31/2021 09:00:51 - INFO - __main__ - Step 109027: {'lr': 8.874639461042838e-05, 'samples': 20933184, 'steps': 109026, 'loss/train': 0.8284927010536194} 08/31/2021 09:00:54 - INFO - __main__ - Step 109028: {'lr': 8.87423393898221e-05, 'samples': 20933376, 'steps': 109027, 'loss/train': 0.17411789298057556} 08/31/2021 09:00:54 - INFO - __main__ - Step 109029: {'lr': 8.87382842418761e-05, 'samples': 20933568, 'steps': 109028, 'loss/train': 0.7555272579193115} 08/31/2021 09:00:54 - INFO - __main__ - Step 109030: {'lr': 8.873422916659207e-05, 'samples': 20933760, 'steps': 109029, 'loss/train': 1.0849831104278564} 08/31/2021 09:00:55 - INFO - __main__ - Step 109031: {'lr': 8.873017416397189e-05, 'samples': 20933952, 'steps': 109030, 'loss/train': 1.6739224195480347} 08/31/2021 09:00:55 - INFO - __main__ - Step 109032: {'lr': 8.872611923401741e-05, 'samples': 20934144, 'steps': 109031, 'loss/train': 1.2656043767929077} 08/31/2021 09:00:55 - INFO - __main__ - Step 109033: {'lr': 8.872206437673045e-05, 'samples': 20934336, 'steps': 109032, 'loss/train': 0.2456987351179123} 08/31/2021 09:00:57 - INFO - __main__ - Step 109034: {'lr': 8.871800959211284e-05, 'samples': 20934528, 'steps': 109033, 'loss/train': 1.0223407745361328} 08/31/2021 09:00:57 - INFO - __main__ - Step 109035: {'lr': 8.871395488016642e-05, 'samples': 20934720, 'steps': 109034, 'loss/train': 0.8480657935142517} 08/31/2021 09:00:58 - INFO - __main__ - Step 109036: {'lr': 8.870990024089299e-05, 'samples': 20934912, 'steps': 109035, 'loss/train': 1.163283109664917} 08/31/2021 09:00:58 - INFO - __main__ - Step 109037: {'lr': 8.870584567429437e-05, 'samples': 20935104, 'steps': 109036, 'loss/train': 0.865613579750061} 08/31/2021 09:00:59 - INFO - __main__ - Step 109038: {'lr': 8.870179118037244e-05, 'samples': 20935296, 'steps': 109037, 'loss/train': 0.9829911589622498} 08/31/2021 09:01:00 - INFO - __main__ - Step 109039: {'lr': 8.869773675912899e-05, 'samples': 20935488, 'steps': 109038, 'loss/train': 0.5126933455467224} 08/31/2021 09:01:00 - INFO - __main__ - Step 109040: {'lr': 8.869368241056583e-05, 'samples': 20935680, 'steps': 109039, 'loss/train': 1.2944695949554443} 08/31/2021 09:01:01 - INFO - __main__ - Step 109041: {'lr': 8.868962813468484e-05, 'samples': 20935872, 'steps': 109040, 'loss/train': 1.274835228919983} 08/31/2021 09:01:01 - INFO - __main__ - Step 109042: {'lr': 8.868557393148787e-05, 'samples': 20936064, 'steps': 109041, 'loss/train': 0.9752923250198364} 08/31/2021 09:01:02 - INFO - __main__ - Step 109043: {'lr': 8.868151980097661e-05, 'samples': 20936256, 'steps': 109042, 'loss/train': 1.631321668624878} 08/31/2021 09:01:03 - INFO - __main__ - Step 109044: {'lr': 8.867746574315299e-05, 'samples': 20936448, 'steps': 109043, 'loss/train': 1.541251301765442} 08/31/2021 09:01:04 - INFO - __main__ - Step 109045: {'lr': 8.867341175801879e-05, 'samples': 20936640, 'steps': 109044, 'loss/train': 1.2588810920715332} 08/31/2021 09:01:04 - INFO - __main__ - Step 109046: {'lr': 8.866935784557587e-05, 'samples': 20936832, 'steps': 109045, 'loss/train': 0.516878604888916} 08/31/2021 09:01:04 - INFO - __main__ - Step 109047: {'lr': 8.866530400582607e-05, 'samples': 20937024, 'steps': 109046, 'loss/train': 0.5079734921455383} 08/31/2021 09:01:05 - INFO - __main__ - Step 109048: {'lr': 8.866125023877116e-05, 'samples': 20937216, 'steps': 109047, 'loss/train': 0.1684078723192215} 08/31/2021 09:01:06 - INFO - __main__ - Step 109049: {'lr': 8.865719654441302e-05, 'samples': 20937408, 'steps': 109048, 'loss/train': 1.0011563301086426} 08/31/2021 09:01:07 - INFO - __main__ - Step 109050: {'lr': 8.865314292275345e-05, 'samples': 20937600, 'steps': 109049, 'loss/train': 1.041439175605774} 08/31/2021 09:01:07 - INFO - __main__ - Step 109051: {'lr': 8.864908937379429e-05, 'samples': 20937792, 'steps': 109050, 'loss/train': 0.7902605533599854} 08/31/2021 09:01:07 - INFO - __main__ - Step 109052: {'lr': 8.864503589753733e-05, 'samples': 20937984, 'steps': 109051, 'loss/train': 1.306102991104126} 08/31/2021 09:01:08 - INFO - __main__ - Step 109053: {'lr': 8.864098249398448e-05, 'samples': 20938176, 'steps': 109052, 'loss/train': 0.4938145577907562} 08/31/2021 09:01:09 - INFO - __main__ - Step 109054: {'lr': 8.863692916313749e-05, 'samples': 20938368, 'steps': 109053, 'loss/train': 1.1586209535598755} 08/31/2021 09:01:10 - INFO - __main__ - Step 109055: {'lr': 8.863287590499827e-05, 'samples': 20938560, 'steps': 109054, 'loss/train': 0.9210852384567261} 08/31/2021 09:01:10 - INFO - __main__ - Step 109056: {'lr': 8.862882271956852e-05, 'samples': 20938752, 'steps': 109055, 'loss/train': 1.417323112487793} 08/31/2021 09:01:10 - INFO - __main__ - Step 109057: {'lr': 8.862476960685014e-05, 'samples': 20938944, 'steps': 109056, 'loss/train': 1.9223824739456177} 08/31/2021 09:01:11 - INFO - __main__ - Step 109058: {'lr': 8.862071656684495e-05, 'samples': 20939136, 'steps': 109057, 'loss/train': 1.1761295795440674} 08/31/2021 09:01:12 - INFO - __main__ - Step 109059: {'lr': 8.861666359955475e-05, 'samples': 20939328, 'steps': 109058, 'loss/train': 0.8743367791175842} 08/31/2021 09:01:13 - INFO - __main__ - Step 109060: {'lr': 8.861261070498142e-05, 'samples': 20939520, 'steps': 109059, 'loss/train': 1.0133329629898071} 08/31/2021 09:01:13 - INFO - __main__ - Step 109061: {'lr': 8.860855788312674e-05, 'samples': 20939712, 'steps': 109060, 'loss/train': 1.0785484313964844} 08/31/2021 09:01:13 - INFO - __main__ - Step 109062: {'lr': 8.860450513399257e-05, 'samples': 20939904, 'steps': 109061, 'loss/train': 0.3637886941432953} 08/31/2021 09:01:14 - INFO - __main__ - Step 109063: {'lr': 8.860045245758069e-05, 'samples': 20940096, 'steps': 109062, 'loss/train': 1.3162493705749512} 08/31/2021 09:01:14 - INFO - __main__ - Step 109064: {'lr': 8.859639985389297e-05, 'samples': 20940288, 'steps': 109063, 'loss/train': 0.7708278298377991} 08/31/2021 09:01:16 - INFO - __main__ - Step 109065: {'lr': 8.859234732293126e-05, 'samples': 20940480, 'steps': 109064, 'loss/train': 1.0654596090316772} 08/31/2021 09:01:16 - INFO - __main__ - Step 109066: {'lr': 8.85882948646973e-05, 'samples': 20940672, 'steps': 109065, 'loss/train': 0.3720647394657135} 08/31/2021 09:01:17 - INFO - __main__ - Step 109067: {'lr': 8.858424247919298e-05, 'samples': 20940864, 'steps': 109066, 'loss/train': 5.555324077606201} 08/31/2021 09:01:17 - INFO - __main__ - Step 109068: {'lr': 8.858019016642011e-05, 'samples': 20941056, 'steps': 109067, 'loss/train': 5.1526198387146} 08/31/2021 09:01:17 - INFO - __main__ - Step 109069: {'lr': 8.857613792638059e-05, 'samples': 20941248, 'steps': 109068, 'loss/train': 0.5344973206520081} 08/31/2021 09:01:18 - INFO - __main__ - Step 109070: {'lr': 8.85720857590761e-05, 'samples': 20941440, 'steps': 109069, 'loss/train': 0.6641697883605957} 08/31/2021 09:01:19 - INFO - __main__ - Step 109071: {'lr': 8.856803366450853e-05, 'samples': 20941632, 'steps': 109070, 'loss/train': 0.970506489276886} 08/31/2021 09:01:20 - INFO - __main__ - Step 109072: {'lr': 8.85639816426797e-05, 'samples': 20941824, 'steps': 109071, 'loss/train': 1.2694060802459717} 08/31/2021 09:01:20 - INFO - __main__ - Step 109073: {'lr': 8.855992969359147e-05, 'samples': 20942016, 'steps': 109072, 'loss/train': 1.0980597734451294} 08/31/2021 09:01:20 - INFO - __main__ - Step 109074: {'lr': 8.855587781724565e-05, 'samples': 20942208, 'steps': 109073, 'loss/train': 0.7947466969490051} 08/31/2021 09:01:21 - INFO - __main__ - Step 109075: {'lr': 8.855182601364403e-05, 'samples': 20942400, 'steps': 109074, 'loss/train': 1.6841371059417725} 08/31/2021 09:01:22 - INFO - __main__ - Step 109076: {'lr': 8.854777428278848e-05, 'samples': 20942592, 'steps': 109075, 'loss/train': 1.1203982830047607} 08/31/2021 09:01:23 - INFO - __main__ - Step 109077: {'lr': 8.854372262468083e-05, 'samples': 20942784, 'steps': 109076, 'loss/train': 1.0780701637268066} 08/31/2021 09:01:23 - INFO - __main__ - Step 109078: {'lr': 8.853967103932286e-05, 'samples': 20942976, 'steps': 109077, 'loss/train': 0.5567473769187927} 08/31/2021 09:01:23 - INFO - __main__ - Step 109079: {'lr': 8.853561952671646e-05, 'samples': 20943168, 'steps': 109078, 'loss/train': 1.0320930480957031} 08/31/2021 09:01:24 - INFO - __main__ - Step 109080: {'lr': 8.853156808686338e-05, 'samples': 20943360, 'steps': 109079, 'loss/train': 1.4273416996002197} 08/31/2021 09:01:25 - INFO - __main__ - Step 109081: {'lr': 8.85275167197655e-05, 'samples': 20943552, 'steps': 109080, 'loss/train': 1.2260135412216187} 08/31/2021 09:01:26 - INFO - __main__ - Step 109082: {'lr': 8.852346542542471e-05, 'samples': 20943744, 'steps': 109081, 'loss/train': 0.29999732971191406} 08/31/2021 09:01:26 - INFO - __main__ - Step 109083: {'lr': 8.851941420384266e-05, 'samples': 20943936, 'steps': 109082, 'loss/train': 1.1261485815048218} 08/31/2021 09:01:26 - INFO - __main__ - Step 109084: {'lr': 8.851536305502128e-05, 'samples': 20944128, 'steps': 109083, 'loss/train': 1.2992286682128906} 08/31/2021 09:01:27 - INFO - __main__ - Step 109085: {'lr': 8.851131197896239e-05, 'samples': 20944320, 'steps': 109084, 'loss/train': 1.1096652746200562} 08/31/2021 09:01:29 - INFO - __main__ - Step 109086: {'lr': 8.85072609756678e-05, 'samples': 20944512, 'steps': 109085, 'loss/train': 1.1044727563858032} 08/31/2021 09:01:29 - INFO - __main__ - Step 109087: {'lr': 8.850321004513937e-05, 'samples': 20944704, 'steps': 109086, 'loss/train': 1.83164644241333} 08/31/2021 09:01:30 - INFO - __main__ - Step 109088: {'lr': 8.849915918737889e-05, 'samples': 20944896, 'steps': 109087, 'loss/train': 1.6337363719940186} 08/31/2021 09:01:30 - INFO - __main__ - Step 109089: {'lr': 8.84951084023882e-05, 'samples': 20945088, 'steps': 109088, 'loss/train': 1.206597924232483} 08/31/2021 09:01:30 - INFO - __main__ - Step 109090: {'lr': 8.84910576901691e-05, 'samples': 20945280, 'steps': 109089, 'loss/train': 1.1862534284591675} 08/31/2021 09:01:31 - INFO - __main__ - Step 109091: {'lr': 8.848700705072346e-05, 'samples': 20945472, 'steps': 109090, 'loss/train': 1.244378924369812} 08/31/2021 09:01:32 - INFO - __main__ - Step 109092: {'lr': 8.848295648405308e-05, 'samples': 20945664, 'steps': 109091, 'loss/train': 1.4446842670440674} 08/31/2021 09:01:33 - INFO - __main__ - Step 109093: {'lr': 8.847890599015975e-05, 'samples': 20945856, 'steps': 109092, 'loss/train': 0.6932029724121094} 08/31/2021 09:01:33 - INFO - __main__ - Step 109094: {'lr': 8.847485556904547e-05, 'samples': 20946048, 'steps': 109093, 'loss/train': 1.1756829023361206} 08/31/2021 09:01:33 - INFO - __main__ - Step 109095: {'lr': 8.847080522071183e-05, 'samples': 20946240, 'steps': 109094, 'loss/train': 1.0735318660736084} 08/31/2021 09:01:34 - INFO - __main__ - Step 109096: {'lr': 8.846675494516074e-05, 'samples': 20946432, 'steps': 109095, 'loss/train': 1.3179295063018799} 08/31/2021 09:01:35 - INFO - __main__ - Step 109097: {'lr': 8.846270474239403e-05, 'samples': 20946624, 'steps': 109096, 'loss/train': 1.1825008392333984} 08/31/2021 09:01:36 - INFO - __main__ - Step 109098: {'lr': 8.845865461241354e-05, 'samples': 20946816, 'steps': 109097, 'loss/train': 1.3285287618637085} 08/31/2021 09:01:36 - INFO - __main__ - Step 109099: {'lr': 8.845460455522111e-05, 'samples': 20947008, 'steps': 109098, 'loss/train': 1.2768458127975464} 08/31/2021 09:01:37 - INFO - __main__ - Step 109100: {'lr': 8.845055457081852e-05, 'samples': 20947200, 'steps': 109099, 'loss/train': 1.525589942932129} 08/31/2021 09:01:37 - INFO - __main__ - Step 109101: {'lr': 8.844650465920761e-05, 'samples': 20947392, 'steps': 109100, 'loss/train': 1.2561578750610352} 08/31/2021 09:01:38 - INFO - __main__ - Step 109102: {'lr': 8.844245482039023e-05, 'samples': 20947584, 'steps': 109101, 'loss/train': 1.8514378070831299} 08/31/2021 09:01:39 - INFO - __main__ - Step 109103: {'lr': 8.843840505436818e-05, 'samples': 20947776, 'steps': 109102, 'loss/train': 1.4653100967407227} 08/31/2021 09:01:39 - INFO - __main__ - Step 109104: {'lr': 8.84343553611433e-05, 'samples': 20947968, 'steps': 109103, 'loss/train': 0.8354406356811523} 08/31/2021 09:01:40 - INFO - __main__ - Step 109105: {'lr': 8.843030574071747e-05, 'samples': 20948160, 'steps': 109104, 'loss/train': 0.2987406551837921} 08/31/2021 09:01:40 - INFO - __main__ - Step 109106: {'lr': 8.842625619309239e-05, 'samples': 20948352, 'steps': 109105, 'loss/train': 0.98309326171875} 08/31/2021 09:01:42 - INFO - __main__ - Step 109107: {'lr': 8.842220671826992e-05, 'samples': 20948544, 'steps': 109106, 'loss/train': 1.2329788208007812} 08/31/2021 09:01:42 - INFO - __main__ - Step 109108: {'lr': 8.841815731625194e-05, 'samples': 20948736, 'steps': 109107, 'loss/train': 0.9746666550636292} 08/31/2021 09:01:42 - INFO - __main__ - Step 109109: {'lr': 8.841410798704022e-05, 'samples': 20948928, 'steps': 109108, 'loss/train': 1.0505847930908203} 08/31/2021 09:01:43 - INFO - __main__ - Step 109110: {'lr': 8.841005873063662e-05, 'samples': 20949120, 'steps': 109109, 'loss/train': 1.1602410078048706} 08/31/2021 09:01:43 - INFO - __main__ - Step 109111: {'lr': 8.840600954704295e-05, 'samples': 20949312, 'steps': 109110, 'loss/train': 0.7675904631614685} 08/31/2021 09:01:43 - INFO - __main__ - Step 109112: {'lr': 8.840196043626106e-05, 'samples': 20949504, 'steps': 109111, 'loss/train': 0.716619074344635} 08/31/2021 09:01:45 - INFO - __main__ - Step 109113: {'lr': 8.839791139829273e-05, 'samples': 20949696, 'steps': 109112, 'loss/train': 0.03121311590075493} 08/31/2021 09:01:45 - INFO - __main__ - Step 109114: {'lr': 8.839386243313982e-05, 'samples': 20949888, 'steps': 109113, 'loss/train': 1.2818644046783447} 08/31/2021 09:01:46 - INFO - __main__ - Step 109115: {'lr': 8.838981354080411e-05, 'samples': 20950080, 'steps': 109114, 'loss/train': 1.4372457265853882} 08/31/2021 09:01:46 - INFO - __main__ - Step 109116: {'lr': 8.838576472128757e-05, 'samples': 20950272, 'steps': 109115, 'loss/train': 0.8216843605041504} 08/31/2021 09:01:46 - INFO - __main__ - Step 109117: {'lr': 8.838171597459182e-05, 'samples': 20950464, 'steps': 109116, 'loss/train': 0.5964603424072266} 08/31/2021 09:01:48 - INFO - __main__ - Step 109118: {'lr': 8.837766730071878e-05, 'samples': 20950656, 'steps': 109117, 'loss/train': 0.6059900522232056} 08/31/2021 09:01:48 - INFO - __main__ - Step 109119: {'lr': 8.837361869967029e-05, 'samples': 20950848, 'steps': 109118, 'loss/train': 1.0286598205566406} 08/31/2021 09:01:49 - INFO - __main__ - Step 109120: {'lr': 8.836957017144812e-05, 'samples': 20951040, 'steps': 109119, 'loss/train': 0.12978985905647278} 08/31/2021 09:01:49 - INFO - __main__ - Step 109121: {'lr': 8.836552171605413e-05, 'samples': 20951232, 'steps': 109120, 'loss/train': 0.7403405904769897} 08/31/2021 09:01:49 - INFO - __main__ - Step 109122: {'lr': 8.836147333349015e-05, 'samples': 20951424, 'steps': 109121, 'loss/train': 1.5319641828536987} 08/31/2021 09:01:51 - INFO - __main__ - Step 109123: {'lr': 8.835742502375799e-05, 'samples': 20951616, 'steps': 109122, 'loss/train': 1.2342891693115234} 08/31/2021 09:01:51 - INFO - __main__ - Step 109124: {'lr': 8.835337678685948e-05, 'samples': 20951808, 'steps': 109123, 'loss/train': 0.6804888844490051} 08/31/2021 09:01:52 - INFO - __main__ - Step 109125: {'lr': 8.834932862279646e-05, 'samples': 20952000, 'steps': 109124, 'loss/train': 0.9081788659095764} 08/31/2021 09:01:52 - INFO - __main__ - Step 109126: {'lr': 8.834528053157081e-05, 'samples': 20952192, 'steps': 109125, 'loss/train': 1.214957594871521} 08/31/2021 09:01:53 - INFO - __main__ - Step 109127: {'lr': 8.834123251318419e-05, 'samples': 20952384, 'steps': 109126, 'loss/train': 0.8943786025047302} 08/31/2021 09:01:54 - INFO - __main__ - Step 109128: {'lr': 8.833718456763853e-05, 'samples': 20952576, 'steps': 109127, 'loss/train': 0.15836957097053528} 08/31/2021 09:01:55 - INFO - __main__ - Step 109129: {'lr': 8.833313669493561e-05, 'samples': 20952768, 'steps': 109128, 'loss/train': 1.0841673612594604} 08/31/2021 09:01:55 - INFO - __main__ - Step 109130: {'lr': 8.832908889507732e-05, 'samples': 20952960, 'steps': 109129, 'loss/train': 1.4764236211776733} 08/31/2021 09:01:55 - INFO - __main__ - Step 109131: {'lr': 8.832504116806545e-05, 'samples': 20953152, 'steps': 109130, 'loss/train': 0.5833042860031128} 08/31/2021 09:01:56 - INFO - __main__ - Step 109132: {'lr': 8.83209935139018e-05, 'samples': 20953344, 'steps': 109131, 'loss/train': 1.8838798999786377} 08/31/2021 09:01:57 - INFO - __main__ - Step 109133: {'lr': 8.831694593258824e-05, 'samples': 20953536, 'steps': 109132, 'loss/train': 0.536011815071106} 08/31/2021 09:01:58 - INFO - __main__ - Step 109134: {'lr': 8.831289842412655e-05, 'samples': 20953728, 'steps': 109133, 'loss/train': 0.9705744981765747} 08/31/2021 09:01:58 - INFO - __main__ - Step 109135: {'lr': 8.830885098851857e-05, 'samples': 20953920, 'steps': 109134, 'loss/train': 0.5906128883361816} 08/31/2021 09:01:58 - INFO - __main__ - Step 109136: {'lr': 8.830480362576613e-05, 'samples': 20954112, 'steps': 109135, 'loss/train': 0.175317645072937} 08/31/2021 09:01:59 - INFO - __main__ - Step 109137: {'lr': 8.830075633587115e-05, 'samples': 20954304, 'steps': 109136, 'loss/train': 1.1475249528884888} 08/31/2021 09:02:01 - INFO - __main__ - Step 109138: {'lr': 8.829670911883525e-05, 'samples': 20954496, 'steps': 109137, 'loss/train': 1.229041337966919} 08/31/2021 09:02:01 - INFO - __main__ - Step 109139: {'lr': 8.829266197466035e-05, 'samples': 20954688, 'steps': 109138, 'loss/train': 0.8734217286109924} 08/31/2021 09:02:02 - INFO - __main__ - Step 109140: {'lr': 8.82886149033483e-05, 'samples': 20954880, 'steps': 109139, 'loss/train': 1.3310750722885132} 08/31/2021 09:02:02 - INFO - __main__ - Step 109141: {'lr': 8.828456790490092e-05, 'samples': 20955072, 'steps': 109140, 'loss/train': 1.2760061025619507} 08/31/2021 09:02:02 - INFO - __main__ - Step 109142: {'lr': 8.828052097931999e-05, 'samples': 20955264, 'steps': 109141, 'loss/train': 0.775908887386322} 08/31/2021 09:02:03 - INFO - __main__ - Step 109143: {'lr': 8.827647412660735e-05, 'samples': 20955456, 'steps': 109142, 'loss/train': 1.024715542793274} 08/31/2021 09:02:04 - INFO - __main__ - Step 109144: {'lr': 8.827242734676485e-05, 'samples': 20955648, 'steps': 109143, 'loss/train': 5.024062633514404} 08/31/2021 09:02:05 - INFO - __main__ - Step 109145: {'lr': 8.82683806397943e-05, 'samples': 20955840, 'steps': 109144, 'loss/train': 1.3752477169036865} 08/31/2021 09:02:05 - INFO - __main__ - Step 109146: {'lr': 8.826433400569755e-05, 'samples': 20956032, 'steps': 109145, 'loss/train': 0.9803667664527893} 08/31/2021 09:02:05 - INFO - __main__ - Step 109147: {'lr': 8.826028744447637e-05, 'samples': 20956224, 'steps': 109146, 'loss/train': 1.3785895109176636} 08/31/2021 09:02:06 - INFO - __main__ - Step 109148: {'lr': 8.82562409561326e-05, 'samples': 20956416, 'steps': 109147, 'loss/train': 1.5356584787368774} 08/31/2021 09:02:08 - INFO - __main__ - Step 109149: {'lr': 8.82521945406681e-05, 'samples': 20956608, 'steps': 109148, 'loss/train': 1.0586357116699219} 08/31/2021 09:02:08 - INFO - __main__ - Step 109150: {'lr': 8.824814819808472e-05, 'samples': 20956800, 'steps': 109149, 'loss/train': 1.4072173833847046} 08/31/2021 09:02:08 - INFO - __main__ - Step 109151: {'lr': 8.824410192838417e-05, 'samples': 20956992, 'steps': 109150, 'loss/train': 0.8506672978401184} 08/31/2021 09:02:09 - INFO - __main__ - Step 109152: {'lr': 8.82400557315683e-05, 'samples': 20957184, 'steps': 109151, 'loss/train': 1.1586586236953735} 08/31/2021 09:02:09 - INFO - __main__ - Step 109153: {'lr': 8.8236009607639e-05, 'samples': 20957376, 'steps': 109152, 'loss/train': 1.140372633934021} 08/31/2021 09:02:10 - INFO - __main__ - Step 109154: {'lr': 8.823196355659801e-05, 'samples': 20957568, 'steps': 109153, 'loss/train': 0.022329729050397873} 08/31/2021 09:02:11 - INFO - __main__ - Step 109155: {'lr': 8.822791757844726e-05, 'samples': 20957760, 'steps': 109154, 'loss/train': 0.017398208379745483} 08/31/2021 09:02:12 - INFO - __main__ - Step 109156: {'lr': 8.822387167318846e-05, 'samples': 20957952, 'steps': 109155, 'loss/train': 1.4147194623947144} 08/31/2021 09:02:12 - INFO - __main__ - Step 109157: {'lr': 8.821982584082353e-05, 'samples': 20958144, 'steps': 109156, 'loss/train': 0.6118041276931763} 08/31/2021 09:02:12 - INFO - __main__ - Step 109158: {'lr': 8.821578008135423e-05, 'samples': 20958336, 'steps': 109157, 'loss/train': 0.8045203685760498} 08/31/2021 09:02:13 - INFO - __main__ - Step 109159: {'lr': 8.821173439478241e-05, 'samples': 20958528, 'steps': 109158, 'loss/train': 1.1527498960494995} 08/31/2021 09:02:13 - INFO - __main__ - Step 109160: {'lr': 8.820768878110988e-05, 'samples': 20958720, 'steps': 109159, 'loss/train': 1.3100086450576782} 08/31/2021 09:02:15 - INFO - __main__ - Step 109161: {'lr': 8.820364324033847e-05, 'samples': 20958912, 'steps': 109160, 'loss/train': 1.0601574182510376} 08/31/2021 09:02:15 - INFO - __main__ - Step 109162: {'lr': 8.819959777246999e-05, 'samples': 20959104, 'steps': 109161, 'loss/train': 1.269370198249817} 08/31/2021 09:02:16 - INFO - __main__ - Step 109163: {'lr': 8.819555237750637e-05, 'samples': 20959296, 'steps': 109162, 'loss/train': 1.2954437732696533} 08/31/2021 09:02:16 - INFO - __main__ - Step 109164: {'lr': 8.819150705544926e-05, 'samples': 20959488, 'steps': 109163, 'loss/train': 5.700456142425537} 08/31/2021 09:02:16 - INFO - __main__ - Step 109165: {'lr': 8.818746180630054e-05, 'samples': 20959680, 'steps': 109164, 'loss/train': 0.41910335421562195} 08/31/2021 09:02:18 - INFO - __main__ - Step 109166: {'lr': 8.818341663006208e-05, 'samples': 20959872, 'steps': 109165, 'loss/train': 1.107456088066101} 08/31/2021 09:02:18 - INFO - __main__ - Step 109167: {'lr': 8.817937152673566e-05, 'samples': 20960064, 'steps': 109166, 'loss/train': 1.118054986000061} 08/31/2021 09:02:19 - INFO - __main__ - Step 109168: {'lr': 8.817532649632312e-05, 'samples': 20960256, 'steps': 109167, 'loss/train': 1.046268105506897} 08/31/2021 09:02:19 - INFO - __main__ - Step 109169: {'lr': 8.817128153882628e-05, 'samples': 20960448, 'steps': 109168, 'loss/train': 1.269053339958191} 08/31/2021 09:02:19 - INFO - __main__ - Step 109170: {'lr': 8.816723665424698e-05, 'samples': 20960640, 'steps': 109169, 'loss/train': 1.1730760335922241} 08/31/2021 09:02:21 - INFO - __main__ - Step 109171: {'lr': 8.8163191842587e-05, 'samples': 20960832, 'steps': 109170, 'loss/train': 2.102940559387207} 08/31/2021 09:02:21 - INFO - __main__ - Step 109172: {'lr': 8.815914710384821e-05, 'samples': 20961024, 'steps': 109171, 'loss/train': 0.8413175940513611} 08/31/2021 09:02:22 - INFO - __main__ - Step 109173: {'lr': 8.815510243803238e-05, 'samples': 20961216, 'steps': 109172, 'loss/train': 1.2428674697875977} 08/31/2021 09:02:22 - INFO - __main__ - Step 109174: {'lr': 8.815105784514139e-05, 'samples': 20961408, 'steps': 109173, 'loss/train': 0.5434764623641968} 08/31/2021 09:02:22 - INFO - __main__ - Step 109175: {'lr': 8.814701332517702e-05, 'samples': 20961600, 'steps': 109174, 'loss/train': 1.7557451725006104} 08/31/2021 09:02:23 - INFO - __main__ - Step 109176: {'lr': 8.814296887814122e-05, 'samples': 20961792, 'steps': 109175, 'loss/train': 1.100212574005127} 08/31/2021 09:02:24 - INFO - __main__ - Step 109177: {'lr': 8.81389245040356e-05, 'samples': 20961984, 'steps': 109176, 'loss/train': 0.6686725616455078} 08/31/2021 09:02:25 - INFO - __main__ - Step 109178: {'lr': 8.813488020286206e-05, 'samples': 20962176, 'steps': 109177, 'loss/train': 0.7337749004364014} 08/31/2021 09:02:25 - INFO - __main__ - Step 109179: {'lr': 8.813083597462249e-05, 'samples': 20962368, 'steps': 109178, 'loss/train': 1.450914740562439} 08/31/2021 09:02:26 - INFO - __main__ - Step 109180: {'lr': 8.812679181931863e-05, 'samples': 20962560, 'steps': 109179, 'loss/train': 1.177012324333191} 08/31/2021 09:02:26 - INFO - __main__ - Step 109181: {'lr': 8.812274773695236e-05, 'samples': 20962752, 'steps': 109180, 'loss/train': 0.09912815690040588} 08/31/2021 09:02:27 - INFO - __main__ - Step 109182: {'lr': 8.811870372752548e-05, 'samples': 20962944, 'steps': 109181, 'loss/train': 1.1757177114486694} 08/31/2021 09:02:28 - INFO - __main__ - Step 109183: {'lr': 8.81146597910398e-05, 'samples': 20963136, 'steps': 109182, 'loss/train': 1.203688144683838} 08/31/2021 09:02:28 - INFO - __main__ - Step 109184: {'lr': 8.811061592749716e-05, 'samples': 20963328, 'steps': 109183, 'loss/train': 0.6935093402862549} 08/31/2021 09:02:29 - INFO - __main__ - Step 109185: {'lr': 8.810657213689938e-05, 'samples': 20963520, 'steps': 109184, 'loss/train': 0.8130090236663818} 08/31/2021 09:02:29 - INFO - __main__ - Step 109186: {'lr': 8.810252841924829e-05, 'samples': 20963712, 'steps': 109185, 'loss/train': 0.8895314931869507} 08/31/2021 09:02:30 - INFO - __main__ - Step 109187: {'lr': 8.809848477454568e-05, 'samples': 20963904, 'steps': 109186, 'loss/train': 1.250120997428894} 08/31/2021 09:02:31 - INFO - __main__ - Step 109188: {'lr': 8.809444120279342e-05, 'samples': 20964096, 'steps': 109187, 'loss/train': 1.4297187328338623} 08/31/2021 09:02:31 - INFO - __main__ - Step 109189: {'lr': 8.809039770399329e-05, 'samples': 20964288, 'steps': 109188, 'loss/train': 0.8075456023216248} 08/31/2021 09:02:32 - INFO - __main__ - Step 109190: {'lr': 8.808635427814723e-05, 'samples': 20964480, 'steps': 109189, 'loss/train': 1.257728934288025} 08/31/2021 09:02:32 - INFO - __main__ - Step 109191: {'lr': 8.808231092525687e-05, 'samples': 20964672, 'steps': 109190, 'loss/train': 1.3260339498519897} 08/31/2021 09:02:34 - INFO - __main__ - Step 109192: {'lr': 8.807826764532412e-05, 'samples': 20964864, 'steps': 109191, 'loss/train': 1.0677298307418823} 08/31/2021 09:02:35 - INFO - __main__ - Step 109193: {'lr': 8.807422443835081e-05, 'samples': 20965056, 'steps': 109192, 'loss/train': 1.4896199703216553} 08/31/2021 09:02:35 - INFO - __main__ - Step 109194: {'lr': 8.807018130433875e-05, 'samples': 20965248, 'steps': 109193, 'loss/train': 1.6988388299942017} 08/31/2021 09:02:35 - INFO - __main__ - Step 109195: {'lr': 8.806613824328976e-05, 'samples': 20965440, 'steps': 109194, 'loss/train': 1.1034225225448608} 08/31/2021 09:02:36 - INFO - __main__ - Step 109196: {'lr': 8.806209525520567e-05, 'samples': 20965632, 'steps': 109195, 'loss/train': 1.3039047718048096} 08/31/2021 09:02:36 - INFO - __main__ - Step 109197: {'lr': 8.805805234008832e-05, 'samples': 20965824, 'steps': 109196, 'loss/train': 1.22835373878479} 08/31/2021 09:02:38 - INFO - __main__ - Step 109198: {'lr': 8.805400949793948e-05, 'samples': 20966016, 'steps': 109197, 'loss/train': 1.0663083791732788} 08/31/2021 09:02:38 - INFO - __main__ - Step 109199: {'lr': 8.804996672876103e-05, 'samples': 20966208, 'steps': 109198, 'loss/train': 1.139230728149414} 08/31/2021 09:02:39 - INFO - __main__ - Step 109200: {'lr': 8.804592403255477e-05, 'samples': 20966400, 'steps': 109199, 'loss/train': 0.037481848150491714} 08/31/2021 09:02:39 - INFO - __main__ - Step 109201: {'lr': 8.804188140932252e-05, 'samples': 20966592, 'steps': 109200, 'loss/train': 1.170835018157959} 08/31/2021 09:02:39 - INFO - __main__ - Step 109202: {'lr': 8.803783885906608e-05, 'samples': 20966784, 'steps': 109201, 'loss/train': 0.8781854510307312} 08/31/2021 09:02:41 - INFO - __main__ - Step 109203: {'lr': 8.803379638178735e-05, 'samples': 20966976, 'steps': 109202, 'loss/train': 0.04223368316888809} 08/31/2021 09:02:41 - INFO - __main__ - Step 109204: {'lr': 8.802975397748805e-05, 'samples': 20967168, 'steps': 109203, 'loss/train': 0.9727481603622437} 08/31/2021 09:02:42 - INFO - __main__ - Step 109205: {'lr': 8.802571164617004e-05, 'samples': 20967360, 'steps': 109204, 'loss/train': 1.2027125358581543} 08/31/2021 09:02:42 - INFO - __main__ - Step 109206: {'lr': 8.802166938783512e-05, 'samples': 20967552, 'steps': 109205, 'loss/train': 0.8649020195007324} 08/31/2021 09:02:42 - INFO - __main__ - Step 109207: {'lr': 8.801762720248516e-05, 'samples': 20967744, 'steps': 109206, 'loss/train': 1.2840588092803955} 08/31/2021 09:02:44 - INFO - __main__ - Step 109208: {'lr': 8.801358509012194e-05, 'samples': 20967936, 'steps': 109207, 'loss/train': 0.8442610502243042} 08/31/2021 09:02:44 - INFO - __main__ - Step 109209: {'lr': 8.800954305074732e-05, 'samples': 20968128, 'steps': 109208, 'loss/train': 1.1069021224975586} 08/31/2021 09:02:45 - INFO - __main__ - Step 109210: {'lr': 8.800550108436308e-05, 'samples': 20968320, 'steps': 109209, 'loss/train': 0.14312870800495148} 08/31/2021 09:02:45 - INFO - __main__ - Step 109211: {'lr': 8.800145919097108e-05, 'samples': 20968512, 'steps': 109210, 'loss/train': 1.620544195175171} 08/31/2021 09:02:45 - INFO - __main__ - Step 109212: {'lr': 8.799741737057313e-05, 'samples': 20968704, 'steps': 109211, 'loss/train': 1.4662821292877197} 08/31/2021 09:02:47 - INFO - __main__ - Step 109213: {'lr': 8.799337562317103e-05, 'samples': 20968896, 'steps': 109212, 'loss/train': 2.11102557182312} 08/31/2021 09:02:48 - INFO - __main__ - Step 109214: {'lr': 8.79893339487666e-05, 'samples': 20969088, 'steps': 109213, 'loss/train': 0.04567883163690567} 08/31/2021 09:02:48 - INFO - __main__ - Step 109215: {'lr': 8.798529234736168e-05, 'samples': 20969280, 'steps': 109214, 'loss/train': 0.053129926323890686} 08/31/2021 09:02:48 - INFO - __main__ - Step 109216: {'lr': 8.79812508189581e-05, 'samples': 20969472, 'steps': 109215, 'loss/train': 1.4113366603851318} 08/31/2021 09:02:49 - INFO - __main__ - Step 109217: {'lr': 8.797720936355777e-05, 'samples': 20969664, 'steps': 109216, 'loss/train': 1.0958689451217651} 08/31/2021 09:02:49 - INFO - __main__ - Step 109218: {'lr': 8.797316798116228e-05, 'samples': 20969856, 'steps': 109217, 'loss/train': 0.7961720824241638} 08/31/2021 09:02:51 - INFO - __main__ - Step 109219: {'lr': 8.796912667177361e-05, 'samples': 20970048, 'steps': 109218, 'loss/train': 0.13527673482894897} 08/31/2021 09:02:51 - INFO - __main__ - Step 109220: {'lr': 8.796508543539356e-05, 'samples': 20970240, 'steps': 109219, 'loss/train': 1.1590057611465454} 08/31/2021 09:02:52 - INFO - __main__ - Step 109221: {'lr': 8.796104427202392e-05, 'samples': 20970432, 'steps': 109220, 'loss/train': 0.45123887062072754} 08/31/2021 09:02:52 - INFO - __main__ - Step 109222: {'lr': 8.795700318166654e-05, 'samples': 20970624, 'steps': 109221, 'loss/train': 1.3930059671401978} 08/31/2021 09:02:52 - INFO - __main__ - Step 109223: {'lr': 8.795296216432325e-05, 'samples': 20970816, 'steps': 109222, 'loss/train': 1.0866446495056152} 08/31/2021 09:02:53 - INFO - __main__ - Step 109224: {'lr': 8.794892121999581e-05, 'samples': 20971008, 'steps': 109223, 'loss/train': 1.1641123294830322} 08/31/2021 09:02:54 - INFO - __main__ - Step 109225: {'lr': 8.794488034868614e-05, 'samples': 20971200, 'steps': 109224, 'loss/train': 1.2970945835113525} 08/31/2021 09:02:55 - INFO - __main__ - Step 109226: {'lr': 8.794083955039597e-05, 'samples': 20971392, 'steps': 109225, 'loss/train': 0.44866570830345154} 08/31/2021 09:02:55 - INFO - __main__ - Step 109227: {'lr': 8.793679882512717e-05, 'samples': 20971584, 'steps': 109226, 'loss/train': 0.9961469173431396} 08/31/2021 09:02:55 - INFO - __main__ - Step 109228: {'lr': 8.793275817288154e-05, 'samples': 20971776, 'steps': 109227, 'loss/train': 1.0087480545043945} 08/31/2021 09:02:56 - INFO - __main__ - Step 109229: {'lr': 8.792871759366091e-05, 'samples': 20971968, 'steps': 109228, 'loss/train': 1.3077781200408936} 08/31/2021 09:02:57 - INFO - __main__ - Step 109230: {'lr': 8.792467708746721e-05, 'samples': 20972160, 'steps': 109229, 'loss/train': 0.9023979902267456} 08/31/2021 09:02:58 - INFO - __main__ - Step 109231: {'lr': 8.792063665430203e-05, 'samples': 20972352, 'steps': 109230, 'loss/train': 1.3933855295181274} 08/31/2021 09:02:58 - INFO - __main__ - Step 109232: {'lr': 8.791659629416731e-05, 'samples': 20972544, 'steps': 109231, 'loss/train': 1.6434334516525269} 08/31/2021 09:02:58 - INFO - __main__ - Step 109233: {'lr': 8.791255600706489e-05, 'samples': 20972736, 'steps': 109232, 'loss/train': 1.553369164466858} 08/31/2021 09:02:59 - INFO - __main__ - Step 109234: {'lr': 8.790851579299658e-05, 'samples': 20972928, 'steps': 109233, 'loss/train': 2.9387435913085938} 08/31/2021 09:03:00 - INFO - __main__ - Step 109235: {'lr': 8.790447565196416e-05, 'samples': 20973120, 'steps': 109234, 'loss/train': 1.4160188436508179} 08/31/2021 09:03:01 - INFO - __main__ - Step 109236: {'lr': 8.790043558396951e-05, 'samples': 20973312, 'steps': 109235, 'loss/train': 0.9629226922988892} 08/31/2021 09:03:01 - INFO - __main__ - Step 109237: {'lr': 8.789639558901441e-05, 'samples': 20973504, 'steps': 109236, 'loss/train': 1.0841625928878784} 08/31/2021 09:03:01 - INFO - __main__ - Step 109238: {'lr': 8.789235566710069e-05, 'samples': 20973696, 'steps': 109237, 'loss/train': 0.5308155417442322} 08/31/2021 09:03:02 - INFO - __main__ - Step 109239: {'lr': 8.788831581823018e-05, 'samples': 20973888, 'steps': 109238, 'loss/train': 0.8219637870788574} 08/31/2021 09:03:02 - INFO - __main__ - Step 109240: {'lr': 8.788427604240467e-05, 'samples': 20974080, 'steps': 109239, 'loss/train': 0.8779363036155701} 08/31/2021 09:03:03 - INFO - __main__ - Step 109241: {'lr': 8.788023633962603e-05, 'samples': 20974272, 'steps': 109240, 'loss/train': 1.2647429704666138} 08/31/2021 09:03:04 - INFO - __main__ - Step 109242: {'lr': 8.787619670989605e-05, 'samples': 20974464, 'steps': 109241, 'loss/train': 1.7746798992156982} 08/31/2021 09:03:04 - INFO - __main__ - Step 109243: {'lr': 8.787215715321656e-05, 'samples': 20974656, 'steps': 109242, 'loss/train': 0.7496368288993835} 08/31/2021 09:03:05 - INFO - __main__ - Step 109244: {'lr': 8.786811766958944e-05, 'samples': 20974848, 'steps': 109243, 'loss/train': 0.7316129207611084} 08/31/2021 09:03:05 - INFO - __main__ - Step 109245: {'lr': 8.786407825901638e-05, 'samples': 20975040, 'steps': 109244, 'loss/train': 1.1371406316757202} 08/31/2021 09:03:06 - INFO - __main__ - Step 109246: {'lr': 8.786003892149925e-05, 'samples': 20975232, 'steps': 109245, 'loss/train': 0.8989407420158386} 08/31/2021 09:03:07 - INFO - __main__ - Step 109247: {'lr': 8.785599965703989e-05, 'samples': 20975424, 'steps': 109246, 'loss/train': 1.2232311964035034} 08/31/2021 09:03:07 - INFO - __main__ - Step 109248: {'lr': 8.785196046564012e-05, 'samples': 20975616, 'steps': 109247, 'loss/train': 1.1759625673294067} 08/31/2021 09:03:08 - INFO - __main__ - Step 109249: {'lr': 8.784792134730174e-05, 'samples': 20975808, 'steps': 109248, 'loss/train': 5.747255325317383} 08/31/2021 09:03:08 - INFO - __main__ - Step 109250: {'lr': 8.784388230202658e-05, 'samples': 20976000, 'steps': 109249, 'loss/train': 0.8117637038230896} 08/31/2021 09:03:10 - INFO - __main__ - Step 109251: {'lr': 8.783984332981649e-05, 'samples': 20976192, 'steps': 109250, 'loss/train': 0.9636085033416748} 08/31/2021 09:03:11 - INFO - __main__ - Step 109252: {'lr': 8.783580443067324e-05, 'samples': 20976384, 'steps': 109251, 'loss/train': 1.4616334438323975} 08/31/2021 09:03:11 - INFO - __main__ - Step 109253: {'lr': 8.783176560459869e-05, 'samples': 20976576, 'steps': 109252, 'loss/train': 1.3820971250534058} 08/31/2021 09:03:11 - INFO - __main__ - Step 109254: {'lr': 8.782772685159463e-05, 'samples': 20976768, 'steps': 109253, 'loss/train': 1.2267463207244873} 08/31/2021 09:03:12 - INFO - __main__ - Step 109255: {'lr': 8.782368817166291e-05, 'samples': 20976960, 'steps': 109254, 'loss/train': 0.6561828851699829} 08/31/2021 09:03:12 - INFO - __main__ - Step 109256: {'lr': 8.781964956480531e-05, 'samples': 20977152, 'steps': 109255, 'loss/train': 1.1685621738433838} 08/31/2021 09:03:14 - INFO - __main__ - Step 109257: {'lr': 8.781561103102378e-05, 'samples': 20977344, 'steps': 109256, 'loss/train': 1.4796149730682373} 08/31/2021 09:03:14 - INFO - __main__ - Step 109258: {'lr': 8.781157257031996e-05, 'samples': 20977536, 'steps': 109257, 'loss/train': 0.7043662071228027} 08/31/2021 09:03:14 - INFO - __main__ - Step 109259: {'lr': 8.780753418269571e-05, 'samples': 20977728, 'steps': 109258, 'loss/train': 1.079294204711914} 08/31/2021 09:03:15 - INFO - __main__ - Step 109260: {'lr': 8.78034958681529e-05, 'samples': 20977920, 'steps': 109259, 'loss/train': 0.5833526849746704} 08/31/2021 09:03:15 - INFO - __main__ - Step 109261: {'lr': 8.779945762669334e-05, 'samples': 20978112, 'steps': 109260, 'loss/train': 0.09013640880584717} 08/31/2021 09:03:17 - INFO - __main__ - Step 109262: {'lr': 8.779541945831881e-05, 'samples': 20978304, 'steps': 109261, 'loss/train': 1.0390112400054932} 08/31/2021 09:03:18 - INFO - __main__ - Step 109263: {'lr': 8.779138136303119e-05, 'samples': 20978496, 'steps': 109262, 'loss/train': 0.8276894688606262} 08/31/2021 09:03:18 - INFO - __main__ - Step 109264: {'lr': 8.778734334083226e-05, 'samples': 20978688, 'steps': 109263, 'loss/train': 1.0361040830612183} 08/31/2021 09:03:18 - INFO - __main__ - Step 109265: {'lr': 8.778330539172385e-05, 'samples': 20978880, 'steps': 109264, 'loss/train': 1.1359119415283203} 08/31/2021 09:03:19 - INFO - __main__ - Step 109266: {'lr': 8.77792675157078e-05, 'samples': 20979072, 'steps': 109265, 'loss/train': 0.17396040260791779} 08/31/2021 09:03:20 - INFO - __main__ - Step 109267: {'lr': 8.777522971278587e-05, 'samples': 20979264, 'steps': 109266, 'loss/train': 0.09732518345117569} 08/31/2021 09:03:21 - INFO - __main__ - Step 109268: {'lr': 8.777119198295996e-05, 'samples': 20979456, 'steps': 109267, 'loss/train': 0.5574849843978882} 08/31/2021 09:03:21 - INFO - __main__ - Step 109269: {'lr': 8.776715432623181e-05, 'samples': 20979648, 'steps': 109268, 'loss/train': 1.7008562088012695} 08/31/2021 09:03:21 - INFO - __main__ - Step 109270: {'lr': 8.776311674260329e-05, 'samples': 20979840, 'steps': 109269, 'loss/train': 1.0390877723693848} 08/31/2021 09:03:22 - INFO - __main__ - Step 109271: {'lr': 8.775907923207629e-05, 'samples': 20980032, 'steps': 109270, 'loss/train': 0.5883631706237793} 08/31/2021 09:03:23 - INFO - __main__ - Step 109272: {'lr': 8.775504179465249e-05, 'samples': 20980224, 'steps': 109271, 'loss/train': 1.8753856420516968} 08/31/2021 09:03:24 - INFO - __main__ - Step 109273: {'lr': 8.775100443033374e-05, 'samples': 20980416, 'steps': 109272, 'loss/train': 1.3453060388565063} 08/31/2021 09:03:24 - INFO - __main__ - Step 109274: {'lr': 8.774696713912186e-05, 'samples': 20980608, 'steps': 109273, 'loss/train': 1.6321264505386353} 08/31/2021 09:03:24 - INFO - __main__ - Step 109275: {'lr': 8.774292992101873e-05, 'samples': 20980800, 'steps': 109274, 'loss/train': 1.3722416162490845} 08/31/2021 09:03:25 - INFO - __main__ - Step 109276: {'lr': 8.773889277602611e-05, 'samples': 20980992, 'steps': 109275, 'loss/train': 1.2040469646453857} 08/31/2021 09:03:25 - INFO - __main__ - Step 109277: {'lr': 8.773485570414586e-05, 'samples': 20981184, 'steps': 109276, 'loss/train': 1.2944061756134033} 08/31/2021 09:03:27 - INFO - __main__ - Step 109278: {'lr': 8.773081870537978e-05, 'samples': 20981376, 'steps': 109277, 'loss/train': 0.7735229134559631} 08/31/2021 09:03:27 - INFO - __main__ - Step 109279: {'lr': 8.772678177972968e-05, 'samples': 20981568, 'steps': 109278, 'loss/train': 1.0550159215927124} 08/31/2021 09:03:27 - INFO - __main__ - Step 109280: {'lr': 8.772274492719737e-05, 'samples': 20981760, 'steps': 109279, 'loss/train': 0.10442592948675156} 08/31/2021 09:03:28 - INFO - __main__ - Step 109281: {'lr': 8.77187081477847e-05, 'samples': 20981952, 'steps': 109280, 'loss/train': 0.07480273395776749} 08/31/2021 09:03:28 - INFO - __main__ - Step 109282: {'lr': 8.771467144149348e-05, 'samples': 20982144, 'steps': 109281, 'loss/train': 1.708001732826233} 08/31/2021 09:03:30 - INFO - __main__ - Step 109283: {'lr': 8.771063480832553e-05, 'samples': 20982336, 'steps': 109282, 'loss/train': 1.278303623199463} 08/31/2021 09:03:30 - INFO - __main__ - Step 109284: {'lr': 8.770659824828276e-05, 'samples': 20982528, 'steps': 109283, 'loss/train': 1.9822460412979126} 08/31/2021 09:03:30 - INFO - __main__ - Step 109285: {'lr': 8.770256176136676e-05, 'samples': 20982720, 'steps': 109284, 'loss/train': 1.3178951740264893} 08/31/2021 09:03:31 - INFO - __main__ - Step 109286: {'lr': 8.769852534757953e-05, 'samples': 20982912, 'steps': 109285, 'loss/train': 0.8397419452667236} 08/31/2021 09:03:31 - INFO - __main__ - Step 109287: {'lr': 8.769448900692281e-05, 'samples': 20983104, 'steps': 109286, 'loss/train': 0.9116559624671936} 08/31/2021 09:03:33 - INFO - __main__ - Step 109288: {'lr': 8.769045273939846e-05, 'samples': 20983296, 'steps': 109287, 'loss/train': 1.2659968137741089} 08/31/2021 09:03:33 - INFO - __main__ - Step 109289: {'lr': 8.768641654500828e-05, 'samples': 20983488, 'steps': 109288, 'loss/train': 0.9544283747673035} 08/31/2021 09:03:34 - INFO - __main__ - Step 109290: {'lr': 8.768238042375412e-05, 'samples': 20983680, 'steps': 109289, 'loss/train': 0.5720853805541992} 08/31/2021 09:03:34 - INFO - __main__ - Step 109291: {'lr': 8.767834437563776e-05, 'samples': 20983872, 'steps': 109290, 'loss/train': 1.406620740890503} 08/31/2021 09:03:34 - INFO - __main__ - Step 109292: {'lr': 8.767430840066103e-05, 'samples': 20984064, 'steps': 109291, 'loss/train': 0.9211271405220032} 08/31/2021 09:03:35 - INFO - __main__ - Step 109293: {'lr': 8.767027249882576e-05, 'samples': 20984256, 'steps': 109292, 'loss/train': 1.2705698013305664} 08/31/2021 09:03:36 - INFO - __main__ - Step 109294: {'lr': 8.766623667013374e-05, 'samples': 20984448, 'steps': 109293, 'loss/train': 0.9588578939437866} 08/31/2021 09:03:37 - INFO - __main__ - Step 109295: {'lr': 8.766220091458682e-05, 'samples': 20984640, 'steps': 109294, 'loss/train': 1.648454189300537} 08/31/2021 09:03:37 - INFO - __main__ - Step 109296: {'lr': 8.765816523218681e-05, 'samples': 20984832, 'steps': 109295, 'loss/train': 0.5473567843437195} 08/31/2021 09:03:37 - INFO - __main__ - Step 109297: {'lr': 8.765412962293562e-05, 'samples': 20985024, 'steps': 109296, 'loss/train': 0.8900592923164368} 08/31/2021 09:03:38 - INFO - __main__ - Step 109298: {'lr': 8.765009408683488e-05, 'samples': 20985216, 'steps': 109297, 'loss/train': 1.1918554306030273} 08/31/2021 09:03:39 - INFO - __main__ - Step 109299: {'lr': 8.76460586238865e-05, 'samples': 20985408, 'steps': 109298, 'loss/train': 0.9969597458839417} 08/31/2021 09:03:40 - INFO - __main__ - Step 109300: {'lr': 8.764202323409232e-05, 'samples': 20985600, 'steps': 109299, 'loss/train': 0.6621870398521423} 08/31/2021 09:03:40 - INFO - __main__ - Step 109301: {'lr': 8.763798791745412e-05, 'samples': 20985792, 'steps': 109300, 'loss/train': 1.5157533884048462} 08/31/2021 09:03:41 - INFO - __main__ - Step 109302: {'lr': 8.763395267397373e-05, 'samples': 20985984, 'steps': 109301, 'loss/train': 1.291163444519043} 08/31/2021 09:03:41 - INFO - __main__ - Step 109303: {'lr': 8.762991750365298e-05, 'samples': 20986176, 'steps': 109302, 'loss/train': 1.2148683071136475} 08/31/2021 09:03:43 - INFO - __main__ - Step 109304: {'lr': 8.762588240649369e-05, 'samples': 20986368, 'steps': 109303, 'loss/train': 1.0158032178878784} 08/31/2021 09:03:43 - INFO - __main__ - Step 109305: {'lr': 8.762184738249767e-05, 'samples': 20986560, 'steps': 109304, 'loss/train': 0.5120469927787781} 08/31/2021 09:03:44 - INFO - __main__ - Step 109306: {'lr': 8.761781243166675e-05, 'samples': 20986752, 'steps': 109305, 'loss/train': 1.3515456914901733} 08/31/2021 09:03:44 - INFO - __main__ - Step 109307: {'lr': 8.761377755400271e-05, 'samples': 20986944, 'steps': 109306, 'loss/train': 1.4308832883834839} 08/31/2021 09:03:44 - INFO - __main__ - Step 109308: {'lr': 8.760974274950741e-05, 'samples': 20987136, 'steps': 109307, 'loss/train': 0.646312415599823} 08/31/2021 09:03:46 - INFO - __main__ - Step 109309: {'lr': 8.760570801818266e-05, 'samples': 20987328, 'steps': 109308, 'loss/train': 0.992464005947113} 08/31/2021 09:03:46 - INFO - __main__ - Step 109310: {'lr': 8.760167336003028e-05, 'samples': 20987520, 'steps': 109309, 'loss/train': 0.6923949122428894} 08/31/2021 09:03:47 - INFO - __main__ - Step 109311: {'lr': 8.759763877505214e-05, 'samples': 20987712, 'steps': 109310, 'loss/train': 0.788101315498352} 08/31/2021 09:03:47 - INFO - __main__ - Step 109312: {'lr': 8.759360426324994e-05, 'samples': 20987904, 'steps': 109311, 'loss/train': 1.5035895109176636} 08/31/2021 09:03:47 - INFO - __main__ - Step 109313: {'lr': 8.758956982462555e-05, 'samples': 20988096, 'steps': 109312, 'loss/train': 0.14766351878643036} 08/31/2021 09:03:49 - INFO - __main__ - Step 109314: {'lr': 8.758553545918077e-05, 'samples': 20988288, 'steps': 109313, 'loss/train': 1.1631884574890137} 08/31/2021 09:03:49 - INFO - __main__ - Step 109315: {'lr': 8.758150116691746e-05, 'samples': 20988480, 'steps': 109314, 'loss/train': 1.1011337041854858} 08/31/2021 09:03:50 - INFO - __main__ - Step 109316: {'lr': 8.757746694783744e-05, 'samples': 20988672, 'steps': 109315, 'loss/train': 0.9669877886772156} 08/31/2021 09:03:50 - INFO - __main__ - Step 109317: {'lr': 8.757343280194246e-05, 'samples': 20988864, 'steps': 109316, 'loss/train': 1.305227518081665} 08/31/2021 09:03:50 - INFO - __main__ - Step 109318: {'lr': 8.756939872923442e-05, 'samples': 20989056, 'steps': 109317, 'loss/train': 1.175154447555542} 08/31/2021 09:03:52 - INFO - __main__ - Step 109319: {'lr': 8.75653647297151e-05, 'samples': 20989248, 'steps': 109318, 'loss/train': 1.7691700458526611} 08/31/2021 09:03:53 - INFO - __main__ - Step 109320: {'lr': 8.75613308033863e-05, 'samples': 20989440, 'steps': 109319, 'loss/train': 1.4895981550216675} 08/31/2021 09:03:53 - INFO - __main__ - Step 109321: {'lr': 8.755729695024989e-05, 'samples': 20989632, 'steps': 109320, 'loss/train': 0.9248825907707214} 08/31/2021 09:03:53 - INFO - __main__ - Step 109322: {'lr': 8.755326317030763e-05, 'samples': 20989824, 'steps': 109321, 'loss/train': 1.0747231245040894} 08/31/2021 09:03:54 - INFO - __main__ - Step 109323: {'lr': 8.754922946356136e-05, 'samples': 20990016, 'steps': 109322, 'loss/train': 0.016804296523332596} 08/31/2021 09:03:54 - INFO - __main__ - Step 109324: {'lr': 8.7545195830013e-05, 'samples': 20990208, 'steps': 109323, 'loss/train': 0.014954490587115288} 08/31/2021 09:03:56 - INFO - __main__ - Step 109325: {'lr': 8.754116226966418e-05, 'samples': 20990400, 'steps': 109324, 'loss/train': 1.6092585325241089} 08/31/2021 09:03:56 - INFO - __main__ - Step 109326: {'lr': 8.75371287825168e-05, 'samples': 20990592, 'steps': 109325, 'loss/train': 1.3426588773727417} 08/31/2021 09:03:57 - INFO - __main__ - Step 109327: {'lr': 8.753309536857268e-05, 'samples': 20990784, 'steps': 109326, 'loss/train': 1.2354052066802979} 08/31/2021 09:03:57 - INFO - __main__ - Step 109328: {'lr': 8.752906202783364e-05, 'samples': 20990976, 'steps': 109327, 'loss/train': 0.8506634831428528} 08/31/2021 09:03:57 - INFO - __main__ - Step 109329: {'lr': 8.752502876030153e-05, 'samples': 20991168, 'steps': 109328, 'loss/train': 0.19961465895175934} 08/31/2021 09:03:58 - INFO - __main__ - Step 109330: {'lr': 8.752099556597809e-05, 'samples': 20991360, 'steps': 109329, 'loss/train': 0.8365517258644104} 08/31/2021 09:03:59 - INFO - __main__ - Step 109331: {'lr': 8.751696244486521e-05, 'samples': 20991552, 'steps': 109330, 'loss/train': 1.3384199142456055} 08/31/2021 09:04:00 - INFO - __main__ - Step 109332: {'lr': 8.751292939696467e-05, 'samples': 20991744, 'steps': 109331, 'loss/train': 0.7869371771812439} 08/31/2021 09:04:00 - INFO - __main__ - Step 109333: {'lr': 8.75088964222783e-05, 'samples': 20991936, 'steps': 109332, 'loss/train': 0.01715039648115635} 08/31/2021 09:04:01 - INFO - __main__ - Step 109334: {'lr': 8.750486352080789e-05, 'samples': 20992128, 'steps': 109333, 'loss/train': 0.55122971534729} 08/31/2021 09:04:01 - INFO - __main__ - Step 109335: {'lr': 8.750083069255532e-05, 'samples': 20992320, 'steps': 109334, 'loss/train': 1.1671189069747925} 08/31/2021 09:04:01 - INFO - __main__ - Step 109336: {'lr': 8.749679793752232e-05, 'samples': 20992512, 'steps': 109335, 'loss/train': 0.8711854815483093} 08/31/2021 09:04:03 - INFO - __main__ - Step 109337: {'lr': 8.749276525571082e-05, 'samples': 20992704, 'steps': 109336, 'loss/train': 1.5845046043395996} 08/31/2021 09:04:03 - INFO - __main__ - Step 109338: {'lr': 8.748873264712259e-05, 'samples': 20992896, 'steps': 109337, 'loss/train': 1.0058560371398926} 08/31/2021 09:04:04 - INFO - __main__ - Step 109339: {'lr': 8.748470011175938e-05, 'samples': 20993088, 'steps': 109338, 'loss/train': 0.9035443067550659} 08/31/2021 09:04:04 - INFO - __main__ - Step 109340: {'lr': 8.748066764962307e-05, 'samples': 20993280, 'steps': 109339, 'loss/train': 0.5750101804733276} 08/31/2021 09:04:04 - INFO - __main__ - Step 109341: {'lr': 8.747663526071545e-05, 'samples': 20993472, 'steps': 109340, 'loss/train': 0.7724401950836182} 08/31/2021 09:04:06 - INFO - __main__ - Step 109342: {'lr': 8.747260294503834e-05, 'samples': 20993664, 'steps': 109341, 'loss/train': 1.3843368291854858} 08/31/2021 09:04:06 - INFO - __main__ - Step 109343: {'lr': 8.746857070259356e-05, 'samples': 20993856, 'steps': 109342, 'loss/train': 1.1418640613555908} 08/31/2021 09:04:07 - INFO - __main__ - Step 109344: {'lr': 8.746453853338296e-05, 'samples': 20994048, 'steps': 109343, 'loss/train': 0.39229539036750793} 08/31/2021 09:04:07 - INFO - __main__ - Step 109345: {'lr': 8.746050643740833e-05, 'samples': 20994240, 'steps': 109344, 'loss/train': 0.6318665742874146} 08/31/2021 09:04:07 - INFO - __main__ - Step 109346: {'lr': 8.745647441467147e-05, 'samples': 20994432, 'steps': 109345, 'loss/train': 1.1301745176315308} 08/31/2021 09:04:09 - INFO - __main__ - Step 109347: {'lr': 8.745244246517423e-05, 'samples': 20994624, 'steps': 109346, 'loss/train': 0.638823926448822} 08/31/2021 09:04:09 - INFO - __main__ - Step 109348: {'lr': 8.74484105889184e-05, 'samples': 20994816, 'steps': 109347, 'loss/train': 1.223262071609497} 08/31/2021 09:04:10 - INFO - __main__ - Step 109349: {'lr': 8.74443787859058e-05, 'samples': 20995008, 'steps': 109348, 'loss/train': 1.2634079456329346} 08/31/2021 09:04:10 - INFO - __main__ - Step 109350: {'lr': 8.744034705613827e-05, 'samples': 20995200, 'steps': 109349, 'loss/train': 0.6256753206253052} 08/31/2021 09:04:10 - INFO - __main__ - Step 109351: {'lr': 8.743631539961769e-05, 'samples': 20995392, 'steps': 109350, 'loss/train': 0.9750109314918518} 08/31/2021 09:04:12 - INFO - __main__ - Step 109352: {'lr': 8.743228381634571e-05, 'samples': 20995584, 'steps': 109351, 'loss/train': 0.8420199155807495} 08/31/2021 09:04:12 - INFO - __main__ - Step 109353: {'lr': 8.742825230632423e-05, 'samples': 20995776, 'steps': 109352, 'loss/train': 1.364962100982666} 08/31/2021 09:04:13 - INFO - __main__ - Step 109354: {'lr': 8.742422086955509e-05, 'samples': 20995968, 'steps': 109353, 'loss/train': 0.9152905344963074} 08/31/2021 09:04:13 - INFO - __main__ - Step 109355: {'lr': 8.742018950604005e-05, 'samples': 20996160, 'steps': 109354, 'loss/train': 0.8867858648300171} 08/31/2021 09:04:13 - INFO - __main__ - Step 109356: {'lr': 8.7416158215781e-05, 'samples': 20996352, 'steps': 109355, 'loss/train': 0.4843151867389679} 08/31/2021 09:04:16 - INFO - __main__ - Step 109357: {'lr': 8.74121269987797e-05, 'samples': 20996544, 'steps': 109356, 'loss/train': 1.3113042116165161} 08/31/2021 09:04:16 - INFO - __main__ - Step 109358: {'lr': 8.7408095855038e-05, 'samples': 20996736, 'steps': 109357, 'loss/train': 1.0544484853744507} 08/31/2021 09:04:17 - INFO - __main__ - Step 109359: {'lr': 8.74040647845577e-05, 'samples': 20996928, 'steps': 109358, 'loss/train': 1.2234691381454468} 08/31/2021 09:04:17 - INFO - __main__ - Step 109360: {'lr': 8.740003378734062e-05, 'samples': 20997120, 'steps': 109359, 'loss/train': 0.8370933532714844} 08/31/2021 09:04:17 - INFO - __main__ - Step 109361: {'lr': 8.739600286338859e-05, 'samples': 20997312, 'steps': 109360, 'loss/train': 0.4596763849258423} 08/31/2021 09:04:18 - INFO - __main__ - Step 109362: {'lr': 8.739197201270338e-05, 'samples': 20997504, 'steps': 109361, 'loss/train': 0.3437274098396301} 08/31/2021 09:04:19 - INFO - __main__ - Step 109363: {'lr': 8.738794123528696e-05, 'samples': 20997696, 'steps': 109362, 'loss/train': 0.48582953214645386} 08/31/2021 09:04:20 - INFO - __main__ - Step 109364: {'lr': 8.738391053114092e-05, 'samples': 20997888, 'steps': 109363, 'loss/train': 1.383488655090332} 08/31/2021 09:04:20 - INFO - __main__ - Step 109365: {'lr': 8.737987990026717e-05, 'samples': 20998080, 'steps': 109364, 'loss/train': 0.6525558829307556} 08/31/2021 09:04:20 - INFO - __main__ - Step 109366: {'lr': 8.737584934266754e-05, 'samples': 20998272, 'steps': 109365, 'loss/train': 1.2991838455200195} 08/31/2021 09:04:21 - INFO - __main__ - Step 109367: {'lr': 8.737181885834386e-05, 'samples': 20998464, 'steps': 109366, 'loss/train': 0.8386001586914062} 08/31/2021 09:04:22 - INFO - __main__ - Step 109368: {'lr': 8.736778844729792e-05, 'samples': 20998656, 'steps': 109367, 'loss/train': 1.1451680660247803} 08/31/2021 09:04:23 - INFO - __main__ - Step 109369: {'lr': 8.736375810953154e-05, 'samples': 20998848, 'steps': 109368, 'loss/train': 1.518608808517456} 08/31/2021 09:04:23 - INFO - __main__ - Step 109370: {'lr': 8.735972784504654e-05, 'samples': 20999040, 'steps': 109369, 'loss/train': 0.8460706472396851} 08/31/2021 09:04:23 - INFO - __main__ - Step 109371: {'lr': 8.735569765384474e-05, 'samples': 20999232, 'steps': 109370, 'loss/train': 1.2352465391159058} 08/31/2021 09:04:24 - INFO - __main__ - Step 109372: {'lr': 8.735166753592797e-05, 'samples': 20999424, 'steps': 109371, 'loss/train': 1.2544673681259155} 08/31/2021 09:04:25 - INFO - __main__ - Step 109373: {'lr': 8.734763749129809e-05, 'samples': 20999616, 'steps': 109372, 'loss/train': 0.9890812039375305} 08/31/2021 09:04:26 - INFO - __main__ - Step 109374: {'lr': 8.734360751995677e-05, 'samples': 20999808, 'steps': 109373, 'loss/train': 1.1459546089172363} 08/31/2021 09:04:26 - INFO - __main__ - Step 109375: {'lr': 8.733957762190593e-05, 'samples': 21000000, 'steps': 109374, 'loss/train': 0.5899189710617065} 08/31/2021 09:04:26 - INFO - __main__ - Step 109376: {'lr': 8.733554779714734e-05, 'samples': 21000192, 'steps': 109375, 'loss/train': 1.3515534400939941} 08/31/2021 09:04:27 - INFO - __main__ - Step 109377: {'lr': 8.733151804568287e-05, 'samples': 21000384, 'steps': 109376, 'loss/train': 1.1853660345077515} 08/31/2021 09:04:28 - INFO - __main__ - Step 109378: {'lr': 8.732748836751427e-05, 'samples': 21000576, 'steps': 109377, 'loss/train': 0.10177137702703476} 08/31/2021 09:04:29 - INFO - __main__ - Step 109379: {'lr': 8.732345876264344e-05, 'samples': 21000768, 'steps': 109378, 'loss/train': 0.9971399307250977} 08/31/2021 09:04:29 - INFO - __main__ - Step 109380: {'lr': 8.731942923107211e-05, 'samples': 21000960, 'steps': 109379, 'loss/train': 0.02614937350153923} 08/31/2021 09:04:30 - INFO - __main__ - Step 109381: {'lr': 8.731539977280217e-05, 'samples': 21001152, 'steps': 109380, 'loss/train': 0.03380299359560013} 08/31/2021 09:04:30 - INFO - __main__ - Step 109382: {'lr': 8.731137038783537e-05, 'samples': 21001344, 'steps': 109381, 'loss/train': 0.4911686182022095} 08/31/2021 09:04:31 - INFO - __main__ - Step 109383: {'lr': 8.730734107617358e-05, 'samples': 21001536, 'steps': 109382, 'loss/train': 1.4314833879470825} 08/31/2021 09:04:32 - INFO - __main__ - Step 109384: {'lr': 8.730331183781867e-05, 'samples': 21001728, 'steps': 109383, 'loss/train': 1.339848518371582} 08/31/2021 09:04:32 - INFO - __main__ - Step 109385: {'lr': 8.72992826727723e-05, 'samples': 21001920, 'steps': 109384, 'loss/train': 1.182043433189392} 08/31/2021 09:04:33 - INFO - __main__ - Step 109386: {'lr': 8.729525358103632e-05, 'samples': 21002112, 'steps': 109385, 'loss/train': 0.13790133595466614} 08/31/2021 09:04:33 - INFO - __main__ - Step 109387: {'lr': 8.729122456261262e-05, 'samples': 21002304, 'steps': 109386, 'loss/train': 1.2697010040283203} 08/31/2021 09:04:33 - INFO - __main__ - Step 109388: {'lr': 8.728719561750298e-05, 'samples': 21002496, 'steps': 109387, 'loss/train': 1.210679531097412} 08/31/2021 09:04:35 - INFO - __main__ - Step 109389: {'lr': 8.728316674570924e-05, 'samples': 21002688, 'steps': 109388, 'loss/train': 0.8378022313117981} 08/31/2021 09:04:35 - INFO - __main__ - Step 109390: {'lr': 8.727913794723316e-05, 'samples': 21002880, 'steps': 109389, 'loss/train': 1.5262863636016846} 08/31/2021 09:04:36 - INFO - __main__ - Step 109391: {'lr': 8.72751092220766e-05, 'samples': 21003072, 'steps': 109390, 'loss/train': 1.8185709714889526} 08/31/2021 09:04:36 - INFO - __main__ - Step 109392: {'lr': 8.727108057024138e-05, 'samples': 21003264, 'steps': 109391, 'loss/train': 0.5334575176239014} 08/31/2021 09:04:36 - INFO - __main__ - Step 109393: {'lr': 8.72670519917293e-05, 'samples': 21003456, 'steps': 109392, 'loss/train': 0.13964712619781494} 08/31/2021 09:04:38 - INFO - __main__ - Step 109394: {'lr': 8.726302348654216e-05, 'samples': 21003648, 'steps': 109393, 'loss/train': 0.796405017375946} 08/31/2021 09:04:38 - INFO - __main__ - Step 109395: {'lr': 8.725899505468188e-05, 'samples': 21003840, 'steps': 109394, 'loss/train': 0.8831614851951599} 08/31/2021 09:04:39 - INFO - __main__ - Step 109396: {'lr': 8.72549666961501e-05, 'samples': 21004032, 'steps': 109395, 'loss/train': 0.47533029317855835} 08/31/2021 09:04:39 - INFO - __main__ - Step 109397: {'lr': 8.725093841094873e-05, 'samples': 21004224, 'steps': 109396, 'loss/train': 0.7858170866966248} 08/31/2021 09:04:39 - INFO - __main__ - Step 109398: {'lr': 8.724691019907954e-05, 'samples': 21004416, 'steps': 109397, 'loss/train': 1.1610112190246582} 08/31/2021 09:04:41 - INFO - __main__ - Step 109399: {'lr': 8.724288206054443e-05, 'samples': 21004608, 'steps': 109398, 'loss/train': 0.7774813771247864} 08/31/2021 09:04:41 - INFO - __main__ - Step 109400: {'lr': 8.723885399534512e-05, 'samples': 21004800, 'steps': 109399, 'loss/train': 1.3334693908691406} 08/31/2021 09:04:41 - INFO - __main__ - Step 109401: {'lr': 8.72348260034835e-05, 'samples': 21004992, 'steps': 109400, 'loss/train': 0.7002412676811218} 08/31/2021 09:04:42 - INFO - __main__ - Step 109402: {'lr': 8.723079808496135e-05, 'samples': 21005184, 'steps': 109401, 'loss/train': 0.474366694688797} 08/31/2021 09:04:42 - INFO - __main__ - Step 109403: {'lr': 8.722677023978048e-05, 'samples': 21005376, 'steps': 109402, 'loss/train': 0.040596675127744675} 08/31/2021 09:04:44 - INFO - __main__ - Step 109404: {'lr': 8.722274246794273e-05, 'samples': 21005568, 'steps': 109403, 'loss/train': 0.49171072244644165} 08/31/2021 09:04:45 - INFO - __main__ - Step 109405: {'lr': 8.72187147694499e-05, 'samples': 21005760, 'steps': 109404, 'loss/train': 0.035605743527412415} 08/31/2021 09:04:45 - INFO - __main__ - Step 109406: {'lr': 8.72146871443039e-05, 'samples': 21005952, 'steps': 109405, 'loss/train': 1.6271895170211792} 08/31/2021 09:04:45 - INFO - __main__ - Step 109407: {'lr': 8.721065959250635e-05, 'samples': 21006144, 'steps': 109406, 'loss/train': 0.8685879707336426} 08/31/2021 09:04:46 - INFO - __main__ - Step 109408: {'lr': 8.720663211405915e-05, 'samples': 21006336, 'steps': 109407, 'loss/train': 2.10774827003479} 08/31/2021 09:04:47 - INFO - __main__ - Step 109409: {'lr': 8.720260470896416e-05, 'samples': 21006528, 'steps': 109408, 'loss/train': 0.06355029344558716} 08/31/2021 09:04:48 - INFO - __main__ - Step 109410: {'lr': 8.719857737722314e-05, 'samples': 21006720, 'steps': 109409, 'loss/train': 1.134992241859436} 08/31/2021 09:04:48 - INFO - __main__ - Step 109411: {'lr': 8.719455011883795e-05, 'samples': 21006912, 'steps': 109410, 'loss/train': 1.4390711784362793} 08/31/2021 09:04:49 - INFO - __main__ - Step 109412: {'lr': 8.719052293381036e-05, 'samples': 21007104, 'steps': 109411, 'loss/train': 1.794152021408081} 08/31/2021 09:04:49 - INFO - __main__ - Step 109413: {'lr': 8.718649582214222e-05, 'samples': 21007296, 'steps': 109412, 'loss/train': 0.40396201610565186} 08/31/2021 09:04:49 - INFO - __main__ - Step 109414: {'lr': 8.718246878383535e-05, 'samples': 21007488, 'steps': 109413, 'loss/train': 1.179643154144287} 08/31/2021 09:04:51 - INFO - __main__ - Step 109415: {'lr': 8.717844181889153e-05, 'samples': 21007680, 'steps': 109414, 'loss/train': 1.5946484804153442} 08/31/2021 09:04:52 - INFO - __main__ - Step 109416: {'lr': 8.717441492731259e-05, 'samples': 21007872, 'steps': 109415, 'loss/train': 1.166930079460144} 08/31/2021 09:04:52 - INFO - __main__ - Step 109417: {'lr': 8.717038810910035e-05, 'samples': 21008064, 'steps': 109416, 'loss/train': 0.799920916557312} 08/31/2021 09:04:52 - INFO - __main__ - Step 109418: {'lr': 8.716636136425671e-05, 'samples': 21008256, 'steps': 109417, 'loss/train': 1.1948336362838745} 08/31/2021 09:04:53 - INFO - __main__ - Step 109419: {'lr': 8.716233469278328e-05, 'samples': 21008448, 'steps': 109418, 'loss/train': 1.3147754669189453} 08/31/2021 09:04:55 - INFO - __main__ - Step 109420: {'lr': 8.715830809468203e-05, 'samples': 21008640, 'steps': 109419, 'loss/train': 1.389685869216919} 08/31/2021 09:04:55 - INFO - __main__ - Step 109421: {'lr': 8.715428156995473e-05, 'samples': 21008832, 'steps': 109420, 'loss/train': 1.0744884014129639} 08/31/2021 09:04:55 - INFO - __main__ - Step 109422: {'lr': 8.715025511860317e-05, 'samples': 21009024, 'steps': 109421, 'loss/train': 0.7045795917510986} 08/31/2021 09:04:56 - INFO - __main__ - Step 109423: {'lr': 8.714622874062919e-05, 'samples': 21009216, 'steps': 109422, 'loss/train': 1.7314362525939941} 08/31/2021 09:04:56 - INFO - __main__ - Step 109424: {'lr': 8.714220243603462e-05, 'samples': 21009408, 'steps': 109423, 'loss/train': 0.7522725462913513} 08/31/2021 09:04:57 - INFO - __main__ - Step 109425: {'lr': 8.713817620482129e-05, 'samples': 21009600, 'steps': 109424, 'loss/train': 0.14298783242702484} 08/31/2021 09:04:58 - INFO - __main__ - Step 109426: {'lr': 8.713415004699093e-05, 'samples': 21009792, 'steps': 109425, 'loss/train': 0.2553248405456543} 08/31/2021 09:04:59 - INFO - __main__ - Step 109427: {'lr': 8.713012396254547e-05, 'samples': 21009984, 'steps': 109426, 'loss/train': 1.2072172164916992} 08/31/2021 09:04:59 - INFO - __main__ - Step 109428: {'lr': 8.712609795148662e-05, 'samples': 21010176, 'steps': 109427, 'loss/train': 0.9948497414588928} 08/31/2021 09:04:59 - INFO - __main__ - Step 109429: {'lr': 8.712207201381625e-05, 'samples': 21010368, 'steps': 109428, 'loss/train': 1.6746398210525513} 08/31/2021 09:05:00 - INFO - __main__ - Step 109430: {'lr': 8.711804614953614e-05, 'samples': 21010560, 'steps': 109429, 'loss/train': 0.8275840282440186} 08/31/2021 09:05:01 - INFO - __main__ - Step 109431: {'lr': 8.711402035864815e-05, 'samples': 21010752, 'steps': 109430, 'loss/train': 0.7661949992179871} 08/31/2021 09:05:01 - INFO - __main__ - Step 109432: {'lr': 8.710999464115416e-05, 'samples': 21010944, 'steps': 109431, 'loss/train': 1.3767133951187134} 08/31/2021 09:05:02 - INFO - __main__ - Step 109433: {'lr': 8.710596899705579e-05, 'samples': 21011136, 'steps': 109432, 'loss/train': 1.1580368280410767} 08/31/2021 09:05:02 - INFO - __main__ - Step 109434: {'lr': 8.710194342635495e-05, 'samples': 21011328, 'steps': 109433, 'loss/train': 0.8877609968185425} 08/31/2021 09:05:03 - INFO - __main__ - Step 109435: {'lr': 8.709791792905347e-05, 'samples': 21011520, 'steps': 109434, 'loss/train': 0.5324933528900146} 08/31/2021 09:05:04 - INFO - __main__ - Step 109436: {'lr': 8.709389250515314e-05, 'samples': 21011712, 'steps': 109435, 'loss/train': 1.222904920578003} 08/31/2021 09:05:04 - INFO - __main__ - Step 109437: {'lr': 8.708986715465583e-05, 'samples': 21011904, 'steps': 109436, 'loss/train': 1.0354989767074585} 08/31/2021 09:05:05 - INFO - __main__ - Step 109438: {'lr': 8.708584187756326e-05, 'samples': 21012096, 'steps': 109437, 'loss/train': 0.683869481086731} 08/31/2021 09:05:05 - INFO - __main__ - Step 109439: {'lr': 8.708181667387736e-05, 'samples': 21012288, 'steps': 109438, 'loss/train': 0.901750385761261} 08/31/2021 09:05:05 - INFO - __main__ - Step 109440: {'lr': 8.707779154359982e-05, 'samples': 21012480, 'steps': 109439, 'loss/train': 1.1779882907867432} 08/31/2021 09:05:07 - INFO - __main__ - Step 109441: {'lr': 8.707376648673255e-05, 'samples': 21012672, 'steps': 109440, 'loss/train': 1.058372974395752} 08/31/2021 09:05:07 - INFO - __main__ - Step 109442: {'lr': 8.706974150327732e-05, 'samples': 21012864, 'steps': 109441, 'loss/train': 1.59396493434906} 08/31/2021 09:05:08 - INFO - __main__ - Step 109443: {'lr': 8.706571659323592e-05, 'samples': 21013056, 'steps': 109442, 'loss/train': 0.9924495220184326} 08/31/2021 09:05:08 - INFO - __main__ - Step 109444: {'lr': 8.706169175661022e-05, 'samples': 21013248, 'steps': 109443, 'loss/train': 1.0638099908828735} 08/31/2021 09:05:08 - INFO - __main__ - Step 109445: {'lr': 8.70576669934021e-05, 'samples': 21013440, 'steps': 109444, 'loss/train': 1.6194322109222412} 08/31/2021 09:05:10 - INFO - __main__ - Step 109446: {'lr': 8.705364230361318e-05, 'samples': 21013632, 'steps': 109445, 'loss/train': 0.1289261132478714} 08/31/2021 09:05:11 - INFO - __main__ - Step 109447: {'lr': 8.704961768724537e-05, 'samples': 21013824, 'steps': 109446, 'loss/train': 0.14387409389019012} 08/31/2021 09:05:11 - INFO - __main__ - Step 109448: {'lr': 8.70455931443005e-05, 'samples': 21014016, 'steps': 109447, 'loss/train': 1.1348960399627686} 08/31/2021 09:05:11 - INFO - __main__ - Step 109449: {'lr': 8.704156867478036e-05, 'samples': 21014208, 'steps': 109448, 'loss/train': 1.2423447370529175} 08/31/2021 09:05:12 - INFO - __main__ - Step 109450: {'lr': 8.703754427868679e-05, 'samples': 21014400, 'steps': 109449, 'loss/train': 0.6074953675270081} 08/31/2021 09:05:12 - INFO - __main__ - Step 109451: {'lr': 8.703351995602158e-05, 'samples': 21014592, 'steps': 109450, 'loss/train': 1.115310549736023} 08/31/2021 09:05:14 - INFO - __main__ - Step 109452: {'lr': 8.702949570678656e-05, 'samples': 21014784, 'steps': 109451, 'loss/train': 3.3286633491516113} 08/31/2021 09:05:14 - INFO - __main__ - Step 109453: {'lr': 8.70254715309835e-05, 'samples': 21014976, 'steps': 109452, 'loss/train': 0.891343355178833} 08/31/2021 09:05:15 - INFO - __main__ - Step 109454: {'lr': 8.702144742861429e-05, 'samples': 21015168, 'steps': 109453, 'loss/train': 0.0731443464756012} 08/31/2021 09:05:15 - INFO - __main__ - Step 109455: {'lr': 8.70174233996807e-05, 'samples': 21015360, 'steps': 109454, 'loss/train': 0.9599013328552246} 08/31/2021 09:05:15 - INFO - __main__ - Step 109456: {'lr': 8.701339944418452e-05, 'samples': 21015552, 'steps': 109455, 'loss/train': 1.4826266765594482} 08/31/2021 09:05:17 - INFO - __main__ - Step 109457: {'lr': 8.70093755621276e-05, 'samples': 21015744, 'steps': 109456, 'loss/train': 1.008796215057373} 08/31/2021 09:05:17 - INFO - __main__ - Step 109458: {'lr': 8.70053517535117e-05, 'samples': 21015936, 'steps': 109457, 'loss/train': 1.1736235618591309} 08/31/2021 09:05:18 - INFO - __main__ - Step 109459: {'lr': 8.700132801833883e-05, 'samples': 21016128, 'steps': 109458, 'loss/train': 0.8823871612548828} 08/31/2021 09:05:18 - INFO - __main__ - Step 109460: {'lr': 8.699730435661052e-05, 'samples': 21016320, 'steps': 109459, 'loss/train': 1.114016056060791} 08/31/2021 09:05:18 - INFO - __main__ - Step 109461: {'lr': 8.699328076832871e-05, 'samples': 21016512, 'steps': 109460, 'loss/train': 1.0467534065246582} 08/31/2021 09:05:19 - INFO - __main__ - Step 109462: {'lr': 8.698925725349522e-05, 'samples': 21016704, 'steps': 109461, 'loss/train': 1.0098063945770264} 08/31/2021 09:05:20 - INFO - __main__ - Step 109463: {'lr': 8.698523381211185e-05, 'samples': 21016896, 'steps': 109462, 'loss/train': 0.06906259804964066} 08/31/2021 09:05:21 - INFO - __main__ - Step 109464: {'lr': 8.698121044418042e-05, 'samples': 21017088, 'steps': 109463, 'loss/train': 1.290073037147522} 08/31/2021 09:05:21 - INFO - __main__ - Step 109465: {'lr': 8.697718714970274e-05, 'samples': 21017280, 'steps': 109464, 'loss/train': 0.04556757211685181} 08/31/2021 09:05:21 - INFO - __main__ - Step 109466: {'lr': 8.697316392868063e-05, 'samples': 21017472, 'steps': 109465, 'loss/train': 1.3320245742797852} 08/31/2021 09:05:22 - INFO - __main__ - Step 109467: {'lr': 8.696914078111586e-05, 'samples': 21017664, 'steps': 109466, 'loss/train': 1.2882274389266968} 08/31/2021 09:05:24 - INFO - __main__ - Step 109468: {'lr': 8.696511770701032e-05, 'samples': 21017856, 'steps': 109467, 'loss/train': 0.7569302916526794} 08/31/2021 09:05:24 - INFO - __main__ - Step 109469: {'lr': 8.696109470636579e-05, 'samples': 21018048, 'steps': 109468, 'loss/train': 1.253579020500183} 08/31/2021 09:05:24 - INFO - __main__ - Step 109470: {'lr': 8.695707177918405e-05, 'samples': 21018240, 'steps': 109469, 'loss/train': 1.3255615234375} 08/31/2021 09:05:25 - INFO - __main__ - Step 109471: {'lr': 8.695304892546696e-05, 'samples': 21018432, 'steps': 109470, 'loss/train': 0.7346082925796509} 08/31/2021 09:05:25 - INFO - __main__ - Step 109472: {'lr': 8.694902614521639e-05, 'samples': 21018624, 'steps': 109471, 'loss/train': 1.1157346963882446} 08/31/2021 09:05:27 - INFO - __main__ - Step 109473: {'lr': 8.694500343843395e-05, 'samples': 21018816, 'steps': 109472, 'loss/train': 0.32374194264411926} 08/31/2021 09:05:27 - INFO - __main__ - Step 109474: {'lr': 8.694098080512161e-05, 'samples': 21019008, 'steps': 109473, 'loss/train': 1.4005099534988403} 08/31/2021 09:05:28 - INFO - __main__ - Step 109475: {'lr': 8.693695824528113e-05, 'samples': 21019200, 'steps': 109474, 'loss/train': 1.0462632179260254} 08/31/2021 09:05:28 - INFO - __main__ - Step 109476: {'lr': 8.693293575891437e-05, 'samples': 21019392, 'steps': 109475, 'loss/train': 1.0522257089614868} 08/31/2021 09:05:28 - INFO - __main__ - Step 109477: {'lr': 8.69289133460231e-05, 'samples': 21019584, 'steps': 109476, 'loss/train': 0.5212755799293518} 08/31/2021 09:05:30 - INFO - __main__ - Step 109478: {'lr': 8.692489100660913e-05, 'samples': 21019776, 'steps': 109477, 'loss/train': 1.1705020666122437} 08/31/2021 09:05:30 - INFO - __main__ - Step 109479: {'lr': 8.692086874067432e-05, 'samples': 21019968, 'steps': 109478, 'loss/train': 1.5594747066497803} 08/31/2021 09:05:31 - INFO - __main__ - Step 109480: {'lr': 8.69168465482204e-05, 'samples': 21020160, 'steps': 109479, 'loss/train': 0.7306839227676392} 08/31/2021 09:05:31 - INFO - __main__ - Step 109481: {'lr': 8.691282442924927e-05, 'samples': 21020352, 'steps': 109480, 'loss/train': 0.14154231548309326} 08/31/2021 09:05:31 - INFO - __main__ - Step 109482: {'lr': 8.690880238376269e-05, 'samples': 21020544, 'steps': 109481, 'loss/train': 1.5134962797164917} 08/31/2021 09:05:33 - INFO - __main__ - Step 109483: {'lr': 8.69047804117625e-05, 'samples': 21020736, 'steps': 109482, 'loss/train': 0.9949405789375305} 08/31/2021 09:05:33 - INFO - __main__ - Step 109484: {'lr': 8.69007585132505e-05, 'samples': 21020928, 'steps': 109483, 'loss/train': 1.331478238105774} 08/31/2021 09:05:34 - INFO - __main__ - Step 109485: {'lr': 8.689673668822848e-05, 'samples': 21021120, 'steps': 109484, 'loss/train': 1.4520689249038696} 08/31/2021 09:05:34 - INFO - __main__ - Step 109486: {'lr': 8.689271493669836e-05, 'samples': 21021312, 'steps': 109485, 'loss/train': 1.316811203956604} 08/31/2021 09:05:34 - INFO - __main__ - Step 109487: {'lr': 8.68886932586618e-05, 'samples': 21021504, 'steps': 109486, 'loss/train': 1.0688879489898682} 08/31/2021 09:05:36 - INFO - __main__ - Step 109488: {'lr': 8.688467165412067e-05, 'samples': 21021696, 'steps': 109487, 'loss/train': 0.9789818525314331} 08/31/2021 09:05:37 - INFO - __main__ - Step 109489: {'lr': 8.68806501230768e-05, 'samples': 21021888, 'steps': 109488, 'loss/train': 1.223250389099121} 08/31/2021 09:05:37 - INFO - __main__ - Step 109490: {'lr': 8.687662866553197e-05, 'samples': 21022080, 'steps': 109489, 'loss/train': 1.3284273147583008} 08/31/2021 09:05:38 - INFO - __main__ - Step 109491: {'lr': 8.687260728148805e-05, 'samples': 21022272, 'steps': 109490, 'loss/train': 0.813618004322052} 08/31/2021 09:05:38 - INFO - __main__ - Step 109492: {'lr': 8.68685859709468e-05, 'samples': 21022464, 'steps': 109491, 'loss/train': 0.7206425070762634} 08/31/2021 09:05:38 - INFO - __main__ - Step 109493: {'lr': 8.686456473391003e-05, 'samples': 21022656, 'steps': 109492, 'loss/train': 0.8507968783378601} 08/31/2021 09:05:39 - INFO - __main__ - Step 109494: {'lr': 8.686054357037959e-05, 'samples': 21022848, 'steps': 109493, 'loss/train': 1.0348279476165771} 08/31/2021 09:05:40 - INFO - __main__ - Step 109495: {'lr': 8.685652248035725e-05, 'samples': 21023040, 'steps': 109494, 'loss/train': 1.0702972412109375} 08/31/2021 09:05:41 - INFO - __main__ - Step 109496: {'lr': 8.685250146384486e-05, 'samples': 21023232, 'steps': 109495, 'loss/train': 1.0773124694824219} 08/31/2021 09:05:41 - INFO - __main__ - Step 109497: {'lr': 8.68484805208442e-05, 'samples': 21023424, 'steps': 109496, 'loss/train': 0.7910988330841064} 08/31/2021 09:05:41 - INFO - __main__ - Step 109498: {'lr': 8.684445965135712e-05, 'samples': 21023616, 'steps': 109497, 'loss/train': 1.5375707149505615} 08/31/2021 09:05:42 - INFO - __main__ - Step 109499: {'lr': 8.684043885538548e-05, 'samples': 21023808, 'steps': 109498, 'loss/train': 1.2724173069000244} 08/31/2021 09:05:44 - INFO - __main__ - Step 109500: {'lr': 8.683641813293094e-05, 'samples': 21024000, 'steps': 109499, 'loss/train': 1.258644938468933} 08/31/2021 09:05:44 - INFO - __main__ - Step 109501: {'lr': 8.683239748399538e-05, 'samples': 21024192, 'steps': 109500, 'loss/train': 0.29703035950660706} 08/31/2021 09:05:45 - INFO - __main__ - Step 109502: {'lr': 8.682837690858064e-05, 'samples': 21024384, 'steps': 109501, 'loss/train': 0.8519830107688904} 08/31/2021 09:05:45 - INFO - __main__ - Step 109503: {'lr': 8.682435640668851e-05, 'samples': 21024576, 'steps': 109502, 'loss/train': 1.1535494327545166} 08/31/2021 09:05:46 - INFO - __main__ - Step 109504: {'lr': 8.682033597832078e-05, 'samples': 21024768, 'steps': 109503, 'loss/train': 0.844351589679718} 08/31/2021 09:05:46 - INFO - __main__ - Step 109505: {'lr': 8.681631562347933e-05, 'samples': 21024960, 'steps': 109504, 'loss/train': 0.07880645245313644} 08/31/2021 09:05:46 - INFO - __main__ - Step 109506: {'lr': 8.681229534216592e-05, 'samples': 21025152, 'steps': 109505, 'loss/train': 0.04631304368376732} 08/31/2021 09:05:48 - INFO - __main__ - Step 109507: {'lr': 8.680827513438236e-05, 'samples': 21025344, 'steps': 109506, 'loss/train': 0.01577044650912285} 08/31/2021 09:05:48 - INFO - __main__ - Step 109508: {'lr': 8.680425500013047e-05, 'samples': 21025536, 'steps': 109507, 'loss/train': 1.1517298221588135} 08/31/2021 09:05:48 - INFO - __main__ - Step 109509: {'lr': 8.680023493941208e-05, 'samples': 21025728, 'steps': 109508, 'loss/train': 1.0331894159317017} 08/31/2021 09:05:49 - INFO - __main__ - Step 109510: {'lr': 8.679621495222898e-05, 'samples': 21025920, 'steps': 109509, 'loss/train': 1.1936687231063843} 08/31/2021 09:05:49 - INFO - __main__ - Step 109511: {'lr': 8.679219503858299e-05, 'samples': 21026112, 'steps': 109510, 'loss/train': 0.9080804586410522} 08/31/2021 09:05:52 - INFO - __main__ - Step 109512: {'lr': 8.678817519847592e-05, 'samples': 21026304, 'steps': 109511, 'loss/train': 1.2084499597549438} 08/31/2021 09:05:52 - INFO - __main__ - Step 109513: {'lr': 8.678415543190965e-05, 'samples': 21026496, 'steps': 109512, 'loss/train': 0.7891914248466492} 08/31/2021 09:05:52 - INFO - __main__ - Step 109514: {'lr': 8.678013573888585e-05, 'samples': 21026688, 'steps': 109513, 'loss/train': 1.6724406480789185} 08/31/2021 09:05:53 - INFO - __main__ - Step 109515: {'lr': 8.677611611940639e-05, 'samples': 21026880, 'steps': 109514, 'loss/train': 0.35916948318481445} 08/31/2021 09:05:53 - INFO - __main__ - Step 109516: {'lr': 8.677209657347312e-05, 'samples': 21027072, 'steps': 109515, 'loss/train': 0.31391003727912903} 08/31/2021 09:05:53 - INFO - __main__ - Step 109517: {'lr': 8.676807710108781e-05, 'samples': 21027264, 'steps': 109516, 'loss/train': 0.29853224754333496} 08/31/2021 09:05:55 - INFO - __main__ - Step 109518: {'lr': 8.676405770225226e-05, 'samples': 21027456, 'steps': 109517, 'loss/train': 0.27673089504241943} 08/31/2021 09:05:55 - INFO - __main__ - Step 109519: {'lr': 8.676003837696833e-05, 'samples': 21027648, 'steps': 109518, 'loss/train': 0.9625409841537476} 08/31/2021 09:05:56 - INFO - __main__ - Step 109520: {'lr': 8.67560191252378e-05, 'samples': 21027840, 'steps': 109519, 'loss/train': 1.1071254014968872} 08/31/2021 09:05:56 - INFO - __main__ - Step 109521: {'lr': 8.675199994706251e-05, 'samples': 21028032, 'steps': 109520, 'loss/train': 1.7103859186172485} 08/31/2021 09:05:56 - INFO - __main__ - Step 109522: {'lr': 8.674798084244423e-05, 'samples': 21028224, 'steps': 109521, 'loss/train': 0.9490204453468323} 08/31/2021 09:05:59 - INFO - __main__ - Step 109523: {'lr': 8.67439618113848e-05, 'samples': 21028416, 'steps': 109522, 'loss/train': 1.2480417490005493} 08/31/2021 09:05:59 - INFO - __main__ - Step 109524: {'lr': 8.6739942853886e-05, 'samples': 21028608, 'steps': 109523, 'loss/train': 0.8563866019248962} 08/31/2021 09:06:00 - INFO - __main__ - Step 109525: {'lr': 8.67359239699497e-05, 'samples': 21028800, 'steps': 109524, 'loss/train': 0.5408439040184021} 08/31/2021 09:06:00 - INFO - __main__ - Step 109526: {'lr': 8.673190515957774e-05, 'samples': 21028992, 'steps': 109525, 'loss/train': 0.5267857313156128} 08/31/2021 09:06:00 - INFO - __main__ - Step 109527: {'lr': 8.672788642277177e-05, 'samples': 21029184, 'steps': 109526, 'loss/train': 0.4530164897441864} 08/31/2021 09:06:01 - INFO - __main__ - Step 109528: {'lr': 8.672386775953369e-05, 'samples': 21029376, 'steps': 109527, 'loss/train': 0.7041419148445129} 08/31/2021 09:06:02 - INFO - __main__ - Step 109529: {'lr': 8.671984916986533e-05, 'samples': 21029568, 'steps': 109528, 'loss/train': 1.114013671875} 08/31/2021 09:06:03 - INFO - __main__ - Step 109530: {'lr': 8.671583065376848e-05, 'samples': 21029760, 'steps': 109529, 'loss/train': 1.451768159866333} 08/31/2021 09:06:03 - INFO - __main__ - Step 109531: {'lr': 8.671181221124497e-05, 'samples': 21029952, 'steps': 109530, 'loss/train': 0.801914393901825} 08/31/2021 09:06:03 - INFO - __main__ - Step 109532: {'lr': 8.67077938422966e-05, 'samples': 21030144, 'steps': 109531, 'loss/train': 0.8797857761383057} 08/31/2021 09:06:04 - INFO - __main__ - Step 109533: {'lr': 8.670377554692516e-05, 'samples': 21030336, 'steps': 109532, 'loss/train': 1.7258321046829224} 08/31/2021 09:06:05 - INFO - __main__ - Step 109534: {'lr': 8.66997573251325e-05, 'samples': 21030528, 'steps': 109533, 'loss/train': 0.4264909327030182} 08/31/2021 09:06:06 - INFO - __main__ - Step 109535: {'lr': 8.669573917692039e-05, 'samples': 21030720, 'steps': 109534, 'loss/train': 0.031522829085588455} 08/31/2021 09:06:06 - INFO - __main__ - Step 109536: {'lr': 8.669172110229065e-05, 'samples': 21030912, 'steps': 109535, 'loss/train': 1.3003690242767334} 08/31/2021 09:06:06 - INFO - __main__ - Step 109537: {'lr': 8.668770310124513e-05, 'samples': 21031104, 'steps': 109536, 'loss/train': 2.1890759468078613} 08/31/2021 09:06:07 - INFO - __main__ - Step 109538: {'lr': 8.668368517378558e-05, 'samples': 21031296, 'steps': 109537, 'loss/train': 1.3134925365447998} 08/31/2021 09:06:08 - INFO - __main__ - Step 109539: {'lr': 8.667966731991394e-05, 'samples': 21031488, 'steps': 109538, 'loss/train': 0.7224889397621155} 08/31/2021 09:06:09 - INFO - __main__ - Step 109540: {'lr': 8.667564953963183e-05, 'samples': 21031680, 'steps': 109539, 'loss/train': 0.9137135148048401} 08/31/2021 09:06:09 - INFO - __main__ - Step 109541: {'lr': 8.667163183294119e-05, 'samples': 21031872, 'steps': 109540, 'loss/train': 1.2062171697616577} 08/31/2021 09:06:10 - INFO - __main__ - Step 109542: {'lr': 8.666761419984376e-05, 'samples': 21032064, 'steps': 109541, 'loss/train': 0.2106151282787323} 08/31/2021 09:06:10 - INFO - __main__ - Step 109543: {'lr': 8.666359664034137e-05, 'samples': 21032256, 'steps': 109542, 'loss/train': 0.7409941554069519} 08/31/2021 09:06:10 - INFO - __main__ - Step 109544: {'lr': 8.665957915443587e-05, 'samples': 21032448, 'steps': 109543, 'loss/train': 2.501044273376465} 08/31/2021 09:06:12 - INFO - __main__ - Step 109545: {'lr': 8.665556174212905e-05, 'samples': 21032640, 'steps': 109544, 'loss/train': 0.8127780556678772} 08/31/2021 09:06:13 - INFO - __main__ - Step 109546: {'lr': 8.665154440342269e-05, 'samples': 21032832, 'steps': 109545, 'loss/train': 1.3137131929397583} 08/31/2021 09:06:13 - INFO - __main__ - Step 109547: {'lr': 8.66475271383186e-05, 'samples': 21033024, 'steps': 109546, 'loss/train': 1.1007895469665527} 08/31/2021 09:06:13 - INFO - __main__ - Step 109548: {'lr': 8.664350994681866e-05, 'samples': 21033216, 'steps': 109547, 'loss/train': 1.3857203722000122} 08/31/2021 09:06:14 - INFO - __main__ - Step 109549: {'lr': 8.663949282892461e-05, 'samples': 21033408, 'steps': 109548, 'loss/train': 1.8193458318710327} 08/31/2021 09:06:15 - INFO - __main__ - Step 109550: {'lr': 8.663547578463829e-05, 'samples': 21033600, 'steps': 109549, 'loss/train': 1.1148829460144043} 08/31/2021 09:06:16 - INFO - __main__ - Step 109551: {'lr': 8.66314588139615e-05, 'samples': 21033792, 'steps': 109550, 'loss/train': 1.0066144466400146} 08/31/2021 09:06:16 - INFO - __main__ - Step 109552: {'lr': 8.662744191689606e-05, 'samples': 21033984, 'steps': 109551, 'loss/train': 0.5963144898414612} 08/31/2021 09:06:16 - INFO - __main__ - Step 109553: {'lr': 8.662342509344387e-05, 'samples': 21034176, 'steps': 109552, 'loss/train': 0.27636441588401794} 08/31/2021 09:06:17 - INFO - __main__ - Step 109554: {'lr': 8.661940834360655e-05, 'samples': 21034368, 'steps': 109553, 'loss/train': 1.619210958480835} 08/31/2021 09:06:18 - INFO - __main__ - Step 109555: {'lr': 8.6615391667386e-05, 'samples': 21034560, 'steps': 109554, 'loss/train': 1.0129550695419312} 08/31/2021 09:06:19 - INFO - __main__ - Step 109556: {'lr': 8.661137506478403e-05, 'samples': 21034752, 'steps': 109555, 'loss/train': 0.6983411312103271} 08/31/2021 09:06:19 - INFO - __main__ - Step 109557: {'lr': 8.660735853580245e-05, 'samples': 21034944, 'steps': 109556, 'loss/train': 1.3116455078125} 08/31/2021 09:06:19 - INFO - __main__ - Step 109558: {'lr': 8.660334208044307e-05, 'samples': 21035136, 'steps': 109557, 'loss/train': 1.309079647064209} 08/31/2021 09:06:20 - INFO - __main__ - Step 109559: {'lr': 8.659932569870771e-05, 'samples': 21035328, 'steps': 109558, 'loss/train': 1.3895727396011353} 08/31/2021 09:06:21 - INFO - __main__ - Step 109560: {'lr': 8.659530939059818e-05, 'samples': 21035520, 'steps': 109559, 'loss/train': 0.8631908297538757} 08/31/2021 09:06:22 - INFO - __main__ - Step 109561: {'lr': 8.659129315611627e-05, 'samples': 21035712, 'steps': 109560, 'loss/train': 1.9653245210647583} 08/31/2021 09:06:22 - INFO - __main__ - Step 109562: {'lr': 8.65872769952638e-05, 'samples': 21035904, 'steps': 109561, 'loss/train': 1.11077880859375} 08/31/2021 09:06:22 - INFO - __main__ - Step 109563: {'lr': 8.658326090804262e-05, 'samples': 21036096, 'steps': 109562, 'loss/train': 1.3325823545455933} 08/31/2021 09:06:23 - INFO - __main__ - Step 109564: {'lr': 8.657924489445446e-05, 'samples': 21036288, 'steps': 109563, 'loss/train': 1.2005715370178223} 08/31/2021 09:06:24 - INFO - __main__ - Step 109565: {'lr': 8.657522895450118e-05, 'samples': 21036480, 'steps': 109564, 'loss/train': 0.03097541630268097} 08/31/2021 09:06:25 - INFO - __main__ - Step 109566: {'lr': 8.657121308818467e-05, 'samples': 21036672, 'steps': 109565, 'loss/train': 0.9464542269706726} 08/31/2021 09:06:25 - INFO - __main__ - Step 109567: {'lr': 8.656719729550655e-05, 'samples': 21036864, 'steps': 109566, 'loss/train': 0.022883370518684387} 08/31/2021 09:06:25 - INFO - __main__ - Step 109568: {'lr': 8.656318157646875e-05, 'samples': 21037056, 'steps': 109567, 'loss/train': 1.625653624534607} 08/31/2021 09:06:26 - INFO - __main__ - Step 109569: {'lr': 8.655916593107305e-05, 'samples': 21037248, 'steps': 109568, 'loss/train': 1.5543276071548462} 08/31/2021 09:06:26 - INFO - __main__ - Step 109570: {'lr': 8.655515035932127e-05, 'samples': 21037440, 'steps': 109569, 'loss/train': 0.8983341455459595} 08/31/2021 09:06:27 - INFO - __main__ - Step 109571: {'lr': 8.655113486121519e-05, 'samples': 21037632, 'steps': 109570, 'loss/train': 0.9342929124832153} 08/31/2021 09:06:28 - INFO - __main__ - Step 109572: {'lr': 8.654711943675666e-05, 'samples': 21037824, 'steps': 109571, 'loss/train': 0.9530139565467834} 08/31/2021 09:06:28 - INFO - __main__ - Step 109573: {'lr': 8.65431040859475e-05, 'samples': 21038016, 'steps': 109572, 'loss/train': 0.4599377512931824} 08/31/2021 09:06:29 - INFO - __main__ - Step 109574: {'lr': 8.653908880878947e-05, 'samples': 21038208, 'steps': 109573, 'loss/train': 1.1889923810958862} 08/31/2021 09:06:29 - INFO - __main__ - Step 109575: {'lr': 8.653507360528442e-05, 'samples': 21038400, 'steps': 109574, 'loss/train': 1.6103172302246094} 08/31/2021 09:06:31 - INFO - __main__ - Step 109576: {'lr': 8.653105847543413e-05, 'samples': 21038592, 'steps': 109575, 'loss/train': 1.2494428157806396} 08/31/2021 09:06:31 - INFO - __main__ - Step 109577: {'lr': 8.652704341924045e-05, 'samples': 21038784, 'steps': 109576, 'loss/train': 1.0644190311431885} 08/31/2021 09:06:31 - INFO - __main__ - Step 109578: {'lr': 8.652302843670512e-05, 'samples': 21038976, 'steps': 109577, 'loss/train': 1.1242268085479736} 08/31/2021 09:06:32 - INFO - __main__ - Step 109579: {'lr': 8.651901352783001e-05, 'samples': 21039168, 'steps': 109578, 'loss/train': 0.884358823299408} 08/31/2021 09:06:32 - INFO - __main__ - Step 109580: {'lr': 8.6514998692617e-05, 'samples': 21039360, 'steps': 109579, 'loss/train': 0.025794193148612976} 08/31/2021 09:06:35 - INFO - __main__ - Step 109581: {'lr': 8.651098393106774e-05, 'samples': 21039552, 'steps': 109580, 'loss/train': 0.3425443768501282} 08/31/2021 09:06:35 - INFO - __main__ - Step 109582: {'lr': 8.650696924318407e-05, 'samples': 21039744, 'steps': 109581, 'loss/train': 1.18869948387146} 08/31/2021 09:06:35 - INFO - __main__ - Step 109583: {'lr': 8.650295462896787e-05, 'samples': 21039936, 'steps': 109582, 'loss/train': 1.1565437316894531} 08/31/2021 09:06:36 - INFO - __main__ - Step 109584: {'lr': 8.649894008842088e-05, 'samples': 21040128, 'steps': 109583, 'loss/train': 0.1364741176366806} 08/31/2021 09:06:36 - INFO - __main__ - Step 109585: {'lr': 8.649492562154499e-05, 'samples': 21040320, 'steps': 109584, 'loss/train': 0.8509073257446289} 08/31/2021 09:06:37 - INFO - __main__ - Step 109586: {'lr': 8.649091122834193e-05, 'samples': 21040512, 'steps': 109585, 'loss/train': 0.8194999694824219} 08/31/2021 09:06:38 - INFO - __main__ - Step 109587: {'lr': 8.648689690881356e-05, 'samples': 21040704, 'steps': 109586, 'loss/train': 0.527550995349884} 08/31/2021 09:06:38 - INFO - __main__ - Step 109588: {'lr': 8.648288266296164e-05, 'samples': 21040896, 'steps': 109587, 'loss/train': 1.2104696035385132} 08/31/2021 09:06:39 - INFO - __main__ - Step 109589: {'lr': 8.647886849078804e-05, 'samples': 21041088, 'steps': 109588, 'loss/train': 1.6426231861114502} 08/31/2021 09:06:39 - INFO - __main__ - Step 109590: {'lr': 8.647485439229452e-05, 'samples': 21041280, 'steps': 109589, 'loss/train': 1.1353061199188232} 08/31/2021 09:06:40 - INFO - __main__ - Step 109591: {'lr': 8.647084036748292e-05, 'samples': 21041472, 'steps': 109590, 'loss/train': 1.110459566116333} 08/31/2021 09:06:41 - INFO - __main__ - Step 109592: {'lr': 8.646682641635506e-05, 'samples': 21041664, 'steps': 109591, 'loss/train': 0.4070482850074768} 08/31/2021 09:06:41 - INFO - __main__ - Step 109593: {'lr': 8.646281253891278e-05, 'samples': 21041856, 'steps': 109592, 'loss/train': 1.2137751579284668} 08/31/2021 09:06:42 - INFO - __main__ - Step 109594: {'lr': 8.645879873515774e-05, 'samples': 21042048, 'steps': 109593, 'loss/train': 1.2179464101791382} 08/31/2021 09:06:42 - INFO - __main__ - Step 109595: {'lr': 8.645478500509185e-05, 'samples': 21042240, 'steps': 109594, 'loss/train': 1.1781837940216064} 08/31/2021 09:06:43 - INFO - __main__ - Step 109596: {'lr': 8.645077134871693e-05, 'samples': 21042432, 'steps': 109595, 'loss/train': 1.2071831226348877} 08/31/2021 09:06:44 - INFO - __main__ - Step 109597: {'lr': 8.644675776603475e-05, 'samples': 21042624, 'steps': 109596, 'loss/train': 1.0316872596740723} 08/31/2021 09:06:44 - INFO - __main__ - Step 109598: {'lr': 8.644274425704713e-05, 'samples': 21042816, 'steps': 109597, 'loss/train': 1.145615816116333} 08/31/2021 09:06:45 - INFO - __main__ - Step 109599: {'lr': 8.643873082175591e-05, 'samples': 21043008, 'steps': 109598, 'loss/train': 0.9996358752250671} 08/31/2021 09:06:45 - INFO - __main__ - Step 109600: {'lr': 8.643471746016285e-05, 'samples': 21043200, 'steps': 109599, 'loss/train': 1.3166863918304443} 08/31/2021 09:06:46 - INFO - __main__ - Step 109601: {'lr': 8.643070417226978e-05, 'samples': 21043392, 'steps': 109600, 'loss/train': 0.6864966154098511} 08/31/2021 09:06:47 - INFO - __main__ - Step 109602: {'lr': 8.642669095807853e-05, 'samples': 21043584, 'steps': 109601, 'loss/train': 1.2498934268951416} 08/31/2021 09:06:47 - INFO - __main__ - Step 109603: {'lr': 8.64226778175909e-05, 'samples': 21043776, 'steps': 109602, 'loss/train': 1.2065162658691406} 08/31/2021 09:06:48 - INFO - __main__ - Step 109604: {'lr': 8.641866475080865e-05, 'samples': 21043968, 'steps': 109603, 'loss/train': 0.4247612953186035} 08/31/2021 09:06:48 - INFO - __main__ - Step 109605: {'lr': 8.641465175773364e-05, 'samples': 21044160, 'steps': 109604, 'loss/train': 1.40215265750885} 08/31/2021 09:06:50 - INFO - __main__ - Step 109606: {'lr': 8.641063883836767e-05, 'samples': 21044352, 'steps': 109605, 'loss/train': 1.177076816558838} 08/31/2021 09:06:50 - INFO - __main__ - Step 109607: {'lr': 8.640662599271262e-05, 'samples': 21044544, 'steps': 109606, 'loss/train': 0.8945357203483582} 08/31/2021 09:06:50 - INFO - __main__ - Step 109608: {'lr': 8.640261322077015e-05, 'samples': 21044736, 'steps': 109607, 'loss/train': 1.2759665250778198} 08/31/2021 09:06:51 - INFO - __main__ - Step 109609: {'lr': 8.639860052254212e-05, 'samples': 21044928, 'steps': 109608, 'loss/train': 0.8576114177703857} 08/31/2021 09:06:51 - INFO - __main__ - Step 109610: {'lr': 8.639458789803037e-05, 'samples': 21045120, 'steps': 109609, 'loss/train': 0.5294211506843567} 08/31/2021 09:06:51 - INFO - __main__ - Step 109611: {'lr': 8.639057534723668e-05, 'samples': 21045312, 'steps': 109610, 'loss/train': 1.3625999689102173} 08/31/2021 09:06:53 - INFO - __main__ - Step 109612: {'lr': 8.638656287016288e-05, 'samples': 21045504, 'steps': 109611, 'loss/train': 1.2971234321594238} 08/31/2021 09:06:53 - INFO - __main__ - Step 109613: {'lr': 8.638255046681077e-05, 'samples': 21045696, 'steps': 109612, 'loss/train': 0.5720177292823792} 08/31/2021 09:06:54 - INFO - __main__ - Step 109614: {'lr': 8.637853813718216e-05, 'samples': 21045888, 'steps': 109613, 'loss/train': 1.048160195350647} 08/31/2021 09:06:54 - INFO - __main__ - Step 109615: {'lr': 8.637452588127887e-05, 'samples': 21046080, 'steps': 109614, 'loss/train': 1.186279535293579} 08/31/2021 09:06:54 - INFO - __main__ - Step 109616: {'lr': 8.637051369910265e-05, 'samples': 21046272, 'steps': 109615, 'loss/train': 0.5887988805770874} 08/31/2021 09:06:56 - INFO - __main__ - Step 109617: {'lr': 8.63665015906554e-05, 'samples': 21046464, 'steps': 109616, 'loss/train': 1.227174997329712} 08/31/2021 09:06:56 - INFO - __main__ - Step 109618: {'lr': 8.636248955593883e-05, 'samples': 21046656, 'steps': 109617, 'loss/train': 1.2482481002807617} 08/31/2021 09:06:56 - INFO - __main__ - Step 109619: {'lr': 8.635847759495485e-05, 'samples': 21046848, 'steps': 109618, 'loss/train': 1.2466696500778198} 08/31/2021 09:06:57 - INFO - __main__ - Step 109620: {'lr': 8.635446570770528e-05, 'samples': 21047040, 'steps': 109619, 'loss/train': 0.7751721143722534} 08/31/2021 09:06:57 - INFO - __main__ - Step 109621: {'lr': 8.635045389419178e-05, 'samples': 21047232, 'steps': 109620, 'loss/train': 1.0587372779846191} 08/31/2021 09:06:59 - INFO - __main__ - Step 109622: {'lr': 8.63464421544162e-05, 'samples': 21047424, 'steps': 109621, 'loss/train': 0.17174741625785828} 08/31/2021 09:06:59 - INFO - __main__ - Step 109623: {'lr': 8.634243048838045e-05, 'samples': 21047616, 'steps': 109622, 'loss/train': 0.46823641657829285} 08/31/2021 09:07:00 - INFO - __main__ - Step 109624: {'lr': 8.633841889608623e-05, 'samples': 21047808, 'steps': 109623, 'loss/train': 1.460947871208191} 08/31/2021 09:07:00 - INFO - __main__ - Step 109625: {'lr': 8.63344073775354e-05, 'samples': 21048000, 'steps': 109624, 'loss/train': 1.347442626953125} 08/31/2021 09:07:00 - INFO - __main__ - Step 109626: {'lr': 8.63303959327298e-05, 'samples': 21048192, 'steps': 109625, 'loss/train': 0.7528598308563232} 08/31/2021 09:07:02 - INFO - __main__ - Step 109627: {'lr': 8.632638456167114e-05, 'samples': 21048384, 'steps': 109626, 'loss/train': 1.0204055309295654} 08/31/2021 09:07:02 - INFO - __main__ - Step 109628: {'lr': 8.632237326436132e-05, 'samples': 21048576, 'steps': 109627, 'loss/train': 1.2594062089920044} 08/31/2021 09:07:03 - INFO - __main__ - Step 109629: {'lr': 8.631836204080209e-05, 'samples': 21048768, 'steps': 109628, 'loss/train': 1.3266488313674927} 08/31/2021 09:07:03 - INFO - __main__ - Step 109630: {'lr': 8.631435089099532e-05, 'samples': 21048960, 'steps': 109629, 'loss/train': 0.7726607918739319} 08/31/2021 09:07:03 - INFO - __main__ - Step 109631: {'lr': 8.631033981494282e-05, 'samples': 21049152, 'steps': 109630, 'loss/train': 1.0625067949295044} 08/31/2021 09:07:05 - INFO - __main__ - Step 109632: {'lr': 8.63063288126463e-05, 'samples': 21049344, 'steps': 109631, 'loss/train': 1.7385585308074951} 08/31/2021 09:07:06 - INFO - __main__ - Step 109633: {'lr': 8.630231788410762e-05, 'samples': 21049536, 'steps': 109632, 'loss/train': 0.4449025094509125} 08/31/2021 09:07:06 - INFO - __main__ - Step 109634: {'lr': 8.629830702932856e-05, 'samples': 21049728, 'steps': 109633, 'loss/train': 0.4664746820926666} 08/31/2021 09:07:07 - INFO - __main__ - Step 109635: {'lr': 8.629429624831098e-05, 'samples': 21049920, 'steps': 109634, 'loss/train': 1.7246133089065552} 08/31/2021 09:07:07 - INFO - __main__ - Step 109636: {'lr': 8.629028554105666e-05, 'samples': 21050112, 'steps': 109635, 'loss/train': 1.255039930343628} 08/31/2021 09:07:08 - INFO - __main__ - Step 109637: {'lr': 8.628627490756743e-05, 'samples': 21050304, 'steps': 109636, 'loss/train': 0.7294701337814331} 08/31/2021 09:07:09 - INFO - __main__ - Step 109638: {'lr': 8.628226434784506e-05, 'samples': 21050496, 'steps': 109637, 'loss/train': 1.1768451929092407} 08/31/2021 09:07:09 - INFO - __main__ - Step 109639: {'lr': 8.627825386189136e-05, 'samples': 21050688, 'steps': 109638, 'loss/train': 0.6897410154342651} 08/31/2021 09:07:10 - INFO - __main__ - Step 109640: {'lr': 8.62742434497082e-05, 'samples': 21050880, 'steps': 109639, 'loss/train': 1.0238045454025269} 08/31/2021 09:07:10 - INFO - __main__ - Step 109641: {'lr': 8.627023311129729e-05, 'samples': 21051072, 'steps': 109640, 'loss/train': 0.03752599284052849} 08/31/2021 09:07:12 - INFO - __main__ - Step 109642: {'lr': 8.626622284666058e-05, 'samples': 21051264, 'steps': 109641, 'loss/train': 0.8593400716781616} 08/31/2021 09:07:12 - INFO - __main__ - Step 109643: {'lr': 8.626221265579973e-05, 'samples': 21051456, 'steps': 109642, 'loss/train': 0.5831655263900757} 08/31/2021 09:07:12 - INFO - __main__ - Step 109644: {'lr': 8.625820253871655e-05, 'samples': 21051648, 'steps': 109643, 'loss/train': 1.0570429563522339} 08/31/2021 09:07:13 - INFO - __main__ - Step 109645: {'lr': 8.625419249541294e-05, 'samples': 21051840, 'steps': 109644, 'loss/train': 0.6096997857093811} 08/31/2021 09:07:13 - INFO - __main__ - Step 109646: {'lr': 8.625018252589065e-05, 'samples': 21052032, 'steps': 109645, 'loss/train': 1.1633223295211792} 08/31/2021 09:07:15 - INFO - __main__ - Step 109647: {'lr': 8.62461726301515e-05, 'samples': 21052224, 'steps': 109646, 'loss/train': 1.2284380197525024} 08/31/2021 09:07:16 - INFO - __main__ - Step 109648: {'lr': 8.62421628081973e-05, 'samples': 21052416, 'steps': 109647, 'loss/train': 1.361430287361145} 08/31/2021 09:07:16 - INFO - __main__ - Step 109649: {'lr': 8.623815306002986e-05, 'samples': 21052608, 'steps': 109648, 'loss/train': 1.3880717754364014} 08/31/2021 09:07:16 - INFO - __main__ - Step 109650: {'lr': 8.623414338565097e-05, 'samples': 21052800, 'steps': 109649, 'loss/train': 0.870713472366333} 08/31/2021 09:07:17 - INFO - __main__ - Step 109651: {'lr': 8.623013378506245e-05, 'samples': 21052992, 'steps': 109650, 'loss/train': 1.1016613245010376} 08/31/2021 09:07:17 - INFO - __main__ - Step 109652: {'lr': 8.622612425826612e-05, 'samples': 21053184, 'steps': 109651, 'loss/train': 1.5776523351669312} 08/31/2021 09:07:17 - INFO - __main__ - Step 109653: {'lr': 8.622211480526382e-05, 'samples': 21053376, 'steps': 109652, 'loss/train': 1.3524088859558105} 08/31/2021 09:07:19 - INFO - __main__ - Step 109654: {'lr': 8.621810542605727e-05, 'samples': 21053568, 'steps': 109653, 'loss/train': 0.39621028304100037} 08/31/2021 09:07:19 - INFO - __main__ - Step 109655: {'lr': 8.621409612064829e-05, 'samples': 21053760, 'steps': 109654, 'loss/train': 1.233760118484497} 08/31/2021 09:07:20 - INFO - __main__ - Step 109656: {'lr': 8.621008688903869e-05, 'samples': 21053952, 'steps': 109655, 'loss/train': 0.1116458922624588} 08/31/2021 09:07:20 - INFO - __main__ - Step 109657: {'lr': 8.620607773123031e-05, 'samples': 21054144, 'steps': 109656, 'loss/train': 0.6807094216346741} 08/31/2021 09:07:20 - INFO - __main__ - Step 109658: {'lr': 8.620206864722496e-05, 'samples': 21054336, 'steps': 109657, 'loss/train': 1.2941381931304932} 08/31/2021 09:07:22 - INFO - __main__ - Step 109659: {'lr': 8.619805963702443e-05, 'samples': 21054528, 'steps': 109658, 'loss/train': 1.4385054111480713} 08/31/2021 09:07:22 - INFO - __main__ - Step 109660: {'lr': 8.619405070063052e-05, 'samples': 21054720, 'steps': 109659, 'loss/train': 1.2487504482269287} 08/31/2021 09:07:23 - INFO - __main__ - Step 109661: {'lr': 8.619004183804505e-05, 'samples': 21054912, 'steps': 109660, 'loss/train': 0.02234090119600296} 08/31/2021 09:07:23 - INFO - __main__ - Step 109662: {'lr': 8.618603304926981e-05, 'samples': 21055104, 'steps': 109661, 'loss/train': 1.4214794635772705} 08/31/2021 09:07:23 - INFO - __main__ - Step 109663: {'lr': 8.61820243343066e-05, 'samples': 21055296, 'steps': 109662, 'loss/train': 1.7832438945770264} 08/31/2021 09:07:25 - INFO - __main__ - Step 109664: {'lr': 8.617801569315736e-05, 'samples': 21055488, 'steps': 109663, 'loss/train': 0.2307538390159607} 08/31/2021 09:07:25 - INFO - __main__ - Step 109665: {'lr': 8.617400712582369e-05, 'samples': 21055680, 'steps': 109664, 'loss/train': 1.1815584897994995} 08/31/2021 09:07:26 - INFO - __main__ - Step 109666: {'lr': 8.616999863230746e-05, 'samples': 21055872, 'steps': 109665, 'loss/train': 1.1573694944381714} 08/31/2021 09:07:26 - INFO - __main__ - Step 109667: {'lr': 8.616599021261052e-05, 'samples': 21056064, 'steps': 109666, 'loss/train': 1.6133925914764404} 08/31/2021 09:07:26 - INFO - __main__ - Step 109668: {'lr': 8.616198186673462e-05, 'samples': 21056256, 'steps': 109667, 'loss/train': 0.9530892968177795} 08/31/2021 09:07:27 - INFO - __main__ - Step 109669: {'lr': 8.615797359468166e-05, 'samples': 21056448, 'steps': 109668, 'loss/train': 0.6863855719566345} 08/31/2021 09:07:28 - INFO - __main__ - Step 109670: {'lr': 8.615396539645334e-05, 'samples': 21056640, 'steps': 109669, 'loss/train': 1.1495676040649414} 08/31/2021 09:07:29 - INFO - __main__ - Step 109671: {'lr': 8.614995727205155e-05, 'samples': 21056832, 'steps': 109670, 'loss/train': 1.029179573059082} 08/31/2021 09:07:29 - INFO - __main__ - Step 109672: {'lr': 8.614594922147805e-05, 'samples': 21057024, 'steps': 109671, 'loss/train': 0.7757511734962463} 08/31/2021 09:07:29 - INFO - __main__ - Step 109673: {'lr': 8.614194124473465e-05, 'samples': 21057216, 'steps': 109672, 'loss/train': 1.1972174644470215} 08/31/2021 09:07:30 - INFO - __main__ - Step 109674: {'lr': 8.613793334182316e-05, 'samples': 21057408, 'steps': 109673, 'loss/train': 1.8281617164611816} 08/31/2021 09:07:32 - INFO - __main__ - Step 109675: {'lr': 8.613392551274549e-05, 'samples': 21057600, 'steps': 109674, 'loss/train': 0.8623883724212646} 08/31/2021 09:07:32 - INFO - __main__ - Step 109676: {'lr': 8.612991775750326e-05, 'samples': 21057792, 'steps': 109675, 'loss/train': 0.9365790486335754} 08/31/2021 09:07:33 - INFO - __main__ - Step 109677: {'lr': 8.612591007609832e-05, 'samples': 21057984, 'steps': 109676, 'loss/train': 1.5581183433532715} 08/31/2021 09:07:33 - INFO - __main__ - Step 109678: {'lr': 8.612190246853257e-05, 'samples': 21058176, 'steps': 109677, 'loss/train': 1.3760440349578857} 08/31/2021 09:07:33 - INFO - __main__ - Step 109679: {'lr': 8.611789493480773e-05, 'samples': 21058368, 'steps': 109678, 'loss/train': 0.5238962769508362} 08/31/2021 09:07:34 - INFO - __main__ - Step 109680: {'lr': 8.611388747492565e-05, 'samples': 21058560, 'steps': 109679, 'loss/train': 0.39799565076828003} 08/31/2021 09:07:35 - INFO - __main__ - Step 109681: {'lr': 8.610988008888812e-05, 'samples': 21058752, 'steps': 109680, 'loss/train': 0.09652460366487503} 08/31/2021 09:07:36 - INFO - __main__ - Step 109682: {'lr': 8.610587277669696e-05, 'samples': 21058944, 'steps': 109681, 'loss/train': 1.2794057130813599} 08/31/2021 09:07:36 - INFO - __main__ - Step 109683: {'lr': 8.610186553835394e-05, 'samples': 21059136, 'steps': 109682, 'loss/train': 0.8111547827720642} 08/31/2021 09:07:37 - INFO - __main__ - Step 109684: {'lr': 8.609785837386092e-05, 'samples': 21059328, 'steps': 109683, 'loss/train': 1.3102420568466187} 08/31/2021 09:07:37 - INFO - __main__ - Step 109685: {'lr': 8.609385128321965e-05, 'samples': 21059520, 'steps': 109684, 'loss/train': 0.7089244723320007} 08/31/2021 09:07:39 - INFO - __main__ - Step 109686: {'lr': 8.608984426643196e-05, 'samples': 21059712, 'steps': 109685, 'loss/train': 1.0163668394088745} 08/31/2021 09:07:39 - INFO - __main__ - Step 109687: {'lr': 8.608583732349976e-05, 'samples': 21059904, 'steps': 109686, 'loss/train': 0.37585917115211487} 08/31/2021 09:07:40 - INFO - __main__ - Step 109688: {'lr': 8.608183045442466e-05, 'samples': 21060096, 'steps': 109687, 'loss/train': 1.2795473337173462} 08/31/2021 09:07:40 - INFO - __main__ - Step 109689: {'lr': 8.607782365920854e-05, 'samples': 21060288, 'steps': 109688, 'loss/train': 0.7338038086891174} 08/31/2021 09:07:40 - INFO - __main__ - Step 109690: {'lr': 8.607381693785326e-05, 'samples': 21060480, 'steps': 109689, 'loss/train': 1.2797244787216187} 08/31/2021 09:07:42 - INFO - __main__ - Step 109691: {'lr': 8.606981029036057e-05, 'samples': 21060672, 'steps': 109690, 'loss/train': 0.7638698220252991} 08/31/2021 09:07:42 - INFO - __main__ - Step 109692: {'lr': 8.606580371673228e-05, 'samples': 21060864, 'steps': 109691, 'loss/train': 1.2216929197311401} 08/31/2021 09:07:43 - INFO - __main__ - Step 109693: {'lr': 8.606179721697022e-05, 'samples': 21061056, 'steps': 109692, 'loss/train': 1.463110327720642} 08/31/2021 09:07:43 - INFO - __main__ - Step 109694: {'lr': 8.60577907910762e-05, 'samples': 21061248, 'steps': 109693, 'loss/train': 0.317645788192749} 08/31/2021 09:07:44 - INFO - __main__ - Step 109695: {'lr': 8.605378443905199e-05, 'samples': 21061440, 'steps': 109694, 'loss/train': 1.7882192134857178} 08/31/2021 09:07:45 - INFO - __main__ - Step 109696: {'lr': 8.604977816089942e-05, 'samples': 21061632, 'steps': 109695, 'loss/train': 0.2193615585565567} 08/31/2021 09:07:45 - INFO - __main__ - Step 109697: {'lr': 8.604577195662031e-05, 'samples': 21061824, 'steps': 109696, 'loss/train': 1.1223129034042358} 08/31/2021 09:07:46 - INFO - __main__ - Step 109698: {'lr': 8.604176582621642e-05, 'samples': 21062016, 'steps': 109697, 'loss/train': 0.7766956686973572} 08/31/2021 09:07:46 - INFO - __main__ - Step 109699: {'lr': 8.603775976968959e-05, 'samples': 21062208, 'steps': 109698, 'loss/train': 1.49200439453125} 08/31/2021 09:07:46 - INFO - __main__ - Step 109700: {'lr': 8.60337537870416e-05, 'samples': 21062400, 'steps': 109699, 'loss/train': 1.5136829614639282} 08/31/2021 09:07:48 - INFO - __main__ - Step 109701: {'lr': 8.602974787827436e-05, 'samples': 21062592, 'steps': 109700, 'loss/train': 3.0740137100219727} 08/31/2021 09:07:48 - INFO - __main__ - Step 109702: {'lr': 8.602574204338953e-05, 'samples': 21062784, 'steps': 109701, 'loss/train': 0.262266606092453} 08/31/2021 09:07:49 - INFO - __main__ - Step 109703: {'lr': 8.602173628238893e-05, 'samples': 21062976, 'steps': 109702, 'loss/train': 0.1370309591293335} 08/31/2021 09:07:49 - INFO - __main__ - Step 109704: {'lr': 8.601773059527442e-05, 'samples': 21063168, 'steps': 109703, 'loss/train': 0.8593771457672119} 08/31/2021 09:07:49 - INFO - __main__ - Step 109705: {'lr': 8.601372498204779e-05, 'samples': 21063360, 'steps': 109704, 'loss/train': 1.0046815872192383} 08/31/2021 09:07:50 - INFO - __main__ - Step 109706: {'lr': 8.600971944271086e-05, 'samples': 21063552, 'steps': 109705, 'loss/train': 1.2035506963729858} 08/31/2021 09:07:51 - INFO - __main__ - Step 109707: {'lr': 8.600571397726543e-05, 'samples': 21063744, 'steps': 109706, 'loss/train': 1.5252119302749634} 08/31/2021 09:07:52 - INFO - __main__ - Step 109708: {'lr': 8.600170858571326e-05, 'samples': 21063936, 'steps': 109707, 'loss/train': 1.3026206493377686} 08/31/2021 09:07:52 - INFO - __main__ - Step 109709: {'lr': 8.59977032680562e-05, 'samples': 21064128, 'steps': 109708, 'loss/train': 1.1966205835342407} 08/31/2021 09:07:52 - INFO - __main__ - Step 109710: {'lr': 8.599369802429604e-05, 'samples': 21064320, 'steps': 109709, 'loss/train': 1.7282861471176147} 08/31/2021 09:07:53 - INFO - __main__ - Step 109711: {'lr': 8.598969285443461e-05, 'samples': 21064512, 'steps': 109710, 'loss/train': 1.24760103225708} 08/31/2021 09:07:55 - INFO - __main__ - Step 109712: {'lr': 8.598568775847368e-05, 'samples': 21064704, 'steps': 109711, 'loss/train': 0.497186541557312} 08/31/2021 09:07:55 - INFO - __main__ - Step 109713: {'lr': 8.598168273641507e-05, 'samples': 21064896, 'steps': 109712, 'loss/train': 1.2761669158935547} 08/31/2021 09:07:55 - INFO - __main__ - Step 109714: {'lr': 8.597767778826065e-05, 'samples': 21065088, 'steps': 109713, 'loss/train': 1.3600472211837769} 08/31/2021 09:07:56 - INFO - __main__ - Step 109715: {'lr': 8.59736729140121e-05, 'samples': 21065280, 'steps': 109714, 'loss/train': 1.382265329360962} 08/31/2021 09:07:56 - INFO - __main__ - Step 109716: {'lr': 8.596966811367127e-05, 'samples': 21065472, 'steps': 109715, 'loss/train': 0.8822656869888306} 08/31/2021 09:07:57 - INFO - __main__ - Step 109717: {'lr': 8.596566338723996e-05, 'samples': 21065664, 'steps': 109716, 'loss/train': 1.2800191640853882} 08/31/2021 09:07:58 - INFO - __main__ - Step 109718: {'lr': 8.596165873472004e-05, 'samples': 21065856, 'steps': 109717, 'loss/train': 1.5650131702423096} 08/31/2021 09:07:58 - INFO - __main__ - Step 109719: {'lr': 8.59576541561132e-05, 'samples': 21066048, 'steps': 109718, 'loss/train': 1.9528982639312744} 08/31/2021 09:07:59 - INFO - __main__ - Step 109720: {'lr': 8.595364965142136e-05, 'samples': 21066240, 'steps': 109719, 'loss/train': 1.3714470863342285} 08/31/2021 09:07:59 - INFO - __main__ - Step 109721: {'lr': 8.594964522064624e-05, 'samples': 21066432, 'steps': 109720, 'loss/train': 3.1486780643463135} 08/31/2021 09:08:00 - INFO - __main__ - Step 109722: {'lr': 8.59456408637897e-05, 'samples': 21066624, 'steps': 109721, 'loss/train': 0.9691880941390991} 08/31/2021 09:08:01 - INFO - __main__ - Step 109723: {'lr': 8.594163658085352e-05, 'samples': 21066816, 'steps': 109722, 'loss/train': 1.001790165901184} 08/31/2021 09:08:01 - INFO - __main__ - Step 109724: {'lr': 8.593763237183952e-05, 'samples': 21067008, 'steps': 109723, 'loss/train': 1.2083154916763306} 08/31/2021 09:08:02 - INFO - __main__ - Step 109725: {'lr': 8.593362823674947e-05, 'samples': 21067200, 'steps': 109724, 'loss/train': 0.3248477280139923} 08/31/2021 09:08:02 - INFO - __main__ - Step 109726: {'lr': 8.59296241755852e-05, 'samples': 21067392, 'steps': 109725, 'loss/train': 0.6262058615684509} 08/31/2021 09:08:02 - INFO - __main__ - Step 109727: {'lr': 8.592562018834851e-05, 'samples': 21067584, 'steps': 109726, 'loss/train': 1.4708558320999146} 08/31/2021 09:08:04 - INFO - __main__ - Step 109728: {'lr': 8.592161627504127e-05, 'samples': 21067776, 'steps': 109727, 'loss/train': 0.8480581641197205} 08/31/2021 09:08:04 - INFO - __main__ - Step 109729: {'lr': 8.591761243566518e-05, 'samples': 21067968, 'steps': 109728, 'loss/train': 0.8300310373306274} 08/31/2021 09:08:05 - INFO - __main__ - Step 109730: {'lr': 8.591360867022206e-05, 'samples': 21068160, 'steps': 109729, 'loss/train': 0.6690343022346497} 08/31/2021 09:08:05 - INFO - __main__ - Step 109731: {'lr': 8.590960497871373e-05, 'samples': 21068352, 'steps': 109730, 'loss/train': 1.7389802932739258} 08/31/2021 09:08:05 - INFO - __main__ - Step 109732: {'lr': 8.590560136114198e-05, 'samples': 21068544, 'steps': 109731, 'loss/train': 1.3789151906967163} 08/31/2021 09:08:07 - INFO - __main__ - Step 109733: {'lr': 8.590159781750867e-05, 'samples': 21068736, 'steps': 109732, 'loss/train': 1.1724507808685303} 08/31/2021 09:08:08 - INFO - __main__ - Step 109734: {'lr': 8.589759434781555e-05, 'samples': 21068928, 'steps': 109733, 'loss/train': 1.1463855504989624} 08/31/2021 09:08:08 - INFO - __main__ - Step 109735: {'lr': 8.589359095206445e-05, 'samples': 21069120, 'steps': 109734, 'loss/train': 1.142195224761963} 08/31/2021 09:08:08 - INFO - __main__ - Step 109736: {'lr': 8.588958763025715e-05, 'samples': 21069312, 'steps': 109735, 'loss/train': 1.5476195812225342} 08/31/2021 09:08:09 - INFO - __main__ - Step 109737: {'lr': 8.588558438239547e-05, 'samples': 21069504, 'steps': 109736, 'loss/train': 0.3954411745071411} 08/31/2021 09:08:10 - INFO - __main__ - Step 109738: {'lr': 8.588158120848122e-05, 'samples': 21069696, 'steps': 109737, 'loss/train': 1.1191024780273438} 08/31/2021 09:08:11 - INFO - __main__ - Step 109739: {'lr': 8.587757810851621e-05, 'samples': 21069888, 'steps': 109738, 'loss/train': 0.8649333715438843} 08/31/2021 09:08:11 - INFO - __main__ - Step 109740: {'lr': 8.58735750825022e-05, 'samples': 21070080, 'steps': 109739, 'loss/train': 1.504191517829895} 08/31/2021 09:08:11 - INFO - __main__ - Step 109741: {'lr': 8.586957213044114e-05, 'samples': 21070272, 'steps': 109740, 'loss/train': 1.294408917427063} 08/31/2021 09:08:12 - INFO - __main__ - Step 109742: {'lr': 8.586556925233463e-05, 'samples': 21070464, 'steps': 109741, 'loss/train': 1.454949140548706} 08/31/2021 09:08:12 - INFO - __main__ - Step 109743: {'lr': 8.586156644818455e-05, 'samples': 21070656, 'steps': 109742, 'loss/train': 0.8393450975418091} 08/31/2021 09:08:14 - INFO - __main__ - Step 109744: {'lr': 8.585756371799272e-05, 'samples': 21070848, 'steps': 109743, 'loss/train': 1.2068296670913696} 08/31/2021 09:08:15 - INFO - __main__ - Step 109745: {'lr': 8.585356106176093e-05, 'samples': 21071040, 'steps': 109744, 'loss/train': 0.9681614637374878} 08/31/2021 09:08:15 - INFO - __main__ - Step 109746: {'lr': 8.5849558479491e-05, 'samples': 21071232, 'steps': 109745, 'loss/train': 1.16028892993927} 08/31/2021 09:08:15 - INFO - __main__ - Step 109747: {'lr': 8.584555597118474e-05, 'samples': 21071424, 'steps': 109746, 'loss/train': 1.5393385887145996} 08/31/2021 09:08:16 - INFO - __main__ - Step 109748: {'lr': 8.584155353684392e-05, 'samples': 21071616, 'steps': 109747, 'loss/train': 0.7564128041267395} 08/31/2021 09:08:17 - INFO - __main__ - Step 109749: {'lr': 8.583755117647038e-05, 'samples': 21071808, 'steps': 109748, 'loss/train': 1.636193037033081} 08/31/2021 09:08:18 - INFO - __main__ - Step 109750: {'lr': 8.583354889006589e-05, 'samples': 21072000, 'steps': 109749, 'loss/train': 1.1132526397705078} 08/31/2021 09:08:18 - INFO - __main__ - Step 109751: {'lr': 8.582954667763226e-05, 'samples': 21072192, 'steps': 109750, 'loss/train': 0.12939727306365967} 08/31/2021 09:08:18 - INFO - __main__ - Step 109752: {'lr': 8.582554453917132e-05, 'samples': 21072384, 'steps': 109751, 'loss/train': 0.718832790851593} 08/31/2021 09:08:19 - INFO - __main__ - Step 109753: {'lr': 8.582154247468485e-05, 'samples': 21072576, 'steps': 109752, 'loss/train': 0.938623309135437} 08/31/2021 09:08:20 - INFO - __main__ - Step 109754: {'lr': 8.581754048417468e-05, 'samples': 21072768, 'steps': 109753, 'loss/train': 0.7285679578781128} 08/31/2021 09:08:21 - INFO - __main__ - Step 109755: {'lr': 8.581353856764266e-05, 'samples': 21072960, 'steps': 109754, 'loss/train': 0.9653802514076233} 08/31/2021 09:08:21 - INFO - __main__ - Step 109756: {'lr': 8.580953672509043e-05, 'samples': 21073152, 'steps': 109755, 'loss/train': 0.9174444079399109} 08/31/2021 09:08:21 - INFO - __main__ - Step 109757: {'lr': 8.580553495651991e-05, 'samples': 21073344, 'steps': 109756, 'loss/train': 1.2297916412353516} 08/31/2021 09:08:22 - INFO - __main__ - Step 109758: {'lr': 8.580153326193288e-05, 'samples': 21073536, 'steps': 109757, 'loss/train': 0.08975863456726074} 08/31/2021 09:08:22 - INFO - __main__ - Step 109759: {'lr': 8.579753164133114e-05, 'samples': 21073728, 'steps': 109758, 'loss/train': 1.174912452697754} 08/31/2021 09:08:24 - INFO - __main__ - Step 109760: {'lr': 8.579353009471649e-05, 'samples': 21073920, 'steps': 109759, 'loss/train': 1.7067811489105225} 08/31/2021 09:08:24 - INFO - __main__ - Step 109761: {'lr': 8.578952862209075e-05, 'samples': 21074112, 'steps': 109760, 'loss/train': 0.9096996188163757} 08/31/2021 09:08:25 - INFO - __main__ - Step 109762: {'lr': 8.57855272234557e-05, 'samples': 21074304, 'steps': 109761, 'loss/train': 1.1996655464172363} 08/31/2021 09:08:25 - INFO - __main__ - Step 109763: {'lr': 8.578152589881318e-05, 'samples': 21074496, 'steps': 109762, 'loss/train': 1.0802676677703857} 08/31/2021 09:08:25 - INFO - __main__ - Step 109764: {'lr': 8.577752464816496e-05, 'samples': 21074688, 'steps': 109763, 'loss/train': 0.8592026829719543} 08/31/2021 09:08:27 - INFO - __main__ - Step 109765: {'lr': 8.577352347151285e-05, 'samples': 21074880, 'steps': 109764, 'loss/train': 1.127960443496704} 08/31/2021 09:08:27 - INFO - __main__ - Step 109766: {'lr': 8.576952236885868e-05, 'samples': 21075072, 'steps': 109765, 'loss/train': 1.0434297323226929} 08/31/2021 09:08:28 - INFO - __main__ - Step 109767: {'lr': 8.57655213402042e-05, 'samples': 21075264, 'steps': 109766, 'loss/train': 1.0873265266418457} 08/31/2021 09:08:28 - INFO - __main__ - Step 109768: {'lr': 8.576152038555132e-05, 'samples': 21075456, 'steps': 109767, 'loss/train': 0.9689233303070068} 08/31/2021 09:08:28 - INFO - __main__ - Step 109769: {'lr': 8.575751950490172e-05, 'samples': 21075648, 'steps': 109768, 'loss/train': 0.1454911231994629} 08/31/2021 09:08:30 - INFO - __main__ - Step 109770: {'lr': 8.57535186982572e-05, 'samples': 21075840, 'steps': 109769, 'loss/train': 1.4151270389556885} 08/31/2021 09:08:31 - INFO - __main__ - Step 109771: {'lr': 8.574951796561964e-05, 'samples': 21076032, 'steps': 109770, 'loss/train': 0.7856435775756836} 08/31/2021 09:08:31 - INFO - __main__ - Step 109772: {'lr': 8.574551730699082e-05, 'samples': 21076224, 'steps': 109771, 'loss/train': 0.03455156087875366} 08/31/2021 09:08:31 - INFO - __main__ - Step 109773: {'lr': 8.574151672237251e-05, 'samples': 21076416, 'steps': 109772, 'loss/train': 1.032605528831482} 08/31/2021 09:08:32 - INFO - __main__ - Step 109774: {'lr': 8.573751621176657e-05, 'samples': 21076608, 'steps': 109773, 'loss/train': 1.4519612789154053} 08/31/2021 09:08:33 - INFO - __main__ - Step 109775: {'lr': 8.573351577517474e-05, 'samples': 21076800, 'steps': 109774, 'loss/train': 0.8332417011260986} 08/31/2021 09:08:33 - INFO - __main__ - Step 109776: {'lr': 8.572951541259885e-05, 'samples': 21076992, 'steps': 109775, 'loss/train': 1.3869787454605103} 08/31/2021 09:08:34 - INFO - __main__ - Step 109777: {'lr': 8.572551512404072e-05, 'samples': 21077184, 'steps': 109776, 'loss/train': 1.0105116367340088} 08/31/2021 09:08:34 - INFO - __main__ - Step 109778: {'lr': 8.572151490950214e-05, 'samples': 21077376, 'steps': 109777, 'loss/train': 0.6807621717453003} 08/31/2021 09:08:35 - INFO - __main__ - Step 109779: {'lr': 8.57175147689849e-05, 'samples': 21077568, 'steps': 109778, 'loss/train': 0.9873929619789124} 08/31/2021 09:08:36 - INFO - __main__ - Step 109780: {'lr': 8.571351470249083e-05, 'samples': 21077760, 'steps': 109779, 'loss/train': 1.3899917602539062} 08/31/2021 09:08:37 - INFO - __main__ - Step 109781: {'lr': 8.570951471002178e-05, 'samples': 21077952, 'steps': 109780, 'loss/train': 0.018194351345300674} 08/31/2021 09:08:37 - INFO - __main__ - Step 109782: {'lr': 8.570551479157942e-05, 'samples': 21078144, 'steps': 109781, 'loss/train': 1.209765076637268} 08/31/2021 09:08:37 - INFO - __main__ - Step 109783: {'lr': 8.570151494716561e-05, 'samples': 21078336, 'steps': 109782, 'loss/train': 0.6390474438667297} 08/31/2021 09:08:38 - INFO - __main__ - Step 109784: {'lr': 8.569751517678218e-05, 'samples': 21078528, 'steps': 109783, 'loss/train': 0.9768070578575134} 08/31/2021 09:08:38 - INFO - __main__ - Step 109785: {'lr': 8.569351548043089e-05, 'samples': 21078720, 'steps': 109784, 'loss/train': 1.1792328357696533} 08/31/2021 09:08:40 - INFO - __main__ - Step 109786: {'lr': 8.568951585811358e-05, 'samples': 21078912, 'steps': 109785, 'loss/train': 1.5036133527755737} 08/31/2021 09:08:40 - INFO - __main__ - Step 109787: {'lr': 8.568551630983201e-05, 'samples': 21079104, 'steps': 109786, 'loss/train': 1.5249096155166626} 08/31/2021 09:08:40 - INFO - __main__ - Step 109788: {'lr': 8.568151683558806e-05, 'samples': 21079296, 'steps': 109787, 'loss/train': 1.4299767017364502} 08/31/2021 09:08:41 - INFO - __main__ - Step 109789: {'lr': 8.567751743538344e-05, 'samples': 21079488, 'steps': 109788, 'loss/train': 0.4652099311351776} 08/31/2021 09:08:41 - INFO - __main__ - Step 109790: {'lr': 8.567351810922003e-05, 'samples': 21079680, 'steps': 109789, 'loss/train': 0.686325192451477} 08/31/2021 09:08:43 - INFO - __main__ - Step 109791: {'lr': 8.566951885709956e-05, 'samples': 21079872, 'steps': 109790, 'loss/train': 1.1743029356002808} 08/31/2021 09:08:43 - INFO - __main__ - Step 109792: {'lr': 8.56655196790239e-05, 'samples': 21080064, 'steps': 109791, 'loss/train': 0.7131978273391724} 08/31/2021 09:08:43 - INFO - __main__ - Step 109793: {'lr': 8.566152057499479e-05, 'samples': 21080256, 'steps': 109792, 'loss/train': 1.4258145093917847} 08/31/2021 09:08:44 - INFO - __main__ - Step 109794: {'lr': 8.565752154501411e-05, 'samples': 21080448, 'steps': 109793, 'loss/train': 1.6457579135894775} 08/31/2021 09:08:44 - INFO - __main__ - Step 109795: {'lr': 8.565352258908365e-05, 'samples': 21080640, 'steps': 109794, 'loss/train': 0.9430857300758362} 08/31/2021 09:08:46 - INFO - __main__ - Step 109796: {'lr': 8.564952370720513e-05, 'samples': 21080832, 'steps': 109795, 'loss/train': 0.3999185860157013} 08/31/2021 09:08:47 - INFO - __main__ - Step 109797: {'lr': 8.564552489938037e-05, 'samples': 21081024, 'steps': 109796, 'loss/train': 1.0302711725234985} 08/31/2021 09:08:47 - INFO - __main__ - Step 109798: {'lr': 8.564152616561122e-05, 'samples': 21081216, 'steps': 109797, 'loss/train': 0.9852102994918823} 08/31/2021 09:08:47 - INFO - __main__ - Step 109799: {'lr': 8.563752750589946e-05, 'samples': 21081408, 'steps': 109798, 'loss/train': 0.7019480466842651} 08/31/2021 09:08:48 - INFO - __main__ - Step 109800: {'lr': 8.56335289202469e-05, 'samples': 21081600, 'steps': 109799, 'loss/train': 1.2446582317352295} 08/31/2021 09:08:49 - INFO - __main__ - Step 109801: {'lr': 8.562953040865531e-05, 'samples': 21081792, 'steps': 109800, 'loss/train': 0.17832672595977783} 08/31/2021 09:08:50 - INFO - __main__ - Step 109802: {'lr': 8.562553197112651e-05, 'samples': 21081984, 'steps': 109801, 'loss/train': 0.6896446943283081} 08/31/2021 09:08:50 - INFO - __main__ - Step 109803: {'lr': 8.562153360766234e-05, 'samples': 21082176, 'steps': 109802, 'loss/train': 0.9882676601409912} 08/31/2021 09:08:50 - INFO - __main__ - Step 109804: {'lr': 8.561753531826457e-05, 'samples': 21082368, 'steps': 109803, 'loss/train': 1.3173209428787231} 08/31/2021 09:08:51 - INFO - __main__ - Step 109805: {'lr': 8.561353710293499e-05, 'samples': 21082560, 'steps': 109804, 'loss/train': 0.5450618267059326} 08/31/2021 09:08:52 - INFO - __main__ - Step 109806: {'lr': 8.560953896167542e-05, 'samples': 21082752, 'steps': 109805, 'loss/train': 1.008264183998108} 08/31/2021 09:08:52 - INFO - __main__ - Step 109807: {'lr': 8.560554089448766e-05, 'samples': 21082944, 'steps': 109806, 'loss/train': 1.0717518329620361} 08/31/2021 09:08:53 - INFO - __main__ - Step 109808: {'lr': 8.560154290137357e-05, 'samples': 21083136, 'steps': 109807, 'loss/train': 0.9539169073104858} 08/31/2021 09:08:53 - INFO - __main__ - Step 109809: {'lr': 8.559754498233483e-05, 'samples': 21083328, 'steps': 109808, 'loss/train': 1.159468650817871} 08/31/2021 09:08:54 - INFO - __main__ - Step 109810: {'lr': 8.559354713737327e-05, 'samples': 21083520, 'steps': 109809, 'loss/train': 1.3185352087020874} 08/31/2021 09:08:55 - INFO - __main__ - Step 109811: {'lr': 8.558954936649074e-05, 'samples': 21083712, 'steps': 109810, 'loss/train': 1.4661943912506104} 08/31/2021 09:08:55 - INFO - __main__ - Step 109812: {'lr': 8.5585551669689e-05, 'samples': 21083904, 'steps': 109811, 'loss/train': 0.7635228633880615} 08/31/2021 09:08:56 - INFO - __main__ - Step 109813: {'lr': 8.55815540469699e-05, 'samples': 21084096, 'steps': 109812, 'loss/train': 1.6042962074279785} 08/31/2021 09:08:56 - INFO - __main__ - Step 109814: {'lr': 8.55775564983352e-05, 'samples': 21084288, 'steps': 109813, 'loss/train': 2.564554214477539} 08/31/2021 09:08:56 - INFO - __main__ - Step 109815: {'lr': 8.557355902378675e-05, 'samples': 21084480, 'steps': 109814, 'loss/train': 1.42527437210083} 08/31/2021 09:08:58 - INFO - __main__ - Step 109816: {'lr': 8.556956162332628e-05, 'samples': 21084672, 'steps': 109815, 'loss/train': 1.4053295850753784} 08/31/2021 09:08:58 - INFO - __main__ - Step 109817: {'lr': 8.556556429695564e-05, 'samples': 21084864, 'steps': 109816, 'loss/train': 0.7402075529098511} 08/31/2021 09:08:59 - INFO - __main__ - Step 109818: {'lr': 8.55615670446766e-05, 'samples': 21085056, 'steps': 109817, 'loss/train': 1.398112416267395} 08/31/2021 09:08:59 - INFO - __main__ - Step 109819: {'lr': 8.555756986649099e-05, 'samples': 21085248, 'steps': 109818, 'loss/train': 0.6735877990722656} 08/31/2021 09:09:00 - INFO - __main__ - Step 109820: {'lr': 8.555357276240062e-05, 'samples': 21085440, 'steps': 109819, 'loss/train': 1.922004222869873} 08/31/2021 09:09:01 - INFO - __main__ - Step 109821: {'lr': 8.554957573240727e-05, 'samples': 21085632, 'steps': 109820, 'loss/train': 0.4022069275379181} 08/31/2021 09:09:02 - INFO - __main__ - Step 109822: {'lr': 8.554557877651281e-05, 'samples': 21085824, 'steps': 109821, 'loss/train': 1.2668921947479248} 08/31/2021 09:09:02 - INFO - __main__ - Step 109823: {'lr': 8.554158189471889e-05, 'samples': 21086016, 'steps': 109822, 'loss/train': 1.049360752105713} 08/31/2021 09:09:02 - INFO - __main__ - Step 109824: {'lr': 8.553758508702742e-05, 'samples': 21086208, 'steps': 109823, 'loss/train': 0.9653425216674805} 08/31/2021 09:09:03 - INFO - __main__ - Step 109825: {'lr': 8.553358835344015e-05, 'samples': 21086400, 'steps': 109824, 'loss/train': 1.377073884010315} 08/31/2021 09:09:03 - INFO - __main__ - Step 109826: {'lr': 8.552959169395894e-05, 'samples': 21086592, 'steps': 109825, 'loss/train': 1.0745652914047241} 08/31/2021 09:09:05 - INFO - __main__ - Step 109827: {'lr': 8.552559510858552e-05, 'samples': 21086784, 'steps': 109826, 'loss/train': 1.570961356163025} 08/31/2021 09:09:05 - INFO - __main__ - Step 109828: {'lr': 8.552159859732176e-05, 'samples': 21086976, 'steps': 109827, 'loss/train': 1.2219434976577759} 08/31/2021 09:09:05 - INFO - __main__ - Step 109829: {'lr': 8.551760216016941e-05, 'samples': 21087168, 'steps': 109828, 'loss/train': 1.1909496784210205} 08/31/2021 09:09:06 - INFO - __main__ - Step 109830: {'lr': 8.551360579713027e-05, 'samples': 21087360, 'steps': 109829, 'loss/train': 1.0037480592727661} 08/31/2021 09:09:06 - INFO - __main__ - Step 109831: {'lr': 8.550960950820619e-05, 'samples': 21087552, 'steps': 109830, 'loss/train': 0.7168065905570984} 08/31/2021 09:09:08 - INFO - __main__ - Step 109832: {'lr': 8.550561329339895e-05, 'samples': 21087744, 'steps': 109831, 'loss/train': 0.37678325176239014} 08/31/2021 09:09:08 - INFO - __main__ - Step 109833: {'lr': 8.550161715271032e-05, 'samples': 21087936, 'steps': 109832, 'loss/train': 1.0464938879013062} 08/31/2021 09:09:08 - INFO - __main__ - Step 109834: {'lr': 8.549762108614215e-05, 'samples': 21088128, 'steps': 109833, 'loss/train': 1.9310966730117798} 08/31/2021 09:09:09 - INFO - __main__ - Step 109835: {'lr': 8.549362509369626e-05, 'samples': 21088320, 'steps': 109834, 'loss/train': 0.6427769064903259} 08/31/2021 09:09:09 - INFO - __main__ - Step 109836: {'lr': 8.548962917537434e-05, 'samples': 21088512, 'steps': 109835, 'loss/train': 0.9834378957748413} 08/31/2021 09:09:11 - INFO - __main__ - Step 109837: {'lr': 8.548563333117826e-05, 'samples': 21088704, 'steps': 109836, 'loss/train': 1.3504571914672852} 08/31/2021 09:09:11 - INFO - __main__ - Step 109838: {'lr': 8.548163756110983e-05, 'samples': 21088896, 'steps': 109837, 'loss/train': 0.02102726511657238} 08/31/2021 09:09:11 - INFO - __main__ - Step 109839: {'lr': 8.547764186517079e-05, 'samples': 21089088, 'steps': 109838, 'loss/train': 1.2187410593032837} 08/31/2021 09:09:12 - INFO - __main__ - Step 109840: {'lr': 8.547364624336301e-05, 'samples': 21089280, 'steps': 109839, 'loss/train': 0.6295871734619141} 08/31/2021 09:09:12 - INFO - __main__ - Step 109841: {'lr': 8.546965069568827e-05, 'samples': 21089472, 'steps': 109840, 'loss/train': 1.229539155960083} 08/31/2021 09:09:14 - INFO - __main__ - Step 109842: {'lr': 8.546565522214838e-05, 'samples': 21089664, 'steps': 109841, 'loss/train': 0.3292807340621948} 08/31/2021 09:09:14 - INFO - __main__ - Step 109843: {'lr': 8.54616598227451e-05, 'samples': 21089856, 'steps': 109842, 'loss/train': 1.3329845666885376} 08/31/2021 09:09:14 - INFO - __main__ - Step 109844: {'lr': 8.545766449748027e-05, 'samples': 21090048, 'steps': 109843, 'loss/train': 0.8427820205688477} 08/31/2021 09:09:15 - INFO - __main__ - Step 109845: {'lr': 8.545366924635566e-05, 'samples': 21090240, 'steps': 109844, 'loss/train': 0.41490328311920166} 08/31/2021 09:09:15 - INFO - __main__ - Step 109846: {'lr': 8.544967406937313e-05, 'samples': 21090432, 'steps': 109845, 'loss/train': 1.322770357131958} 08/31/2021 09:09:17 - INFO - __main__ - Step 109847: {'lr': 8.544567896653441e-05, 'samples': 21090624, 'steps': 109846, 'loss/train': 1.148931622505188} 08/31/2021 09:09:17 - INFO - __main__ - Step 109848: {'lr': 8.544168393784132e-05, 'samples': 21090816, 'steps': 109847, 'loss/train': 0.9805880188941956} 08/31/2021 09:09:18 - INFO - __main__ - Step 109849: {'lr': 8.543768898329577e-05, 'samples': 21091008, 'steps': 109848, 'loss/train': 1.1313412189483643} 08/31/2021 09:09:18 - INFO - __main__ - Step 109850: {'lr': 8.543369410289936e-05, 'samples': 21091200, 'steps': 109849, 'loss/train': 0.9369718432426453} 08/31/2021 09:09:18 - INFO - __main__ - Step 109851: {'lr': 8.542969929665397e-05, 'samples': 21091392, 'steps': 109850, 'loss/train': 0.6342496871948242} 08/31/2021 09:09:20 - INFO - __main__ - Step 109852: {'lr': 8.542570456456144e-05, 'samples': 21091584, 'steps': 109851, 'loss/train': 1.3907465934753418} 08/31/2021 09:09:21 - INFO - __main__ - Step 109853: {'lr': 8.542170990662357e-05, 'samples': 21091776, 'steps': 109852, 'loss/train': 0.6286081075668335} 08/31/2021 09:09:21 - INFO - __main__ - Step 109854: {'lr': 8.541771532284212e-05, 'samples': 21091968, 'steps': 109853, 'loss/train': 1.0687077045440674} 08/31/2021 09:09:22 - INFO - __main__ - Step 109855: {'lr': 8.541372081321888e-05, 'samples': 21092160, 'steps': 109854, 'loss/train': 1.3269059658050537} 08/31/2021 09:09:22 - INFO - __main__ - Step 109856: {'lr': 8.540972637775571e-05, 'samples': 21092352, 'steps': 109855, 'loss/train': 1.3541911840438843} 08/31/2021 09:09:24 - INFO - __main__ - Step 109857: {'lr': 8.540573201645438e-05, 'samples': 21092544, 'steps': 109856, 'loss/train': 1.0527607202529907} 08/31/2021 09:09:24 - INFO - __main__ - Step 109858: {'lr': 8.540173772931667e-05, 'samples': 21092736, 'steps': 109857, 'loss/train': 1.1060220003128052} 08/31/2021 09:09:24 - INFO - __main__ - Step 109859: {'lr': 8.539774351634441e-05, 'samples': 21092928, 'steps': 109858, 'loss/train': 0.19144529104232788} 08/31/2021 09:09:25 - INFO - __main__ - Step 109860: {'lr': 8.539374937753938e-05, 'samples': 21093120, 'steps': 109859, 'loss/train': 0.34459078311920166} 08/31/2021 09:09:25 - INFO - __main__ - Step 109861: {'lr': 8.538975531290339e-05, 'samples': 21093312, 'steps': 109860, 'loss/train': 0.4894702434539795} 08/31/2021 09:09:27 - INFO - __main__ - Step 109862: {'lr': 8.53857613224383e-05, 'samples': 21093504, 'steps': 109861, 'loss/train': 0.02525702677667141} 08/31/2021 09:09:27 - INFO - __main__ - Step 109863: {'lr': 8.538176740614578e-05, 'samples': 21093696, 'steps': 109862, 'loss/train': 1.1893113851547241} 08/31/2021 09:09:27 - INFO - __main__ - Step 109864: {'lr': 8.53777735640277e-05, 'samples': 21093888, 'steps': 109863, 'loss/train': 1.3427609205245972} 08/31/2021 09:09:28 - INFO - __main__ - Step 109865: {'lr': 8.537377979608586e-05, 'samples': 21094080, 'steps': 109864, 'loss/train': 1.0303055047988892} 08/31/2021 09:09:28 - INFO - __main__ - Step 109866: {'lr': 8.536978610232205e-05, 'samples': 21094272, 'steps': 109865, 'loss/train': 1.9052209854125977} 08/31/2021 09:09:29 - INFO - __main__ - Step 109867: {'lr': 8.536579248273804e-05, 'samples': 21094464, 'steps': 109866, 'loss/train': 1.7815016508102417} 08/31/2021 09:09:30 - INFO - __main__ - Step 109868: {'lr': 8.53617989373357e-05, 'samples': 21094656, 'steps': 109867, 'loss/train': 1.0073314905166626} 08/31/2021 09:09:31 - INFO - __main__ - Step 109869: {'lr': 8.53578054661168e-05, 'samples': 21094848, 'steps': 109868, 'loss/train': 0.7034009695053101} 08/31/2021 09:09:31 - INFO - __main__ - Step 109870: {'lr': 8.53538120690831e-05, 'samples': 21095040, 'steps': 109869, 'loss/train': 0.8843583464622498} 08/31/2021 09:09:31 - INFO - __main__ - Step 109871: {'lr': 8.534981874623646e-05, 'samples': 21095232, 'steps': 109870, 'loss/train': 1.0113227367401123} 08/31/2021 09:09:32 - INFO - __main__ - Step 109872: {'lr': 8.534582549757864e-05, 'samples': 21095424, 'steps': 109871, 'loss/train': 0.08934256434440613} 08/31/2021 09:09:33 - INFO - __main__ - Step 109873: {'lr': 8.534183232311143e-05, 'samples': 21095616, 'steps': 109872, 'loss/train': 0.3058048188686371} 08/31/2021 09:09:34 - INFO - __main__ - Step 109874: {'lr': 8.533783922283669e-05, 'samples': 21095808, 'steps': 109873, 'loss/train': 0.6903607845306396} 08/31/2021 09:09:34 - INFO - __main__ - Step 109875: {'lr': 8.533384619675616e-05, 'samples': 21096000, 'steps': 109874, 'loss/train': 0.7589457035064697} 08/31/2021 09:09:34 - INFO - __main__ - Step 109876: {'lr': 8.532985324487173e-05, 'samples': 21096192, 'steps': 109875, 'loss/train': 1.2660199403762817} 08/31/2021 09:09:35 - INFO - __main__ - Step 109877: {'lr': 8.532586036718503e-05, 'samples': 21096384, 'steps': 109876, 'loss/train': 0.043455906212329865} 08/31/2021 09:09:36 - INFO - __main__ - Step 109878: {'lr': 8.5321867563698e-05, 'samples': 21096576, 'steps': 109877, 'loss/train': 1.450624942779541} 08/31/2021 09:09:37 - INFO - __main__ - Step 109879: {'lr': 8.531787483441236e-05, 'samples': 21096768, 'steps': 109878, 'loss/train': 0.023433391004800797} 08/31/2021 09:09:37 - INFO - __main__ - Step 109880: {'lr': 8.531388217932998e-05, 'samples': 21096960, 'steps': 109879, 'loss/train': 1.152266263961792} 08/31/2021 09:09:38 - INFO - __main__ - Step 109881: {'lr': 8.53098895984526e-05, 'samples': 21097152, 'steps': 109880, 'loss/train': 2.696117877960205} 08/31/2021 09:09:38 - INFO - __main__ - Step 109882: {'lr': 8.530589709178204e-05, 'samples': 21097344, 'steps': 109881, 'loss/train': 2.6451690196990967} 08/31/2021 09:09:38 - INFO - __main__ - Step 109883: {'lr': 8.530190465932011e-05, 'samples': 21097536, 'steps': 109882, 'loss/train': 0.8275425434112549} 08/31/2021 09:09:40 - INFO - __main__ - Step 109884: {'lr': 8.529791230106859e-05, 'samples': 21097728, 'steps': 109883, 'loss/train': 1.1984866857528687} 08/31/2021 09:09:40 - INFO - __main__ - Step 109885: {'lr': 8.529392001702929e-05, 'samples': 21097920, 'steps': 109884, 'loss/train': 1.3544831275939941} 08/31/2021 09:09:41 - INFO - __main__ - Step 109886: {'lr': 8.528992780720402e-05, 'samples': 21098112, 'steps': 109885, 'loss/train': 1.1969565153121948} 08/31/2021 09:09:41 - INFO - __main__ - Step 109887: {'lr': 8.528593567159456e-05, 'samples': 21098304, 'steps': 109886, 'loss/train': 0.49327778816223145} 08/31/2021 09:09:41 - INFO - __main__ - Step 109888: {'lr': 8.528194361020272e-05, 'samples': 21098496, 'steps': 109887, 'loss/train': 0.7373438477516174} 08/31/2021 09:09:43 - INFO - __main__ - Step 109889: {'lr': 8.527795162303037e-05, 'samples': 21098688, 'steps': 109888, 'loss/train': 1.5474860668182373} 08/31/2021 09:09:44 - INFO - __main__ - Step 109890: {'lr': 8.527395971007914e-05, 'samples': 21098880, 'steps': 109889, 'loss/train': 1.437390685081482} 08/31/2021 09:09:44 - INFO - __main__ - Step 109891: {'lr': 8.526996787135094e-05, 'samples': 21099072, 'steps': 109890, 'loss/train': 0.5741513967514038} 08/31/2021 09:09:44 - INFO - __main__ - Step 109892: {'lr': 8.526597610684755e-05, 'samples': 21099264, 'steps': 109891, 'loss/train': 0.6059377193450928} 08/31/2021 09:09:45 - INFO - __main__ - Step 109893: {'lr': 8.526198441657077e-05, 'samples': 21099456, 'steps': 109892, 'loss/train': 0.5765573978424072} 08/31/2021 09:09:46 - INFO - __main__ - Step 109894: {'lr': 8.52579928005224e-05, 'samples': 21099648, 'steps': 109893, 'loss/train': 1.1267826557159424} 08/31/2021 09:09:47 - INFO - __main__ - Step 109895: {'lr': 8.525400125870422e-05, 'samples': 21099840, 'steps': 109894, 'loss/train': 1.1753194332122803} 08/31/2021 09:09:47 - INFO - __main__ - Step 109896: {'lr': 8.525000979111806e-05, 'samples': 21100032, 'steps': 109895, 'loss/train': 1.3252224922180176} 08/31/2021 09:09:47 - INFO - __main__ - Step 109897: {'lr': 8.52460183977657e-05, 'samples': 21100224, 'steps': 109896, 'loss/train': 0.13672927021980286} 08/31/2021 09:09:48 - INFO - __main__ - Step 109898: {'lr': 8.524202707864892e-05, 'samples': 21100416, 'steps': 109897, 'loss/train': 1.357495665550232} 08/31/2021 09:09:49 - INFO - __main__ - Step 109899: {'lr': 8.523803583376957e-05, 'samples': 21100608, 'steps': 109898, 'loss/train': 1.7312361001968384} 08/31/2021 09:09:50 - INFO - __main__ - Step 109900: {'lr': 8.523404466312951e-05, 'samples': 21100800, 'steps': 109899, 'loss/train': 0.7071691155433655} 08/31/2021 09:09:50 - INFO - __main__ - Step 109901: {'lr': 8.523005356673032e-05, 'samples': 21100992, 'steps': 109900, 'loss/train': 1.0591192245483398} 08/31/2021 09:09:50 - INFO - __main__ - Step 109902: {'lr': 8.522606254457396e-05, 'samples': 21101184, 'steps': 109901, 'loss/train': 0.6031057238578796} 08/31/2021 09:09:51 - INFO - __main__ - Step 109903: {'lr': 8.522207159666217e-05, 'samples': 21101376, 'steps': 109902, 'loss/train': 0.9527881741523743} 08/31/2021 09:09:51 - INFO - __main__ - Step 109904: {'lr': 8.52180807229968e-05, 'samples': 21101568, 'steps': 109903, 'loss/train': 1.0424758195877075} 08/31/2021 09:09:53 - INFO - __main__ - Step 109905: {'lr': 8.52140899235796e-05, 'samples': 21101760, 'steps': 109904, 'loss/train': 0.8658561706542969} 08/31/2021 09:09:54 - INFO - __main__ - Step 109906: {'lr': 8.521009919841242e-05, 'samples': 21101952, 'steps': 109905, 'loss/train': 1.4605917930603027} 08/31/2021 09:09:54 - INFO - __main__ - Step 109907: {'lr': 8.520610854749697e-05, 'samples': 21102144, 'steps': 109906, 'loss/train': 1.3840112686157227} 08/31/2021 09:09:54 - INFO - __main__ - Step 109908: {'lr': 8.520211797083516e-05, 'samples': 21102336, 'steps': 109907, 'loss/train': 0.6908459067344666} 08/31/2021 09:09:55 - INFO - __main__ - Step 109909: {'lr': 8.51981274684287e-05, 'samples': 21102528, 'steps': 109908, 'loss/train': 1.2760732173919678} 08/31/2021 09:09:56 - INFO - __main__ - Step 109910: {'lr': 8.519413704027942e-05, 'samples': 21102720, 'steps': 109909, 'loss/train': 0.20908814668655396} 08/31/2021 09:09:57 - INFO - __main__ - Step 109911: {'lr': 8.519014668638922e-05, 'samples': 21102912, 'steps': 109910, 'loss/train': 1.2565726041793823} 08/31/2021 09:09:57 - INFO - __main__ - Step 109912: {'lr': 8.51861564067597e-05, 'samples': 21103104, 'steps': 109911, 'loss/train': 1.027438998222351} 08/31/2021 09:09:57 - INFO - __main__ - Step 109913: {'lr': 8.518216620139273e-05, 'samples': 21103296, 'steps': 109912, 'loss/train': 1.1367361545562744} 08/31/2021 09:09:58 - INFO - __main__ - Step 109914: {'lr': 8.517817607029019e-05, 'samples': 21103488, 'steps': 109913, 'loss/train': 1.1023738384246826} 08/31/2021 09:09:59 - INFO - __main__ - Step 109915: {'lr': 8.517418601345378e-05, 'samples': 21103680, 'steps': 109914, 'loss/train': 0.7706219553947449} 08/31/2021 09:10:00 - INFO - __main__ - Step 109916: {'lr': 8.517019603088536e-05, 'samples': 21103872, 'steps': 109915, 'loss/train': 1.3841655254364014} 08/31/2021 09:10:00 - INFO - __main__ - Step 109917: {'lr': 8.516620612258668e-05, 'samples': 21104064, 'steps': 109916, 'loss/train': 0.26047182083129883} 08/31/2021 09:10:00 - INFO - __main__ - Step 109918: {'lr': 8.516221628855961e-05, 'samples': 21104256, 'steps': 109917, 'loss/train': 0.8528114557266235} 08/31/2021 09:10:01 - INFO - __main__ - Step 109919: {'lr': 8.515822652880586e-05, 'samples': 21104448, 'steps': 109918, 'loss/train': 1.2234007120132446} 08/31/2021 09:10:02 - INFO - __main__ - Step 109920: {'lr': 8.515423684332726e-05, 'samples': 21104640, 'steps': 109919, 'loss/train': 1.1658132076263428} 08/31/2021 09:10:02 - INFO - __main__ - Step 109921: {'lr': 8.515024723212566e-05, 'samples': 21104832, 'steps': 109920, 'loss/train': 0.9815484285354614} 08/31/2021 09:10:03 - INFO - __main__ - Step 109922: {'lr': 8.514625769520288e-05, 'samples': 21105024, 'steps': 109921, 'loss/train': 1.2529056072235107} 08/31/2021 09:10:03 - INFO - __main__ - Step 109923: {'lr': 8.514226823256054e-05, 'samples': 21105216, 'steps': 109922, 'loss/train': 1.0678001642227173} 08/31/2021 09:10:03 - INFO - __main__ - Step 109924: {'lr': 8.513827884420059e-05, 'samples': 21105408, 'steps': 109923, 'loss/train': 1.5729665756225586} 08/31/2021 09:10:05 - INFO - __main__ - Step 109925: {'lr': 8.513428953012478e-05, 'samples': 21105600, 'steps': 109924, 'loss/train': 0.9628756046295166} 08/31/2021 09:10:06 - INFO - __main__ - Step 109926: {'lr': 8.513030029033492e-05, 'samples': 21105792, 'steps': 109925, 'loss/train': 1.1761589050292969} 08/31/2021 09:10:06 - INFO - __main__ - Step 109927: {'lr': 8.512631112483276e-05, 'samples': 21105984, 'steps': 109926, 'loss/train': 1.3896459341049194} 08/31/2021 09:10:06 - INFO - __main__ - Step 109928: {'lr': 8.512232203362019e-05, 'samples': 21106176, 'steps': 109927, 'loss/train': 0.7906524538993835} 08/31/2021 09:10:07 - INFO - __main__ - Step 109929: {'lr': 8.511833301669894e-05, 'samples': 21106368, 'steps': 109928, 'loss/train': 0.19957077503204346} 08/31/2021 09:10:08 - INFO - __main__ - Step 109930: {'lr': 8.511434407407082e-05, 'samples': 21106560, 'steps': 109929, 'loss/train': 1.149919033050537} 08/31/2021 09:10:08 - INFO - __main__ - Step 109931: {'lr': 8.511035520573764e-05, 'samples': 21106752, 'steps': 109930, 'loss/train': 1.2644321918487549} 08/31/2021 09:10:09 - INFO - __main__ - Step 109932: {'lr': 8.510636641170119e-05, 'samples': 21106944, 'steps': 109931, 'loss/train': 0.7757483124732971} 08/31/2021 09:10:09 - INFO - __main__ - Step 109933: {'lr': 8.510237769196333e-05, 'samples': 21107136, 'steps': 109932, 'loss/train': 1.6110985279083252} 08/31/2021 09:10:09 - INFO - __main__ - Step 109934: {'lr': 8.509838904652573e-05, 'samples': 21107328, 'steps': 109933, 'loss/train': 0.6941070556640625} 08/31/2021 09:10:11 - INFO - __main__ - Step 109935: {'lr': 8.509440047539024e-05, 'samples': 21107520, 'steps': 109934, 'loss/train': 1.1199474334716797} 08/31/2021 09:10:11 - INFO - __main__ - Step 109936: {'lr': 8.509041197855869e-05, 'samples': 21107712, 'steps': 109935, 'loss/train': 1.5752661228179932} 08/31/2021 09:10:12 - INFO - __main__ - Step 109937: {'lr': 8.508642355603285e-05, 'samples': 21107904, 'steps': 109936, 'loss/train': 1.1601529121398926} 08/31/2021 09:10:12 - INFO - __main__ - Step 109938: {'lr': 8.50824352078145e-05, 'samples': 21108096, 'steps': 109937, 'loss/train': 1.2364513874053955} 08/31/2021 09:10:12 - INFO - __main__ - Step 109939: {'lr': 8.507844693390548e-05, 'samples': 21108288, 'steps': 109938, 'loss/train': 0.7962949275970459} 08/31/2021 09:10:14 - INFO - __main__ - Step 109940: {'lr': 8.507445873430756e-05, 'samples': 21108480, 'steps': 109939, 'loss/train': 0.9830105304718018} 08/31/2021 09:10:14 - INFO - __main__ - Step 109941: {'lr': 8.507047060902253e-05, 'samples': 21108672, 'steps': 109940, 'loss/train': 1.385492205619812} 08/31/2021 09:10:15 - INFO - __main__ - Step 109942: {'lr': 8.506648255805225e-05, 'samples': 21108864, 'steps': 109941, 'loss/train': 0.7992376685142517} 08/31/2021 09:10:15 - INFO - __main__ - Step 109943: {'lr': 8.506249458139843e-05, 'samples': 21109056, 'steps': 109942, 'loss/train': 1.0738672018051147} 08/31/2021 09:10:15 - INFO - __main__ - Step 109944: {'lr': 8.505850667906298e-05, 'samples': 21109248, 'steps': 109943, 'loss/train': 1.2162435054779053} 08/31/2021 09:10:17 - INFO - __main__ - Step 109945: {'lr': 8.505451885104756e-05, 'samples': 21109440, 'steps': 109944, 'loss/train': 1.0378457307815552} 08/31/2021 09:10:17 - INFO - __main__ - Step 109946: {'lr': 8.5050531097354e-05, 'samples': 21109632, 'steps': 109945, 'loss/train': 0.4197849631309509} 08/31/2021 09:10:18 - INFO - __main__ - Step 109947: {'lr': 8.504654341798415e-05, 'samples': 21109824, 'steps': 109946, 'loss/train': 1.2917345762252808} 08/31/2021 09:10:18 - INFO - __main__ - Step 109948: {'lr': 8.50425558129398e-05, 'samples': 21110016, 'steps': 109947, 'loss/train': 0.5525599718093872} 08/31/2021 09:10:18 - INFO - __main__ - Step 109949: {'lr': 8.50385682822227e-05, 'samples': 21110208, 'steps': 109948, 'loss/train': 1.5162017345428467} 08/31/2021 09:10:20 - INFO - __main__ - Step 109950: {'lr': 8.503458082583468e-05, 'samples': 21110400, 'steps': 109949, 'loss/train': 1.0095385313034058} 08/31/2021 09:10:21 - INFO - __main__ - Step 109951: {'lr': 8.503059344377754e-05, 'samples': 21110592, 'steps': 109950, 'loss/train': 1.1384371519088745} 08/31/2021 09:10:21 - INFO - __main__ - Step 109952: {'lr': 8.502660613605303e-05, 'samples': 21110784, 'steps': 109951, 'loss/train': 0.8713759779930115} 08/31/2021 09:10:21 - INFO - __main__ - Step 109953: {'lr': 8.502261890266302e-05, 'samples': 21110976, 'steps': 109952, 'loss/train': 0.37849465012550354} 08/31/2021 09:10:22 - INFO - __main__ - Step 109954: {'lr': 8.501863174360927e-05, 'samples': 21111168, 'steps': 109953, 'loss/train': 1.3332862854003906} 08/31/2021 09:10:23 - INFO - __main__ - Step 109955: {'lr': 8.501464465889358e-05, 'samples': 21111360, 'steps': 109954, 'loss/train': 0.03203779086470604} 08/31/2021 09:10:24 - INFO - __main__ - Step 109956: {'lr': 8.501065764851784e-05, 'samples': 21111552, 'steps': 109955, 'loss/train': 0.8866919279098511} 08/31/2021 09:10:24 - INFO - __main__ - Step 109957: {'lr': 8.500667071248366e-05, 'samples': 21111744, 'steps': 109956, 'loss/train': 1.3957953453063965} 08/31/2021 09:10:24 - INFO - __main__ - Step 109958: {'lr': 8.500268385079294e-05, 'samples': 21111936, 'steps': 109957, 'loss/train': 0.7885448932647705} 08/31/2021 09:10:25 - INFO - __main__ - Step 109959: {'lr': 8.499869706344742e-05, 'samples': 21112128, 'steps': 109958, 'loss/train': 0.9020761251449585} 08/31/2021 09:10:25 - INFO - __main__ - Step 109960: {'lr': 8.499471035044897e-05, 'samples': 21112320, 'steps': 109959, 'loss/train': 1.2920533418655396} 08/31/2021 09:10:27 - INFO - __main__ - Step 109961: {'lr': 8.499072371179936e-05, 'samples': 21112512, 'steps': 109960, 'loss/train': 1.1421136856079102} 08/31/2021 09:10:28 - INFO - __main__ - Step 109962: {'lr': 8.498673714750038e-05, 'samples': 21112704, 'steps': 109961, 'loss/train': 0.9438742995262146} 08/31/2021 09:10:28 - INFO - __main__ - Step 109963: {'lr': 8.498275065755384e-05, 'samples': 21112896, 'steps': 109962, 'loss/train': 1.3305336236953735} 08/31/2021 09:10:28 - INFO - __main__ - Step 109964: {'lr': 8.497876424196152e-05, 'samples': 21113088, 'steps': 109963, 'loss/train': 1.4787522554397583} 08/31/2021 09:10:29 - INFO - __main__ - Step 109965: {'lr': 8.497477790072522e-05, 'samples': 21113280, 'steps': 109964, 'loss/train': 1.1269872188568115} 08/31/2021 09:10:30 - INFO - __main__ - Step 109966: {'lr': 8.497079163384674e-05, 'samples': 21113472, 'steps': 109965, 'loss/train': 1.1434749364852905} 08/31/2021 09:10:31 - INFO - __main__ - Step 109967: {'lr': 8.496680544132788e-05, 'samples': 21113664, 'steps': 109966, 'loss/train': 1.0752886533737183} 08/31/2021 09:10:31 - INFO - __main__ - Step 109968: {'lr': 8.49628193231704e-05, 'samples': 21113856, 'steps': 109967, 'loss/train': 0.5566545724868774} 08/31/2021 09:10:31 - INFO - __main__ - Step 109969: {'lr': 8.495883327937615e-05, 'samples': 21114048, 'steps': 109968, 'loss/train': 0.20824375748634338} 08/31/2021 09:10:32 - INFO - __main__ - Step 109970: {'lr': 8.495484730994699e-05, 'samples': 21114240, 'steps': 109969, 'loss/train': 1.2667338848114014} 08/31/2021 09:10:33 - INFO - __main__ - Step 109971: {'lr': 8.495086141488454e-05, 'samples': 21114432, 'steps': 109970, 'loss/train': 0.24979406595230103} 08/31/2021 09:10:34 - INFO - __main__ - Step 109972: {'lr': 8.494687559419071e-05, 'samples': 21114624, 'steps': 109971, 'loss/train': 1.5590016841888428} 08/31/2021 09:10:34 - INFO - __main__ - Step 109973: {'lr': 8.494288984786724e-05, 'samples': 21114816, 'steps': 109972, 'loss/train': 1.5709680318832397} 08/31/2021 09:10:34 - INFO - __main__ - Step 109974: {'lr': 8.493890417591596e-05, 'samples': 21115008, 'steps': 109973, 'loss/train': 0.767064094543457} 08/31/2021 09:10:35 - INFO - __main__ - Step 109975: {'lr': 8.493491857833865e-05, 'samples': 21115200, 'steps': 109974, 'loss/train': 1.3023358583450317} 08/31/2021 09:10:36 - INFO - __main__ - Step 109976: {'lr': 8.493093305513716e-05, 'samples': 21115392, 'steps': 109975, 'loss/train': 1.3884164094924927} 08/31/2021 09:10:37 - INFO - __main__ - Step 109977: {'lr': 8.49269476063132e-05, 'samples': 21115584, 'steps': 109976, 'loss/train': 1.6927579641342163} 08/31/2021 09:10:37 - INFO - __main__ - Step 109978: {'lr': 8.492296223186866e-05, 'samples': 21115776, 'steps': 109977, 'loss/train': 1.3221369981765747} 08/31/2021 09:10:37 - INFO - __main__ - Step 109979: {'lr': 8.491897693180523e-05, 'samples': 21115968, 'steps': 109978, 'loss/train': 0.7912372350692749} 08/31/2021 09:10:38 - INFO - __main__ - Step 109980: {'lr': 8.491499170612479e-05, 'samples': 21116160, 'steps': 109979, 'loss/train': 0.5894321799278259} 08/31/2021 09:10:39 - INFO - __main__ - Step 109981: {'lr': 8.491100655482911e-05, 'samples': 21116352, 'steps': 109980, 'loss/train': 0.8445884585380554} 08/31/2021 09:10:40 - INFO - __main__ - Step 109982: {'lr': 8.490702147791998e-05, 'samples': 21116544, 'steps': 109981, 'loss/train': 1.6096864938735962} 08/31/2021 09:10:40 - INFO - __main__ - Step 109983: {'lr': 8.490303647539929e-05, 'samples': 21116736, 'steps': 109982, 'loss/train': 1.3337982892990112} 08/31/2021 09:10:41 - INFO - __main__ - Step 109984: {'lr': 8.489905154726865e-05, 'samples': 21116928, 'steps': 109983, 'loss/train': 1.052199363708496} 08/31/2021 09:10:41 - INFO - __main__ - Step 109985: {'lr': 8.489506669352995e-05, 'samples': 21117120, 'steps': 109984, 'loss/train': 0.8860517144203186} 08/31/2021 09:10:42 - INFO - __main__ - Step 109986: {'lr': 8.489108191418499e-05, 'samples': 21117312, 'steps': 109985, 'loss/train': 0.05170169472694397} 08/31/2021 09:10:43 - INFO - __main__ - Step 109987: {'lr': 8.488709720923554e-05, 'samples': 21117504, 'steps': 109986, 'loss/train': 0.08050922304391861} 08/31/2021 09:10:43 - INFO - __main__ - Step 109988: {'lr': 8.488311257868344e-05, 'samples': 21117696, 'steps': 109987, 'loss/train': 1.444540023803711} 08/31/2021 09:10:43 - INFO - __main__ - Step 109989: {'lr': 8.487912802253045e-05, 'samples': 21117888, 'steps': 109988, 'loss/train': 1.5638526678085327} 08/31/2021 09:10:44 - INFO - __main__ - Step 109990: {'lr': 8.487514354077839e-05, 'samples': 21118080, 'steps': 109989, 'loss/train': 0.9307273626327515} 08/31/2021 09:10:44 - INFO - __main__ - Step 109991: {'lr': 8.487115913342902e-05, 'samples': 21118272, 'steps': 109990, 'loss/train': 0.998885989189148} 08/31/2021 09:10:46 - INFO - __main__ - Step 109992: {'lr': 8.48671748004842e-05, 'samples': 21118464, 'steps': 109991, 'loss/train': 1.1800771951675415} 08/31/2021 09:10:46 - INFO - __main__ - Step 109993: {'lr': 8.486319054194563e-05, 'samples': 21118656, 'steps': 109992, 'loss/train': 1.025713562965393} 08/31/2021 09:10:47 - INFO - __main__ - Step 109994: {'lr': 8.485920635781519e-05, 'samples': 21118848, 'steps': 109993, 'loss/train': 1.5308834314346313} 08/31/2021 09:10:47 - INFO - __main__ - Step 109995: {'lr': 8.485522224809464e-05, 'samples': 21119040, 'steps': 109994, 'loss/train': 1.1083987951278687} 08/31/2021 09:10:47 - INFO - __main__ - Step 109996: {'lr': 8.485123821278579e-05, 'samples': 21119232, 'steps': 109995, 'loss/train': 1.776496171951294} 08/31/2021 09:10:49 - INFO - __main__ - Step 109997: {'lr': 8.484725425189047e-05, 'samples': 21119424, 'steps': 109996, 'loss/train': 1.230336308479309} 08/31/2021 09:10:49 - INFO - __main__ - Step 109998: {'lr': 8.484327036541037e-05, 'samples': 21119616, 'steps': 109997, 'loss/train': 2.0884745121002197} 08/31/2021 09:10:50 - INFO - __main__ - Step 109999: {'lr': 8.483928655334733e-05, 'samples': 21119808, 'steps': 109998, 'loss/train': 0.03303946554660797} 08/31/2021 09:10:50 - INFO - __main__ - Step 110000: {'lr': 8.483530281570317e-05, 'samples': 21120000, 'steps': 109999, 'loss/train': 0.9056457877159119} 08/31/2021 09:10:51 - INFO - __main__ - Step 110001: {'lr': 8.483131915247969e-05, 'samples': 21120192, 'steps': 110000, 'loss/train': 1.7326221466064453} 08/31/2021 09:10:52 - INFO - __main__ - Step 110002: {'lr': 8.482733556367864e-05, 'samples': 21120384, 'steps': 110001, 'loss/train': 1.2785365581512451} 08/31/2021 09:10:53 - INFO - __main__ - Step 110003: {'lr': 8.482335204930186e-05, 'samples': 21120576, 'steps': 110002, 'loss/train': 0.3916466534137726} 08/31/2021 09:10:53 - INFO - __main__ - Step 110004: {'lr': 8.481936860935113e-05, 'samples': 21120768, 'steps': 110003, 'loss/train': 0.4166146516799927} 08/31/2021 09:10:53 - INFO - __main__ - Step 110005: {'lr': 8.481538524382823e-05, 'samples': 21120960, 'steps': 110004, 'loss/train': 1.1168535947799683} 08/31/2021 09:10:54 - INFO - __main__ - Step 110006: {'lr': 8.481140195273498e-05, 'samples': 21121152, 'steps': 110005, 'loss/train': 1.6427929401397705} 08/31/2021 09:10:54 - INFO - __main__ - Step 110007: {'lr': 8.480741873607318e-05, 'samples': 21121344, 'steps': 110006, 'loss/train': 0.6571260690689087} 08/31/2021 09:10:56 - INFO - __main__ - Step 110008: {'lr': 8.480343559384457e-05, 'samples': 21121536, 'steps': 110007, 'loss/train': 0.9616068601608276} 08/31/2021 09:10:56 - INFO - __main__ - Step 110009: {'lr': 8.479945252605101e-05, 'samples': 21121728, 'steps': 110008, 'loss/train': 1.9898887872695923} 08/31/2021 09:10:57 - INFO - __main__ - Step 110010: {'lr': 8.479546953269434e-05, 'samples': 21121920, 'steps': 110009, 'loss/train': 0.9225320816040039} 08/31/2021 09:10:57 - INFO - __main__ - Step 110011: {'lr': 8.479148661377619e-05, 'samples': 21122112, 'steps': 110010, 'loss/train': 1.3969815969467163} 08/31/2021 09:10:57 - INFO - __main__ - Step 110012: {'lr': 8.478750376929848e-05, 'samples': 21122304, 'steps': 110011, 'loss/train': 1.0398906469345093} 08/31/2021 09:10:59 - INFO - __main__ - Step 110013: {'lr': 8.478352099926293e-05, 'samples': 21122496, 'steps': 110012, 'loss/train': 0.8750824928283691} 08/31/2021 09:11:00 - INFO - __main__ - Step 110014: {'lr': 8.477953830367141e-05, 'samples': 21122688, 'steps': 110013, 'loss/train': 0.635531485080719} 08/31/2021 09:11:00 - INFO - __main__ - Step 110015: {'lr': 8.477555568252566e-05, 'samples': 21122880, 'steps': 110014, 'loss/train': 0.8362929821014404} 08/31/2021 09:11:01 - INFO - __main__ - Step 110016: {'lr': 8.477157313582751e-05, 'samples': 21123072, 'steps': 110015, 'loss/train': 1.2087479829788208} 08/31/2021 09:11:01 - INFO - __main__ - Step 110017: {'lr': 8.476759066357873e-05, 'samples': 21123264, 'steps': 110016, 'loss/train': 1.230894923210144} 08/31/2021 09:11:01 - INFO - __main__ - Step 110018: {'lr': 8.476360826578112e-05, 'samples': 21123456, 'steps': 110017, 'loss/train': 0.9860773682594299} 08/31/2021 09:11:03 - INFO - __main__ - Step 110019: {'lr': 8.475962594243647e-05, 'samples': 21123648, 'steps': 110018, 'loss/train': 0.8501462340354919} 08/31/2021 09:11:03 - INFO - __main__ - Step 110020: {'lr': 8.47556436935466e-05, 'samples': 21123840, 'steps': 110019, 'loss/train': 0.7941586375236511} 08/31/2021 09:11:04 - INFO - __main__ - Step 110021: {'lr': 8.47516615191133e-05, 'samples': 21124032, 'steps': 110020, 'loss/train': 0.1260433793067932} 08/31/2021 09:11:04 - INFO - __main__ - Step 110022: {'lr': 8.474767941913831e-05, 'samples': 21124224, 'steps': 110021, 'loss/train': 0.04611276835203171} 08/31/2021 09:11:04 - INFO - __main__ - Step 110023: {'lr': 8.474369739362359e-05, 'samples': 21124416, 'steps': 110022, 'loss/train': 1.062951683998108} 08/31/2021 09:11:06 - INFO - __main__ - Step 110024: {'lr': 8.47397154425707e-05, 'samples': 21124608, 'steps': 110023, 'loss/train': 0.7212101221084595} 08/31/2021 09:11:06 - INFO - __main__ - Step 110025: {'lr': 8.473573356598155e-05, 'samples': 21124800, 'steps': 110024, 'loss/train': 1.0310370922088623} 08/31/2021 09:11:07 - INFO - __main__ - Step 110026: {'lr': 8.473175176385795e-05, 'samples': 21124992, 'steps': 110025, 'loss/train': 1.2561113834381104} 08/31/2021 09:11:07 - INFO - __main__ - Step 110027: {'lr': 8.472777003620164e-05, 'samples': 21125184, 'steps': 110026, 'loss/train': 1.0078240633010864} 08/31/2021 09:11:07 - INFO - __main__ - Step 110028: {'lr': 8.472378838301445e-05, 'samples': 21125376, 'steps': 110027, 'loss/train': 0.06823182851076126} 08/31/2021 09:11:09 - INFO - __main__ - Step 110029: {'lr': 8.471980680429819e-05, 'samples': 21125568, 'steps': 110028, 'loss/train': 1.5299350023269653} 08/31/2021 09:11:10 - INFO - __main__ - Step 110030: {'lr': 8.471582530005462e-05, 'samples': 21125760, 'steps': 110029, 'loss/train': 0.9714974164962769} 08/31/2021 09:11:10 - INFO - __main__ - Step 110031: {'lr': 8.471184387028555e-05, 'samples': 21125952, 'steps': 110030, 'loss/train': 1.060984492301941} 08/31/2021 09:11:10 - INFO - __main__ - Step 110032: {'lr': 8.470786251499279e-05, 'samples': 21126144, 'steps': 110031, 'loss/train': 1.3073430061340332} 08/31/2021 09:11:11 - INFO - __main__ - Step 110033: {'lr': 8.470388123417811e-05, 'samples': 21126336, 'steps': 110032, 'loss/train': 1.4235610961914062} 08/31/2021 09:11:12 - INFO - __main__ - Step 110034: {'lr': 8.469990002784328e-05, 'samples': 21126528, 'steps': 110033, 'loss/train': 0.14139215648174286} 08/31/2021 09:11:12 - INFO - __main__ - Step 110035: {'lr': 8.469591889599016e-05, 'samples': 21126720, 'steps': 110034, 'loss/train': 1.4139997959136963} 08/31/2021 09:11:13 - INFO - __main__ - Step 110036: {'lr': 8.46919378386205e-05, 'samples': 21126912, 'steps': 110035, 'loss/train': 0.399928480386734} 08/31/2021 09:11:13 - INFO - __main__ - Step 110037: {'lr': 8.468795685573619e-05, 'samples': 21127104, 'steps': 110036, 'loss/train': 1.745129108428955} 08/31/2021 09:11:13 - INFO - __main__ - Step 110038: {'lr': 8.468397594733884e-05, 'samples': 21127296, 'steps': 110037, 'loss/train': 1.2242686748504639} 08/31/2021 09:11:15 - INFO - __main__ - Step 110039: {'lr': 8.467999511343033e-05, 'samples': 21127488, 'steps': 110038, 'loss/train': 0.8376353979110718} 08/31/2021 09:11:16 - INFO - __main__ - Step 110040: {'lr': 8.467601435401249e-05, 'samples': 21127680, 'steps': 110039, 'loss/train': 1.243795394897461} 08/31/2021 09:11:16 - INFO - __main__ - Step 110041: {'lr': 8.467203366908707e-05, 'samples': 21127872, 'steps': 110040, 'loss/train': 0.8519776463508606} 08/31/2021 09:11:16 - INFO - __main__ - Step 110042: {'lr': 8.466805305865588e-05, 'samples': 21128064, 'steps': 110041, 'loss/train': 1.5587773323059082} 08/31/2021 09:11:17 - INFO - __main__ - Step 110043: {'lr': 8.466407252272071e-05, 'samples': 21128256, 'steps': 110042, 'loss/train': 1.1586638689041138} 08/31/2021 09:11:17 - INFO - __main__ - Step 110044: {'lr': 8.466009206128337e-05, 'samples': 21128448, 'steps': 110043, 'loss/train': 0.5317493677139282} 08/31/2021 09:11:18 - INFO - __main__ - Step 110045: {'lr': 8.465611167434564e-05, 'samples': 21128640, 'steps': 110044, 'loss/train': 1.4396672248840332} 08/31/2021 09:11:19 - INFO - __main__ - Step 110046: {'lr': 8.465213136190931e-05, 'samples': 21128832, 'steps': 110045, 'loss/train': 1.387969732284546} 08/31/2021 09:11:19 - INFO - __main__ - Step 110047: {'lr': 8.464815112397617e-05, 'samples': 21129024, 'steps': 110046, 'loss/train': 1.0421569347381592} 08/31/2021 09:11:20 - INFO - __main__ - Step 110048: {'lr': 8.464417096054804e-05, 'samples': 21129216, 'steps': 110047, 'loss/train': 1.454148769378662} 08/31/2021 09:11:20 - INFO - __main__ - Step 110049: {'lr': 8.46401908716267e-05, 'samples': 21129408, 'steps': 110048, 'loss/train': 1.429330587387085} 08/31/2021 09:11:22 - INFO - __main__ - Step 110050: {'lr': 8.463621085721398e-05, 'samples': 21129600, 'steps': 110049, 'loss/train': 1.077307105064392} 08/31/2021 09:11:22 - INFO - __main__ - Step 110051: {'lr': 8.46322309173116e-05, 'samples': 21129792, 'steps': 110050, 'loss/train': 1.1202069520950317} 08/31/2021 09:11:22 - INFO - __main__ - Step 110052: {'lr': 8.462825105192135e-05, 'samples': 21129984, 'steps': 110051, 'loss/train': 0.5048642158508301} 08/31/2021 09:11:23 - INFO - __main__ - Step 110053: {'lr': 8.462427126104507e-05, 'samples': 21130176, 'steps': 110052, 'loss/train': 0.34865278005599976} 08/31/2021 09:11:23 - INFO - __main__ - Step 110054: {'lr': 8.462029154468454e-05, 'samples': 21130368, 'steps': 110053, 'loss/train': 2.0215795040130615} 08/31/2021 09:11:24 - INFO - __main__ - Step 110055: {'lr': 8.461631190284156e-05, 'samples': 21130560, 'steps': 110054, 'loss/train': 1.749150276184082} 08/31/2021 09:11:25 - INFO - __main__ - Step 110056: {'lr': 8.46123323355179e-05, 'samples': 21130752, 'steps': 110055, 'loss/train': 0.1684863269329071} 08/31/2021 09:11:25 - INFO - __main__ - Step 110057: {'lr': 8.46083528427154e-05, 'samples': 21130944, 'steps': 110056, 'loss/train': 0.40396493673324585} 08/31/2021 09:11:26 - INFO - __main__ - Step 110058: {'lr': 8.46043734244358e-05, 'samples': 21131136, 'steps': 110057, 'loss/train': 1.2993371486663818} 08/31/2021 09:11:26 - INFO - __main__ - Step 110059: {'lr': 8.460039408068093e-05, 'samples': 21131328, 'steps': 110058, 'loss/train': 1.3223274946212769} 08/31/2021 09:11:27 - INFO - __main__ - Step 110060: {'lr': 8.459641481145255e-05, 'samples': 21131520, 'steps': 110059, 'loss/train': 0.8316701650619507} 08/31/2021 09:11:28 - INFO - __main__ - Step 110061: {'lr': 8.45924356167525e-05, 'samples': 21131712, 'steps': 110060, 'loss/train': 1.0117772817611694} 08/31/2021 09:11:28 - INFO - __main__ - Step 110062: {'lr': 8.458845649658253e-05, 'samples': 21131904, 'steps': 110061, 'loss/train': 0.9914066195487976} 08/31/2021 09:11:29 - INFO - __main__ - Step 110063: {'lr': 8.458447745094446e-05, 'samples': 21132096, 'steps': 110062, 'loss/train': 0.8692271113395691} 08/31/2021 09:11:29 - INFO - __main__ - Step 110064: {'lr': 8.458049847984015e-05, 'samples': 21132288, 'steps': 110063, 'loss/train': 0.9445228576660156} 08/31/2021 09:11:31 - INFO - __main__ - Step 110065: {'lr': 8.457651958327122e-05, 'samples': 21132480, 'steps': 110064, 'loss/train': 1.2593284845352173} 08/31/2021 09:11:31 - INFO - __main__ - Step 110066: {'lr': 8.457254076123957e-05, 'samples': 21132672, 'steps': 110065, 'loss/train': 1.0699963569641113} 08/31/2021 09:11:32 - INFO - __main__ - Step 110067: {'lr': 8.456856201374699e-05, 'samples': 21132864, 'steps': 110066, 'loss/train': 1.0939525365829468} 08/31/2021 09:11:32 - INFO - __main__ - Step 110068: {'lr': 8.456458334079525e-05, 'samples': 21133056, 'steps': 110067, 'loss/train': 1.981001853942871} 08/31/2021 09:11:32 - INFO - __main__ - Step 110069: {'lr': 8.456060474238616e-05, 'samples': 21133248, 'steps': 110068, 'loss/train': 1.1941207647323608} 08/31/2021 09:11:33 - INFO - __main__ - Step 110070: {'lr': 8.45566262185215e-05, 'samples': 21133440, 'steps': 110069, 'loss/train': 0.88069087266922} 08/31/2021 09:11:34 - INFO - __main__ - Step 110071: {'lr': 8.45526477692031e-05, 'samples': 21133632, 'steps': 110070, 'loss/train': 1.0883673429489136} 08/31/2021 09:11:35 - INFO - __main__ - Step 110072: {'lr': 8.45486693944327e-05, 'samples': 21133824, 'steps': 110071, 'loss/train': 1.6321760416030884} 08/31/2021 09:11:35 - INFO - __main__ - Step 110073: {'lr': 8.454469109421211e-05, 'samples': 21134016, 'steps': 110072, 'loss/train': 1.8524435758590698} 08/31/2021 09:11:35 - INFO - __main__ - Step 110074: {'lr': 8.454071286854314e-05, 'samples': 21134208, 'steps': 110073, 'loss/train': 0.18956318497657776} 08/31/2021 09:11:36 - INFO - __main__ - Step 110075: {'lr': 8.453673471742757e-05, 'samples': 21134400, 'steps': 110074, 'loss/train': 1.0446741580963135} 08/31/2021 09:11:37 - INFO - __main__ - Step 110076: {'lr': 8.453275664086719e-05, 'samples': 21134592, 'steps': 110075, 'loss/train': 1.2154070138931274} 08/31/2021 09:11:38 - INFO - __main__ - Step 110077: {'lr': 8.452877863886388e-05, 'samples': 21134784, 'steps': 110076, 'loss/train': 0.9987866878509521} 08/31/2021 09:11:38 - INFO - __main__ - Step 110078: {'lr': 8.452480071141927e-05, 'samples': 21134976, 'steps': 110077, 'loss/train': 1.0476690530776978} 08/31/2021 09:11:39 - INFO - __main__ - Step 110079: {'lr': 8.452082285853524e-05, 'samples': 21135168, 'steps': 110078, 'loss/train': 1.0913548469543457} 08/31/2021 09:11:39 - INFO - __main__ - Step 110080: {'lr': 8.451684508021355e-05, 'samples': 21135360, 'steps': 110079, 'loss/train': 1.0951628684997559} 08/31/2021 09:11:40 - INFO - __main__ - Step 110081: {'lr': 8.451286737645603e-05, 'samples': 21135552, 'steps': 110080, 'loss/train': 0.9216821789741516} 08/31/2021 09:11:41 - INFO - __main__ - Step 110082: {'lr': 8.450888974726446e-05, 'samples': 21135744, 'steps': 110081, 'loss/train': 0.13812687993049622} 08/31/2021 09:11:41 - INFO - __main__ - Step 110083: {'lr': 8.450491219264061e-05, 'samples': 21135936, 'steps': 110082, 'loss/train': 0.5710996389389038} 08/31/2021 09:11:42 - INFO - __main__ - Step 110084: {'lr': 8.450093471258632e-05, 'samples': 21136128, 'steps': 110083, 'loss/train': 1.1101291179656982} 08/31/2021 09:11:42 - INFO - __main__ - Step 110085: {'lr': 8.449695730710335e-05, 'samples': 21136320, 'steps': 110084, 'loss/train': 1.1368190050125122} 08/31/2021 09:11:44 - INFO - __main__ - Step 110086: {'lr': 8.449297997619351e-05, 'samples': 21136512, 'steps': 110085, 'loss/train': 0.8992822766304016} 08/31/2021 09:11:44 - INFO - __main__ - Step 110087: {'lr': 8.448900271985854e-05, 'samples': 21136704, 'steps': 110086, 'loss/train': 0.23286937177181244} 08/31/2021 09:11:44 - INFO - __main__ - Step 110088: {'lr': 8.448502553810031e-05, 'samples': 21136896, 'steps': 110087, 'loss/train': 1.4561307430267334} 08/31/2021 09:11:45 - INFO - __main__ - Step 110089: {'lr': 8.448104843092055e-05, 'samples': 21137088, 'steps': 110088, 'loss/train': 1.2311912775039673} 08/31/2021 09:11:45 - INFO - __main__ - Step 110090: {'lr': 8.447707139832109e-05, 'samples': 21137280, 'steps': 110089, 'loss/train': 1.5894653797149658} 08/31/2021 09:11:45 - INFO - __main__ - Step 110091: {'lr': 8.447309444030379e-05, 'samples': 21137472, 'steps': 110090, 'loss/train': 1.7987213134765625} 08/31/2021 09:11:47 - INFO - __main__ - Step 110092: {'lr': 8.446911755687025e-05, 'samples': 21137664, 'steps': 110091, 'loss/train': 1.2797794342041016} 08/31/2021 09:11:47 - INFO - __main__ - Step 110093: {'lr': 8.44651407480224e-05, 'samples': 21137856, 'steps': 110092, 'loss/train': 1.348097562789917} 08/31/2021 09:11:47 - INFO - __main__ - Step 110094: {'lr': 8.4461164013762e-05, 'samples': 21138048, 'steps': 110093, 'loss/train': 0.8653092980384827} 08/31/2021 09:11:48 - INFO - __main__ - Step 110095: {'lr': 8.445718735409083e-05, 'samples': 21138240, 'steps': 110094, 'loss/train': 3.7391905784606934} 08/31/2021 09:11:48 - INFO - __main__ - Step 110096: {'lr': 8.445321076901072e-05, 'samples': 21138432, 'steps': 110095, 'loss/train': 1.151573896408081} 08/31/2021 09:11:50 - INFO - __main__ - Step 110097: {'lr': 8.44492342585234e-05, 'samples': 21138624, 'steps': 110096, 'loss/train': 0.6995542645454407} 08/31/2021 09:11:51 - INFO - __main__ - Step 110098: {'lr': 8.444525782263074e-05, 'samples': 21138816, 'steps': 110097, 'loss/train': 1.0488227605819702} 08/31/2021 09:11:51 - INFO - __main__ - Step 110099: {'lr': 8.444128146133448e-05, 'samples': 21139008, 'steps': 110098, 'loss/train': 1.1359357833862305} 08/31/2021 09:11:52 - INFO - __main__ - Step 110100: {'lr': 8.443730517463643e-05, 'samples': 21139200, 'steps': 110099, 'loss/train': 1.615764856338501} 08/31/2021 09:11:52 - INFO - __main__ - Step 110101: {'lr': 8.443332896253836e-05, 'samples': 21139392, 'steps': 110100, 'loss/train': 1.7497004270553589} 08/31/2021 09:11:52 - INFO - __main__ - Step 110102: {'lr': 8.442935282504208e-05, 'samples': 21139584, 'steps': 110101, 'loss/train': 1.751514196395874} 08/31/2021 09:11:54 - INFO - __main__ - Step 110103: {'lr': 8.44253767621494e-05, 'samples': 21139776, 'steps': 110102, 'loss/train': 2.145235300064087} 08/31/2021 09:11:54 - INFO - __main__ - Step 110104: {'lr': 8.442140077386215e-05, 'samples': 21139968, 'steps': 110103, 'loss/train': 1.1244373321533203} 08/31/2021 09:11:55 - INFO - __main__ - Step 110105: {'lr': 8.441742486018198e-05, 'samples': 21140160, 'steps': 110104, 'loss/train': 1.0393331050872803} 08/31/2021 09:11:55 - INFO - __main__ - Step 110106: {'lr': 8.441344902111076e-05, 'samples': 21140352, 'steps': 110105, 'loss/train': 1.2697534561157227} 08/31/2021 09:11:55 - INFO - __main__ - Step 110107: {'lr': 8.44094732566503e-05, 'samples': 21140544, 'steps': 110106, 'loss/train': 1.5151467323303223} 08/31/2021 09:11:56 - INFO - __main__ - Step 110108: {'lr': 8.440549756680238e-05, 'samples': 21140736, 'steps': 110107, 'loss/train': 1.4961916208267212} 08/31/2021 09:11:58 - INFO - __main__ - Step 110109: {'lr': 8.440152195156878e-05, 'samples': 21140928, 'steps': 110108, 'loss/train': 0.926885187625885} 08/31/2021 09:11:58 - INFO - __main__ - Step 110110: {'lr': 8.439754641095129e-05, 'samples': 21141120, 'steps': 110109, 'loss/train': 1.1214972734451294} 08/31/2021 09:11:59 - INFO - __main__ - Step 110111: {'lr': 8.43935709449517e-05, 'samples': 21141312, 'steps': 110110, 'loss/train': 1.1884937286376953} 08/31/2021 09:11:59 - INFO - __main__ - Step 110112: {'lr': 8.438959555357184e-05, 'samples': 21141504, 'steps': 110111, 'loss/train': 0.7806402444839478} 08/31/2021 09:11:59 - INFO - __main__ - Step 110113: {'lr': 8.438562023681346e-05, 'samples': 21141696, 'steps': 110112, 'loss/train': 1.7241102457046509} 08/31/2021 09:12:01 - INFO - __main__ - Step 110114: {'lr': 8.438164499467834e-05, 'samples': 21141888, 'steps': 110113, 'loss/train': 0.9692758917808533} 08/31/2021 09:12:01 - INFO - __main__ - Step 110115: {'lr': 8.437766982716835e-05, 'samples': 21142080, 'steps': 110114, 'loss/train': 1.1712719202041626} 08/31/2021 09:12:02 - INFO - __main__ - Step 110116: {'lr': 8.437369473428518e-05, 'samples': 21142272, 'steps': 110115, 'loss/train': 1.274750828742981} 08/31/2021 09:12:02 - INFO - __main__ - Step 110117: {'lr': 8.436971971603069e-05, 'samples': 21142464, 'steps': 110116, 'loss/train': 1.5305054187774658} 08/31/2021 09:12:03 - INFO - __main__ - Step 110118: {'lr': 8.436574477240672e-05, 'samples': 21142656, 'steps': 110117, 'loss/train': 1.352590560913086} 08/31/2021 09:12:04 - INFO - __main__ - Step 110119: {'lr': 8.436176990341491e-05, 'samples': 21142848, 'steps': 110118, 'loss/train': 1.4092326164245605} 08/31/2021 09:12:04 - INFO - __main__ - Step 110120: {'lr': 8.435779510905715e-05, 'samples': 21143040, 'steps': 110119, 'loss/train': 0.9780914783477783} 08/31/2021 09:12:05 - INFO - __main__ - Step 110121: {'lr': 8.435382038933517e-05, 'samples': 21143232, 'steps': 110120, 'loss/train': 1.2423492670059204} 08/31/2021 09:12:05 - INFO - __main__ - Step 110122: {'lr': 8.434984574425084e-05, 'samples': 21143424, 'steps': 110121, 'loss/train': 1.2920222282409668} 08/31/2021 09:12:05 - INFO - __main__ - Step 110123: {'lr': 8.434587117380587e-05, 'samples': 21143616, 'steps': 110122, 'loss/train': 0.12272179126739502} 08/31/2021 09:12:07 - INFO - __main__ - Step 110124: {'lr': 8.434189667800212e-05, 'samples': 21143808, 'steps': 110123, 'loss/train': 0.8761037588119507} 08/31/2021 09:12:07 - INFO - __main__ - Step 110125: {'lr': 8.433792225684139e-05, 'samples': 21144000, 'steps': 110124, 'loss/train': 0.9791674613952637} 08/31/2021 09:12:08 - INFO - __main__ - Step 110126: {'lr': 8.43339479103254e-05, 'samples': 21144192, 'steps': 110125, 'loss/train': 1.1247605085372925} 08/31/2021 09:12:08 - INFO - __main__ - Step 110127: {'lr': 8.432997363845599e-05, 'samples': 21144384, 'steps': 110126, 'loss/train': 1.356400728225708} 08/31/2021 09:12:09 - INFO - __main__ - Step 110128: {'lr': 8.432599944123492e-05, 'samples': 21144576, 'steps': 110127, 'loss/train': 0.16481277346611023} 08/31/2021 09:12:10 - INFO - __main__ - Step 110129: {'lr': 8.4322025318664e-05, 'samples': 21144768, 'steps': 110128, 'loss/train': 1.1574252843856812} 08/31/2021 09:12:10 - INFO - __main__ - Step 110130: {'lr': 8.431805127074502e-05, 'samples': 21144960, 'steps': 110129, 'loss/train': 0.807296097278595} 08/31/2021 09:12:11 - INFO - __main__ - Step 110131: {'lr': 8.431407729747987e-05, 'samples': 21145152, 'steps': 110130, 'loss/train': 1.029958963394165} 08/31/2021 09:12:11 - INFO - __main__ - Step 110132: {'lr': 8.431010339887012e-05, 'samples': 21145344, 'steps': 110131, 'loss/train': 0.82481849193573} 08/31/2021 09:12:12 - INFO - __main__ - Step 110133: {'lr': 8.43061295749177e-05, 'samples': 21145536, 'steps': 110132, 'loss/train': 0.8174096345901489} 08/31/2021 09:12:13 - INFO - __main__ - Step 110134: {'lr': 8.43021558256244e-05, 'samples': 21145728, 'steps': 110133, 'loss/train': 1.16529381275177} 08/31/2021 09:12:14 - INFO - __main__ - Step 110135: {'lr': 8.429818215099197e-05, 'samples': 21145920, 'steps': 110134, 'loss/train': 0.9901909232139587} 08/31/2021 09:12:14 - INFO - __main__ - Step 110136: {'lr': 8.429420855102224e-05, 'samples': 21146112, 'steps': 110135, 'loss/train': 1.0295246839523315} 08/31/2021 09:12:14 - INFO - __main__ - Step 110137: {'lr': 8.429023502571698e-05, 'samples': 21146304, 'steps': 110136, 'loss/train': 1.0084431171417236} 08/31/2021 09:12:15 - INFO - __main__ - Step 110138: {'lr': 8.428626157507796e-05, 'samples': 21146496, 'steps': 110137, 'loss/train': 1.708337664604187} 08/31/2021 09:12:15 - INFO - __main__ - Step 110139: {'lr': 8.428228819910703e-05, 'samples': 21146688, 'steps': 110138, 'loss/train': 0.7733734846115112} 08/31/2021 09:12:17 - INFO - __main__ - Step 110140: {'lr': 8.42783148978059e-05, 'samples': 21146880, 'steps': 110139, 'loss/train': 0.46060508489608765} 08/31/2021 09:12:17 - INFO - __main__ - Step 110141: {'lr': 8.427434167117646e-05, 'samples': 21147072, 'steps': 110140, 'loss/train': 0.5518874526023865} 08/31/2021 09:12:17 - INFO - __main__ - Step 110142: {'lr': 8.42703685192204e-05, 'samples': 21147264, 'steps': 110141, 'loss/train': 0.9434306621551514} 08/31/2021 09:12:18 - INFO - __main__ - Step 110143: {'lr': 8.426639544193957e-05, 'samples': 21147456, 'steps': 110142, 'loss/train': 1.0502839088439941} 08/31/2021 09:12:18 - INFO - __main__ - Step 110144: {'lr': 8.426242243933582e-05, 'samples': 21147648, 'steps': 110143, 'loss/train': 1.030437707901001} 08/31/2021 09:12:20 - INFO - __main__ - Step 110145: {'lr': 8.425844951141079e-05, 'samples': 21147840, 'steps': 110144, 'loss/train': 1.2473390102386475} 08/31/2021 09:12:20 - INFO - __main__ - Step 110146: {'lr': 8.425447665816633e-05, 'samples': 21148032, 'steps': 110145, 'loss/train': 1.4832595586776733} 08/31/2021 09:12:20 - INFO - __main__ - Step 110147: {'lr': 8.425050387960426e-05, 'samples': 21148224, 'steps': 110146, 'loss/train': 1.2732059955596924} 08/31/2021 09:12:21 - INFO - __main__ - Step 110148: {'lr': 8.424653117572633e-05, 'samples': 21148416, 'steps': 110147, 'loss/train': 1.106749176979065} 08/31/2021 09:12:21 - INFO - __main__ - Step 110149: {'lr': 8.424255854653439e-05, 'samples': 21148608, 'steps': 110148, 'loss/train': 0.6702794432640076} 08/31/2021 09:12:23 - INFO - __main__ - Step 110150: {'lr': 8.423858599203018e-05, 'samples': 21148800, 'steps': 110149, 'loss/train': 0.2054874151945114} 08/31/2021 09:12:23 - INFO - __main__ - Step 110151: {'lr': 8.423461351221551e-05, 'samples': 21148992, 'steps': 110150, 'loss/train': 1.1389710903167725} 08/31/2021 09:12:24 - INFO - __main__ - Step 110152: {'lr': 8.423064110709216e-05, 'samples': 21149184, 'steps': 110151, 'loss/train': 0.017975423485040665} 08/31/2021 09:12:24 - INFO - __main__ - Step 110153: {'lr': 8.422666877666194e-05, 'samples': 21149376, 'steps': 110152, 'loss/train': 0.46411818265914917} 08/31/2021 09:12:24 - INFO - __main__ - Step 110154: {'lr': 8.42226965209266e-05, 'samples': 21149568, 'steps': 110153, 'loss/train': 0.9927206635475159} 08/31/2021 09:12:26 - INFO - __main__ - Step 110155: {'lr': 8.421872433988798e-05, 'samples': 21149760, 'steps': 110154, 'loss/train': 2.4285595417022705} 08/31/2021 09:12:27 - INFO - __main__ - Step 110156: {'lr': 8.421475223354782e-05, 'samples': 21149952, 'steps': 110155, 'loss/train': 1.4333070516586304} 08/31/2021 09:12:27 - INFO - __main__ - Step 110157: {'lr': 8.421078020190794e-05, 'samples': 21150144, 'steps': 110156, 'loss/train': 1.1165661811828613} 08/31/2021 09:12:28 - INFO - __main__ - Step 110158: {'lr': 8.420680824497023e-05, 'samples': 21150336, 'steps': 110157, 'loss/train': 1.170758843421936} 08/31/2021 09:12:28 - INFO - __main__ - Step 110159: {'lr': 8.420283636273626e-05, 'samples': 21150528, 'steps': 110158, 'loss/train': 1.5628358125686646} 08/31/2021 09:12:28 - INFO - __main__ - Step 110160: {'lr': 8.419886455520795e-05, 'samples': 21150720, 'steps': 110159, 'loss/train': 0.1326906830072403} 08/31/2021 09:12:29 - INFO - __main__ - Step 110161: {'lr': 8.419489282238707e-05, 'samples': 21150912, 'steps': 110160, 'loss/train': 0.017486313357949257} 08/31/2021 09:12:31 - INFO - __main__ - Step 110162: {'lr': 8.419092116427542e-05, 'samples': 21151104, 'steps': 110161, 'loss/train': 0.01634221524000168} 08/31/2021 09:12:31 - INFO - __main__ - Step 110163: {'lr': 8.418694958087477e-05, 'samples': 21151296, 'steps': 110162, 'loss/train': 0.9552754759788513} 08/31/2021 09:12:32 - INFO - __main__ - Step 110164: {'lr': 8.418297807218695e-05, 'samples': 21151488, 'steps': 110163, 'loss/train': 1.279375672340393} 08/31/2021 09:12:32 - INFO - __main__ - Step 110165: {'lr': 8.417900663821368e-05, 'samples': 21151680, 'steps': 110164, 'loss/train': 0.855984091758728} 08/31/2021 09:12:32 - INFO - __main__ - Step 110166: {'lr': 8.417503527895681e-05, 'samples': 21151872, 'steps': 110165, 'loss/train': 1.4330785274505615} 08/31/2021 09:12:34 - INFO - __main__ - Step 110167: {'lr': 8.417106399441813e-05, 'samples': 21152064, 'steps': 110166, 'loss/train': 1.0173778533935547} 08/31/2021 09:12:34 - INFO - __main__ - Step 110168: {'lr': 8.416709278459939e-05, 'samples': 21152256, 'steps': 110167, 'loss/train': 0.7016446590423584} 08/31/2021 09:12:35 - INFO - __main__ - Step 110169: {'lr': 8.416312164950246e-05, 'samples': 21152448, 'steps': 110168, 'loss/train': 1.199646234512329} 08/31/2021 09:12:35 - INFO - __main__ - Step 110170: {'lr': 8.415915058912901e-05, 'samples': 21152640, 'steps': 110169, 'loss/train': 1.161271333694458} 08/31/2021 09:12:35 - INFO - __main__ - Step 110171: {'lr': 8.41551796034809e-05, 'samples': 21152832, 'steps': 110170, 'loss/train': 0.9415691494941711} 08/31/2021 09:12:37 - INFO - __main__ - Step 110172: {'lr': 8.415120869255987e-05, 'samples': 21153024, 'steps': 110171, 'loss/train': 0.036678414791822433} 08/31/2021 09:12:37 - INFO - __main__ - Step 110173: {'lr': 8.41472378563678e-05, 'samples': 21153216, 'steps': 110172, 'loss/train': 1.0566273927688599} 08/31/2021 09:12:38 - INFO - __main__ - Step 110174: {'lr': 8.414326709490638e-05, 'samples': 21153408, 'steps': 110173, 'loss/train': 0.18176309764385223} 08/31/2021 09:12:38 - INFO - __main__ - Step 110175: {'lr': 8.413929640817746e-05, 'samples': 21153600, 'steps': 110174, 'loss/train': 1.1991751194000244} 08/31/2021 09:12:38 - INFO - __main__ - Step 110176: {'lr': 8.41353257961828e-05, 'samples': 21153792, 'steps': 110175, 'loss/train': 0.9954955577850342} 08/31/2021 09:12:40 - INFO - __main__ - Step 110177: {'lr': 8.413135525892423e-05, 'samples': 21153984, 'steps': 110176, 'loss/train': 1.0001654624938965} 08/31/2021 09:12:40 - INFO - __main__ - Step 110178: {'lr': 8.41273847964035e-05, 'samples': 21154176, 'steps': 110177, 'loss/train': 0.4441753923892975} 08/31/2021 09:12:41 - INFO - __main__ - Step 110179: {'lr': 8.412341440862239e-05, 'samples': 21154368, 'steps': 110178, 'loss/train': 1.460768699645996} 08/31/2021 09:12:41 - INFO - __main__ - Step 110180: {'lr': 8.41194440955828e-05, 'samples': 21154560, 'steps': 110179, 'loss/train': 0.9154748916625977} 08/31/2021 09:12:41 - INFO - __main__ - Step 110181: {'lr': 8.411547385728638e-05, 'samples': 21154752, 'steps': 110180, 'loss/train': 0.896723747253418} 08/31/2021 09:12:43 - INFO - __main__ - Step 110182: {'lr': 8.411150369373494e-05, 'samples': 21154944, 'steps': 110181, 'loss/train': 0.89201420545578} 08/31/2021 09:12:44 - INFO - __main__ - Step 110183: {'lr': 8.410753360493032e-05, 'samples': 21155136, 'steps': 110182, 'loss/train': 0.9332504272460938} 08/31/2021 09:12:44 - INFO - __main__ - Step 110184: {'lr': 8.410356359087424e-05, 'samples': 21155328, 'steps': 110183, 'loss/train': 1.343500018119812} 08/31/2021 09:12:44 - INFO - __main__ - Step 110185: {'lr': 8.409959365156857e-05, 'samples': 21155520, 'steps': 110184, 'loss/train': 1.4535263776779175} 08/31/2021 09:12:45 - INFO - __main__ - Step 110186: {'lr': 8.409562378701504e-05, 'samples': 21155712, 'steps': 110185, 'loss/train': 5.6994547843933105} 08/31/2021 09:12:45 - INFO - __main__ - Step 110187: {'lr': 8.409165399721549e-05, 'samples': 21155904, 'steps': 110186, 'loss/train': 1.1481413841247559} 08/31/2021 09:12:46 - INFO - __main__ - Step 110188: {'lr': 8.408768428217167e-05, 'samples': 21156096, 'steps': 110187, 'loss/train': 0.8245636820793152} 08/31/2021 09:12:47 - INFO - __main__ - Step 110189: {'lr': 8.408371464188536e-05, 'samples': 21156288, 'steps': 110188, 'loss/train': 0.9944839477539062} 08/31/2021 09:12:47 - INFO - __main__ - Step 110190: {'lr': 8.407974507635838e-05, 'samples': 21156480, 'steps': 110189, 'loss/train': 1.5245224237442017} 08/31/2021 09:12:48 - INFO - __main__ - Step 110191: {'lr': 8.40757755855926e-05, 'samples': 21156672, 'steps': 110190, 'loss/train': 1.6924718618392944} 08/31/2021 09:12:48 - INFO - __main__ - Step 110192: {'lr': 8.407180616958962e-05, 'samples': 21156864, 'steps': 110191, 'loss/train': 0.3664628267288208} 08/31/2021 09:12:50 - INFO - __main__ - Step 110193: {'lr': 8.406783682835134e-05, 'samples': 21157056, 'steps': 110192, 'loss/train': 1.8787893056869507} 08/31/2021 09:12:50 - INFO - __main__ - Step 110194: {'lr': 8.40638675618795e-05, 'samples': 21157248, 'steps': 110193, 'loss/train': 1.1473252773284912} 08/31/2021 09:12:50 - INFO - __main__ - Step 110195: {'lr': 8.405989837017597e-05, 'samples': 21157440, 'steps': 110194, 'loss/train': 2.1339073181152344} 08/31/2021 09:12:51 - INFO - __main__ - Step 110196: {'lr': 8.405592925324246e-05, 'samples': 21157632, 'steps': 110195, 'loss/train': 1.8634380102157593} 08/31/2021 09:12:51 - INFO - __main__ - Step 110197: {'lr': 8.405196021108077e-05, 'samples': 21157824, 'steps': 110196, 'loss/train': 0.8195485472679138} 08/31/2021 09:12:51 - INFO - __main__ - Step 110198: {'lr': 8.404799124369272e-05, 'samples': 21158016, 'steps': 110197, 'loss/train': 1.572930932044983} 08/31/2021 09:12:53 - INFO - __main__ - Step 110199: {'lr': 8.40440223510801e-05, 'samples': 21158208, 'steps': 110198, 'loss/train': 1.0530647039413452} 08/31/2021 09:12:54 - INFO - __main__ - Step 110200: {'lr': 8.404005353324468e-05, 'samples': 21158400, 'steps': 110199, 'loss/train': 0.6161497831344604} 08/31/2021 09:12:54 - INFO - __main__ - Step 110201: {'lr': 8.403608479018832e-05, 'samples': 21158592, 'steps': 110200, 'loss/train': 1.583016037940979} 08/31/2021 09:12:54 - INFO - __main__ - Step 110202: {'lr': 8.403211612191266e-05, 'samples': 21158784, 'steps': 110201, 'loss/train': 0.6916511058807373} 08/31/2021 09:12:55 - INFO - __main__ - Step 110203: {'lr': 8.402814752841956e-05, 'samples': 21158976, 'steps': 110202, 'loss/train': 1.010928988456726} 08/31/2021 09:12:56 - INFO - __main__ - Step 110204: {'lr': 8.402417900971082e-05, 'samples': 21159168, 'steps': 110203, 'loss/train': 0.4722751975059509} 08/31/2021 09:12:57 - INFO - __main__ - Step 110205: {'lr': 8.402021056578823e-05, 'samples': 21159360, 'steps': 110204, 'loss/train': 1.1436156034469604} 08/31/2021 09:12:57 - INFO - __main__ - Step 110206: {'lr': 8.401624219665358e-05, 'samples': 21159552, 'steps': 110205, 'loss/train': 1.141254186630249} 08/31/2021 09:12:57 - INFO - __main__ - Step 110207: {'lr': 8.401227390230864e-05, 'samples': 21159744, 'steps': 110206, 'loss/train': 1.54704749584198} 08/31/2021 09:12:58 - INFO - __main__ - Step 110208: {'lr': 8.400830568275519e-05, 'samples': 21159936, 'steps': 110207, 'loss/train': 1.2840843200683594} 08/31/2021 09:12:59 - INFO - __main__ - Step 110209: {'lr': 8.400433753799508e-05, 'samples': 21160128, 'steps': 110208, 'loss/train': 1.1334017515182495} 08/31/2021 09:13:00 - INFO - __main__ - Step 110210: {'lr': 8.400036946803002e-05, 'samples': 21160320, 'steps': 110209, 'loss/train': 1.0744876861572266} 08/31/2021 09:13:00 - INFO - __main__ - Step 110211: {'lr': 8.399640147286183e-05, 'samples': 21160512, 'steps': 110210, 'loss/train': 1.5725696086883545} 08/31/2021 09:13:00 - INFO - __main__ - Step 110212: {'lr': 8.399243355249239e-05, 'samples': 21160704, 'steps': 110211, 'loss/train': 0.24675481021404266} 08/31/2021 09:13:01 - INFO - __main__ - Step 110213: {'lr': 8.398846570692334e-05, 'samples': 21160896, 'steps': 110212, 'loss/train': 1.2578285932540894} 08/31/2021 09:13:01 - INFO - __main__ - Step 110214: {'lr': 8.39844979361565e-05, 'samples': 21161088, 'steps': 110213, 'loss/train': 1.430350661277771} 08/31/2021 09:13:03 - INFO - __main__ - Step 110215: {'lr': 8.398053024019366e-05, 'samples': 21161280, 'steps': 110214, 'loss/train': 1.460996150970459} 08/31/2021 09:13:04 - INFO - __main__ - Step 110216: {'lr': 8.397656261903668e-05, 'samples': 21161472, 'steps': 110215, 'loss/train': 1.5064958333969116} 08/31/2021 09:13:04 - INFO - __main__ - Step 110217: {'lr': 8.397259507268728e-05, 'samples': 21161664, 'steps': 110216, 'loss/train': 0.05805710703134537} 08/31/2021 09:13:04 - INFO - __main__ - Step 110218: {'lr': 8.396862760114726e-05, 'samples': 21161856, 'steps': 110217, 'loss/train': 0.12531237304210663} 08/31/2021 09:13:05 - INFO - __main__ - Step 110219: {'lr': 8.396466020441842e-05, 'samples': 21162048, 'steps': 110218, 'loss/train': 1.264794111251831} 08/31/2021 09:13:07 - INFO - __main__ - Step 110220: {'lr': 8.396069288250254e-05, 'samples': 21162240, 'steps': 110219, 'loss/train': 0.3497074246406555} 08/31/2021 09:13:07 - INFO - __main__ - Step 110221: {'lr': 8.395672563540141e-05, 'samples': 21162432, 'steps': 110220, 'loss/train': 0.7233130931854248} 08/31/2021 09:13:08 - INFO - __main__ - Step 110222: {'lr': 8.395275846311681e-05, 'samples': 21162624, 'steps': 110221, 'loss/train': 1.0695396661758423} 08/31/2021 09:13:08 - INFO - __main__ - Step 110223: {'lr': 8.394879136565053e-05, 'samples': 21162816, 'steps': 110222, 'loss/train': 1.2548905611038208} 08/31/2021 09:13:08 - INFO - __main__ - Step 110224: {'lr': 8.39448243430044e-05, 'samples': 21163008, 'steps': 110223, 'loss/train': 1.064374566078186} 08/31/2021 09:13:10 - INFO - __main__ - Step 110225: {'lr': 8.394085739518023e-05, 'samples': 21163200, 'steps': 110224, 'loss/train': 0.5203798413276672} 08/31/2021 09:13:10 - INFO - __main__ - Step 110226: {'lr': 8.393689052217964e-05, 'samples': 21163392, 'steps': 110225, 'loss/train': 1.3310359716415405} 08/31/2021 09:13:11 - INFO - __main__ - Step 110227: {'lr': 8.393292372400455e-05, 'samples': 21163584, 'steps': 110226, 'loss/train': 1.309423804283142} 08/31/2021 09:13:11 - INFO - __main__ - Step 110228: {'lr': 8.392895700065673e-05, 'samples': 21163776, 'steps': 110227, 'loss/train': 0.3705635070800781} 08/31/2021 09:13:11 - INFO - __main__ - Step 110229: {'lr': 8.392499035213794e-05, 'samples': 21163968, 'steps': 110228, 'loss/train': 1.2776525020599365} 08/31/2021 09:13:12 - INFO - __main__ - Step 110230: {'lr': 8.392102377844998e-05, 'samples': 21164160, 'steps': 110229, 'loss/train': 0.9494626522064209} 08/31/2021 09:13:13 - INFO - __main__ - Step 110231: {'lr': 8.391705727959467e-05, 'samples': 21164352, 'steps': 110230, 'loss/train': 0.7220562696456909} 08/31/2021 09:13:14 - INFO - __main__ - Step 110232: {'lr': 8.391309085557375e-05, 'samples': 21164544, 'steps': 110231, 'loss/train': 1.070771336555481} 08/31/2021 09:13:14 - INFO - __main__ - Step 110233: {'lr': 8.390912450638904e-05, 'samples': 21164736, 'steps': 110232, 'loss/train': 1.2842210531234741} 08/31/2021 09:13:14 - INFO - __main__ - Step 110234: {'lr': 8.390515823204231e-05, 'samples': 21164928, 'steps': 110233, 'loss/train': 1.8108493089675903} 08/31/2021 09:13:15 - INFO - __main__ - Step 110235: {'lr': 8.390119203253538e-05, 'samples': 21165120, 'steps': 110234, 'loss/train': 0.42840567231178284} 08/31/2021 09:13:17 - INFO - __main__ - Step 110236: {'lr': 8.389722590786997e-05, 'samples': 21165312, 'steps': 110235, 'loss/train': 1.1929885149002075} 08/31/2021 09:13:17 - INFO - __main__ - Step 110237: {'lr': 8.389325985804794e-05, 'samples': 21165504, 'steps': 110236, 'loss/train': 1.758787751197815} 08/31/2021 09:13:17 - INFO - __main__ - Step 110238: {'lr': 8.3889293883071e-05, 'samples': 21165696, 'steps': 110237, 'loss/train': 1.7499006986618042} 08/31/2021 09:13:18 - INFO - __main__ - Step 110239: {'lr': 8.38853279829411e-05, 'samples': 21165888, 'steps': 110238, 'loss/train': 1.1186909675598145} 08/31/2021 09:13:18 - INFO - __main__ - Step 110240: {'lr': 8.388136215765982e-05, 'samples': 21166080, 'steps': 110239, 'loss/train': 1.2127965688705444} 08/31/2021 09:13:19 - INFO - __main__ - Step 110241: {'lr': 8.387739640722902e-05, 'samples': 21166272, 'steps': 110240, 'loss/train': 0.9839131832122803} 08/31/2021 09:13:20 - INFO - __main__ - Step 110242: {'lr': 8.387343073165052e-05, 'samples': 21166464, 'steps': 110241, 'loss/train': 1.3853636980056763} 08/31/2021 09:13:20 - INFO - __main__ - Step 110243: {'lr': 8.386946513092608e-05, 'samples': 21166656, 'steps': 110242, 'loss/train': 1.1480220556259155} 08/31/2021 09:13:21 - INFO - __main__ - Step 110244: {'lr': 8.386549960505749e-05, 'samples': 21166848, 'steps': 110243, 'loss/train': 1.515480637550354} 08/31/2021 09:13:21 - INFO - __main__ - Step 110245: {'lr': 8.386153415404654e-05, 'samples': 21167040, 'steps': 110244, 'loss/train': 1.3182963132858276} 08/31/2021 09:13:21 - INFO - __main__ - Step 110246: {'lr': 8.385756877789504e-05, 'samples': 21167232, 'steps': 110245, 'loss/train': 0.8647670149803162} 08/31/2021 09:13:23 - INFO - __main__ - Step 110247: {'lr': 8.385360347660476e-05, 'samples': 21167424, 'steps': 110246, 'loss/train': 1.3805228471755981} 08/31/2021 09:13:23 - INFO - __main__ - Step 110248: {'lr': 8.384963825017744e-05, 'samples': 21167616, 'steps': 110247, 'loss/train': 0.9903991222381592} 08/31/2021 09:13:24 - INFO - __main__ - Step 110249: {'lr': 8.384567309861494e-05, 'samples': 21167808, 'steps': 110248, 'loss/train': 1.3019587993621826} 08/31/2021 09:13:24 - INFO - __main__ - Step 110250: {'lr': 8.3841708021919e-05, 'samples': 21168000, 'steps': 110249, 'loss/train': 1.2090662717819214} 08/31/2021 09:13:24 - INFO - __main__ - Step 110251: {'lr': 8.383774302009145e-05, 'samples': 21168192, 'steps': 110250, 'loss/train': 1.3551768064498901} 08/31/2021 09:13:26 - INFO - __main__ - Step 110252: {'lr': 8.383377809313411e-05, 'samples': 21168384, 'steps': 110251, 'loss/train': 1.1800925731658936} 08/31/2021 09:13:26 - INFO - __main__ - Step 110253: {'lr': 8.382981324104863e-05, 'samples': 21168576, 'steps': 110252, 'loss/train': 0.03348829597234726} 08/31/2021 09:13:27 - INFO - __main__ - Step 110254: {'lr': 8.382584846383687e-05, 'samples': 21168768, 'steps': 110253, 'loss/train': 1.4942865371704102} 08/31/2021 09:13:27 - INFO - __main__ - Step 110255: {'lr': 8.38218837615006e-05, 'samples': 21168960, 'steps': 110254, 'loss/train': 1.452448844909668} 08/31/2021 09:13:27 - INFO - __main__ - Step 110256: {'lr': 8.381791913404166e-05, 'samples': 21169152, 'steps': 110255, 'loss/train': 1.354486107826233} 08/31/2021 09:13:29 - INFO - __main__ - Step 110257: {'lr': 8.381395458146179e-05, 'samples': 21169344, 'steps': 110256, 'loss/train': 0.6998597979545593} 08/31/2021 09:13:29 - INFO - __main__ - Step 110258: {'lr': 8.380999010376278e-05, 'samples': 21169536, 'steps': 110257, 'loss/train': 1.3368678092956543} 08/31/2021 09:13:30 - INFO - __main__ - Step 110259: {'lr': 8.380602570094642e-05, 'samples': 21169728, 'steps': 110258, 'loss/train': 0.9484792351722717} 08/31/2021 09:13:30 - INFO - __main__ - Step 110260: {'lr': 8.38020613730145e-05, 'samples': 21169920, 'steps': 110259, 'loss/train': 0.08759754151105881} 08/31/2021 09:13:30 - INFO - __main__ - Step 110261: {'lr': 8.37980971199688e-05, 'samples': 21170112, 'steps': 110260, 'loss/train': 1.4220802783966064} 08/31/2021 09:13:31 - INFO - __main__ - Step 110262: {'lr': 8.379413294181116e-05, 'samples': 21170304, 'steps': 110261, 'loss/train': 0.5926051139831543} 08/31/2021 09:13:32 - INFO - __main__ - Step 110263: {'lr': 8.379016883854327e-05, 'samples': 21170496, 'steps': 110262, 'loss/train': 1.1759142875671387} 08/31/2021 09:13:33 - INFO - __main__ - Step 110264: {'lr': 8.378620481016697e-05, 'samples': 21170688, 'steps': 110263, 'loss/train': 0.8547091484069824} 08/31/2021 09:13:33 - INFO - __main__ - Step 110265: {'lr': 8.378224085668412e-05, 'samples': 21170880, 'steps': 110264, 'loss/train': 0.7536357045173645} 08/31/2021 09:13:33 - INFO - __main__ - Step 110266: {'lr': 8.377827697809637e-05, 'samples': 21171072, 'steps': 110265, 'loss/train': 0.799858808517456} 08/31/2021 09:13:34 - INFO - __main__ - Step 110267: {'lr': 8.377431317440556e-05, 'samples': 21171264, 'steps': 110266, 'loss/train': 1.3866127729415894} 08/31/2021 09:13:36 - INFO - __main__ - Step 110268: {'lr': 8.377034944561346e-05, 'samples': 21171456, 'steps': 110267, 'loss/train': 1.428436040878296} 08/31/2021 09:13:36 - INFO - __main__ - Step 110269: {'lr': 8.376638579172189e-05, 'samples': 21171648, 'steps': 110268, 'loss/train': 0.03856825828552246} 08/31/2021 09:13:36 - INFO - __main__ - Step 110270: {'lr': 8.376242221273262e-05, 'samples': 21171840, 'steps': 110269, 'loss/train': 1.3188550472259521} 08/31/2021 09:13:37 - INFO - __main__ - Step 110271: {'lr': 8.375845870864743e-05, 'samples': 21172032, 'steps': 110270, 'loss/train': 0.9920118451118469} 08/31/2021 09:13:37 - INFO - __main__ - Step 110272: {'lr': 8.375449527946812e-05, 'samples': 21172224, 'steps': 110271, 'loss/train': 1.184464454650879} 08/31/2021 09:13:39 - INFO - __main__ - Step 110273: {'lr': 8.375053192519647e-05, 'samples': 21172416, 'steps': 110272, 'loss/train': 1.2236344814300537} 08/31/2021 09:13:40 - INFO - __main__ - Step 110274: {'lr': 8.374656864583427e-05, 'samples': 21172608, 'steps': 110273, 'loss/train': 1.3606488704681396} 08/31/2021 09:13:40 - INFO - __main__ - Step 110275: {'lr': 8.374260544138329e-05, 'samples': 21172800, 'steps': 110274, 'loss/train': 1.056501865386963} 08/31/2021 09:13:40 - INFO - __main__ - Step 110276: {'lr': 8.373864231184533e-05, 'samples': 21172992, 'steps': 110275, 'loss/train': 0.8187862634658813} 08/31/2021 09:13:41 - INFO - __main__ - Step 110277: {'lr': 8.373467925722217e-05, 'samples': 21173184, 'steps': 110276, 'loss/train': 0.9712700843811035} 08/31/2021 09:13:42 - INFO - __main__ - Step 110278: {'lr': 8.373071627751561e-05, 'samples': 21173376, 'steps': 110277, 'loss/train': 0.6952425241470337} 08/31/2021 09:13:43 - INFO - __main__ - Step 110279: {'lr': 8.372675337272747e-05, 'samples': 21173568, 'steps': 110278, 'loss/train': 0.4554291367530823} 08/31/2021 09:13:43 - INFO - __main__ - Step 110280: {'lr': 8.372279054285944e-05, 'samples': 21173760, 'steps': 110279, 'loss/train': 0.6168022155761719} 08/31/2021 09:13:44 - INFO - __main__ - Step 110281: {'lr': 8.371882778791334e-05, 'samples': 21173952, 'steps': 110280, 'loss/train': 1.5177645683288574} 08/31/2021 09:13:44 - INFO - __main__ - Step 110282: {'lr': 8.371486510789097e-05, 'samples': 21174144, 'steps': 110281, 'loss/train': 1.1042391061782837} 08/31/2021 09:13:46 - INFO - __main__ - Step 110283: {'lr': 8.371090250279415e-05, 'samples': 21174336, 'steps': 110282, 'loss/train': 0.8547751307487488} 08/31/2021 09:13:46 - INFO - __main__ - Step 110284: {'lr': 8.37069399726246e-05, 'samples': 21174528, 'steps': 110283, 'loss/train': 1.0985264778137207} 08/31/2021 09:13:46 - INFO - __main__ - Step 110285: {'lr': 8.370297751738416e-05, 'samples': 21174720, 'steps': 110284, 'loss/train': 1.5580965280532837} 08/31/2021 09:13:47 - INFO - __main__ - Step 110286: {'lr': 8.369901513707456e-05, 'samples': 21174912, 'steps': 110285, 'loss/train': 1.306283712387085} 08/31/2021 09:13:47 - INFO - __main__ - Step 110287: {'lr': 8.369505283169763e-05, 'samples': 21175104, 'steps': 110286, 'loss/train': 0.979537844657898} 08/31/2021 09:13:48 - INFO - __main__ - Step 110288: {'lr': 8.369109060125513e-05, 'samples': 21175296, 'steps': 110287, 'loss/train': 0.5909027457237244} 08/31/2021 09:13:49 - INFO - __main__ - Step 110289: {'lr': 8.368712844574888e-05, 'samples': 21175488, 'steps': 110288, 'loss/train': 1.432632565498352} 08/31/2021 09:13:49 - INFO - __main__ - Step 110290: {'lr': 8.368316636518064e-05, 'samples': 21175680, 'steps': 110289, 'loss/train': 1.1859530210494995} 08/31/2021 09:13:50 - INFO - __main__ - Step 110291: {'lr': 8.367920435955217e-05, 'samples': 21175872, 'steps': 110290, 'loss/train': 0.036232221871614456} 08/31/2021 09:13:50 - INFO - __main__ - Step 110292: {'lr': 8.36752424288654e-05, 'samples': 21176064, 'steps': 110291, 'loss/train': 0.028020834550261497} 08/31/2021 09:13:50 - INFO - __main__ - Step 110293: {'lr': 8.367128057312192e-05, 'samples': 21176256, 'steps': 110292, 'loss/train': 1.2010698318481445} 08/31/2021 09:13:52 - INFO - __main__ - Step 110294: {'lr': 8.366731879232359e-05, 'samples': 21176448, 'steps': 110293, 'loss/train': 0.7980687618255615} 08/31/2021 09:13:53 - INFO - __main__ - Step 110295: {'lr': 8.366335708647218e-05, 'samples': 21176640, 'steps': 110294, 'loss/train': 1.1861211061477661} 08/31/2021 09:13:53 - INFO - __main__ - Step 110296: {'lr': 8.36593954555695e-05, 'samples': 21176832, 'steps': 110295, 'loss/train': 1.8043209314346313} 08/31/2021 09:13:53 - INFO - __main__ - Step 110297: {'lr': 8.365543389961735e-05, 'samples': 21177024, 'steps': 110296, 'loss/train': 0.7920684218406677} 08/31/2021 09:13:54 - INFO - __main__ - Step 110298: {'lr': 8.365147241861748e-05, 'samples': 21177216, 'steps': 110297, 'loss/train': 0.954098641872406} 08/31/2021 09:13:55 - INFO - __main__ - Step 110299: {'lr': 8.364751101257167e-05, 'samples': 21177408, 'steps': 110298, 'loss/train': 1.172959327697754} 08/31/2021 09:13:56 - INFO - __main__ - Step 110300: {'lr': 8.364354968148177e-05, 'samples': 21177600, 'steps': 110299, 'loss/train': 0.36944645643234253} 08/31/2021 09:13:56 - INFO - __main__ - Step 110301: {'lr': 8.363958842534949e-05, 'samples': 21177792, 'steps': 110300, 'loss/train': 1.102555751800537} 08/31/2021 09:13:56 - INFO - __main__ - Step 110302: {'lr': 8.363562724417664e-05, 'samples': 21177984, 'steps': 110301, 'loss/train': 1.7343820333480835} 08/31/2021 09:13:57 - INFO - __main__ - Step 110303: {'lr': 8.363166613796502e-05, 'samples': 21178176, 'steps': 110302, 'loss/train': 1.7659541368484497} 08/31/2021 09:13:58 - INFO - __main__ - Step 110304: {'lr': 8.362770510671641e-05, 'samples': 21178368, 'steps': 110303, 'loss/train': 1.456812858581543} 08/31/2021 09:13:59 - INFO - __main__ - Step 110305: {'lr': 8.362374415043258e-05, 'samples': 21178560, 'steps': 110304, 'loss/train': 0.7777333855628967} 08/31/2021 09:13:59 - INFO - __main__ - Step 110306: {'lr': 8.361978326911541e-05, 'samples': 21178752, 'steps': 110305, 'loss/train': 0.2728969156742096} 08/31/2021 09:14:00 - INFO - __main__ - Step 110307: {'lr': 8.36158224627665e-05, 'samples': 21178944, 'steps': 110306, 'loss/train': 1.285454511642456} 08/31/2021 09:14:00 - INFO - __main__ - Step 110308: {'lr': 8.361186173138774e-05, 'samples': 21179136, 'steps': 110307, 'loss/train': 1.2112133502960205} 08/31/2021 09:14:00 - INFO - __main__ - Step 110309: {'lr': 8.360790107498092e-05, 'samples': 21179328, 'steps': 110308, 'loss/train': 0.036697451025247574} 08/31/2021 09:14:02 - INFO - __main__ - Step 110310: {'lr': 8.36039404935478e-05, 'samples': 21179520, 'steps': 110309, 'loss/train': 1.6415048837661743} 08/31/2021 09:14:02 - INFO - __main__ - Step 110311: {'lr': 8.359997998709019e-05, 'samples': 21179712, 'steps': 110310, 'loss/train': 1.215340256690979} 08/31/2021 09:14:03 - INFO - __main__ - Step 110312: {'lr': 8.359601955560986e-05, 'samples': 21179904, 'steps': 110311, 'loss/train': 1.395163655281067} 08/31/2021 09:14:03 - INFO - __main__ - Step 110313: {'lr': 8.359205919910858e-05, 'samples': 21180096, 'steps': 110312, 'loss/train': 1.242453694343567} 08/31/2021 09:14:03 - INFO - __main__ - Step 110314: {'lr': 8.358809891758815e-05, 'samples': 21180288, 'steps': 110313, 'loss/train': 0.6691756248474121} 08/31/2021 09:14:05 - INFO - __main__ - Step 110315: {'lr': 8.358413871105037e-05, 'samples': 21180480, 'steps': 110314, 'loss/train': 1.4447325468063354} 08/31/2021 09:14:05 - INFO - __main__ - Step 110316: {'lr': 8.358017857949701e-05, 'samples': 21180672, 'steps': 110315, 'loss/train': 1.116593837738037} 08/31/2021 09:14:06 - INFO - __main__ - Step 110317: {'lr': 8.357621852292984e-05, 'samples': 21180864, 'steps': 110316, 'loss/train': 1.0583064556121826} 08/31/2021 09:14:06 - INFO - __main__ - Step 110318: {'lr': 8.357225854135067e-05, 'samples': 21181056, 'steps': 110317, 'loss/train': 1.351340889930725} 08/31/2021 09:14:06 - INFO - __main__ - Step 110319: {'lr': 8.356829863476134e-05, 'samples': 21181248, 'steps': 110318, 'loss/train': 1.3893458843231201} 08/31/2021 09:14:08 - INFO - __main__ - Step 110320: {'lr': 8.35643388031635e-05, 'samples': 21181440, 'steps': 110319, 'loss/train': 1.1336346864700317} 08/31/2021 09:14:08 - INFO - __main__ - Step 110321: {'lr': 8.3560379046559e-05, 'samples': 21181632, 'steps': 110320, 'loss/train': 1.3826442956924438} 08/31/2021 09:14:08 - INFO - __main__ - Step 110322: {'lr': 8.355641936494962e-05, 'samples': 21181824, 'steps': 110321, 'loss/train': 0.6184664964675903} 08/31/2021 09:14:09 - INFO - __main__ - Step 110323: {'lr': 8.355245975833714e-05, 'samples': 21182016, 'steps': 110322, 'loss/train': 1.299063801765442} 08/31/2021 09:14:09 - INFO - __main__ - Step 110324: {'lr': 8.354850022672336e-05, 'samples': 21182208, 'steps': 110323, 'loss/train': 1.3828938007354736} 08/31/2021 09:14:11 - INFO - __main__ - Step 110325: {'lr': 8.354454077011006e-05, 'samples': 21182400, 'steps': 110324, 'loss/train': 0.08036688715219498} 08/31/2021 09:14:11 - INFO - __main__ - Step 110326: {'lr': 8.354058138849902e-05, 'samples': 21182592, 'steps': 110325, 'loss/train': 1.3946348428726196} 08/31/2021 09:14:11 - INFO - __main__ - Step 110327: {'lr': 8.353662208189203e-05, 'samples': 21182784, 'steps': 110326, 'loss/train': 1.5605136156082153} 08/31/2021 09:14:12 - INFO - __main__ - Step 110328: {'lr': 8.353266285029085e-05, 'samples': 21182976, 'steps': 110327, 'loss/train': 0.9588717222213745} 08/31/2021 09:14:12 - INFO - __main__ - Step 110329: {'lr': 8.352870369369731e-05, 'samples': 21183168, 'steps': 110328, 'loss/train': 0.8778438568115234} 08/31/2021 09:14:13 - INFO - __main__ - Step 110330: {'lr': 8.352474461211315e-05, 'samples': 21183360, 'steps': 110329, 'loss/train': 0.5185567736625671} 08/31/2021 09:14:15 - INFO - __main__ - Step 110331: {'lr': 8.352078560554019e-05, 'samples': 21183552, 'steps': 110330, 'loss/train': 0.8048032522201538} 08/31/2021 09:14:15 - INFO - __main__ - Step 110332: {'lr': 8.351682667398017e-05, 'samples': 21183744, 'steps': 110331, 'loss/train': 0.24663135409355164} 08/31/2021 09:14:15 - INFO - __main__ - Step 110333: {'lr': 8.3512867817435e-05, 'samples': 21183936, 'steps': 110332, 'loss/train': 0.9957932233810425} 08/31/2021 09:14:16 - INFO - __main__ - Step 110334: {'lr': 8.350890903590627e-05, 'samples': 21184128, 'steps': 110333, 'loss/train': 0.4299963414669037} 08/31/2021 09:14:16 - INFO - __main__ - Step 110335: {'lr': 8.350495032939587e-05, 'samples': 21184320, 'steps': 110334, 'loss/train': 1.4265791177749634} 08/31/2021 09:14:18 - INFO - __main__ - Step 110336: {'lr': 8.350099169790554e-05, 'samples': 21184512, 'steps': 110335, 'loss/train': 1.159440279006958} 08/31/2021 09:14:18 - INFO - __main__ - Step 110337: {'lr': 8.349703314143711e-05, 'samples': 21184704, 'steps': 110336, 'loss/train': 1.3617931604385376} 08/31/2021 09:14:19 - INFO - __main__ - Step 110338: {'lr': 8.349307465999236e-05, 'samples': 21184896, 'steps': 110337, 'loss/train': 0.6357265710830688} 08/31/2021 09:14:19 - INFO - __main__ - Step 110339: {'lr': 8.348911625357305e-05, 'samples': 21185088, 'steps': 110338, 'loss/train': 1.668519377708435} 08/31/2021 09:14:19 - INFO - __main__ - Step 110340: {'lr': 8.348515792218098e-05, 'samples': 21185280, 'steps': 110339, 'loss/train': 1.7522211074829102} 08/31/2021 09:14:20 - INFO - __main__ - Step 110341: {'lr': 8.348119966581793e-05, 'samples': 21185472, 'steps': 110340, 'loss/train': 0.36389410495758057} 08/31/2021 09:14:21 - INFO - __main__ - Step 110342: {'lr': 8.347724148448569e-05, 'samples': 21185664, 'steps': 110341, 'loss/train': 1.468855857849121} 08/31/2021 09:14:22 - INFO - __main__ - Step 110343: {'lr': 8.3473283378186e-05, 'samples': 21185856, 'steps': 110342, 'loss/train': 1.445719599723816} 08/31/2021 09:14:22 - INFO - __main__ - Step 110344: {'lr': 8.346932534692069e-05, 'samples': 21186048, 'steps': 110343, 'loss/train': 1.1439136266708374} 08/31/2021 09:14:22 - INFO - __main__ - Step 110345: {'lr': 8.346536739069155e-05, 'samples': 21186240, 'steps': 110344, 'loss/train': 0.529008686542511} 08/31/2021 09:14:23 - INFO - __main__ - Step 110346: {'lr': 8.346140950950043e-05, 'samples': 21186432, 'steps': 110345, 'loss/train': 1.1723213195800781} 08/31/2021 09:14:24 - INFO - __main__ - Step 110347: {'lr': 8.345745170334896e-05, 'samples': 21186624, 'steps': 110346, 'loss/train': 0.856529176235199} 08/31/2021 09:14:25 - INFO - __main__ - Step 110348: {'lr': 8.345349397223894e-05, 'samples': 21186816, 'steps': 110347, 'loss/train': 1.177769660949707} 08/31/2021 09:14:25 - INFO - __main__ - Step 110349: {'lr': 8.344953631617225e-05, 'samples': 21187008, 'steps': 110348, 'loss/train': 1.3053171634674072} 08/31/2021 09:14:26 - INFO - __main__ - Step 110350: {'lr': 8.344557873515063e-05, 'samples': 21187200, 'steps': 110349, 'loss/train': 0.5605714321136475} 08/31/2021 09:14:26 - INFO - __main__ - Step 110351: {'lr': 8.344162122917584e-05, 'samples': 21187392, 'steps': 110350, 'loss/train': 0.781393826007843} 08/31/2021 09:14:27 - INFO - __main__ - Step 110352: {'lr': 8.343766379824969e-05, 'samples': 21187584, 'steps': 110351, 'loss/train': 0.952244758605957} 08/31/2021 09:14:28 - INFO - __main__ - Step 110353: {'lr': 8.343370644237397e-05, 'samples': 21187776, 'steps': 110352, 'loss/train': 0.03635061904788017} 08/31/2021 09:14:28 - INFO - __main__ - Step 110354: {'lr': 8.342974916155044e-05, 'samples': 21187968, 'steps': 110353, 'loss/train': 1.1138865947723389} 08/31/2021 09:14:29 - INFO - __main__ - Step 110355: {'lr': 8.34257919557809e-05, 'samples': 21188160, 'steps': 110354, 'loss/train': 1.593313217163086} 08/31/2021 09:14:29 - INFO - __main__ - Step 110356: {'lr': 8.342183482506713e-05, 'samples': 21188352, 'steps': 110355, 'loss/train': 1.3978675603866577} 08/31/2021 09:14:31 - INFO - __main__ - Step 110357: {'lr': 8.34178777694109e-05, 'samples': 21188544, 'steps': 110356, 'loss/train': 1.1235315799713135} 08/31/2021 09:14:31 - INFO - __main__ - Step 110358: {'lr': 8.3413920788814e-05, 'samples': 21188736, 'steps': 110357, 'loss/train': 1.1076949834823608} 08/31/2021 09:14:31 - INFO - __main__ - Step 110359: {'lr': 8.340996388327823e-05, 'samples': 21188928, 'steps': 110358, 'loss/train': 1.1070842742919922} 08/31/2021 09:14:32 - INFO - __main__ - Step 110360: {'lr': 8.340600705280544e-05, 'samples': 21189120, 'steps': 110359, 'loss/train': 0.7985886931419373} 08/31/2021 09:14:32 - INFO - __main__ - Step 110361: {'lr': 8.340205029739725e-05, 'samples': 21189312, 'steps': 110360, 'loss/train': 1.773962378501892} 08/31/2021 09:14:34 - INFO - __main__ - Step 110362: {'lr': 8.339809361705553e-05, 'samples': 21189504, 'steps': 110361, 'loss/train': 1.351648211479187} 08/31/2021 09:14:34 - INFO - __main__ - Step 110363: {'lr': 8.339413701178206e-05, 'samples': 21189696, 'steps': 110362, 'loss/train': 1.2600903511047363} 08/31/2021 09:14:34 - INFO - __main__ - Step 110364: {'lr': 8.339018048157859e-05, 'samples': 21189888, 'steps': 110363, 'loss/train': 0.10241975635290146} 08/31/2021 09:14:35 - INFO - __main__ - Step 110365: {'lr': 8.338622402644696e-05, 'samples': 21190080, 'steps': 110364, 'loss/train': 1.493162989616394} 08/31/2021 09:14:35 - INFO - __main__ - Step 110366: {'lr': 8.338226764638892e-05, 'samples': 21190272, 'steps': 110365, 'loss/train': 0.6878131031990051} 08/31/2021 09:14:37 - INFO - __main__ - Step 110367: {'lr': 8.337831134140628e-05, 'samples': 21190464, 'steps': 110366, 'loss/train': 0.9414005279541016} 08/31/2021 09:14:37 - INFO - __main__ - Step 110368: {'lr': 8.337435511150077e-05, 'samples': 21190656, 'steps': 110367, 'loss/train': 1.0154094696044922} 08/31/2021 09:14:37 - INFO - __main__ - Step 110369: {'lr': 8.337039895667423e-05, 'samples': 21190848, 'steps': 110368, 'loss/train': 1.5252188444137573} 08/31/2021 09:14:38 - INFO - __main__ - Step 110370: {'lr': 8.336644287692841e-05, 'samples': 21191040, 'steps': 110369, 'loss/train': 0.9140191674232483} 08/31/2021 09:14:38 - INFO - __main__ - Step 110371: {'lr': 8.336248687226508e-05, 'samples': 21191232, 'steps': 110370, 'loss/train': 1.4110772609710693} 08/31/2021 09:14:38 - INFO - __main__ - Step 110372: {'lr': 8.335853094268605e-05, 'samples': 21191424, 'steps': 110371, 'loss/train': 1.8494681119918823} 08/31/2021 09:14:40 - INFO - __main__ - Step 110373: {'lr': 8.335457508819319e-05, 'samples': 21191616, 'steps': 110372, 'loss/train': 1.1561511754989624} 08/31/2021 09:14:40 - INFO - __main__ - Step 110374: {'lr': 8.33506193087881e-05, 'samples': 21191808, 'steps': 110373, 'loss/train': 1.5474927425384521} 08/31/2021 09:14:41 - INFO - __main__ - Step 110375: {'lr': 8.334666360447265e-05, 'samples': 21192000, 'steps': 110374, 'loss/train': 1.376940131187439} 08/31/2021 09:14:41 - INFO - __main__ - Step 110376: {'lr': 8.334270797524862e-05, 'samples': 21192192, 'steps': 110375, 'loss/train': 1.4031243324279785} 08/31/2021 09:14:42 - INFO - __main__ - Step 110377: {'lr': 8.33387524211178e-05, 'samples': 21192384, 'steps': 110376, 'loss/train': 1.433923602104187} 08/31/2021 09:14:43 - INFO - __main__ - Step 110378: {'lr': 8.333479694208196e-05, 'samples': 21192576, 'steps': 110377, 'loss/train': 0.5079748630523682} 08/31/2021 09:14:43 - INFO - __main__ - Step 110379: {'lr': 8.333084153814288e-05, 'samples': 21192768, 'steps': 110378, 'loss/train': 0.9934008717536926} 08/31/2021 09:14:44 - INFO - __main__ - Step 110380: {'lr': 8.332688620930237e-05, 'samples': 21192960, 'steps': 110379, 'loss/train': 0.33086833357810974} 08/31/2021 09:14:44 - INFO - __main__ - Step 110381: {'lr': 8.332293095556218e-05, 'samples': 21193152, 'steps': 110380, 'loss/train': 0.8612865805625916} 08/31/2021 09:14:44 - INFO - __main__ - Step 110382: {'lr': 8.33189757769241e-05, 'samples': 21193344, 'steps': 110381, 'loss/train': 0.7522097826004028} 08/31/2021 09:14:47 - INFO - __main__ - Step 110383: {'lr': 8.331502067338995e-05, 'samples': 21193536, 'steps': 110382, 'loss/train': 0.1888190060853958} 08/31/2021 09:14:47 - INFO - __main__ - Step 110384: {'lr': 8.331106564496143e-05, 'samples': 21193728, 'steps': 110383, 'loss/train': 1.5724819898605347} 08/31/2021 09:14:47 - INFO - __main__ - Step 110385: {'lr': 8.33071106916404e-05, 'samples': 21193920, 'steps': 110384, 'loss/train': 0.755912184715271} 08/31/2021 09:14:48 - INFO - __main__ - Step 110386: {'lr': 8.33031558134287e-05, 'samples': 21194112, 'steps': 110385, 'loss/train': 2.9992823600769043} 08/31/2021 09:14:48 - INFO - __main__ - Step 110387: {'lr': 8.329920101032795e-05, 'samples': 21194304, 'steps': 110386, 'loss/train': 0.870886504650116} 08/31/2021 09:14:50 - INFO - __main__ - Step 110388: {'lr': 8.329524628233998e-05, 'samples': 21194496, 'steps': 110387, 'loss/train': 0.9379371404647827} 08/31/2021 09:14:50 - INFO - __main__ - Step 110389: {'lr': 8.329129162946661e-05, 'samples': 21194688, 'steps': 110388, 'loss/train': 0.6045657396316528} 08/31/2021 09:14:50 - INFO - __main__ - Step 110390: {'lr': 8.328733705170963e-05, 'samples': 21194880, 'steps': 110389, 'loss/train': 1.53045654296875} 08/31/2021 09:14:51 - INFO - __main__ - Step 110391: {'lr': 8.328338254907079e-05, 'samples': 21195072, 'steps': 110390, 'loss/train': 0.980110228061676} 08/31/2021 09:14:51 - INFO - __main__ - Step 110392: {'lr': 8.327942812155187e-05, 'samples': 21195264, 'steps': 110391, 'loss/train': 0.80091392993927} 08/31/2021 09:14:53 - INFO - __main__ - Step 110393: {'lr': 8.32754737691547e-05, 'samples': 21195456, 'steps': 110392, 'loss/train': 1.4385201930999756} 08/31/2021 09:14:53 - INFO - __main__ - Step 110394: {'lr': 8.3271519491881e-05, 'samples': 21195648, 'steps': 110393, 'loss/train': 0.7767798900604248} 08/31/2021 09:14:53 - INFO - __main__ - Step 110395: {'lr': 8.326756528973259e-05, 'samples': 21195840, 'steps': 110394, 'loss/train': 1.6263662576675415} 08/31/2021 09:14:54 - INFO - __main__ - Step 110396: {'lr': 8.326361116271125e-05, 'samples': 21196032, 'steps': 110395, 'loss/train': 1.015209436416626} 08/31/2021 09:14:54 - INFO - __main__ - Step 110397: {'lr': 8.325965711081873e-05, 'samples': 21196224, 'steps': 110396, 'loss/train': 1.1402528285980225} 08/31/2021 09:14:54 - INFO - __main__ - Step 110398: {'lr': 8.325570313405687e-05, 'samples': 21196416, 'steps': 110397, 'loss/train': 1.200976014137268} 08/31/2021 09:14:56 - INFO - __main__ - Step 110399: {'lr': 8.32517492324274e-05, 'samples': 21196608, 'steps': 110398, 'loss/train': 1.656553030014038} 08/31/2021 09:14:56 - INFO - __main__ - Step 110400: {'lr': 8.32477954059322e-05, 'samples': 21196800, 'steps': 110399, 'loss/train': 1.1626805067062378} 08/31/2021 09:14:57 - INFO - __main__ - Step 110401: {'lr': 8.324384165457289e-05, 'samples': 21196992, 'steps': 110400, 'loss/train': 1.268149733543396} 08/31/2021 09:14:57 - INFO - __main__ - Step 110402: {'lr': 8.323988797835132e-05, 'samples': 21197184, 'steps': 110401, 'loss/train': 1.0571953058242798} 08/31/2021 09:14:57 - INFO - __main__ - Step 110403: {'lr': 8.323593437726928e-05, 'samples': 21197376, 'steps': 110402, 'loss/train': 1.2790488004684448} 08/31/2021 09:14:59 - INFO - __main__ - Step 110404: {'lr': 8.323198085132857e-05, 'samples': 21197568, 'steps': 110403, 'loss/train': 1.4042448997497559} 08/31/2021 09:14:59 - INFO - __main__ - Step 110405: {'lr': 8.322802740053098e-05, 'samples': 21197760, 'steps': 110404, 'loss/train': 0.6010589599609375} 08/31/2021 09:15:00 - INFO - __main__ - Step 110406: {'lr': 8.322407402487822e-05, 'samples': 21197952, 'steps': 110405, 'loss/train': 1.2669639587402344} 08/31/2021 09:15:00 - INFO - __main__ - Step 110407: {'lr': 8.322012072437216e-05, 'samples': 21198144, 'steps': 110406, 'loss/train': 1.0130378007888794} 08/31/2021 09:15:01 - INFO - __main__ - Step 110408: {'lr': 8.32161674990145e-05, 'samples': 21198336, 'steps': 110407, 'loss/train': 1.0856436491012573} 08/31/2021 09:15:02 - INFO - __main__ - Step 110409: {'lr': 8.32122143488071e-05, 'samples': 21198528, 'steps': 110408, 'loss/train': 1.2159761190414429} 08/31/2021 09:15:02 - INFO - __main__ - Step 110410: {'lr': 8.320826127375166e-05, 'samples': 21198720, 'steps': 110409, 'loss/train': 1.4451239109039307} 08/31/2021 09:15:03 - INFO - __main__ - Step 110411: {'lr': 8.320430827385004e-05, 'samples': 21198912, 'steps': 110410, 'loss/train': 0.9988259077072144} 08/31/2021 09:15:03 - INFO - __main__ - Step 110412: {'lr': 8.320035534910397e-05, 'samples': 21199104, 'steps': 110411, 'loss/train': 0.7612143158912659} 08/31/2021 09:15:03 - INFO - __main__ - Step 110413: {'lr': 8.319640249951535e-05, 'samples': 21199296, 'steps': 110412, 'loss/train': 0.16291488707065582} 08/31/2021 09:15:05 - INFO - __main__ - Step 110414: {'lr': 8.319244972508574e-05, 'samples': 21199488, 'steps': 110413, 'loss/train': 0.26073330640792847} 08/31/2021 09:15:05 - INFO - __main__ - Step 110415: {'lr': 8.318849702581707e-05, 'samples': 21199680, 'steps': 110414, 'loss/train': 0.4955151081085205} 08/31/2021 09:15:06 - INFO - __main__ - Step 110416: {'lr': 8.318454440171106e-05, 'samples': 21199872, 'steps': 110415, 'loss/train': 1.3735575675964355} 08/31/2021 09:15:06 - INFO - __main__ - Step 110417: {'lr': 8.318059185276955e-05, 'samples': 21200064, 'steps': 110416, 'loss/train': 0.6917718648910522} 08/31/2021 09:15:06 - INFO - __main__ - Step 110418: {'lr': 8.317663937899425e-05, 'samples': 21200256, 'steps': 110417, 'loss/train': 1.1745103597640991} 08/31/2021 09:15:08 - INFO - __main__ - Step 110419: {'lr': 8.317268698038701e-05, 'samples': 21200448, 'steps': 110418, 'loss/train': 0.9803110957145691} 08/31/2021 09:15:09 - INFO - __main__ - Step 110420: {'lr': 8.316873465694957e-05, 'samples': 21200640, 'steps': 110419, 'loss/train': 0.34999731183052063} 08/31/2021 09:15:09 - INFO - __main__ - Step 110421: {'lr': 8.316478240868375e-05, 'samples': 21200832, 'steps': 110420, 'loss/train': 1.1415371894836426} 08/31/2021 09:15:09 - INFO - __main__ - Step 110422: {'lr': 8.316083023559129e-05, 'samples': 21201024, 'steps': 110421, 'loss/train': 0.835554301738739} 08/31/2021 09:15:10 - INFO - __main__ - Step 110423: {'lr': 8.315687813767397e-05, 'samples': 21201216, 'steps': 110422, 'loss/train': 1.2854360342025757} 08/31/2021 09:15:11 - INFO - __main__ - Step 110424: {'lr': 8.315292611493361e-05, 'samples': 21201408, 'steps': 110423, 'loss/train': 1.2008639574050903} 08/31/2021 09:15:12 - INFO - __main__ - Step 110425: {'lr': 8.314897416737197e-05, 'samples': 21201600, 'steps': 110424, 'loss/train': 1.2082278728485107} 08/31/2021 09:15:12 - INFO - __main__ - Step 110426: {'lr': 8.31450222949908e-05, 'samples': 21201792, 'steps': 110425, 'loss/train': 0.9941827654838562} 08/31/2021 09:15:13 - INFO - __main__ - Step 110427: {'lr': 8.314107049779202e-05, 'samples': 21201984, 'steps': 110426, 'loss/train': 1.53451406955719} 08/31/2021 09:15:13 - INFO - __main__ - Step 110428: {'lr': 8.313711877577718e-05, 'samples': 21202176, 'steps': 110427, 'loss/train': 1.6300030946731567} 08/31/2021 09:15:13 - INFO - __main__ - Step 110429: {'lr': 8.313316712894819e-05, 'samples': 21202368, 'steps': 110428, 'loss/train': 1.0859242677688599} 08/31/2021 09:15:15 - INFO - __main__ - Step 110430: {'lr': 8.312921555730685e-05, 'samples': 21202560, 'steps': 110429, 'loss/train': 1.245369553565979} 08/31/2021 09:15:15 - INFO - __main__ - Step 110431: {'lr': 8.312526406085489e-05, 'samples': 21202752, 'steps': 110430, 'loss/train': 1.248199462890625} 08/31/2021 09:15:16 - INFO - __main__ - Step 110432: {'lr': 8.312131263959411e-05, 'samples': 21202944, 'steps': 110431, 'loss/train': 1.1162469387054443} 08/31/2021 09:15:16 - INFO - __main__ - Step 110433: {'lr': 8.311736129352629e-05, 'samples': 21203136, 'steps': 110432, 'loss/train': 1.2586673498153687} 08/31/2021 09:15:16 - INFO - __main__ - Step 110434: {'lr': 8.311341002265322e-05, 'samples': 21203328, 'steps': 110433, 'loss/train': 0.8352304697036743} 08/31/2021 09:15:18 - INFO - __main__ - Step 110435: {'lr': 8.310945882697665e-05, 'samples': 21203520, 'steps': 110434, 'loss/train': 0.9788040518760681} 08/31/2021 09:15:19 - INFO - __main__ - Step 110436: {'lr': 8.310550770649841e-05, 'samples': 21203712, 'steps': 110435, 'loss/train': 1.2445508241653442} 08/31/2021 09:15:19 - INFO - __main__ - Step 110437: {'lr': 8.310155666122032e-05, 'samples': 21203904, 'steps': 110436, 'loss/train': 0.728513240814209} 08/31/2021 09:15:19 - INFO - __main__ - Step 110438: {'lr': 8.309760569114403e-05, 'samples': 21204096, 'steps': 110437, 'loss/train': 1.2875014543533325} 08/31/2021 09:15:20 - INFO - __main__ - Step 110439: {'lr': 8.309365479627138e-05, 'samples': 21204288, 'steps': 110438, 'loss/train': 1.5235700607299805} 08/31/2021 09:15:22 - INFO - __main__ - Step 110440: {'lr': 8.308970397660412e-05, 'samples': 21204480, 'steps': 110439, 'loss/train': 1.2129547595977783} 08/31/2021 09:15:22 - INFO - __main__ - Step 110441: {'lr': 8.308575323214409e-05, 'samples': 21204672, 'steps': 110440, 'loss/train': 0.016046613454818726} 08/31/2021 09:15:22 - INFO - __main__ - Step 110442: {'lr': 8.308180256289306e-05, 'samples': 21204864, 'steps': 110441, 'loss/train': 1.0029138326644897} 08/31/2021 09:15:23 - INFO - __main__ - Step 110443: {'lr': 8.307785196885276e-05, 'samples': 21205056, 'steps': 110442, 'loss/train': 1.4938777685165405} 08/31/2021 09:15:23 - INFO - __main__ - Step 110444: {'lr': 8.307390145002503e-05, 'samples': 21205248, 'steps': 110443, 'loss/train': 0.09851863980293274} 08/31/2021 09:15:24 - INFO - __main__ - Step 110445: {'lr': 8.30699510064116e-05, 'samples': 21205440, 'steps': 110444, 'loss/train': 1.2722821235656738} 08/31/2021 09:15:25 - INFO - __main__ - Step 110446: {'lr': 8.306600063801428e-05, 'samples': 21205632, 'steps': 110445, 'loss/train': 0.26223188638687134} 08/31/2021 09:15:25 - INFO - __main__ - Step 110447: {'lr': 8.306205034483485e-05, 'samples': 21205824, 'steps': 110446, 'loss/train': 1.1722111701965332} 08/31/2021 09:15:26 - INFO - __main__ - Step 110448: {'lr': 8.305810012687518e-05, 'samples': 21206016, 'steps': 110447, 'loss/train': 0.8097697496414185} 08/31/2021 09:15:26 - INFO - __main__ - Step 110449: {'lr': 8.305414998413685e-05, 'samples': 21206208, 'steps': 110448, 'loss/train': 1.0909318923950195} 08/31/2021 09:15:27 - INFO - __main__ - Step 110450: {'lr': 8.305019991662178e-05, 'samples': 21206400, 'steps': 110449, 'loss/train': 1.5876853466033936} 08/31/2021 09:15:28 - INFO - __main__ - Step 110451: {'lr': 8.304624992433168e-05, 'samples': 21206592, 'steps': 110450, 'loss/train': 0.5703641176223755} 08/31/2021 09:15:28 - INFO - __main__ - Step 110452: {'lr': 8.304230000726837e-05, 'samples': 21206784, 'steps': 110451, 'loss/train': 1.0629888772964478} 08/31/2021 09:15:29 - INFO - __main__ - Step 110453: {'lr': 8.303835016543362e-05, 'samples': 21206976, 'steps': 110452, 'loss/train': 0.9003155827522278} 08/31/2021 09:15:29 - INFO - __main__ - Step 110454: {'lr': 8.30344003988292e-05, 'samples': 21207168, 'steps': 110453, 'loss/train': 0.8827896118164062} 08/31/2021 09:15:29 - INFO - __main__ - Step 110455: {'lr': 8.303045070745693e-05, 'samples': 21207360, 'steps': 110454, 'loss/train': 1.2914466857910156} 08/31/2021 09:15:31 - INFO - __main__ - Step 110456: {'lr': 8.302650109131857e-05, 'samples': 21207552, 'steps': 110455, 'loss/train': 1.073833703994751} 08/31/2021 09:15:31 - INFO - __main__ - Step 110457: {'lr': 8.302255155041586e-05, 'samples': 21207744, 'steps': 110456, 'loss/train': 1.4182926416397095} 08/31/2021 09:15:32 - INFO - __main__ - Step 110458: {'lr': 8.301860208475062e-05, 'samples': 21207936, 'steps': 110457, 'loss/train': 1.1460891962051392} 08/31/2021 09:15:32 - INFO - __main__ - Step 110459: {'lr': 8.301465269432471e-05, 'samples': 21208128, 'steps': 110458, 'loss/train': 1.0130823850631714} 08/31/2021 09:15:32 - INFO - __main__ - Step 110460: {'lr': 8.301070337913974e-05, 'samples': 21208320, 'steps': 110459, 'loss/train': 1.0351831912994385} 08/31/2021 09:15:34 - INFO - __main__ - Step 110461: {'lr': 8.300675413919757e-05, 'samples': 21208512, 'steps': 110460, 'loss/train': 0.46602922677993774} 08/31/2021 09:15:35 - INFO - __main__ - Step 110462: {'lr': 8.300280497449997e-05, 'samples': 21208704, 'steps': 110461, 'loss/train': 1.9766895771026611} 08/31/2021 09:15:35 - INFO - __main__ - Step 110463: {'lr': 8.299885588504874e-05, 'samples': 21208896, 'steps': 110462, 'loss/train': 0.8428918123245239} 08/31/2021 09:15:35 - INFO - __main__ - Step 110464: {'lr': 8.299490687084566e-05, 'samples': 21209088, 'steps': 110463, 'loss/train': 0.38605159521102905} 08/31/2021 09:15:36 - INFO - __main__ - Step 110465: {'lr': 8.299095793189249e-05, 'samples': 21209280, 'steps': 110464, 'loss/train': 1.5637884140014648} 08/31/2021 09:15:37 - INFO - __main__ - Step 110466: {'lr': 8.2987009068191e-05, 'samples': 21209472, 'steps': 110465, 'loss/train': 0.759787917137146} 08/31/2021 09:15:38 - INFO - __main__ - Step 110467: {'lr': 8.2983060279743e-05, 'samples': 21209664, 'steps': 110466, 'loss/train': 1.326547622680664} 08/31/2021 09:15:38 - INFO - __main__ - Step 110468: {'lr': 8.297911156655025e-05, 'samples': 21209856, 'steps': 110467, 'loss/train': 0.7541279792785645} 08/31/2021 09:15:38 - INFO - __main__ - Step 110469: {'lr': 8.297516292861454e-05, 'samples': 21210048, 'steps': 110468, 'loss/train': 1.6157763004302979} 08/31/2021 09:15:39 - INFO - __main__ - Step 110470: {'lr': 8.297121436593771e-05, 'samples': 21210240, 'steps': 110469, 'loss/train': 1.4344630241394043} 08/31/2021 09:15:39 - INFO - __main__ - Step 110471: {'lr': 8.296726587852141e-05, 'samples': 21210432, 'steps': 110470, 'loss/train': 1.5288755893707275} 08/31/2021 09:15:41 - INFO - __main__ - Step 110472: {'lr': 8.296331746636748e-05, 'samples': 21210624, 'steps': 110471, 'loss/train': 0.8303515315055847} 08/31/2021 09:15:41 - INFO - __main__ - Step 110473: {'lr': 8.295936912947772e-05, 'samples': 21210816, 'steps': 110472, 'loss/train': 1.433297872543335} 08/31/2021 09:15:42 - INFO - __main__ - Step 110474: {'lr': 8.295542086785385e-05, 'samples': 21211008, 'steps': 110473, 'loss/train': 0.4396393895149231} 08/31/2021 09:15:42 - INFO - __main__ - Step 110475: {'lr': 8.295147268149772e-05, 'samples': 21211200, 'steps': 110474, 'loss/train': 0.028118321672081947} 08/31/2021 09:15:42 - INFO - __main__ - Step 110476: {'lr': 8.294752457041108e-05, 'samples': 21211392, 'steps': 110475, 'loss/train': 0.024497821927070618} 08/31/2021 09:15:44 - INFO - __main__ - Step 110477: {'lr': 8.29435765345957e-05, 'samples': 21211584, 'steps': 110476, 'loss/train': 0.09186863899230957} 08/31/2021 09:15:44 - INFO - __main__ - Step 110478: {'lr': 8.293962857405335e-05, 'samples': 21211776, 'steps': 110477, 'loss/train': 0.9474096894264221} 08/31/2021 09:15:45 - INFO - __main__ - Step 110479: {'lr': 8.293568068878585e-05, 'samples': 21211968, 'steps': 110478, 'loss/train': 0.47584912180900574} 08/31/2021 09:15:45 - INFO - __main__ - Step 110480: {'lr': 8.293173287879493e-05, 'samples': 21212160, 'steps': 110479, 'loss/train': 1.1322507858276367} 08/31/2021 09:15:45 - INFO - __main__ - Step 110481: {'lr': 8.292778514408251e-05, 'samples': 21212352, 'steps': 110480, 'loss/train': 1.630962610244751} 08/31/2021 09:15:47 - INFO - __main__ - Step 110482: {'lr': 8.292383748465013e-05, 'samples': 21212544, 'steps': 110481, 'loss/train': 0.7024258971214294} 08/31/2021 09:15:47 - INFO - __main__ - Step 110483: {'lr': 8.29198899004997e-05, 'samples': 21212736, 'steps': 110482, 'loss/train': 1.3335201740264893} 08/31/2021 09:15:48 - INFO - __main__ - Step 110484: {'lr': 8.291594239163299e-05, 'samples': 21212928, 'steps': 110483, 'loss/train': 0.9296233654022217} 08/31/2021 09:15:48 - INFO - __main__ - Step 110485: {'lr': 8.29119949580518e-05, 'samples': 21213120, 'steps': 110484, 'loss/train': 0.576898992061615} 08/31/2021 09:15:48 - INFO - __main__ - Step 110486: {'lr': 8.290804759975788e-05, 'samples': 21213312, 'steps': 110485, 'loss/train': 1.1112971305847168} 08/31/2021 09:15:51 - INFO - __main__ - Step 110487: {'lr': 8.2904100316753e-05, 'samples': 21213504, 'steps': 110486, 'loss/train': 0.9119216203689575} 08/31/2021 09:15:51 - INFO - __main__ - Step 110488: {'lr': 8.290015310903895e-05, 'samples': 21213696, 'steps': 110487, 'loss/train': 1.3532352447509766} 08/31/2021 09:15:51 - INFO - __main__ - Step 110489: {'lr': 8.289620597661754e-05, 'samples': 21213888, 'steps': 110488, 'loss/train': 0.8774339556694031} 08/31/2021 09:15:52 - INFO - __main__ - Step 110490: {'lr': 8.289225891949051e-05, 'samples': 21214080, 'steps': 110489, 'loss/train': 0.04917477071285248} 08/31/2021 09:15:52 - INFO - __main__ - Step 110491: {'lr': 8.288831193765963e-05, 'samples': 21214272, 'steps': 110490, 'loss/train': 1.2330102920532227} 08/31/2021 09:15:52 - INFO - __main__ - Step 110492: {'lr': 8.288436503112673e-05, 'samples': 21214464, 'steps': 110491, 'loss/train': 0.7543315887451172} 08/31/2021 09:15:55 - INFO - __main__ - Step 110493: {'lr': 8.288041819989353e-05, 'samples': 21214656, 'steps': 110492, 'loss/train': 1.3937225341796875} 08/31/2021 09:15:55 - INFO - __main__ - Step 110494: {'lr': 8.287647144396194e-05, 'samples': 21214848, 'steps': 110493, 'loss/train': 1.097474217414856} 08/31/2021 09:15:56 - INFO - __main__ - Step 110495: {'lr': 8.287252476333354e-05, 'samples': 21215040, 'steps': 110494, 'loss/train': 1.1316674947738647} 08/31/2021 09:15:56 - INFO - __main__ - Step 110496: {'lr': 8.286857815801019e-05, 'samples': 21215232, 'steps': 110495, 'loss/train': 2.0432918071746826} 08/31/2021 09:15:56 - INFO - __main__ - Step 110497: {'lr': 8.286463162799368e-05, 'samples': 21215424, 'steps': 110496, 'loss/train': 0.3304787576198578} 08/31/2021 09:15:57 - INFO - __main__ - Step 110498: {'lr': 8.286068517328579e-05, 'samples': 21215616, 'steps': 110497, 'loss/train': 0.2934083342552185} 08/31/2021 09:15:58 - INFO - __main__ - Step 110499: {'lr': 8.28567387938883e-05, 'samples': 21215808, 'steps': 110498, 'loss/train': 0.2957610487937927} 08/31/2021 09:15:59 - INFO - __main__ - Step 110500: {'lr': 8.285279248980301e-05, 'samples': 21216000, 'steps': 110499, 'loss/train': 0.04837602749466896} 08/31/2021 09:15:59 - INFO - __main__ - Step 110501: {'lr': 8.284884626103165e-05, 'samples': 21216192, 'steps': 110500, 'loss/train': 0.09279219806194305} 08/31/2021 09:16:00 - INFO - __main__ - Step 110502: {'lr': 8.284490010757601e-05, 'samples': 21216384, 'steps': 110501, 'loss/train': 1.5391980409622192} 08/31/2021 09:16:00 - INFO - __main__ - Step 110503: {'lr': 8.284095402943789e-05, 'samples': 21216576, 'steps': 110502, 'loss/train': 0.6611798405647278} 08/31/2021 09:16:01 - INFO - __main__ - Step 110504: {'lr': 8.283700802661906e-05, 'samples': 21216768, 'steps': 110503, 'loss/train': 1.161010503768921} 08/31/2021 09:16:02 - INFO - __main__ - Step 110505: {'lr': 8.283306209912128e-05, 'samples': 21216960, 'steps': 110504, 'loss/train': 1.168933391571045} 08/31/2021 09:16:02 - INFO - __main__ - Step 110506: {'lr': 8.282911624694636e-05, 'samples': 21217152, 'steps': 110505, 'loss/train': 0.6866249442100525} 08/31/2021 09:16:03 - INFO - __main__ - Step 110507: {'lr': 8.282517047009614e-05, 'samples': 21217344, 'steps': 110506, 'loss/train': 1.2419006824493408} 08/31/2021 09:16:03 - INFO - __main__ - Step 110508: {'lr': 8.282122476857223e-05, 'samples': 21217536, 'steps': 110507, 'loss/train': 0.516676664352417} 08/31/2021 09:16:03 - INFO - __main__ - Step 110509: {'lr': 8.28172791423765e-05, 'samples': 21217728, 'steps': 110508, 'loss/train': 1.2853846549987793} 08/31/2021 09:16:05 - INFO - __main__ - Step 110510: {'lr': 8.281333359151072e-05, 'samples': 21217920, 'steps': 110509, 'loss/train': 1.3967149257659912} 08/31/2021 09:16:06 - INFO - __main__ - Step 110511: {'lr': 8.280938811597668e-05, 'samples': 21218112, 'steps': 110510, 'loss/train': 1.8190072774887085} 08/31/2021 09:16:06 - INFO - __main__ - Step 110512: {'lr': 8.280544271577614e-05, 'samples': 21218304, 'steps': 110511, 'loss/train': 1.4930614233016968} 08/31/2021 09:16:06 - INFO - __main__ - Step 110513: {'lr': 8.280149739091088e-05, 'samples': 21218496, 'steps': 110512, 'loss/train': 2.333293914794922} 08/31/2021 09:16:07 - INFO - __main__ - Step 110514: {'lr': 8.27975521413827e-05, 'samples': 21218688, 'steps': 110513, 'loss/train': 0.9502056837081909} 08/31/2021 09:16:07 - INFO - __main__ - Step 110515: {'lr': 8.279360696719338e-05, 'samples': 21218880, 'steps': 110514, 'loss/train': 0.017916690558195114} 08/31/2021 09:16:09 - INFO - __main__ - Step 110516: {'lr': 8.278966186834463e-05, 'samples': 21219072, 'steps': 110515, 'loss/train': 0.2750718593597412} 08/31/2021 09:16:09 - INFO - __main__ - Step 110517: {'lr': 8.278571684483832e-05, 'samples': 21219264, 'steps': 110516, 'loss/train': 0.8412613272666931} 08/31/2021 09:16:09 - INFO - __main__ - Step 110518: {'lr': 8.278177189667618e-05, 'samples': 21219456, 'steps': 110517, 'loss/train': 0.6836323142051697} 08/31/2021 09:16:10 - INFO - __main__ - Step 110519: {'lr': 8.277782702386e-05, 'samples': 21219648, 'steps': 110518, 'loss/train': 0.6504911184310913} 08/31/2021 09:16:10 - INFO - __main__ - Step 110520: {'lr': 8.277388222639154e-05, 'samples': 21219840, 'steps': 110519, 'loss/train': 1.059980034828186} 08/31/2021 09:16:12 - INFO - __main__ - Step 110521: {'lr': 8.276993750427267e-05, 'samples': 21220032, 'steps': 110520, 'loss/train': 0.8003405928611755} 08/31/2021 09:16:12 - INFO - __main__ - Step 110522: {'lr': 8.276599285750499e-05, 'samples': 21220224, 'steps': 110521, 'loss/train': 0.6296658515930176} 08/31/2021 09:16:13 - INFO - __main__ - Step 110523: {'lr': 8.276204828609038e-05, 'samples': 21220416, 'steps': 110522, 'loss/train': 1.0411136150360107} 08/31/2021 09:16:13 - INFO - __main__ - Step 110524: {'lr': 8.275810379003063e-05, 'samples': 21220608, 'steps': 110523, 'loss/train': 0.043665796518325806} 08/31/2021 09:16:13 - INFO - __main__ - Step 110525: {'lr': 8.275415936932748e-05, 'samples': 21220800, 'steps': 110524, 'loss/train': 0.062393248081207275} 08/31/2021 09:16:15 - INFO - __main__ - Step 110526: {'lr': 8.275021502398273e-05, 'samples': 21220992, 'steps': 110525, 'loss/train': 0.38029950857162476} 08/31/2021 09:16:15 - INFO - __main__ - Step 110527: {'lr': 8.274627075399816e-05, 'samples': 21221184, 'steps': 110526, 'loss/train': 1.1792253255844116} 08/31/2021 09:16:16 - INFO - __main__ - Step 110528: {'lr': 8.274232655937553e-05, 'samples': 21221376, 'steps': 110527, 'loss/train': 1.1540002822875977} 08/31/2021 09:16:16 - INFO - __main__ - Step 110529: {'lr': 8.273838244011661e-05, 'samples': 21221568, 'steps': 110528, 'loss/train': 1.0579495429992676} 08/31/2021 09:16:16 - INFO - __main__ - Step 110530: {'lr': 8.273443839622321e-05, 'samples': 21221760, 'steps': 110529, 'loss/train': 1.0819108486175537} 08/31/2021 09:16:18 - INFO - __main__ - Step 110531: {'lr': 8.273049442769708e-05, 'samples': 21221952, 'steps': 110530, 'loss/train': 0.8995676040649414} 08/31/2021 09:16:18 - INFO - __main__ - Step 110532: {'lr': 8.272655053454004e-05, 'samples': 21222144, 'steps': 110531, 'loss/train': 1.2802683115005493} 08/31/2021 09:16:19 - INFO - __main__ - Step 110533: {'lr': 8.272260671675381e-05, 'samples': 21222336, 'steps': 110532, 'loss/train': 1.0378369092941284} 08/31/2021 09:16:19 - INFO - __main__ - Step 110534: {'lr': 8.271866297434028e-05, 'samples': 21222528, 'steps': 110533, 'loss/train': 1.3244059085845947} 08/31/2021 09:16:19 - INFO - __main__ - Step 110535: {'lr': 8.271471930730107e-05, 'samples': 21222720, 'steps': 110534, 'loss/train': 1.112743854522705} 08/31/2021 09:16:21 - INFO - __main__ - Step 110536: {'lr': 8.2710775715638e-05, 'samples': 21222912, 'steps': 110535, 'loss/train': 0.9328434467315674} 08/31/2021 09:16:21 - INFO - __main__ - Step 110537: {'lr': 8.270683219935288e-05, 'samples': 21223104, 'steps': 110536, 'loss/train': 1.3563215732574463} 08/31/2021 09:16:22 - INFO - __main__ - Step 110538: {'lr': 8.27028887584475e-05, 'samples': 21223296, 'steps': 110537, 'loss/train': 1.026795744895935} 08/31/2021 09:16:22 - INFO - __main__ - Step 110539: {'lr': 8.269894539292361e-05, 'samples': 21223488, 'steps': 110538, 'loss/train': 1.3149769306182861} 08/31/2021 09:16:22 - INFO - __main__ - Step 110540: {'lr': 8.269500210278296e-05, 'samples': 21223680, 'steps': 110539, 'loss/train': 1.3784679174423218} 08/31/2021 09:16:24 - INFO - __main__ - Step 110541: {'lr': 8.269105888802739e-05, 'samples': 21223872, 'steps': 110540, 'loss/train': 1.0653194189071655} 08/31/2021 09:16:25 - INFO - __main__ - Step 110542: {'lr': 8.268711574865864e-05, 'samples': 21224064, 'steps': 110541, 'loss/train': 1.243670105934143} 08/31/2021 09:16:25 - INFO - __main__ - Step 110543: {'lr': 8.268317268467851e-05, 'samples': 21224256, 'steps': 110542, 'loss/train': 1.2520474195480347} 08/31/2021 09:16:25 - INFO - __main__ - Step 110544: {'lr': 8.267922969608874e-05, 'samples': 21224448, 'steps': 110543, 'loss/train': 0.056561607867479324} 08/31/2021 09:16:26 - INFO - __main__ - Step 110545: {'lr': 8.267528678289113e-05, 'samples': 21224640, 'steps': 110544, 'loss/train': 2.08194637298584} 08/31/2021 09:16:28 - INFO - __main__ - Step 110546: {'lr': 8.267134394508747e-05, 'samples': 21224832, 'steps': 110545, 'loss/train': 1.47121000289917} 08/31/2021 09:16:28 - INFO - __main__ - Step 110547: {'lr': 8.266740118267951e-05, 'samples': 21225024, 'steps': 110546, 'loss/train': 1.4578804969787598} 08/31/2021 09:16:29 - INFO - __main__ - Step 110548: {'lr': 8.266345849566912e-05, 'samples': 21225216, 'steps': 110547, 'loss/train': 1.201784372329712} 08/31/2021 09:16:29 - INFO - __main__ - Step 110549: {'lr': 8.265951588405791e-05, 'samples': 21225408, 'steps': 110548, 'loss/train': 1.6070148944854736} 08/31/2021 09:16:29 - INFO - __main__ - Step 110550: {'lr': 8.265557334784773e-05, 'samples': 21225600, 'steps': 110549, 'loss/train': 1.4564915895462036} 08/31/2021 09:16:31 - INFO - __main__ - Step 110551: {'lr': 8.26516308870404e-05, 'samples': 21225792, 'steps': 110550, 'loss/train': 1.497117042541504} 08/31/2021 09:16:32 - INFO - __main__ - Step 110552: {'lr': 8.264768850163762e-05, 'samples': 21225984, 'steps': 110551, 'loss/train': 1.9421314001083374} 08/31/2021 09:16:32 - INFO - __main__ - Step 110553: {'lr': 8.264374619164122e-05, 'samples': 21226176, 'steps': 110552, 'loss/train': 1.4816631078720093} 08/31/2021 09:16:32 - INFO - __main__ - Step 110554: {'lr': 8.263980395705298e-05, 'samples': 21226368, 'steps': 110553, 'loss/train': 0.830669641494751} 08/31/2021 09:16:33 - INFO - __main__ - Step 110555: {'lr': 8.263586179787466e-05, 'samples': 21226560, 'steps': 110554, 'loss/train': 0.4784473180770874} 08/31/2021 09:16:33 - INFO - __main__ - Step 110556: {'lr': 8.263191971410803e-05, 'samples': 21226752, 'steps': 110555, 'loss/train': 0.9068967700004578} 08/31/2021 09:16:34 - INFO - __main__ - Step 110557: {'lr': 8.262797770575489e-05, 'samples': 21226944, 'steps': 110556, 'loss/train': 1.581633448600769} 08/31/2021 09:16:35 - INFO - __main__ - Step 110558: {'lr': 8.262403577281696e-05, 'samples': 21227136, 'steps': 110557, 'loss/train': 1.0612932443618774} 08/31/2021 09:16:35 - INFO - __main__ - Step 110559: {'lr': 8.262009391529609e-05, 'samples': 21227328, 'steps': 110558, 'loss/train': 1.19115149974823} 08/31/2021 09:16:36 - INFO - __main__ - Step 110560: {'lr': 8.261615213319403e-05, 'samples': 21227520, 'steps': 110559, 'loss/train': 1.0102217197418213} 08/31/2021 09:16:36 - INFO - __main__ - Step 110561: {'lr': 8.261221042651263e-05, 'samples': 21227712, 'steps': 110560, 'loss/train': 1.3276174068450928} 08/31/2021 09:16:38 - INFO - __main__ - Step 110562: {'lr': 8.260826879525349e-05, 'samples': 21227904, 'steps': 110561, 'loss/train': 0.8155295848846436} 08/31/2021 09:16:38 - INFO - __main__ - Step 110563: {'lr': 8.260432723941846e-05, 'samples': 21228096, 'steps': 110562, 'loss/train': 1.186437964439392} 08/31/2021 09:16:38 - INFO - __main__ - Step 110564: {'lr': 8.260038575900939e-05, 'samples': 21228288, 'steps': 110563, 'loss/train': 0.8297755122184753} 08/31/2021 09:16:39 - INFO - __main__ - Step 110565: {'lr': 8.259644435402797e-05, 'samples': 21228480, 'steps': 110564, 'loss/train': 1.3933696746826172} 08/31/2021 09:16:39 - INFO - __main__ - Step 110566: {'lr': 8.2592503024476e-05, 'samples': 21228672, 'steps': 110565, 'loss/train': 1.6742650270462036} 08/31/2021 09:16:41 - INFO - __main__ - Step 110567: {'lr': 8.258856177035528e-05, 'samples': 21228864, 'steps': 110566, 'loss/train': 0.4505775570869446} 08/31/2021 09:16:41 - INFO - __main__ - Step 110568: {'lr': 8.258462059166758e-05, 'samples': 21229056, 'steps': 110567, 'loss/train': 0.47789421677589417} 08/31/2021 09:16:42 - INFO - __main__ - Step 110569: {'lr': 8.258067948841463e-05, 'samples': 21229248, 'steps': 110568, 'loss/train': 1.2608532905578613} 08/31/2021 09:16:42 - INFO - __main__ - Step 110570: {'lr': 8.257673846059827e-05, 'samples': 21229440, 'steps': 110569, 'loss/train': 1.1236881017684937} 08/31/2021 09:16:42 - INFO - __main__ - Step 110571: {'lr': 8.257279750822025e-05, 'samples': 21229632, 'steps': 110570, 'loss/train': 0.863064706325531} 08/31/2021 09:16:44 - INFO - __main__ - Step 110572: {'lr': 8.256885663128233e-05, 'samples': 21229824, 'steps': 110571, 'loss/train': 2.008352756500244} 08/31/2021 09:16:44 - INFO - __main__ - Step 110573: {'lr': 8.25649158297863e-05, 'samples': 21230016, 'steps': 110572, 'loss/train': 0.9249610304832458} 08/31/2021 09:16:45 - INFO - __main__ - Step 110574: {'lr': 8.256097510373395e-05, 'samples': 21230208, 'steps': 110573, 'loss/train': 1.3699312210083008} 08/31/2021 09:16:45 - INFO - __main__ - Step 110575: {'lr': 8.255703445312712e-05, 'samples': 21230400, 'steps': 110574, 'loss/train': 0.5961512923240662} 08/31/2021 09:16:45 - INFO - __main__ - Step 110576: {'lr': 8.255309387796742e-05, 'samples': 21230592, 'steps': 110575, 'loss/train': 1.1749778985977173} 08/31/2021 09:16:47 - INFO - __main__ - Step 110577: {'lr': 8.254915337825672e-05, 'samples': 21230784, 'steps': 110576, 'loss/train': 1.2107051610946655} 08/31/2021 09:16:47 - INFO - __main__ - Step 110578: {'lr': 8.254521295399678e-05, 'samples': 21230976, 'steps': 110577, 'loss/train': 1.8864221572875977} 08/31/2021 09:16:48 - INFO - __main__ - Step 110579: {'lr': 8.254127260518937e-05, 'samples': 21231168, 'steps': 110578, 'loss/train': 0.05754503980278969} 08/31/2021 09:16:48 - INFO - __main__ - Step 110580: {'lr': 8.25373323318363e-05, 'samples': 21231360, 'steps': 110579, 'loss/train': 1.2930898666381836} 08/31/2021 09:16:48 - INFO - __main__ - Step 110581: {'lr': 8.253339213393931e-05, 'samples': 21231552, 'steps': 110580, 'loss/train': 0.8952323198318481} 08/31/2021 09:16:50 - INFO - __main__ - Step 110582: {'lr': 8.252945201150019e-05, 'samples': 21231744, 'steps': 110581, 'loss/train': 1.294777512550354} 08/31/2021 09:16:50 - INFO - __main__ - Step 110583: {'lr': 8.252551196452075e-05, 'samples': 21231936, 'steps': 110582, 'loss/train': 1.3392384052276611} 08/31/2021 09:16:51 - INFO - __main__ - Step 110584: {'lr': 8.252157199300266e-05, 'samples': 21232128, 'steps': 110583, 'loss/train': 1.5733071565628052} 08/31/2021 09:16:51 - INFO - __main__ - Step 110585: {'lr': 8.251763209694782e-05, 'samples': 21232320, 'steps': 110584, 'loss/train': 1.2704417705535889} 08/31/2021 09:16:51 - INFO - __main__ - Step 110586: {'lr': 8.251369227635794e-05, 'samples': 21232512, 'steps': 110585, 'loss/train': 1.3878357410430908} 08/31/2021 09:16:52 - INFO - __main__ - Step 110587: {'lr': 8.25097525312348e-05, 'samples': 21232704, 'steps': 110586, 'loss/train': 0.6159622669219971} 08/31/2021 09:16:53 - INFO - __main__ - Step 110588: {'lr': 8.250581286158026e-05, 'samples': 21232896, 'steps': 110587, 'loss/train': 1.0381742715835571} 08/31/2021 09:16:54 - INFO - __main__ - Step 110589: {'lr': 8.250187326739594e-05, 'samples': 21233088, 'steps': 110588, 'loss/train': 0.7261309623718262} 08/31/2021 09:16:54 - INFO - __main__ - Step 110590: {'lr': 8.24979337486837e-05, 'samples': 21233280, 'steps': 110589, 'loss/train': 3.8747429847717285} 08/31/2021 09:16:54 - INFO - __main__ - Step 110591: {'lr': 8.24939943054453e-05, 'samples': 21233472, 'steps': 110590, 'loss/train': 0.37761563062667847} 08/31/2021 09:16:55 - INFO - __main__ - Step 110592: {'lr': 8.249005493768253e-05, 'samples': 21233664, 'steps': 110591, 'loss/train': 1.2266205549240112} 08/31/2021 09:16:56 - INFO - __main__ - Step 110593: {'lr': 8.248611564539713e-05, 'samples': 21233856, 'steps': 110592, 'loss/train': 0.5631363391876221} 08/31/2021 09:16:57 - INFO - __main__ - Step 110594: {'lr': 8.248217642859091e-05, 'samples': 21234048, 'steps': 110593, 'loss/train': 1.1434743404388428} 08/31/2021 09:16:57 - INFO - __main__ - Step 110595: {'lr': 8.247823728726563e-05, 'samples': 21234240, 'steps': 110594, 'loss/train': 1.4705487489700317} 08/31/2021 09:16:57 - INFO - __main__ - Step 110596: {'lr': 8.247429822142311e-05, 'samples': 21234432, 'steps': 110595, 'loss/train': 1.7051228284835815} 08/31/2021 09:16:58 - INFO - __main__ - Step 110597: {'lr': 8.247035923106505e-05, 'samples': 21234624, 'steps': 110596, 'loss/train': 1.5120521783828735} 08/31/2021 09:17:00 - INFO - __main__ - Step 110598: {'lr': 8.246642031619327e-05, 'samples': 21234816, 'steps': 110597, 'loss/train': 0.5951295495033264} 08/31/2021 09:17:00 - INFO - __main__ - Step 110599: {'lr': 8.246248147680954e-05, 'samples': 21235008, 'steps': 110598, 'loss/train': 1.4756501913070679} 08/31/2021 09:17:01 - INFO - __main__ - Step 110600: {'lr': 8.245854271291561e-05, 'samples': 21235200, 'steps': 110599, 'loss/train': 1.2600655555725098} 08/31/2021 09:17:01 - INFO - __main__ - Step 110601: {'lr': 8.24546040245133e-05, 'samples': 21235392, 'steps': 110600, 'loss/train': 0.48348498344421387} 08/31/2021 09:17:02 - INFO - __main__ - Step 110602: {'lr': 8.245066541160442e-05, 'samples': 21235584, 'steps': 110601, 'loss/train': 1.4124717712402344} 08/31/2021 09:17:03 - INFO - __main__ - Step 110603: {'lr': 8.244672687419064e-05, 'samples': 21235776, 'steps': 110602, 'loss/train': 1.3175410032272339} 08/31/2021 09:17:04 - INFO - __main__ - Step 110604: {'lr': 8.244278841227376e-05, 'samples': 21235968, 'steps': 110603, 'loss/train': 1.4107296466827393} 08/31/2021 09:17:04 - INFO - __main__ - Step 110605: {'lr': 8.243885002585556e-05, 'samples': 21236160, 'steps': 110604, 'loss/train': 0.016254575923085213} 08/31/2021 09:17:05 - INFO - __main__ - Step 110606: {'lr': 8.243491171493783e-05, 'samples': 21236352, 'steps': 110605, 'loss/train': 1.1056393384933472} 08/31/2021 09:17:05 - INFO - __main__ - Step 110607: {'lr': 8.243097347952236e-05, 'samples': 21236544, 'steps': 110606, 'loss/train': 1.5171650648117065} 08/31/2021 09:17:05 - INFO - __main__ - Step 110608: {'lr': 8.24270353196109e-05, 'samples': 21236736, 'steps': 110607, 'loss/train': 1.3233522176742554} 08/31/2021 09:17:07 - INFO - __main__ - Step 110609: {'lr': 8.242309723520522e-05, 'samples': 21236928, 'steps': 110608, 'loss/train': 0.9933949708938599} 08/31/2021 09:17:07 - INFO - __main__ - Step 110610: {'lr': 8.241915922630713e-05, 'samples': 21237120, 'steps': 110609, 'loss/train': 1.4276522397994995} 08/31/2021 09:17:08 - INFO - __main__ - Step 110611: {'lr': 8.241522129291837e-05, 'samples': 21237312, 'steps': 110610, 'loss/train': 0.5951128005981445} 08/31/2021 09:17:08 - INFO - __main__ - Step 110612: {'lr': 8.241128343504073e-05, 'samples': 21237504, 'steps': 110611, 'loss/train': 0.8655062913894653} 08/31/2021 09:17:08 - INFO - __main__ - Step 110613: {'lr': 8.240734565267597e-05, 'samples': 21237696, 'steps': 110612, 'loss/train': 1.1833652257919312} 08/31/2021 09:17:10 - INFO - __main__ - Step 110614: {'lr': 8.240340794582587e-05, 'samples': 21237888, 'steps': 110613, 'loss/train': 1.167298674583435} 08/31/2021 09:17:10 - INFO - __main__ - Step 110615: {'lr': 8.23994703144923e-05, 'samples': 21238080, 'steps': 110614, 'loss/train': 1.2140545845031738} 08/31/2021 09:17:11 - INFO - __main__ - Step 110616: {'lr': 8.239553275867687e-05, 'samples': 21238272, 'steps': 110615, 'loss/train': 0.8351958394050598} 08/31/2021 09:17:11 - INFO - __main__ - Step 110617: {'lr': 8.239159527838142e-05, 'samples': 21238464, 'steps': 110616, 'loss/train': 1.0505996942520142} 08/31/2021 09:17:11 - INFO - __main__ - Step 110618: {'lr': 8.238765787360772e-05, 'samples': 21238656, 'steps': 110617, 'loss/train': 1.7730538845062256} 08/31/2021 09:17:12 - INFO - __main__ - Step 110619: {'lr': 8.238372054435755e-05, 'samples': 21238848, 'steps': 110618, 'loss/train': 1.3733863830566406} 08/31/2021 09:17:13 - INFO - __main__ - Step 110620: {'lr': 8.237978329063269e-05, 'samples': 21239040, 'steps': 110619, 'loss/train': 1.5384215116500854} 08/31/2021 09:17:13 - INFO - __main__ - Step 110621: {'lr': 8.237584611243493e-05, 'samples': 21239232, 'steps': 110620, 'loss/train': 0.923565149307251} 08/31/2021 09:17:14 - INFO - __main__ - Step 110622: {'lr': 8.237190900976602e-05, 'samples': 21239424, 'steps': 110621, 'loss/train': 0.39260199666023254} 08/31/2021 09:17:14 - INFO - __main__ - Step 110623: {'lr': 8.236797198262775e-05, 'samples': 21239616, 'steps': 110622, 'loss/train': 1.1544936895370483} 08/31/2021 09:17:15 - INFO - __main__ - Step 110624: {'lr': 8.236403503102185e-05, 'samples': 21239808, 'steps': 110623, 'loss/train': 2.0295872688293457} 08/31/2021 09:17:16 - INFO - __main__ - Step 110625: {'lr': 8.236009815495018e-05, 'samples': 21240000, 'steps': 110624, 'loss/train': 1.2754216194152832} 08/31/2021 09:17:16 - INFO - __main__ - Step 110626: {'lr': 8.235616135441443e-05, 'samples': 21240192, 'steps': 110625, 'loss/train': 1.3510538339614868} 08/31/2021 09:17:17 - INFO - __main__ - Step 110627: {'lr': 8.235222462941641e-05, 'samples': 21240384, 'steps': 110626, 'loss/train': 0.5040215849876404} 08/31/2021 09:17:17 - INFO - __main__ - Step 110628: {'lr': 8.2348287979958e-05, 'samples': 21240576, 'steps': 110627, 'loss/train': 1.5291874408721924} 08/31/2021 09:17:18 - INFO - __main__ - Step 110629: {'lr': 8.234435140604074e-05, 'samples': 21240768, 'steps': 110628, 'loss/train': 1.2892060279846191} 08/31/2021 09:17:19 - INFO - __main__ - Step 110630: {'lr': 8.234041490766656e-05, 'samples': 21240960, 'steps': 110629, 'loss/train': 1.4180941581726074} 08/31/2021 09:17:20 - INFO - __main__ - Step 110631: {'lr': 8.23364784848372e-05, 'samples': 21241152, 'steps': 110630, 'loss/train': 1.7569761276245117} 08/31/2021 09:17:20 - INFO - __main__ - Step 110632: {'lr': 8.233254213755442e-05, 'samples': 21241344, 'steps': 110631, 'loss/train': 1.3951127529144287} 08/31/2021 09:17:20 - INFO - __main__ - Step 110633: {'lr': 8.232860586582e-05, 'samples': 21241536, 'steps': 110632, 'loss/train': 1.510908603668213} 08/31/2021 09:17:21 - INFO - __main__ - Step 110634: {'lr': 8.232466966963575e-05, 'samples': 21241728, 'steps': 110633, 'loss/train': 0.6485912799835205} 08/31/2021 09:17:22 - INFO - __main__ - Step 110635: {'lr': 8.232073354900341e-05, 'samples': 21241920, 'steps': 110634, 'loss/train': 0.6621703505516052} 08/31/2021 09:17:23 - INFO - __main__ - Step 110636: {'lr': 8.231679750392473e-05, 'samples': 21242112, 'steps': 110635, 'loss/train': 0.2053953856229782} 08/31/2021 09:17:23 - INFO - __main__ - Step 110637: {'lr': 8.231286153440154e-05, 'samples': 21242304, 'steps': 110636, 'loss/train': 0.04110059142112732} 08/31/2021 09:17:23 - INFO - __main__ - Step 110638: {'lr': 8.23089256404356e-05, 'samples': 21242496, 'steps': 110637, 'loss/train': 4.819382190704346} 08/31/2021 09:17:24 - INFO - __main__ - Step 110639: {'lr': 8.230498982202864e-05, 'samples': 21242688, 'steps': 110638, 'loss/train': 1.558293104171753} 08/31/2021 09:17:25 - INFO - __main__ - Step 110640: {'lr': 8.230105407918248e-05, 'samples': 21242880, 'steps': 110639, 'loss/train': 0.8777549266815186} 08/31/2021 09:17:26 - INFO - __main__ - Step 110641: {'lr': 8.229711841189889e-05, 'samples': 21243072, 'steps': 110640, 'loss/train': 0.08087809383869171} 08/31/2021 09:17:26 - INFO - __main__ - Step 110642: {'lr': 8.22931828201797e-05, 'samples': 21243264, 'steps': 110641, 'loss/train': 0.962725818157196} 08/31/2021 09:17:27 - INFO - __main__ - Step 110643: {'lr': 8.228924730402654e-05, 'samples': 21243456, 'steps': 110642, 'loss/train': 0.6228631734848022} 08/31/2021 09:17:27 - INFO - __main__ - Step 110644: {'lr': 8.228531186344124e-05, 'samples': 21243648, 'steps': 110643, 'loss/train': 1.490828514099121} 08/31/2021 09:17:27 - INFO - __main__ - Step 110645: {'lr': 8.22813764984256e-05, 'samples': 21243840, 'steps': 110644, 'loss/train': 1.4203110933303833} 08/31/2021 09:17:29 - INFO - __main__ - Step 110646: {'lr': 8.227744120898136e-05, 'samples': 21244032, 'steps': 110645, 'loss/train': 0.1000833585858345} 08/31/2021 09:17:29 - INFO - __main__ - Step 110647: {'lr': 8.227350599511036e-05, 'samples': 21244224, 'steps': 110646, 'loss/train': 1.9345113039016724} 08/31/2021 09:17:30 - INFO - __main__ - Step 110648: {'lr': 8.22695708568143e-05, 'samples': 21244416, 'steps': 110647, 'loss/train': 1.0447330474853516} 08/31/2021 09:17:30 - INFO - __main__ - Step 110649: {'lr': 8.226563579409498e-05, 'samples': 21244608, 'steps': 110648, 'loss/train': 0.8183549046516418} 08/31/2021 09:17:30 - INFO - __main__ - Step 110650: {'lr': 8.226170080695419e-05, 'samples': 21244800, 'steps': 110649, 'loss/train': 1.2501630783081055} 08/31/2021 09:17:32 - INFO - __main__ - Step 110651: {'lr': 8.225776589539372e-05, 'samples': 21244992, 'steps': 110650, 'loss/train': 1.20863676071167} 08/31/2021 09:17:32 - INFO - __main__ - Step 110652: {'lr': 8.225383105941525e-05, 'samples': 21245184, 'steps': 110651, 'loss/train': 1.0882278680801392} 08/31/2021 09:17:33 - INFO - __main__ - Step 110653: {'lr': 8.224989629902066e-05, 'samples': 21245376, 'steps': 110652, 'loss/train': 0.5641210675239563} 08/31/2021 09:17:33 - INFO - __main__ - Step 110654: {'lr': 8.224596161421166e-05, 'samples': 21245568, 'steps': 110653, 'loss/train': 1.3955012559890747} 08/31/2021 09:17:34 - INFO - __main__ - Step 110655: {'lr': 8.224202700499011e-05, 'samples': 21245760, 'steps': 110654, 'loss/train': 0.945246160030365} 08/31/2021 09:17:36 - INFO - __main__ - Step 110656: {'lr': 8.223809247135766e-05, 'samples': 21245952, 'steps': 110655, 'loss/train': 1.5229002237319946} 08/31/2021 09:17:36 - INFO - __main__ - Step 110657: {'lr': 8.223415801331614e-05, 'samples': 21246144, 'steps': 110656, 'loss/train': 1.330966830253601} 08/31/2021 09:17:36 - INFO - __main__ - Step 110658: {'lr': 8.22302236308673e-05, 'samples': 21246336, 'steps': 110657, 'loss/train': 1.0103304386138916} 08/31/2021 09:17:37 - INFO - __main__ - Step 110659: {'lr': 8.222628932401293e-05, 'samples': 21246528, 'steps': 110658, 'loss/train': 0.22656387090682983} 08/31/2021 09:17:37 - INFO - __main__ - Step 110660: {'lr': 8.222235509275483e-05, 'samples': 21246720, 'steps': 110659, 'loss/train': 1.5863926410675049} 08/31/2021 09:17:39 - INFO - __main__ - Step 110661: {'lr': 8.221842093709473e-05, 'samples': 21246912, 'steps': 110660, 'loss/train': 1.3855050802230835} 08/31/2021 09:17:39 - INFO - __main__ - Step 110662: {'lr': 8.221448685703442e-05, 'samples': 21247104, 'steps': 110661, 'loss/train': 0.9302087426185608} 08/31/2021 09:17:39 - INFO - __main__ - Step 110663: {'lr': 8.221055285257568e-05, 'samples': 21247296, 'steps': 110662, 'loss/train': 0.8597142696380615} 08/31/2021 09:17:40 - INFO - __main__ - Step 110664: {'lr': 8.220661892372025e-05, 'samples': 21247488, 'steps': 110663, 'loss/train': 0.5563358068466187} 08/31/2021 09:17:40 - INFO - __main__ - Step 110665: {'lr': 8.220268507046997e-05, 'samples': 21247680, 'steps': 110664, 'loss/train': 1.6622662544250488} 08/31/2021 09:17:42 - INFO - __main__ - Step 110666: {'lr': 8.219875129282652e-05, 'samples': 21247872, 'steps': 110665, 'loss/train': 1.3808906078338623} 08/31/2021 09:17:42 - INFO - __main__ - Step 110667: {'lr': 8.219481759079176e-05, 'samples': 21248064, 'steps': 110666, 'loss/train': 1.670422911643982} 08/31/2021 09:17:42 - INFO - __main__ - Step 110668: {'lr': 8.219088396436741e-05, 'samples': 21248256, 'steps': 110667, 'loss/train': 0.8775567412376404} 08/31/2021 09:17:43 - INFO - __main__ - Step 110669: {'lr': 8.218695041355537e-05, 'samples': 21248448, 'steps': 110668, 'loss/train': 0.7129448056221008} 08/31/2021 09:17:43 - INFO - __main__ - Step 110670: {'lr': 8.218301693835719e-05, 'samples': 21248640, 'steps': 110669, 'loss/train': 0.9182939529418945} 08/31/2021 09:17:45 - INFO - __main__ - Step 110671: {'lr': 8.217908353877476e-05, 'samples': 21248832, 'steps': 110670, 'loss/train': 1.4287965297698975} 08/31/2021 09:17:45 - INFO - __main__ - Step 110672: {'lr': 8.217515021480983e-05, 'samples': 21249024, 'steps': 110671, 'loss/train': 0.3338966369628906} 08/31/2021 09:17:46 - INFO - __main__ - Step 110673: {'lr': 8.217121696646421e-05, 'samples': 21249216, 'steps': 110672, 'loss/train': 0.989854097366333} 08/31/2021 09:17:46 - INFO - __main__ - Step 110674: {'lr': 8.216728379373964e-05, 'samples': 21249408, 'steps': 110673, 'loss/train': 0.5816665887832642} 08/31/2021 09:17:46 - INFO - __main__ - Step 110675: {'lr': 8.216335069663791e-05, 'samples': 21249600, 'steps': 110674, 'loss/train': 0.11388672888278961} 08/31/2021 09:17:47 - INFO - __main__ - Step 110676: {'lr': 8.215941767516077e-05, 'samples': 21249792, 'steps': 110675, 'loss/train': 0.9057390689849854} 08/31/2021 09:17:48 - INFO - __main__ - Step 110677: {'lr': 8.215548472931004e-05, 'samples': 21249984, 'steps': 110676, 'loss/train': 1.5399736166000366} 08/31/2021 09:17:48 - INFO - __main__ - Step 110678: {'lr': 8.215155185908743e-05, 'samples': 21250176, 'steps': 110677, 'loss/train': 0.8561946749687195} 08/31/2021 09:17:49 - INFO - __main__ - Step 110679: {'lr': 8.214761906449475e-05, 'samples': 21250368, 'steps': 110678, 'loss/train': 0.9834542274475098} 08/31/2021 09:17:49 - INFO - __main__ - Step 110680: {'lr': 8.214368634553374e-05, 'samples': 21250560, 'steps': 110679, 'loss/train': 1.2592055797576904} 08/31/2021 09:17:51 - INFO - __main__ - Step 110681: {'lr': 8.213975370220622e-05, 'samples': 21250752, 'steps': 110680, 'loss/train': 1.742920994758606} 08/31/2021 09:17:51 - INFO - __main__ - Step 110682: {'lr': 8.213582113451401e-05, 'samples': 21250944, 'steps': 110681, 'loss/train': 1.0116653442382812} 08/31/2021 09:17:52 - INFO - __main__ - Step 110683: {'lr': 8.213188864245873e-05, 'samples': 21251136, 'steps': 110682, 'loss/train': 0.530389666557312} 08/31/2021 09:17:52 - INFO - __main__ - Step 110684: {'lr': 8.212795622604222e-05, 'samples': 21251328, 'steps': 110683, 'loss/train': 2.0360798835754395} 08/31/2021 09:17:52 - INFO - __main__ - Step 110685: {'lr': 8.212402388526627e-05, 'samples': 21251520, 'steps': 110684, 'loss/train': 1.0841370820999146} 08/31/2021 09:17:53 - INFO - __main__ - Step 110686: {'lr': 8.212009162013264e-05, 'samples': 21251712, 'steps': 110685, 'loss/train': 0.9407190680503845} 08/31/2021 09:17:54 - INFO - __main__ - Step 110687: {'lr': 8.211615943064312e-05, 'samples': 21251904, 'steps': 110686, 'loss/train': 1.377972960472107} 08/31/2021 09:17:55 - INFO - __main__ - Step 110688: {'lr': 8.211222731679946e-05, 'samples': 21252096, 'steps': 110687, 'loss/train': 1.3738783597946167} 08/31/2021 09:17:55 - INFO - __main__ - Step 110689: {'lr': 8.210829527860344e-05, 'samples': 21252288, 'steps': 110688, 'loss/train': 0.15017519891262054} 08/31/2021 09:17:55 - INFO - __main__ - Step 110690: {'lr': 8.210436331605683e-05, 'samples': 21252480, 'steps': 110689, 'loss/train': 1.3239476680755615} 08/31/2021 09:17:56 - INFO - __main__ - Step 110691: {'lr': 8.21004314291614e-05, 'samples': 21252672, 'steps': 110690, 'loss/train': 1.1077667474746704} 08/31/2021 09:17:58 - INFO - __main__ - Step 110692: {'lr': 8.209649961791893e-05, 'samples': 21252864, 'steps': 110691, 'loss/train': 0.36115339398384094} 08/31/2021 09:17:58 - INFO - __main__ - Step 110693: {'lr': 8.209256788233119e-05, 'samples': 21253056, 'steps': 110692, 'loss/train': 0.3291923403739929} 08/31/2021 09:17:59 - INFO - __main__ - Step 110694: {'lr': 8.208863622239995e-05, 'samples': 21253248, 'steps': 110693, 'loss/train': 0.4364333748817444} 08/31/2021 09:17:59 - INFO - __main__ - Step 110695: {'lr': 8.208470463812706e-05, 'samples': 21253440, 'steps': 110694, 'loss/train': 0.5445359945297241} 08/31/2021 09:17:59 - INFO - __main__ - Step 110696: {'lr': 8.208077312951412e-05, 'samples': 21253632, 'steps': 110695, 'loss/train': 1.4152694940567017} 08/31/2021 09:18:01 - INFO - __main__ - Step 110697: {'lr': 8.207684169656298e-05, 'samples': 21253824, 'steps': 110696, 'loss/train': 0.963714599609375} 08/31/2021 09:18:01 - INFO - __main__ - Step 110698: {'lr': 8.207291033927545e-05, 'samples': 21254016, 'steps': 110697, 'loss/train': 0.8681904077529907} 08/31/2021 09:18:02 - INFO - __main__ - Step 110699: {'lr': 8.206897905765326e-05, 'samples': 21254208, 'steps': 110698, 'loss/train': 1.4601012468338013} 08/31/2021 09:18:02 - INFO - __main__ - Step 110700: {'lr': 8.206504785169821e-05, 'samples': 21254400, 'steps': 110699, 'loss/train': 0.049517516046762466} 08/31/2021 09:18:02 - INFO - __main__ - Step 110701: {'lr': 8.206111672141204e-05, 'samples': 21254592, 'steps': 110700, 'loss/train': 1.452871561050415} 08/31/2021 09:18:03 - INFO - __main__ - Step 110702: {'lr': 8.205718566679654e-05, 'samples': 21254784, 'steps': 110701, 'loss/train': 0.7788232564926147} 08/31/2021 09:18:04 - INFO - __main__ - Step 110703: {'lr': 8.205325468785348e-05, 'samples': 21254976, 'steps': 110702, 'loss/train': 1.4313057661056519} 08/31/2021 09:18:05 - INFO - __main__ - Step 110704: {'lr': 8.204932378458466e-05, 'samples': 21255168, 'steps': 110703, 'loss/train': 0.8118932843208313} 08/31/2021 09:18:05 - INFO - __main__ - Step 110705: {'lr': 8.204539295699182e-05, 'samples': 21255360, 'steps': 110704, 'loss/train': 0.7249622344970703} 08/31/2021 09:18:05 - INFO - __main__ - Step 110706: {'lr': 8.20414622050768e-05, 'samples': 21255552, 'steps': 110705, 'loss/train': 0.8902581930160522} 08/31/2021 09:18:06 - INFO - __main__ - Step 110707: {'lr': 8.203753152884122e-05, 'samples': 21255744, 'steps': 110706, 'loss/train': 0.2536369860172272} 08/31/2021 09:18:08 - INFO - __main__ - Step 110708: {'lr': 8.203360092828693e-05, 'samples': 21255936, 'steps': 110707, 'loss/train': 1.3197555541992188} 08/31/2021 09:18:08 - INFO - __main__ - Step 110709: {'lr': 8.202967040341572e-05, 'samples': 21256128, 'steps': 110708, 'loss/train': 1.1508572101593018} 08/31/2021 09:18:09 - INFO - __main__ - Step 110710: {'lr': 8.202573995422935e-05, 'samples': 21256320, 'steps': 110709, 'loss/train': 1.3428574800491333} 08/31/2021 09:18:09 - INFO - __main__ - Step 110711: {'lr': 8.202180958072958e-05, 'samples': 21256512, 'steps': 110710, 'loss/train': 1.056579828262329} 08/31/2021 09:18:09 - INFO - __main__ - Step 110712: {'lr': 8.20178792829182e-05, 'samples': 21256704, 'steps': 110711, 'loss/train': 0.7851088643074036} 08/31/2021 09:18:11 - INFO - __main__ - Step 110713: {'lr': 8.201394906079698e-05, 'samples': 21256896, 'steps': 110712, 'loss/train': 1.7933413982391357} 08/31/2021 09:18:11 - INFO - __main__ - Step 110714: {'lr': 8.201001891436765e-05, 'samples': 21257088, 'steps': 110713, 'loss/train': 1.0055739879608154} 08/31/2021 09:18:12 - INFO - __main__ - Step 110715: {'lr': 8.200608884363204e-05, 'samples': 21257280, 'steps': 110714, 'loss/train': 1.6525591611862183} 08/31/2021 09:18:12 - INFO - __main__ - Step 110716: {'lr': 8.200215884859188e-05, 'samples': 21257472, 'steps': 110715, 'loss/train': 0.13149629533290863} 08/31/2021 09:18:12 - INFO - __main__ - Step 110717: {'lr': 8.199822892924905e-05, 'samples': 21257664, 'steps': 110716, 'loss/train': 1.1265983581542969} 08/31/2021 09:18:14 - INFO - __main__ - Step 110718: {'lr': 8.199429908560516e-05, 'samples': 21257856, 'steps': 110717, 'loss/train': 1.2874188423156738} 08/31/2021 09:18:14 - INFO - __main__ - Step 110719: {'lr': 8.199036931766202e-05, 'samples': 21258048, 'steps': 110718, 'loss/train': 0.5072351694107056} 08/31/2021 09:18:15 - INFO - __main__ - Step 110720: {'lr': 8.198643962542143e-05, 'samples': 21258240, 'steps': 110719, 'loss/train': 1.2682063579559326} 08/31/2021 09:18:15 - INFO - __main__ - Step 110721: {'lr': 8.198251000888516e-05, 'samples': 21258432, 'steps': 110720, 'loss/train': 1.202366828918457} 08/31/2021 09:18:15 - INFO - __main__ - Step 110722: {'lr': 8.197858046805498e-05, 'samples': 21258624, 'steps': 110721, 'loss/train': 0.9371274709701538} 08/31/2021 09:18:17 - INFO - __main__ - Step 110723: {'lr': 8.197465100293264e-05, 'samples': 21258816, 'steps': 110722, 'loss/train': 1.3035004138946533} 08/31/2021 09:18:17 - INFO - __main__ - Step 110724: {'lr': 8.197072161351996e-05, 'samples': 21259008, 'steps': 110723, 'loss/train': 0.022285612300038338} 08/31/2021 09:18:18 - INFO - __main__ - Step 110725: {'lr': 8.196679229981866e-05, 'samples': 21259200, 'steps': 110724, 'loss/train': 1.3965239524841309} 08/31/2021 09:18:18 - INFO - __main__ - Step 110726: {'lr': 8.196286306183054e-05, 'samples': 21259392, 'steps': 110725, 'loss/train': 0.9680017232894897} 08/31/2021 09:18:18 - INFO - __main__ - Step 110727: {'lr': 8.195893389955735e-05, 'samples': 21259584, 'steps': 110726, 'loss/train': 0.8433610200881958} 08/31/2021 09:18:20 - INFO - __main__ - Step 110728: {'lr': 8.195500481300097e-05, 'samples': 21259776, 'steps': 110727, 'loss/train': 0.38073813915252686} 08/31/2021 09:18:21 - INFO - __main__ - Step 110729: {'lr': 8.195107580216298e-05, 'samples': 21259968, 'steps': 110728, 'loss/train': 1.04610013961792} 08/31/2021 09:18:21 - INFO - __main__ - Step 110730: {'lr': 8.194714686704524e-05, 'samples': 21260160, 'steps': 110729, 'loss/train': 0.10447563230991364} 08/31/2021 09:18:22 - INFO - __main__ - Step 110731: {'lr': 8.194321800764953e-05, 'samples': 21260352, 'steps': 110730, 'loss/train': 1.3744131326675415} 08/31/2021 09:18:22 - INFO - __main__ - Step 110732: {'lr': 8.193928922397762e-05, 'samples': 21260544, 'steps': 110731, 'loss/train': 1.647553563117981} 08/31/2021 09:18:24 - INFO - __main__ - Step 110733: {'lr': 8.193536051603123e-05, 'samples': 21260736, 'steps': 110732, 'loss/train': 1.4575209617614746} 08/31/2021 09:18:24 - INFO - __main__ - Step 110734: {'lr': 8.193143188381221e-05, 'samples': 21260928, 'steps': 110733, 'loss/train': 1.3296440839767456} 08/31/2021 09:18:24 - INFO - __main__ - Step 110735: {'lr': 8.192750332732229e-05, 'samples': 21261120, 'steps': 110734, 'loss/train': 1.2164998054504395} 08/31/2021 09:18:25 - INFO - __main__ - Step 110736: {'lr': 8.192357484656324e-05, 'samples': 21261312, 'steps': 110735, 'loss/train': 0.3285916745662689} 08/31/2021 09:18:25 - INFO - __main__ - Step 110737: {'lr': 8.191964644153686e-05, 'samples': 21261504, 'steps': 110736, 'loss/train': 1.5647759437561035} 08/31/2021 09:18:25 - INFO - __main__ - Step 110738: {'lr': 8.191571811224486e-05, 'samples': 21261696, 'steps': 110737, 'loss/train': 0.445920467376709} 08/31/2021 09:18:27 - INFO - __main__ - Step 110739: {'lr': 8.191178985868914e-05, 'samples': 21261888, 'steps': 110738, 'loss/train': 0.9052721858024597} 08/31/2021 09:18:27 - INFO - __main__ - Step 110740: {'lr': 8.190786168087128e-05, 'samples': 21262080, 'steps': 110739, 'loss/train': 1.9453357458114624} 08/31/2021 09:18:28 - INFO - __main__ - Step 110741: {'lr': 8.190393357879313e-05, 'samples': 21262272, 'steps': 110740, 'loss/train': 1.4867963790893555} 08/31/2021 09:18:28 - INFO - __main__ - Step 110742: {'lr': 8.19000055524565e-05, 'samples': 21262464, 'steps': 110741, 'loss/train': 1.2902635335922241} 08/31/2021 09:18:28 - INFO - __main__ - Step 110743: {'lr': 8.189607760186313e-05, 'samples': 21262656, 'steps': 110742, 'loss/train': 2.055755138397217} 08/31/2021 09:18:30 - INFO - __main__ - Step 110744: {'lr': 8.189214972701478e-05, 'samples': 21262848, 'steps': 110743, 'loss/train': 0.6047078371047974} 08/31/2021 09:18:31 - INFO - __main__ - Step 110745: {'lr': 8.188822192791326e-05, 'samples': 21263040, 'steps': 110744, 'loss/train': 0.5896366834640503} 08/31/2021 09:18:31 - INFO - __main__ - Step 110746: {'lr': 8.188429420456028e-05, 'samples': 21263232, 'steps': 110745, 'loss/train': 1.1029047966003418} 08/31/2021 09:18:31 - INFO - __main__ - Step 110747: {'lr': 8.188036655695766e-05, 'samples': 21263424, 'steps': 110746, 'loss/train': 0.7337815761566162} 08/31/2021 09:18:32 - INFO - __main__ - Step 110748: {'lr': 8.187643898510716e-05, 'samples': 21263616, 'steps': 110747, 'loss/train': 0.03528466075658798} 08/31/2021 09:18:33 - INFO - __main__ - Step 110749: {'lr': 8.187251148901053e-05, 'samples': 21263808, 'steps': 110748, 'loss/train': 0.3771430253982544} 08/31/2021 09:18:34 - INFO - __main__ - Step 110750: {'lr': 8.186858406866965e-05, 'samples': 21264000, 'steps': 110749, 'loss/train': 1.2711278200149536} 08/31/2021 09:18:34 - INFO - __main__ - Step 110751: {'lr': 8.186465672408608e-05, 'samples': 21264192, 'steps': 110750, 'loss/train': 0.29133644700050354} 08/31/2021 09:18:34 - INFO - __main__ - Step 110752: {'lr': 8.186072945526174e-05, 'samples': 21264384, 'steps': 110751, 'loss/train': 0.416969358921051} 08/31/2021 09:18:35 - INFO - __main__ - Step 110753: {'lr': 8.185680226219832e-05, 'samples': 21264576, 'steps': 110752, 'loss/train': 1.2809679508209229} 08/31/2021 09:18:36 - INFO - __main__ - Step 110754: {'lr': 8.185287514489767e-05, 'samples': 21264768, 'steps': 110753, 'loss/train': 0.11391914635896683} 08/31/2021 09:18:37 - INFO - __main__ - Step 110755: {'lr': 8.184894810336149e-05, 'samples': 21264960, 'steps': 110754, 'loss/train': 1.2701338529586792} 08/31/2021 09:18:37 - INFO - __main__ - Step 110756: {'lr': 8.18450211375916e-05, 'samples': 21265152, 'steps': 110755, 'loss/train': 1.6233744621276855} 08/31/2021 09:18:37 - INFO - __main__ - Step 110757: {'lr': 8.184109424758973e-05, 'samples': 21265344, 'steps': 110756, 'loss/train': 0.8087886571884155} 08/31/2021 09:18:38 - INFO - __main__ - Step 110758: {'lr': 8.183716743335767e-05, 'samples': 21265536, 'steps': 110757, 'loss/train': 1.1925735473632812} 08/31/2021 09:18:39 - INFO - __main__ - Step 110759: {'lr': 8.18332406948972e-05, 'samples': 21265728, 'steps': 110758, 'loss/train': 0.9198260307312012} 08/31/2021 09:18:40 - INFO - __main__ - Step 110760: {'lr': 8.182931403221006e-05, 'samples': 21265920, 'steps': 110759, 'loss/train': 0.7205453515052795} 08/31/2021 09:18:40 - INFO - __main__ - Step 110761: {'lr': 8.182538744529805e-05, 'samples': 21266112, 'steps': 110760, 'loss/train': 0.9356457591056824} 08/31/2021 09:18:40 - INFO - __main__ - Step 110762: {'lr': 8.182146093416292e-05, 'samples': 21266304, 'steps': 110761, 'loss/train': 1.2392433881759644} 08/31/2021 09:18:41 - INFO - __main__ - Step 110763: {'lr': 8.181753449880652e-05, 'samples': 21266496, 'steps': 110762, 'loss/train': 1.207004189491272} 08/31/2021 09:18:43 - INFO - __main__ - Step 110764: {'lr': 8.181360813923047e-05, 'samples': 21266688, 'steps': 110763, 'loss/train': 1.109623670578003} 08/31/2021 09:18:43 - INFO - __main__ - Step 110765: {'lr': 8.18096818554366e-05, 'samples': 21266880, 'steps': 110764, 'loss/train': 1.460601806640625} 08/31/2021 09:18:44 - INFO - __main__ - Step 110766: {'lr': 8.180575564742673e-05, 'samples': 21267072, 'steps': 110765, 'loss/train': 0.44334274530410767} 08/31/2021 09:18:44 - INFO - __main__ - Step 110767: {'lr': 8.180182951520257e-05, 'samples': 21267264, 'steps': 110766, 'loss/train': 1.5911049842834473} 08/31/2021 09:18:44 - INFO - __main__ - Step 110768: {'lr': 8.179790345876589e-05, 'samples': 21267456, 'steps': 110767, 'loss/train': 1.406638264656067} 08/31/2021 09:18:46 - INFO - __main__ - Step 110769: {'lr': 8.179397747811851e-05, 'samples': 21267648, 'steps': 110768, 'loss/train': 0.6220075488090515} 08/31/2021 09:18:46 - INFO - __main__ - Step 110770: {'lr': 8.179005157326214e-05, 'samples': 21267840, 'steps': 110769, 'loss/train': 1.2466599941253662} 08/31/2021 09:18:47 - INFO - __main__ - Step 110771: {'lr': 8.17861257441986e-05, 'samples': 21268032, 'steps': 110770, 'loss/train': 2.1574363708496094} 08/31/2021 09:18:47 - INFO - __main__ - Step 110772: {'lr': 8.178219999092962e-05, 'samples': 21268224, 'steps': 110771, 'loss/train': 1.880650281906128} 08/31/2021 09:18:47 - INFO - __main__ - Step 110773: {'lr': 8.1778274313457e-05, 'samples': 21268416, 'steps': 110772, 'loss/train': 0.8779886960983276} 08/31/2021 09:18:49 - INFO - __main__ - Step 110774: {'lr': 8.177434871178247e-05, 'samples': 21268608, 'steps': 110773, 'loss/train': 0.6811196208000183} 08/31/2021 09:18:49 - INFO - __main__ - Step 110775: {'lr': 8.177042318590785e-05, 'samples': 21268800, 'steps': 110774, 'loss/train': 1.4613934755325317} 08/31/2021 09:18:50 - INFO - __main__ - Step 110776: {'lr': 8.176649773583495e-05, 'samples': 21268992, 'steps': 110775, 'loss/train': 0.8793125748634338} 08/31/2021 09:18:50 - INFO - __main__ - Step 110777: {'lr': 8.176257236156539e-05, 'samples': 21269184, 'steps': 110776, 'loss/train': 0.7905877828598022} 08/31/2021 09:18:50 - INFO - __main__ - Step 110778: {'lr': 8.175864706310102e-05, 'samples': 21269376, 'steps': 110777, 'loss/train': 0.6279986500740051} 08/31/2021 09:18:51 - INFO - __main__ - Step 110779: {'lr': 8.175472184044361e-05, 'samples': 21269568, 'steps': 110778, 'loss/train': 0.6429950594902039} 08/31/2021 09:18:52 - INFO - __main__ - Step 110780: {'lr': 8.175079669359492e-05, 'samples': 21269760, 'steps': 110779, 'loss/train': 0.8341579437255859} 08/31/2021 09:18:53 - INFO - __main__ - Step 110781: {'lr': 8.174687162255672e-05, 'samples': 21269952, 'steps': 110780, 'loss/train': 1.4902600049972534} 08/31/2021 09:18:53 - INFO - __main__ - Step 110782: {'lr': 8.174294662733078e-05, 'samples': 21270144, 'steps': 110781, 'loss/train': 1.0435112714767456} 08/31/2021 09:18:54 - INFO - __main__ - Step 110783: {'lr': 8.173902170791888e-05, 'samples': 21270336, 'steps': 110782, 'loss/train': 1.1750768423080444} 08/31/2021 09:18:54 - INFO - __main__ - Step 110784: {'lr': 8.173509686432279e-05, 'samples': 21270528, 'steps': 110783, 'loss/train': 1.3634657859802246} 08/31/2021 09:18:56 - INFO - __main__ - Step 110785: {'lr': 8.173117209654427e-05, 'samples': 21270720, 'steps': 110784, 'loss/train': 0.977125883102417} 08/31/2021 09:18:56 - INFO - __main__ - Step 110786: {'lr': 8.172724740458506e-05, 'samples': 21270912, 'steps': 110785, 'loss/train': 1.9783790111541748} 08/31/2021 09:18:56 - INFO - __main__ - Step 110787: {'lr': 8.172332278844699e-05, 'samples': 21271104, 'steps': 110786, 'loss/train': 0.70198655128479} 08/31/2021 09:18:57 - INFO - __main__ - Step 110788: {'lr': 8.171939824813176e-05, 'samples': 21271296, 'steps': 110787, 'loss/train': 0.7661373615264893} 08/31/2021 09:18:57 - INFO - __main__ - Step 110789: {'lr': 8.17154737836412e-05, 'samples': 21271488, 'steps': 110788, 'loss/train': 0.29983025789260864} 08/31/2021 09:18:59 - INFO - __main__ - Step 110790: {'lr': 8.171154939497713e-05, 'samples': 21271680, 'steps': 110789, 'loss/train': 0.5890450477600098} 08/31/2021 09:18:59 - INFO - __main__ - Step 110791: {'lr': 8.170762508214114e-05, 'samples': 21271872, 'steps': 110790, 'loss/train': 0.18375006318092346} 08/31/2021 09:18:59 - INFO - __main__ - Step 110792: {'lr': 8.170370084513511e-05, 'samples': 21272064, 'steps': 110791, 'loss/train': 1.464072585105896} 08/31/2021 09:19:00 - INFO - __main__ - Step 110793: {'lr': 8.16997766839608e-05, 'samples': 21272256, 'steps': 110792, 'loss/train': 0.8130354285240173} 08/31/2021 09:19:00 - INFO - __main__ - Step 110794: {'lr': 8.169585259861997e-05, 'samples': 21272448, 'steps': 110793, 'loss/train': 1.3906902074813843} 08/31/2021 09:19:02 - INFO - __main__ - Step 110795: {'lr': 8.169192858911436e-05, 'samples': 21272640, 'steps': 110794, 'loss/train': 1.7954466342926025} 08/31/2021 09:19:02 - INFO - __main__ - Step 110796: {'lr': 8.168800465544582e-05, 'samples': 21272832, 'steps': 110795, 'loss/train': 1.4293949604034424} 08/31/2021 09:19:03 - INFO - __main__ - Step 110797: {'lr': 8.168408079761605e-05, 'samples': 21273024, 'steps': 110796, 'loss/train': 0.9380001425743103} 08/31/2021 09:19:03 - INFO - __main__ - Step 110798: {'lr': 8.168015701562684e-05, 'samples': 21273216, 'steps': 110797, 'loss/train': 0.7537954449653625} 08/31/2021 09:19:04 - INFO - __main__ - Step 110799: {'lr': 8.167623330947993e-05, 'samples': 21273408, 'steps': 110798, 'loss/train': 1.3865962028503418} 08/31/2021 09:19:04 - INFO - __main__ - Step 110800: {'lr': 8.167230967917713e-05, 'samples': 21273600, 'steps': 110799, 'loss/train': 0.5901414752006531} 08/31/2021 09:19:05 - INFO - __main__ - Step 110801: {'lr': 8.166838612472019e-05, 'samples': 21273792, 'steps': 110800, 'loss/train': 1.5721111297607422} 08/31/2021 09:19:06 - INFO - __main__ - Step 110802: {'lr': 8.166446264611088e-05, 'samples': 21273984, 'steps': 110801, 'loss/train': 1.1270627975463867} 08/31/2021 09:19:06 - INFO - __main__ - Step 110803: {'lr': 8.166053924335104e-05, 'samples': 21274176, 'steps': 110802, 'loss/train': 1.1100698709487915} 08/31/2021 09:19:07 - INFO - __main__ - Step 110804: {'lr': 8.165661591644227e-05, 'samples': 21274368, 'steps': 110803, 'loss/train': 1.0861220359802246} 08/31/2021 09:19:07 - INFO - __main__ - Step 110805: {'lr': 8.165269266538644e-05, 'samples': 21274560, 'steps': 110804, 'loss/train': 0.6919553875923157} 08/31/2021 09:19:08 - INFO - __main__ - Step 110806: {'lr': 8.164876949018532e-05, 'samples': 21274752, 'steps': 110805, 'loss/train': 1.573920488357544} 08/31/2021 09:19:09 - INFO - __main__ - Step 110807: {'lr': 8.164484639084065e-05, 'samples': 21274944, 'steps': 110806, 'loss/train': 0.9186415672302246} 08/31/2021 09:19:09 - INFO - __main__ - Step 110808: {'lr': 8.164092336735424e-05, 'samples': 21275136, 'steps': 110807, 'loss/train': 0.46410927176475525} 08/31/2021 09:19:10 - INFO - __main__ - Step 110809: {'lr': 8.163700041972783e-05, 'samples': 21275328, 'steps': 110808, 'loss/train': 1.2289785146713257} 08/31/2021 09:19:10 - INFO - __main__ - Step 110810: {'lr': 8.163307754796318e-05, 'samples': 21275520, 'steps': 110809, 'loss/train': 0.5656894445419312} 08/31/2021 09:19:12 - INFO - __main__ - Step 110811: {'lr': 8.162915475206206e-05, 'samples': 21275712, 'steps': 110810, 'loss/train': 0.9165232181549072} 08/31/2021 09:19:12 - INFO - __main__ - Step 110812: {'lr': 8.162523203202623e-05, 'samples': 21275904, 'steps': 110811, 'loss/train': 1.2146859169006348} 08/31/2021 09:19:13 - INFO - __main__ - Step 110813: {'lr': 8.16213093878575e-05, 'samples': 21276096, 'steps': 110812, 'loss/train': 0.01713370904326439} 08/31/2021 09:19:13 - INFO - __main__ - Step 110814: {'lr': 8.16173868195576e-05, 'samples': 21276288, 'steps': 110813, 'loss/train': 0.35787686705589294} 08/31/2021 09:19:13 - INFO - __main__ - Step 110815: {'lr': 8.16134643271283e-05, 'samples': 21276480, 'steps': 110814, 'loss/train': 1.1210399866104126} 08/31/2021 09:19:14 - INFO - __main__ - Step 110816: {'lr': 8.160954191057137e-05, 'samples': 21276672, 'steps': 110815, 'loss/train': 1.2514036893844604} 08/31/2021 09:19:16 - INFO - __main__ - Step 110817: {'lr': 8.160561956988868e-05, 'samples': 21276864, 'steps': 110816, 'loss/train': 1.4984885454177856} 08/31/2021 09:19:16 - INFO - __main__ - Step 110818: {'lr': 8.160169730508182e-05, 'samples': 21277056, 'steps': 110817, 'loss/train': 0.20228199660778046} 08/31/2021 09:19:17 - INFO - __main__ - Step 110819: {'lr': 8.159777511615263e-05, 'samples': 21277248, 'steps': 110818, 'loss/train': 0.7013943195343018} 08/31/2021 09:19:17 - INFO - __main__ - Step 110820: {'lr': 8.15938530031029e-05, 'samples': 21277440, 'steps': 110819, 'loss/train': 1.1237578392028809} 08/31/2021 09:19:17 - INFO - __main__ - Step 110821: {'lr': 8.158993096593437e-05, 'samples': 21277632, 'steps': 110820, 'loss/train': 1.0117851495742798} 08/31/2021 09:19:19 - INFO - __main__ - Step 110822: {'lr': 8.15860090046488e-05, 'samples': 21277824, 'steps': 110821, 'loss/train': 1.1937795877456665} 08/31/2021 09:19:19 - INFO - __main__ - Step 110823: {'lr': 8.1582087119248e-05, 'samples': 21278016, 'steps': 110822, 'loss/train': 0.533856987953186} 08/31/2021 09:19:20 - INFO - __main__ - Step 110824: {'lr': 8.15781653097337e-05, 'samples': 21278208, 'steps': 110823, 'loss/train': 0.43406400084495544} 08/31/2021 09:19:20 - INFO - __main__ - Step 110825: {'lr': 8.157424357610768e-05, 'samples': 21278400, 'steps': 110824, 'loss/train': 1.018927812576294} 08/31/2021 09:19:20 - INFO - __main__ - Step 110826: {'lr': 8.157032191837171e-05, 'samples': 21278592, 'steps': 110825, 'loss/train': 1.4662045240402222} 08/31/2021 09:19:22 - INFO - __main__ - Step 110827: {'lr': 8.156640033652754e-05, 'samples': 21278784, 'steps': 110826, 'loss/train': 1.3992668390274048} 08/31/2021 09:19:22 - INFO - __main__ - Step 110828: {'lr': 8.156247883057696e-05, 'samples': 21278976, 'steps': 110827, 'loss/train': 1.471885085105896} 08/31/2021 09:19:23 - INFO - __main__ - Step 110829: {'lr': 8.155855740052173e-05, 'samples': 21279168, 'steps': 110828, 'loss/train': 0.6836485862731934} 08/31/2021 09:19:23 - INFO - __main__ - Step 110830: {'lr': 8.15546360463637e-05, 'samples': 21279360, 'steps': 110829, 'loss/train': 0.7683542370796204} 08/31/2021 09:19:23 - INFO - __main__ - Step 110831: {'lr': 8.155071476810446e-05, 'samples': 21279552, 'steps': 110830, 'loss/train': 0.09313567727804184} 08/31/2021 09:19:24 - INFO - __main__ - Step 110832: {'lr': 8.15467935657459e-05, 'samples': 21279744, 'steps': 110831, 'loss/train': 1.5284385681152344} 08/31/2021 09:19:25 - INFO - __main__ - Step 110833: {'lr': 8.154287243928973e-05, 'samples': 21279936, 'steps': 110832, 'loss/train': 1.3623627424240112} 08/31/2021 09:19:26 - INFO - __main__ - Step 110834: {'lr': 8.153895138873773e-05, 'samples': 21280128, 'steps': 110833, 'loss/train': 0.9388112425804138} 08/31/2021 09:19:26 - INFO - __main__ - Step 110835: {'lr': 8.153503041409172e-05, 'samples': 21280320, 'steps': 110834, 'loss/train': 0.3925044536590576} 08/31/2021 09:19:26 - INFO - __main__ - Step 110836: {'lr': 8.153110951535339e-05, 'samples': 21280512, 'steps': 110835, 'loss/train': 1.2845265865325928} 08/31/2021 09:19:27 - INFO - __main__ - Step 110837: {'lr': 8.152718869252454e-05, 'samples': 21280704, 'steps': 110836, 'loss/train': 1.0005404949188232} 08/31/2021 09:19:28 - INFO - __main__ - Step 110838: {'lr': 8.152326794560697e-05, 'samples': 21280896, 'steps': 110837, 'loss/train': 1.3834824562072754} 08/31/2021 09:19:29 - INFO - __main__ - Step 110839: {'lr': 8.151934727460239e-05, 'samples': 21281088, 'steps': 110838, 'loss/train': 0.6861399412155151} 08/31/2021 09:19:29 - INFO - __main__ - Step 110840: {'lr': 8.151542667951258e-05, 'samples': 21281280, 'steps': 110839, 'loss/train': 1.5267096757888794} 08/31/2021 09:19:29 - INFO - __main__ - Step 110841: {'lr': 8.151150616033934e-05, 'samples': 21281472, 'steps': 110840, 'loss/train': 1.540294885635376} 08/31/2021 09:19:30 - INFO - __main__ - Step 110842: {'lr': 8.150758571708442e-05, 'samples': 21281664, 'steps': 110841, 'loss/train': 1.0068776607513428} 08/31/2021 09:19:31 - INFO - __main__ - Step 110843: {'lr': 8.150366534974956e-05, 'samples': 21281856, 'steps': 110842, 'loss/train': 0.22340235114097595} 08/31/2021 09:19:32 - INFO - __main__ - Step 110844: {'lr': 8.149974505833665e-05, 'samples': 21282048, 'steps': 110843, 'loss/train': 1.4042677879333496} 08/31/2021 09:19:32 - INFO - __main__ - Step 110845: {'lr': 8.149582484284728e-05, 'samples': 21282240, 'steps': 110844, 'loss/train': 1.6348825693130493} 08/31/2021 09:19:32 - INFO - __main__ - Step 110846: {'lr': 8.149190470328327e-05, 'samples': 21282432, 'steps': 110845, 'loss/train': 0.7659494280815125} 08/31/2021 09:19:33 - INFO - __main__ - Step 110847: {'lr': 8.148798463964643e-05, 'samples': 21282624, 'steps': 110846, 'loss/train': 1.645550012588501} 08/31/2021 09:19:34 - INFO - __main__ - Step 110848: {'lr': 8.14840646519385e-05, 'samples': 21282816, 'steps': 110847, 'loss/train': 1.0163671970367432} 08/31/2021 09:19:35 - INFO - __main__ - Step 110849: {'lr': 8.148014474016122e-05, 'samples': 21283008, 'steps': 110848, 'loss/train': 0.12480110675096512} 08/31/2021 09:19:35 - INFO - __main__ - Step 110850: {'lr': 8.147622490431642e-05, 'samples': 21283200, 'steps': 110849, 'loss/train': 1.5856136083602905} 08/31/2021 09:19:35 - INFO - __main__ - Step 110851: {'lr': 8.147230514440582e-05, 'samples': 21283392, 'steps': 110850, 'loss/train': 0.22982929646968842} 08/31/2021 09:19:36 - INFO - __main__ - Step 110852: {'lr': 8.146838546043119e-05, 'samples': 21283584, 'steps': 110851, 'loss/train': 0.6894606947898865} 08/31/2021 09:19:38 - INFO - __main__ - Step 110853: {'lr': 8.14644658523943e-05, 'samples': 21283776, 'steps': 110852, 'loss/train': 1.0928677320480347} 08/31/2021 09:19:38 - INFO - __main__ - Step 110854: {'lr': 8.146054632029695e-05, 'samples': 21283968, 'steps': 110853, 'loss/train': 1.460311770439148} 08/31/2021 09:19:38 - INFO - __main__ - Step 110855: {'lr': 8.145662686414085e-05, 'samples': 21284160, 'steps': 110854, 'loss/train': 0.03248963505029678} 08/31/2021 09:19:39 - INFO - __main__ - Step 110856: {'lr': 8.14527074839278e-05, 'samples': 21284352, 'steps': 110855, 'loss/train': 1.1844977140426636} 08/31/2021 09:19:39 - INFO - __main__ - Step 110857: {'lr': 8.144878817965968e-05, 'samples': 21284544, 'steps': 110856, 'loss/train': 4.2942214012146} 08/31/2021 09:19:39 - INFO - __main__ - Step 110858: {'lr': 8.144486895133798e-05, 'samples': 21284736, 'steps': 110857, 'loss/train': 0.9436736702919006} 08/31/2021 09:19:41 - INFO - __main__ - Step 110859: {'lr': 8.144094979896469e-05, 'samples': 21284928, 'steps': 110858, 'loss/train': 0.8517507910728455} 08/31/2021 09:19:41 - INFO - __main__ - Step 110860: {'lr': 8.143703072254147e-05, 'samples': 21285120, 'steps': 110859, 'loss/train': 0.6915028095245361} 08/31/2021 09:19:42 - INFO - __main__ - Step 110861: {'lr': 8.143311172207013e-05, 'samples': 21285312, 'steps': 110860, 'loss/train': 0.9697514772415161} 08/31/2021 09:19:42 - INFO - __main__ - Step 110862: {'lr': 8.142919279755243e-05, 'samples': 21285504, 'steps': 110861, 'loss/train': 0.18420836329460144} 08/31/2021 09:19:42 - INFO - __main__ - Step 110863: {'lr': 8.142527394899013e-05, 'samples': 21285696, 'steps': 110862, 'loss/train': 1.3359047174453735} 08/31/2021 09:19:44 - INFO - __main__ - Step 110864: {'lr': 8.1421355176385e-05, 'samples': 21285888, 'steps': 110863, 'loss/train': 0.7829208970069885} 08/31/2021 09:19:44 - INFO - __main__ - Step 110865: {'lr': 8.141743647973881e-05, 'samples': 21286080, 'steps': 110864, 'loss/train': 1.5656569004058838} 08/31/2021 09:19:45 - INFO - __main__ - Step 110866: {'lr': 8.141351785905332e-05, 'samples': 21286272, 'steps': 110865, 'loss/train': 1.5020723342895508} 08/31/2021 09:19:45 - INFO - __main__ - Step 110867: {'lr': 8.140959931433028e-05, 'samples': 21286464, 'steps': 110866, 'loss/train': 1.2369385957717896} 08/31/2021 09:19:45 - INFO - __main__ - Step 110868: {'lr': 8.140568084557151e-05, 'samples': 21286656, 'steps': 110867, 'loss/train': 0.9040202498435974} 08/31/2021 09:19:47 - INFO - __main__ - Step 110869: {'lr': 8.140176245277872e-05, 'samples': 21286848, 'steps': 110868, 'loss/train': 0.9901378750801086} 08/31/2021 09:19:47 - INFO - __main__ - Step 110870: {'lr': 8.139784413595369e-05, 'samples': 21287040, 'steps': 110869, 'loss/train': 1.4091262817382812} 08/31/2021 09:19:48 - INFO - __main__ - Step 110871: {'lr': 8.139392589509827e-05, 'samples': 21287232, 'steps': 110870, 'loss/train': 0.5216642618179321} 08/31/2021 09:19:48 - INFO - __main__ - Step 110872: {'lr': 8.139000773021407e-05, 'samples': 21287424, 'steps': 110871, 'loss/train': 1.2926177978515625} 08/31/2021 09:19:48 - INFO - __main__ - Step 110873: {'lr': 8.138608964130292e-05, 'samples': 21287616, 'steps': 110872, 'loss/train': 0.3052144944667816} 08/31/2021 09:19:49 - INFO - __main__ - Step 110874: {'lr': 8.138217162836662e-05, 'samples': 21287808, 'steps': 110873, 'loss/train': 0.876129686832428} 08/31/2021 09:19:52 - INFO - __main__ - Step 110875: {'lr': 8.137825369140689e-05, 'samples': 21288000, 'steps': 110874, 'loss/train': 1.0183693170547485} 08/31/2021 09:19:52 - INFO - __main__ - Step 110876: {'lr': 8.137433583042553e-05, 'samples': 21288192, 'steps': 110875, 'loss/train': 1.6377019882202148} 08/31/2021 09:19:52 - INFO - __main__ - Step 110877: {'lr': 8.13704180454243e-05, 'samples': 21288384, 'steps': 110876, 'loss/train': 1.7257003784179688} 08/31/2021 09:19:53 - INFO - __main__ - Step 110878: {'lr': 8.136650033640494e-05, 'samples': 21288576, 'steps': 110877, 'loss/train': 0.8884322047233582} 08/31/2021 09:19:53 - INFO - __main__ - Step 110879: {'lr': 8.136258270336924e-05, 'samples': 21288768, 'steps': 110878, 'loss/train': 1.1085166931152344} 08/31/2021 09:19:53 - INFO - __main__ - Step 110880: {'lr': 8.135866514631895e-05, 'samples': 21288960, 'steps': 110879, 'loss/train': 1.1198158264160156} 08/31/2021 09:19:55 - INFO - __main__ - Step 110881: {'lr': 8.135474766525586e-05, 'samples': 21289152, 'steps': 110880, 'loss/train': 0.9669467210769653} 08/31/2021 09:19:55 - INFO - __main__ - Step 110882: {'lr': 8.135083026018169e-05, 'samples': 21289344, 'steps': 110881, 'loss/train': 1.1653889417648315} 08/31/2021 09:19:56 - INFO - __main__ - Step 110883: {'lr': 8.134691293109825e-05, 'samples': 21289536, 'steps': 110882, 'loss/train': 1.4478135108947754} 08/31/2021 09:19:56 - INFO - __main__ - Step 110884: {'lr': 8.134299567800738e-05, 'samples': 21289728, 'steps': 110883, 'loss/train': 0.347724974155426} 08/31/2021 09:19:56 - INFO - __main__ - Step 110885: {'lr': 8.133907850091066e-05, 'samples': 21289920, 'steps': 110884, 'loss/train': 1.1555734872817993} 08/31/2021 09:19:58 - INFO - __main__ - Step 110886: {'lr': 8.133516139980996e-05, 'samples': 21290112, 'steps': 110885, 'loss/train': 0.1228264570236206} 08/31/2021 09:19:58 - INFO - __main__ - Step 110887: {'lr': 8.133124437470702e-05, 'samples': 21290304, 'steps': 110886, 'loss/train': 0.11800941824913025} 08/31/2021 09:19:59 - INFO - __main__ - Step 110888: {'lr': 8.132732742560361e-05, 'samples': 21290496, 'steps': 110887, 'loss/train': 0.903942346572876} 08/31/2021 09:19:59 - INFO - __main__ - Step 110889: {'lr': 8.132341055250153e-05, 'samples': 21290688, 'steps': 110888, 'loss/train': 2.404873847961426} 08/31/2021 09:19:59 - INFO - __main__ - Step 110890: {'lr': 8.131949375540249e-05, 'samples': 21290880, 'steps': 110889, 'loss/train': 1.1852707862854004} 08/31/2021 09:20:00 - INFO - __main__ - Step 110891: {'lr': 8.13155770343083e-05, 'samples': 21291072, 'steps': 110890, 'loss/train': 0.7976445555686951} 08/31/2021 09:20:02 - INFO - __main__ - Step 110892: {'lr': 8.131166038922072e-05, 'samples': 21291264, 'steps': 110891, 'loss/train': 0.15649373829364777} 08/31/2021 09:20:02 - INFO - __main__ - Step 110893: {'lr': 8.130774382014147e-05, 'samples': 21291456, 'steps': 110892, 'loss/train': 1.3925285339355469} 08/31/2021 09:20:02 - INFO - __main__ - Step 110894: {'lr': 8.130382732707236e-05, 'samples': 21291648, 'steps': 110893, 'loss/train': 1.0622024536132812} 08/31/2021 09:20:03 - INFO - __main__ - Step 110895: {'lr': 8.129991091001515e-05, 'samples': 21291840, 'steps': 110894, 'loss/train': 0.7432510852813721} 08/31/2021 09:20:03 - INFO - __main__ - Step 110896: {'lr': 8.12959945689716e-05, 'samples': 21292032, 'steps': 110895, 'loss/train': 1.1452444791793823} 08/31/2021 09:20:05 - INFO - __main__ - Step 110897: {'lr': 8.129207830394355e-05, 'samples': 21292224, 'steps': 110896, 'loss/train': 0.7068078517913818} 08/31/2021 09:20:05 - INFO - __main__ - Step 110898: {'lr': 8.128816211493261e-05, 'samples': 21292416, 'steps': 110897, 'loss/train': 0.8754367828369141} 08/31/2021 09:20:06 - INFO - __main__ - Step 110899: {'lr': 8.128424600194062e-05, 'samples': 21292608, 'steps': 110898, 'loss/train': 1.0390634536743164} 08/31/2021 09:20:06 - INFO - __main__ - Step 110900: {'lr': 8.128032996496934e-05, 'samples': 21292800, 'steps': 110899, 'loss/train': 0.36742013692855835} 08/31/2021 09:20:06 - INFO - __main__ - Step 110901: {'lr': 8.127641400402053e-05, 'samples': 21292992, 'steps': 110900, 'loss/train': 1.051509976387024} 08/31/2021 09:20:08 - INFO - __main__ - Step 110902: {'lr': 8.127249811909598e-05, 'samples': 21293184, 'steps': 110901, 'loss/train': 0.16007985174655914} 08/31/2021 09:20:08 - INFO - __main__ - Step 110903: {'lr': 8.126858231019742e-05, 'samples': 21293376, 'steps': 110902, 'loss/train': 1.4589557647705078} 08/31/2021 09:20:09 - INFO - __main__ - Step 110904: {'lr': 8.126466657732665e-05, 'samples': 21293568, 'steps': 110903, 'loss/train': 1.1696710586547852} 08/31/2021 09:20:09 - INFO - __main__ - Step 110905: {'lr': 8.126075092048541e-05, 'samples': 21293760, 'steps': 110904, 'loss/train': 1.2400892972946167} 08/31/2021 09:20:09 - INFO - __main__ - Step 110906: {'lr': 8.125683533967548e-05, 'samples': 21293952, 'steps': 110905, 'loss/train': 0.990506649017334} 08/31/2021 09:20:11 - INFO - __main__ - Step 110907: {'lr': 8.12529198348986e-05, 'samples': 21294144, 'steps': 110906, 'loss/train': 1.2876534461975098} 08/31/2021 09:20:12 - INFO - __main__ - Step 110908: {'lr': 8.124900440615657e-05, 'samples': 21294336, 'steps': 110907, 'loss/train': 1.094556212425232} 08/31/2021 09:20:12 - INFO - __main__ - Step 110909: {'lr': 8.124508905345112e-05, 'samples': 21294528, 'steps': 110908, 'loss/train': 1.7390952110290527} 08/31/2021 09:20:12 - INFO - __main__ - Step 110910: {'lr': 8.124117377678405e-05, 'samples': 21294720, 'steps': 110909, 'loss/train': 1.6079756021499634} 08/31/2021 09:20:13 - INFO - __main__ - Step 110911: {'lr': 8.123725857615716e-05, 'samples': 21294912, 'steps': 110910, 'loss/train': 2.70717191696167} 08/31/2021 09:20:13 - INFO - __main__ - Step 110912: {'lr': 8.12333434515721e-05, 'samples': 21295104, 'steps': 110911, 'loss/train': 1.5991610288619995} 08/31/2021 09:20:15 - INFO - __main__ - Step 110913: {'lr': 8.122942840303067e-05, 'samples': 21295296, 'steps': 110912, 'loss/train': 1.724639654159546} 08/31/2021 09:20:15 - INFO - __main__ - Step 110914: {'lr': 8.122551343053467e-05, 'samples': 21295488, 'steps': 110913, 'loss/train': 1.0492889881134033} 08/31/2021 09:20:15 - INFO - __main__ - Step 110915: {'lr': 8.122159853408583e-05, 'samples': 21295680, 'steps': 110914, 'loss/train': 1.092934012413025} 08/31/2021 09:20:16 - INFO - __main__ - Step 110916: {'lr': 8.121768371368593e-05, 'samples': 21295872, 'steps': 110915, 'loss/train': 0.9336517453193665} 08/31/2021 09:20:16 - INFO - __main__ - Step 110917: {'lr': 8.121376896933677e-05, 'samples': 21296064, 'steps': 110916, 'loss/train': 0.7217824459075928} 08/31/2021 09:20:18 - INFO - __main__ - Step 110918: {'lr': 8.120985430104005e-05, 'samples': 21296256, 'steps': 110917, 'loss/train': 0.683821976184845} 08/31/2021 09:20:18 - INFO - __main__ - Step 110919: {'lr': 8.120593970879758e-05, 'samples': 21296448, 'steps': 110918, 'loss/train': 1.2807612419128418} 08/31/2021 09:20:19 - INFO - __main__ - Step 110920: {'lr': 8.120202519261111e-05, 'samples': 21296640, 'steps': 110919, 'loss/train': 0.35358288884162903} 08/31/2021 09:20:19 - INFO - __main__ - Step 110921: {'lr': 8.11981107524824e-05, 'samples': 21296832, 'steps': 110920, 'loss/train': 0.18279357254505157} 08/31/2021 09:20:19 - INFO - __main__ - Step 110922: {'lr': 8.119419638841322e-05, 'samples': 21297024, 'steps': 110921, 'loss/train': 0.020404433831572533} 08/31/2021 09:20:20 - INFO - __main__ - Step 110923: {'lr': 8.119028210040533e-05, 'samples': 21297216, 'steps': 110922, 'loss/train': 0.6219609975814819} 08/31/2021 09:20:21 - INFO - __main__ - Step 110924: {'lr': 8.118636788846057e-05, 'samples': 21297408, 'steps': 110923, 'loss/train': 0.060424938797950745} 08/31/2021 09:20:22 - INFO - __main__ - Step 110925: {'lr': 8.118245375258055e-05, 'samples': 21297600, 'steps': 110924, 'loss/train': 1.3044894933700562} 08/31/2021 09:20:22 - INFO - __main__ - Step 110926: {'lr': 8.11785396927671e-05, 'samples': 21297792, 'steps': 110925, 'loss/train': 0.6462001204490662} 08/31/2021 09:20:22 - INFO - __main__ - Step 110927: {'lr': 8.117462570902201e-05, 'samples': 21297984, 'steps': 110926, 'loss/train': 1.153467059135437} 08/31/2021 09:20:23 - INFO - __main__ - Step 110928: {'lr': 8.117071180134703e-05, 'samples': 21298176, 'steps': 110927, 'loss/train': 0.4478788673877716} 08/31/2021 09:20:25 - INFO - __main__ - Step 110929: {'lr': 8.116679796974389e-05, 'samples': 21298368, 'steps': 110928, 'loss/train': 1.381720781326294} 08/31/2021 09:20:25 - INFO - __main__ - Step 110930: {'lr': 8.116288421421441e-05, 'samples': 21298560, 'steps': 110929, 'loss/train': 0.3727119565010071} 08/31/2021 09:20:26 - INFO - __main__ - Step 110931: {'lr': 8.115897053476034e-05, 'samples': 21298752, 'steps': 110930, 'loss/train': 1.386500597000122} 08/31/2021 09:20:26 - INFO - __main__ - Step 110932: {'lr': 8.115505693138341e-05, 'samples': 21298944, 'steps': 110931, 'loss/train': 1.5211029052734375} 08/31/2021 09:20:26 - INFO - __main__ - Step 110933: {'lr': 8.115114340408541e-05, 'samples': 21299136, 'steps': 110932, 'loss/train': 1.2148499488830566} 08/31/2021 09:20:28 - INFO - __main__ - Step 110934: {'lr': 8.114722995286811e-05, 'samples': 21299328, 'steps': 110933, 'loss/train': 1.234209418296814} 08/31/2021 09:20:29 - INFO - __main__ - Step 110935: {'lr': 8.114331657773327e-05, 'samples': 21299520, 'steps': 110934, 'loss/train': 2.3357510566711426} 08/31/2021 09:20:29 - INFO - __main__ - Step 110936: {'lr': 8.113940327868263e-05, 'samples': 21299712, 'steps': 110935, 'loss/train': 0.9490737915039062} 08/31/2021 09:20:29 - INFO - __main__ - Step 110937: {'lr': 8.1135490055718e-05, 'samples': 21299904, 'steps': 110936, 'loss/train': 1.050499439239502} 08/31/2021 09:20:30 - INFO - __main__ - Step 110938: {'lr': 8.113157690884115e-05, 'samples': 21300096, 'steps': 110937, 'loss/train': 0.025004548951983452} 08/31/2021 09:20:31 - INFO - __main__ - Step 110939: {'lr': 8.112766383805373e-05, 'samples': 21300288, 'steps': 110938, 'loss/train': 1.226353406906128} 08/31/2021 09:20:32 - INFO - __main__ - Step 110940: {'lr': 8.11237508433576e-05, 'samples': 21300480, 'steps': 110939, 'loss/train': 0.6286027431488037} 08/31/2021 09:20:32 - INFO - __main__ - Step 110941: {'lr': 8.111983792475449e-05, 'samples': 21300672, 'steps': 110940, 'loss/train': 0.7536914348602295} 08/31/2021 09:20:32 - INFO - __main__ - Step 110942: {'lr': 8.111592508224618e-05, 'samples': 21300864, 'steps': 110941, 'loss/train': 0.5702789425849915} 08/31/2021 09:20:33 - INFO - __main__ - Step 110943: {'lr': 8.111201231583443e-05, 'samples': 21301056, 'steps': 110942, 'loss/train': 0.8708254098892212} 08/31/2021 09:20:33 - INFO - __main__ - Step 110944: {'lr': 8.110809962552099e-05, 'samples': 21301248, 'steps': 110943, 'loss/train': 0.45632484555244446} 08/31/2021 09:20:34 - INFO - __main__ - Step 110945: {'lr': 8.110418701130765e-05, 'samples': 21301440, 'steps': 110944, 'loss/train': 0.6292262673377991} 08/31/2021 09:20:35 - INFO - __main__ - Step 110946: {'lr': 8.110027447319614e-05, 'samples': 21301632, 'steps': 110945, 'loss/train': 1.7185722589492798} 08/31/2021 09:20:35 - INFO - __main__ - Step 110947: {'lr': 8.109636201118825e-05, 'samples': 21301824, 'steps': 110946, 'loss/train': 1.113127589225769} 08/31/2021 09:20:36 - INFO - __main__ - Step 110948: {'lr': 8.109244962528575e-05, 'samples': 21302016, 'steps': 110947, 'loss/train': 1.2489516735076904} 08/31/2021 09:20:36 - INFO - __main__ - Step 110949: {'lr': 8.108853731549035e-05, 'samples': 21302208, 'steps': 110948, 'loss/train': 1.0652189254760742} 08/31/2021 09:20:37 - INFO - __main__ - Step 110950: {'lr': 8.108462508180386e-05, 'samples': 21302400, 'steps': 110949, 'loss/train': 0.5701164603233337} 08/31/2021 09:20:38 - INFO - __main__ - Step 110951: {'lr': 8.108071292422815e-05, 'samples': 21302592, 'steps': 110950, 'loss/train': 1.1484723091125488} 08/31/2021 09:20:38 - INFO - __main__ - Step 110952: {'lr': 8.107680084276472e-05, 'samples': 21302784, 'steps': 110951, 'loss/train': 0.5964537262916565} 08/31/2021 09:20:39 - INFO - __main__ - Step 110953: {'lr': 8.10728888374155e-05, 'samples': 21302976, 'steps': 110952, 'loss/train': 1.6492266654968262} 08/31/2021 09:20:39 - INFO - __main__ - Step 110954: {'lr': 8.106897690818227e-05, 'samples': 21303168, 'steps': 110953, 'loss/train': 0.8164345622062683} 08/31/2021 09:20:41 - INFO - __main__ - Step 110955: {'lr': 8.106506505506672e-05, 'samples': 21303360, 'steps': 110954, 'loss/train': 1.1798213720321655} 08/31/2021 09:20:41 - INFO - __main__ - Step 110956: {'lr': 8.106115327807064e-05, 'samples': 21303552, 'steps': 110955, 'loss/train': 0.04010573402047157} 08/31/2021 09:20:41 - INFO - __main__ - Step 110957: {'lr': 8.10572415771958e-05, 'samples': 21303744, 'steps': 110956, 'loss/train': 0.8798914551734924} 08/31/2021 09:20:42 - INFO - __main__ - Step 110958: {'lr': 8.105332995244396e-05, 'samples': 21303936, 'steps': 110957, 'loss/train': 1.2500096559524536} 08/31/2021 09:20:42 - INFO - __main__ - Step 110959: {'lr': 8.104941840381689e-05, 'samples': 21304128, 'steps': 110958, 'loss/train': 1.3956470489501953} 08/31/2021 09:20:44 - INFO - __main__ - Step 110960: {'lr': 8.104550693131635e-05, 'samples': 21304320, 'steps': 110959, 'loss/train': 0.8952248692512512} 08/31/2021 09:20:44 - INFO - __main__ - Step 110961: {'lr': 8.104159553494408e-05, 'samples': 21304512, 'steps': 110960, 'loss/train': 0.6092697978019714} 08/31/2021 09:20:45 - INFO - __main__ - Step 110962: {'lr': 8.103768421470187e-05, 'samples': 21304704, 'steps': 110961, 'loss/train': 1.8278206586837769} 08/31/2021 09:20:45 - INFO - __main__ - Step 110963: {'lr': 8.103377297059147e-05, 'samples': 21304896, 'steps': 110962, 'loss/train': 0.8706375956535339} 08/31/2021 09:20:45 - INFO - __main__ - Step 110964: {'lr': 8.102986180261473e-05, 'samples': 21305088, 'steps': 110963, 'loss/train': 1.307450771331787} 08/31/2021 09:20:47 - INFO - __main__ - Step 110965: {'lr': 8.102595071077323e-05, 'samples': 21305280, 'steps': 110964, 'loss/train': 0.46606382727622986} 08/31/2021 09:20:48 - INFO - __main__ - Step 110966: {'lr': 8.102203969506886e-05, 'samples': 21305472, 'steps': 110965, 'loss/train': 0.9419986009597778} 08/31/2021 09:20:48 - INFO - __main__ - Step 110967: {'lr': 8.101812875550332e-05, 'samples': 21305664, 'steps': 110966, 'loss/train': 1.0340521335601807} 08/31/2021 09:20:48 - INFO - __main__ - Step 110968: {'lr': 8.101421789207841e-05, 'samples': 21305856, 'steps': 110967, 'loss/train': 0.9382449388504028} 08/31/2021 09:20:49 - INFO - __main__ - Step 110969: {'lr': 8.10103071047959e-05, 'samples': 21306048, 'steps': 110968, 'loss/train': 0.08129721879959106} 08/31/2021 09:20:50 - INFO - __main__ - Step 110970: {'lr': 8.100639639365754e-05, 'samples': 21306240, 'steps': 110969, 'loss/train': 0.2585478127002716} 08/31/2021 09:20:51 - INFO - __main__ - Step 110971: {'lr': 8.100248575866506e-05, 'samples': 21306432, 'steps': 110970, 'loss/train': 1.4839303493499756} 08/31/2021 09:20:51 - INFO - __main__ - Step 110972: {'lr': 8.099857519982027e-05, 'samples': 21306624, 'steps': 110971, 'loss/train': 0.41285452246665955} 08/31/2021 09:20:51 - INFO - __main__ - Step 110973: {'lr': 8.099466471712491e-05, 'samples': 21306816, 'steps': 110972, 'loss/train': 1.1373491287231445} 08/31/2021 09:20:52 - INFO - __main__ - Step 110974: {'lr': 8.099075431058075e-05, 'samples': 21307008, 'steps': 110973, 'loss/train': 0.2385297268629074} 08/31/2021 09:20:52 - INFO - __main__ - Step 110975: {'lr': 8.098684398018965e-05, 'samples': 21307200, 'steps': 110974, 'loss/train': 0.2856498658657074} 08/31/2021 09:20:54 - INFO - __main__ - Step 110976: {'lr': 8.098293372595317e-05, 'samples': 21307392, 'steps': 110975, 'loss/train': 1.1357136964797974} 08/31/2021 09:20:54 - INFO - __main__ - Step 110977: {'lr': 8.097902354787318e-05, 'samples': 21307584, 'steps': 110976, 'loss/train': 0.42608842253685} 08/31/2021 09:20:54 - INFO - __main__ - Step 110978: {'lr': 8.097511344595141e-05, 'samples': 21307776, 'steps': 110977, 'loss/train': 0.9540767669677734} 08/31/2021 09:20:55 - INFO - __main__ - Step 110979: {'lr': 8.097120342018965e-05, 'samples': 21307968, 'steps': 110978, 'loss/train': 1.4212568998336792} 08/31/2021 09:20:55 - INFO - __main__ - Step 110980: {'lr': 8.096729347058968e-05, 'samples': 21308160, 'steps': 110979, 'loss/train': 1.5577874183654785} 08/31/2021 09:20:57 - INFO - __main__ - Step 110981: {'lr': 8.096338359715322e-05, 'samples': 21308352, 'steps': 110980, 'loss/train': 0.5647892951965332} 08/31/2021 09:20:57 - INFO - __main__ - Step 110982: {'lr': 8.095947379988208e-05, 'samples': 21308544, 'steps': 110981, 'loss/train': 1.2150765657424927} 08/31/2021 09:20:58 - INFO - __main__ - Step 110983: {'lr': 8.095556407877796e-05, 'samples': 21308736, 'steps': 110982, 'loss/train': 1.388008952140808} 08/31/2021 09:20:58 - INFO - __main__ - Step 110984: {'lr': 8.095165443384267e-05, 'samples': 21308928, 'steps': 110983, 'loss/train': 1.3629711866378784} 08/31/2021 09:20:58 - INFO - __main__ - Step 110985: {'lr': 8.094774486507794e-05, 'samples': 21309120, 'steps': 110984, 'loss/train': 0.44515568017959595} 08/31/2021 09:21:00 - INFO - __main__ - Step 110986: {'lr': 8.094383537248565e-05, 'samples': 21309312, 'steps': 110985, 'loss/train': 2.0541436672210693} 08/31/2021 09:21:01 - INFO - __main__ - Step 110987: {'lr': 8.093992595606736e-05, 'samples': 21309504, 'steps': 110986, 'loss/train': 1.2374403476715088} 08/31/2021 09:21:01 - INFO - __main__ - Step 110988: {'lr': 8.093601661582495e-05, 'samples': 21309696, 'steps': 110987, 'loss/train': 1.3004151582717896} 08/31/2021 09:21:02 - INFO - __main__ - Step 110989: {'lr': 8.093210735176015e-05, 'samples': 21309888, 'steps': 110988, 'loss/train': 1.733559250831604} 08/31/2021 09:21:02 - INFO - __main__ - Step 110990: {'lr': 8.092819816387472e-05, 'samples': 21310080, 'steps': 110989, 'loss/train': 1.2058922052383423} 08/31/2021 09:21:03 - INFO - __main__ - Step 110991: {'lr': 8.092428905217048e-05, 'samples': 21310272, 'steps': 110990, 'loss/train': 1.3648631572723389} 08/31/2021 09:21:04 - INFO - __main__ - Step 110992: {'lr': 8.092038001664912e-05, 'samples': 21310464, 'steps': 110991, 'loss/train': 1.2484831809997559} 08/31/2021 09:21:04 - INFO - __main__ - Step 110993: {'lr': 8.09164710573124e-05, 'samples': 21310656, 'steps': 110992, 'loss/train': 1.0076889991760254} 08/31/2021 09:21:05 - INFO - __main__ - Step 110994: {'lr': 8.091256217416215e-05, 'samples': 21310848, 'steps': 110993, 'loss/train': 1.1099159717559814} 08/31/2021 09:21:05 - INFO - __main__ - Step 110995: {'lr': 8.090865336720007e-05, 'samples': 21311040, 'steps': 110994, 'loss/train': 0.9414185285568237} 08/31/2021 09:21:07 - INFO - __main__ - Step 110996: {'lr': 8.090474463642794e-05, 'samples': 21311232, 'steps': 110995, 'loss/train': 1.0844404697418213} 08/31/2021 09:21:07 - INFO - __main__ - Step 110997: {'lr': 8.09008359818476e-05, 'samples': 21311424, 'steps': 110996, 'loss/train': 0.6486649513244629} 08/31/2021 09:21:07 - INFO - __main__ - Step 110998: {'lr': 8.089692740346066e-05, 'samples': 21311616, 'steps': 110997, 'loss/train': 1.3514848947525024} 08/31/2021 09:21:08 - INFO - __main__ - Step 110999: {'lr': 8.089301890126896e-05, 'samples': 21311808, 'steps': 110998, 'loss/train': 0.7305724620819092} 08/31/2021 09:21:08 - INFO - __main__ - Step 111000: {'lr': 8.088911047527425e-05, 'samples': 21312000, 'steps': 110999, 'loss/train': 1.2516098022460938} 08/31/2021 09:21:09 - INFO - __main__ - Step 111001: {'lr': 8.088520212547831e-05, 'samples': 21312192, 'steps': 111000, 'loss/train': 1.215801477432251} 08/31/2021 09:21:10 - INFO - __main__ - Step 111002: {'lr': 8.088129385188289e-05, 'samples': 21312384, 'steps': 111001, 'loss/train': 1.5322307348251343} 08/31/2021 09:21:10 - INFO - __main__ - Step 111003: {'lr': 8.087738565448974e-05, 'samples': 21312576, 'steps': 111002, 'loss/train': 1.1763521432876587} 08/31/2021 09:21:11 - INFO - __main__ - Step 111004: {'lr': 8.087347753330063e-05, 'samples': 21312768, 'steps': 111003, 'loss/train': 0.9304016828536987} 08/31/2021 09:21:11 - INFO - __main__ - Step 111005: {'lr': 8.08695694883173e-05, 'samples': 21312960, 'steps': 111004, 'loss/train': 1.771324634552002} 08/31/2021 09:21:13 - INFO - __main__ - Step 111006: {'lr': 8.086566151954156e-05, 'samples': 21313152, 'steps': 111005, 'loss/train': 0.890723466873169} 08/31/2021 09:21:13 - INFO - __main__ - Step 111007: {'lr': 8.086175362697513e-05, 'samples': 21313344, 'steps': 111006, 'loss/train': 1.1281405687332153} 08/31/2021 09:21:13 - INFO - __main__ - Step 111008: {'lr': 8.085784581061987e-05, 'samples': 21313536, 'steps': 111007, 'loss/train': 1.3752704858779907} 08/31/2021 09:21:14 - INFO - __main__ - Step 111009: {'lr': 8.085393807047737e-05, 'samples': 21313728, 'steps': 111008, 'loss/train': 1.10654878616333} 08/31/2021 09:21:14 - INFO - __main__ - Step 111010: {'lr': 8.085003040654948e-05, 'samples': 21313920, 'steps': 111009, 'loss/train': 1.8374297618865967} 08/31/2021 09:21:14 - INFO - __main__ - Step 111011: {'lr': 8.084612281883796e-05, 'samples': 21314112, 'steps': 111010, 'loss/train': 0.49988505244255066} 08/31/2021 09:21:16 - INFO - __main__ - Step 111012: {'lr': 8.084221530734457e-05, 'samples': 21314304, 'steps': 111011, 'loss/train': 1.600292682647705} 08/31/2021 09:21:17 - INFO - __main__ - Step 111013: {'lr': 8.083830787207106e-05, 'samples': 21314496, 'steps': 111012, 'loss/train': 0.35073351860046387} 08/31/2021 09:21:17 - INFO - __main__ - Step 111014: {'lr': 8.083440051301919e-05, 'samples': 21314688, 'steps': 111013, 'loss/train': 0.965486466884613} 08/31/2021 09:21:17 - INFO - __main__ - Step 111015: {'lr': 8.083049323019074e-05, 'samples': 21314880, 'steps': 111014, 'loss/train': 0.8586856722831726} 08/31/2021 09:21:18 - INFO - __main__ - Step 111016: {'lr': 8.082658602358745e-05, 'samples': 21315072, 'steps': 111015, 'loss/train': 1.2422722578048706} 08/31/2021 09:21:19 - INFO - __main__ - Step 111017: {'lr': 8.08226788932111e-05, 'samples': 21315264, 'steps': 111016, 'loss/train': 1.4780523777008057} 08/31/2021 09:21:20 - INFO - __main__ - Step 111018: {'lr': 8.081877183906342e-05, 'samples': 21315456, 'steps': 111017, 'loss/train': 1.1090121269226074} 08/31/2021 09:21:20 - INFO - __main__ - Step 111019: {'lr': 8.081486486114631e-05, 'samples': 21315648, 'steps': 111018, 'loss/train': 0.6069770455360413} 08/31/2021 09:21:20 - INFO - __main__ - Step 111020: {'lr': 8.08109579594613e-05, 'samples': 21315840, 'steps': 111019, 'loss/train': 0.8076378703117371} 08/31/2021 09:21:21 - INFO - __main__ - Step 111021: {'lr': 8.080705113401026e-05, 'samples': 21316032, 'steps': 111020, 'loss/train': 1.0907323360443115} 08/31/2021 09:21:22 - INFO - __main__ - Step 111022: {'lr': 8.080314438479496e-05, 'samples': 21316224, 'steps': 111021, 'loss/train': 0.6309570670127869} 08/31/2021 09:21:23 - INFO - __main__ - Step 111023: {'lr': 8.079923771181716e-05, 'samples': 21316416, 'steps': 111022, 'loss/train': 1.2546155452728271} 08/31/2021 09:21:23 - INFO - __main__ - Step 111024: {'lr': 8.079533111507861e-05, 'samples': 21316608, 'steps': 111023, 'loss/train': 1.1045047044754028} 08/31/2021 09:21:24 - INFO - __main__ - Step 111025: {'lr': 8.079142459458106e-05, 'samples': 21316800, 'steps': 111024, 'loss/train': 0.7780861854553223} 08/31/2021 09:21:24 - INFO - __main__ - Step 111026: {'lr': 8.078751815032629e-05, 'samples': 21316992, 'steps': 111025, 'loss/train': 1.3174799680709839} 08/31/2021 09:21:26 - INFO - __main__ - Step 111027: {'lr': 8.078361178231605e-05, 'samples': 21317184, 'steps': 111026, 'loss/train': 1.1378815174102783} 08/31/2021 09:21:26 - INFO - __main__ - Step 111028: {'lr': 8.07797054905521e-05, 'samples': 21317376, 'steps': 111027, 'loss/train': 0.9385119676589966} 08/31/2021 09:21:26 - INFO - __main__ - Step 111029: {'lr': 8.077579927503622e-05, 'samples': 21317568, 'steps': 111028, 'loss/train': 1.2208218574523926} 08/31/2021 09:21:27 - INFO - __main__ - Step 111030: {'lr': 8.077189313577016e-05, 'samples': 21317760, 'steps': 111029, 'loss/train': 1.3875932693481445} 08/31/2021 09:21:27 - INFO - __main__ - Step 111031: {'lr': 8.076798707275565e-05, 'samples': 21317952, 'steps': 111030, 'loss/train': 0.06042364612221718} 08/31/2021 09:21:29 - INFO - __main__ - Step 111032: {'lr': 8.076408108599456e-05, 'samples': 21318144, 'steps': 111031, 'loss/train': 1.234070897102356} 08/31/2021 09:21:29 - INFO - __main__ - Step 111033: {'lr': 8.07601751754885e-05, 'samples': 21318336, 'steps': 111032, 'loss/train': 0.6533655524253845} 08/31/2021 09:21:29 - INFO - __main__ - Step 111034: {'lr': 8.075626934123928e-05, 'samples': 21318528, 'steps': 111033, 'loss/train': 1.0232774019241333} 08/31/2021 09:21:30 - INFO - __main__ - Step 111035: {'lr': 8.075236358324866e-05, 'samples': 21318720, 'steps': 111034, 'loss/train': 1.0301960706710815} 08/31/2021 09:21:30 - INFO - __main__ - Step 111036: {'lr': 8.074845790151844e-05, 'samples': 21318912, 'steps': 111035, 'loss/train': 0.4574247896671295} 08/31/2021 09:21:32 - INFO - __main__ - Step 111037: {'lr': 8.074455229605032e-05, 'samples': 21319104, 'steps': 111036, 'loss/train': 1.1008189916610718} 08/31/2021 09:21:32 - INFO - __main__ - Step 111038: {'lr': 8.074064676684611e-05, 'samples': 21319296, 'steps': 111037, 'loss/train': 1.0112584829330444} 08/31/2021 09:21:33 - INFO - __main__ - Step 111039: {'lr': 8.073674131390757e-05, 'samples': 21319488, 'steps': 111038, 'loss/train': 0.9914848804473877} 08/31/2021 09:21:33 - INFO - __main__ - Step 111040: {'lr': 8.073283593723644e-05, 'samples': 21319680, 'steps': 111039, 'loss/train': 1.364237904548645} 08/31/2021 09:21:34 - INFO - __main__ - Step 111041: {'lr': 8.072893063683446e-05, 'samples': 21319872, 'steps': 111040, 'loss/train': 0.7567018270492554} 08/31/2021 09:21:34 - INFO - __main__ - Step 111042: {'lr': 8.07250254127034e-05, 'samples': 21320064, 'steps': 111041, 'loss/train': 0.7251223921775818} 08/31/2021 09:21:35 - INFO - __main__ - Step 111043: {'lr': 8.072112026484507e-05, 'samples': 21320256, 'steps': 111042, 'loss/train': 0.6572672128677368} 08/31/2021 09:21:36 - INFO - __main__ - Step 111044: {'lr': 8.071721519326117e-05, 'samples': 21320448, 'steps': 111043, 'loss/train': 0.8838102221488953} 08/31/2021 09:21:36 - INFO - __main__ - Step 111045: {'lr': 8.071331019795358e-05, 'samples': 21320640, 'steps': 111044, 'loss/train': 1.614128589630127} 08/31/2021 09:21:37 - INFO - __main__ - Step 111046: {'lr': 8.070940527892387e-05, 'samples': 21320832, 'steps': 111045, 'loss/train': 1.328478217124939} 08/31/2021 09:21:37 - INFO - __main__ - Step 111047: {'lr': 8.070550043617386e-05, 'samples': 21321024, 'steps': 111046, 'loss/train': 1.778333306312561} 08/31/2021 09:21:38 - INFO - __main__ - Step 111048: {'lr': 8.070159566970539e-05, 'samples': 21321216, 'steps': 111047, 'loss/train': 1.0837222337722778} 08/31/2021 09:21:39 - INFO - __main__ - Step 111049: {'lr': 8.069769097952012e-05, 'samples': 21321408, 'steps': 111048, 'loss/train': 1.1107960939407349} 08/31/2021 09:21:39 - INFO - __main__ - Step 111050: {'lr': 8.069378636561989e-05, 'samples': 21321600, 'steps': 111049, 'loss/train': 1.0765005350112915} 08/31/2021 09:21:40 - INFO - __main__ - Step 111051: {'lr': 8.068988182800641e-05, 'samples': 21321792, 'steps': 111050, 'loss/train': 0.9006152749061584} 08/31/2021 09:21:40 - INFO - __main__ - Step 111052: {'lr': 8.068597736668149e-05, 'samples': 21321984, 'steps': 111051, 'loss/train': 0.7428470253944397} 08/31/2021 09:21:41 - INFO - __main__ - Step 111053: {'lr': 8.068207298164682e-05, 'samples': 21322176, 'steps': 111052, 'loss/train': 1.531338095664978} 08/31/2021 09:21:42 - INFO - __main__ - Step 111054: {'lr': 8.06781686729042e-05, 'samples': 21322368, 'steps': 111053, 'loss/train': 1.1156177520751953} 08/31/2021 09:21:42 - INFO - __main__ - Step 111055: {'lr': 8.06742644404554e-05, 'samples': 21322560, 'steps': 111054, 'loss/train': 0.6979644894599915} 08/31/2021 09:21:43 - INFO - __main__ - Step 111056: {'lr': 8.067036028430213e-05, 'samples': 21322752, 'steps': 111055, 'loss/train': 1.3212600946426392} 08/31/2021 09:21:43 - INFO - __main__ - Step 111057: {'lr': 8.066645620444621e-05, 'samples': 21322944, 'steps': 111056, 'loss/train': 1.7781130075454712} 08/31/2021 09:21:44 - INFO - __main__ - Step 111058: {'lr': 8.066255220088939e-05, 'samples': 21323136, 'steps': 111057, 'loss/train': 1.0768734216690063} 08/31/2021 09:21:45 - INFO - __main__ - Step 111059: {'lr': 8.065864827363345e-05, 'samples': 21323328, 'steps': 111058, 'loss/train': 1.5927083492279053} 08/31/2021 09:21:45 - INFO - __main__ - Step 111060: {'lr': 8.065474442268006e-05, 'samples': 21323520, 'steps': 111059, 'loss/train': 0.5250332951545715} 08/31/2021 09:21:46 - INFO - __main__ - Step 111061: {'lr': 8.065084064803103e-05, 'samples': 21323712, 'steps': 111060, 'loss/train': 1.4598267078399658} 08/31/2021 09:21:46 - INFO - __main__ - Step 111062: {'lr': 8.064693694968808e-05, 'samples': 21323904, 'steps': 111061, 'loss/train': 1.262020468711853} 08/31/2021 09:21:46 - INFO - __main__ - Step 111063: {'lr': 8.064303332765305e-05, 'samples': 21324096, 'steps': 111062, 'loss/train': 1.311723232269287} 08/31/2021 09:21:48 - INFO - __main__ - Step 111064: {'lr': 8.063912978192763e-05, 'samples': 21324288, 'steps': 111063, 'loss/train': 0.9480278491973877} 08/31/2021 09:21:48 - INFO - __main__ - Step 111065: {'lr': 8.06352263125136e-05, 'samples': 21324480, 'steps': 111064, 'loss/train': 1.4344871044158936} 08/31/2021 09:21:49 - INFO - __main__ - Step 111066: {'lr': 8.063132291941275e-05, 'samples': 21324672, 'steps': 111065, 'loss/train': 0.6740182638168335} 08/31/2021 09:21:49 - INFO - __main__ - Step 111067: {'lr': 8.062741960262681e-05, 'samples': 21324864, 'steps': 111066, 'loss/train': 0.9425626993179321} 08/31/2021 09:21:49 - INFO - __main__ - Step 111068: {'lr': 8.062351636215753e-05, 'samples': 21325056, 'steps': 111067, 'loss/train': 0.8246594071388245} 08/31/2021 09:21:51 - INFO - __main__ - Step 111069: {'lr': 8.061961319800668e-05, 'samples': 21325248, 'steps': 111068, 'loss/train': 0.8841825723648071} 08/31/2021 09:21:52 - INFO - __main__ - Step 111070: {'lr': 8.061571011017601e-05, 'samples': 21325440, 'steps': 111069, 'loss/train': 0.9551910161972046} 08/31/2021 09:21:52 - INFO - __main__ - Step 111071: {'lr': 8.061180709866731e-05, 'samples': 21325632, 'steps': 111070, 'loss/train': 1.3655520677566528} 08/31/2021 09:21:53 - INFO - __main__ - Step 111072: {'lr': 8.060790416348238e-05, 'samples': 21325824, 'steps': 111071, 'loss/train': 1.0117958784103394} 08/31/2021 09:21:53 - INFO - __main__ - Step 111073: {'lr': 8.060400130462284e-05, 'samples': 21326016, 'steps': 111072, 'loss/train': 1.349853277206421} 08/31/2021 09:21:53 - INFO - __main__ - Step 111074: {'lr': 8.060009852209052e-05, 'samples': 21326208, 'steps': 111073, 'loss/train': 0.18768149614334106} 08/31/2021 09:21:55 - INFO - __main__ - Step 111075: {'lr': 8.059619581588717e-05, 'samples': 21326400, 'steps': 111074, 'loss/train': 0.5803409814834595} 08/31/2021 09:21:55 - INFO - __main__ - Step 111076: {'lr': 8.059229318601457e-05, 'samples': 21326592, 'steps': 111075, 'loss/train': 0.8486577272415161} 08/31/2021 09:21:56 - INFO - __main__ - Step 111077: {'lr': 8.058839063247447e-05, 'samples': 21326784, 'steps': 111076, 'loss/train': 1.4943664073944092} 08/31/2021 09:21:56 - INFO - __main__ - Step 111078: {'lr': 8.058448815526865e-05, 'samples': 21326976, 'steps': 111077, 'loss/train': 1.5778234004974365} 08/31/2021 09:21:56 - INFO - __main__ - Step 111079: {'lr': 8.05805857543988e-05, 'samples': 21327168, 'steps': 111078, 'loss/train': 1.0780531167984009} 08/31/2021 09:21:58 - INFO - __main__ - Step 111080: {'lr': 8.057668342986673e-05, 'samples': 21327360, 'steps': 111079, 'loss/train': 1.6700743436813354} 08/31/2021 09:21:59 - INFO - __main__ - Step 111081: {'lr': 8.057278118167421e-05, 'samples': 21327552, 'steps': 111080, 'loss/train': 0.5159095525741577} 08/31/2021 09:21:59 - INFO - __main__ - Step 111082: {'lr': 8.056887900982298e-05, 'samples': 21327744, 'steps': 111081, 'loss/train': 4.187019348144531} 08/31/2021 09:21:59 - INFO - __main__ - Step 111083: {'lr': 8.05649769143148e-05, 'samples': 21327936, 'steps': 111082, 'loss/train': 5.483604907989502} 08/31/2021 09:22:00 - INFO - __main__ - Step 111084: {'lr': 8.056107489515143e-05, 'samples': 21328128, 'steps': 111083, 'loss/train': 1.280595064163208} 08/31/2021 09:22:01 - INFO - __main__ - Step 111085: {'lr': 8.055717295233465e-05, 'samples': 21328320, 'steps': 111084, 'loss/train': 1.0365123748779297} 08/31/2021 09:22:02 - INFO - __main__ - Step 111086: {'lr': 8.055327108586621e-05, 'samples': 21328512, 'steps': 111085, 'loss/train': 1.0709718465805054} 08/31/2021 09:22:02 - INFO - __main__ - Step 111087: {'lr': 8.054936929574782e-05, 'samples': 21328704, 'steps': 111086, 'loss/train': 0.31768742203712463} 08/31/2021 09:22:02 - INFO - __main__ - Step 111088: {'lr': 8.054546758198125e-05, 'samples': 21328896, 'steps': 111087, 'loss/train': 0.7589367032051086} 08/31/2021 09:22:03 - INFO - __main__ - Step 111089: {'lr': 8.054156594456827e-05, 'samples': 21329088, 'steps': 111088, 'loss/train': 1.0500253438949585} 08/31/2021 09:22:05 - INFO - __main__ - Step 111090: {'lr': 8.053766438351068e-05, 'samples': 21329280, 'steps': 111089, 'loss/train': 1.3543168306350708} 08/31/2021 09:22:06 - INFO - __main__ - Step 111091: {'lr': 8.053376289881017e-05, 'samples': 21329472, 'steps': 111090, 'loss/train': 0.9748280644416809} 08/31/2021 09:22:06 - INFO - __main__ - Step 111092: {'lr': 8.052986149046854e-05, 'samples': 21329664, 'steps': 111091, 'loss/train': 1.4552198648452759} 08/31/2021 09:22:07 - INFO - __main__ - Step 111093: {'lr': 8.052596015848754e-05, 'samples': 21329856, 'steps': 111092, 'loss/train': 1.7747281789779663} 08/31/2021 09:22:07 - INFO - __main__ - Step 111094: {'lr': 8.052205890286892e-05, 'samples': 21330048, 'steps': 111093, 'loss/train': 1.8886867761611938} 08/31/2021 09:22:07 - INFO - __main__ - Step 111095: {'lr': 8.051815772361446e-05, 'samples': 21330240, 'steps': 111094, 'loss/train': 0.8469627499580383} 08/31/2021 09:22:08 - INFO - __main__ - Step 111096: {'lr': 8.05142566207259e-05, 'samples': 21330432, 'steps': 111095, 'loss/train': 1.6741374731063843} 08/31/2021 09:22:09 - INFO - __main__ - Step 111097: {'lr': 8.0510355594205e-05, 'samples': 21330624, 'steps': 111096, 'loss/train': 0.01969986967742443} 08/31/2021 09:22:10 - INFO - __main__ - Step 111098: {'lr': 8.050645464405352e-05, 'samples': 21330816, 'steps': 111097, 'loss/train': 1.2625995874404907} 08/31/2021 09:22:10 - INFO - __main__ - Step 111099: {'lr': 8.050255377027327e-05, 'samples': 21331008, 'steps': 111098, 'loss/train': 0.7996204495429993} 08/31/2021 09:22:10 - INFO - __main__ - Step 111100: {'lr': 8.049865297286591e-05, 'samples': 21331200, 'steps': 111099, 'loss/train': 1.571761131286621} 08/31/2021 09:22:11 - INFO - __main__ - Step 111101: {'lr': 8.049475225183323e-05, 'samples': 21331392, 'steps': 111100, 'loss/train': 1.3331103324890137} 08/31/2021 09:22:11 - INFO - __main__ - Step 111102: {'lr': 8.049085160717699e-05, 'samples': 21331584, 'steps': 111101, 'loss/train': 1.0433540344238281} 08/31/2021 09:22:13 - INFO - __main__ - Step 111103: {'lr': 8.048695103889895e-05, 'samples': 21331776, 'steps': 111102, 'loss/train': 1.631363868713379} 08/31/2021 09:22:13 - INFO - __main__ - Step 111104: {'lr': 8.048305054700089e-05, 'samples': 21331968, 'steps': 111103, 'loss/train': 0.2578056752681732} 08/31/2021 09:22:13 - INFO - __main__ - Step 111105: {'lr': 8.047915013148454e-05, 'samples': 21332160, 'steps': 111104, 'loss/train': 0.6772546768188477} 08/31/2021 09:22:14 - INFO - __main__ - Step 111106: {'lr': 8.047524979235168e-05, 'samples': 21332352, 'steps': 111105, 'loss/train': 0.1288202404975891} 08/31/2021 09:22:14 - INFO - __main__ - Step 111107: {'lr': 8.047134952960405e-05, 'samples': 21332544, 'steps': 111106, 'loss/train': 0.2059173434972763} 08/31/2021 09:22:15 - INFO - __main__ - Step 111108: {'lr': 8.046744934324343e-05, 'samples': 21332736, 'steps': 111107, 'loss/train': 1.058337926864624} 08/31/2021 09:22:16 - INFO - __main__ - Step 111109: {'lr': 8.046354923327154e-05, 'samples': 21332928, 'steps': 111108, 'loss/train': 1.5008825063705444} 08/31/2021 09:22:16 - INFO - __main__ - Step 111110: {'lr': 8.045964919969018e-05, 'samples': 21333120, 'steps': 111109, 'loss/train': 1.365249752998352} 08/31/2021 09:22:17 - INFO - __main__ - Step 111111: {'lr': 8.045574924250106e-05, 'samples': 21333312, 'steps': 111110, 'loss/train': 0.8694484829902649} 08/31/2021 09:22:17 - INFO - __main__ - Step 111112: {'lr': 8.045184936170596e-05, 'samples': 21333504, 'steps': 111111, 'loss/train': 1.268300175666809} 08/31/2021 09:22:19 - INFO - __main__ - Step 111113: {'lr': 8.044794955730675e-05, 'samples': 21333696, 'steps': 111112, 'loss/train': 1.1680511236190796} 08/31/2021 09:22:19 - INFO - __main__ - Step 111114: {'lr': 8.044404982930498e-05, 'samples': 21333888, 'steps': 111113, 'loss/train': 0.6895514726638794} 08/31/2021 09:22:20 - INFO - __main__ - Step 111115: {'lr': 8.04401501777025e-05, 'samples': 21334080, 'steps': 111114, 'loss/train': 1.1828135251998901} 08/31/2021 09:22:20 - INFO - __main__ - Step 111116: {'lr': 8.04362506025011e-05, 'samples': 21334272, 'steps': 111115, 'loss/train': 0.6143234968185425} 08/31/2021 09:22:20 - INFO - __main__ - Step 111117: {'lr': 8.043235110370247e-05, 'samples': 21334464, 'steps': 111116, 'loss/train': 1.5139456987380981} 08/31/2021 09:22:21 - INFO - __main__ - Step 111118: {'lr': 8.042845168130844e-05, 'samples': 21334656, 'steps': 111117, 'loss/train': 1.415234088897705} 08/31/2021 09:22:22 - INFO - __main__ - Step 111119: {'lr': 8.042455233532072e-05, 'samples': 21334848, 'steps': 111118, 'loss/train': 1.6941694021224976} 08/31/2021 09:22:23 - INFO - __main__ - Step 111120: {'lr': 8.042065306574106e-05, 'samples': 21335040, 'steps': 111119, 'loss/train': 0.8569186329841614} 08/31/2021 09:22:23 - INFO - __main__ - Step 111121: {'lr': 8.041675387257127e-05, 'samples': 21335232, 'steps': 111120, 'loss/train': 1.0116385221481323} 08/31/2021 09:22:24 - INFO - __main__ - Step 111122: {'lr': 8.041285475581306e-05, 'samples': 21335424, 'steps': 111121, 'loss/train': 2.0253214836120605} 08/31/2021 09:22:24 - INFO - __main__ - Step 111123: {'lr': 8.040895571546818e-05, 'samples': 21335616, 'steps': 111122, 'loss/train': 0.6533125042915344} 08/31/2021 09:22:25 - INFO - __main__ - Step 111124: {'lr': 8.040505675153845e-05, 'samples': 21335808, 'steps': 111123, 'loss/train': 1.8450565338134766} 08/31/2021 09:22:26 - INFO - __main__ - Step 111125: {'lr': 8.040115786402555e-05, 'samples': 21336000, 'steps': 111124, 'loss/train': 1.2241177558898926} 08/31/2021 09:22:26 - INFO - __main__ - Step 111126: {'lr': 8.039725905293138e-05, 'samples': 21336192, 'steps': 111125, 'loss/train': 1.108439326286316} 08/31/2021 09:22:27 - INFO - __main__ - Step 111127: {'lr': 8.039336031825748e-05, 'samples': 21336384, 'steps': 111126, 'loss/train': 1.1761435270309448} 08/31/2021 09:22:27 - INFO - __main__ - Step 111128: {'lr': 8.038946166000575e-05, 'samples': 21336576, 'steps': 111127, 'loss/train': 1.7010880708694458} 08/31/2021 09:22:28 - INFO - __main__ - Step 111129: {'lr': 8.038556307817787e-05, 'samples': 21336768, 'steps': 111128, 'loss/train': 0.9596195816993713} 08/31/2021 09:22:29 - INFO - __main__ - Step 111130: {'lr': 8.038166457277565e-05, 'samples': 21336960, 'steps': 111129, 'loss/train': 2.165421485900879} 08/31/2021 09:22:29 - INFO - __main__ - Step 111131: {'lr': 8.037776614380085e-05, 'samples': 21337152, 'steps': 111130, 'loss/train': 1.4239283800125122} 08/31/2021 09:22:30 - INFO - __main__ - Step 111132: {'lr': 8.03738677912552e-05, 'samples': 21337344, 'steps': 111131, 'loss/train': 0.028323616832494736} 08/31/2021 09:22:30 - INFO - __main__ - Step 111133: {'lr': 8.036996951514047e-05, 'samples': 21337536, 'steps': 111132, 'loss/train': 0.6442694067955017} 08/31/2021 09:22:31 - INFO - __main__ - Step 111134: {'lr': 8.036607131545839e-05, 'samples': 21337728, 'steps': 111133, 'loss/train': 0.6453770399093628} 08/31/2021 09:22:32 - INFO - __main__ - Step 111135: {'lr': 8.036217319221079e-05, 'samples': 21337920, 'steps': 111134, 'loss/train': 0.7728741765022278} 08/31/2021 09:22:32 - INFO - __main__ - Step 111136: {'lr': 8.035827514539934e-05, 'samples': 21338112, 'steps': 111135, 'loss/train': 1.032530665397644} 08/31/2021 09:22:33 - INFO - __main__ - Step 111137: {'lr': 8.035437717502583e-05, 'samples': 21338304, 'steps': 111136, 'loss/train': 1.1449859142303467} 08/31/2021 09:22:33 - INFO - __main__ - Step 111138: {'lr': 8.035047928109204e-05, 'samples': 21338496, 'steps': 111137, 'loss/train': 0.6670335531234741} 08/31/2021 09:22:35 - INFO - __main__ - Step 111139: {'lr': 8.034658146359977e-05, 'samples': 21338688, 'steps': 111138, 'loss/train': 1.1931214332580566} 08/31/2021 09:22:35 - INFO - __main__ - Step 111140: {'lr': 8.034268372255066e-05, 'samples': 21338880, 'steps': 111139, 'loss/train': 1.1568831205368042} 08/31/2021 09:22:36 - INFO - __main__ - Step 111141: {'lr': 8.03387860579465e-05, 'samples': 21339072, 'steps': 111140, 'loss/train': 0.05739060789346695} 08/31/2021 09:22:36 - INFO - __main__ - Step 111142: {'lr': 8.033488846978907e-05, 'samples': 21339264, 'steps': 111141, 'loss/train': 0.901074230670929} 08/31/2021 09:22:36 - INFO - __main__ - Step 111143: {'lr': 8.03309909580801e-05, 'samples': 21339456, 'steps': 111142, 'loss/train': 1.5279451608657837} 08/31/2021 09:22:37 - INFO - __main__ - Step 111144: {'lr': 8.032709352282138e-05, 'samples': 21339648, 'steps': 111143, 'loss/train': 1.3954254388809204} 08/31/2021 09:22:39 - INFO - __main__ - Step 111145: {'lr': 8.032319616401468e-05, 'samples': 21339840, 'steps': 111144, 'loss/train': 1.3372001647949219} 08/31/2021 09:22:39 - INFO - __main__ - Step 111146: {'lr': 8.03192988816617e-05, 'samples': 21340032, 'steps': 111145, 'loss/train': 5.711742401123047} 08/31/2021 09:22:39 - INFO - __main__ - Step 111147: {'lr': 8.031540167576423e-05, 'samples': 21340224, 'steps': 111146, 'loss/train': 1.8071017265319824} 08/31/2021 09:22:40 - INFO - __main__ - Step 111148: {'lr': 8.031150454632402e-05, 'samples': 21340416, 'steps': 111147, 'loss/train': 1.01472806930542} 08/31/2021 09:22:40 - INFO - __main__ - Step 111149: {'lr': 8.030760749334285e-05, 'samples': 21340608, 'steps': 111148, 'loss/train': 0.5522227883338928} 08/31/2021 09:22:42 - INFO - __main__ - Step 111150: {'lr': 8.030371051682241e-05, 'samples': 21340800, 'steps': 111149, 'loss/train': 1.0697758197784424} 08/31/2021 09:22:42 - INFO - __main__ - Step 111151: {'lr': 8.029981361676455e-05, 'samples': 21340992, 'steps': 111150, 'loss/train': 0.6650519371032715} 08/31/2021 09:22:43 - INFO - __main__ - Step 111152: {'lr': 8.029591679317094e-05, 'samples': 21341184, 'steps': 111151, 'loss/train': 0.3495608866214752} 08/31/2021 09:22:43 - INFO - __main__ - Step 111153: {'lr': 8.029202004604346e-05, 'samples': 21341376, 'steps': 111152, 'loss/train': 0.2677970230579376} 08/31/2021 09:22:43 - INFO - __main__ - Step 111154: {'lr': 8.028812337538371e-05, 'samples': 21341568, 'steps': 111153, 'loss/train': 0.7567387819290161} 08/31/2021 09:22:44 - INFO - __main__ - Step 111155: {'lr': 8.028422678119348e-05, 'samples': 21341760, 'steps': 111154, 'loss/train': 0.21278591454029083} 08/31/2021 09:22:45 - INFO - __main__ - Step 111156: {'lr': 8.028033026347459e-05, 'samples': 21341952, 'steps': 111155, 'loss/train': 1.01497220993042} 08/31/2021 09:22:46 - INFO - __main__ - Step 111157: {'lr': 8.027643382222877e-05, 'samples': 21342144, 'steps': 111156, 'loss/train': 0.04204053059220314} 08/31/2021 09:22:46 - INFO - __main__ - Step 111158: {'lr': 8.027253745745775e-05, 'samples': 21342336, 'steps': 111157, 'loss/train': 1.356484293937683} 08/31/2021 09:22:47 - INFO - __main__ - Step 111159: {'lr': 8.026864116916329e-05, 'samples': 21342528, 'steps': 111158, 'loss/train': 1.0656559467315674} 08/31/2021 09:22:47 - INFO - __main__ - Step 111160: {'lr': 8.02647449573472e-05, 'samples': 21342720, 'steps': 111159, 'loss/train': 0.435298353433609} 08/31/2021 09:22:48 - INFO - __main__ - Step 111161: {'lr': 8.026084882201118e-05, 'samples': 21342912, 'steps': 111160, 'loss/train': 0.84751957654953} 08/31/2021 09:22:49 - INFO - __main__ - Step 111162: {'lr': 8.025695276315701e-05, 'samples': 21343104, 'steps': 111161, 'loss/train': 1.1104929447174072} 08/31/2021 09:22:49 - INFO - __main__ - Step 111163: {'lr': 8.02530567807864e-05, 'samples': 21343296, 'steps': 111162, 'loss/train': 0.905284583568573} 08/31/2021 09:22:50 - INFO - __main__ - Step 111164: {'lr': 8.024916087490119e-05, 'samples': 21343488, 'steps': 111163, 'loss/train': 1.4234274625778198} 08/31/2021 09:22:50 - INFO - __main__ - Step 111165: {'lr': 8.024526504550306e-05, 'samples': 21343680, 'steps': 111164, 'loss/train': 1.3661670684814453} 08/31/2021 09:22:52 - INFO - __main__ - Step 111166: {'lr': 8.024136929259391e-05, 'samples': 21343872, 'steps': 111165, 'loss/train': 1.0362883806228638} 08/31/2021 09:22:52 - INFO - __main__ - Step 111167: {'lr': 8.023747361617526e-05, 'samples': 21344064, 'steps': 111166, 'loss/train': 1.1804291009902954} 08/31/2021 09:22:52 - INFO - __main__ - Step 111168: {'lr': 8.0233578016249e-05, 'samples': 21344256, 'steps': 111167, 'loss/train': 1.4401146173477173} 08/31/2021 09:22:53 - INFO - __main__ - Step 111169: {'lr': 8.022968249281687e-05, 'samples': 21344448, 'steps': 111168, 'loss/train': 0.7580738067626953} 08/31/2021 09:22:53 - INFO - __main__ - Step 111170: {'lr': 8.02257870458806e-05, 'samples': 21344640, 'steps': 111169, 'loss/train': 1.8110129833221436} 08/31/2021 09:22:55 - INFO - __main__ - Step 111171: {'lr': 8.0221891675442e-05, 'samples': 21344832, 'steps': 111170, 'loss/train': 0.7696161866188049} 08/31/2021 09:22:55 - INFO - __main__ - Step 111172: {'lr': 8.021799638150278e-05, 'samples': 21345024, 'steps': 111171, 'loss/train': 0.1485951840877533} 08/31/2021 09:22:55 - INFO - __main__ - Step 111173: {'lr': 8.021410116406474e-05, 'samples': 21345216, 'steps': 111172, 'loss/train': 1.1627262830734253} 08/31/2021 09:22:56 - INFO - __main__ - Step 111174: {'lr': 8.021020602312959e-05, 'samples': 21345408, 'steps': 111173, 'loss/train': 0.7882521748542786} 08/31/2021 09:22:56 - INFO - __main__ - Step 111175: {'lr': 8.02063109586991e-05, 'samples': 21345600, 'steps': 111174, 'loss/train': 0.8785713315010071} 08/31/2021 09:22:56 - INFO - __main__ - Step 111176: {'lr': 8.020241597077501e-05, 'samples': 21345792, 'steps': 111175, 'loss/train': 0.6429553627967834} 08/31/2021 09:22:58 - INFO - __main__ - Step 111177: {'lr': 8.019852105935912e-05, 'samples': 21345984, 'steps': 111176, 'loss/train': 1.1818679571151733} 08/31/2021 09:22:58 - INFO - __main__ - Step 111178: {'lr': 8.019462622445314e-05, 'samples': 21346176, 'steps': 111177, 'loss/train': 0.5945746898651123} 08/31/2021 09:22:59 - INFO - __main__ - Step 111179: {'lr': 8.019073146605884e-05, 'samples': 21346368, 'steps': 111178, 'loss/train': 1.1902453899383545} 08/31/2021 09:22:59 - INFO - __main__ - Step 111180: {'lr': 8.018683678417806e-05, 'samples': 21346560, 'steps': 111179, 'loss/train': 0.36795520782470703} 08/31/2021 09:22:59 - INFO - __main__ - Step 111181: {'lr': 8.018294217881238e-05, 'samples': 21346752, 'steps': 111180, 'loss/train': 1.2687678337097168} 08/31/2021 09:23:01 - INFO - __main__ - Step 111182: {'lr': 8.017904764996367e-05, 'samples': 21346944, 'steps': 111181, 'loss/train': 0.7963176965713501} 08/31/2021 09:23:02 - INFO - __main__ - Step 111183: {'lr': 8.017515319763363e-05, 'samples': 21347136, 'steps': 111182, 'loss/train': 0.921984076499939} 08/31/2021 09:23:02 - INFO - __main__ - Step 111184: {'lr': 8.017125882182408e-05, 'samples': 21347328, 'steps': 111183, 'loss/train': 0.3741298019886017} 08/31/2021 09:23:02 - INFO - __main__ - Step 111185: {'lr': 8.01673645225367e-05, 'samples': 21347520, 'steps': 111184, 'loss/train': 0.876517117023468} 08/31/2021 09:23:03 - INFO - __main__ - Step 111186: {'lr': 8.016347029977334e-05, 'samples': 21347712, 'steps': 111185, 'loss/train': 0.9362932443618774} 08/31/2021 09:23:05 - INFO - __main__ - Step 111187: {'lr': 8.015957615353564e-05, 'samples': 21347904, 'steps': 111186, 'loss/train': 0.6844561696052551} 08/31/2021 09:23:05 - INFO - __main__ - Step 111188: {'lr': 8.015568208382545e-05, 'samples': 21348096, 'steps': 111187, 'loss/train': 1.2170647382736206} 08/31/2021 09:23:06 - INFO - __main__ - Step 111189: {'lr': 8.015178809064447e-05, 'samples': 21348288, 'steps': 111188, 'loss/train': 0.7584819793701172} 08/31/2021 09:23:06 - INFO - __main__ - Step 111190: {'lr': 8.014789417399448e-05, 'samples': 21348480, 'steps': 111189, 'loss/train': 1.038210153579712} 08/31/2021 09:23:06 - INFO - __main__ - Step 111191: {'lr': 8.014400033387725e-05, 'samples': 21348672, 'steps': 111190, 'loss/train': 1.304040551185608} 08/31/2021 09:23:07 - INFO - __main__ - Step 111192: {'lr': 8.01401065702945e-05, 'samples': 21348864, 'steps': 111191, 'loss/train': 0.016405446454882622} 08/31/2021 09:23:08 - INFO - __main__ - Step 111193: {'lr': 8.013621288324805e-05, 'samples': 21349056, 'steps': 111192, 'loss/train': 1.2436531782150269} 08/31/2021 09:23:09 - INFO - __main__ - Step 111194: {'lr': 8.013231927273954e-05, 'samples': 21349248, 'steps': 111193, 'loss/train': 1.630928874015808} 08/31/2021 09:23:09 - INFO - __main__ - Step 111195: {'lr': 8.01284257387708e-05, 'samples': 21349440, 'steps': 111194, 'loss/train': 0.9121671319007874} 08/31/2021 09:23:09 - INFO - __main__ - Step 111196: {'lr': 8.012453228134356e-05, 'samples': 21349632, 'steps': 111195, 'loss/train': 1.5819926261901855} 08/31/2021 09:23:10 - INFO - __main__ - Step 111197: {'lr': 8.012063890045957e-05, 'samples': 21349824, 'steps': 111196, 'loss/train': 1.4588027000427246} 08/31/2021 09:23:11 - INFO - __main__ - Step 111198: {'lr': 8.011674559612061e-05, 'samples': 21350016, 'steps': 111197, 'loss/train': 0.9619876742362976} 08/31/2021 09:23:11 - INFO - __main__ - Step 111199: {'lr': 8.011285236832843e-05, 'samples': 21350208, 'steps': 111198, 'loss/train': 1.1604212522506714} 08/31/2021 09:23:12 - INFO - __main__ - Step 111200: {'lr': 8.010895921708478e-05, 'samples': 21350400, 'steps': 111199, 'loss/train': 1.2144402265548706} 08/31/2021 09:23:12 - INFO - __main__ - Step 111201: {'lr': 8.010506614239138e-05, 'samples': 21350592, 'steps': 111200, 'loss/train': 1.2244997024536133} 08/31/2021 09:23:13 - INFO - __main__ - Step 111202: {'lr': 8.010117314425006e-05, 'samples': 21350784, 'steps': 111201, 'loss/train': 0.11962448060512543} 08/31/2021 09:23:15 - INFO - __main__ - Step 111203: {'lr': 8.00972802226625e-05, 'samples': 21350976, 'steps': 111202, 'loss/train': 0.8177680969238281} 08/31/2021 09:23:16 - INFO - __main__ - Step 111204: {'lr': 8.009338737763047e-05, 'samples': 21351168, 'steps': 111203, 'loss/train': 0.9782246947288513} 08/31/2021 09:23:16 - INFO - __main__ - Step 111205: {'lr': 8.008949460915577e-05, 'samples': 21351360, 'steps': 111204, 'loss/train': 0.6075186133384705} 08/31/2021 09:23:16 - INFO - __main__ - Step 111206: {'lr': 8.008560191724012e-05, 'samples': 21351552, 'steps': 111205, 'loss/train': 1.2033872604370117} 08/31/2021 09:23:17 - INFO - __main__ - Step 111207: {'lr': 8.008170930188536e-05, 'samples': 21351744, 'steps': 111206, 'loss/train': 0.3798832595348358} 08/31/2021 09:23:17 - INFO - __main__ - Step 111208: {'lr': 8.007781676309306e-05, 'samples': 21351936, 'steps': 111207, 'loss/train': 0.017779603600502014} 08/31/2021 09:23:19 - INFO - __main__ - Step 111209: {'lr': 8.007392430086507e-05, 'samples': 21352128, 'steps': 111208, 'loss/train': 0.45995402336120605} 08/31/2021 09:23:19 - INFO - __main__ - Step 111210: {'lr': 8.007003191520316e-05, 'samples': 21352320, 'steps': 111209, 'loss/train': 0.9489998817443848} 08/31/2021 09:23:19 - INFO - __main__ - Step 111211: {'lr': 8.006613960610906e-05, 'samples': 21352512, 'steps': 111210, 'loss/train': 1.5800799131393433} 08/31/2021 09:23:20 - INFO - __main__ - Step 111212: {'lr': 8.006224737358455e-05, 'samples': 21352704, 'steps': 111211, 'loss/train': 1.2953367233276367} 08/31/2021 09:23:20 - INFO - __main__ - Step 111213: {'lr': 8.005835521763136e-05, 'samples': 21352896, 'steps': 111212, 'loss/train': 1.4122062921524048} 08/31/2021 09:23:21 - INFO - __main__ - Step 111214: {'lr': 8.005446313825126e-05, 'samples': 21353088, 'steps': 111213, 'loss/train': 1.6321581602096558} 08/31/2021 09:23:22 - INFO - __main__ - Step 111215: {'lr': 8.005057113544598e-05, 'samples': 21353280, 'steps': 111214, 'loss/train': 5.824114799499512} 08/31/2021 09:23:23 - INFO - __main__ - Step 111216: {'lr': 8.004667920921732e-05, 'samples': 21353472, 'steps': 111215, 'loss/train': 2.3033559322357178} 08/31/2021 09:23:23 - INFO - __main__ - Step 111217: {'lr': 8.004278735956697e-05, 'samples': 21353664, 'steps': 111216, 'loss/train': 0.6423195004463196} 08/31/2021 09:23:23 - INFO - __main__ - Step 111218: {'lr': 8.003889558649674e-05, 'samples': 21353856, 'steps': 111217, 'loss/train': 1.5546108484268188} 08/31/2021 09:23:24 - INFO - __main__ - Step 111219: {'lr': 8.003500389000837e-05, 'samples': 21354048, 'steps': 111218, 'loss/train': 0.17157208919525146} 08/31/2021 09:23:25 - INFO - __main__ - Step 111220: {'lr': 8.003111227010365e-05, 'samples': 21354240, 'steps': 111219, 'loss/train': 0.7294156551361084} 08/31/2021 09:23:25 - INFO - __main__ - Step 111221: {'lr': 8.002722072678423e-05, 'samples': 21354432, 'steps': 111220, 'loss/train': 0.7926197648048401} 08/31/2021 09:23:26 - INFO - __main__ - Step 111222: {'lr': 8.002332926005192e-05, 'samples': 21354624, 'steps': 111221, 'loss/train': 1.391038179397583} 08/31/2021 09:23:26 - INFO - __main__ - Step 111223: {'lr': 8.001943786990848e-05, 'samples': 21354816, 'steps': 111222, 'loss/train': 1.1456952095031738} 08/31/2021 09:23:27 - INFO - __main__ - Step 111224: {'lr': 8.001554655635565e-05, 'samples': 21355008, 'steps': 111223, 'loss/train': 1.0586907863616943} 08/31/2021 09:23:28 - INFO - __main__ - Step 111225: {'lr': 8.001165531939519e-05, 'samples': 21355200, 'steps': 111224, 'loss/train': 1.1714107990264893} 08/31/2021 09:23:29 - INFO - __main__ - Step 111226: {'lr': 8.000776415902886e-05, 'samples': 21355392, 'steps': 111225, 'loss/train': 1.3262028694152832} 08/31/2021 09:23:29 - INFO - __main__ - Step 111227: {'lr': 8.000387307525841e-05, 'samples': 21355584, 'steps': 111226, 'loss/train': 1.336383581161499} 08/31/2021 09:23:30 - INFO - __main__ - Step 111228: {'lr': 7.999998206808559e-05, 'samples': 21355776, 'steps': 111227, 'loss/train': 0.5469486117362976} 08/31/2021 09:23:30 - INFO - __main__ - Step 111229: {'lr': 7.999609113751217e-05, 'samples': 21355968, 'steps': 111228, 'loss/train': 0.6817238926887512} 08/31/2021 09:23:31 - INFO - __main__ - Step 111230: {'lr': 7.999220028353985e-05, 'samples': 21356160, 'steps': 111229, 'loss/train': 0.1159047856926918} 08/31/2021 09:23:32 - INFO - __main__ - Step 111231: {'lr': 7.998830950617044e-05, 'samples': 21356352, 'steps': 111230, 'loss/train': 0.26231491565704346} 08/31/2021 09:23:32 - INFO - __main__ - Step 111232: {'lr': 7.998441880540569e-05, 'samples': 21356544, 'steps': 111231, 'loss/train': 1.6221035718917847} 08/31/2021 09:23:33 - INFO - __main__ - Step 111233: {'lr': 7.99805281812474e-05, 'samples': 21356736, 'steps': 111232, 'loss/train': 1.263437032699585} 08/31/2021 09:23:33 - INFO - __main__ - Step 111234: {'lr': 7.99766376336972e-05, 'samples': 21356928, 'steps': 111233, 'loss/train': 1.0493990182876587} 08/31/2021 09:23:33 - INFO - __main__ - Step 111235: {'lr': 7.997274716275688e-05, 'samples': 21357120, 'steps': 111234, 'loss/train': 0.761111319065094} 08/31/2021 09:23:35 - INFO - __main__ - Step 111236: {'lr': 7.996885676842822e-05, 'samples': 21357312, 'steps': 111235, 'loss/train': 2.237471342086792} 08/31/2021 09:23:35 - INFO - __main__ - Step 111237: {'lr': 7.996496645071296e-05, 'samples': 21357504, 'steps': 111236, 'loss/train': 0.6858596801757812} 08/31/2021 09:23:36 - INFO - __main__ - Step 111238: {'lr': 7.996107620961291e-05, 'samples': 21357696, 'steps': 111237, 'loss/train': 1.309791088104248} 08/31/2021 09:23:36 - INFO - __main__ - Step 111239: {'lr': 7.995718604512972e-05, 'samples': 21357888, 'steps': 111238, 'loss/train': 1.035159945487976} 08/31/2021 09:23:36 - INFO - __main__ - Step 111240: {'lr': 7.995329595726522e-05, 'samples': 21358080, 'steps': 111239, 'loss/train': 1.2937805652618408} 08/31/2021 09:23:38 - INFO - __main__ - Step 111241: {'lr': 7.994940594602116e-05, 'samples': 21358272, 'steps': 111240, 'loss/train': 0.33731675148010254} 08/31/2021 09:23:39 - INFO - __main__ - Step 111242: {'lr': 7.994551601139924e-05, 'samples': 21358464, 'steps': 111241, 'loss/train': 0.9904228448867798} 08/31/2021 09:23:39 - INFO - __main__ - Step 111243: {'lr': 7.994162615340125e-05, 'samples': 21358656, 'steps': 111242, 'loss/train': 0.057626668363809586} 08/31/2021 09:23:39 - INFO - __main__ - Step 111244: {'lr': 7.993773637202903e-05, 'samples': 21358848, 'steps': 111243, 'loss/train': 0.4213913679122925} 08/31/2021 09:23:40 - INFO - __main__ - Step 111245: {'lr': 7.993384666728418e-05, 'samples': 21359040, 'steps': 111244, 'loss/train': 1.180126428604126} 08/31/2021 09:23:40 - INFO - __main__ - Step 111246: {'lr': 7.99299570391685e-05, 'samples': 21359232, 'steps': 111245, 'loss/train': 1.968616247177124} 08/31/2021 09:23:41 - INFO - __main__ - Step 111247: {'lr': 7.992606748768374e-05, 'samples': 21359424, 'steps': 111246, 'loss/train': 1.3822630643844604} 08/31/2021 09:23:42 - INFO - __main__ - Step 111248: {'lr': 7.992217801283169e-05, 'samples': 21359616, 'steps': 111247, 'loss/train': 1.2529890537261963} 08/31/2021 09:23:42 - INFO - __main__ - Step 111249: {'lr': 7.991828861461406e-05, 'samples': 21359808, 'steps': 111248, 'loss/train': 1.587802529335022} 08/31/2021 09:23:43 - INFO - __main__ - Step 111250: {'lr': 7.991439929303265e-05, 'samples': 21360000, 'steps': 111249, 'loss/train': 0.4382871985435486} 08/31/2021 09:23:43 - INFO - __main__ - Step 111251: {'lr': 7.991051004808916e-05, 'samples': 21360192, 'steps': 111250, 'loss/train': 1.626692533493042} 08/31/2021 09:23:44 - INFO - __main__ - Step 111252: {'lr': 7.99066208797854e-05, 'samples': 21360384, 'steps': 111251, 'loss/train': 0.3497227728366852} 08/31/2021 09:23:45 - INFO - __main__ - Step 111253: {'lr': 7.990273178812307e-05, 'samples': 21360576, 'steps': 111252, 'loss/train': 0.7225849628448486} 08/31/2021 09:23:45 - INFO - __main__ - Step 111254: {'lr': 7.989884277310398e-05, 'samples': 21360768, 'steps': 111253, 'loss/train': 1.3118515014648438} 08/31/2021 09:23:46 - INFO - __main__ - Step 111255: {'lr': 7.989495383472989e-05, 'samples': 21360960, 'steps': 111254, 'loss/train': 1.411311149597168} 08/31/2021 09:23:46 - INFO - __main__ - Step 111256: {'lr': 7.989106497300241e-05, 'samples': 21361152, 'steps': 111255, 'loss/train': 1.029478669166565} 08/31/2021 09:23:48 - INFO - __main__ - Step 111257: {'lr': 7.988717618792344e-05, 'samples': 21361344, 'steps': 111256, 'loss/train': 1.600579857826233} 08/31/2021 09:23:48 - INFO - __main__ - Step 111258: {'lr': 7.988328747949467e-05, 'samples': 21361536, 'steps': 111257, 'loss/train': 1.4593218564987183} 08/31/2021 09:23:48 - INFO - __main__ - Step 111259: {'lr': 7.987939884771786e-05, 'samples': 21361728, 'steps': 111258, 'loss/train': 0.03843339532613754} 08/31/2021 09:23:49 - INFO - __main__ - Step 111260: {'lr': 7.987551029259474e-05, 'samples': 21361920, 'steps': 111259, 'loss/train': 1.005145788192749} 08/31/2021 09:23:49 - INFO - __main__ - Step 111261: {'lr': 7.987162181412713e-05, 'samples': 21362112, 'steps': 111260, 'loss/train': 0.7911279797554016} 08/31/2021 09:23:52 - INFO - __main__ - Step 111262: {'lr': 7.986773341231673e-05, 'samples': 21362304, 'steps': 111261, 'loss/train': 1.394203782081604} 08/31/2021 09:23:52 - INFO - __main__ - Step 111263: {'lr': 7.986384508716529e-05, 'samples': 21362496, 'steps': 111262, 'loss/train': 0.7385446429252625} 08/31/2021 09:23:53 - INFO - __main__ - Step 111264: {'lr': 7.985995683867459e-05, 'samples': 21362688, 'steps': 111263, 'loss/train': 1.1308742761611938} 08/31/2021 09:23:53 - INFO - __main__ - Step 111265: {'lr': 7.985606866684635e-05, 'samples': 21362880, 'steps': 111264, 'loss/train': 1.1648297309875488} 08/31/2021 09:23:53 - INFO - __main__ - Step 111266: {'lr': 7.985218057168245e-05, 'samples': 21363072, 'steps': 111265, 'loss/train': 0.34306836128234863} 08/31/2021 09:23:55 - INFO - __main__ - Step 111267: {'lr': 7.984829255318444e-05, 'samples': 21363264, 'steps': 111266, 'loss/train': 0.42932555079460144} 08/31/2021 09:23:55 - INFO - __main__ - Step 111268: {'lr': 7.984440461135418e-05, 'samples': 21363456, 'steps': 111267, 'loss/train': 0.7643634080886841} 08/31/2021 09:23:56 - INFO - __main__ - Step 111269: {'lr': 7.984051674619338e-05, 'samples': 21363648, 'steps': 111268, 'loss/train': 1.135361671447754} 08/31/2021 09:23:56 - INFO - __main__ - Step 111270: {'lr': 7.983662895770383e-05, 'samples': 21363840, 'steps': 111269, 'loss/train': 0.9674493670463562} 08/31/2021 09:23:56 - INFO - __main__ - Step 111271: {'lr': 7.983274124588724e-05, 'samples': 21364032, 'steps': 111270, 'loss/train': 0.7499700784683228} 08/31/2021 09:23:58 - INFO - __main__ - Step 111272: {'lr': 7.982885361074544e-05, 'samples': 21364224, 'steps': 111271, 'loss/train': 0.6808158159255981} 08/31/2021 09:23:58 - INFO - __main__ - Step 111273: {'lr': 7.98249660522801e-05, 'samples': 21364416, 'steps': 111272, 'loss/train': 0.6674676537513733} 08/31/2021 09:23:59 - INFO - __main__ - Step 111274: {'lr': 7.9821078570493e-05, 'samples': 21364608, 'steps': 111273, 'loss/train': 1.016983985900879} 08/31/2021 09:23:59 - INFO - __main__ - Step 111275: {'lr': 7.981719116538591e-05, 'samples': 21364800, 'steps': 111274, 'loss/train': 1.254357933998108} 08/31/2021 09:23:59 - INFO - __main__ - Step 111276: {'lr': 7.981330383696064e-05, 'samples': 21364992, 'steps': 111275, 'loss/train': 0.9848188757896423} 08/31/2021 09:24:01 - INFO - __main__ - Step 111277: {'lr': 7.980941658521882e-05, 'samples': 21365184, 'steps': 111276, 'loss/train': 1.3651740550994873} 08/31/2021 09:24:01 - INFO - __main__ - Step 111278: {'lr': 7.980552941016219e-05, 'samples': 21365376, 'steps': 111277, 'loss/train': 0.9798837304115295} 08/31/2021 09:24:02 - INFO - __main__ - Step 111279: {'lr': 7.980164231179262e-05, 'samples': 21365568, 'steps': 111278, 'loss/train': 0.9636138081550598} 08/31/2021 09:24:02 - INFO - __main__ - Step 111280: {'lr': 7.979775529011177e-05, 'samples': 21365760, 'steps': 111279, 'loss/train': 1.5453835725784302} 08/31/2021 09:24:02 - INFO - __main__ - Step 111281: {'lr': 7.979386834512145e-05, 'samples': 21365952, 'steps': 111280, 'loss/train': 1.377747893333435} 08/31/2021 09:24:03 - INFO - __main__ - Step 111282: {'lr': 7.978998147682338e-05, 'samples': 21366144, 'steps': 111281, 'loss/train': 1.3313547372817993} 08/31/2021 09:24:04 - INFO - __main__ - Step 111283: {'lr': 7.97860946852193e-05, 'samples': 21366336, 'steps': 111282, 'loss/train': 0.254878968000412} 08/31/2021 09:24:05 - INFO - __main__ - Step 111284: {'lr': 7.978220797031099e-05, 'samples': 21366528, 'steps': 111283, 'loss/train': 0.790661096572876} 08/31/2021 09:24:05 - INFO - __main__ - Step 111285: {'lr': 7.977832133210019e-05, 'samples': 21366720, 'steps': 111284, 'loss/train': 0.840516209602356} 08/31/2021 09:24:05 - INFO - __main__ - Step 111286: {'lr': 7.977443477058866e-05, 'samples': 21366912, 'steps': 111285, 'loss/train': 1.2590913772583008} 08/31/2021 09:24:06 - INFO - __main__ - Step 111287: {'lr': 7.97705482857782e-05, 'samples': 21367104, 'steps': 111286, 'loss/train': 1.4868535995483398} 08/31/2021 09:24:07 - INFO - __main__ - Step 111288: {'lr': 7.976666187767042e-05, 'samples': 21367296, 'steps': 111287, 'loss/train': 1.1780927181243896} 08/31/2021 09:24:08 - INFO - __main__ - Step 111289: {'lr': 7.976277554626718e-05, 'samples': 21367488, 'steps': 111288, 'loss/train': 0.5843177437782288} 08/31/2021 09:24:08 - INFO - __main__ - Step 111290: {'lr': 7.975888929157021e-05, 'samples': 21367680, 'steps': 111289, 'loss/train': 0.9674926996231079} 08/31/2021 09:24:08 - INFO - __main__ - Step 111291: {'lr': 7.975500311358125e-05, 'samples': 21367872, 'steps': 111290, 'loss/train': 1.4226194620132446} 08/31/2021 09:24:09 - INFO - __main__ - Step 111292: {'lr': 7.975111701230206e-05, 'samples': 21368064, 'steps': 111291, 'loss/train': 0.31744372844696045} 08/31/2021 09:24:10 - INFO - __main__ - Step 111293: {'lr': 7.974723098773437e-05, 'samples': 21368256, 'steps': 111292, 'loss/train': 1.1886799335479736} 08/31/2021 09:24:11 - INFO - __main__ - Step 111294: {'lr': 7.974334503987998e-05, 'samples': 21368448, 'steps': 111293, 'loss/train': 0.46069857478141785} 08/31/2021 09:24:11 - INFO - __main__ - Step 111295: {'lr': 7.973945916874059e-05, 'samples': 21368640, 'steps': 111294, 'loss/train': 1.3591245412826538} 08/31/2021 09:24:11 - INFO - __main__ - Step 111296: {'lr': 7.9735573374318e-05, 'samples': 21368832, 'steps': 111295, 'loss/train': 0.5077080726623535} 08/31/2021 09:24:12 - INFO - __main__ - Step 111297: {'lr': 7.97316876566139e-05, 'samples': 21369024, 'steps': 111296, 'loss/train': 0.11234230548143387} 08/31/2021 09:24:13 - INFO - __main__ - Step 111298: {'lr': 7.97278020156301e-05, 'samples': 21369216, 'steps': 111297, 'loss/train': 1.9304906129837036} 08/31/2021 09:24:14 - INFO - __main__ - Step 111299: {'lr': 7.972391645136831e-05, 'samples': 21369408, 'steps': 111298, 'loss/train': 1.1773195266723633} 08/31/2021 09:24:14 - INFO - __main__ - Step 111300: {'lr': 7.97200309638303e-05, 'samples': 21369600, 'steps': 111299, 'loss/train': 2.125713586807251} 08/31/2021 09:24:14 - INFO - __main__ - Step 111301: {'lr': 7.97161455530179e-05, 'samples': 21369792, 'steps': 111300, 'loss/train': 0.9531420469284058} 08/31/2021 09:24:15 - INFO - __main__ - Step 111302: {'lr': 7.971226021893269e-05, 'samples': 21369984, 'steps': 111301, 'loss/train': 1.3932840824127197} 08/31/2021 09:24:16 - INFO - __main__ - Step 111303: {'lr': 7.970837496157651e-05, 'samples': 21370176, 'steps': 111302, 'loss/train': 0.5484715700149536} 08/31/2021 09:24:17 - INFO - __main__ - Step 111304: {'lr': 7.97044897809511e-05, 'samples': 21370368, 'steps': 111303, 'loss/train': 1.4243346452713013} 08/31/2021 09:24:17 - INFO - __main__ - Step 111305: {'lr': 7.970060467705822e-05, 'samples': 21370560, 'steps': 111304, 'loss/train': 1.0184305906295776} 08/31/2021 09:24:17 - INFO - __main__ - Step 111306: {'lr': 7.969671964989964e-05, 'samples': 21370752, 'steps': 111305, 'loss/train': 1.0693838596343994} 08/31/2021 09:24:18 - INFO - __main__ - Step 111307: {'lr': 7.969283469947708e-05, 'samples': 21370944, 'steps': 111306, 'loss/train': 1.0871121883392334} 08/31/2021 09:24:20 - INFO - __main__ - Step 111308: {'lr': 7.968894982579228e-05, 'samples': 21371136, 'steps': 111307, 'loss/train': 0.7217313051223755} 08/31/2021 09:24:20 - INFO - __main__ - Step 111309: {'lr': 7.968506502884703e-05, 'samples': 21371328, 'steps': 111308, 'loss/train': 1.6858248710632324} 08/31/2021 09:24:21 - INFO - __main__ - Step 111310: {'lr': 7.968118030864307e-05, 'samples': 21371520, 'steps': 111309, 'loss/train': 1.8144539594650269} 08/31/2021 09:24:21 - INFO - __main__ - Step 111311: {'lr': 7.967729566518215e-05, 'samples': 21371712, 'steps': 111310, 'loss/train': 0.9235235452651978} 08/31/2021 09:24:21 - INFO - __main__ - Step 111312: {'lr': 7.967341109846599e-05, 'samples': 21371904, 'steps': 111311, 'loss/train': 0.763473629951477} 08/31/2021 09:24:23 - INFO - __main__ - Step 111313: {'lr': 7.966952660849635e-05, 'samples': 21372096, 'steps': 111312, 'loss/train': 1.1565358638763428} 08/31/2021 09:24:23 - INFO - __main__ - Step 111314: {'lr': 7.966564219527511e-05, 'samples': 21372288, 'steps': 111313, 'loss/train': 1.140279769897461} 08/31/2021 09:24:24 - INFO - __main__ - Step 111315: {'lr': 7.966175785880378e-05, 'samples': 21372480, 'steps': 111314, 'loss/train': 1.2902686595916748} 08/31/2021 09:24:24 - INFO - __main__ - Step 111316: {'lr': 7.965787359908428e-05, 'samples': 21372672, 'steps': 111315, 'loss/train': 1.6621427536010742} 08/31/2021 09:24:24 - INFO - __main__ - Step 111317: {'lr': 7.96539894161183e-05, 'samples': 21372864, 'steps': 111316, 'loss/train': 2.0788557529449463} 08/31/2021 09:24:26 - INFO - __main__ - Step 111318: {'lr': 7.965010530990758e-05, 'samples': 21373056, 'steps': 111317, 'loss/train': 0.8316193222999573} 08/31/2021 09:24:27 - INFO - __main__ - Step 111319: {'lr': 7.96462212804539e-05, 'samples': 21373248, 'steps': 111318, 'loss/train': 1.5226866006851196} 08/31/2021 09:24:27 - INFO - __main__ - Step 111320: {'lr': 7.964233732775902e-05, 'samples': 21373440, 'steps': 111319, 'loss/train': 1.004024624824524} 08/31/2021 09:24:27 - INFO - __main__ - Step 111321: {'lr': 7.963845345182466e-05, 'samples': 21373632, 'steps': 111320, 'loss/train': 1.6872022151947021} 08/31/2021 09:24:28 - INFO - __main__ - Step 111322: {'lr': 7.96345696526526e-05, 'samples': 21373824, 'steps': 111321, 'loss/train': 0.626066267490387} 08/31/2021 09:24:28 - INFO - __main__ - Step 111323: {'lr': 7.963068593024455e-05, 'samples': 21374016, 'steps': 111322, 'loss/train': 0.7332669496536255} 08/31/2021 09:24:30 - INFO - __main__ - Step 111324: {'lr': 7.962680228460232e-05, 'samples': 21374208, 'steps': 111323, 'loss/train': 0.31049075722694397} 08/31/2021 09:24:30 - INFO - __main__ - Step 111325: {'lr': 7.96229187157276e-05, 'samples': 21374400, 'steps': 111324, 'loss/train': 1.1177691221237183} 08/31/2021 09:24:30 - INFO - __main__ - Step 111326: {'lr': 7.961903522362215e-05, 'samples': 21374592, 'steps': 111325, 'loss/train': 0.028391430154442787} 08/31/2021 09:24:31 - INFO - __main__ - Step 111327: {'lr': 7.961515180828777e-05, 'samples': 21374784, 'steps': 111326, 'loss/train': 0.6570029854774475} 08/31/2021 09:24:31 - INFO - __main__ - Step 111328: {'lr': 7.961126846972622e-05, 'samples': 21374976, 'steps': 111327, 'loss/train': 1.1446243524551392} 08/31/2021 09:24:33 - INFO - __main__ - Step 111329: {'lr': 7.960738520793914e-05, 'samples': 21375168, 'steps': 111328, 'loss/train': 1.326904058456421} 08/31/2021 09:24:34 - INFO - __main__ - Step 111330: {'lr': 7.960350202292834e-05, 'samples': 21375360, 'steps': 111329, 'loss/train': 1.0907630920410156} 08/31/2021 09:24:34 - INFO - __main__ - Step 111331: {'lr': 7.959961891469558e-05, 'samples': 21375552, 'steps': 111330, 'loss/train': 0.9845508933067322} 08/31/2021 09:24:34 - INFO - __main__ - Step 111332: {'lr': 7.959573588324259e-05, 'samples': 21375744, 'steps': 111331, 'loss/train': 0.8723948001861572} 08/31/2021 09:24:35 - INFO - __main__ - Step 111333: {'lr': 7.959185292857113e-05, 'samples': 21375936, 'steps': 111332, 'loss/train': 1.0355350971221924} 08/31/2021 09:24:36 - INFO - __main__ - Step 111334: {'lr': 7.958797005068296e-05, 'samples': 21376128, 'steps': 111333, 'loss/train': 0.943393886089325} 08/31/2021 09:24:37 - INFO - __main__ - Step 111335: {'lr': 7.958408724957982e-05, 'samples': 21376320, 'steps': 111334, 'loss/train': 1.109763503074646} 08/31/2021 09:24:37 - INFO - __main__ - Step 111336: {'lr': 7.958020452526346e-05, 'samples': 21376512, 'steps': 111335, 'loss/train': 0.5734465718269348} 08/31/2021 09:24:37 - INFO - __main__ - Step 111337: {'lr': 7.957632187773565e-05, 'samples': 21376704, 'steps': 111336, 'loss/train': 1.7794301509857178} 08/31/2021 09:24:38 - INFO - __main__ - Step 111338: {'lr': 7.957243930699809e-05, 'samples': 21376896, 'steps': 111337, 'loss/train': 1.6058663129806519} 08/31/2021 09:24:39 - INFO - __main__ - Step 111339: {'lr': 7.956855681305256e-05, 'samples': 21377088, 'steps': 111338, 'loss/train': 1.378351092338562} 08/31/2021 09:24:40 - INFO - __main__ - Step 111340: {'lr': 7.956467439590082e-05, 'samples': 21377280, 'steps': 111339, 'loss/train': 0.9906830191612244} 08/31/2021 09:24:40 - INFO - __main__ - Step 111341: {'lr': 7.956079205554468e-05, 'samples': 21377472, 'steps': 111340, 'loss/train': 1.0403684377670288} 08/31/2021 09:24:40 - INFO - __main__ - Step 111342: {'lr': 7.955690979198573e-05, 'samples': 21377664, 'steps': 111341, 'loss/train': 1.2813313007354736} 08/31/2021 09:24:41 - INFO - __main__ - Step 111343: {'lr': 7.955302760522582e-05, 'samples': 21377856, 'steps': 111342, 'loss/train': 0.49877819418907166} 08/31/2021 09:24:42 - INFO - __main__ - Step 111344: {'lr': 7.954914549526668e-05, 'samples': 21378048, 'steps': 111343, 'loss/train': 0.9297385811805725} 08/31/2021 09:24:43 - INFO - __main__ - Step 111345: {'lr': 7.954526346211008e-05, 'samples': 21378240, 'steps': 111344, 'loss/train': 0.7365437150001526} 08/31/2021 09:24:43 - INFO - __main__ - Step 111346: {'lr': 7.954138150575773e-05, 'samples': 21378432, 'steps': 111345, 'loss/train': 1.567782998085022} 08/31/2021 09:24:44 - INFO - __main__ - Step 111347: {'lr': 7.953749962621142e-05, 'samples': 21378624, 'steps': 111346, 'loss/train': 0.047536373138427734} 08/31/2021 09:24:44 - INFO - __main__ - Step 111348: {'lr': 7.953361782347288e-05, 'samples': 21378816, 'steps': 111347, 'loss/train': 1.2640535831451416} 08/31/2021 09:24:44 - INFO - __main__ - Step 111349: {'lr': 7.952973609754386e-05, 'samples': 21379008, 'steps': 111348, 'loss/train': 0.8420405387878418} 08/31/2021 09:24:46 - INFO - __main__ - Step 111350: {'lr': 7.952585444842611e-05, 'samples': 21379200, 'steps': 111349, 'loss/train': 5.798818588256836} 08/31/2021 09:24:46 - INFO - __main__ - Step 111351: {'lr': 7.952197287612137e-05, 'samples': 21379392, 'steps': 111350, 'loss/train': 0.7108203172683716} 08/31/2021 09:24:47 - INFO - __main__ - Step 111352: {'lr': 7.951809138063141e-05, 'samples': 21379584, 'steps': 111351, 'loss/train': 0.881432294845581} 08/31/2021 09:24:47 - INFO - __main__ - Step 111353: {'lr': 7.951420996195796e-05, 'samples': 21379776, 'steps': 111352, 'loss/train': 1.0344467163085938} 08/31/2021 09:24:47 - INFO - __main__ - Step 111354: {'lr': 7.95103286201028e-05, 'samples': 21379968, 'steps': 111353, 'loss/train': 1.2973380088806152} 08/31/2021 09:24:49 - INFO - __main__ - Step 111355: {'lr': 7.950644735506771e-05, 'samples': 21380160, 'steps': 111354, 'loss/train': 1.2440627813339233} 08/31/2021 09:24:50 - INFO - __main__ - Step 111356: {'lr': 7.950256616685431e-05, 'samples': 21380352, 'steps': 111355, 'loss/train': 1.1245918273925781} 08/31/2021 09:24:50 - INFO - __main__ - Step 111357: {'lr': 7.949868505546443e-05, 'samples': 21380544, 'steps': 111356, 'loss/train': 0.31069377064704895} 08/31/2021 09:24:50 - INFO - __main__ - Step 111358: {'lr': 7.949480402089978e-05, 'samples': 21380736, 'steps': 111357, 'loss/train': 0.10416290909051895} 08/31/2021 09:24:51 - INFO - __main__ - Step 111359: {'lr': 7.949092306316219e-05, 'samples': 21380928, 'steps': 111358, 'loss/train': 1.217612862586975} 08/31/2021 09:24:52 - INFO - __main__ - Step 111360: {'lr': 7.948704218225333e-05, 'samples': 21381120, 'steps': 111359, 'loss/train': 1.2106741666793823} 08/31/2021 09:24:53 - INFO - __main__ - Step 111361: {'lr': 7.948316137817497e-05, 'samples': 21381312, 'steps': 111360, 'loss/train': 0.1967613399028778} 08/31/2021 09:24:53 - INFO - __main__ - Step 111362: {'lr': 7.947928065092888e-05, 'samples': 21381504, 'steps': 111361, 'loss/train': 0.9066089391708374} 08/31/2021 09:24:53 - INFO - __main__ - Step 111363: {'lr': 7.947540000051678e-05, 'samples': 21381696, 'steps': 111362, 'loss/train': 1.2716306447982788} 08/31/2021 09:24:54 - INFO - __main__ - Step 111364: {'lr': 7.947151942694045e-05, 'samples': 21381888, 'steps': 111363, 'loss/train': 1.1635169982910156} 08/31/2021 09:24:56 - INFO - __main__ - Step 111365: {'lr': 7.946763893020162e-05, 'samples': 21382080, 'steps': 111364, 'loss/train': 0.9394720792770386} 08/31/2021 09:24:56 - INFO - __main__ - Step 111366: {'lr': 7.946375851030205e-05, 'samples': 21382272, 'steps': 111365, 'loss/train': 0.7094048857688904} 08/31/2021 09:24:57 - INFO - __main__ - Step 111367: {'lr': 7.945987816724346e-05, 'samples': 21382464, 'steps': 111366, 'loss/train': 0.5331061482429504} 08/31/2021 09:24:57 - INFO - __main__ - Step 111368: {'lr': 7.94559979010277e-05, 'samples': 21382656, 'steps': 111367, 'loss/train': 1.0832401514053345} 08/31/2021 09:24:57 - INFO - __main__ - Step 111369: {'lr': 7.945211771165636e-05, 'samples': 21382848, 'steps': 111368, 'loss/train': 0.8790853023529053} 08/31/2021 09:24:59 - INFO - __main__ - Step 111370: {'lr': 7.944823759913128e-05, 'samples': 21383040, 'steps': 111369, 'loss/train': 1.1623724699020386} 08/31/2021 09:25:00 - INFO - __main__ - Step 111371: {'lr': 7.944435756345417e-05, 'samples': 21383232, 'steps': 111370, 'loss/train': 1.4566538333892822} 08/31/2021 09:25:00 - INFO - __main__ - Step 111372: {'lr': 7.94404776046268e-05, 'samples': 21383424, 'steps': 111371, 'loss/train': 1.2683106660842896} 08/31/2021 09:25:00 - INFO - __main__ - Step 111373: {'lr': 7.94365977226509e-05, 'samples': 21383616, 'steps': 111372, 'loss/train': 0.9793773293495178} 08/31/2021 09:25:01 - INFO - __main__ - Step 111374: {'lr': 7.943271791752829e-05, 'samples': 21383808, 'steps': 111373, 'loss/train': 1.4428139925003052} 08/31/2021 09:25:01 - INFO - __main__ - Step 111375: {'lr': 7.942883818926063e-05, 'samples': 21384000, 'steps': 111374, 'loss/train': 1.0374011993408203} 08/31/2021 09:25:03 - INFO - __main__ - Step 111376: {'lr': 7.942495853784972e-05, 'samples': 21384192, 'steps': 111375, 'loss/train': 1.7574344873428345} 08/31/2021 09:25:03 - INFO - __main__ - Step 111377: {'lr': 7.942107896329728e-05, 'samples': 21384384, 'steps': 111376, 'loss/train': 0.9045616388320923} 08/31/2021 09:25:03 - INFO - __main__ - Step 111378: {'lr': 7.941719946560507e-05, 'samples': 21384576, 'steps': 111377, 'loss/train': 1.2862284183502197} 08/31/2021 09:25:04 - INFO - __main__ - Step 111379: {'lr': 7.941332004477483e-05, 'samples': 21384768, 'steps': 111378, 'loss/train': 0.5611590147018433} 08/31/2021 09:25:04 - INFO - __main__ - Step 111380: {'lr': 7.940944070080832e-05, 'samples': 21384960, 'steps': 111379, 'loss/train': 1.7125459909439087} 08/31/2021 09:25:06 - INFO - __main__ - Step 111381: {'lr': 7.940556143370739e-05, 'samples': 21385152, 'steps': 111380, 'loss/train': 0.9822956919670105} 08/31/2021 09:25:06 - INFO - __main__ - Step 111382: {'lr': 7.940168224347358e-05, 'samples': 21385344, 'steps': 111381, 'loss/train': 0.9493621587753296} 08/31/2021 09:25:06 - INFO - __main__ - Step 111383: {'lr': 7.939780313010875e-05, 'samples': 21385536, 'steps': 111382, 'loss/train': 0.8684512972831726} 08/31/2021 09:25:07 - INFO - __main__ - Step 111384: {'lr': 7.939392409361462e-05, 'samples': 21385728, 'steps': 111383, 'loss/train': 1.400619387626648} 08/31/2021 09:25:07 - INFO - __main__ - Step 111385: {'lr': 7.939004513399295e-05, 'samples': 21385920, 'steps': 111384, 'loss/train': 1.1333740949630737} 08/31/2021 09:25:09 - INFO - __main__ - Step 111386: {'lr': 7.93861662512455e-05, 'samples': 21386112, 'steps': 111385, 'loss/train': 0.2774602174758911} 08/31/2021 09:25:09 - INFO - __main__ - Step 111387: {'lr': 7.938228744537404e-05, 'samples': 21386304, 'steps': 111386, 'loss/train': 0.9400092363357544} 08/31/2021 09:25:10 - INFO - __main__ - Step 111388: {'lr': 7.937840871638025e-05, 'samples': 21386496, 'steps': 111387, 'loss/train': 1.4492743015289307} 08/31/2021 09:25:10 - INFO - __main__ - Step 111389: {'lr': 7.937453006426592e-05, 'samples': 21386688, 'steps': 111388, 'loss/train': 1.0881727933883667} 08/31/2021 09:25:10 - INFO - __main__ - Step 111390: {'lr': 7.937065148903283e-05, 'samples': 21386880, 'steps': 111389, 'loss/train': 0.11893543601036072} 08/31/2021 09:25:11 - INFO - __main__ - Step 111391: {'lr': 7.936677299068265e-05, 'samples': 21387072, 'steps': 111390, 'loss/train': 0.9768748879432678} 08/31/2021 09:25:12 - INFO - __main__ - Step 111392: {'lr': 7.93628945692172e-05, 'samples': 21387264, 'steps': 111391, 'loss/train': 1.2065359354019165} 08/31/2021 09:25:13 - INFO - __main__ - Step 111393: {'lr': 7.935901622463818e-05, 'samples': 21387456, 'steps': 111392, 'loss/train': 0.624961793422699} 08/31/2021 09:25:13 - INFO - __main__ - Step 111394: {'lr': 7.935513795694735e-05, 'samples': 21387648, 'steps': 111393, 'loss/train': 0.6983986496925354} 08/31/2021 09:25:13 - INFO - __main__ - Step 111395: {'lr': 7.935125976614655e-05, 'samples': 21387840, 'steps': 111394, 'loss/train': 1.1069555282592773} 08/31/2021 09:25:14 - INFO - __main__ - Step 111396: {'lr': 7.934738165223737e-05, 'samples': 21388032, 'steps': 111395, 'loss/train': 1.363553762435913} 08/31/2021 09:25:15 - INFO - __main__ - Step 111397: {'lr': 7.93435036152216e-05, 'samples': 21388224, 'steps': 111396, 'loss/train': 1.3578155040740967} 08/31/2021 09:25:16 - INFO - __main__ - Step 111398: {'lr': 7.933962565510103e-05, 'samples': 21388416, 'steps': 111397, 'loss/train': 0.9204790592193604} 08/31/2021 09:25:16 - INFO - __main__ - Step 111399: {'lr': 7.933574777187738e-05, 'samples': 21388608, 'steps': 111398, 'loss/train': 1.115458607673645} 08/31/2021 09:25:16 - INFO - __main__ - Step 111400: {'lr': 7.933186996555244e-05, 'samples': 21388800, 'steps': 111399, 'loss/train': 0.9785454273223877} 08/31/2021 09:25:17 - INFO - __main__ - Step 111401: {'lr': 7.932799223612788e-05, 'samples': 21388992, 'steps': 111400, 'loss/train': 1.191503882408142} 08/31/2021 09:25:18 - INFO - __main__ - Step 111402: {'lr': 7.932411458360553e-05, 'samples': 21389184, 'steps': 111401, 'loss/train': 1.4153722524642944} 08/31/2021 09:25:19 - INFO - __main__ - Step 111403: {'lr': 7.93202370079871e-05, 'samples': 21389376, 'steps': 111402, 'loss/train': 1.2706525325775146} 08/31/2021 09:25:19 - INFO - __main__ - Step 111404: {'lr': 7.931635950927432e-05, 'samples': 21389568, 'steps': 111403, 'loss/train': 1.7381099462509155} 08/31/2021 09:25:20 - INFO - __main__ - Step 111405: {'lr': 7.931248208746895e-05, 'samples': 21389760, 'steps': 111404, 'loss/train': 1.196878433227539} 08/31/2021 09:25:20 - INFO - __main__ - Step 111406: {'lr': 7.930860474257276e-05, 'samples': 21389952, 'steps': 111405, 'loss/train': 1.2634204626083374} 08/31/2021 09:25:22 - INFO - __main__ - Step 111407: {'lr': 7.930472747458747e-05, 'samples': 21390144, 'steps': 111406, 'loss/train': 1.401625394821167} 08/31/2021 09:25:22 - INFO - __main__ - Step 111408: {'lr': 7.930085028351492e-05, 'samples': 21390336, 'steps': 111407, 'loss/train': 0.09437138587236404} 08/31/2021 09:25:23 - INFO - __main__ - Step 111409: {'lr': 7.929697316935666e-05, 'samples': 21390528, 'steps': 111408, 'loss/train': 0.5790159106254578} 08/31/2021 09:25:23 - INFO - __main__ - Step 111410: {'lr': 7.929309613211457e-05, 'samples': 21390720, 'steps': 111409, 'loss/train': 0.9769155979156494} 08/31/2021 09:25:23 - INFO - __main__ - Step 111411: {'lr': 7.928921917179041e-05, 'samples': 21390912, 'steps': 111410, 'loss/train': 0.9056009650230408} 08/31/2021 09:25:25 - INFO - __main__ - Step 111412: {'lr': 7.928534228838585e-05, 'samples': 21391104, 'steps': 111411, 'loss/train': 0.9033112525939941} 08/31/2021 09:25:25 - INFO - __main__ - Step 111413: {'lr': 7.928146548190271e-05, 'samples': 21391296, 'steps': 111412, 'loss/train': 0.7690219879150391} 08/31/2021 09:25:25 - INFO - __main__ - Step 111414: {'lr': 7.92775887523427e-05, 'samples': 21391488, 'steps': 111413, 'loss/train': 0.9217957854270935} 08/31/2021 09:25:26 - INFO - __main__ - Step 111415: {'lr': 7.927371209970757e-05, 'samples': 21391680, 'steps': 111414, 'loss/train': 1.1875931024551392} 08/31/2021 09:25:26 - INFO - __main__ - Step 111416: {'lr': 7.926983552399908e-05, 'samples': 21391872, 'steps': 111415, 'loss/train': 0.6640985608100891} 08/31/2021 09:25:28 - INFO - __main__ - Step 111417: {'lr': 7.926595902521893e-05, 'samples': 21392064, 'steps': 111416, 'loss/train': 0.4734569191932678} 08/31/2021 09:25:29 - INFO - __main__ - Step 111418: {'lr': 7.926208260336896e-05, 'samples': 21392256, 'steps': 111417, 'loss/train': 0.6020036935806274} 08/31/2021 09:25:29 - INFO - __main__ - Step 111419: {'lr': 7.925820625845082e-05, 'samples': 21392448, 'steps': 111418, 'loss/train': 1.322996735572815} 08/31/2021 09:25:29 - INFO - __main__ - Step 111420: {'lr': 7.92543299904663e-05, 'samples': 21392640, 'steps': 111419, 'loss/train': 0.8957099318504333} 08/31/2021 09:25:30 - INFO - __main__ - Step 111421: {'lr': 7.925045379941717e-05, 'samples': 21392832, 'steps': 111420, 'loss/train': 0.5610120892524719} 08/31/2021 09:25:31 - INFO - __main__ - Step 111422: {'lr': 7.924657768530521e-05, 'samples': 21393024, 'steps': 111421, 'loss/train': 0.41458526253700256} 08/31/2021 09:25:32 - INFO - __main__ - Step 111423: {'lr': 7.924270164813205e-05, 'samples': 21393216, 'steps': 111422, 'loss/train': 1.4459962844848633} 08/31/2021 09:25:32 - INFO - __main__ - Step 111424: {'lr': 7.923882568789947e-05, 'samples': 21393408, 'steps': 111423, 'loss/train': 0.5583876371383667} 08/31/2021 09:25:32 - INFO - __main__ - Step 111425: {'lr': 7.923494980460924e-05, 'samples': 21393600, 'steps': 111424, 'loss/train': 0.6966102123260498} 08/31/2021 09:25:33 - INFO - __main__ - Step 111426: {'lr': 7.923107399826313e-05, 'samples': 21393792, 'steps': 111425, 'loss/train': 1.0179065465927124} 08/31/2021 09:25:34 - INFO - __main__ - Step 111427: {'lr': 7.922719826886283e-05, 'samples': 21393984, 'steps': 111426, 'loss/train': 1.32450270652771} 08/31/2021 09:25:35 - INFO - __main__ - Step 111428: {'lr': 7.922332261641013e-05, 'samples': 21394176, 'steps': 111427, 'loss/train': 0.8149099946022034} 08/31/2021 09:25:35 - INFO - __main__ - Step 111429: {'lr': 7.921944704090678e-05, 'samples': 21394368, 'steps': 111428, 'loss/train': 0.8920220732688904} 08/31/2021 09:25:35 - INFO - __main__ - Step 111430: {'lr': 7.92155715423545e-05, 'samples': 21394560, 'steps': 111429, 'loss/train': 0.1255991905927658} 08/31/2021 09:25:36 - INFO - __main__ - Step 111431: {'lr': 7.921169612075504e-05, 'samples': 21394752, 'steps': 111430, 'loss/train': 0.9167799353599548} 08/31/2021 09:25:38 - INFO - __main__ - Step 111432: {'lr': 7.920782077611019e-05, 'samples': 21394944, 'steps': 111431, 'loss/train': 1.3442271947860718} 08/31/2021 09:25:38 - INFO - __main__ - Step 111433: {'lr': 7.920394550842163e-05, 'samples': 21395136, 'steps': 111432, 'loss/train': 0.11045234650373459} 08/31/2021 09:25:38 - INFO - __main__ - Step 111434: {'lr': 7.920007031769114e-05, 'samples': 21395328, 'steps': 111433, 'loss/train': 0.016438765451312065} 08/31/2021 09:25:39 - INFO - __main__ - Step 111435: {'lr': 7.919619520392055e-05, 'samples': 21395520, 'steps': 111434, 'loss/train': 0.8179168105125427} 08/31/2021 09:25:39 - INFO - __main__ - Step 111436: {'lr': 7.919232016711142e-05, 'samples': 21395712, 'steps': 111435, 'loss/train': 1.832993984222412} 08/31/2021 09:25:39 - INFO - __main__ - Step 111437: {'lr': 7.918844520726561e-05, 'samples': 21395904, 'steps': 111436, 'loss/train': 1.0354533195495605} 08/31/2021 09:25:41 - INFO - __main__ - Step 111438: {'lr': 7.918457032438487e-05, 'samples': 21396096, 'steps': 111437, 'loss/train': 1.3127999305725098} 08/31/2021 09:25:41 - INFO - __main__ - Step 111439: {'lr': 7.91806955184709e-05, 'samples': 21396288, 'steps': 111438, 'loss/train': 0.7965413928031921} 08/31/2021 09:25:42 - INFO - __main__ - Step 111440: {'lr': 7.917682078952549e-05, 'samples': 21396480, 'steps': 111439, 'loss/train': 1.7167154550552368} 08/31/2021 09:25:42 - INFO - __main__ - Step 111441: {'lr': 7.917294613755033e-05, 'samples': 21396672, 'steps': 111440, 'loss/train': 1.311815857887268} 08/31/2021 09:25:42 - INFO - __main__ - Step 111442: {'lr': 7.916907156254724e-05, 'samples': 21396864, 'steps': 111441, 'loss/train': 1.0069606304168701} 08/31/2021 09:25:43 - INFO - __main__ - Step 111443: {'lr': 7.916519706451791e-05, 'samples': 21397056, 'steps': 111442, 'loss/train': 0.6557778120040894} 08/31/2021 09:25:44 - INFO - __main__ - Step 111444: {'lr': 7.916132264346412e-05, 'samples': 21397248, 'steps': 111443, 'loss/train': 0.9228584170341492} 08/31/2021 09:25:45 - INFO - __main__ - Step 111445: {'lr': 7.915744829938762e-05, 'samples': 21397440, 'steps': 111444, 'loss/train': 0.5603708028793335} 08/31/2021 09:25:45 - INFO - __main__ - Step 111446: {'lr': 7.915357403229012e-05, 'samples': 21397632, 'steps': 111445, 'loss/train': 1.043586254119873} 08/31/2021 09:25:45 - INFO - __main__ - Step 111447: {'lr': 7.914969984217337e-05, 'samples': 21397824, 'steps': 111446, 'loss/train': 1.0863206386566162} 08/31/2021 09:25:46 - INFO - __main__ - Step 111448: {'lr': 7.914582572903914e-05, 'samples': 21398016, 'steps': 111447, 'loss/train': 1.1238243579864502} 08/31/2021 09:25:47 - INFO - __main__ - Step 111449: {'lr': 7.914195169288924e-05, 'samples': 21398208, 'steps': 111448, 'loss/train': 1.2064073085784912} 08/31/2021 09:25:48 - INFO - __main__ - Step 111450: {'lr': 7.913807773372527e-05, 'samples': 21398400, 'steps': 111449, 'loss/train': 1.0517020225524902} 08/31/2021 09:25:48 - INFO - __main__ - Step 111451: {'lr': 7.913420385154904e-05, 'samples': 21398592, 'steps': 111450, 'loss/train': 0.9528228640556335} 08/31/2021 09:25:49 - INFO - __main__ - Step 111452: {'lr': 7.91303300463623e-05, 'samples': 21398784, 'steps': 111451, 'loss/train': 0.01619289629161358} 08/31/2021 09:25:49 - INFO - __main__ - Step 111453: {'lr': 7.91264563181668e-05, 'samples': 21398976, 'steps': 111452, 'loss/train': 1.842465877532959} 08/31/2021 09:25:49 - INFO - __main__ - Step 111454: {'lr': 7.912258266696428e-05, 'samples': 21399168, 'steps': 111453, 'loss/train': 1.3421518802642822} 08/31/2021 09:25:51 - INFO - __main__ - Step 111455: {'lr': 7.911870909275647e-05, 'samples': 21399360, 'steps': 111454, 'loss/train': 1.299904227256775} 08/31/2021 09:25:51 - INFO - __main__ - Step 111456: {'lr': 7.911483559554516e-05, 'samples': 21399552, 'steps': 111455, 'loss/train': 1.5025449991226196} 08/31/2021 09:25:52 - INFO - __main__ - Step 111457: {'lr': 7.911096217533206e-05, 'samples': 21399744, 'steps': 111456, 'loss/train': 0.8406054973602295} 08/31/2021 09:25:52 - INFO - __main__ - Step 111458: {'lr': 7.910708883211892e-05, 'samples': 21399936, 'steps': 111457, 'loss/train': 1.2732287645339966} 08/31/2021 09:25:52 - INFO - __main__ - Step 111459: {'lr': 7.91032155659075e-05, 'samples': 21400128, 'steps': 111458, 'loss/train': 0.8293591737747192} 08/31/2021 09:25:54 - INFO - __main__ - Step 111460: {'lr': 7.909934237669952e-05, 'samples': 21400320, 'steps': 111459, 'loss/train': 0.2614438235759735} 08/31/2021 09:25:54 - INFO - __main__ - Step 111461: {'lr': 7.909546926449675e-05, 'samples': 21400512, 'steps': 111460, 'loss/train': 1.0899358987808228} 08/31/2021 09:25:55 - INFO - __main__ - Step 111462: {'lr': 7.909159622930102e-05, 'samples': 21400704, 'steps': 111461, 'loss/train': 1.0375796556472778} 08/31/2021 09:25:55 - INFO - __main__ - Step 111463: {'lr': 7.908772327111386e-05, 'samples': 21400896, 'steps': 111462, 'loss/train': 1.577621340751648} 08/31/2021 09:25:55 - INFO - __main__ - Step 111464: {'lr': 7.908385038993715e-05, 'samples': 21401088, 'steps': 111463, 'loss/train': 0.876157283782959} 08/31/2021 09:25:57 - INFO - __main__ - Step 111465: {'lr': 7.907997758577262e-05, 'samples': 21401280, 'steps': 111464, 'loss/train': 0.9827287197113037} 08/31/2021 09:25:57 - INFO - __main__ - Step 111466: {'lr': 7.907610485862202e-05, 'samples': 21401472, 'steps': 111465, 'loss/train': 0.9748404026031494} 08/31/2021 09:25:58 - INFO - __main__ - Step 111467: {'lr': 7.907223220848708e-05, 'samples': 21401664, 'steps': 111466, 'loss/train': 1.185032844543457} 08/31/2021 09:25:58 - INFO - __main__ - Step 111468: {'lr': 7.906835963536956e-05, 'samples': 21401856, 'steps': 111467, 'loss/train': 1.4691987037658691} 08/31/2021 09:25:58 - INFO - __main__ - Step 111469: {'lr': 7.90644871392712e-05, 'samples': 21402048, 'steps': 111468, 'loss/train': 1.6861053705215454} 08/31/2021 09:26:00 - INFO - __main__ - Step 111470: {'lr': 7.906061472019374e-05, 'samples': 21402240, 'steps': 111469, 'loss/train': 0.9256740212440491} 08/31/2021 09:26:00 - INFO - __main__ - Step 111471: {'lr': 7.905674237813895e-05, 'samples': 21402432, 'steps': 111470, 'loss/train': 1.0601203441619873} 08/31/2021 09:26:01 - INFO - __main__ - Step 111472: {'lr': 7.905287011310852e-05, 'samples': 21402624, 'steps': 111471, 'loss/train': 1.3445924520492554} 08/31/2021 09:26:01 - INFO - __main__ - Step 111473: {'lr': 7.904899792510425e-05, 'samples': 21402816, 'steps': 111472, 'loss/train': 1.1280215978622437} 08/31/2021 09:26:01 - INFO - __main__ - Step 111474: {'lr': 7.904512581412787e-05, 'samples': 21403008, 'steps': 111473, 'loss/train': 1.0228873491287231} 08/31/2021 09:26:04 - INFO - __main__ - Step 111475: {'lr': 7.904125378018109e-05, 'samples': 21403200, 'steps': 111474, 'loss/train': 0.19351385533809662} 08/31/2021 09:26:04 - INFO - __main__ - Step 111476: {'lr': 7.90373818232658e-05, 'samples': 21403392, 'steps': 111475, 'loss/train': 1.3414639234542847} 08/31/2021 09:26:05 - INFO - __main__ - Step 111477: {'lr': 7.903350994338351e-05, 'samples': 21403584, 'steps': 111476, 'loss/train': 1.3230057954788208} 08/31/2021 09:26:05 - INFO - __main__ - Step 111478: {'lr': 7.902963814053612e-05, 'samples': 21403776, 'steps': 111477, 'loss/train': 1.302783727645874} 08/31/2021 09:26:05 - INFO - __main__ - Step 111479: {'lr': 7.902576641472531e-05, 'samples': 21403968, 'steps': 111478, 'loss/train': 1.2322331666946411} 08/31/2021 09:26:07 - INFO - __main__ - Step 111480: {'lr': 7.902189476595287e-05, 'samples': 21404160, 'steps': 111479, 'loss/train': 0.9871306419372559} 08/31/2021 09:26:07 - INFO - __main__ - Step 111481: {'lr': 7.901802319422052e-05, 'samples': 21404352, 'steps': 111480, 'loss/train': 0.5093382596969604} 08/31/2021 09:26:08 - INFO - __main__ - Step 111482: {'lr': 7.901415169953e-05, 'samples': 21404544, 'steps': 111481, 'loss/train': 0.659626841545105} 08/31/2021 09:26:08 - INFO - __main__ - Step 111483: {'lr': 7.901028028188306e-05, 'samples': 21404736, 'steps': 111482, 'loss/train': 1.2217001914978027} 08/31/2021 09:26:08 - INFO - __main__ - Step 111484: {'lr': 7.900640894128147e-05, 'samples': 21404928, 'steps': 111483, 'loss/train': 1.0210323333740234} 08/31/2021 09:26:10 - INFO - __main__ - Step 111485: {'lr': 7.900253767772694e-05, 'samples': 21405120, 'steps': 111484, 'loss/train': 1.0395029783248901} 08/31/2021 09:26:10 - INFO - __main__ - Step 111486: {'lr': 7.899866649122123e-05, 'samples': 21405312, 'steps': 111485, 'loss/train': 0.6114217042922974} 08/31/2021 09:26:11 - INFO - __main__ - Step 111487: {'lr': 7.899479538176607e-05, 'samples': 21405504, 'steps': 111486, 'loss/train': 0.800495982170105} 08/31/2021 09:26:11 - INFO - __main__ - Step 111488: {'lr': 7.899092434936325e-05, 'samples': 21405696, 'steps': 111487, 'loss/train': 0.848022997379303} 08/31/2021 09:26:11 - INFO - __main__ - Step 111489: {'lr': 7.898705339401455e-05, 'samples': 21405888, 'steps': 111488, 'loss/train': 1.3040324449539185} 08/31/2021 09:26:13 - INFO - __main__ - Step 111490: {'lr': 7.898318251572153e-05, 'samples': 21406080, 'steps': 111489, 'loss/train': 1.0102728605270386} 08/31/2021 09:26:13 - INFO - __main__ - Step 111491: {'lr': 7.897931171448608e-05, 'samples': 21406272, 'steps': 111490, 'loss/train': 1.062996506690979} 08/31/2021 09:26:13 - INFO - __main__ - Step 111492: {'lr': 7.89754409903099e-05, 'samples': 21406464, 'steps': 111491, 'loss/train': 1.2190237045288086} 08/31/2021 09:26:14 - INFO - __main__ - Step 111493: {'lr': 7.897157034319476e-05, 'samples': 21406656, 'steps': 111492, 'loss/train': 1.5861910581588745} 08/31/2021 09:26:14 - INFO - __main__ - Step 111494: {'lr': 7.896769977314239e-05, 'samples': 21406848, 'steps': 111493, 'loss/train': 0.5550845265388489} 08/31/2021 09:26:15 - INFO - __main__ - Step 111495: {'lr': 7.896382928015452e-05, 'samples': 21407040, 'steps': 111494, 'loss/train': 0.5584161281585693} 08/31/2021 09:26:16 - INFO - __main__ - Step 111496: {'lr': 7.895995886423293e-05, 'samples': 21407232, 'steps': 111495, 'loss/train': 0.22279444336891174} 08/31/2021 09:26:17 - INFO - __main__ - Step 111497: {'lr': 7.895608852537934e-05, 'samples': 21407424, 'steps': 111496, 'loss/train': 1.0475738048553467} 08/31/2021 09:26:17 - INFO - __main__ - Step 111498: {'lr': 7.89522182635955e-05, 'samples': 21407616, 'steps': 111497, 'loss/train': 1.33365797996521} 08/31/2021 09:26:17 - INFO - __main__ - Step 111499: {'lr': 7.894834807888313e-05, 'samples': 21407808, 'steps': 111498, 'loss/train': 0.49756917357444763} 08/31/2021 09:26:18 - INFO - __main__ - Step 111500: {'lr': 7.894447797124401e-05, 'samples': 21408000, 'steps': 111499, 'loss/train': 1.7031269073486328} 08/31/2021 09:26:19 - INFO - __main__ - Step 111501: {'lr': 7.894060794067987e-05, 'samples': 21408192, 'steps': 111500, 'loss/train': 0.638176441192627} 08/31/2021 09:26:20 - INFO - __main__ - Step 111502: {'lr': 7.893673798719253e-05, 'samples': 21408384, 'steps': 111501, 'loss/train': 1.1338201761245728} 08/31/2021 09:26:20 - INFO - __main__ - Step 111503: {'lr': 7.893286811078357e-05, 'samples': 21408576, 'steps': 111502, 'loss/train': 1.3981740474700928} 08/31/2021 09:26:20 - INFO - __main__ - Step 111504: {'lr': 7.892899831145481e-05, 'samples': 21408768, 'steps': 111503, 'loss/train': 1.1703966856002808} 08/31/2021 09:26:21 - INFO - __main__ - Step 111505: {'lr': 7.892512858920803e-05, 'samples': 21408960, 'steps': 111504, 'loss/train': 1.3340777158737183} 08/31/2021 09:26:22 - INFO - __main__ - Step 111506: {'lr': 7.892125894404492e-05, 'samples': 21409152, 'steps': 111505, 'loss/train': 1.2123334407806396} 08/31/2021 09:26:23 - INFO - __main__ - Step 111507: {'lr': 7.891738937596729e-05, 'samples': 21409344, 'steps': 111506, 'loss/train': 0.26408448815345764} 08/31/2021 09:26:23 - INFO - __main__ - Step 111508: {'lr': 7.89135198849768e-05, 'samples': 21409536, 'steps': 111507, 'loss/train': 0.47990235686302185} 08/31/2021 09:26:23 - INFO - __main__ - Step 111509: {'lr': 7.890965047107526e-05, 'samples': 21409728, 'steps': 111508, 'loss/train': 0.9308452010154724} 08/31/2021 09:26:24 - INFO - __main__ - Step 111510: {'lr': 7.890578113426439e-05, 'samples': 21409920, 'steps': 111509, 'loss/train': 1.2892528772354126} 08/31/2021 09:26:25 - INFO - __main__ - Step 111511: {'lr': 7.890191187454593e-05, 'samples': 21410112, 'steps': 111510, 'loss/train': 0.9522422552108765} 08/31/2021 09:26:26 - INFO - __main__ - Step 111512: {'lr': 7.889804269192172e-05, 'samples': 21410304, 'steps': 111511, 'loss/train': 1.5805754661560059} 08/31/2021 09:26:26 - INFO - __main__ - Step 111513: {'lr': 7.889417358639334e-05, 'samples': 21410496, 'steps': 111512, 'loss/train': 1.2616559267044067} 08/31/2021 09:26:26 - INFO - __main__ - Step 111514: {'lr': 7.889030455796259e-05, 'samples': 21410688, 'steps': 111513, 'loss/train': 0.9890680909156799} 08/31/2021 09:26:27 - INFO - __main__ - Step 111515: {'lr': 7.888643560663123e-05, 'samples': 21410880, 'steps': 111514, 'loss/train': 0.5643125772476196} 08/31/2021 09:26:28 - INFO - __main__ - Step 111516: {'lr': 7.888256673240099e-05, 'samples': 21411072, 'steps': 111515, 'loss/train': 1.0761255025863647} 08/31/2021 09:26:29 - INFO - __main__ - Step 111517: {'lr': 7.887869793527363e-05, 'samples': 21411264, 'steps': 111516, 'loss/train': 1.3659117221832275} 08/31/2021 09:26:29 - INFO - __main__ - Step 111518: {'lr': 7.887482921525088e-05, 'samples': 21411456, 'steps': 111517, 'loss/train': 0.9337915182113647} 08/31/2021 09:26:29 - INFO - __main__ - Step 111519: {'lr': 7.88709605723345e-05, 'samples': 21411648, 'steps': 111518, 'loss/train': 0.19931815564632416} 08/31/2021 09:26:30 - INFO - __main__ - Step 111520: {'lr': 7.886709200652625e-05, 'samples': 21411840, 'steps': 111519, 'loss/train': 1.560150384902954} 08/31/2021 09:26:31 - INFO - __main__ - Step 111521: {'lr': 7.886322351782782e-05, 'samples': 21412032, 'steps': 111520, 'loss/train': 0.12442631274461746} 08/31/2021 09:26:32 - INFO - __main__ - Step 111522: {'lr': 7.885935510624099e-05, 'samples': 21412224, 'steps': 111521, 'loss/train': 1.5146868228912354} 08/31/2021 09:26:32 - INFO - __main__ - Step 111523: {'lr': 7.885548677176756e-05, 'samples': 21412416, 'steps': 111522, 'loss/train': 1.1569141149520874} 08/31/2021 09:26:32 - INFO - __main__ - Step 111524: {'lr': 7.885161851440914e-05, 'samples': 21412608, 'steps': 111523, 'loss/train': 0.9612491130828857} 08/31/2021 09:26:33 - INFO - __main__ - Step 111525: {'lr': 7.884775033416755e-05, 'samples': 21412800, 'steps': 111524, 'loss/train': 0.1312887966632843} 08/31/2021 09:26:33 - INFO - __main__ - Step 111526: {'lr': 7.884388223104449e-05, 'samples': 21412992, 'steps': 111525, 'loss/train': 0.7813593745231628} 08/31/2021 09:26:35 - INFO - __main__ - Step 111527: {'lr': 7.884001420504175e-05, 'samples': 21413184, 'steps': 111526, 'loss/train': 0.9975178837776184} 08/31/2021 09:26:36 - INFO - __main__ - Step 111528: {'lr': 7.883614625616109e-05, 'samples': 21413376, 'steps': 111527, 'loss/train': 1.108428955078125} 08/31/2021 09:26:36 - INFO - __main__ - Step 111529: {'lr': 7.883227838440419e-05, 'samples': 21413568, 'steps': 111528, 'loss/train': 0.7824264764785767} 08/31/2021 09:26:36 - INFO - __main__ - Step 111530: {'lr': 7.882841058977283e-05, 'samples': 21413760, 'steps': 111529, 'loss/train': 0.12882259488105774} 08/31/2021 09:26:37 - INFO - __main__ - Step 111531: {'lr': 7.882454287226873e-05, 'samples': 21413952, 'steps': 111530, 'loss/train': 1.5869054794311523} 08/31/2021 09:26:39 - INFO - __main__ - Step 111532: {'lr': 7.882067523189368e-05, 'samples': 21414144, 'steps': 111531, 'loss/train': 1.4158990383148193} 08/31/2021 09:26:39 - INFO - __main__ - Step 111533: {'lr': 7.881680766864938e-05, 'samples': 21414336, 'steps': 111532, 'loss/train': 0.879319965839386} 08/31/2021 09:26:40 - INFO - __main__ - Step 111534: {'lr': 7.881294018253765e-05, 'samples': 21414528, 'steps': 111533, 'loss/train': 1.3821053504943848} 08/31/2021 09:26:40 - INFO - __main__ - Step 111535: {'lr': 7.880907277356008e-05, 'samples': 21414720, 'steps': 111534, 'loss/train': 0.9754154086112976} 08/31/2021 09:26:40 - INFO - __main__ - Step 111536: {'lr': 7.880520544171854e-05, 'samples': 21414912, 'steps': 111535, 'loss/train': 1.3426709175109863} 08/31/2021 09:26:42 - INFO - __main__ - Step 111537: {'lr': 7.880133818701471e-05, 'samples': 21415104, 'steps': 111536, 'loss/train': 0.1070309728384018} 08/31/2021 09:26:42 - INFO - __main__ - Step 111538: {'lr': 7.879747100945037e-05, 'samples': 21415296, 'steps': 111537, 'loss/train': 1.33012056350708} 08/31/2021 09:26:43 - INFO - __main__ - Step 111539: {'lr': 7.879360390902724e-05, 'samples': 21415488, 'steps': 111538, 'loss/train': 0.9734852313995361} 08/31/2021 09:26:43 - INFO - __main__ - Step 111540: {'lr': 7.878973688574706e-05, 'samples': 21415680, 'steps': 111539, 'loss/train': 1.2282540798187256} 08/31/2021 09:26:43 - INFO - __main__ - Step 111541: {'lr': 7.87858699396116e-05, 'samples': 21415872, 'steps': 111540, 'loss/train': 1.4356054067611694} 08/31/2021 09:26:44 - INFO - __main__ - Step 111542: {'lr': 7.878200307062255e-05, 'samples': 21416064, 'steps': 111541, 'loss/train': 1.0210868120193481} 08/31/2021 09:26:45 - INFO - __main__ - Step 111543: {'lr': 7.877813627878173e-05, 'samples': 21416256, 'steps': 111542, 'loss/train': 1.1788127422332764} 08/31/2021 09:26:46 - INFO - __main__ - Step 111544: {'lr': 7.877426956409082e-05, 'samples': 21416448, 'steps': 111543, 'loss/train': 1.2902579307556152} 08/31/2021 09:26:46 - INFO - __main__ - Step 111545: {'lr': 7.877040292655165e-05, 'samples': 21416640, 'steps': 111544, 'loss/train': 1.4046944379806519} 08/31/2021 09:26:46 - INFO - __main__ - Step 111546: {'lr': 7.876653636616582e-05, 'samples': 21416832, 'steps': 111545, 'loss/train': 1.9173673391342163} 08/31/2021 09:26:47 - INFO - __main__ - Step 111547: {'lr': 7.876266988293515e-05, 'samples': 21417024, 'steps': 111546, 'loss/train': 1.0380616188049316} 08/31/2021 09:26:48 - INFO - __main__ - Step 111548: {'lr': 7.87588034768614e-05, 'samples': 21417216, 'steps': 111547, 'loss/train': 1.128029704093933} 08/31/2021 09:26:49 - INFO - __main__ - Step 111549: {'lr': 7.875493714794627e-05, 'samples': 21417408, 'steps': 111548, 'loss/train': 1.1684083938598633} 08/31/2021 09:26:49 - INFO - __main__ - Step 111550: {'lr': 7.875107089619152e-05, 'samples': 21417600, 'steps': 111549, 'loss/train': 0.8147314190864563} 08/31/2021 09:26:49 - INFO - __main__ - Step 111551: {'lr': 7.874720472159891e-05, 'samples': 21417792, 'steps': 111550, 'loss/train': 1.3208931684494019} 08/31/2021 09:26:50 - INFO - __main__ - Step 111552: {'lr': 7.874333862417016e-05, 'samples': 21417984, 'steps': 111551, 'loss/train': 0.8479331135749817} 08/31/2021 09:26:51 - INFO - __main__ - Step 111553: {'lr': 7.873947260390701e-05, 'samples': 21418176, 'steps': 111552, 'loss/train': 1.1423238515853882} 08/31/2021 09:26:52 - INFO - __main__ - Step 111554: {'lr': 7.87356066608112e-05, 'samples': 21418368, 'steps': 111553, 'loss/train': 1.5933916568756104} 08/31/2021 09:26:52 - INFO - __main__ - Step 111555: {'lr': 7.873174079488452e-05, 'samples': 21418560, 'steps': 111554, 'loss/train': 0.9260703921318054} 08/31/2021 09:26:53 - INFO - __main__ - Step 111556: {'lr': 7.872787500612874e-05, 'samples': 21418752, 'steps': 111555, 'loss/train': 2.0547494888305664} 08/31/2021 09:26:53 - INFO - __main__ - Step 111557: {'lr': 7.872400929454543e-05, 'samples': 21418944, 'steps': 111556, 'loss/train': 1.1883552074432373} 08/31/2021 09:26:53 - INFO - __main__ - Step 111558: {'lr': 7.872014366013647e-05, 'samples': 21419136, 'steps': 111557, 'loss/train': 0.033074915409088135} 08/31/2021 09:26:55 - INFO - __main__ - Step 111559: {'lr': 7.871627810290355e-05, 'samples': 21419328, 'steps': 111558, 'loss/train': 0.6245222091674805} 08/31/2021 09:26:55 - INFO - __main__ - Step 111560: {'lr': 7.871241262284845e-05, 'samples': 21419520, 'steps': 111559, 'loss/train': 1.0637041330337524} 08/31/2021 09:26:56 - INFO - __main__ - Step 111561: {'lr': 7.870854721997289e-05, 'samples': 21419712, 'steps': 111560, 'loss/train': 0.9455861449241638} 08/31/2021 09:26:56 - INFO - __main__ - Step 111562: {'lr': 7.87046818942786e-05, 'samples': 21419904, 'steps': 111561, 'loss/train': 0.8915756940841675} 08/31/2021 09:26:57 - INFO - __main__ - Step 111563: {'lr': 7.870081664576737e-05, 'samples': 21420096, 'steps': 111562, 'loss/train': 1.4187809228897095} 08/31/2021 09:26:58 - INFO - __main__ - Step 111564: {'lr': 7.869695147444087e-05, 'samples': 21420288, 'steps': 111563, 'loss/train': 0.8357287049293518} 08/31/2021 09:26:58 - INFO - __main__ - Step 111565: {'lr': 7.86930863803009e-05, 'samples': 21420480, 'steps': 111564, 'loss/train': 0.7394019365310669} 08/31/2021 09:26:59 - INFO - __main__ - Step 111566: {'lr': 7.868922136334919e-05, 'samples': 21420672, 'steps': 111565, 'loss/train': 1.1190307140350342} 08/31/2021 09:26:59 - INFO - __main__ - Step 111567: {'lr': 7.868535642358746e-05, 'samples': 21420864, 'steps': 111566, 'loss/train': 0.6928584575653076} 08/31/2021 09:26:59 - INFO - __main__ - Step 111568: {'lr': 7.868149156101748e-05, 'samples': 21421056, 'steps': 111567, 'loss/train': 1.2039711475372314} 08/31/2021 09:27:01 - INFO - __main__ - Step 111569: {'lr': 7.867762677564094e-05, 'samples': 21421248, 'steps': 111568, 'loss/train': 1.0868167877197266} 08/31/2021 09:27:02 - INFO - __main__ - Step 111570: {'lr': 7.867376206745974e-05, 'samples': 21421440, 'steps': 111569, 'loss/train': 1.0904330015182495} 08/31/2021 09:27:02 - INFO - __main__ - Step 111571: {'lr': 7.86698974364754e-05, 'samples': 21421632, 'steps': 111570, 'loss/train': 1.2006659507751465} 08/31/2021 09:27:02 - INFO - __main__ - Step 111572: {'lr': 7.866603288268976e-05, 'samples': 21421824, 'steps': 111571, 'loss/train': 1.4133036136627197} 08/31/2021 09:27:03 - INFO - __main__ - Step 111573: {'lr': 7.866216840610455e-05, 'samples': 21422016, 'steps': 111572, 'loss/train': 1.0435670614242554} 08/31/2021 09:27:04 - INFO - __main__ - Step 111574: {'lr': 7.865830400672152e-05, 'samples': 21422208, 'steps': 111573, 'loss/train': 0.05536356195807457} 08/31/2021 09:27:05 - INFO - __main__ - Step 111575: {'lr': 7.865443968454245e-05, 'samples': 21422400, 'steps': 111574, 'loss/train': 1.3480308055877686} 08/31/2021 09:27:05 - INFO - __main__ - Step 111576: {'lr': 7.865057543956902e-05, 'samples': 21422592, 'steps': 111575, 'loss/train': 0.8824524283409119} 08/31/2021 09:27:05 - INFO - __main__ - Step 111577: {'lr': 7.8646711271803e-05, 'samples': 21422784, 'steps': 111576, 'loss/train': 1.0877749919891357} 08/31/2021 09:27:06 - INFO - __main__ - Step 111578: {'lr': 7.864284718124615e-05, 'samples': 21422976, 'steps': 111577, 'loss/train': 0.1417047530412674} 08/31/2021 09:27:06 - INFO - __main__ - Step 111579: {'lr': 7.863898316790016e-05, 'samples': 21423168, 'steps': 111578, 'loss/train': 0.8955734968185425} 08/31/2021 09:27:09 - INFO - __main__ - Step 111580: {'lr': 7.86351192317668e-05, 'samples': 21423360, 'steps': 111579, 'loss/train': 0.8296026587486267} 08/31/2021 09:27:09 - INFO - __main__ - Step 111581: {'lr': 7.863125537284783e-05, 'samples': 21423552, 'steps': 111580, 'loss/train': 0.7200308442115784} 08/31/2021 09:27:10 - INFO - __main__ - Step 111582: {'lr': 7.862739159114496e-05, 'samples': 21423744, 'steps': 111581, 'loss/train': 1.4361323118209839} 08/31/2021 09:27:10 - INFO - __main__ - Step 111583: {'lr': 7.862352788666003e-05, 'samples': 21423936, 'steps': 111582, 'loss/train': 0.9633221626281738} 08/31/2021 09:27:10 - INFO - __main__ - Step 111584: {'lr': 7.86196642593946e-05, 'samples': 21424128, 'steps': 111583, 'loss/train': 1.1537071466445923} 08/31/2021 09:27:11 - INFO - __main__ - Step 111585: {'lr': 7.861580070935051e-05, 'samples': 21424320, 'steps': 111584, 'loss/train': 1.4938973188400269} 08/31/2021 09:27:12 - INFO - __main__ - Step 111586: {'lr': 7.861193723652951e-05, 'samples': 21424512, 'steps': 111585, 'loss/train': 0.4587987959384918} 08/31/2021 09:27:13 - INFO - __main__ - Step 111587: {'lr': 7.86080738409333e-05, 'samples': 21424704, 'steps': 111586, 'loss/train': 1.3736391067504883} 08/31/2021 09:27:13 - INFO - __main__ - Step 111588: {'lr': 7.860421052256366e-05, 'samples': 21424896, 'steps': 111587, 'loss/train': 1.8679193258285522} 08/31/2021 09:27:13 - INFO - __main__ - Step 111589: {'lr': 7.860034728142231e-05, 'samples': 21425088, 'steps': 111588, 'loss/train': 5.776585102081299} 08/31/2021 09:27:14 - INFO - __main__ - Step 111590: {'lr': 7.859648411751103e-05, 'samples': 21425280, 'steps': 111589, 'loss/train': 1.010562777519226} 08/31/2021 09:27:14 - INFO - __main__ - Step 111591: {'lr': 7.85926210308315e-05, 'samples': 21425472, 'steps': 111590, 'loss/train': 0.20743174850940704} 08/31/2021 09:27:16 - INFO - __main__ - Step 111592: {'lr': 7.858875802138552e-05, 'samples': 21425664, 'steps': 111591, 'loss/train': 0.04238784313201904} 08/31/2021 09:27:16 - INFO - __main__ - Step 111593: {'lr': 7.858489508917477e-05, 'samples': 21425856, 'steps': 111592, 'loss/train': 0.8754770755767822} 08/31/2021 09:27:17 - INFO - __main__ - Step 111594: {'lr': 7.858103223420101e-05, 'samples': 21426048, 'steps': 111593, 'loss/train': 0.6011940836906433} 08/31/2021 09:27:17 - INFO - __main__ - Step 111595: {'lr': 7.857716945646603e-05, 'samples': 21426240, 'steps': 111594, 'loss/train': 1.5630748271942139} 08/31/2021 09:27:17 - INFO - __main__ - Step 111596: {'lr': 7.857330675597152e-05, 'samples': 21426432, 'steps': 111595, 'loss/train': 0.8631746768951416} 08/31/2021 09:27:19 - INFO - __main__ - Step 111597: {'lr': 7.85694441327193e-05, 'samples': 21426624, 'steps': 111596, 'loss/train': 1.6922825574874878} 08/31/2021 09:27:19 - INFO - __main__ - Step 111598: {'lr': 7.856558158671095e-05, 'samples': 21426816, 'steps': 111597, 'loss/train': 1.089232087135315} 08/31/2021 09:27:20 - INFO - __main__ - Step 111599: {'lr': 7.856171911794834e-05, 'samples': 21427008, 'steps': 111598, 'loss/train': 0.9367533922195435} 08/31/2021 09:27:20 - INFO - __main__ - Step 111600: {'lr': 7.855785672643315e-05, 'samples': 21427200, 'steps': 111599, 'loss/train': 1.082902431488037} 08/31/2021 09:27:20 - INFO - __main__ - Step 111601: {'lr': 7.855399441216716e-05, 'samples': 21427392, 'steps': 111600, 'loss/train': 0.6567075848579407} 08/31/2021 09:27:22 - INFO - __main__ - Step 111602: {'lr': 7.855013217515209e-05, 'samples': 21427584, 'steps': 111601, 'loss/train': 0.030518345534801483} 08/31/2021 09:27:23 - INFO - __main__ - Step 111603: {'lr': 7.854627001538966e-05, 'samples': 21427776, 'steps': 111602, 'loss/train': 1.0806571245193481} 08/31/2021 09:27:23 - INFO - __main__ - Step 111604: {'lr': 7.854240793288167e-05, 'samples': 21427968, 'steps': 111603, 'loss/train': 0.9428462982177734} 08/31/2021 09:27:24 - INFO - __main__ - Step 111605: {'lr': 7.853854592762983e-05, 'samples': 21428160, 'steps': 111604, 'loss/train': 1.8776729106903076} 08/31/2021 09:27:24 - INFO - __main__ - Step 111606: {'lr': 7.853468399963584e-05, 'samples': 21428352, 'steps': 111605, 'loss/train': 0.9774929881095886} 08/31/2021 09:27:24 - INFO - __main__ - Step 111607: {'lr': 7.85308221489015e-05, 'samples': 21428544, 'steps': 111606, 'loss/train': 1.0388970375061035} 08/31/2021 09:27:26 - INFO - __main__ - Step 111608: {'lr': 7.85269603754285e-05, 'samples': 21428736, 'steps': 111607, 'loss/train': 2.2017288208007812} 08/31/2021 09:27:26 - INFO - __main__ - Step 111609: {'lr': 7.852309867921864e-05, 'samples': 21428928, 'steps': 111608, 'loss/train': 1.212755799293518} 08/31/2021 09:27:27 - INFO - __main__ - Step 111610: {'lr': 7.85192370602737e-05, 'samples': 21429120, 'steps': 111609, 'loss/train': 1.3271695375442505} 08/31/2021 09:27:27 - INFO - __main__ - Step 111611: {'lr': 7.851537551859525e-05, 'samples': 21429312, 'steps': 111610, 'loss/train': 0.541528582572937} 08/31/2021 09:27:27 - INFO - __main__ - Step 111612: {'lr': 7.85115140541851e-05, 'samples': 21429504, 'steps': 111611, 'loss/train': 0.7497491836547852} 08/31/2021 09:27:29 - INFO - __main__ - Step 111613: {'lr': 7.850765266704507e-05, 'samples': 21429696, 'steps': 111612, 'loss/train': 0.028136061504483223} 08/31/2021 09:27:29 - INFO - __main__ - Step 111614: {'lr': 7.850379135717681e-05, 'samples': 21429888, 'steps': 111613, 'loss/train': 0.9322394728660583} 08/31/2021 09:27:30 - INFO - __main__ - Step 111615: {'lr': 7.849993012458211e-05, 'samples': 21430080, 'steps': 111614, 'loss/train': 1.3688249588012695} 08/31/2021 09:27:30 - INFO - __main__ - Step 111616: {'lr': 7.84960689692627e-05, 'samples': 21430272, 'steps': 111615, 'loss/train': 1.5108040571212769} 08/31/2021 09:27:31 - INFO - __main__ - Step 111617: {'lr': 7.84922078912203e-05, 'samples': 21430464, 'steps': 111616, 'loss/train': 1.4162499904632568} 08/31/2021 09:27:32 - INFO - __main__ - Step 111618: {'lr': 7.848834689045667e-05, 'samples': 21430656, 'steps': 111617, 'loss/train': 2.2121715545654297} 08/31/2021 09:27:33 - INFO - __main__ - Step 111619: {'lr': 7.848448596697355e-05, 'samples': 21430848, 'steps': 111618, 'loss/train': 1.1953234672546387} 08/31/2021 09:27:33 - INFO - __main__ - Step 111620: {'lr': 7.848062512077267e-05, 'samples': 21431040, 'steps': 111619, 'loss/train': 1.1650073528289795} 08/31/2021 09:27:33 - INFO - __main__ - Step 111621: {'lr': 7.847676435185577e-05, 'samples': 21431232, 'steps': 111620, 'loss/train': 0.016937335953116417} 08/31/2021 09:27:34 - INFO - __main__ - Step 111622: {'lr': 7.847290366022459e-05, 'samples': 21431424, 'steps': 111621, 'loss/train': 1.404787540435791} 08/31/2021 09:27:34 - INFO - __main__ - Step 111623: {'lr': 7.846904304588096e-05, 'samples': 21431616, 'steps': 111622, 'loss/train': 1.0905157327651978} 08/31/2021 09:27:36 - INFO - __main__ - Step 111624: {'lr': 7.846518250882645e-05, 'samples': 21431808, 'steps': 111623, 'loss/train': 1.3472820520401} 08/31/2021 09:27:36 - INFO - __main__ - Step 111625: {'lr': 7.84613220490629e-05, 'samples': 21432000, 'steps': 111624, 'loss/train': 0.9556056261062622} 08/31/2021 09:27:37 - INFO - __main__ - Step 111626: {'lr': 7.845746166659201e-05, 'samples': 21432192, 'steps': 111625, 'loss/train': 0.7267315983772278} 08/31/2021 09:27:37 - INFO - __main__ - Step 111627: {'lr': 7.845360136141556e-05, 'samples': 21432384, 'steps': 111626, 'loss/train': 1.3679863214492798} 08/31/2021 09:27:37 - INFO - __main__ - Step 111628: {'lr': 7.844974113353523e-05, 'samples': 21432576, 'steps': 111627, 'loss/train': 1.4569776058197021} 08/31/2021 09:27:38 - INFO - __main__ - Step 111629: {'lr': 7.844588098295283e-05, 'samples': 21432768, 'steps': 111628, 'loss/train': 1.0059702396392822} 08/31/2021 09:27:39 - INFO - __main__ - Step 111630: {'lr': 7.844202090967006e-05, 'samples': 21432960, 'steps': 111629, 'loss/train': 1.2478910684585571} 08/31/2021 09:27:40 - INFO - __main__ - Step 111631: {'lr': 7.843816091368866e-05, 'samples': 21433152, 'steps': 111630, 'loss/train': 1.297861933708191} 08/31/2021 09:27:40 - INFO - __main__ - Step 111632: {'lr': 7.84343009950104e-05, 'samples': 21433344, 'steps': 111631, 'loss/train': 1.1087095737457275} 08/31/2021 09:27:41 - INFO - __main__ - Step 111633: {'lr': 7.843044115363698e-05, 'samples': 21433536, 'steps': 111632, 'loss/train': 1.3525296449661255} 08/31/2021 09:27:41 - INFO - __main__ - Step 111634: {'lr': 7.842658138957018e-05, 'samples': 21433728, 'steps': 111633, 'loss/train': 0.3869025409221649} 08/31/2021 09:27:43 - INFO - __main__ - Step 111635: {'lr': 7.842272170281168e-05, 'samples': 21433920, 'steps': 111634, 'loss/train': 1.1176114082336426} 08/31/2021 09:27:43 - INFO - __main__ - Step 111636: {'lr': 7.841886209336327e-05, 'samples': 21434112, 'steps': 111635, 'loss/train': 1.0144902467727661} 08/31/2021 09:27:44 - INFO - __main__ - Step 111637: {'lr': 7.841500256122674e-05, 'samples': 21434304, 'steps': 111636, 'loss/train': 0.6017727255821228} 08/31/2021 09:27:44 - INFO - __main__ - Step 111638: {'lr': 7.841114310640371e-05, 'samples': 21434496, 'steps': 111637, 'loss/train': 1.0102430582046509} 08/31/2021 09:27:44 - INFO - __main__ - Step 111639: {'lr': 7.840728372889597e-05, 'samples': 21434688, 'steps': 111638, 'loss/train': 1.8917937278747559} 08/31/2021 09:27:46 - INFO - __main__ - Step 111640: {'lr': 7.840342442870524e-05, 'samples': 21434880, 'steps': 111639, 'loss/train': 1.2708051204681396} 08/31/2021 09:27:46 - INFO - __main__ - Step 111641: {'lr': 7.839956520583327e-05, 'samples': 21435072, 'steps': 111640, 'loss/train': 1.0049200057983398} 08/31/2021 09:27:47 - INFO - __main__ - Step 111642: {'lr': 7.839570606028185e-05, 'samples': 21435264, 'steps': 111641, 'loss/train': 0.49393534660339355} 08/31/2021 09:27:47 - INFO - __main__ - Step 111643: {'lr': 7.839184699205263e-05, 'samples': 21435456, 'steps': 111642, 'loss/train': 0.6485201120376587} 08/31/2021 09:27:47 - INFO - __main__ - Step 111644: {'lr': 7.838798800114741e-05, 'samples': 21435648, 'steps': 111643, 'loss/train': 0.9919729232788086} 08/31/2021 09:27:49 - INFO - __main__ - Step 111645: {'lr': 7.838412908756792e-05, 'samples': 21435840, 'steps': 111644, 'loss/train': 0.1060757040977478} 08/31/2021 09:27:50 - INFO - __main__ - Step 111646: {'lr': 7.838027025131592e-05, 'samples': 21436032, 'steps': 111645, 'loss/train': 1.3453022241592407} 08/31/2021 09:27:50 - INFO - __main__ - Step 111647: {'lr': 7.837641149239308e-05, 'samples': 21436224, 'steps': 111646, 'loss/train': 0.029341666027903557} 08/31/2021 09:27:50 - INFO - __main__ - Step 111648: {'lr': 7.837255281080119e-05, 'samples': 21436416, 'steps': 111647, 'loss/train': 1.3732775449752808} 08/31/2021 09:27:51 - INFO - __main__ - Step 111649: {'lr': 7.8368694206542e-05, 'samples': 21436608, 'steps': 111648, 'loss/train': 1.4619520902633667} 08/31/2021 09:27:53 - INFO - __main__ - Step 111650: {'lr': 7.836483567961727e-05, 'samples': 21436800, 'steps': 111649, 'loss/train': 0.1608056277036667} 08/31/2021 09:27:53 - INFO - __main__ - Step 111651: {'lr': 7.836097723002866e-05, 'samples': 21436992, 'steps': 111650, 'loss/train': 2.086456060409546} 08/31/2021 09:27:54 - INFO - __main__ - Step 111652: {'lr': 7.83571188577779e-05, 'samples': 21437184, 'steps': 111651, 'loss/train': 0.7481544017791748} 08/31/2021 09:27:54 - INFO - __main__ - Step 111653: {'lr': 7.835326056286682e-05, 'samples': 21437376, 'steps': 111652, 'loss/train': 0.024178210645914078} 08/31/2021 09:27:55 - INFO - __main__ - Step 111654: {'lr': 7.834940234529709e-05, 'samples': 21437568, 'steps': 111653, 'loss/train': 0.014597602188587189} 08/31/2021 09:27:55 - INFO - __main__ - Step 111655: {'lr': 7.834554420507048e-05, 'samples': 21437760, 'steps': 111654, 'loss/train': 0.32637009024620056} 08/31/2021 09:27:55 - INFO - __main__ - Step 111656: {'lr': 7.83416861421887e-05, 'samples': 21437952, 'steps': 111655, 'loss/train': 0.24782025814056396} 08/31/2021 09:27:57 - INFO - __main__ - Step 111657: {'lr': 7.833782815665353e-05, 'samples': 21438144, 'steps': 111656, 'loss/train': 1.3498380184173584} 08/31/2021 09:27:57 - INFO - __main__ - Step 111658: {'lr': 7.833397024846666e-05, 'samples': 21438336, 'steps': 111657, 'loss/train': 1.0143839120864868} 08/31/2021 09:27:58 - INFO - __main__ - Step 111659: {'lr': 7.833011241762988e-05, 'samples': 21438528, 'steps': 111658, 'loss/train': 1.0617643594741821} 08/31/2021 09:27:58 - INFO - __main__ - Step 111660: {'lr': 7.83262546641449e-05, 'samples': 21438720, 'steps': 111659, 'loss/train': 1.4972270727157593} 08/31/2021 09:27:59 - INFO - __main__ - Step 111661: {'lr': 7.832239698801344e-05, 'samples': 21438912, 'steps': 111660, 'loss/train': 0.7238525152206421} 08/31/2021 09:28:00 - INFO - __main__ - Step 111662: {'lr': 7.831853938923727e-05, 'samples': 21439104, 'steps': 111661, 'loss/train': 0.12558363378047943} 08/31/2021 09:28:00 - INFO - __main__ - Step 111663: {'lr': 7.831468186781812e-05, 'samples': 21439296, 'steps': 111662, 'loss/train': 1.2583857774734497} 08/31/2021 09:28:01 - INFO - __main__ - Step 111664: {'lr': 7.831082442375778e-05, 'samples': 21439488, 'steps': 111663, 'loss/train': 2.4370713233947754} 08/31/2021 09:28:01 - INFO - __main__ - Step 111665: {'lr': 7.830696705705789e-05, 'samples': 21439680, 'steps': 111664, 'loss/train': 1.4162167310714722} 08/31/2021 09:28:01 - INFO - __main__ - Step 111666: {'lr': 7.830310976772021e-05, 'samples': 21439872, 'steps': 111665, 'loss/train': 1.2020028829574585} 08/31/2021 09:28:03 - INFO - __main__ - Step 111667: {'lr': 7.829925255574652e-05, 'samples': 21440064, 'steps': 111666, 'loss/train': 0.9074230790138245} 08/31/2021 09:28:04 - INFO - __main__ - Step 111668: {'lr': 7.829539542113851e-05, 'samples': 21440256, 'steps': 111667, 'loss/train': 1.334592580795288} 08/31/2021 09:28:04 - INFO - __main__ - Step 111669: {'lr': 7.829153836389796e-05, 'samples': 21440448, 'steps': 111668, 'loss/train': 1.4106892347335815} 08/31/2021 09:28:04 - INFO - __main__ - Step 111670: {'lr': 7.828768138402659e-05, 'samples': 21440640, 'steps': 111669, 'loss/train': 0.9813550114631653} 08/31/2021 09:28:05 - INFO - __main__ - Step 111671: {'lr': 7.828382448152615e-05, 'samples': 21440832, 'steps': 111670, 'loss/train': 1.1926627159118652} 08/31/2021 09:28:05 - INFO - __main__ - Step 111672: {'lr': 7.827996765639836e-05, 'samples': 21441024, 'steps': 111671, 'loss/train': 0.07918031513690948} 08/31/2021 09:28:06 - INFO - __main__ - Step 111673: {'lr': 7.827611090864495e-05, 'samples': 21441216, 'steps': 111672, 'loss/train': 0.7553418278694153} 08/31/2021 09:28:07 - INFO - __main__ - Step 111674: {'lr': 7.82722542382677e-05, 'samples': 21441408, 'steps': 111673, 'loss/train': 1.164989948272705} 08/31/2021 09:28:07 - INFO - __main__ - Step 111675: {'lr': 7.826839764526833e-05, 'samples': 21441600, 'steps': 111674, 'loss/train': 0.025330469012260437} 08/31/2021 09:28:08 - INFO - __main__ - Step 111676: {'lr': 7.826454112964853e-05, 'samples': 21441792, 'steps': 111675, 'loss/train': 0.8326135873794556} 08/31/2021 09:28:08 - INFO - __main__ - Step 111677: {'lr': 7.82606846914102e-05, 'samples': 21441984, 'steps': 111676, 'loss/train': 1.0289281606674194} 08/31/2021 09:28:10 - INFO - __main__ - Step 111678: {'lr': 7.825682833055487e-05, 'samples': 21442176, 'steps': 111677, 'loss/train': 1.3561980724334717} 08/31/2021 09:28:10 - INFO - __main__ - Step 111679: {'lr': 7.825297204708434e-05, 'samples': 21442368, 'steps': 111678, 'loss/train': 0.5584568977355957} 08/31/2021 09:28:10 - INFO - __main__ - Step 111680: {'lr': 7.824911584100037e-05, 'samples': 21442560, 'steps': 111679, 'loss/train': 1.1428455114364624} 08/31/2021 09:28:11 - INFO - __main__ - Step 111681: {'lr': 7.824525971230473e-05, 'samples': 21442752, 'steps': 111680, 'loss/train': 1.5530030727386475} 08/31/2021 09:28:11 - INFO - __main__ - Step 111682: {'lr': 7.824140366099907e-05, 'samples': 21442944, 'steps': 111681, 'loss/train': 1.6690064668655396} 08/31/2021 09:28:13 - INFO - __main__ - Step 111683: {'lr': 7.823754768708525e-05, 'samples': 21443136, 'steps': 111682, 'loss/train': 0.8174843788146973} 08/31/2021 09:28:13 - INFO - __main__ - Step 111684: {'lr': 7.823369179056489e-05, 'samples': 21443328, 'steps': 111683, 'loss/train': 2.7712411880493164} 08/31/2021 09:28:13 - INFO - __main__ - Step 111685: {'lr': 7.822983597143982e-05, 'samples': 21443520, 'steps': 111684, 'loss/train': 1.4738813638687134} 08/31/2021 09:28:14 - INFO - __main__ - Step 111686: {'lr': 7.82259802297117e-05, 'samples': 21443712, 'steps': 111685, 'loss/train': 1.35459303855896} 08/31/2021 09:28:14 - INFO - __main__ - Step 111687: {'lr': 7.82221245653823e-05, 'samples': 21443904, 'steps': 111686, 'loss/train': 0.8092252016067505} 08/31/2021 09:28:16 - INFO - __main__ - Step 111688: {'lr': 7.821826897845338e-05, 'samples': 21444096, 'steps': 111687, 'loss/train': 1.3588488101959229} 08/31/2021 09:28:16 - INFO - __main__ - Step 111689: {'lr': 7.821441346892667e-05, 'samples': 21444288, 'steps': 111688, 'loss/train': 1.2976006269454956} 08/31/2021 09:28:16 - INFO - __main__ - Step 111690: {'lr': 7.821055803680386e-05, 'samples': 21444480, 'steps': 111689, 'loss/train': 1.4144084453582764} 08/31/2021 09:28:17 - INFO - __main__ - Step 111691: {'lr': 7.820670268208682e-05, 'samples': 21444672, 'steps': 111690, 'loss/train': 1.5319406986236572} 08/31/2021 09:28:17 - INFO - __main__ - Step 111692: {'lr': 7.820284740477712e-05, 'samples': 21444864, 'steps': 111691, 'loss/train': 1.3302891254425049} 08/31/2021 09:28:19 - INFO - __main__ - Step 111693: {'lr': 7.819899220487655e-05, 'samples': 21445056, 'steps': 111692, 'loss/train': 0.8766304850578308} 08/31/2021 09:28:20 - INFO - __main__ - Step 111694: {'lr': 7.819513708238684e-05, 'samples': 21445248, 'steps': 111693, 'loss/train': 0.7588984966278076} 08/31/2021 09:28:20 - INFO - __main__ - Step 111695: {'lr': 7.819128203730979e-05, 'samples': 21445440, 'steps': 111694, 'loss/train': 0.8245357871055603} 08/31/2021 09:28:20 - INFO - __main__ - Step 111696: {'lr': 7.81874270696471e-05, 'samples': 21445632, 'steps': 111695, 'loss/train': 1.5339993238449097} 08/31/2021 09:28:21 - INFO - __main__ - Step 111697: {'lr': 7.818357217940048e-05, 'samples': 21445824, 'steps': 111696, 'loss/train': 1.9223341941833496} 08/31/2021 09:28:22 - INFO - __main__ - Step 111698: {'lr': 7.81797173665717e-05, 'samples': 21446016, 'steps': 111697, 'loss/train': 1.1256392002105713} 08/31/2021 09:28:23 - INFO - __main__ - Step 111699: {'lr': 7.817586263116247e-05, 'samples': 21446208, 'steps': 111698, 'loss/train': 1.1145967245101929} 08/31/2021 09:28:23 - INFO - __main__ - Step 111700: {'lr': 7.817200797317458e-05, 'samples': 21446400, 'steps': 111699, 'loss/train': 0.33000192046165466} 08/31/2021 09:28:23 - INFO - __main__ - Step 111701: {'lr': 7.816815339260972e-05, 'samples': 21446592, 'steps': 111700, 'loss/train': 1.6894962787628174} 08/31/2021 09:28:24 - INFO - __main__ - Step 111702: {'lr': 7.81642988894696e-05, 'samples': 21446784, 'steps': 111701, 'loss/train': 0.5580785274505615} 08/31/2021 09:28:25 - INFO - __main__ - Step 111703: {'lr': 7.816044446375603e-05, 'samples': 21446976, 'steps': 111702, 'loss/train': 1.0391806364059448} 08/31/2021 09:28:26 - INFO - __main__ - Step 111704: {'lr': 7.81565901154708e-05, 'samples': 21447168, 'steps': 111703, 'loss/train': 0.4790826141834259} 08/31/2021 09:28:26 - INFO - __main__ - Step 111705: {'lr': 7.815273584461546e-05, 'samples': 21447360, 'steps': 111704, 'loss/train': 0.512239933013916} 08/31/2021 09:28:26 - INFO - __main__ - Step 111706: {'lr': 7.814888165119186e-05, 'samples': 21447552, 'steps': 111705, 'loss/train': 1.2046653032302856} 08/31/2021 09:28:27 - INFO - __main__ - Step 111707: {'lr': 7.814502753520173e-05, 'samples': 21447744, 'steps': 111706, 'loss/train': 1.5084656476974487} 08/31/2021 09:28:29 - INFO - __main__ - Step 111708: {'lr': 7.814117349664676e-05, 'samples': 21447936, 'steps': 111707, 'loss/train': 1.0504419803619385} 08/31/2021 09:28:29 - INFO - __main__ - Step 111709: {'lr': 7.813731953552877e-05, 'samples': 21448128, 'steps': 111708, 'loss/train': 0.6180660724639893} 08/31/2021 09:28:29 - INFO - __main__ - Step 111710: {'lr': 7.813346565184943e-05, 'samples': 21448320, 'steps': 111709, 'loss/train': 1.117311716079712} 08/31/2021 09:28:30 - INFO - __main__ - Step 111711: {'lr': 7.812961184561048e-05, 'samples': 21448512, 'steps': 111710, 'loss/train': 1.4322742223739624} 08/31/2021 09:28:30 - INFO - __main__ - Step 111712: {'lr': 7.812575811681371e-05, 'samples': 21448704, 'steps': 111711, 'loss/train': 0.024779438972473145} 08/31/2021 09:28:30 - INFO - __main__ - Step 111713: {'lr': 7.81219044654608e-05, 'samples': 21448896, 'steps': 111712, 'loss/train': 0.02071981132030487} 08/31/2021 09:28:31 - INFO - __main__ - Step 111714: {'lr': 7.811805089155352e-05, 'samples': 21449088, 'steps': 111713, 'loss/train': 2.4415290355682373} 08/31/2021 09:28:32 - INFO - __main__ - Step 111715: {'lr': 7.811419739509359e-05, 'samples': 21449280, 'steps': 111714, 'loss/train': 1.5936050415039062} 08/31/2021 09:28:33 - INFO - __main__ - Step 111716: {'lr': 7.811034397608275e-05, 'samples': 21449472, 'steps': 111715, 'loss/train': 1.1757913827896118} 08/31/2021 09:28:33 - INFO - __main__ - Step 111717: {'lr': 7.810649063452272e-05, 'samples': 21449664, 'steps': 111716, 'loss/train': 0.8578094244003296} 08/31/2021 09:28:33 - INFO - __main__ - Step 111718: {'lr': 7.810263737041534e-05, 'samples': 21449856, 'steps': 111717, 'loss/train': 0.8496178984642029} 08/31/2021 09:28:34 - INFO - __main__ - Step 111719: {'lr': 7.809878418376221e-05, 'samples': 21450048, 'steps': 111718, 'loss/train': 0.8925012946128845} 08/31/2021 09:28:35 - INFO - __main__ - Step 111720: {'lr': 7.809493107456508e-05, 'samples': 21450240, 'steps': 111719, 'loss/train': 0.2959166467189789} 08/31/2021 09:28:36 - INFO - __main__ - Step 111721: {'lr': 7.809107804282572e-05, 'samples': 21450432, 'steps': 111720, 'loss/train': 1.4948557615280151} 08/31/2021 09:28:36 - INFO - __main__ - Step 111722: {'lr': 7.80872250885459e-05, 'samples': 21450624, 'steps': 111721, 'loss/train': 2.282101631164551} 08/31/2021 09:28:36 - INFO - __main__ - Step 111723: {'lr': 7.808337221172729e-05, 'samples': 21450816, 'steps': 111722, 'loss/train': 1.344404697418213} 08/31/2021 09:28:37 - INFO - __main__ - Step 111724: {'lr': 7.807951941237168e-05, 'samples': 21451008, 'steps': 111723, 'loss/train': 1.1268757581710815} 08/31/2021 09:28:38 - INFO - __main__ - Step 111725: {'lr': 7.807566669048078e-05, 'samples': 21451200, 'steps': 111724, 'loss/train': 1.1869679689407349} 08/31/2021 09:28:39 - INFO - __main__ - Step 111726: {'lr': 7.807181404605634e-05, 'samples': 21451392, 'steps': 111725, 'loss/train': 1.3978474140167236} 08/31/2021 09:28:39 - INFO - __main__ - Step 111727: {'lr': 7.806796147910005e-05, 'samples': 21451584, 'steps': 111726, 'loss/train': 1.3957046270370483} 08/31/2021 09:28:39 - INFO - __main__ - Step 111728: {'lr': 7.806410898961372e-05, 'samples': 21451776, 'steps': 111727, 'loss/train': 1.2468762397766113} 08/31/2021 09:28:40 - INFO - __main__ - Step 111729: {'lr': 7.806025657759905e-05, 'samples': 21451968, 'steps': 111728, 'loss/train': 1.239851713180542} 08/31/2021 09:28:41 - INFO - __main__ - Step 111730: {'lr': 7.805640424305777e-05, 'samples': 21452160, 'steps': 111729, 'loss/train': 0.8657286167144775} 08/31/2021 09:28:42 - INFO - __main__ - Step 111731: {'lr': 7.805255198599171e-05, 'samples': 21452352, 'steps': 111730, 'loss/train': 0.5525750517845154} 08/31/2021 09:28:42 - INFO - __main__ - Step 111732: {'lr': 7.804869980640242e-05, 'samples': 21452544, 'steps': 111731, 'loss/train': 0.5941300392150879} 08/31/2021 09:28:43 - INFO - __main__ - Step 111733: {'lr': 7.804484770429174e-05, 'samples': 21452736, 'steps': 111732, 'loss/train': 1.7663832902908325} 08/31/2021 09:28:43 - INFO - __main__ - Step 111734: {'lr': 7.804099567966139e-05, 'samples': 21452928, 'steps': 111733, 'loss/train': 1.0348461866378784} 08/31/2021 09:28:44 - INFO - __main__ - Step 111735: {'lr': 7.803714373251311e-05, 'samples': 21453120, 'steps': 111734, 'loss/train': 1.2026740312576294} 08/31/2021 09:28:45 - INFO - __main__ - Step 111736: {'lr': 7.803329186284866e-05, 'samples': 21453312, 'steps': 111735, 'loss/train': 0.4220743179321289} 08/31/2021 09:28:45 - INFO - __main__ - Step 111737: {'lr': 7.802944007066973e-05, 'samples': 21453504, 'steps': 111736, 'loss/train': 0.481901615858078} 08/31/2021 09:28:46 - INFO - __main__ - Step 111738: {'lr': 7.802558835597809e-05, 'samples': 21453696, 'steps': 111737, 'loss/train': 0.757037341594696} 08/31/2021 09:28:46 - INFO - __main__ - Step 111739: {'lr': 7.802173671877547e-05, 'samples': 21453888, 'steps': 111738, 'loss/train': 0.5212938189506531} 08/31/2021 09:28:46 - INFO - __main__ - Step 111740: {'lr': 7.801788515906361e-05, 'samples': 21454080, 'steps': 111739, 'loss/train': 0.6212774515151978} 08/31/2021 09:28:48 - INFO - __main__ - Step 111741: {'lr': 7.801403367684423e-05, 'samples': 21454272, 'steps': 111740, 'loss/train': 1.184064507484436} 08/31/2021 09:28:48 - INFO - __main__ - Step 111742: {'lr': 7.801018227211906e-05, 'samples': 21454464, 'steps': 111741, 'loss/train': 1.3710927963256836} 08/31/2021 09:28:49 - INFO - __main__ - Step 111743: {'lr': 7.800633094488987e-05, 'samples': 21454656, 'steps': 111742, 'loss/train': 0.6928755640983582} 08/31/2021 09:28:49 - INFO - __main__ - Step 111744: {'lr': 7.800247969515845e-05, 'samples': 21454848, 'steps': 111743, 'loss/train': 1.4100008010864258} 08/31/2021 09:28:49 - INFO - __main__ - Step 111745: {'lr': 7.799862852292635e-05, 'samples': 21455040, 'steps': 111744, 'loss/train': 1.2637218236923218} 08/31/2021 09:28:51 - INFO - __main__ - Step 111746: {'lr': 7.799477742819544e-05, 'samples': 21455232, 'steps': 111745, 'loss/train': 0.9007744789123535} 08/31/2021 09:28:52 - INFO - __main__ - Step 111747: {'lr': 7.799092641096742e-05, 'samples': 21455424, 'steps': 111746, 'loss/train': 1.5552600622177124} 08/31/2021 09:28:52 - INFO - __main__ - Step 111748: {'lr': 7.798707547124404e-05, 'samples': 21455616, 'steps': 111747, 'loss/train': 1.1003007888793945} 08/31/2021 09:28:53 - INFO - __main__ - Step 111749: {'lr': 7.798322460902704e-05, 'samples': 21455808, 'steps': 111748, 'loss/train': 1.0657707452774048} 08/31/2021 09:28:53 - INFO - __main__ - Step 111750: {'lr': 7.797937382431813e-05, 'samples': 21456000, 'steps': 111749, 'loss/train': 0.6661512851715088} 08/31/2021 09:28:55 - INFO - __main__ - Step 111751: {'lr': 7.797552311711905e-05, 'samples': 21456192, 'steps': 111750, 'loss/train': 1.0951286554336548} 08/31/2021 09:28:55 - INFO - __main__ - Step 111752: {'lr': 7.797167248743156e-05, 'samples': 21456384, 'steps': 111751, 'loss/train': 0.04865611344575882} 08/31/2021 09:28:56 - INFO - __main__ - Step 111753: {'lr': 7.79678219352574e-05, 'samples': 21456576, 'steps': 111752, 'loss/train': 0.9466403722763062} 08/31/2021 09:28:56 - INFO - __main__ - Step 111754: {'lr': 7.796397146059824e-05, 'samples': 21456768, 'steps': 111753, 'loss/train': 0.9018469452857971} 08/31/2021 09:28:56 - INFO - __main__ - Step 111755: {'lr': 7.796012106345587e-05, 'samples': 21456960, 'steps': 111754, 'loss/train': 0.9649187922477722} 08/31/2021 09:28:58 - INFO - __main__ - Step 111756: {'lr': 7.795627074383204e-05, 'samples': 21457152, 'steps': 111755, 'loss/train': 1.2770631313323975} 08/31/2021 09:28:58 - INFO - __main__ - Step 111757: {'lr': 7.795242050172844e-05, 'samples': 21457344, 'steps': 111756, 'loss/train': 1.071792721748352} 08/31/2021 09:28:59 - INFO - __main__ - Step 111758: {'lr': 7.794857033714691e-05, 'samples': 21457536, 'steps': 111757, 'loss/train': 0.38126978278160095} 08/31/2021 09:28:59 - INFO - __main__ - Step 111759: {'lr': 7.794472025008903e-05, 'samples': 21457728, 'steps': 111758, 'loss/train': 0.8680126070976257} 08/31/2021 09:28:59 - INFO - __main__ - Step 111760: {'lr': 7.79408702405566e-05, 'samples': 21457920, 'steps': 111759, 'loss/train': 1.1227372884750366} 08/31/2021 09:29:01 - INFO - __main__ - Step 111761: {'lr': 7.793702030855135e-05, 'samples': 21458112, 'steps': 111760, 'loss/train': 0.907931923866272} 08/31/2021 09:29:01 - INFO - __main__ - Step 111762: {'lr': 7.793317045407502e-05, 'samples': 21458304, 'steps': 111761, 'loss/train': 0.9774662852287292} 08/31/2021 09:29:02 - INFO - __main__ - Step 111763: {'lr': 7.792932067712935e-05, 'samples': 21458496, 'steps': 111762, 'loss/train': 0.21918879449367523} 08/31/2021 09:29:02 - INFO - __main__ - Step 111764: {'lr': 7.792547097771608e-05, 'samples': 21458688, 'steps': 111763, 'loss/train': 0.5314878821372986} 08/31/2021 09:29:02 - INFO - __main__ - Step 111765: {'lr': 7.792162135583694e-05, 'samples': 21458880, 'steps': 111764, 'loss/train': 1.6079224348068237} 08/31/2021 09:29:04 - INFO - __main__ - Step 111766: {'lr': 7.791777181149364e-05, 'samples': 21459072, 'steps': 111765, 'loss/train': 0.3117159307003021} 08/31/2021 09:29:04 - INFO - __main__ - Step 111767: {'lr': 7.791392234468797e-05, 'samples': 21459264, 'steps': 111766, 'loss/train': 2.068546772003174} 08/31/2021 09:29:05 - INFO - __main__ - Step 111768: {'lr': 7.79100729554216e-05, 'samples': 21459456, 'steps': 111767, 'loss/train': 0.7601395845413208} 08/31/2021 09:29:05 - INFO - __main__ - Step 111769: {'lr': 7.790622364369632e-05, 'samples': 21459648, 'steps': 111768, 'loss/train': 1.7472506761550903} 08/31/2021 09:29:05 - INFO - __main__ - Step 111770: {'lr': 7.790237440951389e-05, 'samples': 21459840, 'steps': 111769, 'loss/train': 1.847180724143982} 08/31/2021 09:29:06 - INFO - __main__ - Step 111771: {'lr': 7.789852525287593e-05, 'samples': 21460032, 'steps': 111770, 'loss/train': 1.333880066871643} 08/31/2021 09:29:07 - INFO - __main__ - Step 111772: {'lr': 7.789467617378426e-05, 'samples': 21460224, 'steps': 111771, 'loss/train': 0.3389798700809479} 08/31/2021 09:29:08 - INFO - __main__ - Step 111773: {'lr': 7.789082717224058e-05, 'samples': 21460416, 'steps': 111772, 'loss/train': 0.1449223756790161} 08/31/2021 09:29:08 - INFO - __main__ - Step 111774: {'lr': 7.788697824824664e-05, 'samples': 21460608, 'steps': 111773, 'loss/train': 1.0085718631744385} 08/31/2021 09:29:08 - INFO - __main__ - Step 111775: {'lr': 7.788312940180417e-05, 'samples': 21460800, 'steps': 111774, 'loss/train': 0.4873644709587097} 08/31/2021 09:29:09 - INFO - __main__ - Step 111776: {'lr': 7.787928063291489e-05, 'samples': 21460992, 'steps': 111775, 'loss/train': 0.8277747631072998} 08/31/2021 09:29:10 - INFO - __main__ - Step 111777: {'lr': 7.787543194158056e-05, 'samples': 21461184, 'steps': 111776, 'loss/train': 1.2926783561706543} 08/31/2021 09:29:11 - INFO - __main__ - Step 111778: {'lr': 7.787158332780292e-05, 'samples': 21461376, 'steps': 111777, 'loss/train': 0.4515841007232666} 08/31/2021 09:29:11 - INFO - __main__ - Step 111779: {'lr': 7.786773479158365e-05, 'samples': 21461568, 'steps': 111778, 'loss/train': 0.06952421367168427} 08/31/2021 09:29:11 - INFO - __main__ - Step 111780: {'lr': 7.786388633292457e-05, 'samples': 21461760, 'steps': 111779, 'loss/train': 1.5634260177612305} 08/31/2021 09:29:12 - INFO - __main__ - Step 111781: {'lr': 7.786003795182742e-05, 'samples': 21461952, 'steps': 111780, 'loss/train': 0.8082244992256165} 08/31/2021 09:29:13 - INFO - __main__ - Step 111782: {'lr': 7.78561896482938e-05, 'samples': 21462144, 'steps': 111781, 'loss/train': 1.0739027261734009} 08/31/2021 09:29:14 - INFO - __main__ - Step 111783: {'lr': 7.785234142232552e-05, 'samples': 21462336, 'steps': 111782, 'loss/train': 1.5638123750686646} 08/31/2021 09:29:14 - INFO - __main__ - Step 111784: {'lr': 7.784849327392432e-05, 'samples': 21462528, 'steps': 111783, 'loss/train': 1.1320445537567139} 08/31/2021 09:29:14 - INFO - __main__ - Step 111785: {'lr': 7.784464520309196e-05, 'samples': 21462720, 'steps': 111784, 'loss/train': 1.6108225584030151} 08/31/2021 09:29:15 - INFO - __main__ - Step 111786: {'lr': 7.784079720983012e-05, 'samples': 21462912, 'steps': 111785, 'loss/train': 1.4636001586914062} 08/31/2021 09:29:16 - INFO - __main__ - Step 111787: {'lr': 7.783694929414056e-05, 'samples': 21463104, 'steps': 111786, 'loss/train': 1.1733205318450928} 08/31/2021 09:29:17 - INFO - __main__ - Step 111788: {'lr': 7.783310145602502e-05, 'samples': 21463296, 'steps': 111787, 'loss/train': 0.291143000125885} 08/31/2021 09:29:17 - INFO - __main__ - Step 111789: {'lr': 7.782925369548524e-05, 'samples': 21463488, 'steps': 111788, 'loss/train': 2.0422861576080322} 08/31/2021 09:29:17 - INFO - __main__ - Step 111790: {'lr': 7.782540601252291e-05, 'samples': 21463680, 'steps': 111789, 'loss/train': 1.3117767572402954} 08/31/2021 09:29:18 - INFO - __main__ - Step 111791: {'lr': 7.782155840713984e-05, 'samples': 21463872, 'steps': 111790, 'loss/train': 1.196563482284546} 08/31/2021 09:29:19 - INFO - __main__ - Step 111792: {'lr': 7.781771087933775e-05, 'samples': 21464064, 'steps': 111791, 'loss/train': 1.277603268623352} 08/31/2021 09:29:20 - INFO - __main__ - Step 111793: {'lr': 7.78138634291183e-05, 'samples': 21464256, 'steps': 111792, 'loss/train': 0.7290289402008057} 08/31/2021 09:29:20 - INFO - __main__ - Step 111794: {'lr': 7.781001605648324e-05, 'samples': 21464448, 'steps': 111793, 'loss/train': 1.0437105894088745} 08/31/2021 09:29:20 - INFO - __main__ - Step 111795: {'lr': 7.780616876143435e-05, 'samples': 21464640, 'steps': 111794, 'loss/train': 0.8828873634338379} 08/31/2021 09:29:21 - INFO - __main__ - Step 111796: {'lr': 7.780232154397334e-05, 'samples': 21464832, 'steps': 111795, 'loss/train': 1.2405915260314941} 08/31/2021 09:29:23 - INFO - __main__ - Step 111797: {'lr': 7.779847440410196e-05, 'samples': 21465024, 'steps': 111796, 'loss/train': 1.0824816226959229} 08/31/2021 09:29:23 - INFO - __main__ - Step 111798: {'lr': 7.779462734182188e-05, 'samples': 21465216, 'steps': 111797, 'loss/train': 1.2698085308074951} 08/31/2021 09:29:24 - INFO - __main__ - Step 111799: {'lr': 7.779078035713493e-05, 'samples': 21465408, 'steps': 111798, 'loss/train': 1.260661005973816} 08/31/2021 09:29:24 - INFO - __main__ - Step 111800: {'lr': 7.778693345004278e-05, 'samples': 21465600, 'steps': 111799, 'loss/train': 0.894312858581543} 08/31/2021 09:29:24 - INFO - __main__ - Step 111801: {'lr': 7.77830866205472e-05, 'samples': 21465792, 'steps': 111800, 'loss/train': 1.2708120346069336} 08/31/2021 09:29:26 - INFO - __main__ - Step 111802: {'lr': 7.777923986864987e-05, 'samples': 21465984, 'steps': 111801, 'loss/train': 1.155936598777771} 08/31/2021 09:29:27 - INFO - __main__ - Step 111803: {'lr': 7.777539319435267e-05, 'samples': 21466176, 'steps': 111802, 'loss/train': 0.8017951250076294} 08/31/2021 09:29:27 - INFO - __main__ - Step 111804: {'lr': 7.777154659765712e-05, 'samples': 21466368, 'steps': 111803, 'loss/train': 1.2603121995925903} 08/31/2021 09:29:27 - INFO - __main__ - Step 111805: {'lr': 7.776770007856504e-05, 'samples': 21466560, 'steps': 111804, 'loss/train': 1.1271650791168213} 08/31/2021 09:29:28 - INFO - __main__ - Step 111806: {'lr': 7.776385363707821e-05, 'samples': 21466752, 'steps': 111805, 'loss/train': 1.247928261756897} 08/31/2021 09:29:28 - INFO - __main__ - Step 111807: {'lr': 7.776000727319832e-05, 'samples': 21466944, 'steps': 111806, 'loss/train': 1.2212759256362915} 08/31/2021 09:29:30 - INFO - __main__ - Step 111808: {'lr': 7.775616098692708e-05, 'samples': 21467136, 'steps': 111807, 'loss/train': 0.8476658463478088} 08/31/2021 09:29:30 - INFO - __main__ - Step 111809: {'lr': 7.77523147782663e-05, 'samples': 21467328, 'steps': 111808, 'loss/train': 1.2662475109100342} 08/31/2021 09:29:30 - INFO - __main__ - Step 111810: {'lr': 7.774846864721766e-05, 'samples': 21467520, 'steps': 111809, 'loss/train': 1.2254621982574463} 08/31/2021 09:29:31 - INFO - __main__ - Step 111811: {'lr': 7.77446225937829e-05, 'samples': 21467712, 'steps': 111810, 'loss/train': 1.138897180557251} 08/31/2021 09:29:31 - INFO - __main__ - Step 111812: {'lr': 7.774077661796374e-05, 'samples': 21467904, 'steps': 111811, 'loss/train': 1.2915269136428833} 08/31/2021 09:29:33 - INFO - __main__ - Step 111813: {'lr': 7.773693071976192e-05, 'samples': 21468096, 'steps': 111812, 'loss/train': 1.1185208559036255} 08/31/2021 09:29:34 - INFO - __main__ - Step 111814: {'lr': 7.773308489917929e-05, 'samples': 21468288, 'steps': 111813, 'loss/train': 0.9137244820594788} 08/31/2021 09:29:34 - INFO - __main__ - Step 111815: {'lr': 7.772923915621737e-05, 'samples': 21468480, 'steps': 111814, 'loss/train': 0.4215182960033417} 08/31/2021 09:29:35 - INFO - __main__ - Step 111816: {'lr': 7.772539349087802e-05, 'samples': 21468672, 'steps': 111815, 'loss/train': 1.291214942932129} 08/31/2021 09:29:35 - INFO - __main__ - Step 111817: {'lr': 7.772154790316294e-05, 'samples': 21468864, 'steps': 111816, 'loss/train': 1.3363577127456665} 08/31/2021 09:29:35 - INFO - __main__ - Step 111818: {'lr': 7.771770239307388e-05, 'samples': 21469056, 'steps': 111817, 'loss/train': 0.6962926983833313} 08/31/2021 09:29:37 - INFO - __main__ - Step 111819: {'lr': 7.771385696061253e-05, 'samples': 21469248, 'steps': 111818, 'loss/train': 0.7166504859924316} 08/31/2021 09:29:38 - INFO - __main__ - Step 111820: {'lr': 7.77100116057807e-05, 'samples': 21469440, 'steps': 111819, 'loss/train': 0.8132814764976501} 08/31/2021 09:29:38 - INFO - __main__ - Step 111821: {'lr': 7.770616632858005e-05, 'samples': 21469632, 'steps': 111820, 'loss/train': 0.7922999858856201} 08/31/2021 09:29:38 - INFO - __main__ - Step 111822: {'lr': 7.770232112901235e-05, 'samples': 21469824, 'steps': 111821, 'loss/train': 0.935395359992981} 08/31/2021 09:29:39 - INFO - __main__ - Step 111823: {'lr': 7.769847600707936e-05, 'samples': 21470016, 'steps': 111822, 'loss/train': 0.7763007879257202} 08/31/2021 09:29:39 - INFO - __main__ - Step 111824: {'lr': 7.769463096278273e-05, 'samples': 21470208, 'steps': 111823, 'loss/train': 0.01642918586730957} 08/31/2021 09:29:41 - INFO - __main__ - Step 111825: {'lr': 7.769078599612433e-05, 'samples': 21470400, 'steps': 111824, 'loss/train': 0.19869142770767212} 08/31/2021 09:29:41 - INFO - __main__ - Step 111826: {'lr': 7.768694110710575e-05, 'samples': 21470592, 'steps': 111825, 'loss/train': 0.7976894378662109} 08/31/2021 09:29:42 - INFO - __main__ - Step 111827: {'lr': 7.768309629572875e-05, 'samples': 21470784, 'steps': 111826, 'loss/train': 0.1494905948638916} 08/31/2021 09:29:42 - INFO - __main__ - Step 111828: {'lr': 7.76792515619951e-05, 'samples': 21470976, 'steps': 111827, 'loss/train': 1.4350337982177734} 08/31/2021 09:29:42 - INFO - __main__ - Step 111829: {'lr': 7.767540690590652e-05, 'samples': 21471168, 'steps': 111828, 'loss/train': 1.027275800704956} 08/31/2021 09:29:43 - INFO - __main__ - Step 111830: {'lr': 7.767156232746473e-05, 'samples': 21471360, 'steps': 111829, 'loss/train': 1.0360339879989624} 08/31/2021 09:29:44 - INFO - __main__ - Step 111831: {'lr': 7.766771782667148e-05, 'samples': 21471552, 'steps': 111830, 'loss/train': 1.0379976034164429} 08/31/2021 09:29:45 - INFO - __main__ - Step 111832: {'lr': 7.766387340352852e-05, 'samples': 21471744, 'steps': 111831, 'loss/train': 0.3638610541820526} 08/31/2021 09:29:45 - INFO - __main__ - Step 111833: {'lr': 7.766002905803751e-05, 'samples': 21471936, 'steps': 111832, 'loss/train': 1.5363545417785645} 08/31/2021 09:29:45 - INFO - __main__ - Step 111834: {'lr': 7.765618479020026e-05, 'samples': 21472128, 'steps': 111833, 'loss/train': 1.0524685382843018} 08/31/2021 09:29:46 - INFO - __main__ - Step 111835: {'lr': 7.76523406000185e-05, 'samples': 21472320, 'steps': 111834, 'loss/train': 0.8551337122917175} 08/31/2021 09:29:46 - INFO - __main__ - Step 111836: {'lr': 7.76484964874939e-05, 'samples': 21472512, 'steps': 111835, 'loss/train': 1.7108681201934814} 08/31/2021 09:29:48 - INFO - __main__ - Step 111837: {'lr': 7.764465245262822e-05, 'samples': 21472704, 'steps': 111836, 'loss/train': 1.1472078561782837} 08/31/2021 09:29:49 - INFO - __main__ - Step 111838: {'lr': 7.764080849542323e-05, 'samples': 21472896, 'steps': 111837, 'loss/train': 0.705570638179779} 08/31/2021 09:29:49 - INFO - __main__ - Step 111839: {'lr': 7.763696461588069e-05, 'samples': 21473088, 'steps': 111838, 'loss/train': 1.4446824789047241} 08/31/2021 09:29:50 - INFO - __main__ - Step 111840: {'lr': 7.76331208140022e-05, 'samples': 21473280, 'steps': 111839, 'loss/train': 0.6183574795722961} 08/31/2021 09:29:50 - INFO - __main__ - Step 111841: {'lr': 7.762927708978959e-05, 'samples': 21473472, 'steps': 111840, 'loss/train': 1.7626250982284546} 08/31/2021 09:29:50 - INFO - __main__ - Step 111842: {'lr': 7.762543344324454e-05, 'samples': 21473664, 'steps': 111841, 'loss/train': 1.7488899230957031} 08/31/2021 09:29:52 - INFO - __main__ - Step 111843: {'lr': 7.762158987436881e-05, 'samples': 21473856, 'steps': 111842, 'loss/train': 0.15109825134277344} 08/31/2021 09:29:52 - INFO - __main__ - Step 111844: {'lr': 7.761774638316416e-05, 'samples': 21474048, 'steps': 111843, 'loss/train': 1.4509313106536865} 08/31/2021 09:29:53 - INFO - __main__ - Step 111845: {'lr': 7.761390296963224e-05, 'samples': 21474240, 'steps': 111844, 'loss/train': 0.8161315321922302} 08/31/2021 09:29:53 - INFO - __main__ - Step 111846: {'lr': 7.761005963377487e-05, 'samples': 21474432, 'steps': 111845, 'loss/train': 1.509169578552246} 08/31/2021 09:29:53 - INFO - __main__ - Step 111847: {'lr': 7.760621637559375e-05, 'samples': 21474624, 'steps': 111846, 'loss/train': 0.9664647579193115} 08/31/2021 09:29:55 - INFO - __main__ - Step 111848: {'lr': 7.760237319509061e-05, 'samples': 21474816, 'steps': 111847, 'loss/train': 1.4279507398605347} 08/31/2021 09:29:55 - INFO - __main__ - Step 111849: {'lr': 7.759853009226717e-05, 'samples': 21475008, 'steps': 111848, 'loss/train': 1.2648037672042847} 08/31/2021 09:29:56 - INFO - __main__ - Step 111850: {'lr': 7.759468706712519e-05, 'samples': 21475200, 'steps': 111849, 'loss/train': 1.45363187789917} 08/31/2021 09:29:56 - INFO - __main__ - Step 111851: {'lr': 7.759084411966636e-05, 'samples': 21475392, 'steps': 111850, 'loss/train': 0.8676339983940125} 08/31/2021 09:29:56 - INFO - __main__ - Step 111852: {'lr': 7.758700124989254e-05, 'samples': 21475584, 'steps': 111851, 'loss/train': 1.298679232597351} 08/31/2021 09:29:58 - INFO - __main__ - Step 111853: {'lr': 7.758315845780526e-05, 'samples': 21475776, 'steps': 111852, 'loss/train': 0.6308801770210266} 08/31/2021 09:29:58 - INFO - __main__ - Step 111854: {'lr': 7.757931574340635e-05, 'samples': 21475968, 'steps': 111853, 'loss/train': 0.5953100323677063} 08/31/2021 09:29:58 - INFO - __main__ - Step 111855: {'lr': 7.757547310669752e-05, 'samples': 21476160, 'steps': 111854, 'loss/train': 0.8057841658592224} 08/31/2021 09:29:59 - INFO - __main__ - Step 111856: {'lr': 7.757163054768055e-05, 'samples': 21476352, 'steps': 111855, 'loss/train': 0.4785560071468353} 08/31/2021 09:29:59 - INFO - __main__ - Step 111857: {'lr': 7.756778806635714e-05, 'samples': 21476544, 'steps': 111856, 'loss/train': 1.273266315460205} 08/31/2021 09:29:59 - INFO - __main__ - Step 111858: {'lr': 7.756394566272901e-05, 'samples': 21476736, 'steps': 111857, 'loss/train': 1.1424421072006226} 08/31/2021 09:30:01 - INFO - __main__ - Step 111859: {'lr': 7.756010333679791e-05, 'samples': 21476928, 'steps': 111858, 'loss/train': 1.1316190958023071} 08/31/2021 09:30:02 - INFO - __main__ - Step 111860: {'lr': 7.755626108856556e-05, 'samples': 21477120, 'steps': 111859, 'loss/train': 1.0566596984863281} 08/31/2021 09:30:02 - INFO - __main__ - Step 111861: {'lr': 7.755241891803372e-05, 'samples': 21477312, 'steps': 111860, 'loss/train': 0.7879273891448975} 08/31/2021 09:30:03 - INFO - __main__ - Step 111862: {'lr': 7.754857682520408e-05, 'samples': 21477504, 'steps': 111861, 'loss/train': 1.645992636680603} 08/31/2021 09:30:03 - INFO - __main__ - Step 111863: {'lr': 7.75447348100784e-05, 'samples': 21477696, 'steps': 111862, 'loss/train': 0.5610571503639221} 08/31/2021 09:30:05 - INFO - __main__ - Step 111864: {'lr': 7.75408928726584e-05, 'samples': 21477888, 'steps': 111863, 'loss/train': 1.1890580654144287} 08/31/2021 09:30:05 - INFO - __main__ - Step 111865: {'lr': 7.753705101294589e-05, 'samples': 21478080, 'steps': 111864, 'loss/train': 1.3619247674942017} 08/31/2021 09:30:05 - INFO - __main__ - Step 111866: {'lr': 7.753320923094246e-05, 'samples': 21478272, 'steps': 111865, 'loss/train': 1.0246334075927734} 08/31/2021 09:30:06 - INFO - __main__ - Step 111867: {'lr': 7.752936752664988e-05, 'samples': 21478464, 'steps': 111866, 'loss/train': 0.38231414556503296} 08/31/2021 09:30:06 - INFO - __main__ - Step 111868: {'lr': 7.75255259000699e-05, 'samples': 21478656, 'steps': 111867, 'loss/train': 1.2049400806427002} 08/31/2021 09:30:08 - INFO - __main__ - Step 111869: {'lr': 7.752168435120426e-05, 'samples': 21478848, 'steps': 111868, 'loss/train': 0.9874480962753296} 08/31/2021 09:30:08 - INFO - __main__ - Step 111870: {'lr': 7.75178428800547e-05, 'samples': 21479040, 'steps': 111869, 'loss/train': 1.6603254079818726} 08/31/2021 09:30:08 - INFO - __main__ - Step 111871: {'lr': 7.751400148662293e-05, 'samples': 21479232, 'steps': 111870, 'loss/train': 1.4420794248580933} 08/31/2021 09:30:09 - INFO - __main__ - Step 111872: {'lr': 7.75101601709107e-05, 'samples': 21479424, 'steps': 111871, 'loss/train': 1.2624455690383911} 08/31/2021 09:30:09 - INFO - __main__ - Step 111873: {'lr': 7.750631893291973e-05, 'samples': 21479616, 'steps': 111872, 'loss/train': 1.0092253684997559} 08/31/2021 09:30:11 - INFO - __main__ - Step 111874: {'lr': 7.750247777265177e-05, 'samples': 21479808, 'steps': 111873, 'loss/train': 1.6366108655929565} 08/31/2021 09:30:11 - INFO - __main__ - Step 111875: {'lr': 7.749863669010848e-05, 'samples': 21480000, 'steps': 111874, 'loss/train': 1.1232856512069702} 08/31/2021 09:30:11 - INFO - __main__ - Step 111876: {'lr': 7.749479568529169e-05, 'samples': 21480192, 'steps': 111875, 'loss/train': 1.6506760120391846} 08/31/2021 09:30:12 - INFO - __main__ - Step 111877: {'lr': 7.749095475820306e-05, 'samples': 21480384, 'steps': 111876, 'loss/train': 1.11231529712677} 08/31/2021 09:30:12 - INFO - __main__ - Step 111878: {'lr': 7.748711390884434e-05, 'samples': 21480576, 'steps': 111877, 'loss/train': 1.6548640727996826} 08/31/2021 09:30:14 - INFO - __main__ - Step 111879: {'lr': 7.748327313721737e-05, 'samples': 21480768, 'steps': 111878, 'loss/train': 0.5754362940788269} 08/31/2021 09:30:14 - INFO - __main__ - Step 111880: {'lr': 7.747943244332367e-05, 'samples': 21480960, 'steps': 111879, 'loss/train': 0.8320377469062805} 08/31/2021 09:30:14 - INFO - __main__ - Step 111881: {'lr': 7.747559182716507e-05, 'samples': 21481152, 'steps': 111880, 'loss/train': 0.9363770484924316} 08/31/2021 09:30:15 - INFO - __main__ - Step 111882: {'lr': 7.747175128874331e-05, 'samples': 21481344, 'steps': 111881, 'loss/train': 0.645493745803833} 08/31/2021 09:30:15 - INFO - __main__ - Step 111883: {'lr': 7.746791082806015e-05, 'samples': 21481536, 'steps': 111882, 'loss/train': 1.1121137142181396} 08/31/2021 09:30:17 - INFO - __main__ - Step 111884: {'lr': 7.746407044511724e-05, 'samples': 21481728, 'steps': 111883, 'loss/train': 0.7622596025466919} 08/31/2021 09:30:17 - INFO - __main__ - Step 111885: {'lr': 7.746023013991641e-05, 'samples': 21481920, 'steps': 111884, 'loss/train': 1.2145068645477295} 08/31/2021 09:30:17 - INFO - __main__ - Step 111886: {'lr': 7.745638991245929e-05, 'samples': 21482112, 'steps': 111885, 'loss/train': 1.586756706237793} 08/31/2021 09:30:18 - INFO - __main__ - Step 111887: {'lr': 7.745254976274769e-05, 'samples': 21482304, 'steps': 111886, 'loss/train': 0.6714014410972595} 08/31/2021 09:30:18 - INFO - __main__ - Step 111888: {'lr': 7.744870969078327e-05, 'samples': 21482496, 'steps': 111887, 'loss/train': 1.7209124565124512} 08/31/2021 09:30:19 - INFO - __main__ - Step 111889: {'lr': 7.744486969656783e-05, 'samples': 21482688, 'steps': 111888, 'loss/train': 1.589383840560913} 08/31/2021 09:30:20 - INFO - __main__ - Step 111890: {'lr': 7.744102978010306e-05, 'samples': 21482880, 'steps': 111889, 'loss/train': 1.1622766256332397} 08/31/2021 09:30:20 - INFO - __main__ - Step 111891: {'lr': 7.743718994139071e-05, 'samples': 21483072, 'steps': 111890, 'loss/train': 1.240847110748291} 08/31/2021 09:30:21 - INFO - __main__ - Step 111892: {'lr': 7.743335018043257e-05, 'samples': 21483264, 'steps': 111891, 'loss/train': 0.941182553768158} 08/31/2021 09:30:21 - INFO - __main__ - Step 111893: {'lr': 7.742951049723022e-05, 'samples': 21483456, 'steps': 111892, 'loss/train': 1.0018384456634521} 08/31/2021 09:30:23 - INFO - __main__ - Step 111894: {'lr': 7.742567089178546e-05, 'samples': 21483648, 'steps': 111893, 'loss/train': 0.7075274586677551} 08/31/2021 09:30:23 - INFO - __main__ - Step 111895: {'lr': 7.742183136410006e-05, 'samples': 21483840, 'steps': 111894, 'loss/train': 0.5967100262641907} 08/31/2021 09:30:24 - INFO - __main__ - Step 111896: {'lr': 7.741799191417567e-05, 'samples': 21484032, 'steps': 111895, 'loss/train': 1.333358883857727} 08/31/2021 09:30:24 - INFO - __main__ - Step 111897: {'lr': 7.741415254201411e-05, 'samples': 21484224, 'steps': 111896, 'loss/train': 1.4486801624298096} 08/31/2021 09:30:24 - INFO - __main__ - Step 111898: {'lr': 7.741031324761707e-05, 'samples': 21484416, 'steps': 111897, 'loss/train': 0.827577531337738} 08/31/2021 09:30:25 - INFO - __main__ - Step 111899: {'lr': 7.740647403098627e-05, 'samples': 21484608, 'steps': 111898, 'loss/train': 1.3465956449508667} 08/31/2021 09:30:26 - INFO - __main__ - Step 111900: {'lr': 7.740263489212343e-05, 'samples': 21484800, 'steps': 111899, 'loss/train': 1.3958417177200317} 08/31/2021 09:30:27 - INFO - __main__ - Step 111901: {'lr': 7.739879583103033e-05, 'samples': 21484992, 'steps': 111900, 'loss/train': 0.6455076336860657} 08/31/2021 09:30:27 - INFO - __main__ - Step 111902: {'lr': 7.739495684770864e-05, 'samples': 21485184, 'steps': 111901, 'loss/train': 1.0632292032241821} 08/31/2021 09:30:27 - INFO - __main__ - Step 111903: {'lr': 7.739111794216014e-05, 'samples': 21485376, 'steps': 111902, 'loss/train': 0.7578829526901245} 08/31/2021 09:30:28 - INFO - __main__ - Step 111904: {'lr': 7.738727911438653e-05, 'samples': 21485568, 'steps': 111903, 'loss/train': 1.0521252155303955} 08/31/2021 09:30:29 - INFO - __main__ - Step 111905: {'lr': 7.738344036438957e-05, 'samples': 21485760, 'steps': 111904, 'loss/train': 1.4578704833984375} 08/31/2021 09:30:30 - INFO - __main__ - Step 111906: {'lr': 7.737960169217104e-05, 'samples': 21485952, 'steps': 111905, 'loss/train': 1.5541534423828125} 08/31/2021 09:30:30 - INFO - __main__ - Step 111907: {'lr': 7.73757630977325e-05, 'samples': 21486144, 'steps': 111906, 'loss/train': 0.03770550340414047} 08/31/2021 09:30:30 - INFO - __main__ - Step 111908: {'lr': 7.737192458107578e-05, 'samples': 21486336, 'steps': 111907, 'loss/train': 2.0369532108306885} 08/31/2021 09:30:31 - INFO - __main__ - Step 111909: {'lr': 7.736808614220262e-05, 'samples': 21486528, 'steps': 111908, 'loss/train': 1.091843843460083} 08/31/2021 09:30:33 - INFO - __main__ - Step 111910: {'lr': 7.736424778111473e-05, 'samples': 21486720, 'steps': 111909, 'loss/train': 0.6897701621055603} 08/31/2021 09:30:33 - INFO - __main__ - Step 111911: {'lr': 7.736040949781384e-05, 'samples': 21486912, 'steps': 111910, 'loss/train': 0.769747257232666} 08/31/2021 09:30:34 - INFO - __main__ - Step 111912: {'lr': 7.73565712923017e-05, 'samples': 21487104, 'steps': 111911, 'loss/train': 0.5704574584960938} 08/31/2021 09:30:34 - INFO - __main__ - Step 111913: {'lr': 7.735273316457999e-05, 'samples': 21487296, 'steps': 111912, 'loss/train': 1.2932299375534058} 08/31/2021 09:30:34 - INFO - __main__ - Step 111914: {'lr': 7.734889511465051e-05, 'samples': 21487488, 'steps': 111913, 'loss/train': 1.1326279640197754} 08/31/2021 09:30:36 - INFO - __main__ - Step 111915: {'lr': 7.734505714251493e-05, 'samples': 21487680, 'steps': 111914, 'loss/train': 1.022695779800415} 08/31/2021 09:30:36 - INFO - __main__ - Step 111916: {'lr': 7.734121924817505e-05, 'samples': 21487872, 'steps': 111915, 'loss/train': 0.887206494808197} 08/31/2021 09:30:37 - INFO - __main__ - Step 111917: {'lr': 7.733738143163252e-05, 'samples': 21488064, 'steps': 111916, 'loss/train': 1.2031551599502563} 08/31/2021 09:30:37 - INFO - __main__ - Step 111918: {'lr': 7.733354369288909e-05, 'samples': 21488256, 'steps': 111917, 'loss/train': 0.9344386458396912} 08/31/2021 09:30:37 - INFO - __main__ - Step 111919: {'lr': 7.732970603194659e-05, 'samples': 21488448, 'steps': 111918, 'loss/train': 1.3265053033828735} 08/31/2021 09:30:39 - INFO - __main__ - Step 111920: {'lr': 7.73258684488066e-05, 'samples': 21488640, 'steps': 111919, 'loss/train': 0.3840174376964569} 08/31/2021 09:30:40 - INFO - __main__ - Step 111921: {'lr': 7.732203094347088e-05, 'samples': 21488832, 'steps': 111920, 'loss/train': 1.384883999824524} 08/31/2021 09:30:40 - INFO - __main__ - Step 111922: {'lr': 7.73181935159412e-05, 'samples': 21489024, 'steps': 111921, 'loss/train': 0.7186289429664612} 08/31/2021 09:30:40 - INFO - __main__ - Step 111923: {'lr': 7.731435616621926e-05, 'samples': 21489216, 'steps': 111922, 'loss/train': 1.225991129875183} 08/31/2021 09:30:41 - INFO - __main__ - Step 111924: {'lr': 7.731051889430685e-05, 'samples': 21489408, 'steps': 111923, 'loss/train': 0.04398713260889053} 08/31/2021 09:30:41 - INFO - __main__ - Step 111925: {'lr': 7.730668170020561e-05, 'samples': 21489600, 'steps': 111924, 'loss/train': 0.3468971848487854} 08/31/2021 09:30:41 - INFO - __main__ - Step 111926: {'lr': 7.730284458391734e-05, 'samples': 21489792, 'steps': 111925, 'loss/train': 0.031781155616045} 08/31/2021 09:30:43 - INFO - __main__ - Step 111927: {'lr': 7.729900754544373e-05, 'samples': 21489984, 'steps': 111926, 'loss/train': 0.015295211225748062} 08/31/2021 09:30:43 - INFO - __main__ - Step 111928: {'lr': 7.729517058478653e-05, 'samples': 21490176, 'steps': 111927, 'loss/train': 1.031494379043579} 08/31/2021 09:30:44 - INFO - __main__ - Step 111929: {'lr': 7.729133370194747e-05, 'samples': 21490368, 'steps': 111928, 'loss/train': 1.1258876323699951} 08/31/2021 09:30:44 - INFO - __main__ - Step 111930: {'lr': 7.728749689692823e-05, 'samples': 21490560, 'steps': 111929, 'loss/train': 0.6723093390464783} 08/31/2021 09:30:44 - INFO - __main__ - Step 111931: {'lr': 7.728366016973062e-05, 'samples': 21490752, 'steps': 111930, 'loss/train': 1.0881192684173584} 08/31/2021 09:30:46 - INFO - __main__ - Step 111932: {'lr': 7.727982352035631e-05, 'samples': 21490944, 'steps': 111931, 'loss/train': 1.0701446533203125} 08/31/2021 09:30:46 - INFO - __main__ - Step 111933: {'lr': 7.727598694880714e-05, 'samples': 21491136, 'steps': 111932, 'loss/train': 1.022199034690857} 08/31/2021 09:30:47 - INFO - __main__ - Step 111934: {'lr': 7.727215045508464e-05, 'samples': 21491328, 'steps': 111933, 'loss/train': 1.3164381980895996} 08/31/2021 09:30:47 - INFO - __main__ - Step 111935: {'lr': 7.726831403919068e-05, 'samples': 21491520, 'steps': 111934, 'loss/train': 1.4755175113677979} 08/31/2021 09:30:47 - INFO - __main__ - Step 111936: {'lr': 7.726447770112693e-05, 'samples': 21491712, 'steps': 111935, 'loss/train': 1.118760108947754} 08/31/2021 09:30:49 - INFO - __main__ - Step 111937: {'lr': 7.726064144089515e-05, 'samples': 21491904, 'steps': 111936, 'loss/train': 1.5614957809448242} 08/31/2021 09:30:50 - INFO - __main__ - Step 111938: {'lr': 7.725680525849704e-05, 'samples': 21492096, 'steps': 111937, 'loss/train': 1.3509591817855835} 08/31/2021 09:30:50 - INFO - __main__ - Step 111939: {'lr': 7.725296915393438e-05, 'samples': 21492288, 'steps': 111938, 'loss/train': 1.2320692539215088} 08/31/2021 09:30:50 - INFO - __main__ - Step 111940: {'lr': 7.724913312720886e-05, 'samples': 21492480, 'steps': 111939, 'loss/train': 1.5243061780929565} 08/31/2021 09:30:51 - INFO - __main__ - Step 111941: {'lr': 7.724529717832218e-05, 'samples': 21492672, 'steps': 111940, 'loss/train': 1.9532235860824585} 08/31/2021 09:30:52 - INFO - __main__ - Step 111942: {'lr': 7.724146130727614e-05, 'samples': 21492864, 'steps': 111941, 'loss/train': 1.328282356262207} 08/31/2021 09:30:53 - INFO - __main__ - Step 111943: {'lr': 7.72376255140724e-05, 'samples': 21493056, 'steps': 111942, 'loss/train': 1.7390375137329102} 08/31/2021 09:30:53 - INFO - __main__ - Step 111944: {'lr': 7.723378979871276e-05, 'samples': 21493248, 'steps': 111943, 'loss/train': 0.016722340136766434} 08/31/2021 09:30:54 - INFO - __main__ - Step 111945: {'lr': 7.722995416119888e-05, 'samples': 21493440, 'steps': 111944, 'loss/train': 0.014496573247015476} 08/31/2021 09:30:54 - INFO - __main__ - Step 111946: {'lr': 7.722611860153259e-05, 'samples': 21493632, 'steps': 111945, 'loss/train': 1.6659899950027466} 08/31/2021 09:30:54 - INFO - __main__ - Step 111947: {'lr': 7.72222831197155e-05, 'samples': 21493824, 'steps': 111946, 'loss/train': 0.6013644337654114} 08/31/2021 09:30:56 - INFO - __main__ - Step 111948: {'lr': 7.721844771574934e-05, 'samples': 21494016, 'steps': 111947, 'loss/train': 1.6357251405715942} 08/31/2021 09:30:56 - INFO - __main__ - Step 111949: {'lr': 7.721461238963589e-05, 'samples': 21494208, 'steps': 111948, 'loss/train': 1.7890841960906982} 08/31/2021 09:30:57 - INFO - __main__ - Step 111950: {'lr': 7.721077714137689e-05, 'samples': 21494400, 'steps': 111949, 'loss/train': 1.3049466609954834} 08/31/2021 09:30:57 - INFO - __main__ - Step 111951: {'lr': 7.720694197097406e-05, 'samples': 21494592, 'steps': 111950, 'loss/train': 0.03652772679924965} 08/31/2021 09:30:57 - INFO - __main__ - Step 111952: {'lr': 7.720310687842908e-05, 'samples': 21494784, 'steps': 111951, 'loss/train': 1.198053002357483} 08/31/2021 09:30:59 - INFO - __main__ - Step 111953: {'lr': 7.719927186374373e-05, 'samples': 21494976, 'steps': 111952, 'loss/train': 1.5946924686431885} 08/31/2021 09:30:59 - INFO - __main__ - Step 111954: {'lr': 7.719543692691972e-05, 'samples': 21495168, 'steps': 111953, 'loss/train': 0.9478891491889954} 08/31/2021 09:31:00 - INFO - __main__ - Step 111955: {'lr': 7.719160206795877e-05, 'samples': 21495360, 'steps': 111954, 'loss/train': 0.9139664173126221} 08/31/2021 09:31:00 - INFO - __main__ - Step 111956: {'lr': 7.718776728686263e-05, 'samples': 21495552, 'steps': 111955, 'loss/train': 1.1343700885772705} 08/31/2021 09:31:01 - INFO - __main__ - Step 111957: {'lr': 7.718393258363302e-05, 'samples': 21495744, 'steps': 111956, 'loss/train': 0.8333807587623596} 08/31/2021 09:31:01 - INFO - __main__ - Step 111958: {'lr': 7.718009795827166e-05, 'samples': 21495936, 'steps': 111957, 'loss/train': 1.4670735597610474} 08/31/2021 09:31:02 - INFO - __main__ - Step 111959: {'lr': 7.717626341078027e-05, 'samples': 21496128, 'steps': 111958, 'loss/train': 1.3597573041915894} 08/31/2021 09:31:03 - INFO - __main__ - Step 111960: {'lr': 7.717242894116067e-05, 'samples': 21496320, 'steps': 111959, 'loss/train': 1.5736968517303467} 08/31/2021 09:31:03 - INFO - __main__ - Step 111961: {'lr': 7.716859454941444e-05, 'samples': 21496512, 'steps': 111960, 'loss/train': 1.2745378017425537} 08/31/2021 09:31:04 - INFO - __main__ - Step 111962: {'lr': 7.716476023554336e-05, 'samples': 21496704, 'steps': 111961, 'loss/train': 1.3094466924667358} 08/31/2021 09:31:04 - INFO - __main__ - Step 111963: {'lr': 7.716092599954919e-05, 'samples': 21496896, 'steps': 111962, 'loss/train': 1.2398481369018555} 08/31/2021 09:31:05 - INFO - __main__ - Step 111964: {'lr': 7.715709184143363e-05, 'samples': 21497088, 'steps': 111963, 'loss/train': 1.8227965831756592} 08/31/2021 09:31:06 - INFO - __main__ - Step 111965: {'lr': 7.715325776119841e-05, 'samples': 21497280, 'steps': 111964, 'loss/train': 1.7869654893875122} 08/31/2021 09:31:06 - INFO - __main__ - Step 111966: {'lr': 7.714942375884526e-05, 'samples': 21497472, 'steps': 111965, 'loss/train': 0.9569673538208008} 08/31/2021 09:31:07 - INFO - __main__ - Step 111967: {'lr': 7.714558983437594e-05, 'samples': 21497664, 'steps': 111966, 'loss/train': 0.958106279373169} 08/31/2021 09:31:07 - INFO - __main__ - Step 111968: {'lr': 7.714175598779213e-05, 'samples': 21497856, 'steps': 111967, 'loss/train': 1.1072062253952026} 08/31/2021 09:31:09 - INFO - __main__ - Step 111969: {'lr': 7.713792221909558e-05, 'samples': 21498048, 'steps': 111968, 'loss/train': 1.1601322889328003} 08/31/2021 09:31:10 - INFO - __main__ - Step 111970: {'lr': 7.713408852828801e-05, 'samples': 21498240, 'steps': 111969, 'loss/train': 1.3553545475006104} 08/31/2021 09:31:10 - INFO - __main__ - Step 111971: {'lr': 7.713025491537115e-05, 'samples': 21498432, 'steps': 111970, 'loss/train': 1.061115026473999} 08/31/2021 09:31:10 - INFO - __main__ - Step 111972: {'lr': 7.712642138034676e-05, 'samples': 21498624, 'steps': 111971, 'loss/train': 1.2050379514694214} 08/31/2021 09:31:11 - INFO - __main__ - Step 111973: {'lr': 7.712258792321658e-05, 'samples': 21498816, 'steps': 111972, 'loss/train': 1.1319373846054077} 08/31/2021 09:31:12 - INFO - __main__ - Step 111974: {'lr': 7.711875454398223e-05, 'samples': 21499008, 'steps': 111973, 'loss/train': 0.9942500591278076} 08/31/2021 09:31:13 - INFO - __main__ - Step 111975: {'lr': 7.711492124264549e-05, 'samples': 21499200, 'steps': 111974, 'loss/train': 1.0898274183273315} 08/31/2021 09:31:13 - INFO - __main__ - Step 111976: {'lr': 7.71110880192081e-05, 'samples': 21499392, 'steps': 111975, 'loss/train': 1.3670518398284912} 08/31/2021 09:31:13 - INFO - __main__ - Step 111977: {'lr': 7.710725487367182e-05, 'samples': 21499584, 'steps': 111976, 'loss/train': 1.0451383590698242} 08/31/2021 09:31:14 - INFO - __main__ - Step 111978: {'lr': 7.71034218060383e-05, 'samples': 21499776, 'steps': 111977, 'loss/train': 1.2718117237091064} 08/31/2021 09:31:16 - INFO - __main__ - Step 111979: {'lr': 7.709958881630932e-05, 'samples': 21499968, 'steps': 111978, 'loss/train': 1.6754872798919678} 08/31/2021 09:31:16 - INFO - __main__ - Step 111980: {'lr': 7.709575590448661e-05, 'samples': 21500160, 'steps': 111979, 'loss/train': 0.07409238815307617} 08/31/2021 09:31:17 - INFO - __main__ - Step 111981: {'lr': 7.70919230705719e-05, 'samples': 21500352, 'steps': 111980, 'loss/train': 0.2735993564128876} 08/31/2021 09:31:17 - INFO - __main__ - Step 111982: {'lr': 7.708809031456688e-05, 'samples': 21500544, 'steps': 111981, 'loss/train': 0.030501345172524452} 08/31/2021 09:31:18 - INFO - __main__ - Step 111983: {'lr': 7.708425763647328e-05, 'samples': 21500736, 'steps': 111982, 'loss/train': 1.6568228006362915} 08/31/2021 09:31:19 - INFO - __main__ - Step 111984: {'lr': 7.708042503629286e-05, 'samples': 21500928, 'steps': 111983, 'loss/train': 0.6975796222686768} 08/31/2021 09:31:19 - INFO - __main__ - Step 111985: {'lr': 7.707659251402735e-05, 'samples': 21501120, 'steps': 111984, 'loss/train': 1.457301139831543} 08/31/2021 09:31:20 - INFO - __main__ - Step 111986: {'lr': 7.707276006967854e-05, 'samples': 21501312, 'steps': 111985, 'loss/train': 1.1397148370742798} 08/31/2021 09:31:20 - INFO - __main__ - Step 111987: {'lr': 7.706892770324798e-05, 'samples': 21501504, 'steps': 111986, 'loss/train': 1.324886679649353} 08/31/2021 09:31:21 - INFO - __main__ - Step 111988: {'lr': 7.706509541473747e-05, 'samples': 21501696, 'steps': 111987, 'loss/train': 1.1349718570709229} 08/31/2021 09:31:22 - INFO - __main__ - Step 111989: {'lr': 7.706126320414877e-05, 'samples': 21501888, 'steps': 111988, 'loss/train': 0.8033319711685181} 08/31/2021 09:31:23 - INFO - __main__ - Step 111990: {'lr': 7.705743107148363e-05, 'samples': 21502080, 'steps': 111989, 'loss/train': 1.2343858480453491} 08/31/2021 09:31:23 - INFO - __main__ - Step 111991: {'lr': 7.705359901674371e-05, 'samples': 21502272, 'steps': 111990, 'loss/train': 1.1334596872329712} 08/31/2021 09:31:23 - INFO - __main__ - Step 111992: {'lr': 7.70497670399308e-05, 'samples': 21502464, 'steps': 111991, 'loss/train': 0.7598161101341248} 08/31/2021 09:31:24 - INFO - __main__ - Step 111993: {'lr': 7.704593514104658e-05, 'samples': 21502656, 'steps': 111992, 'loss/train': 1.7803168296813965} 08/31/2021 09:31:24 - INFO - __main__ - Step 111994: {'lr': 7.704210332009278e-05, 'samples': 21502848, 'steps': 111993, 'loss/train': 1.4115287065505981} 08/31/2021 09:31:26 - INFO - __main__ - Step 111995: {'lr': 7.703827157707116e-05, 'samples': 21503040, 'steps': 111994, 'loss/train': 0.8387312889099121} 08/31/2021 09:31:26 - INFO - __main__ - Step 111996: {'lr': 7.703443991198342e-05, 'samples': 21503232, 'steps': 111995, 'loss/train': 0.9245702624320984} 08/31/2021 09:31:26 - INFO - __main__ - Step 111997: {'lr': 7.703060832483128e-05, 'samples': 21503424, 'steps': 111996, 'loss/train': 1.1127386093139648} 08/31/2021 09:31:27 - INFO - __main__ - Step 111998: {'lr': 7.702677681561649e-05, 'samples': 21503616, 'steps': 111997, 'loss/train': 1.0738136768341064} 08/31/2021 09:31:27 - INFO - __main__ - Step 111999: {'lr': 7.702294538434077e-05, 'samples': 21503808, 'steps': 111998, 'loss/train': 1.2411433458328247} 08/31/2021 09:31:30 - INFO - __main__ - Step 112000: {'lr': 7.70191140310059e-05, 'samples': 21504000, 'steps': 111999, 'loss/train': 1.8291101455688477} 08/31/2021 09:31:30 - INFO - __main__ - Step 112001: {'lr': 7.701528275561349e-05, 'samples': 21504192, 'steps': 112000, 'loss/train': 1.0026617050170898} 08/31/2021 09:31:30 - INFO - __main__ - Step 112002: {'lr': 7.70114515581653e-05, 'samples': 21504384, 'steps': 112001, 'loss/train': 1.716464877128601} 08/31/2021 09:31:31 - INFO - __main__ - Step 112003: {'lr': 7.700762043866311e-05, 'samples': 21504576, 'steps': 112002, 'loss/train': 0.754346489906311} 08/31/2021 09:31:31 - INFO - __main__ - Step 112004: {'lr': 7.700378939710859e-05, 'samples': 21504768, 'steps': 112003, 'loss/train': 0.7218077778816223} 08/31/2021 09:31:31 - INFO - __main__ - Step 112005: {'lr': 7.699995843350351e-05, 'samples': 21504960, 'steps': 112004, 'loss/train': 0.5415871143341064} 08/31/2021 09:31:33 - INFO - __main__ - Step 112006: {'lr': 7.699612754784957e-05, 'samples': 21505152, 'steps': 112005, 'loss/train': 0.7999387979507446} 08/31/2021 09:31:34 - INFO - __main__ - Step 112007: {'lr': 7.699229674014851e-05, 'samples': 21505344, 'steps': 112006, 'loss/train': 0.015300757251679897} 08/31/2021 09:31:34 - INFO - __main__ - Step 112008: {'lr': 7.698846601040205e-05, 'samples': 21505536, 'steps': 112007, 'loss/train': 0.7687624096870422} 08/31/2021 09:31:35 - INFO - __main__ - Step 112009: {'lr': 7.698463535861192e-05, 'samples': 21505728, 'steps': 112008, 'loss/train': 1.1806637048721313} 08/31/2021 09:31:35 - INFO - __main__ - Step 112010: {'lr': 7.698080478477984e-05, 'samples': 21505920, 'steps': 112009, 'loss/train': 0.9282587170600891} 08/31/2021 09:31:35 - INFO - __main__ - Step 112011: {'lr': 7.697697428890754e-05, 'samples': 21506112, 'steps': 112010, 'loss/train': 1.2345303297042847} 08/31/2021 09:31:37 - INFO - __main__ - Step 112012: {'lr': 7.697314387099676e-05, 'samples': 21506304, 'steps': 112011, 'loss/train': 0.28629541397094727} 08/31/2021 09:31:37 - INFO - __main__ - Step 112013: {'lr': 7.696931353104927e-05, 'samples': 21506496, 'steps': 112012, 'loss/train': 0.9794089198112488} 08/31/2021 09:31:38 - INFO - __main__ - Step 112014: {'lr': 7.696548326906668e-05, 'samples': 21506688, 'steps': 112013, 'loss/train': 1.2206757068634033} 08/31/2021 09:31:38 - INFO - __main__ - Step 112015: {'lr': 7.696165308505076e-05, 'samples': 21506880, 'steps': 112014, 'loss/train': 0.493879497051239} 08/31/2021 09:31:38 - INFO - __main__ - Step 112016: {'lr': 7.695782297900325e-05, 'samples': 21507072, 'steps': 112015, 'loss/train': 1.1698263883590698} 08/31/2021 09:31:40 - INFO - __main__ - Step 112017: {'lr': 7.695399295092586e-05, 'samples': 21507264, 'steps': 112016, 'loss/train': 1.7369258403778076} 08/31/2021 09:31:40 - INFO - __main__ - Step 112018: {'lr': 7.695016300082036e-05, 'samples': 21507456, 'steps': 112017, 'loss/train': 1.1322965621948242} 08/31/2021 09:31:40 - INFO - __main__ - Step 112019: {'lr': 7.694633312868843e-05, 'samples': 21507648, 'steps': 112018, 'loss/train': 0.4212910532951355} 08/31/2021 09:31:41 - INFO - __main__ - Step 112020: {'lr': 7.694250333453182e-05, 'samples': 21507840, 'steps': 112019, 'loss/train': 1.0399196147918701} 08/31/2021 09:31:41 - INFO - __main__ - Step 112021: {'lr': 7.693867361835222e-05, 'samples': 21508032, 'steps': 112020, 'loss/train': 1.9753862619400024} 08/31/2021 09:31:43 - INFO - __main__ - Step 112022: {'lr': 7.693484398015141e-05, 'samples': 21508224, 'steps': 112021, 'loss/train': 1.2990535497665405} 08/31/2021 09:31:44 - INFO - __main__ - Step 112023: {'lr': 7.693101441993108e-05, 'samples': 21508416, 'steps': 112022, 'loss/train': 1.316545009613037} 08/31/2021 09:31:44 - INFO - __main__ - Step 112024: {'lr': 7.692718493769296e-05, 'samples': 21508608, 'steps': 112023, 'loss/train': 0.5272313952445984} 08/31/2021 09:31:45 - INFO - __main__ - Step 112025: {'lr': 7.69233555334388e-05, 'samples': 21508800, 'steps': 112024, 'loss/train': 0.4279899001121521} 08/31/2021 09:31:45 - INFO - __main__ - Step 112026: {'lr': 7.69195262071703e-05, 'samples': 21508992, 'steps': 112025, 'loss/train': 1.578099012374878} 08/31/2021 09:31:47 - INFO - __main__ - Step 112027: {'lr': 7.691569695888925e-05, 'samples': 21509184, 'steps': 112026, 'loss/train': 0.8027669787406921} 08/31/2021 09:31:47 - INFO - __main__ - Step 112028: {'lr': 7.691186778859724e-05, 'samples': 21509376, 'steps': 112027, 'loss/train': 0.1332673728466034} 08/31/2021 09:31:48 - INFO - __main__ - Step 112029: {'lr': 7.690803869629609e-05, 'samples': 21509568, 'steps': 112028, 'loss/train': 1.7013483047485352} 08/31/2021 09:31:48 - INFO - __main__ - Step 112030: {'lr': 7.690420968198749e-05, 'samples': 21509760, 'steps': 112029, 'loss/train': 1.721070647239685} 08/31/2021 09:31:48 - INFO - __main__ - Step 112031: {'lr': 7.690038074567319e-05, 'samples': 21509952, 'steps': 112030, 'loss/train': 1.096306324005127} 08/31/2021 09:31:49 - INFO - __main__ - Step 112032: {'lr': 7.689655188735493e-05, 'samples': 21510144, 'steps': 112031, 'loss/train': 2.0546154975891113} 08/31/2021 09:31:50 - INFO - __main__ - Step 112033: {'lr': 7.689272310703438e-05, 'samples': 21510336, 'steps': 112032, 'loss/train': 1.1412969827651978} 08/31/2021 09:31:51 - INFO - __main__ - Step 112034: {'lr': 7.688889440471331e-05, 'samples': 21510528, 'steps': 112033, 'loss/train': 1.3967790603637695} 08/31/2021 09:31:51 - INFO - __main__ - Step 112035: {'lr': 7.688506578039341e-05, 'samples': 21510720, 'steps': 112034, 'loss/train': 0.8112530708312988} 08/31/2021 09:31:51 - INFO - __main__ - Step 112036: {'lr': 7.688123723407644e-05, 'samples': 21510912, 'steps': 112035, 'loss/train': 0.971332311630249} 08/31/2021 09:31:52 - INFO - __main__ - Step 112037: {'lr': 7.687740876576413e-05, 'samples': 21511104, 'steps': 112036, 'loss/train': 1.1660248041152954} 08/31/2021 09:31:53 - INFO - __main__ - Step 112038: {'lr': 7.687358037545819e-05, 'samples': 21511296, 'steps': 112037, 'loss/train': 1.0410066843032837} 08/31/2021 09:31:54 - INFO - __main__ - Step 112039: {'lr': 7.68697520631604e-05, 'samples': 21511488, 'steps': 112038, 'loss/train': 1.1368178129196167} 08/31/2021 09:31:54 - INFO - __main__ - Step 112040: {'lr': 7.686592382887236e-05, 'samples': 21511680, 'steps': 112039, 'loss/train': 0.5628045797348022} 08/31/2021 09:31:54 - INFO - __main__ - Step 112041: {'lr': 7.686209567259586e-05, 'samples': 21511872, 'steps': 112040, 'loss/train': 1.1908400058746338} 08/31/2021 09:31:55 - INFO - __main__ - Step 112042: {'lr': 7.685826759433263e-05, 'samples': 21512064, 'steps': 112041, 'loss/train': 1.2507965564727783} 08/31/2021 09:31:56 - INFO - __main__ - Step 112043: {'lr': 7.68544395940844e-05, 'samples': 21512256, 'steps': 112042, 'loss/train': 1.5866659879684448} 08/31/2021 09:31:57 - INFO - __main__ - Step 112044: {'lr': 7.685061167185287e-05, 'samples': 21512448, 'steps': 112043, 'loss/train': 1.4824272394180298} 08/31/2021 09:31:57 - INFO - __main__ - Step 112045: {'lr': 7.684678382763979e-05, 'samples': 21512640, 'steps': 112044, 'loss/train': 0.1473807990550995} 08/31/2021 09:31:57 - INFO - __main__ - Step 112046: {'lr': 7.68429560614469e-05, 'samples': 21512832, 'steps': 112045, 'loss/train': 1.0143020153045654} 08/31/2021 09:31:58 - INFO - __main__ - Step 112047: {'lr': 7.683912837327589e-05, 'samples': 21513024, 'steps': 112046, 'loss/train': 1.753610372543335} 08/31/2021 09:31:59 - INFO - __main__ - Step 112048: {'lr': 7.683530076312848e-05, 'samples': 21513216, 'steps': 112047, 'loss/train': 0.12183359265327454} 08/31/2021 09:32:00 - INFO - __main__ - Step 112049: {'lr': 7.683147323100642e-05, 'samples': 21513408, 'steps': 112048, 'loss/train': 0.9284793138504028} 08/31/2021 09:32:00 - INFO - __main__ - Step 112050: {'lr': 7.682764577691151e-05, 'samples': 21513600, 'steps': 112049, 'loss/train': 0.8519136905670166} 08/31/2021 09:32:01 - INFO - __main__ - Step 112051: {'lr': 7.68238184008453e-05, 'samples': 21513792, 'steps': 112050, 'loss/train': 0.7932215332984924} 08/31/2021 09:32:01 - INFO - __main__ - Step 112052: {'lr': 7.681999110280963e-05, 'samples': 21513984, 'steps': 112051, 'loss/train': 1.672648549079895} 08/31/2021 09:32:01 - INFO - __main__ - Step 112053: {'lr': 7.681616388280619e-05, 'samples': 21514176, 'steps': 112052, 'loss/train': 0.5665583610534668} 08/31/2021 09:32:03 - INFO - __main__ - Step 112054: {'lr': 7.681233674083668e-05, 'samples': 21514368, 'steps': 112053, 'loss/train': 0.015026930719614029} 08/31/2021 09:32:03 - INFO - __main__ - Step 112055: {'lr': 7.68085096769029e-05, 'samples': 21514560, 'steps': 112054, 'loss/train': 0.9650828242301941} 08/31/2021 09:32:04 - INFO - __main__ - Step 112056: {'lr': 7.680468269100651e-05, 'samples': 21514752, 'steps': 112055, 'loss/train': 0.9886856079101562} 08/31/2021 09:32:04 - INFO - __main__ - Step 112057: {'lr': 7.680085578314927e-05, 'samples': 21514944, 'steps': 112056, 'loss/train': 0.15080174803733826} 08/31/2021 09:32:04 - INFO - __main__ - Step 112058: {'lr': 7.679702895333287e-05, 'samples': 21515136, 'steps': 112057, 'loss/train': 0.5584570169448853} 08/31/2021 09:32:05 - INFO - __main__ - Step 112059: {'lr': 7.679320220155908e-05, 'samples': 21515328, 'steps': 112058, 'loss/train': 1.0341135263442993} 08/31/2021 09:32:06 - INFO - __main__ - Step 112060: {'lr': 7.67893755278296e-05, 'samples': 21515520, 'steps': 112059, 'loss/train': 0.8946266174316406} 08/31/2021 09:32:07 - INFO - __main__ - Step 112061: {'lr': 7.678554893214623e-05, 'samples': 21515712, 'steps': 112060, 'loss/train': 1.2694357633590698} 08/31/2021 09:32:07 - INFO - __main__ - Step 112062: {'lr': 7.678172241451053e-05, 'samples': 21515904, 'steps': 112061, 'loss/train': 0.7551612257957458} 08/31/2021 09:32:07 - INFO - __main__ - Step 112063: {'lr': 7.677789597492433e-05, 'samples': 21516096, 'steps': 112062, 'loss/train': 0.13167592883110046} 08/31/2021 09:32:08 - INFO - __main__ - Step 112064: {'lr': 7.677406961338935e-05, 'samples': 21516288, 'steps': 112063, 'loss/train': 1.349599838256836} 08/31/2021 09:32:09 - INFO - __main__ - Step 112065: {'lr': 7.677024332990726e-05, 'samples': 21516480, 'steps': 112064, 'loss/train': 1.0555392503738403} 08/31/2021 09:32:09 - INFO - __main__ - Step 112066: {'lr': 7.676641712447984e-05, 'samples': 21516672, 'steps': 112065, 'loss/train': 0.9240190386772156} 08/31/2021 09:32:10 - INFO - __main__ - Step 112067: {'lr': 7.67625909971088e-05, 'samples': 21516864, 'steps': 112066, 'loss/train': 1.124923586845398} 08/31/2021 09:32:10 - INFO - __main__ - Step 112068: {'lr': 7.675876494779587e-05, 'samples': 21517056, 'steps': 112067, 'loss/train': 0.20138025283813477} 08/31/2021 09:32:11 - INFO - __main__ - Step 112069: {'lr': 7.675493897654276e-05, 'samples': 21517248, 'steps': 112068, 'loss/train': 1.2521946430206299} 08/31/2021 09:32:12 - INFO - __main__ - Step 112070: {'lr': 7.675111308335119e-05, 'samples': 21517440, 'steps': 112069, 'loss/train': 1.2686183452606201} 08/31/2021 09:32:13 - INFO - __main__ - Step 112071: {'lr': 7.674728726822294e-05, 'samples': 21517632, 'steps': 112070, 'loss/train': 1.2581400871276855} 08/31/2021 09:32:13 - INFO - __main__ - Step 112072: {'lr': 7.674346153115975e-05, 'samples': 21517824, 'steps': 112071, 'loss/train': 1.282390832901001} 08/31/2021 09:32:13 - INFO - __main__ - Step 112073: {'lr': 7.673963587216318e-05, 'samples': 21518016, 'steps': 112072, 'loss/train': 0.40663769841194153} 08/31/2021 09:32:14 - INFO - __main__ - Step 112074: {'lr': 7.673581029123506e-05, 'samples': 21518208, 'steps': 112073, 'loss/train': 0.6577406525611877} 08/31/2021 09:32:16 - INFO - __main__ - Step 112075: {'lr': 7.673198478837711e-05, 'samples': 21518400, 'steps': 112074, 'loss/train': 1.3869107961654663} 08/31/2021 09:32:16 - INFO - __main__ - Step 112076: {'lr': 7.672815936359106e-05, 'samples': 21518592, 'steps': 112075, 'loss/train': 1.2367563247680664} 08/31/2021 09:32:16 - INFO - __main__ - Step 112077: {'lr': 7.672433401687864e-05, 'samples': 21518784, 'steps': 112076, 'loss/train': 0.9653895497322083} 08/31/2021 09:32:17 - INFO - __main__ - Step 112078: {'lr': 7.672050874824154e-05, 'samples': 21518976, 'steps': 112077, 'loss/train': 0.9549924731254578} 08/31/2021 09:32:17 - INFO - __main__ - Step 112079: {'lr': 7.671668355768152e-05, 'samples': 21519168, 'steps': 112078, 'loss/train': 0.5253812670707703} 08/31/2021 09:32:19 - INFO - __main__ - Step 112080: {'lr': 7.67128584452003e-05, 'samples': 21519360, 'steps': 112079, 'loss/train': 0.44200462102890015} 08/31/2021 09:32:19 - INFO - __main__ - Step 112081: {'lr': 7.670903341079957e-05, 'samples': 21519552, 'steps': 112080, 'loss/train': 0.9700705409049988} 08/31/2021 09:32:20 - INFO - __main__ - Step 112082: {'lr': 7.670520845448109e-05, 'samples': 21519744, 'steps': 112081, 'loss/train': 1.044782042503357} 08/31/2021 09:32:20 - INFO - __main__ - Step 112083: {'lr': 7.670138357624665e-05, 'samples': 21519936, 'steps': 112082, 'loss/train': 0.5849052667617798} 08/31/2021 09:32:20 - INFO - __main__ - Step 112084: {'lr': 7.66975587760978e-05, 'samples': 21520128, 'steps': 112083, 'loss/train': 1.3495362997055054} 08/31/2021 09:32:21 - INFO - __main__ - Step 112085: {'lr': 7.669373405403635e-05, 'samples': 21520320, 'steps': 112084, 'loss/train': 1.3378477096557617} 08/31/2021 09:32:22 - INFO - __main__ - Step 112086: {'lr': 7.668990941006404e-05, 'samples': 21520512, 'steps': 112085, 'loss/train': 0.9975347518920898} 08/31/2021 09:32:23 - INFO - __main__ - Step 112087: {'lr': 7.668608484418257e-05, 'samples': 21520704, 'steps': 112086, 'loss/train': 0.01290875393897295} 08/31/2021 09:32:23 - INFO - __main__ - Step 112088: {'lr': 7.66822603563937e-05, 'samples': 21520896, 'steps': 112087, 'loss/train': 1.7513816356658936} 08/31/2021 09:32:24 - INFO - __main__ - Step 112089: {'lr': 7.66784359466991e-05, 'samples': 21521088, 'steps': 112088, 'loss/train': 0.9666003584861755} 08/31/2021 09:32:24 - INFO - __main__ - Step 112090: {'lr': 7.667461161510056e-05, 'samples': 21521280, 'steps': 112089, 'loss/train': 1.4647154808044434} 08/31/2021 09:32:26 - INFO - __main__ - Step 112091: {'lr': 7.667078736159974e-05, 'samples': 21521472, 'steps': 112090, 'loss/train': 0.7300650477409363} 08/31/2021 09:32:26 - INFO - __main__ - Step 112092: {'lr': 7.66669631861984e-05, 'samples': 21521664, 'steps': 112091, 'loss/train': 1.2962502241134644} 08/31/2021 09:32:26 - INFO - __main__ - Step 112093: {'lr': 7.666313908889822e-05, 'samples': 21521856, 'steps': 112092, 'loss/train': 1.3390626907348633} 08/31/2021 09:32:27 - INFO - __main__ - Step 112094: {'lr': 7.665931506970105e-05, 'samples': 21522048, 'steps': 112093, 'loss/train': 0.6572145223617554} 08/31/2021 09:32:27 - INFO - __main__ - Step 112095: {'lr': 7.665549112860845e-05, 'samples': 21522240, 'steps': 112094, 'loss/train': 0.953137993812561} 08/31/2021 09:32:28 - INFO - __main__ - Step 112096: {'lr': 7.665166726562223e-05, 'samples': 21522432, 'steps': 112095, 'loss/train': 0.6142854690551758} 08/31/2021 09:32:29 - INFO - __main__ - Step 112097: {'lr': 7.664784348074404e-05, 'samples': 21522624, 'steps': 112096, 'loss/train': 1.0515528917312622} 08/31/2021 09:32:30 - INFO - __main__ - Step 112098: {'lr': 7.66440197739757e-05, 'samples': 21522816, 'steps': 112097, 'loss/train': 0.03520030528306961} 08/31/2021 09:32:30 - INFO - __main__ - Step 112099: {'lr': 7.66401961453189e-05, 'samples': 21523008, 'steps': 112098, 'loss/train': 1.4083372354507446} 08/31/2021 09:32:30 - INFO - __main__ - Step 112100: {'lr': 7.663637259477532e-05, 'samples': 21523200, 'steps': 112099, 'loss/train': 1.1764267683029175} 08/31/2021 09:32:31 - INFO - __main__ - Step 112101: {'lr': 7.663254912234671e-05, 'samples': 21523392, 'steps': 112100, 'loss/train': 1.0171351432800293} 08/31/2021 09:32:32 - INFO - __main__ - Step 112102: {'lr': 7.662872572803484e-05, 'samples': 21523584, 'steps': 112101, 'loss/train': 0.9392679333686829} 08/31/2021 09:32:33 - INFO - __main__ - Step 112103: {'lr': 7.662490241184134e-05, 'samples': 21523776, 'steps': 112102, 'loss/train': 1.3093363046646118} 08/31/2021 09:32:33 - INFO - __main__ - Step 112104: {'lr': 7.662107917376802e-05, 'samples': 21523968, 'steps': 112103, 'loss/train': 1.152100682258606} 08/31/2021 09:32:33 - INFO - __main__ - Step 112105: {'lr': 7.661725601381655e-05, 'samples': 21524160, 'steps': 112104, 'loss/train': 1.3699088096618652} 08/31/2021 09:32:34 - INFO - __main__ - Step 112106: {'lr': 7.661343293198866e-05, 'samples': 21524352, 'steps': 112105, 'loss/train': 1.604135274887085} 08/31/2021 09:32:34 - INFO - __main__ - Step 112107: {'lr': 7.660960992828619e-05, 'samples': 21524544, 'steps': 112106, 'loss/train': 1.3101003170013428} 08/31/2021 09:32:35 - INFO - __main__ - Step 112108: {'lr': 7.660578700271064e-05, 'samples': 21524736, 'steps': 112107, 'loss/train': 1.7030203342437744} 08/31/2021 09:32:36 - INFO - __main__ - Step 112109: {'lr': 7.660196415526388e-05, 'samples': 21524928, 'steps': 112108, 'loss/train': 1.7510056495666504} 08/31/2021 09:32:36 - INFO - __main__ - Step 112110: {'lr': 7.659814138594759e-05, 'samples': 21525120, 'steps': 112109, 'loss/train': 1.714065432548523} 08/31/2021 09:32:37 - INFO - __main__ - Step 112111: {'lr': 7.65943186947635e-05, 'samples': 21525312, 'steps': 112110, 'loss/train': 0.9492589235305786} 08/31/2021 09:32:37 - INFO - __main__ - Step 112112: {'lr': 7.659049608171334e-05, 'samples': 21525504, 'steps': 112111, 'loss/train': 1.1471352577209473} 08/31/2021 09:32:38 - INFO - __main__ - Step 112113: {'lr': 7.65866735467988e-05, 'samples': 21525696, 'steps': 112112, 'loss/train': 0.7426028847694397} 08/31/2021 09:32:39 - INFO - __main__ - Step 112114: {'lr': 7.658285109002164e-05, 'samples': 21525888, 'steps': 112113, 'loss/train': 1.7107470035552979} 08/31/2021 09:32:39 - INFO - __main__ - Step 112115: {'lr': 7.657902871138359e-05, 'samples': 21526080, 'steps': 112114, 'loss/train': 1.0744028091430664} 08/31/2021 09:32:40 - INFO - __main__ - Step 112116: {'lr': 7.657520641088634e-05, 'samples': 21526272, 'steps': 112115, 'loss/train': 1.0098451375961304} 08/31/2021 09:32:40 - INFO - __main__ - Step 112117: {'lr': 7.657138418853162e-05, 'samples': 21526464, 'steps': 112116, 'loss/train': 1.5520431995391846} 08/31/2021 09:32:41 - INFO - __main__ - Step 112118: {'lr': 7.656756204432116e-05, 'samples': 21526656, 'steps': 112117, 'loss/train': 0.7557921409606934} 08/31/2021 09:32:42 - INFO - __main__ - Step 112119: {'lr': 7.65637399782567e-05, 'samples': 21526848, 'steps': 112118, 'loss/train': 1.006041407585144} 08/31/2021 09:32:42 - INFO - __main__ - Step 112120: {'lr': 7.655991799033992e-05, 'samples': 21527040, 'steps': 112119, 'loss/train': 1.544014573097229} 08/31/2021 09:32:43 - INFO - __main__ - Step 112121: {'lr': 7.655609608057265e-05, 'samples': 21527232, 'steps': 112120, 'loss/train': 0.9158218502998352} 08/31/2021 09:32:43 - INFO - __main__ - Step 112122: {'lr': 7.655227424895647e-05, 'samples': 21527424, 'steps': 112121, 'loss/train': 0.31232860684394836} 08/31/2021 09:32:44 - INFO - __main__ - Step 112123: {'lr': 7.654845249549314e-05, 'samples': 21527616, 'steps': 112122, 'loss/train': 1.0199745893478394} 08/31/2021 09:32:45 - INFO - __main__ - Step 112124: {'lr': 7.65446308201844e-05, 'samples': 21527808, 'steps': 112123, 'loss/train': 0.6287482380867004} 08/31/2021 09:32:45 - INFO - __main__ - Step 112125: {'lr': 7.654080922303198e-05, 'samples': 21528000, 'steps': 112124, 'loss/train': 2.04193115234375} 08/31/2021 09:32:46 - INFO - __main__ - Step 112126: {'lr': 7.653698770403755e-05, 'samples': 21528192, 'steps': 112125, 'loss/train': 1.103683352470398} 08/31/2021 09:32:46 - INFO - __main__ - Step 112127: {'lr': 7.653316626320292e-05, 'samples': 21528384, 'steps': 112126, 'loss/train': 0.8943042159080505} 08/31/2021 09:32:48 - INFO - __main__ - Step 112128: {'lr': 7.652934490052977e-05, 'samples': 21528576, 'steps': 112127, 'loss/train': 0.7823782563209534} 08/31/2021 09:32:48 - INFO - __main__ - Step 112129: {'lr': 7.652552361601981e-05, 'samples': 21528768, 'steps': 112128, 'loss/train': 0.9493250250816345} 08/31/2021 09:32:48 - INFO - __main__ - Step 112130: {'lr': 7.652170240967477e-05, 'samples': 21528960, 'steps': 112129, 'loss/train': 0.9511629939079285} 08/31/2021 09:32:49 - INFO - __main__ - Step 112131: {'lr': 7.651788128149639e-05, 'samples': 21529152, 'steps': 112130, 'loss/train': 1.4492676258087158} 08/31/2021 09:32:49 - INFO - __main__ - Step 112132: {'lr': 7.651406023148635e-05, 'samples': 21529344, 'steps': 112131, 'loss/train': 1.5766348838806152} 08/31/2021 09:32:49 - INFO - __main__ - Step 112133: {'lr': 7.651023925964642e-05, 'samples': 21529536, 'steps': 112132, 'loss/train': 1.2936240434646606} 08/31/2021 09:32:52 - INFO - __main__ - Step 112134: {'lr': 7.650641836597838e-05, 'samples': 21529728, 'steps': 112133, 'loss/train': 0.8853265643119812} 08/31/2021 09:32:52 - INFO - __main__ - Step 112135: {'lr': 7.650259755048378e-05, 'samples': 21529920, 'steps': 112134, 'loss/train': 1.208997368812561} 08/31/2021 09:32:52 - INFO - __main__ - Step 112136: {'lr': 7.649877681316441e-05, 'samples': 21530112, 'steps': 112135, 'loss/train': 1.2792937755584717} 08/31/2021 09:32:53 - INFO - __main__ - Step 112137: {'lr': 7.649495615402205e-05, 'samples': 21530304, 'steps': 112136, 'loss/train': 1.0812095403671265} 08/31/2021 09:32:53 - INFO - __main__ - Step 112138: {'lr': 7.649113557305836e-05, 'samples': 21530496, 'steps': 112137, 'loss/train': 1.4276567697525024} 08/31/2021 09:32:55 - INFO - __main__ - Step 112139: {'lr': 7.648731507027511e-05, 'samples': 21530688, 'steps': 112138, 'loss/train': 1.4810296297073364} 08/31/2021 09:32:55 - INFO - __main__ - Step 112140: {'lr': 7.6483494645674e-05, 'samples': 21530880, 'steps': 112139, 'loss/train': 0.9111000299453735} 08/31/2021 09:32:55 - INFO - __main__ - Step 112141: {'lr': 7.647967429925673e-05, 'samples': 21531072, 'steps': 112140, 'loss/train': 1.4798667430877686} 08/31/2021 09:32:56 - INFO - __main__ - Step 112142: {'lr': 7.647585403102506e-05, 'samples': 21531264, 'steps': 112141, 'loss/train': 1.3587199449539185} 08/31/2021 09:32:56 - INFO - __main__ - Step 112143: {'lr': 7.647203384098067e-05, 'samples': 21531456, 'steps': 112142, 'loss/train': 0.9092230200767517} 08/31/2021 09:32:58 - INFO - __main__ - Step 112144: {'lr': 7.646821372912533e-05, 'samples': 21531648, 'steps': 112143, 'loss/train': 1.3778660297393799} 08/31/2021 09:32:58 - INFO - __main__ - Step 112145: {'lr': 7.64643936954607e-05, 'samples': 21531840, 'steps': 112144, 'loss/train': 1.184992790222168} 08/31/2021 09:32:58 - INFO - __main__ - Step 112146: {'lr': 7.646057373998858e-05, 'samples': 21532032, 'steps': 112145, 'loss/train': 0.7417460083961487} 08/31/2021 09:32:59 - INFO - __main__ - Step 112147: {'lr': 7.645675386271062e-05, 'samples': 21532224, 'steps': 112146, 'loss/train': 1.1761374473571777} 08/31/2021 09:32:59 - INFO - __main__ - Step 112148: {'lr': 7.645293406362863e-05, 'samples': 21532416, 'steps': 112147, 'loss/train': 1.0673919916152954} 08/31/2021 09:32:59 - INFO - __main__ - Step 112149: {'lr': 7.644911434274423e-05, 'samples': 21532608, 'steps': 112148, 'loss/train': 0.9913222193717957} 08/31/2021 09:33:01 - INFO - __main__ - Step 112150: {'lr': 7.644529470005917e-05, 'samples': 21532800, 'steps': 112149, 'loss/train': 1.1375292539596558} 08/31/2021 09:33:01 - INFO - __main__ - Step 112151: {'lr': 7.644147513557517e-05, 'samples': 21532992, 'steps': 112150, 'loss/train': 1.0942269563674927} 08/31/2021 09:33:02 - INFO - __main__ - Step 112152: {'lr': 7.643765564929397e-05, 'samples': 21533184, 'steps': 112151, 'loss/train': 0.4745398759841919} 08/31/2021 09:33:02 - INFO - __main__ - Step 112153: {'lr': 7.643383624121727e-05, 'samples': 21533376, 'steps': 112152, 'loss/train': 1.8854427337646484} 08/31/2021 09:33:02 - INFO - __main__ - Step 112154: {'lr': 7.643001691134682e-05, 'samples': 21533568, 'steps': 112153, 'loss/train': 1.2217463254928589} 08/31/2021 09:33:04 - INFO - __main__ - Step 112155: {'lr': 7.642619765968433e-05, 'samples': 21533760, 'steps': 112154, 'loss/train': 1.1460585594177246} 08/31/2021 09:33:05 - INFO - __main__ - Step 112156: {'lr': 7.642237848623151e-05, 'samples': 21533952, 'steps': 112155, 'loss/train': 1.548484206199646} 08/31/2021 09:33:05 - INFO - __main__ - Step 112157: {'lr': 7.64185593909901e-05, 'samples': 21534144, 'steps': 112156, 'loss/train': 1.5171939134597778} 08/31/2021 09:33:05 - INFO - __main__ - Step 112158: {'lr': 7.64147403739618e-05, 'samples': 21534336, 'steps': 112157, 'loss/train': 0.8469899296760559} 08/31/2021 09:33:06 - INFO - __main__ - Step 112159: {'lr': 7.641092143514832e-05, 'samples': 21534528, 'steps': 112158, 'loss/train': 0.03565419092774391} 08/31/2021 09:33:07 - INFO - __main__ - Step 112160: {'lr': 7.640710257455143e-05, 'samples': 21534720, 'steps': 112159, 'loss/train': 0.7002138495445251} 08/31/2021 09:33:08 - INFO - __main__ - Step 112161: {'lr': 7.64032837921729e-05, 'samples': 21534912, 'steps': 112160, 'loss/train': 1.0317614078521729} 08/31/2021 09:33:08 - INFO - __main__ - Step 112162: {'lr': 7.639946508801427e-05, 'samples': 21535104, 'steps': 112161, 'loss/train': 1.3881241083145142} 08/31/2021 09:33:08 - INFO - __main__ - Step 112163: {'lr': 7.639564646207737e-05, 'samples': 21535296, 'steps': 112162, 'loss/train': 0.8544991612434387} 08/31/2021 09:33:09 - INFO - __main__ - Step 112164: {'lr': 7.639182791436392e-05, 'samples': 21535488, 'steps': 112163, 'loss/train': 1.5000957250595093} 08/31/2021 09:33:10 - INFO - __main__ - Step 112165: {'lr': 7.638800944487561e-05, 'samples': 21535680, 'steps': 112164, 'loss/train': 0.2243364304304123} 08/31/2021 09:33:11 - INFO - __main__ - Step 112166: {'lr': 7.638419105361422e-05, 'samples': 21535872, 'steps': 112165, 'loss/train': 1.342185378074646} 08/31/2021 09:33:11 - INFO - __main__ - Step 112167: {'lr': 7.63803727405814e-05, 'samples': 21536064, 'steps': 112166, 'loss/train': 1.5420677661895752} 08/31/2021 09:33:11 - INFO - __main__ - Step 112168: {'lr': 7.637655450577893e-05, 'samples': 21536256, 'steps': 112167, 'loss/train': 0.37611350417137146} 08/31/2021 09:33:12 - INFO - __main__ - Step 112169: {'lr': 7.637273634920849e-05, 'samples': 21536448, 'steps': 112168, 'loss/train': 0.11300875246524811} 08/31/2021 09:33:13 - INFO - __main__ - Step 112170: {'lr': 7.636891827087183e-05, 'samples': 21536640, 'steps': 112169, 'loss/train': 0.9613233804702759} 08/31/2021 09:33:14 - INFO - __main__ - Step 112171: {'lr': 7.636510027077065e-05, 'samples': 21536832, 'steps': 112170, 'loss/train': 0.28427350521087646} 08/31/2021 09:33:14 - INFO - __main__ - Step 112172: {'lr': 7.636128234890669e-05, 'samples': 21537024, 'steps': 112171, 'loss/train': 1.1026018857955933} 08/31/2021 09:33:14 - INFO - __main__ - Step 112173: {'lr': 7.635746450528164e-05, 'samples': 21537216, 'steps': 112172, 'loss/train': 1.0050970315933228} 08/31/2021 09:33:15 - INFO - __main__ - Step 112174: {'lr': 7.635364673989722e-05, 'samples': 21537408, 'steps': 112173, 'loss/train': 1.080726981163025} 08/31/2021 09:33:16 - INFO - __main__ - Step 112175: {'lr': 7.634982905275528e-05, 'samples': 21537600, 'steps': 112174, 'loss/train': 1.4118725061416626} 08/31/2021 09:33:17 - INFO - __main__ - Step 112176: {'lr': 7.634601144385733e-05, 'samples': 21537792, 'steps': 112175, 'loss/train': 1.13223135471344} 08/31/2021 09:33:17 - INFO - __main__ - Step 112177: {'lr': 7.63421939132052e-05, 'samples': 21537984, 'steps': 112176, 'loss/train': 0.8108388781547546} 08/31/2021 09:33:17 - INFO - __main__ - Step 112178: {'lr': 7.633837646080058e-05, 'samples': 21538176, 'steps': 112177, 'loss/train': 0.9064907431602478} 08/31/2021 09:33:18 - INFO - __main__ - Step 112179: {'lr': 7.633455908664522e-05, 'samples': 21538368, 'steps': 112178, 'loss/train': 1.1118595600128174} 08/31/2021 09:33:18 - INFO - __main__ - Step 112180: {'lr': 7.633074179074085e-05, 'samples': 21538560, 'steps': 112179, 'loss/train': 1.5672203302383423} 08/31/2021 09:33:20 - INFO - __main__ - Step 112181: {'lr': 7.632692457308912e-05, 'samples': 21538752, 'steps': 112180, 'loss/train': 0.1690901517868042} 08/31/2021 09:33:20 - INFO - __main__ - Step 112182: {'lr': 7.632310743369183e-05, 'samples': 21538944, 'steps': 112181, 'loss/train': 1.2819126844406128} 08/31/2021 09:33:20 - INFO - __main__ - Step 112183: {'lr': 7.631929037255064e-05, 'samples': 21539136, 'steps': 112182, 'loss/train': 1.0912302732467651} 08/31/2021 09:33:21 - INFO - __main__ - Step 112184: {'lr': 7.631547338966733e-05, 'samples': 21539328, 'steps': 112183, 'loss/train': 1.9112998247146606} 08/31/2021 09:33:21 - INFO - __main__ - Step 112185: {'lr': 7.631165648504357e-05, 'samples': 21539520, 'steps': 112184, 'loss/train': 1.3808202743530273} 08/31/2021 09:33:23 - INFO - __main__ - Step 112186: {'lr': 7.63078396586811e-05, 'samples': 21539712, 'steps': 112185, 'loss/train': 1.2666124105453491} 08/31/2021 09:33:24 - INFO - __main__ - Step 112187: {'lr': 7.630402291058164e-05, 'samples': 21539904, 'steps': 112186, 'loss/train': 0.391522616147995} 08/31/2021 09:33:24 - INFO - __main__ - Step 112188: {'lr': 7.630020624074699e-05, 'samples': 21540096, 'steps': 112187, 'loss/train': 1.2996656894683838} 08/31/2021 09:33:24 - INFO - __main__ - Step 112189: {'lr': 7.62963896491787e-05, 'samples': 21540288, 'steps': 112188, 'loss/train': 0.7062229514122009} 08/31/2021 09:33:25 - INFO - __main__ - Step 112190: {'lr': 7.62925731358786e-05, 'samples': 21540480, 'steps': 112189, 'loss/train': 1.1942312717437744} 08/31/2021 09:33:26 - INFO - __main__ - Step 112191: {'lr': 7.628875670084834e-05, 'samples': 21540672, 'steps': 112190, 'loss/train': 1.2383085489273071} 08/31/2021 09:33:27 - INFO - __main__ - Step 112192: {'lr': 7.628494034408972e-05, 'samples': 21540864, 'steps': 112191, 'loss/train': 0.6086865067481995} 08/31/2021 09:33:27 - INFO - __main__ - Step 112193: {'lr': 7.628112406560441e-05, 'samples': 21541056, 'steps': 112192, 'loss/train': 1.4370886087417603} 08/31/2021 09:33:27 - INFO - __main__ - Step 112194: {'lr': 7.627730786539416e-05, 'samples': 21541248, 'steps': 112193, 'loss/train': 0.9869408011436462} 08/31/2021 09:33:28 - INFO - __main__ - Step 112195: {'lr': 7.627349174346065e-05, 'samples': 21541440, 'steps': 112194, 'loss/train': 0.1112837865948677} 08/31/2021 09:33:29 - INFO - __main__ - Step 112196: {'lr': 7.626967569980564e-05, 'samples': 21541632, 'steps': 112195, 'loss/train': 1.4208213090896606} 08/31/2021 09:33:30 - INFO - __main__ - Step 112197: {'lr': 7.626585973443084e-05, 'samples': 21541824, 'steps': 112196, 'loss/train': 1.3462941646575928} 08/31/2021 09:33:30 - INFO - __main__ - Step 112198: {'lr': 7.626204384733795e-05, 'samples': 21542016, 'steps': 112197, 'loss/train': 1.027561068534851} 08/31/2021 09:33:30 - INFO - __main__ - Step 112199: {'lr': 7.625822803852872e-05, 'samples': 21542208, 'steps': 112198, 'loss/train': 1.2050373554229736} 08/31/2021 09:33:31 - INFO - __main__ - Step 112200: {'lr': 7.625441230800484e-05, 'samples': 21542400, 'steps': 112199, 'loss/train': 1.1238462924957275} 08/31/2021 09:33:32 - INFO - __main__ - Step 112201: {'lr': 7.625059665576803e-05, 'samples': 21542592, 'steps': 112200, 'loss/train': 1.0095901489257812} 08/31/2021 09:33:33 - INFO - __main__ - Step 112202: {'lr': 7.624678108182009e-05, 'samples': 21542784, 'steps': 112201, 'loss/train': 0.6509361267089844} 08/31/2021 09:33:33 - INFO - __main__ - Step 112203: {'lr': 7.624296558616261e-05, 'samples': 21542976, 'steps': 112202, 'loss/train': 1.1425002813339233} 08/31/2021 09:33:33 - INFO - __main__ - Step 112204: {'lr': 7.623915016879737e-05, 'samples': 21543168, 'steps': 112203, 'loss/train': 0.035556599497795105} 08/31/2021 09:33:34 - INFO - __main__ - Step 112205: {'lr': 7.623533482972608e-05, 'samples': 21543360, 'steps': 112204, 'loss/train': 1.4750944375991821} 08/31/2021 09:33:34 - INFO - __main__ - Step 112206: {'lr': 7.62315195689505e-05, 'samples': 21543552, 'steps': 112205, 'loss/train': 1.656258225440979} 08/31/2021 09:33:35 - INFO - __main__ - Step 112207: {'lr': 7.622770438647227e-05, 'samples': 21543744, 'steps': 112206, 'loss/train': 1.7181463241577148} 08/31/2021 09:33:36 - INFO - __main__ - Step 112208: {'lr': 7.622388928229318e-05, 'samples': 21543936, 'steps': 112207, 'loss/train': 0.8788915872573853} 08/31/2021 09:33:36 - INFO - __main__ - Step 112209: {'lr': 7.622007425641491e-05, 'samples': 21544128, 'steps': 112208, 'loss/train': 1.3387517929077148} 08/31/2021 09:33:37 - INFO - __main__ - Step 112210: {'lr': 7.621625930883922e-05, 'samples': 21544320, 'steps': 112209, 'loss/train': 0.8380867838859558} 08/31/2021 09:33:37 - INFO - __main__ - Step 112211: {'lr': 7.621244443956776e-05, 'samples': 21544512, 'steps': 112210, 'loss/train': 0.6154660582542419} 08/31/2021 09:33:38 - INFO - __main__ - Step 112212: {'lr': 7.620862964860231e-05, 'samples': 21544704, 'steps': 112211, 'loss/train': 0.7597417831420898} 08/31/2021 09:33:39 - INFO - __main__ - Step 112213: {'lr': 7.620481493594458e-05, 'samples': 21544896, 'steps': 112212, 'loss/train': 1.1206766366958618} 08/31/2021 09:33:39 - INFO - __main__ - Step 112214: {'lr': 7.620100030159627e-05, 'samples': 21545088, 'steps': 112213, 'loss/train': 1.4027621746063232} 08/31/2021 09:33:40 - INFO - __main__ - Step 112215: {'lr': 7.619718574555917e-05, 'samples': 21545280, 'steps': 112214, 'loss/train': 1.4290175437927246} 08/31/2021 09:33:40 - INFO - __main__ - Step 112216: {'lr': 7.619337126783488e-05, 'samples': 21545472, 'steps': 112215, 'loss/train': 0.6296077370643616} 08/31/2021 09:33:41 - INFO - __main__ - Step 112217: {'lr': 7.618955686842519e-05, 'samples': 21545664, 'steps': 112216, 'loss/train': 1.0018211603164673} 08/31/2021 09:33:42 - INFO - __main__ - Step 112218: {'lr': 7.618574254733177e-05, 'samples': 21545856, 'steps': 112217, 'loss/train': 1.065907597541809} 08/31/2021 09:33:42 - INFO - __main__ - Step 112219: {'lr': 7.618192830455639e-05, 'samples': 21546048, 'steps': 112218, 'loss/train': 1.218968152999878} 08/31/2021 09:33:43 - INFO - __main__ - Step 112220: {'lr': 7.617811414010073e-05, 'samples': 21546240, 'steps': 112219, 'loss/train': 1.1885184049606323} 08/31/2021 09:33:43 - INFO - __main__ - Step 112221: {'lr': 7.617430005396656e-05, 'samples': 21546432, 'steps': 112220, 'loss/train': 0.4812376797199249} 08/31/2021 09:33:43 - INFO - __main__ - Step 112222: {'lr': 7.617048604615554e-05, 'samples': 21546624, 'steps': 112221, 'loss/train': 1.4780348539352417} 08/31/2021 09:33:45 - INFO - __main__ - Step 112223: {'lr': 7.616667211666944e-05, 'samples': 21546816, 'steps': 112222, 'loss/train': 0.43365171551704407} 08/31/2021 09:33:45 - INFO - __main__ - Step 112224: {'lr': 7.616285826550995e-05, 'samples': 21547008, 'steps': 112223, 'loss/train': 1.301045298576355} 08/31/2021 09:33:46 - INFO - __main__ - Step 112225: {'lr': 7.615904449267877e-05, 'samples': 21547200, 'steps': 112224, 'loss/train': 0.41367003321647644} 08/31/2021 09:33:46 - INFO - __main__ - Step 112226: {'lr': 7.615523079817765e-05, 'samples': 21547392, 'steps': 112225, 'loss/train': 1.133333683013916} 08/31/2021 09:33:46 - INFO - __main__ - Step 112227: {'lr': 7.615141718200832e-05, 'samples': 21547584, 'steps': 112226, 'loss/train': 0.7625336647033691} 08/31/2021 09:33:48 - INFO - __main__ - Step 112228: {'lr': 7.614760364417256e-05, 'samples': 21547776, 'steps': 112227, 'loss/train': 1.3835769891738892} 08/31/2021 09:33:48 - INFO - __main__ - Step 112229: {'lr': 7.61437901846719e-05, 'samples': 21547968, 'steps': 112228, 'loss/train': 0.6688790321350098} 08/31/2021 09:33:49 - INFO - __main__ - Step 112230: {'lr': 7.613997680350821e-05, 'samples': 21548160, 'steps': 112229, 'loss/train': 0.605760931968689} 08/31/2021 09:33:49 - INFO - __main__ - Step 112231: {'lr': 7.613616350068312e-05, 'samples': 21548352, 'steps': 112230, 'loss/train': 0.8837576508522034} 08/31/2021 09:33:50 - INFO - __main__ - Step 112232: {'lr': 7.613235027619841e-05, 'samples': 21548544, 'steps': 112231, 'loss/train': 1.7868012189865112} 08/31/2021 09:33:51 - INFO - __main__ - Step 112233: {'lr': 7.612853713005577e-05, 'samples': 21548736, 'steps': 112232, 'loss/train': 1.160321831703186} 08/31/2021 09:33:52 - INFO - __main__ - Step 112234: {'lr': 7.612472406225696e-05, 'samples': 21548928, 'steps': 112233, 'loss/train': 1.0997949838638306} 08/31/2021 09:33:52 - INFO - __main__ - Step 112235: {'lr': 7.612091107280364e-05, 'samples': 21549120, 'steps': 112234, 'loss/train': 0.012122487649321556} 08/31/2021 09:33:53 - INFO - __main__ - Step 112236: {'lr': 7.611709816169754e-05, 'samples': 21549312, 'steps': 112235, 'loss/train': 0.014936896041035652} 08/31/2021 09:33:53 - INFO - __main__ - Step 112237: {'lr': 7.61132853289404e-05, 'samples': 21549504, 'steps': 112236, 'loss/train': 0.9715501070022583} 08/31/2021 09:33:53 - INFO - __main__ - Step 112238: {'lr': 7.610947257453396e-05, 'samples': 21549696, 'steps': 112237, 'loss/train': 0.8300532102584839} 08/31/2021 09:33:55 - INFO - __main__ - Step 112239: {'lr': 7.610565989847987e-05, 'samples': 21549888, 'steps': 112238, 'loss/train': 0.8622821569442749} 08/31/2021 09:33:56 - INFO - __main__ - Step 112240: {'lr': 7.610184730077991e-05, 'samples': 21550080, 'steps': 112239, 'loss/train': 1.7439936399459839} 08/31/2021 09:33:56 - INFO - __main__ - Step 112241: {'lr': 7.609803478143576e-05, 'samples': 21550272, 'steps': 112240, 'loss/train': 0.4607486426830292} 08/31/2021 09:33:57 - INFO - __main__ - Step 112242: {'lr': 7.609422234044924e-05, 'samples': 21550464, 'steps': 112241, 'loss/train': 0.9155245423316956} 08/31/2021 09:33:57 - INFO - __main__ - Step 112243: {'lr': 7.609040997782191e-05, 'samples': 21550656, 'steps': 112242, 'loss/train': 1.6857494115829468} 08/31/2021 09:33:57 - INFO - __main__ - Step 112244: {'lr': 7.608659769355555e-05, 'samples': 21550848, 'steps': 112243, 'loss/train': 0.04707391560077667} 08/31/2021 09:33:59 - INFO - __main__ - Step 112245: {'lr': 7.608278548765187e-05, 'samples': 21551040, 'steps': 112244, 'loss/train': 1.2275607585906982} 08/31/2021 09:34:00 - INFO - __main__ - Step 112246: {'lr': 7.607897336011263e-05, 'samples': 21551232, 'steps': 112245, 'loss/train': 1.2117817401885986} 08/31/2021 09:34:00 - INFO - __main__ - Step 112247: {'lr': 7.60751613109395e-05, 'samples': 21551424, 'steps': 112246, 'loss/train': 0.4736167788505554} 08/31/2021 09:34:00 - INFO - __main__ - Step 112248: {'lr': 7.607134934013424e-05, 'samples': 21551616, 'steps': 112247, 'loss/train': 1.3080861568450928} 08/31/2021 09:34:01 - INFO - __main__ - Step 112249: {'lr': 7.60675374476985e-05, 'samples': 21551808, 'steps': 112248, 'loss/train': 1.037481665611267} 08/31/2021 09:34:02 - INFO - __main__ - Step 112250: {'lr': 7.606372563363409e-05, 'samples': 21552000, 'steps': 112249, 'loss/train': 1.4705227613449097} 08/31/2021 09:34:03 - INFO - __main__ - Step 112251: {'lr': 7.605991389794267e-05, 'samples': 21552192, 'steps': 112250, 'loss/train': 0.9499964118003845} 08/31/2021 09:34:03 - INFO - __main__ - Step 112252: {'lr': 7.605610224062598e-05, 'samples': 21552384, 'steps': 112251, 'loss/train': 1.221966028213501} 08/31/2021 09:34:03 - INFO - __main__ - Step 112253: {'lr': 7.60522906616857e-05, 'samples': 21552576, 'steps': 112252, 'loss/train': 0.6820440292358398} 08/31/2021 09:34:04 - INFO - __main__ - Step 112254: {'lr': 7.60484791611236e-05, 'samples': 21552768, 'steps': 112253, 'loss/train': 1.2012003660202026} 08/31/2021 09:34:06 - INFO - __main__ - Step 112255: {'lr': 7.604466773894142e-05, 'samples': 21552960, 'steps': 112254, 'loss/train': 1.591674566268921} 08/31/2021 09:34:06 - INFO - __main__ - Step 112256: {'lr': 7.604085639514077e-05, 'samples': 21553152, 'steps': 112255, 'loss/train': 1.3647546768188477} 08/31/2021 09:34:06 - INFO - __main__ - Step 112257: {'lr': 7.603704512972342e-05, 'samples': 21553344, 'steps': 112256, 'loss/train': 1.6333969831466675} 08/31/2021 09:34:07 - INFO - __main__ - Step 112258: {'lr': 7.60332339426911e-05, 'samples': 21553536, 'steps': 112257, 'loss/train': 1.2861019372940063} 08/31/2021 09:34:07 - INFO - __main__ - Step 112259: {'lr': 7.602942283404551e-05, 'samples': 21553728, 'steps': 112258, 'loss/train': 0.09533575177192688} 08/31/2021 09:34:09 - INFO - __main__ - Step 112260: {'lr': 7.602561180378837e-05, 'samples': 21553920, 'steps': 112259, 'loss/train': 1.8963145017623901} 08/31/2021 09:34:09 - INFO - __main__ - Step 112261: {'lr': 7.602180085192142e-05, 'samples': 21554112, 'steps': 112260, 'loss/train': 0.8636676073074341} 08/31/2021 09:34:09 - INFO - __main__ - Step 112262: {'lr': 7.601798997844636e-05, 'samples': 21554304, 'steps': 112261, 'loss/train': 1.3014676570892334} 08/31/2021 09:34:10 - INFO - __main__ - Step 112263: {'lr': 7.601417918336489e-05, 'samples': 21554496, 'steps': 112262, 'loss/train': 0.8168107867240906} 08/31/2021 09:34:10 - INFO - __main__ - Step 112264: {'lr': 7.601036846667877e-05, 'samples': 21554688, 'steps': 112263, 'loss/train': 0.22441047430038452} 08/31/2021 09:34:10 - INFO - __main__ - Step 112265: {'lr': 7.60065578283897e-05, 'samples': 21554880, 'steps': 112264, 'loss/train': 1.3748384714126587} 08/31/2021 09:34:12 - INFO - __main__ - Step 112266: {'lr': 7.600274726849937e-05, 'samples': 21555072, 'steps': 112265, 'loss/train': 1.078783631324768} 08/31/2021 09:34:12 - INFO - __main__ - Step 112267: {'lr': 7.599893678700954e-05, 'samples': 21555264, 'steps': 112266, 'loss/train': 1.2777260541915894} 08/31/2021 09:34:13 - INFO - __main__ - Step 112268: {'lr': 7.599512638392186e-05, 'samples': 21555456, 'steps': 112267, 'loss/train': 0.7290152311325073} 08/31/2021 09:34:13 - INFO - __main__ - Step 112269: {'lr': 7.59913160592382e-05, 'samples': 21555648, 'steps': 112268, 'loss/train': 1.318785548210144} 08/31/2021 09:34:13 - INFO - __main__ - Step 112270: {'lr': 7.59875058129601e-05, 'samples': 21555840, 'steps': 112269, 'loss/train': 0.6885067224502563} 08/31/2021 09:34:15 - INFO - __main__ - Step 112271: {'lr': 7.598369564508934e-05, 'samples': 21556032, 'steps': 112270, 'loss/train': 1.4165339469909668} 08/31/2021 09:34:16 - INFO - __main__ - Step 112272: {'lr': 7.597988555562762e-05, 'samples': 21556224, 'steps': 112271, 'loss/train': 0.048555437475442886} 08/31/2021 09:34:16 - INFO - __main__ - Step 112273: {'lr': 7.597607554457669e-05, 'samples': 21556416, 'steps': 112272, 'loss/train': 1.0936883687973022} 08/31/2021 09:34:16 - INFO - __main__ - Step 112274: {'lr': 7.597226561193826e-05, 'samples': 21556608, 'steps': 112273, 'loss/train': 1.205833911895752} 08/31/2021 09:34:17 - INFO - __main__ - Step 112275: {'lr': 7.596845575771403e-05, 'samples': 21556800, 'steps': 112274, 'loss/train': 0.04569225758314133} 08/31/2021 09:34:18 - INFO - __main__ - Step 112276: {'lr': 7.596464598190575e-05, 'samples': 21556992, 'steps': 112275, 'loss/train': 1.2118659019470215} 08/31/2021 09:34:19 - INFO - __main__ - Step 112277: {'lr': 7.596083628451508e-05, 'samples': 21557184, 'steps': 112276, 'loss/train': 0.9099182486534119} 08/31/2021 09:34:19 - INFO - __main__ - Step 112278: {'lr': 7.59570266655438e-05, 'samples': 21557376, 'steps': 112277, 'loss/train': 1.7722078561782837} 08/31/2021 09:34:19 - INFO - __main__ - Step 112279: {'lr': 7.595321712499359e-05, 'samples': 21557568, 'steps': 112278, 'loss/train': 0.9520733952522278} 08/31/2021 09:34:20 - INFO - __main__ - Step 112280: {'lr': 7.594940766286618e-05, 'samples': 21557760, 'steps': 112279, 'loss/train': 0.8934382200241089} 08/31/2021 09:34:21 - INFO - __main__ - Step 112281: {'lr': 7.594559827916328e-05, 'samples': 21557952, 'steps': 112280, 'loss/train': 1.133764386177063} 08/31/2021 09:34:22 - INFO - __main__ - Step 112282: {'lr': 7.594178897388668e-05, 'samples': 21558144, 'steps': 112281, 'loss/train': 0.8527911305427551} 08/31/2021 09:34:22 - INFO - __main__ - Step 112283: {'lr': 7.593797974703795e-05, 'samples': 21558336, 'steps': 112282, 'loss/train': 0.9628898501396179} 08/31/2021 09:34:23 - INFO - __main__ - Step 112284: {'lr': 7.593417059861887e-05, 'samples': 21558528, 'steps': 112283, 'loss/train': 1.5438705682754517} 08/31/2021 09:34:23 - INFO - __main__ - Step 112285: {'lr': 7.593036152863117e-05, 'samples': 21558720, 'steps': 112284, 'loss/train': 0.04743051156401634} 08/31/2021 09:34:25 - INFO - __main__ - Step 112286: {'lr': 7.592655253707659e-05, 'samples': 21558912, 'steps': 112285, 'loss/train': 0.11096401512622833} 08/31/2021 09:34:25 - INFO - __main__ - Step 112287: {'lr': 7.592274362395679e-05, 'samples': 21559104, 'steps': 112286, 'loss/train': 1.1321306228637695} 08/31/2021 09:34:25 - INFO - __main__ - Step 112288: {'lr': 7.591893478927354e-05, 'samples': 21559296, 'steps': 112287, 'loss/train': 1.1337530612945557} 08/31/2021 09:34:26 - INFO - __main__ - Step 112289: {'lr': 7.59151260330285e-05, 'samples': 21559488, 'steps': 112288, 'loss/train': 0.9490935206413269} 08/31/2021 09:34:26 - INFO - __main__ - Step 112290: {'lr': 7.591131735522344e-05, 'samples': 21559680, 'steps': 112289, 'loss/train': 0.8846325874328613} 08/31/2021 09:34:26 - INFO - __main__ - Step 112291: {'lr': 7.590750875586002e-05, 'samples': 21559872, 'steps': 112290, 'loss/train': 1.3675235509872437} 08/31/2021 09:34:28 - INFO - __main__ - Step 112292: {'lr': 7.590370023494003e-05, 'samples': 21560064, 'steps': 112291, 'loss/train': 0.8283266425132751} 08/31/2021 09:34:28 - INFO - __main__ - Step 112293: {'lr': 7.589989179246515e-05, 'samples': 21560256, 'steps': 112292, 'loss/train': 1.5889109373092651} 08/31/2021 09:34:29 - INFO - __main__ - Step 112294: {'lr': 7.589608342843707e-05, 'samples': 21560448, 'steps': 112293, 'loss/train': 1.3471999168395996} 08/31/2021 09:34:29 - INFO - __main__ - Step 112295: {'lr': 7.589227514285751e-05, 'samples': 21560640, 'steps': 112294, 'loss/train': 0.8548524975776672} 08/31/2021 09:34:29 - INFO - __main__ - Step 112296: {'lr': 7.588846693572831e-05, 'samples': 21560832, 'steps': 112295, 'loss/train': 0.4158010482788086} 08/31/2021 09:34:32 - INFO - __main__ - Step 112297: {'lr': 7.588465880705101e-05, 'samples': 21561024, 'steps': 112296, 'loss/train': 1.2062273025512695} 08/31/2021 09:34:32 - INFO - __main__ - Step 112298: {'lr': 7.588085075682738e-05, 'samples': 21561216, 'steps': 112297, 'loss/train': 1.1861156225204468} 08/31/2021 09:34:32 - INFO - __main__ - Step 112299: {'lr': 7.587704278505917e-05, 'samples': 21561408, 'steps': 112298, 'loss/train': 0.2677222490310669} 08/31/2021 09:34:33 - INFO - __main__ - Step 112300: {'lr': 7.587323489174804e-05, 'samples': 21561600, 'steps': 112299, 'loss/train': 1.414472222328186} 08/31/2021 09:34:33 - INFO - __main__ - Step 112301: {'lr': 7.586942707689578e-05, 'samples': 21561792, 'steps': 112300, 'loss/train': 0.8624195456504822} 08/31/2021 09:34:35 - INFO - __main__ - Step 112302: {'lr': 7.586561934050407e-05, 'samples': 21561984, 'steps': 112301, 'loss/train': 1.0333335399627686} 08/31/2021 09:34:35 - INFO - __main__ - Step 112303: {'lr': 7.586181168257461e-05, 'samples': 21562176, 'steps': 112302, 'loss/train': 1.1595953702926636} 08/31/2021 09:34:35 - INFO - __main__ - Step 112304: {'lr': 7.585800410310912e-05, 'samples': 21562368, 'steps': 112303, 'loss/train': 1.3787249326705933} 08/31/2021 09:34:36 - INFO - __main__ - Step 112305: {'lr': 7.585419660210934e-05, 'samples': 21562560, 'steps': 112304, 'loss/train': 0.8889740705490112} 08/31/2021 09:34:36 - INFO - __main__ - Step 112306: {'lr': 7.585038917957695e-05, 'samples': 21562752, 'steps': 112305, 'loss/train': 1.3546149730682373} 08/31/2021 09:34:38 - INFO - __main__ - Step 112307: {'lr': 7.584658183551371e-05, 'samples': 21562944, 'steps': 112306, 'loss/train': 1.2821061611175537} 08/31/2021 09:34:38 - INFO - __main__ - Step 112308: {'lr': 7.58427745699214e-05, 'samples': 21563136, 'steps': 112307, 'loss/train': 0.262688547372818} 08/31/2021 09:34:39 - INFO - __main__ - Step 112309: {'lr': 7.583896738280155e-05, 'samples': 21563328, 'steps': 112308, 'loss/train': 1.6803584098815918} 08/31/2021 09:34:39 - INFO - __main__ - Step 112310: {'lr': 7.583516027415599e-05, 'samples': 21563520, 'steps': 112309, 'loss/train': 0.7782390117645264} 08/31/2021 09:34:39 - INFO - __main__ - Step 112311: {'lr': 7.58313532439864e-05, 'samples': 21563712, 'steps': 112310, 'loss/train': 0.8519526124000549} 08/31/2021 09:34:41 - INFO - __main__ - Step 112312: {'lr': 7.582754629229454e-05, 'samples': 21563904, 'steps': 112311, 'loss/train': 0.8090449571609497} 08/31/2021 09:34:42 - INFO - __main__ - Step 112313: {'lr': 7.582373941908208e-05, 'samples': 21564096, 'steps': 112312, 'loss/train': 1.5288289785385132} 08/31/2021 09:34:42 - INFO - __main__ - Step 112314: {'lr': 7.581993262435078e-05, 'samples': 21564288, 'steps': 112313, 'loss/train': 1.3621349334716797} 08/31/2021 09:34:43 - INFO - __main__ - Step 112315: {'lr': 7.58161259081023e-05, 'samples': 21564480, 'steps': 112314, 'loss/train': 0.0776538997888565} 08/31/2021 09:34:43 - INFO - __main__ - Step 112316: {'lr': 7.581231927033838e-05, 'samples': 21564672, 'steps': 112315, 'loss/train': 0.06356731802225113} 08/31/2021 09:34:43 - INFO - __main__ - Step 112317: {'lr': 7.580851271106076e-05, 'samples': 21564864, 'steps': 112316, 'loss/train': 0.4034835994243622} 08/31/2021 09:34:45 - INFO - __main__ - Step 112318: {'lr': 7.580470623027113e-05, 'samples': 21565056, 'steps': 112317, 'loss/train': 0.9358188509941101} 08/31/2021 09:34:45 - INFO - __main__ - Step 112319: {'lr': 7.58008998279713e-05, 'samples': 21565248, 'steps': 112318, 'loss/train': 1.0899479389190674} 08/31/2021 09:34:45 - INFO - __main__ - Step 112320: {'lr': 7.579709350416283e-05, 'samples': 21565440, 'steps': 112319, 'loss/train': 1.486322045326233} 08/31/2021 09:34:46 - INFO - __main__ - Step 112321: {'lr': 7.579328725884748e-05, 'samples': 21565632, 'steps': 112320, 'loss/train': 1.2187107801437378} 08/31/2021 09:34:46 - INFO - __main__ - Step 112322: {'lr': 7.578948109202699e-05, 'samples': 21565824, 'steps': 112321, 'loss/train': 0.7832061648368835} 08/31/2021 09:34:48 - INFO - __main__ - Step 112323: {'lr': 7.578567500370306e-05, 'samples': 21566016, 'steps': 112322, 'loss/train': 1.0452020168304443} 08/31/2021 09:34:48 - INFO - __main__ - Step 112324: {'lr': 7.578186899387742e-05, 'samples': 21566208, 'steps': 112323, 'loss/train': 1.4495434761047363} 08/31/2021 09:34:48 - INFO - __main__ - Step 112325: {'lr': 7.577806306255181e-05, 'samples': 21566400, 'steps': 112324, 'loss/train': 3.4616281986236572} 08/31/2021 09:34:49 - INFO - __main__ - Step 112326: {'lr': 7.577425720972789e-05, 'samples': 21566592, 'steps': 112325, 'loss/train': 1.485264539718628} 08/31/2021 09:34:49 - INFO - __main__ - Step 112327: {'lr': 7.577045143540742e-05, 'samples': 21566784, 'steps': 112326, 'loss/train': 0.8353227972984314} 08/31/2021 09:34:51 - INFO - __main__ - Step 112328: {'lr': 7.576664573959208e-05, 'samples': 21566976, 'steps': 112327, 'loss/train': 1.264643669128418} 08/31/2021 09:34:51 - INFO - __main__ - Step 112329: {'lr': 7.57628401222836e-05, 'samples': 21567168, 'steps': 112328, 'loss/train': 0.9842691421508789} 08/31/2021 09:34:52 - INFO - __main__ - Step 112330: {'lr': 7.57590345834838e-05, 'samples': 21567360, 'steps': 112329, 'loss/train': 1.05246901512146} 08/31/2021 09:34:52 - INFO - __main__ - Step 112331: {'lr': 7.575522912319418e-05, 'samples': 21567552, 'steps': 112330, 'loss/train': 0.8392340540885925} 08/31/2021 09:34:52 - INFO - __main__ - Step 112332: {'lr': 7.575142374141658e-05, 'samples': 21567744, 'steps': 112331, 'loss/train': 1.5384739637374878} 08/31/2021 09:34:53 - INFO - __main__ - Step 112333: {'lr': 7.57476184381527e-05, 'samples': 21567936, 'steps': 112332, 'loss/train': 0.6209867000579834} 08/31/2021 09:34:54 - INFO - __main__ - Step 112334: {'lr': 7.574381321340423e-05, 'samples': 21568128, 'steps': 112333, 'loss/train': 0.20750047266483307} 08/31/2021 09:34:55 - INFO - __main__ - Step 112335: {'lr': 7.574000806717294e-05, 'samples': 21568320, 'steps': 112334, 'loss/train': 0.09404953569173813} 08/31/2021 09:34:55 - INFO - __main__ - Step 112336: {'lr': 7.573620299946048e-05, 'samples': 21568512, 'steps': 112335, 'loss/train': 1.5374293327331543} 08/31/2021 09:34:55 - INFO - __main__ - Step 112337: {'lr': 7.573239801026862e-05, 'samples': 21568704, 'steps': 112336, 'loss/train': 0.5432807803153992} 08/31/2021 09:34:56 - INFO - __main__ - Step 112338: {'lr': 7.572859309959906e-05, 'samples': 21568896, 'steps': 112337, 'loss/train': 1.9604697227478027} 08/31/2021 09:34:57 - INFO - __main__ - Step 112339: {'lr': 7.572478826745349e-05, 'samples': 21569088, 'steps': 112338, 'loss/train': 1.6228508949279785} 08/31/2021 09:34:58 - INFO - __main__ - Step 112340: {'lr': 7.572098351383366e-05, 'samples': 21569280, 'steps': 112339, 'loss/train': 1.3541032075881958} 08/31/2021 09:34:58 - INFO - __main__ - Step 112341: {'lr': 7.571717883874135e-05, 'samples': 21569472, 'steps': 112340, 'loss/train': 0.13835297524929047} 08/31/2021 09:34:58 - INFO - __main__ - Step 112342: {'lr': 7.571337424217808e-05, 'samples': 21569664, 'steps': 112341, 'loss/train': 0.7848333716392517} 08/31/2021 09:34:59 - INFO - __main__ - Step 112343: {'lr': 7.57095697241457e-05, 'samples': 21569856, 'steps': 112342, 'loss/train': 0.9349740147590637} 08/31/2021 09:34:59 - INFO - __main__ - Step 112344: {'lr': 7.570576528464587e-05, 'samples': 21570048, 'steps': 112343, 'loss/train': 1.0383256673812866} 08/31/2021 09:35:01 - INFO - __main__ - Step 112345: {'lr': 7.570196092368037e-05, 'samples': 21570240, 'steps': 112344, 'loss/train': 1.2641873359680176} 08/31/2021 09:35:01 - INFO - __main__ - Step 112346: {'lr': 7.569815664125085e-05, 'samples': 21570432, 'steps': 112345, 'loss/train': 1.2088042497634888} 08/31/2021 09:35:01 - INFO - __main__ - Step 112347: {'lr': 7.569435243735907e-05, 'samples': 21570624, 'steps': 112346, 'loss/train': 0.6311744451522827} 08/31/2021 09:35:02 - INFO - __main__ - Step 112348: {'lr': 7.56905483120067e-05, 'samples': 21570816, 'steps': 112347, 'loss/train': 0.9093703627586365} 08/31/2021 09:35:02 - INFO - __main__ - Step 112349: {'lr': 7.56867442651955e-05, 'samples': 21571008, 'steps': 112348, 'loss/train': 0.5997961163520813} 08/31/2021 09:35:04 - INFO - __main__ - Step 112350: {'lr': 7.568294029692715e-05, 'samples': 21571200, 'steps': 112349, 'loss/train': 1.418204665184021} 08/31/2021 09:35:05 - INFO - __main__ - Step 112351: {'lr': 7.567913640720348e-05, 'samples': 21571392, 'steps': 112350, 'loss/train': 0.6327309012413025} 08/31/2021 09:35:05 - INFO - __main__ - Step 112352: {'lr': 7.5675332596026e-05, 'samples': 21571584, 'steps': 112351, 'loss/train': 0.4526340067386627} 08/31/2021 09:35:05 - INFO - __main__ - Step 112353: {'lr': 7.56715288633965e-05, 'samples': 21571776, 'steps': 112352, 'loss/train': 0.058442436158657074} 08/31/2021 09:35:06 - INFO - __main__ - Step 112354: {'lr': 7.566772520931679e-05, 'samples': 21571968, 'steps': 112353, 'loss/train': 0.2869773805141449} 08/31/2021 09:35:08 - INFO - __main__ - Step 112355: {'lr': 7.566392163378846e-05, 'samples': 21572160, 'steps': 112354, 'loss/train': 1.7908663749694824} 08/31/2021 09:35:08 - INFO - __main__ - Step 112356: {'lr': 7.566011813681328e-05, 'samples': 21572352, 'steps': 112355, 'loss/train': 1.3499159812927246} 08/31/2021 09:35:09 - INFO - __main__ - Step 112357: {'lr': 7.565631471839296e-05, 'samples': 21572544, 'steps': 112356, 'loss/train': 1.2672908306121826} 08/31/2021 09:35:09 - INFO - __main__ - Step 112358: {'lr': 7.565251137852924e-05, 'samples': 21572736, 'steps': 112357, 'loss/train': 0.0531252920627594} 08/31/2021 09:35:09 - INFO - __main__ - Step 112359: {'lr': 7.564870811722377e-05, 'samples': 21572928, 'steps': 112358, 'loss/train': 1.3243119716644287} 08/31/2021 09:35:11 - INFO - __main__ - Step 112360: {'lr': 7.564490493447834e-05, 'samples': 21573120, 'steps': 112359, 'loss/train': 1.3796164989471436} 08/31/2021 09:35:11 - INFO - __main__ - Step 112361: {'lr': 7.56411018302946e-05, 'samples': 21573312, 'steps': 112360, 'loss/train': 0.5248333215713501} 08/31/2021 09:35:12 - INFO - __main__ - Step 112362: {'lr': 7.563729880467429e-05, 'samples': 21573504, 'steps': 112361, 'loss/train': 2.0970401763916016} 08/31/2021 09:35:12 - INFO - __main__ - Step 112363: {'lr': 7.563349585761922e-05, 'samples': 21573696, 'steps': 112362, 'loss/train': 0.8322527408599854} 08/31/2021 09:35:12 - INFO - __main__ - Step 112364: {'lr': 7.562969298913091e-05, 'samples': 21573888, 'steps': 112363, 'loss/train': 1.5709153413772583} 08/31/2021 09:35:15 - INFO - __main__ - Step 112365: {'lr': 7.562589019921117e-05, 'samples': 21574080, 'steps': 112364, 'loss/train': 0.9455273151397705} 08/31/2021 09:35:15 - INFO - __main__ - Step 112366: {'lr': 7.562208748786172e-05, 'samples': 21574272, 'steps': 112365, 'loss/train': 1.5329020023345947} 08/31/2021 09:35:16 - INFO - __main__ - Step 112367: {'lr': 7.561828485508426e-05, 'samples': 21574464, 'steps': 112366, 'loss/train': 0.8626745939254761} 08/31/2021 09:35:16 - INFO - __main__ - Step 112368: {'lr': 7.561448230088053e-05, 'samples': 21574656, 'steps': 112367, 'loss/train': 1.202004075050354} 08/31/2021 09:35:16 - INFO - __main__ - Step 112369: {'lr': 7.561067982525222e-05, 'samples': 21574848, 'steps': 112368, 'loss/train': 0.9652186632156372} 08/31/2021 09:35:17 - INFO - __main__ - Step 112370: {'lr': 7.560687742820103e-05, 'samples': 21575040, 'steps': 112369, 'loss/train': 0.8293231129646301} 08/31/2021 09:35:19 - INFO - __main__ - Step 112371: {'lr': 7.560307510972869e-05, 'samples': 21575232, 'steps': 112370, 'loss/train': 0.6282610893249512} 08/31/2021 09:35:19 - INFO - __main__ - Step 112372: {'lr': 7.559927286983692e-05, 'samples': 21575424, 'steps': 112371, 'loss/train': 1.6006077527999878} 08/31/2021 09:35:19 - INFO - __main__ - Step 112373: {'lr': 7.559547070852744e-05, 'samples': 21575616, 'steps': 112372, 'loss/train': 1.2150722742080688} 08/31/2021 09:35:20 - INFO - __main__ - Step 112374: {'lr': 7.559166862580192e-05, 'samples': 21575808, 'steps': 112373, 'loss/train': 1.2233409881591797} 08/31/2021 09:35:20 - INFO - __main__ - Step 112375: {'lr': 7.558786662166212e-05, 'samples': 21576000, 'steps': 112374, 'loss/train': 1.778944492340088} 08/31/2021 09:35:22 - INFO - __main__ - Step 112376: {'lr': 7.558406469610981e-05, 'samples': 21576192, 'steps': 112375, 'loss/train': 0.09699313342571259} 08/31/2021 09:35:22 - INFO - __main__ - Step 112377: {'lr': 7.558026284914655e-05, 'samples': 21576384, 'steps': 112376, 'loss/train': 1.1788119077682495} 08/31/2021 09:35:23 - INFO - __main__ - Step 112378: {'lr': 7.557646108077412e-05, 'samples': 21576576, 'steps': 112377, 'loss/train': 0.8290448188781738} 08/31/2021 09:35:23 - INFO - __main__ - Step 112379: {'lr': 7.557265939099428e-05, 'samples': 21576768, 'steps': 112378, 'loss/train': 0.5456048846244812} 08/31/2021 09:35:24 - INFO - __main__ - Step 112380: {'lr': 7.556885777980868e-05, 'samples': 21576960, 'steps': 112379, 'loss/train': 1.1129095554351807} 08/31/2021 09:35:24 - INFO - __main__ - Step 112381: {'lr': 7.556505624721907e-05, 'samples': 21577152, 'steps': 112380, 'loss/train': 1.5841197967529297} 08/31/2021 09:35:25 - INFO - __main__ - Step 112382: {'lr': 7.556125479322714e-05, 'samples': 21577344, 'steps': 112381, 'loss/train': 1.3172887563705444} 08/31/2021 09:35:26 - INFO - __main__ - Step 112383: {'lr': 7.555745341783463e-05, 'samples': 21577536, 'steps': 112382, 'loss/train': 1.339431881904602} 08/31/2021 09:35:26 - INFO - __main__ - Step 112384: {'lr': 7.555365212104325e-05, 'samples': 21577728, 'steps': 112383, 'loss/train': 1.456865906715393} 08/31/2021 09:35:27 - INFO - __main__ - Step 112385: {'lr': 7.554985090285468e-05, 'samples': 21577920, 'steps': 112384, 'loss/train': 0.7868012189865112} 08/31/2021 09:35:27 - INFO - __main__ - Step 112386: {'lr': 7.554604976327068e-05, 'samples': 21578112, 'steps': 112385, 'loss/train': 1.1171940565109253} 08/31/2021 09:35:28 - INFO - __main__ - Step 112387: {'lr': 7.554224870229292e-05, 'samples': 21578304, 'steps': 112386, 'loss/train': 1.0218523740768433} 08/31/2021 09:35:29 - INFO - __main__ - Step 112388: {'lr': 7.553844771992313e-05, 'samples': 21578496, 'steps': 112387, 'loss/train': 1.595813512802124} 08/31/2021 09:35:29 - INFO - __main__ - Step 112389: {'lr': 7.553464681616303e-05, 'samples': 21578688, 'steps': 112388, 'loss/train': 1.1996064186096191} 08/31/2021 09:35:30 - INFO - __main__ - Step 112390: {'lr': 7.553084599101443e-05, 'samples': 21578880, 'steps': 112389, 'loss/train': 0.6244497895240784} 08/31/2021 09:35:30 - INFO - __main__ - Step 112391: {'lr': 7.552704524447881e-05, 'samples': 21579072, 'steps': 112390, 'loss/train': 0.9734606742858887} 08/31/2021 09:35:31 - INFO - __main__ - Step 112392: {'lr': 7.552324457655804e-05, 'samples': 21579264, 'steps': 112391, 'loss/train': 1.0205506086349487} 08/31/2021 09:35:32 - INFO - __main__ - Step 112393: {'lr': 7.55194439872538e-05, 'samples': 21579456, 'steps': 112392, 'loss/train': 1.220847487449646} 08/31/2021 09:35:32 - INFO - __main__ - Step 112394: {'lr': 7.55156434765678e-05, 'samples': 21579648, 'steps': 112393, 'loss/train': 0.7040171027183533} 08/31/2021 09:35:32 - INFO - __main__ - Step 112395: {'lr': 7.551184304450176e-05, 'samples': 21579840, 'steps': 112394, 'loss/train': 1.1977148056030273} 08/31/2021 09:35:33 - INFO - __main__ - Step 112396: {'lr': 7.55080426910574e-05, 'samples': 21580032, 'steps': 112395, 'loss/train': 1.391689658164978} 08/31/2021 09:35:34 - INFO - __main__ - Step 112397: {'lr': 7.55042424162364e-05, 'samples': 21580224, 'steps': 112396, 'loss/train': 1.436126947402954} 08/31/2021 09:35:35 - INFO - __main__ - Step 112398: {'lr': 7.550044222004051e-05, 'samples': 21580416, 'steps': 112397, 'loss/train': 1.2389271259307861} 08/31/2021 09:35:35 - INFO - __main__ - Step 112399: {'lr': 7.549664210247145e-05, 'samples': 21580608, 'steps': 112398, 'loss/train': 1.2830432653427124} 08/31/2021 09:35:36 - INFO - __main__ - Step 112400: {'lr': 7.549284206353088e-05, 'samples': 21580800, 'steps': 112399, 'loss/train': 0.9018173813819885} 08/31/2021 09:35:36 - INFO - __main__ - Step 112401: {'lr': 7.548904210322058e-05, 'samples': 21580992, 'steps': 112400, 'loss/train': 0.4378485381603241} 08/31/2021 09:35:38 - INFO - __main__ - Step 112402: {'lr': 7.548524222154218e-05, 'samples': 21581184, 'steps': 112401, 'loss/train': 0.8869808912277222} 08/31/2021 09:35:38 - INFO - __main__ - Step 112403: {'lr': 7.548144241849755e-05, 'samples': 21581376, 'steps': 112402, 'loss/train': 0.47438105940818787} 08/31/2021 09:35:39 - INFO - __main__ - Step 112404: {'lr': 7.547764269408818e-05, 'samples': 21581568, 'steps': 112403, 'loss/train': 0.9485135078430176} 08/31/2021 09:35:39 - INFO - __main__ - Step 112405: {'lr': 7.547384304831592e-05, 'samples': 21581760, 'steps': 112404, 'loss/train': 1.0361140966415405} 08/31/2021 09:35:39 - INFO - __main__ - Step 112406: {'lr': 7.547004348118245e-05, 'samples': 21581952, 'steps': 112405, 'loss/train': 0.5627104043960571} 08/31/2021 09:35:40 - INFO - __main__ - Step 112407: {'lr': 7.546624399268945e-05, 'samples': 21582144, 'steps': 112406, 'loss/train': 0.048925161361694336} 08/31/2021 09:35:42 - INFO - __main__ - Step 112408: {'lr': 7.546244458283869e-05, 'samples': 21582336, 'steps': 112407, 'loss/train': 0.7915652990341187} 08/31/2021 09:35:42 - INFO - __main__ - Step 112409: {'lr': 7.545864525163188e-05, 'samples': 21582528, 'steps': 112408, 'loss/train': 0.5322863459587097} 08/31/2021 09:35:42 - INFO - __main__ - Step 112410: {'lr': 7.545484599907068e-05, 'samples': 21582720, 'steps': 112409, 'loss/train': 1.0935349464416504} 08/31/2021 09:35:43 - INFO - __main__ - Step 112411: {'lr': 7.545104682515685e-05, 'samples': 21582912, 'steps': 112410, 'loss/train': 0.873853862285614} 08/31/2021 09:35:43 - INFO - __main__ - Step 112412: {'lr': 7.544724772989209e-05, 'samples': 21583104, 'steps': 112411, 'loss/train': 0.9356892704963684} 08/31/2021 09:35:45 - INFO - __main__ - Step 112413: {'lr': 7.544344871327807e-05, 'samples': 21583296, 'steps': 112412, 'loss/train': 0.6142319440841675} 08/31/2021 09:35:45 - INFO - __main__ - Step 112414: {'lr': 7.543964977531658e-05, 'samples': 21583488, 'steps': 112413, 'loss/train': 1.0493552684783936} 08/31/2021 09:35:46 - INFO - __main__ - Step 112415: {'lr': 7.543585091600927e-05, 'samples': 21583680, 'steps': 112414, 'loss/train': 0.6394416689872742} 08/31/2021 09:35:46 - INFO - __main__ - Step 112416: {'lr': 7.543205213535786e-05, 'samples': 21583872, 'steps': 112415, 'loss/train': 1.415313482284546} 08/31/2021 09:35:46 - INFO - __main__ - Step 112417: {'lr': 7.542825343336418e-05, 'samples': 21584064, 'steps': 112416, 'loss/train': 0.5519028902053833} 08/31/2021 09:35:48 - INFO - __main__ - Step 112418: {'lr': 7.542445481002974e-05, 'samples': 21584256, 'steps': 112417, 'loss/train': 1.0198187828063965} 08/31/2021 09:35:48 - INFO - __main__ - Step 112419: {'lr': 7.542065626535638e-05, 'samples': 21584448, 'steps': 112418, 'loss/train': 0.5204652547836304} 08/31/2021 09:35:48 - INFO - __main__ - Step 112420: {'lr': 7.541685779934574e-05, 'samples': 21584640, 'steps': 112419, 'loss/train': 1.3570295572280884} 08/31/2021 09:35:49 - INFO - __main__ - Step 112421: {'lr': 7.541305941199958e-05, 'samples': 21584832, 'steps': 112420, 'loss/train': 1.288027286529541} 08/31/2021 09:35:49 - INFO - __main__ - Step 112422: {'lr': 7.540926110331961e-05, 'samples': 21585024, 'steps': 112421, 'loss/train': 0.6400539875030518} 08/31/2021 09:35:51 - INFO - __main__ - Step 112423: {'lr': 7.540546287330751e-05, 'samples': 21585216, 'steps': 112422, 'loss/train': 0.31852084398269653} 08/31/2021 09:35:51 - INFO - __main__ - Step 112424: {'lr': 7.540166472196503e-05, 'samples': 21585408, 'steps': 112423, 'loss/train': 2.1823670864105225} 08/31/2021 09:35:51 - INFO - __main__ - Step 112425: {'lr': 7.539786664929388e-05, 'samples': 21585600, 'steps': 112424, 'loss/train': 1.2845375537872314} 08/31/2021 09:35:52 - INFO - __main__ - Step 112426: {'lr': 7.539406865529574e-05, 'samples': 21585792, 'steps': 112425, 'loss/train': 1.106777548789978} 08/31/2021 09:35:52 - INFO - __main__ - Step 112427: {'lr': 7.539027073997235e-05, 'samples': 21585984, 'steps': 112426, 'loss/train': 0.8488600850105286} 08/31/2021 09:35:53 - INFO - __main__ - Step 112428: {'lr': 7.538647290332537e-05, 'samples': 21586176, 'steps': 112427, 'loss/train': 1.1174334287643433} 08/31/2021 09:35:54 - INFO - __main__ - Step 112429: {'lr': 7.53826751453566e-05, 'samples': 21586368, 'steps': 112428, 'loss/train': 1.2442505359649658} 08/31/2021 09:35:54 - INFO - __main__ - Step 112430: {'lr': 7.537887746606775e-05, 'samples': 21586560, 'steps': 112429, 'loss/train': 1.3073999881744385} 08/31/2021 09:35:55 - INFO - __main__ - Step 112431: {'lr': 7.537507986546041e-05, 'samples': 21586752, 'steps': 112430, 'loss/train': 1.054775357246399} 08/31/2021 09:35:55 - INFO - __main__ - Step 112432: {'lr': 7.537128234353638e-05, 'samples': 21586944, 'steps': 112431, 'loss/train': 0.8399659991264343} 08/31/2021 09:35:55 - INFO - __main__ - Step 112433: {'lr': 7.536748490029735e-05, 'samples': 21587136, 'steps': 112432, 'loss/train': 0.7483716011047363} 08/31/2021 09:35:57 - INFO - __main__ - Step 112434: {'lr': 7.536368753574501e-05, 'samples': 21587328, 'steps': 112433, 'loss/train': 0.8490450978279114} 08/31/2021 09:35:57 - INFO - __main__ - Step 112435: {'lr': 7.535989024988113e-05, 'samples': 21587520, 'steps': 112434, 'loss/train': 1.015321969985962} 08/31/2021 09:35:58 - INFO - __main__ - Step 112436: {'lr': 7.535609304270738e-05, 'samples': 21587712, 'steps': 112435, 'loss/train': 1.1455737352371216} 08/31/2021 09:35:58 - INFO - __main__ - Step 112437: {'lr': 7.535229591422549e-05, 'samples': 21587904, 'steps': 112436, 'loss/train': 1.3647500276565552} 08/31/2021 09:35:58 - INFO - __main__ - Step 112438: {'lr': 7.534849886443714e-05, 'samples': 21588096, 'steps': 112437, 'loss/train': 1.0614162683486938} 08/31/2021 09:36:00 - INFO - __main__ - Step 112439: {'lr': 7.534470189334408e-05, 'samples': 21588288, 'steps': 112438, 'loss/train': 0.9047892093658447} 08/31/2021 09:36:00 - INFO - __main__ - Step 112440: {'lr': 7.534090500094798e-05, 'samples': 21588480, 'steps': 112439, 'loss/train': 1.9242854118347168} 08/31/2021 09:36:01 - INFO - __main__ - Step 112441: {'lr': 7.53371081872506e-05, 'samples': 21588672, 'steps': 112440, 'loss/train': 1.1200203895568848} 08/31/2021 09:36:01 - INFO - __main__ - Step 112442: {'lr': 7.533331145225361e-05, 'samples': 21588864, 'steps': 112441, 'loss/train': 1.1577831506729126} 08/31/2021 09:36:01 - INFO - __main__ - Step 112443: {'lr': 7.532951479595873e-05, 'samples': 21589056, 'steps': 112442, 'loss/train': 1.3518452644348145} 08/31/2021 09:36:03 - INFO - __main__ - Step 112444: {'lr': 7.532571821836776e-05, 'samples': 21589248, 'steps': 112443, 'loss/train': 0.36676260828971863} 08/31/2021 09:36:03 - INFO - __main__ - Step 112445: {'lr': 7.532192171948224e-05, 'samples': 21589440, 'steps': 112444, 'loss/train': 1.1277493238449097} 08/31/2021 09:36:04 - INFO - __main__ - Step 112446: {'lr': 7.531812529930399e-05, 'samples': 21589632, 'steps': 112445, 'loss/train': 1.3106633424758911} 08/31/2021 09:36:04 - INFO - __main__ - Step 112447: {'lr': 7.531432895783466e-05, 'samples': 21589824, 'steps': 112446, 'loss/train': 0.7016475200653076} 08/31/2021 09:36:05 - INFO - __main__ - Step 112448: {'lr': 7.5310532695076e-05, 'samples': 21590016, 'steps': 112447, 'loss/train': 1.0789355039596558} 08/31/2021 09:36:06 - INFO - __main__ - Step 112449: {'lr': 7.530673651102976e-05, 'samples': 21590208, 'steps': 112448, 'loss/train': 1.3561573028564453} 08/31/2021 09:36:06 - INFO - __main__ - Step 112450: {'lr': 7.530294040569757e-05, 'samples': 21590400, 'steps': 112449, 'loss/train': 1.018019199371338} 08/31/2021 09:36:07 - INFO - __main__ - Step 112451: {'lr': 7.52991443790812e-05, 'samples': 21590592, 'steps': 112450, 'loss/train': 0.6869305968284607} 08/31/2021 09:36:07 - INFO - __main__ - Step 112452: {'lr': 7.529534843118232e-05, 'samples': 21590784, 'steps': 112451, 'loss/train': 1.1633950471878052} 08/31/2021 09:36:08 - INFO - __main__ - Step 112453: {'lr': 7.529155256200269e-05, 'samples': 21590976, 'steps': 112452, 'loss/train': 1.2333852052688599} 08/31/2021 09:36:09 - INFO - __main__ - Step 112454: {'lr': 7.528775677154398e-05, 'samples': 21591168, 'steps': 112453, 'loss/train': 1.475609302520752} 08/31/2021 09:36:10 - INFO - __main__ - Step 112455: {'lr': 7.52839610598079e-05, 'samples': 21591360, 'steps': 112454, 'loss/train': 0.7202544808387756} 08/31/2021 09:36:10 - INFO - __main__ - Step 112456: {'lr': 7.528016542679616e-05, 'samples': 21591552, 'steps': 112455, 'loss/train': 1.2396175861358643} 08/31/2021 09:36:10 - INFO - __main__ - Step 112457: {'lr': 7.527636987251058e-05, 'samples': 21591744, 'steps': 112456, 'loss/train': 0.933194637298584} 08/31/2021 09:36:11 - INFO - __main__ - Step 112458: {'lr': 7.52725743969527e-05, 'samples': 21591936, 'steps': 112457, 'loss/train': 0.5257317423820496} 08/31/2021 09:36:13 - INFO - __main__ - Step 112459: {'lr': 7.526877900012429e-05, 'samples': 21592128, 'steps': 112458, 'loss/train': 0.5105705857276917} 08/31/2021 09:36:13 - INFO - __main__ - Step 112460: {'lr': 7.526498368202709e-05, 'samples': 21592320, 'steps': 112459, 'loss/train': 1.4637149572372437} 08/31/2021 09:36:14 - INFO - __main__ - Step 112461: {'lr': 7.526118844266274e-05, 'samples': 21592512, 'steps': 112460, 'loss/train': 0.5058993101119995} 08/31/2021 09:36:14 - INFO - __main__ - Step 112462: {'lr': 7.525739328203304e-05, 'samples': 21592704, 'steps': 112461, 'loss/train': 1.2901670932769775} 08/31/2021 09:36:14 - INFO - __main__ - Step 112463: {'lr': 7.525359820013966e-05, 'samples': 21592896, 'steps': 112462, 'loss/train': 0.09510112553834915} 08/31/2021 09:36:15 - INFO - __main__ - Step 112464: {'lr': 7.524980319698433e-05, 'samples': 21593088, 'steps': 112463, 'loss/train': 1.0502928495407104} 08/31/2021 09:36:16 - INFO - __main__ - Step 112465: {'lr': 7.524600827256872e-05, 'samples': 21593280, 'steps': 112464, 'loss/train': 1.2738291025161743} 08/31/2021 09:36:17 - INFO - __main__ - Step 112466: {'lr': 7.524221342689455e-05, 'samples': 21593472, 'steps': 112465, 'loss/train': 1.0538299083709717} 08/31/2021 09:36:17 - INFO - __main__ - Step 112467: {'lr': 7.523841865996356e-05, 'samples': 21593664, 'steps': 112466, 'loss/train': 1.0316760540008545} 08/31/2021 09:36:17 - INFO - __main__ - Step 112468: {'lr': 7.523462397177744e-05, 'samples': 21593856, 'steps': 112467, 'loss/train': 1.3289998769760132} 08/31/2021 09:36:18 - INFO - __main__ - Step 112469: {'lr': 7.52308293623379e-05, 'samples': 21594048, 'steps': 112468, 'loss/train': 0.6202474236488342} 08/31/2021 09:36:19 - INFO - __main__ - Step 112470: {'lr': 7.522703483164673e-05, 'samples': 21594240, 'steps': 112469, 'loss/train': 0.9009941220283508} 08/31/2021 09:36:19 - INFO - __main__ - Step 112471: {'lr': 7.522324037970549e-05, 'samples': 21594432, 'steps': 112470, 'loss/train': 0.6951969265937805} 08/31/2021 09:36:20 - INFO - __main__ - Step 112472: {'lr': 7.521944600651595e-05, 'samples': 21594624, 'steps': 112471, 'loss/train': 0.3819536864757538} 08/31/2021 09:36:20 - INFO - __main__ - Step 112473: {'lr': 7.521565171207984e-05, 'samples': 21594816, 'steps': 112472, 'loss/train': 1.470908522605896} 08/31/2021 09:36:21 - INFO - __main__ - Step 112474: {'lr': 7.521185749639886e-05, 'samples': 21595008, 'steps': 112473, 'loss/train': 1.0974276065826416} 08/31/2021 09:36:23 - INFO - __main__ - Step 112475: {'lr': 7.520806335947469e-05, 'samples': 21595200, 'steps': 112474, 'loss/train': 0.8345896601676941} 08/31/2021 09:36:23 - INFO - __main__ - Step 112476: {'lr': 7.520426930130911e-05, 'samples': 21595392, 'steps': 112475, 'loss/train': 0.6617002487182617} 08/31/2021 09:36:24 - INFO - __main__ - Step 112477: {'lr': 7.520047532190377e-05, 'samples': 21595584, 'steps': 112476, 'loss/train': 0.3683834373950958} 08/31/2021 09:36:24 - INFO - __main__ - Step 112478: {'lr': 7.51966814212604e-05, 'samples': 21595776, 'steps': 112477, 'loss/train': 1.0456032752990723} 08/31/2021 09:36:24 - INFO - __main__ - Step 112479: {'lr': 7.51928875993807e-05, 'samples': 21595968, 'steps': 112478, 'loss/train': 0.9439440965652466} 08/31/2021 09:36:26 - INFO - __main__ - Step 112480: {'lr': 7.51890938562664e-05, 'samples': 21596160, 'steps': 112479, 'loss/train': 0.6563981771469116} 08/31/2021 09:36:27 - INFO - __main__ - Step 112481: {'lr': 7.518530019191922e-05, 'samples': 21596352, 'steps': 112480, 'loss/train': 1.0608628988265991} 08/31/2021 09:36:27 - INFO - __main__ - Step 112482: {'lr': 7.518150660634079e-05, 'samples': 21596544, 'steps': 112481, 'loss/train': 0.9195615649223328} 08/31/2021 09:36:27 - INFO - __main__ - Step 112483: {'lr': 7.517771309953292e-05, 'samples': 21596736, 'steps': 112482, 'loss/train': 1.4830082654953003} 08/31/2021 09:36:28 - INFO - __main__ - Step 112484: {'lr': 7.517391967149734e-05, 'samples': 21596928, 'steps': 112483, 'loss/train': 1.4605239629745483} 08/31/2021 09:36:28 - INFO - __main__ - Step 112485: {'lr': 7.51701263222356e-05, 'samples': 21597120, 'steps': 112484, 'loss/train': 1.293274998664856} 08/31/2021 09:36:28 - INFO - __main__ - Step 112486: {'lr': 7.516633305174953e-05, 'samples': 21597312, 'steps': 112485, 'loss/train': 0.013303005136549473} 08/31/2021 09:36:30 - INFO - __main__ - Step 112487: {'lr': 7.51625398600408e-05, 'samples': 21597504, 'steps': 112486, 'loss/train': 0.016575466841459274} 08/31/2021 09:36:31 - INFO - __main__ - Step 112488: {'lr': 7.515874674711113e-05, 'samples': 21597696, 'steps': 112487, 'loss/train': 0.16575783491134644} 08/31/2021 09:36:31 - INFO - __main__ - Step 112489: {'lr': 7.515495371296225e-05, 'samples': 21597888, 'steps': 112488, 'loss/train': 0.028939370065927505} 08/31/2021 09:36:31 - INFO - __main__ - Step 112490: {'lr': 7.515116075759582e-05, 'samples': 21598080, 'steps': 112489, 'loss/train': 0.03492043539881706} 08/31/2021 09:36:32 - INFO - __main__ - Step 112491: {'lr': 7.514736788101359e-05, 'samples': 21598272, 'steps': 112490, 'loss/train': 0.0737617090344429} 08/31/2021 09:36:33 - INFO - __main__ - Step 112492: {'lr': 7.514357508321726e-05, 'samples': 21598464, 'steps': 112491, 'loss/train': 1.4565198421478271} 08/31/2021 09:36:34 - INFO - __main__ - Step 112493: {'lr': 7.513978236420855e-05, 'samples': 21598656, 'steps': 112492, 'loss/train': 1.090799331665039} 08/31/2021 09:36:34 - INFO - __main__ - Step 112494: {'lr': 7.513598972398913e-05, 'samples': 21598848, 'steps': 112493, 'loss/train': 1.3982748985290527} 08/31/2021 09:36:34 - INFO - __main__ - Step 112495: {'lr': 7.513219716256073e-05, 'samples': 21599040, 'steps': 112494, 'loss/train': 1.1128982305526733} 08/31/2021 09:36:35 - INFO - __main__ - Step 112496: {'lr': 7.51284046799251e-05, 'samples': 21599232, 'steps': 112495, 'loss/train': 1.1217200756072998} 08/31/2021 09:36:36 - INFO - __main__ - Step 112497: {'lr': 7.512461227608397e-05, 'samples': 21599424, 'steps': 112496, 'loss/train': 0.5212231874465942} 08/31/2021 09:36:37 - INFO - __main__ - Step 112498: {'lr': 7.51208199510389e-05, 'samples': 21599616, 'steps': 112497, 'loss/train': 0.9152536392211914} 08/31/2021 09:36:37 - INFO - __main__ - Step 112499: {'lr': 7.51170277047917e-05, 'samples': 21599808, 'steps': 112498, 'loss/train': 1.2259315252304077} 08/31/2021 09:36:38 - INFO - __main__ - Step 112500: {'lr': 7.511323553734409e-05, 'samples': 21600000, 'steps': 112499, 'loss/train': 1.5742263793945312} 08/31/2021 09:36:38 - INFO - __main__ - Step 112501: {'lr': 7.510944344869774e-05, 'samples': 21600192, 'steps': 112500, 'loss/train': 0.7258743047714233} 08/31/2021 09:36:39 - INFO - __main__ - Step 112502: {'lr': 7.510565143885436e-05, 'samples': 21600384, 'steps': 112501, 'loss/train': 1.2754415273666382} 08/31/2021 09:36:40 - INFO - __main__ - Step 112503: {'lr': 7.51018595078157e-05, 'samples': 21600576, 'steps': 112502, 'loss/train': 1.234683871269226} 08/31/2021 09:36:40 - INFO - __main__ - Step 112504: {'lr': 7.509806765558344e-05, 'samples': 21600768, 'steps': 112503, 'loss/train': 1.5995607376098633} 08/31/2021 09:36:41 - INFO - __main__ - Step 112505: {'lr': 7.509427588215928e-05, 'samples': 21600960, 'steps': 112504, 'loss/train': 0.4632169008255005} 08/31/2021 09:36:41 - INFO - __main__ - Step 112506: {'lr': 7.509048418754494e-05, 'samples': 21601152, 'steps': 112505, 'loss/train': 0.7314555048942566} 08/31/2021 09:36:43 - INFO - __main__ - Step 112507: {'lr': 7.508669257174214e-05, 'samples': 21601344, 'steps': 112506, 'loss/train': 1.4862980842590332} 08/31/2021 09:36:43 - INFO - __main__ - Step 112508: {'lr': 7.508290103475257e-05, 'samples': 21601536, 'steps': 112507, 'loss/train': 1.1247118711471558} 08/31/2021 09:36:43 - INFO - __main__ - Step 112509: {'lr': 7.507910957657796e-05, 'samples': 21601728, 'steps': 112508, 'loss/train': 0.4359138011932373} 08/31/2021 09:36:44 - INFO - __main__ - Step 112510: {'lr': 7.507531819721997e-05, 'samples': 21601920, 'steps': 112509, 'loss/train': 0.6532424092292786} 08/31/2021 09:36:44 - INFO - __main__ - Step 112511: {'lr': 7.507152689668045e-05, 'samples': 21602112, 'steps': 112510, 'loss/train': 0.7377477884292603} 08/31/2021 09:36:45 - INFO - __main__ - Step 112512: {'lr': 7.506773567496092e-05, 'samples': 21602304, 'steps': 112511, 'loss/train': 0.7008164525032043} 08/31/2021 09:36:46 - INFO - __main__ - Step 112513: {'lr': 7.506394453206317e-05, 'samples': 21602496, 'steps': 112512, 'loss/train': 1.3435616493225098} 08/31/2021 09:36:46 - INFO - __main__ - Step 112514: {'lr': 7.506015346798889e-05, 'samples': 21602688, 'steps': 112513, 'loss/train': 1.8310693502426147} 08/31/2021 09:36:47 - INFO - __main__ - Step 112515: {'lr': 7.505636248273981e-05, 'samples': 21602880, 'steps': 112514, 'loss/train': 1.126253604888916} 08/31/2021 09:36:47 - INFO - __main__ - Step 112516: {'lr': 7.505257157631765e-05, 'samples': 21603072, 'steps': 112515, 'loss/train': 1.4055585861206055} 08/31/2021 09:36:47 - INFO - __main__ - Step 112517: {'lr': 7.50487807487241e-05, 'samples': 21603264, 'steps': 112516, 'loss/train': 1.2943235635757446} 08/31/2021 09:36:49 - INFO - __main__ - Step 112518: {'lr': 7.504498999996084e-05, 'samples': 21603456, 'steps': 112517, 'loss/train': 1.9030027389526367} 08/31/2021 09:36:50 - INFO - __main__ - Step 112519: {'lr': 7.504119933002964e-05, 'samples': 21603648, 'steps': 112518, 'loss/train': 0.572985053062439} 08/31/2021 09:36:50 - INFO - __main__ - Step 112520: {'lr': 7.503740873893217e-05, 'samples': 21603840, 'steps': 112519, 'loss/train': 0.6394511461257935} 08/31/2021 09:36:51 - INFO - __main__ - Step 112521: {'lr': 7.503361822667012e-05, 'samples': 21604032, 'steps': 112520, 'loss/train': 0.10586779564619064} 08/31/2021 09:36:51 - INFO - __main__ - Step 112522: {'lr': 7.502982779324525e-05, 'samples': 21604224, 'steps': 112521, 'loss/train': 0.8160789012908936} 08/31/2021 09:36:53 - INFO - __main__ - Step 112523: {'lr': 7.502603743865924e-05, 'samples': 21604416, 'steps': 112522, 'loss/train': 1.5213954448699951} 08/31/2021 09:36:53 - INFO - __main__ - Step 112524: {'lr': 7.502224716291386e-05, 'samples': 21604608, 'steps': 112523, 'loss/train': 0.40690234303474426} 08/31/2021 09:36:54 - INFO - __main__ - Step 112525: {'lr': 7.501845696601068e-05, 'samples': 21604800, 'steps': 112524, 'loss/train': 0.6577142477035522} 08/31/2021 09:36:54 - INFO - __main__ - Step 112526: {'lr': 7.50146668479515e-05, 'samples': 21604992, 'steps': 112525, 'loss/train': 1.040196180343628} 08/31/2021 09:36:54 - INFO - __main__ - Step 112527: {'lr': 7.501087680873798e-05, 'samples': 21605184, 'steps': 112526, 'loss/train': 0.02604665420949459} 08/31/2021 09:36:56 - INFO - __main__ - Step 112528: {'lr': 7.500708684837187e-05, 'samples': 21605376, 'steps': 112527, 'loss/train': 0.8034000396728516} 08/31/2021 09:36:56 - INFO - __main__ - Step 112529: {'lr': 7.500329696685487e-05, 'samples': 21605568, 'steps': 112528, 'loss/train': 1.2741602659225464} 08/31/2021 09:36:57 - INFO - __main__ - Step 112530: {'lr': 7.499950716418869e-05, 'samples': 21605760, 'steps': 112529, 'loss/train': 1.2471106052398682} 08/31/2021 09:36:57 - INFO - __main__ - Step 112531: {'lr': 7.499571744037504e-05, 'samples': 21605952, 'steps': 112530, 'loss/train': 1.1589685678482056} 08/31/2021 09:36:57 - INFO - __main__ - Step 112532: {'lr': 7.499192779541561e-05, 'samples': 21606144, 'steps': 112531, 'loss/train': 1.4900164604187012} 08/31/2021 09:36:59 - INFO - __main__ - Step 112533: {'lr': 7.49881382293121e-05, 'samples': 21606336, 'steps': 112532, 'loss/train': 0.40772634744644165} 08/31/2021 09:36:59 - INFO - __main__ - Step 112534: {'lr': 7.498434874206624e-05, 'samples': 21606528, 'steps': 112533, 'loss/train': 1.3205277919769287} 08/31/2021 09:37:00 - INFO - __main__ - Step 112535: {'lr': 7.498055933367976e-05, 'samples': 21606720, 'steps': 112534, 'loss/train': 0.9894787073135376} 08/31/2021 09:37:00 - INFO - __main__ - Step 112536: {'lr': 7.497677000415432e-05, 'samples': 21606912, 'steps': 112535, 'loss/train': 1.3610503673553467} 08/31/2021 09:37:00 - INFO - __main__ - Step 112537: {'lr': 7.497298075349163e-05, 'samples': 21607104, 'steps': 112536, 'loss/train': 0.9589737057685852} 08/31/2021 09:37:02 - INFO - __main__ - Step 112538: {'lr': 7.496919158169352e-05, 'samples': 21607296, 'steps': 112537, 'loss/train': 0.4278773367404938} 08/31/2021 09:37:02 - INFO - __main__ - Step 112539: {'lr': 7.496540248876149e-05, 'samples': 21607488, 'steps': 112538, 'loss/train': 1.3394523859024048} 08/31/2021 09:37:03 - INFO - __main__ - Step 112540: {'lr': 7.496161347469738e-05, 'samples': 21607680, 'steps': 112539, 'loss/train': 1.5892714262008667} 08/31/2021 09:37:03 - INFO - __main__ - Step 112541: {'lr': 7.495782453950284e-05, 'samples': 21607872, 'steps': 112540, 'loss/train': 1.1883106231689453} 08/31/2021 09:37:03 - INFO - __main__ - Step 112542: {'lr': 7.49540356831796e-05, 'samples': 21608064, 'steps': 112541, 'loss/train': 0.9308491945266724} 08/31/2021 09:37:05 - INFO - __main__ - Step 112543: {'lr': 7.495024690572937e-05, 'samples': 21608256, 'steps': 112542, 'loss/train': 1.3030180931091309} 08/31/2021 09:37:05 - INFO - __main__ - Step 112544: {'lr': 7.494645820715387e-05, 'samples': 21608448, 'steps': 112543, 'loss/train': 1.2351454496383667} 08/31/2021 09:37:06 - INFO - __main__ - Step 112545: {'lr': 7.494266958745479e-05, 'samples': 21608640, 'steps': 112544, 'loss/train': 0.1581428498029709} 08/31/2021 09:37:06 - INFO - __main__ - Step 112546: {'lr': 7.493888104663385e-05, 'samples': 21608832, 'steps': 112545, 'loss/train': 1.400551438331604} 08/31/2021 09:37:06 - INFO - __main__ - Step 112547: {'lr': 7.493509258469275e-05, 'samples': 21609024, 'steps': 112546, 'loss/train': 1.4893178939819336} 08/31/2021 09:37:07 - INFO - __main__ - Step 112548: {'lr': 7.49313042016332e-05, 'samples': 21609216, 'steps': 112547, 'loss/train': 0.10951776057481766} 08/31/2021 09:37:08 - INFO - __main__ - Step 112549: {'lr': 7.492751589745686e-05, 'samples': 21609408, 'steps': 112548, 'loss/train': 1.4954257011413574} 08/31/2021 09:37:09 - INFO - __main__ - Step 112550: {'lr': 7.492372767216551e-05, 'samples': 21609600, 'steps': 112549, 'loss/train': 1.3046493530273438} 08/31/2021 09:37:09 - INFO - __main__ - Step 112551: {'lr': 7.491993952576093e-05, 'samples': 21609792, 'steps': 112550, 'loss/train': 1.0714795589447021} 08/31/2021 09:37:09 - INFO - __main__ - Step 112552: {'lr': 7.49161514582446e-05, 'samples': 21609984, 'steps': 112551, 'loss/train': 0.41155001521110535} 08/31/2021 09:37:10 - INFO - __main__ - Step 112553: {'lr': 7.491236346961838e-05, 'samples': 21610176, 'steps': 112552, 'loss/train': 0.9830583333969116} 08/31/2021 09:37:11 - INFO - __main__ - Step 112554: {'lr': 7.490857555988395e-05, 'samples': 21610368, 'steps': 112553, 'loss/train': 1.40509831905365} 08/31/2021 09:37:12 - INFO - __main__ - Step 112555: {'lr': 7.490478772904299e-05, 'samples': 21610560, 'steps': 112554, 'loss/train': 1.467004656791687} 08/31/2021 09:37:12 - INFO - __main__ - Step 112556: {'lr': 7.490099997709724e-05, 'samples': 21610752, 'steps': 112555, 'loss/train': 1.1914796829223633} 08/31/2021 09:37:12 - INFO - __main__ - Step 112557: {'lr': 7.489721230404842e-05, 'samples': 21610944, 'steps': 112556, 'loss/train': 1.2325035333633423} 08/31/2021 09:37:13 - INFO - __main__ - Step 112558: {'lr': 7.489342470989818e-05, 'samples': 21611136, 'steps': 112557, 'loss/train': 1.5637404918670654} 08/31/2021 09:37:14 - INFO - __main__ - Step 112559: {'lr': 7.488963719464828e-05, 'samples': 21611328, 'steps': 112558, 'loss/train': 1.201137900352478} 08/31/2021 09:37:14 - INFO - __main__ - Step 112560: {'lr': 7.48858497583004e-05, 'samples': 21611520, 'steps': 112559, 'loss/train': 1.2329624891281128} 08/31/2021 09:37:15 - INFO - __main__ - Step 112561: {'lr': 7.488206240085627e-05, 'samples': 21611712, 'steps': 112560, 'loss/train': 1.704271674156189} 08/31/2021 09:37:15 - INFO - __main__ - Step 112562: {'lr': 7.487827512231754e-05, 'samples': 21611904, 'steps': 112561, 'loss/train': 1.0249429941177368} 08/31/2021 09:37:16 - INFO - __main__ - Step 112563: {'lr': 7.487448792268601e-05, 'samples': 21612096, 'steps': 112562, 'loss/train': 1.2955126762390137} 08/31/2021 09:37:17 - INFO - __main__ - Step 112564: {'lr': 7.487070080196329e-05, 'samples': 21612288, 'steps': 112563, 'loss/train': 0.3843303918838501} 08/31/2021 09:37:18 - INFO - __main__ - Step 112565: {'lr': 7.486691376015123e-05, 'samples': 21612480, 'steps': 112564, 'loss/train': 0.6594764590263367} 08/31/2021 09:37:18 - INFO - __main__ - Step 112566: {'lr': 7.486312679725135e-05, 'samples': 21612672, 'steps': 112565, 'loss/train': 1.4282008409500122} 08/31/2021 09:37:18 - INFO - __main__ - Step 112567: {'lr': 7.485933991326546e-05, 'samples': 21612864, 'steps': 112566, 'loss/train': 1.5717920064926147} 08/31/2021 09:37:19 - INFO - __main__ - Step 112568: {'lr': 7.485555310819522e-05, 'samples': 21613056, 'steps': 112567, 'loss/train': 1.5383459329605103} 08/31/2021 09:37:21 - INFO - __main__ - Step 112569: {'lr': 7.485176638204239e-05, 'samples': 21613248, 'steps': 112568, 'loss/train': 1.355368971824646} 08/31/2021 09:37:21 - INFO - __main__ - Step 112570: {'lr': 7.484797973480865e-05, 'samples': 21613440, 'steps': 112569, 'loss/train': 1.0909385681152344} 08/31/2021 09:37:21 - INFO - __main__ - Step 112571: {'lr': 7.484419316649569e-05, 'samples': 21613632, 'steps': 112570, 'loss/train': 1.6208255290985107} 08/31/2021 09:37:22 - INFO - __main__ - Step 112572: {'lr': 7.484040667710523e-05, 'samples': 21613824, 'steps': 112571, 'loss/train': 0.9820172786712646} 08/31/2021 09:37:22 - INFO - __main__ - Step 112573: {'lr': 7.483662026663901e-05, 'samples': 21614016, 'steps': 112572, 'loss/train': 0.34860455989837646} 08/31/2021 09:37:24 - INFO - __main__ - Step 112574: {'lr': 7.483283393509869e-05, 'samples': 21614208, 'steps': 112573, 'loss/train': 1.0598925352096558} 08/31/2021 09:37:24 - INFO - __main__ - Step 112575: {'lr': 7.4829047682486e-05, 'samples': 21614400, 'steps': 112574, 'loss/train': 1.204391360282898} 08/31/2021 09:37:25 - INFO - __main__ - Step 112576: {'lr': 7.482526150880261e-05, 'samples': 21614592, 'steps': 112575, 'loss/train': 0.9902686476707458} 08/31/2021 09:37:25 - INFO - __main__ - Step 112577: {'lr': 7.482147541405035e-05, 'samples': 21614784, 'steps': 112576, 'loss/train': 0.8069724440574646} 08/31/2021 09:37:25 - INFO - __main__ - Step 112578: {'lr': 7.481768939823075e-05, 'samples': 21614976, 'steps': 112577, 'loss/train': 0.16095265746116638} 08/31/2021 09:37:26 - INFO - __main__ - Step 112579: {'lr': 7.481390346134562e-05, 'samples': 21615168, 'steps': 112578, 'loss/train': 1.0968385934829712} 08/31/2021 09:37:28 - INFO - __main__ - Step 112580: {'lr': 7.481011760339662e-05, 'samples': 21615360, 'steps': 112579, 'loss/train': 1.4367412328720093} 08/31/2021 09:37:28 - INFO - __main__ - Step 112581: {'lr': 7.480633182438548e-05, 'samples': 21615552, 'steps': 112580, 'loss/train': 1.4674264192581177} 08/31/2021 09:37:28 - INFO - __main__ - Step 112582: {'lr': 7.48025461243139e-05, 'samples': 21615744, 'steps': 112581, 'loss/train': 0.026397336274385452} 08/31/2021 09:37:29 - INFO - __main__ - Step 112583: {'lr': 7.479876050318358e-05, 'samples': 21615936, 'steps': 112582, 'loss/train': 1.9205597639083862} 08/31/2021 09:37:29 - INFO - __main__ - Step 112584: {'lr': 7.479497496099624e-05, 'samples': 21616128, 'steps': 112583, 'loss/train': 0.9909069538116455} 08/31/2021 09:37:31 - INFO - __main__ - Step 112585: {'lr': 7.47911894977536e-05, 'samples': 21616320, 'steps': 112584, 'loss/train': 0.8669241666793823} 08/31/2021 09:37:31 - INFO - __main__ - Step 112586: {'lr': 7.478740411345732e-05, 'samples': 21616512, 'steps': 112585, 'loss/train': 0.9322359561920166} 08/31/2021 09:37:32 - INFO - __main__ - Step 112587: {'lr': 7.478361880810924e-05, 'samples': 21616704, 'steps': 112586, 'loss/train': 0.9375137090682983} 08/31/2021 09:37:32 - INFO - __main__ - Step 112588: {'lr': 7.477983358171087e-05, 'samples': 21616896, 'steps': 112587, 'loss/train': 1.277728796005249} 08/31/2021 09:37:32 - INFO - __main__ - Step 112589: {'lr': 7.477604843426397e-05, 'samples': 21617088, 'steps': 112588, 'loss/train': 1.0024843215942383} 08/31/2021 09:37:34 - INFO - __main__ - Step 112590: {'lr': 7.477226336577031e-05, 'samples': 21617280, 'steps': 112589, 'loss/train': 1.4300463199615479} 08/31/2021 09:37:34 - INFO - __main__ - Step 112591: {'lr': 7.476847837623157e-05, 'samples': 21617472, 'steps': 112590, 'loss/train': 1.0664139986038208} 08/31/2021 09:37:35 - INFO - __main__ - Step 112592: {'lr': 7.476469346564942e-05, 'samples': 21617664, 'steps': 112591, 'loss/train': 1.8134807348251343} 08/31/2021 09:37:35 - INFO - __main__ - Step 112593: {'lr': 7.476090863402563e-05, 'samples': 21617856, 'steps': 112592, 'loss/train': 0.9649601578712463} 08/31/2021 09:37:35 - INFO - __main__ - Step 112594: {'lr': 7.475712388136185e-05, 'samples': 21618048, 'steps': 112593, 'loss/train': 1.8901817798614502} 08/31/2021 09:37:36 - INFO - __main__ - Step 112595: {'lr': 7.475333920765981e-05, 'samples': 21618240, 'steps': 112594, 'loss/train': 1.2069059610366821} 08/31/2021 09:37:37 - INFO - __main__ - Step 112596: {'lr': 7.474955461292121e-05, 'samples': 21618432, 'steps': 112595, 'loss/train': 0.7013829946517944} 08/31/2021 09:37:38 - INFO - __main__ - Step 112597: {'lr': 7.474577009714776e-05, 'samples': 21618624, 'steps': 112596, 'loss/train': 0.3514375686645508} 08/31/2021 09:37:38 - INFO - __main__ - Step 112598: {'lr': 7.474198566034124e-05, 'samples': 21618816, 'steps': 112597, 'loss/train': 1.0550400018692017} 08/31/2021 09:37:39 - INFO - __main__ - Step 112599: {'lr': 7.473820130250319e-05, 'samples': 21619008, 'steps': 112598, 'loss/train': 1.0347976684570312} 08/31/2021 09:37:39 - INFO - __main__ - Step 112600: {'lr': 7.473441702363542e-05, 'samples': 21619200, 'steps': 112599, 'loss/train': 1.4494884014129639} 08/31/2021 09:37:40 - INFO - __main__ - Step 112601: {'lr': 7.47306328237396e-05, 'samples': 21619392, 'steps': 112600, 'loss/train': 1.325371265411377} 08/31/2021 09:37:41 - INFO - __main__ - Step 112602: {'lr': 7.472684870281746e-05, 'samples': 21619584, 'steps': 112601, 'loss/train': 1.0825897455215454} 08/31/2021 09:37:41 - INFO - __main__ - Step 112603: {'lr': 7.47230646608707e-05, 'samples': 21619776, 'steps': 112602, 'loss/train': 1.1327481269836426} 08/31/2021 09:37:42 - INFO - __main__ - Step 112604: {'lr': 7.471928069790101e-05, 'samples': 21619968, 'steps': 112603, 'loss/train': 0.1183374896645546} 08/31/2021 09:37:42 - INFO - __main__ - Step 112605: {'lr': 7.47154968139101e-05, 'samples': 21620160, 'steps': 112604, 'loss/train': 1.2599211931228638} 08/31/2021 09:37:43 - INFO - __main__ - Step 112606: {'lr': 7.47117130088997e-05, 'samples': 21620352, 'steps': 112605, 'loss/train': 0.6976889371871948} 08/31/2021 09:37:44 - INFO - __main__ - Step 112607: {'lr': 7.470792928287151e-05, 'samples': 21620544, 'steps': 112606, 'loss/train': 0.8613412380218506} 08/31/2021 09:37:44 - INFO - __main__ - Step 112608: {'lr': 7.470414563582719e-05, 'samples': 21620736, 'steps': 112607, 'loss/train': 0.9787895679473877} 08/31/2021 09:37:44 - INFO - __main__ - Step 112609: {'lr': 7.470036206776859e-05, 'samples': 21620928, 'steps': 112608, 'loss/train': 1.2604838609695435} 08/31/2021 09:37:45 - INFO - __main__ - Step 112610: {'lr': 7.469657857869719e-05, 'samples': 21621120, 'steps': 112609, 'loss/train': 0.9142290949821472} 08/31/2021 09:37:46 - INFO - __main__ - Step 112611: {'lr': 7.469279516861483e-05, 'samples': 21621312, 'steps': 112610, 'loss/train': 1.0096863508224487} 08/31/2021 09:37:47 - INFO - __main__ - Step 112612: {'lr': 7.468901183752319e-05, 'samples': 21621504, 'steps': 112611, 'loss/train': 1.2485414743423462} 08/31/2021 09:37:47 - INFO - __main__ - Step 112613: {'lr': 7.468522858542395e-05, 'samples': 21621696, 'steps': 112612, 'loss/train': 0.8229047060012817} 08/31/2021 09:37:48 - INFO - __main__ - Step 112614: {'lr': 7.468144541231886e-05, 'samples': 21621888, 'steps': 112613, 'loss/train': 0.5669851303100586} 08/31/2021 09:37:48 - INFO - __main__ - Step 112615: {'lr': 7.46776623182096e-05, 'samples': 21622080, 'steps': 112614, 'loss/train': 1.5100613832473755} 08/31/2021 09:37:49 - INFO - __main__ - Step 112616: {'lr': 7.467387930309791e-05, 'samples': 21622272, 'steps': 112615, 'loss/train': 1.501620888710022} 08/31/2021 09:37:50 - INFO - __main__ - Step 112617: {'lr': 7.467009636698544e-05, 'samples': 21622464, 'steps': 112616, 'loss/train': 1.5857454538345337} 08/31/2021 09:37:50 - INFO - __main__ - Step 112618: {'lr': 7.466631350987391e-05, 'samples': 21622656, 'steps': 112617, 'loss/train': 1.3535327911376953} 08/31/2021 09:37:51 - INFO - __main__ - Step 112619: {'lr': 7.466253073176504e-05, 'samples': 21622848, 'steps': 112618, 'loss/train': 0.6965826749801636} 08/31/2021 09:37:51 - INFO - __main__ - Step 112620: {'lr': 7.465874803266062e-05, 'samples': 21623040, 'steps': 112619, 'loss/train': 0.7069566249847412} 08/31/2021 09:37:52 - INFO - __main__ - Step 112621: {'lr': 7.465496541256217e-05, 'samples': 21623232, 'steps': 112620, 'loss/train': 0.7738845944404602} 08/31/2021 09:37:53 - INFO - __main__ - Step 112622: {'lr': 7.465118287147149e-05, 'samples': 21623424, 'steps': 112621, 'loss/train': 1.080057978630066} 08/31/2021 09:37:53 - INFO - __main__ - Step 112623: {'lr': 7.464740040939027e-05, 'samples': 21623616, 'steps': 112622, 'loss/train': 1.295814871788025} 08/31/2021 09:37:54 - INFO - __main__ - Step 112624: {'lr': 7.464361802632025e-05, 'samples': 21623808, 'steps': 112623, 'loss/train': 1.065209150314331} 08/31/2021 09:37:54 - INFO - __main__ - Step 112625: {'lr': 7.46398357222631e-05, 'samples': 21624000, 'steps': 112624, 'loss/train': 1.3173884153366089} 08/31/2021 09:37:56 - INFO - __main__ - Step 112626: {'lr': 7.463605349722052e-05, 'samples': 21624192, 'steps': 112625, 'loss/train': 1.3095154762268066} 08/31/2021 09:37:56 - INFO - __main__ - Step 112627: {'lr': 7.463227135119424e-05, 'samples': 21624384, 'steps': 112626, 'loss/train': 1.2051137685775757} 08/31/2021 09:37:57 - INFO - __main__ - Step 112628: {'lr': 7.462848928418595e-05, 'samples': 21624576, 'steps': 112627, 'loss/train': 0.5851572155952454} 08/31/2021 09:37:57 - INFO - __main__ - Step 112629: {'lr': 7.462470729619736e-05, 'samples': 21624768, 'steps': 112628, 'loss/train': 1.3296748399734497} 08/31/2021 09:37:57 - INFO - __main__ - Step 112630: {'lr': 7.462092538723017e-05, 'samples': 21624960, 'steps': 112629, 'loss/train': 1.2882941961288452} 08/31/2021 09:37:59 - INFO - __main__ - Step 112631: {'lr': 7.461714355728607e-05, 'samples': 21625152, 'steps': 112630, 'loss/train': 1.1891525983810425} 08/31/2021 09:37:59 - INFO - __main__ - Step 112632: {'lr': 7.461336180636687e-05, 'samples': 21625344, 'steps': 112631, 'loss/train': 1.116857886314392} 08/31/2021 09:38:00 - INFO - __main__ - Step 112633: {'lr': 7.460958013447411e-05, 'samples': 21625536, 'steps': 112632, 'loss/train': 0.028817662969231606} 08/31/2021 09:38:00 - INFO - __main__ - Step 112634: {'lr': 7.460579854160957e-05, 'samples': 21625728, 'steps': 112633, 'loss/train': 1.5461503267288208} 08/31/2021 09:38:00 - INFO - __main__ - Step 112635: {'lr': 7.460201702777494e-05, 'samples': 21625920, 'steps': 112634, 'loss/train': 1.3550399541854858} 08/31/2021 09:38:01 - INFO - __main__ - Step 112636: {'lr': 7.459823559297194e-05, 'samples': 21626112, 'steps': 112635, 'loss/train': 1.5613794326782227} 08/31/2021 09:38:02 - INFO - __main__ - Step 112637: {'lr': 7.459445423720227e-05, 'samples': 21626304, 'steps': 112636, 'loss/train': 1.2467992305755615} 08/31/2021 09:38:03 - INFO - __main__ - Step 112638: {'lr': 7.459067296046761e-05, 'samples': 21626496, 'steps': 112637, 'loss/train': 1.0822376012802124} 08/31/2021 09:38:03 - INFO - __main__ - Step 112639: {'lr': 7.45868917627697e-05, 'samples': 21626688, 'steps': 112638, 'loss/train': 0.6966366767883301} 08/31/2021 09:38:04 - INFO - __main__ - Step 112640: {'lr': 7.458311064411025e-05, 'samples': 21626880, 'steps': 112639, 'loss/train': 1.1074885129928589} 08/31/2021 09:38:04 - INFO - __main__ - Step 112641: {'lr': 7.457932960449094e-05, 'samples': 21627072, 'steps': 112640, 'loss/train': 0.5347426533699036} 08/31/2021 09:38:06 - INFO - __main__ - Step 112642: {'lr': 7.457554864391345e-05, 'samples': 21627264, 'steps': 112641, 'loss/train': 0.32287243008613586} 08/31/2021 09:38:06 - INFO - __main__ - Step 112643: {'lr': 7.457176776237951e-05, 'samples': 21627456, 'steps': 112642, 'loss/train': 0.5578305721282959} 08/31/2021 09:38:06 - INFO - __main__ - Step 112644: {'lr': 7.456798695989084e-05, 'samples': 21627648, 'steps': 112643, 'loss/train': 1.2942477464675903} 08/31/2021 09:38:07 - INFO - __main__ - Step 112645: {'lr': 7.456420623644922e-05, 'samples': 21627840, 'steps': 112644, 'loss/train': 0.2931569516658783} 08/31/2021 09:38:07 - INFO - __main__ - Step 112646: {'lr': 7.456042559205616e-05, 'samples': 21628032, 'steps': 112645, 'loss/train': 1.0122159719467163} 08/31/2021 09:38:09 - INFO - __main__ - Step 112647: {'lr': 7.455664502671347e-05, 'samples': 21628224, 'steps': 112646, 'loss/train': 0.5168712139129639} 08/31/2021 09:38:09 - INFO - __main__ - Step 112648: {'lr': 7.455286454042284e-05, 'samples': 21628416, 'steps': 112647, 'loss/train': 1.0106022357940674} 08/31/2021 09:38:09 - INFO - __main__ - Step 112649: {'lr': 7.454908413318601e-05, 'samples': 21628608, 'steps': 112648, 'loss/train': 1.124375581741333} 08/31/2021 09:38:10 - INFO - __main__ - Step 112650: {'lr': 7.454530380500463e-05, 'samples': 21628800, 'steps': 112649, 'loss/train': 1.1206552982330322} 08/31/2021 09:38:10 - INFO - __main__ - Step 112651: {'lr': 7.454152355588046e-05, 'samples': 21628992, 'steps': 112650, 'loss/train': 1.4205607175827026} 08/31/2021 09:38:11 - INFO - __main__ - Step 112652: {'lr': 7.453774338581515e-05, 'samples': 21629184, 'steps': 112651, 'loss/train': 0.9289175271987915} 08/31/2021 09:38:12 - INFO - __main__ - Step 112653: {'lr': 7.453396329481041e-05, 'samples': 21629376, 'steps': 112652, 'loss/train': 1.2839324474334717} 08/31/2021 09:38:12 - INFO - __main__ - Step 112654: {'lr': 7.453018328286797e-05, 'samples': 21629568, 'steps': 112653, 'loss/train': 0.5610604286193848} 08/31/2021 09:38:13 - INFO - __main__ - Step 112655: {'lr': 7.452640334998953e-05, 'samples': 21629760, 'steps': 112654, 'loss/train': 1.2721437215805054} 08/31/2021 09:38:13 - INFO - __main__ - Step 112656: {'lr': 7.452262349617678e-05, 'samples': 21629952, 'steps': 112655, 'loss/train': 1.1999156475067139} 08/31/2021 09:38:15 - INFO - __main__ - Step 112657: {'lr': 7.451884372143145e-05, 'samples': 21630144, 'steps': 112656, 'loss/train': 0.692919135093689} 08/31/2021 09:38:15 - INFO - __main__ - Step 112658: {'lr': 7.451506402575517e-05, 'samples': 21630336, 'steps': 112657, 'loss/train': 1.099708914756775} 08/31/2021 09:38:16 - INFO - __main__ - Step 112659: {'lr': 7.451128440914981e-05, 'samples': 21630528, 'steps': 112658, 'loss/train': 0.7607504725456238} 08/31/2021 09:38:16 - INFO - __main__ - Step 112660: {'lr': 7.450750487161687e-05, 'samples': 21630720, 'steps': 112659, 'loss/train': 0.876316249370575} 08/31/2021 09:38:16 - INFO - __main__ - Step 112661: {'lr': 7.450372541315815e-05, 'samples': 21630912, 'steps': 112660, 'loss/train': 0.4218918979167938} 08/31/2021 09:38:17 - INFO - __main__ - Step 112662: {'lr': 7.449994603377533e-05, 'samples': 21631104, 'steps': 112661, 'loss/train': 0.7849047780036926} 08/31/2021 09:38:19 - INFO - __main__ - Step 112663: {'lr': 7.449616673347012e-05, 'samples': 21631296, 'steps': 112662, 'loss/train': 0.7825914025306702} 08/31/2021 09:38:20 - INFO - __main__ - Step 112664: {'lr': 7.449238751224425e-05, 'samples': 21631488, 'steps': 112663, 'loss/train': 1.2172280550003052} 08/31/2021 09:38:20 - INFO - __main__ - Step 112665: {'lr': 7.448860837009941e-05, 'samples': 21631680, 'steps': 112664, 'loss/train': 0.2763930559158325} 08/31/2021 09:38:20 - INFO - __main__ - Step 112666: {'lr': 7.448482930703725e-05, 'samples': 21631872, 'steps': 112665, 'loss/train': 0.2449391931295395} 08/31/2021 09:38:21 - INFO - __main__ - Step 112667: {'lr': 7.448105032305954e-05, 'samples': 21632064, 'steps': 112666, 'loss/train': 0.6016227006912231} 08/31/2021 09:38:21 - INFO - __main__ - Step 112668: {'lr': 7.447727141816798e-05, 'samples': 21632256, 'steps': 112667, 'loss/train': 1.6459873914718628} 08/31/2021 09:38:23 - INFO - __main__ - Step 112669: {'lr': 7.447349259236424e-05, 'samples': 21632448, 'steps': 112668, 'loss/train': 0.8313309550285339} 08/31/2021 09:38:23 - INFO - __main__ - Step 112670: {'lr': 7.446971384565004e-05, 'samples': 21632640, 'steps': 112669, 'loss/train': 1.591282606124878} 08/31/2021 09:38:23 - INFO - __main__ - Step 112671: {'lr': 7.446593517802707e-05, 'samples': 21632832, 'steps': 112670, 'loss/train': 1.6844396591186523} 08/31/2021 09:38:24 - INFO - __main__ - Step 112672: {'lr': 7.446215658949713e-05, 'samples': 21633024, 'steps': 112671, 'loss/train': 1.2301069498062134} 08/31/2021 09:38:24 - INFO - __main__ - Step 112673: {'lr': 7.445837808006172e-05, 'samples': 21633216, 'steps': 112672, 'loss/train': 0.9390774965286255} 08/31/2021 09:38:26 - INFO - __main__ - Step 112674: {'lr': 7.44545996497227e-05, 'samples': 21633408, 'steps': 112673, 'loss/train': 0.8252146244049072} 08/31/2021 09:38:26 - INFO - __main__ - Step 112675: {'lr': 7.445082129848172e-05, 'samples': 21633600, 'steps': 112674, 'loss/train': 1.1203564405441284} 08/31/2021 09:38:26 - INFO - __main__ - Step 112676: {'lr': 7.444704302634048e-05, 'samples': 21633792, 'steps': 112675, 'loss/train': 0.9132373929023743} 08/31/2021 09:38:27 - INFO - __main__ - Step 112677: {'lr': 7.44432648333007e-05, 'samples': 21633984, 'steps': 112676, 'loss/train': 1.4953913688659668} 08/31/2021 09:38:27 - INFO - __main__ - Step 112678: {'lr': 7.443948671936404e-05, 'samples': 21634176, 'steps': 112677, 'loss/train': 1.6843485832214355} 08/31/2021 09:38:29 - INFO - __main__ - Step 112679: {'lr': 7.443570868453228e-05, 'samples': 21634368, 'steps': 112678, 'loss/train': 1.4464002847671509} 08/31/2021 09:38:30 - INFO - __main__ - Step 112680: {'lr': 7.443193072880707e-05, 'samples': 21634560, 'steps': 112679, 'loss/train': 1.2331042289733887} 08/31/2021 09:38:30 - INFO - __main__ - Step 112681: {'lr': 7.442815285219012e-05, 'samples': 21634752, 'steps': 112680, 'loss/train': 1.0907680988311768} 08/31/2021 09:38:31 - INFO - __main__ - Step 112682: {'lr': 7.442437505468313e-05, 'samples': 21634944, 'steps': 112681, 'loss/train': 0.40045836567878723} 08/31/2021 09:38:31 - INFO - __main__ - Step 112683: {'lr': 7.442059733628784e-05, 'samples': 21635136, 'steps': 112682, 'loss/train': 1.2619000673294067} 08/31/2021 09:38:31 - INFO - __main__ - Step 112684: {'lr': 7.44168196970059e-05, 'samples': 21635328, 'steps': 112683, 'loss/train': 0.2714177370071411} 08/31/2021 09:38:33 - INFO - __main__ - Step 112685: {'lr': 7.4413042136839e-05, 'samples': 21635520, 'steps': 112684, 'loss/train': 1.3075404167175293} 08/31/2021 09:38:33 - INFO - __main__ - Step 112686: {'lr': 7.440926465578898e-05, 'samples': 21635712, 'steps': 112685, 'loss/train': 0.9469176530838013} 08/31/2021 09:38:34 - INFO - __main__ - Step 112687: {'lr': 7.440548725385737e-05, 'samples': 21635904, 'steps': 112686, 'loss/train': 0.12118696421384811} 08/31/2021 09:38:34 - INFO - __main__ - Step 112688: {'lr': 7.440170993104592e-05, 'samples': 21636096, 'steps': 112687, 'loss/train': 0.7125144600868225} 08/31/2021 09:38:34 - INFO - __main__ - Step 112689: {'lr': 7.439793268735634e-05, 'samples': 21636288, 'steps': 112688, 'loss/train': 1.6177115440368652} 08/31/2021 09:38:36 - INFO - __main__ - Step 112690: {'lr': 7.439415552279036e-05, 'samples': 21636480, 'steps': 112689, 'loss/train': 0.7384575605392456} 08/31/2021 09:38:36 - INFO - __main__ - Step 112691: {'lr': 7.439037843734967e-05, 'samples': 21636672, 'steps': 112690, 'loss/train': 0.8920885920524597} 08/31/2021 09:38:36 - INFO - __main__ - Step 112692: {'lr': 7.438660143103596e-05, 'samples': 21636864, 'steps': 112691, 'loss/train': 1.2676005363464355} 08/31/2021 09:38:37 - INFO - __main__ - Step 112693: {'lr': 7.438282450385092e-05, 'samples': 21637056, 'steps': 112692, 'loss/train': 1.7994660139083862} 08/31/2021 09:38:37 - INFO - __main__ - Step 112694: {'lr': 7.437904765579629e-05, 'samples': 21637248, 'steps': 112693, 'loss/train': 0.9094021320343018} 08/31/2021 09:38:39 - INFO - __main__ - Step 112695: {'lr': 7.437527088687374e-05, 'samples': 21637440, 'steps': 112694, 'loss/train': 1.9518171548843384} 08/31/2021 09:38:39 - INFO - __main__ - Step 112696: {'lr': 7.437149419708497e-05, 'samples': 21637632, 'steps': 112695, 'loss/train': 0.4469827711582184} 08/31/2021 09:38:40 - INFO - __main__ - Step 112697: {'lr': 7.436771758643174e-05, 'samples': 21637824, 'steps': 112696, 'loss/train': 0.9968483448028564} 08/31/2021 09:38:40 - INFO - __main__ - Step 112698: {'lr': 7.436394105491567e-05, 'samples': 21638016, 'steps': 112697, 'loss/train': 1.4367918968200684} 08/31/2021 09:38:40 - INFO - __main__ - Step 112699: {'lr': 7.436016460253858e-05, 'samples': 21638208, 'steps': 112698, 'loss/train': 0.6215283274650574} 08/31/2021 09:38:42 - INFO - __main__ - Step 112700: {'lr': 7.435638822930202e-05, 'samples': 21638400, 'steps': 112699, 'loss/train': 0.7181758880615234} 08/31/2021 09:38:43 - INFO - __main__ - Step 112701: {'lr': 7.435261193520773e-05, 'samples': 21638592, 'steps': 112700, 'loss/train': 0.15285305678844452} 08/31/2021 09:38:43 - INFO - __main__ - Step 112702: {'lr': 7.43488357202575e-05, 'samples': 21638784, 'steps': 112701, 'loss/train': 0.018395010381937027} 08/31/2021 09:38:43 - INFO - __main__ - Step 112703: {'lr': 7.434505958445293e-05, 'samples': 21638976, 'steps': 112702, 'loss/train': 0.8316817283630371} 08/31/2021 09:38:44 - INFO - __main__ - Step 112704: {'lr': 7.434128352779576e-05, 'samples': 21639168, 'steps': 112703, 'loss/train': 0.774811327457428} 08/31/2021 09:38:44 - INFO - __main__ - Step 112705: {'lr': 7.433750755028773e-05, 'samples': 21639360, 'steps': 112704, 'loss/train': 1.816055417060852} 08/31/2021 09:38:45 - INFO - __main__ - Step 112706: {'lr': 7.43337316519305e-05, 'samples': 21639552, 'steps': 112705, 'loss/train': 1.574009656906128} 08/31/2021 09:38:46 - INFO - __main__ - Step 112707: {'lr': 7.432995583272575e-05, 'samples': 21639744, 'steps': 112706, 'loss/train': 0.8318419456481934} 08/31/2021 09:38:46 - INFO - __main__ - Step 112708: {'lr': 7.432618009267525e-05, 'samples': 21639936, 'steps': 112707, 'loss/train': 0.9957628846168518} 08/31/2021 09:38:47 - INFO - __main__ - Step 112709: {'lr': 7.432240443178065e-05, 'samples': 21640128, 'steps': 112708, 'loss/train': 1.0121803283691406} 08/31/2021 09:38:47 - INFO - __main__ - Step 112710: {'lr': 7.431862885004364e-05, 'samples': 21640320, 'steps': 112709, 'loss/train': 1.1638169288635254} 08/31/2021 09:38:49 - INFO - __main__ - Step 112711: {'lr': 7.4314853347466e-05, 'samples': 21640512, 'steps': 112710, 'loss/train': 1.411747932434082} 08/31/2021 09:38:49 - INFO - __main__ - Step 112712: {'lr': 7.43110779240494e-05, 'samples': 21640704, 'steps': 112711, 'loss/train': 0.9756692051887512} 08/31/2021 09:38:50 - INFO - __main__ - Step 112713: {'lr': 7.430730257979545e-05, 'samples': 21640896, 'steps': 112712, 'loss/train': 1.083696722984314} 08/31/2021 09:38:50 - INFO - __main__ - Step 112714: {'lr': 7.430352731470593e-05, 'samples': 21641088, 'steps': 112713, 'loss/train': 0.5339193940162659} 08/31/2021 09:38:50 - INFO - __main__ - Step 112715: {'lr': 7.429975212878254e-05, 'samples': 21641280, 'steps': 112714, 'loss/train': 1.5905109643936157} 08/31/2021 09:38:51 - INFO - __main__ - Step 112716: {'lr': 7.429597702202695e-05, 'samples': 21641472, 'steps': 112715, 'loss/train': 1.7025471925735474} 08/31/2021 09:38:52 - INFO - __main__ - Step 112717: {'lr': 7.42922019944409e-05, 'samples': 21641664, 'steps': 112716, 'loss/train': 0.06290649622678757} 08/31/2021 09:38:53 - INFO - __main__ - Step 112718: {'lr': 7.428842704602604e-05, 'samples': 21641856, 'steps': 112717, 'loss/train': 1.3540741205215454} 08/31/2021 09:38:53 - INFO - __main__ - Step 112719: {'lr': 7.428465217678412e-05, 'samples': 21642048, 'steps': 112718, 'loss/train': 1.5147217512130737} 08/31/2021 09:38:54 - INFO - __main__ - Step 112720: {'lr': 7.428087738671686e-05, 'samples': 21642240, 'steps': 112719, 'loss/train': 1.5481587648391724} 08/31/2021 09:38:54 - INFO - __main__ - Step 112721: {'lr': 7.427710267582588e-05, 'samples': 21642432, 'steps': 112720, 'loss/train': 1.5897489786148071} 08/31/2021 09:38:55 - INFO - __main__ - Step 112722: {'lr': 7.427332804411294e-05, 'samples': 21642624, 'steps': 112721, 'loss/train': 0.755744993686676} 08/31/2021 09:38:56 - INFO - __main__ - Step 112723: {'lr': 7.426955349157971e-05, 'samples': 21642816, 'steps': 112722, 'loss/train': 1.4895168542861938} 08/31/2021 09:38:56 - INFO - __main__ - Step 112724: {'lr': 7.426577901822793e-05, 'samples': 21643008, 'steps': 112723, 'loss/train': 0.8593140840530396} 08/31/2021 09:38:56 - INFO - __main__ - Step 112725: {'lr': 7.426200462405928e-05, 'samples': 21643200, 'steps': 112724, 'loss/train': 0.8416417241096497} 08/31/2021 09:38:57 - INFO - __main__ - Step 112726: {'lr': 7.425823030907553e-05, 'samples': 21643392, 'steps': 112725, 'loss/train': 1.6853734254837036} 08/31/2021 09:38:58 - INFO - __main__ - Step 112727: {'lr': 7.425445607327822e-05, 'samples': 21643584, 'steps': 112726, 'loss/train': 0.9226836562156677} 08/31/2021 09:38:59 - INFO - __main__ - Step 112728: {'lr': 7.425068191666914e-05, 'samples': 21643776, 'steps': 112727, 'loss/train': 1.5037533044815063} 08/31/2021 09:38:59 - INFO - __main__ - Step 112729: {'lr': 7.424690783925e-05, 'samples': 21643968, 'steps': 112728, 'loss/train': 0.8782218098640442} 08/31/2021 09:39:00 - INFO - __main__ - Step 112730: {'lr': 7.424313384102252e-05, 'samples': 21644160, 'steps': 112729, 'loss/train': 0.9601317048072815} 08/31/2021 09:39:00 - INFO - __main__ - Step 112731: {'lr': 7.423935992198832e-05, 'samples': 21644352, 'steps': 112730, 'loss/train': 0.7252597808837891} 08/31/2021 09:39:02 - INFO - __main__ - Step 112732: {'lr': 7.42355860821492e-05, 'samples': 21644544, 'steps': 112731, 'loss/train': 0.8817030787467957} 08/31/2021 09:39:03 - INFO - __main__ - Step 112733: {'lr': 7.423181232150677e-05, 'samples': 21644736, 'steps': 112732, 'loss/train': 0.25366559624671936} 08/31/2021 09:39:03 - INFO - __main__ - Step 112734: {'lr': 7.422803864006281e-05, 'samples': 21644928, 'steps': 112733, 'loss/train': 1.6453639268875122} 08/31/2021 09:39:03 - INFO - __main__ - Step 112735: {'lr': 7.422426503781896e-05, 'samples': 21645120, 'steps': 112734, 'loss/train': 1.4295344352722168} 08/31/2021 09:39:04 - INFO - __main__ - Step 112736: {'lr': 7.422049151477695e-05, 'samples': 21645312, 'steps': 112735, 'loss/train': 1.6212201118469238} 08/31/2021 09:39:05 - INFO - __main__ - Step 112737: {'lr': 7.421671807093847e-05, 'samples': 21645504, 'steps': 112736, 'loss/train': 0.7546265125274658} 08/31/2021 09:39:06 - INFO - __main__ - Step 112738: {'lr': 7.421294470630524e-05, 'samples': 21645696, 'steps': 112737, 'loss/train': 1.2620984315872192} 08/31/2021 09:39:06 - INFO - __main__ - Step 112739: {'lr': 7.420917142087899e-05, 'samples': 21645888, 'steps': 112738, 'loss/train': 1.564412236213684} 08/31/2021 09:39:07 - INFO - __main__ - Step 112740: {'lr': 7.420539821466132e-05, 'samples': 21646080, 'steps': 112739, 'loss/train': 0.016141371801495552} 08/31/2021 09:39:07 - INFO - __main__ - Step 112741: {'lr': 7.420162508765399e-05, 'samples': 21646272, 'steps': 112740, 'loss/train': 0.49417024850845337} 08/31/2021 09:39:07 - INFO - __main__ - Step 112742: {'lr': 7.419785203985868e-05, 'samples': 21646464, 'steps': 112741, 'loss/train': 0.0510072186589241} 08/31/2021 09:39:09 - INFO - __main__ - Step 112743: {'lr': 7.419407907127712e-05, 'samples': 21646656, 'steps': 112742, 'loss/train': 1.3062350749969482} 08/31/2021 09:39:09 - INFO - __main__ - Step 112744: {'lr': 7.4190306181911e-05, 'samples': 21646848, 'steps': 112743, 'loss/train': 0.8745360374450684} 08/31/2021 09:39:10 - INFO - __main__ - Step 112745: {'lr': 7.418653337176198e-05, 'samples': 21647040, 'steps': 112744, 'loss/train': 0.9205976724624634} 08/31/2021 09:39:10 - INFO - __main__ - Step 112746: {'lr': 7.418276064083182e-05, 'samples': 21647232, 'steps': 112745, 'loss/train': 1.0360667705535889} 08/31/2021 09:39:11 - INFO - __main__ - Step 112747: {'lr': 7.41789879891222e-05, 'samples': 21647424, 'steps': 112746, 'loss/train': 0.025004465132951736} 08/31/2021 09:39:12 - INFO - __main__ - Step 112748: {'lr': 7.41752154166348e-05, 'samples': 21647616, 'steps': 112747, 'loss/train': 0.7149654626846313} 08/31/2021 09:39:13 - INFO - __main__ - Step 112749: {'lr': 7.417144292337135e-05, 'samples': 21647808, 'steps': 112748, 'loss/train': 1.082871913909912} 08/31/2021 09:39:13 - INFO - __main__ - Step 112750: {'lr': 7.416767050933354e-05, 'samples': 21648000, 'steps': 112749, 'loss/train': 0.8148054480552673} 08/31/2021 09:39:13 - INFO - __main__ - Step 112751: {'lr': 7.416389817452304e-05, 'samples': 21648192, 'steps': 112750, 'loss/train': 0.18748539686203003} 08/31/2021 09:39:14 - INFO - __main__ - Step 112752: {'lr': 7.416012591894158e-05, 'samples': 21648384, 'steps': 112751, 'loss/train': 1.4496865272521973} 08/31/2021 09:39:15 - INFO - __main__ - Step 112753: {'lr': 7.415635374259094e-05, 'samples': 21648576, 'steps': 112752, 'loss/train': 1.388620376586914} 08/31/2021 09:39:15 - INFO - __main__ - Step 112754: {'lr': 7.415258164547268e-05, 'samples': 21648768, 'steps': 112753, 'loss/train': 1.5262796878814697} 08/31/2021 09:39:16 - INFO - __main__ - Step 112755: {'lr': 7.414880962758849e-05, 'samples': 21648960, 'steps': 112754, 'loss/train': 1.4811058044433594} 08/31/2021 09:39:16 - INFO - __main__ - Step 112756: {'lr': 7.414503768894019e-05, 'samples': 21649152, 'steps': 112755, 'loss/train': 2.011141777038574} 08/31/2021 09:39:16 - INFO - __main__ - Step 112757: {'lr': 7.41412658295294e-05, 'samples': 21649344, 'steps': 112756, 'loss/train': 1.2917065620422363} 08/31/2021 09:39:18 - INFO - __main__ - Step 112758: {'lr': 7.413749404935785e-05, 'samples': 21649536, 'steps': 112757, 'loss/train': 1.1417765617370605} 08/31/2021 09:39:18 - INFO - __main__ - Step 112759: {'lr': 7.413372234842722e-05, 'samples': 21649728, 'steps': 112758, 'loss/train': 0.3052578866481781} 08/31/2021 09:39:19 - INFO - __main__ - Step 112760: {'lr': 7.412995072673923e-05, 'samples': 21649920, 'steps': 112759, 'loss/train': 1.4704293012619019} 08/31/2021 09:39:19 - INFO - __main__ - Step 112761: {'lr': 7.412617918429556e-05, 'samples': 21650112, 'steps': 112760, 'loss/train': 1.1208739280700684} 08/31/2021 09:39:19 - INFO - __main__ - Step 112762: {'lr': 7.412240772109794e-05, 'samples': 21650304, 'steps': 112761, 'loss/train': 0.9384480118751526} 08/31/2021 09:39:21 - INFO - __main__ - Step 112763: {'lr': 7.411863633714802e-05, 'samples': 21650496, 'steps': 112762, 'loss/train': 1.0080554485321045} 08/31/2021 09:39:22 - INFO - __main__ - Step 112764: {'lr': 7.411486503244754e-05, 'samples': 21650688, 'steps': 112763, 'loss/train': 0.9052693247795105} 08/31/2021 09:39:22 - INFO - __main__ - Step 112765: {'lr': 7.411109380699818e-05, 'samples': 21650880, 'steps': 112764, 'loss/train': 0.13734638690948486} 08/31/2021 09:39:22 - INFO - __main__ - Step 112766: {'lr': 7.410732266080175e-05, 'samples': 21651072, 'steps': 112765, 'loss/train': 0.8806858658790588} 08/31/2021 09:39:23 - INFO - __main__ - Step 112767: {'lr': 7.410355159385976e-05, 'samples': 21651264, 'steps': 112766, 'loss/train': 0.7308917045593262} 08/31/2021 09:39:23 - INFO - __main__ - Step 112768: {'lr': 7.409978060617398e-05, 'samples': 21651456, 'steps': 112767, 'loss/train': 0.4318389892578125} 08/31/2021 09:39:24 - INFO - __main__ - Step 112769: {'lr': 7.409600969774614e-05, 'samples': 21651648, 'steps': 112768, 'loss/train': 1.273587703704834} 08/31/2021 09:39:25 - INFO - __main__ - Step 112770: {'lr': 7.409223886857791e-05, 'samples': 21651840, 'steps': 112769, 'loss/train': 0.09330614656209946} 08/31/2021 09:39:25 - INFO - __main__ - Step 112771: {'lr': 7.408846811867101e-05, 'samples': 21652032, 'steps': 112770, 'loss/train': 0.7728074789047241} 08/31/2021 09:39:26 - INFO - __main__ - Step 112772: {'lr': 7.408469744802715e-05, 'samples': 21652224, 'steps': 112771, 'loss/train': 1.3597638607025146} 08/31/2021 09:39:26 - INFO - __main__ - Step 112773: {'lr': 7.4080926856648e-05, 'samples': 21652416, 'steps': 112772, 'loss/train': 0.8303225040435791} 08/31/2021 09:39:28 - INFO - __main__ - Step 112774: {'lr': 7.407715634453523e-05, 'samples': 21652608, 'steps': 112773, 'loss/train': 1.4506152868270874} 08/31/2021 09:39:28 - INFO - __main__ - Step 112775: {'lr': 7.407338591169063e-05, 'samples': 21652800, 'steps': 112774, 'loss/train': 1.2124427556991577} 08/31/2021 09:39:29 - INFO - __main__ - Step 112776: {'lr': 7.406961555811584e-05, 'samples': 21652992, 'steps': 112775, 'loss/train': 0.14544406533241272} 08/31/2021 09:39:29 - INFO - __main__ - Step 112777: {'lr': 7.406584528381255e-05, 'samples': 21653184, 'steps': 112776, 'loss/train': 1.2994167804718018} 08/31/2021 09:39:29 - INFO - __main__ - Step 112778: {'lr': 7.406207508878249e-05, 'samples': 21653376, 'steps': 112777, 'loss/train': 0.6746587157249451} 08/31/2021 09:39:31 - INFO - __main__ - Step 112779: {'lr': 7.405830497302732e-05, 'samples': 21653568, 'steps': 112778, 'loss/train': 1.75380277633667} 08/31/2021 09:39:31 - INFO - __main__ - Step 112780: {'lr': 7.405453493654887e-05, 'samples': 21653760, 'steps': 112779, 'loss/train': 1.25285005569458} 08/31/2021 09:39:32 - INFO - __main__ - Step 112781: {'lr': 7.405076497934862e-05, 'samples': 21653952, 'steps': 112780, 'loss/train': 0.6242883205413818} 08/31/2021 09:39:32 - INFO - __main__ - Step 112782: {'lr': 7.40469951014284e-05, 'samples': 21654144, 'steps': 112781, 'loss/train': 1.2076550722122192} 08/31/2021 09:39:32 - INFO - __main__ - Step 112783: {'lr': 7.40432253027899e-05, 'samples': 21654336, 'steps': 112782, 'loss/train': 0.958267331123352} 08/31/2021 09:39:33 - INFO - __main__ - Step 112784: {'lr': 7.40394555834348e-05, 'samples': 21654528, 'steps': 112783, 'loss/train': 1.5001360177993774} 08/31/2021 09:39:34 - INFO - __main__ - Step 112785: {'lr': 7.403568594336479e-05, 'samples': 21654720, 'steps': 112784, 'loss/train': 0.7956952452659607} 08/31/2021 09:39:35 - INFO - __main__ - Step 112786: {'lr': 7.403191638258162e-05, 'samples': 21654912, 'steps': 112785, 'loss/train': 0.7478289008140564} 08/31/2021 09:39:35 - INFO - __main__ - Step 112787: {'lr': 7.402814690108692e-05, 'samples': 21655104, 'steps': 112786, 'loss/train': 0.6343352794647217} 08/31/2021 09:39:36 - INFO - __main__ - Step 112788: {'lr': 7.402437749888244e-05, 'samples': 21655296, 'steps': 112787, 'loss/train': 1.1472066640853882} 08/31/2021 09:39:36 - INFO - __main__ - Step 112789: {'lr': 7.402060817596984e-05, 'samples': 21655488, 'steps': 112788, 'loss/train': 1.1228855848312378} 08/31/2021 09:39:38 - INFO - __main__ - Step 112790: {'lr': 7.401683893235084e-05, 'samples': 21655680, 'steps': 112789, 'loss/train': 0.08047867566347122} 08/31/2021 09:39:38 - INFO - __main__ - Step 112791: {'lr': 7.401306976802716e-05, 'samples': 21655872, 'steps': 112790, 'loss/train': 1.25461745262146} 08/31/2021 09:39:39 - INFO - __main__ - Step 112792: {'lr': 7.400930068300046e-05, 'samples': 21656064, 'steps': 112791, 'loss/train': 1.3489617109298706} 08/31/2021 09:39:39 - INFO - __main__ - Step 112793: {'lr': 7.400553167727253e-05, 'samples': 21656256, 'steps': 112792, 'loss/train': 0.8877037167549133} 08/31/2021 09:39:39 - INFO - __main__ - Step 112794: {'lr': 7.400176275084492e-05, 'samples': 21656448, 'steps': 112793, 'loss/train': 0.86552494764328} 08/31/2021 09:39:41 - INFO - __main__ - Step 112795: {'lr': 7.39979939037194e-05, 'samples': 21656640, 'steps': 112794, 'loss/train': 1.1530988216400146} 08/31/2021 09:39:41 - INFO - __main__ - Step 112796: {'lr': 7.399422513589765e-05, 'samples': 21656832, 'steps': 112795, 'loss/train': 0.289623886346817} 08/31/2021 09:39:42 - INFO - __main__ - Step 112797: {'lr': 7.399045644738143e-05, 'samples': 21657024, 'steps': 112796, 'loss/train': 1.3357982635498047} 08/31/2021 09:39:42 - INFO - __main__ - Step 112798: {'lr': 7.398668783817236e-05, 'samples': 21657216, 'steps': 112797, 'loss/train': 0.9503690600395203} 08/31/2021 09:39:42 - INFO - __main__ - Step 112799: {'lr': 7.398291930827216e-05, 'samples': 21657408, 'steps': 112798, 'loss/train': 1.1545844078063965} 08/31/2021 09:39:44 - INFO - __main__ - Step 112800: {'lr': 7.397915085768257e-05, 'samples': 21657600, 'steps': 112799, 'loss/train': 1.4561817646026611} 08/31/2021 09:39:44 - INFO - __main__ - Step 112801: {'lr': 7.397538248640526e-05, 'samples': 21657792, 'steps': 112800, 'loss/train': 1.3920236825942993} 08/31/2021 09:39:45 - INFO - __main__ - Step 112802: {'lr': 7.39716141944419e-05, 'samples': 21657984, 'steps': 112801, 'loss/train': 1.49203360080719} 08/31/2021 09:39:45 - INFO - __main__ - Step 112803: {'lr': 7.396784598179424e-05, 'samples': 21658176, 'steps': 112802, 'loss/train': 1.126312017440796} 08/31/2021 09:39:45 - INFO - __main__ - Step 112804: {'lr': 7.396407784846393e-05, 'samples': 21658368, 'steps': 112803, 'loss/train': 3.342405319213867} 08/31/2021 09:39:46 - INFO - __main__ - Step 112805: {'lr': 7.396030979445271e-05, 'samples': 21658560, 'steps': 112804, 'loss/train': 1.1728980541229248} 08/31/2021 09:39:47 - INFO - __main__ - Step 112806: {'lr': 7.395654181976224e-05, 'samples': 21658752, 'steps': 112805, 'loss/train': 1.115139365196228} 08/31/2021 09:39:48 - INFO - __main__ - Step 112807: {'lr': 7.395277392439431e-05, 'samples': 21658944, 'steps': 112806, 'loss/train': 1.1693627834320068} 08/31/2021 09:39:48 - INFO - __main__ - Step 112808: {'lr': 7.394900610835049e-05, 'samples': 21659136, 'steps': 112807, 'loss/train': 1.1248260736465454} 08/31/2021 09:39:48 - INFO - __main__ - Step 112809: {'lr': 7.394523837163253e-05, 'samples': 21659328, 'steps': 112808, 'loss/train': 1.235715627670288} 08/31/2021 09:39:49 - INFO - __main__ - Step 112810: {'lr': 7.39414707142421e-05, 'samples': 21659520, 'steps': 112809, 'loss/train': 1.6640130281448364} 08/31/2021 09:39:50 - INFO - __main__ - Step 112811: {'lr': 7.393770313618095e-05, 'samples': 21659712, 'steps': 112810, 'loss/train': 0.18966707587242126} 08/31/2021 09:39:51 - INFO - __main__ - Step 112812: {'lr': 7.393393563745073e-05, 'samples': 21659904, 'steps': 112811, 'loss/train': 1.1252787113189697} 08/31/2021 09:39:51 - INFO - __main__ - Step 112813: {'lr': 7.393016821805321e-05, 'samples': 21660096, 'steps': 112812, 'loss/train': 1.1272251605987549} 08/31/2021 09:39:51 - INFO - __main__ - Step 112814: {'lr': 7.392640087798999e-05, 'samples': 21660288, 'steps': 112813, 'loss/train': 1.2192485332489014} 08/31/2021 09:39:52 - INFO - __main__ - Step 112815: {'lr': 7.392263361726284e-05, 'samples': 21660480, 'steps': 112814, 'loss/train': 1.7419993877410889} 08/31/2021 09:39:53 - INFO - __main__ - Step 112816: {'lr': 7.391886643587343e-05, 'samples': 21660672, 'steps': 112815, 'loss/train': 1.0854517221450806} 08/31/2021 09:39:54 - INFO - __main__ - Step 112817: {'lr': 7.391509933382346e-05, 'samples': 21660864, 'steps': 112816, 'loss/train': 0.7709357142448425} 08/31/2021 09:39:54 - INFO - __main__ - Step 112818: {'lr': 7.391133231111464e-05, 'samples': 21661056, 'steps': 112817, 'loss/train': 1.1798382997512817} 08/31/2021 09:39:54 - INFO - __main__ - Step 112819: {'lr': 7.390756536774865e-05, 'samples': 21661248, 'steps': 112818, 'loss/train': 0.85503751039505} 08/31/2021 09:39:55 - INFO - __main__ - Step 112820: {'lr': 7.390379850372728e-05, 'samples': 21661440, 'steps': 112819, 'loss/train': 0.820107638835907} 08/31/2021 09:39:55 - INFO - __main__ - Step 112821: {'lr': 7.390003171905205e-05, 'samples': 21661632, 'steps': 112820, 'loss/train': 0.9454923868179321} 08/31/2021 09:39:57 - INFO - __main__ - Step 112822: {'lr': 7.389626501372474e-05, 'samples': 21661824, 'steps': 112821, 'loss/train': 1.1575806140899658} 08/31/2021 09:39:57 - INFO - __main__ - Step 112823: {'lr': 7.389249838774706e-05, 'samples': 21662016, 'steps': 112822, 'loss/train': 1.3386094570159912} 08/31/2021 09:39:57 - INFO - __main__ - Step 112824: {'lr': 7.388873184112071e-05, 'samples': 21662208, 'steps': 112823, 'loss/train': 1.0386189222335815} 08/31/2021 09:39:58 - INFO - __main__ - Step 112825: {'lr': 7.388496537384736e-05, 'samples': 21662400, 'steps': 112824, 'loss/train': 0.5350645184516907} 08/31/2021 09:39:58 - INFO - __main__ - Step 112826: {'lr': 7.388119898592876e-05, 'samples': 21662592, 'steps': 112825, 'loss/train': 1.0465939044952393} 08/31/2021 09:40:00 - INFO - __main__ - Step 112827: {'lr': 7.387743267736658e-05, 'samples': 21662784, 'steps': 112826, 'loss/train': 0.7935733199119568} 08/31/2021 09:40:00 - INFO - __main__ - Step 112828: {'lr': 7.387366644816249e-05, 'samples': 21662976, 'steps': 112827, 'loss/train': 1.1894521713256836} 08/31/2021 09:40:01 - INFO - __main__ - Step 112829: {'lr': 7.386990029831819e-05, 'samples': 21663168, 'steps': 112828, 'loss/train': 1.4862412214279175} 08/31/2021 09:40:01 - INFO - __main__ - Step 112830: {'lr': 7.386613422783542e-05, 'samples': 21663360, 'steps': 112829, 'loss/train': 0.49364173412323} 08/31/2021 09:40:01 - INFO - __main__ - Step 112831: {'lr': 7.386236823671585e-05, 'samples': 21663552, 'steps': 112830, 'loss/train': 1.2763121128082275} 08/31/2021 09:40:03 - INFO - __main__ - Step 112832: {'lr': 7.385860232496117e-05, 'samples': 21663744, 'steps': 112831, 'loss/train': 0.18423917889595032} 08/31/2021 09:40:03 - INFO - __main__ - Step 112833: {'lr': 7.385483649257318e-05, 'samples': 21663936, 'steps': 112832, 'loss/train': 0.762191653251648} 08/31/2021 09:40:04 - INFO - __main__ - Step 112834: {'lr': 7.385107073955338e-05, 'samples': 21664128, 'steps': 112833, 'loss/train': 0.8901844620704651} 08/31/2021 09:40:04 - INFO - __main__ - Step 112835: {'lr': 7.38473050659036e-05, 'samples': 21664320, 'steps': 112834, 'loss/train': 0.5789873003959656} 08/31/2021 09:40:04 - INFO - __main__ - Step 112836: {'lr': 7.384353947162547e-05, 'samples': 21664512, 'steps': 112835, 'loss/train': 0.1573745161294937} 08/31/2021 09:40:06 - INFO - __main__ - Step 112837: {'lr': 7.383977395672076e-05, 'samples': 21664704, 'steps': 112836, 'loss/train': 1.0440603494644165} 08/31/2021 09:40:06 - INFO - __main__ - Step 112838: {'lr': 7.38360085211911e-05, 'samples': 21664896, 'steps': 112837, 'loss/train': 2.111469030380249} 08/31/2021 09:40:07 - INFO - __main__ - Step 112839: {'lr': 7.383224316503823e-05, 'samples': 21665088, 'steps': 112838, 'loss/train': 0.9121952652931213} 08/31/2021 09:40:07 - INFO - __main__ - Step 112840: {'lr': 7.382847788826383e-05, 'samples': 21665280, 'steps': 112839, 'loss/train': 0.8931906819343567} 08/31/2021 09:40:07 - INFO - __main__ - Step 112841: {'lr': 7.38247126908696e-05, 'samples': 21665472, 'steps': 112840, 'loss/train': 1.4828879833221436} 08/31/2021 09:40:09 - INFO - __main__ - Step 112842: {'lr': 7.382094757285724e-05, 'samples': 21665664, 'steps': 112841, 'loss/train': 1.0837879180908203} 08/31/2021 09:40:10 - INFO - __main__ - Step 112843: {'lr': 7.381718253422842e-05, 'samples': 21665856, 'steps': 112842, 'loss/train': 1.889121174812317} 08/31/2021 09:40:10 - INFO - __main__ - Step 112844: {'lr': 7.381341757498489e-05, 'samples': 21666048, 'steps': 112843, 'loss/train': 1.104874849319458} 08/31/2021 09:40:10 - INFO - __main__ - Step 112845: {'lr': 7.380965269512837e-05, 'samples': 21666240, 'steps': 112844, 'loss/train': 1.4567219018936157} 08/31/2021 09:40:11 - INFO - __main__ - Step 112846: {'lr': 7.380588789466044e-05, 'samples': 21666432, 'steps': 112845, 'loss/train': 0.8308014869689941} 08/31/2021 09:40:12 - INFO - __main__ - Step 112847: {'lr': 7.380212317358287e-05, 'samples': 21666624, 'steps': 112846, 'loss/train': 0.9775628447532654} 08/31/2021 09:40:13 - INFO - __main__ - Step 112848: {'lr': 7.379835853189731e-05, 'samples': 21666816, 'steps': 112847, 'loss/train': 0.4282037913799286} 08/31/2021 09:40:13 - INFO - __main__ - Step 112849: {'lr': 7.379459396960551e-05, 'samples': 21667008, 'steps': 112848, 'loss/train': 0.9635957479476929} 08/31/2021 09:40:14 - INFO - __main__ - Step 112850: {'lr': 7.379082948670915e-05, 'samples': 21667200, 'steps': 112849, 'loss/train': 0.8545221090316772} 08/31/2021 09:40:14 - INFO - __main__ - Step 112851: {'lr': 7.378706508320993e-05, 'samples': 21667392, 'steps': 112850, 'loss/train': 0.04442526400089264} 08/31/2021 09:40:14 - INFO - __main__ - Step 112852: {'lr': 7.378330075910949e-05, 'samples': 21667584, 'steps': 112851, 'loss/train': 0.5672615170478821} 08/31/2021 09:40:16 - INFO - __main__ - Step 112853: {'lr': 7.377953651440964e-05, 'samples': 21667776, 'steps': 112852, 'loss/train': 1.5746814012527466} 08/31/2021 09:40:16 - INFO - __main__ - Step 112854: {'lr': 7.377577234911198e-05, 'samples': 21667968, 'steps': 112853, 'loss/train': 1.2093350887298584} 08/31/2021 09:40:17 - INFO - __main__ - Step 112855: {'lr': 7.377200826321823e-05, 'samples': 21668160, 'steps': 112854, 'loss/train': 0.7595457434654236} 08/31/2021 09:40:17 - INFO - __main__ - Step 112856: {'lr': 7.376824425673017e-05, 'samples': 21668352, 'steps': 112855, 'loss/train': 1.0727633237838745} 08/31/2021 09:40:17 - INFO - __main__ - Step 112857: {'lr': 7.376448032964938e-05, 'samples': 21668544, 'steps': 112856, 'loss/train': 1.2909231185913086} 08/31/2021 09:40:19 - INFO - __main__ - Step 112858: {'lr': 7.376071648197757e-05, 'samples': 21668736, 'steps': 112857, 'loss/train': 1.3923556804656982} 08/31/2021 09:40:19 - INFO - __main__ - Step 112859: {'lr': 7.375695271371646e-05, 'samples': 21668928, 'steps': 112858, 'loss/train': 0.5303052663803101} 08/31/2021 09:40:20 - INFO - __main__ - Step 112860: {'lr': 7.375318902486775e-05, 'samples': 21669120, 'steps': 112859, 'loss/train': 0.9724161624908447} 08/31/2021 09:40:20 - INFO - __main__ - Step 112861: {'lr': 7.374942541543315e-05, 'samples': 21669312, 'steps': 112860, 'loss/train': 1.3932608366012573} 08/31/2021 09:40:20 - INFO - __main__ - Step 112862: {'lr': 7.37456618854143e-05, 'samples': 21669504, 'steps': 112861, 'loss/train': 0.6334184408187866} 08/31/2021 09:40:22 - INFO - __main__ - Step 112863: {'lr': 7.374189843481297e-05, 'samples': 21669696, 'steps': 112862, 'loss/train': 1.0226871967315674} 08/31/2021 09:40:22 - INFO - __main__ - Step 112864: {'lr': 7.37381350636308e-05, 'samples': 21669888, 'steps': 112863, 'loss/train': 0.30756622552871704} 08/31/2021 09:40:23 - INFO - __main__ - Step 112865: {'lr': 7.373437177186951e-05, 'samples': 21670080, 'steps': 112864, 'loss/train': 0.8125219345092773} 08/31/2021 09:40:23 - INFO - __main__ - Step 112866: {'lr': 7.373060855953079e-05, 'samples': 21670272, 'steps': 112865, 'loss/train': 1.036686897277832} 08/31/2021 09:40:23 - INFO - __main__ - Step 112867: {'lr': 7.372684542661643e-05, 'samples': 21670464, 'steps': 112866, 'loss/train': 1.646949052810669} 08/31/2021 09:40:25 - INFO - __main__ - Step 112868: {'lr': 7.372308237312794e-05, 'samples': 21670656, 'steps': 112867, 'loss/train': 1.1314531564712524} 08/31/2021 09:40:25 - INFO - __main__ - Step 112869: {'lr': 7.371931939906712e-05, 'samples': 21670848, 'steps': 112868, 'loss/train': 1.2224854230880737} 08/31/2021 09:40:26 - INFO - __main__ - Step 112870: {'lr': 7.371555650443565e-05, 'samples': 21671040, 'steps': 112869, 'loss/train': 0.6371505260467529} 08/31/2021 09:40:26 - INFO - __main__ - Step 112871: {'lr': 7.371179368923522e-05, 'samples': 21671232, 'steps': 112870, 'loss/train': 1.1676771640777588} 08/31/2021 09:40:26 - INFO - __main__ - Step 112872: {'lr': 7.370803095346757e-05, 'samples': 21671424, 'steps': 112871, 'loss/train': 0.2533798813819885} 08/31/2021 09:40:28 - INFO - __main__ - Step 112873: {'lr': 7.370426829713433e-05, 'samples': 21671616, 'steps': 112872, 'loss/train': 1.3868194818496704} 08/31/2021 09:40:28 - INFO - __main__ - Step 112874: {'lr': 7.370050572023723e-05, 'samples': 21671808, 'steps': 112873, 'loss/train': 0.7307546734809875} 08/31/2021 09:40:29 - INFO - __main__ - Step 112875: {'lr': 7.369674322277798e-05, 'samples': 21672000, 'steps': 112874, 'loss/train': 1.1652441024780273} 08/31/2021 09:40:29 - INFO - __main__ - Step 112876: {'lr': 7.369298080475822e-05, 'samples': 21672192, 'steps': 112875, 'loss/train': 0.9044557213783264} 08/31/2021 09:40:29 - INFO - __main__ - Step 112877: {'lr': 7.368921846617971e-05, 'samples': 21672384, 'steps': 112876, 'loss/train': 0.747924268245697} 08/31/2021 09:40:31 - INFO - __main__ - Step 112878: {'lr': 7.36854562070442e-05, 'samples': 21672576, 'steps': 112877, 'loss/train': 0.45575305819511414} 08/31/2021 09:40:31 - INFO - __main__ - Step 112879: {'lr': 7.368169402735322e-05, 'samples': 21672768, 'steps': 112878, 'loss/train': 0.9026973247528076} 08/31/2021 09:40:32 - INFO - __main__ - Step 112880: {'lr': 7.367793192710853e-05, 'samples': 21672960, 'steps': 112879, 'loss/train': 1.1554079055786133} 08/31/2021 09:40:32 - INFO - __main__ - Step 112881: {'lr': 7.367416990631187e-05, 'samples': 21673152, 'steps': 112880, 'loss/train': 0.2542741000652313} 08/31/2021 09:40:32 - INFO - __main__ - Step 112882: {'lr': 7.367040796496487e-05, 'samples': 21673344, 'steps': 112881, 'loss/train': 1.153125524520874} 08/31/2021 09:40:34 - INFO - __main__ - Step 112883: {'lr': 7.36666461030693e-05, 'samples': 21673536, 'steps': 112882, 'loss/train': 1.472239375114441} 08/31/2021 09:40:35 - INFO - __main__ - Step 112884: {'lr': 7.366288432062682e-05, 'samples': 21673728, 'steps': 112883, 'loss/train': 0.9304249286651611} 08/31/2021 09:40:35 - INFO - __main__ - Step 112885: {'lr': 7.36591226176391e-05, 'samples': 21673920, 'steps': 112884, 'loss/train': 2.150686740875244} 08/31/2021 09:40:35 - INFO - __main__ - Step 112886: {'lr': 7.365536099410786e-05, 'samples': 21674112, 'steps': 112885, 'loss/train': 0.9859259724617004} 08/31/2021 09:40:36 - INFO - __main__ - Step 112887: {'lr': 7.365159945003481e-05, 'samples': 21674304, 'steps': 112886, 'loss/train': 1.7377269268035889} 08/31/2021 09:40:37 - INFO - __main__ - Step 112888: {'lr': 7.36478379854216e-05, 'samples': 21674496, 'steps': 112887, 'loss/train': 1.1051920652389526} 08/31/2021 09:40:38 - INFO - __main__ - Step 112889: {'lr': 7.364407660027006e-05, 'samples': 21674688, 'steps': 112888, 'loss/train': 1.2017807960510254} 08/31/2021 09:40:38 - INFO - __main__ - Step 112890: {'lr': 7.364031529458171e-05, 'samples': 21674880, 'steps': 112889, 'loss/train': 1.2690238952636719} 08/31/2021 09:40:38 - INFO - __main__ - Step 112891: {'lr': 7.363655406835829e-05, 'samples': 21675072, 'steps': 112890, 'loss/train': 1.1092015504837036} 08/31/2021 09:40:39 - INFO - __main__ - Step 112892: {'lr': 7.36327929216015e-05, 'samples': 21675264, 'steps': 112891, 'loss/train': 1.2315824031829834} 08/31/2021 09:40:40 - INFO - __main__ - Step 112893: {'lr': 7.362903185431307e-05, 'samples': 21675456, 'steps': 112892, 'loss/train': 0.0442684032022953} 08/31/2021 09:40:41 - INFO - __main__ - Step 112894: {'lr': 7.362527086649468e-05, 'samples': 21675648, 'steps': 112893, 'loss/train': 1.1168397665023804} 08/31/2021 09:40:41 - INFO - __main__ - Step 112895: {'lr': 7.362150995814801e-05, 'samples': 21675840, 'steps': 112894, 'loss/train': 1.2283082008361816} 08/31/2021 09:40:41 - INFO - __main__ - Step 112896: {'lr': 7.361774912927479e-05, 'samples': 21676032, 'steps': 112895, 'loss/train': 0.5375896096229553} 08/31/2021 09:40:42 - INFO - __main__ - Step 112897: {'lr': 7.361398837987668e-05, 'samples': 21676224, 'steps': 112896, 'loss/train': 5.720258712768555} 08/31/2021 09:40:42 - INFO - __main__ - Step 112898: {'lr': 7.361022770995538e-05, 'samples': 21676416, 'steps': 112897, 'loss/train': 0.4486212432384491} 08/31/2021 09:40:44 - INFO - __main__ - Step 112899: {'lr': 7.360646711951257e-05, 'samples': 21676608, 'steps': 112898, 'loss/train': 2.327831268310547} 08/31/2021 09:40:45 - INFO - __main__ - Step 112900: {'lr': 7.360270660855001e-05, 'samples': 21676800, 'steps': 112899, 'loss/train': 1.0146931409835815} 08/31/2021 09:40:45 - INFO - __main__ - Step 112901: {'lr': 7.359894617706939e-05, 'samples': 21676992, 'steps': 112900, 'loss/train': 0.8563024997711182} 08/31/2021 09:40:45 - INFO - __main__ - Step 112902: {'lr': 7.359518582507229e-05, 'samples': 21677184, 'steps': 112901, 'loss/train': 0.17027029395103455} 08/31/2021 09:40:46 - INFO - __main__ - Step 112903: {'lr': 7.359142555256048e-05, 'samples': 21677376, 'steps': 112902, 'loss/train': 1.6407285928726196} 08/31/2021 09:40:47 - INFO - __main__ - Step 112904: {'lr': 7.358766535953565e-05, 'samples': 21677568, 'steps': 112903, 'loss/train': 0.9012745022773743} 08/31/2021 09:40:48 - INFO - __main__ - Step 112905: {'lr': 7.35839052459995e-05, 'samples': 21677760, 'steps': 112904, 'loss/train': 1.2021749019622803} 08/31/2021 09:40:48 - INFO - __main__ - Step 112906: {'lr': 7.358014521195372e-05, 'samples': 21677952, 'steps': 112905, 'loss/train': 0.7256149649620056} 08/31/2021 09:40:48 - INFO - __main__ - Step 112907: {'lr': 7.357638525740001e-05, 'samples': 21678144, 'steps': 112906, 'loss/train': 0.6034651398658752} 08/31/2021 09:40:49 - INFO - __main__ - Step 112908: {'lr': 7.357262538234005e-05, 'samples': 21678336, 'steps': 112907, 'loss/train': 0.26740169525146484} 08/31/2021 09:40:50 - INFO - __main__ - Step 112909: {'lr': 7.356886558677555e-05, 'samples': 21678528, 'steps': 112908, 'loss/train': 0.9363471269607544} 08/31/2021 09:40:51 - INFO - __main__ - Step 112910: {'lr': 7.356510587070819e-05, 'samples': 21678720, 'steps': 112909, 'loss/train': 1.1111948490142822} 08/31/2021 09:40:51 - INFO - __main__ - Step 112911: {'lr': 7.356134623413968e-05, 'samples': 21678912, 'steps': 112910, 'loss/train': 1.1109278202056885} 08/31/2021 09:40:51 - INFO - __main__ - Step 112912: {'lr': 7.355758667707168e-05, 'samples': 21679104, 'steps': 112911, 'loss/train': 1.0330578088760376} 08/31/2021 09:40:52 - INFO - __main__ - Step 112913: {'lr': 7.355382719950593e-05, 'samples': 21679296, 'steps': 112912, 'loss/train': 1.1180627346038818} 08/31/2021 09:40:53 - INFO - __main__ - Step 112914: {'lr': 7.355006780144419e-05, 'samples': 21679488, 'steps': 112913, 'loss/train': 1.3484359979629517} 08/31/2021 09:40:54 - INFO - __main__ - Step 112915: {'lr': 7.354630848288796e-05, 'samples': 21679680, 'steps': 112914, 'loss/train': 1.4036788940429688} 08/31/2021 09:40:54 - INFO - __main__ - Step 112916: {'lr': 7.354254924383907e-05, 'samples': 21679872, 'steps': 112915, 'loss/train': 1.3891440629959106} 08/31/2021 09:40:54 - INFO - __main__ - Step 112917: {'lr': 7.353879008429917e-05, 'samples': 21680064, 'steps': 112916, 'loss/train': 0.9475243091583252} 08/31/2021 09:40:55 - INFO - __main__ - Step 112918: {'lr': 7.353503100426995e-05, 'samples': 21680256, 'steps': 112917, 'loss/train': 1.5481683015823364} 08/31/2021 09:40:56 - INFO - __main__ - Step 112919: {'lr': 7.353127200375315e-05, 'samples': 21680448, 'steps': 112918, 'loss/train': 0.6070989966392517} 08/31/2021 09:40:57 - INFO - __main__ - Step 112920: {'lr': 7.352751308275043e-05, 'samples': 21680640, 'steps': 112919, 'loss/train': 0.12917956709861755} 08/31/2021 09:40:57 - INFO - __main__ - Step 112921: {'lr': 7.352375424126347e-05, 'samples': 21680832, 'steps': 112920, 'loss/train': 0.04377021640539169} 08/31/2021 09:40:58 - INFO - __main__ - Step 112922: {'lr': 7.3519995479294e-05, 'samples': 21681024, 'steps': 112921, 'loss/train': 0.583992600440979} 08/31/2021 09:40:58 - INFO - __main__ - Step 112923: {'lr': 7.351623679684372e-05, 'samples': 21681216, 'steps': 112922, 'loss/train': 1.0888715982437134} 08/31/2021 09:40:59 - INFO - __main__ - Step 112924: {'lr': 7.351247819391427e-05, 'samples': 21681408, 'steps': 112923, 'loss/train': 1.061649203300476} 08/31/2021 09:41:00 - INFO - __main__ - Step 112925: {'lr': 7.350871967050738e-05, 'samples': 21681600, 'steps': 112924, 'loss/train': 1.2768077850341797} 08/31/2021 09:41:00 - INFO - __main__ - Step 112926: {'lr': 7.350496122662472e-05, 'samples': 21681792, 'steps': 112925, 'loss/train': 0.6855561137199402} 08/31/2021 09:41:01 - INFO - __main__ - Step 112927: {'lr': 7.350120286226803e-05, 'samples': 21681984, 'steps': 112926, 'loss/train': 1.3048487901687622} 08/31/2021 09:41:01 - INFO - __main__ - Step 112928: {'lr': 7.349744457743904e-05, 'samples': 21682176, 'steps': 112927, 'loss/train': 0.895316481590271} 08/31/2021 09:41:03 - INFO - __main__ - Step 112929: {'lr': 7.34936863721393e-05, 'samples': 21682368, 'steps': 112928, 'loss/train': 1.4656858444213867} 08/31/2021 09:41:03 - INFO - __main__ - Step 112930: {'lr': 7.348992824637057e-05, 'samples': 21682560, 'steps': 112929, 'loss/train': 1.1787018775939941} 08/31/2021 09:41:03 - INFO - __main__ - Step 112931: {'lr': 7.348617020013457e-05, 'samples': 21682752, 'steps': 112930, 'loss/train': 1.3074941635131836} 08/31/2021 09:41:04 - INFO - __main__ - Step 112932: {'lr': 7.348241223343299e-05, 'samples': 21682944, 'steps': 112931, 'loss/train': 1.541573405265808} 08/31/2021 09:41:04 - INFO - __main__ - Step 112933: {'lr': 7.34786543462675e-05, 'samples': 21683136, 'steps': 112932, 'loss/train': 0.9482647180557251} 08/31/2021 09:41:04 - INFO - __main__ - Step 112934: {'lr': 7.347489653863979e-05, 'samples': 21683328, 'steps': 112933, 'loss/train': 1.0646867752075195} 08/31/2021 09:41:06 - INFO - __main__ - Step 112935: {'lr': 7.34711388105516e-05, 'samples': 21683520, 'steps': 112934, 'loss/train': 1.349291443824768} 08/31/2021 09:41:06 - INFO - __main__ - Step 112936: {'lr': 7.346738116200455e-05, 'samples': 21683712, 'steps': 112935, 'loss/train': 1.222110390663147} 08/31/2021 09:41:07 - INFO - __main__ - Step 112937: {'lr': 7.346362359300038e-05, 'samples': 21683904, 'steps': 112936, 'loss/train': 0.924928605556488} 08/31/2021 09:41:07 - INFO - __main__ - Step 112938: {'lr': 7.34598661035408e-05, 'samples': 21684096, 'steps': 112937, 'loss/train': 0.9773262739181519} 08/31/2021 09:41:07 - INFO - __main__ - Step 112939: {'lr': 7.345610869362746e-05, 'samples': 21684288, 'steps': 112938, 'loss/train': 0.5358594655990601} 08/31/2021 09:41:09 - INFO - __main__ - Step 112940: {'lr': 7.345235136326208e-05, 'samples': 21684480, 'steps': 112939, 'loss/train': 2.1629884243011475} 08/31/2021 09:41:09 - INFO - __main__ - Step 112941: {'lr': 7.344859411244645e-05, 'samples': 21684672, 'steps': 112940, 'loss/train': 0.9806191921234131} 08/31/2021 09:41:10 - INFO - __main__ - Step 112942: {'lr': 7.344483694118203e-05, 'samples': 21684864, 'steps': 112941, 'loss/train': 1.5972833633422852} 08/31/2021 09:41:10 - INFO - __main__ - Step 112943: {'lr': 7.344107984947068e-05, 'samples': 21685056, 'steps': 112942, 'loss/train': 1.0746065378189087} 08/31/2021 09:41:10 - INFO - __main__ - Step 112944: {'lr': 7.343732283731405e-05, 'samples': 21685248, 'steps': 112943, 'loss/train': 0.6434628367424011} 08/31/2021 09:41:12 - INFO - __main__ - Step 112945: {'lr': 7.343356590471384e-05, 'samples': 21685440, 'steps': 112944, 'loss/train': 0.24678725004196167} 08/31/2021 09:41:12 - INFO - __main__ - Step 112946: {'lr': 7.342980905167173e-05, 'samples': 21685632, 'steps': 112945, 'loss/train': 0.4975029230117798} 08/31/2021 09:41:13 - INFO - __main__ - Step 112947: {'lr': 7.342605227818944e-05, 'samples': 21685824, 'steps': 112946, 'loss/train': 0.6302924752235413} 08/31/2021 09:41:13 - INFO - __main__ - Step 112948: {'lr': 7.342229558426864e-05, 'samples': 21686016, 'steps': 112947, 'loss/train': 0.638147234916687} 08/31/2021 09:41:13 - INFO - __main__ - Step 112949: {'lr': 7.341853896991099e-05, 'samples': 21686208, 'steps': 112948, 'loss/train': 1.4954848289489746} 08/31/2021 09:41:16 - INFO - __main__ - Step 112950: {'lr': 7.341478243511825e-05, 'samples': 21686400, 'steps': 112949, 'loss/train': 0.8415874242782593} 08/31/2021 09:41:16 - INFO - __main__ - Step 112951: {'lr': 7.34110259798921e-05, 'samples': 21686592, 'steps': 112950, 'loss/train': 1.1175570487976074} 08/31/2021 09:41:16 - INFO - __main__ - Step 112952: {'lr': 7.340726960423421e-05, 'samples': 21686784, 'steps': 112951, 'loss/train': 1.0183465480804443} 08/31/2021 09:41:17 - INFO - __main__ - Step 112953: {'lr': 7.340351330814626e-05, 'samples': 21686976, 'steps': 112952, 'loss/train': 0.9916529059410095} 08/31/2021 09:41:17 - INFO - __main__ - Step 112954: {'lr': 7.339975709163008e-05, 'samples': 21687168, 'steps': 112953, 'loss/train': 1.5717748403549194} 08/31/2021 09:41:19 - INFO - __main__ - Step 112955: {'lr': 7.339600095468712e-05, 'samples': 21687360, 'steps': 112954, 'loss/train': 1.2524996995925903} 08/31/2021 09:41:19 - INFO - __main__ - Step 112956: {'lr': 7.339224489731921e-05, 'samples': 21687552, 'steps': 112955, 'loss/train': 0.9358806610107422} 08/31/2021 09:41:19 - INFO - __main__ - Step 112957: {'lr': 7.338848891952804e-05, 'samples': 21687744, 'steps': 112956, 'loss/train': 1.6008126735687256} 08/31/2021 09:41:20 - INFO - __main__ - Step 112958: {'lr': 7.338473302131529e-05, 'samples': 21687936, 'steps': 112957, 'loss/train': 0.5561155080795288} 08/31/2021 09:41:20 - INFO - __main__ - Step 112959: {'lr': 7.338097720268267e-05, 'samples': 21688128, 'steps': 112958, 'loss/train': 0.8043711185455322} 08/31/2021 09:41:22 - INFO - __main__ - Step 112960: {'lr': 7.337722146363182e-05, 'samples': 21688320, 'steps': 112959, 'loss/train': 1.2553914785385132} 08/31/2021 09:41:22 - INFO - __main__ - Step 112961: {'lr': 7.337346580416449e-05, 'samples': 21688512, 'steps': 112960, 'loss/train': 1.3890584707260132} 08/31/2021 09:41:23 - INFO - __main__ - Step 112962: {'lr': 7.336971022428235e-05, 'samples': 21688704, 'steps': 112961, 'loss/train': 1.1862345933914185} 08/31/2021 09:41:23 - INFO - __main__ - Step 112963: {'lr': 7.336595472398711e-05, 'samples': 21688896, 'steps': 112962, 'loss/train': 0.02416100725531578} 08/31/2021 09:41:23 - INFO - __main__ - Step 112964: {'lr': 7.336219930328042e-05, 'samples': 21689088, 'steps': 112963, 'loss/train': 0.7488316297531128} 08/31/2021 09:41:24 - INFO - __main__ - Step 112965: {'lr': 7.335844396216399e-05, 'samples': 21689280, 'steps': 112964, 'loss/train': 1.1686573028564453} 08/31/2021 09:41:25 - INFO - __main__ - Step 112966: {'lr': 7.335468870063952e-05, 'samples': 21689472, 'steps': 112965, 'loss/train': 1.47524893283844} 08/31/2021 09:41:26 - INFO - __main__ - Step 112967: {'lr': 7.335093351870873e-05, 'samples': 21689664, 'steps': 112966, 'loss/train': 1.1371597051620483} 08/31/2021 09:41:26 - INFO - __main__ - Step 112968: {'lr': 7.334717841637334e-05, 'samples': 21689856, 'steps': 112967, 'loss/train': 1.1464743614196777} 08/31/2021 09:41:26 - INFO - __main__ - Step 112969: {'lr': 7.334342339363492e-05, 'samples': 21690048, 'steps': 112968, 'loss/train': 1.8744566440582275} 08/31/2021 09:41:27 - INFO - __main__ - Step 112970: {'lr': 7.333966845049522e-05, 'samples': 21690240, 'steps': 112969, 'loss/train': 1.0136151313781738} 08/31/2021 09:41:28 - INFO - __main__ - Step 112971: {'lr': 7.333591358695594e-05, 'samples': 21690432, 'steps': 112970, 'loss/train': 1.6660008430480957} 08/31/2021 09:41:29 - INFO - __main__ - Step 112972: {'lr': 7.333215880301877e-05, 'samples': 21690624, 'steps': 112971, 'loss/train': 0.9154543280601501} 08/31/2021 09:41:29 - INFO - __main__ - Step 112973: {'lr': 7.332840409868541e-05, 'samples': 21690816, 'steps': 112972, 'loss/train': 1.1926072835922241} 08/31/2021 09:41:29 - INFO - __main__ - Step 112974: {'lr': 7.332464947395753e-05, 'samples': 21691008, 'steps': 112973, 'loss/train': 0.8221728801727295} 08/31/2021 09:41:31 - INFO - __main__ - Step 112975: {'lr': 7.332089492883684e-05, 'samples': 21691200, 'steps': 112974, 'loss/train': 1.0212829113006592} 08/31/2021 09:41:31 - INFO - __main__ - Step 112976: {'lr': 7.331714046332504e-05, 'samples': 21691392, 'steps': 112975, 'loss/train': 1.0692564249038696} 08/31/2021 09:41:32 - INFO - __main__ - Step 112977: {'lr': 7.33133860774238e-05, 'samples': 21691584, 'steps': 112976, 'loss/train': 1.6856913566589355} 08/31/2021 09:41:32 - INFO - __main__ - Step 112978: {'lr': 7.330963177113484e-05, 'samples': 21691776, 'steps': 112977, 'loss/train': 1.5872600078582764} 08/31/2021 09:41:32 - INFO - __main__ - Step 112979: {'lr': 7.33058775444598e-05, 'samples': 21691968, 'steps': 112978, 'loss/train': 0.3952886164188385} 08/31/2021 09:41:33 - INFO - __main__ - Step 112980: {'lr': 7.330212339740045e-05, 'samples': 21692160, 'steps': 112979, 'loss/train': 0.37345051765441895} 08/31/2021 09:41:34 - INFO - __main__ - Step 112981: {'lr': 7.329836932995848e-05, 'samples': 21692352, 'steps': 112980, 'loss/train': 1.0253125429153442} 08/31/2021 09:41:35 - INFO - __main__ - Step 112982: {'lr': 7.329461534213546e-05, 'samples': 21692544, 'steps': 112981, 'loss/train': 1.1159006357192993} 08/31/2021 09:41:35 - INFO - __main__ - Step 112983: {'lr': 7.329086143393318e-05, 'samples': 21692736, 'steps': 112982, 'loss/train': 0.8621228337287903} 08/31/2021 09:41:35 - INFO - __main__ - Step 112984: {'lr': 7.328710760535329e-05, 'samples': 21692928, 'steps': 112983, 'loss/train': 1.3800183534622192} 08/31/2021 09:41:36 - INFO - __main__ - Step 112985: {'lr': 7.328335385639751e-05, 'samples': 21693120, 'steps': 112984, 'loss/train': 0.6076498627662659} 08/31/2021 09:41:38 - INFO - __main__ - Step 112986: {'lr': 7.327960018706753e-05, 'samples': 21693312, 'steps': 112985, 'loss/train': 1.1636706590652466} 08/31/2021 09:41:38 - INFO - __main__ - Step 112987: {'lr': 7.327584659736503e-05, 'samples': 21693504, 'steps': 112986, 'loss/train': 1.0403053760528564} 08/31/2021 09:41:38 - INFO - __main__ - Step 112988: {'lr': 7.327209308729171e-05, 'samples': 21693696, 'steps': 112987, 'loss/train': 0.234930157661438} 08/31/2021 09:41:39 - INFO - __main__ - Step 112989: {'lr': 7.326833965684925e-05, 'samples': 21693888, 'steps': 112988, 'loss/train': 0.20955216884613037} 08/31/2021 09:41:39 - INFO - __main__ - Step 112990: {'lr': 7.326458630603936e-05, 'samples': 21694080, 'steps': 112989, 'loss/train': 1.0692335367202759} 08/31/2021 09:41:41 - INFO - __main__ - Step 112991: {'lr': 7.326083303486372e-05, 'samples': 21694272, 'steps': 112990, 'loss/train': 1.2675788402557373} 08/31/2021 09:41:41 - INFO - __main__ - Step 112992: {'lr': 7.3257079843324e-05, 'samples': 21694464, 'steps': 112991, 'loss/train': 0.999194860458374} 08/31/2021 09:41:42 - INFO - __main__ - Step 112993: {'lr': 7.325332673142193e-05, 'samples': 21694656, 'steps': 112992, 'loss/train': 1.1460387706756592} 08/31/2021 09:41:42 - INFO - __main__ - Step 112994: {'lr': 7.324957369915919e-05, 'samples': 21694848, 'steps': 112993, 'loss/train': 1.6926007270812988} 08/31/2021 09:41:42 - INFO - __main__ - Step 112995: {'lr': 7.324582074653754e-05, 'samples': 21695040, 'steps': 112994, 'loss/train': 1.315116047859192} 08/31/2021 09:41:43 - INFO - __main__ - Step 112996: {'lr': 7.32420678735585e-05, 'samples': 21695232, 'steps': 112995, 'loss/train': 1.1608127355575562} 08/31/2021 09:41:44 - INFO - __main__ - Step 112997: {'lr': 7.323831508022388e-05, 'samples': 21695424, 'steps': 112996, 'loss/train': 1.3596715927124023} 08/31/2021 09:41:45 - INFO - __main__ - Step 112998: {'lr': 7.323456236653534e-05, 'samples': 21695616, 'steps': 112997, 'loss/train': 0.12026776373386383} 08/31/2021 09:41:45 - INFO - __main__ - Step 112999: {'lr': 7.323080973249457e-05, 'samples': 21695808, 'steps': 112998, 'loss/train': 1.0505599975585938} 08/31/2021 09:41:45 - INFO - __main__ - Step 113000: {'lr': 7.322705717810327e-05, 'samples': 21696000, 'steps': 112999, 'loss/train': 1.4966024160385132} 08/31/2021 09:41:46 - INFO - __main__ - Step 113001: {'lr': 7.322330470336314e-05, 'samples': 21696192, 'steps': 113000, 'loss/train': 0.02440418303012848} 08/31/2021 09:41:48 - INFO - __main__ - Step 113002: {'lr': 7.321955230827585e-05, 'samples': 21696384, 'steps': 113001, 'loss/train': 1.1100908517837524} 08/31/2021 09:41:49 - INFO - __main__ - Step 113003: {'lr': 7.321579999284311e-05, 'samples': 21696576, 'steps': 113002, 'loss/train': 0.8569858074188232} 08/31/2021 09:41:49 - INFO - __main__ - Step 113004: {'lr': 7.32120477570666e-05, 'samples': 21696768, 'steps': 113003, 'loss/train': 0.7725622057914734} 08/31/2021 09:41:49 - INFO - __main__ - Step 113005: {'lr': 7.320829560094802e-05, 'samples': 21696960, 'steps': 113004, 'loss/train': 0.4714627265930176} 08/31/2021 09:41:50 - INFO - __main__ - Step 113006: {'lr': 7.320454352448905e-05, 'samples': 21697152, 'steps': 113005, 'loss/train': 1.009321928024292} 08/31/2021 09:41:50 - INFO - __main__ - Step 113007: {'lr': 7.320079152769138e-05, 'samples': 21697344, 'steps': 113006, 'loss/train': 0.7824416160583496} 08/31/2021 09:41:52 - INFO - __main__ - Step 113008: {'lr': 7.319703961055679e-05, 'samples': 21697536, 'steps': 113007, 'loss/train': 1.335089921951294} 08/31/2021 09:41:52 - INFO - __main__ - Step 113009: {'lr': 7.319328777308679e-05, 'samples': 21697728, 'steps': 113008, 'loss/train': 1.0911493301391602} 08/31/2021 09:41:52 - INFO - __main__ - Step 113010: {'lr': 7.318953601528319e-05, 'samples': 21697920, 'steps': 113009, 'loss/train': 1.3658545017242432} 08/31/2021 09:41:53 - INFO - __main__ - Step 113011: {'lr': 7.318578433714765e-05, 'samples': 21698112, 'steps': 113010, 'loss/train': 0.663947343826294} 08/31/2021 09:41:53 - INFO - __main__ - Step 113012: {'lr': 7.318203273868185e-05, 'samples': 21698304, 'steps': 113011, 'loss/train': 1.4093419313430786} 08/31/2021 09:41:55 - INFO - __main__ - Step 113013: {'lr': 7.317828121988752e-05, 'samples': 21698496, 'steps': 113012, 'loss/train': 0.52874755859375} 08/31/2021 09:41:55 - INFO - __main__ - Step 113014: {'lr': 7.317452978076631e-05, 'samples': 21698688, 'steps': 113013, 'loss/train': 1.0353751182556152} 08/31/2021 09:41:55 - INFO - __main__ - Step 113015: {'lr': 7.317077842131995e-05, 'samples': 21698880, 'steps': 113014, 'loss/train': 0.960320770740509} 08/31/2021 09:41:56 - INFO - __main__ - Step 113016: {'lr': 7.316702714155007e-05, 'samples': 21699072, 'steps': 113015, 'loss/train': 0.708022952079773} 08/31/2021 09:41:56 - INFO - __main__ - Step 113017: {'lr': 7.316327594145843e-05, 'samples': 21699264, 'steps': 113016, 'loss/train': 0.9559900760650635} 08/31/2021 09:41:58 - INFO - __main__ - Step 113018: {'lr': 7.315952482104668e-05, 'samples': 21699456, 'steps': 113017, 'loss/train': 1.073344111442566} 08/31/2021 09:41:58 - INFO - __main__ - Step 113019: {'lr': 7.315577378031654e-05, 'samples': 21699648, 'steps': 113018, 'loss/train': 1.335680603981018} 08/31/2021 09:41:59 - INFO - __main__ - Step 113020: {'lr': 7.315202281926966e-05, 'samples': 21699840, 'steps': 113019, 'loss/train': 0.9712886810302734} 08/31/2021 09:41:59 - INFO - __main__ - Step 113021: {'lr': 7.314827193790774e-05, 'samples': 21700032, 'steps': 113020, 'loss/train': 5.729918479919434} 08/31/2021 09:41:59 - INFO - __main__ - Step 113022: {'lr': 7.314452113623257e-05, 'samples': 21700224, 'steps': 113021, 'loss/train': 1.2450661659240723} 08/31/2021 09:42:00 - INFO - __main__ - Step 113023: {'lr': 7.314077041424569e-05, 'samples': 21700416, 'steps': 113022, 'loss/train': 0.48729026317596436} 08/31/2021 09:42:01 - INFO - __main__ - Step 113024: {'lr': 7.313701977194884e-05, 'samples': 21700608, 'steps': 113023, 'loss/train': 1.3371018171310425} 08/31/2021 09:42:02 - INFO - __main__ - Step 113025: {'lr': 7.313326920934368e-05, 'samples': 21700800, 'steps': 113024, 'loss/train': 0.35545772314071655} 08/31/2021 09:42:02 - INFO - __main__ - Step 113026: {'lr': 7.312951872643198e-05, 'samples': 21700992, 'steps': 113025, 'loss/train': 1.1479966640472412} 08/31/2021 09:42:02 - INFO - __main__ - Step 113027: {'lr': 7.312576832321538e-05, 'samples': 21701184, 'steps': 113026, 'loss/train': 0.6093354821205139} 08/31/2021 09:42:03 - INFO - __main__ - Step 113028: {'lr': 7.312201799969559e-05, 'samples': 21701376, 'steps': 113027, 'loss/train': 1.375078558921814} 08/31/2021 09:42:04 - INFO - __main__ - Step 113029: {'lr': 7.311826775587426e-05, 'samples': 21701568, 'steps': 113028, 'loss/train': 1.1336454153060913} 08/31/2021 09:42:05 - INFO - __main__ - Step 113030: {'lr': 7.311451759175314e-05, 'samples': 21701760, 'steps': 113029, 'loss/train': 0.5807275772094727} 08/31/2021 09:42:05 - INFO - __main__ - Step 113031: {'lr': 7.311076750733389e-05, 'samples': 21701952, 'steps': 113030, 'loss/train': 1.240337610244751} 08/31/2021 09:42:05 - INFO - __main__ - Step 113032: {'lr': 7.310701750261817e-05, 'samples': 21702144, 'steps': 113031, 'loss/train': 0.9757195115089417} 08/31/2021 09:42:06 - INFO - __main__ - Step 113033: {'lr': 7.310326757760772e-05, 'samples': 21702336, 'steps': 113032, 'loss/train': 0.8124843835830688} 08/31/2021 09:42:07 - INFO - __main__ - Step 113034: {'lr': 7.30995177323042e-05, 'samples': 21702528, 'steps': 113033, 'loss/train': 0.6833042502403259} 08/31/2021 09:42:08 - INFO - __main__ - Step 113035: {'lr': 7.309576796670938e-05, 'samples': 21702720, 'steps': 113034, 'loss/train': 0.9222546219825745} 08/31/2021 09:42:08 - INFO - __main__ - Step 113036: {'lr': 7.309201828082482e-05, 'samples': 21702912, 'steps': 113035, 'loss/train': 0.9759528040885925} 08/31/2021 09:42:08 - INFO - __main__ - Step 113037: {'lr': 7.308826867465223e-05, 'samples': 21703104, 'steps': 113036, 'loss/train': 0.5311521887779236} 08/31/2021 09:42:09 - INFO - __main__ - Step 113038: {'lr': 7.30845191481934e-05, 'samples': 21703296, 'steps': 113037, 'loss/train': 0.5739456415176392} 08/31/2021 09:42:10 - INFO - __main__ - Step 113039: {'lr': 7.308076970144989e-05, 'samples': 21703488, 'steps': 113038, 'loss/train': 0.4791922867298126} 08/31/2021 09:42:11 - INFO - __main__ - Step 113040: {'lr': 7.307702033442348e-05, 'samples': 21703680, 'steps': 113039, 'loss/train': 0.6266400814056396} 08/31/2021 09:42:11 - INFO - __main__ - Step 113041: {'lr': 7.307327104711583e-05, 'samples': 21703872, 'steps': 113040, 'loss/train': 1.1851524114608765} 08/31/2021 09:42:12 - INFO - __main__ - Step 113042: {'lr': 7.306952183952863e-05, 'samples': 21704064, 'steps': 113041, 'loss/train': 0.9450560212135315} 08/31/2021 09:42:12 - INFO - __main__ - Step 113043: {'lr': 7.30657727116636e-05, 'samples': 21704256, 'steps': 113042, 'loss/train': 1.1677753925323486} 08/31/2021 09:42:12 - INFO - __main__ - Step 113044: {'lr': 7.306202366352238e-05, 'samples': 21704448, 'steps': 113043, 'loss/train': 1.2669931650161743} 08/31/2021 09:42:14 - INFO - __main__ - Step 113045: {'lr': 7.30582746951067e-05, 'samples': 21704640, 'steps': 113044, 'loss/train': 1.4378595352172852} 08/31/2021 09:42:14 - INFO - __main__ - Step 113046: {'lr': 7.305452580641822e-05, 'samples': 21704832, 'steps': 113045, 'loss/train': 1.605869174003601} 08/31/2021 09:42:15 - INFO - __main__ - Step 113047: {'lr': 7.305077699745863e-05, 'samples': 21705024, 'steps': 113046, 'loss/train': 1.1414278745651245} 08/31/2021 09:42:15 - INFO - __main__ - Step 113048: {'lr': 7.304702826822962e-05, 'samples': 21705216, 'steps': 113047, 'loss/train': 1.7208596467971802} 08/31/2021 09:42:15 - INFO - __main__ - Step 113049: {'lr': 7.3043279618733e-05, 'samples': 21705408, 'steps': 113048, 'loss/train': 1.038975477218628} 08/31/2021 09:42:18 - INFO - __main__ - Step 113050: {'lr': 7.303953104897024e-05, 'samples': 21705600, 'steps': 113049, 'loss/train': 0.7922874689102173} 08/31/2021 09:42:18 - INFO - __main__ - Step 113051: {'lr': 7.303578255894316e-05, 'samples': 21705792, 'steps': 113050, 'loss/train': 1.0873175859451294} 08/31/2021 09:42:18 - INFO - __main__ - Step 113052: {'lr': 7.303203414865342e-05, 'samples': 21705984, 'steps': 113051, 'loss/train': 0.6525769829750061} 08/31/2021 09:42:19 - INFO - __main__ - Step 113053: {'lr': 7.30282858181027e-05, 'samples': 21706176, 'steps': 113052, 'loss/train': 5.826011657714844} 08/31/2021 09:42:19 - INFO - __main__ - Step 113054: {'lr': 7.302453756729272e-05, 'samples': 21706368, 'steps': 113053, 'loss/train': 0.7520328164100647} 08/31/2021 09:42:19 - INFO - __main__ - Step 113055: {'lr': 7.302078939622513e-05, 'samples': 21706560, 'steps': 113054, 'loss/train': 0.23853306472301483} 08/31/2021 09:42:21 - INFO - __main__ - Step 113056: {'lr': 7.301704130490166e-05, 'samples': 21706752, 'steps': 113055, 'loss/train': 0.4535180330276489} 08/31/2021 09:42:21 - INFO - __main__ - Step 113057: {'lr': 7.301329329332398e-05, 'samples': 21706944, 'steps': 113056, 'loss/train': 1.3056670427322388} 08/31/2021 09:42:22 - INFO - __main__ - Step 113058: {'lr': 7.300954536149379e-05, 'samples': 21707136, 'steps': 113057, 'loss/train': 1.393848180770874} 08/31/2021 09:42:22 - INFO - __main__ - Step 113059: {'lr': 7.300579750941275e-05, 'samples': 21707328, 'steps': 113058, 'loss/train': 1.2382181882858276} 08/31/2021 09:42:22 - INFO - __main__ - Step 113060: {'lr': 7.300204973708258e-05, 'samples': 21707520, 'steps': 113059, 'loss/train': 1.2908947467803955} 08/31/2021 09:42:24 - INFO - __main__ - Step 113061: {'lr': 7.299830204450495e-05, 'samples': 21707712, 'steps': 113060, 'loss/train': 1.7099952697753906} 08/31/2021 09:42:24 - INFO - __main__ - Step 113062: {'lr': 7.299455443168162e-05, 'samples': 21707904, 'steps': 113061, 'loss/train': 1.5496501922607422} 08/31/2021 09:42:25 - INFO - __main__ - Step 113063: {'lr': 7.299080689861415e-05, 'samples': 21708096, 'steps': 113062, 'loss/train': 1.0793145895004272} 08/31/2021 09:42:25 - INFO - __main__ - Step 113064: {'lr': 7.298705944530425e-05, 'samples': 21708288, 'steps': 113063, 'loss/train': 1.346399188041687} 08/31/2021 09:42:25 - INFO - __main__ - Step 113065: {'lr': 7.298331207175371e-05, 'samples': 21708480, 'steps': 113064, 'loss/train': 0.5540827512741089} 08/31/2021 09:42:26 - INFO - __main__ - Step 113066: {'lr': 7.297956477796414e-05, 'samples': 21708672, 'steps': 113065, 'loss/train': 0.5337945818901062} 08/31/2021 09:42:27 - INFO - __main__ - Step 113067: {'lr': 7.297581756393723e-05, 'samples': 21708864, 'steps': 113066, 'loss/train': 1.1823153495788574} 08/31/2021 09:42:28 - INFO - __main__ - Step 113068: {'lr': 7.297207042967468e-05, 'samples': 21709056, 'steps': 113067, 'loss/train': 0.5468321442604065} 08/31/2021 09:42:28 - INFO - __main__ - Step 113069: {'lr': 7.29683233751782e-05, 'samples': 21709248, 'steps': 113068, 'loss/train': 1.1861135959625244} 08/31/2021 09:42:29 - INFO - __main__ - Step 113070: {'lr': 7.296457640044945e-05, 'samples': 21709440, 'steps': 113069, 'loss/train': 1.8364510536193848} 08/31/2021 09:42:29 - INFO - __main__ - Step 113071: {'lr': 7.296082950549015e-05, 'samples': 21709632, 'steps': 113070, 'loss/train': 0.8847251534461975} 08/31/2021 09:42:31 - INFO - __main__ - Step 113072: {'lr': 7.295708269030194e-05, 'samples': 21709824, 'steps': 113071, 'loss/train': 0.8746243119239807} 08/31/2021 09:42:31 - INFO - __main__ - Step 113073: {'lr': 7.295333595488657e-05, 'samples': 21710016, 'steps': 113072, 'loss/train': 1.966303825378418} 08/31/2021 09:42:31 - INFO - __main__ - Step 113074: {'lr': 7.294958929924567e-05, 'samples': 21710208, 'steps': 113073, 'loss/train': 0.33047959208488464} 08/31/2021 09:42:32 - INFO - __main__ - Step 113075: {'lr': 7.294584272338103e-05, 'samples': 21710400, 'steps': 113074, 'loss/train': 0.6644335389137268} 08/31/2021 09:42:32 - INFO - __main__ - Step 113076: {'lr': 7.294209622729419e-05, 'samples': 21710592, 'steps': 113075, 'loss/train': 1.257462978363037} 08/31/2021 09:42:34 - INFO - __main__ - Step 113077: {'lr': 7.293834981098692e-05, 'samples': 21710784, 'steps': 113076, 'loss/train': 1.101355791091919} 08/31/2021 09:42:34 - INFO - __main__ - Step 113078: {'lr': 7.293460347446088e-05, 'samples': 21710976, 'steps': 113077, 'loss/train': 1.2800899744033813} 08/31/2021 09:42:34 - INFO - __main__ - Step 113079: {'lr': 7.293085721771778e-05, 'samples': 21711168, 'steps': 113078, 'loss/train': 1.1134932041168213} 08/31/2021 09:42:35 - INFO - __main__ - Step 113080: {'lr': 7.29271110407593e-05, 'samples': 21711360, 'steps': 113079, 'loss/train': 0.20536759495735168} 08/31/2021 09:42:35 - INFO - __main__ - Step 113081: {'lr': 7.292336494358714e-05, 'samples': 21711552, 'steps': 113080, 'loss/train': 1.0404889583587646} 08/31/2021 09:42:36 - INFO - __main__ - Step 113082: {'lr': 7.2919618926203e-05, 'samples': 21711744, 'steps': 113081, 'loss/train': 1.4007320404052734} 08/31/2021 09:42:37 - INFO - __main__ - Step 113083: {'lr': 7.291587298860853e-05, 'samples': 21711936, 'steps': 113082, 'loss/train': 0.45497626066207886} 08/31/2021 09:42:37 - INFO - __main__ - Step 113084: {'lr': 7.291212713080542e-05, 'samples': 21712128, 'steps': 113083, 'loss/train': 0.9603493809700012} 08/31/2021 09:42:38 - INFO - __main__ - Step 113085: {'lr': 7.290838135279537e-05, 'samples': 21712320, 'steps': 113084, 'loss/train': 1.3661630153656006} 08/31/2021 09:42:38 - INFO - __main__ - Step 113086: {'lr': 7.290463565458008e-05, 'samples': 21712512, 'steps': 113085, 'loss/train': 1.261107087135315} 08/31/2021 09:42:39 - INFO - __main__ - Step 113087: {'lr': 7.290089003616124e-05, 'samples': 21712704, 'steps': 113086, 'loss/train': 0.7590693831443787} 08/31/2021 09:42:40 - INFO - __main__ - Step 113088: {'lr': 7.289714449754051e-05, 'samples': 21712896, 'steps': 113087, 'loss/train': 1.5085186958312988} 08/31/2021 09:42:40 - INFO - __main__ - Step 113089: {'lr': 7.289339903871969e-05, 'samples': 21713088, 'steps': 113088, 'loss/train': 1.1197880506515503} 08/31/2021 09:42:41 - INFO - __main__ - Step 113090: {'lr': 7.28896536597003e-05, 'samples': 21713280, 'steps': 113089, 'loss/train': 1.1587178707122803} 08/31/2021 09:42:41 - INFO - __main__ - Step 113091: {'lr': 7.288590836048406e-05, 'samples': 21713472, 'steps': 113090, 'loss/train': 0.9491664171218872} 08/31/2021 09:42:42 - INFO - __main__ - Step 113092: {'lr': 7.288216314107271e-05, 'samples': 21713664, 'steps': 113091, 'loss/train': 0.1235252097249031} 08/31/2021 09:42:43 - INFO - __main__ - Step 113093: {'lr': 7.287841800146794e-05, 'samples': 21713856, 'steps': 113092, 'loss/train': 1.6354429721832275} 08/31/2021 09:42:43 - INFO - __main__ - Step 113094: {'lr': 7.287467294167142e-05, 'samples': 21714048, 'steps': 113093, 'loss/train': 0.998974621295929} 08/31/2021 09:42:44 - INFO - __main__ - Step 113095: {'lr': 7.287092796168484e-05, 'samples': 21714240, 'steps': 113094, 'loss/train': 1.3095661401748657} 08/31/2021 09:42:44 - INFO - __main__ - Step 113096: {'lr': 7.286718306150989e-05, 'samples': 21714432, 'steps': 113095, 'loss/train': 0.9445329904556274} 08/31/2021 09:42:44 - INFO - __main__ - Step 113097: {'lr': 7.286343824114821e-05, 'samples': 21714624, 'steps': 113096, 'loss/train': 1.3594977855682373} 08/31/2021 09:42:46 - INFO - __main__ - Step 113098: {'lr': 7.285969350060159e-05, 'samples': 21714816, 'steps': 113097, 'loss/train': 1.5272985696792603} 08/31/2021 09:42:46 - INFO - __main__ - Step 113099: {'lr': 7.285594883987162e-05, 'samples': 21715008, 'steps': 113098, 'loss/train': 1.5887539386749268} 08/31/2021 09:42:47 - INFO - __main__ - Step 113100: {'lr': 7.285220425896005e-05, 'samples': 21715200, 'steps': 113099, 'loss/train': 1.1945828199386597} 08/31/2021 09:42:47 - INFO - __main__ - Step 113101: {'lr': 7.284845975786853e-05, 'samples': 21715392, 'steps': 113100, 'loss/train': 1.6953567266464233} 08/31/2021 09:42:47 - INFO - __main__ - Step 113102: {'lr': 7.284471533659884e-05, 'samples': 21715584, 'steps': 113101, 'loss/train': 0.708861231803894} 08/31/2021 09:42:49 - INFO - __main__ - Step 113103: {'lr': 7.284097099515253e-05, 'samples': 21715776, 'steps': 113102, 'loss/train': 1.088356852531433} 08/31/2021 09:42:50 - INFO - __main__ - Step 113104: {'lr': 7.283722673353133e-05, 'samples': 21715968, 'steps': 113103, 'loss/train': 1.463752031326294} 08/31/2021 09:42:50 - INFO - __main__ - Step 113105: {'lr': 7.283348255173692e-05, 'samples': 21716160, 'steps': 113104, 'loss/train': 0.938789427280426} 08/31/2021 09:42:51 - INFO - __main__ - Step 113106: {'lr': 7.282973844977103e-05, 'samples': 21716352, 'steps': 113105, 'loss/train': 0.8402350544929504} 08/31/2021 09:42:51 - INFO - __main__ - Step 113107: {'lr': 7.282599442763532e-05, 'samples': 21716544, 'steps': 113106, 'loss/train': 0.504224956035614} 08/31/2021 09:42:53 - INFO - __main__ - Step 113108: {'lr': 7.282225048533148e-05, 'samples': 21716736, 'steps': 113107, 'loss/train': 0.605043351650238} 08/31/2021 09:42:53 - INFO - __main__ - Step 113109: {'lr': 7.281850662286121e-05, 'samples': 21716928, 'steps': 113108, 'loss/train': 1.6891356706619263} 08/31/2021 09:42:54 - INFO - __main__ - Step 113110: {'lr': 7.281476284022618e-05, 'samples': 21717120, 'steps': 113109, 'loss/train': 0.743621289730072} 08/31/2021 09:42:54 - INFO - __main__ - Step 113111: {'lr': 7.28110191374281e-05, 'samples': 21717312, 'steps': 113110, 'loss/train': 1.237718939781189} 08/31/2021 09:42:54 - INFO - __main__ - Step 113112: {'lr': 7.280727551446862e-05, 'samples': 21717504, 'steps': 113111, 'loss/train': 1.7157175540924072} 08/31/2021 09:42:55 - INFO - __main__ - Step 113113: {'lr': 7.280353197134945e-05, 'samples': 21717696, 'steps': 113112, 'loss/train': 1.3657505512237549} 08/31/2021 09:42:56 - INFO - __main__ - Step 113114: {'lr': 7.279978850807237e-05, 'samples': 21717888, 'steps': 113113, 'loss/train': 2.426255226135254} 08/31/2021 09:42:57 - INFO - __main__ - Step 113115: {'lr': 7.279604512463886e-05, 'samples': 21718080, 'steps': 113114, 'loss/train': 0.7994746565818787} 08/31/2021 09:42:57 - INFO - __main__ - Step 113116: {'lr': 7.279230182105075e-05, 'samples': 21718272, 'steps': 113115, 'loss/train': 1.921120524406433} 08/31/2021 09:42:57 - INFO - __main__ - Step 113117: {'lr': 7.278855859730968e-05, 'samples': 21718464, 'steps': 113116, 'loss/train': 1.212783932685852} 08/31/2021 09:42:58 - INFO - __main__ - Step 113118: {'lr': 7.278481545341737e-05, 'samples': 21718656, 'steps': 113117, 'loss/train': 0.937151312828064} 08/31/2021 09:42:59 - INFO - __main__ - Step 113119: {'lr': 7.278107238937545e-05, 'samples': 21718848, 'steps': 113118, 'loss/train': 0.962958574295044} 08/31/2021 09:43:00 - INFO - __main__ - Step 113120: {'lr': 7.277732940518566e-05, 'samples': 21719040, 'steps': 113119, 'loss/train': 1.1023485660552979} 08/31/2021 09:43:00 - INFO - __main__ - Step 113121: {'lr': 7.277358650084967e-05, 'samples': 21719232, 'steps': 113120, 'loss/train': 0.7957286238670349} 08/31/2021 09:43:00 - INFO - __main__ - Step 113122: {'lr': 7.276984367636918e-05, 'samples': 21719424, 'steps': 113121, 'loss/train': 0.13420040905475616} 08/31/2021 09:43:01 - INFO - __main__ - Step 113123: {'lr': 7.276610093174585e-05, 'samples': 21719616, 'steps': 113122, 'loss/train': 0.14079315960407257} 08/31/2021 09:43:02 - INFO - __main__ - Step 113124: {'lr': 7.276235826698138e-05, 'samples': 21719808, 'steps': 113123, 'loss/train': 0.922075092792511} 08/31/2021 09:43:03 - INFO - __main__ - Step 113125: {'lr': 7.275861568207756e-05, 'samples': 21720000, 'steps': 113124, 'loss/train': 1.291886329650879} 08/31/2021 09:43:03 - INFO - __main__ - Step 113126: {'lr': 7.275487317703586e-05, 'samples': 21720192, 'steps': 113125, 'loss/train': 1.1171350479125977} 08/31/2021 09:43:03 - INFO - __main__ - Step 113127: {'lr': 7.275113075185811e-05, 'samples': 21720384, 'steps': 113126, 'loss/train': 0.9392787218093872} 08/31/2021 09:43:04 - INFO - __main__ - Step 113128: {'lr': 7.274738840654594e-05, 'samples': 21720576, 'steps': 113127, 'loss/train': 0.9616582989692688} 08/31/2021 09:43:05 - INFO - __main__ - Step 113129: {'lr': 7.274364614110108e-05, 'samples': 21720768, 'steps': 113128, 'loss/train': 0.5834738612174988} 08/31/2021 09:43:06 - INFO - __main__ - Step 113130: {'lr': 7.273990395552519e-05, 'samples': 21720960, 'steps': 113129, 'loss/train': 1.6661831140518188} 08/31/2021 09:43:06 - INFO - __main__ - Step 113131: {'lr': 7.273616184981995e-05, 'samples': 21721152, 'steps': 113130, 'loss/train': 1.0124659538269043} 08/31/2021 09:43:06 - INFO - __main__ - Step 113132: {'lr': 7.273241982398706e-05, 'samples': 21721344, 'steps': 113131, 'loss/train': 1.2787355184555054} 08/31/2021 09:43:07 - INFO - __main__ - Step 113133: {'lr': 7.272867787802823e-05, 'samples': 21721536, 'steps': 113132, 'loss/train': 0.9602505564689636} 08/31/2021 09:43:09 - INFO - __main__ - Step 113134: {'lr': 7.272493601194513e-05, 'samples': 21721728, 'steps': 113133, 'loss/train': 0.6110765933990479} 08/31/2021 09:43:09 - INFO - __main__ - Step 113135: {'lr': 7.272119422573941e-05, 'samples': 21721920, 'steps': 113134, 'loss/train': 1.2648042440414429} 08/31/2021 09:43:09 - INFO - __main__ - Step 113136: {'lr': 7.271745251941287e-05, 'samples': 21722112, 'steps': 113135, 'loss/train': 0.4865240156650543} 08/31/2021 09:43:10 - INFO - __main__ - Step 113137: {'lr': 7.271371089296702e-05, 'samples': 21722304, 'steps': 113136, 'loss/train': 1.4368447065353394} 08/31/2021 09:43:10 - INFO - __main__ - Step 113138: {'lr': 7.270996934640367e-05, 'samples': 21722496, 'steps': 113137, 'loss/train': 0.015490244142711163} 08/31/2021 09:43:10 - INFO - __main__ - Step 113139: {'lr': 7.270622787972444e-05, 'samples': 21722688, 'steps': 113138, 'loss/train': 0.015988152474164963} 08/31/2021 09:43:11 - INFO - __main__ - Step 113140: {'lr': 7.270248649293107e-05, 'samples': 21722880, 'steps': 113139, 'loss/train': 1.4589366912841797} 08/31/2021 09:43:12 - INFO - __main__ - Step 113141: {'lr': 7.26987451860252e-05, 'samples': 21723072, 'steps': 113140, 'loss/train': 0.3260570168495178} 08/31/2021 09:43:13 - INFO - __main__ - Step 113142: {'lr': 7.269500395900857e-05, 'samples': 21723264, 'steps': 113141, 'loss/train': 1.6967997550964355} 08/31/2021 09:43:13 - INFO - __main__ - Step 113143: {'lr': 7.269126281188282e-05, 'samples': 21723456, 'steps': 113142, 'loss/train': 1.3171052932739258} 08/31/2021 09:43:14 - INFO - __main__ - Step 113144: {'lr': 7.268752174464966e-05, 'samples': 21723648, 'steps': 113143, 'loss/train': 1.294804334640503} 08/31/2021 09:43:14 - INFO - __main__ - Step 113145: {'lr': 7.268378075731074e-05, 'samples': 21723840, 'steps': 113144, 'loss/train': 0.8274641633033752} 08/31/2021 09:43:16 - INFO - __main__ - Step 113146: {'lr': 7.268003984986779e-05, 'samples': 21724032, 'steps': 113145, 'loss/train': 1.6648204326629639} 08/31/2021 09:43:16 - INFO - __main__ - Step 113147: {'lr': 7.267629902232256e-05, 'samples': 21724224, 'steps': 113146, 'loss/train': 1.200084924697876} 08/31/2021 09:43:17 - INFO - __main__ - Step 113148: {'lr': 7.267255827467655e-05, 'samples': 21724416, 'steps': 113147, 'loss/train': 0.3763192296028137} 08/31/2021 09:43:17 - INFO - __main__ - Step 113149: {'lr': 7.266881760693158e-05, 'samples': 21724608, 'steps': 113148, 'loss/train': 0.9432297348976135} 08/31/2021 09:43:17 - INFO - __main__ - Step 113150: {'lr': 7.266507701908928e-05, 'samples': 21724800, 'steps': 113149, 'loss/train': 0.9739009141921997} 08/31/2021 09:43:18 - INFO - __main__ - Step 113151: {'lr': 7.26613365111514e-05, 'samples': 21724992, 'steps': 113150, 'loss/train': 0.9689794182777405} 08/31/2021 09:43:19 - INFO - __main__ - Step 113152: {'lr': 7.265759608311956e-05, 'samples': 21725184, 'steps': 113151, 'loss/train': 0.016421888023614883} 08/31/2021 09:43:20 - INFO - __main__ - Step 113153: {'lr': 7.265385573499545e-05, 'samples': 21725376, 'steps': 113152, 'loss/train': 1.2336113452911377} 08/31/2021 09:43:20 - INFO - __main__ - Step 113154: {'lr': 7.26501154667808e-05, 'samples': 21725568, 'steps': 113153, 'loss/train': 1.396172046661377} 08/31/2021 09:43:21 - INFO - __main__ - Step 113155: {'lr': 7.264637527847726e-05, 'samples': 21725760, 'steps': 113154, 'loss/train': 1.6208460330963135} 08/31/2021 09:43:21 - INFO - __main__ - Step 113156: {'lr': 7.264263517008654e-05, 'samples': 21725952, 'steps': 113155, 'loss/train': 0.3265015184879303} 08/31/2021 09:43:21 - INFO - __main__ - Step 113157: {'lr': 7.26388951416103e-05, 'samples': 21726144, 'steps': 113156, 'loss/train': 1.657523274421692} 08/31/2021 09:43:23 - INFO - __main__ - Step 113158: {'lr': 7.263515519305033e-05, 'samples': 21726336, 'steps': 113157, 'loss/train': 1.10175359249115} 08/31/2021 09:43:24 - INFO - __main__ - Step 113159: {'lr': 7.263141532440811e-05, 'samples': 21726528, 'steps': 113158, 'loss/train': 1.0413860082626343} 08/31/2021 09:43:24 - INFO - __main__ - Step 113160: {'lr': 7.262767553568548e-05, 'samples': 21726720, 'steps': 113159, 'loss/train': 1.2760162353515625} 08/31/2021 09:43:24 - INFO - __main__ - Step 113161: {'lr': 7.262393582688407e-05, 'samples': 21726912, 'steps': 113160, 'loss/train': 1.0866432189941406} 08/31/2021 09:43:25 - INFO - __main__ - Step 113162: {'lr': 7.262019619800556e-05, 'samples': 21727104, 'steps': 113161, 'loss/train': 1.0818754434585571} 08/31/2021 09:43:27 - INFO - __main__ - Step 113163: {'lr': 7.261645664905167e-05, 'samples': 21727296, 'steps': 113162, 'loss/train': 0.05370950698852539} 08/31/2021 09:43:27 - INFO - __main__ - Step 113164: {'lr': 7.261271718002404e-05, 'samples': 21727488, 'steps': 113163, 'loss/train': 0.6379479765892029} 08/31/2021 09:43:28 - INFO - __main__ - Step 113165: {'lr': 7.260897779092443e-05, 'samples': 21727680, 'steps': 113164, 'loss/train': 1.1469804048538208} 08/31/2021 09:43:28 - INFO - __main__ - Step 113166: {'lr': 7.260523848175443e-05, 'samples': 21727872, 'steps': 113165, 'loss/train': 0.6398093104362488} 08/31/2021 09:43:28 - INFO - __main__ - Step 113167: {'lr': 7.26014992525158e-05, 'samples': 21728064, 'steps': 113166, 'loss/train': 0.5406067967414856} 08/31/2021 09:43:30 - INFO - __main__ - Step 113168: {'lr': 7.25977601032102e-05, 'samples': 21728256, 'steps': 113167, 'loss/train': 0.5070908069610596} 08/31/2021 09:43:30 - INFO - __main__ - Step 113169: {'lr': 7.25940210338393e-05, 'samples': 21728448, 'steps': 113168, 'loss/train': 1.1389282941818237} 08/31/2021 09:43:31 - INFO - __main__ - Step 113170: {'lr': 7.259028204440487e-05, 'samples': 21728640, 'steps': 113169, 'loss/train': 1.3677793741226196} 08/31/2021 09:43:31 - INFO - __main__ - Step 113171: {'lr': 7.258654313490845e-05, 'samples': 21728832, 'steps': 113170, 'loss/train': 0.40781348943710327} 08/31/2021 09:43:31 - INFO - __main__ - Step 113172: {'lr': 7.25828043053518e-05, 'samples': 21729024, 'steps': 113171, 'loss/train': 0.9075893759727478} 08/31/2021 09:43:32 - INFO - __main__ - Step 113173: {'lr': 7.257906555573659e-05, 'samples': 21729216, 'steps': 113172, 'loss/train': 0.9454805850982666} 08/31/2021 09:43:33 - INFO - __main__ - Step 113174: {'lr': 7.257532688606452e-05, 'samples': 21729408, 'steps': 113173, 'loss/train': 1.13628351688385} 08/31/2021 09:43:34 - INFO - __main__ - Step 113175: {'lr': 7.257158829633728e-05, 'samples': 21729600, 'steps': 113174, 'loss/train': 0.07205035537481308} 08/31/2021 09:43:34 - INFO - __main__ - Step 113176: {'lr': 7.256784978655654e-05, 'samples': 21729792, 'steps': 113175, 'loss/train': 0.9191823601722717} 08/31/2021 09:43:35 - INFO - __main__ - Step 113177: {'lr': 7.256411135672398e-05, 'samples': 21729984, 'steps': 113176, 'loss/train': 0.9444818496704102} 08/31/2021 09:43:35 - INFO - __main__ - Step 113178: {'lr': 7.256037300684129e-05, 'samples': 21730176, 'steps': 113177, 'loss/train': 0.21909336745738983} 08/31/2021 09:43:36 - INFO - __main__ - Step 113179: {'lr': 7.255663473691016e-05, 'samples': 21730368, 'steps': 113178, 'loss/train': 0.0380634181201458} 08/31/2021 09:43:37 - INFO - __main__ - Step 113180: {'lr': 7.255289654693228e-05, 'samples': 21730560, 'steps': 113179, 'loss/train': 1.178728699684143} 08/31/2021 09:43:37 - INFO - __main__ - Step 113181: {'lr': 7.254915843690932e-05, 'samples': 21730752, 'steps': 113180, 'loss/train': 1.0302780866622925} 08/31/2021 09:43:38 - INFO - __main__ - Step 113182: {'lr': 7.254542040684298e-05, 'samples': 21730944, 'steps': 113181, 'loss/train': 1.1638989448547363} 08/31/2021 09:43:38 - INFO - __main__ - Step 113183: {'lr': 7.254168245673501e-05, 'samples': 21731136, 'steps': 113182, 'loss/train': 2.0678200721740723} 08/31/2021 09:43:39 - INFO - __main__ - Step 113184: {'lr': 7.253794458658694e-05, 'samples': 21731328, 'steps': 113183, 'loss/train': 1.1568201780319214} 08/31/2021 09:43:40 - INFO - __main__ - Step 113185: {'lr': 7.253420679640055e-05, 'samples': 21731520, 'steps': 113184, 'loss/train': 1.276304841041565} 08/31/2021 09:43:40 - INFO - __main__ - Step 113186: {'lr': 7.253046908617747e-05, 'samples': 21731712, 'steps': 113185, 'loss/train': 1.306541085243225} 08/31/2021 09:43:41 - INFO - __main__ - Step 113187: {'lr': 7.252673145591945e-05, 'samples': 21731904, 'steps': 113186, 'loss/train': 1.1373156309127808} 08/31/2021 09:43:41 - INFO - __main__ - Step 113188: {'lr': 7.252299390562814e-05, 'samples': 21732096, 'steps': 113187, 'loss/train': 1.4169280529022217} 08/31/2021 09:43:42 - INFO - __main__ - Step 113189: {'lr': 7.251925643530524e-05, 'samples': 21732288, 'steps': 113188, 'loss/train': 1.2353259325027466} 08/31/2021 09:43:43 - INFO - __main__ - Step 113190: {'lr': 7.251551904495241e-05, 'samples': 21732480, 'steps': 113189, 'loss/train': 0.8572688698768616} 08/31/2021 09:43:43 - INFO - __main__ - Step 113191: {'lr': 7.251178173457135e-05, 'samples': 21732672, 'steps': 113190, 'loss/train': 1.1724752187728882} 08/31/2021 09:43:43 - INFO - __main__ - Step 113192: {'lr': 7.250804450416376e-05, 'samples': 21732864, 'steps': 113191, 'loss/train': 0.6855423450469971} 08/31/2021 09:43:44 - INFO - __main__ - Step 113193: {'lr': 7.250430735373129e-05, 'samples': 21733056, 'steps': 113192, 'loss/train': 1.3043212890625} 08/31/2021 09:43:46 - INFO - __main__ - Step 113194: {'lr': 7.250057028327564e-05, 'samples': 21733248, 'steps': 113193, 'loss/train': 1.4831929206848145} 08/31/2021 09:43:46 - INFO - __main__ - Step 113195: {'lr': 7.24968332927985e-05, 'samples': 21733440, 'steps': 113194, 'loss/train': 1.1538989543914795} 08/31/2021 09:43:47 - INFO - __main__ - Step 113196: {'lr': 7.249309638230162e-05, 'samples': 21733632, 'steps': 113195, 'loss/train': 1.4213937520980835} 08/31/2021 09:43:47 - INFO - __main__ - Step 113197: {'lr': 7.248935955178654e-05, 'samples': 21733824, 'steps': 113196, 'loss/train': 0.9859228730201721} 08/31/2021 09:43:47 - INFO - __main__ - Step 113198: {'lr': 7.248562280125501e-05, 'samples': 21734016, 'steps': 113197, 'loss/train': 1.6752902269363403} 08/31/2021 09:43:48 - INFO - __main__ - Step 113199: {'lr': 7.248188613070871e-05, 'samples': 21734208, 'steps': 113198, 'loss/train': 0.8316495418548584} 08/31/2021 09:43:49 - INFO - __main__ - Step 113200: {'lr': 7.247814954014934e-05, 'samples': 21734400, 'steps': 113199, 'loss/train': 0.06857730448246002} 08/31/2021 09:43:50 - INFO - __main__ - Step 113201: {'lr': 7.247441302957858e-05, 'samples': 21734592, 'steps': 113200, 'loss/train': 1.0296813249588013} 08/31/2021 09:43:50 - INFO - __main__ - Step 113202: {'lr': 7.247067659899812e-05, 'samples': 21734784, 'steps': 113201, 'loss/train': 0.4879051446914673} 08/31/2021 09:43:50 - INFO - __main__ - Step 113203: {'lr': 7.24669402484096e-05, 'samples': 21734976, 'steps': 113202, 'loss/train': 1.690802812576294} 08/31/2021 09:43:51 - INFO - __main__ - Step 113204: {'lr': 7.246320397781478e-05, 'samples': 21735168, 'steps': 113203, 'loss/train': 0.4573197662830353} 08/31/2021 09:43:52 - INFO - __main__ - Step 113205: {'lr': 7.245946778721526e-05, 'samples': 21735360, 'steps': 113204, 'loss/train': 1.3472660779953003} 08/31/2021 09:43:53 - INFO - __main__ - Step 113206: {'lr': 7.245573167661282e-05, 'samples': 21735552, 'steps': 113205, 'loss/train': 1.3771753311157227} 08/31/2021 09:43:53 - INFO - __main__ - Step 113207: {'lr': 7.245199564600904e-05, 'samples': 21735744, 'steps': 113206, 'loss/train': 1.4202053546905518} 08/31/2021 09:43:53 - INFO - __main__ - Step 113208: {'lr': 7.244825969540566e-05, 'samples': 21735936, 'steps': 113207, 'loss/train': 1.3469655513763428} 08/31/2021 09:43:54 - INFO - __main__ - Step 113209: {'lr': 7.244452382480435e-05, 'samples': 21736128, 'steps': 113208, 'loss/train': 1.2610646486282349} 08/31/2021 09:43:56 - INFO - __main__ - Step 113210: {'lr': 7.244078803420689e-05, 'samples': 21736320, 'steps': 113209, 'loss/train': 0.8808621764183044} 08/31/2021 09:43:56 - INFO - __main__ - Step 113211: {'lr': 7.24370523236148e-05, 'samples': 21736512, 'steps': 113210, 'loss/train': 3.4173357486724854} 08/31/2021 09:43:57 - INFO - __main__ - Step 113212: {'lr': 7.243331669302982e-05, 'samples': 21736704, 'steps': 113211, 'loss/train': 1.3407907485961914} 08/31/2021 09:43:57 - INFO - __main__ - Step 113213: {'lr': 7.242958114245365e-05, 'samples': 21736896, 'steps': 113212, 'loss/train': 1.5666682720184326} 08/31/2021 09:43:57 - INFO - __main__ - Step 113214: {'lr': 7.242584567188796e-05, 'samples': 21737088, 'steps': 113213, 'loss/train': 1.689592957496643} 08/31/2021 09:43:59 - INFO - __main__ - Step 113215: {'lr': 7.242211028133447e-05, 'samples': 21737280, 'steps': 113214, 'loss/train': 1.0357059240341187} 08/31/2021 09:44:00 - INFO - __main__ - Step 113216: {'lr': 7.241837497079481e-05, 'samples': 21737472, 'steps': 113215, 'loss/train': 1.1865160465240479} 08/31/2021 09:44:00 - INFO - __main__ - Step 113217: {'lr': 7.241463974027072e-05, 'samples': 21737664, 'steps': 113216, 'loss/train': 1.263972520828247} 08/31/2021 09:44:00 - INFO - __main__ - Step 113218: {'lr': 7.241090458976382e-05, 'samples': 21737856, 'steps': 113217, 'loss/train': 1.067287802696228} 08/31/2021 09:44:01 - INFO - __main__ - Step 113219: {'lr': 7.240716951927584e-05, 'samples': 21738048, 'steps': 113218, 'loss/train': 1.2513436079025269} 08/31/2021 09:44:01 - INFO - __main__ - Step 113220: {'lr': 7.240343452880843e-05, 'samples': 21738240, 'steps': 113219, 'loss/train': 0.5545637011528015} 08/31/2021 09:44:03 - INFO - __main__ - Step 113221: {'lr': 7.239969961836332e-05, 'samples': 21738432, 'steps': 113220, 'loss/train': 0.5258058309555054} 08/31/2021 09:44:03 - INFO - __main__ - Step 113222: {'lr': 7.239596478794216e-05, 'samples': 21738624, 'steps': 113221, 'loss/train': 0.9871225357055664} 08/31/2021 09:44:03 - INFO - __main__ - Step 113223: {'lr': 7.239223003754672e-05, 'samples': 21738816, 'steps': 113222, 'loss/train': 1.4074419736862183} 08/31/2021 09:44:04 - INFO - __main__ - Step 113224: {'lr': 7.238849536717851e-05, 'samples': 21739008, 'steps': 113223, 'loss/train': 0.12633837759494781} 08/31/2021 09:44:04 - INFO - __main__ - Step 113225: {'lr': 7.23847607768393e-05, 'samples': 21739200, 'steps': 113224, 'loss/train': 0.04879723861813545} 08/31/2021 09:44:06 - INFO - __main__ - Step 113226: {'lr': 7.238102626653079e-05, 'samples': 21739392, 'steps': 113225, 'loss/train': 0.1472608894109726} 08/31/2021 09:44:06 - INFO - __main__ - Step 113227: {'lr': 7.237729183625463e-05, 'samples': 21739584, 'steps': 113226, 'loss/train': 1.1675435304641724} 08/31/2021 09:44:06 - INFO - __main__ - Step 113228: {'lr': 7.237355748601255e-05, 'samples': 21739776, 'steps': 113227, 'loss/train': 0.1359301060438156} 08/31/2021 09:44:07 - INFO - __main__ - Step 113229: {'lr': 7.236982321580618e-05, 'samples': 21739968, 'steps': 113228, 'loss/train': 2.1910736560821533} 08/31/2021 09:44:07 - INFO - __main__ - Step 113230: {'lr': 7.236608902563724e-05, 'samples': 21740160, 'steps': 113229, 'loss/train': 1.1145206689834595} 08/31/2021 09:44:09 - INFO - __main__ - Step 113231: {'lr': 7.236235491550738e-05, 'samples': 21740352, 'steps': 113230, 'loss/train': 0.31507551670074463} 08/31/2021 09:44:09 - INFO - __main__ - Step 113232: {'lr': 7.23586208854183e-05, 'samples': 21740544, 'steps': 113231, 'loss/train': 1.1938657760620117} 08/31/2021 09:44:09 - INFO - __main__ - Step 113233: {'lr': 7.235488693537171e-05, 'samples': 21740736, 'steps': 113232, 'loss/train': 1.7081420421600342} 08/31/2021 09:44:10 - INFO - __main__ - Step 113234: {'lr': 7.235115306536927e-05, 'samples': 21740928, 'steps': 113233, 'loss/train': 1.1434121131896973} 08/31/2021 09:44:10 - INFO - __main__ - Step 113235: {'lr': 7.234741927541264e-05, 'samples': 21741120, 'steps': 113234, 'loss/train': 0.791170597076416} 08/31/2021 09:44:12 - INFO - __main__ - Step 113236: {'lr': 7.234368556550353e-05, 'samples': 21741312, 'steps': 113235, 'loss/train': 0.8959822654724121} 08/31/2021 09:44:12 - INFO - __main__ - Step 113237: {'lr': 7.233995193564369e-05, 'samples': 21741504, 'steps': 113236, 'loss/train': 1.1229536533355713} 08/31/2021 09:44:12 - INFO - __main__ - Step 113238: {'lr': 7.233621838583462e-05, 'samples': 21741696, 'steps': 113237, 'loss/train': 1.3009155988693237} 08/31/2021 09:44:13 - INFO - __main__ - Step 113239: {'lr': 7.233248491607816e-05, 'samples': 21741888, 'steps': 113238, 'loss/train': 1.2705012559890747} 08/31/2021 09:44:13 - INFO - __main__ - Step 113240: {'lr': 7.232875152637591e-05, 'samples': 21742080, 'steps': 113239, 'loss/train': 0.31952279806137085} 08/31/2021 09:44:15 - INFO - __main__ - Step 113241: {'lr': 7.232501821672957e-05, 'samples': 21742272, 'steps': 113240, 'loss/train': 1.5889084339141846} 08/31/2021 09:44:15 - INFO - __main__ - Step 113242: {'lr': 7.232128498714086e-05, 'samples': 21742464, 'steps': 113241, 'loss/train': 1.2520347833633423} 08/31/2021 09:44:16 - INFO - __main__ - Step 113243: {'lr': 7.231755183761143e-05, 'samples': 21742656, 'steps': 113242, 'loss/train': 1.9574878215789795} 08/31/2021 09:44:16 - INFO - __main__ - Step 113244: {'lr': 7.231381876814296e-05, 'samples': 21742848, 'steps': 113243, 'loss/train': 1.044800043106079} 08/31/2021 09:44:16 - INFO - __main__ - Step 113245: {'lr': 7.231008577873719e-05, 'samples': 21743040, 'steps': 113244, 'loss/train': 1.2578339576721191} 08/31/2021 09:44:17 - INFO - __main__ - Step 113246: {'lr': 7.230635286939569e-05, 'samples': 21743232, 'steps': 113245, 'loss/train': 0.985244631767273} 08/31/2021 09:44:18 - INFO - __main__ - Step 113247: {'lr': 7.230262004012023e-05, 'samples': 21743424, 'steps': 113246, 'loss/train': 0.20220865309238434} 08/31/2021 09:44:19 - INFO - __main__ - Step 113248: {'lr': 7.229888729091247e-05, 'samples': 21743616, 'steps': 113247, 'loss/train': 1.240445613861084} 08/31/2021 09:44:19 - INFO - __main__ - Step 113249: {'lr': 7.229515462177408e-05, 'samples': 21743808, 'steps': 113248, 'loss/train': 0.8569369316101074} 08/31/2021 09:44:19 - INFO - __main__ - Step 113250: {'lr': 7.229142203270687e-05, 'samples': 21744000, 'steps': 113249, 'loss/train': 1.3710154294967651} 08/31/2021 09:44:20 - INFO - __main__ - Step 113251: {'lr': 7.228768952371226e-05, 'samples': 21744192, 'steps': 113250, 'loss/train': 1.4934865236282349} 08/31/2021 09:44:21 - INFO - __main__ - Step 113252: {'lr': 7.22839570947921e-05, 'samples': 21744384, 'steps': 113251, 'loss/train': 1.0622550249099731} 08/31/2021 09:44:22 - INFO - __main__ - Step 113253: {'lr': 7.228022474594805e-05, 'samples': 21744576, 'steps': 113252, 'loss/train': 1.2919594049453735} 08/31/2021 09:44:22 - INFO - __main__ - Step 113254: {'lr': 7.227649247718182e-05, 'samples': 21744768, 'steps': 113253, 'loss/train': 0.869090735912323} 08/31/2021 09:44:23 - INFO - __main__ - Step 113255: {'lr': 7.227276028849503e-05, 'samples': 21744960, 'steps': 113254, 'loss/train': 0.7222226858139038} 08/31/2021 09:44:23 - INFO - __main__ - Step 113256: {'lr': 7.22690281798894e-05, 'samples': 21745152, 'steps': 113255, 'loss/train': 1.4826993942260742} 08/31/2021 09:44:25 - INFO - __main__ - Step 113257: {'lr': 7.226529615136657e-05, 'samples': 21745344, 'steps': 113256, 'loss/train': 1.3513110876083374} 08/31/2021 09:44:25 - INFO - __main__ - Step 113258: {'lr': 7.226156420292829e-05, 'samples': 21745536, 'steps': 113257, 'loss/train': 0.1820281744003296} 08/31/2021 09:44:25 - INFO - __main__ - Step 113259: {'lr': 7.225783233457619e-05, 'samples': 21745728, 'steps': 113258, 'loss/train': 1.2229039669036865} 08/31/2021 09:44:26 - INFO - __main__ - Step 113260: {'lr': 7.225410054631199e-05, 'samples': 21745920, 'steps': 113259, 'loss/train': 1.9680014848709106} 08/31/2021 09:44:26 - INFO - __main__ - Step 113261: {'lr': 7.225036883813733e-05, 'samples': 21746112, 'steps': 113260, 'loss/train': 1.0433495044708252} 08/31/2021 09:44:28 - INFO - __main__ - Step 113262: {'lr': 7.224663721005393e-05, 'samples': 21746304, 'steps': 113261, 'loss/train': 1.3454705476760864} 08/31/2021 09:44:28 - INFO - __main__ - Step 113263: {'lr': 7.224290566206343e-05, 'samples': 21746496, 'steps': 113262, 'loss/train': 1.3381160497665405} 08/31/2021 09:44:29 - INFO - __main__ - Step 113264: {'lr': 7.223917419416762e-05, 'samples': 21746688, 'steps': 113263, 'loss/train': 0.7932295203208923} 08/31/2021 09:44:29 - INFO - __main__ - Step 113265: {'lr': 7.223544280636802e-05, 'samples': 21746880, 'steps': 113264, 'loss/train': 1.6056835651397705} 08/31/2021 09:44:29 - INFO - __main__ - Step 113266: {'lr': 7.223171149866636e-05, 'samples': 21747072, 'steps': 113265, 'loss/train': 0.5494537353515625} 08/31/2021 09:44:31 - INFO - __main__ - Step 113267: {'lr': 7.222798027106439e-05, 'samples': 21747264, 'steps': 113266, 'loss/train': 1.1247614622116089} 08/31/2021 09:44:32 - INFO - __main__ - Step 113268: {'lr': 7.222424912356373e-05, 'samples': 21747456, 'steps': 113267, 'loss/train': 1.3011020421981812} 08/31/2021 09:44:32 - INFO - __main__ - Step 113269: {'lr': 7.222051805616609e-05, 'samples': 21747648, 'steps': 113268, 'loss/train': 0.39709654450416565} 08/31/2021 09:44:32 - INFO - __main__ - Step 113270: {'lr': 7.22167870688731e-05, 'samples': 21747840, 'steps': 113269, 'loss/train': 1.593183159828186} 08/31/2021 09:44:33 - INFO - __main__ - Step 113271: {'lr': 7.221305616168653e-05, 'samples': 21748032, 'steps': 113270, 'loss/train': 1.1309888362884521} 08/31/2021 09:44:33 - INFO - __main__ - Step 113272: {'lr': 7.2209325334608e-05, 'samples': 21748224, 'steps': 113271, 'loss/train': 1.5464074611663818} 08/31/2021 09:44:35 - INFO - __main__ - Step 113273: {'lr': 7.22055945876392e-05, 'samples': 21748416, 'steps': 113272, 'loss/train': 1.0398175716400146} 08/31/2021 09:44:35 - INFO - __main__ - Step 113274: {'lr': 7.220186392078182e-05, 'samples': 21748608, 'steps': 113273, 'loss/train': 1.70883047580719} 08/31/2021 09:44:36 - INFO - __main__ - Step 113275: {'lr': 7.219813333403755e-05, 'samples': 21748800, 'steps': 113274, 'loss/train': 0.07075464725494385} 08/31/2021 09:44:36 - INFO - __main__ - Step 113276: {'lr': 7.219440282740802e-05, 'samples': 21748992, 'steps': 113275, 'loss/train': 1.0187644958496094} 08/31/2021 09:44:36 - INFO - __main__ - Step 113277: {'lr': 7.219067240089505e-05, 'samples': 21749184, 'steps': 113276, 'loss/train': 0.7887349724769592} 08/31/2021 09:44:38 - INFO - __main__ - Step 113278: {'lr': 7.218694205450013e-05, 'samples': 21749376, 'steps': 113277, 'loss/train': 1.249826431274414} 08/31/2021 09:44:38 - INFO - __main__ - Step 113279: {'lr': 7.218321178822507e-05, 'samples': 21749568, 'steps': 113278, 'loss/train': 0.9940664768218994} 08/31/2021 09:44:39 - INFO - __main__ - Step 113280: {'lr': 7.217948160207147e-05, 'samples': 21749760, 'steps': 113279, 'loss/train': 1.73610520362854} 08/31/2021 09:44:39 - INFO - __main__ - Step 113281: {'lr': 7.217575149604105e-05, 'samples': 21749952, 'steps': 113280, 'loss/train': 1.1136558055877686} 08/31/2021 09:44:39 - INFO - __main__ - Step 113282: {'lr': 7.217202147013552e-05, 'samples': 21750144, 'steps': 113281, 'loss/train': 0.7678488492965698} 08/31/2021 09:44:41 - INFO - __main__ - Step 113283: {'lr': 7.21682915243565e-05, 'samples': 21750336, 'steps': 113282, 'loss/train': 1.5039902925491333} 08/31/2021 09:44:41 - INFO - __main__ - Step 113284: {'lr': 7.216456165870572e-05, 'samples': 21750528, 'steps': 113283, 'loss/train': 1.0460872650146484} 08/31/2021 09:44:42 - INFO - __main__ - Step 113285: {'lr': 7.216083187318487e-05, 'samples': 21750720, 'steps': 113284, 'loss/train': 1.3873350620269775} 08/31/2021 09:44:42 - INFO - __main__ - Step 113286: {'lr': 7.215710216779555e-05, 'samples': 21750912, 'steps': 113285, 'loss/train': 0.9699088931083679} 08/31/2021 09:44:42 - INFO - __main__ - Step 113287: {'lr': 7.215337254253954e-05, 'samples': 21751104, 'steps': 113286, 'loss/train': 0.9739986062049866} 08/31/2021 09:44:44 - INFO - __main__ - Step 113288: {'lr': 7.214964299741847e-05, 'samples': 21751296, 'steps': 113287, 'loss/train': 1.6150304079055786} 08/31/2021 09:44:45 - INFO - __main__ - Step 113289: {'lr': 7.214591353243402e-05, 'samples': 21751488, 'steps': 113288, 'loss/train': 1.437255620956421} 08/31/2021 09:44:45 - INFO - __main__ - Step 113290: {'lr': 7.214218414758786e-05, 'samples': 21751680, 'steps': 113289, 'loss/train': 0.9510161876678467} 08/31/2021 09:44:45 - INFO - __main__ - Step 113291: {'lr': 7.213845484288179e-05, 'samples': 21751872, 'steps': 113290, 'loss/train': 0.014565889723598957} 08/31/2021 09:44:46 - INFO - __main__ - Step 113292: {'lr': 7.21347256183173e-05, 'samples': 21752064, 'steps': 113291, 'loss/train': 1.4766424894332886} 08/31/2021 09:44:46 - INFO - __main__ - Step 113293: {'lr': 7.213099647389614e-05, 'samples': 21752256, 'steps': 113292, 'loss/train': 0.9808146357536316} 08/31/2021 09:44:46 - INFO - __main__ - Step 113294: {'lr': 7.212726740962002e-05, 'samples': 21752448, 'steps': 113293, 'loss/train': 1.160266399383545} 08/31/2021 09:44:48 - INFO - __main__ - Step 113295: {'lr': 7.212353842549064e-05, 'samples': 21752640, 'steps': 113294, 'loss/train': 0.2549428343772888} 08/31/2021 09:44:48 - INFO - __main__ - Step 113296: {'lr': 7.211980952150962e-05, 'samples': 21752832, 'steps': 113295, 'loss/train': 1.1134063005447388} 08/31/2021 09:44:49 - INFO - __main__ - Step 113297: {'lr': 7.211608069767867e-05, 'samples': 21753024, 'steps': 113296, 'loss/train': 0.1198142021894455} 08/31/2021 09:44:49 - INFO - __main__ - Step 113298: {'lr': 7.211235195399948e-05, 'samples': 21753216, 'steps': 113297, 'loss/train': 1.177230715751648} 08/31/2021 09:44:49 - INFO - __main__ - Step 113299: {'lr': 7.210862329047371e-05, 'samples': 21753408, 'steps': 113298, 'loss/train': 1.1353212594985962} 08/31/2021 09:44:51 - INFO - __main__ - Step 113300: {'lr': 7.210489470710304e-05, 'samples': 21753600, 'steps': 113299, 'loss/train': 1.4334425926208496} 08/31/2021 09:44:51 - INFO - __main__ - Step 113301: {'lr': 7.210116620388917e-05, 'samples': 21753792, 'steps': 113300, 'loss/train': 0.547300398349762} 08/31/2021 09:44:52 - INFO - __main__ - Step 113302: {'lr': 7.209743778083377e-05, 'samples': 21753984, 'steps': 113301, 'loss/train': 1.0300047397613525} 08/31/2021 09:44:52 - INFO - __main__ - Step 113303: {'lr': 7.209370943793853e-05, 'samples': 21754176, 'steps': 113302, 'loss/train': 1.4804495573043823} 08/31/2021 09:44:53 - INFO - __main__ - Step 113304: {'lr': 7.208998117520518e-05, 'samples': 21754368, 'steps': 113303, 'loss/train': 1.2782227993011475} 08/31/2021 09:44:54 - INFO - __main__ - Step 113305: {'lr': 7.208625299263526e-05, 'samples': 21754560, 'steps': 113304, 'loss/train': 0.615229606628418} 08/31/2021 09:44:55 - INFO - __main__ - Step 113306: {'lr': 7.208252489023054e-05, 'samples': 21754752, 'steps': 113305, 'loss/train': 1.1495873928070068} 08/31/2021 09:44:55 - INFO - __main__ - Step 113307: {'lr': 7.207879686799268e-05, 'samples': 21754944, 'steps': 113306, 'loss/train': 0.9267144799232483} 08/31/2021 09:44:55 - INFO - __main__ - Step 113308: {'lr': 7.207506892592339e-05, 'samples': 21755136, 'steps': 113307, 'loss/train': 1.114638328552246} 08/31/2021 09:44:56 - INFO - __main__ - Step 113309: {'lr': 7.20713410640243e-05, 'samples': 21755328, 'steps': 113308, 'loss/train': 0.8211297988891602} 08/31/2021 09:44:56 - INFO - __main__ - Step 113310: {'lr': 7.206761328229714e-05, 'samples': 21755520, 'steps': 113309, 'loss/train': 1.2976049184799194} 08/31/2021 09:44:58 - INFO - __main__ - Step 113311: {'lr': 7.206388558074356e-05, 'samples': 21755712, 'steps': 113310, 'loss/train': 1.0578244924545288} 08/31/2021 09:44:58 - INFO - __main__ - Step 113312: {'lr': 7.206015795936524e-05, 'samples': 21755904, 'steps': 113311, 'loss/train': 1.505265474319458} 08/31/2021 09:44:58 - INFO - __main__ - Step 113313: {'lr': 7.205643041816387e-05, 'samples': 21756096, 'steps': 113312, 'loss/train': 1.3926657438278198} 08/31/2021 09:44:59 - INFO - __main__ - Step 113314: {'lr': 7.205270295714111e-05, 'samples': 21756288, 'steps': 113313, 'loss/train': 0.9146608114242554} 08/31/2021 09:44:59 - INFO - __main__ - Step 113315: {'lr': 7.204897557629869e-05, 'samples': 21756480, 'steps': 113314, 'loss/train': 0.1319427788257599} 08/31/2021 09:45:01 - INFO - __main__ - Step 113316: {'lr': 7.204524827563824e-05, 'samples': 21756672, 'steps': 113315, 'loss/train': 1.406707525253296} 08/31/2021 09:45:01 - INFO - __main__ - Step 113317: {'lr': 7.204152105516154e-05, 'samples': 21756864, 'steps': 113316, 'loss/train': 1.0454576015472412} 08/31/2021 09:45:01 - INFO - __main__ - Step 113318: {'lr': 7.203779391487009e-05, 'samples': 21757056, 'steps': 113317, 'loss/train': 1.2318509817123413} 08/31/2021 09:45:02 - INFO - __main__ - Step 113319: {'lr': 7.203406685476568e-05, 'samples': 21757248, 'steps': 113318, 'loss/train': 1.4349427223205566} 08/31/2021 09:45:02 - INFO - __main__ - Step 113320: {'lr': 7.203033987484997e-05, 'samples': 21757440, 'steps': 113319, 'loss/train': 0.920571506023407} 08/31/2021 09:45:05 - INFO - __main__ - Step 113321: {'lr': 7.202661297512464e-05, 'samples': 21757632, 'steps': 113320, 'loss/train': 6.314053058624268} 08/31/2021 09:45:05 - INFO - __main__ - Step 113322: {'lr': 7.202288615559138e-05, 'samples': 21757824, 'steps': 113321, 'loss/train': 1.7444806098937988} 08/31/2021 09:45:06 - INFO - __main__ - Step 113323: {'lr': 7.201915941625184e-05, 'samples': 21758016, 'steps': 113322, 'loss/train': 1.0371133089065552} 08/31/2021 09:45:06 - INFO - __main__ - Step 113324: {'lr': 7.201543275710773e-05, 'samples': 21758208, 'steps': 113323, 'loss/train': 0.06803109496831894} 08/31/2021 09:45:06 - INFO - __main__ - Step 113325: {'lr': 7.201170617816072e-05, 'samples': 21758400, 'steps': 113324, 'loss/train': 1.4423000812530518} 08/31/2021 09:45:08 - INFO - __main__ - Step 113326: {'lr': 7.20079796794125e-05, 'samples': 21758592, 'steps': 113325, 'loss/train': 0.2675439417362213} 08/31/2021 09:45:08 - INFO - __main__ - Step 113327: {'lr': 7.200425326086474e-05, 'samples': 21758784, 'steps': 113326, 'loss/train': 1.3175921440124512} 08/31/2021 09:45:09 - INFO - __main__ - Step 113328: {'lr': 7.20005269225191e-05, 'samples': 21758976, 'steps': 113327, 'loss/train': 1.5441726446151733} 08/31/2021 09:45:09 - INFO - __main__ - Step 113329: {'lr': 7.199680066437728e-05, 'samples': 21759168, 'steps': 113328, 'loss/train': 0.7725979089736938} 08/31/2021 09:45:09 - INFO - __main__ - Step 113330: {'lr': 7.199307448644097e-05, 'samples': 21759360, 'steps': 113329, 'loss/train': 0.6193888187408447} 08/31/2021 09:45:11 - INFO - __main__ - Step 113331: {'lr': 7.198934838871187e-05, 'samples': 21759552, 'steps': 113330, 'loss/train': 1.2488831281661987} 08/31/2021 09:45:12 - INFO - __main__ - Step 113332: {'lr': 7.198562237119158e-05, 'samples': 21759744, 'steps': 113331, 'loss/train': 1.7818613052368164} 08/31/2021 09:45:12 - INFO - __main__ - Step 113333: {'lr': 7.198189643388184e-05, 'samples': 21759936, 'steps': 113332, 'loss/train': 0.7775626182556152} 08/31/2021 09:45:12 - INFO - __main__ - Step 113334: {'lr': 7.197817057678427e-05, 'samples': 21760128, 'steps': 113333, 'loss/train': 0.998144268989563} 08/31/2021 09:45:13 - INFO - __main__ - Step 113335: {'lr': 7.197444479990062e-05, 'samples': 21760320, 'steps': 113334, 'loss/train': 1.3043839931488037} 08/31/2021 09:45:13 - INFO - __main__ - Step 113336: {'lr': 7.197071910323252e-05, 'samples': 21760512, 'steps': 113335, 'loss/train': 1.0565075874328613} 08/31/2021 09:45:15 - INFO - __main__ - Step 113337: {'lr': 7.196699348678165e-05, 'samples': 21760704, 'steps': 113336, 'loss/train': 1.2901743650436401} 08/31/2021 09:45:15 - INFO - __main__ - Step 113338: {'lr': 7.196326795054974e-05, 'samples': 21760896, 'steps': 113337, 'loss/train': 2.9091577529907227} 08/31/2021 09:45:15 - INFO - __main__ - Step 113339: {'lr': 7.195954249453842e-05, 'samples': 21761088, 'steps': 113338, 'loss/train': 1.351494550704956} 08/31/2021 09:45:16 - INFO - __main__ - Step 113340: {'lr': 7.195581711874938e-05, 'samples': 21761280, 'steps': 113339, 'loss/train': 1.3935376405715942} 08/31/2021 09:45:16 - INFO - __main__ - Step 113341: {'lr': 7.19520918231843e-05, 'samples': 21761472, 'steps': 113340, 'loss/train': 1.1201608180999756} 08/31/2021 09:45:18 - INFO - __main__ - Step 113342: {'lr': 7.194836660784487e-05, 'samples': 21761664, 'steps': 113341, 'loss/train': 1.6062803268432617} 08/31/2021 09:45:18 - INFO - __main__ - Step 113343: {'lr': 7.194464147273275e-05, 'samples': 21761856, 'steps': 113342, 'loss/train': 1.2668441534042358} 08/31/2021 09:45:18 - INFO - __main__ - Step 113344: {'lr': 7.194091641784969e-05, 'samples': 21762048, 'steps': 113343, 'loss/train': 0.9931762218475342} 08/31/2021 09:45:19 - INFO - __main__ - Step 113345: {'lr': 7.193719144319727e-05, 'samples': 21762240, 'steps': 113344, 'loss/train': 0.705877423286438} 08/31/2021 09:45:19 - INFO - __main__ - Step 113346: {'lr': 7.193346654877717e-05, 'samples': 21762432, 'steps': 113345, 'loss/train': 1.8872647285461426} 08/31/2021 09:45:21 - INFO - __main__ - Step 113347: {'lr': 7.19297417345911e-05, 'samples': 21762624, 'steps': 113346, 'loss/train': 0.969926655292511} 08/31/2021 09:45:21 - INFO - __main__ - Step 113348: {'lr': 7.192601700064078e-05, 'samples': 21762816, 'steps': 113347, 'loss/train': 0.8040785193443298} 08/31/2021 09:45:21 - INFO - __main__ - Step 113349: {'lr': 7.192229234692779e-05, 'samples': 21763008, 'steps': 113348, 'loss/train': 1.261809229850769} 08/31/2021 09:45:22 - INFO - __main__ - Step 113350: {'lr': 7.19185677734539e-05, 'samples': 21763200, 'steps': 113349, 'loss/train': 0.024187518283724785} 08/31/2021 09:45:22 - INFO - __main__ - Step 113351: {'lr': 7.191484328022077e-05, 'samples': 21763392, 'steps': 113350, 'loss/train': 1.2081325054168701} 08/31/2021 09:45:24 - INFO - __main__ - Step 113352: {'lr': 7.191111886723003e-05, 'samples': 21763584, 'steps': 113351, 'loss/train': 0.5015157461166382} 08/31/2021 09:45:24 - INFO - __main__ - Step 113353: {'lr': 7.190739453448341e-05, 'samples': 21763776, 'steps': 113352, 'loss/train': 1.2407915592193604} 08/31/2021 09:45:24 - INFO - __main__ - Step 113354: {'lr': 7.190367028198258e-05, 'samples': 21763968, 'steps': 113353, 'loss/train': 0.800521731376648} 08/31/2021 09:45:25 - INFO - __main__ - Step 113355: {'lr': 7.189994610972919e-05, 'samples': 21764160, 'steps': 113354, 'loss/train': 0.9780237674713135} 08/31/2021 09:45:25 - INFO - __main__ - Step 113356: {'lr': 7.189622201772494e-05, 'samples': 21764352, 'steps': 113355, 'loss/train': 1.0722322463989258} 08/31/2021 09:45:27 - INFO - __main__ - Step 113357: {'lr': 7.18924980059715e-05, 'samples': 21764544, 'steps': 113356, 'loss/train': 1.1522740125656128} 08/31/2021 09:45:27 - INFO - __main__ - Step 113358: {'lr': 7.188877407447065e-05, 'samples': 21764736, 'steps': 113357, 'loss/train': 1.2047439813613892} 08/31/2021 09:45:28 - INFO - __main__ - Step 113359: {'lr': 7.188505022322386e-05, 'samples': 21764928, 'steps': 113358, 'loss/train': 1.6483819484710693} 08/31/2021 09:45:28 - INFO - __main__ - Step 113360: {'lr': 7.188132645223295e-05, 'samples': 21765120, 'steps': 113359, 'loss/train': 4.5500030517578125} 08/31/2021 09:45:28 - INFO - __main__ - Step 113361: {'lr': 7.187760276149954e-05, 'samples': 21765312, 'steps': 113360, 'loss/train': 0.9562759399414062} 08/31/2021 09:45:29 - INFO - __main__ - Step 113362: {'lr': 7.187387915102536e-05, 'samples': 21765504, 'steps': 113361, 'loss/train': 1.794416904449463} 08/31/2021 09:45:30 - INFO - __main__ - Step 113363: {'lr': 7.187015562081203e-05, 'samples': 21765696, 'steps': 113362, 'loss/train': 1.1473618745803833} 08/31/2021 09:45:31 - INFO - __main__ - Step 113364: {'lr': 7.186643217086128e-05, 'samples': 21765888, 'steps': 113363, 'loss/train': 0.6598923802375793} 08/31/2021 09:45:31 - INFO - __main__ - Step 113365: {'lr': 7.186270880117476e-05, 'samples': 21766080, 'steps': 113364, 'loss/train': 1.5689326524734497} 08/31/2021 09:45:31 - INFO - __main__ - Step 113366: {'lr': 7.185898551175418e-05, 'samples': 21766272, 'steps': 113365, 'loss/train': 1.513916254043579} 08/31/2021 09:45:32 - INFO - __main__ - Step 113367: {'lr': 7.185526230260117e-05, 'samples': 21766464, 'steps': 113366, 'loss/train': 0.9253721833229065} 08/31/2021 09:45:33 - INFO - __main__ - Step 113368: {'lr': 7.185153917371742e-05, 'samples': 21766656, 'steps': 113367, 'loss/train': 1.3017531633377075} 08/31/2021 09:45:34 - INFO - __main__ - Step 113369: {'lr': 7.184781612510464e-05, 'samples': 21766848, 'steps': 113368, 'loss/train': 1.1346575021743774} 08/31/2021 09:45:34 - INFO - __main__ - Step 113370: {'lr': 7.184409315676446e-05, 'samples': 21767040, 'steps': 113369, 'loss/train': 1.6432675123214722} 08/31/2021 09:45:34 - INFO - __main__ - Step 113371: {'lr': 7.184037026869867e-05, 'samples': 21767232, 'steps': 113370, 'loss/train': 1.2775975465774536} 08/31/2021 09:45:35 - INFO - __main__ - Step 113372: {'lr': 7.183664746090879e-05, 'samples': 21767424, 'steps': 113371, 'loss/train': 1.223647952079773} 08/31/2021 09:45:36 - INFO - __main__ - Step 113373: {'lr': 7.183292473339656e-05, 'samples': 21767616, 'steps': 113372, 'loss/train': 1.515497088432312} 08/31/2021 09:45:37 - INFO - __main__ - Step 113374: {'lr': 7.182920208616367e-05, 'samples': 21767808, 'steps': 113373, 'loss/train': 1.415842056274414} 08/31/2021 09:45:37 - INFO - __main__ - Step 113375: {'lr': 7.182547951921178e-05, 'samples': 21768000, 'steps': 113374, 'loss/train': 0.9074731469154358} 08/31/2021 09:45:37 - INFO - __main__ - Step 113376: {'lr': 7.18217570325426e-05, 'samples': 21768192, 'steps': 113375, 'loss/train': 1.7629411220550537} 08/31/2021 09:45:38 - INFO - __main__ - Step 113377: {'lr': 7.181803462615777e-05, 'samples': 21768384, 'steps': 113376, 'loss/train': 1.0246202945709229} 08/31/2021 09:45:40 - INFO - __main__ - Step 113378: {'lr': 7.1814312300059e-05, 'samples': 21768576, 'steps': 113377, 'loss/train': 1.4115744829177856} 08/31/2021 09:45:40 - INFO - __main__ - Step 113379: {'lr': 7.181059005424793e-05, 'samples': 21768768, 'steps': 113378, 'loss/train': 0.950774610042572} 08/31/2021 09:45:40 - INFO - __main__ - Step 113380: {'lr': 7.180686788872628e-05, 'samples': 21768960, 'steps': 113379, 'loss/train': 0.7505215406417847} 08/31/2021 09:45:41 - INFO - __main__ - Step 113381: {'lr': 7.180314580349568e-05, 'samples': 21769152, 'steps': 113380, 'loss/train': 0.6930930614471436} 08/31/2021 09:45:41 - INFO - __main__ - Step 113382: {'lr': 7.179942379855786e-05, 'samples': 21769344, 'steps': 113381, 'loss/train': 1.3282277584075928} 08/31/2021 09:45:43 - INFO - __main__ - Step 113383: {'lr': 7.179570187391454e-05, 'samples': 21769536, 'steps': 113382, 'loss/train': 1.3165013790130615} 08/31/2021 09:45:43 - INFO - __main__ - Step 113384: {'lr': 7.179198002956724e-05, 'samples': 21769728, 'steps': 113383, 'loss/train': 1.1669385433197021} 08/31/2021 09:45:44 - INFO - __main__ - Step 113385: {'lr': 7.178825826551772e-05, 'samples': 21769920, 'steps': 113384, 'loss/train': 1.5242836475372314} 08/31/2021 09:45:44 - INFO - __main__ - Step 113386: {'lr': 7.178453658176767e-05, 'samples': 21770112, 'steps': 113385, 'loss/train': 0.6998988389968872} 08/31/2021 09:45:44 - INFO - __main__ - Step 113387: {'lr': 7.178081497831877e-05, 'samples': 21770304, 'steps': 113386, 'loss/train': 1.7802003622055054} 08/31/2021 09:45:45 - INFO - __main__ - Step 113388: {'lr': 7.177709345517266e-05, 'samples': 21770496, 'steps': 113387, 'loss/train': 0.8803568482398987} 08/31/2021 09:45:46 - INFO - __main__ - Step 113389: {'lr': 7.177337201233106e-05, 'samples': 21770688, 'steps': 113388, 'loss/train': 1.3187882900238037} 08/31/2021 09:45:47 - INFO - __main__ - Step 113390: {'lr': 7.176965064979562e-05, 'samples': 21770880, 'steps': 113389, 'loss/train': 0.09133922308683395} 08/31/2021 09:45:47 - INFO - __main__ - Step 113391: {'lr': 7.176592936756801e-05, 'samples': 21771072, 'steps': 113390, 'loss/train': 1.2102687358856201} 08/31/2021 09:45:48 - INFO - __main__ - Step 113392: {'lr': 7.176220816564995e-05, 'samples': 21771264, 'steps': 113391, 'loss/train': 1.1359137296676636} 08/31/2021 09:45:48 - INFO - __main__ - Step 113393: {'lr': 7.175848704404309e-05, 'samples': 21771456, 'steps': 113392, 'loss/train': 1.1741018295288086} 08/31/2021 09:45:50 - INFO - __main__ - Step 113394: {'lr': 7.175476600274916e-05, 'samples': 21771648, 'steps': 113393, 'loss/train': 1.0690088272094727} 08/31/2021 09:45:50 - INFO - __main__ - Step 113395: {'lr': 7.175104504176971e-05, 'samples': 21771840, 'steps': 113394, 'loss/train': 1.2545706033706665} 08/31/2021 09:45:51 - INFO - __main__ - Step 113396: {'lr': 7.174732416110649e-05, 'samples': 21772032, 'steps': 113395, 'loss/train': 1.4071037769317627} 08/31/2021 09:45:51 - INFO - __main__ - Step 113397: {'lr': 7.17436033607612e-05, 'samples': 21772224, 'steps': 113396, 'loss/train': 0.8133677244186401} 08/31/2021 09:45:51 - INFO - __main__ - Step 113398: {'lr': 7.173988264073544e-05, 'samples': 21772416, 'steps': 113397, 'loss/train': 1.2029898166656494} 08/31/2021 09:45:53 - INFO - __main__ - Step 113399: {'lr': 7.173616200103098e-05, 'samples': 21772608, 'steps': 113398, 'loss/train': 1.472524881362915} 08/31/2021 09:45:53 - INFO - __main__ - Step 113400: {'lr': 7.173244144164945e-05, 'samples': 21772800, 'steps': 113399, 'loss/train': 1.3771227598190308} 08/31/2021 09:45:54 - INFO - __main__ - Step 113401: {'lr': 7.172872096259253e-05, 'samples': 21772992, 'steps': 113400, 'loss/train': 1.4108067750930786} 08/31/2021 09:45:54 - INFO - __main__ - Step 113402: {'lr': 7.172500056386189e-05, 'samples': 21773184, 'steps': 113401, 'loss/train': 0.7081584930419922} 08/31/2021 09:45:54 - INFO - __main__ - Step 113403: {'lr': 7.17212802454592e-05, 'samples': 21773376, 'steps': 113402, 'loss/train': 0.2356492578983307} 08/31/2021 09:45:56 - INFO - __main__ - Step 113404: {'lr': 7.171756000738616e-05, 'samples': 21773568, 'steps': 113403, 'loss/train': 1.4317662715911865} 08/31/2021 09:45:56 - INFO - __main__ - Step 113405: {'lr': 7.171383984964452e-05, 'samples': 21773760, 'steps': 113404, 'loss/train': 0.9383253455162048} 08/31/2021 09:45:56 - INFO - __main__ - Step 113406: {'lr': 7.171011977223579e-05, 'samples': 21773952, 'steps': 113405, 'loss/train': 1.536413311958313} 08/31/2021 09:45:57 - INFO - __main__ - Step 113407: {'lr': 7.170639977516174e-05, 'samples': 21774144, 'steps': 113406, 'loss/train': 1.069211483001709} 08/31/2021 09:45:57 - INFO - __main__ - Step 113408: {'lr': 7.170267985842405e-05, 'samples': 21774336, 'steps': 113407, 'loss/train': 1.4103068113327026} 08/31/2021 09:45:59 - INFO - __main__ - Step 113409: {'lr': 7.169896002202434e-05, 'samples': 21774528, 'steps': 113408, 'loss/train': 0.7148852944374084} 08/31/2021 09:45:59 - INFO - __main__ - Step 113410: {'lr': 7.169524026596436e-05, 'samples': 21774720, 'steps': 113409, 'loss/train': 0.883463442325592} 08/31/2021 09:46:00 - INFO - __main__ - Step 113411: {'lr': 7.169152059024572e-05, 'samples': 21774912, 'steps': 113410, 'loss/train': 0.32142719626426697} 08/31/2021 09:46:00 - INFO - __main__ - Step 113412: {'lr': 7.168780099487016e-05, 'samples': 21775104, 'steps': 113411, 'loss/train': 0.7559950351715088} 08/31/2021 09:46:00 - INFO - __main__ - Step 113413: {'lr': 7.168408147983931e-05, 'samples': 21775296, 'steps': 113412, 'loss/train': 0.9729152917861938} 08/31/2021 09:46:01 - INFO - __main__ - Step 113414: {'lr': 7.168036204515487e-05, 'samples': 21775488, 'steps': 113413, 'loss/train': 0.601172149181366} 08/31/2021 09:46:02 - INFO - __main__ - Step 113415: {'lr': 7.16766426908185e-05, 'samples': 21775680, 'steps': 113414, 'loss/train': 0.8520907163619995} 08/31/2021 09:46:03 - INFO - __main__ - Step 113416: {'lr': 7.167292341683196e-05, 'samples': 21775872, 'steps': 113415, 'loss/train': 1.1217418909072876} 08/31/2021 09:46:03 - INFO - __main__ - Step 113417: {'lr': 7.166920422319678e-05, 'samples': 21776064, 'steps': 113416, 'loss/train': 1.2133655548095703} 08/31/2021 09:46:03 - INFO - __main__ - Step 113418: {'lr': 7.16654851099147e-05, 'samples': 21776256, 'steps': 113417, 'loss/train': 1.0727169513702393} 08/31/2021 09:46:04 - INFO - __main__ - Step 113419: {'lr': 7.16617660769874e-05, 'samples': 21776448, 'steps': 113418, 'loss/train': 1.4931718111038208} 08/31/2021 09:46:05 - INFO - __main__ - Step 113420: {'lr': 7.165804712441656e-05, 'samples': 21776640, 'steps': 113419, 'loss/train': 0.2885744869709015} 08/31/2021 09:46:06 - INFO - __main__ - Step 113421: {'lr': 7.165432825220384e-05, 'samples': 21776832, 'steps': 113420, 'loss/train': 1.6933873891830444} 08/31/2021 09:46:06 - INFO - __main__ - Step 113422: {'lr': 7.165060946035093e-05, 'samples': 21777024, 'steps': 113421, 'loss/train': 1.235766053199768} 08/31/2021 09:46:06 - INFO - __main__ - Step 113423: {'lr': 7.164689074885952e-05, 'samples': 21777216, 'steps': 113422, 'loss/train': 1.7088161706924438} 08/31/2021 09:46:07 - INFO - __main__ - Step 113424: {'lr': 7.164317211773125e-05, 'samples': 21777408, 'steps': 113423, 'loss/train': 0.4154934287071228} 08/31/2021 09:46:08 - INFO - __main__ - Step 113425: {'lr': 7.163945356696782e-05, 'samples': 21777600, 'steps': 113424, 'loss/train': 0.727858304977417} 08/31/2021 09:46:09 - INFO - __main__ - Step 113426: {'lr': 7.163573509657098e-05, 'samples': 21777792, 'steps': 113425, 'loss/train': 1.4438563585281372} 08/31/2021 09:46:09 - INFO - __main__ - Step 113427: {'lr': 7.163201670654226e-05, 'samples': 21777984, 'steps': 113426, 'loss/train': 0.9929177165031433} 08/31/2021 09:46:09 - INFO - __main__ - Step 113428: {'lr': 7.16282983968834e-05, 'samples': 21778176, 'steps': 113427, 'loss/train': 0.34366393089294434} 08/31/2021 09:46:10 - INFO - __main__ - Step 113429: {'lr': 7.162458016759604e-05, 'samples': 21778368, 'steps': 113428, 'loss/train': 1.1316546201705933} 08/31/2021 09:46:12 - INFO - __main__ - Step 113430: {'lr': 7.162086201868192e-05, 'samples': 21778560, 'steps': 113429, 'loss/train': 1.1987898349761963} 08/31/2021 09:46:12 - INFO - __main__ - Step 113431: {'lr': 7.161714395014272e-05, 'samples': 21778752, 'steps': 113430, 'loss/train': 0.7115366458892822} 08/31/2021 09:46:13 - INFO - __main__ - Step 113432: {'lr': 7.161342596198004e-05, 'samples': 21778944, 'steps': 113431, 'loss/train': 0.3030114471912384} 08/31/2021 09:46:13 - INFO - __main__ - Step 113433: {'lr': 7.160970805419558e-05, 'samples': 21779136, 'steps': 113432, 'loss/train': 1.036576509475708} 08/31/2021 09:46:13 - INFO - __main__ - Step 113434: {'lr': 7.160599022679107e-05, 'samples': 21779328, 'steps': 113433, 'loss/train': 1.1794159412384033} 08/31/2021 09:46:15 - INFO - __main__ - Step 113435: {'lr': 7.160227247976814e-05, 'samples': 21779520, 'steps': 113434, 'loss/train': 0.974152147769928} 08/31/2021 09:46:15 - INFO - __main__ - Step 113436: {'lr': 7.159855481312846e-05, 'samples': 21779712, 'steps': 113435, 'loss/train': 0.5206267237663269} 08/31/2021 09:46:16 - INFO - __main__ - Step 113437: {'lr': 7.15948372268737e-05, 'samples': 21779904, 'steps': 113436, 'loss/train': 0.8723707795143127} 08/31/2021 09:46:16 - INFO - __main__ - Step 113438: {'lr': 7.159111972100568e-05, 'samples': 21780096, 'steps': 113437, 'loss/train': 1.034998893737793} 08/31/2021 09:46:16 - INFO - __main__ - Step 113439: {'lr': 7.158740229552585e-05, 'samples': 21780288, 'steps': 113438, 'loss/train': 1.1947619915008545} 08/31/2021 09:46:17 - INFO - __main__ - Step 113440: {'lr': 7.158368495043599e-05, 'samples': 21780480, 'steps': 113439, 'loss/train': 1.0814768075942993} 08/31/2021 09:46:18 - INFO - __main__ - Step 113441: {'lr': 7.157996768573773e-05, 'samples': 21780672, 'steps': 113440, 'loss/train': 0.6000176072120667} 08/31/2021 09:46:19 - INFO - __main__ - Step 113442: {'lr': 7.157625050143282e-05, 'samples': 21780864, 'steps': 113441, 'loss/train': 1.2239813804626465} 08/31/2021 09:46:19 - INFO - __main__ - Step 113443: {'lr': 7.15725333975229e-05, 'samples': 21781056, 'steps': 113442, 'loss/train': 1.1901901960372925} 08/31/2021 09:46:19 - INFO - __main__ - Step 113444: {'lr': 7.156881637400964e-05, 'samples': 21781248, 'steps': 113443, 'loss/train': 1.438033938407898} 08/31/2021 09:46:20 - INFO - __main__ - Step 113445: {'lr': 7.156509943089471e-05, 'samples': 21781440, 'steps': 113444, 'loss/train': 1.0209804773330688} 08/31/2021 09:46:21 - INFO - __main__ - Step 113446: {'lr': 7.156138256817979e-05, 'samples': 21781632, 'steps': 113445, 'loss/train': 1.0036643743515015} 08/31/2021 09:46:22 - INFO - __main__ - Step 113447: {'lr': 7.155766578586656e-05, 'samples': 21781824, 'steps': 113446, 'loss/train': 0.8094987273216248} 08/31/2021 09:46:22 - INFO - __main__ - Step 113448: {'lr': 7.155394908395671e-05, 'samples': 21782016, 'steps': 113447, 'loss/train': 2.505713701248169} 08/31/2021 09:46:22 - INFO - __main__ - Step 113449: {'lr': 7.155023246245188e-05, 'samples': 21782208, 'steps': 113448, 'loss/train': 0.9744122624397278} 08/31/2021 09:46:23 - INFO - __main__ - Step 113450: {'lr': 7.154651592135374e-05, 'samples': 21782400, 'steps': 113449, 'loss/train': 0.9301955103874207} 08/31/2021 09:46:24 - INFO - __main__ - Step 113451: {'lr': 7.154279946066402e-05, 'samples': 21782592, 'steps': 113450, 'loss/train': 0.4999869167804718} 08/31/2021 09:46:25 - INFO - __main__ - Step 113452: {'lr': 7.153908308038446e-05, 'samples': 21782784, 'steps': 113451, 'loss/train': 1.2885558605194092} 08/31/2021 09:46:25 - INFO - __main__ - Step 113453: {'lr': 7.153536678051651e-05, 'samples': 21782976, 'steps': 113452, 'loss/train': 1.2403223514556885} 08/31/2021 09:46:26 - INFO - __main__ - Step 113454: {'lr': 7.153165056106197e-05, 'samples': 21783168, 'steps': 113453, 'loss/train': 2.3033008575439453} 08/31/2021 09:46:26 - INFO - __main__ - Step 113455: {'lr': 7.152793442202254e-05, 'samples': 21783360, 'steps': 113454, 'loss/train': 1.105201244354248} 08/31/2021 09:46:27 - INFO - __main__ - Step 113456: {'lr': 7.152421836339987e-05, 'samples': 21783552, 'steps': 113455, 'loss/train': 1.0548826456069946} 08/31/2021 09:46:28 - INFO - __main__ - Step 113457: {'lr': 7.152050238519561e-05, 'samples': 21783744, 'steps': 113456, 'loss/train': 0.9070226550102234} 08/31/2021 09:46:28 - INFO - __main__ - Step 113458: {'lr': 7.151678648741148e-05, 'samples': 21783936, 'steps': 113457, 'loss/train': 1.5054714679718018} 08/31/2021 09:46:29 - INFO - __main__ - Step 113459: {'lr': 7.151307067004911e-05, 'samples': 21784128, 'steps': 113458, 'loss/train': 1.0912226438522339} 08/31/2021 09:46:29 - INFO - __main__ - Step 113460: {'lr': 7.150935493311023e-05, 'samples': 21784320, 'steps': 113459, 'loss/train': 1.327492356300354} 08/31/2021 09:46:29 - INFO - __main__ - Step 113461: {'lr': 7.150563927659645e-05, 'samples': 21784512, 'steps': 113460, 'loss/train': 0.7451297640800476} 08/31/2021 09:46:31 - INFO - __main__ - Step 113462: {'lr': 7.150192370050948e-05, 'samples': 21784704, 'steps': 113461, 'loss/train': 0.6902769207954407} 08/31/2021 09:46:31 - INFO - __main__ - Step 113463: {'lr': 7.149820820485098e-05, 'samples': 21784896, 'steps': 113462, 'loss/train': 0.49852454662323} 08/31/2021 09:46:32 - INFO - __main__ - Step 113464: {'lr': 7.149449278962267e-05, 'samples': 21785088, 'steps': 113463, 'loss/train': 1.0584745407104492} 08/31/2021 09:46:32 - INFO - __main__ - Step 113465: {'lr': 7.14907774548262e-05, 'samples': 21785280, 'steps': 113464, 'loss/train': 0.5405767560005188} 08/31/2021 09:46:32 - INFO - __main__ - Step 113466: {'lr': 7.148706220046322e-05, 'samples': 21785472, 'steps': 113465, 'loss/train': 0.34283939003944397} 08/31/2021 09:46:34 - INFO - __main__ - Step 113467: {'lr': 7.148334702653539e-05, 'samples': 21785664, 'steps': 113466, 'loss/train': 0.8728058934211731} 08/31/2021 09:46:34 - INFO - __main__ - Step 113468: {'lr': 7.147963193304441e-05, 'samples': 21785856, 'steps': 113467, 'loss/train': 1.3693580627441406} 08/31/2021 09:46:35 - INFO - __main__ - Step 113469: {'lr': 7.147591691999195e-05, 'samples': 21786048, 'steps': 113468, 'loss/train': 1.118285894393921} 08/31/2021 09:46:35 - INFO - __main__ - Step 113470: {'lr': 7.147220198737966e-05, 'samples': 21786240, 'steps': 113469, 'loss/train': 0.6516579985618591} 08/31/2021 09:46:35 - INFO - __main__ - Step 113471: {'lr': 7.146848713520929e-05, 'samples': 21786432, 'steps': 113470, 'loss/train': 1.0188833475112915} 08/31/2021 09:46:37 - INFO - __main__ - Step 113472: {'lr': 7.146477236348245e-05, 'samples': 21786624, 'steps': 113471, 'loss/train': 1.2270855903625488} 08/31/2021 09:46:37 - INFO - __main__ - Step 113473: {'lr': 7.146105767220082e-05, 'samples': 21786816, 'steps': 113472, 'loss/train': 0.9415907859802246} 08/31/2021 09:46:38 - INFO - __main__ - Step 113474: {'lr': 7.145734306136609e-05, 'samples': 21787008, 'steps': 113473, 'loss/train': 1.0917742252349854} 08/31/2021 09:46:38 - INFO - __main__ - Step 113475: {'lr': 7.145362853097989e-05, 'samples': 21787200, 'steps': 113474, 'loss/train': 1.6657965183258057} 08/31/2021 09:46:38 - INFO - __main__ - Step 113476: {'lr': 7.144991408104398e-05, 'samples': 21787392, 'steps': 113475, 'loss/train': 0.6839932799339294} 08/31/2021 09:46:40 - INFO - __main__ - Step 113477: {'lr': 7.144619971155997e-05, 'samples': 21787584, 'steps': 113476, 'loss/train': 0.8010446429252625} 08/31/2021 09:46:40 - INFO - __main__ - Step 113478: {'lr': 7.144248542252954e-05, 'samples': 21787776, 'steps': 113477, 'loss/train': 1.5340954065322876} 08/31/2021 09:46:41 - INFO - __main__ - Step 113479: {'lr': 7.143877121395445e-05, 'samples': 21787968, 'steps': 113478, 'loss/train': 1.1381607055664062} 08/31/2021 09:46:41 - INFO - __main__ - Step 113480: {'lr': 7.14350570858362e-05, 'samples': 21788160, 'steps': 113479, 'loss/train': 0.6068199872970581} 08/31/2021 09:46:41 - INFO - __main__ - Step 113481: {'lr': 7.143134303817659e-05, 'samples': 21788352, 'steps': 113480, 'loss/train': 0.7500712871551514} 08/31/2021 09:46:43 - INFO - __main__ - Step 113482: {'lr': 7.142762907097721e-05, 'samples': 21788544, 'steps': 113481, 'loss/train': 0.9502185583114624} 08/31/2021 09:46:44 - INFO - __main__ - Step 113483: {'lr': 7.142391518423986e-05, 'samples': 21788736, 'steps': 113482, 'loss/train': 0.6961057186126709} 08/31/2021 09:46:44 - INFO - __main__ - Step 113484: {'lr': 7.142020137796606e-05, 'samples': 21788928, 'steps': 113483, 'loss/train': 1.098626971244812} 08/31/2021 09:46:45 - INFO - __main__ - Step 113485: {'lr': 7.141648765215761e-05, 'samples': 21789120, 'steps': 113484, 'loss/train': 1.1608537435531616} 08/31/2021 09:46:45 - INFO - __main__ - Step 113486: {'lr': 7.141277400681615e-05, 'samples': 21789312, 'steps': 113485, 'loss/train': 0.7716169357299805} 08/31/2021 09:46:45 - INFO - __main__ - Step 113487: {'lr': 7.140906044194329e-05, 'samples': 21789504, 'steps': 113486, 'loss/train': 1.5560516119003296} 08/31/2021 09:46:47 - INFO - __main__ - Step 113488: {'lr': 7.140534695754078e-05, 'samples': 21789696, 'steps': 113487, 'loss/train': 0.3871087431907654} 08/31/2021 09:46:48 - INFO - __main__ - Step 113489: {'lr': 7.140163355361027e-05, 'samples': 21789888, 'steps': 113488, 'loss/train': 0.08932065218687057} 08/31/2021 09:46:48 - INFO - __main__ - Step 113490: {'lr': 7.13979202301534e-05, 'samples': 21790080, 'steps': 113489, 'loss/train': 1.6447923183441162} 08/31/2021 09:46:48 - INFO - __main__ - Step 113491: {'lr': 7.139420698717188e-05, 'samples': 21790272, 'steps': 113490, 'loss/train': 1.1204386949539185} 08/31/2021 09:46:49 - INFO - __main__ - Step 113492: {'lr': 7.139049382466747e-05, 'samples': 21790464, 'steps': 113491, 'loss/train': 1.1294608116149902} 08/31/2021 09:46:51 - INFO - __main__ - Step 113493: {'lr': 7.138678074264165e-05, 'samples': 21790656, 'steps': 113492, 'loss/train': 0.9493091106414795} 08/31/2021 09:46:51 - INFO - __main__ - Step 113494: {'lr': 7.138306774109621e-05, 'samples': 21790848, 'steps': 113493, 'loss/train': 3.364781141281128} 08/31/2021 09:46:51 - INFO - __main__ - Step 113495: {'lr': 7.13793548200328e-05, 'samples': 21791040, 'steps': 113494, 'loss/train': 3.8762643337249756} 08/31/2021 09:46:52 - INFO - __main__ - Step 113496: {'lr': 7.137564197945309e-05, 'samples': 21791232, 'steps': 113495, 'loss/train': 2.0084261894226074} 08/31/2021 09:46:52 - INFO - __main__ - Step 113497: {'lr': 7.137192921935876e-05, 'samples': 21791424, 'steps': 113496, 'loss/train': 2.5197479724884033} 08/31/2021 09:46:52 - INFO - __main__ - Step 113498: {'lr': 7.136821653975147e-05, 'samples': 21791616, 'steps': 113497, 'loss/train': 1.7517961263656616} 08/31/2021 09:46:54 - INFO - __main__ - Step 113499: {'lr': 7.136450394063293e-05, 'samples': 21791808, 'steps': 113498, 'loss/train': 0.9892088770866394} 08/31/2021 09:46:55 - INFO - __main__ - Step 113500: {'lr': 7.136079142200478e-05, 'samples': 21792000, 'steps': 113499, 'loss/train': 1.4978324174880981} 08/31/2021 09:46:55 - INFO - __main__ - Step 113501: {'lr': 7.13570789838687e-05, 'samples': 21792192, 'steps': 113500, 'loss/train': 0.7888227105140686} 08/31/2021 09:46:55 - INFO - __main__ - Step 113502: {'lr': 7.135336662622635e-05, 'samples': 21792384, 'steps': 113501, 'loss/train': 1.317430019378662} 08/31/2021 09:46:56 - INFO - __main__ - Step 113503: {'lr': 7.134965434907942e-05, 'samples': 21792576, 'steps': 113502, 'loss/train': 0.04490915313363075} 08/31/2021 09:46:58 - INFO - __main__ - Step 113504: {'lr': 7.134594215242959e-05, 'samples': 21792768, 'steps': 113503, 'loss/train': 1.1543723344802856} 08/31/2021 09:46:58 - INFO - __main__ - Step 113505: {'lr': 7.134223003627851e-05, 'samples': 21792960, 'steps': 113504, 'loss/train': 1.0377278327941895} 08/31/2021 09:46:59 - INFO - __main__ - Step 113506: {'lr': 7.133851800062796e-05, 'samples': 21793152, 'steps': 113505, 'loss/train': 0.08415980637073517} 08/31/2021 09:46:59 - INFO - __main__ - Step 113507: {'lr': 7.133480604547943e-05, 'samples': 21793344, 'steps': 113506, 'loss/train': 0.6793307065963745} 08/31/2021 09:46:59 - INFO - __main__ - Step 113508: {'lr': 7.133109417083466e-05, 'samples': 21793536, 'steps': 113507, 'loss/train': 1.4105298519134521} 08/31/2021 09:47:00 - INFO - __main__ - Step 113509: {'lr': 7.132738237669536e-05, 'samples': 21793728, 'steps': 113508, 'loss/train': 0.9199883937835693} 08/31/2021 09:47:01 - INFO - __main__ - Step 113510: {'lr': 7.132367066306319e-05, 'samples': 21793920, 'steps': 113509, 'loss/train': 0.8006671071052551} 08/31/2021 09:47:02 - INFO - __main__ - Step 113511: {'lr': 7.131995902993981e-05, 'samples': 21794112, 'steps': 113510, 'loss/train': 1.12050461769104} 08/31/2021 09:47:02 - INFO - __main__ - Step 113512: {'lr': 7.13162474773269e-05, 'samples': 21794304, 'steps': 113511, 'loss/train': 2.158926486968994} 08/31/2021 09:47:02 - INFO - __main__ - Step 113513: {'lr': 7.131253600522614e-05, 'samples': 21794496, 'steps': 113512, 'loss/train': 1.1309692859649658} 08/31/2021 09:47:03 - INFO - __main__ - Step 113514: {'lr': 7.130882461363916e-05, 'samples': 21794688, 'steps': 113513, 'loss/train': 1.3122062683105469} 08/31/2021 09:47:04 - INFO - __main__ - Step 113515: {'lr': 7.13051133025677e-05, 'samples': 21794880, 'steps': 113514, 'loss/train': 0.9663839340209961} 08/31/2021 09:47:05 - INFO - __main__ - Step 113516: {'lr': 7.130140207201338e-05, 'samples': 21795072, 'steps': 113515, 'loss/train': 0.7891799807548523} 08/31/2021 09:47:05 - INFO - __main__ - Step 113517: {'lr': 7.129769092197791e-05, 'samples': 21795264, 'steps': 113516, 'loss/train': 1.2658264636993408} 08/31/2021 09:47:05 - INFO - __main__ - Step 113518: {'lr': 7.129397985246294e-05, 'samples': 21795456, 'steps': 113517, 'loss/train': 1.6087616682052612} 08/31/2021 09:47:06 - INFO - __main__ - Step 113519: {'lr': 7.12902688634702e-05, 'samples': 21795648, 'steps': 113518, 'loss/train': 1.2320479154586792} 08/31/2021 09:47:07 - INFO - __main__ - Step 113520: {'lr': 7.128655795500127e-05, 'samples': 21795840, 'steps': 113519, 'loss/train': 1.7939777374267578} 08/31/2021 09:47:07 - INFO - __main__ - Step 113521: {'lr': 7.128284712705782e-05, 'samples': 21796032, 'steps': 113520, 'loss/train': 1.2786487340927124} 08/31/2021 09:47:08 - INFO - __main__ - Step 113522: {'lr': 7.12791363796416e-05, 'samples': 21796224, 'steps': 113521, 'loss/train': 0.8717381358146667} 08/31/2021 09:47:08 - INFO - __main__ - Step 113523: {'lr': 7.127542571275419e-05, 'samples': 21796416, 'steps': 113522, 'loss/train': 1.1534483432769775} 08/31/2021 09:47:09 - INFO - __main__ - Step 113524: {'lr': 7.127171512639735e-05, 'samples': 21796608, 'steps': 113523, 'loss/train': 1.4613254070281982} 08/31/2021 09:47:10 - INFO - __main__ - Step 113525: {'lr': 7.126800462057273e-05, 'samples': 21796800, 'steps': 113524, 'loss/train': 1.0477917194366455} 08/31/2021 09:47:10 - INFO - __main__ - Step 113526: {'lr': 7.126429419528196e-05, 'samples': 21796992, 'steps': 113525, 'loss/train': 1.3297035694122314} 08/31/2021 09:47:11 - INFO - __main__ - Step 113527: {'lr': 7.126058385052676e-05, 'samples': 21797184, 'steps': 113526, 'loss/train': 1.0064918994903564} 08/31/2021 09:47:11 - INFO - __main__ - Step 113528: {'lr': 7.125687358630878e-05, 'samples': 21797376, 'steps': 113527, 'loss/train': 1.0468236207962036} 08/31/2021 09:47:11 - INFO - __main__ - Step 113529: {'lr': 7.125316340262969e-05, 'samples': 21797568, 'steps': 113528, 'loss/train': 1.0714433193206787} 08/31/2021 09:47:13 - INFO - __main__ - Step 113530: {'lr': 7.124945329949115e-05, 'samples': 21797760, 'steps': 113529, 'loss/train': 0.6013715267181396} 08/31/2021 09:47:14 - INFO - __main__ - Step 113531: {'lr': 7.124574327689487e-05, 'samples': 21797952, 'steps': 113530, 'loss/train': 0.473018616437912} 08/31/2021 09:47:14 - INFO - __main__ - Step 113532: {'lr': 7.12420333348425e-05, 'samples': 21798144, 'steps': 113531, 'loss/train': 1.1713894605636597} 08/31/2021 09:47:14 - INFO - __main__ - Step 113533: {'lr': 7.123832347333578e-05, 'samples': 21798336, 'steps': 113532, 'loss/train': 0.8772453665733337} 08/31/2021 09:47:15 - INFO - __main__ - Step 113534: {'lr': 7.123461369237624e-05, 'samples': 21798528, 'steps': 113533, 'loss/train': 2.0628855228424072} 08/31/2021 09:47:16 - INFO - __main__ - Step 113535: {'lr': 7.12309039919656e-05, 'samples': 21798720, 'steps': 113534, 'loss/train': 1.1580593585968018} 08/31/2021 09:47:17 - INFO - __main__ - Step 113536: {'lr': 7.12271943721056e-05, 'samples': 21798912, 'steps': 113535, 'loss/train': 0.6127545833587646} 08/31/2021 09:47:17 - INFO - __main__ - Step 113537: {'lr': 7.122348483279783e-05, 'samples': 21799104, 'steps': 113536, 'loss/train': 0.11432858556509018} 08/31/2021 09:47:17 - INFO - __main__ - Step 113538: {'lr': 7.121977537404403e-05, 'samples': 21799296, 'steps': 113537, 'loss/train': 1.0539685487747192} 08/31/2021 09:47:18 - INFO - __main__ - Step 113539: {'lr': 7.121606599584582e-05, 'samples': 21799488, 'steps': 113538, 'loss/train': 1.2304643392562866} 08/31/2021 09:47:20 - INFO - __main__ - Step 113540: {'lr': 7.121235669820489e-05, 'samples': 21799680, 'steps': 113539, 'loss/train': 1.318448543548584} 08/31/2021 09:47:20 - INFO - __main__ - Step 113541: {'lr': 7.120864748112293e-05, 'samples': 21799872, 'steps': 113540, 'loss/train': 1.1890252828598022} 08/31/2021 09:47:21 - INFO - __main__ - Step 113542: {'lr': 7.12049383446016e-05, 'samples': 21800064, 'steps': 113541, 'loss/train': 0.17726470530033112} 08/31/2021 09:47:21 - INFO - __main__ - Step 113543: {'lr': 7.120122928864253e-05, 'samples': 21800256, 'steps': 113542, 'loss/train': 0.37208810448646545} 08/31/2021 09:47:21 - INFO - __main__ - Step 113544: {'lr': 7.119752031324745e-05, 'samples': 21800448, 'steps': 113543, 'loss/train': 1.359953761100769} 08/31/2021 09:47:23 - INFO - __main__ - Step 113545: {'lr': 7.119381141841802e-05, 'samples': 21800640, 'steps': 113544, 'loss/train': 1.2633105516433716} 08/31/2021 09:47:23 - INFO - __main__ - Step 113546: {'lr': 7.119010260415595e-05, 'samples': 21800832, 'steps': 113545, 'loss/train': 1.1732370853424072} 08/31/2021 09:47:24 - INFO - __main__ - Step 113547: {'lr': 7.118639387046281e-05, 'samples': 21801024, 'steps': 113546, 'loss/train': 0.5445592999458313} 08/31/2021 09:47:24 - INFO - __main__ - Step 113548: {'lr': 7.11826852173403e-05, 'samples': 21801216, 'steps': 113547, 'loss/train': 0.7833221554756165} 08/31/2021 09:47:24 - INFO - __main__ - Step 113549: {'lr': 7.117897664479012e-05, 'samples': 21801408, 'steps': 113548, 'loss/train': 1.1280244588851929} 08/31/2021 09:47:26 - INFO - __main__ - Step 113550: {'lr': 7.117526815281394e-05, 'samples': 21801600, 'steps': 113549, 'loss/train': 0.4510924816131592} 08/31/2021 09:47:26 - INFO - __main__ - Step 113551: {'lr': 7.11715597414134e-05, 'samples': 21801792, 'steps': 113550, 'loss/train': 1.1873116493225098} 08/31/2021 09:47:27 - INFO - __main__ - Step 113552: {'lr': 7.116785141059023e-05, 'samples': 21801984, 'steps': 113551, 'loss/train': 0.5986300110816956} 08/31/2021 09:47:27 - INFO - __main__ - Step 113553: {'lr': 7.116414316034606e-05, 'samples': 21802176, 'steps': 113552, 'loss/train': 0.03696345537900925} 08/31/2021 09:47:27 - INFO - __main__ - Step 113554: {'lr': 7.116043499068256e-05, 'samples': 21802368, 'steps': 113553, 'loss/train': 0.45495063066482544} 08/31/2021 09:47:29 - INFO - __main__ - Step 113555: {'lr': 7.11567269016014e-05, 'samples': 21802560, 'steps': 113554, 'loss/train': 1.4914458990097046} 08/31/2021 09:47:29 - INFO - __main__ - Step 113556: {'lr': 7.115301889310427e-05, 'samples': 21802752, 'steps': 113555, 'loss/train': 0.9512845873832703} 08/31/2021 09:47:30 - INFO - __main__ - Step 113557: {'lr': 7.114931096519281e-05, 'samples': 21802944, 'steps': 113556, 'loss/train': 1.2126928567886353} 08/31/2021 09:47:30 - INFO - __main__ - Step 113558: {'lr': 7.114560311786874e-05, 'samples': 21803136, 'steps': 113557, 'loss/train': 0.32822540402412415} 08/31/2021 09:47:30 - INFO - __main__ - Step 113559: {'lr': 7.114189535113377e-05, 'samples': 21803328, 'steps': 113558, 'loss/train': 0.7244760990142822} 08/31/2021 09:47:31 - INFO - __main__ - Step 113560: {'lr': 7.113818766498942e-05, 'samples': 21803520, 'steps': 113559, 'loss/train': 0.8458096981048584} 08/31/2021 09:47:32 - INFO - __main__ - Step 113561: {'lr': 7.113448005943743e-05, 'samples': 21803712, 'steps': 113560, 'loss/train': 1.6406139135360718} 08/31/2021 09:47:33 - INFO - __main__ - Step 113562: {'lr': 7.11307725344795e-05, 'samples': 21803904, 'steps': 113561, 'loss/train': 1.228643774986267} 08/31/2021 09:47:33 - INFO - __main__ - Step 113563: {'lr': 7.11270650901173e-05, 'samples': 21804096, 'steps': 113562, 'loss/train': 1.390008807182312} 08/31/2021 09:47:33 - INFO - __main__ - Step 113564: {'lr': 7.112335772635245e-05, 'samples': 21804288, 'steps': 113563, 'loss/train': 1.6768628358840942} 08/31/2021 09:47:34 - INFO - __main__ - Step 113565: {'lr': 7.111965044318667e-05, 'samples': 21804480, 'steps': 113564, 'loss/train': 1.2136822938919067} 08/31/2021 09:47:35 - INFO - __main__ - Step 113566: {'lr': 7.111594324062162e-05, 'samples': 21804672, 'steps': 113565, 'loss/train': 0.44567346572875977} 08/31/2021 09:47:36 - INFO - __main__ - Step 113567: {'lr': 7.111223611865895e-05, 'samples': 21804864, 'steps': 113566, 'loss/train': 1.946810245513916} 08/31/2021 09:47:36 - INFO - __main__ - Step 113568: {'lr': 7.110852907730036e-05, 'samples': 21805056, 'steps': 113567, 'loss/train': 2.148937940597534} 08/31/2021 09:47:36 - INFO - __main__ - Step 113569: {'lr': 7.11048221165475e-05, 'samples': 21805248, 'steps': 113568, 'loss/train': 1.1325151920318604} 08/31/2021 09:47:37 - INFO - __main__ - Step 113570: {'lr': 7.110111523640205e-05, 'samples': 21805440, 'steps': 113569, 'loss/train': 1.2338454723358154} 08/31/2021 09:47:38 - INFO - __main__ - Step 113571: {'lr': 7.109740843686568e-05, 'samples': 21805632, 'steps': 113570, 'loss/train': 1.2555323839187622} 08/31/2021 09:47:39 - INFO - __main__ - Step 113572: {'lr': 7.109370171794005e-05, 'samples': 21805824, 'steps': 113571, 'loss/train': 1.1066241264343262} 08/31/2021 09:47:39 - INFO - __main__ - Step 113573: {'lr': 7.10899950796269e-05, 'samples': 21806016, 'steps': 113572, 'loss/train': 0.8996406197547913} 08/31/2021 09:47:39 - INFO - __main__ - Step 113574: {'lr': 7.10862885219278e-05, 'samples': 21806208, 'steps': 113573, 'loss/train': 0.21404659748077393} 08/31/2021 09:47:40 - INFO - __main__ - Step 113575: {'lr': 7.108258204484445e-05, 'samples': 21806400, 'steps': 113574, 'loss/train': 1.0211724042892456} 08/31/2021 09:47:41 - INFO - __main__ - Step 113576: {'lr': 7.10788756483785e-05, 'samples': 21806592, 'steps': 113575, 'loss/train': 1.2819287776947021} 08/31/2021 09:47:42 - INFO - __main__ - Step 113577: {'lr': 7.107516933253166e-05, 'samples': 21806784, 'steps': 113576, 'loss/train': 1.3440968990325928} 08/31/2021 09:47:42 - INFO - __main__ - Step 113578: {'lr': 7.107146309730558e-05, 'samples': 21806976, 'steps': 113577, 'loss/train': 1.2394466400146484} 08/31/2021 09:47:42 - INFO - __main__ - Step 113579: {'lr': 7.106775694270196e-05, 'samples': 21807168, 'steps': 113578, 'loss/train': 0.9382379651069641} 08/31/2021 09:47:43 - INFO - __main__ - Step 113580: {'lr': 7.106405086872242e-05, 'samples': 21807360, 'steps': 113579, 'loss/train': 0.980208158493042} 08/31/2021 09:47:44 - INFO - __main__ - Step 113581: {'lr': 7.106034487536866e-05, 'samples': 21807552, 'steps': 113580, 'loss/train': 1.2378020286560059} 08/31/2021 09:47:45 - INFO - __main__ - Step 113582: {'lr': 7.105663896264236e-05, 'samples': 21807744, 'steps': 113581, 'loss/train': 1.4630454778671265} 08/31/2021 09:47:45 - INFO - __main__ - Step 113583: {'lr': 7.10529331305452e-05, 'samples': 21807936, 'steps': 113582, 'loss/train': 1.1877557039260864} 08/31/2021 09:47:45 - INFO - __main__ - Step 113584: {'lr': 7.104922737907879e-05, 'samples': 21808128, 'steps': 113583, 'loss/train': 1.2268600463867188} 08/31/2021 09:47:46 - INFO - __main__ - Step 113585: {'lr': 7.104552170824485e-05, 'samples': 21808320, 'steps': 113584, 'loss/train': 1.1934857368469238} 08/31/2021 09:47:47 - INFO - __main__ - Step 113586: {'lr': 7.10418161180451e-05, 'samples': 21808512, 'steps': 113585, 'loss/train': 0.7060359120368958} 08/31/2021 09:47:48 - INFO - __main__ - Step 113587: {'lr': 7.10381106084811e-05, 'samples': 21808704, 'steps': 113586, 'loss/train': 1.3404333591461182} 08/31/2021 09:47:48 - INFO - __main__ - Step 113588: {'lr': 7.103440517955454e-05, 'samples': 21808896, 'steps': 113587, 'loss/train': 1.6362546682357788} 08/31/2021 09:47:49 - INFO - __main__ - Step 113589: {'lr': 7.103069983126714e-05, 'samples': 21809088, 'steps': 113588, 'loss/train': 0.8506374955177307} 08/31/2021 09:47:49 - INFO - __main__ - Step 113590: {'lr': 7.102699456362053e-05, 'samples': 21809280, 'steps': 113589, 'loss/train': 1.4831788539886475} 08/31/2021 09:47:51 - INFO - __main__ - Step 113591: {'lr': 7.102328937661637e-05, 'samples': 21809472, 'steps': 113590, 'loss/train': 0.7134632468223572} 08/31/2021 09:47:51 - INFO - __main__ - Step 113592: {'lr': 7.10195842702564e-05, 'samples': 21809664, 'steps': 113591, 'loss/train': 1.2465275526046753} 08/31/2021 09:47:52 - INFO - __main__ - Step 113593: {'lr': 7.10158792445422e-05, 'samples': 21809856, 'steps': 113592, 'loss/train': 1.275012731552124} 08/31/2021 09:47:52 - INFO - __main__ - Step 113594: {'lr': 7.101217429947552e-05, 'samples': 21810048, 'steps': 113593, 'loss/train': 0.4642576575279236} 08/31/2021 09:47:52 - INFO - __main__ - Step 113595: {'lr': 7.100846943505799e-05, 'samples': 21810240, 'steps': 113594, 'loss/train': 0.8254144787788391} 08/31/2021 09:47:54 - INFO - __main__ - Step 113596: {'lr': 7.100476465129125e-05, 'samples': 21810432, 'steps': 113595, 'loss/train': 1.2548891305923462} 08/31/2021 09:47:55 - INFO - __main__ - Step 113597: {'lr': 7.100105994817702e-05, 'samples': 21810624, 'steps': 113596, 'loss/train': 1.0658854246139526} 08/31/2021 09:47:55 - INFO - __main__ - Step 113598: {'lr': 7.099735532571694e-05, 'samples': 21810816, 'steps': 113597, 'loss/train': 0.44906729459762573} 08/31/2021 09:47:55 - INFO - __main__ - Step 113599: {'lr': 7.099365078391271e-05, 'samples': 21811008, 'steps': 113598, 'loss/train': 2.0047669410705566} 08/31/2021 09:47:56 - INFO - __main__ - Step 113600: {'lr': 7.098994632276603e-05, 'samples': 21811200, 'steps': 113599, 'loss/train': 0.9922146797180176} 08/31/2021 09:47:56 - INFO - __main__ - Step 113601: {'lr': 7.098624194227845e-05, 'samples': 21811392, 'steps': 113600, 'loss/train': 0.016301138326525688} 08/31/2021 09:47:57 - INFO - __main__ - Step 113602: {'lr': 7.098253764245171e-05, 'samples': 21811584, 'steps': 113601, 'loss/train': 0.6933665871620178} 08/31/2021 09:47:58 - INFO - __main__ - Step 113603: {'lr': 7.097883342328748e-05, 'samples': 21811776, 'steps': 113602, 'loss/train': 1.0414284467697144} 08/31/2021 09:47:59 - INFO - __main__ - Step 113604: {'lr': 7.097512928478744e-05, 'samples': 21811968, 'steps': 113603, 'loss/train': 1.2236578464508057} 08/31/2021 09:47:59 - INFO - __main__ - Step 113605: {'lr': 7.097142522695321e-05, 'samples': 21812160, 'steps': 113604, 'loss/train': 0.8252435326576233} 08/31/2021 09:47:59 - INFO - __main__ - Step 113606: {'lr': 7.096772124978651e-05, 'samples': 21812352, 'steps': 113605, 'loss/train': 1.7299491167068481} 08/31/2021 09:48:00 - INFO - __main__ - Step 113607: {'lr': 7.0964017353289e-05, 'samples': 21812544, 'steps': 113606, 'loss/train': 0.7942831516265869} 08/31/2021 09:48:01 - INFO - __main__ - Step 113608: {'lr': 7.096031353746235e-05, 'samples': 21812736, 'steps': 113607, 'loss/train': 0.7573294639587402} 08/31/2021 09:48:02 - INFO - __main__ - Step 113609: {'lr': 7.09566098023082e-05, 'samples': 21812928, 'steps': 113608, 'loss/train': 0.15428777039051056} 08/31/2021 09:48:02 - INFO - __main__ - Step 113610: {'lr': 7.095290614782823e-05, 'samples': 21813120, 'steps': 113609, 'loss/train': 1.605746865272522} 08/31/2021 09:48:03 - INFO - __main__ - Step 113611: {'lr': 7.094920257402413e-05, 'samples': 21813312, 'steps': 113610, 'loss/train': 1.3858274221420288} 08/31/2021 09:48:03 - INFO - __main__ - Step 113612: {'lr': 7.094549908089756e-05, 'samples': 21813504, 'steps': 113611, 'loss/train': 0.8483606576919556} 08/31/2021 09:48:03 - INFO - __main__ - Step 113613: {'lr': 7.094179566845027e-05, 'samples': 21813696, 'steps': 113612, 'loss/train': 0.799457311630249} 08/31/2021 09:48:05 - INFO - __main__ - Step 113614: {'lr': 7.093809233668374e-05, 'samples': 21813888, 'steps': 113613, 'loss/train': 1.0753810405731201} 08/31/2021 09:48:06 - INFO - __main__ - Step 113615: {'lr': 7.093438908559977e-05, 'samples': 21814080, 'steps': 113614, 'loss/train': 1.540268063545227} 08/31/2021 09:48:06 - INFO - __main__ - Step 113616: {'lr': 7.093068591519999e-05, 'samples': 21814272, 'steps': 113615, 'loss/train': 1.098604440689087} 08/31/2021 09:48:07 - INFO - __main__ - Step 113617: {'lr': 7.092698282548607e-05, 'samples': 21814464, 'steps': 113616, 'loss/train': 1.409404993057251} 08/31/2021 09:48:07 - INFO - __main__ - Step 113618: {'lr': 7.092327981645971e-05, 'samples': 21814656, 'steps': 113617, 'loss/train': 1.2256863117218018} 08/31/2021 09:48:08 - INFO - __main__ - Step 113619: {'lr': 7.091957688812253e-05, 'samples': 21814848, 'steps': 113618, 'loss/train': 0.418049693107605} 08/31/2021 09:48:09 - INFO - __main__ - Step 113620: {'lr': 7.091587404047625e-05, 'samples': 21815040, 'steps': 113619, 'loss/train': 1.2660820484161377} 08/31/2021 09:48:09 - INFO - __main__ - Step 113621: {'lr': 7.09121712735225e-05, 'samples': 21815232, 'steps': 113620, 'loss/train': 1.281185507774353} 08/31/2021 09:48:09 - INFO - __main__ - Step 113622: {'lr': 7.090846858726296e-05, 'samples': 21815424, 'steps': 113621, 'loss/train': 1.4863005876541138} 08/31/2021 09:48:10 - INFO - __main__ - Step 113623: {'lr': 7.090476598169932e-05, 'samples': 21815616, 'steps': 113622, 'loss/train': 0.6597021222114563} 08/31/2021 09:48:11 - INFO - __main__ - Step 113624: {'lr': 7.09010634568332e-05, 'samples': 21815808, 'steps': 113623, 'loss/train': 1.1661419868469238} 08/31/2021 09:48:12 - INFO - __main__ - Step 113625: {'lr': 7.08973610126663e-05, 'samples': 21816000, 'steps': 113624, 'loss/train': 1.1287872791290283} 08/31/2021 09:48:12 - INFO - __main__ - Step 113626: {'lr': 7.08936586492003e-05, 'samples': 21816192, 'steps': 113625, 'loss/train': 0.9575127959251404} 08/31/2021 09:48:12 - INFO - __main__ - Step 113627: {'lr': 7.088995636643694e-05, 'samples': 21816384, 'steps': 113626, 'loss/train': 0.5233672857284546} 08/31/2021 09:48:13 - INFO - __main__ - Step 113628: {'lr': 7.088625416437772e-05, 'samples': 21816576, 'steps': 113627, 'loss/train': 1.2874648571014404} 08/31/2021 09:48:15 - INFO - __main__ - Step 113629: {'lr': 7.088255204302437e-05, 'samples': 21816768, 'steps': 113628, 'loss/train': 0.12691926956176758} 08/31/2021 09:48:15 - INFO - __main__ - Step 113630: {'lr': 7.087885000237859e-05, 'samples': 21816960, 'steps': 113629, 'loss/train': 1.4442837238311768} 08/31/2021 09:48:16 - INFO - __main__ - Step 113631: {'lr': 7.087514804244205e-05, 'samples': 21817152, 'steps': 113630, 'loss/train': 1.0008485317230225} 08/31/2021 09:48:16 - INFO - __main__ - Step 113632: {'lr': 7.087144616321639e-05, 'samples': 21817344, 'steps': 113631, 'loss/train': 0.04459303617477417} 08/31/2021 09:48:16 - INFO - __main__ - Step 113633: {'lr': 7.086774436470328e-05, 'samples': 21817536, 'steps': 113632, 'loss/train': 1.2920364141464233} 08/31/2021 09:48:17 - INFO - __main__ - Step 113634: {'lr': 7.086404264690443e-05, 'samples': 21817728, 'steps': 113633, 'loss/train': 1.4786540269851685} 08/31/2021 09:48:17 - INFO - __main__ - Step 113635: {'lr': 7.086034100982145e-05, 'samples': 21817920, 'steps': 113634, 'loss/train': 0.8733009696006775} 08/31/2021 09:48:19 - INFO - __main__ - Step 113636: {'lr': 7.085663945345605e-05, 'samples': 21818112, 'steps': 113635, 'loss/train': 2.2486798763275146} 08/31/2021 09:48:19 - INFO - __main__ - Step 113637: {'lr': 7.085293797780989e-05, 'samples': 21818304, 'steps': 113636, 'loss/train': 1.6668775081634521} 08/31/2021 09:48:19 - INFO - __main__ - Step 113638: {'lr': 7.084923658288462e-05, 'samples': 21818496, 'steps': 113637, 'loss/train': 1.2231738567352295} 08/31/2021 09:48:20 - INFO - __main__ - Step 113639: {'lr': 7.084553526868192e-05, 'samples': 21818688, 'steps': 113638, 'loss/train': 0.8924925327301025} 08/31/2021 09:48:20 - INFO - __main__ - Step 113640: {'lr': 7.084183403520353e-05, 'samples': 21818880, 'steps': 113639, 'loss/train': 1.4036931991577148} 08/31/2021 09:48:20 - INFO - __main__ - Step 113641: {'lr': 7.083813288245098e-05, 'samples': 21819072, 'steps': 113640, 'loss/train': 1.750665545463562} 08/31/2021 09:48:22 - INFO - __main__ - Step 113642: {'lr': 7.0834431810426e-05, 'samples': 21819264, 'steps': 113641, 'loss/train': 0.8376540541648865} 08/31/2021 09:48:23 - INFO - __main__ - Step 113643: {'lr': 7.083073081913027e-05, 'samples': 21819456, 'steps': 113642, 'loss/train': 1.2318201065063477} 08/31/2021 09:48:23 - INFO - __main__ - Step 113644: {'lr': 7.082702990856543e-05, 'samples': 21819648, 'steps': 113643, 'loss/train': 1.3470596075057983} 08/31/2021 09:48:23 - INFO - __main__ - Step 113645: {'lr': 7.082332907873317e-05, 'samples': 21819840, 'steps': 113644, 'loss/train': 1.4834356307983398} 08/31/2021 09:48:24 - INFO - __main__ - Step 113646: {'lr': 7.081962832963515e-05, 'samples': 21820032, 'steps': 113645, 'loss/train': 0.8942387700080872} 08/31/2021 09:48:25 - INFO - __main__ - Step 113647: {'lr': 7.081592766127304e-05, 'samples': 21820224, 'steps': 113646, 'loss/train': 0.036960769444704056} 08/31/2021 09:48:26 - INFO - __main__ - Step 113648: {'lr': 7.081222707364851e-05, 'samples': 21820416, 'steps': 113647, 'loss/train': 1.7925281524658203} 08/31/2021 09:48:26 - INFO - __main__ - Step 113649: {'lr': 7.080852656676323e-05, 'samples': 21820608, 'steps': 113648, 'loss/train': 1.8059413433074951} 08/31/2021 09:48:26 - INFO - __main__ - Step 113650: {'lr': 7.080482614061887e-05, 'samples': 21820800, 'steps': 113649, 'loss/train': 1.4869743585586548} 08/31/2021 09:48:27 - INFO - __main__ - Step 113651: {'lr': 7.080112579521709e-05, 'samples': 21820992, 'steps': 113650, 'loss/train': 0.9196696877479553} 08/31/2021 09:48:29 - INFO - __main__ - Step 113652: {'lr': 7.079742553055962e-05, 'samples': 21821184, 'steps': 113651, 'loss/train': 0.04496511444449425} 08/31/2021 09:48:29 - INFO - __main__ - Step 113653: {'lr': 7.079372534664799e-05, 'samples': 21821376, 'steps': 113652, 'loss/train': 0.5450648069381714} 08/31/2021 09:48:29 - INFO - __main__ - Step 113654: {'lr': 7.079002524348396e-05, 'samples': 21821568, 'steps': 113653, 'loss/train': 1.3315620422363281} 08/31/2021 09:48:30 - INFO - __main__ - Step 113655: {'lr': 7.078632522106915e-05, 'samples': 21821760, 'steps': 113654, 'loss/train': 0.9556457996368408} 08/31/2021 09:48:30 - INFO - __main__ - Step 113656: {'lr': 7.07826252794053e-05, 'samples': 21821952, 'steps': 113655, 'loss/train': 0.03539268672466278} 08/31/2021 09:48:32 - INFO - __main__ - Step 113657: {'lr': 7.077892541849398e-05, 'samples': 21822144, 'steps': 113656, 'loss/train': 0.5526142716407776} 08/31/2021 09:48:32 - INFO - __main__ - Step 113658: {'lr': 7.077522563833694e-05, 'samples': 21822336, 'steps': 113657, 'loss/train': 0.8551340699195862} 08/31/2021 09:48:32 - INFO - __main__ - Step 113659: {'lr': 7.077152593893583e-05, 'samples': 21822528, 'steps': 113658, 'loss/train': 0.9637628197669983} 08/31/2021 09:48:33 - INFO - __main__ - Step 113660: {'lr': 7.076782632029227e-05, 'samples': 21822720, 'steps': 113659, 'loss/train': 1.0297281742095947} 08/31/2021 09:48:33 - INFO - __main__ - Step 113661: {'lr': 7.076412678240798e-05, 'samples': 21822912, 'steps': 113660, 'loss/train': 1.4713242053985596} 08/31/2021 09:48:35 - INFO - __main__ - Step 113662: {'lr': 7.07604273252847e-05, 'samples': 21823104, 'steps': 113661, 'loss/train': 0.6365430951118469} 08/31/2021 09:48:35 - INFO - __main__ - Step 113663: {'lr': 7.07567279489239e-05, 'samples': 21823296, 'steps': 113662, 'loss/train': 1.1917675733566284} 08/31/2021 09:48:36 - INFO - __main__ - Step 113664: {'lr': 7.075302865332736e-05, 'samples': 21823488, 'steps': 113663, 'loss/train': 0.7509409785270691} 08/31/2021 09:48:36 - INFO - __main__ - Step 113665: {'lr': 7.074932943849677e-05, 'samples': 21823680, 'steps': 113664, 'loss/train': 0.018643414601683617} 08/31/2021 09:48:36 - INFO - __main__ - Step 113666: {'lr': 7.074563030443373e-05, 'samples': 21823872, 'steps': 113665, 'loss/train': 0.7294151782989502} 08/31/2021 09:48:37 - INFO - __main__ - Step 113667: {'lr': 7.074193125113996e-05, 'samples': 21824064, 'steps': 113666, 'loss/train': 0.9887639880180359} 08/31/2021 09:48:38 - INFO - __main__ - Step 113668: {'lr': 7.073823227861712e-05, 'samples': 21824256, 'steps': 113667, 'loss/train': 0.3479869067668915} 08/31/2021 09:48:39 - INFO - __main__ - Step 113669: {'lr': 7.073453338686684e-05, 'samples': 21824448, 'steps': 113668, 'loss/train': 1.2349542379379272} 08/31/2021 09:48:39 - INFO - __main__ - Step 113670: {'lr': 7.073083457589083e-05, 'samples': 21824640, 'steps': 113669, 'loss/train': 0.9785557985305786} 08/31/2021 09:48:40 - INFO - __main__ - Step 113671: {'lr': 7.072713584569071e-05, 'samples': 21824832, 'steps': 113670, 'loss/train': 1.062555193901062} 08/31/2021 09:48:40 - INFO - __main__ - Step 113672: {'lr': 7.072343719626822e-05, 'samples': 21825024, 'steps': 113671, 'loss/train': 1.723952293395996} 08/31/2021 09:48:40 - INFO - __main__ - Step 113673: {'lr': 7.071973862762504e-05, 'samples': 21825216, 'steps': 113672, 'loss/train': 0.5024929642677307} 08/31/2021 09:48:42 - INFO - __main__ - Step 113674: {'lr': 7.071604013976268e-05, 'samples': 21825408, 'steps': 113673, 'loss/train': 1.4567915201187134} 08/31/2021 09:48:42 - INFO - __main__ - Step 113675: {'lr': 7.071234173268296e-05, 'samples': 21825600, 'steps': 113674, 'loss/train': 1.0654972791671753} 08/31/2021 09:48:43 - INFO - __main__ - Step 113676: {'lr': 7.070864340638744e-05, 'samples': 21825792, 'steps': 113675, 'loss/train': 1.7527607679367065} 08/31/2021 09:48:43 - INFO - __main__ - Step 113677: {'lr': 7.070494516087786e-05, 'samples': 21825984, 'steps': 113676, 'loss/train': 0.6835052967071533} 08/31/2021 09:48:43 - INFO - __main__ - Step 113678: {'lr': 7.070124699615588e-05, 'samples': 21826176, 'steps': 113677, 'loss/train': 0.9175881743431091} 08/31/2021 09:48:45 - INFO - __main__ - Step 113679: {'lr': 7.069754891222313e-05, 'samples': 21826368, 'steps': 113678, 'loss/train': 1.4440959692001343} 08/31/2021 09:48:45 - INFO - __main__ - Step 113680: {'lr': 7.069385090908128e-05, 'samples': 21826560, 'steps': 113679, 'loss/train': 0.9692610502243042} 08/31/2021 09:48:46 - INFO - __main__ - Step 113681: {'lr': 7.069015298673206e-05, 'samples': 21826752, 'steps': 113680, 'loss/train': 0.9490736722946167} 08/31/2021 09:48:46 - INFO - __main__ - Step 113682: {'lr': 7.068645514517707e-05, 'samples': 21826944, 'steps': 113681, 'loss/train': 1.1755964756011963} 08/31/2021 09:48:46 - INFO - __main__ - Step 113683: {'lr': 7.068275738441798e-05, 'samples': 21827136, 'steps': 113682, 'loss/train': 0.9846161007881165} 08/31/2021 09:48:47 - INFO - __main__ - Step 113684: {'lr': 7.067905970445657e-05, 'samples': 21827328, 'steps': 113683, 'loss/train': 0.8737314343452454} 08/31/2021 09:48:48 - INFO - __main__ - Step 113685: {'lr': 7.067536210529433e-05, 'samples': 21827520, 'steps': 113684, 'loss/train': 1.7834457159042358} 08/31/2021 09:48:49 - INFO - __main__ - Step 113686: {'lr': 7.0671664586933e-05, 'samples': 21827712, 'steps': 113685, 'loss/train': 0.9033875465393066} 08/31/2021 09:48:49 - INFO - __main__ - Step 113687: {'lr': 7.066796714937424e-05, 'samples': 21827904, 'steps': 113686, 'loss/train': 0.6402384042739868} 08/31/2021 09:48:49 - INFO - __main__ - Step 113688: {'lr': 7.066426979261975e-05, 'samples': 21828096, 'steps': 113687, 'loss/train': 1.4703278541564941} 08/31/2021 09:48:50 - INFO - __main__ - Step 113689: {'lr': 7.066057251667116e-05, 'samples': 21828288, 'steps': 113688, 'loss/train': 1.1839097738265991} 08/31/2021 09:48:51 - INFO - __main__ - Step 113690: {'lr': 7.065687532153015e-05, 'samples': 21828480, 'steps': 113689, 'loss/train': 1.0928013324737549} 08/31/2021 09:48:52 - INFO - __main__ - Step 113691: {'lr': 7.065317820719838e-05, 'samples': 21828672, 'steps': 113690, 'loss/train': 1.2393028736114502} 08/31/2021 09:48:52 - INFO - __main__ - Step 113692: {'lr': 7.06494811736775e-05, 'samples': 21828864, 'steps': 113691, 'loss/train': 0.69913649559021} 08/31/2021 09:48:53 - INFO - __main__ - Step 113693: {'lr': 7.064578422096924e-05, 'samples': 21829056, 'steps': 113692, 'loss/train': 1.232445478439331} 08/31/2021 09:48:53 - INFO - __main__ - Step 113694: {'lr': 7.06420873490752e-05, 'samples': 21829248, 'steps': 113693, 'loss/train': 0.12322433292865753} 08/31/2021 09:48:54 - INFO - __main__ - Step 113695: {'lr': 7.063839055799714e-05, 'samples': 21829440, 'steps': 113694, 'loss/train': 0.7493723630905151} 08/31/2021 09:48:55 - INFO - __main__ - Step 113696: {'lr': 7.063469384773658e-05, 'samples': 21829632, 'steps': 113695, 'loss/train': 0.9762467741966248} 08/31/2021 09:48:55 - INFO - __main__ - Step 113697: {'lr': 7.063099721829528e-05, 'samples': 21829824, 'steps': 113696, 'loss/train': 0.38197144865989685} 08/31/2021 09:48:56 - INFO - __main__ - Step 113698: {'lr': 7.062730066967485e-05, 'samples': 21830016, 'steps': 113697, 'loss/train': 1.5175021886825562} 08/31/2021 09:48:56 - INFO - __main__ - Step 113699: {'lr': 7.062360420187703e-05, 'samples': 21830208, 'steps': 113698, 'loss/train': 1.3621519804000854} 08/31/2021 09:48:56 - INFO - __main__ - Step 113700: {'lr': 7.06199078149034e-05, 'samples': 21830400, 'steps': 113699, 'loss/train': 0.9076893329620361} 08/31/2021 09:48:58 - INFO - __main__ - Step 113701: {'lr': 7.061621150875569e-05, 'samples': 21830592, 'steps': 113700, 'loss/train': 0.965886116027832} 08/31/2021 09:48:58 - INFO - __main__ - Step 113702: {'lr': 7.061251528343557e-05, 'samples': 21830784, 'steps': 113701, 'loss/train': 1.1703280210494995} 08/31/2021 09:48:59 - INFO - __main__ - Step 113703: {'lr': 7.060881913894465e-05, 'samples': 21830976, 'steps': 113702, 'loss/train': 1.1863449811935425} 08/31/2021 09:48:59 - INFO - __main__ - Step 113704: {'lr': 7.060512307528466e-05, 'samples': 21831168, 'steps': 113703, 'loss/train': 0.9912843704223633} 08/31/2021 09:48:59 - INFO - __main__ - Step 113705: {'lr': 7.060142709245721e-05, 'samples': 21831360, 'steps': 113704, 'loss/train': 0.8687636852264404} 08/31/2021 09:49:01 - INFO - __main__ - Step 113706: {'lr': 7.059773119046397e-05, 'samples': 21831552, 'steps': 113705, 'loss/train': 0.8801007866859436} 08/31/2021 09:49:02 - INFO - __main__ - Step 113707: {'lr': 7.059403536930675e-05, 'samples': 21831744, 'steps': 113706, 'loss/train': 1.1071566343307495} 08/31/2021 09:49:02 - INFO - __main__ - Step 113708: {'lr': 7.059033962898698e-05, 'samples': 21831936, 'steps': 113707, 'loss/train': 0.9137731790542603} 08/31/2021 09:49:03 - INFO - __main__ - Step 113709: {'lr': 7.058664396950645e-05, 'samples': 21832128, 'steps': 113708, 'loss/train': 1.0877033472061157} 08/31/2021 09:49:03 - INFO - __main__ - Step 113710: {'lr': 7.058294839086679e-05, 'samples': 21832320, 'steps': 113709, 'loss/train': 1.2755343914031982} 08/31/2021 09:49:04 - INFO - __main__ - Step 113711: {'lr': 7.057925289306972e-05, 'samples': 21832512, 'steps': 113710, 'loss/train': 1.1846660375595093} 08/31/2021 09:49:05 - INFO - __main__ - Step 113712: {'lr': 7.057555747611683e-05, 'samples': 21832704, 'steps': 113711, 'loss/train': 0.07531221956014633} 08/31/2021 09:49:05 - INFO - __main__ - Step 113713: {'lr': 7.057186214000985e-05, 'samples': 21832896, 'steps': 113712, 'loss/train': 1.2807294130325317} 08/31/2021 09:49:06 - INFO - __main__ - Step 113714: {'lr': 7.05681668847504e-05, 'samples': 21833088, 'steps': 113713, 'loss/train': 1.1229039430618286} 08/31/2021 09:49:06 - INFO - __main__ - Step 113715: {'lr': 7.056447171034017e-05, 'samples': 21833280, 'steps': 113714, 'loss/train': 1.2465659379959106} 08/31/2021 09:49:07 - INFO - __main__ - Step 113716: {'lr': 7.056077661678084e-05, 'samples': 21833472, 'steps': 113715, 'loss/train': 1.018649697303772} 08/31/2021 09:49:08 - INFO - __main__ - Step 113717: {'lr': 7.055708160407404e-05, 'samples': 21833664, 'steps': 113716, 'loss/train': 1.0722124576568604} 08/31/2021 09:49:08 - INFO - __main__ - Step 113718: {'lr': 7.055338667222144e-05, 'samples': 21833856, 'steps': 113717, 'loss/train': 1.7624213695526123} 08/31/2021 09:49:09 - INFO - __main__ - Step 113719: {'lr': 7.054969182122473e-05, 'samples': 21834048, 'steps': 113718, 'loss/train': 0.9281005263328552} 08/31/2021 09:49:09 - INFO - __main__ - Step 113720: {'lr': 7.054599705108556e-05, 'samples': 21834240, 'steps': 113719, 'loss/train': 0.8730703592300415} 08/31/2021 09:49:10 - INFO - __main__ - Step 113721: {'lr': 7.054230236180567e-05, 'samples': 21834432, 'steps': 113720, 'loss/train': 1.4250370264053345} 08/31/2021 09:49:11 - INFO - __main__ - Step 113722: {'lr': 7.053860775338658e-05, 'samples': 21834624, 'steps': 113721, 'loss/train': 0.9258383512496948} 08/31/2021 09:49:11 - INFO - __main__ - Step 113723: {'lr': 7.053491322583e-05, 'samples': 21834816, 'steps': 113722, 'loss/train': 1.8489257097244263} 08/31/2021 09:49:12 - INFO - __main__ - Step 113724: {'lr': 7.053121877913765e-05, 'samples': 21835008, 'steps': 113723, 'loss/train': 0.704119861125946} 08/31/2021 09:49:12 - INFO - __main__ - Step 113725: {'lr': 7.052752441331114e-05, 'samples': 21835200, 'steps': 113724, 'loss/train': 1.0388089418411255} 08/31/2021 09:49:14 - INFO - __main__ - Step 113726: {'lr': 7.052383012835217e-05, 'samples': 21835392, 'steps': 113725, 'loss/train': 0.8225307464599609} 08/31/2021 09:49:14 - INFO - __main__ - Step 113727: {'lr': 7.052013592426237e-05, 'samples': 21835584, 'steps': 113726, 'loss/train': 1.198109745979309} 08/31/2021 09:49:14 - INFO - __main__ - Step 113728: {'lr': 7.051644180104346e-05, 'samples': 21835776, 'steps': 113727, 'loss/train': 0.9159403443336487} 08/31/2021 09:49:15 - INFO - __main__ - Step 113729: {'lr': 7.051274775869706e-05, 'samples': 21835968, 'steps': 113728, 'loss/train': 1.4376983642578125} 08/31/2021 09:49:15 - INFO - __main__ - Step 113730: {'lr': 7.050905379722483e-05, 'samples': 21836160, 'steps': 113729, 'loss/train': 0.03804916515946388} 08/31/2021 09:49:17 - INFO - __main__ - Step 113731: {'lr': 7.050535991662849e-05, 'samples': 21836352, 'steps': 113730, 'loss/train': 1.003932237625122} 08/31/2021 09:49:17 - INFO - __main__ - Step 113732: {'lr': 7.050166611690962e-05, 'samples': 21836544, 'steps': 113731, 'loss/train': 0.6320419907569885} 08/31/2021 09:49:17 - INFO - __main__ - Step 113733: {'lr': 7.049797239806996e-05, 'samples': 21836736, 'steps': 113732, 'loss/train': 1.1623425483703613} 08/31/2021 09:49:18 - INFO - __main__ - Step 113734: {'lr': 7.049427876011119e-05, 'samples': 21836928, 'steps': 113733, 'loss/train': 1.1213629245758057} 08/31/2021 09:49:18 - INFO - __main__ - Step 113735: {'lr': 7.049058520303489e-05, 'samples': 21837120, 'steps': 113734, 'loss/train': 0.6865653395652771} 08/31/2021 09:49:20 - INFO - __main__ - Step 113736: {'lr': 7.048689172684272e-05, 'samples': 21837312, 'steps': 113735, 'loss/train': 1.0563881397247314} 08/31/2021 09:49:20 - INFO - __main__ - Step 113737: {'lr': 7.048319833153641e-05, 'samples': 21837504, 'steps': 113736, 'loss/train': 0.6496008634567261} 08/31/2021 09:49:20 - INFO - __main__ - Step 113738: {'lr': 7.047950501711762e-05, 'samples': 21837696, 'steps': 113737, 'loss/train': 1.2342939376831055} 08/31/2021 09:49:21 - INFO - __main__ - Step 113739: {'lr': 7.047581178358797e-05, 'samples': 21837888, 'steps': 113738, 'loss/train': 1.0514302253723145} 08/31/2021 09:49:21 - INFO - __main__ - Step 113740: {'lr': 7.047211863094915e-05, 'samples': 21838080, 'steps': 113739, 'loss/train': 1.3552722930908203} 08/31/2021 09:49:21 - INFO - __main__ - Step 113741: {'lr': 7.046842555920283e-05, 'samples': 21838272, 'steps': 113740, 'loss/train': 1.1371817588806152} 08/31/2021 09:49:23 - INFO - __main__ - Step 113742: {'lr': 7.046473256835065e-05, 'samples': 21838464, 'steps': 113741, 'loss/train': 0.8072580099105835} 08/31/2021 09:49:24 - INFO - __main__ - Step 113743: {'lr': 7.046103965839431e-05, 'samples': 21838656, 'steps': 113742, 'loss/train': 0.0773279145359993} 08/31/2021 09:49:24 - INFO - __main__ - Step 113744: {'lr': 7.045734682933547e-05, 'samples': 21838848, 'steps': 113743, 'loss/train': 1.0063862800598145} 08/31/2021 09:49:24 - INFO - __main__ - Step 113745: {'lr': 7.045365408117573e-05, 'samples': 21839040, 'steps': 113744, 'loss/train': 1.2272663116455078} 08/31/2021 09:49:25 - INFO - __main__ - Step 113746: {'lr': 7.044996141391685e-05, 'samples': 21839232, 'steps': 113745, 'loss/train': 1.1713367700576782} 08/31/2021 09:49:26 - INFO - __main__ - Step 113747: {'lr': 7.044626882756041e-05, 'samples': 21839424, 'steps': 113746, 'loss/train': 1.337592363357544} 08/31/2021 09:49:27 - INFO - __main__ - Step 113748: {'lr': 7.044257632210822e-05, 'samples': 21839616, 'steps': 113747, 'loss/train': 0.9288649559020996} 08/31/2021 09:49:27 - INFO - __main__ - Step 113749: {'lr': 7.043888389756176e-05, 'samples': 21839808, 'steps': 113748, 'loss/train': 1.9662859439849854} 08/31/2021 09:49:27 - INFO - __main__ - Step 113750: {'lr': 7.043519155392272e-05, 'samples': 21840000, 'steps': 113749, 'loss/train': 1.1117380857467651} 08/31/2021 09:49:28 - INFO - __main__ - Step 113751: {'lr': 7.043149929119285e-05, 'samples': 21840192, 'steps': 113750, 'loss/train': 0.7987977266311646} 08/31/2021 09:49:29 - INFO - __main__ - Step 113752: {'lr': 7.042780710937377e-05, 'samples': 21840384, 'steps': 113751, 'loss/train': 1.3224613666534424} 08/31/2021 09:49:30 - INFO - __main__ - Step 113753: {'lr': 7.042411500846715e-05, 'samples': 21840576, 'steps': 113752, 'loss/train': 1.124397873878479} 08/31/2021 09:49:30 - INFO - __main__ - Step 113754: {'lr': 7.042042298847464e-05, 'samples': 21840768, 'steps': 113753, 'loss/train': 1.414957880973816} 08/31/2021 09:49:30 - INFO - __main__ - Step 113755: {'lr': 7.041673104939794e-05, 'samples': 21840960, 'steps': 113754, 'loss/train': 0.7904144525527954} 08/31/2021 09:49:31 - INFO - __main__ - Step 113756: {'lr': 7.041303919123868e-05, 'samples': 21841152, 'steps': 113755, 'loss/train': 0.9945145845413208} 08/31/2021 09:49:33 - INFO - __main__ - Step 113757: {'lr': 7.040934741399854e-05, 'samples': 21841344, 'steps': 113756, 'loss/train': 0.8015219569206238} 08/31/2021 09:49:33 - INFO - __main__ - Step 113758: {'lr': 7.040565571767916e-05, 'samples': 21841536, 'steps': 113757, 'loss/train': 1.045271635055542} 08/31/2021 09:49:34 - INFO - __main__ - Step 113759: {'lr': 7.040196410228223e-05, 'samples': 21841728, 'steps': 113758, 'loss/train': 0.991094172000885} 08/31/2021 09:49:34 - INFO - __main__ - Step 113760: {'lr': 7.03982725678094e-05, 'samples': 21841920, 'steps': 113759, 'loss/train': 1.0448476076126099} 08/31/2021 09:49:34 - INFO - __main__ - Step 113761: {'lr': 7.039458111426241e-05, 'samples': 21842112, 'steps': 113760, 'loss/train': 1.3741766214370728} 08/31/2021 09:49:35 - INFO - __main__ - Step 113762: {'lr': 7.039088974164278e-05, 'samples': 21842304, 'steps': 113761, 'loss/train': 1.3494843244552612} 08/31/2021 09:49:36 - INFO - __main__ - Step 113763: {'lr': 7.038719844995226e-05, 'samples': 21842496, 'steps': 113762, 'loss/train': 1.5617631673812866} 08/31/2021 09:49:37 - INFO - __main__ - Step 113764: {'lr': 7.038350723919246e-05, 'samples': 21842688, 'steps': 113763, 'loss/train': 1.8170433044433594} 08/31/2021 09:49:37 - INFO - __main__ - Step 113765: {'lr': 7.037981610936509e-05, 'samples': 21842880, 'steps': 113764, 'loss/train': 0.020821647718548775} 08/31/2021 09:49:37 - INFO - __main__ - Step 113766: {'lr': 7.037612506047183e-05, 'samples': 21843072, 'steps': 113765, 'loss/train': 1.4413059949874878} 08/31/2021 09:49:38 - INFO - __main__ - Step 113767: {'lr': 7.037243409251429e-05, 'samples': 21843264, 'steps': 113766, 'loss/train': 0.657983124256134} 08/31/2021 09:49:39 - INFO - __main__ - Step 113768: {'lr': 7.036874320549416e-05, 'samples': 21843456, 'steps': 113767, 'loss/train': 0.7006306648254395} 08/31/2021 09:49:40 - INFO - __main__ - Step 113769: {'lr': 7.036505239941313e-05, 'samples': 21843648, 'steps': 113768, 'loss/train': 1.1127798557281494} 08/31/2021 09:49:40 - INFO - __main__ - Step 113770: {'lr': 7.036136167427279e-05, 'samples': 21843840, 'steps': 113769, 'loss/train': 0.8426565527915955} 08/31/2021 09:49:40 - INFO - __main__ - Step 113771: {'lr': 7.03576710300749e-05, 'samples': 21844032, 'steps': 113770, 'loss/train': 0.9696077704429626} 08/31/2021 09:49:41 - INFO - __main__ - Step 113772: {'lr': 7.035398046682104e-05, 'samples': 21844224, 'steps': 113771, 'loss/train': 0.7536606192588806} 08/31/2021 09:49:42 - INFO - __main__ - Step 113773: {'lr': 7.03502899845129e-05, 'samples': 21844416, 'steps': 113772, 'loss/train': 0.9043223857879639} 08/31/2021 09:49:43 - INFO - __main__ - Step 113774: {'lr': 7.034659958315215e-05, 'samples': 21844608, 'steps': 113773, 'loss/train': 1.0875153541564941} 08/31/2021 09:49:43 - INFO - __main__ - Step 113775: {'lr': 7.034290926274054e-05, 'samples': 21844800, 'steps': 113774, 'loss/train': 1.3100972175598145} 08/31/2021 09:49:43 - INFO - __main__ - Step 113776: {'lr': 7.033921902327955e-05, 'samples': 21844992, 'steps': 113775, 'loss/train': 0.8455379009246826} 08/31/2021 09:49:44 - INFO - __main__ - Step 113777: {'lr': 7.033552886477096e-05, 'samples': 21845184, 'steps': 113776, 'loss/train': 0.6249788999557495} 08/31/2021 09:49:45 - INFO - __main__ - Step 113778: {'lr': 7.033183878721639e-05, 'samples': 21845376, 'steps': 113777, 'loss/train': 1.431239366531372} 08/31/2021 09:49:46 - INFO - __main__ - Step 113779: {'lr': 7.032814879061753e-05, 'samples': 21845568, 'steps': 113778, 'loss/train': 1.7482150793075562} 08/31/2021 09:49:46 - INFO - __main__ - Step 113780: {'lr': 7.032445887497602e-05, 'samples': 21845760, 'steps': 113779, 'loss/train': 1.0911446809768677} 08/31/2021 09:49:46 - INFO - __main__ - Step 113781: {'lr': 7.032076904029356e-05, 'samples': 21845952, 'steps': 113780, 'loss/train': 1.148895025253296} 08/31/2021 09:49:47 - INFO - __main__ - Step 113782: {'lr': 7.031707928657174e-05, 'samples': 21846144, 'steps': 113781, 'loss/train': 1.4420286417007446} 08/31/2021 09:49:47 - INFO - __main__ - Step 113783: {'lr': 7.031338961381231e-05, 'samples': 21846336, 'steps': 113782, 'loss/train': 1.0140494108200073} 08/31/2021 09:49:49 - INFO - __main__ - Step 113784: {'lr': 7.03097000220169e-05, 'samples': 21846528, 'steps': 113783, 'loss/train': 1.2274870872497559} 08/31/2021 09:49:49 - INFO - __main__ - Step 113785: {'lr': 7.030601051118715e-05, 'samples': 21846720, 'steps': 113784, 'loss/train': 0.8455144166946411} 08/31/2021 09:49:49 - INFO - __main__ - Step 113786: {'lr': 7.030232108132475e-05, 'samples': 21846912, 'steps': 113785, 'loss/train': 1.1775686740875244} 08/31/2021 09:49:50 - INFO - __main__ - Step 113787: {'lr': 7.029863173243134e-05, 'samples': 21847104, 'steps': 113786, 'loss/train': 0.8737055659294128} 08/31/2021 09:49:50 - INFO - __main__ - Step 113788: {'lr': 7.029494246450869e-05, 'samples': 21847296, 'steps': 113787, 'loss/train': 0.48005354404449463} 08/31/2021 09:49:52 - INFO - __main__ - Step 113789: {'lr': 7.029125327755825e-05, 'samples': 21847488, 'steps': 113788, 'loss/train': 0.8198583722114563} 08/31/2021 09:49:52 - INFO - __main__ - Step 113790: {'lr': 7.028756417158183e-05, 'samples': 21847680, 'steps': 113789, 'loss/train': 1.1003758907318115} 08/31/2021 09:49:52 - INFO - __main__ - Step 113791: {'lr': 7.028387514658105e-05, 'samples': 21847872, 'steps': 113790, 'loss/train': 1.357597827911377} 08/31/2021 09:49:53 - INFO - __main__ - Step 113792: {'lr': 7.02801862025576e-05, 'samples': 21848064, 'steps': 113791, 'loss/train': 1.173570156097412} 08/31/2021 09:49:53 - INFO - __main__ - Step 113793: {'lr': 7.027649733951311e-05, 'samples': 21848256, 'steps': 113792, 'loss/train': 0.6193866729736328} 08/31/2021 09:49:53 - INFO - __main__ - Step 113794: {'lr': 7.027280855744925e-05, 'samples': 21848448, 'steps': 113793, 'loss/train': 1.2692155838012695} 08/31/2021 09:49:55 - INFO - __main__ - Step 113795: {'lr': 7.02691198563677e-05, 'samples': 21848640, 'steps': 113794, 'loss/train': 0.8916469216346741} 08/31/2021 09:49:56 - INFO - __main__ - Step 113796: {'lr': 7.02654312362701e-05, 'samples': 21848832, 'steps': 113795, 'loss/train': 0.42791837453842163} 08/31/2021 09:49:56 - INFO - __main__ - Step 113797: {'lr': 7.026174269715812e-05, 'samples': 21849024, 'steps': 113796, 'loss/train': 1.1661969423294067} 08/31/2021 09:49:56 - INFO - __main__ - Step 113798: {'lr': 7.025805423903345e-05, 'samples': 21849216, 'steps': 113797, 'loss/train': 1.4269334077835083} 08/31/2021 09:49:57 - INFO - __main__ - Step 113799: {'lr': 7.025436586189771e-05, 'samples': 21849408, 'steps': 113798, 'loss/train': 1.0697004795074463} 08/31/2021 09:49:59 - INFO - __main__ - Step 113800: {'lr': 7.02506775657526e-05, 'samples': 21849600, 'steps': 113799, 'loss/train': 0.9021316766738892} 08/31/2021 09:49:59 - INFO - __main__ - Step 113801: {'lr': 7.024698935059981e-05, 'samples': 21849792, 'steps': 113800, 'loss/train': 0.7093937993049622} 08/31/2021 09:50:00 - INFO - __main__ - Step 113802: {'lr': 7.024330121644088e-05, 'samples': 21849984, 'steps': 113801, 'loss/train': 0.015570065006613731} 08/31/2021 09:50:00 - INFO - __main__ - Step 113803: {'lr': 7.023961316327756e-05, 'samples': 21850176, 'steps': 113802, 'loss/train': 0.36263132095336914} 08/31/2021 09:50:00 - INFO - __main__ - Step 113804: {'lr': 7.023592519111149e-05, 'samples': 21850368, 'steps': 113803, 'loss/train': 0.9883988499641418} 08/31/2021 09:50:01 - INFO - __main__ - Step 113805: {'lr': 7.023223729994432e-05, 'samples': 21850560, 'steps': 113804, 'loss/train': 1.2213001251220703} 08/31/2021 09:50:02 - INFO - __main__ - Step 113806: {'lr': 7.022854948977775e-05, 'samples': 21850752, 'steps': 113805, 'loss/train': 1.418054223060608} 08/31/2021 09:50:03 - INFO - __main__ - Step 113807: {'lr': 7.022486176061344e-05, 'samples': 21850944, 'steps': 113806, 'loss/train': 0.1047726646065712} 08/31/2021 09:50:03 - INFO - __main__ - Step 113808: {'lr': 7.022117411245299e-05, 'samples': 21851136, 'steps': 113807, 'loss/train': 0.524431586265564} 08/31/2021 09:50:03 - INFO - __main__ - Step 113809: {'lr': 7.021748654529813e-05, 'samples': 21851328, 'steps': 113808, 'loss/train': 0.77769535779953} 08/31/2021 09:50:04 - INFO - __main__ - Step 113810: {'lr': 7.021379905915048e-05, 'samples': 21851520, 'steps': 113809, 'loss/train': 0.15332354605197906} 08/31/2021 09:50:04 - INFO - __main__ - Step 113811: {'lr': 7.021011165401173e-05, 'samples': 21851712, 'steps': 113810, 'loss/train': 1.6906428337097168} 08/31/2021 09:50:06 - INFO - __main__ - Step 113812: {'lr': 7.020642432988353e-05, 'samples': 21851904, 'steps': 113811, 'loss/train': 1.0471502542495728} 08/31/2021 09:50:06 - INFO - __main__ - Step 113813: {'lr': 7.020273708676756e-05, 'samples': 21852096, 'steps': 113812, 'loss/train': 0.8574093580245972} 08/31/2021 09:50:06 - INFO - __main__ - Step 113814: {'lr': 7.019904992466542e-05, 'samples': 21852288, 'steps': 113813, 'loss/train': 1.7084029912948608} 08/31/2021 09:50:07 - INFO - __main__ - Step 113815: {'lr': 7.019536284357891e-05, 'samples': 21852480, 'steps': 113814, 'loss/train': 1.0070335865020752} 08/31/2021 09:50:07 - INFO - __main__ - Step 113816: {'lr': 7.019167584350953e-05, 'samples': 21852672, 'steps': 113815, 'loss/train': 1.1712746620178223} 08/31/2021 09:50:09 - INFO - __main__ - Step 113817: {'lr': 7.018798892445899e-05, 'samples': 21852864, 'steps': 113816, 'loss/train': 1.324402093887329} 08/31/2021 09:50:10 - INFO - __main__ - Step 113818: {'lr': 7.018430208642898e-05, 'samples': 21853056, 'steps': 113817, 'loss/train': 1.6074824333190918} 08/31/2021 09:50:10 - INFO - __main__ - Step 113819: {'lr': 7.018061532942113e-05, 'samples': 21853248, 'steps': 113818, 'loss/train': 1.2456904649734497} 08/31/2021 09:50:11 - INFO - __main__ - Step 113820: {'lr': 7.017692865343714e-05, 'samples': 21853440, 'steps': 113819, 'loss/train': 0.4625631868839264} 08/31/2021 09:50:11 - INFO - __main__ - Step 113821: {'lr': 7.017324205847864e-05, 'samples': 21853632, 'steps': 113820, 'loss/train': 1.7525845766067505} 08/31/2021 09:50:13 - INFO - __main__ - Step 113822: {'lr': 7.016955554454732e-05, 'samples': 21853824, 'steps': 113821, 'loss/train': 0.89253169298172} 08/31/2021 09:50:13 - INFO - __main__ - Step 113823: {'lr': 7.01658691116448e-05, 'samples': 21854016, 'steps': 113822, 'loss/train': 1.4778167009353638} 08/31/2021 09:50:13 - INFO - __main__ - Step 113824: {'lr': 7.016218275977277e-05, 'samples': 21854208, 'steps': 113823, 'loss/train': 1.0080597400665283} 08/31/2021 09:50:14 - INFO - __main__ - Step 113825: {'lr': 7.015849648893288e-05, 'samples': 21854400, 'steps': 113824, 'loss/train': 1.008437991142273} 08/31/2021 09:50:14 - INFO - __main__ - Step 113826: {'lr': 7.015481029912682e-05, 'samples': 21854592, 'steps': 113825, 'loss/train': 0.9942492246627808} 08/31/2021 09:50:16 - INFO - __main__ - Step 113827: {'lr': 7.015112419035621e-05, 'samples': 21854784, 'steps': 113826, 'loss/train': 0.4485398232936859} 08/31/2021 09:50:16 - INFO - __main__ - Step 113828: {'lr': 7.014743816262281e-05, 'samples': 21854976, 'steps': 113827, 'loss/train': 1.1275337934494019} 08/31/2021 09:50:17 - INFO - __main__ - Step 113829: {'lr': 7.014375221592812e-05, 'samples': 21855168, 'steps': 113828, 'loss/train': 0.7235310077667236} 08/31/2021 09:50:17 - INFO - __main__ - Step 113830: {'lr': 7.014006635027387e-05, 'samples': 21855360, 'steps': 113829, 'loss/train': 0.22684870660305023} 08/31/2021 09:50:17 - INFO - __main__ - Step 113831: {'lr': 7.013638056566174e-05, 'samples': 21855552, 'steps': 113830, 'loss/train': 1.567457914352417} 08/31/2021 09:50:19 - INFO - __main__ - Step 113832: {'lr': 7.01326948620934e-05, 'samples': 21855744, 'steps': 113831, 'loss/train': 1.372407078742981} 08/31/2021 09:50:19 - INFO - __main__ - Step 113833: {'lr': 7.012900923957047e-05, 'samples': 21855936, 'steps': 113832, 'loss/train': 0.041392598301172256} 08/31/2021 09:50:20 - INFO - __main__ - Step 113834: {'lr': 7.012532369809462e-05, 'samples': 21856128, 'steps': 113833, 'loss/train': 0.8852983713150024} 08/31/2021 09:50:20 - INFO - __main__ - Step 113835: {'lr': 7.012163823766757e-05, 'samples': 21856320, 'steps': 113834, 'loss/train': 0.6895726919174194} 08/31/2021 09:50:20 - INFO - __main__ - Step 113836: {'lr': 7.011795285829089e-05, 'samples': 21856512, 'steps': 113835, 'loss/train': 1.593949794769287} 08/31/2021 09:50:22 - INFO - __main__ - Step 113837: {'lr': 7.01142675599663e-05, 'samples': 21856704, 'steps': 113836, 'loss/train': 1.2730928659439087} 08/31/2021 09:50:22 - INFO - __main__ - Step 113838: {'lr': 7.011058234269543e-05, 'samples': 21856896, 'steps': 113837, 'loss/train': 0.42930442094802856} 08/31/2021 09:50:23 - INFO - __main__ - Step 113839: {'lr': 7.010689720647998e-05, 'samples': 21857088, 'steps': 113838, 'loss/train': 1.2345001697540283} 08/31/2021 09:50:23 - INFO - __main__ - Step 113840: {'lr': 7.010321215132159e-05, 'samples': 21857280, 'steps': 113839, 'loss/train': 1.4897218942642212} 08/31/2021 09:50:23 - INFO - __main__ - Step 113841: {'lr': 7.00995271772219e-05, 'samples': 21857472, 'steps': 113840, 'loss/train': 0.9993105530738831} 08/31/2021 09:50:25 - INFO - __main__ - Step 113842: {'lr': 7.009584228418267e-05, 'samples': 21857664, 'steps': 113841, 'loss/train': 1.1482526063919067} 08/31/2021 09:50:25 - INFO - __main__ - Step 113843: {'lr': 7.009215747220538e-05, 'samples': 21857856, 'steps': 113842, 'loss/train': 0.42480742931365967} 08/31/2021 09:50:26 - INFO - __main__ - Step 113844: {'lr': 7.008847274129182e-05, 'samples': 21858048, 'steps': 113843, 'loss/train': 0.759240984916687} 08/31/2021 09:50:26 - INFO - __main__ - Step 113845: {'lr': 7.008478809144359e-05, 'samples': 21858240, 'steps': 113844, 'loss/train': 1.7135753631591797} 08/31/2021 09:50:26 - INFO - __main__ - Step 113846: {'lr': 7.008110352266239e-05, 'samples': 21858432, 'steps': 113845, 'loss/train': 1.2115356922149658} 08/31/2021 09:50:28 - INFO - __main__ - Step 113847: {'lr': 7.007741903494987e-05, 'samples': 21858624, 'steps': 113846, 'loss/train': 0.8576719164848328} 08/31/2021 09:50:28 - INFO - __main__ - Step 113848: {'lr': 7.007373462830768e-05, 'samples': 21858816, 'steps': 113847, 'loss/train': 1.179593801498413} 08/31/2021 09:50:29 - INFO - __main__ - Step 113849: {'lr': 7.007005030273753e-05, 'samples': 21859008, 'steps': 113848, 'loss/train': 1.0785447359085083} 08/31/2021 09:50:29 - INFO - __main__ - Step 113850: {'lr': 7.006636605824099e-05, 'samples': 21859200, 'steps': 113849, 'loss/train': 1.1281001567840576} 08/31/2021 09:50:29 - INFO - __main__ - Step 113851: {'lr': 7.006268189481979e-05, 'samples': 21859392, 'steps': 113850, 'loss/train': 1.2256022691726685} 08/31/2021 09:50:30 - INFO - __main__ - Step 113852: {'lr': 7.005899781247557e-05, 'samples': 21859584, 'steps': 113851, 'loss/train': 1.3251008987426758} 08/31/2021 09:50:32 - INFO - __main__ - Step 113853: {'lr': 7.005531381120997e-05, 'samples': 21859776, 'steps': 113852, 'loss/train': 1.2918776273727417} 08/31/2021 09:50:32 - INFO - __main__ - Step 113854: {'lr': 7.005162989102467e-05, 'samples': 21859968, 'steps': 113853, 'loss/train': 0.9497979283332825} 08/31/2021 09:50:32 - INFO - __main__ - Step 113855: {'lr': 7.004794605192144e-05, 'samples': 21860160, 'steps': 113854, 'loss/train': 1.3857184648513794} 08/31/2021 09:50:33 - INFO - __main__ - Step 113856: {'lr': 7.004426229390174e-05, 'samples': 21860352, 'steps': 113855, 'loss/train': 0.6871346235275269} 08/31/2021 09:50:33 - INFO - __main__ - Step 113857: {'lr': 7.004057861696727e-05, 'samples': 21860544, 'steps': 113856, 'loss/train': 0.08538859337568283} 08/31/2021 09:50:35 - INFO - __main__ - Step 113858: {'lr': 7.003689502111979e-05, 'samples': 21860736, 'steps': 113857, 'loss/train': 1.2107641696929932} 08/31/2021 09:50:35 - INFO - __main__ - Step 113859: {'lr': 7.003321150636091e-05, 'samples': 21860928, 'steps': 113858, 'loss/train': 0.0650375559926033} 08/31/2021 09:50:36 - INFO - __main__ - Step 113860: {'lr': 7.002952807269225e-05, 'samples': 21861120, 'steps': 113859, 'loss/train': 1.1405975818634033} 08/31/2021 09:50:36 - INFO - __main__ - Step 113861: {'lr': 7.002584472011553e-05, 'samples': 21861312, 'steps': 113860, 'loss/train': 0.13869424164295197} 08/31/2021 09:50:37 - INFO - __main__ - Step 113862: {'lr': 7.00221614486324e-05, 'samples': 21861504, 'steps': 113861, 'loss/train': 1.4626097679138184} 08/31/2021 09:50:38 - INFO - __main__ - Step 113863: {'lr': 7.001847825824448e-05, 'samples': 21861696, 'steps': 113862, 'loss/train': 0.8556503653526306} 08/31/2021 09:50:38 - INFO - __main__ - Step 113864: {'lr': 7.001479514895349e-05, 'samples': 21861888, 'steps': 113863, 'loss/train': 0.9398984313011169} 08/31/2021 09:50:39 - INFO - __main__ - Step 113865: {'lr': 7.001111212076103e-05, 'samples': 21862080, 'steps': 113864, 'loss/train': 1.6497220993041992} 08/31/2021 09:50:39 - INFO - __main__ - Step 113866: {'lr': 7.000742917366878e-05, 'samples': 21862272, 'steps': 113865, 'loss/train': 1.1025220155715942} 08/31/2021 09:50:39 - INFO - __main__ - Step 113867: {'lr': 7.000374630767842e-05, 'samples': 21862464, 'steps': 113866, 'loss/train': 0.8826842904090881} 08/31/2021 09:50:41 - INFO - __main__ - Step 113868: {'lr': 7.00000635227916e-05, 'samples': 21862656, 'steps': 113867, 'loss/train': 1.3368688821792603} 08/31/2021 09:50:42 - INFO - __main__ - Step 113869: {'lr': 6.999638081901002e-05, 'samples': 21862848, 'steps': 113868, 'loss/train': 0.9425874948501587} 08/31/2021 09:50:42 - INFO - __main__ - Step 113870: {'lr': 6.999269819633525e-05, 'samples': 21863040, 'steps': 113869, 'loss/train': 1.4063048362731934} 08/31/2021 09:50:43 - INFO - __main__ - Step 113871: {'lr': 6.998901565476898e-05, 'samples': 21863232, 'steps': 113870, 'loss/train': 1.4085811376571655} 08/31/2021 09:50:43 - INFO - __main__ - Step 113872: {'lr': 6.998533319431288e-05, 'samples': 21863424, 'steps': 113871, 'loss/train': 1.528403878211975} 08/31/2021 09:50:44 - INFO - __main__ - Step 113873: {'lr': 6.998165081496863e-05, 'samples': 21863616, 'steps': 113872, 'loss/train': 1.238637924194336} 08/31/2021 09:50:45 - INFO - __main__ - Step 113874: {'lr': 6.997796851673785e-05, 'samples': 21863808, 'steps': 113873, 'loss/train': 1.1867625713348389} 08/31/2021 09:50:45 - INFO - __main__ - Step 113875: {'lr': 6.997428629962221e-05, 'samples': 21864000, 'steps': 113874, 'loss/train': 0.9886218309402466} 08/31/2021 09:50:46 - INFO - __main__ - Step 113876: {'lr': 6.997060416362338e-05, 'samples': 21864192, 'steps': 113875, 'loss/train': 0.8427309393882751} 08/31/2021 09:50:46 - INFO - __main__ - Step 113877: {'lr': 6.996692210874305e-05, 'samples': 21864384, 'steps': 113876, 'loss/train': 1.2230767011642456} 08/31/2021 09:50:48 - INFO - __main__ - Step 113878: {'lr': 6.996324013498282e-05, 'samples': 21864576, 'steps': 113877, 'loss/train': 1.052711844444275} 08/31/2021 09:50:48 - INFO - __main__ - Step 113879: {'lr': 6.995955824234437e-05, 'samples': 21864768, 'steps': 113878, 'loss/train': 1.4644485712051392} 08/31/2021 09:50:48 - INFO - __main__ - Step 113880: {'lr': 6.99558764308294e-05, 'samples': 21864960, 'steps': 113879, 'loss/train': 1.1118388175964355} 08/31/2021 09:50:49 - INFO - __main__ - Step 113881: {'lr': 6.995219470043951e-05, 'samples': 21865152, 'steps': 113880, 'loss/train': 1.0201616287231445} 08/31/2021 09:50:49 - INFO - __main__ - Step 113882: {'lr': 6.994851305117644e-05, 'samples': 21865344, 'steps': 113881, 'loss/train': 0.839512825012207} 08/31/2021 09:50:50 - INFO - __main__ - Step 113883: {'lr': 6.994483148304175e-05, 'samples': 21865536, 'steps': 113882, 'loss/train': 0.9137080907821655} 08/31/2021 09:50:51 - INFO - __main__ - Step 113884: {'lr': 6.994114999603713e-05, 'samples': 21865728, 'steps': 113883, 'loss/train': 1.3323960304260254} 08/31/2021 09:50:51 - INFO - __main__ - Step 113885: {'lr': 6.993746859016422e-05, 'samples': 21865920, 'steps': 113884, 'loss/train': 1.2592551708221436} 08/31/2021 09:50:52 - INFO - __main__ - Step 113886: {'lr': 6.993378726542476e-05, 'samples': 21866112, 'steps': 113885, 'loss/train': 0.48193299770355225} 08/31/2021 09:50:52 - INFO - __main__ - Step 113887: {'lr': 6.993010602182031e-05, 'samples': 21866304, 'steps': 113886, 'loss/train': 1.1625460386276245} 08/31/2021 09:50:54 - INFO - __main__ - Step 113888: {'lr': 6.992642485935261e-05, 'samples': 21866496, 'steps': 113887, 'loss/train': 1.3091084957122803} 08/31/2021 09:50:54 - INFO - __main__ - Step 113889: {'lr': 6.992274377802327e-05, 'samples': 21866688, 'steps': 113888, 'loss/train': 0.9435188174247742} 08/31/2021 09:50:54 - INFO - __main__ - Step 113890: {'lr': 6.991906277783396e-05, 'samples': 21866880, 'steps': 113889, 'loss/train': 1.0108140707015991} 08/31/2021 09:50:55 - INFO - __main__ - Step 113891: {'lr': 6.991538185878634e-05, 'samples': 21867072, 'steps': 113890, 'loss/train': 1.2036480903625488} 08/31/2021 09:50:55 - INFO - __main__ - Step 113892: {'lr': 6.991170102088207e-05, 'samples': 21867264, 'steps': 113891, 'loss/train': 0.031671419739723206} 08/31/2021 09:50:57 - INFO - __main__ - Step 113893: {'lr': 6.990802026412283e-05, 'samples': 21867456, 'steps': 113892, 'loss/train': 1.0179622173309326} 08/31/2021 09:50:57 - INFO - __main__ - Step 113894: {'lr': 6.990433958851023e-05, 'samples': 21867648, 'steps': 113893, 'loss/train': 0.9300468564033508} 08/31/2021 09:50:58 - INFO - __main__ - Step 113895: {'lr': 6.990065899404597e-05, 'samples': 21867840, 'steps': 113894, 'loss/train': 1.2529263496398926} 08/31/2021 09:50:58 - INFO - __main__ - Step 113896: {'lr': 6.989697848073177e-05, 'samples': 21868032, 'steps': 113895, 'loss/train': 0.8291143178939819} 08/31/2021 09:50:58 - INFO - __main__ - Step 113897: {'lr': 6.989329804856912e-05, 'samples': 21868224, 'steps': 113896, 'loss/train': 0.39326515793800354} 08/31/2021 09:50:59 - INFO - __main__ - Step 113898: {'lr': 6.988961769755978e-05, 'samples': 21868416, 'steps': 113897, 'loss/train': 1.41645348072052} 08/31/2021 09:51:00 - INFO - __main__ - Step 113899: {'lr': 6.98859374277054e-05, 'samples': 21868608, 'steps': 113898, 'loss/train': 1.3372843265533447} 08/31/2021 09:51:01 - INFO - __main__ - Step 113900: {'lr': 6.988225723900765e-05, 'samples': 21868800, 'steps': 113899, 'loss/train': 0.8445729613304138} 08/31/2021 09:51:01 - INFO - __main__ - Step 113901: {'lr': 6.987857713146817e-05, 'samples': 21868992, 'steps': 113900, 'loss/train': 0.9674294590950012} 08/31/2021 09:51:01 - INFO - __main__ - Step 113902: {'lr': 6.98748971050886e-05, 'samples': 21869184, 'steps': 113901, 'loss/train': 1.178896188735962} 08/31/2021 09:51:02 - INFO - __main__ - Step 113903: {'lr': 6.987121715987066e-05, 'samples': 21869376, 'steps': 113902, 'loss/train': 1.0994622707366943} 08/31/2021 09:51:03 - INFO - __main__ - Step 113904: {'lr': 6.986753729581594e-05, 'samples': 21869568, 'steps': 113903, 'loss/train': 0.4023541212081909} 08/31/2021 09:51:04 - INFO - __main__ - Step 113905: {'lr': 6.986385751292615e-05, 'samples': 21869760, 'steps': 113904, 'loss/train': 1.1837661266326904} 08/31/2021 09:51:04 - INFO - __main__ - Step 113906: {'lr': 6.986017781120291e-05, 'samples': 21869952, 'steps': 113905, 'loss/train': 1.559276819229126} 08/31/2021 09:51:04 - INFO - __main__ - Step 113907: {'lr': 6.985649819064788e-05, 'samples': 21870144, 'steps': 113906, 'loss/train': 1.1253912448883057} 08/31/2021 09:51:05 - INFO - __main__ - Step 113908: {'lr': 6.985281865126275e-05, 'samples': 21870336, 'steps': 113907, 'loss/train': 0.6136357188224792} 08/31/2021 09:51:06 - INFO - __main__ - Step 113909: {'lr': 6.984913919304925e-05, 'samples': 21870528, 'steps': 113908, 'loss/train': 1.0640814304351807} 08/31/2021 09:51:07 - INFO - __main__ - Step 113910: {'lr': 6.984545981600884e-05, 'samples': 21870720, 'steps': 113909, 'loss/train': 1.5986436605453491} 08/31/2021 09:51:07 - INFO - __main__ - Step 113911: {'lr': 6.984178052014331e-05, 'samples': 21870912, 'steps': 113910, 'loss/train': 1.4422130584716797} 08/31/2021 09:51:07 - INFO - __main__ - Step 113912: {'lr': 6.983810130545429e-05, 'samples': 21871104, 'steps': 113911, 'loss/train': 0.9554018974304199} 08/31/2021 09:51:08 - INFO - __main__ - Step 113913: {'lr': 6.983442217194344e-05, 'samples': 21871296, 'steps': 113912, 'loss/train': 0.7839992642402649} 08/31/2021 09:51:09 - INFO - __main__ - Step 113914: {'lr': 6.983074311961244e-05, 'samples': 21871488, 'steps': 113913, 'loss/train': 0.9407075047492981} 08/31/2021 09:51:10 - INFO - __main__ - Step 113915: {'lr': 6.982706414846288e-05, 'samples': 21871680, 'steps': 113914, 'loss/train': 0.6019166707992554} 08/31/2021 09:51:10 - INFO - __main__ - Step 113916: {'lr': 6.982338525849649e-05, 'samples': 21871872, 'steps': 113915, 'loss/train': 1.388803243637085} 08/31/2021 09:51:10 - INFO - __main__ - Step 113917: {'lr': 6.981970644971492e-05, 'samples': 21872064, 'steps': 113916, 'loss/train': 1.1930344104766846} 08/31/2021 09:51:11 - INFO - __main__ - Step 113918: {'lr': 6.981602772211979e-05, 'samples': 21872256, 'steps': 113917, 'loss/train': 1.3031400442123413} 08/31/2021 09:51:12 - INFO - __main__ - Step 113919: {'lr': 6.981234907571277e-05, 'samples': 21872448, 'steps': 113918, 'loss/train': 1.3386741876602173} 08/31/2021 09:51:13 - INFO - __main__ - Step 113920: {'lr': 6.98086705104956e-05, 'samples': 21872640, 'steps': 113919, 'loss/train': 0.9825043082237244} 08/31/2021 09:51:13 - INFO - __main__ - Step 113921: {'lr': 6.980499202646981e-05, 'samples': 21872832, 'steps': 113920, 'loss/train': 0.9649656414985657} 08/31/2021 09:51:14 - INFO - __main__ - Step 113922: {'lr': 6.980131362363709e-05, 'samples': 21873024, 'steps': 113921, 'loss/train': 0.5704132914543152} 08/31/2021 09:51:14 - INFO - __main__ - Step 113923: {'lr': 6.979763530199914e-05, 'samples': 21873216, 'steps': 113922, 'loss/train': 0.6369076371192932} 08/31/2021 09:51:14 - INFO - __main__ - Step 113924: {'lr': 6.979395706155758e-05, 'samples': 21873408, 'steps': 113923, 'loss/train': 0.8260701894760132} 08/31/2021 09:51:17 - INFO - __main__ - Step 113925: {'lr': 6.979027890231407e-05, 'samples': 21873600, 'steps': 113924, 'loss/train': 0.4713549315929413} 08/31/2021 09:51:17 - INFO - __main__ - Step 113926: {'lr': 6.97866008242703e-05, 'samples': 21873792, 'steps': 113925, 'loss/train': 1.2157437801361084} 08/31/2021 09:51:17 - INFO - __main__ - Step 113927: {'lr': 6.978292282742791e-05, 'samples': 21873984, 'steps': 113926, 'loss/train': 0.9364623427391052} 08/31/2021 09:51:18 - INFO - __main__ - Step 113928: {'lr': 6.977924491178852e-05, 'samples': 21874176, 'steps': 113927, 'loss/train': 1.2130705118179321} 08/31/2021 09:51:18 - INFO - __main__ - Step 113929: {'lr': 6.977556707735385e-05, 'samples': 21874368, 'steps': 113928, 'loss/train': 0.7566735148429871} 08/31/2021 09:51:20 - INFO - __main__ - Step 113930: {'lr': 6.977188932412554e-05, 'samples': 21874560, 'steps': 113929, 'loss/train': 1.1855783462524414} 08/31/2021 09:51:20 - INFO - __main__ - Step 113931: {'lr': 6.976821165210528e-05, 'samples': 21874752, 'steps': 113930, 'loss/train': 1.1947388648986816} 08/31/2021 09:51:21 - INFO - __main__ - Step 113932: {'lr': 6.976453406129462e-05, 'samples': 21874944, 'steps': 113931, 'loss/train': 0.7409427762031555} 08/31/2021 09:51:21 - INFO - __main__ - Step 113933: {'lr': 6.976085655169529e-05, 'samples': 21875136, 'steps': 113932, 'loss/train': 1.2003092765808105} 08/31/2021 09:51:21 - INFO - __main__ - Step 113934: {'lr': 6.975717912330892e-05, 'samples': 21875328, 'steps': 113933, 'loss/train': 1.5645127296447754} 08/31/2021 09:51:23 - INFO - __main__ - Step 113935: {'lr': 6.975350177613718e-05, 'samples': 21875520, 'steps': 113934, 'loss/train': 0.8889496922492981} 08/31/2021 09:51:23 - INFO - __main__ - Step 113936: {'lr': 6.974982451018175e-05, 'samples': 21875712, 'steps': 113935, 'loss/train': 1.7888622283935547} 08/31/2021 09:51:24 - INFO - __main__ - Step 113937: {'lr': 6.974614732544426e-05, 'samples': 21875904, 'steps': 113936, 'loss/train': 1.3270753622055054} 08/31/2021 09:51:24 - INFO - __main__ - Step 113938: {'lr': 6.974247022192636e-05, 'samples': 21876096, 'steps': 113937, 'loss/train': 0.5018258690834045} 08/31/2021 09:51:24 - INFO - __main__ - Step 113939: {'lr': 6.973879319962975e-05, 'samples': 21876288, 'steps': 113938, 'loss/train': 1.1788384914398193} 08/31/2021 09:51:26 - INFO - __main__ - Step 113940: {'lr': 6.973511625855605e-05, 'samples': 21876480, 'steps': 113939, 'loss/train': 1.3600282669067383} 08/31/2021 09:51:26 - INFO - __main__ - Step 113941: {'lr': 6.973143939870691e-05, 'samples': 21876672, 'steps': 113940, 'loss/train': 0.6150314807891846} 08/31/2021 09:51:27 - INFO - __main__ - Step 113942: {'lr': 6.97277626200841e-05, 'samples': 21876864, 'steps': 113941, 'loss/train': 1.069471001625061} 08/31/2021 09:51:27 - INFO - __main__ - Step 113943: {'lr': 6.972408592268909e-05, 'samples': 21877056, 'steps': 113942, 'loss/train': 0.9200001358985901} 08/31/2021 09:51:27 - INFO - __main__ - Step 113944: {'lr': 6.97204093065236e-05, 'samples': 21877248, 'steps': 113943, 'loss/train': 1.3853707313537598} 08/31/2021 09:51:28 - INFO - __main__ - Step 113945: {'lr': 6.971673277158936e-05, 'samples': 21877440, 'steps': 113944, 'loss/train': 1.3342030048370361} 08/31/2021 09:51:29 - INFO - __main__ - Step 113946: {'lr': 6.971305631788794e-05, 'samples': 21877632, 'steps': 113945, 'loss/train': 0.29154035449028015} 08/31/2021 09:51:30 - INFO - __main__ - Step 113947: {'lr': 6.970937994542104e-05, 'samples': 21877824, 'steps': 113946, 'loss/train': 0.24921603500843048} 08/31/2021 09:51:30 - INFO - __main__ - Step 113948: {'lr': 6.970570365419032e-05, 'samples': 21878016, 'steps': 113947, 'loss/train': 0.9325618147850037} 08/31/2021 09:51:30 - INFO - __main__ - Step 113949: {'lr': 6.970202744419743e-05, 'samples': 21878208, 'steps': 113948, 'loss/train': 1.0420325994491577} 08/31/2021 09:51:31 - INFO - __main__ - Step 113950: {'lr': 6.969835131544403e-05, 'samples': 21878400, 'steps': 113949, 'loss/train': 1.5593600273132324} 08/31/2021 09:51:32 - INFO - __main__ - Step 113951: {'lr': 6.969467526793174e-05, 'samples': 21878592, 'steps': 113950, 'loss/train': 0.9705786108970642} 08/31/2021 09:51:33 - INFO - __main__ - Step 113952: {'lr': 6.969099930166228e-05, 'samples': 21878784, 'steps': 113951, 'loss/train': 1.256200909614563} 08/31/2021 09:51:33 - INFO - __main__ - Step 113953: {'lr': 6.968732341663733e-05, 'samples': 21878976, 'steps': 113952, 'loss/train': 0.40793323516845703} 08/31/2021 09:51:33 - INFO - __main__ - Step 113954: {'lr': 6.968364761285842e-05, 'samples': 21879168, 'steps': 113953, 'loss/train': 1.4568675756454468} 08/31/2021 09:51:34 - INFO - __main__ - Step 113955: {'lr': 6.96799718903273e-05, 'samples': 21879360, 'steps': 113954, 'loss/train': 1.2128658294677734} 08/31/2021 09:51:35 - INFO - __main__ - Step 113956: {'lr': 6.967629624904556e-05, 'samples': 21879552, 'steps': 113955, 'loss/train': 1.508195400238037} 08/31/2021 09:51:36 - INFO - __main__ - Step 113957: {'lr': 6.967262068901492e-05, 'samples': 21879744, 'steps': 113956, 'loss/train': 1.2437492609024048} 08/31/2021 09:51:36 - INFO - __main__ - Step 113958: {'lr': 6.966894521023704e-05, 'samples': 21879936, 'steps': 113957, 'loss/train': 1.1181557178497314} 08/31/2021 09:51:36 - INFO - __main__ - Step 113959: {'lr': 6.966526981271352e-05, 'samples': 21880128, 'steps': 113958, 'loss/train': 1.5444786548614502} 08/31/2021 09:51:37 - INFO - __main__ - Step 113960: {'lr': 6.966159449644605e-05, 'samples': 21880320, 'steps': 113959, 'loss/train': 1.448568344116211} 08/31/2021 09:51:39 - INFO - __main__ - Step 113961: {'lr': 6.965791926143627e-05, 'samples': 21880512, 'steps': 113960, 'loss/train': 1.5869864225387573} 08/31/2021 09:51:39 - INFO - __main__ - Step 113962: {'lr': 6.965424410768587e-05, 'samples': 21880704, 'steps': 113961, 'loss/train': 0.7912145256996155} 08/31/2021 09:51:39 - INFO - __main__ - Step 113963: {'lr': 6.965056903519648e-05, 'samples': 21880896, 'steps': 113962, 'loss/train': 1.7627005577087402} 08/31/2021 09:51:40 - INFO - __main__ - Step 113964: {'lr': 6.964689404396981e-05, 'samples': 21881088, 'steps': 113963, 'loss/train': 0.35190290212631226} 08/31/2021 09:51:40 - INFO - __main__ - Step 113965: {'lr': 6.964321913400742e-05, 'samples': 21881280, 'steps': 113964, 'loss/train': 1.099032998085022} 08/31/2021 09:51:42 - INFO - __main__ - Step 113966: {'lr': 6.963954430531103e-05, 'samples': 21881472, 'steps': 113965, 'loss/train': 0.8716630935668945} 08/31/2021 09:51:42 - INFO - __main__ - Step 113967: {'lr': 6.963586955788224e-05, 'samples': 21881664, 'steps': 113966, 'loss/train': 0.8247172832489014} 08/31/2021 09:51:42 - INFO - __main__ - Step 113968: {'lr': 6.963219489172276e-05, 'samples': 21881856, 'steps': 113967, 'loss/train': 0.9869101047515869} 08/31/2021 09:51:43 - INFO - __main__ - Step 113969: {'lr': 6.962852030683423e-05, 'samples': 21882048, 'steps': 113968, 'loss/train': 0.4566025137901306} 08/31/2021 09:51:43 - INFO - __main__ - Step 113970: {'lr': 6.962484580321829e-05, 'samples': 21882240, 'steps': 113969, 'loss/train': 1.1987463235855103} 08/31/2021 09:51:43 - INFO - __main__ - Step 113971: {'lr': 6.962117138087662e-05, 'samples': 21882432, 'steps': 113970, 'loss/train': 1.0727310180664062} 08/31/2021 09:51:46 - INFO - __main__ - Step 113972: {'lr': 6.961749703981087e-05, 'samples': 21882624, 'steps': 113971, 'loss/train': 1.7314453125} 08/31/2021 09:51:46 - INFO - __main__ - Step 113973: {'lr': 6.96138227800227e-05, 'samples': 21882816, 'steps': 113972, 'loss/train': 0.43066999316215515} 08/31/2021 09:51:46 - INFO - __main__ - Step 113974: {'lr': 6.961014860151376e-05, 'samples': 21883008, 'steps': 113973, 'loss/train': 0.9055215716362} 08/31/2021 09:51:47 - INFO - __main__ - Step 113975: {'lr': 6.96064745042857e-05, 'samples': 21883200, 'steps': 113974, 'loss/train': 0.34320077300071716} 08/31/2021 09:51:47 - INFO - __main__ - Step 113976: {'lr': 6.960280048834025e-05, 'samples': 21883392, 'steps': 113975, 'loss/train': 0.08245530724525452} 08/31/2021 09:51:49 - INFO - __main__ - Step 113977: {'lr': 6.959912655367892e-05, 'samples': 21883584, 'steps': 113976, 'loss/train': 1.1310819387435913} 08/31/2021 09:51:50 - INFO - __main__ - Step 113978: {'lr': 6.959545270030343e-05, 'samples': 21883776, 'steps': 113977, 'loss/train': 1.4392509460449219} 08/31/2021 09:51:50 - INFO - __main__ - Step 113979: {'lr': 6.959177892821544e-05, 'samples': 21883968, 'steps': 113978, 'loss/train': 1.3358371257781982} 08/31/2021 09:51:50 - INFO - __main__ - Step 113980: {'lr': 6.958810523741663e-05, 'samples': 21884160, 'steps': 113979, 'loss/train': 4.1855788230896} 08/31/2021 09:51:51 - INFO - __main__ - Step 113981: {'lr': 6.958443162790864e-05, 'samples': 21884352, 'steps': 113980, 'loss/train': 1.6527738571166992} 08/31/2021 09:51:52 - INFO - __main__ - Step 113982: {'lr': 6.958075809969311e-05, 'samples': 21884544, 'steps': 113981, 'loss/train': 1.5438735485076904} 08/31/2021 09:51:53 - INFO - __main__ - Step 113983: {'lr': 6.95770846527717e-05, 'samples': 21884736, 'steps': 113982, 'loss/train': 1.6724772453308105} 08/31/2021 09:51:53 - INFO - __main__ - Step 113984: {'lr': 6.957341128714608e-05, 'samples': 21884928, 'steps': 113983, 'loss/train': 1.1583220958709717} 08/31/2021 09:51:53 - INFO - __main__ - Step 113985: {'lr': 6.956973800281791e-05, 'samples': 21885120, 'steps': 113984, 'loss/train': 1.077584981918335} 08/31/2021 09:51:54 - INFO - __main__ - Step 113986: {'lr': 6.95660647997888e-05, 'samples': 21885312, 'steps': 113985, 'loss/train': 1.4839756488800049} 08/31/2021 09:51:55 - INFO - __main__ - Step 113987: {'lr': 6.956239167806048e-05, 'samples': 21885504, 'steps': 113986, 'loss/train': 1.5225794315338135} 08/31/2021 09:51:56 - INFO - __main__ - Step 113988: {'lr': 6.955871863763452e-05, 'samples': 21885696, 'steps': 113987, 'loss/train': 1.2870923280715942} 08/31/2021 09:51:56 - INFO - __main__ - Step 113989: {'lr': 6.955504567851264e-05, 'samples': 21885888, 'steps': 113988, 'loss/train': 1.2724610567092896} 08/31/2021 09:51:56 - INFO - __main__ - Step 113990: {'lr': 6.955137280069653e-05, 'samples': 21886080, 'steps': 113989, 'loss/train': 1.1582800149917603} 08/31/2021 09:51:57 - INFO - __main__ - Step 113991: {'lr': 6.954770000418773e-05, 'samples': 21886272, 'steps': 113990, 'loss/train': 1.1717780828475952} 08/31/2021 09:51:57 - INFO - __main__ - Step 113992: {'lr': 6.954402728898796e-05, 'samples': 21886464, 'steps': 113991, 'loss/train': 1.5668203830718994} 08/31/2021 09:51:59 - INFO - __main__ - Step 113993: {'lr': 6.954035465509884e-05, 'samples': 21886656, 'steps': 113992, 'loss/train': 0.8843286037445068} 08/31/2021 09:51:59 - INFO - __main__ - Step 113994: {'lr': 6.953668210252207e-05, 'samples': 21886848, 'steps': 113993, 'loss/train': 0.720476508140564} 08/31/2021 09:52:00 - INFO - __main__ - Step 113995: {'lr': 6.953300963125928e-05, 'samples': 21887040, 'steps': 113994, 'loss/train': 1.004384160041809} 08/31/2021 09:52:00 - INFO - __main__ - Step 113996: {'lr': 6.952933724131211e-05, 'samples': 21887232, 'steps': 113995, 'loss/train': 1.3058481216430664} 08/31/2021 09:52:00 - INFO - __main__ - Step 113997: {'lr': 6.952566493268225e-05, 'samples': 21887424, 'steps': 113996, 'loss/train': 1.4949512481689453} 08/31/2021 09:52:02 - INFO - __main__ - Step 113998: {'lr': 6.952199270537136e-05, 'samples': 21887616, 'steps': 113997, 'loss/train': 1.173852801322937} 08/31/2021 09:52:02 - INFO - __main__ - Step 113999: {'lr': 6.951832055938106e-05, 'samples': 21887808, 'steps': 113998, 'loss/train': 1.2661408185958862} 08/31/2021 09:52:02 - INFO - __main__ - Step 114000: {'lr': 6.9514648494713e-05, 'samples': 21888000, 'steps': 113999, 'loss/train': 0.412199467420578} 08/31/2021 09:52:03 - INFO - __main__ - Step 114001: {'lr': 6.95109765113689e-05, 'samples': 21888192, 'steps': 114000, 'loss/train': 0.28297385573387146} 08/31/2021 09:52:03 - INFO - __main__ - Step 114002: {'lr': 6.950730460935034e-05, 'samples': 21888384, 'steps': 114001, 'loss/train': 1.1465120315551758} 08/31/2021 09:52:05 - INFO - __main__ - Step 114003: {'lr': 6.950363278865909e-05, 'samples': 21888576, 'steps': 114002, 'loss/train': 1.1538209915161133} 08/31/2021 09:52:05 - INFO - __main__ - Step 114004: {'lr': 6.949996104929663e-05, 'samples': 21888768, 'steps': 114003, 'loss/train': 0.9517199993133545} 08/31/2021 09:52:06 - INFO - __main__ - Step 114005: {'lr': 6.949628939126471e-05, 'samples': 21888960, 'steps': 114004, 'loss/train': 0.8589492440223694} 08/31/2021 09:52:06 - INFO - __main__ - Step 114006: {'lr': 6.949261781456497e-05, 'samples': 21889152, 'steps': 114005, 'loss/train': 1.074754238128662} 08/31/2021 09:52:06 - INFO - __main__ - Step 114007: {'lr': 6.948894631919908e-05, 'samples': 21889344, 'steps': 114006, 'loss/train': 1.4681100845336914} 08/31/2021 09:52:08 - INFO - __main__ - Step 114008: {'lr': 6.948527490516867e-05, 'samples': 21889536, 'steps': 114007, 'loss/train': 1.4815949201583862} 08/31/2021 09:52:08 - INFO - __main__ - Step 114009: {'lr': 6.948160357247543e-05, 'samples': 21889728, 'steps': 114008, 'loss/train': 1.0342634916305542} 08/31/2021 09:52:09 - INFO - __main__ - Step 114010: {'lr': 6.947793232112098e-05, 'samples': 21889920, 'steps': 114009, 'loss/train': 1.3088948726654053} 08/31/2021 09:52:09 - INFO - __main__ - Step 114011: {'lr': 6.9474261151107e-05, 'samples': 21890112, 'steps': 114010, 'loss/train': 1.0327703952789307} 08/31/2021 09:52:09 - INFO - __main__ - Step 114012: {'lr': 6.947059006243511e-05, 'samples': 21890304, 'steps': 114011, 'loss/train': 0.4016836881637573} 08/31/2021 09:52:11 - INFO - __main__ - Step 114013: {'lr': 6.946691905510702e-05, 'samples': 21890496, 'steps': 114012, 'loss/train': 1.484086275100708} 08/31/2021 09:52:11 - INFO - __main__ - Step 114014: {'lr': 6.946324812912433e-05, 'samples': 21890688, 'steps': 114013, 'loss/train': 1.5624347925186157} 08/31/2021 09:52:12 - INFO - __main__ - Step 114015: {'lr': 6.945957728448871e-05, 'samples': 21890880, 'steps': 114014, 'loss/train': 1.5566637516021729} 08/31/2021 09:52:12 - INFO - __main__ - Step 114016: {'lr': 6.945590652120182e-05, 'samples': 21891072, 'steps': 114015, 'loss/train': 1.0654109716415405} 08/31/2021 09:52:12 - INFO - __main__ - Step 114017: {'lr': 6.945223583926538e-05, 'samples': 21891264, 'steps': 114016, 'loss/train': 0.9266629219055176} 08/31/2021 09:52:13 - INFO - __main__ - Step 114018: {'lr': 6.944856523868092e-05, 'samples': 21891456, 'steps': 114017, 'loss/train': 0.4550000727176666} 08/31/2021 09:52:14 - INFO - __main__ - Step 114019: {'lr': 6.944489471945015e-05, 'samples': 21891648, 'steps': 114018, 'loss/train': 1.0241568088531494} 08/31/2021 09:52:15 - INFO - __main__ - Step 114020: {'lr': 6.944122428157473e-05, 'samples': 21891840, 'steps': 114019, 'loss/train': 0.9639015793800354} 08/31/2021 09:52:15 - INFO - __main__ - Step 114021: {'lr': 6.94375539250563e-05, 'samples': 21892032, 'steps': 114020, 'loss/train': 1.0337821245193481} 08/31/2021 09:52:15 - INFO - __main__ - Step 114022: {'lr': 6.94338836498965e-05, 'samples': 21892224, 'steps': 114021, 'loss/train': 0.8559634685516357} 08/31/2021 09:52:16 - INFO - __main__ - Step 114023: {'lr': 6.943021345609704e-05, 'samples': 21892416, 'steps': 114022, 'loss/train': 0.974456787109375} 08/31/2021 09:52:17 - INFO - __main__ - Step 114024: {'lr': 6.94265433436595e-05, 'samples': 21892608, 'steps': 114023, 'loss/train': 1.2627158164978027} 08/31/2021 09:52:18 - INFO - __main__ - Step 114025: {'lr': 6.942287331258562e-05, 'samples': 21892800, 'steps': 114024, 'loss/train': 1.1176416873931885} 08/31/2021 09:52:18 - INFO - __main__ - Step 114026: {'lr': 6.941920336287696e-05, 'samples': 21892992, 'steps': 114025, 'loss/train': 0.9813427925109863} 08/31/2021 09:52:18 - INFO - __main__ - Step 114027: {'lr': 6.941553349453525e-05, 'samples': 21893184, 'steps': 114026, 'loss/train': 1.4622292518615723} 08/31/2021 09:52:19 - INFO - __main__ - Step 114028: {'lr': 6.941186370756211e-05, 'samples': 21893376, 'steps': 114027, 'loss/train': 1.0929639339447021} 08/31/2021 09:52:20 - INFO - __main__ - Step 114029: {'lr': 6.940819400195919e-05, 'samples': 21893568, 'steps': 114028, 'loss/train': 1.7581833600997925} 08/31/2021 09:52:21 - INFO - __main__ - Step 114030: {'lr': 6.940452437772824e-05, 'samples': 21893760, 'steps': 114029, 'loss/train': 0.8114413619041443} 08/31/2021 09:52:21 - INFO - __main__ - Step 114031: {'lr': 6.940085483487074e-05, 'samples': 21893952, 'steps': 114030, 'loss/train': 1.203249454498291} 08/31/2021 09:52:21 - INFO - __main__ - Step 114032: {'lr': 6.939718537338843e-05, 'samples': 21894144, 'steps': 114031, 'loss/train': 1.3893179893493652} 08/31/2021 09:52:22 - INFO - __main__ - Step 114033: {'lr': 6.939351599328298e-05, 'samples': 21894336, 'steps': 114032, 'loss/train': 0.9899357557296753} 08/31/2021 09:52:24 - INFO - __main__ - Step 114034: {'lr': 6.9389846694556e-05, 'samples': 21894528, 'steps': 114033, 'loss/train': 0.8551040887832642} 08/31/2021 09:52:24 - INFO - __main__ - Step 114035: {'lr': 6.938617747720916e-05, 'samples': 21894720, 'steps': 114034, 'loss/train': 1.4177080392837524} 08/31/2021 09:52:25 - INFO - __main__ - Step 114036: {'lr': 6.938250834124413e-05, 'samples': 21894912, 'steps': 114035, 'loss/train': 0.6638404130935669} 08/31/2021 09:52:25 - INFO - __main__ - Step 114037: {'lr': 6.937883928666256e-05, 'samples': 21895104, 'steps': 114036, 'loss/train': 1.2346711158752441} 08/31/2021 09:52:26 - INFO - __main__ - Step 114038: {'lr': 6.937517031346611e-05, 'samples': 21895296, 'steps': 114037, 'loss/train': 1.8506109714508057} 08/31/2021 09:52:26 - INFO - __main__ - Step 114039: {'lr': 6.93715014216564e-05, 'samples': 21895488, 'steps': 114038, 'loss/train': 1.2287782430648804} 08/31/2021 09:52:27 - INFO - __main__ - Step 114040: {'lr': 6.936783261123511e-05, 'samples': 21895680, 'steps': 114039, 'loss/train': 1.0596299171447754} 08/31/2021 09:52:28 - INFO - __main__ - Step 114041: {'lr': 6.93641638822039e-05, 'samples': 21895872, 'steps': 114040, 'loss/train': 0.7800902128219604} 08/31/2021 09:52:28 - INFO - __main__ - Step 114042: {'lr': 6.936049523456439e-05, 'samples': 21896064, 'steps': 114041, 'loss/train': 1.381797432899475} 08/31/2021 09:52:28 - INFO - __main__ - Step 114043: {'lr': 6.935682666831836e-05, 'samples': 21896256, 'steps': 114042, 'loss/train': 1.0437486171722412} 08/31/2021 09:52:29 - INFO - __main__ - Step 114044: {'lr': 6.935315818346725e-05, 'samples': 21896448, 'steps': 114043, 'loss/train': 1.1146769523620605} 08/31/2021 09:52:30 - INFO - __main__ - Step 114045: {'lr': 6.934948978001281e-05, 'samples': 21896640, 'steps': 114044, 'loss/train': 1.337168574333191} 08/31/2021 09:52:31 - INFO - __main__ - Step 114046: {'lr': 6.934582145795673e-05, 'samples': 21896832, 'steps': 114045, 'loss/train': 1.2232787609100342} 08/31/2021 09:52:31 - INFO - __main__ - Step 114047: {'lr': 6.934215321730064e-05, 'samples': 21897024, 'steps': 114046, 'loss/train': 0.6751248836517334} 08/31/2021 09:52:31 - INFO - __main__ - Step 114048: {'lr': 6.933848505804616e-05, 'samples': 21897216, 'steps': 114047, 'loss/train': 1.3451101779937744} 08/31/2021 09:52:32 - INFO - __main__ - Step 114049: {'lr': 6.9334816980195e-05, 'samples': 21897408, 'steps': 114048, 'loss/train': 1.254487156867981} 08/31/2021 09:52:33 - INFO - __main__ - Step 114050: {'lr': 6.933114898374876e-05, 'samples': 21897600, 'steps': 114049, 'loss/train': 0.6511754989624023} 08/31/2021 09:52:34 - INFO - __main__ - Step 114051: {'lr': 6.932748106870912e-05, 'samples': 21897792, 'steps': 114050, 'loss/train': 0.4631928503513336} 08/31/2021 09:52:34 - INFO - __main__ - Step 114052: {'lr': 6.932381323507775e-05, 'samples': 21897984, 'steps': 114051, 'loss/train': 1.5148272514343262} 08/31/2021 09:52:34 - INFO - __main__ - Step 114053: {'lr': 6.932014548285625e-05, 'samples': 21898176, 'steps': 114052, 'loss/train': 1.2903518676757812} 08/31/2021 09:52:35 - INFO - __main__ - Step 114054: {'lr': 6.931647781204633e-05, 'samples': 21898368, 'steps': 114053, 'loss/train': 0.8389026522636414} 08/31/2021 09:52:37 - INFO - __main__ - Step 114055: {'lr': 6.93128102226496e-05, 'samples': 21898560, 'steps': 114054, 'loss/train': 0.5335372090339661} 08/31/2021 09:52:37 - INFO - __main__ - Step 114056: {'lr': 6.930914271466776e-05, 'samples': 21898752, 'steps': 114055, 'loss/train': 1.5867596864700317} 08/31/2021 09:52:37 - INFO - __main__ - Step 114057: {'lr': 6.930547528810247e-05, 'samples': 21898944, 'steps': 114056, 'loss/train': 2.2083849906921387} 08/31/2021 09:52:38 - INFO - __main__ - Step 114058: {'lr': 6.930180794295529e-05, 'samples': 21899136, 'steps': 114057, 'loss/train': 0.9122598767280579} 08/31/2021 09:52:38 - INFO - __main__ - Step 114059: {'lr': 6.929814067922794e-05, 'samples': 21899328, 'steps': 114058, 'loss/train': 0.8313152194023132} 08/31/2021 09:52:40 - INFO - __main__ - Step 114060: {'lr': 6.929447349692203e-05, 'samples': 21899520, 'steps': 114059, 'loss/train': 1.8741569519042969} 08/31/2021 09:52:40 - INFO - __main__ - Step 114061: {'lr': 6.929080639603924e-05, 'samples': 21899712, 'steps': 114060, 'loss/train': 1.1185842752456665} 08/31/2021 09:52:41 - INFO - __main__ - Step 114062: {'lr': 6.928713937658124e-05, 'samples': 21899904, 'steps': 114061, 'loss/train': 0.2569122314453125} 08/31/2021 09:52:41 - INFO - __main__ - Step 114063: {'lr': 6.928347243854966e-05, 'samples': 21900096, 'steps': 114062, 'loss/train': 1.0890394449234009} 08/31/2021 09:52:41 - INFO - __main__ - Step 114064: {'lr': 6.927980558194616e-05, 'samples': 21900288, 'steps': 114063, 'loss/train': 1.6842447519302368} 08/31/2021 09:52:42 - INFO - __main__ - Step 114065: {'lr': 6.927613880677238e-05, 'samples': 21900480, 'steps': 114064, 'loss/train': 1.0014870166778564} 08/31/2021 09:52:43 - INFO - __main__ - Step 114066: {'lr': 6.927247211303001e-05, 'samples': 21900672, 'steps': 114065, 'loss/train': 1.2623566389083862} 08/31/2021 09:52:44 - INFO - __main__ - Step 114067: {'lr': 6.926880550072065e-05, 'samples': 21900864, 'steps': 114066, 'loss/train': 1.4352844953536987} 08/31/2021 09:52:44 - INFO - __main__ - Step 114068: {'lr': 6.926513896984602e-05, 'samples': 21901056, 'steps': 114067, 'loss/train': 0.694115161895752} 08/31/2021 09:52:44 - INFO - __main__ - Step 114069: {'lr': 6.926147252040768e-05, 'samples': 21901248, 'steps': 114068, 'loss/train': 1.1317150592803955} 08/31/2021 09:52:45 - INFO - __main__ - Step 114070: {'lr': 6.925780615240742e-05, 'samples': 21901440, 'steps': 114069, 'loss/train': 1.2048864364624023} 08/31/2021 09:52:46 - INFO - __main__ - Step 114071: {'lr': 6.925413986584675e-05, 'samples': 21901632, 'steps': 114070, 'loss/train': 0.7608428001403809} 08/31/2021 09:52:47 - INFO - __main__ - Step 114072: {'lr': 6.925047366072734e-05, 'samples': 21901824, 'steps': 114071, 'loss/train': 0.6781041026115417} 08/31/2021 09:52:47 - INFO - __main__ - Step 114073: {'lr': 6.92468075370509e-05, 'samples': 21902016, 'steps': 114072, 'loss/train': 0.7453535199165344} 08/31/2021 09:52:47 - INFO - __main__ - Step 114074: {'lr': 6.924314149481905e-05, 'samples': 21902208, 'steps': 114073, 'loss/train': 1.241307258605957} 08/31/2021 09:52:48 - INFO - __main__ - Step 114075: {'lr': 6.923947553403345e-05, 'samples': 21902400, 'steps': 114074, 'loss/train': 0.6902301907539368} 08/31/2021 09:52:49 - INFO - __main__ - Step 114076: {'lr': 6.923580965469578e-05, 'samples': 21902592, 'steps': 114075, 'loss/train': 1.1477073431015015} 08/31/2021 09:52:50 - INFO - __main__ - Step 114077: {'lr': 6.923214385680765e-05, 'samples': 21902784, 'steps': 114076, 'loss/train': 1.5342787504196167} 08/31/2021 09:52:50 - INFO - __main__ - Step 114078: {'lr': 6.92284781403707e-05, 'samples': 21902976, 'steps': 114077, 'loss/train': 0.45974504947662354} 08/31/2021 09:52:51 - INFO - __main__ - Step 114079: {'lr': 6.922481250538665e-05, 'samples': 21903168, 'steps': 114078, 'loss/train': 1.157257080078125} 08/31/2021 09:52:51 - INFO - __main__ - Step 114080: {'lr': 6.922114695185708e-05, 'samples': 21903360, 'steps': 114079, 'loss/train': 1.5711653232574463} 08/31/2021 09:52:52 - INFO - __main__ - Step 114081: {'lr': 6.921748147978368e-05, 'samples': 21903552, 'steps': 114080, 'loss/train': 0.611537754535675} 08/31/2021 09:52:53 - INFO - __main__ - Step 114082: {'lr': 6.92138160891681e-05, 'samples': 21903744, 'steps': 114081, 'loss/train': 1.5969340801239014} 08/31/2021 09:52:53 - INFO - __main__ - Step 114083: {'lr': 6.921015078001197e-05, 'samples': 21903936, 'steps': 114082, 'loss/train': 1.353057861328125} 08/31/2021 09:52:54 - INFO - __main__ - Step 114084: {'lr': 6.920648555231704e-05, 'samples': 21904128, 'steps': 114083, 'loss/train': 1.1898077726364136} 08/31/2021 09:52:54 - INFO - __main__ - Step 114085: {'lr': 6.92028204060848e-05, 'samples': 21904320, 'steps': 114084, 'loss/train': 1.2084108591079712} 08/31/2021 09:52:56 - INFO - __main__ - Step 114086: {'lr': 6.919915534131698e-05, 'samples': 21904512, 'steps': 114085, 'loss/train': 1.3020572662353516} 08/31/2021 09:52:56 - INFO - __main__ - Step 114087: {'lr': 6.919549035801522e-05, 'samples': 21904704, 'steps': 114086, 'loss/train': 1.1274501085281372} 08/31/2021 09:52:57 - INFO - __main__ - Step 114088: {'lr': 6.919182545618121e-05, 'samples': 21904896, 'steps': 114087, 'loss/train': 0.2340552806854248} 08/31/2021 09:52:57 - INFO - __main__ - Step 114089: {'lr': 6.918816063581657e-05, 'samples': 21905088, 'steps': 114088, 'loss/train': 0.3426576256752014} 08/31/2021 09:52:57 - INFO - __main__ - Step 114090: {'lr': 6.918449589692294e-05, 'samples': 21905280, 'steps': 114089, 'loss/train': 1.383893609046936} 08/31/2021 09:52:58 - INFO - __main__ - Step 114091: {'lr': 6.918083123950198e-05, 'samples': 21905472, 'steps': 114090, 'loss/train': 0.6768255829811096} 08/31/2021 09:52:59 - INFO - __main__ - Step 114092: {'lr': 6.917716666355536e-05, 'samples': 21905664, 'steps': 114091, 'loss/train': 0.6078172922134399} 08/31/2021 09:53:00 - INFO - __main__ - Step 114093: {'lr': 6.917350216908471e-05, 'samples': 21905856, 'steps': 114092, 'loss/train': 0.9346595406532288} 08/31/2021 09:53:00 - INFO - __main__ - Step 114094: {'lr': 6.91698377560917e-05, 'samples': 21906048, 'steps': 114093, 'loss/train': 1.2765998840332031} 08/31/2021 09:53:00 - INFO - __main__ - Step 114095: {'lr': 6.916617342457796e-05, 'samples': 21906240, 'steps': 114094, 'loss/train': 1.1310611963272095} 08/31/2021 09:53:01 - INFO - __main__ - Step 114096: {'lr': 6.916250917454516e-05, 'samples': 21906432, 'steps': 114095, 'loss/train': 1.191643238067627} 08/31/2021 09:53:02 - INFO - __main__ - Step 114097: {'lr': 6.9158845005995e-05, 'samples': 21906624, 'steps': 114096, 'loss/train': 1.2625246047973633} 08/31/2021 09:53:03 - INFO - __main__ - Step 114098: {'lr': 6.915518091892903e-05, 'samples': 21906816, 'steps': 114097, 'loss/train': 0.8112444281578064} 08/31/2021 09:53:03 - INFO - __main__ - Step 114099: {'lr': 6.915151691334892e-05, 'samples': 21907008, 'steps': 114098, 'loss/train': 1.6433416604995728} 08/31/2021 09:53:03 - INFO - __main__ - Step 114100: {'lr': 6.914785298925636e-05, 'samples': 21907200, 'steps': 114099, 'loss/train': 1.0781179666519165} 08/31/2021 09:53:04 - INFO - __main__ - Step 114101: {'lr': 6.914418914665299e-05, 'samples': 21907392, 'steps': 114100, 'loss/train': 0.8476288318634033} 08/31/2021 09:53:05 - INFO - __main__ - Step 114102: {'lr': 6.914052538554044e-05, 'samples': 21907584, 'steps': 114101, 'loss/train': 1.6023533344268799} 08/31/2021 09:53:06 - INFO - __main__ - Step 114103: {'lr': 6.913686170592037e-05, 'samples': 21907776, 'steps': 114102, 'loss/train': 0.7130312919616699} 08/31/2021 09:53:06 - INFO - __main__ - Step 114104: {'lr': 6.913319810779448e-05, 'samples': 21907968, 'steps': 114103, 'loss/train': 0.7073086500167847} 08/31/2021 09:53:07 - INFO - __main__ - Step 114105: {'lr': 6.912953459116433e-05, 'samples': 21908160, 'steps': 114104, 'loss/train': 0.980607271194458} 08/31/2021 09:53:07 - INFO - __main__ - Step 114106: {'lr': 6.912587115603167e-05, 'samples': 21908352, 'steps': 114105, 'loss/train': 1.0393614768981934} 08/31/2021 09:53:09 - INFO - __main__ - Step 114107: {'lr': 6.912220780239806e-05, 'samples': 21908544, 'steps': 114106, 'loss/train': 0.4123166501522064} 08/31/2021 09:53:09 - INFO - __main__ - Step 114108: {'lr': 6.911854453026522e-05, 'samples': 21908736, 'steps': 114107, 'loss/train': 0.2707726061344147} 08/31/2021 09:53:09 - INFO - __main__ - Step 114109: {'lr': 6.911488133963475e-05, 'samples': 21908928, 'steps': 114108, 'loss/train': 0.9524365663528442} 08/31/2021 09:53:10 - INFO - __main__ - Step 114110: {'lr': 6.911121823050834e-05, 'samples': 21909120, 'steps': 114109, 'loss/train': 0.41555044054985046} 08/31/2021 09:53:10 - INFO - __main__ - Step 114111: {'lr': 6.91075552028877e-05, 'samples': 21909312, 'steps': 114110, 'loss/train': 0.024581698700785637} 08/31/2021 09:53:12 - INFO - __main__ - Step 114112: {'lr': 6.910389225677433e-05, 'samples': 21909504, 'steps': 114111, 'loss/train': 1.116251826286316} 08/31/2021 09:53:12 - INFO - __main__ - Step 114113: {'lr': 6.910022939216994e-05, 'samples': 21909696, 'steps': 114112, 'loss/train': 1.5464489459991455} 08/31/2021 09:53:13 - INFO - __main__ - Step 114114: {'lr': 6.90965666090762e-05, 'samples': 21909888, 'steps': 114113, 'loss/train': 1.0971283912658691} 08/31/2021 09:53:13 - INFO - __main__ - Step 114115: {'lr': 6.909290390749479e-05, 'samples': 21910080, 'steps': 114114, 'loss/train': 1.1214511394500732} 08/31/2021 09:53:13 - INFO - __main__ - Step 114116: {'lr': 6.908924128742727e-05, 'samples': 21910272, 'steps': 114115, 'loss/train': 1.3304070234298706} 08/31/2021 09:53:14 - INFO - __main__ - Step 114117: {'lr': 6.908557874887538e-05, 'samples': 21910464, 'steps': 114116, 'loss/train': 0.8148021697998047} 08/31/2021 09:53:15 - INFO - __main__ - Step 114118: {'lr': 6.908191629184074e-05, 'samples': 21910656, 'steps': 114117, 'loss/train': 1.4513391256332397} 08/31/2021 09:53:16 - INFO - __main__ - Step 114119: {'lr': 6.907825391632497e-05, 'samples': 21910848, 'steps': 114118, 'loss/train': 0.01812347210943699} 08/31/2021 09:53:16 - INFO - __main__ - Step 114120: {'lr': 6.907459162232976e-05, 'samples': 21911040, 'steps': 114119, 'loss/train': 0.01586872898042202} 08/31/2021 09:53:17 - INFO - __main__ - Step 114121: {'lr': 6.907092940985676e-05, 'samples': 21911232, 'steps': 114120, 'loss/train': 0.72472083568573} 08/31/2021 09:53:17 - INFO - __main__ - Step 114122: {'lr': 6.906726727890758e-05, 'samples': 21911424, 'steps': 114121, 'loss/train': 0.5386144518852234} 08/31/2021 09:53:17 - INFO - __main__ - Step 114123: {'lr': 6.906360522948393e-05, 'samples': 21911616, 'steps': 114122, 'loss/train': 0.04805243760347366} 08/31/2021 09:53:19 - INFO - __main__ - Step 114124: {'lr': 6.905994326158748e-05, 'samples': 21911808, 'steps': 114123, 'loss/train': 1.3682814836502075} 08/31/2021 09:53:19 - INFO - __main__ - Step 114125: {'lr': 6.905628137521977e-05, 'samples': 21912000, 'steps': 114124, 'loss/train': 1.6323925256729126} 08/31/2021 09:53:20 - INFO - __main__ - Step 114126: {'lr': 6.905261957038251e-05, 'samples': 21912192, 'steps': 114125, 'loss/train': 0.5524440407752991} 08/31/2021 09:53:20 - INFO - __main__ - Step 114127: {'lr': 6.904895784707732e-05, 'samples': 21912384, 'steps': 114126, 'loss/train': 0.9079856276512146} 08/31/2021 09:53:20 - INFO - __main__ - Step 114128: {'lr': 6.904529620530589e-05, 'samples': 21912576, 'steps': 114127, 'loss/train': 0.9664522409439087} 08/31/2021 09:53:22 - INFO - __main__ - Step 114129: {'lr': 6.904163464506985e-05, 'samples': 21912768, 'steps': 114128, 'loss/train': 0.6373620629310608} 08/31/2021 09:53:22 - INFO - __main__ - Step 114130: {'lr': 6.903797316637086e-05, 'samples': 21912960, 'steps': 114129, 'loss/train': 1.137603759765625} 08/31/2021 09:53:23 - INFO - __main__ - Step 114131: {'lr': 6.903431176921058e-05, 'samples': 21913152, 'steps': 114130, 'loss/train': 1.1332354545593262} 08/31/2021 09:53:23 - INFO - __main__ - Step 114132: {'lr': 6.903065045359064e-05, 'samples': 21913344, 'steps': 114131, 'loss/train': 0.9055166840553284} 08/31/2021 09:53:23 - INFO - __main__ - Step 114133: {'lr': 6.90269892195127e-05, 'samples': 21913536, 'steps': 114132, 'loss/train': 1.0684890747070312} 08/31/2021 09:53:25 - INFO - __main__ - Step 114134: {'lr': 6.902332806697839e-05, 'samples': 21913728, 'steps': 114133, 'loss/train': 1.2854340076446533} 08/31/2021 09:53:25 - INFO - __main__ - Step 114135: {'lr': 6.901966699598939e-05, 'samples': 21913920, 'steps': 114134, 'loss/train': 1.2965408563613892} 08/31/2021 09:53:26 - INFO - __main__ - Step 114136: {'lr': 6.901600600654734e-05, 'samples': 21914112, 'steps': 114135, 'loss/train': 1.2327475547790527} 08/31/2021 09:53:26 - INFO - __main__ - Step 114137: {'lr': 6.901234509865387e-05, 'samples': 21914304, 'steps': 114136, 'loss/train': 1.2769993543624878} 08/31/2021 09:53:26 - INFO - __main__ - Step 114138: {'lr': 6.900868427231074e-05, 'samples': 21914496, 'steps': 114137, 'loss/train': 1.3957984447479248} 08/31/2021 09:53:27 - INFO - __main__ - Step 114139: {'lr': 6.900502352751942e-05, 'samples': 21914688, 'steps': 114138, 'loss/train': 0.3192458748817444} 08/31/2021 09:53:29 - INFO - __main__ - Step 114140: {'lr': 6.900136286428163e-05, 'samples': 21914880, 'steps': 114139, 'loss/train': 1.5215893983840942} 08/31/2021 09:53:30 - INFO - __main__ - Step 114141: {'lr': 6.899770228259905e-05, 'samples': 21915072, 'steps': 114140, 'loss/train': 1.2320643663406372} 08/31/2021 09:53:30 - INFO - __main__ - Step 114142: {'lr': 6.899404178247328e-05, 'samples': 21915264, 'steps': 114141, 'loss/train': 0.5854710340499878} 08/31/2021 09:53:30 - INFO - __main__ - Step 114143: {'lr': 6.899038136390603e-05, 'samples': 21915456, 'steps': 114142, 'loss/train': 0.09709551930427551} 08/31/2021 09:53:31 - INFO - __main__ - Step 114144: {'lr': 6.898672102689893e-05, 'samples': 21915648, 'steps': 114143, 'loss/train': 1.3948440551757812} 08/31/2021 09:53:32 - INFO - __main__ - Step 114145: {'lr': 6.898306077145361e-05, 'samples': 21915840, 'steps': 114144, 'loss/train': 1.2313988208770752} 08/31/2021 09:53:33 - INFO - __main__ - Step 114146: {'lr': 6.897940059757171e-05, 'samples': 21916032, 'steps': 114145, 'loss/train': 2.3259294033050537} 08/31/2021 09:53:33 - INFO - __main__ - Step 114147: {'lr': 6.897574050525493e-05, 'samples': 21916224, 'steps': 114146, 'loss/train': 0.8415022492408752} 08/31/2021 09:53:33 - INFO - __main__ - Step 114148: {'lr': 6.897208049450488e-05, 'samples': 21916416, 'steps': 114147, 'loss/train': 1.2057985067367554} 08/31/2021 09:53:34 - INFO - __main__ - Step 114149: {'lr': 6.89684205653232e-05, 'samples': 21916608, 'steps': 114148, 'loss/train': 0.5739143490791321} 08/31/2021 09:53:35 - INFO - __main__ - Step 114150: {'lr': 6.896476071771157e-05, 'samples': 21916800, 'steps': 114149, 'loss/train': 1.2617346048355103} 08/31/2021 09:53:36 - INFO - __main__ - Step 114151: {'lr': 6.896110095167171e-05, 'samples': 21916992, 'steps': 114150, 'loss/train': 0.9414116740226746} 08/31/2021 09:53:36 - INFO - __main__ - Step 114152: {'lr': 6.89574412672051e-05, 'samples': 21917184, 'steps': 114151, 'loss/train': 1.2948782444000244} 08/31/2021 09:53:36 - INFO - __main__ - Step 114153: {'lr': 6.895378166431346e-05, 'samples': 21917376, 'steps': 114152, 'loss/train': 1.3386433124542236} 08/31/2021 09:53:37 - INFO - __main__ - Step 114154: {'lr': 6.895012214299846e-05, 'samples': 21917568, 'steps': 114153, 'loss/train': 1.2917015552520752} 08/31/2021 09:53:38 - INFO - __main__ - Step 114155: {'lr': 6.894646270326175e-05, 'samples': 21917760, 'steps': 114154, 'loss/train': 1.1265755891799927} 08/31/2021 09:53:39 - INFO - __main__ - Step 114156: {'lr': 6.894280334510498e-05, 'samples': 21917952, 'steps': 114155, 'loss/train': 1.2650752067565918} 08/31/2021 09:53:39 - INFO - __main__ - Step 114157: {'lr': 6.893914406852974e-05, 'samples': 21918144, 'steps': 114156, 'loss/train': 1.419956922531128} 08/31/2021 09:53:39 - INFO - __main__ - Step 114158: {'lr': 6.893548487353777e-05, 'samples': 21918336, 'steps': 114157, 'loss/train': 1.2802690267562866} 08/31/2021 09:53:40 - INFO - __main__ - Step 114159: {'lr': 6.893182576013065e-05, 'samples': 21918528, 'steps': 114158, 'loss/train': 1.0295435190200806} 08/31/2021 09:53:41 - INFO - __main__ - Step 114160: {'lr': 6.892816672831009e-05, 'samples': 21918720, 'steps': 114159, 'loss/train': 1.1904528141021729} 08/31/2021 09:53:42 - INFO - __main__ - Step 114161: {'lr': 6.892450777807769e-05, 'samples': 21918912, 'steps': 114160, 'loss/train': 1.1753603219985962} 08/31/2021 09:53:42 - INFO - __main__ - Step 114162: {'lr': 6.89208489094351e-05, 'samples': 21919104, 'steps': 114161, 'loss/train': 1.3813427686691284} 08/31/2021 09:53:42 - INFO - __main__ - Step 114163: {'lr': 6.891719012238399e-05, 'samples': 21919296, 'steps': 114162, 'loss/train': 1.0920392274856567} 08/31/2021 09:53:43 - INFO - __main__ - Step 114164: {'lr': 6.891353141692608e-05, 'samples': 21919488, 'steps': 114163, 'loss/train': 1.4150736331939697} 08/31/2021 09:53:43 - INFO - __main__ - Step 114165: {'lr': 6.890987279306285e-05, 'samples': 21919680, 'steps': 114164, 'loss/train': 0.8041816353797913} 08/31/2021 09:53:45 - INFO - __main__ - Step 114166: {'lr': 6.890621425079604e-05, 'samples': 21919872, 'steps': 114165, 'loss/train': 1.346299409866333} 08/31/2021 09:53:45 - INFO - __main__ - Step 114167: {'lr': 6.89025557901273e-05, 'samples': 21920064, 'steps': 114166, 'loss/train': 1.481519341468811} 08/31/2021 09:53:45 - INFO - __main__ - Step 114168: {'lr': 6.889889741105828e-05, 'samples': 21920256, 'steps': 114167, 'loss/train': 0.7840514779090881} 08/31/2021 09:53:46 - INFO - __main__ - Step 114169: {'lr': 6.889523911359063e-05, 'samples': 21920448, 'steps': 114168, 'loss/train': 0.5559191107749939} 08/31/2021 09:53:46 - INFO - __main__ - Step 114170: {'lr': 6.889158089772599e-05, 'samples': 21920640, 'steps': 114169, 'loss/train': 1.0377789735794067} 08/31/2021 09:53:48 - INFO - __main__ - Step 114171: {'lr': 6.888792276346597e-05, 'samples': 21920832, 'steps': 114170, 'loss/train': 1.1957701444625854} 08/31/2021 09:53:48 - INFO - __main__ - Step 114172: {'lr': 6.88842647108123e-05, 'samples': 21921024, 'steps': 114171, 'loss/train': 0.8081629872322083} 08/31/2021 09:53:49 - INFO - __main__ - Step 114173: {'lr': 6.888060673976656e-05, 'samples': 21921216, 'steps': 114172, 'loss/train': 0.7202220559120178} 08/31/2021 09:53:49 - INFO - __main__ - Step 114174: {'lr': 6.887694885033044e-05, 'samples': 21921408, 'steps': 114173, 'loss/train': 1.0660595893859863} 08/31/2021 09:53:49 - INFO - __main__ - Step 114175: {'lr': 6.887329104250556e-05, 'samples': 21921600, 'steps': 114174, 'loss/train': 1.1027612686157227} 08/31/2021 09:53:51 - INFO - __main__ - Step 114176: {'lr': 6.88696333162936e-05, 'samples': 21921792, 'steps': 114175, 'loss/train': 0.9705306887626648} 08/31/2021 09:53:51 - INFO - __main__ - Step 114177: {'lr': 6.886597567169617e-05, 'samples': 21921984, 'steps': 114176, 'loss/train': 1.1334221363067627} 08/31/2021 09:53:52 - INFO - __main__ - Step 114178: {'lr': 6.886231810871502e-05, 'samples': 21922176, 'steps': 114177, 'loss/train': 1.3018176555633545} 08/31/2021 09:53:52 - INFO - __main__ - Step 114179: {'lr': 6.885866062735163e-05, 'samples': 21922368, 'steps': 114178, 'loss/train': 0.9204819798469543} 08/31/2021 09:53:52 - INFO - __main__ - Step 114180: {'lr': 6.885500322760773e-05, 'samples': 21922560, 'steps': 114179, 'loss/train': 0.8855347037315369} 08/31/2021 09:53:54 - INFO - __main__ - Step 114181: {'lr': 6.885134590948497e-05, 'samples': 21922752, 'steps': 114180, 'loss/train': 0.9602956771850586} 08/31/2021 09:53:54 - INFO - __main__ - Step 114182: {'lr': 6.8847688672985e-05, 'samples': 21922944, 'steps': 114181, 'loss/train': 1.3155730962753296} 08/31/2021 09:53:55 - INFO - __main__ - Step 114183: {'lr': 6.884403151810947e-05, 'samples': 21923136, 'steps': 114182, 'loss/train': 1.1702409982681274} 08/31/2021 09:53:55 - INFO - __main__ - Step 114184: {'lr': 6.884037444486002e-05, 'samples': 21923328, 'steps': 114183, 'loss/train': 0.5592535734176636} 08/31/2021 09:53:55 - INFO - __main__ - Step 114185: {'lr': 6.883671745323833e-05, 'samples': 21923520, 'steps': 114184, 'loss/train': 1.5752941370010376} 08/31/2021 09:53:56 - INFO - __main__ - Step 114186: {'lr': 6.883306054324598e-05, 'samples': 21923712, 'steps': 114185, 'loss/train': 0.5871254205703735} 08/31/2021 09:53:57 - INFO - __main__ - Step 114187: {'lr': 6.88294037148847e-05, 'samples': 21923904, 'steps': 114186, 'loss/train': 1.1203181743621826} 08/31/2021 09:53:58 - INFO - __main__ - Step 114188: {'lr': 6.882574696815605e-05, 'samples': 21924096, 'steps': 114187, 'loss/train': 1.248541235923767} 08/31/2021 09:53:58 - INFO - __main__ - Step 114189: {'lr': 6.882209030306181e-05, 'samples': 21924288, 'steps': 114188, 'loss/train': 1.1646528244018555} 08/31/2021 09:53:58 - INFO - __main__ - Step 114190: {'lr': 6.881843371960348e-05, 'samples': 21924480, 'steps': 114189, 'loss/train': 0.6160008311271667} 08/31/2021 09:53:59 - INFO - __main__ - Step 114191: {'lr': 6.881477721778276e-05, 'samples': 21924672, 'steps': 114190, 'loss/train': 1.124754786491394} 08/31/2021 09:54:01 - INFO - __main__ - Step 114192: {'lr': 6.88111207976013e-05, 'samples': 21924864, 'steps': 114191, 'loss/train': 1.5794894695281982} 08/31/2021 09:54:01 - INFO - __main__ - Step 114193: {'lr': 6.880746445906075e-05, 'samples': 21925056, 'steps': 114192, 'loss/train': 1.2500288486480713} 08/31/2021 09:54:02 - INFO - __main__ - Step 114194: {'lr': 6.880380820216279e-05, 'samples': 21925248, 'steps': 114193, 'loss/train': 1.4666165113449097} 08/31/2021 09:54:02 - INFO - __main__ - Step 114195: {'lr': 6.880015202690901e-05, 'samples': 21925440, 'steps': 114194, 'loss/train': 1.5155326128005981} 08/31/2021 09:54:02 - INFO - __main__ - Step 114196: {'lr': 6.87964959333011e-05, 'samples': 21925632, 'steps': 114195, 'loss/train': 0.787857711315155} 08/31/2021 09:54:04 - INFO - __main__ - Step 114197: {'lr': 6.879283992134066e-05, 'samples': 21925824, 'steps': 114196, 'loss/train': 0.46269118785858154} 08/31/2021 09:54:04 - INFO - __main__ - Step 114198: {'lr': 6.87891839910294e-05, 'samples': 21926016, 'steps': 114197, 'loss/train': 0.6305480003356934} 08/31/2021 09:54:05 - INFO - __main__ - Step 114199: {'lr': 6.878552814236894e-05, 'samples': 21926208, 'steps': 114198, 'loss/train': 0.805724024772644} 08/31/2021 09:54:05 - INFO - __main__ - Step 114200: {'lr': 6.878187237536099e-05, 'samples': 21926400, 'steps': 114199, 'loss/train': 0.7561425566673279} 08/31/2021 09:54:05 - INFO - __main__ - Step 114201: {'lr': 6.877821669000705e-05, 'samples': 21926592, 'steps': 114200, 'loss/train': 1.1848618984222412} 08/31/2021 09:54:07 - INFO - __main__ - Step 114202: {'lr': 6.877456108630886e-05, 'samples': 21926784, 'steps': 114201, 'loss/train': 0.9998687505722046} 08/31/2021 09:54:08 - INFO - __main__ - Step 114203: {'lr': 6.877090556426807e-05, 'samples': 21926976, 'steps': 114202, 'loss/train': 1.685283899307251} 08/31/2021 09:54:08 - INFO - __main__ - Step 114204: {'lr': 6.87672501238863e-05, 'samples': 21927168, 'steps': 114203, 'loss/train': 0.4741455614566803} 08/31/2021 09:54:08 - INFO - __main__ - Step 114205: {'lr': 6.87635947651652e-05, 'samples': 21927360, 'steps': 114204, 'loss/train': 1.1309771537780762} 08/31/2021 09:54:09 - INFO - __main__ - Step 114206: {'lr': 6.875993948810643e-05, 'samples': 21927552, 'steps': 114205, 'loss/train': 1.0448293685913086} 08/31/2021 09:54:10 - INFO - __main__ - Step 114207: {'lr': 6.875628429271166e-05, 'samples': 21927744, 'steps': 114206, 'loss/train': 0.03699200972914696} 08/31/2021 09:54:11 - INFO - __main__ - Step 114208: {'lr': 6.875262917898248e-05, 'samples': 21927936, 'steps': 114207, 'loss/train': 1.0815465450286865} 08/31/2021 09:54:11 - INFO - __main__ - Step 114209: {'lr': 6.874897414692057e-05, 'samples': 21928128, 'steps': 114208, 'loss/train': 0.6382499933242798} 08/31/2021 09:54:12 - INFO - __main__ - Step 114210: {'lr': 6.87453191965276e-05, 'samples': 21928320, 'steps': 114209, 'loss/train': 0.016895856708288193} 08/31/2021 09:54:12 - INFO - __main__ - Step 114211: {'lr': 6.874166432780526e-05, 'samples': 21928512, 'steps': 114210, 'loss/train': 0.47448089718818665} 08/31/2021 09:54:12 - INFO - __main__ - Step 114212: {'lr': 6.873800954075505e-05, 'samples': 21928704, 'steps': 114211, 'loss/train': 0.7565836310386658} 08/31/2021 09:54:14 - INFO - __main__ - Step 114213: {'lr': 6.873435483537869e-05, 'samples': 21928896, 'steps': 114212, 'loss/train': 1.7015115022659302} 08/31/2021 09:54:14 - INFO - __main__ - Step 114214: {'lr': 6.873070021167783e-05, 'samples': 21929088, 'steps': 114213, 'loss/train': 1.0515413284301758} 08/31/2021 09:54:15 - INFO - __main__ - Step 114215: {'lr': 6.872704566965413e-05, 'samples': 21929280, 'steps': 114214, 'loss/train': 1.2117712497711182} 08/31/2021 09:54:15 - INFO - __main__ - Step 114216: {'lr': 6.872339120930921e-05, 'samples': 21929472, 'steps': 114215, 'loss/train': 1.317448616027832} 08/31/2021 09:54:15 - INFO - __main__ - Step 114217: {'lr': 6.871973683064475e-05, 'samples': 21929664, 'steps': 114216, 'loss/train': 1.4880220890045166} 08/31/2021 09:54:17 - INFO - __main__ - Step 114218: {'lr': 6.871608253366238e-05, 'samples': 21929856, 'steps': 114217, 'loss/train': 1.3920859098434448} 08/31/2021 09:54:18 - INFO - __main__ - Step 114219: {'lr': 6.871242831836374e-05, 'samples': 21930048, 'steps': 114218, 'loss/train': 1.7354834079742432} 08/31/2021 09:54:18 - INFO - __main__ - Step 114220: {'lr': 6.870877418475047e-05, 'samples': 21930240, 'steps': 114219, 'loss/train': 0.728035032749176} 08/31/2021 09:54:19 - INFO - __main__ - Step 114221: {'lr': 6.870512013282423e-05, 'samples': 21930432, 'steps': 114220, 'loss/train': 0.7662751078605652} 08/31/2021 09:54:19 - INFO - __main__ - Step 114222: {'lr': 6.870146616258677e-05, 'samples': 21930624, 'steps': 114221, 'loss/train': 1.1055166721343994} 08/31/2021 09:54:19 - INFO - __main__ - Step 114223: {'lr': 6.869781227403954e-05, 'samples': 21930816, 'steps': 114222, 'loss/train': 0.8785837292671204} 08/31/2021 09:54:20 - INFO - __main__ - Step 114224: {'lr': 6.869415846718427e-05, 'samples': 21931008, 'steps': 114223, 'loss/train': 1.436254858970642} 08/31/2021 09:54:22 - INFO - __main__ - Step 114225: {'lr': 6.869050474202263e-05, 'samples': 21931200, 'steps': 114224, 'loss/train': 0.5883489847183228} 08/31/2021 09:54:22 - INFO - __main__ - Step 114226: {'lr': 6.868685109855624e-05, 'samples': 21931392, 'steps': 114225, 'loss/train': 1.0205423831939697} 08/31/2021 09:54:22 - INFO - __main__ - Step 114227: {'lr': 6.868319753678675e-05, 'samples': 21931584, 'steps': 114226, 'loss/train': 1.3057703971862793} 08/31/2021 09:54:23 - INFO - __main__ - Step 114228: {'lr': 6.867954405671581e-05, 'samples': 21931776, 'steps': 114227, 'loss/train': 0.06990653276443481} 08/31/2021 09:54:23 - INFO - __main__ - Step 114229: {'lr': 6.867589065834509e-05, 'samples': 21931968, 'steps': 114228, 'loss/train': 1.0182276964187622} 08/31/2021 09:54:25 - INFO - __main__ - Step 114230: {'lr': 6.867223734167622e-05, 'samples': 21932160, 'steps': 114229, 'loss/train': 0.8680480122566223} 08/31/2021 09:54:25 - INFO - __main__ - Step 114231: {'lr': 6.866858410671081e-05, 'samples': 21932352, 'steps': 114230, 'loss/train': 1.0548659563064575} 08/31/2021 09:54:26 - INFO - __main__ - Step 114232: {'lr': 6.866493095345055e-05, 'samples': 21932544, 'steps': 114231, 'loss/train': 1.7700936794281006} 08/31/2021 09:54:26 - INFO - __main__ - Step 114233: {'lr': 6.866127788189717e-05, 'samples': 21932736, 'steps': 114232, 'loss/train': 0.7971440553665161} 08/31/2021 09:54:26 - INFO - __main__ - Step 114234: {'lr': 6.865762489205213e-05, 'samples': 21932928, 'steps': 114233, 'loss/train': 1.2909045219421387} 08/31/2021 09:54:28 - INFO - __main__ - Step 114235: {'lr': 6.865397198391715e-05, 'samples': 21933120, 'steps': 114234, 'loss/train': 1.1101943254470825} 08/31/2021 09:54:28 - INFO - __main__ - Step 114236: {'lr': 6.865031915749392e-05, 'samples': 21933312, 'steps': 114235, 'loss/train': 0.7928096652030945} 08/31/2021 09:54:29 - INFO - __main__ - Step 114237: {'lr': 6.864666641278405e-05, 'samples': 21933504, 'steps': 114236, 'loss/train': 1.6594126224517822} 08/31/2021 09:54:29 - INFO - __main__ - Step 114238: {'lr': 6.864301374978918e-05, 'samples': 21933696, 'steps': 114237, 'loss/train': 0.8932767510414124} 08/31/2021 09:54:29 - INFO - __main__ - Step 114239: {'lr': 6.8639361168511e-05, 'samples': 21933888, 'steps': 114238, 'loss/train': 1.643197774887085} 08/31/2021 09:54:31 - INFO - __main__ - Step 114240: {'lr': 6.863570866895109e-05, 'samples': 21934080, 'steps': 114239, 'loss/train': 0.6486164331436157} 08/31/2021 09:54:31 - INFO - __main__ - Step 114241: {'lr': 6.863205625111113e-05, 'samples': 21934272, 'steps': 114240, 'loss/train': 0.5567889213562012} 08/31/2021 09:54:32 - INFO - __main__ - Step 114242: {'lr': 6.862840391499278e-05, 'samples': 21934464, 'steps': 114241, 'loss/train': 0.881855845451355} 08/31/2021 09:54:32 - INFO - __main__ - Step 114243: {'lr': 6.862475166059767e-05, 'samples': 21934656, 'steps': 114242, 'loss/train': 1.1715391874313354} 08/31/2021 09:54:32 - INFO - __main__ - Step 114244: {'lr': 6.862109948792746e-05, 'samples': 21934848, 'steps': 114243, 'loss/train': 0.02710900828242302} 08/31/2021 09:54:34 - INFO - __main__ - Step 114245: {'lr': 6.861744739698386e-05, 'samples': 21935040, 'steps': 114244, 'loss/train': 1.630683422088623} 08/31/2021 09:54:34 - INFO - __main__ - Step 114246: {'lr': 6.861379538776835e-05, 'samples': 21935232, 'steps': 114245, 'loss/train': 0.3649947941303253} 08/31/2021 09:54:35 - INFO - __main__ - Step 114247: {'lr': 6.861014346028268e-05, 'samples': 21935424, 'steps': 114246, 'loss/train': 0.7881366014480591} 08/31/2021 09:54:35 - INFO - __main__ - Step 114248: {'lr': 6.860649161452848e-05, 'samples': 21935616, 'steps': 114247, 'loss/train': 1.698613166809082} 08/31/2021 09:54:35 - INFO - __main__ - Step 114249: {'lr': 6.860283985050738e-05, 'samples': 21935808, 'steps': 114248, 'loss/train': 1.6157689094543457} 08/31/2021 09:54:38 - INFO - __main__ - Step 114250: {'lr': 6.859918816822103e-05, 'samples': 21936000, 'steps': 114249, 'loss/train': 0.10434438288211823} 08/31/2021 09:54:38 - INFO - __main__ - Step 114251: {'lr': 6.859553656767112e-05, 'samples': 21936192, 'steps': 114250, 'loss/train': 0.5546088814735413} 08/31/2021 09:54:39 - INFO - __main__ - Step 114252: {'lr': 6.859188504885924e-05, 'samples': 21936384, 'steps': 114251, 'loss/train': 1.4935623407363892} 08/31/2021 09:54:39 - INFO - __main__ - Step 114253: {'lr': 6.858823361178706e-05, 'samples': 21936576, 'steps': 114252, 'loss/train': 1.4856271743774414} 08/31/2021 09:54:39 - INFO - __main__ - Step 114254: {'lr': 6.858458225645622e-05, 'samples': 21936768, 'steps': 114253, 'loss/train': 1.3307844400405884} 08/31/2021 09:54:40 - INFO - __main__ - Step 114255: {'lr': 6.858093098286839e-05, 'samples': 21936960, 'steps': 114254, 'loss/train': 5.754254341125488} 08/31/2021 09:54:40 - INFO - __main__ - Step 114256: {'lr': 6.857727979102518e-05, 'samples': 21937152, 'steps': 114255, 'loss/train': 5.697419166564941} 08/31/2021 09:54:42 - INFO - __main__ - Step 114257: {'lr': 6.857362868092823e-05, 'samples': 21937344, 'steps': 114256, 'loss/train': 1.0333797931671143} 08/31/2021 09:54:42 - INFO - __main__ - Step 114258: {'lr': 6.856997765257921e-05, 'samples': 21937536, 'steps': 114257, 'loss/train': 1.471329927444458} 08/31/2021 09:54:43 - INFO - __main__ - Step 114259: {'lr': 6.856632670597988e-05, 'samples': 21937728, 'steps': 114258, 'loss/train': 1.0147085189819336} 08/31/2021 09:54:43 - INFO - __main__ - Step 114260: {'lr': 6.856267584113163e-05, 'samples': 21937920, 'steps': 114259, 'loss/train': 0.9334803819656372} 08/31/2021 09:54:43 - INFO - __main__ - Step 114261: {'lr': 6.855902505803627e-05, 'samples': 21938112, 'steps': 114260, 'loss/train': 0.9564447999000549} 08/31/2021 09:54:45 - INFO - __main__ - Step 114262: {'lr': 6.855537435669539e-05, 'samples': 21938304, 'steps': 114261, 'loss/train': 1.0010321140289307} 08/31/2021 09:54:45 - INFO - __main__ - Step 114263: {'lr': 6.855172373711066e-05, 'samples': 21938496, 'steps': 114262, 'loss/train': 1.2793711423873901} 08/31/2021 09:54:46 - INFO - __main__ - Step 114264: {'lr': 6.854807319928375e-05, 'samples': 21938688, 'steps': 114263, 'loss/train': 2.208876848220825} 08/31/2021 09:54:46 - INFO - __main__ - Step 114265: {'lr': 6.854442274321626e-05, 'samples': 21938880, 'steps': 114264, 'loss/train': 0.8256897330284119} 08/31/2021 09:54:46 - INFO - __main__ - Step 114266: {'lr': 6.854077236890985e-05, 'samples': 21939072, 'steps': 114265, 'loss/train': 0.7255913615226746} 08/31/2021 09:54:47 - INFO - __main__ - Step 114267: {'lr': 6.853712207636617e-05, 'samples': 21939264, 'steps': 114266, 'loss/train': 1.4088079929351807} 08/31/2021 09:54:48 - INFO - __main__ - Step 114268: {'lr': 6.853347186558686e-05, 'samples': 21939456, 'steps': 114267, 'loss/train': 1.591685175895691} 08/31/2021 09:54:49 - INFO - __main__ - Step 114269: {'lr': 6.852982173657357e-05, 'samples': 21939648, 'steps': 114268, 'loss/train': 1.5229856967926025} 08/31/2021 09:54:49 - INFO - __main__ - Step 114270: {'lr': 6.852617168932796e-05, 'samples': 21939840, 'steps': 114269, 'loss/train': 1.1343547105789185} 08/31/2021 09:54:49 - INFO - __main__ - Step 114271: {'lr': 6.852252172385165e-05, 'samples': 21940032, 'steps': 114270, 'loss/train': 0.1256953924894333} 08/31/2021 09:54:50 - INFO - __main__ - Step 114272: {'lr': 6.851887184014635e-05, 'samples': 21940224, 'steps': 114271, 'loss/train': 1.133488655090332} 08/31/2021 09:54:51 - INFO - __main__ - Step 114273: {'lr': 6.851522203821358e-05, 'samples': 21940416, 'steps': 114272, 'loss/train': 1.0235354900360107} 08/31/2021 09:54:52 - INFO - __main__ - Step 114274: {'lr': 6.851157231805504e-05, 'samples': 21940608, 'steps': 114273, 'loss/train': 0.8344688415527344} 08/31/2021 09:54:52 - INFO - __main__ - Step 114275: {'lr': 6.85079226796724e-05, 'samples': 21940800, 'steps': 114274, 'loss/train': 1.0600982904434204} 08/31/2021 09:54:52 - INFO - __main__ - Step 114276: {'lr': 6.850427312306729e-05, 'samples': 21940992, 'steps': 114275, 'loss/train': 1.2001270055770874} 08/31/2021 09:54:53 - INFO - __main__ - Step 114277: {'lr': 6.850062364824136e-05, 'samples': 21941184, 'steps': 114276, 'loss/train': 0.9127978086471558} 08/31/2021 09:54:54 - INFO - __main__ - Step 114278: {'lr': 6.849697425519621e-05, 'samples': 21941376, 'steps': 114277, 'loss/train': 1.1072529554367065} 08/31/2021 09:54:55 - INFO - __main__ - Step 114279: {'lr': 6.849332494393356e-05, 'samples': 21941568, 'steps': 114278, 'loss/train': 1.4968516826629639} 08/31/2021 09:54:55 - INFO - __main__ - Step 114280: {'lr': 6.848967571445503e-05, 'samples': 21941760, 'steps': 114279, 'loss/train': 1.3252946138381958} 08/31/2021 09:54:55 - INFO - __main__ - Step 114281: {'lr': 6.84860265667622e-05, 'samples': 21941952, 'steps': 114280, 'loss/train': 1.2966381311416626} 08/31/2021 09:54:56 - INFO - __main__ - Step 114282: {'lr': 6.848237750085681e-05, 'samples': 21942144, 'steps': 114281, 'loss/train': 1.2484867572784424} 08/31/2021 09:54:57 - INFO - __main__ - Step 114283: {'lr': 6.847872851674044e-05, 'samples': 21942336, 'steps': 114282, 'loss/train': 0.6428256630897522} 08/31/2021 09:54:58 - INFO - __main__ - Step 114284: {'lr': 6.847507961441474e-05, 'samples': 21942528, 'steps': 114283, 'loss/train': 0.03397730737924576} 08/31/2021 09:54:58 - INFO - __main__ - Step 114285: {'lr': 6.847143079388146e-05, 'samples': 21942720, 'steps': 114284, 'loss/train': 0.8494165539741516} 08/31/2021 09:54:58 - INFO - __main__ - Step 114286: {'lr': 6.846778205514209e-05, 'samples': 21942912, 'steps': 114285, 'loss/train': 1.0422124862670898} 08/31/2021 09:54:59 - INFO - __main__ - Step 114287: {'lr': 6.846413339819832e-05, 'samples': 21943104, 'steps': 114286, 'loss/train': 1.5267857313156128} 08/31/2021 09:55:01 - INFO - __main__ - Step 114288: {'lr': 6.846048482305181e-05, 'samples': 21943296, 'steps': 114287, 'loss/train': 0.6856160163879395} 08/31/2021 09:55:01 - INFO - __main__ - Step 114289: {'lr': 6.84568363297042e-05, 'samples': 21943488, 'steps': 114288, 'loss/train': 0.6948447227478027} 08/31/2021 09:55:02 - INFO - __main__ - Step 114290: {'lr': 6.845318791815717e-05, 'samples': 21943680, 'steps': 114289, 'loss/train': 1.0125454664230347} 08/31/2021 09:55:02 - INFO - __main__ - Step 114291: {'lr': 6.844953958841229e-05, 'samples': 21943872, 'steps': 114290, 'loss/train': 1.5437970161437988} 08/31/2021 09:55:02 - INFO - __main__ - Step 114292: {'lr': 6.844589134047127e-05, 'samples': 21944064, 'steps': 114291, 'loss/train': 1.2717788219451904} 08/31/2021 09:55:03 - INFO - __main__ - Step 114293: {'lr': 6.844224317433572e-05, 'samples': 21944256, 'steps': 114292, 'loss/train': 1.231347680091858} 08/31/2021 09:55:04 - INFO - __main__ - Step 114294: {'lr': 6.84385950900073e-05, 'samples': 21944448, 'steps': 114293, 'loss/train': 0.05520118772983551} 08/31/2021 09:55:05 - INFO - __main__ - Step 114295: {'lr': 6.843494708748765e-05, 'samples': 21944640, 'steps': 114294, 'loss/train': 0.027897153049707413} 08/31/2021 09:55:05 - INFO - __main__ - Step 114296: {'lr': 6.84312991667784e-05, 'samples': 21944832, 'steps': 114295, 'loss/train': 1.3851531744003296} 08/31/2021 09:55:06 - INFO - __main__ - Step 114297: {'lr': 6.84276513278812e-05, 'samples': 21945024, 'steps': 114296, 'loss/train': 0.614320695400238} 08/31/2021 09:55:06 - INFO - __main__ - Step 114298: {'lr': 6.842400357079773e-05, 'samples': 21945216, 'steps': 114297, 'loss/train': 0.22588896751403809} 08/31/2021 09:55:07 - INFO - __main__ - Step 114299: {'lr': 6.842035589552964e-05, 'samples': 21945408, 'steps': 114298, 'loss/train': 0.5292697548866272} 08/31/2021 09:55:08 - INFO - __main__ - Step 114300: {'lr': 6.841670830207846e-05, 'samples': 21945600, 'steps': 114299, 'loss/train': 0.9819614291191101} 08/31/2021 09:55:08 - INFO - __main__ - Step 114301: {'lr': 6.841306079044596e-05, 'samples': 21945792, 'steps': 114300, 'loss/train': 1.4839853048324585} 08/31/2021 09:55:09 - INFO - __main__ - Step 114302: {'lr': 6.840941336063369e-05, 'samples': 21945984, 'steps': 114301, 'loss/train': 0.8208417296409607} 08/31/2021 09:55:09 - INFO - __main__ - Step 114303: {'lr': 6.840576601264334e-05, 'samples': 21946176, 'steps': 114302, 'loss/train': 3.6827614307403564} 08/31/2021 09:55:09 - INFO - __main__ - Step 114304: {'lr': 6.840211874647656e-05, 'samples': 21946368, 'steps': 114303, 'loss/train': 1.1947104930877686} 08/31/2021 09:55:12 - INFO - __main__ - Step 114305: {'lr': 6.839847156213497e-05, 'samples': 21946560, 'steps': 114304, 'loss/train': 0.9817231893539429} 08/31/2021 09:55:12 - INFO - __main__ - Step 114306: {'lr': 6.839482445962023e-05, 'samples': 21946752, 'steps': 114305, 'loss/train': 1.0139398574829102} 08/31/2021 09:55:13 - INFO - __main__ - Step 114307: {'lr': 6.8391177438934e-05, 'samples': 21946944, 'steps': 114306, 'loss/train': 1.510989785194397} 08/31/2021 09:55:13 - INFO - __main__ - Step 114308: {'lr': 6.838753050007788e-05, 'samples': 21947136, 'steps': 114307, 'loss/train': 0.019745098426938057} 08/31/2021 09:55:13 - INFO - __main__ - Step 114309: {'lr': 6.838388364305353e-05, 'samples': 21947328, 'steps': 114308, 'loss/train': 1.1380326747894287} 08/31/2021 09:55:14 - INFO - __main__ - Step 114310: {'lr': 6.838023686786262e-05, 'samples': 21947520, 'steps': 114309, 'loss/train': 0.8373222947120667} 08/31/2021 09:55:15 - INFO - __main__ - Step 114311: {'lr': 6.837659017450676e-05, 'samples': 21947712, 'steps': 114310, 'loss/train': 1.304375171661377} 08/31/2021 09:55:16 - INFO - __main__ - Step 114312: {'lr': 6.83729435629877e-05, 'samples': 21947904, 'steps': 114311, 'loss/train': 0.7686640620231628} 08/31/2021 09:55:16 - INFO - __main__ - Step 114313: {'lr': 6.836929703330688e-05, 'samples': 21948096, 'steps': 114312, 'loss/train': 0.32429039478302} 08/31/2021 09:55:16 - INFO - __main__ - Step 114314: {'lr': 6.836565058546609e-05, 'samples': 21948288, 'steps': 114313, 'loss/train': 0.5947821140289307} 08/31/2021 09:55:17 - INFO - __main__ - Step 114315: {'lr': 6.836200421946692e-05, 'samples': 21948480, 'steps': 114314, 'loss/train': 0.03017568401992321} 08/31/2021 09:55:17 - INFO - __main__ - Step 114316: {'lr': 6.8358357935311e-05, 'samples': 21948672, 'steps': 114315, 'loss/train': 1.0107309818267822} 08/31/2021 09:55:19 - INFO - __main__ - Step 114317: {'lr': 6.835471173300004e-05, 'samples': 21948864, 'steps': 114316, 'loss/train': 1.1655834913253784} 08/31/2021 09:55:19 - INFO - __main__ - Step 114318: {'lr': 6.835106561253562e-05, 'samples': 21949056, 'steps': 114317, 'loss/train': 0.6817492246627808} 08/31/2021 09:55:19 - INFO - __main__ - Step 114319: {'lr': 6.834741957391943e-05, 'samples': 21949248, 'steps': 114318, 'loss/train': 1.3535159826278687} 08/31/2021 09:55:20 - INFO - __main__ - Step 114320: {'lr': 6.834377361715308e-05, 'samples': 21949440, 'steps': 114319, 'loss/train': 1.1802566051483154} 08/31/2021 09:55:20 - INFO - __main__ - Step 114321: {'lr': 6.834012774223821e-05, 'samples': 21949632, 'steps': 114320, 'loss/train': 1.1491661071777344} 08/31/2021 09:55:22 - INFO - __main__ - Step 114322: {'lr': 6.83364819491765e-05, 'samples': 21949824, 'steps': 114321, 'loss/train': 1.4404417276382446} 08/31/2021 09:55:22 - INFO - __main__ - Step 114323: {'lr': 6.833283623796955e-05, 'samples': 21950016, 'steps': 114322, 'loss/train': 1.5213440656661987} 08/31/2021 09:55:23 - INFO - __main__ - Step 114324: {'lr': 6.8329190608619e-05, 'samples': 21950208, 'steps': 114323, 'loss/train': 0.8572080135345459} 08/31/2021 09:55:23 - INFO - __main__ - Step 114325: {'lr': 6.832554506112657e-05, 'samples': 21950400, 'steps': 114324, 'loss/train': 1.352293848991394} 08/31/2021 09:55:23 - INFO - __main__ - Step 114326: {'lr': 6.832189959549387e-05, 'samples': 21950592, 'steps': 114325, 'loss/train': 1.5527392625808716} 08/31/2021 09:55:24 - INFO - __main__ - Step 114327: {'lr': 6.831825421172247e-05, 'samples': 21950784, 'steps': 114326, 'loss/train': 1.172624945640564} 08/31/2021 09:55:26 - INFO - __main__ - Step 114328: {'lr': 6.831460890981403e-05, 'samples': 21950976, 'steps': 114327, 'loss/train': 0.5873245596885681} 08/31/2021 09:55:26 - INFO - __main__ - Step 114329: {'lr': 6.831096368977028e-05, 'samples': 21951168, 'steps': 114328, 'loss/train': 1.4460060596466064} 08/31/2021 09:55:27 - INFO - __main__ - Step 114330: {'lr': 6.830731855159275e-05, 'samples': 21951360, 'steps': 114329, 'loss/train': 1.3412071466445923} 08/31/2021 09:55:27 - INFO - __main__ - Step 114331: {'lr': 6.830367349528316e-05, 'samples': 21951552, 'steps': 114330, 'loss/train': 1.2273340225219727} 08/31/2021 09:55:27 - INFO - __main__ - Step 114332: {'lr': 6.830002852084314e-05, 'samples': 21951744, 'steps': 114331, 'loss/train': 0.5311270952224731} 08/31/2021 09:55:28 - INFO - __main__ - Step 114333: {'lr': 6.829638362827431e-05, 'samples': 21951936, 'steps': 114332, 'loss/train': 0.8429160714149475} 08/31/2021 09:55:29 - INFO - __main__ - Step 114334: {'lr': 6.829273881757833e-05, 'samples': 21952128, 'steps': 114333, 'loss/train': 0.7772935032844543} 08/31/2021 09:55:30 - INFO - __main__ - Step 114335: {'lr': 6.828909408875683e-05, 'samples': 21952320, 'steps': 114334, 'loss/train': 1.351718544960022} 08/31/2021 09:55:30 - INFO - __main__ - Step 114336: {'lr': 6.828544944181147e-05, 'samples': 21952512, 'steps': 114335, 'loss/train': 1.0040435791015625} 08/31/2021 09:55:30 - INFO - __main__ - Step 114337: {'lr': 6.828180487674387e-05, 'samples': 21952704, 'steps': 114336, 'loss/train': 2.0571534633636475} 08/31/2021 09:55:31 - INFO - __main__ - Step 114338: {'lr': 6.827816039355572e-05, 'samples': 21952896, 'steps': 114337, 'loss/train': 0.03131450340151787} 08/31/2021 09:55:32 - INFO - __main__ - Step 114339: {'lr': 6.827451599224867e-05, 'samples': 21953088, 'steps': 114338, 'loss/train': 1.287876844406128} 08/31/2021 09:55:33 - INFO - __main__ - Step 114340: {'lr': 6.827087167282425e-05, 'samples': 21953280, 'steps': 114339, 'loss/train': 0.4227127730846405} 08/31/2021 09:55:33 - INFO - __main__ - Step 114341: {'lr': 6.826722743528419e-05, 'samples': 21953472, 'steps': 114340, 'loss/train': 1.0651928186416626} 08/31/2021 09:55:33 - INFO - __main__ - Step 114342: {'lr': 6.826358327963009e-05, 'samples': 21953664, 'steps': 114341, 'loss/train': 0.24633349478244781} 08/31/2021 09:55:34 - INFO - __main__ - Step 114343: {'lr': 6.825993920586359e-05, 'samples': 21953856, 'steps': 114342, 'loss/train': 1.8841289281845093} 08/31/2021 09:55:35 - INFO - __main__ - Step 114344: {'lr': 6.825629521398641e-05, 'samples': 21954048, 'steps': 114343, 'loss/train': 1.0053608417510986} 08/31/2021 09:55:36 - INFO - __main__ - Step 114345: {'lr': 6.825265130400011e-05, 'samples': 21954240, 'steps': 114344, 'loss/train': 1.3700166940689087} 08/31/2021 09:55:36 - INFO - __main__ - Step 114346: {'lr': 6.824900747590637e-05, 'samples': 21954432, 'steps': 114345, 'loss/train': 1.1673084497451782} 08/31/2021 09:55:36 - INFO - __main__ - Step 114347: {'lr': 6.824536372970683e-05, 'samples': 21954624, 'steps': 114346, 'loss/train': 1.1095962524414062} 08/31/2021 09:55:37 - INFO - __main__ - Step 114348: {'lr': 6.824172006540311e-05, 'samples': 21954816, 'steps': 114347, 'loss/train': 0.9274887442588806} 08/31/2021 09:55:38 - INFO - __main__ - Step 114349: {'lr': 6.823807648299688e-05, 'samples': 21955008, 'steps': 114348, 'loss/train': 0.9682011008262634} 08/31/2021 09:55:39 - INFO - __main__ - Step 114350: {'lr': 6.823443298248974e-05, 'samples': 21955200, 'steps': 114349, 'loss/train': 0.2966086268424988} 08/31/2021 09:55:39 - INFO - __main__ - Step 114351: {'lr': 6.823078956388337e-05, 'samples': 21955392, 'steps': 114350, 'loss/train': 0.04109331965446472} 08/31/2021 09:55:40 - INFO - __main__ - Step 114352: {'lr': 6.822714622717944e-05, 'samples': 21955584, 'steps': 114351, 'loss/train': 0.04529790207743645} 08/31/2021 09:55:40 - INFO - __main__ - Step 114353: {'lr': 6.822350297237958e-05, 'samples': 21955776, 'steps': 114352, 'loss/train': 0.3931695520877838} 08/31/2021 09:55:41 - INFO - __main__ - Step 114354: {'lr': 6.821985979948533e-05, 'samples': 21955968, 'steps': 114353, 'loss/train': 1.1482740640640259} 08/31/2021 09:55:42 - INFO - __main__ - Step 114355: {'lr': 6.821621670849845e-05, 'samples': 21956160, 'steps': 114354, 'loss/train': 0.9861298203468323} 08/31/2021 09:55:42 - INFO - __main__ - Step 114356: {'lr': 6.821257369942049e-05, 'samples': 21956352, 'steps': 114355, 'loss/train': 0.6569244861602783} 08/31/2021 09:55:42 - INFO - __main__ - Step 114357: {'lr': 6.820893077225318e-05, 'samples': 21956544, 'steps': 114356, 'loss/train': 0.47166532278060913} 08/31/2021 09:55:43 - INFO - __main__ - Step 114358: {'lr': 6.82052879269981e-05, 'samples': 21956736, 'steps': 114357, 'loss/train': 1.1342841386795044} 08/31/2021 09:55:43 - INFO - __main__ - Step 114359: {'lr': 6.820164516365691e-05, 'samples': 21956928, 'steps': 114358, 'loss/train': 1.5049906969070435} 08/31/2021 09:55:46 - INFO - __main__ - Step 114360: {'lr': 6.819800248223123e-05, 'samples': 21957120, 'steps': 114359, 'loss/train': 1.5667420625686646} 08/31/2021 09:55:46 - INFO - __main__ - Step 114361: {'lr': 6.819435988272276e-05, 'samples': 21957312, 'steps': 114360, 'loss/train': 1.527840256690979} 08/31/2021 09:55:47 - INFO - __main__ - Step 114362: {'lr': 6.81907173651331e-05, 'samples': 21957504, 'steps': 114361, 'loss/train': 0.08287809789180756} 08/31/2021 09:55:47 - INFO - __main__ - Step 114363: {'lr': 6.818707492946391e-05, 'samples': 21957696, 'steps': 114362, 'loss/train': 1.2592482566833496} 08/31/2021 09:55:47 - INFO - __main__ - Step 114364: {'lr': 6.818343257571679e-05, 'samples': 21957888, 'steps': 114363, 'loss/train': 0.040001749992370605} 08/31/2021 09:55:49 - INFO - __main__ - Step 114365: {'lr': 6.817979030389343e-05, 'samples': 21958080, 'steps': 114364, 'loss/train': 2.0430850982666016} 08/31/2021 09:55:49 - INFO - __main__ - Step 114366: {'lr': 6.817614811399551e-05, 'samples': 21958272, 'steps': 114365, 'loss/train': 0.5837798714637756} 08/31/2021 09:55:50 - INFO - __main__ - Step 114367: {'lr': 6.817250600602454e-05, 'samples': 21958464, 'steps': 114366, 'loss/train': 1.076343059539795} 08/31/2021 09:55:50 - INFO - __main__ - Step 114368: {'lr': 6.816886397998226e-05, 'samples': 21958656, 'steps': 114367, 'loss/train': 1.6188459396362305} 08/31/2021 09:55:51 - INFO - __main__ - Step 114369: {'lr': 6.816522203587025e-05, 'samples': 21958848, 'steps': 114368, 'loss/train': 0.17337960004806519} 08/31/2021 09:55:52 - INFO - __main__ - Step 114370: {'lr': 6.81615801736902e-05, 'samples': 21959040, 'steps': 114369, 'loss/train': 1.2440567016601562} 08/31/2021 09:55:53 - INFO - __main__ - Step 114371: {'lr': 6.815793839344372e-05, 'samples': 21959232, 'steps': 114370, 'loss/train': 1.0553169250488281} 08/31/2021 09:55:53 - INFO - __main__ - Step 114372: {'lr': 6.815429669513249e-05, 'samples': 21959424, 'steps': 114371, 'loss/train': 0.9687318801879883} 08/31/2021 09:55:53 - INFO - __main__ - Step 114373: {'lr': 6.815065507875811e-05, 'samples': 21959616, 'steps': 114372, 'loss/train': 0.11642349511384964} 08/31/2021 09:55:54 - INFO - __main__ - Step 114374: {'lr': 6.814701354432226e-05, 'samples': 21959808, 'steps': 114373, 'loss/train': 0.9043905138969421} 08/31/2021 09:55:55 - INFO - __main__ - Step 114375: {'lr': 6.814337209182652e-05, 'samples': 21960000, 'steps': 114374, 'loss/train': 0.5511332750320435} 08/31/2021 09:55:56 - INFO - __main__ - Step 114376: {'lr': 6.813973072127261e-05, 'samples': 21960192, 'steps': 114375, 'loss/train': 0.7070747017860413} 08/31/2021 09:55:56 - INFO - __main__ - Step 114377: {'lr': 6.813608943266211e-05, 'samples': 21960384, 'steps': 114376, 'loss/train': 0.9223554134368896} 08/31/2021 09:55:57 - INFO - __main__ - Step 114378: {'lr': 6.81324482259967e-05, 'samples': 21960576, 'steps': 114377, 'loss/train': 1.1200495958328247} 08/31/2021 09:55:57 - INFO - __main__ - Step 114379: {'lr': 6.8128807101278e-05, 'samples': 21960768, 'steps': 114378, 'loss/train': 0.730755627155304} 08/31/2021 09:55:59 - INFO - __main__ - Step 114380: {'lr': 6.812516605850771e-05, 'samples': 21960960, 'steps': 114379, 'loss/train': 1.1735310554504395} 08/31/2021 09:55:59 - INFO - __main__ - Step 114381: {'lr': 6.812152509768734e-05, 'samples': 21961152, 'steps': 114380, 'loss/train': 0.6548031568527222} 08/31/2021 09:55:59 - INFO - __main__ - Step 114382: {'lr': 6.811788421881862e-05, 'samples': 21961344, 'steps': 114381, 'loss/train': 1.3825757503509521} 08/31/2021 09:56:00 - INFO - __main__ - Step 114383: {'lr': 6.811424342190318e-05, 'samples': 21961536, 'steps': 114382, 'loss/train': 1.4526257514953613} 08/31/2021 09:56:00 - INFO - __main__ - Step 114384: {'lr': 6.811060270694263e-05, 'samples': 21961728, 'steps': 114383, 'loss/train': 0.6820613741874695} 08/31/2021 09:56:00 - INFO - __main__ - Step 114385: {'lr': 6.810696207393865e-05, 'samples': 21961920, 'steps': 114384, 'loss/train': 0.9287770390510559} 08/31/2021 09:56:02 - INFO - __main__ - Step 114386: {'lr': 6.810332152289286e-05, 'samples': 21962112, 'steps': 114385, 'loss/train': 0.6581976413726807} 08/31/2021 09:56:03 - INFO - __main__ - Step 114387: {'lr': 6.809968105380692e-05, 'samples': 21962304, 'steps': 114386, 'loss/train': 1.104901671409607} 08/31/2021 09:56:03 - INFO - __main__ - Step 114388: {'lr': 6.809604066668246e-05, 'samples': 21962496, 'steps': 114387, 'loss/train': 1.5626356601715088} 08/31/2021 09:56:03 - INFO - __main__ - Step 114389: {'lr': 6.809240036152109e-05, 'samples': 21962688, 'steps': 114388, 'loss/train': 0.6724610328674316} 08/31/2021 09:56:04 - INFO - __main__ - Step 114390: {'lr': 6.80887601383245e-05, 'samples': 21962880, 'steps': 114389, 'loss/train': 0.869446873664856} 08/31/2021 09:56:05 - INFO - __main__ - Step 114391: {'lr': 6.80851199970943e-05, 'samples': 21963072, 'steps': 114390, 'loss/train': 1.3608170747756958} 08/31/2021 09:56:06 - INFO - __main__ - Step 114392: {'lr': 6.808147993783215e-05, 'samples': 21963264, 'steps': 114391, 'loss/train': 0.8181746006011963} 08/31/2021 09:56:06 - INFO - __main__ - Step 114393: {'lr': 6.807783996053974e-05, 'samples': 21963456, 'steps': 114392, 'loss/train': 1.843659520149231} 08/31/2021 09:56:06 - INFO - __main__ - Step 114394: {'lr': 6.807420006521855e-05, 'samples': 21963648, 'steps': 114393, 'loss/train': 1.2525653839111328} 08/31/2021 09:56:07 - INFO - __main__ - Step 114395: {'lr': 6.807056025187036e-05, 'samples': 21963840, 'steps': 114394, 'loss/train': 1.3507674932479858} 08/31/2021 09:56:08 - INFO - __main__ - Step 114396: {'lr': 6.806692052049674e-05, 'samples': 21964032, 'steps': 114395, 'loss/train': 1.0938453674316406} 08/31/2021 09:56:09 - INFO - __main__ - Step 114397: {'lr': 6.806328087109937e-05, 'samples': 21964224, 'steps': 114396, 'loss/train': 1.3574681282043457} 08/31/2021 09:56:09 - INFO - __main__ - Step 114398: {'lr': 6.805964130367986e-05, 'samples': 21964416, 'steps': 114397, 'loss/train': 0.13531549274921417} 08/31/2021 09:56:09 - INFO - __main__ - Step 114399: {'lr': 6.80560018182399e-05, 'samples': 21964608, 'steps': 114398, 'loss/train': 1.1601492166519165} 08/31/2021 09:56:10 - INFO - __main__ - Step 114400: {'lr': 6.805236241478108e-05, 'samples': 21964800, 'steps': 114399, 'loss/train': 0.4350866377353668} 08/31/2021 09:56:11 - INFO - __main__ - Step 114401: {'lr': 6.804872309330506e-05, 'samples': 21964992, 'steps': 114400, 'loss/train': 1.4367461204528809} 08/31/2021 09:56:12 - INFO - __main__ - Step 114402: {'lr': 6.804508385381348e-05, 'samples': 21965184, 'steps': 114401, 'loss/train': 1.2906769514083862} 08/31/2021 09:56:12 - INFO - __main__ - Step 114403: {'lr': 6.8041444696308e-05, 'samples': 21965376, 'steps': 114402, 'loss/train': 1.2187714576721191} 08/31/2021 09:56:12 - INFO - __main__ - Step 114404: {'lr': 6.803780562079021e-05, 'samples': 21965568, 'steps': 114403, 'loss/train': 0.3337147831916809} 08/31/2021 09:56:13 - INFO - __main__ - Step 114405: {'lr': 6.803416662726175e-05, 'samples': 21965760, 'steps': 114404, 'loss/train': 1.5810974836349487} 08/31/2021 09:56:14 - INFO - __main__ - Step 114406: {'lr': 6.80305277157244e-05, 'samples': 21965952, 'steps': 114405, 'loss/train': 1.3601861000061035} 08/31/2021 09:56:15 - INFO - __main__ - Step 114407: {'lr': 6.802688888617962e-05, 'samples': 21966144, 'steps': 114406, 'loss/train': 0.3844998776912689} 08/31/2021 09:56:15 - INFO - __main__ - Step 114408: {'lr': 6.802325013862908e-05, 'samples': 21966336, 'steps': 114407, 'loss/train': 2.1057276725769043} 08/31/2021 09:56:15 - INFO - __main__ - Step 114409: {'lr': 6.801961147307447e-05, 'samples': 21966528, 'steps': 114408, 'loss/train': 0.191862553358078} 08/31/2021 09:56:16 - INFO - __main__ - Step 114410: {'lr': 6.801597288951745e-05, 'samples': 21966720, 'steps': 114409, 'loss/train': 1.4063199758529663} 08/31/2021 09:56:17 - INFO - __main__ - Step 114411: {'lr': 6.801233438795957e-05, 'samples': 21966912, 'steps': 114410, 'loss/train': 1.0273319482803345} 08/31/2021 09:56:18 - INFO - __main__ - Step 114412: {'lr': 6.800869596840257e-05, 'samples': 21967104, 'steps': 114411, 'loss/train': 0.9165803790092468} 08/31/2021 09:56:18 - INFO - __main__ - Step 114413: {'lr': 6.8005057630848e-05, 'samples': 21967296, 'steps': 114412, 'loss/train': 1.5080182552337646} 08/31/2021 09:56:18 - INFO - __main__ - Step 114414: {'lr': 6.800141937529755e-05, 'samples': 21967488, 'steps': 114413, 'loss/train': 0.2349414825439453} 08/31/2021 09:56:19 - INFO - __main__ - Step 114415: {'lr': 6.799778120175287e-05, 'samples': 21967680, 'steps': 114414, 'loss/train': 1.035172462463379} 08/31/2021 09:56:19 - INFO - __main__ - Step 114416: {'lr': 6.79941431102156e-05, 'samples': 21967872, 'steps': 114415, 'loss/train': 1.107696294784546} 08/31/2021 09:56:22 - INFO - __main__ - Step 114417: {'lr': 6.799050510068733e-05, 'samples': 21968064, 'steps': 114416, 'loss/train': 0.45088520646095276} 08/31/2021 09:56:22 - INFO - __main__ - Step 114418: {'lr': 6.798686717316973e-05, 'samples': 21968256, 'steps': 114417, 'loss/train': 1.3377071619033813} 08/31/2021 09:56:23 - INFO - __main__ - Step 114419: {'lr': 6.798322932766446e-05, 'samples': 21968448, 'steps': 114418, 'loss/train': 0.7352408170700073} 08/31/2021 09:56:23 - INFO - __main__ - Step 114420: {'lr': 6.797959156417318e-05, 'samples': 21968640, 'steps': 114419, 'loss/train': 1.4000452756881714} 08/31/2021 09:56:23 - INFO - __main__ - Step 114421: {'lr': 6.797595388269745e-05, 'samples': 21968832, 'steps': 114420, 'loss/train': 0.863422155380249} 08/31/2021 09:56:25 - INFO - __main__ - Step 114422: {'lr': 6.797231628323892e-05, 'samples': 21969024, 'steps': 114421, 'loss/train': 0.033236753195524216} 08/31/2021 09:56:25 - INFO - __main__ - Step 114423: {'lr': 6.796867876579926e-05, 'samples': 21969216, 'steps': 114422, 'loss/train': 1.0871262550354004} 08/31/2021 09:56:26 - INFO - __main__ - Step 114424: {'lr': 6.796504133038012e-05, 'samples': 21969408, 'steps': 114423, 'loss/train': 0.9735658168792725} 08/31/2021 09:56:26 - INFO - __main__ - Step 114425: {'lr': 6.796140397698311e-05, 'samples': 21969600, 'steps': 114424, 'loss/train': 1.6490978002548218} 08/31/2021 09:56:26 - INFO - __main__ - Step 114426: {'lr': 6.795776670560988e-05, 'samples': 21969792, 'steps': 114425, 'loss/train': 1.021437644958496} 08/31/2021 09:56:27 - INFO - __main__ - Step 114427: {'lr': 6.795412951626206e-05, 'samples': 21969984, 'steps': 114426, 'loss/train': 5.790607452392578} 08/31/2021 09:56:28 - INFO - __main__ - Step 114428: {'lr': 6.795049240894132e-05, 'samples': 21970176, 'steps': 114427, 'loss/train': 0.5870633125305176} 08/31/2021 09:56:29 - INFO - __main__ - Step 114429: {'lr': 6.794685538364928e-05, 'samples': 21970368, 'steps': 114428, 'loss/train': 1.5494171380996704} 08/31/2021 09:56:29 - INFO - __main__ - Step 114430: {'lr': 6.794321844038756e-05, 'samples': 21970560, 'steps': 114429, 'loss/train': 1.6547242403030396} 08/31/2021 09:56:29 - INFO - __main__ - Step 114431: {'lr': 6.793958157915784e-05, 'samples': 21970752, 'steps': 114430, 'loss/train': 1.0661693811416626} 08/31/2021 09:56:30 - INFO - __main__ - Step 114432: {'lr': 6.79359447999617e-05, 'samples': 21970944, 'steps': 114431, 'loss/train': 1.0158929824829102} 08/31/2021 09:56:31 - INFO - __main__ - Step 114433: {'lr': 6.793230810280093e-05, 'samples': 21971136, 'steps': 114432, 'loss/train': 0.7994012832641602} 08/31/2021 09:56:32 - INFO - __main__ - Step 114434: {'lr': 6.792867148767695e-05, 'samples': 21971328, 'steps': 114433, 'loss/train': 1.0025800466537476} 08/31/2021 09:56:32 - INFO - __main__ - Step 114435: {'lr': 6.792503495459152e-05, 'samples': 21971520, 'steps': 114434, 'loss/train': 0.16992883384227753} 08/31/2021 09:56:32 - INFO - __main__ - Step 114436: {'lr': 6.792139850354626e-05, 'samples': 21971712, 'steps': 114435, 'loss/train': 0.8372734189033508} 08/31/2021 09:56:33 - INFO - __main__ - Step 114437: {'lr': 6.791776213454279e-05, 'samples': 21971904, 'steps': 114436, 'loss/train': 0.999233067035675} 08/31/2021 09:56:34 - INFO - __main__ - Step 114438: {'lr': 6.791412584758278e-05, 'samples': 21972096, 'steps': 114437, 'loss/train': 1.3491876125335693} 08/31/2021 09:56:35 - INFO - __main__ - Step 114439: {'lr': 6.791048964266786e-05, 'samples': 21972288, 'steps': 114438, 'loss/train': 0.9924663305282593} 08/31/2021 09:56:35 - INFO - __main__ - Step 114440: {'lr': 6.790685351979963e-05, 'samples': 21972480, 'steps': 114439, 'loss/train': 1.6009222269058228} 08/31/2021 09:56:35 - INFO - __main__ - Step 114441: {'lr': 6.790321747897979e-05, 'samples': 21972672, 'steps': 114440, 'loss/train': 1.0840084552764893} 08/31/2021 09:56:36 - INFO - __main__ - Step 114442: {'lr': 6.789958152020995e-05, 'samples': 21972864, 'steps': 114441, 'loss/train': 0.23447906970977783} 08/31/2021 09:56:37 - INFO - __main__ - Step 114443: {'lr': 6.789594564349175e-05, 'samples': 21973056, 'steps': 114442, 'loss/train': 1.0606240034103394} 08/31/2021 09:56:38 - INFO - __main__ - Step 114444: {'lr': 6.789230984882683e-05, 'samples': 21973248, 'steps': 114443, 'loss/train': 1.2111073732376099} 08/31/2021 09:56:38 - INFO - __main__ - Step 114445: {'lr': 6.78886741362168e-05, 'samples': 21973440, 'steps': 114444, 'loss/train': 1.22763991355896} 08/31/2021 09:56:38 - INFO - __main__ - Step 114446: {'lr': 6.788503850566336e-05, 'samples': 21973632, 'steps': 114445, 'loss/train': 0.6446808576583862} 08/31/2021 09:56:39 - INFO - __main__ - Step 114447: {'lr': 6.788140295716816e-05, 'samples': 21973824, 'steps': 114446, 'loss/train': 1.4738277196884155} 08/31/2021 09:56:40 - INFO - __main__ - Step 114448: {'lr': 6.787776749073271e-05, 'samples': 21974016, 'steps': 114447, 'loss/train': 1.040706992149353} 08/31/2021 09:56:40 - INFO - __main__ - Step 114449: {'lr': 6.787413210635874e-05, 'samples': 21974208, 'steps': 114448, 'loss/train': 0.691169798374176} 08/31/2021 09:56:41 - INFO - __main__ - Step 114450: {'lr': 6.787049680404789e-05, 'samples': 21974400, 'steps': 114449, 'loss/train': 0.7491890788078308} 08/31/2021 09:56:41 - INFO - __main__ - Step 114451: {'lr': 6.786686158380176e-05, 'samples': 21974592, 'steps': 114450, 'loss/train': 1.427321195602417} 08/31/2021 09:56:41 - INFO - __main__ - Step 114452: {'lr': 6.786322644562202e-05, 'samples': 21974784, 'steps': 114451, 'loss/train': 1.5548529624938965} 08/31/2021 09:56:42 - INFO - __main__ - Step 114453: {'lr': 6.785959138951028e-05, 'samples': 21974976, 'steps': 114452, 'loss/train': 0.7706128358840942} 08/31/2021 09:56:43 - INFO - __main__ - Step 114454: {'lr': 6.785595641546825e-05, 'samples': 21975168, 'steps': 114453, 'loss/train': 1.4561711549758911} 08/31/2021 09:56:44 - INFO - __main__ - Step 114455: {'lr': 6.785232152349746e-05, 'samples': 21975360, 'steps': 114454, 'loss/train': 0.025362469255924225} 08/31/2021 09:56:44 - INFO - __main__ - Step 114456: {'lr': 6.784868671359962e-05, 'samples': 21975552, 'steps': 114455, 'loss/train': 0.8239385485649109} 08/31/2021 09:56:45 - INFO - __main__ - Step 114457: {'lr': 6.784505198577637e-05, 'samples': 21975744, 'steps': 114456, 'loss/train': 2.109485387802124} 08/31/2021 09:56:45 - INFO - __main__ - Step 114458: {'lr': 6.784141734002939e-05, 'samples': 21975936, 'steps': 114457, 'loss/train': 1.011099100112915} 08/31/2021 09:56:46 - INFO - __main__ - Step 114459: {'lr': 6.783778277636019e-05, 'samples': 21976128, 'steps': 114458, 'loss/train': 0.6674385666847229} 08/31/2021 09:56:47 - INFO - __main__ - Step 114460: {'lr': 6.783414829477044e-05, 'samples': 21976320, 'steps': 114459, 'loss/train': 1.520992636680603} 08/31/2021 09:56:47 - INFO - __main__ - Step 114461: {'lr': 6.783051389526184e-05, 'samples': 21976512, 'steps': 114460, 'loss/train': 0.7207799553871155} 08/31/2021 09:56:48 - INFO - __main__ - Step 114462: {'lr': 6.7826879577836e-05, 'samples': 21976704, 'steps': 114461, 'loss/train': 0.1625979095697403} 08/31/2021 09:56:48 - INFO - __main__ - Step 114463: {'lr': 6.782324534249456e-05, 'samples': 21976896, 'steps': 114462, 'loss/train': 1.1178374290466309} 08/31/2021 09:56:50 - INFO - __main__ - Step 114464: {'lr': 6.781961118923916e-05, 'samples': 21977088, 'steps': 114463, 'loss/train': 1.0468130111694336} 08/31/2021 09:56:50 - INFO - __main__ - Step 114465: {'lr': 6.781597711807142e-05, 'samples': 21977280, 'steps': 114464, 'loss/train': 0.9202038645744324} 08/31/2021 09:56:50 - INFO - __main__ - Step 114466: {'lr': 6.781234312899299e-05, 'samples': 21977472, 'steps': 114465, 'loss/train': 1.8010560274124146} 08/31/2021 09:56:51 - INFO - __main__ - Step 114467: {'lr': 6.780870922200549e-05, 'samples': 21977664, 'steps': 114466, 'loss/train': 0.8559808731079102} 08/31/2021 09:56:51 - INFO - __main__ - Step 114468: {'lr': 6.780507539711058e-05, 'samples': 21977856, 'steps': 114467, 'loss/train': 0.3921680748462677} 08/31/2021 09:56:53 - INFO - __main__ - Step 114469: {'lr': 6.780144165430999e-05, 'samples': 21978048, 'steps': 114468, 'loss/train': 1.5702265501022339} 08/31/2021 09:56:53 - INFO - __main__ - Step 114470: {'lr': 6.779780799360518e-05, 'samples': 21978240, 'steps': 114469, 'loss/train': 0.18443506956100464} 08/31/2021 09:56:54 - INFO - __main__ - Step 114471: {'lr': 6.779417441499786e-05, 'samples': 21978432, 'steps': 114470, 'loss/train': 0.9282341003417969} 08/31/2021 09:56:54 - INFO - __main__ - Step 114472: {'lr': 6.779054091848966e-05, 'samples': 21978624, 'steps': 114471, 'loss/train': 0.7912538051605225} 08/31/2021 09:56:54 - INFO - __main__ - Step 114473: {'lr': 6.778690750408226e-05, 'samples': 21978816, 'steps': 114472, 'loss/train': 1.1335219144821167} 08/31/2021 09:56:56 - INFO - __main__ - Step 114474: {'lr': 6.778327417177724e-05, 'samples': 21979008, 'steps': 114473, 'loss/train': 1.4666743278503418} 08/31/2021 09:56:56 - INFO - __main__ - Step 114475: {'lr': 6.777964092157626e-05, 'samples': 21979200, 'steps': 114474, 'loss/train': 1.0080351829528809} 08/31/2021 09:56:57 - INFO - __main__ - Step 114476: {'lr': 6.777600775348097e-05, 'samples': 21979392, 'steps': 114475, 'loss/train': 0.7974674105644226} 08/31/2021 09:56:57 - INFO - __main__ - Step 114477: {'lr': 6.777237466749304e-05, 'samples': 21979584, 'steps': 114476, 'loss/train': 0.6257385611534119} 08/31/2021 09:56:57 - INFO - __main__ - Step 114478: {'lr': 6.776874166361402e-05, 'samples': 21979776, 'steps': 114477, 'loss/train': 1.7445447444915771} 08/31/2021 09:56:59 - INFO - __main__ - Step 114479: {'lr': 6.77651087418456e-05, 'samples': 21979968, 'steps': 114478, 'loss/train': 1.651042103767395} 08/31/2021 09:56:59 - INFO - __main__ - Step 114480: {'lr': 6.776147590218947e-05, 'samples': 21980160, 'steps': 114479, 'loss/train': 0.973069429397583} 08/31/2021 09:57:00 - INFO - __main__ - Step 114481: {'lr': 6.775784314464717e-05, 'samples': 21980352, 'steps': 114480, 'loss/train': 0.6709554195404053} 08/31/2021 09:57:00 - INFO - __main__ - Step 114482: {'lr': 6.775421046922034e-05, 'samples': 21980544, 'steps': 114481, 'loss/train': 1.42222261428833} 08/31/2021 09:57:00 - INFO - __main__ - Step 114483: {'lr': 6.775057787591069e-05, 'samples': 21980736, 'steps': 114482, 'loss/train': 1.068666696548462} 08/31/2021 09:57:02 - INFO - __main__ - Step 114484: {'lr': 6.774694536471979e-05, 'samples': 21980928, 'steps': 114483, 'loss/train': 1.6686522960662842} 08/31/2021 09:57:02 - INFO - __main__ - Step 114485: {'lr': 6.774331293564931e-05, 'samples': 21981120, 'steps': 114484, 'loss/train': 0.8085751533508301} 08/31/2021 09:57:03 - INFO - __main__ - Step 114486: {'lr': 6.773968058870086e-05, 'samples': 21981312, 'steps': 114485, 'loss/train': 0.1253068596124649} 08/31/2021 09:57:03 - INFO - __main__ - Step 114487: {'lr': 6.773604832387611e-05, 'samples': 21981504, 'steps': 114486, 'loss/train': 1.0113534927368164} 08/31/2021 09:57:03 - INFO - __main__ - Step 114488: {'lr': 6.77324161411767e-05, 'samples': 21981696, 'steps': 114487, 'loss/train': 0.4510098993778229} 08/31/2021 09:57:04 - INFO - __main__ - Step 114489: {'lr': 6.772878404060424e-05, 'samples': 21981888, 'steps': 114488, 'loss/train': 1.202812671661377} 08/31/2021 09:57:06 - INFO - __main__ - Step 114490: {'lr': 6.772515202216037e-05, 'samples': 21982080, 'steps': 114489, 'loss/train': 1.3928240537643433} 08/31/2021 09:57:06 - INFO - __main__ - Step 114491: {'lr': 6.772152008584681e-05, 'samples': 21982272, 'steps': 114490, 'loss/train': 1.513763189315796} 08/31/2021 09:57:06 - INFO - __main__ - Step 114492: {'lr': 6.771788823166505e-05, 'samples': 21982464, 'steps': 114491, 'loss/train': 1.9228246212005615} 08/31/2021 09:57:07 - INFO - __main__ - Step 114493: {'lr': 6.771425645961682e-05, 'samples': 21982656, 'steps': 114492, 'loss/train': 1.3878345489501953} 08/31/2021 09:57:07 - INFO - __main__ - Step 114494: {'lr': 6.771062476970372e-05, 'samples': 21982848, 'steps': 114493, 'loss/train': 2.1734261512756348} 08/31/2021 09:57:09 - INFO - __main__ - Step 114495: {'lr': 6.770699316192738e-05, 'samples': 21983040, 'steps': 114494, 'loss/train': 1.2760804891586304} 08/31/2021 09:57:09 - INFO - __main__ - Step 114496: {'lr': 6.770336163628946e-05, 'samples': 21983232, 'steps': 114495, 'loss/train': 0.6741806268692017} 08/31/2021 09:57:09 - INFO - __main__ - Step 114497: {'lr': 6.76997301927916e-05, 'samples': 21983424, 'steps': 114496, 'loss/train': 1.216564655303955} 08/31/2021 09:57:10 - INFO - __main__ - Step 114498: {'lr': 6.769609883143544e-05, 'samples': 21983616, 'steps': 114497, 'loss/train': 1.0905580520629883} 08/31/2021 09:57:10 - INFO - __main__ - Step 114499: {'lr': 6.769246755222258e-05, 'samples': 21983808, 'steps': 114498, 'loss/train': 0.9618748426437378} 08/31/2021 09:57:12 - INFO - __main__ - Step 114500: {'lr': 6.768883635515468e-05, 'samples': 21984000, 'steps': 114499, 'loss/train': 1.1411303281784058} 08/31/2021 09:57:13 - INFO - __main__ - Step 114501: {'lr': 6.768520524023347e-05, 'samples': 21984192, 'steps': 114500, 'loss/train': 1.7699344158172607} 08/31/2021 09:57:13 - INFO - __main__ - Step 114502: {'lr': 6.768157420746043e-05, 'samples': 21984384, 'steps': 114501, 'loss/train': 0.3900434076786041} 08/31/2021 09:57:13 - INFO - __main__ - Step 114503: {'lr': 6.767794325683724e-05, 'samples': 21984576, 'steps': 114502, 'loss/train': 1.0767714977264404} 08/31/2021 09:57:14 - INFO - __main__ - Step 114504: {'lr': 6.767431238836554e-05, 'samples': 21984768, 'steps': 114503, 'loss/train': 1.2512617111206055} 08/31/2021 09:57:15 - INFO - __main__ - Step 114505: {'lr': 6.7670681602047e-05, 'samples': 21984960, 'steps': 114504, 'loss/train': 1.0981392860412598} 08/31/2021 09:57:16 - INFO - __main__ - Step 114506: {'lr': 6.766705089788325e-05, 'samples': 21985152, 'steps': 114505, 'loss/train': 1.1683348417282104} 08/31/2021 09:57:16 - INFO - __main__ - Step 114507: {'lr': 6.766342027587592e-05, 'samples': 21985344, 'steps': 114506, 'loss/train': 1.6604406833648682} 08/31/2021 09:57:16 - INFO - __main__ - Step 114508: {'lr': 6.76597897360266e-05, 'samples': 21985536, 'steps': 114507, 'loss/train': 1.0177409648895264} 08/31/2021 09:57:17 - INFO - __main__ - Step 114509: {'lr': 6.765615927833698e-05, 'samples': 21985728, 'steps': 114508, 'loss/train': 1.2752563953399658} 08/31/2021 09:57:17 - INFO - __main__ - Step 114510: {'lr': 6.765252890280868e-05, 'samples': 21985920, 'steps': 114509, 'loss/train': 1.639307975769043} 08/31/2021 09:57:18 - INFO - __main__ - Step 114511: {'lr': 6.764889860944334e-05, 'samples': 21986112, 'steps': 114510, 'loss/train': 1.1767319440841675} 08/31/2021 09:57:19 - INFO - __main__ - Step 114512: {'lr': 6.764526839824262e-05, 'samples': 21986304, 'steps': 114511, 'loss/train': 0.9130759835243225} 08/31/2021 09:57:19 - INFO - __main__ - Step 114513: {'lr': 6.764163826920807e-05, 'samples': 21986496, 'steps': 114512, 'loss/train': 0.9954541921615601} 08/31/2021 09:57:20 - INFO - __main__ - Step 114514: {'lr': 6.76380082223415e-05, 'samples': 21986688, 'steps': 114513, 'loss/train': 1.546059489250183} 08/31/2021 09:57:20 - INFO - __main__ - Step 114515: {'lr': 6.763437825764435e-05, 'samples': 21986880, 'steps': 114514, 'loss/train': 1.1142053604125977} 08/31/2021 09:57:22 - INFO - __main__ - Step 114516: {'lr': 6.763074837511835e-05, 'samples': 21987072, 'steps': 114515, 'loss/train': 1.210589051246643} 08/31/2021 09:57:22 - INFO - __main__ - Step 114517: {'lr': 6.762711857476509e-05, 'samples': 21987264, 'steps': 114516, 'loss/train': 1.066040277481079} 08/31/2021 09:57:22 - INFO - __main__ - Step 114518: {'lr': 6.762348885658626e-05, 'samples': 21987456, 'steps': 114517, 'loss/train': 1.427263617515564} 08/31/2021 09:57:23 - INFO - __main__ - Step 114519: {'lr': 6.761985922058344e-05, 'samples': 21987648, 'steps': 114518, 'loss/train': 5.754737377166748} 08/31/2021 09:57:23 - INFO - __main__ - Step 114520: {'lr': 6.761622966675832e-05, 'samples': 21987840, 'steps': 114519, 'loss/train': 1.211366891860962} 08/31/2021 09:57:23 - INFO - __main__ - Step 114521: {'lr': 6.761260019511251e-05, 'samples': 21988032, 'steps': 114520, 'loss/train': 0.6435002684593201} 08/31/2021 09:57:25 - INFO - __main__ - Step 114522: {'lr': 6.760897080564766e-05, 'samples': 21988224, 'steps': 114521, 'loss/train': 1.1875619888305664} 08/31/2021 09:57:26 - INFO - __main__ - Step 114523: {'lr': 6.760534149836537e-05, 'samples': 21988416, 'steps': 114522, 'loss/train': 0.7249559164047241} 08/31/2021 09:57:26 - INFO - __main__ - Step 114524: {'lr': 6.760171227326731e-05, 'samples': 21988608, 'steps': 114523, 'loss/train': 1.0035430192947388} 08/31/2021 09:57:26 - INFO - __main__ - Step 114525: {'lr': 6.75980831303551e-05, 'samples': 21988800, 'steps': 114524, 'loss/train': 1.1590676307678223} 08/31/2021 09:57:27 - INFO - __main__ - Step 114526: {'lr': 6.759445406963038e-05, 'samples': 21988992, 'steps': 114525, 'loss/train': 1.4020835161209106} 08/31/2021 09:57:28 - INFO - __main__ - Step 114527: {'lr': 6.759082509109488e-05, 'samples': 21989184, 'steps': 114526, 'loss/train': 1.4835087060928345} 08/31/2021 09:57:28 - INFO - __main__ - Step 114528: {'lr': 6.758719619475004e-05, 'samples': 21989376, 'steps': 114527, 'loss/train': 0.9515299201011658} 08/31/2021 09:57:29 - INFO - __main__ - Step 114529: {'lr': 6.758356738059759e-05, 'samples': 21989568, 'steps': 114528, 'loss/train': 0.5619990825653076} 08/31/2021 09:57:29 - INFO - __main__ - Step 114530: {'lr': 6.757993864863917e-05, 'samples': 21989760, 'steps': 114529, 'loss/train': 0.8865273594856262} 08/31/2021 09:57:30 - INFO - __main__ - Step 114531: {'lr': 6.757630999887643e-05, 'samples': 21989952, 'steps': 114530, 'loss/train': 1.061340570449829} 08/31/2021 09:57:31 - INFO - __main__ - Step 114532: {'lr': 6.757268143131098e-05, 'samples': 21990144, 'steps': 114531, 'loss/train': 0.8743572235107422} 08/31/2021 09:57:32 - INFO - __main__ - Step 114533: {'lr': 6.756905294594448e-05, 'samples': 21990336, 'steps': 114532, 'loss/train': 0.025140326470136642} 08/31/2021 09:57:32 - INFO - __main__ - Step 114534: {'lr': 6.756542454277853e-05, 'samples': 21990528, 'steps': 114533, 'loss/train': 0.49513569474220276} 08/31/2021 09:57:32 - INFO - __main__ - Step 114535: {'lr': 6.75617962218148e-05, 'samples': 21990720, 'steps': 114534, 'loss/train': 1.3880524635314941} 08/31/2021 09:57:33 - INFO - __main__ - Step 114536: {'lr': 6.755816798305492e-05, 'samples': 21990912, 'steps': 114535, 'loss/train': 1.2268459796905518} 08/31/2021 09:57:34 - INFO - __main__ - Step 114537: {'lr': 6.755453982650047e-05, 'samples': 21991104, 'steps': 114536, 'loss/train': 1.2858878374099731} 08/31/2021 09:57:35 - INFO - __main__ - Step 114538: {'lr': 6.755091175215316e-05, 'samples': 21991296, 'steps': 114537, 'loss/train': 1.4076236486434937} 08/31/2021 09:57:35 - INFO - __main__ - Step 114539: {'lr': 6.75472837600146e-05, 'samples': 21991488, 'steps': 114538, 'loss/train': 0.9911299347877502} 08/31/2021 09:57:35 - INFO - __main__ - Step 114540: {'lr': 6.75436558500864e-05, 'samples': 21991680, 'steps': 114539, 'loss/train': 1.1439458131790161} 08/31/2021 09:57:36 - INFO - __main__ - Step 114541: {'lr': 6.75400280223703e-05, 'samples': 21991872, 'steps': 114540, 'loss/train': 0.645119309425354} 08/31/2021 09:57:37 - INFO - __main__ - Step 114542: {'lr': 6.753640027686778e-05, 'samples': 21992064, 'steps': 114541, 'loss/train': 1.1209521293640137} 08/31/2021 09:57:38 - INFO - __main__ - Step 114543: {'lr': 6.753277261358054e-05, 'samples': 21992256, 'steps': 114542, 'loss/train': 0.9471648335456848} 08/31/2021 09:57:38 - INFO - __main__ - Step 114544: {'lr': 6.752914503251021e-05, 'samples': 21992448, 'steps': 114543, 'loss/train': 0.8752883672714233} 08/31/2021 09:57:38 - INFO - __main__ - Step 114545: {'lr': 6.752551753365843e-05, 'samples': 21992640, 'steps': 114544, 'loss/train': 0.3759097456932068} 08/31/2021 09:57:39 - INFO - __main__ - Step 114546: {'lr': 6.752189011702683e-05, 'samples': 21992832, 'steps': 114545, 'loss/train': 0.11509875953197479} 08/31/2021 09:57:40 - INFO - __main__ - Step 114547: {'lr': 6.751826278261705e-05, 'samples': 21993024, 'steps': 114546, 'loss/train': 1.6888006925582886} 08/31/2021 09:57:41 - INFO - __main__ - Step 114548: {'lr': 6.751463553043075e-05, 'samples': 21993216, 'steps': 114547, 'loss/train': 1.458827018737793} 08/31/2021 09:57:41 - INFO - __main__ - Step 114549: {'lr': 6.75110083604695e-05, 'samples': 21993408, 'steps': 114548, 'loss/train': 1.0603657960891724} 08/31/2021 09:57:42 - INFO - __main__ - Step 114550: {'lr': 6.750738127273501e-05, 'samples': 21993600, 'steps': 114549, 'loss/train': 1.3420612812042236} 08/31/2021 09:57:42 - INFO - __main__ - Step 114551: {'lr': 6.750375426722886e-05, 'samples': 21993792, 'steps': 114550, 'loss/train': 0.6215590834617615} 08/31/2021 09:57:42 - INFO - __main__ - Step 114552: {'lr': 6.75001273439527e-05, 'samples': 21993984, 'steps': 114551, 'loss/train': 0.636417031288147} 08/31/2021 09:57:44 - INFO - __main__ - Step 114553: {'lr': 6.749650050290818e-05, 'samples': 21994176, 'steps': 114552, 'loss/train': 0.8569208383560181} 08/31/2021 09:57:44 - INFO - __main__ - Step 114554: {'lr': 6.749287374409698e-05, 'samples': 21994368, 'steps': 114553, 'loss/train': 0.3546041250228882} 08/31/2021 09:57:45 - INFO - __main__ - Step 114555: {'lr': 6.748924706752061e-05, 'samples': 21994560, 'steps': 114554, 'loss/train': 1.2934939861297607} 08/31/2021 09:57:45 - INFO - __main__ - Step 114556: {'lr': 6.748562047318076e-05, 'samples': 21994752, 'steps': 114555, 'loss/train': 1.011806607246399} 08/31/2021 09:57:45 - INFO - __main__ - Step 114557: {'lr': 6.748199396107909e-05, 'samples': 21994944, 'steps': 114556, 'loss/train': 1.2273534536361694} 08/31/2021 09:57:48 - INFO - __main__ - Step 114558: {'lr': 6.747836753121719e-05, 'samples': 21995136, 'steps': 114557, 'loss/train': 0.47022315859794617} 08/31/2021 09:57:48 - INFO - __main__ - Step 114559: {'lr': 6.747474118359675e-05, 'samples': 21995328, 'steps': 114558, 'loss/train': 0.8407237529754639} 08/31/2021 09:57:49 - INFO - __main__ - Step 114560: {'lr': 6.747111491821937e-05, 'samples': 21995520, 'steps': 114559, 'loss/train': 0.9382535815238953} 08/31/2021 09:57:49 - INFO - __main__ - Step 114561: {'lr': 6.746748873508669e-05, 'samples': 21995712, 'steps': 114560, 'loss/train': 1.6562983989715576} 08/31/2021 09:57:49 - INFO - __main__ - Step 114562: {'lr': 6.746386263420032e-05, 'samples': 21995904, 'steps': 114561, 'loss/train': 0.13308748602867126} 08/31/2021 09:57:51 - INFO - __main__ - Step 114563: {'lr': 6.746023661556194e-05, 'samples': 21996096, 'steps': 114562, 'loss/train': 0.5808212757110596} 08/31/2021 09:57:52 - INFO - __main__ - Step 114564: {'lr': 6.745661067917314e-05, 'samples': 21996288, 'steps': 114563, 'loss/train': 0.8344821929931641} 08/31/2021 09:57:52 - INFO - __main__ - Step 114565: {'lr': 6.745298482503559e-05, 'samples': 21996480, 'steps': 114564, 'loss/train': 1.1591706275939941} 08/31/2021 09:57:52 - INFO - __main__ - Step 114566: {'lr': 6.744935905315091e-05, 'samples': 21996672, 'steps': 114565, 'loss/train': 1.4058398008346558} 08/31/2021 09:57:53 - INFO - __main__ - Step 114567: {'lr': 6.744573336352072e-05, 'samples': 21996864, 'steps': 114566, 'loss/train': 0.903826117515564} 08/31/2021 09:57:53 - INFO - __main__ - Step 114568: {'lr': 6.744210775614676e-05, 'samples': 21997056, 'steps': 114567, 'loss/train': 1.759294867515564} 08/31/2021 09:57:55 - INFO - __main__ - Step 114569: {'lr': 6.743848223103047e-05, 'samples': 21997248, 'steps': 114568, 'loss/train': 5.843113422393799} 08/31/2021 09:57:55 - INFO - __main__ - Step 114570: {'lr': 6.74348567881736e-05, 'samples': 21997440, 'steps': 114569, 'loss/train': 1.3487026691436768} 08/31/2021 09:57:55 - INFO - __main__ - Step 114571: {'lr': 6.743123142757776e-05, 'samples': 21997632, 'steps': 114570, 'loss/train': 0.9772714376449585} 08/31/2021 09:57:56 - INFO - __main__ - Step 114572: {'lr': 6.74276061492446e-05, 'samples': 21997824, 'steps': 114571, 'loss/train': 1.4957633018493652} 08/31/2021 09:57:56 - INFO - __main__ - Step 114573: {'lr': 6.742398095317573e-05, 'samples': 21998016, 'steps': 114572, 'loss/train': 1.2995549440383911} 08/31/2021 09:57:57 - INFO - __main__ - Step 114574: {'lr': 6.742035583937278e-05, 'samples': 21998208, 'steps': 114573, 'loss/train': 0.9600065350532532} 08/31/2021 09:57:58 - INFO - __main__ - Step 114575: {'lr': 6.741673080783742e-05, 'samples': 21998400, 'steps': 114574, 'loss/train': 1.4705597162246704} 08/31/2021 09:57:58 - INFO - __main__ - Step 114576: {'lr': 6.741310585857127e-05, 'samples': 21998592, 'steps': 114575, 'loss/train': 1.2337266206741333} 08/31/2021 09:57:59 - INFO - __main__ - Step 114577: {'lr': 6.740948099157596e-05, 'samples': 21998784, 'steps': 114576, 'loss/train': 1.8149985074996948} 08/31/2021 09:57:59 - INFO - __main__ - Step 114578: {'lr': 6.740585620685311e-05, 'samples': 21998976, 'steps': 114577, 'loss/train': 1.462438941001892} 08/31/2021 09:58:00 - INFO - __main__ - Step 114579: {'lr': 6.740223150440435e-05, 'samples': 21999168, 'steps': 114578, 'loss/train': 1.056719422340393} 08/31/2021 09:58:01 - INFO - __main__ - Step 114580: {'lr': 6.739860688423135e-05, 'samples': 21999360, 'steps': 114579, 'loss/train': 1.2574695348739624} 08/31/2021 09:58:01 - INFO - __main__ - Step 114581: {'lr': 6.739498234633579e-05, 'samples': 21999552, 'steps': 114580, 'loss/train': 1.4641728401184082} 08/31/2021 09:58:02 - INFO - __main__ - Step 114582: {'lr': 6.739135789071915e-05, 'samples': 21999744, 'steps': 114581, 'loss/train': 0.3351093530654907} 08/31/2021 09:58:02 - INFO - __main__ - Step 114583: {'lr': 6.738773351738317e-05, 'samples': 21999936, 'steps': 114582, 'loss/train': 1.8175605535507202} 08/31/2021 09:58:03 - INFO - __main__ - Step 114584: {'lr': 6.738410922632943e-05, 'samples': 22000128, 'steps': 114583, 'loss/train': 0.9631704688072205} 08/31/2021 09:58:04 - INFO - __main__ - Step 114585: {'lr': 6.738048501755961e-05, 'samples': 22000320, 'steps': 114584, 'loss/train': 0.6972661018371582} 08/31/2021 09:58:04 - INFO - __main__ - Step 114586: {'lr': 6.73768608910753e-05, 'samples': 22000512, 'steps': 114585, 'loss/train': 1.6521633863449097} 08/31/2021 09:58:05 - INFO - __main__ - Step 114587: {'lr': 6.737323684687818e-05, 'samples': 22000704, 'steps': 114586, 'loss/train': 1.436040997505188} 08/31/2021 09:58:05 - INFO - __main__ - Step 114588: {'lr': 6.736961288496988e-05, 'samples': 22000896, 'steps': 114587, 'loss/train': 0.938864529132843} 08/31/2021 09:58:07 - INFO - __main__ - Step 114589: {'lr': 6.736598900535198e-05, 'samples': 22001088, 'steps': 114588, 'loss/train': 0.9355956315994263} 08/31/2021 09:58:08 - INFO - __main__ - Step 114590: {'lr': 6.736236520802616e-05, 'samples': 22001280, 'steps': 114589, 'loss/train': 0.9839329123497009} 08/31/2021 09:58:08 - INFO - __main__ - Step 114591: {'lr': 6.735874149299404e-05, 'samples': 22001472, 'steps': 114590, 'loss/train': 0.7867734432220459} 08/31/2021 09:58:08 - INFO - __main__ - Step 114592: {'lr': 6.735511786025725e-05, 'samples': 22001664, 'steps': 114591, 'loss/train': 1.1644971370697021} 08/31/2021 09:58:09 - INFO - __main__ - Step 114593: {'lr': 6.735149430981743e-05, 'samples': 22001856, 'steps': 114592, 'loss/train': 1.2411655187606812} 08/31/2021 09:58:11 - INFO - __main__ - Step 114594: {'lr': 6.73478708416762e-05, 'samples': 22002048, 'steps': 114593, 'loss/train': 0.23166614770889282} 08/31/2021 09:58:11 - INFO - __main__ - Step 114595: {'lr': 6.734424745583528e-05, 'samples': 22002240, 'steps': 114594, 'loss/train': 1.1186808347702026} 08/31/2021 09:58:12 - INFO - __main__ - Step 114596: {'lr': 6.734062415229616e-05, 'samples': 22002432, 'steps': 114595, 'loss/train': 0.9758989810943604} 08/31/2021 09:58:12 - INFO - __main__ - Step 114597: {'lr': 6.733700093106055e-05, 'samples': 22002624, 'steps': 114596, 'loss/train': 1.6664745807647705} 08/31/2021 09:58:12 - INFO - __main__ - Step 114598: {'lr': 6.733337779213003e-05, 'samples': 22002816, 'steps': 114597, 'loss/train': 1.3145335912704468} 08/31/2021 09:58:13 - INFO - __main__ - Step 114599: {'lr': 6.732975473550629e-05, 'samples': 22003008, 'steps': 114598, 'loss/train': 1.011130928993225} 08/31/2021 09:58:13 - INFO - __main__ - Step 114600: {'lr': 6.732613176119093e-05, 'samples': 22003200, 'steps': 114599, 'loss/train': 0.03286093473434448} 08/31/2021 09:58:15 - INFO - __main__ - Step 114601: {'lr': 6.732250886918562e-05, 'samples': 22003392, 'steps': 114600, 'loss/train': 1.2119686603546143} 08/31/2021 09:58:15 - INFO - __main__ - Step 114602: {'lr': 6.731888605949197e-05, 'samples': 22003584, 'steps': 114601, 'loss/train': 1.3000881671905518} 08/31/2021 09:58:16 - INFO - __main__ - Step 114603: {'lr': 6.731526333211157e-05, 'samples': 22003776, 'steps': 114602, 'loss/train': 2.5244669914245605} 08/31/2021 09:58:16 - INFO - __main__ - Step 114604: {'lr': 6.731164068704612e-05, 'samples': 22003968, 'steps': 114603, 'loss/train': 1.0572495460510254} 08/31/2021 09:58:16 - INFO - __main__ - Step 114605: {'lr': 6.730801812429724e-05, 'samples': 22004160, 'steps': 114604, 'loss/train': 0.834100604057312} 08/31/2021 09:58:18 - INFO - __main__ - Step 114606: {'lr': 6.730439564386654e-05, 'samples': 22004352, 'steps': 114605, 'loss/train': 1.097868800163269} 08/31/2021 09:58:18 - INFO - __main__ - Step 114607: {'lr': 6.730077324575564e-05, 'samples': 22004544, 'steps': 114606, 'loss/train': 1.2965775728225708} 08/31/2021 09:58:19 - INFO - __main__ - Step 114608: {'lr': 6.72971509299663e-05, 'samples': 22004736, 'steps': 114607, 'loss/train': 1.3929692506790161} 08/31/2021 09:58:19 - INFO - __main__ - Step 114609: {'lr': 6.729352869649993e-05, 'samples': 22004928, 'steps': 114608, 'loss/train': 1.1024364233016968} 08/31/2021 09:58:19 - INFO - __main__ - Step 114610: {'lr': 6.72899065453583e-05, 'samples': 22005120, 'steps': 114609, 'loss/train': 1.4198757410049438} 08/31/2021 09:58:20 - INFO - __main__ - Step 114611: {'lr': 6.728628447654304e-05, 'samples': 22005312, 'steps': 114610, 'loss/train': 1.523208498954773} 08/31/2021 09:58:22 - INFO - __main__ - Step 114612: {'lr': 6.728266249005572e-05, 'samples': 22005504, 'steps': 114611, 'loss/train': 1.9773173332214355} 08/31/2021 09:58:22 - INFO - __main__ - Step 114613: {'lr': 6.727904058589804e-05, 'samples': 22005696, 'steps': 114612, 'loss/train': 0.9364984631538391} 08/31/2021 09:58:22 - INFO - __main__ - Step 114614: {'lr': 6.727541876407159e-05, 'samples': 22005888, 'steps': 114613, 'loss/train': 0.7185684442520142} 08/31/2021 09:58:23 - INFO - __main__ - Step 114615: {'lr': 6.7271797024578e-05, 'samples': 22006080, 'steps': 114614, 'loss/train': 0.7459390759468079} 08/31/2021 09:58:23 - INFO - __main__ - Step 114616: {'lr': 6.726817536741894e-05, 'samples': 22006272, 'steps': 114615, 'loss/train': 0.8694247603416443} 08/31/2021 09:58:25 - INFO - __main__ - Step 114617: {'lr': 6.726455379259602e-05, 'samples': 22006464, 'steps': 114616, 'loss/train': 0.7965916395187378} 08/31/2021 09:58:25 - INFO - __main__ - Step 114618: {'lr': 6.726093230011088e-05, 'samples': 22006656, 'steps': 114617, 'loss/train': 0.6002322435379028} 08/31/2021 09:58:25 - INFO - __main__ - Step 114619: {'lr': 6.725731088996515e-05, 'samples': 22006848, 'steps': 114618, 'loss/train': 0.7602020502090454} 08/31/2021 09:58:26 - INFO - __main__ - Step 114620: {'lr': 6.725368956216044e-05, 'samples': 22007040, 'steps': 114619, 'loss/train': 0.9982813000679016} 08/31/2021 09:58:26 - INFO - __main__ - Step 114621: {'lr': 6.725006831669839e-05, 'samples': 22007232, 'steps': 114620, 'loss/train': 0.9916316866874695} 08/31/2021 09:58:28 - INFO - __main__ - Step 114622: {'lr': 6.724644715358072e-05, 'samples': 22007424, 'steps': 114621, 'loss/train': 0.4555228054523468} 08/31/2021 09:58:28 - INFO - __main__ - Step 114623: {'lr': 6.724282607280893e-05, 'samples': 22007616, 'steps': 114622, 'loss/train': 0.3667510449886322} 08/31/2021 09:58:29 - INFO - __main__ - Step 114624: {'lr': 6.723920507438466e-05, 'samples': 22007808, 'steps': 114623, 'loss/train': 0.9588122367858887} 08/31/2021 09:58:29 - INFO - __main__ - Step 114625: {'lr': 6.723558415830963e-05, 'samples': 22008000, 'steps': 114624, 'loss/train': 0.7547538876533508} 08/31/2021 09:58:29 - INFO - __main__ - Step 114626: {'lr': 6.723196332458539e-05, 'samples': 22008192, 'steps': 114625, 'loss/train': 1.0737498998641968} 08/31/2021 09:58:31 - INFO - __main__ - Step 114627: {'lr': 6.722834257321361e-05, 'samples': 22008384, 'steps': 114626, 'loss/train': 1.5361602306365967} 08/31/2021 09:58:31 - INFO - __main__ - Step 114628: {'lr': 6.722472190419593e-05, 'samples': 22008576, 'steps': 114627, 'loss/train': 1.2650598287582397} 08/31/2021 09:58:32 - INFO - __main__ - Step 114629: {'lr': 6.722110131753398e-05, 'samples': 22008768, 'steps': 114628, 'loss/train': 1.64297616481781} 08/31/2021 09:58:32 - INFO - __main__ - Step 114630: {'lr': 6.721748081322938e-05, 'samples': 22008960, 'steps': 114629, 'loss/train': 0.8450219631195068} 08/31/2021 09:58:32 - INFO - __main__ - Step 114631: {'lr': 6.721386039128374e-05, 'samples': 22009152, 'steps': 114630, 'loss/train': 1.2134596109390259} 08/31/2021 09:58:34 - INFO - __main__ - Step 114632: {'lr': 6.721024005169874e-05, 'samples': 22009344, 'steps': 114631, 'loss/train': 0.6238793730735779} 08/31/2021 09:58:34 - INFO - __main__ - Step 114633: {'lr': 6.720661979447595e-05, 'samples': 22009536, 'steps': 114632, 'loss/train': 1.0701500177383423} 08/31/2021 09:58:35 - INFO - __main__ - Step 114634: {'lr': 6.720299961961707e-05, 'samples': 22009728, 'steps': 114633, 'loss/train': 1.1584972143173218} 08/31/2021 09:58:35 - INFO - __main__ - Step 114635: {'lr': 6.719937952712376e-05, 'samples': 22009920, 'steps': 114634, 'loss/train': 0.34222742915153503} 08/31/2021 09:58:35 - INFO - __main__ - Step 114636: {'lr': 6.71957595169975e-05, 'samples': 22010112, 'steps': 114635, 'loss/train': 1.548596978187561} 08/31/2021 09:58:36 - INFO - __main__ - Step 114637: {'lr': 6.719213958924003e-05, 'samples': 22010304, 'steps': 114636, 'loss/train': 0.031320635229349136} 08/31/2021 09:58:37 - INFO - __main__ - Step 114638: {'lr': 6.718851974385296e-05, 'samples': 22010496, 'steps': 114637, 'loss/train': 1.2929967641830444} 08/31/2021 09:58:38 - INFO - __main__ - Step 114639: {'lr': 6.71848999808379e-05, 'samples': 22010688, 'steps': 114638, 'loss/train': 0.9151206612586975} 08/31/2021 09:58:38 - INFO - __main__ - Step 114640: {'lr': 6.718128030019651e-05, 'samples': 22010880, 'steps': 114639, 'loss/train': 0.8940505385398865} 08/31/2021 09:58:38 - INFO - __main__ - Step 114641: {'lr': 6.717766070193043e-05, 'samples': 22011072, 'steps': 114640, 'loss/train': 1.2095979452133179} 08/31/2021 09:58:39 - INFO - __main__ - Step 114642: {'lr': 6.717404118604129e-05, 'samples': 22011264, 'steps': 114641, 'loss/train': 1.0031028985977173} 08/31/2021 09:58:40 - INFO - __main__ - Step 114643: {'lr': 6.717042175253068e-05, 'samples': 22011456, 'steps': 114642, 'loss/train': 1.4152858257293701} 08/31/2021 09:58:41 - INFO - __main__ - Step 114644: {'lr': 6.716680240140025e-05, 'samples': 22011648, 'steps': 114643, 'loss/train': 0.9819040298461914} 08/31/2021 09:58:41 - INFO - __main__ - Step 114645: {'lr': 6.716318313265166e-05, 'samples': 22011840, 'steps': 114644, 'loss/train': 0.8528288006782532} 08/31/2021 09:58:41 - INFO - __main__ - Step 114646: {'lr': 6.71595639462865e-05, 'samples': 22012032, 'steps': 114645, 'loss/train': 1.2371968030929565} 08/31/2021 09:58:42 - INFO - __main__ - Step 114647: {'lr': 6.715594484230645e-05, 'samples': 22012224, 'steps': 114646, 'loss/train': 0.7927923202514648} 08/31/2021 09:58:44 - INFO - __main__ - Step 114648: {'lr': 6.715232582071315e-05, 'samples': 22012416, 'steps': 114647, 'loss/train': 0.5514287948608398} 08/31/2021 09:58:44 - INFO - __main__ - Step 114649: {'lr': 6.714870688150812e-05, 'samples': 22012608, 'steps': 114648, 'loss/train': 1.092596173286438} 08/31/2021 09:58:44 - INFO - __main__ - Step 114650: {'lr': 6.714508802469308e-05, 'samples': 22012800, 'steps': 114649, 'loss/train': 0.8218038082122803} 08/31/2021 09:58:45 - INFO - __main__ - Step 114651: {'lr': 6.714146925026962e-05, 'samples': 22012992, 'steps': 114650, 'loss/train': 1.7991291284561157} 08/31/2021 09:58:45 - INFO - __main__ - Step 114652: {'lr': 6.71378505582394e-05, 'samples': 22013184, 'steps': 114651, 'loss/train': 0.017042141407728195} 08/31/2021 09:58:45 - INFO - __main__ - Step 114653: {'lr': 6.713423194860405e-05, 'samples': 22013376, 'steps': 114652, 'loss/train': 1.8843231201171875} 08/31/2021 09:58:47 - INFO - __main__ - Step 114654: {'lr': 6.713061342136517e-05, 'samples': 22013568, 'steps': 114653, 'loss/train': 1.5679508447647095} 08/31/2021 09:58:48 - INFO - __main__ - Step 114655: {'lr': 6.712699497652444e-05, 'samples': 22013760, 'steps': 114654, 'loss/train': 1.1326404809951782} 08/31/2021 09:58:48 - INFO - __main__ - Step 114656: {'lr': 6.712337661408347e-05, 'samples': 22013952, 'steps': 114655, 'loss/train': 0.8585674166679382} 08/31/2021 09:58:48 - INFO - __main__ - Step 114657: {'lr': 6.711975833404385e-05, 'samples': 22014144, 'steps': 114656, 'loss/train': 1.2705827951431274} 08/31/2021 09:58:49 - INFO - __main__ - Step 114658: {'lr': 6.711614013640727e-05, 'samples': 22014336, 'steps': 114657, 'loss/train': 1.1347006559371948} 08/31/2021 09:58:50 - INFO - __main__ - Step 114659: {'lr': 6.711252202117533e-05, 'samples': 22014528, 'steps': 114658, 'loss/train': 0.931134819984436} 08/31/2021 09:58:51 - INFO - __main__ - Step 114660: {'lr': 6.710890398834968e-05, 'samples': 22014720, 'steps': 114659, 'loss/train': 1.1431866884231567} 08/31/2021 09:58:51 - INFO - __main__ - Step 114661: {'lr': 6.71052860379319e-05, 'samples': 22014912, 'steps': 114660, 'loss/train': 0.13809189200401306} 08/31/2021 09:58:51 - INFO - __main__ - Step 114662: {'lr': 6.710166816992377e-05, 'samples': 22015104, 'steps': 114661, 'loss/train': 1.4674385786056519} 08/31/2021 09:58:52 - INFO - __main__ - Step 114663: {'lr': 6.70980503843267e-05, 'samples': 22015296, 'steps': 114662, 'loss/train': 0.8733050227165222} 08/31/2021 09:58:53 - INFO - __main__ - Step 114664: {'lr': 6.709443268114243e-05, 'samples': 22015488, 'steps': 114663, 'loss/train': 0.6199886798858643} 08/31/2021 09:58:54 - INFO - __main__ - Step 114665: {'lr': 6.709081506037262e-05, 'samples': 22015680, 'steps': 114664, 'loss/train': 1.3029948472976685} 08/31/2021 09:58:54 - INFO - __main__ - Step 114666: {'lr': 6.708719752201883e-05, 'samples': 22015872, 'steps': 114665, 'loss/train': 1.088932991027832} 08/31/2021 09:58:55 - INFO - __main__ - Step 114667: {'lr': 6.708358006608273e-05, 'samples': 22016064, 'steps': 114666, 'loss/train': 1.0639861822128296} 08/31/2021 09:58:55 - INFO - __main__ - Step 114668: {'lr': 6.707996269256598e-05, 'samples': 22016256, 'steps': 114667, 'loss/train': 1.1747380495071411} 08/31/2021 09:58:57 - INFO - __main__ - Step 114669: {'lr': 6.707634540147014e-05, 'samples': 22016448, 'steps': 114668, 'loss/train': 0.39049723744392395} 08/31/2021 09:58:58 - INFO - __main__ - Step 114670: {'lr': 6.707272819279688e-05, 'samples': 22016640, 'steps': 114669, 'loss/train': 1.4673088788986206} 08/31/2021 09:58:58 - INFO - __main__ - Step 114671: {'lr': 6.706911106654784e-05, 'samples': 22016832, 'steps': 114670, 'loss/train': 0.5703927278518677} 08/31/2021 09:58:58 - INFO - __main__ - Step 114672: {'lr': 6.706549402272463e-05, 'samples': 22017024, 'steps': 114671, 'loss/train': 0.6984493136405945} 08/31/2021 09:58:59 - INFO - __main__ - Step 114673: {'lr': 6.706187706132888e-05, 'samples': 22017216, 'steps': 114672, 'loss/train': 1.5184112787246704} 08/31/2021 09:59:00 - INFO - __main__ - Step 114674: {'lr': 6.705826018236222e-05, 'samples': 22017408, 'steps': 114673, 'loss/train': 1.553638219833374} 08/31/2021 09:59:01 - INFO - __main__ - Step 114675: {'lr': 6.705464338582637e-05, 'samples': 22017600, 'steps': 114674, 'loss/train': 1.3473533391952515} 08/31/2021 09:59:01 - INFO - __main__ - Step 114676: {'lr': 6.70510266717228e-05, 'samples': 22017792, 'steps': 114675, 'loss/train': 1.21682608127594} 08/31/2021 09:59:01 - INFO - __main__ - Step 114677: {'lr': 6.704741004005322e-05, 'samples': 22017984, 'steps': 114676, 'loss/train': 1.1039762496948242} 08/31/2021 09:59:02 - INFO - __main__ - Step 114678: {'lr': 6.704379349081924e-05, 'samples': 22018176, 'steps': 114677, 'loss/train': 1.5115315914154053} 08/31/2021 09:59:03 - INFO - __main__ - Step 114679: {'lr': 6.704017702402251e-05, 'samples': 22018368, 'steps': 114678, 'loss/train': 1.0922945737838745} 08/31/2021 09:59:04 - INFO - __main__ - Step 114680: {'lr': 6.703656063966466e-05, 'samples': 22018560, 'steps': 114679, 'loss/train': 0.8207993507385254} 08/31/2021 09:59:04 - INFO - __main__ - Step 114681: {'lr': 6.703294433774731e-05, 'samples': 22018752, 'steps': 114680, 'loss/train': 0.9698492288589478} 08/31/2021 09:59:05 - INFO - __main__ - Step 114682: {'lr': 6.70293281182721e-05, 'samples': 22018944, 'steps': 114681, 'loss/train': 1.1324117183685303} 08/31/2021 09:59:05 - INFO - __main__ - Step 114683: {'lr': 6.702571198124064e-05, 'samples': 22019136, 'steps': 114682, 'loss/train': 1.2911752462387085} 08/31/2021 09:59:05 - INFO - __main__ - Step 114684: {'lr': 6.702209592665457e-05, 'samples': 22019328, 'steps': 114683, 'loss/train': 0.8807255625724792} 08/31/2021 09:59:07 - INFO - __main__ - Step 114685: {'lr': 6.701847995451552e-05, 'samples': 22019520, 'steps': 114684, 'loss/train': 1.2221341133117676} 08/31/2021 09:59:07 - INFO - __main__ - Step 114686: {'lr': 6.70148640648251e-05, 'samples': 22019712, 'steps': 114685, 'loss/train': 0.9866673946380615} 08/31/2021 09:59:08 - INFO - __main__ - Step 114687: {'lr': 6.701124825758498e-05, 'samples': 22019904, 'steps': 114686, 'loss/train': 0.8455082774162292} 08/31/2021 09:59:08 - INFO - __main__ - Step 114688: {'lr': 6.700763253279676e-05, 'samples': 22020096, 'steps': 114687, 'loss/train': 0.811556875705719} 08/31/2021 09:59:08 - INFO - __main__ - Step 114689: {'lr': 6.700401689046217e-05, 'samples': 22020288, 'steps': 114688, 'loss/train': 0.1506568193435669} 08/31/2021 09:59:10 - INFO - __main__ - Step 114690: {'lr': 6.700040133058266e-05, 'samples': 22020480, 'steps': 114689, 'loss/train': 1.0651026964187622} 08/31/2021 09:59:10 - INFO - __main__ - Step 114691: {'lr': 6.699678585315994e-05, 'samples': 22020672, 'steps': 114690, 'loss/train': 1.5254480838775635} 08/31/2021 09:59:11 - INFO - __main__ - Step 114692: {'lr': 6.699317045819564e-05, 'samples': 22020864, 'steps': 114691, 'loss/train': 0.711702287197113} 08/31/2021 09:59:11 - INFO - __main__ - Step 114693: {'lr': 6.698955514569141e-05, 'samples': 22021056, 'steps': 114692, 'loss/train': 1.1005275249481201} 08/31/2021 09:59:11 - INFO - __main__ - Step 114694: {'lr': 6.698593991564886e-05, 'samples': 22021248, 'steps': 114693, 'loss/train': 0.9333074688911438} 08/31/2021 09:59:13 - INFO - __main__ - Step 114695: {'lr': 6.698232476806962e-05, 'samples': 22021440, 'steps': 114694, 'loss/train': 1.6994080543518066} 08/31/2021 09:59:13 - INFO - __main__ - Step 114696: {'lr': 6.697870970295531e-05, 'samples': 22021632, 'steps': 114695, 'loss/train': 0.9218952059745789} 08/31/2021 09:59:14 - INFO - __main__ - Step 114697: {'lr': 6.697509472030758e-05, 'samples': 22021824, 'steps': 114696, 'loss/train': 1.465419054031372} 08/31/2021 09:59:14 - INFO - __main__ - Step 114698: {'lr': 6.697147982012803e-05, 'samples': 22022016, 'steps': 114697, 'loss/train': 0.4774896204471588} 08/31/2021 09:59:14 - INFO - __main__ - Step 114699: {'lr': 6.696786500241834e-05, 'samples': 22022208, 'steps': 114698, 'loss/train': 1.1994589567184448} 08/31/2021 09:59:16 - INFO - __main__ - Step 114700: {'lr': 6.696425026718006e-05, 'samples': 22022400, 'steps': 114699, 'loss/train': 1.7233754396438599} 08/31/2021 09:59:17 - INFO - __main__ - Step 114701: {'lr': 6.69606356144149e-05, 'samples': 22022592, 'steps': 114700, 'loss/train': 1.3250768184661865} 08/31/2021 09:59:17 - INFO - __main__ - Step 114702: {'lr': 6.695702104412452e-05, 'samples': 22022784, 'steps': 114701, 'loss/train': 1.5753355026245117} 08/31/2021 09:59:17 - INFO - __main__ - Step 114703: {'lr': 6.695340655631041e-05, 'samples': 22022976, 'steps': 114702, 'loss/train': 0.9642173051834106} 08/31/2021 09:59:18 - INFO - __main__ - Step 114704: {'lr': 6.694979215097426e-05, 'samples': 22023168, 'steps': 114703, 'loss/train': 1.0470576286315918} 08/31/2021 09:59:18 - INFO - __main__ - Step 114705: {'lr': 6.694617782811772e-05, 'samples': 22023360, 'steps': 114704, 'loss/train': 1.197811484336853} 08/31/2021 09:59:20 - INFO - __main__ - Step 114706: {'lr': 6.694256358774239e-05, 'samples': 22023552, 'steps': 114705, 'loss/train': 0.7121491432189941} 08/31/2021 09:59:20 - INFO - __main__ - Step 114707: {'lr': 6.693894942984993e-05, 'samples': 22023744, 'steps': 114706, 'loss/train': 1.0330209732055664} 08/31/2021 09:59:20 - INFO - __main__ - Step 114708: {'lr': 6.693533535444197e-05, 'samples': 22023936, 'steps': 114707, 'loss/train': 2.3006362915039062} 08/31/2021 09:59:21 - INFO - __main__ - Step 114709: {'lr': 6.693172136152009e-05, 'samples': 22024128, 'steps': 114708, 'loss/train': 0.9119567275047302} 08/31/2021 09:59:21 - INFO - __main__ - Step 114710: {'lr': 6.692810745108599e-05, 'samples': 22024320, 'steps': 114709, 'loss/train': 0.9782299399375916} 08/31/2021 09:59:22 - INFO - __main__ - Step 114711: {'lr': 6.692449362314123e-05, 'samples': 22024512, 'steps': 114710, 'loss/train': 1.2803248167037964} 08/31/2021 09:59:23 - INFO - __main__ - Step 114712: {'lr': 6.692087987768746e-05, 'samples': 22024704, 'steps': 114711, 'loss/train': 0.6388574838638306} 08/31/2021 09:59:23 - INFO - __main__ - Step 114713: {'lr': 6.691726621472635e-05, 'samples': 22024896, 'steps': 114712, 'loss/train': 0.8256405591964722} 08/31/2021 09:59:24 - INFO - __main__ - Step 114714: {'lr': 6.691365263425948e-05, 'samples': 22025088, 'steps': 114713, 'loss/train': 0.6946551203727722} 08/31/2021 09:59:24 - INFO - __main__ - Step 114715: {'lr': 6.691003913628848e-05, 'samples': 22025280, 'steps': 114714, 'loss/train': 1.5381989479064941} 08/31/2021 09:59:26 - INFO - __main__ - Step 114716: {'lr': 6.690642572081507e-05, 'samples': 22025472, 'steps': 114715, 'loss/train': 0.5862749814987183} 08/31/2021 09:59:26 - INFO - __main__ - Step 114717: {'lr': 6.690281238784075e-05, 'samples': 22025664, 'steps': 114716, 'loss/train': 1.2736656665802002} 08/31/2021 09:59:26 - INFO - __main__ - Step 114718: {'lr': 6.689919913736717e-05, 'samples': 22025856, 'steps': 114717, 'loss/train': 0.8444468379020691} 08/31/2021 09:59:27 - INFO - __main__ - Step 114719: {'lr': 6.689558596939599e-05, 'samples': 22026048, 'steps': 114718, 'loss/train': 1.5799134969711304} 08/31/2021 09:59:27 - INFO - __main__ - Step 114720: {'lr': 6.689197288392885e-05, 'samples': 22026240, 'steps': 114719, 'loss/train': 1.2450017929077148} 08/31/2021 09:59:29 - INFO - __main__ - Step 114721: {'lr': 6.688835988096734e-05, 'samples': 22026432, 'steps': 114720, 'loss/train': 1.6055476665496826} 08/31/2021 09:59:30 - INFO - __main__ - Step 114722: {'lr': 6.688474696051312e-05, 'samples': 22026624, 'steps': 114721, 'loss/train': 0.30850356817245483} 08/31/2021 09:59:30 - INFO - __main__ - Step 114723: {'lr': 6.68811341225678e-05, 'samples': 22026816, 'steps': 114722, 'loss/train': 0.4796770215034485} 08/31/2021 09:59:31 - INFO - __main__ - Step 114724: {'lr': 6.687752136713301e-05, 'samples': 22027008, 'steps': 114723, 'loss/train': 1.5076812505722046} 08/31/2021 09:59:31 - INFO - __main__ - Step 114725: {'lr': 6.68739086942104e-05, 'samples': 22027200, 'steps': 114724, 'loss/train': 1.262726068496704} 08/31/2021 09:59:33 - INFO - __main__ - Step 114726: {'lr': 6.687029610380158e-05, 'samples': 22027392, 'steps': 114725, 'loss/train': 1.2200927734375} 08/31/2021 09:59:33 - INFO - __main__ - Step 114727: {'lr': 6.686668359590825e-05, 'samples': 22027584, 'steps': 114726, 'loss/train': 1.0267702341079712} 08/31/2021 09:59:33 - INFO - __main__ - Step 114728: {'lr': 6.68630711705319e-05, 'samples': 22027776, 'steps': 114727, 'loss/train': 0.7041849493980408} 08/31/2021 09:59:34 - INFO - __main__ - Step 114729: {'lr': 6.68594588276742e-05, 'samples': 22027968, 'steps': 114728, 'loss/train': 0.9819949865341187} 08/31/2021 09:59:34 - INFO - __main__ - Step 114730: {'lr': 6.685584656733682e-05, 'samples': 22028160, 'steps': 114729, 'loss/train': 0.47544485330581665} 08/31/2021 09:59:34 - INFO - __main__ - Step 114731: {'lr': 6.685223438952134e-05, 'samples': 22028352, 'steps': 114730, 'loss/train': 1.0453354120254517} 08/31/2021 09:59:36 - INFO - __main__ - Step 114732: {'lr': 6.684862229422945e-05, 'samples': 22028544, 'steps': 114731, 'loss/train': 1.3611842393875122} 08/31/2021 09:59:36 - INFO - __main__ - Step 114733: {'lr': 6.684501028146272e-05, 'samples': 22028736, 'steps': 114732, 'loss/train': 0.2314615398645401} 08/31/2021 09:59:37 - INFO - __main__ - Step 114734: {'lr': 6.684139835122282e-05, 'samples': 22028928, 'steps': 114733, 'loss/train': 1.1185036897659302} 08/31/2021 09:59:37 - INFO - __main__ - Step 114735: {'lr': 6.683778650351138e-05, 'samples': 22029120, 'steps': 114734, 'loss/train': 0.5331069827079773} 08/31/2021 09:59:37 - INFO - __main__ - Step 114736: {'lr': 6.683417473832998e-05, 'samples': 22029312, 'steps': 114735, 'loss/train': 1.5825799703598022} 08/31/2021 09:59:39 - INFO - __main__ - Step 114737: {'lr': 6.683056305568036e-05, 'samples': 22029504, 'steps': 114736, 'loss/train': 1.5088417530059814} 08/31/2021 09:59:40 - INFO - __main__ - Step 114738: {'lr': 6.682695145556397e-05, 'samples': 22029696, 'steps': 114737, 'loss/train': 0.9018728733062744} 08/31/2021 09:59:40 - INFO - __main__ - Step 114739: {'lr': 6.682333993798254e-05, 'samples': 22029888, 'steps': 114738, 'loss/train': 0.7451140880584717} 08/31/2021 09:59:41 - INFO - __main__ - Step 114740: {'lr': 6.681972850293769e-05, 'samples': 22030080, 'steps': 114739, 'loss/train': 1.5879167318344116} 08/31/2021 09:59:41 - INFO - __main__ - Step 114741: {'lr': 6.681611715043104e-05, 'samples': 22030272, 'steps': 114740, 'loss/train': 1.7773984670639038} 08/31/2021 09:59:41 - INFO - __main__ - Step 114742: {'lr': 6.681250588046422e-05, 'samples': 22030464, 'steps': 114741, 'loss/train': 0.6966744065284729} 08/31/2021 09:59:43 - INFO - __main__ - Step 114743: {'lr': 6.680889469303885e-05, 'samples': 22030656, 'steps': 114742, 'loss/train': 0.8096049427986145} 08/31/2021 09:59:43 - INFO - __main__ - Step 114744: {'lr': 6.68052835881566e-05, 'samples': 22030848, 'steps': 114743, 'loss/train': 0.9446796178817749} 08/31/2021 09:59:44 - INFO - __main__ - Step 114745: {'lr': 6.680167256581904e-05, 'samples': 22031040, 'steps': 114744, 'loss/train': 1.0931158065795898} 08/31/2021 09:59:44 - INFO - __main__ - Step 114746: {'lr': 6.67980616260278e-05, 'samples': 22031232, 'steps': 114745, 'loss/train': 1.41666841506958} 08/31/2021 09:59:44 - INFO - __main__ - Step 114747: {'lr': 6.679445076878455e-05, 'samples': 22031424, 'steps': 114746, 'loss/train': 1.0130058526992798} 08/31/2021 09:59:46 - INFO - __main__ - Step 114748: {'lr': 6.679083999409097e-05, 'samples': 22031616, 'steps': 114747, 'loss/train': 1.2716939449310303} 08/31/2021 09:59:46 - INFO - __main__ - Step 114749: {'lr': 6.678722930194853e-05, 'samples': 22031808, 'steps': 114748, 'loss/train': 1.116621732711792} 08/31/2021 09:59:46 - INFO - __main__ - Step 114750: {'lr': 6.678361869235891e-05, 'samples': 22032000, 'steps': 114749, 'loss/train': 0.03241086006164551} 08/31/2021 09:59:47 - INFO - __main__ - Step 114751: {'lr': 6.678000816532381e-05, 'samples': 22032192, 'steps': 114750, 'loss/train': 0.8405965566635132} 08/31/2021 09:59:47 - INFO - __main__ - Step 114752: {'lr': 6.67763977208448e-05, 'samples': 22032384, 'steps': 114751, 'loss/train': 0.9215835928916931} 08/31/2021 09:59:49 - INFO - __main__ - Step 114753: {'lr': 6.677278735892348e-05, 'samples': 22032576, 'steps': 114752, 'loss/train': 1.0005342960357666} 08/31/2021 09:59:49 - INFO - __main__ - Step 114754: {'lr': 6.676917707956154e-05, 'samples': 22032768, 'steps': 114753, 'loss/train': 0.9147549271583557} 08/31/2021 09:59:50 - INFO - __main__ - Step 114755: {'lr': 6.676556688276058e-05, 'samples': 22032960, 'steps': 114754, 'loss/train': 1.4002991914749146} 08/31/2021 09:59:50 - INFO - __main__ - Step 114756: {'lr': 6.676195676852223e-05, 'samples': 22033152, 'steps': 114755, 'loss/train': 1.0978662967681885} 08/31/2021 09:59:50 - INFO - __main__ - Step 114757: {'lr': 6.675834673684814e-05, 'samples': 22033344, 'steps': 114756, 'loss/train': 0.6304309964179993} 08/31/2021 09:59:51 - INFO - __main__ - Step 114758: {'lr': 6.675473678773989e-05, 'samples': 22033536, 'steps': 114757, 'loss/train': 0.3697885572910309} 08/31/2021 09:59:52 - INFO - __main__ - Step 114759: {'lr': 6.675112692119919e-05, 'samples': 22033728, 'steps': 114758, 'loss/train': 1.4260190725326538} 08/31/2021 09:59:53 - INFO - __main__ - Step 114760: {'lr': 6.674751713722755e-05, 'samples': 22033920, 'steps': 114759, 'loss/train': 1.0285048484802246} 08/31/2021 09:59:53 - INFO - __main__ - Step 114761: {'lr': 6.674390743582662e-05, 'samples': 22034112, 'steps': 114760, 'loss/train': 1.6045335531234741} 08/31/2021 09:59:53 - INFO - __main__ - Step 114762: {'lr': 6.674029781699809e-05, 'samples': 22034304, 'steps': 114761, 'loss/train': 0.8439475893974304} 08/31/2021 09:59:54 - INFO - __main__ - Step 114763: {'lr': 6.673668828074354e-05, 'samples': 22034496, 'steps': 114762, 'loss/train': 0.9225717782974243} 08/31/2021 09:59:55 - INFO - __main__ - Step 114764: {'lr': 6.673307882706461e-05, 'samples': 22034688, 'steps': 114763, 'loss/train': 1.442603588104248} 08/31/2021 09:59:56 - INFO - __main__ - Step 114765: {'lr': 6.672946945596292e-05, 'samples': 22034880, 'steps': 114764, 'loss/train': 0.5327026844024658} 08/31/2021 09:59:56 - INFO - __main__ - Step 114766: {'lr': 6.672586016744012e-05, 'samples': 22035072, 'steps': 114765, 'loss/train': 1.047220230102539} 08/31/2021 09:59:57 - INFO - __main__ - Step 114767: {'lr': 6.672225096149781e-05, 'samples': 22035264, 'steps': 114766, 'loss/train': 1.076851725578308} 08/31/2021 09:59:57 - INFO - __main__ - Step 114768: {'lr': 6.671864183813765e-05, 'samples': 22035456, 'steps': 114767, 'loss/train': 1.3207504749298096} 08/31/2021 09:59:59 - INFO - __main__ - Step 114769: {'lr': 6.671503279736121e-05, 'samples': 22035648, 'steps': 114768, 'loss/train': 1.275202751159668} 08/31/2021 09:59:59 - INFO - __main__ - Step 114770: {'lr': 6.671142383917023e-05, 'samples': 22035840, 'steps': 114769, 'loss/train': 3.337865114212036} 08/31/2021 09:59:59 - INFO - __main__ - Step 114771: {'lr': 6.670781496356618e-05, 'samples': 22036032, 'steps': 114770, 'loss/train': 1.143234133720398} 08/31/2021 10:00:00 - INFO - __main__ - Step 114772: {'lr': 6.670420617055076e-05, 'samples': 22036224, 'steps': 114771, 'loss/train': 1.162890911102295} 08/31/2021 10:00:00 - INFO - __main__ - Step 114773: {'lr': 6.670059746012561e-05, 'samples': 22036416, 'steps': 114772, 'loss/train': 0.14101529121398926} 08/31/2021 10:00:02 - INFO - __main__ - Step 114774: {'lr': 6.669698883229233e-05, 'samples': 22036608, 'steps': 114773, 'loss/train': 1.1350581645965576} 08/31/2021 10:00:03 - INFO - __main__ - Step 114775: {'lr': 6.669338028705255e-05, 'samples': 22036800, 'steps': 114774, 'loss/train': 1.2360836267471313} 08/31/2021 10:00:03 - INFO - __main__ - Step 114776: {'lr': 6.668977182440792e-05, 'samples': 22036992, 'steps': 114775, 'loss/train': 1.4933176040649414} 08/31/2021 10:00:03 - INFO - __main__ - Step 114777: {'lr': 6.668616344436005e-05, 'samples': 22037184, 'steps': 114776, 'loss/train': 1.266769289970398} 08/31/2021 10:00:04 - INFO - __main__ - Step 114778: {'lr': 6.668255514691055e-05, 'samples': 22037376, 'steps': 114777, 'loss/train': 1.4121458530426025} 08/31/2021 10:00:04 - INFO - __main__ - Step 114779: {'lr': 6.667894693206106e-05, 'samples': 22037568, 'steps': 114778, 'loss/train': 5.191995143890381} 08/31/2021 10:00:06 - INFO - __main__ - Step 114780: {'lr': 6.667533879981322e-05, 'samples': 22037760, 'steps': 114779, 'loss/train': 1.500217318534851} 08/31/2021 10:00:06 - INFO - __main__ - Step 114781: {'lr': 6.667173075016864e-05, 'samples': 22037952, 'steps': 114780, 'loss/train': 1.2823539972305298} 08/31/2021 10:00:06 - INFO - __main__ - Step 114782: {'lr': 6.666812278312895e-05, 'samples': 22038144, 'steps': 114781, 'loss/train': 0.4578567147254944} 08/31/2021 10:00:07 - INFO - __main__ - Step 114783: {'lr': 6.666451489869585e-05, 'samples': 22038336, 'steps': 114782, 'loss/train': 1.1682125329971313} 08/31/2021 10:00:07 - INFO - __main__ - Step 114784: {'lr': 6.66609070968708e-05, 'samples': 22038528, 'steps': 114783, 'loss/train': 0.7979008555412292} 08/31/2021 10:00:09 - INFO - __main__ - Step 114785: {'lr': 6.665729937765556e-05, 'samples': 22038720, 'steps': 114784, 'loss/train': 1.3528947830200195} 08/31/2021 10:00:09 - INFO - __main__ - Step 114786: {'lr': 6.665369174105169e-05, 'samples': 22038912, 'steps': 114785, 'loss/train': 1.0535415410995483} 08/31/2021 10:00:10 - INFO - __main__ - Step 114787: {'lr': 6.665008418706081e-05, 'samples': 22039104, 'steps': 114786, 'loss/train': 1.4493929147720337} 08/31/2021 10:00:10 - INFO - __main__ - Step 114788: {'lr': 6.664647671568461e-05, 'samples': 22039296, 'steps': 114787, 'loss/train': 0.016496000811457634} 08/31/2021 10:00:11 - INFO - __main__ - Step 114789: {'lr': 6.664286932692464e-05, 'samples': 22039488, 'steps': 114788, 'loss/train': 0.015747081488370895} 08/31/2021 10:00:11 - INFO - __main__ - Step 114790: {'lr': 6.66392620207826e-05, 'samples': 22039680, 'steps': 114789, 'loss/train': 1.1295233964920044} 08/31/2021 10:00:13 - INFO - __main__ - Step 114791: {'lr': 6.663565479726008e-05, 'samples': 22039872, 'steps': 114790, 'loss/train': 0.4041699469089508} 08/31/2021 10:00:13 - INFO - __main__ - Step 114792: {'lr': 6.663204765635869e-05, 'samples': 22040064, 'steps': 114791, 'loss/train': 0.3492989242076874} 08/31/2021 10:00:14 - INFO - __main__ - Step 114793: {'lr': 6.662844059808007e-05, 'samples': 22040256, 'steps': 114792, 'loss/train': 0.01640547625720501} 08/31/2021 10:00:14 - INFO - __main__ - Step 114794: {'lr': 6.662483362242583e-05, 'samples': 22040448, 'steps': 114793, 'loss/train': 0.7006649971008301} 08/31/2021 10:00:14 - INFO - __main__ - Step 114795: {'lr': 6.662122672939764e-05, 'samples': 22040640, 'steps': 114794, 'loss/train': 1.1199380159378052} 08/31/2021 10:00:15 - INFO - __main__ - Step 114796: {'lr': 6.661761991899715e-05, 'samples': 22040832, 'steps': 114795, 'loss/train': 0.7365919947624207} 08/31/2021 10:00:16 - INFO - __main__ - Step 114797: {'lr': 6.661401319122587e-05, 'samples': 22041024, 'steps': 114796, 'loss/train': 1.511726975440979} 08/31/2021 10:00:17 - INFO - __main__ - Step 114798: {'lr': 6.661040654608547e-05, 'samples': 22041216, 'steps': 114797, 'loss/train': 0.8793339729309082} 08/31/2021 10:00:17 - INFO - __main__ - Step 114799: {'lr': 6.660679998357761e-05, 'samples': 22041408, 'steps': 114798, 'loss/train': 0.6204206943511963} 08/31/2021 10:00:17 - INFO - __main__ - Step 114800: {'lr': 6.660319350370386e-05, 'samples': 22041600, 'steps': 114799, 'loss/train': 0.7733238339424133} 08/31/2021 10:00:18 - INFO - __main__ - Step 114801: {'lr': 6.65995871064659e-05, 'samples': 22041792, 'steps': 114800, 'loss/train': 1.3325788974761963} 08/31/2021 10:00:20 - INFO - __main__ - Step 114802: {'lr': 6.659598079186535e-05, 'samples': 22041984, 'steps': 114801, 'loss/train': 1.3160642385482788} 08/31/2021 10:00:20 - INFO - __main__ - Step 114803: {'lr': 6.659237455990383e-05, 'samples': 22042176, 'steps': 114802, 'loss/train': 0.5570529699325562} 08/31/2021 10:00:20 - INFO - __main__ - Step 114804: {'lr': 6.658876841058292e-05, 'samples': 22042368, 'steps': 114803, 'loss/train': 1.0534870624542236} 08/31/2021 10:00:21 - INFO - __main__ - Step 114805: {'lr': 6.65851623439043e-05, 'samples': 22042560, 'steps': 114804, 'loss/train': 0.9231829643249512} 08/31/2021 10:00:21 - INFO - __main__ - Step 114806: {'lr': 6.65815563598696e-05, 'samples': 22042752, 'steps': 114805, 'loss/train': 0.048919301480054855} 08/31/2021 10:00:23 - INFO - __main__ - Step 114807: {'lr': 6.657795045848039e-05, 'samples': 22042944, 'steps': 114806, 'loss/train': 1.577041506767273} 08/31/2021 10:00:23 - INFO - __main__ - Step 114808: {'lr': 6.657434463973833e-05, 'samples': 22043136, 'steps': 114807, 'loss/train': 1.211767315864563} 08/31/2021 10:00:24 - INFO - __main__ - Step 114809: {'lr': 6.657073890364504e-05, 'samples': 22043328, 'steps': 114808, 'loss/train': 0.5285502672195435} 08/31/2021 10:00:24 - INFO - __main__ - Step 114810: {'lr': 6.656713325020219e-05, 'samples': 22043520, 'steps': 114809, 'loss/train': 1.212519884109497} 08/31/2021 10:00:24 - INFO - __main__ - Step 114811: {'lr': 6.656352767941132e-05, 'samples': 22043712, 'steps': 114810, 'loss/train': 1.1509848833084106} 08/31/2021 10:00:25 - INFO - __main__ - Step 114812: {'lr': 6.65599221912741e-05, 'samples': 22043904, 'steps': 114811, 'loss/train': 0.035751648247241974} 08/31/2021 10:00:26 - INFO - __main__ - Step 114813: {'lr': 6.655631678579213e-05, 'samples': 22044096, 'steps': 114812, 'loss/train': 0.04554678499698639} 08/31/2021 10:00:27 - INFO - __main__ - Step 114814: {'lr': 6.655271146296707e-05, 'samples': 22044288, 'steps': 114813, 'loss/train': 1.5492088794708252} 08/31/2021 10:00:27 - INFO - __main__ - Step 114815: {'lr': 6.65491062228005e-05, 'samples': 22044480, 'steps': 114814, 'loss/train': 1.0174527168273926} 08/31/2021 10:00:28 - INFO - __main__ - Step 114816: {'lr': 6.654550106529411e-05, 'samples': 22044672, 'steps': 114815, 'loss/train': 1.2846859693527222} 08/31/2021 10:00:28 - INFO - __main__ - Step 114817: {'lr': 6.654189599044946e-05, 'samples': 22044864, 'steps': 114816, 'loss/train': 1.474352478981018} 08/31/2021 10:00:28 - INFO - __main__ - Step 114818: {'lr': 6.653829099826819e-05, 'samples': 22045056, 'steps': 114817, 'loss/train': 0.6162683963775635} 08/31/2021 10:00:30 - INFO - __main__ - Step 114819: {'lr': 6.653468608875196e-05, 'samples': 22045248, 'steps': 114818, 'loss/train': 1.7043250799179077} 08/31/2021 10:00:30 - INFO - __main__ - Step 114820: {'lr': 6.653108126190235e-05, 'samples': 22045440, 'steps': 114819, 'loss/train': 1.1892703771591187} 08/31/2021 10:00:30 - INFO - __main__ - Step 114821: {'lr': 6.652747651772104e-05, 'samples': 22045632, 'steps': 114820, 'loss/train': 0.239518404006958} 08/31/2021 10:00:31 - INFO - __main__ - Step 114822: {'lr': 6.652387185620956e-05, 'samples': 22045824, 'steps': 114821, 'loss/train': 1.5250355005264282} 08/31/2021 10:00:31 - INFO - __main__ - Step 114823: {'lr': 6.65202672773697e-05, 'samples': 22046016, 'steps': 114822, 'loss/train': 0.8801324963569641} 08/31/2021 10:00:33 - INFO - __main__ - Step 114824: {'lr': 6.651666278120291e-05, 'samples': 22046208, 'steps': 114823, 'loss/train': 0.7734147310256958} 08/31/2021 10:00:33 - INFO - __main__ - Step 114825: {'lr': 6.651305836771087e-05, 'samples': 22046400, 'steps': 114824, 'loss/train': 0.9148717522621155} 08/31/2021 10:00:33 - INFO - __main__ - Step 114826: {'lr': 6.650945403689521e-05, 'samples': 22046592, 'steps': 114825, 'loss/train': 1.3902475833892822} 08/31/2021 10:00:34 - INFO - __main__ - Step 114827: {'lr': 6.650584978875757e-05, 'samples': 22046784, 'steps': 114826, 'loss/train': 1.2338100671768188} 08/31/2021 10:00:34 - INFO - __main__ - Step 114828: {'lr': 6.650224562329957e-05, 'samples': 22046976, 'steps': 114827, 'loss/train': 1.3992575407028198} 08/31/2021 10:00:36 - INFO - __main__ - Step 114829: {'lr': 6.649864154052279e-05, 'samples': 22047168, 'steps': 114828, 'loss/train': 1.379459261894226} 08/31/2021 10:00:37 - INFO - __main__ - Step 114830: {'lr': 6.649503754042893e-05, 'samples': 22047360, 'steps': 114829, 'loss/train': 1.2319214344024658} 08/31/2021 10:00:37 - INFO - __main__ - Step 114831: {'lr': 6.649143362301954e-05, 'samples': 22047552, 'steps': 114830, 'loss/train': 1.0470634698867798} 08/31/2021 10:00:37 - INFO - __main__ - Step 114832: {'lr': 6.648782978829632e-05, 'samples': 22047744, 'steps': 114831, 'loss/train': 1.0879261493682861} 08/31/2021 10:00:38 - INFO - __main__ - Step 114833: {'lr': 6.64842260362608e-05, 'samples': 22047936, 'steps': 114832, 'loss/train': 0.7164005041122437} 08/31/2021 10:00:39 - INFO - __main__ - Step 114834: {'lr': 6.64806223669147e-05, 'samples': 22048128, 'steps': 114833, 'loss/train': 2.6000125408172607} 08/31/2021 10:00:40 - INFO - __main__ - Step 114835: {'lr': 6.647701878025958e-05, 'samples': 22048320, 'steps': 114834, 'loss/train': 1.0828763246536255} 08/31/2021 10:00:40 - INFO - __main__ - Step 114836: {'lr': 6.647341527629707e-05, 'samples': 22048512, 'steps': 114835, 'loss/train': 1.2029014825820923} 08/31/2021 10:00:40 - INFO - __main__ - Step 114837: {'lr': 6.646981185502893e-05, 'samples': 22048704, 'steps': 114836, 'loss/train': 0.664188802242279} 08/31/2021 10:00:41 - INFO - __main__ - Step 114838: {'lr': 6.646620851645654e-05, 'samples': 22048896, 'steps': 114837, 'loss/train': 1.3691835403442383} 08/31/2021 10:00:41 - INFO - __main__ - Step 114839: {'lr': 6.646260526058167e-05, 'samples': 22049088, 'steps': 114838, 'loss/train': 1.2694865465164185} 08/31/2021 10:00:43 - INFO - __main__ - Step 114840: {'lr': 6.645900208740591e-05, 'samples': 22049280, 'steps': 114839, 'loss/train': 1.2913974523544312} 08/31/2021 10:00:43 - INFO - __main__ - Step 114841: {'lr': 6.645539899693087e-05, 'samples': 22049472, 'steps': 114840, 'loss/train': 0.4141949415206909} 08/31/2021 10:00:43 - INFO - __main__ - Step 114842: {'lr': 6.64517959891582e-05, 'samples': 22049664, 'steps': 114841, 'loss/train': 1.6494638919830322} 08/31/2021 10:00:44 - INFO - __main__ - Step 114843: {'lr': 6.644819306408956e-05, 'samples': 22049856, 'steps': 114842, 'loss/train': 1.3915382623672485} 08/31/2021 10:00:44 - INFO - __main__ - Step 114844: {'lr': 6.64445902217265e-05, 'samples': 22050048, 'steps': 114843, 'loss/train': 1.0058867931365967} 08/31/2021 10:00:46 - INFO - __main__ - Step 114845: {'lr': 6.644098746207067e-05, 'samples': 22050240, 'steps': 114844, 'loss/train': 1.5593146085739136} 08/31/2021 10:00:47 - INFO - __main__ - Step 114846: {'lr': 6.64373847851237e-05, 'samples': 22050432, 'steps': 114845, 'loss/train': 1.101178765296936} 08/31/2021 10:00:47 - INFO - __main__ - Step 114847: {'lr': 6.643378219088722e-05, 'samples': 22050624, 'steps': 114846, 'loss/train': 5.229498863220215} 08/31/2021 10:00:48 - INFO - __main__ - Step 114848: {'lr': 6.643017967936285e-05, 'samples': 22050816, 'steps': 114847, 'loss/train': 4.934423446655273} 08/31/2021 10:00:48 - INFO - __main__ - Step 114849: {'lr': 6.642657725055221e-05, 'samples': 22051008, 'steps': 114848, 'loss/train': 2.9011361598968506} 08/31/2021 10:00:48 - INFO - __main__ - Step 114850: {'lr': 6.642297490445698e-05, 'samples': 22051200, 'steps': 114849, 'loss/train': 0.8963510990142822} 08/31/2021 10:00:49 - INFO - __main__ - Step 114851: {'lr': 6.641937264107867e-05, 'samples': 22051392, 'steps': 114850, 'loss/train': 1.2580187320709229} 08/31/2021 10:00:50 - INFO - __main__ - Step 114852: {'lr': 6.641577046041894e-05, 'samples': 22051584, 'steps': 114851, 'loss/train': 1.5174674987792969} 08/31/2021 10:00:51 - INFO - __main__ - Step 114853: {'lr': 6.641216836247946e-05, 'samples': 22051776, 'steps': 114852, 'loss/train': 0.9809154868125916} 08/31/2021 10:00:51 - INFO - __main__ - Step 114854: {'lr': 6.640856634726178e-05, 'samples': 22051968, 'steps': 114853, 'loss/train': 1.3484703302383423} 08/31/2021 10:00:51 - INFO - __main__ - Step 114855: {'lr': 6.640496441476759e-05, 'samples': 22052160, 'steps': 114854, 'loss/train': 0.16241607069969177} 08/31/2021 10:00:52 - INFO - __main__ - Step 114856: {'lr': 6.640136256499848e-05, 'samples': 22052352, 'steps': 114855, 'loss/train': 1.060295820236206} 08/31/2021 10:00:52 - INFO - __main__ - Step 114857: {'lr': 6.639776079795612e-05, 'samples': 22052544, 'steps': 114856, 'loss/train': 1.3666731119155884} 08/31/2021 10:00:54 - INFO - __main__ - Step 114858: {'lr': 6.639415911364205e-05, 'samples': 22052736, 'steps': 114857, 'loss/train': 1.6374658346176147} 08/31/2021 10:00:54 - INFO - __main__ - Step 114859: {'lr': 6.639055751205797e-05, 'samples': 22052928, 'steps': 114858, 'loss/train': 0.4862406849861145} 08/31/2021 10:00:55 - INFO - __main__ - Step 114860: {'lr': 6.638695599320547e-05, 'samples': 22053120, 'steps': 114859, 'loss/train': 1.1633682250976562} 08/31/2021 10:00:55 - INFO - __main__ - Step 114861: {'lr': 6.638335455708613e-05, 'samples': 22053312, 'steps': 114860, 'loss/train': 1.5612820386886597} 08/31/2021 10:00:55 - INFO - __main__ - Step 114862: {'lr': 6.637975320370165e-05, 'samples': 22053504, 'steps': 114861, 'loss/train': 2.1205780506134033} 08/31/2021 10:00:57 - INFO - __main__ - Step 114863: {'lr': 6.637615193305362e-05, 'samples': 22053696, 'steps': 114862, 'loss/train': 1.2660735845565796} 08/31/2021 10:00:57 - INFO - __main__ - Step 114864: {'lr': 6.637255074514375e-05, 'samples': 22053888, 'steps': 114863, 'loss/train': 1.0577211380004883} 08/31/2021 10:00:58 - INFO - __main__ - Step 114865: {'lr': 6.636894963997348e-05, 'samples': 22054080, 'steps': 114864, 'loss/train': 0.5840340256690979} 08/31/2021 10:00:58 - INFO - __main__ - Step 114866: {'lr': 6.636534861754453e-05, 'samples': 22054272, 'steps': 114865, 'loss/train': 1.4203938245773315} 08/31/2021 10:00:58 - INFO - __main__ - Step 114867: {'lr': 6.636174767785855e-05, 'samples': 22054464, 'steps': 114866, 'loss/train': 0.5323039889335632} 08/31/2021 10:01:00 - INFO - __main__ - Step 114868: {'lr': 6.63581468209171e-05, 'samples': 22054656, 'steps': 114867, 'loss/train': 1.559794306755066} 08/31/2021 10:01:00 - INFO - __main__ - Step 114869: {'lr': 6.635454604672183e-05, 'samples': 22054848, 'steps': 114868, 'loss/train': 1.6516273021697998} 08/31/2021 10:01:01 - INFO - __main__ - Step 114870: {'lr': 6.63509453552744e-05, 'samples': 22055040, 'steps': 114869, 'loss/train': 1.3220624923706055} 08/31/2021 10:01:01 - INFO - __main__ - Step 114871: {'lr': 6.634734474657636e-05, 'samples': 22055232, 'steps': 114870, 'loss/train': 1.477447271347046} 08/31/2021 10:01:01 - INFO - __main__ - Step 114872: {'lr': 6.634374422062939e-05, 'samples': 22055424, 'steps': 114871, 'loss/train': 1.3217933177947998} 08/31/2021 10:01:03 - INFO - __main__ - Step 114873: {'lr': 6.634014377743511e-05, 'samples': 22055616, 'steps': 114872, 'loss/train': 1.0100343227386475} 08/31/2021 10:01:04 - INFO - __main__ - Step 114874: {'lr': 6.63365434169951e-05, 'samples': 22055808, 'steps': 114873, 'loss/train': 0.03632393106818199} 08/31/2021 10:01:04 - INFO - __main__ - Step 114875: {'lr': 6.633294313931104e-05, 'samples': 22056000, 'steps': 114874, 'loss/train': 1.1316759586334229} 08/31/2021 10:01:04 - INFO - __main__ - Step 114876: {'lr': 6.63293429443845e-05, 'samples': 22056192, 'steps': 114875, 'loss/train': 0.25343403220176697} 08/31/2021 10:01:05 - INFO - __main__ - Step 114877: {'lr': 6.63257428322172e-05, 'samples': 22056384, 'steps': 114876, 'loss/train': 0.6685957908630371} 08/31/2021 10:01:06 - INFO - __main__ - Step 114878: {'lr': 6.632214280281063e-05, 'samples': 22056576, 'steps': 114877, 'loss/train': 0.9177900552749634} 08/31/2021 10:01:07 - INFO - __main__ - Step 114879: {'lr': 6.631854285616646e-05, 'samples': 22056768, 'steps': 114878, 'loss/train': 0.3932521641254425} 08/31/2021 10:01:07 - INFO - __main__ - Step 114880: {'lr': 6.63149429922863e-05, 'samples': 22056960, 'steps': 114879, 'loss/train': 0.1324402391910553} 08/31/2021 10:01:07 - INFO - __main__ - Step 114881: {'lr': 6.63113432111718e-05, 'samples': 22057152, 'steps': 114880, 'loss/train': 0.9268788695335388} 08/31/2021 10:01:08 - INFO - __main__ - Step 114882: {'lr': 6.630774351282459e-05, 'samples': 22057344, 'steps': 114881, 'loss/train': 1.4648348093032837} 08/31/2021 10:01:08 - INFO - __main__ - Step 114883: {'lr': 6.630414389724626e-05, 'samples': 22057536, 'steps': 114882, 'loss/train': 1.599849820137024} 08/31/2021 10:01:09 - INFO - __main__ - Step 114884: {'lr': 6.630054436443847e-05, 'samples': 22057728, 'steps': 114883, 'loss/train': 0.7663267850875854} 08/31/2021 10:01:10 - INFO - __main__ - Step 114885: {'lr': 6.62969449144028e-05, 'samples': 22057920, 'steps': 114884, 'loss/train': 1.2215967178344727} 08/31/2021 10:01:10 - INFO - __main__ - Step 114886: {'lr': 6.629334554714089e-05, 'samples': 22058112, 'steps': 114885, 'loss/train': 0.6662204265594482} 08/31/2021 10:01:11 - INFO - __main__ - Step 114887: {'lr': 6.628974626265439e-05, 'samples': 22058304, 'steps': 114886, 'loss/train': 1.1302142143249512} 08/31/2021 10:01:11 - INFO - __main__ - Step 114888: {'lr': 6.628614706094488e-05, 'samples': 22058496, 'steps': 114887, 'loss/train': 0.8825684189796448} 08/31/2021 10:01:14 - INFO - __main__ - Step 114889: {'lr': 6.628254794201399e-05, 'samples': 22058688, 'steps': 114888, 'loss/train': 1.5310856103897095} 08/31/2021 10:01:14 - INFO - __main__ - Step 114890: {'lr': 6.627894890586342e-05, 'samples': 22058880, 'steps': 114889, 'loss/train': 0.24738013744354248} 08/31/2021 10:01:15 - INFO - __main__ - Step 114891: {'lr': 6.627534995249465e-05, 'samples': 22059072, 'steps': 114890, 'loss/train': 0.27501505613327026} 08/31/2021 10:01:15 - INFO - __main__ - Step 114892: {'lr': 6.627175108190938e-05, 'samples': 22059264, 'steps': 114891, 'loss/train': 1.312008023262024} 08/31/2021 10:01:15 - INFO - __main__ - Step 114893: {'lr': 6.62681522941092e-05, 'samples': 22059456, 'steps': 114892, 'loss/train': 1.4398813247680664} 08/31/2021 10:01:16 - INFO - __main__ - Step 114894: {'lr': 6.62645535890958e-05, 'samples': 22059648, 'steps': 114893, 'loss/train': 1.472365379333496} 08/31/2021 10:01:17 - INFO - __main__ - Step 114895: {'lr': 6.626095496687074e-05, 'samples': 22059840, 'steps': 114894, 'loss/train': 1.3618072271347046} 08/31/2021 10:01:18 - INFO - __main__ - Step 114896: {'lr': 6.625735642743563e-05, 'samples': 22060032, 'steps': 114895, 'loss/train': 0.9932733774185181} 08/31/2021 10:01:18 - INFO - __main__ - Step 114897: {'lr': 6.625375797079213e-05, 'samples': 22060224, 'steps': 114896, 'loss/train': 1.05419921875} 08/31/2021 10:01:18 - INFO - __main__ - Step 114898: {'lr': 6.625015959694189e-05, 'samples': 22060416, 'steps': 114897, 'loss/train': 1.0472482442855835} 08/31/2021 10:01:19 - INFO - __main__ - Step 114899: {'lr': 6.624656130588644e-05, 'samples': 22060608, 'steps': 114898, 'loss/train': 0.5168076157569885} 08/31/2021 10:01:19 - INFO - __main__ - Step 114900: {'lr': 6.624296309762748e-05, 'samples': 22060800, 'steps': 114899, 'loss/train': 0.4448138475418091} 08/31/2021 10:01:21 - INFO - __main__ - Step 114901: {'lr': 6.623936497216663e-05, 'samples': 22060992, 'steps': 114900, 'loss/train': 1.5860482454299927} 08/31/2021 10:01:21 - INFO - __main__ - Step 114902: {'lr': 6.623576692950545e-05, 'samples': 22061184, 'steps': 114901, 'loss/train': 0.45406055450439453} 08/31/2021 10:01:21 - INFO - __main__ - Step 114903: {'lr': 6.623216896964559e-05, 'samples': 22061376, 'steps': 114902, 'loss/train': 0.7715733647346497} 08/31/2021 10:01:22 - INFO - __main__ - Step 114904: {'lr': 6.622857109258879e-05, 'samples': 22061568, 'steps': 114903, 'loss/train': 1.2287315130233765} 08/31/2021 10:01:22 - INFO - __main__ - Step 114905: {'lr': 6.622497329833647e-05, 'samples': 22061760, 'steps': 114904, 'loss/train': 0.8221083283424377} 08/31/2021 10:01:24 - INFO - __main__ - Step 114906: {'lr': 6.622137558689031e-05, 'samples': 22061952, 'steps': 114905, 'loss/train': 1.4138343334197998} 08/31/2021 10:01:24 - INFO - __main__ - Step 114907: {'lr': 6.621777795825201e-05, 'samples': 22062144, 'steps': 114906, 'loss/train': 0.6901146173477173} 08/31/2021 10:01:24 - INFO - __main__ - Step 114908: {'lr': 6.62141804124231e-05, 'samples': 22062336, 'steps': 114907, 'loss/train': 0.7369309663772583} 08/31/2021 10:01:25 - INFO - __main__ - Step 114909: {'lr': 6.621058294940529e-05, 'samples': 22062528, 'steps': 114908, 'loss/train': 1.4234706163406372} 08/31/2021 10:01:25 - INFO - __main__ - Step 114910: {'lr': 6.620698556920013e-05, 'samples': 22062720, 'steps': 114909, 'loss/train': 0.9370840191841125} 08/31/2021 10:01:27 - INFO - __main__ - Step 114911: {'lr': 6.620338827180928e-05, 'samples': 22062912, 'steps': 114910, 'loss/train': 1.1567871570587158} 08/31/2021 10:01:27 - INFO - __main__ - Step 114912: {'lr': 6.619979105723433e-05, 'samples': 22063104, 'steps': 114911, 'loss/train': 1.904240369796753} 08/31/2021 10:01:28 - INFO - __main__ - Step 114913: {'lr': 6.619619392547693e-05, 'samples': 22063296, 'steps': 114912, 'loss/train': 1.528476357460022} 08/31/2021 10:01:28 - INFO - __main__ - Step 114914: {'lr': 6.619259687653867e-05, 'samples': 22063488, 'steps': 114913, 'loss/train': 0.22867539525032043} 08/31/2021 10:01:28 - INFO - __main__ - Step 114915: {'lr': 6.618899991042121e-05, 'samples': 22063680, 'steps': 114914, 'loss/train': 0.8766538500785828} 08/31/2021 10:01:30 - INFO - __main__ - Step 114916: {'lr': 6.618540302712614e-05, 'samples': 22063872, 'steps': 114915, 'loss/train': 0.8724090456962585} 08/31/2021 10:01:30 - INFO - __main__ - Step 114917: {'lr': 6.618180622665517e-05, 'samples': 22064064, 'steps': 114916, 'loss/train': 1.5094680786132812} 08/31/2021 10:01:31 - INFO - __main__ - Step 114918: {'lr': 6.617820950900977e-05, 'samples': 22064256, 'steps': 114917, 'loss/train': 1.2867306470870972} 08/31/2021 10:01:31 - INFO - __main__ - Step 114919: {'lr': 6.617461287419163e-05, 'samples': 22064448, 'steps': 114918, 'loss/train': 1.5036510229110718} 08/31/2021 10:01:31 - INFO - __main__ - Step 114920: {'lr': 6.617101632220238e-05, 'samples': 22064640, 'steps': 114919, 'loss/train': 1.70707106590271} 08/31/2021 10:01:33 - INFO - __main__ - Step 114921: {'lr': 6.616741985304361e-05, 'samples': 22064832, 'steps': 114920, 'loss/train': 0.9491026997566223} 08/31/2021 10:01:33 - INFO - __main__ - Step 114922: {'lr': 6.616382346671698e-05, 'samples': 22065024, 'steps': 114921, 'loss/train': 1.3229211568832397} 08/31/2021 10:01:34 - INFO - __main__ - Step 114923: {'lr': 6.61602271632241e-05, 'samples': 22065216, 'steps': 114922, 'loss/train': 0.7176868319511414} 08/31/2021 10:01:34 - INFO - __main__ - Step 114924: {'lr': 6.615663094256658e-05, 'samples': 22065408, 'steps': 114923, 'loss/train': 1.4330309629440308} 08/31/2021 10:01:34 - INFO - __main__ - Step 114925: {'lr': 6.615303480474601e-05, 'samples': 22065600, 'steps': 114924, 'loss/train': 1.2462633848190308} 08/31/2021 10:01:36 - INFO - __main__ - Step 114926: {'lr': 6.614943874976409e-05, 'samples': 22065792, 'steps': 114925, 'loss/train': 1.4684978723526} 08/31/2021 10:01:36 - INFO - __main__ - Step 114927: {'lr': 6.61458427776224e-05, 'samples': 22065984, 'steps': 114926, 'loss/train': 0.5398984551429749} 08/31/2021 10:01:37 - INFO - __main__ - Step 114928: {'lr': 6.614224688832255e-05, 'samples': 22066176, 'steps': 114927, 'loss/train': 1.4310696125030518} 08/31/2021 10:01:37 - INFO - __main__ - Step 114929: {'lr': 6.613865108186615e-05, 'samples': 22066368, 'steps': 114928, 'loss/train': 1.1532175540924072} 08/31/2021 10:01:37 - INFO - __main__ - Step 114930: {'lr': 6.613505535825485e-05, 'samples': 22066560, 'steps': 114929, 'loss/train': 1.7010315656661987} 08/31/2021 10:01:38 - INFO - __main__ - Step 114931: {'lr': 6.613145971749029e-05, 'samples': 22066752, 'steps': 114930, 'loss/train': 1.2668029069900513} 08/31/2021 10:01:39 - INFO - __main__ - Step 114932: {'lr': 6.612786415957403e-05, 'samples': 22066944, 'steps': 114931, 'loss/train': 0.38093191385269165} 08/31/2021 10:01:40 - INFO - __main__ - Step 114933: {'lr': 6.612426868450771e-05, 'samples': 22067136, 'steps': 114932, 'loss/train': 1.3594386577606201} 08/31/2021 10:01:40 - INFO - __main__ - Step 114934: {'lr': 6.612067329229296e-05, 'samples': 22067328, 'steps': 114933, 'loss/train': 0.3142540156841278} 08/31/2021 10:01:40 - INFO - __main__ - Step 114935: {'lr': 6.611707798293137e-05, 'samples': 22067520, 'steps': 114934, 'loss/train': 1.2424014806747437} 08/31/2021 10:01:41 - INFO - __main__ - Step 114936: {'lr': 6.611348275642462e-05, 'samples': 22067712, 'steps': 114935, 'loss/train': 1.1235874891281128} 08/31/2021 10:01:42 - INFO - __main__ - Step 114937: {'lr': 6.610988761277428e-05, 'samples': 22067904, 'steps': 114936, 'loss/train': 0.6748530268669128} 08/31/2021 10:01:43 - INFO - __main__ - Step 114938: {'lr': 6.610629255198197e-05, 'samples': 22068096, 'steps': 114937, 'loss/train': 0.7704341411590576} 08/31/2021 10:01:43 - INFO - __main__ - Step 114939: {'lr': 6.610269757404936e-05, 'samples': 22068288, 'steps': 114938, 'loss/train': 1.0945507287979126} 08/31/2021 10:01:43 - INFO - __main__ - Step 114940: {'lr': 6.609910267897804e-05, 'samples': 22068480, 'steps': 114939, 'loss/train': 0.6674624085426331} 08/31/2021 10:01:44 - INFO - __main__ - Step 114941: {'lr': 6.60955078667696e-05, 'samples': 22068672, 'steps': 114940, 'loss/train': 0.9133973121643066} 08/31/2021 10:01:46 - INFO - __main__ - Step 114942: {'lr': 6.609191313742569e-05, 'samples': 22068864, 'steps': 114941, 'loss/train': 0.3208983242511749} 08/31/2021 10:01:46 - INFO - __main__ - Step 114943: {'lr': 6.608831849094792e-05, 'samples': 22069056, 'steps': 114942, 'loss/train': 0.9757035970687866} 08/31/2021 10:01:47 - INFO - __main__ - Step 114944: {'lr': 6.608472392733802e-05, 'samples': 22069248, 'steps': 114943, 'loss/train': 1.0471336841583252} 08/31/2021 10:01:47 - INFO - __main__ - Step 114945: {'lr': 6.608112944659741e-05, 'samples': 22069440, 'steps': 114944, 'loss/train': 0.030636334791779518} 08/31/2021 10:01:47 - INFO - __main__ - Step 114946: {'lr': 6.607753504872783e-05, 'samples': 22069632, 'steps': 114945, 'loss/train': 1.0938775539398193} 08/31/2021 10:01:49 - INFO - __main__ - Step 114947: {'lr': 6.607394073373083e-05, 'samples': 22069824, 'steps': 114946, 'loss/train': 1.1598793268203735} 08/31/2021 10:01:50 - INFO - __main__ - Step 114948: {'lr': 6.60703465016081e-05, 'samples': 22070016, 'steps': 114947, 'loss/train': 3.3933587074279785} 08/31/2021 10:01:50 - INFO - __main__ - Step 114949: {'lr': 6.606675235236122e-05, 'samples': 22070208, 'steps': 114948, 'loss/train': 0.5998641848564148} 08/31/2021 10:01:51 - INFO - __main__ - Step 114950: {'lr': 6.606315828599185e-05, 'samples': 22070400, 'steps': 114949, 'loss/train': 0.8609646558761597} 08/31/2021 10:01:51 - INFO - __main__ - Step 114951: {'lr': 6.605956430250156e-05, 'samples': 22070592, 'steps': 114950, 'loss/train': 0.5808660984039307} 08/31/2021 10:01:51 - INFO - __main__ - Step 114952: {'lr': 6.605597040189201e-05, 'samples': 22070784, 'steps': 114951, 'loss/train': 2.70774507522583} 08/31/2021 10:01:53 - INFO - __main__ - Step 114953: {'lr': 6.60523765841648e-05, 'samples': 22070976, 'steps': 114952, 'loss/train': 2.0595614910125732} 08/31/2021 10:01:53 - INFO - __main__ - Step 114954: {'lr': 6.604878284932153e-05, 'samples': 22071168, 'steps': 114953, 'loss/train': 1.1199461221694946} 08/31/2021 10:01:54 - INFO - __main__ - Step 114955: {'lr': 6.604518919736385e-05, 'samples': 22071360, 'steps': 114954, 'loss/train': 0.8689873814582825} 08/31/2021 10:01:54 - INFO - __main__ - Step 114956: {'lr': 6.604159562829338e-05, 'samples': 22071552, 'steps': 114955, 'loss/train': 1.2118955850601196} 08/31/2021 10:01:54 - INFO - __main__ - Step 114957: {'lr': 6.60380021421117e-05, 'samples': 22071744, 'steps': 114956, 'loss/train': 1.106235384941101} 08/31/2021 10:01:56 - INFO - __main__ - Step 114958: {'lr': 6.603440873882055e-05, 'samples': 22071936, 'steps': 114957, 'loss/train': 1.1833980083465576} 08/31/2021 10:01:56 - INFO - __main__ - Step 114959: {'lr': 6.603081541842137e-05, 'samples': 22072128, 'steps': 114958, 'loss/train': 1.0696499347686768} 08/31/2021 10:01:57 - INFO - __main__ - Step 114960: {'lr': 6.602722218091589e-05, 'samples': 22072320, 'steps': 114959, 'loss/train': 1.3028719425201416} 08/31/2021 10:01:57 - INFO - __main__ - Step 114961: {'lr': 6.602362902630571e-05, 'samples': 22072512, 'steps': 114960, 'loss/train': 0.8467510342597961} 08/31/2021 10:01:57 - INFO - __main__ - Step 114962: {'lr': 6.60200359545924e-05, 'samples': 22072704, 'steps': 114961, 'loss/train': 1.55171537399292} 08/31/2021 10:01:59 - INFO - __main__ - Step 114963: {'lr': 6.601644296577766e-05, 'samples': 22072896, 'steps': 114962, 'loss/train': 1.2280023097991943} 08/31/2021 10:01:59 - INFO - __main__ - Step 114964: {'lr': 6.601285005986307e-05, 'samples': 22073088, 'steps': 114963, 'loss/train': 0.9142619967460632} 08/31/2021 10:02:00 - INFO - __main__ - Step 114965: {'lr': 6.600925723685025e-05, 'samples': 22073280, 'steps': 114964, 'loss/train': 1.043441653251648} 08/31/2021 10:02:00 - INFO - __main__ - Step 114966: {'lr': 6.600566449674081e-05, 'samples': 22073472, 'steps': 114965, 'loss/train': 0.9501643776893616} 08/31/2021 10:02:00 - INFO - __main__ - Step 114967: {'lr': 6.600207183953638e-05, 'samples': 22073664, 'steps': 114966, 'loss/train': 1.561726450920105} 08/31/2021 10:02:03 - INFO - __main__ - Step 114968: {'lr': 6.599847926523855e-05, 'samples': 22073856, 'steps': 114967, 'loss/train': 0.4275151789188385} 08/31/2021 10:02:03 - INFO - __main__ - Step 114969: {'lr': 6.599488677384902e-05, 'samples': 22074048, 'steps': 114968, 'loss/train': 1.56001877784729} 08/31/2021 10:02:04 - INFO - __main__ - Step 114970: {'lr': 6.599129436536933e-05, 'samples': 22074240, 'steps': 114969, 'loss/train': 1.138654351234436} 08/31/2021 10:02:04 - INFO - __main__ - Step 114971: {'lr': 6.598770203980117e-05, 'samples': 22074432, 'steps': 114970, 'loss/train': 0.7883212566375732} 08/31/2021 10:02:04 - INFO - __main__ - Step 114972: {'lr': 6.598410979714609e-05, 'samples': 22074624, 'steps': 114971, 'loss/train': 1.2327800989151} 08/31/2021 10:02:05 - INFO - __main__ - Step 114973: {'lr': 6.59805176374057e-05, 'samples': 22074816, 'steps': 114972, 'loss/train': 1.320041537284851} 08/31/2021 10:02:05 - INFO - __main__ - Step 114974: {'lr': 6.597692556058163e-05, 'samples': 22075008, 'steps': 114973, 'loss/train': 1.041234016418457} 08/31/2021 10:02:06 - INFO - __main__ - Step 114975: {'lr': 6.597333356667557e-05, 'samples': 22075200, 'steps': 114974, 'loss/train': 2.1675379276275635} 08/31/2021 10:02:07 - INFO - __main__ - Step 114976: {'lr': 6.596974165568903e-05, 'samples': 22075392, 'steps': 114975, 'loss/train': 0.9624523520469666} 08/31/2021 10:02:07 - INFO - __main__ - Step 114977: {'lr': 6.596614982762372e-05, 'samples': 22075584, 'steps': 114976, 'loss/train': 1.2498070001602173} 08/31/2021 10:02:08 - INFO - __main__ - Step 114978: {'lr': 6.596255808248122e-05, 'samples': 22075776, 'steps': 114977, 'loss/train': 0.5243718028068542} 08/31/2021 10:02:08 - INFO - __main__ - Step 114979: {'lr': 6.595896642026315e-05, 'samples': 22075968, 'steps': 114978, 'loss/train': 1.7261550426483154} 08/31/2021 10:02:10 - INFO - __main__ - Step 114980: {'lr': 6.595537484097112e-05, 'samples': 22076160, 'steps': 114979, 'loss/train': 1.4663714170455933} 08/31/2021 10:02:10 - INFO - __main__ - Step 114981: {'lr': 6.595178334460674e-05, 'samples': 22076352, 'steps': 114980, 'loss/train': 1.9324753284454346} 08/31/2021 10:02:10 - INFO - __main__ - Step 114982: {'lr': 6.594819193117168e-05, 'samples': 22076544, 'steps': 114981, 'loss/train': 1.2859303951263428} 08/31/2021 10:02:11 - INFO - __main__ - Step 114983: {'lr': 6.594460060066754e-05, 'samples': 22076736, 'steps': 114982, 'loss/train': 1.2253810167312622} 08/31/2021 10:02:11 - INFO - __main__ - Step 114984: {'lr': 6.594100935309596e-05, 'samples': 22076928, 'steps': 114983, 'loss/train': 1.0389535427093506} 08/31/2021 10:02:13 - INFO - __main__ - Step 114985: {'lr': 6.593741818845845e-05, 'samples': 22077120, 'steps': 114984, 'loss/train': 1.3416171073913574} 08/31/2021 10:02:13 - INFO - __main__ - Step 114986: {'lr': 6.593382710675672e-05, 'samples': 22077312, 'steps': 114985, 'loss/train': 0.6355152726173401} 08/31/2021 10:02:13 - INFO - __main__ - Step 114987: {'lr': 6.593023610799234e-05, 'samples': 22077504, 'steps': 114986, 'loss/train': 1.1217708587646484} 08/31/2021 10:02:14 - INFO - __main__ - Step 114988: {'lr': 6.592664519216698e-05, 'samples': 22077696, 'steps': 114987, 'loss/train': 1.3793271780014038} 08/31/2021 10:02:14 - INFO - __main__ - Step 114989: {'lr': 6.592305435928222e-05, 'samples': 22077888, 'steps': 114988, 'loss/train': 1.2355304956436157} 08/31/2021 10:02:16 - INFO - __main__ - Step 114990: {'lr': 6.59194636093397e-05, 'samples': 22078080, 'steps': 114989, 'loss/train': 0.6454587578773499} 08/31/2021 10:02:16 - INFO - __main__ - Step 114991: {'lr': 6.591587294234102e-05, 'samples': 22078272, 'steps': 114990, 'loss/train': 1.4552652835845947} 08/31/2021 10:02:17 - INFO - __main__ - Step 114992: {'lr': 6.591228235828781e-05, 'samples': 22078464, 'steps': 114991, 'loss/train': 0.8314013481140137} 08/31/2021 10:02:17 - INFO - __main__ - Step 114993: {'lr': 6.590869185718169e-05, 'samples': 22078656, 'steps': 114992, 'loss/train': 1.312213659286499} 08/31/2021 10:02:17 - INFO - __main__ - Step 114994: {'lr': 6.590510143902425e-05, 'samples': 22078848, 'steps': 114993, 'loss/train': 1.5983015298843384} 08/31/2021 10:02:18 - INFO - __main__ - Step 114995: {'lr': 6.590151110381723e-05, 'samples': 22079040, 'steps': 114994, 'loss/train': 0.9208917021751404} 08/31/2021 10:02:19 - INFO - __main__ - Step 114996: {'lr': 6.589792085156207e-05, 'samples': 22079232, 'steps': 114995, 'loss/train': 0.8855979442596436} 08/31/2021 10:02:20 - INFO - __main__ - Step 114997: {'lr': 6.589433068226047e-05, 'samples': 22079424, 'steps': 114996, 'loss/train': 0.9545351266860962} 08/31/2021 10:02:20 - INFO - __main__ - Step 114998: {'lr': 6.589074059591404e-05, 'samples': 22079616, 'steps': 114997, 'loss/train': 1.412163257598877} 08/31/2021 10:02:20 - INFO - __main__ - Step 114999: {'lr': 6.58871505925244e-05, 'samples': 22079808, 'steps': 114998, 'loss/train': 0.5385236740112305} 08/31/2021 10:02:21 - INFO - __main__ - Step 115000: {'lr': 6.588356067209316e-05, 'samples': 22080000, 'steps': 114999, 'loss/train': 1.204641580581665} 08/31/2021 10:02:23 - INFO - __main__ - Step 115001: {'lr': 6.587997083462196e-05, 'samples': 22080192, 'steps': 115000, 'loss/train': 0.20506802201271057} 08/31/2021 10:02:23 - INFO - __main__ - Step 115002: {'lr': 6.58763810801124e-05, 'samples': 22080384, 'steps': 115001, 'loss/train': 0.82442706823349} 08/31/2021 10:02:24 - INFO - __main__ - Step 115003: {'lr': 6.587279140856609e-05, 'samples': 22080576, 'steps': 115002, 'loss/train': 0.8325100541114807} 08/31/2021 10:02:24 - INFO - __main__ - Step 115004: {'lr': 6.586920181998468e-05, 'samples': 22080768, 'steps': 115003, 'loss/train': 0.025934748351573944} 08/31/2021 10:02:24 - INFO - __main__ - Step 115005: {'lr': 6.586561231436975e-05, 'samples': 22080960, 'steps': 115004, 'loss/train': 2.8029167652130127} 08/31/2021 10:02:26 - INFO - __main__ - Step 115006: {'lr': 6.5862022891723e-05, 'samples': 22081152, 'steps': 115005, 'loss/train': 0.7094994783401489} 08/31/2021 10:02:26 - INFO - __main__ - Step 115007: {'lr': 6.585843355204593e-05, 'samples': 22081344, 'steps': 115006, 'loss/train': 1.5469224452972412} 08/31/2021 10:02:27 - INFO - __main__ - Step 115008: {'lr': 6.58548442953402e-05, 'samples': 22081536, 'steps': 115007, 'loss/train': 0.31182676553726196} 08/31/2021 10:02:27 - INFO - __main__ - Step 115009: {'lr': 6.585125512160742e-05, 'samples': 22081728, 'steps': 115008, 'loss/train': 0.6719648241996765} 08/31/2021 10:02:27 - INFO - __main__ - Step 115010: {'lr': 6.584766603084924e-05, 'samples': 22081920, 'steps': 115009, 'loss/train': 0.9242329001426697} 08/31/2021 10:02:29 - INFO - __main__ - Step 115011: {'lr': 6.584407702306727e-05, 'samples': 22082112, 'steps': 115010, 'loss/train': 1.243813395500183} 08/31/2021 10:02:29 - INFO - __main__ - Step 115012: {'lr': 6.58404880982631e-05, 'samples': 22082304, 'steps': 115011, 'loss/train': 1.6236164569854736} 08/31/2021 10:02:30 - INFO - __main__ - Step 115013: {'lr': 6.583689925643835e-05, 'samples': 22082496, 'steps': 115012, 'loss/train': 0.9873213768005371} 08/31/2021 10:02:30 - INFO - __main__ - Step 115014: {'lr': 6.583331049759467e-05, 'samples': 22082688, 'steps': 115013, 'loss/train': 1.1099523305892944} 08/31/2021 10:02:30 - INFO - __main__ - Step 115015: {'lr': 6.582972182173366e-05, 'samples': 22082880, 'steps': 115014, 'loss/train': 1.5220354795455933} 08/31/2021 10:02:32 - INFO - __main__ - Step 115016: {'lr': 6.582613322885695e-05, 'samples': 22083072, 'steps': 115015, 'loss/train': 1.351497769355774} 08/31/2021 10:02:32 - INFO - __main__ - Step 115017: {'lr': 6.582254471896618e-05, 'samples': 22083264, 'steps': 115016, 'loss/train': 1.0725573301315308} 08/31/2021 10:02:33 - INFO - __main__ - Step 115018: {'lr': 6.581895629206288e-05, 'samples': 22083456, 'steps': 115017, 'loss/train': 1.2862218618392944} 08/31/2021 10:02:33 - INFO - __main__ - Step 115019: {'lr': 6.581536794814871e-05, 'samples': 22083648, 'steps': 115018, 'loss/train': 1.0804380178451538} 08/31/2021 10:02:33 - INFO - __main__ - Step 115020: {'lr': 6.581177968722529e-05, 'samples': 22083840, 'steps': 115019, 'loss/train': 0.23038548231124878} 08/31/2021 10:02:34 - INFO - __main__ - Step 115021: {'lr': 6.580819150929427e-05, 'samples': 22084032, 'steps': 115020, 'loss/train': 1.2717410326004028} 08/31/2021 10:02:36 - INFO - __main__ - Step 115022: {'lr': 6.58046034143572e-05, 'samples': 22084224, 'steps': 115021, 'loss/train': 1.0933703184127808} 08/31/2021 10:02:36 - INFO - __main__ - Step 115023: {'lr': 6.580101540241573e-05, 'samples': 22084416, 'steps': 115022, 'loss/train': 1.3059579133987427} 08/31/2021 10:02:37 - INFO - __main__ - Step 115024: {'lr': 6.57974274734715e-05, 'samples': 22084608, 'steps': 115023, 'loss/train': 1.0522146224975586} 08/31/2021 10:02:37 - INFO - __main__ - Step 115025: {'lr': 6.579383962752611e-05, 'samples': 22084800, 'steps': 115024, 'loss/train': 0.29885345697402954} 08/31/2021 10:02:38 - INFO - __main__ - Step 115026: {'lr': 6.579025186458116e-05, 'samples': 22084992, 'steps': 115025, 'loss/train': 0.06308232247829437} 08/31/2021 10:02:39 - INFO - __main__ - Step 115027: {'lr': 6.578666418463827e-05, 'samples': 22085184, 'steps': 115026, 'loss/train': 1.0392000675201416} 08/31/2021 10:02:39 - INFO - __main__ - Step 115028: {'lr': 6.578307658769916e-05, 'samples': 22085376, 'steps': 115027, 'loss/train': 1.341232419013977} 08/31/2021 10:02:40 - INFO - __main__ - Step 115029: {'lr': 6.577948907376527e-05, 'samples': 22085568, 'steps': 115028, 'loss/train': 0.633312463760376} 08/31/2021 10:02:40 - INFO - __main__ - Step 115030: {'lr': 6.577590164283831e-05, 'samples': 22085760, 'steps': 115029, 'loss/train': 0.8693231344223022} 08/31/2021 10:02:42 - INFO - __main__ - Step 115031: {'lr': 6.577231429491986e-05, 'samples': 22085952, 'steps': 115030, 'loss/train': 1.6073271036148071} 08/31/2021 10:02:42 - INFO - __main__ - Step 115032: {'lr': 6.57687270300116e-05, 'samples': 22086144, 'steps': 115031, 'loss/train': 1.2676115036010742} 08/31/2021 10:02:43 - INFO - __main__ - Step 115033: {'lr': 6.576513984811508e-05, 'samples': 22086336, 'steps': 115032, 'loss/train': 0.8542109727859497} 08/31/2021 10:02:43 - INFO - __main__ - Step 115034: {'lr': 6.576155274923196e-05, 'samples': 22086528, 'steps': 115033, 'loss/train': 1.0588972568511963} 08/31/2021 10:02:43 - INFO - __main__ - Step 115035: {'lr': 6.575796573336384e-05, 'samples': 22086720, 'steps': 115034, 'loss/train': 0.02887391299009323} 08/31/2021 10:02:44 - INFO - __main__ - Step 115036: {'lr': 6.575437880051233e-05, 'samples': 22086912, 'steps': 115035, 'loss/train': 0.058170534670352936} 08/31/2021 10:02:44 - INFO - __main__ - Step 115037: {'lr': 6.575079195067907e-05, 'samples': 22087104, 'steps': 115036, 'loss/train': 0.5436441898345947} 08/31/2021 10:02:45 - INFO - __main__ - Step 115038: {'lr': 6.574720518386565e-05, 'samples': 22087296, 'steps': 115037, 'loss/train': 1.5616711378097534} 08/31/2021 10:02:46 - INFO - __main__ - Step 115039: {'lr': 6.574361850007376e-05, 'samples': 22087488, 'steps': 115038, 'loss/train': 0.9704195261001587} 08/31/2021 10:02:46 - INFO - __main__ - Step 115040: {'lr': 6.574003189930488e-05, 'samples': 22087680, 'steps': 115039, 'loss/train': 0.8296076059341431} 08/31/2021 10:02:47 - INFO - __main__ - Step 115041: {'lr': 6.57364453815607e-05, 'samples': 22087872, 'steps': 115040, 'loss/train': 1.0907824039459229} 08/31/2021 10:02:47 - INFO - __main__ - Step 115042: {'lr': 6.573285894684287e-05, 'samples': 22088064, 'steps': 115041, 'loss/train': 1.0613014698028564} 08/31/2021 10:02:48 - INFO - __main__ - Step 115043: {'lr': 6.572927259515293e-05, 'samples': 22088256, 'steps': 115042, 'loss/train': 0.8357860445976257} 08/31/2021 10:02:49 - INFO - __main__ - Step 115044: {'lr': 6.572568632649253e-05, 'samples': 22088448, 'steps': 115043, 'loss/train': 1.09916090965271} 08/31/2021 10:02:49 - INFO - __main__ - Step 115045: {'lr': 6.572210014086333e-05, 'samples': 22088640, 'steps': 115044, 'loss/train': 0.4880748689174652} 08/31/2021 10:02:50 - INFO - __main__ - Step 115046: {'lr': 6.571851403826686e-05, 'samples': 22088832, 'steps': 115045, 'loss/train': 1.4361201524734497} 08/31/2021 10:02:50 - INFO - __main__ - Step 115047: {'lr': 6.571492801870483e-05, 'samples': 22089024, 'steps': 115046, 'loss/train': 1.441656231880188} 08/31/2021 10:02:52 - INFO - __main__ - Step 115048: {'lr': 6.571134208217877e-05, 'samples': 22089216, 'steps': 115047, 'loss/train': 1.962730050086975} 08/31/2021 10:02:52 - INFO - __main__ - Step 115049: {'lr': 6.570775622869039e-05, 'samples': 22089408, 'steps': 115048, 'loss/train': 0.7351599335670471} 08/31/2021 10:02:52 - INFO - __main__ - Step 115050: {'lr': 6.57041704582412e-05, 'samples': 22089600, 'steps': 115049, 'loss/train': 0.28003087639808655} 08/31/2021 10:02:53 - INFO - __main__ - Step 115051: {'lr': 6.570058477083288e-05, 'samples': 22089792, 'steps': 115050, 'loss/train': 1.4805095195770264} 08/31/2021 10:02:53 - INFO - __main__ - Step 115052: {'lr': 6.56969991664671e-05, 'samples': 22089984, 'steps': 115051, 'loss/train': 1.925197720527649} 08/31/2021 10:02:55 - INFO - __main__ - Step 115053: {'lr': 6.569341364514537e-05, 'samples': 22090176, 'steps': 115052, 'loss/train': 1.5279101133346558} 08/31/2021 10:02:56 - INFO - __main__ - Step 115054: {'lr': 6.568982820686931e-05, 'samples': 22090368, 'steps': 115053, 'loss/train': 1.1854783296585083} 08/31/2021 10:02:56 - INFO - __main__ - Step 115055: {'lr': 6.568624285164057e-05, 'samples': 22090560, 'steps': 115054, 'loss/train': 1.192331314086914} 08/31/2021 10:02:56 - INFO - __main__ - Step 115056: {'lr': 6.568265757946076e-05, 'samples': 22090752, 'steps': 115055, 'loss/train': 1.3807443380355835} 08/31/2021 10:02:57 - INFO - __main__ - Step 115057: {'lr': 6.567907239033153e-05, 'samples': 22090944, 'steps': 115056, 'loss/train': 1.5396820306777954} 08/31/2021 10:02:58 - INFO - __main__ - Step 115058: {'lr': 6.567548728425443e-05, 'samples': 22091136, 'steps': 115057, 'loss/train': 1.223113775253296} 08/31/2021 10:02:59 - INFO - __main__ - Step 115059: {'lr': 6.567190226123113e-05, 'samples': 22091328, 'steps': 115058, 'loss/train': 1.3813447952270508} 08/31/2021 10:02:59 - INFO - __main__ - Step 115060: {'lr': 6.566831732126324e-05, 'samples': 22091520, 'steps': 115059, 'loss/train': 1.3731615543365479} 08/31/2021 10:02:59 - INFO - __main__ - Step 115061: {'lr': 6.566473246435234e-05, 'samples': 22091712, 'steps': 115060, 'loss/train': 1.2561874389648438} 08/31/2021 10:03:00 - INFO - __main__ - Step 115062: {'lr': 6.566114769050008e-05, 'samples': 22091904, 'steps': 115061, 'loss/train': 0.8093527555465698} 08/31/2021 10:03:02 - INFO - __main__ - Step 115063: {'lr': 6.565756299970804e-05, 'samples': 22092096, 'steps': 115062, 'loss/train': 1.118112325668335} 08/31/2021 10:03:02 - INFO - __main__ - Step 115064: {'lr': 6.56539783919779e-05, 'samples': 22092288, 'steps': 115063, 'loss/train': 1.3215643167495728} 08/31/2021 10:03:02 - INFO - __main__ - Step 115065: {'lr': 6.565039386731128e-05, 'samples': 22092480, 'steps': 115064, 'loss/train': 0.08509465306997299} 08/31/2021 10:03:03 - INFO - __main__ - Step 115066: {'lr': 6.564680942570966e-05, 'samples': 22092672, 'steps': 115065, 'loss/train': 1.0237597227096558} 08/31/2021 10:03:03 - INFO - __main__ - Step 115067: {'lr': 6.564322506717477e-05, 'samples': 22092864, 'steps': 115066, 'loss/train': 1.7647387981414795} 08/31/2021 10:03:04 - INFO - __main__ - Step 115068: {'lr': 6.563964079170817e-05, 'samples': 22093056, 'steps': 115067, 'loss/train': 0.8109058737754822} 08/31/2021 10:03:05 - INFO - __main__ - Step 115069: {'lr': 6.563605659931152e-05, 'samples': 22093248, 'steps': 115068, 'loss/train': 0.7718614339828491} 08/31/2021 10:03:05 - INFO - __main__ - Step 115070: {'lr': 6.563247248998644e-05, 'samples': 22093440, 'steps': 115069, 'loss/train': 0.9935463666915894} 08/31/2021 10:03:06 - INFO - __main__ - Step 115071: {'lr': 6.56288884637345e-05, 'samples': 22093632, 'steps': 115070, 'loss/train': 0.8280588984489441} 08/31/2021 10:03:06 - INFO - __main__ - Step 115072: {'lr': 6.562530452055731e-05, 'samples': 22093824, 'steps': 115071, 'loss/train': 1.0572503805160522} 08/31/2021 10:03:08 - INFO - __main__ - Step 115073: {'lr': 6.562172066045655e-05, 'samples': 22094016, 'steps': 115072, 'loss/train': 0.9164493083953857} 08/31/2021 10:03:08 - INFO - __main__ - Step 115074: {'lr': 6.56181368834338e-05, 'samples': 22094208, 'steps': 115073, 'loss/train': 1.0397008657455444} 08/31/2021 10:03:08 - INFO - __main__ - Step 115075: {'lr': 6.561455318949063e-05, 'samples': 22094400, 'steps': 115074, 'loss/train': 1.2103041410446167} 08/31/2021 10:03:09 - INFO - __main__ - Step 115076: {'lr': 6.561096957862875e-05, 'samples': 22094592, 'steps': 115075, 'loss/train': 1.2441378831863403} 08/31/2021 10:03:09 - INFO - __main__ - Step 115077: {'lr': 6.56073860508497e-05, 'samples': 22094784, 'steps': 115076, 'loss/train': 1.0077425241470337} 08/31/2021 10:03:11 - INFO - __main__ - Step 115078: {'lr': 6.560380260615512e-05, 'samples': 22094976, 'steps': 115077, 'loss/train': 1.5580228567123413} 08/31/2021 10:03:11 - INFO - __main__ - Step 115079: {'lr': 6.560021924454668e-05, 'samples': 22095168, 'steps': 115078, 'loss/train': 0.6738359332084656} 08/31/2021 10:03:12 - INFO - __main__ - Step 115080: {'lr': 6.559663596602588e-05, 'samples': 22095360, 'steps': 115079, 'loss/train': 1.1994729042053223} 08/31/2021 10:03:12 - INFO - __main__ - Step 115081: {'lr': 6.559305277059438e-05, 'samples': 22095552, 'steps': 115080, 'loss/train': 0.45583465695381165} 08/31/2021 10:03:12 - INFO - __main__ - Step 115082: {'lr': 6.55894696582538e-05, 'samples': 22095744, 'steps': 115081, 'loss/train': 1.4425921440124512} 08/31/2021 10:03:14 - INFO - __main__ - Step 115083: {'lr': 6.558588662900577e-05, 'samples': 22095936, 'steps': 115082, 'loss/train': 1.2983468770980835} 08/31/2021 10:03:14 - INFO - __main__ - Step 115084: {'lr': 6.558230368285189e-05, 'samples': 22096128, 'steps': 115083, 'loss/train': 1.2029975652694702} 08/31/2021 10:03:15 - INFO - __main__ - Step 115085: {'lr': 6.55787208197938e-05, 'samples': 22096320, 'steps': 115084, 'loss/train': 0.2710147500038147} 08/31/2021 10:03:15 - INFO - __main__ - Step 115086: {'lr': 6.557513803983306e-05, 'samples': 22096512, 'steps': 115085, 'loss/train': 1.4490962028503418} 08/31/2021 10:03:16 - INFO - __main__ - Step 115087: {'lr': 6.557155534297133e-05, 'samples': 22096704, 'steps': 115086, 'loss/train': 1.0632891654968262} 08/31/2021 10:03:16 - INFO - __main__ - Step 115088: {'lr': 6.55679727292102e-05, 'samples': 22096896, 'steps': 115087, 'loss/train': 0.6676395535469055} 08/31/2021 10:03:18 - INFO - __main__ - Step 115089: {'lr': 6.556439019855131e-05, 'samples': 22097088, 'steps': 115088, 'loss/train': 1.1244964599609375} 08/31/2021 10:03:18 - INFO - __main__ - Step 115090: {'lr': 6.556080775099626e-05, 'samples': 22097280, 'steps': 115089, 'loss/train': 0.017276141792535782} 08/31/2021 10:03:19 - INFO - __main__ - Step 115091: {'lr': 6.555722538654665e-05, 'samples': 22097472, 'steps': 115090, 'loss/train': 0.3932245671749115} 08/31/2021 10:03:19 - INFO - __main__ - Step 115092: {'lr': 6.555364310520421e-05, 'samples': 22097664, 'steps': 115091, 'loss/train': 1.2211129665374756} 08/31/2021 10:03:19 - INFO - __main__ - Step 115093: {'lr': 6.555006090697035e-05, 'samples': 22097856, 'steps': 115092, 'loss/train': 0.7061031460762024} 08/31/2021 10:03:20 - INFO - __main__ - Step 115094: {'lr': 6.55464787918468e-05, 'samples': 22098048, 'steps': 115093, 'loss/train': 1.979094386100769} 08/31/2021 10:03:21 - INFO - __main__ - Step 115095: {'lr': 6.554289675983516e-05, 'samples': 22098240, 'steps': 115094, 'loss/train': 1.2057380676269531} 08/31/2021 10:03:22 - INFO - __main__ - Step 115096: {'lr': 6.553931481093703e-05, 'samples': 22098432, 'steps': 115095, 'loss/train': 1.4203788042068481} 08/31/2021 10:03:22 - INFO - __main__ - Step 115097: {'lr': 6.553573294515405e-05, 'samples': 22098624, 'steps': 115096, 'loss/train': 1.3689312934875488} 08/31/2021 10:03:22 - INFO - __main__ - Step 115098: {'lr': 6.553215116248781e-05, 'samples': 22098816, 'steps': 115097, 'loss/train': 1.2808481454849243} 08/31/2021 10:03:23 - INFO - __main__ - Step 115099: {'lr': 6.552856946293998e-05, 'samples': 22099008, 'steps': 115098, 'loss/train': 0.8125830292701721} 08/31/2021 10:03:24 - INFO - __main__ - Step 115100: {'lr': 6.552498784651209e-05, 'samples': 22099200, 'steps': 115099, 'loss/train': 0.5954793095588684} 08/31/2021 10:03:25 - INFO - __main__ - Step 115101: {'lr': 6.55214063132058e-05, 'samples': 22099392, 'steps': 115100, 'loss/train': 0.7984435558319092} 08/31/2021 10:03:25 - INFO - __main__ - Step 115102: {'lr': 6.551782486302271e-05, 'samples': 22099584, 'steps': 115101, 'loss/train': 0.14961515367031097} 08/31/2021 10:03:26 - INFO - __main__ - Step 115103: {'lr': 6.551424349596444e-05, 'samples': 22099776, 'steps': 115102, 'loss/train': 0.7013911008834839} 08/31/2021 10:03:26 - INFO - __main__ - Step 115104: {'lr': 6.55106622120326e-05, 'samples': 22099968, 'steps': 115103, 'loss/train': 1.437755823135376} 08/31/2021 10:03:28 - INFO - __main__ - Step 115105: {'lr': 6.550708101122885e-05, 'samples': 22100160, 'steps': 115104, 'loss/train': 1.5681688785552979} 08/31/2021 10:03:28 - INFO - __main__ - Step 115106: {'lr': 6.550349989355481e-05, 'samples': 22100352, 'steps': 115105, 'loss/train': 0.9028570652008057} 08/31/2021 10:03:29 - INFO - __main__ - Step 115107: {'lr': 6.549991885901197e-05, 'samples': 22100544, 'steps': 115106, 'loss/train': 1.2770227193832397} 08/31/2021 10:03:29 - INFO - __main__ - Step 115108: {'lr': 6.549633790760204e-05, 'samples': 22100736, 'steps': 115107, 'loss/train': 1.1440037488937378} 08/31/2021 10:03:29 - INFO - __main__ - Step 115109: {'lr': 6.549275703932659e-05, 'samples': 22100928, 'steps': 115108, 'loss/train': 1.5990407466888428} 08/31/2021 10:03:31 - INFO - __main__ - Step 115110: {'lr': 6.548917625418727e-05, 'samples': 22101120, 'steps': 115109, 'loss/train': 1.418174147605896} 08/31/2021 10:03:31 - INFO - __main__ - Step 115111: {'lr': 6.548559555218567e-05, 'samples': 22101312, 'steps': 115110, 'loss/train': 1.2097305059432983} 08/31/2021 10:03:32 - INFO - __main__ - Step 115112: {'lr': 6.54820149333234e-05, 'samples': 22101504, 'steps': 115111, 'loss/train': 1.183742880821228} 08/31/2021 10:03:32 - INFO - __main__ - Step 115113: {'lr': 6.547843439760209e-05, 'samples': 22101696, 'steps': 115112, 'loss/train': 0.9783803820610046} 08/31/2021 10:03:32 - INFO - __main__ - Step 115114: {'lr': 6.547485394502337e-05, 'samples': 22101888, 'steps': 115113, 'loss/train': 1.1048269271850586} 08/31/2021 10:03:34 - INFO - __main__ - Step 115115: {'lr': 6.547127357558883e-05, 'samples': 22102080, 'steps': 115114, 'loss/train': 2.0590975284576416} 08/31/2021 10:03:34 - INFO - __main__ - Step 115116: {'lr': 6.546769328930008e-05, 'samples': 22102272, 'steps': 115115, 'loss/train': 0.1334712654352188} 08/31/2021 10:03:35 - INFO - __main__ - Step 115117: {'lr': 6.546411308615873e-05, 'samples': 22102464, 'steps': 115116, 'loss/train': 1.2165035009384155} 08/31/2021 10:03:35 - INFO - __main__ - Step 115118: {'lr': 6.546053296616644e-05, 'samples': 22102656, 'steps': 115117, 'loss/train': 1.069250226020813} 08/31/2021 10:03:36 - INFO - __main__ - Step 115119: {'lr': 6.545695292932482e-05, 'samples': 22102848, 'steps': 115118, 'loss/train': 1.1682878732681274} 08/31/2021 10:03:36 - INFO - __main__ - Step 115120: {'lr': 6.545337297563539e-05, 'samples': 22103040, 'steps': 115119, 'loss/train': 1.2548131942749023} 08/31/2021 10:03:37 - INFO - __main__ - Step 115121: {'lr': 6.544979310509983e-05, 'samples': 22103232, 'steps': 115120, 'loss/train': 1.38890540599823} 08/31/2021 10:03:38 - INFO - __main__ - Step 115122: {'lr': 6.544621331771974e-05, 'samples': 22103424, 'steps': 115121, 'loss/train': 1.4120609760284424} 08/31/2021 10:03:38 - INFO - __main__ - Step 115123: {'lr': 6.544263361349673e-05, 'samples': 22103616, 'steps': 115122, 'loss/train': 1.0091968774795532} 08/31/2021 10:03:38 - INFO - __main__ - Step 115124: {'lr': 6.543905399243244e-05, 'samples': 22103808, 'steps': 115123, 'loss/train': 1.5462325811386108} 08/31/2021 10:03:39 - INFO - __main__ - Step 115125: {'lr': 6.543547445452844e-05, 'samples': 22104000, 'steps': 115124, 'loss/train': 0.08144363760948181} 08/31/2021 10:03:41 - INFO - __main__ - Step 115126: {'lr': 6.543189499978639e-05, 'samples': 22104192, 'steps': 115125, 'loss/train': 0.5177875757217407} 08/31/2021 10:03:41 - INFO - __main__ - Step 115127: {'lr': 6.542831562820787e-05, 'samples': 22104384, 'steps': 115126, 'loss/train': 1.0976980924606323} 08/31/2021 10:03:41 - INFO - __main__ - Step 115128: {'lr': 6.54247363397945e-05, 'samples': 22104576, 'steps': 115127, 'loss/train': 0.14455145597457886} 08/31/2021 10:03:42 - INFO - __main__ - Step 115129: {'lr': 6.542115713454791e-05, 'samples': 22104768, 'steps': 115128, 'loss/train': 1.4270082712173462} 08/31/2021 10:03:42 - INFO - __main__ - Step 115130: {'lr': 6.541757801246968e-05, 'samples': 22104960, 'steps': 115129, 'loss/train': 2.0442698001861572} 08/31/2021 10:03:44 - INFO - __main__ - Step 115131: {'lr': 6.541399897356143e-05, 'samples': 22105152, 'steps': 115130, 'loss/train': 0.027980461716651917} 08/31/2021 10:03:44 - INFO - __main__ - Step 115132: {'lr': 6.541042001782488e-05, 'samples': 22105344, 'steps': 115131, 'loss/train': 1.0509477853775024} 08/31/2021 10:03:44 - INFO - __main__ - Step 115133: {'lr': 6.540684114526147e-05, 'samples': 22105536, 'steps': 115132, 'loss/train': 2.001446485519409} 08/31/2021 10:03:45 - INFO - __main__ - Step 115134: {'lr': 6.54032623558729e-05, 'samples': 22105728, 'steps': 115133, 'loss/train': 1.0672272443771362} 08/31/2021 10:03:45 - INFO - __main__ - Step 115135: {'lr': 6.539968364966076e-05, 'samples': 22105920, 'steps': 115134, 'loss/train': 1.1189444065093994} 08/31/2021 10:03:47 - INFO - __main__ - Step 115136: {'lr': 6.539610502662666e-05, 'samples': 22106112, 'steps': 115135, 'loss/train': 0.9101722240447998} 08/31/2021 10:03:47 - INFO - __main__ - Step 115137: {'lr': 6.539252648677224e-05, 'samples': 22106304, 'steps': 115136, 'loss/train': 0.4385965168476105} 08/31/2021 10:03:48 - INFO - __main__ - Step 115138: {'lr': 6.538894803009909e-05, 'samples': 22106496, 'steps': 115137, 'loss/train': 0.9820067882537842} 08/31/2021 10:03:48 - INFO - __main__ - Step 115139: {'lr': 6.538536965660886e-05, 'samples': 22106688, 'steps': 115138, 'loss/train': 0.7052447199821472} 08/31/2021 10:03:48 - INFO - __main__ - Step 115140: {'lr': 6.53817913663031e-05, 'samples': 22106880, 'steps': 115139, 'loss/train': 0.779009997844696} 08/31/2021 10:03:50 - INFO - __main__ - Step 115141: {'lr': 6.537821315918347e-05, 'samples': 22107072, 'steps': 115140, 'loss/train': 1.3983715772628784} 08/31/2021 10:03:50 - INFO - __main__ - Step 115142: {'lr': 6.537463503525157e-05, 'samples': 22107264, 'steps': 115141, 'loss/train': 1.6148920059204102} 08/31/2021 10:03:51 - INFO - __main__ - Step 115143: {'lr': 6.537105699450901e-05, 'samples': 22107456, 'steps': 115142, 'loss/train': 1.297124981880188} 08/31/2021 10:03:51 - INFO - __main__ - Step 115144: {'lr': 6.536747903695739e-05, 'samples': 22107648, 'steps': 115143, 'loss/train': 0.3386596441268921} 08/31/2021 10:03:51 - INFO - __main__ - Step 115145: {'lr': 6.536390116259835e-05, 'samples': 22107840, 'steps': 115144, 'loss/train': 1.1195489168167114} 08/31/2021 10:03:53 - INFO - __main__ - Step 115146: {'lr': 6.536032337143355e-05, 'samples': 22108032, 'steps': 115145, 'loss/train': 0.6873968243598938} 08/31/2021 10:03:53 - INFO - __main__ - Step 115147: {'lr': 6.535674566346448e-05, 'samples': 22108224, 'steps': 115146, 'loss/train': 1.2116222381591797} 08/31/2021 10:03:54 - INFO - __main__ - Step 115148: {'lr': 6.535316803869279e-05, 'samples': 22108416, 'steps': 115147, 'loss/train': 1.4704701900482178} 08/31/2021 10:03:54 - INFO - __main__ - Step 115149: {'lr': 6.534959049712014e-05, 'samples': 22108608, 'steps': 115148, 'loss/train': 1.6806483268737793} 08/31/2021 10:03:54 - INFO - __main__ - Step 115150: {'lr': 6.53460130387481e-05, 'samples': 22108800, 'steps': 115149, 'loss/train': 0.28727200627326965} 08/31/2021 10:03:55 - INFO - __main__ - Step 115151: {'lr': 6.53424356635783e-05, 'samples': 22108992, 'steps': 115150, 'loss/train': 0.2525734603404999} 08/31/2021 10:03:56 - INFO - __main__ - Step 115152: {'lr': 6.533885837161236e-05, 'samples': 22109184, 'steps': 115151, 'loss/train': 0.822590172290802} 08/31/2021 10:03:57 - INFO - __main__ - Step 115153: {'lr': 6.533528116285184e-05, 'samples': 22109376, 'steps': 115152, 'loss/train': 1.3226771354675293} 08/31/2021 10:03:57 - INFO - __main__ - Step 115154: {'lr': 6.533170403729843e-05, 'samples': 22109568, 'steps': 115153, 'loss/train': 1.1004925966262817} 08/31/2021 10:03:57 - INFO - __main__ - Step 115155: {'lr': 6.532812699495369e-05, 'samples': 22109760, 'steps': 115154, 'loss/train': 1.41459321975708} 08/31/2021 10:03:58 - INFO - __main__ - Step 115156: {'lr': 6.532455003581925e-05, 'samples': 22109952, 'steps': 115155, 'loss/train': 1.2610292434692383} 08/31/2021 10:03:59 - INFO - __main__ - Step 115157: {'lr': 6.532097315989675e-05, 'samples': 22110144, 'steps': 115156, 'loss/train': 0.9182409048080444} 08/31/2021 10:04:00 - INFO - __main__ - Step 115158: {'lr': 6.531739636718773e-05, 'samples': 22110336, 'steps': 115157, 'loss/train': 1.4643429517745972} 08/31/2021 10:04:00 - INFO - __main__ - Step 115159: {'lr': 6.531381965769392e-05, 'samples': 22110528, 'steps': 115158, 'loss/train': 1.9918503761291504} 08/31/2021 10:04:00 - INFO - __main__ - Step 115160: {'lr': 6.531024303141678e-05, 'samples': 22110720, 'steps': 115159, 'loss/train': 1.1268852949142456} 08/31/2021 10:04:01 - INFO - __main__ - Step 115161: {'lr': 6.530666648835801e-05, 'samples': 22110912, 'steps': 115160, 'loss/train': 0.9316895604133606} 08/31/2021 10:04:03 - INFO - __main__ - Step 115162: {'lr': 6.530309002851917e-05, 'samples': 22111104, 'steps': 115161, 'loss/train': 1.3239235877990723} 08/31/2021 10:04:03 - INFO - __main__ - Step 115163: {'lr': 6.529951365190195e-05, 'samples': 22111296, 'steps': 115162, 'loss/train': 0.45169058442115784} 08/31/2021 10:04:03 - INFO - __main__ - Step 115164: {'lr': 6.529593735850789e-05, 'samples': 22111488, 'steps': 115163, 'loss/train': 1.1289714574813843} 08/31/2021 10:04:04 - INFO - __main__ - Step 115165: {'lr': 6.529236114833864e-05, 'samples': 22111680, 'steps': 115164, 'loss/train': 1.9610602855682373} 08/31/2021 10:04:04 - INFO - __main__ - Step 115166: {'lr': 6.528878502139582e-05, 'samples': 22111872, 'steps': 115165, 'loss/train': 0.12442269921302795} 08/31/2021 10:04:06 - INFO - __main__ - Step 115167: {'lr': 6.528520897768101e-05, 'samples': 22112064, 'steps': 115166, 'loss/train': 1.0301727056503296} 08/31/2021 10:04:06 - INFO - __main__ - Step 115168: {'lr': 6.52816330171958e-05, 'samples': 22112256, 'steps': 115167, 'loss/train': 1.176628589630127} 08/31/2021 10:04:07 - INFO - __main__ - Step 115169: {'lr': 6.527805713994189e-05, 'samples': 22112448, 'steps': 115168, 'loss/train': 1.0464298725128174} 08/31/2021 10:04:07 - INFO - __main__ - Step 115170: {'lr': 6.527448134592082e-05, 'samples': 22112640, 'steps': 115169, 'loss/train': 1.0498172044754028} 08/31/2021 10:04:07 - INFO - __main__ - Step 115171: {'lr': 6.527090563513419e-05, 'samples': 22112832, 'steps': 115170, 'loss/train': 2.0570082664489746} 08/31/2021 10:04:09 - INFO - __main__ - Step 115172: {'lr': 6.526733000758368e-05, 'samples': 22113024, 'steps': 115171, 'loss/train': 1.0817646980285645} 08/31/2021 10:04:09 - INFO - __main__ - Step 115173: {'lr': 6.52637544632709e-05, 'samples': 22113216, 'steps': 115172, 'loss/train': 0.7072618007659912} 08/31/2021 10:04:10 - INFO - __main__ - Step 115174: {'lr': 6.526017900219738e-05, 'samples': 22113408, 'steps': 115173, 'loss/train': 0.6503268480300903} 08/31/2021 10:04:10 - INFO - __main__ - Step 115175: {'lr': 6.525660362436475e-05, 'samples': 22113600, 'steps': 115174, 'loss/train': 0.027884885668754578} 08/31/2021 10:04:10 - INFO - __main__ - Step 115176: {'lr': 6.525302832977465e-05, 'samples': 22113792, 'steps': 115175, 'loss/train': 1.5262906551361084} 08/31/2021 10:04:12 - INFO - __main__ - Step 115177: {'lr': 6.524945311842867e-05, 'samples': 22113984, 'steps': 115176, 'loss/train': 1.0673128366470337} 08/31/2021 10:04:13 - INFO - __main__ - Step 115178: {'lr': 6.524587799032846e-05, 'samples': 22114176, 'steps': 115177, 'loss/train': 2.0339059829711914} 08/31/2021 10:04:13 - INFO - __main__ - Step 115179: {'lr': 6.524230294547559e-05, 'samples': 22114368, 'steps': 115178, 'loss/train': 1.6352195739746094} 08/31/2021 10:04:13 - INFO - __main__ - Step 115180: {'lr': 6.52387279838717e-05, 'samples': 22114560, 'steps': 115179, 'loss/train': 1.5933581590652466} 08/31/2021 10:04:14 - INFO - __main__ - Step 115181: {'lr': 6.52351531055184e-05, 'samples': 22114752, 'steps': 115180, 'loss/train': 1.7688418626785278} 08/31/2021 10:04:14 - INFO - __main__ - Step 115182: {'lr': 6.523157831041727e-05, 'samples': 22114944, 'steps': 115181, 'loss/train': 1.1052287817001343} 08/31/2021 10:04:15 - INFO - __main__ - Step 115183: {'lr': 6.522800359856992e-05, 'samples': 22115136, 'steps': 115182, 'loss/train': 0.4899238348007202} 08/31/2021 10:04:16 - INFO - __main__ - Step 115184: {'lr': 6.522442896997801e-05, 'samples': 22115328, 'steps': 115183, 'loss/train': 1.3968603610992432} 08/31/2021 10:04:16 - INFO - __main__ - Step 115185: {'lr': 6.52208544246431e-05, 'samples': 22115520, 'steps': 115184, 'loss/train': 0.1933611035346985} 08/31/2021 10:04:17 - INFO - __main__ - Step 115186: {'lr': 6.52172799625669e-05, 'samples': 22115712, 'steps': 115185, 'loss/train': 0.690115213394165} 08/31/2021 10:04:17 - INFO - __main__ - Step 115187: {'lr': 6.521370558375089e-05, 'samples': 22115904, 'steps': 115186, 'loss/train': 1.5628724098205566} 08/31/2021 10:04:18 - INFO - __main__ - Step 115188: {'lr': 6.521013128819673e-05, 'samples': 22116096, 'steps': 115187, 'loss/train': 1.220594882965088} 08/31/2021 10:04:19 - INFO - __main__ - Step 115189: {'lr': 6.5206557075906e-05, 'samples': 22116288, 'steps': 115188, 'loss/train': 0.8742906451225281} 08/31/2021 10:04:19 - INFO - __main__ - Step 115190: {'lr': 6.520298294688037e-05, 'samples': 22116480, 'steps': 115189, 'loss/train': 0.9653924107551575} 08/31/2021 10:04:19 - INFO - __main__ - Step 115191: {'lr': 6.519940890112141e-05, 'samples': 22116672, 'steps': 115190, 'loss/train': 0.907233476638794} 08/31/2021 10:04:20 - INFO - __main__ - Step 115192: {'lr': 6.519583493863077e-05, 'samples': 22116864, 'steps': 115191, 'loss/train': 1.474639654159546} 08/31/2021 10:04:22 - INFO - __main__ - Step 115193: {'lr': 6.519226105941003e-05, 'samples': 22117056, 'steps': 115192, 'loss/train': 1.1461637020111084} 08/31/2021 10:04:22 - INFO - __main__ - Step 115194: {'lr': 6.518868726346078e-05, 'samples': 22117248, 'steps': 115193, 'loss/train': 0.5201062560081482} 08/31/2021 10:04:23 - INFO - __main__ - Step 115195: {'lr': 6.518511355078468e-05, 'samples': 22117440, 'steps': 115194, 'loss/train': 1.494199275970459} 08/31/2021 10:04:23 - INFO - __main__ - Step 115196: {'lr': 6.518153992138332e-05, 'samples': 22117632, 'steps': 115195, 'loss/train': 0.01426702830940485} 08/31/2021 10:04:23 - INFO - __main__ - Step 115197: {'lr': 6.517796637525827e-05, 'samples': 22117824, 'steps': 115196, 'loss/train': 1.3043606281280518} 08/31/2021 10:04:24 - INFO - __main__ - Step 115198: {'lr': 6.517439291241121e-05, 'samples': 22118016, 'steps': 115197, 'loss/train': 1.235137939453125} 08/31/2021 10:04:25 - INFO - __main__ - Step 115199: {'lr': 6.51708195328437e-05, 'samples': 22118208, 'steps': 115198, 'loss/train': 1.3889819383621216} 08/31/2021 10:04:26 - INFO - __main__ - Step 115200: {'lr': 6.516724623655745e-05, 'samples': 22118400, 'steps': 115199, 'loss/train': 1.2405158281326294} 08/31/2021 10:04:26 - INFO - __main__ - Step 115201: {'lr': 6.516367302355392e-05, 'samples': 22118592, 'steps': 115200, 'loss/train': 1.5039888620376587} 08/31/2021 10:04:26 - INFO - __main__ - Step 115202: {'lr': 6.516009989383476e-05, 'samples': 22118784, 'steps': 115201, 'loss/train': 1.6711881160736084} 08/31/2021 10:04:27 - INFO - __main__ - Step 115203: {'lr': 6.515652684740164e-05, 'samples': 22118976, 'steps': 115202, 'loss/train': 1.3224526643753052} 08/31/2021 10:04:27 - INFO - __main__ - Step 115204: {'lr': 6.51529538842561e-05, 'samples': 22119168, 'steps': 115203, 'loss/train': 1.2128878831863403} 08/31/2021 10:04:29 - INFO - __main__ - Step 115205: {'lr': 6.514938100439982e-05, 'samples': 22119360, 'steps': 115204, 'loss/train': 1.179847002029419} 08/31/2021 10:04:29 - INFO - __main__ - Step 115206: {'lr': 6.514580820783436e-05, 'samples': 22119552, 'steps': 115205, 'loss/train': 1.2574673891067505} 08/31/2021 10:04:29 - INFO - __main__ - Step 115207: {'lr': 6.514223549456136e-05, 'samples': 22119744, 'steps': 115206, 'loss/train': 0.4962896406650543} 08/31/2021 10:04:30 - INFO - __main__ - Step 115208: {'lr': 6.51386628645824e-05, 'samples': 22119936, 'steps': 115207, 'loss/train': 0.034870684146881104} 08/31/2021 10:04:30 - INFO - __main__ - Step 115209: {'lr': 6.513509031789911e-05, 'samples': 22120128, 'steps': 115208, 'loss/train': 0.8013336658477783} 08/31/2021 10:04:32 - INFO - __main__ - Step 115210: {'lr': 6.51315178545131e-05, 'samples': 22120320, 'steps': 115209, 'loss/train': 1.3607957363128662} 08/31/2021 10:04:33 - INFO - __main__ - Step 115211: {'lr': 6.512794547442597e-05, 'samples': 22120512, 'steps': 115210, 'loss/train': 0.886021077632904} 08/31/2021 10:04:33 - INFO - __main__ - Step 115212: {'lr': 6.512437317763934e-05, 'samples': 22120704, 'steps': 115211, 'loss/train': 0.027996452525258064} 08/31/2021 10:04:33 - INFO - __main__ - Step 115213: {'lr': 6.512080096415488e-05, 'samples': 22120896, 'steps': 115212, 'loss/train': 0.014300208538770676} 08/31/2021 10:04:34 - INFO - __main__ - Step 115214: {'lr': 6.511722883397406e-05, 'samples': 22121088, 'steps': 115213, 'loss/train': 0.9846816062927246} 08/31/2021 10:04:34 - INFO - __main__ - Step 115215: {'lr': 6.511365678709857e-05, 'samples': 22121280, 'steps': 115214, 'loss/train': 1.2000081539154053} 08/31/2021 10:04:34 - INFO - __main__ - Step 115216: {'lr': 6.511008482353001e-05, 'samples': 22121472, 'steps': 115215, 'loss/train': 0.014072946272790432} 08/31/2021 10:04:36 - INFO - __main__ - Step 115217: {'lr': 6.510651294327e-05, 'samples': 22121664, 'steps': 115216, 'loss/train': 1.1258505582809448} 08/31/2021 10:04:37 - INFO - __main__ - Step 115218: {'lr': 6.510294114632015e-05, 'samples': 22121856, 'steps': 115217, 'loss/train': 1.0296704769134521} 08/31/2021 10:04:37 - INFO - __main__ - Step 115219: {'lr': 6.509936943268205e-05, 'samples': 22122048, 'steps': 115218, 'loss/train': 0.9627969264984131} 08/31/2021 10:04:38 - INFO - __main__ - Step 115220: {'lr': 6.50957978023573e-05, 'samples': 22122240, 'steps': 115219, 'loss/train': 1.8986904621124268} 08/31/2021 10:04:38 - INFO - __main__ - Step 115221: {'lr': 6.509222625534755e-05, 'samples': 22122432, 'steps': 115220, 'loss/train': 0.859255850315094} 08/31/2021 10:04:40 - INFO - __main__ - Step 115222: {'lr': 6.508865479165441e-05, 'samples': 22122624, 'steps': 115221, 'loss/train': 1.0221346616744995} 08/31/2021 10:04:41 - INFO - __main__ - Step 115223: {'lr': 6.508508341127945e-05, 'samples': 22122816, 'steps': 115222, 'loss/train': 1.4503931999206543} 08/31/2021 10:04:41 - INFO - __main__ - Step 115224: {'lr': 6.508151211422427e-05, 'samples': 22123008, 'steps': 115223, 'loss/train': 4.372420787811279} 08/31/2021 10:04:42 - INFO - __main__ - Step 115225: {'lr': 6.507794090049055e-05, 'samples': 22123200, 'steps': 115224, 'loss/train': 4.275186538696289} 08/31/2021 10:04:42 - INFO - __main__ - Step 115226: {'lr': 6.507436977007985e-05, 'samples': 22123392, 'steps': 115225, 'loss/train': 4.33187198638916} 08/31/2021 10:04:42 - INFO - __main__ - Step 115227: {'lr': 6.507079872299384e-05, 'samples': 22123584, 'steps': 115226, 'loss/train': 1.3492623567581177} 08/31/2021 10:04:43 - INFO - __main__ - Step 115228: {'lr': 6.506722775923402e-05, 'samples': 22123776, 'steps': 115227, 'loss/train': 1.0904558897018433} 08/31/2021 10:04:44 - INFO - __main__ - Step 115229: {'lr': 6.506365687880203e-05, 'samples': 22123968, 'steps': 115228, 'loss/train': 0.9896503686904907} 08/31/2021 10:04:45 - INFO - __main__ - Step 115230: {'lr': 6.506008608169953e-05, 'samples': 22124160, 'steps': 115229, 'loss/train': 1.3394663333892822} 08/31/2021 10:04:45 - INFO - __main__ - Step 115231: {'lr': 6.505651536792808e-05, 'samples': 22124352, 'steps': 115230, 'loss/train': 1.3667364120483398} 08/31/2021 10:04:45 - INFO - __main__ - Step 115232: {'lr': 6.505294473748932e-05, 'samples': 22124544, 'steps': 115231, 'loss/train': 1.3410941362380981} 08/31/2021 10:04:46 - INFO - __main__ - Step 115233: {'lr': 6.504937419038485e-05, 'samples': 22124736, 'steps': 115232, 'loss/train': 1.4988257884979248} 08/31/2021 10:04:47 - INFO - __main__ - Step 115234: {'lr': 6.504580372661628e-05, 'samples': 22124928, 'steps': 115233, 'loss/train': 0.7469944953918457} 08/31/2021 10:04:48 - INFO - __main__ - Step 115235: {'lr': 6.50422333461852e-05, 'samples': 22125120, 'steps': 115234, 'loss/train': 1.1791216135025024} 08/31/2021 10:04:48 - INFO - __main__ - Step 115236: {'lr': 6.503866304909326e-05, 'samples': 22125312, 'steps': 115235, 'loss/train': 1.059329628944397} 08/31/2021 10:04:48 - INFO - __main__ - Step 115237: {'lr': 6.503509283534204e-05, 'samples': 22125504, 'steps': 115236, 'loss/train': 1.0037717819213867} 08/31/2021 10:04:49 - INFO - __main__ - Step 115238: {'lr': 6.503152270493312e-05, 'samples': 22125696, 'steps': 115237, 'loss/train': 1.1745343208312988} 08/31/2021 10:04:50 - INFO - __main__ - Step 115239: {'lr': 6.502795265786817e-05, 'samples': 22125888, 'steps': 115238, 'loss/train': 1.3754198551177979} 08/31/2021 10:04:51 - INFO - __main__ - Step 115240: {'lr': 6.502438269414884e-05, 'samples': 22126080, 'steps': 115239, 'loss/train': 1.5378338098526} 08/31/2021 10:04:51 - INFO - __main__ - Step 115241: {'lr': 6.502081281377661e-05, 'samples': 22126272, 'steps': 115240, 'loss/train': 1.2844760417938232} 08/31/2021 10:04:52 - INFO - __main__ - Step 115242: {'lr': 6.501724301675313e-05, 'samples': 22126464, 'steps': 115241, 'loss/train': 2.394235610961914} 08/31/2021 10:04:52 - INFO - __main__ - Step 115243: {'lr': 6.501367330308003e-05, 'samples': 22126656, 'steps': 115242, 'loss/train': 0.6715319752693176} 08/31/2021 10:04:52 - INFO - __main__ - Step 115244: {'lr': 6.501010367275892e-05, 'samples': 22126848, 'steps': 115243, 'loss/train': 0.4228169918060303} 08/31/2021 10:04:54 - INFO - __main__ - Step 115245: {'lr': 6.500653412579139e-05, 'samples': 22127040, 'steps': 115244, 'loss/train': 0.36877575516700745} 08/31/2021 10:04:54 - INFO - __main__ - Step 115246: {'lr': 6.500296466217906e-05, 'samples': 22127232, 'steps': 115245, 'loss/train': 0.34729868173599243} 08/31/2021 10:04:55 - INFO - __main__ - Step 115247: {'lr': 6.499939528192356e-05, 'samples': 22127424, 'steps': 115246, 'loss/train': 1.151236653327942} 08/31/2021 10:04:55 - INFO - __main__ - Step 115248: {'lr': 6.499582598502645e-05, 'samples': 22127616, 'steps': 115247, 'loss/train': 0.8655997514724731} 08/31/2021 10:04:55 - INFO - __main__ - Step 115249: {'lr': 6.49922567714894e-05, 'samples': 22127808, 'steps': 115248, 'loss/train': 1.0529472827911377} 08/31/2021 10:04:57 - INFO - __main__ - Step 115250: {'lr': 6.498868764131396e-05, 'samples': 22128000, 'steps': 115249, 'loss/train': 0.6053061485290527} 08/31/2021 10:04:57 - INFO - __main__ - Step 115251: {'lr': 6.498511859450176e-05, 'samples': 22128192, 'steps': 115250, 'loss/train': 1.671504259109497} 08/31/2021 10:04:58 - INFO - __main__ - Step 115252: {'lr': 6.498154963105441e-05, 'samples': 22128384, 'steps': 115251, 'loss/train': 1.2728345394134521} 08/31/2021 10:04:58 - INFO - __main__ - Step 115253: {'lr': 6.497798075097361e-05, 'samples': 22128576, 'steps': 115252, 'loss/train': 0.6983370780944824} 08/31/2021 10:04:58 - INFO - __main__ - Step 115254: {'lr': 6.497441195426079e-05, 'samples': 22128768, 'steps': 115253, 'loss/train': 1.204418659210205} 08/31/2021 10:05:00 - INFO - __main__ - Step 115255: {'lr': 6.497084324091765e-05, 'samples': 22128960, 'steps': 115254, 'loss/train': 1.2992435693740845} 08/31/2021 10:05:01 - INFO - __main__ - Step 115256: {'lr': 6.496727461094579e-05, 'samples': 22129152, 'steps': 115255, 'loss/train': 1.4034689664840698} 08/31/2021 10:05:01 - INFO - __main__ - Step 115257: {'lr': 6.496370606434682e-05, 'samples': 22129344, 'steps': 115256, 'loss/train': 0.6123790144920349} 08/31/2021 10:05:01 - INFO - __main__ - Step 115258: {'lr': 6.496013760112235e-05, 'samples': 22129536, 'steps': 115257, 'loss/train': 0.6885490417480469} 08/31/2021 10:05:02 - INFO - __main__ - Step 115259: {'lr': 6.495656922127399e-05, 'samples': 22129728, 'steps': 115258, 'loss/train': 0.42023494839668274} 08/31/2021 10:05:02 - INFO - __main__ - Step 115260: {'lr': 6.495300092480332e-05, 'samples': 22129920, 'steps': 115259, 'loss/train': 1.3803731203079224} 08/31/2021 10:05:04 - INFO - __main__ - Step 115261: {'lr': 6.494943271171202e-05, 'samples': 22130112, 'steps': 115260, 'loss/train': 1.139732837677002} 08/31/2021 10:05:04 - INFO - __main__ - Step 115262: {'lr': 6.494586458200161e-05, 'samples': 22130304, 'steps': 115261, 'loss/train': 1.9497135877609253} 08/31/2021 10:05:04 - INFO - __main__ - Step 115263: {'lr': 6.494229653567377e-05, 'samples': 22130496, 'steps': 115262, 'loss/train': 1.1642318964004517} 08/31/2021 10:05:05 - INFO - __main__ - Step 115264: {'lr': 6.493872857273012e-05, 'samples': 22130688, 'steps': 115263, 'loss/train': 0.07557288557291031} 08/31/2021 10:05:05 - INFO - __main__ - Step 115265: {'lr': 6.493516069317218e-05, 'samples': 22130880, 'steps': 115264, 'loss/train': 0.9279385805130005} 08/31/2021 10:05:07 - INFO - __main__ - Step 115266: {'lr': 6.493159289700157e-05, 'samples': 22131072, 'steps': 115265, 'loss/train': 1.255484700202942} 08/31/2021 10:05:07 - INFO - __main__ - Step 115267: {'lr': 6.492802518421994e-05, 'samples': 22131264, 'steps': 115266, 'loss/train': 0.3563389182090759} 08/31/2021 10:05:08 - INFO - __main__ - Step 115268: {'lr': 6.49244575548289e-05, 'samples': 22131456, 'steps': 115267, 'loss/train': 1.238507628440857} 08/31/2021 10:05:08 - INFO - __main__ - Step 115269: {'lr': 6.492089000883e-05, 'samples': 22131648, 'steps': 115268, 'loss/train': 0.867264449596405} 08/31/2021 10:05:08 - INFO - __main__ - Step 115270: {'lr': 6.491732254622493e-05, 'samples': 22131840, 'steps': 115269, 'loss/train': 1.2494271993637085} 08/31/2021 10:05:09 - INFO - __main__ - Step 115271: {'lr': 6.491375516701526e-05, 'samples': 22132032, 'steps': 115270, 'loss/train': 0.44313761591911316} 08/31/2021 10:05:10 - INFO - __main__ - Step 115272: {'lr': 6.491018787120259e-05, 'samples': 22132224, 'steps': 115271, 'loss/train': 1.3964139223098755} 08/31/2021 10:05:11 - INFO - __main__ - Step 115273: {'lr': 6.490662065878853e-05, 'samples': 22132416, 'steps': 115272, 'loss/train': 1.3044745922088623} 08/31/2021 10:05:11 - INFO - __main__ - Step 115274: {'lr': 6.490305352977469e-05, 'samples': 22132608, 'steps': 115273, 'loss/train': 1.330031394958496} 08/31/2021 10:05:11 - INFO - __main__ - Step 115275: {'lr': 6.489948648416274e-05, 'samples': 22132800, 'steps': 115274, 'loss/train': 1.7606022357940674} 08/31/2021 10:05:12 - INFO - __main__ - Step 115276: {'lr': 6.489591952195417e-05, 'samples': 22132992, 'steps': 115275, 'loss/train': 1.4696520566940308} 08/31/2021 10:05:14 - INFO - __main__ - Step 115277: {'lr': 6.489235264315063e-05, 'samples': 22133184, 'steps': 115276, 'loss/train': 0.25565361976623535} 08/31/2021 10:05:14 - INFO - __main__ - Step 115278: {'lr': 6.488878584775374e-05, 'samples': 22133376, 'steps': 115277, 'loss/train': 1.5183629989624023} 08/31/2021 10:05:15 - INFO - __main__ - Step 115279: {'lr': 6.488521913576512e-05, 'samples': 22133568, 'steps': 115278, 'loss/train': 0.756687581539154} 08/31/2021 10:05:15 - INFO - __main__ - Step 115280: {'lr': 6.488165250718634e-05, 'samples': 22133760, 'steps': 115279, 'loss/train': 0.888127326965332} 08/31/2021 10:05:15 - INFO - __main__ - Step 115281: {'lr': 6.487808596201905e-05, 'samples': 22133952, 'steps': 115280, 'loss/train': 1.084911823272705} 08/31/2021 10:05:17 - INFO - __main__ - Step 115282: {'lr': 6.487451950026482e-05, 'samples': 22134144, 'steps': 115281, 'loss/train': 1.1423273086547852} 08/31/2021 10:05:17 - INFO - __main__ - Step 115283: {'lr': 6.487095312192529e-05, 'samples': 22134336, 'steps': 115282, 'loss/train': 1.1648457050323486} 08/31/2021 10:05:18 - INFO - __main__ - Step 115284: {'lr': 6.486738682700204e-05, 'samples': 22134528, 'steps': 115283, 'loss/train': 0.9241398572921753} 08/31/2021 10:05:18 - INFO - __main__ - Step 115285: {'lr': 6.486382061549673e-05, 'samples': 22134720, 'steps': 115284, 'loss/train': 0.8814311623573303} 08/31/2021 10:05:18 - INFO - __main__ - Step 115286: {'lr': 6.486025448741095e-05, 'samples': 22134912, 'steps': 115285, 'loss/train': 1.1473151445388794} 08/31/2021 10:05:20 - INFO - __main__ - Step 115287: {'lr': 6.485668844274623e-05, 'samples': 22135104, 'steps': 115286, 'loss/train': 0.3194291591644287} 08/31/2021 10:05:21 - INFO - __main__ - Step 115288: {'lr': 6.485312248150421e-05, 'samples': 22135296, 'steps': 115287, 'loss/train': 0.623526394367218} 08/31/2021 10:05:21 - INFO - __main__ - Step 115289: {'lr': 6.484955660368655e-05, 'samples': 22135488, 'steps': 115288, 'loss/train': 1.4261003732681274} 08/31/2021 10:05:21 - INFO - __main__ - Step 115290: {'lr': 6.484599080929479e-05, 'samples': 22135680, 'steps': 115289, 'loss/train': 0.857528805732727} 08/31/2021 10:05:22 - INFO - __main__ - Step 115291: {'lr': 6.48424250983306e-05, 'samples': 22135872, 'steps': 115290, 'loss/train': 1.468923568725586} 08/31/2021 10:05:22 - INFO - __main__ - Step 115292: {'lr': 6.483885947079554e-05, 'samples': 22136064, 'steps': 115291, 'loss/train': 0.01735001616179943} 08/31/2021 10:05:24 - INFO - __main__ - Step 115293: {'lr': 6.483529392669121e-05, 'samples': 22136256, 'steps': 115292, 'loss/train': 0.05696025863289833} 08/31/2021 10:05:24 - INFO - __main__ - Step 115294: {'lr': 6.483172846601928e-05, 'samples': 22136448, 'steps': 115293, 'loss/train': 0.4811944365501404} 08/31/2021 10:05:24 - INFO - __main__ - Step 115295: {'lr': 6.482816308878129e-05, 'samples': 22136640, 'steps': 115294, 'loss/train': 0.8582046627998352} 08/31/2021 10:05:25 - INFO - __main__ - Step 115296: {'lr': 6.482459779497887e-05, 'samples': 22136832, 'steps': 115295, 'loss/train': 1.5090906620025635} 08/31/2021 10:05:25 - INFO - __main__ - Step 115297: {'lr': 6.482103258461373e-05, 'samples': 22137024, 'steps': 115296, 'loss/train': 1.1962841749191284} 08/31/2021 10:05:27 - INFO - __main__ - Step 115298: {'lr': 6.481746745768729e-05, 'samples': 22137216, 'steps': 115297, 'loss/train': 1.1553901433944702} 08/31/2021 10:05:27 - INFO - __main__ - Step 115299: {'lr': 6.481390241420123e-05, 'samples': 22137408, 'steps': 115298, 'loss/train': 0.9217677116394043} 08/31/2021 10:05:27 - INFO - __main__ - Step 115300: {'lr': 6.481033745415719e-05, 'samples': 22137600, 'steps': 115299, 'loss/train': 0.631215512752533} 08/31/2021 10:05:28 - INFO - __main__ - Step 115301: {'lr': 6.480677257755671e-05, 'samples': 22137792, 'steps': 115300, 'loss/train': 1.0160483121871948} 08/31/2021 10:05:28 - INFO - __main__ - Step 115302: {'lr': 6.48032077844015e-05, 'samples': 22137984, 'steps': 115301, 'loss/train': 1.8443461656570435} 08/31/2021 10:05:29 - INFO - __main__ - Step 115303: {'lr': 6.479964307469305e-05, 'samples': 22138176, 'steps': 115302, 'loss/train': 1.0715070962905884} 08/31/2021 10:05:30 - INFO - __main__ - Step 115304: {'lr': 6.479607844843305e-05, 'samples': 22138368, 'steps': 115303, 'loss/train': 0.4230740964412689} 08/31/2021 10:05:31 - INFO - __main__ - Step 115305: {'lr': 6.479251390562308e-05, 'samples': 22138560, 'steps': 115304, 'loss/train': 1.1631025075912476} 08/31/2021 10:05:31 - INFO - __main__ - Step 115306: {'lr': 6.478894944626474e-05, 'samples': 22138752, 'steps': 115305, 'loss/train': 1.290861964225769} 08/31/2021 10:05:31 - INFO - __main__ - Step 115307: {'lr': 6.478538507035964e-05, 'samples': 22138944, 'steps': 115306, 'loss/train': 0.977876603603363} 08/31/2021 10:05:32 - INFO - __main__ - Step 115308: {'lr': 6.478182077790948e-05, 'samples': 22139136, 'steps': 115307, 'loss/train': 1.21962308883667} 08/31/2021 10:05:33 - INFO - __main__ - Step 115309: {'lr': 6.477825656891567e-05, 'samples': 22139328, 'steps': 115308, 'loss/train': 0.5734157562255859} 08/31/2021 10:05:33 - INFO - __main__ - Step 115310: {'lr': 6.477469244337994e-05, 'samples': 22139520, 'steps': 115309, 'loss/train': 1.2644685506820679} 08/31/2021 10:05:34 - INFO - __main__ - Step 115311: {'lr': 6.477112840130387e-05, 'samples': 22139712, 'steps': 115310, 'loss/train': 1.5062440633773804} 08/31/2021 10:05:34 - INFO - __main__ - Step 115312: {'lr': 6.476756444268908e-05, 'samples': 22139904, 'steps': 115311, 'loss/train': 1.2888339757919312} 08/31/2021 10:05:35 - INFO - __main__ - Step 115313: {'lr': 6.476400056753715e-05, 'samples': 22140096, 'steps': 115312, 'loss/train': 0.1559542864561081} 08/31/2021 10:05:36 - INFO - __main__ - Step 115314: {'lr': 6.476043677584972e-05, 'samples': 22140288, 'steps': 115313, 'loss/train': 1.1413823366165161} 08/31/2021 10:05:37 - INFO - __main__ - Step 115315: {'lr': 6.475687306762837e-05, 'samples': 22140480, 'steps': 115314, 'loss/train': 0.048989176750183105} 08/31/2021 10:05:37 - INFO - __main__ - Step 115316: {'lr': 6.475330944287472e-05, 'samples': 22140672, 'steps': 115315, 'loss/train': 0.5079882740974426} 08/31/2021 10:05:38 - INFO - __main__ - Step 115317: {'lr': 6.474974590159036e-05, 'samples': 22140864, 'steps': 115316, 'loss/train': 0.964772641658783} 08/31/2021 10:05:38 - INFO - __main__ - Step 115318: {'lr': 6.474618244377689e-05, 'samples': 22141056, 'steps': 115317, 'loss/train': 1.242263913154602} 08/31/2021 10:05:38 - INFO - __main__ - Step 115319: {'lr': 6.474261906943596e-05, 'samples': 22141248, 'steps': 115318, 'loss/train': 1.499271273612976} 08/31/2021 10:05:40 - INFO - __main__ - Step 115320: {'lr': 6.473905577856915e-05, 'samples': 22141440, 'steps': 115319, 'loss/train': 1.3620190620422363} 08/31/2021 10:05:40 - INFO - __main__ - Step 115321: {'lr': 6.473549257117811e-05, 'samples': 22141632, 'steps': 115320, 'loss/train': 1.0006039142608643} 08/31/2021 10:05:41 - INFO - __main__ - Step 115322: {'lr': 6.473192944726437e-05, 'samples': 22141824, 'steps': 115321, 'loss/train': 1.1761572360992432} 08/31/2021 10:05:41 - INFO - __main__ - Step 115323: {'lr': 6.472836640682953e-05, 'samples': 22142016, 'steps': 115322, 'loss/train': 0.8820514678955078} 08/31/2021 10:05:41 - INFO - __main__ - Step 115324: {'lr': 6.472480344987522e-05, 'samples': 22142208, 'steps': 115323, 'loss/train': 1.171737551689148} 08/31/2021 10:05:42 - INFO - __main__ - Step 115325: {'lr': 6.472124057640308e-05, 'samples': 22142400, 'steps': 115324, 'loss/train': 0.1970926821231842} 08/31/2021 10:05:43 - INFO - __main__ - Step 115326: {'lr': 6.471767778641466e-05, 'samples': 22142592, 'steps': 115325, 'loss/train': 1.1988911628723145} 08/31/2021 10:05:44 - INFO - __main__ - Step 115327: {'lr': 6.471411507991163e-05, 'samples': 22142784, 'steps': 115326, 'loss/train': 1.3378602266311646} 08/31/2021 10:05:44 - INFO - __main__ - Step 115328: {'lr': 6.471055245689553e-05, 'samples': 22142976, 'steps': 115327, 'loss/train': 0.7507209777832031} 08/31/2021 10:05:44 - INFO - __main__ - Step 115329: {'lr': 6.470698991736801e-05, 'samples': 22143168, 'steps': 115328, 'loss/train': 0.6826837658882141} 08/31/2021 10:05:45 - INFO - __main__ - Step 115330: {'lr': 6.470342746133068e-05, 'samples': 22143360, 'steps': 115329, 'loss/train': 0.7495271563529968} 08/31/2021 10:05:47 - INFO - __main__ - Step 115331: {'lr': 6.469986508878508e-05, 'samples': 22143552, 'steps': 115330, 'loss/train': 1.2596758604049683} 08/31/2021 10:05:47 - INFO - __main__ - Step 115332: {'lr': 6.46963027997329e-05, 'samples': 22143744, 'steps': 115331, 'loss/train': 1.4705612659454346} 08/31/2021 10:05:47 - INFO - __main__ - Step 115333: {'lr': 6.46927405941757e-05, 'samples': 22143936, 'steps': 115332, 'loss/train': 0.8738416433334351} 08/31/2021 10:05:48 - INFO - __main__ - Step 115334: {'lr': 6.468917847211517e-05, 'samples': 22144128, 'steps': 115333, 'loss/train': 0.5448405742645264} 08/31/2021 10:05:48 - INFO - __main__ - Step 115335: {'lr': 6.468561643355276e-05, 'samples': 22144320, 'steps': 115334, 'loss/train': 1.131349802017212} 08/31/2021 10:05:50 - INFO - __main__ - Step 115336: {'lr': 6.468205447849012e-05, 'samples': 22144512, 'steps': 115335, 'loss/train': 1.0093756914138794} 08/31/2021 10:05:51 - INFO - __main__ - Step 115337: {'lr': 6.467849260692893e-05, 'samples': 22144704, 'steps': 115336, 'loss/train': 1.381346344947815} 08/31/2021 10:05:51 - INFO - __main__ - Step 115338: {'lr': 6.467493081887071e-05, 'samples': 22144896, 'steps': 115337, 'loss/train': 2.330698251724243} 08/31/2021 10:05:52 - INFO - __main__ - Step 115339: {'lr': 6.467136911431715e-05, 'samples': 22145088, 'steps': 115338, 'loss/train': 2.298192262649536} 08/31/2021 10:05:52 - INFO - __main__ - Step 115340: {'lr': 6.466780749326978e-05, 'samples': 22145280, 'steps': 115339, 'loss/train': 0.9533684849739075} 08/31/2021 10:05:52 - INFO - __main__ - Step 115341: {'lr': 6.466424595573026e-05, 'samples': 22145472, 'steps': 115340, 'loss/train': 0.02590487152338028} 08/31/2021 10:05:53 - INFO - __main__ - Step 115342: {'lr': 6.466068450170015e-05, 'samples': 22145664, 'steps': 115341, 'loss/train': 0.029764391481876373} 08/31/2021 10:05:54 - INFO - __main__ - Step 115343: {'lr': 6.465712313118107e-05, 'samples': 22145856, 'steps': 115342, 'loss/train': 0.687393307685852} 08/31/2021 10:05:55 - INFO - __main__ - Step 115344: {'lr': 6.465356184417465e-05, 'samples': 22146048, 'steps': 115343, 'loss/train': 1.0063639879226685} 08/31/2021 10:05:55 - INFO - __main__ - Step 115345: {'lr': 6.465000064068247e-05, 'samples': 22146240, 'steps': 115344, 'loss/train': 1.214629054069519} 08/31/2021 10:05:55 - INFO - __main__ - Step 115346: {'lr': 6.464643952070614e-05, 'samples': 22146432, 'steps': 115345, 'loss/train': 0.2606019377708435} 08/31/2021 10:05:56 - INFO - __main__ - Step 115347: {'lr': 6.464287848424727e-05, 'samples': 22146624, 'steps': 115346, 'loss/train': 1.0641006231307983} 08/31/2021 10:05:56 - INFO - __main__ - Step 115348: {'lr': 6.463931753130752e-05, 'samples': 22146816, 'steps': 115347, 'loss/train': 1.2642943859100342} 08/31/2021 10:05:58 - INFO - __main__ - Step 115349: {'lr': 6.463575666188837e-05, 'samples': 22147008, 'steps': 115348, 'loss/train': 0.8921529054641724} 08/31/2021 10:05:58 - INFO - __main__ - Step 115350: {'lr': 6.463219587599148e-05, 'samples': 22147200, 'steps': 115349, 'loss/train': 1.5180467367172241} 08/31/2021 10:05:58 - INFO - __main__ - Step 115351: {'lr': 6.462863517361847e-05, 'samples': 22147392, 'steps': 115350, 'loss/train': 1.2129244804382324} 08/31/2021 10:05:59 - INFO - __main__ - Step 115352: {'lr': 6.462507455477092e-05, 'samples': 22147584, 'steps': 115351, 'loss/train': 0.9942366480827332} 08/31/2021 10:05:59 - INFO - __main__ - Step 115353: {'lr': 6.462151401945046e-05, 'samples': 22147776, 'steps': 115352, 'loss/train': 1.1735199689865112} 08/31/2021 10:06:01 - INFO - __main__ - Step 115354: {'lr': 6.461795356765868e-05, 'samples': 22147968, 'steps': 115353, 'loss/train': 0.7147969007492065} 08/31/2021 10:06:02 - INFO - __main__ - Step 115355: {'lr': 6.461439319939721e-05, 'samples': 22148160, 'steps': 115354, 'loss/train': 0.5147066712379456} 08/31/2021 10:06:02 - INFO - __main__ - Step 115356: {'lr': 6.461083291466762e-05, 'samples': 22148352, 'steps': 115355, 'loss/train': 0.6388947367668152} 08/31/2021 10:06:02 - INFO - __main__ - Step 115357: {'lr': 6.460727271347153e-05, 'samples': 22148544, 'steps': 115356, 'loss/train': 0.069981150329113} 08/31/2021 10:06:03 - INFO - __main__ - Step 115358: {'lr': 6.460371259581052e-05, 'samples': 22148736, 'steps': 115357, 'loss/train': 1.1353737115859985} 08/31/2021 10:06:04 - INFO - __main__ - Step 115359: {'lr': 6.460015256168625e-05, 'samples': 22148928, 'steps': 115358, 'loss/train': 0.041926462203264236} 08/31/2021 10:06:05 - INFO - __main__ - Step 115360: {'lr': 6.459659261110029e-05, 'samples': 22149120, 'steps': 115359, 'loss/train': 0.587546706199646} 08/31/2021 10:06:05 - INFO - __main__ - Step 115361: {'lr': 6.459303274405429e-05, 'samples': 22149312, 'steps': 115360, 'loss/train': 0.9512363076210022} 08/31/2021 10:06:05 - INFO - __main__ - Step 115362: {'lr': 6.458947296054977e-05, 'samples': 22149504, 'steps': 115361, 'loss/train': 1.4886744022369385} 08/31/2021 10:06:06 - INFO - __main__ - Step 115363: {'lr': 6.458591326058832e-05, 'samples': 22149696, 'steps': 115362, 'loss/train': 0.9063714146614075} 08/31/2021 10:06:07 - INFO - __main__ - Step 115364: {'lr': 6.458235364417164e-05, 'samples': 22149888, 'steps': 115363, 'loss/train': 1.0140011310577393} 08/31/2021 10:06:08 - INFO - __main__ - Step 115365: {'lr': 6.457879411130127e-05, 'samples': 22150080, 'steps': 115364, 'loss/train': 1.363171100616455} 08/31/2021 10:06:08 - INFO - __main__ - Step 115366: {'lr': 6.457523466197884e-05, 'samples': 22150272, 'steps': 115365, 'loss/train': 1.5685800313949585} 08/31/2021 10:06:08 - INFO - __main__ - Step 115367: {'lr': 6.457167529620597e-05, 'samples': 22150464, 'steps': 115366, 'loss/train': 1.7932993173599243} 08/31/2021 10:06:09 - INFO - __main__ - Step 115368: {'lr': 6.456811601398421e-05, 'samples': 22150656, 'steps': 115367, 'loss/train': 1.2924271821975708} 08/31/2021 10:06:10 - INFO - __main__ - Step 115369: {'lr': 6.456455681531522e-05, 'samples': 22150848, 'steps': 115368, 'loss/train': 0.49806469678878784} 08/31/2021 10:06:11 - INFO - __main__ - Step 115370: {'lr': 6.456099770020058e-05, 'samples': 22151040, 'steps': 115369, 'loss/train': 1.1053082942962646} 08/31/2021 10:06:11 - INFO - __main__ - Step 115371: {'lr': 6.455743866864186e-05, 'samples': 22151232, 'steps': 115370, 'loss/train': 1.3313807249069214} 08/31/2021 10:06:11 - INFO - __main__ - Step 115372: {'lr': 6.455387972064073e-05, 'samples': 22151424, 'steps': 115371, 'loss/train': 1.2475734949111938} 08/31/2021 10:06:12 - INFO - __main__ - Step 115373: {'lr': 6.455032085619874e-05, 'samples': 22151616, 'steps': 115372, 'loss/train': 0.804186224937439} 08/31/2021 10:06:13 - INFO - __main__ - Step 115374: {'lr': 6.454676207531751e-05, 'samples': 22151808, 'steps': 115373, 'loss/train': 0.8274465799331665} 08/31/2021 10:06:14 - INFO - __main__ - Step 115375: {'lr': 6.454320337799874e-05, 'samples': 22152000, 'steps': 115374, 'loss/train': 1.2164522409439087} 08/31/2021 10:06:14 - INFO - __main__ - Step 115376: {'lr': 6.453964476424387e-05, 'samples': 22152192, 'steps': 115375, 'loss/train': 0.8394412398338318} 08/31/2021 10:06:14 - INFO - __main__ - Step 115377: {'lr': 6.453608623405454e-05, 'samples': 22152384, 'steps': 115376, 'loss/train': 1.1704623699188232} 08/31/2021 10:06:15 - INFO - __main__ - Step 115378: {'lr': 6.453252778743244e-05, 'samples': 22152576, 'steps': 115377, 'loss/train': 1.685035228729248} 08/31/2021 10:06:16 - INFO - __main__ - Step 115379: {'lr': 6.452896942437909e-05, 'samples': 22152768, 'steps': 115378, 'loss/train': 1.0580674409866333} 08/31/2021 10:06:17 - INFO - __main__ - Step 115380: {'lr': 6.452541114489613e-05, 'samples': 22152960, 'steps': 115379, 'loss/train': 1.3346565961837769} 08/31/2021 10:06:17 - INFO - __main__ - Step 115381: {'lr': 6.452185294898514e-05, 'samples': 22153152, 'steps': 115380, 'loss/train': 1.394690990447998} 08/31/2021 10:06:17 - INFO - __main__ - Step 115382: {'lr': 6.451829483664775e-05, 'samples': 22153344, 'steps': 115381, 'loss/train': 0.9395819306373596} 08/31/2021 10:06:18 - INFO - __main__ - Step 115383: {'lr': 6.451473680788555e-05, 'samples': 22153536, 'steps': 115382, 'loss/train': 1.1620985269546509} 08/31/2021 10:06:20 - INFO - __main__ - Step 115384: {'lr': 6.451117886270017e-05, 'samples': 22153728, 'steps': 115383, 'loss/train': 1.4320738315582275} 08/31/2021 10:06:20 - INFO - __main__ - Step 115385: {'lr': 6.450762100109317e-05, 'samples': 22153920, 'steps': 115384, 'loss/train': 0.9986414313316345} 08/31/2021 10:06:21 - INFO - __main__ - Step 115386: {'lr': 6.450406322306618e-05, 'samples': 22154112, 'steps': 115385, 'loss/train': 1.4887118339538574} 08/31/2021 10:06:21 - INFO - __main__ - Step 115387: {'lr': 6.45005055286208e-05, 'samples': 22154304, 'steps': 115386, 'loss/train': 0.4605358839035034} 08/31/2021 10:06:21 - INFO - __main__ - Step 115388: {'lr': 6.44969479177587e-05, 'samples': 22154496, 'steps': 115387, 'loss/train': 0.952566385269165} 08/31/2021 10:06:23 - INFO - __main__ - Step 115389: {'lr': 6.449339039048136e-05, 'samples': 22154688, 'steps': 115388, 'loss/train': 0.9161017537117004} 08/31/2021 10:06:23 - INFO - __main__ - Step 115390: {'lr': 6.44898329467904e-05, 'samples': 22154880, 'steps': 115389, 'loss/train': 1.1436622142791748} 08/31/2021 10:06:24 - INFO - __main__ - Step 115391: {'lr': 6.448627558668748e-05, 'samples': 22155072, 'steps': 115390, 'loss/train': 1.1816343069076538} 08/31/2021 10:06:24 - INFO - __main__ - Step 115392: {'lr': 6.448271831017418e-05, 'samples': 22155264, 'steps': 115391, 'loss/train': 0.6915942430496216} 08/31/2021 10:06:24 - INFO - __main__ - Step 115393: {'lr': 6.44791611172521e-05, 'samples': 22155456, 'steps': 115392, 'loss/train': 0.6886703372001648} 08/31/2021 10:06:26 - INFO - __main__ - Step 115394: {'lr': 6.447560400792286e-05, 'samples': 22155648, 'steps': 115393, 'loss/train': 1.9945317506790161} 08/31/2021 10:06:26 - INFO - __main__ - Step 115395: {'lr': 6.447204698218803e-05, 'samples': 22155840, 'steps': 115394, 'loss/train': 1.4840482473373413} 08/31/2021 10:06:27 - INFO - __main__ - Step 115396: {'lr': 6.446849004004924e-05, 'samples': 22156032, 'steps': 115395, 'loss/train': 1.4741185903549194} 08/31/2021 10:06:27 - INFO - __main__ - Step 115397: {'lr': 6.446493318150809e-05, 'samples': 22156224, 'steps': 115396, 'loss/train': 1.5609463453292847} 08/31/2021 10:06:27 - INFO - __main__ - Step 115398: {'lr': 6.446137640656616e-05, 'samples': 22156416, 'steps': 115397, 'loss/train': 0.5980516672134399} 08/31/2021 10:06:28 - INFO - __main__ - Step 115399: {'lr': 6.445781971522507e-05, 'samples': 22156608, 'steps': 115398, 'loss/train': 1.1499824523925781} 08/31/2021 10:06:29 - INFO - __main__ - Step 115400: {'lr': 6.445426310748644e-05, 'samples': 22156800, 'steps': 115399, 'loss/train': 1.2839168310165405} 08/31/2021 10:06:30 - INFO - __main__ - Step 115401: {'lr': 6.445070658335195e-05, 'samples': 22156992, 'steps': 115400, 'loss/train': 1.5241343975067139} 08/31/2021 10:06:30 - INFO - __main__ - Step 115402: {'lr': 6.444715014282301e-05, 'samples': 22157184, 'steps': 115401, 'loss/train': 0.5447476506233215} 08/31/2021 10:06:30 - INFO - __main__ - Step 115403: {'lr': 6.444359378590131e-05, 'samples': 22157376, 'steps': 115402, 'loss/train': 0.7596403956413269} 08/31/2021 10:06:31 - INFO - __main__ - Step 115404: {'lr': 6.444003751258848e-05, 'samples': 22157568, 'steps': 115403, 'loss/train': 0.4513131082057953} 08/31/2021 10:06:32 - INFO - __main__ - Step 115405: {'lr': 6.44364813228861e-05, 'samples': 22157760, 'steps': 115404, 'loss/train': 0.8400315046310425} 08/31/2021 10:06:33 - INFO - __main__ - Step 115406: {'lr': 6.443292521679578e-05, 'samples': 22157952, 'steps': 115405, 'loss/train': 0.23476354777812958} 08/31/2021 10:06:33 - INFO - __main__ - Step 115407: {'lr': 6.442936919431913e-05, 'samples': 22158144, 'steps': 115406, 'loss/train': 1.757340431213379} 08/31/2021 10:06:33 - INFO - __main__ - Step 115408: {'lr': 6.442581325545774e-05, 'samples': 22158336, 'steps': 115407, 'loss/train': 0.6318113803863525} 08/31/2021 10:06:34 - INFO - __main__ - Step 115409: {'lr': 6.44222574002132e-05, 'samples': 22158528, 'steps': 115408, 'loss/train': 0.6848767995834351} 08/31/2021 10:06:35 - INFO - __main__ - Step 115410: {'lr': 6.441870162858714e-05, 'samples': 22158720, 'steps': 115409, 'loss/train': 0.793319582939148} 08/31/2021 10:06:36 - INFO - __main__ - Step 115411: {'lr': 6.441514594058115e-05, 'samples': 22158912, 'steps': 115410, 'loss/train': 0.9958963990211487} 08/31/2021 10:06:36 - INFO - __main__ - Step 115412: {'lr': 6.441159033619681e-05, 'samples': 22159104, 'steps': 115411, 'loss/train': 1.9326940774917603} 08/31/2021 10:06:37 - INFO - __main__ - Step 115413: {'lr': 6.440803481543578e-05, 'samples': 22159296, 'steps': 115412, 'loss/train': 1.1775892972946167} 08/31/2021 10:06:37 - INFO - __main__ - Step 115414: {'lr': 6.44044793782996e-05, 'samples': 22159488, 'steps': 115413, 'loss/train': 1.0135785341262817} 08/31/2021 10:06:38 - INFO - __main__ - Step 115415: {'lr': 6.440092402478997e-05, 'samples': 22159680, 'steps': 115414, 'loss/train': 0.6376634836196899} 08/31/2021 10:06:39 - INFO - __main__ - Step 115416: {'lr': 6.439736875490836e-05, 'samples': 22159872, 'steps': 115415, 'loss/train': 1.209572434425354} 08/31/2021 10:06:39 - INFO - __main__ - Step 115417: {'lr': 6.439381356865642e-05, 'samples': 22160064, 'steps': 115416, 'loss/train': 1.1518815755844116} 08/31/2021 10:06:39 - INFO - __main__ - Step 115418: {'lr': 6.439025846603578e-05, 'samples': 22160256, 'steps': 115417, 'loss/train': 1.5518728494644165} 08/31/2021 10:06:40 - INFO - __main__ - Step 115419: {'lr': 6.4386703447048e-05, 'samples': 22160448, 'steps': 115418, 'loss/train': 1.7073441743850708} 08/31/2021 10:06:41 - INFO - __main__ - Step 115420: {'lr': 6.438314851169472e-05, 'samples': 22160640, 'steps': 115419, 'loss/train': 0.7371989488601685} 08/31/2021 10:06:42 - INFO - __main__ - Step 115421: {'lr': 6.437959365997753e-05, 'samples': 22160832, 'steps': 115420, 'loss/train': 1.1844817399978638} 08/31/2021 10:06:42 - INFO - __main__ - Step 115422: {'lr': 6.437603889189805e-05, 'samples': 22161024, 'steps': 115421, 'loss/train': 1.4635015726089478} 08/31/2021 10:06:42 - INFO - __main__ - Step 115423: {'lr': 6.437248420745783e-05, 'samples': 22161216, 'steps': 115422, 'loss/train': 1.6698540449142456} 08/31/2021 10:06:43 - INFO - __main__ - Step 115424: {'lr': 6.436892960665853e-05, 'samples': 22161408, 'steps': 115423, 'loss/train': 1.1970163583755493} 08/31/2021 10:06:43 - INFO - __main__ - Step 115425: {'lr': 6.436537508950172e-05, 'samples': 22161600, 'steps': 115424, 'loss/train': 0.9035201668739319} 08/31/2021 10:06:45 - INFO - __main__ - Step 115426: {'lr': 6.4361820655989e-05, 'samples': 22161792, 'steps': 115425, 'loss/train': 1.1808923482894897} 08/31/2021 10:06:45 - INFO - __main__ - Step 115427: {'lr': 6.435826630612197e-05, 'samples': 22161984, 'steps': 115426, 'loss/train': 1.268509864807129} 08/31/2021 10:06:46 - INFO - __main__ - Step 115428: {'lr': 6.435471203990231e-05, 'samples': 22162176, 'steps': 115427, 'loss/train': 1.8708041906356812} 08/31/2021 10:06:46 - INFO - __main__ - Step 115429: {'lr': 6.43511578573315e-05, 'samples': 22162368, 'steps': 115428, 'loss/train': 4.306362628936768} 08/31/2021 10:06:46 - INFO - __main__ - Step 115430: {'lr': 6.43476037584112e-05, 'samples': 22162560, 'steps': 115429, 'loss/train': 0.4053018093109131} 08/31/2021 10:06:48 - INFO - __main__ - Step 115431: {'lr': 6.434404974314297e-05, 'samples': 22162752, 'steps': 115430, 'loss/train': 1.232051968574524} 08/31/2021 10:06:48 - INFO - __main__ - Step 115432: {'lr': 6.434049581152848e-05, 'samples': 22162944, 'steps': 115431, 'loss/train': 1.3649121522903442} 08/31/2021 10:06:49 - INFO - __main__ - Step 115433: {'lr': 6.43369419635693e-05, 'samples': 22163136, 'steps': 115432, 'loss/train': 1.1971913576126099} 08/31/2021 10:06:49 - INFO - __main__ - Step 115434: {'lr': 6.433338819926701e-05, 'samples': 22163328, 'steps': 115433, 'loss/train': 1.211427092552185} 08/31/2021 10:06:49 - INFO - __main__ - Step 115435: {'lr': 6.432983451862323e-05, 'samples': 22163520, 'steps': 115434, 'loss/train': 1.20323646068573} 08/31/2021 10:06:51 - INFO - __main__ - Step 115436: {'lr': 6.432628092163955e-05, 'samples': 22163712, 'steps': 115435, 'loss/train': 0.8128620982170105} 08/31/2021 10:06:52 - INFO - __main__ - Step 115437: {'lr': 6.432272740831759e-05, 'samples': 22163904, 'steps': 115436, 'loss/train': 0.7238688468933105} 08/31/2021 10:06:52 - INFO - __main__ - Step 115438: {'lr': 6.431917397865897e-05, 'samples': 22164096, 'steps': 115437, 'loss/train': 1.35456383228302} 08/31/2021 10:06:52 - INFO - __main__ - Step 115439: {'lr': 6.431562063266524e-05, 'samples': 22164288, 'steps': 115438, 'loss/train': 1.3371902704238892} 08/31/2021 10:06:53 - INFO - __main__ - Step 115440: {'lr': 6.431206737033804e-05, 'samples': 22164480, 'steps': 115439, 'loss/train': 1.0121911764144897} 08/31/2021 10:06:55 - INFO - __main__ - Step 115441: {'lr': 6.430851419167896e-05, 'samples': 22164672, 'steps': 115440, 'loss/train': 1.4126142263412476} 08/31/2021 10:06:55 - INFO - __main__ - Step 115442: {'lr': 6.430496109668965e-05, 'samples': 22164864, 'steps': 115441, 'loss/train': 1.1380113363265991} 08/31/2021 10:06:55 - INFO - __main__ - Step 115443: {'lr': 6.43014080853716e-05, 'samples': 22165056, 'steps': 115442, 'loss/train': 1.5299381017684937} 08/31/2021 10:06:56 - INFO - __main__ - Step 115444: {'lr': 6.429785515772646e-05, 'samples': 22165248, 'steps': 115443, 'loss/train': 1.5970628261566162} 08/31/2021 10:06:56 - INFO - __main__ - Step 115445: {'lr': 6.429430231375585e-05, 'samples': 22165440, 'steps': 115444, 'loss/train': 1.09916353225708} 08/31/2021 10:06:57 - INFO - __main__ - Step 115446: {'lr': 6.429074955346137e-05, 'samples': 22165632, 'steps': 115445, 'loss/train': 1.288620948791504} 08/31/2021 10:06:58 - INFO - __main__ - Step 115447: {'lr': 6.428719687684462e-05, 'samples': 22165824, 'steps': 115446, 'loss/train': 0.05796441435813904} 08/31/2021 10:06:58 - INFO - __main__ - Step 115448: {'lr': 6.428364428390714e-05, 'samples': 22166016, 'steps': 115447, 'loss/train': 0.46531856060028076} 08/31/2021 10:06:59 - INFO - __main__ - Step 115449: {'lr': 6.428009177465064e-05, 'samples': 22166208, 'steps': 115448, 'loss/train': 1.1906358003616333} 08/31/2021 10:06:59 - INFO - __main__ - Step 115450: {'lr': 6.427653934907665e-05, 'samples': 22166400, 'steps': 115449, 'loss/train': 1.370918869972229} 08/31/2021 10:07:00 - INFO - __main__ - Step 115451: {'lr': 6.427298700718678e-05, 'samples': 22166592, 'steps': 115450, 'loss/train': 1.1659023761749268} 08/31/2021 10:07:01 - INFO - __main__ - Step 115452: {'lr': 6.426943474898264e-05, 'samples': 22166784, 'steps': 115451, 'loss/train': 1.2814797163009644} 08/31/2021 10:07:01 - INFO - __main__ - Step 115453: {'lr': 6.42658825744658e-05, 'samples': 22166976, 'steps': 115452, 'loss/train': 1.137771725654602} 08/31/2021 10:07:02 - INFO - __main__ - Step 115454: {'lr': 6.426233048363795e-05, 'samples': 22167168, 'steps': 115453, 'loss/train': 0.6909841299057007} 08/31/2021 10:07:02 - INFO - __main__ - Step 115455: {'lr': 6.425877847650064e-05, 'samples': 22167360, 'steps': 115454, 'loss/train': 0.9791314005851746} 08/31/2021 10:07:03 - INFO - __main__ - Step 115456: {'lr': 6.425522655305541e-05, 'samples': 22167552, 'steps': 115455, 'loss/train': 0.31255611777305603} 08/31/2021 10:07:04 - INFO - __main__ - Step 115457: {'lr': 6.42516747133039e-05, 'samples': 22167744, 'steps': 115456, 'loss/train': 1.8450335264205933} 08/31/2021 10:07:05 - INFO - __main__ - Step 115458: {'lr': 6.424812295724775e-05, 'samples': 22167936, 'steps': 115457, 'loss/train': 1.4342238903045654} 08/31/2021 10:07:05 - INFO - __main__ - Step 115459: {'lr': 6.424457128488847e-05, 'samples': 22168128, 'steps': 115458, 'loss/train': 0.4745131731033325} 08/31/2021 10:07:05 - INFO - __main__ - Step 115460: {'lr': 6.424101969622779e-05, 'samples': 22168320, 'steps': 115459, 'loss/train': 1.3588889837265015} 08/31/2021 10:07:06 - INFO - __main__ - Step 115461: {'lr': 6.423746819126718e-05, 'samples': 22168512, 'steps': 115460, 'loss/train': 1.640899896621704} 08/31/2021 10:07:07 - INFO - __main__ - Step 115462: {'lr': 6.423391677000834e-05, 'samples': 22168704, 'steps': 115461, 'loss/train': 1.2613009214401245} 08/31/2021 10:07:08 - INFO - __main__ - Step 115463: {'lr': 6.423036543245281e-05, 'samples': 22168896, 'steps': 115462, 'loss/train': 0.8949066996574402} 08/31/2021 10:07:08 - INFO - __main__ - Step 115464: {'lr': 6.422681417860221e-05, 'samples': 22169088, 'steps': 115463, 'loss/train': 0.9439465999603271} 08/31/2021 10:07:08 - INFO - __main__ - Step 115465: {'lr': 6.422326300845815e-05, 'samples': 22169280, 'steps': 115464, 'loss/train': 1.2098416090011597} 08/31/2021 10:07:09 - INFO - __main__ - Step 115466: {'lr': 6.421971192202222e-05, 'samples': 22169472, 'steps': 115465, 'loss/train': 1.1626697778701782} 08/31/2021 10:07:10 - INFO - __main__ - Step 115467: {'lr': 6.421616091929602e-05, 'samples': 22169664, 'steps': 115466, 'loss/train': 1.2184264659881592} 08/31/2021 10:07:11 - INFO - __main__ - Step 115468: {'lr': 6.421261000028114e-05, 'samples': 22169856, 'steps': 115467, 'loss/train': 0.5114278197288513} 08/31/2021 10:07:11 - INFO - __main__ - Step 115469: {'lr': 6.420905916497927e-05, 'samples': 22170048, 'steps': 115468, 'loss/train': 0.9076389670372009} 08/31/2021 10:07:11 - INFO - __main__ - Step 115470: {'lr': 6.420550841339187e-05, 'samples': 22170240, 'steps': 115469, 'loss/train': 1.0993926525115967} 08/31/2021 10:07:12 - INFO - __main__ - Step 115471: {'lr': 6.420195774552059e-05, 'samples': 22170432, 'steps': 115470, 'loss/train': 1.5209845304489136} 08/31/2021 10:07:13 - INFO - __main__ - Step 115472: {'lr': 6.419840716136705e-05, 'samples': 22170624, 'steps': 115471, 'loss/train': 1.7766779661178589} 08/31/2021 10:07:14 - INFO - __main__ - Step 115473: {'lr': 6.419485666093283e-05, 'samples': 22170816, 'steps': 115472, 'loss/train': 1.0960776805877686} 08/31/2021 10:07:14 - INFO - __main__ - Step 115474: {'lr': 6.419130624421954e-05, 'samples': 22171008, 'steps': 115473, 'loss/train': 1.0158506631851196} 08/31/2021 10:07:14 - INFO - __main__ - Step 115475: {'lr': 6.418775591122881e-05, 'samples': 22171200, 'steps': 115474, 'loss/train': 1.0948320627212524} 08/31/2021 10:07:15 - INFO - __main__ - Step 115476: {'lr': 6.418420566196217e-05, 'samples': 22171392, 'steps': 115475, 'loss/train': 0.2830480933189392} 08/31/2021 10:07:17 - INFO - __main__ - Step 115477: {'lr': 6.418065549642127e-05, 'samples': 22171584, 'steps': 115476, 'loss/train': 1.4020942449569702} 08/31/2021 10:07:17 - INFO - __main__ - Step 115478: {'lr': 6.41771054146077e-05, 'samples': 22171776, 'steps': 115477, 'loss/train': 1.3434981107711792} 08/31/2021 10:07:18 - INFO - __main__ - Step 115479: {'lr': 6.417355541652306e-05, 'samples': 22171968, 'steps': 115478, 'loss/train': 1.9355568885803223} 08/31/2021 10:07:18 - INFO - __main__ - Step 115480: {'lr': 6.417000550216896e-05, 'samples': 22172160, 'steps': 115479, 'loss/train': 0.8682845830917358} 08/31/2021 10:07:18 - INFO - __main__ - Step 115481: {'lr': 6.416645567154697e-05, 'samples': 22172352, 'steps': 115480, 'loss/train': 0.9194126129150391} 08/31/2021 10:07:19 - INFO - __main__ - Step 115482: {'lr': 6.416290592465879e-05, 'samples': 22172544, 'steps': 115481, 'loss/train': 0.9353677034378052} 08/31/2021 10:07:20 - INFO - __main__ - Step 115483: {'lr': 6.415935626150587e-05, 'samples': 22172736, 'steps': 115482, 'loss/train': 0.8603572249412537} 08/31/2021 10:07:21 - INFO - __main__ - Step 115484: {'lr': 6.415580668208987e-05, 'samples': 22172928, 'steps': 115483, 'loss/train': 0.9662467241287231} 08/31/2021 10:07:21 - INFO - __main__ - Step 115485: {'lr': 6.41522571864124e-05, 'samples': 22173120, 'steps': 115484, 'loss/train': 1.7762959003448486} 08/31/2021 10:07:21 - INFO - __main__ - Step 115486: {'lr': 6.414870777447504e-05, 'samples': 22173312, 'steps': 115485, 'loss/train': 1.3115178346633911} 08/31/2021 10:07:22 - INFO - __main__ - Step 115487: {'lr': 6.414515844627942e-05, 'samples': 22173504, 'steps': 115486, 'loss/train': 1.2935411930084229} 08/31/2021 10:07:24 - INFO - __main__ - Step 115488: {'lr': 6.414160920182712e-05, 'samples': 22173696, 'steps': 115487, 'loss/train': 1.301089882850647} 08/31/2021 10:07:24 - INFO - __main__ - Step 115489: {'lr': 6.413806004111974e-05, 'samples': 22173888, 'steps': 115488, 'loss/train': 1.5766915082931519} 08/31/2021 10:07:25 - INFO - __main__ - Step 115490: {'lr': 6.41345109641589e-05, 'samples': 22174080, 'steps': 115489, 'loss/train': 0.6102985143661499} 08/31/2021 10:07:25 - INFO - __main__ - Step 115491: {'lr': 6.413096197094615e-05, 'samples': 22174272, 'steps': 115490, 'loss/train': 1.2305322885513306} 08/31/2021 10:07:26 - INFO - __main__ - Step 115492: {'lr': 6.412741306148315e-05, 'samples': 22174464, 'steps': 115491, 'loss/train': 1.1121952533721924} 08/31/2021 10:07:27 - INFO - __main__ - Step 115493: {'lr': 6.412386423577143e-05, 'samples': 22174656, 'steps': 115492, 'loss/train': 1.9036544561386108} 08/31/2021 10:07:28 - INFO - __main__ - Step 115494: {'lr': 6.412031549381266e-05, 'samples': 22174848, 'steps': 115493, 'loss/train': 0.556679904460907} 08/31/2021 10:07:28 - INFO - __main__ - Step 115495: {'lr': 6.411676683560841e-05, 'samples': 22175040, 'steps': 115494, 'loss/train': 1.075405240058899} 08/31/2021 10:07:28 - INFO - __main__ - Step 115496: {'lr': 6.411321826116034e-05, 'samples': 22175232, 'steps': 115495, 'loss/train': 1.242224931716919} 08/31/2021 10:07:29 - INFO - __main__ - Step 115497: {'lr': 6.410966977046993e-05, 'samples': 22175424, 'steps': 115496, 'loss/train': 1.8948180675506592} 08/31/2021 10:07:30 - INFO - __main__ - Step 115498: {'lr': 6.41061213635388e-05, 'samples': 22175616, 'steps': 115497, 'loss/train': 0.6974804997444153} 08/31/2021 10:07:31 - INFO - __main__ - Step 115499: {'lr': 6.410257304036859e-05, 'samples': 22175808, 'steps': 115498, 'loss/train': 0.9983296990394592} 08/31/2021 10:07:31 - INFO - __main__ - Step 115500: {'lr': 6.409902480096091e-05, 'samples': 22176000, 'steps': 115499, 'loss/train': 0.6615739464759827} 08/31/2021 10:07:31 - INFO - __main__ - Step 115501: {'lr': 6.409547664531735e-05, 'samples': 22176192, 'steps': 115500, 'loss/train': 1.5689669847488403} 08/31/2021 10:07:32 - INFO - __main__ - Step 115502: {'lr': 6.409192857343946e-05, 'samples': 22176384, 'steps': 115501, 'loss/train': 0.9089809656143188} 08/31/2021 10:07:32 - INFO - __main__ - Step 115503: {'lr': 6.40883805853289e-05, 'samples': 22176576, 'steps': 115502, 'loss/train': 1.4500007629394531} 08/31/2021 10:07:34 - INFO - __main__ - Step 115504: {'lr': 6.408483268098725e-05, 'samples': 22176768, 'steps': 115503, 'loss/train': 0.915209949016571} 08/31/2021 10:07:34 - INFO - __main__ - Step 115505: {'lr': 6.408128486041611e-05, 'samples': 22176960, 'steps': 115504, 'loss/train': 0.01680145226418972} 08/31/2021 10:07:35 - INFO - __main__ - Step 115506: {'lr': 6.407773712361706e-05, 'samples': 22177152, 'steps': 115505, 'loss/train': 1.0094739198684692} 08/31/2021 10:07:35 - INFO - __main__ - Step 115507: {'lr': 6.407418947059173e-05, 'samples': 22177344, 'steps': 115506, 'loss/train': 1.2799633741378784} 08/31/2021 10:07:35 - INFO - __main__ - Step 115508: {'lr': 6.407064190134168e-05, 'samples': 22177536, 'steps': 115507, 'loss/train': 0.983781635761261} 08/31/2021 10:07:36 - INFO - __main__ - Step 115509: {'lr': 6.406709441586863e-05, 'samples': 22177728, 'steps': 115508, 'loss/train': 1.2015221118927002} 08/31/2021 10:07:37 - INFO - __main__ - Step 115510: {'lr': 6.4063547014174e-05, 'samples': 22177920, 'steps': 115509, 'loss/train': 0.5506202578544617} 08/31/2021 10:07:38 - INFO - __main__ - Step 115511: {'lr': 6.405999969625944e-05, 'samples': 22178112, 'steps': 115510, 'loss/train': 0.9201024770736694} 08/31/2021 10:07:38 - INFO - __main__ - Step 115512: {'lr': 6.40564524621266e-05, 'samples': 22178304, 'steps': 115511, 'loss/train': 0.34538376331329346} 08/31/2021 10:07:38 - INFO - __main__ - Step 115513: {'lr': 6.405290531177704e-05, 'samples': 22178496, 'steps': 115512, 'loss/train': 1.074621558189392} 08/31/2021 10:07:39 - INFO - __main__ - Step 115514: {'lr': 6.404935824521238e-05, 'samples': 22178688, 'steps': 115513, 'loss/train': 1.3174242973327637} 08/31/2021 10:07:41 - INFO - __main__ - Step 115515: {'lr': 6.40458112624342e-05, 'samples': 22178880, 'steps': 115514, 'loss/train': 1.218347191810608} 08/31/2021 10:07:41 - INFO - __main__ - Step 115516: {'lr': 6.404226436344412e-05, 'samples': 22179072, 'steps': 115515, 'loss/train': 1.4029526710510254} 08/31/2021 10:07:41 - INFO - __main__ - Step 115517: {'lr': 6.403871754824372e-05, 'samples': 22179264, 'steps': 115516, 'loss/train': 0.05125301331281662} 08/31/2021 10:07:42 - INFO - __main__ - Step 115518: {'lr': 6.40351708168346e-05, 'samples': 22179456, 'steps': 115517, 'loss/train': 0.8069950938224792} 08/31/2021 10:07:42 - INFO - __main__ - Step 115519: {'lr': 6.403162416921837e-05, 'samples': 22179648, 'steps': 115518, 'loss/train': 1.498365879058838} 08/31/2021 10:07:44 - INFO - __main__ - Step 115520: {'lr': 6.402807760539661e-05, 'samples': 22179840, 'steps': 115519, 'loss/train': 0.827486515045166} 08/31/2021 10:07:44 - INFO - __main__ - Step 115521: {'lr': 6.402453112537093e-05, 'samples': 22180032, 'steps': 115520, 'loss/train': 1.0024560689926147} 08/31/2021 10:07:45 - INFO - __main__ - Step 115522: {'lr': 6.4020984729143e-05, 'samples': 22180224, 'steps': 115521, 'loss/train': 1.1994273662567139} 08/31/2021 10:07:45 - INFO - __main__ - Step 115523: {'lr': 6.401743841671429e-05, 'samples': 22180416, 'steps': 115522, 'loss/train': 0.20734304189682007} 08/31/2021 10:07:45 - INFO - __main__ - Step 115524: {'lr': 6.401389218808643e-05, 'samples': 22180608, 'steps': 115523, 'loss/train': 0.8720892667770386} 08/31/2021 10:07:47 - INFO - __main__ - Step 115525: {'lr': 6.401034604326105e-05, 'samples': 22180800, 'steps': 115524, 'loss/train': 0.6935456991195679} 08/31/2021 10:07:47 - INFO - __main__ - Step 115526: {'lr': 6.400679998223974e-05, 'samples': 22180992, 'steps': 115525, 'loss/train': 0.2782285809516907} 08/31/2021 10:07:48 - INFO - __main__ - Step 115527: {'lr': 6.40032540050241e-05, 'samples': 22181184, 'steps': 115526, 'loss/train': 0.040171895176172256} 08/31/2021 10:07:48 - INFO - __main__ - Step 115528: {'lr': 6.399970811161571e-05, 'samples': 22181376, 'steps': 115527, 'loss/train': 1.0178357362747192} 08/31/2021 10:07:48 - INFO - __main__ - Step 115529: {'lr': 6.399616230201619e-05, 'samples': 22181568, 'steps': 115528, 'loss/train': 1.2125132083892822} 08/31/2021 10:07:50 - INFO - __main__ - Step 115530: {'lr': 6.399261657622712e-05, 'samples': 22181760, 'steps': 115529, 'loss/train': 2.4235057830810547} 08/31/2021 10:07:50 - INFO - __main__ - Step 115531: {'lr': 6.398907093425013e-05, 'samples': 22181952, 'steps': 115530, 'loss/train': 4.372710704803467} 08/31/2021 10:07:51 - INFO - __main__ - Step 115532: {'lr': 6.398552537608676e-05, 'samples': 22182144, 'steps': 115531, 'loss/train': 0.8946360945701599} 08/31/2021 10:07:51 - INFO - __main__ - Step 115533: {'lr': 6.398197990173874e-05, 'samples': 22182336, 'steps': 115532, 'loss/train': 1.469026803970337} 08/31/2021 10:07:51 - INFO - __main__ - Step 115534: {'lr': 6.39784345112075e-05, 'samples': 22182528, 'steps': 115533, 'loss/train': 1.2262604236602783} 08/31/2021 10:07:53 - INFO - __main__ - Step 115535: {'lr': 6.397488920449468e-05, 'samples': 22182720, 'steps': 115534, 'loss/train': 1.060761570930481} 08/31/2021 10:07:53 - INFO - __main__ - Step 115536: {'lr': 6.397134398160192e-05, 'samples': 22182912, 'steps': 115535, 'loss/train': 1.2105329036712646} 08/31/2021 10:07:54 - INFO - __main__ - Step 115537: {'lr': 6.396779884253081e-05, 'samples': 22183104, 'steps': 115536, 'loss/train': 0.983618974685669} 08/31/2021 10:07:54 - INFO - __main__ - Step 115538: {'lr': 6.396425378728294e-05, 'samples': 22183296, 'steps': 115537, 'loss/train': 0.7748263478279114} 08/31/2021 10:07:54 - INFO - __main__ - Step 115539: {'lr': 6.396070881585988e-05, 'samples': 22183488, 'steps': 115538, 'loss/train': 1.1802136898040771} 08/31/2021 10:07:55 - INFO - __main__ - Step 115540: {'lr': 6.395716392826328e-05, 'samples': 22183680, 'steps': 115539, 'loss/train': 1.137134075164795} 08/31/2021 10:07:56 - INFO - __main__ - Step 115541: {'lr': 6.395361912449472e-05, 'samples': 22183872, 'steps': 115540, 'loss/train': 2.650074005126953} 08/31/2021 10:07:57 - INFO - __main__ - Step 115542: {'lr': 6.395007440455577e-05, 'samples': 22184064, 'steps': 115541, 'loss/train': 1.282038688659668} 08/31/2021 10:07:57 - INFO - __main__ - Step 115543: {'lr': 6.394652976844804e-05, 'samples': 22184256, 'steps': 115542, 'loss/train': 0.9893079400062561} 08/31/2021 10:07:57 - INFO - __main__ - Step 115544: {'lr': 6.39429852161732e-05, 'samples': 22184448, 'steps': 115543, 'loss/train': 1.3052469491958618} 08/31/2021 10:07:58 - INFO - __main__ - Step 115545: {'lr': 6.393944074773273e-05, 'samples': 22184640, 'steps': 115544, 'loss/train': 1.0566600561141968} 08/31/2021 10:07:59 - INFO - __main__ - Step 115546: {'lr': 6.393589636312827e-05, 'samples': 22184832, 'steps': 115545, 'loss/train': 0.5982990860939026} 08/31/2021 10:08:00 - INFO - __main__ - Step 115547: {'lr': 6.393235206236143e-05, 'samples': 22185024, 'steps': 115546, 'loss/train': 0.9745377898216248} 08/31/2021 10:08:00 - INFO - __main__ - Step 115548: {'lr': 6.392880784543378e-05, 'samples': 22185216, 'steps': 115547, 'loss/train': 1.144943118095398} 08/31/2021 10:08:00 - INFO - __main__ - Step 115549: {'lr': 6.392526371234694e-05, 'samples': 22185408, 'steps': 115548, 'loss/train': 1.0056629180908203} 08/31/2021 10:08:01 - INFO - __main__ - Step 115550: {'lr': 6.392171966310253e-05, 'samples': 22185600, 'steps': 115549, 'loss/train': 0.9838905930519104} 08/31/2021 10:08:03 - INFO - __main__ - Step 115551: {'lr': 6.391817569770211e-05, 'samples': 22185792, 'steps': 115550, 'loss/train': 1.1966638565063477} 08/31/2021 10:08:03 - INFO - __main__ - Step 115552: {'lr': 6.391463181614726e-05, 'samples': 22185984, 'steps': 115551, 'loss/train': 0.9654478430747986} 08/31/2021 10:08:04 - INFO - __main__ - Step 115553: {'lr': 6.391108801843964e-05, 'samples': 22186176, 'steps': 115552, 'loss/train': 1.1908918619155884} 08/31/2021 10:08:04 - INFO - __main__ - Step 115554: {'lr': 6.390754430458081e-05, 'samples': 22186368, 'steps': 115553, 'loss/train': 0.4480881690979004} 08/31/2021 10:08:04 - INFO - __main__ - Step 115555: {'lr': 6.390400067457245e-05, 'samples': 22186560, 'steps': 115554, 'loss/train': 1.363724946975708} 08/31/2021 10:08:06 - INFO - __main__ - Step 115556: {'lr': 6.390045712841597e-05, 'samples': 22186752, 'steps': 115555, 'loss/train': 1.8014330863952637} 08/31/2021 10:08:07 - INFO - __main__ - Step 115557: {'lr': 6.389691366611308e-05, 'samples': 22186944, 'steps': 115556, 'loss/train': 1.2871390581130981} 08/31/2021 10:08:07 - INFO - __main__ - Step 115558: {'lr': 6.389337028766539e-05, 'samples': 22187136, 'steps': 115557, 'loss/train': 1.5246660709381104} 08/31/2021 10:08:08 - INFO - __main__ - Step 115559: {'lr': 6.388982699307447e-05, 'samples': 22187328, 'steps': 115558, 'loss/train': 1.4716310501098633} 08/31/2021 10:08:08 - INFO - __main__ - Step 115560: {'lr': 6.388628378234191e-05, 'samples': 22187520, 'steps': 115559, 'loss/train': 0.5616650581359863} 08/31/2021 10:08:10 - INFO - __main__ - Step 115561: {'lr': 6.388274065546931e-05, 'samples': 22187712, 'steps': 115560, 'loss/train': 0.04812999069690704} 08/31/2021 10:08:10 - INFO - __main__ - Step 115562: {'lr': 6.38791976124583e-05, 'samples': 22187904, 'steps': 115561, 'loss/train': 1.585126280784607} 08/31/2021 10:08:10 - INFO - __main__ - Step 115563: {'lr': 6.387565465331044e-05, 'samples': 22188096, 'steps': 115562, 'loss/train': 1.367654800415039} 08/31/2021 10:08:11 - INFO - __main__ - Step 115564: {'lr': 6.387211177802735e-05, 'samples': 22188288, 'steps': 115563, 'loss/train': 0.28676798939704895} 08/31/2021 10:08:11 - INFO - __main__ - Step 115565: {'lr': 6.386856898661059e-05, 'samples': 22188480, 'steps': 115564, 'loss/train': 0.9956547021865845} 08/31/2021 10:08:11 - INFO - __main__ - Step 115566: {'lr': 6.386502627906188e-05, 'samples': 22188672, 'steps': 115565, 'loss/train': 0.7345286011695862} 08/31/2021 10:08:14 - INFO - __main__ - Step 115567: {'lr': 6.386148365538263e-05, 'samples': 22188864, 'steps': 115566, 'loss/train': 1.445657730102539} 08/31/2021 10:08:14 - INFO - __main__ - Step 115568: {'lr': 6.385794111557453e-05, 'samples': 22189056, 'steps': 115567, 'loss/train': 0.9610534906387329} 08/31/2021 10:08:15 - INFO - __main__ - Step 115569: {'lr': 6.385439865963916e-05, 'samples': 22189248, 'steps': 115568, 'loss/train': 0.762020468711853} 08/31/2021 10:08:15 - INFO - __main__ - Step 115570: {'lr': 6.385085628757811e-05, 'samples': 22189440, 'steps': 115569, 'loss/train': 0.9129853248596191} 08/31/2021 10:08:15 - INFO - __main__ - Step 115571: {'lr': 6.384731399939303e-05, 'samples': 22189632, 'steps': 115570, 'loss/train': 0.2995575964450836} 08/31/2021 10:08:16 - INFO - __main__ - Step 115572: {'lr': 6.384377179508543e-05, 'samples': 22189824, 'steps': 115571, 'loss/train': 0.26701465249061584} 08/31/2021 10:08:17 - INFO - __main__ - Step 115573: {'lr': 6.384022967465699e-05, 'samples': 22190016, 'steps': 115572, 'loss/train': 0.39913368225097656} 08/31/2021 10:08:18 - INFO - __main__ - Step 115574: {'lr': 6.383668763810926e-05, 'samples': 22190208, 'steps': 115573, 'loss/train': 1.2596224546432495} 08/31/2021 10:08:18 - INFO - __main__ - Step 115575: {'lr': 6.383314568544385e-05, 'samples': 22190400, 'steps': 115574, 'loss/train': 1.485504150390625} 08/31/2021 10:08:18 - INFO - __main__ - Step 115576: {'lr': 6.382960381666244e-05, 'samples': 22190592, 'steps': 115575, 'loss/train': 0.508452832698822} 08/31/2021 10:08:19 - INFO - __main__ - Step 115577: {'lr': 6.382606203176644e-05, 'samples': 22190784, 'steps': 115576, 'loss/train': 1.3888148069381714} 08/31/2021 10:08:20 - INFO - __main__ - Step 115578: {'lr': 6.382252033075755e-05, 'samples': 22190976, 'steps': 115577, 'loss/train': 1.365929365158081} 08/31/2021 10:08:21 - INFO - __main__ - Step 115579: {'lr': 6.381897871363737e-05, 'samples': 22191168, 'steps': 115578, 'loss/train': 1.606407642364502} 08/31/2021 10:08:21 - INFO - __main__ - Step 115580: {'lr': 6.381543718040747e-05, 'samples': 22191360, 'steps': 115579, 'loss/train': 1.8021999597549438} 08/31/2021 10:08:21 - INFO - __main__ - Step 115581: {'lr': 6.381189573106947e-05, 'samples': 22191552, 'steps': 115580, 'loss/train': 0.803679883480072} 08/31/2021 10:08:22 - INFO - __main__ - Step 115582: {'lr': 6.380835436562496e-05, 'samples': 22191744, 'steps': 115581, 'loss/train': 1.5282361507415771} 08/31/2021 10:08:23 - INFO - __main__ - Step 115583: {'lr': 6.380481308407552e-05, 'samples': 22191936, 'steps': 115582, 'loss/train': 1.3603401184082031} 08/31/2021 10:08:24 - INFO - __main__ - Step 115584: {'lr': 6.380127188642277e-05, 'samples': 22192128, 'steps': 115583, 'loss/train': 1.0942224264144897} 08/31/2021 10:08:24 - INFO - __main__ - Step 115585: {'lr': 6.379773077266829e-05, 'samples': 22192320, 'steps': 115584, 'loss/train': 1.134376049041748} 08/31/2021 10:08:24 - INFO - __main__ - Step 115586: {'lr': 6.379418974281367e-05, 'samples': 22192512, 'steps': 115585, 'loss/train': 1.0588332414627075} 08/31/2021 10:08:25 - INFO - __main__ - Step 115587: {'lr': 6.379064879686053e-05, 'samples': 22192704, 'steps': 115586, 'loss/train': 1.2739603519439697} 08/31/2021 10:08:25 - INFO - __main__ - Step 115588: {'lr': 6.378710793481044e-05, 'samples': 22192896, 'steps': 115587, 'loss/train': 1.486833095550537} 08/31/2021 10:08:27 - INFO - __main__ - Step 115589: {'lr': 6.3783567156665e-05, 'samples': 22193088, 'steps': 115588, 'loss/train': 0.882110059261322} 08/31/2021 10:08:27 - INFO - __main__ - Step 115590: {'lr': 6.37800264624259e-05, 'samples': 22193280, 'steps': 115589, 'loss/train': 1.6334880590438843} 08/31/2021 10:08:28 - INFO - __main__ - Step 115591: {'lr': 6.377648585209455e-05, 'samples': 22193472, 'steps': 115590, 'loss/train': 1.2712912559509277} 08/31/2021 10:08:28 - INFO - __main__ - Step 115592: {'lr': 6.377294532567265e-05, 'samples': 22193664, 'steps': 115591, 'loss/train': 0.027070293202996254} 08/31/2021 10:08:28 - INFO - __main__ - Step 115593: {'lr': 6.376940488316179e-05, 'samples': 22193856, 'steps': 115592, 'loss/train': 0.7391260862350464} 08/31/2021 10:08:30 - INFO - __main__ - Step 115594: {'lr': 6.376586452456359e-05, 'samples': 22194048, 'steps': 115593, 'loss/train': 0.7782939672470093} 08/31/2021 10:08:30 - INFO - __main__ - Step 115595: {'lr': 6.37623242498796e-05, 'samples': 22194240, 'steps': 115594, 'loss/train': 0.4744431972503662} 08/31/2021 10:08:31 - INFO - __main__ - Step 115596: {'lr': 6.375878405911143e-05, 'samples': 22194432, 'steps': 115595, 'loss/train': 1.2763755321502686} 08/31/2021 10:08:31 - INFO - __main__ - Step 115597: {'lr': 6.375524395226064e-05, 'samples': 22194624, 'steps': 115596, 'loss/train': 1.1344951391220093} 08/31/2021 10:08:31 - INFO - __main__ - Step 115598: {'lr': 6.375170392932891e-05, 'samples': 22194816, 'steps': 115597, 'loss/train': 1.4058191776275635} 08/31/2021 10:08:33 - INFO - __main__ - Step 115599: {'lr': 6.37481639903178e-05, 'samples': 22195008, 'steps': 115598, 'loss/train': 1.2718464136123657} 08/31/2021 10:08:34 - INFO - __main__ - Step 115600: {'lr': 6.374462413522886e-05, 'samples': 22195200, 'steps': 115599, 'loss/train': 2.4132983684539795} 08/31/2021 10:08:34 - INFO - __main__ - Step 115601: {'lr': 6.374108436406373e-05, 'samples': 22195392, 'steps': 115600, 'loss/train': 2.6835615634918213} 08/31/2021 10:08:34 - INFO - __main__ - Step 115602: {'lr': 6.373754467682399e-05, 'samples': 22195584, 'steps': 115601, 'loss/train': 1.6396323442459106} 08/31/2021 10:08:35 - INFO - __main__ - Step 115603: {'lr': 6.373400507351132e-05, 'samples': 22195776, 'steps': 115602, 'loss/train': 0.030549582093954086} 08/31/2021 10:08:35 - INFO - __main__ - Step 115604: {'lr': 6.373046555412715e-05, 'samples': 22195968, 'steps': 115603, 'loss/train': 1.4405875205993652} 08/31/2021 10:08:37 - INFO - __main__ - Step 115605: {'lr': 6.372692611867314e-05, 'samples': 22196160, 'steps': 115604, 'loss/train': 0.02520635351538658} 08/31/2021 10:08:38 - INFO - __main__ - Step 115606: {'lr': 6.372338676715095e-05, 'samples': 22196352, 'steps': 115605, 'loss/train': 1.6072182655334473} 08/31/2021 10:08:38 - INFO - __main__ - Step 115607: {'lr': 6.371984749956208e-05, 'samples': 22196544, 'steps': 115606, 'loss/train': 1.2866722345352173} 08/31/2021 10:08:39 - INFO - __main__ - Step 115608: {'lr': 6.371630831590822e-05, 'samples': 22196736, 'steps': 115607, 'loss/train': 1.048200249671936} 08/31/2021 10:08:39 - INFO - __main__ - Step 115609: {'lr': 6.371276921619087e-05, 'samples': 22196928, 'steps': 115608, 'loss/train': 1.4446572065353394} 08/31/2021 10:08:40 - INFO - __main__ - Step 115610: {'lr': 6.37092302004117e-05, 'samples': 22197120, 'steps': 115609, 'loss/train': 0.03954191878437996} 08/31/2021 10:08:41 - INFO - __main__ - Step 115611: {'lr': 6.370569126857225e-05, 'samples': 22197312, 'steps': 115610, 'loss/train': 0.8854306936264038} 08/31/2021 10:08:41 - INFO - __main__ - Step 115612: {'lr': 6.370215242067418e-05, 'samples': 22197504, 'steps': 115611, 'loss/train': 1.0229060649871826} 08/31/2021 10:08:42 - INFO - __main__ - Step 115613: {'lr': 6.369861365671903e-05, 'samples': 22197696, 'steps': 115612, 'loss/train': 0.570167601108551} 08/31/2021 10:08:42 - INFO - __main__ - Step 115614: {'lr': 6.36950749767084e-05, 'samples': 22197888, 'steps': 115613, 'loss/train': 1.0826479196548462} 08/31/2021 10:08:44 - INFO - __main__ - Step 115615: {'lr': 6.36915363806439e-05, 'samples': 22198080, 'steps': 115614, 'loss/train': 1.0423996448516846} 08/31/2021 10:08:45 - INFO - __main__ - Step 115616: {'lr': 6.368799786852711e-05, 'samples': 22198272, 'steps': 115615, 'loss/train': 0.10989872366189957} 08/31/2021 10:08:45 - INFO - __main__ - Step 115617: {'lr': 6.368445944035972e-05, 'samples': 22198464, 'steps': 115616, 'loss/train': 0.10974445194005966} 08/31/2021 10:08:45 - INFO - __main__ - Step 115618: {'lr': 6.368092109614315e-05, 'samples': 22198656, 'steps': 115617, 'loss/train': 1.4935742616653442} 08/31/2021 10:08:46 - INFO - __main__ - Step 115619: {'lr': 6.36773828358791e-05, 'samples': 22198848, 'steps': 115618, 'loss/train': 0.8097723722457886} 08/31/2021 10:08:46 - INFO - __main__ - Step 115620: {'lr': 6.367384465956913e-05, 'samples': 22199040, 'steps': 115619, 'loss/train': 1.695543885231018} 08/31/2021 10:08:48 - INFO - __main__ - Step 115621: {'lr': 6.367030656721484e-05, 'samples': 22199232, 'steps': 115620, 'loss/train': 0.7257794141769409} 08/31/2021 10:08:48 - INFO - __main__ - Step 115622: {'lr': 6.366676855881786e-05, 'samples': 22199424, 'steps': 115621, 'loss/train': 0.033813878893852234} 08/31/2021 10:08:48 - INFO - __main__ - Step 115623: {'lr': 6.366323063437976e-05, 'samples': 22199616, 'steps': 115622, 'loss/train': 1.5609002113342285} 08/31/2021 10:08:49 - INFO - __main__ - Step 115624: {'lr': 6.365969279390213e-05, 'samples': 22199808, 'steps': 115623, 'loss/train': 0.701721727848053} 08/31/2021 10:08:49 - INFO - __main__ - Step 115625: {'lr': 6.365615503738656e-05, 'samples': 22200000, 'steps': 115624, 'loss/train': 1.1650499105453491} 08/31/2021 10:08:51 - INFO - __main__ - Step 115626: {'lr': 6.365261736483464e-05, 'samples': 22200192, 'steps': 115625, 'loss/train': 0.7720422744750977} 08/31/2021 10:08:51 - INFO - __main__ - Step 115627: {'lr': 6.364907977624799e-05, 'samples': 22200384, 'steps': 115626, 'loss/train': 0.9543424248695374} 08/31/2021 10:08:52 - INFO - __main__ - Step 115628: {'lr': 6.364554227162819e-05, 'samples': 22200576, 'steps': 115627, 'loss/train': 2.1079180240631104} 08/31/2021 10:08:52 - INFO - __main__ - Step 115629: {'lr': 6.364200485097682e-05, 'samples': 22200768, 'steps': 115628, 'loss/train': 1.8908113241195679} 08/31/2021 10:08:52 - INFO - __main__ - Step 115630: {'lr': 6.363846751429555e-05, 'samples': 22200960, 'steps': 115629, 'loss/train': 1.4523546695709229} 08/31/2021 10:08:54 - INFO - __main__ - Step 115631: {'lr': 6.363493026158587e-05, 'samples': 22201152, 'steps': 115630, 'loss/train': 1.2159442901611328} 08/31/2021 10:08:54 - INFO - __main__ - Step 115632: {'lr': 6.363139309284941e-05, 'samples': 22201344, 'steps': 115631, 'loss/train': 1.71970796585083} 08/31/2021 10:08:55 - INFO - __main__ - Step 115633: {'lr': 6.362785600808777e-05, 'samples': 22201536, 'steps': 115632, 'loss/train': 0.5067172050476074} 08/31/2021 10:08:55 - INFO - __main__ - Step 115634: {'lr': 6.362431900730251e-05, 'samples': 22201728, 'steps': 115633, 'loss/train': 1.027917504310608} 08/31/2021 10:08:55 - INFO - __main__ - Step 115635: {'lr': 6.362078209049526e-05, 'samples': 22201920, 'steps': 115634, 'loss/train': 1.4410778284072876} 08/31/2021 10:08:57 - INFO - __main__ - Step 115636: {'lr': 6.361724525766766e-05, 'samples': 22202112, 'steps': 115635, 'loss/train': 0.21063721179962158} 08/31/2021 10:08:57 - INFO - __main__ - Step 115637: {'lr': 6.36137085088212e-05, 'samples': 22202304, 'steps': 115636, 'loss/train': 0.7555475234985352} 08/31/2021 10:08:58 - INFO - __main__ - Step 115638: {'lr': 6.361017184395757e-05, 'samples': 22202496, 'steps': 115637, 'loss/train': 0.8050887584686279} 08/31/2021 10:08:58 - INFO - __main__ - Step 115639: {'lr': 6.360663526307828e-05, 'samples': 22202688, 'steps': 115638, 'loss/train': 1.8816367387771606} 08/31/2021 10:08:58 - INFO - __main__ - Step 115640: {'lr': 6.360309876618498e-05, 'samples': 22202880, 'steps': 115639, 'loss/train': 0.744555652141571} 08/31/2021 10:09:00 - INFO - __main__ - Step 115641: {'lr': 6.359956235327924e-05, 'samples': 22203072, 'steps': 115640, 'loss/train': 1.3318581581115723} 08/31/2021 10:09:00 - INFO - __main__ - Step 115642: {'lr': 6.359602602436268e-05, 'samples': 22203264, 'steps': 115641, 'loss/train': 1.2146393060684204} 08/31/2021 10:09:01 - INFO - __main__ - Step 115643: {'lr': 6.359248977943693e-05, 'samples': 22203456, 'steps': 115642, 'loss/train': 0.7917055487632751} 08/31/2021 10:09:01 - INFO - __main__ - Step 115644: {'lr': 6.358895361850347e-05, 'samples': 22203648, 'steps': 115643, 'loss/train': 0.20610497891902924} 08/31/2021 10:09:02 - INFO - __main__ - Step 115645: {'lr': 6.358541754156394e-05, 'samples': 22203840, 'steps': 115644, 'loss/train': 1.0279872417449951} 08/31/2021 10:09:02 - INFO - __main__ - Step 115646: {'lr': 6.358188154861994e-05, 'samples': 22204032, 'steps': 115645, 'loss/train': 1.2007129192352295} 08/31/2021 10:09:03 - INFO - __main__ - Step 115647: {'lr': 6.357834563967307e-05, 'samples': 22204224, 'steps': 115646, 'loss/train': 1.653896689414978} 08/31/2021 10:09:04 - INFO - __main__ - Step 115648: {'lr': 6.357480981472493e-05, 'samples': 22204416, 'steps': 115647, 'loss/train': 0.808996856212616} 08/31/2021 10:09:04 - INFO - __main__ - Step 115649: {'lr': 6.35712740737771e-05, 'samples': 22204608, 'steps': 115648, 'loss/train': 0.8899192810058594} 08/31/2021 10:09:04 - INFO - __main__ - Step 115650: {'lr': 6.356773841683116e-05, 'samples': 22204800, 'steps': 115649, 'loss/train': 1.3695377111434937} 08/31/2021 10:09:05 - INFO - __main__ - Step 115651: {'lr': 6.356420284388876e-05, 'samples': 22204992, 'steps': 115650, 'loss/train': 1.3422237634658813} 08/31/2021 10:09:06 - INFO - __main__ - Step 115652: {'lr': 6.356066735495142e-05, 'samples': 22205184, 'steps': 115651, 'loss/train': 1.004598617553711} 08/31/2021 10:09:07 - INFO - __main__ - Step 115653: {'lr': 6.355713195002078e-05, 'samples': 22205376, 'steps': 115652, 'loss/train': 1.028348684310913} 08/31/2021 10:09:07 - INFO - __main__ - Step 115654: {'lr': 6.35535966290984e-05, 'samples': 22205568, 'steps': 115653, 'loss/train': 6.246700286865234} 08/31/2021 10:09:08 - INFO - __main__ - Step 115655: {'lr': 6.355006139218592e-05, 'samples': 22205760, 'steps': 115654, 'loss/train': 1.0053871870040894} 08/31/2021 10:09:08 - INFO - __main__ - Step 115656: {'lr': 6.354652623928489e-05, 'samples': 22205952, 'steps': 115655, 'loss/train': 1.668720006942749} 08/31/2021 10:09:08 - INFO - __main__ - Step 115657: {'lr': 6.3542991170397e-05, 'samples': 22206144, 'steps': 115656, 'loss/train': 1.1257001161575317} 08/31/2021 10:09:11 - INFO - __main__ - Step 115658: {'lr': 6.353945618552367e-05, 'samples': 22206336, 'steps': 115657, 'loss/train': 0.7862553000450134} 08/31/2021 10:09:11 - INFO - __main__ - Step 115659: {'lr': 6.353592128466662e-05, 'samples': 22206528, 'steps': 115658, 'loss/train': 0.7158880829811096} 08/31/2021 10:09:11 - INFO - __main__ - Step 115660: {'lr': 6.353238646782739e-05, 'samples': 22206720, 'steps': 115659, 'loss/train': 0.8649365305900574} 08/31/2021 10:09:12 - INFO - __main__ - Step 115661: {'lr': 6.352885173500755e-05, 'samples': 22206912, 'steps': 115660, 'loss/train': 0.8893188834190369} 08/31/2021 10:09:12 - INFO - __main__ - Step 115662: {'lr': 6.352531708620878e-05, 'samples': 22207104, 'steps': 115661, 'loss/train': 1.1289869546890259} 08/31/2021 10:09:14 - INFO - __main__ - Step 115663: {'lr': 6.352178252143262e-05, 'samples': 22207296, 'steps': 115662, 'loss/train': 1.305047631263733} 08/31/2021 10:09:14 - INFO - __main__ - Step 115664: {'lr': 6.351824804068066e-05, 'samples': 22207488, 'steps': 115663, 'loss/train': 1.1332741975784302} 08/31/2021 10:09:14 - INFO - __main__ - Step 115665: {'lr': 6.351471364395448e-05, 'samples': 22207680, 'steps': 115664, 'loss/train': 1.747132420539856} 08/31/2021 10:09:15 - INFO - __main__ - Step 115666: {'lr': 6.351117933125569e-05, 'samples': 22207872, 'steps': 115665, 'loss/train': 0.6646695733070374} 08/31/2021 10:09:15 - INFO - __main__ - Step 115667: {'lr': 6.350764510258592e-05, 'samples': 22208064, 'steps': 115666, 'loss/train': 0.7467270493507385} 08/31/2021 10:09:17 - INFO - __main__ - Step 115668: {'lr': 6.35041109579467e-05, 'samples': 22208256, 'steps': 115667, 'loss/train': 0.7582589983940125} 08/31/2021 10:09:17 - INFO - __main__ - Step 115669: {'lr': 6.350057689733968e-05, 'samples': 22208448, 'steps': 115668, 'loss/train': 1.25801682472229} 08/31/2021 10:09:17 - INFO - __main__ - Step 115670: {'lr': 6.349704292076647e-05, 'samples': 22208640, 'steps': 115669, 'loss/train': 1.1152266263961792} 08/31/2021 10:09:18 - INFO - __main__ - Step 115671: {'lr': 6.349350902822854e-05, 'samples': 22208832, 'steps': 115670, 'loss/train': 1.1708347797393799} 08/31/2021 10:09:18 - INFO - __main__ - Step 115672: {'lr': 6.348997521972758e-05, 'samples': 22209024, 'steps': 115671, 'loss/train': 0.8744875192642212} 08/31/2021 10:09:20 - INFO - __main__ - Step 115673: {'lr': 6.348644149526512e-05, 'samples': 22209216, 'steps': 115672, 'loss/train': 1.2998155355453491} 08/31/2021 10:09:20 - INFO - __main__ - Step 115674: {'lr': 6.348290785484282e-05, 'samples': 22209408, 'steps': 115673, 'loss/train': 1.0546023845672607} 08/31/2021 10:09:20 - INFO - __main__ - Step 115675: {'lr': 6.347937429846224e-05, 'samples': 22209600, 'steps': 115674, 'loss/train': 1.295318603515625} 08/31/2021 10:09:21 - INFO - __main__ - Step 115676: {'lr': 6.347584082612498e-05, 'samples': 22209792, 'steps': 115675, 'loss/train': 1.1546803712844849} 08/31/2021 10:09:21 - INFO - __main__ - Step 115677: {'lr': 6.347230743783262e-05, 'samples': 22209984, 'steps': 115676, 'loss/train': 1.1428172588348389} 08/31/2021 10:09:23 - INFO - __main__ - Step 115678: {'lr': 6.346877413358677e-05, 'samples': 22210176, 'steps': 115677, 'loss/train': 1.3050765991210938} 08/31/2021 10:09:23 - INFO - __main__ - Step 115679: {'lr': 6.346524091338899e-05, 'samples': 22210368, 'steps': 115678, 'loss/train': 1.8544508218765259} 08/31/2021 10:09:24 - INFO - __main__ - Step 115680: {'lr': 6.346170777724089e-05, 'samples': 22210560, 'steps': 115679, 'loss/train': 1.2841386795043945} 08/31/2021 10:09:24 - INFO - __main__ - Step 115681: {'lr': 6.345817472514409e-05, 'samples': 22210752, 'steps': 115680, 'loss/train': 1.095916509628296} 08/31/2021 10:09:24 - INFO - __main__ - Step 115682: {'lr': 6.345464175710017e-05, 'samples': 22210944, 'steps': 115681, 'loss/train': 0.5912139415740967} 08/31/2021 10:09:26 - INFO - __main__ - Step 115683: {'lr': 6.345110887311068e-05, 'samples': 22211136, 'steps': 115682, 'loss/train': 1.0325530767440796} 08/31/2021 10:09:26 - INFO - __main__ - Step 115684: {'lr': 6.344757607317734e-05, 'samples': 22211328, 'steps': 115683, 'loss/train': 1.6943178176879883} 08/31/2021 10:09:27 - INFO - __main__ - Step 115685: {'lr': 6.344404335730152e-05, 'samples': 22211520, 'steps': 115684, 'loss/train': 1.3261862993240356} 08/31/2021 10:09:27 - INFO - __main__ - Step 115686: {'lr': 6.344051072548499e-05, 'samples': 22211712, 'steps': 115685, 'loss/train': 1.1374964714050293} 08/31/2021 10:09:27 - INFO - __main__ - Step 115687: {'lr': 6.343697817772928e-05, 'samples': 22211904, 'steps': 115686, 'loss/train': 1.2805254459381104} 08/31/2021 10:09:29 - INFO - __main__ - Step 115688: {'lr': 6.343344571403598e-05, 'samples': 22212096, 'steps': 115687, 'loss/train': 0.8906154036521912} 08/31/2021 10:09:29 - INFO - __main__ - Step 115689: {'lr': 6.342991333440667e-05, 'samples': 22212288, 'steps': 115688, 'loss/train': 0.7988796234130859} 08/31/2021 10:09:30 - INFO - __main__ - Step 115690: {'lr': 6.342638103884299e-05, 'samples': 22212480, 'steps': 115689, 'loss/train': 1.1893943548202515} 08/31/2021 10:09:30 - INFO - __main__ - Step 115691: {'lr': 6.34228488273465e-05, 'samples': 22212672, 'steps': 115690, 'loss/train': 0.5905812978744507} 08/31/2021 10:09:30 - INFO - __main__ - Step 115692: {'lr': 6.341931669991877e-05, 'samples': 22212864, 'steps': 115691, 'loss/train': 0.12412884086370468} 08/31/2021 10:09:31 - INFO - __main__ - Step 115693: {'lr': 6.341578465656145e-05, 'samples': 22213056, 'steps': 115692, 'loss/train': 1.8682043552398682} 08/31/2021 10:09:32 - INFO - __main__ - Step 115694: {'lr': 6.341225269727608e-05, 'samples': 22213248, 'steps': 115693, 'loss/train': 0.8782269954681396} 08/31/2021 10:09:33 - INFO - __main__ - Step 115695: {'lr': 6.340872082206428e-05, 'samples': 22213440, 'steps': 115694, 'loss/train': 1.2862073183059692} 08/31/2021 10:09:33 - INFO - __main__ - Step 115696: {'lr': 6.340518903092762e-05, 'samples': 22213632, 'steps': 115695, 'loss/train': 1.3624372482299805} 08/31/2021 10:09:34 - INFO - __main__ - Step 115697: {'lr': 6.340165732386777e-05, 'samples': 22213824, 'steps': 115696, 'loss/train': 1.151167392730713} 08/31/2021 10:09:34 - INFO - __main__ - Step 115698: {'lr': 6.339812570088622e-05, 'samples': 22214016, 'steps': 115697, 'loss/train': 0.03378046303987503} 08/31/2021 10:09:35 - INFO - __main__ - Step 115699: {'lr': 6.339459416198454e-05, 'samples': 22214208, 'steps': 115698, 'loss/train': 0.94110506772995} 08/31/2021 10:09:36 - INFO - __main__ - Step 115700: {'lr': 6.339106270716442e-05, 'samples': 22214400, 'steps': 115699, 'loss/train': 1.363456130027771} 08/31/2021 10:09:36 - INFO - __main__ - Step 115701: {'lr': 6.338753133642738e-05, 'samples': 22214592, 'steps': 115700, 'loss/train': 0.9041175842285156} 08/31/2021 10:09:37 - INFO - __main__ - Step 115702: {'lr': 6.338400004977505e-05, 'samples': 22214784, 'steps': 115701, 'loss/train': 0.5562620162963867} 08/31/2021 10:09:37 - INFO - __main__ - Step 115703: {'lr': 6.338046884720899e-05, 'samples': 22214976, 'steps': 115702, 'loss/train': 1.984569787979126} 08/31/2021 10:09:39 - INFO - __main__ - Step 115704: {'lr': 6.337693772873084e-05, 'samples': 22215168, 'steps': 115703, 'loss/train': 1.0564814805984497} 08/31/2021 10:09:39 - INFO - __main__ - Step 115705: {'lr': 6.337340669434216e-05, 'samples': 22215360, 'steps': 115704, 'loss/train': 1.0201301574707031} 08/31/2021 10:09:39 - INFO - __main__ - Step 115706: {'lr': 6.336987574404454e-05, 'samples': 22215552, 'steps': 115705, 'loss/train': 1.2693400382995605} 08/31/2021 10:09:40 - INFO - __main__ - Step 115707: {'lr': 6.336634487783957e-05, 'samples': 22215744, 'steps': 115706, 'loss/train': 0.38194429874420166} 08/31/2021 10:09:40 - INFO - __main__ - Step 115708: {'lr': 6.336281409572884e-05, 'samples': 22215936, 'steps': 115707, 'loss/train': 1.4688568115234375} 08/31/2021 10:09:41 - INFO - __main__ - Step 115709: {'lr': 6.335928339771393e-05, 'samples': 22216128, 'steps': 115708, 'loss/train': 1.2033642530441284} 08/31/2021 10:09:42 - INFO - __main__ - Step 115710: {'lr': 6.335575278379649e-05, 'samples': 22216320, 'steps': 115709, 'loss/train': 1.578252911567688} 08/31/2021 10:09:42 - INFO - __main__ - Step 115711: {'lr': 6.33522222539781e-05, 'samples': 22216512, 'steps': 115710, 'loss/train': 1.3564409017562866} 08/31/2021 10:09:43 - INFO - __main__ - Step 115712: {'lr': 6.334869180826027e-05, 'samples': 22216704, 'steps': 115711, 'loss/train': 0.399970680475235} 08/31/2021 10:09:43 - INFO - __main__ - Step 115713: {'lr': 6.334516144664465e-05, 'samples': 22216896, 'steps': 115712, 'loss/train': 0.9649070501327515} 08/31/2021 10:09:45 - INFO - __main__ - Step 115714: {'lr': 6.33416311691328e-05, 'samples': 22217088, 'steps': 115713, 'loss/train': 0.7437821626663208} 08/31/2021 10:09:46 - INFO - __main__ - Step 115715: {'lr': 6.333810097572631e-05, 'samples': 22217280, 'steps': 115714, 'loss/train': 0.9689795970916748} 08/31/2021 10:09:46 - INFO - __main__ - Step 115716: {'lr': 6.333457086642683e-05, 'samples': 22217472, 'steps': 115715, 'loss/train': 1.051418662071228} 08/31/2021 10:09:46 - INFO - __main__ - Step 115717: {'lr': 6.333104084123589e-05, 'samples': 22217664, 'steps': 115716, 'loss/train': 1.0340421199798584} 08/31/2021 10:09:47 - INFO - __main__ - Step 115718: {'lr': 6.332751090015512e-05, 'samples': 22217856, 'steps': 115717, 'loss/train': 1.5404517650604248} 08/31/2021 10:09:48 - INFO - __main__ - Step 115719: {'lr': 6.332398104318606e-05, 'samples': 22218048, 'steps': 115718, 'loss/train': 0.9016515612602234} 08/31/2021 10:09:49 - INFO - __main__ - Step 115720: {'lr': 6.332045127033037e-05, 'samples': 22218240, 'steps': 115719, 'loss/train': 0.2216770052909851} 08/31/2021 10:09:49 - INFO - __main__ - Step 115721: {'lr': 6.331692158158958e-05, 'samples': 22218432, 'steps': 115720, 'loss/train': 1.1160410642623901} 08/31/2021 10:09:50 - INFO - __main__ - Step 115722: {'lr': 6.331339197696531e-05, 'samples': 22218624, 'steps': 115721, 'loss/train': 0.9007344245910645} 08/31/2021 10:09:50 - INFO - __main__ - Step 115723: {'lr': 6.330986245645917e-05, 'samples': 22218816, 'steps': 115722, 'loss/train': 0.5480359196662903} 08/31/2021 10:09:50 - INFO - __main__ - Step 115724: {'lr': 6.330633302007277e-05, 'samples': 22219008, 'steps': 115723, 'loss/train': 0.025882435962557793} 08/31/2021 10:09:52 - INFO - __main__ - Step 115725: {'lr': 6.330280366780758e-05, 'samples': 22219200, 'steps': 115724, 'loss/train': 1.3178672790527344} 08/31/2021 10:09:52 - INFO - __main__ - Step 115726: {'lr': 6.32992743996653e-05, 'samples': 22219392, 'steps': 115725, 'loss/train': 1.2061630487442017} 08/31/2021 10:09:53 - INFO - __main__ - Step 115727: {'lr': 6.329574521564746e-05, 'samples': 22219584, 'steps': 115726, 'loss/train': 1.2284038066864014} 08/31/2021 10:09:53 - INFO - __main__ - Step 115728: {'lr': 6.329221611575567e-05, 'samples': 22219776, 'steps': 115727, 'loss/train': 1.0372413396835327} 08/31/2021 10:09:53 - INFO - __main__ - Step 115729: {'lr': 6.328868709999152e-05, 'samples': 22219968, 'steps': 115728, 'loss/train': 1.318720817565918} 08/31/2021 10:09:55 - INFO - __main__ - Step 115730: {'lr': 6.328515816835664e-05, 'samples': 22220160, 'steps': 115729, 'loss/train': 1.0947538614273071} 08/31/2021 10:09:55 - INFO - __main__ - Step 115731: {'lr': 6.328162932085254e-05, 'samples': 22220352, 'steps': 115730, 'loss/train': 0.6331467032432556} 08/31/2021 10:09:56 - INFO - __main__ - Step 115732: {'lr': 6.32781005574809e-05, 'samples': 22220544, 'steps': 115731, 'loss/train': 1.2822364568710327} 08/31/2021 10:09:56 - INFO - __main__ - Step 115733: {'lr': 6.327457187824326e-05, 'samples': 22220736, 'steps': 115732, 'loss/train': 1.3908355236053467} 08/31/2021 10:09:56 - INFO - __main__ - Step 115734: {'lr': 6.32710432831412e-05, 'samples': 22220928, 'steps': 115733, 'loss/train': 0.8809241056442261} 08/31/2021 10:09:58 - INFO - __main__ - Step 115735: {'lr': 6.326751477217632e-05, 'samples': 22221120, 'steps': 115734, 'loss/train': 0.880194902420044} 08/31/2021 10:09:58 - INFO - __main__ - Step 115736: {'lr': 6.326398634535024e-05, 'samples': 22221312, 'steps': 115735, 'loss/train': 1.3130673170089722} 08/31/2021 10:09:58 - INFO - __main__ - Step 115737: {'lr': 6.326045800266452e-05, 'samples': 22221504, 'steps': 115736, 'loss/train': 1.4927034378051758} 08/31/2021 10:09:59 - INFO - __main__ - Step 115738: {'lr': 6.325692974412081e-05, 'samples': 22221696, 'steps': 115737, 'loss/train': 1.254011631011963} 08/31/2021 10:09:59 - INFO - __main__ - Step 115739: {'lr': 6.325340156972059e-05, 'samples': 22221888, 'steps': 115738, 'loss/train': 0.4408719837665558} 08/31/2021 10:10:01 - INFO - __main__ - Step 115740: {'lr': 6.32498734794655e-05, 'samples': 22222080, 'steps': 115739, 'loss/train': 0.9417089223861694} 08/31/2021 10:10:02 - INFO - __main__ - Step 115741: {'lr': 6.324634547335714e-05, 'samples': 22222272, 'steps': 115740, 'loss/train': 1.5194576978683472} 08/31/2021 10:10:02 - INFO - __main__ - Step 115742: {'lr': 6.324281755139711e-05, 'samples': 22222464, 'steps': 115741, 'loss/train': 1.5749807357788086} 08/31/2021 10:10:02 - INFO - __main__ - Step 115743: {'lr': 6.323928971358698e-05, 'samples': 22222656, 'steps': 115742, 'loss/train': 1.1919074058532715} 08/31/2021 10:10:03 - INFO - __main__ - Step 115744: {'lr': 6.323576195992831e-05, 'samples': 22222848, 'steps': 115743, 'loss/train': 0.9456615447998047} 08/31/2021 10:10:03 - INFO - __main__ - Step 115745: {'lr': 6.323223429042274e-05, 'samples': 22223040, 'steps': 115744, 'loss/train': 1.07797372341156} 08/31/2021 10:10:05 - INFO - __main__ - Step 115746: {'lr': 6.322870670507186e-05, 'samples': 22223232, 'steps': 115745, 'loss/train': 1.7761647701263428} 08/31/2021 10:10:05 - INFO - __main__ - Step 115747: {'lr': 6.322517920387725e-05, 'samples': 22223424, 'steps': 115746, 'loss/train': 0.9838193655014038} 08/31/2021 10:10:05 - INFO - __main__ - Step 115748: {'lr': 6.322165178684044e-05, 'samples': 22223616, 'steps': 115747, 'loss/train': 1.681361436843872} 08/31/2021 10:10:06 - INFO - __main__ - Step 115749: {'lr': 6.321812445396313e-05, 'samples': 22223808, 'steps': 115748, 'loss/train': 0.49122220277786255} 08/31/2021 10:10:06 - INFO - __main__ - Step 115750: {'lr': 6.32145972052468e-05, 'samples': 22224000, 'steps': 115749, 'loss/train': 1.3085582256317139} 08/31/2021 10:10:07 - INFO - __main__ - Step 115751: {'lr': 6.32110700406932e-05, 'samples': 22224192, 'steps': 115750, 'loss/train': 1.4399398565292358} 08/31/2021 10:10:08 - INFO - __main__ - Step 115752: {'lr': 6.320754296030373e-05, 'samples': 22224384, 'steps': 115751, 'loss/train': 1.6622967720031738} 08/31/2021 10:10:08 - INFO - __main__ - Step 115753: {'lr': 6.320401596408007e-05, 'samples': 22224576, 'steps': 115752, 'loss/train': 0.9227212071418762} 08/31/2021 10:10:09 - INFO - __main__ - Step 115754: {'lr': 6.320048905202378e-05, 'samples': 22224768, 'steps': 115753, 'loss/train': 0.6376171708106995} 08/31/2021 10:10:09 - INFO - __main__ - Step 115755: {'lr': 6.319696222413645e-05, 'samples': 22224960, 'steps': 115754, 'loss/train': 1.126366376876831} 08/31/2021 10:10:11 - INFO - __main__ - Step 115756: {'lr': 6.319343548041973e-05, 'samples': 22225152, 'steps': 115755, 'loss/train': 0.8539812564849854} 08/31/2021 10:10:11 - INFO - __main__ - Step 115757: {'lr': 6.318990882087513e-05, 'samples': 22225344, 'steps': 115756, 'loss/train': 1.9143785238265991} 08/31/2021 10:10:12 - INFO - __main__ - Step 115758: {'lr': 6.318638224550429e-05, 'samples': 22225536, 'steps': 115757, 'loss/train': 1.1259230375289917} 08/31/2021 10:10:12 - INFO - __main__ - Step 115759: {'lr': 6.318285575430877e-05, 'samples': 22225728, 'steps': 115758, 'loss/train': 0.029846325516700745} 08/31/2021 10:10:12 - INFO - __main__ - Step 115760: {'lr': 6.317932934729018e-05, 'samples': 22225920, 'steps': 115759, 'loss/train': 0.683219313621521} 08/31/2021 10:10:13 - INFO - __main__ - Step 115761: {'lr': 6.317580302445011e-05, 'samples': 22226112, 'steps': 115760, 'loss/train': 1.1726640462875366} 08/31/2021 10:10:13 - INFO - __main__ - Step 115762: {'lr': 6.317227678579013e-05, 'samples': 22226304, 'steps': 115761, 'loss/train': 0.015179581940174103} 08/31/2021 10:10:15 - INFO - __main__ - Step 115763: {'lr': 6.316875063131186e-05, 'samples': 22226496, 'steps': 115762, 'loss/train': 0.867570698261261} 08/31/2021 10:10:15 - INFO - __main__ - Step 115764: {'lr': 6.316522456101693e-05, 'samples': 22226688, 'steps': 115763, 'loss/train': 0.03214080631732941} 08/31/2021 10:10:16 - INFO - __main__ - Step 115765: {'lr': 6.316169857490678e-05, 'samples': 22226880, 'steps': 115764, 'loss/train': 0.6023268699645996} 08/31/2021 10:10:16 - INFO - __main__ - Step 115766: {'lr': 6.315817267298307e-05, 'samples': 22227072, 'steps': 115765, 'loss/train': 0.04081680253148079} 08/31/2021 10:10:16 - INFO - __main__ - Step 115767: {'lr': 6.315464685524744e-05, 'samples': 22227264, 'steps': 115766, 'loss/train': 0.037289950996637344} 08/31/2021 10:10:19 - INFO - __main__ - Step 115768: {'lr': 6.315112112170143e-05, 'samples': 22227456, 'steps': 115767, 'loss/train': 1.373775601387024} 08/31/2021 10:10:19 - INFO - __main__ - Step 115769: {'lr': 6.314759547234664e-05, 'samples': 22227648, 'steps': 115768, 'loss/train': 0.5242278575897217} 08/31/2021 10:10:20 - INFO - __main__ - Step 115770: {'lr': 6.314406990718466e-05, 'samples': 22227840, 'steps': 115769, 'loss/train': 0.4122377634048462} 08/31/2021 10:10:20 - INFO - __main__ - Step 115771: {'lr': 6.314054442621709e-05, 'samples': 22228032, 'steps': 115770, 'loss/train': 1.4692628383636475} 08/31/2021 10:10:20 - INFO - __main__ - Step 115772: {'lr': 6.313701902944549e-05, 'samples': 22228224, 'steps': 115771, 'loss/train': 1.1027367115020752} 08/31/2021 10:10:22 - INFO - __main__ - Step 115773: {'lr': 6.313349371687147e-05, 'samples': 22228416, 'steps': 115772, 'loss/train': 1.4681808948516846} 08/31/2021 10:10:22 - INFO - __main__ - Step 115774: {'lr': 6.312996848849662e-05, 'samples': 22228608, 'steps': 115773, 'loss/train': 0.32468149065971375} 08/31/2021 10:10:23 - INFO - __main__ - Step 115775: {'lr': 6.312644334432252e-05, 'samples': 22228800, 'steps': 115774, 'loss/train': 0.6935186386108398} 08/31/2021 10:10:23 - INFO - __main__ - Step 115776: {'lr': 6.312291828435076e-05, 'samples': 22228992, 'steps': 115775, 'loss/train': 1.198651909828186} 08/31/2021 10:10:23 - INFO - __main__ - Step 115777: {'lr': 6.311939330858293e-05, 'samples': 22229184, 'steps': 115776, 'loss/train': 0.408832848072052} 08/31/2021 10:10:24 - INFO - __main__ - Step 115778: {'lr': 6.311586841702069e-05, 'samples': 22229376, 'steps': 115777, 'loss/train': 0.9833014011383057} 08/31/2021 10:10:25 - INFO - __main__ - Step 115779: {'lr': 6.31123436096655e-05, 'samples': 22229568, 'steps': 115778, 'loss/train': 1.2734242677688599} 08/31/2021 10:10:26 - INFO - __main__ - Step 115780: {'lr': 6.310881888651898e-05, 'samples': 22229760, 'steps': 115779, 'loss/train': 1.376976728439331} 08/31/2021 10:10:26 - INFO - __main__ - Step 115781: {'lr': 6.310529424758276e-05, 'samples': 22229952, 'steps': 115780, 'loss/train': 1.4676295518875122} 08/31/2021 10:10:26 - INFO - __main__ - Step 115782: {'lr': 6.310176969285839e-05, 'samples': 22230144, 'steps': 115781, 'loss/train': 0.10753326863050461} 08/31/2021 10:10:27 - INFO - __main__ - Step 115783: {'lr': 6.30982452223475e-05, 'samples': 22230336, 'steps': 115782, 'loss/train': 1.5528708696365356} 08/31/2021 10:10:28 - INFO - __main__ - Step 115784: {'lr': 6.309472083605165e-05, 'samples': 22230528, 'steps': 115783, 'loss/train': 0.4019547402858734} 08/31/2021 10:10:29 - INFO - __main__ - Step 115785: {'lr': 6.309119653397241e-05, 'samples': 22230720, 'steps': 115784, 'loss/train': 0.8650126457214355} 08/31/2021 10:10:29 - INFO - __main__ - Step 115786: {'lr': 6.308767231611142e-05, 'samples': 22230912, 'steps': 115785, 'loss/train': 0.7820910215377808} 08/31/2021 10:10:29 - INFO - __main__ - Step 115787: {'lr': 6.308414818247024e-05, 'samples': 22231104, 'steps': 115786, 'loss/train': 1.3814517259597778} 08/31/2021 10:10:30 - INFO - __main__ - Step 115788: {'lr': 6.308062413305046e-05, 'samples': 22231296, 'steps': 115787, 'loss/train': 0.04684501886367798} 08/31/2021 10:10:31 - INFO - __main__ - Step 115789: {'lr': 6.307710016785365e-05, 'samples': 22231488, 'steps': 115788, 'loss/train': 0.6466869711875916} 08/31/2021 10:10:32 - INFO - __main__ - Step 115790: {'lr': 6.307357628688143e-05, 'samples': 22231680, 'steps': 115789, 'loss/train': 0.774699866771698} 08/31/2021 10:10:32 - INFO - __main__ - Step 115791: {'lr': 6.307005249013545e-05, 'samples': 22231872, 'steps': 115790, 'loss/train': 0.8320863246917725} 08/31/2021 10:10:32 - INFO - __main__ - Step 115792: {'lr': 6.306652877761712e-05, 'samples': 22232064, 'steps': 115791, 'loss/train': 1.4633740186691284} 08/31/2021 10:10:33 - INFO - __main__ - Step 115793: {'lr': 6.306300514932814e-05, 'samples': 22232256, 'steps': 115792, 'loss/train': 0.6759966611862183} 08/31/2021 10:10:34 - INFO - __main__ - Step 115794: {'lr': 6.305948160527009e-05, 'samples': 22232448, 'steps': 115793, 'loss/train': 0.5584968328475952} 08/31/2021 10:10:35 - INFO - __main__ - Step 115795: {'lr': 6.305595814544458e-05, 'samples': 22232640, 'steps': 115794, 'loss/train': 0.1529415100812912} 08/31/2021 10:10:35 - INFO - __main__ - Step 115796: {'lr': 6.305243476985311e-05, 'samples': 22232832, 'steps': 115795, 'loss/train': 1.346046805381775} 08/31/2021 10:10:35 - INFO - __main__ - Step 115797: {'lr': 6.304891147849737e-05, 'samples': 22233024, 'steps': 115796, 'loss/train': 1.0067695379257202} 08/31/2021 10:10:36 - INFO - __main__ - Step 115798: {'lr': 6.30453882713789e-05, 'samples': 22233216, 'steps': 115797, 'loss/train': 1.0576812028884888} 08/31/2021 10:10:37 - INFO - __main__ - Step 115799: {'lr': 6.304186514849928e-05, 'samples': 22233408, 'steps': 115798, 'loss/train': 1.2533938884735107} 08/31/2021 10:10:38 - INFO - __main__ - Step 115800: {'lr': 6.303834210986012e-05, 'samples': 22233600, 'steps': 115799, 'loss/train': 1.5309486389160156} 08/31/2021 10:10:38 - INFO - __main__ - Step 115801: {'lr': 6.303481915546299e-05, 'samples': 22233792, 'steps': 115800, 'loss/train': 0.8381583094596863} 08/31/2021 10:10:38 - INFO - __main__ - Step 115802: {'lr': 6.303129628530957e-05, 'samples': 22233984, 'steps': 115801, 'loss/train': 1.092790961265564} 08/31/2021 10:10:39 - INFO - __main__ - Step 115803: {'lr': 6.302777349940128e-05, 'samples': 22234176, 'steps': 115802, 'loss/train': 0.5577293038368225} 08/31/2021 10:10:40 - INFO - __main__ - Step 115804: {'lr': 6.302425079773979e-05, 'samples': 22234368, 'steps': 115803, 'loss/train': 1.2266342639923096} 08/31/2021 10:10:41 - INFO - __main__ - Step 115805: {'lr': 6.302072818032672e-05, 'samples': 22234560, 'steps': 115804, 'loss/train': 1.1875011920928955} 08/31/2021 10:10:41 - INFO - __main__ - Step 115806: {'lr': 6.30172056471636e-05, 'samples': 22234752, 'steps': 115805, 'loss/train': 1.6721642017364502} 08/31/2021 10:10:41 - INFO - __main__ - Step 115807: {'lr': 6.301368319825204e-05, 'samples': 22234944, 'steps': 115806, 'loss/train': 0.8419281244277954} 08/31/2021 10:10:42 - INFO - __main__ - Step 115808: {'lr': 6.301016083359362e-05, 'samples': 22235136, 'steps': 115807, 'loss/train': 0.5858244299888611} 08/31/2021 10:10:43 - INFO - __main__ - Step 115809: {'lr': 6.300663855318994e-05, 'samples': 22235328, 'steps': 115808, 'loss/train': 1.4173387289047241} 08/31/2021 10:10:44 - INFO - __main__ - Step 115810: {'lr': 6.300311635704259e-05, 'samples': 22235520, 'steps': 115809, 'loss/train': 1.0613112449645996} 08/31/2021 10:10:44 - INFO - __main__ - Step 115811: {'lr': 6.299959424515314e-05, 'samples': 22235712, 'steps': 115810, 'loss/train': 0.25987493991851807} 08/31/2021 10:10:44 - INFO - __main__ - Step 115812: {'lr': 6.299607221752327e-05, 'samples': 22235904, 'steps': 115811, 'loss/train': 0.6235495805740356} 08/31/2021 10:10:45 - INFO - __main__ - Step 115813: {'lr': 6.299255027415443e-05, 'samples': 22236096, 'steps': 115812, 'loss/train': 1.2372090816497803} 08/31/2021 10:10:46 - INFO - __main__ - Step 115814: {'lr': 6.298902841504822e-05, 'samples': 22236288, 'steps': 115813, 'loss/train': 1.2485471963882446} 08/31/2021 10:10:47 - INFO - __main__ - Step 115815: {'lr': 6.29855066402063e-05, 'samples': 22236480, 'steps': 115814, 'loss/train': 2.743598699569702} 08/31/2021 10:10:47 - INFO - __main__ - Step 115816: {'lr': 6.29819849496302e-05, 'samples': 22236672, 'steps': 115815, 'loss/train': 0.6652019619941711} 08/31/2021 10:10:48 - INFO - __main__ - Step 115817: {'lr': 6.297846334332155e-05, 'samples': 22236864, 'steps': 115816, 'loss/train': 0.6422178745269775} 08/31/2021 10:10:48 - INFO - __main__ - Step 115818: {'lr': 6.297494182128192e-05, 'samples': 22237056, 'steps': 115817, 'loss/train': 1.6035327911376953} 08/31/2021 10:10:49 - INFO - __main__ - Step 115819: {'lr': 6.297142038351289e-05, 'samples': 22237248, 'steps': 115818, 'loss/train': 0.31566599011421204} 08/31/2021 10:10:50 - INFO - __main__ - Step 115820: {'lr': 6.296789903001604e-05, 'samples': 22237440, 'steps': 115819, 'loss/train': 0.03510357439517975} 08/31/2021 10:10:50 - INFO - __main__ - Step 115821: {'lr': 6.2964377760793e-05, 'samples': 22237632, 'steps': 115820, 'loss/train': 0.9614346623420715} 08/31/2021 10:10:51 - INFO - __main__ - Step 115822: {'lr': 6.29608565758453e-05, 'samples': 22237824, 'steps': 115821, 'loss/train': 0.7516422271728516} 08/31/2021 10:10:51 - INFO - __main__ - Step 115823: {'lr': 6.295733547517463e-05, 'samples': 22238016, 'steps': 115822, 'loss/train': 1.4024577140808105} 08/31/2021 10:10:53 - INFO - __main__ - Step 115824: {'lr': 6.295381445878243e-05, 'samples': 22238208, 'steps': 115823, 'loss/train': 1.625422716140747} 08/31/2021 10:10:53 - INFO - __main__ - Step 115825: {'lr': 6.295029352667033e-05, 'samples': 22238400, 'steps': 115824, 'loss/train': 1.3651926517486572} 08/31/2021 10:10:54 - INFO - __main__ - Step 115826: {'lr': 6.294677267883997e-05, 'samples': 22238592, 'steps': 115825, 'loss/train': 1.4176353216171265} 08/31/2021 10:10:54 - INFO - __main__ - Step 115827: {'lr': 6.29432519152929e-05, 'samples': 22238784, 'steps': 115826, 'loss/train': 1.5066208839416504} 08/31/2021 10:10:55 - INFO - __main__ - Step 115828: {'lr': 6.293973123603073e-05, 'samples': 22238976, 'steps': 115827, 'loss/train': 1.239758014678955} 08/31/2021 10:10:55 - INFO - __main__ - Step 115829: {'lr': 6.293621064105501e-05, 'samples': 22239168, 'steps': 115828, 'loss/train': 1.1249748468399048} 08/31/2021 10:10:56 - INFO - __main__ - Step 115830: {'lr': 6.293269013036734e-05, 'samples': 22239360, 'steps': 115829, 'loss/train': 1.127771258354187} 08/31/2021 10:10:57 - INFO - __main__ - Step 115831: {'lr': 6.292916970396934e-05, 'samples': 22239552, 'steps': 115830, 'loss/train': 1.0785168409347534} 08/31/2021 10:10:57 - INFO - __main__ - Step 115832: {'lr': 6.292564936186254e-05, 'samples': 22239744, 'steps': 115831, 'loss/train': 0.9011834859848022} 08/31/2021 10:10:58 - INFO - __main__ - Step 115833: {'lr': 6.292212910404857e-05, 'samples': 22239936, 'steps': 115832, 'loss/train': 1.1185390949249268} 08/31/2021 10:10:58 - INFO - __main__ - Step 115834: {'lr': 6.291860893052908e-05, 'samples': 22240128, 'steps': 115833, 'loss/train': 1.0288560390472412} 08/31/2021 10:11:00 - INFO - __main__ - Step 115835: {'lr': 6.291508884130548e-05, 'samples': 22240320, 'steps': 115834, 'loss/train': 0.8923001885414124} 08/31/2021 10:11:00 - INFO - __main__ - Step 115836: {'lr': 6.29115688363795e-05, 'samples': 22240512, 'steps': 115835, 'loss/train': 0.6122168898582458} 08/31/2021 10:11:00 - INFO - __main__ - Step 115837: {'lr': 6.290804891575263e-05, 'samples': 22240704, 'steps': 115836, 'loss/train': 1.0994597673416138} 08/31/2021 10:11:01 - INFO - __main__ - Step 115838: {'lr': 6.290452907942653e-05, 'samples': 22240896, 'steps': 115837, 'loss/train': 1.4300464391708374} 08/31/2021 10:11:01 - INFO - __main__ - Step 115839: {'lr': 6.290100932740278e-05, 'samples': 22241088, 'steps': 115838, 'loss/train': 1.75994873046875} 08/31/2021 10:11:03 - INFO - __main__ - Step 115840: {'lr': 6.289748965968292e-05, 'samples': 22241280, 'steps': 115839, 'loss/train': 0.9023144245147705} 08/31/2021 10:11:03 - INFO - __main__ - Step 115841: {'lr': 6.289397007626856e-05, 'samples': 22241472, 'steps': 115840, 'loss/train': 1.6910614967346191} 08/31/2021 10:11:03 - INFO - __main__ - Step 115842: {'lr': 6.28904505771613e-05, 'samples': 22241664, 'steps': 115841, 'loss/train': 1.0533174276351929} 08/31/2021 10:11:04 - INFO - __main__ - Step 115843: {'lr': 6.288693116236275e-05, 'samples': 22241856, 'steps': 115842, 'loss/train': 1.5932570695877075} 08/31/2021 10:11:04 - INFO - __main__ - Step 115844: {'lr': 6.28834118318744e-05, 'samples': 22242048, 'steps': 115843, 'loss/train': 0.8473117351531982} 08/31/2021 10:11:04 - INFO - __main__ - Step 115845: {'lr': 6.287989258569801e-05, 'samples': 22242240, 'steps': 115844, 'loss/train': 1.763006329536438} 08/31/2021 10:11:07 - INFO - __main__ - Step 115846: {'lr': 6.287637342383498e-05, 'samples': 22242432, 'steps': 115845, 'loss/train': 0.316683828830719} 08/31/2021 10:11:07 - INFO - __main__ - Step 115847: {'lr': 6.287285434628696e-05, 'samples': 22242624, 'steps': 115846, 'loss/train': 0.19198815524578094} 08/31/2021 10:11:07 - INFO - __main__ - Step 115848: {'lr': 6.286933535305556e-05, 'samples': 22242816, 'steps': 115847, 'loss/train': 0.2567439079284668} 08/31/2021 10:11:08 - INFO - __main__ - Step 115849: {'lr': 6.286581644414233e-05, 'samples': 22243008, 'steps': 115848, 'loss/train': 1.0140252113342285} 08/31/2021 10:11:08 - INFO - __main__ - Step 115850: {'lr': 6.286229761954887e-05, 'samples': 22243200, 'steps': 115849, 'loss/train': 0.4255073666572571} 08/31/2021 10:11:08 - INFO - __main__ - Step 115851: {'lr': 6.285877887927676e-05, 'samples': 22243392, 'steps': 115850, 'loss/train': 0.029546035453677177} 08/31/2021 10:11:10 - INFO - __main__ - Step 115852: {'lr': 6.285526022332763e-05, 'samples': 22243584, 'steps': 115851, 'loss/train': 0.4626966118812561} 08/31/2021 10:11:10 - INFO - __main__ - Step 115853: {'lr': 6.285174165170302e-05, 'samples': 22243776, 'steps': 115852, 'loss/train': 0.6813470125198364} 08/31/2021 10:11:11 - INFO - __main__ - Step 115854: {'lr': 6.284822316440452e-05, 'samples': 22243968, 'steps': 115853, 'loss/train': 0.9822443127632141} 08/31/2021 10:11:11 - INFO - __main__ - Step 115855: {'lr': 6.284470476143372e-05, 'samples': 22244160, 'steps': 115854, 'loss/train': 1.3147956132888794} 08/31/2021 10:11:11 - INFO - __main__ - Step 115856: {'lr': 6.284118644279224e-05, 'samples': 22244352, 'steps': 115855, 'loss/train': 1.276594877243042} 08/31/2021 10:11:12 - INFO - __main__ - Step 115857: {'lr': 6.283766820848161e-05, 'samples': 22244544, 'steps': 115856, 'loss/train': 0.7442383766174316} 08/31/2021 10:11:13 - INFO - __main__ - Step 115858: {'lr': 6.283415005850343e-05, 'samples': 22244736, 'steps': 115857, 'loss/train': 1.4255084991455078} 08/31/2021 10:11:14 - INFO - __main__ - Step 115859: {'lr': 6.283063199285938e-05, 'samples': 22244928, 'steps': 115858, 'loss/train': 1.2557854652404785} 08/31/2021 10:11:14 - INFO - __main__ - Step 115860: {'lr': 6.282711401155089e-05, 'samples': 22245120, 'steps': 115859, 'loss/train': 1.3268402814865112} 08/31/2021 10:11:14 - INFO - __main__ - Step 115861: {'lr': 6.28235961145796e-05, 'samples': 22245312, 'steps': 115860, 'loss/train': 0.9110602736473083} 08/31/2021 10:11:15 - INFO - __main__ - Step 115862: {'lr': 6.28200783019471e-05, 'samples': 22245504, 'steps': 115861, 'loss/train': 1.560064435005188} 08/31/2021 10:11:16 - INFO - __main__ - Step 115863: {'lr': 6.2816560573655e-05, 'samples': 22245696, 'steps': 115862, 'loss/train': 1.0499076843261719} 08/31/2021 10:11:17 - INFO - __main__ - Step 115864: {'lr': 6.281304292970489e-05, 'samples': 22245888, 'steps': 115863, 'loss/train': 1.8340294361114502} 08/31/2021 10:11:17 - INFO - __main__ - Step 115865: {'lr': 6.28095253700983e-05, 'samples': 22246080, 'steps': 115864, 'loss/train': 0.8735859990119934} 08/31/2021 10:11:17 - INFO - __main__ - Step 115866: {'lr': 6.280600789483686e-05, 'samples': 22246272, 'steps': 115865, 'loss/train': 0.6127249002456665} 08/31/2021 10:11:18 - INFO - __main__ - Step 115867: {'lr': 6.280249050392215e-05, 'samples': 22246464, 'steps': 115866, 'loss/train': 1.1705384254455566} 08/31/2021 10:11:19 - INFO - __main__ - Step 115868: {'lr': 6.279897319735576e-05, 'samples': 22246656, 'steps': 115867, 'loss/train': 0.9012755155563354} 08/31/2021 10:11:20 - INFO - __main__ - Step 115869: {'lr': 6.279545597513925e-05, 'samples': 22246848, 'steps': 115868, 'loss/train': 1.635972261428833} 08/31/2021 10:11:20 - INFO - __main__ - Step 115870: {'lr': 6.279193883727421e-05, 'samples': 22247040, 'steps': 115869, 'loss/train': 2.2121472358703613} 08/31/2021 10:11:20 - INFO - __main__ - Step 115871: {'lr': 6.278842178376224e-05, 'samples': 22247232, 'steps': 115870, 'loss/train': 1.2680246829986572} 08/31/2021 10:11:21 - INFO - __main__ - Step 115872: {'lr': 6.2784904814605e-05, 'samples': 22247424, 'steps': 115871, 'loss/train': 1.3013837337493896} 08/31/2021 10:11:23 - INFO - __main__ - Step 115873: {'lr': 6.27813879298039e-05, 'samples': 22247616, 'steps': 115872, 'loss/train': 0.9202457070350647} 08/31/2021 10:11:23 - INFO - __main__ - Step 115874: {'lr': 6.277787112936065e-05, 'samples': 22247808, 'steps': 115873, 'loss/train': 1.325168490409851} 08/31/2021 10:11:24 - INFO - __main__ - Step 115875: {'lr': 6.277435441327678e-05, 'samples': 22248000, 'steps': 115874, 'loss/train': 1.179187297821045} 08/31/2021 10:11:24 - INFO - __main__ - Step 115876: {'lr': 6.27708377815539e-05, 'samples': 22248192, 'steps': 115875, 'loss/train': 0.015630990266799927} 08/31/2021 10:11:24 - INFO - __main__ - Step 115877: {'lr': 6.27673212341936e-05, 'samples': 22248384, 'steps': 115876, 'loss/train': 0.912403404712677} 08/31/2021 10:11:25 - INFO - __main__ - Step 115878: {'lr': 6.276380477119742e-05, 'samples': 22248576, 'steps': 115877, 'loss/train': 1.1585108041763306} 08/31/2021 10:11:27 - INFO - __main__ - Step 115879: {'lr': 6.276028839256703e-05, 'samples': 22248768, 'steps': 115878, 'loss/train': 1.574952483177185} 08/31/2021 10:11:27 - INFO - __main__ - Step 115880: {'lr': 6.275677209830393e-05, 'samples': 22248960, 'steps': 115879, 'loss/train': 0.9257703423500061} 08/31/2021 10:11:28 - INFO - __main__ - Step 115881: {'lr': 6.275325588840975e-05, 'samples': 22249152, 'steps': 115880, 'loss/train': 1.5700225830078125} 08/31/2021 10:11:28 - INFO - __main__ - Step 115882: {'lr': 6.274973976288606e-05, 'samples': 22249344, 'steps': 115881, 'loss/train': 1.2703900337219238} 08/31/2021 10:11:28 - INFO - __main__ - Step 115883: {'lr': 6.274622372173447e-05, 'samples': 22249536, 'steps': 115882, 'loss/train': 1.229189157485962} 08/31/2021 10:11:30 - INFO - __main__ - Step 115884: {'lr': 6.274270776495652e-05, 'samples': 22249728, 'steps': 115883, 'loss/train': 1.0720844268798828} 08/31/2021 10:11:30 - INFO - __main__ - Step 115885: {'lr': 6.273919189255389e-05, 'samples': 22249920, 'steps': 115884, 'loss/train': 1.056751012802124} 08/31/2021 10:11:31 - INFO - __main__ - Step 115886: {'lr': 6.273567610452801e-05, 'samples': 22250112, 'steps': 115885, 'loss/train': 1.2613035440444946} 08/31/2021 10:11:31 - INFO - __main__ - Step 115887: {'lr': 6.273216040088056e-05, 'samples': 22250304, 'steps': 115886, 'loss/train': 0.3607740104198456} 08/31/2021 10:11:31 - INFO - __main__ - Step 115888: {'lr': 6.272864478161311e-05, 'samples': 22250496, 'steps': 115887, 'loss/train': 0.46316924691200256} 08/31/2021 10:11:33 - INFO - __main__ - Step 115889: {'lr': 6.272512924672725e-05, 'samples': 22250688, 'steps': 115888, 'loss/train': 1.3872169256210327} 08/31/2021 10:11:33 - INFO - __main__ - Step 115890: {'lr': 6.272161379622454e-05, 'samples': 22250880, 'steps': 115889, 'loss/train': 1.3137537240982056} 08/31/2021 10:11:34 - INFO - __main__ - Step 115891: {'lr': 6.271809843010659e-05, 'samples': 22251072, 'steps': 115890, 'loss/train': 0.7368829250335693} 08/31/2021 10:11:34 - INFO - __main__ - Step 115892: {'lr': 6.271458314837498e-05, 'samples': 22251264, 'steps': 115891, 'loss/train': 1.287450909614563} 08/31/2021 10:11:34 - INFO - __main__ - Step 115893: {'lr': 6.271106795103127e-05, 'samples': 22251456, 'steps': 115892, 'loss/train': 1.1277921199798584} 08/31/2021 10:11:35 - INFO - __main__ - Step 115894: {'lr': 6.270755283807708e-05, 'samples': 22251648, 'steps': 115893, 'loss/train': 0.9432485699653625} 08/31/2021 10:11:37 - INFO - __main__ - Step 115895: {'lr': 6.270403780951394e-05, 'samples': 22251840, 'steps': 115894, 'loss/train': 1.2216097116470337} 08/31/2021 10:11:37 - INFO - __main__ - Step 115896: {'lr': 6.270052286534353e-05, 'samples': 22252032, 'steps': 115895, 'loss/train': 0.6338821053504944} 08/31/2021 10:11:37 - INFO - __main__ - Step 115897: {'lr': 6.269700800556732e-05, 'samples': 22252224, 'steps': 115896, 'loss/train': 0.07139142602682114} 08/31/2021 10:11:38 - INFO - __main__ - Step 115898: {'lr': 6.2693493230187e-05, 'samples': 22252416, 'steps': 115897, 'loss/train': 1.138849139213562} 08/31/2021 10:11:38 - INFO - __main__ - Step 115899: {'lr': 6.268997853920413e-05, 'samples': 22252608, 'steps': 115898, 'loss/train': 1.0937933921813965} 08/31/2021 10:11:38 - INFO - __main__ - Step 115900: {'lr': 6.26864639326202e-05, 'samples': 22252800, 'steps': 115899, 'loss/train': 1.0568737983703613} 08/31/2021 10:11:40 - INFO - __main__ - Step 115901: {'lr': 6.268294941043687e-05, 'samples': 22252992, 'steps': 115900, 'loss/train': 0.03867584839463234} 08/31/2021 10:11:40 - INFO - __main__ - Step 115902: {'lr': 6.267943497265571e-05, 'samples': 22253184, 'steps': 115901, 'loss/train': 0.037468209862709045} 08/31/2021 10:11:41 - INFO - __main__ - Step 115903: {'lr': 6.267592061927833e-05, 'samples': 22253376, 'steps': 115902, 'loss/train': 1.0780644416809082} 08/31/2021 10:11:41 - INFO - __main__ - Step 115904: {'lr': 6.267240635030624e-05, 'samples': 22253568, 'steps': 115903, 'loss/train': 0.2011580914258957} 08/31/2021 10:11:41 - INFO - __main__ - Step 115905: {'lr': 6.266889216574112e-05, 'samples': 22253760, 'steps': 115904, 'loss/train': 1.3770976066589355} 08/31/2021 10:11:43 - INFO - __main__ - Step 115906: {'lr': 6.266537806558448e-05, 'samples': 22253952, 'steps': 115905, 'loss/train': 1.3244426250457764} 08/31/2021 10:11:43 - INFO - __main__ - Step 115907: {'lr': 6.266186404983792e-05, 'samples': 22254144, 'steps': 115906, 'loss/train': 0.8332129120826721} 08/31/2021 10:11:44 - INFO - __main__ - Step 115908: {'lr': 6.265835011850307e-05, 'samples': 22254336, 'steps': 115907, 'loss/train': 0.8360320329666138} 08/31/2021 10:11:44 - INFO - __main__ - Step 115909: {'lr': 6.265483627158144e-05, 'samples': 22254528, 'steps': 115908, 'loss/train': 0.9188844561576843} 08/31/2021 10:11:45 - INFO - __main__ - Step 115910: {'lr': 6.265132250907468e-05, 'samples': 22254720, 'steps': 115909, 'loss/train': 0.8122181296348572} 08/31/2021 10:11:45 - INFO - __main__ - Step 115911: {'lr': 6.264780883098431e-05, 'samples': 22254912, 'steps': 115910, 'loss/train': 0.3392866849899292} 08/31/2021 10:11:46 - INFO - __main__ - Step 115912: {'lr': 6.264429523731205e-05, 'samples': 22255104, 'steps': 115911, 'loss/train': 0.7745487689971924} 08/31/2021 10:11:47 - INFO - __main__ - Step 115913: {'lr': 6.264078172805929e-05, 'samples': 22255296, 'steps': 115912, 'loss/train': 1.3805723190307617} 08/31/2021 10:11:47 - INFO - __main__ - Step 115914: {'lr': 6.263726830322772e-05, 'samples': 22255488, 'steps': 115913, 'loss/train': 0.47928813099861145} 08/31/2021 10:11:47 - INFO - __main__ - Step 115915: {'lr': 6.26337549628189e-05, 'samples': 22255680, 'steps': 115914, 'loss/train': 1.2389953136444092} 08/31/2021 10:11:48 - INFO - __main__ - Step 115916: {'lr': 6.26302417068344e-05, 'samples': 22255872, 'steps': 115915, 'loss/train': 1.5147267580032349} 08/31/2021 10:11:49 - INFO - __main__ - Step 115917: {'lr': 6.262672853527581e-05, 'samples': 22256064, 'steps': 115916, 'loss/train': 1.6758867502212524} 08/31/2021 10:11:50 - INFO - __main__ - Step 115918: {'lr': 6.262321544814476e-05, 'samples': 22256256, 'steps': 115917, 'loss/train': 0.8204829692840576} 08/31/2021 10:11:50 - INFO - __main__ - Step 115919: {'lr': 6.26197024454428e-05, 'samples': 22256448, 'steps': 115918, 'loss/train': 0.02973363921046257} 08/31/2021 10:11:51 - INFO - __main__ - Step 115920: {'lr': 6.261618952717149e-05, 'samples': 22256640, 'steps': 115919, 'loss/train': 1.0007127523422241} 08/31/2021 10:11:51 - INFO - __main__ - Step 115921: {'lr': 6.261267669333242e-05, 'samples': 22256832, 'steps': 115920, 'loss/train': 1.2664122581481934} 08/31/2021 10:11:52 - INFO - __main__ - Step 115922: {'lr': 6.260916394392721e-05, 'samples': 22257024, 'steps': 115921, 'loss/train': 0.6254037618637085} 08/31/2021 10:11:53 - INFO - __main__ - Step 115923: {'lr': 6.260565127895743e-05, 'samples': 22257216, 'steps': 115922, 'loss/train': 0.8889890313148499} 08/31/2021 10:11:53 - INFO - __main__ - Step 115924: {'lr': 6.260213869842462e-05, 'samples': 22257408, 'steps': 115923, 'loss/train': 1.267925500869751} 08/31/2021 10:11:54 - INFO - __main__ - Step 115925: {'lr': 6.259862620233043e-05, 'samples': 22257600, 'steps': 115924, 'loss/train': 1.4229645729064941} 08/31/2021 10:11:54 - INFO - __main__ - Step 115926: {'lr': 6.259511379067645e-05, 'samples': 22257792, 'steps': 115925, 'loss/train': 1.522674560546875} 08/31/2021 10:11:55 - INFO - __main__ - Step 115927: {'lr': 6.259160146346416e-05, 'samples': 22257984, 'steps': 115926, 'loss/train': 2.0447075366973877} 08/31/2021 10:11:56 - INFO - __main__ - Step 115928: {'lr': 6.25880892206952e-05, 'samples': 22258176, 'steps': 115927, 'loss/train': 0.44100138545036316} 08/31/2021 10:11:56 - INFO - __main__ - Step 115929: {'lr': 6.258457706237116e-05, 'samples': 22258368, 'steps': 115928, 'loss/train': 0.5749629735946655} 08/31/2021 10:11:56 - INFO - __main__ - Step 115930: {'lr': 6.258106498849361e-05, 'samples': 22258560, 'steps': 115929, 'loss/train': 0.7698420286178589} 08/31/2021 10:11:57 - INFO - __main__ - Step 115931: {'lr': 6.257755299906415e-05, 'samples': 22258752, 'steps': 115930, 'loss/train': 0.9981790781021118} 08/31/2021 10:11:59 - INFO - __main__ - Step 115932: {'lr': 6.257404109408435e-05, 'samples': 22258944, 'steps': 115931, 'loss/train': 1.235215663909912} 08/31/2021 10:11:59 - INFO - __main__ - Step 115933: {'lr': 6.257052927355577e-05, 'samples': 22259136, 'steps': 115932, 'loss/train': 0.8647881746292114} 08/31/2021 10:12:00 - INFO - __main__ - Step 115934: {'lr': 6.256701753748007e-05, 'samples': 22259328, 'steps': 115933, 'loss/train': 1.150665044784546} 08/31/2021 10:12:00 - INFO - __main__ - Step 115935: {'lr': 6.256350588585873e-05, 'samples': 22259520, 'steps': 115934, 'loss/train': 1.315455436706543} 08/31/2021 10:12:00 - INFO - __main__ - Step 115936: {'lr': 6.255999431869342e-05, 'samples': 22259712, 'steps': 115935, 'loss/train': 0.7761967182159424} 08/31/2021 10:12:01 - INFO - __main__ - Step 115937: {'lr': 6.255648283598565e-05, 'samples': 22259904, 'steps': 115936, 'loss/train': 0.02109467424452305} 08/31/2021 10:12:02 - INFO - __main__ - Step 115938: {'lr': 6.255297143773705e-05, 'samples': 22260096, 'steps': 115937, 'loss/train': 1.121800422668457} 08/31/2021 10:12:03 - INFO - __main__ - Step 115939: {'lr': 6.254946012394926e-05, 'samples': 22260288, 'steps': 115938, 'loss/train': 1.2390090227127075} 08/31/2021 10:12:03 - INFO - __main__ - Step 115940: {'lr': 6.254594889462373e-05, 'samples': 22260480, 'steps': 115939, 'loss/train': 1.2099950313568115} 08/31/2021 10:12:04 - INFO - __main__ - Step 115941: {'lr': 6.25424377497621e-05, 'samples': 22260672, 'steps': 115940, 'loss/train': 1.3031282424926758} 08/31/2021 10:12:04 - INFO - __main__ - Step 115942: {'lr': 6.253892668936593e-05, 'samples': 22260864, 'steps': 115941, 'loss/train': 0.03681155666708946} 08/31/2021 10:12:05 - INFO - __main__ - Step 115943: {'lr': 6.253541571343686e-05, 'samples': 22261056, 'steps': 115942, 'loss/train': 1.2302818298339844} 08/31/2021 10:12:06 - INFO - __main__ - Step 115944: {'lr': 6.25319048219764e-05, 'samples': 22261248, 'steps': 115943, 'loss/train': 0.8904946446418762} 08/31/2021 10:12:06 - INFO - __main__ - Step 115945: {'lr': 6.25283940149862e-05, 'samples': 22261440, 'steps': 115944, 'loss/train': 0.808843195438385} 08/31/2021 10:12:07 - INFO - __main__ - Step 115946: {'lr': 6.25248832924678e-05, 'samples': 22261632, 'steps': 115945, 'loss/train': 0.7161821126937866} 08/31/2021 10:12:07 - INFO - __main__ - Step 115947: {'lr': 6.252137265442282e-05, 'samples': 22261824, 'steps': 115946, 'loss/train': 0.5709840059280396} 08/31/2021 10:12:08 - INFO - __main__ - Step 115948: {'lr': 6.251786210085281e-05, 'samples': 22262016, 'steps': 115947, 'loss/train': 1.3669315576553345} 08/31/2021 10:12:09 - INFO - __main__ - Step 115949: {'lr': 6.251435163175933e-05, 'samples': 22262208, 'steps': 115948, 'loss/train': 1.4304823875427246} 08/31/2021 10:12:09 - INFO - __main__ - Step 115950: {'lr': 6.251084124714402e-05, 'samples': 22262400, 'steps': 115949, 'loss/train': 1.3802255392074585} 08/31/2021 10:12:10 - INFO - __main__ - Step 115951: {'lr': 6.250733094700842e-05, 'samples': 22262592, 'steps': 115950, 'loss/train': 1.1838692426681519} 08/31/2021 10:12:10 - INFO - __main__ - Step 115952: {'lr': 6.25038207313541e-05, 'samples': 22262784, 'steps': 115951, 'loss/train': 0.6793427467346191} 08/31/2021 10:12:11 - INFO - __main__ - Step 115953: {'lr': 6.250031060018277e-05, 'samples': 22262976, 'steps': 115952, 'loss/train': 1.5359033346176147} 08/31/2021 10:12:12 - INFO - __main__ - Step 115954: {'lr': 6.249680055349583e-05, 'samples': 22263168, 'steps': 115953, 'loss/train': 0.5347905158996582} 08/31/2021 10:12:12 - INFO - __main__ - Step 115955: {'lr': 6.249329059129494e-05, 'samples': 22263360, 'steps': 115954, 'loss/train': 0.135635107755661} 08/31/2021 10:12:13 - INFO - __main__ - Step 115956: {'lr': 6.248978071358166e-05, 'samples': 22263552, 'steps': 115955, 'loss/train': 0.7372456789016724} 08/31/2021 10:12:13 - INFO - __main__ - Step 115957: {'lr': 6.248627092035761e-05, 'samples': 22263744, 'steps': 115956, 'loss/train': 1.3013811111450195} 08/31/2021 10:12:14 - INFO - __main__ - Step 115958: {'lr': 6.248276121162432e-05, 'samples': 22263936, 'steps': 115957, 'loss/train': 0.5548391342163086} 08/31/2021 10:12:15 - INFO - __main__ - Step 115959: {'lr': 6.247925158738344e-05, 'samples': 22264128, 'steps': 115958, 'loss/train': 1.2694648504257202} 08/31/2021 10:12:15 - INFO - __main__ - Step 115960: {'lr': 6.247574204763651e-05, 'samples': 22264320, 'steps': 115959, 'loss/train': 1.1042203903198242} 08/31/2021 10:12:16 - INFO - __main__ - Step 115961: {'lr': 6.24722325923851e-05, 'samples': 22264512, 'steps': 115960, 'loss/train': 1.447563886642456} 08/31/2021 10:12:16 - INFO - __main__ - Step 115962: {'lr': 6.246872322163083e-05, 'samples': 22264704, 'steps': 115961, 'loss/train': 1.5622738599777222} 08/31/2021 10:12:17 - INFO - __main__ - Step 115963: {'lr': 6.246521393537527e-05, 'samples': 22264896, 'steps': 115962, 'loss/train': 1.5703272819519043} 08/31/2021 10:12:18 - INFO - __main__ - Step 115964: {'lr': 6.246170473361995e-05, 'samples': 22265088, 'steps': 115963, 'loss/train': 1.1326156854629517} 08/31/2021 10:12:18 - INFO - __main__ - Step 115965: {'lr': 6.245819561636653e-05, 'samples': 22265280, 'steps': 115964, 'loss/train': 0.628339946269989} 08/31/2021 10:12:19 - INFO - __main__ - Step 115966: {'lr': 6.245468658361662e-05, 'samples': 22265472, 'steps': 115965, 'loss/train': 1.1697533130645752} 08/31/2021 10:12:19 - INFO - __main__ - Step 115967: {'lr': 6.245117763537164e-05, 'samples': 22265664, 'steps': 115966, 'loss/train': 1.2442833185195923} 08/31/2021 10:12:20 - INFO - __main__ - Step 115968: {'lr': 6.244766877163327e-05, 'samples': 22265856, 'steps': 115967, 'loss/train': 1.3785020112991333} 08/31/2021 10:12:21 - INFO - __main__ - Step 115969: {'lr': 6.24441599924031e-05, 'samples': 22266048, 'steps': 115968, 'loss/train': 1.3809573650360107} 08/31/2021 10:12:21 - INFO - __main__ - Step 115970: {'lr': 6.244065129768267e-05, 'samples': 22266240, 'steps': 115969, 'loss/train': 1.051027774810791} 08/31/2021 10:12:22 - INFO - __main__ - Step 115971: {'lr': 6.243714268747364e-05, 'samples': 22266432, 'steps': 115970, 'loss/train': 1.7108738422393799} 08/31/2021 10:12:22 - INFO - __main__ - Step 115972: {'lr': 6.24336341617775e-05, 'samples': 22266624, 'steps': 115971, 'loss/train': 0.5341475605964661} 08/31/2021 10:12:22 - INFO - __main__ - Step 115973: {'lr': 6.243012572059586e-05, 'samples': 22266816, 'steps': 115972, 'loss/train': 1.4414781332015991} 08/31/2021 10:12:24 - INFO - __main__ - Step 115974: {'lr': 6.242661736393035e-05, 'samples': 22267008, 'steps': 115973, 'loss/train': 1.1068472862243652} 08/31/2021 10:12:24 - INFO - __main__ - Step 115975: {'lr': 6.242310909178248e-05, 'samples': 22267200, 'steps': 115974, 'loss/train': 1.0578908920288086} 08/31/2021 10:12:25 - INFO - __main__ - Step 115976: {'lr': 6.241960090415388e-05, 'samples': 22267392, 'steps': 115975, 'loss/train': 1.100683569908142} 08/31/2021 10:12:25 - INFO - __main__ - Step 115977: {'lr': 6.24160928010461e-05, 'samples': 22267584, 'steps': 115976, 'loss/train': 1.2515190839767456} 08/31/2021 10:12:25 - INFO - __main__ - Step 115978: {'lr': 6.241258478246073e-05, 'samples': 22267776, 'steps': 115977, 'loss/train': 1.1917932033538818} 08/31/2021 10:12:27 - INFO - __main__ - Step 115979: {'lr': 6.240907684839935e-05, 'samples': 22267968, 'steps': 115978, 'loss/train': 1.4505940675735474} 08/31/2021 10:12:28 - INFO - __main__ - Step 115980: {'lr': 6.240556899886366e-05, 'samples': 22268160, 'steps': 115979, 'loss/train': 1.2221266031265259} 08/31/2021 10:12:28 - INFO - __main__ - Step 115981: {'lr': 6.240206123385503e-05, 'samples': 22268352, 'steps': 115980, 'loss/train': 0.8331853747367859} 08/31/2021 10:12:29 - INFO - __main__ - Step 115982: {'lr': 6.239855355337512e-05, 'samples': 22268544, 'steps': 115981, 'loss/train': 1.2998186349868774} 08/31/2021 10:12:29 - INFO - __main__ - Step 115983: {'lr': 6.239504595742554e-05, 'samples': 22268736, 'steps': 115982, 'loss/train': 1.1627225875854492} 08/31/2021 10:12:30 - INFO - __main__ - Step 115984: {'lr': 6.239153844600787e-05, 'samples': 22268928, 'steps': 115983, 'loss/train': 1.3359869718551636} 08/31/2021 10:12:31 - INFO - __main__ - Step 115985: {'lr': 6.238803101912366e-05, 'samples': 22269120, 'steps': 115984, 'loss/train': 0.7561874389648438} 08/31/2021 10:12:31 - INFO - __main__ - Step 115986: {'lr': 6.23845236767745e-05, 'samples': 22269312, 'steps': 115985, 'loss/train': 0.8682880997657776} 08/31/2021 10:12:32 - INFO - __main__ - Step 115987: {'lr': 6.238101641896199e-05, 'samples': 22269504, 'steps': 115986, 'loss/train': 0.8205223679542542} 08/31/2021 10:12:32 - INFO - __main__ - Step 115988: {'lr': 6.237750924568772e-05, 'samples': 22269696, 'steps': 115987, 'loss/train': 1.3716691732406616} 08/31/2021 10:12:34 - INFO - __main__ - Step 115989: {'lr': 6.237400215695321e-05, 'samples': 22269888, 'steps': 115988, 'loss/train': 1.3672593832015991} 08/31/2021 10:12:34 - INFO - __main__ - Step 115990: {'lr': 6.23704951527601e-05, 'samples': 22270080, 'steps': 115989, 'loss/train': 0.9613891839981079} 08/31/2021 10:12:34 - INFO - __main__ - Step 115991: {'lr': 6.236698823310996e-05, 'samples': 22270272, 'steps': 115990, 'loss/train': 0.7886232137680054} 08/31/2021 10:12:35 - INFO - __main__ - Step 115992: {'lr': 6.236348139800436e-05, 'samples': 22270464, 'steps': 115991, 'loss/train': 0.7374354004859924} 08/31/2021 10:12:35 - INFO - __main__ - Step 115993: {'lr': 6.235997464744492e-05, 'samples': 22270656, 'steps': 115992, 'loss/train': 0.09960586577653885} 08/31/2021 10:12:35 - INFO - __main__ - Step 115994: {'lr': 6.235646798143313e-05, 'samples': 22270848, 'steps': 115993, 'loss/train': 1.178202509880066} 08/31/2021 10:12:37 - INFO - __main__ - Step 115995: {'lr': 6.235296139997062e-05, 'samples': 22271040, 'steps': 115994, 'loss/train': 1.8869417905807495} 08/31/2021 10:12:38 - INFO - __main__ - Step 115996: {'lr': 6.234945490305896e-05, 'samples': 22271232, 'steps': 115995, 'loss/train': 1.160117268562317} 08/31/2021 10:12:38 - INFO - __main__ - Step 115997: {'lr': 6.234594849069975e-05, 'samples': 22271424, 'steps': 115996, 'loss/train': 1.2152599096298218} 08/31/2021 10:12:38 - INFO - __main__ - Step 115998: {'lr': 6.234244216289456e-05, 'samples': 22271616, 'steps': 115997, 'loss/train': 0.7982354164123535} 08/31/2021 10:12:39 - INFO - __main__ - Step 115999: {'lr': 6.233893591964495e-05, 'samples': 22271808, 'steps': 115998, 'loss/train': 0.23429538309574127} 08/31/2021 10:12:40 - INFO - __main__ - Step 116000: {'lr': 6.233542976095255e-05, 'samples': 22272000, 'steps': 115999, 'loss/train': 1.339656114578247} 08/31/2021 10:12:41 - INFO - __main__ - Step 116001: {'lr': 6.23319236868189e-05, 'samples': 22272192, 'steps': 116000, 'loss/train': 1.228444218635559} 08/31/2021 10:12:41 - INFO - __main__ - Step 116002: {'lr': 6.23284176972456e-05, 'samples': 22272384, 'steps': 116001, 'loss/train': 0.7981396317481995} 08/31/2021 10:12:41 - INFO - __main__ - Step 116003: {'lr': 6.232491179223421e-05, 'samples': 22272576, 'steps': 116002, 'loss/train': 1.2129616737365723} 08/31/2021 10:12:42 - INFO - __main__ - Step 116004: {'lr': 6.232140597178629e-05, 'samples': 22272768, 'steps': 116003, 'loss/train': 0.6653004288673401} 08/31/2021 10:12:43 - INFO - __main__ - Step 116005: {'lr': 6.231790023590348e-05, 'samples': 22272960, 'steps': 116004, 'loss/train': 1.2173749208450317} 08/31/2021 10:12:44 - INFO - __main__ - Step 116006: {'lr': 6.23143945845874e-05, 'samples': 22273152, 'steps': 116005, 'loss/train': 1.5702255964279175} 08/31/2021 10:12:44 - INFO - __main__ - Step 116007: {'lr': 6.231088901783947e-05, 'samples': 22273344, 'steps': 116006, 'loss/train': 2.296915292739868} 08/31/2021 10:12:44 - INFO - __main__ - Step 116008: {'lr': 6.230738353566137e-05, 'samples': 22273536, 'steps': 116007, 'loss/train': 1.1373295783996582} 08/31/2021 10:12:45 - INFO - __main__ - Step 116009: {'lr': 6.230387813805467e-05, 'samples': 22273728, 'steps': 116008, 'loss/train': 1.3756123781204224} 08/31/2021 10:12:46 - INFO - __main__ - Step 116010: {'lr': 6.230037282502093e-05, 'samples': 22273920, 'steps': 116009, 'loss/train': 1.2558432817459106} 08/31/2021 10:12:47 - INFO - __main__ - Step 116011: {'lr': 6.229686759656175e-05, 'samples': 22274112, 'steps': 116010, 'loss/train': 2.1822779178619385} 08/31/2021 10:12:47 - INFO - __main__ - Step 116012: {'lr': 6.229336245267872e-05, 'samples': 22274304, 'steps': 116011, 'loss/train': 0.9163280725479126} 08/31/2021 10:12:47 - INFO - __main__ - Step 116013: {'lr': 6.22898573933734e-05, 'samples': 22274496, 'steps': 116012, 'loss/train': 1.2052208185195923} 08/31/2021 10:12:48 - INFO - __main__ - Step 116014: {'lr': 6.228635241864736e-05, 'samples': 22274688, 'steps': 116013, 'loss/train': 1.1970347166061401} 08/31/2021 10:12:49 - INFO - __main__ - Step 116015: {'lr': 6.228284752850218e-05, 'samples': 22274880, 'steps': 116014, 'loss/train': 0.8965126872062683} 08/31/2021 10:12:50 - INFO - __main__ - Step 116016: {'lr': 6.227934272293947e-05, 'samples': 22275072, 'steps': 116015, 'loss/train': 0.7409398555755615} 08/31/2021 10:12:50 - INFO - __main__ - Step 116017: {'lr': 6.227583800196079e-05, 'samples': 22275264, 'steps': 116016, 'loss/train': 1.0268415212631226} 08/31/2021 10:12:51 - INFO - __main__ - Step 116018: {'lr': 6.227233336556772e-05, 'samples': 22275456, 'steps': 116017, 'loss/train': 1.3191910982131958} 08/31/2021 10:12:51 - INFO - __main__ - Step 116019: {'lr': 6.226882881376186e-05, 'samples': 22275648, 'steps': 116018, 'loss/train': 0.03058682195842266} 08/31/2021 10:12:52 - INFO - __main__ - Step 116020: {'lr': 6.226532434654484e-05, 'samples': 22275840, 'steps': 116019, 'loss/train': 1.0711629390716553} 08/31/2021 10:12:53 - INFO - __main__ - Step 116021: {'lr': 6.226181996391809e-05, 'samples': 22276032, 'steps': 116020, 'loss/train': 1.4551438093185425} 08/31/2021 10:12:53 - INFO - __main__ - Step 116022: {'lr': 6.225831566588324e-05, 'samples': 22276224, 'steps': 116021, 'loss/train': 1.1818482875823975} 08/31/2021 10:12:54 - INFO - __main__ - Step 116023: {'lr': 6.22548114524419e-05, 'samples': 22276416, 'steps': 116022, 'loss/train': 1.1124632358551025} 08/31/2021 10:12:54 - INFO - __main__ - Step 116024: {'lr': 6.225130732359566e-05, 'samples': 22276608, 'steps': 116023, 'loss/train': 1.013657808303833} 08/31/2021 10:12:55 - INFO - __main__ - Step 116025: {'lr': 6.224780327934609e-05, 'samples': 22276800, 'steps': 116024, 'loss/train': 1.6078237295150757} 08/31/2021 10:12:56 - INFO - __main__ - Step 116026: {'lr': 6.224429931969474e-05, 'samples': 22276992, 'steps': 116025, 'loss/train': 1.1784943342208862} 08/31/2021 10:12:56 - INFO - __main__ - Step 116027: {'lr': 6.224079544464326e-05, 'samples': 22277184, 'steps': 116026, 'loss/train': 1.0680532455444336} 08/31/2021 10:12:57 - INFO - __main__ - Step 116028: {'lr': 6.223729165419311e-05, 'samples': 22277376, 'steps': 116027, 'loss/train': 1.2202508449554443} 08/31/2021 10:12:57 - INFO - __main__ - Step 116029: {'lr': 6.2233787948346e-05, 'samples': 22277568, 'steps': 116028, 'loss/train': 1.1858406066894531} 08/31/2021 10:12:57 - INFO - __main__ - Step 116030: {'lr': 6.223028432710343e-05, 'samples': 22277760, 'steps': 116029, 'loss/train': 1.4174085855484009} 08/31/2021 10:12:59 - INFO - __main__ - Step 116031: {'lr': 6.222678079046699e-05, 'samples': 22277952, 'steps': 116030, 'loss/train': 1.0419913530349731} 08/31/2021 10:13:00 - INFO - __main__ - Step 116032: {'lr': 6.222327733843824e-05, 'samples': 22278144, 'steps': 116031, 'loss/train': 1.6355453729629517} 08/31/2021 10:13:00 - INFO - __main__ - Step 116033: {'lr': 6.221977397101889e-05, 'samples': 22278336, 'steps': 116032, 'loss/train': 1.4429895877838135} 08/31/2021 10:13:01 - INFO - __main__ - Step 116034: {'lr': 6.221627068821035e-05, 'samples': 22278528, 'steps': 116033, 'loss/train': 0.9099439382553101} 08/31/2021 10:13:01 - INFO - __main__ - Step 116035: {'lr': 6.221276749001423e-05, 'samples': 22278720, 'steps': 116034, 'loss/train': 1.1373847723007202} 08/31/2021 10:13:03 - INFO - __main__ - Step 116036: {'lr': 6.220926437643215e-05, 'samples': 22278912, 'steps': 116035, 'loss/train': 1.4189882278442383} 08/31/2021 10:13:03 - INFO - __main__ - Step 116037: {'lr': 6.220576134746567e-05, 'samples': 22279104, 'steps': 116036, 'loss/train': 0.9977003335952759} 08/31/2021 10:13:03 - INFO - __main__ - Step 116038: {'lr': 6.220225840311638e-05, 'samples': 22279296, 'steps': 116037, 'loss/train': 1.6215782165527344} 08/31/2021 10:13:04 - INFO - __main__ - Step 116039: {'lr': 6.219875554338586e-05, 'samples': 22279488, 'steps': 116038, 'loss/train': 1.6839450597763062} 08/31/2021 10:13:04 - INFO - __main__ - Step 116040: {'lr': 6.21952527682757e-05, 'samples': 22279680, 'steps': 116039, 'loss/train': 0.6555514335632324} 08/31/2021 10:13:06 - INFO - __main__ - Step 116041: {'lr': 6.219175007778744e-05, 'samples': 22279872, 'steps': 116040, 'loss/train': 1.099011778831482} 08/31/2021 10:13:06 - INFO - __main__ - Step 116042: {'lr': 6.218824747192267e-05, 'samples': 22280064, 'steps': 116041, 'loss/train': 1.3890056610107422} 08/31/2021 10:13:07 - INFO - __main__ - Step 116043: {'lr': 6.2184744950683e-05, 'samples': 22280256, 'steps': 116042, 'loss/train': 1.234539270401001} 08/31/2021 10:13:07 - INFO - __main__ - Step 116044: {'lr': 6.218124251406998e-05, 'samples': 22280448, 'steps': 116043, 'loss/train': 0.030297189950942993} 08/31/2021 10:13:07 - INFO - __main__ - Step 116045: {'lr': 6.217774016208518e-05, 'samples': 22280640, 'steps': 116044, 'loss/train': 0.9135698676109314} 08/31/2021 10:13:09 - INFO - __main__ - Step 116046: {'lr': 6.21742378947302e-05, 'samples': 22280832, 'steps': 116045, 'loss/train': 1.6398029327392578} 08/31/2021 10:13:09 - INFO - __main__ - Step 116047: {'lr': 6.217073571200668e-05, 'samples': 22281024, 'steps': 116046, 'loss/train': 1.6053171157836914} 08/31/2021 10:13:10 - INFO - __main__ - Step 116048: {'lr': 6.216723361391607e-05, 'samples': 22281216, 'steps': 116047, 'loss/train': 1.2617980241775513} 08/31/2021 10:13:10 - INFO - __main__ - Step 116049: {'lr': 6.216373160045999e-05, 'samples': 22281408, 'steps': 116048, 'loss/train': 1.132306456565857} 08/31/2021 10:13:10 - INFO - __main__ - Step 116050: {'lr': 6.216022967164004e-05, 'samples': 22281600, 'steps': 116049, 'loss/train': 1.802476167678833} 08/31/2021 10:13:12 - INFO - __main__ - Step 116051: {'lr': 6.215672782745779e-05, 'samples': 22281792, 'steps': 116050, 'loss/train': 1.0224741697311401} 08/31/2021 10:13:12 - INFO - __main__ - Step 116052: {'lr': 6.215322606791482e-05, 'samples': 22281984, 'steps': 116051, 'loss/train': 0.9187337160110474} 08/31/2021 10:13:13 - INFO - __main__ - Step 116053: {'lr': 6.214972439301273e-05, 'samples': 22282176, 'steps': 116052, 'loss/train': 1.2963776588439941} 08/31/2021 10:13:13 - INFO - __main__ - Step 116054: {'lr': 6.214622280275304e-05, 'samples': 22282368, 'steps': 116053, 'loss/train': 1.4153071641921997} 08/31/2021 10:13:13 - INFO - __main__ - Step 116055: {'lr': 6.214272129713738e-05, 'samples': 22282560, 'steps': 116054, 'loss/train': 0.8701224327087402} 08/31/2021 10:13:15 - INFO - __main__ - Step 116056: {'lr': 6.21392198761673e-05, 'samples': 22282752, 'steps': 116055, 'loss/train': 0.6523185968399048} 08/31/2021 10:13:16 - INFO - __main__ - Step 116057: {'lr': 6.21357185398444e-05, 'samples': 22282944, 'steps': 116056, 'loss/train': 0.7892919182777405} 08/31/2021 10:13:16 - INFO - __main__ - Step 116058: {'lr': 6.213221728817025e-05, 'samples': 22283136, 'steps': 116057, 'loss/train': 0.7280242443084717} 08/31/2021 10:13:16 - INFO - __main__ - Step 116059: {'lr': 6.212871612114648e-05, 'samples': 22283328, 'steps': 116058, 'loss/train': 0.5087061524391174} 08/31/2021 10:13:17 - INFO - __main__ - Step 116060: {'lr': 6.212521503877455e-05, 'samples': 22283520, 'steps': 116059, 'loss/train': 0.11634206026792526} 08/31/2021 10:13:17 - INFO - __main__ - Step 116061: {'lr': 6.21217140410561e-05, 'samples': 22283712, 'steps': 116060, 'loss/train': 0.015155026689171791} 08/31/2021 10:13:17 - INFO - __main__ - Step 116062: {'lr': 6.21182131279927e-05, 'samples': 22283904, 'steps': 116061, 'loss/train': 0.7749218940734863} 08/31/2021 10:13:19 - INFO - __main__ - Step 116063: {'lr': 6.211471229958595e-05, 'samples': 22284096, 'steps': 116062, 'loss/train': 0.5045925378799438} 08/31/2021 10:13:20 - INFO - __main__ - Step 116064: {'lr': 6.21112115558374e-05, 'samples': 22284288, 'steps': 116063, 'loss/train': 1.0318161249160767} 08/31/2021 10:13:20 - INFO - __main__ - Step 116065: {'lr': 6.210771089674863e-05, 'samples': 22284480, 'steps': 116064, 'loss/train': 0.9480038285255432} 08/31/2021 10:13:20 - INFO - __main__ - Step 116066: {'lr': 6.210421032232125e-05, 'samples': 22284672, 'steps': 116065, 'loss/train': 1.508154273033142} 08/31/2021 10:13:21 - INFO - __main__ - Step 116067: {'lr': 6.21007098325568e-05, 'samples': 22284864, 'steps': 116066, 'loss/train': 0.42120617628097534} 08/31/2021 10:13:22 - INFO - __main__ - Step 116068: {'lr': 6.209720942745686e-05, 'samples': 22285056, 'steps': 116067, 'loss/train': 0.026603706181049347} 08/31/2021 10:13:23 - INFO - __main__ - Step 116069: {'lr': 6.209370910702302e-05, 'samples': 22285248, 'steps': 116068, 'loss/train': 1.259934425354004} 08/31/2021 10:13:23 - INFO - __main__ - Step 116070: {'lr': 6.209020887125694e-05, 'samples': 22285440, 'steps': 116069, 'loss/train': 1.1032694578170776} 08/31/2021 10:13:24 - INFO - __main__ - Step 116071: {'lr': 6.208670872016003e-05, 'samples': 22285632, 'steps': 116070, 'loss/train': 0.7646414637565613} 08/31/2021 10:13:24 - INFO - __main__ - Step 116072: {'lr': 6.208320865373396e-05, 'samples': 22285824, 'steps': 116071, 'loss/train': 1.342757225036621} 08/31/2021 10:13:26 - INFO - __main__ - Step 116073: {'lr': 6.207970867198028e-05, 'samples': 22286016, 'steps': 116072, 'loss/train': 1.2384406328201294} 08/31/2021 10:13:26 - INFO - __main__ - Step 116074: {'lr': 6.207620877490061e-05, 'samples': 22286208, 'steps': 116073, 'loss/train': 1.3249627351760864} 08/31/2021 10:13:26 - INFO - __main__ - Step 116075: {'lr': 6.207270896249648e-05, 'samples': 22286400, 'steps': 116074, 'loss/train': 0.0857231393456459} 08/31/2021 10:13:27 - INFO - __main__ - Step 116076: {'lr': 6.20692092347695e-05, 'samples': 22286592, 'steps': 116075, 'loss/train': 1.1213558912277222} 08/31/2021 10:13:27 - INFO - __main__ - Step 116077: {'lr': 6.206570959172122e-05, 'samples': 22286784, 'steps': 116076, 'loss/train': 1.0532130002975464} 08/31/2021 10:13:27 - INFO - __main__ - Step 116078: {'lr': 6.206221003335325e-05, 'samples': 22286976, 'steps': 116077, 'loss/train': 0.6944109797477722} 08/31/2021 10:13:29 - INFO - __main__ - Step 116079: {'lr': 6.205871055966713e-05, 'samples': 22287168, 'steps': 116078, 'loss/train': 0.8146215081214905} 08/31/2021 10:13:29 - INFO - __main__ - Step 116080: {'lr': 6.205521117066445e-05, 'samples': 22287360, 'steps': 116079, 'loss/train': 1.318737268447876} 08/31/2021 10:13:30 - INFO - __main__ - Step 116081: {'lr': 6.20517118663469e-05, 'samples': 22287552, 'steps': 116080, 'loss/train': 1.2740399837493896} 08/31/2021 10:13:30 - INFO - __main__ - Step 116082: {'lr': 6.204821264671584e-05, 'samples': 22287744, 'steps': 116081, 'loss/train': 1.0330296754837036} 08/31/2021 10:13:30 - INFO - __main__ - Step 116083: {'lr': 6.204471351177296e-05, 'samples': 22287936, 'steps': 116082, 'loss/train': 1.2487530708312988} 08/31/2021 10:13:33 - INFO - __main__ - Step 116084: {'lr': 6.204121446151983e-05, 'samples': 22288128, 'steps': 116083, 'loss/train': 0.8114866614341736} 08/31/2021 10:13:33 - INFO - __main__ - Step 116085: {'lr': 6.203771549595804e-05, 'samples': 22288320, 'steps': 116084, 'loss/train': 1.6415634155273438} 08/31/2021 10:13:33 - INFO - __main__ - Step 116086: {'lr': 6.203421661508916e-05, 'samples': 22288512, 'steps': 116085, 'loss/train': 1.2053558826446533} 08/31/2021 10:13:34 - INFO - __main__ - Step 116087: {'lr': 6.203071781891476e-05, 'samples': 22288704, 'steps': 116086, 'loss/train': 1.8104209899902344} 08/31/2021 10:13:34 - INFO - __main__ - Step 116088: {'lr': 6.202721910743639e-05, 'samples': 22288896, 'steps': 116087, 'loss/train': 0.8860201239585876} 08/31/2021 10:13:36 - INFO - __main__ - Step 116089: {'lr': 6.202372048065569e-05, 'samples': 22289088, 'steps': 116088, 'loss/train': 0.3377138376235962} 08/31/2021 10:13:36 - INFO - __main__ - Step 116090: {'lr': 6.202022193857417e-05, 'samples': 22289280, 'steps': 116089, 'loss/train': 0.9423485398292542} 08/31/2021 10:13:36 - INFO - __main__ - Step 116091: {'lr': 6.201672348119348e-05, 'samples': 22289472, 'steps': 116090, 'loss/train': 0.7310601472854614} 08/31/2021 10:13:37 - INFO - __main__ - Step 116092: {'lr': 6.201322510851518e-05, 'samples': 22289664, 'steps': 116091, 'loss/train': 0.11958815902471542} 08/31/2021 10:13:37 - INFO - __main__ - Step 116093: {'lr': 6.200972682054076e-05, 'samples': 22289856, 'steps': 116092, 'loss/train': 1.3723982572555542} 08/31/2021 10:13:39 - INFO - __main__ - Step 116094: {'lr': 6.200622861727187e-05, 'samples': 22290048, 'steps': 116093, 'loss/train': 1.7082948684692383} 08/31/2021 10:13:39 - INFO - __main__ - Step 116095: {'lr': 6.200273049871006e-05, 'samples': 22290240, 'steps': 116094, 'loss/train': 0.842962920665741} 08/31/2021 10:13:40 - INFO - __main__ - Step 116096: {'lr': 6.199923246485692e-05, 'samples': 22290432, 'steps': 116095, 'loss/train': 1.3323533535003662} 08/31/2021 10:13:40 - INFO - __main__ - Step 116097: {'lr': 6.199573451571403e-05, 'samples': 22290624, 'steps': 116096, 'loss/train': 1.2885617017745972} 08/31/2021 10:13:40 - INFO - __main__ - Step 116098: {'lr': 6.199223665128297e-05, 'samples': 22290816, 'steps': 116097, 'loss/train': 1.0791393518447876} 08/31/2021 10:13:41 - INFO - __main__ - Step 116099: {'lr': 6.198873887156528e-05, 'samples': 22291008, 'steps': 116098, 'loss/train': 1.1256481409072876} 08/31/2021 10:13:42 - INFO - __main__ - Step 116100: {'lr': 6.198524117656259e-05, 'samples': 22291200, 'steps': 116099, 'loss/train': 0.6311489939689636} 08/31/2021 10:13:43 - INFO - __main__ - Step 116101: {'lr': 6.198174356627645e-05, 'samples': 22291392, 'steps': 116100, 'loss/train': 1.2997630834579468} 08/31/2021 10:13:43 - INFO - __main__ - Step 116102: {'lr': 6.197824604070842e-05, 'samples': 22291584, 'steps': 116101, 'loss/train': 1.6523289680480957} 08/31/2021 10:13:43 - INFO - __main__ - Step 116103: {'lr': 6.197474859986016e-05, 'samples': 22291776, 'steps': 116102, 'loss/train': 0.8291903138160706} 08/31/2021 10:13:44 - INFO - __main__ - Step 116104: {'lr': 6.197125124373313e-05, 'samples': 22291968, 'steps': 116103, 'loss/train': 0.35221999883651733} 08/31/2021 10:13:45 - INFO - __main__ - Step 116105: {'lr': 6.196775397232893e-05, 'samples': 22292160, 'steps': 116104, 'loss/train': 1.155295491218567} 08/31/2021 10:13:46 - INFO - __main__ - Step 116106: {'lr': 6.196425678564916e-05, 'samples': 22292352, 'steps': 116105, 'loss/train': 1.3052436113357544} 08/31/2021 10:13:46 - INFO - __main__ - Step 116107: {'lr': 6.196075968369538e-05, 'samples': 22292544, 'steps': 116106, 'loss/train': 0.8948615193367004} 08/31/2021 10:13:46 - INFO - __main__ - Step 116108: {'lr': 6.19572626664692e-05, 'samples': 22292736, 'steps': 116107, 'loss/train': 0.81983482837677} 08/31/2021 10:13:47 - INFO - __main__ - Step 116109: {'lr': 6.195376573397218e-05, 'samples': 22292928, 'steps': 116108, 'loss/train': 0.025892361998558044} 08/31/2021 10:13:48 - INFO - __main__ - Step 116110: {'lr': 6.195026888620589e-05, 'samples': 22293120, 'steps': 116109, 'loss/train': 1.0226117372512817} 08/31/2021 10:13:49 - INFO - __main__ - Step 116111: {'lr': 6.19467721231719e-05, 'samples': 22293312, 'steps': 116110, 'loss/train': 1.3216874599456787} 08/31/2021 10:13:49 - INFO - __main__ - Step 116112: {'lr': 6.19432754448718e-05, 'samples': 22293504, 'steps': 116111, 'loss/train': 0.8680473566055298} 08/31/2021 10:13:49 - INFO - __main__ - Step 116113: {'lr': 6.193977885130714e-05, 'samples': 22293696, 'steps': 116112, 'loss/train': 0.8546308279037476} 08/31/2021 10:13:50 - INFO - __main__ - Step 116114: {'lr': 6.193628234247961e-05, 'samples': 22293888, 'steps': 116113, 'loss/train': 0.7422985434532166} 08/31/2021 10:13:51 - INFO - __main__ - Step 116115: {'lr': 6.19327859183906e-05, 'samples': 22294080, 'steps': 116114, 'loss/train': 0.7737759947776794} 08/31/2021 10:13:52 - INFO - __main__ - Step 116116: {'lr': 6.192928957904179e-05, 'samples': 22294272, 'steps': 116115, 'loss/train': 1.306883454322815} 08/31/2021 10:13:52 - INFO - __main__ - Step 116117: {'lr': 6.192579332443471e-05, 'samples': 22294464, 'steps': 116116, 'loss/train': 1.1014412641525269} 08/31/2021 10:13:52 - INFO - __main__ - Step 116118: {'lr': 6.192229715457098e-05, 'samples': 22294656, 'steps': 116117, 'loss/train': 1.2394659519195557} 08/31/2021 10:13:53 - INFO - __main__ - Step 116119: {'lr': 6.191880106945219e-05, 'samples': 22294848, 'steps': 116118, 'loss/train': 1.1641510725021362} 08/31/2021 10:13:54 - INFO - __main__ - Step 116120: {'lr': 6.191530506907985e-05, 'samples': 22295040, 'steps': 116119, 'loss/train': 0.470951646566391} 08/31/2021 10:13:55 - INFO - __main__ - Step 116121: {'lr': 6.19118091534556e-05, 'samples': 22295232, 'steps': 116120, 'loss/train': 1.1915639638900757} 08/31/2021 10:13:55 - INFO - __main__ - Step 116122: {'lr': 6.190831332258095e-05, 'samples': 22295424, 'steps': 116121, 'loss/train': 1.1186455488204956} 08/31/2021 10:13:55 - INFO - __main__ - Step 116123: {'lr': 6.190481757645753e-05, 'samples': 22295616, 'steps': 116122, 'loss/train': 0.7188665270805359} 08/31/2021 10:13:56 - INFO - __main__ - Step 116124: {'lr': 6.19013219150869e-05, 'samples': 22295808, 'steps': 116123, 'loss/train': 1.1743706464767456} 08/31/2021 10:13:56 - INFO - __main__ - Step 116125: {'lr': 6.189782633847063e-05, 'samples': 22296000, 'steps': 116124, 'loss/train': 1.2856056690216064} 08/31/2021 10:13:57 - INFO - __main__ - Step 116126: {'lr': 6.189433084661031e-05, 'samples': 22296192, 'steps': 116125, 'loss/train': 0.6926990151405334} 08/31/2021 10:13:58 - INFO - __main__ - Step 116127: {'lr': 6.189083543950755e-05, 'samples': 22296384, 'steps': 116126, 'loss/train': 1.4991365671157837} 08/31/2021 10:13:58 - INFO - __main__ - Step 116128: {'lr': 6.188734011716382e-05, 'samples': 22296576, 'steps': 116127, 'loss/train': 1.2131659984588623} 08/31/2021 10:13:59 - INFO - __main__ - Step 116129: {'lr': 6.188384487958074e-05, 'samples': 22296768, 'steps': 116128, 'loss/train': 0.8169859051704407} 08/31/2021 10:13:59 - INFO - __main__ - Step 116130: {'lr': 6.18803497267599e-05, 'samples': 22296960, 'steps': 116129, 'loss/train': 0.9978481531143188} 08/31/2021 10:14:00 - INFO - __main__ - Step 116131: {'lr': 6.187685465870287e-05, 'samples': 22297152, 'steps': 116130, 'loss/train': 1.1605584621429443} 08/31/2021 10:14:01 - INFO - __main__ - Step 116132: {'lr': 6.187335967541125e-05, 'samples': 22297344, 'steps': 116131, 'loss/train': 1.1723484992980957} 08/31/2021 10:14:01 - INFO - __main__ - Step 116133: {'lr': 6.186986477688657e-05, 'samples': 22297536, 'steps': 116132, 'loss/train': 1.6435437202453613} 08/31/2021 10:14:02 - INFO - __main__ - Step 116134: {'lr': 6.186636996313041e-05, 'samples': 22297728, 'steps': 116133, 'loss/train': 0.6763352155685425} 08/31/2021 10:14:02 - INFO - __main__ - Step 116135: {'lr': 6.186287523414438e-05, 'samples': 22297920, 'steps': 116134, 'loss/train': 0.35845592617988586} 08/31/2021 10:14:04 - INFO - __main__ - Step 116136: {'lr': 6.185938058993005e-05, 'samples': 22298112, 'steps': 116135, 'loss/train': 0.9289090037345886} 08/31/2021 10:14:04 - INFO - __main__ - Step 116137: {'lr': 6.185588603048898e-05, 'samples': 22298304, 'steps': 116136, 'loss/train': 1.9151297807693481} 08/31/2021 10:14:04 - INFO - __main__ - Step 116138: {'lr': 6.185239155582274e-05, 'samples': 22298496, 'steps': 116137, 'loss/train': 1.1825928688049316} 08/31/2021 10:14:05 - INFO - __main__ - Step 116139: {'lr': 6.184889716593286e-05, 'samples': 22298688, 'steps': 116138, 'loss/train': 0.9312944412231445} 08/31/2021 10:14:05 - INFO - __main__ - Step 116140: {'lr': 6.184540286082103e-05, 'samples': 22298880, 'steps': 116139, 'loss/train': 0.7503232955932617} 08/31/2021 10:14:07 - INFO - __main__ - Step 116141: {'lr': 6.184190864048877e-05, 'samples': 22299072, 'steps': 116140, 'loss/train': 1.208276391029358} 08/31/2021 10:14:08 - INFO - __main__ - Step 116142: {'lr': 6.183841450493763e-05, 'samples': 22299264, 'steps': 116141, 'loss/train': 1.6488406658172607} 08/31/2021 10:14:08 - INFO - __main__ - Step 116143: {'lr': 6.183492045416916e-05, 'samples': 22299456, 'steps': 116142, 'loss/train': 0.7917026877403259} 08/31/2021 10:14:08 - INFO - __main__ - Step 116144: {'lr': 6.183142648818499e-05, 'samples': 22299648, 'steps': 116143, 'loss/train': 1.0268558263778687} 08/31/2021 10:14:09 - INFO - __main__ - Step 116145: {'lr': 6.182793260698666e-05, 'samples': 22299840, 'steps': 116144, 'loss/train': 0.8201634883880615} 08/31/2021 10:14:10 - INFO - __main__ - Step 116146: {'lr': 6.182443881057576e-05, 'samples': 22300032, 'steps': 116145, 'loss/train': 0.367574006319046} 08/31/2021 10:14:11 - INFO - __main__ - Step 116147: {'lr': 6.182094509895386e-05, 'samples': 22300224, 'steps': 116146, 'loss/train': 1.0885027647018433} 08/31/2021 10:14:11 - INFO - __main__ - Step 116148: {'lr': 6.181745147212257e-05, 'samples': 22300416, 'steps': 116147, 'loss/train': 0.6973538398742676} 08/31/2021 10:14:12 - INFO - __main__ - Step 116149: {'lr': 6.18139579300834e-05, 'samples': 22300608, 'steps': 116148, 'loss/train': 1.3407279253005981} 08/31/2021 10:14:12 - INFO - __main__ - Step 116150: {'lr': 6.181046447283798e-05, 'samples': 22300800, 'steps': 116149, 'loss/train': 0.3226463198661804} 08/31/2021 10:14:13 - INFO - __main__ - Step 116151: {'lr': 6.180697110038783e-05, 'samples': 22300992, 'steps': 116150, 'loss/train': 1.285767674446106} 08/31/2021 10:14:14 - INFO - __main__ - Step 116152: {'lr': 6.180347781273457e-05, 'samples': 22301184, 'steps': 116151, 'loss/train': 0.6570825576782227} 08/31/2021 10:14:14 - INFO - __main__ - Step 116153: {'lr': 6.179998460987976e-05, 'samples': 22301376, 'steps': 116152, 'loss/train': 0.25663310289382935} 08/31/2021 10:14:15 - INFO - __main__ - Step 116154: {'lr': 6.179649149182507e-05, 'samples': 22301568, 'steps': 116153, 'loss/train': 0.8597161769866943} 08/31/2021 10:14:15 - INFO - __main__ - Step 116155: {'lr': 6.179299845857186e-05, 'samples': 22301760, 'steps': 116154, 'loss/train': 0.9285849928855896} 08/31/2021 10:14:17 - INFO - __main__ - Step 116156: {'lr': 6.178950551012185e-05, 'samples': 22301952, 'steps': 116155, 'loss/train': 1.430057406425476} 08/31/2021 10:14:17 - INFO - __main__ - Step 116157: {'lr': 6.178601264647659e-05, 'samples': 22302144, 'steps': 116156, 'loss/train': 0.9332978129386902} 08/31/2021 10:14:17 - INFO - __main__ - Step 116158: {'lr': 6.178251986763764e-05, 'samples': 22302336, 'steps': 116157, 'loss/train': 0.9435668587684631} 08/31/2021 10:14:18 - INFO - __main__ - Step 116159: {'lr': 6.177902717360656e-05, 'samples': 22302528, 'steps': 116158, 'loss/train': 0.14449313282966614} 08/31/2021 10:14:18 - INFO - __main__ - Step 116160: {'lr': 6.177553456438498e-05, 'samples': 22302720, 'steps': 116159, 'loss/train': 0.7771835327148438} 08/31/2021 10:14:18 - INFO - __main__ - Step 116161: {'lr': 6.177204203997441e-05, 'samples': 22302912, 'steps': 116160, 'loss/train': 0.9213950634002686} 08/31/2021 10:14:20 - INFO - __main__ - Step 116162: {'lr': 6.176854960037648e-05, 'samples': 22303104, 'steps': 116161, 'loss/train': 1.2684344053268433} 08/31/2021 10:14:20 - INFO - __main__ - Step 116163: {'lr': 6.176505724559272e-05, 'samples': 22303296, 'steps': 116162, 'loss/train': 0.7777934670448303} 08/31/2021 10:14:21 - INFO - __main__ - Step 116164: {'lr': 6.176156497562471e-05, 'samples': 22303488, 'steps': 116163, 'loss/train': 0.6589248776435852} 08/31/2021 10:14:21 - INFO - __main__ - Step 116165: {'lr': 6.175807279047405e-05, 'samples': 22303680, 'steps': 116164, 'loss/train': 1.2491939067840576} 08/31/2021 10:14:21 - INFO - __main__ - Step 116166: {'lr': 6.175458069014231e-05, 'samples': 22303872, 'steps': 116165, 'loss/train': 1.1557159423828125} 08/31/2021 10:14:23 - INFO - __main__ - Step 116167: {'lr': 6.175108867463103e-05, 'samples': 22304064, 'steps': 116166, 'loss/train': 1.3619861602783203} 08/31/2021 10:14:23 - INFO - __main__ - Step 116168: {'lr': 6.17475967439419e-05, 'samples': 22304256, 'steps': 116167, 'loss/train': 0.38713380694389343} 08/31/2021 10:14:24 - INFO - __main__ - Step 116169: {'lr': 6.17441048980763e-05, 'samples': 22304448, 'steps': 116168, 'loss/train': 1.4131730794906616} 08/31/2021 10:14:24 - INFO - __main__ - Step 116170: {'lr': 6.174061313703591e-05, 'samples': 22304640, 'steps': 116169, 'loss/train': 1.3733254671096802} 08/31/2021 10:14:24 - INFO - __main__ - Step 116171: {'lr': 6.17371214608223e-05, 'samples': 22304832, 'steps': 116170, 'loss/train': 1.021324872970581} 08/31/2021 10:14:26 - INFO - __main__ - Step 116172: {'lr': 6.173362986943703e-05, 'samples': 22305024, 'steps': 116171, 'loss/train': 1.2797448635101318} 08/31/2021 10:14:26 - INFO - __main__ - Step 116173: {'lr': 6.173013836288169e-05, 'samples': 22305216, 'steps': 116172, 'loss/train': 0.9345689415931702} 08/31/2021 10:14:27 - INFO - __main__ - Step 116174: {'lr': 6.172664694115782e-05, 'samples': 22305408, 'steps': 116173, 'loss/train': 0.5002519488334656} 08/31/2021 10:14:27 - INFO - __main__ - Step 116175: {'lr': 6.172315560426705e-05, 'samples': 22305600, 'steps': 116174, 'loss/train': 1.1667917966842651} 08/31/2021 10:14:28 - INFO - __main__ - Step 116176: {'lr': 6.171966435221091e-05, 'samples': 22305792, 'steps': 116175, 'loss/train': 1.5453702211380005} 08/31/2021 10:14:29 - INFO - __main__ - Step 116177: {'lr': 6.171617318499098e-05, 'samples': 22305984, 'steps': 116176, 'loss/train': 1.511939287185669} 08/31/2021 10:14:30 - INFO - __main__ - Step 116178: {'lr': 6.171268210260883e-05, 'samples': 22306176, 'steps': 116177, 'loss/train': 0.5853617191314697} 08/31/2021 10:14:30 - INFO - __main__ - Step 116179: {'lr': 6.170919110506606e-05, 'samples': 22306368, 'steps': 116178, 'loss/train': 0.5559381246566772} 08/31/2021 10:14:30 - INFO - __main__ - Step 116180: {'lr': 6.17057001923642e-05, 'samples': 22306560, 'steps': 116179, 'loss/train': 1.1955013275146484} 08/31/2021 10:14:31 - INFO - __main__ - Step 116181: {'lr': 6.170220936450494e-05, 'samples': 22306752, 'steps': 116180, 'loss/train': 1.1263362169265747} 08/31/2021 10:14:32 - INFO - __main__ - Step 116182: {'lr': 6.169871862148968e-05, 'samples': 22306944, 'steps': 116181, 'loss/train': 1.69365656375885} 08/31/2021 10:14:32 - INFO - __main__ - Step 116183: {'lr': 6.169522796332005e-05, 'samples': 22307136, 'steps': 116182, 'loss/train': 1.3612226247787476} 08/31/2021 10:14:33 - INFO - __main__ - Step 116184: {'lr': 6.169173738999767e-05, 'samples': 22307328, 'steps': 116183, 'loss/train': 1.1930474042892456} 08/31/2021 10:14:33 - INFO - __main__ - Step 116185: {'lr': 6.168824690152408e-05, 'samples': 22307520, 'steps': 116184, 'loss/train': 0.8899629712104797} 08/31/2021 10:14:34 - INFO - __main__ - Step 116186: {'lr': 6.168475649790086e-05, 'samples': 22307712, 'steps': 116185, 'loss/train': 1.2943031787872314} 08/31/2021 10:14:34 - INFO - __main__ - Step 116187: {'lr': 6.168126617912958e-05, 'samples': 22307904, 'steps': 116186, 'loss/train': 1.1699374914169312} 08/31/2021 10:14:36 - INFO - __main__ - Step 116188: {'lr': 6.167777594521181e-05, 'samples': 22308096, 'steps': 116187, 'loss/train': 0.689551055431366} 08/31/2021 10:14:36 - INFO - __main__ - Step 116189: {'lr': 6.167428579614915e-05, 'samples': 22308288, 'steps': 116188, 'loss/train': 1.9234812259674072} 08/31/2021 10:14:36 - INFO - __main__ - Step 116190: {'lr': 6.167079573194314e-05, 'samples': 22308480, 'steps': 116189, 'loss/train': 0.6442528963088989} 08/31/2021 10:14:37 - INFO - __main__ - Step 116191: {'lr': 6.166730575259535e-05, 'samples': 22308672, 'steps': 116190, 'loss/train': 2.1183743476867676} 08/31/2021 10:14:37 - INFO - __main__ - Step 116192: {'lr': 6.166381585810737e-05, 'samples': 22308864, 'steps': 116191, 'loss/train': 0.7948312163352966} 08/31/2021 10:14:39 - INFO - __main__ - Step 116193: {'lr': 6.166032604848079e-05, 'samples': 22309056, 'steps': 116192, 'loss/train': 1.3361879587173462} 08/31/2021 10:14:40 - INFO - __main__ - Step 116194: {'lr': 6.165683632371716e-05, 'samples': 22309248, 'steps': 116193, 'loss/train': 0.8494647741317749} 08/31/2021 10:14:40 - INFO - __main__ - Step 116195: {'lr': 6.165334668381812e-05, 'samples': 22309440, 'steps': 116194, 'loss/train': 1.0704489946365356} 08/31/2021 10:14:41 - INFO - __main__ - Step 116196: {'lr': 6.164985712878507e-05, 'samples': 22309632, 'steps': 116195, 'loss/train': 0.7511624693870544} 08/31/2021 10:14:41 - INFO - __main__ - Step 116197: {'lr': 6.164636765861972e-05, 'samples': 22309824, 'steps': 116196, 'loss/train': 1.1318001747131348} 08/31/2021 10:14:41 - INFO - __main__ - Step 116198: {'lr': 6.16428782733236e-05, 'samples': 22310016, 'steps': 116197, 'loss/train': 1.1737759113311768} 08/31/2021 10:14:43 - INFO - __main__ - Step 116199: {'lr': 6.163938897289831e-05, 'samples': 22310208, 'steps': 116198, 'loss/train': 1.5049790143966675} 08/31/2021 10:14:43 - INFO - __main__ - Step 116200: {'lr': 6.163589975734537e-05, 'samples': 22310400, 'steps': 116199, 'loss/train': 1.2256625890731812} 08/31/2021 10:14:44 - INFO - __main__ - Step 116201: {'lr': 6.163241062666641e-05, 'samples': 22310592, 'steps': 116200, 'loss/train': 1.2215416431427002} 08/31/2021 10:14:44 - INFO - __main__ - Step 116202: {'lr': 6.162892158086297e-05, 'samples': 22310784, 'steps': 116201, 'loss/train': 1.2670289278030396} 08/31/2021 10:14:44 - INFO - __main__ - Step 116203: {'lr': 6.162543261993664e-05, 'samples': 22310976, 'steps': 116202, 'loss/train': 1.7889350652694702} 08/31/2021 10:14:46 - INFO - __main__ - Step 116204: {'lr': 6.1621943743889e-05, 'samples': 22311168, 'steps': 116203, 'loss/train': 1.5938446521759033} 08/31/2021 10:14:46 - INFO - __main__ - Step 116205: {'lr': 6.161845495272159e-05, 'samples': 22311360, 'steps': 116204, 'loss/train': 0.6759538054466248} 08/31/2021 10:14:47 - INFO - __main__ - Step 116206: {'lr': 6.161496624643598e-05, 'samples': 22311552, 'steps': 116205, 'loss/train': 0.975875198841095} 08/31/2021 10:14:47 - INFO - __main__ - Step 116207: {'lr': 6.161147762503378e-05, 'samples': 22311744, 'steps': 116206, 'loss/train': 1.086842656135559} 08/31/2021 10:14:48 - INFO - __main__ - Step 116208: {'lr': 6.160798908851658e-05, 'samples': 22311936, 'steps': 116207, 'loss/train': 1.7994539737701416} 08/31/2021 10:14:49 - INFO - __main__ - Step 116209: {'lr': 6.160450063688589e-05, 'samples': 22312128, 'steps': 116208, 'loss/train': 0.02885540947318077} 08/31/2021 10:14:49 - INFO - __main__ - Step 116210: {'lr': 6.160101227014328e-05, 'samples': 22312320, 'steps': 116209, 'loss/train': 0.622850239276886} 08/31/2021 10:14:50 - INFO - __main__ - Step 116211: {'lr': 6.159752398829035e-05, 'samples': 22312512, 'steps': 116210, 'loss/train': 1.232391357421875} 08/31/2021 10:14:50 - INFO - __main__ - Step 116212: {'lr': 6.159403579132866e-05, 'samples': 22312704, 'steps': 116211, 'loss/train': 0.8244982361793518} 08/31/2021 10:14:50 - INFO - __main__ - Step 116213: {'lr': 6.159054767925978e-05, 'samples': 22312896, 'steps': 116212, 'loss/train': 1.6332788467407227} 08/31/2021 10:14:52 - INFO - __main__ - Step 116214: {'lr': 6.158705965208533e-05, 'samples': 22313088, 'steps': 116213, 'loss/train': 1.0424944162368774} 08/31/2021 10:14:52 - INFO - __main__ - Step 116215: {'lr': 6.158357170980683e-05, 'samples': 22313280, 'steps': 116214, 'loss/train': 1.0124952793121338} 08/31/2021 10:14:53 - INFO - __main__ - Step 116216: {'lr': 6.158008385242583e-05, 'samples': 22313472, 'steps': 116215, 'loss/train': 1.1552046537399292} 08/31/2021 10:14:53 - INFO - __main__ - Step 116217: {'lr': 6.157659607994398e-05, 'samples': 22313664, 'steps': 116216, 'loss/train': 1.6634162664413452} 08/31/2021 10:14:53 - INFO - __main__ - Step 116218: {'lr': 6.15731083923628e-05, 'samples': 22313856, 'steps': 116217, 'loss/train': 1.2395633459091187} 08/31/2021 10:14:54 - INFO - __main__ - Step 116219: {'lr': 6.156962078968387e-05, 'samples': 22314048, 'steps': 116218, 'loss/train': 0.7150027751922607} 08/31/2021 10:14:55 - INFO - __main__ - Step 116220: {'lr': 6.156613327190874e-05, 'samples': 22314240, 'steps': 116219, 'loss/train': 0.6859223246574402} 08/31/2021 10:14:56 - INFO - __main__ - Step 116221: {'lr': 6.1562645839039e-05, 'samples': 22314432, 'steps': 116220, 'loss/train': 1.0056984424591064} 08/31/2021 10:14:56 - INFO - __main__ - Step 116222: {'lr': 6.155915849107633e-05, 'samples': 22314624, 'steps': 116221, 'loss/train': 0.9738432765007019} 08/31/2021 10:14:56 - INFO - __main__ - Step 116223: {'lr': 6.155567122802211e-05, 'samples': 22314816, 'steps': 116222, 'loss/train': 0.7865509986877441} 08/31/2021 10:14:57 - INFO - __main__ - Step 116224: {'lr': 6.155218404987797e-05, 'samples': 22315008, 'steps': 116223, 'loss/train': 0.9897669553756714} 08/31/2021 10:14:58 - INFO - __main__ - Step 116225: {'lr': 6.154869695664555e-05, 'samples': 22315200, 'steps': 116224, 'loss/train': 1.361928105354309} 08/31/2021 10:14:59 - INFO - __main__ - Step 116226: {'lr': 6.154520994832635e-05, 'samples': 22315392, 'steps': 116225, 'loss/train': 1.4392741918563843} 08/31/2021 10:14:59 - INFO - __main__ - Step 116227: {'lr': 6.154172302492197e-05, 'samples': 22315584, 'steps': 116226, 'loss/train': 1.1899443864822388} 08/31/2021 10:15:00 - INFO - __main__ - Step 116228: {'lr': 6.153823618643401e-05, 'samples': 22315776, 'steps': 116227, 'loss/train': 1.1629592180252075} 08/31/2021 10:15:00 - INFO - __main__ - Step 116229: {'lr': 6.153474943286399e-05, 'samples': 22315968, 'steps': 116228, 'loss/train': 0.7218201160430908} 08/31/2021 10:15:03 - INFO - __main__ - Step 116230: {'lr': 6.153126276421351e-05, 'samples': 22316160, 'steps': 116229, 'loss/train': 1.3562580347061157} 08/31/2021 10:15:03 - INFO - __main__ - Step 116231: {'lr': 6.152777618048414e-05, 'samples': 22316352, 'steps': 116230, 'loss/train': 1.0444886684417725} 08/31/2021 10:15:04 - INFO - __main__ - Step 116232: {'lr': 6.152428968167742e-05, 'samples': 22316544, 'steps': 116231, 'loss/train': 0.5568712949752808} 08/31/2021 10:15:04 - INFO - __main__ - Step 116233: {'lr': 6.152080326779497e-05, 'samples': 22316736, 'steps': 116232, 'loss/train': 0.7512208819389343} 08/31/2021 10:15:04 - INFO - __main__ - Step 116234: {'lr': 6.151731693883833e-05, 'samples': 22316928, 'steps': 116233, 'loss/train': 0.3336794078350067} 08/31/2021 10:15:05 - INFO - __main__ - Step 116235: {'lr': 6.151383069480914e-05, 'samples': 22317120, 'steps': 116234, 'loss/train': 0.6064491271972656} 08/31/2021 10:15:05 - INFO - __main__ - Step 116236: {'lr': 6.151034453570887e-05, 'samples': 22317312, 'steps': 116235, 'loss/train': 0.26592668890953064} 08/31/2021 10:15:05 - INFO - __main__ - Step 116237: {'lr': 6.150685846153911e-05, 'samples': 22317504, 'steps': 116236, 'loss/train': 0.26353564858436584} 08/31/2021 10:15:07 - INFO - __main__ - Step 116238: {'lr': 6.150337247230145e-05, 'samples': 22317696, 'steps': 116237, 'loss/train': 0.25619757175445557} 08/31/2021 10:15:07 - INFO - __main__ - Step 116239: {'lr': 6.149988656799746e-05, 'samples': 22317888, 'steps': 116238, 'loss/train': 1.7626076936721802} 08/31/2021 10:15:08 - INFO - __main__ - Step 116240: {'lr': 6.149640074862872e-05, 'samples': 22318080, 'steps': 116239, 'loss/train': 1.2389860153198242} 08/31/2021 10:15:08 - INFO - __main__ - Step 116241: {'lr': 6.149291501419679e-05, 'samples': 22318272, 'steps': 116240, 'loss/train': 0.8333724141120911} 08/31/2021 10:15:08 - INFO - __main__ - Step 116242: {'lr': 6.148942936470325e-05, 'samples': 22318464, 'steps': 116241, 'loss/train': 1.9314234256744385} 08/31/2021 10:15:10 - INFO - __main__ - Step 116243: {'lr': 6.148594380014966e-05, 'samples': 22318656, 'steps': 116242, 'loss/train': 1.5916999578475952} 08/31/2021 10:15:10 - INFO - __main__ - Step 116244: {'lr': 6.148245832053759e-05, 'samples': 22318848, 'steps': 116243, 'loss/train': 1.0875741243362427} 08/31/2021 10:15:11 - INFO - __main__ - Step 116245: {'lr': 6.14789729258686e-05, 'samples': 22319040, 'steps': 116244, 'loss/train': 1.081192970275879} 08/31/2021 10:15:11 - INFO - __main__ - Step 116246: {'lr': 6.14754876161443e-05, 'samples': 22319232, 'steps': 116245, 'loss/train': 1.1135597229003906} 08/31/2021 10:15:11 - INFO - __main__ - Step 116247: {'lr': 6.147200239136622e-05, 'samples': 22319424, 'steps': 116246, 'loss/train': 1.4030280113220215} 08/31/2021 10:15:13 - INFO - __main__ - Step 116248: {'lr': 6.146851725153604e-05, 'samples': 22319616, 'steps': 116247, 'loss/train': 0.9517082571983337} 08/31/2021 10:15:14 - INFO - __main__ - Step 116249: {'lr': 6.146503219665514e-05, 'samples': 22319808, 'steps': 116248, 'loss/train': 1.1210201978683472} 08/31/2021 10:15:14 - INFO - __main__ - Step 116250: {'lr': 6.14615472267252e-05, 'samples': 22320000, 'steps': 116249, 'loss/train': 0.8822740912437439} 08/31/2021 10:15:15 - INFO - __main__ - Step 116251: {'lr': 6.145806234174778e-05, 'samples': 22320192, 'steps': 116250, 'loss/train': 1.2767058610916138} 08/31/2021 10:15:15 - INFO - __main__ - Step 116252: {'lr': 6.145457754172446e-05, 'samples': 22320384, 'steps': 116251, 'loss/train': 1.7248778343200684} 08/31/2021 10:15:17 - INFO - __main__ - Step 116253: {'lr': 6.145109282665675e-05, 'samples': 22320576, 'steps': 116252, 'loss/train': 1.524694561958313} 08/31/2021 10:15:17 - INFO - __main__ - Step 116254: {'lr': 6.144760819654632e-05, 'samples': 22320768, 'steps': 116253, 'loss/train': 0.3260039985179901} 08/31/2021 10:15:18 - INFO - __main__ - Step 116255: {'lr': 6.144412365139468e-05, 'samples': 22320960, 'steps': 116254, 'loss/train': 1.0229929685592651} 08/31/2021 10:15:18 - INFO - __main__ - Step 116256: {'lr': 6.144063919120338e-05, 'samples': 22321152, 'steps': 116255, 'loss/train': 0.7939337491989136} 08/31/2021 10:15:18 - INFO - __main__ - Step 116257: {'lr': 6.143715481597403e-05, 'samples': 22321344, 'steps': 116256, 'loss/train': 0.7907591462135315} 08/31/2021 10:15:19 - INFO - __main__ - Step 116258: {'lr': 6.143367052570819e-05, 'samples': 22321536, 'steps': 116257, 'loss/train': 0.37605687975883484} 08/31/2021 10:15:20 - INFO - __main__ - Step 116259: {'lr': 6.143018632040745e-05, 'samples': 22321728, 'steps': 116258, 'loss/train': 0.8773487210273743} 08/31/2021 10:15:21 - INFO - __main__ - Step 116260: {'lr': 6.142670220007335e-05, 'samples': 22321920, 'steps': 116259, 'loss/train': 1.179632544517517} 08/31/2021 10:15:21 - INFO - __main__ - Step 116261: {'lr': 6.142321816470745e-05, 'samples': 22322112, 'steps': 116260, 'loss/train': 1.3015875816345215} 08/31/2021 10:15:22 - INFO - __main__ - Step 116262: {'lr': 6.141973421431141e-05, 'samples': 22322304, 'steps': 116261, 'loss/train': 0.9392455220222473} 08/31/2021 10:15:22 - INFO - __main__ - Step 116263: {'lr': 6.141625034888668e-05, 'samples': 22322496, 'steps': 116262, 'loss/train': 1.6883991956710815} 08/31/2021 10:15:23 - INFO - __main__ - Step 116264: {'lr': 6.141276656843484e-05, 'samples': 22322688, 'steps': 116263, 'loss/train': 1.053975224494934} 08/31/2021 10:15:24 - INFO - __main__ - Step 116265: {'lr': 6.140928287295753e-05, 'samples': 22322880, 'steps': 116264, 'loss/train': 0.846824049949646} 08/31/2021 10:15:24 - INFO - __main__ - Step 116266: {'lr': 6.140579926245627e-05, 'samples': 22323072, 'steps': 116265, 'loss/train': 1.3101787567138672} 08/31/2021 10:15:25 - INFO - __main__ - Step 116267: {'lr': 6.140231573693267e-05, 'samples': 22323264, 'steps': 116266, 'loss/train': 0.03984003886580467} 08/31/2021 10:15:25 - INFO - __main__ - Step 116268: {'lr': 6.139883229638823e-05, 'samples': 22323456, 'steps': 116267, 'loss/train': 1.3220820426940918} 08/31/2021 10:15:27 - INFO - __main__ - Step 116269: {'lr': 6.13953489408246e-05, 'samples': 22323648, 'steps': 116268, 'loss/train': 1.0026450157165527} 08/31/2021 10:15:27 - INFO - __main__ - Step 116270: {'lr': 6.139186567024333e-05, 'samples': 22323840, 'steps': 116269, 'loss/train': 0.9225929975509644} 08/31/2021 10:15:27 - INFO - __main__ - Step 116271: {'lr': 6.138838248464595e-05, 'samples': 22324032, 'steps': 116270, 'loss/train': 0.9351816773414612} 08/31/2021 10:15:28 - INFO - __main__ - Step 116272: {'lr': 6.138489938403405e-05, 'samples': 22324224, 'steps': 116271, 'loss/train': 1.3872908353805542} 08/31/2021 10:15:28 - INFO - __main__ - Step 116273: {'lr': 6.138141636840922e-05, 'samples': 22324416, 'steps': 116272, 'loss/train': 0.9598660469055176} 08/31/2021 10:15:29 - INFO - __main__ - Step 116274: {'lr': 6.1377933437773e-05, 'samples': 22324608, 'steps': 116273, 'loss/train': 1.1147829294204712} 08/31/2021 10:15:30 - INFO - __main__ - Step 116275: {'lr': 6.137445059212707e-05, 'samples': 22324800, 'steps': 116274, 'loss/train': 1.0497411489486694} 08/31/2021 10:15:30 - INFO - __main__ - Step 116276: {'lr': 6.13709678314728e-05, 'samples': 22324992, 'steps': 116275, 'loss/train': 0.8300818800926208} 08/31/2021 10:15:31 - INFO - __main__ - Step 116277: {'lr': 6.136748515581187e-05, 'samples': 22325184, 'steps': 116276, 'loss/train': 0.31530988216400146} 08/31/2021 10:15:31 - INFO - __main__ - Step 116278: {'lr': 6.136400256514585e-05, 'samples': 22325376, 'steps': 116277, 'loss/train': 1.449142575263977} 08/31/2021 10:15:33 - INFO - __main__ - Step 116279: {'lr': 6.136052005947629e-05, 'samples': 22325568, 'steps': 116278, 'loss/train': 1.519288420677185} 08/31/2021 10:15:33 - INFO - __main__ - Step 116280: {'lr': 6.135703763880477e-05, 'samples': 22325760, 'steps': 116279, 'loss/train': 0.4139383137226105} 08/31/2021 10:15:33 - INFO - __main__ - Step 116281: {'lr': 6.135355530313286e-05, 'samples': 22325952, 'steps': 116280, 'loss/train': 1.2433717250823975} 08/31/2021 10:15:34 - INFO - __main__ - Step 116282: {'lr': 6.135007305246212e-05, 'samples': 22326144, 'steps': 116281, 'loss/train': 0.597276508808136} 08/31/2021 10:15:34 - INFO - __main__ - Step 116283: {'lr': 6.134659088679412e-05, 'samples': 22326336, 'steps': 116282, 'loss/train': 1.119673252105713} 08/31/2021 10:15:36 - INFO - __main__ - Step 116284: {'lr': 6.134310880613045e-05, 'samples': 22326528, 'steps': 116283, 'loss/train': 1.4251255989074707} 08/31/2021 10:15:36 - INFO - __main__ - Step 116285: {'lr': 6.133962681047267e-05, 'samples': 22326720, 'steps': 116284, 'loss/train': 1.2371190786361694} 08/31/2021 10:15:37 - INFO - __main__ - Step 116286: {'lr': 6.133614489982234e-05, 'samples': 22326912, 'steps': 116285, 'loss/train': 1.1270114183425903} 08/31/2021 10:15:37 - INFO - __main__ - Step 116287: {'lr': 6.1332663074181e-05, 'samples': 22327104, 'steps': 116286, 'loss/train': 0.9864546656608582} 08/31/2021 10:15:37 - INFO - __main__ - Step 116288: {'lr': 6.132918133355029e-05, 'samples': 22327296, 'steps': 116287, 'loss/train': 1.608089804649353} 08/31/2021 10:15:38 - INFO - __main__ - Step 116289: {'lr': 6.13256996779318e-05, 'samples': 22327488, 'steps': 116288, 'loss/train': 0.74683678150177} 08/31/2021 10:15:39 - INFO - __main__ - Step 116290: {'lr': 6.132221810732697e-05, 'samples': 22327680, 'steps': 116289, 'loss/train': 1.218740463256836} 08/31/2021 10:15:40 - INFO - __main__ - Step 116291: {'lr': 6.131873662173743e-05, 'samples': 22327872, 'steps': 116290, 'loss/train': 1.3312714099884033} 08/31/2021 10:15:40 - INFO - __main__ - Step 116292: {'lr': 6.131525522116476e-05, 'samples': 22328064, 'steps': 116291, 'loss/train': 0.28054219484329224} 08/31/2021 10:15:40 - INFO - __main__ - Step 116293: {'lr': 6.131177390561052e-05, 'samples': 22328256, 'steps': 116292, 'loss/train': 1.487789273262024} 08/31/2021 10:15:41 - INFO - __main__ - Step 116294: {'lr': 6.130829267507629e-05, 'samples': 22328448, 'steps': 116293, 'loss/train': 1.0400291681289673} 08/31/2021 10:15:42 - INFO - __main__ - Step 116295: {'lr': 6.130481152956364e-05, 'samples': 22328640, 'steps': 116294, 'loss/train': 0.13185416162014008} 08/31/2021 10:15:43 - INFO - __main__ - Step 116296: {'lr': 6.13013304690741e-05, 'samples': 22328832, 'steps': 116295, 'loss/train': 0.5285756587982178} 08/31/2021 10:15:43 - INFO - __main__ - Step 116297: {'lr': 6.129784949360928e-05, 'samples': 22329024, 'steps': 116296, 'loss/train': 0.9765022993087769} 08/31/2021 10:15:44 - INFO - __main__ - Step 116298: {'lr': 6.129436860317076e-05, 'samples': 22329216, 'steps': 116297, 'loss/train': 0.8113064169883728} 08/31/2021 10:15:44 - INFO - __main__ - Step 116299: {'lr': 6.129088779776005e-05, 'samples': 22329408, 'steps': 116298, 'loss/train': 1.9971617460250854} 08/31/2021 10:15:45 - INFO - __main__ - Step 116300: {'lr': 6.128740707737876e-05, 'samples': 22329600, 'steps': 116299, 'loss/train': 1.5637904405593872} 08/31/2021 10:15:46 - INFO - __main__ - Step 116301: {'lr': 6.128392644202848e-05, 'samples': 22329792, 'steps': 116300, 'loss/train': 1.344469666481018} 08/31/2021 10:15:46 - INFO - __main__ - Step 116302: {'lr': 6.128044589171081e-05, 'samples': 22329984, 'steps': 116301, 'loss/train': 1.5275275707244873} 08/31/2021 10:15:47 - INFO - __main__ - Step 116303: {'lr': 6.127696542642718e-05, 'samples': 22330176, 'steps': 116302, 'loss/train': 1.8216136693954468} 08/31/2021 10:15:47 - INFO - __main__ - Step 116304: {'lr': 6.127348504617924e-05, 'samples': 22330368, 'steps': 116303, 'loss/train': 1.1748839616775513} 08/31/2021 10:15:49 - INFO - __main__ - Step 116305: {'lr': 6.127000475096855e-05, 'samples': 22330560, 'steps': 116304, 'loss/train': 0.3806113004684448} 08/31/2021 10:15:49 - INFO - __main__ - Step 116306: {'lr': 6.126652454079671e-05, 'samples': 22330752, 'steps': 116305, 'loss/train': 1.092443823814392} 08/31/2021 10:15:50 - INFO - __main__ - Step 116307: {'lr': 6.126304441566521e-05, 'samples': 22330944, 'steps': 116306, 'loss/train': 0.7692380547523499} 08/31/2021 10:15:50 - INFO - __main__ - Step 116308: {'lr': 6.125956437557572e-05, 'samples': 22331136, 'steps': 116307, 'loss/train': 2.0640997886657715} 08/31/2021 10:15:50 - INFO - __main__ - Step 116309: {'lr': 6.125608442052974e-05, 'samples': 22331328, 'steps': 116308, 'loss/train': 0.664469838142395} 08/31/2021 10:15:51 - INFO - __main__ - Step 116310: {'lr': 6.125260455052886e-05, 'samples': 22331520, 'steps': 116309, 'loss/train': 0.9097222089767456} 08/31/2021 10:15:52 - INFO - __main__ - Step 116311: {'lr': 6.124912476557462e-05, 'samples': 22331712, 'steps': 116310, 'loss/train': 1.4865508079528809} 08/31/2021 10:15:53 - INFO - __main__ - Step 116312: {'lr': 6.124564506566866e-05, 'samples': 22331904, 'steps': 116311, 'loss/train': 1.1296495199203491} 08/31/2021 10:15:53 - INFO - __main__ - Step 116313: {'lr': 6.124216545081245e-05, 'samples': 22332096, 'steps': 116312, 'loss/train': 1.168228268623352} 08/31/2021 10:15:53 - INFO - __main__ - Step 116314: {'lr': 6.123868592100761e-05, 'samples': 22332288, 'steps': 116313, 'loss/train': 1.3484253883361816} 08/31/2021 10:15:54 - INFO - __main__ - Step 116315: {'lr': 6.123520647625575e-05, 'samples': 22332480, 'steps': 116314, 'loss/train': 0.12156780064105988} 08/31/2021 10:15:56 - INFO - __main__ - Step 116316: {'lr': 6.123172711655845e-05, 'samples': 22332672, 'steps': 116315, 'loss/train': 1.7610244750976562} 08/31/2021 10:15:57 - INFO - __main__ - Step 116317: {'lr': 6.122824784191713e-05, 'samples': 22332864, 'steps': 116316, 'loss/train': 0.3415153920650482} 08/31/2021 10:15:57 - INFO - __main__ - Step 116318: {'lr': 6.122476865233346e-05, 'samples': 22333056, 'steps': 116317, 'loss/train': 0.3071853518486023} 08/31/2021 10:15:57 - INFO - __main__ - Step 116319: {'lr': 6.122128954780898e-05, 'samples': 22333248, 'steps': 116318, 'loss/train': 0.27669283747673035} 08/31/2021 10:15:58 - INFO - __main__ - Step 116320: {'lr': 6.12178105283453e-05, 'samples': 22333440, 'steps': 116319, 'loss/train': 1.1777492761611938} 08/31/2021 10:15:58 - INFO - __main__ - Step 116321: {'lr': 6.121433159394394e-05, 'samples': 22333632, 'steps': 116320, 'loss/train': 0.4842787981033325} 08/31/2021 10:16:00 - INFO - __main__ - Step 116322: {'lr': 6.12108527446065e-05, 'samples': 22333824, 'steps': 116321, 'loss/train': 1.3533519506454468} 08/31/2021 10:16:00 - INFO - __main__ - Step 116323: {'lr': 6.120737398033452e-05, 'samples': 22334016, 'steps': 116322, 'loss/train': 0.8181985020637512} 08/31/2021 10:16:00 - INFO - __main__ - Step 116324: {'lr': 6.120389530112961e-05, 'samples': 22334208, 'steps': 116323, 'loss/train': 1.053289532661438} 08/31/2021 10:16:01 - INFO - __main__ - Step 116325: {'lr': 6.120041670699328e-05, 'samples': 22334400, 'steps': 116324, 'loss/train': 0.9170711040496826} 08/31/2021 10:16:01 - INFO - __main__ - Step 116326: {'lr': 6.119693819792716e-05, 'samples': 22334592, 'steps': 116325, 'loss/train': 0.9406210780143738} 08/31/2021 10:16:01 - INFO - __main__ - Step 116327: {'lr': 6.119345977393276e-05, 'samples': 22334784, 'steps': 116326, 'loss/train': 1.3926817178726196} 08/31/2021 10:16:03 - INFO - __main__ - Step 116328: {'lr': 6.118998143501178e-05, 'samples': 22334976, 'steps': 116327, 'loss/train': 1.3974779844284058} 08/31/2021 10:16:03 - INFO - __main__ - Step 116329: {'lr': 6.118650318116559e-05, 'samples': 22335168, 'steps': 116328, 'loss/train': 2.400118350982666} 08/31/2021 10:16:04 - INFO - __main__ - Step 116330: {'lr': 6.118302501239584e-05, 'samples': 22335360, 'steps': 116329, 'loss/train': 0.3307897746562958} 08/31/2021 10:16:04 - INFO - __main__ - Step 116331: {'lr': 6.117954692870411e-05, 'samples': 22335552, 'steps': 116330, 'loss/train': 1.2254984378814697} 08/31/2021 10:16:04 - INFO - __main__ - Step 116332: {'lr': 6.117606893009195e-05, 'samples': 22335744, 'steps': 116331, 'loss/train': 0.3345589339733124} 08/31/2021 10:16:06 - INFO - __main__ - Step 116333: {'lr': 6.117259101656097e-05, 'samples': 22335936, 'steps': 116332, 'loss/train': 1.1740117073059082} 08/31/2021 10:16:06 - INFO - __main__ - Step 116334: {'lr': 6.116911318811269e-05, 'samples': 22336128, 'steps': 116333, 'loss/train': 1.1636178493499756} 08/31/2021 10:16:07 - INFO - __main__ - Step 116335: {'lr': 6.116563544474867e-05, 'samples': 22336320, 'steps': 116334, 'loss/train': 1.566717505455017} 08/31/2021 10:16:07 - INFO - __main__ - Step 116336: {'lr': 6.116215778647056e-05, 'samples': 22336512, 'steps': 116335, 'loss/train': 0.8701104521751404} 08/31/2021 10:16:07 - INFO - __main__ - Step 116337: {'lr': 6.11586802132798e-05, 'samples': 22336704, 'steps': 116336, 'loss/train': 1.0587949752807617} 08/31/2021 10:16:09 - INFO - __main__ - Step 116338: {'lr': 6.115520272517808e-05, 'samples': 22336896, 'steps': 116337, 'loss/train': 1.1743963956832886} 08/31/2021 10:16:09 - INFO - __main__ - Step 116339: {'lr': 6.115172532216695e-05, 'samples': 22337088, 'steps': 116338, 'loss/train': 0.13350771367549896} 08/31/2021 10:16:10 - INFO - __main__ - Step 116340: {'lr': 6.11482480042479e-05, 'samples': 22337280, 'steps': 116339, 'loss/train': 1.0342475175857544} 08/31/2021 10:16:10 - INFO - __main__ - Step 116341: {'lr': 6.11447707714225e-05, 'samples': 22337472, 'steps': 116340, 'loss/train': 1.8532352447509766} 08/31/2021 10:16:10 - INFO - __main__ - Step 116342: {'lr': 6.114129362369237e-05, 'samples': 22337664, 'steps': 116341, 'loss/train': 1.073806881904602} 08/31/2021 10:16:12 - INFO - __main__ - Step 116343: {'lr': 6.113781656105904e-05, 'samples': 22337856, 'steps': 116342, 'loss/train': 0.8369088172912598} 08/31/2021 10:16:12 - INFO - __main__ - Step 116344: {'lr': 6.113433958352413e-05, 'samples': 22338048, 'steps': 116343, 'loss/train': 1.3137701749801636} 08/31/2021 10:16:13 - INFO - __main__ - Step 116345: {'lr': 6.113086269108914e-05, 'samples': 22338240, 'steps': 116344, 'loss/train': 0.621648371219635} 08/31/2021 10:16:13 - INFO - __main__ - Step 116346: {'lr': 6.11273858837557e-05, 'samples': 22338432, 'steps': 116345, 'loss/train': 0.5537724494934082} 08/31/2021 10:16:13 - INFO - __main__ - Step 116347: {'lr': 6.11239091615253e-05, 'samples': 22338624, 'steps': 116346, 'loss/train': 1.2216272354125977} 08/31/2021 10:16:15 - INFO - __main__ - Step 116348: {'lr': 6.112043252439958e-05, 'samples': 22338816, 'steps': 116347, 'loss/train': 1.5675872564315796} 08/31/2021 10:16:15 - INFO - __main__ - Step 116349: {'lr': 6.111695597238006e-05, 'samples': 22339008, 'steps': 116348, 'loss/train': 1.1901413202285767} 08/31/2021 10:16:16 - INFO - __main__ - Step 116350: {'lr': 6.111347950546845e-05, 'samples': 22339200, 'steps': 116349, 'loss/train': 0.4019269347190857} 08/31/2021 10:16:16 - INFO - __main__ - Step 116351: {'lr': 6.111000312366607e-05, 'samples': 22339392, 'steps': 116350, 'loss/train': 0.8316166400909424} 08/31/2021 10:16:16 - INFO - __main__ - Step 116352: {'lr': 6.110652682697462e-05, 'samples': 22339584, 'steps': 116351, 'loss/train': 1.1067384481430054} 08/31/2021 10:16:17 - INFO - __main__ - Step 116353: {'lr': 6.110305061539565e-05, 'samples': 22339776, 'steps': 116352, 'loss/train': 0.6714032888412476} 08/31/2021 10:16:18 - INFO - __main__ - Step 116354: {'lr': 6.109957448893074e-05, 'samples': 22339968, 'steps': 116353, 'loss/train': 0.44930097460746765} 08/31/2021 10:16:19 - INFO - __main__ - Step 116355: {'lr': 6.109609844758144e-05, 'samples': 22340160, 'steps': 116354, 'loss/train': 1.0835055112838745} 08/31/2021 10:16:19 - INFO - __main__ - Step 116356: {'lr': 6.109262249134931e-05, 'samples': 22340352, 'steps': 116355, 'loss/train': 1.1922119855880737} 08/31/2021 10:16:19 - INFO - __main__ - Step 116357: {'lr': 6.108914662023596e-05, 'samples': 22340544, 'steps': 116356, 'loss/train': 0.4147745668888092} 08/31/2021 10:16:20 - INFO - __main__ - Step 116358: {'lr': 6.108567083424291e-05, 'samples': 22340736, 'steps': 116357, 'loss/train': 0.7742075324058533} 08/31/2021 10:16:22 - INFO - __main__ - Step 116359: {'lr': 6.108219513337174e-05, 'samples': 22340928, 'steps': 116358, 'loss/train': 1.2904222011566162} 08/31/2021 10:16:22 - INFO - __main__ - Step 116360: {'lr': 6.1078719517624e-05, 'samples': 22341120, 'steps': 116359, 'loss/train': 1.1824325323104858} 08/31/2021 10:16:23 - INFO - __main__ - Step 116361: {'lr': 6.107524398700137e-05, 'samples': 22341312, 'steps': 116360, 'loss/train': 1.6838061809539795} 08/31/2021 10:16:23 - INFO - __main__ - Step 116362: {'lr': 6.107176854150526e-05, 'samples': 22341504, 'steps': 116361, 'loss/train': 1.051827311515808} 08/31/2021 10:16:23 - INFO - __main__ - Step 116363: {'lr': 6.106829318113726e-05, 'samples': 22341696, 'steps': 116362, 'loss/train': 1.2445247173309326} 08/31/2021 10:16:24 - INFO - __main__ - Step 116364: {'lr': 6.106481790589901e-05, 'samples': 22341888, 'steps': 116363, 'loss/train': 5.7014288902282715} 08/31/2021 10:16:25 - INFO - __main__ - Step 116365: {'lr': 6.1061342715792e-05, 'samples': 22342080, 'steps': 116364, 'loss/train': 0.8543714880943298} 08/31/2021 10:16:26 - INFO - __main__ - Step 116366: {'lr': 6.105786761081786e-05, 'samples': 22342272, 'steps': 116365, 'loss/train': 0.7777320146560669} 08/31/2021 10:16:26 - INFO - __main__ - Step 116367: {'lr': 6.105439259097812e-05, 'samples': 22342464, 'steps': 116366, 'loss/train': 1.0279783010482788} 08/31/2021 10:16:26 - INFO - __main__ - Step 116368: {'lr': 6.105091765627435e-05, 'samples': 22342656, 'steps': 116367, 'loss/train': 1.4504189491271973} 08/31/2021 10:16:27 - INFO - __main__ - Step 116369: {'lr': 6.104744280670813e-05, 'samples': 22342848, 'steps': 116368, 'loss/train': 1.1071661710739136} 08/31/2021 10:16:29 - INFO - __main__ - Step 116370: {'lr': 6.104396804228101e-05, 'samples': 22343040, 'steps': 116369, 'loss/train': 0.2808544933795929} 08/31/2021 10:16:29 - INFO - __main__ - Step 116371: {'lr': 6.104049336299458e-05, 'samples': 22343232, 'steps': 116370, 'loss/train': 1.4125933647155762} 08/31/2021 10:16:29 - INFO - __main__ - Step 116372: {'lr': 6.103701876885043e-05, 'samples': 22343424, 'steps': 116371, 'loss/train': 1.710624098777771} 08/31/2021 10:16:30 - INFO - __main__ - Step 116373: {'lr': 6.103354425985003e-05, 'samples': 22343616, 'steps': 116372, 'loss/train': 0.03489387407898903} 08/31/2021 10:16:30 - INFO - __main__ - Step 116374: {'lr': 6.1030069835995016e-05, 'samples': 22343808, 'steps': 116373, 'loss/train': 1.0831600427627563} 08/31/2021 10:16:31 - INFO - __main__ - Step 116375: {'lr': 6.10265954972869e-05, 'samples': 22344000, 'steps': 116374, 'loss/train': 0.934048056602478} 08/31/2021 10:16:32 - INFO - __main__ - Step 116376: {'lr': 6.1023121243727306e-05, 'samples': 22344192, 'steps': 116375, 'loss/train': 1.3931187391281128} 08/31/2021 10:16:32 - INFO - __main__ - Step 116377: {'lr': 6.1019647075317766e-05, 'samples': 22344384, 'steps': 116376, 'loss/train': 0.9626544117927551} 08/31/2021 10:16:33 - INFO - __main__ - Step 116378: {'lr': 6.101617299205986e-05, 'samples': 22344576, 'steps': 116377, 'loss/train': 0.25525176525115967} 08/31/2021 10:16:33 - INFO - __main__ - Step 116379: {'lr': 6.101269899395514e-05, 'samples': 22344768, 'steps': 116378, 'loss/train': 1.290961742401123} 08/31/2021 10:16:35 - INFO - __main__ - Step 116380: {'lr': 6.1009225081005203e-05, 'samples': 22344960, 'steps': 116379, 'loss/train': 0.9711276292800903} 08/31/2021 10:16:35 - INFO - __main__ - Step 116381: {'lr': 6.1005751253211586e-05, 'samples': 22345152, 'steps': 116380, 'loss/train': 1.433858036994934} 08/31/2021 10:16:36 - INFO - __main__ - Step 116382: {'lr': 6.100227751057588e-05, 'samples': 22345344, 'steps': 116381, 'loss/train': 0.6829839944839478} 08/31/2021 10:16:36 - INFO - __main__ - Step 116383: {'lr': 6.0998803853099666e-05, 'samples': 22345536, 'steps': 116382, 'loss/train': 1.1378895044326782} 08/31/2021 10:16:36 - INFO - __main__ - Step 116384: {'lr': 6.099533028078444e-05, 'samples': 22345728, 'steps': 116383, 'loss/train': 1.7445837259292603} 08/31/2021 10:16:38 - INFO - __main__ - Step 116385: {'lr': 6.0991856793631756e-05, 'samples': 22345920, 'steps': 116384, 'loss/train': 0.1367095410823822} 08/31/2021 10:16:39 - INFO - __main__ - Step 116386: {'lr': 6.0988383391643255e-05, 'samples': 22346112, 'steps': 116385, 'loss/train': 0.15157289803028107} 08/31/2021 10:16:39 - INFO - __main__ - Step 116387: {'lr': 6.098491007482046e-05, 'samples': 22346304, 'steps': 116386, 'loss/train': 1.2533276081085205} 08/31/2021 10:16:39 - INFO - __main__ - Step 116388: {'lr': 6.098143684316496e-05, 'samples': 22346496, 'steps': 116387, 'loss/train': 1.3876852989196777} 08/31/2021 10:16:40 - INFO - __main__ - Step 116389: {'lr': 6.0977963696678294e-05, 'samples': 22346688, 'steps': 116388, 'loss/train': 1.8958595991134644} 08/31/2021 10:16:40 - INFO - __main__ - Step 116390: {'lr': 6.097449063536206e-05, 'samples': 22346880, 'steps': 116389, 'loss/train': 1.3948917388916016} 08/31/2021 10:16:41 - INFO - __main__ - Step 116391: {'lr': 6.097101765921781e-05, 'samples': 22347072, 'steps': 116390, 'loss/train': 1.26611328125} 08/31/2021 10:16:42 - INFO - __main__ - Step 116392: {'lr': 6.096754476824706e-05, 'samples': 22347264, 'steps': 116391, 'loss/train': 1.2480874061584473} 08/31/2021 10:16:42 - INFO - __main__ - Step 116393: {'lr': 6.096407196245146e-05, 'samples': 22347456, 'steps': 116392, 'loss/train': 0.9512978792190552} 08/31/2021 10:16:43 - INFO - __main__ - Step 116394: {'lr': 6.0960599241832505e-05, 'samples': 22347648, 'steps': 116393, 'loss/train': 1.2439450025558472} 08/31/2021 10:16:43 - INFO - __main__ - Step 116395: {'lr': 6.09571266063918e-05, 'samples': 22347840, 'steps': 116394, 'loss/train': 1.697020411491394} 08/31/2021 10:16:44 - INFO - __main__ - Step 116396: {'lr': 6.0953654056130955e-05, 'samples': 22348032, 'steps': 116395, 'loss/train': 1.1977028846740723} 08/31/2021 10:16:45 - INFO - __main__ - Step 116397: {'lr': 6.0950181591051425e-05, 'samples': 22348224, 'steps': 116396, 'loss/train': 1.0591386556625366} 08/31/2021 10:16:45 - INFO - __main__ - Step 116398: {'lr': 6.0946709211154806e-05, 'samples': 22348416, 'steps': 116397, 'loss/train': 1.002899408340454} 08/31/2021 10:16:46 - INFO - __main__ - Step 116399: {'lr': 6.094323691644271e-05, 'samples': 22348608, 'steps': 116398, 'loss/train': 1.1585125923156738} 08/31/2021 10:16:46 - INFO - __main__ - Step 116400: {'lr': 6.0939764706916646e-05, 'samples': 22348800, 'steps': 116399, 'loss/train': 1.461707592010498} 08/31/2021 10:16:47 - INFO - __main__ - Step 116401: {'lr': 6.0936292582578215e-05, 'samples': 22348992, 'steps': 116400, 'loss/train': 1.0430426597595215} 08/31/2021 10:16:48 - INFO - __main__ - Step 116402: {'lr': 6.093282054342897e-05, 'samples': 22349184, 'steps': 116401, 'loss/train': 0.6604019999504089} 08/31/2021 10:16:48 - INFO - __main__ - Step 116403: {'lr': 6.092934858947049e-05, 'samples': 22349376, 'steps': 116402, 'loss/train': 0.4730702042579651} 08/31/2021 10:16:49 - INFO - __main__ - Step 116404: {'lr': 6.092587672070432e-05, 'samples': 22349568, 'steps': 116403, 'loss/train': 0.12011553347110748} 08/31/2021 10:16:49 - INFO - __main__ - Step 116405: {'lr': 6.0922404937132054e-05, 'samples': 22349760, 'steps': 116404, 'loss/train': 0.10217192769050598} 08/31/2021 10:16:50 - INFO - __main__ - Step 116406: {'lr': 6.091893323875519e-05, 'samples': 22349952, 'steps': 116405, 'loss/train': 1.195980429649353} 08/31/2021 10:16:51 - INFO - __main__ - Step 116407: {'lr': 6.091546162557537e-05, 'samples': 22350144, 'steps': 116406, 'loss/train': 1.4120573997497559} 08/31/2021 10:16:51 - INFO - __main__ - Step 116408: {'lr': 6.091199009759413e-05, 'samples': 22350336, 'steps': 116407, 'loss/train': 1.103537917137146} 08/31/2021 10:16:52 - INFO - __main__ - Step 116409: {'lr': 6.0908518654813007e-05, 'samples': 22350528, 'steps': 116408, 'loss/train': 1.2262907028198242} 08/31/2021 10:16:52 - INFO - __main__ - Step 116410: {'lr': 6.0905047297233676e-05, 'samples': 22350720, 'steps': 116409, 'loss/train': 1.3372658491134644} 08/31/2021 10:16:53 - INFO - __main__ - Step 116411: {'lr': 6.090157602485752e-05, 'samples': 22350912, 'steps': 116410, 'loss/train': 1.3983232975006104} 08/31/2021 10:16:54 - INFO - __main__ - Step 116412: {'lr': 6.0898104837686206e-05, 'samples': 22351104, 'steps': 116411, 'loss/train': 1.2867956161499023} 08/31/2021 10:16:54 - INFO - __main__ - Step 116413: {'lr': 6.089463373572129e-05, 'samples': 22351296, 'steps': 116412, 'loss/train': 0.3857302665710449} 08/31/2021 10:16:55 - INFO - __main__ - Step 116414: {'lr': 6.089116271896436e-05, 'samples': 22351488, 'steps': 116413, 'loss/train': 1.3120877742767334} 08/31/2021 10:16:55 - INFO - __main__ - Step 116415: {'lr': 6.0887691787416903e-05, 'samples': 22351680, 'steps': 116414, 'loss/train': 1.0414224863052368} 08/31/2021 10:16:55 - INFO - __main__ - Step 116416: {'lr': 6.0884220941080564e-05, 'samples': 22351872, 'steps': 116415, 'loss/train': 1.2095246315002441} 08/31/2021 10:16:58 - INFO - __main__ - Step 116417: {'lr': 6.08807501799569e-05, 'samples': 22352064, 'steps': 116416, 'loss/train': 0.47292110323905945} 08/31/2021 10:16:59 - INFO - __main__ - Step 116418: {'lr': 6.0877279504047396e-05, 'samples': 22352256, 'steps': 116417, 'loss/train': 1.4444011449813843} 08/31/2021 10:16:59 - INFO - __main__ - Step 116419: {'lr': 6.0873808913353704e-05, 'samples': 22352448, 'steps': 116418, 'loss/train': 1.3995062112808228} 08/31/2021 10:16:59 - INFO - __main__ - Step 116420: {'lr': 6.087033840787737e-05, 'samples': 22352640, 'steps': 116419, 'loss/train': 0.9511362910270691} 08/31/2021 10:17:00 - INFO - __main__ - Step 116421: {'lr': 6.086686798761992e-05, 'samples': 22352832, 'steps': 116420, 'loss/train': 1.0611966848373413} 08/31/2021 10:17:00 - INFO - __main__ - Step 116422: {'lr': 6.0863397652582944e-05, 'samples': 22353024, 'steps': 116421, 'loss/train': 1.422786831855774} 08/31/2021 10:17:00 - INFO - __main__ - Step 116423: {'lr': 6.085992740276808e-05, 'samples': 22353216, 'steps': 116422, 'loss/train': 0.8639073371887207} 08/31/2021 10:17:02 - INFO - __main__ - Step 116424: {'lr': 6.085645723817673e-05, 'samples': 22353408, 'steps': 116423, 'loss/train': 0.2907126545906067} 08/31/2021 10:17:03 - INFO - __main__ - Step 116425: {'lr': 6.0852987158810545e-05, 'samples': 22353600, 'steps': 116424, 'loss/train': 0.7241851091384888} 08/31/2021 10:17:03 - INFO - __main__ - Step 116426: {'lr': 6.08495171646711e-05, 'samples': 22353792, 'steps': 116425, 'loss/train': 0.34099647402763367} 08/31/2021 10:17:03 - INFO - __main__ - Step 116427: {'lr': 6.0846047255759926e-05, 'samples': 22353984, 'steps': 116426, 'loss/train': 1.0095136165618896} 08/31/2021 10:17:04 - INFO - __main__ - Step 116428: {'lr': 6.0842577432078604e-05, 'samples': 22354176, 'steps': 116427, 'loss/train': 1.0840715169906616} 08/31/2021 10:17:05 - INFO - __main__ - Step 116429: {'lr': 6.083910769362871e-05, 'samples': 22354368, 'steps': 116428, 'loss/train': 1.0080479383468628} 08/31/2021 10:17:06 - INFO - __main__ - Step 116430: {'lr': 6.0835638040411815e-05, 'samples': 22354560, 'steps': 116429, 'loss/train': 0.8815687894821167} 08/31/2021 10:17:06 - INFO - __main__ - Step 116431: {'lr': 6.0832168472429424e-05, 'samples': 22354752, 'steps': 116430, 'loss/train': 0.788234293460846} 08/31/2021 10:17:06 - INFO - __main__ - Step 116432: {'lr': 6.082869898968316e-05, 'samples': 22354944, 'steps': 116431, 'loss/train': 1.2179962396621704} 08/31/2021 10:17:07 - INFO - __main__ - Step 116433: {'lr': 6.0825229592174544e-05, 'samples': 22355136, 'steps': 116432, 'loss/train': 1.3848949670791626} 08/31/2021 10:17:08 - INFO - __main__ - Step 116434: {'lr': 6.0821760279905187e-05, 'samples': 22355328, 'steps': 116433, 'loss/train': 1.286870002746582} 08/31/2021 10:17:09 - INFO - __main__ - Step 116435: {'lr': 6.081829105287662e-05, 'samples': 22355520, 'steps': 116434, 'loss/train': 1.55964195728302} 08/31/2021 10:17:09 - INFO - __main__ - Step 116436: {'lr': 6.081482191109039e-05, 'samples': 22355712, 'steps': 116435, 'loss/train': 1.8767430782318115} 08/31/2021 10:17:09 - INFO - __main__ - Step 116437: {'lr': 6.081135285454817e-05, 'samples': 22355904, 'steps': 116436, 'loss/train': 0.5640247464179993} 08/31/2021 10:17:10 - INFO - __main__ - Step 116438: {'lr': 6.080788388325137e-05, 'samples': 22356096, 'steps': 116437, 'loss/train': 1.0034996271133423} 08/31/2021 10:17:11 - INFO - __main__ - Step 116439: {'lr': 6.0804414997201604e-05, 'samples': 22356288, 'steps': 116438, 'loss/train': 0.43159061670303345} 08/31/2021 10:17:12 - INFO - __main__ - Step 116440: {'lr': 6.080094619640045e-05, 'samples': 22356480, 'steps': 116439, 'loss/train': 0.45550936460494995} 08/31/2021 10:17:12 - INFO - __main__ - Step 116441: {'lr': 6.079747748084949e-05, 'samples': 22356672, 'steps': 116440, 'loss/train': 0.8812036514282227} 08/31/2021 10:17:12 - INFO - __main__ - Step 116442: {'lr': 6.079400885055025e-05, 'samples': 22356864, 'steps': 116441, 'loss/train': 1.2158950567245483} 08/31/2021 10:17:13 - INFO - __main__ - Step 116443: {'lr': 6.079054030550432e-05, 'samples': 22357056, 'steps': 116442, 'loss/train': 1.2509171962738037} 08/31/2021 10:17:14 - INFO - __main__ - Step 116444: {'lr': 6.078707184571325e-05, 'samples': 22357248, 'steps': 116443, 'loss/train': 1.070364236831665} 08/31/2021 10:17:15 - INFO - __main__ - Step 116445: {'lr': 6.078360347117859e-05, 'samples': 22357440, 'steps': 116444, 'loss/train': 1.116683840751648} 08/31/2021 10:17:15 - INFO - __main__ - Step 116446: {'lr': 6.0780135181901925e-05, 'samples': 22357632, 'steps': 116445, 'loss/train': 1.804701328277588} 08/31/2021 10:17:16 - INFO - __main__ - Step 116447: {'lr': 6.077666697788481e-05, 'samples': 22357824, 'steps': 116446, 'loss/train': 0.03609856590628624} 08/31/2021 10:17:16 - INFO - __main__ - Step 116448: {'lr': 6.0773198859128826e-05, 'samples': 22358016, 'steps': 116447, 'loss/train': 1.2482174634933472} 08/31/2021 10:17:16 - INFO - __main__ - Step 116449: {'lr': 6.0769730825635496e-05, 'samples': 22358208, 'steps': 116448, 'loss/train': 1.1127331256866455} 08/31/2021 10:17:18 - INFO - __main__ - Step 116450: {'lr': 6.0766262877406496e-05, 'samples': 22358400, 'steps': 116449, 'loss/train': 0.9823262691497803} 08/31/2021 10:17:18 - INFO - __main__ - Step 116451: {'lr': 6.076279501444323e-05, 'samples': 22358592, 'steps': 116450, 'loss/train': 0.3077572286128998} 08/31/2021 10:17:19 - INFO - __main__ - Step 116452: {'lr': 6.075932723674732e-05, 'samples': 22358784, 'steps': 116451, 'loss/train': 1.3331304788589478} 08/31/2021 10:17:19 - INFO - __main__ - Step 116453: {'lr': 6.075585954432033e-05, 'samples': 22358976, 'steps': 116452, 'loss/train': 0.501218855381012} 08/31/2021 10:17:19 - INFO - __main__ - Step 116454: {'lr': 6.075239193716384e-05, 'samples': 22359168, 'steps': 116453, 'loss/train': 0.9958602786064148} 08/31/2021 10:17:21 - INFO - __main__ - Step 116455: {'lr': 6.074892441527938e-05, 'samples': 22359360, 'steps': 116454, 'loss/train': 0.8068424463272095} 08/31/2021 10:17:21 - INFO - __main__ - Step 116456: {'lr': 6.074545697866854e-05, 'samples': 22359552, 'steps': 116455, 'loss/train': 0.3285062909126282} 08/31/2021 10:17:22 - INFO - __main__ - Step 116457: {'lr': 6.074198962733291e-05, 'samples': 22359744, 'steps': 116456, 'loss/train': 0.9393052458763123} 08/31/2021 10:17:22 - INFO - __main__ - Step 116458: {'lr': 6.073852236127397e-05, 'samples': 22359936, 'steps': 116457, 'loss/train': 1.0556199550628662} 08/31/2021 10:17:22 - INFO - __main__ - Step 116459: {'lr': 6.073505518049338e-05, 'samples': 22360128, 'steps': 116458, 'loss/train': 0.6494420766830444} 08/31/2021 10:17:24 - INFO - __main__ - Step 116460: {'lr': 6.073158808499263e-05, 'samples': 22360320, 'steps': 116459, 'loss/train': 0.3373014032840729} 08/31/2021 10:17:24 - INFO - __main__ - Step 116461: {'lr': 6.072812107477329e-05, 'samples': 22360512, 'steps': 116460, 'loss/train': 1.2855803966522217} 08/31/2021 10:17:25 - INFO - __main__ - Step 116462: {'lr': 6.072465414983697e-05, 'samples': 22360704, 'steps': 116461, 'loss/train': 1.080214500427246} 08/31/2021 10:17:25 - INFO - __main__ - Step 116463: {'lr': 6.072118731018517e-05, 'samples': 22360896, 'steps': 116462, 'loss/train': 1.574662685394287} 08/31/2021 10:17:25 - INFO - __main__ - Step 116464: {'lr': 6.071772055581959e-05, 'samples': 22361088, 'steps': 116463, 'loss/train': 0.9741806983947754} 08/31/2021 10:17:27 - INFO - __main__ - Step 116465: {'lr': 6.0714253886741595e-05, 'samples': 22361280, 'steps': 116464, 'loss/train': 0.9420086741447449} 08/31/2021 10:17:28 - INFO - __main__ - Step 116466: {'lr': 6.071078730295282e-05, 'samples': 22361472, 'steps': 116465, 'loss/train': 0.8234875798225403} 08/31/2021 10:17:28 - INFO - __main__ - Step 116467: {'lr': 6.0707320804454846e-05, 'samples': 22361664, 'steps': 116466, 'loss/train': 0.202750101685524} 08/31/2021 10:17:28 - INFO - __main__ - Step 116468: {'lr': 6.0703854391249256e-05, 'samples': 22361856, 'steps': 116467, 'loss/train': 0.3916243016719818} 08/31/2021 10:17:29 - INFO - __main__ - Step 116469: {'lr': 6.070038806333758e-05, 'samples': 22362048, 'steps': 116468, 'loss/train': 1.0827761888504028} 08/31/2021 10:17:31 - INFO - __main__ - Step 116470: {'lr': 6.069692182072137e-05, 'samples': 22362240, 'steps': 116469, 'loss/train': 1.702939748764038} 08/31/2021 10:17:31 - INFO - __main__ - Step 116471: {'lr': 6.069345566340223e-05, 'samples': 22362432, 'steps': 116470, 'loss/train': 1.586679220199585} 08/31/2021 10:17:32 - INFO - __main__ - Step 116472: {'lr': 6.0689989591381666e-05, 'samples': 22362624, 'steps': 116471, 'loss/train': 0.7903079986572266} 08/31/2021 10:17:32 - INFO - __main__ - Step 116473: {'lr': 6.068652360466131e-05, 'samples': 22362816, 'steps': 116472, 'loss/train': 0.9500574469566345} 08/31/2021 10:17:32 - INFO - __main__ - Step 116474: {'lr': 6.068305770324267e-05, 'samples': 22363008, 'steps': 116473, 'loss/train': 1.0451782941818237} 08/31/2021 10:17:34 - INFO - __main__ - Step 116475: {'lr': 6.067959188712732e-05, 'samples': 22363200, 'steps': 116474, 'loss/train': 0.6647031307220459} 08/31/2021 10:17:35 - INFO - __main__ - Step 116476: {'lr': 6.067612615631682e-05, 'samples': 22363392, 'steps': 116475, 'loss/train': 1.349810004234314} 08/31/2021 10:17:35 - INFO - __main__ - Step 116477: {'lr': 6.06726605108128e-05, 'samples': 22363584, 'steps': 116476, 'loss/train': 0.6861713528633118} 08/31/2021 10:17:36 - INFO - __main__ - Step 116478: {'lr': 6.066919495061671e-05, 'samples': 22363776, 'steps': 116477, 'loss/train': 0.792416512966156} 08/31/2021 10:17:36 - INFO - __main__ - Step 116479: {'lr': 6.066572947573015e-05, 'samples': 22363968, 'steps': 116478, 'loss/train': 0.815430223941803} 08/31/2021 10:17:36 - INFO - __main__ - Step 116480: {'lr': 6.066226408615469e-05, 'samples': 22364160, 'steps': 116479, 'loss/train': 1.356459617614746} 08/31/2021 10:17:38 - INFO - __main__ - Step 116481: {'lr': 6.065879878189187e-05, 'samples': 22364352, 'steps': 116480, 'loss/train': 0.051544513553380966} 08/31/2021 10:17:39 - INFO - __main__ - Step 116482: {'lr': 6.065533356294331e-05, 'samples': 22364544, 'steps': 116481, 'loss/train': 0.8992004990577698} 08/31/2021 10:17:39 - INFO - __main__ - Step 116483: {'lr': 6.0651868429310505e-05, 'samples': 22364736, 'steps': 116482, 'loss/train': 1.4183189868927002} 08/31/2021 10:17:39 - INFO - __main__ - Step 116484: {'lr': 6.064840338099506e-05, 'samples': 22364928, 'steps': 116483, 'loss/train': 1.2891056537628174} 08/31/2021 10:17:40 - INFO - __main__ - Step 116485: {'lr': 6.064493841799854e-05, 'samples': 22365120, 'steps': 116484, 'loss/train': 1.7184818983078003} 08/31/2021 10:17:40 - INFO - __main__ - Step 116486: {'lr': 6.064147354032246e-05, 'samples': 22365312, 'steps': 116485, 'loss/train': 0.8815696835517883} 08/31/2021 10:17:42 - INFO - __main__ - Step 116487: {'lr': 6.063800874796843e-05, 'samples': 22365504, 'steps': 116486, 'loss/train': 0.11127864569425583} 08/31/2021 10:17:43 - INFO - __main__ - Step 116488: {'lr': 6.063454404093796e-05, 'samples': 22365696, 'steps': 116487, 'loss/train': 1.4846001863479614} 08/31/2021 10:17:43 - INFO - __main__ - Step 116489: {'lr': 6.063107941923268e-05, 'samples': 22365888, 'steps': 116488, 'loss/train': 0.5215848684310913} 08/31/2021 10:17:43 - INFO - __main__ - Step 116490: {'lr': 6.0627614882854174e-05, 'samples': 22366080, 'steps': 116489, 'loss/train': 1.0954935550689697} 08/31/2021 10:17:44 - INFO - __main__ - Step 116491: {'lr': 6.062415043180386e-05, 'samples': 22366272, 'steps': 116490, 'loss/train': 0.22723418474197388} 08/31/2021 10:17:45 - INFO - __main__ - Step 116492: {'lr': 6.06206860660834e-05, 'samples': 22366464, 'steps': 116491, 'loss/train': 0.06802015006542206} 08/31/2021 10:17:46 - INFO - __main__ - Step 116493: {'lr': 6.0617221785694315e-05, 'samples': 22366656, 'steps': 116492, 'loss/train': 0.4419257640838623} 08/31/2021 10:17:46 - INFO - __main__ - Step 116494: {'lr': 6.0613757590638196e-05, 'samples': 22366848, 'steps': 116493, 'loss/train': 1.8258575201034546} 08/31/2021 10:17:46 - INFO - __main__ - Step 116495: {'lr': 6.0610293480916595e-05, 'samples': 22367040, 'steps': 116494, 'loss/train': 1.090732455253601} 08/31/2021 10:17:47 - INFO - __main__ - Step 116496: {'lr': 6.060682945653106e-05, 'samples': 22367232, 'steps': 116495, 'loss/train': 0.02926541492342949} 08/31/2021 10:17:48 - INFO - __main__ - Step 116497: {'lr': 6.0603365517483186e-05, 'samples': 22367424, 'steps': 116496, 'loss/train': 1.3770469427108765} 08/31/2021 10:17:49 - INFO - __main__ - Step 116498: {'lr': 6.059990166377452e-05, 'samples': 22367616, 'steps': 116497, 'loss/train': 0.9970482587814331} 08/31/2021 10:17:49 - INFO - __main__ - Step 116499: {'lr': 6.0596437895406615e-05, 'samples': 22367808, 'steps': 116498, 'loss/train': 1.0241438150405884} 08/31/2021 10:17:49 - INFO - __main__ - Step 116500: {'lr': 6.0592974212381e-05, 'samples': 22368000, 'steps': 116499, 'loss/train': 1.2987531423568726} 08/31/2021 10:17:50 - INFO - __main__ - Step 116501: {'lr': 6.0589510614699305e-05, 'samples': 22368192, 'steps': 116500, 'loss/train': 0.5264414548873901} 08/31/2021 10:17:51 - INFO - __main__ - Step 116502: {'lr': 6.058604710236304e-05, 'samples': 22368384, 'steps': 116501, 'loss/train': 0.7604452967643738} 08/31/2021 10:17:52 - INFO - __main__ - Step 116503: {'lr': 6.058258367537376e-05, 'samples': 22368576, 'steps': 116502, 'loss/train': 0.2883509695529938} 08/31/2021 10:17:52 - INFO - __main__ - Step 116504: {'lr': 6.057912033373314e-05, 'samples': 22368768, 'steps': 116503, 'loss/train': 1.2860671281814575} 08/31/2021 10:17:52 - INFO - __main__ - Step 116505: {'lr': 6.057565707744256e-05, 'samples': 22368960, 'steps': 116504, 'loss/train': 0.4027237296104431} 08/31/2021 10:17:53 - INFO - __main__ - Step 116506: {'lr': 6.0572193906503676e-05, 'samples': 22369152, 'steps': 116505, 'loss/train': 0.9859153628349304} 08/31/2021 10:17:54 - INFO - __main__ - Step 116507: {'lr': 6.0568730820918044e-05, 'samples': 22369344, 'steps': 116506, 'loss/train': 1.4198566675186157} 08/31/2021 10:17:55 - INFO - __main__ - Step 116508: {'lr': 6.056526782068719e-05, 'samples': 22369536, 'steps': 116507, 'loss/train': 1.0052167177200317} 08/31/2021 10:17:55 - INFO - __main__ - Step 116509: {'lr': 6.056180490581273e-05, 'samples': 22369728, 'steps': 116508, 'loss/train': 0.16482336819171906} 08/31/2021 10:17:56 - INFO - __main__ - Step 116510: {'lr': 6.055834207629621e-05, 'samples': 22369920, 'steps': 116509, 'loss/train': 1.107224941253662} 08/31/2021 10:17:56 - INFO - __main__ - Step 116511: {'lr': 6.055487933213916e-05, 'samples': 22370112, 'steps': 116510, 'loss/train': 0.05361676588654518} 08/31/2021 10:17:58 - INFO - __main__ - Step 116512: {'lr': 6.055141667334313e-05, 'samples': 22370304, 'steps': 116511, 'loss/train': 0.8832116723060608} 08/31/2021 10:17:58 - INFO - __main__ - Step 116513: {'lr': 6.0547954099909736e-05, 'samples': 22370496, 'steps': 116512, 'loss/train': 1.2451919317245483} 08/31/2021 10:17:59 - INFO - __main__ - Step 116514: {'lr': 6.054449161184053e-05, 'samples': 22370688, 'steps': 116513, 'loss/train': 0.2421937882900238} 08/31/2021 10:17:59 - INFO - __main__ - Step 116515: {'lr': 6.054102920913701e-05, 'samples': 22370880, 'steps': 116514, 'loss/train': 1.6663012504577637} 08/31/2021 10:17:59 - INFO - __main__ - Step 116516: {'lr': 6.0537566891800815e-05, 'samples': 22371072, 'steps': 116515, 'loss/train': 0.758940577507019} 08/31/2021 10:18:01 - INFO - __main__ - Step 116517: {'lr': 6.053410465983353e-05, 'samples': 22371264, 'steps': 116516, 'loss/train': 0.04190448299050331} 08/31/2021 10:18:01 - INFO - __main__ - Step 116518: {'lr': 6.053064251323656e-05, 'samples': 22371456, 'steps': 116517, 'loss/train': 1.0248894691467285} 08/31/2021 10:18:02 - INFO - __main__ - Step 116519: {'lr': 6.052718045201158e-05, 'samples': 22371648, 'steps': 116518, 'loss/train': 1.1776297092437744} 08/31/2021 10:18:02 - INFO - __main__ - Step 116520: {'lr': 6.052371847616015e-05, 'samples': 22371840, 'steps': 116519, 'loss/train': 1.2533068656921387} 08/31/2021 10:18:02 - INFO - __main__ - Step 116521: {'lr': 6.0520256585683774e-05, 'samples': 22372032, 'steps': 116520, 'loss/train': 1.414917230606079} 08/31/2021 10:18:04 - INFO - __main__ - Step 116522: {'lr': 6.051679478058405e-05, 'samples': 22372224, 'steps': 116521, 'loss/train': 1.3685572147369385} 08/31/2021 10:18:05 - INFO - __main__ - Step 116523: {'lr': 6.051333306086254e-05, 'samples': 22372416, 'steps': 116522, 'loss/train': 0.9465432167053223} 08/31/2021 10:18:05 - INFO - __main__ - Step 116524: {'lr': 6.0509871426520814e-05, 'samples': 22372608, 'steps': 116523, 'loss/train': 0.0551181361079216} 08/31/2021 10:18:06 - INFO - __main__ - Step 116525: {'lr': 6.05064098775604e-05, 'samples': 22372800, 'steps': 116524, 'loss/train': 1.0319550037384033} 08/31/2021 10:18:06 - INFO - __main__ - Step 116526: {'lr': 6.050294841398285e-05, 'samples': 22372992, 'steps': 116525, 'loss/train': 0.5927466750144958} 08/31/2021 10:18:07 - INFO - __main__ - Step 116527: {'lr': 6.049948703578978e-05, 'samples': 22373184, 'steps': 116526, 'loss/train': 0.9603695273399353} 08/31/2021 10:18:08 - INFO - __main__ - Step 116528: {'lr': 6.0496025742982715e-05, 'samples': 22373376, 'steps': 116527, 'loss/train': 0.93589848279953} 08/31/2021 10:18:08 - INFO - __main__ - Step 116529: {'lr': 6.0492564535563204e-05, 'samples': 22373568, 'steps': 116528, 'loss/train': 0.6521877646446228} 08/31/2021 10:18:09 - INFO - __main__ - Step 116530: {'lr': 6.048910341353284e-05, 'samples': 22373760, 'steps': 116529, 'loss/train': 0.48325279355049133} 08/31/2021 10:18:09 - INFO - __main__ - Step 116531: {'lr': 6.0485642376893216e-05, 'samples': 22373952, 'steps': 116530, 'loss/train': 1.289662480354309} 08/31/2021 10:18:10 - INFO - __main__ - Step 116532: {'lr': 6.048218142564577e-05, 'samples': 22374144, 'steps': 116531, 'loss/train': 1.118467926979065} 08/31/2021 10:18:11 - INFO - __main__ - Step 116533: {'lr': 6.047872055979212e-05, 'samples': 22374336, 'steps': 116532, 'loss/train': 1.5199835300445557} 08/31/2021 10:18:11 - INFO - __main__ - Step 116534: {'lr': 6.0475259779333854e-05, 'samples': 22374528, 'steps': 116533, 'loss/train': 1.2350406646728516} 08/31/2021 10:18:12 - INFO - __main__ - Step 116535: {'lr': 6.04717990842725e-05, 'samples': 22374720, 'steps': 116534, 'loss/train': 1.343588948249817} 08/31/2021 10:18:12 - INFO - __main__ - Step 116536: {'lr': 6.046833847460961e-05, 'samples': 22374912, 'steps': 116535, 'loss/train': 1.2996511459350586} 08/31/2021 10:18:12 - INFO - __main__ - Step 116537: {'lr': 6.046487795034678e-05, 'samples': 22375104, 'steps': 116536, 'loss/train': 1.095740795135498} 08/31/2021 10:18:14 - INFO - __main__ - Step 116538: {'lr': 6.0461417511485565e-05, 'samples': 22375296, 'steps': 116537, 'loss/train': 1.2077147960662842} 08/31/2021 10:18:15 - INFO - __main__ - Step 116539: {'lr': 6.0457957158027486e-05, 'samples': 22375488, 'steps': 116538, 'loss/train': 0.050211623311042786} 08/31/2021 10:18:15 - INFO - __main__ - Step 116540: {'lr': 6.045449688997415e-05, 'samples': 22375680, 'steps': 116539, 'loss/train': 1.3754444122314453} 08/31/2021 10:18:15 - INFO - __main__ - Step 116541: {'lr': 6.045103670732707e-05, 'samples': 22375872, 'steps': 116540, 'loss/train': 1.4720324277877808} 08/31/2021 10:18:16 - INFO - __main__ - Step 116542: {'lr': 6.044757661008785e-05, 'samples': 22376064, 'steps': 116541, 'loss/train': 1.425468921661377} 08/31/2021 10:18:17 - INFO - __main__ - Step 116543: {'lr': 6.044411659825799e-05, 'samples': 22376256, 'steps': 116542, 'loss/train': 0.23852196335792542} 08/31/2021 10:18:18 - INFO - __main__ - Step 116544: {'lr': 6.0440656671839204e-05, 'samples': 22376448, 'steps': 116543, 'loss/train': 1.1086586713790894} 08/31/2021 10:18:18 - INFO - __main__ - Step 116545: {'lr': 6.043719683083282e-05, 'samples': 22376640, 'steps': 116544, 'loss/train': 1.620980978012085} 08/31/2021 10:18:18 - INFO - __main__ - Step 116546: {'lr': 6.043373707524055e-05, 'samples': 22376832, 'steps': 116545, 'loss/train': 1.0720808506011963} 08/31/2021 10:18:19 - INFO - __main__ - Step 116547: {'lr': 6.0430277405063875e-05, 'samples': 22377024, 'steps': 116546, 'loss/train': 1.7092905044555664} 08/31/2021 10:18:20 - INFO - __main__ - Step 116548: {'lr': 6.042681782030443e-05, 'samples': 22377216, 'steps': 116547, 'loss/train': 0.8059930801391602} 08/31/2021 10:18:21 - INFO - __main__ - Step 116549: {'lr': 6.0423358320963715e-05, 'samples': 22377408, 'steps': 116548, 'loss/train': 1.2461469173431396} 08/31/2021 10:18:21 - INFO - __main__ - Step 116550: {'lr': 6.04198989070433e-05, 'samples': 22377600, 'steps': 116549, 'loss/train': 0.9926555752754211} 08/31/2021 10:18:21 - INFO - __main__ - Step 116551: {'lr': 6.041643957854476e-05, 'samples': 22377792, 'steps': 116550, 'loss/train': 1.1406843662261963} 08/31/2021 10:18:22 - INFO - __main__ - Step 116552: {'lr': 6.041298033546966e-05, 'samples': 22377984, 'steps': 116551, 'loss/train': 1.2982053756713867} 08/31/2021 10:18:23 - INFO - __main__ - Step 116553: {'lr': 6.040952117781953e-05, 'samples': 22378176, 'steps': 116552, 'loss/train': 1.1570899486541748} 08/31/2021 10:18:24 - INFO - __main__ - Step 116554: {'lr': 6.040606210559593e-05, 'samples': 22378368, 'steps': 116553, 'loss/train': 0.8464978933334351} 08/31/2021 10:18:24 - INFO - __main__ - Step 116555: {'lr': 6.040260311880047e-05, 'samples': 22378560, 'steps': 116554, 'loss/train': 1.2664446830749512} 08/31/2021 10:18:24 - INFO - __main__ - Step 116556: {'lr': 6.039914421743464e-05, 'samples': 22378752, 'steps': 116555, 'loss/train': 1.69133460521698} 08/31/2021 10:18:25 - INFO - __main__ - Step 116557: {'lr': 6.039568540150006e-05, 'samples': 22378944, 'steps': 116556, 'loss/train': 1.7117490768432617} 08/31/2021 10:18:25 - INFO - __main__ - Step 116558: {'lr': 6.039222667099831e-05, 'samples': 22379136, 'steps': 116557, 'loss/train': 1.4368269443511963} 08/31/2021 10:18:27 - INFO - __main__ - Step 116559: {'lr': 6.038876802593082e-05, 'samples': 22379328, 'steps': 116558, 'loss/train': 0.16721130907535553} 08/31/2021 10:18:27 - INFO - __main__ - Step 116560: {'lr': 6.038530946629925e-05, 'samples': 22379520, 'steps': 116559, 'loss/train': 0.8431402444839478} 08/31/2021 10:18:27 - INFO - __main__ - Step 116561: {'lr': 6.038185099210511e-05, 'samples': 22379712, 'steps': 116560, 'loss/train': 0.9327747821807861} 08/31/2021 10:18:28 - INFO - __main__ - Step 116562: {'lr': 6.037839260334999e-05, 'samples': 22379904, 'steps': 116561, 'loss/train': 1.5569556951522827} 08/31/2021 10:18:28 - INFO - __main__ - Step 116563: {'lr': 6.037493430003543e-05, 'samples': 22380096, 'steps': 116562, 'loss/train': 0.9896320104598999} 08/31/2021 10:18:30 - INFO - __main__ - Step 116564: {'lr': 6.0371476082163006e-05, 'samples': 22380288, 'steps': 116563, 'loss/train': 0.9849863648414612} 08/31/2021 10:18:30 - INFO - __main__ - Step 116565: {'lr': 6.036801794973429e-05, 'samples': 22380480, 'steps': 116564, 'loss/train': 1.4255810976028442} 08/31/2021 10:18:30 - INFO - __main__ - Step 116566: {'lr': 6.036455990275078e-05, 'samples': 22380672, 'steps': 116565, 'loss/train': 1.0215036869049072} 08/31/2021 10:18:31 - INFO - __main__ - Step 116567: {'lr': 6.036110194121411e-05, 'samples': 22380864, 'steps': 116566, 'loss/train': 0.8152481317520142} 08/31/2021 10:18:31 - INFO - __main__ - Step 116568: {'lr': 6.035764406512578e-05, 'samples': 22381056, 'steps': 116567, 'loss/train': 1.364322543144226} 08/31/2021 10:18:32 - INFO - __main__ - Step 116569: {'lr': 6.0354186274487356e-05, 'samples': 22381248, 'steps': 116568, 'loss/train': 1.2981443405151367} 08/31/2021 10:18:33 - INFO - __main__ - Step 116570: {'lr': 6.0350728569300434e-05, 'samples': 22381440, 'steps': 116569, 'loss/train': 1.0731348991394043} 08/31/2021 10:18:33 - INFO - __main__ - Step 116571: {'lr': 6.0347270949566626e-05, 'samples': 22381632, 'steps': 116570, 'loss/train': 1.2165817022323608} 08/31/2021 10:18:34 - INFO - __main__ - Step 116572: {'lr': 6.03438134152873e-05, 'samples': 22381824, 'steps': 116571, 'loss/train': 1.3935970067977905} 08/31/2021 10:18:34 - INFO - __main__ - Step 116573: {'lr': 6.034035596646417e-05, 'samples': 22382016, 'steps': 116572, 'loss/train': 0.6842974424362183} 08/31/2021 10:18:36 - INFO - __main__ - Step 116574: {'lr': 6.033689860309871e-05, 'samples': 22382208, 'steps': 116573, 'loss/train': 1.1438592672348022} 08/31/2021 10:18:37 - INFO - __main__ - Step 116575: {'lr': 6.0333441325192557e-05, 'samples': 22382400, 'steps': 116574, 'loss/train': 0.8416665196418762} 08/31/2021 10:18:37 - INFO - __main__ - Step 116576: {'lr': 6.032998413274721e-05, 'samples': 22382592, 'steps': 116575, 'loss/train': 1.627636194229126} 08/31/2021 10:18:37 - INFO - __main__ - Step 116577: {'lr': 6.032652702576424e-05, 'samples': 22382784, 'steps': 116576, 'loss/train': 1.1072078943252563} 08/31/2021 10:18:38 - INFO - __main__ - Step 116578: {'lr': 6.03230700042452e-05, 'samples': 22382976, 'steps': 116577, 'loss/train': 1.1997653245925903} 08/31/2021 10:18:38 - INFO - __main__ - Step 116579: {'lr': 6.031961306819167e-05, 'samples': 22383168, 'steps': 116578, 'loss/train': 1.6369516849517822} 08/31/2021 10:18:40 - INFO - __main__ - Step 116580: {'lr': 6.031615621760519e-05, 'samples': 22383360, 'steps': 116579, 'loss/train': 0.3438827693462372} 08/31/2021 10:18:41 - INFO - __main__ - Step 116581: {'lr': 6.031269945248735e-05, 'samples': 22383552, 'steps': 116580, 'loss/train': 0.5773876905441284} 08/31/2021 10:18:41 - INFO - __main__ - Step 116582: {'lr': 6.030924277283964e-05, 'samples': 22383744, 'steps': 116581, 'loss/train': 1.0253851413726807} 08/31/2021 10:18:42 - INFO - __main__ - Step 116583: {'lr': 6.0305786178663693e-05, 'samples': 22383936, 'steps': 116582, 'loss/train': 0.3531957268714905} 08/31/2021 10:18:42 - INFO - __main__ - Step 116584: {'lr': 6.030232966996102e-05, 'samples': 22384128, 'steps': 116583, 'loss/train': 0.021909276023507118} 08/31/2021 10:18:42 - INFO - __main__ - Step 116585: {'lr': 6.029887324673325e-05, 'samples': 22384320, 'steps': 116584, 'loss/train': 0.6841992735862732} 08/31/2021 10:18:44 - INFO - __main__ - Step 116586: {'lr': 6.029541690898183e-05, 'samples': 22384512, 'steps': 116585, 'loss/train': 1.1757088899612427} 08/31/2021 10:18:44 - INFO - __main__ - Step 116587: {'lr': 6.029196065670833e-05, 'samples': 22384704, 'steps': 116586, 'loss/train': 0.8660475611686707} 08/31/2021 10:18:45 - INFO - __main__ - Step 116588: {'lr': 6.028850448991438e-05, 'samples': 22384896, 'steps': 116587, 'loss/train': 1.0860885381698608} 08/31/2021 10:18:45 - INFO - __main__ - Step 116589: {'lr': 6.02850484086015e-05, 'samples': 22385088, 'steps': 116588, 'loss/train': 0.6389071941375732} 08/31/2021 10:18:45 - INFO - __main__ - Step 116590: {'lr': 6.028159241277123e-05, 'samples': 22385280, 'steps': 116589, 'loss/train': 1.1836426258087158} 08/31/2021 10:18:47 - INFO - __main__ - Step 116591: {'lr': 6.027813650242517e-05, 'samples': 22385472, 'steps': 116590, 'loss/train': 1.5839170217514038} 08/31/2021 10:18:47 - INFO - __main__ - Step 116592: {'lr': 6.0274680677564835e-05, 'samples': 22385664, 'steps': 116591, 'loss/train': 1.297178030014038} 08/31/2021 10:18:48 - INFO - __main__ - Step 116593: {'lr': 6.027122493819182e-05, 'samples': 22385856, 'steps': 116592, 'loss/train': 1.274214744567871} 08/31/2021 10:18:48 - INFO - __main__ - Step 116594: {'lr': 6.026776928430763e-05, 'samples': 22386048, 'steps': 116593, 'loss/train': 1.1328253746032715} 08/31/2021 10:18:48 - INFO - __main__ - Step 116595: {'lr': 6.02643137159139e-05, 'samples': 22386240, 'steps': 116594, 'loss/train': 0.3754732608795166} 08/31/2021 10:18:50 - INFO - __main__ - Step 116596: {'lr': 6.026085823301211e-05, 'samples': 22386432, 'steps': 116595, 'loss/train': 0.9787560105323792} 08/31/2021 10:18:50 - INFO - __main__ - Step 116597: {'lr': 6.0257402835603934e-05, 'samples': 22386624, 'steps': 116596, 'loss/train': 1.2512507438659668} 08/31/2021 10:18:51 - INFO - __main__ - Step 116598: {'lr': 6.025394752369076e-05, 'samples': 22386816, 'steps': 116597, 'loss/train': 1.4357142448425293} 08/31/2021 10:18:51 - INFO - __main__ - Step 116599: {'lr': 6.025049229727425e-05, 'samples': 22387008, 'steps': 116598, 'loss/train': 0.9061486721038818} 08/31/2021 10:18:51 - INFO - __main__ - Step 116600: {'lr': 6.0247037156355935e-05, 'samples': 22387200, 'steps': 116599, 'loss/train': 1.2219213247299194} 08/31/2021 10:18:53 - INFO - __main__ - Step 116601: {'lr': 6.024358210093736e-05, 'samples': 22387392, 'steps': 116600, 'loss/train': 0.8746603727340698} 08/31/2021 10:18:53 - INFO - __main__ - Step 116602: {'lr': 6.024012713102012e-05, 'samples': 22387584, 'steps': 116601, 'loss/train': 1.0721594095230103} 08/31/2021 10:18:54 - INFO - __main__ - Step 116603: {'lr': 6.023667224660573e-05, 'samples': 22387776, 'steps': 116602, 'loss/train': 0.7192354202270508} 08/31/2021 10:18:54 - INFO - __main__ - Step 116604: {'lr': 6.023321744769578e-05, 'samples': 22387968, 'steps': 116603, 'loss/train': 1.1808712482452393} 08/31/2021 10:18:54 - INFO - __main__ - Step 116605: {'lr': 6.022976273429182e-05, 'samples': 22388160, 'steps': 116604, 'loss/train': 1.7356334924697876} 08/31/2021 10:18:55 - INFO - __main__ - Step 116606: {'lr': 6.02263081063954e-05, 'samples': 22388352, 'steps': 116605, 'loss/train': 0.7559395432472229} 08/31/2021 10:18:57 - INFO - __main__ - Step 116607: {'lr': 6.0222853564008056e-05, 'samples': 22388544, 'steps': 116606, 'loss/train': 0.7029961943626404} 08/31/2021 10:18:57 - INFO - __main__ - Step 116608: {'lr': 6.021939910713145e-05, 'samples': 22388736, 'steps': 116607, 'loss/train': 4.4479899406433105} 08/31/2021 10:18:58 - INFO - __main__ - Step 116609: {'lr': 6.0215944735767e-05, 'samples': 22388928, 'steps': 116608, 'loss/train': 1.1238083839416504} 08/31/2021 10:18:58 - INFO - __main__ - Step 116610: {'lr': 6.021249044991628e-05, 'samples': 22389120, 'steps': 116609, 'loss/train': 0.12467176467180252} 08/31/2021 10:18:58 - INFO - __main__ - Step 116611: {'lr': 6.0209036249580905e-05, 'samples': 22389312, 'steps': 116610, 'loss/train': 0.1014067605137825} 08/31/2021 10:19:00 - INFO - __main__ - Step 116612: {'lr': 6.020558213476243e-05, 'samples': 22389504, 'steps': 116611, 'loss/train': 1.0862865447998047} 08/31/2021 10:19:01 - INFO - __main__ - Step 116613: {'lr': 6.020212810546236e-05, 'samples': 22389696, 'steps': 116612, 'loss/train': 2.742279052734375} 08/31/2021 10:19:01 - INFO - __main__ - Step 116614: {'lr': 6.0198674161682285e-05, 'samples': 22389888, 'steps': 116613, 'loss/train': 0.6327289938926697} 08/31/2021 10:19:01 - INFO - __main__ - Step 116615: {'lr': 6.019522030342378e-05, 'samples': 22390080, 'steps': 116614, 'loss/train': 0.10516002774238586} 08/31/2021 10:19:02 - INFO - __main__ - Step 116616: {'lr': 6.019176653068836e-05, 'samples': 22390272, 'steps': 116615, 'loss/train': 1.319868803024292} 08/31/2021 10:19:02 - INFO - __main__ - Step 116617: {'lr': 6.018831284347762e-05, 'samples': 22390464, 'steps': 116616, 'loss/train': 0.947023332118988} 08/31/2021 10:19:04 - INFO - __main__ - Step 116618: {'lr': 6.0184859241793064e-05, 'samples': 22390656, 'steps': 116617, 'loss/train': 0.9210653305053711} 08/31/2021 10:19:04 - INFO - __main__ - Step 116619: {'lr': 6.018140572563638e-05, 'samples': 22390848, 'steps': 116618, 'loss/train': 1.542046070098877} 08/31/2021 10:19:04 - INFO - __main__ - Step 116620: {'lr': 6.017795229500894e-05, 'samples': 22391040, 'steps': 116619, 'loss/train': 0.09029990434646606} 08/31/2021 10:19:05 - INFO - __main__ - Step 116621: {'lr': 6.0174498949912396e-05, 'samples': 22391232, 'steps': 116620, 'loss/train': 1.088810920715332} 08/31/2021 10:19:05 - INFO - __main__ - Step 116622: {'lr': 6.0171045690348285e-05, 'samples': 22391424, 'steps': 116621, 'loss/train': 0.6327469348907471} 08/31/2021 10:19:07 - INFO - __main__ - Step 116623: {'lr': 6.016759251631818e-05, 'samples': 22391616, 'steps': 116622, 'loss/train': 0.17635458707809448} 08/31/2021 10:19:07 - INFO - __main__ - Step 116624: {'lr': 6.016413942782362e-05, 'samples': 22391808, 'steps': 116623, 'loss/train': 0.9697243571281433} 08/31/2021 10:19:08 - INFO - __main__ - Step 116625: {'lr': 6.0160686424866193e-05, 'samples': 22392000, 'steps': 116624, 'loss/train': 1.2326726913452148} 08/31/2021 10:19:08 - INFO - __main__ - Step 116626: {'lr': 6.0157233507447394e-05, 'samples': 22392192, 'steps': 116625, 'loss/train': 2.264296770095825} 08/31/2021 10:19:08 - INFO - __main__ - Step 116627: {'lr': 6.015378067556884e-05, 'samples': 22392384, 'steps': 116626, 'loss/train': 1.8715914487838745} 08/31/2021 10:19:10 - INFO - __main__ - Step 116628: {'lr': 6.015032792923206e-05, 'samples': 22392576, 'steps': 116627, 'loss/train': 0.028481606394052505} 08/31/2021 10:19:11 - INFO - __main__ - Step 116629: {'lr': 6.0146875268438595e-05, 'samples': 22392768, 'steps': 116628, 'loss/train': 1.2727429866790771} 08/31/2021 10:19:11 - INFO - __main__ - Step 116630: {'lr': 6.014342269319012e-05, 'samples': 22392960, 'steps': 116629, 'loss/train': 1.0224822759628296} 08/31/2021 10:19:12 - INFO - __main__ - Step 116631: {'lr': 6.013997020348799e-05, 'samples': 22393152, 'steps': 116630, 'loss/train': 0.9350742697715759} 08/31/2021 10:19:12 - INFO - __main__ - Step 116632: {'lr': 6.013651779933388e-05, 'samples': 22393344, 'steps': 116631, 'loss/train': 0.4636484682559967} 08/31/2021 10:19:12 - INFO - __main__ - Step 116633: {'lr': 6.0133065480729334e-05, 'samples': 22393536, 'steps': 116632, 'loss/train': 1.2902711629867554} 08/31/2021 10:19:13 - INFO - __main__ - Step 116634: {'lr': 6.012961324767588e-05, 'samples': 22393728, 'steps': 116633, 'loss/train': 0.07677564024925232} 08/31/2021 10:19:16 - INFO - __main__ - Step 116635: {'lr': 6.012616110017508e-05, 'samples': 22393920, 'steps': 116634, 'loss/train': 0.06740105152130127} 08/31/2021 10:19:16 - INFO - __main__ - Step 116636: {'lr': 6.012270903822853e-05, 'samples': 22394112, 'steps': 116635, 'loss/train': 1.3279309272766113} 08/31/2021 10:19:17 - INFO - __main__ - Step 116637: {'lr': 6.011925706183774e-05, 'samples': 22394304, 'steps': 116636, 'loss/train': 0.8864900469779968} 08/31/2021 10:19:17 - INFO - __main__ - Step 116638: {'lr': 6.011580517100429e-05, 'samples': 22394496, 'steps': 116637, 'loss/train': 1.0748294591903687} 08/31/2021 10:19:17 - INFO - __main__ - Step 116639: {'lr': 6.0112353365729706e-05, 'samples': 22394688, 'steps': 116638, 'loss/train': 0.5518619418144226} 08/31/2021 10:19:18 - INFO - __main__ - Step 116640: {'lr': 6.010890164601568e-05, 'samples': 22394880, 'steps': 116639, 'loss/train': 0.13524118065834045} 08/31/2021 10:19:19 - INFO - __main__ - Step 116641: {'lr': 6.010545001186354e-05, 'samples': 22395072, 'steps': 116640, 'loss/train': 0.8296966552734375} 08/31/2021 10:19:20 - INFO - __main__ - Step 116642: {'lr': 6.010199846327496e-05, 'samples': 22395264, 'steps': 116641, 'loss/train': 1.2935608625411987} 08/31/2021 10:19:20 - INFO - __main__ - Step 116643: {'lr': 6.0098547000251524e-05, 'samples': 22395456, 'steps': 116642, 'loss/train': 0.6322121024131775} 08/31/2021 10:19:20 - INFO - __main__ - Step 116644: {'lr': 6.009509562279472e-05, 'samples': 22395648, 'steps': 116643, 'loss/train': 1.8614002466201782} 08/31/2021 10:19:21 - INFO - __main__ - Step 116645: {'lr': 6.009164433090614e-05, 'samples': 22395840, 'steps': 116644, 'loss/train': 0.8571237921714783} 08/31/2021 10:19:22 - INFO - __main__ - Step 116646: {'lr': 6.008819312458735e-05, 'samples': 22396032, 'steps': 116645, 'loss/train': 0.9630950093269348} 08/31/2021 10:19:23 - INFO - __main__ - Step 116647: {'lr': 6.008474200383987e-05, 'samples': 22396224, 'steps': 116646, 'loss/train': 1.0286064147949219} 08/31/2021 10:19:23 - INFO - __main__ - Step 116648: {'lr': 6.0081290968665296e-05, 'samples': 22396416, 'steps': 116647, 'loss/train': 1.3384606838226318} 08/31/2021 10:19:24 - INFO - __main__ - Step 116649: {'lr': 6.007784001906513e-05, 'samples': 22396608, 'steps': 116648, 'loss/train': 0.7521423101425171} 08/31/2021 10:19:24 - INFO - __main__ - Step 116650: {'lr': 6.0074389155040984e-05, 'samples': 22396800, 'steps': 116649, 'loss/train': 1.0275189876556396} 08/31/2021 10:19:24 - INFO - __main__ - Step 116651: {'lr': 6.0070938376594384e-05, 'samples': 22396992, 'steps': 116650, 'loss/train': 0.9420680403709412} 08/31/2021 10:19:26 - INFO - __main__ - Step 116652: {'lr': 6.0067487683726965e-05, 'samples': 22397184, 'steps': 116651, 'loss/train': 1.0013974905014038} 08/31/2021 10:19:26 - INFO - __main__ - Step 116653: {'lr': 6.006403707644012e-05, 'samples': 22397376, 'steps': 116652, 'loss/train': 0.843666136264801} 08/31/2021 10:19:27 - INFO - __main__ - Step 116654: {'lr': 6.006058655473548e-05, 'samples': 22397568, 'steps': 116653, 'loss/train': 0.26495489478111267} 08/31/2021 10:19:27 - INFO - __main__ - Step 116655: {'lr': 6.005713611861463e-05, 'samples': 22397760, 'steps': 116654, 'loss/train': 0.7906749844551086} 08/31/2021 10:19:28 - INFO - __main__ - Step 116656: {'lr': 6.00536857680791e-05, 'samples': 22397952, 'steps': 116655, 'loss/train': 1.3516908884048462} 08/31/2021 10:19:29 - INFO - __main__ - Step 116657: {'lr': 6.0050235503130434e-05, 'samples': 22398144, 'steps': 116656, 'loss/train': 0.04635603725910187} 08/31/2021 10:19:30 - INFO - __main__ - Step 116658: {'lr': 6.004678532377023e-05, 'samples': 22398336, 'steps': 116657, 'loss/train': 0.6185638308525085} 08/31/2021 10:19:30 - INFO - __main__ - Step 116659: {'lr': 6.004333523e-05, 'samples': 22398528, 'steps': 116658, 'loss/train': 0.9107196927070618} 08/31/2021 10:19:30 - INFO - __main__ - Step 116660: {'lr': 6.00398852218213e-05, 'samples': 22398720, 'steps': 116659, 'loss/train': 0.14313319325447083} 08/31/2021 10:19:31 - INFO - __main__ - Step 116661: {'lr': 6.003643529923569e-05, 'samples': 22398912, 'steps': 116660, 'loss/train': 1.2091822624206543} 08/31/2021 10:19:32 - INFO - __main__ - Step 116662: {'lr': 6.0032985462244756e-05, 'samples': 22399104, 'steps': 116661, 'loss/train': 0.4558378756046295} 08/31/2021 10:19:33 - INFO - __main__ - Step 116663: {'lr': 6.002953571085001e-05, 'samples': 22399296, 'steps': 116662, 'loss/train': 1.270904779434204} 08/31/2021 10:19:33 - INFO - __main__ - Step 116664: {'lr': 6.0026086045053025e-05, 'samples': 22399488, 'steps': 116663, 'loss/train': 0.22272270917892456} 08/31/2021 10:19:34 - INFO - __main__ - Step 116665: {'lr': 6.002263646485545e-05, 'samples': 22399680, 'steps': 116664, 'loss/train': 0.19384866952896118} 08/31/2021 10:19:34 - INFO - __main__ - Step 116666: {'lr': 6.0019186970258655e-05, 'samples': 22399872, 'steps': 116665, 'loss/train': 0.18068289756774902} 08/31/2021 10:19:34 - INFO - __main__ - Step 116667: {'lr': 6.0015737561264275e-05, 'samples': 22400064, 'steps': 116666, 'loss/train': 0.7277349829673767} 08/31/2021 10:19:36 - INFO - __main__ - Step 116668: {'lr': 6.001228823787386e-05, 'samples': 22400256, 'steps': 116667, 'loss/train': 0.8558728694915771} 08/31/2021 10:19:36 - INFO - __main__ - Step 116669: {'lr': 6.000883900008899e-05, 'samples': 22400448, 'steps': 116668, 'loss/train': 1.1066499948501587} 08/31/2021 10:19:37 - INFO - __main__ - Step 116670: {'lr': 6.000538984791121e-05, 'samples': 22400640, 'steps': 116669, 'loss/train': 1.091403603553772} 08/31/2021 10:19:37 - INFO - __main__ - Step 116671: {'lr': 6.000194078134208e-05, 'samples': 22400832, 'steps': 116670, 'loss/train': 0.795615017414093} 08/31/2021 10:19:37 - INFO - __main__ - Step 116672: {'lr': 5.9998491800383137e-05, 'samples': 22401024, 'steps': 116671, 'loss/train': 1.730370283126831} 08/31/2021 10:19:39 - INFO - __main__ - Step 116673: {'lr': 5.999504290503593e-05, 'samples': 22401216, 'steps': 116672, 'loss/train': 1.7980570793151855} 08/31/2021 10:19:39 - INFO - __main__ - Step 116674: {'lr': 5.999159409530203e-05, 'samples': 22401408, 'steps': 116673, 'loss/train': 0.5223067402839661} 08/31/2021 10:19:40 - INFO - __main__ - Step 116675: {'lr': 5.9988145371182996e-05, 'samples': 22401600, 'steps': 116674, 'loss/train': 1.264794945716858} 08/31/2021 10:19:40 - INFO - __main__ - Step 116676: {'lr': 5.9984696732680366e-05, 'samples': 22401792, 'steps': 116675, 'loss/train': 0.47652822732925415} 08/31/2021 10:19:40 - INFO - __main__ - Step 116677: {'lr': 5.998124817979569e-05, 'samples': 22401984, 'steps': 116676, 'loss/train': 1.3120113611221313} 08/31/2021 10:19:41 - INFO - __main__ - Step 116678: {'lr': 5.997779971253054e-05, 'samples': 22402176, 'steps': 116677, 'loss/train': 1.1098017692565918} 08/31/2021 10:19:42 - INFO - __main__ - Step 116679: {'lr': 5.997435133088652e-05, 'samples': 22402368, 'steps': 116678, 'loss/train': 0.8147355914115906} 08/31/2021 10:19:43 - INFO - __main__ - Step 116680: {'lr': 5.9970903034865076e-05, 'samples': 22402560, 'steps': 116679, 'loss/train': 0.22915400564670563} 08/31/2021 10:19:43 - INFO - __main__ - Step 116681: {'lr': 5.996745482446778e-05, 'samples': 22402752, 'steps': 116680, 'loss/train': 1.4381505250930786} 08/31/2021 10:19:43 - INFO - __main__ - Step 116682: {'lr': 5.9964006699696235e-05, 'samples': 22402944, 'steps': 116681, 'loss/train': 1.3085811138153076} 08/31/2021 10:19:44 - INFO - __main__ - Step 116683: {'lr': 5.996055866055197e-05, 'samples': 22403136, 'steps': 116682, 'loss/train': 0.5106806755065918} 08/31/2021 10:19:45 - INFO - __main__ - Step 116684: {'lr': 5.995711070703658e-05, 'samples': 22403328, 'steps': 116683, 'loss/train': 1.984349012374878} 08/31/2021 10:19:46 - INFO - __main__ - Step 116685: {'lr': 5.995366283915155e-05, 'samples': 22403520, 'steps': 116684, 'loss/train': 1.1165707111358643} 08/31/2021 10:19:46 - INFO - __main__ - Step 116686: {'lr': 5.995021505689846e-05, 'samples': 22403712, 'steps': 116685, 'loss/train': 0.37083473801612854} 08/31/2021 10:19:46 - INFO - __main__ - Step 116687: {'lr': 5.9946767360278874e-05, 'samples': 22403904, 'steps': 116686, 'loss/train': 1.126598596572876} 08/31/2021 10:19:47 - INFO - __main__ - Step 116688: {'lr': 5.994331974929434e-05, 'samples': 22404096, 'steps': 116687, 'loss/train': 0.5214152336120605} 08/31/2021 10:19:49 - INFO - __main__ - Step 116689: {'lr': 5.993987222394645e-05, 'samples': 22404288, 'steps': 116688, 'loss/train': 1.5722965002059937} 08/31/2021 10:19:49 - INFO - __main__ - Step 116690: {'lr': 5.993642478423669e-05, 'samples': 22404480, 'steps': 116689, 'loss/train': 1.6638113260269165} 08/31/2021 10:19:50 - INFO - __main__ - Step 116691: {'lr': 5.993297743016665e-05, 'samples': 22404672, 'steps': 116690, 'loss/train': 1.2811139822006226} 08/31/2021 10:19:50 - INFO - __main__ - Step 116692: {'lr': 5.992953016173794e-05, 'samples': 22404864, 'steps': 116691, 'loss/train': 1.0543267726898193} 08/31/2021 10:19:50 - INFO - __main__ - Step 116693: {'lr': 5.992608297895199e-05, 'samples': 22405056, 'steps': 116692, 'loss/train': 0.9980245232582092} 08/31/2021 10:19:52 - INFO - __main__ - Step 116694: {'lr': 5.99226358818104e-05, 'samples': 22405248, 'steps': 116693, 'loss/train': 1.173516035079956} 08/31/2021 10:19:52 - INFO - __main__ - Step 116695: {'lr': 5.9919188870314753e-05, 'samples': 22405440, 'steps': 116694, 'loss/train': 0.5672763586044312} 08/31/2021 10:19:53 - INFO - __main__ - Step 116696: {'lr': 5.991574194446658e-05, 'samples': 22405632, 'steps': 116695, 'loss/train': 0.49100950360298157} 08/31/2021 10:19:53 - INFO - __main__ - Step 116697: {'lr': 5.991229510426744e-05, 'samples': 22405824, 'steps': 116696, 'loss/train': 0.7838671207427979} 08/31/2021 10:19:53 - INFO - __main__ - Step 116698: {'lr': 5.990884834971888e-05, 'samples': 22406016, 'steps': 116697, 'loss/train': 1.9205119609832764} 08/31/2021 10:19:55 - INFO - __main__ - Step 116699: {'lr': 5.990540168082248e-05, 'samples': 22406208, 'steps': 116698, 'loss/train': 1.4119760990142822} 08/31/2021 10:19:55 - INFO - __main__ - Step 116700: {'lr': 5.990195509757976e-05, 'samples': 22406400, 'steps': 116699, 'loss/train': 0.48036035895347595} 08/31/2021 10:19:56 - INFO - __main__ - Step 116701: {'lr': 5.989850859999227e-05, 'samples': 22406592, 'steps': 116700, 'loss/train': 0.9090695977210999} 08/31/2021 10:19:56 - INFO - __main__ - Step 116702: {'lr': 5.9895062188061594e-05, 'samples': 22406784, 'steps': 116701, 'loss/train': 0.8309786915779114} 08/31/2021 10:19:56 - INFO - __main__ - Step 116703: {'lr': 5.9891615861789286e-05, 'samples': 22406976, 'steps': 116702, 'loss/train': 0.2261965274810791} 08/31/2021 10:19:58 - INFO - __main__ - Step 116704: {'lr': 5.988816962117685e-05, 'samples': 22407168, 'steps': 116703, 'loss/train': 0.7914414405822754} 08/31/2021 10:19:58 - INFO - __main__ - Step 116705: {'lr': 5.9884723466225897e-05, 'samples': 22407360, 'steps': 116704, 'loss/train': 1.1824136972427368} 08/31/2021 10:19:59 - INFO - __main__ - Step 116706: {'lr': 5.988127739693802e-05, 'samples': 22407552, 'steps': 116705, 'loss/train': 0.9245821237564087} 08/31/2021 10:19:59 - INFO - __main__ - Step 116707: {'lr': 5.987783141331463e-05, 'samples': 22407744, 'steps': 116706, 'loss/train': 0.026084618642926216} 08/31/2021 10:19:59 - INFO - __main__ - Step 116708: {'lr': 5.9874385515357345e-05, 'samples': 22407936, 'steps': 116707, 'loss/train': 0.8643409609794617} 08/31/2021 10:20:00 - INFO - __main__ - Step 116709: {'lr': 5.9870939703067754e-05, 'samples': 22408128, 'steps': 116708, 'loss/train': 1.3752986192703247} 08/31/2021 10:20:01 - INFO - __main__ - Step 116710: {'lr': 5.986749397644736e-05, 'samples': 22408320, 'steps': 116709, 'loss/train': 0.028772547841072083} 08/31/2021 10:20:02 - INFO - __main__ - Step 116711: {'lr': 5.986404833549774e-05, 'samples': 22408512, 'steps': 116710, 'loss/train': 0.3763117492198944} 08/31/2021 10:20:02 - INFO - __main__ - Step 116712: {'lr': 5.986060278022046e-05, 'samples': 22408704, 'steps': 116711, 'loss/train': 0.8814852833747864} 08/31/2021 10:20:03 - INFO - __main__ - Step 116713: {'lr': 5.9857157310617054e-05, 'samples': 22408896, 'steps': 116712, 'loss/train': 0.4579837918281555} 08/31/2021 10:20:03 - INFO - __main__ - Step 116714: {'lr': 5.985371192668907e-05, 'samples': 22409088, 'steps': 116713, 'loss/train': 1.3480231761932373} 08/31/2021 10:20:04 - INFO - __main__ - Step 116715: {'lr': 5.9850266628438096e-05, 'samples': 22409280, 'steps': 116714, 'loss/train': 1.200513243675232} 08/31/2021 10:20:05 - INFO - __main__ - Step 116716: {'lr': 5.984682141586561e-05, 'samples': 22409472, 'steps': 116715, 'loss/train': 1.580437421798706} 08/31/2021 10:20:05 - INFO - __main__ - Step 116717: {'lr': 5.9843376288973236e-05, 'samples': 22409664, 'steps': 116716, 'loss/train': 0.5676808953285217} 08/31/2021 10:20:06 - INFO - __main__ - Step 116718: {'lr': 5.983993124776252e-05, 'samples': 22409856, 'steps': 116717, 'loss/train': 1.220960021018982} 08/31/2021 10:20:06 - INFO - __main__ - Step 116719: {'lr': 5.9836486292235065e-05, 'samples': 22410048, 'steps': 116718, 'loss/train': 0.37813618779182434} 08/31/2021 10:20:07 - INFO - __main__ - Step 116720: {'lr': 5.9833041422392264e-05, 'samples': 22410240, 'steps': 116719, 'loss/train': 1.0813018083572388} 08/31/2021 10:20:08 - INFO - __main__ - Step 116721: {'lr': 5.982959663823576e-05, 'samples': 22410432, 'steps': 116720, 'loss/train': 0.8807319402694702} 08/31/2021 10:20:08 - INFO - __main__ - Step 116722: {'lr': 5.982615193976712e-05, 'samples': 22410624, 'steps': 116721, 'loss/train': 1.0295212268829346} 08/31/2021 10:20:09 - INFO - __main__ - Step 116723: {'lr': 5.9822707326987886e-05, 'samples': 22410816, 'steps': 116722, 'loss/train': 0.839448869228363} 08/31/2021 10:20:09 - INFO - __main__ - Step 116724: {'lr': 5.9819262799899576e-05, 'samples': 22411008, 'steps': 116723, 'loss/train': 0.025680910795927048} 08/31/2021 10:20:11 - INFO - __main__ - Step 116725: {'lr': 5.98158183585038e-05, 'samples': 22411200, 'steps': 116724, 'loss/train': 0.9668339490890503} 08/31/2021 10:20:11 - INFO - __main__ - Step 116726: {'lr': 5.9812374002802065e-05, 'samples': 22411392, 'steps': 116725, 'loss/train': 1.1341274976730347} 08/31/2021 10:20:11 - INFO - __main__ - Step 116727: {'lr': 5.980892973279595e-05, 'samples': 22411584, 'steps': 116726, 'loss/train': 1.287567138671875} 08/31/2021 10:20:12 - INFO - __main__ - Step 116728: {'lr': 5.9805485548487e-05, 'samples': 22411776, 'steps': 116727, 'loss/train': 1.2816177606582642} 08/31/2021 10:20:12 - INFO - __main__ - Step 116729: {'lr': 5.980204144987675e-05, 'samples': 22411968, 'steps': 116728, 'loss/train': 1.0802147388458252} 08/31/2021 10:20:13 - INFO - __main__ - Step 116730: {'lr': 5.979859743696678e-05, 'samples': 22412160, 'steps': 116729, 'loss/train': 1.3137186765670776} 08/31/2021 10:20:14 - INFO - __main__ - Step 116731: {'lr': 5.9795153509758615e-05, 'samples': 22412352, 'steps': 116730, 'loss/train': 1.4183402061462402} 08/31/2021 10:20:14 - INFO - __main__ - Step 116732: {'lr': 5.9791709668253894e-05, 'samples': 22412544, 'steps': 116731, 'loss/train': 0.5780122876167297} 08/31/2021 10:20:15 - INFO - __main__ - Step 116733: {'lr': 5.978826591245401e-05, 'samples': 22412736, 'steps': 116732, 'loss/train': 1.4847744703292847} 08/31/2021 10:20:15 - INFO - __main__ - Step 116734: {'lr': 5.978482224236062e-05, 'samples': 22412928, 'steps': 116733, 'loss/train': 1.3220040798187256} 08/31/2021 10:20:16 - INFO - __main__ - Step 116735: {'lr': 5.978137865797523e-05, 'samples': 22413120, 'steps': 116734, 'loss/train': 1.4030226469039917} 08/31/2021 10:20:17 - INFO - __main__ - Step 116736: {'lr': 5.977793515929944e-05, 'samples': 22413312, 'steps': 116735, 'loss/train': 1.3291473388671875} 08/31/2021 10:20:17 - INFO - __main__ - Step 116737: {'lr': 5.977449174633476e-05, 'samples': 22413504, 'steps': 116736, 'loss/train': 1.16890549659729} 08/31/2021 10:20:18 - INFO - __main__ - Step 116738: {'lr': 5.977104841908276e-05, 'samples': 22413696, 'steps': 116737, 'loss/train': 1.1510341167449951} 08/31/2021 10:20:18 - INFO - __main__ - Step 116739: {'lr': 5.976760517754501e-05, 'samples': 22413888, 'steps': 116738, 'loss/train': 0.9589408040046692} 08/31/2021 10:20:18 - INFO - __main__ - Step 116740: {'lr': 5.976416202172302e-05, 'samples': 22414080, 'steps': 116739, 'loss/train': 0.9130238890647888} 08/31/2021 10:20:21 - INFO - __main__ - Step 116741: {'lr': 5.9760718951618356e-05, 'samples': 22414272, 'steps': 116740, 'loss/train': 1.291783094406128} 08/31/2021 10:20:21 - INFO - __main__ - Step 116742: {'lr': 5.97572759672326e-05, 'samples': 22414464, 'steps': 116741, 'loss/train': 1.4503482580184937} 08/31/2021 10:20:22 - INFO - __main__ - Step 116743: {'lr': 5.975383306856727e-05, 'samples': 22414656, 'steps': 116742, 'loss/train': 1.453847050666809} 08/31/2021 10:20:22 - INFO - __main__ - Step 116744: {'lr': 5.975039025562393e-05, 'samples': 22414848, 'steps': 116743, 'loss/train': 0.6169172525405884} 08/31/2021 10:20:22 - INFO - __main__ - Step 116745: {'lr': 5.974694752840412e-05, 'samples': 22415040, 'steps': 116744, 'loss/train': 1.273384928703308} 08/31/2021 10:20:24 - INFO - __main__ - Step 116746: {'lr': 5.974350488690947e-05, 'samples': 22415232, 'steps': 116745, 'loss/train': 0.8760954141616821} 08/31/2021 10:20:24 - INFO - __main__ - Step 116747: {'lr': 5.97400623311414e-05, 'samples': 22415424, 'steps': 116746, 'loss/train': 0.9388132095336914} 08/31/2021 10:20:24 - INFO - __main__ - Step 116748: {'lr': 5.973661986110151e-05, 'samples': 22415616, 'steps': 116747, 'loss/train': 0.4287949502468109} 08/31/2021 10:20:25 - INFO - __main__ - Step 116749: {'lr': 5.9733177476791386e-05, 'samples': 22415808, 'steps': 116748, 'loss/train': 1.4860864877700806} 08/31/2021 10:20:25 - INFO - __main__ - Step 116750: {'lr': 5.9729735178212535e-05, 'samples': 22416000, 'steps': 116749, 'loss/train': 0.7802826762199402} 08/31/2021 10:20:27 - INFO - __main__ - Step 116751: {'lr': 5.972629296536655e-05, 'samples': 22416192, 'steps': 116750, 'loss/train': 0.48763492703437805} 08/31/2021 10:20:27 - INFO - __main__ - Step 116752: {'lr': 5.9722850838254935e-05, 'samples': 22416384, 'steps': 116751, 'loss/train': 0.5858801603317261} 08/31/2021 10:20:28 - INFO - __main__ - Step 116753: {'lr': 5.971940879687929e-05, 'samples': 22416576, 'steps': 116752, 'loss/train': 1.5377233028411865} 08/31/2021 10:20:28 - INFO - __main__ - Step 116754: {'lr': 5.9715966841241115e-05, 'samples': 22416768, 'steps': 116753, 'loss/train': 1.4255344867706299} 08/31/2021 10:20:28 - INFO - __main__ - Step 116755: {'lr': 5.9712524971342026e-05, 'samples': 22416960, 'steps': 116754, 'loss/train': 1.5427448749542236} 08/31/2021 10:20:30 - INFO - __main__ - Step 116756: {'lr': 5.9709083187183515e-05, 'samples': 22417152, 'steps': 116755, 'loss/train': 1.457577109336853} 08/31/2021 10:20:30 - INFO - __main__ - Step 116757: {'lr': 5.970564148876714e-05, 'samples': 22417344, 'steps': 116756, 'loss/train': 1.3946799039840698} 08/31/2021 10:20:31 - INFO - __main__ - Step 116758: {'lr': 5.970219987609449e-05, 'samples': 22417536, 'steps': 116757, 'loss/train': 1.309808611869812} 08/31/2021 10:20:31 - INFO - __main__ - Step 116759: {'lr': 5.969875834916716e-05, 'samples': 22417728, 'steps': 116758, 'loss/train': 0.04326362535357475} 08/31/2021 10:20:32 - INFO - __main__ - Step 116760: {'lr': 5.9695316907986544e-05, 'samples': 22417920, 'steps': 116759, 'loss/train': 0.7881619334220886} 08/31/2021 10:20:33 - INFO - __main__ - Step 116761: {'lr': 5.9691875552554315e-05, 'samples': 22418112, 'steps': 116760, 'loss/train': 0.7368592023849487} 08/31/2021 10:20:33 - INFO - __main__ - Step 116762: {'lr': 5.968843428287196e-05, 'samples': 22418304, 'steps': 116761, 'loss/train': 1.039266586303711} 08/31/2021 10:20:34 - INFO - __main__ - Step 116763: {'lr': 5.968499309894107e-05, 'samples': 22418496, 'steps': 116762, 'loss/train': 0.41499367356300354} 08/31/2021 10:20:34 - INFO - __main__ - Step 116764: {'lr': 5.9681552000763194e-05, 'samples': 22418688, 'steps': 116763, 'loss/train': 1.143052101135254} 08/31/2021 10:20:35 - INFO - __main__ - Step 116765: {'lr': 5.9678110988339864e-05, 'samples': 22418880, 'steps': 116764, 'loss/train': 1.1737645864486694} 08/31/2021 10:20:36 - INFO - __main__ - Step 116766: {'lr': 5.9674670061672656e-05, 'samples': 22419072, 'steps': 116765, 'loss/train': 0.7973779439926147} 08/31/2021 10:20:36 - INFO - __main__ - Step 116767: {'lr': 5.967122922076307e-05, 'samples': 22419264, 'steps': 116766, 'loss/train': 0.9537444710731506} 08/31/2021 10:20:37 - INFO - __main__ - Step 116768: {'lr': 5.9667788465612716e-05, 'samples': 22419456, 'steps': 116767, 'loss/train': 2.2574210166931152} 08/31/2021 10:20:37 - INFO - __main__ - Step 116769: {'lr': 5.9664347796223126e-05, 'samples': 22419648, 'steps': 116768, 'loss/train': 1.6355338096618652} 08/31/2021 10:20:37 - INFO - __main__ - Step 116770: {'lr': 5.9660907212595846e-05, 'samples': 22419840, 'steps': 116769, 'loss/train': 1.5716851949691772} 08/31/2021 10:20:38 - INFO - __main__ - Step 116771: {'lr': 5.965746671473241e-05, 'samples': 22420032, 'steps': 116770, 'loss/train': 1.2009992599487305} 08/31/2021 10:20:39 - INFO - __main__ - Step 116772: {'lr': 5.965402630263436e-05, 'samples': 22420224, 'steps': 116771, 'loss/train': 0.9983371496200562} 08/31/2021 10:20:40 - INFO - __main__ - Step 116773: {'lr': 5.965058597630338e-05, 'samples': 22420416, 'steps': 116772, 'loss/train': 0.9264028668403625} 08/31/2021 10:20:40 - INFO - __main__ - Step 116774: {'lr': 5.964714573574082e-05, 'samples': 22420608, 'steps': 116773, 'loss/train': 1.086108684539795} 08/31/2021 10:20:40 - INFO - __main__ - Step 116775: {'lr': 5.964370558094831e-05, 'samples': 22420800, 'steps': 116774, 'loss/train': 1.6343575716018677} 08/31/2021 10:20:41 - INFO - __main__ - Step 116776: {'lr': 5.9640265511927445e-05, 'samples': 22420992, 'steps': 116775, 'loss/train': 1.3025381565093994} 08/31/2021 10:20:42 - INFO - __main__ - Step 116777: {'lr': 5.9636825528679686e-05, 'samples': 22421184, 'steps': 116776, 'loss/train': 1.5407005548477173} 08/31/2021 10:20:43 - INFO - __main__ - Step 116778: {'lr': 5.9633385631206685e-05, 'samples': 22421376, 'steps': 116777, 'loss/train': 1.1868245601654053} 08/31/2021 10:20:43 - INFO - __main__ - Step 116779: {'lr': 5.9629945819509926e-05, 'samples': 22421568, 'steps': 116778, 'loss/train': 1.2501857280731201} 08/31/2021 10:20:44 - INFO - __main__ - Step 116780: {'lr': 5.9626506093590966e-05, 'samples': 22421760, 'steps': 116779, 'loss/train': 1.0429612398147583} 08/31/2021 10:20:44 - INFO - __main__ - Step 116781: {'lr': 5.9623066453451365e-05, 'samples': 22421952, 'steps': 116780, 'loss/train': 1.6996049880981445} 08/31/2021 10:20:47 - INFO - __main__ - Step 116782: {'lr': 5.961962689909267e-05, 'samples': 22422144, 'steps': 116781, 'loss/train': 0.02650490775704384} 08/31/2021 10:20:47 - INFO - __main__ - Step 116783: {'lr': 5.961618743051645e-05, 'samples': 22422336, 'steps': 116782, 'loss/train': 1.1337506771087646} 08/31/2021 10:20:47 - INFO - __main__ - Step 116784: {'lr': 5.961274804772423e-05, 'samples': 22422528, 'steps': 116783, 'loss/train': 1.7257814407348633} 08/31/2021 10:20:48 - INFO - __main__ - Step 116785: {'lr': 5.960930875071757e-05, 'samples': 22422720, 'steps': 116784, 'loss/train': 1.727787733078003} 08/31/2021 10:20:48 - INFO - __main__ - Step 116786: {'lr': 5.960586953949809e-05, 'samples': 22422912, 'steps': 116785, 'loss/train': 1.7105931043624878} 08/31/2021 10:20:48 - INFO - __main__ - Step 116787: {'lr': 5.960243041406718e-05, 'samples': 22423104, 'steps': 116786, 'loss/train': 1.714967966079712} 08/31/2021 10:20:49 - INFO - __main__ - Step 116788: {'lr': 5.959899137442648e-05, 'samples': 22423296, 'steps': 116787, 'loss/train': 1.0438319444656372} 08/31/2021 10:20:49 - INFO - __main__ - Step 116789: {'lr': 5.9595552420577545e-05, 'samples': 22423488, 'steps': 116788, 'loss/train': 0.963590681552887} 08/31/2021 10:20:51 - INFO - __main__ - Step 116790: {'lr': 5.959211355252192e-05, 'samples': 22423680, 'steps': 116789, 'loss/train': 1.186147689819336} 08/31/2021 10:20:51 - INFO - __main__ - Step 116791: {'lr': 5.9588674770261143e-05, 'samples': 22423872, 'steps': 116790, 'loss/train': 1.7546327114105225} 08/31/2021 10:20:52 - INFO - __main__ - Step 116792: {'lr': 5.958523607379679e-05, 'samples': 22424064, 'steps': 116791, 'loss/train': 1.2101807594299316} 08/31/2021 10:20:52 - INFO - __main__ - Step 116793: {'lr': 5.958179746313036e-05, 'samples': 22424256, 'steps': 116792, 'loss/train': 1.3151919841766357} 08/31/2021 10:20:52 - INFO - __main__ - Step 116794: {'lr': 5.957835893826347e-05, 'samples': 22424448, 'steps': 116793, 'loss/train': 0.9617295861244202} 08/31/2021 10:20:54 - INFO - __main__ - Step 116795: {'lr': 5.9574920499197606e-05, 'samples': 22424640, 'steps': 116794, 'loss/train': 0.17868925631046295} 08/31/2021 10:20:54 - INFO - __main__ - Step 116796: {'lr': 5.957148214593436e-05, 'samples': 22424832, 'steps': 116795, 'loss/train': 0.46194079518318176} 08/31/2021 10:20:55 - INFO - __main__ - Step 116797: {'lr': 5.956804387847525e-05, 'samples': 22425024, 'steps': 116796, 'loss/train': 1.267696738243103} 08/31/2021 10:20:55 - INFO - __main__ - Step 116798: {'lr': 5.956460569682184e-05, 'samples': 22425216, 'steps': 116797, 'loss/train': 0.6882562637329102} 08/31/2021 10:20:55 - INFO - __main__ - Step 116799: {'lr': 5.956116760097569e-05, 'samples': 22425408, 'steps': 116798, 'loss/train': 0.2380586862564087} 08/31/2021 10:20:57 - INFO - __main__ - Step 116800: {'lr': 5.955772959093842e-05, 'samples': 22425600, 'steps': 116799, 'loss/train': 1.349736213684082} 08/31/2021 10:20:58 - INFO - __main__ - Step 116801: {'lr': 5.955429166671139e-05, 'samples': 22425792, 'steps': 116800, 'loss/train': 1.1109203100204468} 08/31/2021 10:20:58 - INFO - __main__ - Step 116802: {'lr': 5.955085382829631e-05, 'samples': 22425984, 'steps': 116801, 'loss/train': 1.312106728553772} 08/31/2021 10:20:59 - INFO - __main__ - Step 116803: {'lr': 5.954741607569464e-05, 'samples': 22426176, 'steps': 116802, 'loss/train': 1.3177746534347534} 08/31/2021 10:20:59 - INFO - __main__ - Step 116804: {'lr': 5.9543978408907965e-05, 'samples': 22426368, 'steps': 116803, 'loss/train': 1.32003915309906} 08/31/2021 10:21:00 - INFO - __main__ - Step 116805: {'lr': 5.9540540827937836e-05, 'samples': 22426560, 'steps': 116804, 'loss/train': 1.2360831499099731} 08/31/2021 10:21:01 - INFO - __main__ - Step 116806: {'lr': 5.9537103332785805e-05, 'samples': 22426752, 'steps': 116805, 'loss/train': 1.3587448596954346} 08/31/2021 10:21:01 - INFO - __main__ - Step 116807: {'lr': 5.953366592345344e-05, 'samples': 22426944, 'steps': 116806, 'loss/train': 1.5359631776809692} 08/31/2021 10:21:01 - INFO - __main__ - Step 116808: {'lr': 5.9530228599942227e-05, 'samples': 22427136, 'steps': 116807, 'loss/train': 1.0062063932418823} 08/31/2021 10:21:02 - INFO - __main__ - Step 116809: {'lr': 5.952679136225378e-05, 'samples': 22427328, 'steps': 116808, 'loss/train': 0.787622332572937} 08/31/2021 10:21:03 - INFO - __main__ - Step 116810: {'lr': 5.952335421038962e-05, 'samples': 22427520, 'steps': 116809, 'loss/train': 1.3116021156311035} 08/31/2021 10:21:04 - INFO - __main__ - Step 116811: {'lr': 5.9519917144351286e-05, 'samples': 22427712, 'steps': 116810, 'loss/train': 2.3196299076080322} 08/31/2021 10:21:04 - INFO - __main__ - Step 116812: {'lr': 5.951648016414035e-05, 'samples': 22427904, 'steps': 116811, 'loss/train': 0.8647592067718506} 08/31/2021 10:21:04 - INFO - __main__ - Step 116813: {'lr': 5.95130432697584e-05, 'samples': 22428096, 'steps': 116812, 'loss/train': 1.443831443786621} 08/31/2021 10:21:05 - INFO - __main__ - Step 116814: {'lr': 5.95096064612069e-05, 'samples': 22428288, 'steps': 116813, 'loss/train': 1.2916951179504395} 08/31/2021 10:21:05 - INFO - __main__ - Step 116815: {'lr': 5.950616973848738e-05, 'samples': 22428480, 'steps': 116814, 'loss/train': 0.5667696595191956} 08/31/2021 10:21:07 - INFO - __main__ - Step 116816: {'lr': 5.950273310160148e-05, 'samples': 22428672, 'steps': 116815, 'loss/train': 1.029384970664978} 08/31/2021 10:21:07 - INFO - __main__ - Step 116817: {'lr': 5.94992965505507e-05, 'samples': 22428864, 'steps': 116816, 'loss/train': 1.0309232473373413} 08/31/2021 10:21:08 - INFO - __main__ - Step 116818: {'lr': 5.949586008533658e-05, 'samples': 22429056, 'steps': 116817, 'loss/train': 2.135096311569214} 08/31/2021 10:21:08 - INFO - __main__ - Step 116819: {'lr': 5.9492423705960724e-05, 'samples': 22429248, 'steps': 116818, 'loss/train': 1.4290666580200195} 08/31/2021 10:21:08 - INFO - __main__ - Step 116820: {'lr': 5.9488987412424615e-05, 'samples': 22429440, 'steps': 116819, 'loss/train': 1.3345770835876465} 08/31/2021 10:21:10 - INFO - __main__ - Step 116821: {'lr': 5.948555120472981e-05, 'samples': 22429632, 'steps': 116820, 'loss/train': 0.7675108909606934} 08/31/2021 10:21:10 - INFO - __main__ - Step 116822: {'lr': 5.9482115082877903e-05, 'samples': 22429824, 'steps': 116821, 'loss/train': 0.371975302696228} 08/31/2021 10:21:11 - INFO - __main__ - Step 116823: {'lr': 5.9478679046870405e-05, 'samples': 22430016, 'steps': 116822, 'loss/train': 1.607562780380249} 08/31/2021 10:21:11 - INFO - __main__ - Step 116824: {'lr': 5.9475243096708876e-05, 'samples': 22430208, 'steps': 116823, 'loss/train': 0.5565277934074402} 08/31/2021 10:21:11 - INFO - __main__ - Step 116825: {'lr': 5.947180723239487e-05, 'samples': 22430400, 'steps': 116824, 'loss/train': 0.7494298815727234} 08/31/2021 10:21:13 - INFO - __main__ - Step 116826: {'lr': 5.9468371453929946e-05, 'samples': 22430592, 'steps': 116825, 'loss/train': 0.9420323371887207} 08/31/2021 10:21:13 - INFO - __main__ - Step 116827: {'lr': 5.9464935761315676e-05, 'samples': 22430784, 'steps': 116826, 'loss/train': 0.11523069441318512} 08/31/2021 10:21:14 - INFO - __main__ - Step 116828: {'lr': 5.946150015455348e-05, 'samples': 22430976, 'steps': 116827, 'loss/train': 1.2175754308700562} 08/31/2021 10:21:14 - INFO - __main__ - Step 116829: {'lr': 5.945806463364503e-05, 'samples': 22431168, 'steps': 116828, 'loss/train': 1.5484302043914795} 08/31/2021 10:21:14 - INFO - __main__ - Step 116830: {'lr': 5.945462919859182e-05, 'samples': 22431360, 'steps': 116829, 'loss/train': 1.3197687864303589} 08/31/2021 10:21:16 - INFO - __main__ - Step 116831: {'lr': 5.94511938493954e-05, 'samples': 22431552, 'steps': 116830, 'loss/train': 1.3936494588851929} 08/31/2021 10:21:16 - INFO - __main__ - Step 116832: {'lr': 5.944775858605736e-05, 'samples': 22431744, 'steps': 116831, 'loss/train': 0.7907142043113708} 08/31/2021 10:21:17 - INFO - __main__ - Step 116833: {'lr': 5.9444323408579196e-05, 'samples': 22431936, 'steps': 116832, 'loss/train': 1.0272893905639648} 08/31/2021 10:21:17 - INFO - __main__ - Step 116834: {'lr': 5.944088831696248e-05, 'samples': 22432128, 'steps': 116833, 'loss/train': 0.5501735806465149} 08/31/2021 10:21:17 - INFO - __main__ - Step 116835: {'lr': 5.9437453311208754e-05, 'samples': 22432320, 'steps': 116834, 'loss/train': 0.9089788794517517} 08/31/2021 10:21:18 - INFO - __main__ - Step 116836: {'lr': 5.9434018391319596e-05, 'samples': 22432512, 'steps': 116835, 'loss/train': 1.0660572052001953} 08/31/2021 10:21:20 - INFO - __main__ - Step 116837: {'lr': 5.9430583557296525e-05, 'samples': 22432704, 'steps': 116836, 'loss/train': 0.5119438767433167} 08/31/2021 10:21:20 - INFO - __main__ - Step 116838: {'lr': 5.9427148809141074e-05, 'samples': 22432896, 'steps': 116837, 'loss/train': 0.508847713470459} 08/31/2021 10:21:20 - INFO - __main__ - Step 116839: {'lr': 5.942371414685482e-05, 'samples': 22433088, 'steps': 116838, 'loss/train': 1.9663593769073486} 08/31/2021 10:21:21 - INFO - __main__ - Step 116840: {'lr': 5.942027957043935e-05, 'samples': 22433280, 'steps': 116839, 'loss/train': 0.9602177143096924} 08/31/2021 10:21:21 - INFO - __main__ - Step 116841: {'lr': 5.941684507989611e-05, 'samples': 22433472, 'steps': 116840, 'loss/train': 1.4136446714401245} 08/31/2021 10:21:23 - INFO - __main__ - Step 116842: {'lr': 5.941341067522671e-05, 'samples': 22433664, 'steps': 116841, 'loss/train': 1.1174479722976685} 08/31/2021 10:21:23 - INFO - __main__ - Step 116843: {'lr': 5.940997635643267e-05, 'samples': 22433856, 'steps': 116842, 'loss/train': 0.5131269097328186} 08/31/2021 10:21:23 - INFO - __main__ - Step 116844: {'lr': 5.940654212351557e-05, 'samples': 22434048, 'steps': 116843, 'loss/train': 1.44546377658844} 08/31/2021 10:21:24 - INFO - __main__ - Step 116845: {'lr': 5.940310797647691e-05, 'samples': 22434240, 'steps': 116844, 'loss/train': 1.310081124305725} 08/31/2021 10:21:24 - INFO - __main__ - Step 116846: {'lr': 5.939967391531831e-05, 'samples': 22434432, 'steps': 116845, 'loss/train': 0.7784209251403809} 08/31/2021 10:21:26 - INFO - __main__ - Step 116847: {'lr': 5.939623994004123e-05, 'samples': 22434624, 'steps': 116846, 'loss/train': 1.28993558883667} 08/31/2021 10:21:26 - INFO - __main__ - Step 116848: {'lr': 5.9392806050647286e-05, 'samples': 22434816, 'steps': 116847, 'loss/train': 1.419272541999817} 08/31/2021 10:21:27 - INFO - __main__ - Step 116849: {'lr': 5.9389372247138004e-05, 'samples': 22435008, 'steps': 116848, 'loss/train': 1.0213638544082642} 08/31/2021 10:21:27 - INFO - __main__ - Step 116850: {'lr': 5.938593852951493e-05, 'samples': 22435200, 'steps': 116849, 'loss/train': 1.4127298593521118} 08/31/2021 10:21:27 - INFO - __main__ - Step 116851: {'lr': 5.9382504897779606e-05, 'samples': 22435392, 'steps': 116850, 'loss/train': 1.4997676610946655} 08/31/2021 10:21:29 - INFO - __main__ - Step 116852: {'lr': 5.93790713519336e-05, 'samples': 22435584, 'steps': 116851, 'loss/train': 1.455204725265503} 08/31/2021 10:21:30 - INFO - __main__ - Step 116853: {'lr': 5.93756378919785e-05, 'samples': 22435776, 'steps': 116852, 'loss/train': 1.2216756343841553} 08/31/2021 10:21:30 - INFO - __main__ - Step 116854: {'lr': 5.9372204517915725e-05, 'samples': 22435968, 'steps': 116853, 'loss/train': 0.5274747610092163} 08/31/2021 10:21:31 - INFO - __main__ - Step 116855: {'lr': 5.936877122974688e-05, 'samples': 22436160, 'steps': 116854, 'loss/train': 1.6198703050613403} 08/31/2021 10:21:31 - INFO - __main__ - Step 116856: {'lr': 5.9365338027473544e-05, 'samples': 22436352, 'steps': 116855, 'loss/train': 1.7039214372634888} 08/31/2021 10:21:33 - INFO - __main__ - Step 116857: {'lr': 5.936190491109725e-05, 'samples': 22436544, 'steps': 116856, 'loss/train': 1.2963083982467651} 08/31/2021 10:21:33 - INFO - __main__ - Step 116858: {'lr': 5.9358471880619516e-05, 'samples': 22436736, 'steps': 116857, 'loss/train': 0.75444495677948} 08/31/2021 10:21:33 - INFO - __main__ - Step 116859: {'lr': 5.935503893604194e-05, 'samples': 22436928, 'steps': 116858, 'loss/train': 1.0487326383590698} 08/31/2021 10:21:34 - INFO - __main__ - Step 116860: {'lr': 5.9351606077366e-05, 'samples': 22437120, 'steps': 116859, 'loss/train': 0.2144760638475418} 08/31/2021 10:21:34 - INFO - __main__ - Step 116861: {'lr': 5.934817330459333e-05, 'samples': 22437312, 'steps': 116860, 'loss/train': 1.185965895652771} 08/31/2021 10:21:36 - INFO - __main__ - Step 116862: {'lr': 5.9344740617725405e-05, 'samples': 22437504, 'steps': 116861, 'loss/train': 1.310719609260559} 08/31/2021 10:21:37 - INFO - __main__ - Step 116863: {'lr': 5.934130801676382e-05, 'samples': 22437696, 'steps': 116862, 'loss/train': 0.7799354791641235} 08/31/2021 10:21:37 - INFO - __main__ - Step 116864: {'lr': 5.9337875501710074e-05, 'samples': 22437888, 'steps': 116863, 'loss/train': 0.41246575117111206} 08/31/2021 10:21:37 - INFO - __main__ - Step 116865: {'lr': 5.933444307256575e-05, 'samples': 22438080, 'steps': 116864, 'loss/train': 1.5908410549163818} 08/31/2021 10:21:38 - INFO - __main__ - Step 116866: {'lr': 5.933101072933247e-05, 'samples': 22438272, 'steps': 116865, 'loss/train': 1.2804256677627563} 08/31/2021 10:21:38 - INFO - __main__ - Step 116867: {'lr': 5.932757847201159e-05, 'samples': 22438464, 'steps': 116866, 'loss/train': 1.7184165716171265} 08/31/2021 10:21:40 - INFO - __main__ - Step 116868: {'lr': 5.9324146300604786e-05, 'samples': 22438656, 'steps': 116867, 'loss/train': 0.022999027743935585} 08/31/2021 10:21:40 - INFO - __main__ - Step 116869: {'lr': 5.932071421511359e-05, 'samples': 22438848, 'steps': 116868, 'loss/train': 1.2681971788406372} 08/31/2021 10:21:41 - INFO - __main__ - Step 116870: {'lr': 5.93172822155395e-05, 'samples': 22439040, 'steps': 116869, 'loss/train': 0.11316939443349838} 08/31/2021 10:21:41 - INFO - __main__ - Step 116871: {'lr': 5.931385030188413e-05, 'samples': 22439232, 'steps': 116870, 'loss/train': 0.3619645833969116} 08/31/2021 10:21:41 - INFO - __main__ - Step 116872: {'lr': 5.9310418474149e-05, 'samples': 22439424, 'steps': 116871, 'loss/train': 1.4509499073028564} 08/31/2021 10:21:43 - INFO - __main__ - Step 116873: {'lr': 5.930698673233564e-05, 'samples': 22439616, 'steps': 116872, 'loss/train': 1.1929152011871338} 08/31/2021 10:21:44 - INFO - __main__ - Step 116874: {'lr': 5.930355507644561e-05, 'samples': 22439808, 'steps': 116873, 'loss/train': 0.8936673998832703} 08/31/2021 10:21:44 - INFO - __main__ - Step 116875: {'lr': 5.930012350648045e-05, 'samples': 22440000, 'steps': 116874, 'loss/train': 1.0913515090942383} 08/31/2021 10:21:44 - INFO - __main__ - Step 116876: {'lr': 5.92966920224417e-05, 'samples': 22440192, 'steps': 116875, 'loss/train': 1.2520925998687744} 08/31/2021 10:21:45 - INFO - __main__ - Step 116877: {'lr': 5.929326062433102e-05, 'samples': 22440384, 'steps': 116876, 'loss/train': 0.03611330687999725} 08/31/2021 10:21:46 - INFO - __main__ - Step 116878: {'lr': 5.928982931214977e-05, 'samples': 22440576, 'steps': 116877, 'loss/train': 1.4426652193069458} 08/31/2021 10:21:47 - INFO - __main__ - Step 116879: {'lr': 5.9286398085899586e-05, 'samples': 22440768, 'steps': 116878, 'loss/train': 1.2791414260864258} 08/31/2021 10:21:47 - INFO - __main__ - Step 116880: {'lr': 5.928296694558199e-05, 'samples': 22440960, 'steps': 116879, 'loss/train': 0.9016265869140625} 08/31/2021 10:21:47 - INFO - __main__ - Step 116881: {'lr': 5.9279535891198556e-05, 'samples': 22441152, 'steps': 116880, 'loss/train': 0.8650846481323242} 08/31/2021 10:21:48 - INFO - __main__ - Step 116882: {'lr': 5.927610492275082e-05, 'samples': 22441344, 'steps': 116881, 'loss/train': 1.1895556449890137} 08/31/2021 10:21:49 - INFO - __main__ - Step 116883: {'lr': 5.9272674040240334e-05, 'samples': 22441536, 'steps': 116882, 'loss/train': 1.0822163820266724} 08/31/2021 10:21:50 - INFO - __main__ - Step 116884: {'lr': 5.926924324366864e-05, 'samples': 22441728, 'steps': 116883, 'loss/train': 0.13367749750614166} 08/31/2021 10:21:50 - INFO - __main__ - Step 116885: {'lr': 5.926581253303728e-05, 'samples': 22441920, 'steps': 116884, 'loss/train': 1.8732562065124512} 08/31/2021 10:21:50 - INFO - __main__ - Step 116886: {'lr': 5.926238190834779e-05, 'samples': 22442112, 'steps': 116885, 'loss/train': 0.20830699801445007} 08/31/2021 10:21:51 - INFO - __main__ - Step 116887: {'lr': 5.92589513696018e-05, 'samples': 22442304, 'steps': 116886, 'loss/train': 1.73210871219635} 08/31/2021 10:21:52 - INFO - __main__ - Step 116888: {'lr': 5.9255520916800724e-05, 'samples': 22442496, 'steps': 116887, 'loss/train': 0.765373170375824} 08/31/2021 10:21:53 - INFO - __main__ - Step 116889: {'lr': 5.925209054994615e-05, 'samples': 22442688, 'steps': 116888, 'loss/train': 1.7784528732299805} 08/31/2021 10:21:53 - INFO - __main__ - Step 116890: {'lr': 5.9248660269039665e-05, 'samples': 22442880, 'steps': 116889, 'loss/train': 0.9108052253723145} 08/31/2021 10:21:53 - INFO - __main__ - Step 116891: {'lr': 5.924523007408278e-05, 'samples': 22443072, 'steps': 116890, 'loss/train': 1.461361050605774} 08/31/2021 10:21:54 - INFO - __main__ - Step 116892: {'lr': 5.9241799965077034e-05, 'samples': 22443264, 'steps': 116891, 'loss/train': 1.0187582969665527} 08/31/2021 10:21:54 - INFO - __main__ - Step 116893: {'lr': 5.9238369942024e-05, 'samples': 22443456, 'steps': 116892, 'loss/train': 2.564446449279785} 08/31/2021 10:21:56 - INFO - __main__ - Step 116894: {'lr': 5.923494000492521e-05, 'samples': 22443648, 'steps': 116893, 'loss/train': 1.0507285594940186} 08/31/2021 10:21:56 - INFO - __main__ - Step 116895: {'lr': 5.9231510153782224e-05, 'samples': 22443840, 'steps': 116894, 'loss/train': 1.7501074075698853} 08/31/2021 10:21:56 - INFO - __main__ - Step 116896: {'lr': 5.9228080388596587e-05, 'samples': 22444032, 'steps': 116895, 'loss/train': 0.7517327666282654} 08/31/2021 10:21:57 - INFO - __main__ - Step 116897: {'lr': 5.9224650709369804e-05, 'samples': 22444224, 'steps': 116896, 'loss/train': 1.6502506732940674} 08/31/2021 10:21:57 - INFO - __main__ - Step 116898: {'lr': 5.922122111610354e-05, 'samples': 22444416, 'steps': 116897, 'loss/train': 1.212507724761963} 08/31/2021 10:21:59 - INFO - __main__ - Step 116899: {'lr': 5.9217791608799174e-05, 'samples': 22444608, 'steps': 116898, 'loss/train': 0.21716688573360443} 08/31/2021 10:21:59 - INFO - __main__ - Step 116900: {'lr': 5.921436218745832e-05, 'samples': 22444800, 'steps': 116899, 'loss/train': 0.026728689670562744} 08/31/2021 10:21:59 - INFO - __main__ - Step 116901: {'lr': 5.921093285208254e-05, 'samples': 22444992, 'steps': 116900, 'loss/train': 0.5795738697052002} 08/31/2021 10:22:00 - INFO - __main__ - Step 116902: {'lr': 5.9207503602673354e-05, 'samples': 22445184, 'steps': 116901, 'loss/train': 1.1540238857269287} 08/31/2021 10:22:00 - INFO - __main__ - Step 116903: {'lr': 5.920407443923234e-05, 'samples': 22445376, 'steps': 116902, 'loss/train': 1.1887412071228027} 08/31/2021 10:22:02 - INFO - __main__ - Step 116904: {'lr': 5.920064536176101e-05, 'samples': 22445568, 'steps': 116903, 'loss/train': 0.876908004283905} 08/31/2021 10:22:03 - INFO - __main__ - Step 116905: {'lr': 5.919721637026093e-05, 'samples': 22445760, 'steps': 116904, 'loss/train': 0.6206759214401245} 08/31/2021 10:22:03 - INFO - __main__ - Step 116906: {'lr': 5.919378746473364e-05, 'samples': 22445952, 'steps': 116905, 'loss/train': 0.9472579956054688} 08/31/2021 10:22:03 - INFO - __main__ - Step 116907: {'lr': 5.9190358645180713e-05, 'samples': 22446144, 'steps': 116906, 'loss/train': 0.6060015559196472} 08/31/2021 10:22:04 - INFO - __main__ - Step 116908: {'lr': 5.9186929911603624e-05, 'samples': 22446336, 'steps': 116907, 'loss/train': 1.155671238899231} 08/31/2021 10:22:05 - INFO - __main__ - Step 116909: {'lr': 5.918350126400407e-05, 'samples': 22446528, 'steps': 116908, 'loss/train': 1.5195097923278809} 08/31/2021 10:22:06 - INFO - __main__ - Step 116910: {'lr': 5.918007270238337e-05, 'samples': 22446720, 'steps': 116909, 'loss/train': 1.0298811197280884} 08/31/2021 10:22:06 - INFO - __main__ - Step 116911: {'lr': 5.917664422674321e-05, 'samples': 22446912, 'steps': 116910, 'loss/train': 0.9136332273483276} 08/31/2021 10:22:06 - INFO - __main__ - Step 116912: {'lr': 5.917321583708513e-05, 'samples': 22447104, 'steps': 116911, 'loss/train': 1.3057684898376465} 08/31/2021 10:22:07 - INFO - __main__ - Step 116913: {'lr': 5.9169787533410625e-05, 'samples': 22447296, 'steps': 116912, 'loss/train': 1.0388541221618652} 08/31/2021 10:22:09 - INFO - __main__ - Step 116914: {'lr': 5.9166359315721256e-05, 'samples': 22447488, 'steps': 116913, 'loss/train': 1.0324476957321167} 08/31/2021 10:22:09 - INFO - __main__ - Step 116915: {'lr': 5.9162931184018606e-05, 'samples': 22447680, 'steps': 116914, 'loss/train': 1.3218369483947754} 08/31/2021 10:22:09 - INFO - __main__ - Step 116916: {'lr': 5.915950313830421e-05, 'samples': 22447872, 'steps': 116915, 'loss/train': 0.9350351095199585} 08/31/2021 10:22:10 - INFO - __main__ - Step 116917: {'lr': 5.915607517857957e-05, 'samples': 22448064, 'steps': 116916, 'loss/train': 1.4416372776031494} 08/31/2021 10:22:10 - INFO - __main__ - Step 116918: {'lr': 5.9152647304846265e-05, 'samples': 22448256, 'steps': 116917, 'loss/train': 1.6858710050582886} 08/31/2021 10:22:11 - INFO - __main__ - Step 116919: {'lr': 5.914921951710583e-05, 'samples': 22448448, 'steps': 116918, 'loss/train': 1.2080813646316528} 08/31/2021 10:22:12 - INFO - __main__ - Step 116920: {'lr': 5.914579181535981e-05, 'samples': 22448640, 'steps': 116919, 'loss/train': 0.7125935554504395} 08/31/2021 10:22:12 - INFO - __main__ - Step 116921: {'lr': 5.914236419960983e-05, 'samples': 22448832, 'steps': 116920, 'loss/train': 1.3996552228927612} 08/31/2021 10:22:13 - INFO - __main__ - Step 116922: {'lr': 5.9138936669857286e-05, 'samples': 22449024, 'steps': 116921, 'loss/train': 0.8851566314697266} 08/31/2021 10:22:13 - INFO - __main__ - Step 116923: {'lr': 5.913550922610378e-05, 'samples': 22449216, 'steps': 116922, 'loss/train': 1.1405271291732788} 08/31/2021 10:22:15 - INFO - __main__ - Step 116924: {'lr': 5.9132081868350866e-05, 'samples': 22449408, 'steps': 116923, 'loss/train': 0.9405675530433655} 08/31/2021 10:22:15 - INFO - __main__ - Step 116925: {'lr': 5.9128654596600104e-05, 'samples': 22449600, 'steps': 116924, 'loss/train': 0.6423358917236328} 08/31/2021 10:22:15 - INFO - __main__ - Step 116926: {'lr': 5.912522741085302e-05, 'samples': 22449792, 'steps': 116925, 'loss/train': 1.1707850694656372} 08/31/2021 10:22:16 - INFO - __main__ - Step 116927: {'lr': 5.912180031111117e-05, 'samples': 22449984, 'steps': 116926, 'loss/train': 0.9626770615577698} 08/31/2021 10:22:16 - INFO - __main__ - Step 116928: {'lr': 5.911837329737607e-05, 'samples': 22450176, 'steps': 116927, 'loss/train': 0.9439370632171631} 08/31/2021 10:22:16 - INFO - __main__ - Step 116929: {'lr': 5.9114946369649316e-05, 'samples': 22450368, 'steps': 116928, 'loss/train': 0.7268680334091187} 08/31/2021 10:22:18 - INFO - __main__ - Step 116930: {'lr': 5.91115195279324e-05, 'samples': 22450560, 'steps': 116929, 'loss/train': 0.8166864514350891} 08/31/2021 10:22:18 - INFO - __main__ - Step 116931: {'lr': 5.9108092772226896e-05, 'samples': 22450752, 'steps': 116930, 'loss/train': 0.7423323392868042} 08/31/2021 10:22:19 - INFO - __main__ - Step 116932: {'lr': 5.9104666102534345e-05, 'samples': 22450944, 'steps': 116931, 'loss/train': 1.5928548574447632} 08/31/2021 10:22:19 - INFO - __main__ - Step 116933: {'lr': 5.910123951885626e-05, 'samples': 22451136, 'steps': 116932, 'loss/train': 1.3810362815856934} 08/31/2021 10:22:19 - INFO - __main__ - Step 116934: {'lr': 5.90978130211943e-05, 'samples': 22451328, 'steps': 116933, 'loss/train': 1.5380568504333496} 08/31/2021 10:22:21 - INFO - __main__ - Step 116935: {'lr': 5.9094386609549855e-05, 'samples': 22451520, 'steps': 116934, 'loss/train': 1.054958462715149} 08/31/2021 10:22:22 - INFO - __main__ - Step 116936: {'lr': 5.909096028392452e-05, 'samples': 22451712, 'steps': 116935, 'loss/train': 1.2498234510421753} 08/31/2021 10:22:22 - INFO - __main__ - Step 116937: {'lr': 5.908753404431985e-05, 'samples': 22451904, 'steps': 116936, 'loss/train': 1.2197879552841187} 08/31/2021 10:22:23 - INFO - __main__ - Step 116938: {'lr': 5.90841078907374e-05, 'samples': 22452096, 'steps': 116937, 'loss/train': 0.8656111359596252} 08/31/2021 10:22:23 - INFO - __main__ - Step 116939: {'lr': 5.908068182317872e-05, 'samples': 22452288, 'steps': 116938, 'loss/train': 0.7856552600860596} 08/31/2021 10:22:23 - INFO - __main__ - Step 116940: {'lr': 5.907725584164533e-05, 'samples': 22452480, 'steps': 116939, 'loss/train': 1.3256008625030518} 08/31/2021 10:22:25 - INFO - __main__ - Step 116941: {'lr': 5.907382994613877e-05, 'samples': 22452672, 'steps': 116940, 'loss/train': 0.022332120686769485} 08/31/2021 10:22:25 - INFO - __main__ - Step 116942: {'lr': 5.9070404136660594e-05, 'samples': 22452864, 'steps': 116941, 'loss/train': 1.5820879936218262} 08/31/2021 10:22:26 - INFO - __main__ - Step 116943: {'lr': 5.9066978413212374e-05, 'samples': 22453056, 'steps': 116942, 'loss/train': 1.359456181526184} 08/31/2021 10:22:26 - INFO - __main__ - Step 116944: {'lr': 5.906355277579559e-05, 'samples': 22453248, 'steps': 116943, 'loss/train': 1.000854253768921} 08/31/2021 10:22:26 - INFO - __main__ - Step 116945: {'lr': 5.906012722441184e-05, 'samples': 22453440, 'steps': 116944, 'loss/train': 0.4962223768234253} 08/31/2021 10:22:28 - INFO - __main__ - Step 116946: {'lr': 5.905670175906266e-05, 'samples': 22453632, 'steps': 116945, 'loss/train': 0.8700311183929443} 08/31/2021 10:22:28 - INFO - __main__ - Step 116947: {'lr': 5.9053276379749584e-05, 'samples': 22453824, 'steps': 116946, 'loss/train': 1.0998488664627075} 08/31/2021 10:22:28 - INFO - __main__ - Step 116948: {'lr': 5.90498510864742e-05, 'samples': 22454016, 'steps': 116947, 'loss/train': 0.9138337969779968} 08/31/2021 10:22:29 - INFO - __main__ - Step 116949: {'lr': 5.904642587923797e-05, 'samples': 22454208, 'steps': 116948, 'loss/train': 1.2327574491500854} 08/31/2021 10:22:29 - INFO - __main__ - Step 116950: {'lr': 5.904300075804245e-05, 'samples': 22454400, 'steps': 116949, 'loss/train': 0.518307626247406} 08/31/2021 10:22:31 - INFO - __main__ - Step 116951: {'lr': 5.903957572288923e-05, 'samples': 22454592, 'steps': 116950, 'loss/train': 1.4759036302566528} 08/31/2021 10:22:31 - INFO - __main__ - Step 116952: {'lr': 5.90361507737798e-05, 'samples': 22454784, 'steps': 116951, 'loss/train': 1.6200131177902222} 08/31/2021 10:22:31 - INFO - __main__ - Step 116953: {'lr': 5.903272591071576e-05, 'samples': 22454976, 'steps': 116952, 'loss/train': 0.28720641136169434} 08/31/2021 10:22:32 - INFO - __main__ - Step 116954: {'lr': 5.902930113369862e-05, 'samples': 22455168, 'steps': 116953, 'loss/train': 2.067105293273926} 08/31/2021 10:22:32 - INFO - __main__ - Step 116955: {'lr': 5.902587644272991e-05, 'samples': 22455360, 'steps': 116954, 'loss/train': 1.0366175174713135} 08/31/2021 10:22:34 - INFO - __main__ - Step 116956: {'lr': 5.902245183781122e-05, 'samples': 22455552, 'steps': 116955, 'loss/train': 1.9196398258209229} 08/31/2021 10:22:34 - INFO - __main__ - Step 116957: {'lr': 5.901902731894404e-05, 'samples': 22455744, 'steps': 116956, 'loss/train': 0.6408730149269104} 08/31/2021 10:22:35 - INFO - __main__ - Step 116958: {'lr': 5.901560288612998e-05, 'samples': 22455936, 'steps': 116957, 'loss/train': 1.313310980796814} 08/31/2021 10:22:35 - INFO - __main__ - Step 116959: {'lr': 5.901217853937049e-05, 'samples': 22456128, 'steps': 116958, 'loss/train': 1.0071320533752441} 08/31/2021 10:22:35 - INFO - __main__ - Step 116960: {'lr': 5.9008754278667196e-05, 'samples': 22456320, 'steps': 116959, 'loss/train': 1.114277958869934} 08/31/2021 10:22:36 - INFO - __main__ - Step 116961: {'lr': 5.9005330104021675e-05, 'samples': 22456512, 'steps': 116960, 'loss/train': 1.1527113914489746} 08/31/2021 10:22:38 - INFO - __main__ - Step 116962: {'lr': 5.9001906015435344e-05, 'samples': 22456704, 'steps': 116961, 'loss/train': 1.0792127847671509} 08/31/2021 10:22:38 - INFO - __main__ - Step 116963: {'lr': 5.8998482012909804e-05, 'samples': 22456896, 'steps': 116962, 'loss/train': 1.4176740646362305} 08/31/2021 10:22:38 - INFO - __main__ - Step 116964: {'lr': 5.899505809644659e-05, 'samples': 22457088, 'steps': 116963, 'loss/train': 0.8926556706428528} 08/31/2021 10:22:39 - INFO - __main__ - Step 116965: {'lr': 5.8991634266047254e-05, 'samples': 22457280, 'steps': 116964, 'loss/train': 1.4137952327728271} 08/31/2021 10:22:39 - INFO - __main__ - Step 116966: {'lr': 5.8988210521713355e-05, 'samples': 22457472, 'steps': 116965, 'loss/train': 1.3171340227127075} 08/31/2021 10:22:41 - INFO - __main__ - Step 116967: {'lr': 5.898478686344641e-05, 'samples': 22457664, 'steps': 116966, 'loss/train': 1.3025949001312256} 08/31/2021 10:22:41 - INFO - __main__ - Step 116968: {'lr': 5.898136329124798e-05, 'samples': 22457856, 'steps': 116967, 'loss/train': 1.393957257270813} 08/31/2021 10:22:41 - INFO - __main__ - Step 116969: {'lr': 5.897793980511959e-05, 'samples': 22458048, 'steps': 116968, 'loss/train': 1.9200634956359863} 08/31/2021 10:22:42 - INFO - __main__ - Step 116970: {'lr': 5.8974516405062824e-05, 'samples': 22458240, 'steps': 116969, 'loss/train': 1.1010761260986328} 08/31/2021 10:22:42 - INFO - __main__ - Step 116971: {'lr': 5.8971093091079145e-05, 'samples': 22458432, 'steps': 116970, 'loss/train': 0.9035027027130127} 08/31/2021 10:22:44 - INFO - __main__ - Step 116972: {'lr': 5.8967669863170175e-05, 'samples': 22458624, 'steps': 116971, 'loss/train': 0.9748365879058838} 08/31/2021 10:22:44 - INFO - __main__ - Step 116973: {'lr': 5.8964246721337404e-05, 'samples': 22458816, 'steps': 116972, 'loss/train': 1.0183532238006592} 08/31/2021 10:22:45 - INFO - __main__ - Step 116974: {'lr': 5.89608236655825e-05, 'samples': 22459008, 'steps': 116973, 'loss/train': 1.5208234786987305} 08/31/2021 10:22:45 - INFO - __main__ - Step 116975: {'lr': 5.89574006959068e-05, 'samples': 22459200, 'steps': 116974, 'loss/train': 0.3809818923473358} 08/31/2021 10:22:45 - INFO - __main__ - Step 116976: {'lr': 5.895397781231196e-05, 'samples': 22459392, 'steps': 116975, 'loss/train': 0.9616490006446838} 08/31/2021 10:22:47 - INFO - __main__ - Step 116977: {'lr': 5.895055501479951e-05, 'samples': 22459584, 'steps': 116976, 'loss/train': 0.8554218411445618} 08/31/2021 10:22:47 - INFO - __main__ - Step 116978: {'lr': 5.894713230337098e-05, 'samples': 22459776, 'steps': 116977, 'loss/train': 1.1580898761749268} 08/31/2021 10:22:48 - INFO - __main__ - Step 116979: {'lr': 5.894370967802793e-05, 'samples': 22459968, 'steps': 116978, 'loss/train': 0.9125520586967468} 08/31/2021 10:22:48 - INFO - __main__ - Step 116980: {'lr': 5.8940287138771895e-05, 'samples': 22460160, 'steps': 116979, 'loss/train': 1.5464638471603394} 08/31/2021 10:22:48 - INFO - __main__ - Step 116981: {'lr': 5.893686468560444e-05, 'samples': 22460352, 'steps': 116980, 'loss/train': 0.7522566914558411} 08/31/2021 10:22:50 - INFO - __main__ - Step 116982: {'lr': 5.893344231852707e-05, 'samples': 22460544, 'steps': 116981, 'loss/train': 0.20433203876018524} 08/31/2021 10:22:50 - INFO - __main__ - Step 116983: {'lr': 5.8930020037541335e-05, 'samples': 22460736, 'steps': 116982, 'loss/train': 1.1505621671676636} 08/31/2021 10:22:51 - INFO - __main__ - Step 116984: {'lr': 5.8926597842648784e-05, 'samples': 22460928, 'steps': 116983, 'loss/train': 1.4874497652053833} 08/31/2021 10:22:51 - INFO - __main__ - Step 116985: {'lr': 5.8923175733850945e-05, 'samples': 22461120, 'steps': 116984, 'loss/train': 0.7953720688819885} 08/31/2021 10:22:51 - INFO - __main__ - Step 116986: {'lr': 5.891975371114941e-05, 'samples': 22461312, 'steps': 116985, 'loss/train': 1.6499302387237549} 08/31/2021 10:22:52 - INFO - __main__ - Step 116987: {'lr': 5.8916331774545665e-05, 'samples': 22461504, 'steps': 116986, 'loss/train': 0.4922773241996765} 08/31/2021 10:22:53 - INFO - __main__ - Step 116988: {'lr': 5.8912909924041355e-05, 'samples': 22461696, 'steps': 116987, 'loss/train': 0.23807530105113983} 08/31/2021 10:22:54 - INFO - __main__ - Step 116989: {'lr': 5.890948815963787e-05, 'samples': 22461888, 'steps': 116988, 'loss/train': 1.3368908166885376} 08/31/2021 10:22:54 - INFO - __main__ - Step 116990: {'lr': 5.8906066481336815e-05, 'samples': 22462080, 'steps': 116989, 'loss/train': 0.9193402528762817} 08/31/2021 10:22:54 - INFO - __main__ - Step 116991: {'lr': 5.890264488913971e-05, 'samples': 22462272, 'steps': 116990, 'loss/train': 1.2804588079452515} 08/31/2021 10:22:55 - INFO - __main__ - Step 116992: {'lr': 5.889922338304815e-05, 'samples': 22462464, 'steps': 116991, 'loss/train': 1.7543413639068604} 08/31/2021 10:22:56 - INFO - __main__ - Step 116993: {'lr': 5.8895801963063656e-05, 'samples': 22462656, 'steps': 116992, 'loss/train': 1.623081088066101} 08/31/2021 10:22:57 - INFO - __main__ - Step 116994: {'lr': 5.889238062918775e-05, 'samples': 22462848, 'steps': 116993, 'loss/train': 1.1193863153457642} 08/31/2021 10:22:57 - INFO - __main__ - Step 116995: {'lr': 5.8888959381422025e-05, 'samples': 22463040, 'steps': 116994, 'loss/train': 0.9225102066993713} 08/31/2021 10:22:57 - INFO - __main__ - Step 116996: {'lr': 5.8885538219767944e-05, 'samples': 22463232, 'steps': 116995, 'loss/train': 1.3804248571395874} 08/31/2021 10:22:58 - INFO - __main__ - Step 116997: {'lr': 5.8882117144227115e-05, 'samples': 22463424, 'steps': 116996, 'loss/train': 1.1748913526535034} 08/31/2021 10:22:58 - INFO - __main__ - Step 116998: {'lr': 5.887869615480104e-05, 'samples': 22463616, 'steps': 116997, 'loss/train': 1.2308082580566406} 08/31/2021 10:22:59 - INFO - __main__ - Step 116999: {'lr': 5.887527525149128e-05, 'samples': 22463808, 'steps': 116998, 'loss/train': 1.3120434284210205} 08/31/2021 10:23:00 - INFO - __main__ - Step 117000: {'lr': 5.8871854434299375e-05, 'samples': 22464000, 'steps': 116999, 'loss/train': 0.8004015684127808} 08/31/2021 10:23:00 - INFO - __main__ - Step 117001: {'lr': 5.886843370322692e-05, 'samples': 22464192, 'steps': 117000, 'loss/train': 1.017519474029541} 08/31/2021 10:23:01 - INFO - __main__ - Step 117002: {'lr': 5.8865013058275354e-05, 'samples': 22464384, 'steps': 117001, 'loss/train': 1.7363853454589844} 08/31/2021 10:23:01 - INFO - __main__ - Step 117003: {'lr': 5.8861592499446225e-05, 'samples': 22464576, 'steps': 117002, 'loss/train': 1.5425083637237549} 08/31/2021 10:23:03 - INFO - __main__ - Step 117004: {'lr': 5.885817202674115e-05, 'samples': 22464768, 'steps': 117003, 'loss/train': 1.0105317831039429} 08/31/2021 10:23:03 - INFO - __main__ - Step 117005: {'lr': 5.8854751640161633e-05, 'samples': 22464960, 'steps': 117004, 'loss/train': 1.0196963548660278} 08/31/2021 10:23:03 - INFO - __main__ - Step 117006: {'lr': 5.8851331339709186e-05, 'samples': 22465152, 'steps': 117005, 'loss/train': 1.4281964302062988} 08/31/2021 10:23:04 - INFO - __main__ - Step 117007: {'lr': 5.88479111253854e-05, 'samples': 22465344, 'steps': 117006, 'loss/train': 0.9226406216621399} 08/31/2021 10:23:04 - INFO - __main__ - Step 117008: {'lr': 5.88444909971918e-05, 'samples': 22465536, 'steps': 117007, 'loss/train': 1.3371284008026123} 08/31/2021 10:23:06 - INFO - __main__ - Step 117009: {'lr': 5.8841070955129916e-05, 'samples': 22465728, 'steps': 117008, 'loss/train': 0.815194308757782} 08/31/2021 10:23:06 - INFO - __main__ - Step 117010: {'lr': 5.883765099920127e-05, 'samples': 22465920, 'steps': 117009, 'loss/train': 1.6302820444107056} 08/31/2021 10:23:06 - INFO - __main__ - Step 117011: {'lr': 5.8834231129407476e-05, 'samples': 22466112, 'steps': 117010, 'loss/train': 1.0486562252044678} 08/31/2021 10:23:07 - INFO - __main__ - Step 117012: {'lr': 5.8830811345749995e-05, 'samples': 22466304, 'steps': 117011, 'loss/train': 1.1352781057357788} 08/31/2021 10:23:07 - INFO - __main__ - Step 117013: {'lr': 5.882739164823039e-05, 'samples': 22466496, 'steps': 117012, 'loss/train': 0.9832732081413269} 08/31/2021 10:23:09 - INFO - __main__ - Step 117014: {'lr': 5.882397203685025e-05, 'samples': 22466688, 'steps': 117013, 'loss/train': 0.6482927799224854} 08/31/2021 10:23:09 - INFO - __main__ - Step 117015: {'lr': 5.882055251161114e-05, 'samples': 22466880, 'steps': 117014, 'loss/train': 1.4577440023422241} 08/31/2021 10:23:10 - INFO - __main__ - Step 117016: {'lr': 5.8817133072514463e-05, 'samples': 22467072, 'steps': 117015, 'loss/train': 1.304749608039856} 08/31/2021 10:23:10 - INFO - __main__ - Step 117017: {'lr': 5.881371371956182e-05, 'samples': 22467264, 'steps': 117016, 'loss/train': 1.3758174180984497} 08/31/2021 10:23:11 - INFO - __main__ - Step 117018: {'lr': 5.881029445275476e-05, 'samples': 22467456, 'steps': 117017, 'loss/train': 0.9001585841178894} 08/31/2021 10:23:12 - INFO - __main__ - Step 117019: {'lr': 5.880687527209486e-05, 'samples': 22467648, 'steps': 117018, 'loss/train': 1.0278996229171753} 08/31/2021 10:23:12 - INFO - __main__ - Step 117020: {'lr': 5.880345617758362e-05, 'samples': 22467840, 'steps': 117019, 'loss/train': 0.7955520153045654} 08/31/2021 10:23:13 - INFO - __main__ - Step 117021: {'lr': 5.880003716922261e-05, 'samples': 22468032, 'steps': 117020, 'loss/train': 0.6131053566932678} 08/31/2021 10:23:13 - INFO - __main__ - Step 117022: {'lr': 5.879661824701332e-05, 'samples': 22468224, 'steps': 117021, 'loss/train': 1.3108513355255127} 08/31/2021 10:23:13 - INFO - __main__ - Step 117023: {'lr': 5.879319941095734e-05, 'samples': 22468416, 'steps': 117022, 'loss/train': 0.9428268671035767} 08/31/2021 10:23:15 - INFO - __main__ - Step 117024: {'lr': 5.8789780661056194e-05, 'samples': 22468608, 'steps': 117023, 'loss/train': 1.0234042406082153} 08/31/2021 10:23:15 - INFO - __main__ - Step 117025: {'lr': 5.8786361997311436e-05, 'samples': 22468800, 'steps': 117024, 'loss/train': 1.015938401222229} 08/31/2021 10:23:16 - INFO - __main__ - Step 117026: {'lr': 5.8782943419724565e-05, 'samples': 22468992, 'steps': 117025, 'loss/train': 1.9456905126571655} 08/31/2021 10:23:16 - INFO - __main__ - Step 117027: {'lr': 5.877952492829716e-05, 'samples': 22469184, 'steps': 117026, 'loss/train': 1.2918168306350708} 08/31/2021 10:23:16 - INFO - __main__ - Step 117028: {'lr': 5.8776106523030835e-05, 'samples': 22469376, 'steps': 117027, 'loss/train': 1.1012156009674072} 08/31/2021 10:23:18 - INFO - __main__ - Step 117029: {'lr': 5.877268820392698e-05, 'samples': 22469568, 'steps': 117028, 'loss/train': 1.3808820247650146} 08/31/2021 10:23:18 - INFO - __main__ - Step 117030: {'lr': 5.876926997098717e-05, 'samples': 22469760, 'steps': 117029, 'loss/train': 1.3031535148620605} 08/31/2021 10:23:19 - INFO - __main__ - Step 117031: {'lr': 5.8765851824212984e-05, 'samples': 22469952, 'steps': 117030, 'loss/train': 1.4207853078842163} 08/31/2021 10:23:19 - INFO - __main__ - Step 117032: {'lr': 5.876243376360596e-05, 'samples': 22470144, 'steps': 117031, 'loss/train': 0.7206264138221741} 08/31/2021 10:23:20 - INFO - __main__ - Step 117033: {'lr': 5.8759015789167646e-05, 'samples': 22470336, 'steps': 117032, 'loss/train': 1.1168876886367798} 08/31/2021 10:23:20 - INFO - __main__ - Step 117034: {'lr': 5.875559790089957e-05, 'samples': 22470528, 'steps': 117033, 'loss/train': 1.517799735069275} 08/31/2021 10:23:21 - INFO - __main__ - Step 117035: {'lr': 5.875218009880323e-05, 'samples': 22470720, 'steps': 117034, 'loss/train': 0.9485505819320679} 08/31/2021 10:23:22 - INFO - __main__ - Step 117036: {'lr': 5.8748762382880236e-05, 'samples': 22470912, 'steps': 117035, 'loss/train': 1.0755560398101807} 08/31/2021 10:23:22 - INFO - __main__ - Step 117037: {'lr': 5.874534475313212e-05, 'samples': 22471104, 'steps': 117036, 'loss/train': 1.558415412902832} 08/31/2021 10:23:23 - INFO - __main__ - Step 117038: {'lr': 5.874192720956037e-05, 'samples': 22471296, 'steps': 117037, 'loss/train': 1.0796446800231934} 08/31/2021 10:23:23 - INFO - __main__ - Step 117039: {'lr': 5.873850975216655e-05, 'samples': 22471488, 'steps': 117038, 'loss/train': 1.4111342430114746} 08/31/2021 10:23:25 - INFO - __main__ - Step 117040: {'lr': 5.873509238095223e-05, 'samples': 22471680, 'steps': 117039, 'loss/train': 1.3546756505966187} 08/31/2021 10:23:25 - INFO - __main__ - Step 117041: {'lr': 5.873167509591892e-05, 'samples': 22471872, 'steps': 117040, 'loss/train': 0.9425192475318909} 08/31/2021 10:23:26 - INFO - __main__ - Step 117042: {'lr': 5.8728257897068234e-05, 'samples': 22472064, 'steps': 117041, 'loss/train': 1.3517441749572754} 08/31/2021 10:23:26 - INFO - __main__ - Step 117043: {'lr': 5.872484078440154e-05, 'samples': 22472256, 'steps': 117042, 'loss/train': 0.802786648273468} 08/31/2021 10:23:26 - INFO - __main__ - Step 117044: {'lr': 5.872142375792053e-05, 'samples': 22472448, 'steps': 117043, 'loss/train': 1.7465262413024902} 08/31/2021 10:23:28 - INFO - __main__ - Step 117045: {'lr': 5.871800681762668e-05, 'samples': 22472640, 'steps': 117044, 'loss/train': 0.07854349911212921} 08/31/2021 10:23:28 - INFO - __main__ - Step 117046: {'lr': 5.8714589963521524e-05, 'samples': 22472832, 'steps': 117045, 'loss/train': 1.1989833116531372} 08/31/2021 10:23:29 - INFO - __main__ - Step 117047: {'lr': 5.871117319560665e-05, 'samples': 22473024, 'steps': 117046, 'loss/train': 1.4841176271438599} 08/31/2021 10:23:29 - INFO - __main__ - Step 117048: {'lr': 5.8707756513883546e-05, 'samples': 22473216, 'steps': 117047, 'loss/train': 0.8663195967674255} 08/31/2021 10:23:29 - INFO - __main__ - Step 117049: {'lr': 5.8704339918353806e-05, 'samples': 22473408, 'steps': 117048, 'loss/train': 0.8326785564422607} 08/31/2021 10:23:31 - INFO - __main__ - Step 117050: {'lr': 5.870092340901892e-05, 'samples': 22473600, 'steps': 117049, 'loss/train': 1.1554549932479858} 08/31/2021 10:23:31 - INFO - __main__ - Step 117051: {'lr': 5.8697506985880446e-05, 'samples': 22473792, 'steps': 117050, 'loss/train': 1.1782115697860718} 08/31/2021 10:23:32 - INFO - __main__ - Step 117052: {'lr': 5.869409064893991e-05, 'samples': 22473984, 'steps': 117051, 'loss/train': 0.6941502690315247} 08/31/2021 10:23:32 - INFO - __main__ - Step 117053: {'lr': 5.869067439819889e-05, 'samples': 22474176, 'steps': 117052, 'loss/train': 0.3959391415119171} 08/31/2021 10:23:32 - INFO - __main__ - Step 117054: {'lr': 5.868725823365889e-05, 'samples': 22474368, 'steps': 117053, 'loss/train': 1.0456606149673462} 08/31/2021 10:23:34 - INFO - __main__ - Step 117055: {'lr': 5.868384215532152e-05, 'samples': 22474560, 'steps': 117054, 'loss/train': 0.5705899596214294} 08/31/2021 10:23:34 - INFO - __main__ - Step 117056: {'lr': 5.8680426163188195e-05, 'samples': 22474752, 'steps': 117055, 'loss/train': 0.9975343942642212} 08/31/2021 10:23:35 - INFO - __main__ - Step 117057: {'lr': 5.867701025726052e-05, 'samples': 22474944, 'steps': 117056, 'loss/train': 1.501469612121582} 08/31/2021 10:23:35 - INFO - __main__ - Step 117058: {'lr': 5.867359443754003e-05, 'samples': 22475136, 'steps': 117057, 'loss/train': 1.2939199209213257} 08/31/2021 10:23:35 - INFO - __main__ - Step 117059: {'lr': 5.867017870402827e-05, 'samples': 22475328, 'steps': 117058, 'loss/train': 1.0994207859039307} 08/31/2021 10:23:36 - INFO - __main__ - Step 117060: {'lr': 5.8666763056726777e-05, 'samples': 22475520, 'steps': 117059, 'loss/train': 0.7662224173545837} 08/31/2021 10:23:37 - INFO - __main__ - Step 117061: {'lr': 5.866334749563707e-05, 'samples': 22475712, 'steps': 117060, 'loss/train': 0.8123913407325745} 08/31/2021 10:23:38 - INFO - __main__ - Step 117062: {'lr': 5.865993202076073e-05, 'samples': 22475904, 'steps': 117061, 'loss/train': 0.8971447348594666} 08/31/2021 10:23:38 - INFO - __main__ - Step 117063: {'lr': 5.865651663209925e-05, 'samples': 22476096, 'steps': 117062, 'loss/train': 1.581874966621399} 08/31/2021 10:23:38 - INFO - __main__ - Step 117064: {'lr': 5.865310132965421e-05, 'samples': 22476288, 'steps': 117063, 'loss/train': 0.9495821595191956} 08/31/2021 10:23:39 - INFO - __main__ - Step 117065: {'lr': 5.864968611342711e-05, 'samples': 22476480, 'steps': 117064, 'loss/train': 1.4252362251281738} 08/31/2021 10:23:40 - INFO - __main__ - Step 117066: {'lr': 5.8646270983419515e-05, 'samples': 22476672, 'steps': 117065, 'loss/train': 1.5566257238388062} 08/31/2021 10:23:41 - INFO - __main__ - Step 117067: {'lr': 5.864285593963298e-05, 'samples': 22476864, 'steps': 117066, 'loss/train': 0.33120623230934143} 08/31/2021 10:23:41 - INFO - __main__ - Step 117068: {'lr': 5.8639440982068995e-05, 'samples': 22477056, 'steps': 117067, 'loss/train': 1.487004280090332} 08/31/2021 10:23:41 - INFO - __main__ - Step 117069: {'lr': 5.863602611072921e-05, 'samples': 22477248, 'steps': 117068, 'loss/train': 0.9311383366584778} 08/31/2021 10:23:42 - INFO - __main__ - Step 117070: {'lr': 5.863261132561501e-05, 'samples': 22477440, 'steps': 117069, 'loss/train': 1.3030924797058105} 08/31/2021 10:23:44 - INFO - __main__ - Step 117071: {'lr': 5.8629196626728e-05, 'samples': 22477632, 'steps': 117070, 'loss/train': 0.6819160580635071} 08/31/2021 10:23:44 - INFO - __main__ - Step 117072: {'lr': 5.8625782014069706e-05, 'samples': 22477824, 'steps': 117071, 'loss/train': 0.945187509059906} 08/31/2021 10:23:45 - INFO - __main__ - Step 117073: {'lr': 5.8622367487641685e-05, 'samples': 22478016, 'steps': 117072, 'loss/train': 1.004134178161621} 08/31/2021 10:23:45 - INFO - __main__ - Step 117074: {'lr': 5.8618953047445494e-05, 'samples': 22478208, 'steps': 117073, 'loss/train': 1.1719343662261963} 08/31/2021 10:23:45 - INFO - __main__ - Step 117075: {'lr': 5.861553869348263e-05, 'samples': 22478400, 'steps': 117074, 'loss/train': 1.273659586906433} 08/31/2021 10:23:47 - INFO - __main__ - Step 117076: {'lr': 5.861212442575464e-05, 'samples': 22478592, 'steps': 117075, 'loss/train': 0.46574246883392334} 08/31/2021 10:23:47 - INFO - __main__ - Step 117077: {'lr': 5.860871024426309e-05, 'samples': 22478784, 'steps': 117076, 'loss/train': 1.6489824056625366} 08/31/2021 10:23:48 - INFO - __main__ - Step 117078: {'lr': 5.86052961490095e-05, 'samples': 22478976, 'steps': 117077, 'loss/train': 1.5261257886886597} 08/31/2021 10:23:48 - INFO - __main__ - Step 117079: {'lr': 5.8601882139995426e-05, 'samples': 22479168, 'steps': 117078, 'loss/train': 1.3240432739257812} 08/31/2021 10:23:49 - INFO - __main__ - Step 117080: {'lr': 5.859846821722237e-05, 'samples': 22479360, 'steps': 117079, 'loss/train': 1.2829746007919312} 08/31/2021 10:23:50 - INFO - __main__ - Step 117081: {'lr': 5.85950543806919e-05, 'samples': 22479552, 'steps': 117080, 'loss/train': 1.178383231163025} 08/31/2021 10:23:51 - INFO - __main__ - Step 117082: {'lr': 5.859164063040562e-05, 'samples': 22479744, 'steps': 117081, 'loss/train': 1.026890516281128} 08/31/2021 10:23:51 - INFO - __main__ - Step 117083: {'lr': 5.85882269663649e-05, 'samples': 22479936, 'steps': 117082, 'loss/train': 0.02957995980978012} 08/31/2021 10:23:51 - INFO - __main__ - Step 117084: {'lr': 5.858481338857138e-05, 'samples': 22480128, 'steps': 117083, 'loss/train': 0.8467444181442261} 08/31/2021 10:23:52 - INFO - __main__ - Step 117085: {'lr': 5.85813998970266e-05, 'samples': 22480320, 'steps': 117084, 'loss/train': 1.311384677886963} 08/31/2021 10:23:53 - INFO - __main__ - Step 117086: {'lr': 5.857798649173207e-05, 'samples': 22480512, 'steps': 117085, 'loss/train': 0.6989132165908813} 08/31/2021 10:23:54 - INFO - __main__ - Step 117087: {'lr': 5.8574573172689356e-05, 'samples': 22480704, 'steps': 117086, 'loss/train': 1.298075556755066} 08/31/2021 10:23:54 - INFO - __main__ - Step 117088: {'lr': 5.857115993990001e-05, 'samples': 22480896, 'steps': 117087, 'loss/train': 0.9114381074905396} 08/31/2021 10:23:54 - INFO - __main__ - Step 117089: {'lr': 5.856774679336552e-05, 'samples': 22481088, 'steps': 117088, 'loss/train': 0.9191036820411682} 08/31/2021 10:23:55 - INFO - __main__ - Step 117090: {'lr': 5.856433373308745e-05, 'samples': 22481280, 'steps': 117089, 'loss/train': 1.5194005966186523} 08/31/2021 10:23:56 - INFO - __main__ - Step 117091: {'lr': 5.856092075906733e-05, 'samples': 22481472, 'steps': 117090, 'loss/train': 1.4205013513565063} 08/31/2021 10:23:57 - INFO - __main__ - Step 117092: {'lr': 5.8557507871306705e-05, 'samples': 22481664, 'steps': 117091, 'loss/train': 1.3822858333587646} 08/31/2021 10:23:57 - INFO - __main__ - Step 117093: {'lr': 5.855409506980713e-05, 'samples': 22481856, 'steps': 117092, 'loss/train': 5.765933513641357} 08/31/2021 10:23:57 - INFO - __main__ - Step 117094: {'lr': 5.855068235457012e-05, 'samples': 22482048, 'steps': 117093, 'loss/train': 1.3613637685775757} 08/31/2021 10:23:58 - INFO - __main__ - Step 117095: {'lr': 5.854726972559729e-05, 'samples': 22482240, 'steps': 117094, 'loss/train': 0.6461316347122192} 08/31/2021 10:23:58 - INFO - __main__ - Step 117096: {'lr': 5.854385718289004e-05, 'samples': 22482432, 'steps': 117095, 'loss/train': 0.022207345813512802} 08/31/2021 10:24:00 - INFO - __main__ - Step 117097: {'lr': 5.854044472644995e-05, 'samples': 22482624, 'steps': 117096, 'loss/train': 0.6022771596908569} 08/31/2021 10:24:01 - INFO - __main__ - Step 117098: {'lr': 5.8537032356278605e-05, 'samples': 22482816, 'steps': 117097, 'loss/train': 1.8199344873428345} 08/31/2021 10:24:01 - INFO - __main__ - Step 117099: {'lr': 5.85336200723775e-05, 'samples': 22483008, 'steps': 117098, 'loss/train': 1.5905050039291382} 08/31/2021 10:24:01 - INFO - __main__ - Step 117100: {'lr': 5.853020787474822e-05, 'samples': 22483200, 'steps': 117099, 'loss/train': 1.2196805477142334} 08/31/2021 10:24:02 - INFO - __main__ - Step 117101: {'lr': 5.8526795763392235e-05, 'samples': 22483392, 'steps': 117100, 'loss/train': 0.9019117951393127} 08/31/2021 10:24:02 - INFO - __main__ - Step 117102: {'lr': 5.852338373831115e-05, 'samples': 22483584, 'steps': 117101, 'loss/train': 1.2264288663864136} 08/31/2021 10:24:03 - INFO - __main__ - Step 117103: {'lr': 5.851997179950647e-05, 'samples': 22483776, 'steps': 117102, 'loss/train': 1.7370539903640747} 08/31/2021 10:24:04 - INFO - __main__ - Step 117104: {'lr': 5.8516559946979714e-05, 'samples': 22483968, 'steps': 117103, 'loss/train': 1.520385980606079} 08/31/2021 10:24:04 - INFO - __main__ - Step 117105: {'lr': 5.8513148180732476e-05, 'samples': 22484160, 'steps': 117104, 'loss/train': 0.5141958594322205} 08/31/2021 10:24:05 - INFO - __main__ - Step 117106: {'lr': 5.850973650076624e-05, 'samples': 22484352, 'steps': 117105, 'loss/train': 1.2246943712234497} 08/31/2021 10:24:05 - INFO - __main__ - Step 117107: {'lr': 5.850632490708255e-05, 'samples': 22484544, 'steps': 117106, 'loss/train': 1.7581908702850342} 08/31/2021 10:24:07 - INFO - __main__ - Step 117108: {'lr': 5.850291339968297e-05, 'samples': 22484736, 'steps': 117107, 'loss/train': 1.349765658378601} 08/31/2021 10:24:07 - INFO - __main__ - Step 117109: {'lr': 5.8499501978569094e-05, 'samples': 22484928, 'steps': 117108, 'loss/train': 0.9280268549919128} 08/31/2021 10:24:08 - INFO - __main__ - Step 117110: {'lr': 5.849609064374231e-05, 'samples': 22485120, 'steps': 117109, 'loss/train': 1.1992762088775635} 08/31/2021 10:24:08 - INFO - __main__ - Step 117111: {'lr': 5.8492679395204254e-05, 'samples': 22485312, 'steps': 117110, 'loss/train': 0.474961519241333} 08/31/2021 10:24:08 - INFO - __main__ - Step 117112: {'lr': 5.848926823295642e-05, 'samples': 22485504, 'steps': 117111, 'loss/train': 0.0786421000957489} 08/31/2021 10:24:11 - INFO - __main__ - Step 117113: {'lr': 5.848585715700036e-05, 'samples': 22485696, 'steps': 117112, 'loss/train': 0.4844200909137726} 08/31/2021 10:24:11 - INFO - __main__ - Step 117114: {'lr': 5.848244616733764e-05, 'samples': 22485888, 'steps': 117113, 'loss/train': 0.3142482340335846} 08/31/2021 10:24:12 - INFO - __main__ - Step 117115: {'lr': 5.847903526396975e-05, 'samples': 22486080, 'steps': 117114, 'loss/train': 0.2914082407951355} 08/31/2021 10:24:12 - INFO - __main__ - Step 117116: {'lr': 5.8475624446898275e-05, 'samples': 22486272, 'steps': 117115, 'loss/train': 0.25737321376800537} 08/31/2021 10:24:12 - INFO - __main__ - Step 117117: {'lr': 5.847221371612471e-05, 'samples': 22486464, 'steps': 117116, 'loss/train': 0.633807361125946} 08/31/2021 10:24:13 - INFO - __main__ - Step 117118: {'lr': 5.846880307165062e-05, 'samples': 22486656, 'steps': 117117, 'loss/train': 1.693737506866455} 08/31/2021 10:24:13 - INFO - __main__ - Step 117119: {'lr': 5.8465392513477514e-05, 'samples': 22486848, 'steps': 117118, 'loss/train': 1.2402675151824951} 08/31/2021 10:24:15 - INFO - __main__ - Step 117120: {'lr': 5.8461982041606964e-05, 'samples': 22487040, 'steps': 117119, 'loss/train': 0.6724234223365784} 08/31/2021 10:24:15 - INFO - __main__ - Step 117121: {'lr': 5.8458571656040486e-05, 'samples': 22487232, 'steps': 117120, 'loss/train': 1.5872507095336914} 08/31/2021 10:24:16 - INFO - __main__ - Step 117122: {'lr': 5.84551613567797e-05, 'samples': 22487424, 'steps': 117121, 'loss/train': 1.461717128753662} 08/31/2021 10:24:16 - INFO - __main__ - Step 117123: {'lr': 5.845175114382598e-05, 'samples': 22487616, 'steps': 117122, 'loss/train': 0.7617783546447754} 08/31/2021 10:24:16 - INFO - __main__ - Step 117124: {'lr': 5.844834101718094e-05, 'samples': 22487808, 'steps': 117123, 'loss/train': 2.315272331237793} 08/31/2021 10:24:18 - INFO - __main__ - Step 117125: {'lr': 5.8444930976846136e-05, 'samples': 22488000, 'steps': 117124, 'loss/train': 1.7404760122299194} 08/31/2021 10:24:19 - INFO - __main__ - Step 117126: {'lr': 5.8441521022823076e-05, 'samples': 22488192, 'steps': 117125, 'loss/train': 1.5436030626296997} 08/31/2021 10:24:19 - INFO - __main__ - Step 117127: {'lr': 5.8438111155113324e-05, 'samples': 22488384, 'steps': 117126, 'loss/train': 0.05956849828362465} 08/31/2021 10:24:20 - INFO - __main__ - Step 117128: {'lr': 5.84347013737184e-05, 'samples': 22488576, 'steps': 117127, 'loss/train': 1.3857192993164062} 08/31/2021 10:24:20 - INFO - __main__ - Step 117129: {'lr': 5.8431291678639836e-05, 'samples': 22488768, 'steps': 117128, 'loss/train': 0.8939821720123291} 08/31/2021 10:24:22 - INFO - __main__ - Step 117130: {'lr': 5.84278820698792e-05, 'samples': 22488960, 'steps': 117129, 'loss/train': 0.8779515624046326} 08/31/2021 10:24:22 - INFO - __main__ - Step 117131: {'lr': 5.842447254743796e-05, 'samples': 22489152, 'steps': 117130, 'loss/train': 1.2482839822769165} 08/31/2021 10:24:23 - INFO - __main__ - Step 117132: {'lr': 5.842106311131773e-05, 'samples': 22489344, 'steps': 117131, 'loss/train': 0.4759780764579773} 08/31/2021 10:24:23 - INFO - __main__ - Step 117133: {'lr': 5.8417653761520004e-05, 'samples': 22489536, 'steps': 117132, 'loss/train': 0.5050439834594727} 08/31/2021 10:24:23 - INFO - __main__ - Step 117134: {'lr': 5.8414244498046416e-05, 'samples': 22489728, 'steps': 117133, 'loss/train': 1.3815492391586304} 08/31/2021 10:24:24 - INFO - __main__ - Step 117135: {'lr': 5.8410835320898306e-05, 'samples': 22489920, 'steps': 117134, 'loss/train': 4.601162433624268} 08/31/2021 10:24:25 - INFO - __main__ - Step 117136: {'lr': 5.8407426230077334e-05, 'samples': 22490112, 'steps': 117135, 'loss/train': 1.1881990432739258} 08/31/2021 10:24:26 - INFO - __main__ - Step 117137: {'lr': 5.8404017225585025e-05, 'samples': 22490304, 'steps': 117136, 'loss/train': 1.019795536994934} 08/31/2021 10:24:26 - INFO - __main__ - Step 117138: {'lr': 5.840060830742292e-05, 'samples': 22490496, 'steps': 117137, 'loss/train': 1.2161478996276855} 08/31/2021 10:24:27 - INFO - __main__ - Step 117139: {'lr': 5.839719947559252e-05, 'samples': 22490688, 'steps': 117138, 'loss/train': 1.4168808460235596} 08/31/2021 10:24:27 - INFO - __main__ - Step 117140: {'lr': 5.83937907300954e-05, 'samples': 22490880, 'steps': 117139, 'loss/train': 1.12189781665802} 08/31/2021 10:24:28 - INFO - __main__ - Step 117141: {'lr': 5.839038207093309e-05, 'samples': 22491072, 'steps': 117140, 'loss/train': 1.1123623847961426} 08/31/2021 10:24:29 - INFO - __main__ - Step 117142: {'lr': 5.838697349810709e-05, 'samples': 22491264, 'steps': 117141, 'loss/train': 1.2950152158737183} 08/31/2021 10:24:29 - INFO - __main__ - Step 117143: {'lr': 5.838356501161898e-05, 'samples': 22491456, 'steps': 117142, 'loss/train': 1.3768590688705444} 08/31/2021 10:24:29 - INFO - __main__ - Step 117144: {'lr': 5.838015661147028e-05, 'samples': 22491648, 'steps': 117143, 'loss/train': 0.5606589913368225} 08/31/2021 10:24:30 - INFO - __main__ - Step 117145: {'lr': 5.837674829766257e-05, 'samples': 22491840, 'steps': 117144, 'loss/train': 1.0152435302734375} 08/31/2021 10:24:31 - INFO - __main__ - Step 117146: {'lr': 5.837334007019729e-05, 'samples': 22492032, 'steps': 117145, 'loss/train': 0.8614688515663147} 08/31/2021 10:24:32 - INFO - __main__ - Step 117147: {'lr': 5.8369931929076026e-05, 'samples': 22492224, 'steps': 117146, 'loss/train': 0.9795217514038086} 08/31/2021 10:24:32 - INFO - __main__ - Step 117148: {'lr': 5.8366523874300334e-05, 'samples': 22492416, 'steps': 117147, 'loss/train': 0.7293335795402527} 08/31/2021 10:24:32 - INFO - __main__ - Step 117149: {'lr': 5.83631159058717e-05, 'samples': 22492608, 'steps': 117148, 'loss/train': 0.9675740003585815} 08/31/2021 10:24:33 - INFO - __main__ - Step 117150: {'lr': 5.8359708023791704e-05, 'samples': 22492800, 'steps': 117149, 'loss/train': 1.4248502254486084} 08/31/2021 10:24:34 - INFO - __main__ - Step 117151: {'lr': 5.835630022806185e-05, 'samples': 22492992, 'steps': 117150, 'loss/train': 1.284114956855774} 08/31/2021 10:24:35 - INFO - __main__ - Step 117152: {'lr': 5.8352892518683695e-05, 'samples': 22493184, 'steps': 117151, 'loss/train': 0.6165118217468262} 08/31/2021 10:24:35 - INFO - __main__ - Step 117153: {'lr': 5.8349484895658775e-05, 'samples': 22493376, 'steps': 117152, 'loss/train': 1.4151138067245483} 08/31/2021 10:24:36 - INFO - __main__ - Step 117154: {'lr': 5.834607735898861e-05, 'samples': 22493568, 'steps': 117153, 'loss/train': 1.429030418395996} 08/31/2021 10:24:36 - INFO - __main__ - Step 117155: {'lr': 5.834266990867476e-05, 'samples': 22493760, 'steps': 117154, 'loss/train': 1.1698803901672363} 08/31/2021 10:24:38 - INFO - __main__ - Step 117156: {'lr': 5.8339262544718826e-05, 'samples': 22493952, 'steps': 117155, 'loss/train': 1.3066465854644775} 08/31/2021 10:24:38 - INFO - __main__ - Step 117157: {'lr': 5.8335855267122176e-05, 'samples': 22494144, 'steps': 117156, 'loss/train': 1.085431694984436} 08/31/2021 10:24:38 - INFO - __main__ - Step 117158: {'lr': 5.8332448075886416e-05, 'samples': 22494336, 'steps': 117157, 'loss/train': 0.8739878535270691} 08/31/2021 10:24:39 - INFO - __main__ - Step 117159: {'lr': 5.832904097101313e-05, 'samples': 22494528, 'steps': 117158, 'loss/train': 1.1786291599273682} 08/31/2021 10:24:39 - INFO - __main__ - Step 117160: {'lr': 5.832563395250379e-05, 'samples': 22494720, 'steps': 117159, 'loss/train': 0.6506387591362} 08/31/2021 10:24:41 - INFO - __main__ - Step 117161: {'lr': 5.832222702036e-05, 'samples': 22494912, 'steps': 117160, 'loss/train': 1.5419965982437134} 08/31/2021 10:24:41 - INFO - __main__ - Step 117162: {'lr': 5.831882017458323e-05, 'samples': 22495104, 'steps': 117161, 'loss/train': 0.8162167072296143} 08/31/2021 10:24:42 - INFO - __main__ - Step 117163: {'lr': 5.8315413415175045e-05, 'samples': 22495296, 'steps': 117162, 'loss/train': 0.0272002462297678} 08/31/2021 10:24:42 - INFO - __main__ - Step 117164: {'lr': 5.8312006742136966e-05, 'samples': 22495488, 'steps': 117163, 'loss/train': 1.0387791395187378} 08/31/2021 10:24:42 - INFO - __main__ - Step 117165: {'lr': 5.8308600155470545e-05, 'samples': 22495680, 'steps': 117164, 'loss/train': 4.300402641296387} 08/31/2021 10:24:44 - INFO - __main__ - Step 117166: {'lr': 5.830519365517731e-05, 'samples': 22495872, 'steps': 117165, 'loss/train': 1.3568775653839111} 08/31/2021 10:24:44 - INFO - __main__ - Step 117167: {'lr': 5.830178724125887e-05, 'samples': 22496064, 'steps': 117166, 'loss/train': 1.5775569677352905} 08/31/2021 10:24:45 - INFO - __main__ - Step 117168: {'lr': 5.829838091371664e-05, 'samples': 22496256, 'steps': 117167, 'loss/train': 1.6607030630111694} 08/31/2021 10:24:45 - INFO - __main__ - Step 117169: {'lr': 5.829497467255218e-05, 'samples': 22496448, 'steps': 117168, 'loss/train': 0.7018261551856995} 08/31/2021 10:24:45 - INFO - __main__ - Step 117170: {'lr': 5.829156851776704e-05, 'samples': 22496640, 'steps': 117169, 'loss/train': 1.3419623374938965} 08/31/2021 10:24:47 - INFO - __main__ - Step 117171: {'lr': 5.8288162449362774e-05, 'samples': 22496832, 'steps': 117170, 'loss/train': 0.7892956733703613} 08/31/2021 10:24:47 - INFO - __main__ - Step 117172: {'lr': 5.828475646734088e-05, 'samples': 22497024, 'steps': 117171, 'loss/train': 1.4810529947280884} 08/31/2021 10:24:48 - INFO - __main__ - Step 117173: {'lr': 5.828135057170295e-05, 'samples': 22497216, 'steps': 117172, 'loss/train': 0.5873956084251404} 08/31/2021 10:24:48 - INFO - __main__ - Step 117174: {'lr': 5.827794476245046e-05, 'samples': 22497408, 'steps': 117173, 'loss/train': 1.3653794527053833} 08/31/2021 10:24:48 - INFO - __main__ - Step 117175: {'lr': 5.827453903958496e-05, 'samples': 22497600, 'steps': 117174, 'loss/train': 1.8340941667556763} 08/31/2021 10:24:49 - INFO - __main__ - Step 117176: {'lr': 5.827113340310802e-05, 'samples': 22497792, 'steps': 117175, 'loss/train': 0.8682536482810974} 08/31/2021 10:24:51 - INFO - __main__ - Step 117177: {'lr': 5.826772785302114e-05, 'samples': 22497984, 'steps': 117176, 'loss/train': 0.8187819719314575} 08/31/2021 10:24:52 - INFO - __main__ - Step 117178: {'lr': 5.826432238932594e-05, 'samples': 22498176, 'steps': 117177, 'loss/train': 1.2246676683425903} 08/31/2021 10:24:52 - INFO - __main__ - Step 117179: {'lr': 5.82609170120238e-05, 'samples': 22498368, 'steps': 117178, 'loss/train': 1.7435758113861084} 08/31/2021 10:24:52 - INFO - __main__ - Step 117180: {'lr': 5.825751172111635e-05, 'samples': 22498560, 'steps': 117179, 'loss/train': 1.1952779293060303} 08/31/2021 10:24:53 - INFO - __main__ - Step 117181: {'lr': 5.825410651660507e-05, 'samples': 22498752, 'steps': 117180, 'loss/train': 1.0653526782989502} 08/31/2021 10:24:54 - INFO - __main__ - Step 117182: {'lr': 5.825070139849156e-05, 'samples': 22498944, 'steps': 117181, 'loss/train': 0.9562227129936218} 08/31/2021 10:24:54 - INFO - __main__ - Step 117183: {'lr': 5.824729636677731e-05, 'samples': 22499136, 'steps': 117182, 'loss/train': 1.1886823177337646} 08/31/2021 10:24:55 - INFO - __main__ - Step 117184: {'lr': 5.8243891421463884e-05, 'samples': 22499328, 'steps': 117183, 'loss/train': 1.4990142583847046} 08/31/2021 10:24:55 - INFO - __main__ - Step 117185: {'lr': 5.824048656255279e-05, 'samples': 22499520, 'steps': 117184, 'loss/train': 1.3978102207183838} 08/31/2021 10:24:56 - INFO - __main__ - Step 117186: {'lr': 5.823708179004558e-05, 'samples': 22499712, 'steps': 117185, 'loss/train': 1.43252694606781} 08/31/2021 10:24:57 - INFO - __main__ - Step 117187: {'lr': 5.8233677103943785e-05, 'samples': 22499904, 'steps': 117186, 'loss/train': 1.1522963047027588} 08/31/2021 10:24:58 - INFO - __main__ - Step 117188: {'lr': 5.823027250424892e-05, 'samples': 22500096, 'steps': 117187, 'loss/train': 1.2369592189788818} 08/31/2021 10:24:58 - INFO - __main__ - Step 117189: {'lr': 5.8226867990962554e-05, 'samples': 22500288, 'steps': 117188, 'loss/train': 0.6892220377922058} 08/31/2021 10:24:58 - INFO - __main__ - Step 117190: {'lr': 5.8223463564086255e-05, 'samples': 22500480, 'steps': 117189, 'loss/train': 1.0009429454803467} 08/31/2021 10:24:59 - INFO - __main__ - Step 117191: {'lr': 5.8220059223621444e-05, 'samples': 22500672, 'steps': 117190, 'loss/train': 1.488490343093872} 08/31/2021 10:25:00 - INFO - __main__ - Step 117192: {'lr': 5.821665496956971e-05, 'samples': 22500864, 'steps': 117191, 'loss/train': 1.37607741355896} 08/31/2021 10:25:00 - INFO - __main__ - Step 117193: {'lr': 5.82132508019326e-05, 'samples': 22501056, 'steps': 117192, 'loss/train': 0.5518127083778381} 08/31/2021 10:25:01 - INFO - __main__ - Step 117194: {'lr': 5.820984672071161e-05, 'samples': 22501248, 'steps': 117193, 'loss/train': 0.9818597435951233} 08/31/2021 10:25:01 - INFO - __main__ - Step 117195: {'lr': 5.8206442725908334e-05, 'samples': 22501440, 'steps': 117194, 'loss/train': 1.3136484622955322} 08/31/2021 10:25:02 - INFO - __main__ - Step 117196: {'lr': 5.820303881752429e-05, 'samples': 22501632, 'steps': 117195, 'loss/train': 1.268863558769226} 08/31/2021 10:25:03 - INFO - __main__ - Step 117197: {'lr': 5.819963499556097e-05, 'samples': 22501824, 'steps': 117196, 'loss/train': 1.044325351715088} 08/31/2021 10:25:03 - INFO - __main__ - Step 117198: {'lr': 5.819623126001994e-05, 'samples': 22502016, 'steps': 117197, 'loss/train': 1.0652157068252563} 08/31/2021 10:25:04 - INFO - __main__ - Step 117199: {'lr': 5.819282761090272e-05, 'samples': 22502208, 'steps': 117198, 'loss/train': 1.495179295539856} 08/31/2021 10:25:04 - INFO - __main__ - Step 117200: {'lr': 5.8189424048210874e-05, 'samples': 22502400, 'steps': 117199, 'loss/train': 0.9957592487335205} 08/31/2021 10:25:05 - INFO - __main__ - Step 117201: {'lr': 5.818602057194589e-05, 'samples': 22502592, 'steps': 117200, 'loss/train': 1.1404109001159668} 08/31/2021 10:25:06 - INFO - __main__ - Step 117202: {'lr': 5.818261718210935e-05, 'samples': 22502784, 'steps': 117201, 'loss/train': 0.9532134532928467} 08/31/2021 10:25:06 - INFO - __main__ - Step 117203: {'lr': 5.8179213878702814e-05, 'samples': 22502976, 'steps': 117202, 'loss/train': 0.7354328632354736} 08/31/2021 10:25:07 - INFO - __main__ - Step 117204: {'lr': 5.81758106617277e-05, 'samples': 22503168, 'steps': 117203, 'loss/train': 0.6351286768913269} 08/31/2021 10:25:07 - INFO - __main__ - Step 117205: {'lr': 5.817240753118561e-05, 'samples': 22503360, 'steps': 117204, 'loss/train': 1.465219259262085} 08/31/2021 10:25:07 - INFO - __main__ - Step 117206: {'lr': 5.816900448707807e-05, 'samples': 22503552, 'steps': 117205, 'loss/train': 1.04636812210083} 08/31/2021 10:25:09 - INFO - __main__ - Step 117207: {'lr': 5.816560152940662e-05, 'samples': 22503744, 'steps': 117206, 'loss/train': 1.2959516048431396} 08/31/2021 10:25:09 - INFO - __main__ - Step 117208: {'lr': 5.816219865817277e-05, 'samples': 22503936, 'steps': 117207, 'loss/train': 0.9601176381111145} 08/31/2021 10:25:10 - INFO - __main__ - Step 117209: {'lr': 5.815879587337808e-05, 'samples': 22504128, 'steps': 117208, 'loss/train': 1.7228245735168457} 08/31/2021 10:25:10 - INFO - __main__ - Step 117210: {'lr': 5.815539317502408e-05, 'samples': 22504320, 'steps': 117209, 'loss/train': 1.5536870956420898} 08/31/2021 10:25:11 - INFO - __main__ - Step 117211: {'lr': 5.815199056311232e-05, 'samples': 22504512, 'steps': 117210, 'loss/train': 0.9520096778869629} 08/31/2021 10:25:12 - INFO - __main__ - Step 117212: {'lr': 5.814858803764428e-05, 'samples': 22504704, 'steps': 117211, 'loss/train': 1.4244462251663208} 08/31/2021 10:25:13 - INFO - __main__ - Step 117213: {'lr': 5.814518559862156e-05, 'samples': 22504896, 'steps': 117212, 'loss/train': 2.198888063430786} 08/31/2021 10:25:13 - INFO - __main__ - Step 117214: {'lr': 5.814178324604563e-05, 'samples': 22505088, 'steps': 117213, 'loss/train': 0.8403365015983582} 08/31/2021 10:25:13 - INFO - __main__ - Step 117215: {'lr': 5.8138380979918055e-05, 'samples': 22505280, 'steps': 117214, 'loss/train': 0.6529986262321472} 08/31/2021 10:25:14 - INFO - __main__ - Step 117216: {'lr': 5.813497880024046e-05, 'samples': 22505472, 'steps': 117215, 'loss/train': 1.088813066482544} 08/31/2021 10:25:15 - INFO - __main__ - Step 117217: {'lr': 5.813157670701419e-05, 'samples': 22505664, 'steps': 117216, 'loss/train': 0.49566152691841125} 08/31/2021 10:25:16 - INFO - __main__ - Step 117218: {'lr': 5.812817470024087e-05, 'samples': 22505856, 'steps': 117217, 'loss/train': 0.9416186213493347} 08/31/2021 10:25:16 - INFO - __main__ - Step 117219: {'lr': 5.812477277992204e-05, 'samples': 22506048, 'steps': 117218, 'loss/train': 0.6593614220619202} 08/31/2021 10:25:16 - INFO - __main__ - Step 117220: {'lr': 5.812137094605924e-05, 'samples': 22506240, 'steps': 117219, 'loss/train': 1.5874004364013672} 08/31/2021 10:25:17 - INFO - __main__ - Step 117221: {'lr': 5.8117969198653977e-05, 'samples': 22506432, 'steps': 117220, 'loss/train': 1.0225690603256226} 08/31/2021 10:25:19 - INFO - __main__ - Step 117222: {'lr': 5.8114567537707774e-05, 'samples': 22506624, 'steps': 117221, 'loss/train': 1.1349235773086548} 08/31/2021 10:25:19 - INFO - __main__ - Step 117223: {'lr': 5.8111165963222216e-05, 'samples': 22506816, 'steps': 117222, 'loss/train': 1.18840491771698} 08/31/2021 10:25:20 - INFO - __main__ - Step 117224: {'lr': 5.810776447519881e-05, 'samples': 22507008, 'steps': 117223, 'loss/train': 1.3828721046447754} 08/31/2021 10:25:20 - INFO - __main__ - Step 117225: {'lr': 5.8104363073639063e-05, 'samples': 22507200, 'steps': 117224, 'loss/train': 1.289923071861267} 08/31/2021 10:25:20 - INFO - __main__ - Step 117226: {'lr': 5.810096175854454e-05, 'samples': 22507392, 'steps': 117225, 'loss/train': 0.04178020358085632} 08/31/2021 10:25:21 - INFO - __main__ - Step 117227: {'lr': 5.809756052991674e-05, 'samples': 22507584, 'steps': 117226, 'loss/train': 0.12017686665058136} 08/31/2021 10:25:21 - INFO - __main__ - Step 117228: {'lr': 5.809415938775725e-05, 'samples': 22507776, 'steps': 117227, 'loss/train': 0.6817690134048462} 08/31/2021 10:25:23 - INFO - __main__ - Step 117229: {'lr': 5.809075833206756e-05, 'samples': 22507968, 'steps': 117228, 'loss/train': 2.3169143199920654} 08/31/2021 10:25:24 - INFO - __main__ - Step 117230: {'lr': 5.808735736284929e-05, 'samples': 22508160, 'steps': 117229, 'loss/train': 1.1708416938781738} 08/31/2021 10:25:24 - INFO - __main__ - Step 117231: {'lr': 5.808395648010381e-05, 'samples': 22508352, 'steps': 117230, 'loss/train': 1.5781067609786987} 08/31/2021 10:25:24 - INFO - __main__ - Step 117232: {'lr': 5.808055568383275e-05, 'samples': 22508544, 'steps': 117231, 'loss/train': 1.3358047008514404} 08/31/2021 10:25:25 - INFO - __main__ - Step 117233: {'lr': 5.8077154974037624e-05, 'samples': 22508736, 'steps': 117232, 'loss/train': 1.3328263759613037} 08/31/2021 10:25:27 - INFO - __main__ - Step 117234: {'lr': 5.807375435071996e-05, 'samples': 22508928, 'steps': 117233, 'loss/train': 0.062174443155527115} 08/31/2021 10:25:27 - INFO - __main__ - Step 117235: {'lr': 5.8070353813881315e-05, 'samples': 22509120, 'steps': 117234, 'loss/train': 0.5871862769126892} 08/31/2021 10:25:28 - INFO - __main__ - Step 117236: {'lr': 5.8066953363523186e-05, 'samples': 22509312, 'steps': 117235, 'loss/train': 0.5592958927154541} 08/31/2021 10:25:28 - INFO - __main__ - Step 117237: {'lr': 5.806355299964716e-05, 'samples': 22509504, 'steps': 117236, 'loss/train': 1.0255846977233887} 08/31/2021 10:25:28 - INFO - __main__ - Step 117238: {'lr': 5.806015272225471e-05, 'samples': 22509696, 'steps': 117237, 'loss/train': 0.7429747581481934} 08/31/2021 10:25:29 - INFO - __main__ - Step 117239: {'lr': 5.80567525313474e-05, 'samples': 22509888, 'steps': 117238, 'loss/train': 1.247804045677185} 08/31/2021 10:25:30 - INFO - __main__ - Step 117240: {'lr': 5.805335242692675e-05, 'samples': 22510080, 'steps': 117239, 'loss/train': 1.2393827438354492} 08/31/2021 10:25:31 - INFO - __main__ - Step 117241: {'lr': 5.80499524089943e-05, 'samples': 22510272, 'steps': 117240, 'loss/train': 0.9998544454574585} 08/31/2021 10:25:31 - INFO - __main__ - Step 117242: {'lr': 5.804655247755158e-05, 'samples': 22510464, 'steps': 117241, 'loss/train': 0.9405357241630554} 08/31/2021 10:25:32 - INFO - __main__ - Step 117243: {'lr': 5.804315263260021e-05, 'samples': 22510656, 'steps': 117242, 'loss/train': 1.0064808130264282} 08/31/2021 10:25:32 - INFO - __main__ - Step 117244: {'lr': 5.803975287414154e-05, 'samples': 22510848, 'steps': 117243, 'loss/train': 0.7401059865951538} 08/31/2021 10:25:33 - INFO - __main__ - Step 117245: {'lr': 5.803635320217721e-05, 'samples': 22511040, 'steps': 117244, 'loss/train': 1.4957079887390137} 08/31/2021 10:25:34 - INFO - __main__ - Step 117246: {'lr': 5.803295361670874e-05, 'samples': 22511232, 'steps': 117245, 'loss/train': 0.8700618743896484} 08/31/2021 10:25:34 - INFO - __main__ - Step 117247: {'lr': 5.802955411773764e-05, 'samples': 22511424, 'steps': 117246, 'loss/train': 0.7815656065940857} 08/31/2021 10:25:35 - INFO - __main__ - Step 117248: {'lr': 5.802615470526548e-05, 'samples': 22511616, 'steps': 117247, 'loss/train': 0.9881818294525146} 08/31/2021 10:25:35 - INFO - __main__ - Step 117249: {'lr': 5.8022755379293744e-05, 'samples': 22511808, 'steps': 117248, 'loss/train': 1.4135277271270752} 08/31/2021 10:25:35 - INFO - __main__ - Step 117250: {'lr': 5.801935613982403e-05, 'samples': 22512000, 'steps': 117249, 'loss/train': 1.1879726648330688} 08/31/2021 10:25:37 - INFO - __main__ - Step 117251: {'lr': 5.80159569868578e-05, 'samples': 22512192, 'steps': 117250, 'loss/train': 0.6304728984832764} 08/31/2021 10:25:37 - INFO - __main__ - Step 117252: {'lr': 5.801255792039664e-05, 'samples': 22512384, 'steps': 117251, 'loss/train': 0.6437749862670898} 08/31/2021 10:25:38 - INFO - __main__ - Step 117253: {'lr': 5.800915894044204e-05, 'samples': 22512576, 'steps': 117252, 'loss/train': 1.16106379032135} 08/31/2021 10:25:38 - INFO - __main__ - Step 117254: {'lr': 5.8005760046995567e-05, 'samples': 22512768, 'steps': 117253, 'loss/train': 1.2114837169647217} 08/31/2021 10:25:38 - INFO - __main__ - Step 117255: {'lr': 5.8002361240058724e-05, 'samples': 22512960, 'steps': 117254, 'loss/train': 0.2187204658985138} 08/31/2021 10:25:40 - INFO - __main__ - Step 117256: {'lr': 5.799896251963305e-05, 'samples': 22513152, 'steps': 117255, 'loss/train': 1.1109706163406372} 08/31/2021 10:25:40 - INFO - __main__ - Step 117257: {'lr': 5.7995563885720164e-05, 'samples': 22513344, 'steps': 117256, 'loss/train': 0.852014422416687} 08/31/2021 10:25:41 - INFO - __main__ - Step 117258: {'lr': 5.799216533832144e-05, 'samples': 22513536, 'steps': 117257, 'loss/train': 1.1877979040145874} 08/31/2021 10:25:41 - INFO - __main__ - Step 117259: {'lr': 5.798876687743848e-05, 'samples': 22513728, 'steps': 117258, 'loss/train': 1.3625870943069458} 08/31/2021 10:25:41 - INFO - __main__ - Step 117260: {'lr': 5.798536850307282e-05, 'samples': 22513920, 'steps': 117259, 'loss/train': 0.36288413405418396} 08/31/2021 10:25:43 - INFO - __main__ - Step 117261: {'lr': 5.7981970215225996e-05, 'samples': 22514112, 'steps': 117260, 'loss/train': 1.298518180847168} 08/31/2021 10:25:43 - INFO - __main__ - Step 117262: {'lr': 5.797857201389953e-05, 'samples': 22514304, 'steps': 117261, 'loss/train': 0.5947911143302917} 08/31/2021 10:25:44 - INFO - __main__ - Step 117263: {'lr': 5.797517389909496e-05, 'samples': 22514496, 'steps': 117262, 'loss/train': 1.3058563470840454} 08/31/2021 10:25:44 - INFO - __main__ - Step 117264: {'lr': 5.7971775870813815e-05, 'samples': 22514688, 'steps': 117263, 'loss/train': 1.8193066120147705} 08/31/2021 10:25:44 - INFO - __main__ - Step 117265: {'lr': 5.7968377929057594e-05, 'samples': 22514880, 'steps': 117264, 'loss/train': 1.1403253078460693} 08/31/2021 10:25:46 - INFO - __main__ - Step 117266: {'lr': 5.796498007382789e-05, 'samples': 22515072, 'steps': 117265, 'loss/train': 1.152639627456665} 08/31/2021 10:25:47 - INFO - __main__ - Step 117267: {'lr': 5.796158230512621e-05, 'samples': 22515264, 'steps': 117266, 'loss/train': 1.0862916707992554} 08/31/2021 10:25:47 - INFO - __main__ - Step 117268: {'lr': 5.795818462295405e-05, 'samples': 22515456, 'steps': 117267, 'loss/train': 0.9084069132804871} 08/31/2021 10:25:47 - INFO - __main__ - Step 117269: {'lr': 5.795478702731299e-05, 'samples': 22515648, 'steps': 117268, 'loss/train': 1.0894445180892944} 08/31/2021 10:25:48 - INFO - __main__ - Step 117270: {'lr': 5.795138951820461e-05, 'samples': 22515840, 'steps': 117269, 'loss/train': 0.3115537166595459} 08/31/2021 10:25:49 - INFO - __main__ - Step 117271: {'lr': 5.7947992095630284e-05, 'samples': 22516032, 'steps': 117270, 'loss/train': 0.20965337753295898} 08/31/2021 10:25:50 - INFO - __main__ - Step 117272: {'lr': 5.7944594759591626e-05, 'samples': 22516224, 'steps': 117271, 'loss/train': 1.1729894876480103} 08/31/2021 10:25:50 - INFO - __main__ - Step 117273: {'lr': 5.794119751009019e-05, 'samples': 22516416, 'steps': 117272, 'loss/train': 1.5815311670303345} 08/31/2021 10:25:50 - INFO - __main__ - Step 117274: {'lr': 5.793780034712748e-05, 'samples': 22516608, 'steps': 117273, 'loss/train': 1.1839138269424438} 08/31/2021 10:25:51 - INFO - __main__ - Step 117275: {'lr': 5.7934403270705035e-05, 'samples': 22516800, 'steps': 117274, 'loss/train': 1.139707088470459} 08/31/2021 10:25:52 - INFO - __main__ - Step 117276: {'lr': 5.793100628082437e-05, 'samples': 22516992, 'steps': 117275, 'loss/train': 0.804149329662323} 08/31/2021 10:25:52 - INFO - __main__ - Step 117277: {'lr': 5.792760937748703e-05, 'samples': 22517184, 'steps': 117276, 'loss/train': 0.807275116443634} 08/31/2021 10:25:53 - INFO - __main__ - Step 117278: {'lr': 5.792421256069458e-05, 'samples': 22517376, 'steps': 117277, 'loss/train': 1.416883945465088} 08/31/2021 10:25:53 - INFO - __main__ - Step 117279: {'lr': 5.792081583044847e-05, 'samples': 22517568, 'steps': 117278, 'loss/train': 1.2896625995635986} 08/31/2021 10:25:54 - INFO - __main__ - Step 117280: {'lr': 5.791741918675031e-05, 'samples': 22517760, 'steps': 117279, 'loss/train': 0.9718590974807739} 08/31/2021 10:25:55 - INFO - __main__ - Step 117281: {'lr': 5.791402262960158e-05, 'samples': 22517952, 'steps': 117280, 'loss/train': 1.0839600563049316} 08/31/2021 10:25:56 - INFO - __main__ - Step 117282: {'lr': 5.791062615900383e-05, 'samples': 22518144, 'steps': 117281, 'loss/train': 0.8587820529937744} 08/31/2021 10:25:56 - INFO - __main__ - Step 117283: {'lr': 5.79072297749586e-05, 'samples': 22518336, 'steps': 117282, 'loss/train': 1.4676222801208496} 08/31/2021 10:25:57 - INFO - __main__ - Step 117284: {'lr': 5.7903833477467475e-05, 'samples': 22518528, 'steps': 117283, 'loss/train': 0.048588503152132034} 08/31/2021 10:25:57 - INFO - __main__ - Step 117285: {'lr': 5.7900437266531826e-05, 'samples': 22518720, 'steps': 117284, 'loss/train': 0.7753754258155823} 08/31/2021 10:25:59 - INFO - __main__ - Step 117286: {'lr': 5.78970411421533e-05, 'samples': 22518912, 'steps': 117285, 'loss/train': 0.15223771333694458} 08/31/2021 10:26:00 - INFO - __main__ - Step 117287: {'lr': 5.78936451043334e-05, 'samples': 22519104, 'steps': 117286, 'loss/train': 1.0220699310302734} 08/31/2021 10:26:00 - INFO - __main__ - Step 117288: {'lr': 5.7890249153073644e-05, 'samples': 22519296, 'steps': 117287, 'loss/train': 1.0058923959732056} 08/31/2021 10:26:00 - INFO - __main__ - Step 117289: {'lr': 5.7886853288375594e-05, 'samples': 22519488, 'steps': 117288, 'loss/train': 0.8300765156745911} 08/31/2021 10:26:01 - INFO - __main__ - Step 117290: {'lr': 5.788345751024074e-05, 'samples': 22519680, 'steps': 117289, 'loss/train': 1.6044784784317017} 08/31/2021 10:26:01 - INFO - __main__ - Step 117291: {'lr': 5.788006181867064e-05, 'samples': 22519872, 'steps': 117290, 'loss/train': 1.366473913192749} 08/31/2021 10:26:03 - INFO - __main__ - Step 117292: {'lr': 5.7876666213666854e-05, 'samples': 22520064, 'steps': 117291, 'loss/train': 1.6628186702728271} 08/31/2021 10:26:03 - INFO - __main__ - Step 117293: {'lr': 5.787327069523085e-05, 'samples': 22520256, 'steps': 117292, 'loss/train': 0.05898505449295044} 08/31/2021 10:26:04 - INFO - __main__ - Step 117294: {'lr': 5.786987526336418e-05, 'samples': 22520448, 'steps': 117293, 'loss/train': 1.0555391311645508} 08/31/2021 10:26:04 - INFO - __main__ - Step 117295: {'lr': 5.78664799180684e-05, 'samples': 22520640, 'steps': 117294, 'loss/train': 0.8317505717277527} 08/31/2021 10:26:04 - INFO - __main__ - Step 117296: {'lr': 5.7863084659345e-05, 'samples': 22520832, 'steps': 117295, 'loss/train': 1.311362385749817} 08/31/2021 10:26:06 - INFO - __main__ - Step 117297: {'lr': 5.785968948719561e-05, 'samples': 22521024, 'steps': 117296, 'loss/train': 1.8462342023849487} 08/31/2021 10:26:06 - INFO - __main__ - Step 117298: {'lr': 5.78562944016216e-05, 'samples': 22521216, 'steps': 117297, 'loss/train': 0.9298881888389587} 08/31/2021 10:26:07 - INFO - __main__ - Step 117299: {'lr': 5.785289940262459e-05, 'samples': 22521408, 'steps': 117298, 'loss/train': 1.2751511335372925} 08/31/2021 10:26:07 - INFO - __main__ - Step 117300: {'lr': 5.7849504490206095e-05, 'samples': 22521600, 'steps': 117299, 'loss/train': 1.140365481376648} 08/31/2021 10:26:07 - INFO - __main__ - Step 117301: {'lr': 5.784610966436765e-05, 'samples': 22521792, 'steps': 117300, 'loss/train': 1.1185733079910278} 08/31/2021 10:26:09 - INFO - __main__ - Step 117302: {'lr': 5.7842714925110783e-05, 'samples': 22521984, 'steps': 117301, 'loss/train': 1.2562134265899658} 08/31/2021 10:26:09 - INFO - __main__ - Step 117303: {'lr': 5.7839320272437016e-05, 'samples': 22522176, 'steps': 117302, 'loss/train': 1.4453240633010864} 08/31/2021 10:26:10 - INFO - __main__ - Step 117304: {'lr': 5.783592570634788e-05, 'samples': 22522368, 'steps': 117303, 'loss/train': 0.9410165548324585} 08/31/2021 10:26:10 - INFO - __main__ - Step 117305: {'lr': 5.783253122684493e-05, 'samples': 22522560, 'steps': 117304, 'loss/train': 1.0789885520935059} 08/31/2021 10:26:10 - INFO - __main__ - Step 117306: {'lr': 5.7829136833929676e-05, 'samples': 22522752, 'steps': 117305, 'loss/train': 1.3762435913085938} 08/31/2021 10:26:12 - INFO - __main__ - Step 117307: {'lr': 5.782574252760364e-05, 'samples': 22522944, 'steps': 117306, 'loss/train': 1.6063967943191528} 08/31/2021 10:26:12 - INFO - __main__ - Step 117308: {'lr': 5.7822348307868336e-05, 'samples': 22523136, 'steps': 117307, 'loss/train': 1.0866210460662842} 08/31/2021 10:26:13 - INFO - __main__ - Step 117309: {'lr': 5.781895417472535e-05, 'samples': 22523328, 'steps': 117308, 'loss/train': 0.8317632675170898} 08/31/2021 10:26:13 - INFO - __main__ - Step 117310: {'lr': 5.781556012817618e-05, 'samples': 22523520, 'steps': 117309, 'loss/train': 1.0581480264663696} 08/31/2021 10:26:13 - INFO - __main__ - Step 117311: {'lr': 5.7812166168222406e-05, 'samples': 22523712, 'steps': 117310, 'loss/train': 0.989766538143158} 08/31/2021 10:26:14 - INFO - __main__ - Step 117312: {'lr': 5.780877229486542e-05, 'samples': 22523904, 'steps': 117311, 'loss/train': 1.2431567907333374} 08/31/2021 10:26:15 - INFO - __main__ - Step 117313: {'lr': 5.7805378508106856e-05, 'samples': 22524096, 'steps': 117312, 'loss/train': 1.4485468864440918} 08/31/2021 10:26:16 - INFO - __main__ - Step 117314: {'lr': 5.780198480794824e-05, 'samples': 22524288, 'steps': 117313, 'loss/train': 1.7150177955627441} 08/31/2021 10:26:16 - INFO - __main__ - Step 117315: {'lr': 5.779859119439104e-05, 'samples': 22524480, 'steps': 117314, 'loss/train': 1.05307936668396} 08/31/2021 10:26:16 - INFO - __main__ - Step 117316: {'lr': 5.779519766743688e-05, 'samples': 22524672, 'steps': 117315, 'loss/train': 1.0435627698898315} 08/31/2021 10:26:17 - INFO - __main__ - Step 117317: {'lr': 5.7791804227087184e-05, 'samples': 22524864, 'steps': 117316, 'loss/train': 0.9818754196166992} 08/31/2021 10:26:18 - INFO - __main__ - Step 117318: {'lr': 5.778841087334358e-05, 'samples': 22525056, 'steps': 117317, 'loss/train': 1.0305562019348145} 08/31/2021 10:26:19 - INFO - __main__ - Step 117319: {'lr': 5.7785017606207524e-05, 'samples': 22525248, 'steps': 117318, 'loss/train': 1.2440392971038818} 08/31/2021 10:26:19 - INFO - __main__ - Step 117320: {'lr': 5.7781624425680577e-05, 'samples': 22525440, 'steps': 117319, 'loss/train': 0.7287536263465881} 08/31/2021 10:26:19 - INFO - __main__ - Step 117321: {'lr': 5.777823133176427e-05, 'samples': 22525632, 'steps': 117320, 'loss/train': 1.0306193828582764} 08/31/2021 10:26:20 - INFO - __main__ - Step 117322: {'lr': 5.777483832446012e-05, 'samples': 22525824, 'steps': 117321, 'loss/train': 1.1822032928466797} 08/31/2021 10:26:21 - INFO - __main__ - Step 117323: {'lr': 5.777144540376969e-05, 'samples': 22526016, 'steps': 117322, 'loss/train': 0.7473649382591248} 08/31/2021 10:26:22 - INFO - __main__ - Step 117324: {'lr': 5.776805256969453e-05, 'samples': 22526208, 'steps': 117323, 'loss/train': 1.2535529136657715} 08/31/2021 10:26:22 - INFO - __main__ - Step 117325: {'lr': 5.7764659822236024e-05, 'samples': 22526400, 'steps': 117324, 'loss/train': 1.0034841299057007} 08/31/2021 10:26:22 - INFO - __main__ - Step 117326: {'lr': 5.776126716139582e-05, 'samples': 22526592, 'steps': 117325, 'loss/train': 1.5171172618865967} 08/31/2021 10:26:23 - INFO - __main__ - Step 117327: {'lr': 5.7757874587175437e-05, 'samples': 22526784, 'steps': 117326, 'loss/train': 0.7380185723304749} 08/31/2021 10:26:24 - INFO - __main__ - Step 117328: {'lr': 5.7754482099576375e-05, 'samples': 22526976, 'steps': 117327, 'loss/train': 0.5558174252510071} 08/31/2021 10:26:25 - INFO - __main__ - Step 117329: {'lr': 5.7751089698600154e-05, 'samples': 22527168, 'steps': 117328, 'loss/train': 0.9791365265846252} 08/31/2021 10:26:25 - INFO - __main__ - Step 117330: {'lr': 5.774769738424837e-05, 'samples': 22527360, 'steps': 117329, 'loss/train': 1.093084692955017} 08/31/2021 10:26:25 - INFO - __main__ - Step 117331: {'lr': 5.774430515652246e-05, 'samples': 22527552, 'steps': 117330, 'loss/train': 0.8233346343040466} 08/31/2021 10:26:26 - INFO - __main__ - Step 117332: {'lr': 5.7740913015424026e-05, 'samples': 22527744, 'steps': 117331, 'loss/train': 0.9373234510421753} 08/31/2021 10:26:27 - INFO - __main__ - Step 117333: {'lr': 5.7737520960954585e-05, 'samples': 22527936, 'steps': 117332, 'loss/train': 1.3601324558258057} 08/31/2021 10:26:28 - INFO - __main__ - Step 117334: {'lr': 5.7734128993115614e-05, 'samples': 22528128, 'steps': 117333, 'loss/train': 1.4519321918487549} 08/31/2021 10:26:28 - INFO - __main__ - Step 117335: {'lr': 5.773073711190871e-05, 'samples': 22528320, 'steps': 117334, 'loss/train': 0.021336562931537628} 08/31/2021 10:26:28 - INFO - __main__ - Step 117336: {'lr': 5.772734531733534e-05, 'samples': 22528512, 'steps': 117335, 'loss/train': 0.9349470734596252} 08/31/2021 10:26:29 - INFO - __main__ - Step 117337: {'lr': 5.7723953609397166e-05, 'samples': 22528704, 'steps': 117336, 'loss/train': 1.3258343935012817} 08/31/2021 10:26:31 - INFO - __main__ - Step 117338: {'lr': 5.77205619880955e-05, 'samples': 22528896, 'steps': 117337, 'loss/train': 1.016857624053955} 08/31/2021 10:26:31 - INFO - __main__ - Step 117339: {'lr': 5.7717170453432e-05, 'samples': 22529088, 'steps': 117338, 'loss/train': 0.6940588355064392} 08/31/2021 10:26:31 - INFO - __main__ - Step 117340: {'lr': 5.7713779005408196e-05, 'samples': 22529280, 'steps': 117339, 'loss/train': 1.2799540758132935} 08/31/2021 10:26:32 - INFO - __main__ - Step 117341: {'lr': 5.7710387644025584e-05, 'samples': 22529472, 'steps': 117340, 'loss/train': 1.1247849464416504} 08/31/2021 10:26:32 - INFO - __main__ - Step 117342: {'lr': 5.7706996369285695e-05, 'samples': 22529664, 'steps': 117341, 'loss/train': 1.7825307846069336} 08/31/2021 10:26:34 - INFO - __main__ - Step 117343: {'lr': 5.770360518119005e-05, 'samples': 22529856, 'steps': 117342, 'loss/train': 1.3627221584320068} 08/31/2021 10:26:34 - INFO - __main__ - Step 117344: {'lr': 5.7700214079740216e-05, 'samples': 22530048, 'steps': 117343, 'loss/train': 0.9468600153923035} 08/31/2021 10:26:35 - INFO - __main__ - Step 117345: {'lr': 5.76968230649377e-05, 'samples': 22530240, 'steps': 117344, 'loss/train': 0.023783929646015167} 08/31/2021 10:26:35 - INFO - __main__ - Step 117346: {'lr': 5.7693432136784017e-05, 'samples': 22530432, 'steps': 117345, 'loss/train': 1.4963080883026123} 08/31/2021 10:26:35 - INFO - __main__ - Step 117347: {'lr': 5.769004129528072e-05, 'samples': 22530624, 'steps': 117346, 'loss/train': 0.9026556015014648} 08/31/2021 10:26:36 - INFO - __main__ - Step 117348: {'lr': 5.768665054042932e-05, 'samples': 22530816, 'steps': 117347, 'loss/train': 1.6338214874267578} 08/31/2021 10:26:37 - INFO - __main__ - Step 117349: {'lr': 5.7683259872231356e-05, 'samples': 22531008, 'steps': 117348, 'loss/train': 1.1750953197479248} 08/31/2021 10:26:37 - INFO - __main__ - Step 117350: {'lr': 5.767986929068833e-05, 'samples': 22531200, 'steps': 117349, 'loss/train': 0.9628419280052185} 08/31/2021 10:26:38 - INFO - __main__ - Step 117351: {'lr': 5.767647879580184e-05, 'samples': 22531392, 'steps': 117350, 'loss/train': 1.3902047872543335} 08/31/2021 10:26:38 - INFO - __main__ - Step 117352: {'lr': 5.767308838757332e-05, 'samples': 22531584, 'steps': 117351, 'loss/train': 1.2463617324829102} 08/31/2021 10:26:38 - INFO - __main__ - Step 117353: {'lr': 5.766969806600433e-05, 'samples': 22531776, 'steps': 117352, 'loss/train': 0.31750252842903137} 08/31/2021 10:26:40 - INFO - __main__ - Step 117354: {'lr': 5.7666307831096415e-05, 'samples': 22531968, 'steps': 117353, 'loss/train': 0.9720405340194702} 08/31/2021 10:26:41 - INFO - __main__ - Step 117355: {'lr': 5.766291768285109e-05, 'samples': 22532160, 'steps': 117354, 'loss/train': 1.0897637605667114} 08/31/2021 10:26:41 - INFO - __main__ - Step 117356: {'lr': 5.765952762126989e-05, 'samples': 22532352, 'steps': 117355, 'loss/train': 1.246266484260559} 08/31/2021 10:26:41 - INFO - __main__ - Step 117357: {'lr': 5.765613764635433e-05, 'samples': 22532544, 'steps': 117356, 'loss/train': 1.5158530473709106} 08/31/2021 10:26:42 - INFO - __main__ - Step 117358: {'lr': 5.7652747758105946e-05, 'samples': 22532736, 'steps': 117357, 'loss/train': 0.48328524827957153} 08/31/2021 10:26:43 - INFO - __main__ - Step 117359: {'lr': 5.764935795652626e-05, 'samples': 22532928, 'steps': 117358, 'loss/train': 1.2340542078018188} 08/31/2021 10:26:43 - INFO - __main__ - Step 117360: {'lr': 5.764596824161683e-05, 'samples': 22533120, 'steps': 117359, 'loss/train': 0.9540321230888367} 08/31/2021 10:26:44 - INFO - __main__ - Step 117361: {'lr': 5.764257861337913e-05, 'samples': 22533312, 'steps': 117360, 'loss/train': 1.4385672807693481} 08/31/2021 10:26:44 - INFO - __main__ - Step 117362: {'lr': 5.763918907181473e-05, 'samples': 22533504, 'steps': 117361, 'loss/train': 0.7594183683395386} 08/31/2021 10:26:45 - INFO - __main__ - Step 117363: {'lr': 5.7635799616925136e-05, 'samples': 22533696, 'steps': 117362, 'loss/train': 0.43612807989120483} 08/31/2021 10:26:46 - INFO - __main__ - Step 117364: {'lr': 5.763241024871196e-05, 'samples': 22533888, 'steps': 117363, 'loss/train': 0.5157126188278198} 08/31/2021 10:26:46 - INFO - __main__ - Step 117365: {'lr': 5.762902096717656e-05, 'samples': 22534080, 'steps': 117364, 'loss/train': 1.2023773193359375} 08/31/2021 10:26:47 - INFO - __main__ - Step 117366: {'lr': 5.762563177232058e-05, 'samples': 22534272, 'steps': 117365, 'loss/train': 1.4508709907531738} 08/31/2021 10:26:47 - INFO - __main__ - Step 117367: {'lr': 5.762224266414554e-05, 'samples': 22534464, 'steps': 117366, 'loss/train': 1.046176791191101} 08/31/2021 10:26:48 - INFO - __main__ - Step 117368: {'lr': 5.76188536426529e-05, 'samples': 22534656, 'steps': 117367, 'loss/train': 0.5922443866729736} 08/31/2021 10:26:49 - INFO - __main__ - Step 117369: {'lr': 5.7615464707844264e-05, 'samples': 22534848, 'steps': 117368, 'loss/train': 1.0962074995040894} 08/31/2021 10:26:49 - INFO - __main__ - Step 117370: {'lr': 5.7612075859721144e-05, 'samples': 22535040, 'steps': 117369, 'loss/train': 1.281229019165039} 08/31/2021 10:26:50 - INFO - __main__ - Step 117371: {'lr': 5.7608687098285015e-05, 'samples': 22535232, 'steps': 117370, 'loss/train': 1.1901276111602783} 08/31/2021 10:26:50 - INFO - __main__ - Step 117372: {'lr': 5.7605298423537483e-05, 'samples': 22535424, 'steps': 117371, 'loss/train': 1.2812753915786743} 08/31/2021 10:26:51 - INFO - __main__ - Step 117373: {'lr': 5.760190983548e-05, 'samples': 22535616, 'steps': 117372, 'loss/train': 0.4024662673473358} 08/31/2021 10:26:52 - INFO - __main__ - Step 117374: {'lr': 5.759852133411414e-05, 'samples': 22535808, 'steps': 117373, 'loss/train': 0.9148058295249939} 08/31/2021 10:26:52 - INFO - __main__ - Step 117375: {'lr': 5.759513291944143e-05, 'samples': 22536000, 'steps': 117374, 'loss/train': 1.1187591552734375} 08/31/2021 10:26:53 - INFO - __main__ - Step 117376: {'lr': 5.759174459146338e-05, 'samples': 22536192, 'steps': 117375, 'loss/train': 1.3241561651229858} 08/31/2021 10:26:53 - INFO - __main__ - Step 117377: {'lr': 5.7588356350181505e-05, 'samples': 22536384, 'steps': 117376, 'loss/train': 0.8444426655769348} 08/31/2021 10:26:53 - INFO - __main__ - Step 117378: {'lr': 5.758496819559744e-05, 'samples': 22536576, 'steps': 117377, 'loss/train': 0.7349441647529602} 08/31/2021 10:26:54 - INFO - __main__ - Step 117379: {'lr': 5.758158012771253e-05, 'samples': 22536768, 'steps': 117378, 'loss/train': 1.4211589097976685} 08/31/2021 10:26:55 - INFO - __main__ - Step 117380: {'lr': 5.75781921465284e-05, 'samples': 22536960, 'steps': 117379, 'loss/train': 1.1634011268615723} 08/31/2021 10:26:56 - INFO - __main__ - Step 117381: {'lr': 5.757480425204656e-05, 'samples': 22537152, 'steps': 117380, 'loss/train': 0.7133014798164368} 08/31/2021 10:26:56 - INFO - __main__ - Step 117382: {'lr': 5.757141644426856e-05, 'samples': 22537344, 'steps': 117381, 'loss/train': 0.6903075575828552} 08/31/2021 10:26:56 - INFO - __main__ - Step 117383: {'lr': 5.756802872319589e-05, 'samples': 22537536, 'steps': 117382, 'loss/train': 0.543926477432251} 08/31/2021 10:26:58 - INFO - __main__ - Step 117384: {'lr': 5.7564641088830114e-05, 'samples': 22537728, 'steps': 117383, 'loss/train': 0.8103286623954773} 08/31/2021 10:26:59 - INFO - __main__ - Step 117385: {'lr': 5.756125354117272e-05, 'samples': 22537920, 'steps': 117384, 'loss/train': 1.1916342973709106} 08/31/2021 10:26:59 - INFO - __main__ - Step 117386: {'lr': 5.755786608022528e-05, 'samples': 22538112, 'steps': 117385, 'loss/train': 0.3477253317832947} 08/31/2021 10:26:59 - INFO - __main__ - Step 117387: {'lr': 5.755447870598929e-05, 'samples': 22538304, 'steps': 117386, 'loss/train': 0.997136652469635} 08/31/2021 10:27:00 - INFO - __main__ - Step 117388: {'lr': 5.755109141846626e-05, 'samples': 22538496, 'steps': 117387, 'loss/train': 0.019025400280952454} 08/31/2021 10:27:00 - INFO - __main__ - Step 117389: {'lr': 5.754770421765776e-05, 'samples': 22538688, 'steps': 117388, 'loss/train': 0.0174085833132267} 08/31/2021 10:27:00 - INFO - __main__ - Step 117390: {'lr': 5.7544317103565306e-05, 'samples': 22538880, 'steps': 117389, 'loss/train': 2.2920327186584473} 08/31/2021 10:27:02 - INFO - __main__ - Step 117391: {'lr': 5.754093007619046e-05, 'samples': 22539072, 'steps': 117390, 'loss/train': 0.9259763360023499} 08/31/2021 10:27:03 - INFO - __main__ - Step 117392: {'lr': 5.7537543135534637e-05, 'samples': 22539264, 'steps': 117391, 'loss/train': 0.60526043176651} 08/31/2021 10:27:03 - INFO - __main__ - Step 117393: {'lr': 5.753415628159944e-05, 'samples': 22539456, 'steps': 117392, 'loss/train': 1.2738745212554932} 08/31/2021 10:27:03 - INFO - __main__ - Step 117394: {'lr': 5.7530769514386375e-05, 'samples': 22539648, 'steps': 117393, 'loss/train': 1.6927717924118042} 08/31/2021 10:27:04 - INFO - __main__ - Step 117395: {'lr': 5.752738283389697e-05, 'samples': 22539840, 'steps': 117394, 'loss/train': 1.0840717554092407} 08/31/2021 10:27:06 - INFO - __main__ - Step 117396: {'lr': 5.7523996240132745e-05, 'samples': 22540032, 'steps': 117395, 'loss/train': 1.4744184017181396} 08/31/2021 10:27:06 - INFO - __main__ - Step 117397: {'lr': 5.752060973309525e-05, 'samples': 22540224, 'steps': 117396, 'loss/train': 1.1867265701293945} 08/31/2021 10:27:06 - INFO - __main__ - Step 117398: {'lr': 5.7517223312786e-05, 'samples': 22540416, 'steps': 117397, 'loss/train': 0.8787274360656738} 08/31/2021 10:27:07 - INFO - __main__ - Step 117399: {'lr': 5.751383697920653e-05, 'samples': 22540608, 'steps': 117398, 'loss/train': 0.798316240310669} 08/31/2021 10:27:07 - INFO - __main__ - Step 117400: {'lr': 5.7510450732358335e-05, 'samples': 22540800, 'steps': 117399, 'loss/train': 0.6715613603591919} 08/31/2021 10:27:09 - INFO - __main__ - Step 117401: {'lr': 5.7507064572242976e-05, 'samples': 22540992, 'steps': 117400, 'loss/train': 1.6371339559555054} 08/31/2021 10:27:09 - INFO - __main__ - Step 117402: {'lr': 5.7503678498861955e-05, 'samples': 22541184, 'steps': 117401, 'loss/train': 1.6484161615371704} 08/31/2021 10:27:10 - INFO - __main__ - Step 117403: {'lr': 5.750029251221686e-05, 'samples': 22541376, 'steps': 117402, 'loss/train': 0.0873597040772438} 08/31/2021 10:27:10 - INFO - __main__ - Step 117404: {'lr': 5.749690661230914e-05, 'samples': 22541568, 'steps': 117403, 'loss/train': 1.0702205896377563} 08/31/2021 10:27:10 - INFO - __main__ - Step 117405: {'lr': 5.7493520799140304e-05, 'samples': 22541760, 'steps': 117404, 'loss/train': 0.2780280113220215} 08/31/2021 10:27:12 - INFO - __main__ - Step 117406: {'lr': 5.749013507271192e-05, 'samples': 22541952, 'steps': 117405, 'loss/train': 1.1502575874328613} 08/31/2021 10:27:12 - INFO - __main__ - Step 117407: {'lr': 5.748674943302551e-05, 'samples': 22542144, 'steps': 117406, 'loss/train': 1.2094907760620117} 08/31/2021 10:27:13 - INFO - __main__ - Step 117408: {'lr': 5.74833638800826e-05, 'samples': 22542336, 'steps': 117407, 'loss/train': 1.459930419921875} 08/31/2021 10:27:13 - INFO - __main__ - Step 117409: {'lr': 5.747997841388472e-05, 'samples': 22542528, 'steps': 117408, 'loss/train': 0.8783527612686157} 08/31/2021 10:27:13 - INFO - __main__ - Step 117410: {'lr': 5.747659303443339e-05, 'samples': 22542720, 'steps': 117409, 'loss/train': 0.9087204933166504} 08/31/2021 10:27:15 - INFO - __main__ - Step 117411: {'lr': 5.7473207741730146e-05, 'samples': 22542912, 'steps': 117410, 'loss/train': 0.8057891130447388} 08/31/2021 10:27:16 - INFO - __main__ - Step 117412: {'lr': 5.746982253577651e-05, 'samples': 22543104, 'steps': 117411, 'loss/train': 1.332918405532837} 08/31/2021 10:27:16 - INFO - __main__ - Step 117413: {'lr': 5.746643741657398e-05, 'samples': 22543296, 'steps': 117412, 'loss/train': 1.3049100637435913} 08/31/2021 10:27:16 - INFO - __main__ - Step 117414: {'lr': 5.7463052384124194e-05, 'samples': 22543488, 'steps': 117413, 'loss/train': 0.9406095743179321} 08/31/2021 10:27:17 - INFO - __main__ - Step 117415: {'lr': 5.745966743842848e-05, 'samples': 22543680, 'steps': 117414, 'loss/train': 2.335228681564331} 08/31/2021 10:27:18 - INFO - __main__ - Step 117416: {'lr': 5.745628257948851e-05, 'samples': 22543872, 'steps': 117415, 'loss/train': 1.359610915184021} 08/31/2021 10:27:19 - INFO - __main__ - Step 117417: {'lr': 5.7452897807305725e-05, 'samples': 22544064, 'steps': 117416, 'loss/train': 1.403274655342102} 08/31/2021 10:27:19 - INFO - __main__ - Step 117418: {'lr': 5.7449513121881734e-05, 'samples': 22544256, 'steps': 117417, 'loss/train': 0.09494993835687637} 08/31/2021 10:27:20 - INFO - __main__ - Step 117419: {'lr': 5.7446128523218013e-05, 'samples': 22544448, 'steps': 117418, 'loss/train': 1.584582805633545} 08/31/2021 10:27:20 - INFO - __main__ - Step 117420: {'lr': 5.744274401131608e-05, 'samples': 22544640, 'steps': 117419, 'loss/train': 0.9871724843978882} 08/31/2021 10:27:20 - INFO - __main__ - Step 117421: {'lr': 5.743935958617746e-05, 'samples': 22544832, 'steps': 117420, 'loss/train': 0.06795540452003479} 08/31/2021 10:27:22 - INFO - __main__ - Step 117422: {'lr': 5.7435975247803726e-05, 'samples': 22545024, 'steps': 117421, 'loss/train': 0.4598047137260437} 08/31/2021 10:27:22 - INFO - __main__ - Step 117423: {'lr': 5.743259099619635e-05, 'samples': 22545216, 'steps': 117422, 'loss/train': 1.0938570499420166} 08/31/2021 10:27:23 - INFO - __main__ - Step 117424: {'lr': 5.742920683135689e-05, 'samples': 22545408, 'steps': 117423, 'loss/train': 1.5599535703659058} 08/31/2021 10:27:23 - INFO - __main__ - Step 117425: {'lr': 5.742582275328692e-05, 'samples': 22545600, 'steps': 117424, 'loss/train': 0.8471634387969971} 08/31/2021 10:27:23 - INFO - __main__ - Step 117426: {'lr': 5.7422438761987856e-05, 'samples': 22545792, 'steps': 117425, 'loss/train': 1.153379201889038} 08/31/2021 10:27:24 - INFO - __main__ - Step 117427: {'lr': 5.741905485746124e-05, 'samples': 22545984, 'steps': 117426, 'loss/train': 0.7299713492393494} 08/31/2021 10:27:25 - INFO - __main__ - Step 117428: {'lr': 5.741567103970863e-05, 'samples': 22546176, 'steps': 117427, 'loss/train': 1.7361513376235962} 08/31/2021 10:27:26 - INFO - __main__ - Step 117429: {'lr': 5.7412287308731546e-05, 'samples': 22546368, 'steps': 117428, 'loss/train': 1.3236523866653442} 08/31/2021 10:27:26 - INFO - __main__ - Step 117430: {'lr': 5.740890366453153e-05, 'samples': 22546560, 'steps': 117429, 'loss/train': 0.8691248893737793} 08/31/2021 10:27:26 - INFO - __main__ - Step 117431: {'lr': 5.740552010711009e-05, 'samples': 22546752, 'steps': 117430, 'loss/train': 1.355383276939392} 08/31/2021 10:27:27 - INFO - __main__ - Step 117432: {'lr': 5.740213663646873e-05, 'samples': 22546944, 'steps': 117431, 'loss/train': 1.1609820127487183} 08/31/2021 10:27:29 - INFO - __main__ - Step 117433: {'lr': 5.739875325260902e-05, 'samples': 22547136, 'steps': 117432, 'loss/train': 0.8515099883079529} 08/31/2021 10:27:29 - INFO - __main__ - Step 117434: {'lr': 5.739536995553243e-05, 'samples': 22547328, 'steps': 117433, 'loss/train': 0.028592772781848907} 08/31/2021 10:27:30 - INFO - __main__ - Step 117435: {'lr': 5.7391986745240516e-05, 'samples': 22547520, 'steps': 117434, 'loss/train': 1.4874284267425537} 08/31/2021 10:27:30 - INFO - __main__ - Step 117436: {'lr': 5.73886036217349e-05, 'samples': 22547712, 'steps': 117435, 'loss/train': 1.0281119346618652} 08/31/2021 10:27:31 - INFO - __main__ - Step 117437: {'lr': 5.7385220585016914e-05, 'samples': 22547904, 'steps': 117436, 'loss/train': 0.9302029609680176} 08/31/2021 10:27:32 - INFO - __main__ - Step 117438: {'lr': 5.7381837635088195e-05, 'samples': 22548096, 'steps': 117437, 'loss/train': 1.74702787399292} 08/31/2021 10:27:33 - INFO - __main__ - Step 117439: {'lr': 5.737845477195022e-05, 'samples': 22548288, 'steps': 117438, 'loss/train': 1.0401374101638794} 08/31/2021 10:27:33 - INFO - __main__ - Step 117440: {'lr': 5.737507199560457e-05, 'samples': 22548480, 'steps': 117439, 'loss/train': 0.9576507806777954} 08/31/2021 10:27:33 - INFO - __main__ - Step 117441: {'lr': 5.737168930605272e-05, 'samples': 22548672, 'steps': 117440, 'loss/train': 1.4879299402236938} 08/31/2021 10:27:34 - INFO - __main__ - Step 117442: {'lr': 5.7368306703296234e-05, 'samples': 22548864, 'steps': 117441, 'loss/train': 0.5678689479827881} 08/31/2021 10:27:35 - INFO - __main__ - Step 117443: {'lr': 5.7364924187336606e-05, 'samples': 22549056, 'steps': 117442, 'loss/train': 1.0280559062957764} 08/31/2021 10:27:36 - INFO - __main__ - Step 117444: {'lr': 5.7361541758175344e-05, 'samples': 22549248, 'steps': 117443, 'loss/train': 0.9186027646064758} 08/31/2021 10:27:36 - INFO - __main__ - Step 117445: {'lr': 5.735815941581404e-05, 'samples': 22549440, 'steps': 117444, 'loss/train': 2.3531551361083984} 08/31/2021 10:27:36 - INFO - __main__ - Step 117446: {'lr': 5.735477716025417e-05, 'samples': 22549632, 'steps': 117445, 'loss/train': 1.6141988039016724} 08/31/2021 10:27:37 - INFO - __main__ - Step 117447: {'lr': 5.73513949914973e-05, 'samples': 22549824, 'steps': 117446, 'loss/train': 0.9328145384788513} 08/31/2021 10:27:37 - INFO - __main__ - Step 117448: {'lr': 5.734801290954489e-05, 'samples': 22550016, 'steps': 117447, 'loss/train': 1.4562138319015503} 08/31/2021 10:27:38 - INFO - __main__ - Step 117449: {'lr': 5.7344630914398455e-05, 'samples': 22550208, 'steps': 117448, 'loss/train': 1.4007128477096558} 08/31/2021 10:27:39 - INFO - __main__ - Step 117450: {'lr': 5.734124900605958e-05, 'samples': 22550400, 'steps': 117449, 'loss/train': 0.9240977168083191} 08/31/2021 10:27:39 - INFO - __main__ - Step 117451: {'lr': 5.733786718452977e-05, 'samples': 22550592, 'steps': 117450, 'loss/train': 1.088749647140503} 08/31/2021 10:27:40 - INFO - __main__ - Step 117452: {'lr': 5.733448544981054e-05, 'samples': 22550784, 'steps': 117451, 'loss/train': 1.0458863973617554} 08/31/2021 10:27:40 - INFO - __main__ - Step 117453: {'lr': 5.7331103801903403e-05, 'samples': 22550976, 'steps': 117452, 'loss/train': 0.168027862906456} 08/31/2021 10:27:42 - INFO - __main__ - Step 117454: {'lr': 5.7327722240809926e-05, 'samples': 22551168, 'steps': 117453, 'loss/train': 0.2729582190513611} 08/31/2021 10:27:42 - INFO - __main__ - Step 117455: {'lr': 5.732434076653159e-05, 'samples': 22551360, 'steps': 117454, 'loss/train': 0.37507104873657227} 08/31/2021 10:27:43 - INFO - __main__ - Step 117456: {'lr': 5.732095937906992e-05, 'samples': 22551552, 'steps': 117455, 'loss/train': 1.084608793258667} 08/31/2021 10:27:43 - INFO - __main__ - Step 117457: {'lr': 5.731757807842647e-05, 'samples': 22551744, 'steps': 117456, 'loss/train': 1.0148106813430786} 08/31/2021 10:27:43 - INFO - __main__ - Step 117458: {'lr': 5.731419686460279e-05, 'samples': 22551936, 'steps': 117457, 'loss/train': 1.1514617204666138} 08/31/2021 10:27:45 - INFO - __main__ - Step 117459: {'lr': 5.731081573760033e-05, 'samples': 22552128, 'steps': 117458, 'loss/train': 1.20558762550354} 08/31/2021 10:27:45 - INFO - __main__ - Step 117460: {'lr': 5.7307434697420616e-05, 'samples': 22552320, 'steps': 117459, 'loss/train': 1.2016451358795166} 08/31/2021 10:27:45 - INFO - __main__ - Step 117461: {'lr': 5.7304053744065193e-05, 'samples': 22552512, 'steps': 117460, 'loss/train': 1.1909469366073608} 08/31/2021 10:27:46 - INFO - __main__ - Step 117462: {'lr': 5.7300672877535595e-05, 'samples': 22552704, 'steps': 117461, 'loss/train': 1.036861777305603} 08/31/2021 10:27:46 - INFO - __main__ - Step 117463: {'lr': 5.729729209783335e-05, 'samples': 22552896, 'steps': 117462, 'loss/train': 1.153304100036621} 08/31/2021 10:27:48 - INFO - __main__ - Step 117464: {'lr': 5.729391140495999e-05, 'samples': 22553088, 'steps': 117463, 'loss/train': 0.42451170086860657} 08/31/2021 10:27:48 - INFO - __main__ - Step 117465: {'lr': 5.7290530798916995e-05, 'samples': 22553280, 'steps': 117464, 'loss/train': 1.4683092832565308} 08/31/2021 10:27:49 - INFO - __main__ - Step 117466: {'lr': 5.7287150279705904e-05, 'samples': 22553472, 'steps': 117465, 'loss/train': 1.5497751235961914} 08/31/2021 10:27:49 - INFO - __main__ - Step 117467: {'lr': 5.728376984732825e-05, 'samples': 22553664, 'steps': 117466, 'loss/train': 0.07321666181087494} 08/31/2021 10:27:49 - INFO - __main__ - Step 117468: {'lr': 5.7280389501785575e-05, 'samples': 22553856, 'steps': 117467, 'loss/train': 0.7776740193367004} 08/31/2021 10:27:51 - INFO - __main__ - Step 117469: {'lr': 5.727700924307938e-05, 'samples': 22554048, 'steps': 117468, 'loss/train': 1.4337035417556763} 08/31/2021 10:27:52 - INFO - __main__ - Step 117470: {'lr': 5.727362907121117e-05, 'samples': 22554240, 'steps': 117469, 'loss/train': 1.4547810554504395} 08/31/2021 10:27:52 - INFO - __main__ - Step 117471: {'lr': 5.727024898618252e-05, 'samples': 22554432, 'steps': 117470, 'loss/train': 1.5413566827774048} 08/31/2021 10:27:52 - INFO - __main__ - Step 117472: {'lr': 5.726686898799496e-05, 'samples': 22554624, 'steps': 117471, 'loss/train': 1.1944838762283325} 08/31/2021 10:27:53 - INFO - __main__ - Step 117473: {'lr': 5.726348907664994e-05, 'samples': 22554816, 'steps': 117472, 'loss/train': 0.07485876977443695} 08/31/2021 10:27:53 - INFO - __main__ - Step 117474: {'lr': 5.7260109252149e-05, 'samples': 22555008, 'steps': 117473, 'loss/train': 0.6416715383529663} 08/31/2021 10:27:55 - INFO - __main__ - Step 117475: {'lr': 5.7256729514493677e-05, 'samples': 22555200, 'steps': 117474, 'loss/train': 1.0438278913497925} 08/31/2021 10:27:55 - INFO - __main__ - Step 117476: {'lr': 5.72533498636855e-05, 'samples': 22555392, 'steps': 117475, 'loss/train': 1.2325738668441772} 08/31/2021 10:27:55 - INFO - __main__ - Step 117477: {'lr': 5.7249970299725977e-05, 'samples': 22555584, 'steps': 117476, 'loss/train': 0.11704696714878082} 08/31/2021 10:27:56 - INFO - __main__ - Step 117478: {'lr': 5.7246590822616654e-05, 'samples': 22555776, 'steps': 117477, 'loss/train': 1.1200826168060303} 08/31/2021 10:27:56 - INFO - __main__ - Step 117479: {'lr': 5.7243211432359055e-05, 'samples': 22555968, 'steps': 117478, 'loss/train': 0.36497387290000916} 08/31/2021 10:27:58 - INFO - __main__ - Step 117480: {'lr': 5.723983212895467e-05, 'samples': 22556160, 'steps': 117479, 'loss/train': 0.8429976105690002} 08/31/2021 10:27:58 - INFO - __main__ - Step 117481: {'lr': 5.7236452912405034e-05, 'samples': 22556352, 'steps': 117480, 'loss/train': 1.015771508216858} 08/31/2021 10:27:58 - INFO - __main__ - Step 117482: {'lr': 5.72330737827117e-05, 'samples': 22556544, 'steps': 117481, 'loss/train': 1.0765290260314941} 08/31/2021 10:27:59 - INFO - __main__ - Step 117483: {'lr': 5.722969473987616e-05, 'samples': 22556736, 'steps': 117482, 'loss/train': 0.9655777812004089} 08/31/2021 10:27:59 - INFO - __main__ - Step 117484: {'lr': 5.722631578389995e-05, 'samples': 22556928, 'steps': 117483, 'loss/train': 1.1285291910171509} 08/31/2021 10:28:01 - INFO - __main__ - Step 117485: {'lr': 5.722293691478467e-05, 'samples': 22557120, 'steps': 117484, 'loss/train': 1.2951419353485107} 08/31/2021 10:28:01 - INFO - __main__ - Step 117486: {'lr': 5.7219558132531656e-05, 'samples': 22557312, 'steps': 117485, 'loss/train': 1.7930244207382202} 08/31/2021 10:28:01 - INFO - __main__ - Step 117487: {'lr': 5.7216179437142576e-05, 'samples': 22557504, 'steps': 117486, 'loss/train': 0.9123130440711975} 08/31/2021 10:28:02 - INFO - __main__ - Step 117488: {'lr': 5.721280082861888e-05, 'samples': 22557696, 'steps': 117487, 'loss/train': 1.7157422304153442} 08/31/2021 10:28:02 - INFO - __main__ - Step 117489: {'lr': 5.720942230696213e-05, 'samples': 22557888, 'steps': 117488, 'loss/train': 1.9779953956604004} 08/31/2021 10:28:02 - INFO - __main__ - Step 117490: {'lr': 5.7206043872173846e-05, 'samples': 22558080, 'steps': 117489, 'loss/train': 1.1821612119674683} 08/31/2021 10:28:05 - INFO - __main__ - Step 117491: {'lr': 5.7202665524255516e-05, 'samples': 22558272, 'steps': 117490, 'loss/train': 0.3704723119735718} 08/31/2021 10:28:05 - INFO - __main__ - Step 117492: {'lr': 5.719928726320872e-05, 'samples': 22558464, 'steps': 117491, 'loss/train': 1.0727721452713013} 08/31/2021 10:28:05 - INFO - __main__ - Step 117493: {'lr': 5.719590908903494e-05, 'samples': 22558656, 'steps': 117492, 'loss/train': 0.27372586727142334} 08/31/2021 10:28:06 - INFO - __main__ - Step 117494: {'lr': 5.7192531001735716e-05, 'samples': 22558848, 'steps': 117493, 'loss/train': 1.082515001296997} 08/31/2021 10:28:06 - INFO - __main__ - Step 117495: {'lr': 5.718915300131256e-05, 'samples': 22559040, 'steps': 117494, 'loss/train': 1.8388832807540894} 08/31/2021 10:28:07 - INFO - __main__ - Step 117496: {'lr': 5.718577508776698e-05, 'samples': 22559232, 'steps': 117495, 'loss/train': 0.8089550733566284} 08/31/2021 10:28:08 - INFO - __main__ - Step 117497: {'lr': 5.718239726110053e-05, 'samples': 22559424, 'steps': 117496, 'loss/train': 1.5283070802688599} 08/31/2021 10:28:08 - INFO - __main__ - Step 117498: {'lr': 5.717901952131471e-05, 'samples': 22559616, 'steps': 117497, 'loss/train': 0.45277515053749084} 08/31/2021 10:28:09 - INFO - __main__ - Step 117499: {'lr': 5.7175641868411124e-05, 'samples': 22559808, 'steps': 117498, 'loss/train': 1.9824358224868774} 08/31/2021 10:28:09 - INFO - __main__ - Step 117500: {'lr': 5.7172264302391145e-05, 'samples': 22560000, 'steps': 117499, 'loss/train': 1.0596234798431396} 08/31/2021 10:28:11 - INFO - __main__ - Step 117501: {'lr': 5.7168886823256355e-05, 'samples': 22560192, 'steps': 117500, 'loss/train': 1.3321924209594727} 08/31/2021 10:28:11 - INFO - __main__ - Step 117502: {'lr': 5.7165509431008315e-05, 'samples': 22560384, 'steps': 117501, 'loss/train': 0.01664193533360958} 08/31/2021 10:28:12 - INFO - __main__ - Step 117503: {'lr': 5.7162132125648495e-05, 'samples': 22560576, 'steps': 117502, 'loss/train': 1.239764928817749} 08/31/2021 10:28:12 - INFO - __main__ - Step 117504: {'lr': 5.715875490717845e-05, 'samples': 22560768, 'steps': 117503, 'loss/train': 0.8293529152870178} 08/31/2021 10:28:12 - INFO - __main__ - Step 117505: {'lr': 5.7155377775599706e-05, 'samples': 22560960, 'steps': 117504, 'loss/train': 1.1671333312988281} 08/31/2021 10:28:13 - INFO - __main__ - Step 117506: {'lr': 5.715200073091378e-05, 'samples': 22561152, 'steps': 117505, 'loss/train': 0.15542879700660706} 08/31/2021 10:28:14 - INFO - __main__ - Step 117507: {'lr': 5.714862377312216e-05, 'samples': 22561344, 'steps': 117506, 'loss/train': 0.5800839066505432} 08/31/2021 10:28:15 - INFO - __main__ - Step 117508: {'lr': 5.7145246902226416e-05, 'samples': 22561536, 'steps': 117507, 'loss/train': 1.4190688133239746} 08/31/2021 10:28:15 - INFO - __main__ - Step 117509: {'lr': 5.7141870118228026e-05, 'samples': 22561728, 'steps': 117508, 'loss/train': 0.8128732442855835} 08/31/2021 10:28:16 - INFO - __main__ - Step 117510: {'lr': 5.713849342112856e-05, 'samples': 22561920, 'steps': 117509, 'loss/train': 1.4626424312591553} 08/31/2021 10:28:16 - INFO - __main__ - Step 117511: {'lr': 5.713511681092951e-05, 'samples': 22562112, 'steps': 117510, 'loss/train': 1.4222415685653687} 08/31/2021 10:28:17 - INFO - __main__ - Step 117512: {'lr': 5.713174028763246e-05, 'samples': 22562304, 'steps': 117511, 'loss/train': 0.07604751735925674} 08/31/2021 10:28:18 - INFO - __main__ - Step 117513: {'lr': 5.712836385123879e-05, 'samples': 22562496, 'steps': 117512, 'loss/train': 1.2282809019088745} 08/31/2021 10:28:18 - INFO - __main__ - Step 117514: {'lr': 5.71249875017501e-05, 'samples': 22562688, 'steps': 117513, 'loss/train': 1.4764702320098877} 08/31/2021 10:28:19 - INFO - __main__ - Step 117515: {'lr': 5.7121611239167954e-05, 'samples': 22562880, 'steps': 117514, 'loss/train': 1.623579740524292} 08/31/2021 10:28:19 - INFO - __main__ - Step 117516: {'lr': 5.711823506349379e-05, 'samples': 22563072, 'steps': 117515, 'loss/train': 0.7388535141944885} 08/31/2021 10:28:20 - INFO - __main__ - Step 117517: {'lr': 5.7114858974729204e-05, 'samples': 22563264, 'steps': 117516, 'loss/train': 1.391238808631897} 08/31/2021 10:28:21 - INFO - __main__ - Step 117518: {'lr': 5.7111482972875664e-05, 'samples': 22563456, 'steps': 117517, 'loss/train': 0.9697515964508057} 08/31/2021 10:28:21 - INFO - __main__ - Step 117519: {'lr': 5.710810705793473e-05, 'samples': 22563648, 'steps': 117518, 'loss/train': 0.7479463219642639} 08/31/2021 10:28:22 - INFO - __main__ - Step 117520: {'lr': 5.710473122990789e-05, 'samples': 22563840, 'steps': 117519, 'loss/train': 1.3544522523880005} 08/31/2021 10:28:22 - INFO - __main__ - Step 117521: {'lr': 5.710135548879669e-05, 'samples': 22564032, 'steps': 117520, 'loss/train': 0.1947190761566162} 08/31/2021 10:28:24 - INFO - __main__ - Step 117522: {'lr': 5.709797983460266e-05, 'samples': 22564224, 'steps': 117521, 'loss/train': 1.2426902055740356} 08/31/2021 10:28:24 - INFO - __main__ - Step 117523: {'lr': 5.709460426732727e-05, 'samples': 22564416, 'steps': 117522, 'loss/train': 1.1596571207046509} 08/31/2021 10:28:24 - INFO - __main__ - Step 117524: {'lr': 5.7091228786972094e-05, 'samples': 22564608, 'steps': 117523, 'loss/train': 1.210870385169983} 08/31/2021 10:28:25 - INFO - __main__ - Step 117525: {'lr': 5.708785339353864e-05, 'samples': 22564800, 'steps': 117524, 'loss/train': 0.3914732336997986} 08/31/2021 10:28:25 - INFO - __main__ - Step 117526: {'lr': 5.7084478087028494e-05, 'samples': 22564992, 'steps': 117525, 'loss/train': 1.5237243175506592} 08/31/2021 10:28:26 - INFO - __main__ - Step 117527: {'lr': 5.7081102867443e-05, 'samples': 22565184, 'steps': 117526, 'loss/train': 0.04706944152712822} 08/31/2021 10:28:27 - INFO - __main__ - Step 117528: {'lr': 5.7077727734783814e-05, 'samples': 22565376, 'steps': 117527, 'loss/train': 0.8056032061576843} 08/31/2021 10:28:27 - INFO - __main__ - Step 117529: {'lr': 5.7074352689052425e-05, 'samples': 22565568, 'steps': 117528, 'loss/train': 1.671651005744934} 08/31/2021 10:28:28 - INFO - __main__ - Step 117530: {'lr': 5.707097773025035e-05, 'samples': 22565760, 'steps': 117529, 'loss/train': 1.3971647024154663} 08/31/2021 10:28:28 - INFO - __main__ - Step 117531: {'lr': 5.7067602858379144e-05, 'samples': 22565952, 'steps': 117530, 'loss/train': 1.1813080310821533} 08/31/2021 10:28:28 - INFO - __main__ - Step 117532: {'lr': 5.706422807344025e-05, 'samples': 22566144, 'steps': 117531, 'loss/train': 0.5625690221786499} 08/31/2021 10:28:30 - INFO - __main__ - Step 117533: {'lr': 5.7060853375435264e-05, 'samples': 22566336, 'steps': 117532, 'loss/train': 0.7534043788909912} 08/31/2021 10:28:30 - INFO - __main__ - Step 117534: {'lr': 5.7057478764365676e-05, 'samples': 22566528, 'steps': 117533, 'loss/train': 0.8520200848579407} 08/31/2021 10:28:31 - INFO - __main__ - Step 117535: {'lr': 5.705410424023302e-05, 'samples': 22566720, 'steps': 117534, 'loss/train': 0.5412607192993164} 08/31/2021 10:28:31 - INFO - __main__ - Step 117536: {'lr': 5.70507298030388e-05, 'samples': 22566912, 'steps': 117535, 'loss/train': 1.0847468376159668} 08/31/2021 10:28:32 - INFO - __main__ - Step 117537: {'lr': 5.704735545278453e-05, 'samples': 22567104, 'steps': 117536, 'loss/train': 1.2036656141281128} 08/31/2021 10:28:33 - INFO - __main__ - Step 117538: {'lr': 5.704398118947177e-05, 'samples': 22567296, 'steps': 117537, 'loss/train': 0.8793869614601135} 08/31/2021 10:28:34 - INFO - __main__ - Step 117539: {'lr': 5.704060701310207e-05, 'samples': 22567488, 'steps': 117538, 'loss/train': 1.3678369522094727} 08/31/2021 10:28:34 - INFO - __main__ - Step 117540: {'lr': 5.703723292367682e-05, 'samples': 22567680, 'steps': 117539, 'loss/train': 1.232909083366394} 08/31/2021 10:28:34 - INFO - __main__ - Step 117541: {'lr': 5.703385892119764e-05, 'samples': 22567872, 'steps': 117540, 'loss/train': 0.947249174118042} 08/31/2021 10:28:35 - INFO - __main__ - Step 117542: {'lr': 5.703048500566599e-05, 'samples': 22568064, 'steps': 117541, 'loss/train': 1.7630971670150757} 08/31/2021 10:28:37 - INFO - __main__ - Step 117543: {'lr': 5.702711117708345e-05, 'samples': 22568256, 'steps': 117542, 'loss/train': 0.046658944338560104} 08/31/2021 10:28:37 - INFO - __main__ - Step 117544: {'lr': 5.70237374354515e-05, 'samples': 22568448, 'steps': 117543, 'loss/train': 1.1418826580047607} 08/31/2021 10:28:38 - INFO - __main__ - Step 117545: {'lr': 5.702036378077169e-05, 'samples': 22568640, 'steps': 117544, 'loss/train': 1.5514127016067505} 08/31/2021 10:28:38 - INFO - __main__ - Step 117546: {'lr': 5.7016990213045516e-05, 'samples': 22568832, 'steps': 117545, 'loss/train': 1.7421823740005493} 08/31/2021 10:28:38 - INFO - __main__ - Step 117547: {'lr': 5.7013616732274534e-05, 'samples': 22569024, 'steps': 117546, 'loss/train': 0.14161525666713715} 08/31/2021 10:28:39 - INFO - __main__ - Step 117548: {'lr': 5.701024333846019e-05, 'samples': 22569216, 'steps': 117547, 'loss/train': 1.4728468656539917} 08/31/2021 10:28:41 - INFO - __main__ - Step 117549: {'lr': 5.7006870031604096e-05, 'samples': 22569408, 'steps': 117548, 'loss/train': 1.1501376628875732} 08/31/2021 10:28:41 - INFO - __main__ - Step 117550: {'lr': 5.7003496811707716e-05, 'samples': 22569600, 'steps': 117549, 'loss/train': 1.1194957494735718} 08/31/2021 10:28:41 - INFO - __main__ - Step 117551: {'lr': 5.700012367877258e-05, 'samples': 22569792, 'steps': 117550, 'loss/train': 0.015432106330990791} 08/31/2021 10:28:42 - INFO - __main__ - Step 117552: {'lr': 5.6996750632800215e-05, 'samples': 22569984, 'steps': 117551, 'loss/train': 1.7098761796951294} 08/31/2021 10:28:42 - INFO - __main__ - Step 117553: {'lr': 5.6993377673792205e-05, 'samples': 22570176, 'steps': 117552, 'loss/train': 1.1042218208312988} 08/31/2021 10:28:43 - INFO - __main__ - Step 117554: {'lr': 5.69900048017499e-05, 'samples': 22570368, 'steps': 117553, 'loss/train': 0.18258081376552582} 08/31/2021 10:28:44 - INFO - __main__ - Step 117555: {'lr': 5.698663201667495e-05, 'samples': 22570560, 'steps': 117554, 'loss/train': 1.0470253229141235} 08/31/2021 10:28:44 - INFO - __main__ - Step 117556: {'lr': 5.698325931856885e-05, 'samples': 22570752, 'steps': 117555, 'loss/train': 0.7728793025016785} 08/31/2021 10:28:45 - INFO - __main__ - Step 117557: {'lr': 5.6979886707433123e-05, 'samples': 22570944, 'steps': 117556, 'loss/train': 0.9210044145584106} 08/31/2021 10:28:45 - INFO - __main__ - Step 117558: {'lr': 5.697651418326924e-05, 'samples': 22571136, 'steps': 117557, 'loss/train': 0.7882452607154846} 08/31/2021 10:28:46 - INFO - __main__ - Step 117559: {'lr': 5.697314174607879e-05, 'samples': 22571328, 'steps': 117558, 'loss/train': 2.0719447135925293} 08/31/2021 10:28:47 - INFO - __main__ - Step 117560: {'lr': 5.696976939586327e-05, 'samples': 22571520, 'steps': 117559, 'loss/train': 0.39587411284446716} 08/31/2021 10:28:48 - INFO - __main__ - Step 117561: {'lr': 5.6966397132624166e-05, 'samples': 22571712, 'steps': 117560, 'loss/train': 1.1743252277374268} 08/31/2021 10:28:48 - INFO - __main__ - Step 117562: {'lr': 5.696302495636305e-05, 'samples': 22571904, 'steps': 117561, 'loss/train': 0.35782527923583984} 08/31/2021 10:28:48 - INFO - __main__ - Step 117563: {'lr': 5.695965286708141e-05, 'samples': 22572096, 'steps': 117562, 'loss/train': 1.0646134614944458} 08/31/2021 10:28:49 - INFO - __main__ - Step 117564: {'lr': 5.6956280864780775e-05, 'samples': 22572288, 'steps': 117563, 'loss/train': 0.4863603711128235} 08/31/2021 10:28:50 - INFO - __main__ - Step 117565: {'lr': 5.6952908949462646e-05, 'samples': 22572480, 'steps': 117564, 'loss/train': 0.46051129698753357} 08/31/2021 10:28:51 - INFO - __main__ - Step 117566: {'lr': 5.694953712112863e-05, 'samples': 22572672, 'steps': 117565, 'loss/train': 0.9564730525016785} 08/31/2021 10:28:51 - INFO - __main__ - Step 117567: {'lr': 5.6946165379780115e-05, 'samples': 22572864, 'steps': 117566, 'loss/train': 1.131967544555664} 08/31/2021 10:28:52 - INFO - __main__ - Step 117568: {'lr': 5.694279372541866e-05, 'samples': 22573056, 'steps': 117567, 'loss/train': 2.0164289474487305} 08/31/2021 10:28:52 - INFO - __main__ - Step 117569: {'lr': 5.6939422158045844e-05, 'samples': 22573248, 'steps': 117568, 'loss/train': 0.601409375667572} 08/31/2021 10:28:53 - INFO - __main__ - Step 117570: {'lr': 5.693605067766311e-05, 'samples': 22573440, 'steps': 117569, 'loss/train': 1.5393786430358887} 08/31/2021 10:28:54 - INFO - __main__ - Step 117571: {'lr': 5.693267928427201e-05, 'samples': 22573632, 'steps': 117570, 'loss/train': 0.9566604495048523} 08/31/2021 10:28:54 - INFO - __main__ - Step 117572: {'lr': 5.6929307977874076e-05, 'samples': 22573824, 'steps': 117571, 'loss/train': 0.7051647305488586} 08/31/2021 10:28:55 - INFO - __main__ - Step 117573: {'lr': 5.692593675847082e-05, 'samples': 22574016, 'steps': 117572, 'loss/train': 0.34163984656333923} 08/31/2021 10:28:55 - INFO - __main__ - Step 117574: {'lr': 5.692256562606376e-05, 'samples': 22574208, 'steps': 117573, 'loss/train': 1.477932095527649} 08/31/2021 10:28:55 - INFO - __main__ - Step 117575: {'lr': 5.691919458065439e-05, 'samples': 22574400, 'steps': 117574, 'loss/train': 1.2887375354766846} 08/31/2021 10:28:57 - INFO - __main__ - Step 117576: {'lr': 5.691582362224429e-05, 'samples': 22574592, 'steps': 117575, 'loss/train': 1.2926347255706787} 08/31/2021 10:28:57 - INFO - __main__ - Step 117577: {'lr': 5.69124527508349e-05, 'samples': 22574784, 'steps': 117576, 'loss/train': 1.3359702825546265} 08/31/2021 10:28:58 - INFO - __main__ - Step 117578: {'lr': 5.69090819664278e-05, 'samples': 22574976, 'steps': 117577, 'loss/train': 1.5115761756896973} 08/31/2021 10:28:58 - INFO - __main__ - Step 117579: {'lr': 5.690571126902458e-05, 'samples': 22575168, 'steps': 117578, 'loss/train': 1.2860279083251953} 08/31/2021 10:28:58 - INFO - __main__ - Step 117580: {'lr': 5.6902340658626564e-05, 'samples': 22575360, 'steps': 117579, 'loss/train': 1.4764759540557861} 08/31/2021 10:29:00 - INFO - __main__ - Step 117581: {'lr': 5.689897013523537e-05, 'samples': 22575552, 'steps': 117580, 'loss/train': 1.8223025798797607} 08/31/2021 10:29:00 - INFO - __main__ - Step 117582: {'lr': 5.689559969885255e-05, 'samples': 22575744, 'steps': 117581, 'loss/train': 0.8498911261558533} 08/31/2021 10:29:01 - INFO - __main__ - Step 117583: {'lr': 5.689222934947958e-05, 'samples': 22575936, 'steps': 117582, 'loss/train': 0.900336503982544} 08/31/2021 10:29:01 - INFO - __main__ - Step 117584: {'lr': 5.688885908711797e-05, 'samples': 22576128, 'steps': 117583, 'loss/train': 1.098732352256775} 08/31/2021 10:29:01 - INFO - __main__ - Step 117585: {'lr': 5.688548891176929e-05, 'samples': 22576320, 'steps': 117584, 'loss/train': 0.6830602884292603} 08/31/2021 10:29:03 - INFO - __main__ - Step 117586: {'lr': 5.6882118823435e-05, 'samples': 22576512, 'steps': 117585, 'loss/train': 1.2013906240463257} 08/31/2021 10:29:03 - INFO - __main__ - Step 117587: {'lr': 5.687874882211666e-05, 'samples': 22576704, 'steps': 117586, 'loss/train': 0.14147086441516876} 08/31/2021 10:29:04 - INFO - __main__ - Step 117588: {'lr': 5.68753789078158e-05, 'samples': 22576896, 'steps': 117587, 'loss/train': 0.05701136589050293} 08/31/2021 10:29:04 - INFO - __main__ - Step 117589: {'lr': 5.6872009080533885e-05, 'samples': 22577088, 'steps': 117588, 'loss/train': 1.214255690574646} 08/31/2021 10:29:04 - INFO - __main__ - Step 117590: {'lr': 5.6868639340272474e-05, 'samples': 22577280, 'steps': 117589, 'loss/train': 0.7115426659584045} 08/31/2021 10:29:06 - INFO - __main__ - Step 117591: {'lr': 5.6865269687033066e-05, 'samples': 22577472, 'steps': 117590, 'loss/train': 1.0087718963623047} 08/31/2021 10:29:06 - INFO - __main__ - Step 117592: {'lr': 5.686190012081719e-05, 'samples': 22577664, 'steps': 117591, 'loss/train': 0.5308879017829895} 08/31/2021 10:29:06 - INFO - __main__ - Step 117593: {'lr': 5.685853064162644e-05, 'samples': 22577856, 'steps': 117592, 'loss/train': 0.8003612160682678} 08/31/2021 10:29:07 - INFO - __main__ - Step 117594: {'lr': 5.685516124946219e-05, 'samples': 22578048, 'steps': 117593, 'loss/train': 1.0254439115524292} 08/31/2021 10:29:07 - INFO - __main__ - Step 117595: {'lr': 5.685179194432599e-05, 'samples': 22578240, 'steps': 117594, 'loss/train': 1.2464419603347778} 08/31/2021 10:29:09 - INFO - __main__ - Step 117596: {'lr': 5.684842272621943e-05, 'samples': 22578432, 'steps': 117595, 'loss/train': 0.9995618462562561} 08/31/2021 10:29:09 - INFO - __main__ - Step 117597: {'lr': 5.684505359514397e-05, 'samples': 22578624, 'steps': 117596, 'loss/train': 0.8227267861366272} 08/31/2021 10:29:09 - INFO - __main__ - Step 117598: {'lr': 5.684168455110117e-05, 'samples': 22578816, 'steps': 117597, 'loss/train': 1.3236629962921143} 08/31/2021 10:29:10 - INFO - __main__ - Step 117599: {'lr': 5.68383155940925e-05, 'samples': 22579008, 'steps': 117598, 'loss/train': 1.3704713582992554} 08/31/2021 10:29:10 - INFO - __main__ - Step 117600: {'lr': 5.6834946724119515e-05, 'samples': 22579200, 'steps': 117599, 'loss/train': 0.8623366951942444} 08/31/2021 10:29:12 - INFO - __main__ - Step 117601: {'lr': 5.683157794118371e-05, 'samples': 22579392, 'steps': 117600, 'loss/train': 0.7271677851676941} 08/31/2021 10:29:13 - INFO - __main__ - Step 117602: {'lr': 5.6828209245286644e-05, 'samples': 22579584, 'steps': 117601, 'loss/train': 0.0398888885974884} 08/31/2021 10:29:13 - INFO - __main__ - Step 117603: {'lr': 5.682484063642979e-05, 'samples': 22579776, 'steps': 117602, 'loss/train': 1.3041605949401855} 08/31/2021 10:29:13 - INFO - __main__ - Step 117604: {'lr': 5.6821472114614666e-05, 'samples': 22579968, 'steps': 117603, 'loss/train': 0.9334701299667358} 08/31/2021 10:29:14 - INFO - __main__ - Step 117605: {'lr': 5.681810367984283e-05, 'samples': 22580160, 'steps': 117604, 'loss/train': 0.8629205822944641} 08/31/2021 10:29:16 - INFO - __main__ - Step 117606: {'lr': 5.6814735332115844e-05, 'samples': 22580352, 'steps': 117605, 'loss/train': 1.1869233846664429} 08/31/2021 10:29:16 - INFO - __main__ - Step 117607: {'lr': 5.681136707143506e-05, 'samples': 22580544, 'steps': 117606, 'loss/train': 0.9334849119186401} 08/31/2021 10:29:16 - INFO - __main__ - Step 117608: {'lr': 5.680799889780211e-05, 'samples': 22580736, 'steps': 117607, 'loss/train': 0.893422544002533} 08/31/2021 10:29:17 - INFO - __main__ - Step 117609: {'lr': 5.680463081121851e-05, 'samples': 22580928, 'steps': 117608, 'loss/train': 0.9786359071731567} 08/31/2021 10:29:17 - INFO - __main__ - Step 117610: {'lr': 5.680126281168574e-05, 'samples': 22581120, 'steps': 117609, 'loss/train': 0.9872179627418518} 08/31/2021 10:29:17 - INFO - __main__ - Step 117611: {'lr': 5.679789489920536e-05, 'samples': 22581312, 'steps': 117610, 'loss/train': 1.4215344190597534} 08/31/2021 10:29:19 - INFO - __main__ - Step 117612: {'lr': 5.6794527073778854e-05, 'samples': 22581504, 'steps': 117611, 'loss/train': 1.2595704793930054} 08/31/2021 10:29:19 - INFO - __main__ - Step 117613: {'lr': 5.679115933540777e-05, 'samples': 22581696, 'steps': 117612, 'loss/train': 1.0080517530441284} 08/31/2021 10:29:20 - INFO - __main__ - Step 117614: {'lr': 5.6787791684093563e-05, 'samples': 22581888, 'steps': 117613, 'loss/train': 1.2439948320388794} 08/31/2021 10:29:20 - INFO - __main__ - Step 117615: {'lr': 5.678442411983783e-05, 'samples': 22582080, 'steps': 117614, 'loss/train': 1.4593424797058105} 08/31/2021 10:29:21 - INFO - __main__ - Step 117616: {'lr': 5.678105664264205e-05, 'samples': 22582272, 'steps': 117615, 'loss/train': 1.2852317094802856} 08/31/2021 10:29:21 - INFO - __main__ - Step 117617: {'lr': 5.677768925250776e-05, 'samples': 22582464, 'steps': 117616, 'loss/train': 0.7277761101722717} 08/31/2021 10:29:22 - INFO - __main__ - Step 117618: {'lr': 5.677432194943644e-05, 'samples': 22582656, 'steps': 117617, 'loss/train': 0.7306768298149109} 08/31/2021 10:29:23 - INFO - __main__ - Step 117619: {'lr': 5.677095473342964e-05, 'samples': 22582848, 'steps': 117618, 'loss/train': 1.6518149375915527} 08/31/2021 10:29:23 - INFO - __main__ - Step 117620: {'lr': 5.676758760448891e-05, 'samples': 22583040, 'steps': 117619, 'loss/train': 0.8636143803596497} 08/31/2021 10:29:24 - INFO - __main__ - Step 117621: {'lr': 5.6764220562615685e-05, 'samples': 22583232, 'steps': 117620, 'loss/train': 0.6025018095970154} 08/31/2021 10:29:24 - INFO - __main__ - Step 117622: {'lr': 5.676085360781152e-05, 'samples': 22583424, 'steps': 117621, 'loss/train': 0.570307731628418} 08/31/2021 10:29:26 - INFO - __main__ - Step 117623: {'lr': 5.6757486740077916e-05, 'samples': 22583616, 'steps': 117622, 'loss/train': 0.8962405323982239} 08/31/2021 10:29:26 - INFO - __main__ - Step 117624: {'lr': 5.67541199594164e-05, 'samples': 22583808, 'steps': 117623, 'loss/train': 1.1468273401260376} 08/31/2021 10:29:26 - INFO - __main__ - Step 117625: {'lr': 5.6750753265828514e-05, 'samples': 22584000, 'steps': 117624, 'loss/train': 1.2778449058532715} 08/31/2021 10:29:27 - INFO - __main__ - Step 117626: {'lr': 5.6747386659315755e-05, 'samples': 22584192, 'steps': 117625, 'loss/train': 0.13420380651950836} 08/31/2021 10:29:27 - INFO - __main__ - Step 117627: {'lr': 5.674402013987964e-05, 'samples': 22584384, 'steps': 117626, 'loss/train': 0.4852425754070282} 08/31/2021 10:29:29 - INFO - __main__ - Step 117628: {'lr': 5.674065370752168e-05, 'samples': 22584576, 'steps': 117627, 'loss/train': 0.3572024405002594} 08/31/2021 10:29:29 - INFO - __main__ - Step 117629: {'lr': 5.67372873622434e-05, 'samples': 22584768, 'steps': 117628, 'loss/train': 1.1048049926757812} 08/31/2021 10:29:29 - INFO - __main__ - Step 117630: {'lr': 5.673392110404632e-05, 'samples': 22584960, 'steps': 117629, 'loss/train': 1.205284833908081} 08/31/2021 10:29:30 - INFO - __main__ - Step 117631: {'lr': 5.673055493293197e-05, 'samples': 22585152, 'steps': 117630, 'loss/train': 1.281442642211914} 08/31/2021 10:29:30 - INFO - __main__ - Step 117632: {'lr': 5.672718884890182e-05, 'samples': 22585344, 'steps': 117631, 'loss/train': 1.1630171537399292} 08/31/2021 10:29:31 - INFO - __main__ - Step 117633: {'lr': 5.672382285195751e-05, 'samples': 22585536, 'steps': 117632, 'loss/train': 1.2046061754226685} 08/31/2021 10:29:32 - INFO - __main__ - Step 117634: {'lr': 5.6720456942100374e-05, 'samples': 22585728, 'steps': 117633, 'loss/train': 1.9663875102996826} 08/31/2021 10:29:32 - INFO - __main__ - Step 117635: {'lr': 5.6717091119332016e-05, 'samples': 22585920, 'steps': 117634, 'loss/train': 1.6409372091293335} 08/31/2021 10:29:33 - INFO - __main__ - Step 117636: {'lr': 5.6713725383653965e-05, 'samples': 22586112, 'steps': 117635, 'loss/train': 1.1979042291641235} 08/31/2021 10:29:33 - INFO - __main__ - Step 117637: {'lr': 5.671035973506775e-05, 'samples': 22586304, 'steps': 117636, 'loss/train': 1.0734952688217163} 08/31/2021 10:29:33 - INFO - __main__ - Step 117638: {'lr': 5.670699417357483e-05, 'samples': 22586496, 'steps': 117637, 'loss/train': 0.6408120393753052} 08/31/2021 10:29:35 - INFO - __main__ - Step 117639: {'lr': 5.670362869917675e-05, 'samples': 22586688, 'steps': 117638, 'loss/train': 0.8208010196685791} 08/31/2021 10:29:36 - INFO - __main__ - Step 117640: {'lr': 5.670026331187505e-05, 'samples': 22586880, 'steps': 117639, 'loss/train': 0.9514034390449524} 08/31/2021 10:29:36 - INFO - __main__ - Step 117641: {'lr': 5.6696898011671244e-05, 'samples': 22587072, 'steps': 117640, 'loss/train': 0.589499294757843} 08/31/2021 10:29:36 - INFO - __main__ - Step 117642: {'lr': 5.6693532798566816e-05, 'samples': 22587264, 'steps': 117641, 'loss/train': 1.4179083108901978} 08/31/2021 10:29:37 - INFO - __main__ - Step 117643: {'lr': 5.66901676725633e-05, 'samples': 22587456, 'steps': 117642, 'loss/train': 0.9089140892028809} 08/31/2021 10:29:38 - INFO - __main__ - Step 117644: {'lr': 5.668680263366219e-05, 'samples': 22587648, 'steps': 117643, 'loss/train': 0.0546330027282238} 08/31/2021 10:29:39 - INFO - __main__ - Step 117645: {'lr': 5.668343768186504e-05, 'samples': 22587840, 'steps': 117644, 'loss/train': 0.9859712719917297} 08/31/2021 10:29:39 - INFO - __main__ - Step 117646: {'lr': 5.668007281717336e-05, 'samples': 22588032, 'steps': 117645, 'loss/train': 1.2594034671783447} 08/31/2021 10:29:40 - INFO - __main__ - Step 117647: {'lr': 5.6676708039588715e-05, 'samples': 22588224, 'steps': 117646, 'loss/train': 1.2984071969985962} 08/31/2021 10:29:40 - INFO - __main__ - Step 117648: {'lr': 5.6673343349112506e-05, 'samples': 22588416, 'steps': 117647, 'loss/train': 1.1784716844558716} 08/31/2021 10:29:42 - INFO - __main__ - Step 117649: {'lr': 5.666997874574628e-05, 'samples': 22588608, 'steps': 117648, 'loss/train': 1.6495603322982788} 08/31/2021 10:29:42 - INFO - __main__ - Step 117650: {'lr': 5.66666142294916e-05, 'samples': 22588800, 'steps': 117649, 'loss/train': 1.5538722276687622} 08/31/2021 10:29:42 - INFO - __main__ - Step 117651: {'lr': 5.666324980034995e-05, 'samples': 22588992, 'steps': 117650, 'loss/train': 0.6681084632873535} 08/31/2021 10:29:43 - INFO - __main__ - Step 117652: {'lr': 5.6659885458322875e-05, 'samples': 22589184, 'steps': 117651, 'loss/train': 1.176736831665039} 08/31/2021 10:29:43 - INFO - __main__ - Step 117653: {'lr': 5.665652120341186e-05, 'samples': 22589376, 'steps': 117652, 'loss/train': 1.7555254697799683} 08/31/2021 10:29:45 - INFO - __main__ - Step 117654: {'lr': 5.665315703561844e-05, 'samples': 22589568, 'steps': 117653, 'loss/train': 1.242324948310852} 08/31/2021 10:29:46 - INFO - __main__ - Step 117655: {'lr': 5.6649792954944104e-05, 'samples': 22589760, 'steps': 117654, 'loss/train': 1.3527497053146362} 08/31/2021 10:29:46 - INFO - __main__ - Step 117656: {'lr': 5.664642896139041e-05, 'samples': 22589952, 'steps': 117655, 'loss/train': 0.558664083480835} 08/31/2021 10:29:46 - INFO - __main__ - Step 117657: {'lr': 5.6643065054958836e-05, 'samples': 22590144, 'steps': 117656, 'loss/train': 0.6164700984954834} 08/31/2021 10:29:47 - INFO - __main__ - Step 117658: {'lr': 5.6639701235650904e-05, 'samples': 22590336, 'steps': 117657, 'loss/train': 0.608286440372467} 08/31/2021 10:29:48 - INFO - __main__ - Step 117659: {'lr': 5.6636337503468164e-05, 'samples': 22590528, 'steps': 117658, 'loss/train': 1.1059564352035522} 08/31/2021 10:29:49 - INFO - __main__ - Step 117660: {'lr': 5.663297385841215e-05, 'samples': 22590720, 'steps': 117659, 'loss/train': 1.342058777809143} 08/31/2021 10:29:49 - INFO - __main__ - Step 117661: {'lr': 5.662961030048427e-05, 'samples': 22590912, 'steps': 117660, 'loss/train': 1.1622295379638672} 08/31/2021 10:29:49 - INFO - __main__ - Step 117662: {'lr': 5.6626246829686115e-05, 'samples': 22591104, 'steps': 117661, 'loss/train': 3.328029155731201} 08/31/2021 10:29:50 - INFO - __main__ - Step 117663: {'lr': 5.662288344601921e-05, 'samples': 22591296, 'steps': 117662, 'loss/train': 0.6792489290237427} 08/31/2021 10:29:51 - INFO - __main__ - Step 117664: {'lr': 5.6619520149485015e-05, 'samples': 22591488, 'steps': 117663, 'loss/train': 1.2610081434249878} 08/31/2021 10:29:52 - INFO - __main__ - Step 117665: {'lr': 5.6616156940085095e-05, 'samples': 22591680, 'steps': 117664, 'loss/train': 1.3494973182678223} 08/31/2021 10:29:52 - INFO - __main__ - Step 117666: {'lr': 5.6612793817820945e-05, 'samples': 22591872, 'steps': 117665, 'loss/train': 1.0333034992218018} 08/31/2021 10:29:52 - INFO - __main__ - Step 117667: {'lr': 5.6609430782694096e-05, 'samples': 22592064, 'steps': 117666, 'loss/train': 1.09213387966156} 08/31/2021 10:29:53 - INFO - __main__ - Step 117668: {'lr': 5.660606783470604e-05, 'samples': 22592256, 'steps': 117667, 'loss/train': 0.881575882434845} 08/31/2021 10:29:54 - INFO - __main__ - Step 117669: {'lr': 5.6602704973858306e-05, 'samples': 22592448, 'steps': 117668, 'loss/train': 1.6544315814971924} 08/31/2021 10:29:55 - INFO - __main__ - Step 117670: {'lr': 5.659934220015242e-05, 'samples': 22592640, 'steps': 117669, 'loss/train': 1.3299496173858643} 08/31/2021 10:29:55 - INFO - __main__ - Step 117671: {'lr': 5.6595979513589883e-05, 'samples': 22592832, 'steps': 117670, 'loss/train': 0.38309067487716675} 08/31/2021 10:29:55 - INFO - __main__ - Step 117672: {'lr': 5.6592616914172277e-05, 'samples': 22593024, 'steps': 117671, 'loss/train': 0.7209779620170593} 08/31/2021 10:29:56 - INFO - __main__ - Step 117673: {'lr': 5.658925440190099e-05, 'samples': 22593216, 'steps': 117672, 'loss/train': 1.0577328205108643} 08/31/2021 10:29:57 - INFO - __main__ - Step 117674: {'lr': 5.6585891976777604e-05, 'samples': 22593408, 'steps': 117673, 'loss/train': 1.130983829498291} 08/31/2021 10:29:58 - INFO - __main__ - Step 117675: {'lr': 5.6582529638803614e-05, 'samples': 22593600, 'steps': 117674, 'loss/train': 1.5203614234924316} 08/31/2021 10:29:58 - INFO - __main__ - Step 117676: {'lr': 5.657916738798055e-05, 'samples': 22593792, 'steps': 117675, 'loss/train': 1.6316533088684082} 08/31/2021 10:29:58 - INFO - __main__ - Step 117677: {'lr': 5.657580522430994e-05, 'samples': 22593984, 'steps': 117676, 'loss/train': 0.6907328367233276} 08/31/2021 10:29:59 - INFO - __main__ - Step 117678: {'lr': 5.657244314779331e-05, 'samples': 22594176, 'steps': 117677, 'loss/train': 0.9160090088844299} 08/31/2021 10:30:00 - INFO - __main__ - Step 117679: {'lr': 5.656908115843212e-05, 'samples': 22594368, 'steps': 117678, 'loss/train': 1.1223946809768677} 08/31/2021 10:30:01 - INFO - __main__ - Step 117680: {'lr': 5.656571925622792e-05, 'samples': 22594560, 'steps': 117679, 'loss/train': 0.705790638923645} 08/31/2021 10:30:01 - INFO - __main__ - Step 117681: {'lr': 5.656235744118224e-05, 'samples': 22594752, 'steps': 117680, 'loss/train': 1.3973349332809448} 08/31/2021 10:30:01 - INFO - __main__ - Step 117682: {'lr': 5.655899571329656e-05, 'samples': 22594944, 'steps': 117681, 'loss/train': 1.4911161661148071} 08/31/2021 10:30:02 - INFO - __main__ - Step 117683: {'lr': 5.65556340725725e-05, 'samples': 22595136, 'steps': 117682, 'loss/train': 1.1783119440078735} 08/31/2021 10:30:02 - INFO - __main__ - Step 117684: {'lr': 5.6552272519011375e-05, 'samples': 22595328, 'steps': 117683, 'loss/train': 0.6148000955581665} 08/31/2021 10:30:04 - INFO - __main__ - Step 117685: {'lr': 5.654891105261487e-05, 'samples': 22595520, 'steps': 117684, 'loss/train': 1.3389288187026978} 08/31/2021 10:30:04 - INFO - __main__ - Step 117686: {'lr': 5.654554967338441e-05, 'samples': 22595712, 'steps': 117685, 'loss/train': 1.2786169052124023} 08/31/2021 10:30:05 - INFO - __main__ - Step 117687: {'lr': 5.654218838132152e-05, 'samples': 22595904, 'steps': 117686, 'loss/train': 0.06006093695759773} 08/31/2021 10:30:05 - INFO - __main__ - Step 117688: {'lr': 5.653882717642775e-05, 'samples': 22596096, 'steps': 117687, 'loss/train': 1.4197255373001099} 08/31/2021 10:30:05 - INFO - __main__ - Step 117689: {'lr': 5.65354660587046e-05, 'samples': 22596288, 'steps': 117688, 'loss/train': 1.4630769491195679} 08/31/2021 10:30:07 - INFO - __main__ - Step 117690: {'lr': 5.6532105028153594e-05, 'samples': 22596480, 'steps': 117689, 'loss/train': 1.282683253288269} 08/31/2021 10:30:08 - INFO - __main__ - Step 117691: {'lr': 5.6528744084776234e-05, 'samples': 22596672, 'steps': 117690, 'loss/train': 4.203370094299316} 08/31/2021 10:30:08 - INFO - __main__ - Step 117692: {'lr': 5.6525383228574036e-05, 'samples': 22596864, 'steps': 117691, 'loss/train': 0.9330891370773315} 08/31/2021 10:30:08 - INFO - __main__ - Step 117693: {'lr': 5.6522022459548515e-05, 'samples': 22597056, 'steps': 117692, 'loss/train': 1.1748511791229248} 08/31/2021 10:30:09 - INFO - __main__ - Step 117694: {'lr': 5.651866177770124e-05, 'samples': 22597248, 'steps': 117693, 'loss/train': 1.6347888708114624} 08/31/2021 10:30:09 - INFO - __main__ - Step 117695: {'lr': 5.651530118303361e-05, 'samples': 22597440, 'steps': 117694, 'loss/train': 0.03869698941707611} 08/31/2021 10:30:10 - INFO - __main__ - Step 117696: {'lr': 5.651194067554721e-05, 'samples': 22597632, 'steps': 117695, 'loss/train': 1.3883609771728516} 08/31/2021 10:30:11 - INFO - __main__ - Step 117697: {'lr': 5.650858025524353e-05, 'samples': 22597824, 'steps': 117696, 'loss/train': 1.4879902601242065} 08/31/2021 10:30:11 - INFO - __main__ - Step 117698: {'lr': 5.650521992212409e-05, 'samples': 22598016, 'steps': 117697, 'loss/train': 1.5149366855621338} 08/31/2021 10:30:12 - INFO - __main__ - Step 117699: {'lr': 5.650185967619045e-05, 'samples': 22598208, 'steps': 117698, 'loss/train': 1.4594841003417969} 08/31/2021 10:30:12 - INFO - __main__ - Step 117700: {'lr': 5.6498499517444044e-05, 'samples': 22598400, 'steps': 117699, 'loss/train': 0.679189145565033} 08/31/2021 10:30:13 - INFO - __main__ - Step 117701: {'lr': 5.6495139445886465e-05, 'samples': 22598592, 'steps': 117700, 'loss/train': 1.187069058418274} 08/31/2021 10:30:14 - INFO - __main__ - Step 117702: {'lr': 5.649177946151915e-05, 'samples': 22598784, 'steps': 117701, 'loss/train': 0.7586790323257446} 08/31/2021 10:30:14 - INFO - __main__ - Step 117703: {'lr': 5.6488419564343695e-05, 'samples': 22598976, 'steps': 117702, 'loss/train': 0.8341125249862671} 08/31/2021 10:30:15 - INFO - __main__ - Step 117704: {'lr': 5.648505975436155e-05, 'samples': 22599168, 'steps': 117703, 'loss/train': 1.2047535181045532} 08/31/2021 10:30:15 - INFO - __main__ - Step 117705: {'lr': 5.6481700031574324e-05, 'samples': 22599360, 'steps': 117704, 'loss/train': 2.4712841510772705} 08/31/2021 10:30:17 - INFO - __main__ - Step 117706: {'lr': 5.647834039598338e-05, 'samples': 22599552, 'steps': 117705, 'loss/train': 0.9238559603691101} 08/31/2021 10:30:18 - INFO - __main__ - Step 117707: {'lr': 5.647498084759031e-05, 'samples': 22599744, 'steps': 117706, 'loss/train': 1.2560243606567383} 08/31/2021 10:30:18 - INFO - __main__ - Step 117708: {'lr': 5.647162138639664e-05, 'samples': 22599936, 'steps': 117707, 'loss/train': 1.1472370624542236} 08/31/2021 10:30:18 - INFO - __main__ - Step 117709: {'lr': 5.646826201240385e-05, 'samples': 22600128, 'steps': 117708, 'loss/train': 1.5499173402786255} 08/31/2021 10:30:19 - INFO - __main__ - Step 117710: {'lr': 5.64649027256135e-05, 'samples': 22600320, 'steps': 117709, 'loss/train': 1.110735297203064} 08/31/2021 10:30:20 - INFO - __main__ - Step 117711: {'lr': 5.6461543526027056e-05, 'samples': 22600512, 'steps': 117710, 'loss/train': 1.0262210369110107} 08/31/2021 10:30:21 - INFO - __main__ - Step 117712: {'lr': 5.645818441364606e-05, 'samples': 22600704, 'steps': 117711, 'loss/train': 1.6230897903442383} 08/31/2021 10:30:21 - INFO - __main__ - Step 117713: {'lr': 5.645482538847202e-05, 'samples': 22600896, 'steps': 117712, 'loss/train': 0.6997120976448059} 08/31/2021 10:30:21 - INFO - __main__ - Step 117714: {'lr': 5.6451466450506474e-05, 'samples': 22601088, 'steps': 117713, 'loss/train': 0.9663720726966858} 08/31/2021 10:30:22 - INFO - __main__ - Step 117715: {'lr': 5.644810759975094e-05, 'samples': 22601280, 'steps': 117714, 'loss/train': 0.6673977971076965} 08/31/2021 10:30:23 - INFO - __main__ - Step 117716: {'lr': 5.644474883620687e-05, 'samples': 22601472, 'steps': 117715, 'loss/train': 0.49314600229263306} 08/31/2021 10:30:24 - INFO - __main__ - Step 117717: {'lr': 5.6441390159875786e-05, 'samples': 22601664, 'steps': 117716, 'loss/train': 1.7010120153427124} 08/31/2021 10:30:24 - INFO - __main__ - Step 117718: {'lr': 5.643803157075922e-05, 'samples': 22601856, 'steps': 117717, 'loss/train': 3.0606372356414795} 08/31/2021 10:30:24 - INFO - __main__ - Step 117719: {'lr': 5.643467306885871e-05, 'samples': 22602048, 'steps': 117718, 'loss/train': 1.2684047222137451} 08/31/2021 10:30:25 - INFO - __main__ - Step 117720: {'lr': 5.643131465417575e-05, 'samples': 22602240, 'steps': 117719, 'loss/train': 0.4897993803024292} 08/31/2021 10:30:26 - INFO - __main__ - Step 117721: {'lr': 5.6427956326711825e-05, 'samples': 22602432, 'steps': 117720, 'loss/train': 0.42482084035873413} 08/31/2021 10:30:27 - INFO - __main__ - Step 117722: {'lr': 5.6424598086468494e-05, 'samples': 22602624, 'steps': 117721, 'loss/train': 1.3812512159347534} 08/31/2021 10:30:27 - INFO - __main__ - Step 117723: {'lr': 5.642123993344725e-05, 'samples': 22602816, 'steps': 117722, 'loss/train': 0.8552038669586182} 08/31/2021 10:30:27 - INFO - __main__ - Step 117724: {'lr': 5.641788186764962e-05, 'samples': 22603008, 'steps': 117723, 'loss/train': 0.5623394250869751} 08/31/2021 10:30:28 - INFO - __main__ - Step 117725: {'lr': 5.6414523889077084e-05, 'samples': 22603200, 'steps': 117724, 'loss/train': 0.5830268859863281} 08/31/2021 10:30:29 - INFO - __main__ - Step 117726: {'lr': 5.641116599773119e-05, 'samples': 22603392, 'steps': 117725, 'loss/train': 1.2826186418533325} 08/31/2021 10:30:30 - INFO - __main__ - Step 117727: {'lr': 5.640780819361352e-05, 'samples': 22603584, 'steps': 117726, 'loss/train': 0.7298573851585388} 08/31/2021 10:30:30 - INFO - __main__ - Step 117728: {'lr': 5.6404450476725405e-05, 'samples': 22603776, 'steps': 117727, 'loss/train': 0.7219262719154358} 08/31/2021 10:30:30 - INFO - __main__ - Step 117729: {'lr': 5.6401092847068485e-05, 'samples': 22603968, 'steps': 117728, 'loss/train': 1.1375397443771362} 08/31/2021 10:30:31 - INFO - __main__ - Step 117730: {'lr': 5.6397735304644235e-05, 'samples': 22604160, 'steps': 117729, 'loss/train': 0.6468538641929626} 08/31/2021 10:30:32 - INFO - __main__ - Step 117731: {'lr': 5.639437784945417e-05, 'samples': 22604352, 'steps': 117730, 'loss/train': 0.8384258151054382} 08/31/2021 10:30:33 - INFO - __main__ - Step 117732: {'lr': 5.63910204814998e-05, 'samples': 22604544, 'steps': 117731, 'loss/train': 1.4138280153274536} 08/31/2021 10:30:33 - INFO - __main__ - Step 117733: {'lr': 5.6387663200782676e-05, 'samples': 22604736, 'steps': 117732, 'loss/train': 0.8088269233703613} 08/31/2021 10:30:34 - INFO - __main__ - Step 117734: {'lr': 5.638430600730427e-05, 'samples': 22604928, 'steps': 117733, 'loss/train': 1.1044114828109741} 08/31/2021 10:30:34 - INFO - __main__ - Step 117735: {'lr': 5.63809489010661e-05, 'samples': 22605120, 'steps': 117734, 'loss/train': 1.228638768196106} 08/31/2021 10:30:34 - INFO - __main__ - Step 117736: {'lr': 5.63775918820697e-05, 'samples': 22605312, 'steps': 117735, 'loss/train': 1.2964590787887573} 08/31/2021 10:30:36 - INFO - __main__ - Step 117737: {'lr': 5.637423495031657e-05, 'samples': 22605504, 'steps': 117736, 'loss/train': 0.5503222942352295} 08/31/2021 10:30:36 - INFO - __main__ - Step 117738: {'lr': 5.637087810580821e-05, 'samples': 22605696, 'steps': 117737, 'loss/train': 1.4784928560256958} 08/31/2021 10:30:37 - INFO - __main__ - Step 117739: {'lr': 5.636752134854614e-05, 'samples': 22605888, 'steps': 117738, 'loss/train': 1.5010360479354858} 08/31/2021 10:30:37 - INFO - __main__ - Step 117740: {'lr': 5.636416467853189e-05, 'samples': 22606080, 'steps': 117739, 'loss/train': 1.1264311075210571} 08/31/2021 10:30:37 - INFO - __main__ - Step 117741: {'lr': 5.636080809576705e-05, 'samples': 22606272, 'steps': 117740, 'loss/train': 0.8293187618255615} 08/31/2021 10:30:39 - INFO - __main__ - Step 117742: {'lr': 5.635745160025294e-05, 'samples': 22606464, 'steps': 117741, 'loss/train': 1.4331902265548706} 08/31/2021 10:30:39 - INFO - __main__ - Step 117743: {'lr': 5.6354095191991194e-05, 'samples': 22606656, 'steps': 117742, 'loss/train': 1.5180883407592773} 08/31/2021 10:30:39 - INFO - __main__ - Step 117744: {'lr': 5.63507388709833e-05, 'samples': 22606848, 'steps': 117743, 'loss/train': 1.153232216835022} 08/31/2021 10:30:40 - INFO - __main__ - Step 117745: {'lr': 5.6347382637230746e-05, 'samples': 22607040, 'steps': 117744, 'loss/train': 0.6438639760017395} 08/31/2021 10:30:40 - INFO - __main__ - Step 117746: {'lr': 5.634402649073511e-05, 'samples': 22607232, 'steps': 117745, 'loss/train': 1.1141668558120728} 08/31/2021 10:30:42 - INFO - __main__ - Step 117747: {'lr': 5.634067043149785e-05, 'samples': 22607424, 'steps': 117746, 'loss/train': 1.1899981498718262} 08/31/2021 10:30:42 - INFO - __main__ - Step 117748: {'lr': 5.633731445952051e-05, 'samples': 22607616, 'steps': 117747, 'loss/train': 1.1034423112869263} 08/31/2021 10:30:42 - INFO - __main__ - Step 117749: {'lr': 5.633395857480456e-05, 'samples': 22607808, 'steps': 117748, 'loss/train': 0.8107375502586365} 08/31/2021 10:30:43 - INFO - __main__ - Step 117750: {'lr': 5.6330602777351556e-05, 'samples': 22608000, 'steps': 117749, 'loss/train': 1.5315021276474} 08/31/2021 10:30:43 - INFO - __main__ - Step 117751: {'lr': 5.6327247067163e-05, 'samples': 22608192, 'steps': 117750, 'loss/train': 0.5579808950424194} 08/31/2021 10:30:45 - INFO - __main__ - Step 117752: {'lr': 5.632389144424038e-05, 'samples': 22608384, 'steps': 117751, 'loss/train': 1.5394561290740967} 08/31/2021 10:30:45 - INFO - __main__ - Step 117753: {'lr': 5.632053590858524e-05, 'samples': 22608576, 'steps': 117752, 'loss/train': 1.080137014389038} 08/31/2021 10:30:46 - INFO - __main__ - Step 117754: {'lr': 5.6317180460199155e-05, 'samples': 22608768, 'steps': 117753, 'loss/train': 0.861143171787262} 08/31/2021 10:30:46 - INFO - __main__ - Step 117755: {'lr': 5.631382509908348e-05, 'samples': 22608960, 'steps': 117754, 'loss/train': 1.7452654838562012} 08/31/2021 10:30:46 - INFO - __main__ - Step 117756: {'lr': 5.6310469825239824e-05, 'samples': 22609152, 'steps': 117755, 'loss/train': 0.8990636467933655} 08/31/2021 10:30:48 - INFO - __main__ - Step 117757: {'lr': 5.6307114638669666e-05, 'samples': 22609344, 'steps': 117756, 'loss/train': 0.6550924181938171} 08/31/2021 10:30:48 - INFO - __main__ - Step 117758: {'lr': 5.630375953937453e-05, 'samples': 22609536, 'steps': 117757, 'loss/train': 1.2339040040969849} 08/31/2021 10:30:49 - INFO - __main__ - Step 117759: {'lr': 5.6300404527355935e-05, 'samples': 22609728, 'steps': 117758, 'loss/train': 1.311961054801941} 08/31/2021 10:30:49 - INFO - __main__ - Step 117760: {'lr': 5.629704960261539e-05, 'samples': 22609920, 'steps': 117759, 'loss/train': 0.8613359928131104} 08/31/2021 10:30:49 - INFO - __main__ - Step 117761: {'lr': 5.629369476515439e-05, 'samples': 22610112, 'steps': 117760, 'loss/train': 0.9797601699829102} 08/31/2021 10:30:52 - INFO - __main__ - Step 117762: {'lr': 5.629034001497449e-05, 'samples': 22610304, 'steps': 117761, 'loss/train': 0.24456612765789032} 08/31/2021 10:30:52 - INFO - __main__ - Step 117763: {'lr': 5.6286985352077156e-05, 'samples': 22610496, 'steps': 117762, 'loss/train': 1.088952898979187} 08/31/2021 10:30:52 - INFO - __main__ - Step 117764: {'lr': 5.6283630776463895e-05, 'samples': 22610688, 'steps': 117763, 'loss/train': 1.0488184690475464} 08/31/2021 10:30:53 - INFO - __main__ - Step 117765: {'lr': 5.628027628813629e-05, 'samples': 22610880, 'steps': 117764, 'loss/train': 0.8275052309036255} 08/31/2021 10:30:53 - INFO - __main__ - Step 117766: {'lr': 5.627692188709577e-05, 'samples': 22611072, 'steps': 117765, 'loss/train': 0.33871930837631226} 08/31/2021 10:30:55 - INFO - __main__ - Step 117767: {'lr': 5.6273567573343896e-05, 'samples': 22611264, 'steps': 117766, 'loss/train': 0.9442819952964783} 08/31/2021 10:30:55 - INFO - __main__ - Step 117768: {'lr': 5.62702133468822e-05, 'samples': 22611456, 'steps': 117767, 'loss/train': 1.4852548837661743} 08/31/2021 10:30:55 - INFO - __main__ - Step 117769: {'lr': 5.6266859207712126e-05, 'samples': 22611648, 'steps': 117768, 'loss/train': 1.111764907836914} 08/31/2021 10:30:56 - INFO - __main__ - Step 117770: {'lr': 5.62635051558352e-05, 'samples': 22611840, 'steps': 117769, 'loss/train': 1.9109902381896973} 08/31/2021 10:30:56 - INFO - __main__ - Step 117771: {'lr': 5.6260151191252965e-05, 'samples': 22612032, 'steps': 117770, 'loss/train': 1.0470058917999268} 08/31/2021 10:30:58 - INFO - __main__ - Step 117772: {'lr': 5.625679731396691e-05, 'samples': 22612224, 'steps': 117771, 'loss/train': 2.0262205600738525} 08/31/2021 10:30:58 - INFO - __main__ - Step 117773: {'lr': 5.6253443523978515e-05, 'samples': 22612416, 'steps': 117772, 'loss/train': 0.035372696816921234} 08/31/2021 10:30:59 - INFO - __main__ - Step 117774: {'lr': 5.6250089821289375e-05, 'samples': 22612608, 'steps': 117773, 'loss/train': 2.334451675415039} 08/31/2021 10:30:59 - INFO - __main__ - Step 117775: {'lr': 5.6246736205900926e-05, 'samples': 22612800, 'steps': 117774, 'loss/train': 1.3228586912155151} 08/31/2021 10:30:59 - INFO - __main__ - Step 117776: {'lr': 5.624338267781473e-05, 'samples': 22612992, 'steps': 117775, 'loss/train': 3.6527979373931885} 08/31/2021 10:31:00 - INFO - __main__ - Step 117777: {'lr': 5.624002923703225e-05, 'samples': 22613184, 'steps': 117776, 'loss/train': 1.5357863903045654} 08/31/2021 10:31:01 - INFO - __main__ - Step 117778: {'lr': 5.623667588355505e-05, 'samples': 22613376, 'steps': 117777, 'loss/train': 0.7990794777870178} 08/31/2021 10:31:02 - INFO - __main__ - Step 117779: {'lr': 5.623332261738462e-05, 'samples': 22613568, 'steps': 117778, 'loss/train': 0.654502809047699} 08/31/2021 10:31:02 - INFO - __main__ - Step 117780: {'lr': 5.622996943852243e-05, 'samples': 22613760, 'steps': 117779, 'loss/train': 1.302821159362793} 08/31/2021 10:31:02 - INFO - __main__ - Step 117781: {'lr': 5.6226616346970125e-05, 'samples': 22613952, 'steps': 117780, 'loss/train': 0.4255819022655487} 08/31/2021 10:31:03 - INFO - __main__ - Step 117782: {'lr': 5.622326334272904e-05, 'samples': 22614144, 'steps': 117781, 'loss/train': 1.0166089534759521} 08/31/2021 10:31:04 - INFO - __main__ - Step 117783: {'lr': 5.621991042580074e-05, 'samples': 22614336, 'steps': 117782, 'loss/train': 0.4562391936779022} 08/31/2021 10:31:05 - INFO - __main__ - Step 117784: {'lr': 5.621655759618677e-05, 'samples': 22614528, 'steps': 117783, 'loss/train': 1.1638460159301758} 08/31/2021 10:31:05 - INFO - __main__ - Step 117785: {'lr': 5.6213204853888646e-05, 'samples': 22614720, 'steps': 117784, 'loss/train': 0.829167366027832} 08/31/2021 10:31:05 - INFO - __main__ - Step 117786: {'lr': 5.620985219890784e-05, 'samples': 22614912, 'steps': 117785, 'loss/train': 0.3671760857105255} 08/31/2021 10:31:06 - INFO - __main__ - Step 117787: {'lr': 5.620649963124591e-05, 'samples': 22615104, 'steps': 117786, 'loss/train': 1.6627568006515503} 08/31/2021 10:31:07 - INFO - __main__ - Step 117788: {'lr': 5.6203147150904326e-05, 'samples': 22615296, 'steps': 117787, 'loss/train': 1.5705755949020386} 08/31/2021 10:31:08 - INFO - __main__ - Step 117789: {'lr': 5.6199794757884614e-05, 'samples': 22615488, 'steps': 117788, 'loss/train': 1.0597914457321167} 08/31/2021 10:31:08 - INFO - __main__ - Step 117790: {'lr': 5.619644245218827e-05, 'samples': 22615680, 'steps': 117789, 'loss/train': 1.2278484106063843} 08/31/2021 10:31:08 - INFO - __main__ - Step 117791: {'lr': 5.6193090233816826e-05, 'samples': 22615872, 'steps': 117790, 'loss/train': 0.13083063066005707} 08/31/2021 10:31:09 - INFO - __main__ - Step 117792: {'lr': 5.618973810277178e-05, 'samples': 22616064, 'steps': 117791, 'loss/train': 1.328310251235962} 08/31/2021 10:31:10 - INFO - __main__ - Step 117793: {'lr': 5.6186386059054686e-05, 'samples': 22616256, 'steps': 117792, 'loss/train': 1.7114413976669312} 08/31/2021 10:31:11 - INFO - __main__ - Step 117794: {'lr': 5.618303410266698e-05, 'samples': 22616448, 'steps': 117793, 'loss/train': 0.5653408169746399} 08/31/2021 10:31:11 - INFO - __main__ - Step 117795: {'lr': 5.617968223361028e-05, 'samples': 22616640, 'steps': 117794, 'loss/train': 1.0567524433135986} 08/31/2021 10:31:12 - INFO - __main__ - Step 117796: {'lr': 5.6176330451885946e-05, 'samples': 22616832, 'steps': 117795, 'loss/train': 0.5255998969078064} 08/31/2021 10:31:12 - INFO - __main__ - Step 117797: {'lr': 5.617297875749558e-05, 'samples': 22617024, 'steps': 117796, 'loss/train': 0.37202778458595276} 08/31/2021 10:31:13 - INFO - __main__ - Step 117798: {'lr': 5.616962715044069e-05, 'samples': 22617216, 'steps': 117797, 'loss/train': 0.7062475681304932} 08/31/2021 10:31:14 - INFO - __main__ - Step 117799: {'lr': 5.616627563072277e-05, 'samples': 22617408, 'steps': 117798, 'loss/train': 1.0076992511749268} 08/31/2021 10:31:14 - INFO - __main__ - Step 117800: {'lr': 5.616292419834332e-05, 'samples': 22617600, 'steps': 117799, 'loss/train': 1.3629740476608276} 08/31/2021 10:31:15 - INFO - __main__ - Step 117801: {'lr': 5.6159572853303864e-05, 'samples': 22617792, 'steps': 117800, 'loss/train': 1.2033039331436157} 08/31/2021 10:31:15 - INFO - __main__ - Step 117802: {'lr': 5.6156221595605935e-05, 'samples': 22617984, 'steps': 117801, 'loss/train': 0.687486469745636} 08/31/2021 10:31:15 - INFO - __main__ - Step 117803: {'lr': 5.6152870425250994e-05, 'samples': 22618176, 'steps': 117802, 'loss/train': 0.35570505261421204} 08/31/2021 10:31:17 - INFO - __main__ - Step 117804: {'lr': 5.6149519342240607e-05, 'samples': 22618368, 'steps': 117803, 'loss/train': 1.3702927827835083} 08/31/2021 10:31:17 - INFO - __main__ - Step 117805: {'lr': 5.6146168346576236e-05, 'samples': 22618560, 'steps': 117804, 'loss/train': 0.7562708258628845} 08/31/2021 10:31:18 - INFO - __main__ - Step 117806: {'lr': 5.6142817438259415e-05, 'samples': 22618752, 'steps': 117805, 'loss/train': 1.2356255054473877} 08/31/2021 10:31:18 - INFO - __main__ - Step 117807: {'lr': 5.613946661729166e-05, 'samples': 22618944, 'steps': 117806, 'loss/train': 0.7029588222503662} 08/31/2021 10:31:18 - INFO - __main__ - Step 117808: {'lr': 5.6136115883674536e-05, 'samples': 22619136, 'steps': 117807, 'loss/train': 1.3693366050720215} 08/31/2021 10:31:20 - INFO - __main__ - Step 117809: {'lr': 5.61327652374094e-05, 'samples': 22619328, 'steps': 117808, 'loss/train': 1.1405515670776367} 08/31/2021 10:31:20 - INFO - __main__ - Step 117810: {'lr': 5.6129414678497856e-05, 'samples': 22619520, 'steps': 117809, 'loss/train': 1.4650822877883911} 08/31/2021 10:31:21 - INFO - __main__ - Step 117811: {'lr': 5.612606420694141e-05, 'samples': 22619712, 'steps': 117810, 'loss/train': 0.70149165391922} 08/31/2021 10:31:21 - INFO - __main__ - Step 117812: {'lr': 5.612271382274159e-05, 'samples': 22619904, 'steps': 117811, 'loss/train': 1.4428167343139648} 08/31/2021 10:31:21 - INFO - __main__ - Step 117813: {'lr': 5.6119363525899855e-05, 'samples': 22620096, 'steps': 117812, 'loss/train': 1.0570096969604492} 08/31/2021 10:31:24 - INFO - __main__ - Step 117814: {'lr': 5.611601331641775e-05, 'samples': 22620288, 'steps': 117813, 'loss/train': 0.05729541555047035} 08/31/2021 10:31:25 - INFO - __main__ - Step 117815: {'lr': 5.611266319429678e-05, 'samples': 22620480, 'steps': 117814, 'loss/train': 1.2896616458892822} 08/31/2021 10:31:25 - INFO - __main__ - Step 117816: {'lr': 5.6109313159538436e-05, 'samples': 22620672, 'steps': 117815, 'loss/train': 5.318148612976074} 08/31/2021 10:31:26 - INFO - __main__ - Step 117817: {'lr': 5.6105963212144253e-05, 'samples': 22620864, 'steps': 117816, 'loss/train': 1.0296586751937866} 08/31/2021 10:31:26 - INFO - __main__ - Step 117818: {'lr': 5.610261335211575e-05, 'samples': 22621056, 'steps': 117817, 'loss/train': 2.4284234046936035} 08/31/2021 10:31:26 - INFO - __main__ - Step 117819: {'lr': 5.6099263579454384e-05, 'samples': 22621248, 'steps': 117818, 'loss/train': 0.8964316248893738} 08/31/2021 10:31:27 - INFO - __main__ - Step 117820: {'lr': 5.609591389416171e-05, 'samples': 22621440, 'steps': 117819, 'loss/train': 1.4211584329605103} 08/31/2021 10:31:28 - INFO - __main__ - Step 117821: {'lr': 5.6092564296239325e-05, 'samples': 22621632, 'steps': 117820, 'loss/train': 1.3769397735595703} 08/31/2021 10:31:29 - INFO - __main__ - Step 117822: {'lr': 5.608921478568854e-05, 'samples': 22621824, 'steps': 117821, 'loss/train': 1.2668181657791138} 08/31/2021 10:31:29 - INFO - __main__ - Step 117823: {'lr': 5.6085865362510954e-05, 'samples': 22622016, 'steps': 117822, 'loss/train': 1.3091788291931152} 08/31/2021 10:31:29 - INFO - __main__ - Step 117824: {'lr': 5.608251602670811e-05, 'samples': 22622208, 'steps': 117823, 'loss/train': 0.5385799407958984} 08/31/2021 10:31:30 - INFO - __main__ - Step 117825: {'lr': 5.607916677828148e-05, 'samples': 22622400, 'steps': 117824, 'loss/train': 0.745509147644043} 08/31/2021 10:31:30 - INFO - __main__ - Step 117826: {'lr': 5.607581761723257e-05, 'samples': 22622592, 'steps': 117825, 'loss/train': 0.6218211054801941} 08/31/2021 10:31:32 - INFO - __main__ - Step 117827: {'lr': 5.607246854356293e-05, 'samples': 22622784, 'steps': 117826, 'loss/train': 0.6807599067687988} 08/31/2021 10:31:32 - INFO - __main__ - Step 117828: {'lr': 5.6069119557274035e-05, 'samples': 22622976, 'steps': 117827, 'loss/train': 1.629054069519043} 08/31/2021 10:31:32 - INFO - __main__ - Step 117829: {'lr': 5.60657706583674e-05, 'samples': 22623168, 'steps': 117828, 'loss/train': 0.6100745797157288} 08/31/2021 10:31:33 - INFO - __main__ - Step 117830: {'lr': 5.606242184684451e-05, 'samples': 22623360, 'steps': 117829, 'loss/train': 0.8217790722846985} 08/31/2021 10:31:33 - INFO - __main__ - Step 117831: {'lr': 5.6059073122706945e-05, 'samples': 22623552, 'steps': 117830, 'loss/train': 1.2870559692382812} 08/31/2021 10:31:34 - INFO - __main__ - Step 117832: {'lr': 5.6055724485956136e-05, 'samples': 22623744, 'steps': 117831, 'loss/train': 1.2101811170578003} 08/31/2021 10:31:35 - INFO - __main__ - Step 117833: {'lr': 5.6052375936593655e-05, 'samples': 22623936, 'steps': 117832, 'loss/train': 1.2546672821044922} 08/31/2021 10:31:35 - INFO - __main__ - Step 117834: {'lr': 5.604902747462096e-05, 'samples': 22624128, 'steps': 117833, 'loss/train': 1.6928112506866455} 08/31/2021 10:31:36 - INFO - __main__ - Step 117835: {'lr': 5.604567910003966e-05, 'samples': 22624320, 'steps': 117834, 'loss/train': 0.5808947086334229} 08/31/2021 10:31:36 - INFO - __main__ - Step 117836: {'lr': 5.6042330812851094e-05, 'samples': 22624512, 'steps': 117835, 'loss/train': 1.4143383502960205} 08/31/2021 10:31:37 - INFO - __main__ - Step 117837: {'lr': 5.6038982613056874e-05, 'samples': 22624704, 'steps': 117836, 'loss/train': 1.4399304389953613} 08/31/2021 10:31:38 - INFO - __main__ - Step 117838: {'lr': 5.603563450065849e-05, 'samples': 22624896, 'steps': 117837, 'loss/train': 1.2570844888687134} 08/31/2021 10:31:38 - INFO - __main__ - Step 117839: {'lr': 5.6032286475657474e-05, 'samples': 22625088, 'steps': 117838, 'loss/train': 1.3032766580581665} 08/31/2021 10:31:39 - INFO - __main__ - Step 117840: {'lr': 5.6028938538055297e-05, 'samples': 22625280, 'steps': 117839, 'loss/train': 0.8323845863342285} 08/31/2021 10:31:39 - INFO - __main__ - Step 117841: {'lr': 5.602559068785351e-05, 'samples': 22625472, 'steps': 117840, 'loss/train': 1.671194314956665} 08/31/2021 10:31:41 - INFO - __main__ - Step 117842: {'lr': 5.602224292505356e-05, 'samples': 22625664, 'steps': 117841, 'loss/train': 1.0762566328048706} 08/31/2021 10:31:41 - INFO - __main__ - Step 117843: {'lr': 5.601889524965703e-05, 'samples': 22625856, 'steps': 117842, 'loss/train': 1.0363117456436157} 08/31/2021 10:31:41 - INFO - __main__ - Step 117844: {'lr': 5.601554766166539e-05, 'samples': 22626048, 'steps': 117843, 'loss/train': 1.0010945796966553} 08/31/2021 10:31:42 - INFO - __main__ - Step 117845: {'lr': 5.601220016108013e-05, 'samples': 22626240, 'steps': 117844, 'loss/train': 1.2726596593856812} 08/31/2021 10:31:42 - INFO - __main__ - Step 117846: {'lr': 5.600885274790279e-05, 'samples': 22626432, 'steps': 117845, 'loss/train': 0.8639190793037415} 08/31/2021 10:31:44 - INFO - __main__ - Step 117847: {'lr': 5.6005505422134866e-05, 'samples': 22626624, 'steps': 117846, 'loss/train': 1.1250413656234741} 08/31/2021 10:31:44 - INFO - __main__ - Step 117848: {'lr': 5.6002158183777936e-05, 'samples': 22626816, 'steps': 117847, 'loss/train': 0.6508000493049622} 08/31/2021 10:31:44 - INFO - __main__ - Step 117849: {'lr': 5.599881103283338e-05, 'samples': 22627008, 'steps': 117848, 'loss/train': 0.7719448804855347} 08/31/2021 10:31:45 - INFO - __main__ - Step 117850: {'lr': 5.599546396930277e-05, 'samples': 22627200, 'steps': 117849, 'loss/train': 1.125510334968567} 08/31/2021 10:31:45 - INFO - __main__ - Step 117851: {'lr': 5.59921169931876e-05, 'samples': 22627392, 'steps': 117850, 'loss/train': 1.03738534450531} 08/31/2021 10:31:47 - INFO - __main__ - Step 117852: {'lr': 5.598877010448938e-05, 'samples': 22627584, 'steps': 117851, 'loss/train': 1.6252210140228271} 08/31/2021 10:31:47 - INFO - __main__ - Step 117853: {'lr': 5.598542330320963e-05, 'samples': 22627776, 'steps': 117852, 'loss/train': 1.2457808256149292} 08/31/2021 10:31:47 - INFO - __main__ - Step 117854: {'lr': 5.5982076589349866e-05, 'samples': 22627968, 'steps': 117853, 'loss/train': 0.8231081962585449} 08/31/2021 10:31:48 - INFO - __main__ - Step 117855: {'lr': 5.597872996291156e-05, 'samples': 22628160, 'steps': 117854, 'loss/train': 0.16238722205162048} 08/31/2021 10:31:48 - INFO - __main__ - Step 117856: {'lr': 5.597538342389627e-05, 'samples': 22628352, 'steps': 117855, 'loss/train': 1.4948137998580933} 08/31/2021 10:31:48 - INFO - __main__ - Step 117857: {'lr': 5.597203697230549e-05, 'samples': 22628544, 'steps': 117856, 'loss/train': 0.8133150935173035} 08/31/2021 10:31:50 - INFO - __main__ - Step 117858: {'lr': 5.596869060814069e-05, 'samples': 22628736, 'steps': 117857, 'loss/train': 0.9055453538894653} 08/31/2021 10:31:50 - INFO - __main__ - Step 117859: {'lr': 5.596534433140341e-05, 'samples': 22628928, 'steps': 117858, 'loss/train': 1.0984081029891968} 08/31/2021 10:31:51 - INFO - __main__ - Step 117860: {'lr': 5.5961998142095156e-05, 'samples': 22629120, 'steps': 117859, 'loss/train': 1.0980656147003174} 08/31/2021 10:31:51 - INFO - __main__ - Step 117861: {'lr': 5.5958652040217414e-05, 'samples': 22629312, 'steps': 117860, 'loss/train': 1.1156448125839233} 08/31/2021 10:31:51 - INFO - __main__ - Step 117862: {'lr': 5.595530602577178e-05, 'samples': 22629504, 'steps': 117861, 'loss/train': 1.1480282545089722} 08/31/2021 10:31:53 - INFO - __main__ - Step 117863: {'lr': 5.5951960098759637e-05, 'samples': 22629696, 'steps': 117862, 'loss/train': 0.7947065234184265} 08/31/2021 10:31:54 - INFO - __main__ - Step 117864: {'lr': 5.594861425918255e-05, 'samples': 22629888, 'steps': 117863, 'loss/train': 1.726614236831665} 08/31/2021 10:31:54 - INFO - __main__ - Step 117865: {'lr': 5.5945268507042013e-05, 'samples': 22630080, 'steps': 117864, 'loss/train': 0.01645001582801342} 08/31/2021 10:31:54 - INFO - __main__ - Step 117866: {'lr': 5.5941922842339565e-05, 'samples': 22630272, 'steps': 117865, 'loss/train': 1.3218514919281006} 08/31/2021 10:31:55 - INFO - __main__ - Step 117867: {'lr': 5.5938577265076674e-05, 'samples': 22630464, 'steps': 117866, 'loss/train': 1.2989362478256226} 08/31/2021 10:31:57 - INFO - __main__ - Step 117868: {'lr': 5.5935231775254865e-05, 'samples': 22630656, 'steps': 117867, 'loss/train': 0.537857711315155} 08/31/2021 10:31:58 - INFO - __main__ - Step 117869: {'lr': 5.5931886372875634e-05, 'samples': 22630848, 'steps': 117868, 'loss/train': 0.9787237048149109} 08/31/2021 10:31:58 - INFO - __main__ - Step 117870: {'lr': 5.592854105794051e-05, 'samples': 22631040, 'steps': 117869, 'loss/train': 1.3542131185531616} 08/31/2021 10:31:58 - INFO - __main__ - Step 117871: {'lr': 5.5925195830451e-05, 'samples': 22631232, 'steps': 117870, 'loss/train': 0.3700896203517914} 08/31/2021 10:31:59 - INFO - __main__ - Step 117872: {'lr': 5.592185069040859e-05, 'samples': 22631424, 'steps': 117871, 'loss/train': 0.8590336441993713} 08/31/2021 10:31:59 - INFO - __main__ - Step 117873: {'lr': 5.591850563781481e-05, 'samples': 22631616, 'steps': 117872, 'loss/train': 0.8443359136581421} 08/31/2021 10:32:00 - INFO - __main__ - Step 117874: {'lr': 5.5915160672671134e-05, 'samples': 22631808, 'steps': 117873, 'loss/train': 1.3666859865188599} 08/31/2021 10:32:01 - INFO - __main__ - Step 117875: {'lr': 5.59118157949792e-05, 'samples': 22632000, 'steps': 117874, 'loss/train': 1.0864629745483398} 08/31/2021 10:32:01 - INFO - __main__ - Step 117876: {'lr': 5.590847100474031e-05, 'samples': 22632192, 'steps': 117875, 'loss/train': 1.1094717979431152} 08/31/2021 10:32:02 - INFO - __main__ - Step 117877: {'lr': 5.590512630195607e-05, 'samples': 22632384, 'steps': 117876, 'loss/train': 1.4264568090438843} 08/31/2021 10:32:02 - INFO - __main__ - Step 117878: {'lr': 5.590178168662799e-05, 'samples': 22632576, 'steps': 117877, 'loss/train': 0.14680857956409454} 08/31/2021 10:32:03 - INFO - __main__ - Step 117879: {'lr': 5.589843715875756e-05, 'samples': 22632768, 'steps': 117878, 'loss/train': 0.9818354845046997} 08/31/2021 10:32:04 - INFO - __main__ - Step 117880: {'lr': 5.5895092718346306e-05, 'samples': 22632960, 'steps': 117879, 'loss/train': 1.1089602708816528} 08/31/2021 10:32:04 - INFO - __main__ - Step 117881: {'lr': 5.589174836539573e-05, 'samples': 22633152, 'steps': 117880, 'loss/train': 1.0480725765228271} 08/31/2021 10:32:05 - INFO - __main__ - Step 117882: {'lr': 5.5888404099907336e-05, 'samples': 22633344, 'steps': 117881, 'loss/train': 0.5602228045463562} 08/31/2021 10:32:05 - INFO - __main__ - Step 117883: {'lr': 5.588505992188264e-05, 'samples': 22633536, 'steps': 117882, 'loss/train': 1.2519986629486084} 08/31/2021 10:32:06 - INFO - __main__ - Step 117884: {'lr': 5.588171583132315e-05, 'samples': 22633728, 'steps': 117883, 'loss/train': 1.0640896558761597} 08/31/2021 10:32:07 - INFO - __main__ - Step 117885: {'lr': 5.587837182823033e-05, 'samples': 22633920, 'steps': 117884, 'loss/train': 1.312558889389038} 08/31/2021 10:32:07 - INFO - __main__ - Step 117886: {'lr': 5.5875027912605735e-05, 'samples': 22634112, 'steps': 117885, 'loss/train': 0.6919844150543213} 08/31/2021 10:32:08 - INFO - __main__ - Step 117887: {'lr': 5.587168408445087e-05, 'samples': 22634304, 'steps': 117886, 'loss/train': 1.1415228843688965} 08/31/2021 10:32:08 - INFO - __main__ - Step 117888: {'lr': 5.586834034376723e-05, 'samples': 22634496, 'steps': 117887, 'loss/train': 0.6609113812446594} 08/31/2021 10:32:09 - INFO - __main__ - Step 117889: {'lr': 5.586499669055636e-05, 'samples': 22634688, 'steps': 117888, 'loss/train': 1.0258530378341675} 08/31/2021 10:32:10 - INFO - __main__ - Step 117890: {'lr': 5.5861653124819696e-05, 'samples': 22634880, 'steps': 117889, 'loss/train': 0.8841063380241394} 08/31/2021 10:32:10 - INFO - __main__ - Step 117891: {'lr': 5.5858309646558746e-05, 'samples': 22635072, 'steps': 117890, 'loss/train': 1.137194037437439} 08/31/2021 10:32:11 - INFO - __main__ - Step 117892: {'lr': 5.585496625577505e-05, 'samples': 22635264, 'steps': 117891, 'loss/train': 0.7530382871627808} 08/31/2021 10:32:11 - INFO - __main__ - Step 117893: {'lr': 5.5851622952470124e-05, 'samples': 22635456, 'steps': 117892, 'loss/train': 1.4606473445892334} 08/31/2021 10:32:11 - INFO - __main__ - Step 117894: {'lr': 5.584827973664544e-05, 'samples': 22635648, 'steps': 117893, 'loss/train': 0.793644368648529} 08/31/2021 10:32:13 - INFO - __main__ - Step 117895: {'lr': 5.5844936608302535e-05, 'samples': 22635840, 'steps': 117894, 'loss/train': 1.1374197006225586} 08/31/2021 10:32:13 - INFO - __main__ - Step 117896: {'lr': 5.584159356744292e-05, 'samples': 22636032, 'steps': 117895, 'loss/train': 0.503174364566803} 08/31/2021 10:32:14 - INFO - __main__ - Step 117897: {'lr': 5.5838250614068055e-05, 'samples': 22636224, 'steps': 117896, 'loss/train': 1.2501338720321655} 08/31/2021 10:32:14 - INFO - __main__ - Step 117898: {'lr': 5.583490774817951e-05, 'samples': 22636416, 'steps': 117897, 'loss/train': 0.03442016988992691} 08/31/2021 10:32:14 - INFO - __main__ - Step 117899: {'lr': 5.583156496977876e-05, 'samples': 22636608, 'steps': 117898, 'loss/train': 1.2950223684310913} 08/31/2021 10:32:16 - INFO - __main__ - Step 117900: {'lr': 5.582822227886728e-05, 'samples': 22636800, 'steps': 117899, 'loss/train': 1.0248486995697021} 08/31/2021 10:32:17 - INFO - __main__ - Step 117901: {'lr': 5.582487967544664e-05, 'samples': 22636992, 'steps': 117900, 'loss/train': 0.9058530926704407} 08/31/2021 10:32:17 - INFO - __main__ - Step 117902: {'lr': 5.582153715951835e-05, 'samples': 22637184, 'steps': 117901, 'loss/train': 1.7449240684509277} 08/31/2021 10:32:18 - INFO - __main__ - Step 117903: {'lr': 5.5818194731083824e-05, 'samples': 22637376, 'steps': 117902, 'loss/train': 1.76087486743927} 08/31/2021 10:32:18 - INFO - __main__ - Step 117904: {'lr': 5.581485239014464e-05, 'samples': 22637568, 'steps': 117903, 'loss/train': 1.0319204330444336} 08/31/2021 10:32:18 - INFO - __main__ - Step 117905: {'lr': 5.581151013670227e-05, 'samples': 22637760, 'steps': 117904, 'loss/train': 1.3129829168319702} 08/31/2021 10:32:20 - INFO - __main__ - Step 117906: {'lr': 5.5808167970758245e-05, 'samples': 22637952, 'steps': 117905, 'loss/train': 1.1941472291946411} 08/31/2021 10:32:20 - INFO - __main__ - Step 117907: {'lr': 5.580482589231406e-05, 'samples': 22638144, 'steps': 117906, 'loss/train': 1.0951448678970337} 08/31/2021 10:32:21 - INFO - __main__ - Step 117908: {'lr': 5.580148390137121e-05, 'samples': 22638336, 'steps': 117907, 'loss/train': 0.9358742237091064} 08/31/2021 10:32:21 - INFO - __main__ - Step 117909: {'lr': 5.579814199793123e-05, 'samples': 22638528, 'steps': 117908, 'loss/train': 1.152855396270752} 08/31/2021 10:32:21 - INFO - __main__ - Step 117910: {'lr': 5.579480018199559e-05, 'samples': 22638720, 'steps': 117909, 'loss/train': 0.9306854009628296} 08/31/2021 10:32:23 - INFO - __main__ - Step 117911: {'lr': 5.579145845356584e-05, 'samples': 22638912, 'steps': 117910, 'loss/train': 1.6378930807113647} 08/31/2021 10:32:23 - INFO - __main__ - Step 117912: {'lr': 5.578811681264345e-05, 'samples': 22639104, 'steps': 117911, 'loss/train': 1.2597907781600952} 08/31/2021 10:32:24 - INFO - __main__ - Step 117913: {'lr': 5.5784775259229954e-05, 'samples': 22639296, 'steps': 117912, 'loss/train': 0.7135329246520996} 08/31/2021 10:32:24 - INFO - __main__ - Step 117914: {'lr': 5.578143379332684e-05, 'samples': 22639488, 'steps': 117913, 'loss/train': 1.8972057104110718} 08/31/2021 10:32:24 - INFO - __main__ - Step 117915: {'lr': 5.577809241493559e-05, 'samples': 22639680, 'steps': 117914, 'loss/train': 1.2536225318908691} 08/31/2021 10:32:25 - INFO - __main__ - Step 117916: {'lr': 5.5774751124057834e-05, 'samples': 22639872, 'steps': 117915, 'loss/train': 1.3575382232666016} 08/31/2021 10:32:26 - INFO - __main__ - Step 117917: {'lr': 5.5771409920694873e-05, 'samples': 22640064, 'steps': 117916, 'loss/train': 0.3775680959224701} 08/31/2021 10:32:27 - INFO - __main__ - Step 117918: {'lr': 5.576806880484836e-05, 'samples': 22640256, 'steps': 117917, 'loss/train': 0.887459933757782} 08/31/2021 10:32:27 - INFO - __main__ - Step 117919: {'lr': 5.576472777651972e-05, 'samples': 22640448, 'steps': 117918, 'loss/train': 0.9918442964553833} 08/31/2021 10:32:28 - INFO - __main__ - Step 117920: {'lr': 5.576138683571053e-05, 'samples': 22640640, 'steps': 117919, 'loss/train': 1.4035897254943848} 08/31/2021 10:32:28 - INFO - __main__ - Step 117921: {'lr': 5.575804598242223e-05, 'samples': 22640832, 'steps': 117920, 'loss/train': 1.2050496339797974} 08/31/2021 10:32:30 - INFO - __main__ - Step 117922: {'lr': 5.5754705216656375e-05, 'samples': 22641024, 'steps': 117921, 'loss/train': 0.9279485940933228} 08/31/2021 10:32:30 - INFO - __main__ - Step 117923: {'lr': 5.575136453841445e-05, 'samples': 22641216, 'steps': 117922, 'loss/train': 0.9812257289886475} 08/31/2021 10:32:31 - INFO - __main__ - Step 117924: {'lr': 5.574802394769796e-05, 'samples': 22641408, 'steps': 117923, 'loss/train': 1.0903314352035522} 08/31/2021 10:32:31 - INFO - __main__ - Step 117925: {'lr': 5.574468344450842e-05, 'samples': 22641600, 'steps': 117924, 'loss/train': 0.02854345738887787} 08/31/2021 10:32:31 - INFO - __main__ - Step 117926: {'lr': 5.574134302884731e-05, 'samples': 22641792, 'steps': 117925, 'loss/train': 0.8962777853012085} 08/31/2021 10:32:33 - INFO - __main__ - Step 117927: {'lr': 5.5738002700716164e-05, 'samples': 22641984, 'steps': 117926, 'loss/train': 2.140772819519043} 08/31/2021 10:32:34 - INFO - __main__ - Step 117928: {'lr': 5.573466246011649e-05, 'samples': 22642176, 'steps': 117927, 'loss/train': 0.2746642231941223} 08/31/2021 10:32:34 - INFO - __main__ - Step 117929: {'lr': 5.573132230704983e-05, 'samples': 22642368, 'steps': 117928, 'loss/train': 1.3320199251174927} 08/31/2021 10:32:34 - INFO - __main__ - Step 117930: {'lr': 5.57279822415176e-05, 'samples': 22642560, 'steps': 117929, 'loss/train': 0.908720850944519} 08/31/2021 10:32:35 - INFO - __main__ - Step 117931: {'lr': 5.572464226352131e-05, 'samples': 22642752, 'steps': 117930, 'loss/train': 2.149975299835205} 08/31/2021 10:32:36 - INFO - __main__ - Step 117932: {'lr': 5.57213023730625e-05, 'samples': 22642944, 'steps': 117931, 'loss/train': 0.29082831740379333} 08/31/2021 10:32:37 - INFO - __main__ - Step 117933: {'lr': 5.571796257014267e-05, 'samples': 22643136, 'steps': 117932, 'loss/train': 1.0674601793289185} 08/31/2021 10:32:37 - INFO - __main__ - Step 117934: {'lr': 5.571462285476333e-05, 'samples': 22643328, 'steps': 117933, 'loss/train': 1.0552034378051758} 08/31/2021 10:32:38 - INFO - __main__ - Step 117935: {'lr': 5.5711283226926005e-05, 'samples': 22643520, 'steps': 117934, 'loss/train': 0.9518571496009827} 08/31/2021 10:32:38 - INFO - __main__ - Step 117936: {'lr': 5.570794368663218e-05, 'samples': 22643712, 'steps': 117935, 'loss/train': 0.8983210325241089} 08/31/2021 10:32:39 - INFO - __main__ - Step 117937: {'lr': 5.570460423388332e-05, 'samples': 22643904, 'steps': 117936, 'loss/train': 1.4458591938018799} 08/31/2021 10:32:40 - INFO - __main__ - Step 117938: {'lr': 5.570126486868099e-05, 'samples': 22644096, 'steps': 117937, 'loss/train': 0.9649060368537903} 08/31/2021 10:32:40 - INFO - __main__ - Step 117939: {'lr': 5.569792559102668e-05, 'samples': 22644288, 'steps': 117938, 'loss/train': 0.4353499412536621} 08/31/2021 10:32:41 - INFO - __main__ - Step 117940: {'lr': 5.569458640092187e-05, 'samples': 22644480, 'steps': 117939, 'loss/train': 0.03218302130699158} 08/31/2021 10:32:41 - INFO - __main__ - Step 117941: {'lr': 5.5691247298368164e-05, 'samples': 22644672, 'steps': 117940, 'loss/train': 0.09523303806781769} 08/31/2021 10:32:41 - INFO - __main__ - Step 117942: {'lr': 5.5687908283366925e-05, 'samples': 22644864, 'steps': 117941, 'loss/train': 0.9035758376121521} 08/31/2021 10:32:43 - INFO - __main__ - Step 117943: {'lr': 5.56845693559197e-05, 'samples': 22645056, 'steps': 117942, 'loss/train': 0.22098718583583832} 08/31/2021 10:32:43 - INFO - __main__ - Step 117944: {'lr': 5.5681230516027996e-05, 'samples': 22645248, 'steps': 117943, 'loss/train': 1.7002463340759277} 08/31/2021 10:32:44 - INFO - __main__ - Step 117945: {'lr': 5.567789176369334e-05, 'samples': 22645440, 'steps': 117944, 'loss/train': 0.9680230617523193} 08/31/2021 10:32:44 - INFO - __main__ - Step 117946: {'lr': 5.567455309891722e-05, 'samples': 22645632, 'steps': 117945, 'loss/train': 1.3031926155090332} 08/31/2021 10:32:44 - INFO - __main__ - Step 117947: {'lr': 5.567121452170118e-05, 'samples': 22645824, 'steps': 117946, 'loss/train': 0.9759594798088074} 08/31/2021 10:32:46 - INFO - __main__ - Step 117948: {'lr': 5.5667876032046675e-05, 'samples': 22646016, 'steps': 117947, 'loss/train': 0.7623688578605652} 08/31/2021 10:32:47 - INFO - __main__ - Step 117949: {'lr': 5.566453762995521e-05, 'samples': 22646208, 'steps': 117948, 'loss/train': 1.9728968143463135} 08/31/2021 10:32:47 - INFO - __main__ - Step 117950: {'lr': 5.566119931542832e-05, 'samples': 22646400, 'steps': 117949, 'loss/train': 1.9527223110198975} 08/31/2021 10:32:48 - INFO - __main__ - Step 117951: {'lr': 5.565786108846749e-05, 'samples': 22646592, 'steps': 117950, 'loss/train': 1.4120817184448242} 08/31/2021 10:32:48 - INFO - __main__ - Step 117952: {'lr': 5.56545229490743e-05, 'samples': 22646784, 'steps': 117951, 'loss/train': 1.6145992279052734} 08/31/2021 10:32:48 - INFO - __main__ - Step 117953: {'lr': 5.565118489725013e-05, 'samples': 22646976, 'steps': 117952, 'loss/train': 1.55145263671875} 08/31/2021 10:32:49 - INFO - __main__ - Step 117954: {'lr': 5.564784693299652e-05, 'samples': 22647168, 'steps': 117953, 'loss/train': 1.3480260372161865} 08/31/2021 10:32:50 - INFO - __main__ - Step 117955: {'lr': 5.564450905631499e-05, 'samples': 22647360, 'steps': 117954, 'loss/train': 1.431516408920288} 08/31/2021 10:32:51 - INFO - __main__ - Step 117956: {'lr': 5.564117126720705e-05, 'samples': 22647552, 'steps': 117955, 'loss/train': 3.367230176925659} 08/31/2021 10:32:51 - INFO - __main__ - Step 117957: {'lr': 5.56378335656742e-05, 'samples': 22647744, 'steps': 117956, 'loss/train': 1.2275413274765015} 08/31/2021 10:32:51 - INFO - __main__ - Step 117958: {'lr': 5.5634495951717936e-05, 'samples': 22647936, 'steps': 117957, 'loss/train': 1.3389875888824463} 08/31/2021 10:32:52 - INFO - __main__ - Step 117959: {'lr': 5.563115842533978e-05, 'samples': 22648128, 'steps': 117958, 'loss/train': 1.1236519813537598} 08/31/2021 10:32:53 - INFO - __main__ - Step 117960: {'lr': 5.56278209865412e-05, 'samples': 22648320, 'steps': 117959, 'loss/train': 1.3149008750915527} 08/31/2021 10:32:54 - INFO - __main__ - Step 117961: {'lr': 5.562448363532374e-05, 'samples': 22648512, 'steps': 117960, 'loss/train': 0.6462379097938538} 08/31/2021 10:32:54 - INFO - __main__ - Step 117962: {'lr': 5.562114637168897e-05, 'samples': 22648704, 'steps': 117961, 'loss/train': 0.7957692742347717} 08/31/2021 10:32:54 - INFO - __main__ - Step 117963: {'lr': 5.5617809195638244e-05, 'samples': 22648896, 'steps': 117962, 'loss/train': 1.1398791074752808} 08/31/2021 10:32:55 - INFO - __main__ - Step 117964: {'lr': 5.5614472107173105e-05, 'samples': 22649088, 'steps': 117963, 'loss/train': 1.1632899045944214} 08/31/2021 10:32:56 - INFO - __main__ - Step 117965: {'lr': 5.5611135106295116e-05, 'samples': 22649280, 'steps': 117964, 'loss/train': 0.802875816822052} 08/31/2021 10:32:57 - INFO - __main__ - Step 117966: {'lr': 5.5607798193005735e-05, 'samples': 22649472, 'steps': 117965, 'loss/train': 0.6933582425117493} 08/31/2021 10:32:57 - INFO - __main__ - Step 117967: {'lr': 5.5604461367306486e-05, 'samples': 22649664, 'steps': 117966, 'loss/train': 0.8689245581626892} 08/31/2021 10:32:57 - INFO - __main__ - Step 117968: {'lr': 5.560112462919886e-05, 'samples': 22649856, 'steps': 117967, 'loss/train': 1.7305585145950317} 08/31/2021 10:32:58 - INFO - __main__ - Step 117969: {'lr': 5.559778797868437e-05, 'samples': 22650048, 'steps': 117968, 'loss/train': 1.1612980365753174} 08/31/2021 10:32:59 - INFO - __main__ - Step 117970: {'lr': 5.559445141576453e-05, 'samples': 22650240, 'steps': 117969, 'loss/train': 1.181828498840332} 08/31/2021 10:33:00 - INFO - __main__ - Step 117971: {'lr': 5.559111494044081e-05, 'samples': 22650432, 'steps': 117970, 'loss/train': 0.6899846196174622} 08/31/2021 10:33:00 - INFO - __main__ - Step 117972: {'lr': 5.558777855271474e-05, 'samples': 22650624, 'steps': 117971, 'loss/train': 1.2940504550933838} 08/31/2021 10:33:01 - INFO - __main__ - Step 117973: {'lr': 5.558444225258788e-05, 'samples': 22650816, 'steps': 117972, 'loss/train': 0.6581745743751526} 08/31/2021 10:33:01 - INFO - __main__ - Step 117974: {'lr': 5.5581106040061614e-05, 'samples': 22651008, 'steps': 117973, 'loss/train': 0.0406845398247242} 08/31/2021 10:33:01 - INFO - __main__ - Step 117975: {'lr': 5.5577769915137497e-05, 'samples': 22651200, 'steps': 117974, 'loss/train': 1.0953909158706665} 08/31/2021 10:33:03 - INFO - __main__ - Step 117976: {'lr': 5.557443387781702e-05, 'samples': 22651392, 'steps': 117975, 'loss/train': 1.3471451997756958} 08/31/2021 10:33:03 - INFO - __main__ - Step 117977: {'lr': 5.5571097928101724e-05, 'samples': 22651584, 'steps': 117976, 'loss/train': 1.0346577167510986} 08/31/2021 10:33:04 - INFO - __main__ - Step 117978: {'lr': 5.556776206599309e-05, 'samples': 22651776, 'steps': 117977, 'loss/train': 0.034246888011693954} 08/31/2021 10:33:04 - INFO - __main__ - Step 117979: {'lr': 5.556442629149264e-05, 'samples': 22651968, 'steps': 117978, 'loss/train': 0.9188665747642517} 08/31/2021 10:33:04 - INFO - __main__ - Step 117980: {'lr': 5.556109060460182e-05, 'samples': 22652160, 'steps': 117979, 'loss/train': 1.3995239734649658} 08/31/2021 10:33:06 - INFO - __main__ - Step 117981: {'lr': 5.55577550053222e-05, 'samples': 22652352, 'steps': 117980, 'loss/train': 1.6879202127456665} 08/31/2021 10:33:07 - INFO - __main__ - Step 117982: {'lr': 5.555441949365522e-05, 'samples': 22652544, 'steps': 117981, 'loss/train': 0.891078531742096} 08/31/2021 10:33:07 - INFO - __main__ - Step 117983: {'lr': 5.5551084069602466e-05, 'samples': 22652736, 'steps': 117982, 'loss/train': 1.4729865789413452} 08/31/2021 10:33:08 - INFO - __main__ - Step 117984: {'lr': 5.554774873316543e-05, 'samples': 22652928, 'steps': 117983, 'loss/train': 1.258238673210144} 08/31/2021 10:33:08 - INFO - __main__ - Step 117985: {'lr': 5.554441348434553e-05, 'samples': 22653120, 'steps': 117984, 'loss/train': 1.1255238056182861} 08/31/2021 10:33:10 - INFO - __main__ - Step 117986: {'lr': 5.5541078323144285e-05, 'samples': 22653312, 'steps': 117985, 'loss/train': 0.8887289762496948} 08/31/2021 10:33:10 - INFO - __main__ - Step 117987: {'lr': 5.553774324956326e-05, 'samples': 22653504, 'steps': 117986, 'loss/train': 1.2773995399475098} 08/31/2021 10:33:11 - INFO - __main__ - Step 117988: {'lr': 5.553440826360393e-05, 'samples': 22653696, 'steps': 117987, 'loss/train': 1.1934044361114502} 08/31/2021 10:33:11 - INFO - __main__ - Step 117989: {'lr': 5.553107336526777e-05, 'samples': 22653888, 'steps': 117988, 'loss/train': 1.4366077184677124} 08/31/2021 10:33:11 - INFO - __main__ - Step 117990: {'lr': 5.552773855455631e-05, 'samples': 22654080, 'steps': 117989, 'loss/train': 0.49278730154037476} 08/31/2021 10:33:13 - INFO - __main__ - Step 117991: {'lr': 5.552440383147106e-05, 'samples': 22654272, 'steps': 117990, 'loss/train': 1.3958667516708374} 08/31/2021 10:33:13 - INFO - __main__ - Step 117992: {'lr': 5.5521069196013515e-05, 'samples': 22654464, 'steps': 117991, 'loss/train': 0.8471631407737732} 08/31/2021 10:33:14 - INFO - __main__ - Step 117993: {'lr': 5.551773464818516e-05, 'samples': 22654656, 'steps': 117992, 'loss/train': 1.267823338508606} 08/31/2021 10:33:14 - INFO - __main__ - Step 117994: {'lr': 5.5514400187987536e-05, 'samples': 22654848, 'steps': 117993, 'loss/train': 1.0989912748336792} 08/31/2021 10:33:14 - INFO - __main__ - Step 117995: {'lr': 5.551106581542212e-05, 'samples': 22655040, 'steps': 117994, 'loss/train': 0.8798019886016846} 08/31/2021 10:33:16 - INFO - __main__ - Step 117996: {'lr': 5.550773153049046e-05, 'samples': 22655232, 'steps': 117995, 'loss/train': 0.7597646713256836} 08/31/2021 10:33:16 - INFO - __main__ - Step 117997: {'lr': 5.550439733319396e-05, 'samples': 22655424, 'steps': 117996, 'loss/train': 1.419258952140808} 08/31/2021 10:33:17 - INFO - __main__ - Step 117998: {'lr': 5.550106322353418e-05, 'samples': 22655616, 'steps': 117997, 'loss/train': 0.33373740315437317} 08/31/2021 10:33:17 - INFO - __main__ - Step 117999: {'lr': 5.5497729201512636e-05, 'samples': 22655808, 'steps': 117998, 'loss/train': 0.6941890716552734} 08/31/2021 10:33:17 - INFO - __main__ - Step 118000: {'lr': 5.5494395267130795e-05, 'samples': 22656000, 'steps': 117999, 'loss/train': 0.7494014501571655} 08/31/2021 10:33:19 - INFO - __main__ - Step 118001: {'lr': 5.549106142039018e-05, 'samples': 22656192, 'steps': 118000, 'loss/train': 0.9622806906700134} 08/31/2021 10:33:19 - INFO - __main__ - Step 118002: {'lr': 5.5487727661292284e-05, 'samples': 22656384, 'steps': 118001, 'loss/train': 1.0772569179534912} 08/31/2021 10:33:20 - INFO - __main__ - Step 118003: {'lr': 5.5484393989838624e-05, 'samples': 22656576, 'steps': 118002, 'loss/train': 1.1404831409454346} 08/31/2021 10:33:20 - INFO - __main__ - Step 118004: {'lr': 5.548106040603068e-05, 'samples': 22656768, 'steps': 118003, 'loss/train': 1.1853768825531006} 08/31/2021 10:33:20 - INFO - __main__ - Step 118005: {'lr': 5.547772690986999e-05, 'samples': 22656960, 'steps': 118004, 'loss/train': 0.9716610908508301} 08/31/2021 10:33:22 - INFO - __main__ - Step 118006: {'lr': 5.547439350135802e-05, 'samples': 22657152, 'steps': 118005, 'loss/train': 1.4199131727218628} 08/31/2021 10:33:22 - INFO - __main__ - Step 118007: {'lr': 5.54710601804963e-05, 'samples': 22657344, 'steps': 118006, 'loss/train': 1.2142077684402466} 08/31/2021 10:33:23 - INFO - __main__ - Step 118008: {'lr': 5.5467726947286326e-05, 'samples': 22657536, 'steps': 118007, 'loss/train': 1.1780580282211304} 08/31/2021 10:33:23 - INFO - __main__ - Step 118009: {'lr': 5.546439380172957e-05, 'samples': 22657728, 'steps': 118008, 'loss/train': 0.8356359004974365} 08/31/2021 10:33:23 - INFO - __main__ - Step 118010: {'lr': 5.546106074382765e-05, 'samples': 22657920, 'steps': 118009, 'loss/train': 0.8972939848899841} 08/31/2021 10:33:25 - INFO - __main__ - Step 118011: {'lr': 5.545772777358188e-05, 'samples': 22658112, 'steps': 118010, 'loss/train': 1.2241723537445068} 08/31/2021 10:33:25 - INFO - __main__ - Step 118012: {'lr': 5.5454394890993855e-05, 'samples': 22658304, 'steps': 118011, 'loss/train': 1.1664537191390991} 08/31/2021 10:33:26 - INFO - __main__ - Step 118013: {'lr': 5.5451062096065094e-05, 'samples': 22658496, 'steps': 118012, 'loss/train': 0.6885267496109009} 08/31/2021 10:33:26 - INFO - __main__ - Step 118014: {'lr': 5.544772938879708e-05, 'samples': 22658688, 'steps': 118013, 'loss/train': 0.9006533026695251} 08/31/2021 10:33:26 - INFO - __main__ - Step 118015: {'lr': 5.54443967691913e-05, 'samples': 22658880, 'steps': 118014, 'loss/train': 0.4080064296722412} 08/31/2021 10:33:27 - INFO - __main__ - Step 118016: {'lr': 5.544106423724929e-05, 'samples': 22659072, 'steps': 118015, 'loss/train': 1.3378381729125977} 08/31/2021 10:33:28 - INFO - __main__ - Step 118017: {'lr': 5.543773179297254e-05, 'samples': 22659264, 'steps': 118016, 'loss/train': 1.3116520643234253} 08/31/2021 10:33:29 - INFO - __main__ - Step 118018: {'lr': 5.5434399436362524e-05, 'samples': 22659456, 'steps': 118017, 'loss/train': 1.1655148267745972} 08/31/2021 10:33:29 - INFO - __main__ - Step 118019: {'lr': 5.543106716742077e-05, 'samples': 22659648, 'steps': 118018, 'loss/train': 0.6451342105865479} 08/31/2021 10:33:29 - INFO - __main__ - Step 118020: {'lr': 5.542773498614878e-05, 'samples': 22659840, 'steps': 118019, 'loss/train': 1.1851999759674072} 08/31/2021 10:33:30 - INFO - __main__ - Step 118021: {'lr': 5.5424402892548076e-05, 'samples': 22660032, 'steps': 118020, 'loss/train': 1.7563016414642334} 08/31/2021 10:33:31 - INFO - __main__ - Step 118022: {'lr': 5.54210708866201e-05, 'samples': 22660224, 'steps': 118021, 'loss/train': 1.245688557624817} 08/31/2021 10:33:32 - INFO - __main__ - Step 118023: {'lr': 5.541773896836647e-05, 'samples': 22660416, 'steps': 118022, 'loss/train': 1.3057862520217896} 08/31/2021 10:33:32 - INFO - __main__ - Step 118024: {'lr': 5.541440713778853e-05, 'samples': 22660608, 'steps': 118023, 'loss/train': 1.150389313697815} 08/31/2021 10:33:32 - INFO - __main__ - Step 118025: {'lr': 5.541107539488785e-05, 'samples': 22660800, 'steps': 118024, 'loss/train': 1.3383105993270874} 08/31/2021 10:33:33 - INFO - __main__ - Step 118026: {'lr': 5.540774373966595e-05, 'samples': 22660992, 'steps': 118025, 'loss/train': 0.636038064956665} 08/31/2021 10:33:34 - INFO - __main__ - Step 118027: {'lr': 5.5404412172124305e-05, 'samples': 22661184, 'steps': 118026, 'loss/train': 1.4449963569641113} 08/31/2021 10:33:35 - INFO - __main__ - Step 118028: {'lr': 5.5401080692264435e-05, 'samples': 22661376, 'steps': 118027, 'loss/train': 0.5531924962997437} 08/31/2021 10:33:35 - INFO - __main__ - Step 118029: {'lr': 5.539774930008784e-05, 'samples': 22661568, 'steps': 118028, 'loss/train': 0.5580974817276001} 08/31/2021 10:33:35 - INFO - __main__ - Step 118030: {'lr': 5.5394417995596e-05, 'samples': 22661760, 'steps': 118029, 'loss/train': 0.25634893774986267} 08/31/2021 10:33:36 - INFO - __main__ - Step 118031: {'lr': 5.539108677879046e-05, 'samples': 22661952, 'steps': 118030, 'loss/train': 1.2379708290100098} 08/31/2021 10:33:36 - INFO - __main__ - Step 118032: {'lr': 5.538775564967266e-05, 'samples': 22662144, 'steps': 118031, 'loss/train': 1.761051058769226} 08/31/2021 10:33:38 - INFO - __main__ - Step 118033: {'lr': 5.5384424608244165e-05, 'samples': 22662336, 'steps': 118032, 'loss/train': 1.0529435873031616} 08/31/2021 10:33:39 - INFO - __main__ - Step 118034: {'lr': 5.5381093654506416e-05, 'samples': 22662528, 'steps': 118033, 'loss/train': 0.9783024191856384} 08/31/2021 10:33:39 - INFO - __main__ - Step 118035: {'lr': 5.5377762788460964e-05, 'samples': 22662720, 'steps': 118034, 'loss/train': 1.4831621646881104} 08/31/2021 10:33:39 - INFO - __main__ - Step 118036: {'lr': 5.5374432010109274e-05, 'samples': 22662912, 'steps': 118035, 'loss/train': 1.0611629486083984} 08/31/2021 10:33:40 - INFO - __main__ - Step 118037: {'lr': 5.5371101319452945e-05, 'samples': 22663104, 'steps': 118036, 'loss/train': 1.2580344676971436} 08/31/2021 10:33:41 - INFO - __main__ - Step 118038: {'lr': 5.536777071649332e-05, 'samples': 22663296, 'steps': 118037, 'loss/train': 2.068284511566162} 08/31/2021 10:33:42 - INFO - __main__ - Step 118039: {'lr': 5.536444020123199e-05, 'samples': 22663488, 'steps': 118038, 'loss/train': 1.0527563095092773} 08/31/2021 10:33:42 - INFO - __main__ - Step 118040: {'lr': 5.5361109773670426e-05, 'samples': 22663680, 'steps': 118039, 'loss/train': 1.0904074907302856} 08/31/2021 10:33:42 - INFO - __main__ - Step 118041: {'lr': 5.535777943381012e-05, 'samples': 22663872, 'steps': 118040, 'loss/train': 0.031154369935393333} 08/31/2021 10:33:43 - INFO - __main__ - Step 118042: {'lr': 5.535444918165264e-05, 'samples': 22664064, 'steps': 118041, 'loss/train': 0.8342173099517822} 08/31/2021 10:33:45 - INFO - __main__ - Step 118043: {'lr': 5.5351119017199415e-05, 'samples': 22664256, 'steps': 118042, 'loss/train': 0.9313760995864868} 08/31/2021 10:33:45 - INFO - __main__ - Step 118044: {'lr': 5.534778894045197e-05, 'samples': 22664448, 'steps': 118043, 'loss/train': 1.5814450979232788} 08/31/2021 10:33:46 - INFO - __main__ - Step 118045: {'lr': 5.53444589514118e-05, 'samples': 22664640, 'steps': 118044, 'loss/train': 0.6967385411262512} 08/31/2021 10:33:46 - INFO - __main__ - Step 118046: {'lr': 5.534112905008043e-05, 'samples': 22664832, 'steps': 118045, 'loss/train': 1.6120651960372925} 08/31/2021 10:33:46 - INFO - __main__ - Step 118047: {'lr': 5.5337799236459345e-05, 'samples': 22665024, 'steps': 118046, 'loss/train': 0.036855507642030716} 08/31/2021 10:33:47 - INFO - __main__ - Step 118048: {'lr': 5.533446951055004e-05, 'samples': 22665216, 'steps': 118047, 'loss/train': 0.036462876945734024} 08/31/2021 10:33:48 - INFO - __main__ - Step 118049: {'lr': 5.5331139872354e-05, 'samples': 22665408, 'steps': 118048, 'loss/train': 1.3315935134887695} 08/31/2021 10:33:49 - INFO - __main__ - Step 118050: {'lr': 5.532781032187284e-05, 'samples': 22665600, 'steps': 118049, 'loss/train': 1.4174057245254517} 08/31/2021 10:33:49 - INFO - __main__ - Step 118051: {'lr': 5.532448085910788e-05, 'samples': 22665792, 'steps': 118050, 'loss/train': 1.4028582572937012} 08/31/2021 10:33:49 - INFO - __main__ - Step 118052: {'lr': 5.532115148406072e-05, 'samples': 22665984, 'steps': 118051, 'loss/train': 1.117842197418213} 08/31/2021 10:33:50 - INFO - __main__ - Step 118053: {'lr': 5.531782219673284e-05, 'samples': 22666176, 'steps': 118052, 'loss/train': 1.383610725402832} 08/31/2021 10:33:51 - INFO - __main__ - Step 118054: {'lr': 5.5314492997125734e-05, 'samples': 22666368, 'steps': 118053, 'loss/train': 1.6423728466033936} 08/31/2021 10:33:52 - INFO - __main__ - Step 118055: {'lr': 5.5311163885240935e-05, 'samples': 22666560, 'steps': 118054, 'loss/train': 1.4861865043640137} 08/31/2021 10:33:52 - INFO - __main__ - Step 118056: {'lr': 5.5307834861079903e-05, 'samples': 22666752, 'steps': 118055, 'loss/train': 0.9086809158325195} 08/31/2021 10:33:52 - INFO - __main__ - Step 118057: {'lr': 5.530450592464414e-05, 'samples': 22666944, 'steps': 118056, 'loss/train': 1.3479552268981934} 08/31/2021 10:33:53 - INFO - __main__ - Step 118058: {'lr': 5.5301177075935184e-05, 'samples': 22667136, 'steps': 118057, 'loss/train': 1.4209014177322388} 08/31/2021 10:33:54 - INFO - __main__ - Step 118059: {'lr': 5.529784831495452e-05, 'samples': 22667328, 'steps': 118058, 'loss/train': 1.876627802848816} 08/31/2021 10:33:55 - INFO - __main__ - Step 118060: {'lr': 5.5294519641703625e-05, 'samples': 22667520, 'steps': 118059, 'loss/train': 1.0597811937332153} 08/31/2021 10:33:55 - INFO - __main__ - Step 118061: {'lr': 5.529119105618402e-05, 'samples': 22667712, 'steps': 118060, 'loss/train': 1.5785466432571411} 08/31/2021 10:33:55 - INFO - __main__ - Step 118062: {'lr': 5.528786255839721e-05, 'samples': 22667904, 'steps': 118061, 'loss/train': 1.1149104833602905} 08/31/2021 10:33:56 - INFO - __main__ - Step 118063: {'lr': 5.528453414834475e-05, 'samples': 22668096, 'steps': 118062, 'loss/train': 1.0462831258773804} 08/31/2021 10:33:57 - INFO - __main__ - Step 118064: {'lr': 5.5281205826027996e-05, 'samples': 22668288, 'steps': 118063, 'loss/train': 0.08618004620075226} 08/31/2021 10:33:58 - INFO - __main__ - Step 118065: {'lr': 5.527787759144853e-05, 'samples': 22668480, 'steps': 118064, 'loss/train': 1.3804872035980225} 08/31/2021 10:33:58 - INFO - __main__ - Step 118066: {'lr': 5.527454944460786e-05, 'samples': 22668672, 'steps': 118065, 'loss/train': 0.924223780632019} 08/31/2021 10:33:58 - INFO - __main__ - Step 118067: {'lr': 5.527122138550747e-05, 'samples': 22668864, 'steps': 118066, 'loss/train': 1.0792447328567505} 08/31/2021 10:33:59 - INFO - __main__ - Step 118068: {'lr': 5.526789341414884e-05, 'samples': 22669056, 'steps': 118067, 'loss/train': 0.6788783669471741} 08/31/2021 10:34:00 - INFO - __main__ - Step 118069: {'lr': 5.526456553053352e-05, 'samples': 22669248, 'steps': 118068, 'loss/train': 1.5262778997421265} 08/31/2021 10:34:01 - INFO - __main__ - Step 118070: {'lr': 5.526123773466296e-05, 'samples': 22669440, 'steps': 118069, 'loss/train': 0.8131850361824036} 08/31/2021 10:34:01 - INFO - __main__ - Step 118071: {'lr': 5.525791002653868e-05, 'samples': 22669632, 'steps': 118070, 'loss/train': 1.3588244915008545} 08/31/2021 10:34:01 - INFO - __main__ - Step 118072: {'lr': 5.5254582406162214e-05, 'samples': 22669824, 'steps': 118071, 'loss/train': 1.7345366477966309} 08/31/2021 10:34:02 - INFO - __main__ - Step 118073: {'lr': 5.5251254873534994e-05, 'samples': 22670016, 'steps': 118072, 'loss/train': 1.0921878814697266} 08/31/2021 10:34:02 - INFO - __main__ - Step 118074: {'lr': 5.524792742865856e-05, 'samples': 22670208, 'steps': 118073, 'loss/train': 0.9548289775848389} 08/31/2021 10:34:04 - INFO - __main__ - Step 118075: {'lr': 5.524460007153442e-05, 'samples': 22670400, 'steps': 118074, 'loss/train': 0.9858881831169128} 08/31/2021 10:34:04 - INFO - __main__ - Step 118076: {'lr': 5.524127280216404e-05, 'samples': 22670592, 'steps': 118075, 'loss/train': 0.5848466157913208} 08/31/2021 10:34:04 - INFO - __main__ - Step 118077: {'lr': 5.5237945620549014e-05, 'samples': 22670784, 'steps': 118076, 'loss/train': 0.7144117951393127} 08/31/2021 10:34:05 - INFO - __main__ - Step 118078: {'lr': 5.523461852669071e-05, 'samples': 22670976, 'steps': 118077, 'loss/train': 1.2784720659255981} 08/31/2021 10:34:05 - INFO - __main__ - Step 118079: {'lr': 5.523129152059064e-05, 'samples': 22671168, 'steps': 118078, 'loss/train': 1.4637871980667114} 08/31/2021 10:34:07 - INFO - __main__ - Step 118080: {'lr': 5.522796460225038e-05, 'samples': 22671360, 'steps': 118079, 'loss/train': 0.2551010847091675} 08/31/2021 10:34:07 - INFO - __main__ - Step 118081: {'lr': 5.522463777167139e-05, 'samples': 22671552, 'steps': 118080, 'loss/train': 0.24146339297294617} 08/31/2021 10:34:07 - INFO - __main__ - Step 118082: {'lr': 5.522131102885516e-05, 'samples': 22671744, 'steps': 118081, 'loss/train': 0.9462484121322632} 08/31/2021 10:34:08 - INFO - __main__ - Step 118083: {'lr': 5.521798437380321e-05, 'samples': 22671936, 'steps': 118082, 'loss/train': 1.5216870307922363} 08/31/2021 10:34:08 - INFO - __main__ - Step 118084: {'lr': 5.5214657806517024e-05, 'samples': 22672128, 'steps': 118083, 'loss/train': 1.2630254030227661} 08/31/2021 10:34:10 - INFO - __main__ - Step 118085: {'lr': 5.521133132699813e-05, 'samples': 22672320, 'steps': 118084, 'loss/train': 0.7053848505020142} 08/31/2021 10:34:10 - INFO - __main__ - Step 118086: {'lr': 5.520800493524797e-05, 'samples': 22672512, 'steps': 118085, 'loss/train': 0.9401437640190125} 08/31/2021 10:34:10 - INFO - __main__ - Step 118087: {'lr': 5.52046786312681e-05, 'samples': 22672704, 'steps': 118086, 'loss/train': 1.1520973443984985} 08/31/2021 10:34:11 - INFO - __main__ - Step 118088: {'lr': 5.520135241505999e-05, 'samples': 22672896, 'steps': 118087, 'loss/train': 1.3380961418151855} 08/31/2021 10:34:11 - INFO - __main__ - Step 118089: {'lr': 5.5198026286625155e-05, 'samples': 22673088, 'steps': 118088, 'loss/train': 0.5957860350608826} 08/31/2021 10:34:13 - INFO - __main__ - Step 118090: {'lr': 5.519470024596512e-05, 'samples': 22673280, 'steps': 118089, 'loss/train': 0.46684789657592773} 08/31/2021 10:34:14 - INFO - __main__ - Step 118091: {'lr': 5.5191374293081325e-05, 'samples': 22673472, 'steps': 118090, 'loss/train': 0.8783487677574158} 08/31/2021 10:34:14 - INFO - __main__ - Step 118092: {'lr': 5.5188048427975254e-05, 'samples': 22673664, 'steps': 118091, 'loss/train': 1.1845890283584595} 08/31/2021 10:34:14 - INFO - __main__ - Step 118093: {'lr': 5.518472265064845e-05, 'samples': 22673856, 'steps': 118092, 'loss/train': 1.1309309005737305} 08/31/2021 10:34:15 - INFO - __main__ - Step 118094: {'lr': 5.5181396961102416e-05, 'samples': 22674048, 'steps': 118093, 'loss/train': 0.6437451839447021} 08/31/2021 10:34:16 - INFO - __main__ - Step 118095: {'lr': 5.517807135933864e-05, 'samples': 22674240, 'steps': 118094, 'loss/train': 1.350798487663269} 08/31/2021 10:34:17 - INFO - __main__ - Step 118096: {'lr': 5.517474584535859e-05, 'samples': 22674432, 'steps': 118095, 'loss/train': 0.5974944233894348} 08/31/2021 10:34:17 - INFO - __main__ - Step 118097: {'lr': 5.5171420419163815e-05, 'samples': 22674624, 'steps': 118096, 'loss/train': 1.0802397727966309} 08/31/2021 10:34:17 - INFO - __main__ - Step 118098: {'lr': 5.5168095080755793e-05, 'samples': 22674816, 'steps': 118097, 'loss/train': 0.882287859916687} 08/31/2021 10:34:18 - INFO - __main__ - Step 118099: {'lr': 5.516476983013602e-05, 'samples': 22675008, 'steps': 118098, 'loss/train': 0.5314879417419434} 08/31/2021 10:34:19 - INFO - __main__ - Step 118100: {'lr': 5.516144466730599e-05, 'samples': 22675200, 'steps': 118099, 'loss/train': 1.5044811964035034} 08/31/2021 10:34:20 - INFO - __main__ - Step 118101: {'lr': 5.515811959226722e-05, 'samples': 22675392, 'steps': 118100, 'loss/train': 1.1596311330795288} 08/31/2021 10:34:20 - INFO - __main__ - Step 118102: {'lr': 5.515479460502118e-05, 'samples': 22675584, 'steps': 118101, 'loss/train': 0.9559275507926941} 08/31/2021 10:34:21 - INFO - __main__ - Step 118103: {'lr': 5.515146970556936e-05, 'samples': 22675776, 'steps': 118102, 'loss/train': 1.2528774738311768} 08/31/2021 10:34:21 - INFO - __main__ - Step 118104: {'lr': 5.51481448939134e-05, 'samples': 22675968, 'steps': 118103, 'loss/train': 1.341019868850708} 08/31/2021 10:34:23 - INFO - __main__ - Step 118105: {'lr': 5.5144820170054565e-05, 'samples': 22676160, 'steps': 118104, 'loss/train': 0.9170834422111511} 08/31/2021 10:34:24 - INFO - __main__ - Step 118106: {'lr': 5.51414955339945e-05, 'samples': 22676352, 'steps': 118105, 'loss/train': 2.2304255962371826} 08/31/2021 10:34:24 - INFO - __main__ - Step 118107: {'lr': 5.513817098573465e-05, 'samples': 22676544, 'steps': 118106, 'loss/train': 0.572163462638855} 08/31/2021 10:34:24 - INFO - __main__ - Step 118108: {'lr': 5.513484652527656e-05, 'samples': 22676736, 'steps': 118107, 'loss/train': 0.4954168200492859} 08/31/2021 10:34:25 - INFO - __main__ - Step 118109: {'lr': 5.513152215262168e-05, 'samples': 22676928, 'steps': 118108, 'loss/train': 1.2122464179992676} 08/31/2021 10:34:25 - INFO - __main__ - Step 118110: {'lr': 5.512819786777151e-05, 'samples': 22677120, 'steps': 118109, 'loss/train': 1.2048380374908447} 08/31/2021 10:34:26 - INFO - __main__ - Step 118111: {'lr': 5.5124873670727604e-05, 'samples': 22677312, 'steps': 118110, 'loss/train': 0.8119208812713623} 08/31/2021 10:34:27 - INFO - __main__ - Step 118112: {'lr': 5.51215495614914e-05, 'samples': 22677504, 'steps': 118111, 'loss/train': 0.6369384527206421} 08/31/2021 10:34:27 - INFO - __main__ - Step 118113: {'lr': 5.511822554006443e-05, 'samples': 22677696, 'steps': 118112, 'loss/train': 1.5536752939224243} 08/31/2021 10:34:28 - INFO - __main__ - Step 118114: {'lr': 5.511490160644819e-05, 'samples': 22677888, 'steps': 118113, 'loss/train': 1.5466058254241943} 08/31/2021 10:34:28 - INFO - __main__ - Step 118115: {'lr': 5.511157776064415e-05, 'samples': 22678080, 'steps': 118114, 'loss/train': 1.0666706562042236} 08/31/2021 10:34:29 - INFO - __main__ - Step 118116: {'lr': 5.510825400265382e-05, 'samples': 22678272, 'steps': 118115, 'loss/train': 0.8904542922973633} 08/31/2021 10:34:30 - INFO - __main__ - Step 118117: {'lr': 5.510493033247879e-05, 'samples': 22678464, 'steps': 118116, 'loss/train': 1.4811701774597168} 08/31/2021 10:34:30 - INFO - __main__ - Step 118118: {'lr': 5.510160675012041e-05, 'samples': 22678656, 'steps': 118117, 'loss/train': 1.0772686004638672} 08/31/2021 10:34:31 - INFO - __main__ - Step 118119: {'lr': 5.5098283255580226e-05, 'samples': 22678848, 'steps': 118118, 'loss/train': 1.0113611221313477} 08/31/2021 10:34:31 - INFO - __main__ - Step 118120: {'lr': 5.5094959848859734e-05, 'samples': 22679040, 'steps': 118119, 'loss/train': 0.9833158850669861} 08/31/2021 10:34:33 - INFO - __main__ - Step 118121: {'lr': 5.5091636529960466e-05, 'samples': 22679232, 'steps': 118120, 'loss/train': 0.2266380488872528} 08/31/2021 10:34:33 - INFO - __main__ - Step 118122: {'lr': 5.508831329888389e-05, 'samples': 22679424, 'steps': 118121, 'loss/train': 0.9246640205383301} 08/31/2021 10:34:33 - INFO - __main__ - Step 118123: {'lr': 5.508499015563151e-05, 'samples': 22679616, 'steps': 118122, 'loss/train': 0.04100852087140083} 08/31/2021 10:34:34 - INFO - __main__ - Step 118124: {'lr': 5.508166710020482e-05, 'samples': 22679808, 'steps': 118123, 'loss/train': 1.1370253562927246} 08/31/2021 10:34:34 - INFO - __main__ - Step 118125: {'lr': 5.5078344132605316e-05, 'samples': 22680000, 'steps': 118124, 'loss/train': 0.3856859803199768} 08/31/2021 10:34:36 - INFO - __main__ - Step 118126: {'lr': 5.507502125283453e-05, 'samples': 22680192, 'steps': 118125, 'loss/train': 0.0922156497836113} 08/31/2021 10:34:36 - INFO - __main__ - Step 118127: {'lr': 5.507169846089391e-05, 'samples': 22680384, 'steps': 118126, 'loss/train': 0.9014958739280701} 08/31/2021 10:34:36 - INFO - __main__ - Step 118128: {'lr': 5.5068375756784996e-05, 'samples': 22680576, 'steps': 118127, 'loss/train': 1.4539014101028442} 08/31/2021 10:34:37 - INFO - __main__ - Step 118129: {'lr': 5.506505314050925e-05, 'samples': 22680768, 'steps': 118128, 'loss/train': 1.4195982217788696} 08/31/2021 10:34:37 - INFO - __main__ - Step 118130: {'lr': 5.506173061206818e-05, 'samples': 22680960, 'steps': 118129, 'loss/train': 1.275244116783142} 08/31/2021 10:34:39 - INFO - __main__ - Step 118131: {'lr': 5.505840817146338e-05, 'samples': 22681152, 'steps': 118130, 'loss/train': 1.1440856456756592} 08/31/2021 10:34:39 - INFO - __main__ - Step 118132: {'lr': 5.5055085818696144e-05, 'samples': 22681344, 'steps': 118131, 'loss/train': 1.313401699066162} 08/31/2021 10:34:40 - INFO - __main__ - Step 118133: {'lr': 5.505176355376812e-05, 'samples': 22681536, 'steps': 118132, 'loss/train': 1.7169666290283203} 08/31/2021 10:34:40 - INFO - __main__ - Step 118134: {'lr': 5.504844137668072e-05, 'samples': 22681728, 'steps': 118133, 'loss/train': 0.7931349277496338} 08/31/2021 10:34:40 - INFO - __main__ - Step 118135: {'lr': 5.5045119287435526e-05, 'samples': 22681920, 'steps': 118134, 'loss/train': 1.106142520904541} 08/31/2021 10:34:41 - INFO - __main__ - Step 118136: {'lr': 5.504179728603395e-05, 'samples': 22682112, 'steps': 118135, 'loss/train': 0.024306239560246468} 08/31/2021 10:34:42 - INFO - __main__ - Step 118137: {'lr': 5.503847537247755e-05, 'samples': 22682304, 'steps': 118136, 'loss/train': 0.4730665683746338} 08/31/2021 10:34:43 - INFO - __main__ - Step 118138: {'lr': 5.503515354676783e-05, 'samples': 22682496, 'steps': 118137, 'loss/train': 0.9768643975257874} 08/31/2021 10:34:43 - INFO - __main__ - Step 118139: {'lr': 5.503183180890622e-05, 'samples': 22682688, 'steps': 118138, 'loss/train': 1.3734713792800903} 08/31/2021 10:34:44 - INFO - __main__ - Step 118140: {'lr': 5.502851015889429e-05, 'samples': 22682880, 'steps': 118139, 'loss/train': 1.2582255601882935} 08/31/2021 10:34:44 - INFO - __main__ - Step 118141: {'lr': 5.50251885967335e-05, 'samples': 22683072, 'steps': 118140, 'loss/train': 1.7397756576538086} 08/31/2021 10:34:46 - INFO - __main__ - Step 118142: {'lr': 5.502186712242535e-05, 'samples': 22683264, 'steps': 118141, 'loss/train': 1.5636487007141113} 08/31/2021 10:34:47 - INFO - __main__ - Step 118143: {'lr': 5.5018545735971314e-05, 'samples': 22683456, 'steps': 118142, 'loss/train': 1.7761597633361816} 08/31/2021 10:34:47 - INFO - __main__ - Step 118144: {'lr': 5.5015224437373005e-05, 'samples': 22683648, 'steps': 118143, 'loss/train': 1.4639849662780762} 08/31/2021 10:34:47 - INFO - __main__ - Step 118145: {'lr': 5.5011903226631745e-05, 'samples': 22683840, 'steps': 118144, 'loss/train': 0.3554973006248474} 08/31/2021 10:34:48 - INFO - __main__ - Step 118146: {'lr': 5.500858210374912e-05, 'samples': 22684032, 'steps': 118145, 'loss/train': 1.549149513244629} 08/31/2021 10:34:49 - INFO - __main__ - Step 118147: {'lr': 5.5005261068726634e-05, 'samples': 22684224, 'steps': 118146, 'loss/train': 1.3662861585617065} 08/31/2021 10:34:50 - INFO - __main__ - Step 118148: {'lr': 5.500194012156576e-05, 'samples': 22684416, 'steps': 118147, 'loss/train': 0.7703097462654114} 08/31/2021 10:34:50 - INFO - __main__ - Step 118149: {'lr': 5.499861926226799e-05, 'samples': 22684608, 'steps': 118148, 'loss/train': 1.6361181735992432} 08/31/2021 10:34:50 - INFO - __main__ - Step 118150: {'lr': 5.4995298490834844e-05, 'samples': 22684800, 'steps': 118149, 'loss/train': 0.14556270837783813} 08/31/2021 10:34:51 - INFO - __main__ - Step 118151: {'lr': 5.499197780726781e-05, 'samples': 22684992, 'steps': 118150, 'loss/train': 1.0234928131103516} 08/31/2021 10:34:52 - INFO - __main__ - Step 118152: {'lr': 5.498865721156837e-05, 'samples': 22685184, 'steps': 118151, 'loss/train': 0.513832151889801} 08/31/2021 10:34:53 - INFO - __main__ - Step 118153: {'lr': 5.4985336703738034e-05, 'samples': 22685376, 'steps': 118152, 'loss/train': 1.3655509948730469} 08/31/2021 10:34:53 - INFO - __main__ - Step 118154: {'lr': 5.4982016283778304e-05, 'samples': 22685568, 'steps': 118153, 'loss/train': 1.646742582321167} 08/31/2021 10:34:53 - INFO - __main__ - Step 118155: {'lr': 5.497869595169064e-05, 'samples': 22685760, 'steps': 118154, 'loss/train': 1.2233638763427734} 08/31/2021 10:34:54 - INFO - __main__ - Step 118156: {'lr': 5.49753757074766e-05, 'samples': 22685952, 'steps': 118155, 'loss/train': 0.9331173896789551} 08/31/2021 10:34:54 - INFO - __main__ - Step 118157: {'lr': 5.4972055551137625e-05, 'samples': 22686144, 'steps': 118156, 'loss/train': 0.4898744523525238} 08/31/2021 10:34:56 - INFO - __main__ - Step 118158: {'lr': 5.496873548267531e-05, 'samples': 22686336, 'steps': 118157, 'loss/train': 1.2180801630020142} 08/31/2021 10:34:56 - INFO - __main__ - Step 118159: {'lr': 5.4965415502091026e-05, 'samples': 22686528, 'steps': 118158, 'loss/train': 0.8157643675804138} 08/31/2021 10:34:57 - INFO - __main__ - Step 118160: {'lr': 5.496209560938628e-05, 'samples': 22686720, 'steps': 118159, 'loss/train': 0.018834639340639114} 08/31/2021 10:34:57 - INFO - __main__ - Step 118161: {'lr': 5.4958775804562625e-05, 'samples': 22686912, 'steps': 118160, 'loss/train': 0.6628736853599548} 08/31/2021 10:34:58 - INFO - __main__ - Step 118162: {'lr': 5.495545608762154e-05, 'samples': 22687104, 'steps': 118161, 'loss/train': 0.8142940402030945} 08/31/2021 10:34:58 - INFO - __main__ - Step 118163: {'lr': 5.4952136458564505e-05, 'samples': 22687296, 'steps': 118162, 'loss/train': 0.6742838025093079} 08/31/2021 10:34:59 - INFO - __main__ - Step 118164: {'lr': 5.4948816917393035e-05, 'samples': 22687488, 'steps': 118163, 'loss/train': 1.1783535480499268} 08/31/2021 10:35:00 - INFO - __main__ - Step 118165: {'lr': 5.494549746410859e-05, 'samples': 22687680, 'steps': 118164, 'loss/train': 1.3127391338348389} 08/31/2021 10:35:00 - INFO - __main__ - Step 118166: {'lr': 5.494217809871274e-05, 'samples': 22687872, 'steps': 118165, 'loss/train': 0.7998290061950684} 08/31/2021 10:35:00 - INFO - __main__ - Step 118167: {'lr': 5.493885882120689e-05, 'samples': 22688064, 'steps': 118166, 'loss/train': 1.1453921794891357} 08/31/2021 10:35:01 - INFO - __main__ - Step 118168: {'lr': 5.493553963159262e-05, 'samples': 22688256, 'steps': 118167, 'loss/train': 1.4051936864852905} 08/31/2021 10:35:02 - INFO - __main__ - Step 118169: {'lr': 5.493222052987137e-05, 'samples': 22688448, 'steps': 118168, 'loss/train': 0.4757973551750183} 08/31/2021 10:35:03 - INFO - __main__ - Step 118170: {'lr': 5.492890151604466e-05, 'samples': 22688640, 'steps': 118169, 'loss/train': 1.3202835321426392} 08/31/2021 10:35:03 - INFO - __main__ - Step 118171: {'lr': 5.4925582590114016e-05, 'samples': 22688832, 'steps': 118170, 'loss/train': 0.45165014266967773} 08/31/2021 10:35:03 - INFO - __main__ - Step 118172: {'lr': 5.4922263752080845e-05, 'samples': 22689024, 'steps': 118171, 'loss/train': 1.0469481945037842} 08/31/2021 10:35:04 - INFO - __main__ - Step 118173: {'lr': 5.491894500194669e-05, 'samples': 22689216, 'steps': 118172, 'loss/train': 1.9215401411056519} 08/31/2021 10:35:06 - INFO - __main__ - Step 118174: {'lr': 5.491562633971306e-05, 'samples': 22689408, 'steps': 118173, 'loss/train': 0.8806369304656982} 08/31/2021 10:35:06 - INFO - __main__ - Step 118175: {'lr': 5.491230776538142e-05, 'samples': 22689600, 'steps': 118174, 'loss/train': 1.2798351049423218} 08/31/2021 10:35:06 - INFO - __main__ - Step 118176: {'lr': 5.4908989278953295e-05, 'samples': 22689792, 'steps': 118175, 'loss/train': 1.4291266202926636} 08/31/2021 10:35:07 - INFO - __main__ - Step 118177: {'lr': 5.4905670880430165e-05, 'samples': 22689984, 'steps': 118176, 'loss/train': 1.4823330640792847} 08/31/2021 10:35:07 - INFO - __main__ - Step 118178: {'lr': 5.490235256981352e-05, 'samples': 22690176, 'steps': 118177, 'loss/train': 1.098122477531433} 08/31/2021 10:35:07 - INFO - __main__ - Step 118179: {'lr': 5.489903434710489e-05, 'samples': 22690368, 'steps': 118178, 'loss/train': 0.4056299030780792} 08/31/2021 10:35:09 - INFO - __main__ - Step 118180: {'lr': 5.489571621230571e-05, 'samples': 22690560, 'steps': 118179, 'loss/train': 0.24862413108348846} 08/31/2021 10:35:09 - INFO - __main__ - Step 118181: {'lr': 5.489239816541755e-05, 'samples': 22690752, 'steps': 118180, 'loss/train': 1.5651758909225464} 08/31/2021 10:35:10 - INFO - __main__ - Step 118182: {'lr': 5.4889080206441846e-05, 'samples': 22690944, 'steps': 118181, 'loss/train': 1.3266311883926392} 08/31/2021 10:35:10 - INFO - __main__ - Step 118183: {'lr': 5.488576233538009e-05, 'samples': 22691136, 'steps': 118182, 'loss/train': 1.597264051437378} 08/31/2021 10:35:10 - INFO - __main__ - Step 118184: {'lr': 5.48824445522339e-05, 'samples': 22691328, 'steps': 118183, 'loss/train': 0.5262551307678223} 08/31/2021 10:35:12 - INFO - __main__ - Step 118185: {'lr': 5.487912685700458e-05, 'samples': 22691520, 'steps': 118184, 'loss/train': 1.2769591808319092} 08/31/2021 10:35:12 - INFO - __main__ - Step 118186: {'lr': 5.487580924969374e-05, 'samples': 22691712, 'steps': 118185, 'loss/train': 0.7277992963790894} 08/31/2021 10:35:13 - INFO - __main__ - Step 118187: {'lr': 5.487249173030282e-05, 'samples': 22691904, 'steps': 118186, 'loss/train': 1.139526128768921} 08/31/2021 10:35:13 - INFO - __main__ - Step 118188: {'lr': 5.486917429883334e-05, 'samples': 22692096, 'steps': 118187, 'loss/train': 0.67181396484375} 08/31/2021 10:35:14 - INFO - __main__ - Step 118189: {'lr': 5.486585695528681e-05, 'samples': 22692288, 'steps': 118188, 'loss/train': 0.9111095666885376} 08/31/2021 10:35:15 - INFO - __main__ - Step 118190: {'lr': 5.486253969966473e-05, 'samples': 22692480, 'steps': 118189, 'loss/train': 1.3187110424041748} 08/31/2021 10:35:15 - INFO - __main__ - Step 118191: {'lr': 5.4859222531968565e-05, 'samples': 22692672, 'steps': 118190, 'loss/train': 0.8211202621459961} 08/31/2021 10:35:16 - INFO - __main__ - Step 118192: {'lr': 5.485590545219982e-05, 'samples': 22692864, 'steps': 118191, 'loss/train': 1.116476058959961} 08/31/2021 10:35:16 - INFO - __main__ - Step 118193: {'lr': 5.4852588460360006e-05, 'samples': 22693056, 'steps': 118192, 'loss/train': 0.7336297035217285} 08/31/2021 10:35:16 - INFO - __main__ - Step 118194: {'lr': 5.484927155645059e-05, 'samples': 22693248, 'steps': 118193, 'loss/train': 1.282820224761963} 08/31/2021 10:35:18 - INFO - __main__ - Step 118195: {'lr': 5.48459547404731e-05, 'samples': 22693440, 'steps': 118194, 'loss/train': 1.1146390438079834} 08/31/2021 10:35:18 - INFO - __main__ - Step 118196: {'lr': 5.4842638012429e-05, 'samples': 22693632, 'steps': 118195, 'loss/train': 1.0474843978881836} 08/31/2021 10:35:19 - INFO - __main__ - Step 118197: {'lr': 5.483932137231978e-05, 'samples': 22693824, 'steps': 118196, 'loss/train': 1.4836108684539795} 08/31/2021 10:35:19 - INFO - __main__ - Step 118198: {'lr': 5.483600482014703e-05, 'samples': 22694016, 'steps': 118197, 'loss/train': 2.824469566345215} 08/31/2021 10:35:19 - INFO - __main__ - Step 118199: {'lr': 5.48326883559121e-05, 'samples': 22694208, 'steps': 118198, 'loss/train': 0.15177717804908752} 08/31/2021 10:35:22 - INFO - __main__ - Step 118200: {'lr': 5.482937197961654e-05, 'samples': 22694400, 'steps': 118199, 'loss/train': 0.7921124696731567} 08/31/2021 10:35:23 - INFO - __main__ - Step 118201: {'lr': 5.4826055691261864e-05, 'samples': 22694592, 'steps': 118200, 'loss/train': 0.6192171573638916} 08/31/2021 10:35:23 - INFO - __main__ - Step 118202: {'lr': 5.482273949084957e-05, 'samples': 22694784, 'steps': 118201, 'loss/train': 0.7070932984352112} 08/31/2021 10:35:23 - INFO - __main__ - Step 118203: {'lr': 5.481942337838111e-05, 'samples': 22694976, 'steps': 118202, 'loss/train': 1.7391393184661865} 08/31/2021 10:35:24 - INFO - __main__ - Step 118204: {'lr': 5.4816107353858033e-05, 'samples': 22695168, 'steps': 118203, 'loss/train': 0.818723738193512} 08/31/2021 10:35:24 - INFO - __main__ - Step 118205: {'lr': 5.4812791417281796e-05, 'samples': 22695360, 'steps': 118204, 'loss/train': 0.7836660146713257} 08/31/2021 10:35:25 - INFO - __main__ - Step 118206: {'lr': 5.480947556865387e-05, 'samples': 22695552, 'steps': 118205, 'loss/train': 0.9238561391830444} 08/31/2021 10:35:26 - INFO - __main__ - Step 118207: {'lr': 5.480615980797582e-05, 'samples': 22695744, 'steps': 118206, 'loss/train': 1.2828550338745117} 08/31/2021 10:35:27 - INFO - __main__ - Step 118208: {'lr': 5.480284413524908e-05, 'samples': 22695936, 'steps': 118207, 'loss/train': 0.8298659920692444} 08/31/2021 10:35:27 - INFO - __main__ - Step 118209: {'lr': 5.479952855047527e-05, 'samples': 22696128, 'steps': 118208, 'loss/train': 1.4762651920318604} 08/31/2021 10:35:28 - INFO - __main__ - Step 118210: {'lr': 5.479621305365567e-05, 'samples': 22696320, 'steps': 118209, 'loss/train': 0.4138961136341095} 08/31/2021 10:35:28 - INFO - __main__ - Step 118211: {'lr': 5.4792897644791925e-05, 'samples': 22696512, 'steps': 118210, 'loss/train': 1.601694107055664} 08/31/2021 10:35:29 - INFO - __main__ - Step 118212: {'lr': 5.478958232388545e-05, 'samples': 22696704, 'steps': 118211, 'loss/train': 1.1741306781768799} 08/31/2021 10:35:30 - INFO - __main__ - Step 118213: {'lr': 5.4786267090937787e-05, 'samples': 22696896, 'steps': 118212, 'loss/train': 0.973304271697998} 08/31/2021 10:35:30 - INFO - __main__ - Step 118214: {'lr': 5.4782951945950424e-05, 'samples': 22697088, 'steps': 118213, 'loss/train': 1.2175464630126953} 08/31/2021 10:35:30 - INFO - __main__ - Step 118215: {'lr': 5.477963688892487e-05, 'samples': 22697280, 'steps': 118214, 'loss/train': 0.7043954730033875} 08/31/2021 10:35:31 - INFO - __main__ - Step 118216: {'lr': 5.4776321919862565e-05, 'samples': 22697472, 'steps': 118215, 'loss/train': 1.304571270942688} 08/31/2021 10:35:32 - INFO - __main__ - Step 118217: {'lr': 5.477300703876506e-05, 'samples': 22697664, 'steps': 118216, 'loss/train': 0.823405921459198} 08/31/2021 10:35:33 - INFO - __main__ - Step 118218: {'lr': 5.476969224563383e-05, 'samples': 22697856, 'steps': 118217, 'loss/train': 1.432120442390442} 08/31/2021 10:35:33 - INFO - __main__ - Step 118219: {'lr': 5.476637754047034e-05, 'samples': 22698048, 'steps': 118218, 'loss/train': 0.8242786526679993} 08/31/2021 10:35:34 - INFO - __main__ - Step 118220: {'lr': 5.476306292327618e-05, 'samples': 22698240, 'steps': 118219, 'loss/train': 0.8648847341537476} 08/31/2021 10:35:34 - INFO - __main__ - Step 118221: {'lr': 5.475974839405273e-05, 'samples': 22698432, 'steps': 118220, 'loss/train': 1.6417814493179321} 08/31/2021 10:35:34 - INFO - __main__ - Step 118222: {'lr': 5.47564339528015e-05, 'samples': 22698624, 'steps': 118221, 'loss/train': 0.8239092230796814} 08/31/2021 10:35:36 - INFO - __main__ - Step 118223: {'lr': 5.4753119599524006e-05, 'samples': 22698816, 'steps': 118222, 'loss/train': 0.967616856098175} 08/31/2021 10:35:37 - INFO - __main__ - Step 118224: {'lr': 5.474980533422175e-05, 'samples': 22699008, 'steps': 118223, 'loss/train': 1.3563942909240723} 08/31/2021 10:35:37 - INFO - __main__ - Step 118225: {'lr': 5.474649115689623e-05, 'samples': 22699200, 'steps': 118224, 'loss/train': 0.9909517765045166} 08/31/2021 10:35:37 - INFO - __main__ - Step 118226: {'lr': 5.474317706754892e-05, 'samples': 22699392, 'steps': 118225, 'loss/train': 0.32718172669410706} 08/31/2021 10:35:38 - INFO - __main__ - Step 118227: {'lr': 5.473986306618131e-05, 'samples': 22699584, 'steps': 118226, 'loss/train': 0.0382610559463501} 08/31/2021 10:35:39 - INFO - __main__ - Step 118228: {'lr': 5.473654915279491e-05, 'samples': 22699776, 'steps': 118227, 'loss/train': 1.5101341009140015} 08/31/2021 10:35:40 - INFO - __main__ - Step 118229: {'lr': 5.473323532739122e-05, 'samples': 22699968, 'steps': 118228, 'loss/train': 1.4738625288009644} 08/31/2021 10:35:40 - INFO - __main__ - Step 118230: {'lr': 5.4729921589971726e-05, 'samples': 22700160, 'steps': 118229, 'loss/train': 0.7924505472183228} 08/31/2021 10:35:40 - INFO - __main__ - Step 118231: {'lr': 5.472660794053796e-05, 'samples': 22700352, 'steps': 118230, 'loss/train': 1.0036543607711792} 08/31/2021 10:35:41 - INFO - __main__ - Step 118232: {'lr': 5.472329437909132e-05, 'samples': 22700544, 'steps': 118231, 'loss/train': 1.2617976665496826} 08/31/2021 10:35:42 - INFO - __main__ - Step 118233: {'lr': 5.4719980905633346e-05, 'samples': 22700736, 'steps': 118232, 'loss/train': 1.7819864749908447} 08/31/2021 10:35:43 - INFO - __main__ - Step 118234: {'lr': 5.471666752016552e-05, 'samples': 22700928, 'steps': 118233, 'loss/train': 0.7120270133018494} 08/31/2021 10:35:43 - INFO - __main__ - Step 118235: {'lr': 5.4713354222689385e-05, 'samples': 22701120, 'steps': 118234, 'loss/train': 2.1285672187805176} 08/31/2021 10:35:44 - INFO - __main__ - Step 118236: {'lr': 5.471004101320637e-05, 'samples': 22701312, 'steps': 118235, 'loss/train': 0.6013232469558716} 08/31/2021 10:35:44 - INFO - __main__ - Step 118237: {'lr': 5.470672789171802e-05, 'samples': 22701504, 'steps': 118236, 'loss/train': 0.9025256037712097} 08/31/2021 10:35:45 - INFO - __main__ - Step 118238: {'lr': 5.4703414858225777e-05, 'samples': 22701696, 'steps': 118237, 'loss/train': 0.64970463514328} 08/31/2021 10:35:46 - INFO - __main__ - Step 118239: {'lr': 5.470010191273117e-05, 'samples': 22701888, 'steps': 118238, 'loss/train': 1.4359610080718994} 08/31/2021 10:35:46 - INFO - __main__ - Step 118240: {'lr': 5.46967890552357e-05, 'samples': 22702080, 'steps': 118239, 'loss/train': 1.2743221521377563} 08/31/2021 10:35:47 - INFO - __main__ - Step 118241: {'lr': 5.4693476285740813e-05, 'samples': 22702272, 'steps': 118240, 'loss/train': 0.9887008666992188} 08/31/2021 10:35:47 - INFO - __main__ - Step 118242: {'lr': 5.4690163604248137e-05, 'samples': 22702464, 'steps': 118241, 'loss/train': 0.8158356547355652} 08/31/2021 10:35:47 - INFO - __main__ - Step 118243: {'lr': 5.468685101075896e-05, 'samples': 22702656, 'steps': 118242, 'loss/train': 1.3398271799087524} 08/31/2021 10:35:49 - INFO - __main__ - Step 118244: {'lr': 5.468353850527488e-05, 'samples': 22702848, 'steps': 118243, 'loss/train': 0.867484450340271} 08/31/2021 10:35:50 - INFO - __main__ - Step 118245: {'lr': 5.468022608779741e-05, 'samples': 22703040, 'steps': 118244, 'loss/train': 1.0425444841384888} 08/31/2021 10:35:50 - INFO - __main__ - Step 118246: {'lr': 5.467691375832798e-05, 'samples': 22703232, 'steps': 118245, 'loss/train': 0.050718020647764206} 08/31/2021 10:35:50 - INFO - __main__ - Step 118247: {'lr': 5.467360151686815e-05, 'samples': 22703424, 'steps': 118246, 'loss/train': 0.11330533027648926} 08/31/2021 10:35:51 - INFO - __main__ - Step 118248: {'lr': 5.4670289363419365e-05, 'samples': 22703616, 'steps': 118247, 'loss/train': 1.296330213546753} 08/31/2021 10:35:51 - INFO - __main__ - Step 118249: {'lr': 5.466697729798314e-05, 'samples': 22703808, 'steps': 118248, 'loss/train': 0.31362706422805786} 08/31/2021 10:35:52 - INFO - __main__ - Step 118250: {'lr': 5.466366532056094e-05, 'samples': 22704000, 'steps': 118249, 'loss/train': 1.5633772611618042} 08/31/2021 10:35:53 - INFO - __main__ - Step 118251: {'lr': 5.4660353431154306e-05, 'samples': 22704192, 'steps': 118250, 'loss/train': 2.0561537742614746} 08/31/2021 10:35:53 - INFO - __main__ - Step 118252: {'lr': 5.4657041629764674e-05, 'samples': 22704384, 'steps': 118251, 'loss/train': 1.2564830780029297} 08/31/2021 10:35:54 - INFO - __main__ - Step 118253: {'lr': 5.465372991639367e-05, 'samples': 22704576, 'steps': 118252, 'loss/train': 0.609825849533081} 08/31/2021 10:35:54 - INFO - __main__ - Step 118254: {'lr': 5.4650418291042584e-05, 'samples': 22704768, 'steps': 118253, 'loss/train': 0.8692871332168579} 08/31/2021 10:35:56 - INFO - __main__ - Step 118255: {'lr': 5.4647106753713014e-05, 'samples': 22704960, 'steps': 118254, 'loss/train': 0.7468172907829285} 08/31/2021 10:35:57 - INFO - __main__ - Step 118256: {'lr': 5.464379530440644e-05, 'samples': 22705152, 'steps': 118255, 'loss/train': 1.131962776184082} 08/31/2021 10:35:57 - INFO - __main__ - Step 118257: {'lr': 5.4640483943124376e-05, 'samples': 22705344, 'steps': 118256, 'loss/train': 1.4030317068099976} 08/31/2021 10:35:58 - INFO - __main__ - Step 118258: {'lr': 5.463717266986826e-05, 'samples': 22705536, 'steps': 118257, 'loss/train': 5.730565071105957} 08/31/2021 10:35:58 - INFO - __main__ - Step 118259: {'lr': 5.4633861484639644e-05, 'samples': 22705728, 'steps': 118258, 'loss/train': 1.206334114074707} 08/31/2021 10:35:58 - INFO - __main__ - Step 118260: {'lr': 5.463055038744e-05, 'samples': 22705920, 'steps': 118259, 'loss/train': 0.8534749150276184} 08/31/2021 10:36:00 - INFO - __main__ - Step 118261: {'lr': 5.46272393782708e-05, 'samples': 22706112, 'steps': 118260, 'loss/train': 0.4520672559738159} 08/31/2021 10:36:00 - INFO - __main__ - Step 118262: {'lr': 5.4623928457133545e-05, 'samples': 22706304, 'steps': 118261, 'loss/train': 0.02408677153289318} 08/31/2021 10:36:01 - INFO - __main__ - Step 118263: {'lr': 5.4620617624029755e-05, 'samples': 22706496, 'steps': 118262, 'loss/train': 1.5093106031417847} 08/31/2021 10:36:01 - INFO - __main__ - Step 118264: {'lr': 5.4617306878960885e-05, 'samples': 22706688, 'steps': 118263, 'loss/train': 1.2081433534622192} 08/31/2021 10:36:01 - INFO - __main__ - Step 118265: {'lr': 5.4613996221928505e-05, 'samples': 22706880, 'steps': 118264, 'loss/train': 0.6320720911026001} 08/31/2021 10:36:03 - INFO - __main__ - Step 118266: {'lr': 5.461068565293401e-05, 'samples': 22707072, 'steps': 118265, 'loss/train': 0.7701571583747864} 08/31/2021 10:36:03 - INFO - __main__ - Step 118267: {'lr': 5.460737517197889e-05, 'samples': 22707264, 'steps': 118266, 'loss/train': 0.8557093143463135} 08/31/2021 10:36:04 - INFO - __main__ - Step 118268: {'lr': 5.460406477906468e-05, 'samples': 22707456, 'steps': 118267, 'loss/train': 1.0495431423187256} 08/31/2021 10:36:04 - INFO - __main__ - Step 118269: {'lr': 5.460075447419286e-05, 'samples': 22707648, 'steps': 118268, 'loss/train': 0.5333138704299927} 08/31/2021 10:36:04 - INFO - __main__ - Step 118270: {'lr': 5.459744425736493e-05, 'samples': 22707840, 'steps': 118269, 'loss/train': 0.36531373858451843} 08/31/2021 10:36:06 - INFO - __main__ - Step 118271: {'lr': 5.459413412858236e-05, 'samples': 22708032, 'steps': 118270, 'loss/train': 1.6718071699142456} 08/31/2021 10:36:07 - INFO - __main__ - Step 118272: {'lr': 5.4590824087846686e-05, 'samples': 22708224, 'steps': 118271, 'loss/train': 1.1861895322799683} 08/31/2021 10:36:07 - INFO - __main__ - Step 118273: {'lr': 5.4587514135159364e-05, 'samples': 22708416, 'steps': 118272, 'loss/train': 1.692818284034729} 08/31/2021 10:36:07 - INFO - __main__ - Step 118274: {'lr': 5.458420427052188e-05, 'samples': 22708608, 'steps': 118273, 'loss/train': 1.3647540807724} 08/31/2021 10:36:08 - INFO - __main__ - Step 118275: {'lr': 5.4580894493935745e-05, 'samples': 22708800, 'steps': 118274, 'loss/train': 0.9031026363372803} 08/31/2021 10:36:09 - INFO - __main__ - Step 118276: {'lr': 5.457758480540245e-05, 'samples': 22708992, 'steps': 118275, 'loss/train': 1.144037127494812} 08/31/2021 10:36:10 - INFO - __main__ - Step 118277: {'lr': 5.4574275204923476e-05, 'samples': 22709184, 'steps': 118276, 'loss/train': 1.3347563743591309} 08/31/2021 10:36:10 - INFO - __main__ - Step 118278: {'lr': 5.4570965692500305e-05, 'samples': 22709376, 'steps': 118277, 'loss/train': 1.399033546447754} 08/31/2021 10:36:10 - INFO - __main__ - Step 118279: {'lr': 5.456765626813451e-05, 'samples': 22709568, 'steps': 118278, 'loss/train': 1.166819453239441} 08/31/2021 10:36:11 - INFO - __main__ - Step 118280: {'lr': 5.4564346931827465e-05, 'samples': 22709760, 'steps': 118279, 'loss/train': 1.612980604171753} 08/31/2021 10:36:12 - INFO - __main__ - Step 118281: {'lr': 5.45610376835807e-05, 'samples': 22709952, 'steps': 118280, 'loss/train': 1.4322904348373413} 08/31/2021 10:36:13 - INFO - __main__ - Step 118282: {'lr': 5.4557728523395717e-05, 'samples': 22710144, 'steps': 118281, 'loss/train': 1.3820840120315552} 08/31/2021 10:36:13 - INFO - __main__ - Step 118283: {'lr': 5.4554419451274014e-05, 'samples': 22710336, 'steps': 118282, 'loss/train': 0.07908128201961517} 08/31/2021 10:36:13 - INFO - __main__ - Step 118284: {'lr': 5.455111046721706e-05, 'samples': 22710528, 'steps': 118283, 'loss/train': 0.49111783504486084} 08/31/2021 10:36:14 - INFO - __main__ - Step 118285: {'lr': 5.454780157122635e-05, 'samples': 22710720, 'steps': 118284, 'loss/train': 1.7765356302261353} 08/31/2021 10:36:16 - INFO - __main__ - Step 118286: {'lr': 5.454449276330339e-05, 'samples': 22710912, 'steps': 118285, 'loss/train': 1.72615647315979} 08/31/2021 10:36:16 - INFO - __main__ - Step 118287: {'lr': 5.454118404344968e-05, 'samples': 22711104, 'steps': 118286, 'loss/train': 0.039959218353033066} 08/31/2021 10:36:17 - INFO - __main__ - Step 118288: {'lr': 5.453787541166669e-05, 'samples': 22711296, 'steps': 118287, 'loss/train': 0.4801098108291626} 08/31/2021 10:36:17 - INFO - __main__ - Step 118289: {'lr': 5.4534566867955906e-05, 'samples': 22711488, 'steps': 118288, 'loss/train': 0.913901150226593} 08/31/2021 10:36:17 - INFO - __main__ - Step 118290: {'lr': 5.453125841231884e-05, 'samples': 22711680, 'steps': 118289, 'loss/train': 0.7502806782722473} 08/31/2021 10:36:18 - INFO - __main__ - Step 118291: {'lr': 5.4527950044757e-05, 'samples': 22711872, 'steps': 118290, 'loss/train': 0.25711074471473694} 08/31/2021 10:36:19 - INFO - __main__ - Step 118292: {'lr': 5.452464176527189e-05, 'samples': 22712064, 'steps': 118291, 'loss/train': 0.7121515870094299} 08/31/2021 10:36:20 - INFO - __main__ - Step 118293: {'lr': 5.4521333573864875e-05, 'samples': 22712256, 'steps': 118292, 'loss/train': 0.7071076035499573} 08/31/2021 10:36:20 - INFO - __main__ - Step 118294: {'lr': 5.451802547053755e-05, 'samples': 22712448, 'steps': 118293, 'loss/train': 1.4039441347122192} 08/31/2021 10:36:20 - INFO - __main__ - Step 118295: {'lr': 5.451471745529138e-05, 'samples': 22712640, 'steps': 118294, 'loss/train': 1.1881771087646484} 08/31/2021 10:36:21 - INFO - __main__ - Step 118296: {'lr': 5.451140952812789e-05, 'samples': 22712832, 'steps': 118295, 'loss/train': 1.3109521865844727} 08/31/2021 10:36:22 - INFO - __main__ - Step 118297: {'lr': 5.450810168904852e-05, 'samples': 22713024, 'steps': 118296, 'loss/train': 1.063869833946228} 08/31/2021 10:36:23 - INFO - __main__ - Step 118298: {'lr': 5.450479393805477e-05, 'samples': 22713216, 'steps': 118297, 'loss/train': 1.6487722396850586} 08/31/2021 10:36:23 - INFO - __main__ - Step 118299: {'lr': 5.4501486275148145e-05, 'samples': 22713408, 'steps': 118298, 'loss/train': 0.8098157048225403} 08/31/2021 10:36:24 - INFO - __main__ - Step 118300: {'lr': 5.449817870033013e-05, 'samples': 22713600, 'steps': 118299, 'loss/train': 1.3722891807556152} 08/31/2021 10:36:24 - INFO - __main__ - Step 118301: {'lr': 5.449487121360225e-05, 'samples': 22713792, 'steps': 118300, 'loss/train': 1.243573546409607} 08/31/2021 10:36:24 - INFO - __main__ - Step 118302: {'lr': 5.449156381496595e-05, 'samples': 22713984, 'steps': 118301, 'loss/train': 1.2612589597702026} 08/31/2021 10:36:26 - INFO - __main__ - Step 118303: {'lr': 5.448825650442274e-05, 'samples': 22714176, 'steps': 118302, 'loss/train': 1.308834195137024} 08/31/2021 10:36:26 - INFO - __main__ - Step 118304: {'lr': 5.448494928197409e-05, 'samples': 22714368, 'steps': 118303, 'loss/train': 1.113282322883606} 08/31/2021 10:36:27 - INFO - __main__ - Step 118305: {'lr': 5.448164214762158e-05, 'samples': 22714560, 'steps': 118304, 'loss/train': 2.0658154487609863} 08/31/2021 10:36:27 - INFO - __main__ - Step 118306: {'lr': 5.4478335101366546e-05, 'samples': 22714752, 'steps': 118305, 'loss/train': 1.6684904098510742} 08/31/2021 10:36:27 - INFO - __main__ - Step 118307: {'lr': 5.4475028143210563e-05, 'samples': 22714944, 'steps': 118306, 'loss/train': 2.389705181121826} 08/31/2021 10:36:29 - INFO - __main__ - Step 118308: {'lr': 5.447172127315514e-05, 'samples': 22715136, 'steps': 118307, 'loss/train': 0.9326981902122498} 08/31/2021 10:36:29 - INFO - __main__ - Step 118309: {'lr': 5.446841449120171e-05, 'samples': 22715328, 'steps': 118308, 'loss/train': 1.1985150575637817} 08/31/2021 10:36:30 - INFO - __main__ - Step 118310: {'lr': 5.446510779735181e-05, 'samples': 22715520, 'steps': 118309, 'loss/train': 1.0458729267120361} 08/31/2021 10:36:30 - INFO - __main__ - Step 118311: {'lr': 5.44618011916069e-05, 'samples': 22715712, 'steps': 118310, 'loss/train': 1.1482387781143188} 08/31/2021 10:36:30 - INFO - __main__ - Step 118312: {'lr': 5.445849467396849e-05, 'samples': 22715904, 'steps': 118311, 'loss/train': 1.549790382385254} 08/31/2021 10:36:33 - INFO - __main__ - Step 118313: {'lr': 5.445518824443807e-05, 'samples': 22716096, 'steps': 118312, 'loss/train': 0.02383619174361229} 08/31/2021 10:36:33 - INFO - __main__ - Step 118314: {'lr': 5.4451881903017144e-05, 'samples': 22716288, 'steps': 118313, 'loss/train': 1.114189863204956} 08/31/2021 10:36:34 - INFO - __main__ - Step 118315: {'lr': 5.4448575649707146e-05, 'samples': 22716480, 'steps': 118314, 'loss/train': 1.2487465143203735} 08/31/2021 10:36:34 - INFO - __main__ - Step 118316: {'lr': 5.444526948450965e-05, 'samples': 22716672, 'steps': 118315, 'loss/train': 1.3956352472305298} 08/31/2021 10:36:34 - INFO - __main__ - Step 118317: {'lr': 5.444196340742605e-05, 'samples': 22716864, 'steps': 118316, 'loss/train': 0.6962186098098755} 08/31/2021 10:36:35 - INFO - __main__ - Step 118318: {'lr': 5.443865741845791e-05, 'samples': 22717056, 'steps': 118317, 'loss/train': 0.7507421374320984} 08/31/2021 10:36:36 - INFO - __main__ - Step 118319: {'lr': 5.443535151760676e-05, 'samples': 22717248, 'steps': 118318, 'loss/train': 1.368494987487793} 08/31/2021 10:36:37 - INFO - __main__ - Step 118320: {'lr': 5.443204570487395e-05, 'samples': 22717440, 'steps': 118319, 'loss/train': 1.4317047595977783} 08/31/2021 10:36:37 - INFO - __main__ - Step 118321: {'lr': 5.4428739980261014e-05, 'samples': 22717632, 'steps': 118320, 'loss/train': 0.8321632742881775} 08/31/2021 10:36:37 - INFO - __main__ - Step 118322: {'lr': 5.442543434376951e-05, 'samples': 22717824, 'steps': 118321, 'loss/train': 1.1894776821136475} 08/31/2021 10:36:38 - INFO - __main__ - Step 118323: {'lr': 5.442212879540087e-05, 'samples': 22718016, 'steps': 118322, 'loss/train': 0.5175445675849915} 08/31/2021 10:36:39 - INFO - __main__ - Step 118324: {'lr': 5.44188233351566e-05, 'samples': 22718208, 'steps': 118323, 'loss/train': 0.6831591725349426} 08/31/2021 10:36:40 - INFO - __main__ - Step 118325: {'lr': 5.44155179630382e-05, 'samples': 22718400, 'steps': 118324, 'loss/train': 1.1891248226165771} 08/31/2021 10:36:40 - INFO - __main__ - Step 118326: {'lr': 5.4412212679047144e-05, 'samples': 22718592, 'steps': 118325, 'loss/train': 0.6281765103340149} 08/31/2021 10:36:40 - INFO - __main__ - Step 118327: {'lr': 5.440890748318494e-05, 'samples': 22718784, 'steps': 118326, 'loss/train': 0.9303512573242188} 08/31/2021 10:36:41 - INFO - __main__ - Step 118328: {'lr': 5.440560237545306e-05, 'samples': 22718976, 'steps': 118327, 'loss/train': 0.8381880521774292} 08/31/2021 10:36:42 - INFO - __main__ - Step 118329: {'lr': 5.440229735585297e-05, 'samples': 22719168, 'steps': 118328, 'loss/train': 0.22874215245246887} 08/31/2021 10:36:42 - INFO - __main__ - Step 118330: {'lr': 5.4398992424386204e-05, 'samples': 22719360, 'steps': 118329, 'loss/train': 0.3477804958820343} 08/31/2021 10:36:43 - INFO - __main__ - Step 118331: {'lr': 5.439568758105423e-05, 'samples': 22719552, 'steps': 118330, 'loss/train': 0.8102450370788574} 08/31/2021 10:36:43 - INFO - __main__ - Step 118332: {'lr': 5.439238282585862e-05, 'samples': 22719744, 'steps': 118331, 'loss/train': 0.884767472743988} 08/31/2021 10:36:44 - INFO - __main__ - Step 118333: {'lr': 5.438907815880073e-05, 'samples': 22719936, 'steps': 118332, 'loss/train': 1.3837628364562988} 08/31/2021 10:36:46 - INFO - __main__ - Step 118334: {'lr': 5.438577357988206e-05, 'samples': 22720128, 'steps': 118333, 'loss/train': 0.9951706528663635} 08/31/2021 10:36:47 - INFO - __main__ - Step 118335: {'lr': 5.4382469089104185e-05, 'samples': 22720320, 'steps': 118334, 'loss/train': 0.30982667207717896} 08/31/2021 10:36:47 - INFO - __main__ - Step 118336: {'lr': 5.437916468646853e-05, 'samples': 22720512, 'steps': 118335, 'loss/train': 1.5333054065704346} 08/31/2021 10:36:47 - INFO - __main__ - Step 118337: {'lr': 5.4375860371976585e-05, 'samples': 22720704, 'steps': 118336, 'loss/train': 0.7004801630973816} 08/31/2021 10:36:48 - INFO - __main__ - Step 118338: {'lr': 5.437255614562989e-05, 'samples': 22720896, 'steps': 118337, 'loss/train': 1.7225420475006104} 08/31/2021 10:36:48 - INFO - __main__ - Step 118339: {'lr': 5.43692520074299e-05, 'samples': 22721088, 'steps': 118338, 'loss/train': 1.1723343133926392} 08/31/2021 10:36:48 - INFO - __main__ - Step 118340: {'lr': 5.4365947957378094e-05, 'samples': 22721280, 'steps': 118339, 'loss/train': 1.2622706890106201} 08/31/2021 10:36:50 - INFO - __main__ - Step 118341: {'lr': 5.436264399547597e-05, 'samples': 22721472, 'steps': 118340, 'loss/train': 1.3690431118011475} 08/31/2021 10:36:50 - INFO - __main__ - Step 118342: {'lr': 5.435934012172503e-05, 'samples': 22721664, 'steps': 118341, 'loss/train': 1.1211780309677124} 08/31/2021 10:36:51 - INFO - __main__ - Step 118343: {'lr': 5.435603633612676e-05, 'samples': 22721856, 'steps': 118342, 'loss/train': 1.3182920217514038} 08/31/2021 10:36:51 - INFO - __main__ - Step 118344: {'lr': 5.435273263868262e-05, 'samples': 22722048, 'steps': 118343, 'loss/train': 1.250044345855713} 08/31/2021 10:36:51 - INFO - __main__ - Step 118345: {'lr': 5.4349429029394135e-05, 'samples': 22722240, 'steps': 118344, 'loss/train': 1.2506868839263916} 08/31/2021 10:36:52 - INFO - __main__ - Step 118346: {'lr': 5.4346125508262845e-05, 'samples': 22722432, 'steps': 118345, 'loss/train': 1.439322829246521} 08/31/2021 10:36:53 - INFO - __main__ - Step 118347: {'lr': 5.434282207529009e-05, 'samples': 22722624, 'steps': 118346, 'loss/train': 1.1354482173919678} 08/31/2021 10:36:54 - INFO - __main__ - Step 118348: {'lr': 5.433951873047746e-05, 'samples': 22722816, 'steps': 118347, 'loss/train': 1.2436212301254272} 08/31/2021 10:36:54 - INFO - __main__ - Step 118349: {'lr': 5.433621547382642e-05, 'samples': 22723008, 'steps': 118348, 'loss/train': 1.0938669443130493} 08/31/2021 10:36:54 - INFO - __main__ - Step 118350: {'lr': 5.433291230533843e-05, 'samples': 22723200, 'steps': 118349, 'loss/train': 1.2605311870574951} 08/31/2021 10:36:55 - INFO - __main__ - Step 118351: {'lr': 5.4329609225015035e-05, 'samples': 22723392, 'steps': 118350, 'loss/train': 0.4953587055206299} 08/31/2021 10:36:57 - INFO - __main__ - Step 118352: {'lr': 5.4326306232857724e-05, 'samples': 22723584, 'steps': 118351, 'loss/train': 1.4265661239624023} 08/31/2021 10:36:57 - INFO - __main__ - Step 118353: {'lr': 5.432300332886792e-05, 'samples': 22723776, 'steps': 118352, 'loss/train': 0.9060707092285156} 08/31/2021 10:36:58 - INFO - __main__ - Step 118354: {'lr': 5.431970051304716e-05, 'samples': 22723968, 'steps': 118353, 'loss/train': 1.2134639024734497} 08/31/2021 10:36:58 - INFO - __main__ - Step 118355: {'lr': 5.4316397785396934e-05, 'samples': 22724160, 'steps': 118354, 'loss/train': 1.2792332172393799} 08/31/2021 10:36:58 - INFO - __main__ - Step 118356: {'lr': 5.431309514591873e-05, 'samples': 22724352, 'steps': 118355, 'loss/train': 1.335189700126648} 08/31/2021 10:36:59 - INFO - __main__ - Step 118357: {'lr': 5.4309792594613996e-05, 'samples': 22724544, 'steps': 118356, 'loss/train': 1.9181630611419678} 08/31/2021 10:37:01 - INFO - __main__ - Step 118358: {'lr': 5.430649013148428e-05, 'samples': 22724736, 'steps': 118357, 'loss/train': 2.278244972229004} 08/31/2021 10:37:01 - INFO - __main__ - Step 118359: {'lr': 5.430318775653109e-05, 'samples': 22724928, 'steps': 118358, 'loss/train': 0.4360617399215698} 08/31/2021 10:37:01 - INFO - __main__ - Step 118360: {'lr': 5.429988546975581e-05, 'samples': 22725120, 'steps': 118359, 'loss/train': 0.32131072878837585} 08/31/2021 10:37:02 - INFO - __main__ - Step 118361: {'lr': 5.4296583271159964e-05, 'samples': 22725312, 'steps': 118360, 'loss/train': 0.07115638256072998} 08/31/2021 10:37:02 - INFO - __main__ - Step 118362: {'lr': 5.429328116074505e-05, 'samples': 22725504, 'steps': 118361, 'loss/train': 0.7488827109336853} 08/31/2021 10:37:04 - INFO - __main__ - Step 118363: {'lr': 5.428997913851258e-05, 'samples': 22725696, 'steps': 118362, 'loss/train': 1.2984355688095093} 08/31/2021 10:37:04 - INFO - __main__ - Step 118364: {'lr': 5.4286677204464037e-05, 'samples': 22725888, 'steps': 118363, 'loss/train': 0.8621777892112732} 08/31/2021 10:37:04 - INFO - __main__ - Step 118365: {'lr': 5.4283375358600866e-05, 'samples': 22726080, 'steps': 118364, 'loss/train': 0.027296414598822594} 08/31/2021 10:37:05 - INFO - __main__ - Step 118366: {'lr': 5.4280073600924626e-05, 'samples': 22726272, 'steps': 118365, 'loss/train': 0.6580742001533508} 08/31/2021 10:37:05 - INFO - __main__ - Step 118367: {'lr': 5.4276771931436734e-05, 'samples': 22726464, 'steps': 118366, 'loss/train': 0.7916277050971985} 08/31/2021 10:37:08 - INFO - __main__ - Step 118368: {'lr': 5.4273470350138713e-05, 'samples': 22726656, 'steps': 118367, 'loss/train': 1.110860824584961} 08/31/2021 10:37:08 - INFO - __main__ - Step 118369: {'lr': 5.427016885703206e-05, 'samples': 22726848, 'steps': 118368, 'loss/train': 0.8197199106216431} 08/31/2021 10:37:08 - INFO - __main__ - Step 118370: {'lr': 5.426686745211823e-05, 'samples': 22727040, 'steps': 118369, 'loss/train': 0.03418000787496567} 08/31/2021 10:37:09 - INFO - __main__ - Step 118371: {'lr': 5.426356613539873e-05, 'samples': 22727232, 'steps': 118370, 'loss/train': 0.8959790468215942} 08/31/2021 10:37:09 - INFO - __main__ - Step 118372: {'lr': 5.4260264906875054e-05, 'samples': 22727424, 'steps': 118371, 'loss/train': 1.2217069864273071} 08/31/2021 10:37:11 - INFO - __main__ - Step 118373: {'lr': 5.425696376654876e-05, 'samples': 22727616, 'steps': 118372, 'loss/train': 0.9883123636245728} 08/31/2021 10:37:11 - INFO - __main__ - Step 118374: {'lr': 5.425366271442117e-05, 'samples': 22727808, 'steps': 118373, 'loss/train': 1.1283661127090454} 08/31/2021 10:37:11 - INFO - __main__ - Step 118375: {'lr': 5.425036175049389e-05, 'samples': 22728000, 'steps': 118374, 'loss/train': 2.180525064468384} 08/31/2021 10:37:12 - INFO - __main__ - Step 118376: {'lr': 5.424706087476836e-05, 'samples': 22728192, 'steps': 118375, 'loss/train': 0.6183187365531921} 08/31/2021 10:37:12 - INFO - __main__ - Step 118377: {'lr': 5.4243760087246075e-05, 'samples': 22728384, 'steps': 118376, 'loss/train': 0.9281529784202576} 08/31/2021 10:37:12 - INFO - __main__ - Step 118378: {'lr': 5.424045938792852e-05, 'samples': 22728576, 'steps': 118377, 'loss/train': 0.9145042300224304} 08/31/2021 10:37:14 - INFO - __main__ - Step 118379: {'lr': 5.4237158776817204e-05, 'samples': 22728768, 'steps': 118378, 'loss/train': 1.6171241998672485} 08/31/2021 10:37:15 - INFO - __main__ - Step 118380: {'lr': 5.423385825391361e-05, 'samples': 22728960, 'steps': 118379, 'loss/train': 3.7875542640686035} 08/31/2021 10:37:15 - INFO - __main__ - Step 118381: {'lr': 5.4230557819219236e-05, 'samples': 22729152, 'steps': 118380, 'loss/train': 0.05286836624145508} 08/31/2021 10:37:15 - INFO - __main__ - Step 118382: {'lr': 5.422725747273552e-05, 'samples': 22729344, 'steps': 118381, 'loss/train': 1.7433204650878906} 08/31/2021 10:37:16 - INFO - __main__ - Step 118383: {'lr': 5.4223957214463996e-05, 'samples': 22729536, 'steps': 118382, 'loss/train': 1.5422613620758057} 08/31/2021 10:37:17 - INFO - __main__ - Step 118384: {'lr': 5.4220657044406126e-05, 'samples': 22729728, 'steps': 118383, 'loss/train': 1.0213735103607178} 08/31/2021 10:37:18 - INFO - __main__ - Step 118385: {'lr': 5.4217356962563417e-05, 'samples': 22729920, 'steps': 118384, 'loss/train': 0.47010481357574463} 08/31/2021 10:37:18 - INFO - __main__ - Step 118386: {'lr': 5.4214056968937414e-05, 'samples': 22730112, 'steps': 118385, 'loss/train': 1.8162803649902344} 08/31/2021 10:37:18 - INFO - __main__ - Step 118387: {'lr': 5.421075706352946e-05, 'samples': 22730304, 'steps': 118386, 'loss/train': 0.027708617970347404} 08/31/2021 10:37:19 - INFO - __main__ - Step 118388: {'lr': 5.420745724634113e-05, 'samples': 22730496, 'steps': 118387, 'loss/train': 0.7993382215499878} 08/31/2021 10:37:20 - INFO - __main__ - Step 118389: {'lr': 5.42041575173739e-05, 'samples': 22730688, 'steps': 118388, 'loss/train': 0.7555814981460571} 08/31/2021 10:37:21 - INFO - __main__ - Step 118390: {'lr': 5.4200857876629234e-05, 'samples': 22730880, 'steps': 118389, 'loss/train': 1.508428692817688} 08/31/2021 10:37:21 - INFO - __main__ - Step 118391: {'lr': 5.4197558324108635e-05, 'samples': 22731072, 'steps': 118390, 'loss/train': 1.0310282707214355} 08/31/2021 10:37:21 - INFO - __main__ - Step 118392: {'lr': 5.419425885981363e-05, 'samples': 22731264, 'steps': 118391, 'loss/train': 0.786564826965332} 08/31/2021 10:37:22 - INFO - __main__ - Step 118393: {'lr': 5.419095948374564e-05, 'samples': 22731456, 'steps': 118392, 'loss/train': 0.9577265381813049} 08/31/2021 10:37:23 - INFO - __main__ - Step 118394: {'lr': 5.4187660195906205e-05, 'samples': 22731648, 'steps': 118393, 'loss/train': 1.091254472732544} 08/31/2021 10:37:24 - INFO - __main__ - Step 118395: {'lr': 5.418436099629678e-05, 'samples': 22731840, 'steps': 118394, 'loss/train': 0.17904695868492126} 08/31/2021 10:37:24 - INFO - __main__ - Step 118396: {'lr': 5.418106188491886e-05, 'samples': 22732032, 'steps': 118395, 'loss/train': 0.5491243004798889} 08/31/2021 10:37:24 - INFO - __main__ - Step 118397: {'lr': 5.417776286177392e-05, 'samples': 22732224, 'steps': 118396, 'loss/train': 1.2296438217163086} 08/31/2021 10:37:25 - INFO - __main__ - Step 118398: {'lr': 5.4174463926863485e-05, 'samples': 22732416, 'steps': 118397, 'loss/train': 1.4856916666030884} 08/31/2021 10:37:26 - INFO - __main__ - Step 118399: {'lr': 5.417116508018899e-05, 'samples': 22732608, 'steps': 118398, 'loss/train': 1.179840326309204} 08/31/2021 10:37:27 - INFO - __main__ - Step 118400: {'lr': 5.4167866321752025e-05, 'samples': 22732800, 'steps': 118399, 'loss/train': 1.059745192527771} 08/31/2021 10:37:27 - INFO - __main__ - Step 118401: {'lr': 5.416456765155392e-05, 'samples': 22732992, 'steps': 118400, 'loss/train': 1.1582869291305542} 08/31/2021 10:37:27 - INFO - __main__ - Step 118402: {'lr': 5.416126906959626e-05, 'samples': 22733184, 'steps': 118401, 'loss/train': 1.2915407419204712} 08/31/2021 10:37:28 - INFO - __main__ - Step 118403: {'lr': 5.4157970575880486e-05, 'samples': 22733376, 'steps': 118402, 'loss/train': 1.0598118305206299} 08/31/2021 10:37:29 - INFO - __main__ - Step 118404: {'lr': 5.415467217040812e-05, 'samples': 22733568, 'steps': 118403, 'loss/train': 1.3257471323013306} 08/31/2021 10:37:30 - INFO - __main__ - Step 118405: {'lr': 5.415137385318064e-05, 'samples': 22733760, 'steps': 118404, 'loss/train': 1.4487248659133911} 08/31/2021 10:37:30 - INFO - __main__ - Step 118406: {'lr': 5.414807562419951e-05, 'samples': 22733952, 'steps': 118405, 'loss/train': 0.9527826905250549} 08/31/2021 10:37:30 - INFO - __main__ - Step 118407: {'lr': 5.414477748346625e-05, 'samples': 22734144, 'steps': 118406, 'loss/train': 1.494275689125061} 08/31/2021 10:37:31 - INFO - __main__ - Step 118408: {'lr': 5.414147943098233e-05, 'samples': 22734336, 'steps': 118407, 'loss/train': 1.3525636196136475} 08/31/2021 10:37:32 - INFO - __main__ - Step 118409: {'lr': 5.4138181466749256e-05, 'samples': 22734528, 'steps': 118408, 'loss/train': 0.4404441714286804} 08/31/2021 10:37:33 - INFO - __main__ - Step 118410: {'lr': 5.413488359076846e-05, 'samples': 22734720, 'steps': 118409, 'loss/train': 0.9670013189315796} 08/31/2021 10:37:33 - INFO - __main__ - Step 118411: {'lr': 5.413158580304148e-05, 'samples': 22734912, 'steps': 118410, 'loss/train': 1.001349925994873} 08/31/2021 10:37:34 - INFO - __main__ - Step 118412: {'lr': 5.412828810356979e-05, 'samples': 22735104, 'steps': 118411, 'loss/train': 1.2605900764465332} 08/31/2021 10:37:34 - INFO - __main__ - Step 118413: {'lr': 5.412499049235495e-05, 'samples': 22735296, 'steps': 118412, 'loss/train': 1.3116925954818726} 08/31/2021 10:37:34 - INFO - __main__ - Step 118414: {'lr': 5.412169296939826e-05, 'samples': 22735488, 'steps': 118413, 'loss/train': 0.6977448463439941} 08/31/2021 10:37:36 - INFO - __main__ - Step 118415: {'lr': 5.411839553470135e-05, 'samples': 22735680, 'steps': 118414, 'loss/train': 1.7697384357452393} 08/31/2021 10:37:36 - INFO - __main__ - Step 118416: {'lr': 5.411509818826566e-05, 'samples': 22735872, 'steps': 118415, 'loss/train': 1.1897151470184326} 08/31/2021 10:37:37 - INFO - __main__ - Step 118417: {'lr': 5.411180093009266e-05, 'samples': 22736064, 'steps': 118416, 'loss/train': 1.2825746536254883} 08/31/2021 10:37:37 - INFO - __main__ - Step 118418: {'lr': 5.4108503760183895e-05, 'samples': 22736256, 'steps': 118417, 'loss/train': 1.2290464639663696} 08/31/2021 10:37:37 - INFO - __main__ - Step 118419: {'lr': 5.410520667854077e-05, 'samples': 22736448, 'steps': 118418, 'loss/train': 0.8956744074821472} 08/31/2021 10:37:39 - INFO - __main__ - Step 118420: {'lr': 5.4101909685164845e-05, 'samples': 22736640, 'steps': 118419, 'loss/train': 0.727719247341156} 08/31/2021 10:37:40 - INFO - __main__ - Step 118421: {'lr': 5.4098612780057595e-05, 'samples': 22736832, 'steps': 118420, 'loss/train': 0.4994078278541565} 08/31/2021 10:37:40 - INFO - __main__ - Step 118422: {'lr': 5.4095315963220455e-05, 'samples': 22737024, 'steps': 118421, 'loss/train': 1.822741985321045} 08/31/2021 10:37:41 - INFO - __main__ - Step 118423: {'lr': 5.4092019234654955e-05, 'samples': 22737216, 'steps': 118422, 'loss/train': 2.012773036956787} 08/31/2021 10:37:41 - INFO - __main__ - Step 118424: {'lr': 5.408872259436257e-05, 'samples': 22737408, 'steps': 118423, 'loss/train': 1.5231574773788452} 08/31/2021 10:37:41 - INFO - __main__ - Step 118425: {'lr': 5.408542604234479e-05, 'samples': 22737600, 'steps': 118424, 'loss/train': 0.5856048464775085} 08/31/2021 10:37:43 - INFO - __main__ - Step 118426: {'lr': 5.4082129578603146e-05, 'samples': 22737792, 'steps': 118425, 'loss/train': 0.8794877529144287} 08/31/2021 10:37:44 - INFO - __main__ - Step 118427: {'lr': 5.4078833203139e-05, 'samples': 22737984, 'steps': 118426, 'loss/train': 1.16171395778656} 08/31/2021 10:37:44 - INFO - __main__ - Step 118428: {'lr': 5.407553691595393e-05, 'samples': 22738176, 'steps': 118427, 'loss/train': 0.04709223285317421} 08/31/2021 10:37:44 - INFO - __main__ - Step 118429: {'lr': 5.407224071704939e-05, 'samples': 22738368, 'steps': 118428, 'loss/train': 0.015618310309946537} 08/31/2021 10:37:45 - INFO - __main__ - Step 118430: {'lr': 5.406894460642686e-05, 'samples': 22738560, 'steps': 118429, 'loss/train': 0.7033543586730957} 08/31/2021 10:37:45 - INFO - __main__ - Step 118431: {'lr': 5.4065648584087856e-05, 'samples': 22738752, 'steps': 118430, 'loss/train': 0.8542249202728271} 08/31/2021 10:37:47 - INFO - __main__ - Step 118432: {'lr': 5.406235265003384e-05, 'samples': 22738944, 'steps': 118431, 'loss/train': 0.9035437703132629} 08/31/2021 10:37:47 - INFO - __main__ - Step 118433: {'lr': 5.405905680426631e-05, 'samples': 22739136, 'steps': 118432, 'loss/train': 0.8334085941314697} 08/31/2021 10:37:47 - INFO - __main__ - Step 118434: {'lr': 5.405576104678675e-05, 'samples': 22739328, 'steps': 118433, 'loss/train': 1.3822991847991943} 08/31/2021 10:37:48 - INFO - __main__ - Step 118435: {'lr': 5.4052465377596645e-05, 'samples': 22739520, 'steps': 118434, 'loss/train': 1.117966651916504} 08/31/2021 10:37:48 - INFO - __main__ - Step 118436: {'lr': 5.4049169796697465e-05, 'samples': 22739712, 'steps': 118435, 'loss/train': 1.2530096769332886} 08/31/2021 10:37:50 - INFO - __main__ - Step 118437: {'lr': 5.404587430409069e-05, 'samples': 22739904, 'steps': 118436, 'loss/train': 0.9897636771202087} 08/31/2021 10:37:50 - INFO - __main__ - Step 118438: {'lr': 5.404257889977785e-05, 'samples': 22740096, 'steps': 118437, 'loss/train': 1.6748822927474976} 08/31/2021 10:37:51 - INFO - __main__ - Step 118439: {'lr': 5.40392835837604e-05, 'samples': 22740288, 'steps': 118438, 'loss/train': 1.2440311908721924} 08/31/2021 10:37:51 - INFO - __main__ - Step 118440: {'lr': 5.4035988356039874e-05, 'samples': 22740480, 'steps': 118439, 'loss/train': 0.5877489447593689} 08/31/2021 10:37:51 - INFO - __main__ - Step 118441: {'lr': 5.4032693216617634e-05, 'samples': 22740672, 'steps': 118440, 'loss/train': 1.7859182357788086} 08/31/2021 10:37:53 - INFO - __main__ - Step 118442: {'lr': 5.4029398165495265e-05, 'samples': 22740864, 'steps': 118441, 'loss/train': 1.0607678890228271} 08/31/2021 10:37:53 - INFO - __main__ - Step 118443: {'lr': 5.4026103202674204e-05, 'samples': 22741056, 'steps': 118442, 'loss/train': 1.094409704208374} 08/31/2021 10:37:54 - INFO - __main__ - Step 118444: {'lr': 5.4022808328155955e-05, 'samples': 22741248, 'steps': 118443, 'loss/train': 1.7044286727905273} 08/31/2021 10:37:54 - INFO - __main__ - Step 118445: {'lr': 5.401951354194201e-05, 'samples': 22741440, 'steps': 118444, 'loss/train': 1.0672988891601562} 08/31/2021 10:37:54 - INFO - __main__ - Step 118446: {'lr': 5.401621884403385e-05, 'samples': 22741632, 'steps': 118445, 'loss/train': 1.0338053703308105} 08/31/2021 10:37:56 - INFO - __main__ - Step 118447: {'lr': 5.401292423443296e-05, 'samples': 22741824, 'steps': 118446, 'loss/train': 1.0475088357925415} 08/31/2021 10:37:57 - INFO - __main__ - Step 118448: {'lr': 5.400962971314083e-05, 'samples': 22742016, 'steps': 118447, 'loss/train': 0.833182692527771} 08/31/2021 10:37:57 - INFO - __main__ - Step 118449: {'lr': 5.400633528015891e-05, 'samples': 22742208, 'steps': 118448, 'loss/train': 1.1062898635864258} 08/31/2021 10:37:58 - INFO - __main__ - Step 118450: {'lr': 5.400304093548875e-05, 'samples': 22742400, 'steps': 118449, 'loss/train': 1.1821900606155396} 08/31/2021 10:37:58 - INFO - __main__ - Step 118451: {'lr': 5.399974667913177e-05, 'samples': 22742592, 'steps': 118450, 'loss/train': 0.9853436350822449} 08/31/2021 10:37:58 - INFO - __main__ - Step 118452: {'lr': 5.3996452511089474e-05, 'samples': 22742784, 'steps': 118451, 'loss/train': 1.404232382774353} 08/31/2021 10:38:00 - INFO - __main__ - Step 118453: {'lr': 5.399315843136343e-05, 'samples': 22742976, 'steps': 118452, 'loss/train': 1.300519585609436} 08/31/2021 10:38:00 - INFO - __main__ - Step 118454: {'lr': 5.398986443995496e-05, 'samples': 22743168, 'steps': 118453, 'loss/train': 0.046676263213157654} 08/31/2021 10:38:01 - INFO - __main__ - Step 118455: {'lr': 5.398657053686565e-05, 'samples': 22743360, 'steps': 118454, 'loss/train': 0.7839745879173279} 08/31/2021 10:38:01 - INFO - __main__ - Step 118456: {'lr': 5.3983276722096966e-05, 'samples': 22743552, 'steps': 118455, 'loss/train': 1.0653796195983887} 08/31/2021 10:38:01 - INFO - __main__ - Step 118457: {'lr': 5.3979982995650406e-05, 'samples': 22743744, 'steps': 118456, 'loss/train': 0.9646568298339844} 08/31/2021 10:38:03 - INFO - __main__ - Step 118458: {'lr': 5.397668935752742e-05, 'samples': 22743936, 'steps': 118457, 'loss/train': 1.4446232318878174} 08/31/2021 10:38:04 - INFO - __main__ - Step 118459: {'lr': 5.39733958077295e-05, 'samples': 22744128, 'steps': 118458, 'loss/train': 0.6229982972145081} 08/31/2021 10:38:04 - INFO - __main__ - Step 118460: {'lr': 5.3970102346258184e-05, 'samples': 22744320, 'steps': 118459, 'loss/train': 1.0410135984420776} 08/31/2021 10:38:04 - INFO - __main__ - Step 118461: {'lr': 5.3966808973114874e-05, 'samples': 22744512, 'steps': 118460, 'loss/train': 0.6100482940673828} 08/31/2021 10:38:05 - INFO - __main__ - Step 118462: {'lr': 5.396351568830113e-05, 'samples': 22744704, 'steps': 118461, 'loss/train': 1.0851802825927734} 08/31/2021 10:38:06 - INFO - __main__ - Step 118463: {'lr': 5.396022249181837e-05, 'samples': 22744896, 'steps': 118462, 'loss/train': 1.121080994606018} 08/31/2021 10:38:07 - INFO - __main__ - Step 118464: {'lr': 5.395692938366814e-05, 'samples': 22745088, 'steps': 118463, 'loss/train': 1.0784422159194946} 08/31/2021 10:38:07 - INFO - __main__ - Step 118465: {'lr': 5.395363636385187e-05, 'samples': 22745280, 'steps': 118464, 'loss/train': 1.1239391565322876} 08/31/2021 10:38:07 - INFO - __main__ - Step 118466: {'lr': 5.3950343432371066e-05, 'samples': 22745472, 'steps': 118465, 'loss/train': 1.0342555046081543} 08/31/2021 10:38:08 - INFO - __main__ - Step 118467: {'lr': 5.39470505892273e-05, 'samples': 22745664, 'steps': 118466, 'loss/train': 0.9304607510566711} 08/31/2021 10:38:08 - INFO - __main__ - Step 118468: {'lr': 5.394375783442187e-05, 'samples': 22745856, 'steps': 118467, 'loss/train': 0.23458923399448395} 08/31/2021 10:38:10 - INFO - __main__ - Step 118469: {'lr': 5.394046516795637e-05, 'samples': 22746048, 'steps': 118468, 'loss/train': 1.5472567081451416} 08/31/2021 10:38:10 - INFO - __main__ - Step 118470: {'lr': 5.393717258983227e-05, 'samples': 22746240, 'steps': 118469, 'loss/train': 0.24253414571285248} 08/31/2021 10:38:10 - INFO - __main__ - Step 118471: {'lr': 5.393388010005107e-05, 'samples': 22746432, 'steps': 118470, 'loss/train': 0.04064488410949707} 08/31/2021 10:38:11 - INFO - __main__ - Step 118472: {'lr': 5.393058769861423e-05, 'samples': 22746624, 'steps': 118471, 'loss/train': 1.3346014022827148} 08/31/2021 10:38:11 - INFO - __main__ - Step 118473: {'lr': 5.392729538552324e-05, 'samples': 22746816, 'steps': 118472, 'loss/train': 0.08848053216934204} 08/31/2021 10:38:13 - INFO - __main__ - Step 118474: {'lr': 5.392400316077958e-05, 'samples': 22747008, 'steps': 118473, 'loss/train': 1.1151801347732544} 08/31/2021 10:38:14 - INFO - __main__ - Step 118475: {'lr': 5.392071102438473e-05, 'samples': 22747200, 'steps': 118474, 'loss/train': 0.849988579750061} 08/31/2021 10:38:14 - INFO - __main__ - Step 118476: {'lr': 5.39174189763402e-05, 'samples': 22747392, 'steps': 118475, 'loss/train': 1.2834585905075073} 08/31/2021 10:38:15 - INFO - __main__ - Step 118477: {'lr': 5.391412701664744e-05, 'samples': 22747584, 'steps': 118476, 'loss/train': 0.9648764729499817} 08/31/2021 10:38:15 - INFO - __main__ - Step 118478: {'lr': 5.3910835145308036e-05, 'samples': 22747776, 'steps': 118477, 'loss/train': 1.0521787405014038} 08/31/2021 10:38:16 - INFO - __main__ - Step 118479: {'lr': 5.390754336232331e-05, 'samples': 22747968, 'steps': 118478, 'loss/train': 0.8003724217414856} 08/31/2021 10:38:17 - INFO - __main__ - Step 118480: {'lr': 5.3904251667694806e-05, 'samples': 22748160, 'steps': 118479, 'loss/train': 0.6141926646232605} 08/31/2021 10:38:17 - INFO - __main__ - Step 118481: {'lr': 5.390096006142403e-05, 'samples': 22748352, 'steps': 118480, 'loss/train': 1.560167908668518} 08/31/2021 10:38:18 - INFO - __main__ - Step 118482: {'lr': 5.389766854351247e-05, 'samples': 22748544, 'steps': 118481, 'loss/train': 1.2204691171646118} 08/31/2021 10:38:18 - INFO - __main__ - Step 118483: {'lr': 5.3894377113961555e-05, 'samples': 22748736, 'steps': 118482, 'loss/train': 1.1817995309829712} 08/31/2021 10:38:19 - INFO - __main__ - Step 118484: {'lr': 5.389108577277285e-05, 'samples': 22748928, 'steps': 118483, 'loss/train': 1.8680709600448608} 08/31/2021 10:38:20 - INFO - __main__ - Step 118485: {'lr': 5.388779451994777e-05, 'samples': 22749120, 'steps': 118484, 'loss/train': 1.1869962215423584} 08/31/2021 10:38:20 - INFO - __main__ - Step 118486: {'lr': 5.388450335548783e-05, 'samples': 22749312, 'steps': 118485, 'loss/train': 1.0668389797210693} 08/31/2021 10:38:20 - INFO - __main__ - Step 118487: {'lr': 5.3881212279394524e-05, 'samples': 22749504, 'steps': 118486, 'loss/train': 1.0301001071929932} 08/31/2021 10:38:21 - INFO - __main__ - Step 118488: {'lr': 5.3877921291669296e-05, 'samples': 22749696, 'steps': 118487, 'loss/train': 1.2817717790603638} 08/31/2021 10:38:23 - INFO - __main__ - Step 118489: {'lr': 5.3874630392313714e-05, 'samples': 22749888, 'steps': 118488, 'loss/train': 1.4353785514831543} 08/31/2021 10:38:23 - INFO - __main__ - Step 118490: {'lr': 5.387133958132914e-05, 'samples': 22750080, 'steps': 118489, 'loss/train': 1.2076616287231445} 08/31/2021 10:38:24 - INFO - __main__ - Step 118491: {'lr': 5.38680488587171e-05, 'samples': 22750272, 'steps': 118490, 'loss/train': 1.1576781272888184} 08/31/2021 10:38:24 - INFO - __main__ - Step 118492: {'lr': 5.386475822447912e-05, 'samples': 22750464, 'steps': 118491, 'loss/train': 0.038342658430337906} 08/31/2021 10:38:24 - INFO - __main__ - Step 118493: {'lr': 5.386146767861663e-05, 'samples': 22750656, 'steps': 118492, 'loss/train': 1.0071308612823486} 08/31/2021 10:38:25 - INFO - __main__ - Step 118494: {'lr': 5.385817722113115e-05, 'samples': 22750848, 'steps': 118493, 'loss/train': 0.9119722843170166} 08/31/2021 10:38:25 - INFO - __main__ - Step 118495: {'lr': 5.385488685202414e-05, 'samples': 22751040, 'steps': 118494, 'loss/train': 1.1449352502822876} 08/31/2021 10:38:27 - INFO - __main__ - Step 118496: {'lr': 5.3851596571297065e-05, 'samples': 22751232, 'steps': 118495, 'loss/train': 0.8657873272895813} 08/31/2021 10:38:27 - INFO - __main__ - Step 118497: {'lr': 5.384830637895147e-05, 'samples': 22751424, 'steps': 118496, 'loss/train': 1.7869112491607666} 08/31/2021 10:38:27 - INFO - __main__ - Step 118498: {'lr': 5.384501627498881e-05, 'samples': 22751616, 'steps': 118497, 'loss/train': 1.1807278394699097} 08/31/2021 10:38:28 - INFO - __main__ - Step 118499: {'lr': 5.384172625941053e-05, 'samples': 22751808, 'steps': 118498, 'loss/train': 1.4652518033981323} 08/31/2021 10:38:28 - INFO - __main__ - Step 118500: {'lr': 5.3838436332218215e-05, 'samples': 22752000, 'steps': 118499, 'loss/train': 1.1101047992706299} 08/31/2021 10:38:30 - INFO - __main__ - Step 118501: {'lr': 5.38351464934132e-05, 'samples': 22752192, 'steps': 118500, 'loss/train': 1.174391746520996} 08/31/2021 10:38:30 - INFO - __main__ - Step 118502: {'lr': 5.383185674299706e-05, 'samples': 22752384, 'steps': 118501, 'loss/train': 1.0872132778167725} 08/31/2021 10:38:31 - INFO - __main__ - Step 118503: {'lr': 5.382856708097125e-05, 'samples': 22752576, 'steps': 118502, 'loss/train': 1.1401773691177368} 08/31/2021 10:38:31 - INFO - __main__ - Step 118504: {'lr': 5.382527750733726e-05, 'samples': 22752768, 'steps': 118503, 'loss/train': 1.2982505559921265} 08/31/2021 10:38:31 - INFO - __main__ - Step 118505: {'lr': 5.382198802209659e-05, 'samples': 22752960, 'steps': 118504, 'loss/train': 1.555309772491455} 08/31/2021 10:38:33 - INFO - __main__ - Step 118506: {'lr': 5.381869862525069e-05, 'samples': 22753152, 'steps': 118505, 'loss/train': 1.9432876110076904} 08/31/2021 10:38:34 - INFO - __main__ - Step 118507: {'lr': 5.381540931680104e-05, 'samples': 22753344, 'steps': 118506, 'loss/train': 1.5229153633117676} 08/31/2021 10:38:34 - INFO - __main__ - Step 118508: {'lr': 5.3812120096749154e-05, 'samples': 22753536, 'steps': 118507, 'loss/train': 0.9409512281417847} 08/31/2021 10:38:35 - INFO - __main__ - Step 118509: {'lr': 5.380883096509651e-05, 'samples': 22753728, 'steps': 118508, 'loss/train': 0.8726117610931396} 08/31/2021 10:38:35 - INFO - __main__ - Step 118510: {'lr': 5.380554192184456e-05, 'samples': 22753920, 'steps': 118509, 'loss/train': 0.8789927959442139} 08/31/2021 10:38:35 - INFO - __main__ - Step 118511: {'lr': 5.38022529669949e-05, 'samples': 22754112, 'steps': 118510, 'loss/train': 0.026177408173680305} 08/31/2021 10:38:37 - INFO - __main__ - Step 118512: {'lr': 5.379896410054883e-05, 'samples': 22754304, 'steps': 118511, 'loss/train': 0.01707984320819378} 08/31/2021 10:38:37 - INFO - __main__ - Step 118513: {'lr': 5.37956753225079e-05, 'samples': 22754496, 'steps': 118512, 'loss/train': 1.1395959854125977} 08/31/2021 10:38:38 - INFO - __main__ - Step 118514: {'lr': 5.379238663287364e-05, 'samples': 22754688, 'steps': 118513, 'loss/train': 0.8187639713287354} 08/31/2021 10:38:38 - INFO - __main__ - Step 118515: {'lr': 5.37890980316475e-05, 'samples': 22754880, 'steps': 118514, 'loss/train': 1.374556064605713} 08/31/2021 10:38:38 - INFO - __main__ - Step 118516: {'lr': 5.378580951883097e-05, 'samples': 22755072, 'steps': 118515, 'loss/train': 1.1252800226211548} 08/31/2021 10:38:40 - INFO - __main__ - Step 118517: {'lr': 5.37825210944255e-05, 'samples': 22755264, 'steps': 118516, 'loss/train': 0.8355501890182495} 08/31/2021 10:38:41 - INFO - __main__ - Step 118518: {'lr': 5.3779232758432606e-05, 'samples': 22755456, 'steps': 118517, 'loss/train': 1.426883339881897} 08/31/2021 10:38:41 - INFO - __main__ - Step 118519: {'lr': 5.377594451085377e-05, 'samples': 22755648, 'steps': 118518, 'loss/train': 0.7374204993247986} 08/31/2021 10:38:41 - INFO - __main__ - Step 118520: {'lr': 5.3772656351690486e-05, 'samples': 22755840, 'steps': 118519, 'loss/train': 0.789129376411438} 08/31/2021 10:38:42 - INFO - __main__ - Step 118521: {'lr': 5.37693682809442e-05, 'samples': 22756032, 'steps': 118520, 'loss/train': 1.2894222736358643} 08/31/2021 10:38:42 - INFO - __main__ - Step 118522: {'lr': 5.3766080298616457e-05, 'samples': 22756224, 'steps': 118521, 'loss/train': 0.05490865930914879} 08/31/2021 10:38:44 - INFO - __main__ - Step 118523: {'lr': 5.376279240470863e-05, 'samples': 22756416, 'steps': 118522, 'loss/train': 1.1007437705993652} 08/31/2021 10:38:44 - INFO - __main__ - Step 118524: {'lr': 5.375950459922227e-05, 'samples': 22756608, 'steps': 118523, 'loss/train': 1.063645839691162} 08/31/2021 10:38:45 - INFO - __main__ - Step 118525: {'lr': 5.3756216882158844e-05, 'samples': 22756800, 'steps': 118524, 'loss/train': 0.9546517133712769} 08/31/2021 10:38:45 - INFO - __main__ - Step 118526: {'lr': 5.375292925351985e-05, 'samples': 22756992, 'steps': 118525, 'loss/train': 0.014801605604588985} 08/31/2021 10:38:46 - INFO - __main__ - Step 118527: {'lr': 5.3749641713306764e-05, 'samples': 22757184, 'steps': 118526, 'loss/train': 1.6017816066741943} 08/31/2021 10:38:46 - INFO - __main__ - Step 118528: {'lr': 5.374635426152102e-05, 'samples': 22757376, 'steps': 118527, 'loss/train': 0.841279149055481} 08/31/2021 10:38:47 - INFO - __main__ - Step 118529: {'lr': 5.374306689816419e-05, 'samples': 22757568, 'steps': 118528, 'loss/train': 1.4125101566314697} 08/31/2021 10:38:48 - INFO - __main__ - Step 118530: {'lr': 5.3739779623237674e-05, 'samples': 22757760, 'steps': 118529, 'loss/train': 1.088335633277893} 08/31/2021 10:38:48 - INFO - __main__ - Step 118531: {'lr': 5.3736492436743e-05, 'samples': 22757952, 'steps': 118530, 'loss/train': 1.5197864770889282} 08/31/2021 10:38:49 - INFO - __main__ - Step 118532: {'lr': 5.373320533868162e-05, 'samples': 22758144, 'steps': 118531, 'loss/train': 0.9813081622123718} 08/31/2021 10:38:49 - INFO - __main__ - Step 118533: {'lr': 5.3729918329055025e-05, 'samples': 22758336, 'steps': 118532, 'loss/train': 2.2677347660064697} 08/31/2021 10:38:51 - INFO - __main__ - Step 118534: {'lr': 5.3726631407864795e-05, 'samples': 22758528, 'steps': 118533, 'loss/train': 1.7438753843307495} 08/31/2021 10:38:52 - INFO - __main__ - Step 118535: {'lr': 5.372334457511222e-05, 'samples': 22758720, 'steps': 118534, 'loss/train': 1.0166242122650146} 08/31/2021 10:38:52 - INFO - __main__ - Step 118536: {'lr': 5.372005783079889e-05, 'samples': 22758912, 'steps': 118535, 'loss/train': 0.11160185188055038} 08/31/2021 10:38:52 - INFO - __main__ - Step 118537: {'lr': 5.3716771174926264e-05, 'samples': 22759104, 'steps': 118536, 'loss/train': 1.4495723247528076} 08/31/2021 10:38:53 - INFO - __main__ - Step 118538: {'lr': 5.371348460749584e-05, 'samples': 22759296, 'steps': 118537, 'loss/train': 2.307251214981079} 08/31/2021 10:38:54 - INFO - __main__ - Step 118539: {'lr': 5.371019812850911e-05, 'samples': 22759488, 'steps': 118538, 'loss/train': 1.6035364866256714} 08/31/2021 10:38:55 - INFO - __main__ - Step 118540: {'lr': 5.370691173796752e-05, 'samples': 22759680, 'steps': 118539, 'loss/train': 0.8542937636375427} 08/31/2021 10:38:55 - INFO - __main__ - Step 118541: {'lr': 5.3703625435872564e-05, 'samples': 22759872, 'steps': 118540, 'loss/train': 1.303573489189148} 08/31/2021 10:38:55 - INFO - __main__ - Step 118542: {'lr': 5.3700339222225726e-05, 'samples': 22760064, 'steps': 118541, 'loss/train': 1.1526050567626953} 08/31/2021 10:38:56 - INFO - __main__ - Step 118543: {'lr': 5.369705309702847e-05, 'samples': 22760256, 'steps': 118542, 'loss/train': 0.5448923110961914} 08/31/2021 10:38:57 - INFO - __main__ - Step 118544: {'lr': 5.369376706028231e-05, 'samples': 22760448, 'steps': 118543, 'loss/train': 0.9590392708778381} 08/31/2021 10:38:58 - INFO - __main__ - Step 118545: {'lr': 5.369048111198871e-05, 'samples': 22760640, 'steps': 118544, 'loss/train': 1.2155579328536987} 08/31/2021 10:38:58 - INFO - __main__ - Step 118546: {'lr': 5.3687195252149155e-05, 'samples': 22760832, 'steps': 118545, 'loss/train': 0.11848846077919006} 08/31/2021 10:38:58 - INFO - __main__ - Step 118547: {'lr': 5.368390948076518e-05, 'samples': 22761024, 'steps': 118546, 'loss/train': 1.0610260963439941} 08/31/2021 10:38:59 - INFO - __main__ - Step 118548: {'lr': 5.368062379783814e-05, 'samples': 22761216, 'steps': 118547, 'loss/train': 0.46606627106666565} 08/31/2021 10:39:00 - INFO - __main__ - Step 118549: {'lr': 5.367733820336956e-05, 'samples': 22761408, 'steps': 118548, 'loss/train': 1.3928263187408447} 08/31/2021 10:39:01 - INFO - __main__ - Step 118550: {'lr': 5.3674052697360976e-05, 'samples': 22761600, 'steps': 118549, 'loss/train': 0.6925396919250488} 08/31/2021 10:39:01 - INFO - __main__ - Step 118551: {'lr': 5.367076727981382e-05, 'samples': 22761792, 'steps': 118550, 'loss/train': 0.40068238973617554} 08/31/2021 10:39:01 - INFO - __main__ - Step 118552: {'lr': 5.3667481950729596e-05, 'samples': 22761984, 'steps': 118551, 'loss/train': 1.3307157754898071} 08/31/2021 10:39:02 - INFO - __main__ - Step 118553: {'lr': 5.366419671010975e-05, 'samples': 22762176, 'steps': 118552, 'loss/train': 0.8921946287155151} 08/31/2021 10:39:03 - INFO - __main__ - Step 118554: {'lr': 5.36609115579558e-05, 'samples': 22762368, 'steps': 118553, 'loss/train': 0.7210792303085327} 08/31/2021 10:39:04 - INFO - __main__ - Step 118555: {'lr': 5.365762649426922e-05, 'samples': 22762560, 'steps': 118554, 'loss/train': 0.7881488800048828} 08/31/2021 10:39:04 - INFO - __main__ - Step 118556: {'lr': 5.3654341519051495e-05, 'samples': 22762752, 'steps': 118555, 'loss/train': 1.0631904602050781} 08/31/2021 10:39:04 - INFO - __main__ - Step 118557: {'lr': 5.3651056632304076e-05, 'samples': 22762944, 'steps': 118556, 'loss/train': 1.7788323163986206} 08/31/2021 10:39:05 - INFO - __main__ - Step 118558: {'lr': 5.364777183402847e-05, 'samples': 22763136, 'steps': 118557, 'loss/train': 0.08087444305419922} 08/31/2021 10:39:05 - INFO - __main__ - Step 118559: {'lr': 5.3644487124226146e-05, 'samples': 22763328, 'steps': 118558, 'loss/train': 0.5369004607200623} 08/31/2021 10:39:06 - INFO - __main__ - Step 118560: {'lr': 5.364120250289858e-05, 'samples': 22763520, 'steps': 118559, 'loss/train': 1.4059529304504395} 08/31/2021 10:39:07 - INFO - __main__ - Step 118561: {'lr': 5.363791797004733e-05, 'samples': 22763712, 'steps': 118560, 'loss/train': 0.2653767764568329} 08/31/2021 10:39:07 - INFO - __main__ - Step 118562: {'lr': 5.363463352567374e-05, 'samples': 22763904, 'steps': 118561, 'loss/train': 0.8536075949668884} 08/31/2021 10:39:08 - INFO - __main__ - Step 118563: {'lr': 5.363134916977933e-05, 'samples': 22764096, 'steps': 118562, 'loss/train': 1.541101098060608} 08/31/2021 10:39:08 - INFO - __main__ - Step 118564: {'lr': 5.362806490236563e-05, 'samples': 22764288, 'steps': 118563, 'loss/train': 1.3034427165985107} 08/31/2021 10:39:10 - INFO - __main__ - Step 118565: {'lr': 5.3624780723434103e-05, 'samples': 22764480, 'steps': 118564, 'loss/train': 1.3328560590744019} 08/31/2021 10:39:10 - INFO - __main__ - Step 118566: {'lr': 5.362149663298618e-05, 'samples': 22764672, 'steps': 118565, 'loss/train': 1.2734270095825195} 08/31/2021 10:39:10 - INFO - __main__ - Step 118567: {'lr': 5.3618212631023426e-05, 'samples': 22764864, 'steps': 118566, 'loss/train': 0.9004440307617188} 08/31/2021 10:39:11 - INFO - __main__ - Step 118568: {'lr': 5.361492871754725e-05, 'samples': 22765056, 'steps': 118567, 'loss/train': 1.0152442455291748} 08/31/2021 10:39:11 - INFO - __main__ - Step 118569: {'lr': 5.361164489255915e-05, 'samples': 22765248, 'steps': 118568, 'loss/train': 0.6008554697036743} 08/31/2021 10:39:13 - INFO - __main__ - Step 118570: {'lr': 5.360836115606063e-05, 'samples': 22765440, 'steps': 118569, 'loss/train': 0.7227192521095276} 08/31/2021 10:39:13 - INFO - __main__ - Step 118571: {'lr': 5.360507750805313e-05, 'samples': 22765632, 'steps': 118570, 'loss/train': 0.40496596693992615} 08/31/2021 10:39:14 - INFO - __main__ - Step 118572: {'lr': 5.360179394853818e-05, 'samples': 22765824, 'steps': 118571, 'loss/train': 1.1640095710754395} 08/31/2021 10:39:14 - INFO - __main__ - Step 118573: {'lr': 5.359851047751721e-05, 'samples': 22766016, 'steps': 118572, 'loss/train': 0.8829401135444641} 08/31/2021 10:39:14 - INFO - __main__ - Step 118574: {'lr': 5.359522709499179e-05, 'samples': 22766208, 'steps': 118573, 'loss/train': 0.9891401529312134} 08/31/2021 10:39:16 - INFO - __main__ - Step 118575: {'lr': 5.3591943800963274e-05, 'samples': 22766400, 'steps': 118574, 'loss/train': 0.9278905391693115} 08/31/2021 10:39:16 - INFO - __main__ - Step 118576: {'lr': 5.358866059543319e-05, 'samples': 22766592, 'steps': 118575, 'loss/train': 0.26939016580581665} 08/31/2021 10:39:17 - INFO - __main__ - Step 118577: {'lr': 5.358537747840303e-05, 'samples': 22766784, 'steps': 118576, 'loss/train': 1.2573353052139282} 08/31/2021 10:39:17 - INFO - __main__ - Step 118578: {'lr': 5.358209444987425e-05, 'samples': 22766976, 'steps': 118577, 'loss/train': 1.5435776710510254} 08/31/2021 10:39:17 - INFO - __main__ - Step 118579: {'lr': 5.357881150984836e-05, 'samples': 22767168, 'steps': 118578, 'loss/train': 0.2686954736709595} 08/31/2021 10:39:18 - INFO - __main__ - Step 118580: {'lr': 5.3575528658326846e-05, 'samples': 22767360, 'steps': 118579, 'loss/train': 0.6006817817687988} 08/31/2021 10:39:19 - INFO - __main__ - Step 118581: {'lr': 5.3572245895311154e-05, 'samples': 22767552, 'steps': 118580, 'loss/train': 1.320425271987915} 08/31/2021 10:39:20 - INFO - __main__ - Step 118582: {'lr': 5.356896322080276e-05, 'samples': 22767744, 'steps': 118581, 'loss/train': 0.8050440549850464} 08/31/2021 10:39:20 - INFO - __main__ - Step 118583: {'lr': 5.356568063480316e-05, 'samples': 22767936, 'steps': 118582, 'loss/train': 1.0546952486038208} 08/31/2021 10:39:20 - INFO - __main__ - Step 118584: {'lr': 5.356239813731387e-05, 'samples': 22768128, 'steps': 118583, 'loss/train': 1.3881301879882812} 08/31/2021 10:39:21 - INFO - __main__ - Step 118585: {'lr': 5.35591157283363e-05, 'samples': 22768320, 'steps': 118584, 'loss/train': 0.8010603189468384} 08/31/2021 10:39:23 - INFO - __main__ - Step 118586: {'lr': 5.3555833407871955e-05, 'samples': 22768512, 'steps': 118585, 'loss/train': 1.2451120615005493} 08/31/2021 10:39:23 - INFO - __main__ - Step 118587: {'lr': 5.355255117592234e-05, 'samples': 22768704, 'steps': 118586, 'loss/train': 0.3604816794395447} 08/31/2021 10:39:24 - INFO - __main__ - Step 118588: {'lr': 5.3549269032488966e-05, 'samples': 22768896, 'steps': 118587, 'loss/train': 0.5947778224945068} 08/31/2021 10:39:24 - INFO - __main__ - Step 118589: {'lr': 5.354598697757321e-05, 'samples': 22769088, 'steps': 118588, 'loss/train': 1.1097984313964844} 08/31/2021 10:39:24 - INFO - __main__ - Step 118590: {'lr': 5.3542705011176585e-05, 'samples': 22769280, 'steps': 118589, 'loss/train': 1.4243096113204956} 08/31/2021 10:39:26 - INFO - __main__ - Step 118591: {'lr': 5.35394231333006e-05, 'samples': 22769472, 'steps': 118590, 'loss/train': 1.2845131158828735} 08/31/2021 10:39:26 - INFO - __main__ - Step 118592: {'lr': 5.3536141343946716e-05, 'samples': 22769664, 'steps': 118591, 'loss/train': 0.36026084423065186} 08/31/2021 10:39:27 - INFO - __main__ - Step 118593: {'lr': 5.353285964311641e-05, 'samples': 22769856, 'steps': 118592, 'loss/train': 0.325443834066391} 08/31/2021 10:39:27 - INFO - __main__ - Step 118594: {'lr': 5.3529578030811186e-05, 'samples': 22770048, 'steps': 118593, 'loss/train': 1.044464111328125} 08/31/2021 10:39:27 - INFO - __main__ - Step 118595: {'lr': 5.352629650703247e-05, 'samples': 22770240, 'steps': 118594, 'loss/train': 1.7547435760498047} 08/31/2021 10:39:29 - INFO - __main__ - Step 118596: {'lr': 5.3523015071781783e-05, 'samples': 22770432, 'steps': 118595, 'loss/train': 0.9678295254707336} 08/31/2021 10:39:30 - INFO - __main__ - Step 118597: {'lr': 5.351973372506061e-05, 'samples': 22770624, 'steps': 118596, 'loss/train': 0.8555346727371216} 08/31/2021 10:39:30 - INFO - __main__ - Step 118598: {'lr': 5.3516452466870395e-05, 'samples': 22770816, 'steps': 118597, 'loss/train': 0.8823679685592651} 08/31/2021 10:39:30 - INFO - __main__ - Step 118599: {'lr': 5.351317129721264e-05, 'samples': 22771008, 'steps': 118598, 'loss/train': 1.36591374874115} 08/31/2021 10:39:31 - INFO - __main__ - Step 118600: {'lr': 5.350989021608882e-05, 'samples': 22771200, 'steps': 118599, 'loss/train': 0.045779839158058167} 08/31/2021 10:39:32 - INFO - __main__ - Step 118601: {'lr': 5.3506609223500477e-05, 'samples': 22771392, 'steps': 118600, 'loss/train': 1.309541940689087} 08/31/2021 10:39:33 - INFO - __main__ - Step 118602: {'lr': 5.350332831944896e-05, 'samples': 22771584, 'steps': 118601, 'loss/train': 0.02606862224638462} 08/31/2021 10:39:33 - INFO - __main__ - Step 118603: {'lr': 5.350004750393581e-05, 'samples': 22771776, 'steps': 118602, 'loss/train': 0.3762337565422058} 08/31/2021 10:39:33 - INFO - __main__ - Step 118604: {'lr': 5.34967667769625e-05, 'samples': 22771968, 'steps': 118603, 'loss/train': 0.942919909954071} 08/31/2021 10:39:34 - INFO - __main__ - Step 118605: {'lr': 5.34934861385305e-05, 'samples': 22772160, 'steps': 118604, 'loss/train': 1.4008467197418213} 08/31/2021 10:39:35 - INFO - __main__ - Step 118606: {'lr': 5.3490205588641344e-05, 'samples': 22772352, 'steps': 118605, 'loss/train': 1.6839573383331299} 08/31/2021 10:39:36 - INFO - __main__ - Step 118607: {'lr': 5.348692512729644e-05, 'samples': 22772544, 'steps': 118606, 'loss/train': 0.026433704420924187} 08/31/2021 10:39:36 - INFO - __main__ - Step 118608: {'lr': 5.34836447544973e-05, 'samples': 22772736, 'steps': 118607, 'loss/train': 0.8664581179618835} 08/31/2021 10:39:37 - INFO - __main__ - Step 118609: {'lr': 5.34803644702454e-05, 'samples': 22772928, 'steps': 118608, 'loss/train': 1.3640168905258179} 08/31/2021 10:39:37 - INFO - __main__ - Step 118610: {'lr': 5.34770842745422e-05, 'samples': 22773120, 'steps': 118609, 'loss/train': 1.1869451999664307} 08/31/2021 10:39:39 - INFO - __main__ - Step 118611: {'lr': 5.347380416738923e-05, 'samples': 22773312, 'steps': 118610, 'loss/train': 0.7547465562820435} 08/31/2021 10:39:39 - INFO - __main__ - Step 118612: {'lr': 5.347052414878789e-05, 'samples': 22773504, 'steps': 118611, 'loss/train': 1.2350527048110962} 08/31/2021 10:39:40 - INFO - __main__ - Step 118613: {'lr': 5.346724421873972e-05, 'samples': 22773696, 'steps': 118612, 'loss/train': 0.8689135909080505} 08/31/2021 10:39:40 - INFO - __main__ - Step 118614: {'lr': 5.3463964377246184e-05, 'samples': 22773888, 'steps': 118613, 'loss/train': 1.0435006618499756} 08/31/2021 10:39:40 - INFO - __main__ - Step 118615: {'lr': 5.346068462430881e-05, 'samples': 22774080, 'steps': 118614, 'loss/train': 0.33329156041145325} 08/31/2021 10:39:42 - INFO - __main__ - Step 118616: {'lr': 5.345740495992896e-05, 'samples': 22774272, 'steps': 118615, 'loss/train': 1.2540682554244995} 08/31/2021 10:39:42 - INFO - __main__ - Step 118617: {'lr': 5.345412538410815e-05, 'samples': 22774464, 'steps': 118616, 'loss/train': 0.9340906739234924} 08/31/2021 10:39:42 - INFO - __main__ - Step 118618: {'lr': 5.34508458968479e-05, 'samples': 22774656, 'steps': 118617, 'loss/train': 0.0443425327539444} 08/31/2021 10:39:43 - INFO - __main__ - Step 118619: {'lr': 5.3447566498149665e-05, 'samples': 22774848, 'steps': 118618, 'loss/train': 1.534006118774414} 08/31/2021 10:39:43 - INFO - __main__ - Step 118620: {'lr': 5.344428718801489e-05, 'samples': 22775040, 'steps': 118619, 'loss/train': 1.2953217029571533} 08/31/2021 10:39:45 - INFO - __main__ - Step 118621: {'lr': 5.344100796644513e-05, 'samples': 22775232, 'steps': 118620, 'loss/train': 1.3853780031204224} 08/31/2021 10:39:45 - INFO - __main__ - Step 118622: {'lr': 5.3437728833441804e-05, 'samples': 22775424, 'steps': 118621, 'loss/train': 1.132826328277588} 08/31/2021 10:39:45 - INFO - __main__ - Step 118623: {'lr': 5.3434449789006385e-05, 'samples': 22775616, 'steps': 118622, 'loss/train': 0.8990270495414734} 08/31/2021 10:39:46 - INFO - __main__ - Step 118624: {'lr': 5.343117083314039e-05, 'samples': 22775808, 'steps': 118623, 'loss/train': 1.7469496726989746} 08/31/2021 10:39:46 - INFO - __main__ - Step 118625: {'lr': 5.342789196584527e-05, 'samples': 22776000, 'steps': 118624, 'loss/train': 1.4684189558029175} 08/31/2021 10:39:48 - INFO - __main__ - Step 118626: {'lr': 5.342461318712252e-05, 'samples': 22776192, 'steps': 118625, 'loss/train': 1.3006852865219116} 08/31/2021 10:39:48 - INFO - __main__ - Step 118627: {'lr': 5.342133449697359e-05, 'samples': 22776384, 'steps': 118626, 'loss/train': 1.019675374031067} 08/31/2021 10:39:49 - INFO - __main__ - Step 118628: {'lr': 5.341805589540005e-05, 'samples': 22776576, 'steps': 118627, 'loss/train': 0.9276618957519531} 08/31/2021 10:39:49 - INFO - __main__ - Step 118629: {'lr': 5.3414777382403215e-05, 'samples': 22776768, 'steps': 118628, 'loss/train': 1.63874351978302} 08/31/2021 10:39:49 - INFO - __main__ - Step 118630: {'lr': 5.3411498957984664e-05, 'samples': 22776960, 'steps': 118629, 'loss/train': 0.9126415848731995} 08/31/2021 10:39:51 - INFO - __main__ - Step 118631: {'lr': 5.340822062214587e-05, 'samples': 22777152, 'steps': 118630, 'loss/train': 0.6729822754859924} 08/31/2021 10:39:52 - INFO - __main__ - Step 118632: {'lr': 5.3404942374888274e-05, 'samples': 22777344, 'steps': 118631, 'loss/train': 1.1787233352661133} 08/31/2021 10:39:52 - INFO - __main__ - Step 118633: {'lr': 5.3401664216213395e-05, 'samples': 22777536, 'steps': 118632, 'loss/train': 0.6905509233474731} 08/31/2021 10:39:52 - INFO - __main__ - Step 118634: {'lr': 5.339838614612269e-05, 'samples': 22777728, 'steps': 118633, 'loss/train': 0.5229308605194092} 08/31/2021 10:39:53 - INFO - __main__ - Step 118635: {'lr': 5.339510816461762e-05, 'samples': 22777920, 'steps': 118634, 'loss/train': 0.8553256988525391} 08/31/2021 10:39:55 - INFO - __main__ - Step 118636: {'lr': 5.339183027169972e-05, 'samples': 22778112, 'steps': 118635, 'loss/train': 1.3179004192352295} 08/31/2021 10:39:55 - INFO - __main__ - Step 118637: {'lr': 5.33885524673704e-05, 'samples': 22778304, 'steps': 118636, 'loss/train': 0.9463741779327393} 08/31/2021 10:39:56 - INFO - __main__ - Step 118638: {'lr': 5.338527475163116e-05, 'samples': 22778496, 'steps': 118637, 'loss/train': 0.6448104977607727} 08/31/2021 10:39:56 - INFO - __main__ - Step 118639: {'lr': 5.3381997124483496e-05, 'samples': 22778688, 'steps': 118638, 'loss/train': 1.0144474506378174} 08/31/2021 10:39:56 - INFO - __main__ - Step 118640: {'lr': 5.337871958592885e-05, 'samples': 22778880, 'steps': 118639, 'loss/train': 0.3861692249774933} 08/31/2021 10:39:57 - INFO - __main__ - Step 118641: {'lr': 5.337544213596873e-05, 'samples': 22779072, 'steps': 118640, 'loss/train': 1.107538104057312} 08/31/2021 10:39:58 - INFO - __main__ - Step 118642: {'lr': 5.337216477460469e-05, 'samples': 22779264, 'steps': 118641, 'loss/train': 0.6723395586013794} 08/31/2021 10:39:59 - INFO - __main__ - Step 118643: {'lr': 5.336888750183802e-05, 'samples': 22779456, 'steps': 118642, 'loss/train': 0.6477328538894653} 08/31/2021 10:39:59 - INFO - __main__ - Step 118644: {'lr': 5.3365610317670285e-05, 'samples': 22779648, 'steps': 118643, 'loss/train': 0.7303022742271423} 08/31/2021 10:39:59 - INFO - __main__ - Step 118645: {'lr': 5.3362333222103016e-05, 'samples': 22779840, 'steps': 118644, 'loss/train': 0.23366844654083252} 08/31/2021 10:40:00 - INFO - __main__ - Step 118646: {'lr': 5.335905621513762e-05, 'samples': 22780032, 'steps': 118645, 'loss/train': 0.970007061958313} 08/31/2021 10:40:01 - INFO - __main__ - Step 118647: {'lr': 5.3355779296775595e-05, 'samples': 22780224, 'steps': 118646, 'loss/train': 1.2005869150161743} 08/31/2021 10:40:02 - INFO - __main__ - Step 118648: {'lr': 5.335250246701842e-05, 'samples': 22780416, 'steps': 118647, 'loss/train': 1.2746719121932983} 08/31/2021 10:40:02 - INFO - __main__ - Step 118649: {'lr': 5.334922572586759e-05, 'samples': 22780608, 'steps': 118648, 'loss/train': 1.308975100517273} 08/31/2021 10:40:03 - INFO - __main__ - Step 118650: {'lr': 5.3345949073324547e-05, 'samples': 22780800, 'steps': 118649, 'loss/train': 0.8521318435668945} 08/31/2021 10:40:03 - INFO - __main__ - Step 118651: {'lr': 5.334267250939079e-05, 'samples': 22780992, 'steps': 118650, 'loss/train': 1.3691695928573608} 08/31/2021 10:40:05 - INFO - __main__ - Step 118652: {'lr': 5.333939603406779e-05, 'samples': 22781184, 'steps': 118651, 'loss/train': 0.8988990783691406} 08/31/2021 10:40:05 - INFO - __main__ - Step 118653: {'lr': 5.3336119647357044e-05, 'samples': 22781376, 'steps': 118652, 'loss/train': 0.6216596961021423} 08/31/2021 10:40:05 - INFO - __main__ - Step 118654: {'lr': 5.333284334925997e-05, 'samples': 22781568, 'steps': 118653, 'loss/train': 1.2943540811538696} 08/31/2021 10:40:06 - INFO - __main__ - Step 118655: {'lr': 5.3329567139778185e-05, 'samples': 22781760, 'steps': 118654, 'loss/train': 0.03417659178376198} 08/31/2021 10:40:06 - INFO - __main__ - Step 118656: {'lr': 5.332629101891298e-05, 'samples': 22781952, 'steps': 118655, 'loss/train': 0.796733558177948} 08/31/2021 10:40:08 - INFO - __main__ - Step 118657: {'lr': 5.332301498666592e-05, 'samples': 22782144, 'steps': 118656, 'loss/train': 0.9640956521034241} 08/31/2021 10:40:09 - INFO - __main__ - Step 118658: {'lr': 5.3319739043038466e-05, 'samples': 22782336, 'steps': 118657, 'loss/train': 0.9944925308227539} 08/31/2021 10:40:09 - INFO - __main__ - Step 118659: {'lr': 5.33164631880321e-05, 'samples': 22782528, 'steps': 118658, 'loss/train': 1.0523920059204102} 08/31/2021 10:40:10 - INFO - __main__ - Step 118660: {'lr': 5.331318742164831e-05, 'samples': 22782720, 'steps': 118659, 'loss/train': 0.7515106797218323} 08/31/2021 10:40:10 - INFO - __main__ - Step 118661: {'lr': 5.330991174388855e-05, 'samples': 22782912, 'steps': 118660, 'loss/train': 0.8501220941543579} 08/31/2021 10:40:10 - INFO - __main__ - Step 118662: {'lr': 5.330663615475431e-05, 'samples': 22783104, 'steps': 118661, 'loss/train': 0.7669242024421692} 08/31/2021 10:40:12 - INFO - __main__ - Step 118663: {'lr': 5.330336065424707e-05, 'samples': 22783296, 'steps': 118662, 'loss/train': 1.203856110572815} 08/31/2021 10:40:12 - INFO - __main__ - Step 118664: {'lr': 5.330008524236832e-05, 'samples': 22783488, 'steps': 118663, 'loss/train': 1.3973758220672607} 08/31/2021 10:40:13 - INFO - __main__ - Step 118665: {'lr': 5.3296809919119475e-05, 'samples': 22783680, 'steps': 118664, 'loss/train': 1.6729087829589844} 08/31/2021 10:40:13 - INFO - __main__ - Step 118666: {'lr': 5.329353468450207e-05, 'samples': 22783872, 'steps': 118665, 'loss/train': 0.944913387298584} 08/31/2021 10:40:13 - INFO - __main__ - Step 118667: {'lr': 5.329025953851757e-05, 'samples': 22784064, 'steps': 118666, 'loss/train': 1.3524101972579956} 08/31/2021 10:40:15 - INFO - __main__ - Step 118668: {'lr': 5.328698448116753e-05, 'samples': 22784256, 'steps': 118667, 'loss/train': 1.2778242826461792} 08/31/2021 10:40:15 - INFO - __main__ - Step 118669: {'lr': 5.328370951245323e-05, 'samples': 22784448, 'steps': 118668, 'loss/train': 1.0810526609420776} 08/31/2021 10:40:16 - INFO - __main__ - Step 118670: {'lr': 5.328043463237628e-05, 'samples': 22784640, 'steps': 118669, 'loss/train': 0.9811256527900696} 08/31/2021 10:40:16 - INFO - __main__ - Step 118671: {'lr': 5.3277159840938145e-05, 'samples': 22784832, 'steps': 118670, 'loss/train': 0.39513498544692993} 08/31/2021 10:40:16 - INFO - __main__ - Step 118672: {'lr': 5.327388513814024e-05, 'samples': 22785024, 'steps': 118671, 'loss/train': 1.7226101160049438} 08/31/2021 10:40:17 - INFO - __main__ - Step 118673: {'lr': 5.3270610523984134e-05, 'samples': 22785216, 'steps': 118672, 'loss/train': 1.1121647357940674} 08/31/2021 10:40:18 - INFO - __main__ - Step 118674: {'lr': 5.326733599847122e-05, 'samples': 22785408, 'steps': 118673, 'loss/train': 1.3959954977035522} 08/31/2021 10:40:19 - INFO - __main__ - Step 118675: {'lr': 5.326406156160304e-05, 'samples': 22785600, 'steps': 118674, 'loss/train': 1.5011426210403442} 08/31/2021 10:40:19 - INFO - __main__ - Step 118676: {'lr': 5.326078721338101e-05, 'samples': 22785792, 'steps': 118675, 'loss/train': 1.0174452066421509} 08/31/2021 10:40:19 - INFO - __main__ - Step 118677: {'lr': 5.325751295380665e-05, 'samples': 22785984, 'steps': 118676, 'loss/train': 1.8084053993225098} 08/31/2021 10:40:20 - INFO - __main__ - Step 118678: {'lr': 5.325423878288141e-05, 'samples': 22786176, 'steps': 118677, 'loss/train': 1.4841747283935547} 08/31/2021 10:40:21 - INFO - __main__ - Step 118679: {'lr': 5.325096470060678e-05, 'samples': 22786368, 'steps': 118678, 'loss/train': 1.3559880256652832} 08/31/2021 10:40:22 - INFO - __main__ - Step 118680: {'lr': 5.3247690706984236e-05, 'samples': 22786560, 'steps': 118679, 'loss/train': 0.8895630836486816} 08/31/2021 10:40:22 - INFO - __main__ - Step 118681: {'lr': 5.3244416802015225e-05, 'samples': 22786752, 'steps': 118680, 'loss/train': 0.06739442050457001} 08/31/2021 10:40:23 - INFO - __main__ - Step 118682: {'lr': 5.3241142985701317e-05, 'samples': 22786944, 'steps': 118681, 'loss/train': 0.8858994841575623} 08/31/2021 10:40:23 - INFO - __main__ - Step 118683: {'lr': 5.323786925804386e-05, 'samples': 22787136, 'steps': 118682, 'loss/train': 0.702203094959259} 08/31/2021 10:40:25 - INFO - __main__ - Step 118684: {'lr': 5.3234595619044366e-05, 'samples': 22787328, 'steps': 118683, 'loss/train': 1.45281982421875} 08/31/2021 10:40:25 - INFO - __main__ - Step 118685: {'lr': 5.3231322068704347e-05, 'samples': 22787520, 'steps': 118684, 'loss/train': 0.765138566493988} 08/31/2021 10:40:26 - INFO - __main__ - Step 118686: {'lr': 5.3228048607025264e-05, 'samples': 22787712, 'steps': 118685, 'loss/train': 1.0077999830245972} 08/31/2021 10:40:26 - INFO - __main__ - Step 118687: {'lr': 5.322477523400856e-05, 'samples': 22787904, 'steps': 118686, 'loss/train': 1.5943362712860107} 08/31/2021 10:40:26 - INFO - __main__ - Step 118688: {'lr': 5.322150194965575e-05, 'samples': 22788096, 'steps': 118687, 'loss/train': 1.0814467668533325} 08/31/2021 10:40:29 - INFO - __main__ - Step 118689: {'lr': 5.321822875396829e-05, 'samples': 22788288, 'steps': 118688, 'loss/train': 0.09399695694446564} 08/31/2021 10:40:29 - INFO - __main__ - Step 118690: {'lr': 5.3214955646947646e-05, 'samples': 22788480, 'steps': 118689, 'loss/train': 1.0722016096115112} 08/31/2021 10:40:29 - INFO - __main__ - Step 118691: {'lr': 5.321168262859533e-05, 'samples': 22788672, 'steps': 118690, 'loss/train': 0.793657660484314} 08/31/2021 10:40:30 - INFO - __main__ - Step 118692: {'lr': 5.320840969891277e-05, 'samples': 22788864, 'steps': 118691, 'loss/train': 1.1974787712097168} 08/31/2021 10:40:30 - INFO - __main__ - Step 118693: {'lr': 5.3205136857901486e-05, 'samples': 22789056, 'steps': 118692, 'loss/train': 0.2776089906692505} 08/31/2021 10:40:31 - INFO - __main__ - Step 118694: {'lr': 5.3201864105562936e-05, 'samples': 22789248, 'steps': 118693, 'loss/train': 0.25404462218284607} 08/31/2021 10:40:31 - INFO - __main__ - Step 118695: {'lr': 5.319859144189862e-05, 'samples': 22789440, 'steps': 118694, 'loss/train': 0.3308974504470825} 08/31/2021 10:40:33 - INFO - __main__ - Step 118696: {'lr': 5.3195318866909956e-05, 'samples': 22789632, 'steps': 118695, 'loss/train': 0.48336920142173767} 08/31/2021 10:40:33 - INFO - __main__ - Step 118697: {'lr': 5.3192046380598406e-05, 'samples': 22789824, 'steps': 118696, 'loss/train': 1.7833991050720215} 08/31/2021 10:40:34 - INFO - __main__ - Step 118698: {'lr': 5.318877398296551e-05, 'samples': 22790016, 'steps': 118697, 'loss/train': 1.7358710765838623} 08/31/2021 10:40:34 - INFO - __main__ - Step 118699: {'lr': 5.31855016740127e-05, 'samples': 22790208, 'steps': 118698, 'loss/train': 0.72632896900177} 08/31/2021 10:40:34 - INFO - __main__ - Step 118700: {'lr': 5.318222945374149e-05, 'samples': 22790400, 'steps': 118699, 'loss/train': 1.3716095685958862} 08/31/2021 10:40:36 - INFO - __main__ - Step 118701: {'lr': 5.3178957322153304e-05, 'samples': 22790592, 'steps': 118700, 'loss/train': 0.8006311655044556} 08/31/2021 10:40:36 - INFO - __main__ - Step 118702: {'lr': 5.317568527924965e-05, 'samples': 22790784, 'steps': 118701, 'loss/train': 1.2356491088867188} 08/31/2021 10:40:37 - INFO - __main__ - Step 118703: {'lr': 5.3172413325032e-05, 'samples': 22790976, 'steps': 118702, 'loss/train': 0.04699321836233139} 08/31/2021 10:40:37 - INFO - __main__ - Step 118704: {'lr': 5.316914145950183e-05, 'samples': 22791168, 'steps': 118703, 'loss/train': 1.4705442190170288} 08/31/2021 10:40:37 - INFO - __main__ - Step 118705: {'lr': 5.31658696826606e-05, 'samples': 22791360, 'steps': 118704, 'loss/train': 1.1047860383987427} 08/31/2021 10:40:39 - INFO - __main__ - Step 118706: {'lr': 5.316259799450979e-05, 'samples': 22791552, 'steps': 118705, 'loss/train': 1.2866822481155396} 08/31/2021 10:40:39 - INFO - __main__ - Step 118707: {'lr': 5.315932639505086e-05, 'samples': 22791744, 'steps': 118706, 'loss/train': 1.0911250114440918} 08/31/2021 10:40:40 - INFO - __main__ - Step 118708: {'lr': 5.315605488428532e-05, 'samples': 22791936, 'steps': 118707, 'loss/train': 0.6520830392837524} 08/31/2021 10:40:40 - INFO - __main__ - Step 118709: {'lr': 5.3152783462214696e-05, 'samples': 22792128, 'steps': 118708, 'loss/train': 1.5128623247146606} 08/31/2021 10:40:40 - INFO - __main__ - Step 118710: {'lr': 5.314951212884031e-05, 'samples': 22792320, 'steps': 118709, 'loss/train': 0.8447067737579346} 08/31/2021 10:40:42 - INFO - __main__ - Step 118711: {'lr': 5.3146240884163726e-05, 'samples': 22792512, 'steps': 118710, 'loss/train': 1.2660603523254395} 08/31/2021 10:40:42 - INFO - __main__ - Step 118712: {'lr': 5.3142969728186416e-05, 'samples': 22792704, 'steps': 118711, 'loss/train': 1.7708343267440796} 08/31/2021 10:40:43 - INFO - __main__ - Step 118713: {'lr': 5.3139698660909814e-05, 'samples': 22792896, 'steps': 118712, 'loss/train': 0.3590846657752991} 08/31/2021 10:40:43 - INFO - __main__ - Step 118714: {'lr': 5.313642768233545e-05, 'samples': 22793088, 'steps': 118713, 'loss/train': 1.5387544631958008} 08/31/2021 10:40:44 - INFO - __main__ - Step 118715: {'lr': 5.3133156792464775e-05, 'samples': 22793280, 'steps': 118714, 'loss/train': 0.6704795956611633} 08/31/2021 10:40:44 - INFO - __main__ - Step 118716: {'lr': 5.312988599129925e-05, 'samples': 22793472, 'steps': 118715, 'loss/train': 1.6420921087265015} 08/31/2021 10:40:45 - INFO - __main__ - Step 118717: {'lr': 5.312661527884038e-05, 'samples': 22793664, 'steps': 118716, 'loss/train': 1.3119577169418335} 08/31/2021 10:40:46 - INFO - __main__ - Step 118718: {'lr': 5.312334465508961e-05, 'samples': 22793856, 'steps': 118717, 'loss/train': 1.2608699798583984} 08/31/2021 10:40:46 - INFO - __main__ - Step 118719: {'lr': 5.31200741200484e-05, 'samples': 22794048, 'steps': 118718, 'loss/train': 1.031894326210022} 08/31/2021 10:40:47 - INFO - __main__ - Step 118720: {'lr': 5.3116803673718264e-05, 'samples': 22794240, 'steps': 118719, 'loss/train': 1.564422845840454} 08/31/2021 10:40:47 - INFO - __main__ - Step 118721: {'lr': 5.3113533316100664e-05, 'samples': 22794432, 'steps': 118720, 'loss/train': 1.4403184652328491} 08/31/2021 10:40:48 - INFO - __main__ - Step 118722: {'lr': 5.311026304719713e-05, 'samples': 22794624, 'steps': 118721, 'loss/train': 0.42905694246292114} 08/31/2021 10:40:49 - INFO - __main__ - Step 118723: {'lr': 5.3106992867009016e-05, 'samples': 22794816, 'steps': 118722, 'loss/train': 1.1601080894470215} 08/31/2021 10:40:49 - INFO - __main__ - Step 118724: {'lr': 5.310372277553785e-05, 'samples': 22795008, 'steps': 118723, 'loss/train': 1.4477169513702393} 08/31/2021 10:40:50 - INFO - __main__ - Step 118725: {'lr': 5.310045277278511e-05, 'samples': 22795200, 'steps': 118724, 'loss/train': 1.097896933555603} 08/31/2021 10:40:50 - INFO - __main__ - Step 118726: {'lr': 5.309718285875226e-05, 'samples': 22795392, 'steps': 118725, 'loss/train': 1.5911697149276733} 08/31/2021 10:40:51 - INFO - __main__ - Step 118727: {'lr': 5.309391303344077e-05, 'samples': 22795584, 'steps': 118726, 'loss/train': 1.0426288843154907} 08/31/2021 10:40:52 - INFO - __main__ - Step 118728: {'lr': 5.309064329685212e-05, 'samples': 22795776, 'steps': 118727, 'loss/train': 1.1755691766738892} 08/31/2021 10:40:52 - INFO - __main__ - Step 118729: {'lr': 5.30873736489878e-05, 'samples': 22795968, 'steps': 118728, 'loss/train': 0.38280707597732544} 08/31/2021 10:40:53 - INFO - __main__ - Step 118730: {'lr': 5.308410408984929e-05, 'samples': 22796160, 'steps': 118729, 'loss/train': 1.7073135375976562} 08/31/2021 10:40:53 - INFO - __main__ - Step 118731: {'lr': 5.308083461943802e-05, 'samples': 22796352, 'steps': 118730, 'loss/train': 0.870909571647644} 08/31/2021 10:40:55 - INFO - __main__ - Step 118732: {'lr': 5.307756523775551e-05, 'samples': 22796544, 'steps': 118731, 'loss/train': 0.3502858877182007} 08/31/2021 10:40:55 - INFO - __main__ - Step 118733: {'lr': 5.3074295944803176e-05, 'samples': 22796736, 'steps': 118732, 'loss/train': 1.1956645250320435} 08/31/2021 10:40:55 - INFO - __main__ - Step 118734: {'lr': 5.307102674058256e-05, 'samples': 22796928, 'steps': 118733, 'loss/train': 1.5361027717590332} 08/31/2021 10:40:56 - INFO - __main__ - Step 118735: {'lr': 5.306775762509508e-05, 'samples': 22797120, 'steps': 118734, 'loss/train': 1.2595921754837036} 08/31/2021 10:40:56 - INFO - __main__ - Step 118736: {'lr': 5.3064488598342285e-05, 'samples': 22797312, 'steps': 118735, 'loss/train': 0.6467931270599365} 08/31/2021 10:40:57 - INFO - __main__ - Step 118737: {'lr': 5.3061219660325566e-05, 'samples': 22797504, 'steps': 118736, 'loss/train': 0.558363139629364} 08/31/2021 10:40:58 - INFO - __main__ - Step 118738: {'lr': 5.305795081104639e-05, 'samples': 22797696, 'steps': 118737, 'loss/train': 1.3580769300460815} 08/31/2021 10:40:58 - INFO - __main__ - Step 118739: {'lr': 5.305468205050626e-05, 'samples': 22797888, 'steps': 118738, 'loss/train': 0.5368273854255676} 08/31/2021 10:40:59 - INFO - __main__ - Step 118740: {'lr': 5.305141337870667e-05, 'samples': 22798080, 'steps': 118739, 'loss/train': 0.6461832523345947} 08/31/2021 10:40:59 - INFO - __main__ - Step 118741: {'lr': 5.304814479564907e-05, 'samples': 22798272, 'steps': 118740, 'loss/train': 1.1747287511825562} 08/31/2021 10:41:01 - INFO - __main__ - Step 118742: {'lr': 5.3044876301334924e-05, 'samples': 22798464, 'steps': 118741, 'loss/train': 1.36570405960083} 08/31/2021 10:41:01 - INFO - __main__ - Step 118743: {'lr': 5.304160789576573e-05, 'samples': 22798656, 'steps': 118742, 'loss/train': 0.04442567378282547} 08/31/2021 10:41:02 - INFO - __main__ - Step 118744: {'lr': 5.303833957894294e-05, 'samples': 22798848, 'steps': 118743, 'loss/train': 1.3358790874481201} 08/31/2021 10:41:02 - INFO - __main__ - Step 118745: {'lr': 5.303507135086805e-05, 'samples': 22799040, 'steps': 118744, 'loss/train': 1.2944320440292358} 08/31/2021 10:41:02 - INFO - __main__ - Step 118746: {'lr': 5.30318032115425e-05, 'samples': 22799232, 'steps': 118745, 'loss/train': 0.11735443025827408} 08/31/2021 10:41:04 - INFO - __main__ - Step 118747: {'lr': 5.302853516096787e-05, 'samples': 22799424, 'steps': 118746, 'loss/train': 1.197492003440857} 08/31/2021 10:41:05 - INFO - __main__ - Step 118748: {'lr': 5.302526719914544e-05, 'samples': 22799616, 'steps': 118747, 'loss/train': 1.2696874141693115} 08/31/2021 10:41:05 - INFO - __main__ - Step 118749: {'lr': 5.302199932607682e-05, 'samples': 22799808, 'steps': 118748, 'loss/train': 1.6364909410476685} 08/31/2021 10:41:06 - INFO - __main__ - Step 118750: {'lr': 5.3018731541763424e-05, 'samples': 22800000, 'steps': 118749, 'loss/train': 0.9936040639877319} 08/31/2021 10:41:06 - INFO - __main__ - Step 118751: {'lr': 5.301546384620676e-05, 'samples': 22800192, 'steps': 118750, 'loss/train': 1.3765569925308228} 08/31/2021 10:41:06 - INFO - __main__ - Step 118752: {'lr': 5.301219623940828e-05, 'samples': 22800384, 'steps': 118751, 'loss/train': 1.3016407489776611} 08/31/2021 10:41:08 - INFO - __main__ - Step 118753: {'lr': 5.3008928721369474e-05, 'samples': 22800576, 'steps': 118752, 'loss/train': 1.1875795125961304} 08/31/2021 10:41:08 - INFO - __main__ - Step 118754: {'lr': 5.3005661292091803e-05, 'samples': 22800768, 'steps': 118753, 'loss/train': 1.1339974403381348} 08/31/2021 10:41:09 - INFO - __main__ - Step 118755: {'lr': 5.300239395157674e-05, 'samples': 22800960, 'steps': 118754, 'loss/train': 1.458146333694458} 08/31/2021 10:41:09 - INFO - __main__ - Step 118756: {'lr': 5.299912669982576e-05, 'samples': 22801152, 'steps': 118755, 'loss/train': 1.2982441186904907} 08/31/2021 10:41:09 - INFO - __main__ - Step 118757: {'lr': 5.299585953684033e-05, 'samples': 22801344, 'steps': 118756, 'loss/train': 0.7754145860671997} 08/31/2021 10:41:11 - INFO - __main__ - Step 118758: {'lr': 5.2992592462622e-05, 'samples': 22801536, 'steps': 118757, 'loss/train': 1.0545991659164429} 08/31/2021 10:41:11 - INFO - __main__ - Step 118759: {'lr': 5.298932547717209e-05, 'samples': 22801728, 'steps': 118758, 'loss/train': 1.3108083009719849} 08/31/2021 10:41:12 - INFO - __main__ - Step 118760: {'lr': 5.298605858049216e-05, 'samples': 22801920, 'steps': 118759, 'loss/train': 1.1909877061843872} 08/31/2021 10:41:12 - INFO - __main__ - Step 118761: {'lr': 5.298279177258366e-05, 'samples': 22802112, 'steps': 118760, 'loss/train': 0.8541965484619141} 08/31/2021 10:41:12 - INFO - __main__ - Step 118762: {'lr': 5.297952505344808e-05, 'samples': 22802304, 'steps': 118761, 'loss/train': 1.4392640590667725} 08/31/2021 10:41:14 - INFO - __main__ - Step 118763: {'lr': 5.2976258423086874e-05, 'samples': 22802496, 'steps': 118762, 'loss/train': 0.7639901638031006} 08/31/2021 10:41:14 - INFO - __main__ - Step 118764: {'lr': 5.2972991881501535e-05, 'samples': 22802688, 'steps': 118763, 'loss/train': 0.7223583459854126} 08/31/2021 10:41:15 - INFO - __main__ - Step 118765: {'lr': 5.296972542869355e-05, 'samples': 22802880, 'steps': 118764, 'loss/train': 0.9317029714584351} 08/31/2021 10:41:15 - INFO - __main__ - Step 118766: {'lr': 5.296645906466432e-05, 'samples': 22803072, 'steps': 118765, 'loss/train': 0.947578489780426} 08/31/2021 10:41:15 - INFO - __main__ - Step 118767: {'lr': 5.296319278941539e-05, 'samples': 22803264, 'steps': 118766, 'loss/train': 1.474212408065796} 08/31/2021 10:41:17 - INFO - __main__ - Step 118768: {'lr': 5.295992660294821e-05, 'samples': 22803456, 'steps': 118767, 'loss/train': 0.6944257616996765} 08/31/2021 10:41:17 - INFO - __main__ - Step 118769: {'lr': 5.295666050526432e-05, 'samples': 22803648, 'steps': 118768, 'loss/train': 1.9013142585754395} 08/31/2021 10:41:18 - INFO - __main__ - Step 118770: {'lr': 5.295339449636502e-05, 'samples': 22803840, 'steps': 118769, 'loss/train': 0.4045579135417938} 08/31/2021 10:41:18 - INFO - __main__ - Step 118771: {'lr': 5.295012857625189e-05, 'samples': 22804032, 'steps': 118770, 'loss/train': 0.15972794592380524} 08/31/2021 10:41:18 - INFO - __main__ - Step 118772: {'lr': 5.294686274492641e-05, 'samples': 22804224, 'steps': 118771, 'loss/train': 1.674979329109192} 08/31/2021 10:41:19 - INFO - __main__ - Step 118773: {'lr': 5.294359700239001e-05, 'samples': 22804416, 'steps': 118772, 'loss/train': 1.2512354850769043} 08/31/2021 10:41:20 - INFO - __main__ - Step 118774: {'lr': 5.2940331348644206e-05, 'samples': 22804608, 'steps': 118773, 'loss/train': 1.7875779867172241} 08/31/2021 10:41:21 - INFO - __main__ - Step 118775: {'lr': 5.2937065783690423e-05, 'samples': 22804800, 'steps': 118774, 'loss/train': 1.1694484949111938} 08/31/2021 10:41:21 - INFO - __main__ - Step 118776: {'lr': 5.293380030753017e-05, 'samples': 22804992, 'steps': 118775, 'loss/train': 1.4204449653625488} 08/31/2021 10:41:21 - INFO - __main__ - Step 118777: {'lr': 5.293053492016492e-05, 'samples': 22805184, 'steps': 118776, 'loss/train': 1.452943205833435} 08/31/2021 10:41:22 - INFO - __main__ - Step 118778: {'lr': 5.292726962159611e-05, 'samples': 22805376, 'steps': 118777, 'loss/train': 1.5547573566436768} 08/31/2021 10:41:23 - INFO - __main__ - Step 118779: {'lr': 5.292400441182524e-05, 'samples': 22805568, 'steps': 118778, 'loss/train': 1.135475516319275} 08/31/2021 10:41:24 - INFO - __main__ - Step 118780: {'lr': 5.292073929085384e-05, 'samples': 22805760, 'steps': 118779, 'loss/train': 1.101625680923462} 08/31/2021 10:41:24 - INFO - __main__ - Step 118781: {'lr': 5.2917474258683264e-05, 'samples': 22805952, 'steps': 118780, 'loss/train': 1.223264455795288} 08/31/2021 10:41:24 - INFO - __main__ - Step 118782: {'lr': 5.2914209315315015e-05, 'samples': 22806144, 'steps': 118781, 'loss/train': 0.24846793711185455} 08/31/2021 10:41:25 - INFO - __main__ - Step 118783: {'lr': 5.291094446075057e-05, 'samples': 22806336, 'steps': 118782, 'loss/train': 1.1238751411437988} 08/31/2021 10:41:26 - INFO - __main__ - Step 118784: {'lr': 5.290767969499141e-05, 'samples': 22806528, 'steps': 118783, 'loss/train': 1.229979157447815} 08/31/2021 10:41:27 - INFO - __main__ - Step 118785: {'lr': 5.2904415018039026e-05, 'samples': 22806720, 'steps': 118784, 'loss/train': 0.5617207884788513} 08/31/2021 10:41:27 - INFO - __main__ - Step 118786: {'lr': 5.290115042989488e-05, 'samples': 22806912, 'steps': 118785, 'loss/train': 0.6043542623519897} 08/31/2021 10:41:27 - INFO - __main__ - Step 118787: {'lr': 5.289788593056041e-05, 'samples': 22807104, 'steps': 118786, 'loss/train': 0.9104058742523193} 08/31/2021 10:41:28 - INFO - __main__ - Step 118788: {'lr': 5.289462152003713e-05, 'samples': 22807296, 'steps': 118787, 'loss/train': 1.6872109174728394} 08/31/2021 10:41:29 - INFO - __main__ - Step 118789: {'lr': 5.289135719832649e-05, 'samples': 22807488, 'steps': 118788, 'loss/train': 1.246588110923767} 08/31/2021 10:41:30 - INFO - __main__ - Step 118790: {'lr': 5.288809296543001e-05, 'samples': 22807680, 'steps': 118789, 'loss/train': 1.383689522743225} 08/31/2021 10:41:30 - INFO - __main__ - Step 118791: {'lr': 5.288482882134907e-05, 'samples': 22807872, 'steps': 118790, 'loss/train': 0.9761416912078857} 08/31/2021 10:41:30 - INFO - __main__ - Step 118792: {'lr': 5.288156476608516e-05, 'samples': 22808064, 'steps': 118791, 'loss/train': 0.9856822490692139} 08/31/2021 10:41:31 - INFO - __main__ - Step 118793: {'lr': 5.287830079963979e-05, 'samples': 22808256, 'steps': 118792, 'loss/train': 1.9011343717575073} 08/31/2021 10:41:32 - INFO - __main__ - Step 118794: {'lr': 5.287503692201443e-05, 'samples': 22808448, 'steps': 118793, 'loss/train': 0.9291832447052002} 08/31/2021 10:41:33 - INFO - __main__ - Step 118795: {'lr': 5.287177313321051e-05, 'samples': 22808640, 'steps': 118794, 'loss/train': 0.02694982849061489} 08/31/2021 10:41:33 - INFO - __main__ - Step 118796: {'lr': 5.2868509433229544e-05, 'samples': 22808832, 'steps': 118795, 'loss/train': 1.0198323726654053} 08/31/2021 10:41:33 - INFO - __main__ - Step 118797: {'lr': 5.2865245822073e-05, 'samples': 22809024, 'steps': 118796, 'loss/train': 0.03777794539928436} 08/31/2021 10:41:34 - INFO - __main__ - Step 118798: {'lr': 5.2861982299742314e-05, 'samples': 22809216, 'steps': 118797, 'loss/train': 1.3596420288085938} 08/31/2021 10:41:35 - INFO - __main__ - Step 118799: {'lr': 5.285871886623897e-05, 'samples': 22809408, 'steps': 118798, 'loss/train': 0.9951554536819458} 08/31/2021 10:41:36 - INFO - __main__ - Step 118800: {'lr': 5.285545552156445e-05, 'samples': 22809600, 'steps': 118799, 'loss/train': 1.8615788221359253} 08/31/2021 10:41:36 - INFO - __main__ - Step 118801: {'lr': 5.285219226572022e-05, 'samples': 22809792, 'steps': 118800, 'loss/train': 0.2960663437843323} 08/31/2021 10:41:37 - INFO - __main__ - Step 118802: {'lr': 5.284892909870775e-05, 'samples': 22809984, 'steps': 118801, 'loss/train': 1.2010581493377686} 08/31/2021 10:41:37 - INFO - __main__ - Step 118803: {'lr': 5.284566602052859e-05, 'samples': 22810176, 'steps': 118802, 'loss/train': 1.027614712715149} 08/31/2021 10:41:37 - INFO - __main__ - Step 118804: {'lr': 5.284240303118407e-05, 'samples': 22810368, 'steps': 118803, 'loss/train': 1.0597412586212158} 08/31/2021 10:41:39 - INFO - __main__ - Step 118805: {'lr': 5.28391401306757e-05, 'samples': 22810560, 'steps': 118804, 'loss/train': 1.0239874124526978} 08/31/2021 10:41:40 - INFO - __main__ - Step 118806: {'lr': 5.2835877319004965e-05, 'samples': 22810752, 'steps': 118805, 'loss/train': 0.6768302917480469} 08/31/2021 10:41:40 - INFO - __main__ - Step 118807: {'lr': 5.2832614596173364e-05, 'samples': 22810944, 'steps': 118806, 'loss/train': 0.12897248566150665} 08/31/2021 10:41:41 - INFO - __main__ - Step 118808: {'lr': 5.282935196218233e-05, 'samples': 22811136, 'steps': 118807, 'loss/train': 1.7222094535827637} 08/31/2021 10:41:41 - INFO - __main__ - Step 118809: {'lr': 5.282608941703335e-05, 'samples': 22811328, 'steps': 118808, 'loss/train': 1.3063513040542603} 08/31/2021 10:41:42 - INFO - __main__ - Step 118810: {'lr': 5.282282696072788e-05, 'samples': 22811520, 'steps': 118809, 'loss/train': 1.0141193866729736} 08/31/2021 10:41:43 - INFO - __main__ - Step 118811: {'lr': 5.281956459326742e-05, 'samples': 22811712, 'steps': 118810, 'loss/train': 1.1554646492004395} 08/31/2021 10:41:43 - INFO - __main__ - Step 118812: {'lr': 5.2816302314653424e-05, 'samples': 22811904, 'steps': 118811, 'loss/train': 1.113855004310608} 08/31/2021 10:41:44 - INFO - __main__ - Step 118813: {'lr': 5.281304012488733e-05, 'samples': 22812096, 'steps': 118812, 'loss/train': 1.077756643295288} 08/31/2021 10:41:44 - INFO - __main__ - Step 118814: {'lr': 5.280977802397066e-05, 'samples': 22812288, 'steps': 118813, 'loss/train': 0.9999540448188782} 08/31/2021 10:41:46 - INFO - __main__ - Step 118815: {'lr': 5.2806516011904866e-05, 'samples': 22812480, 'steps': 118814, 'loss/train': 0.9981885552406311} 08/31/2021 10:41:46 - INFO - __main__ - Step 118816: {'lr': 5.280325408869147e-05, 'samples': 22812672, 'steps': 118815, 'loss/train': 0.6074953079223633} 08/31/2021 10:41:46 - INFO - __main__ - Step 118817: {'lr': 5.279999225433182e-05, 'samples': 22812864, 'steps': 118816, 'loss/train': 1.011112928390503} 08/31/2021 10:41:47 - INFO - __main__ - Step 118818: {'lr': 5.279673050882747e-05, 'samples': 22813056, 'steps': 118817, 'loss/train': 0.8132396340370178} 08/31/2021 10:41:47 - INFO - __main__ - Step 118819: {'lr': 5.279346885217984e-05, 'samples': 22813248, 'steps': 118818, 'loss/train': 1.0826762914657593} 08/31/2021 10:41:47 - INFO - __main__ - Step 118820: {'lr': 5.279020728439043e-05, 'samples': 22813440, 'steps': 118819, 'loss/train': 0.3139033019542694} 08/31/2021 10:41:49 - INFO - __main__ - Step 118821: {'lr': 5.278694580546073e-05, 'samples': 22813632, 'steps': 118820, 'loss/train': 1.39413321018219} 08/31/2021 10:41:49 - INFO - __main__ - Step 118822: {'lr': 5.278368441539219e-05, 'samples': 22813824, 'steps': 118821, 'loss/train': 1.1507655382156372} 08/31/2021 10:41:50 - INFO - __main__ - Step 118823: {'lr': 5.2780423114186265e-05, 'samples': 22814016, 'steps': 118822, 'loss/train': 1.354495644569397} 08/31/2021 10:41:50 - INFO - __main__ - Step 118824: {'lr': 5.277716190184442e-05, 'samples': 22814208, 'steps': 118823, 'loss/train': 1.1540164947509766} 08/31/2021 10:41:50 - INFO - __main__ - Step 118825: {'lr': 5.277390077836819e-05, 'samples': 22814400, 'steps': 118824, 'loss/train': 1.3969703912734985} 08/31/2021 10:41:52 - INFO - __main__ - Step 118826: {'lr': 5.2770639743758956e-05, 'samples': 22814592, 'steps': 118825, 'loss/train': 0.7440032958984375} 08/31/2021 10:41:52 - INFO - __main__ - Step 118827: {'lr': 5.276737879801824e-05, 'samples': 22814784, 'steps': 118826, 'loss/train': 1.2822281122207642} 08/31/2021 10:41:53 - INFO - __main__ - Step 118828: {'lr': 5.276411794114752e-05, 'samples': 22814976, 'steps': 118827, 'loss/train': 1.5304388999938965} 08/31/2021 10:41:53 - INFO - __main__ - Step 118829: {'lr': 5.276085717314821e-05, 'samples': 22815168, 'steps': 118828, 'loss/train': 0.8638659715652466} 08/31/2021 10:41:53 - INFO - __main__ - Step 118830: {'lr': 5.27575964940219e-05, 'samples': 22815360, 'steps': 118829, 'loss/train': 1.5636043548583984} 08/31/2021 10:41:55 - INFO - __main__ - Step 118831: {'lr': 5.2754335903769904e-05, 'samples': 22815552, 'steps': 118830, 'loss/train': 1.210137963294983} 08/31/2021 10:41:56 - INFO - __main__ - Step 118832: {'lr': 5.2751075402393764e-05, 'samples': 22815744, 'steps': 118831, 'loss/train': 1.370729684829712} 08/31/2021 10:41:56 - INFO - __main__ - Step 118833: {'lr': 5.274781498989495e-05, 'samples': 22815936, 'steps': 118832, 'loss/train': 1.1964101791381836} 08/31/2021 10:41:57 - INFO - __main__ - Step 118834: {'lr': 5.274455466627492e-05, 'samples': 22816128, 'steps': 118833, 'loss/train': 0.8346193432807922} 08/31/2021 10:41:57 - INFO - __main__ - Step 118835: {'lr': 5.274129443153514e-05, 'samples': 22816320, 'steps': 118834, 'loss/train': 0.07455946505069733} 08/31/2021 10:41:57 - INFO - __main__ - Step 118836: {'lr': 5.273803428567711e-05, 'samples': 22816512, 'steps': 118835, 'loss/train': 1.2370871305465698} 08/31/2021 10:41:59 - INFO - __main__ - Step 118837: {'lr': 5.273477422870227e-05, 'samples': 22816704, 'steps': 118836, 'loss/train': 0.7268823981285095} 08/31/2021 10:41:59 - INFO - __main__ - Step 118838: {'lr': 5.2731514260612095e-05, 'samples': 22816896, 'steps': 118837, 'loss/train': 1.4861879348754883} 08/31/2021 10:42:00 - INFO - __main__ - Step 118839: {'lr': 5.272825438140805e-05, 'samples': 22817088, 'steps': 118838, 'loss/train': 1.3207181692123413} 08/31/2021 10:42:00 - INFO - __main__ - Step 118840: {'lr': 5.272499459109162e-05, 'samples': 22817280, 'steps': 118839, 'loss/train': 1.9567962884902954} 08/31/2021 10:42:00 - INFO - __main__ - Step 118841: {'lr': 5.272173488966425e-05, 'samples': 22817472, 'steps': 118840, 'loss/train': 1.3722909688949585} 08/31/2021 10:42:01 - INFO - __main__ - Step 118842: {'lr': 5.271847527712742e-05, 'samples': 22817664, 'steps': 118841, 'loss/train': 1.055484414100647} 08/31/2021 10:42:02 - INFO - __main__ - Step 118843: {'lr': 5.271521575348268e-05, 'samples': 22817856, 'steps': 118842, 'loss/train': 1.0343981981277466} 08/31/2021 10:42:03 - INFO - __main__ - Step 118844: {'lr': 5.2711956318731355e-05, 'samples': 22818048, 'steps': 118843, 'loss/train': 0.09283546358346939} 08/31/2021 10:42:03 - INFO - __main__ - Step 118845: {'lr': 5.2708696972874973e-05, 'samples': 22818240, 'steps': 118844, 'loss/train': 0.5544000267982483} 08/31/2021 10:42:04 - INFO - __main__ - Step 118846: {'lr': 5.270543771591502e-05, 'samples': 22818432, 'steps': 118845, 'loss/train': 1.269330620765686} 08/31/2021 10:42:04 - INFO - __main__ - Step 118847: {'lr': 5.270217854785292e-05, 'samples': 22818624, 'steps': 118846, 'loss/train': 0.8190391063690186} 08/31/2021 10:42:06 - INFO - __main__ - Step 118848: {'lr': 5.269891946869021e-05, 'samples': 22818816, 'steps': 118847, 'loss/train': 0.6956205368041992} 08/31/2021 10:42:07 - INFO - __main__ - Step 118849: {'lr': 5.2695660478428307e-05, 'samples': 22819008, 'steps': 118848, 'loss/train': 1.590657114982605} 08/31/2021 10:42:07 - INFO - __main__ - Step 118850: {'lr': 5.269240157706867e-05, 'samples': 22819200, 'steps': 118849, 'loss/train': 1.4329946041107178} 08/31/2021 10:42:08 - INFO - __main__ - Step 118851: {'lr': 5.268914276461281e-05, 'samples': 22819392, 'steps': 118850, 'loss/train': 1.7358356714248657} 08/31/2021 10:42:08 - INFO - __main__ - Step 118852: {'lr': 5.26858840410622e-05, 'samples': 22819584, 'steps': 118851, 'loss/train': 0.8874478340148926} 08/31/2021 10:42:08 - INFO - __main__ - Step 118853: {'lr': 5.268262540641827e-05, 'samples': 22819776, 'steps': 118852, 'loss/train': 0.8276128768920898} 08/31/2021 10:42:09 - INFO - __main__ - Step 118854: {'lr': 5.2679366860682507e-05, 'samples': 22819968, 'steps': 118853, 'loss/train': 0.9568403959274292} 08/31/2021 10:42:09 - INFO - __main__ - Step 118855: {'lr': 5.267610840385637e-05, 'samples': 22820160, 'steps': 118854, 'loss/train': 1.64356529712677} 08/31/2021 10:42:11 - INFO - __main__ - Step 118856: {'lr': 5.267285003594133e-05, 'samples': 22820352, 'steps': 118855, 'loss/train': 1.3873785734176636} 08/31/2021 10:42:11 - INFO - __main__ - Step 118857: {'lr': 5.266959175693894e-05, 'samples': 22820544, 'steps': 118856, 'loss/train': 1.2661159038543701} 08/31/2021 10:42:11 - INFO - __main__ - Step 118858: {'lr': 5.266633356685052e-05, 'samples': 22820736, 'steps': 118857, 'loss/train': 1.335684061050415} 08/31/2021 10:42:12 - INFO - __main__ - Step 118859: {'lr': 5.2663075465677585e-05, 'samples': 22820928, 'steps': 118858, 'loss/train': 1.3423399925231934} 08/31/2021 10:42:12 - INFO - __main__ - Step 118860: {'lr': 5.265981745342163e-05, 'samples': 22821120, 'steps': 118859, 'loss/train': 1.1019070148468018} 08/31/2021 10:42:14 - INFO - __main__ - Step 118861: {'lr': 5.2656559530084136e-05, 'samples': 22821312, 'steps': 118860, 'loss/train': 0.46322518587112427} 08/31/2021 10:42:15 - INFO - __main__ - Step 118862: {'lr': 5.2653301695666536e-05, 'samples': 22821504, 'steps': 118861, 'loss/train': 0.0961882546544075} 08/31/2021 10:42:15 - INFO - __main__ - Step 118863: {'lr': 5.265004395017031e-05, 'samples': 22821696, 'steps': 118862, 'loss/train': 1.2411147356033325} 08/31/2021 10:42:15 - INFO - __main__ - Step 118864: {'lr': 5.264678629359693e-05, 'samples': 22821888, 'steps': 118863, 'loss/train': 0.6799203157424927} 08/31/2021 10:42:16 - INFO - __main__ - Step 118865: {'lr': 5.2643528725947854e-05, 'samples': 22822080, 'steps': 118864, 'loss/train': 1.0115786790847778} 08/31/2021 10:42:17 - INFO - __main__ - Step 118866: {'lr': 5.264027124722459e-05, 'samples': 22822272, 'steps': 118865, 'loss/train': 1.3357479572296143} 08/31/2021 10:42:18 - INFO - __main__ - Step 118867: {'lr': 5.2637013857428555e-05, 'samples': 22822464, 'steps': 118866, 'loss/train': 0.4666787087917328} 08/31/2021 10:42:18 - INFO - __main__ - Step 118868: {'lr': 5.2633756556561216e-05, 'samples': 22822656, 'steps': 118867, 'loss/train': 0.46774718165397644} 08/31/2021 10:42:19 - INFO - __main__ - Step 118869: {'lr': 5.2630499344624077e-05, 'samples': 22822848, 'steps': 118868, 'loss/train': 1.1612963676452637} 08/31/2021 10:42:19 - INFO - __main__ - Step 118870: {'lr': 5.262724222161866e-05, 'samples': 22823040, 'steps': 118869, 'loss/train': 0.7996537089347839} 08/31/2021 10:42:21 - INFO - __main__ - Step 118871: {'lr': 5.26239851875463e-05, 'samples': 22823232, 'steps': 118870, 'loss/train': 0.9283114075660706} 08/31/2021 10:42:21 - INFO - __main__ - Step 118872: {'lr': 5.2620728242408516e-05, 'samples': 22823424, 'steps': 118871, 'loss/train': 0.9274972081184387} 08/31/2021 10:42:21 - INFO - __main__ - Step 118873: {'lr': 5.2617471386206817e-05, 'samples': 22823616, 'steps': 118872, 'loss/train': 0.8723974823951721} 08/31/2021 10:42:22 - INFO - __main__ - Step 118874: {'lr': 5.2614214618942614e-05, 'samples': 22823808, 'steps': 118873, 'loss/train': 0.5891184210777283} 08/31/2021 10:42:22 - INFO - __main__ - Step 118875: {'lr': 5.261095794061738e-05, 'samples': 22824000, 'steps': 118874, 'loss/train': 0.995217502117157} 08/31/2021 10:42:24 - INFO - __main__ - Step 118876: {'lr': 5.260770135123264e-05, 'samples': 22824192, 'steps': 118875, 'loss/train': 1.2967684268951416} 08/31/2021 10:42:24 - INFO - __main__ - Step 118877: {'lr': 5.2604444850789804e-05, 'samples': 22824384, 'steps': 118876, 'loss/train': 1.1213719844818115} 08/31/2021 10:42:25 - INFO - __main__ - Step 118878: {'lr': 5.260118843929035e-05, 'samples': 22824576, 'steps': 118877, 'loss/train': 1.2212016582489014} 08/31/2021 10:42:25 - INFO - __main__ - Step 118879: {'lr': 5.259793211673578e-05, 'samples': 22824768, 'steps': 118878, 'loss/train': 0.34782445430755615} 08/31/2021 10:42:25 - INFO - __main__ - Step 118880: {'lr': 5.25946758831275e-05, 'samples': 22824960, 'steps': 118879, 'loss/train': 0.8888128995895386} 08/31/2021 10:42:27 - INFO - __main__ - Step 118881: {'lr': 5.259141973846704e-05, 'samples': 22825152, 'steps': 118880, 'loss/train': 1.0697145462036133} 08/31/2021 10:42:27 - INFO - __main__ - Step 118882: {'lr': 5.2588163682755845e-05, 'samples': 22825344, 'steps': 118881, 'loss/train': 1.422643780708313} 08/31/2021 10:42:28 - INFO - __main__ - Step 118883: {'lr': 5.258490771599536e-05, 'samples': 22825536, 'steps': 118882, 'loss/train': 1.2470853328704834} 08/31/2021 10:42:28 - INFO - __main__ - Step 118884: {'lr': 5.2581651838187136e-05, 'samples': 22825728, 'steps': 118883, 'loss/train': 1.287231683731079} 08/31/2021 10:42:28 - INFO - __main__ - Step 118885: {'lr': 5.2578396049332514e-05, 'samples': 22825920, 'steps': 118884, 'loss/train': 0.8750479817390442} 08/31/2021 10:42:30 - INFO - __main__ - Step 118886: {'lr': 5.2575140349433034e-05, 'samples': 22826112, 'steps': 118885, 'loss/train': 0.7793166041374207} 08/31/2021 10:42:30 - INFO - __main__ - Step 118887: {'lr': 5.2571884738490114e-05, 'samples': 22826304, 'steps': 118886, 'loss/train': 1.0431561470031738} 08/31/2021 10:42:31 - INFO - __main__ - Step 118888: {'lr': 5.256862921650529e-05, 'samples': 22826496, 'steps': 118887, 'loss/train': 1.3067626953125} 08/31/2021 10:42:31 - INFO - __main__ - Step 118889: {'lr': 5.256537378347997e-05, 'samples': 22826688, 'steps': 118888, 'loss/train': 1.2752820253372192} 08/31/2021 10:42:32 - INFO - __main__ - Step 118890: {'lr': 5.256211843941566e-05, 'samples': 22826880, 'steps': 118889, 'loss/train': 1.6171908378601074} 08/31/2021 10:42:32 - INFO - __main__ - Step 118891: {'lr': 5.255886318431383e-05, 'samples': 22827072, 'steps': 118890, 'loss/train': 0.8598917722702026} 08/31/2021 10:42:34 - INFO - __main__ - Step 118892: {'lr': 5.255560801817591e-05, 'samples': 22827264, 'steps': 118891, 'loss/train': 0.6647071242332458} 08/31/2021 10:42:34 - INFO - __main__ - Step 118893: {'lr': 5.255235294100338e-05, 'samples': 22827456, 'steps': 118892, 'loss/train': 0.5631536841392517} 08/31/2021 10:42:34 - INFO - __main__ - Step 118894: {'lr': 5.254909795279772e-05, 'samples': 22827648, 'steps': 118893, 'loss/train': 0.854229211807251} 08/31/2021 10:42:35 - INFO - __main__ - Step 118895: {'lr': 5.2545843053560385e-05, 'samples': 22827840, 'steps': 118894, 'loss/train': 0.486855149269104} 08/31/2021 10:42:35 - INFO - __main__ - Step 118896: {'lr': 5.254258824329286e-05, 'samples': 22828032, 'steps': 118895, 'loss/train': 1.4983997344970703} 08/31/2021 10:42:37 - INFO - __main__ - Step 118897: {'lr': 5.2539333521996634e-05, 'samples': 22828224, 'steps': 118896, 'loss/train': 1.689292073249817} 08/31/2021 10:42:37 - INFO - __main__ - Step 118898: {'lr': 5.25360788896731e-05, 'samples': 22828416, 'steps': 118897, 'loss/train': 1.1080479621887207} 08/31/2021 10:42:38 - INFO - __main__ - Step 118899: {'lr': 5.253282434632376e-05, 'samples': 22828608, 'steps': 118898, 'loss/train': 0.645126461982727} 08/31/2021 10:42:38 - INFO - __main__ - Step 118900: {'lr': 5.252956989195007e-05, 'samples': 22828800, 'steps': 118899, 'loss/train': 1.4003170728683472} 08/31/2021 10:42:38 - INFO - __main__ - Step 118901: {'lr': 5.252631552655351e-05, 'samples': 22828992, 'steps': 118900, 'loss/train': 0.8238505721092224} 08/31/2021 10:42:40 - INFO - __main__ - Step 118902: {'lr': 5.2523061250135564e-05, 'samples': 22829184, 'steps': 118901, 'loss/train': 1.329267978668213} 08/31/2021 10:42:40 - INFO - __main__ - Step 118903: {'lr': 5.2519807062697654e-05, 'samples': 22829376, 'steps': 118902, 'loss/train': 1.587615728378296} 08/31/2021 10:42:41 - INFO - __main__ - Step 118904: {'lr': 5.2516552964241294e-05, 'samples': 22829568, 'steps': 118903, 'loss/train': 0.9313033223152161} 08/31/2021 10:42:41 - INFO - __main__ - Step 118905: {'lr': 5.251329895476792e-05, 'samples': 22829760, 'steps': 118904, 'loss/train': 1.0774459838867188} 08/31/2021 10:42:41 - INFO - __main__ - Step 118906: {'lr': 5.2510045034279003e-05, 'samples': 22829952, 'steps': 118905, 'loss/train': 1.2461048364639282} 08/31/2021 10:42:43 - INFO - __main__ - Step 118907: {'lr': 5.2506791202775987e-05, 'samples': 22830144, 'steps': 118906, 'loss/train': 0.9901494979858398} 08/31/2021 10:42:44 - INFO - __main__ - Step 118908: {'lr': 5.25035374602604e-05, 'samples': 22830336, 'steps': 118907, 'loss/train': 0.7193965315818787} 08/31/2021 10:42:44 - INFO - __main__ - Step 118909: {'lr': 5.2500283806733664e-05, 'samples': 22830528, 'steps': 118908, 'loss/train': 0.856830358505249} 08/31/2021 10:42:45 - INFO - __main__ - Step 118910: {'lr': 5.249703024219732e-05, 'samples': 22830720, 'steps': 118909, 'loss/train': 0.9848397374153137} 08/31/2021 10:42:45 - INFO - __main__ - Step 118911: {'lr': 5.249377676665268e-05, 'samples': 22830912, 'steps': 118910, 'loss/train': 1.1893914937973022} 08/31/2021 10:42:46 - INFO - __main__ - Step 118912: {'lr': 5.2490523380101323e-05, 'samples': 22831104, 'steps': 118911, 'loss/train': 0.9678000807762146} 08/31/2021 10:42:47 - INFO - __main__ - Step 118913: {'lr': 5.248727008254467e-05, 'samples': 22831296, 'steps': 118912, 'loss/train': 0.8182680606842041} 08/31/2021 10:42:47 - INFO - __main__ - Step 118914: {'lr': 5.248401687398421e-05, 'samples': 22831488, 'steps': 118913, 'loss/train': 1.4577397108078003} 08/31/2021 10:42:48 - INFO - __main__ - Step 118915: {'lr': 5.24807637544214e-05, 'samples': 22831680, 'steps': 118914, 'loss/train': 1.0668529272079468} 08/31/2021 10:42:48 - INFO - __main__ - Step 118916: {'lr': 5.247751072385773e-05, 'samples': 22831872, 'steps': 118915, 'loss/train': 1.329736351966858} 08/31/2021 10:42:48 - INFO - __main__ - Step 118917: {'lr': 5.2474257782294615e-05, 'samples': 22832064, 'steps': 118916, 'loss/train': 1.0263352394104004} 08/31/2021 10:42:50 - INFO - __main__ - Step 118918: {'lr': 5.247100492973358e-05, 'samples': 22832256, 'steps': 118917, 'loss/train': 1.3715317249298096} 08/31/2021 10:42:51 - INFO - __main__ - Step 118919: {'lr': 5.2467752166176055e-05, 'samples': 22832448, 'steps': 118918, 'loss/train': 0.7325789332389832} 08/31/2021 10:42:51 - INFO - __main__ - Step 118920: {'lr': 5.246449949162349e-05, 'samples': 22832640, 'steps': 118919, 'loss/train': 0.056155506521463394} 08/31/2021 10:42:51 - INFO - __main__ - Step 118921: {'lr': 5.2461246906077396e-05, 'samples': 22832832, 'steps': 118920, 'loss/train': 0.9084665775299072} 08/31/2021 10:42:52 - INFO - __main__ - Step 118922: {'lr': 5.245799440953922e-05, 'samples': 22833024, 'steps': 118921, 'loss/train': 0.9259061217308044} 08/31/2021 10:42:53 - INFO - __main__ - Step 118923: {'lr': 5.245474200201042e-05, 'samples': 22833216, 'steps': 118922, 'loss/train': 2.19812273979187} 08/31/2021 10:42:54 - INFO - __main__ - Step 118924: {'lr': 5.24514896834925e-05, 'samples': 22833408, 'steps': 118923, 'loss/train': 1.0959105491638184} 08/31/2021 10:42:54 - INFO - __main__ - Step 118925: {'lr': 5.2448237453986856e-05, 'samples': 22833600, 'steps': 118924, 'loss/train': 0.02912813425064087} 08/31/2021 10:42:55 - INFO - __main__ - Step 118926: {'lr': 5.244498531349498e-05, 'samples': 22833792, 'steps': 118925, 'loss/train': 1.7134013175964355} 08/31/2021 10:42:55 - INFO - __main__ - Step 118927: {'lr': 5.2441733262018346e-05, 'samples': 22833984, 'steps': 118926, 'loss/train': 0.7046205401420593} 08/31/2021 10:42:56 - INFO - __main__ - Step 118928: {'lr': 5.243848129955842e-05, 'samples': 22834176, 'steps': 118927, 'loss/train': 0.02703818678855896} 08/31/2021 10:42:57 - INFO - __main__ - Step 118929: {'lr': 5.243522942611667e-05, 'samples': 22834368, 'steps': 118928, 'loss/train': 0.8871214985847473} 08/31/2021 10:42:57 - INFO - __main__ - Step 118930: {'lr': 5.243197764169455e-05, 'samples': 22834560, 'steps': 118929, 'loss/train': 1.5274810791015625} 08/31/2021 10:42:57 - INFO - __main__ - Step 118931: {'lr': 5.242872594629352e-05, 'samples': 22834752, 'steps': 118930, 'loss/train': 1.0061432123184204} 08/31/2021 10:42:58 - INFO - __main__ - Step 118932: {'lr': 5.24254743399151e-05, 'samples': 22834944, 'steps': 118931, 'loss/train': 0.7390643954277039} 08/31/2021 10:43:00 - INFO - __main__ - Step 118933: {'lr': 5.2422222822560676e-05, 'samples': 22835136, 'steps': 118932, 'loss/train': 1.435831069946289} 08/31/2021 10:43:00 - INFO - __main__ - Step 118934: {'lr': 5.241897139423177e-05, 'samples': 22835328, 'steps': 118933, 'loss/train': 1.5084638595581055} 08/31/2021 10:43:01 - INFO - __main__ - Step 118935: {'lr': 5.241572005492981e-05, 'samples': 22835520, 'steps': 118934, 'loss/train': 1.2755874395370483} 08/31/2021 10:43:01 - INFO - __main__ - Step 118936: {'lr': 5.2412468804656274e-05, 'samples': 22835712, 'steps': 118935, 'loss/train': 1.054631233215332} 08/31/2021 10:43:01 - INFO - __main__ - Step 118937: {'lr': 5.240921764341269e-05, 'samples': 22835904, 'steps': 118936, 'loss/train': 1.8604495525360107} 08/31/2021 10:43:02 - INFO - __main__ - Step 118938: {'lr': 5.240596657120042e-05, 'samples': 22836096, 'steps': 118937, 'loss/train': 1.1574363708496094} 08/31/2021 10:43:03 - INFO - __main__ - Step 118939: {'lr': 5.2402715588020985e-05, 'samples': 22836288, 'steps': 118938, 'loss/train': 1.0122323036193848} 08/31/2021 10:43:04 - INFO - __main__ - Step 118940: {'lr': 5.23994646938758e-05, 'samples': 22836480, 'steps': 118939, 'loss/train': 0.5009582042694092} 08/31/2021 10:43:04 - INFO - __main__ - Step 118941: {'lr': 5.239621388876639e-05, 'samples': 22836672, 'steps': 118940, 'loss/train': 1.1677219867706299} 08/31/2021 10:43:05 - INFO - __main__ - Step 118942: {'lr': 5.239296317269418e-05, 'samples': 22836864, 'steps': 118941, 'loss/train': 0.7346140742301941} 08/31/2021 10:43:05 - INFO - __main__ - Step 118943: {'lr': 5.238971254566066e-05, 'samples': 22837056, 'steps': 118942, 'loss/train': 1.1407126188278198} 08/31/2021 10:43:07 - INFO - __main__ - Step 118944: {'lr': 5.238646200766731e-05, 'samples': 22837248, 'steps': 118943, 'loss/train': 1.1244901418685913} 08/31/2021 10:43:08 - INFO - __main__ - Step 118945: {'lr': 5.238321155871553e-05, 'samples': 22837440, 'steps': 118944, 'loss/train': 0.9672346711158752} 08/31/2021 10:43:08 - INFO - __main__ - Step 118946: {'lr': 5.237996119880686e-05, 'samples': 22837632, 'steps': 118945, 'loss/train': 1.4892736673355103} 08/31/2021 10:43:08 - INFO - __main__ - Step 118947: {'lr': 5.237671092794272e-05, 'samples': 22837824, 'steps': 118946, 'loss/train': 0.8012940287590027} 08/31/2021 10:43:09 - INFO - __main__ - Step 118948: {'lr': 5.2373460746124564e-05, 'samples': 22838016, 'steps': 118947, 'loss/train': 0.9928426742553711} 08/31/2021 10:43:09 - INFO - __main__ - Step 118949: {'lr': 5.23702106533539e-05, 'samples': 22838208, 'steps': 118948, 'loss/train': 0.37984225153923035} 08/31/2021 10:43:09 - INFO - __main__ - Step 118950: {'lr': 5.236696064963214e-05, 'samples': 22838400, 'steps': 118949, 'loss/train': 0.7422391176223755} 08/31/2021 10:43:11 - INFO - __main__ - Step 118951: {'lr': 5.236371073496088e-05, 'samples': 22838592, 'steps': 118950, 'loss/train': 1.080440640449524} 08/31/2021 10:43:12 - INFO - __main__ - Step 118952: {'lr': 5.236046090934141e-05, 'samples': 22838784, 'steps': 118951, 'loss/train': 0.9645788669586182} 08/31/2021 10:43:12 - INFO - __main__ - Step 118953: {'lr': 5.235721117277526e-05, 'samples': 22838976, 'steps': 118952, 'loss/train': 1.1738320589065552} 08/31/2021 10:43:12 - INFO - __main__ - Step 118954: {'lr': 5.2353961525263895e-05, 'samples': 22839168, 'steps': 118953, 'loss/train': 1.686322808265686} 08/31/2021 10:43:14 - INFO - __main__ - Step 118955: {'lr': 5.23507119668088e-05, 'samples': 22839360, 'steps': 118954, 'loss/train': 1.0189294815063477} 08/31/2021 10:43:15 - INFO - __main__ - Step 118956: {'lr': 5.23474624974114e-05, 'samples': 22839552, 'steps': 118955, 'loss/train': 1.00192129611969} 08/31/2021 10:43:15 - INFO - __main__ - Step 118957: {'lr': 5.234421311707319e-05, 'samples': 22839744, 'steps': 118956, 'loss/train': 1.4028637409210205} 08/31/2021 10:43:15 - INFO - __main__ - Step 118958: {'lr': 5.234096382579565e-05, 'samples': 22839936, 'steps': 118957, 'loss/train': 1.6116329431533813} 08/31/2021 10:43:16 - INFO - __main__ - Step 118959: {'lr': 5.23377146235802e-05, 'samples': 22840128, 'steps': 118958, 'loss/train': 1.7253562211990356} 08/31/2021 10:43:16 - INFO - __main__ - Step 118960: {'lr': 5.233446551042834e-05, 'samples': 22840320, 'steps': 118959, 'loss/train': 0.028409132733941078} 08/31/2021 10:43:18 - INFO - __main__ - Step 118961: {'lr': 5.233121648634151e-05, 'samples': 22840512, 'steps': 118960, 'loss/train': 0.02314511127769947} 08/31/2021 10:43:19 - INFO - __main__ - Step 118962: {'lr': 5.232796755132119e-05, 'samples': 22840704, 'steps': 118961, 'loss/train': 1.4470678567886353} 08/31/2021 10:43:19 - INFO - __main__ - Step 118963: {'lr': 5.2324718705368814e-05, 'samples': 22840896, 'steps': 118962, 'loss/train': 1.1219545602798462} 08/31/2021 10:43:19 - INFO - __main__ - Step 118964: {'lr': 5.2321469948485965e-05, 'samples': 22841088, 'steps': 118963, 'loss/train': 0.38957902789115906} 08/31/2021 10:43:20 - INFO - __main__ - Step 118965: {'lr': 5.231822128067393e-05, 'samples': 22841280, 'steps': 118964, 'loss/train': 0.9153953194618225} 08/31/2021 10:43:20 - INFO - __main__ - Step 118966: {'lr': 5.231497270193425e-05, 'samples': 22841472, 'steps': 118965, 'loss/train': 1.243788242340088} 08/31/2021 10:43:22 - INFO - __main__ - Step 118967: {'lr': 5.23117242122684e-05, 'samples': 22841664, 'steps': 118966, 'loss/train': 1.2547022104263306} 08/31/2021 10:43:22 - INFO - __main__ - Step 118968: {'lr': 5.230847581167786e-05, 'samples': 22841856, 'steps': 118967, 'loss/train': 0.9477028846740723} 08/31/2021 10:43:22 - INFO - __main__ - Step 118969: {'lr': 5.2305227500164033e-05, 'samples': 22842048, 'steps': 118968, 'loss/train': 1.673216700553894} 08/31/2021 10:43:23 - INFO - __main__ - Step 118970: {'lr': 5.2301979277728426e-05, 'samples': 22842240, 'steps': 118969, 'loss/train': 1.2285523414611816} 08/31/2021 10:43:23 - INFO - __main__ - Step 118971: {'lr': 5.22987311443725e-05, 'samples': 22842432, 'steps': 118970, 'loss/train': 1.4384396076202393} 08/31/2021 10:43:24 - INFO - __main__ - Step 118972: {'lr': 5.229548310009774e-05, 'samples': 22842624, 'steps': 118971, 'loss/train': 0.4521726965904236} 08/31/2021 10:43:25 - INFO - __main__ - Step 118973: {'lr': 5.2292235144905555e-05, 'samples': 22842816, 'steps': 118972, 'loss/train': 0.6842027306556702} 08/31/2021 10:43:25 - INFO - __main__ - Step 118974: {'lr': 5.228898727879744e-05, 'samples': 22843008, 'steps': 118973, 'loss/train': 1.1360234022140503} 08/31/2021 10:43:26 - INFO - __main__ - Step 118975: {'lr': 5.228573950177487e-05, 'samples': 22843200, 'steps': 118974, 'loss/train': 0.6918262839317322} 08/31/2021 10:43:26 - INFO - __main__ - Step 118976: {'lr': 5.2282491813839286e-05, 'samples': 22843392, 'steps': 118975, 'loss/train': 1.4260776042938232} 08/31/2021 10:43:28 - INFO - __main__ - Step 118977: {'lr': 5.227924421499217e-05, 'samples': 22843584, 'steps': 118976, 'loss/train': 0.40319228172302246} 08/31/2021 10:43:28 - INFO - __main__ - Step 118978: {'lr': 5.227599670523503e-05, 'samples': 22843776, 'steps': 118977, 'loss/train': 1.0192657709121704} 08/31/2021 10:43:28 - INFO - __main__ - Step 118979: {'lr': 5.2272749284569236e-05, 'samples': 22843968, 'steps': 118978, 'loss/train': 0.785557210445404} 08/31/2021 10:43:29 - INFO - __main__ - Step 118980: {'lr': 5.226950195299626e-05, 'samples': 22844160, 'steps': 118979, 'loss/train': 1.178850769996643} 08/31/2021 10:43:29 - INFO - __main__ - Step 118981: {'lr': 5.22662547105176e-05, 'samples': 22844352, 'steps': 118980, 'loss/train': 0.6583003997802734} 08/31/2021 10:43:29 - INFO - __main__ - Step 118982: {'lr': 5.226300755713473e-05, 'samples': 22844544, 'steps': 118981, 'loss/train': 1.5081889629364014} 08/31/2021 10:43:31 - INFO - __main__ - Step 118983: {'lr': 5.225976049284908e-05, 'samples': 22844736, 'steps': 118982, 'loss/train': 0.646773636341095} 08/31/2021 10:43:32 - INFO - __main__ - Step 118984: {'lr': 5.225651351766214e-05, 'samples': 22844928, 'steps': 118983, 'loss/train': 1.578865647315979} 08/31/2021 10:43:32 - INFO - __main__ - Step 118985: {'lr': 5.225326663157534e-05, 'samples': 22845120, 'steps': 118984, 'loss/train': 0.9176813960075378} 08/31/2021 10:43:33 - INFO - __main__ - Step 118986: {'lr': 5.2250019834590184e-05, 'samples': 22845312, 'steps': 118985, 'loss/train': 0.04862213879823685} 08/31/2021 10:43:33 - INFO - __main__ - Step 118987: {'lr': 5.224677312670814e-05, 'samples': 22845504, 'steps': 118986, 'loss/train': 1.2399803400039673} 08/31/2021 10:43:35 - INFO - __main__ - Step 118988: {'lr': 5.2243526507930625e-05, 'samples': 22845696, 'steps': 118987, 'loss/train': 0.988070547580719} 08/31/2021 10:43:36 - INFO - __main__ - Step 118989: {'lr': 5.224027997825911e-05, 'samples': 22845888, 'steps': 118988, 'loss/train': 1.518939733505249} 08/31/2021 10:43:36 - INFO - __main__ - Step 118990: {'lr': 5.22370335376951e-05, 'samples': 22846080, 'steps': 118989, 'loss/train': 1.0460950136184692} 08/31/2021 10:43:37 - INFO - __main__ - Step 118991: {'lr': 5.223378718624008e-05, 'samples': 22846272, 'steps': 118990, 'loss/train': 1.4791650772094727} 08/31/2021 10:43:37 - INFO - __main__ - Step 118992: {'lr': 5.2230540923895424e-05, 'samples': 22846464, 'steps': 118991, 'loss/train': 0.9989932775497437} 08/31/2021 10:43:37 - INFO - __main__ - Step 118993: {'lr': 5.2227294750662625e-05, 'samples': 22846656, 'steps': 118992, 'loss/train': 1.3920214176177979} 08/31/2021 10:43:38 - INFO - __main__ - Step 118994: {'lr': 5.222404866654312e-05, 'samples': 22846848, 'steps': 118993, 'loss/train': 1.7255074977874756} 08/31/2021 10:43:40 - INFO - __main__ - Step 118995: {'lr': 5.2220802671538446e-05, 'samples': 22847040, 'steps': 118994, 'loss/train': 0.5946338772773743} 08/31/2021 10:43:40 - INFO - __main__ - Step 118996: {'lr': 5.2217556765650014e-05, 'samples': 22847232, 'steps': 118995, 'loss/train': 1.681685209274292} 08/31/2021 10:43:40 - INFO - __main__ - Step 118997: {'lr': 5.2214310948879294e-05, 'samples': 22847424, 'steps': 118996, 'loss/train': 0.5348698496818542} 08/31/2021 10:43:41 - INFO - __main__ - Step 118998: {'lr': 5.2211065221227763e-05, 'samples': 22847616, 'steps': 118997, 'loss/train': 1.3465033769607544} 08/31/2021 10:43:41 - INFO - __main__ - Step 118999: {'lr': 5.220781958269688e-05, 'samples': 22847808, 'steps': 118998, 'loss/train': 0.4658348262310028} 08/31/2021 10:43:43 - INFO - __main__ - Step 119000: {'lr': 5.22045740332881e-05, 'samples': 22848000, 'steps': 118999, 'loss/train': 1.0929765701293945} 08/31/2021 10:43:43 - INFO - __main__ - Step 119001: {'lr': 5.220132857300286e-05, 'samples': 22848192, 'steps': 119000, 'loss/train': 1.4344791173934937} 08/31/2021 10:43:43 - INFO - __main__ - Step 119002: {'lr': 5.2198083201842664e-05, 'samples': 22848384, 'steps': 119001, 'loss/train': 1.4772744178771973} 08/31/2021 10:43:44 - INFO - __main__ - Step 119003: {'lr': 5.219483791980897e-05, 'samples': 22848576, 'steps': 119002, 'loss/train': 1.0627787113189697} 08/31/2021 10:43:44 - INFO - __main__ - Step 119004: {'lr': 5.219159272690321e-05, 'samples': 22848768, 'steps': 119003, 'loss/train': 0.9922392964363098} 08/31/2021 10:43:45 - INFO - __main__ - Step 119005: {'lr': 5.218834762312696e-05, 'samples': 22848960, 'steps': 119004, 'loss/train': 3.5899462699890137} 08/31/2021 10:43:46 - INFO - __main__ - Step 119006: {'lr': 5.21851026084815e-05, 'samples': 22849152, 'steps': 119005, 'loss/train': 1.1895910501480103} 08/31/2021 10:43:47 - INFO - __main__ - Step 119007: {'lr': 5.21818576829684e-05, 'samples': 22849344, 'steps': 119006, 'loss/train': 0.5292574167251587} 08/31/2021 10:43:47 - INFO - __main__ - Step 119008: {'lr': 5.217861284658909e-05, 'samples': 22849536, 'steps': 119007, 'loss/train': 0.928546130657196} 08/31/2021 10:43:47 - INFO - __main__ - Step 119009: {'lr': 5.217536809934503e-05, 'samples': 22849728, 'steps': 119008, 'loss/train': 0.83601975440979} 08/31/2021 10:43:48 - INFO - __main__ - Step 119010: {'lr': 5.21721234412377e-05, 'samples': 22849920, 'steps': 119009, 'loss/train': 1.2294366359710693} 08/31/2021 10:43:49 - INFO - __main__ - Step 119011: {'lr': 5.2168878872268594e-05, 'samples': 22850112, 'steps': 119010, 'loss/train': 0.5629632472991943} 08/31/2021 10:43:50 - INFO - __main__ - Step 119012: {'lr': 5.21656343924391e-05, 'samples': 22850304, 'steps': 119011, 'loss/train': 1.2188349962234497} 08/31/2021 10:43:50 - INFO - __main__ - Step 119013: {'lr': 5.216239000175074e-05, 'samples': 22850496, 'steps': 119012, 'loss/train': 0.9562135338783264} 08/31/2021 10:43:51 - INFO - __main__ - Step 119014: {'lr': 5.215914570020494e-05, 'samples': 22850688, 'steps': 119013, 'loss/train': 1.1758754253387451} 08/31/2021 10:43:51 - INFO - __main__ - Step 119015: {'lr': 5.215590148780317e-05, 'samples': 22850880, 'steps': 119014, 'loss/train': 1.3145240545272827} 08/31/2021 10:43:52 - INFO - __main__ - Step 119016: {'lr': 5.2152657364547e-05, 'samples': 22851072, 'steps': 119015, 'loss/train': 0.42037853598594666} 08/31/2021 10:43:53 - INFO - __main__ - Step 119017: {'lr': 5.2149413330437685e-05, 'samples': 22851264, 'steps': 119016, 'loss/train': 1.3606964349746704} 08/31/2021 10:43:53 - INFO - __main__ - Step 119018: {'lr': 5.214616938547681e-05, 'samples': 22851456, 'steps': 119017, 'loss/train': 0.8394061326980591} 08/31/2021 10:43:54 - INFO - __main__ - Step 119019: {'lr': 5.2142925529665816e-05, 'samples': 22851648, 'steps': 119018, 'loss/train': 0.7972636222839355} 08/31/2021 10:43:54 - INFO - __main__ - Step 119020: {'lr': 5.2139681763006154e-05, 'samples': 22851840, 'steps': 119019, 'loss/train': 0.03906765207648277} 08/31/2021 10:43:55 - INFO - __main__ - Step 119021: {'lr': 5.213643808549931e-05, 'samples': 22852032, 'steps': 119020, 'loss/train': 1.3624545335769653} 08/31/2021 10:43:56 - INFO - __main__ - Step 119022: {'lr': 5.213319449714674e-05, 'samples': 22852224, 'steps': 119021, 'loss/train': 1.5206005573272705} 08/31/2021 10:43:56 - INFO - __main__ - Step 119023: {'lr': 5.212995099794987e-05, 'samples': 22852416, 'steps': 119022, 'loss/train': 0.564566433429718} 08/31/2021 10:43:57 - INFO - __main__ - Step 119024: {'lr': 5.2126707587910216e-05, 'samples': 22852608, 'steps': 119023, 'loss/train': 1.5750987529754639} 08/31/2021 10:43:57 - INFO - __main__ - Step 119025: {'lr': 5.2123464267029215e-05, 'samples': 22852800, 'steps': 119024, 'loss/train': 1.0026648044586182} 08/31/2021 10:43:57 - INFO - __main__ - Step 119026: {'lr': 5.212022103530834e-05, 'samples': 22852992, 'steps': 119025, 'loss/train': 1.2237809896469116} 08/31/2021 10:43:59 - INFO - __main__ - Step 119027: {'lr': 5.211697789274908e-05, 'samples': 22853184, 'steps': 119026, 'loss/train': 0.8088238835334778} 08/31/2021 10:44:00 - INFO - __main__ - Step 119028: {'lr': 5.2113734839352806e-05, 'samples': 22853376, 'steps': 119027, 'loss/train': 1.652016282081604} 08/31/2021 10:44:00 - INFO - __main__ - Step 119029: {'lr': 5.211049187512101e-05, 'samples': 22853568, 'steps': 119028, 'loss/train': 0.9889671206474304} 08/31/2021 10:44:01 - INFO - __main__ - Step 119030: {'lr': 5.21072490000552e-05, 'samples': 22853760, 'steps': 119029, 'loss/train': 0.7152194380760193} 08/31/2021 10:44:01 - INFO - __main__ - Step 119031: {'lr': 5.210400621415679e-05, 'samples': 22853952, 'steps': 119030, 'loss/train': 0.8871648907661438} 08/31/2021 10:44:02 - INFO - __main__ - Step 119032: {'lr': 5.210076351742726e-05, 'samples': 22854144, 'steps': 119031, 'loss/train': 0.9475904107093811} 08/31/2021 10:44:03 - INFO - __main__ - Step 119033: {'lr': 5.2097520909868076e-05, 'samples': 22854336, 'steps': 119032, 'loss/train': 1.4578860998153687} 08/31/2021 10:44:03 - INFO - __main__ - Step 119034: {'lr': 5.2094278391480705e-05, 'samples': 22854528, 'steps': 119033, 'loss/train': 1.2137997150421143} 08/31/2021 10:44:03 - INFO - __main__ - Step 119035: {'lr': 5.209103596226658e-05, 'samples': 22854720, 'steps': 119034, 'loss/train': 1.5073680877685547} 08/31/2021 10:44:04 - INFO - __main__ - Step 119036: {'lr': 5.208779362222721e-05, 'samples': 22854912, 'steps': 119035, 'loss/train': 1.167907476425171} 08/31/2021 10:44:05 - INFO - __main__ - Step 119037: {'lr': 5.208455137136406e-05, 'samples': 22855104, 'steps': 119036, 'loss/train': 1.098955512046814} 08/31/2021 10:44:06 - INFO - __main__ - Step 119038: {'lr': 5.208130920967852e-05, 'samples': 22855296, 'steps': 119037, 'loss/train': 0.9864731431007385} 08/31/2021 10:44:06 - INFO - __main__ - Step 119039: {'lr': 5.207806713717206e-05, 'samples': 22855488, 'steps': 119038, 'loss/train': 0.8472597599029541} 08/31/2021 10:44:07 - INFO - __main__ - Step 119040: {'lr': 5.207482515384618e-05, 'samples': 22855680, 'steps': 119039, 'loss/train': 1.6054567098617554} 08/31/2021 10:44:07 - INFO - __main__ - Step 119041: {'lr': 5.2071583259702346e-05, 'samples': 22855872, 'steps': 119040, 'loss/train': 0.6347429156303406} 08/31/2021 10:44:08 - INFO - __main__ - Step 119042: {'lr': 5.206834145474199e-05, 'samples': 22856064, 'steps': 119041, 'loss/train': 1.0276540517807007} 08/31/2021 10:44:09 - INFO - __main__ - Step 119043: {'lr': 5.206509973896656e-05, 'samples': 22856256, 'steps': 119042, 'loss/train': 1.2524890899658203} 08/31/2021 10:44:09 - INFO - __main__ - Step 119044: {'lr': 5.206185811237757e-05, 'samples': 22856448, 'steps': 119043, 'loss/train': 1.2155487537384033} 08/31/2021 10:44:10 - INFO - __main__ - Step 119045: {'lr': 5.205861657497646e-05, 'samples': 22856640, 'steps': 119044, 'loss/train': 1.2994846105575562} 08/31/2021 10:44:10 - INFO - __main__ - Step 119046: {'lr': 5.205537512676467e-05, 'samples': 22856832, 'steps': 119045, 'loss/train': 1.3114664554595947} 08/31/2021 10:44:11 - INFO - __main__ - Step 119047: {'lr': 5.2052133767743677e-05, 'samples': 22857024, 'steps': 119046, 'loss/train': 1.22025728225708} 08/31/2021 10:44:12 - INFO - __main__ - Step 119048: {'lr': 5.2048892497915e-05, 'samples': 22857216, 'steps': 119047, 'loss/train': 1.5463217496871948} 08/31/2021 10:44:12 - INFO - __main__ - Step 119049: {'lr': 5.204565131727995e-05, 'samples': 22857408, 'steps': 119048, 'loss/train': 2.50321888923645} 08/31/2021 10:44:13 - INFO - __main__ - Step 119050: {'lr': 5.204241022584011e-05, 'samples': 22857600, 'steps': 119049, 'loss/train': 1.4410070180892944} 08/31/2021 10:44:13 - INFO - __main__ - Step 119051: {'lr': 5.203916922359689e-05, 'samples': 22857792, 'steps': 119050, 'loss/train': 0.11826524883508682} 08/31/2021 10:44:13 - INFO - __main__ - Step 119052: {'lr': 5.203592831055176e-05, 'samples': 22857984, 'steps': 119051, 'loss/train': 0.3892602324485779} 08/31/2021 10:44:15 - INFO - __main__ - Step 119053: {'lr': 5.20326874867062e-05, 'samples': 22858176, 'steps': 119052, 'loss/train': 1.627959966659546} 08/31/2021 10:44:15 - INFO - __main__ - Step 119054: {'lr': 5.202944675206164e-05, 'samples': 22858368, 'steps': 119053, 'loss/train': 1.1097640991210938} 08/31/2021 10:44:16 - INFO - __main__ - Step 119055: {'lr': 5.2026206106619564e-05, 'samples': 22858560, 'steps': 119054, 'loss/train': 1.0513994693756104} 08/31/2021 10:44:16 - INFO - __main__ - Step 119056: {'lr': 5.202296555038144e-05, 'samples': 22858752, 'steps': 119055, 'loss/train': 0.8128591179847717} 08/31/2021 10:44:16 - INFO - __main__ - Step 119057: {'lr': 5.201972508334871e-05, 'samples': 22858944, 'steps': 119056, 'loss/train': 0.43857744336128235} 08/31/2021 10:44:18 - INFO - __main__ - Step 119058: {'lr': 5.201648470552281e-05, 'samples': 22859136, 'steps': 119057, 'loss/train': 1.3970868587493896} 08/31/2021 10:44:18 - INFO - __main__ - Step 119059: {'lr': 5.2013244416905306e-05, 'samples': 22859328, 'steps': 119058, 'loss/train': 0.45249274373054504} 08/31/2021 10:44:19 - INFO - __main__ - Step 119060: {'lr': 5.201000421749752e-05, 'samples': 22859520, 'steps': 119059, 'loss/train': 0.9087569713592529} 08/31/2021 10:44:19 - INFO - __main__ - Step 119061: {'lr': 5.200676410730096e-05, 'samples': 22859712, 'steps': 119060, 'loss/train': 1.0709701776504517} 08/31/2021 10:44:19 - INFO - __main__ - Step 119062: {'lr': 5.200352408631712e-05, 'samples': 22859904, 'steps': 119061, 'loss/train': 0.9311035871505737} 08/31/2021 10:44:21 - INFO - __main__ - Step 119063: {'lr': 5.200028415454741e-05, 'samples': 22860096, 'steps': 119062, 'loss/train': 1.5739507675170898} 08/31/2021 10:44:22 - INFO - __main__ - Step 119064: {'lr': 5.199704431199334e-05, 'samples': 22860288, 'steps': 119063, 'loss/train': 1.152087688446045} 08/31/2021 10:44:22 - INFO - __main__ - Step 119065: {'lr': 5.199380455865632e-05, 'samples': 22860480, 'steps': 119064, 'loss/train': 0.5030243992805481} 08/31/2021 10:44:22 - INFO - __main__ - Step 119066: {'lr': 5.199056489453785e-05, 'samples': 22860672, 'steps': 119065, 'loss/train': 0.8337456583976746} 08/31/2021 10:44:23 - INFO - __main__ - Step 119067: {'lr': 5.198732531963937e-05, 'samples': 22860864, 'steps': 119066, 'loss/train': 0.7613574266433716} 08/31/2021 10:44:23 - INFO - __main__ - Step 119068: {'lr': 5.1984085833962356e-05, 'samples': 22861056, 'steps': 119067, 'loss/train': 0.3714195489883423} 08/31/2021 10:44:25 - INFO - __main__ - Step 119069: {'lr': 5.198084643750825e-05, 'samples': 22861248, 'steps': 119068, 'loss/train': 0.04885781556367874} 08/31/2021 10:44:25 - INFO - __main__ - Step 119070: {'lr': 5.197760713027852e-05, 'samples': 22861440, 'steps': 119069, 'loss/train': 1.104561448097229} 08/31/2021 10:44:26 - INFO - __main__ - Step 119071: {'lr': 5.197436791227464e-05, 'samples': 22861632, 'steps': 119070, 'loss/train': 0.8107287287712097} 08/31/2021 10:44:26 - INFO - __main__ - Step 119072: {'lr': 5.197112878349811e-05, 'samples': 22861824, 'steps': 119071, 'loss/train': 0.6729891896247864} 08/31/2021 10:44:26 - INFO - __main__ - Step 119073: {'lr': 5.1967889743950255e-05, 'samples': 22862016, 'steps': 119072, 'loss/train': 0.8284180760383606} 08/31/2021 10:44:28 - INFO - __main__ - Step 119074: {'lr': 5.196465079363263e-05, 'samples': 22862208, 'steps': 119073, 'loss/train': 2.0262739658355713} 08/31/2021 10:44:29 - INFO - __main__ - Step 119075: {'lr': 5.1961411932546667e-05, 'samples': 22862400, 'steps': 119074, 'loss/train': 1.0140419006347656} 08/31/2021 10:44:29 - INFO - __main__ - Step 119076: {'lr': 5.1958173160693845e-05, 'samples': 22862592, 'steps': 119075, 'loss/train': 1.5339757204055786} 08/31/2021 10:44:30 - INFO - __main__ - Step 119077: {'lr': 5.1954934478075586e-05, 'samples': 22862784, 'steps': 119076, 'loss/train': 0.8876197934150696} 08/31/2021 10:44:30 - INFO - __main__ - Step 119078: {'lr': 5.195169588469342e-05, 'samples': 22862976, 'steps': 119077, 'loss/train': 1.0703200101852417} 08/31/2021 10:44:30 - INFO - __main__ - Step 119079: {'lr': 5.194845738054874e-05, 'samples': 22863168, 'steps': 119078, 'loss/train': 0.8880961537361145} 08/31/2021 10:44:32 - INFO - __main__ - Step 119080: {'lr': 5.1945218965643026e-05, 'samples': 22863360, 'steps': 119079, 'loss/train': 0.1666639745235443} 08/31/2021 10:44:32 - INFO - __main__ - Step 119081: {'lr': 5.194198063997774e-05, 'samples': 22863552, 'steps': 119080, 'loss/train': 0.9979128241539001} 08/31/2021 10:44:33 - INFO - __main__ - Step 119082: {'lr': 5.1938742403554366e-05, 'samples': 22863744, 'steps': 119081, 'loss/train': 1.0224406719207764} 08/31/2021 10:44:33 - INFO - __main__ - Step 119083: {'lr': 5.1935504256374303e-05, 'samples': 22863936, 'steps': 119082, 'loss/train': 0.028638986870646477} 08/31/2021 10:44:33 - INFO - __main__ - Step 119084: {'lr': 5.1932266198439075e-05, 'samples': 22864128, 'steps': 119083, 'loss/train': 1.3776193857192993} 08/31/2021 10:44:35 - INFO - __main__ - Step 119085: {'lr': 5.192902822975015e-05, 'samples': 22864320, 'steps': 119084, 'loss/train': 0.5479331016540527} 08/31/2021 10:44:35 - INFO - __main__ - Step 119086: {'lr': 5.192579035030892e-05, 'samples': 22864512, 'steps': 119085, 'loss/train': 1.0275628566741943} 08/31/2021 10:44:36 - INFO - __main__ - Step 119087: {'lr': 5.1922552560116825e-05, 'samples': 22864704, 'steps': 119086, 'loss/train': 0.9098184108734131} 08/31/2021 10:44:36 - INFO - __main__ - Step 119088: {'lr': 5.191931485917542e-05, 'samples': 22864896, 'steps': 119087, 'loss/train': 0.3717707395553589} 08/31/2021 10:44:36 - INFO - __main__ - Step 119089: {'lr': 5.191607724748609e-05, 'samples': 22865088, 'steps': 119088, 'loss/train': 0.7775671482086182} 08/31/2021 10:44:38 - INFO - __main__ - Step 119090: {'lr': 5.191283972505031e-05, 'samples': 22865280, 'steps': 119089, 'loss/train': 0.9440674781799316} 08/31/2021 10:44:38 - INFO - __main__ - Step 119091: {'lr': 5.1909602291869557e-05, 'samples': 22865472, 'steps': 119090, 'loss/train': 1.0912526845932007} 08/31/2021 10:44:39 - INFO - __main__ - Step 119092: {'lr': 5.190636494794529e-05, 'samples': 22865664, 'steps': 119091, 'loss/train': 1.519885540008545} 08/31/2021 10:44:39 - INFO - __main__ - Step 119093: {'lr': 5.190312769327896e-05, 'samples': 22865856, 'steps': 119092, 'loss/train': 1.3565781116485596} 08/31/2021 10:44:39 - INFO - __main__ - Step 119094: {'lr': 5.1899890527872004e-05, 'samples': 22866048, 'steps': 119093, 'loss/train': 0.03335343301296234} 08/31/2021 10:44:41 - INFO - __main__ - Step 119095: {'lr': 5.1896653451725895e-05, 'samples': 22866240, 'steps': 119094, 'loss/train': 1.5041590929031372} 08/31/2021 10:44:42 - INFO - __main__ - Step 119096: {'lr': 5.189341646484211e-05, 'samples': 22866432, 'steps': 119095, 'loss/train': 0.6052259802818298} 08/31/2021 10:44:42 - INFO - __main__ - Step 119097: {'lr': 5.1890179567222114e-05, 'samples': 22866624, 'steps': 119096, 'loss/train': 1.2679591178894043} 08/31/2021 10:44:42 - INFO - __main__ - Step 119098: {'lr': 5.188694275886732e-05, 'samples': 22866816, 'steps': 119097, 'loss/train': 0.8840165734291077} 08/31/2021 10:44:43 - INFO - __main__ - Step 119099: {'lr': 5.188370603977929e-05, 'samples': 22867008, 'steps': 119098, 'loss/train': 1.3454136848449707} 08/31/2021 10:44:44 - INFO - __main__ - Step 119100: {'lr': 5.188046940995933e-05, 'samples': 22867200, 'steps': 119099, 'loss/train': 0.9921559691429138} 08/31/2021 10:44:45 - INFO - __main__ - Step 119101: {'lr': 5.187723286940899e-05, 'samples': 22867392, 'steps': 119100, 'loss/train': 0.5626952052116394} 08/31/2021 10:44:45 - INFO - __main__ - Step 119102: {'lr': 5.1873996418129704e-05, 'samples': 22867584, 'steps': 119101, 'loss/train': 0.04244137927889824} 08/31/2021 10:44:46 - INFO - __main__ - Step 119103: {'lr': 5.187076005612293e-05, 'samples': 22867776, 'steps': 119102, 'loss/train': 0.6370061635971069} 08/31/2021 10:44:46 - INFO - __main__ - Step 119104: {'lr': 5.186752378339013e-05, 'samples': 22867968, 'steps': 119103, 'loss/train': 1.2528295516967773} 08/31/2021 10:44:47 - INFO - __main__ - Step 119105: {'lr': 5.186428759993278e-05, 'samples': 22868160, 'steps': 119104, 'loss/train': 0.769785463809967} 08/31/2021 10:44:48 - INFO - __main__ - Step 119106: {'lr': 5.1861051505752324e-05, 'samples': 22868352, 'steps': 119105, 'loss/train': 1.2119280099868774} 08/31/2021 10:44:48 - INFO - __main__ - Step 119107: {'lr': 5.185781550085023e-05, 'samples': 22868544, 'steps': 119106, 'loss/train': 1.3382495641708374} 08/31/2021 10:44:48 - INFO - __main__ - Step 119108: {'lr': 5.185457958522791e-05, 'samples': 22868736, 'steps': 119107, 'loss/train': 0.8043602108955383} 08/31/2021 10:44:49 - INFO - __main__ - Step 119109: {'lr': 5.185134375888689e-05, 'samples': 22868928, 'steps': 119108, 'loss/train': 1.1604089736938477} 08/31/2021 10:44:50 - INFO - __main__ - Step 119110: {'lr': 5.18481080218286e-05, 'samples': 22869120, 'steps': 119109, 'loss/train': 1.2632564306259155} 08/31/2021 10:44:51 - INFO - __main__ - Step 119111: {'lr': 5.184487237405447e-05, 'samples': 22869312, 'steps': 119110, 'loss/train': 1.532948613166809} 08/31/2021 10:44:51 - INFO - __main__ - Step 119112: {'lr': 5.184163681556606e-05, 'samples': 22869504, 'steps': 119111, 'loss/train': 1.5067107677459717} 08/31/2021 10:44:51 - INFO - __main__ - Step 119113: {'lr': 5.183840134636469e-05, 'samples': 22869696, 'steps': 119112, 'loss/train': 0.5208811163902283} 08/31/2021 10:44:52 - INFO - __main__ - Step 119114: {'lr': 5.183516596645188e-05, 'samples': 22869888, 'steps': 119113, 'loss/train': 0.8818439841270447} 08/31/2021 10:44:54 - INFO - __main__ - Step 119115: {'lr': 5.1831930675829086e-05, 'samples': 22870080, 'steps': 119114, 'loss/train': 1.2265342473983765} 08/31/2021 10:44:54 - INFO - __main__ - Step 119116: {'lr': 5.1828695474497754e-05, 'samples': 22870272, 'steps': 119115, 'loss/train': 1.5506548881530762} 08/31/2021 10:44:55 - INFO - __main__ - Step 119117: {'lr': 5.182546036245936e-05, 'samples': 22870464, 'steps': 119116, 'loss/train': 1.1791408061981201} 08/31/2021 10:44:55 - INFO - __main__ - Step 119118: {'lr': 5.1822225339715366e-05, 'samples': 22870656, 'steps': 119117, 'loss/train': 2.3576979637145996} 08/31/2021 10:44:55 - INFO - __main__ - Step 119119: {'lr': 5.181899040626722e-05, 'samples': 22870848, 'steps': 119118, 'loss/train': 2.1416304111480713} 08/31/2021 10:44:56 - INFO - __main__ - Step 119120: {'lr': 5.1815755562116376e-05, 'samples': 22871040, 'steps': 119119, 'loss/train': 1.2415889501571655} 08/31/2021 10:44:57 - INFO - __main__ - Step 119121: {'lr': 5.181252080726428e-05, 'samples': 22871232, 'steps': 119120, 'loss/train': 0.5074461698532104} 08/31/2021 10:44:58 - INFO - __main__ - Step 119122: {'lr': 5.18092861417124e-05, 'samples': 22871424, 'steps': 119121, 'loss/train': 1.0231820344924927} 08/31/2021 10:44:58 - INFO - __main__ - Step 119123: {'lr': 5.1806051565462226e-05, 'samples': 22871616, 'steps': 119122, 'loss/train': 0.9479652047157288} 08/31/2021 10:44:58 - INFO - __main__ - Step 119124: {'lr': 5.180281707851517e-05, 'samples': 22871808, 'steps': 119123, 'loss/train': 1.3805280923843384} 08/31/2021 10:44:59 - INFO - __main__ - Step 119125: {'lr': 5.1799582680872705e-05, 'samples': 22872000, 'steps': 119124, 'loss/train': 1.2102357149124146} 08/31/2021 10:45:00 - INFO - __main__ - Step 119126: {'lr': 5.1796348372536354e-05, 'samples': 22872192, 'steps': 119125, 'loss/train': 0.8917791843414307} 08/31/2021 10:45:01 - INFO - __main__ - Step 119127: {'lr': 5.179311415350746e-05, 'samples': 22872384, 'steps': 119126, 'loss/train': 1.649976372718811} 08/31/2021 10:45:01 - INFO - __main__ - Step 119128: {'lr': 5.178988002378751e-05, 'samples': 22872576, 'steps': 119127, 'loss/train': 1.0594862699508667} 08/31/2021 10:45:01 - INFO - __main__ - Step 119129: {'lr': 5.1786645983377984e-05, 'samples': 22872768, 'steps': 119128, 'loss/train': 0.7227675914764404} 08/31/2021 10:45:02 - INFO - __main__ - Step 119130: {'lr': 5.178341203228035e-05, 'samples': 22872960, 'steps': 119129, 'loss/train': 1.674564242362976} 08/31/2021 10:45:04 - INFO - __main__ - Step 119131: {'lr': 5.1780178170496046e-05, 'samples': 22873152, 'steps': 119130, 'loss/train': 1.5076061487197876} 08/31/2021 10:45:04 - INFO - __main__ - Step 119132: {'lr': 5.1776944398026524e-05, 'samples': 22873344, 'steps': 119131, 'loss/train': 1.0219603776931763} 08/31/2021 10:45:05 - INFO - __main__ - Step 119133: {'lr': 5.177371071487327e-05, 'samples': 22873536, 'steps': 119132, 'loss/train': 1.2903573513031006} 08/31/2021 10:45:05 - INFO - __main__ - Step 119134: {'lr': 5.1770477121037693e-05, 'samples': 22873728, 'steps': 119133, 'loss/train': 1.4183287620544434} 08/31/2021 10:45:05 - INFO - __main__ - Step 119135: {'lr': 5.1767243616521325e-05, 'samples': 22873920, 'steps': 119134, 'loss/train': 1.555715799331665} 08/31/2021 10:45:07 - INFO - __main__ - Step 119136: {'lr': 5.176401020132554e-05, 'samples': 22874112, 'steps': 119135, 'loss/train': 0.4047453701496124} 08/31/2021 10:45:07 - INFO - __main__ - Step 119137: {'lr': 5.176077687545186e-05, 'samples': 22874304, 'steps': 119136, 'loss/train': 0.9036926627159119} 08/31/2021 10:45:08 - INFO - __main__ - Step 119138: {'lr': 5.17575436389017e-05, 'samples': 22874496, 'steps': 119137, 'loss/train': 0.7561078071594238} 08/31/2021 10:45:08 - INFO - __main__ - Step 119139: {'lr': 5.1754310491676586e-05, 'samples': 22874688, 'steps': 119138, 'loss/train': 0.7846477031707764} 08/31/2021 10:45:08 - INFO - __main__ - Step 119140: {'lr': 5.175107743377788e-05, 'samples': 22874880, 'steps': 119139, 'loss/train': 0.47481855750083923} 08/31/2021 10:45:10 - INFO - __main__ - Step 119141: {'lr': 5.1747844465207056e-05, 'samples': 22875072, 'steps': 119140, 'loss/train': 0.7683652639389038} 08/31/2021 10:45:10 - INFO - __main__ - Step 119142: {'lr': 5.1744611585965605e-05, 'samples': 22875264, 'steps': 119141, 'loss/train': 1.2759729623794556} 08/31/2021 10:45:11 - INFO - __main__ - Step 119143: {'lr': 5.174137879605498e-05, 'samples': 22875456, 'steps': 119142, 'loss/train': 1.1007791757583618} 08/31/2021 10:45:11 - INFO - __main__ - Step 119144: {'lr': 5.173814609547661e-05, 'samples': 22875648, 'steps': 119143, 'loss/train': 0.26276129484176636} 08/31/2021 10:45:12 - INFO - __main__ - Step 119145: {'lr': 5.173491348423201e-05, 'samples': 22875840, 'steps': 119144, 'loss/train': 1.1513350009918213} 08/31/2021 10:45:13 - INFO - __main__ - Step 119146: {'lr': 5.173168096232256e-05, 'samples': 22876032, 'steps': 119145, 'loss/train': 1.3861478567123413} 08/31/2021 10:45:14 - INFO - __main__ - Step 119147: {'lr': 5.172844852974978e-05, 'samples': 22876224, 'steps': 119146, 'loss/train': 1.0528191328048706} 08/31/2021 10:45:14 - INFO - __main__ - Step 119148: {'lr': 5.17252161865151e-05, 'samples': 22876416, 'steps': 119147, 'loss/train': 1.6569688320159912} 08/31/2021 10:45:14 - INFO - __main__ - Step 119149: {'lr': 5.172198393261995e-05, 'samples': 22876608, 'steps': 119148, 'loss/train': 0.8522273302078247} 08/31/2021 10:45:15 - INFO - __main__ - Step 119150: {'lr': 5.1718751768065844e-05, 'samples': 22876800, 'steps': 119149, 'loss/train': 1.9058642387390137} 08/31/2021 10:45:15 - INFO - __main__ - Step 119151: {'lr': 5.171551969285421e-05, 'samples': 22876992, 'steps': 119150, 'loss/train': 0.7845999002456665} 08/31/2021 10:45:17 - INFO - __main__ - Step 119152: {'lr': 5.1712287706986547e-05, 'samples': 22877184, 'steps': 119151, 'loss/train': 0.9718448519706726} 08/31/2021 10:45:17 - INFO - __main__ - Step 119153: {'lr': 5.1709055810464203e-05, 'samples': 22877376, 'steps': 119152, 'loss/train': 0.847357451915741} 08/31/2021 10:45:17 - INFO - __main__ - Step 119154: {'lr': 5.170582400328872e-05, 'samples': 22877568, 'steps': 119153, 'loss/train': 1.0565812587738037} 08/31/2021 10:45:18 - INFO - __main__ - Step 119155: {'lr': 5.170259228546151e-05, 'samples': 22877760, 'steps': 119154, 'loss/train': 1.0440011024475098} 08/31/2021 10:45:18 - INFO - __main__ - Step 119156: {'lr': 5.1699360656984076e-05, 'samples': 22877952, 'steps': 119155, 'loss/train': 0.4262547791004181} 08/31/2021 10:45:20 - INFO - __main__ - Step 119157: {'lr': 5.169612911785782e-05, 'samples': 22878144, 'steps': 119156, 'loss/train': 0.21124382317066193} 08/31/2021 10:45:20 - INFO - __main__ - Step 119158: {'lr': 5.1692897668084247e-05, 'samples': 22878336, 'steps': 119157, 'loss/train': 0.46224772930145264} 08/31/2021 10:45:20 - INFO - __main__ - Step 119159: {'lr': 5.1689666307664804e-05, 'samples': 22878528, 'steps': 119158, 'loss/train': 1.2454147338867188} 08/31/2021 10:45:21 - INFO - __main__ - Step 119160: {'lr': 5.168643503660092e-05, 'samples': 22878720, 'steps': 119159, 'loss/train': 0.7034447193145752} 08/31/2021 10:45:21 - INFO - __main__ - Step 119161: {'lr': 5.1683203854894086e-05, 'samples': 22878912, 'steps': 119160, 'loss/train': 0.9659950137138367} 08/31/2021 10:45:23 - INFO - __main__ - Step 119162: {'lr': 5.167997276254571e-05, 'samples': 22879104, 'steps': 119161, 'loss/train': 1.4405070543289185} 08/31/2021 10:45:23 - INFO - __main__ - Step 119163: {'lr': 5.1676741759557305e-05, 'samples': 22879296, 'steps': 119162, 'loss/train': 0.9989834427833557} 08/31/2021 10:45:23 - INFO - __main__ - Step 119164: {'lr': 5.167351084593028e-05, 'samples': 22879488, 'steps': 119163, 'loss/train': 1.216289758682251} 08/31/2021 10:45:24 - INFO - __main__ - Step 119165: {'lr': 5.1670280021666125e-05, 'samples': 22879680, 'steps': 119164, 'loss/train': 1.2354645729064941} 08/31/2021 10:45:24 - INFO - __main__ - Step 119166: {'lr': 5.166704928676636e-05, 'samples': 22879872, 'steps': 119165, 'loss/train': 0.9271748065948486} 08/31/2021 10:45:26 - INFO - __main__ - Step 119167: {'lr': 5.166381864123226e-05, 'samples': 22880064, 'steps': 119166, 'loss/train': 1.226781964302063} 08/31/2021 10:45:26 - INFO - __main__ - Step 119168: {'lr': 5.166058808506541e-05, 'samples': 22880256, 'steps': 119167, 'loss/train': 0.928762674331665} 08/31/2021 10:45:26 - INFO - __main__ - Step 119169: {'lr': 5.165735761826723e-05, 'samples': 22880448, 'steps': 119168, 'loss/train': 0.9443702101707458} 08/31/2021 10:45:27 - INFO - __main__ - Step 119170: {'lr': 5.165412724083918e-05, 'samples': 22880640, 'steps': 119169, 'loss/train': 0.5438203811645508} 08/31/2021 10:45:27 - INFO - __main__ - Step 119171: {'lr': 5.165089695278272e-05, 'samples': 22880832, 'steps': 119170, 'loss/train': 0.9743282198905945} 08/31/2021 10:45:29 - INFO - __main__ - Step 119172: {'lr': 5.164766675409932e-05, 'samples': 22881024, 'steps': 119171, 'loss/train': 0.5494946837425232} 08/31/2021 10:45:29 - INFO - __main__ - Step 119173: {'lr': 5.16444366447904e-05, 'samples': 22881216, 'steps': 119172, 'loss/train': 0.8192653059959412} 08/31/2021 10:45:29 - INFO - __main__ - Step 119174: {'lr': 5.1641206624857465e-05, 'samples': 22881408, 'steps': 119173, 'loss/train': 1.0787619352340698} 08/31/2021 10:45:30 - INFO - __main__ - Step 119175: {'lr': 5.1637976694301926e-05, 'samples': 22881600, 'steps': 119174, 'loss/train': 0.45610207319259644} 08/31/2021 10:45:30 - INFO - __main__ - Step 119176: {'lr': 5.163474685312525e-05, 'samples': 22881792, 'steps': 119175, 'loss/train': 0.9878200888633728} 08/31/2021 10:45:31 - INFO - __main__ - Step 119177: {'lr': 5.163151710132888e-05, 'samples': 22881984, 'steps': 119176, 'loss/train': 1.3199461698532104} 08/31/2021 10:45:32 - INFO - __main__ - Step 119178: {'lr': 5.162828743891432e-05, 'samples': 22882176, 'steps': 119177, 'loss/train': 0.6767511367797852} 08/31/2021 10:45:32 - INFO - __main__ - Step 119179: {'lr': 5.162505786588303e-05, 'samples': 22882368, 'steps': 119178, 'loss/train': 0.9393371939659119} 08/31/2021 10:45:33 - INFO - __main__ - Step 119180: {'lr': 5.162182838223639e-05, 'samples': 22882560, 'steps': 119179, 'loss/train': 0.6275473833084106} 08/31/2021 10:45:33 - INFO - __main__ - Step 119181: {'lr': 5.161859898797586e-05, 'samples': 22882752, 'steps': 119180, 'loss/train': 1.4027857780456543} 08/31/2021 10:45:35 - INFO - __main__ - Step 119182: {'lr': 5.161536968310296e-05, 'samples': 22882944, 'steps': 119181, 'loss/train': 0.6703678965568542} 08/31/2021 10:45:36 - INFO - __main__ - Step 119183: {'lr': 5.161214046761908e-05, 'samples': 22883136, 'steps': 119182, 'loss/train': 0.8759701251983643} 08/31/2021 10:45:36 - INFO - __main__ - Step 119184: {'lr': 5.1608911341525734e-05, 'samples': 22883328, 'steps': 119183, 'loss/train': 0.7664788365364075} 08/31/2021 10:45:36 - INFO - __main__ - Step 119185: {'lr': 5.1605682304824346e-05, 'samples': 22883520, 'steps': 119184, 'loss/train': 1.0000346899032593} 08/31/2021 10:45:37 - INFO - __main__ - Step 119186: {'lr': 5.160245335751637e-05, 'samples': 22883712, 'steps': 119185, 'loss/train': 1.199544072151184} 08/31/2021 10:45:38 - INFO - __main__ - Step 119187: {'lr': 5.159922449960327e-05, 'samples': 22883904, 'steps': 119186, 'loss/train': 0.7299966216087341} 08/31/2021 10:45:39 - INFO - __main__ - Step 119188: {'lr': 5.15959957310865e-05, 'samples': 22884096, 'steps': 119187, 'loss/train': 0.8156551122665405} 08/31/2021 10:45:39 - INFO - __main__ - Step 119189: {'lr': 5.1592767051967526e-05, 'samples': 22884288, 'steps': 119188, 'loss/train': 0.3756020665168762} 08/31/2021 10:45:40 - INFO - __main__ - Step 119190: {'lr': 5.158953846224776e-05, 'samples': 22884480, 'steps': 119189, 'loss/train': 1.1162985563278198} 08/31/2021 10:45:40 - INFO - __main__ - Step 119191: {'lr': 5.15863099619287e-05, 'samples': 22884672, 'steps': 119190, 'loss/train': 1.0790565013885498} 08/31/2021 10:45:40 - INFO - __main__ - Step 119192: {'lr': 5.15830815510118e-05, 'samples': 22884864, 'steps': 119191, 'loss/train': 0.7414067387580872} 08/31/2021 10:45:42 - INFO - __main__ - Step 119193: {'lr': 5.157985322949857e-05, 'samples': 22885056, 'steps': 119192, 'loss/train': 1.450055480003357} 08/31/2021 10:45:42 - INFO - __main__ - Step 119194: {'lr': 5.15766249973903e-05, 'samples': 22885248, 'steps': 119193, 'loss/train': 0.8618518114089966} 08/31/2021 10:45:43 - INFO - __main__ - Step 119195: {'lr': 5.1573396854688566e-05, 'samples': 22885440, 'steps': 119194, 'loss/train': 2.043740749359131} 08/31/2021 10:45:43 - INFO - __main__ - Step 119196: {'lr': 5.157016880139479e-05, 'samples': 22885632, 'steps': 119195, 'loss/train': 1.4987373352050781} 08/31/2021 10:45:43 - INFO - __main__ - Step 119197: {'lr': 5.156694083751043e-05, 'samples': 22885824, 'steps': 119196, 'loss/train': 0.9626712203025818} 08/31/2021 10:45:45 - INFO - __main__ - Step 119198: {'lr': 5.1563712963036944e-05, 'samples': 22886016, 'steps': 119197, 'loss/train': 0.4098191261291504} 08/31/2021 10:45:46 - INFO - __main__ - Step 119199: {'lr': 5.156048517797579e-05, 'samples': 22886208, 'steps': 119198, 'loss/train': 1.2720866203308105} 08/31/2021 10:45:46 - INFO - __main__ - Step 119200: {'lr': 5.155725748232842e-05, 'samples': 22886400, 'steps': 119199, 'loss/train': 0.9331333637237549} 08/31/2021 10:45:46 - INFO - __main__ - Step 119201: {'lr': 5.155402987609628e-05, 'samples': 22886592, 'steps': 119200, 'loss/train': 1.0391308069229126} 08/31/2021 10:45:47 - INFO - __main__ - Step 119202: {'lr': 5.155080235928086e-05, 'samples': 22886784, 'steps': 119201, 'loss/train': 0.11931726336479187} 08/31/2021 10:45:47 - INFO - __main__ - Step 119203: {'lr': 5.1547574931883554e-05, 'samples': 22886976, 'steps': 119202, 'loss/train': 1.5049728155136108} 08/31/2021 10:45:48 - INFO - __main__ - Step 119204: {'lr': 5.154434759390586e-05, 'samples': 22887168, 'steps': 119203, 'loss/train': 1.1859463453292847} 08/31/2021 10:45:49 - INFO - __main__ - Step 119205: {'lr': 5.154112034534922e-05, 'samples': 22887360, 'steps': 119204, 'loss/train': 1.2699980735778809} 08/31/2021 10:45:49 - INFO - __main__ - Step 119206: {'lr': 5.153789318621516e-05, 'samples': 22887552, 'steps': 119205, 'loss/train': 0.5345496535301208} 08/31/2021 10:45:50 - INFO - __main__ - Step 119207: {'lr': 5.153466611650498e-05, 'samples': 22887744, 'steps': 119206, 'loss/train': 1.3841291666030884} 08/31/2021 10:45:50 - INFO - __main__ - Step 119208: {'lr': 5.1531439136220244e-05, 'samples': 22887936, 'steps': 119207, 'loss/train': 1.038651943206787} 08/31/2021 10:45:51 - INFO - __main__ - Step 119209: {'lr': 5.1528212245362363e-05, 'samples': 22888128, 'steps': 119208, 'loss/train': 1.0176823139190674} 08/31/2021 10:45:52 - INFO - __main__ - Step 119210: {'lr': 5.1524985443932805e-05, 'samples': 22888320, 'steps': 119209, 'loss/train': 1.348872423171997} 08/31/2021 10:45:52 - INFO - __main__ - Step 119211: {'lr': 5.1521758731933045e-05, 'samples': 22888512, 'steps': 119210, 'loss/train': 1.5654635429382324} 08/31/2021 10:45:53 - INFO - __main__ - Step 119212: {'lr': 5.1518532109364495e-05, 'samples': 22888704, 'steps': 119211, 'loss/train': 1.1545891761779785} 08/31/2021 10:45:53 - INFO - __main__ - Step 119213: {'lr': 5.151530557622863e-05, 'samples': 22888896, 'steps': 119212, 'loss/train': 1.750504970550537} 08/31/2021 10:45:55 - INFO - __main__ - Step 119214: {'lr': 5.1512079132526924e-05, 'samples': 22889088, 'steps': 119213, 'loss/train': 1.1995619535446167} 08/31/2021 10:45:55 - INFO - __main__ - Step 119215: {'lr': 5.150885277826078e-05, 'samples': 22889280, 'steps': 119214, 'loss/train': 1.0097639560699463} 08/31/2021 10:45:55 - INFO - __main__ - Step 119216: {'lr': 5.150562651343171e-05, 'samples': 22889472, 'steps': 119215, 'loss/train': 0.9098774790763855} 08/31/2021 10:45:56 - INFO - __main__ - Step 119217: {'lr': 5.1502400338041156e-05, 'samples': 22889664, 'steps': 119216, 'loss/train': 1.0368753671646118} 08/31/2021 10:45:56 - INFO - __main__ - Step 119218: {'lr': 5.149917425209052e-05, 'samples': 22889856, 'steps': 119217, 'loss/train': 0.9298161268234253} 08/31/2021 10:45:58 - INFO - __main__ - Step 119219: {'lr': 5.1495948255581323e-05, 'samples': 22890048, 'steps': 119218, 'loss/train': 0.946635901927948} 08/31/2021 10:45:58 - INFO - __main__ - Step 119220: {'lr': 5.149272234851504e-05, 'samples': 22890240, 'steps': 119219, 'loss/train': 0.39643383026123047} 08/31/2021 10:45:58 - INFO - __main__ - Step 119221: {'lr': 5.148949653089302e-05, 'samples': 22890432, 'steps': 119220, 'loss/train': 0.9605941772460938} 08/31/2021 10:45:59 - INFO - __main__ - Step 119222: {'lr': 5.148627080271675e-05, 'samples': 22890624, 'steps': 119221, 'loss/train': 1.1108064651489258} 08/31/2021 10:45:59 - INFO - __main__ - Step 119223: {'lr': 5.148304516398772e-05, 'samples': 22890816, 'steps': 119222, 'loss/train': 0.9601142406463623} 08/31/2021 10:46:00 - INFO - __main__ - Step 119224: {'lr': 5.1479819614707355e-05, 'samples': 22891008, 'steps': 119223, 'loss/train': 1.1257187128067017} 08/31/2021 10:46:01 - INFO - __main__ - Step 119225: {'lr': 5.1476594154877126e-05, 'samples': 22891200, 'steps': 119224, 'loss/train': 1.2451251745224} 08/31/2021 10:46:01 - INFO - __main__ - Step 119226: {'lr': 5.1473368784498483e-05, 'samples': 22891392, 'steps': 119225, 'loss/train': 3.2014777660369873} 08/31/2021 10:46:02 - INFO - __main__ - Step 119227: {'lr': 5.1470143503572876e-05, 'samples': 22891584, 'steps': 119226, 'loss/train': 1.0857161283493042} 08/31/2021 10:46:02 - INFO - __main__ - Step 119228: {'lr': 5.146691831210176e-05, 'samples': 22891776, 'steps': 119227, 'loss/train': 2.476310968399048} 08/31/2021 10:46:02 - INFO - __main__ - Step 119229: {'lr': 5.1463693210086594e-05, 'samples': 22891968, 'steps': 119228, 'loss/train': 1.6896110773086548} 08/31/2021 10:46:04 - INFO - __main__ - Step 119230: {'lr': 5.146046819752881e-05, 'samples': 22892160, 'steps': 119229, 'loss/train': 1.0717054605484009} 08/31/2021 10:46:05 - INFO - __main__ - Step 119231: {'lr': 5.145724327442988e-05, 'samples': 22892352, 'steps': 119230, 'loss/train': 1.1380771398544312} 08/31/2021 10:46:05 - INFO - __main__ - Step 119232: {'lr': 5.145401844079126e-05, 'samples': 22892544, 'steps': 119231, 'loss/train': 0.7840991616249084} 08/31/2021 10:46:05 - INFO - __main__ - Step 119233: {'lr': 5.145079369661443e-05, 'samples': 22892736, 'steps': 119232, 'loss/train': 1.2733104228973389} 08/31/2021 10:46:06 - INFO - __main__ - Step 119234: {'lr': 5.144756904190076e-05, 'samples': 22892928, 'steps': 119233, 'loss/train': 1.4011660814285278} 08/31/2021 10:46:07 - INFO - __main__ - Step 119235: {'lr': 5.144434447665178e-05, 'samples': 22893120, 'steps': 119234, 'loss/train': 0.8244883418083191} 08/31/2021 10:46:08 - INFO - __main__ - Step 119236: {'lr': 5.1441120000868865e-05, 'samples': 22893312, 'steps': 119235, 'loss/train': 1.8300813436508179} 08/31/2021 10:46:08 - INFO - __main__ - Step 119237: {'lr': 5.143789561455356e-05, 'samples': 22893504, 'steps': 119236, 'loss/train': 1.2223703861236572} 08/31/2021 10:46:08 - INFO - __main__ - Step 119238: {'lr': 5.1434671317707264e-05, 'samples': 22893696, 'steps': 119237, 'loss/train': 1.0352935791015625} 08/31/2021 10:46:09 - INFO - __main__ - Step 119239: {'lr': 5.1431447110331434e-05, 'samples': 22893888, 'steps': 119238, 'loss/train': 1.8301483392715454} 08/31/2021 10:46:11 - INFO - __main__ - Step 119240: {'lr': 5.1428222992427525e-05, 'samples': 22894080, 'steps': 119239, 'loss/train': 1.0944212675094604} 08/31/2021 10:46:11 - INFO - __main__ - Step 119241: {'lr': 5.1424998963996994e-05, 'samples': 22894272, 'steps': 119240, 'loss/train': 0.15613295137882233} 08/31/2021 10:46:12 - INFO - __main__ - Step 119242: {'lr': 5.1421775025041304e-05, 'samples': 22894464, 'steps': 119241, 'loss/train': 1.1831074953079224} 08/31/2021 10:46:12 - INFO - __main__ - Step 119243: {'lr': 5.1418551175561905e-05, 'samples': 22894656, 'steps': 119242, 'loss/train': 1.1499662399291992} 08/31/2021 10:46:12 - INFO - __main__ - Step 119244: {'lr': 5.1415327415560235e-05, 'samples': 22894848, 'steps': 119243, 'loss/train': 1.5666567087173462} 08/31/2021 10:46:14 - INFO - __main__ - Step 119245: {'lr': 5.141210374503774e-05, 'samples': 22895040, 'steps': 119244, 'loss/train': 1.1939163208007812} 08/31/2021 10:46:14 - INFO - __main__ - Step 119246: {'lr': 5.140888016399592e-05, 'samples': 22895232, 'steps': 119245, 'loss/train': 1.4084469079971313} 08/31/2021 10:46:15 - INFO - __main__ - Step 119247: {'lr': 5.140565667243624e-05, 'samples': 22895424, 'steps': 119246, 'loss/train': 1.2351809740066528} 08/31/2021 10:46:15 - INFO - __main__ - Step 119248: {'lr': 5.140243327036004e-05, 'samples': 22895616, 'steps': 119247, 'loss/train': 1.5737396478652954} 08/31/2021 10:46:16 - INFO - __main__ - Step 119249: {'lr': 5.1399209957768836e-05, 'samples': 22895808, 'steps': 119248, 'loss/train': 1.1244145631790161} 08/31/2021 10:46:16 - INFO - __main__ - Step 119250: {'lr': 5.139598673466409e-05, 'samples': 22896000, 'steps': 119249, 'loss/train': 0.7158752679824829} 08/31/2021 10:46:17 - INFO - __main__ - Step 119251: {'lr': 5.1392763601047247e-05, 'samples': 22896192, 'steps': 119250, 'loss/train': 1.0428378582000732} 08/31/2021 10:46:18 - INFO - __main__ - Step 119252: {'lr': 5.138954055691975e-05, 'samples': 22896384, 'steps': 119251, 'loss/train': 1.182267427444458} 08/31/2021 10:46:18 - INFO - __main__ - Step 119253: {'lr': 5.1386317602283075e-05, 'samples': 22896576, 'steps': 119252, 'loss/train': 0.07206922769546509} 08/31/2021 10:46:18 - INFO - __main__ - Step 119254: {'lr': 5.1383094737138645e-05, 'samples': 22896768, 'steps': 119253, 'loss/train': 0.8803378343582153} 08/31/2021 10:46:19 - INFO - __main__ - Step 119255: {'lr': 5.137987196148794e-05, 'samples': 22896960, 'steps': 119254, 'loss/train': 0.9550396203994751} 08/31/2021 10:46:20 - INFO - __main__ - Step 119256: {'lr': 5.1376649275332396e-05, 'samples': 22897152, 'steps': 119255, 'loss/train': 1.0761597156524658} 08/31/2021 10:46:21 - INFO - __main__ - Step 119257: {'lr': 5.137342667867345e-05, 'samples': 22897344, 'steps': 119256, 'loss/train': 0.5941885113716125} 08/31/2021 10:46:21 - INFO - __main__ - Step 119258: {'lr': 5.1370204171512614e-05, 'samples': 22897536, 'steps': 119257, 'loss/train': 1.2493834495544434} 08/31/2021 10:46:21 - INFO - __main__ - Step 119259: {'lr': 5.1366981753851265e-05, 'samples': 22897728, 'steps': 119258, 'loss/train': 1.1197117567062378} 08/31/2021 10:46:22 - INFO - __main__ - Step 119260: {'lr': 5.136375942569096e-05, 'samples': 22897920, 'steps': 119259, 'loss/train': 1.8151838779449463} 08/31/2021 10:46:23 - INFO - __main__ - Step 119261: {'lr': 5.136053718703304e-05, 'samples': 22898112, 'steps': 119260, 'loss/train': 0.9960299730300903} 08/31/2021 10:46:24 - INFO - __main__ - Step 119262: {'lr': 5.1357315037878966e-05, 'samples': 22898304, 'steps': 119261, 'loss/train': 0.5491089820861816} 08/31/2021 10:46:24 - INFO - __main__ - Step 119263: {'lr': 5.135409297823024e-05, 'samples': 22898496, 'steps': 119262, 'loss/train': 0.7386285066604614} 08/31/2021 10:46:24 - INFO - __main__ - Step 119264: {'lr': 5.1350871008088274e-05, 'samples': 22898688, 'steps': 119263, 'loss/train': 0.668735921382904} 08/31/2021 10:46:25 - INFO - __main__ - Step 119265: {'lr': 5.134764912745457e-05, 'samples': 22898880, 'steps': 119264, 'loss/train': 1.204432725906372} 08/31/2021 10:46:26 - INFO - __main__ - Step 119266: {'lr': 5.1344427336330515e-05, 'samples': 22899072, 'steps': 119265, 'loss/train': 1.2093898057937622} 08/31/2021 10:46:27 - INFO - __main__ - Step 119267: {'lr': 5.1341205634717616e-05, 'samples': 22899264, 'steps': 119266, 'loss/train': 1.4566880464553833} 08/31/2021 10:46:27 - INFO - __main__ - Step 119268: {'lr': 5.13379840226173e-05, 'samples': 22899456, 'steps': 119267, 'loss/train': 1.4577200412750244} 08/31/2021 10:46:27 - INFO - __main__ - Step 119269: {'lr': 5.1334762500031024e-05, 'samples': 22899648, 'steps': 119268, 'loss/train': 1.1197267770767212} 08/31/2021 10:46:28 - INFO - __main__ - Step 119270: {'lr': 5.133154106696025e-05, 'samples': 22899840, 'steps': 119269, 'loss/train': 0.38108476996421814} 08/31/2021 10:46:30 - INFO - __main__ - Step 119271: {'lr': 5.13283197234064e-05, 'samples': 22900032, 'steps': 119270, 'loss/train': 0.9212985634803772} 08/31/2021 10:46:30 - INFO - __main__ - Step 119272: {'lr': 5.132509846937094e-05, 'samples': 22900224, 'steps': 119271, 'loss/train': 1.3780843019485474} 08/31/2021 10:46:30 - INFO - __main__ - Step 119273: {'lr': 5.132187730485541e-05, 'samples': 22900416, 'steps': 119272, 'loss/train': 0.017031433060765266} 08/31/2021 10:46:31 - INFO - __main__ - Step 119274: {'lr': 5.131865622986112e-05, 'samples': 22900608, 'steps': 119273, 'loss/train': 0.5784618854522705} 08/31/2021 10:46:31 - INFO - __main__ - Step 119275: {'lr': 5.131543524438956e-05, 'samples': 22900800, 'steps': 119274, 'loss/train': 1.0755937099456787} 08/31/2021 10:46:31 - INFO - __main__ - Step 119276: {'lr': 5.1312214348442186e-05, 'samples': 22900992, 'steps': 119275, 'loss/train': 1.1690409183502197} 08/31/2021 10:46:32 - INFO - __main__ - Step 119277: {'lr': 5.130899354202048e-05, 'samples': 22901184, 'steps': 119276, 'loss/train': 1.341394305229187} 08/31/2021 10:46:33 - INFO - __main__ - Step 119278: {'lr': 5.130577282512586e-05, 'samples': 22901376, 'steps': 119277, 'loss/train': 1.301538348197937} 08/31/2021 10:46:34 - INFO - __main__ - Step 119279: {'lr': 5.130255219775981e-05, 'samples': 22901568, 'steps': 119278, 'loss/train': 1.2397929430007935} 08/31/2021 10:46:34 - INFO - __main__ - Step 119280: {'lr': 5.129933165992376e-05, 'samples': 22901760, 'steps': 119279, 'loss/train': 0.5990691184997559} 08/31/2021 10:46:34 - INFO - __main__ - Step 119281: {'lr': 5.129611121161914e-05, 'samples': 22901952, 'steps': 119280, 'loss/train': 0.9427964687347412} 08/31/2021 10:46:35 - INFO - __main__ - Step 119282: {'lr': 5.129289085284747e-05, 'samples': 22902144, 'steps': 119281, 'loss/train': 1.3333503007888794} 08/31/2021 10:46:37 - INFO - __main__ - Step 119283: {'lr': 5.128967058361014e-05, 'samples': 22902336, 'steps': 119282, 'loss/train': 0.9551953673362732} 08/31/2021 10:46:37 - INFO - __main__ - Step 119284: {'lr': 5.128645040390867e-05, 'samples': 22902528, 'steps': 119283, 'loss/train': 1.2545232772827148} 08/31/2021 10:46:37 - INFO - __main__ - Step 119285: {'lr': 5.1283230313744405e-05, 'samples': 22902720, 'steps': 119284, 'loss/train': 1.0011186599731445} 08/31/2021 10:46:38 - INFO - __main__ - Step 119286: {'lr': 5.128001031311885e-05, 'samples': 22902912, 'steps': 119285, 'loss/train': 2.2993783950805664} 08/31/2021 10:46:38 - INFO - __main__ - Step 119287: {'lr': 5.127679040203345e-05, 'samples': 22903104, 'steps': 119286, 'loss/train': 1.298100471496582} 08/31/2021 10:46:39 - INFO - __main__ - Step 119288: {'lr': 5.127357058048968e-05, 'samples': 22903296, 'steps': 119287, 'loss/train': 1.1677827835083008} 08/31/2021 10:46:40 - INFO - __main__ - Step 119289: {'lr': 5.127035084848894e-05, 'samples': 22903488, 'steps': 119288, 'loss/train': 0.7779311537742615} 08/31/2021 10:46:40 - INFO - __main__ - Step 119290: {'lr': 5.126713120603274e-05, 'samples': 22903680, 'steps': 119289, 'loss/train': 1.4972074031829834} 08/31/2021 10:46:41 - INFO - __main__ - Step 119291: {'lr': 5.12639116531225e-05, 'samples': 22903872, 'steps': 119290, 'loss/train': 0.2932761013507843} 08/31/2021 10:46:41 - INFO - __main__ - Step 119292: {'lr': 5.126069218975965e-05, 'samples': 22904064, 'steps': 119291, 'loss/train': 0.9016075730323792} 08/31/2021 10:46:42 - INFO - __main__ - Step 119293: {'lr': 5.12574728159457e-05, 'samples': 22904256, 'steps': 119292, 'loss/train': 0.9565272331237793} 08/31/2021 10:46:44 - INFO - __main__ - Step 119294: {'lr': 5.125425353168203e-05, 'samples': 22904448, 'steps': 119293, 'loss/train': 1.4504464864730835} 08/31/2021 10:46:45 - INFO - __main__ - Step 119295: {'lr': 5.125103433697023e-05, 'samples': 22904640, 'steps': 119294, 'loss/train': 0.12161831557750702} 08/31/2021 10:46:45 - INFO - __main__ - Step 119296: {'lr': 5.124781523181155e-05, 'samples': 22904832, 'steps': 119295, 'loss/train': 1.236981749534607} 08/31/2021 10:46:45 - INFO - __main__ - Step 119297: {'lr': 5.1244596216207555e-05, 'samples': 22905024, 'steps': 119296, 'loss/train': 1.077980875968933} 08/31/2021 10:46:46 - INFO - __main__ - Step 119298: {'lr': 5.124137729015968e-05, 'samples': 22905216, 'steps': 119297, 'loss/train': 1.2393238544464111} 08/31/2021 10:46:47 - INFO - __main__ - Step 119299: {'lr': 5.123815845366936e-05, 'samples': 22905408, 'steps': 119298, 'loss/train': 1.2314789295196533} 08/31/2021 10:46:48 - INFO - __main__ - Step 119300: {'lr': 5.123493970673807e-05, 'samples': 22905600, 'steps': 119299, 'loss/train': 1.438582181930542} 08/31/2021 10:46:48 - INFO - __main__ - Step 119301: {'lr': 5.123172104936724e-05, 'samples': 22905792, 'steps': 119300, 'loss/train': 1.3060963153839111} 08/31/2021 10:46:49 - INFO - __main__ - Step 119302: {'lr': 5.122850248155836e-05, 'samples': 22905984, 'steps': 119301, 'loss/train': 2.0871222019195557} 08/31/2021 10:46:49 - INFO - __main__ - Step 119303: {'lr': 5.122528400331281e-05, 'samples': 22906176, 'steps': 119302, 'loss/train': 1.0778290033340454} 08/31/2021 10:46:49 - INFO - __main__ - Step 119304: {'lr': 5.122206561463211e-05, 'samples': 22906368, 'steps': 119303, 'loss/train': 1.3123971223831177} 08/31/2021 10:46:51 - INFO - __main__ - Step 119305: {'lr': 5.121884731551765e-05, 'samples': 22906560, 'steps': 119304, 'loss/train': 0.6395794749259949} 08/31/2021 10:46:51 - INFO - __main__ - Step 119306: {'lr': 5.1215629105970995e-05, 'samples': 22906752, 'steps': 119305, 'loss/train': 0.14797523617744446} 08/31/2021 10:46:52 - INFO - __main__ - Step 119307: {'lr': 5.121241098599344e-05, 'samples': 22906944, 'steps': 119306, 'loss/train': 0.7145551443099976} 08/31/2021 10:46:52 - INFO - __main__ - Step 119308: {'lr': 5.120919295558652e-05, 'samples': 22907136, 'steps': 119307, 'loss/train': 0.9527541995048523} 08/31/2021 10:46:52 - INFO - __main__ - Step 119309: {'lr': 5.120597501475163e-05, 'samples': 22907328, 'steps': 119308, 'loss/train': 1.339189887046814} 08/31/2021 10:46:54 - INFO - __main__ - Step 119310: {'lr': 5.1202757163490294e-05, 'samples': 22907520, 'steps': 119309, 'loss/train': 1.078698992729187} 08/31/2021 10:46:55 - INFO - __main__ - Step 119311: {'lr': 5.119953940180391e-05, 'samples': 22907712, 'steps': 119310, 'loss/train': 0.03423067927360535} 08/31/2021 10:46:55 - INFO - __main__ - Step 119312: {'lr': 5.119632172969396e-05, 'samples': 22907904, 'steps': 119311, 'loss/train': 0.8586699962615967} 08/31/2021 10:46:55 - INFO - __main__ - Step 119313: {'lr': 5.1193104147161885e-05, 'samples': 22908096, 'steps': 119312, 'loss/train': 1.3290044069290161} 08/31/2021 10:46:56 - INFO - __main__ - Step 119314: {'lr': 5.118988665420912e-05, 'samples': 22908288, 'steps': 119313, 'loss/train': 0.9667534232139587} 08/31/2021 10:46:57 - INFO - __main__ - Step 119315: {'lr': 5.118666925083712e-05, 'samples': 22908480, 'steps': 119314, 'loss/train': 1.1484252214431763} 08/31/2021 10:46:58 - INFO - __main__ - Step 119316: {'lr': 5.118345193704735e-05, 'samples': 22908672, 'steps': 119315, 'loss/train': 1.5591466426849365} 08/31/2021 10:46:58 - INFO - __main__ - Step 119317: {'lr': 5.118023471284131e-05, 'samples': 22908864, 'steps': 119316, 'loss/train': 1.4507359266281128} 08/31/2021 10:46:58 - INFO - __main__ - Step 119318: {'lr': 5.11770175782203e-05, 'samples': 22909056, 'steps': 119317, 'loss/train': 1.5940346717834473} 08/31/2021 10:46:59 - INFO - __main__ - Step 119319: {'lr': 5.1173800533185876e-05, 'samples': 22909248, 'steps': 119318, 'loss/train': 1.0571117401123047} 08/31/2021 10:47:00 - INFO - __main__ - Step 119320: {'lr': 5.117058357773946e-05, 'samples': 22909440, 'steps': 119319, 'loss/train': 1.216681718826294} 08/31/2021 10:47:01 - INFO - __main__ - Step 119321: {'lr': 5.1167366711882546e-05, 'samples': 22909632, 'steps': 119320, 'loss/train': 0.027382202446460724} 08/31/2021 10:47:01 - INFO - __main__ - Step 119322: {'lr': 5.116414993561652e-05, 'samples': 22909824, 'steps': 119321, 'loss/train': 1.5450615882873535} 08/31/2021 10:47:01 - INFO - __main__ - Step 119323: {'lr': 5.116093324894286e-05, 'samples': 22910016, 'steps': 119322, 'loss/train': 1.5233237743377686} 08/31/2021 10:47:02 - INFO - __main__ - Step 119324: {'lr': 5.1157716651863e-05, 'samples': 22910208, 'steps': 119323, 'loss/train': 1.3880447149276733} 08/31/2021 10:47:03 - INFO - __main__ - Step 119325: {'lr': 5.1154500144378446e-05, 'samples': 22910400, 'steps': 119324, 'loss/train': 1.5019501447677612} 08/31/2021 10:47:04 - INFO - __main__ - Step 119326: {'lr': 5.1151283726490583e-05, 'samples': 22910592, 'steps': 119325, 'loss/train': 1.1513718366622925} 08/31/2021 10:47:04 - INFO - __main__ - Step 119327: {'lr': 5.1148067398200884e-05, 'samples': 22910784, 'steps': 119326, 'loss/train': 1.0843160152435303} 08/31/2021 10:47:04 - INFO - __main__ - Step 119328: {'lr': 5.1144851159510844e-05, 'samples': 22910976, 'steps': 119327, 'loss/train': 0.48860225081443787} 08/31/2021 10:47:05 - INFO - __main__ - Step 119329: {'lr': 5.114163501042182e-05, 'samples': 22911168, 'steps': 119328, 'loss/train': 0.4964480996131897} 08/31/2021 10:47:06 - INFO - __main__ - Step 119330: {'lr': 5.113841895093532e-05, 'samples': 22911360, 'steps': 119329, 'loss/train': 1.3712327480316162} 08/31/2021 10:47:07 - INFO - __main__ - Step 119331: {'lr': 5.113520298105276e-05, 'samples': 22911552, 'steps': 119330, 'loss/train': 1.3117115497589111} 08/31/2021 10:47:07 - INFO - __main__ - Step 119332: {'lr': 5.11319871007756e-05, 'samples': 22911744, 'steps': 119331, 'loss/train': 1.485841155052185} 08/31/2021 10:47:07 - INFO - __main__ - Step 119333: {'lr': 5.112877131010532e-05, 'samples': 22911936, 'steps': 119332, 'loss/train': 1.1082276105880737} 08/31/2021 10:47:08 - INFO - __main__ - Step 119334: {'lr': 5.1125555609043334e-05, 'samples': 22912128, 'steps': 119333, 'loss/train': 1.688546061515808} 08/31/2021 10:47:08 - INFO - __main__ - Step 119335: {'lr': 5.112233999759111e-05, 'samples': 22912320, 'steps': 119334, 'loss/train': 1.2398486137390137} 08/31/2021 10:47:10 - INFO - __main__ - Step 119336: {'lr': 5.11191244757501e-05, 'samples': 22912512, 'steps': 119335, 'loss/train': 0.7688047885894775} 08/31/2021 10:47:10 - INFO - __main__ - Step 119337: {'lr': 5.111590904352173e-05, 'samples': 22912704, 'steps': 119336, 'loss/train': 0.2479047030210495} 08/31/2021 10:47:11 - INFO - __main__ - Step 119338: {'lr': 5.111269370090746e-05, 'samples': 22912896, 'steps': 119337, 'loss/train': 2.205427646636963} 08/31/2021 10:47:11 - INFO - __main__ - Step 119339: {'lr': 5.1109478447908755e-05, 'samples': 22913088, 'steps': 119338, 'loss/train': 0.6515741944313049} 08/31/2021 10:47:11 - INFO - __main__ - Step 119340: {'lr': 5.110626328452703e-05, 'samples': 22913280, 'steps': 119339, 'loss/train': 1.4104828834533691} 08/31/2021 10:47:13 - INFO - __main__ - Step 119341: {'lr': 5.1103048210763833e-05, 'samples': 22913472, 'steps': 119340, 'loss/train': 0.717351496219635} 08/31/2021 10:47:13 - INFO - __main__ - Step 119342: {'lr': 5.109983322662046e-05, 'samples': 22913664, 'steps': 119341, 'loss/train': 0.9459224939346313} 08/31/2021 10:47:14 - INFO - __main__ - Step 119343: {'lr': 5.109661833209844e-05, 'samples': 22913856, 'steps': 119342, 'loss/train': 1.0796080827713013} 08/31/2021 10:47:14 - INFO - __main__ - Step 119344: {'lr': 5.109340352719921e-05, 'samples': 22914048, 'steps': 119343, 'loss/train': 1.0702166557312012} 08/31/2021 10:47:14 - INFO - __main__ - Step 119345: {'lr': 5.109018881192423e-05, 'samples': 22914240, 'steps': 119344, 'loss/train': 1.2079647779464722} 08/31/2021 10:47:17 - INFO - __main__ - Step 119346: {'lr': 5.108697418627495e-05, 'samples': 22914432, 'steps': 119345, 'loss/train': 1.9732091426849365} 08/31/2021 10:47:18 - INFO - __main__ - Step 119347: {'lr': 5.1083759650252775e-05, 'samples': 22914624, 'steps': 119346, 'loss/train': 1.263380527496338} 08/31/2021 10:47:18 - INFO - __main__ - Step 119348: {'lr': 5.108054520385921e-05, 'samples': 22914816, 'steps': 119347, 'loss/train': 0.5788347125053406} 08/31/2021 10:47:18 - INFO - __main__ - Step 119349: {'lr': 5.1077330847095704e-05, 'samples': 22915008, 'steps': 119348, 'loss/train': 0.38912442326545715} 08/31/2021 10:47:19 - INFO - __main__ - Step 119350: {'lr': 5.1074116579963666e-05, 'samples': 22915200, 'steps': 119349, 'loss/train': 0.8571822643280029} 08/31/2021 10:47:19 - INFO - __main__ - Step 119351: {'lr': 5.107090240246454e-05, 'samples': 22915392, 'steps': 119350, 'loss/train': 1.6776759624481201} 08/31/2021 10:47:20 - INFO - __main__ - Step 119352: {'lr': 5.106768831459982e-05, 'samples': 22915584, 'steps': 119351, 'loss/train': 0.9428651928901672} 08/31/2021 10:47:21 - INFO - __main__ - Step 119353: {'lr': 5.106447431637093e-05, 'samples': 22915776, 'steps': 119352, 'loss/train': 1.1360301971435547} 08/31/2021 10:47:21 - INFO - __main__ - Step 119354: {'lr': 5.106126040777936e-05, 'samples': 22915968, 'steps': 119353, 'loss/train': 1.283329963684082} 08/31/2021 10:47:22 - INFO - __main__ - Step 119355: {'lr': 5.1058046588826484e-05, 'samples': 22916160, 'steps': 119354, 'loss/train': 0.875401496887207} 08/31/2021 10:47:22 - INFO - __main__ - Step 119356: {'lr': 5.105483285951376e-05, 'samples': 22916352, 'steps': 119355, 'loss/train': 0.5163649320602417} 08/31/2021 10:47:24 - INFO - __main__ - Step 119357: {'lr': 5.105161921984267e-05, 'samples': 22916544, 'steps': 119356, 'loss/train': 1.580142617225647} 08/31/2021 10:47:24 - INFO - __main__ - Step 119358: {'lr': 5.104840566981464e-05, 'samples': 22916736, 'steps': 119357, 'loss/train': 1.347001075744629} 08/31/2021 10:47:25 - INFO - __main__ - Step 119359: {'lr': 5.104519220943113e-05, 'samples': 22916928, 'steps': 119358, 'loss/train': 0.47947290539741516} 08/31/2021 10:47:25 - INFO - __main__ - Step 119360: {'lr': 5.104197883869357e-05, 'samples': 22917120, 'steps': 119359, 'loss/train': 1.0135987997055054} 08/31/2021 10:47:25 - INFO - __main__ - Step 119361: {'lr': 5.103876555760345e-05, 'samples': 22917312, 'steps': 119360, 'loss/train': 0.044333603233098984} 08/31/2021 10:47:27 - INFO - __main__ - Step 119362: {'lr': 5.10355523661622e-05, 'samples': 22917504, 'steps': 119361, 'loss/train': 1.0877567529678345} 08/31/2021 10:47:27 - INFO - __main__ - Step 119363: {'lr': 5.103233926437123e-05, 'samples': 22917696, 'steps': 119362, 'loss/train': 1.3420894145965576} 08/31/2021 10:47:28 - INFO - __main__ - Step 119364: {'lr': 5.102912625223205e-05, 'samples': 22917888, 'steps': 119363, 'loss/train': 1.1217964887619019} 08/31/2021 10:47:28 - INFO - __main__ - Step 119365: {'lr': 5.102591332974604e-05, 'samples': 22918080, 'steps': 119364, 'loss/train': 0.7986434102058411} 08/31/2021 10:47:28 - INFO - __main__ - Step 119366: {'lr': 5.1022700496914706e-05, 'samples': 22918272, 'steps': 119365, 'loss/train': 1.2419469356536865} 08/31/2021 10:47:30 - INFO - __main__ - Step 119367: {'lr': 5.1019487753739464e-05, 'samples': 22918464, 'steps': 119366, 'loss/train': 0.9624870419502258} 08/31/2021 10:47:30 - INFO - __main__ - Step 119368: {'lr': 5.101627510022186e-05, 'samples': 22918656, 'steps': 119367, 'loss/train': 1.2293099164962769} 08/31/2021 10:47:31 - INFO - __main__ - Step 119369: {'lr': 5.101306253636315e-05, 'samples': 22918848, 'steps': 119368, 'loss/train': 1.0631662607192993} 08/31/2021 10:47:31 - INFO - __main__ - Step 119370: {'lr': 5.100985006216491e-05, 'samples': 22919040, 'steps': 119369, 'loss/train': 1.5018465518951416} 08/31/2021 10:47:31 - INFO - __main__ - Step 119371: {'lr': 5.100663767762853e-05, 'samples': 22919232, 'steps': 119370, 'loss/train': 1.1911883354187012} 08/31/2021 10:47:32 - INFO - __main__ - Step 119372: {'lr': 5.1003425382755516e-05, 'samples': 22919424, 'steps': 119371, 'loss/train': 0.8321439027786255} 08/31/2021 10:47:33 - INFO - __main__ - Step 119373: {'lr': 5.10002131775473e-05, 'samples': 22919616, 'steps': 119372, 'loss/train': 0.6251884698867798} 08/31/2021 10:47:34 - INFO - __main__ - Step 119374: {'lr': 5.0997001062005274e-05, 'samples': 22919808, 'steps': 119373, 'loss/train': 1.4002186059951782} 08/31/2021 10:47:34 - INFO - __main__ - Step 119375: {'lr': 5.099378903613097e-05, 'samples': 22920000, 'steps': 119374, 'loss/train': 1.0469037294387817} 08/31/2021 10:47:34 - INFO - __main__ - Step 119376: {'lr': 5.0990577099925774e-05, 'samples': 22920192, 'steps': 119375, 'loss/train': 1.0964524745941162} 08/31/2021 10:47:35 - INFO - __main__ - Step 119377: {'lr': 5.098736525339115e-05, 'samples': 22920384, 'steps': 119376, 'loss/train': 0.7271342277526855} 08/31/2021 10:47:36 - INFO - __main__ - Step 119378: {'lr': 5.098415349652855e-05, 'samples': 22920576, 'steps': 119377, 'loss/train': 1.129012107849121} 08/31/2021 10:47:37 - INFO - __main__ - Step 119379: {'lr': 5.0980941829339436e-05, 'samples': 22920768, 'steps': 119378, 'loss/train': 0.773509681224823} 08/31/2021 10:47:37 - INFO - __main__ - Step 119380: {'lr': 5.0977730251825226e-05, 'samples': 22920960, 'steps': 119379, 'loss/train': 2.1354563236236572} 08/31/2021 10:47:37 - INFO - __main__ - Step 119381: {'lr': 5.0974518763987425e-05, 'samples': 22921152, 'steps': 119380, 'loss/train': 0.6356531977653503} 08/31/2021 10:47:38 - INFO - __main__ - Step 119382: {'lr': 5.097130736582739e-05, 'samples': 22921344, 'steps': 119381, 'loss/train': 1.5499413013458252} 08/31/2021 10:47:39 - INFO - __main__ - Step 119383: {'lr': 5.096809605734662e-05, 'samples': 22921536, 'steps': 119382, 'loss/train': 1.04159414768219} 08/31/2021 10:47:40 - INFO - __main__ - Step 119384: {'lr': 5.096488483854655e-05, 'samples': 22921728, 'steps': 119383, 'loss/train': 1.968454360961914} 08/31/2021 10:47:40 - INFO - __main__ - Step 119385: {'lr': 5.096167370942864e-05, 'samples': 22921920, 'steps': 119384, 'loss/train': 0.6292928457260132} 08/31/2021 10:47:40 - INFO - __main__ - Step 119386: {'lr': 5.095846266999429e-05, 'samples': 22922112, 'steps': 119385, 'loss/train': 0.558052659034729} 08/31/2021 10:47:41 - INFO - __main__ - Step 119387: {'lr': 5.095525172024504e-05, 'samples': 22922304, 'steps': 119386, 'loss/train': 0.39997991919517517} 08/31/2021 10:47:42 - INFO - __main__ - Step 119388: {'lr': 5.095204086018224e-05, 'samples': 22922496, 'steps': 119387, 'loss/train': 1.389549970626831} 08/31/2021 10:47:43 - INFO - __main__ - Step 119389: {'lr': 5.0948830089807384e-05, 'samples': 22922688, 'steps': 119388, 'loss/train': 0.9228894114494324} 08/31/2021 10:47:43 - INFO - __main__ - Step 119390: {'lr': 5.094561940912193e-05, 'samples': 22922880, 'steps': 119389, 'loss/train': 1.0825392007827759} 08/31/2021 10:47:43 - INFO - __main__ - Step 119391: {'lr': 5.0942408818127315e-05, 'samples': 22923072, 'steps': 119390, 'loss/train': 0.7777702212333679} 08/31/2021 10:47:44 - INFO - __main__ - Step 119392: {'lr': 5.0939198316824945e-05, 'samples': 22923264, 'steps': 119391, 'loss/train': 1.1709320545196533} 08/31/2021 10:47:45 - INFO - __main__ - Step 119393: {'lr': 5.093598790521634e-05, 'samples': 22923456, 'steps': 119392, 'loss/train': 0.9509900808334351} 08/31/2021 10:47:46 - INFO - __main__ - Step 119394: {'lr': 5.093277758330295e-05, 'samples': 22923648, 'steps': 119393, 'loss/train': 0.9995712041854858} 08/31/2021 10:47:46 - INFO - __main__ - Step 119395: {'lr': 5.0929567351086115e-05, 'samples': 22923840, 'steps': 119394, 'loss/train': 0.8351672887802124} 08/31/2021 10:47:47 - INFO - __main__ - Step 119396: {'lr': 5.092635720856734e-05, 'samples': 22924032, 'steps': 119395, 'loss/train': 1.0364587306976318} 08/31/2021 10:47:47 - INFO - __main__ - Step 119397: {'lr': 5.0923147155748084e-05, 'samples': 22924224, 'steps': 119396, 'loss/train': 5.524869918823242} 08/31/2021 10:47:47 - INFO - __main__ - Step 119398: {'lr': 5.0919937192629774e-05, 'samples': 22924416, 'steps': 119397, 'loss/train': 1.0470942258834839} 08/31/2021 10:47:49 - INFO - __main__ - Step 119399: {'lr': 5.0916727319213874e-05, 'samples': 22924608, 'steps': 119398, 'loss/train': 1.3045860528945923} 08/31/2021 10:47:49 - INFO - __main__ - Step 119400: {'lr': 5.091351753550183e-05, 'samples': 22924800, 'steps': 119399, 'loss/train': 0.7910741567611694} 08/31/2021 10:47:50 - INFO - __main__ - Step 119401: {'lr': 5.0910307841495085e-05, 'samples': 22924992, 'steps': 119400, 'loss/train': 1.0115500688552856} 08/31/2021 10:47:50 - INFO - __main__ - Step 119402: {'lr': 5.0907098237195084e-05, 'samples': 22925184, 'steps': 119401, 'loss/train': 1.505649209022522} 08/31/2021 10:47:51 - INFO - __main__ - Step 119403: {'lr': 5.0903888722603265e-05, 'samples': 22925376, 'steps': 119402, 'loss/train': 0.028592385351657867} 08/31/2021 10:47:53 - INFO - __main__ - Step 119404: {'lr': 5.0900679297721105e-05, 'samples': 22925568, 'steps': 119403, 'loss/train': 0.7589142918586731} 08/31/2021 10:47:53 - INFO - __main__ - Step 119405: {'lr': 5.0897469962549986e-05, 'samples': 22925760, 'steps': 119404, 'loss/train': 1.3018337488174438} 08/31/2021 10:47:53 - INFO - __main__ - Step 119406: {'lr': 5.089426071709144e-05, 'samples': 22925952, 'steps': 119405, 'loss/train': 1.0381345748901367} 08/31/2021 10:47:54 - INFO - __main__ - Step 119407: {'lr': 5.0891051561346824e-05, 'samples': 22926144, 'steps': 119406, 'loss/train': 1.0265040397644043} 08/31/2021 10:47:54 - INFO - __main__ - Step 119408: {'lr': 5.088784249531772e-05, 'samples': 22926336, 'steps': 119407, 'loss/train': 1.9768600463867188} 08/31/2021 10:47:56 - INFO - __main__ - Step 119409: {'lr': 5.0884633519005406e-05, 'samples': 22926528, 'steps': 119408, 'loss/train': 1.2747241258621216} 08/31/2021 10:47:56 - INFO - __main__ - Step 119410: {'lr': 5.088142463241141e-05, 'samples': 22926720, 'steps': 119409, 'loss/train': 1.2947182655334473} 08/31/2021 10:47:57 - INFO - __main__ - Step 119411: {'lr': 5.087821583553717e-05, 'samples': 22926912, 'steps': 119410, 'loss/train': 1.2510849237442017} 08/31/2021 10:47:57 - INFO - __main__ - Step 119412: {'lr': 5.0875007128384136e-05, 'samples': 22927104, 'steps': 119411, 'loss/train': 1.2461822032928467} 08/31/2021 10:47:57 - INFO - __main__ - Step 119413: {'lr': 5.087179851095375e-05, 'samples': 22927296, 'steps': 119412, 'loss/train': 1.092983365058899} 08/31/2021 10:47:58 - INFO - __main__ - Step 119414: {'lr': 5.0868589983247446e-05, 'samples': 22927488, 'steps': 119413, 'loss/train': 0.018464872613549232} 08/31/2021 10:47:59 - INFO - __main__ - Step 119415: {'lr': 5.086538154526668e-05, 'samples': 22927680, 'steps': 119414, 'loss/train': 0.01681808941066265} 08/31/2021 10:48:00 - INFO - __main__ - Step 119416: {'lr': 5.086217319701292e-05, 'samples': 22927872, 'steps': 119415, 'loss/train': 1.2970484495162964} 08/31/2021 10:48:00 - INFO - __main__ - Step 119417: {'lr': 5.085896493848757e-05, 'samples': 22928064, 'steps': 119416, 'loss/train': 0.36273783445358276} 08/31/2021 10:48:00 - INFO - __main__ - Step 119418: {'lr': 5.085575676969212e-05, 'samples': 22928256, 'steps': 119417, 'loss/train': 1.4888988733291626} 08/31/2021 10:48:01 - INFO - __main__ - Step 119419: {'lr': 5.0852548690627994e-05, 'samples': 22928448, 'steps': 119418, 'loss/train': 0.9952324032783508} 08/31/2021 10:48:02 - INFO - __main__ - Step 119420: {'lr': 5.084934070129662e-05, 'samples': 22928640, 'steps': 119419, 'loss/train': 1.0880308151245117} 08/31/2021 10:48:03 - INFO - __main__ - Step 119421: {'lr': 5.084613280169953e-05, 'samples': 22928832, 'steps': 119420, 'loss/train': 0.9872704744338989} 08/31/2021 10:48:03 - INFO - __main__ - Step 119422: {'lr': 5.084292499183804e-05, 'samples': 22929024, 'steps': 119421, 'loss/train': 0.15690405666828156} 08/31/2021 10:48:03 - INFO - __main__ - Step 119423: {'lr': 5.083971727171366e-05, 'samples': 22929216, 'steps': 119422, 'loss/train': 1.0540385246276855} 08/31/2021 10:48:04 - INFO - __main__ - Step 119424: {'lr': 5.083650964132783e-05, 'samples': 22929408, 'steps': 119423, 'loss/train': 1.307063341140747} 08/31/2021 10:48:05 - INFO - __main__ - Step 119425: {'lr': 5.083330210068196e-05, 'samples': 22929600, 'steps': 119424, 'loss/train': 0.8595337867736816} 08/31/2021 10:48:06 - INFO - __main__ - Step 119426: {'lr': 5.083009464977756e-05, 'samples': 22929792, 'steps': 119425, 'loss/train': 0.7290379405021667} 08/31/2021 10:48:06 - INFO - __main__ - Step 119427: {'lr': 5.0826887288616066e-05, 'samples': 22929984, 'steps': 119426, 'loss/train': 1.2307466268539429} 08/31/2021 10:48:06 - INFO - __main__ - Step 119428: {'lr': 5.0823680017198866e-05, 'samples': 22930176, 'steps': 119427, 'loss/train': 1.6846330165863037} 08/31/2021 10:48:07 - INFO - __main__ - Step 119429: {'lr': 5.082047283552746e-05, 'samples': 22930368, 'steps': 119428, 'loss/train': 1.0873825550079346} 08/31/2021 10:48:07 - INFO - __main__ - Step 119430: {'lr': 5.081726574360326e-05, 'samples': 22930560, 'steps': 119429, 'loss/train': 1.4577035903930664} 08/31/2021 10:48:09 - INFO - __main__ - Step 119431: {'lr': 5.081405874142775e-05, 'samples': 22930752, 'steps': 119430, 'loss/train': 1.0439585447311401} 08/31/2021 10:48:09 - INFO - __main__ - Step 119432: {'lr': 5.081085182900233e-05, 'samples': 22930944, 'steps': 119431, 'loss/train': 1.2894586324691772} 08/31/2021 10:48:09 - INFO - __main__ - Step 119433: {'lr': 5.080764500632848e-05, 'samples': 22931136, 'steps': 119432, 'loss/train': 1.2083637714385986} 08/31/2021 10:48:10 - INFO - __main__ - Step 119434: {'lr': 5.080443827340764e-05, 'samples': 22931328, 'steps': 119433, 'loss/train': 1.0560015439987183} 08/31/2021 10:48:10 - INFO - __main__ - Step 119435: {'lr': 5.0801231630241304e-05, 'samples': 22931520, 'steps': 119434, 'loss/train': 1.1660125255584717} 08/31/2021 10:48:12 - INFO - __main__ - Step 119436: {'lr': 5.0798025076830786e-05, 'samples': 22931712, 'steps': 119435, 'loss/train': 1.3719043731689453} 08/31/2021 10:48:12 - INFO - __main__ - Step 119437: {'lr': 5.079481861317761e-05, 'samples': 22931904, 'steps': 119436, 'loss/train': 1.001359224319458} 08/31/2021 10:48:12 - INFO - __main__ - Step 119438: {'lr': 5.079161223928322e-05, 'samples': 22932096, 'steps': 119437, 'loss/train': 1.9733750820159912} 08/31/2021 10:48:13 - INFO - __main__ - Step 119439: {'lr': 5.078840595514902e-05, 'samples': 22932288, 'steps': 119438, 'loss/train': 0.5422013401985168} 08/31/2021 10:48:13 - INFO - __main__ - Step 119440: {'lr': 5.0785199760776526e-05, 'samples': 22932480, 'steps': 119439, 'loss/train': 0.03294004499912262} 08/31/2021 10:48:15 - INFO - __main__ - Step 119441: {'lr': 5.078199365616715e-05, 'samples': 22932672, 'steps': 119440, 'loss/train': 1.698718547821045} 08/31/2021 10:48:15 - INFO - __main__ - Step 119442: {'lr': 5.077878764132232e-05, 'samples': 22932864, 'steps': 119441, 'loss/train': 1.1596693992614746} 08/31/2021 10:48:16 - INFO - __main__ - Step 119443: {'lr': 5.0775581716243495e-05, 'samples': 22933056, 'steps': 119442, 'loss/train': 0.347513347864151} 08/31/2021 10:48:16 - INFO - __main__ - Step 119444: {'lr': 5.0772375880932114e-05, 'samples': 22933248, 'steps': 119443, 'loss/train': 0.5227558016777039} 08/31/2021 10:48:16 - INFO - __main__ - Step 119445: {'lr': 5.0769170135389644e-05, 'samples': 22933440, 'steps': 119444, 'loss/train': 0.06623692810535431} 08/31/2021 10:48:18 - INFO - __main__ - Step 119446: {'lr': 5.076596447961751e-05, 'samples': 22933632, 'steps': 119445, 'loss/train': 0.42127013206481934} 08/31/2021 10:48:19 - INFO - __main__ - Step 119447: {'lr': 5.076275891361714e-05, 'samples': 22933824, 'steps': 119446, 'loss/train': 1.4050512313842773} 08/31/2021 10:48:19 - INFO - __main__ - Step 119448: {'lr': 5.075955343739005e-05, 'samples': 22934016, 'steps': 119447, 'loss/train': 0.735451340675354} 08/31/2021 10:48:19 - INFO - __main__ - Step 119449: {'lr': 5.075634805093759e-05, 'samples': 22934208, 'steps': 119448, 'loss/train': 1.4162167310714722} 08/31/2021 10:48:20 - INFO - __main__ - Step 119450: {'lr': 5.0753142754261266e-05, 'samples': 22934400, 'steps': 119449, 'loss/train': 0.017859870567917824} 08/31/2021 10:48:20 - INFO - __main__ - Step 119451: {'lr': 5.0749937547362456e-05, 'samples': 22934592, 'steps': 119450, 'loss/train': 0.3077363669872284} 08/31/2021 10:48:22 - INFO - __main__ - Step 119452: {'lr': 5.074673243024266e-05, 'samples': 22934784, 'steps': 119451, 'loss/train': 1.5896151065826416} 08/31/2021 10:48:22 - INFO - __main__ - Step 119453: {'lr': 5.074352740290333e-05, 'samples': 22934976, 'steps': 119452, 'loss/train': 1.5703587532043457} 08/31/2021 10:48:22 - INFO - __main__ - Step 119454: {'lr': 5.074032246534591e-05, 'samples': 22935168, 'steps': 119453, 'loss/train': 0.7776638865470886} 08/31/2021 10:48:23 - INFO - __main__ - Step 119455: {'lr': 5.073711761757177e-05, 'samples': 22935360, 'steps': 119454, 'loss/train': 1.4861046075820923} 08/31/2021 10:48:23 - INFO - __main__ - Step 119456: {'lr': 5.073391285958246e-05, 'samples': 22935552, 'steps': 119455, 'loss/train': 0.9702985882759094} 08/31/2021 10:48:23 - INFO - __main__ - Step 119457: {'lr': 5.073070819137934e-05, 'samples': 22935744, 'steps': 119456, 'loss/train': 0.9104605913162231} 08/31/2021 10:48:25 - INFO - __main__ - Step 119458: {'lr': 5.072750361296391e-05, 'samples': 22935936, 'steps': 119457, 'loss/train': 1.0797737836837769} 08/31/2021 10:48:26 - INFO - __main__ - Step 119459: {'lr': 5.072429912433757e-05, 'samples': 22936128, 'steps': 119458, 'loss/train': 1.078276515007019} 08/31/2021 10:48:26 - INFO - __main__ - Step 119460: {'lr': 5.072109472550179e-05, 'samples': 22936320, 'steps': 119459, 'loss/train': 0.5140671730041504} 08/31/2021 10:48:27 - INFO - __main__ - Step 119461: {'lr': 5.071789041645802e-05, 'samples': 22936512, 'steps': 119460, 'loss/train': 1.152123212814331} 08/31/2021 10:48:27 - INFO - __main__ - Step 119462: {'lr': 5.071468619720776e-05, 'samples': 22936704, 'steps': 119461, 'loss/train': 0.9235906004905701} 08/31/2021 10:48:28 - INFO - __main__ - Step 119463: {'lr': 5.071148206775234e-05, 'samples': 22936896, 'steps': 119462, 'loss/train': 0.5253589749336243} 08/31/2021 10:48:29 - INFO - __main__ - Step 119464: {'lr': 5.070827802809322e-05, 'samples': 22937088, 'steps': 119463, 'loss/train': 4.683403491973877} 08/31/2021 10:48:29 - INFO - __main__ - Step 119465: {'lr': 5.070507407823188e-05, 'samples': 22937280, 'steps': 119464, 'loss/train': 0.5927156805992126} 08/31/2021 10:48:30 - INFO - __main__ - Step 119466: {'lr': 5.070187021816977e-05, 'samples': 22937472, 'steps': 119465, 'loss/train': 1.1371724605560303} 08/31/2021 10:48:30 - INFO - __main__ - Step 119467: {'lr': 5.069866644790833e-05, 'samples': 22937664, 'steps': 119466, 'loss/train': 0.9257859587669373} 08/31/2021 10:48:32 - INFO - __main__ - Step 119468: {'lr': 5.069546276744896e-05, 'samples': 22937856, 'steps': 119467, 'loss/train': 1.1479331254959106} 08/31/2021 10:48:32 - INFO - __main__ - Step 119469: {'lr': 5.0692259176793154e-05, 'samples': 22938048, 'steps': 119468, 'loss/train': 1.6749286651611328} 08/31/2021 10:48:32 - INFO - __main__ - Step 119470: {'lr': 5.068905567594237e-05, 'samples': 22938240, 'steps': 119469, 'loss/train': 0.8611266016960144} 08/31/2021 10:48:33 - INFO - __main__ - Step 119471: {'lr': 5.0685852264898e-05, 'samples': 22938432, 'steps': 119470, 'loss/train': 1.2058571577072144} 08/31/2021 10:48:33 - INFO - __main__ - Step 119472: {'lr': 5.068264894366148e-05, 'samples': 22938624, 'steps': 119471, 'loss/train': 1.217793345451355} 08/31/2021 10:48:35 - INFO - __main__ - Step 119473: {'lr': 5.067944571223432e-05, 'samples': 22938816, 'steps': 119472, 'loss/train': 1.2564754486083984} 08/31/2021 10:48:35 - INFO - __main__ - Step 119474: {'lr': 5.0676242570617924e-05, 'samples': 22939008, 'steps': 119473, 'loss/train': 0.7793998122215271} 08/31/2021 10:48:35 - INFO - __main__ - Step 119475: {'lr': 5.06730395188138e-05, 'samples': 22939200, 'steps': 119474, 'loss/train': 1.0603246688842773} 08/31/2021 10:48:36 - INFO - __main__ - Step 119476: {'lr': 5.066983655682325e-05, 'samples': 22939392, 'steps': 119475, 'loss/train': 1.1258989572525024} 08/31/2021 10:48:36 - INFO - __main__ - Step 119477: {'lr': 5.06666336846478e-05, 'samples': 22939584, 'steps': 119476, 'loss/train': 1.2497421503067017} 08/31/2021 10:48:36 - INFO - __main__ - Step 119478: {'lr': 5.066343090228889e-05, 'samples': 22939776, 'steps': 119477, 'loss/train': 1.561629295349121} 08/31/2021 10:48:38 - INFO - __main__ - Step 119479: {'lr': 5.066022820974797e-05, 'samples': 22939968, 'steps': 119478, 'loss/train': 2.016144275665283} 08/31/2021 10:48:38 - INFO - __main__ - Step 119480: {'lr': 5.065702560702648e-05, 'samples': 22940160, 'steps': 119479, 'loss/train': 0.8959423899650574} 08/31/2021 10:48:39 - INFO - __main__ - Step 119481: {'lr': 5.0653823094125834e-05, 'samples': 22940352, 'steps': 119480, 'loss/train': 1.188289999961853} 08/31/2021 10:48:39 - INFO - __main__ - Step 119482: {'lr': 5.06506206710475e-05, 'samples': 22940544, 'steps': 119481, 'loss/train': 1.1278433799743652} 08/31/2021 10:48:39 - INFO - __main__ - Step 119483: {'lr': 5.064741833779296e-05, 'samples': 22940736, 'steps': 119482, 'loss/train': 2.249638319015503} 08/31/2021 10:48:41 - INFO - __main__ - Step 119484: {'lr': 5.064421609436359e-05, 'samples': 22940928, 'steps': 119483, 'loss/train': 1.1110939979553223} 08/31/2021 10:48:41 - INFO - __main__ - Step 119485: {'lr': 5.0641013940760843e-05, 'samples': 22941120, 'steps': 119484, 'loss/train': 1.3043315410614014} 08/31/2021 10:48:42 - INFO - __main__ - Step 119486: {'lr': 5.063781187698621e-05, 'samples': 22941312, 'steps': 119485, 'loss/train': 1.372521996498108} 08/31/2021 10:48:42 - INFO - __main__ - Step 119487: {'lr': 5.0634609903041086e-05, 'samples': 22941504, 'steps': 119486, 'loss/train': 0.9623226523399353} 08/31/2021 10:48:42 - INFO - __main__ - Step 119488: {'lr': 5.063140801892693e-05, 'samples': 22941696, 'steps': 119487, 'loss/train': 0.8067052960395813} 08/31/2021 10:48:44 - INFO - __main__ - Step 119489: {'lr': 5.0628206224645254e-05, 'samples': 22941888, 'steps': 119488, 'loss/train': 1.4569694995880127} 08/31/2021 10:48:44 - INFO - __main__ - Step 119490: {'lr': 5.062500452019736e-05, 'samples': 22942080, 'steps': 119489, 'loss/train': 1.4213799238204956} 08/31/2021 10:48:45 - INFO - __main__ - Step 119491: {'lr': 5.0621802905584766e-05, 'samples': 22942272, 'steps': 119490, 'loss/train': 1.2137914896011353} 08/31/2021 10:48:45 - INFO - __main__ - Step 119492: {'lr': 5.061860138080892e-05, 'samples': 22942464, 'steps': 119491, 'loss/train': 0.2478218525648117} 08/31/2021 10:48:46 - INFO - __main__ - Step 119493: {'lr': 5.061539994587125e-05, 'samples': 22942656, 'steps': 119492, 'loss/train': 0.8136162757873535} 08/31/2021 10:48:47 - INFO - __main__ - Step 119494: {'lr': 5.0612198600773206e-05, 'samples': 22942848, 'steps': 119493, 'loss/train': 1.1169037818908691} 08/31/2021 10:48:48 - INFO - __main__ - Step 119495: {'lr': 5.060899734551622e-05, 'samples': 22943040, 'steps': 119494, 'loss/train': 1.4179776906967163} 08/31/2021 10:48:48 - INFO - __main__ - Step 119496: {'lr': 5.060579618010175e-05, 'samples': 22943232, 'steps': 119495, 'loss/train': 0.8398116230964661} 08/31/2021 10:48:49 - INFO - __main__ - Step 119497: {'lr': 5.060259510453125e-05, 'samples': 22943424, 'steps': 119496, 'loss/train': 1.0902297496795654} 08/31/2021 10:48:49 - INFO - __main__ - Step 119498: {'lr': 5.059939411880613e-05, 'samples': 22943616, 'steps': 119497, 'loss/train': 1.6500825881958008} 08/31/2021 10:48:49 - INFO - __main__ - Step 119499: {'lr': 5.0596193222927826e-05, 'samples': 22943808, 'steps': 119498, 'loss/train': 0.8830618858337402} 08/31/2021 10:48:51 - INFO - __main__ - Step 119500: {'lr': 5.0592992416897826e-05, 'samples': 22944000, 'steps': 119499, 'loss/train': 0.02841159701347351} 08/31/2021 10:48:51 - INFO - __main__ - Step 119501: {'lr': 5.0589791700717537e-05, 'samples': 22944192, 'steps': 119500, 'loss/train': 0.7086821794509888} 08/31/2021 10:48:52 - INFO - __main__ - Step 119502: {'lr': 5.0586591074388456e-05, 'samples': 22944384, 'steps': 119501, 'loss/train': 1.3472237586975098} 08/31/2021 10:48:52 - INFO - __main__ - Step 119503: {'lr': 5.0583390537911946e-05, 'samples': 22944576, 'steps': 119502, 'loss/train': 0.9483713507652283} 08/31/2021 10:48:53 - INFO - __main__ - Step 119504: {'lr': 5.058019009128948e-05, 'samples': 22944768, 'steps': 119503, 'loss/train': 1.2557549476623535} 08/31/2021 10:48:53 - INFO - __main__ - Step 119505: {'lr': 5.0576989734522486e-05, 'samples': 22944960, 'steps': 119504, 'loss/train': 1.0109469890594482} 08/31/2021 10:48:54 - INFO - __main__ - Step 119506: {'lr': 5.057378946761243e-05, 'samples': 22945152, 'steps': 119505, 'loss/train': 0.8741247653961182} 08/31/2021 10:48:55 - INFO - __main__ - Step 119507: {'lr': 5.0570589290560744e-05, 'samples': 22945344, 'steps': 119506, 'loss/train': 1.191809892654419} 08/31/2021 10:48:55 - INFO - __main__ - Step 119508: {'lr': 5.0567389203368866e-05, 'samples': 22945536, 'steps': 119507, 'loss/train': 1.3742378950119019} 08/31/2021 10:48:56 - INFO - __main__ - Step 119509: {'lr': 5.056418920603825e-05, 'samples': 22945728, 'steps': 119508, 'loss/train': 0.6467965841293335} 08/31/2021 10:48:56 - INFO - __main__ - Step 119510: {'lr': 5.0560989298570334e-05, 'samples': 22945920, 'steps': 119509, 'loss/train': 1.2702698707580566} 08/31/2021 10:48:57 - INFO - __main__ - Step 119511: {'lr': 5.055778948096657e-05, 'samples': 22946112, 'steps': 119510, 'loss/train': 1.1344029903411865} 08/31/2021 10:48:58 - INFO - __main__ - Step 119512: {'lr': 5.055458975322838e-05, 'samples': 22946304, 'steps': 119511, 'loss/train': 1.3830264806747437} 08/31/2021 10:48:58 - INFO - __main__ - Step 119513: {'lr': 5.0551390115357225e-05, 'samples': 22946496, 'steps': 119512, 'loss/train': 0.9310058355331421} 08/31/2021 10:48:58 - INFO - __main__ - Step 119514: {'lr': 5.054819056735452e-05, 'samples': 22946688, 'steps': 119513, 'loss/train': 1.2621077299118042} 08/31/2021 10:48:59 - INFO - __main__ - Step 119515: {'lr': 5.054499110922181e-05, 'samples': 22946880, 'steps': 119514, 'loss/train': 1.1813721656799316} 08/31/2021 10:49:01 - INFO - __main__ - Step 119516: {'lr': 5.054179174096035e-05, 'samples': 22947072, 'steps': 119515, 'loss/train': 1.8274381160736084} 08/31/2021 10:49:01 - INFO - __main__ - Step 119517: {'lr': 5.0538592462571695e-05, 'samples': 22947264, 'steps': 119516, 'loss/train': 1.4666184186935425} 08/31/2021 10:49:02 - INFO - __main__ - Step 119518: {'lr': 5.053539327405729e-05, 'samples': 22947456, 'steps': 119517, 'loss/train': 1.0517419576644897} 08/31/2021 10:49:02 - INFO - __main__ - Step 119519: {'lr': 5.0532194175418545e-05, 'samples': 22947648, 'steps': 119518, 'loss/train': 1.3707927465438843} 08/31/2021 10:49:03 - INFO - __main__ - Step 119520: {'lr': 5.052899516665691e-05, 'samples': 22947840, 'steps': 119519, 'loss/train': 0.6542346477508545} 08/31/2021 10:49:04 - INFO - __main__ - Step 119521: {'lr': 5.052579624777384e-05, 'samples': 22948032, 'steps': 119520, 'loss/train': 0.346523255109787} 08/31/2021 10:49:04 - INFO - __main__ - Step 119522: {'lr': 5.052259741877077e-05, 'samples': 22948224, 'steps': 119521, 'loss/train': 0.3408448398113251} 08/31/2021 10:49:05 - INFO - __main__ - Step 119523: {'lr': 5.051939867964914e-05, 'samples': 22948416, 'steps': 119522, 'loss/train': 1.1213791370391846} 08/31/2021 10:49:05 - INFO - __main__ - Step 119524: {'lr': 5.051620003041038e-05, 'samples': 22948608, 'steps': 119523, 'loss/train': 0.7009855508804321} 08/31/2021 10:49:06 - INFO - __main__ - Step 119525: {'lr': 5.0513001471055945e-05, 'samples': 22948800, 'steps': 119524, 'loss/train': 1.069054365158081} 08/31/2021 10:49:07 - INFO - __main__ - Step 119526: {'lr': 5.0509803001587276e-05, 'samples': 22948992, 'steps': 119525, 'loss/train': 1.642117977142334} 08/31/2021 10:49:08 - INFO - __main__ - Step 119527: {'lr': 5.050660462200582e-05, 'samples': 22949184, 'steps': 119526, 'loss/train': 1.649168848991394} 08/31/2021 10:49:08 - INFO - __main__ - Step 119528: {'lr': 5.0503406332312985e-05, 'samples': 22949376, 'steps': 119527, 'loss/train': 1.344626784324646} 08/31/2021 10:49:08 - INFO - __main__ - Step 119529: {'lr': 5.0500208132510326e-05, 'samples': 22949568, 'steps': 119528, 'loss/train': 0.34543997049331665} 08/31/2021 10:49:09 - INFO - __main__ - Step 119530: {'lr': 5.0497010022599126e-05, 'samples': 22949760, 'steps': 119529, 'loss/train': 0.688420295715332} 08/31/2021 10:49:10 - INFO - __main__ - Step 119531: {'lr': 5.049381200258088e-05, 'samples': 22949952, 'steps': 119530, 'loss/train': 0.646976888179779} 08/31/2021 10:49:11 - INFO - __main__ - Step 119532: {'lr': 5.049061407245706e-05, 'samples': 22950144, 'steps': 119531, 'loss/train': 1.0732393264770508} 08/31/2021 10:49:11 - INFO - __main__ - Step 119533: {'lr': 5.04874162322291e-05, 'samples': 22950336, 'steps': 119532, 'loss/train': 1.2426656484603882} 08/31/2021 10:49:11 - INFO - __main__ - Step 119534: {'lr': 5.0484218481898405e-05, 'samples': 22950528, 'steps': 119533, 'loss/train': 0.3074512481689453} 08/31/2021 10:49:12 - INFO - __main__ - Step 119535: {'lr': 5.0481020821466465e-05, 'samples': 22950720, 'steps': 119534, 'loss/train': 1.465735673904419} 08/31/2021 10:49:13 - INFO - __main__ - Step 119536: {'lr': 5.0477823250934665e-05, 'samples': 22950912, 'steps': 119535, 'loss/train': 1.7283058166503906} 08/31/2021 10:49:14 - INFO - __main__ - Step 119537: {'lr': 5.047462577030451e-05, 'samples': 22951104, 'steps': 119536, 'loss/train': 1.6048617362976074} 08/31/2021 10:49:14 - INFO - __main__ - Step 119538: {'lr': 5.047142837957741e-05, 'samples': 22951296, 'steps': 119537, 'loss/train': 0.11524578928947449} 08/31/2021 10:49:14 - INFO - __main__ - Step 119539: {'lr': 5.046823107875478e-05, 'samples': 22951488, 'steps': 119538, 'loss/train': 0.10279432684183121} 08/31/2021 10:49:15 - INFO - __main__ - Step 119540: {'lr': 5.0465033867838125e-05, 'samples': 22951680, 'steps': 119539, 'loss/train': 0.7056280374526978} 08/31/2021 10:49:16 - INFO - __main__ - Step 119541: {'lr': 5.0461836746828804e-05, 'samples': 22951872, 'steps': 119540, 'loss/train': 1.604336142539978} 08/31/2021 10:49:17 - INFO - __main__ - Step 119542: {'lr': 5.045863971572839e-05, 'samples': 22952064, 'steps': 119541, 'loss/train': 1.5710281133651733} 08/31/2021 10:49:17 - INFO - __main__ - Step 119543: {'lr': 5.0455442774538175e-05, 'samples': 22952256, 'steps': 119542, 'loss/train': 0.8025756478309631} 08/31/2021 10:49:17 - INFO - __main__ - Step 119544: {'lr': 5.0452245923259645e-05, 'samples': 22952448, 'steps': 119543, 'loss/train': 1.3934228420257568} 08/31/2021 10:49:18 - INFO - __main__ - Step 119545: {'lr': 5.0449049161894246e-05, 'samples': 22952640, 'steps': 119544, 'loss/train': 0.35543951392173767} 08/31/2021 10:49:19 - INFO - __main__ - Step 119546: {'lr': 5.0445852490443453e-05, 'samples': 22952832, 'steps': 119545, 'loss/train': 0.8371715545654297} 08/31/2021 10:49:20 - INFO - __main__ - Step 119547: {'lr': 5.0442655908908644e-05, 'samples': 22953024, 'steps': 119546, 'loss/train': 1.4414194822311401} 08/31/2021 10:49:20 - INFO - __main__ - Step 119548: {'lr': 5.0439459417291335e-05, 'samples': 22953216, 'steps': 119547, 'loss/train': 1.3203742504119873} 08/31/2021 10:49:21 - INFO - __main__ - Step 119549: {'lr': 5.0436263015592896e-05, 'samples': 22953408, 'steps': 119548, 'loss/train': 0.6064007878303528} 08/31/2021 10:49:21 - INFO - __main__ - Step 119550: {'lr': 5.043306670381481e-05, 'samples': 22953600, 'steps': 119549, 'loss/train': 1.4455955028533936} 08/31/2021 10:49:22 - INFO - __main__ - Step 119551: {'lr': 5.042987048195849e-05, 'samples': 22953792, 'steps': 119550, 'loss/train': 1.6113486289978027} 08/31/2021 10:49:23 - INFO - __main__ - Step 119552: {'lr': 5.0426674350025407e-05, 'samples': 22953984, 'steps': 119551, 'loss/train': 1.1183247566223145} 08/31/2021 10:49:23 - INFO - __main__ - Step 119553: {'lr': 5.042347830801705e-05, 'samples': 22954176, 'steps': 119552, 'loss/train': 1.637650966644287} 08/31/2021 10:49:24 - INFO - __main__ - Step 119554: {'lr': 5.042028235593474e-05, 'samples': 22954368, 'steps': 119553, 'loss/train': 1.4836541414260864} 08/31/2021 10:49:24 - INFO - __main__ - Step 119555: {'lr': 5.0417086493779934e-05, 'samples': 22954560, 'steps': 119554, 'loss/train': 2.01214861869812} 08/31/2021 10:49:24 - INFO - __main__ - Step 119556: {'lr': 5.041389072155414e-05, 'samples': 22954752, 'steps': 119555, 'loss/train': 0.964893639087677} 08/31/2021 10:49:26 - INFO - __main__ - Step 119557: {'lr': 5.041069503925877e-05, 'samples': 22954944, 'steps': 119556, 'loss/train': 1.1377143859863281} 08/31/2021 10:49:27 - INFO - __main__ - Step 119558: {'lr': 5.040749944689524e-05, 'samples': 22955136, 'steps': 119557, 'loss/train': 1.2606498003005981} 08/31/2021 10:49:27 - INFO - __main__ - Step 119559: {'lr': 5.0404303944465015e-05, 'samples': 22955328, 'steps': 119558, 'loss/train': 0.02686030976474285} 08/31/2021 10:49:27 - INFO - __main__ - Step 119560: {'lr': 5.0401108531969525e-05, 'samples': 22955520, 'steps': 119559, 'loss/train': 0.11657366901636124} 08/31/2021 10:49:28 - INFO - __main__ - Step 119561: {'lr': 5.039791320941023e-05, 'samples': 22955712, 'steps': 119560, 'loss/train': 0.6237803101539612} 08/31/2021 10:49:28 - INFO - __main__ - Step 119562: {'lr': 5.039471797678854e-05, 'samples': 22955904, 'steps': 119561, 'loss/train': 0.7589539885520935} 08/31/2021 10:49:30 - INFO - __main__ - Step 119563: {'lr': 5.0391522834105944e-05, 'samples': 22956096, 'steps': 119562, 'loss/train': 1.3830773830413818} 08/31/2021 10:49:31 - INFO - __main__ - Step 119564: {'lr': 5.038832778136387e-05, 'samples': 22956288, 'steps': 119563, 'loss/train': 1.1331456899642944} 08/31/2021 10:49:31 - INFO - __main__ - Step 119565: {'lr': 5.038513281856369e-05, 'samples': 22956480, 'steps': 119564, 'loss/train': 1.583655834197998} 08/31/2021 10:49:31 - INFO - __main__ - Step 119566: {'lr': 5.038193794570689e-05, 'samples': 22956672, 'steps': 119565, 'loss/train': 0.6196916103363037} 08/31/2021 10:49:33 - INFO - __main__ - Step 119567: {'lr': 5.037874316279492e-05, 'samples': 22956864, 'steps': 119566, 'loss/train': 0.6700677871704102} 08/31/2021 10:49:33 - INFO - __main__ - Step 119568: {'lr': 5.0375548469829196e-05, 'samples': 22957056, 'steps': 119567, 'loss/train': 1.0661613941192627} 08/31/2021 10:49:34 - INFO - __main__ - Step 119569: {'lr': 5.037235386681116e-05, 'samples': 22957248, 'steps': 119568, 'loss/train': 1.3986661434173584} 08/31/2021 10:49:34 - INFO - __main__ - Step 119570: {'lr': 5.0369159353742284e-05, 'samples': 22957440, 'steps': 119569, 'loss/train': 1.467930793762207} 08/31/2021 10:49:34 - INFO - __main__ - Step 119571: {'lr': 5.036596493062395e-05, 'samples': 22957632, 'steps': 119570, 'loss/train': 1.1373937129974365} 08/31/2021 10:49:36 - INFO - __main__ - Step 119572: {'lr': 5.036277059745767e-05, 'samples': 22957824, 'steps': 119571, 'loss/train': 1.124601125717163} 08/31/2021 10:49:36 - INFO - __main__ - Step 119573: {'lr': 5.035957635424482e-05, 'samples': 22958016, 'steps': 119572, 'loss/train': 0.9194849133491516} 08/31/2021 10:49:37 - INFO - __main__ - Step 119574: {'lr': 5.035638220098687e-05, 'samples': 22958208, 'steps': 119573, 'loss/train': 1.1441400051116943} 08/31/2021 10:49:37 - INFO - __main__ - Step 119575: {'lr': 5.035318813768533e-05, 'samples': 22958400, 'steps': 119574, 'loss/train': 0.5588286519050598} 08/31/2021 10:49:37 - INFO - __main__ - Step 119576: {'lr': 5.034999416434147e-05, 'samples': 22958592, 'steps': 119575, 'loss/train': 0.9733712673187256} 08/31/2021 10:49:38 - INFO - __main__ - Step 119577: {'lr': 5.034680028095684e-05, 'samples': 22958784, 'steps': 119576, 'loss/train': 0.8089199066162109} 08/31/2021 10:49:39 - INFO - __main__ - Step 119578: {'lr': 5.034360648753286e-05, 'samples': 22958976, 'steps': 119577, 'loss/train': 1.0137349367141724} 08/31/2021 10:49:40 - INFO - __main__ - Step 119579: {'lr': 5.034041278407098e-05, 'samples': 22959168, 'steps': 119578, 'loss/train': 1.113992691040039} 08/31/2021 10:49:40 - INFO - __main__ - Step 119580: {'lr': 5.03372191705726e-05, 'samples': 22959360, 'steps': 119579, 'loss/train': 1.125142216682434} 08/31/2021 10:49:41 - INFO - __main__ - Step 119581: {'lr': 5.033402564703923e-05, 'samples': 22959552, 'steps': 119580, 'loss/train': 0.2837297022342682} 08/31/2021 10:49:41 - INFO - __main__ - Step 119582: {'lr': 5.0330832213472235e-05, 'samples': 22959744, 'steps': 119581, 'loss/train': 0.7570006251335144} 08/31/2021 10:49:42 - INFO - __main__ - Step 119583: {'lr': 5.03276388698731e-05, 'samples': 22959936, 'steps': 119582, 'loss/train': 0.25937697291374207} 08/31/2021 10:49:43 - INFO - __main__ - Step 119584: {'lr': 5.032444561624325e-05, 'samples': 22960128, 'steps': 119583, 'loss/train': 1.9536978006362915} 08/31/2021 10:49:43 - INFO - __main__ - Step 119585: {'lr': 5.0321252452584094e-05, 'samples': 22960320, 'steps': 119584, 'loss/train': 0.8217077255249023} 08/31/2021 10:49:44 - INFO - __main__ - Step 119586: {'lr': 5.0318059378897193e-05, 'samples': 22960512, 'steps': 119585, 'loss/train': 0.7924891114234924} 08/31/2021 10:49:44 - INFO - __main__ - Step 119587: {'lr': 5.031486639518385e-05, 'samples': 22960704, 'steps': 119586, 'loss/train': 1.3360852003097534} 08/31/2021 10:49:46 - INFO - __main__ - Step 119588: {'lr': 5.03116735014455e-05, 'samples': 22960896, 'steps': 119587, 'loss/train': 1.0058521032333374} 08/31/2021 10:49:47 - INFO - __main__ - Step 119589: {'lr': 5.030848069768365e-05, 'samples': 22961088, 'steps': 119588, 'loss/train': 1.2654187679290771} 08/31/2021 10:49:47 - INFO - __main__ - Step 119590: {'lr': 5.0305287983899714e-05, 'samples': 22961280, 'steps': 119589, 'loss/train': 0.8427028656005859} 08/31/2021 10:49:47 - INFO - __main__ - Step 119591: {'lr': 5.030209536009514e-05, 'samples': 22961472, 'steps': 119590, 'loss/train': 1.5731921195983887} 08/31/2021 10:49:48 - INFO - __main__ - Step 119592: {'lr': 5.029890282627136e-05, 'samples': 22961664, 'steps': 119591, 'loss/train': 0.9123978018760681} 08/31/2021 10:49:48 - INFO - __main__ - Step 119593: {'lr': 5.0295710382429807e-05, 'samples': 22961856, 'steps': 119592, 'loss/train': 1.7574769258499146} 08/31/2021 10:49:48 - INFO - __main__ - Step 119594: {'lr': 5.0292518028571935e-05, 'samples': 22962048, 'steps': 119593, 'loss/train': 1.742526888847351} 08/31/2021 10:49:50 - INFO - __main__ - Step 119595: {'lr': 5.0289325764699164e-05, 'samples': 22962240, 'steps': 119594, 'loss/train': 1.326249361038208} 08/31/2021 10:49:50 - INFO - __main__ - Step 119596: {'lr': 5.028613359081294e-05, 'samples': 22962432, 'steps': 119595, 'loss/train': 1.8999555110931396} 08/31/2021 10:49:51 - INFO - __main__ - Step 119597: {'lr': 5.028294150691479e-05, 'samples': 22962624, 'steps': 119596, 'loss/train': 1.5027180910110474} 08/31/2021 10:49:51 - INFO - __main__ - Step 119598: {'lr': 5.027974951300596e-05, 'samples': 22962816, 'steps': 119597, 'loss/train': 1.162217378616333} 08/31/2021 10:49:51 - INFO - __main__ - Step 119599: {'lr': 5.027655760908803e-05, 'samples': 22963008, 'steps': 119598, 'loss/train': 1.0278440713882446} 08/31/2021 10:49:53 - INFO - __main__ - Step 119600: {'lr': 5.027336579516237e-05, 'samples': 22963200, 'steps': 119599, 'loss/train': 0.9570419788360596} 08/31/2021 10:49:54 - INFO - __main__ - Step 119601: {'lr': 5.027017407123047e-05, 'samples': 22963392, 'steps': 119600, 'loss/train': 0.8776109218597412} 08/31/2021 10:49:54 - INFO - __main__ - Step 119602: {'lr': 5.0266982437293745e-05, 'samples': 22963584, 'steps': 119601, 'loss/train': 1.159745454788208} 08/31/2021 10:49:55 - INFO - __main__ - Step 119603: {'lr': 5.026379089335362e-05, 'samples': 22963776, 'steps': 119602, 'loss/train': 0.575577974319458} 08/31/2021 10:49:55 - INFO - __main__ - Step 119604: {'lr': 5.026059943941158e-05, 'samples': 22963968, 'steps': 119603, 'loss/train': 1.3080577850341797} 08/31/2021 10:49:55 - INFO - __main__ - Step 119605: {'lr': 5.0257408075468995e-05, 'samples': 22964160, 'steps': 119604, 'loss/train': 0.46645039319992065} 08/31/2021 10:49:57 - INFO - __main__ - Step 119606: {'lr': 5.0254216801527364e-05, 'samples': 22964352, 'steps': 119605, 'loss/train': 0.4306222200393677} 08/31/2021 10:49:58 - INFO - __main__ - Step 119607: {'lr': 5.02510256175881e-05, 'samples': 22964544, 'steps': 119606, 'loss/train': 1.2468156814575195} 08/31/2021 10:49:58 - INFO - __main__ - Step 119608: {'lr': 5.0247834523652644e-05, 'samples': 22964736, 'steps': 119607, 'loss/train': 1.2589032649993896} 08/31/2021 10:49:59 - INFO - __main__ - Step 119609: {'lr': 5.024464351972241e-05, 'samples': 22964928, 'steps': 119608, 'loss/train': 1.1174317598342896} 08/31/2021 10:49:59 - INFO - __main__ - Step 119610: {'lr': 5.024145260579893e-05, 'samples': 22965120, 'steps': 119609, 'loss/train': 0.916308581829071} 08/31/2021 10:50:00 - INFO - __main__ - Step 119611: {'lr': 5.023826178188351e-05, 'samples': 22965312, 'steps': 119610, 'loss/train': 0.9143555760383606} 08/31/2021 10:50:01 - INFO - __main__ - Step 119612: {'lr': 5.0235071047977644e-05, 'samples': 22965504, 'steps': 119611, 'loss/train': 0.3757554590702057} 08/31/2021 10:50:01 - INFO - __main__ - Step 119613: {'lr': 5.0231880404082774e-05, 'samples': 22965696, 'steps': 119612, 'loss/train': 1.727689266204834} 08/31/2021 10:50:02 - INFO - __main__ - Step 119614: {'lr': 5.022868985020035e-05, 'samples': 22965888, 'steps': 119613, 'loss/train': 0.950836718082428} 08/31/2021 10:50:02 - INFO - __main__ - Step 119615: {'lr': 5.022549938633178e-05, 'samples': 22966080, 'steps': 119614, 'loss/train': 0.7504291534423828} 08/31/2021 10:50:02 - INFO - __main__ - Step 119616: {'lr': 5.022230901247851e-05, 'samples': 22966272, 'steps': 119615, 'loss/train': 1.238938808441162} 08/31/2021 10:50:04 - INFO - __main__ - Step 119617: {'lr': 5.021911872864199e-05, 'samples': 22966464, 'steps': 119616, 'loss/train': 1.2360070943832397} 08/31/2021 10:50:04 - INFO - __main__ - Step 119618: {'lr': 5.0215928534823655e-05, 'samples': 22966656, 'steps': 119617, 'loss/train': 0.47951796650886536} 08/31/2021 10:50:05 - INFO - __main__ - Step 119619: {'lr': 5.0212738431024945e-05, 'samples': 22966848, 'steps': 119618, 'loss/train': 1.4287374019622803} 08/31/2021 10:50:05 - INFO - __main__ - Step 119620: {'lr': 5.0209548417247284e-05, 'samples': 22967040, 'steps': 119619, 'loss/train': 0.9762510061264038} 08/31/2021 10:50:05 - INFO - __main__ - Step 119621: {'lr': 5.020635849349214e-05, 'samples': 22967232, 'steps': 119620, 'loss/train': 0.7224808931350708} 08/31/2021 10:50:08 - INFO - __main__ - Step 119622: {'lr': 5.020316865976091e-05, 'samples': 22967424, 'steps': 119621, 'loss/train': 0.9518700242042542} 08/31/2021 10:50:08 - INFO - __main__ - Step 119623: {'lr': 5.01999789160551e-05, 'samples': 22967616, 'steps': 119622, 'loss/train': 1.6197173595428467} 08/31/2021 10:50:09 - INFO - __main__ - Step 119624: {'lr': 5.0196789262376055e-05, 'samples': 22967808, 'steps': 119623, 'loss/train': 0.7982711791992188} 08/31/2021 10:50:09 - INFO - __main__ - Step 119625: {'lr': 5.019359969872525e-05, 'samples': 22968000, 'steps': 119624, 'loss/train': 1.9071632623672485} 08/31/2021 10:50:10 - INFO - __main__ - Step 119626: {'lr': 5.019041022510412e-05, 'samples': 22968192, 'steps': 119625, 'loss/train': 0.690172016620636} 08/31/2021 10:50:11 - INFO - __main__ - Step 119627: {'lr': 5.018722084151409e-05, 'samples': 22968384, 'steps': 119626, 'loss/train': 1.1343939304351807} 08/31/2021 10:50:12 - INFO - __main__ - Step 119628: {'lr': 5.018403154795664e-05, 'samples': 22968576, 'steps': 119627, 'loss/train': 0.8253728747367859} 08/31/2021 10:50:12 - INFO - __main__ - Step 119629: {'lr': 5.018084234443318e-05, 'samples': 22968768, 'steps': 119628, 'loss/train': 1.053714394569397} 08/31/2021 10:50:12 - INFO - __main__ - Step 119630: {'lr': 5.017765323094514e-05, 'samples': 22968960, 'steps': 119629, 'loss/train': 1.2646533250808716} 08/31/2021 10:50:13 - INFO - __main__ - Step 119631: {'lr': 5.017446420749397e-05, 'samples': 22969152, 'steps': 119630, 'loss/train': 1.3440961837768555} 08/31/2021 10:50:13 - INFO - __main__ - Step 119632: {'lr': 5.017127527408111e-05, 'samples': 22969344, 'steps': 119631, 'loss/train': 0.9615315794944763} 08/31/2021 10:50:15 - INFO - __main__ - Step 119633: {'lr': 5.016808643070797e-05, 'samples': 22969536, 'steps': 119632, 'loss/train': 1.1930869817733765} 08/31/2021 10:50:15 - INFO - __main__ - Step 119634: {'lr': 5.016489767737603e-05, 'samples': 22969728, 'steps': 119633, 'loss/train': 1.1269406080245972} 08/31/2021 10:50:16 - INFO - __main__ - Step 119635: {'lr': 5.0161709014086675e-05, 'samples': 22969920, 'steps': 119634, 'loss/train': 0.3929749131202698} 08/31/2021 10:50:16 - INFO - __main__ - Step 119636: {'lr': 5.015852044084146e-05, 'samples': 22970112, 'steps': 119635, 'loss/train': 1.166789174079895} 08/31/2021 10:50:16 - INFO - __main__ - Step 119637: {'lr': 5.0155331957641656e-05, 'samples': 22970304, 'steps': 119636, 'loss/train': 0.8758442401885986} 08/31/2021 10:50:18 - INFO - __main__ - Step 119638: {'lr': 5.015214356448877e-05, 'samples': 22970496, 'steps': 119637, 'loss/train': 0.028722472488880157} 08/31/2021 10:50:19 - INFO - __main__ - Step 119639: {'lr': 5.014895526138427e-05, 'samples': 22970688, 'steps': 119638, 'loss/train': 0.933853805065155} 08/31/2021 10:50:19 - INFO - __main__ - Step 119640: {'lr': 5.0145767048329545e-05, 'samples': 22970880, 'steps': 119639, 'loss/train': 0.16435794532299042} 08/31/2021 10:50:19 - INFO - __main__ - Step 119641: {'lr': 5.014257892532606e-05, 'samples': 22971072, 'steps': 119640, 'loss/train': 1.0821703672409058} 08/31/2021 10:50:20 - INFO - __main__ - Step 119642: {'lr': 5.013939089237523e-05, 'samples': 22971264, 'steps': 119641, 'loss/train': 0.028723571449518204} 08/31/2021 10:50:22 - INFO - __main__ - Step 119643: {'lr': 5.013620294947854e-05, 'samples': 22971456, 'steps': 119642, 'loss/train': 0.3198452293872833} 08/31/2021 10:50:22 - INFO - __main__ - Step 119644: {'lr': 5.013301509663737e-05, 'samples': 22971648, 'steps': 119643, 'loss/train': 1.2695448398590088} 08/31/2021 10:50:22 - INFO - __main__ - Step 119645: {'lr': 5.012982733385319e-05, 'samples': 22971840, 'steps': 119644, 'loss/train': 0.08460510522127151} 08/31/2021 10:50:23 - INFO - __main__ - Step 119646: {'lr': 5.0126639661127405e-05, 'samples': 22972032, 'steps': 119645, 'loss/train': 1.0734988451004028} 08/31/2021 10:50:23 - INFO - __main__ - Step 119647: {'lr': 5.01234520784615e-05, 'samples': 22972224, 'steps': 119646, 'loss/train': 1.317287802696228} 08/31/2021 10:50:24 - INFO - __main__ - Step 119648: {'lr': 5.012026458585686e-05, 'samples': 22972416, 'steps': 119647, 'loss/train': 0.8492401838302612} 08/31/2021 10:50:24 - INFO - __main__ - Step 119649: {'lr': 5.011707718331496e-05, 'samples': 22972608, 'steps': 119648, 'loss/train': 1.788312554359436} 08/31/2021 10:50:25 - INFO - __main__ - Step 119650: {'lr': 5.011388987083726e-05, 'samples': 22972800, 'steps': 119649, 'loss/train': 0.014576363377273083} 08/31/2021 10:50:26 - INFO - __main__ - Step 119651: {'lr': 5.011070264842513e-05, 'samples': 22972992, 'steps': 119650, 'loss/train': 0.5809436440467834} 08/31/2021 10:50:26 - INFO - __main__ - Step 119652: {'lr': 5.0107515516080006e-05, 'samples': 22973184, 'steps': 119651, 'loss/train': 0.7320736646652222} 08/31/2021 10:50:27 - INFO - __main__ - Step 119653: {'lr': 5.010432847380336e-05, 'samples': 22973376, 'steps': 119652, 'loss/train': 0.7941907048225403} 08/31/2021 10:50:27 - INFO - __main__ - Step 119654: {'lr': 5.010114152159661e-05, 'samples': 22973568, 'steps': 119653, 'loss/train': 0.6174429655075073} 08/31/2021 10:50:27 - INFO - __main__ - Step 119655: {'lr': 5.009795465946121e-05, 'samples': 22973760, 'steps': 119654, 'loss/train': 0.8681445717811584} 08/31/2021 10:50:30 - INFO - __main__ - Step 119656: {'lr': 5.0094767887398583e-05, 'samples': 22973952, 'steps': 119655, 'loss/train': 1.1867655515670776} 08/31/2021 10:50:30 - INFO - __main__ - Step 119657: {'lr': 5.009158120541016e-05, 'samples': 22974144, 'steps': 119656, 'loss/train': 1.7548582553863525} 08/31/2021 10:50:30 - INFO - __main__ - Step 119658: {'lr': 5.00883946134974e-05, 'samples': 22974336, 'steps': 119657, 'loss/train': 1.746458888053894} 08/31/2021 10:50:31 - INFO - __main__ - Step 119659: {'lr': 5.0085208111661726e-05, 'samples': 22974528, 'steps': 119658, 'loss/train': 0.7683065533638} 08/31/2021 10:50:31 - INFO - __main__ - Step 119660: {'lr': 5.0082021699904554e-05, 'samples': 22974720, 'steps': 119659, 'loss/train': 1.1900826692581177} 08/31/2021 10:50:31 - INFO - __main__ - Step 119661: {'lr': 5.007883537822736e-05, 'samples': 22974912, 'steps': 119660, 'loss/train': 1.2429747581481934} 08/31/2021 10:50:33 - INFO - __main__ - Step 119662: {'lr': 5.007564914663157e-05, 'samples': 22975104, 'steps': 119661, 'loss/train': 1.2530862092971802} 08/31/2021 10:50:33 - INFO - __main__ - Step 119663: {'lr': 5.007246300511864e-05, 'samples': 22975296, 'steps': 119662, 'loss/train': 1.031093716621399} 08/31/2021 10:50:34 - INFO - __main__ - Step 119664: {'lr': 5.006927695368993e-05, 'samples': 22975488, 'steps': 119663, 'loss/train': 0.0772794634103775} 08/31/2021 10:50:34 - INFO - __main__ - Step 119665: {'lr': 5.006609099234691e-05, 'samples': 22975680, 'steps': 119664, 'loss/train': 1.5383387804031372} 08/31/2021 10:50:34 - INFO - __main__ - Step 119666: {'lr': 5.0062905121091015e-05, 'samples': 22975872, 'steps': 119665, 'loss/train': 1.090488076210022} 08/31/2021 10:50:36 - INFO - __main__ - Step 119667: {'lr': 5.00597193399237e-05, 'samples': 22976064, 'steps': 119666, 'loss/train': 0.5231711864471436} 08/31/2021 10:50:36 - INFO - __main__ - Step 119668: {'lr': 5.005653364884638e-05, 'samples': 22976256, 'steps': 119667, 'loss/train': 1.2004493474960327} 08/31/2021 10:50:37 - INFO - __main__ - Step 119669: {'lr': 5.005334804786052e-05, 'samples': 22976448, 'steps': 119668, 'loss/train': 1.2149896621704102} 08/31/2021 10:50:37 - INFO - __main__ - Step 119670: {'lr': 5.005016253696751e-05, 'samples': 22976640, 'steps': 119669, 'loss/train': 0.9393226504325867} 08/31/2021 10:50:37 - INFO - __main__ - Step 119671: {'lr': 5.004697711616882e-05, 'samples': 22976832, 'steps': 119670, 'loss/train': 1.720832347869873} 08/31/2021 10:50:38 - INFO - __main__ - Step 119672: {'lr': 5.004379178546589e-05, 'samples': 22977024, 'steps': 119671, 'loss/train': 1.4273748397827148} 08/31/2021 10:50:39 - INFO - __main__ - Step 119673: {'lr': 5.004060654486014e-05, 'samples': 22977216, 'steps': 119672, 'loss/train': 0.9512815475463867} 08/31/2021 10:50:40 - INFO - __main__ - Step 119674: {'lr': 5.0037421394352994e-05, 'samples': 22977408, 'steps': 119673, 'loss/train': 1.8034380674362183} 08/31/2021 10:50:40 - INFO - __main__ - Step 119675: {'lr': 5.003423633394591e-05, 'samples': 22977600, 'steps': 119674, 'loss/train': 1.3135777711868286} 08/31/2021 10:50:40 - INFO - __main__ - Step 119676: {'lr': 5.0031051363640306e-05, 'samples': 22977792, 'steps': 119675, 'loss/train': 0.5341843962669373} 08/31/2021 10:50:41 - INFO - __main__ - Step 119677: {'lr': 5.0027866483437715e-05, 'samples': 22977984, 'steps': 119676, 'loss/train': 1.1937156915664673} 08/31/2021 10:50:43 - INFO - __main__ - Step 119678: {'lr': 5.002468169333937e-05, 'samples': 22978176, 'steps': 119677, 'loss/train': 1.652703046798706} 08/31/2021 10:50:43 - INFO - __main__ - Step 119679: {'lr': 5.002149699334685e-05, 'samples': 22978368, 'steps': 119678, 'loss/train': 0.8499290347099304} 08/31/2021 10:50:44 - INFO - __main__ - Step 119680: {'lr': 5.001831238346155e-05, 'samples': 22978560, 'steps': 119679, 'loss/train': 0.3568193316459656} 08/31/2021 10:50:44 - INFO - __main__ - Step 119681: {'lr': 5.0015127863684926e-05, 'samples': 22978752, 'steps': 119680, 'loss/train': 0.03590919449925423} 08/31/2021 10:50:45 - INFO - __main__ - Step 119682: {'lr': 5.001194343401838e-05, 'samples': 22978944, 'steps': 119681, 'loss/train': 0.21409301459789276} 08/31/2021 10:50:46 - INFO - __main__ - Step 119683: {'lr': 5.0008759094463367e-05, 'samples': 22979136, 'steps': 119682, 'loss/train': 1.1716225147247314} 08/31/2021 10:50:47 - INFO - __main__ - Step 119684: {'lr': 5.000557484502133e-05, 'samples': 22979328, 'steps': 119683, 'loss/train': 0.9909246563911438} 08/31/2021 10:50:47 - INFO - __main__ - Step 119685: {'lr': 5.00023906856937e-05, 'samples': 22979520, 'steps': 119684, 'loss/train': 1.0554869174957275} 08/31/2021 10:50:47 - INFO - __main__ - Step 119686: {'lr': 4.999920661648191e-05, 'samples': 22979712, 'steps': 119685, 'loss/train': 1.2141594886779785} 08/31/2021 10:50:48 - INFO - __main__ - Step 119687: {'lr': 4.999602263738737e-05, 'samples': 22979904, 'steps': 119686, 'loss/train': 1.6058837175369263} 08/31/2021 10:50:48 - INFO - __main__ - Step 119688: {'lr': 4.9992838748411537e-05, 'samples': 22980096, 'steps': 119687, 'loss/train': 2.3459131717681885} 08/31/2021 10:50:50 - INFO - __main__ - Step 119689: {'lr': 4.998965494955587e-05, 'samples': 22980288, 'steps': 119688, 'loss/train': 1.0770803689956665} 08/31/2021 10:50:50 - INFO - __main__ - Step 119690: {'lr': 4.9986471240821815e-05, 'samples': 22980480, 'steps': 119689, 'loss/train': 0.8639066815376282} 08/31/2021 10:50:50 - INFO - __main__ - Step 119691: {'lr': 4.9983287622210715e-05, 'samples': 22980672, 'steps': 119690, 'loss/train': 1.081424355506897} 08/31/2021 10:50:51 - INFO - __main__ - Step 119692: {'lr': 4.9980104093724084e-05, 'samples': 22980864, 'steps': 119691, 'loss/train': 1.1684530973434448} 08/31/2021 10:50:51 - INFO - __main__ - Step 119693: {'lr': 4.9976920655363304e-05, 'samples': 22981056, 'steps': 119692, 'loss/train': 1.8546358346939087} 08/31/2021 10:50:53 - INFO - __main__ - Step 119694: {'lr': 4.9973737307129844e-05, 'samples': 22981248, 'steps': 119693, 'loss/train': 1.3167427778244019} 08/31/2021 10:50:53 - INFO - __main__ - Step 119695: {'lr': 4.997055404902512e-05, 'samples': 22981440, 'steps': 119694, 'loss/train': 1.2183125019073486} 08/31/2021 10:50:54 - INFO - __main__ - Step 119696: {'lr': 4.996737088105058e-05, 'samples': 22981632, 'steps': 119695, 'loss/train': 0.6964340806007385} 08/31/2021 10:50:54 - INFO - __main__ - Step 119697: {'lr': 4.996418780320766e-05, 'samples': 22981824, 'steps': 119696, 'loss/train': 0.7407038807868958} 08/31/2021 10:50:54 - INFO - __main__ - Step 119698: {'lr': 4.996100481549781e-05, 'samples': 22982016, 'steps': 119697, 'loss/train': 1.3685657978057861} 08/31/2021 10:50:55 - INFO - __main__ - Step 119699: {'lr': 4.995782191792242e-05, 'samples': 22982208, 'steps': 119698, 'loss/train': 0.9035497903823853} 08/31/2021 10:50:56 - INFO - __main__ - Step 119700: {'lr': 4.995463911048295e-05, 'samples': 22982400, 'steps': 119699, 'loss/train': 0.8194494843482971} 08/31/2021 10:50:57 - INFO - __main__ - Step 119701: {'lr': 4.995145639318085e-05, 'samples': 22982592, 'steps': 119700, 'loss/train': 0.7361347079277039} 08/31/2021 10:50:57 - INFO - __main__ - Step 119702: {'lr': 4.9948273766017516e-05, 'samples': 22982784, 'steps': 119701, 'loss/train': 0.026814330369234085} 08/31/2021 10:50:57 - INFO - __main__ - Step 119703: {'lr': 4.994509122899441e-05, 'samples': 22982976, 'steps': 119702, 'loss/train': 1.3978029489517212} 08/31/2021 10:50:58 - INFO - __main__ - Step 119704: {'lr': 4.994190878211302e-05, 'samples': 22983168, 'steps': 119703, 'loss/train': 1.5413250923156738} 08/31/2021 10:50:59 - INFO - __main__ - Step 119705: {'lr': 4.993872642537467e-05, 'samples': 22983360, 'steps': 119704, 'loss/train': 0.8878212571144104} 08/31/2021 10:51:00 - INFO - __main__ - Step 119706: {'lr': 4.993554415878085e-05, 'samples': 22983552, 'steps': 119705, 'loss/train': 1.115090250968933} 08/31/2021 10:51:00 - INFO - __main__ - Step 119707: {'lr': 4.9932361982332945e-05, 'samples': 22983744, 'steps': 119706, 'loss/train': 1.136950135231018} 08/31/2021 10:51:01 - INFO - __main__ - Step 119708: {'lr': 4.992917989603246e-05, 'samples': 22983936, 'steps': 119707, 'loss/train': 1.1558033227920532} 08/31/2021 10:51:01 - INFO - __main__ - Step 119709: {'lr': 4.992599789988081e-05, 'samples': 22984128, 'steps': 119708, 'loss/train': 0.9393556118011475} 08/31/2021 10:51:02 - INFO - __main__ - Step 119710: {'lr': 4.992281599387938e-05, 'samples': 22984320, 'steps': 119709, 'loss/train': 1.1661900281906128} 08/31/2021 10:51:03 - INFO - __main__ - Step 119711: {'lr': 4.9919634178029665e-05, 'samples': 22984512, 'steps': 119710, 'loss/train': 1.0421329736709595} 08/31/2021 10:51:03 - INFO - __main__ - Step 119712: {'lr': 4.991645245233309e-05, 'samples': 22984704, 'steps': 119711, 'loss/train': 0.984298050403595} 08/31/2021 10:51:04 - INFO - __main__ - Step 119713: {'lr': 4.991327081679106e-05, 'samples': 22984896, 'steps': 119712, 'loss/train': 1.5934224128723145} 08/31/2021 10:51:04 - INFO - __main__ - Step 119714: {'lr': 4.9910089271405e-05, 'samples': 22985088, 'steps': 119713, 'loss/train': 0.5713057518005371} 08/31/2021 10:51:06 - INFO - __main__ - Step 119715: {'lr': 4.9906907816176405e-05, 'samples': 22985280, 'steps': 119714, 'loss/train': 0.1044151708483696} 08/31/2021 10:51:06 - INFO - __main__ - Step 119716: {'lr': 4.990372645110663e-05, 'samples': 22985472, 'steps': 119715, 'loss/train': 1.4163668155670166} 08/31/2021 10:51:06 - INFO - __main__ - Step 119717: {'lr': 4.990054517619724e-05, 'samples': 22985664, 'steps': 119716, 'loss/train': 0.660293459892273} 08/31/2021 10:51:07 - INFO - __main__ - Step 119718: {'lr': 4.989736399144954e-05, 'samples': 22985856, 'steps': 119717, 'loss/train': 0.8821769952774048} 08/31/2021 10:51:07 - INFO - __main__ - Step 119719: {'lr': 4.989418289686495e-05, 'samples': 22986048, 'steps': 119718, 'loss/train': 0.8808246850967407} 08/31/2021 10:51:09 - INFO - __main__ - Step 119720: {'lr': 4.989100189244497e-05, 'samples': 22986240, 'steps': 119719, 'loss/train': 0.9455055594444275} 08/31/2021 10:51:09 - INFO - __main__ - Step 119721: {'lr': 4.988782097819103e-05, 'samples': 22986432, 'steps': 119720, 'loss/train': 0.6253445744514465} 08/31/2021 10:51:09 - INFO - __main__ - Step 119722: {'lr': 4.9884640154104515e-05, 'samples': 22986624, 'steps': 119721, 'loss/train': 1.2490627765655518} 08/31/2021 10:51:10 - INFO - __main__ - Step 119723: {'lr': 4.988145942018693e-05, 'samples': 22986816, 'steps': 119722, 'loss/train': 1.1136053800582886} 08/31/2021 10:51:10 - INFO - __main__ - Step 119724: {'lr': 4.987827877643966e-05, 'samples': 22987008, 'steps': 119723, 'loss/train': 0.47083204984664917} 08/31/2021 10:51:11 - INFO - __main__ - Step 119725: {'lr': 4.987509822286413e-05, 'samples': 22987200, 'steps': 119724, 'loss/train': 1.14763605594635} 08/31/2021 10:51:12 - INFO - __main__ - Step 119726: {'lr': 4.9871917759461815e-05, 'samples': 22987392, 'steps': 119725, 'loss/train': 1.4791029691696167} 08/31/2021 10:51:13 - INFO - __main__ - Step 119727: {'lr': 4.986873738623412e-05, 'samples': 22987584, 'steps': 119726, 'loss/train': 1.5294603109359741} 08/31/2021 10:51:13 - INFO - __main__ - Step 119728: {'lr': 4.9865557103182465e-05, 'samples': 22987776, 'steps': 119727, 'loss/train': 1.171073079109192} 08/31/2021 10:51:13 - INFO - __main__ - Step 119729: {'lr': 4.986237691030834e-05, 'samples': 22987968, 'steps': 119728, 'loss/train': 0.059542153030633926} 08/31/2021 10:51:14 - INFO - __main__ - Step 119730: {'lr': 4.985919680761311e-05, 'samples': 22988160, 'steps': 119729, 'loss/train': 1.2342184782028198} 08/31/2021 10:51:16 - INFO - __main__ - Step 119731: {'lr': 4.9856016795098324e-05, 'samples': 22988352, 'steps': 119730, 'loss/train': 0.6663076877593994} 08/31/2021 10:51:16 - INFO - __main__ - Step 119732: {'lr': 4.9852836872765236e-05, 'samples': 22988544, 'steps': 119731, 'loss/train': 0.7989054322242737} 08/31/2021 10:51:17 - INFO - __main__ - Step 119733: {'lr': 4.984965704061539e-05, 'samples': 22988736, 'steps': 119732, 'loss/train': 0.9211482405662537} 08/31/2021 10:51:17 - INFO - __main__ - Step 119734: {'lr': 4.984647729865019e-05, 'samples': 22988928, 'steps': 119733, 'loss/train': 0.8339698910713196} 08/31/2021 10:51:17 - INFO - __main__ - Step 119735: {'lr': 4.9843297646871096e-05, 'samples': 22989120, 'steps': 119734, 'loss/train': 1.2291781902313232} 08/31/2021 10:51:19 - INFO - __main__ - Step 119736: {'lr': 4.984011808527952e-05, 'samples': 22989312, 'steps': 119735, 'loss/train': 1.1509788036346436} 08/31/2021 10:51:19 - INFO - __main__ - Step 119737: {'lr': 4.983693861387689e-05, 'samples': 22989504, 'steps': 119736, 'loss/train': 0.49338677525520325} 08/31/2021 10:51:20 - INFO - __main__ - Step 119738: {'lr': 4.983375923266464e-05, 'samples': 22989696, 'steps': 119737, 'loss/train': 0.8720282316207886} 08/31/2021 10:51:20 - INFO - __main__ - Step 119739: {'lr': 4.983057994164422e-05, 'samples': 22989888, 'steps': 119738, 'loss/train': 1.1399880647659302} 08/31/2021 10:51:20 - INFO - __main__ - Step 119740: {'lr': 4.982740074081704e-05, 'samples': 22990080, 'steps': 119739, 'loss/train': 1.2612924575805664} 08/31/2021 10:51:22 - INFO - __main__ - Step 119741: {'lr': 4.9824221630184544e-05, 'samples': 22990272, 'steps': 119740, 'loss/train': 1.3945255279541016} 08/31/2021 10:51:22 - INFO - __main__ - Step 119742: {'lr': 4.982104260974818e-05, 'samples': 22990464, 'steps': 119741, 'loss/train': 0.8337174654006958} 08/31/2021 10:51:23 - INFO - __main__ - Step 119743: {'lr': 4.9817863679509354e-05, 'samples': 22990656, 'steps': 119742, 'loss/train': 0.13682174682617188} 08/31/2021 10:51:23 - INFO - __main__ - Step 119744: {'lr': 4.9814684839469606e-05, 'samples': 22990848, 'steps': 119743, 'loss/train': 0.5925297737121582} 08/31/2021 10:51:23 - INFO - __main__ - Step 119745: {'lr': 4.981150608963017e-05, 'samples': 22991040, 'steps': 119744, 'loss/train': 1.2936393022537231} 08/31/2021 10:51:24 - INFO - __main__ - Step 119746: {'lr': 4.9808327429992585e-05, 'samples': 22991232, 'steps': 119745, 'loss/train': 1.0722427368164062} 08/31/2021 10:51:26 - INFO - __main__ - Step 119747: {'lr': 4.980514886055829e-05, 'samples': 22991424, 'steps': 119746, 'loss/train': 0.8338834047317505} 08/31/2021 10:51:26 - INFO - __main__ - Step 119748: {'lr': 4.980197038132869e-05, 'samples': 22991616, 'steps': 119747, 'loss/train': 1.2693902254104614} 08/31/2021 10:51:27 - INFO - __main__ - Step 119749: {'lr': 4.979879199230525e-05, 'samples': 22991808, 'steps': 119748, 'loss/train': 0.01676909811794758} 08/31/2021 10:51:27 - INFO - __main__ - Step 119750: {'lr': 4.979561369348939e-05, 'samples': 22992000, 'steps': 119749, 'loss/train': 1.122138261795044} 08/31/2021 10:51:27 - INFO - __main__ - Step 119751: {'lr': 4.979243548488252e-05, 'samples': 22992192, 'steps': 119750, 'loss/train': 0.4384138882160187} 08/31/2021 10:51:28 - INFO - __main__ - Step 119752: {'lr': 4.9789257366486094e-05, 'samples': 22992384, 'steps': 119751, 'loss/train': 1.4108717441558838} 08/31/2021 10:51:29 - INFO - __main__ - Step 119753: {'lr': 4.978607933830154e-05, 'samples': 22992576, 'steps': 119752, 'loss/train': 1.3671019077301025} 08/31/2021 10:51:30 - INFO - __main__ - Step 119754: {'lr': 4.9782901400330285e-05, 'samples': 22992768, 'steps': 119753, 'loss/train': 0.8848878145217896} 08/31/2021 10:51:30 - INFO - __main__ - Step 119755: {'lr': 4.9779723552573764e-05, 'samples': 22992960, 'steps': 119754, 'loss/train': 1.3617061376571655} 08/31/2021 10:51:30 - INFO - __main__ - Step 119756: {'lr': 4.9776545795033435e-05, 'samples': 22993152, 'steps': 119755, 'loss/train': 0.6645374298095703} 08/31/2021 10:51:31 - INFO - __main__ - Step 119757: {'lr': 4.977336812771074e-05, 'samples': 22993344, 'steps': 119756, 'loss/train': 1.5345349311828613} 08/31/2021 10:51:32 - INFO - __main__ - Step 119758: {'lr': 4.9770190550607024e-05, 'samples': 22993536, 'steps': 119757, 'loss/train': 1.2035695314407349} 08/31/2021 10:51:33 - INFO - __main__ - Step 119759: {'lr': 4.9767013063723775e-05, 'samples': 22993728, 'steps': 119758, 'loss/train': 1.3805171251296997} 08/31/2021 10:51:33 - INFO - __main__ - Step 119760: {'lr': 4.9763835667062416e-05, 'samples': 22993920, 'steps': 119759, 'loss/train': 0.028063423931598663} 08/31/2021 10:51:33 - INFO - __main__ - Step 119761: {'lr': 4.976065836062435e-05, 'samples': 22994112, 'steps': 119760, 'loss/train': 0.6492540240287781} 08/31/2021 10:51:34 - INFO - __main__ - Step 119762: {'lr': 4.975748114441109e-05, 'samples': 22994304, 'steps': 119761, 'loss/train': 1.2002884149551392} 08/31/2021 10:51:34 - INFO - __main__ - Step 119763: {'lr': 4.9754304018423986e-05, 'samples': 22994496, 'steps': 119762, 'loss/train': 0.5833746194839478} 08/31/2021 10:51:36 - INFO - __main__ - Step 119764: {'lr': 4.9751126982664515e-05, 'samples': 22994688, 'steps': 119763, 'loss/train': 5.305050849914551} 08/31/2021 10:51:36 - INFO - __main__ - Step 119765: {'lr': 4.9747950037134116e-05, 'samples': 22994880, 'steps': 119764, 'loss/train': 1.4270681142807007} 08/31/2021 10:51:37 - INFO - __main__ - Step 119766: {'lr': 4.974477318183418e-05, 'samples': 22995072, 'steps': 119765, 'loss/train': 0.5042482614517212} 08/31/2021 10:51:37 - INFO - __main__ - Step 119767: {'lr': 4.974159641676615e-05, 'samples': 22995264, 'steps': 119766, 'loss/train': 1.255229115486145} 08/31/2021 10:51:37 - INFO - __main__ - Step 119768: {'lr': 4.973841974193147e-05, 'samples': 22995456, 'steps': 119767, 'loss/train': 1.2662373781204224} 08/31/2021 10:51:39 - INFO - __main__ - Step 119769: {'lr': 4.9735243157331574e-05, 'samples': 22995648, 'steps': 119768, 'loss/train': 1.5210084915161133} 08/31/2021 10:51:39 - INFO - __main__ - Step 119770: {'lr': 4.9732066662967895e-05, 'samples': 22995840, 'steps': 119769, 'loss/train': 0.36457663774490356} 08/31/2021 10:51:40 - INFO - __main__ - Step 119771: {'lr': 4.972889025884192e-05, 'samples': 22996032, 'steps': 119770, 'loss/train': 1.3557296991348267} 08/31/2021 10:51:40 - INFO - __main__ - Step 119772: {'lr': 4.9725713944954956e-05, 'samples': 22996224, 'steps': 119771, 'loss/train': 1.0646296739578247} 08/31/2021 10:51:40 - INFO - __main__ - Step 119773: {'lr': 4.972253772130847e-05, 'samples': 22996416, 'steps': 119772, 'loss/train': 1.2847124338150024} 08/31/2021 10:51:42 - INFO - __main__ - Step 119774: {'lr': 4.9719361587903936e-05, 'samples': 22996608, 'steps': 119773, 'loss/train': 1.2220404148101807} 08/31/2021 10:51:43 - INFO - __main__ - Step 119775: {'lr': 4.9716185544742774e-05, 'samples': 22996800, 'steps': 119774, 'loss/train': 0.9535117149353027} 08/31/2021 10:51:43 - INFO - __main__ - Step 119776: {'lr': 4.9713009591826394e-05, 'samples': 22996992, 'steps': 119775, 'loss/train': 1.0732449293136597} 08/31/2021 10:51:43 - INFO - __main__ - Step 119777: {'lr': 4.9709833729156244e-05, 'samples': 22997184, 'steps': 119776, 'loss/train': 1.0143688917160034} 08/31/2021 10:51:44 - INFO - __main__ - Step 119778: {'lr': 4.970665795673376e-05, 'samples': 22997376, 'steps': 119777, 'loss/train': 0.8034767508506775} 08/31/2021 10:51:45 - INFO - __main__ - Step 119779: {'lr': 4.970348227456034e-05, 'samples': 22997568, 'steps': 119778, 'loss/train': 1.3003770112991333} 08/31/2021 10:51:46 - INFO - __main__ - Step 119780: {'lr': 4.970030668263748e-05, 'samples': 22997760, 'steps': 119779, 'loss/train': 0.8859542608261108} 08/31/2021 10:51:46 - INFO - __main__ - Step 119781: {'lr': 4.969713118096656e-05, 'samples': 22997952, 'steps': 119780, 'loss/train': 0.5153821706771851} 08/31/2021 10:51:47 - INFO - __main__ - Step 119782: {'lr': 4.9693955769548995e-05, 'samples': 22998144, 'steps': 119781, 'loss/train': 1.3116780519485474} 08/31/2021 10:51:47 - INFO - __main__ - Step 119783: {'lr': 4.969078044838626e-05, 'samples': 22998336, 'steps': 119782, 'loss/train': 1.1827635765075684} 08/31/2021 10:51:47 - INFO - __main__ - Step 119784: {'lr': 4.968760521747984e-05, 'samples': 22998528, 'steps': 119783, 'loss/train': 0.5149737000465393} 08/31/2021 10:51:49 - INFO - __main__ - Step 119785: {'lr': 4.9684430076831015e-05, 'samples': 22998720, 'steps': 119784, 'loss/train': 0.350103497505188} 08/31/2021 10:51:50 - INFO - __main__ - Step 119786: {'lr': 4.9681255026441304e-05, 'samples': 22998912, 'steps': 119785, 'loss/train': 1.0124588012695312} 08/31/2021 10:51:50 - INFO - __main__ - Step 119787: {'lr': 4.9678080066312136e-05, 'samples': 22999104, 'steps': 119786, 'loss/train': 0.01919102482497692} 08/31/2021 10:51:50 - INFO - __main__ - Step 119788: {'lr': 4.9674905196444906e-05, 'samples': 22999296, 'steps': 119787, 'loss/train': 0.12855151295661926} 08/31/2021 10:51:51 - INFO - __main__ - Step 119789: {'lr': 4.967173041684112e-05, 'samples': 22999488, 'steps': 119788, 'loss/train': 0.6419827938079834} 08/31/2021 10:51:51 - INFO - __main__ - Step 119790: {'lr': 4.9668555727502115e-05, 'samples': 22999680, 'steps': 119789, 'loss/train': 1.407352089881897} 08/31/2021 10:51:53 - INFO - __main__ - Step 119791: {'lr': 4.966538112842939e-05, 'samples': 22999872, 'steps': 119790, 'loss/train': 0.884726345539093} 08/31/2021 10:51:54 - INFO - __main__ - Step 119792: {'lr': 4.966220661962434e-05, 'samples': 23000064, 'steps': 119791, 'loss/train': 1.0315903425216675} 08/31/2021 10:51:54 - INFO - __main__ - Step 119793: {'lr': 4.9659032201088414e-05, 'samples': 23000256, 'steps': 119792, 'loss/train': 0.7109557390213013} 08/31/2021 10:51:54 - INFO - __main__ - Step 119794: {'lr': 4.9655857872823036e-05, 'samples': 23000448, 'steps': 119793, 'loss/train': 0.8325938582420349} 08/31/2021 10:51:55 - INFO - __main__ - Step 119795: {'lr': 4.965268363482964e-05, 'samples': 23000640, 'steps': 119794, 'loss/train': 1.206270694732666} 08/31/2021 10:51:56 - INFO - __main__ - Step 119796: {'lr': 4.9649509487109665e-05, 'samples': 23000832, 'steps': 119795, 'loss/train': 1.282341718673706} 08/31/2021 10:51:57 - INFO - __main__ - Step 119797: {'lr': 4.964633542966451e-05, 'samples': 23001024, 'steps': 119796, 'loss/train': 1.2093170881271362} 08/31/2021 10:51:57 - INFO - __main__ - Step 119798: {'lr': 4.96431614624957e-05, 'samples': 23001216, 'steps': 119797, 'loss/train': 1.306197166442871} 08/31/2021 10:51:57 - INFO - __main__ - Step 119799: {'lr': 4.9639987585604505e-05, 'samples': 23001408, 'steps': 119798, 'loss/train': 1.5238338708877563} 08/31/2021 10:51:58 - INFO - __main__ - Step 119800: {'lr': 4.963681379899246e-05, 'samples': 23001600, 'steps': 119799, 'loss/train': 0.27660825848579407} 08/31/2021 10:51:59 - INFO - __main__ - Step 119801: {'lr': 4.963364010266097e-05, 'samples': 23001792, 'steps': 119800, 'loss/train': 1.2267396450042725} 08/31/2021 10:52:00 - INFO - __main__ - Step 119802: {'lr': 4.9630466496611486e-05, 'samples': 23001984, 'steps': 119801, 'loss/train': 0.7675384879112244} 08/31/2021 10:52:00 - INFO - __main__ - Step 119803: {'lr': 4.962729298084539e-05, 'samples': 23002176, 'steps': 119802, 'loss/train': 0.022976435720920563} 08/31/2021 10:52:00 - INFO - __main__ - Step 119804: {'lr': 4.962411955536417e-05, 'samples': 23002368, 'steps': 119803, 'loss/train': 1.4515732526779175} 08/31/2021 10:52:01 - INFO - __main__ - Step 119805: {'lr': 4.962094622016922e-05, 'samples': 23002560, 'steps': 119804, 'loss/train': 0.9052743911743164} 08/31/2021 10:52:02 - INFO - __main__ - Step 119806: {'lr': 4.961777297526199e-05, 'samples': 23002752, 'steps': 119805, 'loss/train': 0.8273863792419434} 08/31/2021 10:52:03 - INFO - __main__ - Step 119807: {'lr': 4.9614599820643895e-05, 'samples': 23002944, 'steps': 119806, 'loss/train': 1.8660027980804443} 08/31/2021 10:52:03 - INFO - __main__ - Step 119808: {'lr': 4.961142675631636e-05, 'samples': 23003136, 'steps': 119807, 'loss/train': 1.2923957109451294} 08/31/2021 10:52:04 - INFO - __main__ - Step 119809: {'lr': 4.960825378228082e-05, 'samples': 23003328, 'steps': 119808, 'loss/train': 1.2195188999176025} 08/31/2021 10:52:04 - INFO - __main__ - Step 119810: {'lr': 4.960508089853871e-05, 'samples': 23003520, 'steps': 119809, 'loss/train': 0.9012718796730042} 08/31/2021 10:52:05 - INFO - __main__ - Step 119811: {'lr': 4.9601908105091546e-05, 'samples': 23003712, 'steps': 119810, 'loss/train': 0.6399447321891785} 08/31/2021 10:52:06 - INFO - __main__ - Step 119812: {'lr': 4.959873540194057e-05, 'samples': 23003904, 'steps': 119811, 'loss/train': 1.6457977294921875} 08/31/2021 10:52:06 - INFO - __main__ - Step 119813: {'lr': 4.9595562789087335e-05, 'samples': 23004096, 'steps': 119812, 'loss/train': 1.4397684335708618} 08/31/2021 10:52:07 - INFO - __main__ - Step 119814: {'lr': 4.959239026653326e-05, 'samples': 23004288, 'steps': 119813, 'loss/train': 0.9837505221366882} 08/31/2021 10:52:07 - INFO - __main__ - Step 119815: {'lr': 4.9589217834279724e-05, 'samples': 23004480, 'steps': 119814, 'loss/train': 1.134118676185608} 08/31/2021 10:52:09 - INFO - __main__ - Step 119816: {'lr': 4.958604549232823e-05, 'samples': 23004672, 'steps': 119815, 'loss/train': 1.7908326387405396} 08/31/2021 10:52:09 - INFO - __main__ - Step 119817: {'lr': 4.9582873240680145e-05, 'samples': 23004864, 'steps': 119816, 'loss/train': 1.822861671447754} 08/31/2021 10:52:09 - INFO - __main__ - Step 119818: {'lr': 4.957970107933693e-05, 'samples': 23005056, 'steps': 119817, 'loss/train': 0.12353940308094025} 08/31/2021 10:52:10 - INFO - __main__ - Step 119819: {'lr': 4.957652900830001e-05, 'samples': 23005248, 'steps': 119818, 'loss/train': 0.7941797375679016} 08/31/2021 10:52:10 - INFO - __main__ - Step 119820: {'lr': 4.957335702757082e-05, 'samples': 23005440, 'steps': 119819, 'loss/train': 1.3880099058151245} 08/31/2021 10:52:10 - INFO - __main__ - Step 119821: {'lr': 4.957018513715078e-05, 'samples': 23005632, 'steps': 119820, 'loss/train': 1.1900792121887207} 08/31/2021 10:52:12 - INFO - __main__ - Step 119822: {'lr': 4.9567013337041386e-05, 'samples': 23005824, 'steps': 119821, 'loss/train': 0.022205695509910583} 08/31/2021 10:52:13 - INFO - __main__ - Step 119823: {'lr': 4.956384162724395e-05, 'samples': 23006016, 'steps': 119822, 'loss/train': 0.06455254554748535} 08/31/2021 10:52:13 - INFO - __main__ - Step 119824: {'lr': 4.956067000775993e-05, 'samples': 23006208, 'steps': 119823, 'loss/train': 1.0644736289978027} 08/31/2021 10:52:13 - INFO - __main__ - Step 119825: {'lr': 4.955749847859078e-05, 'samples': 23006400, 'steps': 119824, 'loss/train': 0.8072724938392639} 08/31/2021 10:52:14 - INFO - __main__ - Step 119826: {'lr': 4.955432703973794e-05, 'samples': 23006592, 'steps': 119825, 'loss/train': 1.5081554651260376} 08/31/2021 10:52:15 - INFO - __main__ - Step 119827: {'lr': 4.955115569120283e-05, 'samples': 23006784, 'steps': 119826, 'loss/train': 0.027643928304314613} 08/31/2021 10:52:15 - INFO - __main__ - Step 119828: {'lr': 4.954798443298689e-05, 'samples': 23006976, 'steps': 119827, 'loss/train': 1.5637904405593872} 08/31/2021 10:52:16 - INFO - __main__ - Step 119829: {'lr': 4.954481326509153e-05, 'samples': 23007168, 'steps': 119828, 'loss/train': 1.2025353908538818} 08/31/2021 10:52:16 - INFO - __main__ - Step 119830: {'lr': 4.954164218751817e-05, 'samples': 23007360, 'steps': 119829, 'loss/train': 0.21847128868103027} 08/31/2021 10:52:17 - INFO - __main__ - Step 119831: {'lr': 4.953847120026825e-05, 'samples': 23007552, 'steps': 119830, 'loss/train': 0.9881169199943542} 08/31/2021 10:52:18 - INFO - __main__ - Step 119832: {'lr': 4.9535300303343186e-05, 'samples': 23007744, 'steps': 119831, 'loss/train': 0.556837797164917} 08/31/2021 10:52:19 - INFO - __main__ - Step 119833: {'lr': 4.953212949674452e-05, 'samples': 23007936, 'steps': 119832, 'loss/train': 1.0433577299118042} 08/31/2021 10:52:19 - INFO - __main__ - Step 119834: {'lr': 4.95289587804735e-05, 'samples': 23008128, 'steps': 119833, 'loss/train': 1.1874558925628662} 08/31/2021 10:52:19 - INFO - __main__ - Step 119835: {'lr': 4.9525788154531654e-05, 'samples': 23008320, 'steps': 119834, 'loss/train': 1.2331335544586182} 08/31/2021 10:52:20 - INFO - __main__ - Step 119836: {'lr': 4.952261761892038e-05, 'samples': 23008512, 'steps': 119835, 'loss/train': 0.9247125387191772} 08/31/2021 10:52:22 - INFO - __main__ - Step 119837: {'lr': 4.9519447173641125e-05, 'samples': 23008704, 'steps': 119836, 'loss/train': 0.34475380182266235} 08/31/2021 10:52:22 - INFO - __main__ - Step 119838: {'lr': 4.9516276818695304e-05, 'samples': 23008896, 'steps': 119837, 'loss/train': 0.7799463272094727} 08/31/2021 10:52:23 - INFO - __main__ - Step 119839: {'lr': 4.951310655408436e-05, 'samples': 23009088, 'steps': 119838, 'loss/train': 1.4184849262237549} 08/31/2021 10:52:23 - INFO - __main__ - Step 119840: {'lr': 4.950993637980972e-05, 'samples': 23009280, 'steps': 119839, 'loss/train': 1.2326393127441406} 08/31/2021 10:52:24 - INFO - __main__ - Step 119841: {'lr': 4.950676629587281e-05, 'samples': 23009472, 'steps': 119840, 'loss/train': 1.2262012958526611} 08/31/2021 10:52:25 - INFO - __main__ - Step 119842: {'lr': 4.950359630227505e-05, 'samples': 23009664, 'steps': 119841, 'loss/train': 1.3056401014328003} 08/31/2021 10:52:26 - INFO - __main__ - Step 119843: {'lr': 4.950042639901789e-05, 'samples': 23009856, 'steps': 119842, 'loss/train': 0.9430760145187378} 08/31/2021 10:52:26 - INFO - __main__ - Step 119844: {'lr': 4.94972565861028e-05, 'samples': 23010048, 'steps': 119843, 'loss/train': 0.5884994268417358} 08/31/2021 10:52:26 - INFO - __main__ - Step 119845: {'lr': 4.94940868635311e-05, 'samples': 23010240, 'steps': 119844, 'loss/train': 1.2712308168411255} 08/31/2021 10:52:27 - INFO - __main__ - Step 119846: {'lr': 4.949091723130425e-05, 'samples': 23010432, 'steps': 119845, 'loss/train': 0.8962376713752747} 08/31/2021 10:52:27 - INFO - __main__ - Step 119847: {'lr': 4.948774768942371e-05, 'samples': 23010624, 'steps': 119846, 'loss/train': 0.47866469621658325} 08/31/2021 10:52:29 - INFO - __main__ - Step 119848: {'lr': 4.94845782378909e-05, 'samples': 23010816, 'steps': 119847, 'loss/train': 1.3971973657608032} 08/31/2021 10:52:29 - INFO - __main__ - Step 119849: {'lr': 4.948140887670724e-05, 'samples': 23011008, 'steps': 119848, 'loss/train': 2.290330171585083} 08/31/2021 10:52:29 - INFO - __main__ - Step 119850: {'lr': 4.9478239605874166e-05, 'samples': 23011200, 'steps': 119849, 'loss/train': 1.359241247177124} 08/31/2021 10:52:30 - INFO - __main__ - Step 119851: {'lr': 4.947507042539309e-05, 'samples': 23011392, 'steps': 119850, 'loss/train': 1.1447852849960327} 08/31/2021 10:52:30 - INFO - __main__ - Step 119852: {'lr': 4.9471901335265465e-05, 'samples': 23011584, 'steps': 119851, 'loss/train': 0.9968975186347961} 08/31/2021 10:52:32 - INFO - __main__ - Step 119853: {'lr': 4.9468732335492705e-05, 'samples': 23011776, 'steps': 119852, 'loss/train': 1.072286605834961} 08/31/2021 10:52:32 - INFO - __main__ - Step 119854: {'lr': 4.946556342607622e-05, 'samples': 23011968, 'steps': 119853, 'loss/train': 0.8374788761138916} 08/31/2021 10:52:32 - INFO - __main__ - Step 119855: {'lr': 4.946239460701757e-05, 'samples': 23012160, 'steps': 119854, 'loss/train': 0.9408776164054871} 08/31/2021 10:52:33 - INFO - __main__ - Step 119856: {'lr': 4.945922587831797e-05, 'samples': 23012352, 'steps': 119855, 'loss/train': 1.5524708032608032} 08/31/2021 10:52:33 - INFO - __main__ - Step 119857: {'lr': 4.9456057239978954e-05, 'samples': 23012544, 'steps': 119856, 'loss/train': 1.3856955766677856} 08/31/2021 10:52:35 - INFO - __main__ - Step 119858: {'lr': 4.945288869200193e-05, 'samples': 23012736, 'steps': 119857, 'loss/train': 0.1370854526758194} 08/31/2021 10:52:35 - INFO - __main__ - Step 119859: {'lr': 4.944972023438837e-05, 'samples': 23012928, 'steps': 119858, 'loss/train': 0.7744333148002625} 08/31/2021 10:52:35 - INFO - __main__ - Step 119860: {'lr': 4.944655186713965e-05, 'samples': 23013120, 'steps': 119859, 'loss/train': 0.3473427891731262} 08/31/2021 10:52:36 - INFO - __main__ - Step 119861: {'lr': 4.944338359025724e-05, 'samples': 23013312, 'steps': 119860, 'loss/train': 1.1116247177124023} 08/31/2021 10:52:36 - INFO - __main__ - Step 119862: {'lr': 4.944021540374252e-05, 'samples': 23013504, 'steps': 119861, 'loss/train': 0.7229812741279602} 08/31/2021 10:52:38 - INFO - __main__ - Step 119863: {'lr': 4.943704730759696e-05, 'samples': 23013696, 'steps': 119862, 'loss/train': 0.9915628433227539} 08/31/2021 10:52:39 - INFO - __main__ - Step 119864: {'lr': 4.943387930182197e-05, 'samples': 23013888, 'steps': 119863, 'loss/train': 0.6096898317337036} 08/31/2021 10:52:39 - INFO - __main__ - Step 119865: {'lr': 4.9430711386419023e-05, 'samples': 23014080, 'steps': 119864, 'loss/train': 1.073913812637329} 08/31/2021 10:52:39 - INFO - __main__ - Step 119866: {'lr': 4.942754356138948e-05, 'samples': 23014272, 'steps': 119865, 'loss/train': 0.48731479048728943} 08/31/2021 10:52:40 - INFO - __main__ - Step 119867: {'lr': 4.942437582673476e-05, 'samples': 23014464, 'steps': 119866, 'loss/train': 0.6659645438194275} 08/31/2021 10:52:40 - INFO - __main__ - Step 119868: {'lr': 4.942120818245632e-05, 'samples': 23014656, 'steps': 119867, 'loss/train': 2.0748541355133057} 08/31/2021 10:52:41 - INFO - __main__ - Step 119869: {'lr': 4.9418040628555594e-05, 'samples': 23014848, 'steps': 119868, 'loss/train': 0.025903433561325073} 08/31/2021 10:52:42 - INFO - __main__ - Step 119870: {'lr': 4.9414873165034015e-05, 'samples': 23015040, 'steps': 119869, 'loss/train': 1.699480414390564} 08/31/2021 10:52:42 - INFO - __main__ - Step 119871: {'lr': 4.9411705791893e-05, 'samples': 23015232, 'steps': 119870, 'loss/train': 1.5315686464309692} 08/31/2021 10:52:43 - INFO - __main__ - Step 119872: {'lr': 4.940853850913396e-05, 'samples': 23015424, 'steps': 119871, 'loss/train': 0.029261935502290726} 08/31/2021 10:52:43 - INFO - __main__ - Step 119873: {'lr': 4.9405371316758345e-05, 'samples': 23015616, 'steps': 119872, 'loss/train': 1.7503401041030884} 08/31/2021 10:52:44 - INFO - __main__ - Step 119874: {'lr': 4.940220421476757e-05, 'samples': 23015808, 'steps': 119873, 'loss/train': 1.1649483442306519} 08/31/2021 10:52:45 - INFO - __main__ - Step 119875: {'lr': 4.9399037203163075e-05, 'samples': 23016000, 'steps': 119874, 'loss/train': 0.026756651699543} 08/31/2021 10:52:45 - INFO - __main__ - Step 119876: {'lr': 4.939587028194625e-05, 'samples': 23016192, 'steps': 119875, 'loss/train': 0.9958327412605286} 08/31/2021 10:52:45 - INFO - __main__ - Step 119877: {'lr': 4.939270345111857e-05, 'samples': 23016384, 'steps': 119876, 'loss/train': 0.9590126872062683} 08/31/2021 10:52:46 - INFO - __main__ - Step 119878: {'lr': 4.9389536710681524e-05, 'samples': 23016576, 'steps': 119877, 'loss/train': 1.4344528913497925} 08/31/2021 10:52:48 - INFO - __main__ - Step 119879: {'lr': 4.938637006063637e-05, 'samples': 23016768, 'steps': 119878, 'loss/train': 0.8113471269607544} 08/31/2021 10:52:48 - INFO - __main__ - Step 119880: {'lr': 4.938320350098463e-05, 'samples': 23016960, 'steps': 119879, 'loss/train': 1.3745735883712769} 08/31/2021 10:52:49 - INFO - __main__ - Step 119881: {'lr': 4.938003703172772e-05, 'samples': 23017152, 'steps': 119880, 'loss/train': 0.6871976852416992} 08/31/2021 10:52:49 - INFO - __main__ - Step 119882: {'lr': 4.9376870652867086e-05, 'samples': 23017344, 'steps': 119881, 'loss/train': 0.08355587720870972} 08/31/2021 10:52:49 - INFO - __main__ - Step 119883: {'lr': 4.9373704364404106e-05, 'samples': 23017536, 'steps': 119882, 'loss/train': 1.7359044551849365} 08/31/2021 10:52:51 - INFO - __main__ - Step 119884: {'lr': 4.937053816634027e-05, 'samples': 23017728, 'steps': 119883, 'loss/train': 1.3823108673095703} 08/31/2021 10:52:51 - INFO - __main__ - Step 119885: {'lr': 4.9367372058676975e-05, 'samples': 23017920, 'steps': 119884, 'loss/train': 1.5510644912719727} 08/31/2021 10:52:52 - INFO - __main__ - Step 119886: {'lr': 4.9364206041415616e-05, 'samples': 23018112, 'steps': 119885, 'loss/train': 0.1853512078523636} 08/31/2021 10:52:52 - INFO - __main__ - Step 119887: {'lr': 4.936104011455766e-05, 'samples': 23018304, 'steps': 119886, 'loss/train': 0.6187730431556702} 08/31/2021 10:52:53 - INFO - __main__ - Step 119888: {'lr': 4.935787427810454e-05, 'samples': 23018496, 'steps': 119887, 'loss/train': 1.545973539352417} 08/31/2021 10:52:54 - INFO - __main__ - Step 119889: {'lr': 4.9354708532057646e-05, 'samples': 23018688, 'steps': 119888, 'loss/train': 1.7103617191314697} 08/31/2021 10:52:55 - INFO - __main__ - Step 119890: {'lr': 4.9351542876418436e-05, 'samples': 23018880, 'steps': 119889, 'loss/train': 0.5742464065551758} 08/31/2021 10:52:55 - INFO - __main__ - Step 119891: {'lr': 4.9348377311188325e-05, 'samples': 23019072, 'steps': 119890, 'loss/train': 0.5408364534378052} 08/31/2021 10:52:55 - INFO - __main__ - Step 119892: {'lr': 4.934521183636881e-05, 'samples': 23019264, 'steps': 119891, 'loss/train': 1.2974580526351929} 08/31/2021 10:52:56 - INFO - __main__ - Step 119893: {'lr': 4.9342046451961163e-05, 'samples': 23019456, 'steps': 119892, 'loss/train': 0.7227721810340881} 08/31/2021 10:52:56 - INFO - __main__ - Step 119894: {'lr': 4.933888115796689e-05, 'samples': 23019648, 'steps': 119893, 'loss/train': 1.181427240371704} 08/31/2021 10:52:58 - INFO - __main__ - Step 119895: {'lr': 4.933571595438743e-05, 'samples': 23019840, 'steps': 119894, 'loss/train': 5.720456600189209} 08/31/2021 10:52:58 - INFO - __main__ - Step 119896: {'lr': 4.9332550841224205e-05, 'samples': 23020032, 'steps': 119895, 'loss/train': 0.8079118132591248} 08/31/2021 10:52:58 - INFO - __main__ - Step 119897: {'lr': 4.932938581847865e-05, 'samples': 23020224, 'steps': 119896, 'loss/train': 0.9617522358894348} 08/31/2021 10:52:59 - INFO - __main__ - Step 119898: {'lr': 4.932622088615216e-05, 'samples': 23020416, 'steps': 119897, 'loss/train': 1.1853536367416382} 08/31/2021 10:52:59 - INFO - __main__ - Step 119899: {'lr': 4.932305604424617e-05, 'samples': 23020608, 'steps': 119898, 'loss/train': 1.3260239362716675} 08/31/2021 10:53:01 - INFO - __main__ - Step 119900: {'lr': 4.931989129276212e-05, 'samples': 23020800, 'steps': 119899, 'loss/train': 1.1355172395706177} 08/31/2021 10:53:02 - INFO - __main__ - Step 119901: {'lr': 4.931672663170145e-05, 'samples': 23020992, 'steps': 119900, 'loss/train': 0.1075107604265213} 08/31/2021 10:53:02 - INFO - __main__ - Step 119902: {'lr': 4.931356206106555e-05, 'samples': 23021184, 'steps': 119901, 'loss/train': 1.5991235971450806} 08/31/2021 10:53:03 - INFO - __main__ - Step 119903: {'lr': 4.931039758085587e-05, 'samples': 23021376, 'steps': 119902, 'loss/train': 1.0825227499008179} 08/31/2021 10:53:03 - INFO - __main__ - Step 119904: {'lr': 4.9307233191073805e-05, 'samples': 23021568, 'steps': 119903, 'loss/train': 1.040706992149353} 08/31/2021 10:53:05 - INFO - __main__ - Step 119905: {'lr': 4.93040688917209e-05, 'samples': 23021760, 'steps': 119904, 'loss/train': 1.690829873085022} 08/31/2021 10:53:05 - INFO - __main__ - Step 119906: {'lr': 4.930090468279841e-05, 'samples': 23021952, 'steps': 119905, 'loss/train': 0.9284200072288513} 08/31/2021 10:53:05 - INFO - __main__ - Step 119907: {'lr': 4.92977405643078e-05, 'samples': 23022144, 'steps': 119906, 'loss/train': 1.2812854051589966} 08/31/2021 10:53:06 - INFO - __main__ - Step 119908: {'lr': 4.929457653625058e-05, 'samples': 23022336, 'steps': 119907, 'loss/train': 0.42330121994018555} 08/31/2021 10:53:06 - INFO - __main__ - Step 119909: {'lr': 4.92914125986281e-05, 'samples': 23022528, 'steps': 119908, 'loss/train': 0.8592944145202637} 08/31/2021 10:53:07 - INFO - __main__ - Step 119910: {'lr': 4.9288248751441835e-05, 'samples': 23022720, 'steps': 119909, 'loss/train': 2.4127962589263916} 08/31/2021 10:53:08 - INFO - __main__ - Step 119911: {'lr': 4.928508499469317e-05, 'samples': 23022912, 'steps': 119910, 'loss/train': 1.0977869033813477} 08/31/2021 10:53:08 - INFO - __main__ - Step 119912: {'lr': 4.928192132838355e-05, 'samples': 23023104, 'steps': 119911, 'loss/train': 0.9387788772583008} 08/31/2021 10:53:09 - INFO - __main__ - Step 119913: {'lr': 4.927875775251439e-05, 'samples': 23023296, 'steps': 119912, 'loss/train': 1.0768356323242188} 08/31/2021 10:53:09 - INFO - __main__ - Step 119914: {'lr': 4.927559426708714e-05, 'samples': 23023488, 'steps': 119913, 'loss/train': 1.3126877546310425} 08/31/2021 10:53:09 - INFO - __main__ - Step 119915: {'lr': 4.92724308721032e-05, 'samples': 23023680, 'steps': 119914, 'loss/train': 1.594126582145691} 08/31/2021 10:53:11 - INFO - __main__ - Step 119916: {'lr': 4.9269267567564004e-05, 'samples': 23023872, 'steps': 119915, 'loss/train': 1.110231876373291} 08/31/2021 10:53:11 - INFO - __main__ - Step 119917: {'lr': 4.926610435347098e-05, 'samples': 23024064, 'steps': 119916, 'loss/train': 1.1919699907302856} 08/31/2021 10:53:12 - INFO - __main__ - Step 119918: {'lr': 4.9262941229825556e-05, 'samples': 23024256, 'steps': 119917, 'loss/train': 1.1471549272537231} 08/31/2021 10:53:12 - INFO - __main__ - Step 119919: {'lr': 4.925977819662922e-05, 'samples': 23024448, 'steps': 119918, 'loss/train': 0.9437779188156128} 08/31/2021 10:53:13 - INFO - __main__ - Step 119920: {'lr': 4.925661525388328e-05, 'samples': 23024640, 'steps': 119919, 'loss/train': 1.7360683679580688} 08/31/2021 10:53:14 - INFO - __main__ - Step 119921: {'lr': 4.925345240158918e-05, 'samples': 23024832, 'steps': 119920, 'loss/train': 1.5444560050964355} 08/31/2021 10:53:14 - INFO - __main__ - Step 119922: {'lr': 4.9250289639748395e-05, 'samples': 23025024, 'steps': 119921, 'loss/train': 1.0382108688354492} 08/31/2021 10:53:15 - INFO - __main__ - Step 119923: {'lr': 4.9247126968362336e-05, 'samples': 23025216, 'steps': 119922, 'loss/train': 1.1588021516799927} 08/31/2021 10:53:15 - INFO - __main__ - Step 119924: {'lr': 4.924396438743242e-05, 'samples': 23025408, 'steps': 119923, 'loss/train': 1.339701533317566} 08/31/2021 10:53:16 - INFO - __main__ - Step 119925: {'lr': 4.9240801896960065e-05, 'samples': 23025600, 'steps': 119924, 'loss/train': 0.8720462322235107} 08/31/2021 10:53:17 - INFO - __main__ - Step 119926: {'lr': 4.9237639496946706e-05, 'samples': 23025792, 'steps': 119925, 'loss/train': 1.2568926811218262} 08/31/2021 10:53:17 - INFO - __main__ - Step 119927: {'lr': 4.9234477187393796e-05, 'samples': 23025984, 'steps': 119926, 'loss/train': 1.210585117340088} 08/31/2021 10:53:18 - INFO - __main__ - Step 119928: {'lr': 4.923131496830269e-05, 'samples': 23026176, 'steps': 119927, 'loss/train': 1.4850976467132568} 08/31/2021 10:53:18 - INFO - __main__ - Step 119929: {'lr': 4.922815283967489e-05, 'samples': 23026368, 'steps': 119928, 'loss/train': 1.1647475957870483} 08/31/2021 10:53:19 - INFO - __main__ - Step 119930: {'lr': 4.9224990801511774e-05, 'samples': 23026560, 'steps': 119929, 'loss/train': 0.7832951545715332} 08/31/2021 10:53:19 - INFO - __main__ - Step 119931: {'lr': 4.9221828853814795e-05, 'samples': 23026752, 'steps': 119930, 'loss/train': 0.8267862200737} 08/31/2021 10:53:20 - INFO - __main__ - Step 119932: {'lr': 4.921866699658539e-05, 'samples': 23026944, 'steps': 119931, 'loss/train': 0.4700475037097931} 08/31/2021 10:53:21 - INFO - __main__ - Step 119933: {'lr': 4.921550522982493e-05, 'samples': 23027136, 'steps': 119932, 'loss/train': 0.8728771805763245} 08/31/2021 10:53:21 - INFO - __main__ - Step 119934: {'lr': 4.921234355353482e-05, 'samples': 23027328, 'steps': 119933, 'loss/train': 0.8743515014648438} 08/31/2021 10:53:22 - INFO - __main__ - Step 119935: {'lr': 4.9209181967716566e-05, 'samples': 23027520, 'steps': 119934, 'loss/train': 0.4632091820240021} 08/31/2021 10:53:22 - INFO - __main__ - Step 119936: {'lr': 4.920602047237155e-05, 'samples': 23027712, 'steps': 119935, 'loss/train': 1.0789904594421387} 08/31/2021 10:53:24 - INFO - __main__ - Step 119937: {'lr': 4.920285906750122e-05, 'samples': 23027904, 'steps': 119936, 'loss/train': 1.4803699254989624} 08/31/2021 10:53:24 - INFO - __main__ - Step 119938: {'lr': 4.9199697753106956e-05, 'samples': 23028096, 'steps': 119937, 'loss/train': 1.069822907447815} 08/31/2021 10:53:25 - INFO - __main__ - Step 119939: {'lr': 4.9196536529190204e-05, 'samples': 23028288, 'steps': 119938, 'loss/train': 1.1302508115768433} 08/31/2021 10:53:25 - INFO - __main__ - Step 119940: {'lr': 4.9193375395752415e-05, 'samples': 23028480, 'steps': 119939, 'loss/train': 0.014247422106564045} 08/31/2021 10:53:25 - INFO - __main__ - Step 119941: {'lr': 4.919021435279497e-05, 'samples': 23028672, 'steps': 119940, 'loss/train': 1.0691560506820679} 08/31/2021 10:53:26 - INFO - __main__ - Step 119942: {'lr': 4.9187053400319345e-05, 'samples': 23028864, 'steps': 119941, 'loss/train': 1.1952732801437378} 08/31/2021 10:53:27 - INFO - __main__ - Step 119943: {'lr': 4.918389253832692e-05, 'samples': 23029056, 'steps': 119942, 'loss/train': 0.9930257797241211} 08/31/2021 10:53:28 - INFO - __main__ - Step 119944: {'lr': 4.9180731766819117e-05, 'samples': 23029248, 'steps': 119943, 'loss/train': 1.0928277969360352} 08/31/2021 10:53:28 - INFO - __main__ - Step 119945: {'lr': 4.91775710857974e-05, 'samples': 23029440, 'steps': 119944, 'loss/train': 1.0296099185943604} 08/31/2021 10:53:28 - INFO - __main__ - Step 119946: {'lr': 4.917441049526322e-05, 'samples': 23029632, 'steps': 119945, 'loss/train': 1.7115174531936646} 08/31/2021 10:53:29 - INFO - __main__ - Step 119947: {'lr': 4.917124999521791e-05, 'samples': 23029824, 'steps': 119946, 'loss/train': 0.724113404750824} 08/31/2021 10:53:31 - INFO - __main__ - Step 119948: {'lr': 4.916808958566293e-05, 'samples': 23030016, 'steps': 119947, 'loss/train': 0.11438151448965073} 08/31/2021 10:53:31 - INFO - __main__ - Step 119949: {'lr': 4.916492926659968e-05, 'samples': 23030208, 'steps': 119948, 'loss/train': 0.8879048228263855} 08/31/2021 10:53:32 - INFO - __main__ - Step 119950: {'lr': 4.916176903802966e-05, 'samples': 23030400, 'steps': 119949, 'loss/train': 1.0895026922225952} 08/31/2021 10:53:32 - INFO - __main__ - Step 119951: {'lr': 4.915860889995421e-05, 'samples': 23030592, 'steps': 119950, 'loss/train': 0.9462690949440002} 08/31/2021 10:53:32 - INFO - __main__ - Step 119952: {'lr': 4.91554488523748e-05, 'samples': 23030784, 'steps': 119951, 'loss/train': 0.656641960144043} 08/31/2021 10:53:34 - INFO - __main__ - Step 119953: {'lr': 4.915228889529286e-05, 'samples': 23030976, 'steps': 119952, 'loss/train': 1.2472732067108154} 08/31/2021 10:53:34 - INFO - __main__ - Step 119954: {'lr': 4.91491290287098e-05, 'samples': 23031168, 'steps': 119953, 'loss/train': 0.5967181921005249} 08/31/2021 10:53:35 - INFO - __main__ - Step 119955: {'lr': 4.9145969252627016e-05, 'samples': 23031360, 'steps': 119954, 'loss/train': 1.4096304178237915} 08/31/2021 10:53:35 - INFO - __main__ - Step 119956: {'lr': 4.9142809567045974e-05, 'samples': 23031552, 'steps': 119955, 'loss/train': 1.5294123888015747} 08/31/2021 10:53:35 - INFO - __main__ - Step 119957: {'lr': 4.91396499719681e-05, 'samples': 23031744, 'steps': 119956, 'loss/train': 1.5819696187973022} 08/31/2021 10:53:37 - INFO - __main__ - Step 119958: {'lr': 4.9136490467394765e-05, 'samples': 23031936, 'steps': 119957, 'loss/train': 0.692837655544281} 08/31/2021 10:53:38 - INFO - __main__ - Step 119959: {'lr': 4.913333105332754e-05, 'samples': 23032128, 'steps': 119958, 'loss/train': 1.4990090131759644} 08/31/2021 10:53:38 - INFO - __main__ - Step 119960: {'lr': 4.913017172976764e-05, 'samples': 23032320, 'steps': 119959, 'loss/train': 0.6486883759498596} 08/31/2021 10:53:38 - INFO - __main__ - Step 119961: {'lr': 4.9127012496716585e-05, 'samples': 23032512, 'steps': 119960, 'loss/train': 0.016438474878668785} 08/31/2021 10:53:39 - INFO - __main__ - Step 119962: {'lr': 4.91238533541758e-05, 'samples': 23032704, 'steps': 119961, 'loss/train': 0.7960349321365356} 08/31/2021 10:53:39 - INFO - __main__ - Step 119963: {'lr': 4.912069430214672e-05, 'samples': 23032896, 'steps': 119962, 'loss/train': 0.6431553959846497} 08/31/2021 10:53:41 - INFO - __main__ - Step 119964: {'lr': 4.9117535340630736e-05, 'samples': 23033088, 'steps': 119963, 'loss/train': 1.0795713663101196} 08/31/2021 10:53:41 - INFO - __main__ - Step 119965: {'lr': 4.91143764696293e-05, 'samples': 23033280, 'steps': 119964, 'loss/train': 0.9240149259567261} 08/31/2021 10:53:41 - INFO - __main__ - Step 119966: {'lr': 4.911121768914381e-05, 'samples': 23033472, 'steps': 119965, 'loss/train': 0.8910410404205322} 08/31/2021 10:53:42 - INFO - __main__ - Step 119967: {'lr': 4.910805899917573e-05, 'samples': 23033664, 'steps': 119966, 'loss/train': 1.202121376991272} 08/31/2021 10:53:42 - INFO - __main__ - Step 119968: {'lr': 4.9104900399726454e-05, 'samples': 23033856, 'steps': 119967, 'loss/train': 1.684966802597046} 08/31/2021 10:53:43 - INFO - __main__ - Step 119969: {'lr': 4.9101741890797415e-05, 'samples': 23034048, 'steps': 119968, 'loss/train': 1.2184115648269653} 08/31/2021 10:53:44 - INFO - __main__ - Step 119970: {'lr': 4.9098583472390015e-05, 'samples': 23034240, 'steps': 119969, 'loss/train': 1.8427844047546387} 08/31/2021 10:53:44 - INFO - __main__ - Step 119971: {'lr': 4.909542514450571e-05, 'samples': 23034432, 'steps': 119970, 'loss/train': 0.9385855197906494} 08/31/2021 10:53:45 - INFO - __main__ - Step 119972: {'lr': 4.9092266907145884e-05, 'samples': 23034624, 'steps': 119971, 'loss/train': 1.3405781984329224} 08/31/2021 10:53:45 - INFO - __main__ - Step 119973: {'lr': 4.908910876031206e-05, 'samples': 23034816, 'steps': 119972, 'loss/train': 0.9405722618103027} 08/31/2021 10:53:45 - INFO - __main__ - Step 119974: {'lr': 4.908595070400551e-05, 'samples': 23035008, 'steps': 119973, 'loss/train': 1.4319446086883545} 08/31/2021 10:53:47 - INFO - __main__ - Step 119975: {'lr': 4.9082792738227745e-05, 'samples': 23035200, 'steps': 119974, 'loss/train': 1.38857102394104} 08/31/2021 10:53:48 - INFO - __main__ - Step 119976: {'lr': 4.907963486298017e-05, 'samples': 23035392, 'steps': 119975, 'loss/train': 0.38333678245544434} 08/31/2021 10:53:48 - INFO - __main__ - Step 119977: {'lr': 4.907647707826421e-05, 'samples': 23035584, 'steps': 119976, 'loss/train': 0.9941232800483704} 08/31/2021 10:53:48 - INFO - __main__ - Step 119978: {'lr': 4.90733193840813e-05, 'samples': 23035776, 'steps': 119977, 'loss/train': 1.7763006687164307} 08/31/2021 10:53:49 - INFO - __main__ - Step 119979: {'lr': 4.907016178043283e-05, 'samples': 23035968, 'steps': 119978, 'loss/train': 1.4428800344467163} 08/31/2021 10:53:51 - INFO - __main__ - Step 119980: {'lr': 4.9067004267320245e-05, 'samples': 23036160, 'steps': 119979, 'loss/train': 1.6529210805892944} 08/31/2021 10:53:51 - INFO - __main__ - Step 119981: {'lr': 4.906384684474499e-05, 'samples': 23036352, 'steps': 119980, 'loss/train': 0.9240065813064575} 08/31/2021 10:53:51 - INFO - __main__ - Step 119982: {'lr': 4.906068951270845e-05, 'samples': 23036544, 'steps': 119981, 'loss/train': 0.7652552723884583} 08/31/2021 10:53:52 - INFO - __main__ - Step 119983: {'lr': 4.905753227121204e-05, 'samples': 23036736, 'steps': 119982, 'loss/train': 0.9217451810836792} 08/31/2021 10:53:52 - INFO - __main__ - Step 119984: {'lr': 4.905437512025723e-05, 'samples': 23036928, 'steps': 119983, 'loss/train': 1.2065573930740356} 08/31/2021 10:53:53 - INFO - __main__ - Step 119985: {'lr': 4.9051218059845444e-05, 'samples': 23037120, 'steps': 119984, 'loss/train': 0.9682162404060364} 08/31/2021 10:53:54 - INFO - __main__ - Step 119986: {'lr': 4.904806108997811e-05, 'samples': 23037312, 'steps': 119985, 'loss/train': 0.5431162118911743} 08/31/2021 10:53:54 - INFO - __main__ - Step 119987: {'lr': 4.904490421065655e-05, 'samples': 23037504, 'steps': 119986, 'loss/train': 1.1492401361465454} 08/31/2021 10:53:55 - INFO - __main__ - Step 119988: {'lr': 4.904174742188228e-05, 'samples': 23037696, 'steps': 119987, 'loss/train': 1.2495263814926147} 08/31/2021 10:53:55 - INFO - __main__ - Step 119989: {'lr': 4.903859072365666e-05, 'samples': 23037888, 'steps': 119988, 'loss/train': 0.36579206585884094} 08/31/2021 10:53:56 - INFO - __main__ - Step 119990: {'lr': 4.903543411598119e-05, 'samples': 23038080, 'steps': 119989, 'loss/train': 0.9179809093475342} 08/31/2021 10:53:57 - INFO - __main__ - Step 119991: {'lr': 4.9032277598857225e-05, 'samples': 23038272, 'steps': 119990, 'loss/train': 1.2174735069274902} 08/31/2021 10:53:57 - INFO - __main__ - Step 119992: {'lr': 4.902912117228622e-05, 'samples': 23038464, 'steps': 119991, 'loss/train': 1.454068899154663} 08/31/2021 10:53:58 - INFO - __main__ - Step 119993: {'lr': 4.902596483626959e-05, 'samples': 23038656, 'steps': 119992, 'loss/train': 1.0959826707839966} 08/31/2021 10:53:58 - INFO - __main__ - Step 119994: {'lr': 4.902280859080876e-05, 'samples': 23038848, 'steps': 119993, 'loss/train': 1.5381903648376465} 08/31/2021 10:53:58 - INFO - __main__ - Step 119995: {'lr': 4.9019652435905174e-05, 'samples': 23039040, 'steps': 119994, 'loss/train': 1.72261381149292} 08/31/2021 10:54:00 - INFO - __main__ - Step 119996: {'lr': 4.901649637156022e-05, 'samples': 23039232, 'steps': 119995, 'loss/train': 1.1717051267623901} 08/31/2021 10:54:00 - INFO - __main__ - Step 119997: {'lr': 4.90133403977753e-05, 'samples': 23039424, 'steps': 119996, 'loss/train': 1.1826457977294922} 08/31/2021 10:54:01 - INFO - __main__ - Step 119998: {'lr': 4.901018451455191e-05, 'samples': 23039616, 'steps': 119997, 'loss/train': 1.0883736610412598} 08/31/2021 10:54:01 - INFO - __main__ - Step 119999: {'lr': 4.9007028721891415e-05, 'samples': 23039808, 'steps': 119998, 'loss/train': 1.4473236799240112} 08/31/2021 10:54:01 - INFO - __main__ - Step 120000: {'lr': 4.900387301979531e-05, 'samples': 23040000, 'steps': 119999, 'loss/train': 1.080132007598877} 08/31/2021 10:54:01 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 11:02:45 - INFO - __main__ - Step 120000: {'loss/eval': 0.9812400937080383, 'perplexity': 2.667762517929077} 08/31/2021 11:02:45 - INFO - __main__ - Saving model checkpoint 08/31/2021 11:03:46 - INFO - __main__ - Step 120001: {'lr': 4.900071740826489e-05, 'samples': 23040192, 'steps': 120000, 'loss/train': 1.0667316913604736} 08/31/2021 11:03:46 - INFO - __main__ - Step 120002: {'lr': 4.8997561887301646e-05, 'samples': 23040384, 'steps': 120001, 'loss/train': 1.0216734409332275} 08/31/2021 11:03:46 - INFO - __main__ - Step 120003: {'lr': 4.8994406456907e-05, 'samples': 23040576, 'steps': 120002, 'loss/train': 0.5475693345069885} 08/31/2021 11:03:47 - INFO - __main__ - Step 120004: {'lr': 4.899125111708239e-05, 'samples': 23040768, 'steps': 120003, 'loss/train': 0.7656961679458618} 08/31/2021 11:03:47 - INFO - __main__ - Step 120005: {'lr': 4.8988095867829204e-05, 'samples': 23040960, 'steps': 120004, 'loss/train': 0.818742573261261} 08/31/2021 11:03:49 - INFO - __main__ - Step 120006: {'lr': 4.898494070914889e-05, 'samples': 23041152, 'steps': 120005, 'loss/train': 0.20741325616836548} 08/31/2021 11:03:50 - INFO - __main__ - Step 120007: {'lr': 4.898178564104286e-05, 'samples': 23041344, 'steps': 120006, 'loss/train': 0.40705111622810364} 08/31/2021 11:03:50 - INFO - __main__ - Step 120008: {'lr': 4.897863066351252e-05, 'samples': 23041536, 'steps': 120007, 'loss/train': 0.948672890663147} 08/31/2021 11:03:51 - INFO - __main__ - Step 120009: {'lr': 4.897547577655931e-05, 'samples': 23041728, 'steps': 120008, 'loss/train': 1.2413498163223267} 08/31/2021 11:03:51 - INFO - __main__ - Step 120010: {'lr': 4.897232098018467e-05, 'samples': 23041920, 'steps': 120009, 'loss/train': 0.3229791522026062} 08/31/2021 11:03:52 - INFO - __main__ - Step 120011: {'lr': 4.896916627438999e-05, 'samples': 23042112, 'steps': 120010, 'loss/train': 1.0646922588348389} 08/31/2021 11:03:53 - INFO - __main__ - Step 120012: {'lr': 4.896601165917669e-05, 'samples': 23042304, 'steps': 120011, 'loss/train': 0.36036911606788635} 08/31/2021 11:03:53 - INFO - __main__ - Step 120013: {'lr': 4.8962857134546265e-05, 'samples': 23042496, 'steps': 120012, 'loss/train': 0.9018886685371399} 08/31/2021 11:03:53 - INFO - __main__ - Step 120014: {'lr': 4.895970270050001e-05, 'samples': 23042688, 'steps': 120013, 'loss/train': 1.1858290433883667} 08/31/2021 11:03:54 - INFO - __main__ - Step 120015: {'lr': 4.895654835703944e-05, 'samples': 23042880, 'steps': 120014, 'loss/train': 0.368141233921051} 08/31/2021 11:03:56 - INFO - __main__ - Step 120016: {'lr': 4.895339410416591e-05, 'samples': 23043072, 'steps': 120015, 'loss/train': 1.329045295715332} 08/31/2021 11:03:56 - INFO - __main__ - Step 120017: {'lr': 4.8950239941880916e-05, 'samples': 23043264, 'steps': 120016, 'loss/train': 1.5501203536987305} 08/31/2021 11:03:57 - INFO - __main__ - Step 120018: {'lr': 4.894708587018582e-05, 'samples': 23043456, 'steps': 120017, 'loss/train': 0.11691209673881531} 08/31/2021 11:03:57 - INFO - __main__ - Step 120019: {'lr': 4.894393188908206e-05, 'samples': 23043648, 'steps': 120018, 'loss/train': 1.5245566368103027} 08/31/2021 11:03:57 - INFO - __main__ - Step 120020: {'lr': 4.894077799857105e-05, 'samples': 23043840, 'steps': 120019, 'loss/train': 0.9822481274604797} 08/31/2021 11:03:58 - INFO - __main__ - Step 120021: {'lr': 4.893762419865425e-05, 'samples': 23044032, 'steps': 120020, 'loss/train': 1.5649571418762207} 08/31/2021 11:03:59 - INFO - __main__ - Step 120022: {'lr': 4.8934470489333056e-05, 'samples': 23044224, 'steps': 120021, 'loss/train': 1.7457213401794434} 08/31/2021 11:04:00 - INFO - __main__ - Step 120023: {'lr': 4.893131687060886e-05, 'samples': 23044416, 'steps': 120022, 'loss/train': 0.7591381072998047} 08/31/2021 11:04:00 - INFO - __main__ - Step 120024: {'lr': 4.8928163342483124e-05, 'samples': 23044608, 'steps': 120023, 'loss/train': 0.20356141030788422} 08/31/2021 11:04:00 - INFO - __main__ - Step 120025: {'lr': 4.892500990495727e-05, 'samples': 23044800, 'steps': 120024, 'loss/train': 1.9101104736328125} 08/31/2021 11:04:01 - INFO - __main__ - Step 120026: {'lr': 4.892185655803275e-05, 'samples': 23044992, 'steps': 120025, 'loss/train': 0.8118762373924255} 08/31/2021 11:04:02 - INFO - __main__ - Step 120027: {'lr': 4.8918703301710884e-05, 'samples': 23045184, 'steps': 120026, 'loss/train': 0.5593397617340088} 08/31/2021 11:04:03 - INFO - __main__ - Step 120028: {'lr': 4.891555013599314e-05, 'samples': 23045376, 'steps': 120027, 'loss/train': 1.0160435438156128} 08/31/2021 11:04:03 - INFO - __main__ - Step 120029: {'lr': 4.8912397060880935e-05, 'samples': 23045568, 'steps': 120028, 'loss/train': 1.4641571044921875} 08/31/2021 11:04:03 - INFO - __main__ - Step 120030: {'lr': 4.890924407637573e-05, 'samples': 23045760, 'steps': 120029, 'loss/train': 2.8274102210998535} 08/31/2021 11:04:04 - INFO - __main__ - Step 120031: {'lr': 4.890609118247888e-05, 'samples': 23045952, 'steps': 120030, 'loss/train': 0.7292611002922058} 08/31/2021 11:04:04 - INFO - __main__ - Step 120032: {'lr': 4.890293837919188e-05, 'samples': 23046144, 'steps': 120031, 'loss/train': 0.8570055365562439} 08/31/2021 11:04:06 - INFO - __main__ - Step 120033: {'lr': 4.889978566651609e-05, 'samples': 23046336, 'steps': 120032, 'loss/train': 1.0724245309829712} 08/31/2021 11:04:06 - INFO - __main__ - Step 120034: {'lr': 4.8896633044452966e-05, 'samples': 23046528, 'steps': 120033, 'loss/train': 1.3974252939224243} 08/31/2021 11:04:07 - INFO - __main__ - Step 120035: {'lr': 4.8893480513003906e-05, 'samples': 23046720, 'steps': 120034, 'loss/train': 1.788021206855774} 08/31/2021 11:04:07 - INFO - __main__ - Step 120036: {'lr': 4.8890328072170336e-05, 'samples': 23046912, 'steps': 120035, 'loss/train': 1.4181674718856812} 08/31/2021 11:04:07 - INFO - __main__ - Step 120037: {'lr': 4.88871757219537e-05, 'samples': 23047104, 'steps': 120036, 'loss/train': 1.1535286903381348} 08/31/2021 11:04:09 - INFO - __main__ - Step 120038: {'lr': 4.888402346235538e-05, 'samples': 23047296, 'steps': 120037, 'loss/train': 1.2416417598724365} 08/31/2021 11:04:09 - INFO - __main__ - Step 120039: {'lr': 4.8880871293376816e-05, 'samples': 23047488, 'steps': 120038, 'loss/train': 1.7159781455993652} 08/31/2021 11:04:10 - INFO - __main__ - Step 120040: {'lr': 4.887771921501949e-05, 'samples': 23047680, 'steps': 120039, 'loss/train': 1.3964426517486572} 08/31/2021 11:04:10 - INFO - __main__ - Step 120041: {'lr': 4.887456722728473e-05, 'samples': 23047872, 'steps': 120040, 'loss/train': 1.296535611152649} 08/31/2021 11:04:10 - INFO - __main__ - Step 120042: {'lr': 4.8871415330173946e-05, 'samples': 23048064, 'steps': 120041, 'loss/train': 1.4040858745574951} 08/31/2021 11:04:12 - INFO - __main__ - Step 120043: {'lr': 4.8868263523688616e-05, 'samples': 23048256, 'steps': 120042, 'loss/train': 0.6504566669464111} 08/31/2021 11:04:12 - INFO - __main__ - Step 120044: {'lr': 4.8865111807830125e-05, 'samples': 23048448, 'steps': 120043, 'loss/train': 1.3430026769638062} 08/31/2021 11:04:13 - INFO - __main__ - Step 120045: {'lr': 4.8861960182599945e-05, 'samples': 23048640, 'steps': 120044, 'loss/train': 1.7870746850967407} 08/31/2021 11:04:13 - INFO - __main__ - Step 120046: {'lr': 4.885880864799944e-05, 'samples': 23048832, 'steps': 120045, 'loss/train': 0.9681476950645447} 08/31/2021 11:04:13 - INFO - __main__ - Step 120047: {'lr': 4.885565720403007e-05, 'samples': 23049024, 'steps': 120046, 'loss/train': 0.8281185030937195} 08/31/2021 11:04:15 - INFO - __main__ - Step 120048: {'lr': 4.88525058506932e-05, 'samples': 23049216, 'steps': 120047, 'loss/train': 0.8798233270645142} 08/31/2021 11:04:15 - INFO - __main__ - Step 120049: {'lr': 4.884935458799031e-05, 'samples': 23049408, 'steps': 120048, 'loss/train': 0.9306758642196655} 08/31/2021 11:04:16 - INFO - __main__ - Step 120050: {'lr': 4.8846203415922804e-05, 'samples': 23049600, 'steps': 120049, 'loss/train': 0.7212159037590027} 08/31/2021 11:04:16 - INFO - __main__ - Step 120051: {'lr': 4.88430523344921e-05, 'samples': 23049792, 'steps': 120050, 'loss/train': 0.9745286107063293} 08/31/2021 11:04:17 - INFO - __main__ - Step 120052: {'lr': 4.8839901343699586e-05, 'samples': 23049984, 'steps': 120051, 'loss/train': 0.5797576308250427} 08/31/2021 11:04:18 - INFO - __main__ - Step 120053: {'lr': 4.883675044354679e-05, 'samples': 23050176, 'steps': 120052, 'loss/train': 0.967129647731781} 08/31/2021 11:04:18 - INFO - __main__ - Step 120054: {'lr': 4.883359963403497e-05, 'samples': 23050368, 'steps': 120053, 'loss/train': 0.6562988758087158} 08/31/2021 11:04:19 - INFO - __main__ - Step 120055: {'lr': 4.883044891516564e-05, 'samples': 23050560, 'steps': 120054, 'loss/train': 1.2830220460891724} 08/31/2021 11:04:19 - INFO - __main__ - Step 120056: {'lr': 4.882729828694021e-05, 'samples': 23050752, 'steps': 120055, 'loss/train': 1.33364999294281} 08/31/2021 11:04:19 - INFO - __main__ - Step 120057: {'lr': 4.882414774936009e-05, 'samples': 23050944, 'steps': 120056, 'loss/train': 1.011740803718567} 08/31/2021 11:04:20 - INFO - __main__ - Step 120058: {'lr': 4.88209973024267e-05, 'samples': 23051136, 'steps': 120057, 'loss/train': 1.2082154750823975} 08/31/2021 11:04:22 - INFO - __main__ - Step 120059: {'lr': 4.881784694614147e-05, 'samples': 23051328, 'steps': 120058, 'loss/train': 0.7356204986572266} 08/31/2021 11:04:22 - INFO - __main__ - Step 120060: {'lr': 4.881469668050581e-05, 'samples': 23051520, 'steps': 120059, 'loss/train': 0.4863114058971405} 08/31/2021 11:04:22 - INFO - __main__ - Step 120061: {'lr': 4.881154650552114e-05, 'samples': 23051712, 'steps': 120060, 'loss/train': 1.0415667295455933} 08/31/2021 11:04:23 - INFO - __main__ - Step 120062: {'lr': 4.8808396421188896e-05, 'samples': 23051904, 'steps': 120061, 'loss/train': 1.6036421060562134} 08/31/2021 11:04:23 - INFO - __main__ - Step 120063: {'lr': 4.880524642751047e-05, 'samples': 23052096, 'steps': 120062, 'loss/train': 1.0437287092208862} 08/31/2021 11:04:25 - INFO - __main__ - Step 120064: {'lr': 4.880209652448731e-05, 'samples': 23052288, 'steps': 120063, 'loss/train': 1.685312032699585} 08/31/2021 11:04:26 - INFO - __main__ - Step 120065: {'lr': 4.8798946712120816e-05, 'samples': 23052480, 'steps': 120064, 'loss/train': 0.941399872303009} 08/31/2021 11:04:26 - INFO - __main__ - Step 120066: {'lr': 4.8795796990412397e-05, 'samples': 23052672, 'steps': 120065, 'loss/train': 1.5896570682525635} 08/31/2021 11:04:26 - INFO - __main__ - Step 120067: {'lr': 4.879264735936356e-05, 'samples': 23052864, 'steps': 120066, 'loss/train': 1.441210389137268} 08/31/2021 11:04:27 - INFO - __main__ - Step 120068: {'lr': 4.87894978189756e-05, 'samples': 23053056, 'steps': 120067, 'loss/train': 1.5637072324752808} 08/31/2021 11:04:28 - INFO - __main__ - Step 120069: {'lr': 4.8786348369249975e-05, 'samples': 23053248, 'steps': 120068, 'loss/train': 0.09709151834249496} 08/31/2021 11:04:29 - INFO - __main__ - Step 120070: {'lr': 4.87831990101881e-05, 'samples': 23053440, 'steps': 120069, 'loss/train': 0.9207898378372192} 08/31/2021 11:04:29 - INFO - __main__ - Step 120071: {'lr': 4.8780049741791426e-05, 'samples': 23053632, 'steps': 120070, 'loss/train': 1.808172345161438} 08/31/2021 11:04:29 - INFO - __main__ - Step 120072: {'lr': 4.877690056406137e-05, 'samples': 23053824, 'steps': 120071, 'loss/train': 1.2274398803710938} 08/31/2021 11:04:30 - INFO - __main__ - Step 120073: {'lr': 4.8773751476999336e-05, 'samples': 23054016, 'steps': 120072, 'loss/train': 1.0911846160888672} 08/31/2021 11:04:31 - INFO - __main__ - Step 120074: {'lr': 4.877060248060672e-05, 'samples': 23054208, 'steps': 120073, 'loss/train': 1.2557777166366577} 08/31/2021 11:04:32 - INFO - __main__ - Step 120075: {'lr': 4.876745357488499e-05, 'samples': 23054400, 'steps': 120074, 'loss/train': 0.9328652024269104} 08/31/2021 11:04:32 - INFO - __main__ - Step 120076: {'lr': 4.8764304759835534e-05, 'samples': 23054592, 'steps': 120075, 'loss/train': 1.3379770517349243} 08/31/2021 11:04:32 - INFO - __main__ - Step 120077: {'lr': 4.876115603545978e-05, 'samples': 23054784, 'steps': 120076, 'loss/train': 0.7106872200965881} 08/31/2021 11:04:33 - INFO - __main__ - Step 120078: {'lr': 4.875800740175912e-05, 'samples': 23054976, 'steps': 120077, 'loss/train': 0.968997061252594} 08/31/2021 11:04:34 - INFO - __main__ - Step 120079: {'lr': 4.8754858858735014e-05, 'samples': 23055168, 'steps': 120078, 'loss/train': 0.6921579837799072} 08/31/2021 11:04:35 - INFO - __main__ - Step 120080: {'lr': 4.875171040638893e-05, 'samples': 23055360, 'steps': 120079, 'loss/train': 1.442907691001892} 08/31/2021 11:04:35 - INFO - __main__ - Step 120081: {'lr': 4.8748562044722166e-05, 'samples': 23055552, 'steps': 120080, 'loss/train': 1.130306363105774} 08/31/2021 11:04:35 - INFO - __main__ - Step 120082: {'lr': 4.8745413773736176e-05, 'samples': 23055744, 'steps': 120081, 'loss/train': 0.8288522362709045} 08/31/2021 11:04:36 - INFO - __main__ - Step 120083: {'lr': 4.8742265593432394e-05, 'samples': 23055936, 'steps': 120082, 'loss/train': 1.2213084697723389} 08/31/2021 11:04:36 - INFO - __main__ - Step 120084: {'lr': 4.8739117503812245e-05, 'samples': 23056128, 'steps': 120083, 'loss/train': 0.6785884499549866} 08/31/2021 11:04:38 - INFO - __main__ - Step 120085: {'lr': 4.873596950487716e-05, 'samples': 23056320, 'steps': 120084, 'loss/train': 1.0940080881118774} 08/31/2021 11:04:38 - INFO - __main__ - Step 120086: {'lr': 4.8732821596628534e-05, 'samples': 23056512, 'steps': 120085, 'loss/train': 1.2303502559661865} 08/31/2021 11:04:38 - INFO - __main__ - Step 120087: {'lr': 4.8729673779067784e-05, 'samples': 23056704, 'steps': 120086, 'loss/train': 1.2834699153900146} 08/31/2021 11:04:39 - INFO - __main__ - Step 120088: {'lr': 4.8726526052196325e-05, 'samples': 23056896, 'steps': 120087, 'loss/train': 1.5071611404418945} 08/31/2021 11:04:39 - INFO - __main__ - Step 120089: {'lr': 4.8723378416015626e-05, 'samples': 23057088, 'steps': 120088, 'loss/train': 1.0890945196151733} 08/31/2021 11:04:41 - INFO - __main__ - Step 120090: {'lr': 4.872023087052704e-05, 'samples': 23057280, 'steps': 120089, 'loss/train': 0.8140194416046143} 08/31/2021 11:04:41 - INFO - __main__ - Step 120091: {'lr': 4.871708341573208e-05, 'samples': 23057472, 'steps': 120090, 'loss/train': 1.3026056289672852} 08/31/2021 11:04:41 - INFO - __main__ - Step 120092: {'lr': 4.871393605163202e-05, 'samples': 23057664, 'steps': 120091, 'loss/train': 1.0191693305969238} 08/31/2021 11:04:42 - INFO - __main__ - Step 120093: {'lr': 4.8710788778228375e-05, 'samples': 23057856, 'steps': 120092, 'loss/train': 0.3990698754787445} 08/31/2021 11:04:42 - INFO - __main__ - Step 120094: {'lr': 4.8707641595522546e-05, 'samples': 23058048, 'steps': 120093, 'loss/train': 1.5370219945907593} 08/31/2021 11:04:44 - INFO - __main__ - Step 120095: {'lr': 4.870449450351594e-05, 'samples': 23058240, 'steps': 120094, 'loss/train': 1.129604458808899} 08/31/2021 11:04:44 - INFO - __main__ - Step 120096: {'lr': 4.870134750220998e-05, 'samples': 23058432, 'steps': 120095, 'loss/train': 1.0861159563064575} 08/31/2021 11:04:44 - INFO - __main__ - Step 120097: {'lr': 4.869820059160607e-05, 'samples': 23058624, 'steps': 120096, 'loss/train': 1.3417168855667114} 08/31/2021 11:04:45 - INFO - __main__ - Step 120098: {'lr': 4.869505377170566e-05, 'samples': 23058816, 'steps': 120097, 'loss/train': 1.3171181678771973} 08/31/2021 11:04:45 - INFO - __main__ - Step 120099: {'lr': 4.869190704251017e-05, 'samples': 23059008, 'steps': 120098, 'loss/train': 0.48504695296287537} 08/31/2021 11:04:47 - INFO - __main__ - Step 120100: {'lr': 4.8688760404020985e-05, 'samples': 23059200, 'steps': 120099, 'loss/train': 1.3262932300567627} 08/31/2021 11:04:47 - INFO - __main__ - Step 120101: {'lr': 4.8685613856239513e-05, 'samples': 23059392, 'steps': 120100, 'loss/train': 0.8855383992195129} 08/31/2021 11:04:47 - INFO - __main__ - Step 120102: {'lr': 4.868246739916729e-05, 'samples': 23059584, 'steps': 120101, 'loss/train': 0.7799394130706787} 08/31/2021 11:04:48 - INFO - __main__ - Step 120103: {'lr': 4.867932103280559e-05, 'samples': 23059776, 'steps': 120102, 'loss/train': 0.8996447324752808} 08/31/2021 11:04:48 - INFO - __main__ - Step 120104: {'lr': 4.8676174757155855e-05, 'samples': 23059968, 'steps': 120103, 'loss/train': 0.6493908166885376} 08/31/2021 11:04:49 - INFO - __main__ - Step 120105: {'lr': 4.867302857221953e-05, 'samples': 23060160, 'steps': 120104, 'loss/train': 1.3467410802841187} 08/31/2021 11:04:50 - INFO - __main__ - Step 120106: {'lr': 4.866988247799806e-05, 'samples': 23060352, 'steps': 120105, 'loss/train': 1.9352772235870361} 08/31/2021 11:04:50 - INFO - __main__ - Step 120107: {'lr': 4.86667364744928e-05, 'samples': 23060544, 'steps': 120106, 'loss/train': 0.9362730383872986} 08/31/2021 11:04:51 - INFO - __main__ - Step 120108: {'lr': 4.8663590561705215e-05, 'samples': 23060736, 'steps': 120107, 'loss/train': 1.4263218641281128} 08/31/2021 11:04:51 - INFO - __main__ - Step 120109: {'lr': 4.866044473963671e-05, 'samples': 23060928, 'steps': 120108, 'loss/train': 1.4310996532440186} 08/31/2021 11:04:53 - INFO - __main__ - Step 120110: {'lr': 4.865729900828869e-05, 'samples': 23061120, 'steps': 120109, 'loss/train': 1.0120142698287964} 08/31/2021 11:04:53 - INFO - __main__ - Step 120111: {'lr': 4.86541533676626e-05, 'samples': 23061312, 'steps': 120110, 'loss/train': 1.1615437269210815} 08/31/2021 11:04:53 - INFO - __main__ - Step 120112: {'lr': 4.8651007817759914e-05, 'samples': 23061504, 'steps': 120111, 'loss/train': 0.36837583780288696} 08/31/2021 11:04:54 - INFO - __main__ - Step 120113: {'lr': 4.864786235858187e-05, 'samples': 23061696, 'steps': 120112, 'loss/train': 0.7306913137435913} 08/31/2021 11:04:54 - INFO - __main__ - Step 120114: {'lr': 4.864471699013004e-05, 'samples': 23061888, 'steps': 120113, 'loss/train': 0.785140335559845} 08/31/2021 11:04:56 - INFO - __main__ - Step 120115: {'lr': 4.864157171240577e-05, 'samples': 23062080, 'steps': 120114, 'loss/train': 0.3203881084918976} 08/31/2021 11:04:57 - INFO - __main__ - Step 120116: {'lr': 4.863842652541051e-05, 'samples': 23062272, 'steps': 120115, 'loss/train': 0.9170435070991516} 08/31/2021 11:04:57 - INFO - __main__ - Step 120117: {'lr': 4.8635281429145665e-05, 'samples': 23062464, 'steps': 120116, 'loss/train': 0.3721044659614563} 08/31/2021 11:04:57 - INFO - __main__ - Step 120118: {'lr': 4.863213642361264e-05, 'samples': 23062656, 'steps': 120117, 'loss/train': 0.7094947099685669} 08/31/2021 11:04:58 - INFO - __main__ - Step 120119: {'lr': 4.8628991508812895e-05, 'samples': 23062848, 'steps': 120118, 'loss/train': 1.2400132417678833} 08/31/2021 11:04:58 - INFO - __main__ - Step 120120: {'lr': 4.862584668474779e-05, 'samples': 23063040, 'steps': 120119, 'loss/train': 1.3741360902786255} 08/31/2021 11:05:00 - INFO - __main__ - Step 120121: {'lr': 4.8622701951418795e-05, 'samples': 23063232, 'steps': 120120, 'loss/train': 0.9048556089401245} 08/31/2021 11:05:00 - INFO - __main__ - Step 120122: {'lr': 4.861955730882728e-05, 'samples': 23063424, 'steps': 120121, 'loss/train': 0.39298149943351746} 08/31/2021 11:05:01 - INFO - __main__ - Step 120123: {'lr': 4.861641275697479e-05, 'samples': 23063616, 'steps': 120122, 'loss/train': 0.026425398886203766} 08/31/2021 11:05:01 - INFO - __main__ - Step 120124: {'lr': 4.861326829586252e-05, 'samples': 23063808, 'steps': 120123, 'loss/train': 1.4732075929641724} 08/31/2021 11:05:01 - INFO - __main__ - Step 120125: {'lr': 4.861012392549205e-05, 'samples': 23064000, 'steps': 120124, 'loss/train': 1.091894507408142} 08/31/2021 11:05:03 - INFO - __main__ - Step 120126: {'lr': 4.8606979645864716e-05, 'samples': 23064192, 'steps': 120125, 'loss/train': 0.9096662998199463} 08/31/2021 11:05:03 - INFO - __main__ - Step 120127: {'lr': 4.860383545698199e-05, 'samples': 23064384, 'steps': 120126, 'loss/train': 1.3589110374450684} 08/31/2021 11:05:04 - INFO - __main__ - Step 120128: {'lr': 4.860069135884526e-05, 'samples': 23064576, 'steps': 120127, 'loss/train': 1.0598362684249878} 08/31/2021 11:05:04 - INFO - __main__ - Step 120129: {'lr': 4.859754735145594e-05, 'samples': 23064768, 'steps': 120128, 'loss/train': 0.4621832072734833} 08/31/2021 11:05:04 - INFO - __main__ - Step 120130: {'lr': 4.859440343481547e-05, 'samples': 23064960, 'steps': 120129, 'loss/train': 1.0440912246704102} 08/31/2021 11:05:06 - INFO - __main__ - Step 120131: {'lr': 4.859125960892527e-05, 'samples': 23065152, 'steps': 120130, 'loss/train': 0.8132762312889099} 08/31/2021 11:05:06 - INFO - __main__ - Step 120132: {'lr': 4.85881158737867e-05, 'samples': 23065344, 'steps': 120131, 'loss/train': 0.9958520531654358} 08/31/2021 11:05:07 - INFO - __main__ - Step 120133: {'lr': 4.8584972229401255e-05, 'samples': 23065536, 'steps': 120132, 'loss/train': 1.1240952014923096} 08/31/2021 11:05:07 - INFO - __main__ - Step 120134: {'lr': 4.858182867577035e-05, 'samples': 23065728, 'steps': 120133, 'loss/train': 1.0335205793380737} 08/31/2021 11:05:07 - INFO - __main__ - Step 120135: {'lr': 4.857868521289532e-05, 'samples': 23065920, 'steps': 120134, 'loss/train': 0.5466201305389404} 08/31/2021 11:05:09 - INFO - __main__ - Step 120136: {'lr': 4.857554184077762e-05, 'samples': 23066112, 'steps': 120135, 'loss/train': 0.9320221543312073} 08/31/2021 11:05:09 - INFO - __main__ - Step 120137: {'lr': 4.8572398559418665e-05, 'samples': 23066304, 'steps': 120136, 'loss/train': 0.9381747245788574} 08/31/2021 11:05:10 - INFO - __main__ - Step 120138: {'lr': 4.8569255368819897e-05, 'samples': 23066496, 'steps': 120137, 'loss/train': 0.8317478895187378} 08/31/2021 11:05:10 - INFO - __main__ - Step 120139: {'lr': 4.8566112268982694e-05, 'samples': 23066688, 'steps': 120138, 'loss/train': 1.1665881872177124} 08/31/2021 11:05:10 - INFO - __main__ - Step 120140: {'lr': 4.856296925990853e-05, 'samples': 23066880, 'steps': 120139, 'loss/train': 1.7815861701965332} 08/31/2021 11:05:12 - INFO - __main__ - Step 120141: {'lr': 4.855982634159875e-05, 'samples': 23067072, 'steps': 120140, 'loss/train': 1.4024255275726318} 08/31/2021 11:05:12 - INFO - __main__ - Step 120142: {'lr': 4.855668351405479e-05, 'samples': 23067264, 'steps': 120141, 'loss/train': 1.3607885837554932} 08/31/2021 11:05:13 - INFO - __main__ - Step 120143: {'lr': 4.855354077727811e-05, 'samples': 23067456, 'steps': 120142, 'loss/train': 1.3537266254425049} 08/31/2021 11:05:13 - INFO - __main__ - Step 120144: {'lr': 4.855039813127007e-05, 'samples': 23067648, 'steps': 120143, 'loss/train': 1.327337622642517} 08/31/2021 11:05:14 - INFO - __main__ - Step 120145: {'lr': 4.8547255576032154e-05, 'samples': 23067840, 'steps': 120144, 'loss/train': 0.45732933282852173} 08/31/2021 11:05:15 - INFO - __main__ - Step 120146: {'lr': 4.85441131115657e-05, 'samples': 23068032, 'steps': 120145, 'loss/train': 1.0129599571228027} 08/31/2021 11:05:15 - INFO - __main__ - Step 120147: {'lr': 4.8540970737872226e-05, 'samples': 23068224, 'steps': 120146, 'loss/train': 1.6424949169158936} 08/31/2021 11:05:16 - INFO - __main__ - Step 120148: {'lr': 4.853782845495303e-05, 'samples': 23068416, 'steps': 120147, 'loss/train': 1.474766731262207} 08/31/2021 11:05:16 - INFO - __main__ - Step 120149: {'lr': 4.853468626280957e-05, 'samples': 23068608, 'steps': 120148, 'loss/train': 1.0327905416488647} 08/31/2021 11:05:16 - INFO - __main__ - Step 120150: {'lr': 4.853154416144329e-05, 'samples': 23068800, 'steps': 120149, 'loss/train': 0.9432052969932556} 08/31/2021 11:05:18 - INFO - __main__ - Step 120151: {'lr': 4.852840215085558e-05, 'samples': 23068992, 'steps': 120150, 'loss/train': 1.2278636693954468} 08/31/2021 11:05:19 - INFO - __main__ - Step 120152: {'lr': 4.852526023104784e-05, 'samples': 23069184, 'steps': 120151, 'loss/train': 1.0801359415054321} 08/31/2021 11:05:19 - INFO - __main__ - Step 120153: {'lr': 4.852211840202153e-05, 'samples': 23069376, 'steps': 120152, 'loss/train': 0.7507647275924683} 08/31/2021 11:05:19 - INFO - __main__ - Step 120154: {'lr': 4.8518976663778055e-05, 'samples': 23069568, 'steps': 120153, 'loss/train': 0.11051817238330841} 08/31/2021 11:05:20 - INFO - __main__ - Step 120155: {'lr': 4.851583501631879e-05, 'samples': 23069760, 'steps': 120154, 'loss/train': 1.3922138214111328} 08/31/2021 11:05:20 - INFO - __main__ - Step 120156: {'lr': 4.851269345964521e-05, 'samples': 23069952, 'steps': 120155, 'loss/train': 0.17722956836223602} 08/31/2021 11:05:22 - INFO - __main__ - Step 120157: {'lr': 4.850955199375867e-05, 'samples': 23070144, 'steps': 120156, 'loss/train': 1.018710732460022} 08/31/2021 11:05:22 - INFO - __main__ - Step 120158: {'lr': 4.850641061866065e-05, 'samples': 23070336, 'steps': 120157, 'loss/train': 0.9934017658233643} 08/31/2021 11:05:22 - INFO - __main__ - Step 120159: {'lr': 4.850326933435251e-05, 'samples': 23070528, 'steps': 120158, 'loss/train': 0.9188040494918823} 08/31/2021 11:05:23 - INFO - __main__ - Step 120160: {'lr': 4.8500128140835684e-05, 'samples': 23070720, 'steps': 120159, 'loss/train': 1.11270010471344} 08/31/2021 11:05:23 - INFO - __main__ - Step 120161: {'lr': 4.8496987038111676e-05, 'samples': 23070912, 'steps': 120160, 'loss/train': 1.3299560546875} 08/31/2021 11:05:25 - INFO - __main__ - Step 120162: {'lr': 4.849384602618173e-05, 'samples': 23071104, 'steps': 120161, 'loss/train': 0.9336153268814087} 08/31/2021 11:05:25 - INFO - __main__ - Step 120163: {'lr': 4.849070510504735e-05, 'samples': 23071296, 'steps': 120162, 'loss/train': 1.492864966392517} 08/31/2021 11:05:25 - INFO - __main__ - Step 120164: {'lr': 4.848756427470999e-05, 'samples': 23071488, 'steps': 120163, 'loss/train': 1.197798728942871} 08/31/2021 11:05:26 - INFO - __main__ - Step 120165: {'lr': 4.848442353517099e-05, 'samples': 23071680, 'steps': 120164, 'loss/train': 0.7466633319854736} 08/31/2021 11:05:26 - INFO - __main__ - Step 120166: {'lr': 4.8481282886431774e-05, 'samples': 23071872, 'steps': 120165, 'loss/train': 0.9050780534744263} 08/31/2021 11:05:28 - INFO - __main__ - Step 120167: {'lr': 4.847814232849382e-05, 'samples': 23072064, 'steps': 120166, 'loss/train': 0.6868869662284851} 08/31/2021 11:05:29 - INFO - __main__ - Step 120168: {'lr': 4.8475001861358506e-05, 'samples': 23072256, 'steps': 120167, 'loss/train': 0.2590677738189697} 08/31/2021 11:05:29 - INFO - __main__ - Step 120169: {'lr': 4.847186148502722e-05, 'samples': 23072448, 'steps': 120168, 'loss/train': 1.346616506576538} 08/31/2021 11:05:29 - INFO - __main__ - Step 120170: {'lr': 4.8468721199501436e-05, 'samples': 23072640, 'steps': 120169, 'loss/train': 1.0028225183486938} 08/31/2021 11:05:30 - INFO - __main__ - Step 120171: {'lr': 4.846558100478252e-05, 'samples': 23072832, 'steps': 120170, 'loss/train': 1.2894443273544312} 08/31/2021 11:05:31 - INFO - __main__ - Step 120172: {'lr': 4.84624409008719e-05, 'samples': 23073024, 'steps': 120171, 'loss/train': 1.3668142557144165} 08/31/2021 11:05:32 - INFO - __main__ - Step 120173: {'lr': 4.845930088777098e-05, 'samples': 23073216, 'steps': 120172, 'loss/train': 1.3793411254882812} 08/31/2021 11:05:32 - INFO - __main__ - Step 120174: {'lr': 4.845616096548128e-05, 'samples': 23073408, 'steps': 120173, 'loss/train': 1.1041679382324219} 08/31/2021 11:05:32 - INFO - __main__ - Step 120175: {'lr': 4.8453021134004044e-05, 'samples': 23073600, 'steps': 120174, 'loss/train': 1.1578338146209717} 08/31/2021 11:05:33 - INFO - __main__ - Step 120176: {'lr': 4.8449881393340776e-05, 'samples': 23073792, 'steps': 120175, 'loss/train': 1.280009150505066} 08/31/2021 11:05:33 - INFO - __main__ - Step 120177: {'lr': 4.844674174349287e-05, 'samples': 23073984, 'steps': 120176, 'loss/train': 0.8576576709747314} 08/31/2021 11:05:34 - INFO - __main__ - Step 120178: {'lr': 4.844360218446176e-05, 'samples': 23074176, 'steps': 120177, 'loss/train': 2.046229362487793} 08/31/2021 11:05:35 - INFO - __main__ - Step 120179: {'lr': 4.844046271624886e-05, 'samples': 23074368, 'steps': 120178, 'loss/train': 1.3865752220153809} 08/31/2021 11:05:35 - INFO - __main__ - Step 120180: {'lr': 4.843732333885556e-05, 'samples': 23074560, 'steps': 120179, 'loss/train': 0.48751991987228394} 08/31/2021 11:05:36 - INFO - __main__ - Step 120181: {'lr': 4.8434184052283306e-05, 'samples': 23074752, 'steps': 120180, 'loss/train': 1.2042806148529053} 08/31/2021 11:05:36 - INFO - __main__ - Step 120182: {'lr': 4.843104485653349e-05, 'samples': 23074944, 'steps': 120181, 'loss/train': 0.5385062098503113} 08/31/2021 11:05:37 - INFO - __main__ - Step 120183: {'lr': 4.842790575160755e-05, 'samples': 23075136, 'steps': 120182, 'loss/train': 0.7992367744445801} 08/31/2021 11:05:38 - INFO - __main__ - Step 120184: {'lr': 4.842476673750687e-05, 'samples': 23075328, 'steps': 120183, 'loss/train': 0.7377833724021912} 08/31/2021 11:05:38 - INFO - __main__ - Step 120185: {'lr': 4.842162781423287e-05, 'samples': 23075520, 'steps': 120184, 'loss/train': 1.2455607652664185} 08/31/2021 11:05:39 - INFO - __main__ - Step 120186: {'lr': 4.8418488981786997e-05, 'samples': 23075712, 'steps': 120185, 'loss/train': 0.6687706112861633} 08/31/2021 11:05:39 - INFO - __main__ - Step 120187: {'lr': 4.841535024017063e-05, 'samples': 23075904, 'steps': 120186, 'loss/train': 1.0940130949020386} 08/31/2021 11:05:40 - INFO - __main__ - Step 120188: {'lr': 4.841221158938527e-05, 'samples': 23076096, 'steps': 120187, 'loss/train': 0.8942352533340454} 08/31/2021 11:05:41 - INFO - __main__ - Step 120189: {'lr': 4.8409073029432176e-05, 'samples': 23076288, 'steps': 120188, 'loss/train': 0.6093491911888123} 08/31/2021 11:05:41 - INFO - __main__ - Step 120190: {'lr': 4.840593456031287e-05, 'samples': 23076480, 'steps': 120189, 'loss/train': 0.9839728474617004} 08/31/2021 11:05:42 - INFO - __main__ - Step 120191: {'lr': 4.8402796182028694e-05, 'samples': 23076672, 'steps': 120190, 'loss/train': 0.12138379365205765} 08/31/2021 11:05:42 - INFO - __main__ - Step 120192: {'lr': 4.839965789458115e-05, 'samples': 23076864, 'steps': 120191, 'loss/train': 1.0084290504455566} 08/31/2021 11:05:44 - INFO - __main__ - Step 120193: {'lr': 4.8396519697971596e-05, 'samples': 23077056, 'steps': 120192, 'loss/train': 1.0419024229049683} 08/31/2021 11:05:44 - INFO - __main__ - Step 120194: {'lr': 4.839338159220144e-05, 'samples': 23077248, 'steps': 120193, 'loss/train': 1.565685510635376} 08/31/2021 11:05:45 - INFO - __main__ - Step 120195: {'lr': 4.8390243577272145e-05, 'samples': 23077440, 'steps': 120194, 'loss/train': 1.8543263673782349} 08/31/2021 11:05:45 - INFO - __main__ - Step 120196: {'lr': 4.8387105653185076e-05, 'samples': 23077632, 'steps': 120195, 'loss/train': 0.9640952348709106} 08/31/2021 11:05:45 - INFO - __main__ - Step 120197: {'lr': 4.838396781994167e-05, 'samples': 23077824, 'steps': 120196, 'loss/train': 0.40182340145111084} 08/31/2021 11:05:46 - INFO - __main__ - Step 120198: {'lr': 4.838083007754335e-05, 'samples': 23078016, 'steps': 120197, 'loss/train': 0.4044012129306793} 08/31/2021 11:05:47 - INFO - __main__ - Step 120199: {'lr': 4.837769242599149e-05, 'samples': 23078208, 'steps': 120198, 'loss/train': 1.1475313901901245} 08/31/2021 11:05:48 - INFO - __main__ - Step 120200: {'lr': 4.8374554865287554e-05, 'samples': 23078400, 'steps': 120199, 'loss/train': 1.1753753423690796} 08/31/2021 11:05:48 - INFO - __main__ - Step 120201: {'lr': 4.837141739543299e-05, 'samples': 23078592, 'steps': 120200, 'loss/train': 1.020224690437317} 08/31/2021 11:05:49 - INFO - __main__ - Step 120202: {'lr': 4.836828001642909e-05, 'samples': 23078784, 'steps': 120201, 'loss/train': 1.359070062637329} 08/31/2021 11:05:49 - INFO - __main__ - Step 120203: {'lr': 4.8365142728277326e-05, 'samples': 23078976, 'steps': 120202, 'loss/train': 1.1515368223190308} 08/31/2021 11:05:49 - INFO - __main__ - Step 120204: {'lr': 4.8362005530979106e-05, 'samples': 23079168, 'steps': 120203, 'loss/train': 1.5243569612503052} 08/31/2021 11:05:51 - INFO - __main__ - Step 120205: {'lr': 4.8358868424535876e-05, 'samples': 23079360, 'steps': 120204, 'loss/train': 0.903103768825531} 08/31/2021 11:05:51 - INFO - __main__ - Step 120206: {'lr': 4.8355731408949025e-05, 'samples': 23079552, 'steps': 120205, 'loss/train': 0.8742859363555908} 08/31/2021 11:05:52 - INFO - __main__ - Step 120207: {'lr': 4.835259448421997e-05, 'samples': 23079744, 'steps': 120206, 'loss/train': 0.8977189064025879} 08/31/2021 11:05:52 - INFO - __main__ - Step 120208: {'lr': 4.834945765035012e-05, 'samples': 23079936, 'steps': 120207, 'loss/train': 0.03499870002269745} 08/31/2021 11:05:52 - INFO - __main__ - Step 120209: {'lr': 4.8346320907340897e-05, 'samples': 23080128, 'steps': 120208, 'loss/train': 0.06179969757795334} 08/31/2021 11:05:54 - INFO - __main__ - Step 120210: {'lr': 4.834318425519371e-05, 'samples': 23080320, 'steps': 120209, 'loss/train': 1.5832065343856812} 08/31/2021 11:05:54 - INFO - __main__ - Step 120211: {'lr': 4.834004769390998e-05, 'samples': 23080512, 'steps': 120210, 'loss/train': 1.0067425966262817} 08/31/2021 11:05:55 - INFO - __main__ - Step 120212: {'lr': 4.83369112234911e-05, 'samples': 23080704, 'steps': 120211, 'loss/train': 0.023603355512022972} 08/31/2021 11:05:55 - INFO - __main__ - Step 120213: {'lr': 4.83337748439385e-05, 'samples': 23080896, 'steps': 120212, 'loss/train': 1.166380763053894} 08/31/2021 11:05:55 - INFO - __main__ - Step 120214: {'lr': 4.8330638555253575e-05, 'samples': 23081088, 'steps': 120213, 'loss/train': 1.0449680089950562} 08/31/2021 11:05:57 - INFO - __main__ - Step 120215: {'lr': 4.832750235743783e-05, 'samples': 23081280, 'steps': 120214, 'loss/train': 1.0984026193618774} 08/31/2021 11:05:57 - INFO - __main__ - Step 120216: {'lr': 4.8324366250492553e-05, 'samples': 23081472, 'steps': 120215, 'loss/train': 0.6921743154525757} 08/31/2021 11:05:58 - INFO - __main__ - Step 120217: {'lr': 4.832123023441917e-05, 'samples': 23081664, 'steps': 120216, 'loss/train': 1.2603089809417725} 08/31/2021 11:05:58 - INFO - __main__ - Step 120218: {'lr': 4.831809430921916e-05, 'samples': 23081856, 'steps': 120217, 'loss/train': 1.102042555809021} 08/31/2021 11:05:58 - INFO - __main__ - Step 120219: {'lr': 4.831495847489389e-05, 'samples': 23082048, 'steps': 120218, 'loss/train': 1.221990942955017} 08/31/2021 11:06:00 - INFO - __main__ - Step 120220: {'lr': 4.831182273144477e-05, 'samples': 23082240, 'steps': 120219, 'loss/train': 1.2124768495559692} 08/31/2021 11:06:00 - INFO - __main__ - Step 120221: {'lr': 4.830868707887326e-05, 'samples': 23082432, 'steps': 120220, 'loss/train': 1.29325270652771} 08/31/2021 11:06:01 - INFO - __main__ - Step 120222: {'lr': 4.830555151718072e-05, 'samples': 23082624, 'steps': 120221, 'loss/train': 0.48849910497665405} 08/31/2021 11:06:01 - INFO - __main__ - Step 120223: {'lr': 4.830241604636862e-05, 'samples': 23082816, 'steps': 120222, 'loss/train': 0.9395814538002014} 08/31/2021 11:06:01 - INFO - __main__ - Step 120224: {'lr': 4.829928066643829e-05, 'samples': 23083008, 'steps': 120223, 'loss/train': 0.13255013525485992} 08/31/2021 11:06:03 - INFO - __main__ - Step 120225: {'lr': 4.829614537739124e-05, 'samples': 23083200, 'steps': 120224, 'loss/train': 1.1282752752304077} 08/31/2021 11:06:04 - INFO - __main__ - Step 120226: {'lr': 4.82930101792288e-05, 'samples': 23083392, 'steps': 120225, 'loss/train': 0.7061386704444885} 08/31/2021 11:06:04 - INFO - __main__ - Step 120227: {'lr': 4.8289875071952425e-05, 'samples': 23083584, 'steps': 120226, 'loss/train': 0.5007188320159912} 08/31/2021 11:06:05 - INFO - __main__ - Step 120228: {'lr': 4.82867400555636e-05, 'samples': 23083776, 'steps': 120227, 'loss/train': 1.3008733987808228} 08/31/2021 11:06:05 - INFO - __main__ - Step 120229: {'lr': 4.8283605130063576e-05, 'samples': 23083968, 'steps': 120228, 'loss/train': 0.5529364943504333} 08/31/2021 11:06:06 - INFO - __main__ - Step 120230: {'lr': 4.828047029545385e-05, 'samples': 23084160, 'steps': 120229, 'loss/train': 0.6546206474304199} 08/31/2021 11:06:07 - INFO - __main__ - Step 120231: {'lr': 4.827733555173583e-05, 'samples': 23084352, 'steps': 120230, 'loss/train': 0.743371307849884} 08/31/2021 11:06:07 - INFO - __main__ - Step 120232: {'lr': 4.8274200898910936e-05, 'samples': 23084544, 'steps': 120231, 'loss/train': 1.347602367401123} 08/31/2021 11:06:08 - INFO - __main__ - Step 120233: {'lr': 4.8271066336980586e-05, 'samples': 23084736, 'steps': 120232, 'loss/train': 1.2772338390350342} 08/31/2021 11:06:08 - INFO - __main__ - Step 120234: {'lr': 4.826793186594616e-05, 'samples': 23084928, 'steps': 120233, 'loss/train': 0.44808316230773926} 08/31/2021 11:06:09 - INFO - __main__ - Step 120235: {'lr': 4.826479748580908e-05, 'samples': 23085120, 'steps': 120234, 'loss/train': 1.031786322593689} 08/31/2021 11:06:10 - INFO - __main__ - Step 120236: {'lr': 4.82616631965708e-05, 'samples': 23085312, 'steps': 120235, 'loss/train': 5.803847312927246} 08/31/2021 11:06:10 - INFO - __main__ - Step 120237: {'lr': 4.825852899823269e-05, 'samples': 23085504, 'steps': 120236, 'loss/train': 0.8085135817527771} 08/31/2021 11:06:11 - INFO - __main__ - Step 120238: {'lr': 4.825539489079617e-05, 'samples': 23085696, 'steps': 120237, 'loss/train': 1.0844801664352417} 08/31/2021 11:06:11 - INFO - __main__ - Step 120239: {'lr': 4.8252260874262654e-05, 'samples': 23085888, 'steps': 120238, 'loss/train': 0.45573747158050537} 08/31/2021 11:06:13 - INFO - __main__ - Step 120240: {'lr': 4.824912694863356e-05, 'samples': 23086080, 'steps': 120239, 'loss/train': 1.3141826391220093} 08/31/2021 11:06:13 - INFO - __main__ - Step 120241: {'lr': 4.824599311391031e-05, 'samples': 23086272, 'steps': 120240, 'loss/train': 1.874684453010559} 08/31/2021 11:06:13 - INFO - __main__ - Step 120242: {'lr': 4.824285937009434e-05, 'samples': 23086464, 'steps': 120241, 'loss/train': 1.1538245677947998} 08/31/2021 11:06:14 - INFO - __main__ - Step 120243: {'lr': 4.823972571718699e-05, 'samples': 23086656, 'steps': 120242, 'loss/train': 1.0299924612045288} 08/31/2021 11:06:14 - INFO - __main__ - Step 120244: {'lr': 4.8236592155189693e-05, 'samples': 23086848, 'steps': 120243, 'loss/train': 0.7365242838859558} 08/31/2021 11:06:16 - INFO - __main__ - Step 120245: {'lr': 4.8233458684103866e-05, 'samples': 23087040, 'steps': 120244, 'loss/train': 0.9588170051574707} 08/31/2021 11:06:16 - INFO - __main__ - Step 120246: {'lr': 4.8230325303930925e-05, 'samples': 23087232, 'steps': 120245, 'loss/train': 1.2461373805999756} 08/31/2021 11:06:16 - INFO - __main__ - Step 120247: {'lr': 4.8227192014672294e-05, 'samples': 23087424, 'steps': 120246, 'loss/train': 0.09174399077892303} 08/31/2021 11:06:17 - INFO - __main__ - Step 120248: {'lr': 4.822405881632938e-05, 'samples': 23087616, 'steps': 120247, 'loss/train': 0.6449859738349915} 08/31/2021 11:06:17 - INFO - __main__ - Step 120249: {'lr': 4.8220925708903604e-05, 'samples': 23087808, 'steps': 120248, 'loss/train': 0.9857154488563538} 08/31/2021 11:06:18 - INFO - __main__ - Step 120250: {'lr': 4.8217792692396345e-05, 'samples': 23088000, 'steps': 120249, 'loss/train': 1.1412161588668823} 08/31/2021 11:06:19 - INFO - __main__ - Step 120251: {'lr': 4.8214659766809026e-05, 'samples': 23088192, 'steps': 120250, 'loss/train': 1.4466608762741089} 08/31/2021 11:06:19 - INFO - __main__ - Step 120252: {'lr': 4.821152693214309e-05, 'samples': 23088384, 'steps': 120251, 'loss/train': 0.03828657045960426} 08/31/2021 11:06:20 - INFO - __main__ - Step 120253: {'lr': 4.820839418839992e-05, 'samples': 23088576, 'steps': 120252, 'loss/train': 0.6499171257019043} 08/31/2021 11:06:20 - INFO - __main__ - Step 120254: {'lr': 4.820526153558094e-05, 'samples': 23088768, 'steps': 120253, 'loss/train': 0.7609497308731079} 08/31/2021 11:06:21 - INFO - __main__ - Step 120255: {'lr': 4.8202128973687616e-05, 'samples': 23088960, 'steps': 120254, 'loss/train': 0.16088618338108063} 08/31/2021 11:06:22 - INFO - __main__ - Step 120256: {'lr': 4.819899650272122e-05, 'samples': 23089152, 'steps': 120255, 'loss/train': 0.9472804069519043} 08/31/2021 11:06:22 - INFO - __main__ - Step 120257: {'lr': 4.819586412268326e-05, 'samples': 23089344, 'steps': 120256, 'loss/train': 0.4858822822570801} 08/31/2021 11:06:23 - INFO - __main__ - Step 120258: {'lr': 4.819273183357511e-05, 'samples': 23089536, 'steps': 120257, 'loss/train': 1.9621397256851196} 08/31/2021 11:06:23 - INFO - __main__ - Step 120259: {'lr': 4.818959963539821e-05, 'samples': 23089728, 'steps': 120258, 'loss/train': 1.0782623291015625} 08/31/2021 11:06:23 - INFO - __main__ - Step 120260: {'lr': 4.818646752815398e-05, 'samples': 23089920, 'steps': 120259, 'loss/train': 0.6253323554992676} 08/31/2021 11:06:25 - INFO - __main__ - Step 120261: {'lr': 4.818333551184379e-05, 'samples': 23090112, 'steps': 120260, 'loss/train': 0.685732364654541} 08/31/2021 11:06:25 - INFO - __main__ - Step 120262: {'lr': 4.818020358646908e-05, 'samples': 23090304, 'steps': 120261, 'loss/train': 0.5843353271484375} 08/31/2021 11:06:26 - INFO - __main__ - Step 120263: {'lr': 4.817707175203126e-05, 'samples': 23090496, 'steps': 120262, 'loss/train': 1.0976465940475464} 08/31/2021 11:06:26 - INFO - __main__ - Step 120264: {'lr': 4.817394000853173e-05, 'samples': 23090688, 'steps': 120263, 'loss/train': 0.8264601826667786} 08/31/2021 11:06:26 - INFO - __main__ - Step 120265: {'lr': 4.81708083559719e-05, 'samples': 23090880, 'steps': 120264, 'loss/train': 1.2629798650741577} 08/31/2021 11:06:28 - INFO - __main__ - Step 120266: {'lr': 4.8167676794353214e-05, 'samples': 23091072, 'steps': 120265, 'loss/train': 0.9689378142356873} 08/31/2021 11:06:28 - INFO - __main__ - Step 120267: {'lr': 4.816454532367706e-05, 'samples': 23091264, 'steps': 120266, 'loss/train': 1.3006983995437622} 08/31/2021 11:06:29 - INFO - __main__ - Step 120268: {'lr': 4.816141394394488e-05, 'samples': 23091456, 'steps': 120267, 'loss/train': 1.3063815832138062} 08/31/2021 11:06:29 - INFO - __main__ - Step 120269: {'lr': 4.815828265515801e-05, 'samples': 23091648, 'steps': 120268, 'loss/train': 0.8061255216598511} 08/31/2021 11:06:29 - INFO - __main__ - Step 120270: {'lr': 4.8155151457317915e-05, 'samples': 23091840, 'steps': 120269, 'loss/train': 1.0792442560195923} 08/31/2021 11:06:30 - INFO - __main__ - Step 120271: {'lr': 4.8152020350425984e-05, 'samples': 23092032, 'steps': 120270, 'loss/train': 0.6218321919441223} 08/31/2021 11:06:31 - INFO - __main__ - Step 120272: {'lr': 4.814888933448363e-05, 'samples': 23092224, 'steps': 120271, 'loss/train': 1.1361037492752075} 08/31/2021 11:06:32 - INFO - __main__ - Step 120273: {'lr': 4.8145758409492285e-05, 'samples': 23092416, 'steps': 120272, 'loss/train': 0.7810111045837402} 08/31/2021 11:06:32 - INFO - __main__ - Step 120274: {'lr': 4.8142627575453316e-05, 'samples': 23092608, 'steps': 120273, 'loss/train': 1.5637928247451782} 08/31/2021 11:06:32 - INFO - __main__ - Step 120275: {'lr': 4.813949683236821e-05, 'samples': 23092800, 'steps': 120274, 'loss/train': 1.4200738668441772} 08/31/2021 11:06:33 - INFO - __main__ - Step 120276: {'lr': 4.813636618023829e-05, 'samples': 23092992, 'steps': 120275, 'loss/train': 0.8933098316192627} 08/31/2021 11:06:35 - INFO - __main__ - Step 120277: {'lr': 4.813323561906502e-05, 'samples': 23093184, 'steps': 120276, 'loss/train': 1.2988122701644897} 08/31/2021 11:06:35 - INFO - __main__ - Step 120278: {'lr': 4.81301051488498e-05, 'samples': 23093376, 'steps': 120277, 'loss/train': 1.3113057613372803} 08/31/2021 11:06:36 - INFO - __main__ - Step 120279: {'lr': 4.812697476959405e-05, 'samples': 23093568, 'steps': 120278, 'loss/train': 0.4204690754413605} 08/31/2021 11:06:36 - INFO - __main__ - Step 120280: {'lr': 4.8123844481299166e-05, 'samples': 23093760, 'steps': 120279, 'loss/train': 0.695412278175354} 08/31/2021 11:06:36 - INFO - __main__ - Step 120281: {'lr': 4.8120714283966555e-05, 'samples': 23093952, 'steps': 120280, 'loss/train': 1.3438645601272583} 08/31/2021 11:06:38 - INFO - __main__ - Step 120282: {'lr': 4.811758417759771e-05, 'samples': 23094144, 'steps': 120281, 'loss/train': 0.991958737373352} 08/31/2021 11:06:38 - INFO - __main__ - Step 120283: {'lr': 4.8114454162193896e-05, 'samples': 23094336, 'steps': 120282, 'loss/train': 1.2426743507385254} 08/31/2021 11:06:39 - INFO - __main__ - Step 120284: {'lr': 4.8111324237756606e-05, 'samples': 23094528, 'steps': 120283, 'loss/train': 0.5595445036888123} 08/31/2021 11:06:39 - INFO - __main__ - Step 120285: {'lr': 4.810819440428721e-05, 'samples': 23094720, 'steps': 120284, 'loss/train': 1.0005496740341187} 08/31/2021 11:06:39 - INFO - __main__ - Step 120286: {'lr': 4.810506466178718e-05, 'samples': 23094912, 'steps': 120285, 'loss/train': 0.7224110960960388} 08/31/2021 11:06:41 - INFO - __main__ - Step 120287: {'lr': 4.8101935010257864e-05, 'samples': 23095104, 'steps': 120286, 'loss/train': 0.8677930235862732} 08/31/2021 11:06:41 - INFO - __main__ - Step 120288: {'lr': 4.8098805449700716e-05, 'samples': 23095296, 'steps': 120287, 'loss/train': 0.08856362104415894} 08/31/2021 11:06:42 - INFO - __main__ - Step 120289: {'lr': 4.809567598011713e-05, 'samples': 23095488, 'steps': 120288, 'loss/train': 0.8564079999923706} 08/31/2021 11:06:42 - INFO - __main__ - Step 120290: {'lr': 4.809254660150852e-05, 'samples': 23095680, 'steps': 120289, 'loss/train': 0.8106332421302795} 08/31/2021 11:06:42 - INFO - __main__ - Step 120291: {'lr': 4.8089417313876286e-05, 'samples': 23095872, 'steps': 120290, 'loss/train': 0.9947826862335205} 08/31/2021 11:06:44 - INFO - __main__ - Step 120292: {'lr': 4.8086288117221846e-05, 'samples': 23096064, 'steps': 120291, 'loss/train': 0.7032657861709595} 08/31/2021 11:06:44 - INFO - __main__ - Step 120293: {'lr': 4.808315901154661e-05, 'samples': 23096256, 'steps': 120292, 'loss/train': 0.990391731262207} 08/31/2021 11:06:45 - INFO - __main__ - Step 120294: {'lr': 4.808002999685199e-05, 'samples': 23096448, 'steps': 120293, 'loss/train': 0.5757875442504883} 08/31/2021 11:06:45 - INFO - __main__ - Step 120295: {'lr': 4.807690107313945e-05, 'samples': 23096640, 'steps': 120294, 'loss/train': 1.162879467010498} 08/31/2021 11:06:45 - INFO - __main__ - Step 120296: {'lr': 4.807377224041026e-05, 'samples': 23096832, 'steps': 120295, 'loss/train': 1.5630544424057007} 08/31/2021 11:06:47 - INFO - __main__ - Step 120297: {'lr': 4.807064349866594e-05, 'samples': 23097024, 'steps': 120296, 'loss/train': 1.2161767482757568} 08/31/2021 11:06:47 - INFO - __main__ - Step 120298: {'lr': 4.806751484790786e-05, 'samples': 23097216, 'steps': 120297, 'loss/train': 1.0256638526916504} 08/31/2021 11:06:48 - INFO - __main__ - Step 120299: {'lr': 4.806438628813745e-05, 'samples': 23097408, 'steps': 120298, 'loss/train': 1.2790757417678833} 08/31/2021 11:06:48 - INFO - __main__ - Step 120300: {'lr': 4.806125781935611e-05, 'samples': 23097600, 'steps': 120299, 'loss/train': 0.9822635650634766} 08/31/2021 11:06:48 - INFO - __main__ - Step 120301: {'lr': 4.805812944156526e-05, 'samples': 23097792, 'steps': 120300, 'loss/train': 1.5162460803985596} 08/31/2021 11:06:50 - INFO - __main__ - Step 120302: {'lr': 4.805500115476627e-05, 'samples': 23097984, 'steps': 120301, 'loss/train': 0.6947522163391113} 08/31/2021 11:06:51 - INFO - __main__ - Step 120303: {'lr': 4.80518729589606e-05, 'samples': 23098176, 'steps': 120302, 'loss/train': 1.0407620668411255} 08/31/2021 11:06:51 - INFO - __main__ - Step 120304: {'lr': 4.8048744854149643e-05, 'samples': 23098368, 'steps': 120303, 'loss/train': 1.3257348537445068} 08/31/2021 11:06:51 - INFO - __main__ - Step 120305: {'lr': 4.804561684033482e-05, 'samples': 23098560, 'steps': 120304, 'loss/train': 0.06140850856900215} 08/31/2021 11:06:52 - INFO - __main__ - Step 120306: {'lr': 4.80424889175175e-05, 'samples': 23098752, 'steps': 120305, 'loss/train': 1.1154067516326904} 08/31/2021 11:06:53 - INFO - __main__ - Step 120307: {'lr': 4.803936108569912e-05, 'samples': 23098944, 'steps': 120306, 'loss/train': 1.4757500886917114} 08/31/2021 11:06:54 - INFO - __main__ - Step 120308: {'lr': 4.803623334488111e-05, 'samples': 23099136, 'steps': 120307, 'loss/train': 0.9246843457221985} 08/31/2021 11:06:54 - INFO - __main__ - Step 120309: {'lr': 4.803310569506489e-05, 'samples': 23099328, 'steps': 120308, 'loss/train': 1.0862305164337158} 08/31/2021 11:06:54 - INFO - __main__ - Step 120310: {'lr': 4.802997813625179e-05, 'samples': 23099520, 'steps': 120309, 'loss/train': 1.1005092859268188} 08/31/2021 11:06:55 - INFO - __main__ - Step 120311: {'lr': 4.8026850668443256e-05, 'samples': 23099712, 'steps': 120310, 'loss/train': 1.0476354360580444} 08/31/2021 11:06:55 - INFO - __main__ - Step 120312: {'lr': 4.80237232916407e-05, 'samples': 23099904, 'steps': 120311, 'loss/train': 0.9589678049087524} 08/31/2021 11:06:57 - INFO - __main__ - Step 120313: {'lr': 4.802059600584557e-05, 'samples': 23100096, 'steps': 120312, 'loss/train': 0.7992662191390991} 08/31/2021 11:06:57 - INFO - __main__ - Step 120314: {'lr': 4.8017468811059226e-05, 'samples': 23100288, 'steps': 120313, 'loss/train': 1.0260509252548218} 08/31/2021 11:06:58 - INFO - __main__ - Step 120315: {'lr': 4.801434170728308e-05, 'samples': 23100480, 'steps': 120314, 'loss/train': 0.12004121392965317} 08/31/2021 11:06:58 - INFO - __main__ - Step 120316: {'lr': 4.801121469451855e-05, 'samples': 23100672, 'steps': 120315, 'loss/train': 0.7396852374076843} 08/31/2021 11:06:58 - INFO - __main__ - Step 120317: {'lr': 4.800808777276708e-05, 'samples': 23100864, 'steps': 120316, 'loss/train': 1.554447054862976} 08/31/2021 11:07:00 - INFO - __main__ - Step 120318: {'lr': 4.8004960942030026e-05, 'samples': 23101056, 'steps': 120317, 'loss/train': 1.4866876602172852} 08/31/2021 11:07:00 - INFO - __main__ - Step 120319: {'lr': 4.800183420230883e-05, 'samples': 23101248, 'steps': 120318, 'loss/train': 1.418074131011963} 08/31/2021 11:07:01 - INFO - __main__ - Step 120320: {'lr': 4.799870755360489e-05, 'samples': 23101440, 'steps': 120319, 'loss/train': 1.3907396793365479} 08/31/2021 11:07:01 - INFO - __main__ - Step 120321: {'lr': 4.7995580995919605e-05, 'samples': 23101632, 'steps': 120320, 'loss/train': 0.7970865368843079} 08/31/2021 11:07:01 - INFO - __main__ - Step 120322: {'lr': 4.799245452925446e-05, 'samples': 23101824, 'steps': 120321, 'loss/train': 1.6568962335586548} 08/31/2021 11:07:03 - INFO - __main__ - Step 120323: {'lr': 4.798932815361076e-05, 'samples': 23102016, 'steps': 120322, 'loss/train': 0.9367251992225647} 08/31/2021 11:07:03 - INFO - __main__ - Step 120324: {'lr': 4.798620186898991e-05, 'samples': 23102208, 'steps': 120323, 'loss/train': 1.2615234851837158} 08/31/2021 11:07:04 - INFO - __main__ - Step 120325: {'lr': 4.798307567539339e-05, 'samples': 23102400, 'steps': 120324, 'loss/train': 0.18169617652893066} 08/31/2021 11:07:04 - INFO - __main__ - Step 120326: {'lr': 4.797994957282256e-05, 'samples': 23102592, 'steps': 120325, 'loss/train': 1.5885281562805176} 08/31/2021 11:07:04 - INFO - __main__ - Step 120327: {'lr': 4.797682356127886e-05, 'samples': 23102784, 'steps': 120326, 'loss/train': 1.0228420495986938} 08/31/2021 11:07:06 - INFO - __main__ - Step 120328: {'lr': 4.7973697640763704e-05, 'samples': 23102976, 'steps': 120327, 'loss/train': 1.204346776008606} 08/31/2021 11:07:06 - INFO - __main__ - Step 120329: {'lr': 4.797057181127845e-05, 'samples': 23103168, 'steps': 120328, 'loss/train': 0.7850958108901978} 08/31/2021 11:07:06 - INFO - __main__ - Step 120330: {'lr': 4.796744607282455e-05, 'samples': 23103360, 'steps': 120329, 'loss/train': 0.7651745676994324} 08/31/2021 11:07:07 - INFO - __main__ - Step 120331: {'lr': 4.796432042540341e-05, 'samples': 23103552, 'steps': 120330, 'loss/train': 0.8627299070358276} 08/31/2021 11:07:07 - INFO - __main__ - Step 120332: {'lr': 4.796119486901643e-05, 'samples': 23103744, 'steps': 120331, 'loss/train': 0.8968814015388489} 08/31/2021 11:07:09 - INFO - __main__ - Step 120333: {'lr': 4.795806940366498e-05, 'samples': 23103936, 'steps': 120332, 'loss/train': 1.3503388166427612} 08/31/2021 11:07:10 - INFO - __main__ - Step 120334: {'lr': 4.795494402935055e-05, 'samples': 23104128, 'steps': 120333, 'loss/train': 0.772809624671936} 08/31/2021 11:07:10 - INFO - __main__ - Step 120335: {'lr': 4.795181874607449e-05, 'samples': 23104320, 'steps': 120334, 'loss/train': 1.7243051528930664} 08/31/2021 11:07:10 - INFO - __main__ - Step 120336: {'lr': 4.79486935538383e-05, 'samples': 23104512, 'steps': 120335, 'loss/train': 0.9284337759017944} 08/31/2021 11:07:11 - INFO - __main__ - Step 120337: {'lr': 4.794556845264322e-05, 'samples': 23104704, 'steps': 120336, 'loss/train': 1.5343371629714966} 08/31/2021 11:07:12 - INFO - __main__ - Step 120338: {'lr': 4.794244344249077e-05, 'samples': 23104896, 'steps': 120337, 'loss/train': 0.8038468956947327} 08/31/2021 11:07:13 - INFO - __main__ - Step 120339: {'lr': 4.793931852338232e-05, 'samples': 23105088, 'steps': 120338, 'loss/train': 0.9898362159729004} 08/31/2021 11:07:13 - INFO - __main__ - Step 120340: {'lr': 4.793619369531932e-05, 'samples': 23105280, 'steps': 120339, 'loss/train': 0.9061790704727173} 08/31/2021 11:07:13 - INFO - __main__ - Step 120341: {'lr': 4.793306895830313e-05, 'samples': 23105472, 'steps': 120340, 'loss/train': 0.2692281901836395} 08/31/2021 11:07:14 - INFO - __main__ - Step 120342: {'lr': 4.792994431233519e-05, 'samples': 23105664, 'steps': 120341, 'loss/train': 1.1729950904846191} 08/31/2021 11:07:15 - INFO - __main__ - Step 120343: {'lr': 4.792681975741689e-05, 'samples': 23105856, 'steps': 120342, 'loss/train': 1.2846795320510864} 08/31/2021 11:07:16 - INFO - __main__ - Step 120344: {'lr': 4.7923695293549645e-05, 'samples': 23106048, 'steps': 120343, 'loss/train': 1.548053503036499} 08/31/2021 11:07:16 - INFO - __main__ - Step 120345: {'lr': 4.7920570920734905e-05, 'samples': 23106240, 'steps': 120344, 'loss/train': 1.1599444150924683} 08/31/2021 11:07:16 - INFO - __main__ - Step 120346: {'lr': 4.791744663897399e-05, 'samples': 23106432, 'steps': 120345, 'loss/train': 1.2655694484710693} 08/31/2021 11:07:17 - INFO - __main__ - Step 120347: {'lr': 4.791432244826838e-05, 'samples': 23106624, 'steps': 120346, 'loss/train': 1.2914652824401855} 08/31/2021 11:07:17 - INFO - __main__ - Step 120348: {'lr': 4.7911198348619514e-05, 'samples': 23106816, 'steps': 120347, 'loss/train': 0.18233583867549896} 08/31/2021 11:07:19 - INFO - __main__ - Step 120349: {'lr': 4.790807434002867e-05, 'samples': 23107008, 'steps': 120348, 'loss/train': 0.46903133392333984} 08/31/2021 11:07:19 - INFO - __main__ - Step 120350: {'lr': 4.7904950422497343e-05, 'samples': 23107200, 'steps': 120349, 'loss/train': 1.2152259349822998} 08/31/2021 11:07:20 - INFO - __main__ - Step 120351: {'lr': 4.790182659602693e-05, 'samples': 23107392, 'steps': 120350, 'loss/train': 0.0927337184548378} 08/31/2021 11:07:20 - INFO - __main__ - Step 120352: {'lr': 4.7898702860618815e-05, 'samples': 23107584, 'steps': 120351, 'loss/train': 0.15809983015060425} 08/31/2021 11:07:20 - INFO - __main__ - Step 120353: {'lr': 4.789557921627444e-05, 'samples': 23107776, 'steps': 120352, 'loss/train': 1.461664080619812} 08/31/2021 11:07:22 - INFO - __main__ - Step 120354: {'lr': 4.789245566299519e-05, 'samples': 23107968, 'steps': 120353, 'loss/train': 1.540362000465393} 08/31/2021 11:07:22 - INFO - __main__ - Step 120355: {'lr': 4.788933220078251e-05, 'samples': 23108160, 'steps': 120354, 'loss/train': 0.9384544491767883} 08/31/2021 11:07:23 - INFO - __main__ - Step 120356: {'lr': 4.7886208829637734e-05, 'samples': 23108352, 'steps': 120355, 'loss/train': 0.7734956741333008} 08/31/2021 11:07:23 - INFO - __main__ - Step 120357: {'lr': 4.788308554956233e-05, 'samples': 23108544, 'steps': 120356, 'loss/train': 0.5093603134155273} 08/31/2021 11:07:23 - INFO - __main__ - Step 120358: {'lr': 4.787996236055772e-05, 'samples': 23108736, 'steps': 120357, 'loss/train': 1.3649271726608276} 08/31/2021 11:07:25 - INFO - __main__ - Step 120359: {'lr': 4.787683926262532e-05, 'samples': 23108928, 'steps': 120358, 'loss/train': 1.625064730644226} 08/31/2021 11:07:26 - INFO - __main__ - Step 120360: {'lr': 4.787371625576642e-05, 'samples': 23109120, 'steps': 120359, 'loss/train': 1.52535080909729} 08/31/2021 11:07:26 - INFO - __main__ - Step 120361: {'lr': 4.787059333998251e-05, 'samples': 23109312, 'steps': 120360, 'loss/train': 0.3654477596282959} 08/31/2021 11:07:27 - INFO - __main__ - Step 120362: {'lr': 4.786747051527501e-05, 'samples': 23109504, 'steps': 120361, 'loss/train': 5.804711818695068} 08/31/2021 11:07:27 - INFO - __main__ - Step 120363: {'lr': 4.786434778164528e-05, 'samples': 23109696, 'steps': 120362, 'loss/train': 5.750197410583496} 08/31/2021 11:07:27 - INFO - __main__ - Step 120364: {'lr': 4.7861225139094774e-05, 'samples': 23109888, 'steps': 120363, 'loss/train': 5.786983489990234} 08/31/2021 11:07:28 - INFO - __main__ - Step 120365: {'lr': 4.785810258762488e-05, 'samples': 23110080, 'steps': 120364, 'loss/train': 1.0258435010910034} 08/31/2021 11:07:28 - INFO - __main__ - Step 120366: {'lr': 4.785498012723702e-05, 'samples': 23110272, 'steps': 120365, 'loss/train': 0.500435471534729} 08/31/2021 11:07:30 - INFO - __main__ - Step 120367: {'lr': 4.785185775793257e-05, 'samples': 23110464, 'steps': 120366, 'loss/train': 1.332492470741272} 08/31/2021 11:07:31 - INFO - __main__ - Step 120368: {'lr': 4.784873547971294e-05, 'samples': 23110656, 'steps': 120367, 'loss/train': 1.4169336557388306} 08/31/2021 11:07:31 - INFO - __main__ - Step 120369: {'lr': 4.784561329257958e-05, 'samples': 23110848, 'steps': 120368, 'loss/train': 0.12951335310935974} 08/31/2021 11:07:32 - INFO - __main__ - Step 120370: {'lr': 4.7842491196533914e-05, 'samples': 23111040, 'steps': 120369, 'loss/train': 1.1927794218063354} 08/31/2021 11:07:32 - INFO - __main__ - Step 120371: {'lr': 4.7839369191577246e-05, 'samples': 23111232, 'steps': 120370, 'loss/train': 1.0957422256469727} 08/31/2021 11:07:34 - INFO - __main__ - Step 120372: {'lr': 4.783624727771102e-05, 'samples': 23111424, 'steps': 120371, 'loss/train': 0.7070906758308411} 08/31/2021 11:07:34 - INFO - __main__ - Step 120373: {'lr': 4.7833125454936676e-05, 'samples': 23111616, 'steps': 120372, 'loss/train': 1.092315912246704} 08/31/2021 11:07:34 - INFO - __main__ - Step 120374: {'lr': 4.7830003723255605e-05, 'samples': 23111808, 'steps': 120373, 'loss/train': 1.6404504776000977} 08/31/2021 11:07:35 - INFO - __main__ - Step 120375: {'lr': 4.782688208266922e-05, 'samples': 23112000, 'steps': 120374, 'loss/train': 0.40334346890449524} 08/31/2021 11:07:35 - INFO - __main__ - Step 120376: {'lr': 4.7823760533178914e-05, 'samples': 23112192, 'steps': 120375, 'loss/train': 1.2690045833587646} 08/31/2021 11:07:37 - INFO - __main__ - Step 120377: {'lr': 4.782063907478609e-05, 'samples': 23112384, 'steps': 120376, 'loss/train': 1.0450338125228882} 08/31/2021 11:07:37 - INFO - __main__ - Step 120378: {'lr': 4.781751770749221e-05, 'samples': 23112576, 'steps': 120377, 'loss/train': 0.9036902189254761} 08/31/2021 11:07:37 - INFO - __main__ - Step 120379: {'lr': 4.781439643129859e-05, 'samples': 23112768, 'steps': 120378, 'loss/train': 0.9894238114356995} 08/31/2021 11:07:38 - INFO - __main__ - Step 120380: {'lr': 4.781127524620671e-05, 'samples': 23112960, 'steps': 120379, 'loss/train': 0.8195573091506958} 08/31/2021 11:07:38 - INFO - __main__ - Step 120381: {'lr': 4.780815415221801e-05, 'samples': 23113152, 'steps': 120380, 'loss/train': 2.0034878253936768} 08/31/2021 11:07:40 - INFO - __main__ - Step 120382: {'lr': 4.780503314933376e-05, 'samples': 23113344, 'steps': 120381, 'loss/train': 0.9416264295578003} 08/31/2021 11:07:41 - INFO - __main__ - Step 120383: {'lr': 4.780191223755545e-05, 'samples': 23113536, 'steps': 120382, 'loss/train': 1.341973900794983} 08/31/2021 11:07:41 - INFO - __main__ - Step 120384: {'lr': 4.779879141688448e-05, 'samples': 23113728, 'steps': 120383, 'loss/train': 0.9937880039215088} 08/31/2021 11:07:41 - INFO - __main__ - Step 120385: {'lr': 4.779567068732224e-05, 'samples': 23113920, 'steps': 120384, 'loss/train': 1.359960913658142} 08/31/2021 11:07:42 - INFO - __main__ - Step 120386: {'lr': 4.7792550048870146e-05, 'samples': 23114112, 'steps': 120385, 'loss/train': 0.10698888450860977} 08/31/2021 11:07:42 - INFO - __main__ - Step 120387: {'lr': 4.7789429501529644e-05, 'samples': 23114304, 'steps': 120386, 'loss/train': 1.16562020778656} 08/31/2021 11:07:44 - INFO - __main__ - Step 120388: {'lr': 4.7786309045302065e-05, 'samples': 23114496, 'steps': 120387, 'loss/train': 1.2293550968170166} 08/31/2021 11:07:44 - INFO - __main__ - Step 120389: {'lr': 4.7783188680188884e-05, 'samples': 23114688, 'steps': 120388, 'loss/train': 0.5969574451446533} 08/31/2021 11:07:44 - INFO - __main__ - Step 120390: {'lr': 4.778006840619148e-05, 'samples': 23114880, 'steps': 120389, 'loss/train': 0.8981388807296753} 08/31/2021 11:07:45 - INFO - __main__ - Step 120391: {'lr': 4.7776948223311215e-05, 'samples': 23115072, 'steps': 120390, 'loss/train': 0.2398512363433838} 08/31/2021 11:07:45 - INFO - __main__ - Step 120392: {'lr': 4.7773828131549654e-05, 'samples': 23115264, 'steps': 120391, 'loss/train': 1.0755945444107056} 08/31/2021 11:07:47 - INFO - __main__ - Step 120393: {'lr': 4.7770708130908e-05, 'samples': 23115456, 'steps': 120392, 'loss/train': 1.1480175256729126} 08/31/2021 11:07:47 - INFO - __main__ - Step 120394: {'lr': 4.776758822138774e-05, 'samples': 23115648, 'steps': 120393, 'loss/train': 1.3221914768218994} 08/31/2021 11:07:47 - INFO - __main__ - Step 120395: {'lr': 4.776446840299028e-05, 'samples': 23115840, 'steps': 120394, 'loss/train': 0.026077495887875557} 08/31/2021 11:07:48 - INFO - __main__ - Step 120396: {'lr': 4.776134867571705e-05, 'samples': 23116032, 'steps': 120395, 'loss/train': 0.6830165386199951} 08/31/2021 11:07:48 - INFO - __main__ - Step 120397: {'lr': 4.7758229039569414e-05, 'samples': 23116224, 'steps': 120396, 'loss/train': 1.4481171369552612} 08/31/2021 11:07:50 - INFO - __main__ - Step 120398: {'lr': 4.775510949454881e-05, 'samples': 23116416, 'steps': 120397, 'loss/train': 0.8223992586135864} 08/31/2021 11:07:50 - INFO - __main__ - Step 120399: {'lr': 4.775199004065661e-05, 'samples': 23116608, 'steps': 120398, 'loss/train': 1.182867407798767} 08/31/2021 11:07:51 - INFO - __main__ - Step 120400: {'lr': 4.774887067789427e-05, 'samples': 23116800, 'steps': 120399, 'loss/train': 0.6211618185043335} 08/31/2021 11:07:51 - INFO - __main__ - Step 120401: {'lr': 4.7745751406263163e-05, 'samples': 23116992, 'steps': 120400, 'loss/train': 1.4867851734161377} 08/31/2021 11:07:51 - INFO - __main__ - Step 120402: {'lr': 4.774263222576469e-05, 'samples': 23117184, 'steps': 120401, 'loss/train': 0.5487751364707947} 08/31/2021 11:07:52 - INFO - __main__ - Step 120403: {'lr': 4.7739513136400346e-05, 'samples': 23117376, 'steps': 120402, 'loss/train': 0.9189284443855286} 08/31/2021 11:07:53 - INFO - __main__ - Step 120404: {'lr': 4.773639413817138e-05, 'samples': 23117568, 'steps': 120403, 'loss/train': 0.9836595058441162} 08/31/2021 11:07:54 - INFO - __main__ - Step 120405: {'lr': 4.773327523107926e-05, 'samples': 23117760, 'steps': 120404, 'loss/train': 0.767414391040802} 08/31/2021 11:07:54 - INFO - __main__ - Step 120406: {'lr': 4.773015641512543e-05, 'samples': 23117952, 'steps': 120405, 'loss/train': 0.9554055333137512} 08/31/2021 11:07:54 - INFO - __main__ - Step 120407: {'lr': 4.772703769031125e-05, 'samples': 23118144, 'steps': 120406, 'loss/train': 0.8400035500526428} 08/31/2021 11:07:55 - INFO - __main__ - Step 120408: {'lr': 4.772391905663817e-05, 'samples': 23118336, 'steps': 120407, 'loss/train': 1.2901434898376465} 08/31/2021 11:07:56 - INFO - __main__ - Step 120409: {'lr': 4.772080051410757e-05, 'samples': 23118528, 'steps': 120408, 'loss/train': 1.0612989664077759} 08/31/2021 11:07:57 - INFO - __main__ - Step 120410: {'lr': 4.771768206272084e-05, 'samples': 23118720, 'steps': 120409, 'loss/train': 1.1771694421768188} 08/31/2021 11:07:57 - INFO - __main__ - Step 120411: {'lr': 4.77145637024794e-05, 'samples': 23118912, 'steps': 120410, 'loss/train': 1.1894391775131226} 08/31/2021 11:07:57 - INFO - __main__ - Step 120412: {'lr': 4.771144543338465e-05, 'samples': 23119104, 'steps': 120411, 'loss/train': 0.8577622175216675} 08/31/2021 11:07:58 - INFO - __main__ - Step 120413: {'lr': 4.770832725543803e-05, 'samples': 23119296, 'steps': 120412, 'loss/train': 1.101138949394226} 08/31/2021 11:07:59 - INFO - __main__ - Step 120414: {'lr': 4.770520916864088e-05, 'samples': 23119488, 'steps': 120413, 'loss/train': 1.315682291984558} 08/31/2021 11:08:00 - INFO - __main__ - Step 120415: {'lr': 4.7702091172994676e-05, 'samples': 23119680, 'steps': 120414, 'loss/train': 1.0097267627716064} 08/31/2021 11:08:00 - INFO - __main__ - Step 120416: {'lr': 4.7698973268500836e-05, 'samples': 23119872, 'steps': 120415, 'loss/train': 0.5270302295684814} 08/31/2021 11:08:01 - INFO - __main__ - Step 120417: {'lr': 4.7695855455160644e-05, 'samples': 23120064, 'steps': 120416, 'loss/train': 1.535955786705017} 08/31/2021 11:08:01 - INFO - __main__ - Step 120418: {'lr': 4.769273773297558e-05, 'samples': 23120256, 'steps': 120417, 'loss/train': 0.6483237147331238} 08/31/2021 11:08:01 - INFO - __main__ - Step 120419: {'lr': 4.768962010194705e-05, 'samples': 23120448, 'steps': 120418, 'loss/train': 0.3835262656211853} 08/31/2021 11:08:03 - INFO - __main__ - Step 120420: {'lr': 4.7686502562076465e-05, 'samples': 23120640, 'steps': 120419, 'loss/train': 0.9785672426223755} 08/31/2021 11:08:03 - INFO - __main__ - Step 120421: {'lr': 4.7683385113365227e-05, 'samples': 23120832, 'steps': 120420, 'loss/train': 1.0758092403411865} 08/31/2021 11:08:04 - INFO - __main__ - Step 120422: {'lr': 4.768026775581472e-05, 'samples': 23121024, 'steps': 120421, 'loss/train': 1.3417906761169434} 08/31/2021 11:08:04 - INFO - __main__ - Step 120423: {'lr': 4.7677150489426365e-05, 'samples': 23121216, 'steps': 120422, 'loss/train': 1.1591169834136963} 08/31/2021 11:08:04 - INFO - __main__ - Step 120424: {'lr': 4.767403331420156e-05, 'samples': 23121408, 'steps': 120423, 'loss/train': 1.062902808189392} 08/31/2021 11:08:06 - INFO - __main__ - Step 120425: {'lr': 4.767091623014169e-05, 'samples': 23121600, 'steps': 120424, 'loss/train': 1.150028109550476} 08/31/2021 11:08:06 - INFO - __main__ - Step 120426: {'lr': 4.766779923724823e-05, 'samples': 23121792, 'steps': 120425, 'loss/train': 1.4071649312973022} 08/31/2021 11:08:07 - INFO - __main__ - Step 120427: {'lr': 4.766468233552251e-05, 'samples': 23121984, 'steps': 120426, 'loss/train': 0.8884729146957397} 08/31/2021 11:08:07 - INFO - __main__ - Step 120428: {'lr': 4.766156552496595e-05, 'samples': 23122176, 'steps': 120427, 'loss/train': 0.6519317030906677} 08/31/2021 11:08:07 - INFO - __main__ - Step 120429: {'lr': 4.7658448805579984e-05, 'samples': 23122368, 'steps': 120428, 'loss/train': 1.1187653541564941} 08/31/2021 11:08:09 - INFO - __main__ - Step 120430: {'lr': 4.765533217736609e-05, 'samples': 23122560, 'steps': 120429, 'loss/train': 1.1793549060821533} 08/31/2021 11:08:09 - INFO - __main__ - Step 120431: {'lr': 4.7652215640325485e-05, 'samples': 23122752, 'steps': 120430, 'loss/train': 0.922286331653595} 08/31/2021 11:08:10 - INFO - __main__ - Step 120432: {'lr': 4.764909919445967e-05, 'samples': 23122944, 'steps': 120431, 'loss/train': 0.25928226113319397} 08/31/2021 11:08:10 - INFO - __main__ - Step 120433: {'lr': 4.7645982839770034e-05, 'samples': 23123136, 'steps': 120432, 'loss/train': 1.0519905090332031} 08/31/2021 11:08:10 - INFO - __main__ - Step 120434: {'lr': 4.764286657625802e-05, 'samples': 23123328, 'steps': 120433, 'loss/train': 0.711171567440033} 08/31/2021 11:08:12 - INFO - __main__ - Step 120435: {'lr': 4.7639750403925016e-05, 'samples': 23123520, 'steps': 120434, 'loss/train': 0.4122042655944824} 08/31/2021 11:08:12 - INFO - __main__ - Step 120436: {'lr': 4.7636634322772405e-05, 'samples': 23123712, 'steps': 120435, 'loss/train': 3.2254059314727783} 08/31/2021 11:08:13 - INFO - __main__ - Step 120437: {'lr': 4.7633518332801576e-05, 'samples': 23123904, 'steps': 120436, 'loss/train': 0.24360932409763336} 08/31/2021 11:08:13 - INFO - __main__ - Step 120438: {'lr': 4.7630402434014006e-05, 'samples': 23124096, 'steps': 120437, 'loss/train': 1.407548427581787} 08/31/2021 11:08:13 - INFO - __main__ - Step 120439: {'lr': 4.7627286626411025e-05, 'samples': 23124288, 'steps': 120438, 'loss/train': 1.7715562582015991} 08/31/2021 11:08:14 - INFO - __main__ - Step 120440: {'lr': 4.7624170909994074e-05, 'samples': 23124480, 'steps': 120439, 'loss/train': 0.7530739903450012} 08/31/2021 11:08:16 - INFO - __main__ - Step 120441: {'lr': 4.762105528476457e-05, 'samples': 23124672, 'steps': 120440, 'loss/train': 1.200257420539856} 08/31/2021 11:08:16 - INFO - __main__ - Step 120442: {'lr': 4.761793975072387e-05, 'samples': 23124864, 'steps': 120441, 'loss/train': 1.8489362001419067} 08/31/2021 11:08:17 - INFO - __main__ - Step 120443: {'lr': 4.761482430787348e-05, 'samples': 23125056, 'steps': 120442, 'loss/train': 1.4484161138534546} 08/31/2021 11:08:17 - INFO - __main__ - Step 120444: {'lr': 4.761170895621464e-05, 'samples': 23125248, 'steps': 120443, 'loss/train': 1.2037900686264038} 08/31/2021 11:08:17 - INFO - __main__ - Step 120445: {'lr': 4.7608593695748856e-05, 'samples': 23125440, 'steps': 120444, 'loss/train': 2.3830513954162598} 08/31/2021 11:08:19 - INFO - __main__ - Step 120446: {'lr': 4.760547852647753e-05, 'samples': 23125632, 'steps': 120445, 'loss/train': 1.8307595252990723} 08/31/2021 11:08:19 - INFO - __main__ - Step 120447: {'lr': 4.760236344840202e-05, 'samples': 23125824, 'steps': 120446, 'loss/train': 0.7445920705795288} 08/31/2021 11:08:20 - INFO - __main__ - Step 120448: {'lr': 4.7599248461523805e-05, 'samples': 23126016, 'steps': 120447, 'loss/train': 1.5131621360778809} 08/31/2021 11:08:20 - INFO - __main__ - Step 120449: {'lr': 4.759613356584422e-05, 'samples': 23126208, 'steps': 120448, 'loss/train': 1.2826554775238037} 08/31/2021 11:08:20 - INFO - __main__ - Step 120450: {'lr': 4.7593018761364685e-05, 'samples': 23126400, 'steps': 120449, 'loss/train': 1.120684027671814} 08/31/2021 11:08:22 - INFO - __main__ - Step 120451: {'lr': 4.758990404808664e-05, 'samples': 23126592, 'steps': 120450, 'loss/train': 1.4048668146133423} 08/31/2021 11:08:23 - INFO - __main__ - Step 120452: {'lr': 4.758678942601144e-05, 'samples': 23126784, 'steps': 120451, 'loss/train': 0.897091269493103} 08/31/2021 11:08:23 - INFO - __main__ - Step 120453: {'lr': 4.758367489514051e-05, 'samples': 23126976, 'steps': 120452, 'loss/train': 1.5203266143798828} 08/31/2021 11:08:23 - INFO - __main__ - Step 120454: {'lr': 4.7580560455475264e-05, 'samples': 23127168, 'steps': 120453, 'loss/train': 0.6981784105300903} 08/31/2021 11:08:24 - INFO - __main__ - Step 120455: {'lr': 4.7577446107017086e-05, 'samples': 23127360, 'steps': 120454, 'loss/train': 1.4712717533111572} 08/31/2021 11:08:25 - INFO - __main__ - Step 120456: {'lr': 4.757433184976737e-05, 'samples': 23127552, 'steps': 120455, 'loss/train': 1.0313810110092163} 08/31/2021 11:08:26 - INFO - __main__ - Step 120457: {'lr': 4.757121768372763e-05, 'samples': 23127744, 'steps': 120456, 'loss/train': 1.7421462535858154} 08/31/2021 11:08:26 - INFO - __main__ - Step 120458: {'lr': 4.75681036088991e-05, 'samples': 23127936, 'steps': 120457, 'loss/train': 1.0872472524642944} 08/31/2021 11:08:26 - INFO - __main__ - Step 120459: {'lr': 4.7564989625283245e-05, 'samples': 23128128, 'steps': 120458, 'loss/train': 1.0758757591247559} 08/31/2021 11:08:27 - INFO - __main__ - Step 120460: {'lr': 4.756187573288151e-05, 'samples': 23128320, 'steps': 120459, 'loss/train': 1.243591547012329} 08/31/2021 11:08:28 - INFO - __main__ - Step 120461: {'lr': 4.7558761931695255e-05, 'samples': 23128512, 'steps': 120460, 'loss/train': 1.5496735572814941} 08/31/2021 11:08:29 - INFO - __main__ - Step 120462: {'lr': 4.75556482217259e-05, 'samples': 23128704, 'steps': 120461, 'loss/train': 1.1061466932296753} 08/31/2021 11:08:29 - INFO - __main__ - Step 120463: {'lr': 4.7552534602974846e-05, 'samples': 23128896, 'steps': 120462, 'loss/train': 1.0399088859558105} 08/31/2021 11:08:29 - INFO - __main__ - Step 120464: {'lr': 4.7549421075443497e-05, 'samples': 23129088, 'steps': 120463, 'loss/train': 0.5169876217842102} 08/31/2021 11:08:30 - INFO - __main__ - Step 120465: {'lr': 4.754630763913323e-05, 'samples': 23129280, 'steps': 120464, 'loss/train': 1.311522364616394} 08/31/2021 11:08:31 - INFO - __main__ - Step 120466: {'lr': 4.7543194294045495e-05, 'samples': 23129472, 'steps': 120465, 'loss/train': 0.10170716047286987} 08/31/2021 11:08:32 - INFO - __main__ - Step 120467: {'lr': 4.7540081040181675e-05, 'samples': 23129664, 'steps': 120466, 'loss/train': 1.0066591501235962} 08/31/2021 11:08:32 - INFO - __main__ - Step 120468: {'lr': 4.753696787754319e-05, 'samples': 23129856, 'steps': 120467, 'loss/train': 1.248473048210144} 08/31/2021 11:08:32 - INFO - __main__ - Step 120469: {'lr': 4.7533854806131396e-05, 'samples': 23130048, 'steps': 120468, 'loss/train': 1.3759033679962158} 08/31/2021 11:08:33 - INFO - __main__ - Step 120470: {'lr': 4.75307418259478e-05, 'samples': 23130240, 'steps': 120469, 'loss/train': 0.8851996660232544} 08/31/2021 11:08:34 - INFO - __main__ - Step 120471: {'lr': 4.752762893699364e-05, 'samples': 23130432, 'steps': 120470, 'loss/train': 0.7790979743003845} 08/31/2021 11:08:35 - INFO - __main__ - Step 120472: {'lr': 4.752451613927042e-05, 'samples': 23130624, 'steps': 120471, 'loss/train': 1.3092705011367798} 08/31/2021 11:08:35 - INFO - __main__ - Step 120473: {'lr': 4.752140343277953e-05, 'samples': 23130816, 'steps': 120472, 'loss/train': 1.1866953372955322} 08/31/2021 11:08:35 - INFO - __main__ - Step 120474: {'lr': 4.7518290817522375e-05, 'samples': 23131008, 'steps': 120473, 'loss/train': 0.9232425689697266} 08/31/2021 11:08:36 - INFO - __main__ - Step 120475: {'lr': 4.7515178293500354e-05, 'samples': 23131200, 'steps': 120474, 'loss/train': 0.9653647541999817} 08/31/2021 11:08:38 - INFO - __main__ - Step 120476: {'lr': 4.751206586071485e-05, 'samples': 23131392, 'steps': 120475, 'loss/train': 1.4305357933044434} 08/31/2021 11:08:38 - INFO - __main__ - Step 120477: {'lr': 4.750895351916732e-05, 'samples': 23131584, 'steps': 120476, 'loss/train': 1.8775230646133423} 08/31/2021 11:08:38 - INFO - __main__ - Step 120478: {'lr': 4.750584126885909e-05, 'samples': 23131776, 'steps': 120477, 'loss/train': 0.4549039602279663} 08/31/2021 11:08:39 - INFO - __main__ - Step 120479: {'lr': 4.750272910979164e-05, 'samples': 23131968, 'steps': 120478, 'loss/train': 1.2717117071151733} 08/31/2021 11:08:39 - INFO - __main__ - Step 120480: {'lr': 4.749961704196632e-05, 'samples': 23132160, 'steps': 120479, 'loss/train': 0.02357163466513157} 08/31/2021 11:08:39 - INFO - __main__ - Step 120481: {'lr': 4.749650506538453e-05, 'samples': 23132352, 'steps': 120480, 'loss/train': 1.1562168598175049} 08/31/2021 11:08:41 - INFO - __main__ - Step 120482: {'lr': 4.7493393180047725e-05, 'samples': 23132544, 'steps': 120481, 'loss/train': 1.4159404039382935} 08/31/2021 11:08:41 - INFO - __main__ - Step 120483: {'lr': 4.749028138595723e-05, 'samples': 23132736, 'steps': 120482, 'loss/train': 1.5379483699798584} 08/31/2021 11:08:42 - INFO - __main__ - Step 120484: {'lr': 4.748716968311459e-05, 'samples': 23132928, 'steps': 120483, 'loss/train': 1.5498673915863037} 08/31/2021 11:08:42 - INFO - __main__ - Step 120485: {'lr': 4.7484058071521036e-05, 'samples': 23133120, 'steps': 120484, 'loss/train': 0.8645671606063843} 08/31/2021 11:08:42 - INFO - __main__ - Step 120486: {'lr': 4.748094655117805e-05, 'samples': 23133312, 'steps': 120485, 'loss/train': 0.5529968738555908} 08/31/2021 11:08:44 - INFO - __main__ - Step 120487: {'lr': 4.7477835122087e-05, 'samples': 23133504, 'steps': 120486, 'loss/train': 1.4105968475341797} 08/31/2021 11:08:44 - INFO - __main__ - Step 120488: {'lr': 4.7474723784249304e-05, 'samples': 23133696, 'steps': 120487, 'loss/train': 1.0813446044921875} 08/31/2021 11:08:45 - INFO - __main__ - Step 120489: {'lr': 4.747161253766641e-05, 'samples': 23133888, 'steps': 120488, 'loss/train': 1.5022523403167725} 08/31/2021 11:08:45 - INFO - __main__ - Step 120490: {'lr': 4.746850138233966e-05, 'samples': 23134080, 'steps': 120489, 'loss/train': 1.1500568389892578} 08/31/2021 11:08:45 - INFO - __main__ - Step 120491: {'lr': 4.746539031827046e-05, 'samples': 23134272, 'steps': 120490, 'loss/train': 1.1842666864395142} 08/31/2021 11:08:48 - INFO - __main__ - Step 120492: {'lr': 4.746227934546027e-05, 'samples': 23134464, 'steps': 120491, 'loss/train': 0.9979186654090881} 08/31/2021 11:08:48 - INFO - __main__ - Step 120493: {'lr': 4.7459168463910405e-05, 'samples': 23134656, 'steps': 120492, 'loss/train': 1.2649524211883545} 08/31/2021 11:08:48 - INFO - __main__ - Step 120494: {'lr': 4.745605767362235e-05, 'samples': 23134848, 'steps': 120493, 'loss/train': 0.6829307079315186} 08/31/2021 11:08:49 - INFO - __main__ - Step 120495: {'lr': 4.745294697459746e-05, 'samples': 23135040, 'steps': 120494, 'loss/train': 0.712083101272583} 08/31/2021 11:08:49 - INFO - __main__ - Step 120496: {'lr': 4.744983636683714e-05, 'samples': 23135232, 'steps': 120495, 'loss/train': 0.9149895906448364} 08/31/2021 11:08:51 - INFO - __main__ - Step 120497: {'lr': 4.744672585034288e-05, 'samples': 23135424, 'steps': 120496, 'loss/train': 1.0746883153915405} 08/31/2021 11:08:51 - INFO - __main__ - Step 120498: {'lr': 4.744361542511591e-05, 'samples': 23135616, 'steps': 120497, 'loss/train': 0.6313642859458923} 08/31/2021 11:08:52 - INFO - __main__ - Step 120499: {'lr': 4.744050509115774e-05, 'samples': 23135808, 'steps': 120498, 'loss/train': 1.1177623271942139} 08/31/2021 11:08:52 - INFO - __main__ - Step 120500: {'lr': 4.7437394848469764e-05, 'samples': 23136000, 'steps': 120499, 'loss/train': 0.2874111831188202} 08/31/2021 11:08:52 - INFO - __main__ - Step 120501: {'lr': 4.7434284697053354e-05, 'samples': 23136192, 'steps': 120500, 'loss/train': 1.0735074281692505} 08/31/2021 11:08:54 - INFO - __main__ - Step 120502: {'lr': 4.7431174636909934e-05, 'samples': 23136384, 'steps': 120501, 'loss/train': 1.2624260187149048} 08/31/2021 11:08:54 - INFO - __main__ - Step 120503: {'lr': 4.7428064668040895e-05, 'samples': 23136576, 'steps': 120502, 'loss/train': 1.1027570962905884} 08/31/2021 11:08:54 - INFO - __main__ - Step 120504: {'lr': 4.7424954790447645e-05, 'samples': 23136768, 'steps': 120503, 'loss/train': 0.5382112860679626} 08/31/2021 11:08:55 - INFO - __main__ - Step 120505: {'lr': 4.742184500413157e-05, 'samples': 23136960, 'steps': 120504, 'loss/train': 1.2420645952224731} 08/31/2021 11:08:55 - INFO - __main__ - Step 120506: {'lr': 4.74187353090941e-05, 'samples': 23137152, 'steps': 120505, 'loss/train': 0.13227225840091705} 08/31/2021 11:08:57 - INFO - __main__ - Step 120507: {'lr': 4.741562570533664e-05, 'samples': 23137344, 'steps': 120506, 'loss/train': 1.142269492149353} 08/31/2021 11:08:58 - INFO - __main__ - Step 120508: {'lr': 4.741251619286055e-05, 'samples': 23137536, 'steps': 120507, 'loss/train': 1.1363492012023926} 08/31/2021 11:08:58 - INFO - __main__ - Step 120509: {'lr': 4.740940677166727e-05, 'samples': 23137728, 'steps': 120508, 'loss/train': 0.4527056813240051} 08/31/2021 11:08:58 - INFO - __main__ - Step 120510: {'lr': 4.740629744175823e-05, 'samples': 23137920, 'steps': 120509, 'loss/train': 0.014680229127407074} 08/31/2021 11:08:59 - INFO - __main__ - Step 120511: {'lr': 4.7403188203134744e-05, 'samples': 23138112, 'steps': 120510, 'loss/train': 0.017274102196097374} 08/31/2021 11:08:59 - INFO - __main__ - Step 120512: {'lr': 4.740007905579824e-05, 'samples': 23138304, 'steps': 120511, 'loss/train': 0.7965938448905945} 08/31/2021 11:09:00 - INFO - __main__ - Step 120513: {'lr': 4.739696999975013e-05, 'samples': 23138496, 'steps': 120512, 'loss/train': 0.3737179934978485} 08/31/2021 11:09:01 - INFO - __main__ - Step 120514: {'lr': 4.7393861034991826e-05, 'samples': 23138688, 'steps': 120513, 'loss/train': 1.0361018180847168} 08/31/2021 11:09:01 - INFO - __main__ - Step 120515: {'lr': 4.739075216152475e-05, 'samples': 23138880, 'steps': 120514, 'loss/train': 0.8324598670005798} 08/31/2021 11:09:02 - INFO - __main__ - Step 120516: {'lr': 4.738764337935023e-05, 'samples': 23139072, 'steps': 120515, 'loss/train': 1.136846899986267} 08/31/2021 11:09:02 - INFO - __main__ - Step 120517: {'lr': 4.7384534688469735e-05, 'samples': 23139264, 'steps': 120516, 'loss/train': 1.4470640420913696} 08/31/2021 11:09:02 - INFO - __main__ - Step 120518: {'lr': 4.738142608888463e-05, 'samples': 23139456, 'steps': 120517, 'loss/train': 1.0124317407608032} 08/31/2021 11:09:04 - INFO - __main__ - Step 120519: {'lr': 4.737831758059633e-05, 'samples': 23139648, 'steps': 120518, 'loss/train': 0.28465715050697327} 08/31/2021 11:09:04 - INFO - __main__ - Step 120520: {'lr': 4.737520916360624e-05, 'samples': 23139840, 'steps': 120519, 'loss/train': 1.4514529705047607} 08/31/2021 11:09:05 - INFO - __main__ - Step 120521: {'lr': 4.737210083791577e-05, 'samples': 23140032, 'steps': 120520, 'loss/train': 1.3841400146484375} 08/31/2021 11:09:05 - INFO - __main__ - Step 120522: {'lr': 4.736899260352629e-05, 'samples': 23140224, 'steps': 120521, 'loss/train': 1.5646356344223022} 08/31/2021 11:09:05 - INFO - __main__ - Step 120523: {'lr': 4.7365884460439185e-05, 'samples': 23140416, 'steps': 120522, 'loss/train': 0.027370963245630264} 08/31/2021 11:09:07 - INFO - __main__ - Step 120524: {'lr': 4.736277640865599e-05, 'samples': 23140608, 'steps': 120523, 'loss/train': 0.864547073841095} 08/31/2021 11:09:07 - INFO - __main__ - Step 120525: {'lr': 4.7359668448177905e-05, 'samples': 23140800, 'steps': 120524, 'loss/train': 1.2892374992370605} 08/31/2021 11:09:08 - INFO - __main__ - Step 120526: {'lr': 4.7356560579006444e-05, 'samples': 23140992, 'steps': 120525, 'loss/train': 0.12125782668590546} 08/31/2021 11:09:08 - INFO - __main__ - Step 120527: {'lr': 4.7353452801143e-05, 'samples': 23141184, 'steps': 120526, 'loss/train': 1.3353761434555054} 08/31/2021 11:09:08 - INFO - __main__ - Step 120528: {'lr': 4.7350345114588964e-05, 'samples': 23141376, 'steps': 120527, 'loss/train': 1.9137312173843384} 08/31/2021 11:09:10 - INFO - __main__ - Step 120529: {'lr': 4.734723751934572e-05, 'samples': 23141568, 'steps': 120528, 'loss/train': 1.3310136795043945} 08/31/2021 11:09:10 - INFO - __main__ - Step 120530: {'lr': 4.734413001541468e-05, 'samples': 23141760, 'steps': 120529, 'loss/train': 0.8542492389678955} 08/31/2021 11:09:11 - INFO - __main__ - Step 120531: {'lr': 4.7341022602797265e-05, 'samples': 23141952, 'steps': 120530, 'loss/train': 1.2010589838027954} 08/31/2021 11:09:11 - INFO - __main__ - Step 120532: {'lr': 4.733791528149484e-05, 'samples': 23142144, 'steps': 120531, 'loss/train': 0.32387036085128784} 08/31/2021 11:09:11 - INFO - __main__ - Step 120533: {'lr': 4.7334808051508834e-05, 'samples': 23142336, 'steps': 120532, 'loss/train': 1.7314618825912476} 08/31/2021 11:09:13 - INFO - __main__ - Step 120534: {'lr': 4.7331700912840644e-05, 'samples': 23142528, 'steps': 120533, 'loss/train': 0.11140984296798706} 08/31/2021 11:09:13 - INFO - __main__ - Step 120535: {'lr': 4.732859386549165e-05, 'samples': 23142720, 'steps': 120534, 'loss/train': 0.2258489727973938} 08/31/2021 11:09:14 - INFO - __main__ - Step 120536: {'lr': 4.7325486909463254e-05, 'samples': 23142912, 'steps': 120535, 'loss/train': 0.8920168876647949} 08/31/2021 11:09:14 - INFO - __main__ - Step 120537: {'lr': 4.732238004475695e-05, 'samples': 23143104, 'steps': 120536, 'loss/train': 1.0346955060958862} 08/31/2021 11:09:15 - INFO - __main__ - Step 120538: {'lr': 4.731927327137397e-05, 'samples': 23143296, 'steps': 120537, 'loss/train': 0.031769026070833206} 08/31/2021 11:09:16 - INFO - __main__ - Step 120539: {'lr': 4.731616658931584e-05, 'samples': 23143488, 'steps': 120538, 'loss/train': 1.5653458833694458} 08/31/2021 11:09:16 - INFO - __main__ - Step 120540: {'lr': 4.731305999858387e-05, 'samples': 23143680, 'steps': 120539, 'loss/train': 1.1855069398880005} 08/31/2021 11:09:17 - INFO - __main__ - Step 120541: {'lr': 4.730995349917952e-05, 'samples': 23143872, 'steps': 120540, 'loss/train': 1.1109968423843384} 08/31/2021 11:09:17 - INFO - __main__ - Step 120542: {'lr': 4.7306847091104195e-05, 'samples': 23144064, 'steps': 120541, 'loss/train': 1.2392479181289673} 08/31/2021 11:09:17 - INFO - __main__ - Step 120543: {'lr': 4.730374077435926e-05, 'samples': 23144256, 'steps': 120542, 'loss/train': 0.8229961395263672} 08/31/2021 11:09:20 - INFO - __main__ - Step 120544: {'lr': 4.730063454894615e-05, 'samples': 23144448, 'steps': 120543, 'loss/train': 1.3138991594314575} 08/31/2021 11:09:20 - INFO - __main__ - Step 120545: {'lr': 4.729752841486623e-05, 'samples': 23144640, 'steps': 120544, 'loss/train': 0.07866312563419342} 08/31/2021 11:09:20 - INFO - __main__ - Step 120546: {'lr': 4.729442237212092e-05, 'samples': 23144832, 'steps': 120545, 'loss/train': 0.33167266845703125} 08/31/2021 11:09:21 - INFO - __main__ - Step 120547: {'lr': 4.7291316420711605e-05, 'samples': 23145024, 'steps': 120546, 'loss/train': 0.7578396201133728} 08/31/2021 11:09:21 - INFO - __main__ - Step 120548: {'lr': 4.7288210560639696e-05, 'samples': 23145216, 'steps': 120547, 'loss/train': 1.0879167318344116} 08/31/2021 11:09:22 - INFO - __main__ - Step 120549: {'lr': 4.7285104791906617e-05, 'samples': 23145408, 'steps': 120548, 'loss/train': 1.442721962928772} 08/31/2021 11:09:23 - INFO - __main__ - Step 120550: {'lr': 4.728199911451372e-05, 'samples': 23145600, 'steps': 120549, 'loss/train': 1.0730743408203125} 08/31/2021 11:09:23 - INFO - __main__ - Step 120551: {'lr': 4.727889352846249e-05, 'samples': 23145792, 'steps': 120550, 'loss/train': 1.338718295097351} 08/31/2021 11:09:24 - INFO - __main__ - Step 120552: {'lr': 4.727578803375421e-05, 'samples': 23145984, 'steps': 120551, 'loss/train': 1.0244276523590088} 08/31/2021 11:09:24 - INFO - __main__ - Step 120553: {'lr': 4.7272682630390335e-05, 'samples': 23146176, 'steps': 120552, 'loss/train': 1.3114030361175537} 08/31/2021 11:09:25 - INFO - __main__ - Step 120554: {'lr': 4.726957731837222e-05, 'samples': 23146368, 'steps': 120553, 'loss/train': 0.2465808391571045} 08/31/2021 11:09:26 - INFO - __main__ - Step 120555: {'lr': 4.726647209770135e-05, 'samples': 23146560, 'steps': 120554, 'loss/train': 0.2244030237197876} 08/31/2021 11:09:27 - INFO - __main__ - Step 120556: {'lr': 4.7263366968379076e-05, 'samples': 23146752, 'steps': 120555, 'loss/train': 1.077013611793518} 08/31/2021 11:09:27 - INFO - __main__ - Step 120557: {'lr': 4.726026193040678e-05, 'samples': 23146944, 'steps': 120556, 'loss/train': 1.0827405452728271} 08/31/2021 11:09:27 - INFO - __main__ - Step 120558: {'lr': 4.725715698378588e-05, 'samples': 23147136, 'steps': 120557, 'loss/train': 0.7235039472579956} 08/31/2021 11:09:28 - INFO - __main__ - Step 120559: {'lr': 4.72540521285178e-05, 'samples': 23147328, 'steps': 120558, 'loss/train': 4.298430919647217} 08/31/2021 11:09:29 - INFO - __main__ - Step 120560: {'lr': 4.725094736460389e-05, 'samples': 23147520, 'steps': 120559, 'loss/train': 1.3450431823730469} 08/31/2021 11:09:30 - INFO - __main__ - Step 120561: {'lr': 4.72478426920456e-05, 'samples': 23147712, 'steps': 120560, 'loss/train': 1.3703638315200806} 08/31/2021 11:09:30 - INFO - __main__ - Step 120562: {'lr': 4.7244738110844286e-05, 'samples': 23147904, 'steps': 120561, 'loss/train': 1.0518938302993774} 08/31/2021 11:09:31 - INFO - __main__ - Step 120563: {'lr': 4.724163362100137e-05, 'samples': 23148096, 'steps': 120562, 'loss/train': 1.019253134727478} 08/31/2021 11:09:31 - INFO - __main__ - Step 120564: {'lr': 4.723852922251831e-05, 'samples': 23148288, 'steps': 120563, 'loss/train': 0.28700515627861023} 08/31/2021 11:09:31 - INFO - __main__ - Step 120565: {'lr': 4.723542491539637e-05, 'samples': 23148480, 'steps': 120564, 'loss/train': 1.3878202438354492} 08/31/2021 11:09:33 - INFO - __main__ - Step 120566: {'lr': 4.723232069963704e-05, 'samples': 23148672, 'steps': 120565, 'loss/train': 1.3095581531524658} 08/31/2021 11:09:33 - INFO - __main__ - Step 120567: {'lr': 4.722921657524168e-05, 'samples': 23148864, 'steps': 120566, 'loss/train': 0.9741774797439575} 08/31/2021 11:09:34 - INFO - __main__ - Step 120568: {'lr': 4.7226112542211707e-05, 'samples': 23149056, 'steps': 120567, 'loss/train': 1.2577170133590698} 08/31/2021 11:09:34 - INFO - __main__ - Step 120569: {'lr': 4.7223008600548515e-05, 'samples': 23149248, 'steps': 120568, 'loss/train': 0.9035346508026123} 08/31/2021 11:09:34 - INFO - __main__ - Step 120570: {'lr': 4.7219904750253506e-05, 'samples': 23149440, 'steps': 120569, 'loss/train': 1.4402753114700317} 08/31/2021 11:09:36 - INFO - __main__ - Step 120571: {'lr': 4.721680099132808e-05, 'samples': 23149632, 'steps': 120570, 'loss/train': 1.105026364326477} 08/31/2021 11:09:36 - INFO - __main__ - Step 120572: {'lr': 4.721369732377362e-05, 'samples': 23149824, 'steps': 120571, 'loss/train': 0.9031258821487427} 08/31/2021 11:09:37 - INFO - __main__ - Step 120573: {'lr': 4.721059374759157e-05, 'samples': 23150016, 'steps': 120572, 'loss/train': 0.9314941167831421} 08/31/2021 11:09:37 - INFO - __main__ - Step 120574: {'lr': 4.720749026278329e-05, 'samples': 23150208, 'steps': 120573, 'loss/train': 1.0306187868118286} 08/31/2021 11:09:37 - INFO - __main__ - Step 120575: {'lr': 4.7204386869350165e-05, 'samples': 23150400, 'steps': 120574, 'loss/train': 1.451578974723816} 08/31/2021 11:09:39 - INFO - __main__ - Step 120576: {'lr': 4.720128356729364e-05, 'samples': 23150592, 'steps': 120575, 'loss/train': 1.255466103553772} 08/31/2021 11:09:39 - INFO - __main__ - Step 120577: {'lr': 4.719818035661508e-05, 'samples': 23150784, 'steps': 120576, 'loss/train': 1.1283965110778809} 08/31/2021 11:09:40 - INFO - __main__ - Step 120578: {'lr': 4.719507723731595e-05, 'samples': 23150976, 'steps': 120577, 'loss/train': 0.7572106122970581} 08/31/2021 11:09:40 - INFO - __main__ - Step 120579: {'lr': 4.7191974209397495e-05, 'samples': 23151168, 'steps': 120578, 'loss/train': 0.5934815406799316} 08/31/2021 11:09:40 - INFO - __main__ - Step 120580: {'lr': 4.7188871272861254e-05, 'samples': 23151360, 'steps': 120579, 'loss/train': 1.2314343452453613} 08/31/2021 11:09:42 - INFO - __main__ - Step 120581: {'lr': 4.718576842770855e-05, 'samples': 23151552, 'steps': 120580, 'loss/train': 0.7824079394340515} 08/31/2021 11:09:43 - INFO - __main__ - Step 120582: {'lr': 4.718266567394083e-05, 'samples': 23151744, 'steps': 120581, 'loss/train': 1.5014853477478027} 08/31/2021 11:09:43 - INFO - __main__ - Step 120583: {'lr': 4.7179563011559455e-05, 'samples': 23151936, 'steps': 120582, 'loss/train': 0.3065739870071411} 08/31/2021 11:09:43 - INFO - __main__ - Step 120584: {'lr': 4.717646044056584e-05, 'samples': 23152128, 'steps': 120583, 'loss/train': 1.6784974336624146} 08/31/2021 11:09:44 - INFO - __main__ - Step 120585: {'lr': 4.717335796096139e-05, 'samples': 23152320, 'steps': 120584, 'loss/train': 0.5105018019676208} 08/31/2021 11:09:44 - INFO - __main__ - Step 120586: {'lr': 4.7170255572747485e-05, 'samples': 23152512, 'steps': 120585, 'loss/train': 0.6319718360900879} 08/31/2021 11:09:46 - INFO - __main__ - Step 120587: {'lr': 4.716715327592555e-05, 'samples': 23152704, 'steps': 120586, 'loss/train': 0.0329885259270668} 08/31/2021 11:09:46 - INFO - __main__ - Step 120588: {'lr': 4.716405107049696e-05, 'samples': 23152896, 'steps': 120587, 'loss/train': 0.5928289890289307} 08/31/2021 11:09:47 - INFO - __main__ - Step 120589: {'lr': 4.7160948956463115e-05, 'samples': 23153088, 'steps': 120588, 'loss/train': 0.6631938219070435} 08/31/2021 11:09:47 - INFO - __main__ - Step 120590: {'lr': 4.715784693382541e-05, 'samples': 23153280, 'steps': 120589, 'loss/train': 1.0797780752182007} 08/31/2021 11:09:47 - INFO - __main__ - Step 120591: {'lr': 4.715474500258532e-05, 'samples': 23153472, 'steps': 120590, 'loss/train': 0.8871784806251526} 08/31/2021 11:09:49 - INFO - __main__ - Step 120592: {'lr': 4.715164316274409e-05, 'samples': 23153664, 'steps': 120591, 'loss/train': 0.9030742049217224} 08/31/2021 11:09:49 - INFO - __main__ - Step 120593: {'lr': 4.714854141430322e-05, 'samples': 23153856, 'steps': 120592, 'loss/train': 1.101844310760498} 08/31/2021 11:09:50 - INFO - __main__ - Step 120594: {'lr': 4.7145439757264095e-05, 'samples': 23154048, 'steps': 120593, 'loss/train': 0.5259847640991211} 08/31/2021 11:09:50 - INFO - __main__ - Step 120595: {'lr': 4.714233819162808e-05, 'samples': 23154240, 'steps': 120594, 'loss/train': 0.5394495725631714} 08/31/2021 11:09:50 - INFO - __main__ - Step 120596: {'lr': 4.713923671739662e-05, 'samples': 23154432, 'steps': 120595, 'loss/train': 1.7039146423339844} 08/31/2021 11:09:52 - INFO - __main__ - Step 120597: {'lr': 4.713613533457106e-05, 'samples': 23154624, 'steps': 120596, 'loss/train': 0.9310132265090942} 08/31/2021 11:09:52 - INFO - __main__ - Step 120598: {'lr': 4.713303404315286e-05, 'samples': 23154816, 'steps': 120597, 'loss/train': 0.9295061826705933} 08/31/2021 11:09:53 - INFO - __main__ - Step 120599: {'lr': 4.712993284314338e-05, 'samples': 23155008, 'steps': 120598, 'loss/train': 1.1824289560317993} 08/31/2021 11:09:53 - INFO - __main__ - Step 120600: {'lr': 4.712683173454399e-05, 'samples': 23155200, 'steps': 120599, 'loss/train': 0.6985073089599609} 08/31/2021 11:09:53 - INFO - __main__ - Step 120601: {'lr': 4.712373071735615e-05, 'samples': 23155392, 'steps': 120600, 'loss/train': 1.3542630672454834} 08/31/2021 11:09:56 - INFO - __main__ - Step 120602: {'lr': 4.7120629791581214e-05, 'samples': 23155584, 'steps': 120601, 'loss/train': 1.3009778261184692} 08/31/2021 11:09:57 - INFO - __main__ - Step 120603: {'lr': 4.7117528957220604e-05, 'samples': 23155776, 'steps': 120602, 'loss/train': 0.7602051496505737} 08/31/2021 11:09:57 - INFO - __main__ - Step 120604: {'lr': 4.7114428214275694e-05, 'samples': 23155968, 'steps': 120603, 'loss/train': 1.0772130489349365} 08/31/2021 11:09:57 - INFO - __main__ - Step 120605: {'lr': 4.711132756274794e-05, 'samples': 23156160, 'steps': 120604, 'loss/train': 0.023832892999053} 08/31/2021 11:09:58 - INFO - __main__ - Step 120606: {'lr': 4.710822700263867e-05, 'samples': 23156352, 'steps': 120605, 'loss/train': 0.044804662466049194} 08/31/2021 11:09:58 - INFO - __main__ - Step 120607: {'lr': 4.710512653394927e-05, 'samples': 23156544, 'steps': 120606, 'loss/train': 0.9760973453521729} 08/31/2021 11:10:00 - INFO - __main__ - Step 120608: {'lr': 4.710202615668116e-05, 'samples': 23156736, 'steps': 120607, 'loss/train': 1.563730001449585} 08/31/2021 11:10:00 - INFO - __main__ - Step 120609: {'lr': 4.709892587083578e-05, 'samples': 23156928, 'steps': 120608, 'loss/train': 1.4574286937713623} 08/31/2021 11:10:00 - INFO - __main__ - Step 120610: {'lr': 4.709582567641446e-05, 'samples': 23157120, 'steps': 120609, 'loss/train': 1.6164846420288086} 08/31/2021 11:10:01 - INFO - __main__ - Step 120611: {'lr': 4.709272557341865e-05, 'samples': 23157312, 'steps': 120610, 'loss/train': 1.5682287216186523} 08/31/2021 11:10:01 - INFO - __main__ - Step 120612: {'lr': 4.708962556184973e-05, 'samples': 23157504, 'steps': 120611, 'loss/train': 0.2707119882106781} 08/31/2021 11:10:01 - INFO - __main__ - Step 120613: {'lr': 4.70865256417091e-05, 'samples': 23157696, 'steps': 120612, 'loss/train': 1.2518442869186401} 08/31/2021 11:10:03 - INFO - __main__ - Step 120614: {'lr': 4.7083425812998126e-05, 'samples': 23157888, 'steps': 120613, 'loss/train': 0.023081375285983086} 08/31/2021 11:10:03 - INFO - __main__ - Step 120615: {'lr': 4.708032607571824e-05, 'samples': 23158080, 'steps': 120614, 'loss/train': 0.3732355833053589} 08/31/2021 11:10:04 - INFO - __main__ - Step 120616: {'lr': 4.707722642987081e-05, 'samples': 23158272, 'steps': 120615, 'loss/train': 0.8293368816375732} 08/31/2021 11:10:04 - INFO - __main__ - Step 120617: {'lr': 4.707412687545734e-05, 'samples': 23158464, 'steps': 120616, 'loss/train': 1.011727213859558} 08/31/2021 11:10:04 - INFO - __main__ - Step 120618: {'lr': 4.707102741247907e-05, 'samples': 23158656, 'steps': 120617, 'loss/train': 0.9434621334075928} 08/31/2021 11:10:06 - INFO - __main__ - Step 120619: {'lr': 4.7067928040937455e-05, 'samples': 23158848, 'steps': 120618, 'loss/train': 0.7185593843460083} 08/31/2021 11:10:07 - INFO - __main__ - Step 120620: {'lr': 4.70648287608339e-05, 'samples': 23159040, 'steps': 120619, 'loss/train': 0.6964841485023499} 08/31/2021 11:10:07 - INFO - __main__ - Step 120621: {'lr': 4.706172957216981e-05, 'samples': 23159232, 'steps': 120620, 'loss/train': 0.9312962293624878} 08/31/2021 11:10:07 - INFO - __main__ - Step 120622: {'lr': 4.705863047494657e-05, 'samples': 23159424, 'steps': 120621, 'loss/train': 0.9542865753173828} 08/31/2021 11:10:08 - INFO - __main__ - Step 120623: {'lr': 4.705553146916558e-05, 'samples': 23159616, 'steps': 120622, 'loss/train': 1.0304828882217407} 08/31/2021 11:10:09 - INFO - __main__ - Step 120624: {'lr': 4.7052432554828215e-05, 'samples': 23159808, 'steps': 120623, 'loss/train': 0.38718870282173157} 08/31/2021 11:10:10 - INFO - __main__ - Step 120625: {'lr': 4.704933373193593e-05, 'samples': 23160000, 'steps': 120624, 'loss/train': 0.34220853447914124} 08/31/2021 11:10:10 - INFO - __main__ - Step 120626: {'lr': 4.7046235000490045e-05, 'samples': 23160192, 'steps': 120625, 'loss/train': 1.5221805572509766} 08/31/2021 11:10:10 - INFO - __main__ - Step 120627: {'lr': 4.704313636049204e-05, 'samples': 23160384, 'steps': 120626, 'loss/train': 0.040565382689237595} 08/31/2021 11:10:11 - INFO - __main__ - Step 120628: {'lr': 4.70400378119433e-05, 'samples': 23160576, 'steps': 120627, 'loss/train': 1.2593317031860352} 08/31/2021 11:10:12 - INFO - __main__ - Step 120629: {'lr': 4.7036939354845124e-05, 'samples': 23160768, 'steps': 120628, 'loss/train': 1.326829433441162} 08/31/2021 11:10:13 - INFO - __main__ - Step 120630: {'lr': 4.703384098919897e-05, 'samples': 23160960, 'steps': 120629, 'loss/train': 0.5670517683029175} 08/31/2021 11:10:13 - INFO - __main__ - Step 120631: {'lr': 4.703074271500624e-05, 'samples': 23161152, 'steps': 120630, 'loss/train': 1.4967823028564453} 08/31/2021 11:10:13 - INFO - __main__ - Step 120632: {'lr': 4.702764453226832e-05, 'samples': 23161344, 'steps': 120631, 'loss/train': 1.5727728605270386} 08/31/2021 11:10:14 - INFO - __main__ - Step 120633: {'lr': 4.702454644098661e-05, 'samples': 23161536, 'steps': 120632, 'loss/train': 1.0948628187179565} 08/31/2021 11:10:14 - INFO - __main__ - Step 120634: {'lr': 4.7021448441162516e-05, 'samples': 23161728, 'steps': 120633, 'loss/train': 1.4984524250030518} 08/31/2021 11:10:16 - INFO - __main__ - Step 120635: {'lr': 4.701835053279743e-05, 'samples': 23161920, 'steps': 120634, 'loss/train': 0.4695417284965515} 08/31/2021 11:10:16 - INFO - __main__ - Step 120636: {'lr': 4.7015252715892744e-05, 'samples': 23162112, 'steps': 120635, 'loss/train': 1.4363723993301392} 08/31/2021 11:10:16 - INFO - __main__ - Step 120637: {'lr': 4.701215499044983e-05, 'samples': 23162304, 'steps': 120636, 'loss/train': 0.1386132687330246} 08/31/2021 11:10:17 - INFO - __main__ - Step 120638: {'lr': 4.700905735647012e-05, 'samples': 23162496, 'steps': 120637, 'loss/train': 0.8297709226608276} 08/31/2021 11:10:17 - INFO - __main__ - Step 120639: {'lr': 4.700595981395508e-05, 'samples': 23162688, 'steps': 120638, 'loss/train': 1.6145901679992676} 08/31/2021 11:10:19 - INFO - __main__ - Step 120640: {'lr': 4.700286236290593e-05, 'samples': 23162880, 'steps': 120639, 'loss/train': 1.5625646114349365} 08/31/2021 11:10:19 - INFO - __main__ - Step 120641: {'lr': 4.699976500332417e-05, 'samples': 23163072, 'steps': 120640, 'loss/train': 1.4321149587631226} 08/31/2021 11:10:20 - INFO - __main__ - Step 120642: {'lr': 4.699666773521119e-05, 'samples': 23163264, 'steps': 120641, 'loss/train': 0.3280072510242462} 08/31/2021 11:10:20 - INFO - __main__ - Step 120643: {'lr': 4.699357055856837e-05, 'samples': 23163456, 'steps': 120642, 'loss/train': 0.06805171817541122} 08/31/2021 11:10:20 - INFO - __main__ - Step 120644: {'lr': 4.699047347339711e-05, 'samples': 23163648, 'steps': 120643, 'loss/train': 1.0417354106903076} 08/31/2021 11:10:22 - INFO - __main__ - Step 120645: {'lr': 4.6987376479698805e-05, 'samples': 23163840, 'steps': 120644, 'loss/train': 0.5246742963790894} 08/31/2021 11:10:22 - INFO - __main__ - Step 120646: {'lr': 4.698427957747486e-05, 'samples': 23164032, 'steps': 120645, 'loss/train': 1.523314356803894} 08/31/2021 11:10:23 - INFO - __main__ - Step 120647: {'lr': 4.6981182766726696e-05, 'samples': 23164224, 'steps': 120646, 'loss/train': 1.0432369709014893} 08/31/2021 11:10:23 - INFO - __main__ - Step 120648: {'lr': 4.697808604745563e-05, 'samples': 23164416, 'steps': 120647, 'loss/train': 1.237486481666565} 08/31/2021 11:10:23 - INFO - __main__ - Step 120649: {'lr': 4.697498941966313e-05, 'samples': 23164608, 'steps': 120648, 'loss/train': 1.1900869607925415} 08/31/2021 11:10:25 - INFO - __main__ - Step 120650: {'lr': 4.697189288335063e-05, 'samples': 23164800, 'steps': 120649, 'loss/train': 1.5362284183502197} 08/31/2021 11:10:25 - INFO - __main__ - Step 120651: {'lr': 4.69687964385194e-05, 'samples': 23164992, 'steps': 120650, 'loss/train': 1.728201985359192} 08/31/2021 11:10:26 - INFO - __main__ - Step 120652: {'lr': 4.69657000851709e-05, 'samples': 23165184, 'steps': 120651, 'loss/train': 1.8902580738067627} 08/31/2021 11:10:26 - INFO - __main__ - Step 120653: {'lr': 4.696260382330653e-05, 'samples': 23165376, 'steps': 120652, 'loss/train': 0.6086685657501221} 08/31/2021 11:10:26 - INFO - __main__ - Step 120654: {'lr': 4.6959507652927666e-05, 'samples': 23165568, 'steps': 120653, 'loss/train': 1.8936493396759033} 08/31/2021 11:10:29 - INFO - __main__ - Step 120655: {'lr': 4.695641157403571e-05, 'samples': 23165760, 'steps': 120654, 'loss/train': 1.7077500820159912} 08/31/2021 11:10:29 - INFO - __main__ - Step 120656: {'lr': 4.695331558663207e-05, 'samples': 23165952, 'steps': 120655, 'loss/train': 1.5405393838882446} 08/31/2021 11:10:30 - INFO - __main__ - Step 120657: {'lr': 4.695021969071811e-05, 'samples': 23166144, 'steps': 120656, 'loss/train': 1.7447504997253418} 08/31/2021 11:10:30 - INFO - __main__ - Step 120658: {'lr': 4.694712388629527e-05, 'samples': 23166336, 'steps': 120657, 'loss/train': 1.259424090385437} 08/31/2021 11:10:31 - INFO - __main__ - Step 120659: {'lr': 4.694402817336493e-05, 'samples': 23166528, 'steps': 120658, 'loss/train': 1.1545628309249878} 08/31/2021 11:10:31 - INFO - __main__ - Step 120660: {'lr': 4.694093255192847e-05, 'samples': 23166720, 'steps': 120659, 'loss/train': 0.6780267357826233} 08/31/2021 11:10:33 - INFO - __main__ - Step 120661: {'lr': 4.693783702198734e-05, 'samples': 23166912, 'steps': 120660, 'loss/train': 1.4088326692581177} 08/31/2021 11:10:33 - INFO - __main__ - Step 120662: {'lr': 4.6934741583542826e-05, 'samples': 23167104, 'steps': 120661, 'loss/train': 0.9829918742179871} 08/31/2021 11:10:33 - INFO - __main__ - Step 120663: {'lr': 4.69316462365964e-05, 'samples': 23167296, 'steps': 120662, 'loss/train': 1.2739559412002563} 08/31/2021 11:10:34 - INFO - __main__ - Step 120664: {'lr': 4.6928550981149454e-05, 'samples': 23167488, 'steps': 120663, 'loss/train': 0.8224299550056458} 08/31/2021 11:10:34 - INFO - __main__ - Step 120665: {'lr': 4.692545581720334e-05, 'samples': 23167680, 'steps': 120664, 'loss/train': 0.024869201704859734} 08/31/2021 11:10:34 - INFO - __main__ - Step 120666: {'lr': 4.69223607447595e-05, 'samples': 23167872, 'steps': 120665, 'loss/train': 1.179307460784912} 08/31/2021 11:10:36 - INFO - __main__ - Step 120667: {'lr': 4.69192657638193e-05, 'samples': 23168064, 'steps': 120666, 'loss/train': 1.4173672199249268} 08/31/2021 11:10:36 - INFO - __main__ - Step 120668: {'lr': 4.691617087438416e-05, 'samples': 23168256, 'steps': 120667, 'loss/train': 0.2219981849193573} 08/31/2021 11:10:37 - INFO - __main__ - Step 120669: {'lr': 4.691307607645543e-05, 'samples': 23168448, 'steps': 120668, 'loss/train': 1.1056785583496094} 08/31/2021 11:10:37 - INFO - __main__ - Step 120670: {'lr': 4.690998137003455e-05, 'samples': 23168640, 'steps': 120669, 'loss/train': 0.227966770529747} 08/31/2021 11:10:37 - INFO - __main__ - Step 120671: {'lr': 4.690688675512292e-05, 'samples': 23168832, 'steps': 120670, 'loss/train': 1.3958740234375} 08/31/2021 11:10:39 - INFO - __main__ - Step 120672: {'lr': 4.690379223172195e-05, 'samples': 23169024, 'steps': 120671, 'loss/train': 0.49096694588661194} 08/31/2021 11:10:39 - INFO - __main__ - Step 120673: {'lr': 4.690069779983294e-05, 'samples': 23169216, 'steps': 120672, 'loss/train': 1.0560091733932495} 08/31/2021 11:10:40 - INFO - __main__ - Step 120674: {'lr': 4.689760345945735e-05, 'samples': 23169408, 'steps': 120673, 'loss/train': 1.1284422874450684} 08/31/2021 11:10:40 - INFO - __main__ - Step 120675: {'lr': 4.689450921059654e-05, 'samples': 23169600, 'steps': 120674, 'loss/train': 1.1630449295043945} 08/31/2021 11:10:40 - INFO - __main__ - Step 120676: {'lr': 4.689141505325195e-05, 'samples': 23169792, 'steps': 120675, 'loss/train': 0.7657602429389954} 08/31/2021 11:10:42 - INFO - __main__ - Step 120677: {'lr': 4.6888320987424956e-05, 'samples': 23169984, 'steps': 120676, 'loss/train': 1.2999004125595093} 08/31/2021 11:10:42 - INFO - __main__ - Step 120678: {'lr': 4.688522701311695e-05, 'samples': 23170176, 'steps': 120677, 'loss/train': 1.2816874980926514} 08/31/2021 11:10:43 - INFO - __main__ - Step 120679: {'lr': 4.688213313032933e-05, 'samples': 23170368, 'steps': 120678, 'loss/train': 0.8850378394126892} 08/31/2021 11:10:43 - INFO - __main__ - Step 120680: {'lr': 4.6879039339063456e-05, 'samples': 23170560, 'steps': 120679, 'loss/train': 1.0011390447616577} 08/31/2021 11:10:43 - INFO - __main__ - Step 120681: {'lr': 4.6875945639320796e-05, 'samples': 23170752, 'steps': 120680, 'loss/train': 0.7881277799606323} 08/31/2021 11:10:45 - INFO - __main__ - Step 120682: {'lr': 4.687285203110267e-05, 'samples': 23170944, 'steps': 120681, 'loss/train': 1.455270767211914} 08/31/2021 11:10:45 - INFO - __main__ - Step 120683: {'lr': 4.6869758514410524e-05, 'samples': 23171136, 'steps': 120682, 'loss/train': 0.23522403836250305} 08/31/2021 11:10:46 - INFO - __main__ - Step 120684: {'lr': 4.6866665089245696e-05, 'samples': 23171328, 'steps': 120683, 'loss/train': 1.3131059408187866} 08/31/2021 11:10:46 - INFO - __main__ - Step 120685: {'lr': 4.686357175560971e-05, 'samples': 23171520, 'steps': 120684, 'loss/train': 0.8380608558654785} 08/31/2021 11:10:46 - INFO - __main__ - Step 120686: {'lr': 4.686047851350381e-05, 'samples': 23171712, 'steps': 120685, 'loss/train': 0.8000910878181458} 08/31/2021 11:10:48 - INFO - __main__ - Step 120687: {'lr': 4.685738536292941e-05, 'samples': 23171904, 'steps': 120686, 'loss/train': 0.9179897308349609} 08/31/2021 11:10:48 - INFO - __main__ - Step 120688: {'lr': 4.6854292303887965e-05, 'samples': 23172096, 'steps': 120687, 'loss/train': 0.05174819752573967} 08/31/2021 11:10:49 - INFO - __main__ - Step 120689: {'lr': 4.6851199336380826e-05, 'samples': 23172288, 'steps': 120688, 'loss/train': 1.0943137407302856} 08/31/2021 11:10:49 - INFO - __main__ - Step 120690: {'lr': 4.6848106460409406e-05, 'samples': 23172480, 'steps': 120689, 'loss/train': 0.5764657855033875} 08/31/2021 11:10:49 - INFO - __main__ - Step 120691: {'lr': 4.6845013675975076e-05, 'samples': 23172672, 'steps': 120690, 'loss/train': 1.5000706911087036} 08/31/2021 11:10:51 - INFO - __main__ - Step 120692: {'lr': 4.6841920983079264e-05, 'samples': 23172864, 'steps': 120691, 'loss/train': 0.962863564491272} 08/31/2021 11:10:52 - INFO - __main__ - Step 120693: {'lr': 4.6838828381723346e-05, 'samples': 23173056, 'steps': 120692, 'loss/train': 1.217673659324646} 08/31/2021 11:10:52 - INFO - __main__ - Step 120694: {'lr': 4.683573587190873e-05, 'samples': 23173248, 'steps': 120693, 'loss/train': 1.0858958959579468} 08/31/2021 11:10:52 - INFO - __main__ - Step 120695: {'lr': 4.6832643453636776e-05, 'samples': 23173440, 'steps': 120694, 'loss/train': 1.076496958732605} 08/31/2021 11:10:53 - INFO - __main__ - Step 120696: {'lr': 4.682955112690892e-05, 'samples': 23173632, 'steps': 120695, 'loss/train': 1.2338480949401855} 08/31/2021 11:10:53 - INFO - __main__ - Step 120697: {'lr': 4.6826458891726513e-05, 'samples': 23173824, 'steps': 120696, 'loss/train': 0.6129184365272522} 08/31/2021 11:10:54 - INFO - __main__ - Step 120698: {'lr': 4.6823366748090985e-05, 'samples': 23174016, 'steps': 120697, 'loss/train': 1.176540493965149} 08/31/2021 11:10:55 - INFO - __main__ - Step 120699: {'lr': 4.682027469600378e-05, 'samples': 23174208, 'steps': 120698, 'loss/train': 0.9133285880088806} 08/31/2021 11:10:55 - INFO - __main__ - Step 120700: {'lr': 4.6817182735466145e-05, 'samples': 23174400, 'steps': 120699, 'loss/train': 1.111924648284912} 08/31/2021 11:10:56 - INFO - __main__ - Step 120701: {'lr': 4.681409086647956e-05, 'samples': 23174592, 'steps': 120700, 'loss/train': 1.855027675628662} 08/31/2021 11:10:56 - INFO - __main__ - Step 120702: {'lr': 4.68109990890454e-05, 'samples': 23174784, 'steps': 120701, 'loss/train': 0.18375574052333832} 08/31/2021 11:10:57 - INFO - __main__ - Step 120703: {'lr': 4.6807907403165066e-05, 'samples': 23174976, 'steps': 120702, 'loss/train': 2.2224206924438477} 08/31/2021 11:10:58 - INFO - __main__ - Step 120704: {'lr': 4.6804815808839965e-05, 'samples': 23175168, 'steps': 120703, 'loss/train': 1.230431079864502} 08/31/2021 11:10:58 - INFO - __main__ - Step 120705: {'lr': 4.680172430607146e-05, 'samples': 23175360, 'steps': 120704, 'loss/train': 1.3587185144424438} 08/31/2021 11:10:59 - INFO - __main__ - Step 120706: {'lr': 4.6798632894861e-05, 'samples': 23175552, 'steps': 120705, 'loss/train': 1.5813548564910889} 08/31/2021 11:10:59 - INFO - __main__ - Step 120707: {'lr': 4.6795541575209905e-05, 'samples': 23175744, 'steps': 120706, 'loss/train': 1.3210866451263428} 08/31/2021 11:11:00 - INFO - __main__ - Step 120708: {'lr': 4.6792450347119624e-05, 'samples': 23175936, 'steps': 120707, 'loss/train': 1.4783726930618286} 08/31/2021 11:11:01 - INFO - __main__ - Step 120709: {'lr': 4.678935921059152e-05, 'samples': 23176128, 'steps': 120708, 'loss/train': 1.01898992061615} 08/31/2021 11:11:01 - INFO - __main__ - Step 120710: {'lr': 4.6786268165626975e-05, 'samples': 23176320, 'steps': 120709, 'loss/train': 1.3693649768829346} 08/31/2021 11:11:02 - INFO - __main__ - Step 120711: {'lr': 4.678317721222744e-05, 'samples': 23176512, 'steps': 120710, 'loss/train': 0.7232348918914795} 08/31/2021 11:11:02 - INFO - __main__ - Step 120712: {'lr': 4.6780086350394326e-05, 'samples': 23176704, 'steps': 120711, 'loss/train': 1.1540721654891968} 08/31/2021 11:11:04 - INFO - __main__ - Step 120713: {'lr': 4.677699558012888e-05, 'samples': 23176896, 'steps': 120712, 'loss/train': 0.6752030253410339} 08/31/2021 11:11:04 - INFO - __main__ - Step 120714: {'lr': 4.67739049014326e-05, 'samples': 23177088, 'steps': 120713, 'loss/train': 0.6861501932144165} 08/31/2021 11:11:05 - INFO - __main__ - Step 120715: {'lr': 4.677081431430685e-05, 'samples': 23177280, 'steps': 120714, 'loss/train': 1.5830851793289185} 08/31/2021 11:11:05 - INFO - __main__ - Step 120716: {'lr': 4.676772381875308e-05, 'samples': 23177472, 'steps': 120715, 'loss/train': 0.32866472005844116} 08/31/2021 11:11:05 - INFO - __main__ - Step 120717: {'lr': 4.676463341477258e-05, 'samples': 23177664, 'steps': 120716, 'loss/train': 1.118856430053711} 08/31/2021 11:11:07 - INFO - __main__ - Step 120718: {'lr': 4.6761543102366826e-05, 'samples': 23177856, 'steps': 120717, 'loss/train': 2.194401502609253} 08/31/2021 11:11:07 - INFO - __main__ - Step 120719: {'lr': 4.6758452881537185e-05, 'samples': 23178048, 'steps': 120718, 'loss/train': 1.0035138130187988} 08/31/2021 11:11:08 - INFO - __main__ - Step 120720: {'lr': 4.675536275228506e-05, 'samples': 23178240, 'steps': 120719, 'loss/train': 0.6399074792861938} 08/31/2021 11:11:08 - INFO - __main__ - Step 120721: {'lr': 4.675227271461183e-05, 'samples': 23178432, 'steps': 120720, 'loss/train': 1.3184689283370972} 08/31/2021 11:11:08 - INFO - __main__ - Step 120722: {'lr': 4.674918276851886e-05, 'samples': 23178624, 'steps': 120721, 'loss/train': 1.3448773622512817} 08/31/2021 11:11:09 - INFO - __main__ - Step 120723: {'lr': 4.674609291400758e-05, 'samples': 23178816, 'steps': 120722, 'loss/train': 1.3253474235534668} 08/31/2021 11:11:10 - INFO - __main__ - Step 120724: {'lr': 4.67430031510794e-05, 'samples': 23179008, 'steps': 120723, 'loss/train': 1.1861591339111328} 08/31/2021 11:11:11 - INFO - __main__ - Step 120725: {'lr': 4.673991347973566e-05, 'samples': 23179200, 'steps': 120724, 'loss/train': 1.3250583410263062} 08/31/2021 11:11:11 - INFO - __main__ - Step 120726: {'lr': 4.673682389997785e-05, 'samples': 23179392, 'steps': 120725, 'loss/train': 0.7298535108566284} 08/31/2021 11:11:12 - INFO - __main__ - Step 120727: {'lr': 4.6733734411807255e-05, 'samples': 23179584, 'steps': 120726, 'loss/train': 0.632771372795105} 08/31/2021 11:11:12 - INFO - __main__ - Step 120728: {'lr': 4.673064501522528e-05, 'samples': 23179776, 'steps': 120727, 'loss/train': 0.6720324158668518} 08/31/2021 11:11:14 - INFO - __main__ - Step 120729: {'lr': 4.6727555710233325e-05, 'samples': 23179968, 'steps': 120728, 'loss/train': 1.4381811618804932} 08/31/2021 11:11:14 - INFO - __main__ - Step 120730: {'lr': 4.6724466496832816e-05, 'samples': 23180160, 'steps': 120729, 'loss/train': 1.233305811882019} 08/31/2021 11:11:15 - INFO - __main__ - Step 120731: {'lr': 4.6721377375025105e-05, 'samples': 23180352, 'steps': 120730, 'loss/train': 1.2381579875946045} 08/31/2021 11:11:15 - INFO - __main__ - Step 120732: {'lr': 4.671828834481162e-05, 'samples': 23180544, 'steps': 120731, 'loss/train': 1.703934669494629} 08/31/2021 11:11:15 - INFO - __main__ - Step 120733: {'lr': 4.671519940619376e-05, 'samples': 23180736, 'steps': 120732, 'loss/train': 0.935703694820404} 08/31/2021 11:11:17 - INFO - __main__ - Step 120734: {'lr': 4.671211055917285e-05, 'samples': 23180928, 'steps': 120733, 'loss/train': 1.017045497894287} 08/31/2021 11:11:17 - INFO - __main__ - Step 120735: {'lr': 4.6709021803750364e-05, 'samples': 23181120, 'steps': 120734, 'loss/train': 0.3547610342502594} 08/31/2021 11:11:18 - INFO - __main__ - Step 120736: {'lr': 4.6705933139927634e-05, 'samples': 23181312, 'steps': 120735, 'loss/train': 1.1942564249038696} 08/31/2021 11:11:18 - INFO - __main__ - Step 120737: {'lr': 4.670284456770607e-05, 'samples': 23181504, 'steps': 120736, 'loss/train': 1.1391181945800781} 08/31/2021 11:11:18 - INFO - __main__ - Step 120738: {'lr': 4.669975608708707e-05, 'samples': 23181696, 'steps': 120737, 'loss/train': 0.7600499987602234} 08/31/2021 11:11:20 - INFO - __main__ - Step 120739: {'lr': 4.66966676980721e-05, 'samples': 23181888, 'steps': 120738, 'loss/train': 0.24367336928844452} 08/31/2021 11:11:20 - INFO - __main__ - Step 120740: {'lr': 4.6693579400662405e-05, 'samples': 23182080, 'steps': 120739, 'loss/train': 1.1681960821151733} 08/31/2021 11:11:21 - INFO - __main__ - Step 120741: {'lr': 4.669049119485943e-05, 'samples': 23182272, 'steps': 120740, 'loss/train': 0.5436940789222717} 08/31/2021 11:11:21 - INFO - __main__ - Step 120742: {'lr': 4.6687403080664606e-05, 'samples': 23182464, 'steps': 120741, 'loss/train': 1.1737438440322876} 08/31/2021 11:11:21 - INFO - __main__ - Step 120743: {'lr': 4.66843150580793e-05, 'samples': 23182656, 'steps': 120742, 'loss/train': 0.8408132195472717} 08/31/2021 11:11:23 - INFO - __main__ - Step 120744: {'lr': 4.668122712710487e-05, 'samples': 23182848, 'steps': 120743, 'loss/train': 1.3411071300506592} 08/31/2021 11:11:24 - INFO - __main__ - Step 120745: {'lr': 4.667813928774278e-05, 'samples': 23183040, 'steps': 120744, 'loss/train': 1.1411950588226318} 08/31/2021 11:11:24 - INFO - __main__ - Step 120746: {'lr': 4.6675051539994375e-05, 'samples': 23183232, 'steps': 120745, 'loss/train': 2.068387269973755} 08/31/2021 11:11:24 - INFO - __main__ - Step 120747: {'lr': 4.6671963883861054e-05, 'samples': 23183424, 'steps': 120746, 'loss/train': 0.4541206657886505} 08/31/2021 11:11:25 - INFO - __main__ - Step 120748: {'lr': 4.666887631934419e-05, 'samples': 23183616, 'steps': 120747, 'loss/train': 0.28479161858558655} 08/31/2021 11:11:26 - INFO - __main__ - Step 120749: {'lr': 4.6665788846445205e-05, 'samples': 23183808, 'steps': 120748, 'loss/train': 1.1254509687423706} 08/31/2021 11:11:27 - INFO - __main__ - Step 120750: {'lr': 4.666270146516549e-05, 'samples': 23184000, 'steps': 120749, 'loss/train': 1.0693978071212769} 08/31/2021 11:11:27 - INFO - __main__ - Step 120751: {'lr': 4.665961417550641e-05, 'samples': 23184192, 'steps': 120750, 'loss/train': 1.5344339609146118} 08/31/2021 11:11:27 - INFO - __main__ - Step 120752: {'lr': 4.665652697746944e-05, 'samples': 23184384, 'steps': 120751, 'loss/train': 1.3867672681808472} 08/31/2021 11:11:28 - INFO - __main__ - Step 120753: {'lr': 4.665343987105583e-05, 'samples': 23184576, 'steps': 120752, 'loss/train': 0.5279364585876465} 08/31/2021 11:11:28 - INFO - __main__ - Step 120754: {'lr': 4.6650352856267035e-05, 'samples': 23184768, 'steps': 120753, 'loss/train': 0.9807955622673035} 08/31/2021 11:11:30 - INFO - __main__ - Step 120755: {'lr': 4.664726593310448e-05, 'samples': 23184960, 'steps': 120754, 'loss/train': 0.8267794251441956} 08/31/2021 11:11:30 - INFO - __main__ - Step 120756: {'lr': 4.664417910156951e-05, 'samples': 23185152, 'steps': 120755, 'loss/train': 0.3909652829170227} 08/31/2021 11:11:30 - INFO - __main__ - Step 120757: {'lr': 4.664109236166353e-05, 'samples': 23185344, 'steps': 120756, 'loss/train': 1.2029008865356445} 08/31/2021 11:11:31 - INFO - __main__ - Step 120758: {'lr': 4.663800571338794e-05, 'samples': 23185536, 'steps': 120757, 'loss/train': 1.6624681949615479} 08/31/2021 11:11:31 - INFO - __main__ - Step 120759: {'lr': 4.6634919156744147e-05, 'samples': 23185728, 'steps': 120758, 'loss/train': 1.1958677768707275} 08/31/2021 11:11:33 - INFO - __main__ - Step 120760: {'lr': 4.663183269173352e-05, 'samples': 23185920, 'steps': 120759, 'loss/train': 1.326661229133606} 08/31/2021 11:11:33 - INFO - __main__ - Step 120761: {'lr': 4.6628746318357423e-05, 'samples': 23186112, 'steps': 120760, 'loss/train': 0.3552391529083252} 08/31/2021 11:11:34 - INFO - __main__ - Step 120762: {'lr': 4.662566003661728e-05, 'samples': 23186304, 'steps': 120761, 'loss/train': 0.8884392976760864} 08/31/2021 11:11:34 - INFO - __main__ - Step 120763: {'lr': 4.66225738465145e-05, 'samples': 23186496, 'steps': 120762, 'loss/train': 0.6739791631698608} 08/31/2021 11:11:34 - INFO - __main__ - Step 120764: {'lr': 4.661948774805041e-05, 'samples': 23186688, 'steps': 120763, 'loss/train': 0.6807407736778259} 08/31/2021 11:11:37 - INFO - __main__ - Step 120765: {'lr': 4.661640174122647e-05, 'samples': 23186880, 'steps': 120764, 'loss/train': 0.9141666889190674} 08/31/2021 11:11:37 - INFO - __main__ - Step 120766: {'lr': 4.661331582604411e-05, 'samples': 23187072, 'steps': 120765, 'loss/train': 2.0733489990234375} 08/31/2021 11:11:38 - INFO - __main__ - Step 120767: {'lr': 4.661023000250458e-05, 'samples': 23187264, 'steps': 120766, 'loss/train': 1.319089412689209} 08/31/2021 11:11:38 - INFO - __main__ - Step 120768: {'lr': 4.660714427060933e-05, 'samples': 23187456, 'steps': 120767, 'loss/train': 0.8594204187393188} 08/31/2021 11:11:38 - INFO - __main__ - Step 120769: {'lr': 4.6604058630359766e-05, 'samples': 23187648, 'steps': 120768, 'loss/train': 0.9084439277648926} 08/31/2021 11:11:40 - INFO - __main__ - Step 120770: {'lr': 4.660097308175728e-05, 'samples': 23187840, 'steps': 120769, 'loss/train': 0.9436168074607849} 08/31/2021 11:11:40 - INFO - __main__ - Step 120771: {'lr': 4.659788762480327e-05, 'samples': 23188032, 'steps': 120770, 'loss/train': 1.0351392030715942} 08/31/2021 11:11:41 - INFO - __main__ - Step 120772: {'lr': 4.659480225949911e-05, 'samples': 23188224, 'steps': 120771, 'loss/train': 1.0799914598464966} 08/31/2021 11:11:41 - INFO - __main__ - Step 120773: {'lr': 4.6591716985846164e-05, 'samples': 23188416, 'steps': 120772, 'loss/train': 1.3200074434280396} 08/31/2021 11:11:41 - INFO - __main__ - Step 120774: {'lr': 4.658863180384587e-05, 'samples': 23188608, 'steps': 120773, 'loss/train': 1.086559534072876} 08/31/2021 11:11:43 - INFO - __main__ - Step 120775: {'lr': 4.65855467134996e-05, 'samples': 23188800, 'steps': 120774, 'loss/train': 0.027191467583179474} 08/31/2021 11:11:44 - INFO - __main__ - Step 120776: {'lr': 4.658246171480876e-05, 'samples': 23188992, 'steps': 120775, 'loss/train': 1.1816599369049072} 08/31/2021 11:11:44 - INFO - __main__ - Step 120777: {'lr': 4.657937680777469e-05, 'samples': 23189184, 'steps': 120776, 'loss/train': 1.6548750400543213} 08/31/2021 11:11:44 - INFO - __main__ - Step 120778: {'lr': 4.657629199239885e-05, 'samples': 23189376, 'steps': 120777, 'loss/train': 1.4439496994018555} 08/31/2021 11:11:45 - INFO - __main__ - Step 120779: {'lr': 4.657320726868264e-05, 'samples': 23189568, 'steps': 120778, 'loss/train': 1.6214333772659302} 08/31/2021 11:11:45 - INFO - __main__ - Step 120780: {'lr': 4.6570122636627324e-05, 'samples': 23189760, 'steps': 120779, 'loss/train': 1.6097596883773804} 08/31/2021 11:11:46 - INFO - __main__ - Step 120781: {'lr': 4.656703809623439e-05, 'samples': 23189952, 'steps': 120780, 'loss/train': 1.1118971109390259} 08/31/2021 11:11:47 - INFO - __main__ - Step 120782: {'lr': 4.656395364750521e-05, 'samples': 23190144, 'steps': 120781, 'loss/train': 1.2663570642471313} 08/31/2021 11:11:47 - INFO - __main__ - Step 120783: {'lr': 4.656086929044118e-05, 'samples': 23190336, 'steps': 120782, 'loss/train': 1.6206724643707275} 08/31/2021 11:11:48 - INFO - __main__ - Step 120784: {'lr': 4.6557785025043656e-05, 'samples': 23190528, 'steps': 120783, 'loss/train': 0.8583841323852539} 08/31/2021 11:11:48 - INFO - __main__ - Step 120785: {'lr': 4.655470085131408e-05, 'samples': 23190720, 'steps': 120784, 'loss/train': 0.841917097568512} 08/31/2021 11:11:50 - INFO - __main__ - Step 120786: {'lr': 4.6551616769253815e-05, 'samples': 23190912, 'steps': 120785, 'loss/train': 1.2871145009994507} 08/31/2021 11:11:50 - INFO - __main__ - Step 120787: {'lr': 4.654853277886423e-05, 'samples': 23191104, 'steps': 120786, 'loss/train': 1.1199644804000854} 08/31/2021 11:11:50 - INFO - __main__ - Step 120788: {'lr': 4.654544888014675e-05, 'samples': 23191296, 'steps': 120787, 'loss/train': 1.4512892961502075} 08/31/2021 11:11:51 - INFO - __main__ - Step 120789: {'lr': 4.6542365073102746e-05, 'samples': 23191488, 'steps': 120788, 'loss/train': 1.4676902294158936} 08/31/2021 11:11:51 - INFO - __main__ - Step 120790: {'lr': 4.6539281357733637e-05, 'samples': 23191680, 'steps': 120789, 'loss/train': 0.6674227118492126} 08/31/2021 11:11:53 - INFO - __main__ - Step 120791: {'lr': 4.653619773404077e-05, 'samples': 23191872, 'steps': 120790, 'loss/train': 0.8576996922492981} 08/31/2021 11:11:53 - INFO - __main__ - Step 120792: {'lr': 4.653311420202555e-05, 'samples': 23192064, 'steps': 120791, 'loss/train': 1.1159216165542603} 08/31/2021 11:11:54 - INFO - __main__ - Step 120793: {'lr': 4.653003076168944e-05, 'samples': 23192256, 'steps': 120792, 'loss/train': 1.2794996500015259} 08/31/2021 11:11:54 - INFO - __main__ - Step 120794: {'lr': 4.652694741303371e-05, 'samples': 23192448, 'steps': 120793, 'loss/train': 0.8942981958389282} 08/31/2021 11:11:54 - INFO - __main__ - Step 120795: {'lr': 4.652386415605975e-05, 'samples': 23192640, 'steps': 120794, 'loss/train': 1.1326704025268555} 08/31/2021 11:11:55 - INFO - __main__ - Step 120796: {'lr': 4.652078099076903e-05, 'samples': 23192832, 'steps': 120795, 'loss/train': 1.3246595859527588} 08/31/2021 11:11:56 - INFO - __main__ - Step 120797: {'lr': 4.65176979171629e-05, 'samples': 23193024, 'steps': 120796, 'loss/train': 1.249503493309021} 08/31/2021 11:11:57 - INFO - __main__ - Step 120798: {'lr': 4.651461493524276e-05, 'samples': 23193216, 'steps': 120797, 'loss/train': 0.9117067456245422} 08/31/2021 11:11:57 - INFO - __main__ - Step 120799: {'lr': 4.6511532045009994e-05, 'samples': 23193408, 'steps': 120798, 'loss/train': 1.1423951387405396} 08/31/2021 11:11:57 - INFO - __main__ - Step 120800: {'lr': 4.650844924646599e-05, 'samples': 23193600, 'steps': 120799, 'loss/train': 0.8964360356330872} 08/31/2021 11:11:58 - INFO - __main__ - Step 120801: {'lr': 4.6505366539612155e-05, 'samples': 23193792, 'steps': 120800, 'loss/train': 0.8719547986984253} 08/31/2021 11:11:59 - INFO - __main__ - Step 120802: {'lr': 4.650228392444983e-05, 'samples': 23193984, 'steps': 120801, 'loss/train': 0.0942305251955986} 08/31/2021 11:12:00 - INFO - __main__ - Step 120803: {'lr': 4.6499201400980464e-05, 'samples': 23194176, 'steps': 120802, 'loss/train': 0.6269677877426147} 08/31/2021 11:12:00 - INFO - __main__ - Step 120804: {'lr': 4.649611896920539e-05, 'samples': 23194368, 'steps': 120803, 'loss/train': 0.803970456123352} 08/31/2021 11:12:00 - INFO - __main__ - Step 120805: {'lr': 4.6493036629126046e-05, 'samples': 23194560, 'steps': 120804, 'loss/train': 1.0260564088821411} 08/31/2021 11:12:01 - INFO - __main__ - Step 120806: {'lr': 4.6489954380743856e-05, 'samples': 23194752, 'steps': 120805, 'loss/train': 0.6915170550346375} 08/31/2021 11:12:02 - INFO - __main__ - Step 120807: {'lr': 4.648687222406009e-05, 'samples': 23194944, 'steps': 120806, 'loss/train': 1.4910486936569214} 08/31/2021 11:12:03 - INFO - __main__ - Step 120808: {'lr': 4.648379015907619e-05, 'samples': 23195136, 'steps': 120807, 'loss/train': 1.3661694526672363} 08/31/2021 11:12:03 - INFO - __main__ - Step 120809: {'lr': 4.648070818579356e-05, 'samples': 23195328, 'steps': 120808, 'loss/train': 1.3560657501220703} 08/31/2021 11:12:03 - INFO - __main__ - Step 120810: {'lr': 4.647762630421359e-05, 'samples': 23195520, 'steps': 120809, 'loss/train': 0.9878666400909424} 08/31/2021 11:12:04 - INFO - __main__ - Step 120811: {'lr': 4.647454451433766e-05, 'samples': 23195712, 'steps': 120810, 'loss/train': 0.90323406457901} 08/31/2021 11:12:05 - INFO - __main__ - Step 120812: {'lr': 4.6471462816167155e-05, 'samples': 23195904, 'steps': 120811, 'loss/train': 1.0030356645584106} 08/31/2021 11:12:06 - INFO - __main__ - Step 120813: {'lr': 4.6468381209703455e-05, 'samples': 23196096, 'steps': 120812, 'loss/train': 0.5757161974906921} 08/31/2021 11:12:06 - INFO - __main__ - Step 120814: {'lr': 4.646529969494798e-05, 'samples': 23196288, 'steps': 120813, 'loss/train': 0.3859202265739441} 08/31/2021 11:12:06 - INFO - __main__ - Step 120815: {'lr': 4.646221827190208e-05, 'samples': 23196480, 'steps': 120814, 'loss/train': 1.612982988357544} 08/31/2021 11:12:07 - INFO - __main__ - Step 120816: {'lr': 4.645913694056719e-05, 'samples': 23196672, 'steps': 120815, 'loss/train': 0.6370710134506226} 08/31/2021 11:12:08 - INFO - __main__ - Step 120817: {'lr': 4.645605570094466e-05, 'samples': 23196864, 'steps': 120816, 'loss/train': 1.3730440139770508} 08/31/2021 11:12:09 - INFO - __main__ - Step 120818: {'lr': 4.64529745530359e-05, 'samples': 23197056, 'steps': 120817, 'loss/train': 1.1233203411102295} 08/31/2021 11:12:09 - INFO - __main__ - Step 120819: {'lr': 4.6449893496842284e-05, 'samples': 23197248, 'steps': 120818, 'loss/train': 1.0592982769012451} 08/31/2021 11:12:09 - INFO - __main__ - Step 120820: {'lr': 4.6446812532365266e-05, 'samples': 23197440, 'steps': 120819, 'loss/train': 0.8228539228439331} 08/31/2021 11:12:10 - INFO - __main__ - Step 120821: {'lr': 4.6443731659606107e-05, 'samples': 23197632, 'steps': 120820, 'loss/train': 0.024598870426416397} 08/31/2021 11:12:12 - INFO - __main__ - Step 120822: {'lr': 4.644065087856625e-05, 'samples': 23197824, 'steps': 120821, 'loss/train': 1.0884617567062378} 08/31/2021 11:12:12 - INFO - __main__ - Step 120823: {'lr': 4.6437570189247105e-05, 'samples': 23198016, 'steps': 120822, 'loss/train': 1.6763153076171875} 08/31/2021 11:12:13 - INFO - __main__ - Step 120824: {'lr': 4.643448959165006e-05, 'samples': 23198208, 'steps': 120823, 'loss/train': 0.230755016207695} 08/31/2021 11:12:13 - INFO - __main__ - Step 120825: {'lr': 4.6431409085776474e-05, 'samples': 23198400, 'steps': 120824, 'loss/train': 1.0577973127365112} 08/31/2021 11:12:13 - INFO - __main__ - Step 120826: {'lr': 4.642832867162777e-05, 'samples': 23198592, 'steps': 120825, 'loss/train': 1.3123023509979248} 08/31/2021 11:12:14 - INFO - __main__ - Step 120827: {'lr': 4.6425248349205306e-05, 'samples': 23198784, 'steps': 120826, 'loss/train': 1.0090031623840332} 08/31/2021 11:12:15 - INFO - __main__ - Step 120828: {'lr': 4.64221681185105e-05, 'samples': 23198976, 'steps': 120827, 'loss/train': 1.4106919765472412} 08/31/2021 11:12:16 - INFO - __main__ - Step 120829: {'lr': 4.641908797954472e-05, 'samples': 23199168, 'steps': 120828, 'loss/train': 5.689716815948486} 08/31/2021 11:12:16 - INFO - __main__ - Step 120830: {'lr': 4.641600793230935e-05, 'samples': 23199360, 'steps': 120829, 'loss/train': 0.6800164580345154} 08/31/2021 11:12:16 - INFO - __main__ - Step 120831: {'lr': 4.64129279768058e-05, 'samples': 23199552, 'steps': 120830, 'loss/train': 1.000339150428772} 08/31/2021 11:12:17 - INFO - __main__ - Step 120832: {'lr': 4.640984811303542e-05, 'samples': 23199744, 'steps': 120831, 'loss/train': 1.391573429107666} 08/31/2021 11:12:19 - INFO - __main__ - Step 120833: {'lr': 4.6406768340999686e-05, 'samples': 23199936, 'steps': 120832, 'loss/train': 1.1633801460266113} 08/31/2021 11:12:20 - INFO - __main__ - Step 120834: {'lr': 4.6403688660699886e-05, 'samples': 23200128, 'steps': 120833, 'loss/train': 1.3777265548706055} 08/31/2021 11:12:20 - INFO - __main__ - Step 120835: {'lr': 4.6400609072137414e-05, 'samples': 23200320, 'steps': 120834, 'loss/train': 5.778774261474609} 08/31/2021 11:12:20 - INFO - __main__ - Step 120836: {'lr': 4.639752957531368e-05, 'samples': 23200512, 'steps': 120835, 'loss/train': 5.794859409332275} 08/31/2021 11:12:21 - INFO - __main__ - Step 120837: {'lr': 4.639445017023011e-05, 'samples': 23200704, 'steps': 120836, 'loss/train': 5.768808841705322} 08/31/2021 11:12:21 - INFO - __main__ - Step 120838: {'lr': 4.639137085688802e-05, 'samples': 23200896, 'steps': 120837, 'loss/train': 1.1250897645950317} 08/31/2021 11:12:21 - INFO - __main__ - Step 120839: {'lr': 4.638829163528888e-05, 'samples': 23201088, 'steps': 120838, 'loss/train': 0.7575952410697937} 08/31/2021 11:12:22 - INFO - __main__ - Step 120840: {'lr': 4.638521250543401e-05, 'samples': 23201280, 'steps': 120839, 'loss/train': 1.120179533958435} 08/31/2021 11:12:23 - INFO - __main__ - Step 120841: {'lr': 4.638213346732481e-05, 'samples': 23201472, 'steps': 120840, 'loss/train': 0.6653966307640076} 08/31/2021 11:12:24 - INFO - __main__ - Step 120842: {'lr': 4.637905452096269e-05, 'samples': 23201664, 'steps': 120841, 'loss/train': 0.741023600101471} 08/31/2021 11:12:24 - INFO - __main__ - Step 120843: {'lr': 4.6375975666349045e-05, 'samples': 23201856, 'steps': 120842, 'loss/train': 0.9531533122062683} 08/31/2021 11:12:25 - INFO - __main__ - Step 120844: {'lr': 4.63728969034852e-05, 'samples': 23202048, 'steps': 120843, 'loss/train': 1.0954488515853882} 08/31/2021 11:12:25 - INFO - __main__ - Step 120845: {'lr': 4.636981823237263e-05, 'samples': 23202240, 'steps': 120844, 'loss/train': 0.9506115317344666} 08/31/2021 11:12:25 - INFO - __main__ - Step 120846: {'lr': 4.636673965301266e-05, 'samples': 23202432, 'steps': 120845, 'loss/train': 1.6439440250396729} 08/31/2021 11:12:27 - INFO - __main__ - Step 120847: {'lr': 4.636366116540674e-05, 'samples': 23202624, 'steps': 120846, 'loss/train': 1.457498550415039} 08/31/2021 11:12:27 - INFO - __main__ - Step 120848: {'lr': 4.636058276955618e-05, 'samples': 23202816, 'steps': 120847, 'loss/train': 1.3477360010147095} 08/31/2021 11:12:28 - INFO - __main__ - Step 120849: {'lr': 4.635750446546239e-05, 'samples': 23203008, 'steps': 120848, 'loss/train': 1.3913072347640991} 08/31/2021 11:12:28 - INFO - __main__ - Step 120850: {'lr': 4.6354426253126746e-05, 'samples': 23203200, 'steps': 120849, 'loss/train': 1.065366268157959} 08/31/2021 11:12:28 - INFO - __main__ - Step 120851: {'lr': 4.635134813255068e-05, 'samples': 23203392, 'steps': 120850, 'loss/train': 0.9096966981887817} 08/31/2021 11:12:30 - INFO - __main__ - Step 120852: {'lr': 4.6348270103735545e-05, 'samples': 23203584, 'steps': 120851, 'loss/train': 1.269809603691101} 08/31/2021 11:12:30 - INFO - __main__ - Step 120853: {'lr': 4.634519216668273e-05, 'samples': 23203776, 'steps': 120852, 'loss/train': 0.4862726926803589} 08/31/2021 11:12:31 - INFO - __main__ - Step 120854: {'lr': 4.6342114321393624e-05, 'samples': 23203968, 'steps': 120853, 'loss/train': 1.2190325260162354} 08/31/2021 11:12:31 - INFO - __main__ - Step 120855: {'lr': 4.633903656786964e-05, 'samples': 23204160, 'steps': 120854, 'loss/train': 0.8116087317466736} 08/31/2021 11:12:31 - INFO - __main__ - Step 120856: {'lr': 4.6335958906112143e-05, 'samples': 23204352, 'steps': 120855, 'loss/train': 1.0771194696426392} 08/31/2021 11:12:33 - INFO - __main__ - Step 120857: {'lr': 4.6332881336122514e-05, 'samples': 23204544, 'steps': 120856, 'loss/train': 0.3646543025970459} 08/31/2021 11:12:33 - INFO - __main__ - Step 120858: {'lr': 4.632980385790214e-05, 'samples': 23204736, 'steps': 120857, 'loss/train': 0.613797664642334} 08/31/2021 11:12:33 - INFO - __main__ - Step 120859: {'lr': 4.632672647145239e-05, 'samples': 23204928, 'steps': 120858, 'loss/train': 1.224859356880188} 08/31/2021 11:12:34 - INFO - __main__ - Step 120860: {'lr': 4.6323649176774786e-05, 'samples': 23205120, 'steps': 120859, 'loss/train': 1.3175145387649536} 08/31/2021 11:12:34 - INFO - __main__ - Step 120861: {'lr': 4.632057197387052e-05, 'samples': 23205312, 'steps': 120860, 'loss/train': 1.7094948291778564} 08/31/2021 11:12:36 - INFO - __main__ - Step 120862: {'lr': 4.631749486274103e-05, 'samples': 23205504, 'steps': 120861, 'loss/train': 0.746000349521637} 08/31/2021 11:12:36 - INFO - __main__ - Step 120863: {'lr': 4.6314417843387776e-05, 'samples': 23205696, 'steps': 120862, 'loss/train': 1.1912872791290283} 08/31/2021 11:12:37 - INFO - __main__ - Step 120864: {'lr': 4.63113409158121e-05, 'samples': 23205888, 'steps': 120863, 'loss/train': 0.7831672430038452} 08/31/2021 11:12:37 - INFO - __main__ - Step 120865: {'lr': 4.6308264080015374e-05, 'samples': 23206080, 'steps': 120864, 'loss/train': 0.7442993521690369} 08/31/2021 11:12:37 - INFO - __main__ - Step 120866: {'lr': 4.6305187335999006e-05, 'samples': 23206272, 'steps': 120865, 'loss/train': 0.976012647151947} 08/31/2021 11:12:39 - INFO - __main__ - Step 120867: {'lr': 4.630211068376436e-05, 'samples': 23206464, 'steps': 120866, 'loss/train': 0.9808924198150635} 08/31/2021 11:12:39 - INFO - __main__ - Step 120868: {'lr': 4.629903412331288e-05, 'samples': 23206656, 'steps': 120867, 'loss/train': 1.0452136993408203} 08/31/2021 11:12:40 - INFO - __main__ - Step 120869: {'lr': 4.629595765464587e-05, 'samples': 23206848, 'steps': 120868, 'loss/train': 0.8038646578788757} 08/31/2021 11:12:40 - INFO - __main__ - Step 120870: {'lr': 4.629288127776479e-05, 'samples': 23207040, 'steps': 120869, 'loss/train': 0.5058509707450867} 08/31/2021 11:12:40 - INFO - __main__ - Step 120871: {'lr': 4.628980499267096e-05, 'samples': 23207232, 'steps': 120870, 'loss/train': 1.4707750082015991} 08/31/2021 11:12:42 - INFO - __main__ - Step 120872: {'lr': 4.6286728799365824e-05, 'samples': 23207424, 'steps': 120871, 'loss/train': 0.9633175134658813} 08/31/2021 11:12:42 - INFO - __main__ - Step 120873: {'lr': 4.6283652697850815e-05, 'samples': 23207616, 'steps': 120872, 'loss/train': 0.4535504877567291} 08/31/2021 11:12:43 - INFO - __main__ - Step 120874: {'lr': 4.628057668812719e-05, 'samples': 23207808, 'steps': 120873, 'loss/train': 0.7289182543754578} 08/31/2021 11:12:43 - INFO - __main__ - Step 120875: {'lr': 4.627750077019635e-05, 'samples': 23208000, 'steps': 120874, 'loss/train': 1.1058908700942993} 08/31/2021 11:12:43 - INFO - __main__ - Step 120876: {'lr': 4.6274424944059756e-05, 'samples': 23208192, 'steps': 120875, 'loss/train': 1.1565275192260742} 08/31/2021 11:12:44 - INFO - __main__ - Step 120877: {'lr': 4.6271349209718764e-05, 'samples': 23208384, 'steps': 120876, 'loss/train': 1.1930105686187744} 08/31/2021 11:12:46 - INFO - __main__ - Step 120878: {'lr': 4.626827356717475e-05, 'samples': 23208576, 'steps': 120877, 'loss/train': 1.2676109075546265} 08/31/2021 11:12:46 - INFO - __main__ - Step 120879: {'lr': 4.626519801642912e-05, 'samples': 23208768, 'steps': 120878, 'loss/train': 0.7923041582107544} 08/31/2021 11:12:47 - INFO - __main__ - Step 120880: {'lr': 4.6262122557483244e-05, 'samples': 23208960, 'steps': 120879, 'loss/train': 1.0053272247314453} 08/31/2021 11:12:47 - INFO - __main__ - Step 120881: {'lr': 4.6259047190338495e-05, 'samples': 23209152, 'steps': 120880, 'loss/train': 1.0199449062347412} 08/31/2021 11:12:48 - INFO - __main__ - Step 120882: {'lr': 4.625597191499631e-05, 'samples': 23209344, 'steps': 120881, 'loss/train': 0.4302268624305725} 08/31/2021 11:12:49 - INFO - __main__ - Step 120883: {'lr': 4.625289673145802e-05, 'samples': 23209536, 'steps': 120882, 'loss/train': 1.1132105588912964} 08/31/2021 11:12:50 - INFO - __main__ - Step 120884: {'lr': 4.624982163972502e-05, 'samples': 23209728, 'steps': 120883, 'loss/train': 1.1172956228256226} 08/31/2021 11:12:50 - INFO - __main__ - Step 120885: {'lr': 4.624674663979872e-05, 'samples': 23209920, 'steps': 120884, 'loss/train': 0.9712947607040405} 08/31/2021 11:12:50 - INFO - __main__ - Step 120886: {'lr': 4.624367173168054e-05, 'samples': 23210112, 'steps': 120885, 'loss/train': 1.2993764877319336} 08/31/2021 11:12:51 - INFO - __main__ - Step 120887: {'lr': 4.624059691537178e-05, 'samples': 23210304, 'steps': 120886, 'loss/train': 1.144452691078186} 08/31/2021 11:12:52 - INFO - __main__ - Step 120888: {'lr': 4.6237522190873846e-05, 'samples': 23210496, 'steps': 120887, 'loss/train': 0.8173102736473083} 08/31/2021 11:12:53 - INFO - __main__ - Step 120889: {'lr': 4.623444755818812e-05, 'samples': 23210688, 'steps': 120888, 'loss/train': 1.3222028017044067} 08/31/2021 11:12:53 - INFO - __main__ - Step 120890: {'lr': 4.623137301731603e-05, 'samples': 23210880, 'steps': 120889, 'loss/train': 1.2630610466003418} 08/31/2021 11:12:54 - INFO - __main__ - Step 120891: {'lr': 4.622829856825894e-05, 'samples': 23211072, 'steps': 120890, 'loss/train': 1.351913332939148} 08/31/2021 11:12:54 - INFO - __main__ - Step 120892: {'lr': 4.622522421101824e-05, 'samples': 23211264, 'steps': 120891, 'loss/train': 1.4032188653945923} 08/31/2021 11:12:56 - INFO - __main__ - Step 120893: {'lr': 4.6222149945595314e-05, 'samples': 23211456, 'steps': 120892, 'loss/train': 1.221656322479248} 08/31/2021 11:12:56 - INFO - __main__ - Step 120894: {'lr': 4.6219075771991525e-05, 'samples': 23211648, 'steps': 120893, 'loss/train': 1.3044832944869995} 08/31/2021 11:12:56 - INFO - __main__ - Step 120895: {'lr': 4.621600169020829e-05, 'samples': 23211840, 'steps': 120894, 'loss/train': 0.9275660514831543} 08/31/2021 11:12:57 - INFO - __main__ - Step 120896: {'lr': 4.621292770024696e-05, 'samples': 23212032, 'steps': 120895, 'loss/train': 0.7336114645004272} 08/31/2021 11:12:57 - INFO - __main__ - Step 120897: {'lr': 4.6209853802109014e-05, 'samples': 23212224, 'steps': 120896, 'loss/train': 0.47674426436424255} 08/31/2021 11:12:59 - INFO - __main__ - Step 120898: {'lr': 4.62067799957957e-05, 'samples': 23212416, 'steps': 120897, 'loss/train': 0.7956773042678833} 08/31/2021 11:12:59 - INFO - __main__ - Step 120899: {'lr': 4.620370628130846e-05, 'samples': 23212608, 'steps': 120898, 'loss/train': 1.1916922330856323} 08/31/2021 11:12:59 - INFO - __main__ - Step 120900: {'lr': 4.6200632658648714e-05, 'samples': 23212800, 'steps': 120899, 'loss/train': 1.1971765756607056} 08/31/2021 11:13:00 - INFO - __main__ - Step 120901: {'lr': 4.619755912781779e-05, 'samples': 23212992, 'steps': 120900, 'loss/train': 0.7416834831237793} 08/31/2021 11:13:00 - INFO - __main__ - Step 120902: {'lr': 4.61944856888171e-05, 'samples': 23213184, 'steps': 120901, 'loss/train': 0.424254834651947} 08/31/2021 11:13:02 - INFO - __main__ - Step 120903: {'lr': 4.6191412341648035e-05, 'samples': 23213376, 'steps': 120902, 'loss/train': 1.3154258728027344} 08/31/2021 11:13:02 - INFO - __main__ - Step 120904: {'lr': 4.618833908631198e-05, 'samples': 23213568, 'steps': 120903, 'loss/train': 0.9499985575675964} 08/31/2021 11:13:02 - INFO - __main__ - Step 120905: {'lr': 4.6185265922810335e-05, 'samples': 23213760, 'steps': 120904, 'loss/train': 1.3368031978607178} 08/31/2021 11:13:03 - INFO - __main__ - Step 120906: {'lr': 4.6182192851144416e-05, 'samples': 23213952, 'steps': 120905, 'loss/train': 0.3643542230129242} 08/31/2021 11:13:03 - INFO - __main__ - Step 120907: {'lr': 4.617911987131568e-05, 'samples': 23214144, 'steps': 120906, 'loss/train': 1.1666688919067383} 08/31/2021 11:13:05 - INFO - __main__ - Step 120908: {'lr': 4.617604698332556e-05, 'samples': 23214336, 'steps': 120907, 'loss/train': 0.5102617740631104} 08/31/2021 11:13:05 - INFO - __main__ - Step 120909: {'lr': 4.617297418717531e-05, 'samples': 23214528, 'steps': 120908, 'loss/train': 0.5012245178222656} 08/31/2021 11:13:05 - INFO - __main__ - Step 120910: {'lr': 4.616990148286635e-05, 'samples': 23214720, 'steps': 120909, 'loss/train': 1.5118827819824219} 08/31/2021 11:13:06 - INFO - __main__ - Step 120911: {'lr': 4.616682887040008e-05, 'samples': 23214912, 'steps': 120910, 'loss/train': 1.065909504890442} 08/31/2021 11:13:06 - INFO - __main__ - Step 120912: {'lr': 4.616375634977793e-05, 'samples': 23215104, 'steps': 120911, 'loss/train': 0.751481294631958} 08/31/2021 11:13:06 - INFO - __main__ - Step 120913: {'lr': 4.6160683921001204e-05, 'samples': 23215296, 'steps': 120912, 'loss/train': 0.8867625594139099} 08/31/2021 11:13:08 - INFO - __main__ - Step 120914: {'lr': 4.615761158407136e-05, 'samples': 23215488, 'steps': 120913, 'loss/train': 1.779058814048767} 08/31/2021 11:13:09 - INFO - __main__ - Step 120915: {'lr': 4.615453933898975e-05, 'samples': 23215680, 'steps': 120914, 'loss/train': 1.4216716289520264} 08/31/2021 11:13:09 - INFO - __main__ - Step 120916: {'lr': 4.6151467185757744e-05, 'samples': 23215872, 'steps': 120915, 'loss/train': 1.7642614841461182} 08/31/2021 11:13:09 - INFO - __main__ - Step 120917: {'lr': 4.614839512437674e-05, 'samples': 23216064, 'steps': 120916, 'loss/train': 1.0374997854232788} 08/31/2021 11:13:10 - INFO - __main__ - Step 120918: {'lr': 4.614532315484812e-05, 'samples': 23216256, 'steps': 120917, 'loss/train': 1.9275281429290771} 08/31/2021 11:13:11 - INFO - __main__ - Step 120919: {'lr': 4.614225127717334e-05, 'samples': 23216448, 'steps': 120918, 'loss/train': 1.221575379371643} 08/31/2021 11:13:11 - INFO - __main__ - Step 120920: {'lr': 4.613917949135366e-05, 'samples': 23216640, 'steps': 120919, 'loss/train': 1.3690307140350342} 08/31/2021 11:13:12 - INFO - __main__ - Step 120921: {'lr': 4.613610779739053e-05, 'samples': 23216832, 'steps': 120920, 'loss/train': 0.9809329509735107} 08/31/2021 11:13:12 - INFO - __main__ - Step 120922: {'lr': 4.613303619528531e-05, 'samples': 23217024, 'steps': 120921, 'loss/train': 0.8625116944313049} 08/31/2021 11:13:13 - INFO - __main__ - Step 120923: {'lr': 4.612996468503938e-05, 'samples': 23217216, 'steps': 120922, 'loss/train': 0.929035484790802} 08/31/2021 11:13:14 - INFO - __main__ - Step 120924: {'lr': 4.612689326665417e-05, 'samples': 23217408, 'steps': 120923, 'loss/train': 1.4055458307266235} 08/31/2021 11:13:15 - INFO - __main__ - Step 120925: {'lr': 4.6123821940131014e-05, 'samples': 23217600, 'steps': 120924, 'loss/train': 1.3114731311798096} 08/31/2021 11:13:15 - INFO - __main__ - Step 120926: {'lr': 4.6120750705471337e-05, 'samples': 23217792, 'steps': 120925, 'loss/train': 0.7887612581253052} 08/31/2021 11:13:15 - INFO - __main__ - Step 120927: {'lr': 4.611767956267648e-05, 'samples': 23217984, 'steps': 120926, 'loss/train': 1.470950722694397} 08/31/2021 11:13:16 - INFO - __main__ - Step 120928: {'lr': 4.6114608511747893e-05, 'samples': 23218176, 'steps': 120927, 'loss/train': 0.28594428300857544} 08/31/2021 11:13:16 - INFO - __main__ - Step 120929: {'lr': 4.611153755268688e-05, 'samples': 23218368, 'steps': 120928, 'loss/train': 2.044262170791626} 08/31/2021 11:13:19 - INFO - __main__ - Step 120930: {'lr': 4.610846668549493e-05, 'samples': 23218560, 'steps': 120929, 'loss/train': 1.3738692998886108} 08/31/2021 11:13:19 - INFO - __main__ - Step 120931: {'lr': 4.610539591017332e-05, 'samples': 23218752, 'steps': 120930, 'loss/train': 0.9135280251502991} 08/31/2021 11:13:19 - INFO - __main__ - Step 120932: {'lr': 4.610232522672345e-05, 'samples': 23218944, 'steps': 120931, 'loss/train': 1.8211748600006104} 08/31/2021 11:13:20 - INFO - __main__ - Step 120933: {'lr': 4.609925463514672e-05, 'samples': 23219136, 'steps': 120932, 'loss/train': 0.7123565077781677} 08/31/2021 11:13:20 - INFO - __main__ - Step 120934: {'lr': 4.609618413544453e-05, 'samples': 23219328, 'steps': 120933, 'loss/train': 0.5071395039558411} 08/31/2021 11:13:21 - INFO - __main__ - Step 120935: {'lr': 4.6093113727618266e-05, 'samples': 23219520, 'steps': 120934, 'loss/train': 1.2471191883087158} 08/31/2021 11:13:22 - INFO - __main__ - Step 120936: {'lr': 4.609004341166928e-05, 'samples': 23219712, 'steps': 120935, 'loss/train': 0.5497057437896729} 08/31/2021 11:13:22 - INFO - __main__ - Step 120937: {'lr': 4.608697318759897e-05, 'samples': 23219904, 'steps': 120936, 'loss/train': 1.0053369998931885} 08/31/2021 11:13:23 - INFO - __main__ - Step 120938: {'lr': 4.6083903055408744e-05, 'samples': 23220096, 'steps': 120937, 'loss/train': 1.4718947410583496} 08/31/2021 11:13:23 - INFO - __main__ - Step 120939: {'lr': 4.608083301509994e-05, 'samples': 23220288, 'steps': 120938, 'loss/train': 1.0891491174697876} 08/31/2021 11:13:25 - INFO - __main__ - Step 120940: {'lr': 4.6077763066673995e-05, 'samples': 23220480, 'steps': 120939, 'loss/train': 1.1249417066574097} 08/31/2021 11:13:25 - INFO - __main__ - Step 120941: {'lr': 4.60746932101323e-05, 'samples': 23220672, 'steps': 120940, 'loss/train': 0.4830644130706787} 08/31/2021 11:13:26 - INFO - __main__ - Step 120942: {'lr': 4.6071623445476166e-05, 'samples': 23220864, 'steps': 120941, 'loss/train': 1.0806416273117065} 08/31/2021 11:13:26 - INFO - __main__ - Step 120943: {'lr': 4.6068553772706964e-05, 'samples': 23221056, 'steps': 120942, 'loss/train': 0.32934820652008057} 08/31/2021 11:13:26 - INFO - __main__ - Step 120944: {'lr': 4.606548419182619e-05, 'samples': 23221248, 'steps': 120943, 'loss/train': 0.8938984870910645} 08/31/2021 11:13:27 - INFO - __main__ - Step 120945: {'lr': 4.606241470283512e-05, 'samples': 23221440, 'steps': 120944, 'loss/train': 0.970618486404419} 08/31/2021 11:13:28 - INFO - __main__ - Step 120946: {'lr': 4.6059345305735164e-05, 'samples': 23221632, 'steps': 120945, 'loss/train': 0.8127875924110413} 08/31/2021 11:13:29 - INFO - __main__ - Step 120947: {'lr': 4.605627600052775e-05, 'samples': 23221824, 'steps': 120946, 'loss/train': 1.1091254949569702} 08/31/2021 11:13:29 - INFO - __main__ - Step 120948: {'lr': 4.6053206787214225e-05, 'samples': 23222016, 'steps': 120947, 'loss/train': 1.0821855068206787} 08/31/2021 11:13:29 - INFO - __main__ - Step 120949: {'lr': 4.6050137665795967e-05, 'samples': 23222208, 'steps': 120948, 'loss/train': 0.9529586434364319} 08/31/2021 11:13:30 - INFO - __main__ - Step 120950: {'lr': 4.604706863627439e-05, 'samples': 23222400, 'steps': 120949, 'loss/train': 0.5251746773719788} 08/31/2021 11:13:32 - INFO - __main__ - Step 120951: {'lr': 4.604399969865083e-05, 'samples': 23222592, 'steps': 120950, 'loss/train': 0.7527087926864624} 08/31/2021 11:13:32 - INFO - __main__ - Step 120952: {'lr': 4.6040930852926735e-05, 'samples': 23222784, 'steps': 120951, 'loss/train': 1.0415509939193726} 08/31/2021 11:13:32 - INFO - __main__ - Step 120953: {'lr': 4.603786209910341e-05, 'samples': 23222976, 'steps': 120952, 'loss/train': 1.0689016580581665} 08/31/2021 11:13:33 - INFO - __main__ - Step 120954: {'lr': 4.6034793437182364e-05, 'samples': 23223168, 'steps': 120953, 'loss/train': 0.7080743312835693} 08/31/2021 11:13:33 - INFO - __main__ - Step 120955: {'lr': 4.6031724867164834e-05, 'samples': 23223360, 'steps': 120954, 'loss/train': 1.1968785524368286} 08/31/2021 11:13:33 - INFO - __main__ - Step 120956: {'lr': 4.6028656389052236e-05, 'samples': 23223552, 'steps': 120955, 'loss/train': 1.5709059238433838} 08/31/2021 11:13:35 - INFO - __main__ - Step 120957: {'lr': 4.602558800284598e-05, 'samples': 23223744, 'steps': 120956, 'loss/train': 0.0313098207116127} 08/31/2021 11:13:35 - INFO - __main__ - Step 120958: {'lr': 4.6022519708547486e-05, 'samples': 23223936, 'steps': 120957, 'loss/train': 0.8861923813819885} 08/31/2021 11:13:36 - INFO - __main__ - Step 120959: {'lr': 4.601945150615805e-05, 'samples': 23224128, 'steps': 120958, 'loss/train': 1.1442592144012451} 08/31/2021 11:13:36 - INFO - __main__ - Step 120960: {'lr': 4.6016383395679124e-05, 'samples': 23224320, 'steps': 120959, 'loss/train': 1.750375747680664} 08/31/2021 11:13:36 - INFO - __main__ - Step 120961: {'lr': 4.601331537711206e-05, 'samples': 23224512, 'steps': 120960, 'loss/train': 1.2463828325271606} 08/31/2021 11:13:38 - INFO - __main__ - Step 120962: {'lr': 4.601024745045826e-05, 'samples': 23224704, 'steps': 120961, 'loss/train': 1.0090206861495972} 08/31/2021 11:13:38 - INFO - __main__ - Step 120963: {'lr': 4.6007179615719096e-05, 'samples': 23224896, 'steps': 120962, 'loss/train': 0.4914880394935608} 08/31/2021 11:13:39 - INFO - __main__ - Step 120964: {'lr': 4.600411187289594e-05, 'samples': 23225088, 'steps': 120963, 'loss/train': 1.027706265449524} 08/31/2021 11:13:39 - INFO - __main__ - Step 120965: {'lr': 4.600104422199017e-05, 'samples': 23225280, 'steps': 120964, 'loss/train': 0.6912919878959656} 08/31/2021 11:13:39 - INFO - __main__ - Step 120966: {'lr': 4.5997976663003205e-05, 'samples': 23225472, 'steps': 120965, 'loss/train': 1.0688457489013672} 08/31/2021 11:13:41 - INFO - __main__ - Step 120967: {'lr': 4.599490919593638e-05, 'samples': 23225664, 'steps': 120966, 'loss/train': 1.0418751239776611} 08/31/2021 11:13:41 - INFO - __main__ - Step 120968: {'lr': 4.599184182079119e-05, 'samples': 23225856, 'steps': 120967, 'loss/train': 1.3961771726608276} 08/31/2021 11:13:42 - INFO - __main__ - Step 120969: {'lr': 4.598877453756886e-05, 'samples': 23226048, 'steps': 120968, 'loss/train': 1.24973726272583} 08/31/2021 11:13:42 - INFO - __main__ - Step 120970: {'lr': 4.598570734627083e-05, 'samples': 23226240, 'steps': 120969, 'loss/train': 1.412368655204773} 08/31/2021 11:13:42 - INFO - __main__ - Step 120971: {'lr': 4.5982640246898495e-05, 'samples': 23226432, 'steps': 120970, 'loss/train': 1.2732535600662231} 08/31/2021 11:13:44 - INFO - __main__ - Step 120972: {'lr': 4.5979573239453235e-05, 'samples': 23226624, 'steps': 120971, 'loss/train': 0.8706539273262024} 08/31/2021 11:13:44 - INFO - __main__ - Step 120973: {'lr': 4.5976506323936433e-05, 'samples': 23226816, 'steps': 120972, 'loss/train': 0.22759850323200226} 08/31/2021 11:13:45 - INFO - __main__ - Step 120974: {'lr': 4.597343950034946e-05, 'samples': 23227008, 'steps': 120973, 'loss/train': 0.7606022357940674} 08/31/2021 11:13:45 - INFO - __main__ - Step 120975: {'lr': 4.59703727686937e-05, 'samples': 23227200, 'steps': 120974, 'loss/train': 1.0180307626724243} 08/31/2021 11:13:45 - INFO - __main__ - Step 120976: {'lr': 4.596730612897057e-05, 'samples': 23227392, 'steps': 120975, 'loss/train': 0.3280012905597687} 08/31/2021 11:13:46 - INFO - __main__ - Step 120977: {'lr': 4.59642395811814e-05, 'samples': 23227584, 'steps': 120976, 'loss/train': 0.745762825012207} 08/31/2021 11:13:47 - INFO - __main__ - Step 120978: {'lr': 4.596117312532761e-05, 'samples': 23227776, 'steps': 120977, 'loss/train': 3.041398763656616} 08/31/2021 11:13:48 - INFO - __main__ - Step 120979: {'lr': 4.5958106761410574e-05, 'samples': 23227968, 'steps': 120978, 'loss/train': 0.9248316287994385} 08/31/2021 11:13:48 - INFO - __main__ - Step 120980: {'lr': 4.5955040489431635e-05, 'samples': 23228160, 'steps': 120979, 'loss/train': 0.9083806872367859} 08/31/2021 11:13:48 - INFO - __main__ - Step 120981: {'lr': 4.5951974309392295e-05, 'samples': 23228352, 'steps': 120980, 'loss/train': 0.8451623916625977} 08/31/2021 11:13:49 - INFO - __main__ - Step 120982: {'lr': 4.594890822129377e-05, 'samples': 23228544, 'steps': 120981, 'loss/train': 1.2142291069030762} 08/31/2021 11:13:51 - INFO - __main__ - Step 120983: {'lr': 4.5945842225137534e-05, 'samples': 23228736, 'steps': 120982, 'loss/train': 0.9461165070533752} 08/31/2021 11:13:51 - INFO - __main__ - Step 120984: {'lr': 4.5942776320924945e-05, 'samples': 23228928, 'steps': 120983, 'loss/train': 1.274451494216919} 08/31/2021 11:13:52 - INFO - __main__ - Step 120985: {'lr': 4.593971050865739e-05, 'samples': 23229120, 'steps': 120984, 'loss/train': 1.5767241716384888} 08/31/2021 11:13:52 - INFO - __main__ - Step 120986: {'lr': 4.593664478833626e-05, 'samples': 23229312, 'steps': 120985, 'loss/train': 0.18328526616096497} 08/31/2021 11:13:52 - INFO - __main__ - Step 120987: {'lr': 4.593357915996291e-05, 'samples': 23229504, 'steps': 120986, 'loss/train': 1.0153687000274658} 08/31/2021 11:13:54 - INFO - __main__ - Step 120988: {'lr': 4.5930513623538756e-05, 'samples': 23229696, 'steps': 120987, 'loss/train': 1.708294153213501} 08/31/2021 11:13:54 - INFO - __main__ - Step 120989: {'lr': 4.5927448179065165e-05, 'samples': 23229888, 'steps': 120988, 'loss/train': 1.712711215019226} 08/31/2021 11:13:55 - INFO - __main__ - Step 120990: {'lr': 4.592438282654351e-05, 'samples': 23230080, 'steps': 120989, 'loss/train': 0.9462317824363708} 08/31/2021 11:13:55 - INFO - __main__ - Step 120991: {'lr': 4.5921317565975174e-05, 'samples': 23230272, 'steps': 120990, 'loss/train': 0.7045249938964844} 08/31/2021 11:13:55 - INFO - __main__ - Step 120992: {'lr': 4.591825239736155e-05, 'samples': 23230464, 'steps': 120991, 'loss/train': 1.2119827270507812} 08/31/2021 11:13:57 - INFO - __main__ - Step 120993: {'lr': 4.5915187320704016e-05, 'samples': 23230656, 'steps': 120992, 'loss/train': 1.7095829248428345} 08/31/2021 11:13:58 - INFO - __main__ - Step 120994: {'lr': 4.5912122336004e-05, 'samples': 23230848, 'steps': 120993, 'loss/train': 0.02691158838570118} 08/31/2021 11:13:58 - INFO - __main__ - Step 120995: {'lr': 4.590905744326279e-05, 'samples': 23231040, 'steps': 120994, 'loss/train': 0.9562957882881165} 08/31/2021 11:13:58 - INFO - __main__ - Step 120996: {'lr': 4.59059926424818e-05, 'samples': 23231232, 'steps': 120995, 'loss/train': 0.81055748462677} 08/31/2021 11:13:59 - INFO - __main__ - Step 120997: {'lr': 4.5902927933662406e-05, 'samples': 23231424, 'steps': 120996, 'loss/train': 1.6867449283599854} 08/31/2021 11:14:00 - INFO - __main__ - Step 120998: {'lr': 4.589986331680601e-05, 'samples': 23231616, 'steps': 120997, 'loss/train': 0.027955053374171257} 08/31/2021 11:14:01 - INFO - __main__ - Step 120999: {'lr': 4.5896798791914e-05, 'samples': 23231808, 'steps': 120998, 'loss/train': 0.3904634416103363} 08/31/2021 11:14:01 - INFO - __main__ - Step 121000: {'lr': 4.589373435898772e-05, 'samples': 23232000, 'steps': 120999, 'loss/train': 0.017254678532481194} 08/31/2021 11:14:02 - INFO - __main__ - Step 121001: {'lr': 4.5890670018028604e-05, 'samples': 23232192, 'steps': 121000, 'loss/train': 0.6911953091621399} 08/31/2021 11:14:02 - INFO - __main__ - Step 121002: {'lr': 4.588760576903797e-05, 'samples': 23232384, 'steps': 121001, 'loss/train': 1.5144824981689453} 08/31/2021 11:14:02 - INFO - __main__ - Step 121003: {'lr': 4.588454161201727e-05, 'samples': 23232576, 'steps': 121002, 'loss/train': 0.45226559042930603} 08/31/2021 11:14:03 - INFO - __main__ - Step 121004: {'lr': 4.588147754696781e-05, 'samples': 23232768, 'steps': 121003, 'loss/train': 0.015780717134475708} 08/31/2021 11:14:05 - INFO - __main__ - Step 121005: {'lr': 4.5878413573891026e-05, 'samples': 23232960, 'steps': 121004, 'loss/train': 1.8760629892349243} 08/31/2021 11:14:05 - INFO - __main__ - Step 121006: {'lr': 4.587534969278828e-05, 'samples': 23233152, 'steps': 121005, 'loss/train': 0.4320703148841858} 08/31/2021 11:14:05 - INFO - __main__ - Step 121007: {'lr': 4.587228590366094e-05, 'samples': 23233344, 'steps': 121006, 'loss/train': 1.233473539352417} 08/31/2021 11:14:06 - INFO - __main__ - Step 121008: {'lr': 4.5869222206510466e-05, 'samples': 23233536, 'steps': 121007, 'loss/train': 1.560531735420227} 08/31/2021 11:14:06 - INFO - __main__ - Step 121009: {'lr': 4.586615860133811e-05, 'samples': 23233728, 'steps': 121008, 'loss/train': 1.4246503114700317} 08/31/2021 11:14:07 - INFO - __main__ - Step 121010: {'lr': 4.586309508814529e-05, 'samples': 23233920, 'steps': 121009, 'loss/train': 0.7620760798454285} 08/31/2021 11:14:09 - INFO - __main__ - Step 121011: {'lr': 4.586003166693345e-05, 'samples': 23234112, 'steps': 121010, 'loss/train': 0.13930293917655945} 08/31/2021 11:14:09 - INFO - __main__ - Step 121012: {'lr': 4.585696833770389e-05, 'samples': 23234304, 'steps': 121011, 'loss/train': 1.2490713596343994} 08/31/2021 11:14:09 - INFO - __main__ - Step 121013: {'lr': 4.585390510045806e-05, 'samples': 23234496, 'steps': 121012, 'loss/train': 0.6512460112571716} 08/31/2021 11:14:10 - INFO - __main__ - Step 121014: {'lr': 4.585084195519729e-05, 'samples': 23234688, 'steps': 121013, 'loss/train': 0.9339358806610107} 08/31/2021 11:14:10 - INFO - __main__ - Step 121015: {'lr': 4.5847778901922984e-05, 'samples': 23234880, 'steps': 121014, 'loss/train': 0.016714105382561684} 08/31/2021 11:14:10 - INFO - __main__ - Step 121016: {'lr': 4.584471594063655e-05, 'samples': 23235072, 'steps': 121015, 'loss/train': 0.014658673666417599} 08/31/2021 11:14:12 - INFO - __main__ - Step 121017: {'lr': 4.584165307133931e-05, 'samples': 23235264, 'steps': 121016, 'loss/train': 0.9626452922821045} 08/31/2021 11:14:12 - INFO - __main__ - Step 121018: {'lr': 4.583859029403267e-05, 'samples': 23235456, 'steps': 121017, 'loss/train': 1.0087789297103882} 08/31/2021 11:14:13 - INFO - __main__ - Step 121019: {'lr': 4.583552760871801e-05, 'samples': 23235648, 'steps': 121018, 'loss/train': 0.11448127031326294} 08/31/2021 11:14:13 - INFO - __main__ - Step 121020: {'lr': 4.5832465015396704e-05, 'samples': 23235840, 'steps': 121019, 'loss/train': 0.8622453212738037} 08/31/2021 11:14:13 - INFO - __main__ - Step 121021: {'lr': 4.582940251407022e-05, 'samples': 23236032, 'steps': 121020, 'loss/train': 1.6369268894195557} 08/31/2021 11:14:15 - INFO - __main__ - Step 121022: {'lr': 4.5826340104739766e-05, 'samples': 23236224, 'steps': 121021, 'loss/train': 0.8715517520904541} 08/31/2021 11:14:15 - INFO - __main__ - Step 121023: {'lr': 4.582327778740683e-05, 'samples': 23236416, 'steps': 121022, 'loss/train': 0.7795816659927368} 08/31/2021 11:14:16 - INFO - __main__ - Step 121024: {'lr': 4.5820215562072775e-05, 'samples': 23236608, 'steps': 121023, 'loss/train': 1.043517827987671} 08/31/2021 11:14:16 - INFO - __main__ - Step 121025: {'lr': 4.581715342873899e-05, 'samples': 23236800, 'steps': 121024, 'loss/train': 0.3933335244655609} 08/31/2021 11:14:16 - INFO - __main__ - Step 121026: {'lr': 4.581409138740683e-05, 'samples': 23236992, 'steps': 121025, 'loss/train': 1.245036005973816} 08/31/2021 11:14:18 - INFO - __main__ - Step 121027: {'lr': 4.581102943807772e-05, 'samples': 23237184, 'steps': 121026, 'loss/train': 0.9067307114601135} 08/31/2021 11:14:18 - INFO - __main__ - Step 121028: {'lr': 4.580796758075298e-05, 'samples': 23237376, 'steps': 121027, 'loss/train': 1.2304322719573975} 08/31/2021 11:14:19 - INFO - __main__ - Step 121029: {'lr': 4.5804905815434e-05, 'samples': 23237568, 'steps': 121028, 'loss/train': 0.5566796064376831} 08/31/2021 11:14:19 - INFO - __main__ - Step 121030: {'lr': 4.5801844142122214e-05, 'samples': 23237760, 'steps': 121029, 'loss/train': 0.8560192584991455} 08/31/2021 11:14:19 - INFO - __main__ - Step 121031: {'lr': 4.579878256081896e-05, 'samples': 23237952, 'steps': 121030, 'loss/train': 1.0041431188583374} 08/31/2021 11:14:21 - INFO - __main__ - Step 121032: {'lr': 4.57957210715256e-05, 'samples': 23238144, 'steps': 121031, 'loss/train': 1.1393961906433105} 08/31/2021 11:14:21 - INFO - __main__ - Step 121033: {'lr': 4.5792659674243566e-05, 'samples': 23238336, 'steps': 121032, 'loss/train': 1.4225471019744873} 08/31/2021 11:14:22 - INFO - __main__ - Step 121034: {'lr': 4.57895983689742e-05, 'samples': 23238528, 'steps': 121033, 'loss/train': 1.0951910018920898} 08/31/2021 11:14:22 - INFO - __main__ - Step 121035: {'lr': 4.578653715571896e-05, 'samples': 23238720, 'steps': 121034, 'loss/train': 1.1260565519332886} 08/31/2021 11:14:22 - INFO - __main__ - Step 121036: {'lr': 4.578347603447908e-05, 'samples': 23238912, 'steps': 121035, 'loss/train': 0.9318598508834839} 08/31/2021 11:14:23 - INFO - __main__ - Step 121037: {'lr': 4.578041500525601e-05, 'samples': 23239104, 'steps': 121036, 'loss/train': 0.44719061255455017} 08/31/2021 11:14:25 - INFO - __main__ - Step 121038: {'lr': 4.577735406805114e-05, 'samples': 23239296, 'steps': 121037, 'loss/train': 0.6301584243774414} 08/31/2021 11:14:25 - INFO - __main__ - Step 121039: {'lr': 4.5774293222865835e-05, 'samples': 23239488, 'steps': 121038, 'loss/train': 0.014205335639417171} 08/31/2021 11:14:25 - INFO - __main__ - Step 121040: {'lr': 4.5771232469701495e-05, 'samples': 23239680, 'steps': 121039, 'loss/train': 0.7821514010429382} 08/31/2021 11:14:26 - INFO - __main__ - Step 121041: {'lr': 4.576817180855949e-05, 'samples': 23239872, 'steps': 121040, 'loss/train': 0.9687727689743042} 08/31/2021 11:14:26 - INFO - __main__ - Step 121042: {'lr': 4.576511123944119e-05, 'samples': 23240064, 'steps': 121041, 'loss/train': 0.9743009805679321} 08/31/2021 11:14:26 - INFO - __main__ - Step 121043: {'lr': 4.5762050762347965e-05, 'samples': 23240256, 'steps': 121042, 'loss/train': 0.8621166944503784} 08/31/2021 11:14:28 - INFO - __main__ - Step 121044: {'lr': 4.5758990377281234e-05, 'samples': 23240448, 'steps': 121043, 'loss/train': 0.08352289348840714} 08/31/2021 11:14:29 - INFO - __main__ - Step 121045: {'lr': 4.5755930084242335e-05, 'samples': 23240640, 'steps': 121044, 'loss/train': 1.4952521324157715} 08/31/2021 11:14:29 - INFO - __main__ - Step 121046: {'lr': 4.575286988323266e-05, 'samples': 23240832, 'steps': 121045, 'loss/train': 1.3279751539230347} 08/31/2021 11:14:30 - INFO - __main__ - Step 121047: {'lr': 4.5749809774253584e-05, 'samples': 23241024, 'steps': 121046, 'loss/train': 1.3170307874679565} 08/31/2021 11:14:30 - INFO - __main__ - Step 121048: {'lr': 4.574674975730655e-05, 'samples': 23241216, 'steps': 121047, 'loss/train': 0.8077448606491089} 08/31/2021 11:14:32 - INFO - __main__ - Step 121049: {'lr': 4.5743689832392854e-05, 'samples': 23241408, 'steps': 121048, 'loss/train': 1.026700735092163} 08/31/2021 11:14:32 - INFO - __main__ - Step 121050: {'lr': 4.574062999951387e-05, 'samples': 23241600, 'steps': 121049, 'loss/train': 1.5545097589492798} 08/31/2021 11:14:33 - INFO - __main__ - Step 121051: {'lr': 4.5737570258671006e-05, 'samples': 23241792, 'steps': 121050, 'loss/train': 1.0839266777038574} 08/31/2021 11:14:33 - INFO - __main__ - Step 121052: {'lr': 4.5734510609865634e-05, 'samples': 23241984, 'steps': 121051, 'loss/train': 1.2656755447387695} 08/31/2021 11:14:33 - INFO - __main__ - Step 121053: {'lr': 4.5731451053099174e-05, 'samples': 23242176, 'steps': 121052, 'loss/train': 1.0885533094406128} 08/31/2021 11:14:34 - INFO - __main__ - Step 121054: {'lr': 4.572839158837294e-05, 'samples': 23242368, 'steps': 121053, 'loss/train': 0.052308954298496246} 08/31/2021 11:14:35 - INFO - __main__ - Step 121055: {'lr': 4.5725332215688336e-05, 'samples': 23242560, 'steps': 121054, 'loss/train': 0.017852002754807472} 08/31/2021 11:14:36 - INFO - __main__ - Step 121056: {'lr': 4.572227293504677e-05, 'samples': 23242752, 'steps': 121055, 'loss/train': 0.6727156639099121} 08/31/2021 11:14:36 - INFO - __main__ - Step 121057: {'lr': 4.571921374644958e-05, 'samples': 23242944, 'steps': 121056, 'loss/train': 0.9127559661865234} 08/31/2021 11:14:36 - INFO - __main__ - Step 121058: {'lr': 4.5716154649898174e-05, 'samples': 23243136, 'steps': 121057, 'loss/train': 1.2781943082809448} 08/31/2021 11:14:37 - INFO - __main__ - Step 121059: {'lr': 4.571309564539389e-05, 'samples': 23243328, 'steps': 121058, 'loss/train': 0.9076679944992065} 08/31/2021 11:14:38 - INFO - __main__ - Step 121060: {'lr': 4.5710036732938164e-05, 'samples': 23243520, 'steps': 121059, 'loss/train': 1.2008867263793945} 08/31/2021 11:14:39 - INFO - __main__ - Step 121061: {'lr': 4.570697791253231e-05, 'samples': 23243712, 'steps': 121060, 'loss/train': 0.9627924561500549} 08/31/2021 11:14:39 - INFO - __main__ - Step 121062: {'lr': 4.570391918417782e-05, 'samples': 23243904, 'steps': 121061, 'loss/train': 0.625611424446106} 08/31/2021 11:14:39 - INFO - __main__ - Step 121063: {'lr': 4.570086054787595e-05, 'samples': 23244096, 'steps': 121062, 'loss/train': 1.2106362581253052} 08/31/2021 11:14:40 - INFO - __main__ - Step 121064: {'lr': 4.569780200362808e-05, 'samples': 23244288, 'steps': 121063, 'loss/train': 1.2189724445343018} 08/31/2021 11:14:41 - INFO - __main__ - Step 121065: {'lr': 4.569474355143566e-05, 'samples': 23244480, 'steps': 121064, 'loss/train': 0.9963517189025879} 08/31/2021 11:14:42 - INFO - __main__ - Step 121066: {'lr': 4.569168519130001e-05, 'samples': 23244672, 'steps': 121065, 'loss/train': 0.27617859840393066} 08/31/2021 11:14:42 - INFO - __main__ - Step 121067: {'lr': 4.5688626923222564e-05, 'samples': 23244864, 'steps': 121066, 'loss/train': 0.33338120579719543} 08/31/2021 11:14:42 - INFO - __main__ - Step 121068: {'lr': 4.568556874720464e-05, 'samples': 23245056, 'steps': 121067, 'loss/train': 0.8702318072319031} 08/31/2021 11:14:43 - INFO - __main__ - Step 121069: {'lr': 4.5682510663247664e-05, 'samples': 23245248, 'steps': 121068, 'loss/train': 0.9005969166755676} 08/31/2021 11:14:44 - INFO - __main__ - Step 121070: {'lr': 4.5679452671352985e-05, 'samples': 23245440, 'steps': 121069, 'loss/train': 1.0556044578552246} 08/31/2021 11:14:45 - INFO - __main__ - Step 121071: {'lr': 4.5676394771522e-05, 'samples': 23245632, 'steps': 121070, 'loss/train': 1.7517337799072266} 08/31/2021 11:14:45 - INFO - __main__ - Step 121072: {'lr': 4.567333696375609e-05, 'samples': 23245824, 'steps': 121071, 'loss/train': 1.015819787979126} 08/31/2021 11:14:46 - INFO - __main__ - Step 121073: {'lr': 4.5670279248056585e-05, 'samples': 23246016, 'steps': 121072, 'loss/train': 0.2402874082326889} 08/31/2021 11:14:46 - INFO - __main__ - Step 121074: {'lr': 4.5667221624424936e-05, 'samples': 23246208, 'steps': 121073, 'loss/train': 1.968057632446289} 08/31/2021 11:14:47 - INFO - __main__ - Step 121075: {'lr': 4.566416409286253e-05, 'samples': 23246400, 'steps': 121074, 'loss/train': 1.8246508836746216} 08/31/2021 11:14:48 - INFO - __main__ - Step 121076: {'lr': 4.5661106653370646e-05, 'samples': 23246592, 'steps': 121075, 'loss/train': 0.7927241921424866} 08/31/2021 11:14:48 - INFO - __main__ - Step 121077: {'lr': 4.565804930595069e-05, 'samples': 23246784, 'steps': 121076, 'loss/train': 1.162995457649231} 08/31/2021 11:14:49 - INFO - __main__ - Step 121078: {'lr': 4.565499205060408e-05, 'samples': 23246976, 'steps': 121077, 'loss/train': 0.9012469053268433} 08/31/2021 11:14:49 - INFO - __main__ - Step 121079: {'lr': 4.565193488733219e-05, 'samples': 23247168, 'steps': 121078, 'loss/train': 1.0412709712982178} 08/31/2021 11:14:51 - INFO - __main__ - Step 121080: {'lr': 4.5648877816136356e-05, 'samples': 23247360, 'steps': 121079, 'loss/train': 0.9281795620918274} 08/31/2021 11:14:51 - INFO - __main__ - Step 121081: {'lr': 4.5645820837017986e-05, 'samples': 23247552, 'steps': 121080, 'loss/train': 1.5783698558807373} 08/31/2021 11:14:51 - INFO - __main__ - Step 121082: {'lr': 4.564276394997849e-05, 'samples': 23247744, 'steps': 121081, 'loss/train': 1.034812331199646} 08/31/2021 11:14:52 - INFO - __main__ - Step 121083: {'lr': 4.5639707155019195e-05, 'samples': 23247936, 'steps': 121082, 'loss/train': 1.258407473564148} 08/31/2021 11:14:52 - INFO - __main__ - Step 121084: {'lr': 4.563665045214149e-05, 'samples': 23248128, 'steps': 121083, 'loss/train': 1.1561925411224365} 08/31/2021 11:14:52 - INFO - __main__ - Step 121085: {'lr': 4.5633593841346744e-05, 'samples': 23248320, 'steps': 121084, 'loss/train': 1.0899693965911865} 08/31/2021 11:14:54 - INFO - __main__ - Step 121086: {'lr': 4.5630537322636365e-05, 'samples': 23248512, 'steps': 121085, 'loss/train': 1.3487179279327393} 08/31/2021 11:14:55 - INFO - __main__ - Step 121087: {'lr': 4.562748089601171e-05, 'samples': 23248704, 'steps': 121086, 'loss/train': 0.9943868517875671} 08/31/2021 11:14:55 - INFO - __main__ - Step 121088: {'lr': 4.562442456147414e-05, 'samples': 23248896, 'steps': 121087, 'loss/train': 1.409375548362732} 08/31/2021 11:14:55 - INFO - __main__ - Step 121089: {'lr': 4.5621368319025136e-05, 'samples': 23249088, 'steps': 121088, 'loss/train': 1.313327670097351} 08/31/2021 11:14:56 - INFO - __main__ - Step 121090: {'lr': 4.561831216866594e-05, 'samples': 23249280, 'steps': 121089, 'loss/train': 0.02453722432255745} 08/31/2021 11:14:56 - INFO - __main__ - Step 121091: {'lr': 4.5615256110397934e-05, 'samples': 23249472, 'steps': 121090, 'loss/train': 0.6191571354866028} 08/31/2021 11:14:58 - INFO - __main__ - Step 121092: {'lr': 4.561220014422257e-05, 'samples': 23249664, 'steps': 121091, 'loss/train': 0.014178818091750145} 08/31/2021 11:14:58 - INFO - __main__ - Step 121093: {'lr': 4.5609144270141206e-05, 'samples': 23249856, 'steps': 121092, 'loss/train': 1.1415152549743652} 08/31/2021 11:14:59 - INFO - __main__ - Step 121094: {'lr': 4.5606088488155175e-05, 'samples': 23250048, 'steps': 121093, 'loss/train': 0.0394885390996933} 08/31/2021 11:14:59 - INFO - __main__ - Step 121095: {'lr': 4.560303279826592e-05, 'samples': 23250240, 'steps': 121094, 'loss/train': 1.007939100265503} 08/31/2021 11:14:59 - INFO - __main__ - Step 121096: {'lr': 4.559997720047476e-05, 'samples': 23250432, 'steps': 121095, 'loss/train': 0.9756284356117249} 08/31/2021 11:15:02 - INFO - __main__ - Step 121097: {'lr': 4.5596921694783106e-05, 'samples': 23250624, 'steps': 121096, 'loss/train': 1.183870792388916} 08/31/2021 11:15:02 - INFO - __main__ - Step 121098: {'lr': 4.55938662811923e-05, 'samples': 23250816, 'steps': 121097, 'loss/train': 1.219710111618042} 08/31/2021 11:15:02 - INFO - __main__ - Step 121099: {'lr': 4.559081095970377e-05, 'samples': 23251008, 'steps': 121098, 'loss/train': 1.3064405918121338} 08/31/2021 11:15:03 - INFO - __main__ - Step 121100: {'lr': 4.558775573031887e-05, 'samples': 23251200, 'steps': 121099, 'loss/train': 0.9754951000213623} 08/31/2021 11:15:03 - INFO - __main__ - Step 121101: {'lr': 4.5584700593038955e-05, 'samples': 23251392, 'steps': 121100, 'loss/train': 0.8938323259353638} 08/31/2021 11:15:03 - INFO - __main__ - Step 121102: {'lr': 4.5581645547865505e-05, 'samples': 23251584, 'steps': 121101, 'loss/train': 1.9151440858840942} 08/31/2021 11:15:05 - INFO - __main__ - Step 121103: {'lr': 4.557859059479974e-05, 'samples': 23251776, 'steps': 121102, 'loss/train': 2.330587148666382} 08/31/2021 11:15:05 - INFO - __main__ - Step 121104: {'lr': 4.55755357338431e-05, 'samples': 23251968, 'steps': 121103, 'loss/train': 0.05824177339673042} 08/31/2021 11:15:06 - INFO - __main__ - Step 121105: {'lr': 4.557248096499697e-05, 'samples': 23252160, 'steps': 121104, 'loss/train': 0.9963825345039368} 08/31/2021 11:15:06 - INFO - __main__ - Step 121106: {'lr': 4.5569426288262716e-05, 'samples': 23252352, 'steps': 121105, 'loss/train': 0.18021847307682037} 08/31/2021 11:15:06 - INFO - __main__ - Step 121107: {'lr': 4.5566371703641754e-05, 'samples': 23252544, 'steps': 121106, 'loss/train': 1.4222861528396606} 08/31/2021 11:15:08 - INFO - __main__ - Step 121108: {'lr': 4.556331721113541e-05, 'samples': 23252736, 'steps': 121107, 'loss/train': 0.028355196118354797} 08/31/2021 11:15:08 - INFO - __main__ - Step 121109: {'lr': 4.5560262810745074e-05, 'samples': 23252928, 'steps': 121108, 'loss/train': 1.0106191635131836} 08/31/2021 11:15:09 - INFO - __main__ - Step 121110: {'lr': 4.5557208502472135e-05, 'samples': 23253120, 'steps': 121109, 'loss/train': 1.390344500541687} 08/31/2021 11:15:09 - INFO - __main__ - Step 121111: {'lr': 4.5554154286317986e-05, 'samples': 23253312, 'steps': 121110, 'loss/train': 1.04510498046875} 08/31/2021 11:15:09 - INFO - __main__ - Step 121112: {'lr': 4.555110016228395e-05, 'samples': 23253504, 'steps': 121111, 'loss/train': 0.750723123550415} 08/31/2021 11:15:11 - INFO - __main__ - Step 121113: {'lr': 4.5548046130371446e-05, 'samples': 23253696, 'steps': 121112, 'loss/train': 1.338542103767395} 08/31/2021 11:15:11 - INFO - __main__ - Step 121114: {'lr': 4.5544992190581834e-05, 'samples': 23253888, 'steps': 121113, 'loss/train': 0.8633615374565125} 08/31/2021 11:15:12 - INFO - __main__ - Step 121115: {'lr': 4.554193834291656e-05, 'samples': 23254080, 'steps': 121114, 'loss/train': 0.8689955472946167} 08/31/2021 11:15:12 - INFO - __main__ - Step 121116: {'lr': 4.553888458737687e-05, 'samples': 23254272, 'steps': 121115, 'loss/train': 0.4508344531059265} 08/31/2021 11:15:12 - INFO - __main__ - Step 121117: {'lr': 4.553583092396418e-05, 'samples': 23254464, 'steps': 121116, 'loss/train': 1.1826410293579102} 08/31/2021 11:15:14 - INFO - __main__ - Step 121118: {'lr': 4.553277735267994e-05, 'samples': 23254656, 'steps': 121117, 'loss/train': 1.4655793905258179} 08/31/2021 11:15:14 - INFO - __main__ - Step 121119: {'lr': 4.552972387352544e-05, 'samples': 23254848, 'steps': 121118, 'loss/train': 0.37048283219337463} 08/31/2021 11:15:15 - INFO - __main__ - Step 121120: {'lr': 4.552667048650208e-05, 'samples': 23255040, 'steps': 121119, 'loss/train': 1.0179109573364258} 08/31/2021 11:15:15 - INFO - __main__ - Step 121121: {'lr': 4.552361719161127e-05, 'samples': 23255232, 'steps': 121120, 'loss/train': 0.9423606991767883} 08/31/2021 11:15:15 - INFO - __main__ - Step 121122: {'lr': 4.5520563988854375e-05, 'samples': 23255424, 'steps': 121121, 'loss/train': 0.6151268482208252} 08/31/2021 11:15:17 - INFO - __main__ - Step 121123: {'lr': 4.551751087823272e-05, 'samples': 23255616, 'steps': 121122, 'loss/train': 1.4185456037521362} 08/31/2021 11:15:18 - INFO - __main__ - Step 121124: {'lr': 4.5514457859747754e-05, 'samples': 23255808, 'steps': 121123, 'loss/train': 1.1936959028244019} 08/31/2021 11:15:18 - INFO - __main__ - Step 121125: {'lr': 4.551140493340081e-05, 'samples': 23256000, 'steps': 121124, 'loss/train': 0.10220964252948761} 08/31/2021 11:15:18 - INFO - __main__ - Step 121126: {'lr': 4.5508352099193265e-05, 'samples': 23256192, 'steps': 121125, 'loss/train': 1.6915488243103027} 08/31/2021 11:15:19 - INFO - __main__ - Step 121127: {'lr': 4.5505299357126496e-05, 'samples': 23256384, 'steps': 121126, 'loss/train': 0.027601078152656555} 08/31/2021 11:15:20 - INFO - __main__ - Step 121128: {'lr': 4.550224670720188e-05, 'samples': 23256576, 'steps': 121127, 'loss/train': 0.8222851157188416} 08/31/2021 11:15:21 - INFO - __main__ - Step 121129: {'lr': 4.5499194149420884e-05, 'samples': 23256768, 'steps': 121128, 'loss/train': 0.8063425421714783} 08/31/2021 11:15:21 - INFO - __main__ - Step 121130: {'lr': 4.549614168378471e-05, 'samples': 23256960, 'steps': 121129, 'loss/train': 1.0297666788101196} 08/31/2021 11:15:21 - INFO - __main__ - Step 121131: {'lr': 4.549308931029483e-05, 'samples': 23257152, 'steps': 121130, 'loss/train': 1.0195623636245728} 08/31/2021 11:15:22 - INFO - __main__ - Step 121132: {'lr': 4.5490037028952604e-05, 'samples': 23257344, 'steps': 121131, 'loss/train': 1.6119059324264526} 08/31/2021 11:15:23 - INFO - __main__ - Step 121133: {'lr': 4.548698483975941e-05, 'samples': 23257536, 'steps': 121132, 'loss/train': 1.226718783378601} 08/31/2021 11:15:24 - INFO - __main__ - Step 121134: {'lr': 4.548393274271662e-05, 'samples': 23257728, 'steps': 121133, 'loss/train': 1.1678739786148071} 08/31/2021 11:15:24 - INFO - __main__ - Step 121135: {'lr': 4.548088073782564e-05, 'samples': 23257920, 'steps': 121134, 'loss/train': 0.9267585873603821} 08/31/2021 11:15:24 - INFO - __main__ - Step 121136: {'lr': 4.5477828825087804e-05, 'samples': 23258112, 'steps': 121135, 'loss/train': 1.0665525197982788} 08/31/2021 11:15:25 - INFO - __main__ - Step 121137: {'lr': 4.547477700450448e-05, 'samples': 23258304, 'steps': 121136, 'loss/train': 0.28932973742485046} 08/31/2021 11:15:26 - INFO - __main__ - Step 121138: {'lr': 4.5471725276077096e-05, 'samples': 23258496, 'steps': 121137, 'loss/train': 0.33542686700820923} 08/31/2021 11:15:27 - INFO - __main__ - Step 121139: {'lr': 4.5468673639806974e-05, 'samples': 23258688, 'steps': 121138, 'loss/train': 0.3906495273113251} 08/31/2021 11:15:27 - INFO - __main__ - Step 121140: {'lr': 4.546562209569552e-05, 'samples': 23258880, 'steps': 121139, 'loss/train': 1.1190075874328613} 08/31/2021 11:15:28 - INFO - __main__ - Step 121141: {'lr': 4.54625706437441e-05, 'samples': 23259072, 'steps': 121140, 'loss/train': 0.035604048520326614} 08/31/2021 11:15:28 - INFO - __main__ - Step 121142: {'lr': 4.545951928395417e-05, 'samples': 23259264, 'steps': 121141, 'loss/train': 1.306445837020874} 08/31/2021 11:15:30 - INFO - __main__ - Step 121143: {'lr': 4.545646801632694e-05, 'samples': 23259456, 'steps': 121142, 'loss/train': 1.236565351486206} 08/31/2021 11:15:30 - INFO - __main__ - Step 121144: {'lr': 4.5453416840863876e-05, 'samples': 23259648, 'steps': 121143, 'loss/train': 1.2726327180862427} 08/31/2021 11:15:31 - INFO - __main__ - Step 121145: {'lr': 4.545036575756634e-05, 'samples': 23259840, 'steps': 121144, 'loss/train': 1.2798832654953003} 08/31/2021 11:15:31 - INFO - __main__ - Step 121146: {'lr': 4.544731476643571e-05, 'samples': 23260032, 'steps': 121145, 'loss/train': 0.6607542634010315} 08/31/2021 11:15:31 - INFO - __main__ - Step 121147: {'lr': 4.5444263867473384e-05, 'samples': 23260224, 'steps': 121146, 'loss/train': 1.3280017375946045} 08/31/2021 11:15:32 - INFO - __main__ - Step 121148: {'lr': 4.544121306068069e-05, 'samples': 23260416, 'steps': 121147, 'loss/train': 1.4786502122879028} 08/31/2021 11:15:33 - INFO - __main__ - Step 121149: {'lr': 4.543816234605905e-05, 'samples': 23260608, 'steps': 121148, 'loss/train': 0.028495503589510918} 08/31/2021 11:15:34 - INFO - __main__ - Step 121150: {'lr': 4.543511172360981e-05, 'samples': 23260800, 'steps': 121149, 'loss/train': 1.0537089109420776} 08/31/2021 11:15:34 - INFO - __main__ - Step 121151: {'lr': 4.5432061193334343e-05, 'samples': 23260992, 'steps': 121150, 'loss/train': 0.9274383783340454} 08/31/2021 11:15:34 - INFO - __main__ - Step 121152: {'lr': 4.542901075523406e-05, 'samples': 23261184, 'steps': 121151, 'loss/train': 1.3779700994491577} 08/31/2021 11:15:35 - INFO - __main__ - Step 121153: {'lr': 4.5425960409310294e-05, 'samples': 23261376, 'steps': 121152, 'loss/train': 1.027637004852295} 08/31/2021 11:15:37 - INFO - __main__ - Step 121154: {'lr': 4.5422910155564434e-05, 'samples': 23261568, 'steps': 121153, 'loss/train': 1.106749176979065} 08/31/2021 11:15:37 - INFO - __main__ - Step 121155: {'lr': 4.541985999399789e-05, 'samples': 23261760, 'steps': 121154, 'loss/train': 1.22394859790802} 08/31/2021 11:15:38 - INFO - __main__ - Step 121156: {'lr': 4.5416809924611976e-05, 'samples': 23261952, 'steps': 121155, 'loss/train': 0.10456756502389908} 08/31/2021 11:15:38 - INFO - __main__ - Step 121157: {'lr': 4.541375994740807e-05, 'samples': 23262144, 'steps': 121156, 'loss/train': 2.2062337398529053} 08/31/2021 11:15:39 - INFO - __main__ - Step 121158: {'lr': 4.5410710062387564e-05, 'samples': 23262336, 'steps': 121157, 'loss/train': 1.8357104063034058} 08/31/2021 11:15:39 - INFO - __main__ - Step 121159: {'lr': 4.540766026955184e-05, 'samples': 23262528, 'steps': 121158, 'loss/train': 0.14701882004737854} 08/31/2021 11:15:40 - INFO - __main__ - Step 121160: {'lr': 4.540461056890227e-05, 'samples': 23262720, 'steps': 121159, 'loss/train': 1.3501269817352295} 08/31/2021 11:15:41 - INFO - __main__ - Step 121161: {'lr': 4.540156096044024e-05, 'samples': 23262912, 'steps': 121160, 'loss/train': 1.1366125345230103} 08/31/2021 11:15:41 - INFO - __main__ - Step 121162: {'lr': 4.5398511444167095e-05, 'samples': 23263104, 'steps': 121161, 'loss/train': 1.8113932609558105} 08/31/2021 11:15:42 - INFO - __main__ - Step 121163: {'lr': 4.5395462020084214e-05, 'samples': 23263296, 'steps': 121162, 'loss/train': 1.053486704826355} 08/31/2021 11:15:42 - INFO - __main__ - Step 121164: {'lr': 4.5392412688192994e-05, 'samples': 23263488, 'steps': 121163, 'loss/train': 0.9265093207359314} 08/31/2021 11:15:43 - INFO - __main__ - Step 121165: {'lr': 4.5389363448494786e-05, 'samples': 23263680, 'steps': 121164, 'loss/train': 1.7078148126602173} 08/31/2021 11:15:44 - INFO - __main__ - Step 121166: {'lr': 4.538631430099105e-05, 'samples': 23263872, 'steps': 121165, 'loss/train': 1.1687041521072388} 08/31/2021 11:15:44 - INFO - __main__ - Step 121167: {'lr': 4.538326524568301e-05, 'samples': 23264064, 'steps': 121166, 'loss/train': 1.4786417484283447} 08/31/2021 11:15:45 - INFO - __main__ - Step 121168: {'lr': 4.538021628257211e-05, 'samples': 23264256, 'steps': 121167, 'loss/train': 1.0844645500183105} 08/31/2021 11:15:45 - INFO - __main__ - Step 121169: {'lr': 4.537716741165973e-05, 'samples': 23264448, 'steps': 121168, 'loss/train': 0.31357038021087646} 08/31/2021 11:15:47 - INFO - __main__ - Step 121170: {'lr': 4.537411863294724e-05, 'samples': 23264640, 'steps': 121169, 'loss/train': 1.0043765306472778} 08/31/2021 11:15:47 - INFO - __main__ - Step 121171: {'lr': 4.537106994643603e-05, 'samples': 23264832, 'steps': 121170, 'loss/train': 0.4407195746898651} 08/31/2021 11:15:47 - INFO - __main__ - Step 121172: {'lr': 4.536802135212745e-05, 'samples': 23265024, 'steps': 121171, 'loss/train': 0.7032013535499573} 08/31/2021 11:15:48 - INFO - __main__ - Step 121173: {'lr': 4.536497285002286e-05, 'samples': 23265216, 'steps': 121172, 'loss/train': 1.2169296741485596} 08/31/2021 11:15:48 - INFO - __main__ - Step 121174: {'lr': 4.536192444012369e-05, 'samples': 23265408, 'steps': 121173, 'loss/train': 1.456581473350525} 08/31/2021 11:15:50 - INFO - __main__ - Step 121175: {'lr': 4.535887612243125e-05, 'samples': 23265600, 'steps': 121174, 'loss/train': 0.029934624210000038} 08/31/2021 11:15:50 - INFO - __main__ - Step 121176: {'lr': 4.535582789694695e-05, 'samples': 23265792, 'steps': 121175, 'loss/train': 1.1159896850585938} 08/31/2021 11:15:50 - INFO - __main__ - Step 121177: {'lr': 4.535277976367222e-05, 'samples': 23265984, 'steps': 121176, 'loss/train': 1.4398107528686523} 08/31/2021 11:15:51 - INFO - __main__ - Step 121178: {'lr': 4.534973172260831e-05, 'samples': 23266176, 'steps': 121177, 'loss/train': 1.2617510557174683} 08/31/2021 11:15:51 - INFO - __main__ - Step 121179: {'lr': 4.5346683773756667e-05, 'samples': 23266368, 'steps': 121178, 'loss/train': 1.4671049118041992} 08/31/2021 11:15:51 - INFO - __main__ - Step 121180: {'lr': 4.534363591711863e-05, 'samples': 23266560, 'steps': 121179, 'loss/train': 1.751827597618103} 08/31/2021 11:15:53 - INFO - __main__ - Step 121181: {'lr': 4.5340588152695596e-05, 'samples': 23266752, 'steps': 121180, 'loss/train': 1.1506267786026} 08/31/2021 11:15:53 - INFO - __main__ - Step 121182: {'lr': 4.533754048048894e-05, 'samples': 23266944, 'steps': 121181, 'loss/train': 1.5086702108383179} 08/31/2021 11:15:54 - INFO - __main__ - Step 121183: {'lr': 4.533449290050004e-05, 'samples': 23267136, 'steps': 121182, 'loss/train': 0.22456249594688416} 08/31/2021 11:15:54 - INFO - __main__ - Step 121184: {'lr': 4.5331445412730235e-05, 'samples': 23267328, 'steps': 121183, 'loss/train': 0.07163655757904053} 08/31/2021 11:15:54 - INFO - __main__ - Step 121185: {'lr': 4.5328398017180944e-05, 'samples': 23267520, 'steps': 121184, 'loss/train': 0.4922887682914734} 08/31/2021 11:15:56 - INFO - __main__ - Step 121186: {'lr': 4.532535071385349e-05, 'samples': 23267712, 'steps': 121185, 'loss/train': 1.3043949604034424} 08/31/2021 11:15:57 - INFO - __main__ - Step 121187: {'lr': 4.532230350274938e-05, 'samples': 23267904, 'steps': 121186, 'loss/train': 0.19254343211650848} 08/31/2021 11:15:57 - INFO - __main__ - Step 121188: {'lr': 4.53192563838698e-05, 'samples': 23268096, 'steps': 121187, 'loss/train': 0.02834215946495533} 08/31/2021 11:15:57 - INFO - __main__ - Step 121189: {'lr': 4.53162093572162e-05, 'samples': 23268288, 'steps': 121188, 'loss/train': 0.995840311050415} 08/31/2021 11:15:58 - INFO - __main__ - Step 121190: {'lr': 4.531316242278993e-05, 'samples': 23268480, 'steps': 121189, 'loss/train': 1.5031636953353882} 08/31/2021 11:15:59 - INFO - __main__ - Step 121191: {'lr': 4.5310115580592445e-05, 'samples': 23268672, 'steps': 121190, 'loss/train': 1.3813756704330444} 08/31/2021 11:16:00 - INFO - __main__ - Step 121192: {'lr': 4.530706883062502e-05, 'samples': 23268864, 'steps': 121191, 'loss/train': 0.9248800873756409} 08/31/2021 11:16:00 - INFO - __main__ - Step 121193: {'lr': 4.530402217288909e-05, 'samples': 23269056, 'steps': 121192, 'loss/train': 0.8189882040023804} 08/31/2021 11:16:00 - INFO - __main__ - Step 121194: {'lr': 4.5300975607386026e-05, 'samples': 23269248, 'steps': 121193, 'loss/train': 0.24680858850479126} 08/31/2021 11:16:01 - INFO - __main__ - Step 121195: {'lr': 4.529792913411715e-05, 'samples': 23269440, 'steps': 121194, 'loss/train': 1.1808536052703857} 08/31/2021 11:16:03 - INFO - __main__ - Step 121196: {'lr': 4.5294882753083884e-05, 'samples': 23269632, 'steps': 121195, 'loss/train': 1.2039070129394531} 08/31/2021 11:16:03 - INFO - __main__ - Step 121197: {'lr': 4.529183646428758e-05, 'samples': 23269824, 'steps': 121196, 'loss/train': 0.022358056157827377} 08/31/2021 11:16:03 - INFO - __main__ - Step 121198: {'lr': 4.52887902677297e-05, 'samples': 23270016, 'steps': 121197, 'loss/train': 1.549404501914978} 08/31/2021 11:16:04 - INFO - __main__ - Step 121199: {'lr': 4.528574416341144e-05, 'samples': 23270208, 'steps': 121198, 'loss/train': 0.05576042830944061} 08/31/2021 11:16:04 - INFO - __main__ - Step 121200: {'lr': 4.528269815133429e-05, 'samples': 23270400, 'steps': 121199, 'loss/train': 0.10877329111099243} 08/31/2021 11:16:06 - INFO - __main__ - Step 121201: {'lr': 4.5279652231499574e-05, 'samples': 23270592, 'steps': 121200, 'loss/train': 1.3167110681533813} 08/31/2021 11:16:07 - INFO - __main__ - Step 121202: {'lr': 4.527660640390868e-05, 'samples': 23270784, 'steps': 121201, 'loss/train': 0.8275617957115173} 08/31/2021 11:16:07 - INFO - __main__ - Step 121203: {'lr': 4.527356066856303e-05, 'samples': 23270976, 'steps': 121202, 'loss/train': 1.1551038026809692} 08/31/2021 11:16:07 - INFO - __main__ - Step 121204: {'lr': 4.527051502546392e-05, 'samples': 23271168, 'steps': 121203, 'loss/train': 0.18173640966415405} 08/31/2021 11:16:08 - INFO - __main__ - Step 121205: {'lr': 4.526746947461277e-05, 'samples': 23271360, 'steps': 121204, 'loss/train': 0.6257135272026062} 08/31/2021 11:16:08 - INFO - __main__ - Step 121206: {'lr': 4.526442401601094e-05, 'samples': 23271552, 'steps': 121205, 'loss/train': 0.015906695276498795} 08/31/2021 11:16:10 - INFO - __main__ - Step 121207: {'lr': 4.526137864965979e-05, 'samples': 23271744, 'steps': 121206, 'loss/train': 0.06309977918863297} 08/31/2021 11:16:11 - INFO - __main__ - Step 121208: {'lr': 4.5258333375560704e-05, 'samples': 23271936, 'steps': 121207, 'loss/train': 0.5781004428863525} 08/31/2021 11:16:11 - INFO - __main__ - Step 121209: {'lr': 4.525528819371508e-05, 'samples': 23272128, 'steps': 121208, 'loss/train': 0.6885583996772766} 08/31/2021 11:16:11 - INFO - __main__ - Step 121210: {'lr': 4.5252243104124294e-05, 'samples': 23272320, 'steps': 121209, 'loss/train': 0.6407092809677124} 08/31/2021 11:16:12 - INFO - __main__ - Step 121211: {'lr': 4.524919810678965e-05, 'samples': 23272512, 'steps': 121210, 'loss/train': 1.0411157608032227} 08/31/2021 11:16:13 - INFO - __main__ - Step 121212: {'lr': 4.524615320171255e-05, 'samples': 23272704, 'steps': 121211, 'loss/train': 1.3026411533355713} 08/31/2021 11:16:14 - INFO - __main__ - Step 121213: {'lr': 4.5243108388894364e-05, 'samples': 23272896, 'steps': 121212, 'loss/train': 1.0303221940994263} 08/31/2021 11:16:14 - INFO - __main__ - Step 121214: {'lr': 4.5240063668336466e-05, 'samples': 23273088, 'steps': 121213, 'loss/train': 0.596285343170166} 08/31/2021 11:16:14 - INFO - __main__ - Step 121215: {'lr': 4.523701904004027e-05, 'samples': 23273280, 'steps': 121214, 'loss/train': 1.8477243185043335} 08/31/2021 11:16:15 - INFO - __main__ - Step 121216: {'lr': 4.523397450400707e-05, 'samples': 23273472, 'steps': 121215, 'loss/train': 1.4695754051208496} 08/31/2021 11:16:17 - INFO - __main__ - Step 121217: {'lr': 4.5230930060238316e-05, 'samples': 23273664, 'steps': 121216, 'loss/train': 1.480837345123291} 08/31/2021 11:16:17 - INFO - __main__ - Step 121218: {'lr': 4.5227885708735317e-05, 'samples': 23273856, 'steps': 121217, 'loss/train': 1.2047812938690186} 08/31/2021 11:16:18 - INFO - __main__ - Step 121219: {'lr': 4.522484144949951e-05, 'samples': 23274048, 'steps': 121218, 'loss/train': 1.0123802423477173} 08/31/2021 11:16:18 - INFO - __main__ - Step 121220: {'lr': 4.52217972825322e-05, 'samples': 23274240, 'steps': 121219, 'loss/train': 0.1924009919166565} 08/31/2021 11:16:18 - INFO - __main__ - Step 121221: {'lr': 4.521875320783481e-05, 'samples': 23274432, 'steps': 121220, 'loss/train': 0.9138984680175781} 08/31/2021 11:16:19 - INFO - __main__ - Step 121222: {'lr': 4.521570922540866e-05, 'samples': 23274624, 'steps': 121221, 'loss/train': 0.3706428110599518} 08/31/2021 11:16:20 - INFO - __main__ - Step 121223: {'lr': 4.5212665335255226e-05, 'samples': 23274816, 'steps': 121222, 'loss/train': 1.4730380773544312} 08/31/2021 11:16:21 - INFO - __main__ - Step 121224: {'lr': 4.520962153737576e-05, 'samples': 23275008, 'steps': 121223, 'loss/train': 0.8507108092308044} 08/31/2021 11:16:21 - INFO - __main__ - Step 121225: {'lr': 4.520657783177165e-05, 'samples': 23275200, 'steps': 121224, 'loss/train': 1.2783006429672241} 08/31/2021 11:16:21 - INFO - __main__ - Step 121226: {'lr': 4.520353421844434e-05, 'samples': 23275392, 'steps': 121225, 'loss/train': 1.655778408050537} 08/31/2021 11:16:22 - INFO - __main__ - Step 121227: {'lr': 4.5200490697395126e-05, 'samples': 23275584, 'steps': 121226, 'loss/train': 0.8878579139709473} 08/31/2021 11:16:23 - INFO - __main__ - Step 121228: {'lr': 4.5197447268625404e-05, 'samples': 23275776, 'steps': 121227, 'loss/train': 1.4656239748001099} 08/31/2021 11:16:23 - INFO - __main__ - Step 121229: {'lr': 4.519440393213656e-05, 'samples': 23275968, 'steps': 121228, 'loss/train': 1.1352964639663696} 08/31/2021 11:16:24 - INFO - __main__ - Step 121230: {'lr': 4.519136068792995e-05, 'samples': 23276160, 'steps': 121229, 'loss/train': 1.0310760736465454} 08/31/2021 11:16:24 - INFO - __main__ - Step 121231: {'lr': 4.5188317536006964e-05, 'samples': 23276352, 'steps': 121230, 'loss/train': 1.0999360084533691} 08/31/2021 11:16:25 - INFO - __main__ - Step 121232: {'lr': 4.518527447636897e-05, 'samples': 23276544, 'steps': 121231, 'loss/train': 0.914311408996582} 08/31/2021 11:16:26 - INFO - __main__ - Step 121233: {'lr': 4.518223150901732e-05, 'samples': 23276736, 'steps': 121232, 'loss/train': 0.6833828687667847} 08/31/2021 11:16:27 - INFO - __main__ - Step 121234: {'lr': 4.5179188633953397e-05, 'samples': 23276928, 'steps': 121233, 'loss/train': 0.9940169453620911} 08/31/2021 11:16:27 - INFO - __main__ - Step 121235: {'lr': 4.517614585117855e-05, 'samples': 23277120, 'steps': 121234, 'loss/train': 1.1873327493667603} 08/31/2021 11:16:27 - INFO - __main__ - Step 121236: {'lr': 4.517310316069426e-05, 'samples': 23277312, 'steps': 121235, 'loss/train': 0.424048513174057} 08/31/2021 11:16:28 - INFO - __main__ - Step 121237: {'lr': 4.517006056250175e-05, 'samples': 23277504, 'steps': 121236, 'loss/train': 0.7854031920433044} 08/31/2021 11:16:29 - INFO - __main__ - Step 121238: {'lr': 4.516701805660242e-05, 'samples': 23277696, 'steps': 121237, 'loss/train': 2.001997470855713} 08/31/2021 11:16:30 - INFO - __main__ - Step 121239: {'lr': 4.516397564299771e-05, 'samples': 23277888, 'steps': 121238, 'loss/train': 0.8235622048377991} 08/31/2021 11:16:30 - INFO - __main__ - Step 121240: {'lr': 4.516093332168891e-05, 'samples': 23278080, 'steps': 121239, 'loss/train': 1.0620752573013306} 08/31/2021 11:16:30 - INFO - __main__ - Step 121241: {'lr': 4.515789109267746e-05, 'samples': 23278272, 'steps': 121240, 'loss/train': 0.9236636757850647} 08/31/2021 11:16:31 - INFO - __main__ - Step 121242: {'lr': 4.515484895596469e-05, 'samples': 23278464, 'steps': 121241, 'loss/train': 0.12376432865858078} 08/31/2021 11:16:32 - INFO - __main__ - Step 121243: {'lr': 4.5151806911552016e-05, 'samples': 23278656, 'steps': 121242, 'loss/train': 0.8056126832962036} 08/31/2021 11:16:32 - INFO - __main__ - Step 121244: {'lr': 4.514876495944076e-05, 'samples': 23278848, 'steps': 121243, 'loss/train': 0.9942384958267212} 08/31/2021 11:16:33 - INFO - __main__ - Step 121245: {'lr': 4.5145723099632305e-05, 'samples': 23279040, 'steps': 121244, 'loss/train': 0.470283567905426} 08/31/2021 11:16:33 - INFO - __main__ - Step 121246: {'lr': 4.514268133212801e-05, 'samples': 23279232, 'steps': 121245, 'loss/train': 1.427000880241394} 08/31/2021 11:16:33 - INFO - __main__ - Step 121247: {'lr': 4.5139639656929274e-05, 'samples': 23279424, 'steps': 121246, 'loss/train': 1.128699541091919} 08/31/2021 11:16:35 - INFO - __main__ - Step 121248: {'lr': 4.513659807403744e-05, 'samples': 23279616, 'steps': 121247, 'loss/train': 1.1789085865020752} 08/31/2021 11:16:35 - INFO - __main__ - Step 121249: {'lr': 4.5133556583453916e-05, 'samples': 23279808, 'steps': 121248, 'loss/train': 1.1054517030715942} 08/31/2021 11:16:36 - INFO - __main__ - Step 121250: {'lr': 4.5130515185180103e-05, 'samples': 23280000, 'steps': 121249, 'loss/train': 0.4378548860549927} 08/31/2021 11:16:36 - INFO - __main__ - Step 121251: {'lr': 4.512747387921728e-05, 'samples': 23280192, 'steps': 121250, 'loss/train': 1.3601138591766357} 08/31/2021 11:16:36 - INFO - __main__ - Step 121252: {'lr': 4.5124432665566816e-05, 'samples': 23280384, 'steps': 121251, 'loss/train': 1.3574860095977783} 08/31/2021 11:16:39 - INFO - __main__ - Step 121253: {'lr': 4.512139154423015e-05, 'samples': 23280576, 'steps': 121252, 'loss/train': 1.0571171045303345} 08/31/2021 11:16:39 - INFO - __main__ - Step 121254: {'lr': 4.5118350515208625e-05, 'samples': 23280768, 'steps': 121253, 'loss/train': 1.4599510431289673} 08/31/2021 11:16:39 - INFO - __main__ - Step 121255: {'lr': 4.51153095785036e-05, 'samples': 23280960, 'steps': 121254, 'loss/train': 1.2154122591018677} 08/31/2021 11:16:40 - INFO - __main__ - Step 121256: {'lr': 4.5112268734116446e-05, 'samples': 23281152, 'steps': 121255, 'loss/train': 0.7644476294517517} 08/31/2021 11:16:40 - INFO - __main__ - Step 121257: {'lr': 4.5109227982048555e-05, 'samples': 23281344, 'steps': 121256, 'loss/train': 1.4857168197631836} 08/31/2021 11:16:40 - INFO - __main__ - Step 121258: {'lr': 4.510618732230129e-05, 'samples': 23281536, 'steps': 121257, 'loss/train': 1.3791857957839966} 08/31/2021 11:16:42 - INFO - __main__ - Step 121259: {'lr': 4.510314675487598e-05, 'samples': 23281728, 'steps': 121258, 'loss/train': 0.26255908608436584} 08/31/2021 11:16:42 - INFO - __main__ - Step 121260: {'lr': 4.510010627977407e-05, 'samples': 23281920, 'steps': 121259, 'loss/train': 1.0455061197280884} 08/31/2021 11:16:43 - INFO - __main__ - Step 121261: {'lr': 4.5097065896996856e-05, 'samples': 23282112, 'steps': 121260, 'loss/train': 1.0187995433807373} 08/31/2021 11:16:43 - INFO - __main__ - Step 121262: {'lr': 4.5094025606545766e-05, 'samples': 23282304, 'steps': 121261, 'loss/train': 0.48040223121643066} 08/31/2021 11:16:43 - INFO - __main__ - Step 121263: {'lr': 4.5090985408422216e-05, 'samples': 23282496, 'steps': 121262, 'loss/train': 1.211746096611023} 08/31/2021 11:16:46 - INFO - __main__ - Step 121264: {'lr': 4.508794530262744e-05, 'samples': 23282688, 'steps': 121263, 'loss/train': 0.9967718124389648} 08/31/2021 11:16:46 - INFO - __main__ - Step 121265: {'lr': 4.508490528916287e-05, 'samples': 23282880, 'steps': 121264, 'loss/train': 0.7613903880119324} 08/31/2021 11:16:47 - INFO - __main__ - Step 121266: {'lr': 4.5081865368029856e-05, 'samples': 23283072, 'steps': 121265, 'loss/train': 1.1104555130004883} 08/31/2021 11:16:47 - INFO - __main__ - Step 121267: {'lr': 4.5078825539229815e-05, 'samples': 23283264, 'steps': 121266, 'loss/train': 1.450181007385254} 08/31/2021 11:16:47 - INFO - __main__ - Step 121268: {'lr': 4.5075785802764083e-05, 'samples': 23283456, 'steps': 121267, 'loss/train': 1.6189063787460327} 08/31/2021 11:16:48 - INFO - __main__ - Step 121269: {'lr': 4.507274615863405e-05, 'samples': 23283648, 'steps': 121268, 'loss/train': 0.3076990246772766} 08/31/2021 11:16:49 - INFO - __main__ - Step 121270: {'lr': 4.5069706606841064e-05, 'samples': 23283840, 'steps': 121269, 'loss/train': 1.2811554670333862} 08/31/2021 11:16:50 - INFO - __main__ - Step 121271: {'lr': 4.506666714738653e-05, 'samples': 23284032, 'steps': 121270, 'loss/train': 1.4420682191848755} 08/31/2021 11:16:50 - INFO - __main__ - Step 121272: {'lr': 4.506362778027176e-05, 'samples': 23284224, 'steps': 121271, 'loss/train': 1.3253793716430664} 08/31/2021 11:16:50 - INFO - __main__ - Step 121273: {'lr': 4.5060588505498184e-05, 'samples': 23284416, 'steps': 121272, 'loss/train': 1.1461272239685059} 08/31/2021 11:16:51 - INFO - __main__ - Step 121274: {'lr': 4.505754932306713e-05, 'samples': 23284608, 'steps': 121273, 'loss/train': 1.1608740091323853} 08/31/2021 11:16:52 - INFO - __main__ - Step 121275: {'lr': 4.505451023297999e-05, 'samples': 23284800, 'steps': 121274, 'loss/train': 1.3335270881652832} 08/31/2021 11:16:53 - INFO - __main__ - Step 121276: {'lr': 4.505147123523812e-05, 'samples': 23284992, 'steps': 121275, 'loss/train': 1.1848478317260742} 08/31/2021 11:16:53 - INFO - __main__ - Step 121277: {'lr': 4.504843232984296e-05, 'samples': 23285184, 'steps': 121276, 'loss/train': 0.5432161092758179} 08/31/2021 11:16:54 - INFO - __main__ - Step 121278: {'lr': 4.5045393516795735e-05, 'samples': 23285376, 'steps': 121277, 'loss/train': 0.7266426682472229} 08/31/2021 11:16:54 - INFO - __main__ - Step 121279: {'lr': 4.504235479609792e-05, 'samples': 23285568, 'steps': 121278, 'loss/train': 1.059431552886963} 08/31/2021 11:16:56 - INFO - __main__ - Step 121280: {'lr': 4.5039316167750835e-05, 'samples': 23285760, 'steps': 121279, 'loss/train': 0.3556399941444397} 08/31/2021 11:16:56 - INFO - __main__ - Step 121281: {'lr': 4.503627763175588e-05, 'samples': 23285952, 'steps': 121280, 'loss/train': 1.376598834991455} 08/31/2021 11:16:56 - INFO - __main__ - Step 121282: {'lr': 4.503323918811442e-05, 'samples': 23286144, 'steps': 121281, 'loss/train': 1.5021536350250244} 08/31/2021 11:16:57 - INFO - __main__ - Step 121283: {'lr': 4.503020083682782e-05, 'samples': 23286336, 'steps': 121282, 'loss/train': 1.3855376243591309} 08/31/2021 11:16:57 - INFO - __main__ - Step 121284: {'lr': 4.5027162577897435e-05, 'samples': 23286528, 'steps': 121283, 'loss/train': 1.2028558254241943} 08/31/2021 11:16:57 - INFO - __main__ - Step 121285: {'lr': 4.502412441132467e-05, 'samples': 23286720, 'steps': 121284, 'loss/train': 0.45475026965141296} 08/31/2021 11:16:59 - INFO - __main__ - Step 121286: {'lr': 4.5021086337110856e-05, 'samples': 23286912, 'steps': 121285, 'loss/train': 0.19613182544708252} 08/31/2021 11:16:59 - INFO - __main__ - Step 121287: {'lr': 4.501804835525739e-05, 'samples': 23287104, 'steps': 121286, 'loss/train': 1.0716265439987183} 08/31/2021 11:17:00 - INFO - __main__ - Step 121288: {'lr': 4.501501046576562e-05, 'samples': 23287296, 'steps': 121287, 'loss/train': 1.3931344747543335} 08/31/2021 11:17:00 - INFO - __main__ - Step 121289: {'lr': 4.501197266863691e-05, 'samples': 23287488, 'steps': 121288, 'loss/train': 0.4549936354160309} 08/31/2021 11:17:00 - INFO - __main__ - Step 121290: {'lr': 4.500893496387271e-05, 'samples': 23287680, 'steps': 121289, 'loss/train': 1.3429330587387085} 08/31/2021 11:17:02 - INFO - __main__ - Step 121291: {'lr': 4.500589735147428e-05, 'samples': 23287872, 'steps': 121290, 'loss/train': 1.0826573371887207} 08/31/2021 11:17:02 - INFO - __main__ - Step 121292: {'lr': 4.5002859831443005e-05, 'samples': 23288064, 'steps': 121291, 'loss/train': 0.8738616108894348} 08/31/2021 11:17:03 - INFO - __main__ - Step 121293: {'lr': 4.499982240378028e-05, 'samples': 23288256, 'steps': 121292, 'loss/train': 0.9363855719566345} 08/31/2021 11:17:03 - INFO - __main__ - Step 121294: {'lr': 4.499678506848748e-05, 'samples': 23288448, 'steps': 121293, 'loss/train': 0.43506622314453125} 08/31/2021 11:17:03 - INFO - __main__ - Step 121295: {'lr': 4.499374782556598e-05, 'samples': 23288640, 'steps': 121294, 'loss/train': 1.5554088354110718} 08/31/2021 11:17:05 - INFO - __main__ - Step 121296: {'lr': 4.4990710675017114e-05, 'samples': 23288832, 'steps': 121295, 'loss/train': 1.2019213438034058} 08/31/2021 11:17:06 - INFO - __main__ - Step 121297: {'lr': 4.498767361684228e-05, 'samples': 23289024, 'steps': 121296, 'loss/train': 1.5970985889434814} 08/31/2021 11:17:06 - INFO - __main__ - Step 121298: {'lr': 4.4984636651042826e-05, 'samples': 23289216, 'steps': 121297, 'loss/train': 0.6528607606887817} 08/31/2021 11:17:07 - INFO - __main__ - Step 121299: {'lr': 4.498159977762012e-05, 'samples': 23289408, 'steps': 121298, 'loss/train': 1.311157464981079} 08/31/2021 11:17:07 - INFO - __main__ - Step 121300: {'lr': 4.497856299657557e-05, 'samples': 23289600, 'steps': 121299, 'loss/train': 0.01660250499844551} 08/31/2021 11:17:07 - INFO - __main__ - Step 121301: {'lr': 4.497552630791049e-05, 'samples': 23289792, 'steps': 121300, 'loss/train': 0.015672851353883743} 08/31/2021 11:17:09 - INFO - __main__ - Step 121302: {'lr': 4.4972489711626294e-05, 'samples': 23289984, 'steps': 121301, 'loss/train': 0.6671591401100159} 08/31/2021 11:17:09 - INFO - __main__ - Step 121303: {'lr': 4.496945320772433e-05, 'samples': 23290176, 'steps': 121302, 'loss/train': 0.7192825078964233} 08/31/2021 11:17:10 - INFO - __main__ - Step 121304: {'lr': 4.4966416796206024e-05, 'samples': 23290368, 'steps': 121303, 'loss/train': 1.1389260292053223} 08/31/2021 11:17:10 - INFO - __main__ - Step 121305: {'lr': 4.49633804770726e-05, 'samples': 23290560, 'steps': 121304, 'loss/train': 1.0542349815368652} 08/31/2021 11:17:10 - INFO - __main__ - Step 121306: {'lr': 4.4960344250325555e-05, 'samples': 23290752, 'steps': 121305, 'loss/train': 0.8544419407844543} 08/31/2021 11:17:12 - INFO - __main__ - Step 121307: {'lr': 4.495730811596618e-05, 'samples': 23290944, 'steps': 121306, 'loss/train': 1.0322176218032837} 08/31/2021 11:17:12 - INFO - __main__ - Step 121308: {'lr': 4.495427207399591e-05, 'samples': 23291136, 'steps': 121307, 'loss/train': 1.4214832782745361} 08/31/2021 11:17:13 - INFO - __main__ - Step 121309: {'lr': 4.4951236124416064e-05, 'samples': 23291328, 'steps': 121308, 'loss/train': 0.9128009080886841} 08/31/2021 11:17:13 - INFO - __main__ - Step 121310: {'lr': 4.494820026722801e-05, 'samples': 23291520, 'steps': 121309, 'loss/train': 1.395885944366455} 08/31/2021 11:17:13 - INFO - __main__ - Step 121311: {'lr': 4.4945164502433164e-05, 'samples': 23291712, 'steps': 121310, 'loss/train': 0.6756235957145691} 08/31/2021 11:17:14 - INFO - __main__ - Step 121312: {'lr': 4.494212883003285e-05, 'samples': 23291904, 'steps': 121311, 'loss/train': 0.7894525527954102} 08/31/2021 11:17:15 - INFO - __main__ - Step 121313: {'lr': 4.493909325002846e-05, 'samples': 23292096, 'steps': 121312, 'loss/train': 0.3135298192501068} 08/31/2021 11:17:16 - INFO - __main__ - Step 121314: {'lr': 4.493605776242132e-05, 'samples': 23292288, 'steps': 121313, 'loss/train': 0.2704143226146698} 08/31/2021 11:17:16 - INFO - __main__ - Step 121315: {'lr': 4.4933022367212864e-05, 'samples': 23292480, 'steps': 121314, 'loss/train': 1.0735939741134644} 08/31/2021 11:17:16 - INFO - __main__ - Step 121316: {'lr': 4.492998706440438e-05, 'samples': 23292672, 'steps': 121315, 'loss/train': 0.9325059056282043} 08/31/2021 11:17:17 - INFO - __main__ - Step 121317: {'lr': 4.4926951853997365e-05, 'samples': 23292864, 'steps': 121316, 'loss/train': 0.7229158282279968} 08/31/2021 11:17:19 - INFO - __main__ - Step 121318: {'lr': 4.4923916735993056e-05, 'samples': 23293056, 'steps': 121317, 'loss/train': 0.38578662276268005} 08/31/2021 11:17:19 - INFO - __main__ - Step 121319: {'lr': 4.492088171039285e-05, 'samples': 23293248, 'steps': 121318, 'loss/train': 0.3966636061668396} 08/31/2021 11:17:20 - INFO - __main__ - Step 121320: {'lr': 4.491784677719812e-05, 'samples': 23293440, 'steps': 121319, 'loss/train': 1.0602067708969116} 08/31/2021 11:17:20 - INFO - __main__ - Step 121321: {'lr': 4.4914811936410254e-05, 'samples': 23293632, 'steps': 121320, 'loss/train': 1.3966426849365234} 08/31/2021 11:17:20 - INFO - __main__ - Step 121322: {'lr': 4.4911777188030604e-05, 'samples': 23293824, 'steps': 121321, 'loss/train': 0.9945131540298462} 08/31/2021 11:17:22 - INFO - __main__ - Step 121323: {'lr': 4.490874253206056e-05, 'samples': 23294016, 'steps': 121322, 'loss/train': 1.3861682415008545} 08/31/2021 11:17:22 - INFO - __main__ - Step 121324: {'lr': 4.490570796850146e-05, 'samples': 23294208, 'steps': 121323, 'loss/train': 0.7836046814918518} 08/31/2021 11:17:23 - INFO - __main__ - Step 121325: {'lr': 4.490267349735469e-05, 'samples': 23294400, 'steps': 121324, 'loss/train': 0.750959038734436} 08/31/2021 11:17:23 - INFO - __main__ - Step 121326: {'lr': 4.4899639118621604e-05, 'samples': 23294592, 'steps': 121325, 'loss/train': 0.952131986618042} 08/31/2021 11:17:23 - INFO - __main__ - Step 121327: {'lr': 4.489660483230357e-05, 'samples': 23294784, 'steps': 121326, 'loss/train': 1.2788670063018799} 08/31/2021 11:17:25 - INFO - __main__ - Step 121328: {'lr': 4.489357063840197e-05, 'samples': 23294976, 'steps': 121327, 'loss/train': 1.2979063987731934} 08/31/2021 11:17:26 - INFO - __main__ - Step 121329: {'lr': 4.489053653691816e-05, 'samples': 23295168, 'steps': 121328, 'loss/train': 0.594839870929718} 08/31/2021 11:17:26 - INFO - __main__ - Step 121330: {'lr': 4.488750252785351e-05, 'samples': 23295360, 'steps': 121329, 'loss/train': 1.6134477853775024} 08/31/2021 11:17:26 - INFO - __main__ - Step 121331: {'lr': 4.4884468611209426e-05, 'samples': 23295552, 'steps': 121330, 'loss/train': 1.0287498235702515} 08/31/2021 11:17:27 - INFO - __main__ - Step 121332: {'lr': 4.4881434786987195e-05, 'samples': 23295744, 'steps': 121331, 'loss/train': 1.2413889169692993} 08/31/2021 11:17:28 - INFO - __main__ - Step 121333: {'lr': 4.4878401055188225e-05, 'samples': 23295936, 'steps': 121332, 'loss/train': 1.377355933189392} 08/31/2021 11:17:29 - INFO - __main__ - Step 121334: {'lr': 4.4875367415813885e-05, 'samples': 23296128, 'steps': 121333, 'loss/train': 1.2694530487060547} 08/31/2021 11:17:29 - INFO - __main__ - Step 121335: {'lr': 4.4872333868865524e-05, 'samples': 23296320, 'steps': 121334, 'loss/train': 1.3318675756454468} 08/31/2021 11:17:29 - INFO - __main__ - Step 121336: {'lr': 4.486930041434453e-05, 'samples': 23296512, 'steps': 121335, 'loss/train': 1.2127395868301392} 08/31/2021 11:17:30 - INFO - __main__ - Step 121337: {'lr': 4.4866267052252274e-05, 'samples': 23296704, 'steps': 121336, 'loss/train': 0.6869686841964722} 08/31/2021 11:17:30 - INFO - __main__ - Step 121338: {'lr': 4.486323378259011e-05, 'samples': 23296896, 'steps': 121337, 'loss/train': 1.23032808303833} 08/31/2021 11:17:32 - INFO - __main__ - Step 121339: {'lr': 4.486020060535942e-05, 'samples': 23297088, 'steps': 121338, 'loss/train': 0.776809573173523} 08/31/2021 11:17:33 - INFO - __main__ - Step 121340: {'lr': 4.4857167520561544e-05, 'samples': 23297280, 'steps': 121339, 'loss/train': 1.1600695848464966} 08/31/2021 11:17:33 - INFO - __main__ - Step 121341: {'lr': 4.4854134528197834e-05, 'samples': 23297472, 'steps': 121340, 'loss/train': 1.3486528396606445} 08/31/2021 11:17:33 - INFO - __main__ - Step 121342: {'lr': 4.485110162826972e-05, 'samples': 23297664, 'steps': 121341, 'loss/train': 0.44198668003082275} 08/31/2021 11:17:34 - INFO - __main__ - Step 121343: {'lr': 4.484806882077852e-05, 'samples': 23297856, 'steps': 121342, 'loss/train': 0.40154609084129333} 08/31/2021 11:17:34 - INFO - __main__ - Step 121344: {'lr': 4.4845036105725684e-05, 'samples': 23298048, 'steps': 121343, 'loss/train': 1.362595796585083} 08/31/2021 11:17:35 - INFO - __main__ - Step 121345: {'lr': 4.484200348311246e-05, 'samples': 23298240, 'steps': 121344, 'loss/train': 0.054330307990312576} 08/31/2021 11:17:36 - INFO - __main__ - Step 121346: {'lr': 4.4838970952940235e-05, 'samples': 23298432, 'steps': 121345, 'loss/train': 0.941700279712677} 08/31/2021 11:17:36 - INFO - __main__ - Step 121347: {'lr': 4.4835938515210426e-05, 'samples': 23298624, 'steps': 121346, 'loss/train': 1.8062474727630615} 08/31/2021 11:17:37 - INFO - __main__ - Step 121348: {'lr': 4.4832906169924356e-05, 'samples': 23298816, 'steps': 121347, 'loss/train': 0.7568572759628296} 08/31/2021 11:17:37 - INFO - __main__ - Step 121349: {'lr': 4.482987391708343e-05, 'samples': 23299008, 'steps': 121348, 'loss/train': 1.1479791402816772} 08/31/2021 11:17:38 - INFO - __main__ - Step 121350: {'lr': 4.4826841756689e-05, 'samples': 23299200, 'steps': 121349, 'loss/train': 1.1004810333251953} 08/31/2021 11:17:39 - INFO - __main__ - Step 121351: {'lr': 4.482380968874242e-05, 'samples': 23299392, 'steps': 121350, 'loss/train': 0.023884490132331848} 08/31/2021 11:17:39 - INFO - __main__ - Step 121352: {'lr': 4.482077771324508e-05, 'samples': 23299584, 'steps': 121351, 'loss/train': 1.1303346157073975} 08/31/2021 11:17:40 - INFO - __main__ - Step 121353: {'lr': 4.481774583019832e-05, 'samples': 23299776, 'steps': 121352, 'loss/train': 1.0249121189117432} 08/31/2021 11:17:40 - INFO - __main__ - Step 121354: {'lr': 4.4814714039603494e-05, 'samples': 23299968, 'steps': 121353, 'loss/train': 1.3961092233657837} 08/31/2021 11:17:41 - INFO - __main__ - Step 121355: {'lr': 4.481168234146202e-05, 'samples': 23300160, 'steps': 121354, 'loss/train': 0.7681298851966858} 08/31/2021 11:17:42 - INFO - __main__ - Step 121356: {'lr': 4.4808650735775224e-05, 'samples': 23300352, 'steps': 121355, 'loss/train': 1.5452778339385986} 08/31/2021 11:17:42 - INFO - __main__ - Step 121357: {'lr': 4.480561922254456e-05, 'samples': 23300544, 'steps': 121356, 'loss/train': 1.3832169771194458} 08/31/2021 11:17:43 - INFO - __main__ - Step 121358: {'lr': 4.480258780177124e-05, 'samples': 23300736, 'steps': 121357, 'loss/train': 0.9411364793777466} 08/31/2021 11:17:43 - INFO - __main__ - Step 121359: {'lr': 4.4799556473456706e-05, 'samples': 23300928, 'steps': 121358, 'loss/train': 1.495985507965088} 08/31/2021 11:17:45 - INFO - __main__ - Step 121360: {'lr': 4.4796525237602356e-05, 'samples': 23301120, 'steps': 121359, 'loss/train': 0.9791582226753235} 08/31/2021 11:17:45 - INFO - __main__ - Step 121361: {'lr': 4.479349409420949e-05, 'samples': 23301312, 'steps': 121360, 'loss/train': 1.448973536491394} 08/31/2021 11:17:45 - INFO - __main__ - Step 121362: {'lr': 4.4790463043279524e-05, 'samples': 23301504, 'steps': 121361, 'loss/train': 0.8954208493232727} 08/31/2021 11:17:46 - INFO - __main__ - Step 121363: {'lr': 4.4787432084813814e-05, 'samples': 23301696, 'steps': 121362, 'loss/train': 1.2530441284179688} 08/31/2021 11:17:46 - INFO - __main__ - Step 121364: {'lr': 4.478440121881372e-05, 'samples': 23301888, 'steps': 121363, 'loss/train': 0.8477299213409424} 08/31/2021 11:17:47 - INFO - __main__ - Step 121365: {'lr': 4.478137044528058e-05, 'samples': 23302080, 'steps': 121364, 'loss/train': 1.4725250005722046} 08/31/2021 11:17:48 - INFO - __main__ - Step 121366: {'lr': 4.477833976421583e-05, 'samples': 23302272, 'steps': 121365, 'loss/train': 0.8802347183227539} 08/31/2021 11:17:48 - INFO - __main__ - Step 121367: {'lr': 4.477530917562075e-05, 'samples': 23302464, 'steps': 121366, 'loss/train': 1.1198550462722778} 08/31/2021 11:17:49 - INFO - __main__ - Step 121368: {'lr': 4.4772278679496794e-05, 'samples': 23302656, 'steps': 121367, 'loss/train': 1.462764024734497} 08/31/2021 11:17:49 - INFO - __main__ - Step 121369: {'lr': 4.476924827584525e-05, 'samples': 23302848, 'steps': 121368, 'loss/train': 1.148077368736267} 08/31/2021 11:17:52 - INFO - __main__ - Step 121370: {'lr': 4.476621796466751e-05, 'samples': 23303040, 'steps': 121369, 'loss/train': 1.1069965362548828} 08/31/2021 11:17:52 - INFO - __main__ - Step 121371: {'lr': 4.476318774596502e-05, 'samples': 23303232, 'steps': 121370, 'loss/train': 1.1338534355163574} 08/31/2021 11:17:53 - INFO - __main__ - Step 121372: {'lr': 4.4760157619739036e-05, 'samples': 23303424, 'steps': 121371, 'loss/train': 0.6355109214782715} 08/31/2021 11:17:53 - INFO - __main__ - Step 121373: {'lr': 4.475712758599093e-05, 'samples': 23303616, 'steps': 121372, 'loss/train': 2.0793721675872803} 08/31/2021 11:17:53 - INFO - __main__ - Step 121374: {'lr': 4.47540976447221e-05, 'samples': 23303808, 'steps': 121373, 'loss/train': 0.2571808099746704} 08/31/2021 11:17:54 - INFO - __main__ - Step 121375: {'lr': 4.475106779593391e-05, 'samples': 23304000, 'steps': 121374, 'loss/train': 0.25690966844558716} 08/31/2021 11:17:54 - INFO - __main__ - Step 121376: {'lr': 4.474803803962771e-05, 'samples': 23304192, 'steps': 121375, 'loss/train': 0.12901704013347626} 08/31/2021 11:17:56 - INFO - __main__ - Step 121377: {'lr': 4.4745008375804864e-05, 'samples': 23304384, 'steps': 121376, 'loss/train': 0.7823437452316284} 08/31/2021 11:17:56 - INFO - __main__ - Step 121378: {'lr': 4.474197880446679e-05, 'samples': 23304576, 'steps': 121377, 'loss/train': 0.7072463035583496} 08/31/2021 11:17:57 - INFO - __main__ - Step 121379: {'lr': 4.4738949325614786e-05, 'samples': 23304768, 'steps': 121378, 'loss/train': 0.6562110185623169} 08/31/2021 11:17:57 - INFO - __main__ - Step 121380: {'lr': 4.473591993925025e-05, 'samples': 23304960, 'steps': 121379, 'loss/train': 1.3029193878173828} 08/31/2021 11:17:57 - INFO - __main__ - Step 121381: {'lr': 4.473289064537453e-05, 'samples': 23305152, 'steps': 121380, 'loss/train': 1.0182840824127197} 08/31/2021 11:17:59 - INFO - __main__ - Step 121382: {'lr': 4.472986144398902e-05, 'samples': 23305344, 'steps': 121381, 'loss/train': 0.24513128399848938} 08/31/2021 11:17:59 - INFO - __main__ - Step 121383: {'lr': 4.472683233509506e-05, 'samples': 23305536, 'steps': 121382, 'loss/train': 1.460534691810608} 08/31/2021 11:18:00 - INFO - __main__ - Step 121384: {'lr': 4.472380331869408e-05, 'samples': 23305728, 'steps': 121383, 'loss/train': 0.9273485541343689} 08/31/2021 11:18:00 - INFO - __main__ - Step 121385: {'lr': 4.4720774394787335e-05, 'samples': 23305920, 'steps': 121384, 'loss/train': 0.8122192025184631} 08/31/2021 11:18:00 - INFO - __main__ - Step 121386: {'lr': 4.471774556337624e-05, 'samples': 23306112, 'steps': 121385, 'loss/train': 0.999779224395752} 08/31/2021 11:18:02 - INFO - __main__ - Step 121387: {'lr': 4.471471682446215e-05, 'samples': 23306304, 'steps': 121386, 'loss/train': 0.7818937301635742} 08/31/2021 11:18:02 - INFO - __main__ - Step 121388: {'lr': 4.471168817804644e-05, 'samples': 23306496, 'steps': 121387, 'loss/train': 1.9707367420196533} 08/31/2021 11:18:03 - INFO - __main__ - Step 121389: {'lr': 4.470865962413048e-05, 'samples': 23306688, 'steps': 121388, 'loss/train': 2.0173912048339844} 08/31/2021 11:18:03 - INFO - __main__ - Step 121390: {'lr': 4.4705631162715645e-05, 'samples': 23306880, 'steps': 121389, 'loss/train': 0.934874415397644} 08/31/2021 11:18:03 - INFO - __main__ - Step 121391: {'lr': 4.470260279380328e-05, 'samples': 23307072, 'steps': 121390, 'loss/train': 0.20280010998249054} 08/31/2021 11:18:04 - INFO - __main__ - Step 121392: {'lr': 4.469957451739473e-05, 'samples': 23307264, 'steps': 121391, 'loss/train': 1.3226622343063354} 08/31/2021 11:18:06 - INFO - __main__ - Step 121393: {'lr': 4.469654633349141e-05, 'samples': 23307456, 'steps': 121392, 'loss/train': 1.2172905206680298} 08/31/2021 11:18:06 - INFO - __main__ - Step 121394: {'lr': 4.469351824209464e-05, 'samples': 23307648, 'steps': 121393, 'loss/train': 1.3642804622650146} 08/31/2021 11:18:06 - INFO - __main__ - Step 121395: {'lr': 4.469049024320582e-05, 'samples': 23307840, 'steps': 121394, 'loss/train': 1.2779600620269775} 08/31/2021 11:18:07 - INFO - __main__ - Step 121396: {'lr': 4.4687462336826275e-05, 'samples': 23308032, 'steps': 121395, 'loss/train': 1.119670033454895} 08/31/2021 11:18:07 - INFO - __main__ - Step 121397: {'lr': 4.4684434522957425e-05, 'samples': 23308224, 'steps': 121396, 'loss/train': 0.9112069606781006} 08/31/2021 11:18:09 - INFO - __main__ - Step 121398: {'lr': 4.4681406801600626e-05, 'samples': 23308416, 'steps': 121397, 'loss/train': 1.4079678058624268} 08/31/2021 11:18:10 - INFO - __main__ - Step 121399: {'lr': 4.4678379172757186e-05, 'samples': 23308608, 'steps': 121398, 'loss/train': 1.4760092496871948} 08/31/2021 11:18:10 - INFO - __main__ - Step 121400: {'lr': 4.4675351636428466e-05, 'samples': 23308800, 'steps': 121399, 'loss/train': 0.662699818611145} 08/31/2021 11:18:10 - INFO - __main__ - Step 121401: {'lr': 4.467232419261591e-05, 'samples': 23308992, 'steps': 121400, 'loss/train': 0.5611758232116699} 08/31/2021 11:18:11 - INFO - __main__ - Step 121402: {'lr': 4.4669296841320786e-05, 'samples': 23309184, 'steps': 121401, 'loss/train': 0.7207245826721191} 08/31/2021 11:18:11 - INFO - __main__ - Step 121403: {'lr': 4.466626958254455e-05, 'samples': 23309376, 'steps': 121402, 'loss/train': 1.6978683471679688} 08/31/2021 11:18:13 - INFO - __main__ - Step 121404: {'lr': 4.4663242416288495e-05, 'samples': 23309568, 'steps': 121403, 'loss/train': 1.5741145610809326} 08/31/2021 11:18:13 - INFO - __main__ - Step 121405: {'lr': 4.466021534255402e-05, 'samples': 23309760, 'steps': 121404, 'loss/train': 1.192200779914856} 08/31/2021 11:18:14 - INFO - __main__ - Step 121406: {'lr': 4.46571883613425e-05, 'samples': 23309952, 'steps': 121405, 'loss/train': 0.15574398636817932} 08/31/2021 11:18:14 - INFO - __main__ - Step 121407: {'lr': 4.465416147265528e-05, 'samples': 23310144, 'steps': 121406, 'loss/train': 0.8452528715133667} 08/31/2021 11:18:14 - INFO - __main__ - Step 121408: {'lr': 4.46511346764937e-05, 'samples': 23310336, 'steps': 121407, 'loss/train': 0.03159884735941887} 08/31/2021 11:18:16 - INFO - __main__ - Step 121409: {'lr': 4.464810797285917e-05, 'samples': 23310528, 'steps': 121408, 'loss/train': 1.251468539237976} 08/31/2021 11:18:17 - INFO - __main__ - Step 121410: {'lr': 4.4645081361753045e-05, 'samples': 23310720, 'steps': 121409, 'loss/train': 0.8266119360923767} 08/31/2021 11:18:17 - INFO - __main__ - Step 121411: {'lr': 4.464205484317671e-05, 'samples': 23310912, 'steps': 121410, 'loss/train': 1.6469147205352783} 08/31/2021 11:18:17 - INFO - __main__ - Step 121412: {'lr': 4.4639028417131465e-05, 'samples': 23311104, 'steps': 121411, 'loss/train': 0.6623932123184204} 08/31/2021 11:18:18 - INFO - __main__ - Step 121413: {'lr': 4.4636002083618675e-05, 'samples': 23311296, 'steps': 121412, 'loss/train': 1.2044111490249634} 08/31/2021 11:18:19 - INFO - __main__ - Step 121414: {'lr': 4.4632975842639756e-05, 'samples': 23311488, 'steps': 121413, 'loss/train': 1.7174246311187744} 08/31/2021 11:18:20 - INFO - __main__ - Step 121415: {'lr': 4.4629949694196035e-05, 'samples': 23311680, 'steps': 121414, 'loss/train': 1.2015423774719238} 08/31/2021 11:18:20 - INFO - __main__ - Step 121416: {'lr': 4.462692363828891e-05, 'samples': 23311872, 'steps': 121415, 'loss/train': 0.026666831225156784} 08/31/2021 11:18:20 - INFO - __main__ - Step 121417: {'lr': 4.46238976749197e-05, 'samples': 23312064, 'steps': 121416, 'loss/train': 1.2309987545013428} 08/31/2021 11:18:21 - INFO - __main__ - Step 121418: {'lr': 4.46208718040898e-05, 'samples': 23312256, 'steps': 121417, 'loss/train': 0.6094028949737549} 08/31/2021 11:18:21 - INFO - __main__ - Step 121419: {'lr': 4.4617846025800574e-05, 'samples': 23312448, 'steps': 121418, 'loss/train': 1.1037828922271729} 08/31/2021 11:18:23 - INFO - __main__ - Step 121420: {'lr': 4.461482034005338e-05, 'samples': 23312640, 'steps': 121419, 'loss/train': 1.692427396774292} 08/31/2021 11:18:23 - INFO - __main__ - Step 121421: {'lr': 4.4611794746849565e-05, 'samples': 23312832, 'steps': 121420, 'loss/train': 1.5707114934921265} 08/31/2021 11:18:24 - INFO - __main__ - Step 121422: {'lr': 4.4608769246190506e-05, 'samples': 23313024, 'steps': 121421, 'loss/train': 0.5223127603530884} 08/31/2021 11:18:24 - INFO - __main__ - Step 121423: {'lr': 4.460574383807764e-05, 'samples': 23313216, 'steps': 121422, 'loss/train': 0.4159396290779114} 08/31/2021 11:18:24 - INFO - __main__ - Step 121424: {'lr': 4.4602718522512184e-05, 'samples': 23313408, 'steps': 121423, 'loss/train': 0.013938396237790585} 08/31/2021 11:18:25 - INFO - __main__ - Step 121425: {'lr': 4.459969329949559e-05, 'samples': 23313600, 'steps': 121424, 'loss/train': 0.724340558052063} 08/31/2021 11:18:27 - INFO - __main__ - Step 121426: {'lr': 4.4596668169029184e-05, 'samples': 23313792, 'steps': 121425, 'loss/train': 0.7417265772819519} 08/31/2021 11:18:27 - INFO - __main__ - Step 121427: {'lr': 4.459364313111436e-05, 'samples': 23313984, 'steps': 121426, 'loss/train': 1.1612602472305298} 08/31/2021 11:18:28 - INFO - __main__ - Step 121428: {'lr': 4.459061818575247e-05, 'samples': 23314176, 'steps': 121427, 'loss/train': 0.5918993949890137} 08/31/2021 11:18:28 - INFO - __main__ - Step 121429: {'lr': 4.4587593332944874e-05, 'samples': 23314368, 'steps': 121428, 'loss/train': 1.4137563705444336} 08/31/2021 11:18:28 - INFO - __main__ - Step 121430: {'lr': 4.458456857269294e-05, 'samples': 23314560, 'steps': 121429, 'loss/train': 1.0945559740066528} 08/31/2021 11:18:30 - INFO - __main__ - Step 121431: {'lr': 4.4581543904998025e-05, 'samples': 23314752, 'steps': 121430, 'loss/train': 0.4341030716896057} 08/31/2021 11:18:31 - INFO - __main__ - Step 121432: {'lr': 4.457851932986151e-05, 'samples': 23314944, 'steps': 121431, 'loss/train': 1.283787727355957} 08/31/2021 11:18:31 - INFO - __main__ - Step 121433: {'lr': 4.457549484728474e-05, 'samples': 23315136, 'steps': 121432, 'loss/train': 0.9906281232833862} 08/31/2021 11:18:31 - INFO - __main__ - Step 121434: {'lr': 4.457247045726914e-05, 'samples': 23315328, 'steps': 121433, 'loss/train': 0.3663182258605957} 08/31/2021 11:18:32 - INFO - __main__ - Step 121435: {'lr': 4.4569446159815954e-05, 'samples': 23315520, 'steps': 121434, 'loss/train': 0.7186176776885986} 08/31/2021 11:18:33 - INFO - __main__ - Step 121436: {'lr': 4.4566421954926606e-05, 'samples': 23315712, 'steps': 121435, 'loss/train': 0.345518559217453} 08/31/2021 11:18:34 - INFO - __main__ - Step 121437: {'lr': 4.456339784260246e-05, 'samples': 23315904, 'steps': 121436, 'loss/train': 0.020873669534921646} 08/31/2021 11:18:34 - INFO - __main__ - Step 121438: {'lr': 4.4560373822844865e-05, 'samples': 23316096, 'steps': 121437, 'loss/train': 1.355939269065857} 08/31/2021 11:18:34 - INFO - __main__ - Step 121439: {'lr': 4.4557349895655215e-05, 'samples': 23316288, 'steps': 121438, 'loss/train': 1.4484328031539917} 08/31/2021 11:18:35 - INFO - __main__ - Step 121440: {'lr': 4.455432606103485e-05, 'samples': 23316480, 'steps': 121439, 'loss/train': 1.056502103805542} 08/31/2021 11:18:36 - INFO - __main__ - Step 121441: {'lr': 4.4551302318985134e-05, 'samples': 23316672, 'steps': 121440, 'loss/train': 1.6521987915039062} 08/31/2021 11:18:37 - INFO - __main__ - Step 121442: {'lr': 4.454827866950742e-05, 'samples': 23316864, 'steps': 121441, 'loss/train': 1.6046984195709229} 08/31/2021 11:18:37 - INFO - __main__ - Step 121443: {'lr': 4.4545255112603075e-05, 'samples': 23317056, 'steps': 121442, 'loss/train': 0.9099099636077881} 08/31/2021 11:18:38 - INFO - __main__ - Step 121444: {'lr': 4.454223164827348e-05, 'samples': 23317248, 'steps': 121443, 'loss/train': 1.4224873781204224} 08/31/2021 11:18:38 - INFO - __main__ - Step 121445: {'lr': 4.4539208276520056e-05, 'samples': 23317440, 'steps': 121444, 'loss/train': 0.8525542616844177} 08/31/2021 11:18:39 - INFO - __main__ - Step 121446: {'lr': 4.453618499734402e-05, 'samples': 23317632, 'steps': 121445, 'loss/train': 1.8886815309524536} 08/31/2021 11:18:40 - INFO - __main__ - Step 121447: {'lr': 4.453316181074682e-05, 'samples': 23317824, 'steps': 121446, 'loss/train': 1.1297072172164917} 08/31/2021 11:18:40 - INFO - __main__ - Step 121448: {'lr': 4.453013871672978e-05, 'samples': 23318016, 'steps': 121447, 'loss/train': 1.7558094263076782} 08/31/2021 11:18:41 - INFO - __main__ - Step 121449: {'lr': 4.45271157152943e-05, 'samples': 23318208, 'steps': 121448, 'loss/train': 0.48263639211654663} 08/31/2021 11:18:41 - INFO - __main__ - Step 121450: {'lr': 4.452409280644176e-05, 'samples': 23318400, 'steps': 121449, 'loss/train': 0.603359580039978} 08/31/2021 11:18:43 - INFO - __main__ - Step 121451: {'lr': 4.452106999017347e-05, 'samples': 23318592, 'steps': 121450, 'loss/train': 0.8866795897483826} 08/31/2021 11:18:43 - INFO - __main__ - Step 121452: {'lr': 4.451804726649081e-05, 'samples': 23318784, 'steps': 121451, 'loss/train': 0.8196290135383606} 08/31/2021 11:18:43 - INFO - __main__ - Step 121453: {'lr': 4.451502463539517e-05, 'samples': 23318976, 'steps': 121452, 'loss/train': 0.8694579601287842} 08/31/2021 11:18:44 - INFO - __main__ - Step 121454: {'lr': 4.451200209688785e-05, 'samples': 23319168, 'steps': 121453, 'loss/train': 0.28077396750450134} 08/31/2021 11:18:44 - INFO - __main__ - Step 121455: {'lr': 4.4508979650970285e-05, 'samples': 23319360, 'steps': 121454, 'loss/train': 0.9197796583175659} 08/31/2021 11:18:44 - INFO - __main__ - Step 121456: {'lr': 4.450595729764384e-05, 'samples': 23319552, 'steps': 121455, 'loss/train': 1.3792901039123535} 08/31/2021 11:18:46 - INFO - __main__ - Step 121457: {'lr': 4.4502935036909806e-05, 'samples': 23319744, 'steps': 121456, 'loss/train': 1.0374191999435425} 08/31/2021 11:18:46 - INFO - __main__ - Step 121458: {'lr': 4.449991286876956e-05, 'samples': 23319936, 'steps': 121457, 'loss/train': 0.9560360908508301} 08/31/2021 11:18:47 - INFO - __main__ - Step 121459: {'lr': 4.44968907932245e-05, 'samples': 23320128, 'steps': 121458, 'loss/train': 1.2840602397918701} 08/31/2021 11:18:47 - INFO - __main__ - Step 121460: {'lr': 4.449386881027595e-05, 'samples': 23320320, 'steps': 121459, 'loss/train': 1.3250173330307007} 08/31/2021 11:18:47 - INFO - __main__ - Step 121461: {'lr': 4.449084691992528e-05, 'samples': 23320512, 'steps': 121460, 'loss/train': 0.39308419823646545} 08/31/2021 11:18:49 - INFO - __main__ - Step 121462: {'lr': 4.448782512217389e-05, 'samples': 23320704, 'steps': 121461, 'loss/train': 0.6760080456733704} 08/31/2021 11:18:50 - INFO - __main__ - Step 121463: {'lr': 4.44848034170231e-05, 'samples': 23320896, 'steps': 121462, 'loss/train': 1.482150912284851} 08/31/2021 11:18:50 - INFO - __main__ - Step 121464: {'lr': 4.448178180447429e-05, 'samples': 23321088, 'steps': 121463, 'loss/train': 1.2539721727371216} 08/31/2021 11:18:50 - INFO - __main__ - Step 121465: {'lr': 4.4478760284528825e-05, 'samples': 23321280, 'steps': 121464, 'loss/train': 0.9154008030891418} 08/31/2021 11:18:51 - INFO - __main__ - Step 121466: {'lr': 4.447573885718806e-05, 'samples': 23321472, 'steps': 121465, 'loss/train': 1.3356128931045532} 08/31/2021 11:18:52 - INFO - __main__ - Step 121467: {'lr': 4.447271752245341e-05, 'samples': 23321664, 'steps': 121466, 'loss/train': 0.03945210203528404} 08/31/2021 11:18:53 - INFO - __main__ - Step 121468: {'lr': 4.4469696280326124e-05, 'samples': 23321856, 'steps': 121467, 'loss/train': 1.4775961637496948} 08/31/2021 11:18:53 - INFO - __main__ - Step 121469: {'lr': 4.44666751308076e-05, 'samples': 23322048, 'steps': 121468, 'loss/train': 0.5882116556167603} 08/31/2021 11:18:54 - INFO - __main__ - Step 121470: {'lr': 4.446365407389924e-05, 'samples': 23322240, 'steps': 121469, 'loss/train': 0.03255607932806015} 08/31/2021 11:18:54 - INFO - __main__ - Step 121471: {'lr': 4.446063310960238e-05, 'samples': 23322432, 'steps': 121470, 'loss/train': 1.4928677082061768} 08/31/2021 11:18:55 - INFO - __main__ - Step 121472: {'lr': 4.4457612237918415e-05, 'samples': 23322624, 'steps': 121471, 'loss/train': 1.38158118724823} 08/31/2021 11:18:56 - INFO - __main__ - Step 121473: {'lr': 4.4454591458848645e-05, 'samples': 23322816, 'steps': 121472, 'loss/train': 0.5429848432540894} 08/31/2021 11:18:56 - INFO - __main__ - Step 121474: {'lr': 4.4451570772394475e-05, 'samples': 23323008, 'steps': 121473, 'loss/train': 1.3501684665679932} 08/31/2021 11:18:57 - INFO - __main__ - Step 121475: {'lr': 4.444855017855726e-05, 'samples': 23323200, 'steps': 121474, 'loss/train': 0.9967632293701172} 08/31/2021 11:18:57 - INFO - __main__ - Step 121476: {'lr': 4.444552967733834e-05, 'samples': 23323392, 'steps': 121475, 'loss/train': 1.192623257637024} 08/31/2021 11:18:59 - INFO - __main__ - Step 121477: {'lr': 4.4442509268739103e-05, 'samples': 23323584, 'steps': 121476, 'loss/train': 1.463945746421814} 08/31/2021 11:18:59 - INFO - __main__ - Step 121478: {'lr': 4.443948895276098e-05, 'samples': 23323776, 'steps': 121477, 'loss/train': 0.8298087120056152} 08/31/2021 11:19:00 - INFO - __main__ - Step 121479: {'lr': 4.4436468729405156e-05, 'samples': 23323968, 'steps': 121478, 'loss/train': 0.5134099721908569} 08/31/2021 11:19:00 - INFO - __main__ - Step 121480: {'lr': 4.44334485986731e-05, 'samples': 23324160, 'steps': 121479, 'loss/train': 0.928907036781311} 08/31/2021 11:19:00 - INFO - __main__ - Step 121481: {'lr': 4.443042856056617e-05, 'samples': 23324352, 'steps': 121480, 'loss/train': 0.9604138135910034} 08/31/2021 11:19:02 - INFO - __main__ - Step 121482: {'lr': 4.442740861508571e-05, 'samples': 23324544, 'steps': 121481, 'loss/train': 0.3479436933994293} 08/31/2021 11:19:03 - INFO - __main__ - Step 121483: {'lr': 4.442438876223309e-05, 'samples': 23324736, 'steps': 121482, 'loss/train': 1.1147335767745972} 08/31/2021 11:19:03 - INFO - __main__ - Step 121484: {'lr': 4.442136900200966e-05, 'samples': 23324928, 'steps': 121483, 'loss/train': 1.685962438583374} 08/31/2021 11:19:04 - INFO - __main__ - Step 121485: {'lr': 4.4418349334416795e-05, 'samples': 23325120, 'steps': 121484, 'loss/train': 0.56124347448349} 08/31/2021 11:19:04 - INFO - __main__ - Step 121486: {'lr': 4.441532975945583e-05, 'samples': 23325312, 'steps': 121485, 'loss/train': 1.289504051208496} 08/31/2021 11:19:06 - INFO - __main__ - Step 121487: {'lr': 4.441231027712819e-05, 'samples': 23325504, 'steps': 121486, 'loss/train': 1.113213300704956} 08/31/2021 11:19:06 - INFO - __main__ - Step 121488: {'lr': 4.4409290887435146e-05, 'samples': 23325696, 'steps': 121487, 'loss/train': 1.388933539390564} 08/31/2021 11:19:07 - INFO - __main__ - Step 121489: {'lr': 4.440627159037813e-05, 'samples': 23325888, 'steps': 121488, 'loss/train': 1.391122817993164} 08/31/2021 11:19:07 - INFO - __main__ - Step 121490: {'lr': 4.440325238595847e-05, 'samples': 23326080, 'steps': 121489, 'loss/train': 0.7750958800315857} 08/31/2021 11:19:07 - INFO - __main__ - Step 121491: {'lr': 4.4400233274177524e-05, 'samples': 23326272, 'steps': 121490, 'loss/train': 0.08004634827375412} 08/31/2021 11:19:09 - INFO - __main__ - Step 121492: {'lr': 4.4397214255036735e-05, 'samples': 23326464, 'steps': 121491, 'loss/train': 0.6384096145629883} 08/31/2021 11:19:09 - INFO - __main__ - Step 121493: {'lr': 4.439419532853731e-05, 'samples': 23326656, 'steps': 121492, 'loss/train': 1.1027897596359253} 08/31/2021 11:19:10 - INFO - __main__ - Step 121494: {'lr': 4.439117649468069e-05, 'samples': 23326848, 'steps': 121493, 'loss/train': 1.4320094585418701} 08/31/2021 11:19:10 - INFO - __main__ - Step 121495: {'lr': 4.438815775346824e-05, 'samples': 23327040, 'steps': 121494, 'loss/train': 1.6739248037338257} 08/31/2021 11:19:10 - INFO - __main__ - Step 121496: {'lr': 4.438513910490133e-05, 'samples': 23327232, 'steps': 121495, 'loss/train': 1.1229552030563354} 08/31/2021 11:19:12 - INFO - __main__ - Step 121497: {'lr': 4.4382120548981275e-05, 'samples': 23327424, 'steps': 121496, 'loss/train': 1.3284363746643066} 08/31/2021 11:19:12 - INFO - __main__ - Step 121498: {'lr': 4.437910208570947e-05, 'samples': 23327616, 'steps': 121497, 'loss/train': 0.18174700438976288} 08/31/2021 11:19:13 - INFO - __main__ - Step 121499: {'lr': 4.437608371508728e-05, 'samples': 23327808, 'steps': 121498, 'loss/train': 0.7867377996444702} 08/31/2021 11:19:13 - INFO - __main__ - Step 121500: {'lr': 4.4373065437116057e-05, 'samples': 23328000, 'steps': 121499, 'loss/train': 0.6709666848182678} 08/31/2021 11:19:13 - INFO - __main__ - Step 121501: {'lr': 4.437004725179714e-05, 'samples': 23328192, 'steps': 121500, 'loss/train': 0.9994065761566162} 08/31/2021 11:19:15 - INFO - __main__ - Step 121502: {'lr': 4.436702915913191e-05, 'samples': 23328384, 'steps': 121501, 'loss/train': 0.8830119371414185} 08/31/2021 11:19:15 - INFO - __main__ - Step 121503: {'lr': 4.4364011159121727e-05, 'samples': 23328576, 'steps': 121502, 'loss/train': 1.060992956161499} 08/31/2021 11:19:16 - INFO - __main__ - Step 121504: {'lr': 4.436099325176796e-05, 'samples': 23328768, 'steps': 121503, 'loss/train': 0.9113801121711731} 08/31/2021 11:19:16 - INFO - __main__ - Step 121505: {'lr': 4.435797543707201e-05, 'samples': 23328960, 'steps': 121504, 'loss/train': 1.6504223346710205} 08/31/2021 11:19:16 - INFO - __main__ - Step 121506: {'lr': 4.4354957715035114e-05, 'samples': 23329152, 'steps': 121505, 'loss/train': 0.26040905714035034} 08/31/2021 11:19:18 - INFO - __main__ - Step 121507: {'lr': 4.435194008565871e-05, 'samples': 23329344, 'steps': 121506, 'loss/train': 2.0097267627716064} 08/31/2021 11:19:18 - INFO - __main__ - Step 121508: {'lr': 4.434892254894413e-05, 'samples': 23329536, 'steps': 121507, 'loss/train': 1.3947747945785522} 08/31/2021 11:19:19 - INFO - __main__ - Step 121509: {'lr': 4.434590510489278e-05, 'samples': 23329728, 'steps': 121508, 'loss/train': 0.8677529692649841} 08/31/2021 11:19:19 - INFO - __main__ - Step 121510: {'lr': 4.434288775350598e-05, 'samples': 23329920, 'steps': 121509, 'loss/train': 1.1215951442718506} 08/31/2021 11:19:19 - INFO - __main__ - Step 121511: {'lr': 4.433987049478508e-05, 'samples': 23330112, 'steps': 121510, 'loss/train': 1.2998732328414917} 08/31/2021 11:19:20 - INFO - __main__ - Step 121512: {'lr': 4.433685332873147e-05, 'samples': 23330304, 'steps': 121511, 'loss/train': 1.1149834394454956} 08/31/2021 11:19:21 - INFO - __main__ - Step 121513: {'lr': 4.433383625534651e-05, 'samples': 23330496, 'steps': 121512, 'loss/train': 1.3843368291854858} 08/31/2021 11:19:22 - INFO - __main__ - Step 121514: {'lr': 4.433081927463156e-05, 'samples': 23330688, 'steps': 121513, 'loss/train': 0.8874017000198364} 08/31/2021 11:19:22 - INFO - __main__ - Step 121515: {'lr': 4.4327802386587956e-05, 'samples': 23330880, 'steps': 121514, 'loss/train': 0.7610840797424316} 08/31/2021 11:19:23 - INFO - __main__ - Step 121516: {'lr': 4.432478559121708e-05, 'samples': 23331072, 'steps': 121515, 'loss/train': 0.9806109070777893} 08/31/2021 11:19:23 - INFO - __main__ - Step 121517: {'lr': 4.432176888852027e-05, 'samples': 23331264, 'steps': 121516, 'loss/train': 1.146414041519165} 08/31/2021 11:19:24 - INFO - __main__ - Step 121518: {'lr': 4.4318752278498906e-05, 'samples': 23331456, 'steps': 121517, 'loss/train': 0.779816210269928} 08/31/2021 11:19:25 - INFO - __main__ - Step 121519: {'lr': 4.4315735761154387e-05, 'samples': 23331648, 'steps': 121518, 'loss/train': 3.9008004665374756} 08/31/2021 11:19:25 - INFO - __main__ - Step 121520: {'lr': 4.431271933648798e-05, 'samples': 23331840, 'steps': 121519, 'loss/train': 0.8959546685218811} 08/31/2021 11:19:26 - INFO - __main__ - Step 121521: {'lr': 4.4309703004501074e-05, 'samples': 23332032, 'steps': 121520, 'loss/train': 0.5067459940910339} 08/31/2021 11:19:26 - INFO - __main__ - Step 121522: {'lr': 4.430668676519506e-05, 'samples': 23332224, 'steps': 121521, 'loss/train': 0.9185004830360413} 08/31/2021 11:19:27 - INFO - __main__ - Step 121523: {'lr': 4.430367061857124e-05, 'samples': 23332416, 'steps': 121522, 'loss/train': 0.9812591075897217} 08/31/2021 11:19:28 - INFO - __main__ - Step 121524: {'lr': 4.430065456463106e-05, 'samples': 23332608, 'steps': 121523, 'loss/train': 1.2186046838760376} 08/31/2021 11:19:28 - INFO - __main__ - Step 121525: {'lr': 4.429763860337579e-05, 'samples': 23332800, 'steps': 121524, 'loss/train': 0.33564692735671997} 08/31/2021 11:19:29 - INFO - __main__ - Step 121526: {'lr': 4.429462273480686e-05, 'samples': 23332992, 'steps': 121525, 'loss/train': 1.5246100425720215} 08/31/2021 11:19:29 - INFO - __main__ - Step 121527: {'lr': 4.429160695892559e-05, 'samples': 23333184, 'steps': 121526, 'loss/train': 1.062716007232666} 08/31/2021 11:19:30 - INFO - __main__ - Step 121528: {'lr': 4.4288591275733345e-05, 'samples': 23333376, 'steps': 121527, 'loss/train': 0.5739951133728027} 08/31/2021 11:19:31 - INFO - __main__ - Step 121529: {'lr': 4.428557568523148e-05, 'samples': 23333568, 'steps': 121528, 'loss/train': 0.938264012336731} 08/31/2021 11:19:31 - INFO - __main__ - Step 121530: {'lr': 4.428256018742135e-05, 'samples': 23333760, 'steps': 121529, 'loss/train': 1.608958125114441} 08/31/2021 11:19:32 - INFO - __main__ - Step 121531: {'lr': 4.4279544782304365e-05, 'samples': 23333952, 'steps': 121530, 'loss/train': 1.4118717908859253} 08/31/2021 11:19:32 - INFO - __main__ - Step 121532: {'lr': 4.4276529469881866e-05, 'samples': 23334144, 'steps': 121531, 'loss/train': 1.0710819959640503} 08/31/2021 11:19:32 - INFO - __main__ - Step 121533: {'lr': 4.4273514250155135e-05, 'samples': 23334336, 'steps': 121532, 'loss/train': 0.6897324919700623} 08/31/2021 11:19:34 - INFO - __main__ - Step 121534: {'lr': 4.427049912312558e-05, 'samples': 23334528, 'steps': 121533, 'loss/train': 1.1251225471496582} 08/31/2021 11:19:35 - INFO - __main__ - Step 121535: {'lr': 4.426748408879458e-05, 'samples': 23334720, 'steps': 121534, 'loss/train': 1.4097833633422852} 08/31/2021 11:19:35 - INFO - __main__ - Step 121536: {'lr': 4.4264469147163475e-05, 'samples': 23334912, 'steps': 121535, 'loss/train': 0.9014450907707214} 08/31/2021 11:19:35 - INFO - __main__ - Step 121537: {'lr': 4.426145429823361e-05, 'samples': 23335104, 'steps': 121536, 'loss/train': 0.8309798836708069} 08/31/2021 11:19:36 - INFO - __main__ - Step 121538: {'lr': 4.425843954200637e-05, 'samples': 23335296, 'steps': 121537, 'loss/train': 1.1790940761566162} 08/31/2021 11:19:37 - INFO - __main__ - Step 121539: {'lr': 4.4255424878483107e-05, 'samples': 23335488, 'steps': 121538, 'loss/train': 0.7125958800315857} 08/31/2021 11:19:38 - INFO - __main__ - Step 121540: {'lr': 4.4252410307665166e-05, 'samples': 23335680, 'steps': 121539, 'loss/train': 4.539135456085205} 08/31/2021 11:19:38 - INFO - __main__ - Step 121541: {'lr': 4.4249395829553924e-05, 'samples': 23335872, 'steps': 121540, 'loss/train': 1.3678321838378906} 08/31/2021 11:19:39 - INFO - __main__ - Step 121542: {'lr': 4.4246381444150716e-05, 'samples': 23336064, 'steps': 121541, 'loss/train': 0.8388923406600952} 08/31/2021 11:19:39 - INFO - __main__ - Step 121543: {'lr': 4.424336715145694e-05, 'samples': 23336256, 'steps': 121542, 'loss/train': 1.4759434461593628} 08/31/2021 11:19:40 - INFO - __main__ - Step 121544: {'lr': 4.4240352951473885e-05, 'samples': 23336448, 'steps': 121543, 'loss/train': 0.7169933915138245} 08/31/2021 11:19:41 - INFO - __main__ - Step 121545: {'lr': 4.423733884420297e-05, 'samples': 23336640, 'steps': 121544, 'loss/train': 1.4806792736053467} 08/31/2021 11:19:41 - INFO - __main__ - Step 121546: {'lr': 4.423432482964562e-05, 'samples': 23336832, 'steps': 121545, 'loss/train': 0.9881483316421509} 08/31/2021 11:19:42 - INFO - __main__ - Step 121547: {'lr': 4.4231310907803026e-05, 'samples': 23337024, 'steps': 121546, 'loss/train': 0.9136290550231934} 08/31/2021 11:19:42 - INFO - __main__ - Step 121548: {'lr': 4.4228297078676625e-05, 'samples': 23337216, 'steps': 121547, 'loss/train': 0.8985521197319031} 08/31/2021 11:19:44 - INFO - __main__ - Step 121549: {'lr': 4.422528334226778e-05, 'samples': 23337408, 'steps': 121548, 'loss/train': 1.1574735641479492} 08/31/2021 11:19:44 - INFO - __main__ - Step 121550: {'lr': 4.422226969857785e-05, 'samples': 23337600, 'steps': 121549, 'loss/train': 0.7217405438423157} 08/31/2021 11:19:44 - INFO - __main__ - Step 121551: {'lr': 4.421925614760819e-05, 'samples': 23337792, 'steps': 121550, 'loss/train': 1.2114040851593018} 08/31/2021 11:19:45 - INFO - __main__ - Step 121552: {'lr': 4.421624268936017e-05, 'samples': 23337984, 'steps': 121551, 'loss/train': 0.9653539657592773} 08/31/2021 11:19:45 - INFO - __main__ - Step 121553: {'lr': 4.421322932383512e-05, 'samples': 23338176, 'steps': 121552, 'loss/train': 2.7652440071105957} 08/31/2021 11:19:47 - INFO - __main__ - Step 121554: {'lr': 4.4210216051034395e-05, 'samples': 23338368, 'steps': 121553, 'loss/train': 0.7269222140312195} 08/31/2021 11:19:47 - INFO - __main__ - Step 121555: {'lr': 4.420720287095942e-05, 'samples': 23338560, 'steps': 121554, 'loss/train': 1.8820505142211914} 08/31/2021 11:19:47 - INFO - __main__ - Step 121556: {'lr': 4.420418978361146e-05, 'samples': 23338752, 'steps': 121555, 'loss/train': 0.39553216099739075} 08/31/2021 11:19:48 - INFO - __main__ - Step 121557: {'lr': 4.420117678899194e-05, 'samples': 23338944, 'steps': 121556, 'loss/train': 1.432555913925171} 08/31/2021 11:19:48 - INFO - __main__ - Step 121558: {'lr': 4.4198163887102185e-05, 'samples': 23339136, 'steps': 121557, 'loss/train': 1.668107271194458} 08/31/2021 11:19:50 - INFO - __main__ - Step 121559: {'lr': 4.419515107794361e-05, 'samples': 23339328, 'steps': 121558, 'loss/train': 1.5401012897491455} 08/31/2021 11:19:50 - INFO - __main__ - Step 121560: {'lr': 4.41921383615175e-05, 'samples': 23339520, 'steps': 121559, 'loss/train': 1.024076223373413} 08/31/2021 11:19:51 - INFO - __main__ - Step 121561: {'lr': 4.4189125737825215e-05, 'samples': 23339712, 'steps': 121560, 'loss/train': 0.591870129108429} 08/31/2021 11:19:51 - INFO - __main__ - Step 121562: {'lr': 4.4186113206868135e-05, 'samples': 23339904, 'steps': 121561, 'loss/train': 1.038769006729126} 08/31/2021 11:19:51 - INFO - __main__ - Step 121563: {'lr': 4.418310076864759e-05, 'samples': 23340096, 'steps': 121562, 'loss/train': 0.938735842704773} 08/31/2021 11:19:53 - INFO - __main__ - Step 121564: {'lr': 4.418008842316501e-05, 'samples': 23340288, 'steps': 121563, 'loss/train': 1.1701799631118774} 08/31/2021 11:19:53 - INFO - __main__ - Step 121565: {'lr': 4.417707617042169e-05, 'samples': 23340480, 'steps': 121564, 'loss/train': 1.0393474102020264} 08/31/2021 11:19:54 - INFO - __main__ - Step 121566: {'lr': 4.417406401041898e-05, 'samples': 23340672, 'steps': 121565, 'loss/train': 0.6753880381584167} 08/31/2021 11:19:54 - INFO - __main__ - Step 121567: {'lr': 4.417105194315829e-05, 'samples': 23340864, 'steps': 121566, 'loss/train': 1.3180630207061768} 08/31/2021 11:19:54 - INFO - __main__ - Step 121568: {'lr': 4.416803996864094e-05, 'samples': 23341056, 'steps': 121567, 'loss/train': 0.8767017722129822} 08/31/2021 11:19:56 - INFO - __main__ - Step 121569: {'lr': 4.416502808686829e-05, 'samples': 23341248, 'steps': 121568, 'loss/train': 0.8664053678512573} 08/31/2021 11:19:56 - INFO - __main__ - Step 121570: {'lr': 4.416201629784169e-05, 'samples': 23341440, 'steps': 121569, 'loss/train': 1.2836424112319946} 08/31/2021 11:19:57 - INFO - __main__ - Step 121571: {'lr': 4.415900460156253e-05, 'samples': 23341632, 'steps': 121570, 'loss/train': 0.8870593905448914} 08/31/2021 11:19:57 - INFO - __main__ - Step 121572: {'lr': 4.4155992998032135e-05, 'samples': 23341824, 'steps': 121571, 'loss/train': 1.0113929510116577} 08/31/2021 11:19:57 - INFO - __main__ - Step 121573: {'lr': 4.415298148725194e-05, 'samples': 23342016, 'steps': 121572, 'loss/train': 0.9449499249458313} 08/31/2021 11:19:58 - INFO - __main__ - Step 121574: {'lr': 4.4149970069223165e-05, 'samples': 23342208, 'steps': 121573, 'loss/train': 0.9502576589584351} 08/31/2021 11:19:59 - INFO - __main__ - Step 121575: {'lr': 4.414695874394725e-05, 'samples': 23342400, 'steps': 121574, 'loss/train': 1.1346628665924072} 08/31/2021 11:20:00 - INFO - __main__ - Step 121576: {'lr': 4.414394751142553e-05, 'samples': 23342592, 'steps': 121575, 'loss/train': 0.9976578950881958} 08/31/2021 11:20:00 - INFO - __main__ - Step 121577: {'lr': 4.414093637165939e-05, 'samples': 23342784, 'steps': 121576, 'loss/train': 0.8286993503570557} 08/31/2021 11:20:00 - INFO - __main__ - Step 121578: {'lr': 4.4137925324650136e-05, 'samples': 23342976, 'steps': 121577, 'loss/train': 1.5592975616455078} 08/31/2021 11:20:01 - INFO - __main__ - Step 121579: {'lr': 4.413491437039918e-05, 'samples': 23343168, 'steps': 121578, 'loss/train': 1.0428820848464966} 08/31/2021 11:20:02 - INFO - __main__ - Step 121580: {'lr': 4.413190350890786e-05, 'samples': 23343360, 'steps': 121579, 'loss/train': 1.372753620147705} 08/31/2021 11:20:03 - INFO - __main__ - Step 121581: {'lr': 4.4128892740177507e-05, 'samples': 23343552, 'steps': 121580, 'loss/train': 0.14637121558189392} 08/31/2021 11:20:03 - INFO - __main__ - Step 121582: {'lr': 4.41258820642095e-05, 'samples': 23343744, 'steps': 121581, 'loss/train': 1.692795991897583} 08/31/2021 11:20:03 - INFO - __main__ - Step 121583: {'lr': 4.412287148100519e-05, 'samples': 23343936, 'steps': 121582, 'loss/train': 1.2526129484176636} 08/31/2021 11:20:04 - INFO - __main__ - Step 121584: {'lr': 4.411986099056595e-05, 'samples': 23344128, 'steps': 121583, 'loss/train': 1.2695086002349854} 08/31/2021 11:20:06 - INFO - __main__ - Step 121585: {'lr': 4.411685059289314e-05, 'samples': 23344320, 'steps': 121584, 'loss/train': 0.8082884550094604} 08/31/2021 11:20:06 - INFO - __main__ - Step 121586: {'lr': 4.411384028798812e-05, 'samples': 23344512, 'steps': 121585, 'loss/train': 0.7808603048324585} 08/31/2021 11:20:06 - INFO - __main__ - Step 121587: {'lr': 4.411083007585221e-05, 'samples': 23344704, 'steps': 121586, 'loss/train': 0.91068035364151} 08/31/2021 11:20:07 - INFO - __main__ - Step 121588: {'lr': 4.4107819956486745e-05, 'samples': 23344896, 'steps': 121587, 'loss/train': 0.8067452907562256} 08/31/2021 11:20:07 - INFO - __main__ - Step 121589: {'lr': 4.410480992989313e-05, 'samples': 23345088, 'steps': 121588, 'loss/train': 0.06445552408695221} 08/31/2021 11:20:09 - INFO - __main__ - Step 121590: {'lr': 4.410179999607272e-05, 'samples': 23345280, 'steps': 121589, 'loss/train': 0.881980299949646} 08/31/2021 11:20:10 - INFO - __main__ - Step 121591: {'lr': 4.4098790155026855e-05, 'samples': 23345472, 'steps': 121590, 'loss/train': 1.0829216241836548} 08/31/2021 11:20:10 - INFO - __main__ - Step 121592: {'lr': 4.409578040675691e-05, 'samples': 23345664, 'steps': 121591, 'loss/train': 0.9652300477027893} 08/31/2021 11:20:11 - INFO - __main__ - Step 121593: {'lr': 4.409277075126422e-05, 'samples': 23345856, 'steps': 121592, 'loss/train': 0.6412369608879089} 08/31/2021 11:20:11 - INFO - __main__ - Step 121594: {'lr': 4.408976118855012e-05, 'samples': 23346048, 'steps': 121593, 'loss/train': 1.2633551359176636} 08/31/2021 11:20:12 - INFO - __main__ - Step 121595: {'lr': 4.4086751718616036e-05, 'samples': 23346240, 'steps': 121594, 'loss/train': 1.0776571035385132} 08/31/2021 11:20:13 - INFO - __main__ - Step 121596: {'lr': 4.408374234146328e-05, 'samples': 23346432, 'steps': 121595, 'loss/train': 1.1670774221420288} 08/31/2021 11:20:13 - INFO - __main__ - Step 121597: {'lr': 4.40807330570932e-05, 'samples': 23346624, 'steps': 121596, 'loss/train': 1.1398428678512573} 08/31/2021 11:20:14 - INFO - __main__ - Step 121598: {'lr': 4.407772386550718e-05, 'samples': 23346816, 'steps': 121597, 'loss/train': 0.7669059038162231} 08/31/2021 11:20:14 - INFO - __main__ - Step 121599: {'lr': 4.40747147667066e-05, 'samples': 23347008, 'steps': 121598, 'loss/train': 0.5655152797698975} 08/31/2021 11:20:15 - INFO - __main__ - Step 121600: {'lr': 4.407170576069272e-05, 'samples': 23347200, 'steps': 121599, 'loss/train': 1.9318783283233643} 08/31/2021 11:20:16 - INFO - __main__ - Step 121601: {'lr': 4.4068696847466977e-05, 'samples': 23347392, 'steps': 121600, 'loss/train': 0.9744709730148315} 08/31/2021 11:20:16 - INFO - __main__ - Step 121602: {'lr': 4.406568802703068e-05, 'samples': 23347584, 'steps': 121601, 'loss/train': 0.10815801471471786} 08/31/2021 11:20:17 - INFO - __main__ - Step 121603: {'lr': 4.406267929938521e-05, 'samples': 23347776, 'steps': 121602, 'loss/train': 0.9505770206451416} 08/31/2021 11:20:17 - INFO - __main__ - Step 121604: {'lr': 4.40596706645319e-05, 'samples': 23347968, 'steps': 121603, 'loss/train': 2.0549871921539307} 08/31/2021 11:20:18 - INFO - __main__ - Step 121605: {'lr': 4.405666212247214e-05, 'samples': 23348160, 'steps': 121604, 'loss/train': 1.253771185874939} 08/31/2021 11:20:19 - INFO - __main__ - Step 121606: {'lr': 4.4053653673207264e-05, 'samples': 23348352, 'steps': 121605, 'loss/train': 1.2148170471191406} 08/31/2021 11:20:19 - INFO - __main__ - Step 121607: {'lr': 4.4050645316738665e-05, 'samples': 23348544, 'steps': 121606, 'loss/train': 1.5440152883529663} 08/31/2021 11:20:20 - INFO - __main__ - Step 121608: {'lr': 4.4047637053067633e-05, 'samples': 23348736, 'steps': 121607, 'loss/train': 1.325638771057129} 08/31/2021 11:20:20 - INFO - __main__ - Step 121609: {'lr': 4.404462888219557e-05, 'samples': 23348928, 'steps': 121608, 'loss/train': 1.2140345573425293} 08/31/2021 11:20:21 - INFO - __main__ - Step 121610: {'lr': 4.404162080412383e-05, 'samples': 23349120, 'steps': 121609, 'loss/train': 1.154459834098816} 08/31/2021 11:20:22 - INFO - __main__ - Step 121611: {'lr': 4.403861281885374e-05, 'samples': 23349312, 'steps': 121610, 'loss/train': 0.8779071569442749} 08/31/2021 11:20:22 - INFO - __main__ - Step 121612: {'lr': 4.4035604926386666e-05, 'samples': 23349504, 'steps': 121611, 'loss/train': 1.2069556713104248} 08/31/2021 11:20:23 - INFO - __main__ - Step 121613: {'lr': 4.403259712672406e-05, 'samples': 23349696, 'steps': 121612, 'loss/train': 0.15628714859485626} 08/31/2021 11:20:23 - INFO - __main__ - Step 121614: {'lr': 4.4029589419867096e-05, 'samples': 23349888, 'steps': 121613, 'loss/train': 1.13646399974823} 08/31/2021 11:20:25 - INFO - __main__ - Step 121615: {'lr': 4.402658180581723e-05, 'samples': 23350080, 'steps': 121614, 'loss/train': 0.7847433686256409} 08/31/2021 11:20:25 - INFO - __main__ - Step 121616: {'lr': 4.4023574284575815e-05, 'samples': 23350272, 'steps': 121615, 'loss/train': 1.2470866441726685} 08/31/2021 11:20:25 - INFO - __main__ - Step 121617: {'lr': 4.402056685614419e-05, 'samples': 23350464, 'steps': 121616, 'loss/train': 0.5668660998344421} 08/31/2021 11:20:26 - INFO - __main__ - Step 121618: {'lr': 4.401755952052372e-05, 'samples': 23350656, 'steps': 121617, 'loss/train': 1.4735121726989746} 08/31/2021 11:20:26 - INFO - __main__ - Step 121619: {'lr': 4.4014552277715783e-05, 'samples': 23350848, 'steps': 121618, 'loss/train': 0.7448698878288269} 08/31/2021 11:20:26 - INFO - __main__ - Step 121620: {'lr': 4.401154512772168e-05, 'samples': 23351040, 'steps': 121619, 'loss/train': 1.082613229751587} 08/31/2021 11:20:28 - INFO - __main__ - Step 121621: {'lr': 4.400853807054281e-05, 'samples': 23351232, 'steps': 121620, 'loss/train': 0.44204676151275635} 08/31/2021 11:20:28 - INFO - __main__ - Step 121622: {'lr': 4.4005531106180495e-05, 'samples': 23351424, 'steps': 121621, 'loss/train': 1.1365044116973877} 08/31/2021 11:20:29 - INFO - __main__ - Step 121623: {'lr': 4.400252423463613e-05, 'samples': 23351616, 'steps': 121622, 'loss/train': 1.017969012260437} 08/31/2021 11:20:29 - INFO - __main__ - Step 121624: {'lr': 4.399951745591105e-05, 'samples': 23351808, 'steps': 121623, 'loss/train': 0.9480275511741638} 08/31/2021 11:20:31 - INFO - __main__ - Step 121625: {'lr': 4.39965107700066e-05, 'samples': 23352000, 'steps': 121624, 'loss/train': 1.2072994709014893} 08/31/2021 11:20:31 - INFO - __main__ - Step 121626: {'lr': 4.399350417692421e-05, 'samples': 23352192, 'steps': 121625, 'loss/train': 0.7261911630630493} 08/31/2021 11:20:31 - INFO - __main__ - Step 121627: {'lr': 4.39904976766651e-05, 'samples': 23352384, 'steps': 121626, 'loss/train': 1.3503100872039795} 08/31/2021 11:20:32 - INFO - __main__ - Step 121628: {'lr': 4.398749126923071e-05, 'samples': 23352576, 'steps': 121627, 'loss/train': 1.4472635984420776} 08/31/2021 11:20:32 - INFO - __main__ - Step 121629: {'lr': 4.398448495462237e-05, 'samples': 23352768, 'steps': 121628, 'loss/train': 0.9479951858520508} 08/31/2021 11:20:32 - INFO - __main__ - Step 121630: {'lr': 4.398147873284142e-05, 'samples': 23352960, 'steps': 121629, 'loss/train': 0.7276155948638916} 08/31/2021 11:20:34 - INFO - __main__ - Step 121631: {'lr': 4.397847260388926e-05, 'samples': 23353152, 'steps': 121630, 'loss/train': 1.6341465711593628} 08/31/2021 11:20:34 - INFO - __main__ - Step 121632: {'lr': 4.3975466567767214e-05, 'samples': 23353344, 'steps': 121631, 'loss/train': 1.1993012428283691} 08/31/2021 11:20:35 - INFO - __main__ - Step 121633: {'lr': 4.397246062447666e-05, 'samples': 23353536, 'steps': 121632, 'loss/train': 1.142542839050293} 08/31/2021 11:20:35 - INFO - __main__ - Step 121634: {'lr': 4.39694547740189e-05, 'samples': 23353728, 'steps': 121633, 'loss/train': 0.8286278247833252} 08/31/2021 11:20:35 - INFO - __main__ - Step 121635: {'lr': 4.3966449016395346e-05, 'samples': 23353920, 'steps': 121634, 'loss/train': 1.2328141927719116} 08/31/2021 11:20:37 - INFO - __main__ - Step 121636: {'lr': 4.3963443351607345e-05, 'samples': 23354112, 'steps': 121635, 'loss/train': 0.8138428926467896} 08/31/2021 11:20:37 - INFO - __main__ - Step 121637: {'lr': 4.396043777965622e-05, 'samples': 23354304, 'steps': 121636, 'loss/train': 0.7821143269538879} 08/31/2021 11:20:38 - INFO - __main__ - Step 121638: {'lr': 4.395743230054333e-05, 'samples': 23354496, 'steps': 121637, 'loss/train': 1.4431169033050537} 08/31/2021 11:20:38 - INFO - __main__ - Step 121639: {'lr': 4.395442691427007e-05, 'samples': 23354688, 'steps': 121638, 'loss/train': 0.5557291507720947} 08/31/2021 11:20:38 - INFO - __main__ - Step 121640: {'lr': 4.395142162083782e-05, 'samples': 23354880, 'steps': 121639, 'loss/train': 0.7110180854797363} 08/31/2021 11:20:40 - INFO - __main__ - Step 121641: {'lr': 4.39484164202478e-05, 'samples': 23355072, 'steps': 121640, 'loss/train': 0.4976259469985962} 08/31/2021 11:20:41 - INFO - __main__ - Step 121642: {'lr': 4.394541131250146e-05, 'samples': 23355264, 'steps': 121641, 'loss/train': 1.0981392860412598} 08/31/2021 11:20:41 - INFO - __main__ - Step 121643: {'lr': 4.394240629760013e-05, 'samples': 23355456, 'steps': 121642, 'loss/train': 1.472440242767334} 08/31/2021 11:20:42 - INFO - __main__ - Step 121644: {'lr': 4.393940137554517e-05, 'samples': 23355648, 'steps': 121643, 'loss/train': 1.3791937828063965} 08/31/2021 11:20:42 - INFO - __main__ - Step 121645: {'lr': 4.3936396546337936e-05, 'samples': 23355840, 'steps': 121644, 'loss/train': 1.1627988815307617} 08/31/2021 11:20:44 - INFO - __main__ - Step 121646: {'lr': 4.393339180997979e-05, 'samples': 23356032, 'steps': 121645, 'loss/train': 1.4510711431503296} 08/31/2021 11:20:44 - INFO - __main__ - Step 121647: {'lr': 4.3930387166472074e-05, 'samples': 23356224, 'steps': 121646, 'loss/train': 0.5514593124389648} 08/31/2021 11:20:44 - INFO - __main__ - Step 121648: {'lr': 4.3927382615816134e-05, 'samples': 23356416, 'steps': 121647, 'loss/train': 1.1658276319503784} 08/31/2021 11:20:45 - INFO - __main__ - Step 121649: {'lr': 4.392437815801337e-05, 'samples': 23356608, 'steps': 121648, 'loss/train': 1.8882631063461304} 08/31/2021 11:20:45 - INFO - __main__ - Step 121650: {'lr': 4.392137379306507e-05, 'samples': 23356800, 'steps': 121649, 'loss/train': 1.0936923027038574} 08/31/2021 11:20:47 - INFO - __main__ - Step 121651: {'lr': 4.391836952097264e-05, 'samples': 23356992, 'steps': 121650, 'loss/train': 1.5122846364974976} 08/31/2021 11:20:47 - INFO - __main__ - Step 121652: {'lr': 4.39153653417374e-05, 'samples': 23357184, 'steps': 121651, 'loss/train': 0.9625961184501648} 08/31/2021 11:20:47 - INFO - __main__ - Step 121653: {'lr': 4.391236125536077e-05, 'samples': 23357376, 'steps': 121652, 'loss/train': 0.0887124091386795} 08/31/2021 11:20:48 - INFO - __main__ - Step 121654: {'lr': 4.3909357261844e-05, 'samples': 23357568, 'steps': 121653, 'loss/train': 1.204641580581665} 08/31/2021 11:20:48 - INFO - __main__ - Step 121655: {'lr': 4.390635336118848e-05, 'samples': 23357760, 'steps': 121654, 'loss/train': 0.7351349592208862} 08/31/2021 11:20:48 - INFO - __main__ - Step 121656: {'lr': 4.390334955339559e-05, 'samples': 23357952, 'steps': 121655, 'loss/train': 0.41834530234336853} 08/31/2021 11:20:50 - INFO - __main__ - Step 121657: {'lr': 4.3900345838466666e-05, 'samples': 23358144, 'steps': 121656, 'loss/train': 0.8395946025848389} 08/31/2021 11:20:50 - INFO - __main__ - Step 121658: {'lr': 4.3897342216403066e-05, 'samples': 23358336, 'steps': 121657, 'loss/train': 0.10628636181354523} 08/31/2021 11:20:51 - INFO - __main__ - Step 121659: {'lr': 4.389433868720616e-05, 'samples': 23358528, 'steps': 121658, 'loss/train': 1.1494892835617065} 08/31/2021 11:20:51 - INFO - __main__ - Step 121660: {'lr': 4.389133525087727e-05, 'samples': 23358720, 'steps': 121659, 'loss/train': 1.2853920459747314} 08/31/2021 11:20:51 - INFO - __main__ - Step 121661: {'lr': 4.388833190741775e-05, 'samples': 23358912, 'steps': 121660, 'loss/train': 1.3401949405670166} 08/31/2021 11:20:53 - INFO - __main__ - Step 121662: {'lr': 4.388532865682898e-05, 'samples': 23359104, 'steps': 121661, 'loss/train': 1.0539478063583374} 08/31/2021 11:20:53 - INFO - __main__ - Step 121663: {'lr': 4.388232549911231e-05, 'samples': 23359296, 'steps': 121662, 'loss/train': 0.8710373640060425} 08/31/2021 11:20:54 - INFO - __main__ - Step 121664: {'lr': 4.387932243426907e-05, 'samples': 23359488, 'steps': 121663, 'loss/train': 1.0868390798568726} 08/31/2021 11:20:54 - INFO - __main__ - Step 121665: {'lr': 4.387631946230064e-05, 'samples': 23359680, 'steps': 121664, 'loss/train': 1.473677635192871} 08/31/2021 11:20:54 - INFO - __main__ - Step 121666: {'lr': 4.3873316583208336e-05, 'samples': 23359872, 'steps': 121665, 'loss/train': 1.476457118988037} 08/31/2021 11:20:56 - INFO - __main__ - Step 121667: {'lr': 4.387031379699363e-05, 'samples': 23360064, 'steps': 121666, 'loss/train': 0.3454437851905823} 08/31/2021 11:20:57 - INFO - __main__ - Step 121668: {'lr': 4.3867311103657686e-05, 'samples': 23360256, 'steps': 121667, 'loss/train': 1.517046570777893} 08/31/2021 11:20:57 - INFO - __main__ - Step 121669: {'lr': 4.3864308503201974e-05, 'samples': 23360448, 'steps': 121668, 'loss/train': 0.2683110535144806} 08/31/2021 11:20:57 - INFO - __main__ - Step 121670: {'lr': 4.386130599562782e-05, 'samples': 23360640, 'steps': 121669, 'loss/train': 0.8973664045333862} 08/31/2021 11:20:58 - INFO - __main__ - Step 121671: {'lr': 4.3858303580936566e-05, 'samples': 23360832, 'steps': 121670, 'loss/train': 0.6289759278297424} 08/31/2021 11:20:59 - INFO - __main__ - Step 121672: {'lr': 4.3855301259129594e-05, 'samples': 23361024, 'steps': 121671, 'loss/train': 0.8182041645050049} 08/31/2021 11:21:00 - INFO - __main__ - Step 121673: {'lr': 4.3852299030208235e-05, 'samples': 23361216, 'steps': 121672, 'loss/train': 3.1854991912841797} 08/31/2021 11:21:00 - INFO - __main__ - Step 121674: {'lr': 4.384929689417386e-05, 'samples': 23361408, 'steps': 121673, 'loss/train': 0.4533420503139496} 08/31/2021 11:21:00 - INFO - __main__ - Step 121675: {'lr': 4.384629485102778e-05, 'samples': 23361600, 'steps': 121674, 'loss/train': 1.048564076423645} 08/31/2021 11:21:01 - INFO - __main__ - Step 121676: {'lr': 4.3843292900771407e-05, 'samples': 23361792, 'steps': 121675, 'loss/train': 1.1934127807617188} 08/31/2021 11:21:01 - INFO - __main__ - Step 121677: {'lr': 4.3840291043406064e-05, 'samples': 23361984, 'steps': 121676, 'loss/train': 0.6884505748748779} 08/31/2021 11:21:03 - INFO - __main__ - Step 121678: {'lr': 4.3837289278933104e-05, 'samples': 23362176, 'steps': 121677, 'loss/train': 0.8965286612510681} 08/31/2021 11:21:03 - INFO - __main__ - Step 121679: {'lr': 4.383428760735386e-05, 'samples': 23362368, 'steps': 121678, 'loss/train': 1.2257065773010254} 08/31/2021 11:21:04 - INFO - __main__ - Step 121680: {'lr': 4.3831286028669785e-05, 'samples': 23362560, 'steps': 121679, 'loss/train': 0.7528286576271057} 08/31/2021 11:21:04 - INFO - __main__ - Step 121681: {'lr': 4.3828284542882096e-05, 'samples': 23362752, 'steps': 121680, 'loss/train': 1.2863646745681763} 08/31/2021 11:21:04 - INFO - __main__ - Step 121682: {'lr': 4.3825283149992176e-05, 'samples': 23362944, 'steps': 121681, 'loss/train': 0.4440997838973999} 08/31/2021 11:21:06 - INFO - __main__ - Step 121683: {'lr': 4.382228185000142e-05, 'samples': 23363136, 'steps': 121682, 'loss/train': 1.2650541067123413} 08/31/2021 11:21:06 - INFO - __main__ - Step 121684: {'lr': 4.381928064291116e-05, 'samples': 23363328, 'steps': 121683, 'loss/train': 0.7774048447608948} 08/31/2021 11:21:07 - INFO - __main__ - Step 121685: {'lr': 4.381627952872275e-05, 'samples': 23363520, 'steps': 121684, 'loss/train': 1.7181614637374878} 08/31/2021 11:21:07 - INFO - __main__ - Step 121686: {'lr': 4.3813278507437546e-05, 'samples': 23363712, 'steps': 121685, 'loss/train': 0.9978440999984741} 08/31/2021 11:21:07 - INFO - __main__ - Step 121687: {'lr': 4.38102775790569e-05, 'samples': 23363904, 'steps': 121686, 'loss/train': 1.4218939542770386} 08/31/2021 11:21:08 - INFO - __main__ - Step 121688: {'lr': 4.380727674358215e-05, 'samples': 23364096, 'steps': 121687, 'loss/train': 1.329148530960083} 08/31/2021 11:21:09 - INFO - __main__ - Step 121689: {'lr': 4.380427600101466e-05, 'samples': 23364288, 'steps': 121688, 'loss/train': 0.789125919342041} 08/31/2021 11:21:10 - INFO - __main__ - Step 121690: {'lr': 4.380127535135578e-05, 'samples': 23364480, 'steps': 121689, 'loss/train': 1.646973729133606} 08/31/2021 11:21:10 - INFO - __main__ - Step 121691: {'lr': 4.379827479460688e-05, 'samples': 23364672, 'steps': 121690, 'loss/train': 0.8107370138168335} 08/31/2021 11:21:11 - INFO - __main__ - Step 121692: {'lr': 4.379527433076933e-05, 'samples': 23364864, 'steps': 121691, 'loss/train': 0.9415582418441772} 08/31/2021 11:21:11 - INFO - __main__ - Step 121693: {'lr': 4.379227395984442e-05, 'samples': 23365056, 'steps': 121692, 'loss/train': 1.2811325788497925} 08/31/2021 11:21:13 - INFO - __main__ - Step 121694: {'lr': 4.37892736818335e-05, 'samples': 23365248, 'steps': 121693, 'loss/train': 0.027913205325603485} 08/31/2021 11:21:13 - INFO - __main__ - Step 121695: {'lr': 4.378627349673797e-05, 'samples': 23365440, 'steps': 121694, 'loss/train': 1.2556215524673462} 08/31/2021 11:21:14 - INFO - __main__ - Step 121696: {'lr': 4.378327340455915e-05, 'samples': 23365632, 'steps': 121695, 'loss/train': 0.8271624445915222} 08/31/2021 11:21:14 - INFO - __main__ - Step 121697: {'lr': 4.378027340529841e-05, 'samples': 23365824, 'steps': 121696, 'loss/train': 1.420041799545288} 08/31/2021 11:21:14 - INFO - __main__ - Step 121698: {'lr': 4.37772734989571e-05, 'samples': 23366016, 'steps': 121697, 'loss/train': 1.6846301555633545} 08/31/2021 11:21:16 - INFO - __main__ - Step 121699: {'lr': 4.3774273685536546e-05, 'samples': 23366208, 'steps': 121698, 'loss/train': 1.3579654693603516} 08/31/2021 11:21:17 - INFO - __main__ - Step 121700: {'lr': 4.377127396503816e-05, 'samples': 23366400, 'steps': 121699, 'loss/train': 0.6384144425392151} 08/31/2021 11:21:17 - INFO - __main__ - Step 121701: {'lr': 4.376827433746322e-05, 'samples': 23366592, 'steps': 121700, 'loss/train': 1.4511386156082153} 08/31/2021 11:21:18 - INFO - __main__ - Step 121702: {'lr': 4.3765274802813146e-05, 'samples': 23366784, 'steps': 121701, 'loss/train': 0.0617353618144989} 08/31/2021 11:21:18 - INFO - __main__ - Step 121703: {'lr': 4.376227536108929e-05, 'samples': 23366976, 'steps': 121702, 'loss/train': 1.4553520679473877} 08/31/2021 11:21:19 - INFO - __main__ - Step 121704: {'lr': 4.375927601229293e-05, 'samples': 23367168, 'steps': 121703, 'loss/train': 0.9171158075332642} 08/31/2021 11:21:20 - INFO - __main__ - Step 121705: {'lr': 4.3756276756425434e-05, 'samples': 23367360, 'steps': 121704, 'loss/train': 0.19622547924518585} 08/31/2021 11:21:20 - INFO - __main__ - Step 121706: {'lr': 4.3753277593488214e-05, 'samples': 23367552, 'steps': 121705, 'loss/train': 1.6996523141860962} 08/31/2021 11:21:21 - INFO - __main__ - Step 121707: {'lr': 4.3750278523482536e-05, 'samples': 23367744, 'steps': 121706, 'loss/train': 0.9943653345108032} 08/31/2021 11:21:21 - INFO - __main__ - Step 121708: {'lr': 4.374727954640984e-05, 'samples': 23367936, 'steps': 121707, 'loss/train': 1.0914044380187988} 08/31/2021 11:21:23 - INFO - __main__ - Step 121709: {'lr': 4.374428066227143e-05, 'samples': 23368128, 'steps': 121708, 'loss/train': 0.9827895760536194} 08/31/2021 11:21:23 - INFO - __main__ - Step 121710: {'lr': 4.3741281871068655e-05, 'samples': 23368320, 'steps': 121709, 'loss/train': 0.9094115495681763} 08/31/2021 11:21:24 - INFO - __main__ - Step 121711: {'lr': 4.3738283172802874e-05, 'samples': 23368512, 'steps': 121710, 'loss/train': 1.0281469821929932} 08/31/2021 11:21:24 - INFO - __main__ - Step 121712: {'lr': 4.373528456747544e-05, 'samples': 23368704, 'steps': 121711, 'loss/train': 1.1765356063842773} 08/31/2021 11:21:24 - INFO - __main__ - Step 121713: {'lr': 4.373228605508772e-05, 'samples': 23368896, 'steps': 121712, 'loss/train': 0.5549108386039734} 08/31/2021 11:21:25 - INFO - __main__ - Step 121714: {'lr': 4.37292876356411e-05, 'samples': 23369088, 'steps': 121713, 'loss/train': 0.016402559354901314} 08/31/2021 11:21:26 - INFO - __main__ - Step 121715: {'lr': 4.37262893091368e-05, 'samples': 23369280, 'steps': 121714, 'loss/train': 1.2055332660675049} 08/31/2021 11:21:27 - INFO - __main__ - Step 121716: {'lr': 4.372329107557627e-05, 'samples': 23369472, 'steps': 121715, 'loss/train': 1.2882015705108643} 08/31/2021 11:21:27 - INFO - __main__ - Step 121717: {'lr': 4.3720292934960856e-05, 'samples': 23369664, 'steps': 121716, 'loss/train': 1.3310614824295044} 08/31/2021 11:21:27 - INFO - __main__ - Step 121718: {'lr': 4.371729488729187e-05, 'samples': 23369856, 'steps': 121717, 'loss/train': 1.381333351135254} 08/31/2021 11:21:28 - INFO - __main__ - Step 121719: {'lr': 4.37142969325707e-05, 'samples': 23370048, 'steps': 121718, 'loss/train': 1.503313422203064} 08/31/2021 11:21:28 - INFO - __main__ - Step 121720: {'lr': 4.371129907079868e-05, 'samples': 23370240, 'steps': 121719, 'loss/train': 0.5504125952720642} 08/31/2021 11:21:30 - INFO - __main__ - Step 121721: {'lr': 4.370830130197717e-05, 'samples': 23370432, 'steps': 121720, 'loss/train': 1.0710138082504272} 08/31/2021 11:21:30 - INFO - __main__ - Step 121722: {'lr': 4.37053036261075e-05, 'samples': 23370624, 'steps': 121721, 'loss/train': 1.268120527267456} 08/31/2021 11:21:31 - INFO - __main__ - Step 121723: {'lr': 4.370230604319106e-05, 'samples': 23370816, 'steps': 121722, 'loss/train': 0.9122671484947205} 08/31/2021 11:21:31 - INFO - __main__ - Step 121724: {'lr': 4.369930855322915e-05, 'samples': 23371008, 'steps': 121723, 'loss/train': 1.531406283378601} 08/31/2021 11:21:31 - INFO - __main__ - Step 121725: {'lr': 4.369631115622325e-05, 'samples': 23371200, 'steps': 121724, 'loss/train': 0.8822489380836487} 08/31/2021 11:21:32 - INFO - __main__ - Step 121726: {'lr': 4.369331385217451e-05, 'samples': 23371392, 'steps': 121725, 'loss/train': 0.01435244269669056} 08/31/2021 11:21:33 - INFO - __main__ - Step 121727: {'lr': 4.369031664108439e-05, 'samples': 23371584, 'steps': 121726, 'loss/train': 1.359061360359192} 08/31/2021 11:21:34 - INFO - __main__ - Step 121728: {'lr': 4.368731952295424e-05, 'samples': 23371776, 'steps': 121727, 'loss/train': 1.4296894073486328} 08/31/2021 11:21:34 - INFO - __main__ - Step 121729: {'lr': 4.36843224977854e-05, 'samples': 23371968, 'steps': 121728, 'loss/train': 0.1539880633354187} 08/31/2021 11:21:35 - INFO - __main__ - Step 121730: {'lr': 4.368132556557921e-05, 'samples': 23372160, 'steps': 121729, 'loss/train': 1.278115153312683} 08/31/2021 11:21:35 - INFO - __main__ - Step 121731: {'lr': 4.3678328726337035e-05, 'samples': 23372352, 'steps': 121730, 'loss/train': 1.2343043088912964} 08/31/2021 11:21:36 - INFO - __main__ - Step 121732: {'lr': 4.3675331980060214e-05, 'samples': 23372544, 'steps': 121731, 'loss/train': 1.4426846504211426} 08/31/2021 11:21:37 - INFO - __main__ - Step 121733: {'lr': 4.367233532675011e-05, 'samples': 23372736, 'steps': 121732, 'loss/train': 1.0960804224014282} 08/31/2021 11:21:37 - INFO - __main__ - Step 121734: {'lr': 4.366933876640808e-05, 'samples': 23372928, 'steps': 121733, 'loss/train': 1.3200033903121948} 08/31/2021 11:21:38 - INFO - __main__ - Step 121735: {'lr': 4.366634229903546e-05, 'samples': 23373120, 'steps': 121734, 'loss/train': 3.5185155868530273} 08/31/2021 11:21:38 - INFO - __main__ - Step 121736: {'lr': 4.366334592463364e-05, 'samples': 23373312, 'steps': 121735, 'loss/train': 0.6342271566390991} 08/31/2021 11:21:40 - INFO - __main__ - Step 121737: {'lr': 4.3660349643203894e-05, 'samples': 23373504, 'steps': 121736, 'loss/train': 0.03691945970058441} 08/31/2021 11:21:40 - INFO - __main__ - Step 121738: {'lr': 4.365735345474761e-05, 'samples': 23373696, 'steps': 121737, 'loss/train': 0.7113175392150879} 08/31/2021 11:21:40 - INFO - __main__ - Step 121739: {'lr': 4.365435735926612e-05, 'samples': 23373888, 'steps': 121738, 'loss/train': 0.9905736446380615} 08/31/2021 11:21:41 - INFO - __main__ - Step 121740: {'lr': 4.365136135676082e-05, 'samples': 23374080, 'steps': 121739, 'loss/train': 0.4343762993812561} 08/31/2021 11:21:41 - INFO - __main__ - Step 121741: {'lr': 4.3648365447232994e-05, 'samples': 23374272, 'steps': 121740, 'loss/train': 1.1660511493682861} 08/31/2021 11:21:43 - INFO - __main__ - Step 121742: {'lr': 4.364536963068405e-05, 'samples': 23374464, 'steps': 121741, 'loss/train': 0.8383263349533081} 08/31/2021 11:21:43 - INFO - __main__ - Step 121743: {'lr': 4.364237390711534e-05, 'samples': 23374656, 'steps': 121742, 'loss/train': 1.2626867294311523} 08/31/2021 11:21:44 - INFO - __main__ - Step 121744: {'lr': 4.363937827652817e-05, 'samples': 23374848, 'steps': 121743, 'loss/train': 0.1894901543855667} 08/31/2021 11:21:44 - INFO - __main__ - Step 121745: {'lr': 4.363638273892392e-05, 'samples': 23375040, 'steps': 121744, 'loss/train': 0.02982322871685028} 08/31/2021 11:21:44 - INFO - __main__ - Step 121746: {'lr': 4.3633387294303914e-05, 'samples': 23375232, 'steps': 121745, 'loss/train': 1.5778864622116089} 08/31/2021 11:21:46 - INFO - __main__ - Step 121747: {'lr': 4.36303919426696e-05, 'samples': 23375424, 'steps': 121746, 'loss/train': 0.4647333323955536} 08/31/2021 11:21:46 - INFO - __main__ - Step 121748: {'lr': 4.3627396684022186e-05, 'samples': 23375616, 'steps': 121747, 'loss/train': 1.3461893796920776} 08/31/2021 11:21:47 - INFO - __main__ - Step 121749: {'lr': 4.3624401518363054e-05, 'samples': 23375808, 'steps': 121748, 'loss/train': 1.3476107120513916} 08/31/2021 11:21:47 - INFO - __main__ - Step 121750: {'lr': 4.3621406445693624e-05, 'samples': 23376000, 'steps': 121749, 'loss/train': 0.9427462220191956} 08/31/2021 11:21:47 - INFO - __main__ - Step 121751: {'lr': 4.3618411466015165e-05, 'samples': 23376192, 'steps': 121750, 'loss/train': 1.156925916671753} 08/31/2021 11:21:50 - INFO - __main__ - Step 121752: {'lr': 4.3615416579329105e-05, 'samples': 23376384, 'steps': 121751, 'loss/train': 1.178759217262268} 08/31/2021 11:21:50 - INFO - __main__ - Step 121753: {'lr': 4.3612421785636706e-05, 'samples': 23376576, 'steps': 121752, 'loss/train': 0.7111760973930359} 08/31/2021 11:21:50 - INFO - __main__ - Step 121754: {'lr': 4.36094270849394e-05, 'samples': 23376768, 'steps': 121753, 'loss/train': 1.4102575778961182} 08/31/2021 11:21:51 - INFO - __main__ - Step 121755: {'lr': 4.36064324772385e-05, 'samples': 23376960, 'steps': 121754, 'loss/train': 1.1365814208984375} 08/31/2021 11:21:51 - INFO - __main__ - Step 121756: {'lr': 4.3603437962535354e-05, 'samples': 23377152, 'steps': 121755, 'loss/train': 2.085645914077759} 08/31/2021 11:21:52 - INFO - __main__ - Step 121757: {'lr': 4.360044354083128e-05, 'samples': 23377344, 'steps': 121756, 'loss/train': 1.0129296779632568} 08/31/2021 11:21:53 - INFO - __main__ - Step 121758: {'lr': 4.359744921212772e-05, 'samples': 23377536, 'steps': 121757, 'loss/train': 1.0356546640396118} 08/31/2021 11:21:53 - INFO - __main__ - Step 121759: {'lr': 4.3594454976425915e-05, 'samples': 23377728, 'steps': 121758, 'loss/train': 1.052146077156067} 08/31/2021 11:21:54 - INFO - __main__ - Step 121760: {'lr': 4.359146083372728e-05, 'samples': 23377920, 'steps': 121759, 'loss/train': 1.2015713453292847} 08/31/2021 11:21:54 - INFO - __main__ - Step 121761: {'lr': 4.358846678403322e-05, 'samples': 23378112, 'steps': 121760, 'loss/train': 0.8602808713912964} 08/31/2021 11:21:55 - INFO - __main__ - Step 121762: {'lr': 4.358547282734493e-05, 'samples': 23378304, 'steps': 121761, 'loss/train': 0.9643367528915405} 08/31/2021 11:21:56 - INFO - __main__ - Step 121763: {'lr': 4.358247896366385e-05, 'samples': 23378496, 'steps': 121762, 'loss/train': 1.4310002326965332} 08/31/2021 11:21:57 - INFO - __main__ - Step 121764: {'lr': 4.3579485192991345e-05, 'samples': 23378688, 'steps': 121763, 'loss/train': 1.2311761379241943} 08/31/2021 11:21:57 - INFO - __main__ - Step 121765: {'lr': 4.357649151532872e-05, 'samples': 23378880, 'steps': 121764, 'loss/train': 1.2194510698318481} 08/31/2021 11:21:58 - INFO - __main__ - Step 121766: {'lr': 4.357349793067733e-05, 'samples': 23379072, 'steps': 121765, 'loss/train': 0.7588316798210144} 08/31/2021 11:21:58 - INFO - __main__ - Step 121767: {'lr': 4.357050443903854e-05, 'samples': 23379264, 'steps': 121766, 'loss/train': 0.3317042887210846} 08/31/2021 11:21:58 - INFO - __main__ - Step 121768: {'lr': 4.3567511040413706e-05, 'samples': 23379456, 'steps': 121767, 'loss/train': 0.995800793170929} 08/31/2021 11:22:00 - INFO - __main__ - Step 121769: {'lr': 4.356451773480416e-05, 'samples': 23379648, 'steps': 121768, 'loss/train': 0.6923861503601074} 08/31/2021 11:22:01 - INFO - __main__ - Step 121770: {'lr': 4.356152452221127e-05, 'samples': 23379840, 'steps': 121769, 'loss/train': 0.3937564194202423} 08/31/2021 11:22:01 - INFO - __main__ - Step 121771: {'lr': 4.355853140263635e-05, 'samples': 23380032, 'steps': 121770, 'loss/train': 1.5000433921813965} 08/31/2021 11:22:01 - INFO - __main__ - Step 121772: {'lr': 4.355553837608078e-05, 'samples': 23380224, 'steps': 121771, 'loss/train': 1.4572902917861938} 08/31/2021 11:22:02 - INFO - __main__ - Step 121773: {'lr': 4.3552545442545885e-05, 'samples': 23380416, 'steps': 121772, 'loss/train': 0.5198424458503723} 08/31/2021 11:22:03 - INFO - __main__ - Step 121774: {'lr': 4.354955260203311e-05, 'samples': 23380608, 'steps': 121773, 'loss/train': 1.1074150800704956} 08/31/2021 11:22:04 - INFO - __main__ - Step 121775: {'lr': 4.3546559854543645e-05, 'samples': 23380800, 'steps': 121774, 'loss/train': 0.8305903673171997} 08/31/2021 11:22:04 - INFO - __main__ - Step 121776: {'lr': 4.354356720007893e-05, 'samples': 23380992, 'steps': 121775, 'loss/train': 0.6866087317466736} 08/31/2021 11:22:04 - INFO - __main__ - Step 121777: {'lr': 4.354057463864028e-05, 'samples': 23381184, 'steps': 121776, 'loss/train': 1.0544089078903198} 08/31/2021 11:22:05 - INFO - __main__ - Step 121778: {'lr': 4.353758217022907e-05, 'samples': 23381376, 'steps': 121777, 'loss/train': 0.15346159040927887} 08/31/2021 11:22:06 - INFO - __main__ - Step 121779: {'lr': 4.353458979484665e-05, 'samples': 23381568, 'steps': 121778, 'loss/train': 0.8597381711006165} 08/31/2021 11:22:07 - INFO - __main__ - Step 121780: {'lr': 4.353159751249433e-05, 'samples': 23381760, 'steps': 121779, 'loss/train': 0.9833296537399292} 08/31/2021 11:22:07 - INFO - __main__ - Step 121781: {'lr': 4.352860532317352e-05, 'samples': 23381952, 'steps': 121780, 'loss/train': 4.73228645324707} 08/31/2021 11:22:07 - INFO - __main__ - Step 121782: {'lr': 4.3525613226885504e-05, 'samples': 23382144, 'steps': 121781, 'loss/train': 1.4798303842544556} 08/31/2021 11:22:08 - INFO - __main__ - Step 121783: {'lr': 4.352262122363168e-05, 'samples': 23382336, 'steps': 121782, 'loss/train': 0.17526231706142426} 08/31/2021 11:22:08 - INFO - __main__ - Step 121784: {'lr': 4.351962931341339e-05, 'samples': 23382528, 'steps': 121783, 'loss/train': 1.2844971418380737} 08/31/2021 11:22:10 - INFO - __main__ - Step 121785: {'lr': 4.3516637496231945e-05, 'samples': 23382720, 'steps': 121784, 'loss/train': 1.2755229473114014} 08/31/2021 11:22:10 - INFO - __main__ - Step 121786: {'lr': 4.351364577208872e-05, 'samples': 23382912, 'steps': 121785, 'loss/train': 0.7485902309417725} 08/31/2021 11:22:11 - INFO - __main__ - Step 121787: {'lr': 4.351065414098504e-05, 'samples': 23383104, 'steps': 121786, 'loss/train': 0.9098546504974365} 08/31/2021 11:22:11 - INFO - __main__ - Step 121788: {'lr': 4.3507662602922354e-05, 'samples': 23383296, 'steps': 121787, 'loss/train': 1.3623428344726562} 08/31/2021 11:22:11 - INFO - __main__ - Step 121789: {'lr': 4.350467115790188e-05, 'samples': 23383488, 'steps': 121788, 'loss/train': 0.044335149228572845} 08/31/2021 11:22:13 - INFO - __main__ - Step 121790: {'lr': 4.350167980592501e-05, 'samples': 23383680, 'steps': 121789, 'loss/train': 0.05117455869913101} 08/31/2021 11:22:13 - INFO - __main__ - Step 121791: {'lr': 4.34986885469931e-05, 'samples': 23383872, 'steps': 121790, 'loss/train': 1.1177664995193481} 08/31/2021 11:22:14 - INFO - __main__ - Step 121792: {'lr': 4.349569738110748e-05, 'samples': 23384064, 'steps': 121791, 'loss/train': 0.9032440781593323} 08/31/2021 11:22:14 - INFO - __main__ - Step 121793: {'lr': 4.349270630826952e-05, 'samples': 23384256, 'steps': 121792, 'loss/train': 1.5301910638809204} 08/31/2021 11:22:15 - INFO - __main__ - Step 121794: {'lr': 4.3489715328480535e-05, 'samples': 23384448, 'steps': 121793, 'loss/train': 1.3832778930664062} 08/31/2021 11:22:16 - INFO - __main__ - Step 121795: {'lr': 4.348672444174192e-05, 'samples': 23384640, 'steps': 121794, 'loss/train': 1.2288987636566162} 08/31/2021 11:22:16 - INFO - __main__ - Step 121796: {'lr': 4.3483733648055023e-05, 'samples': 23384832, 'steps': 121795, 'loss/train': 1.5053383111953735} 08/31/2021 11:22:17 - INFO - __main__ - Step 121797: {'lr': 4.348074294742113e-05, 'samples': 23385024, 'steps': 121796, 'loss/train': 1.5508555173873901} 08/31/2021 11:22:17 - INFO - __main__ - Step 121798: {'lr': 4.3477752339841634e-05, 'samples': 23385216, 'steps': 121797, 'loss/train': 1.7558032274246216} 08/31/2021 11:22:17 - INFO - __main__ - Step 121799: {'lr': 4.34747618253179e-05, 'samples': 23385408, 'steps': 121798, 'loss/train': 1.1845864057540894} 08/31/2021 11:22:19 - INFO - __main__ - Step 121800: {'lr': 4.347177140385122e-05, 'samples': 23385600, 'steps': 121799, 'loss/train': 1.032440185546875} 08/31/2021 11:22:20 - INFO - __main__ - Step 121801: {'lr': 4.3468781075443084e-05, 'samples': 23385792, 'steps': 121800, 'loss/train': 0.1257857233285904} 08/31/2021 11:22:20 - INFO - __main__ - Step 121802: {'lr': 4.346579084009461e-05, 'samples': 23385984, 'steps': 121801, 'loss/train': 1.097045660018921} 08/31/2021 11:22:20 - INFO - __main__ - Step 121803: {'lr': 4.346280069780731e-05, 'samples': 23386176, 'steps': 121802, 'loss/train': 1.3479554653167725} 08/31/2021 11:22:21 - INFO - __main__ - Step 121804: {'lr': 4.345981064858245e-05, 'samples': 23386368, 'steps': 121803, 'loss/train': 1.2602494955062866} 08/31/2021 11:22:23 - INFO - __main__ - Step 121805: {'lr': 4.345682069242144e-05, 'samples': 23386560, 'steps': 121804, 'loss/train': 1.199600100517273} 08/31/2021 11:22:23 - INFO - __main__ - Step 121806: {'lr': 4.345383082932558e-05, 'samples': 23386752, 'steps': 121805, 'loss/train': 1.2284400463104248} 08/31/2021 11:22:23 - INFO - __main__ - Step 121807: {'lr': 4.345084105929622e-05, 'samples': 23386944, 'steps': 121806, 'loss/train': 0.8555254936218262} 08/31/2021 11:22:24 - INFO - __main__ - Step 121808: {'lr': 4.3447851382334755e-05, 'samples': 23387136, 'steps': 121807, 'loss/train': 0.7893178462982178} 08/31/2021 11:22:24 - INFO - __main__ - Step 121809: {'lr': 4.3444861798442483e-05, 'samples': 23387328, 'steps': 121808, 'loss/train': 1.3301351070404053} 08/31/2021 11:22:24 - INFO - __main__ - Step 121810: {'lr': 4.344187230762078e-05, 'samples': 23387520, 'steps': 121809, 'loss/train': 1.1289211511611938} 08/31/2021 11:22:26 - INFO - __main__ - Step 121811: {'lr': 4.3438882909870967e-05, 'samples': 23387712, 'steps': 121810, 'loss/train': 0.9139118194580078} 08/31/2021 11:22:26 - INFO - __main__ - Step 121812: {'lr': 4.3435893605194425e-05, 'samples': 23387904, 'steps': 121811, 'loss/train': 1.6739009618759155} 08/31/2021 11:22:27 - INFO - __main__ - Step 121813: {'lr': 4.343290439359249e-05, 'samples': 23388096, 'steps': 121812, 'loss/train': 1.182713508605957} 08/31/2021 11:22:27 - INFO - __main__ - Step 121814: {'lr': 4.3429915275066486e-05, 'samples': 23388288, 'steps': 121813, 'loss/train': 0.9329715967178345} 08/31/2021 11:22:27 - INFO - __main__ - Step 121815: {'lr': 4.342692624961783e-05, 'samples': 23388480, 'steps': 121814, 'loss/train': 0.8243206739425659} 08/31/2021 11:22:29 - INFO - __main__ - Step 121816: {'lr': 4.342393731724775e-05, 'samples': 23388672, 'steps': 121815, 'loss/train': 1.106802225112915} 08/31/2021 11:22:29 - INFO - __main__ - Step 121817: {'lr': 4.342094847795766e-05, 'samples': 23388864, 'steps': 121816, 'loss/train': 1.201330542564392} 08/31/2021 11:22:30 - INFO - __main__ - Step 121818: {'lr': 4.341795973174892e-05, 'samples': 23389056, 'steps': 121817, 'loss/train': 1.1884233951568604} 08/31/2021 11:22:30 - INFO - __main__ - Step 121819: {'lr': 4.341497107862283e-05, 'samples': 23389248, 'steps': 121818, 'loss/train': 1.914346694946289} 08/31/2021 11:22:30 - INFO - __main__ - Step 121820: {'lr': 4.341198251858078e-05, 'samples': 23389440, 'steps': 121819, 'loss/train': 1.3846478462219238} 08/31/2021 11:22:32 - INFO - __main__ - Step 121821: {'lr': 4.340899405162413e-05, 'samples': 23389632, 'steps': 121820, 'loss/train': 1.0953168869018555} 08/31/2021 11:22:33 - INFO - __main__ - Step 121822: {'lr': 4.3406005677754156e-05, 'samples': 23389824, 'steps': 121821, 'loss/train': 1.4745597839355469} 08/31/2021 11:22:33 - INFO - __main__ - Step 121823: {'lr': 4.3403017396972275e-05, 'samples': 23390016, 'steps': 121822, 'loss/train': 0.6867190003395081} 08/31/2021 11:22:34 - INFO - __main__ - Step 121824: {'lr': 4.3400029209279795e-05, 'samples': 23390208, 'steps': 121823, 'loss/train': 1.234659194946289} 08/31/2021 11:22:34 - INFO - __main__ - Step 121825: {'lr': 4.339704111467807e-05, 'samples': 23390400, 'steps': 121824, 'loss/train': 0.014506999403238297} 08/31/2021 11:22:34 - INFO - __main__ - Step 121826: {'lr': 4.3394053113168464e-05, 'samples': 23390592, 'steps': 121825, 'loss/train': 0.9578813314437866} 08/31/2021 11:22:36 - INFO - __main__ - Step 121827: {'lr': 4.339106520475231e-05, 'samples': 23390784, 'steps': 121826, 'loss/train': 0.025449147447943687} 08/31/2021 11:22:37 - INFO - __main__ - Step 121828: {'lr': 4.338807738943098e-05, 'samples': 23390976, 'steps': 121827, 'loss/train': 1.2507492303848267} 08/31/2021 11:22:37 - INFO - __main__ - Step 121829: {'lr': 4.338508966720578e-05, 'samples': 23391168, 'steps': 121828, 'loss/train': 1.5718293190002441} 08/31/2021 11:22:37 - INFO - __main__ - Step 121830: {'lr': 4.3382102038078046e-05, 'samples': 23391360, 'steps': 121829, 'loss/train': 1.4800028800964355} 08/31/2021 11:22:38 - INFO - __main__ - Step 121831: {'lr': 4.337911450204915e-05, 'samples': 23391552, 'steps': 121830, 'loss/train': 0.2641676068305969} 08/31/2021 11:22:40 - INFO - __main__ - Step 121832: {'lr': 4.337612705912045e-05, 'samples': 23391744, 'steps': 121831, 'loss/train': 1.1030833721160889} 08/31/2021 11:22:41 - INFO - __main__ - Step 121833: {'lr': 4.337313970929327e-05, 'samples': 23391936, 'steps': 121832, 'loss/train': 1.0392193794250488} 08/31/2021 11:22:41 - INFO - __main__ - Step 121834: {'lr': 4.3370152452568954e-05, 'samples': 23392128, 'steps': 121833, 'loss/train': 0.8065193891525269} 08/31/2021 11:22:41 - INFO - __main__ - Step 121835: {'lr': 4.3367165288948876e-05, 'samples': 23392320, 'steps': 121834, 'loss/train': 1.7498317956924438} 08/31/2021 11:22:42 - INFO - __main__ - Step 121836: {'lr': 4.336417821843436e-05, 'samples': 23392512, 'steps': 121835, 'loss/train': 1.7349932193756104} 08/31/2021 11:22:42 - INFO - __main__ - Step 121837: {'lr': 4.336119124102675e-05, 'samples': 23392704, 'steps': 121836, 'loss/train': 0.8912404179573059} 08/31/2021 11:22:42 - INFO - __main__ - Step 121838: {'lr': 4.335820435672738e-05, 'samples': 23392896, 'steps': 121837, 'loss/train': 0.790531575679779} 08/31/2021 11:22:43 - INFO - __main__ - Step 121839: {'lr': 4.335521756553765e-05, 'samples': 23393088, 'steps': 121838, 'loss/train': 1.0357024669647217} 08/31/2021 11:22:44 - INFO - __main__ - Step 121840: {'lr': 4.3352230867458845e-05, 'samples': 23393280, 'steps': 121839, 'loss/train': 0.909164547920227} 08/31/2021 11:22:45 - INFO - __main__ - Step 121841: {'lr': 4.334924426249243e-05, 'samples': 23393472, 'steps': 121840, 'loss/train': 0.9389726519584656} 08/31/2021 11:22:45 - INFO - __main__ - Step 121842: {'lr': 4.334625775063958e-05, 'samples': 23393664, 'steps': 121841, 'loss/train': 1.199452519416809} 08/31/2021 11:22:45 - INFO - __main__ - Step 121843: {'lr': 4.334327133190169e-05, 'samples': 23393856, 'steps': 121842, 'loss/train': 1.1785308122634888} 08/31/2021 11:22:46 - INFO - __main__ - Step 121844: {'lr': 4.334028500628015e-05, 'samples': 23394048, 'steps': 121843, 'loss/train': 0.7773004174232483} 08/31/2021 11:22:47 - INFO - __main__ - Step 121845: {'lr': 4.333729877377632e-05, 'samples': 23394240, 'steps': 121844, 'loss/train': 1.1876142024993896} 08/31/2021 11:22:48 - INFO - __main__ - Step 121846: {'lr': 4.333431263439147e-05, 'samples': 23394432, 'steps': 121845, 'loss/train': 1.195940375328064} 08/31/2021 11:22:48 - INFO - __main__ - Step 121847: {'lr': 4.333132658812702e-05, 'samples': 23394624, 'steps': 121846, 'loss/train': 1.1527862548828125} 08/31/2021 11:22:48 - INFO - __main__ - Step 121848: {'lr': 4.332834063498425e-05, 'samples': 23394816, 'steps': 121847, 'loss/train': 0.9025287628173828} 08/31/2021 11:22:49 - INFO - __main__ - Step 121849: {'lr': 4.3325354774964576e-05, 'samples': 23395008, 'steps': 121848, 'loss/train': 1.0210297107696533} 08/31/2021 11:22:50 - INFO - __main__ - Step 121850: {'lr': 4.3322369008069296e-05, 'samples': 23395200, 'steps': 121849, 'loss/train': 1.4289072751998901} 08/31/2021 11:22:51 - INFO - __main__ - Step 121851: {'lr': 4.331938333429977e-05, 'samples': 23395392, 'steps': 121850, 'loss/train': 1.1184898614883423} 08/31/2021 11:22:51 - INFO - __main__ - Step 121852: {'lr': 4.331639775365734e-05, 'samples': 23395584, 'steps': 121851, 'loss/train': 0.34244588017463684} 08/31/2021 11:22:51 - INFO - __main__ - Step 121853: {'lr': 4.331341226614335e-05, 'samples': 23395776, 'steps': 121852, 'loss/train': 1.0144057273864746} 08/31/2021 11:22:52 - INFO - __main__ - Step 121854: {'lr': 4.331042687175915e-05, 'samples': 23395968, 'steps': 121853, 'loss/train': 0.6474495530128479} 08/31/2021 11:22:52 - INFO - __main__ - Step 121855: {'lr': 4.3307441570506116e-05, 'samples': 23396160, 'steps': 121854, 'loss/train': 1.237218976020813} 08/31/2021 11:22:54 - INFO - __main__ - Step 121856: {'lr': 4.330445636238553e-05, 'samples': 23396352, 'steps': 121855, 'loss/train': 1.1293909549713135} 08/31/2021 11:22:55 - INFO - __main__ - Step 121857: {'lr': 4.330147124739875e-05, 'samples': 23396544, 'steps': 121856, 'loss/train': 1.196394443511963} 08/31/2021 11:22:55 - INFO - __main__ - Step 121858: {'lr': 4.329848622554716e-05, 'samples': 23396736, 'steps': 121857, 'loss/train': 1.0446946620941162} 08/31/2021 11:22:56 - INFO - __main__ - Step 121859: {'lr': 4.329550129683207e-05, 'samples': 23396928, 'steps': 121858, 'loss/train': 0.9993010759353638} 08/31/2021 11:22:56 - INFO - __main__ - Step 121860: {'lr': 4.329251646125482e-05, 'samples': 23397120, 'steps': 121859, 'loss/train': 0.8077026009559631} 08/31/2021 11:22:57 - INFO - __main__ - Step 121861: {'lr': 4.32895317188168e-05, 'samples': 23397312, 'steps': 121860, 'loss/train': 0.9185535311698914} 08/31/2021 11:22:58 - INFO - __main__ - Step 121862: {'lr': 4.3286547069519316e-05, 'samples': 23397504, 'steps': 121861, 'loss/train': 0.09815409779548645} 08/31/2021 11:22:58 - INFO - __main__ - Step 121863: {'lr': 4.3283562513363714e-05, 'samples': 23397696, 'steps': 121862, 'loss/train': 0.9988550543785095} 08/31/2021 11:22:59 - INFO - __main__ - Step 121864: {'lr': 4.328057805035135e-05, 'samples': 23397888, 'steps': 121863, 'loss/train': 1.400620698928833} 08/31/2021 11:22:59 - INFO - __main__ - Step 121865: {'lr': 4.327759368048359e-05, 'samples': 23398080, 'steps': 121864, 'loss/train': 0.8934900760650635} 08/31/2021 11:23:00 - INFO - __main__ - Step 121866: {'lr': 4.327460940376174e-05, 'samples': 23398272, 'steps': 121865, 'loss/train': 1.4744325876235962} 08/31/2021 11:23:01 - INFO - __main__ - Step 121867: {'lr': 4.327162522018715e-05, 'samples': 23398464, 'steps': 121866, 'loss/train': 1.0865373611450195} 08/31/2021 11:23:01 - INFO - __main__ - Step 121868: {'lr': 4.326864112976125e-05, 'samples': 23398656, 'steps': 121867, 'loss/train': 0.7443650960922241} 08/31/2021 11:23:02 - INFO - __main__ - Step 121869: {'lr': 4.326565713248526e-05, 'samples': 23398848, 'steps': 121868, 'loss/train': 1.1620912551879883} 08/31/2021 11:23:02 - INFO - __main__ - Step 121870: {'lr': 4.326267322836056e-05, 'samples': 23399040, 'steps': 121869, 'loss/train': 1.1831066608428955} 08/31/2021 11:23:03 - INFO - __main__ - Step 121871: {'lr': 4.3259689417388534e-05, 'samples': 23399232, 'steps': 121870, 'loss/train': 0.26357918977737427} 08/31/2021 11:23:04 - INFO - __main__ - Step 121872: {'lr': 4.325670569957046e-05, 'samples': 23399424, 'steps': 121871, 'loss/train': 1.2472071647644043} 08/31/2021 11:23:04 - INFO - __main__ - Step 121873: {'lr': 4.325372207490774e-05, 'samples': 23399616, 'steps': 121872, 'loss/train': 0.9266144633293152} 08/31/2021 11:23:05 - INFO - __main__ - Step 121874: {'lr': 4.325073854340172e-05, 'samples': 23399808, 'steps': 121873, 'loss/train': 0.9497172236442566} 08/31/2021 11:23:05 - INFO - __main__ - Step 121875: {'lr': 4.3247755105053715e-05, 'samples': 23400000, 'steps': 121874, 'loss/train': 1.7817729711532593} 08/31/2021 11:23:07 - INFO - __main__ - Step 121876: {'lr': 4.3244771759865075e-05, 'samples': 23400192, 'steps': 121875, 'loss/train': 1.2912787199020386} 08/31/2021 11:23:07 - INFO - __main__ - Step 121877: {'lr': 4.3241788507837164e-05, 'samples': 23400384, 'steps': 121876, 'loss/train': 1.1299316883087158} 08/31/2021 11:23:07 - INFO - __main__ - Step 121878: {'lr': 4.323880534897129e-05, 'samples': 23400576, 'steps': 121877, 'loss/train': 0.20315596461296082} 08/31/2021 11:23:08 - INFO - __main__ - Step 121879: {'lr': 4.3235822283268835e-05, 'samples': 23400768, 'steps': 121878, 'loss/train': 1.2890069484710693} 08/31/2021 11:23:08 - INFO - __main__ - Step 121880: {'lr': 4.3232839310731134e-05, 'samples': 23400960, 'steps': 121879, 'loss/train': 1.2813005447387695} 08/31/2021 11:23:08 - INFO - __main__ - Step 121881: {'lr': 4.3229856431359515e-05, 'samples': 23401152, 'steps': 121880, 'loss/train': 1.6490693092346191} 08/31/2021 11:23:10 - INFO - __main__ - Step 121882: {'lr': 4.32268736451554e-05, 'samples': 23401344, 'steps': 121881, 'loss/train': 0.8868131041526794} 08/31/2021 11:23:10 - INFO - __main__ - Step 121883: {'lr': 4.322389095212001e-05, 'samples': 23401536, 'steps': 121882, 'loss/train': 1.0169528722763062} 08/31/2021 11:23:11 - INFO - __main__ - Step 121884: {'lr': 4.322090835225473e-05, 'samples': 23401728, 'steps': 121883, 'loss/train': 1.4010686874389648} 08/31/2021 11:23:11 - INFO - __main__ - Step 121885: {'lr': 4.321792584556092e-05, 'samples': 23401920, 'steps': 121884, 'loss/train': 0.9515737891197205} 08/31/2021 11:23:11 - INFO - __main__ - Step 121886: {'lr': 4.321494343203994e-05, 'samples': 23402112, 'steps': 121885, 'loss/train': 1.2920724153518677} 08/31/2021 11:23:13 - INFO - __main__ - Step 121887: {'lr': 4.321196111169309e-05, 'samples': 23402304, 'steps': 121886, 'loss/train': 1.630184292793274} 08/31/2021 11:23:13 - INFO - __main__ - Step 121888: {'lr': 4.3208978884521744e-05, 'samples': 23402496, 'steps': 121887, 'loss/train': 0.7066516876220703} 08/31/2021 11:23:14 - INFO - __main__ - Step 121889: {'lr': 4.3205996750527246e-05, 'samples': 23402688, 'steps': 121888, 'loss/train': 0.3867778480052948} 08/31/2021 11:23:14 - INFO - __main__ - Step 121890: {'lr': 4.320301470971094e-05, 'samples': 23402880, 'steps': 121889, 'loss/train': 1.0068607330322266} 08/31/2021 11:23:14 - INFO - __main__ - Step 121891: {'lr': 4.3200032762074154e-05, 'samples': 23403072, 'steps': 121890, 'loss/train': 0.7938846945762634} 08/31/2021 11:23:16 - INFO - __main__ - Step 121892: {'lr': 4.319705090761825e-05, 'samples': 23403264, 'steps': 121891, 'loss/train': 2.226715326309204} 08/31/2021 11:23:16 - INFO - __main__ - Step 121893: {'lr': 4.319406914634455e-05, 'samples': 23403456, 'steps': 121892, 'loss/train': 2.2943286895751953} 08/31/2021 11:23:17 - INFO - __main__ - Step 121894: {'lr': 4.3191087478254424e-05, 'samples': 23403648, 'steps': 121893, 'loss/train': 1.1319921016693115} 08/31/2021 11:23:17 - INFO - __main__ - Step 121895: {'lr': 4.318810590334926e-05, 'samples': 23403840, 'steps': 121894, 'loss/train': 0.9727373719215393} 08/31/2021 11:23:17 - INFO - __main__ - Step 121896: {'lr': 4.318512442163031e-05, 'samples': 23404032, 'steps': 121895, 'loss/train': 1.1755356788635254} 08/31/2021 11:23:19 - INFO - __main__ - Step 121897: {'lr': 4.318214303309892e-05, 'samples': 23404224, 'steps': 121896, 'loss/train': 1.2910889387130737} 08/31/2021 11:23:19 - INFO - __main__ - Step 121898: {'lr': 4.317916173775646e-05, 'samples': 23404416, 'steps': 121897, 'loss/train': 1.246617317199707} 08/31/2021 11:23:20 - INFO - __main__ - Step 121899: {'lr': 4.317618053560429e-05, 'samples': 23404608, 'steps': 121898, 'loss/train': 1.1177531480789185} 08/31/2021 11:23:20 - INFO - __main__ - Step 121900: {'lr': 4.3173199426643746e-05, 'samples': 23404800, 'steps': 121899, 'loss/train': 1.8740348815917969} 08/31/2021 11:23:20 - INFO - __main__ - Step 121901: {'lr': 4.317021841087615e-05, 'samples': 23404992, 'steps': 121900, 'loss/train': 0.9814704656600952} 08/31/2021 11:23:22 - INFO - __main__ - Step 121902: {'lr': 4.31672374883029e-05, 'samples': 23405184, 'steps': 121901, 'loss/train': 1.6157501935958862} 08/31/2021 11:23:23 - INFO - __main__ - Step 121903: {'lr': 4.316425665892526e-05, 'samples': 23405376, 'steps': 121902, 'loss/train': 0.7593932747840881} 08/31/2021 11:23:23 - INFO - __main__ - Step 121904: {'lr': 4.316127592274463e-05, 'samples': 23405568, 'steps': 121903, 'loss/train': 1.206189751625061} 08/31/2021 11:23:24 - INFO - __main__ - Step 121905: {'lr': 4.315829527976234e-05, 'samples': 23405760, 'steps': 121904, 'loss/train': 0.898752748966217} 08/31/2021 11:23:24 - INFO - __main__ - Step 121906: {'lr': 4.315531472997972e-05, 'samples': 23405952, 'steps': 121905, 'loss/train': 0.33958700299263} 08/31/2021 11:23:24 - INFO - __main__ - Step 121907: {'lr': 4.3152334273398156e-05, 'samples': 23406144, 'steps': 121906, 'loss/train': 0.01684213988482952} 08/31/2021 11:23:26 - INFO - __main__ - Step 121908: {'lr': 4.314935391001892e-05, 'samples': 23406336, 'steps': 121907, 'loss/train': 0.016255294904112816} 08/31/2021 11:23:27 - INFO - __main__ - Step 121909: {'lr': 4.3146373639843474e-05, 'samples': 23406528, 'steps': 121908, 'loss/train': 1.1669511795043945} 08/31/2021 11:23:27 - INFO - __main__ - Step 121910: {'lr': 4.314339346287299e-05, 'samples': 23406720, 'steps': 121909, 'loss/train': 1.504950761795044} 08/31/2021 11:23:27 - INFO - __main__ - Step 121911: {'lr': 4.314041337910893e-05, 'samples': 23406912, 'steps': 121910, 'loss/train': 1.5709530115127563} 08/31/2021 11:23:28 - INFO - __main__ - Step 121912: {'lr': 4.313743338855261e-05, 'samples': 23407104, 'steps': 121911, 'loss/train': 0.9260172843933105} 08/31/2021 11:23:30 - INFO - __main__ - Step 121913: {'lr': 4.313445349120537e-05, 'samples': 23407296, 'steps': 121912, 'loss/train': 0.16930319368839264} 08/31/2021 11:23:30 - INFO - __main__ - Step 121914: {'lr': 4.3131473687068544e-05, 'samples': 23407488, 'steps': 121913, 'loss/train': 0.8461668491363525} 08/31/2021 11:23:30 - INFO - __main__ - Step 121915: {'lr': 4.312849397614349e-05, 'samples': 23407680, 'steps': 121914, 'loss/train': 1.2937082052230835} 08/31/2021 11:23:31 - INFO - __main__ - Step 121916: {'lr': 4.312551435843154e-05, 'samples': 23407872, 'steps': 121915, 'loss/train': 0.027646014466881752} 08/31/2021 11:23:31 - INFO - __main__ - Step 121917: {'lr': 4.312253483393402e-05, 'samples': 23408064, 'steps': 121916, 'loss/train': 0.015268971212208271} 08/31/2021 11:23:31 - INFO - __main__ - Step 121918: {'lr': 4.3119555402652334e-05, 'samples': 23408256, 'steps': 121917, 'loss/train': 1.1633931398391724} 08/31/2021 11:23:32 - INFO - __main__ - Step 121919: {'lr': 4.311657606458774e-05, 'samples': 23408448, 'steps': 121918, 'loss/train': 1.1606727838516235} 08/31/2021 11:23:33 - INFO - __main__ - Step 121920: {'lr': 4.311359681974167e-05, 'samples': 23408640, 'steps': 121919, 'loss/train': 0.7260506749153137} 08/31/2021 11:23:34 - INFO - __main__ - Step 121921: {'lr': 4.3110617668115384e-05, 'samples': 23408832, 'steps': 121920, 'loss/train': 1.5138006210327148} 08/31/2021 11:23:34 - INFO - __main__ - Step 121922: {'lr': 4.3107638609710346e-05, 'samples': 23409024, 'steps': 121921, 'loss/train': 1.1276285648345947} 08/31/2021 11:23:35 - INFO - __main__ - Step 121923: {'lr': 4.310465964452773e-05, 'samples': 23409216, 'steps': 121922, 'loss/train': 0.41574642062187195} 08/31/2021 11:23:35 - INFO - __main__ - Step 121924: {'lr': 4.3101680772568986e-05, 'samples': 23409408, 'steps': 121923, 'loss/train': 2.341392755508423} 08/31/2021 11:23:37 - INFO - __main__ - Step 121925: {'lr': 4.309870199383542e-05, 'samples': 23409600, 'steps': 121924, 'loss/train': 0.9165316820144653} 08/31/2021 11:23:37 - INFO - __main__ - Step 121926: {'lr': 4.309572330832839e-05, 'samples': 23409792, 'steps': 121925, 'loss/train': 1.1491758823394775} 08/31/2021 11:23:38 - INFO - __main__ - Step 121927: {'lr': 4.309274471604924e-05, 'samples': 23409984, 'steps': 121926, 'loss/train': 1.4018429517745972} 08/31/2021 11:23:38 - INFO - __main__ - Step 121928: {'lr': 4.308976621699928e-05, 'samples': 23410176, 'steps': 121927, 'loss/train': 0.44245341420173645} 08/31/2021 11:23:38 - INFO - __main__ - Step 121929: {'lr': 4.308678781117992e-05, 'samples': 23410368, 'steps': 121928, 'loss/train': 0.9571565389633179} 08/31/2021 11:23:40 - INFO - __main__ - Step 121930: {'lr': 4.308380949859242e-05, 'samples': 23410560, 'steps': 121929, 'loss/train': 0.3678487539291382} 08/31/2021 11:23:40 - INFO - __main__ - Step 121931: {'lr': 4.3080831279238174e-05, 'samples': 23410752, 'steps': 121930, 'loss/train': 0.6526389718055725} 08/31/2021 11:23:41 - INFO - __main__ - Step 121932: {'lr': 4.307785315311852e-05, 'samples': 23410944, 'steps': 121931, 'loss/train': 0.12309815734624863} 08/31/2021 11:23:41 - INFO - __main__ - Step 121933: {'lr': 4.307487512023481e-05, 'samples': 23411136, 'steps': 121932, 'loss/train': 1.1428159475326538} 08/31/2021 11:23:42 - INFO - __main__ - Step 121934: {'lr': 4.307189718058835e-05, 'samples': 23411328, 'steps': 121933, 'loss/train': 0.028170976787805557} 08/31/2021 11:23:42 - INFO - __main__ - Step 121935: {'lr': 4.306891933418047e-05, 'samples': 23411520, 'steps': 121934, 'loss/train': 1.2713618278503418} 08/31/2021 11:23:44 - INFO - __main__ - Step 121936: {'lr': 4.306594158101265e-05, 'samples': 23411712, 'steps': 121935, 'loss/train': 1.2990586757659912} 08/31/2021 11:23:44 - INFO - __main__ - Step 121937: {'lr': 4.306296392108605e-05, 'samples': 23411904, 'steps': 121936, 'loss/train': 0.7590096592903137} 08/31/2021 11:23:45 - INFO - __main__ - Step 121938: {'lr': 4.305998635440206e-05, 'samples': 23412096, 'steps': 121937, 'loss/train': 0.784222424030304} 08/31/2021 11:23:45 - INFO - __main__ - Step 121939: {'lr': 4.305700888096209e-05, 'samples': 23412288, 'steps': 121938, 'loss/train': 1.5696521997451782} 08/31/2021 11:23:45 - INFO - __main__ - Step 121940: {'lr': 4.305403150076739e-05, 'samples': 23412480, 'steps': 121939, 'loss/train': 1.45017409324646} 08/31/2021 11:23:46 - INFO - __main__ - Step 121941: {'lr': 4.3051054213819386e-05, 'samples': 23412672, 'steps': 121940, 'loss/train': 0.015235105529427528} 08/31/2021 11:23:47 - INFO - __main__ - Step 121942: {'lr': 4.304807702011937e-05, 'samples': 23412864, 'steps': 121941, 'loss/train': 0.9672529101371765} 08/31/2021 11:23:48 - INFO - __main__ - Step 121943: {'lr': 4.304509991966871e-05, 'samples': 23413056, 'steps': 121942, 'loss/train': 1.44584321975708} 08/31/2021 11:23:48 - INFO - __main__ - Step 121944: {'lr': 4.304212291246873e-05, 'samples': 23413248, 'steps': 121943, 'loss/train': 1.3715134859085083} 08/31/2021 11:23:48 - INFO - __main__ - Step 121945: {'lr': 4.303914599852077e-05, 'samples': 23413440, 'steps': 121944, 'loss/train': 0.7908012866973877} 08/31/2021 11:23:49 - INFO - __main__ - Step 121946: {'lr': 4.303616917782616e-05, 'samples': 23413632, 'steps': 121945, 'loss/train': 0.3723880350589752} 08/31/2021 11:23:50 - INFO - __main__ - Step 121947: {'lr': 4.303319245038628e-05, 'samples': 23413824, 'steps': 121946, 'loss/train': 0.043037451803684235} 08/31/2021 11:23:51 - INFO - __main__ - Step 121948: {'lr': 4.3030215816202453e-05, 'samples': 23414016, 'steps': 121947, 'loss/train': 0.12689624726772308} 08/31/2021 11:23:51 - INFO - __main__ - Step 121949: {'lr': 4.302723927527607e-05, 'samples': 23414208, 'steps': 121948, 'loss/train': 0.9137584567070007} 08/31/2021 11:23:51 - INFO - __main__ - Step 121950: {'lr': 4.302426282760835e-05, 'samples': 23414400, 'steps': 121949, 'loss/train': 0.39205145835876465} 08/31/2021 11:23:52 - INFO - __main__ - Step 121951: {'lr': 4.302128647320072e-05, 'samples': 23414592, 'steps': 121950, 'loss/train': 1.042481780052185} 08/31/2021 11:23:54 - INFO - __main__ - Step 121952: {'lr': 4.301831021205449e-05, 'samples': 23414784, 'steps': 121951, 'loss/train': 1.0999267101287842} 08/31/2021 11:23:54 - INFO - __main__ - Step 121953: {'lr': 4.3015334044171014e-05, 'samples': 23414976, 'steps': 121952, 'loss/train': 1.670637845993042} 08/31/2021 11:23:55 - INFO - __main__ - Step 121954: {'lr': 4.3012357969551666e-05, 'samples': 23415168, 'steps': 121953, 'loss/train': 1.6156476736068726} 08/31/2021 11:23:55 - INFO - __main__ - Step 121955: {'lr': 4.3009381988197707e-05, 'samples': 23415360, 'steps': 121954, 'loss/train': 1.174513578414917} 08/31/2021 11:23:55 - INFO - __main__ - Step 121956: {'lr': 4.300640610011056e-05, 'samples': 23415552, 'steps': 121955, 'loss/train': 0.7523964047431946} 08/31/2021 11:23:56 - INFO - __main__ - Step 121957: {'lr': 4.300343030529152e-05, 'samples': 23415744, 'steps': 121956, 'loss/train': 0.8651397228240967} 08/31/2021 11:23:57 - INFO - __main__ - Step 121958: {'lr': 4.300045460374194e-05, 'samples': 23415936, 'steps': 121957, 'loss/train': 0.07461004704236984} 08/31/2021 11:23:58 - INFO - __main__ - Step 121959: {'lr': 4.299747899546316e-05, 'samples': 23416128, 'steps': 121958, 'loss/train': 0.5079082250595093} 08/31/2021 11:23:58 - INFO - __main__ - Step 121960: {'lr': 4.299450348045653e-05, 'samples': 23416320, 'steps': 121959, 'loss/train': 0.7373031973838806} 08/31/2021 11:23:58 - INFO - __main__ - Step 121961: {'lr': 4.2991528058723446e-05, 'samples': 23416512, 'steps': 121960, 'loss/train': 1.0636924505233765} 08/31/2021 11:23:59 - INFO - __main__ - Step 121962: {'lr': 4.298855273026511e-05, 'samples': 23416704, 'steps': 121961, 'loss/train': 0.022841596975922585} 08/31/2021 11:24:01 - INFO - __main__ - Step 121963: {'lr': 4.2985577495082946e-05, 'samples': 23416896, 'steps': 121962, 'loss/train': 0.9963176846504211} 08/31/2021 11:24:02 - INFO - __main__ - Step 121964: {'lr': 4.2982602353178305e-05, 'samples': 23417088, 'steps': 121963, 'loss/train': 1.526065707206726} 08/31/2021 11:24:02 - INFO - __main__ - Step 121965: {'lr': 4.297962730455249e-05, 'samples': 23417280, 'steps': 121964, 'loss/train': 0.09447537362575531} 08/31/2021 11:24:02 - INFO - __main__ - Step 121966: {'lr': 4.297665234920686e-05, 'samples': 23417472, 'steps': 121965, 'loss/train': 1.7036939859390259} 08/31/2021 11:24:03 - INFO - __main__ - Step 121967: {'lr': 4.297367748714276e-05, 'samples': 23417664, 'steps': 121966, 'loss/train': 0.8320268988609314} 08/31/2021 11:24:03 - INFO - __main__ - Step 121968: {'lr': 4.297070271836151e-05, 'samples': 23417856, 'steps': 121967, 'loss/train': 1.5551259517669678} 08/31/2021 11:24:04 - INFO - __main__ - Step 121969: {'lr': 4.296772804286447e-05, 'samples': 23418048, 'steps': 121968, 'loss/train': 0.7328904271125793} 08/31/2021 11:24:05 - INFO - __main__ - Step 121970: {'lr': 4.296475346065301e-05, 'samples': 23418240, 'steps': 121969, 'loss/train': 0.8659166097640991} 08/31/2021 11:24:05 - INFO - __main__ - Step 121971: {'lr': 4.29617789717284e-05, 'samples': 23418432, 'steps': 121970, 'loss/train': 0.9663220643997192} 08/31/2021 11:24:06 - INFO - __main__ - Step 121972: {'lr': 4.295880457609211e-05, 'samples': 23418624, 'steps': 121971, 'loss/train': 1.134169340133667} 08/31/2021 11:24:06 - INFO - __main__ - Step 121973: {'lr': 4.29558302737453e-05, 'samples': 23418816, 'steps': 121972, 'loss/train': 1.293371319770813} 08/31/2021 11:24:07 - INFO - __main__ - Step 121974: {'lr': 4.2952856064689403e-05, 'samples': 23419008, 'steps': 121973, 'loss/train': 0.5137858390808105} 08/31/2021 11:24:08 - INFO - __main__ - Step 121975: {'lr': 4.294988194892577e-05, 'samples': 23419200, 'steps': 121974, 'loss/train': 0.29949823021888733} 08/31/2021 11:24:08 - INFO - __main__ - Step 121976: {'lr': 4.2946907926455696e-05, 'samples': 23419392, 'steps': 121975, 'loss/train': 1.4406832456588745} 08/31/2021 11:24:09 - INFO - __main__ - Step 121977: {'lr': 4.2943933997280584e-05, 'samples': 23419584, 'steps': 121976, 'loss/train': 0.19668690860271454} 08/31/2021 11:24:09 - INFO - __main__ - Step 121978: {'lr': 4.29409601614017e-05, 'samples': 23419776, 'steps': 121977, 'loss/train': 1.1720062494277954} 08/31/2021 11:24:11 - INFO - __main__ - Step 121979: {'lr': 4.2937986418820465e-05, 'samples': 23419968, 'steps': 121978, 'loss/train': 1.1548787355422974} 08/31/2021 11:24:11 - INFO - __main__ - Step 121980: {'lr': 4.293501276953815e-05, 'samples': 23420160, 'steps': 121979, 'loss/train': 1.5359693765640259} 08/31/2021 11:24:11 - INFO - __main__ - Step 121981: {'lr': 4.293203921355615e-05, 'samples': 23420352, 'steps': 121980, 'loss/train': 1.076627254486084} 08/31/2021 11:24:12 - INFO - __main__ - Step 121982: {'lr': 4.292906575087574e-05, 'samples': 23420544, 'steps': 121981, 'loss/train': 1.4396268129348755} 08/31/2021 11:24:12 - INFO - __main__ - Step 121983: {'lr': 4.292609238149839e-05, 'samples': 23420736, 'steps': 121982, 'loss/train': 1.029810905456543} 08/31/2021 11:24:14 - INFO - __main__ - Step 121984: {'lr': 4.292311910542529e-05, 'samples': 23420928, 'steps': 121983, 'loss/train': 0.39637285470962524} 08/31/2021 11:24:14 - INFO - __main__ - Step 121985: {'lr': 4.29201459226578e-05, 'samples': 23421120, 'steps': 121984, 'loss/train': 1.1756911277770996} 08/31/2021 11:24:15 - INFO - __main__ - Step 121986: {'lr': 4.291717283319735e-05, 'samples': 23421312, 'steps': 121985, 'loss/train': 0.024802731350064278} 08/31/2021 11:24:15 - INFO - __main__ - Step 121987: {'lr': 4.2914199837045196e-05, 'samples': 23421504, 'steps': 121986, 'loss/train': 0.013749083504080772} 08/31/2021 11:24:15 - INFO - __main__ - Step 121988: {'lr': 4.2911226934202715e-05, 'samples': 23421696, 'steps': 121987, 'loss/train': 0.08793768286705017} 08/31/2021 11:24:16 - INFO - __main__ - Step 121989: {'lr': 4.290825412467123e-05, 'samples': 23421888, 'steps': 121988, 'loss/train': 0.9435227513313293} 08/31/2021 11:24:17 - INFO - __main__ - Step 121990: {'lr': 4.290528140845209e-05, 'samples': 23422080, 'steps': 121989, 'loss/train': 1.326452612876892} 08/31/2021 11:24:18 - INFO - __main__ - Step 121991: {'lr': 4.290230878554663e-05, 'samples': 23422272, 'steps': 121990, 'loss/train': 1.1910436153411865} 08/31/2021 11:24:18 - INFO - __main__ - Step 121992: {'lr': 4.289933625595621e-05, 'samples': 23422464, 'steps': 121991, 'loss/train': 1.239437222480774} 08/31/2021 11:24:18 - INFO - __main__ - Step 121993: {'lr': 4.289636381968215e-05, 'samples': 23422656, 'steps': 121992, 'loss/train': 1.5702165365219116} 08/31/2021 11:24:19 - INFO - __main__ - Step 121994: {'lr': 4.289339147672586e-05, 'samples': 23422848, 'steps': 121993, 'loss/train': 0.9498289227485657} 08/31/2021 11:24:20 - INFO - __main__ - Step 121995: {'lr': 4.289041922708853e-05, 'samples': 23423040, 'steps': 121994, 'loss/train': 0.9603037238121033} 08/31/2021 11:24:21 - INFO - __main__ - Step 121996: {'lr': 4.288744707077158e-05, 'samples': 23423232, 'steps': 121995, 'loss/train': 0.558137834072113} 08/31/2021 11:24:21 - INFO - __main__ - Step 121997: {'lr': 4.288447500777637e-05, 'samples': 23423424, 'steps': 121996, 'loss/train': 0.8510438203811646} 08/31/2021 11:24:21 - INFO - __main__ - Step 121998: {'lr': 4.2881503038104205e-05, 'samples': 23423616, 'steps': 121997, 'loss/train': 1.1948260068893433} 08/31/2021 11:24:22 - INFO - __main__ - Step 121999: {'lr': 4.287853116175644e-05, 'samples': 23423808, 'steps': 121998, 'loss/train': 1.5042438507080078} 08/31/2021 11:24:23 - INFO - __main__ - Step 122000: {'lr': 4.287555937873444e-05, 'samples': 23424000, 'steps': 121999, 'loss/train': 0.7519213557243347} 08/31/2021 11:24:24 - INFO - __main__ - Step 122001: {'lr': 4.287258768903948e-05, 'samples': 23424192, 'steps': 122000, 'loss/train': 0.9532705545425415} 08/31/2021 11:24:24 - INFO - __main__ - Step 122002: {'lr': 4.286961609267295e-05, 'samples': 23424384, 'steps': 122001, 'loss/train': 1.1956028938293457} 08/31/2021 11:24:24 - INFO - __main__ - Step 122003: {'lr': 4.286664458963618e-05, 'samples': 23424576, 'steps': 122002, 'loss/train': 1.1571859121322632} 08/31/2021 11:24:25 - INFO - __main__ - Step 122004: {'lr': 4.286367317993051e-05, 'samples': 23424768, 'steps': 122003, 'loss/train': 1.7157866954803467} 08/31/2021 11:24:26 - INFO - __main__ - Step 122005: {'lr': 4.286070186355731e-05, 'samples': 23424960, 'steps': 122004, 'loss/train': 0.12839829921722412} 08/31/2021 11:24:27 - INFO - __main__ - Step 122006: {'lr': 4.285773064051785e-05, 'samples': 23425152, 'steps': 122005, 'loss/train': 1.5655022859573364} 08/31/2021 11:24:27 - INFO - __main__ - Step 122007: {'lr': 4.285475951081347e-05, 'samples': 23425344, 'steps': 122006, 'loss/train': 0.2812041938304901} 08/31/2021 11:24:27 - INFO - __main__ - Step 122008: {'lr': 4.285178847444557e-05, 'samples': 23425536, 'steps': 122007, 'loss/train': 1.6167622804641724} 08/31/2021 11:24:28 - INFO - __main__ - Step 122009: {'lr': 4.284881753141542e-05, 'samples': 23425728, 'steps': 122008, 'loss/train': 0.7178393006324768} 08/31/2021 11:24:29 - INFO - __main__ - Step 122010: {'lr': 4.284584668172442e-05, 'samples': 23425920, 'steps': 122009, 'loss/train': 1.8367178440093994} 08/31/2021 11:24:30 - INFO - __main__ - Step 122011: {'lr': 4.2842875925373894e-05, 'samples': 23426112, 'steps': 122010, 'loss/train': 0.7780136466026306} 08/31/2021 11:24:30 - INFO - __main__ - Step 122012: {'lr': 4.2839905262365145e-05, 'samples': 23426304, 'steps': 122011, 'loss/train': 2.8282277584075928} 08/31/2021 11:24:30 - INFO - __main__ - Step 122013: {'lr': 4.2836934692699556e-05, 'samples': 23426496, 'steps': 122012, 'loss/train': 1.150961995124817} 08/31/2021 11:24:31 - INFO - __main__ - Step 122014: {'lr': 4.283396421637845e-05, 'samples': 23426688, 'steps': 122013, 'loss/train': 1.283263087272644} 08/31/2021 11:24:31 - INFO - __main__ - Step 122015: {'lr': 4.283099383340316e-05, 'samples': 23426880, 'steps': 122014, 'loss/train': 0.8819797039031982} 08/31/2021 11:24:33 - INFO - __main__ - Step 122016: {'lr': 4.2828023543775074e-05, 'samples': 23427072, 'steps': 122015, 'loss/train': 0.7596370577812195} 08/31/2021 11:24:34 - INFO - __main__ - Step 122017: {'lr': 4.2825053347495425e-05, 'samples': 23427264, 'steps': 122016, 'loss/train': 1.3419798612594604} 08/31/2021 11:24:34 - INFO - __main__ - Step 122018: {'lr': 4.282208324456563e-05, 'samples': 23427456, 'steps': 122017, 'loss/train': 0.9774446487426758} 08/31/2021 11:24:35 - INFO - __main__ - Step 122019: {'lr': 4.2819113234987e-05, 'samples': 23427648, 'steps': 122018, 'loss/train': 1.3926185369491577} 08/31/2021 11:24:35 - INFO - __main__ - Step 122020: {'lr': 4.281614331876088e-05, 'samples': 23427840, 'steps': 122019, 'loss/train': 1.6681721210479736} 08/31/2021 11:24:37 - INFO - __main__ - Step 122021: {'lr': 4.281317349588859e-05, 'samples': 23428032, 'steps': 122020, 'loss/train': 0.7436577677726746} 08/31/2021 11:24:37 - INFO - __main__ - Step 122022: {'lr': 4.281020376637151e-05, 'samples': 23428224, 'steps': 122021, 'loss/train': 1.408370018005371} 08/31/2021 11:24:37 - INFO - __main__ - Step 122023: {'lr': 4.280723413021095e-05, 'samples': 23428416, 'steps': 122022, 'loss/train': 0.15291666984558105} 08/31/2021 11:24:38 - INFO - __main__ - Step 122024: {'lr': 4.280426458740824e-05, 'samples': 23428608, 'steps': 122023, 'loss/train': 0.8971336483955383} 08/31/2021 11:24:38 - INFO - __main__ - Step 122025: {'lr': 4.280129513796474e-05, 'samples': 23428800, 'steps': 122024, 'loss/train': 2.025906562805176} 08/31/2021 11:24:40 - INFO - __main__ - Step 122026: {'lr': 4.2798325781881783e-05, 'samples': 23428992, 'steps': 122025, 'loss/train': 1.2684170007705688} 08/31/2021 11:24:41 - INFO - __main__ - Step 122027: {'lr': 4.2795356519160696e-05, 'samples': 23429184, 'steps': 122026, 'loss/train': 1.7376608848571777} 08/31/2021 11:24:41 - INFO - __main__ - Step 122028: {'lr': 4.279238734980284e-05, 'samples': 23429376, 'steps': 122027, 'loss/train': 0.9462764859199524} 08/31/2021 11:24:41 - INFO - __main__ - Step 122029: {'lr': 4.278941827380953e-05, 'samples': 23429568, 'steps': 122028, 'loss/train': 0.07703094184398651} 08/31/2021 11:24:42 - INFO - __main__ - Step 122030: {'lr': 4.2786449291182166e-05, 'samples': 23429760, 'steps': 122029, 'loss/train': 1.4904556274414062} 08/31/2021 11:24:42 - INFO - __main__ - Step 122031: {'lr': 4.278348040192198e-05, 'samples': 23429952, 'steps': 122030, 'loss/train': 1.7250162363052368} 08/31/2021 11:24:43 - INFO - __main__ - Step 122032: {'lr': 4.2780511606030334e-05, 'samples': 23430144, 'steps': 122031, 'loss/train': 0.3447665274143219} 08/31/2021 11:24:44 - INFO - __main__ - Step 122033: {'lr': 4.27775429035086e-05, 'samples': 23430336, 'steps': 122032, 'loss/train': 1.0309683084487915} 08/31/2021 11:24:44 - INFO - __main__ - Step 122034: {'lr': 4.277457429435813e-05, 'samples': 23430528, 'steps': 122033, 'loss/train': 0.6152199506759644} 08/31/2021 11:24:45 - INFO - __main__ - Step 122035: {'lr': 4.277160577858022e-05, 'samples': 23430720, 'steps': 122034, 'loss/train': 1.1295653581619263} 08/31/2021 11:24:45 - INFO - __main__ - Step 122036: {'lr': 4.2768637356176226e-05, 'samples': 23430912, 'steps': 122035, 'loss/train': 1.0484851598739624} 08/31/2021 11:24:47 - INFO - __main__ - Step 122037: {'lr': 4.276566902714751e-05, 'samples': 23431104, 'steps': 122036, 'loss/train': 1.6080336570739746} 08/31/2021 11:24:47 - INFO - __main__ - Step 122038: {'lr': 4.276270079149536e-05, 'samples': 23431296, 'steps': 122037, 'loss/train': 0.13041217625141144} 08/31/2021 11:24:47 - INFO - __main__ - Step 122039: {'lr': 4.2759732649221146e-05, 'samples': 23431488, 'steps': 122038, 'loss/train': 0.9540746808052063} 08/31/2021 11:24:48 - INFO - __main__ - Step 122040: {'lr': 4.275676460032621e-05, 'samples': 23431680, 'steps': 122039, 'loss/train': 0.7970938682556152} 08/31/2021 11:24:48 - INFO - __main__ - Step 122041: {'lr': 4.2753796644811854e-05, 'samples': 23431872, 'steps': 122040, 'loss/train': 1.0903702974319458} 08/31/2021 11:24:50 - INFO - __main__ - Step 122042: {'lr': 4.275082878267947e-05, 'samples': 23432064, 'steps': 122041, 'loss/train': 1.564833641052246} 08/31/2021 11:24:50 - INFO - __main__ - Step 122043: {'lr': 4.274786101393041e-05, 'samples': 23432256, 'steps': 122042, 'loss/train': 1.734823226928711} 08/31/2021 11:24:50 - INFO - __main__ - Step 122044: {'lr': 4.2744893338565905e-05, 'samples': 23432448, 'steps': 122043, 'loss/train': 0.8303336501121521} 08/31/2021 11:24:51 - INFO - __main__ - Step 122045: {'lr': 4.274192575658734e-05, 'samples': 23432640, 'steps': 122044, 'loss/train': 0.7513747215270996} 08/31/2021 11:24:51 - INFO - __main__ - Step 122046: {'lr': 4.2738958267996065e-05, 'samples': 23432832, 'steps': 122045, 'loss/train': 1.2512348890304565} 08/31/2021 11:24:53 - INFO - __main__ - Step 122047: {'lr': 4.2735990872793453e-05, 'samples': 23433024, 'steps': 122046, 'loss/train': 0.03177402913570404} 08/31/2021 11:24:53 - INFO - __main__ - Step 122048: {'lr': 4.273302357098077e-05, 'samples': 23433216, 'steps': 122047, 'loss/train': 0.6585137844085693} 08/31/2021 11:24:54 - INFO - __main__ - Step 122049: {'lr': 4.273005636255939e-05, 'samples': 23433408, 'steps': 122048, 'loss/train': 0.6234959363937378} 08/31/2021 11:24:54 - INFO - __main__ - Step 122050: {'lr': 4.272708924753066e-05, 'samples': 23433600, 'steps': 122049, 'loss/train': 1.501905083656311} 08/31/2021 11:24:54 - INFO - __main__ - Step 122051: {'lr': 4.2724122225895915e-05, 'samples': 23433792, 'steps': 122050, 'loss/train': 0.9794873595237732} 08/31/2021 11:24:56 - INFO - __main__ - Step 122052: {'lr': 4.272115529765647e-05, 'samples': 23433984, 'steps': 122051, 'loss/train': 1.1586745977401733} 08/31/2021 11:24:56 - INFO - __main__ - Step 122053: {'lr': 4.271818846281367e-05, 'samples': 23434176, 'steps': 122052, 'loss/train': 1.0600515604019165} 08/31/2021 11:24:57 - INFO - __main__ - Step 122054: {'lr': 4.271522172136885e-05, 'samples': 23434368, 'steps': 122053, 'loss/train': 0.7128415703773499} 08/31/2021 11:24:57 - INFO - __main__ - Step 122055: {'lr': 4.271225507332335e-05, 'samples': 23434560, 'steps': 122054, 'loss/train': 1.0731521844863892} 08/31/2021 11:24:57 - INFO - __main__ - Step 122056: {'lr': 4.2709288518678526e-05, 'samples': 23434752, 'steps': 122055, 'loss/train': 0.5781885385513306} 08/31/2021 11:24:59 - INFO - __main__ - Step 122057: {'lr': 4.270632205743577e-05, 'samples': 23434944, 'steps': 122056, 'loss/train': 1.490463137626648} 08/31/2021 11:24:59 - INFO - __main__ - Step 122058: {'lr': 4.270335568959627e-05, 'samples': 23435136, 'steps': 122057, 'loss/train': 1.6819095611572266} 08/31/2021 11:25:00 - INFO - __main__ - Step 122059: {'lr': 4.270038941516144e-05, 'samples': 23435328, 'steps': 122058, 'loss/train': 1.0948735475540161} 08/31/2021 11:25:00 - INFO - __main__ - Step 122060: {'lr': 4.269742323413262e-05, 'samples': 23435520, 'steps': 122059, 'loss/train': 1.2339545488357544} 08/31/2021 11:25:01 - INFO - __main__ - Step 122061: {'lr': 4.269445714651113e-05, 'samples': 23435712, 'steps': 122060, 'loss/train': 1.3490560054779053} 08/31/2021 11:25:01 - INFO - __main__ - Step 122062: {'lr': 4.269149115229831e-05, 'samples': 23435904, 'steps': 122061, 'loss/train': 0.8414096236228943} 08/31/2021 11:25:02 - INFO - __main__ - Step 122063: {'lr': 4.2688525251495525e-05, 'samples': 23436096, 'steps': 122062, 'loss/train': 1.044403076171875} 08/31/2021 11:25:03 - INFO - __main__ - Step 122064: {'lr': 4.26855594441041e-05, 'samples': 23436288, 'steps': 122063, 'loss/train': 1.0616706609725952} 08/31/2021 11:25:03 - INFO - __main__ - Step 122065: {'lr': 4.268259373012534e-05, 'samples': 23436480, 'steps': 122064, 'loss/train': 1.2321174144744873} 08/31/2021 11:25:04 - INFO - __main__ - Step 122066: {'lr': 4.267962810956061e-05, 'samples': 23436672, 'steps': 122065, 'loss/train': 0.9677568078041077} 08/31/2021 11:25:04 - INFO - __main__ - Step 122067: {'lr': 4.2676662582411235e-05, 'samples': 23436864, 'steps': 122066, 'loss/train': 0.7153642773628235} 08/31/2021 11:25:05 - INFO - __main__ - Step 122068: {'lr': 4.267369714867858e-05, 'samples': 23437056, 'steps': 122067, 'loss/train': 0.676577627658844} 08/31/2021 11:25:06 - INFO - __main__ - Step 122069: {'lr': 4.267073180836395e-05, 'samples': 23437248, 'steps': 122068, 'loss/train': 1.439979076385498} 08/31/2021 11:25:06 - INFO - __main__ - Step 122070: {'lr': 4.266776656146873e-05, 'samples': 23437440, 'steps': 122069, 'loss/train': 1.289149284362793} 08/31/2021 11:25:07 - INFO - __main__ - Step 122071: {'lr': 4.266480140799417e-05, 'samples': 23437632, 'steps': 122070, 'loss/train': 0.9403498768806458} 08/31/2021 11:25:07 - INFO - __main__ - Step 122072: {'lr': 4.266183634794166e-05, 'samples': 23437824, 'steps': 122071, 'loss/train': 1.1705820560455322} 08/31/2021 11:25:09 - INFO - __main__ - Step 122073: {'lr': 4.2658871381312494e-05, 'samples': 23438016, 'steps': 122072, 'loss/train': 1.242769718170166} 08/31/2021 11:25:10 - INFO - __main__ - Step 122074: {'lr': 4.265590650810808e-05, 'samples': 23438208, 'steps': 122073, 'loss/train': 0.21759112179279327} 08/31/2021 11:25:10 - INFO - __main__ - Step 122075: {'lr': 4.26529417283297e-05, 'samples': 23438400, 'steps': 122074, 'loss/train': 0.7609884142875671} 08/31/2021 11:25:11 - INFO - __main__ - Step 122076: {'lr': 4.2649977041978706e-05, 'samples': 23438592, 'steps': 122075, 'loss/train': 0.02348642796278} 08/31/2021 11:25:11 - INFO - __main__ - Step 122077: {'lr': 4.2647012449056414e-05, 'samples': 23438784, 'steps': 122076, 'loss/train': 0.6789617538452148} 08/31/2021 11:25:11 - INFO - __main__ - Step 122078: {'lr': 4.2644047949564194e-05, 'samples': 23438976, 'steps': 122077, 'loss/train': 0.014673013240098953} 08/31/2021 11:25:13 - INFO - __main__ - Step 122079: {'lr': 4.264108354350338e-05, 'samples': 23439168, 'steps': 122078, 'loss/train': 0.014835654757916927} 08/31/2021 11:25:13 - INFO - __main__ - Step 122080: {'lr': 4.263811923087527e-05, 'samples': 23439360, 'steps': 122079, 'loss/train': 1.8008044958114624} 08/31/2021 11:25:14 - INFO - __main__ - Step 122081: {'lr': 4.263515501168122e-05, 'samples': 23439552, 'steps': 122080, 'loss/train': 1.2319831848144531} 08/31/2021 11:25:14 - INFO - __main__ - Step 122082: {'lr': 4.26321908859226e-05, 'samples': 23439744, 'steps': 122081, 'loss/train': 1.4853036403656006} 08/31/2021 11:25:14 - INFO - __main__ - Step 122083: {'lr': 4.2629226853600766e-05, 'samples': 23439936, 'steps': 122082, 'loss/train': 1.040601372718811} 08/31/2021 11:25:16 - INFO - __main__ - Step 122084: {'lr': 4.2626262914716916e-05, 'samples': 23440128, 'steps': 122083, 'loss/train': 1.3455252647399902} 08/31/2021 11:25:17 - INFO - __main__ - Step 122085: {'lr': 4.262329906927251e-05, 'samples': 23440320, 'steps': 122084, 'loss/train': 1.1260266304016113} 08/31/2021 11:25:17 - INFO - __main__ - Step 122086: {'lr': 4.2620335317268806e-05, 'samples': 23440512, 'steps': 122085, 'loss/train': 0.06742154061794281} 08/31/2021 11:25:17 - INFO - __main__ - Step 122087: {'lr': 4.2617371658707217e-05, 'samples': 23440704, 'steps': 122086, 'loss/train': 1.1681969165802002} 08/31/2021 11:25:18 - INFO - __main__ - Step 122088: {'lr': 4.261440809358902e-05, 'samples': 23440896, 'steps': 122087, 'loss/train': 1.493068814277649} 08/31/2021 11:25:19 - INFO - __main__ - Step 122089: {'lr': 4.2611444621915575e-05, 'samples': 23441088, 'steps': 122088, 'loss/train': 0.9283024668693542} 08/31/2021 11:25:19 - INFO - __main__ - Step 122090: {'lr': 4.260848124368821e-05, 'samples': 23441280, 'steps': 122089, 'loss/train': 1.1440119743347168} 08/31/2021 11:25:20 - INFO - __main__ - Step 122091: {'lr': 4.260551795890827e-05, 'samples': 23441472, 'steps': 122090, 'loss/train': 0.5185286998748779} 08/31/2021 11:25:20 - INFO - __main__ - Step 122092: {'lr': 4.2602554767577074e-05, 'samples': 23441664, 'steps': 122091, 'loss/train': 0.7995925545692444} 08/31/2021 11:25:21 - INFO - __main__ - Step 122093: {'lr': 4.259959166969596e-05, 'samples': 23441856, 'steps': 122092, 'loss/train': 0.9556158185005188} 08/31/2021 11:25:22 - INFO - __main__ - Step 122094: {'lr': 4.2596628665266285e-05, 'samples': 23442048, 'steps': 122093, 'loss/train': 0.5203390717506409} 08/31/2021 11:25:22 - INFO - __main__ - Step 122095: {'lr': 4.2593665754289354e-05, 'samples': 23442240, 'steps': 122094, 'loss/train': 0.6120944619178772} 08/31/2021 11:25:23 - INFO - __main__ - Step 122096: {'lr': 4.259070293676654e-05, 'samples': 23442432, 'steps': 122095, 'loss/train': 1.0707908868789673} 08/31/2021 11:25:23 - INFO - __main__ - Step 122097: {'lr': 4.258774021269918e-05, 'samples': 23442624, 'steps': 122096, 'loss/train': 1.4296194314956665} 08/31/2021 11:25:24 - INFO - __main__ - Step 122098: {'lr': 4.2584777582088566e-05, 'samples': 23442816, 'steps': 122097, 'loss/train': 1.1952869892120361} 08/31/2021 11:25:25 - INFO - __main__ - Step 122099: {'lr': 4.258181504493602e-05, 'samples': 23443008, 'steps': 122098, 'loss/train': 1.0363304615020752} 08/31/2021 11:25:26 - INFO - __main__ - Step 122100: {'lr': 4.257885260124292e-05, 'samples': 23443200, 'steps': 122099, 'loss/train': 1.5861338376998901} 08/31/2021 11:25:26 - INFO - __main__ - Step 122101: {'lr': 4.2575890251010576e-05, 'samples': 23443392, 'steps': 122100, 'loss/train': 0.8945438861846924} 08/31/2021 11:25:26 - INFO - __main__ - Step 122102: {'lr': 4.257292799424034e-05, 'samples': 23443584, 'steps': 122101, 'loss/train': 0.9036790728569031} 08/31/2021 11:25:27 - INFO - __main__ - Step 122103: {'lr': 4.256996583093356e-05, 'samples': 23443776, 'steps': 122102, 'loss/train': 0.3172784149646759} 08/31/2021 11:25:27 - INFO - __main__ - Step 122104: {'lr': 4.2567003761091516e-05, 'samples': 23443968, 'steps': 122103, 'loss/train': 1.309982180595398} 08/31/2021 11:25:29 - INFO - __main__ - Step 122105: {'lr': 4.256404178471562e-05, 'samples': 23444160, 'steps': 122104, 'loss/train': 1.5818169116973877} 08/31/2021 11:25:29 - INFO - __main__ - Step 122106: {'lr': 4.256107990180713e-05, 'samples': 23444352, 'steps': 122105, 'loss/train': 0.9458969831466675} 08/31/2021 11:25:29 - INFO - __main__ - Step 122107: {'lr': 4.255811811236743e-05, 'samples': 23444544, 'steps': 122106, 'loss/train': 0.9277344346046448} 08/31/2021 11:25:30 - INFO - __main__ - Step 122108: {'lr': 4.255515641639784e-05, 'samples': 23444736, 'steps': 122107, 'loss/train': 0.5577290058135986} 08/31/2021 11:25:30 - INFO - __main__ - Step 122109: {'lr': 4.2552194813899714e-05, 'samples': 23444928, 'steps': 122108, 'loss/train': 1.1160134077072144} 08/31/2021 11:25:32 - INFO - __main__ - Step 122110: {'lr': 4.2549233304874425e-05, 'samples': 23445120, 'steps': 122109, 'loss/train': 0.8429208993911743} 08/31/2021 11:25:32 - INFO - __main__ - Step 122111: {'lr': 4.254627188932317e-05, 'samples': 23445312, 'steps': 122110, 'loss/train': 1.1496156454086304} 08/31/2021 11:25:33 - INFO - __main__ - Step 122112: {'lr': 4.2543310567247364e-05, 'samples': 23445504, 'steps': 122111, 'loss/train': 1.0432084798812866} 08/31/2021 11:25:33 - INFO - __main__ - Step 122113: {'lr': 4.2540349338648364e-05, 'samples': 23445696, 'steps': 122112, 'loss/train': 1.0610415935516357} 08/31/2021 11:25:33 - INFO - __main__ - Step 122114: {'lr': 4.253738820352745e-05, 'samples': 23445888, 'steps': 122113, 'loss/train': 5.819440841674805} 08/31/2021 11:25:34 - INFO - __main__ - Step 122115: {'lr': 4.253442716188602e-05, 'samples': 23446080, 'steps': 122114, 'loss/train': 3.658555746078491} 08/31/2021 11:25:36 - INFO - __main__ - Step 122116: {'lr': 4.2531466213725364e-05, 'samples': 23446272, 'steps': 122115, 'loss/train': 0.9617153406143188} 08/31/2021 11:25:36 - INFO - __main__ - Step 122117: {'lr': 4.2528505359046815e-05, 'samples': 23446464, 'steps': 122116, 'loss/train': 0.9694033265113831} 08/31/2021 11:25:36 - INFO - __main__ - Step 122118: {'lr': 4.252554459785174e-05, 'samples': 23446656, 'steps': 122117, 'loss/train': 1.0801485776901245} 08/31/2021 11:25:37 - INFO - __main__ - Step 122119: {'lr': 4.252258393014144e-05, 'samples': 23446848, 'steps': 122118, 'loss/train': 1.3346271514892578} 08/31/2021 11:25:37 - INFO - __main__ - Step 122120: {'lr': 4.251962335591725e-05, 'samples': 23447040, 'steps': 122119, 'loss/train': 1.104820966720581} 08/31/2021 11:25:39 - INFO - __main__ - Step 122121: {'lr': 4.251666287518055e-05, 'samples': 23447232, 'steps': 122120, 'loss/train': 1.0105382204055786} 08/31/2021 11:25:39 - INFO - __main__ - Step 122122: {'lr': 4.2513702487932595e-05, 'samples': 23447424, 'steps': 122121, 'loss/train': 0.9837479591369629} 08/31/2021 11:25:39 - INFO - __main__ - Step 122123: {'lr': 4.251074219417481e-05, 'samples': 23447616, 'steps': 122122, 'loss/train': 1.2095770835876465} 08/31/2021 11:25:40 - INFO - __main__ - Step 122124: {'lr': 4.250778199390851e-05, 'samples': 23447808, 'steps': 122123, 'loss/train': 1.60500168800354} 08/31/2021 11:25:40 - INFO - __main__ - Step 122125: {'lr': 4.250482188713495e-05, 'samples': 23448000, 'steps': 122124, 'loss/train': 1.034591555595398} 08/31/2021 11:25:40 - INFO - __main__ - Step 122126: {'lr': 4.250186187385552e-05, 'samples': 23448192, 'steps': 122125, 'loss/train': 0.24599474668502808} 08/31/2021 11:25:42 - INFO - __main__ - Step 122127: {'lr': 4.249890195407155e-05, 'samples': 23448384, 'steps': 122126, 'loss/train': 0.9115468859672546} 08/31/2021 11:25:43 - INFO - __main__ - Step 122128: {'lr': 4.2495942127784375e-05, 'samples': 23448576, 'steps': 122127, 'loss/train': 1.158199429512024} 08/31/2021 11:25:43 - INFO - __main__ - Step 122129: {'lr': 4.249298239499533e-05, 'samples': 23448768, 'steps': 122128, 'loss/train': 1.8003875017166138} 08/31/2021 11:25:44 - INFO - __main__ - Step 122130: {'lr': 4.2490022755705735e-05, 'samples': 23448960, 'steps': 122129, 'loss/train': 0.748904287815094} 08/31/2021 11:25:44 - INFO - __main__ - Step 122131: {'lr': 4.248706320991694e-05, 'samples': 23449152, 'steps': 122130, 'loss/train': 1.5493929386138916} 08/31/2021 11:25:46 - INFO - __main__ - Step 122132: {'lr': 4.248410375763026e-05, 'samples': 23449344, 'steps': 122131, 'loss/train': 0.9105746150016785} 08/31/2021 11:25:46 - INFO - __main__ - Step 122133: {'lr': 4.248114439884707e-05, 'samples': 23449536, 'steps': 122132, 'loss/train': 0.747565507888794} 08/31/2021 11:25:47 - INFO - __main__ - Step 122134: {'lr': 4.2478185133568634e-05, 'samples': 23449728, 'steps': 122133, 'loss/train': 0.665190577507019} 08/31/2021 11:25:47 - INFO - __main__ - Step 122135: {'lr': 4.247522596179634e-05, 'samples': 23449920, 'steps': 122134, 'loss/train': 1.00686776638031} 08/31/2021 11:25:47 - INFO - __main__ - Step 122136: {'lr': 4.2472266883531506e-05, 'samples': 23450112, 'steps': 122135, 'loss/train': 0.8666256070137024} 08/31/2021 11:25:49 - INFO - __main__ - Step 122137: {'lr': 4.2469307898775536e-05, 'samples': 23450304, 'steps': 122136, 'loss/train': 1.1226856708526611} 08/31/2021 11:25:49 - INFO - __main__ - Step 122138: {'lr': 4.246634900752963e-05, 'samples': 23450496, 'steps': 122137, 'loss/train': 1.4374920129776} 08/31/2021 11:25:50 - INFO - __main__ - Step 122139: {'lr': 4.24633902097952e-05, 'samples': 23450688, 'steps': 122138, 'loss/train': 1.1737003326416016} 08/31/2021 11:25:50 - INFO - __main__ - Step 122140: {'lr': 4.246043150557355e-05, 'samples': 23450880, 'steps': 122139, 'loss/train': 1.5811622142791748} 08/31/2021 11:25:50 - INFO - __main__ - Step 122141: {'lr': 4.245747289486601e-05, 'samples': 23451072, 'steps': 122140, 'loss/train': 1.7173656225204468} 08/31/2021 11:25:52 - INFO - __main__ - Step 122142: {'lr': 4.245451437767395e-05, 'samples': 23451264, 'steps': 122141, 'loss/train': 1.5290553569793701} 08/31/2021 11:25:52 - INFO - __main__ - Step 122143: {'lr': 4.245155595399869e-05, 'samples': 23451456, 'steps': 122142, 'loss/train': 1.8492143154144287} 08/31/2021 11:25:53 - INFO - __main__ - Step 122144: {'lr': 4.244859762384154e-05, 'samples': 23451648, 'steps': 122143, 'loss/train': 1.1400426626205444} 08/31/2021 11:25:53 - INFO - __main__ - Step 122145: {'lr': 4.244563938720386e-05, 'samples': 23451840, 'steps': 122144, 'loss/train': 1.784141182899475} 08/31/2021 11:25:53 - INFO - __main__ - Step 122146: {'lr': 4.244268124408696e-05, 'samples': 23452032, 'steps': 122145, 'loss/train': 1.4425934553146362} 08/31/2021 11:25:55 - INFO - __main__ - Step 122147: {'lr': 4.2439723194492184e-05, 'samples': 23452224, 'steps': 122146, 'loss/train': 1.4875918626785278} 08/31/2021 11:25:55 - INFO - __main__ - Step 122148: {'lr': 4.243676523842088e-05, 'samples': 23452416, 'steps': 122147, 'loss/train': 0.8016175031661987} 08/31/2021 11:25:56 - INFO - __main__ - Step 122149: {'lr': 4.243380737587435e-05, 'samples': 23452608, 'steps': 122148, 'loss/train': 1.1049975156784058} 08/31/2021 11:25:56 - INFO - __main__ - Step 122150: {'lr': 4.243084960685395e-05, 'samples': 23452800, 'steps': 122149, 'loss/train': 1.0235743522644043} 08/31/2021 11:25:56 - INFO - __main__ - Step 122151: {'lr': 4.242789193136107e-05, 'samples': 23452992, 'steps': 122150, 'loss/train': 0.343938946723938} 08/31/2021 11:25:58 - INFO - __main__ - Step 122152: {'lr': 4.2424934349396924e-05, 'samples': 23453184, 'steps': 122151, 'loss/train': 1.1482738256454468} 08/31/2021 11:25:58 - INFO - __main__ - Step 122153: {'lr': 4.2421976860962915e-05, 'samples': 23453376, 'steps': 122152, 'loss/train': 1.4916013479232788} 08/31/2021 11:25:59 - INFO - __main__ - Step 122154: {'lr': 4.241901946606033e-05, 'samples': 23453568, 'steps': 122153, 'loss/train': 0.9913514256477356} 08/31/2021 11:25:59 - INFO - __main__ - Step 122155: {'lr': 4.2416062164690545e-05, 'samples': 23453760, 'steps': 122154, 'loss/train': 1.4981895685195923} 08/31/2021 11:25:59 - INFO - __main__ - Step 122156: {'lr': 4.2413104956854855e-05, 'samples': 23453952, 'steps': 122155, 'loss/train': 1.31784188747406} 08/31/2021 11:26:00 - INFO - __main__ - Step 122157: {'lr': 4.241014784255465e-05, 'samples': 23454144, 'steps': 122156, 'loss/train': 1.5371631383895874} 08/31/2021 11:26:01 - INFO - __main__ - Step 122158: {'lr': 4.2407190821791205e-05, 'samples': 23454336, 'steps': 122157, 'loss/train': 0.4757109582424164} 08/31/2021 11:26:02 - INFO - __main__ - Step 122159: {'lr': 4.240423389456588e-05, 'samples': 23454528, 'steps': 122158, 'loss/train': 1.3718822002410889} 08/31/2021 11:26:02 - INFO - __main__ - Step 122160: {'lr': 4.240127706088001e-05, 'samples': 23454720, 'steps': 122159, 'loss/train': 1.2648035287857056} 08/31/2021 11:26:03 - INFO - __main__ - Step 122161: {'lr': 4.2398320320734926e-05, 'samples': 23454912, 'steps': 122160, 'loss/train': 0.9430196285247803} 08/31/2021 11:26:03 - INFO - __main__ - Step 122162: {'lr': 4.2395363674131964e-05, 'samples': 23455104, 'steps': 122161, 'loss/train': 0.823205292224884} 08/31/2021 11:26:04 - INFO - __main__ - Step 122163: {'lr': 4.2392407121072426e-05, 'samples': 23455296, 'steps': 122162, 'loss/train': 0.9935992956161499} 08/31/2021 11:26:05 - INFO - __main__ - Step 122164: {'lr': 4.238945066155775e-05, 'samples': 23455488, 'steps': 122163, 'loss/train': 1.3736997842788696} 08/31/2021 11:26:05 - INFO - __main__ - Step 122165: {'lr': 4.238649429558911e-05, 'samples': 23455680, 'steps': 122164, 'loss/train': 0.6840001940727234} 08/31/2021 11:26:06 - INFO - __main__ - Step 122166: {'lr': 4.238353802316791e-05, 'samples': 23455872, 'steps': 122165, 'loss/train': 1.1224424839019775} 08/31/2021 11:26:06 - INFO - __main__ - Step 122167: {'lr': 4.2380581844295466e-05, 'samples': 23456064, 'steps': 122166, 'loss/train': 1.5158112049102783} 08/31/2021 11:26:07 - INFO - __main__ - Step 122168: {'lr': 4.2377625758973167e-05, 'samples': 23456256, 'steps': 122167, 'loss/train': 1.04709792137146} 08/31/2021 11:26:08 - INFO - __main__ - Step 122169: {'lr': 4.2374669767202275e-05, 'samples': 23456448, 'steps': 122168, 'loss/train': 0.7742177248001099} 08/31/2021 11:26:08 - INFO - __main__ - Step 122170: {'lr': 4.237171386898417e-05, 'samples': 23456640, 'steps': 122169, 'loss/train': 0.8805424571037292} 08/31/2021 11:26:09 - INFO - __main__ - Step 122171: {'lr': 4.2368758064320136e-05, 'samples': 23456832, 'steps': 122170, 'loss/train': 1.051426649093628} 08/31/2021 11:26:09 - INFO - __main__ - Step 122172: {'lr': 4.236580235321158e-05, 'samples': 23457024, 'steps': 122171, 'loss/train': 1.0059479475021362} 08/31/2021 11:26:09 - INFO - __main__ - Step 122173: {'lr': 4.236284673565976e-05, 'samples': 23457216, 'steps': 122172, 'loss/train': 0.4587406814098358} 08/31/2021 11:26:11 - INFO - __main__ - Step 122174: {'lr': 4.2359891211666055e-05, 'samples': 23457408, 'steps': 122173, 'loss/train': 1.1906147003173828} 08/31/2021 11:26:11 - INFO - __main__ - Step 122175: {'lr': 4.235693578123176e-05, 'samples': 23457600, 'steps': 122174, 'loss/train': 3.653421401977539} 08/31/2021 11:26:12 - INFO - __main__ - Step 122176: {'lr': 4.2353980444358234e-05, 'samples': 23457792, 'steps': 122175, 'loss/train': 1.3723537921905518} 08/31/2021 11:26:12 - INFO - __main__ - Step 122177: {'lr': 4.2351025201046804e-05, 'samples': 23457984, 'steps': 122176, 'loss/train': 1.570077657699585} 08/31/2021 11:26:12 - INFO - __main__ - Step 122178: {'lr': 4.234807005129887e-05, 'samples': 23458176, 'steps': 122177, 'loss/train': 0.8654025197029114} 08/31/2021 11:26:14 - INFO - __main__ - Step 122179: {'lr': 4.234511499511562e-05, 'samples': 23458368, 'steps': 122178, 'loss/train': 1.2047388553619385} 08/31/2021 11:26:14 - INFO - __main__ - Step 122180: {'lr': 4.234216003249844e-05, 'samples': 23458560, 'steps': 122179, 'loss/train': 1.4894057512283325} 08/31/2021 11:26:15 - INFO - __main__ - Step 122181: {'lr': 4.233920516344869e-05, 'samples': 23458752, 'steps': 122180, 'loss/train': 1.5079982280731201} 08/31/2021 11:26:15 - INFO - __main__ - Step 122182: {'lr': 4.233625038796771e-05, 'samples': 23458944, 'steps': 122181, 'loss/train': 0.7941609621047974} 08/31/2021 11:26:15 - INFO - __main__ - Step 122183: {'lr': 4.233329570605679e-05, 'samples': 23459136, 'steps': 122182, 'loss/train': 1.0864334106445312} 08/31/2021 11:26:18 - INFO - __main__ - Step 122184: {'lr': 4.2330341117717274e-05, 'samples': 23459328, 'steps': 122183, 'loss/train': 1.318532943725586} 08/31/2021 11:26:18 - INFO - __main__ - Step 122185: {'lr': 4.232738662295052e-05, 'samples': 23459520, 'steps': 122184, 'loss/train': 1.2812212705612183} 08/31/2021 11:26:19 - INFO - __main__ - Step 122186: {'lr': 4.232443222175783e-05, 'samples': 23459712, 'steps': 122185, 'loss/train': 0.6931520104408264} 08/31/2021 11:26:19 - INFO - __main__ - Step 122187: {'lr': 4.2321477914140564e-05, 'samples': 23459904, 'steps': 122186, 'loss/train': 1.1344579458236694} 08/31/2021 11:26:19 - INFO - __main__ - Step 122188: {'lr': 4.2318523700100006e-05, 'samples': 23460096, 'steps': 122187, 'loss/train': 1.2476187944412231} 08/31/2021 11:26:20 - INFO - __main__ - Step 122189: {'lr': 4.231556957963753e-05, 'samples': 23460288, 'steps': 122188, 'loss/train': 1.189705729484558} 08/31/2021 11:26:21 - INFO - __main__ - Step 122190: {'lr': 4.231261555275448e-05, 'samples': 23460480, 'steps': 122189, 'loss/train': 1.1232576370239258} 08/31/2021 11:26:21 - INFO - __main__ - Step 122191: {'lr': 4.230966161945218e-05, 'samples': 23460672, 'steps': 122190, 'loss/train': 0.9122064113616943} 08/31/2021 11:26:22 - INFO - __main__ - Step 122192: {'lr': 4.2306707779731916e-05, 'samples': 23460864, 'steps': 122191, 'loss/train': 1.6113935708999634} 08/31/2021 11:26:22 - INFO - __main__ - Step 122193: {'lr': 4.2303754033595015e-05, 'samples': 23461056, 'steps': 122192, 'loss/train': 1.116764783859253} 08/31/2021 11:26:23 - INFO - __main__ - Step 122194: {'lr': 4.230080038104287e-05, 'samples': 23461248, 'steps': 122193, 'loss/train': 1.538912296295166} 08/31/2021 11:26:25 - INFO - __main__ - Step 122195: {'lr': 4.229784682207674e-05, 'samples': 23461440, 'steps': 122194, 'loss/train': 1.4524037837982178} 08/31/2021 11:26:25 - INFO - __main__ - Step 122196: {'lr': 4.2294893356698e-05, 'samples': 23461632, 'steps': 122195, 'loss/train': 0.4115486741065979} 08/31/2021 11:26:26 - INFO - __main__ - Step 122197: {'lr': 4.229193998490802e-05, 'samples': 23461824, 'steps': 122196, 'loss/train': 0.9495500922203064} 08/31/2021 11:26:26 - INFO - __main__ - Step 122198: {'lr': 4.228898670670806e-05, 'samples': 23462016, 'steps': 122197, 'loss/train': 0.29728415608406067} 08/31/2021 11:26:26 - INFO - __main__ - Step 122199: {'lr': 4.228603352209945e-05, 'samples': 23462208, 'steps': 122198, 'loss/train': 0.05331474542617798} 08/31/2021 11:26:27 - INFO - __main__ - Step 122200: {'lr': 4.228308043108359e-05, 'samples': 23462400, 'steps': 122199, 'loss/train': 0.09167317301034927} 08/31/2021 11:26:29 - INFO - __main__ - Step 122201: {'lr': 4.228012743366175e-05, 'samples': 23462592, 'steps': 122200, 'loss/train': 0.02564707025885582} 08/31/2021 11:26:29 - INFO - __main__ - Step 122202: {'lr': 4.227717452983526e-05, 'samples': 23462784, 'steps': 122201, 'loss/train': 1.1401087045669556} 08/31/2021 11:26:29 - INFO - __main__ - Step 122203: {'lr': 4.2274221719605514e-05, 'samples': 23462976, 'steps': 122202, 'loss/train': 0.2927970588207245} 08/31/2021 11:26:30 - INFO - __main__ - Step 122204: {'lr': 4.2271269002973816e-05, 'samples': 23463168, 'steps': 122203, 'loss/train': 1.3643786907196045} 08/31/2021 11:26:30 - INFO - __main__ - Step 122205: {'lr': 4.226831637994144e-05, 'samples': 23463360, 'steps': 122204, 'loss/train': 1.0839775800704956} 08/31/2021 11:26:30 - INFO - __main__ - Step 122206: {'lr': 4.226536385050975e-05, 'samples': 23463552, 'steps': 122205, 'loss/train': 1.0391826629638672} 08/31/2021 11:26:32 - INFO - __main__ - Step 122207: {'lr': 4.22624114146801e-05, 'samples': 23463744, 'steps': 122206, 'loss/train': 0.17919160425662994} 08/31/2021 11:26:33 - INFO - __main__ - Step 122208: {'lr': 4.2259459072453794e-05, 'samples': 23463936, 'steps': 122207, 'loss/train': 0.7214984893798828} 08/31/2021 11:26:33 - INFO - __main__ - Step 122209: {'lr': 4.225650682383214e-05, 'samples': 23464128, 'steps': 122208, 'loss/train': 1.1350702047348022} 08/31/2021 11:26:34 - INFO - __main__ - Step 122210: {'lr': 4.225355466881653e-05, 'samples': 23464320, 'steps': 122209, 'loss/train': 1.1060010194778442} 08/31/2021 11:26:34 - INFO - __main__ - Step 122211: {'lr': 4.225060260740826e-05, 'samples': 23464512, 'steps': 122210, 'loss/train': 0.5477073192596436} 08/31/2021 11:26:34 - INFO - __main__ - Step 122212: {'lr': 4.224765063960864e-05, 'samples': 23464704, 'steps': 122211, 'loss/train': 0.7594149708747864} 08/31/2021 11:26:36 - INFO - __main__ - Step 122213: {'lr': 4.224469876541903e-05, 'samples': 23464896, 'steps': 122212, 'loss/train': 0.750114381313324} 08/31/2021 11:26:36 - INFO - __main__ - Step 122214: {'lr': 4.224174698484079e-05, 'samples': 23465088, 'steps': 122213, 'loss/train': 1.5291434526443481} 08/31/2021 11:26:37 - INFO - __main__ - Step 122215: {'lr': 4.223879529787517e-05, 'samples': 23465280, 'steps': 122214, 'loss/train': 0.7828791737556458} 08/31/2021 11:26:37 - INFO - __main__ - Step 122216: {'lr': 4.223584370452355e-05, 'samples': 23465472, 'steps': 122215, 'loss/train': 1.0717490911483765} 08/31/2021 11:26:38 - INFO - __main__ - Step 122217: {'lr': 4.223289220478726e-05, 'samples': 23465664, 'steps': 122216, 'loss/train': 0.9220539927482605} 08/31/2021 11:26:39 - INFO - __main__ - Step 122218: {'lr': 4.222994079866768e-05, 'samples': 23465856, 'steps': 122217, 'loss/train': 1.4055148363113403} 08/31/2021 11:26:39 - INFO - __main__ - Step 122219: {'lr': 4.222698948616604e-05, 'samples': 23466048, 'steps': 122218, 'loss/train': 1.1103461980819702} 08/31/2021 11:26:40 - INFO - __main__ - Step 122220: {'lr': 4.222403826728369e-05, 'samples': 23466240, 'steps': 122219, 'loss/train': 1.5318422317504883} 08/31/2021 11:26:40 - INFO - __main__ - Step 122221: {'lr': 4.2221087142022e-05, 'samples': 23466432, 'steps': 122220, 'loss/train': 0.549766480922699} 08/31/2021 11:26:40 - INFO - __main__ - Step 122222: {'lr': 4.221813611038228e-05, 'samples': 23466624, 'steps': 122221, 'loss/train': 1.0288313627243042} 08/31/2021 11:26:42 - INFO - __main__ - Step 122223: {'lr': 4.221518517236583e-05, 'samples': 23466816, 'steps': 122222, 'loss/train': 0.8536573648452759} 08/31/2021 11:26:42 - INFO - __main__ - Step 122224: {'lr': 4.221223432797405e-05, 'samples': 23467008, 'steps': 122223, 'loss/train': 0.8158823251724243} 08/31/2021 11:26:43 - INFO - __main__ - Step 122225: {'lr': 4.220928357720821e-05, 'samples': 23467200, 'steps': 122224, 'loss/train': 1.248853087425232} 08/31/2021 11:26:43 - INFO - __main__ - Step 122226: {'lr': 4.2206332920069675e-05, 'samples': 23467392, 'steps': 122225, 'loss/train': 1.4821475744247437} 08/31/2021 11:26:43 - INFO - __main__ - Step 122227: {'lr': 4.220338235655974e-05, 'samples': 23467584, 'steps': 122226, 'loss/train': 0.9853962063789368} 08/31/2021 11:26:44 - INFO - __main__ - Step 122228: {'lr': 4.220043188667977e-05, 'samples': 23467776, 'steps': 122227, 'loss/train': 1.4837064743041992} 08/31/2021 11:26:45 - INFO - __main__ - Step 122229: {'lr': 4.219748151043107e-05, 'samples': 23467968, 'steps': 122228, 'loss/train': 1.2893686294555664} 08/31/2021 11:26:46 - INFO - __main__ - Step 122230: {'lr': 4.219453122781505e-05, 'samples': 23468160, 'steps': 122229, 'loss/train': 0.34980690479278564} 08/31/2021 11:26:46 - INFO - __main__ - Step 122231: {'lr': 4.219158103883289e-05, 'samples': 23468352, 'steps': 122230, 'loss/train': 1.3672603368759155} 08/31/2021 11:26:47 - INFO - __main__ - Step 122232: {'lr': 4.218863094348602e-05, 'samples': 23468544, 'steps': 122231, 'loss/train': 0.6378805637359619} 08/31/2021 11:26:47 - INFO - __main__ - Step 122233: {'lr': 4.2185680941775714e-05, 'samples': 23468736, 'steps': 122232, 'loss/train': 1.0461244583129883} 08/31/2021 11:26:49 - INFO - __main__ - Step 122234: {'lr': 4.218273103370335e-05, 'samples': 23468928, 'steps': 122233, 'loss/train': 0.44885098934173584} 08/31/2021 11:26:49 - INFO - __main__ - Step 122235: {'lr': 4.217978121927024e-05, 'samples': 23469120, 'steps': 122234, 'loss/train': 0.9871621131896973} 08/31/2021 11:26:49 - INFO - __main__ - Step 122236: {'lr': 4.217683149847773e-05, 'samples': 23469312, 'steps': 122235, 'loss/train': 0.0638614147901535} 08/31/2021 11:26:50 - INFO - __main__ - Step 122237: {'lr': 4.217388187132712e-05, 'samples': 23469504, 'steps': 122236, 'loss/train': 0.6082706451416016} 08/31/2021 11:26:50 - INFO - __main__ - Step 122238: {'lr': 4.217093233781974e-05, 'samples': 23469696, 'steps': 122237, 'loss/train': 1.107774019241333} 08/31/2021 11:26:52 - INFO - __main__ - Step 122239: {'lr': 4.216798289795695e-05, 'samples': 23469888, 'steps': 122238, 'loss/train': 1.1604984998703003} 08/31/2021 11:26:53 - INFO - __main__ - Step 122240: {'lr': 4.216503355174006e-05, 'samples': 23470080, 'steps': 122239, 'loss/train': 1.5765612125396729} 08/31/2021 11:26:53 - INFO - __main__ - Step 122241: {'lr': 4.2162084299170455e-05, 'samples': 23470272, 'steps': 122240, 'loss/train': 0.8168690204620361} 08/31/2021 11:26:53 - INFO - __main__ - Step 122242: {'lr': 4.215913514024933e-05, 'samples': 23470464, 'steps': 122241, 'loss/train': 1.222899079322815} 08/31/2021 11:26:54 - INFO - __main__ - Step 122243: {'lr': 4.215618607497812e-05, 'samples': 23470656, 'steps': 122242, 'loss/train': 0.404407262802124} 08/31/2021 11:26:55 - INFO - __main__ - Step 122244: {'lr': 4.2153237103358114e-05, 'samples': 23470848, 'steps': 122243, 'loss/train': 0.6592922806739807} 08/31/2021 11:26:56 - INFO - __main__ - Step 122245: {'lr': 4.215028822539063e-05, 'samples': 23471040, 'steps': 122244, 'loss/train': 0.5521390438079834} 08/31/2021 11:26:56 - INFO - __main__ - Step 122246: {'lr': 4.214733944107704e-05, 'samples': 23471232, 'steps': 122245, 'loss/train': 1.145172119140625} 08/31/2021 11:26:56 - INFO - __main__ - Step 122247: {'lr': 4.214439075041865e-05, 'samples': 23471424, 'steps': 122246, 'loss/train': 0.6914454102516174} 08/31/2021 11:26:57 - INFO - __main__ - Step 122248: {'lr': 4.214144215341678e-05, 'samples': 23471616, 'steps': 122247, 'loss/train': 0.2858215868473053} 08/31/2021 11:26:58 - INFO - __main__ - Step 122249: {'lr': 4.21384936500728e-05, 'samples': 23471808, 'steps': 122248, 'loss/train': 1.4690970182418823} 08/31/2021 11:26:59 - INFO - __main__ - Step 122250: {'lr': 4.2135545240387984e-05, 'samples': 23472000, 'steps': 122249, 'loss/train': 1.0434731245040894} 08/31/2021 11:26:59 - INFO - __main__ - Step 122251: {'lr': 4.213259692436367e-05, 'samples': 23472192, 'steps': 122250, 'loss/train': 1.417452096939087} 08/31/2021 11:26:59 - INFO - __main__ - Step 122252: {'lr': 4.2129648702001285e-05, 'samples': 23472384, 'steps': 122251, 'loss/train': 0.6033399105072021} 08/31/2021 11:27:00 - INFO - __main__ - Step 122253: {'lr': 4.212670057330201e-05, 'samples': 23472576, 'steps': 122252, 'loss/train': 0.9324045777320862} 08/31/2021 11:27:00 - INFO - __main__ - Step 122254: {'lr': 4.2123752538267226e-05, 'samples': 23472768, 'steps': 122253, 'loss/train': 1.1339489221572876} 08/31/2021 11:27:01 - INFO - __main__ - Step 122255: {'lr': 4.2120804596898266e-05, 'samples': 23472960, 'steps': 122254, 'loss/train': 0.7080285549163818} 08/31/2021 11:27:02 - INFO - __main__ - Step 122256: {'lr': 4.2117856749196466e-05, 'samples': 23473152, 'steps': 122255, 'loss/train': 1.0349607467651367} 08/31/2021 11:27:02 - INFO - __main__ - Step 122257: {'lr': 4.2114908995163154e-05, 'samples': 23473344, 'steps': 122256, 'loss/train': 1.5350401401519775} 08/31/2021 11:27:03 - INFO - __main__ - Step 122258: {'lr': 4.2111961334799665e-05, 'samples': 23473536, 'steps': 122257, 'loss/train': 1.1819384098052979} 08/31/2021 11:27:03 - INFO - __main__ - Step 122259: {'lr': 4.210901376810733e-05, 'samples': 23473728, 'steps': 122258, 'loss/train': 0.7772742509841919} 08/31/2021 11:27:04 - INFO - __main__ - Step 122260: {'lr': 4.210606629508743e-05, 'samples': 23473920, 'steps': 122259, 'loss/train': 0.7053407430648804} 08/31/2021 11:27:05 - INFO - __main__ - Step 122261: {'lr': 4.210311891574134e-05, 'samples': 23474112, 'steps': 122260, 'loss/train': 0.7253190279006958} 08/31/2021 11:27:05 - INFO - __main__ - Step 122262: {'lr': 4.210017163007046e-05, 'samples': 23474304, 'steps': 122261, 'loss/train': 1.1890151500701904} 08/31/2021 11:27:06 - INFO - __main__ - Step 122263: {'lr': 4.209722443807595e-05, 'samples': 23474496, 'steps': 122262, 'loss/train': 1.376729130744934} 08/31/2021 11:27:06 - INFO - __main__ - Step 122264: {'lr': 4.209427733975923e-05, 'samples': 23474688, 'steps': 122263, 'loss/train': 1.4869918823242188} 08/31/2021 11:27:07 - INFO - __main__ - Step 122265: {'lr': 4.2091330335121637e-05, 'samples': 23474880, 'steps': 122264, 'loss/train': 1.4801926612854004} 08/31/2021 11:27:08 - INFO - __main__ - Step 122266: {'lr': 4.208838342416446e-05, 'samples': 23475072, 'steps': 122265, 'loss/train': 0.9596772789955139} 08/31/2021 11:27:08 - INFO - __main__ - Step 122267: {'lr': 4.2085436606889044e-05, 'samples': 23475264, 'steps': 122266, 'loss/train': 1.1339235305786133} 08/31/2021 11:27:09 - INFO - __main__ - Step 122268: {'lr': 4.2082489883296744e-05, 'samples': 23475456, 'steps': 122267, 'loss/train': 1.2898331880569458} 08/31/2021 11:27:09 - INFO - __main__ - Step 122269: {'lr': 4.207954325338886e-05, 'samples': 23475648, 'steps': 122268, 'loss/train': 1.581430435180664} 08/31/2021 11:27:10 - INFO - __main__ - Step 122270: {'lr': 4.207659671716671e-05, 'samples': 23475840, 'steps': 122269, 'loss/train': 1.2032766342163086} 08/31/2021 11:27:11 - INFO - __main__ - Step 122271: {'lr': 4.207365027463164e-05, 'samples': 23476032, 'steps': 122270, 'loss/train': 1.4035793542861938} 08/31/2021 11:27:11 - INFO - __main__ - Step 122272: {'lr': 4.2070703925784994e-05, 'samples': 23476224, 'steps': 122271, 'loss/train': 1.195608139038086} 08/31/2021 11:27:12 - INFO - __main__ - Step 122273: {'lr': 4.2067757670628124e-05, 'samples': 23476416, 'steps': 122272, 'loss/train': 1.446269154548645} 08/31/2021 11:27:12 - INFO - __main__ - Step 122274: {'lr': 4.206481150916227e-05, 'samples': 23476608, 'steps': 122273, 'loss/train': 0.4092733860015869} 08/31/2021 11:27:13 - INFO - __main__ - Step 122275: {'lr': 4.206186544138879e-05, 'samples': 23476800, 'steps': 122274, 'loss/train': 0.776296079158783} 08/31/2021 11:27:14 - INFO - __main__ - Step 122276: {'lr': 4.205891946730903e-05, 'samples': 23476992, 'steps': 122275, 'loss/train': 1.374577283859253} 08/31/2021 11:27:14 - INFO - __main__ - Step 122277: {'lr': 4.205597358692431e-05, 'samples': 23477184, 'steps': 122276, 'loss/train': 1.3282078504562378} 08/31/2021 11:27:15 - INFO - __main__ - Step 122278: {'lr': 4.2053027800235955e-05, 'samples': 23477376, 'steps': 122277, 'loss/train': 1.1161034107208252} 08/31/2021 11:27:15 - INFO - __main__ - Step 122279: {'lr': 4.2050082107245284e-05, 'samples': 23477568, 'steps': 122278, 'loss/train': 0.35218584537506104} 08/31/2021 11:27:17 - INFO - __main__ - Step 122280: {'lr': 4.204713650795366e-05, 'samples': 23477760, 'steps': 122279, 'loss/train': 1.604082703590393} 08/31/2021 11:27:17 - INFO - __main__ - Step 122281: {'lr': 4.20441910023624e-05, 'samples': 23477952, 'steps': 122280, 'loss/train': 1.057881474494934} 08/31/2021 11:27:18 - INFO - __main__ - Step 122282: {'lr': 4.204124559047279e-05, 'samples': 23478144, 'steps': 122281, 'loss/train': 1.1576106548309326} 08/31/2021 11:27:18 - INFO - __main__ - Step 122283: {'lr': 4.2038300272286195e-05, 'samples': 23478336, 'steps': 122282, 'loss/train': 1.3858681917190552} 08/31/2021 11:27:18 - INFO - __main__ - Step 122284: {'lr': 4.203535504780392e-05, 'samples': 23478528, 'steps': 122283, 'loss/train': 1.2006844282150269} 08/31/2021 11:27:20 - INFO - __main__ - Step 122285: {'lr': 4.203240991702739e-05, 'samples': 23478720, 'steps': 122284, 'loss/train': 0.8149588108062744} 08/31/2021 11:27:20 - INFO - __main__ - Step 122286: {'lr': 4.2029464879957765e-05, 'samples': 23478912, 'steps': 122285, 'loss/train': 0.02617007866501808} 08/31/2021 11:27:21 - INFO - __main__ - Step 122287: {'lr': 4.202651993659648e-05, 'samples': 23479104, 'steps': 122286, 'loss/train': 0.3421957790851593} 08/31/2021 11:27:21 - INFO - __main__ - Step 122288: {'lr': 4.202357508694482e-05, 'samples': 23479296, 'steps': 122287, 'loss/train': 1.2720973491668701} 08/31/2021 11:27:21 - INFO - __main__ - Step 122289: {'lr': 4.2020630331004115e-05, 'samples': 23479488, 'steps': 122288, 'loss/train': 0.6978542804718018} 08/31/2021 11:27:23 - INFO - __main__ - Step 122290: {'lr': 4.201768566877573e-05, 'samples': 23479680, 'steps': 122289, 'loss/train': 1.0628799200057983} 08/31/2021 11:27:24 - INFO - __main__ - Step 122291: {'lr': 4.2014741100260933e-05, 'samples': 23479872, 'steps': 122290, 'loss/train': 1.0309053659439087} 08/31/2021 11:27:24 - INFO - __main__ - Step 122292: {'lr': 4.201179662546112e-05, 'samples': 23480064, 'steps': 122291, 'loss/train': 0.9712556004524231} 08/31/2021 11:27:24 - INFO - __main__ - Step 122293: {'lr': 4.200885224437756e-05, 'samples': 23480256, 'steps': 122292, 'loss/train': 1.069406270980835} 08/31/2021 11:27:25 - INFO - __main__ - Step 122294: {'lr': 4.200590795701162e-05, 'samples': 23480448, 'steps': 122293, 'loss/train': 0.13071170449256897} 08/31/2021 11:27:27 - INFO - __main__ - Step 122295: {'lr': 4.2002963763364574e-05, 'samples': 23480640, 'steps': 122294, 'loss/train': 1.288846492767334} 08/31/2021 11:27:27 - INFO - __main__ - Step 122296: {'lr': 4.200001966343781e-05, 'samples': 23480832, 'steps': 122295, 'loss/train': 0.7175254225730896} 08/31/2021 11:27:28 - INFO - __main__ - Step 122297: {'lr': 4.1997075657232626e-05, 'samples': 23481024, 'steps': 122296, 'loss/train': 0.4756072163581848} 08/31/2021 11:27:28 - INFO - __main__ - Step 122298: {'lr': 4.199413174475036e-05, 'samples': 23481216, 'steps': 122297, 'loss/train': 0.5340319871902466} 08/31/2021 11:27:28 - INFO - __main__ - Step 122299: {'lr': 4.199118792599238e-05, 'samples': 23481408, 'steps': 122298, 'loss/train': 0.49054867029190063} 08/31/2021 11:27:30 - INFO - __main__ - Step 122300: {'lr': 4.1988244200959894e-05, 'samples': 23481600, 'steps': 122299, 'loss/train': 1.091969609260559} 08/31/2021 11:27:30 - INFO - __main__ - Step 122301: {'lr': 4.19853005696543e-05, 'samples': 23481792, 'steps': 122300, 'loss/train': 0.9916067123413086} 08/31/2021 11:27:31 - INFO - __main__ - Step 122302: {'lr': 4.1982357032076896e-05, 'samples': 23481984, 'steps': 122301, 'loss/train': 0.6424866318702698} 08/31/2021 11:27:31 - INFO - __main__ - Step 122303: {'lr': 4.197941358822907e-05, 'samples': 23482176, 'steps': 122302, 'loss/train': 0.5978859663009644} 08/31/2021 11:27:31 - INFO - __main__ - Step 122304: {'lr': 4.197647023811207e-05, 'samples': 23482368, 'steps': 122303, 'loss/train': 1.0668368339538574} 08/31/2021 11:27:32 - INFO - __main__ - Step 122305: {'lr': 4.197352698172729e-05, 'samples': 23482560, 'steps': 122304, 'loss/train': 0.4156472682952881} 08/31/2021 11:27:33 - INFO - __main__ - Step 122306: {'lr': 4.1970583819076036e-05, 'samples': 23482752, 'steps': 122305, 'loss/train': 1.151851773262024} 08/31/2021 11:27:34 - INFO - __main__ - Step 122307: {'lr': 4.196764075015963e-05, 'samples': 23482944, 'steps': 122306, 'loss/train': 1.2916659116744995} 08/31/2021 11:27:34 - INFO - __main__ - Step 122308: {'lr': 4.1964697774979385e-05, 'samples': 23483136, 'steps': 122307, 'loss/train': 1.217801809310913} 08/31/2021 11:27:35 - INFO - __main__ - Step 122309: {'lr': 4.1961754893536624e-05, 'samples': 23483328, 'steps': 122308, 'loss/train': 2.859581232070923} 08/31/2021 11:27:35 - INFO - __main__ - Step 122310: {'lr': 4.195881210583269e-05, 'samples': 23483520, 'steps': 122309, 'loss/train': 0.5598006248474121} 08/31/2021 11:27:36 - INFO - __main__ - Step 122311: {'lr': 4.195586941186891e-05, 'samples': 23483712, 'steps': 122310, 'loss/train': 0.02247086726129055} 08/31/2021 11:27:37 - INFO - __main__ - Step 122312: {'lr': 4.195292681164667e-05, 'samples': 23483904, 'steps': 122311, 'loss/train': 1.7579280138015747} 08/31/2021 11:27:37 - INFO - __main__ - Step 122313: {'lr': 4.1949984305167166e-05, 'samples': 23484096, 'steps': 122312, 'loss/train': 1.100388765335083} 08/31/2021 11:27:38 - INFO - __main__ - Step 122314: {'lr': 4.194704189243179e-05, 'samples': 23484288, 'steps': 122313, 'loss/train': 0.4752049446105957} 08/31/2021 11:27:38 - INFO - __main__ - Step 122315: {'lr': 4.194409957344186e-05, 'samples': 23484480, 'steps': 122314, 'loss/train': 0.639958381652832} 08/31/2021 11:27:40 - INFO - __main__ - Step 122316: {'lr': 4.19411573481987e-05, 'samples': 23484672, 'steps': 122315, 'loss/train': 0.5124748945236206} 08/31/2021 11:27:40 - INFO - __main__ - Step 122317: {'lr': 4.1938215216703654e-05, 'samples': 23484864, 'steps': 122316, 'loss/train': 0.5640618205070496} 08/31/2021 11:27:40 - INFO - __main__ - Step 122318: {'lr': 4.193527317895807e-05, 'samples': 23485056, 'steps': 122317, 'loss/train': 0.42438405752182007} 08/31/2021 11:27:41 - INFO - __main__ - Step 122319: {'lr': 4.193233123496321e-05, 'samples': 23485248, 'steps': 122318, 'loss/train': 0.023857394233345985} 08/31/2021 11:27:41 - INFO - __main__ - Step 122320: {'lr': 4.192938938472041e-05, 'samples': 23485440, 'steps': 122319, 'loss/train': 1.2037676572799683} 08/31/2021 11:27:43 - INFO - __main__ - Step 122321: {'lr': 4.1926447628231056e-05, 'samples': 23485632, 'steps': 122320, 'loss/train': 0.579284131526947} 08/31/2021 11:27:43 - INFO - __main__ - Step 122322: {'lr': 4.192350596549641e-05, 'samples': 23485824, 'steps': 122321, 'loss/train': 0.9574887156486511} 08/31/2021 11:27:43 - INFO - __main__ - Step 122323: {'lr': 4.192056439651784e-05, 'samples': 23486016, 'steps': 122322, 'loss/train': 1.5392374992370605} 08/31/2021 11:27:44 - INFO - __main__ - Step 122324: {'lr': 4.1917622921296636e-05, 'samples': 23486208, 'steps': 122323, 'loss/train': 1.0309767723083496} 08/31/2021 11:27:44 - INFO - __main__ - Step 122325: {'lr': 4.191468153983419e-05, 'samples': 23486400, 'steps': 122324, 'loss/train': 1.1726895570755005} 08/31/2021 11:27:44 - INFO - __main__ - Step 122326: {'lr': 4.1911740252131734e-05, 'samples': 23486592, 'steps': 122325, 'loss/train': 1.0995056629180908} 08/31/2021 11:27:46 - INFO - __main__ - Step 122327: {'lr': 4.190879905819065e-05, 'samples': 23486784, 'steps': 122326, 'loss/train': 0.8245411515235901} 08/31/2021 11:27:47 - INFO - __main__ - Step 122328: {'lr': 4.1905857958012245e-05, 'samples': 23486976, 'steps': 122327, 'loss/train': 0.9058793783187866} 08/31/2021 11:27:47 - INFO - __main__ - Step 122329: {'lr': 4.1902916951597815e-05, 'samples': 23487168, 'steps': 122328, 'loss/train': 1.553980827331543} 08/31/2021 11:27:47 - INFO - __main__ - Step 122330: {'lr': 4.189997603894877e-05, 'samples': 23487360, 'steps': 122329, 'loss/train': 1.5842102766036987} 08/31/2021 11:27:48 - INFO - __main__ - Step 122331: {'lr': 4.1897035220066354e-05, 'samples': 23487552, 'steps': 122330, 'loss/train': 0.9971716403961182} 08/31/2021 11:27:49 - INFO - __main__ - Step 122332: {'lr': 4.189409449495193e-05, 'samples': 23487744, 'steps': 122331, 'loss/train': 1.2851989269256592} 08/31/2021 11:27:50 - INFO - __main__ - Step 122333: {'lr': 4.1891153863606815e-05, 'samples': 23487936, 'steps': 122332, 'loss/train': 0.3380637764930725} 08/31/2021 11:27:50 - INFO - __main__ - Step 122334: {'lr': 4.188821332603232e-05, 'samples': 23488128, 'steps': 122333, 'loss/train': 1.596799373626709} 08/31/2021 11:27:50 - INFO - __main__ - Step 122335: {'lr': 4.188527288222979e-05, 'samples': 23488320, 'steps': 122334, 'loss/train': 1.084362268447876} 08/31/2021 11:27:51 - INFO - __main__ - Step 122336: {'lr': 4.1882332532200557e-05, 'samples': 23488512, 'steps': 122335, 'loss/train': 0.4245164096355438} 08/31/2021 11:27:52 - INFO - __main__ - Step 122337: {'lr': 4.187939227594595e-05, 'samples': 23488704, 'steps': 122336, 'loss/train': 0.4604388475418091} 08/31/2021 11:27:53 - INFO - __main__ - Step 122338: {'lr': 4.1876452113467246e-05, 'samples': 23488896, 'steps': 122337, 'loss/train': 1.1968364715576172} 08/31/2021 11:27:53 - INFO - __main__ - Step 122339: {'lr': 4.187351204476586e-05, 'samples': 23489088, 'steps': 122338, 'loss/train': 1.1340430974960327} 08/31/2021 11:27:54 - INFO - __main__ - Step 122340: {'lr': 4.187057206984302e-05, 'samples': 23489280, 'steps': 122339, 'loss/train': 1.4631671905517578} 08/31/2021 11:27:54 - INFO - __main__ - Step 122341: {'lr': 4.1867632188700075e-05, 'samples': 23489472, 'steps': 122340, 'loss/train': 1.3740582466125488} 08/31/2021 11:27:55 - INFO - __main__ - Step 122342: {'lr': 4.186469240133836e-05, 'samples': 23489664, 'steps': 122341, 'loss/train': 0.9688027501106262} 08/31/2021 11:27:56 - INFO - __main__ - Step 122343: {'lr': 4.186175270775922e-05, 'samples': 23489856, 'steps': 122342, 'loss/train': 1.6534148454666138} 08/31/2021 11:27:56 - INFO - __main__ - Step 122344: {'lr': 4.185881310796397e-05, 'samples': 23490048, 'steps': 122343, 'loss/train': 0.5458993911743164} 08/31/2021 11:27:57 - INFO - __main__ - Step 122345: {'lr': 4.185587360195389e-05, 'samples': 23490240, 'steps': 122344, 'loss/train': 1.05946946144104} 08/31/2021 11:27:57 - INFO - __main__ - Step 122346: {'lr': 4.185293418973035e-05, 'samples': 23490432, 'steps': 122345, 'loss/train': 1.4733816385269165} 08/31/2021 11:27:59 - INFO - __main__ - Step 122347: {'lr': 4.184999487129468e-05, 'samples': 23490624, 'steps': 122346, 'loss/train': 1.0901570320129395} 08/31/2021 11:27:59 - INFO - __main__ - Step 122348: {'lr': 4.18470556466482e-05, 'samples': 23490816, 'steps': 122347, 'loss/train': 1.6257939338684082} 08/31/2021 11:28:00 - INFO - __main__ - Step 122349: {'lr': 4.18441165157922e-05, 'samples': 23491008, 'steps': 122348, 'loss/train': 3.2045795917510986} 08/31/2021 11:28:00 - INFO - __main__ - Step 122350: {'lr': 4.184117747872804e-05, 'samples': 23491200, 'steps': 122349, 'loss/train': 1.5469107627868652} 08/31/2021 11:28:00 - INFO - __main__ - Step 122351: {'lr': 4.183823853545704e-05, 'samples': 23491392, 'steps': 122350, 'loss/train': 0.2678269147872925} 08/31/2021 11:28:02 - INFO - __main__ - Step 122352: {'lr': 4.183529968598057e-05, 'samples': 23491584, 'steps': 122351, 'loss/train': 0.7995365858078003} 08/31/2021 11:28:02 - INFO - __main__ - Step 122353: {'lr': 4.183236093029985e-05, 'samples': 23491776, 'steps': 122352, 'loss/train': 0.8503701090812683} 08/31/2021 11:28:03 - INFO - __main__ - Step 122354: {'lr': 4.182942226841624e-05, 'samples': 23491968, 'steps': 122353, 'loss/train': 1.3275408744812012} 08/31/2021 11:28:03 - INFO - __main__ - Step 122355: {'lr': 4.18264837003311e-05, 'samples': 23492160, 'steps': 122354, 'loss/train': 1.166033387184143} 08/31/2021 11:28:03 - INFO - __main__ - Step 122356: {'lr': 4.182354522604573e-05, 'samples': 23492352, 'steps': 122355, 'loss/train': 1.0096231698989868} 08/31/2021 11:28:05 - INFO - __main__ - Step 122357: {'lr': 4.1820606845561435e-05, 'samples': 23492544, 'steps': 122356, 'loss/train': 1.105904221534729} 08/31/2021 11:28:05 - INFO - __main__ - Step 122358: {'lr': 4.1817668558879586e-05, 'samples': 23492736, 'steps': 122357, 'loss/train': 1.3008884191513062} 08/31/2021 11:28:06 - INFO - __main__ - Step 122359: {'lr': 4.181473036600147e-05, 'samples': 23492928, 'steps': 122358, 'loss/train': 1.3432997465133667} 08/31/2021 11:28:06 - INFO - __main__ - Step 122360: {'lr': 4.181179226692844e-05, 'samples': 23493120, 'steps': 122359, 'loss/train': 0.85500168800354} 08/31/2021 11:28:06 - INFO - __main__ - Step 122361: {'lr': 4.1808854261661786e-05, 'samples': 23493312, 'steps': 122360, 'loss/train': 1.2434585094451904} 08/31/2021 11:28:08 - INFO - __main__ - Step 122362: {'lr': 4.180591635020287e-05, 'samples': 23493504, 'steps': 122361, 'loss/train': 0.6489452123641968} 08/31/2021 11:28:09 - INFO - __main__ - Step 122363: {'lr': 4.1802978532552964e-05, 'samples': 23493696, 'steps': 122362, 'loss/train': 1.2969411611557007} 08/31/2021 11:28:09 - INFO - __main__ - Step 122364: {'lr': 4.180004080871347e-05, 'samples': 23493888, 'steps': 122363, 'loss/train': 1.4788038730621338} 08/31/2021 11:28:09 - INFO - __main__ - Step 122365: {'lr': 4.179710317868563e-05, 'samples': 23494080, 'steps': 122364, 'loss/train': 1.2066203355789185} 08/31/2021 11:28:10 - INFO - __main__ - Step 122366: {'lr': 4.179416564247085e-05, 'samples': 23494272, 'steps': 122365, 'loss/train': 1.1921249628067017} 08/31/2021 11:28:10 - INFO - __main__ - Step 122367: {'lr': 4.179122820007039e-05, 'samples': 23494464, 'steps': 122366, 'loss/train': 0.8453980684280396} 08/31/2021 11:28:12 - INFO - __main__ - Step 122368: {'lr': 4.1788290851485556e-05, 'samples': 23494656, 'steps': 122367, 'loss/train': 0.383146733045578} 08/31/2021 11:28:12 - INFO - __main__ - Step 122369: {'lr': 4.17853535967177e-05, 'samples': 23494848, 'steps': 122368, 'loss/train': 1.7459063529968262} 08/31/2021 11:28:13 - INFO - __main__ - Step 122370: {'lr': 4.178241643576819e-05, 'samples': 23495040, 'steps': 122369, 'loss/train': 0.6928713917732239} 08/31/2021 11:28:13 - INFO - __main__ - Step 122371: {'lr': 4.177947936863827e-05, 'samples': 23495232, 'steps': 122370, 'loss/train': 1.081284761428833} 08/31/2021 11:28:13 - INFO - __main__ - Step 122372: {'lr': 4.177654239532933e-05, 'samples': 23495424, 'steps': 122371, 'loss/train': 0.04218725860118866} 08/31/2021 11:28:15 - INFO - __main__ - Step 122373: {'lr': 4.177360551584264e-05, 'samples': 23495616, 'steps': 122372, 'loss/train': 0.5340636968612671} 08/31/2021 11:28:15 - INFO - __main__ - Step 122374: {'lr': 4.177066873017957e-05, 'samples': 23495808, 'steps': 122373, 'loss/train': 0.3639983832836151} 08/31/2021 11:28:16 - INFO - __main__ - Step 122375: {'lr': 4.176773203834142e-05, 'samples': 23496000, 'steps': 122374, 'loss/train': 0.9083144664764404} 08/31/2021 11:28:16 - INFO - __main__ - Step 122376: {'lr': 4.176479544032952e-05, 'samples': 23496192, 'steps': 122375, 'loss/train': 1.0334385633468628} 08/31/2021 11:28:16 - INFO - __main__ - Step 122377: {'lr': 4.176185893614517e-05, 'samples': 23496384, 'steps': 122376, 'loss/train': 0.9404658079147339} 08/31/2021 11:28:17 - INFO - __main__ - Step 122378: {'lr': 4.175892252578975e-05, 'samples': 23496576, 'steps': 122377, 'loss/train': 1.2266845703125} 08/31/2021 11:28:18 - INFO - __main__ - Step 122379: {'lr': 4.175598620926457e-05, 'samples': 23496768, 'steps': 122378, 'loss/train': 1.2712229490280151} 08/31/2021 11:28:19 - INFO - __main__ - Step 122380: {'lr': 4.17530499865709e-05, 'samples': 23496960, 'steps': 122379, 'loss/train': 1.0758774280548096} 08/31/2021 11:28:19 - INFO - __main__ - Step 122381: {'lr': 4.1750113857710076e-05, 'samples': 23497152, 'steps': 122380, 'loss/train': 1.4677833318710327} 08/31/2021 11:28:19 - INFO - __main__ - Step 122382: {'lr': 4.174717782268345e-05, 'samples': 23497344, 'steps': 122381, 'loss/train': 1.3789628744125366} 08/31/2021 11:28:20 - INFO - __main__ - Step 122383: {'lr': 4.174424188149231e-05, 'samples': 23497536, 'steps': 122382, 'loss/train': 0.64591383934021} 08/31/2021 11:28:22 - INFO - __main__ - Step 122384: {'lr': 4.1741306034138006e-05, 'samples': 23497728, 'steps': 122383, 'loss/train': 1.770418405532837} 08/31/2021 11:28:22 - INFO - __main__ - Step 122385: {'lr': 4.173837028062186e-05, 'samples': 23497920, 'steps': 122384, 'loss/train': 0.5903960466384888} 08/31/2021 11:28:23 - INFO - __main__ - Step 122386: {'lr': 4.17354346209452e-05, 'samples': 23498112, 'steps': 122385, 'loss/train': 0.8748630881309509} 08/31/2021 11:28:23 - INFO - __main__ - Step 122387: {'lr': 4.1732499055109344e-05, 'samples': 23498304, 'steps': 122386, 'loss/train': 0.02486342377960682} 08/31/2021 11:28:23 - INFO - __main__ - Step 122388: {'lr': 4.172956358311558e-05, 'samples': 23498496, 'steps': 122387, 'loss/train': 0.04518001526594162} 08/31/2021 11:28:24 - INFO - __main__ - Step 122389: {'lr': 4.172662820496528e-05, 'samples': 23498688, 'steps': 122388, 'loss/train': 0.7013899087905884} 08/31/2021 11:28:25 - INFO - __main__ - Step 122390: {'lr': 4.172369292065975e-05, 'samples': 23498880, 'steps': 122389, 'loss/train': 1.1818381547927856} 08/31/2021 11:28:26 - INFO - __main__ - Step 122391: {'lr': 4.1720757730200315e-05, 'samples': 23499072, 'steps': 122390, 'loss/train': 1.1661376953125} 08/31/2021 11:28:26 - INFO - __main__ - Step 122392: {'lr': 4.1717822633588284e-05, 'samples': 23499264, 'steps': 122391, 'loss/train': 0.246864452958107} 08/31/2021 11:28:26 - INFO - __main__ - Step 122393: {'lr': 4.171488763082504e-05, 'samples': 23499456, 'steps': 122392, 'loss/train': 1.1089890003204346} 08/31/2021 11:28:27 - INFO - __main__ - Step 122394: {'lr': 4.171195272191181e-05, 'samples': 23499648, 'steps': 122393, 'loss/train': 1.2715716361999512} 08/31/2021 11:28:27 - INFO - __main__ - Step 122395: {'lr': 4.170901790684994e-05, 'samples': 23499840, 'steps': 122394, 'loss/train': 4.781579494476318} 08/31/2021 11:28:29 - INFO - __main__ - Step 122396: {'lr': 4.1706083185640786e-05, 'samples': 23500032, 'steps': 122395, 'loss/train': 0.864622175693512} 08/31/2021 11:28:29 - INFO - __main__ - Step 122397: {'lr': 4.1703148558285665e-05, 'samples': 23500224, 'steps': 122396, 'loss/train': 0.6564657092094421} 08/31/2021 11:28:30 - INFO - __main__ - Step 122398: {'lr': 4.170021402478588e-05, 'samples': 23500416, 'steps': 122397, 'loss/train': 1.4736218452453613} 08/31/2021 11:28:30 - INFO - __main__ - Step 122399: {'lr': 4.169727958514275e-05, 'samples': 23500608, 'steps': 122398, 'loss/train': 0.013718575239181519} 08/31/2021 11:28:30 - INFO - __main__ - Step 122400: {'lr': 4.169434523935764e-05, 'samples': 23500800, 'steps': 122399, 'loss/train': 1.278184413909912} 08/31/2021 11:28:31 - INFO - __main__ - Step 122401: {'lr': 4.1691410987431815e-05, 'samples': 23500992, 'steps': 122400, 'loss/train': 0.8300191760063171} 08/31/2021 11:28:33 - INFO - __main__ - Step 122402: {'lr': 4.168847682936663e-05, 'samples': 23501184, 'steps': 122401, 'loss/train': 1.2426989078521729} 08/31/2021 11:28:33 - INFO - __main__ - Step 122403: {'lr': 4.1685542765163426e-05, 'samples': 23501376, 'steps': 122402, 'loss/train': 0.9391945004463196} 08/31/2021 11:28:34 - INFO - __main__ - Step 122404: {'lr': 4.16826087948235e-05, 'samples': 23501568, 'steps': 122403, 'loss/train': 0.5140140056610107} 08/31/2021 11:28:34 - INFO - __main__ - Step 122405: {'lr': 4.167967491834815e-05, 'samples': 23501760, 'steps': 122404, 'loss/train': 1.4184026718139648} 08/31/2021 11:28:35 - INFO - __main__ - Step 122406: {'lr': 4.16767411357388e-05, 'samples': 23501952, 'steps': 122405, 'loss/train': 1.5026977062225342} 08/31/2021 11:28:36 - INFO - __main__ - Step 122407: {'lr': 4.167380744699664e-05, 'samples': 23502144, 'steps': 122406, 'loss/train': 0.7723904848098755} 08/31/2021 11:28:37 - INFO - __main__ - Step 122408: {'lr': 4.167087385212304e-05, 'samples': 23502336, 'steps': 122407, 'loss/train': 0.4422111511230469} 08/31/2021 11:28:37 - INFO - __main__ - Step 122409: {'lr': 4.1667940351119345e-05, 'samples': 23502528, 'steps': 122408, 'loss/train': 1.1992743015289307} 08/31/2021 11:28:37 - INFO - __main__ - Step 122410: {'lr': 4.166500694398684e-05, 'samples': 23502720, 'steps': 122409, 'loss/train': 1.0119366645812988} 08/31/2021 11:28:38 - INFO - __main__ - Step 122411: {'lr': 4.1662073630726884e-05, 'samples': 23502912, 'steps': 122410, 'loss/train': 1.5096744298934937} 08/31/2021 11:28:39 - INFO - __main__ - Step 122412: {'lr': 4.165914041134078e-05, 'samples': 23503104, 'steps': 122411, 'loss/train': 1.2040046453475952} 08/31/2021 11:28:39 - INFO - __main__ - Step 122413: {'lr': 4.165620728582983e-05, 'samples': 23503296, 'steps': 122412, 'loss/train': 0.3006435036659241} 08/31/2021 11:28:40 - INFO - __main__ - Step 122414: {'lr': 4.1653274254195406e-05, 'samples': 23503488, 'steps': 122413, 'loss/train': 0.9987452626228333} 08/31/2021 11:28:40 - INFO - __main__ - Step 122415: {'lr': 4.16503413164388e-05, 'samples': 23503680, 'steps': 122414, 'loss/train': 1.3302617073059082} 08/31/2021 11:28:41 - INFO - __main__ - Step 122416: {'lr': 4.164740847256132e-05, 'samples': 23503872, 'steps': 122415, 'loss/train': 1.04909348487854} 08/31/2021 11:28:42 - INFO - __main__ - Step 122417: {'lr': 4.1644475722564304e-05, 'samples': 23504064, 'steps': 122416, 'loss/train': 1.0691829919815063} 08/31/2021 11:28:43 - INFO - __main__ - Step 122418: {'lr': 4.164154306644907e-05, 'samples': 23504256, 'steps': 122417, 'loss/train': 0.8469772338867188} 08/31/2021 11:28:43 - INFO - __main__ - Step 122419: {'lr': 4.163861050421697e-05, 'samples': 23504448, 'steps': 122418, 'loss/train': 1.736193060874939} 08/31/2021 11:28:43 - INFO - __main__ - Step 122420: {'lr': 4.163567803586934e-05, 'samples': 23504640, 'steps': 122419, 'loss/train': 0.8954481482505798} 08/31/2021 11:28:44 - INFO - __main__ - Step 122421: {'lr': 4.163274566140737e-05, 'samples': 23504832, 'steps': 122420, 'loss/train': 0.8767253160476685} 08/31/2021 11:28:46 - INFO - __main__ - Step 122422: {'lr': 4.162981338083252e-05, 'samples': 23505024, 'steps': 122421, 'loss/train': 1.3737984895706177} 08/31/2021 11:28:46 - INFO - __main__ - Step 122423: {'lr': 4.162688119414604e-05, 'samples': 23505216, 'steps': 122422, 'loss/train': 0.8892732858657837} 08/31/2021 11:28:47 - INFO - __main__ - Step 122424: {'lr': 4.1623949101349254e-05, 'samples': 23505408, 'steps': 122423, 'loss/train': 1.9412716627120972} 08/31/2021 11:28:47 - INFO - __main__ - Step 122425: {'lr': 4.162101710244351e-05, 'samples': 23505600, 'steps': 122424, 'loss/train': 1.10664701461792} 08/31/2021 11:28:48 - INFO - __main__ - Step 122426: {'lr': 4.1618085197430125e-05, 'samples': 23505792, 'steps': 122425, 'loss/train': 1.2533212900161743} 08/31/2021 11:28:48 - INFO - __main__ - Step 122427: {'lr': 4.1615153386310415e-05, 'samples': 23505984, 'steps': 122426, 'loss/train': 0.3754144608974457} 08/31/2021 11:28:48 - INFO - __main__ - Step 122428: {'lr': 4.161222166908571e-05, 'samples': 23506176, 'steps': 122427, 'loss/train': 0.5092706084251404} 08/31/2021 11:28:50 - INFO - __main__ - Step 122429: {'lr': 4.160929004575731e-05, 'samples': 23506368, 'steps': 122428, 'loss/train': 0.552036464214325} 08/31/2021 11:28:50 - INFO - __main__ - Step 122430: {'lr': 4.1606358516326545e-05, 'samples': 23506560, 'steps': 122429, 'loss/train': 0.2960979640483856} 08/31/2021 11:28:51 - INFO - __main__ - Step 122431: {'lr': 4.160342708079473e-05, 'samples': 23506752, 'steps': 122430, 'loss/train': 1.4231667518615723} 08/31/2021 11:28:51 - INFO - __main__ - Step 122432: {'lr': 4.1600495739163216e-05, 'samples': 23506944, 'steps': 122431, 'loss/train': 0.02962852083146572} 08/31/2021 11:28:51 - INFO - __main__ - Step 122433: {'lr': 4.159756449143337e-05, 'samples': 23507136, 'steps': 122432, 'loss/train': 1.0506234169006348} 08/31/2021 11:28:53 - INFO - __main__ - Step 122434: {'lr': 4.159463333760638e-05, 'samples': 23507328, 'steps': 122433, 'loss/train': 0.9779556393623352} 08/31/2021 11:28:53 - INFO - __main__ - Step 122435: {'lr': 4.1591702277683606e-05, 'samples': 23507520, 'steps': 122434, 'loss/train': 1.2897366285324097} 08/31/2021 11:28:54 - INFO - __main__ - Step 122436: {'lr': 4.1588771311666415e-05, 'samples': 23507712, 'steps': 122435, 'loss/train': 1.3477305173873901} 08/31/2021 11:28:54 - INFO - __main__ - Step 122437: {'lr': 4.158584043955613e-05, 'samples': 23507904, 'steps': 122436, 'loss/train': 1.4683945178985596} 08/31/2021 11:28:54 - INFO - __main__ - Step 122438: {'lr': 4.1582909661354004e-05, 'samples': 23508096, 'steps': 122437, 'loss/train': 2.5204238891601562} 08/31/2021 11:28:56 - INFO - __main__ - Step 122439: {'lr': 4.157997897706142e-05, 'samples': 23508288, 'steps': 122438, 'loss/train': 1.4057660102844238} 08/31/2021 11:28:56 - INFO - __main__ - Step 122440: {'lr': 4.157704838667969e-05, 'samples': 23508480, 'steps': 122439, 'loss/train': 0.725832998752594} 08/31/2021 11:28:57 - INFO - __main__ - Step 122441: {'lr': 4.1574117890210125e-05, 'samples': 23508672, 'steps': 122440, 'loss/train': 1.1686794757843018} 08/31/2021 11:28:57 - INFO - __main__ - Step 122442: {'lr': 4.1571187487654036e-05, 'samples': 23508864, 'steps': 122441, 'loss/train': 1.0436385869979858} 08/31/2021 11:28:57 - INFO - __main__ - Step 122443: {'lr': 4.156825717901277e-05, 'samples': 23509056, 'steps': 122442, 'loss/train': 1.24113929271698} 08/31/2021 11:28:59 - INFO - __main__ - Step 122444: {'lr': 4.1565326964287635e-05, 'samples': 23509248, 'steps': 122443, 'loss/train': 1.0717614889144897} 08/31/2021 11:29:00 - INFO - __main__ - Step 122445: {'lr': 4.1562396843479925e-05, 'samples': 23509440, 'steps': 122444, 'loss/train': 0.7248775959014893} 08/31/2021 11:29:00 - INFO - __main__ - Step 122446: {'lr': 4.1559466816591065e-05, 'samples': 23509632, 'steps': 122445, 'loss/train': 1.2986514568328857} 08/31/2021 11:29:00 - INFO - __main__ - Step 122447: {'lr': 4.155653688362221e-05, 'samples': 23509824, 'steps': 122446, 'loss/train': 2.0586740970611572} 08/31/2021 11:29:01 - INFO - __main__ - Step 122448: {'lr': 4.1553607044574784e-05, 'samples': 23510016, 'steps': 122447, 'loss/train': 0.029633406549692154} 08/31/2021 11:29:01 - INFO - __main__ - Step 122449: {'lr': 4.155067729945006e-05, 'samples': 23510208, 'steps': 122448, 'loss/train': 0.061753131449222565} 08/31/2021 11:29:03 - INFO - __main__ - Step 122450: {'lr': 4.1547747648249396e-05, 'samples': 23510400, 'steps': 122449, 'loss/train': 0.6640464663505554} 08/31/2021 11:29:03 - INFO - __main__ - Step 122451: {'lr': 4.15448180909741e-05, 'samples': 23510592, 'steps': 122450, 'loss/train': 1.2582495212554932} 08/31/2021 11:29:03 - INFO - __main__ - Step 122452: {'lr': 4.1541888627625505e-05, 'samples': 23510784, 'steps': 122451, 'loss/train': 1.304521083831787} 08/31/2021 11:29:04 - INFO - __main__ - Step 122453: {'lr': 4.153895925820492e-05, 'samples': 23510976, 'steps': 122452, 'loss/train': 1.1405696868896484} 08/31/2021 11:29:04 - INFO - __main__ - Step 122454: {'lr': 4.1536029982713635e-05, 'samples': 23511168, 'steps': 122453, 'loss/train': 1.1334012746810913} 08/31/2021 11:29:05 - INFO - __main__ - Step 122455: {'lr': 4.1533100801153025e-05, 'samples': 23511360, 'steps': 122454, 'loss/train': 1.2986907958984375} 08/31/2021 11:29:06 - INFO - __main__ - Step 122456: {'lr': 4.153017171352436e-05, 'samples': 23511552, 'steps': 122455, 'loss/train': 1.284670114517212} 08/31/2021 11:29:06 - INFO - __main__ - Step 122457: {'lr': 4.1527242719828994e-05, 'samples': 23511744, 'steps': 122456, 'loss/train': 0.7770903706550598} 08/31/2021 11:29:07 - INFO - __main__ - Step 122458: {'lr': 4.152431382006824e-05, 'samples': 23511936, 'steps': 122457, 'loss/train': 0.8634839653968811} 08/31/2021 11:29:07 - INFO - __main__ - Step 122459: {'lr': 4.1521385014243405e-05, 'samples': 23512128, 'steps': 122458, 'loss/train': 1.0920157432556152} 08/31/2021 11:29:09 - INFO - __main__ - Step 122460: {'lr': 4.1518456302355904e-05, 'samples': 23512320, 'steps': 122459, 'loss/train': 1.3217853307724} 08/31/2021 11:29:10 - INFO - __main__ - Step 122461: {'lr': 4.151552768440689e-05, 'samples': 23512512, 'steps': 122460, 'loss/train': 1.3818178176879883} 08/31/2021 11:29:10 - INFO - __main__ - Step 122462: {'lr': 4.151259916039776e-05, 'samples': 23512704, 'steps': 122461, 'loss/train': 0.26556381583213806} 08/31/2021 11:29:10 - INFO - __main__ - Step 122463: {'lr': 4.150967073032982e-05, 'samples': 23512896, 'steps': 122462, 'loss/train': 1.1176820993423462} 08/31/2021 11:29:11 - INFO - __main__ - Step 122464: {'lr': 4.150674239420443e-05, 'samples': 23513088, 'steps': 122463, 'loss/train': 0.19112879037857056} 08/31/2021 11:29:13 - INFO - __main__ - Step 122465: {'lr': 4.150381415202287e-05, 'samples': 23513280, 'steps': 122464, 'loss/train': 0.9503735899925232} 08/31/2021 11:29:13 - INFO - __main__ - Step 122466: {'lr': 4.1500886003786484e-05, 'samples': 23513472, 'steps': 122465, 'loss/train': 0.4562748968601227} 08/31/2021 11:29:14 - INFO - __main__ - Step 122467: {'lr': 4.149795794949657e-05, 'samples': 23513664, 'steps': 122466, 'loss/train': 0.013570304960012436} 08/31/2021 11:29:14 - INFO - __main__ - Step 122468: {'lr': 4.149502998915447e-05, 'samples': 23513856, 'steps': 122467, 'loss/train': 0.02696993760764599} 08/31/2021 11:29:14 - INFO - __main__ - Step 122469: {'lr': 4.14921021227615e-05, 'samples': 23514048, 'steps': 122468, 'loss/train': 0.049310579895973206} 08/31/2021 11:29:15 - INFO - __main__ - Step 122470: {'lr': 4.148917435031896e-05, 'samples': 23514240, 'steps': 122469, 'loss/train': 1.4309083223342896} 08/31/2021 11:29:15 - INFO - __main__ - Step 122471: {'lr': 4.148624667182818e-05, 'samples': 23514432, 'steps': 122470, 'loss/train': 1.167936086654663} 08/31/2021 11:29:16 - INFO - __main__ - Step 122472: {'lr': 4.1483319087290474e-05, 'samples': 23514624, 'steps': 122471, 'loss/train': 1.2334808111190796} 08/31/2021 11:29:17 - INFO - __main__ - Step 122473: {'lr': 4.148039159670722e-05, 'samples': 23514816, 'steps': 122472, 'loss/train': 1.2045999765396118} 08/31/2021 11:29:17 - INFO - __main__ - Step 122474: {'lr': 4.147746420007964e-05, 'samples': 23515008, 'steps': 122473, 'loss/train': 0.7056310772895813} 08/31/2021 11:29:18 - INFO - __main__ - Step 122475: {'lr': 4.1474536897409096e-05, 'samples': 23515200, 'steps': 122474, 'loss/train': 1.2882367372512817} 08/31/2021 11:29:18 - INFO - __main__ - Step 122476: {'lr': 4.14716096886969e-05, 'samples': 23515392, 'steps': 122475, 'loss/train': 1.6729503870010376} 08/31/2021 11:29:18 - INFO - __main__ - Step 122477: {'lr': 4.14686825739444e-05, 'samples': 23515584, 'steps': 122476, 'loss/train': 1.7485712766647339} 08/31/2021 11:29:20 - INFO - __main__ - Step 122478: {'lr': 4.1465755553152876e-05, 'samples': 23515776, 'steps': 122477, 'loss/train': 1.0539695024490356} 08/31/2021 11:29:21 - INFO - __main__ - Step 122479: {'lr': 4.146282862632367e-05, 'samples': 23515968, 'steps': 122478, 'loss/train': 1.7297009229660034} 08/31/2021 11:29:21 - INFO - __main__ - Step 122480: {'lr': 4.1459901793458075e-05, 'samples': 23516160, 'steps': 122479, 'loss/train': 1.0653228759765625} 08/31/2021 11:29:21 - INFO - __main__ - Step 122481: {'lr': 4.145697505455745e-05, 'samples': 23516352, 'steps': 122480, 'loss/train': 1.027222990989685} 08/31/2021 11:29:22 - INFO - __main__ - Step 122482: {'lr': 4.1454048409623105e-05, 'samples': 23516544, 'steps': 122481, 'loss/train': 0.9641435742378235} 08/31/2021 11:29:22 - INFO - __main__ - Step 122483: {'lr': 4.1451121858656324e-05, 'samples': 23516736, 'steps': 122482, 'loss/train': 0.01998806744813919} 08/31/2021 11:29:24 - INFO - __main__ - Step 122484: {'lr': 4.144819540165845e-05, 'samples': 23516928, 'steps': 122483, 'loss/train': 0.02889302745461464} 08/31/2021 11:29:25 - INFO - __main__ - Step 122485: {'lr': 4.144526903863083e-05, 'samples': 23517120, 'steps': 122484, 'loss/train': 0.014989720657467842} 08/31/2021 11:29:25 - INFO - __main__ - Step 122486: {'lr': 4.144234276957473e-05, 'samples': 23517312, 'steps': 122485, 'loss/train': 0.3349875509738922} 08/31/2021 11:29:25 - INFO - __main__ - Step 122487: {'lr': 4.143941659449155e-05, 'samples': 23517504, 'steps': 122486, 'loss/train': 1.3302491903305054} 08/31/2021 11:29:26 - INFO - __main__ - Step 122488: {'lr': 4.1436490513382497e-05, 'samples': 23517696, 'steps': 122487, 'loss/train': 0.6888807415962219} 08/31/2021 11:29:26 - INFO - __main__ - Step 122489: {'lr': 4.143356452624894e-05, 'samples': 23517888, 'steps': 122488, 'loss/train': 1.1615698337554932} 08/31/2021 11:29:28 - INFO - __main__ - Step 122490: {'lr': 4.143063863309221e-05, 'samples': 23518080, 'steps': 122489, 'loss/train': 0.7189134955406189} 08/31/2021 11:29:28 - INFO - __main__ - Step 122491: {'lr': 4.142771283391361e-05, 'samples': 23518272, 'steps': 122490, 'loss/train': 1.8980199098587036} 08/31/2021 11:29:28 - INFO - __main__ - Step 122492: {'lr': 4.142478712871445e-05, 'samples': 23518464, 'steps': 122491, 'loss/train': 1.3303906917572021} 08/31/2021 11:29:29 - INFO - __main__ - Step 122493: {'lr': 4.142186151749608e-05, 'samples': 23518656, 'steps': 122492, 'loss/train': 1.0519336462020874} 08/31/2021 11:29:29 - INFO - __main__ - Step 122494: {'lr': 4.141893600025981e-05, 'samples': 23518848, 'steps': 122493, 'loss/train': 0.976911187171936} 08/31/2021 11:29:31 - INFO - __main__ - Step 122495: {'lr': 4.141601057700692e-05, 'samples': 23519040, 'steps': 122494, 'loss/train': 1.2681628465652466} 08/31/2021 11:29:31 - INFO - __main__ - Step 122496: {'lr': 4.1413085247738764e-05, 'samples': 23519232, 'steps': 122495, 'loss/train': 0.7840849161148071} 08/31/2021 11:29:32 - INFO - __main__ - Step 122497: {'lr': 4.141016001245668e-05, 'samples': 23519424, 'steps': 122496, 'loss/train': 1.4871065616607666} 08/31/2021 11:29:32 - INFO - __main__ - Step 122498: {'lr': 4.1407234871161994e-05, 'samples': 23519616, 'steps': 122497, 'loss/train': 1.5702465772628784} 08/31/2021 11:29:32 - INFO - __main__ - Step 122499: {'lr': 4.140430982385593e-05, 'samples': 23519808, 'steps': 122498, 'loss/train': 0.40691956877708435} 08/31/2021 11:29:34 - INFO - __main__ - Step 122500: {'lr': 4.1401384870539876e-05, 'samples': 23520000, 'steps': 122499, 'loss/train': 0.7322737574577332} 08/31/2021 11:29:34 - INFO - __main__ - Step 122501: {'lr': 4.139846001121514e-05, 'samples': 23520192, 'steps': 122500, 'loss/train': 0.5777205228805542} 08/31/2021 11:29:35 - INFO - __main__ - Step 122502: {'lr': 4.139553524588302e-05, 'samples': 23520384, 'steps': 122501, 'loss/train': 0.3680700361728668} 08/31/2021 11:29:35 - INFO - __main__ - Step 122503: {'lr': 4.139261057454488e-05, 'samples': 23520576, 'steps': 122502, 'loss/train': 1.065360426902771} 08/31/2021 11:29:35 - INFO - __main__ - Step 122504: {'lr': 4.1389685997201996e-05, 'samples': 23520768, 'steps': 122503, 'loss/train': 0.6374276876449585} 08/31/2021 11:29:37 - INFO - __main__ - Step 122505: {'lr': 4.1386761513855704e-05, 'samples': 23520960, 'steps': 122504, 'loss/train': 0.8504660725593567} 08/31/2021 11:29:38 - INFO - __main__ - Step 122506: {'lr': 4.13838371245073e-05, 'samples': 23521152, 'steps': 122505, 'loss/train': 0.24179694056510925} 08/31/2021 11:29:38 - INFO - __main__ - Step 122507: {'lr': 4.1380912829158155e-05, 'samples': 23521344, 'steps': 122506, 'loss/train': 0.5940457582473755} 08/31/2021 11:29:38 - INFO - __main__ - Step 122508: {'lr': 4.137798862780951e-05, 'samples': 23521536, 'steps': 122507, 'loss/train': 0.7624683380126953} 08/31/2021 11:29:39 - INFO - __main__ - Step 122509: {'lr': 4.13750645204628e-05, 'samples': 23521728, 'steps': 122508, 'loss/train': 1.5511407852172852} 08/31/2021 11:29:40 - INFO - __main__ - Step 122510: {'lr': 4.137214050711921e-05, 'samples': 23521920, 'steps': 122509, 'loss/train': 1.4508192539215088} 08/31/2021 11:29:41 - INFO - __main__ - Step 122511: {'lr': 4.136921658778012e-05, 'samples': 23522112, 'steps': 122510, 'loss/train': 0.3837442100048065} 08/31/2021 11:29:41 - INFO - __main__ - Step 122512: {'lr': 4.136629276244686e-05, 'samples': 23522304, 'steps': 122511, 'loss/train': 0.33590275049209595} 08/31/2021 11:29:41 - INFO - __main__ - Step 122513: {'lr': 4.13633690311207e-05, 'samples': 23522496, 'steps': 122512, 'loss/train': 1.4383047819137573} 08/31/2021 11:29:42 - INFO - __main__ - Step 122514: {'lr': 4.1360445393802986e-05, 'samples': 23522688, 'steps': 122513, 'loss/train': 0.8083588480949402} 08/31/2021 11:29:44 - INFO - __main__ - Step 122515: {'lr': 4.1357521850495044e-05, 'samples': 23522880, 'steps': 122514, 'loss/train': 1.023767113685608} 08/31/2021 11:29:44 - INFO - __main__ - Step 122516: {'lr': 4.135459840119818e-05, 'samples': 23523072, 'steps': 122515, 'loss/train': 0.46225211024284363} 08/31/2021 11:29:45 - INFO - __main__ - Step 122517: {'lr': 4.135167504591372e-05, 'samples': 23523264, 'steps': 122516, 'loss/train': 0.7326354384422302} 08/31/2021 11:29:45 - INFO - __main__ - Step 122518: {'lr': 4.134875178464298e-05, 'samples': 23523456, 'steps': 122517, 'loss/train': 1.0646579265594482} 08/31/2021 11:29:45 - INFO - __main__ - Step 122519: {'lr': 4.1345828617387255e-05, 'samples': 23523648, 'steps': 122518, 'loss/train': 0.9185675382614136} 08/31/2021 11:29:46 - INFO - __main__ - Step 122520: {'lr': 4.1342905544147966e-05, 'samples': 23523840, 'steps': 122519, 'loss/train': 1.1158982515335083} 08/31/2021 11:29:47 - INFO - __main__ - Step 122521: {'lr': 4.1339982564926244e-05, 'samples': 23524032, 'steps': 122520, 'loss/train': 0.7457504272460938} 08/31/2021 11:29:48 - INFO - __main__ - Step 122522: {'lr': 4.133705967972354e-05, 'samples': 23524224, 'steps': 122521, 'loss/train': 1.3986982107162476} 08/31/2021 11:29:48 - INFO - __main__ - Step 122523: {'lr': 4.1334136888541126e-05, 'samples': 23524416, 'steps': 122522, 'loss/train': 0.6578084230422974} 08/31/2021 11:29:48 - INFO - __main__ - Step 122524: {'lr': 4.133121419138033e-05, 'samples': 23524608, 'steps': 122523, 'loss/train': 0.05084219202399254} 08/31/2021 11:29:49 - INFO - __main__ - Step 122525: {'lr': 4.132829158824247e-05, 'samples': 23524800, 'steps': 122524, 'loss/train': 1.1158201694488525} 08/31/2021 11:29:50 - INFO - __main__ - Step 122526: {'lr': 4.1325369079128874e-05, 'samples': 23524992, 'steps': 122525, 'loss/train': 1.3498440980911255} 08/31/2021 11:29:51 - INFO - __main__ - Step 122527: {'lr': 4.1322446664040805e-05, 'samples': 23525184, 'steps': 122526, 'loss/train': 1.2761410474777222} 08/31/2021 11:29:51 - INFO - __main__ - Step 122528: {'lr': 4.131952434297967e-05, 'samples': 23525376, 'steps': 122527, 'loss/train': 1.0708491802215576} 08/31/2021 11:29:51 - INFO - __main__ - Step 122529: {'lr': 4.1316602115946704e-05, 'samples': 23525568, 'steps': 122528, 'loss/train': 1.6058472394943237} 08/31/2021 11:29:52 - INFO - __main__ - Step 122530: {'lr': 4.131367998294327e-05, 'samples': 23525760, 'steps': 122529, 'loss/train': 0.87055903673172} 08/31/2021 11:29:53 - INFO - __main__ - Step 122531: {'lr': 4.131075794397074e-05, 'samples': 23525952, 'steps': 122530, 'loss/train': 1.4087246656417847} 08/31/2021 11:29:54 - INFO - __main__ - Step 122532: {'lr': 4.130783599903029e-05, 'samples': 23526144, 'steps': 122531, 'loss/train': 1.3198195695877075} 08/31/2021 11:29:54 - INFO - __main__ - Step 122533: {'lr': 4.130491414812332e-05, 'samples': 23526336, 'steps': 122532, 'loss/train': 1.296511173248291} 08/31/2021 11:29:55 - INFO - __main__ - Step 122534: {'lr': 4.130199239125113e-05, 'samples': 23526528, 'steps': 122533, 'loss/train': 1.5230181217193604} 08/31/2021 11:29:55 - INFO - __main__ - Step 122535: {'lr': 4.1299070728415047e-05, 'samples': 23526720, 'steps': 122534, 'loss/train': 0.6224992275238037} 08/31/2021 11:29:56 - INFO - __main__ - Step 122536: {'lr': 4.129614915961638e-05, 'samples': 23526912, 'steps': 122535, 'loss/train': 1.064540982246399} 08/31/2021 11:29:57 - INFO - __main__ - Step 122537: {'lr': 4.129322768485644e-05, 'samples': 23527104, 'steps': 122536, 'loss/train': 1.8689851760864258} 08/31/2021 11:29:57 - INFO - __main__ - Step 122538: {'lr': 4.129030630413655e-05, 'samples': 23527296, 'steps': 122537, 'loss/train': 0.9226181507110596} 08/31/2021 11:29:58 - INFO - __main__ - Step 122539: {'lr': 4.128738501745802e-05, 'samples': 23527488, 'steps': 122538, 'loss/train': 1.1929500102996826} 08/31/2021 11:29:58 - INFO - __main__ - Step 122540: {'lr': 4.1284463824822205e-05, 'samples': 23527680, 'steps': 122539, 'loss/train': 1.3346669673919678} 08/31/2021 11:30:00 - INFO - __main__ - Step 122541: {'lr': 4.128154272623036e-05, 'samples': 23527872, 'steps': 122540, 'loss/train': 0.7131668329238892} 08/31/2021 11:30:00 - INFO - __main__ - Step 122542: {'lr': 4.1278621721683895e-05, 'samples': 23528064, 'steps': 122541, 'loss/train': 1.6899291276931763} 08/31/2021 11:30:00 - INFO - __main__ - Step 122543: {'lr': 4.127570081118401e-05, 'samples': 23528256, 'steps': 122542, 'loss/train': 0.030562790110707283} 08/31/2021 11:30:01 - INFO - __main__ - Step 122544: {'lr': 4.1272779994732086e-05, 'samples': 23528448, 'steps': 122543, 'loss/train': 1.0512940883636475} 08/31/2021 11:30:01 - INFO - __main__ - Step 122545: {'lr': 4.1269859272329404e-05, 'samples': 23528640, 'steps': 122544, 'loss/train': 1.1018335819244385} 08/31/2021 11:30:03 - INFO - __main__ - Step 122546: {'lr': 4.126693864397732e-05, 'samples': 23528832, 'steps': 122545, 'loss/train': 1.0867210626602173} 08/31/2021 11:30:03 - INFO - __main__ - Step 122547: {'lr': 4.126401810967711e-05, 'samples': 23529024, 'steps': 122546, 'loss/train': 0.26495927572250366} 08/31/2021 11:30:03 - INFO - __main__ - Step 122548: {'lr': 4.126109766943012e-05, 'samples': 23529216, 'steps': 122547, 'loss/train': 1.5010565519332886} 08/31/2021 11:30:04 - INFO - __main__ - Step 122549: {'lr': 4.125817732323767e-05, 'samples': 23529408, 'steps': 122548, 'loss/train': 0.8364596962928772} 08/31/2021 11:30:04 - INFO - __main__ - Step 122550: {'lr': 4.125525707110106e-05, 'samples': 23529600, 'steps': 122549, 'loss/train': 1.1328798532485962} 08/31/2021 11:30:04 - INFO - __main__ - Step 122551: {'lr': 4.12523369130216e-05, 'samples': 23529792, 'steps': 122550, 'loss/train': 1.3122072219848633} 08/31/2021 11:30:06 - INFO - __main__ - Step 122552: {'lr': 4.1249416849000634e-05, 'samples': 23529984, 'steps': 122551, 'loss/train': 0.7294042706489563} 08/31/2021 11:30:06 - INFO - __main__ - Step 122553: {'lr': 4.1246496879039444e-05, 'samples': 23530176, 'steps': 122552, 'loss/train': 0.12868613004684448} 08/31/2021 11:30:07 - INFO - __main__ - Step 122554: {'lr': 4.124357700313944e-05, 'samples': 23530368, 'steps': 122553, 'loss/train': 1.4168168306350708} 08/31/2021 11:30:07 - INFO - __main__ - Step 122555: {'lr': 4.12406572213018e-05, 'samples': 23530560, 'steps': 122554, 'loss/train': 0.21419040858745575} 08/31/2021 11:30:07 - INFO - __main__ - Step 122556: {'lr': 4.123773753352786e-05, 'samples': 23530752, 'steps': 122555, 'loss/train': 1.3255738019943237} 08/31/2021 11:30:09 - INFO - __main__ - Step 122557: {'lr': 4.123481793981901e-05, 'samples': 23530944, 'steps': 122556, 'loss/train': 0.3294740915298462} 08/31/2021 11:30:09 - INFO - __main__ - Step 122558: {'lr': 4.123189844017652e-05, 'samples': 23531136, 'steps': 122557, 'loss/train': 0.6217900514602661} 08/31/2021 11:30:10 - INFO - __main__ - Step 122559: {'lr': 4.122897903460171e-05, 'samples': 23531328, 'steps': 122558, 'loss/train': 0.7438391447067261} 08/31/2021 11:30:10 - INFO - __main__ - Step 122560: {'lr': 4.1226059723095896e-05, 'samples': 23531520, 'steps': 122559, 'loss/train': 1.4301496744155884} 08/31/2021 11:30:10 - INFO - __main__ - Step 122561: {'lr': 4.1223140505660426e-05, 'samples': 23531712, 'steps': 122560, 'loss/train': 1.2221498489379883} 08/31/2021 11:30:12 - INFO - __main__ - Step 122562: {'lr': 4.122022138229656e-05, 'samples': 23531904, 'steps': 122561, 'loss/train': 1.2129356861114502} 08/31/2021 11:30:13 - INFO - __main__ - Step 122563: {'lr': 4.121730235300564e-05, 'samples': 23532096, 'steps': 122562, 'loss/train': 1.4598093032836914} 08/31/2021 11:30:13 - INFO - __main__ - Step 122564: {'lr': 4.121438341778899e-05, 'samples': 23532288, 'steps': 122563, 'loss/train': 0.17085132002830505} 08/31/2021 11:30:13 - INFO - __main__ - Step 122565: {'lr': 4.1211464576647926e-05, 'samples': 23532480, 'steps': 122564, 'loss/train': 0.15836471319198608} 08/31/2021 11:30:14 - INFO - __main__ - Step 122566: {'lr': 4.120854582958375e-05, 'samples': 23532672, 'steps': 122565, 'loss/train': 0.026566611602902412} 08/31/2021 11:30:16 - INFO - __main__ - Step 122567: {'lr': 4.1205627176597816e-05, 'samples': 23532864, 'steps': 122566, 'loss/train': 1.115666151046753} 08/31/2021 11:30:17 - INFO - __main__ - Step 122568: {'lr': 4.120270861769138e-05, 'samples': 23533056, 'steps': 122567, 'loss/train': 0.9516346454620361} 08/31/2021 11:30:17 - INFO - __main__ - Step 122569: {'lr': 4.119979015286576e-05, 'samples': 23533248, 'steps': 122568, 'loss/train': 1.5705986022949219} 08/31/2021 11:30:17 - INFO - __main__ - Step 122570: {'lr': 4.119687178212231e-05, 'samples': 23533440, 'steps': 122569, 'loss/train': 1.5167583227157593} 08/31/2021 11:30:18 - INFO - __main__ - Step 122571: {'lr': 4.1193953505462314e-05, 'samples': 23533632, 'steps': 122570, 'loss/train': 0.908998966217041} 08/31/2021 11:30:18 - INFO - __main__ - Step 122572: {'lr': 4.119103532288709e-05, 'samples': 23533824, 'steps': 122571, 'loss/train': 0.024289287626743317} 08/31/2021 11:30:18 - INFO - __main__ - Step 122573: {'lr': 4.118811723439797e-05, 'samples': 23534016, 'steps': 122572, 'loss/train': 0.0429849736392498} 08/31/2021 11:30:20 - INFO - __main__ - Step 122574: {'lr': 4.118519923999628e-05, 'samples': 23534208, 'steps': 122573, 'loss/train': 0.4199771583080292} 08/31/2021 11:30:20 - INFO - __main__ - Step 122575: {'lr': 4.11822813396833e-05, 'samples': 23534400, 'steps': 122574, 'loss/train': 1.1299811601638794} 08/31/2021 11:30:21 - INFO - __main__ - Step 122576: {'lr': 4.117936353346039e-05, 'samples': 23534592, 'steps': 122575, 'loss/train': 1.3636025190353394} 08/31/2021 11:30:21 - INFO - __main__ - Step 122577: {'lr': 4.117644582132879e-05, 'samples': 23534784, 'steps': 122576, 'loss/train': 1.2354904413223267} 08/31/2021 11:30:21 - INFO - __main__ - Step 122578: {'lr': 4.11735282032899e-05, 'samples': 23534976, 'steps': 122577, 'loss/train': 1.1961911916732788} 08/31/2021 11:30:23 - INFO - __main__ - Step 122579: {'lr': 4.117061067934496e-05, 'samples': 23535168, 'steps': 122578, 'loss/train': 0.8218681812286377} 08/31/2021 11:30:24 - INFO - __main__ - Step 122580: {'lr': 4.116769324949535e-05, 'samples': 23535360, 'steps': 122579, 'loss/train': 1.7516626119613647} 08/31/2021 11:30:24 - INFO - __main__ - Step 122581: {'lr': 4.1164775913742404e-05, 'samples': 23535552, 'steps': 122580, 'loss/train': 1.7302820682525635} 08/31/2021 11:30:25 - INFO - __main__ - Step 122582: {'lr': 4.1161858672087326e-05, 'samples': 23535744, 'steps': 122581, 'loss/train': 1.3055684566497803} 08/31/2021 11:30:25 - INFO - __main__ - Step 122583: {'lr': 4.1158941524531504e-05, 'samples': 23535936, 'steps': 122582, 'loss/train': 1.201934576034546} 08/31/2021 11:30:25 - INFO - __main__ - Step 122584: {'lr': 4.1156024471076245e-05, 'samples': 23536128, 'steps': 122583, 'loss/train': 0.8429949879646301} 08/31/2021 11:30:27 - INFO - __main__ - Step 122585: {'lr': 4.115310751172283e-05, 'samples': 23536320, 'steps': 122584, 'loss/train': 1.0344867706298828} 08/31/2021 11:30:28 - INFO - __main__ - Step 122586: {'lr': 4.115019064647263e-05, 'samples': 23536512, 'steps': 122585, 'loss/train': 1.2213127613067627} 08/31/2021 11:30:28 - INFO - __main__ - Step 122587: {'lr': 4.114727387532691e-05, 'samples': 23536704, 'steps': 122586, 'loss/train': 2.342644453048706} 08/31/2021 11:30:29 - INFO - __main__ - Step 122588: {'lr': 4.114435719828702e-05, 'samples': 23536896, 'steps': 122587, 'loss/train': 1.2470276355743408} 08/31/2021 11:30:29 - INFO - __main__ - Step 122589: {'lr': 4.114144061535424e-05, 'samples': 23537088, 'steps': 122588, 'loss/train': 1.1666367053985596} 08/31/2021 11:30:29 - INFO - __main__ - Step 122590: {'lr': 4.1138524126529936e-05, 'samples': 23537280, 'steps': 122589, 'loss/train': 0.8873693346977234} 08/31/2021 11:30:30 - INFO - __main__ - Step 122591: {'lr': 4.113560773181538e-05, 'samples': 23537472, 'steps': 122590, 'loss/train': 1.6095942258834839} 08/31/2021 11:30:31 - INFO - __main__ - Step 122592: {'lr': 4.113269143121187e-05, 'samples': 23537664, 'steps': 122591, 'loss/train': 0.014436771161854267} 08/31/2021 11:30:32 - INFO - __main__ - Step 122593: {'lr': 4.112977522472078e-05, 'samples': 23537856, 'steps': 122592, 'loss/train': 1.3827801942825317} 08/31/2021 11:30:32 - INFO - __main__ - Step 122594: {'lr': 4.112685911234343e-05, 'samples': 23538048, 'steps': 122593, 'loss/train': 1.8586032390594482} 08/31/2021 11:30:32 - INFO - __main__ - Step 122595: {'lr': 4.1123943094081046e-05, 'samples': 23538240, 'steps': 122594, 'loss/train': 1.8741424083709717} 08/31/2021 11:30:33 - INFO - __main__ - Step 122596: {'lr': 4.112102716993499e-05, 'samples': 23538432, 'steps': 122595, 'loss/train': 0.37900206446647644} 08/31/2021 11:30:34 - INFO - __main__ - Step 122597: {'lr': 4.111811133990656e-05, 'samples': 23538624, 'steps': 122596, 'loss/train': 0.4515690207481384} 08/31/2021 11:30:35 - INFO - __main__ - Step 122598: {'lr': 4.11151956039971e-05, 'samples': 23538816, 'steps': 122597, 'loss/train': 1.6216719150543213} 08/31/2021 11:30:35 - INFO - __main__ - Step 122599: {'lr': 4.11122799622079e-05, 'samples': 23539008, 'steps': 122598, 'loss/train': 1.2070332765579224} 08/31/2021 11:30:35 - INFO - __main__ - Step 122600: {'lr': 4.1109364414540274e-05, 'samples': 23539200, 'steps': 122599, 'loss/train': 1.6949206590652466} 08/31/2021 11:30:36 - INFO - __main__ - Step 122601: {'lr': 4.110644896099558e-05, 'samples': 23539392, 'steps': 122600, 'loss/train': 0.9857621788978577} 08/31/2021 11:30:37 - INFO - __main__ - Step 122602: {'lr': 4.1103533601575065e-05, 'samples': 23539584, 'steps': 122601, 'loss/train': 1.1633732318878174} 08/31/2021 11:30:38 - INFO - __main__ - Step 122603: {'lr': 4.1100618336280096e-05, 'samples': 23539776, 'steps': 122602, 'loss/train': 1.2270041704177856} 08/31/2021 11:30:38 - INFO - __main__ - Step 122604: {'lr': 4.1097703165111935e-05, 'samples': 23539968, 'steps': 122603, 'loss/train': 1.1164655685424805} 08/31/2021 11:30:38 - INFO - __main__ - Step 122605: {'lr': 4.109478808807196e-05, 'samples': 23540160, 'steps': 122604, 'loss/train': 0.7377641201019287} 08/31/2021 11:30:39 - INFO - __main__ - Step 122606: {'lr': 4.1091873105161436e-05, 'samples': 23540352, 'steps': 122605, 'loss/train': 1.7846132516860962} 08/31/2021 11:30:40 - INFO - __main__ - Step 122607: {'lr': 4.108895821638167e-05, 'samples': 23540544, 'steps': 122606, 'loss/train': 1.0902795791625977} 08/31/2021 11:30:41 - INFO - __main__ - Step 122608: {'lr': 4.108604342173408e-05, 'samples': 23540736, 'steps': 122607, 'loss/train': 1.011066198348999} 08/31/2021 11:30:41 - INFO - __main__ - Step 122609: {'lr': 4.108312872121983e-05, 'samples': 23540928, 'steps': 122608, 'loss/train': 0.9031497836112976} 08/31/2021 11:30:41 - INFO - __main__ - Step 122610: {'lr': 4.1080214114840305e-05, 'samples': 23541120, 'steps': 122609, 'loss/train': 0.6453737020492554} 08/31/2021 11:30:42 - INFO - __main__ - Step 122611: {'lr': 4.1077299602596794e-05, 'samples': 23541312, 'steps': 122610, 'loss/train': 1.0790901184082031} 08/31/2021 11:30:43 - INFO - __main__ - Step 122612: {'lr': 4.107438518449064e-05, 'samples': 23541504, 'steps': 122611, 'loss/train': 0.6053176522254944} 08/31/2021 11:30:44 - INFO - __main__ - Step 122613: {'lr': 4.107147086052315e-05, 'samples': 23541696, 'steps': 122612, 'loss/train': 0.9666593074798584} 08/31/2021 11:30:44 - INFO - __main__ - Step 122614: {'lr': 4.106855663069561e-05, 'samples': 23541888, 'steps': 122613, 'loss/train': 0.5486943125724792} 08/31/2021 11:30:44 - INFO - __main__ - Step 122615: {'lr': 4.106564249500938e-05, 'samples': 23542080, 'steps': 122614, 'loss/train': 1.538155198097229} 08/31/2021 11:30:45 - INFO - __main__ - Step 122616: {'lr': 4.106272845346573e-05, 'samples': 23542272, 'steps': 122615, 'loss/train': 1.0834263563156128} 08/31/2021 11:30:45 - INFO - __main__ - Step 122617: {'lr': 4.1059814506065995e-05, 'samples': 23542464, 'steps': 122616, 'loss/train': 0.10284528136253357} 08/31/2021 11:30:47 - INFO - __main__ - Step 122618: {'lr': 4.105690065281148e-05, 'samples': 23542656, 'steps': 122617, 'loss/train': 1.09451162815094} 08/31/2021 11:30:47 - INFO - __main__ - Step 122619: {'lr': 4.105398689370351e-05, 'samples': 23542848, 'steps': 122618, 'loss/train': 1.3848373889923096} 08/31/2021 11:30:48 - INFO - __main__ - Step 122620: {'lr': 4.105107322874338e-05, 'samples': 23543040, 'steps': 122619, 'loss/train': 1.2928203344345093} 08/31/2021 11:30:48 - INFO - __main__ - Step 122621: {'lr': 4.104815965793249e-05, 'samples': 23543232, 'steps': 122620, 'loss/train': 0.9892645478248596} 08/31/2021 11:30:48 - INFO - __main__ - Step 122622: {'lr': 4.104524618127201e-05, 'samples': 23543424, 'steps': 122621, 'loss/train': 0.37615451216697693} 08/31/2021 11:30:50 - INFO - __main__ - Step 122623: {'lr': 4.104233279876329e-05, 'samples': 23543616, 'steps': 122622, 'loss/train': 0.9285874962806702} 08/31/2021 11:30:51 - INFO - __main__ - Step 122624: {'lr': 4.103941951040771e-05, 'samples': 23543808, 'steps': 122623, 'loss/train': 0.7795172929763794} 08/31/2021 11:30:51 - INFO - __main__ - Step 122625: {'lr': 4.103650631620651e-05, 'samples': 23544000, 'steps': 122624, 'loss/train': 1.3172613382339478} 08/31/2021 11:30:51 - INFO - __main__ - Step 122626: {'lr': 4.103359321616104e-05, 'samples': 23544192, 'steps': 122625, 'loss/train': 0.7249796986579895} 08/31/2021 11:30:52 - INFO - __main__ - Step 122627: {'lr': 4.103068021027262e-05, 'samples': 23544384, 'steps': 122626, 'loss/train': 1.5636911392211914} 08/31/2021 11:30:52 - INFO - __main__ - Step 122628: {'lr': 4.1027767298542546e-05, 'samples': 23544576, 'steps': 122627, 'loss/train': 1.2112228870391846} 08/31/2021 11:30:54 - INFO - __main__ - Step 122629: {'lr': 4.102485448097215e-05, 'samples': 23544768, 'steps': 122628, 'loss/train': 0.5731160044670105} 08/31/2021 11:30:55 - INFO - __main__ - Step 122630: {'lr': 4.1021941757562714e-05, 'samples': 23544960, 'steps': 122629, 'loss/train': 1.5673021078109741} 08/31/2021 11:30:55 - INFO - __main__ - Step 122631: {'lr': 4.1019029128315565e-05, 'samples': 23545152, 'steps': 122630, 'loss/train': 1.0743614435195923} 08/31/2021 11:30:56 - INFO - __main__ - Step 122632: {'lr': 4.101611659323204e-05, 'samples': 23545344, 'steps': 122631, 'loss/train': 1.228121042251587} 08/31/2021 11:30:56 - INFO - __main__ - Step 122633: {'lr': 4.101320415231341e-05, 'samples': 23545536, 'steps': 122632, 'loss/train': 1.2801158428192139} 08/31/2021 11:30:58 - INFO - __main__ - Step 122634: {'lr': 4.1010291805560986e-05, 'samples': 23545728, 'steps': 122633, 'loss/train': 0.3027005195617676} 08/31/2021 11:30:58 - INFO - __main__ - Step 122635: {'lr': 4.1007379552976175e-05, 'samples': 23545920, 'steps': 122634, 'loss/train': 0.7871810793876648} 08/31/2021 11:30:58 - INFO - __main__ - Step 122636: {'lr': 4.100446739456018e-05, 'samples': 23546112, 'steps': 122635, 'loss/train': 1.907948613166809} 08/31/2021 11:30:59 - INFO - __main__ - Step 122637: {'lr': 4.100155533031433e-05, 'samples': 23546304, 'steps': 122636, 'loss/train': 0.9168986082077026} 08/31/2021 11:30:59 - INFO - __main__ - Step 122638: {'lr': 4.099864336023992e-05, 'samples': 23546496, 'steps': 122637, 'loss/train': 1.4070968627929688} 08/31/2021 11:31:01 - INFO - __main__ - Step 122639: {'lr': 4.099573148433833e-05, 'samples': 23546688, 'steps': 122638, 'loss/train': 1.176946997642517} 08/31/2021 11:31:01 - INFO - __main__ - Step 122640: {'lr': 4.0992819702610845e-05, 'samples': 23546880, 'steps': 122639, 'loss/train': 0.8991592526435852} 08/31/2021 11:31:01 - INFO - __main__ - Step 122641: {'lr': 4.0989908015058756e-05, 'samples': 23547072, 'steps': 122640, 'loss/train': 1.8819361925125122} 08/31/2021 11:31:02 - INFO - __main__ - Step 122642: {'lr': 4.098699642168338e-05, 'samples': 23547264, 'steps': 122641, 'loss/train': 1.3357248306274414} 08/31/2021 11:31:02 - INFO - __main__ - Step 122643: {'lr': 4.098408492248606e-05, 'samples': 23547456, 'steps': 122642, 'loss/train': 1.3459746837615967} 08/31/2021 11:31:04 - INFO - __main__ - Step 122644: {'lr': 4.098117351746808e-05, 'samples': 23547648, 'steps': 122643, 'loss/train': 1.3443005084991455} 08/31/2021 11:31:04 - INFO - __main__ - Step 122645: {'lr': 4.0978262206630756e-05, 'samples': 23547840, 'steps': 122644, 'loss/train': 0.8791977763175964} 08/31/2021 11:31:05 - INFO - __main__ - Step 122646: {'lr': 4.09753509899754e-05, 'samples': 23548032, 'steps': 122645, 'loss/train': 1.1552259922027588} 08/31/2021 11:31:05 - INFO - __main__ - Step 122647: {'lr': 4.097243986750332e-05, 'samples': 23548224, 'steps': 122646, 'loss/train': 1.2072232961654663} 08/31/2021 11:31:05 - INFO - __main__ - Step 122648: {'lr': 4.0969528839215895e-05, 'samples': 23548416, 'steps': 122647, 'loss/train': 2.1767499446868896} 08/31/2021 11:31:06 - INFO - __main__ - Step 122649: {'lr': 4.096661790511433e-05, 'samples': 23548608, 'steps': 122648, 'loss/train': 1.0410336256027222} 08/31/2021 11:31:06 - INFO - __main__ - Step 122650: {'lr': 4.096370706519994e-05, 'samples': 23548800, 'steps': 122649, 'loss/train': 1.756138563156128} 08/31/2021 11:31:08 - INFO - __main__ - Step 122651: {'lr': 4.0960796319474134e-05, 'samples': 23548992, 'steps': 122650, 'loss/train': 1.4857712984085083} 08/31/2021 11:31:08 - INFO - __main__ - Step 122652: {'lr': 4.095788566793812e-05, 'samples': 23549184, 'steps': 122651, 'loss/train': 1.4438568353652954} 08/31/2021 11:31:09 - INFO - __main__ - Step 122653: {'lr': 4.095497511059329e-05, 'samples': 23549376, 'steps': 122652, 'loss/train': 0.34494051337242126} 08/31/2021 11:31:09 - INFO - __main__ - Step 122654: {'lr': 4.0952064647440914e-05, 'samples': 23549568, 'steps': 122653, 'loss/train': 1.7854548692703247} 08/31/2021 11:31:09 - INFO - __main__ - Step 122655: {'lr': 4.094915427848231e-05, 'samples': 23549760, 'steps': 122654, 'loss/train': 0.957434892654419} 08/31/2021 11:31:11 - INFO - __main__ - Step 122656: {'lr': 4.094624400371877e-05, 'samples': 23549952, 'steps': 122655, 'loss/train': 0.7899128794670105} 08/31/2021 11:31:11 - INFO - __main__ - Step 122657: {'lr': 4.0943333823151655e-05, 'samples': 23550144, 'steps': 122656, 'loss/train': 1.1583813428878784} 08/31/2021 11:31:11 - INFO - __main__ - Step 122658: {'lr': 4.094042373678225e-05, 'samples': 23550336, 'steps': 122657, 'loss/train': 0.8319478631019592} 08/31/2021 11:31:12 - INFO - __main__ - Step 122659: {'lr': 4.093751374461185e-05, 'samples': 23550528, 'steps': 122658, 'loss/train': 1.4169105291366577} 08/31/2021 11:31:12 - INFO - __main__ - Step 122660: {'lr': 4.093460384664177e-05, 'samples': 23550720, 'steps': 122659, 'loss/train': 1.2841442823410034} 08/31/2021 11:31:14 - INFO - __main__ - Step 122661: {'lr': 4.093169404287336e-05, 'samples': 23550912, 'steps': 122660, 'loss/train': 1.7034940719604492} 08/31/2021 11:31:14 - INFO - __main__ - Step 122662: {'lr': 4.0928784333307935e-05, 'samples': 23551104, 'steps': 122661, 'loss/train': 0.9461327195167542} 08/31/2021 11:31:14 - INFO - __main__ - Step 122663: {'lr': 4.0925874717946735e-05, 'samples': 23551296, 'steps': 122662, 'loss/train': 0.9252497553825378} 08/31/2021 11:31:15 - INFO - __main__ - Step 122664: {'lr': 4.092296519679109e-05, 'samples': 23551488, 'steps': 122663, 'loss/train': 0.714365541934967} 08/31/2021 11:31:15 - INFO - __main__ - Step 122665: {'lr': 4.092005576984234e-05, 'samples': 23551680, 'steps': 122664, 'loss/train': 1.0687750577926636} 08/31/2021 11:31:17 - INFO - __main__ - Step 122666: {'lr': 4.0917146437101785e-05, 'samples': 23551872, 'steps': 122665, 'loss/train': 1.7477121353149414} 08/31/2021 11:31:17 - INFO - __main__ - Step 122667: {'lr': 4.091423719857074e-05, 'samples': 23552064, 'steps': 122666, 'loss/train': 0.724643886089325} 08/31/2021 11:31:17 - INFO - __main__ - Step 122668: {'lr': 4.091132805425052e-05, 'samples': 23552256, 'steps': 122667, 'loss/train': 1.2004486322402954} 08/31/2021 11:31:18 - INFO - __main__ - Step 122669: {'lr': 4.090841900414241e-05, 'samples': 23552448, 'steps': 122668, 'loss/train': 1.1307189464569092} 08/31/2021 11:31:18 - INFO - __main__ - Step 122670: {'lr': 4.090551004824777e-05, 'samples': 23552640, 'steps': 122669, 'loss/train': 1.4600893259048462} 08/31/2021 11:31:20 - INFO - __main__ - Step 122671: {'lr': 4.0902601186567856e-05, 'samples': 23552832, 'steps': 122670, 'loss/train': 1.4968942403793335} 08/31/2021 11:31:20 - INFO - __main__ - Step 122672: {'lr': 4.089969241910402e-05, 'samples': 23553024, 'steps': 122671, 'loss/train': 1.2689208984375} 08/31/2021 11:31:20 - INFO - __main__ - Step 122673: {'lr': 4.0896783745857536e-05, 'samples': 23553216, 'steps': 122672, 'loss/train': 0.30502641201019287} 08/31/2021 11:31:21 - INFO - __main__ - Step 122674: {'lr': 4.089387516682974e-05, 'samples': 23553408, 'steps': 122673, 'loss/train': 0.9310351014137268} 08/31/2021 11:31:21 - INFO - __main__ - Step 122675: {'lr': 4.0890966682022e-05, 'samples': 23553600, 'steps': 122674, 'loss/train': 0.6850277185440063} 08/31/2021 11:31:23 - INFO - __main__ - Step 122676: {'lr': 4.088805829143552e-05, 'samples': 23553792, 'steps': 122675, 'loss/train': 1.1699538230895996} 08/31/2021 11:31:23 - INFO - __main__ - Step 122677: {'lr': 4.088514999507162e-05, 'samples': 23553984, 'steps': 122676, 'loss/train': 1.3140844106674194} 08/31/2021 11:31:24 - INFO - __main__ - Step 122678: {'lr': 4.088224179293168e-05, 'samples': 23554176, 'steps': 122677, 'loss/train': 1.0702433586120605} 08/31/2021 11:31:24 - INFO - __main__ - Step 122679: {'lr': 4.087933368501695e-05, 'samples': 23554368, 'steps': 122678, 'loss/train': 0.013007617555558681} 08/31/2021 11:31:25 - INFO - __main__ - Step 122680: {'lr': 4.0876425671328765e-05, 'samples': 23554560, 'steps': 122679, 'loss/train': 0.014785947278141975} 08/31/2021 11:31:25 - INFO - __main__ - Step 122681: {'lr': 4.087351775186846e-05, 'samples': 23554752, 'steps': 122680, 'loss/train': 0.9676054120063782} 08/31/2021 11:31:27 - INFO - __main__ - Step 122682: {'lr': 4.08706099266373e-05, 'samples': 23554944, 'steps': 122681, 'loss/train': 1.3675322532653809} 08/31/2021 11:31:27 - INFO - __main__ - Step 122683: {'lr': 4.0867702195636625e-05, 'samples': 23555136, 'steps': 122682, 'loss/train': 1.346550703048706} 08/31/2021 11:31:28 - INFO - __main__ - Step 122684: {'lr': 4.086479455886774e-05, 'samples': 23555328, 'steps': 122683, 'loss/train': 1.6283618211746216} 08/31/2021 11:31:28 - INFO - __main__ - Step 122685: {'lr': 4.086188701633195e-05, 'samples': 23555520, 'steps': 122684, 'loss/train': 1.1584720611572266} 08/31/2021 11:31:29 - INFO - __main__ - Step 122686: {'lr': 4.085897956803056e-05, 'samples': 23555712, 'steps': 122685, 'loss/train': 1.7579480409622192} 08/31/2021 11:31:30 - INFO - __main__ - Step 122687: {'lr': 4.0856072213964866e-05, 'samples': 23555904, 'steps': 122686, 'loss/train': 1.389923334121704} 08/31/2021 11:31:31 - INFO - __main__ - Step 122688: {'lr': 4.08531649541363e-05, 'samples': 23556096, 'steps': 122687, 'loss/train': 0.2318318486213684} 08/31/2021 11:31:31 - INFO - __main__ - Step 122689: {'lr': 4.085025778854598e-05, 'samples': 23556288, 'steps': 122688, 'loss/train': 1.3789371252059937} 08/31/2021 11:31:32 - INFO - __main__ - Step 122690: {'lr': 4.0847350717195307e-05, 'samples': 23556480, 'steps': 122689, 'loss/train': 1.130399227142334} 08/31/2021 11:31:32 - INFO - __main__ - Step 122691: {'lr': 4.0844443740085614e-05, 'samples': 23556672, 'steps': 122690, 'loss/train': 0.06348802894353867} 08/31/2021 11:31:32 - INFO - __main__ - Step 122692: {'lr': 4.084153685721817e-05, 'samples': 23556864, 'steps': 122691, 'loss/train': 0.03781589865684509} 08/31/2021 11:31:33 - INFO - __main__ - Step 122693: {'lr': 4.0838630068594315e-05, 'samples': 23557056, 'steps': 122692, 'loss/train': 1.119545817375183} 08/31/2021 11:31:34 - INFO - __main__ - Step 122694: {'lr': 4.083572337421534e-05, 'samples': 23557248, 'steps': 122693, 'loss/train': 1.1139187812805176} 08/31/2021 11:31:35 - INFO - __main__ - Step 122695: {'lr': 4.083281677408254e-05, 'samples': 23557440, 'steps': 122694, 'loss/train': 1.7198588848114014} 08/31/2021 11:31:35 - INFO - __main__ - Step 122696: {'lr': 4.082991026819727e-05, 'samples': 23557632, 'steps': 122695, 'loss/train': 1.2692866325378418} 08/31/2021 11:31:36 - INFO - __main__ - Step 122697: {'lr': 4.0827003856560796e-05, 'samples': 23557824, 'steps': 122696, 'loss/train': 0.159796804189682} 08/31/2021 11:31:36 - INFO - __main__ - Step 122698: {'lr': 4.082409753917446e-05, 'samples': 23558016, 'steps': 122697, 'loss/train': 5.717237949371338} 08/31/2021 11:31:36 - INFO - __main__ - Step 122699: {'lr': 4.082119131603956e-05, 'samples': 23558208, 'steps': 122698, 'loss/train': 1.0105235576629639} 08/31/2021 11:31:38 - INFO - __main__ - Step 122700: {'lr': 4.081828518715741e-05, 'samples': 23558400, 'steps': 122699, 'loss/train': 1.944368839263916} 08/31/2021 11:31:38 - INFO - __main__ - Step 122701: {'lr': 4.081537915252931e-05, 'samples': 23558592, 'steps': 122700, 'loss/train': 1.347423791885376} 08/31/2021 11:31:39 - INFO - __main__ - Step 122702: {'lr': 4.0812473212156616e-05, 'samples': 23558784, 'steps': 122701, 'loss/train': 1.1603400707244873} 08/31/2021 11:31:39 - INFO - __main__ - Step 122703: {'lr': 4.0809567366040524e-05, 'samples': 23558976, 'steps': 122702, 'loss/train': 1.031583547592163} 08/31/2021 11:31:39 - INFO - __main__ - Step 122704: {'lr': 4.080666161418245e-05, 'samples': 23559168, 'steps': 122703, 'loss/train': 1.035896897315979} 08/31/2021 11:31:41 - INFO - __main__ - Step 122705: {'lr': 4.080375595658364e-05, 'samples': 23559360, 'steps': 122704, 'loss/train': 1.5571563243865967} 08/31/2021 11:31:41 - INFO - __main__ - Step 122706: {'lr': 4.0800850393245435e-05, 'samples': 23559552, 'steps': 122705, 'loss/train': 0.9004864692687988} 08/31/2021 11:31:42 - INFO - __main__ - Step 122707: {'lr': 4.079794492416913e-05, 'samples': 23559744, 'steps': 122706, 'loss/train': 0.558910071849823} 08/31/2021 11:31:42 - INFO - __main__ - Step 122708: {'lr': 4.0795039549356064e-05, 'samples': 23559936, 'steps': 122707, 'loss/train': 1.2951414585113525} 08/31/2021 11:31:42 - INFO - __main__ - Step 122709: {'lr': 4.079213426880751e-05, 'samples': 23560128, 'steps': 122708, 'loss/train': 1.0742334127426147} 08/31/2021 11:31:44 - INFO - __main__ - Step 122710: {'lr': 4.0789229082524806e-05, 'samples': 23560320, 'steps': 122709, 'loss/train': 1.1079657077789307} 08/31/2021 11:31:44 - INFO - __main__ - Step 122711: {'lr': 4.078632399050922e-05, 'samples': 23560512, 'steps': 122710, 'loss/train': 0.6963096857070923} 08/31/2021 11:31:45 - INFO - __main__ - Step 122712: {'lr': 4.078341899276211e-05, 'samples': 23560704, 'steps': 122711, 'loss/train': 0.18428973853588104} 08/31/2021 11:31:45 - INFO - __main__ - Step 122713: {'lr': 4.0780514089284766e-05, 'samples': 23560896, 'steps': 122712, 'loss/train': 1.0791982412338257} 08/31/2021 11:31:45 - INFO - __main__ - Step 122714: {'lr': 4.077760928007848e-05, 'samples': 23561088, 'steps': 122713, 'loss/train': 0.9150395393371582} 08/31/2021 11:31:47 - INFO - __main__ - Step 122715: {'lr': 4.077470456514465e-05, 'samples': 23561280, 'steps': 122714, 'loss/train': 0.7162173390388489} 08/31/2021 11:31:47 - INFO - __main__ - Step 122716: {'lr': 4.077179994448443e-05, 'samples': 23561472, 'steps': 122715, 'loss/train': 1.2114163637161255} 08/31/2021 11:31:48 - INFO - __main__ - Step 122717: {'lr': 4.0768895418099225e-05, 'samples': 23561664, 'steps': 122716, 'loss/train': 0.45098432898521423} 08/31/2021 11:31:48 - INFO - __main__ - Step 122718: {'lr': 4.076599098599032e-05, 'samples': 23561856, 'steps': 122717, 'loss/train': 0.8808156847953796} 08/31/2021 11:31:48 - INFO - __main__ - Step 122719: {'lr': 4.076308664815903e-05, 'samples': 23562048, 'steps': 122718, 'loss/train': 0.5332353115081787} 08/31/2021 11:31:50 - INFO - __main__ - Step 122720: {'lr': 4.076018240460666e-05, 'samples': 23562240, 'steps': 122719, 'loss/train': 0.7981903553009033} 08/31/2021 11:31:50 - INFO - __main__ - Step 122721: {'lr': 4.0757278255334514e-05, 'samples': 23562432, 'steps': 122720, 'loss/train': 0.9042946696281433} 08/31/2021 11:31:51 - INFO - __main__ - Step 122722: {'lr': 4.0754374200343946e-05, 'samples': 23562624, 'steps': 122721, 'loss/train': 0.764197051525116} 08/31/2021 11:31:51 - INFO - __main__ - Step 122723: {'lr': 4.075147023963619e-05, 'samples': 23562816, 'steps': 122722, 'loss/train': 0.8350324630737305} 08/31/2021 11:31:51 - INFO - __main__ - Step 122724: {'lr': 4.0748566373212615e-05, 'samples': 23563008, 'steps': 122723, 'loss/train': 1.8360060453414917} 08/31/2021 11:31:53 - INFO - __main__ - Step 122725: {'lr': 4.074566260107448e-05, 'samples': 23563200, 'steps': 122724, 'loss/train': 1.5090452432632446} 08/31/2021 11:31:53 - INFO - __main__ - Step 122726: {'lr': 4.074275892322316e-05, 'samples': 23563392, 'steps': 122725, 'loss/train': 1.0672721862792969} 08/31/2021 11:31:54 - INFO - __main__ - Step 122727: {'lr': 4.07398553396599e-05, 'samples': 23563584, 'steps': 122726, 'loss/train': 0.9702371954917908} 08/31/2021 11:31:54 - INFO - __main__ - Step 122728: {'lr': 4.073695185038603e-05, 'samples': 23563776, 'steps': 122727, 'loss/train': 1.4762966632843018} 08/31/2021 11:31:54 - INFO - __main__ - Step 122729: {'lr': 4.073404845540293e-05, 'samples': 23563968, 'steps': 122728, 'loss/train': 0.4303450286388397} 08/31/2021 11:31:56 - INFO - __main__ - Step 122730: {'lr': 4.07311451547118e-05, 'samples': 23564160, 'steps': 122729, 'loss/train': 1.76535964012146} 08/31/2021 11:31:57 - INFO - __main__ - Step 122731: {'lr': 4.072824194831396e-05, 'samples': 23564352, 'steps': 122730, 'loss/train': 0.9216500520706177} 08/31/2021 11:31:57 - INFO - __main__ - Step 122732: {'lr': 4.072533883621074e-05, 'samples': 23564544, 'steps': 122731, 'loss/train': 0.8074201941490173} 08/31/2021 11:31:57 - INFO - __main__ - Step 122733: {'lr': 4.072243581840346e-05, 'samples': 23564736, 'steps': 122732, 'loss/train': 0.7535168528556824} 08/31/2021 11:31:58 - INFO - __main__ - Step 122734: {'lr': 4.0719532894893415e-05, 'samples': 23564928, 'steps': 122733, 'loss/train': 1.007973074913025} 08/31/2021 11:31:58 - INFO - __main__ - Step 122735: {'lr': 4.0716630065681934e-05, 'samples': 23565120, 'steps': 122734, 'loss/train': 0.526911199092865} 08/31/2021 11:32:00 - INFO - __main__ - Step 122736: {'lr': 4.0713727330770306e-05, 'samples': 23565312, 'steps': 122735, 'loss/train': 0.9059380292892456} 08/31/2021 11:32:01 - INFO - __main__ - Step 122737: {'lr': 4.0710824690159825e-05, 'samples': 23565504, 'steps': 122736, 'loss/train': 1.0430444478988647} 08/31/2021 11:32:01 - INFO - __main__ - Step 122738: {'lr': 4.0707922143851826e-05, 'samples': 23565696, 'steps': 122737, 'loss/train': 1.253074288368225} 08/31/2021 11:32:01 - INFO - __main__ - Step 122739: {'lr': 4.070501969184762e-05, 'samples': 23565888, 'steps': 122738, 'loss/train': 1.1823225021362305} 08/31/2021 11:32:02 - INFO - __main__ - Step 122740: {'lr': 4.07021173341485e-05, 'samples': 23566080, 'steps': 122739, 'loss/train': 1.2214105129241943} 08/31/2021 11:32:03 - INFO - __main__ - Step 122741: {'lr': 4.069921507075577e-05, 'samples': 23566272, 'steps': 122740, 'loss/train': 0.911761999130249} 08/31/2021 11:32:04 - INFO - __main__ - Step 122742: {'lr': 4.0696312901670806e-05, 'samples': 23566464, 'steps': 122741, 'loss/train': 1.4883822202682495} 08/31/2021 11:32:04 - INFO - __main__ - Step 122743: {'lr': 4.0693410826894786e-05, 'samples': 23566656, 'steps': 122742, 'loss/train': 0.034299176186323166} 08/31/2021 11:32:05 - INFO - __main__ - Step 122744: {'lr': 4.069050884642911e-05, 'samples': 23566848, 'steps': 122743, 'loss/train': 0.8531456589698792} 08/31/2021 11:32:05 - INFO - __main__ - Step 122745: {'lr': 4.068760696027504e-05, 'samples': 23567040, 'steps': 122744, 'loss/train': 1.1638455390930176} 08/31/2021 11:32:06 - INFO - __main__ - Step 122746: {'lr': 4.068470516843389e-05, 'samples': 23567232, 'steps': 122745, 'loss/train': 0.8390300273895264} 08/31/2021 11:32:07 - INFO - __main__ - Step 122747: {'lr': 4.0681803470907e-05, 'samples': 23567424, 'steps': 122746, 'loss/train': 0.5674667954444885} 08/31/2021 11:32:07 - INFO - __main__ - Step 122748: {'lr': 4.0678901867695656e-05, 'samples': 23567616, 'steps': 122747, 'loss/train': 0.9819461703300476} 08/31/2021 11:32:08 - INFO - __main__ - Step 122749: {'lr': 4.067600035880117e-05, 'samples': 23567808, 'steps': 122748, 'loss/train': 0.6394852995872498} 08/31/2021 11:32:08 - INFO - __main__ - Step 122750: {'lr': 4.067309894422486e-05, 'samples': 23568000, 'steps': 122749, 'loss/train': 1.3519020080566406} 08/31/2021 11:32:10 - INFO - __main__ - Step 122751: {'lr': 4.067019762396801e-05, 'samples': 23568192, 'steps': 122750, 'loss/train': 0.9102989435195923} 08/31/2021 11:32:10 - INFO - __main__ - Step 122752: {'lr': 4.0667296398031934e-05, 'samples': 23568384, 'steps': 122751, 'loss/train': 1.261932134628296} 08/31/2021 11:32:11 - INFO - __main__ - Step 122753: {'lr': 4.066439526641797e-05, 'samples': 23568576, 'steps': 122752, 'loss/train': 0.3414790630340576} 08/31/2021 11:32:11 - INFO - __main__ - Step 122754: {'lr': 4.066149422912738e-05, 'samples': 23568768, 'steps': 122753, 'loss/train': 1.2333388328552246} 08/31/2021 11:32:11 - INFO - __main__ - Step 122755: {'lr': 4.065859328616148e-05, 'samples': 23568960, 'steps': 122754, 'loss/train': 1.1564792394638062} 08/31/2021 11:32:12 - INFO - __main__ - Step 122756: {'lr': 4.065569243752165e-05, 'samples': 23569152, 'steps': 122755, 'loss/train': 0.016083089634776115} 08/31/2021 11:32:13 - INFO - __main__ - Step 122757: {'lr': 4.06527916832091e-05, 'samples': 23569344, 'steps': 122756, 'loss/train': 0.38872429728507996} 08/31/2021 11:32:14 - INFO - __main__ - Step 122758: {'lr': 4.0649891023225136e-05, 'samples': 23569536, 'steps': 122757, 'loss/train': 0.17619270086288452} 08/31/2021 11:32:14 - INFO - __main__ - Step 122759: {'lr': 4.064699045757111e-05, 'samples': 23569728, 'steps': 122758, 'loss/train': 1.7276716232299805} 08/31/2021 11:32:14 - INFO - __main__ - Step 122760: {'lr': 4.064408998624833e-05, 'samples': 23569920, 'steps': 122759, 'loss/train': 1.013423204421997} 08/31/2021 11:32:15 - INFO - __main__ - Step 122761: {'lr': 4.064118960925811e-05, 'samples': 23570112, 'steps': 122760, 'loss/train': 0.9043172597885132} 08/31/2021 11:32:16 - INFO - __main__ - Step 122762: {'lr': 4.063828932660171e-05, 'samples': 23570304, 'steps': 122761, 'loss/train': 1.1051589250564575} 08/31/2021 11:32:17 - INFO - __main__ - Step 122763: {'lr': 4.0635389138280464e-05, 'samples': 23570496, 'steps': 122762, 'loss/train': 1.482251763343811} 08/31/2021 11:32:17 - INFO - __main__ - Step 122764: {'lr': 4.06324890442957e-05, 'samples': 23570688, 'steps': 122763, 'loss/train': 1.3968281745910645} 08/31/2021 11:32:17 - INFO - __main__ - Step 122765: {'lr': 4.06295890446487e-05, 'samples': 23570880, 'steps': 122764, 'loss/train': 1.0229722261428833} 08/31/2021 11:32:18 - INFO - __main__ - Step 122766: {'lr': 4.062668913934078e-05, 'samples': 23571072, 'steps': 122765, 'loss/train': 0.8071051239967346} 08/31/2021 11:32:18 - INFO - __main__ - Step 122767: {'lr': 4.062378932837329e-05, 'samples': 23571264, 'steps': 122766, 'loss/train': 1.0640050172805786} 08/31/2021 11:32:20 - INFO - __main__ - Step 122768: {'lr': 4.0620889611747455e-05, 'samples': 23571456, 'steps': 122767, 'loss/train': 1.1508519649505615} 08/31/2021 11:32:20 - INFO - __main__ - Step 122769: {'lr': 4.0617989989464586e-05, 'samples': 23571648, 'steps': 122768, 'loss/train': 1.5959614515304565} 08/31/2021 11:32:20 - INFO - __main__ - Step 122770: {'lr': 4.0615090461526036e-05, 'samples': 23571840, 'steps': 122769, 'loss/train': 1.0075068473815918} 08/31/2021 11:32:21 - INFO - __main__ - Step 122771: {'lr': 4.061219102793309e-05, 'samples': 23572032, 'steps': 122770, 'loss/train': 1.436868667602539} 08/31/2021 11:32:21 - INFO - __main__ - Step 122772: {'lr': 4.060929168868707e-05, 'samples': 23572224, 'steps': 122771, 'loss/train': 1.3943872451782227} 08/31/2021 11:32:23 - INFO - __main__ - Step 122773: {'lr': 4.060639244378925e-05, 'samples': 23572416, 'steps': 122772, 'loss/train': 1.1163126230239868} 08/31/2021 11:32:23 - INFO - __main__ - Step 122774: {'lr': 4.0603493293240976e-05, 'samples': 23572608, 'steps': 122773, 'loss/train': 1.227131724357605} 08/31/2021 11:32:23 - INFO - __main__ - Step 122775: {'lr': 4.060059423704354e-05, 'samples': 23572800, 'steps': 122774, 'loss/train': 1.3761647939682007} 08/31/2021 11:32:24 - INFO - __main__ - Step 122776: {'lr': 4.0597695275198246e-05, 'samples': 23572992, 'steps': 122775, 'loss/train': 1.072956919670105} 08/31/2021 11:32:25 - INFO - __main__ - Step 122777: {'lr': 4.059479640770639e-05, 'samples': 23573184, 'steps': 122776, 'loss/train': 1.4117647409439087} 08/31/2021 11:32:26 - INFO - __main__ - Step 122778: {'lr': 4.059189763456933e-05, 'samples': 23573376, 'steps': 122777, 'loss/train': 1.2616251707077026} 08/31/2021 11:32:26 - INFO - __main__ - Step 122779: {'lr': 4.05889989557883e-05, 'samples': 23573568, 'steps': 122778, 'loss/train': 0.7938685417175293} 08/31/2021 11:32:26 - INFO - __main__ - Step 122780: {'lr': 4.058610037136462e-05, 'samples': 23573760, 'steps': 122779, 'loss/train': 1.0854889154434204} 08/31/2021 11:32:27 - INFO - __main__ - Step 122781: {'lr': 4.05832018812996e-05, 'samples': 23573952, 'steps': 122780, 'loss/train': 1.127251386642456} 08/31/2021 11:32:27 - INFO - __main__ - Step 122782: {'lr': 4.058030348559458e-05, 'samples': 23574144, 'steps': 122781, 'loss/train': 1.1128076314926147} 08/31/2021 11:32:29 - INFO - __main__ - Step 122783: {'lr': 4.057740518425085e-05, 'samples': 23574336, 'steps': 122782, 'loss/train': 1.4786579608917236} 08/31/2021 11:32:29 - INFO - __main__ - Step 122784: {'lr': 4.057450697726969e-05, 'samples': 23574528, 'steps': 122783, 'loss/train': 1.2398570775985718} 08/31/2021 11:32:30 - INFO - __main__ - Step 122785: {'lr': 4.0571608864652444e-05, 'samples': 23574720, 'steps': 122784, 'loss/train': 0.6979792714118958} 08/31/2021 11:32:30 - INFO - __main__ - Step 122786: {'lr': 4.0568710846400374e-05, 'samples': 23574912, 'steps': 122785, 'loss/train': 0.8925969004631042} 08/31/2021 11:32:30 - INFO - __main__ - Step 122787: {'lr': 4.056581292251482e-05, 'samples': 23575104, 'steps': 122786, 'loss/train': 1.2054787874221802} 08/31/2021 11:32:32 - INFO - __main__ - Step 122788: {'lr': 4.056291509299709e-05, 'samples': 23575296, 'steps': 122787, 'loss/train': 1.4324359893798828} 08/31/2021 11:32:33 - INFO - __main__ - Step 122789: {'lr': 4.0560017357848535e-05, 'samples': 23575488, 'steps': 122788, 'loss/train': 1.398798942565918} 08/31/2021 11:32:33 - INFO - __main__ - Step 122790: {'lr': 4.055711971707035e-05, 'samples': 23575680, 'steps': 122789, 'loss/train': 1.4509506225585938} 08/31/2021 11:32:34 - INFO - __main__ - Step 122791: {'lr': 4.055422217066388e-05, 'samples': 23575872, 'steps': 122790, 'loss/train': 0.6328518390655518} 08/31/2021 11:32:34 - INFO - __main__ - Step 122792: {'lr': 4.0551324718630435e-05, 'samples': 23576064, 'steps': 122791, 'loss/train': 1.5114637613296509} 08/31/2021 11:32:36 - INFO - __main__ - Step 122793: {'lr': 4.0548427360971364e-05, 'samples': 23576256, 'steps': 122792, 'loss/train': 1.2038449048995972} 08/31/2021 11:32:36 - INFO - __main__ - Step 122794: {'lr': 4.054553009768791e-05, 'samples': 23576448, 'steps': 122793, 'loss/train': 0.05828596279025078} 08/31/2021 11:32:37 - INFO - __main__ - Step 122795: {'lr': 4.054263292878144e-05, 'samples': 23576640, 'steps': 122794, 'loss/train': 0.03280530497431755} 08/31/2021 11:32:37 - INFO - __main__ - Step 122796: {'lr': 4.053973585425319e-05, 'samples': 23576832, 'steps': 122795, 'loss/train': 1.2634180784225464} 08/31/2021 11:32:37 - INFO - __main__ - Step 122797: {'lr': 4.053683887410453e-05, 'samples': 23577024, 'steps': 122796, 'loss/train': 0.7672149538993835} 08/31/2021 11:32:38 - INFO - __main__ - Step 122798: {'lr': 4.053394198833674e-05, 'samples': 23577216, 'steps': 122797, 'loss/train': 0.025875026360154152} 08/31/2021 11:32:39 - INFO - __main__ - Step 122799: {'lr': 4.053104519695111e-05, 'samples': 23577408, 'steps': 122798, 'loss/train': 0.43953752517700195} 08/31/2021 11:32:39 - INFO - __main__ - Step 122800: {'lr': 4.0528148499949014e-05, 'samples': 23577600, 'steps': 122799, 'loss/train': 1.133579969406128} 08/31/2021 11:32:40 - INFO - __main__ - Step 122801: {'lr': 4.0525251897331663e-05, 'samples': 23577792, 'steps': 122800, 'loss/train': 1.3327564001083374} 08/31/2021 11:32:40 - INFO - __main__ - Step 122802: {'lr': 4.0522355389100373e-05, 'samples': 23577984, 'steps': 122801, 'loss/train': 1.01713228225708} 08/31/2021 11:32:41 - INFO - __main__ - Step 122803: {'lr': 4.05194589752565e-05, 'samples': 23578176, 'steps': 122802, 'loss/train': 1.081519603729248} 08/31/2021 11:32:42 - INFO - __main__ - Step 122804: {'lr': 4.051656265580131e-05, 'samples': 23578368, 'steps': 122803, 'loss/train': 0.5151592493057251} 08/31/2021 11:32:42 - INFO - __main__ - Step 122805: {'lr': 4.051366643073615e-05, 'samples': 23578560, 'steps': 122804, 'loss/train': 1.1615217924118042} 08/31/2021 11:32:43 - INFO - __main__ - Step 122806: {'lr': 4.0510770300062285e-05, 'samples': 23578752, 'steps': 122805, 'loss/train': 0.8901481032371521} 08/31/2021 11:32:43 - INFO - __main__ - Step 122807: {'lr': 4.050787426378102e-05, 'samples': 23578944, 'steps': 122806, 'loss/train': 1.1919002532958984} 08/31/2021 11:32:43 - INFO - __main__ - Step 122808: {'lr': 4.0504978321893675e-05, 'samples': 23579136, 'steps': 122807, 'loss/train': 1.625404953956604} 08/31/2021 11:32:45 - INFO - __main__ - Step 122809: {'lr': 4.050208247440157e-05, 'samples': 23579328, 'steps': 122808, 'loss/train': 1.2731075286865234} 08/31/2021 11:32:46 - INFO - __main__ - Step 122810: {'lr': 4.049918672130598e-05, 'samples': 23579520, 'steps': 122809, 'loss/train': 0.5945074558258057} 08/31/2021 11:32:46 - INFO - __main__ - Step 122811: {'lr': 4.04962910626083e-05, 'samples': 23579712, 'steps': 122810, 'loss/train': 0.913507342338562} 08/31/2021 11:32:46 - INFO - __main__ - Step 122812: {'lr': 4.049339549830969e-05, 'samples': 23579904, 'steps': 122811, 'loss/train': 0.03876958414912224} 08/31/2021 11:32:47 - INFO - __main__ - Step 122813: {'lr': 4.049050002841154e-05, 'samples': 23580096, 'steps': 122812, 'loss/train': 0.6647813320159912} 08/31/2021 11:32:48 - INFO - __main__ - Step 122814: {'lr': 4.048760465291512e-05, 'samples': 23580288, 'steps': 122813, 'loss/train': 0.028943892568349838} 08/31/2021 11:32:49 - INFO - __main__ - Step 122815: {'lr': 4.048470937182175e-05, 'samples': 23580480, 'steps': 122814, 'loss/train': 0.13975612819194794} 08/31/2021 11:32:49 - INFO - __main__ - Step 122816: {'lr': 4.0481814185132746e-05, 'samples': 23580672, 'steps': 122815, 'loss/train': 0.8299097418785095} 08/31/2021 11:32:50 - INFO - __main__ - Step 122817: {'lr': 4.0478919092849395e-05, 'samples': 23580864, 'steps': 122816, 'loss/train': 1.6339040994644165} 08/31/2021 11:32:50 - INFO - __main__ - Step 122818: {'lr': 4.0476024094973e-05, 'samples': 23581056, 'steps': 122817, 'loss/train': 1.4748971462249756} 08/31/2021 11:32:51 - INFO - __main__ - Step 122819: {'lr': 4.047312919150489e-05, 'samples': 23581248, 'steps': 122818, 'loss/train': 1.4681037664413452} 08/31/2021 11:32:52 - INFO - __main__ - Step 122820: {'lr': 4.047023438244638e-05, 'samples': 23581440, 'steps': 122819, 'loss/train': 0.8858073353767395} 08/31/2021 11:32:52 - INFO - __main__ - Step 122821: {'lr': 4.04673396677987e-05, 'samples': 23581632, 'steps': 122820, 'loss/train': 1.2671245336532593} 08/31/2021 11:32:53 - INFO - __main__ - Step 122822: {'lr': 4.0464445047563246e-05, 'samples': 23581824, 'steps': 122821, 'loss/train': 0.5745540261268616} 08/31/2021 11:32:53 - INFO - __main__ - Step 122823: {'lr': 4.04615505217413e-05, 'samples': 23582016, 'steps': 122822, 'loss/train': 1.395704984664917} 08/31/2021 11:32:53 - INFO - __main__ - Step 122824: {'lr': 4.045865609033411e-05, 'samples': 23582208, 'steps': 122823, 'loss/train': 2.8675694465637207} 08/31/2021 11:32:55 - INFO - __main__ - Step 122825: {'lr': 4.0455761753343005e-05, 'samples': 23582400, 'steps': 122824, 'loss/train': 0.6716681122779846} 08/31/2021 11:32:55 - INFO - __main__ - Step 122826: {'lr': 4.045286751076932e-05, 'samples': 23582592, 'steps': 122825, 'loss/train': 0.6509835720062256} 08/31/2021 11:32:56 - INFO - __main__ - Step 122827: {'lr': 4.044997336261433e-05, 'samples': 23582784, 'steps': 122826, 'loss/train': 0.8558911681175232} 08/31/2021 11:32:56 - INFO - __main__ - Step 122828: {'lr': 4.0447079308879336e-05, 'samples': 23582976, 'steps': 122827, 'loss/train': 0.9343080520629883} 08/31/2021 11:32:56 - INFO - __main__ - Step 122829: {'lr': 4.044418534956567e-05, 'samples': 23583168, 'steps': 122828, 'loss/train': 1.037222146987915} 08/31/2021 11:32:58 - INFO - __main__ - Step 122830: {'lr': 4.044129148467463e-05, 'samples': 23583360, 'steps': 122829, 'loss/train': 0.9901582598686218} 08/31/2021 11:32:58 - INFO - __main__ - Step 122831: {'lr': 4.043839771420749e-05, 'samples': 23583552, 'steps': 122830, 'loss/train': 0.6383596062660217} 08/31/2021 11:32:59 - INFO - __main__ - Step 122832: {'lr': 4.0435504038165563e-05, 'samples': 23583744, 'steps': 122831, 'loss/train': 0.6281910538673401} 08/31/2021 11:32:59 - INFO - __main__ - Step 122833: {'lr': 4.043261045655019e-05, 'samples': 23583936, 'steps': 122832, 'loss/train': 1.0085443258285522} 08/31/2021 11:32:59 - INFO - __main__ - Step 122834: {'lr': 4.0429716969362625e-05, 'samples': 23584128, 'steps': 122833, 'loss/train': 0.9580047726631165} 08/31/2021 11:33:00 - INFO - __main__ - Step 122835: {'lr': 4.042682357660421e-05, 'samples': 23584320, 'steps': 122834, 'loss/train': 1.011670470237732} 08/31/2021 11:33:01 - INFO - __main__ - Step 122836: {'lr': 4.042393027827632e-05, 'samples': 23584512, 'steps': 122835, 'loss/train': 1.0804818868637085} 08/31/2021 11:33:02 - INFO - __main__ - Step 122837: {'lr': 4.0421037074380077e-05, 'samples': 23584704, 'steps': 122836, 'loss/train': 0.8031063675880432} 08/31/2021 11:33:02 - INFO - __main__ - Step 122838: {'lr': 4.041814396491689e-05, 'samples': 23584896, 'steps': 122837, 'loss/train': 0.6404058337211609} 08/31/2021 11:33:02 - INFO - __main__ - Step 122839: {'lr': 4.0415250949888045e-05, 'samples': 23585088, 'steps': 122838, 'loss/train': 0.9662023782730103} 08/31/2021 11:33:03 - INFO - __main__ - Step 122840: {'lr': 4.0412358029294856e-05, 'samples': 23585280, 'steps': 122839, 'loss/train': 0.41530194878578186} 08/31/2021 11:33:04 - INFO - __main__ - Step 122841: {'lr': 4.040946520313865e-05, 'samples': 23585472, 'steps': 122840, 'loss/train': 0.858495831489563} 08/31/2021 11:33:05 - INFO - __main__ - Step 122842: {'lr': 4.040657247142068e-05, 'samples': 23585664, 'steps': 122841, 'loss/train': 0.9732750654220581} 08/31/2021 11:33:05 - INFO - __main__ - Step 122843: {'lr': 4.040367983414228e-05, 'samples': 23585856, 'steps': 122842, 'loss/train': 1.1609294414520264} 08/31/2021 11:33:05 - INFO - __main__ - Step 122844: {'lr': 4.040078729130475e-05, 'samples': 23586048, 'steps': 122843, 'loss/train': 1.0596524477005005} 08/31/2021 11:33:06 - INFO - __main__ - Step 122845: {'lr': 4.039789484290937e-05, 'samples': 23586240, 'steps': 122844, 'loss/train': 0.7399686574935913} 08/31/2021 11:33:08 - INFO - __main__ - Step 122846: {'lr': 4.03950024889575e-05, 'samples': 23586432, 'steps': 122845, 'loss/train': 0.6406243443489075} 08/31/2021 11:33:08 - INFO - __main__ - Step 122847: {'lr': 4.0392110229450387e-05, 'samples': 23586624, 'steps': 122846, 'loss/train': 1.3432117700576782} 08/31/2021 11:33:09 - INFO - __main__ - Step 122848: {'lr': 4.038921806438936e-05, 'samples': 23586816, 'steps': 122847, 'loss/train': 1.6328779458999634} 08/31/2021 11:33:09 - INFO - __main__ - Step 122849: {'lr': 4.0386325993775705e-05, 'samples': 23587008, 'steps': 122848, 'loss/train': 0.8839687705039978} 08/31/2021 11:33:09 - INFO - __main__ - Step 122850: {'lr': 4.038343401761083e-05, 'samples': 23587200, 'steps': 122849, 'loss/train': 1.0502976179122925} 08/31/2021 11:33:11 - INFO - __main__ - Step 122851: {'lr': 4.0380542135895844e-05, 'samples': 23587392, 'steps': 122850, 'loss/train': 0.6579582691192627} 08/31/2021 11:33:11 - INFO - __main__ - Step 122852: {'lr': 4.037765034863217e-05, 'samples': 23587584, 'steps': 122851, 'loss/train': 1.2790738344192505} 08/31/2021 11:33:12 - INFO - __main__ - Step 122853: {'lr': 4.0374758655821104e-05, 'samples': 23587776, 'steps': 122852, 'loss/train': 0.5892527103424072} 08/31/2021 11:33:12 - INFO - __main__ - Step 122854: {'lr': 4.03718670574639e-05, 'samples': 23587968, 'steps': 122853, 'loss/train': 0.21877388656139374} 08/31/2021 11:33:12 - INFO - __main__ - Step 122855: {'lr': 4.036897555356195e-05, 'samples': 23588160, 'steps': 122854, 'loss/train': 0.885945737361908} 08/31/2021 11:33:14 - INFO - __main__ - Step 122856: {'lr': 4.0366084144116465e-05, 'samples': 23588352, 'steps': 122855, 'loss/train': 0.9498888254165649} 08/31/2021 11:33:14 - INFO - __main__ - Step 122857: {'lr': 4.036319282912878e-05, 'samples': 23588544, 'steps': 122856, 'loss/train': 0.9429555535316467} 08/31/2021 11:33:15 - INFO - __main__ - Step 122858: {'lr': 4.0360301608600244e-05, 'samples': 23588736, 'steps': 122857, 'loss/train': 0.7992327809333801} 08/31/2021 11:33:15 - INFO - __main__ - Step 122859: {'lr': 4.035741048253211e-05, 'samples': 23588928, 'steps': 122858, 'loss/train': 0.6900730729103088} 08/31/2021 11:33:15 - INFO - __main__ - Step 122860: {'lr': 4.035451945092567e-05, 'samples': 23589120, 'steps': 122859, 'loss/train': 1.1338517665863037} 08/31/2021 11:33:17 - INFO - __main__ - Step 122861: {'lr': 4.0351628513782266e-05, 'samples': 23589312, 'steps': 122860, 'loss/train': 1.4162648916244507} 08/31/2021 11:33:18 - INFO - __main__ - Step 122862: {'lr': 4.034873767110317e-05, 'samples': 23589504, 'steps': 122861, 'loss/train': 0.9101648926734924} 08/31/2021 11:33:18 - INFO - __main__ - Step 122863: {'lr': 4.0345846922889784e-05, 'samples': 23589696, 'steps': 122862, 'loss/train': 0.9833760857582092} 08/31/2021 11:33:18 - INFO - __main__ - Step 122864: {'lr': 4.034295626914325e-05, 'samples': 23589888, 'steps': 122863, 'loss/train': 0.5929062962532043} 08/31/2021 11:33:19 - INFO - __main__ - Step 122865: {'lr': 4.034006570986493e-05, 'samples': 23590080, 'steps': 122864, 'loss/train': 0.33681049942970276} 08/31/2021 11:33:19 - INFO - __main__ - Step 122866: {'lr': 4.033717524505615e-05, 'samples': 23590272, 'steps': 122865, 'loss/train': 1.3147430419921875} 08/31/2021 11:33:21 - INFO - __main__ - Step 122867: {'lr': 4.033428487471821e-05, 'samples': 23590464, 'steps': 122866, 'loss/train': 1.8280483484268188} 08/31/2021 11:33:21 - INFO - __main__ - Step 122868: {'lr': 4.0331394598852404e-05, 'samples': 23590656, 'steps': 122867, 'loss/train': 1.0213239192962646} 08/31/2021 11:33:22 - INFO - __main__ - Step 122869: {'lr': 4.032850441746003e-05, 'samples': 23590848, 'steps': 122868, 'loss/train': 0.11807031184434891} 08/31/2021 11:33:22 - INFO - __main__ - Step 122870: {'lr': 4.032561433054241e-05, 'samples': 23591040, 'steps': 122869, 'loss/train': 1.2961535453796387} 08/31/2021 11:33:22 - INFO - __main__ - Step 122871: {'lr': 4.032272433810083e-05, 'samples': 23591232, 'steps': 122870, 'loss/train': 1.539045810699463} 08/31/2021 11:33:24 - INFO - __main__ - Step 122872: {'lr': 4.0319834440136594e-05, 'samples': 23591424, 'steps': 122871, 'loss/train': 0.34942537546157837} 08/31/2021 11:33:24 - INFO - __main__ - Step 122873: {'lr': 4.0316944636651004e-05, 'samples': 23591616, 'steps': 122872, 'loss/train': 0.9067744612693787} 08/31/2021 11:33:25 - INFO - __main__ - Step 122874: {'lr': 4.031405492764534e-05, 'samples': 23591808, 'steps': 122873, 'loss/train': 0.6440967917442322} 08/31/2021 11:33:25 - INFO - __main__ - Step 122875: {'lr': 4.0311165313120954e-05, 'samples': 23592000, 'steps': 122874, 'loss/train': 0.043052319437265396} 08/31/2021 11:33:26 - INFO - __main__ - Step 122876: {'lr': 4.030827579307911e-05, 'samples': 23592192, 'steps': 122875, 'loss/train': 0.602845311164856} 08/31/2021 11:33:27 - INFO - __main__ - Step 122877: {'lr': 4.030538636752118e-05, 'samples': 23592384, 'steps': 122876, 'loss/train': 1.4264277219772339} 08/31/2021 11:33:28 - INFO - __main__ - Step 122878: {'lr': 4.0302497036448364e-05, 'samples': 23592576, 'steps': 122877, 'loss/train': 1.0906697511672974} 08/31/2021 11:33:28 - INFO - __main__ - Step 122879: {'lr': 4.0299607799861996e-05, 'samples': 23592768, 'steps': 122878, 'loss/train': 0.8013797998428345} 08/31/2021 11:33:29 - INFO - __main__ - Step 122880: {'lr': 4.029671865776338e-05, 'samples': 23592960, 'steps': 122879, 'loss/train': 0.014366033487021923} 08/31/2021 11:33:29 - INFO - __main__ - Step 122881: {'lr': 4.029382961015385e-05, 'samples': 23593152, 'steps': 122880, 'loss/train': 0.709466278553009} 08/31/2021 11:33:29 - INFO - __main__ - Step 122882: {'lr': 4.029094065703465e-05, 'samples': 23593344, 'steps': 122881, 'loss/train': 0.45006054639816284} 08/31/2021 11:33:31 - INFO - __main__ - Step 122883: {'lr': 4.028805179840714e-05, 'samples': 23593536, 'steps': 122882, 'loss/train': 1.3835959434509277} 08/31/2021 11:33:31 - INFO - __main__ - Step 122884: {'lr': 4.02851630342726e-05, 'samples': 23593728, 'steps': 122883, 'loss/train': 1.2402424812316895} 08/31/2021 11:33:32 - INFO - __main__ - Step 122885: {'lr': 4.02822743646323e-05, 'samples': 23593920, 'steps': 122884, 'loss/train': 1.425658106803894} 08/31/2021 11:33:32 - INFO - __main__ - Step 122886: {'lr': 4.0279385789487614e-05, 'samples': 23594112, 'steps': 122885, 'loss/train': 0.785254955291748} 08/31/2021 11:33:32 - INFO - __main__ - Step 122887: {'lr': 4.0276497308839785e-05, 'samples': 23594304, 'steps': 122886, 'loss/train': 1.4619088172912598} 08/31/2021 11:33:34 - INFO - __main__ - Step 122888: {'lr': 4.027360892269011e-05, 'samples': 23594496, 'steps': 122887, 'loss/train': 0.9300248622894287} 08/31/2021 11:33:34 - INFO - __main__ - Step 122889: {'lr': 4.027072063103993e-05, 'samples': 23594688, 'steps': 122888, 'loss/train': 1.4604849815368652} 08/31/2021 11:33:35 - INFO - __main__ - Step 122890: {'lr': 4.0267832433890596e-05, 'samples': 23594880, 'steps': 122889, 'loss/train': 1.161489486694336} 08/31/2021 11:33:35 - INFO - __main__ - Step 122891: {'lr': 4.0264944331243254e-05, 'samples': 23595072, 'steps': 122890, 'loss/train': 1.390660285949707} 08/31/2021 11:33:35 - INFO - __main__ - Step 122892: {'lr': 4.026205632309932e-05, 'samples': 23595264, 'steps': 122891, 'loss/train': 1.2834844589233398} 08/31/2021 11:33:37 - INFO - __main__ - Step 122893: {'lr': 4.025916840946003e-05, 'samples': 23595456, 'steps': 122892, 'loss/train': 0.8374282717704773} 08/31/2021 11:33:37 - INFO - __main__ - Step 122894: {'lr': 4.0256280590326766e-05, 'samples': 23595648, 'steps': 122893, 'loss/train': 1.2355695962905884} 08/31/2021 11:33:38 - INFO - __main__ - Step 122895: {'lr': 4.025339286570076e-05, 'samples': 23595840, 'steps': 122894, 'loss/train': 1.1366604566574097} 08/31/2021 11:33:38 - INFO - __main__ - Step 122896: {'lr': 4.0250505235583326e-05, 'samples': 23596032, 'steps': 122895, 'loss/train': 1.0419672727584839} 08/31/2021 11:33:38 - INFO - __main__ - Step 122897: {'lr': 4.024761769997579e-05, 'samples': 23596224, 'steps': 122896, 'loss/train': 0.7746700048446655} 08/31/2021 11:33:39 - INFO - __main__ - Step 122898: {'lr': 4.024473025887945e-05, 'samples': 23596416, 'steps': 122897, 'loss/train': 0.6678078770637512} 08/31/2021 11:33:41 - INFO - __main__ - Step 122899: {'lr': 4.02418429122956e-05, 'samples': 23596608, 'steps': 122898, 'loss/train': 0.7209230661392212} 08/31/2021 11:33:42 - INFO - __main__ - Step 122900: {'lr': 4.023895566022553e-05, 'samples': 23596800, 'steps': 122899, 'loss/train': 0.8985855579376221} 08/31/2021 11:33:42 - INFO - __main__ - Step 122901: {'lr': 4.0236068502670556e-05, 'samples': 23596992, 'steps': 122900, 'loss/train': 1.2416263818740845} 08/31/2021 11:33:42 - INFO - __main__ - Step 122902: {'lr': 4.023318143963195e-05, 'samples': 23597184, 'steps': 122901, 'loss/train': 0.6515142917633057} 08/31/2021 11:33:43 - INFO - __main__ - Step 122903: {'lr': 4.023029447111107e-05, 'samples': 23597376, 'steps': 122902, 'loss/train': 1.4215844869613647} 08/31/2021 11:33:44 - INFO - __main__ - Step 122904: {'lr': 4.0227407597109215e-05, 'samples': 23597568, 'steps': 122903, 'loss/train': 1.2373608350753784} 08/31/2021 11:33:45 - INFO - __main__ - Step 122905: {'lr': 4.022452081762762e-05, 'samples': 23597760, 'steps': 122904, 'loss/train': 1.1968656778335571} 08/31/2021 11:33:45 - INFO - __main__ - Step 122906: {'lr': 4.022163413266758e-05, 'samples': 23597952, 'steps': 122905, 'loss/train': 0.6472622752189636} 08/31/2021 11:33:45 - INFO - __main__ - Step 122907: {'lr': 4.0218747542230456e-05, 'samples': 23598144, 'steps': 122906, 'loss/train': 0.34141382575035095} 08/31/2021 11:33:46 - INFO - __main__ - Step 122908: {'lr': 4.0215861046317526e-05, 'samples': 23598336, 'steps': 122907, 'loss/train': 1.1801419258117676} 08/31/2021 11:33:46 - INFO - __main__ - Step 122909: {'lr': 4.021297464493009e-05, 'samples': 23598528, 'steps': 122908, 'loss/train': 0.5010433197021484} 08/31/2021 11:33:48 - INFO - __main__ - Step 122910: {'lr': 4.021008833806947e-05, 'samples': 23598720, 'steps': 122909, 'loss/train': 1.1072163581848145} 08/31/2021 11:33:48 - INFO - __main__ - Step 122911: {'lr': 4.020720212573692e-05, 'samples': 23598912, 'steps': 122910, 'loss/train': 0.9591001272201538} 08/31/2021 11:33:49 - INFO - __main__ - Step 122912: {'lr': 4.0204316007933786e-05, 'samples': 23599104, 'steps': 122911, 'loss/train': 1.5123628377914429} 08/31/2021 11:33:49 - INFO - __main__ - Step 122913: {'lr': 4.020142998466134e-05, 'samples': 23599296, 'steps': 122912, 'loss/train': 1.4683904647827148} 08/31/2021 11:33:49 - INFO - __main__ - Step 122914: {'lr': 4.019854405592091e-05, 'samples': 23599488, 'steps': 122913, 'loss/train': 1.1703697443008423} 08/31/2021 11:33:51 - INFO - __main__ - Step 122915: {'lr': 4.019565822171376e-05, 'samples': 23599680, 'steps': 122914, 'loss/train': 1.353190302848816} 08/31/2021 11:33:51 - INFO - __main__ - Step 122916: {'lr': 4.01927724820412e-05, 'samples': 23599872, 'steps': 122915, 'loss/train': 1.1784982681274414} 08/31/2021 11:33:52 - INFO - __main__ - Step 122917: {'lr': 4.018988683690461e-05, 'samples': 23600064, 'steps': 122916, 'loss/train': 1.474307894706726} 08/31/2021 11:33:52 - INFO - __main__ - Step 122918: {'lr': 4.0187001286305176e-05, 'samples': 23600256, 'steps': 122917, 'loss/train': 1.287466049194336} 08/31/2021 11:33:52 - INFO - __main__ - Step 122919: {'lr': 4.018411583024423e-05, 'samples': 23600448, 'steps': 122918, 'loss/train': 1.1342583894729614} 08/31/2021 11:33:54 - INFO - __main__ - Step 122920: {'lr': 4.018123046872307e-05, 'samples': 23600640, 'steps': 122919, 'loss/train': 0.6826398372650146} 08/31/2021 11:33:54 - INFO - __main__ - Step 122921: {'lr': 4.017834520174302e-05, 'samples': 23600832, 'steps': 122920, 'loss/train': 1.378136157989502} 08/31/2021 11:33:54 - INFO - __main__ - Step 122922: {'lr': 4.017546002930536e-05, 'samples': 23601024, 'steps': 122921, 'loss/train': 0.18124571442604065} 08/31/2021 11:33:55 - INFO - __main__ - Step 122923: {'lr': 4.017257495141141e-05, 'samples': 23601216, 'steps': 122922, 'loss/train': 1.497890591621399} 08/31/2021 11:33:55 - INFO - __main__ - Step 122924: {'lr': 4.0169689968062476e-05, 'samples': 23601408, 'steps': 122923, 'loss/train': 1.0793273448944092} 08/31/2021 11:33:57 - INFO - __main__ - Step 122925: {'lr': 4.0166805079259824e-05, 'samples': 23601600, 'steps': 122924, 'loss/train': 1.9369728565216064} 08/31/2021 11:33:57 - INFO - __main__ - Step 122926: {'lr': 4.0163920285004765e-05, 'samples': 23601792, 'steps': 122925, 'loss/train': 0.47554469108581543} 08/31/2021 11:33:57 - INFO - __main__ - Step 122927: {'lr': 4.016103558529863e-05, 'samples': 23601984, 'steps': 122926, 'loss/train': 0.7410690188407898} 08/31/2021 11:33:58 - INFO - __main__ - Step 122928: {'lr': 4.0158150980142665e-05, 'samples': 23602176, 'steps': 122927, 'loss/train': 1.2896134853363037} 08/31/2021 11:33:58 - INFO - __main__ - Step 122929: {'lr': 4.015526646953821e-05, 'samples': 23602368, 'steps': 122928, 'loss/train': 1.4532045125961304} 08/31/2021 11:34:00 - INFO - __main__ - Step 122930: {'lr': 4.0152382053486617e-05, 'samples': 23602560, 'steps': 122929, 'loss/train': 1.3134040832519531} 08/31/2021 11:34:00 - INFO - __main__ - Step 122931: {'lr': 4.014949773198906e-05, 'samples': 23602752, 'steps': 122930, 'loss/train': 1.1575864553451538} 08/31/2021 11:34:00 - INFO - __main__ - Step 122932: {'lr': 4.014661350504692e-05, 'samples': 23602944, 'steps': 122931, 'loss/train': 0.8018220067024231} 08/31/2021 11:34:01 - INFO - __main__ - Step 122933: {'lr': 4.014372937266145e-05, 'samples': 23603136, 'steps': 122932, 'loss/train': 1.537589192390442} 08/31/2021 11:34:01 - INFO - __main__ - Step 122934: {'lr': 4.0140845334834005e-05, 'samples': 23603328, 'steps': 122933, 'loss/train': 1.0970489978790283} 08/31/2021 11:34:03 - INFO - __main__ - Step 122935: {'lr': 4.0137961391565836e-05, 'samples': 23603520, 'steps': 122934, 'loss/train': 0.37591788172721863} 08/31/2021 11:34:03 - INFO - __main__ - Step 122936: {'lr': 4.013507754285825e-05, 'samples': 23603712, 'steps': 122935, 'loss/train': 0.903176486492157} 08/31/2021 11:34:03 - INFO - __main__ - Step 122937: {'lr': 4.013219378871258e-05, 'samples': 23603904, 'steps': 122936, 'loss/train': 1.2814921140670776} 08/31/2021 11:34:04 - INFO - __main__ - Step 122938: {'lr': 4.0129310129130094e-05, 'samples': 23604096, 'steps': 122937, 'loss/train': 1.8031885623931885} 08/31/2021 11:34:04 - INFO - __main__ - Step 122939: {'lr': 4.012642656411211e-05, 'samples': 23604288, 'steps': 122938, 'loss/train': 0.6794557571411133} 08/31/2021 11:34:06 - INFO - __main__ - Step 122940: {'lr': 4.012354309365992e-05, 'samples': 23604480, 'steps': 122939, 'loss/train': 0.8821121454238892} 08/31/2021 11:34:06 - INFO - __main__ - Step 122941: {'lr': 4.0120659717774843e-05, 'samples': 23604672, 'steps': 122940, 'loss/train': 0.9296685457229614} 08/31/2021 11:34:07 - INFO - __main__ - Step 122942: {'lr': 4.011777643645811e-05, 'samples': 23604864, 'steps': 122941, 'loss/train': 1.7539081573486328} 08/31/2021 11:34:07 - INFO - __main__ - Step 122943: {'lr': 4.0114893249711125e-05, 'samples': 23605056, 'steps': 122942, 'loss/train': 1.1415739059448242} 08/31/2021 11:34:07 - INFO - __main__ - Step 122944: {'lr': 4.011201015753516e-05, 'samples': 23605248, 'steps': 122943, 'loss/train': 0.8366255164146423} 08/31/2021 11:34:08 - INFO - __main__ - Step 122945: {'lr': 4.010912715993143e-05, 'samples': 23605440, 'steps': 122944, 'loss/train': 1.383746862411499} 08/31/2021 11:34:09 - INFO - __main__ - Step 122946: {'lr': 4.0106244256901264e-05, 'samples': 23605632, 'steps': 122945, 'loss/train': 1.142637014389038} 08/31/2021 11:34:10 - INFO - __main__ - Step 122947: {'lr': 4.010336144844601e-05, 'samples': 23605824, 'steps': 122946, 'loss/train': 1.2626243829727173} 08/31/2021 11:34:10 - INFO - __main__ - Step 122948: {'lr': 4.010047873456693e-05, 'samples': 23606016, 'steps': 122947, 'loss/train': 0.6284393668174744} 08/31/2021 11:34:10 - INFO - __main__ - Step 122949: {'lr': 4.009759611526534e-05, 'samples': 23606208, 'steps': 122948, 'loss/train': 1.1313815116882324} 08/31/2021 11:34:11 - INFO - __main__ - Step 122950: {'lr': 4.009471359054254e-05, 'samples': 23606400, 'steps': 122949, 'loss/train': 0.905907154083252} 08/31/2021 11:34:12 - INFO - __main__ - Step 122951: {'lr': 4.009183116039983e-05, 'samples': 23606592, 'steps': 122950, 'loss/train': 0.8452146053314209} 08/31/2021 11:34:13 - INFO - __main__ - Step 122952: {'lr': 4.008894882483849e-05, 'samples': 23606784, 'steps': 122951, 'loss/train': 1.2659237384796143} 08/31/2021 11:34:13 - INFO - __main__ - Step 122953: {'lr': 4.008606658385983e-05, 'samples': 23606976, 'steps': 122952, 'loss/train': 1.1031726598739624} 08/31/2021 11:34:14 - INFO - __main__ - Step 122954: {'lr': 4.008318443746517e-05, 'samples': 23607168, 'steps': 122953, 'loss/train': 1.1308602094650269} 08/31/2021 11:34:14 - INFO - __main__ - Step 122955: {'lr': 4.008030238565577e-05, 'samples': 23607360, 'steps': 122954, 'loss/train': 0.5181409120559692} 08/31/2021 11:34:16 - INFO - __main__ - Step 122956: {'lr': 4.007742042843293e-05, 'samples': 23607552, 'steps': 122955, 'loss/train': 0.024829430505633354} 08/31/2021 11:34:17 - INFO - __main__ - Step 122957: {'lr': 4.007453856579804e-05, 'samples': 23607744, 'steps': 122956, 'loss/train': 1.4707621335983276} 08/31/2021 11:34:17 - INFO - __main__ - Step 122958: {'lr': 4.007165679775226e-05, 'samples': 23607936, 'steps': 122957, 'loss/train': 1.0841408967971802} 08/31/2021 11:34:17 - INFO - __main__ - Step 122959: {'lr': 4.0068775124296965e-05, 'samples': 23608128, 'steps': 122958, 'loss/train': 0.9322420954704285} 08/31/2021 11:34:18 - INFO - __main__ - Step 122960: {'lr': 4.006589354543344e-05, 'samples': 23608320, 'steps': 122959, 'loss/train': 1.6760526895523071} 08/31/2021 11:34:20 - INFO - __main__ - Step 122961: {'lr': 4.0063012061162974e-05, 'samples': 23608512, 'steps': 122960, 'loss/train': 1.2624698877334595} 08/31/2021 11:34:20 - INFO - __main__ - Step 122962: {'lr': 4.006013067148687e-05, 'samples': 23608704, 'steps': 122961, 'loss/train': 1.448079228401184} 08/31/2021 11:34:21 - INFO - __main__ - Step 122963: {'lr': 4.005724937640645e-05, 'samples': 23608896, 'steps': 122962, 'loss/train': 0.8321751356124878} 08/31/2021 11:34:21 - INFO - __main__ - Step 122964: {'lr': 4.0054368175922976e-05, 'samples': 23609088, 'steps': 122963, 'loss/train': 1.6672381162643433} 08/31/2021 11:34:21 - INFO - __main__ - Step 122965: {'lr': 4.005148707003778e-05, 'samples': 23609280, 'steps': 122964, 'loss/train': 1.622963547706604} 08/31/2021 11:34:22 - INFO - __main__ - Step 122966: {'lr': 4.004860605875213e-05, 'samples': 23609472, 'steps': 122965, 'loss/train': 0.8219602108001709} 08/31/2021 11:34:23 - INFO - __main__ - Step 122967: {'lr': 4.004572514206734e-05, 'samples': 23609664, 'steps': 122966, 'loss/train': 0.06450296193361282} 08/31/2021 11:34:24 - INFO - __main__ - Step 122968: {'lr': 4.004284431998473e-05, 'samples': 23609856, 'steps': 122967, 'loss/train': 0.9142343997955322} 08/31/2021 11:34:24 - INFO - __main__ - Step 122969: {'lr': 4.003996359250553e-05, 'samples': 23610048, 'steps': 122968, 'loss/train': 0.9543070197105408} 08/31/2021 11:34:24 - INFO - __main__ - Step 122970: {'lr': 4.0037082959631125e-05, 'samples': 23610240, 'steps': 122969, 'loss/train': 1.6179198026657104} 08/31/2021 11:34:25 - INFO - __main__ - Step 122971: {'lr': 4.0034202421362797e-05, 'samples': 23610432, 'steps': 122970, 'loss/train': 1.1789660453796387} 08/31/2021 11:34:26 - INFO - __main__ - Step 122972: {'lr': 4.003132197770179e-05, 'samples': 23610624, 'steps': 122971, 'loss/train': 1.1657078266143799} 08/31/2021 11:34:27 - INFO - __main__ - Step 122973: {'lr': 4.002844162864941e-05, 'samples': 23610816, 'steps': 122972, 'loss/train': 0.9805340766906738} 08/31/2021 11:34:27 - INFO - __main__ - Step 122974: {'lr': 4.002556137420696e-05, 'samples': 23611008, 'steps': 122973, 'loss/train': 1.3479934930801392} 08/31/2021 11:34:28 - INFO - __main__ - Step 122975: {'lr': 4.002268121437577e-05, 'samples': 23611200, 'steps': 122974, 'loss/train': 0.5538932085037231} 08/31/2021 11:34:28 - INFO - __main__ - Step 122976: {'lr': 4.0019801149157124e-05, 'samples': 23611392, 'steps': 122975, 'loss/train': 0.03386647626757622} 08/31/2021 11:34:30 - INFO - __main__ - Step 122977: {'lr': 4.0016921178552327e-05, 'samples': 23611584, 'steps': 122976, 'loss/train': 0.7354362607002258} 08/31/2021 11:34:30 - INFO - __main__ - Step 122978: {'lr': 4.001404130256264e-05, 'samples': 23611776, 'steps': 122977, 'loss/train': 0.9927152395248413} 08/31/2021 11:34:31 - INFO - __main__ - Step 122979: {'lr': 4.001116152118939e-05, 'samples': 23611968, 'steps': 122978, 'loss/train': 0.4410800635814667} 08/31/2021 11:34:31 - INFO - __main__ - Step 122980: {'lr': 4.000828183443386e-05, 'samples': 23612160, 'steps': 122979, 'loss/train': 1.309743046760559} 08/31/2021 11:34:31 - INFO - __main__ - Step 122981: {'lr': 4.000540224229737e-05, 'samples': 23612352, 'steps': 122980, 'loss/train': 1.2518110275268555} 08/31/2021 11:34:32 - INFO - __main__ - Step 122982: {'lr': 4.000252274478122e-05, 'samples': 23612544, 'steps': 122981, 'loss/train': 1.6059597730636597} 08/31/2021 11:34:33 - INFO - __main__ - Step 122983: {'lr': 3.999964334188669e-05, 'samples': 23612736, 'steps': 122982, 'loss/train': 1.474105954170227} 08/31/2021 11:34:34 - INFO - __main__ - Step 122984: {'lr': 3.999676403361513e-05, 'samples': 23612928, 'steps': 122983, 'loss/train': 1.8056416511535645} 08/31/2021 11:34:34 - INFO - __main__ - Step 122985: {'lr': 3.999388481996771e-05, 'samples': 23613120, 'steps': 122984, 'loss/train': 1.0842928886413574} 08/31/2021 11:34:34 - INFO - __main__ - Step 122986: {'lr': 3.999100570094582e-05, 'samples': 23613312, 'steps': 122985, 'loss/train': 0.15811239182949066} 08/31/2021 11:34:35 - INFO - __main__ - Step 122987: {'lr': 3.998812667655074e-05, 'samples': 23613504, 'steps': 122986, 'loss/train': 0.02925817109644413} 08/31/2021 11:34:36 - INFO - __main__ - Step 122988: {'lr': 3.9985247746783806e-05, 'samples': 23613696, 'steps': 122987, 'loss/train': 0.9909807443618774} 08/31/2021 11:34:37 - INFO - __main__ - Step 122989: {'lr': 3.9982368911646224e-05, 'samples': 23613888, 'steps': 122988, 'loss/train': 0.20946556329727173} 08/31/2021 11:34:37 - INFO - __main__ - Step 122990: {'lr': 3.997949017113939e-05, 'samples': 23614080, 'steps': 122989, 'loss/train': 1.0434106588363647} 08/31/2021 11:34:37 - INFO - __main__ - Step 122991: {'lr': 3.997661152526452e-05, 'samples': 23614272, 'steps': 122990, 'loss/train': 0.8704240918159485} 08/31/2021 11:34:38 - INFO - __main__ - Step 122992: {'lr': 3.997373297402296e-05, 'samples': 23614464, 'steps': 122991, 'loss/train': 1.4530227184295654} 08/31/2021 11:34:39 - INFO - __main__ - Step 122993: {'lr': 3.9970854517416e-05, 'samples': 23614656, 'steps': 122992, 'loss/train': 0.9588605761528015} 08/31/2021 11:34:40 - INFO - __main__ - Step 122994: {'lr': 3.996797615544493e-05, 'samples': 23614848, 'steps': 122993, 'loss/train': 0.9884760975837708} 08/31/2021 11:34:40 - INFO - __main__ - Step 122995: {'lr': 3.996509788811106e-05, 'samples': 23615040, 'steps': 122994, 'loss/train': 1.0925887823104858} 08/31/2021 11:34:40 - INFO - __main__ - Step 122996: {'lr': 3.996221971541566e-05, 'samples': 23615232, 'steps': 122995, 'loss/train': 0.9219244122505188} 08/31/2021 11:34:41 - INFO - __main__ - Step 122997: {'lr': 3.995934163736004e-05, 'samples': 23615424, 'steps': 122996, 'loss/train': 1.6695404052734375} 08/31/2021 11:34:42 - INFO - __main__ - Step 122998: {'lr': 3.995646365394559e-05, 'samples': 23615616, 'steps': 122997, 'loss/train': 0.37646377086639404} 08/31/2021 11:34:42 - INFO - __main__ - Step 122999: {'lr': 3.995358576517341e-05, 'samples': 23615808, 'steps': 122998, 'loss/train': 1.0465565919876099} 08/31/2021 11:34:43 - INFO - __main__ - Step 123000: {'lr': 3.995070797104494e-05, 'samples': 23616000, 'steps': 122999, 'loss/train': 1.2456978559494019} 08/31/2021 11:34:43 - INFO - __main__ - Step 123001: {'lr': 3.994783027156143e-05, 'samples': 23616192, 'steps': 123000, 'loss/train': 0.9953952431678772} 08/31/2021 11:34:43 - INFO - __main__ - Step 123002: {'lr': 3.994495266672418e-05, 'samples': 23616384, 'steps': 123001, 'loss/train': 1.86357843875885} 08/31/2021 11:34:45 - INFO - __main__ - Step 123003: {'lr': 3.9942075156534504e-05, 'samples': 23616576, 'steps': 123002, 'loss/train': 1.2534618377685547} 08/31/2021 11:34:45 - INFO - __main__ - Step 123004: {'lr': 3.993919774099367e-05, 'samples': 23616768, 'steps': 123003, 'loss/train': 0.5740609765052795} 08/31/2021 11:34:46 - INFO - __main__ - Step 123005: {'lr': 3.9936320420103006e-05, 'samples': 23616960, 'steps': 123004, 'loss/train': 1.404396891593933} 08/31/2021 11:34:46 - INFO - __main__ - Step 123006: {'lr': 3.9933443193863775e-05, 'samples': 23617152, 'steps': 123005, 'loss/train': 1.3526309728622437} 08/31/2021 11:34:46 - INFO - __main__ - Step 123007: {'lr': 3.9930566062277325e-05, 'samples': 23617344, 'steps': 123006, 'loss/train': 0.6544143557548523} 08/31/2021 11:34:49 - INFO - __main__ - Step 123008: {'lr': 3.992768902534491e-05, 'samples': 23617536, 'steps': 123007, 'loss/train': 1.9061520099639893} 08/31/2021 11:34:49 - INFO - __main__ - Step 123009: {'lr': 3.992481208306781e-05, 'samples': 23617728, 'steps': 123008, 'loss/train': 1.4834375381469727} 08/31/2021 11:34:49 - INFO - __main__ - Step 123010: {'lr': 3.9921935235447374e-05, 'samples': 23617920, 'steps': 123009, 'loss/train': 1.0721015930175781} 08/31/2021 11:34:50 - INFO - __main__ - Step 123011: {'lr': 3.991905848248492e-05, 'samples': 23618112, 'steps': 123010, 'loss/train': 1.4518768787384033} 08/31/2021 11:34:50 - INFO - __main__ - Step 123012: {'lr': 3.991618182418166e-05, 'samples': 23618304, 'steps': 123011, 'loss/train': 1.462124228477478} 08/31/2021 11:34:52 - INFO - __main__ - Step 123013: {'lr': 3.991330526053891e-05, 'samples': 23618496, 'steps': 123012, 'loss/train': 1.1377602815628052} 08/31/2021 11:34:52 - INFO - __main__ - Step 123014: {'lr': 3.991042879155798e-05, 'samples': 23618688, 'steps': 123013, 'loss/train': 1.4819051027297974} 08/31/2021 11:34:52 - INFO - __main__ - Step 123015: {'lr': 3.9907552417240176e-05, 'samples': 23618880, 'steps': 123014, 'loss/train': 1.2441797256469727} 08/31/2021 11:34:53 - INFO - __main__ - Step 123016: {'lr': 3.990467613758678e-05, 'samples': 23619072, 'steps': 123015, 'loss/train': 1.615256667137146} 08/31/2021 11:34:53 - INFO - __main__ - Step 123017: {'lr': 3.99017999525991e-05, 'samples': 23619264, 'steps': 123016, 'loss/train': 0.871839165687561} 08/31/2021 11:34:55 - INFO - __main__ - Step 123018: {'lr': 3.989892386227842e-05, 'samples': 23619456, 'steps': 123017, 'loss/train': 1.3529000282287598} 08/31/2021 11:34:55 - INFO - __main__ - Step 123019: {'lr': 3.989604786662604e-05, 'samples': 23619648, 'steps': 123018, 'loss/train': 1.4698350429534912} 08/31/2021 11:34:55 - INFO - __main__ - Step 123020: {'lr': 3.989317196564326e-05, 'samples': 23619840, 'steps': 123019, 'loss/train': 1.5255228281021118} 08/31/2021 11:34:56 - INFO - __main__ - Step 123021: {'lr': 3.989029615933137e-05, 'samples': 23620032, 'steps': 123020, 'loss/train': 0.5756279230117798} 08/31/2021 11:34:56 - INFO - __main__ - Step 123022: {'lr': 3.98874204476917e-05, 'samples': 23620224, 'steps': 123021, 'loss/train': 1.1885358095169067} 08/31/2021 11:34:56 - INFO - __main__ - Step 123023: {'lr': 3.9884544830725484e-05, 'samples': 23620416, 'steps': 123022, 'loss/train': 1.205890417098999} 08/31/2021 11:34:58 - INFO - __main__ - Step 123024: {'lr': 3.988166930843407e-05, 'samples': 23620608, 'steps': 123023, 'loss/train': 0.11318188905715942} 08/31/2021 11:34:59 - INFO - __main__ - Step 123025: {'lr': 3.9878793880818804e-05, 'samples': 23620800, 'steps': 123024, 'loss/train': 0.9448158144950867} 08/31/2021 11:34:59 - INFO - __main__ - Step 123026: {'lr': 3.987591854788081e-05, 'samples': 23620992, 'steps': 123025, 'loss/train': 0.8505681157112122} 08/31/2021 11:34:59 - INFO - __main__ - Step 123027: {'lr': 3.9873043309621524e-05, 'samples': 23621184, 'steps': 123026, 'loss/train': 1.0304332971572876} 08/31/2021 11:35:00 - INFO - __main__ - Step 123028: {'lr': 3.987016816604219e-05, 'samples': 23621376, 'steps': 123027, 'loss/train': 0.5273722410202026} 08/31/2021 11:35:01 - INFO - __main__ - Step 123029: {'lr': 3.98672931171441e-05, 'samples': 23621568, 'steps': 123028, 'loss/train': 1.162806510925293} 08/31/2021 11:35:02 - INFO - __main__ - Step 123030: {'lr': 3.9864418162928576e-05, 'samples': 23621760, 'steps': 123029, 'loss/train': 0.020927688106894493} 08/31/2021 11:35:02 - INFO - __main__ - Step 123031: {'lr': 3.986154330339692e-05, 'samples': 23621952, 'steps': 123030, 'loss/train': 0.013820255175232887} 08/31/2021 11:35:03 - INFO - __main__ - Step 123032: {'lr': 3.985866853855038e-05, 'samples': 23622144, 'steps': 123031, 'loss/train': 1.1669126749038696} 08/31/2021 11:35:03 - INFO - __main__ - Step 123033: {'lr': 3.985579386839031e-05, 'samples': 23622336, 'steps': 123032, 'loss/train': 1.8834214210510254} 08/31/2021 11:35:03 - INFO - __main__ - Step 123034: {'lr': 3.985291929291796e-05, 'samples': 23622528, 'steps': 123033, 'loss/train': 0.8667696118354797} 08/31/2021 11:35:05 - INFO - __main__ - Step 123035: {'lr': 3.985004481213464e-05, 'samples': 23622720, 'steps': 123034, 'loss/train': 2.3192265033721924} 08/31/2021 11:35:05 - INFO - __main__ - Step 123036: {'lr': 3.984717042604169e-05, 'samples': 23622912, 'steps': 123035, 'loss/train': 2.1276659965515137} 08/31/2021 11:35:06 - INFO - __main__ - Step 123037: {'lr': 3.984429613464033e-05, 'samples': 23623104, 'steps': 123036, 'loss/train': 0.9900216460227966} 08/31/2021 11:35:06 - INFO - __main__ - Step 123038: {'lr': 3.984142193793189e-05, 'samples': 23623296, 'steps': 123037, 'loss/train': 1.7584378719329834} 08/31/2021 11:35:06 - INFO - __main__ - Step 123039: {'lr': 3.983854783591764e-05, 'samples': 23623488, 'steps': 123038, 'loss/train': 0.9840339422225952} 08/31/2021 11:35:08 - INFO - __main__ - Step 123040: {'lr': 3.98356738285989e-05, 'samples': 23623680, 'steps': 123039, 'loss/train': 1.4400250911712646} 08/31/2021 11:35:08 - INFO - __main__ - Step 123041: {'lr': 3.983279991597699e-05, 'samples': 23623872, 'steps': 123040, 'loss/train': 1.1475837230682373} 08/31/2021 11:35:09 - INFO - __main__ - Step 123042: {'lr': 3.9829926098053165e-05, 'samples': 23624064, 'steps': 123041, 'loss/train': 1.5218168497085571} 08/31/2021 11:35:09 - INFO - __main__ - Step 123043: {'lr': 3.982705237482873e-05, 'samples': 23624256, 'steps': 123042, 'loss/train': 0.6316298842430115} 08/31/2021 11:35:09 - INFO - __main__ - Step 123044: {'lr': 3.982417874630498e-05, 'samples': 23624448, 'steps': 123043, 'loss/train': 0.9359132647514343} 08/31/2021 11:35:11 - INFO - __main__ - Step 123045: {'lr': 3.98213052124832e-05, 'samples': 23624640, 'steps': 123044, 'loss/train': 1.0796819925308228} 08/31/2021 11:35:11 - INFO - __main__ - Step 123046: {'lr': 3.981843177336469e-05, 'samples': 23624832, 'steps': 123045, 'loss/train': 1.5323983430862427} 08/31/2021 11:35:12 - INFO - __main__ - Step 123047: {'lr': 3.981555842895085e-05, 'samples': 23625024, 'steps': 123046, 'loss/train': 1.327297568321228} 08/31/2021 11:35:12 - INFO - __main__ - Step 123048: {'lr': 3.9812685179242775e-05, 'samples': 23625216, 'steps': 123047, 'loss/train': 0.6784403920173645} 08/31/2021 11:35:12 - INFO - __main__ - Step 123049: {'lr': 3.9809812024241885e-05, 'samples': 23625408, 'steps': 123048, 'loss/train': 0.8892240524291992} 08/31/2021 11:35:14 - INFO - __main__ - Step 123050: {'lr': 3.9806938963949465e-05, 'samples': 23625600, 'steps': 123049, 'loss/train': 1.5228649377822876} 08/31/2021 11:35:14 - INFO - __main__ - Step 123051: {'lr': 3.980406599836675e-05, 'samples': 23625792, 'steps': 123050, 'loss/train': 0.842969536781311} 08/31/2021 11:35:15 - INFO - __main__ - Step 123052: {'lr': 3.980119312749511e-05, 'samples': 23625984, 'steps': 123051, 'loss/train': 0.867159366607666} 08/31/2021 11:35:15 - INFO - __main__ - Step 123053: {'lr': 3.979832035133579e-05, 'samples': 23626176, 'steps': 123052, 'loss/train': 0.7391201853752136} 08/31/2021 11:35:15 - INFO - __main__ - Step 123054: {'lr': 3.9795447669890125e-05, 'samples': 23626368, 'steps': 123053, 'loss/train': 1.169924259185791} 08/31/2021 11:35:17 - INFO - __main__ - Step 123055: {'lr': 3.979257508315939e-05, 'samples': 23626560, 'steps': 123054, 'loss/train': 1.3322709798812866} 08/31/2021 11:35:17 - INFO - __main__ - Step 123056: {'lr': 3.9789702591144865e-05, 'samples': 23626752, 'steps': 123055, 'loss/train': 0.9688996076583862} 08/31/2021 11:35:18 - INFO - __main__ - Step 123057: {'lr': 3.978683019384785e-05, 'samples': 23626944, 'steps': 123056, 'loss/train': 1.1408345699310303} 08/31/2021 11:35:18 - INFO - __main__ - Step 123058: {'lr': 3.97839578912697e-05, 'samples': 23627136, 'steps': 123057, 'loss/train': 0.6250429749488831} 08/31/2021 11:35:18 - INFO - __main__ - Step 123059: {'lr': 3.978108568341163e-05, 'samples': 23627328, 'steps': 123058, 'loss/train': 1.0373680591583252} 08/31/2021 11:35:20 - INFO - __main__ - Step 123060: {'lr': 3.977821357027492e-05, 'samples': 23627520, 'steps': 123059, 'loss/train': 1.6207846403121948} 08/31/2021 11:35:21 - INFO - __main__ - Step 123061: {'lr': 3.9775341551860936e-05, 'samples': 23627712, 'steps': 123060, 'loss/train': 0.7121402025222778} 08/31/2021 11:35:21 - INFO - __main__ - Step 123062: {'lr': 3.977246962817091e-05, 'samples': 23627904, 'steps': 123061, 'loss/train': 1.4724174737930298} 08/31/2021 11:35:22 - INFO - __main__ - Step 123063: {'lr': 3.976959779920619e-05, 'samples': 23628096, 'steps': 123062, 'loss/train': 1.2709605693817139} 08/31/2021 11:35:22 - INFO - __main__ - Step 123064: {'lr': 3.9766726064968035e-05, 'samples': 23628288, 'steps': 123063, 'loss/train': 0.6096282601356506} 08/31/2021 11:35:22 - INFO - __main__ - Step 123065: {'lr': 3.976385442545774e-05, 'samples': 23628480, 'steps': 123064, 'loss/train': 1.1974815130233765} 08/31/2021 11:35:24 - INFO - __main__ - Step 123066: {'lr': 3.976098288067661e-05, 'samples': 23628672, 'steps': 123065, 'loss/train': 1.3038734197616577} 08/31/2021 11:35:24 - INFO - __main__ - Step 123067: {'lr': 3.975811143062594e-05, 'samples': 23628864, 'steps': 123066, 'loss/train': 0.23394085466861725} 08/31/2021 11:35:25 - INFO - __main__ - Step 123068: {'lr': 3.9755240075307034e-05, 'samples': 23629056, 'steps': 123067, 'loss/train': 1.3260000944137573} 08/31/2021 11:35:25 - INFO - __main__ - Step 123069: {'lr': 3.975236881472122e-05, 'samples': 23629248, 'steps': 123068, 'loss/train': 1.3139212131500244} 08/31/2021 11:35:25 - INFO - __main__ - Step 123070: {'lr': 3.974949764886968e-05, 'samples': 23629440, 'steps': 123069, 'loss/train': 1.1913975477218628} 08/31/2021 11:35:27 - INFO - __main__ - Step 123071: {'lr': 3.974662657775377e-05, 'samples': 23629632, 'steps': 123070, 'loss/train': 1.107992172241211} 08/31/2021 11:35:27 - INFO - __main__ - Step 123072: {'lr': 3.9743755601374806e-05, 'samples': 23629824, 'steps': 123071, 'loss/train': 1.4097771644592285} 08/31/2021 11:35:28 - INFO - __main__ - Step 123073: {'lr': 3.9740884719734053e-05, 'samples': 23630016, 'steps': 123072, 'loss/train': 0.3476906418800354} 08/31/2021 11:35:28 - INFO - __main__ - Step 123074: {'lr': 3.97380139328328e-05, 'samples': 23630208, 'steps': 123073, 'loss/train': 0.908061146736145} 08/31/2021 11:35:28 - INFO - __main__ - Step 123075: {'lr': 3.973514324067237e-05, 'samples': 23630400, 'steps': 123074, 'loss/train': 0.9379885792732239} 08/31/2021 11:35:30 - INFO - __main__ - Step 123076: {'lr': 3.973227264325402e-05, 'samples': 23630592, 'steps': 123075, 'loss/train': 1.0573031902313232} 08/31/2021 11:35:31 - INFO - __main__ - Step 123077: {'lr': 3.9729402140579075e-05, 'samples': 23630784, 'steps': 123076, 'loss/train': 0.02463565021753311} 08/31/2021 11:35:31 - INFO - __main__ - Step 123078: {'lr': 3.972653173264881e-05, 'samples': 23630976, 'steps': 123077, 'loss/train': 1.2330760955810547} 08/31/2021 11:35:31 - INFO - __main__ - Step 123079: {'lr': 3.972366141946454e-05, 'samples': 23631168, 'steps': 123078, 'loss/train': 1.3131054639816284} 08/31/2021 11:35:32 - INFO - __main__ - Step 123080: {'lr': 3.972079120102759e-05, 'samples': 23631360, 'steps': 123079, 'loss/train': 1.064539909362793} 08/31/2021 11:35:33 - INFO - __main__ - Step 123081: {'lr': 3.9717921077339155e-05, 'samples': 23631552, 'steps': 123080, 'loss/train': 1.2014652490615845} 08/31/2021 11:35:34 - INFO - __main__ - Step 123082: {'lr': 3.971505104840059e-05, 'samples': 23631744, 'steps': 123081, 'loss/train': 0.8063204288482666} 08/31/2021 11:35:34 - INFO - __main__ - Step 123083: {'lr': 3.9712181114213154e-05, 'samples': 23631936, 'steps': 123082, 'loss/train': 1.7410132884979248} 08/31/2021 11:35:34 - INFO - __main__ - Step 123084: {'lr': 3.970931127477817e-05, 'samples': 23632128, 'steps': 123083, 'loss/train': 1.2224034070968628} 08/31/2021 11:35:35 - INFO - __main__ - Step 123085: {'lr': 3.970644153009695e-05, 'samples': 23632320, 'steps': 123084, 'loss/train': 1.007853388786316} 08/31/2021 11:35:36 - INFO - __main__ - Step 123086: {'lr': 3.970357188017074e-05, 'samples': 23632512, 'steps': 123085, 'loss/train': 1.1184090375900269} 08/31/2021 11:35:37 - INFO - __main__ - Step 123087: {'lr': 3.970070232500084e-05, 'samples': 23632704, 'steps': 123086, 'loss/train': 0.7516566514968872} 08/31/2021 11:35:37 - INFO - __main__ - Step 123088: {'lr': 3.9697832864588585e-05, 'samples': 23632896, 'steps': 123087, 'loss/train': 1.1220998764038086} 08/31/2021 11:35:37 - INFO - __main__ - Step 123089: {'lr': 3.969496349893523e-05, 'samples': 23633088, 'steps': 123088, 'loss/train': 0.8834607005119324} 08/31/2021 11:35:38 - INFO - __main__ - Step 123090: {'lr': 3.9692094228042095e-05, 'samples': 23633280, 'steps': 123089, 'loss/train': 1.0825055837631226} 08/31/2021 11:35:39 - INFO - __main__ - Step 123091: {'lr': 3.968922505191044e-05, 'samples': 23633472, 'steps': 123090, 'loss/train': 1.1396204233169556} 08/31/2021 11:35:40 - INFO - __main__ - Step 123092: {'lr': 3.9686355970541624e-05, 'samples': 23633664, 'steps': 123091, 'loss/train': 0.9899275302886963} 08/31/2021 11:35:40 - INFO - __main__ - Step 123093: {'lr': 3.9683486983936865e-05, 'samples': 23633856, 'steps': 123092, 'loss/train': 0.6416458487510681} 08/31/2021 11:35:40 - INFO - __main__ - Step 123094: {'lr': 3.968061809209744e-05, 'samples': 23634048, 'steps': 123093, 'loss/train': 1.3366148471832275} 08/31/2021 11:35:41 - INFO - __main__ - Step 123095: {'lr': 3.9677749295024715e-05, 'samples': 23634240, 'steps': 123094, 'loss/train': 1.0411533117294312} 08/31/2021 11:35:41 - INFO - __main__ - Step 123096: {'lr': 3.967488059271995e-05, 'samples': 23634432, 'steps': 123095, 'loss/train': 1.3234509229660034} 08/31/2021 11:35:43 - INFO - __main__ - Step 123097: {'lr': 3.967201198518441e-05, 'samples': 23634624, 'steps': 123096, 'loss/train': 0.609524130821228} 08/31/2021 11:35:43 - INFO - __main__ - Step 123098: {'lr': 3.9669143472419454e-05, 'samples': 23634816, 'steps': 123097, 'loss/train': 1.8447284698486328} 08/31/2021 11:35:44 - INFO - __main__ - Step 123099: {'lr': 3.966627505442633e-05, 'samples': 23635008, 'steps': 123098, 'loss/train': 2.0373051166534424} 08/31/2021 11:35:44 - INFO - __main__ - Step 123100: {'lr': 3.96634067312063e-05, 'samples': 23635200, 'steps': 123099, 'loss/train': 1.2543851137161255} 08/31/2021 11:35:44 - INFO - __main__ - Step 123101: {'lr': 3.966053850276072e-05, 'samples': 23635392, 'steps': 123100, 'loss/train': 5.742653846740723} 08/31/2021 11:35:46 - INFO - __main__ - Step 123102: {'lr': 3.965767036909085e-05, 'samples': 23635584, 'steps': 123101, 'loss/train': 1.4528781175613403} 08/31/2021 11:35:46 - INFO - __main__ - Step 123103: {'lr': 3.9654802330198e-05, 'samples': 23635776, 'steps': 123102, 'loss/train': 0.48232758045196533} 08/31/2021 11:35:47 - INFO - __main__ - Step 123104: {'lr': 3.9651934386083444e-05, 'samples': 23635968, 'steps': 123103, 'loss/train': 0.0685337483882904} 08/31/2021 11:35:47 - INFO - __main__ - Step 123105: {'lr': 3.964906653674854e-05, 'samples': 23636160, 'steps': 123104, 'loss/train': 0.7988947033882141} 08/31/2021 11:35:47 - INFO - __main__ - Step 123106: {'lr': 3.964619878219444e-05, 'samples': 23636352, 'steps': 123105, 'loss/train': 1.0817325115203857} 08/31/2021 11:35:49 - INFO - __main__ - Step 123107: {'lr': 3.964333112242255e-05, 'samples': 23636544, 'steps': 123106, 'loss/train': 0.5124400854110718} 08/31/2021 11:35:49 - INFO - __main__ - Step 123108: {'lr': 3.964046355743412e-05, 'samples': 23636736, 'steps': 123107, 'loss/train': 1.142397165298462} 08/31/2021 11:35:50 - INFO - __main__ - Step 123109: {'lr': 3.9637596087230445e-05, 'samples': 23636928, 'steps': 123108, 'loss/train': 1.3317084312438965} 08/31/2021 11:35:50 - INFO - __main__ - Step 123110: {'lr': 3.963472871181281e-05, 'samples': 23637120, 'steps': 123109, 'loss/train': 0.09394911676645279} 08/31/2021 11:35:50 - INFO - __main__ - Step 123111: {'lr': 3.963186143118255e-05, 'samples': 23637312, 'steps': 123110, 'loss/train': 1.2784812450408936} 08/31/2021 11:35:51 - INFO - __main__ - Step 123112: {'lr': 3.962899424534092e-05, 'samples': 23637504, 'steps': 123111, 'loss/train': 0.8444451093673706} 08/31/2021 11:35:52 - INFO - __main__ - Step 123113: {'lr': 3.96261271542892e-05, 'samples': 23637696, 'steps': 123112, 'loss/train': 0.9395753145217896} 08/31/2021 11:35:53 - INFO - __main__ - Step 123114: {'lr': 3.9623260158028695e-05, 'samples': 23637888, 'steps': 123113, 'loss/train': 1.131375789642334} 08/31/2021 11:35:53 - INFO - __main__ - Step 123115: {'lr': 3.962039325656072e-05, 'samples': 23638080, 'steps': 123114, 'loss/train': 1.347962737083435} 08/31/2021 11:35:53 - INFO - __main__ - Step 123116: {'lr': 3.961752644988656e-05, 'samples': 23638272, 'steps': 123115, 'loss/train': 0.7239534854888916} 08/31/2021 11:35:54 - INFO - __main__ - Step 123117: {'lr': 3.961465973800749e-05, 'samples': 23638464, 'steps': 123116, 'loss/train': 0.5571549534797668} 08/31/2021 11:35:56 - INFO - __main__ - Step 123118: {'lr': 3.96117931209248e-05, 'samples': 23638656, 'steps': 123117, 'loss/train': 0.9631069898605347} 08/31/2021 11:35:57 - INFO - __main__ - Step 123119: {'lr': 3.960892659863985e-05, 'samples': 23638848, 'steps': 123118, 'loss/train': 1.1095366477966309} 08/31/2021 11:35:57 - INFO - __main__ - Step 123120: {'lr': 3.960606017115381e-05, 'samples': 23639040, 'steps': 123119, 'loss/train': 0.01875654049217701} 08/31/2021 11:35:57 - INFO - __main__ - Step 123121: {'lr': 3.960319383846803e-05, 'samples': 23639232, 'steps': 123120, 'loss/train': 0.7438439130783081} 08/31/2021 11:35:58 - INFO - __main__ - Step 123122: {'lr': 3.960032760058383e-05, 'samples': 23639424, 'steps': 123121, 'loss/train': 1.2008665800094604} 08/31/2021 11:36:00 - INFO - __main__ - Step 123123: {'lr': 3.9597461457502425e-05, 'samples': 23639616, 'steps': 123122, 'loss/train': 1.981119155883789} 08/31/2021 11:36:00 - INFO - __main__ - Step 123124: {'lr': 3.959459540922519e-05, 'samples': 23639808, 'steps': 123123, 'loss/train': 1.248415470123291} 08/31/2021 11:36:00 - INFO - __main__ - Step 123125: {'lr': 3.95917294557534e-05, 'samples': 23640000, 'steps': 123124, 'loss/train': 0.5271462202072144} 08/31/2021 11:36:01 - INFO - __main__ - Step 123126: {'lr': 3.95888635970883e-05, 'samples': 23640192, 'steps': 123125, 'loss/train': 0.8693666458129883} 08/31/2021 11:36:01 - INFO - __main__ - Step 123127: {'lr': 3.958599783323122e-05, 'samples': 23640384, 'steps': 123126, 'loss/train': 1.310367465019226} 08/31/2021 11:36:01 - INFO - __main__ - Step 123128: {'lr': 3.958313216418344e-05, 'samples': 23640576, 'steps': 123127, 'loss/train': 1.1094499826431274} 08/31/2021 11:36:03 - INFO - __main__ - Step 123129: {'lr': 3.958026658994626e-05, 'samples': 23640768, 'steps': 123128, 'loss/train': 1.0598125457763672} 08/31/2021 11:36:04 - INFO - __main__ - Step 123130: {'lr': 3.957740111052097e-05, 'samples': 23640960, 'steps': 123129, 'loss/train': 1.2199708223342896} 08/31/2021 11:36:04 - INFO - __main__ - Step 123131: {'lr': 3.9574535725908856e-05, 'samples': 23641152, 'steps': 123130, 'loss/train': 0.755132257938385} 08/31/2021 11:36:04 - INFO - __main__ - Step 123132: {'lr': 3.957167043611126e-05, 'samples': 23641344, 'steps': 123131, 'loss/train': 0.09708881378173828} 08/31/2021 11:36:05 - INFO - __main__ - Step 123133: {'lr': 3.9568805241129355e-05, 'samples': 23641536, 'steps': 123132, 'loss/train': 1.0728785991668701} 08/31/2021 11:36:06 - INFO - __main__ - Step 123134: {'lr': 3.9565940140964513e-05, 'samples': 23641728, 'steps': 123133, 'loss/train': 1.2921950817108154} 08/31/2021 11:36:07 - INFO - __main__ - Step 123135: {'lr': 3.9563075135618024e-05, 'samples': 23641920, 'steps': 123134, 'loss/train': 1.4300658702850342} 08/31/2021 11:36:07 - INFO - __main__ - Step 123136: {'lr': 3.956021022509113e-05, 'samples': 23642112, 'steps': 123135, 'loss/train': 0.6306988000869751} 08/31/2021 11:36:07 - INFO - __main__ - Step 123137: {'lr': 3.9557345409385184e-05, 'samples': 23642304, 'steps': 123136, 'loss/train': 1.2395505905151367} 08/31/2021 11:36:08 - INFO - __main__ - Step 123138: {'lr': 3.955448068850143e-05, 'samples': 23642496, 'steps': 123137, 'loss/train': 0.4986373782157898} 08/31/2021 11:36:09 - INFO - __main__ - Step 123139: {'lr': 3.95516160624412e-05, 'samples': 23642688, 'steps': 123138, 'loss/train': 0.5844065546989441} 08/31/2021 11:36:10 - INFO - __main__ - Step 123140: {'lr': 3.9548751531205765e-05, 'samples': 23642880, 'steps': 123139, 'loss/train': 0.4931115508079529} 08/31/2021 11:36:10 - INFO - __main__ - Step 123141: {'lr': 3.95458870947964e-05, 'samples': 23643072, 'steps': 123140, 'loss/train': 1.2132833003997803} 08/31/2021 11:36:11 - INFO - __main__ - Step 123142: {'lr': 3.954302275321442e-05, 'samples': 23643264, 'steps': 123141, 'loss/train': 0.9239018559455872} 08/31/2021 11:36:11 - INFO - __main__ - Step 123143: {'lr': 3.9540158506461114e-05, 'samples': 23643456, 'steps': 123142, 'loss/train': 0.4830223619937897} 08/31/2021 11:36:11 - INFO - __main__ - Step 123144: {'lr': 3.9537294354537765e-05, 'samples': 23643648, 'steps': 123143, 'loss/train': 0.9116035103797913} 08/31/2021 11:36:13 - INFO - __main__ - Step 123145: {'lr': 3.9534430297445636e-05, 'samples': 23643840, 'steps': 123144, 'loss/train': 0.7164861559867859} 08/31/2021 11:36:13 - INFO - __main__ - Step 123146: {'lr': 3.953156633518612e-05, 'samples': 23644032, 'steps': 123145, 'loss/train': 1.4488499164581299} 08/31/2021 11:36:14 - INFO - __main__ - Step 123147: {'lr': 3.9528702467760384e-05, 'samples': 23644224, 'steps': 123146, 'loss/train': 1.1353037357330322} 08/31/2021 11:36:14 - INFO - __main__ - Step 123148: {'lr': 3.952583869516976e-05, 'samples': 23644416, 'steps': 123147, 'loss/train': 0.773457944393158} 08/31/2021 11:36:14 - INFO - __main__ - Step 123149: {'lr': 3.952297501741553e-05, 'samples': 23644608, 'steps': 123148, 'loss/train': 1.1418671607971191} 08/31/2021 11:36:16 - INFO - __main__ - Step 123150: {'lr': 3.952011143449902e-05, 'samples': 23644800, 'steps': 123149, 'loss/train': 0.5946093201637268} 08/31/2021 11:36:16 - INFO - __main__ - Step 123151: {'lr': 3.95172479464215e-05, 'samples': 23644992, 'steps': 123150, 'loss/train': 1.4640898704528809} 08/31/2021 11:36:17 - INFO - __main__ - Step 123152: {'lr': 3.951438455318426e-05, 'samples': 23645184, 'steps': 123151, 'loss/train': 1.4212265014648438} 08/31/2021 11:36:17 - INFO - __main__ - Step 123153: {'lr': 3.9511521254788575e-05, 'samples': 23645376, 'steps': 123152, 'loss/train': 1.2101086378097534} 08/31/2021 11:36:17 - INFO - __main__ - Step 123154: {'lr': 3.950865805123577e-05, 'samples': 23645568, 'steps': 123153, 'loss/train': 1.7387111186981201} 08/31/2021 11:36:19 - INFO - __main__ - Step 123155: {'lr': 3.95057949425271e-05, 'samples': 23645760, 'steps': 123154, 'loss/train': 0.8021389245986938} 08/31/2021 11:36:19 - INFO - __main__ - Step 123156: {'lr': 3.9502931928663886e-05, 'samples': 23645952, 'steps': 123155, 'loss/train': 0.8307431936264038} 08/31/2021 11:36:20 - INFO - __main__ - Step 123157: {'lr': 3.9500069009647394e-05, 'samples': 23646144, 'steps': 123156, 'loss/train': 0.4559222459793091} 08/31/2021 11:36:20 - INFO - __main__ - Step 123158: {'lr': 3.949720618547892e-05, 'samples': 23646336, 'steps': 123157, 'loss/train': 0.920090913772583} 08/31/2021 11:36:20 - INFO - __main__ - Step 123159: {'lr': 3.949434345615982e-05, 'samples': 23646528, 'steps': 123158, 'loss/train': 1.3126916885375977} 08/31/2021 11:36:21 - INFO - __main__ - Step 123160: {'lr': 3.949148082169124e-05, 'samples': 23646720, 'steps': 123159, 'loss/train': 0.7515501379966736} 08/31/2021 11:36:22 - INFO - __main__ - Step 123161: {'lr': 3.9488618282074564e-05, 'samples': 23646912, 'steps': 123160, 'loss/train': 1.3324075937271118} 08/31/2021 11:36:23 - INFO - __main__ - Step 123162: {'lr': 3.9485755837311094e-05, 'samples': 23647104, 'steps': 123161, 'loss/train': 0.7459245324134827} 08/31/2021 11:36:23 - INFO - __main__ - Step 123163: {'lr': 3.948289348740205e-05, 'samples': 23647296, 'steps': 123162, 'loss/train': 0.9173412322998047} 08/31/2021 11:36:23 - INFO - __main__ - Step 123164: {'lr': 3.948003123234881e-05, 'samples': 23647488, 'steps': 123163, 'loss/train': 1.4213162660598755} 08/31/2021 11:36:24 - INFO - __main__ - Step 123165: {'lr': 3.9477169072152595e-05, 'samples': 23647680, 'steps': 123164, 'loss/train': 0.707557737827301} 08/31/2021 11:36:25 - INFO - __main__ - Step 123166: {'lr': 3.947430700681473e-05, 'samples': 23647872, 'steps': 123165, 'loss/train': 1.2074894905090332} 08/31/2021 11:36:26 - INFO - __main__ - Step 123167: {'lr': 3.9471445036336486e-05, 'samples': 23648064, 'steps': 123166, 'loss/train': 1.2637982368469238} 08/31/2021 11:36:26 - INFO - __main__ - Step 123168: {'lr': 3.946858316071913e-05, 'samples': 23648256, 'steps': 123167, 'loss/train': 1.3114776611328125} 08/31/2021 11:36:26 - INFO - __main__ - Step 123169: {'lr': 3.946572137996404e-05, 'samples': 23648448, 'steps': 123168, 'loss/train': 0.7097617387771606} 08/31/2021 11:36:27 - INFO - __main__ - Step 123170: {'lr': 3.94628596940724e-05, 'samples': 23648640, 'steps': 123169, 'loss/train': 1.0128159523010254} 08/31/2021 11:36:29 - INFO - __main__ - Step 123171: {'lr': 3.945999810304557e-05, 'samples': 23648832, 'steps': 123170, 'loss/train': 0.8230700492858887} 08/31/2021 11:36:30 - INFO - __main__ - Step 123172: {'lr': 3.945713660688488e-05, 'samples': 23649024, 'steps': 123171, 'loss/train': 0.9805055260658264} 08/31/2021 11:36:30 - INFO - __main__ - Step 123173: {'lr': 3.9454275205591475e-05, 'samples': 23649216, 'steps': 123172, 'loss/train': 0.6617102026939392} 08/31/2021 11:36:30 - INFO - __main__ - Step 123174: {'lr': 3.945141389916676e-05, 'samples': 23649408, 'steps': 123173, 'loss/train': 1.1545969247817993} 08/31/2021 11:36:31 - INFO - __main__ - Step 123175: {'lr': 3.9448552687611964e-05, 'samples': 23649600, 'steps': 123174, 'loss/train': 0.46666693687438965} 08/31/2021 11:36:31 - INFO - __main__ - Step 123176: {'lr': 3.944569157092839e-05, 'samples': 23649792, 'steps': 123175, 'loss/train': 0.015209338627755642} 08/31/2021 11:36:31 - INFO - __main__ - Step 123177: {'lr': 3.944283054911735e-05, 'samples': 23649984, 'steps': 123176, 'loss/train': 0.9016413688659668} 08/31/2021 11:36:33 - INFO - __main__ - Step 123178: {'lr': 3.9439969622180134e-05, 'samples': 23650176, 'steps': 123177, 'loss/train': 0.01662839949131012} 08/31/2021 11:36:33 - INFO - __main__ - Step 123179: {'lr': 3.9437108790117996e-05, 'samples': 23650368, 'steps': 123178, 'loss/train': 1.0718963146209717} 08/31/2021 11:36:34 - INFO - __main__ - Step 123180: {'lr': 3.9434248052932275e-05, 'samples': 23650560, 'steps': 123179, 'loss/train': 1.3908188343048096} 08/31/2021 11:36:34 - INFO - __main__ - Step 123181: {'lr': 3.943138741062421e-05, 'samples': 23650752, 'steps': 123180, 'loss/train': 0.3490583598613739} 08/31/2021 11:36:34 - INFO - __main__ - Step 123182: {'lr': 3.942852686319512e-05, 'samples': 23650944, 'steps': 123181, 'loss/train': 0.28829362988471985} 08/31/2021 11:36:36 - INFO - __main__ - Step 123183: {'lr': 3.942566641064627e-05, 'samples': 23651136, 'steps': 123182, 'loss/train': 0.9976973533630371} 08/31/2021 11:36:36 - INFO - __main__ - Step 123184: {'lr': 3.9422806052978985e-05, 'samples': 23651328, 'steps': 123183, 'loss/train': 0.11576250195503235} 08/31/2021 11:36:37 - INFO - __main__ - Step 123185: {'lr': 3.941994579019453e-05, 'samples': 23651520, 'steps': 123184, 'loss/train': 0.4375028908252716} 08/31/2021 11:36:37 - INFO - __main__ - Step 123186: {'lr': 3.941708562229426e-05, 'samples': 23651712, 'steps': 123185, 'loss/train': 0.8428877592086792} 08/31/2021 11:36:37 - INFO - __main__ - Step 123187: {'lr': 3.941422554927934e-05, 'samples': 23651904, 'steps': 123186, 'loss/train': 2.267268419265747} 08/31/2021 11:36:38 - INFO - __main__ - Step 123188: {'lr': 3.941136557115113e-05, 'samples': 23652096, 'steps': 123187, 'loss/train': 0.7294713258743286} 08/31/2021 11:36:39 - INFO - __main__ - Step 123189: {'lr': 3.940850568791088e-05, 'samples': 23652288, 'steps': 123188, 'loss/train': 1.646722674369812} 08/31/2021 11:36:40 - INFO - __main__ - Step 123190: {'lr': 3.9405645899559945e-05, 'samples': 23652480, 'steps': 123189, 'loss/train': 1.2890150547027588} 08/31/2021 11:36:40 - INFO - __main__ - Step 123191: {'lr': 3.940278620609955e-05, 'samples': 23652672, 'steps': 123190, 'loss/train': 1.4644867181777954} 08/31/2021 11:36:41 - INFO - __main__ - Step 123192: {'lr': 3.939992660753103e-05, 'samples': 23652864, 'steps': 123191, 'loss/train': 0.08325327932834625} 08/31/2021 11:36:41 - INFO - __main__ - Step 123193: {'lr': 3.939706710385563e-05, 'samples': 23653056, 'steps': 123192, 'loss/train': 0.8650313019752502} 08/31/2021 11:36:42 - INFO - __main__ - Step 123194: {'lr': 3.939420769507468e-05, 'samples': 23653248, 'steps': 123193, 'loss/train': 0.6008786559104919} 08/31/2021 11:36:43 - INFO - __main__ - Step 123195: {'lr': 3.939134838118943e-05, 'samples': 23653440, 'steps': 123194, 'loss/train': 1.0362974405288696} 08/31/2021 11:36:43 - INFO - __main__ - Step 123196: {'lr': 3.9388489162201226e-05, 'samples': 23653632, 'steps': 123195, 'loss/train': 0.8088526129722595} 08/31/2021 11:36:44 - INFO - __main__ - Step 123197: {'lr': 3.938563003811127e-05, 'samples': 23653824, 'steps': 123196, 'loss/train': 1.0871241092681885} 08/31/2021 11:36:44 - INFO - __main__ - Step 123198: {'lr': 3.938277100892093e-05, 'samples': 23654016, 'steps': 123197, 'loss/train': 0.7908389568328857} 08/31/2021 11:36:46 - INFO - __main__ - Step 123199: {'lr': 3.9379912074631516e-05, 'samples': 23654208, 'steps': 123198, 'loss/train': 0.41844043135643005} 08/31/2021 11:36:46 - INFO - __main__ - Step 123200: {'lr': 3.937705323524421e-05, 'samples': 23654400, 'steps': 123199, 'loss/train': 1.5757386684417725} 08/31/2021 11:36:47 - INFO - __main__ - Step 123201: {'lr': 3.937419449076035e-05, 'samples': 23654592, 'steps': 123200, 'loss/train': 0.014833802357316017} 08/31/2021 11:36:47 - INFO - __main__ - Step 123202: {'lr': 3.937133584118122e-05, 'samples': 23654784, 'steps': 123201, 'loss/train': 0.7944577932357788} 08/31/2021 11:36:47 - INFO - __main__ - Step 123203: {'lr': 3.9368477286508133e-05, 'samples': 23654976, 'steps': 123202, 'loss/train': 1.3972008228302002} 08/31/2021 11:36:48 - INFO - __main__ - Step 123204: {'lr': 3.936561882674233e-05, 'samples': 23655168, 'steps': 123203, 'loss/train': 1.5253738164901733} 08/31/2021 11:36:49 - INFO - __main__ - Step 123205: {'lr': 3.936276046188517e-05, 'samples': 23655360, 'steps': 123204, 'loss/train': 0.9864940643310547} 08/31/2021 11:36:50 - INFO - __main__ - Step 123206: {'lr': 3.935990219193786e-05, 'samples': 23655552, 'steps': 123205, 'loss/train': 0.6373645663261414} 08/31/2021 11:36:50 - INFO - __main__ - Step 123207: {'lr': 3.9357044016901766e-05, 'samples': 23655744, 'steps': 123206, 'loss/train': 0.8542071580886841} 08/31/2021 11:36:51 - INFO - __main__ - Step 123208: {'lr': 3.9354185936778117e-05, 'samples': 23655936, 'steps': 123207, 'loss/train': 1.9898625612258911} 08/31/2021 11:36:51 - INFO - __main__ - Step 123209: {'lr': 3.935132795156821e-05, 'samples': 23656128, 'steps': 123208, 'loss/train': 0.594485878944397} 08/31/2021 11:36:51 - INFO - __main__ - Step 123210: {'lr': 3.934847006127334e-05, 'samples': 23656320, 'steps': 123209, 'loss/train': 0.9662981033325195} 08/31/2021 11:36:53 - INFO - __main__ - Step 123211: {'lr': 3.9345612265894834e-05, 'samples': 23656512, 'steps': 123210, 'loss/train': 0.8649634122848511} 08/31/2021 11:36:54 - INFO - __main__ - Step 123212: {'lr': 3.934275456543393e-05, 'samples': 23656704, 'steps': 123211, 'loss/train': 1.3359514474868774} 08/31/2021 11:36:54 - INFO - __main__ - Step 123213: {'lr': 3.9339896959891985e-05, 'samples': 23656896, 'steps': 123212, 'loss/train': 1.4572921991348267} 08/31/2021 11:36:54 - INFO - __main__ - Step 123214: {'lr': 3.9337039449270164e-05, 'samples': 23657088, 'steps': 123213, 'loss/train': 1.0135053396224976} 08/31/2021 11:36:55 - INFO - __main__ - Step 123215: {'lr': 3.933418203356984e-05, 'samples': 23657280, 'steps': 123214, 'loss/train': 1.1182628870010376} 08/31/2021 11:36:56 - INFO - __main__ - Step 123216: {'lr': 3.933132471279227e-05, 'samples': 23657472, 'steps': 123215, 'loss/train': 1.3251465559005737} 08/31/2021 11:36:57 - INFO - __main__ - Step 123217: {'lr': 3.932846748693875e-05, 'samples': 23657664, 'steps': 123216, 'loss/train': 1.298174262046814} 08/31/2021 11:36:57 - INFO - __main__ - Step 123218: {'lr': 3.9325610356010566e-05, 'samples': 23657856, 'steps': 123217, 'loss/train': 1.469093918800354} 08/31/2021 11:36:57 - INFO - __main__ - Step 123219: {'lr': 3.9322753320009034e-05, 'samples': 23658048, 'steps': 123218, 'loss/train': 1.010003685951233} 08/31/2021 11:36:58 - INFO - __main__ - Step 123220: {'lr': 3.931989637893541e-05, 'samples': 23658240, 'steps': 123219, 'loss/train': 1.3373204469680786} 08/31/2021 11:36:58 - INFO - __main__ - Step 123221: {'lr': 3.931703953279098e-05, 'samples': 23658432, 'steps': 123220, 'loss/train': 1.1900354623794556} 08/31/2021 11:36:59 - INFO - __main__ - Step 123222: {'lr': 3.9314182781577054e-05, 'samples': 23658624, 'steps': 123221, 'loss/train': 1.1853950023651123} 08/31/2021 11:37:00 - INFO - __main__ - Step 123223: {'lr': 3.931132612529489e-05, 'samples': 23658816, 'steps': 123222, 'loss/train': 0.10416264086961746} 08/31/2021 11:37:00 - INFO - __main__ - Step 123224: {'lr': 3.930846956394582e-05, 'samples': 23659008, 'steps': 123223, 'loss/train': 1.350334882736206} 08/31/2021 11:37:01 - INFO - __main__ - Step 123225: {'lr': 3.930561309753109e-05, 'samples': 23659200, 'steps': 123224, 'loss/train': 0.7496281862258911} 08/31/2021 11:37:01 - INFO - __main__ - Step 123226: {'lr': 3.930275672605205e-05, 'samples': 23659392, 'steps': 123225, 'loss/train': 1.2622705698013306} 08/31/2021 11:37:03 - INFO - __main__ - Step 123227: {'lr': 3.9299900449509875e-05, 'samples': 23659584, 'steps': 123226, 'loss/train': 0.20210818946361542} 08/31/2021 11:37:03 - INFO - __main__ - Step 123228: {'lr': 3.9297044267905924e-05, 'samples': 23659776, 'steps': 123227, 'loss/train': 0.63292396068573} 08/31/2021 11:37:04 - INFO - __main__ - Step 123229: {'lr': 3.929418818124148e-05, 'samples': 23659968, 'steps': 123228, 'loss/train': 1.1225804090499878} 08/31/2021 11:37:04 - INFO - __main__ - Step 123230: {'lr': 3.92913321895178e-05, 'samples': 23660160, 'steps': 123229, 'loss/train': 1.3570623397827148} 08/31/2021 11:37:04 - INFO - __main__ - Step 123231: {'lr': 3.9288476292736216e-05, 'samples': 23660352, 'steps': 123230, 'loss/train': 0.8107042908668518} 08/31/2021 11:37:06 - INFO - __main__ - Step 123232: {'lr': 3.928562049089798e-05, 'samples': 23660544, 'steps': 123231, 'loss/train': 0.6902616620063782} 08/31/2021 11:37:07 - INFO - __main__ - Step 123233: {'lr': 3.928276478400439e-05, 'samples': 23660736, 'steps': 123232, 'loss/train': 1.0277013778686523} 08/31/2021 11:37:07 - INFO - __main__ - Step 123234: {'lr': 3.927990917205673e-05, 'samples': 23660928, 'steps': 123233, 'loss/train': 1.0871671438217163} 08/31/2021 11:37:08 - INFO - __main__ - Step 123235: {'lr': 3.927705365505632e-05, 'samples': 23661120, 'steps': 123234, 'loss/train': 1.1133517026901245} 08/31/2021 11:37:08 - INFO - __main__ - Step 123236: {'lr': 3.9274198233004376e-05, 'samples': 23661312, 'steps': 123235, 'loss/train': 1.2560254335403442} 08/31/2021 11:37:09 - INFO - __main__ - Step 123237: {'lr': 3.927134290590226e-05, 'samples': 23661504, 'steps': 123236, 'loss/train': 1.4091579914093018} 08/31/2021 11:37:10 - INFO - __main__ - Step 123238: {'lr': 3.926848767375121e-05, 'samples': 23661696, 'steps': 123237, 'loss/train': 0.685806393623352} 08/31/2021 11:37:10 - INFO - __main__ - Step 123239: {'lr': 3.9265632536552546e-05, 'samples': 23661888, 'steps': 123238, 'loss/train': 0.5869062542915344} 08/31/2021 11:37:11 - INFO - __main__ - Step 123240: {'lr': 3.926277749430757e-05, 'samples': 23662080, 'steps': 123239, 'loss/train': 0.45627984404563904} 08/31/2021 11:37:11 - INFO - __main__ - Step 123241: {'lr': 3.925992254701749e-05, 'samples': 23662272, 'steps': 123240, 'loss/train': 0.18656858801841736} 08/31/2021 11:37:12 - INFO - __main__ - Step 123242: {'lr': 3.9257067694683654e-05, 'samples': 23662464, 'steps': 123241, 'loss/train': 0.8107028007507324} 08/31/2021 11:37:13 - INFO - __main__ - Step 123243: {'lr': 3.92542129373073e-05, 'samples': 23662656, 'steps': 123242, 'loss/train': 0.6873792409896851} 08/31/2021 11:37:13 - INFO - __main__ - Step 123244: {'lr': 3.9251358274889764e-05, 'samples': 23662848, 'steps': 123243, 'loss/train': 0.9055513739585876} 08/31/2021 11:37:14 - INFO - __main__ - Step 123245: {'lr': 3.92485037074323e-05, 'samples': 23663040, 'steps': 123244, 'loss/train': 1.3680938482284546} 08/31/2021 11:37:14 - INFO - __main__ - Step 123246: {'lr': 3.924564923493623e-05, 'samples': 23663232, 'steps': 123245, 'loss/train': 1.748043179512024} 08/31/2021 11:37:14 - INFO - __main__ - Step 123247: {'lr': 3.9242794857402785e-05, 'samples': 23663424, 'steps': 123246, 'loss/train': 1.2742334604263306} 08/31/2021 11:37:16 - INFO - __main__ - Step 123248: {'lr': 3.923994057483332e-05, 'samples': 23663616, 'steps': 123247, 'loss/train': 1.5036282539367676} 08/31/2021 11:37:16 - INFO - __main__ - Step 123249: {'lr': 3.923708638722906e-05, 'samples': 23663808, 'steps': 123248, 'loss/train': 1.2487670183181763} 08/31/2021 11:37:17 - INFO - __main__ - Step 123250: {'lr': 3.923423229459133e-05, 'samples': 23664000, 'steps': 123249, 'loss/train': 1.101916790008545} 08/31/2021 11:37:17 - INFO - __main__ - Step 123251: {'lr': 3.923137829692139e-05, 'samples': 23664192, 'steps': 123250, 'loss/train': 0.6714300513267517} 08/31/2021 11:37:17 - INFO - __main__ - Step 123252: {'lr': 3.922852439422056e-05, 'samples': 23664384, 'steps': 123251, 'loss/train': 0.07149901241064072} 08/31/2021 11:37:19 - INFO - __main__ - Step 123253: {'lr': 3.922567058649015e-05, 'samples': 23664576, 'steps': 123252, 'loss/train': 0.724267303943634} 08/31/2021 11:37:20 - INFO - __main__ - Step 123254: {'lr': 3.9222816873731335e-05, 'samples': 23664768, 'steps': 123253, 'loss/train': 1.6015092134475708} 08/31/2021 11:37:20 - INFO - __main__ - Step 123255: {'lr': 3.9219963255945485e-05, 'samples': 23664960, 'steps': 123254, 'loss/train': 1.4451427459716797} 08/31/2021 11:37:20 - INFO - __main__ - Step 123256: {'lr': 3.9217109733133835e-05, 'samples': 23665152, 'steps': 123255, 'loss/train': 1.0183486938476562} 08/31/2021 11:37:21 - INFO - __main__ - Step 123257: {'lr': 3.921425630529773e-05, 'samples': 23665344, 'steps': 123256, 'loss/train': 1.3341622352600098} 08/31/2021 11:37:22 - INFO - __main__ - Step 123258: {'lr': 3.921140297243841e-05, 'samples': 23665536, 'steps': 123257, 'loss/train': 0.972645103931427} 08/31/2021 11:37:23 - INFO - __main__ - Step 123259: {'lr': 3.92085497345572e-05, 'samples': 23665728, 'steps': 123258, 'loss/train': 0.026143958792090416} 08/31/2021 11:37:23 - INFO - __main__ - Step 123260: {'lr': 3.920569659165535e-05, 'samples': 23665920, 'steps': 123259, 'loss/train': 0.3836944103240967} 08/31/2021 11:37:23 - INFO - __main__ - Step 123261: {'lr': 3.920284354373419e-05, 'samples': 23666112, 'steps': 123260, 'loss/train': 1.0220807790756226} 08/31/2021 11:37:24 - INFO - __main__ - Step 123262: {'lr': 3.9199990590794934e-05, 'samples': 23666304, 'steps': 123261, 'loss/train': 0.817344069480896} 08/31/2021 11:37:25 - INFO - __main__ - Step 123263: {'lr': 3.9197137732838926e-05, 'samples': 23666496, 'steps': 123262, 'loss/train': 1.0183807611465454} 08/31/2021 11:37:26 - INFO - __main__ - Step 123264: {'lr': 3.919428496986743e-05, 'samples': 23666688, 'steps': 123263, 'loss/train': 1.394041657447815} 08/31/2021 11:37:26 - INFO - __main__ - Step 123265: {'lr': 3.919143230188174e-05, 'samples': 23666880, 'steps': 123264, 'loss/train': 0.8734610080718994} 08/31/2021 11:37:27 - INFO - __main__ - Step 123266: {'lr': 3.918857972888315e-05, 'samples': 23667072, 'steps': 123265, 'loss/train': 0.9687601923942566} 08/31/2021 11:37:27 - INFO - __main__ - Step 123267: {'lr': 3.918572725087299e-05, 'samples': 23667264, 'steps': 123266, 'loss/train': 1.067629337310791} 08/31/2021 11:37:29 - INFO - __main__ - Step 123268: {'lr': 3.918287486785241e-05, 'samples': 23667456, 'steps': 123267, 'loss/train': 0.03079800307750702} 08/31/2021 11:37:29 - INFO - __main__ - Step 123269: {'lr': 3.9180022579822785e-05, 'samples': 23667648, 'steps': 123268, 'loss/train': 0.8532989025115967} 08/31/2021 11:37:30 - INFO - __main__ - Step 123270: {'lr': 3.917717038678539e-05, 'samples': 23667840, 'steps': 123269, 'loss/train': 0.7642338871955872} 08/31/2021 11:37:30 - INFO - __main__ - Step 123271: {'lr': 3.9174318288741515e-05, 'samples': 23668032, 'steps': 123270, 'loss/train': 1.325119137763977} 08/31/2021 11:37:30 - INFO - __main__ - Step 123272: {'lr': 3.917146628569243e-05, 'samples': 23668224, 'steps': 123271, 'loss/train': 0.997953474521637} 08/31/2021 11:37:31 - INFO - __main__ - Step 123273: {'lr': 3.916861437763941e-05, 'samples': 23668416, 'steps': 123272, 'loss/train': 1.498326063156128} 08/31/2021 11:37:32 - INFO - __main__ - Step 123274: {'lr': 3.916576256458379e-05, 'samples': 23668608, 'steps': 123273, 'loss/train': 1.5354011058807373} 08/31/2021 11:37:32 - INFO - __main__ - Step 123275: {'lr': 3.916291084652682e-05, 'samples': 23668800, 'steps': 123274, 'loss/train': 1.0942931175231934} 08/31/2021 11:37:33 - INFO - __main__ - Step 123276: {'lr': 3.916005922346977e-05, 'samples': 23668992, 'steps': 123275, 'loss/train': 1.5457226037979126} 08/31/2021 11:37:33 - INFO - __main__ - Step 123277: {'lr': 3.9157207695413946e-05, 'samples': 23669184, 'steps': 123276, 'loss/train': 1.045597791671753} 08/31/2021 11:37:34 - INFO - __main__ - Step 123278: {'lr': 3.915435626236066e-05, 'samples': 23669376, 'steps': 123277, 'loss/train': 0.8592288494110107} 08/31/2021 11:37:35 - INFO - __main__ - Step 123279: {'lr': 3.9151504924311135e-05, 'samples': 23669568, 'steps': 123278, 'loss/train': 1.3276500701904297} 08/31/2021 11:37:35 - INFO - __main__ - Step 123280: {'lr': 3.9148653681266775e-05, 'samples': 23669760, 'steps': 123279, 'loss/train': 0.9747958183288574} 08/31/2021 11:37:36 - INFO - __main__ - Step 123281: {'lr': 3.914580253322869e-05, 'samples': 23669952, 'steps': 123280, 'loss/train': 0.5545661449432373} 08/31/2021 11:37:36 - INFO - __main__ - Step 123282: {'lr': 3.914295148019828e-05, 'samples': 23670144, 'steps': 123281, 'loss/train': 0.8844384551048279} 08/31/2021 11:37:36 - INFO - __main__ - Step 123283: {'lr': 3.9140100522176786e-05, 'samples': 23670336, 'steps': 123282, 'loss/train': 1.8213109970092773} 08/31/2021 11:37:38 - INFO - __main__ - Step 123284: {'lr': 3.9137249659165515e-05, 'samples': 23670528, 'steps': 123283, 'loss/train': 1.5831985473632812} 08/31/2021 11:37:39 - INFO - __main__ - Step 123285: {'lr': 3.913439889116574e-05, 'samples': 23670720, 'steps': 123284, 'loss/train': 1.3951078653335571} 08/31/2021 11:37:39 - INFO - __main__ - Step 123286: {'lr': 3.913154821817874e-05, 'samples': 23670912, 'steps': 123285, 'loss/train': 0.6268851161003113} 08/31/2021 11:37:39 - INFO - __main__ - Step 123287: {'lr': 3.912869764020583e-05, 'samples': 23671104, 'steps': 123286, 'loss/train': 0.17824813723564148} 08/31/2021 11:37:40 - INFO - __main__ - Step 123288: {'lr': 3.9125847157248264e-05, 'samples': 23671296, 'steps': 123287, 'loss/train': 1.4516607522964478} 08/31/2021 11:37:41 - INFO - __main__ - Step 123289: {'lr': 3.912299676930736e-05, 'samples': 23671488, 'steps': 123288, 'loss/train': 1.703742265701294} 08/31/2021 11:37:42 - INFO - __main__ - Step 123290: {'lr': 3.9120146476384344e-05, 'samples': 23671680, 'steps': 123289, 'loss/train': 0.116902656853199} 08/31/2021 11:37:42 - INFO - __main__ - Step 123291: {'lr': 3.911729627848057e-05, 'samples': 23671872, 'steps': 123290, 'loss/train': 1.2144696712493896} 08/31/2021 11:37:42 - INFO - __main__ - Step 123292: {'lr': 3.9114446175597254e-05, 'samples': 23672064, 'steps': 123291, 'loss/train': 1.2076689004898071} 08/31/2021 11:37:43 - INFO - __main__ - Step 123293: {'lr': 3.9111596167735796e-05, 'samples': 23672256, 'steps': 123292, 'loss/train': 1.489795207977295} 08/31/2021 11:37:45 - INFO - __main__ - Step 123294: {'lr': 3.9108746254897353e-05, 'samples': 23672448, 'steps': 123293, 'loss/train': 0.07937003672122955} 08/31/2021 11:37:45 - INFO - __main__ - Step 123295: {'lr': 3.9105896437083234e-05, 'samples': 23672640, 'steps': 123294, 'loss/train': 0.7847778797149658} 08/31/2021 11:37:46 - INFO - __main__ - Step 123296: {'lr': 3.910304671429474e-05, 'samples': 23672832, 'steps': 123295, 'loss/train': 0.6438305377960205} 08/31/2021 11:37:46 - INFO - __main__ - Step 123297: {'lr': 3.910019708653317e-05, 'samples': 23673024, 'steps': 123296, 'loss/train': 1.2045375108718872} 08/31/2021 11:37:46 - INFO - __main__ - Step 123298: {'lr': 3.909734755379979e-05, 'samples': 23673216, 'steps': 123297, 'loss/train': 0.5329611897468567} 08/31/2021 11:37:47 - INFO - __main__ - Step 123299: {'lr': 3.909449811609589e-05, 'samples': 23673408, 'steps': 123298, 'loss/train': 1.304381012916565} 08/31/2021 11:37:48 - INFO - __main__ - Step 123300: {'lr': 3.909164877342275e-05, 'samples': 23673600, 'steps': 123299, 'loss/train': 0.046340424567461014} 08/31/2021 11:37:49 - INFO - __main__ - Step 123301: {'lr': 3.908879952578168e-05, 'samples': 23673792, 'steps': 123300, 'loss/train': 1.1457223892211914} 08/31/2021 11:37:49 - INFO - __main__ - Step 123302: {'lr': 3.908595037317392e-05, 'samples': 23673984, 'steps': 123301, 'loss/train': 0.8342657685279846} 08/31/2021 11:37:50 - INFO - __main__ - Step 123303: {'lr': 3.908310131560078e-05, 'samples': 23674176, 'steps': 123302, 'loss/train': 1.039326548576355} 08/31/2021 11:37:50 - INFO - __main__ - Step 123304: {'lr': 3.908025235306356e-05, 'samples': 23674368, 'steps': 123303, 'loss/train': 2.3535022735595703} 08/31/2021 11:37:52 - INFO - __main__ - Step 123305: {'lr': 3.9077403485563576e-05, 'samples': 23674560, 'steps': 123304, 'loss/train': 1.1252378225326538} 08/31/2021 11:37:53 - INFO - __main__ - Step 123306: {'lr': 3.9074554713101976e-05, 'samples': 23674752, 'steps': 123305, 'loss/train': 0.827552855014801} 08/31/2021 11:37:53 - INFO - __main__ - Step 123307: {'lr': 3.9071706035680135e-05, 'samples': 23674944, 'steps': 123306, 'loss/train': 1.2012476921081543} 08/31/2021 11:37:53 - INFO - __main__ - Step 123308: {'lr': 3.9068857453299355e-05, 'samples': 23675136, 'steps': 123307, 'loss/train': 1.233835220336914} 08/31/2021 11:37:54 - INFO - __main__ - Step 123309: {'lr': 3.9066008965960856e-05, 'samples': 23675328, 'steps': 123308, 'loss/train': 1.2381343841552734} 08/31/2021 11:37:55 - INFO - __main__ - Step 123310: {'lr': 3.906316057366599e-05, 'samples': 23675520, 'steps': 123309, 'loss/train': 1.1649703979492188} 08/31/2021 11:37:56 - INFO - __main__ - Step 123311: {'lr': 3.906031227641599e-05, 'samples': 23675712, 'steps': 123310, 'loss/train': 1.2613427639007568} 08/31/2021 11:37:56 - INFO - __main__ - Step 123312: {'lr': 3.905746407421215e-05, 'samples': 23675904, 'steps': 123311, 'loss/train': 1.248732089996338} 08/31/2021 11:37:56 - INFO - __main__ - Step 123313: {'lr': 3.9054615967055786e-05, 'samples': 23676096, 'steps': 123312, 'loss/train': 0.8835040926933289} 08/31/2021 11:37:57 - INFO - __main__ - Step 123314: {'lr': 3.905176795494814e-05, 'samples': 23676288, 'steps': 123313, 'loss/train': 0.6355507373809814} 08/31/2021 11:37:59 - INFO - __main__ - Step 123315: {'lr': 3.9048920037890514e-05, 'samples': 23676480, 'steps': 123314, 'loss/train': 1.2854362726211548} 08/31/2021 11:37:59 - INFO - __main__ - Step 123316: {'lr': 3.904607221588427e-05, 'samples': 23676672, 'steps': 123315, 'loss/train': 2.1905696392059326} 08/31/2021 11:37:59 - INFO - __main__ - Step 123317: {'lr': 3.904322448893052e-05, 'samples': 23676864, 'steps': 123316, 'loss/train': 0.12095136195421219} 08/31/2021 11:38:00 - INFO - __main__ - Step 123318: {'lr': 3.9040376857030654e-05, 'samples': 23677056, 'steps': 123317, 'loss/train': 0.0966876894235611} 08/31/2021 11:38:00 - INFO - __main__ - Step 123319: {'lr': 3.903752932018595e-05, 'samples': 23677248, 'steps': 123318, 'loss/train': 0.43714386224746704} 08/31/2021 11:38:00 - INFO - __main__ - Step 123320: {'lr': 3.903468187839765e-05, 'samples': 23677440, 'steps': 123319, 'loss/train': 1.0737780332565308} 08/31/2021 11:38:02 - INFO - __main__ - Step 123321: {'lr': 3.9031834531667085e-05, 'samples': 23677632, 'steps': 123320, 'loss/train': 0.7789724469184875} 08/31/2021 11:38:02 - INFO - __main__ - Step 123322: {'lr': 3.9028987279995516e-05, 'samples': 23677824, 'steps': 123321, 'loss/train': 1.6643269062042236} 08/31/2021 11:38:03 - INFO - __main__ - Step 123323: {'lr': 3.902614012338423e-05, 'samples': 23678016, 'steps': 123322, 'loss/train': 0.746718168258667} 08/31/2021 11:38:03 - INFO - __main__ - Step 123324: {'lr': 3.902329306183453e-05, 'samples': 23678208, 'steps': 123323, 'loss/train': 0.2912842929363251} 08/31/2021 11:38:03 - INFO - __main__ - Step 123325: {'lr': 3.902044609534766e-05, 'samples': 23678400, 'steps': 123324, 'loss/train': 0.16055679321289062} 08/31/2021 11:38:05 - INFO - __main__ - Step 123326: {'lr': 3.901759922392498e-05, 'samples': 23678592, 'steps': 123325, 'loss/train': 1.102631688117981} 08/31/2021 11:38:05 - INFO - __main__ - Step 123327: {'lr': 3.901475244756766e-05, 'samples': 23678784, 'steps': 123326, 'loss/train': 2.4788711071014404} 08/31/2021 11:38:06 - INFO - __main__ - Step 123328: {'lr': 3.901190576627703e-05, 'samples': 23678976, 'steps': 123327, 'loss/train': 1.2501921653747559} 08/31/2021 11:38:06 - INFO - __main__ - Step 123329: {'lr': 3.9009059180054376e-05, 'samples': 23679168, 'steps': 123328, 'loss/train': 1.2702287435531616} 08/31/2021 11:38:06 - INFO - __main__ - Step 123330: {'lr': 3.9006212688901e-05, 'samples': 23679360, 'steps': 123329, 'loss/train': 1.128268837928772} 08/31/2021 11:38:08 - INFO - __main__ - Step 123331: {'lr': 3.9003366292818145e-05, 'samples': 23679552, 'steps': 123330, 'loss/train': 1.6381903886795044} 08/31/2021 11:38:08 - INFO - __main__ - Step 123332: {'lr': 3.900051999180715e-05, 'samples': 23679744, 'steps': 123331, 'loss/train': 2.0808379650115967} 08/31/2021 11:38:09 - INFO - __main__ - Step 123333: {'lr': 3.899767378586924e-05, 'samples': 23679936, 'steps': 123332, 'loss/train': 0.8891259431838989} 08/31/2021 11:38:09 - INFO - __main__ - Step 123334: {'lr': 3.899482767500573e-05, 'samples': 23680128, 'steps': 123333, 'loss/train': 1.1989811658859253} 08/31/2021 11:38:09 - INFO - __main__ - Step 123335: {'lr': 3.899198165921788e-05, 'samples': 23680320, 'steps': 123334, 'loss/train': 1.423438310623169} 08/31/2021 11:38:11 - INFO - __main__ - Step 123336: {'lr': 3.898913573850701e-05, 'samples': 23680512, 'steps': 123335, 'loss/train': 0.9203634858131409} 08/31/2021 11:38:11 - INFO - __main__ - Step 123337: {'lr': 3.8986289912874424e-05, 'samples': 23680704, 'steps': 123336, 'loss/train': 1.6228408813476562} 08/31/2021 11:38:12 - INFO - __main__ - Step 123338: {'lr': 3.8983444182321305e-05, 'samples': 23680896, 'steps': 123337, 'loss/train': 1.3760688304901123} 08/31/2021 11:38:12 - INFO - __main__ - Step 123339: {'lr': 3.898059854684899e-05, 'samples': 23681088, 'steps': 123338, 'loss/train': 0.8514046669006348} 08/31/2021 11:38:12 - INFO - __main__ - Step 123340: {'lr': 3.8977753006458785e-05, 'samples': 23681280, 'steps': 123339, 'loss/train': 0.935072124004364} 08/31/2021 11:38:14 - INFO - __main__ - Step 123341: {'lr': 3.8974907561151905e-05, 'samples': 23681472, 'steps': 123340, 'loss/train': 1.0941976308822632} 08/31/2021 11:38:14 - INFO - __main__ - Step 123342: {'lr': 3.897206221092969e-05, 'samples': 23681664, 'steps': 123341, 'loss/train': 1.0826884508132935} 08/31/2021 11:38:15 - INFO - __main__ - Step 123343: {'lr': 3.896921695579342e-05, 'samples': 23681856, 'steps': 123342, 'loss/train': 0.7056713104248047} 08/31/2021 11:38:15 - INFO - __main__ - Step 123344: {'lr': 3.896637179574436e-05, 'samples': 23682048, 'steps': 123343, 'loss/train': 0.6356576085090637} 08/31/2021 11:38:15 - INFO - __main__ - Step 123345: {'lr': 3.896352673078379e-05, 'samples': 23682240, 'steps': 123344, 'loss/train': 1.1288145780563354} 08/31/2021 11:38:16 - INFO - __main__ - Step 123346: {'lr': 3.8960681760912996e-05, 'samples': 23682432, 'steps': 123345, 'loss/train': 0.997301459312439} 08/31/2021 11:38:17 - INFO - __main__ - Step 123347: {'lr': 3.8957836886133276e-05, 'samples': 23682624, 'steps': 123346, 'loss/train': 0.7178688049316406} 08/31/2021 11:38:18 - INFO - __main__ - Step 123348: {'lr': 3.895499210644596e-05, 'samples': 23682816, 'steps': 123347, 'loss/train': 0.8031617999076843} 08/31/2021 11:38:18 - INFO - __main__ - Step 123349: {'lr': 3.895214742185219e-05, 'samples': 23683008, 'steps': 123348, 'loss/train': 5.732552528381348} 08/31/2021 11:38:19 - INFO - __main__ - Step 123350: {'lr': 3.8949302832353347e-05, 'samples': 23683200, 'steps': 123349, 'loss/train': 0.5730591416358948} 08/31/2021 11:38:19 - INFO - __main__ - Step 123351: {'lr': 3.894645833795066e-05, 'samples': 23683392, 'steps': 123350, 'loss/train': 1.1395564079284668} 08/31/2021 11:38:19 - INFO - __main__ - Step 123352: {'lr': 3.8943613938645456e-05, 'samples': 23683584, 'steps': 123351, 'loss/train': 0.9692618250846863} 08/31/2021 11:38:21 - INFO - __main__ - Step 123353: {'lr': 3.8940769634439014e-05, 'samples': 23683776, 'steps': 123352, 'loss/train': 1.3265581130981445} 08/31/2021 11:38:21 - INFO - __main__ - Step 123354: {'lr': 3.893792542533259e-05, 'samples': 23683968, 'steps': 123353, 'loss/train': 1.1041667461395264} 08/31/2021 11:38:22 - INFO - __main__ - Step 123355: {'lr': 3.89350813113275e-05, 'samples': 23684160, 'steps': 123354, 'loss/train': 1.1485365629196167} 08/31/2021 11:38:22 - INFO - __main__ - Step 123356: {'lr': 3.893223729242498e-05, 'samples': 23684352, 'steps': 123355, 'loss/train': 0.8715702295303345} 08/31/2021 11:38:22 - INFO - __main__ - Step 123357: {'lr': 3.892939336862636e-05, 'samples': 23684544, 'steps': 123356, 'loss/train': 1.750438928604126} 08/31/2021 11:38:24 - INFO - __main__ - Step 123358: {'lr': 3.892654953993288e-05, 'samples': 23684736, 'steps': 123357, 'loss/train': 0.048412442207336426} 08/31/2021 11:38:24 - INFO - __main__ - Step 123359: {'lr': 3.892370580634586e-05, 'samples': 23684928, 'steps': 123358, 'loss/train': 1.314671277999878} 08/31/2021 11:38:25 - INFO - __main__ - Step 123360: {'lr': 3.892086216786655e-05, 'samples': 23685120, 'steps': 123359, 'loss/train': 0.6900481581687927} 08/31/2021 11:38:25 - INFO - __main__ - Step 123361: {'lr': 3.891801862449629e-05, 'samples': 23685312, 'steps': 123360, 'loss/train': 1.1572641134262085} 08/31/2021 11:38:25 - INFO - __main__ - Step 123362: {'lr': 3.891517517623627e-05, 'samples': 23685504, 'steps': 123361, 'loss/train': 1.2507007122039795} 08/31/2021 11:38:27 - INFO - __main__ - Step 123363: {'lr': 3.8912331823087815e-05, 'samples': 23685696, 'steps': 123362, 'loss/train': 0.8972105979919434} 08/31/2021 11:38:28 - INFO - __main__ - Step 123364: {'lr': 3.8909488565052194e-05, 'samples': 23685888, 'steps': 123363, 'loss/train': 1.1973992586135864} 08/31/2021 11:38:28 - INFO - __main__ - Step 123365: {'lr': 3.890664540213071e-05, 'samples': 23686080, 'steps': 123364, 'loss/train': 0.057120390236377716} 08/31/2021 11:38:29 - INFO - __main__ - Step 123366: {'lr': 3.890380233432464e-05, 'samples': 23686272, 'steps': 123365, 'loss/train': 0.7054857611656189} 08/31/2021 11:38:29 - INFO - __main__ - Step 123367: {'lr': 3.8900959361635235e-05, 'samples': 23686464, 'steps': 123366, 'loss/train': 0.8679620623588562} 08/31/2021 11:38:29 - INFO - __main__ - Step 123368: {'lr': 3.889811648406383e-05, 'samples': 23686656, 'steps': 123367, 'loss/train': 1.2828019857406616} 08/31/2021 11:38:31 - INFO - __main__ - Step 123369: {'lr': 3.889527370161164e-05, 'samples': 23686848, 'steps': 123368, 'loss/train': 0.8033934235572815} 08/31/2021 11:38:31 - INFO - __main__ - Step 123370: {'lr': 3.889243101428e-05, 'samples': 23687040, 'steps': 123369, 'loss/train': 0.9070836901664734} 08/31/2021 11:38:32 - INFO - __main__ - Step 123371: {'lr': 3.888958842207019e-05, 'samples': 23687232, 'steps': 123370, 'loss/train': 1.0325632095336914} 08/31/2021 11:38:32 - INFO - __main__ - Step 123372: {'lr': 3.888674592498345e-05, 'samples': 23687424, 'steps': 123371, 'loss/train': 0.9554857611656189} 08/31/2021 11:38:32 - INFO - __main__ - Step 123373: {'lr': 3.88839035230211e-05, 'samples': 23687616, 'steps': 123372, 'loss/train': 1.3187776803970337} 08/31/2021 11:38:34 - INFO - __main__ - Step 123374: {'lr': 3.8881061216184454e-05, 'samples': 23687808, 'steps': 123373, 'loss/train': 1.4088116884231567} 08/31/2021 11:38:34 - INFO - __main__ - Step 123375: {'lr': 3.8878219004474694e-05, 'samples': 23688000, 'steps': 123374, 'loss/train': 0.9640507698059082} 08/31/2021 11:38:35 - INFO - __main__ - Step 123376: {'lr': 3.8875376887893164e-05, 'samples': 23688192, 'steps': 123375, 'loss/train': 1.003823161125183} 08/31/2021 11:38:35 - INFO - __main__ - Step 123377: {'lr': 3.88725348664411e-05, 'samples': 23688384, 'steps': 123376, 'loss/train': 0.7657250165939331} 08/31/2021 11:38:35 - INFO - __main__ - Step 123378: {'lr': 3.8869692940119825e-05, 'samples': 23688576, 'steps': 123377, 'loss/train': 1.144576907157898} 08/31/2021 11:38:37 - INFO - __main__ - Step 123379: {'lr': 3.8866851108930624e-05, 'samples': 23688768, 'steps': 123378, 'loss/train': 0.7968835234642029} 08/31/2021 11:38:37 - INFO - __main__ - Step 123380: {'lr': 3.8864009372874736e-05, 'samples': 23688960, 'steps': 123379, 'loss/train': 1.3008971214294434} 08/31/2021 11:38:38 - INFO - __main__ - Step 123381: {'lr': 3.88611677319535e-05, 'samples': 23689152, 'steps': 123380, 'loss/train': 1.0036091804504395} 08/31/2021 11:38:38 - INFO - __main__ - Step 123382: {'lr': 3.8858326186168136e-05, 'samples': 23689344, 'steps': 123381, 'loss/train': 0.8876710534095764} 08/31/2021 11:38:38 - INFO - __main__ - Step 123383: {'lr': 3.8855484735519946e-05, 'samples': 23689536, 'steps': 123382, 'loss/train': 0.25866085290908813} 08/31/2021 11:38:40 - INFO - __main__ - Step 123384: {'lr': 3.885264338001024e-05, 'samples': 23689728, 'steps': 123383, 'loss/train': 0.7508058547973633} 08/31/2021 11:38:40 - INFO - __main__ - Step 123385: {'lr': 3.884980211964026e-05, 'samples': 23689920, 'steps': 123384, 'loss/train': 0.9649285674095154} 08/31/2021 11:38:41 - INFO - __main__ - Step 123386: {'lr': 3.8846960954411314e-05, 'samples': 23690112, 'steps': 123385, 'loss/train': 1.5415033102035522} 08/31/2021 11:38:41 - INFO - __main__ - Step 123387: {'lr': 3.884411988432468e-05, 'samples': 23690304, 'steps': 123386, 'loss/train': 0.7671276330947876} 08/31/2021 11:38:42 - INFO - __main__ - Step 123388: {'lr': 3.8841278909381664e-05, 'samples': 23690496, 'steps': 123387, 'loss/train': 1.2021777629852295} 08/31/2021 11:38:42 - INFO - __main__ - Step 123389: {'lr': 3.8838438029583454e-05, 'samples': 23690688, 'steps': 123388, 'loss/train': 0.9613783955574036} 08/31/2021 11:38:43 - INFO - __main__ - Step 123390: {'lr': 3.8835597244931384e-05, 'samples': 23690880, 'steps': 123389, 'loss/train': 0.9017192721366882} 08/31/2021 11:38:44 - INFO - __main__ - Step 123391: {'lr': 3.883275655542673e-05, 'samples': 23691072, 'steps': 123390, 'loss/train': 1.359482765197754} 08/31/2021 11:38:44 - INFO - __main__ - Step 123392: {'lr': 3.88299159610708e-05, 'samples': 23691264, 'steps': 123391, 'loss/train': 0.7659651041030884} 08/31/2021 11:38:45 - INFO - __main__ - Step 123393: {'lr': 3.882707546186481e-05, 'samples': 23691456, 'steps': 123392, 'loss/train': 1.2250418663024902} 08/31/2021 11:38:45 - INFO - __main__ - Step 123394: {'lr': 3.882423505781013e-05, 'samples': 23691648, 'steps': 123393, 'loss/train': 1.073877215385437} 08/31/2021 11:38:46 - INFO - __main__ - Step 123395: {'lr': 3.882139474890797e-05, 'samples': 23691840, 'steps': 123394, 'loss/train': 1.0345124006271362} 08/31/2021 11:38:47 - INFO - __main__ - Step 123396: {'lr': 3.881855453515962e-05, 'samples': 23692032, 'steps': 123395, 'loss/train': 1.660703182220459} 08/31/2021 11:38:47 - INFO - __main__ - Step 123397: {'lr': 3.8815714416566365e-05, 'samples': 23692224, 'steps': 123396, 'loss/train': 1.338614821434021} 08/31/2021 11:38:48 - INFO - __main__ - Step 123398: {'lr': 3.8812874393129524e-05, 'samples': 23692416, 'steps': 123397, 'loss/train': 0.05216464400291443} 08/31/2021 11:38:48 - INFO - __main__ - Step 123399: {'lr': 3.881003446485032e-05, 'samples': 23692608, 'steps': 123398, 'loss/train': 0.45564842224121094} 08/31/2021 11:38:49 - INFO - __main__ - Step 123400: {'lr': 3.880719463173005e-05, 'samples': 23692800, 'steps': 123399, 'loss/train': 0.9933552742004395} 08/31/2021 11:38:50 - INFO - __main__ - Step 123401: {'lr': 3.880435489377007e-05, 'samples': 23692992, 'steps': 123400, 'loss/train': 1.0887277126312256} 08/31/2021 11:38:50 - INFO - __main__ - Step 123402: {'lr': 3.880151525097153e-05, 'samples': 23693184, 'steps': 123401, 'loss/train': 1.232106328010559} 08/31/2021 11:38:51 - INFO - __main__ - Step 123403: {'lr': 3.879867570333578e-05, 'samples': 23693376, 'steps': 123402, 'loss/train': 1.5311336517333984} 08/31/2021 11:38:51 - INFO - __main__ - Step 123404: {'lr': 3.879583625086405e-05, 'samples': 23693568, 'steps': 123403, 'loss/train': 1.5992255210876465} 08/31/2021 11:38:52 - INFO - __main__ - Step 123405: {'lr': 3.87929968935577e-05, 'samples': 23693760, 'steps': 123404, 'loss/train': 1.5725873708724976} 08/31/2021 11:38:53 - INFO - __main__ - Step 123406: {'lr': 3.879015763141794e-05, 'samples': 23693952, 'steps': 123405, 'loss/train': 1.044906735420227} 08/31/2021 11:38:53 - INFO - __main__ - Step 123407: {'lr': 3.878731846444608e-05, 'samples': 23694144, 'steps': 123406, 'loss/train': 0.7987353801727295} 08/31/2021 11:38:54 - INFO - __main__ - Step 123408: {'lr': 3.87844793926434e-05, 'samples': 23694336, 'steps': 123407, 'loss/train': 1.114786148071289} 08/31/2021 11:38:54 - INFO - __main__ - Step 123409: {'lr': 3.8781640416011176e-05, 'samples': 23694528, 'steps': 123408, 'loss/train': 1.4845664501190186} 08/31/2021 11:38:56 - INFO - __main__ - Step 123410: {'lr': 3.877880153455069e-05, 'samples': 23694720, 'steps': 123409, 'loss/train': 1.8828518390655518} 08/31/2021 11:38:56 - INFO - __main__ - Step 123411: {'lr': 3.87759627482632e-05, 'samples': 23694912, 'steps': 123410, 'loss/train': 0.6323467493057251} 08/31/2021 11:38:57 - INFO - __main__ - Step 123412: {'lr': 3.877312405715003e-05, 'samples': 23695104, 'steps': 123411, 'loss/train': 1.0281883478164673} 08/31/2021 11:38:57 - INFO - __main__ - Step 123413: {'lr': 3.877028546121239e-05, 'samples': 23695296, 'steps': 123412, 'loss/train': 1.3056938648223877} 08/31/2021 11:38:57 - INFO - __main__ - Step 123414: {'lr': 3.876744696045167e-05, 'samples': 23695488, 'steps': 123413, 'loss/train': 0.026492632925510406} 08/31/2021 11:38:58 - INFO - __main__ - Step 123415: {'lr': 3.8764608554869044e-05, 'samples': 23695680, 'steps': 123414, 'loss/train': 0.02813282236456871} 08/31/2021 11:38:58 - INFO - __main__ - Step 123416: {'lr': 3.876177024446581e-05, 'samples': 23695872, 'steps': 123415, 'loss/train': 1.549560308456421} 08/31/2021 11:39:00 - INFO - __main__ - Step 123417: {'lr': 3.875893202924327e-05, 'samples': 23696064, 'steps': 123416, 'loss/train': 1.8524246215820312} 08/31/2021 11:39:01 - INFO - __main__ - Step 123418: {'lr': 3.875609390920268e-05, 'samples': 23696256, 'steps': 123417, 'loss/train': 0.9487571120262146} 08/31/2021 11:39:01 - INFO - __main__ - Step 123419: {'lr': 3.875325588434536e-05, 'samples': 23696448, 'steps': 123418, 'loss/train': 1.1226195096969604} 08/31/2021 11:39:02 - INFO - __main__ - Step 123420: {'lr': 3.8750417954672546e-05, 'samples': 23696640, 'steps': 123419, 'loss/train': 1.7336708307266235} 08/31/2021 11:39:02 - INFO - __main__ - Step 123421: {'lr': 3.874758012018553e-05, 'samples': 23696832, 'steps': 123420, 'loss/train': 1.3008605241775513} 08/31/2021 11:39:04 - INFO - __main__ - Step 123422: {'lr': 3.87447423808856e-05, 'samples': 23697024, 'steps': 123421, 'loss/train': 1.6257777214050293} 08/31/2021 11:39:04 - INFO - __main__ - Step 123423: {'lr': 3.8741904736774025e-05, 'samples': 23697216, 'steps': 123422, 'loss/train': 0.6682897210121155} 08/31/2021 11:39:05 - INFO - __main__ - Step 123424: {'lr': 3.8739067187852114e-05, 'samples': 23697408, 'steps': 123423, 'loss/train': 0.5811607837677002} 08/31/2021 11:39:05 - INFO - __main__ - Step 123425: {'lr': 3.873622973412108e-05, 'samples': 23697600, 'steps': 123424, 'loss/train': 0.8530173897743225} 08/31/2021 11:39:05 - INFO - __main__ - Step 123426: {'lr': 3.8733392375582265e-05, 'samples': 23697792, 'steps': 123425, 'loss/train': 0.4867662191390991} 08/31/2021 11:39:07 - INFO - __main__ - Step 123427: {'lr': 3.8730555112236916e-05, 'samples': 23697984, 'steps': 123426, 'loss/train': 0.5401865839958191} 08/31/2021 11:39:07 - INFO - __main__ - Step 123428: {'lr': 3.872771794408639e-05, 'samples': 23698176, 'steps': 123427, 'loss/train': 0.037266068160533905} 08/31/2021 11:39:08 - INFO - __main__ - Step 123429: {'lr': 3.8724880871131825e-05, 'samples': 23698368, 'steps': 123428, 'loss/train': 1.606339454650879} 08/31/2021 11:39:08 - INFO - __main__ - Step 123430: {'lr': 3.872204389337455e-05, 'samples': 23698560, 'steps': 123429, 'loss/train': 1.3253369331359863} 08/31/2021 11:39:08 - INFO - __main__ - Step 123431: {'lr': 3.8719207010815885e-05, 'samples': 23698752, 'steps': 123430, 'loss/train': 0.6560402512550354} 08/31/2021 11:39:10 - INFO - __main__ - Step 123432: {'lr': 3.871637022345709e-05, 'samples': 23698944, 'steps': 123431, 'loss/train': 0.8337252140045166} 08/31/2021 11:39:10 - INFO - __main__ - Step 123433: {'lr': 3.8713533531299415e-05, 'samples': 23699136, 'steps': 123432, 'loss/train': 1.3193089962005615} 08/31/2021 11:39:11 - INFO - __main__ - Step 123434: {'lr': 3.871069693434417e-05, 'samples': 23699328, 'steps': 123433, 'loss/train': 0.8433834910392761} 08/31/2021 11:39:11 - INFO - __main__ - Step 123435: {'lr': 3.870786043259264e-05, 'samples': 23699520, 'steps': 123434, 'loss/train': 1.2772570848464966} 08/31/2021 11:39:11 - INFO - __main__ - Step 123436: {'lr': 3.870502402604606e-05, 'samples': 23699712, 'steps': 123435, 'loss/train': 1.2712165117263794} 08/31/2021 11:39:12 - INFO - __main__ - Step 123437: {'lr': 3.870218771470577e-05, 'samples': 23699904, 'steps': 123436, 'loss/train': 1.7845211029052734} 08/31/2021 11:39:13 - INFO - __main__ - Step 123438: {'lr': 3.869935149857298e-05, 'samples': 23700096, 'steps': 123437, 'loss/train': 0.9680631756782532} 08/31/2021 11:39:13 - INFO - __main__ - Step 123439: {'lr': 3.869651537764901e-05, 'samples': 23700288, 'steps': 123438, 'loss/train': 1.4746170043945312} 08/31/2021 11:39:14 - INFO - __main__ - Step 123440: {'lr': 3.869367935193516e-05, 'samples': 23700480, 'steps': 123439, 'loss/train': 0.9826545715332031} 08/31/2021 11:39:14 - INFO - __main__ - Step 123441: {'lr': 3.8690843421432695e-05, 'samples': 23700672, 'steps': 123440, 'loss/train': 1.0163251161575317} 08/31/2021 11:39:14 - INFO - __main__ - Step 123442: {'lr': 3.8688007586142854e-05, 'samples': 23700864, 'steps': 123441, 'loss/train': 0.8199314475059509} 08/31/2021 11:39:16 - INFO - __main__ - Step 123443: {'lr': 3.8685171846066904e-05, 'samples': 23701056, 'steps': 123442, 'loss/train': 1.1539826393127441} 08/31/2021 11:39:16 - INFO - __main__ - Step 123444: {'lr': 3.868233620120618e-05, 'samples': 23701248, 'steps': 123443, 'loss/train': 0.8812079429626465} 08/31/2021 11:39:17 - INFO - __main__ - Step 123445: {'lr': 3.867950065156192e-05, 'samples': 23701440, 'steps': 123444, 'loss/train': 1.2728395462036133} 08/31/2021 11:39:17 - INFO - __main__ - Step 123446: {'lr': 3.867666519713542e-05, 'samples': 23701632, 'steps': 123445, 'loss/train': 1.7072089910507202} 08/31/2021 11:39:17 - INFO - __main__ - Step 123447: {'lr': 3.867382983792794e-05, 'samples': 23701824, 'steps': 123446, 'loss/train': 1.1649360656738281} 08/31/2021 11:39:19 - INFO - __main__ - Step 123448: {'lr': 3.867099457394077e-05, 'samples': 23702016, 'steps': 123447, 'loss/train': 1.1679612398147583} 08/31/2021 11:39:19 - INFO - __main__ - Step 123449: {'lr': 3.8668159405175206e-05, 'samples': 23702208, 'steps': 123448, 'loss/train': 1.0599638223648071} 08/31/2021 11:39:20 - INFO - __main__ - Step 123450: {'lr': 3.8665324331632504e-05, 'samples': 23702400, 'steps': 123449, 'loss/train': 1.318299412727356} 08/31/2021 11:39:20 - INFO - __main__ - Step 123451: {'lr': 3.866248935331396e-05, 'samples': 23702592, 'steps': 123450, 'loss/train': 1.1728028059005737} 08/31/2021 11:39:20 - INFO - __main__ - Step 123452: {'lr': 3.8659654470220826e-05, 'samples': 23702784, 'steps': 123451, 'loss/train': 1.1521750688552856} 08/31/2021 11:39:22 - INFO - __main__ - Step 123453: {'lr': 3.865681968235438e-05, 'samples': 23702976, 'steps': 123452, 'loss/train': 1.7191427946090698} 08/31/2021 11:39:22 - INFO - __main__ - Step 123454: {'lr': 3.865398498971592e-05, 'samples': 23703168, 'steps': 123453, 'loss/train': 0.32149171829223633} 08/31/2021 11:39:23 - INFO - __main__ - Step 123455: {'lr': 3.865115039230677e-05, 'samples': 23703360, 'steps': 123454, 'loss/train': 0.9245429635047913} 08/31/2021 11:39:23 - INFO - __main__ - Step 123456: {'lr': 3.86483158901281e-05, 'samples': 23703552, 'steps': 123455, 'loss/train': 1.272452473640442} 08/31/2021 11:39:23 - INFO - __main__ - Step 123457: {'lr': 3.8645481483181226e-05, 'samples': 23703744, 'steps': 123456, 'loss/train': 1.5598769187927246} 08/31/2021 11:39:25 - INFO - __main__ - Step 123458: {'lr': 3.8642647171467424e-05, 'samples': 23703936, 'steps': 123457, 'loss/train': 1.1254420280456543} 08/31/2021 11:39:26 - INFO - __main__ - Step 123459: {'lr': 3.8639812954988e-05, 'samples': 23704128, 'steps': 123458, 'loss/train': 0.9927873611450195} 08/31/2021 11:39:26 - INFO - __main__ - Step 123460: {'lr': 3.863697883374423e-05, 'samples': 23704320, 'steps': 123459, 'loss/train': 1.9938548803329468} 08/31/2021 11:39:26 - INFO - __main__ - Step 123461: {'lr': 3.863414480773736e-05, 'samples': 23704512, 'steps': 123460, 'loss/train': 1.3598757982254028} 08/31/2021 11:39:27 - INFO - __main__ - Step 123462: {'lr': 3.863131087696867e-05, 'samples': 23704704, 'steps': 123461, 'loss/train': 1.0527522563934326} 08/31/2021 11:39:28 - INFO - __main__ - Step 123463: {'lr': 3.8628477041439456e-05, 'samples': 23704896, 'steps': 123462, 'loss/train': 0.9218457937240601} 08/31/2021 11:39:29 - INFO - __main__ - Step 123464: {'lr': 3.862564330115101e-05, 'samples': 23705088, 'steps': 123463, 'loss/train': 2.89628005027771} 08/31/2021 11:39:29 - INFO - __main__ - Step 123465: {'lr': 3.862280965610457e-05, 'samples': 23705280, 'steps': 123464, 'loss/train': 4.6111907958984375} 08/31/2021 11:39:30 - INFO - __main__ - Step 123466: {'lr': 3.8619976106301416e-05, 'samples': 23705472, 'steps': 123465, 'loss/train': 1.8886213302612305} 08/31/2021 11:39:30 - INFO - __main__ - Step 123467: {'lr': 3.8617142651742876e-05, 'samples': 23705664, 'steps': 123466, 'loss/train': 0.6124347448348999} 08/31/2021 11:39:30 - INFO - __main__ - Step 123468: {'lr': 3.86143092924302e-05, 'samples': 23705856, 'steps': 123467, 'loss/train': 1.563646674156189} 08/31/2021 11:39:32 - INFO - __main__ - Step 123469: {'lr': 3.861147602836465e-05, 'samples': 23706048, 'steps': 123468, 'loss/train': 1.8698803186416626} 08/31/2021 11:39:33 - INFO - __main__ - Step 123470: {'lr': 3.860864285954746e-05, 'samples': 23706240, 'steps': 123469, 'loss/train': 0.906548798084259} 08/31/2021 11:39:33 - INFO - __main__ - Step 123471: {'lr': 3.860580978597999e-05, 'samples': 23706432, 'steps': 123470, 'loss/train': 0.18155963718891144} 08/31/2021 11:39:34 - INFO - __main__ - Step 123472: {'lr': 3.860297680766345e-05, 'samples': 23706624, 'steps': 123471, 'loss/train': 1.009196400642395} 08/31/2021 11:39:34 - INFO - __main__ - Step 123473: {'lr': 3.860014392459918e-05, 'samples': 23706816, 'steps': 123472, 'loss/train': 1.370568871498108} 08/31/2021 11:39:34 - INFO - __main__ - Step 123474: {'lr': 3.859731113678838e-05, 'samples': 23707008, 'steps': 123473, 'loss/train': 1.1303735971450806} 08/31/2021 11:39:36 - INFO - __main__ - Step 123475: {'lr': 3.859447844423242e-05, 'samples': 23707200, 'steps': 123474, 'loss/train': 1.087459921836853} 08/31/2021 11:39:36 - INFO - __main__ - Step 123476: {'lr': 3.859164584693248e-05, 'samples': 23707392, 'steps': 123475, 'loss/train': 1.6045609712600708} 08/31/2021 11:39:37 - INFO - __main__ - Step 123477: {'lr': 3.8588813344889896e-05, 'samples': 23707584, 'steps': 123476, 'loss/train': 0.38859662413597107} 08/31/2021 11:39:37 - INFO - __main__ - Step 123478: {'lr': 3.858598093810595e-05, 'samples': 23707776, 'steps': 123477, 'loss/train': 0.9494748115539551} 08/31/2021 11:39:37 - INFO - __main__ - Step 123479: {'lr': 3.858314862658188e-05, 'samples': 23707968, 'steps': 123478, 'loss/train': 0.12842302024364471} 08/31/2021 11:39:39 - INFO - __main__ - Step 123480: {'lr': 3.858031641031898e-05, 'samples': 23708160, 'steps': 123479, 'loss/train': 1.5236643552780151} 08/31/2021 11:39:39 - INFO - __main__ - Step 123481: {'lr': 3.857748428931854e-05, 'samples': 23708352, 'steps': 123480, 'loss/train': 0.9636071920394897} 08/31/2021 11:39:40 - INFO - __main__ - Step 123482: {'lr': 3.8574652263581865e-05, 'samples': 23708544, 'steps': 123481, 'loss/train': 0.8966200351715088} 08/31/2021 11:39:40 - INFO - __main__ - Step 123483: {'lr': 3.857182033311013e-05, 'samples': 23708736, 'steps': 123482, 'loss/train': 1.6042083501815796} 08/31/2021 11:39:40 - INFO - __main__ - Step 123484: {'lr': 3.8568988497904686e-05, 'samples': 23708928, 'steps': 123483, 'loss/train': 1.1165574789047241} 08/31/2021 11:39:42 - INFO - __main__ - Step 123485: {'lr': 3.856615675796679e-05, 'samples': 23709120, 'steps': 123484, 'loss/train': 1.6014786958694458} 08/31/2021 11:39:42 - INFO - __main__ - Step 123486: {'lr': 3.8563325113297717e-05, 'samples': 23709312, 'steps': 123485, 'loss/train': 0.693026065826416} 08/31/2021 11:39:43 - INFO - __main__ - Step 123487: {'lr': 3.8560493563898766e-05, 'samples': 23709504, 'steps': 123486, 'loss/train': 1.1927415132522583} 08/31/2021 11:39:43 - INFO - __main__ - Step 123488: {'lr': 3.8557662109771155e-05, 'samples': 23709696, 'steps': 123487, 'loss/train': 1.4012748003005981} 08/31/2021 11:39:43 - INFO - __main__ - Step 123489: {'lr': 3.855483075091623e-05, 'samples': 23709888, 'steps': 123488, 'loss/train': 0.7819923758506775} 08/31/2021 11:39:45 - INFO - __main__ - Step 123490: {'lr': 3.855199948733523e-05, 'samples': 23710080, 'steps': 123489, 'loss/train': 2.02112078666687} 08/31/2021 11:39:46 - INFO - __main__ - Step 123491: {'lr': 3.854916831902941e-05, 'samples': 23710272, 'steps': 123490, 'loss/train': 0.5698391199111938} 08/31/2021 11:39:46 - INFO - __main__ - Step 123492: {'lr': 3.8546337246000094e-05, 'samples': 23710464, 'steps': 123491, 'loss/train': 1.476353406906128} 08/31/2021 11:39:47 - INFO - __main__ - Step 123493: {'lr': 3.854350626824854e-05, 'samples': 23710656, 'steps': 123492, 'loss/train': 0.9220278263092041} 08/31/2021 11:39:47 - INFO - __main__ - Step 123494: {'lr': 3.854067538577602e-05, 'samples': 23710848, 'steps': 123493, 'loss/train': 0.930210530757904} 08/31/2021 11:39:47 - INFO - __main__ - Step 123495: {'lr': 3.853784459858387e-05, 'samples': 23711040, 'steps': 123494, 'loss/train': 0.6431796550750732} 08/31/2021 11:39:48 - INFO - __main__ - Step 123496: {'lr': 3.853501390667321e-05, 'samples': 23711232, 'steps': 123495, 'loss/train': 0.016293782740831375} 08/31/2021 11:39:49 - INFO - __main__ - Step 123497: {'lr': 3.853218331004546e-05, 'samples': 23711424, 'steps': 123496, 'loss/train': 0.014028279110789299} 08/31/2021 11:39:50 - INFO - __main__ - Step 123498: {'lr': 3.852935280870182e-05, 'samples': 23711616, 'steps': 123497, 'loss/train': 0.8439258933067322} 08/31/2021 11:39:50 - INFO - __main__ - Step 123499: {'lr': 3.8526522402643594e-05, 'samples': 23711808, 'steps': 123498, 'loss/train': 1.578671932220459} 08/31/2021 11:39:50 - INFO - __main__ - Step 123500: {'lr': 3.8523692091872036e-05, 'samples': 23712000, 'steps': 123499, 'loss/train': 1.309291124343872} 08/31/2021 11:39:51 - INFO - __main__ - Step 123501: {'lr': 3.852086187638845e-05, 'samples': 23712192, 'steps': 123500, 'loss/train': 0.829667329788208} 08/31/2021 11:39:52 - INFO - __main__ - Step 123502: {'lr': 3.8518031756194116e-05, 'samples': 23712384, 'steps': 123501, 'loss/train': 1.393108606338501} 08/31/2021 11:39:53 - INFO - __main__ - Step 123503: {'lr': 3.8515201731290275e-05, 'samples': 23712576, 'steps': 123502, 'loss/train': 0.5195378661155701} 08/31/2021 11:39:53 - INFO - __main__ - Step 123504: {'lr': 3.8512371801678244e-05, 'samples': 23712768, 'steps': 123503, 'loss/train': 2.6421539783477783} 08/31/2021 11:39:54 - INFO - __main__ - Step 123505: {'lr': 3.8509541967359256e-05, 'samples': 23712960, 'steps': 123504, 'loss/train': 1.3603609800338745} 08/31/2021 11:39:54 - INFO - __main__ - Step 123506: {'lr': 3.85067122283346e-05, 'samples': 23713152, 'steps': 123505, 'loss/train': 1.0572291612625122} 08/31/2021 11:39:56 - INFO - __main__ - Step 123507: {'lr': 3.850388258460555e-05, 'samples': 23713344, 'steps': 123506, 'loss/train': 1.1103575229644775} 08/31/2021 11:39:57 - INFO - __main__ - Step 123508: {'lr': 3.8501053036173404e-05, 'samples': 23713536, 'steps': 123507, 'loss/train': 1.1238677501678467} 08/31/2021 11:39:57 - INFO - __main__ - Step 123509: {'lr': 3.8498223583039476e-05, 'samples': 23713728, 'steps': 123508, 'loss/train': 1.256524682044983} 08/31/2021 11:39:57 - INFO - __main__ - Step 123510: {'lr': 3.8495394225204927e-05, 'samples': 23713920, 'steps': 123509, 'loss/train': 1.1101405620574951} 08/31/2021 11:39:58 - INFO - __main__ - Step 123511: {'lr': 3.849256496267109e-05, 'samples': 23714112, 'steps': 123510, 'loss/train': 1.1950464248657227} 08/31/2021 11:39:58 - INFO - __main__ - Step 123512: {'lr': 3.848973579543924e-05, 'samples': 23714304, 'steps': 123511, 'loss/train': 1.1467186212539673} 08/31/2021 11:39:59 - INFO - __main__ - Step 123513: {'lr': 3.8486906723510657e-05, 'samples': 23714496, 'steps': 123512, 'loss/train': 0.03575121983885765} 08/31/2021 11:40:00 - INFO - __main__ - Step 123514: {'lr': 3.8484077746886585e-05, 'samples': 23714688, 'steps': 123513, 'loss/train': 0.8973948955535889} 08/31/2021 11:40:00 - INFO - __main__ - Step 123515: {'lr': 3.848124886556834e-05, 'samples': 23714880, 'steps': 123514, 'loss/train': 1.2937182188034058} 08/31/2021 11:40:01 - INFO - __main__ - Step 123516: {'lr': 3.847842007955718e-05, 'samples': 23715072, 'steps': 123515, 'loss/train': 0.8812005519866943} 08/31/2021 11:40:01 - INFO - __main__ - Step 123517: {'lr': 3.84755913888544e-05, 'samples': 23715264, 'steps': 123516, 'loss/train': 1.2617392539978027} 08/31/2021 11:40:03 - INFO - __main__ - Step 123518: {'lr': 3.8472762793461235e-05, 'samples': 23715456, 'steps': 123517, 'loss/train': 1.445920705795288} 08/31/2021 11:40:03 - INFO - __main__ - Step 123519: {'lr': 3.846993429337897e-05, 'samples': 23715648, 'steps': 123518, 'loss/train': 1.2716295719146729} 08/31/2021 11:40:03 - INFO - __main__ - Step 123520: {'lr': 3.8467105888608885e-05, 'samples': 23715840, 'steps': 123519, 'loss/train': 1.1892701387405396} 08/31/2021 11:40:04 - INFO - __main__ - Step 123521: {'lr': 3.846427757915227e-05, 'samples': 23716032, 'steps': 123520, 'loss/train': 1.3148820400238037} 08/31/2021 11:40:04 - INFO - __main__ - Step 123522: {'lr': 3.846144936501045e-05, 'samples': 23716224, 'steps': 123521, 'loss/train': 1.078510046005249} 08/31/2021 11:40:04 - INFO - __main__ - Step 123523: {'lr': 3.845862124618457e-05, 'samples': 23716416, 'steps': 123522, 'loss/train': 1.1572368144989014} 08/31/2021 11:40:06 - INFO - __main__ - Step 123524: {'lr': 3.8455793222675976e-05, 'samples': 23716608, 'steps': 123523, 'loss/train': 0.8006024360656738} 08/31/2021 11:40:07 - INFO - __main__ - Step 123525: {'lr': 3.845296529448594e-05, 'samples': 23716800, 'steps': 123524, 'loss/train': 0.6695666909217834} 08/31/2021 11:40:07 - INFO - __main__ - Step 123526: {'lr': 3.845013746161574e-05, 'samples': 23716992, 'steps': 123525, 'loss/train': 0.1682075560092926} 08/31/2021 11:40:08 - INFO - __main__ - Step 123527: {'lr': 3.8447309724066625e-05, 'samples': 23717184, 'steps': 123526, 'loss/train': 0.37582704424858093} 08/31/2021 11:40:08 - INFO - __main__ - Step 123528: {'lr': 3.84444820818399e-05, 'samples': 23717376, 'steps': 123527, 'loss/train': 0.7501022815704346} 08/31/2021 11:40:10 - INFO - __main__ - Step 123529: {'lr': 3.8441654534936837e-05, 'samples': 23717568, 'steps': 123528, 'loss/train': 1.3976982831954956} 08/31/2021 11:40:10 - INFO - __main__ - Step 123530: {'lr': 3.843882708335866e-05, 'samples': 23717760, 'steps': 123529, 'loss/train': 0.5558077096939087} 08/31/2021 11:40:10 - INFO - __main__ - Step 123531: {'lr': 3.8435999727106736e-05, 'samples': 23717952, 'steps': 123530, 'loss/train': 0.9973818063735962} 08/31/2021 11:40:11 - INFO - __main__ - Step 123532: {'lr': 3.843317246618225e-05, 'samples': 23718144, 'steps': 123531, 'loss/train': 1.1412968635559082} 08/31/2021 11:40:11 - INFO - __main__ - Step 123533: {'lr': 3.843034530058651e-05, 'samples': 23718336, 'steps': 123532, 'loss/train': 0.8017663955688477} 08/31/2021 11:40:13 - INFO - __main__ - Step 123534: {'lr': 3.8427518230320815e-05, 'samples': 23718528, 'steps': 123533, 'loss/train': 0.22607316076755524} 08/31/2021 11:40:13 - INFO - __main__ - Step 123535: {'lr': 3.8424691255386444e-05, 'samples': 23718720, 'steps': 123534, 'loss/train': 1.4307554960250854} 08/31/2021 11:40:14 - INFO - __main__ - Step 123536: {'lr': 3.842186437578463e-05, 'samples': 23718912, 'steps': 123535, 'loss/train': 1.2292500734329224} 08/31/2021 11:40:14 - INFO - __main__ - Step 123537: {'lr': 3.84190375915166e-05, 'samples': 23719104, 'steps': 123536, 'loss/train': 0.7555629014968872} 08/31/2021 11:40:15 - INFO - __main__ - Step 123538: {'lr': 3.841621090258374e-05, 'samples': 23719296, 'steps': 123537, 'loss/train': 1.6015650033950806} 08/31/2021 11:40:16 - INFO - __main__ - Step 123539: {'lr': 3.841338430898725e-05, 'samples': 23719488, 'steps': 123538, 'loss/train': 0.057817526161670685} 08/31/2021 11:40:16 - INFO - __main__ - Step 123540: {'lr': 3.8410557810728414e-05, 'samples': 23719680, 'steps': 123539, 'loss/train': 0.90050208568573} 08/31/2021 11:40:17 - INFO - __main__ - Step 123541: {'lr': 3.840773140780851e-05, 'samples': 23719872, 'steps': 123540, 'loss/train': 1.0539851188659668} 08/31/2021 11:40:17 - INFO - __main__ - Step 123542: {'lr': 3.840490510022884e-05, 'samples': 23720064, 'steps': 123541, 'loss/train': 1.3570300340652466} 08/31/2021 11:40:18 - INFO - __main__ - Step 123543: {'lr': 3.840207888799063e-05, 'samples': 23720256, 'steps': 123542, 'loss/train': 1.6568660736083984} 08/31/2021 11:40:19 - INFO - __main__ - Step 123544: {'lr': 3.839925277109521e-05, 'samples': 23720448, 'steps': 123543, 'loss/train': 0.48701873421669006} 08/31/2021 11:40:20 - INFO - __main__ - Step 123545: {'lr': 3.83964267495438e-05, 'samples': 23720640, 'steps': 123544, 'loss/train': 1.5623844861984253} 08/31/2021 11:40:20 - INFO - __main__ - Step 123546: {'lr': 3.8393600823337707e-05, 'samples': 23720832, 'steps': 123545, 'loss/train': 1.0044690370559692} 08/31/2021 11:40:20 - INFO - __main__ - Step 123547: {'lr': 3.8390774992478175e-05, 'samples': 23721024, 'steps': 123546, 'loss/train': 0.6086641550064087} 08/31/2021 11:40:21 - INFO - __main__ - Step 123548: {'lr': 3.8387949256966506e-05, 'samples': 23721216, 'steps': 123547, 'loss/train': 0.1309674084186554} 08/31/2021 11:40:22 - INFO - __main__ - Step 123549: {'lr': 3.838512361680402e-05, 'samples': 23721408, 'steps': 123548, 'loss/train': 1.3987274169921875} 08/31/2021 11:40:23 - INFO - __main__ - Step 123550: {'lr': 3.8382298071991866e-05, 'samples': 23721600, 'steps': 123549, 'loss/train': 0.8311465978622437} 08/31/2021 11:40:23 - INFO - __main__ - Step 123551: {'lr': 3.837947262253139e-05, 'samples': 23721792, 'steps': 123550, 'loss/train': 0.7581580877304077} 08/31/2021 11:40:23 - INFO - __main__ - Step 123552: {'lr': 3.8376647268423856e-05, 'samples': 23721984, 'steps': 123551, 'loss/train': 0.9653958082199097} 08/31/2021 11:40:24 - INFO - __main__ - Step 123553: {'lr': 3.837382200967054e-05, 'samples': 23722176, 'steps': 123552, 'loss/train': 0.9565725326538086} 08/31/2021 11:40:25 - INFO - __main__ - Step 123554: {'lr': 3.837099684627271e-05, 'samples': 23722368, 'steps': 123553, 'loss/train': 1.4213035106658936} 08/31/2021 11:40:26 - INFO - __main__ - Step 123555: {'lr': 3.8368171778231656e-05, 'samples': 23722560, 'steps': 123554, 'loss/train': 1.4050394296646118} 08/31/2021 11:40:26 - INFO - __main__ - Step 123556: {'lr': 3.8365346805548624e-05, 'samples': 23722752, 'steps': 123555, 'loss/train': 1.7642838954925537} 08/31/2021 11:40:27 - INFO - __main__ - Step 123557: {'lr': 3.8362521928224926e-05, 'samples': 23722944, 'steps': 123556, 'loss/train': 0.6152526140213013} 08/31/2021 11:40:27 - INFO - __main__ - Step 123558: {'lr': 3.8359697146261777e-05, 'samples': 23723136, 'steps': 123557, 'loss/train': 1.4368871450424194} 08/31/2021 11:40:29 - INFO - __main__ - Step 123559: {'lr': 3.835687245966049e-05, 'samples': 23723328, 'steps': 123558, 'loss/train': 0.1480811983346939} 08/31/2021 11:40:30 - INFO - __main__ - Step 123560: {'lr': 3.835404786842234e-05, 'samples': 23723520, 'steps': 123559, 'loss/train': 1.2793470621109009} 08/31/2021 11:40:30 - INFO - __main__ - Step 123561: {'lr': 3.835122337254859e-05, 'samples': 23723712, 'steps': 123560, 'loss/train': 0.054004717618227005} 08/31/2021 11:40:31 - INFO - __main__ - Step 123562: {'lr': 3.8348398972040565e-05, 'samples': 23723904, 'steps': 123561, 'loss/train': 5.172471523284912} 08/31/2021 11:40:31 - INFO - __main__ - Step 123563: {'lr': 3.834557466689945e-05, 'samples': 23724096, 'steps': 123562, 'loss/train': 1.2552828788757324} 08/31/2021 11:40:31 - INFO - __main__ - Step 123564: {'lr': 3.8342750457126515e-05, 'samples': 23724288, 'steps': 123563, 'loss/train': 0.1169682964682579} 08/31/2021 11:40:32 - INFO - __main__ - Step 123565: {'lr': 3.8339926342723096e-05, 'samples': 23724480, 'steps': 123564, 'loss/train': 0.2782534956932068} 08/31/2021 11:40:32 - INFO - __main__ - Step 123566: {'lr': 3.8337102323690423e-05, 'samples': 23724672, 'steps': 123565, 'loss/train': 0.2800518870353699} 08/31/2021 11:40:34 - INFO - __main__ - Step 123567: {'lr': 3.833427840002982e-05, 'samples': 23724864, 'steps': 123566, 'loss/train': 0.2829636037349701} 08/31/2021 11:40:34 - INFO - __main__ - Step 123568: {'lr': 3.8331454571742474e-05, 'samples': 23725056, 'steps': 123567, 'loss/train': 1.0697216987609863} 08/31/2021 11:40:35 - INFO - __main__ - Step 123569: {'lr': 3.832863083882973e-05, 'samples': 23725248, 'steps': 123568, 'loss/train': 1.52715265750885} 08/31/2021 11:40:35 - INFO - __main__ - Step 123570: {'lr': 3.8325807201292864e-05, 'samples': 23725440, 'steps': 123569, 'loss/train': 1.4258497953414917} 08/31/2021 11:40:35 - INFO - __main__ - Step 123571: {'lr': 3.8322983659133086e-05, 'samples': 23725632, 'steps': 123570, 'loss/train': 1.1299254894256592} 08/31/2021 11:40:37 - INFO - __main__ - Step 123572: {'lr': 3.832016021235174e-05, 'samples': 23725824, 'steps': 123571, 'loss/train': 1.0765992403030396} 08/31/2021 11:40:37 - INFO - __main__ - Step 123573: {'lr': 3.83173368609501e-05, 'samples': 23726016, 'steps': 123572, 'loss/train': 1.29319429397583} 08/31/2021 11:40:38 - INFO - __main__ - Step 123574: {'lr': 3.831451360492935e-05, 'samples': 23726208, 'steps': 123573, 'loss/train': 0.03346801921725273} 08/31/2021 11:40:38 - INFO - __main__ - Step 123575: {'lr': 3.831169044429081e-05, 'samples': 23726400, 'steps': 123574, 'loss/train': 1.5410575866699219} 08/31/2021 11:40:39 - INFO - __main__ - Step 123576: {'lr': 3.830886737903574e-05, 'samples': 23726592, 'steps': 123575, 'loss/train': 0.8031288385391235} 08/31/2021 11:40:40 - INFO - __main__ - Step 123577: {'lr': 3.830604440916546e-05, 'samples': 23726784, 'steps': 123576, 'loss/train': 1.2544084787368774} 08/31/2021 11:40:41 - INFO - __main__ - Step 123578: {'lr': 3.8303221534681186e-05, 'samples': 23726976, 'steps': 123577, 'loss/train': 2.1447179317474365} 08/31/2021 11:40:41 - INFO - __main__ - Step 123579: {'lr': 3.830039875558422e-05, 'samples': 23727168, 'steps': 123578, 'loss/train': 0.19551719725131989} 08/31/2021 11:40:41 - INFO - __main__ - Step 123580: {'lr': 3.829757607187584e-05, 'samples': 23727360, 'steps': 123579, 'loss/train': 1.318834900856018} 08/31/2021 11:40:42 - INFO - __main__ - Step 123581: {'lr': 3.8294753483557296e-05, 'samples': 23727552, 'steps': 123580, 'loss/train': 0.5616343021392822} 08/31/2021 11:40:44 - INFO - __main__ - Step 123582: {'lr': 3.829193099062986e-05, 'samples': 23727744, 'steps': 123581, 'loss/train': 0.8252347111701965} 08/31/2021 11:40:44 - INFO - __main__ - Step 123583: {'lr': 3.8289108593094815e-05, 'samples': 23727936, 'steps': 123582, 'loss/train': 0.8948237299919128} 08/31/2021 11:40:44 - INFO - __main__ - Step 123584: {'lr': 3.828628629095349e-05, 'samples': 23728128, 'steps': 123583, 'loss/train': 1.2058525085449219} 08/31/2021 11:40:45 - INFO - __main__ - Step 123585: {'lr': 3.828346408420705e-05, 'samples': 23728320, 'steps': 123584, 'loss/train': 1.5421490669250488} 08/31/2021 11:40:45 - INFO - __main__ - Step 123586: {'lr': 3.82806419728568e-05, 'samples': 23728512, 'steps': 123585, 'loss/train': 1.4887017011642456} 08/31/2021 11:40:45 - INFO - __main__ - Step 123587: {'lr': 3.827781995690405e-05, 'samples': 23728704, 'steps': 123586, 'loss/train': 1.2680654525756836} 08/31/2021 11:40:47 - INFO - __main__ - Step 123588: {'lr': 3.827499803635001e-05, 'samples': 23728896, 'steps': 123587, 'loss/train': 2.103440284729004} 08/31/2021 11:40:47 - INFO - __main__ - Step 123589: {'lr': 3.827217621119603e-05, 'samples': 23729088, 'steps': 123588, 'loss/train': 0.9845221042633057} 08/31/2021 11:40:48 - INFO - __main__ - Step 123590: {'lr': 3.8269354481443306e-05, 'samples': 23729280, 'steps': 123589, 'loss/train': 0.7100334167480469} 08/31/2021 11:40:48 - INFO - __main__ - Step 123591: {'lr': 3.8266532847093166e-05, 'samples': 23729472, 'steps': 123590, 'loss/train': 1.1653074026107788} 08/31/2021 11:40:48 - INFO - __main__ - Step 123592: {'lr': 3.826371130814685e-05, 'samples': 23729664, 'steps': 123591, 'loss/train': 0.7412513494491577} 08/31/2021 11:40:50 - INFO - __main__ - Step 123593: {'lr': 3.826088986460563e-05, 'samples': 23729856, 'steps': 123592, 'loss/train': 0.04102437198162079} 08/31/2021 11:40:51 - INFO - __main__ - Step 123594: {'lr': 3.825806851647079e-05, 'samples': 23730048, 'steps': 123593, 'loss/train': 0.999186098575592} 08/31/2021 11:40:51 - INFO - __main__ - Step 123595: {'lr': 3.825524726374366e-05, 'samples': 23730240, 'steps': 123594, 'loss/train': 1.1132181882858276} 08/31/2021 11:40:51 - INFO - __main__ - Step 123596: {'lr': 3.8252426106425405e-05, 'samples': 23730432, 'steps': 123595, 'loss/train': 1.506529688835144} 08/31/2021 11:40:52 - INFO - __main__ - Step 123597: {'lr': 3.82496050445173e-05, 'samples': 23730624, 'steps': 123596, 'loss/train': 0.013403931632637978} 08/31/2021 11:40:52 - INFO - __main__ - Step 123598: {'lr': 3.824678407802068e-05, 'samples': 23730816, 'steps': 123597, 'loss/train': 0.014532158151268959} 08/31/2021 11:40:54 - INFO - __main__ - Step 123599: {'lr': 3.82439632069368e-05, 'samples': 23731008, 'steps': 123598, 'loss/train': 0.7278748750686646} 08/31/2021 11:40:54 - INFO - __main__ - Step 123600: {'lr': 3.824114243126692e-05, 'samples': 23731200, 'steps': 123599, 'loss/train': 1.1424447298049927} 08/31/2021 11:40:55 - INFO - __main__ - Step 123601: {'lr': 3.82383217510123e-05, 'samples': 23731392, 'steps': 123600, 'loss/train': 1.1271833181381226} 08/31/2021 11:40:55 - INFO - __main__ - Step 123602: {'lr': 3.823550116617425e-05, 'samples': 23731584, 'steps': 123601, 'loss/train': 1.6753829717636108} 08/31/2021 11:40:55 - INFO - __main__ - Step 123603: {'lr': 3.823268067675398e-05, 'samples': 23731776, 'steps': 123602, 'loss/train': 1.1755075454711914} 08/31/2021 11:40:57 - INFO - __main__ - Step 123604: {'lr': 3.822986028275283e-05, 'samples': 23731968, 'steps': 123603, 'loss/train': 0.8587921857833862} 08/31/2021 11:40:57 - INFO - __main__ - Step 123605: {'lr': 3.822703998417201e-05, 'samples': 23732160, 'steps': 123604, 'loss/train': 5.025379657745361} 08/31/2021 11:40:58 - INFO - __main__ - Step 123606: {'lr': 3.822421978101287e-05, 'samples': 23732352, 'steps': 123605, 'loss/train': 0.7871930003166199} 08/31/2021 11:40:58 - INFO - __main__ - Step 123607: {'lr': 3.822139967327659e-05, 'samples': 23732544, 'steps': 123606, 'loss/train': 0.7926695346832275} 08/31/2021 11:40:58 - INFO - __main__ - Step 123608: {'lr': 3.8218579660964484e-05, 'samples': 23732736, 'steps': 123607, 'loss/train': 1.4210314750671387} 08/31/2021 11:40:59 - INFO - __main__ - Step 123609: {'lr': 3.8215759744077816e-05, 'samples': 23732928, 'steps': 123608, 'loss/train': 1.3020663261413574} 08/31/2021 11:41:00 - INFO - __main__ - Step 123610: {'lr': 3.8212939922617846e-05, 'samples': 23733120, 'steps': 123609, 'loss/train': 1.2144689559936523} 08/31/2021 11:41:01 - INFO - __main__ - Step 123611: {'lr': 3.8210120196585874e-05, 'samples': 23733312, 'steps': 123610, 'loss/train': 0.6468202471733093} 08/31/2021 11:41:01 - INFO - __main__ - Step 123612: {'lr': 3.820730056598315e-05, 'samples': 23733504, 'steps': 123611, 'loss/train': 2.0722758769989014} 08/31/2021 11:41:01 - INFO - __main__ - Step 123613: {'lr': 3.820448103081092e-05, 'samples': 23733696, 'steps': 123612, 'loss/train': 0.1613846719264984} 08/31/2021 11:41:02 - INFO - __main__ - Step 123614: {'lr': 3.8201661591070525e-05, 'samples': 23733888, 'steps': 123613, 'loss/train': 0.4175722301006317} 08/31/2021 11:41:04 - INFO - __main__ - Step 123615: {'lr': 3.8198842246763146e-05, 'samples': 23734080, 'steps': 123614, 'loss/train': 0.647572934627533} 08/31/2021 11:41:04 - INFO - __main__ - Step 123616: {'lr': 3.819602299789013e-05, 'samples': 23734272, 'steps': 123615, 'loss/train': 0.28158098459243774} 08/31/2021 11:41:04 - INFO - __main__ - Step 123617: {'lr': 3.81932038444528e-05, 'samples': 23734464, 'steps': 123616, 'loss/train': 0.8476100564002991} 08/31/2021 11:41:05 - INFO - __main__ - Step 123618: {'lr': 3.819038478645223e-05, 'samples': 23734656, 'steps': 123617, 'loss/train': 0.537098228931427} 08/31/2021 11:41:05 - INFO - __main__ - Step 123619: {'lr': 3.818756582388985e-05, 'samples': 23734848, 'steps': 123618, 'loss/train': 0.3665996193885803} 08/31/2021 11:41:05 - INFO - __main__ - Step 123620: {'lr': 3.818474695676685e-05, 'samples': 23735040, 'steps': 123619, 'loss/train': 0.9480730891227722} 08/31/2021 11:41:07 - INFO - __main__ - Step 123621: {'lr': 3.8181928185084564e-05, 'samples': 23735232, 'steps': 123620, 'loss/train': 1.308536410331726} 08/31/2021 11:41:08 - INFO - __main__ - Step 123622: {'lr': 3.8179109508844235e-05, 'samples': 23735424, 'steps': 123621, 'loss/train': 1.029628872871399} 08/31/2021 11:41:08 - INFO - __main__ - Step 123623: {'lr': 3.817629092804712e-05, 'samples': 23735616, 'steps': 123622, 'loss/train': 1.2828104496002197} 08/31/2021 11:41:08 - INFO - __main__ - Step 123624: {'lr': 3.817347244269448e-05, 'samples': 23735808, 'steps': 123623, 'loss/train': 0.04550844058394432} 08/31/2021 11:41:09 - INFO - __main__ - Step 123625: {'lr': 3.817065405278763e-05, 'samples': 23736000, 'steps': 123624, 'loss/train': 1.3546020984649658} 08/31/2021 11:41:10 - INFO - __main__ - Step 123626: {'lr': 3.81678357583278e-05, 'samples': 23736192, 'steps': 123625, 'loss/train': 1.3703595399856567} 08/31/2021 11:41:11 - INFO - __main__ - Step 123627: {'lr': 3.816501755931628e-05, 'samples': 23736384, 'steps': 123626, 'loss/train': 1.0781787633895874} 08/31/2021 11:41:11 - INFO - __main__ - Step 123628: {'lr': 3.816219945575433e-05, 'samples': 23736576, 'steps': 123627, 'loss/train': 1.3176697492599487} 08/31/2021 11:41:11 - INFO - __main__ - Step 123629: {'lr': 3.815938144764322e-05, 'samples': 23736768, 'steps': 123628, 'loss/train': 0.5908730030059814} 08/31/2021 11:41:12 - INFO - __main__ - Step 123630: {'lr': 3.815656353498429e-05, 'samples': 23736960, 'steps': 123629, 'loss/train': 0.967652440071106} 08/31/2021 11:41:13 - INFO - __main__ - Step 123631: {'lr': 3.8153745717778684e-05, 'samples': 23737152, 'steps': 123630, 'loss/train': 0.9883057475090027} 08/31/2021 11:41:14 - INFO - __main__ - Step 123632: {'lr': 3.815092799602773e-05, 'samples': 23737344, 'steps': 123631, 'loss/train': 0.8699127435684204} 08/31/2021 11:41:14 - INFO - __main__ - Step 123633: {'lr': 3.81481103697327e-05, 'samples': 23737536, 'steps': 123632, 'loss/train': 1.1459829807281494} 08/31/2021 11:41:14 - INFO - __main__ - Step 123634: {'lr': 3.8145292838894865e-05, 'samples': 23737728, 'steps': 123633, 'loss/train': 0.6867987513542175} 08/31/2021 11:41:15 - INFO - __main__ - Step 123635: {'lr': 3.8142475403515506e-05, 'samples': 23737920, 'steps': 123634, 'loss/train': 0.7995919585227966} 08/31/2021 11:41:17 - INFO - __main__ - Step 123636: {'lr': 3.813965806359587e-05, 'samples': 23738112, 'steps': 123635, 'loss/train': 0.043782789260149} 08/31/2021 11:41:17 - INFO - __main__ - Step 123637: {'lr': 3.813684081913721e-05, 'samples': 23738304, 'steps': 123636, 'loss/train': 0.9803520441055298} 08/31/2021 11:41:18 - INFO - __main__ - Step 123638: {'lr': 3.813402367014085e-05, 'samples': 23738496, 'steps': 123637, 'loss/train': 0.02250712923705578} 08/31/2021 11:41:18 - INFO - __main__ - Step 123639: {'lr': 3.813120661660802e-05, 'samples': 23738688, 'steps': 123638, 'loss/train': 0.8697254061698914} 08/31/2021 11:41:18 - INFO - __main__ - Step 123640: {'lr': 3.8128389658539984e-05, 'samples': 23738880, 'steps': 123639, 'loss/train': 0.7936343550682068} 08/31/2021 11:41:20 - INFO - __main__ - Step 123641: {'lr': 3.812557279593803e-05, 'samples': 23739072, 'steps': 123640, 'loss/train': 1.1258412599563599} 08/31/2021 11:41:21 - INFO - __main__ - Step 123642: {'lr': 3.8122756028803443e-05, 'samples': 23739264, 'steps': 123641, 'loss/train': 1.5123591423034668} 08/31/2021 11:41:21 - INFO - __main__ - Step 123643: {'lr': 3.811993935713753e-05, 'samples': 23739456, 'steps': 123642, 'loss/train': 0.8479459881782532} 08/31/2021 11:41:21 - INFO - __main__ - Step 123644: {'lr': 3.811712278094143e-05, 'samples': 23739648, 'steps': 123643, 'loss/train': 1.5367003679275513} 08/31/2021 11:41:22 - INFO - __main__ - Step 123645: {'lr': 3.811430630021648e-05, 'samples': 23739840, 'steps': 123644, 'loss/train': 1.5418373346328735} 08/31/2021 11:41:23 - INFO - __main__ - Step 123646: {'lr': 3.8111489914963966e-05, 'samples': 23740032, 'steps': 123645, 'loss/train': 1.315656065940857} 08/31/2021 11:41:24 - INFO - __main__ - Step 123647: {'lr': 3.8108673625185135e-05, 'samples': 23740224, 'steps': 123646, 'loss/train': 1.3054234981536865} 08/31/2021 11:41:24 - INFO - __main__ - Step 123648: {'lr': 3.8105857430881296e-05, 'samples': 23740416, 'steps': 123647, 'loss/train': 1.3929290771484375} 08/31/2021 11:41:24 - INFO - __main__ - Step 123649: {'lr': 3.810304133205367e-05, 'samples': 23740608, 'steps': 123648, 'loss/train': 0.8265061378479004} 08/31/2021 11:41:25 - INFO - __main__ - Step 123650: {'lr': 3.810022532870352e-05, 'samples': 23740800, 'steps': 123649, 'loss/train': 0.46381646394729614} 08/31/2021 11:41:25 - INFO - __main__ - Step 123651: {'lr': 3.8097409420832176e-05, 'samples': 23740992, 'steps': 123650, 'loss/train': 0.8698047995567322} 08/31/2021 11:41:27 - INFO - __main__ - Step 123652: {'lr': 3.8094593608440836e-05, 'samples': 23741184, 'steps': 123651, 'loss/train': 1.3253074884414673} 08/31/2021 11:41:27 - INFO - __main__ - Step 123653: {'lr': 3.809177789153082e-05, 'samples': 23741376, 'steps': 123652, 'loss/train': 1.0394270420074463} 08/31/2021 11:41:27 - INFO - __main__ - Step 123654: {'lr': 3.808896227010339e-05, 'samples': 23741568, 'steps': 123653, 'loss/train': 1.3167768716812134} 08/31/2021 11:41:28 - INFO - __main__ - Step 123655: {'lr': 3.808614674415978e-05, 'samples': 23741760, 'steps': 123654, 'loss/train': 1.324044108390808} 08/31/2021 11:41:28 - INFO - __main__ - Step 123656: {'lr': 3.808333131370134e-05, 'samples': 23741952, 'steps': 123655, 'loss/train': 0.6745581030845642} 08/31/2021 11:41:30 - INFO - __main__ - Step 123657: {'lr': 3.808051597872925e-05, 'samples': 23742144, 'steps': 123656, 'loss/train': 0.991864025592804} 08/31/2021 11:41:31 - INFO - __main__ - Step 123658: {'lr': 3.8077700739244796e-05, 'samples': 23742336, 'steps': 123657, 'loss/train': 1.1484237909317017} 08/31/2021 11:41:31 - INFO - __main__ - Step 123659: {'lr': 3.807488559524924e-05, 'samples': 23742528, 'steps': 123658, 'loss/train': 1.3219709396362305} 08/31/2021 11:41:31 - INFO - __main__ - Step 123660: {'lr': 3.8072070546743886e-05, 'samples': 23742720, 'steps': 123659, 'loss/train': 0.9863485097885132} 08/31/2021 11:41:32 - INFO - __main__ - Step 123661: {'lr': 3.806925559373001e-05, 'samples': 23742912, 'steps': 123660, 'loss/train': 0.7625769376754761} 08/31/2021 11:41:32 - INFO - __main__ - Step 123662: {'lr': 3.8066440736208825e-05, 'samples': 23743104, 'steps': 123661, 'loss/train': 0.6092832088470459} 08/31/2021 11:41:34 - INFO - __main__ - Step 123663: {'lr': 3.806362597418164e-05, 'samples': 23743296, 'steps': 123662, 'loss/train': 0.724860668182373} 08/31/2021 11:41:34 - INFO - __main__ - Step 123664: {'lr': 3.8060811307649715e-05, 'samples': 23743488, 'steps': 123663, 'loss/train': 0.05176543444395065} 08/31/2021 11:41:34 - INFO - __main__ - Step 123665: {'lr': 3.805799673661431e-05, 'samples': 23743680, 'steps': 123664, 'loss/train': 2.2094082832336426} 08/31/2021 11:41:35 - INFO - __main__ - Step 123666: {'lr': 3.805518226107671e-05, 'samples': 23743872, 'steps': 123665, 'loss/train': 0.9822437763214111} 08/31/2021 11:41:35 - INFO - __main__ - Step 123667: {'lr': 3.8052367881038194e-05, 'samples': 23744064, 'steps': 123666, 'loss/train': 1.4374948740005493} 08/31/2021 11:41:37 - INFO - __main__ - Step 123668: {'lr': 3.8049553596499975e-05, 'samples': 23744256, 'steps': 123667, 'loss/train': 0.4143950939178467} 08/31/2021 11:41:37 - INFO - __main__ - Step 123669: {'lr': 3.804673940746339e-05, 'samples': 23744448, 'steps': 123668, 'loss/train': 1.0973817110061646} 08/31/2021 11:41:38 - INFO - __main__ - Step 123670: {'lr': 3.8043925313929694e-05, 'samples': 23744640, 'steps': 123669, 'loss/train': 0.5127631425857544} 08/31/2021 11:41:38 - INFO - __main__ - Step 123671: {'lr': 3.80411113159001e-05, 'samples': 23744832, 'steps': 123670, 'loss/train': 1.4141404628753662} 08/31/2021 11:41:38 - INFO - __main__ - Step 123672: {'lr': 3.8038297413375914e-05, 'samples': 23745024, 'steps': 123671, 'loss/train': 0.9414428472518921} 08/31/2021 11:41:40 - INFO - __main__ - Step 123673: {'lr': 3.803548360635839e-05, 'samples': 23745216, 'steps': 123672, 'loss/train': 1.2608476877212524} 08/31/2021 11:41:40 - INFO - __main__ - Step 123674: {'lr': 3.8032669894848826e-05, 'samples': 23745408, 'steps': 123673, 'loss/train': 0.3714573383331299} 08/31/2021 11:41:41 - INFO - __main__ - Step 123675: {'lr': 3.802985627884844e-05, 'samples': 23745600, 'steps': 123674, 'loss/train': 1.3790169954299927} 08/31/2021 11:41:41 - INFO - __main__ - Step 123676: {'lr': 3.8027042758358554e-05, 'samples': 23745792, 'steps': 123675, 'loss/train': 0.7921270132064819} 08/31/2021 11:41:41 - INFO - __main__ - Step 123677: {'lr': 3.80242293333804e-05, 'samples': 23745984, 'steps': 123676, 'loss/train': 1.3794238567352295} 08/31/2021 11:41:43 - INFO - __main__ - Step 123678: {'lr': 3.802141600391526e-05, 'samples': 23746176, 'steps': 123677, 'loss/train': 0.5427478551864624} 08/31/2021 11:41:43 - INFO - __main__ - Step 123679: {'lr': 3.801860276996438e-05, 'samples': 23746368, 'steps': 123678, 'loss/train': 1.2571049928665161} 08/31/2021 11:41:44 - INFO - __main__ - Step 123680: {'lr': 3.8015789631529076e-05, 'samples': 23746560, 'steps': 123679, 'loss/train': 0.9664556980133057} 08/31/2021 11:41:44 - INFO - __main__ - Step 123681: {'lr': 3.801297658861058e-05, 'samples': 23746752, 'steps': 123680, 'loss/train': 1.403633952140808} 08/31/2021 11:41:44 - INFO - __main__ - Step 123682: {'lr': 3.801016364121016e-05, 'samples': 23746944, 'steps': 123681, 'loss/train': 1.264654278755188} 08/31/2021 11:41:45 - INFO - __main__ - Step 123683: {'lr': 3.8007350789329154e-05, 'samples': 23747136, 'steps': 123682, 'loss/train': 1.0471231937408447} 08/31/2021 11:41:46 - INFO - __main__ - Step 123684: {'lr': 3.8004538032968686e-05, 'samples': 23747328, 'steps': 123683, 'loss/train': 1.1554275751113892} 08/31/2021 11:41:47 - INFO - __main__ - Step 123685: {'lr': 3.8001725372130116e-05, 'samples': 23747520, 'steps': 123684, 'loss/train': 0.9892452955245972} 08/31/2021 11:41:47 - INFO - __main__ - Step 123686: {'lr': 3.79989128068147e-05, 'samples': 23747712, 'steps': 123685, 'loss/train': 0.754135012626648} 08/31/2021 11:41:48 - INFO - __main__ - Step 123687: {'lr': 3.799610033702369e-05, 'samples': 23747904, 'steps': 123686, 'loss/train': 0.9937936067581177} 08/31/2021 11:41:48 - INFO - __main__ - Step 123688: {'lr': 3.799328796275839e-05, 'samples': 23748096, 'steps': 123687, 'loss/train': 1.2509305477142334} 08/31/2021 11:41:50 - INFO - __main__ - Step 123689: {'lr': 3.799047568402003e-05, 'samples': 23748288, 'steps': 123688, 'loss/train': 1.1568799018859863} 08/31/2021 11:41:51 - INFO - __main__ - Step 123690: {'lr': 3.798766350080987e-05, 'samples': 23748480, 'steps': 123689, 'loss/train': 0.5030947327613831} 08/31/2021 11:41:51 - INFO - __main__ - Step 123691: {'lr': 3.798485141312924e-05, 'samples': 23748672, 'steps': 123690, 'loss/train': 0.8979297280311584} 08/31/2021 11:41:51 - INFO - __main__ - Step 123692: {'lr': 3.798203942097933e-05, 'samples': 23748864, 'steps': 123691, 'loss/train': 1.1076912879943848} 08/31/2021 11:41:52 - INFO - __main__ - Step 123693: {'lr': 3.797922752436145e-05, 'samples': 23749056, 'steps': 123692, 'loss/train': 0.13312877714633942} 08/31/2021 11:41:53 - INFO - __main__ - Step 123694: {'lr': 3.797641572327687e-05, 'samples': 23749248, 'steps': 123693, 'loss/train': 1.6432251930236816} 08/31/2021 11:41:54 - INFO - __main__ - Step 123695: {'lr': 3.797360401772682e-05, 'samples': 23749440, 'steps': 123694, 'loss/train': 0.9841465353965759} 08/31/2021 11:41:54 - INFO - __main__ - Step 123696: {'lr': 3.797079240771262e-05, 'samples': 23749632, 'steps': 123695, 'loss/train': 1.1742290258407593} 08/31/2021 11:41:54 - INFO - __main__ - Step 123697: {'lr': 3.796798089323556e-05, 'samples': 23749824, 'steps': 123696, 'loss/train': 1.1554081439971924} 08/31/2021 11:41:55 - INFO - __main__ - Step 123698: {'lr': 3.796516947429679e-05, 'samples': 23750016, 'steps': 123697, 'loss/train': 0.4636968672275543} 08/31/2021 11:41:56 - INFO - __main__ - Step 123699: {'lr': 3.796235815089763e-05, 'samples': 23750208, 'steps': 123698, 'loss/train': 1.71787691116333} 08/31/2021 11:41:57 - INFO - __main__ - Step 123700: {'lr': 3.7959546923039376e-05, 'samples': 23750400, 'steps': 123699, 'loss/train': 1.2604314088821411} 08/31/2021 11:41:57 - INFO - __main__ - Step 123701: {'lr': 3.7956735790723286e-05, 'samples': 23750592, 'steps': 123700, 'loss/train': 0.9842102527618408} 08/31/2021 11:41:57 - INFO - __main__ - Step 123702: {'lr': 3.7953924753950594e-05, 'samples': 23750784, 'steps': 123701, 'loss/train': 0.1801997274160385} 08/31/2021 11:41:58 - INFO - __main__ - Step 123703: {'lr': 3.795111381272262e-05, 'samples': 23750976, 'steps': 123702, 'loss/train': 1.7245396375656128} 08/31/2021 11:41:59 - INFO - __main__ - Step 123704: {'lr': 3.794830296704058e-05, 'samples': 23751168, 'steps': 123703, 'loss/train': 1.5413473844528198} 08/31/2021 11:42:00 - INFO - __main__ - Step 123705: {'lr': 3.794549221690577e-05, 'samples': 23751360, 'steps': 123704, 'loss/train': 1.2999149560928345} 08/31/2021 11:42:00 - INFO - __main__ - Step 123706: {'lr': 3.794268156231945e-05, 'samples': 23751552, 'steps': 123705, 'loss/train': 0.9724311232566833} 08/31/2021 11:42:00 - INFO - __main__ - Step 123707: {'lr': 3.793987100328289e-05, 'samples': 23751744, 'steps': 123706, 'loss/train': 0.9157914519309998} 08/31/2021 11:42:01 - INFO - __main__ - Step 123708: {'lr': 3.793706053979734e-05, 'samples': 23751936, 'steps': 123707, 'loss/train': 1.5084404945373535} 08/31/2021 11:42:01 - INFO - __main__ - Step 123709: {'lr': 3.793425017186411e-05, 'samples': 23752128, 'steps': 123708, 'loss/train': 1.096126675605774} 08/31/2021 11:42:03 - INFO - __main__ - Step 123710: {'lr': 3.7931439899484474e-05, 'samples': 23752320, 'steps': 123709, 'loss/train': 0.9539034962654114} 08/31/2021 11:42:03 - INFO - __main__ - Step 123711: {'lr': 3.792862972265959e-05, 'samples': 23752512, 'steps': 123710, 'loss/train': 1.0905463695526123} 08/31/2021 11:42:03 - INFO - __main__ - Step 123712: {'lr': 3.792581964139078e-05, 'samples': 23752704, 'steps': 123711, 'loss/train': 1.0324177742004395} 08/31/2021 11:42:04 - INFO - __main__ - Step 123713: {'lr': 3.7923009655679355e-05, 'samples': 23752896, 'steps': 123712, 'loss/train': 0.20837105810642242} 08/31/2021 11:42:04 - INFO - __main__ - Step 123714: {'lr': 3.792019976552652e-05, 'samples': 23753088, 'steps': 123713, 'loss/train': 1.0363521575927734} 08/31/2021 11:42:06 - INFO - __main__ - Step 123715: {'lr': 3.791738997093361e-05, 'samples': 23753280, 'steps': 123714, 'loss/train': 5.625393390655518} 08/31/2021 11:42:06 - INFO - __main__ - Step 123716: {'lr': 3.791458027190181e-05, 'samples': 23753472, 'steps': 123715, 'loss/train': 1.4301027059555054} 08/31/2021 11:42:06 - INFO - __main__ - Step 123717: {'lr': 3.791177066843246e-05, 'samples': 23753664, 'steps': 123716, 'loss/train': 1.2455041408538818} 08/31/2021 11:42:07 - INFO - __main__ - Step 123718: {'lr': 3.7908961160526776e-05, 'samples': 23753856, 'steps': 123717, 'loss/train': 1.504037857055664} 08/31/2021 11:42:07 - INFO - __main__ - Step 123719: {'lr': 3.790615174818604e-05, 'samples': 23754048, 'steps': 123718, 'loss/train': 0.9500529766082764} 08/31/2021 11:42:09 - INFO - __main__ - Step 123720: {'lr': 3.790334243141153e-05, 'samples': 23754240, 'steps': 123719, 'loss/train': 1.230964183807373} 08/31/2021 11:42:09 - INFO - __main__ - Step 123721: {'lr': 3.790053321020448e-05, 'samples': 23754432, 'steps': 123720, 'loss/train': 1.3064805269241333} 08/31/2021 11:42:09 - INFO - __main__ - Step 123722: {'lr': 3.7897724084566184e-05, 'samples': 23754624, 'steps': 123721, 'loss/train': 1.0652344226837158} 08/31/2021 11:42:10 - INFO - __main__ - Step 123723: {'lr': 3.7894915054497906e-05, 'samples': 23754816, 'steps': 123722, 'loss/train': 0.6269091963768005} 08/31/2021 11:42:10 - INFO - __main__ - Step 123724: {'lr': 3.7892106120000966e-05, 'samples': 23755008, 'steps': 123723, 'loss/train': 0.9669608473777771} 08/31/2021 11:42:12 - INFO - __main__ - Step 123725: {'lr': 3.7889297281076515e-05, 'samples': 23755200, 'steps': 123724, 'loss/train': 0.11587455868721008} 08/31/2021 11:42:12 - INFO - __main__ - Step 123726: {'lr': 3.788648853772589e-05, 'samples': 23755392, 'steps': 123725, 'loss/train': 1.161524772644043} 08/31/2021 11:42:12 - INFO - __main__ - Step 123727: {'lr': 3.788367988995031e-05, 'samples': 23755584, 'steps': 123726, 'loss/train': 0.8149546980857849} 08/31/2021 11:42:13 - INFO - __main__ - Step 123728: {'lr': 3.788087133775109e-05, 'samples': 23755776, 'steps': 123727, 'loss/train': 0.6222137212753296} 08/31/2021 11:42:13 - INFO - __main__ - Step 123729: {'lr': 3.787806288112947e-05, 'samples': 23755968, 'steps': 123728, 'loss/train': 1.483662724494934} 08/31/2021 11:42:15 - INFO - __main__ - Step 123730: {'lr': 3.7875254520086694e-05, 'samples': 23756160, 'steps': 123729, 'loss/train': 0.9086953997612} 08/31/2021 11:42:15 - INFO - __main__ - Step 123731: {'lr': 3.787244625462411e-05, 'samples': 23756352, 'steps': 123730, 'loss/train': 1.239979863166809} 08/31/2021 11:42:15 - INFO - __main__ - Step 123732: {'lr': 3.786963808474289e-05, 'samples': 23756544, 'steps': 123731, 'loss/train': 0.8257660269737244} 08/31/2021 11:42:16 - INFO - __main__ - Step 123733: {'lr': 3.786683001044433e-05, 'samples': 23756736, 'steps': 123732, 'loss/train': 1.1321502923965454} 08/31/2021 11:42:16 - INFO - __main__ - Step 123734: {'lr': 3.786402203172973e-05, 'samples': 23756928, 'steps': 123733, 'loss/train': 1.0605039596557617} 08/31/2021 11:42:17 - INFO - __main__ - Step 123735: {'lr': 3.7861214148600303e-05, 'samples': 23757120, 'steps': 123734, 'loss/train': 1.5435155630111694} 08/31/2021 11:42:18 - INFO - __main__ - Step 123736: {'lr': 3.785840636105736e-05, 'samples': 23757312, 'steps': 123735, 'loss/train': 0.038025543093681335} 08/31/2021 11:42:19 - INFO - __main__ - Step 123737: {'lr': 3.785559866910221e-05, 'samples': 23757504, 'steps': 123736, 'loss/train': 0.5918900966644287} 08/31/2021 11:42:19 - INFO - __main__ - Step 123738: {'lr': 3.785279107273598e-05, 'samples': 23757696, 'steps': 123737, 'loss/train': 0.014910894446074963} 08/31/2021 11:42:20 - INFO - __main__ - Step 123739: {'lr': 3.784998357196001e-05, 'samples': 23757888, 'steps': 123738, 'loss/train': 0.014141145162284374} 08/31/2021 11:42:20 - INFO - __main__ - Step 123740: {'lr': 3.784717616677555e-05, 'samples': 23758080, 'steps': 123739, 'loss/train': 1.125091552734375} 08/31/2021 11:42:20 - INFO - __main__ - Step 123741: {'lr': 3.78443688571839e-05, 'samples': 23758272, 'steps': 123740, 'loss/train': 1.0537461042404175} 08/31/2021 11:42:22 - INFO - __main__ - Step 123742: {'lr': 3.7841561643186303e-05, 'samples': 23758464, 'steps': 123741, 'loss/train': 1.8674862384796143} 08/31/2021 11:42:22 - INFO - __main__ - Step 123743: {'lr': 3.783875452478403e-05, 'samples': 23758656, 'steps': 123742, 'loss/train': 0.40410465002059937} 08/31/2021 11:42:23 - INFO - __main__ - Step 123744: {'lr': 3.783594750197833e-05, 'samples': 23758848, 'steps': 123743, 'loss/train': 1.0725630521774292} 08/31/2021 11:42:23 - INFO - __main__ - Step 123745: {'lr': 3.783314057477047e-05, 'samples': 23759040, 'steps': 123744, 'loss/train': 1.7236528396606445} 08/31/2021 11:42:23 - INFO - __main__ - Step 123746: {'lr': 3.7830333743161723e-05, 'samples': 23759232, 'steps': 123745, 'loss/train': 0.9320314526557922} 08/31/2021 11:42:26 - INFO - __main__ - Step 123747: {'lr': 3.782752700715336e-05, 'samples': 23759424, 'steps': 123746, 'loss/train': 1.3099852800369263} 08/31/2021 11:42:26 - INFO - __main__ - Step 123748: {'lr': 3.782472036674664e-05, 'samples': 23759616, 'steps': 123747, 'loss/train': 1.036017894744873} 08/31/2021 11:42:27 - INFO - __main__ - Step 123749: {'lr': 3.7821913821942835e-05, 'samples': 23759808, 'steps': 123748, 'loss/train': 0.41627922654151917} 08/31/2021 11:42:27 - INFO - __main__ - Step 123750: {'lr': 3.781910737274319e-05, 'samples': 23760000, 'steps': 123749, 'loss/train': 0.11096426844596863} 08/31/2021 11:42:27 - INFO - __main__ - Step 123751: {'lr': 3.781630101914904e-05, 'samples': 23760192, 'steps': 123750, 'loss/train': 0.061203014105558395} 08/31/2021 11:42:29 - INFO - __main__ - Step 123752: {'lr': 3.781349476116156e-05, 'samples': 23760384, 'steps': 123751, 'loss/train': 0.29419928789138794} 08/31/2021 11:42:29 - INFO - __main__ - Step 123753: {'lr': 3.7810688598782004e-05, 'samples': 23760576, 'steps': 123752, 'loss/train': 1.4176788330078125} 08/31/2021 11:42:30 - INFO - __main__ - Step 123754: {'lr': 3.78078825320117e-05, 'samples': 23760768, 'steps': 123753, 'loss/train': 0.6275356411933899} 08/31/2021 11:42:30 - INFO - __main__ - Step 123755: {'lr': 3.7805076560851884e-05, 'samples': 23760960, 'steps': 123754, 'loss/train': 1.1389824151992798} 08/31/2021 11:42:30 - INFO - __main__ - Step 123756: {'lr': 3.780227068530381e-05, 'samples': 23761152, 'steps': 123755, 'loss/train': 0.39548033475875854} 08/31/2021 11:42:32 - INFO - __main__ - Step 123757: {'lr': 3.779946490536879e-05, 'samples': 23761344, 'steps': 123756, 'loss/train': 1.459129810333252} 08/31/2021 11:42:32 - INFO - __main__ - Step 123758: {'lr': 3.7796659221048025e-05, 'samples': 23761536, 'steps': 123757, 'loss/train': 1.752860426902771} 08/31/2021 11:42:33 - INFO - __main__ - Step 123759: {'lr': 3.7793853632342834e-05, 'samples': 23761728, 'steps': 123758, 'loss/train': 1.1688485145568848} 08/31/2021 11:42:33 - INFO - __main__ - Step 123760: {'lr': 3.779104813925446e-05, 'samples': 23761920, 'steps': 123759, 'loss/train': 0.6987465620040894} 08/31/2021 11:42:33 - INFO - __main__ - Step 123761: {'lr': 3.7788242741784164e-05, 'samples': 23762112, 'steps': 123760, 'loss/train': 1.35979163646698} 08/31/2021 11:42:35 - INFO - __main__ - Step 123762: {'lr': 3.778543743993318e-05, 'samples': 23762304, 'steps': 123761, 'loss/train': 1.5740718841552734} 08/31/2021 11:42:35 - INFO - __main__ - Step 123763: {'lr': 3.778263223370285e-05, 'samples': 23762496, 'steps': 123762, 'loss/train': 1.1583837270736694} 08/31/2021 11:42:36 - INFO - __main__ - Step 123764: {'lr': 3.7779827123094413e-05, 'samples': 23762688, 'steps': 123763, 'loss/train': 1.0227727890014648} 08/31/2021 11:42:36 - INFO - __main__ - Step 123765: {'lr': 3.777702210810907e-05, 'samples': 23762880, 'steps': 123764, 'loss/train': 1.1075164079666138} 08/31/2021 11:42:36 - INFO - __main__ - Step 123766: {'lr': 3.777421718874813e-05, 'samples': 23763072, 'steps': 123765, 'loss/train': 1.6083812713623047} 08/31/2021 11:42:37 - INFO - __main__ - Step 123767: {'lr': 3.777141236501283e-05, 'samples': 23763264, 'steps': 123766, 'loss/train': 1.5475088357925415} 08/31/2021 11:42:39 - INFO - __main__ - Step 123768: {'lr': 3.7768607636904485e-05, 'samples': 23763456, 'steps': 123767, 'loss/train': 0.7399135231971741} 08/31/2021 11:42:39 - INFO - __main__ - Step 123769: {'lr': 3.776580300442431e-05, 'samples': 23763648, 'steps': 123768, 'loss/train': 0.7718967795372009} 08/31/2021 11:42:39 - INFO - __main__ - Step 123770: {'lr': 3.776299846757358e-05, 'samples': 23763840, 'steps': 123769, 'loss/train': 0.34417805075645447} 08/31/2021 11:42:40 - INFO - __main__ - Step 123771: {'lr': 3.776019402635358e-05, 'samples': 23764032, 'steps': 123770, 'loss/train': 0.03688496723771095} 08/31/2021 11:42:40 - INFO - __main__ - Step 123772: {'lr': 3.7757389680765586e-05, 'samples': 23764224, 'steps': 123771, 'loss/train': 0.7826648950576782} 08/31/2021 11:42:41 - INFO - __main__ - Step 123773: {'lr': 3.7754585430810815e-05, 'samples': 23764416, 'steps': 123772, 'loss/train': 0.6675368547439575} 08/31/2021 11:42:42 - INFO - __main__ - Step 123774: {'lr': 3.775178127649056e-05, 'samples': 23764608, 'steps': 123773, 'loss/train': 0.8936058282852173} 08/31/2021 11:42:42 - INFO - __main__ - Step 123775: {'lr': 3.774897721780607e-05, 'samples': 23764800, 'steps': 123774, 'loss/train': 0.764288604259491} 08/31/2021 11:42:43 - INFO - __main__ - Step 123776: {'lr': 3.77461732547586e-05, 'samples': 23764992, 'steps': 123775, 'loss/train': 0.8486154675483704} 08/31/2021 11:42:43 - INFO - __main__ - Step 123777: {'lr': 3.774336938734951e-05, 'samples': 23765184, 'steps': 123776, 'loss/train': 0.40030717849731445} 08/31/2021 11:42:43 - INFO - __main__ - Step 123778: {'lr': 3.774056561557993e-05, 'samples': 23765376, 'steps': 123777, 'loss/train': 1.0524964332580566} 08/31/2021 11:42:45 - INFO - __main__ - Step 123779: {'lr': 3.7737761939451163e-05, 'samples': 23765568, 'steps': 123778, 'loss/train': 1.3633216619491577} 08/31/2021 11:42:45 - INFO - __main__ - Step 123780: {'lr': 3.773495835896448e-05, 'samples': 23765760, 'steps': 123779, 'loss/train': 0.8971752524375916} 08/31/2021 11:42:46 - INFO - __main__ - Step 123781: {'lr': 3.7732154874121154e-05, 'samples': 23765952, 'steps': 123780, 'loss/train': 0.872309684753418} 08/31/2021 11:42:46 - INFO - __main__ - Step 123782: {'lr': 3.772935148492246e-05, 'samples': 23766144, 'steps': 123781, 'loss/train': 0.32651251554489136} 08/31/2021 11:42:46 - INFO - __main__ - Step 123783: {'lr': 3.7726548191369615e-05, 'samples': 23766336, 'steps': 123782, 'loss/train': 0.9187014102935791} 08/31/2021 11:42:48 - INFO - __main__ - Step 123784: {'lr': 3.7723744993463924e-05, 'samples': 23766528, 'steps': 123783, 'loss/train': 1.2882071733474731} 08/31/2021 11:42:49 - INFO - __main__ - Step 123785: {'lr': 3.772094189120664e-05, 'samples': 23766720, 'steps': 123784, 'loss/train': 1.583465576171875} 08/31/2021 11:42:49 - INFO - __main__ - Step 123786: {'lr': 3.7718138884599046e-05, 'samples': 23766912, 'steps': 123785, 'loss/train': 0.9434694647789001} 08/31/2021 11:42:50 - INFO - __main__ - Step 123787: {'lr': 3.7715335973642354e-05, 'samples': 23767104, 'steps': 123786, 'loss/train': 1.1997865438461304} 08/31/2021 11:42:50 - INFO - __main__ - Step 123788: {'lr': 3.7712533158337867e-05, 'samples': 23767296, 'steps': 123787, 'loss/train': 1.2562282085418701} 08/31/2021 11:42:51 - INFO - __main__ - Step 123789: {'lr': 3.770973043868683e-05, 'samples': 23767488, 'steps': 123788, 'loss/train': 0.25493520498275757} 08/31/2021 11:42:52 - INFO - __main__ - Step 123790: {'lr': 3.770692781469051e-05, 'samples': 23767680, 'steps': 123789, 'loss/train': 0.8705410361289978} 08/31/2021 11:42:52 - INFO - __main__ - Step 123791: {'lr': 3.770412528635023e-05, 'samples': 23767872, 'steps': 123790, 'loss/train': 1.7004621028900146} 08/31/2021 11:42:52 - INFO - __main__ - Step 123792: {'lr': 3.7701322853667144e-05, 'samples': 23768064, 'steps': 123791, 'loss/train': 1.1250795125961304} 08/31/2021 11:42:53 - INFO - __main__ - Step 123793: {'lr': 3.7698520516642576e-05, 'samples': 23768256, 'steps': 123792, 'loss/train': 1.5326248407363892} 08/31/2021 11:42:53 - INFO - __main__ - Step 123794: {'lr': 3.769571827527776e-05, 'samples': 23768448, 'steps': 123793, 'loss/train': 1.1233981847763062} 08/31/2021 11:42:55 - INFO - __main__ - Step 123795: {'lr': 3.769291612957398e-05, 'samples': 23768640, 'steps': 123794, 'loss/train': 0.27896788716316223} 08/31/2021 11:42:55 - INFO - __main__ - Step 123796: {'lr': 3.7690114079532516e-05, 'samples': 23768832, 'steps': 123795, 'loss/train': 0.8064162731170654} 08/31/2021 11:42:56 - INFO - __main__ - Step 123797: {'lr': 3.768731212515458e-05, 'samples': 23769024, 'steps': 123796, 'loss/train': 0.029004132375121117} 08/31/2021 11:42:56 - INFO - __main__ - Step 123798: {'lr': 3.768451026644149e-05, 'samples': 23769216, 'steps': 123797, 'loss/train': 1.3324379920959473} 08/31/2021 11:42:56 - INFO - __main__ - Step 123799: {'lr': 3.7681708503394476e-05, 'samples': 23769408, 'steps': 123798, 'loss/train': 0.8602163195610046} 08/31/2021 11:42:58 - INFO - __main__ - Step 123800: {'lr': 3.7678906836014796e-05, 'samples': 23769600, 'steps': 123799, 'loss/train': 0.33370745182037354} 08/31/2021 11:42:59 - INFO - __main__ - Step 123801: {'lr': 3.767610526430373e-05, 'samples': 23769792, 'steps': 123800, 'loss/train': 0.5858923196792603} 08/31/2021 11:42:59 - INFO - __main__ - Step 123802: {'lr': 3.767330378826256e-05, 'samples': 23769984, 'steps': 123801, 'loss/train': 1.476478934288025} 08/31/2021 11:43:00 - INFO - __main__ - Step 123803: {'lr': 3.7670502407892494e-05, 'samples': 23770176, 'steps': 123802, 'loss/train': 1.013817310333252} 08/31/2021 11:43:00 - INFO - __main__ - Step 123804: {'lr': 3.76677011231949e-05, 'samples': 23770368, 'steps': 123803, 'loss/train': 2.685792922973633} 08/31/2021 11:43:01 - INFO - __main__ - Step 123805: {'lr': 3.766489993417088e-05, 'samples': 23770560, 'steps': 123804, 'loss/train': 0.79924076795578} 08/31/2021 11:43:02 - INFO - __main__ - Step 123806: {'lr': 3.7662098840821805e-05, 'samples': 23770752, 'steps': 123805, 'loss/train': 0.7614513635635376} 08/31/2021 11:43:02 - INFO - __main__ - Step 123807: {'lr': 3.7659297843148893e-05, 'samples': 23770944, 'steps': 123806, 'loss/train': 0.13904012739658356} 08/31/2021 11:43:02 - INFO - __main__ - Step 123808: {'lr': 3.765649694115344e-05, 'samples': 23771136, 'steps': 123807, 'loss/train': 0.5523855090141296} 08/31/2021 11:43:03 - INFO - __main__ - Step 123809: {'lr': 3.7653696134836685e-05, 'samples': 23771328, 'steps': 123808, 'loss/train': 1.4309840202331543} 08/31/2021 11:43:04 - INFO - __main__ - Step 123810: {'lr': 3.765089542419989e-05, 'samples': 23771520, 'steps': 123809, 'loss/train': 0.8339261412620544} 08/31/2021 11:43:05 - INFO - __main__ - Step 123811: {'lr': 3.7648094809244334e-05, 'samples': 23771712, 'steps': 123810, 'loss/train': 0.4190662205219269} 08/31/2021 11:43:05 - INFO - __main__ - Step 123812: {'lr': 3.764529428997127e-05, 'samples': 23771904, 'steps': 123811, 'loss/train': 0.48257678747177124} 08/31/2021 11:43:06 - INFO - __main__ - Step 123813: {'lr': 3.764249386638196e-05, 'samples': 23772096, 'steps': 123812, 'loss/train': 0.24286627769470215} 08/31/2021 11:43:06 - INFO - __main__ - Step 123814: {'lr': 3.7639693538477654e-05, 'samples': 23772288, 'steps': 123813, 'loss/train': 0.9567243456840515} 08/31/2021 11:43:06 - INFO - __main__ - Step 123815: {'lr': 3.7636893306259636e-05, 'samples': 23772480, 'steps': 123814, 'loss/train': 0.6742876768112183} 08/31/2021 11:43:08 - INFO - __main__ - Step 123816: {'lr': 3.7634093169729153e-05, 'samples': 23772672, 'steps': 123815, 'loss/train': 0.727308452129364} 08/31/2021 11:43:09 - INFO - __main__ - Step 123817: {'lr': 3.763129312888747e-05, 'samples': 23772864, 'steps': 123816, 'loss/train': 0.8894245028495789} 08/31/2021 11:43:09 - INFO - __main__ - Step 123818: {'lr': 3.762849318373593e-05, 'samples': 23773056, 'steps': 123817, 'loss/train': 1.3321704864501953} 08/31/2021 11:43:09 - INFO - __main__ - Step 123819: {'lr': 3.7625693334275626e-05, 'samples': 23773248, 'steps': 123818, 'loss/train': 0.9063009023666382} 08/31/2021 11:43:10 - INFO - __main__ - Step 123820: {'lr': 3.7622893580507914e-05, 'samples': 23773440, 'steps': 123819, 'loss/train': 0.23901338875293732} 08/31/2021 11:43:11 - INFO - __main__ - Step 123821: {'lr': 3.762009392243407e-05, 'samples': 23773632, 'steps': 123820, 'loss/train': 0.34124040603637695} 08/31/2021 11:43:12 - INFO - __main__ - Step 123822: {'lr': 3.7617294360055315e-05, 'samples': 23773824, 'steps': 123821, 'loss/train': 0.7788335084915161} 08/31/2021 11:43:12 - INFO - __main__ - Step 123823: {'lr': 3.761449489337293e-05, 'samples': 23774016, 'steps': 123822, 'loss/train': 0.2949274480342865} 08/31/2021 11:43:12 - INFO - __main__ - Step 123824: {'lr': 3.761169552238816e-05, 'samples': 23774208, 'steps': 123823, 'loss/train': 0.5238808393478394} 08/31/2021 11:43:13 - INFO - __main__ - Step 123825: {'lr': 3.7608896247102314e-05, 'samples': 23774400, 'steps': 123824, 'loss/train': 0.6680816411972046} 08/31/2021 11:43:14 - INFO - __main__ - Step 123826: {'lr': 3.760609706751661e-05, 'samples': 23774592, 'steps': 123825, 'loss/train': 1.20729398727417} 08/31/2021 11:43:15 - INFO - __main__ - Step 123827: {'lr': 3.760329798363232e-05, 'samples': 23774784, 'steps': 123826, 'loss/train': 0.9159570932388306} 08/31/2021 11:43:15 - INFO - __main__ - Step 123828: {'lr': 3.7600498995450705e-05, 'samples': 23774976, 'steps': 123827, 'loss/train': 1.3325961828231812} 08/31/2021 11:43:15 - INFO - __main__ - Step 123829: {'lr': 3.759770010297303e-05, 'samples': 23775168, 'steps': 123828, 'loss/train': 0.7083791494369507} 08/31/2021 11:43:16 - INFO - __main__ - Step 123830: {'lr': 3.759490130620055e-05, 'samples': 23775360, 'steps': 123829, 'loss/train': 0.9103718400001526} 08/31/2021 11:43:17 - INFO - __main__ - Step 123831: {'lr': 3.7592102605134596e-05, 'samples': 23775552, 'steps': 123830, 'loss/train': 1.4446111917495728} 08/31/2021 11:43:18 - INFO - __main__ - Step 123832: {'lr': 3.758930399977631e-05, 'samples': 23775744, 'steps': 123831, 'loss/train': 1.4083127975463867} 08/31/2021 11:43:18 - INFO - __main__ - Step 123833: {'lr': 3.7586505490126986e-05, 'samples': 23775936, 'steps': 123832, 'loss/train': 0.3744855523109436} 08/31/2021 11:43:18 - INFO - __main__ - Step 123834: {'lr': 3.758370707618791e-05, 'samples': 23776128, 'steps': 123833, 'loss/train': 1.1231623888015747} 08/31/2021 11:43:19 - INFO - __main__ - Step 123835: {'lr': 3.758090875796033e-05, 'samples': 23776320, 'steps': 123834, 'loss/train': 1.0665396451950073} 08/31/2021 11:43:20 - INFO - __main__ - Step 123836: {'lr': 3.757811053544555e-05, 'samples': 23776512, 'steps': 123835, 'loss/train': 0.3881835639476776} 08/31/2021 11:43:21 - INFO - __main__ - Step 123837: {'lr': 3.7575312408644756e-05, 'samples': 23776704, 'steps': 123836, 'loss/train': 1.0971102714538574} 08/31/2021 11:43:21 - INFO - __main__ - Step 123838: {'lr': 3.757251437755926e-05, 'samples': 23776896, 'steps': 123837, 'loss/train': 1.1488820314407349} 08/31/2021 11:43:21 - INFO - __main__ - Step 123839: {'lr': 3.7569716442190315e-05, 'samples': 23777088, 'steps': 123838, 'loss/train': 1.280220866203308} 08/31/2021 11:43:22 - INFO - __main__ - Step 123840: {'lr': 3.756691860253919e-05, 'samples': 23777280, 'steps': 123839, 'loss/train': 1.2901644706726074} 08/31/2021 11:43:22 - INFO - __main__ - Step 123841: {'lr': 3.7564120858607134e-05, 'samples': 23777472, 'steps': 123840, 'loss/train': 1.3721165657043457} 08/31/2021 11:43:24 - INFO - __main__ - Step 123842: {'lr': 3.7561323210395434e-05, 'samples': 23777664, 'steps': 123841, 'loss/train': 1.170522689819336} 08/31/2021 11:43:24 - INFO - __main__ - Step 123843: {'lr': 3.7558525657905294e-05, 'samples': 23777856, 'steps': 123842, 'loss/train': 0.9367201924324036} 08/31/2021 11:43:25 - INFO - __main__ - Step 123844: {'lr': 3.755572820113801e-05, 'samples': 23778048, 'steps': 123843, 'loss/train': 0.26670125126838684} 08/31/2021 11:43:25 - INFO - __main__ - Step 123845: {'lr': 3.755293084009481e-05, 'samples': 23778240, 'steps': 123844, 'loss/train': 0.4254930317401886} 08/31/2021 11:43:25 - INFO - __main__ - Step 123846: {'lr': 3.755013357477699e-05, 'samples': 23778432, 'steps': 123845, 'loss/train': 0.7507856488227844} 08/31/2021 11:43:27 - INFO - __main__ - Step 123847: {'lr': 3.754733640518582e-05, 'samples': 23778624, 'steps': 123846, 'loss/train': 1.0343436002731323} 08/31/2021 11:43:28 - INFO - __main__ - Step 123848: {'lr': 3.7544539331322514e-05, 'samples': 23778816, 'steps': 123847, 'loss/train': 0.9181087613105774} 08/31/2021 11:43:28 - INFO - __main__ - Step 123849: {'lr': 3.754174235318836e-05, 'samples': 23779008, 'steps': 123848, 'loss/train': 1.7173073291778564} 08/31/2021 11:43:28 - INFO - __main__ - Step 123850: {'lr': 3.753894547078465e-05, 'samples': 23779200, 'steps': 123849, 'loss/train': 0.8700158596038818} 08/31/2021 11:43:29 - INFO - __main__ - Step 123851: {'lr': 3.753614868411259e-05, 'samples': 23779392, 'steps': 123850, 'loss/train': 1.9203495979309082} 08/31/2021 11:43:29 - INFO - __main__ - Step 123852: {'lr': 3.7533351993173454e-05, 'samples': 23779584, 'steps': 123851, 'loss/train': 0.09489987045526505} 08/31/2021 11:43:31 - INFO - __main__ - Step 123853: {'lr': 3.75305553979686e-05, 'samples': 23779776, 'steps': 123852, 'loss/train': 0.3428654074668884} 08/31/2021 11:43:32 - INFO - __main__ - Step 123854: {'lr': 3.7527758898499105e-05, 'samples': 23779968, 'steps': 123853, 'loss/train': 1.5840040445327759} 08/31/2021 11:43:32 - INFO - __main__ - Step 123855: {'lr': 3.752496249476634e-05, 'samples': 23780160, 'steps': 123854, 'loss/train': 0.7012525200843811} 08/31/2021 11:43:32 - INFO - __main__ - Step 123856: {'lr': 3.752216618677157e-05, 'samples': 23780352, 'steps': 123855, 'loss/train': 1.7237422466278076} 08/31/2021 11:43:33 - INFO - __main__ - Step 123857: {'lr': 3.7519369974515994e-05, 'samples': 23780544, 'steps': 123856, 'loss/train': 1.4414784908294678} 08/31/2021 11:43:34 - INFO - __main__ - Step 123858: {'lr': 3.7516573858000945e-05, 'samples': 23780736, 'steps': 123857, 'loss/train': 0.9936444759368896} 08/31/2021 11:43:35 - INFO - __main__ - Step 123859: {'lr': 3.7513777837227616e-05, 'samples': 23780928, 'steps': 123858, 'loss/train': 1.1450749635696411} 08/31/2021 11:43:35 - INFO - __main__ - Step 123860: {'lr': 3.7510981912197315e-05, 'samples': 23781120, 'steps': 123859, 'loss/train': 1.2353837490081787} 08/31/2021 11:43:36 - INFO - __main__ - Step 123861: {'lr': 3.750818608291129e-05, 'samples': 23781312, 'steps': 123860, 'loss/train': 1.0110433101654053} 08/31/2021 11:43:36 - INFO - __main__ - Step 123862: {'lr': 3.750539034937081e-05, 'samples': 23781504, 'steps': 123861, 'loss/train': 1.6080913543701172} 08/31/2021 11:43:38 - INFO - __main__ - Step 123863: {'lr': 3.7502594711577105e-05, 'samples': 23781696, 'steps': 123862, 'loss/train': 1.0433740615844727} 08/31/2021 11:43:38 - INFO - __main__ - Step 123864: {'lr': 3.74997991695315e-05, 'samples': 23781888, 'steps': 123863, 'loss/train': 0.014272368513047695} 08/31/2021 11:43:39 - INFO - __main__ - Step 123865: {'lr': 3.749700372323517e-05, 'samples': 23782080, 'steps': 123864, 'loss/train': 0.014401481486856937} 08/31/2021 11:43:39 - INFO - __main__ - Step 123866: {'lr': 3.749420837268941e-05, 'samples': 23782272, 'steps': 123865, 'loss/train': 1.2155622243881226} 08/31/2021 11:43:39 - INFO - __main__ - Step 123867: {'lr': 3.7491413117895474e-05, 'samples': 23782464, 'steps': 123866, 'loss/train': 1.362877607345581} 08/31/2021 11:43:40 - INFO - __main__ - Step 123868: {'lr': 3.748861795885461e-05, 'samples': 23782656, 'steps': 123867, 'loss/train': 0.2933042645454407} 08/31/2021 11:43:41 - INFO - __main__ - Step 123869: {'lr': 3.7485822895568125e-05, 'samples': 23782848, 'steps': 123868, 'loss/train': 0.9600498676300049} 08/31/2021 11:43:42 - INFO - __main__ - Step 123870: {'lr': 3.7483027928037236e-05, 'samples': 23783040, 'steps': 123869, 'loss/train': 1.5192697048187256} 08/31/2021 11:43:42 - INFO - __main__ - Step 123871: {'lr': 3.748023305626322e-05, 'samples': 23783232, 'steps': 123870, 'loss/train': 0.9143449068069458} 08/31/2021 11:43:42 - INFO - __main__ - Step 123872: {'lr': 3.747743828024733e-05, 'samples': 23783424, 'steps': 123871, 'loss/train': 0.5237845182418823} 08/31/2021 11:43:43 - INFO - __main__ - Step 123873: {'lr': 3.747464359999081e-05, 'samples': 23783616, 'steps': 123872, 'loss/train': 0.26131412386894226} 08/31/2021 11:43:44 - INFO - __main__ - Step 123874: {'lr': 3.747184901549497e-05, 'samples': 23783808, 'steps': 123873, 'loss/train': 0.8165705800056458} 08/31/2021 11:43:45 - INFO - __main__ - Step 123875: {'lr': 3.746905452676105e-05, 'samples': 23784000, 'steps': 123874, 'loss/train': 0.849319338798523} 08/31/2021 11:43:45 - INFO - __main__ - Step 123876: {'lr': 3.746626013379026e-05, 'samples': 23784192, 'steps': 123875, 'loss/train': 0.814163863658905} 08/31/2021 11:43:45 - INFO - __main__ - Step 123877: {'lr': 3.746346583658392e-05, 'samples': 23784384, 'steps': 123876, 'loss/train': 1.0617817640304565} 08/31/2021 11:43:46 - INFO - __main__ - Step 123878: {'lr': 3.7460671635143216e-05, 'samples': 23784576, 'steps': 123877, 'loss/train': 0.5731699466705322} 08/31/2021 11:43:47 - INFO - __main__ - Step 123879: {'lr': 3.745787752946947e-05, 'samples': 23784768, 'steps': 123878, 'loss/train': 1.4955438375473022} 08/31/2021 11:43:48 - INFO - __main__ - Step 123880: {'lr': 3.7455083519563945e-05, 'samples': 23784960, 'steps': 123879, 'loss/train': 0.10117305815219879} 08/31/2021 11:43:48 - INFO - __main__ - Step 123881: {'lr': 3.745228960542785e-05, 'samples': 23785152, 'steps': 123880, 'loss/train': 1.3509505987167358} 08/31/2021 11:43:49 - INFO - __main__ - Step 123882: {'lr': 3.74494957870625e-05, 'samples': 23785344, 'steps': 123881, 'loss/train': 0.6549122929573059} 08/31/2021 11:43:49 - INFO - __main__ - Step 123883: {'lr': 3.7446702064469094e-05, 'samples': 23785536, 'steps': 123882, 'loss/train': 1.1360559463500977} 08/31/2021 11:43:50 - INFO - __main__ - Step 123884: {'lr': 3.744390843764897e-05, 'samples': 23785728, 'steps': 123883, 'loss/train': 1.6435699462890625} 08/31/2021 11:43:51 - INFO - __main__ - Step 123885: {'lr': 3.744111490660329e-05, 'samples': 23785920, 'steps': 123884, 'loss/train': 1.3931257724761963} 08/31/2021 11:43:51 - INFO - __main__ - Step 123886: {'lr': 3.743832147133347e-05, 'samples': 23786112, 'steps': 123885, 'loss/train': 0.8992490172386169} 08/31/2021 11:43:52 - INFO - __main__ - Step 123887: {'lr': 3.7435528131840564e-05, 'samples': 23786304, 'steps': 123886, 'loss/train': 0.6267294883728027} 08/31/2021 11:43:52 - INFO - __main__ - Step 123888: {'lr': 3.7432734888125956e-05, 'samples': 23786496, 'steps': 123887, 'loss/train': 1.0397430658340454} 08/31/2021 11:43:52 - INFO - __main__ - Step 123889: {'lr': 3.742994174019088e-05, 'samples': 23786688, 'steps': 123888, 'loss/train': 1.653175711631775} 08/31/2021 11:43:54 - INFO - __main__ - Step 123890: {'lr': 3.7427148688036566e-05, 'samples': 23786880, 'steps': 123889, 'loss/train': 1.3271446228027344} 08/31/2021 11:43:54 - INFO - __main__ - Step 123891: {'lr': 3.7424355731664306e-05, 'samples': 23787072, 'steps': 123890, 'loss/train': 1.3667572736740112} 08/31/2021 11:43:55 - INFO - __main__ - Step 123892: {'lr': 3.742156287107537e-05, 'samples': 23787264, 'steps': 123891, 'loss/train': 1.030250072479248} 08/31/2021 11:43:55 - INFO - __main__ - Step 123893: {'lr': 3.741877010627098e-05, 'samples': 23787456, 'steps': 123892, 'loss/train': 0.8977339267730713} 08/31/2021 11:43:55 - INFO - __main__ - Step 123894: {'lr': 3.741597743725242e-05, 'samples': 23787648, 'steps': 123893, 'loss/train': 0.3082190155982971} 08/31/2021 11:43:57 - INFO - __main__ - Step 123895: {'lr': 3.7413184864020924e-05, 'samples': 23787840, 'steps': 123894, 'loss/train': 1.326444387435913} 08/31/2021 11:43:57 - INFO - __main__ - Step 123896: {'lr': 3.741039238657778e-05, 'samples': 23788032, 'steps': 123895, 'loss/train': 0.9798604846000671} 08/31/2021 11:43:58 - INFO - __main__ - Step 123897: {'lr': 3.740760000492424e-05, 'samples': 23788224, 'steps': 123896, 'loss/train': 0.966160774230957} 08/31/2021 11:43:58 - INFO - __main__ - Step 123898: {'lr': 3.74048077190616e-05, 'samples': 23788416, 'steps': 123897, 'loss/train': 0.7601398229598999} 08/31/2021 11:43:58 - INFO - __main__ - Step 123899: {'lr': 3.740201552899103e-05, 'samples': 23788608, 'steps': 123898, 'loss/train': 0.9569357633590698} 08/31/2021 11:44:00 - INFO - __main__ - Step 123900: {'lr': 3.739922343471383e-05, 'samples': 23788800, 'steps': 123899, 'loss/train': 1.2782129049301147} 08/31/2021 11:44:00 - INFO - __main__ - Step 123901: {'lr': 3.7396431436231256e-05, 'samples': 23788992, 'steps': 123900, 'loss/train': 5.667054653167725} 08/31/2021 11:44:01 - INFO - __main__ - Step 123902: {'lr': 3.739363953354455e-05, 'samples': 23789184, 'steps': 123901, 'loss/train': 1.0573922395706177} 08/31/2021 11:44:01 - INFO - __main__ - Step 123903: {'lr': 3.739084772665499e-05, 'samples': 23789376, 'steps': 123902, 'loss/train': 1.3296788930892944} 08/31/2021 11:44:02 - INFO - __main__ - Step 123904: {'lr': 3.738805601556386e-05, 'samples': 23789568, 'steps': 123903, 'loss/train': 1.4408209323883057} 08/31/2021 11:44:03 - INFO - __main__ - Step 123905: {'lr': 3.7385264400272376e-05, 'samples': 23789760, 'steps': 123904, 'loss/train': 1.4291751384735107} 08/31/2021 11:44:04 - INFO - __main__ - Step 123906: {'lr': 3.738247288078181e-05, 'samples': 23789952, 'steps': 123905, 'loss/train': 1.31768798828125} 08/31/2021 11:44:04 - INFO - __main__ - Step 123907: {'lr': 3.737968145709342e-05, 'samples': 23790144, 'steps': 123906, 'loss/train': 0.7166080474853516} 08/31/2021 11:44:04 - INFO - __main__ - Step 123908: {'lr': 3.7376890129208476e-05, 'samples': 23790336, 'steps': 123907, 'loss/train': 1.1094616651535034} 08/31/2021 11:44:05 - INFO - __main__ - Step 123909: {'lr': 3.737409889712823e-05, 'samples': 23790528, 'steps': 123908, 'loss/train': 0.7149500250816345} 08/31/2021 11:44:07 - INFO - __main__ - Step 123910: {'lr': 3.73713077608539e-05, 'samples': 23790720, 'steps': 123909, 'loss/train': 0.7984288334846497} 08/31/2021 11:44:08 - INFO - __main__ - Step 123911: {'lr': 3.73685167203868e-05, 'samples': 23790912, 'steps': 123910, 'loss/train': 1.0758459568023682} 08/31/2021 11:44:08 - INFO - __main__ - Step 123912: {'lr': 3.736572577572822e-05, 'samples': 23791104, 'steps': 123911, 'loss/train': 0.9261213541030884} 08/31/2021 11:44:09 - INFO - __main__ - Step 123913: {'lr': 3.736293492687931e-05, 'samples': 23791296, 'steps': 123912, 'loss/train': 1.207344651222229} 08/31/2021 11:44:09 - INFO - __main__ - Step 123914: {'lr': 3.736014417384137e-05, 'samples': 23791488, 'steps': 123913, 'loss/train': 1.0499714612960815} 08/31/2021 11:44:09 - INFO - __main__ - Step 123915: {'lr': 3.7357353516615675e-05, 'samples': 23791680, 'steps': 123914, 'loss/train': 1.1405881643295288} 08/31/2021 11:44:11 - INFO - __main__ - Step 123916: {'lr': 3.735456295520348e-05, 'samples': 23791872, 'steps': 123915, 'loss/train': 0.9396486878395081} 08/31/2021 11:44:11 - INFO - __main__ - Step 123917: {'lr': 3.735177248960603e-05, 'samples': 23792064, 'steps': 123916, 'loss/train': 1.721073865890503} 08/31/2021 11:44:12 - INFO - __main__ - Step 123918: {'lr': 3.7348982119824596e-05, 'samples': 23792256, 'steps': 123917, 'loss/train': 0.47321826219558716} 08/31/2021 11:44:12 - INFO - __main__ - Step 123919: {'lr': 3.734619184586044e-05, 'samples': 23792448, 'steps': 123918, 'loss/train': 1.4076473712921143} 08/31/2021 11:44:13 - INFO - __main__ - Step 123920: {'lr': 3.734340166771477e-05, 'samples': 23792640, 'steps': 123919, 'loss/train': 1.156428337097168} 08/31/2021 11:44:13 - INFO - __main__ - Step 123921: {'lr': 3.734061158538893e-05, 'samples': 23792832, 'steps': 123920, 'loss/train': 0.4465612769126892} 08/31/2021 11:44:14 - INFO - __main__ - Step 123922: {'lr': 3.7337821598884106e-05, 'samples': 23793024, 'steps': 123921, 'loss/train': 0.033213596791028976} 08/31/2021 11:44:15 - INFO - __main__ - Step 123923: {'lr': 3.733503170820157e-05, 'samples': 23793216, 'steps': 123922, 'loss/train': 1.1056408882141113} 08/31/2021 11:44:15 - INFO - __main__ - Step 123924: {'lr': 3.733224191334258e-05, 'samples': 23793408, 'steps': 123923, 'loss/train': 0.9964534044265747} 08/31/2021 11:44:16 - INFO - __main__ - Step 123925: {'lr': 3.7329452214308474e-05, 'samples': 23793600, 'steps': 123924, 'loss/train': 0.8881022334098816} 08/31/2021 11:44:16 - INFO - __main__ - Step 123926: {'lr': 3.7326662611100376e-05, 'samples': 23793792, 'steps': 123925, 'loss/train': 0.358038991689682} 08/31/2021 11:44:17 - INFO - __main__ - Step 123927: {'lr': 3.7323873103719594e-05, 'samples': 23793984, 'steps': 123926, 'loss/train': 0.1632864773273468} 08/31/2021 11:44:18 - INFO - __main__ - Step 123928: {'lr': 3.732108369216741e-05, 'samples': 23794176, 'steps': 123927, 'loss/train': 1.465745210647583} 08/31/2021 11:44:18 - INFO - __main__ - Step 123929: {'lr': 3.731829437644507e-05, 'samples': 23794368, 'steps': 123928, 'loss/train': 1.2169721126556396} 08/31/2021 11:44:19 - INFO - __main__ - Step 123930: {'lr': 3.73155051565538e-05, 'samples': 23794560, 'steps': 123929, 'loss/train': 1.7558609247207642} 08/31/2021 11:44:19 - INFO - __main__ - Step 123931: {'lr': 3.731271603249489e-05, 'samples': 23794752, 'steps': 123930, 'loss/train': 1.3429114818572998} 08/31/2021 11:44:21 - INFO - __main__ - Step 123932: {'lr': 3.7309927004269575e-05, 'samples': 23794944, 'steps': 123931, 'loss/train': 1.7218269109725952} 08/31/2021 11:44:21 - INFO - __main__ - Step 123933: {'lr': 3.730713807187916e-05, 'samples': 23795136, 'steps': 123932, 'loss/train': 1.2713121175765991} 08/31/2021 11:44:21 - INFO - __main__ - Step 123934: {'lr': 3.730434923532483e-05, 'samples': 23795328, 'steps': 123933, 'loss/train': 1.1008998155593872} 08/31/2021 11:44:22 - INFO - __main__ - Step 123935: {'lr': 3.7301560494607894e-05, 'samples': 23795520, 'steps': 123934, 'loss/train': 1.3714616298675537} 08/31/2021 11:44:22 - INFO - __main__ - Step 123936: {'lr': 3.72987718497296e-05, 'samples': 23795712, 'steps': 123935, 'loss/train': 0.7009478807449341} 08/31/2021 11:44:23 - INFO - __main__ - Step 123937: {'lr': 3.729598330069117e-05, 'samples': 23795904, 'steps': 123936, 'loss/train': 0.699102520942688} 08/31/2021 11:44:24 - INFO - __main__ - Step 123938: {'lr': 3.729319484749391e-05, 'samples': 23796096, 'steps': 123937, 'loss/train': 1.1538454294204712} 08/31/2021 11:44:24 - INFO - __main__ - Step 123939: {'lr': 3.729040649013912e-05, 'samples': 23796288, 'steps': 123938, 'loss/train': 0.4809262454509735} 08/31/2021 11:44:25 - INFO - __main__ - Step 123940: {'lr': 3.7287618228627916e-05, 'samples': 23796480, 'steps': 123939, 'loss/train': 1.3258841037750244} 08/31/2021 11:44:25 - INFO - __main__ - Step 123941: {'lr': 3.728483006296163e-05, 'samples': 23796672, 'steps': 123940, 'loss/train': 0.8859221935272217} 08/31/2021 11:44:25 - INFO - __main__ - Step 123942: {'lr': 3.728204199314153e-05, 'samples': 23796864, 'steps': 123941, 'loss/train': 0.7856388688087463} 08/31/2021 11:44:27 - INFO - __main__ - Step 123943: {'lr': 3.7279254019168845e-05, 'samples': 23797056, 'steps': 123942, 'loss/train': 1.417716383934021} 08/31/2021 11:44:27 - INFO - __main__ - Step 123944: {'lr': 3.727646614104485e-05, 'samples': 23797248, 'steps': 123943, 'loss/train': 0.8877343535423279} 08/31/2021 11:44:28 - INFO - __main__ - Step 123945: {'lr': 3.7273678358770795e-05, 'samples': 23797440, 'steps': 123944, 'loss/train': 0.49404680728912354} 08/31/2021 11:44:28 - INFO - __main__ - Step 123946: {'lr': 3.7270890672347955e-05, 'samples': 23797632, 'steps': 123945, 'loss/train': 0.8565603494644165} 08/31/2021 11:44:28 - INFO - __main__ - Step 123947: {'lr': 3.726810308177755e-05, 'samples': 23797824, 'steps': 123946, 'loss/train': 0.10692185908555984} 08/31/2021 11:44:30 - INFO - __main__ - Step 123948: {'lr': 3.726531558706087e-05, 'samples': 23798016, 'steps': 123947, 'loss/train': 0.7094577550888062} 08/31/2021 11:44:30 - INFO - __main__ - Step 123949: {'lr': 3.726252818819914e-05, 'samples': 23798208, 'steps': 123948, 'loss/train': 0.8907232284545898} 08/31/2021 11:44:31 - INFO - __main__ - Step 123950: {'lr': 3.7259740885193626e-05, 'samples': 23798400, 'steps': 123949, 'loss/train': 1.2108237743377686} 08/31/2021 11:44:31 - INFO - __main__ - Step 123951: {'lr': 3.72569536780456e-05, 'samples': 23798592, 'steps': 123950, 'loss/train': 1.6860404014587402} 08/31/2021 11:44:31 - INFO - __main__ - Step 123952: {'lr': 3.725416656675637e-05, 'samples': 23798784, 'steps': 123951, 'loss/train': 0.833948016166687} 08/31/2021 11:44:33 - INFO - __main__ - Step 123953: {'lr': 3.725137955132707e-05, 'samples': 23798976, 'steps': 123952, 'loss/train': 0.7259377241134644} 08/31/2021 11:44:33 - INFO - __main__ - Step 123954: {'lr': 3.7248592631759035e-05, 'samples': 23799168, 'steps': 123953, 'loss/train': 0.945595383644104} 08/31/2021 11:44:34 - INFO - __main__ - Step 123955: {'lr': 3.7245805808053476e-05, 'samples': 23799360, 'steps': 123954, 'loss/train': 0.8620590567588806} 08/31/2021 11:44:34 - INFO - __main__ - Step 123956: {'lr': 3.724301908021169e-05, 'samples': 23799552, 'steps': 123955, 'loss/train': 0.6964401006698608} 08/31/2021 11:44:34 - INFO - __main__ - Step 123957: {'lr': 3.7240232448234905e-05, 'samples': 23799744, 'steps': 123956, 'loss/train': 1.122365117073059} 08/31/2021 11:44:36 - INFO - __main__ - Step 123958: {'lr': 3.723744591212439e-05, 'samples': 23799936, 'steps': 123957, 'loss/train': 0.49515989422798157} 08/31/2021 11:44:37 - INFO - __main__ - Step 123959: {'lr': 3.7234659471881397e-05, 'samples': 23800128, 'steps': 123958, 'loss/train': 0.34487026929855347} 08/31/2021 11:44:37 - INFO - __main__ - Step 123960: {'lr': 3.7231873127507174e-05, 'samples': 23800320, 'steps': 123959, 'loss/train': 0.9834890365600586} 08/31/2021 11:44:38 - INFO - __main__ - Step 123961: {'lr': 3.722908687900301e-05, 'samples': 23800512, 'steps': 123960, 'loss/train': 1.598270058631897} 08/31/2021 11:44:38 - INFO - __main__ - Step 123962: {'lr': 3.722630072637012e-05, 'samples': 23800704, 'steps': 123961, 'loss/train': 0.05083039775490761} 08/31/2021 11:44:38 - INFO - __main__ - Step 123963: {'lr': 3.722351466960977e-05, 'samples': 23800896, 'steps': 123962, 'loss/train': 0.01553510781377554} 08/31/2021 11:44:40 - INFO - __main__ - Step 123964: {'lr': 3.7220728708723225e-05, 'samples': 23801088, 'steps': 123963, 'loss/train': 0.014047102071344852} 08/31/2021 11:44:41 - INFO - __main__ - Step 123965: {'lr': 3.721794284371174e-05, 'samples': 23801280, 'steps': 123964, 'loss/train': 1.2929869890213013} 08/31/2021 11:44:41 - INFO - __main__ - Step 123966: {'lr': 3.721515707457662e-05, 'samples': 23801472, 'steps': 123965, 'loss/train': 0.6217116117477417} 08/31/2021 11:44:41 - INFO - __main__ - Step 123967: {'lr': 3.721237140131903e-05, 'samples': 23801664, 'steps': 123966, 'loss/train': 1.4343981742858887} 08/31/2021 11:44:42 - INFO - __main__ - Step 123968: {'lr': 3.7209585823940236e-05, 'samples': 23801856, 'steps': 123967, 'loss/train': 1.2096209526062012} 08/31/2021 11:44:42 - INFO - __main__ - Step 123969: {'lr': 3.7206800342441534e-05, 'samples': 23802048, 'steps': 123968, 'loss/train': 1.1610677242279053} 08/31/2021 11:44:44 - INFO - __main__ - Step 123970: {'lr': 3.7204014956824155e-05, 'samples': 23802240, 'steps': 123969, 'loss/train': 0.7787593007087708} 08/31/2021 11:44:45 - INFO - __main__ - Step 123971: {'lr': 3.720122966708936e-05, 'samples': 23802432, 'steps': 123970, 'loss/train': 1.7373013496398926} 08/31/2021 11:44:45 - INFO - __main__ - Step 123972: {'lr': 3.719844447323842e-05, 'samples': 23802624, 'steps': 123971, 'loss/train': 0.6283868551254272} 08/31/2021 11:44:45 - INFO - __main__ - Step 123973: {'lr': 3.7195659375272555e-05, 'samples': 23802816, 'steps': 123972, 'loss/train': 1.1362360715866089} 08/31/2021 11:44:46 - INFO - __main__ - Step 123974: {'lr': 3.719287437319308e-05, 'samples': 23803008, 'steps': 123973, 'loss/train': 0.7911549806594849} 08/31/2021 11:44:47 - INFO - __main__ - Step 123975: {'lr': 3.719008946700117e-05, 'samples': 23803200, 'steps': 123974, 'loss/train': 0.8988273739814758} 08/31/2021 11:44:48 - INFO - __main__ - Step 123976: {'lr': 3.7187304656698145e-05, 'samples': 23803392, 'steps': 123975, 'loss/train': 1.4796148538589478} 08/31/2021 11:44:48 - INFO - __main__ - Step 123977: {'lr': 3.718451994228525e-05, 'samples': 23803584, 'steps': 123976, 'loss/train': 0.12064742296934128} 08/31/2021 11:44:48 - INFO - __main__ - Step 123978: {'lr': 3.7181735323763707e-05, 'samples': 23803776, 'steps': 123977, 'loss/train': 0.9153440594673157} 08/31/2021 11:44:49 - INFO - __main__ - Step 123979: {'lr': 3.717895080113484e-05, 'samples': 23803968, 'steps': 123978, 'loss/train': 1.5373398065567017} 08/31/2021 11:44:51 - INFO - __main__ - Step 123980: {'lr': 3.71761663743998e-05, 'samples': 23804160, 'steps': 123979, 'loss/train': 2.3553082942962646} 08/31/2021 11:44:51 - INFO - __main__ - Step 123981: {'lr': 3.717338204355991e-05, 'samples': 23804352, 'steps': 123980, 'loss/train': 1.3710460662841797} 08/31/2021 11:44:51 - INFO - __main__ - Step 123982: {'lr': 3.7170597808616396e-05, 'samples': 23804544, 'steps': 123981, 'loss/train': 0.8166511058807373} 08/31/2021 11:44:52 - INFO - __main__ - Step 123983: {'lr': 3.7167813669570535e-05, 'samples': 23804736, 'steps': 123982, 'loss/train': 0.038934096693992615} 08/31/2021 11:44:52 - INFO - __main__ - Step 123984: {'lr': 3.716502962642357e-05, 'samples': 23804928, 'steps': 123983, 'loss/train': 1.0611591339111328} 08/31/2021 11:44:54 - INFO - __main__ - Step 123985: {'lr': 3.716224567917678e-05, 'samples': 23805120, 'steps': 123984, 'loss/train': 1.044368863105774} 08/31/2021 11:44:54 - INFO - __main__ - Step 123986: {'lr': 3.715946182783136e-05, 'samples': 23805312, 'steps': 123985, 'loss/train': 1.8638088703155518} 08/31/2021 11:44:55 - INFO - __main__ - Step 123987: {'lr': 3.7156678072388624e-05, 'samples': 23805504, 'steps': 123986, 'loss/train': 1.0567117929458618} 08/31/2021 11:44:55 - INFO - __main__ - Step 123988: {'lr': 3.71538944128498e-05, 'samples': 23805696, 'steps': 123987, 'loss/train': 1.3202415704727173} 08/31/2021 11:44:56 - INFO - __main__ - Step 123989: {'lr': 3.7151110849216156e-05, 'samples': 23805888, 'steps': 123988, 'loss/train': 0.513256847858429} 08/31/2021 11:44:56 - INFO - __main__ - Step 123990: {'lr': 3.7148327381488906e-05, 'samples': 23806080, 'steps': 123989, 'loss/train': 1.2206298112869263} 08/31/2021 11:44:58 - INFO - __main__ - Step 123991: {'lr': 3.714554400966938e-05, 'samples': 23806272, 'steps': 123990, 'loss/train': 1.4220621585845947} 08/31/2021 11:44:58 - INFO - __main__ - Step 123992: {'lr': 3.714276073375875e-05, 'samples': 23806464, 'steps': 123991, 'loss/train': 1.3010611534118652} 08/31/2021 11:44:58 - INFO - __main__ - Step 123993: {'lr': 3.713997755375839e-05, 'samples': 23806656, 'steps': 123992, 'loss/train': 1.413791537284851} 08/31/2021 11:44:59 - INFO - __main__ - Step 123994: {'lr': 3.71371944696694e-05, 'samples': 23806848, 'steps': 123993, 'loss/train': 0.2628796398639679} 08/31/2021 11:44:59 - INFO - __main__ - Step 123995: {'lr': 3.7134411481493106e-05, 'samples': 23807040, 'steps': 123994, 'loss/train': 1.1874457597732544} 08/31/2021 11:44:59 - INFO - __main__ - Step 123996: {'lr': 3.713162858923075e-05, 'samples': 23807232, 'steps': 123995, 'loss/train': 0.8514217734336853} 08/31/2021 11:45:01 - INFO - __main__ - Step 123997: {'lr': 3.7128845792883614e-05, 'samples': 23807424, 'steps': 123996, 'loss/train': 0.7324699759483337} 08/31/2021 11:45:01 - INFO - __main__ - Step 123998: {'lr': 3.712606309245295e-05, 'samples': 23807616, 'steps': 123997, 'loss/train': 0.6750713586807251} 08/31/2021 11:45:02 - INFO - __main__ - Step 123999: {'lr': 3.712328048793997e-05, 'samples': 23807808, 'steps': 123998, 'loss/train': 1.3835488557815552} 08/31/2021 11:45:02 - INFO - __main__ - Step 124000: {'lr': 3.712049797934597e-05, 'samples': 23808000, 'steps': 123999, 'loss/train': 0.9955964088439941} 08/31/2021 11:45:03 - INFO - __main__ - Step 124001: {'lr': 3.711771556667218e-05, 'samples': 23808192, 'steps': 124000, 'loss/train': 0.6763427257537842} 08/31/2021 11:45:04 - INFO - __main__ - Step 124002: {'lr': 3.711493324991985e-05, 'samples': 23808384, 'steps': 124001, 'loss/train': 1.6508680582046509} 08/31/2021 11:45:04 - INFO - __main__ - Step 124003: {'lr': 3.711215102909027e-05, 'samples': 23808576, 'steps': 124002, 'loss/train': 0.27888450026512146} 08/31/2021 11:45:05 - INFO - __main__ - Step 124004: {'lr': 3.710936890418468e-05, 'samples': 23808768, 'steps': 124003, 'loss/train': 1.1043397188186646} 08/31/2021 11:45:05 - INFO - __main__ - Step 124005: {'lr': 3.71065868752043e-05, 'samples': 23808960, 'steps': 124004, 'loss/train': 1.0081703662872314} 08/31/2021 11:45:06 - INFO - __main__ - Step 124006: {'lr': 3.710380494215046e-05, 'samples': 23809152, 'steps': 124005, 'loss/train': 0.7225137948989868} 08/31/2021 11:45:07 - INFO - __main__ - Step 124007: {'lr': 3.7101023105024305e-05, 'samples': 23809344, 'steps': 124006, 'loss/train': 0.8455237150192261} 08/31/2021 11:45:07 - INFO - __main__ - Step 124008: {'lr': 3.709824136382717e-05, 'samples': 23809536, 'steps': 124007, 'loss/train': 0.9448246359825134} 08/31/2021 11:45:08 - INFO - __main__ - Step 124009: {'lr': 3.709545971856024e-05, 'samples': 23809728, 'steps': 124008, 'loss/train': 1.347351312637329} 08/31/2021 11:45:08 - INFO - __main__ - Step 124010: {'lr': 3.709267816922485e-05, 'samples': 23809920, 'steps': 124009, 'loss/train': 1.2966282367706299} 08/31/2021 11:45:08 - INFO - __main__ - Step 124011: {'lr': 3.708989671582219e-05, 'samples': 23810112, 'steps': 124010, 'loss/train': 1.2659051418304443} 08/31/2021 11:45:10 - INFO - __main__ - Step 124012: {'lr': 3.7087115358353545e-05, 'samples': 23810304, 'steps': 124011, 'loss/train': 1.160518765449524} 08/31/2021 11:45:11 - INFO - __main__ - Step 124013: {'lr': 3.708433409682016e-05, 'samples': 23810496, 'steps': 124012, 'loss/train': 0.9773573875427246} 08/31/2021 11:45:11 - INFO - __main__ - Step 124014: {'lr': 3.708155293122328e-05, 'samples': 23810688, 'steps': 124013, 'loss/train': 0.8205664157867432} 08/31/2021 11:45:11 - INFO - __main__ - Step 124015: {'lr': 3.707877186156419e-05, 'samples': 23810880, 'steps': 124014, 'loss/train': 0.9126566648483276} 08/31/2021 11:45:12 - INFO - __main__ - Step 124016: {'lr': 3.707599088784411e-05, 'samples': 23811072, 'steps': 124015, 'loss/train': 0.9883593916893005} 08/31/2021 11:45:12 - INFO - __main__ - Step 124017: {'lr': 3.707321001006428e-05, 'samples': 23811264, 'steps': 124016, 'loss/train': 1.8020572662353516} 08/31/2021 11:45:14 - INFO - __main__ - Step 124018: {'lr': 3.707042922822601e-05, 'samples': 23811456, 'steps': 124017, 'loss/train': 0.47844910621643066} 08/31/2021 11:45:15 - INFO - __main__ - Step 124019: {'lr': 3.706764854233055e-05, 'samples': 23811648, 'steps': 124018, 'loss/train': 1.0257009267807007} 08/31/2021 11:45:15 - INFO - __main__ - Step 124020: {'lr': 3.7064867952379066e-05, 'samples': 23811840, 'steps': 124019, 'loss/train': 0.524770975112915} 08/31/2021 11:45:15 - INFO - __main__ - Step 124021: {'lr': 3.706208745837289e-05, 'samples': 23812032, 'steps': 124020, 'loss/train': 1.8622002601623535} 08/31/2021 11:45:16 - INFO - __main__ - Step 124022: {'lr': 3.705930706031321e-05, 'samples': 23812224, 'steps': 124021, 'loss/train': 0.23058564960956573} 08/31/2021 11:45:17 - INFO - __main__ - Step 124023: {'lr': 3.705652675820137e-05, 'samples': 23812416, 'steps': 124022, 'loss/train': 0.9990926384925842} 08/31/2021 11:45:18 - INFO - __main__ - Step 124024: {'lr': 3.705374655203855e-05, 'samples': 23812608, 'steps': 124023, 'loss/train': 1.1457750797271729} 08/31/2021 11:45:18 - INFO - __main__ - Step 124025: {'lr': 3.7050966441826014e-05, 'samples': 23812800, 'steps': 124024, 'loss/train': 1.095660924911499} 08/31/2021 11:45:18 - INFO - __main__ - Step 124026: {'lr': 3.704818642756505e-05, 'samples': 23812992, 'steps': 124025, 'loss/train': 0.10006336122751236} 08/31/2021 11:45:19 - INFO - __main__ - Step 124027: {'lr': 3.704540650925686e-05, 'samples': 23813184, 'steps': 124026, 'loss/train': 1.4229451417922974} 08/31/2021 11:45:20 - INFO - __main__ - Step 124028: {'lr': 3.704262668690275e-05, 'samples': 23813376, 'steps': 124027, 'loss/train': 1.0147193670272827} 08/31/2021 11:45:21 - INFO - __main__ - Step 124029: {'lr': 3.7039846960503944e-05, 'samples': 23813568, 'steps': 124028, 'loss/train': 1.3300786018371582} 08/31/2021 11:45:21 - INFO - __main__ - Step 124030: {'lr': 3.703706733006168e-05, 'samples': 23813760, 'steps': 124029, 'loss/train': 1.1275962591171265} 08/31/2021 11:45:21 - INFO - __main__ - Step 124031: {'lr': 3.7034287795577244e-05, 'samples': 23813952, 'steps': 124030, 'loss/train': 0.7976624965667725} 08/31/2021 11:45:22 - INFO - __main__ - Step 124032: {'lr': 3.703150835705185e-05, 'samples': 23814144, 'steps': 124031, 'loss/train': 1.0554096698760986} 08/31/2021 11:45:22 - INFO - __main__ - Step 124033: {'lr': 3.702872901448684e-05, 'samples': 23814336, 'steps': 124032, 'loss/train': 1.5295050144195557} 08/31/2021 11:45:24 - INFO - __main__ - Step 124034: {'lr': 3.7025949767883344e-05, 'samples': 23814528, 'steps': 124033, 'loss/train': 0.11749861389398575} 08/31/2021 11:45:24 - INFO - __main__ - Step 124035: {'lr': 3.7023170617242666e-05, 'samples': 23814720, 'steps': 124034, 'loss/train': 0.7014328837394714} 08/31/2021 11:45:25 - INFO - __main__ - Step 124036: {'lr': 3.7020391562566064e-05, 'samples': 23814912, 'steps': 124035, 'loss/train': 0.2795718312263489} 08/31/2021 11:45:25 - INFO - __main__ - Step 124037: {'lr': 3.701761260385478e-05, 'samples': 23815104, 'steps': 124036, 'loss/train': 1.3452181816101074} 08/31/2021 11:45:25 - INFO - __main__ - Step 124038: {'lr': 3.701483374111009e-05, 'samples': 23815296, 'steps': 124037, 'loss/train': 1.1572309732437134} 08/31/2021 11:45:27 - INFO - __main__ - Step 124039: {'lr': 3.7012054974333216e-05, 'samples': 23815488, 'steps': 124038, 'loss/train': 0.4117443263530731} 08/31/2021 11:45:27 - INFO - __main__ - Step 124040: {'lr': 3.700927630352543e-05, 'samples': 23815680, 'steps': 124039, 'loss/train': 1.2754803895950317} 08/31/2021 11:45:28 - INFO - __main__ - Step 124041: {'lr': 3.7006497728687974e-05, 'samples': 23815872, 'steps': 124040, 'loss/train': 1.0848294496536255} 08/31/2021 11:45:28 - INFO - __main__ - Step 124042: {'lr': 3.70037192498221e-05, 'samples': 23816064, 'steps': 124041, 'loss/train': 1.3701122999191284} 08/31/2021 11:45:28 - INFO - __main__ - Step 124043: {'lr': 3.700094086692907e-05, 'samples': 23816256, 'steps': 124042, 'loss/train': 0.7429591417312622} 08/31/2021 11:45:30 - INFO - __main__ - Step 124044: {'lr': 3.6998162580010124e-05, 'samples': 23816448, 'steps': 124043, 'loss/train': 1.3279787302017212} 08/31/2021 11:45:30 - INFO - __main__ - Step 124045: {'lr': 3.699538438906652e-05, 'samples': 23816640, 'steps': 124044, 'loss/train': 1.1860158443450928} 08/31/2021 11:45:31 - INFO - __main__ - Step 124046: {'lr': 3.699260629409956e-05, 'samples': 23816832, 'steps': 124045, 'loss/train': 1.6525053977966309} 08/31/2021 11:45:31 - INFO - __main__ - Step 124047: {'lr': 3.698982829511041e-05, 'samples': 23817024, 'steps': 124046, 'loss/train': 1.0235356092453003} 08/31/2021 11:45:31 - INFO - __main__ - Step 124048: {'lr': 3.698705039210035e-05, 'samples': 23817216, 'steps': 124047, 'loss/train': 0.7991050481796265} 08/31/2021 11:45:32 - INFO - __main__ - Step 124049: {'lr': 3.6984272585070615e-05, 'samples': 23817408, 'steps': 124048, 'loss/train': 4.33811092376709} 08/31/2021 11:45:33 - INFO - __main__ - Step 124050: {'lr': 3.6981494874022495e-05, 'samples': 23817600, 'steps': 124049, 'loss/train': 2.0050482749938965} 08/31/2021 11:45:34 - INFO - __main__ - Step 124051: {'lr': 3.697871725895721e-05, 'samples': 23817792, 'steps': 124050, 'loss/train': 0.7730507850646973} 08/31/2021 11:45:34 - INFO - __main__ - Step 124052: {'lr': 3.697593973987606e-05, 'samples': 23817984, 'steps': 124051, 'loss/train': 1.2423152923583984} 08/31/2021 11:45:34 - INFO - __main__ - Step 124053: {'lr': 3.697316231678024e-05, 'samples': 23818176, 'steps': 124052, 'loss/train': 1.1432135105133057} 08/31/2021 11:45:35 - INFO - __main__ - Step 124054: {'lr': 3.6970384989671036e-05, 'samples': 23818368, 'steps': 124053, 'loss/train': 0.8356793522834778} 08/31/2021 11:45:36 - INFO - __main__ - Step 124055: {'lr': 3.6967607758549684e-05, 'samples': 23818560, 'steps': 124054, 'loss/train': 1.1925321817398071} 08/31/2021 11:45:37 - INFO - __main__ - Step 124056: {'lr': 3.696483062341743e-05, 'samples': 23818752, 'steps': 124055, 'loss/train': 1.6124677658081055} 08/31/2021 11:45:37 - INFO - __main__ - Step 124057: {'lr': 3.696205358427557e-05, 'samples': 23818944, 'steps': 124056, 'loss/train': 0.339383989572525} 08/31/2021 11:45:38 - INFO - __main__ - Step 124058: {'lr': 3.695927664112531e-05, 'samples': 23819136, 'steps': 124057, 'loss/train': 1.0159364938735962} 08/31/2021 11:45:38 - INFO - __main__ - Step 124059: {'lr': 3.695649979396789e-05, 'samples': 23819328, 'steps': 124058, 'loss/train': 1.2609251737594604} 08/31/2021 11:45:40 - INFO - __main__ - Step 124060: {'lr': 3.695372304280464e-05, 'samples': 23819520, 'steps': 124059, 'loss/train': 1.1479617357254028} 08/31/2021 11:45:40 - INFO - __main__ - Step 124061: {'lr': 3.695094638763671e-05, 'samples': 23819712, 'steps': 124060, 'loss/train': 0.3004220128059387} 08/31/2021 11:45:40 - INFO - __main__ - Step 124062: {'lr': 3.694816982846541e-05, 'samples': 23819904, 'steps': 124061, 'loss/train': 0.47098982334136963} 08/31/2021 11:45:41 - INFO - __main__ - Step 124063: {'lr': 3.694539336529196e-05, 'samples': 23820096, 'steps': 124062, 'loss/train': 1.4115676879882812} 08/31/2021 11:45:41 - INFO - __main__ - Step 124064: {'lr': 3.694261699811763e-05, 'samples': 23820288, 'steps': 124063, 'loss/train': 0.3120333254337311} 08/31/2021 11:45:43 - INFO - __main__ - Step 124065: {'lr': 3.6939840726943677e-05, 'samples': 23820480, 'steps': 124064, 'loss/train': 0.34055522084236145} 08/31/2021 11:45:43 - INFO - __main__ - Step 124066: {'lr': 3.693706455177134e-05, 'samples': 23820672, 'steps': 124065, 'loss/train': 0.9556362628936768} 08/31/2021 11:45:44 - INFO - __main__ - Step 124067: {'lr': 3.693428847260189e-05, 'samples': 23820864, 'steps': 124066, 'loss/train': 1.0400782823562622} 08/31/2021 11:45:44 - INFO - __main__ - Step 124068: {'lr': 3.693151248943652e-05, 'samples': 23821056, 'steps': 124067, 'loss/train': 1.4188730716705322} 08/31/2021 11:45:44 - INFO - __main__ - Step 124069: {'lr': 3.692873660227655e-05, 'samples': 23821248, 'steps': 124068, 'loss/train': 1.1398247480392456} 08/31/2021 11:45:46 - INFO - __main__ - Step 124070: {'lr': 3.6925960811123205e-05, 'samples': 23821440, 'steps': 124069, 'loss/train': 1.0958166122436523} 08/31/2021 11:45:46 - INFO - __main__ - Step 124071: {'lr': 3.692318511597773e-05, 'samples': 23821632, 'steps': 124070, 'loss/train': 1.097650170326233} 08/31/2021 11:45:46 - INFO - __main__ - Step 124072: {'lr': 3.692040951684139e-05, 'samples': 23821824, 'steps': 124071, 'loss/train': 1.187654733657837} 08/31/2021 11:45:47 - INFO - __main__ - Step 124073: {'lr': 3.691763401371545e-05, 'samples': 23822016, 'steps': 124072, 'loss/train': 0.8407002091407776} 08/31/2021 11:45:47 - INFO - __main__ - Step 124074: {'lr': 3.691485860660113e-05, 'samples': 23822208, 'steps': 124073, 'loss/train': 1.163464069366455} 08/31/2021 11:45:49 - INFO - __main__ - Step 124075: {'lr': 3.6912083295499636e-05, 'samples': 23822400, 'steps': 124074, 'loss/train': 0.1487286239862442} 08/31/2021 11:45:50 - INFO - __main__ - Step 124076: {'lr': 3.690930808041229e-05, 'samples': 23822592, 'steps': 124075, 'loss/train': 0.6468378305435181} 08/31/2021 11:45:50 - INFO - __main__ - Step 124077: {'lr': 3.690653296134033e-05, 'samples': 23822784, 'steps': 124076, 'loss/train': 2.888955593109131} 08/31/2021 11:45:50 - INFO - __main__ - Step 124078: {'lr': 3.6903757938284985e-05, 'samples': 23822976, 'steps': 124077, 'loss/train': 0.9960131049156189} 08/31/2021 11:45:51 - INFO - __main__ - Step 124079: {'lr': 3.690098301124753e-05, 'samples': 23823168, 'steps': 124078, 'loss/train': 1.7320963144302368} 08/31/2021 11:45:52 - INFO - __main__ - Step 124080: {'lr': 3.6898208180229184e-05, 'samples': 23823360, 'steps': 124079, 'loss/train': 1.242882490158081} 08/31/2021 11:45:53 - INFO - __main__ - Step 124081: {'lr': 3.6895433445231243e-05, 'samples': 23823552, 'steps': 124080, 'loss/train': 1.4845503568649292} 08/31/2021 11:45:53 - INFO - __main__ - Step 124082: {'lr': 3.689265880625492e-05, 'samples': 23823744, 'steps': 124081, 'loss/train': 0.8108019232749939} 08/31/2021 11:45:53 - INFO - __main__ - Step 124083: {'lr': 3.6889884263301476e-05, 'samples': 23823936, 'steps': 124082, 'loss/train': 0.3306598961353302} 08/31/2021 11:45:54 - INFO - __main__ - Step 124084: {'lr': 3.688710981637216e-05, 'samples': 23824128, 'steps': 124083, 'loss/train': 1.2325819730758667} 08/31/2021 11:45:54 - INFO - __main__ - Step 124085: {'lr': 3.688433546546821e-05, 'samples': 23824320, 'steps': 124084, 'loss/train': 1.4053658246994019} 08/31/2021 11:45:56 - INFO - __main__ - Step 124086: {'lr': 3.688156121059091e-05, 'samples': 23824512, 'steps': 124085, 'loss/train': 1.2400895357131958} 08/31/2021 11:45:56 - INFO - __main__ - Step 124087: {'lr': 3.687878705174155e-05, 'samples': 23824704, 'steps': 124086, 'loss/train': 0.9074065089225769} 08/31/2021 11:45:56 - INFO - __main__ - Step 124088: {'lr': 3.687601298892126e-05, 'samples': 23824896, 'steps': 124087, 'loss/train': 0.9900426864624023} 08/31/2021 11:45:57 - INFO - __main__ - Step 124089: {'lr': 3.687323902213133e-05, 'samples': 23825088, 'steps': 124088, 'loss/train': 1.4833062887191772} 08/31/2021 11:45:57 - INFO - __main__ - Step 124090: {'lr': 3.6870465151373044e-05, 'samples': 23825280, 'steps': 124089, 'loss/train': 1.3626596927642822} 08/31/2021 11:45:59 - INFO - __main__ - Step 124091: {'lr': 3.686769137664764e-05, 'samples': 23825472, 'steps': 124090, 'loss/train': 1.2804416418075562} 08/31/2021 11:45:59 - INFO - __main__ - Step 124092: {'lr': 3.6864917697956355e-05, 'samples': 23825664, 'steps': 124091, 'loss/train': 0.5773355960845947} 08/31/2021 11:45:59 - INFO - __main__ - Step 124093: {'lr': 3.686214411530048e-05, 'samples': 23825856, 'steps': 124092, 'loss/train': 0.9203901290893555} 08/31/2021 11:46:00 - INFO - __main__ - Step 124094: {'lr': 3.6859370628681195e-05, 'samples': 23826048, 'steps': 124093, 'loss/train': 0.6290410757064819} 08/31/2021 11:46:00 - INFO - __main__ - Step 124095: {'lr': 3.685659723809981e-05, 'samples': 23826240, 'steps': 124094, 'loss/train': 1.5661051273345947} 08/31/2021 11:46:00 - INFO - __main__ - Step 124096: {'lr': 3.685382394355755e-05, 'samples': 23826432, 'steps': 124095, 'loss/train': 0.41158297657966614} 08/31/2021 11:46:02 - INFO - __main__ - Step 124097: {'lr': 3.6851050745055656e-05, 'samples': 23826624, 'steps': 124096, 'loss/train': 1.8458489179611206} 08/31/2021 11:46:03 - INFO - __main__ - Step 124098: {'lr': 3.684827764259541e-05, 'samples': 23826816, 'steps': 124097, 'loss/train': 1.452452301979065} 08/31/2021 11:46:03 - INFO - __main__ - Step 124099: {'lr': 3.684550463617803e-05, 'samples': 23827008, 'steps': 124098, 'loss/train': 0.9407263398170471} 08/31/2021 11:46:03 - INFO - __main__ - Step 124100: {'lr': 3.684273172580482e-05, 'samples': 23827200, 'steps': 124099, 'loss/train': 1.1210070848464966} 08/31/2021 11:46:04 - INFO - __main__ - Step 124101: {'lr': 3.6839958911476953e-05, 'samples': 23827392, 'steps': 124100, 'loss/train': 0.5028145909309387} 08/31/2021 11:46:05 - INFO - __main__ - Step 124102: {'lr': 3.68371861931957e-05, 'samples': 23827584, 'steps': 124101, 'loss/train': 0.027505258098244667} 08/31/2021 11:46:06 - INFO - __main__ - Step 124103: {'lr': 3.6834413570962314e-05, 'samples': 23827776, 'steps': 124102, 'loss/train': 1.1998014450073242} 08/31/2021 11:46:06 - INFO - __main__ - Step 124104: {'lr': 3.683164104477807e-05, 'samples': 23827968, 'steps': 124103, 'loss/train': 1.0751540660858154} 08/31/2021 11:46:06 - INFO - __main__ - Step 124105: {'lr': 3.682886861464418e-05, 'samples': 23828160, 'steps': 124104, 'loss/train': 1.5803794860839844} 08/31/2021 11:46:07 - INFO - __main__ - Step 124106: {'lr': 3.6826096280561936e-05, 'samples': 23828352, 'steps': 124105, 'loss/train': 0.9359350800514221} 08/31/2021 11:46:08 - INFO - __main__ - Step 124107: {'lr': 3.682332404253255e-05, 'samples': 23828544, 'steps': 124106, 'loss/train': 0.9735857248306274} 08/31/2021 11:46:09 - INFO - __main__ - Step 124108: {'lr': 3.6820551900557275e-05, 'samples': 23828736, 'steps': 124107, 'loss/train': 1.3448103666305542} 08/31/2021 11:46:09 - INFO - __main__ - Step 124109: {'lr': 3.6817779854637386e-05, 'samples': 23828928, 'steps': 124108, 'loss/train': 1.4666637182235718} 08/31/2021 11:46:10 - INFO - __main__ - Step 124110: {'lr': 3.68150079047741e-05, 'samples': 23829120, 'steps': 124109, 'loss/train': 1.2905446290969849} 08/31/2021 11:46:10 - INFO - __main__ - Step 124111: {'lr': 3.6812236050968756e-05, 'samples': 23829312, 'steps': 124110, 'loss/train': 1.44858980178833} 08/31/2021 11:46:12 - INFO - __main__ - Step 124112: {'lr': 3.680946429322246e-05, 'samples': 23829504, 'steps': 124111, 'loss/train': 0.8597147464752197} 08/31/2021 11:46:12 - INFO - __main__ - Step 124113: {'lr': 3.680669263153655e-05, 'samples': 23829696, 'steps': 124112, 'loss/train': 1.1256660223007202} 08/31/2021 11:46:13 - INFO - __main__ - Step 124114: {'lr': 3.680392106591224e-05, 'samples': 23829888, 'steps': 124113, 'loss/train': 0.8683756589889526} 08/31/2021 11:46:13 - INFO - __main__ - Step 124115: {'lr': 3.680114959635078e-05, 'samples': 23830080, 'steps': 124114, 'loss/train': 1.1032187938690186} 08/31/2021 11:46:13 - INFO - __main__ - Step 124116: {'lr': 3.679837822285345e-05, 'samples': 23830272, 'steps': 124115, 'loss/train': 0.5382421016693115} 08/31/2021 11:46:14 - INFO - __main__ - Step 124117: {'lr': 3.6795606945421476e-05, 'samples': 23830464, 'steps': 124116, 'loss/train': 1.0355184078216553} 08/31/2021 11:46:15 - INFO - __main__ - Step 124118: {'lr': 3.6792835764056096e-05, 'samples': 23830656, 'steps': 124117, 'loss/train': 2.581371784210205} 08/31/2021 11:46:16 - INFO - __main__ - Step 124119: {'lr': 3.679006467875859e-05, 'samples': 23830848, 'steps': 124118, 'loss/train': 0.2325691431760788} 08/31/2021 11:46:16 - INFO - __main__ - Step 124120: {'lr': 3.678729368953018e-05, 'samples': 23831040, 'steps': 124119, 'loss/train': 0.9113115072250366} 08/31/2021 11:46:16 - INFO - __main__ - Step 124121: {'lr': 3.678452279637215e-05, 'samples': 23831232, 'steps': 124120, 'loss/train': 0.7288175225257874} 08/31/2021 11:46:17 - INFO - __main__ - Step 124122: {'lr': 3.6781751999285764e-05, 'samples': 23831424, 'steps': 124121, 'loss/train': 1.674149513244629} 08/31/2021 11:46:17 - INFO - __main__ - Step 124123: {'lr': 3.677898129827217e-05, 'samples': 23831616, 'steps': 124122, 'loss/train': 0.7701467871665955} 08/31/2021 11:46:18 - INFO - __main__ - Step 124124: {'lr': 3.6776210693332676e-05, 'samples': 23831808, 'steps': 124123, 'loss/train': 0.656348466873169} 08/31/2021 11:46:19 - INFO - __main__ - Step 124125: {'lr': 3.677344018446854e-05, 'samples': 23832000, 'steps': 124124, 'loss/train': 0.6583160758018494} 08/31/2021 11:46:19 - INFO - __main__ - Step 124126: {'lr': 3.6770669771681e-05, 'samples': 23832192, 'steps': 124125, 'loss/train': 1.2667043209075928} 08/31/2021 11:46:20 - INFO - __main__ - Step 124127: {'lr': 3.67678994549713e-05, 'samples': 23832384, 'steps': 124126, 'loss/train': 1.2213947772979736} 08/31/2021 11:46:20 - INFO - __main__ - Step 124128: {'lr': 3.6765129234340695e-05, 'samples': 23832576, 'steps': 124127, 'loss/train': 0.5639898777008057} 08/31/2021 11:46:22 - INFO - __main__ - Step 124129: {'lr': 3.676235910979045e-05, 'samples': 23832768, 'steps': 124128, 'loss/train': 1.1667513847351074} 08/31/2021 11:46:23 - INFO - __main__ - Step 124130: {'lr': 3.6759589081321766e-05, 'samples': 23832960, 'steps': 124129, 'loss/train': 5.795897483825684} 08/31/2021 11:46:23 - INFO - __main__ - Step 124131: {'lr': 3.675681914893594e-05, 'samples': 23833152, 'steps': 124130, 'loss/train': 0.13506248593330383} 08/31/2021 11:46:23 - INFO - __main__ - Step 124132: {'lr': 3.675404931263421e-05, 'samples': 23833344, 'steps': 124131, 'loss/train': 0.856617271900177} 08/31/2021 11:46:24 - INFO - __main__ - Step 124133: {'lr': 3.6751279572417836e-05, 'samples': 23833536, 'steps': 124132, 'loss/train': 1.1028146743774414} 08/31/2021 11:46:25 - INFO - __main__ - Step 124134: {'lr': 3.674850992828802e-05, 'samples': 23833728, 'steps': 124133, 'loss/train': 1.1946786642074585} 08/31/2021 11:46:26 - INFO - __main__ - Step 124135: {'lr': 3.674574038024603e-05, 'samples': 23833920, 'steps': 124134, 'loss/train': 1.1086331605911255} 08/31/2021 11:46:26 - INFO - __main__ - Step 124136: {'lr': 3.6742970928293095e-05, 'samples': 23834112, 'steps': 124135, 'loss/train': 1.0401767492294312} 08/31/2021 11:46:26 - INFO - __main__ - Step 124137: {'lr': 3.674020157243052e-05, 'samples': 23834304, 'steps': 124136, 'loss/train': 1.1529508829116821} 08/31/2021 11:46:27 - INFO - __main__ - Step 124138: {'lr': 3.67374323126595e-05, 'samples': 23834496, 'steps': 124137, 'loss/train': 0.8682700991630554} 08/31/2021 11:46:28 - INFO - __main__ - Step 124139: {'lr': 3.67346631489813e-05, 'samples': 23834688, 'steps': 124138, 'loss/train': 1.4191036224365234} 08/31/2021 11:46:29 - INFO - __main__ - Step 124140: {'lr': 3.673189408139718e-05, 'samples': 23834880, 'steps': 124139, 'loss/train': 4.701654434204102} 08/31/2021 11:46:29 - INFO - __main__ - Step 124141: {'lr': 3.672912510990839e-05, 'samples': 23835072, 'steps': 124140, 'loss/train': 1.0357834100723267} 08/31/2021 11:46:29 - INFO - __main__ - Step 124142: {'lr': 3.672635623451614e-05, 'samples': 23835264, 'steps': 124141, 'loss/train': 0.461558073759079} 08/31/2021 11:46:30 - INFO - __main__ - Step 124143: {'lr': 3.6723587455221696e-05, 'samples': 23835456, 'steps': 124142, 'loss/train': 1.4856942892074585} 08/31/2021 11:46:31 - INFO - __main__ - Step 124144: {'lr': 3.67208187720264e-05, 'samples': 23835648, 'steps': 124143, 'loss/train': 1.1670639514923096} 08/31/2021 11:46:32 - INFO - __main__ - Step 124145: {'lr': 3.671805018493135e-05, 'samples': 23835840, 'steps': 124144, 'loss/train': 1.7957149744033813} 08/31/2021 11:46:32 - INFO - __main__ - Step 124146: {'lr': 3.671528169393784e-05, 'samples': 23836032, 'steps': 124145, 'loss/train': 2.1472504138946533} 08/31/2021 11:46:32 - INFO - __main__ - Step 124147: {'lr': 3.6712513299047123e-05, 'samples': 23836224, 'steps': 124146, 'loss/train': 0.4387723207473755} 08/31/2021 11:46:33 - INFO - __main__ - Step 124148: {'lr': 3.6709745000260474e-05, 'samples': 23836416, 'steps': 124147, 'loss/train': 1.1670384407043457} 08/31/2021 11:46:34 - INFO - __main__ - Step 124149: {'lr': 3.670697679757912e-05, 'samples': 23836608, 'steps': 124148, 'loss/train': 1.160513162612915} 08/31/2021 11:46:35 - INFO - __main__ - Step 124150: {'lr': 3.6704208691004324e-05, 'samples': 23836800, 'steps': 124149, 'loss/train': 0.5942316651344299} 08/31/2021 11:46:35 - INFO - __main__ - Step 124151: {'lr': 3.6701440680537295e-05, 'samples': 23836992, 'steps': 124150, 'loss/train': 0.8810850381851196} 08/31/2021 11:46:35 - INFO - __main__ - Step 124152: {'lr': 3.669867276617933e-05, 'samples': 23837184, 'steps': 124151, 'loss/train': 0.892479419708252} 08/31/2021 11:46:36 - INFO - __main__ - Step 124153: {'lr': 3.669590494793163e-05, 'samples': 23837376, 'steps': 124152, 'loss/train': 1.0893954038619995} 08/31/2021 11:46:36 - INFO - __main__ - Step 124154: {'lr': 3.669313722579548e-05, 'samples': 23837568, 'steps': 124153, 'loss/train': 0.8874913454055786} 08/31/2021 11:46:38 - INFO - __main__ - Step 124155: {'lr': 3.669036959977215e-05, 'samples': 23837760, 'steps': 124154, 'loss/train': 1.1787017583847046} 08/31/2021 11:46:39 - INFO - __main__ - Step 124156: {'lr': 3.6687602069862827e-05, 'samples': 23837952, 'steps': 124155, 'loss/train': 1.563738465309143} 08/31/2021 11:46:39 - INFO - __main__ - Step 124157: {'lr': 3.668483463606875e-05, 'samples': 23838144, 'steps': 124156, 'loss/train': 0.025001587346196175} 08/31/2021 11:46:39 - INFO - __main__ - Step 124158: {'lr': 3.668206729839118e-05, 'samples': 23838336, 'steps': 124157, 'loss/train': 1.8368335962295532} 08/31/2021 11:46:40 - INFO - __main__ - Step 124159: {'lr': 3.66793000568314e-05, 'samples': 23838528, 'steps': 124158, 'loss/train': 1.775349736213684} 08/31/2021 11:46:41 - INFO - __main__ - Step 124160: {'lr': 3.667653291139064e-05, 'samples': 23838720, 'steps': 124159, 'loss/train': 1.1635655164718628} 08/31/2021 11:46:42 - INFO - __main__ - Step 124161: {'lr': 3.667376586207013e-05, 'samples': 23838912, 'steps': 124160, 'loss/train': 1.2507742643356323} 08/31/2021 11:46:43 - INFO - __main__ - Step 124162: {'lr': 3.6670998908871126e-05, 'samples': 23839104, 'steps': 124161, 'loss/train': 0.9932523369789124} 08/31/2021 11:46:43 - INFO - __main__ - Step 124163: {'lr': 3.6668232051794896e-05, 'samples': 23839296, 'steps': 124162, 'loss/train': 1.1016141176223755} 08/31/2021 11:46:43 - INFO - __main__ - Step 124164: {'lr': 3.666546529084266e-05, 'samples': 23839488, 'steps': 124163, 'loss/train': 0.5190766453742981} 08/31/2021 11:46:44 - INFO - __main__ - Step 124165: {'lr': 3.6662698626015676e-05, 'samples': 23839680, 'steps': 124164, 'loss/train': 1.1788336038589478} 08/31/2021 11:46:45 - INFO - __main__ - Step 124166: {'lr': 3.665993205731519e-05, 'samples': 23839872, 'steps': 124165, 'loss/train': 0.8322733044624329} 08/31/2021 11:46:46 - INFO - __main__ - Step 124167: {'lr': 3.6657165584742496e-05, 'samples': 23840064, 'steps': 124166, 'loss/train': 0.03377271816134453} 08/31/2021 11:46:46 - INFO - __main__ - Step 124168: {'lr': 3.665439920829875e-05, 'samples': 23840256, 'steps': 124167, 'loss/train': 1.2620526552200317} 08/31/2021 11:46:46 - INFO - __main__ - Step 124169: {'lr': 3.665163292798521e-05, 'samples': 23840448, 'steps': 124168, 'loss/train': 0.855318546295166} 08/31/2021 11:46:47 - INFO - __main__ - Step 124170: {'lr': 3.664886674380316e-05, 'samples': 23840640, 'steps': 124169, 'loss/train': 0.9501640200614929} 08/31/2021 11:46:49 - INFO - __main__ - Step 124171: {'lr': 3.6646100655753854e-05, 'samples': 23840832, 'steps': 124170, 'loss/train': 0.8428300619125366} 08/31/2021 11:46:49 - INFO - __main__ - Step 124172: {'lr': 3.664333466383851e-05, 'samples': 23841024, 'steps': 124171, 'loss/train': 1.3693568706512451} 08/31/2021 11:46:49 - INFO - __main__ - Step 124173: {'lr': 3.664056876805841e-05, 'samples': 23841216, 'steps': 124172, 'loss/train': 0.8852674961090088} 08/31/2021 11:46:50 - INFO - __main__ - Step 124174: {'lr': 3.663780296841476e-05, 'samples': 23841408, 'steps': 124173, 'loss/train': 1.1080131530761719} 08/31/2021 11:46:50 - INFO - __main__ - Step 124175: {'lr': 3.663503726490883e-05, 'samples': 23841600, 'steps': 124174, 'loss/train': 0.014691755175590515} 08/31/2021 11:46:50 - INFO - __main__ - Step 124176: {'lr': 3.663227165754185e-05, 'samples': 23841792, 'steps': 124175, 'loss/train': 1.199951410293579} 08/31/2021 11:46:51 - INFO - __main__ - Step 124177: {'lr': 3.662950614631508e-05, 'samples': 23841984, 'steps': 124176, 'loss/train': 0.6923395395278931} 08/31/2021 11:46:52 - INFO - __main__ - Step 124178: {'lr': 3.662674073122976e-05, 'samples': 23842176, 'steps': 124177, 'loss/train': 0.7616776823997498} 08/31/2021 11:46:53 - INFO - __main__ - Step 124179: {'lr': 3.6623975412287126e-05, 'samples': 23842368, 'steps': 124178, 'loss/train': 0.8254985809326172} 08/31/2021 11:46:53 - INFO - __main__ - Step 124180: {'lr': 3.662121018948847e-05, 'samples': 23842560, 'steps': 124179, 'loss/train': 1.296978235244751} 08/31/2021 11:46:54 - INFO - __main__ - Step 124181: {'lr': 3.661844506283504e-05, 'samples': 23842752, 'steps': 124180, 'loss/train': 1.3760943412780762} 08/31/2021 11:46:54 - INFO - __main__ - Step 124182: {'lr': 3.661568003232799e-05, 'samples': 23842944, 'steps': 124181, 'loss/train': 1.165830135345459} 08/31/2021 11:46:56 - INFO - __main__ - Step 124183: {'lr': 3.66129150979686e-05, 'samples': 23843136, 'steps': 124182, 'loss/train': 1.4529118537902832} 08/31/2021 11:46:56 - INFO - __main__ - Step 124184: {'lr': 3.661015025975817e-05, 'samples': 23843328, 'steps': 124183, 'loss/train': 1.2777769565582275} 08/31/2021 11:46:57 - INFO - __main__ - Step 124185: {'lr': 3.660738551769791e-05, 'samples': 23843520, 'steps': 124184, 'loss/train': 1.0868638753890991} 08/31/2021 11:46:57 - INFO - __main__ - Step 124186: {'lr': 3.6604620871789064e-05, 'samples': 23843712, 'steps': 124185, 'loss/train': 1.218927025794983} 08/31/2021 11:46:57 - INFO - __main__ - Step 124187: {'lr': 3.660185632203286e-05, 'samples': 23843904, 'steps': 124186, 'loss/train': 1.033140778541565} 08/31/2021 11:46:59 - INFO - __main__ - Step 124188: {'lr': 3.659909186843061e-05, 'samples': 23844096, 'steps': 124187, 'loss/train': 0.915799081325531} 08/31/2021 11:46:59 - INFO - __main__ - Step 124189: {'lr': 3.659632751098349e-05, 'samples': 23844288, 'steps': 124188, 'loss/train': 1.221517562866211} 08/31/2021 11:47:00 - INFO - __main__ - Step 124190: {'lr': 3.6593563249692763e-05, 'samples': 23844480, 'steps': 124189, 'loss/train': 0.2311963587999344} 08/31/2021 11:47:00 - INFO - __main__ - Step 124191: {'lr': 3.65907990845597e-05, 'samples': 23844672, 'steps': 124190, 'loss/train': 0.8310084939002991} 08/31/2021 11:47:01 - INFO - __main__ - Step 124192: {'lr': 3.6588035015585527e-05, 'samples': 23844864, 'steps': 124191, 'loss/train': 1.2068113088607788} 08/31/2021 11:47:02 - INFO - __main__ - Step 124193: {'lr': 3.658527104277148e-05, 'samples': 23845056, 'steps': 124192, 'loss/train': 0.40566959977149963} 08/31/2021 11:47:03 - INFO - __main__ - Step 124194: {'lr': 3.658250716611891e-05, 'samples': 23845248, 'steps': 124193, 'loss/train': 0.8411231637001038} 08/31/2021 11:47:03 - INFO - __main__ - Step 124195: {'lr': 3.657974338562889e-05, 'samples': 23845440, 'steps': 124194, 'loss/train': 0.7888454794883728} 08/31/2021 11:47:03 - INFO - __main__ - Step 124196: {'lr': 3.657697970130272e-05, 'samples': 23845632, 'steps': 124195, 'loss/train': 1.0336724519729614} 08/31/2021 11:47:04 - INFO - __main__ - Step 124197: {'lr': 3.657421611314171e-05, 'samples': 23845824, 'steps': 124196, 'loss/train': 0.6213395595550537} 08/31/2021 11:47:05 - INFO - __main__ - Step 124198: {'lr': 3.657145262114703e-05, 'samples': 23846016, 'steps': 124197, 'loss/train': 1.3798861503601074} 08/31/2021 11:47:06 - INFO - __main__ - Step 124199: {'lr': 3.656868922531997e-05, 'samples': 23846208, 'steps': 124198, 'loss/train': 0.5797286033630371} 08/31/2021 11:47:06 - INFO - __main__ - Step 124200: {'lr': 3.656592592566177e-05, 'samples': 23846400, 'steps': 124199, 'loss/train': 2.4751944541931152} 08/31/2021 11:47:07 - INFO - __main__ - Step 124201: {'lr': 3.6563162722173696e-05, 'samples': 23846592, 'steps': 124200, 'loss/train': 1.2267849445343018} 08/31/2021 11:47:07 - INFO - __main__ - Step 124202: {'lr': 3.6560399614856934e-05, 'samples': 23846784, 'steps': 124201, 'loss/train': 0.6681102514266968} 08/31/2021 11:47:07 - INFO - __main__ - Step 124203: {'lr': 3.655763660371278e-05, 'samples': 23846976, 'steps': 124202, 'loss/train': 0.8872953057289124} 08/31/2021 11:47:09 - INFO - __main__ - Step 124204: {'lr': 3.655487368874244e-05, 'samples': 23847168, 'steps': 124203, 'loss/train': 0.9824697375297546} 08/31/2021 11:47:09 - INFO - __main__ - Step 124205: {'lr': 3.65521108699472e-05, 'samples': 23847360, 'steps': 124204, 'loss/train': 1.0182428359985352} 08/31/2021 11:47:10 - INFO - __main__ - Step 124206: {'lr': 3.654934814732827e-05, 'samples': 23847552, 'steps': 124205, 'loss/train': 1.121148705482483} 08/31/2021 11:47:10 - INFO - __main__ - Step 124207: {'lr': 3.654658552088691e-05, 'samples': 23847744, 'steps': 124206, 'loss/train': 1.520795464515686} 08/31/2021 11:47:10 - INFO - __main__ - Step 124208: {'lr': 3.654382299062445e-05, 'samples': 23847936, 'steps': 124207, 'loss/train': 1.0503839254379272} 08/31/2021 11:47:12 - INFO - __main__ - Step 124209: {'lr': 3.654106055654197e-05, 'samples': 23848128, 'steps': 124208, 'loss/train': 0.5919011235237122} 08/31/2021 11:47:12 - INFO - __main__ - Step 124210: {'lr': 3.6538298218640796e-05, 'samples': 23848320, 'steps': 124209, 'loss/train': 1.292880654335022} 08/31/2021 11:47:13 - INFO - __main__ - Step 124211: {'lr': 3.653553597692216e-05, 'samples': 23848512, 'steps': 124210, 'loss/train': 1.0655593872070312} 08/31/2021 11:47:13 - INFO - __main__ - Step 124212: {'lr': 3.653277383138734e-05, 'samples': 23848704, 'steps': 124211, 'loss/train': 1.1285160779953003} 08/31/2021 11:47:14 - INFO - __main__ - Step 124213: {'lr': 3.653001178203755e-05, 'samples': 23848896, 'steps': 124212, 'loss/train': 1.1365591287612915} 08/31/2021 11:47:15 - INFO - __main__ - Step 124214: {'lr': 3.652724982887404e-05, 'samples': 23849088, 'steps': 124213, 'loss/train': 1.3835175037384033} 08/31/2021 11:47:15 - INFO - __main__ - Step 124215: {'lr': 3.652448797189803e-05, 'samples': 23849280, 'steps': 124214, 'loss/train': 0.9891599416732788} 08/31/2021 11:47:16 - INFO - __main__ - Step 124216: {'lr': 3.652172621111083e-05, 'samples': 23849472, 'steps': 124215, 'loss/train': 1.1316347122192383} 08/31/2021 11:47:16 - INFO - __main__ - Step 124217: {'lr': 3.651896454651363e-05, 'samples': 23849664, 'steps': 124216, 'loss/train': 0.7324317097663879} 08/31/2021 11:47:16 - INFO - __main__ - Step 124218: {'lr': 3.6516202978107704e-05, 'samples': 23849856, 'steps': 124217, 'loss/train': 0.9965274333953857} 08/31/2021 11:47:18 - INFO - __main__ - Step 124219: {'lr': 3.651344150589428e-05, 'samples': 23850048, 'steps': 124218, 'loss/train': 1.4411935806274414} 08/31/2021 11:47:19 - INFO - __main__ - Step 124220: {'lr': 3.6510680129874574e-05, 'samples': 23850240, 'steps': 124219, 'loss/train': 0.30401650071144104} 08/31/2021 11:47:19 - INFO - __main__ - Step 124221: {'lr': 3.650791885004995e-05, 'samples': 23850432, 'steps': 124220, 'loss/train': 1.0830230712890625} 08/31/2021 11:47:19 - INFO - __main__ - Step 124222: {'lr': 3.6505157666421514e-05, 'samples': 23850624, 'steps': 124221, 'loss/train': 1.0209108591079712} 08/31/2021 11:47:20 - INFO - __main__ - Step 124223: {'lr': 3.6502396578990544e-05, 'samples': 23850816, 'steps': 124222, 'loss/train': 1.245524287223816} 08/31/2021 11:47:21 - INFO - __main__ - Step 124224: {'lr': 3.649963558775829e-05, 'samples': 23851008, 'steps': 124223, 'loss/train': 1.0155563354492188} 08/31/2021 11:47:22 - INFO - __main__ - Step 124225: {'lr': 3.6496874692726e-05, 'samples': 23851200, 'steps': 124224, 'loss/train': 0.7299902439117432} 08/31/2021 11:47:22 - INFO - __main__ - Step 124226: {'lr': 3.649411389389495e-05, 'samples': 23851392, 'steps': 124225, 'loss/train': 1.5948340892791748} 08/31/2021 11:47:22 - INFO - __main__ - Step 124227: {'lr': 3.649135319126634e-05, 'samples': 23851584, 'steps': 124226, 'loss/train': 1.6154329776763916} 08/31/2021 11:47:23 - INFO - __main__ - Step 124228: {'lr': 3.648859258484144e-05, 'samples': 23851776, 'steps': 124227, 'loss/train': 0.9132336378097534} 08/31/2021 11:47:24 - INFO - __main__ - Step 124229: {'lr': 3.64858320746215e-05, 'samples': 23851968, 'steps': 124228, 'loss/train': 0.9538804888725281} 08/31/2021 11:47:25 - INFO - __main__ - Step 124230: {'lr': 3.6483071660607715e-05, 'samples': 23852160, 'steps': 124229, 'loss/train': 1.3332704305648804} 08/31/2021 11:47:25 - INFO - __main__ - Step 124231: {'lr': 3.648031134280139e-05, 'samples': 23852352, 'steps': 124230, 'loss/train': 1.5060758590698242} 08/31/2021 11:47:26 - INFO - __main__ - Step 124232: {'lr': 3.647755112120374e-05, 'samples': 23852544, 'steps': 124231, 'loss/train': 0.9734985828399658} 08/31/2021 11:47:26 - INFO - __main__ - Step 124233: {'lr': 3.647479099581599e-05, 'samples': 23852736, 'steps': 124232, 'loss/train': 1.2217590808868408} 08/31/2021 11:47:26 - INFO - __main__ - Step 124234: {'lr': 3.647203096663942e-05, 'samples': 23852928, 'steps': 124233, 'loss/train': 0.931756317615509} 08/31/2021 11:47:28 - INFO - __main__ - Step 124235: {'lr': 3.646927103367531e-05, 'samples': 23853120, 'steps': 124234, 'loss/train': 2.0185153484344482} 08/31/2021 11:47:28 - INFO - __main__ - Step 124236: {'lr': 3.646651119692482e-05, 'samples': 23853312, 'steps': 124235, 'loss/train': 1.144399642944336} 08/31/2021 11:47:29 - INFO - __main__ - Step 124237: {'lr': 3.646375145638919e-05, 'samples': 23853504, 'steps': 124236, 'loss/train': 0.05207764729857445} 08/31/2021 11:47:29 - INFO - __main__ - Step 124238: {'lr': 3.6460991812069715e-05, 'samples': 23853696, 'steps': 124237, 'loss/train': 1.0823912620544434} 08/31/2021 11:47:29 - INFO - __main__ - Step 124239: {'lr': 3.64582322639676e-05, 'samples': 23853888, 'steps': 124238, 'loss/train': 1.3029940128326416} 08/31/2021 11:47:31 - INFO - __main__ - Step 124240: {'lr': 3.645547281208414e-05, 'samples': 23854080, 'steps': 124239, 'loss/train': 0.6912028193473816} 08/31/2021 11:47:32 - INFO - __main__ - Step 124241: {'lr': 3.645271345642054e-05, 'samples': 23854272, 'steps': 124240, 'loss/train': 0.7747048735618591} 08/31/2021 11:47:32 - INFO - __main__ - Step 124242: {'lr': 3.644995419697805e-05, 'samples': 23854464, 'steps': 124241, 'loss/train': 0.7866575121879578} 08/31/2021 11:47:33 - INFO - __main__ - Step 124243: {'lr': 3.644719503375793e-05, 'samples': 23854656, 'steps': 124242, 'loss/train': 0.5661782026290894} 08/31/2021 11:47:33 - INFO - __main__ - Step 124244: {'lr': 3.644443596676139e-05, 'samples': 23854848, 'steps': 124243, 'loss/train': 1.5388357639312744} 08/31/2021 11:47:35 - INFO - __main__ - Step 124245: {'lr': 3.644167699598969e-05, 'samples': 23855040, 'steps': 124244, 'loss/train': 0.7900328040122986} 08/31/2021 11:47:35 - INFO - __main__ - Step 124246: {'lr': 3.6438918121444064e-05, 'samples': 23855232, 'steps': 124245, 'loss/train': 0.3428313136100769} 08/31/2021 11:47:36 - INFO - __main__ - Step 124247: {'lr': 3.64361593431258e-05, 'samples': 23855424, 'steps': 124246, 'loss/train': 0.7315443754196167} 08/31/2021 11:47:36 - INFO - __main__ - Step 124248: {'lr': 3.643340066103615e-05, 'samples': 23855616, 'steps': 124247, 'loss/train': 0.7280279994010925} 08/31/2021 11:47:36 - INFO - __main__ - Step 124249: {'lr': 3.643064207517624e-05, 'samples': 23855808, 'steps': 124248, 'loss/train': 1.1758068799972534} 08/31/2021 11:47:38 - INFO - __main__ - Step 124250: {'lr': 3.642788358554741e-05, 'samples': 23856000, 'steps': 124249, 'loss/train': 0.8612333536148071} 08/31/2021 11:47:38 - INFO - __main__ - Step 124251: {'lr': 3.6425125192150854e-05, 'samples': 23856192, 'steps': 124250, 'loss/train': 0.9444776773452759} 08/31/2021 11:47:39 - INFO - __main__ - Step 124252: {'lr': 3.642236689498787e-05, 'samples': 23856384, 'steps': 124251, 'loss/train': 1.221448540687561} 08/31/2021 11:47:39 - INFO - __main__ - Step 124253: {'lr': 3.6419608694059666e-05, 'samples': 23856576, 'steps': 124252, 'loss/train': 0.4896056056022644} 08/31/2021 11:47:39 - INFO - __main__ - Step 124254: {'lr': 3.641685058936747e-05, 'samples': 23856768, 'steps': 124253, 'loss/train': 1.220359444618225} 08/31/2021 11:47:41 - INFO - __main__ - Step 124255: {'lr': 3.6414092580912575e-05, 'samples': 23856960, 'steps': 124254, 'loss/train': 1.2390080690383911} 08/31/2021 11:47:42 - INFO - __main__ - Step 124256: {'lr': 3.641133466869617e-05, 'samples': 23857152, 'steps': 124255, 'loss/train': 0.3189605176448822} 08/31/2021 11:47:42 - INFO - __main__ - Step 124257: {'lr': 3.640857685271953e-05, 'samples': 23857344, 'steps': 124256, 'loss/train': 0.3596188724040985} 08/31/2021 11:47:42 - INFO - __main__ - Step 124258: {'lr': 3.640581913298388e-05, 'samples': 23857536, 'steps': 124257, 'loss/train': 1.4724994897842407} 08/31/2021 11:47:43 - INFO - __main__ - Step 124259: {'lr': 3.640306150949049e-05, 'samples': 23857728, 'steps': 124258, 'loss/train': 0.015177500434219837} 08/31/2021 11:47:43 - INFO - __main__ - Step 124260: {'lr': 3.640030398224059e-05, 'samples': 23857920, 'steps': 124259, 'loss/train': 0.8253093361854553} 08/31/2021 11:47:45 - INFO - __main__ - Step 124261: {'lr': 3.6397546551235446e-05, 'samples': 23858112, 'steps': 124260, 'loss/train': 0.6857016682624817} 08/31/2021 11:47:45 - INFO - __main__ - Step 124262: {'lr': 3.639478921647624e-05, 'samples': 23858304, 'steps': 124261, 'loss/train': 1.352757215499878} 08/31/2021 11:47:45 - INFO - __main__ - Step 124263: {'lr': 3.639203197796423e-05, 'samples': 23858496, 'steps': 124262, 'loss/train': 0.9667516350746155} 08/31/2021 11:47:46 - INFO - __main__ - Step 124264: {'lr': 3.638927483570067e-05, 'samples': 23858688, 'steps': 124263, 'loss/train': 1.383432149887085} 08/31/2021 11:47:46 - INFO - __main__ - Step 124265: {'lr': 3.6386517789686826e-05, 'samples': 23858880, 'steps': 124264, 'loss/train': 1.0943537950515747} 08/31/2021 11:47:46 - INFO - __main__ - Step 124266: {'lr': 3.6383760839923894e-05, 'samples': 23859072, 'steps': 124265, 'loss/train': 1.3763227462768555} 08/31/2021 11:47:48 - INFO - __main__ - Step 124267: {'lr': 3.638100398641317e-05, 'samples': 23859264, 'steps': 124266, 'loss/train': 1.7406176328659058} 08/31/2021 11:47:48 - INFO - __main__ - Step 124268: {'lr': 3.6378247229155865e-05, 'samples': 23859456, 'steps': 124267, 'loss/train': 1.415064811706543} 08/31/2021 11:47:49 - INFO - __main__ - Step 124269: {'lr': 3.63754905681532e-05, 'samples': 23859648, 'steps': 124268, 'loss/train': 0.9177457690238953} 08/31/2021 11:47:49 - INFO - __main__ - Step 124270: {'lr': 3.637273400340646e-05, 'samples': 23859840, 'steps': 124269, 'loss/train': 1.2508139610290527} 08/31/2021 11:47:51 - INFO - __main__ - Step 124271: {'lr': 3.636997753491689e-05, 'samples': 23860032, 'steps': 124270, 'loss/train': 0.344526082277298} 08/31/2021 11:47:51 - INFO - __main__ - Step 124272: {'lr': 3.636722116268568e-05, 'samples': 23860224, 'steps': 124271, 'loss/train': 0.2933238744735718} 08/31/2021 11:47:52 - INFO - __main__ - Step 124273: {'lr': 3.6364464886714105e-05, 'samples': 23860416, 'steps': 124272, 'loss/train': 0.8516159653663635} 08/31/2021 11:47:52 - INFO - __main__ - Step 124274: {'lr': 3.636170870700342e-05, 'samples': 23860608, 'steps': 124273, 'loss/train': 0.47030264139175415} 08/31/2021 11:47:52 - INFO - __main__ - Step 124275: {'lr': 3.63589526235549e-05, 'samples': 23860800, 'steps': 124274, 'loss/train': 0.8098254203796387} 08/31/2021 11:47:53 - INFO - __main__ - Step 124276: {'lr': 3.635619663636971e-05, 'samples': 23860992, 'steps': 124275, 'loss/train': 0.6363279223442078} 08/31/2021 11:47:54 - INFO - __main__ - Step 124277: {'lr': 3.635344074544908e-05, 'samples': 23861184, 'steps': 124276, 'loss/train': 0.021276719868183136} 08/31/2021 11:47:55 - INFO - __main__ - Step 124278: {'lr': 3.635068495079433e-05, 'samples': 23861376, 'steps': 124277, 'loss/train': 1.0239248275756836} 08/31/2021 11:47:55 - INFO - __main__ - Step 124279: {'lr': 3.6347929252406654e-05, 'samples': 23861568, 'steps': 124278, 'loss/train': 1.9755480289459229} 08/31/2021 11:47:55 - INFO - __main__ - Step 124280: {'lr': 3.634517365028728e-05, 'samples': 23861760, 'steps': 124279, 'loss/train': 0.945687472820282} 08/31/2021 11:47:56 - INFO - __main__ - Step 124281: {'lr': 3.6342418144437504e-05, 'samples': 23861952, 'steps': 124280, 'loss/train': 1.2395925521850586} 08/31/2021 11:47:57 - INFO - __main__ - Step 124282: {'lr': 3.63396627348585e-05, 'samples': 23862144, 'steps': 124281, 'loss/train': 0.40016064047813416} 08/31/2021 11:47:58 - INFO - __main__ - Step 124283: {'lr': 3.6336907421551574e-05, 'samples': 23862336, 'steps': 124282, 'loss/train': 1.1822105646133423} 08/31/2021 11:47:58 - INFO - __main__ - Step 124284: {'lr': 3.633415220451794e-05, 'samples': 23862528, 'steps': 124283, 'loss/train': 1.86208176612854} 08/31/2021 11:47:58 - INFO - __main__ - Step 124285: {'lr': 3.633139708375885e-05, 'samples': 23862720, 'steps': 124284, 'loss/train': 0.06203032284975052} 08/31/2021 11:47:59 - INFO - __main__ - Step 124286: {'lr': 3.6328642059275526e-05, 'samples': 23862912, 'steps': 124285, 'loss/train': 1.0944746732711792} 08/31/2021 11:48:00 - INFO - __main__ - Step 124287: {'lr': 3.6325887131069216e-05, 'samples': 23863104, 'steps': 124286, 'loss/train': 0.1270720660686493} 08/31/2021 11:48:01 - INFO - __main__ - Step 124288: {'lr': 3.632313229914122e-05, 'samples': 23863296, 'steps': 124287, 'loss/train': 0.6628748774528503} 08/31/2021 11:48:01 - INFO - __main__ - Step 124289: {'lr': 3.6320377563492655e-05, 'samples': 23863488, 'steps': 124288, 'loss/train': 0.33444592356681824} 08/31/2021 11:48:01 - INFO - __main__ - Step 124290: {'lr': 3.631762292412486e-05, 'samples': 23863680, 'steps': 124289, 'loss/train': 0.6703594923019409} 08/31/2021 11:48:02 - INFO - __main__ - Step 124291: {'lr': 3.6314868381039004e-05, 'samples': 23863872, 'steps': 124290, 'loss/train': 0.5508096814155579} 08/31/2021 11:48:04 - INFO - __main__ - Step 124292: {'lr': 3.6312113934236415e-05, 'samples': 23864064, 'steps': 124291, 'loss/train': 1.4214961528778076} 08/31/2021 11:48:04 - INFO - __main__ - Step 124293: {'lr': 3.630935958371826e-05, 'samples': 23864256, 'steps': 124292, 'loss/train': 1.2242993116378784} 08/31/2021 11:48:04 - INFO - __main__ - Step 124294: {'lr': 3.630660532948582e-05, 'samples': 23864448, 'steps': 124293, 'loss/train': 0.5887616872787476} 08/31/2021 11:48:05 - INFO - __main__ - Step 124295: {'lr': 3.6303851171540336e-05, 'samples': 23864640, 'steps': 124294, 'loss/train': 0.6552185416221619} 08/31/2021 11:48:05 - INFO - __main__ - Step 124296: {'lr': 3.6301097109883025e-05, 'samples': 23864832, 'steps': 124295, 'loss/train': 0.6010137796401978} 08/31/2021 11:48:07 - INFO - __main__ - Step 124297: {'lr': 3.629834314451516e-05, 'samples': 23865024, 'steps': 124296, 'loss/train': 0.7514270544052124} 08/31/2021 11:48:07 - INFO - __main__ - Step 124298: {'lr': 3.629558927543794e-05, 'samples': 23865216, 'steps': 124297, 'loss/train': 1.153687596321106} 08/31/2021 11:48:07 - INFO - __main__ - Step 124299: {'lr': 3.6292835502652636e-05, 'samples': 23865408, 'steps': 124298, 'loss/train': 0.8312506079673767} 08/31/2021 11:48:08 - INFO - __main__ - Step 124300: {'lr': 3.6290081826160505e-05, 'samples': 23865600, 'steps': 124299, 'loss/train': 1.107672095298767} 08/31/2021 11:48:08 - INFO - __main__ - Step 124301: {'lr': 3.628732824596273e-05, 'samples': 23865792, 'steps': 124300, 'loss/train': 0.6190727949142456} 08/31/2021 11:48:10 - INFO - __main__ - Step 124302: {'lr': 3.628457476206068e-05, 'samples': 23865984, 'steps': 124301, 'loss/train': 1.3146413564682007} 08/31/2021 11:48:10 - INFO - __main__ - Step 124303: {'lr': 3.628182137445543e-05, 'samples': 23866176, 'steps': 124302, 'loss/train': 0.41357100009918213} 08/31/2021 11:48:10 - INFO - __main__ - Step 124304: {'lr': 3.6279068083148293e-05, 'samples': 23866368, 'steps': 124303, 'loss/train': 0.9776975512504578} 08/31/2021 11:48:11 - INFO - __main__ - Step 124305: {'lr': 3.627631488814051e-05, 'samples': 23866560, 'steps': 124304, 'loss/train': 0.43460801243782043} 08/31/2021 11:48:11 - INFO - __main__ - Step 124306: {'lr': 3.627356178943331e-05, 'samples': 23866752, 'steps': 124305, 'loss/train': 0.46542638540267944} 08/31/2021 11:48:11 - INFO - __main__ - Step 124307: {'lr': 3.627080878702796e-05, 'samples': 23866944, 'steps': 124306, 'loss/train': 1.1012028455734253} 08/31/2021 11:48:13 - INFO - __main__ - Step 124308: {'lr': 3.6268055880925686e-05, 'samples': 23867136, 'steps': 124307, 'loss/train': 2.4050495624542236} 08/31/2021 11:48:13 - INFO - __main__ - Step 124309: {'lr': 3.6265303071127716e-05, 'samples': 23867328, 'steps': 124308, 'loss/train': 0.8539164662361145} 08/31/2021 11:48:14 - INFO - __main__ - Step 124310: {'lr': 3.626255035763532e-05, 'samples': 23867520, 'steps': 124309, 'loss/train': 0.999936044216156} 08/31/2021 11:48:14 - INFO - __main__ - Step 124311: {'lr': 3.625979774044969e-05, 'samples': 23867712, 'steps': 124310, 'loss/train': 1.3600335121154785} 08/31/2021 11:48:14 - INFO - __main__ - Step 124312: {'lr': 3.625704521957213e-05, 'samples': 23867904, 'steps': 124311, 'loss/train': 0.4937971234321594} 08/31/2021 11:48:17 - INFO - __main__ - Step 124313: {'lr': 3.6254292795003834e-05, 'samples': 23868096, 'steps': 124312, 'loss/train': 1.2793595790863037} 08/31/2021 11:48:17 - INFO - __main__ - Step 124314: {'lr': 3.625154046674606e-05, 'samples': 23868288, 'steps': 124313, 'loss/train': 0.9023983478546143} 08/31/2021 11:48:18 - INFO - __main__ - Step 124315: {'lr': 3.624878823480007e-05, 'samples': 23868480, 'steps': 124314, 'loss/train': 1.7040079832077026} 08/31/2021 11:48:18 - INFO - __main__ - Step 124316: {'lr': 3.624603609916707e-05, 'samples': 23868672, 'steps': 124315, 'loss/train': 1.7091835737228394} 08/31/2021 11:48:18 - INFO - __main__ - Step 124317: {'lr': 3.624328405984828e-05, 'samples': 23868864, 'steps': 124316, 'loss/train': 0.28384435176849365} 08/31/2021 11:48:19 - INFO - __main__ - Step 124318: {'lr': 3.624053211684497e-05, 'samples': 23869056, 'steps': 124317, 'loss/train': 1.4893742799758911} 08/31/2021 11:48:21 - INFO - __main__ - Step 124319: {'lr': 3.6237780270158366e-05, 'samples': 23869248, 'steps': 124318, 'loss/train': 0.06682977825403214} 08/31/2021 11:48:21 - INFO - __main__ - Step 124320: {'lr': 3.623502851978974e-05, 'samples': 23869440, 'steps': 124319, 'loss/train': 0.7096291184425354} 08/31/2021 11:48:22 - INFO - __main__ - Step 124321: {'lr': 3.6232276865740324e-05, 'samples': 23869632, 'steps': 124320, 'loss/train': 0.7724252939224243} 08/31/2021 11:48:22 - INFO - __main__ - Step 124322: {'lr': 3.6229525308011325e-05, 'samples': 23869824, 'steps': 124321, 'loss/train': 0.288240909576416} 08/31/2021 11:48:23 - INFO - __main__ - Step 124323: {'lr': 3.6226773846604e-05, 'samples': 23870016, 'steps': 124322, 'loss/train': 0.2667209506034851} 08/31/2021 11:48:23 - INFO - __main__ - Step 124324: {'lr': 3.62240224815196e-05, 'samples': 23870208, 'steps': 124323, 'loss/train': 1.7779442071914673} 08/31/2021 11:48:24 - INFO - __main__ - Step 124325: {'lr': 3.622127121275934e-05, 'samples': 23870400, 'steps': 124324, 'loss/train': 0.7451789975166321} 08/31/2021 11:48:25 - INFO - __main__ - Step 124326: {'lr': 3.62185200403245e-05, 'samples': 23870592, 'steps': 124325, 'loss/train': 1.4875342845916748} 08/31/2021 11:48:25 - INFO - __main__ - Step 124327: {'lr': 3.6215768964216275e-05, 'samples': 23870784, 'steps': 124326, 'loss/train': 1.8481512069702148} 08/31/2021 11:48:26 - INFO - __main__ - Step 124328: {'lr': 3.6213017984435935e-05, 'samples': 23870976, 'steps': 124327, 'loss/train': 0.5308327674865723} 08/31/2021 11:48:26 - INFO - __main__ - Step 124329: {'lr': 3.621026710098477e-05, 'samples': 23871168, 'steps': 124328, 'loss/train': 0.8039174675941467} 08/31/2021 11:48:26 - INFO - __main__ - Step 124330: {'lr': 3.6207516313863904e-05, 'samples': 23871360, 'steps': 124329, 'loss/train': 1.073114037513733} 08/31/2021 11:48:28 - INFO - __main__ - Step 124331: {'lr': 3.620476562307462e-05, 'samples': 23871552, 'steps': 124330, 'loss/train': 1.2481273412704468} 08/31/2021 11:48:28 - INFO - __main__ - Step 124332: {'lr': 3.62020150286182e-05, 'samples': 23871744, 'steps': 124331, 'loss/train': 0.36375465989112854} 08/31/2021 11:48:29 - INFO - __main__ - Step 124333: {'lr': 3.6199264530495826e-05, 'samples': 23871936, 'steps': 124332, 'loss/train': 1.0655012130737305} 08/31/2021 11:48:29 - INFO - __main__ - Step 124334: {'lr': 3.619651412870875e-05, 'samples': 23872128, 'steps': 124333, 'loss/train': 0.026109060272574425} 08/31/2021 11:48:29 - INFO - __main__ - Step 124335: {'lr': 3.6193763823258255e-05, 'samples': 23872320, 'steps': 124334, 'loss/train': 1.2850794792175293} 08/31/2021 11:48:31 - INFO - __main__ - Step 124336: {'lr': 3.6191013614145536e-05, 'samples': 23872512, 'steps': 124335, 'loss/train': 1.3688048124313354} 08/31/2021 11:48:31 - INFO - __main__ - Step 124337: {'lr': 3.618826350137186e-05, 'samples': 23872704, 'steps': 124336, 'loss/train': 0.777938961982727} 08/31/2021 11:48:32 - INFO - __main__ - Step 124338: {'lr': 3.6185513484938455e-05, 'samples': 23872896, 'steps': 124337, 'loss/train': 0.8320476412773132} 08/31/2021 11:48:32 - INFO - __main__ - Step 124339: {'lr': 3.618276356484654e-05, 'samples': 23873088, 'steps': 124338, 'loss/train': 1.289797306060791} 08/31/2021 11:48:32 - INFO - __main__ - Step 124340: {'lr': 3.618001374109739e-05, 'samples': 23873280, 'steps': 124339, 'loss/train': 1.1791273355484009} 08/31/2021 11:48:34 - INFO - __main__ - Step 124341: {'lr': 3.6177264013692204e-05, 'samples': 23873472, 'steps': 124340, 'loss/train': 0.614470899105072} 08/31/2021 11:48:34 - INFO - __main__ - Step 124342: {'lr': 3.617451438263231e-05, 'samples': 23873664, 'steps': 124341, 'loss/train': 1.2675232887268066} 08/31/2021 11:48:35 - INFO - __main__ - Step 124343: {'lr': 3.617176484791884e-05, 'samples': 23873856, 'steps': 124342, 'loss/train': 0.38905802369117737} 08/31/2021 11:48:35 - INFO - __main__ - Step 124344: {'lr': 3.616901540955306e-05, 'samples': 23874048, 'steps': 124343, 'loss/train': 1.4982973337173462} 08/31/2021 11:48:35 - INFO - __main__ - Step 124345: {'lr': 3.61662660675362e-05, 'samples': 23874240, 'steps': 124344, 'loss/train': 1.5855225324630737} 08/31/2021 11:48:36 - INFO - __main__ - Step 124346: {'lr': 3.6163516821869554e-05, 'samples': 23874432, 'steps': 124345, 'loss/train': 0.9093976616859436} 08/31/2021 11:48:37 - INFO - __main__ - Step 124347: {'lr': 3.616076767255433e-05, 'samples': 23874624, 'steps': 124346, 'loss/train': 1.265878438949585} 08/31/2021 11:48:38 - INFO - __main__ - Step 124348: {'lr': 3.615801861959175e-05, 'samples': 23874816, 'steps': 124347, 'loss/train': 1.2515147924423218} 08/31/2021 11:48:38 - INFO - __main__ - Step 124349: {'lr': 3.6155269662983046e-05, 'samples': 23875008, 'steps': 124348, 'loss/train': 0.45203420519828796} 08/31/2021 11:48:38 - INFO - __main__ - Step 124350: {'lr': 3.615252080272952e-05, 'samples': 23875200, 'steps': 124349, 'loss/train': 0.5283531546592712} 08/31/2021 11:48:40 - INFO - __main__ - Step 124351: {'lr': 3.614977203883235e-05, 'samples': 23875392, 'steps': 124350, 'loss/train': 0.9619290232658386} 08/31/2021 11:48:41 - INFO - __main__ - Step 124352: {'lr': 3.6147023371292773e-05, 'samples': 23875584, 'steps': 124351, 'loss/train': 0.2606514096260071} 08/31/2021 11:48:41 - INFO - __main__ - Step 124353: {'lr': 3.6144274800112066e-05, 'samples': 23875776, 'steps': 124352, 'loss/train': 0.977695643901825} 08/31/2021 11:48:42 - INFO - __main__ - Step 124354: {'lr': 3.614152632529147e-05, 'samples': 23875968, 'steps': 124353, 'loss/train': 1.5346479415893555} 08/31/2021 11:48:42 - INFO - __main__ - Step 124355: {'lr': 3.613877794683218e-05, 'samples': 23876160, 'steps': 124354, 'loss/train': 0.7435924410820007} 08/31/2021 11:48:42 - INFO - __main__ - Step 124356: {'lr': 3.6136029664735506e-05, 'samples': 23876352, 'steps': 124355, 'loss/train': 1.3505162000656128} 08/31/2021 11:48:44 - INFO - __main__ - Step 124357: {'lr': 3.6133281479002576e-05, 'samples': 23876544, 'steps': 124356, 'loss/train': 0.9158649444580078} 08/31/2021 11:48:44 - INFO - __main__ - Step 124358: {'lr': 3.613053338963471e-05, 'samples': 23876736, 'steps': 124357, 'loss/train': 1.423183798789978} 08/31/2021 11:48:45 - INFO - __main__ - Step 124359: {'lr': 3.6127785396633114e-05, 'samples': 23876928, 'steps': 124358, 'loss/train': 0.923844039440155} 08/31/2021 11:48:45 - INFO - __main__ - Step 124360: {'lr': 3.612503749999904e-05, 'samples': 23877120, 'steps': 124359, 'loss/train': 1.3247264623641968} 08/31/2021 11:48:45 - INFO - __main__ - Step 124361: {'lr': 3.6122289699733716e-05, 'samples': 23877312, 'steps': 124360, 'loss/train': 1.0617364645004272} 08/31/2021 11:48:47 - INFO - __main__ - Step 124362: {'lr': 3.611954199583839e-05, 'samples': 23877504, 'steps': 124361, 'loss/train': 0.8014905452728271} 08/31/2021 11:48:47 - INFO - __main__ - Step 124363: {'lr': 3.61167943883143e-05, 'samples': 23877696, 'steps': 124362, 'loss/train': 0.8344287276268005} 08/31/2021 11:48:48 - INFO - __main__ - Step 124364: {'lr': 3.6114046877162715e-05, 'samples': 23877888, 'steps': 124363, 'loss/train': 0.39664119482040405} 08/31/2021 11:48:48 - INFO - __main__ - Step 124365: {'lr': 3.611129946238481e-05, 'samples': 23878080, 'steps': 124364, 'loss/train': 1.2688127756118774} 08/31/2021 11:48:49 - INFO - __main__ - Step 124366: {'lr': 3.610855214398184e-05, 'samples': 23878272, 'steps': 124365, 'loss/train': 1.0869877338409424} 08/31/2021 11:48:50 - INFO - __main__ - Step 124367: {'lr': 3.610580492195506e-05, 'samples': 23878464, 'steps': 124366, 'loss/train': 0.6360394358634949} 08/31/2021 11:48:51 - INFO - __main__ - Step 124368: {'lr': 3.6103057796305735e-05, 'samples': 23878656, 'steps': 124367, 'loss/train': 1.082763433456421} 08/31/2021 11:48:51 - INFO - __main__ - Step 124369: {'lr': 3.61003107670351e-05, 'samples': 23878848, 'steps': 124368, 'loss/train': 1.5176913738250732} 08/31/2021 11:48:51 - INFO - __main__ - Step 124370: {'lr': 3.609756383414431e-05, 'samples': 23879040, 'steps': 124369, 'loss/train': 1.11436128616333} 08/31/2021 11:48:52 - INFO - __main__ - Step 124371: {'lr': 3.609481699763467e-05, 'samples': 23879232, 'steps': 124370, 'loss/train': 1.111271619796753} 08/31/2021 11:48:53 - INFO - __main__ - Step 124372: {'lr': 3.609207025750738e-05, 'samples': 23879424, 'steps': 124371, 'loss/train': 1.2594226598739624} 08/31/2021 11:48:53 - INFO - __main__ - Step 124373: {'lr': 3.6089323613763716e-05, 'samples': 23879616, 'steps': 124372, 'loss/train': 1.812143087387085} 08/31/2021 11:48:54 - INFO - __main__ - Step 124374: {'lr': 3.608657706640492e-05, 'samples': 23879808, 'steps': 124373, 'loss/train': 1.0921378135681152} 08/31/2021 11:48:54 - INFO - __main__ - Step 124375: {'lr': 3.608383061543219e-05, 'samples': 23880000, 'steps': 124374, 'loss/train': 0.5152102708816528} 08/31/2021 11:48:55 - INFO - __main__ - Step 124376: {'lr': 3.6081084260846803e-05, 'samples': 23880192, 'steps': 124375, 'loss/train': 1.4798698425292969} 08/31/2021 11:48:56 - INFO - __main__ - Step 124377: {'lr': 3.607833800264995e-05, 'samples': 23880384, 'steps': 124376, 'loss/train': 0.7384831309318542} 08/31/2021 11:48:56 - INFO - __main__ - Step 124378: {'lr': 3.607559184084291e-05, 'samples': 23880576, 'steps': 124377, 'loss/train': 0.9789038896560669} 08/31/2021 11:48:57 - INFO - __main__ - Step 124379: {'lr': 3.607284577542691e-05, 'samples': 23880768, 'steps': 124378, 'loss/train': 1.5096715688705444} 08/31/2021 11:48:57 - INFO - __main__ - Step 124380: {'lr': 3.6070099806403246e-05, 'samples': 23880960, 'steps': 124379, 'loss/train': 0.7247434258460999} 08/31/2021 11:48:57 - INFO - __main__ - Step 124381: {'lr': 3.606735393377303e-05, 'samples': 23881152, 'steps': 124380, 'loss/train': 0.21855512261390686} 08/31/2021 11:48:59 - INFO - __main__ - Step 124382: {'lr': 3.6064608157537566e-05, 'samples': 23881344, 'steps': 124381, 'loss/train': 0.9518070816993713} 08/31/2021 11:49:00 - INFO - __main__ - Step 124383: {'lr': 3.6061862477698105e-05, 'samples': 23881536, 'steps': 124382, 'loss/train': 1.316582202911377} 08/31/2021 11:49:00 - INFO - __main__ - Step 124384: {'lr': 3.605911689425584e-05, 'samples': 23881728, 'steps': 124383, 'loss/train': 1.1190381050109863} 08/31/2021 11:49:00 - INFO - __main__ - Step 124385: {'lr': 3.605637140721205e-05, 'samples': 23881920, 'steps': 124384, 'loss/train': 0.4251328408718109} 08/31/2021 11:49:01 - INFO - __main__ - Step 124386: {'lr': 3.6053626016567945e-05, 'samples': 23882112, 'steps': 124385, 'loss/train': 0.8900385499000549} 08/31/2021 11:49:01 - INFO - __main__ - Step 124387: {'lr': 3.605088072232479e-05, 'samples': 23882304, 'steps': 124386, 'loss/train': 1.610230803489685} 08/31/2021 11:49:02 - INFO - __main__ - Step 124388: {'lr': 3.60481355244838e-05, 'samples': 23882496, 'steps': 124387, 'loss/train': 0.3726162612438202} 08/31/2021 11:49:03 - INFO - __main__ - Step 124389: {'lr': 3.604539042304622e-05, 'samples': 23882688, 'steps': 124388, 'loss/train': 1.2874163389205933} 08/31/2021 11:49:03 - INFO - __main__ - Step 124390: {'lr': 3.6042645418013276e-05, 'samples': 23882880, 'steps': 124389, 'loss/train': 0.042484790086746216} 08/31/2021 11:49:04 - INFO - __main__ - Step 124391: {'lr': 3.6039900509386296e-05, 'samples': 23883072, 'steps': 124390, 'loss/train': 1.1674998998641968} 08/31/2021 11:49:04 - INFO - __main__ - Step 124392: {'lr': 3.603715569716634e-05, 'samples': 23883264, 'steps': 124391, 'loss/train': 1.6644545793533325} 08/31/2021 11:49:05 - INFO - __main__ - Step 124393: {'lr': 3.6034410981354764e-05, 'samples': 23883456, 'steps': 124392, 'loss/train': 0.8935722708702087} 08/31/2021 11:49:06 - INFO - __main__ - Step 124394: {'lr': 3.6031666361952794e-05, 'samples': 23883648, 'steps': 124393, 'loss/train': 1.1593682765960693} 08/31/2021 11:49:06 - INFO - __main__ - Step 124395: {'lr': 3.6028921838961646e-05, 'samples': 23883840, 'steps': 124394, 'loss/train': 1.5563459396362305} 08/31/2021 11:49:07 - INFO - __main__ - Step 124396: {'lr': 3.602617741238254e-05, 'samples': 23884032, 'steps': 124395, 'loss/train': 1.1861354112625122} 08/31/2021 11:49:07 - INFO - __main__ - Step 124397: {'lr': 3.602343308221675e-05, 'samples': 23884224, 'steps': 124396, 'loss/train': 1.2909563779830933} 08/31/2021 11:49:08 - INFO - __main__ - Step 124398: {'lr': 3.6020688848465517e-05, 'samples': 23884416, 'steps': 124397, 'loss/train': 0.926423966884613} 08/31/2021 11:49:09 - INFO - __main__ - Step 124399: {'lr': 3.601794471113004e-05, 'samples': 23884608, 'steps': 124398, 'loss/train': 1.0957400798797607} 08/31/2021 11:49:09 - INFO - __main__ - Step 124400: {'lr': 3.601520067021158e-05, 'samples': 23884800, 'steps': 124399, 'loss/train': 0.2133234739303589} 08/31/2021 11:49:10 - INFO - __main__ - Step 124401: {'lr': 3.6012456725711437e-05, 'samples': 23884992, 'steps': 124400, 'loss/train': 0.2617512345314026} 08/31/2021 11:49:10 - INFO - __main__ - Step 124402: {'lr': 3.600971287763069e-05, 'samples': 23885184, 'steps': 124401, 'loss/train': 1.571897268295288} 08/31/2021 11:49:12 - INFO - __main__ - Step 124403: {'lr': 3.600696912597068e-05, 'samples': 23885376, 'steps': 124402, 'loss/train': 1.30689537525177} 08/31/2021 11:49:12 - INFO - __main__ - Step 124404: {'lr': 3.600422547073265e-05, 'samples': 23885568, 'steps': 124403, 'loss/train': 1.3689756393432617} 08/31/2021 11:49:13 - INFO - __main__ - Step 124405: {'lr': 3.600148191191779e-05, 'samples': 23885760, 'steps': 124404, 'loss/train': 1.0948436260223389} 08/31/2021 11:49:13 - INFO - __main__ - Step 124406: {'lr': 3.599873844952736e-05, 'samples': 23885952, 'steps': 124405, 'loss/train': 1.39302659034729} 08/31/2021 11:49:13 - INFO - __main__ - Step 124407: {'lr': 3.5995995083562604e-05, 'samples': 23886144, 'steps': 124406, 'loss/train': 0.9736725091934204} 08/31/2021 11:49:15 - INFO - __main__ - Step 124408: {'lr': 3.599325181402474e-05, 'samples': 23886336, 'steps': 124407, 'loss/train': 1.2513272762298584} 08/31/2021 11:49:15 - INFO - __main__ - Step 124409: {'lr': 3.599050864091505e-05, 'samples': 23886528, 'steps': 124408, 'loss/train': 0.8568651080131531} 08/31/2021 11:49:16 - INFO - __main__ - Step 124410: {'lr': 3.598776556423469e-05, 'samples': 23886720, 'steps': 124409, 'loss/train': 0.7006757259368896} 08/31/2021 11:49:16 - INFO - __main__ - Step 124411: {'lr': 3.598502258398495e-05, 'samples': 23886912, 'steps': 124410, 'loss/train': 1.1482571363449097} 08/31/2021 11:49:16 - INFO - __main__ - Step 124412: {'lr': 3.598227970016712e-05, 'samples': 23887104, 'steps': 124411, 'loss/train': 1.498970627784729} 08/31/2021 11:49:18 - INFO - __main__ - Step 124413: {'lr': 3.597953691278233e-05, 'samples': 23887296, 'steps': 124412, 'loss/train': 0.9203318953514099} 08/31/2021 11:49:18 - INFO - __main__ - Step 124414: {'lr': 3.597679422183184e-05, 'samples': 23887488, 'steps': 124413, 'loss/train': 0.7519310116767883} 08/31/2021 11:49:19 - INFO - __main__ - Step 124415: {'lr': 3.597405162731693e-05, 'samples': 23887680, 'steps': 124414, 'loss/train': 0.8854982256889343} 08/31/2021 11:49:19 - INFO - __main__ - Step 124416: {'lr': 3.5971309129238766e-05, 'samples': 23887872, 'steps': 124415, 'loss/train': 0.5130165219306946} 08/31/2021 11:49:19 - INFO - __main__ - Step 124417: {'lr': 3.596856672759866e-05, 'samples': 23888064, 'steps': 124416, 'loss/train': 1.660605549812317} 08/31/2021 11:49:21 - INFO - __main__ - Step 124418: {'lr': 3.596582442239779e-05, 'samples': 23888256, 'steps': 124417, 'loss/train': 0.5065990686416626} 08/31/2021 11:49:22 - INFO - __main__ - Step 124419: {'lr': 3.596308221363745e-05, 'samples': 23888448, 'steps': 124418, 'loss/train': 1.0388762950897217} 08/31/2021 11:49:22 - INFO - __main__ - Step 124420: {'lr': 3.596034010131882e-05, 'samples': 23888640, 'steps': 124419, 'loss/train': 0.5677922964096069} 08/31/2021 11:49:22 - INFO - __main__ - Step 124421: {'lr': 3.595759808544316e-05, 'samples': 23888832, 'steps': 124420, 'loss/train': 0.5333107709884644} 08/31/2021 11:49:23 - INFO - __main__ - Step 124422: {'lr': 3.595485616601171e-05, 'samples': 23889024, 'steps': 124421, 'loss/train': 1.1642130613327026} 08/31/2021 11:49:23 - INFO - __main__ - Step 124423: {'lr': 3.5952114343025754e-05, 'samples': 23889216, 'steps': 124422, 'loss/train': 1.6509928703308105} 08/31/2021 11:49:25 - INFO - __main__ - Step 124424: {'lr': 3.59493726164864e-05, 'samples': 23889408, 'steps': 124423, 'loss/train': 0.033490631729364395} 08/31/2021 11:49:25 - INFO - __main__ - Step 124425: {'lr': 3.5946630986394974e-05, 'samples': 23889600, 'steps': 124424, 'loss/train': 0.3732058107852936} 08/31/2021 11:49:26 - INFO - __main__ - Step 124426: {'lr': 3.594388945275271e-05, 'samples': 23889792, 'steps': 124425, 'loss/train': 1.2948359251022339} 08/31/2021 11:49:26 - INFO - __main__ - Step 124427: {'lr': 3.594114801556078e-05, 'samples': 23889984, 'steps': 124426, 'loss/train': 0.2781347334384918} 08/31/2021 11:49:26 - INFO - __main__ - Step 124428: {'lr': 3.593840667482048e-05, 'samples': 23890176, 'steps': 124427, 'loss/train': 1.811532974243164} 08/31/2021 11:49:28 - INFO - __main__ - Step 124429: {'lr': 3.593566543053306e-05, 'samples': 23890368, 'steps': 124428, 'loss/train': 1.5826480388641357} 08/31/2021 11:49:28 - INFO - __main__ - Step 124430: {'lr': 3.59329242826997e-05, 'samples': 23890560, 'steps': 124429, 'loss/train': 1.4449697732925415} 08/31/2021 11:49:29 - INFO - __main__ - Step 124431: {'lr': 3.593018323132166e-05, 'samples': 23890752, 'steps': 124430, 'loss/train': 1.6089770793914795} 08/31/2021 11:49:29 - INFO - __main__ - Step 124432: {'lr': 3.5927442276400186e-05, 'samples': 23890944, 'steps': 124431, 'loss/train': 1.3849701881408691} 08/31/2021 11:49:29 - INFO - __main__ - Step 124433: {'lr': 3.592470141793649e-05, 'samples': 23891136, 'steps': 124432, 'loss/train': 0.965459406375885} 08/31/2021 11:49:31 - INFO - __main__ - Step 124434: {'lr': 3.592196065593184e-05, 'samples': 23891328, 'steps': 124433, 'loss/train': 1.2875031232833862} 08/31/2021 11:49:31 - INFO - __main__ - Step 124435: {'lr': 3.5919219990387445e-05, 'samples': 23891520, 'steps': 124434, 'loss/train': 0.7897181510925293} 08/31/2021 11:49:32 - INFO - __main__ - Step 124436: {'lr': 3.59164794213046e-05, 'samples': 23891712, 'steps': 124435, 'loss/train': 0.9842735528945923} 08/31/2021 11:49:32 - INFO - __main__ - Step 124437: {'lr': 3.5913738948684435e-05, 'samples': 23891904, 'steps': 124436, 'loss/train': 1.1596654653549194} 08/31/2021 11:49:32 - INFO - __main__ - Step 124438: {'lr': 3.591099857252822e-05, 'samples': 23892096, 'steps': 124437, 'loss/train': 0.24883385002613068} 08/31/2021 11:49:33 - INFO - __main__ - Step 124439: {'lr': 3.590825829283723e-05, 'samples': 23892288, 'steps': 124438, 'loss/train': 1.0929780006408691} 08/31/2021 11:49:34 - INFO - __main__ - Step 124440: {'lr': 3.590551810961265e-05, 'samples': 23892480, 'steps': 124439, 'loss/train': 0.9679883122444153} 08/31/2021 11:49:35 - INFO - __main__ - Step 124441: {'lr': 3.5902778022855745e-05, 'samples': 23892672, 'steps': 124440, 'loss/train': 1.8291144371032715} 08/31/2021 11:49:35 - INFO - __main__ - Step 124442: {'lr': 3.590003803256775e-05, 'samples': 23892864, 'steps': 124441, 'loss/train': 0.9889212250709534} 08/31/2021 11:49:35 - INFO - __main__ - Step 124443: {'lr': 3.589729813874989e-05, 'samples': 23893056, 'steps': 124442, 'loss/train': 0.98968505859375} 08/31/2021 11:49:36 - INFO - __main__ - Step 124444: {'lr': 3.5894558341403425e-05, 'samples': 23893248, 'steps': 124443, 'loss/train': 1.2380257844924927} 08/31/2021 11:49:37 - INFO - __main__ - Step 124445: {'lr': 3.589181864052954e-05, 'samples': 23893440, 'steps': 124444, 'loss/train': 0.8503993153572083} 08/31/2021 11:49:38 - INFO - __main__ - Step 124446: {'lr': 3.588907903612951e-05, 'samples': 23893632, 'steps': 124445, 'loss/train': 1.0037575960159302} 08/31/2021 11:49:38 - INFO - __main__ - Step 124447: {'lr': 3.588633952820455e-05, 'samples': 23893824, 'steps': 124446, 'loss/train': 1.979764699935913} 08/31/2021 11:49:38 - INFO - __main__ - Step 124448: {'lr': 3.5883600116755926e-05, 'samples': 23894016, 'steps': 124447, 'loss/train': 1.3612256050109863} 08/31/2021 11:49:39 - INFO - __main__ - Step 124449: {'lr': 3.588086080178482e-05, 'samples': 23894208, 'steps': 124448, 'loss/train': 1.3471945524215698} 08/31/2021 11:49:41 - INFO - __main__ - Step 124450: {'lr': 3.5878121583292565e-05, 'samples': 23894400, 'steps': 124449, 'loss/train': 1.9541528224945068} 08/31/2021 11:49:41 - INFO - __main__ - Step 124451: {'lr': 3.587538246128025e-05, 'samples': 23894592, 'steps': 124450, 'loss/train': 0.5975419878959656} 08/31/2021 11:49:42 - INFO - __main__ - Step 124452: {'lr': 3.58726434357492e-05, 'samples': 23894784, 'steps': 124451, 'loss/train': 0.29488861560821533} 08/31/2021 11:49:42 - INFO - __main__ - Step 124453: {'lr': 3.5869904506700636e-05, 'samples': 23894976, 'steps': 124452, 'loss/train': 1.3673057556152344} 08/31/2021 11:49:42 - INFO - __main__ - Step 124454: {'lr': 3.586716567413578e-05, 'samples': 23895168, 'steps': 124453, 'loss/train': 0.45249661803245544} 08/31/2021 11:49:45 - INFO - __main__ - Step 124455: {'lr': 3.586442693805586e-05, 'samples': 23895360, 'steps': 124454, 'loss/train': 0.9449784755706787} 08/31/2021 11:49:45 - INFO - __main__ - Step 124456: {'lr': 3.5861688298462145e-05, 'samples': 23895552, 'steps': 124455, 'loss/train': 0.6873000264167786} 08/31/2021 11:49:46 - INFO - __main__ - Step 124457: {'lr': 3.585894975535584e-05, 'samples': 23895744, 'steps': 124456, 'loss/train': 0.06235603243112564} 08/31/2021 11:49:46 - INFO - __main__ - Step 124458: {'lr': 3.5856211308738204e-05, 'samples': 23895936, 'steps': 124457, 'loss/train': 0.6699116826057434} 08/31/2021 11:49:46 - INFO - __main__ - Step 124459: {'lr': 3.585347295861044e-05, 'samples': 23896128, 'steps': 124458, 'loss/train': 1.5430872440338135} 08/31/2021 11:49:49 - INFO - __main__ - Step 124460: {'lr': 3.58507347049738e-05, 'samples': 23896320, 'steps': 124459, 'loss/train': 0.7178087830543518} 08/31/2021 11:49:49 - INFO - __main__ - Step 124461: {'lr': 3.58479965478295e-05, 'samples': 23896512, 'steps': 124460, 'loss/train': 0.9173060655593872} 08/31/2021 11:49:50 - INFO - __main__ - Step 124462: {'lr': 3.584525848717882e-05, 'samples': 23896704, 'steps': 124461, 'loss/train': 1.2725580930709839} 08/31/2021 11:49:50 - INFO - __main__ - Step 124463: {'lr': 3.5842520523023007e-05, 'samples': 23896896, 'steps': 124462, 'loss/train': 0.9840564131736755} 08/31/2021 11:49:50 - INFO - __main__ - Step 124464: {'lr': 3.583978265536317e-05, 'samples': 23897088, 'steps': 124463, 'loss/train': 0.5790572762489319} 08/31/2021 11:49:51 - INFO - __main__ - Step 124465: {'lr': 3.583704488420064e-05, 'samples': 23897280, 'steps': 124464, 'loss/train': 0.9123009443283081} 08/31/2021 11:49:51 - INFO - __main__ - Step 124466: {'lr': 3.583430720953665e-05, 'samples': 23897472, 'steps': 124465, 'loss/train': 1.8626036643981934} 08/31/2021 11:49:53 - INFO - __main__ - Step 124467: {'lr': 3.583156963137238e-05, 'samples': 23897664, 'steps': 124466, 'loss/train': 1.7010900974273682} 08/31/2021 11:49:53 - INFO - __main__ - Step 124468: {'lr': 3.5828832149709115e-05, 'samples': 23897856, 'steps': 124467, 'loss/train': 1.3095592260360718} 08/31/2021 11:49:53 - INFO - __main__ - Step 124469: {'lr': 3.5826094764548096e-05, 'samples': 23898048, 'steps': 124468, 'loss/train': 1.6435227394104004} 08/31/2021 11:49:54 - INFO - __main__ - Step 124470: {'lr': 3.5823357475890495e-05, 'samples': 23898240, 'steps': 124469, 'loss/train': 0.5208678245544434} 08/31/2021 11:49:54 - INFO - __main__ - Step 124471: {'lr': 3.5820620283737615e-05, 'samples': 23898432, 'steps': 124470, 'loss/train': 1.3752610683441162} 08/31/2021 11:49:55 - INFO - __main__ - Step 124472: {'lr': 3.581788318809065e-05, 'samples': 23898624, 'steps': 124471, 'loss/train': 1.0731104612350464} 08/31/2021 11:49:56 - INFO - __main__ - Step 124473: {'lr': 3.581514618895082e-05, 'samples': 23898816, 'steps': 124472, 'loss/train': 1.0892575979232788} 08/31/2021 11:49:56 - INFO - __main__ - Step 124474: {'lr': 3.5812409286319404e-05, 'samples': 23899008, 'steps': 124473, 'loss/train': 1.3018629550933838} 08/31/2021 11:49:57 - INFO - __main__ - Step 124475: {'lr': 3.580967248019762e-05, 'samples': 23899200, 'steps': 124474, 'loss/train': 1.998819351196289} 08/31/2021 11:49:57 - INFO - __main__ - Step 124476: {'lr': 3.5806935770586665e-05, 'samples': 23899392, 'steps': 124475, 'loss/train': 0.9138337969779968} 08/31/2021 11:49:57 - INFO - __main__ - Step 124477: {'lr': 3.580419915748786e-05, 'samples': 23899584, 'steps': 124476, 'loss/train': 0.13198809325695038} 08/31/2021 11:49:59 - INFO - __main__ - Step 124478: {'lr': 3.580146264090234e-05, 'samples': 23899776, 'steps': 124477, 'loss/train': 1.217966079711914} 08/31/2021 11:50:00 - INFO - __main__ - Step 124479: {'lr': 3.579872622083139e-05, 'samples': 23899968, 'steps': 124478, 'loss/train': 0.10406111925840378} 08/31/2021 11:50:00 - INFO - __main__ - Step 124480: {'lr': 3.57959898972762e-05, 'samples': 23900160, 'steps': 124479, 'loss/train': 0.8105605840682983} 08/31/2021 11:50:00 - INFO - __main__ - Step 124481: {'lr': 3.579325367023803e-05, 'samples': 23900352, 'steps': 124480, 'loss/train': 0.8283424973487854} 08/31/2021 11:50:01 - INFO - __main__ - Step 124482: {'lr': 3.579051753971813e-05, 'samples': 23900544, 'steps': 124481, 'loss/train': 1.0690772533416748} 08/31/2021 11:50:02 - INFO - __main__ - Step 124483: {'lr': 3.578778150571768e-05, 'samples': 23900736, 'steps': 124482, 'loss/train': 0.3860168755054474} 08/31/2021 11:50:02 - INFO - __main__ - Step 124484: {'lr': 3.5785045568238e-05, 'samples': 23900928, 'steps': 124483, 'loss/train': 0.9088648557662964} 08/31/2021 11:50:03 - INFO - __main__ - Step 124485: {'lr': 3.578230972728025e-05, 'samples': 23901120, 'steps': 124484, 'loss/train': 1.3894387483596802} 08/31/2021 11:50:03 - INFO - __main__ - Step 124486: {'lr': 3.577957398284567e-05, 'samples': 23901312, 'steps': 124485, 'loss/train': 0.6820367574691772} 08/31/2021 11:50:04 - INFO - __main__ - Step 124487: {'lr': 3.5776838334935526e-05, 'samples': 23901504, 'steps': 124486, 'loss/train': 1.4982295036315918} 08/31/2021 11:50:04 - INFO - __main__ - Step 124488: {'lr': 3.577410278355103e-05, 'samples': 23901696, 'steps': 124487, 'loss/train': 0.8265705704689026} 08/31/2021 11:50:05 - INFO - __main__ - Step 124489: {'lr': 3.577136732869343e-05, 'samples': 23901888, 'steps': 124488, 'loss/train': 1.3127816915512085} 08/31/2021 11:50:06 - INFO - __main__ - Step 124490: {'lr': 3.576863197036401e-05, 'samples': 23902080, 'steps': 124489, 'loss/train': 0.7308945059776306} 08/31/2021 11:50:06 - INFO - __main__ - Step 124491: {'lr': 3.576589670856384e-05, 'samples': 23902272, 'steps': 124490, 'loss/train': 1.599797010421753} 08/31/2021 11:50:07 - INFO - __main__ - Step 124492: {'lr': 3.576316154329429e-05, 'samples': 23902464, 'steps': 124491, 'loss/train': 1.097814917564392} 08/31/2021 11:50:07 - INFO - __main__ - Step 124493: {'lr': 3.5760426474556546e-05, 'samples': 23902656, 'steps': 124492, 'loss/train': 1.280505657196045} 08/31/2021 11:50:09 - INFO - __main__ - Step 124494: {'lr': 3.5757691502351836e-05, 'samples': 23902848, 'steps': 124493, 'loss/train': 1.2682732343673706} 08/31/2021 11:50:09 - INFO - __main__ - Step 124495: {'lr': 3.5754956626681404e-05, 'samples': 23903040, 'steps': 124494, 'loss/train': 1.0814323425292969} 08/31/2021 11:50:09 - INFO - __main__ - Step 124496: {'lr': 3.575222184754648e-05, 'samples': 23903232, 'steps': 124495, 'loss/train': 2.3261377811431885} 08/31/2021 11:50:10 - INFO - __main__ - Step 124497: {'lr': 3.57494871649483e-05, 'samples': 23903424, 'steps': 124496, 'loss/train': 1.6271085739135742} 08/31/2021 11:50:10 - INFO - __main__ - Step 124498: {'lr': 3.5746752578888124e-05, 'samples': 23903616, 'steps': 124497, 'loss/train': 1.4688868522644043} 08/31/2021 11:50:12 - INFO - __main__ - Step 124499: {'lr': 3.574401808936712e-05, 'samples': 23903808, 'steps': 124498, 'loss/train': 0.8622159361839294} 08/31/2021 11:50:12 - INFO - __main__ - Step 124500: {'lr': 3.5741283696386575e-05, 'samples': 23904000, 'steps': 124499, 'loss/train': 0.9631068706512451} 08/31/2021 11:50:13 - INFO - __main__ - Step 124501: {'lr': 3.57385493999477e-05, 'samples': 23904192, 'steps': 124500, 'loss/train': 1.5446017980575562} 08/31/2021 11:50:13 - INFO - __main__ - Step 124502: {'lr': 3.5735815200051705e-05, 'samples': 23904384, 'steps': 124501, 'loss/train': 1.36891770362854} 08/31/2021 11:50:13 - INFO - __main__ - Step 124503: {'lr': 3.5733081096699924e-05, 'samples': 23904576, 'steps': 124502, 'loss/train': 0.6432972550392151} 08/31/2021 11:50:14 - INFO - __main__ - Step 124504: {'lr': 3.573034708989345e-05, 'samples': 23904768, 'steps': 124503, 'loss/train': 0.5861378312110901} 08/31/2021 11:50:15 - INFO - __main__ - Step 124505: {'lr': 3.572761317963358e-05, 'samples': 23904960, 'steps': 124504, 'loss/train': 0.3782336115837097} 08/31/2021 11:50:16 - INFO - __main__ - Step 124506: {'lr': 3.572487936592153e-05, 'samples': 23905152, 'steps': 124505, 'loss/train': 1.9513367414474487} 08/31/2021 11:50:16 - INFO - __main__ - Step 124507: {'lr': 3.572214564875856e-05, 'samples': 23905344, 'steps': 124506, 'loss/train': 1.154130220413208} 08/31/2021 11:50:16 - INFO - __main__ - Step 124508: {'lr': 3.571941202814588e-05, 'samples': 23905536, 'steps': 124507, 'loss/train': 0.8305388689041138} 08/31/2021 11:50:17 - INFO - __main__ - Step 124509: {'lr': 3.571667850408472e-05, 'samples': 23905728, 'steps': 124508, 'loss/train': 1.3095042705535889} 08/31/2021 11:50:19 - INFO - __main__ - Step 124510: {'lr': 3.57139450765763e-05, 'samples': 23905920, 'steps': 124509, 'loss/train': 1.1822372674942017} 08/31/2021 11:50:19 - INFO - __main__ - Step 124511: {'lr': 3.571121174562189e-05, 'samples': 23906112, 'steps': 124510, 'loss/train': 1.044325828552246} 08/31/2021 11:50:20 - INFO - __main__ - Step 124512: {'lr': 3.570847851122269e-05, 'samples': 23906304, 'steps': 124511, 'loss/train': 1.5742433071136475} 08/31/2021 11:50:20 - INFO - __main__ - Step 124513: {'lr': 3.570574537337998e-05, 'samples': 23906496, 'steps': 124512, 'loss/train': 1.5939357280731201} 08/31/2021 11:50:20 - INFO - __main__ - Step 124514: {'lr': 3.570301233209491e-05, 'samples': 23906688, 'steps': 124513, 'loss/train': 1.0937498807907104} 08/31/2021 11:50:22 - INFO - __main__ - Step 124515: {'lr': 3.570027938736878e-05, 'samples': 23906880, 'steps': 124514, 'loss/train': 1.0257511138916016} 08/31/2021 11:50:22 - INFO - __main__ - Step 124516: {'lr': 3.569754653920279e-05, 'samples': 23907072, 'steps': 124515, 'loss/train': 1.2655868530273438} 08/31/2021 11:50:23 - INFO - __main__ - Step 124517: {'lr': 3.569481378759823e-05, 'samples': 23907264, 'steps': 124516, 'loss/train': 1.2341607809066772} 08/31/2021 11:50:23 - INFO - __main__ - Step 124518: {'lr': 3.569208113255623e-05, 'samples': 23907456, 'steps': 124517, 'loss/train': 0.7305964231491089} 08/31/2021 11:50:23 - INFO - __main__ - Step 124519: {'lr': 3.568934857407807e-05, 'samples': 23907648, 'steps': 124518, 'loss/train': 1.339954137802124} 08/31/2021 11:50:25 - INFO - __main__ - Step 124520: {'lr': 3.568661611216498e-05, 'samples': 23907840, 'steps': 124519, 'loss/train': 1.7402533292770386} 08/31/2021 11:50:26 - INFO - __main__ - Step 124521: {'lr': 3.568388374681819e-05, 'samples': 23908032, 'steps': 124520, 'loss/train': 1.8793026208877563} 08/31/2021 11:50:26 - INFO - __main__ - Step 124522: {'lr': 3.568115147803894e-05, 'samples': 23908224, 'steps': 124521, 'loss/train': 0.9738911390304565} 08/31/2021 11:50:26 - INFO - __main__ - Step 124523: {'lr': 3.567841930582846e-05, 'samples': 23908416, 'steps': 124522, 'loss/train': 1.1573402881622314} 08/31/2021 11:50:27 - INFO - __main__ - Step 124524: {'lr': 3.5675687230187965e-05, 'samples': 23908608, 'steps': 124523, 'loss/train': 1.1281468868255615} 08/31/2021 11:50:28 - INFO - __main__ - Step 124525: {'lr': 3.567295525111872e-05, 'samples': 23908800, 'steps': 124524, 'loss/train': 1.3165069818496704} 08/31/2021 11:50:29 - INFO - __main__ - Step 124526: {'lr': 3.5670223368621914e-05, 'samples': 23908992, 'steps': 124525, 'loss/train': 0.4689105749130249} 08/31/2021 11:50:29 - INFO - __main__ - Step 124527: {'lr': 3.5667491582698805e-05, 'samples': 23909184, 'steps': 124526, 'loss/train': 0.7157741189002991} 08/31/2021 11:50:29 - INFO - __main__ - Step 124528: {'lr': 3.5664759893350605e-05, 'samples': 23909376, 'steps': 124527, 'loss/train': 1.252665638923645} 08/31/2021 11:50:30 - INFO - __main__ - Step 124529: {'lr': 3.5662028300578574e-05, 'samples': 23909568, 'steps': 124528, 'loss/train': 1.3441332578659058} 08/31/2021 11:50:31 - INFO - __main__ - Step 124530: {'lr': 3.5659296804383986e-05, 'samples': 23909760, 'steps': 124529, 'loss/train': 1.079389214515686} 08/31/2021 11:50:32 - INFO - __main__ - Step 124531: {'lr': 3.5656565404767946e-05, 'samples': 23909952, 'steps': 124530, 'loss/train': 2.6240696907043457} 08/31/2021 11:50:32 - INFO - __main__ - Step 124532: {'lr': 3.565383410173176e-05, 'samples': 23910144, 'steps': 124531, 'loss/train': 1.6957863569259644} 08/31/2021 11:50:32 - INFO - __main__ - Step 124533: {'lr': 3.5651102895276624e-05, 'samples': 23910336, 'steps': 124532, 'loss/train': 0.5414711833000183} 08/31/2021 11:50:33 - INFO - __main__ - Step 124534: {'lr': 3.564837178540381e-05, 'samples': 23910528, 'steps': 124533, 'loss/train': 0.8731461763381958} 08/31/2021 11:50:34 - INFO - __main__ - Step 124535: {'lr': 3.5645640772114515e-05, 'samples': 23910720, 'steps': 124534, 'loss/train': 1.2781485319137573} 08/31/2021 11:50:35 - INFO - __main__ - Step 124536: {'lr': 3.5642909855410024e-05, 'samples': 23910912, 'steps': 124535, 'loss/train': 1.0657920837402344} 08/31/2021 11:50:35 - INFO - __main__ - Step 124537: {'lr': 3.564017903529151e-05, 'samples': 23911104, 'steps': 124536, 'loss/train': 0.04615491256117821} 08/31/2021 11:50:35 - INFO - __main__ - Step 124538: {'lr': 3.563744831176022e-05, 'samples': 23911296, 'steps': 124537, 'loss/train': 1.6958444118499756} 08/31/2021 11:50:36 - INFO - __main__ - Step 124539: {'lr': 3.563471768481738e-05, 'samples': 23911488, 'steps': 124538, 'loss/train': 1.1456379890441895} 08/31/2021 11:50:38 - INFO - __main__ - Step 124540: {'lr': 3.563198715446425e-05, 'samples': 23911680, 'steps': 124539, 'loss/train': 1.626152515411377} 08/31/2021 11:50:38 - INFO - __main__ - Step 124541: {'lr': 3.562925672070202e-05, 'samples': 23911872, 'steps': 124540, 'loss/train': 1.6195721626281738} 08/31/2021 11:50:38 - INFO - __main__ - Step 124542: {'lr': 3.562652638353195e-05, 'samples': 23912064, 'steps': 124541, 'loss/train': 1.2912524938583374} 08/31/2021 11:50:39 - INFO - __main__ - Step 124543: {'lr': 3.5623796142955246e-05, 'samples': 23912256, 'steps': 124542, 'loss/train': 1.3377718925476074} 08/31/2021 11:50:39 - INFO - __main__ - Step 124544: {'lr': 3.562106599897322e-05, 'samples': 23912448, 'steps': 124543, 'loss/train': 0.968695342540741} 08/31/2021 11:50:40 - INFO - __main__ - Step 124545: {'lr': 3.561833595158698e-05, 'samples': 23912640, 'steps': 124544, 'loss/train': 0.9127137064933777} 08/31/2021 11:50:41 - INFO - __main__ - Step 124546: {'lr': 3.56156060007978e-05, 'samples': 23912832, 'steps': 124545, 'loss/train': 0.03799045830965042} 08/31/2021 11:50:42 - INFO - __main__ - Step 124547: {'lr': 3.561287614660691e-05, 'samples': 23913024, 'steps': 124546, 'loss/train': 1.5653283596038818} 08/31/2021 11:50:42 - INFO - __main__ - Step 124548: {'lr': 3.561014638901558e-05, 'samples': 23913216, 'steps': 124547, 'loss/train': 0.6510274410247803} 08/31/2021 11:50:42 - INFO - __main__ - Step 124549: {'lr': 3.560741672802498e-05, 'samples': 23913408, 'steps': 124548, 'loss/train': 1.0978686809539795} 08/31/2021 11:50:43 - INFO - __main__ - Step 124550: {'lr': 3.560468716363638e-05, 'samples': 23913600, 'steps': 124549, 'loss/train': 1.463160514831543} 08/31/2021 11:50:45 - INFO - __main__ - Step 124551: {'lr': 3.560195769585101e-05, 'samples': 23913792, 'steps': 124550, 'loss/train': 1.797166347503662} 08/31/2021 11:50:45 - INFO - __main__ - Step 124552: {'lr': 3.559922832467008e-05, 'samples': 23913984, 'steps': 124551, 'loss/train': 1.2119768857955933} 08/31/2021 11:50:46 - INFO - __main__ - Step 124553: {'lr': 3.5596499050094824e-05, 'samples': 23914176, 'steps': 124552, 'loss/train': 1.3229563236236572} 08/31/2021 11:50:46 - INFO - __main__ - Step 124554: {'lr': 3.559376987212648e-05, 'samples': 23914368, 'steps': 124553, 'loss/train': 0.016155365854501724} 08/31/2021 11:50:46 - INFO - __main__ - Step 124555: {'lr': 3.559104079076628e-05, 'samples': 23914560, 'steps': 124554, 'loss/train': 1.552925944328308} 08/31/2021 11:50:47 - INFO - __main__ - Step 124556: {'lr': 3.558831180601546e-05, 'samples': 23914752, 'steps': 124555, 'loss/train': 1.273477554321289} 08/31/2021 11:50:48 - INFO - __main__ - Step 124557: {'lr': 3.5585582917875284e-05, 'samples': 23914944, 'steps': 124556, 'loss/train': 1.6856368780136108} 08/31/2021 11:50:49 - INFO - __main__ - Step 124558: {'lr': 3.558285412634687e-05, 'samples': 23915136, 'steps': 124557, 'loss/train': 2.0479815006256104} 08/31/2021 11:50:49 - INFO - __main__ - Step 124559: {'lr': 3.558012543143152e-05, 'samples': 23915328, 'steps': 124558, 'loss/train': 1.308445692062378} 08/31/2021 11:50:49 - INFO - __main__ - Step 124560: {'lr': 3.5577396833130465e-05, 'samples': 23915520, 'steps': 124559, 'loss/train': 1.0255885124206543} 08/31/2021 11:50:50 - INFO - __main__ - Step 124561: {'lr': 3.55746683314449e-05, 'samples': 23915712, 'steps': 124560, 'loss/train': 1.39877188205719} 08/31/2021 11:50:51 - INFO - __main__ - Step 124562: {'lr': 3.557193992637611e-05, 'samples': 23915904, 'steps': 124561, 'loss/train': 1.0641041994094849} 08/31/2021 11:50:52 - INFO - __main__ - Step 124563: {'lr': 3.556921161792528e-05, 'samples': 23916096, 'steps': 124562, 'loss/train': 0.9195722341537476} 08/31/2021 11:50:52 - INFO - __main__ - Step 124564: {'lr': 3.556648340609367e-05, 'samples': 23916288, 'steps': 124563, 'loss/train': 1.7619463205337524} 08/31/2021 11:50:52 - INFO - __main__ - Step 124565: {'lr': 3.556375529088246e-05, 'samples': 23916480, 'steps': 124564, 'loss/train': 1.0897321701049805} 08/31/2021 11:50:53 - INFO - __main__ - Step 124566: {'lr': 3.556102727229293e-05, 'samples': 23916672, 'steps': 124565, 'loss/train': 1.0535367727279663} 08/31/2021 11:50:53 - INFO - __main__ - Step 124567: {'lr': 3.5558299350326314e-05, 'samples': 23916864, 'steps': 124566, 'loss/train': 0.028400268405675888} 08/31/2021 11:50:55 - INFO - __main__ - Step 124568: {'lr': 3.5555571524983787e-05, 'samples': 23917056, 'steps': 124567, 'loss/train': 1.2142512798309326} 08/31/2021 11:50:56 - INFO - __main__ - Step 124569: {'lr': 3.555284379626664e-05, 'samples': 23917248, 'steps': 124568, 'loss/train': 1.0313125848770142} 08/31/2021 11:50:56 - INFO - __main__ - Step 124570: {'lr': 3.555011616417605e-05, 'samples': 23917440, 'steps': 124569, 'loss/train': 1.6822712421417236} 08/31/2021 11:50:56 - INFO - __main__ - Step 124571: {'lr': 3.554738862871335e-05, 'samples': 23917632, 'steps': 124570, 'loss/train': 1.2019678354263306} 08/31/2021 11:50:57 - INFO - __main__ - Step 124572: {'lr': 3.554466118987959e-05, 'samples': 23917824, 'steps': 124571, 'loss/train': 1.0979028940200806} 08/31/2021 11:50:58 - INFO - __main__ - Step 124573: {'lr': 3.554193384767612e-05, 'samples': 23918016, 'steps': 124572, 'loss/train': 0.26514244079589844} 08/31/2021 11:50:59 - INFO - __main__ - Step 124574: {'lr': 3.5539206602104165e-05, 'samples': 23918208, 'steps': 124573, 'loss/train': 1.2180969715118408} 08/31/2021 11:50:59 - INFO - __main__ - Step 124575: {'lr': 3.553647945316491e-05, 'samples': 23918400, 'steps': 124574, 'loss/train': 1.2478992938995361} 08/31/2021 11:51:00 - INFO - __main__ - Step 124576: {'lr': 3.55337524008596e-05, 'samples': 23918592, 'steps': 124575, 'loss/train': 0.525009036064148} 08/31/2021 11:51:00 - INFO - __main__ - Step 124577: {'lr': 3.553102544518949e-05, 'samples': 23918784, 'steps': 124576, 'loss/train': 1.00018310546875} 08/31/2021 11:51:02 - INFO - __main__ - Step 124578: {'lr': 3.5528298586155776e-05, 'samples': 23918976, 'steps': 124577, 'loss/train': 0.5811070799827576} 08/31/2021 11:51:02 - INFO - __main__ - Step 124579: {'lr': 3.552557182375973e-05, 'samples': 23919168, 'steps': 124578, 'loss/train': 1.2499195337295532} 08/31/2021 11:51:02 - INFO - __main__ - Step 124580: {'lr': 3.5522845158002525e-05, 'samples': 23919360, 'steps': 124579, 'loss/train': 0.28778988122940063} 08/31/2021 11:51:03 - INFO - __main__ - Step 124581: {'lr': 3.552011858888543e-05, 'samples': 23919552, 'steps': 124580, 'loss/train': 0.24141263961791992} 08/31/2021 11:51:03 - INFO - __main__ - Step 124582: {'lr': 3.551739211640964e-05, 'samples': 23919744, 'steps': 124581, 'loss/train': 1.4074172973632812} 08/31/2021 11:51:03 - INFO - __main__ - Step 124583: {'lr': 3.5514665740576435e-05, 'samples': 23919936, 'steps': 124582, 'loss/train': 1.1606061458587646} 08/31/2021 11:51:05 - INFO - __main__ - Step 124584: {'lr': 3.5511939461387033e-05, 'samples': 23920128, 'steps': 124583, 'loss/train': 0.8356748819351196} 08/31/2021 11:51:06 - INFO - __main__ - Step 124585: {'lr': 3.55092132788426e-05, 'samples': 23920320, 'steps': 124584, 'loss/train': 0.025485288351774216} 08/31/2021 11:51:06 - INFO - __main__ - Step 124586: {'lr': 3.5506487192944416e-05, 'samples': 23920512, 'steps': 124585, 'loss/train': 1.346906065940857} 08/31/2021 11:51:06 - INFO - __main__ - Step 124587: {'lr': 3.5503761203693694e-05, 'samples': 23920704, 'steps': 124586, 'loss/train': 1.1752854585647583} 08/31/2021 11:51:07 - INFO - __main__ - Step 124588: {'lr': 3.550103531109167e-05, 'samples': 23920896, 'steps': 124587, 'loss/train': 0.937737226486206} 08/31/2021 11:51:08 - INFO - __main__ - Step 124589: {'lr': 3.549830951513955e-05, 'samples': 23921088, 'steps': 124588, 'loss/train': 1.2247167825698853} 08/31/2021 11:51:09 - INFO - __main__ - Step 124590: {'lr': 3.549558381583859e-05, 'samples': 23921280, 'steps': 124589, 'loss/train': 1.0593745708465576} 08/31/2021 11:51:09 - INFO - __main__ - Step 124591: {'lr': 3.549285821319004e-05, 'samples': 23921472, 'steps': 124590, 'loss/train': 1.8354806900024414} 08/31/2021 11:51:09 - INFO - __main__ - Step 124592: {'lr': 3.549013270719506e-05, 'samples': 23921664, 'steps': 124591, 'loss/train': 1.09341561794281} 08/31/2021 11:51:10 - INFO - __main__ - Step 124593: {'lr': 3.5487407297854936e-05, 'samples': 23921856, 'steps': 124592, 'loss/train': 1.281620979309082} 08/31/2021 11:51:12 - INFO - __main__ - Step 124594: {'lr': 3.548468198517085e-05, 'samples': 23922048, 'steps': 124593, 'loss/train': 1.3157131671905518} 08/31/2021 11:51:12 - INFO - __main__ - Step 124595: {'lr': 3.548195676914409e-05, 'samples': 23922240, 'steps': 124594, 'loss/train': 0.9844619631767273} 08/31/2021 11:51:13 - INFO - __main__ - Step 124596: {'lr': 3.547923164977584e-05, 'samples': 23922432, 'steps': 124595, 'loss/train': 4.044674396514893} 08/31/2021 11:51:13 - INFO - __main__ - Step 124597: {'lr': 3.5476506627067335e-05, 'samples': 23922624, 'steps': 124596, 'loss/train': 3.131525993347168} 08/31/2021 11:51:13 - INFO - __main__ - Step 124598: {'lr': 3.547378170101986e-05, 'samples': 23922816, 'steps': 124597, 'loss/train': 1.0075435638427734} 08/31/2021 11:51:14 - INFO - __main__ - Step 124599: {'lr': 3.5471056871634544e-05, 'samples': 23923008, 'steps': 124598, 'loss/train': 1.604434609413147} 08/31/2021 11:51:15 - INFO - __main__ - Step 124600: {'lr': 3.5468332138912626e-05, 'samples': 23923200, 'steps': 124599, 'loss/train': 1.4949482679367065} 08/31/2021 11:51:16 - INFO - __main__ - Step 124601: {'lr': 3.546560750285541e-05, 'samples': 23923392, 'steps': 124600, 'loss/train': 0.03270211070775986} 08/31/2021 11:51:16 - INFO - __main__ - Step 124602: {'lr': 3.546288296346406e-05, 'samples': 23923584, 'steps': 124601, 'loss/train': 1.5435351133346558} 08/31/2021 11:51:16 - INFO - __main__ - Step 124603: {'lr': 3.5460158520739805e-05, 'samples': 23923776, 'steps': 124602, 'loss/train': 1.128818392753601} 08/31/2021 11:51:17 - INFO - __main__ - Step 124604: {'lr': 3.545743417468392e-05, 'samples': 23923968, 'steps': 124603, 'loss/train': 1.0366328954696655} 08/31/2021 11:51:18 - INFO - __main__ - Step 124605: {'lr': 3.545470992529759e-05, 'samples': 23924160, 'steps': 124604, 'loss/train': 0.649415910243988} 08/31/2021 11:51:19 - INFO - __main__ - Step 124606: {'lr': 3.5451985772582076e-05, 'samples': 23924352, 'steps': 124605, 'loss/train': 0.5093542337417603} 08/31/2021 11:51:19 - INFO - __main__ - Step 124607: {'lr': 3.544926171653856e-05, 'samples': 23924544, 'steps': 124606, 'loss/train': 1.5829741954803467} 08/31/2021 11:51:19 - INFO - __main__ - Step 124608: {'lr': 3.544653775716833e-05, 'samples': 23924736, 'steps': 124607, 'loss/train': 1.0028233528137207} 08/31/2021 11:51:20 - INFO - __main__ - Step 124609: {'lr': 3.544381389447254e-05, 'samples': 23924928, 'steps': 124608, 'loss/train': 1.9160535335540771} 08/31/2021 11:51:21 - INFO - __main__ - Step 124610: {'lr': 3.544109012845248e-05, 'samples': 23925120, 'steps': 124609, 'loss/train': 0.9383457899093628} 08/31/2021 11:51:22 - INFO - __main__ - Step 124611: {'lr': 3.543836645910942e-05, 'samples': 23925312, 'steps': 124610, 'loss/train': 0.949547529220581} 08/31/2021 11:51:22 - INFO - __main__ - Step 124612: {'lr': 3.543564288644443e-05, 'samples': 23925504, 'steps': 124611, 'loss/train': 1.0300925970077515} 08/31/2021 11:51:22 - INFO - __main__ - Step 124613: {'lr': 3.543291941045887e-05, 'samples': 23925696, 'steps': 124612, 'loss/train': 1.6284289360046387} 08/31/2021 11:51:23 - INFO - __main__ - Step 124614: {'lr': 3.543019603115391e-05, 'samples': 23925888, 'steps': 124613, 'loss/train': 1.3692028522491455} 08/31/2021 11:51:24 - INFO - __main__ - Step 124615: {'lr': 3.5427472748530784e-05, 'samples': 23926080, 'steps': 124614, 'loss/train': 0.8997076153755188} 08/31/2021 11:51:25 - INFO - __main__ - Step 124616: {'lr': 3.542474956259073e-05, 'samples': 23926272, 'steps': 124615, 'loss/train': 1.166251301765442} 08/31/2021 11:51:25 - INFO - __main__ - Step 124617: {'lr': 3.542202647333498e-05, 'samples': 23926464, 'steps': 124616, 'loss/train': 0.49335339665412903} 08/31/2021 11:51:26 - INFO - __main__ - Step 124618: {'lr': 3.541930348076475e-05, 'samples': 23926656, 'steps': 124617, 'loss/train': 1.2811999320983887} 08/31/2021 11:51:26 - INFO - __main__ - Step 124619: {'lr': 3.541658058488126e-05, 'samples': 23926848, 'steps': 124618, 'loss/train': 0.6781673431396484} 08/31/2021 11:51:28 - INFO - __main__ - Step 124620: {'lr': 3.541385778568576e-05, 'samples': 23927040, 'steps': 124619, 'loss/train': 1.0665467977523804} 08/31/2021 11:51:29 - INFO - __main__ - Step 124621: {'lr': 3.541113508317945e-05, 'samples': 23927232, 'steps': 124620, 'loss/train': 0.8149351477622986} 08/31/2021 11:51:29 - INFO - __main__ - Step 124622: {'lr': 3.5408412477363596e-05, 'samples': 23927424, 'steps': 124621, 'loss/train': 1.8279682397842407} 08/31/2021 11:51:29 - INFO - __main__ - Step 124623: {'lr': 3.5405689968239366e-05, 'samples': 23927616, 'steps': 124622, 'loss/train': 0.754496693611145} 08/31/2021 11:51:30 - INFO - __main__ - Step 124624: {'lr': 3.540296755580805e-05, 'samples': 23927808, 'steps': 124623, 'loss/train': 0.8469376564025879} 08/31/2021 11:51:30 - INFO - __main__ - Step 124625: {'lr': 3.5400245240070906e-05, 'samples': 23928000, 'steps': 124624, 'loss/train': 1.6144089698791504} 08/31/2021 11:51:31 - INFO - __main__ - Step 124626: {'lr': 3.539752302102903e-05, 'samples': 23928192, 'steps': 124625, 'loss/train': 1.506946325302124} 08/31/2021 11:51:32 - INFO - __main__ - Step 124627: {'lr': 3.539480089868372e-05, 'samples': 23928384, 'steps': 124626, 'loss/train': 1.027574062347412} 08/31/2021 11:51:32 - INFO - __main__ - Step 124628: {'lr': 3.539207887303619e-05, 'samples': 23928576, 'steps': 124627, 'loss/train': 0.8132217526435852} 08/31/2021 11:51:33 - INFO - __main__ - Step 124629: {'lr': 3.538935694408768e-05, 'samples': 23928768, 'steps': 124628, 'loss/train': 0.3300918936729431} 08/31/2021 11:51:33 - INFO - __main__ - Step 124630: {'lr': 3.5386635111839425e-05, 'samples': 23928960, 'steps': 124629, 'loss/train': 1.395046591758728} 08/31/2021 11:51:34 - INFO - __main__ - Step 124631: {'lr': 3.5383913376292626e-05, 'samples': 23929152, 'steps': 124630, 'loss/train': 1.1669418811798096} 08/31/2021 11:51:35 - INFO - __main__ - Step 124632: {'lr': 3.5381191737448556e-05, 'samples': 23929344, 'steps': 124631, 'loss/train': 1.1981512308120728} 08/31/2021 11:51:35 - INFO - __main__ - Step 124633: {'lr': 3.5378470195308374e-05, 'samples': 23929536, 'steps': 124632, 'loss/train': 0.9836582541465759} 08/31/2021 11:51:36 - INFO - __main__ - Step 124634: {'lr': 3.537574874987337e-05, 'samples': 23929728, 'steps': 124633, 'loss/train': 1.0889244079589844} 08/31/2021 11:51:36 - INFO - __main__ - Step 124635: {'lr': 3.537302740114473e-05, 'samples': 23929920, 'steps': 124634, 'loss/train': 0.6802700757980347} 08/31/2021 11:51:38 - INFO - __main__ - Step 124636: {'lr': 3.537030614912368e-05, 'samples': 23930112, 'steps': 124635, 'loss/train': 1.811861515045166} 08/31/2021 11:51:38 - INFO - __main__ - Step 124637: {'lr': 3.536758499381146e-05, 'samples': 23930304, 'steps': 124636, 'loss/train': 1.2413508892059326} 08/31/2021 11:51:38 - INFO - __main__ - Step 124638: {'lr': 3.536486393520935e-05, 'samples': 23930496, 'steps': 124637, 'loss/train': 1.203546166419983} 08/31/2021 11:51:39 - INFO - __main__ - Step 124639: {'lr': 3.53621429733185e-05, 'samples': 23930688, 'steps': 124638, 'loss/train': 0.7822690606117249} 08/31/2021 11:51:39 - INFO - __main__ - Step 124640: {'lr': 3.535942210814011e-05, 'samples': 23930880, 'steps': 124639, 'loss/train': 0.9944160580635071} 08/31/2021 11:51:41 - INFO - __main__ - Step 124641: {'lr': 3.5356701339675475e-05, 'samples': 23931072, 'steps': 124640, 'loss/train': 1.0539389848709106} 08/31/2021 11:51:41 - INFO - __main__ - Step 124642: {'lr': 3.5353980667925804e-05, 'samples': 23931264, 'steps': 124641, 'loss/train': 0.9349083304405212} 08/31/2021 11:51:42 - INFO - __main__ - Step 124643: {'lr': 3.53512600928923e-05, 'samples': 23931456, 'steps': 124642, 'loss/train': 0.9478049874305725} 08/31/2021 11:51:42 - INFO - __main__ - Step 124644: {'lr': 3.534853961457621e-05, 'samples': 23931648, 'steps': 124643, 'loss/train': 1.4815478324890137} 08/31/2021 11:51:42 - INFO - __main__ - Step 124645: {'lr': 3.534581923297875e-05, 'samples': 23931840, 'steps': 124644, 'loss/train': 1.5787855386734009} 08/31/2021 11:51:44 - INFO - __main__ - Step 124646: {'lr': 3.5343098948101174e-05, 'samples': 23932032, 'steps': 124645, 'loss/train': 1.157997727394104} 08/31/2021 11:51:45 - INFO - __main__ - Step 124647: {'lr': 3.534037875994467e-05, 'samples': 23932224, 'steps': 124646, 'loss/train': 1.3885211944580078} 08/31/2021 11:51:45 - INFO - __main__ - Step 124648: {'lr': 3.5337658668510546e-05, 'samples': 23932416, 'steps': 124647, 'loss/train': 1.2803845405578613} 08/31/2021 11:51:45 - INFO - __main__ - Step 124649: {'lr': 3.5334938673799887e-05, 'samples': 23932608, 'steps': 124648, 'loss/train': 1.259220838546753} 08/31/2021 11:51:46 - INFO - __main__ - Step 124650: {'lr': 3.533221877581399e-05, 'samples': 23932800, 'steps': 124649, 'loss/train': 0.6549776196479797} 08/31/2021 11:51:47 - INFO - __main__ - Step 124651: {'lr': 3.532949897455409e-05, 'samples': 23932992, 'steps': 124650, 'loss/train': 0.8550461530685425} 08/31/2021 11:51:48 - INFO - __main__ - Step 124652: {'lr': 3.532677927002142e-05, 'samples': 23933184, 'steps': 124651, 'loss/train': 0.20122990012168884} 08/31/2021 11:51:48 - INFO - __main__ - Step 124653: {'lr': 3.532405966221719e-05, 'samples': 23933376, 'steps': 124652, 'loss/train': 1.4134472608566284} 08/31/2021 11:51:48 - INFO - __main__ - Step 124654: {'lr': 3.532134015114261e-05, 'samples': 23933568, 'steps': 124653, 'loss/train': 0.9124980568885803} 08/31/2021 11:51:49 - INFO - __main__ - Step 124655: {'lr': 3.5318620736798927e-05, 'samples': 23933760, 'steps': 124654, 'loss/train': 0.7376291155815125} 08/31/2021 11:51:49 - INFO - __main__ - Step 124656: {'lr': 3.5315901419187364e-05, 'samples': 23933952, 'steps': 124655, 'loss/train': 0.7341951131820679} 08/31/2021 11:51:50 - INFO - __main__ - Step 124657: {'lr': 3.531318219830912e-05, 'samples': 23934144, 'steps': 124656, 'loss/train': 0.9097623229026794} 08/31/2021 11:51:51 - INFO - __main__ - Step 124658: {'lr': 3.5310463074165465e-05, 'samples': 23934336, 'steps': 124657, 'loss/train': 1.1356253623962402} 08/31/2021 11:51:51 - INFO - __main__ - Step 124659: {'lr': 3.5307744046757656e-05, 'samples': 23934528, 'steps': 124658, 'loss/train': 1.969923496246338} 08/31/2021 11:51:52 - INFO - __main__ - Step 124660: {'lr': 3.5305025116086824e-05, 'samples': 23934720, 'steps': 124659, 'loss/train': 1.6783020496368408} 08/31/2021 11:51:52 - INFO - __main__ - Step 124661: {'lr': 3.5302306282154195e-05, 'samples': 23934912, 'steps': 124660, 'loss/train': 0.6068229079246521} 08/31/2021 11:51:54 - INFO - __main__ - Step 124662: {'lr': 3.529958754496107e-05, 'samples': 23935104, 'steps': 124661, 'loss/train': 1.3174234628677368} 08/31/2021 11:51:54 - INFO - __main__ - Step 124663: {'lr': 3.5296868904508615e-05, 'samples': 23935296, 'steps': 124662, 'loss/train': 0.1579829305410385} 08/31/2021 11:51:55 - INFO - __main__ - Step 124664: {'lr': 3.529415036079811e-05, 'samples': 23935488, 'steps': 124663, 'loss/train': 1.3306844234466553} 08/31/2021 11:51:55 - INFO - __main__ - Step 124665: {'lr': 3.529143191383072e-05, 'samples': 23935680, 'steps': 124664, 'loss/train': 0.6659641265869141} 08/31/2021 11:51:55 - INFO - __main__ - Step 124666: {'lr': 3.528871356360769e-05, 'samples': 23935872, 'steps': 124665, 'loss/train': 1.3744245767593384} 08/31/2021 11:51:57 - INFO - __main__ - Step 124667: {'lr': 3.528599531013027e-05, 'samples': 23936064, 'steps': 124666, 'loss/train': 1.1422219276428223} 08/31/2021 11:51:57 - INFO - __main__ - Step 124668: {'lr': 3.5283277153399685e-05, 'samples': 23936256, 'steps': 124667, 'loss/train': 0.8961599469184875} 08/31/2021 11:51:58 - INFO - __main__ - Step 124669: {'lr': 3.52805590934171e-05, 'samples': 23936448, 'steps': 124668, 'loss/train': 1.13997220993042} 08/31/2021 11:51:58 - INFO - __main__ - Step 124670: {'lr': 3.527784113018387e-05, 'samples': 23936640, 'steps': 124669, 'loss/train': 1.5492923259735107} 08/31/2021 11:51:58 - INFO - __main__ - Step 124671: {'lr': 3.5275123263701055e-05, 'samples': 23936832, 'steps': 124670, 'loss/train': 0.5096381306648254} 08/31/2021 11:52:00 - INFO - __main__ - Step 124672: {'lr': 3.527240549396998e-05, 'samples': 23937024, 'steps': 124671, 'loss/train': 1.1185107231140137} 08/31/2021 11:52:00 - INFO - __main__ - Step 124673: {'lr': 3.5269687820991824e-05, 'samples': 23937216, 'steps': 124672, 'loss/train': 0.8853623867034912} 08/31/2021 11:52:01 - INFO - __main__ - Step 124674: {'lr': 3.5266970244767827e-05, 'samples': 23937408, 'steps': 124673, 'loss/train': 0.735550582408905} 08/31/2021 11:52:01 - INFO - __main__ - Step 124675: {'lr': 3.526425276529924e-05, 'samples': 23937600, 'steps': 124674, 'loss/train': 0.5728048086166382} 08/31/2021 11:52:01 - INFO - __main__ - Step 124676: {'lr': 3.526153538258725e-05, 'samples': 23937792, 'steps': 124675, 'loss/train': 1.2218809127807617} 08/31/2021 11:52:04 - INFO - __main__ - Step 124677: {'lr': 3.5258818096633115e-05, 'samples': 23937984, 'steps': 124676, 'loss/train': 1.6203234195709229} 08/31/2021 11:52:04 - INFO - __main__ - Step 124678: {'lr': 3.5256100907438054e-05, 'samples': 23938176, 'steps': 124677, 'loss/train': 1.0074809789657593} 08/31/2021 11:52:05 - INFO - __main__ - Step 124679: {'lr': 3.525338381500326e-05, 'samples': 23938368, 'steps': 124678, 'loss/train': 1.0332541465759277} 08/31/2021 11:52:05 - INFO - __main__ - Step 124680: {'lr': 3.525066681932998e-05, 'samples': 23938560, 'steps': 124679, 'loss/train': 1.611956238746643} 08/31/2021 11:52:05 - INFO - __main__ - Step 124681: {'lr': 3.5247949920419495e-05, 'samples': 23938752, 'steps': 124680, 'loss/train': 1.155340552330017} 08/31/2021 11:52:06 - INFO - __main__ - Step 124682: {'lr': 3.524523311827291e-05, 'samples': 23938944, 'steps': 124681, 'loss/train': 0.11465102434158325} 08/31/2021 11:52:07 - INFO - __main__ - Step 124683: {'lr': 3.52425164128915e-05, 'samples': 23939136, 'steps': 124682, 'loss/train': 0.03270750120282173} 08/31/2021 11:52:08 - INFO - __main__ - Step 124684: {'lr': 3.52397998042765e-05, 'samples': 23939328, 'steps': 124683, 'loss/train': 0.7347513437271118} 08/31/2021 11:52:08 - INFO - __main__ - Step 124685: {'lr': 3.523708329242914e-05, 'samples': 23939520, 'steps': 124684, 'loss/train': 1.8231641054153442} 08/31/2021 11:52:08 - INFO - __main__ - Step 124686: {'lr': 3.523436687735065e-05, 'samples': 23939712, 'steps': 124685, 'loss/train': 1.8185372352600098} 08/31/2021 11:52:09 - INFO - __main__ - Step 124687: {'lr': 3.5231650559042206e-05, 'samples': 23939904, 'steps': 124686, 'loss/train': 0.42199644446372986} 08/31/2021 11:52:10 - INFO - __main__ - Step 124688: {'lr': 3.52289343375051e-05, 'samples': 23940096, 'steps': 124687, 'loss/train': 1.1574770212173462} 08/31/2021 11:52:11 - INFO - __main__ - Step 124689: {'lr': 3.52262182127405e-05, 'samples': 23940288, 'steps': 124688, 'loss/train': 1.7201231718063354} 08/31/2021 11:52:11 - INFO - __main__ - Step 124690: {'lr': 3.522350218474968e-05, 'samples': 23940480, 'steps': 124689, 'loss/train': 1.1085076332092285} 08/31/2021 11:52:11 - INFO - __main__ - Step 124691: {'lr': 3.522078625353381e-05, 'samples': 23940672, 'steps': 124690, 'loss/train': 1.2243586778640747} 08/31/2021 11:52:12 - INFO - __main__ - Step 124692: {'lr': 3.5218070419094195e-05, 'samples': 23940864, 'steps': 124691, 'loss/train': 1.0733309984207153} 08/31/2021 11:52:13 - INFO - __main__ - Step 124693: {'lr': 3.521535468143197e-05, 'samples': 23941056, 'steps': 124692, 'loss/train': 1.0848876237869263} 08/31/2021 11:52:14 - INFO - __main__ - Step 124694: {'lr': 3.5212639040548364e-05, 'samples': 23941248, 'steps': 124693, 'loss/train': 1.1003838777542114} 08/31/2021 11:52:14 - INFO - __main__ - Step 124695: {'lr': 3.520992349644464e-05, 'samples': 23941440, 'steps': 124694, 'loss/train': 1.1517276763916016} 08/31/2021 11:52:14 - INFO - __main__ - Step 124696: {'lr': 3.5207208049122e-05, 'samples': 23941632, 'steps': 124695, 'loss/train': 1.9268510341644287} 08/31/2021 11:52:15 - INFO - __main__ - Step 124697: {'lr': 3.52044926985817e-05, 'samples': 23941824, 'steps': 124696, 'loss/train': 1.2170050144195557} 08/31/2021 11:52:16 - INFO - __main__ - Step 124698: {'lr': 3.520177744482492e-05, 'samples': 23942016, 'steps': 124697, 'loss/train': 1.1536707878112793} 08/31/2021 11:52:17 - INFO - __main__ - Step 124699: {'lr': 3.5199062287852915e-05, 'samples': 23942208, 'steps': 124698, 'loss/train': 1.1306816339492798} 08/31/2021 11:52:17 - INFO - __main__ - Step 124700: {'lr': 3.51963472276669e-05, 'samples': 23942400, 'steps': 124699, 'loss/train': 1.8794441223144531} 08/31/2021 11:52:18 - INFO - __main__ - Step 124701: {'lr': 3.519363226426808e-05, 'samples': 23942592, 'steps': 124700, 'loss/train': 1.2085055112838745} 08/31/2021 11:52:18 - INFO - __main__ - Step 124702: {'lr': 3.519091739765773e-05, 'samples': 23942784, 'steps': 124701, 'loss/train': 0.5339787602424622} 08/31/2021 11:52:19 - INFO - __main__ - Step 124703: {'lr': 3.5188202627837004e-05, 'samples': 23942976, 'steps': 124702, 'loss/train': 0.8358917832374573} 08/31/2021 11:52:20 - INFO - __main__ - Step 124704: {'lr': 3.5185487954807165e-05, 'samples': 23943168, 'steps': 124703, 'loss/train': 1.1899948120117188} 08/31/2021 11:52:20 - INFO - __main__ - Step 124705: {'lr': 3.518277337856951e-05, 'samples': 23943360, 'steps': 124704, 'loss/train': 1.1135931015014648} 08/31/2021 11:52:21 - INFO - __main__ - Step 124706: {'lr': 3.51800588991251e-05, 'samples': 23943552, 'steps': 124705, 'loss/train': 1.1046372652053833} 08/31/2021 11:52:21 - INFO - __main__ - Step 124707: {'lr': 3.517734451647525e-05, 'samples': 23943744, 'steps': 124706, 'loss/train': 2.8332133293151855} 08/31/2021 11:52:23 - INFO - __main__ - Step 124708: {'lr': 3.5174630230621175e-05, 'samples': 23943936, 'steps': 124707, 'loss/train': 0.41806504130363464} 08/31/2021 11:52:23 - INFO - __main__ - Step 124709: {'lr': 3.517191604156408e-05, 'samples': 23944128, 'steps': 124708, 'loss/train': 0.9361997246742249} 08/31/2021 11:52:24 - INFO - __main__ - Step 124710: {'lr': 3.516920194930523e-05, 'samples': 23944320, 'steps': 124709, 'loss/train': 1.0491350889205933} 08/31/2021 11:52:24 - INFO - __main__ - Step 124711: {'lr': 3.516648795384581e-05, 'samples': 23944512, 'steps': 124710, 'loss/train': 1.2288932800292969} 08/31/2021 11:52:24 - INFO - __main__ - Step 124712: {'lr': 3.516377405518706e-05, 'samples': 23944704, 'steps': 124711, 'loss/train': 0.02710762992501259} 08/31/2021 11:52:25 - INFO - __main__ - Step 124713: {'lr': 3.516106025333018e-05, 'samples': 23944896, 'steps': 124712, 'loss/train': 0.100936658680439} 08/31/2021 11:52:25 - INFO - __main__ - Step 124714: {'lr': 3.5158346548276435e-05, 'samples': 23945088, 'steps': 124713, 'loss/train': 1.2048742771148682} 08/31/2021 11:52:27 - INFO - __main__ - Step 124715: {'lr': 3.515563294002702e-05, 'samples': 23945280, 'steps': 124714, 'loss/train': 1.3447668552398682} 08/31/2021 11:52:27 - INFO - __main__ - Step 124716: {'lr': 3.515291942858317e-05, 'samples': 23945472, 'steps': 124715, 'loss/train': 1.2179239988327026} 08/31/2021 11:52:27 - INFO - __main__ - Step 124717: {'lr': 3.515020601394608e-05, 'samples': 23945664, 'steps': 124716, 'loss/train': 1.3649163246154785} 08/31/2021 11:52:28 - INFO - __main__ - Step 124718: {'lr': 3.5147492696117e-05, 'samples': 23945856, 'steps': 124717, 'loss/train': 1.3077731132507324} 08/31/2021 11:52:28 - INFO - __main__ - Step 124719: {'lr': 3.51447794750972e-05, 'samples': 23946048, 'steps': 124718, 'loss/train': 1.1696738004684448} 08/31/2021 11:52:30 - INFO - __main__ - Step 124720: {'lr': 3.514206635088779e-05, 'samples': 23946240, 'steps': 124719, 'loss/train': 1.631491780281067} 08/31/2021 11:52:30 - INFO - __main__ - Step 124721: {'lr': 3.513935332349005e-05, 'samples': 23946432, 'steps': 124720, 'loss/train': 1.1176449060440063} 08/31/2021 11:52:30 - INFO - __main__ - Step 124722: {'lr': 3.5136640392905205e-05, 'samples': 23946624, 'steps': 124721, 'loss/train': 1.2352551221847534} 08/31/2021 11:52:31 - INFO - __main__ - Step 124723: {'lr': 3.513392755913447e-05, 'samples': 23946816, 'steps': 124722, 'loss/train': 0.6791065335273743} 08/31/2021 11:52:31 - INFO - __main__ - Step 124724: {'lr': 3.513121482217907e-05, 'samples': 23947008, 'steps': 124723, 'loss/train': 0.4006967842578888} 08/31/2021 11:52:33 - INFO - __main__ - Step 124725: {'lr': 3.512850218204022e-05, 'samples': 23947200, 'steps': 124724, 'loss/train': 0.02231200411915779} 08/31/2021 11:52:33 - INFO - __main__ - Step 124726: {'lr': 3.512578963871915e-05, 'samples': 23947392, 'steps': 124725, 'loss/train': 1.0885897874832153} 08/31/2021 11:52:33 - INFO - __main__ - Step 124727: {'lr': 3.5123077192217105e-05, 'samples': 23947584, 'steps': 124726, 'loss/train': 1.539458990097046} 08/31/2021 11:52:34 - INFO - __main__ - Step 124728: {'lr': 3.512036484253528e-05, 'samples': 23947776, 'steps': 124727, 'loss/train': 1.5029091835021973} 08/31/2021 11:52:34 - INFO - __main__ - Step 124729: {'lr': 3.5117652589674895e-05, 'samples': 23947968, 'steps': 124728, 'loss/train': 0.7226028442382812} 08/31/2021 11:52:36 - INFO - __main__ - Step 124730: {'lr': 3.51149404336372e-05, 'samples': 23948160, 'steps': 124729, 'loss/train': 0.9862650632858276} 08/31/2021 11:52:37 - INFO - __main__ - Step 124731: {'lr': 3.5112228374423375e-05, 'samples': 23948352, 'steps': 124730, 'loss/train': 0.417328417301178} 08/31/2021 11:52:37 - INFO - __main__ - Step 124732: {'lr': 3.510951641203472e-05, 'samples': 23948544, 'steps': 124731, 'loss/train': 1.736170768737793} 08/31/2021 11:52:38 - INFO - __main__ - Step 124733: {'lr': 3.510680454647236e-05, 'samples': 23948736, 'steps': 124732, 'loss/train': 1.3312617540359497} 08/31/2021 11:52:38 - INFO - __main__ - Step 124734: {'lr': 3.510409277773755e-05, 'samples': 23948928, 'steps': 124733, 'loss/train': 0.7155205607414246} 08/31/2021 11:52:39 - INFO - __main__ - Step 124735: {'lr': 3.51013811058315e-05, 'samples': 23949120, 'steps': 124734, 'loss/train': 0.5788806676864624} 08/31/2021 11:52:40 - INFO - __main__ - Step 124736: {'lr': 3.5098669530755465e-05, 'samples': 23949312, 'steps': 124735, 'loss/train': 1.6039549112319946} 08/31/2021 11:52:40 - INFO - __main__ - Step 124737: {'lr': 3.509595805251067e-05, 'samples': 23949504, 'steps': 124736, 'loss/train': 1.1996721029281616} 08/31/2021 11:52:40 - INFO - __main__ - Step 124738: {'lr': 3.509324667109831e-05, 'samples': 23949696, 'steps': 124737, 'loss/train': 1.4032617807388306} 08/31/2021 11:52:41 - INFO - __main__ - Step 124739: {'lr': 3.50905353865196e-05, 'samples': 23949888, 'steps': 124738, 'loss/train': 0.7427236437797546} 08/31/2021 11:52:42 - INFO - __main__ - Step 124740: {'lr': 3.508782419877579e-05, 'samples': 23950080, 'steps': 124739, 'loss/train': 0.9279326796531677} 08/31/2021 11:52:43 - INFO - __main__ - Step 124741: {'lr': 3.5085113107868104e-05, 'samples': 23950272, 'steps': 124740, 'loss/train': 1.3656604290008545} 08/31/2021 11:52:43 - INFO - __main__ - Step 124742: {'lr': 3.508240211379773e-05, 'samples': 23950464, 'steps': 124741, 'loss/train': 0.787690281867981} 08/31/2021 11:52:43 - INFO - __main__ - Step 124743: {'lr': 3.5079691216565926e-05, 'samples': 23950656, 'steps': 124742, 'loss/train': 1.6812957525253296} 08/31/2021 11:52:44 - INFO - __main__ - Step 124744: {'lr': 3.507698041617388e-05, 'samples': 23950848, 'steps': 124743, 'loss/train': 0.145257368683815} 08/31/2021 11:52:44 - INFO - __main__ - Step 124745: {'lr': 3.5074269712622845e-05, 'samples': 23951040, 'steps': 124744, 'loss/train': 2.021462917327881} 08/31/2021 11:52:46 - INFO - __main__ - Step 124746: {'lr': 3.507155910591408e-05, 'samples': 23951232, 'steps': 124745, 'loss/train': 1.1174067258834839} 08/31/2021 11:52:46 - INFO - __main__ - Step 124747: {'lr': 3.50688485960487e-05, 'samples': 23951424, 'steps': 124746, 'loss/train': 1.2132017612457275} 08/31/2021 11:52:47 - INFO - __main__ - Step 124748: {'lr': 3.506613818302798e-05, 'samples': 23951616, 'steps': 124747, 'loss/train': 0.5829401016235352} 08/31/2021 11:52:47 - INFO - __main__ - Step 124749: {'lr': 3.5063427866853126e-05, 'samples': 23951808, 'steps': 124748, 'loss/train': 0.7991907000541687} 08/31/2021 11:52:47 - INFO - __main__ - Step 124750: {'lr': 3.506071764752539e-05, 'samples': 23952000, 'steps': 124749, 'loss/train': 1.9515302181243896} 08/31/2021 11:52:49 - INFO - __main__ - Step 124751: {'lr': 3.5058007525045984e-05, 'samples': 23952192, 'steps': 124750, 'loss/train': 0.8441935777664185} 08/31/2021 11:52:50 - INFO - __main__ - Step 124752: {'lr': 3.50552974994161e-05, 'samples': 23952384, 'steps': 124751, 'loss/train': 1.3147366046905518} 08/31/2021 11:52:50 - INFO - __main__ - Step 124753: {'lr': 3.5052587570637004e-05, 'samples': 23952576, 'steps': 124752, 'loss/train': 1.0260217189788818} 08/31/2021 11:52:50 - INFO - __main__ - Step 124754: {'lr': 3.5049877738709876e-05, 'samples': 23952768, 'steps': 124753, 'loss/train': 1.984211802482605} 08/31/2021 11:52:51 - INFO - __main__ - Step 124755: {'lr': 3.504716800363597e-05, 'samples': 23952960, 'steps': 124754, 'loss/train': 0.8576049208641052} 08/31/2021 11:52:51 - INFO - __main__ - Step 124756: {'lr': 3.50444583654165e-05, 'samples': 23953152, 'steps': 124755, 'loss/train': 1.4597773551940918} 08/31/2021 11:52:53 - INFO - __main__ - Step 124757: {'lr': 3.504174882405267e-05, 'samples': 23953344, 'steps': 124756, 'loss/train': 0.07081561535596848} 08/31/2021 11:52:53 - INFO - __main__ - Step 124758: {'lr': 3.503903937954572e-05, 'samples': 23953536, 'steps': 124757, 'loss/train': 1.0328456163406372} 08/31/2021 11:52:54 - INFO - __main__ - Step 124759: {'lr': 3.503633003189691e-05, 'samples': 23953728, 'steps': 124758, 'loss/train': 1.1352159976959229} 08/31/2021 11:52:54 - INFO - __main__ - Step 124760: {'lr': 3.503362078110736e-05, 'samples': 23953920, 'steps': 124759, 'loss/train': 1.2766019105911255} 08/31/2021 11:52:54 - INFO - __main__ - Step 124761: {'lr': 3.5030911627178336e-05, 'samples': 23954112, 'steps': 124760, 'loss/train': 3.696537971496582} 08/31/2021 11:52:56 - INFO - __main__ - Step 124762: {'lr': 3.502820257011105e-05, 'samples': 23954304, 'steps': 124761, 'loss/train': 0.5728747248649597} 08/31/2021 11:52:56 - INFO - __main__ - Step 124763: {'lr': 3.502549360990676e-05, 'samples': 23954496, 'steps': 124762, 'loss/train': 1.1728103160858154} 08/31/2021 11:52:57 - INFO - __main__ - Step 124764: {'lr': 3.502278474656667e-05, 'samples': 23954688, 'steps': 124763, 'loss/train': 1.1543569564819336} 08/31/2021 11:52:57 - INFO - __main__ - Step 124765: {'lr': 3.502007598009199e-05, 'samples': 23954880, 'steps': 124764, 'loss/train': 0.9619186520576477} 08/31/2021 11:52:57 - INFO - __main__ - Step 124766: {'lr': 3.5017367310483936e-05, 'samples': 23955072, 'steps': 124765, 'loss/train': 1.079147458076477} 08/31/2021 11:52:59 - INFO - __main__ - Step 124767: {'lr': 3.501465873774376e-05, 'samples': 23955264, 'steps': 124766, 'loss/train': 0.3143637180328369} 08/31/2021 11:52:59 - INFO - __main__ - Step 124768: {'lr': 3.501195026187265e-05, 'samples': 23955456, 'steps': 124767, 'loss/train': 0.968285083770752} 08/31/2021 11:53:00 - INFO - __main__ - Step 124769: {'lr': 3.500924188287183e-05, 'samples': 23955648, 'steps': 124768, 'loss/train': 1.0062037706375122} 08/31/2021 11:53:00 - INFO - __main__ - Step 124770: {'lr': 3.500653360074255e-05, 'samples': 23955840, 'steps': 124769, 'loss/train': 1.042407512664795} 08/31/2021 11:53:00 - INFO - __main__ - Step 124771: {'lr': 3.5003825415486e-05, 'samples': 23956032, 'steps': 124770, 'loss/train': 0.21080295741558075} 08/31/2021 11:53:01 - INFO - __main__ - Step 124772: {'lr': 3.5001117327103456e-05, 'samples': 23956224, 'steps': 124771, 'loss/train': 1.040211796760559} 08/31/2021 11:53:02 - INFO - __main__ - Step 124773: {'lr': 3.499840933559603e-05, 'samples': 23956416, 'steps': 124772, 'loss/train': 0.9436934590339661} 08/31/2021 11:53:03 - INFO - __main__ - Step 124774: {'lr': 3.4995701440965004e-05, 'samples': 23956608, 'steps': 124773, 'loss/train': 0.06856261193752289} 08/31/2021 11:53:03 - INFO - __main__ - Step 124775: {'lr': 3.4992993643211595e-05, 'samples': 23956800, 'steps': 124774, 'loss/train': 1.1833254098892212} 08/31/2021 11:53:03 - INFO - __main__ - Step 124776: {'lr': 3.499028594233705e-05, 'samples': 23956992, 'steps': 124775, 'loss/train': 2.9252126216888428} 08/31/2021 11:53:04 - INFO - __main__ - Step 124777: {'lr': 3.4987578338342544e-05, 'samples': 23957184, 'steps': 124776, 'loss/train': 1.2135459184646606} 08/31/2021 11:53:06 - INFO - __main__ - Step 124778: {'lr': 3.498487083122931e-05, 'samples': 23957376, 'steps': 124777, 'loss/train': 1.605233907699585} 08/31/2021 11:53:06 - INFO - __main__ - Step 124779: {'lr': 3.498216342099861e-05, 'samples': 23957568, 'steps': 124778, 'loss/train': 0.17371593415737152} 08/31/2021 11:53:07 - INFO - __main__ - Step 124780: {'lr': 3.4979456107651605e-05, 'samples': 23957760, 'steps': 124779, 'loss/train': 0.47664275765419006} 08/31/2021 11:53:07 - INFO - __main__ - Step 124781: {'lr': 3.497674889118954e-05, 'samples': 23957952, 'steps': 124780, 'loss/train': 1.0058872699737549} 08/31/2021 11:53:07 - INFO - __main__ - Step 124782: {'lr': 3.497404177161362e-05, 'samples': 23958144, 'steps': 124781, 'loss/train': 0.937390923500061} 08/31/2021 11:53:09 - INFO - __main__ - Step 124783: {'lr': 3.497133474892508e-05, 'samples': 23958336, 'steps': 124782, 'loss/train': 1.5503723621368408} 08/31/2021 11:53:09 - INFO - __main__ - Step 124784: {'lr': 3.4968627823125154e-05, 'samples': 23958528, 'steps': 124783, 'loss/train': 1.4943304061889648} 08/31/2021 11:53:10 - INFO - __main__ - Step 124785: {'lr': 3.496592099421506e-05, 'samples': 23958720, 'steps': 124784, 'loss/train': 0.8541491627693176} 08/31/2021 11:53:10 - INFO - __main__ - Step 124786: {'lr': 3.4963214262196036e-05, 'samples': 23958912, 'steps': 124785, 'loss/train': 1.1151723861694336} 08/31/2021 11:53:10 - INFO - __main__ - Step 124787: {'lr': 3.4960507627069236e-05, 'samples': 23959104, 'steps': 124786, 'loss/train': 1.1685702800750732} 08/31/2021 11:53:11 - INFO - __main__ - Step 124788: {'lr': 3.4957801088835896e-05, 'samples': 23959296, 'steps': 124787, 'loss/train': 1.2737855911254883} 08/31/2021 11:53:12 - INFO - __main__ - Step 124789: {'lr': 3.4955094647497244e-05, 'samples': 23959488, 'steps': 124788, 'loss/train': 1.100419282913208} 08/31/2021 11:53:13 - INFO - __main__ - Step 124790: {'lr': 3.4952388303054526e-05, 'samples': 23959680, 'steps': 124789, 'loss/train': 0.6651213765144348} 08/31/2021 11:53:13 - INFO - __main__ - Step 124791: {'lr': 3.494968205550894e-05, 'samples': 23959872, 'steps': 124790, 'loss/train': 1.2183771133422852} 08/31/2021 11:53:14 - INFO - __main__ - Step 124792: {'lr': 3.4946975904861704e-05, 'samples': 23960064, 'steps': 124791, 'loss/train': 1.596405267715454} 08/31/2021 11:53:14 - INFO - __main__ - Step 124793: {'lr': 3.494426985111404e-05, 'samples': 23960256, 'steps': 124792, 'loss/train': 0.8232138752937317} 08/31/2021 11:53:15 - INFO - __main__ - Step 124794: {'lr': 3.494156389426717e-05, 'samples': 23960448, 'steps': 124793, 'loss/train': 0.5094719529151917} 08/31/2021 11:53:16 - INFO - __main__ - Step 124795: {'lr': 3.4938858034322314e-05, 'samples': 23960640, 'steps': 124794, 'loss/train': 1.128405213356018} 08/31/2021 11:53:16 - INFO - __main__ - Step 124796: {'lr': 3.4936152271280694e-05, 'samples': 23960832, 'steps': 124795, 'loss/train': 1.0257718563079834} 08/31/2021 11:53:17 - INFO - __main__ - Step 124797: {'lr': 3.4933446605143525e-05, 'samples': 23961024, 'steps': 124796, 'loss/train': 1.1012293100357056} 08/31/2021 11:53:17 - INFO - __main__ - Step 124798: {'lr': 3.4930741035912015e-05, 'samples': 23961216, 'steps': 124797, 'loss/train': 1.2199831008911133} 08/31/2021 11:53:19 - INFO - __main__ - Step 124799: {'lr': 3.492803556358745e-05, 'samples': 23961408, 'steps': 124798, 'loss/train': 0.8492810130119324} 08/31/2021 11:53:19 - INFO - __main__ - Step 124800: {'lr': 3.4925330188170956e-05, 'samples': 23961600, 'steps': 124799, 'loss/train': 0.8224388360977173} 08/31/2021 11:53:19 - INFO - __main__ - Step 124801: {'lr': 3.492262490966377e-05, 'samples': 23961792, 'steps': 124800, 'loss/train': 1.503825068473816} 08/31/2021 11:53:20 - INFO - __main__ - Step 124802: {'lr': 3.491991972806716e-05, 'samples': 23961984, 'steps': 124801, 'loss/train': 1.3329744338989258} 08/31/2021 11:53:20 - INFO - __main__ - Step 124803: {'lr': 3.4917214643382296e-05, 'samples': 23962176, 'steps': 124802, 'loss/train': 1.498108983039856} 08/31/2021 11:53:22 - INFO - __main__ - Step 124804: {'lr': 3.491450965561041e-05, 'samples': 23962368, 'steps': 124803, 'loss/train': 0.6956659555435181} 08/31/2021 11:53:22 - INFO - __main__ - Step 124805: {'lr': 3.491180476475273e-05, 'samples': 23962560, 'steps': 124804, 'loss/train': 0.9714893102645874} 08/31/2021 11:53:23 - INFO - __main__ - Step 124806: {'lr': 3.490909997081046e-05, 'samples': 23962752, 'steps': 124805, 'loss/train': 1.5730828046798706} 08/31/2021 11:53:23 - INFO - __main__ - Step 124807: {'lr': 3.490639527378486e-05, 'samples': 23962944, 'steps': 124806, 'loss/train': 1.7543214559555054} 08/31/2021 11:53:23 - INFO - __main__ - Step 124808: {'lr': 3.49036906736771e-05, 'samples': 23963136, 'steps': 124807, 'loss/train': 0.03794790804386139} 08/31/2021 11:53:24 - INFO - __main__ - Step 124809: {'lr': 3.4900986170488425e-05, 'samples': 23963328, 'steps': 124808, 'loss/train': 1.2776014804840088} 08/31/2021 11:53:25 - INFO - __main__ - Step 124810: {'lr': 3.489828176422005e-05, 'samples': 23963520, 'steps': 124809, 'loss/train': 1.1883149147033691} 08/31/2021 11:53:26 - INFO - __main__ - Step 124811: {'lr': 3.489557745487318e-05, 'samples': 23963712, 'steps': 124810, 'loss/train': 1.1493254899978638} 08/31/2021 11:53:26 - INFO - __main__ - Step 124812: {'lr': 3.489287324244905e-05, 'samples': 23963904, 'steps': 124811, 'loss/train': 1.0014444589614868} 08/31/2021 11:53:26 - INFO - __main__ - Step 124813: {'lr': 3.489016912694892e-05, 'samples': 23964096, 'steps': 124812, 'loss/train': 0.9289983510971069} 08/31/2021 11:53:27 - INFO - __main__ - Step 124814: {'lr': 3.48874651083739e-05, 'samples': 23964288, 'steps': 124813, 'loss/train': 0.418668270111084} 08/31/2021 11:53:29 - INFO - __main__ - Step 124815: {'lr': 3.488476118672529e-05, 'samples': 23964480, 'steps': 124814, 'loss/train': 1.2042109966278076} 08/31/2021 11:53:30 - INFO - __main__ - Step 124816: {'lr': 3.488205736200428e-05, 'samples': 23964672, 'steps': 124815, 'loss/train': 1.0674511194229126} 08/31/2021 11:53:30 - INFO - __main__ - Step 124817: {'lr': 3.487935363421207e-05, 'samples': 23964864, 'steps': 124816, 'loss/train': 0.7996042966842651} 08/31/2021 11:53:30 - INFO - __main__ - Step 124818: {'lr': 3.487665000334994e-05, 'samples': 23965056, 'steps': 124817, 'loss/train': 0.04325217381119728} 08/31/2021 11:53:31 - INFO - __main__ - Step 124819: {'lr': 3.487394646941905e-05, 'samples': 23965248, 'steps': 124818, 'loss/train': 0.6010306477546692} 08/31/2021 11:53:31 - INFO - __main__ - Step 124820: {'lr': 3.4871243032420644e-05, 'samples': 23965440, 'steps': 124819, 'loss/train': 0.8419837951660156} 08/31/2021 11:53:31 - INFO - __main__ - Step 124821: {'lr': 3.4868539692355956e-05, 'samples': 23965632, 'steps': 124820, 'loss/train': 0.06013511121273041} 08/31/2021 11:53:33 - INFO - __main__ - Step 124822: {'lr': 3.4865836449226166e-05, 'samples': 23965824, 'steps': 124821, 'loss/train': 0.9404501914978027} 08/31/2021 11:53:33 - INFO - __main__ - Step 124823: {'lr': 3.486313330303251e-05, 'samples': 23966016, 'steps': 124822, 'loss/train': 1.384325385093689} 08/31/2021 11:53:34 - INFO - __main__ - Step 124824: {'lr': 3.486043025377619e-05, 'samples': 23966208, 'steps': 124823, 'loss/train': 1.3962260484695435} 08/31/2021 11:53:34 - INFO - __main__ - Step 124825: {'lr': 3.4857727301458474e-05, 'samples': 23966400, 'steps': 124824, 'loss/train': 1.6439342498779297} 08/31/2021 11:53:34 - INFO - __main__ - Step 124826: {'lr': 3.4855024446080574e-05, 'samples': 23966592, 'steps': 124825, 'loss/train': 1.3625673055648804} 08/31/2021 11:53:36 - INFO - __main__ - Step 124827: {'lr': 3.485232168764363e-05, 'samples': 23966784, 'steps': 124826, 'loss/train': 1.3882904052734375} 08/31/2021 11:53:36 - INFO - __main__ - Step 124828: {'lr': 3.4849619026148915e-05, 'samples': 23966976, 'steps': 124827, 'loss/train': 1.5097357034683228} 08/31/2021 11:53:37 - INFO - __main__ - Step 124829: {'lr': 3.4846916461597656e-05, 'samples': 23967168, 'steps': 124828, 'loss/train': 0.9441156387329102} 08/31/2021 11:53:37 - INFO - __main__ - Step 124830: {'lr': 3.484421399399104e-05, 'samples': 23967360, 'steps': 124829, 'loss/train': 1.150316596031189} 08/31/2021 11:53:37 - INFO - __main__ - Step 124831: {'lr': 3.48415116233303e-05, 'samples': 23967552, 'steps': 124830, 'loss/train': 1.2582645416259766} 08/31/2021 11:53:40 - INFO - __main__ - Step 124832: {'lr': 3.483880934961667e-05, 'samples': 23967744, 'steps': 124831, 'loss/train': 1.302019715309143} 08/31/2021 11:53:40 - INFO - __main__ - Step 124833: {'lr': 3.483610717285135e-05, 'samples': 23967936, 'steps': 124832, 'loss/train': 1.5151699781417847} 08/31/2021 11:53:40 - INFO - __main__ - Step 124834: {'lr': 3.4833405093035535e-05, 'samples': 23968128, 'steps': 124833, 'loss/train': 1.1632813215255737} 08/31/2021 11:53:41 - INFO - __main__ - Step 124835: {'lr': 3.4830703110170506e-05, 'samples': 23968320, 'steps': 124834, 'loss/train': 0.731838583946228} 08/31/2021 11:53:41 - INFO - __main__ - Step 124836: {'lr': 3.4828001224257416e-05, 'samples': 23968512, 'steps': 124835, 'loss/train': 0.7079788446426392} 08/31/2021 11:53:43 - INFO - __main__ - Step 124837: {'lr': 3.48252994352975e-05, 'samples': 23968704, 'steps': 124836, 'loss/train': 0.09312083572149277} 08/31/2021 11:53:43 - INFO - __main__ - Step 124838: {'lr': 3.4822597743292e-05, 'samples': 23968896, 'steps': 124837, 'loss/train': 0.6565107703208923} 08/31/2021 11:53:43 - INFO - __main__ - Step 124839: {'lr': 3.48198961482421e-05, 'samples': 23969088, 'steps': 124838, 'loss/train': 0.9219643473625183} 08/31/2021 11:53:44 - INFO - __main__ - Step 124840: {'lr': 3.4817194650149124e-05, 'samples': 23969280, 'steps': 124839, 'loss/train': 2.3312020301818848} 08/31/2021 11:53:44 - INFO - __main__ - Step 124841: {'lr': 3.481449324901412e-05, 'samples': 23969472, 'steps': 124840, 'loss/train': 1.0539302825927734} 08/31/2021 11:53:45 - INFO - __main__ - Step 124842: {'lr': 3.4811791944838384e-05, 'samples': 23969664, 'steps': 124841, 'loss/train': 0.7602850794792175} 08/31/2021 11:53:46 - INFO - __main__ - Step 124843: {'lr': 3.480909073762314e-05, 'samples': 23969856, 'steps': 124842, 'loss/train': 1.8142049312591553} 08/31/2021 11:53:46 - INFO - __main__ - Step 124844: {'lr': 3.480638962736959e-05, 'samples': 23970048, 'steps': 124843, 'loss/train': 1.3362630605697632} 08/31/2021 11:53:47 - INFO - __main__ - Step 124845: {'lr': 3.480368861407898e-05, 'samples': 23970240, 'steps': 124844, 'loss/train': 0.8859045505523682} 08/31/2021 11:53:47 - INFO - __main__ - Step 124846: {'lr': 3.48009876977525e-05, 'samples': 23970432, 'steps': 124845, 'loss/train': 1.3332818746566772} 08/31/2021 11:53:49 - INFO - __main__ - Step 124847: {'lr': 3.4798286878391344e-05, 'samples': 23970624, 'steps': 124846, 'loss/train': 0.737868070602417} 08/31/2021 11:53:49 - INFO - __main__ - Step 124848: {'lr': 3.479558615599679e-05, 'samples': 23970816, 'steps': 124847, 'loss/train': 2.7356181144714355} 08/31/2021 11:53:49 - INFO - __main__ - Step 124849: {'lr': 3.479288553057003e-05, 'samples': 23971008, 'steps': 124848, 'loss/train': 0.15810415148735046} 08/31/2021 11:53:50 - INFO - __main__ - Step 124850: {'lr': 3.479018500211226e-05, 'samples': 23971200, 'steps': 124849, 'loss/train': 1.114967703819275} 08/31/2021 11:53:50 - INFO - __main__ - Step 124851: {'lr': 3.478748457062472e-05, 'samples': 23971392, 'steps': 124850, 'loss/train': 1.0720009803771973} 08/31/2021 11:53:52 - INFO - __main__ - Step 124852: {'lr': 3.478478423610862e-05, 'samples': 23971584, 'steps': 124851, 'loss/train': 0.3720371425151825} 08/31/2021 11:53:52 - INFO - __main__ - Step 124853: {'lr': 3.4782083998565224e-05, 'samples': 23971776, 'steps': 124852, 'loss/train': 0.7277889847755432} 08/31/2021 11:53:53 - INFO - __main__ - Step 124854: {'lr': 3.477938385799564e-05, 'samples': 23971968, 'steps': 124853, 'loss/train': 1.1163009405136108} 08/31/2021 11:53:53 - INFO - __main__ - Step 124855: {'lr': 3.4776683814401134e-05, 'samples': 23972160, 'steps': 124854, 'loss/train': 0.8858069181442261} 08/31/2021 11:53:53 - INFO - __main__ - Step 124856: {'lr': 3.477398386778297e-05, 'samples': 23972352, 'steps': 124855, 'loss/train': 1.430010437965393} 08/31/2021 11:53:54 - INFO - __main__ - Step 124857: {'lr': 3.477128401814228e-05, 'samples': 23972544, 'steps': 124856, 'loss/train': 1.4058387279510498} 08/31/2021 11:53:55 - INFO - __main__ - Step 124858: {'lr': 3.4768584265480354e-05, 'samples': 23972736, 'steps': 124857, 'loss/train': 0.023483162745833397} 08/31/2021 11:53:56 - INFO - __main__ - Step 124859: {'lr': 3.476588460979841e-05, 'samples': 23972928, 'steps': 124858, 'loss/train': 0.6977472901344299} 08/31/2021 11:53:56 - INFO - __main__ - Step 124860: {'lr': 3.47631850510976e-05, 'samples': 23973120, 'steps': 124859, 'loss/train': 1.3524339199066162} 08/31/2021 11:53:56 - INFO - __main__ - Step 124861: {'lr': 3.476048558937919e-05, 'samples': 23973312, 'steps': 124860, 'loss/train': 1.2849072217941284} 08/31/2021 11:53:57 - INFO - __main__ - Step 124862: {'lr': 3.475778622464437e-05, 'samples': 23973504, 'steps': 124861, 'loss/train': 0.8668238520622253} 08/31/2021 11:53:58 - INFO - __main__ - Step 124863: {'lr': 3.475508695689439e-05, 'samples': 23973696, 'steps': 124862, 'loss/train': 0.5800937414169312} 08/31/2021 11:53:59 - INFO - __main__ - Step 124864: {'lr': 3.475238778613043e-05, 'samples': 23973888, 'steps': 124863, 'loss/train': 1.3314658403396606} 08/31/2021 11:53:59 - INFO - __main__ - Step 124865: {'lr': 3.474968871235373e-05, 'samples': 23974080, 'steps': 124864, 'loss/train': 0.1142011359333992} 08/31/2021 11:53:59 - INFO - __main__ - Step 124866: {'lr': 3.4746989735565506e-05, 'samples': 23974272, 'steps': 124865, 'loss/train': 1.313183307647705} 08/31/2021 11:54:00 - INFO - __main__ - Step 124867: {'lr': 3.474429085576703e-05, 'samples': 23974464, 'steps': 124866, 'loss/train': 1.3655411005020142} 08/31/2021 11:54:01 - INFO - __main__ - Step 124868: {'lr': 3.474159207295938e-05, 'samples': 23974656, 'steps': 124867, 'loss/train': 0.8977184295654297} 08/31/2021 11:54:02 - INFO - __main__ - Step 124869: {'lr': 3.4738893387143837e-05, 'samples': 23974848, 'steps': 124868, 'loss/train': 1.0234779119491577} 08/31/2021 11:54:02 - INFO - __main__ - Step 124870: {'lr': 3.473619479832166e-05, 'samples': 23975040, 'steps': 124869, 'loss/train': 1.003521203994751} 08/31/2021 11:54:03 - INFO - __main__ - Step 124871: {'lr': 3.4733496306494e-05, 'samples': 23975232, 'steps': 124870, 'loss/train': 0.9254353642463684} 08/31/2021 11:54:03 - INFO - __main__ - Step 124872: {'lr': 3.473079791166212e-05, 'samples': 23975424, 'steps': 124871, 'loss/train': 0.7764187455177307} 08/31/2021 11:54:05 - INFO - __main__ - Step 124873: {'lr': 3.472809961382723e-05, 'samples': 23975616, 'steps': 124872, 'loss/train': 1.1939586400985718} 08/31/2021 11:54:05 - INFO - __main__ - Step 124874: {'lr': 3.472540141299052e-05, 'samples': 23975808, 'steps': 124873, 'loss/train': 0.684467613697052} 08/31/2021 11:54:05 - INFO - __main__ - Step 124875: {'lr': 3.472270330915322e-05, 'samples': 23976000, 'steps': 124874, 'loss/train': 1.0983744859695435} 08/31/2021 11:54:06 - INFO - __main__ - Step 124876: {'lr': 3.472000530231656e-05, 'samples': 23976192, 'steps': 124875, 'loss/train': 1.1612439155578613} 08/31/2021 11:54:06 - INFO - __main__ - Step 124877: {'lr': 3.471730739248174e-05, 'samples': 23976384, 'steps': 124876, 'loss/train': 0.13245177268981934} 08/31/2021 11:54:06 - INFO - __main__ - Step 124878: {'lr': 3.4714609579649975e-05, 'samples': 23976576, 'steps': 124877, 'loss/train': 1.0936492681503296} 08/31/2021 11:54:08 - INFO - __main__ - Step 124879: {'lr': 3.47119118638225e-05, 'samples': 23976768, 'steps': 124878, 'loss/train': 1.3036316633224487} 08/31/2021 11:54:08 - INFO - __main__ - Step 124880: {'lr': 3.470921424500056e-05, 'samples': 23976960, 'steps': 124879, 'loss/train': 0.9735611081123352} 08/31/2021 11:54:09 - INFO - __main__ - Step 124881: {'lr': 3.470651672318525e-05, 'samples': 23977152, 'steps': 124880, 'loss/train': 0.8181139826774597} 08/31/2021 11:54:09 - INFO - __main__ - Step 124882: {'lr': 3.47038192983779e-05, 'samples': 23977344, 'steps': 124881, 'loss/train': 1.397527813911438} 08/31/2021 11:54:10 - INFO - __main__ - Step 124883: {'lr': 3.470112197057967e-05, 'samples': 23977536, 'steps': 124882, 'loss/train': 0.5900388360023499} 08/31/2021 11:54:11 - INFO - __main__ - Step 124884: {'lr': 3.469842473979179e-05, 'samples': 23977728, 'steps': 124883, 'loss/train': 0.863440215587616} 08/31/2021 11:54:11 - INFO - __main__ - Step 124885: {'lr': 3.469572760601547e-05, 'samples': 23977920, 'steps': 124884, 'loss/train': 3.267584800720215} 08/31/2021 11:54:12 - INFO - __main__ - Step 124886: {'lr': 3.469303056925194e-05, 'samples': 23978112, 'steps': 124885, 'loss/train': 0.4492180347442627} 08/31/2021 11:54:12 - INFO - __main__ - Step 124887: {'lr': 3.469033362950241e-05, 'samples': 23978304, 'steps': 124886, 'loss/train': 0.5297287702560425} 08/31/2021 11:54:12 - INFO - __main__ - Step 124888: {'lr': 3.468763678676809e-05, 'samples': 23978496, 'steps': 124887, 'loss/train': 0.32724618911743164} 08/31/2021 11:54:15 - INFO - __main__ - Step 124889: {'lr': 3.468494004105019e-05, 'samples': 23978688, 'steps': 124888, 'loss/train': 1.0356898307800293} 08/31/2021 11:54:15 - INFO - __main__ - Step 124890: {'lr': 3.468224339234996e-05, 'samples': 23978880, 'steps': 124889, 'loss/train': 0.9795330166816711} 08/31/2021 11:54:16 - INFO - __main__ - Step 124891: {'lr': 3.467954684066857e-05, 'samples': 23979072, 'steps': 124890, 'loss/train': 0.10469743609428406} 08/31/2021 11:54:16 - INFO - __main__ - Step 124892: {'lr': 3.467685038600726e-05, 'samples': 23979264, 'steps': 124891, 'loss/train': 1.1902697086334229} 08/31/2021 11:54:16 - INFO - __main__ - Step 124893: {'lr': 3.467415402836729e-05, 'samples': 23979456, 'steps': 124892, 'loss/train': 1.0852311849594116} 08/31/2021 11:54:18 - INFO - __main__ - Step 124894: {'lr': 3.467145776774977e-05, 'samples': 23979648, 'steps': 124893, 'loss/train': 0.7441999912261963} 08/31/2021 11:54:18 - INFO - __main__ - Step 124895: {'lr': 3.466876160415597e-05, 'samples': 23979840, 'steps': 124894, 'loss/train': 0.39089348912239075} 08/31/2021 11:54:19 - INFO - __main__ - Step 124896: {'lr': 3.466606553758708e-05, 'samples': 23980032, 'steps': 124895, 'loss/train': 1.1401220560073853} 08/31/2021 11:54:19 - INFO - __main__ - Step 124897: {'lr': 3.466336956804436e-05, 'samples': 23980224, 'steps': 124896, 'loss/train': 1.0794744491577148} 08/31/2021 11:54:19 - INFO - __main__ - Step 124898: {'lr': 3.4660673695529e-05, 'samples': 23980416, 'steps': 124897, 'loss/train': 1.233014464378357} 08/31/2021 11:54:20 - INFO - __main__ - Step 124899: {'lr': 3.4657977920042217e-05, 'samples': 23980608, 'steps': 124898, 'loss/train': 0.7318827509880066} 08/31/2021 11:54:21 - INFO - __main__ - Step 124900: {'lr': 3.465528224158523e-05, 'samples': 23980800, 'steps': 124899, 'loss/train': 1.024817943572998} 08/31/2021 11:54:22 - INFO - __main__ - Step 124901: {'lr': 3.465258666015925e-05, 'samples': 23980992, 'steps': 124900, 'loss/train': 0.5956644415855408} 08/31/2021 11:54:22 - INFO - __main__ - Step 124902: {'lr': 3.46498911757655e-05, 'samples': 23981184, 'steps': 124901, 'loss/train': 0.8681516647338867} 08/31/2021 11:54:23 - INFO - __main__ - Step 124903: {'lr': 3.4647195788405164e-05, 'samples': 23981376, 'steps': 124902, 'loss/train': 0.6105071902275085} 08/31/2021 11:54:23 - INFO - __main__ - Step 124904: {'lr': 3.4644500498079486e-05, 'samples': 23981568, 'steps': 124903, 'loss/train': 0.8766552209854126} 08/31/2021 11:54:24 - INFO - __main__ - Step 124905: {'lr': 3.464180530478969e-05, 'samples': 23981760, 'steps': 124904, 'loss/train': 1.3502625226974487} 08/31/2021 11:54:25 - INFO - __main__ - Step 124906: {'lr': 3.4639110208537024e-05, 'samples': 23981952, 'steps': 124905, 'loss/train': 1.1344341039657593} 08/31/2021 11:54:25 - INFO - __main__ - Step 124907: {'lr': 3.4636415209322563e-05, 'samples': 23982144, 'steps': 124906, 'loss/train': 0.511058509349823} 08/31/2021 11:54:26 - INFO - __main__ - Step 124908: {'lr': 3.4633720307147647e-05, 'samples': 23982336, 'steps': 124907, 'loss/train': 1.451329231262207} 08/31/2021 11:54:26 - INFO - __main__ - Step 124909: {'lr': 3.463102550201344e-05, 'samples': 23982528, 'steps': 124908, 'loss/train': 1.0473148822784424} 08/31/2021 11:54:27 - INFO - __main__ - Step 124910: {'lr': 3.4628330793921166e-05, 'samples': 23982720, 'steps': 124909, 'loss/train': 0.6399704813957214} 08/31/2021 11:54:28 - INFO - __main__ - Step 124911: {'lr': 3.4625636182872036e-05, 'samples': 23982912, 'steps': 124910, 'loss/train': 1.3696789741516113} 08/31/2021 11:54:28 - INFO - __main__ - Step 124912: {'lr': 3.462294166886729e-05, 'samples': 23983104, 'steps': 124911, 'loss/train': 0.6891362071037292} 08/31/2021 11:54:28 - INFO - __main__ - Step 124913: {'lr': 3.462024725190813e-05, 'samples': 23983296, 'steps': 124912, 'loss/train': 1.0723159313201904} 08/31/2021 11:54:29 - INFO - __main__ - Step 124914: {'lr': 3.4617552931995726e-05, 'samples': 23983488, 'steps': 124913, 'loss/train': 1.6493890285491943} 08/31/2021 11:54:30 - INFO - __main__ - Step 124915: {'lr': 3.461485870913137e-05, 'samples': 23983680, 'steps': 124914, 'loss/train': 0.7910729646682739} 08/31/2021 11:54:31 - INFO - __main__ - Step 124916: {'lr': 3.46121645833162e-05, 'samples': 23983872, 'steps': 124915, 'loss/train': 1.7811908721923828} 08/31/2021 11:54:31 - INFO - __main__ - Step 124917: {'lr': 3.460947055455155e-05, 'samples': 23984064, 'steps': 124916, 'loss/train': 1.460874319076538} 08/31/2021 11:54:32 - INFO - __main__ - Step 124918: {'lr': 3.460677662283848e-05, 'samples': 23984256, 'steps': 124917, 'loss/train': 0.953060507774353} 08/31/2021 11:54:32 - INFO - __main__ - Step 124919: {'lr': 3.460408278817828e-05, 'samples': 23984448, 'steps': 124918, 'loss/train': 1.9810898303985596} 08/31/2021 11:54:32 - INFO - __main__ - Step 124920: {'lr': 3.460138905057214e-05, 'samples': 23984640, 'steps': 124919, 'loss/train': 0.16577893495559692} 08/31/2021 11:54:34 - INFO - __main__ - Step 124921: {'lr': 3.4598695410021305e-05, 'samples': 23984832, 'steps': 124920, 'loss/train': 1.243844985961914} 08/31/2021 11:54:35 - INFO - __main__ - Step 124922: {'lr': 3.459600186652698e-05, 'samples': 23985024, 'steps': 124921, 'loss/train': 0.793388843536377} 08/31/2021 11:54:35 - INFO - __main__ - Step 124923: {'lr': 3.459330842009034e-05, 'samples': 23985216, 'steps': 124922, 'loss/train': 1.2502415180206299} 08/31/2021 11:54:35 - INFO - __main__ - Step 124924: {'lr': 3.459061507071265e-05, 'samples': 23985408, 'steps': 124923, 'loss/train': 2.7136569023132324} 08/31/2021 11:54:36 - INFO - __main__ - Step 124925: {'lr': 3.458792181839512e-05, 'samples': 23985600, 'steps': 124924, 'loss/train': 1.4233832359313965} 08/31/2021 11:54:37 - INFO - __main__ - Step 124926: {'lr': 3.458522866313893e-05, 'samples': 23985792, 'steps': 124925, 'loss/train': 0.9299972653388977} 08/31/2021 11:54:38 - INFO - __main__ - Step 124927: {'lr': 3.458253560494531e-05, 'samples': 23985984, 'steps': 124926, 'loss/train': 0.7036234736442566} 08/31/2021 11:54:38 - INFO - __main__ - Step 124928: {'lr': 3.457984264381556e-05, 'samples': 23986176, 'steps': 124927, 'loss/train': 1.2351652383804321} 08/31/2021 11:54:38 - INFO - __main__ - Step 124929: {'lr': 3.457714977975071e-05, 'samples': 23986368, 'steps': 124928, 'loss/train': 0.822948157787323} 08/31/2021 11:54:39 - INFO - __main__ - Step 124930: {'lr': 3.457445701275211e-05, 'samples': 23986560, 'steps': 124929, 'loss/train': 0.6124112010002136} 08/31/2021 11:54:40 - INFO - __main__ - Step 124931: {'lr': 3.457176434282091e-05, 'samples': 23986752, 'steps': 124930, 'loss/train': 1.270656704902649} 08/31/2021 11:54:41 - INFO - __main__ - Step 124932: {'lr': 3.456907176995835e-05, 'samples': 23986944, 'steps': 124931, 'loss/train': 1.8114047050476074} 08/31/2021 11:54:41 - INFO - __main__ - Step 124933: {'lr': 3.456637929416567e-05, 'samples': 23987136, 'steps': 124932, 'loss/train': 1.7562611103057861} 08/31/2021 11:54:41 - INFO - __main__ - Step 124934: {'lr': 3.4563686915444035e-05, 'samples': 23987328, 'steps': 124933, 'loss/train': 1.309615135192871} 08/31/2021 11:54:42 - INFO - __main__ - Step 124935: {'lr': 3.4560994633794666e-05, 'samples': 23987520, 'steps': 124934, 'loss/train': 1.0512690544128418} 08/31/2021 11:54:43 - INFO - __main__ - Step 124936: {'lr': 3.455830244921882e-05, 'samples': 23987712, 'steps': 124935, 'loss/train': 0.787127673625946} 08/31/2021 11:54:44 - INFO - __main__ - Step 124937: {'lr': 3.455561036171764e-05, 'samples': 23987904, 'steps': 124936, 'loss/train': 0.18927356600761414} 08/31/2021 11:54:44 - INFO - __main__ - Step 124938: {'lr': 3.45529183712924e-05, 'samples': 23988096, 'steps': 124937, 'loss/train': 0.9668494462966919} 08/31/2021 11:54:44 - INFO - __main__ - Step 124939: {'lr': 3.455022647794434e-05, 'samples': 23988288, 'steps': 124938, 'loss/train': 0.44491833448410034} 08/31/2021 11:54:45 - INFO - __main__ - Step 124940: {'lr': 3.454753468167457e-05, 'samples': 23988480, 'steps': 124939, 'loss/train': 1.1952401399612427} 08/31/2021 11:54:45 - INFO - __main__ - Step 124941: {'lr': 3.454484298248437e-05, 'samples': 23988672, 'steps': 124940, 'loss/train': 2.1020946502685547} 08/31/2021 11:54:47 - INFO - __main__ - Step 124942: {'lr': 3.454215138037492e-05, 'samples': 23988864, 'steps': 124941, 'loss/train': 1.7824772596359253} 08/31/2021 11:54:48 - INFO - __main__ - Step 124943: {'lr': 3.4539459875347454e-05, 'samples': 23989056, 'steps': 124942, 'loss/train': 1.25163733959198} 08/31/2021 11:54:48 - INFO - __main__ - Step 124944: {'lr': 3.45367684674032e-05, 'samples': 23989248, 'steps': 124943, 'loss/train': 1.5114277601242065} 08/31/2021 11:54:48 - INFO - __main__ - Step 124945: {'lr': 3.453407715654333e-05, 'samples': 23989440, 'steps': 124944, 'loss/train': 0.9423168897628784} 08/31/2021 11:54:49 - INFO - __main__ - Step 124946: {'lr': 3.453138594276908e-05, 'samples': 23989632, 'steps': 124945, 'loss/train': 0.6539402604103088} 08/31/2021 11:54:50 - INFO - __main__ - Step 124947: {'lr': 3.452869482608167e-05, 'samples': 23989824, 'steps': 124946, 'loss/train': 0.36866551637649536} 08/31/2021 11:54:51 - INFO - __main__ - Step 124948: {'lr': 3.4526003806482325e-05, 'samples': 23990016, 'steps': 124947, 'loss/train': 0.2821490168571472} 08/31/2021 11:54:51 - INFO - __main__ - Step 124949: {'lr': 3.452331288397223e-05, 'samples': 23990208, 'steps': 124948, 'loss/train': 1.364137887954712} 08/31/2021 11:54:51 - INFO - __main__ - Step 124950: {'lr': 3.452062205855264e-05, 'samples': 23990400, 'steps': 124949, 'loss/train': 0.8367284536361694} 08/31/2021 11:54:52 - INFO - __main__ - Step 124951: {'lr': 3.451793133022468e-05, 'samples': 23990592, 'steps': 124950, 'loss/train': 1.166345238685608} 08/31/2021 11:54:53 - INFO - __main__ - Step 124952: {'lr': 3.451524069898962e-05, 'samples': 23990784, 'steps': 124951, 'loss/train': 0.9497334361076355} 08/31/2021 11:54:54 - INFO - __main__ - Step 124953: {'lr': 3.4512550164848694e-05, 'samples': 23990976, 'steps': 124952, 'loss/train': 1.5973105430603027} 08/31/2021 11:54:54 - INFO - __main__ - Step 124954: {'lr': 3.4509859727803046e-05, 'samples': 23991168, 'steps': 124953, 'loss/train': 0.4925365746021271} 08/31/2021 11:54:54 - INFO - __main__ - Step 124955: {'lr': 3.450716938785395e-05, 'samples': 23991360, 'steps': 124954, 'loss/train': 0.6589426398277283} 08/31/2021 11:54:55 - INFO - __main__ - Step 124956: {'lr': 3.45044791450026e-05, 'samples': 23991552, 'steps': 124955, 'loss/train': 0.7707887887954712} 08/31/2021 11:54:57 - INFO - __main__ - Step 124957: {'lr': 3.450178899925022e-05, 'samples': 23991744, 'steps': 124956, 'loss/train': 2.3915109634399414} 08/31/2021 11:54:57 - INFO - __main__ - Step 124958: {'lr': 3.449909895059797e-05, 'samples': 23991936, 'steps': 124957, 'loss/train': 0.7400389313697815} 08/31/2021 11:54:57 - INFO - __main__ - Step 124959: {'lr': 3.449640899904713e-05, 'samples': 23992128, 'steps': 124958, 'loss/train': 1.4241938591003418} 08/31/2021 11:54:58 - INFO - __main__ - Step 124960: {'lr': 3.449371914459887e-05, 'samples': 23992320, 'steps': 124959, 'loss/train': 1.335950255393982} 08/31/2021 11:54:58 - INFO - __main__ - Step 124961: {'lr': 3.449102938725448e-05, 'samples': 23992512, 'steps': 124960, 'loss/train': 2.0579910278320312} 08/31/2021 11:54:58 - INFO - __main__ - Step 124962: {'lr': 3.448833972701504e-05, 'samples': 23992704, 'steps': 124961, 'loss/train': 0.040643125772476196} 08/31/2021 11:55:00 - INFO - __main__ - Step 124963: {'lr': 3.448565016388183e-05, 'samples': 23992896, 'steps': 124962, 'loss/train': 1.0559372901916504} 08/31/2021 11:55:00 - INFO - __main__ - Step 124964: {'lr': 3.4482960697856085e-05, 'samples': 23993088, 'steps': 124963, 'loss/train': 1.1653368473052979} 08/31/2021 11:55:01 - INFO - __main__ - Step 124965: {'lr': 3.448027132893897e-05, 'samples': 23993280, 'steps': 124964, 'loss/train': 0.07147438079118729} 08/31/2021 11:55:01 - INFO - __main__ - Step 124966: {'lr': 3.447758205713172e-05, 'samples': 23993472, 'steps': 124965, 'loss/train': 1.1120933294296265} 08/31/2021 11:55:02 - INFO - __main__ - Step 124967: {'lr': 3.447489288243555e-05, 'samples': 23993664, 'steps': 124966, 'loss/train': 0.997168779373169} 08/31/2021 11:55:03 - INFO - __main__ - Step 124968: {'lr': 3.447220380485166e-05, 'samples': 23993856, 'steps': 124967, 'loss/train': 1.2723108530044556} 08/31/2021 11:55:04 - INFO - __main__ - Step 124969: {'lr': 3.4469514824381264e-05, 'samples': 23994048, 'steps': 124968, 'loss/train': 0.6947829127311707} 08/31/2021 11:55:04 - INFO - __main__ - Step 124970: {'lr': 3.44668259410256e-05, 'samples': 23994240, 'steps': 124969, 'loss/train': 1.4175208806991577} 08/31/2021 11:55:04 - INFO - __main__ - Step 124971: {'lr': 3.4464137154785854e-05, 'samples': 23994432, 'steps': 124970, 'loss/train': 1.6814712285995483} 08/31/2021 11:55:05 - INFO - __main__ - Step 124972: {'lr': 3.4461448465663234e-05, 'samples': 23994624, 'steps': 124971, 'loss/train': 0.5992630124092102} 08/31/2021 11:55:06 - INFO - __main__ - Step 124973: {'lr': 3.445875987365896e-05, 'samples': 23994816, 'steps': 124972, 'loss/train': 0.7422712445259094} 08/31/2021 11:55:07 - INFO - __main__ - Step 124974: {'lr': 3.4456071378774294e-05, 'samples': 23995008, 'steps': 124973, 'loss/train': 1.088708519935608} 08/31/2021 11:55:07 - INFO - __main__ - Step 124975: {'lr': 3.445338298101033e-05, 'samples': 23995200, 'steps': 124974, 'loss/train': 1.319762110710144} 08/31/2021 11:55:07 - INFO - __main__ - Step 124976: {'lr': 3.4450694680368375e-05, 'samples': 23995392, 'steps': 124975, 'loss/train': 0.6780489087104797} 08/31/2021 11:55:08 - INFO - __main__ - Step 124977: {'lr': 3.4448006476849594e-05, 'samples': 23995584, 'steps': 124976, 'loss/train': 0.03407023474574089} 08/31/2021 11:55:08 - INFO - __main__ - Step 124978: {'lr': 3.444531837045522e-05, 'samples': 23995776, 'steps': 124977, 'loss/train': 1.2780767679214478} 08/31/2021 11:55:10 - INFO - __main__ - Step 124979: {'lr': 3.444263036118647e-05, 'samples': 23995968, 'steps': 124978, 'loss/train': 1.0283900499343872} 08/31/2021 11:55:11 - INFO - __main__ - Step 124980: {'lr': 3.4439942449044526e-05, 'samples': 23996160, 'steps': 124979, 'loss/train': 0.9427503943443298} 08/31/2021 11:55:11 - INFO - __main__ - Step 124981: {'lr': 3.4437254634030606e-05, 'samples': 23996352, 'steps': 124980, 'loss/train': 0.9968650937080383} 08/31/2021 11:55:11 - INFO - __main__ - Step 124982: {'lr': 3.443456691614597e-05, 'samples': 23996544, 'steps': 124981, 'loss/train': 0.9164434671401978} 08/31/2021 11:55:12 - INFO - __main__ - Step 124983: {'lr': 3.4431879295391763e-05, 'samples': 23996736, 'steps': 124982, 'loss/train': 1.2312220335006714} 08/31/2021 11:55:12 - INFO - __main__ - Step 124984: {'lr': 3.442919177176923e-05, 'samples': 23996928, 'steps': 124983, 'loss/train': 1.2013767957687378} 08/31/2021 11:55:14 - INFO - __main__ - Step 124985: {'lr': 3.442650434527958e-05, 'samples': 23997120, 'steps': 124984, 'loss/train': 0.5785762071609497} 08/31/2021 11:55:14 - INFO - __main__ - Step 124986: {'lr': 3.442381701592404e-05, 'samples': 23997312, 'steps': 124985, 'loss/train': 0.31267040967941284} 08/31/2021 11:55:15 - INFO - __main__ - Step 124987: {'lr': 3.4421129783703764e-05, 'samples': 23997504, 'steps': 124986, 'loss/train': 1.499607801437378} 08/31/2021 11:55:15 - INFO - __main__ - Step 124988: {'lr': 3.441844264862007e-05, 'samples': 23997696, 'steps': 124987, 'loss/train': 0.7751349210739136} 08/31/2021 11:55:15 - INFO - __main__ - Step 124989: {'lr': 3.441575561067406e-05, 'samples': 23997888, 'steps': 124988, 'loss/train': 1.4567484855651855} 08/31/2021 11:55:17 - INFO - __main__ - Step 124990: {'lr': 3.441306866986696e-05, 'samples': 23998080, 'steps': 124989, 'loss/train': 0.8975555300712585} 08/31/2021 11:55:17 - INFO - __main__ - Step 124991: {'lr': 3.4410381826200016e-05, 'samples': 23998272, 'steps': 124990, 'loss/train': 1.2882788181304932} 08/31/2021 11:55:18 - INFO - __main__ - Step 124992: {'lr': 3.440769507967445e-05, 'samples': 23998464, 'steps': 124991, 'loss/train': 1.3377351760864258} 08/31/2021 11:55:18 - INFO - __main__ - Step 124993: {'lr': 3.440500843029143e-05, 'samples': 23998656, 'steps': 124992, 'loss/train': 1.1775315999984741} 08/31/2021 11:55:18 - INFO - __main__ - Step 124994: {'lr': 3.440232187805217e-05, 'samples': 23998848, 'steps': 124993, 'loss/train': 0.40791556239128113} 08/31/2021 11:55:20 - INFO - __main__ - Step 124995: {'lr': 3.4399635422957904e-05, 'samples': 23999040, 'steps': 124994, 'loss/train': 1.4422935247421265} 08/31/2021 11:55:21 - INFO - __main__ - Step 124996: {'lr': 3.439694906500984e-05, 'samples': 23999232, 'steps': 124995, 'loss/train': 0.08955446630716324} 08/31/2021 11:55:21 - INFO - __main__ - Step 124997: {'lr': 3.439426280420921e-05, 'samples': 23999424, 'steps': 124996, 'loss/train': 1.2135571241378784} 08/31/2021 11:55:22 - INFO - __main__ - Step 124998: {'lr': 3.439157664055717e-05, 'samples': 23999616, 'steps': 124997, 'loss/train': 1.0720388889312744} 08/31/2021 11:55:22 - INFO - __main__ - Step 124999: {'lr': 3.438889057405495e-05, 'samples': 23999808, 'steps': 124998, 'loss/train': 1.5306371450424194} 08/31/2021 11:55:23 - INFO - __main__ - Step 125000: {'lr': 3.438620460470379e-05, 'samples': 24000000, 'steps': 124999, 'loss/train': 1.0208556652069092} 08/31/2021 11:55:24 - INFO - __main__ - Step 125001: {'lr': 3.438351873250492e-05, 'samples': 24000192, 'steps': 125000, 'loss/train': 1.2241761684417725} 08/31/2021 11:55:24 - INFO - __main__ - Step 125002: {'lr': 3.4380832957459476e-05, 'samples': 24000384, 'steps': 125001, 'loss/train': 1.4165724515914917} 08/31/2021 11:55:25 - INFO - __main__ - Step 125003: {'lr': 3.437814727956867e-05, 'samples': 24000576, 'steps': 125002, 'loss/train': 0.5952807664871216} 08/31/2021 11:55:25 - INFO - __main__ - Step 125004: {'lr': 3.437546169883376e-05, 'samples': 24000768, 'steps': 125003, 'loss/train': 1.3850308656692505} 08/31/2021 11:55:27 - INFO - __main__ - Step 125005: {'lr': 3.4372776215255946e-05, 'samples': 24000960, 'steps': 125004, 'loss/train': 0.8192311525344849} 08/31/2021 11:55:27 - INFO - __main__ - Step 125006: {'lr': 3.437009082883641e-05, 'samples': 24001152, 'steps': 125005, 'loss/train': 0.18388068675994873} 08/31/2021 11:55:27 - INFO - __main__ - Step 125007: {'lr': 3.43674055395764e-05, 'samples': 24001344, 'steps': 125006, 'loss/train': 1.0803858041763306} 08/31/2021 11:55:28 - INFO - __main__ - Step 125008: {'lr': 3.436472034747712e-05, 'samples': 24001536, 'steps': 125007, 'loss/train': 1.5865046977996826} 08/31/2021 11:55:28 - INFO - __main__ - Step 125009: {'lr': 3.436203525253975e-05, 'samples': 24001728, 'steps': 125008, 'loss/train': 1.2761460542678833} 08/31/2021 11:55:28 - INFO - __main__ - Step 125010: {'lr': 3.4359350254765527e-05, 'samples': 24001920, 'steps': 125009, 'loss/train': 1.3884766101837158} 08/31/2021 11:55:30 - INFO - __main__ - Step 125011: {'lr': 3.4356665354155656e-05, 'samples': 24002112, 'steps': 125010, 'loss/train': 1.2689194679260254} 08/31/2021 11:55:31 - INFO - __main__ - Step 125012: {'lr': 3.435398055071135e-05, 'samples': 24002304, 'steps': 125011, 'loss/train': 0.5181981325149536} 08/31/2021 11:55:31 - INFO - __main__ - Step 125013: {'lr': 3.435129584443378e-05, 'samples': 24002496, 'steps': 125012, 'loss/train': 0.2169496715068817} 08/31/2021 11:55:31 - INFO - __main__ - Step 125014: {'lr': 3.434861123532429e-05, 'samples': 24002688, 'steps': 125013, 'loss/train': 0.06633510440587997} 08/31/2021 11:55:32 - INFO - __main__ - Step 125015: {'lr': 3.434592672338391e-05, 'samples': 24002880, 'steps': 125014, 'loss/train': 1.142180323600769} 08/31/2021 11:55:33 - INFO - __main__ - Step 125016: {'lr': 3.434324230861391e-05, 'samples': 24003072, 'steps': 125015, 'loss/train': 1.5748544931411743} 08/31/2021 11:55:34 - INFO - __main__ - Step 125017: {'lr': 3.434055799101554e-05, 'samples': 24003264, 'steps': 125016, 'loss/train': 0.5544837713241577} 08/31/2021 11:55:34 - INFO - __main__ - Step 125018: {'lr': 3.4337873770589974e-05, 'samples': 24003456, 'steps': 125017, 'loss/train': 0.7811460494995117} 08/31/2021 11:55:34 - INFO - __main__ - Step 125019: {'lr': 3.433518964733845e-05, 'samples': 24003648, 'steps': 125018, 'loss/train': 1.321091651916504} 08/31/2021 11:55:35 - INFO - __main__ - Step 125020: {'lr': 3.433250562126214e-05, 'samples': 24003840, 'steps': 125019, 'loss/train': 1.515872836112976} 08/31/2021 11:55:36 - INFO - __main__ - Step 125021: {'lr': 3.432982169236229e-05, 'samples': 24004032, 'steps': 125020, 'loss/train': 1.067494511604309} 08/31/2021 11:55:37 - INFO - __main__ - Step 125022: {'lr': 3.43271378606401e-05, 'samples': 24004224, 'steps': 125021, 'loss/train': 1.0670608282089233} 08/31/2021 11:55:37 - INFO - __main__ - Step 125023: {'lr': 3.432445412609678e-05, 'samples': 24004416, 'steps': 125022, 'loss/train': 0.29641851782798767} 08/31/2021 11:55:37 - INFO - __main__ - Step 125024: {'lr': 3.43217704887335e-05, 'samples': 24004608, 'steps': 125023, 'loss/train': 0.449930340051651} 08/31/2021 11:55:38 - INFO - __main__ - Step 125025: {'lr': 3.431908694855154e-05, 'samples': 24004800, 'steps': 125024, 'loss/train': 1.3784494400024414} 08/31/2021 11:55:39 - INFO - __main__ - Step 125026: {'lr': 3.431640350555204e-05, 'samples': 24004992, 'steps': 125025, 'loss/train': 1.022613286972046} 08/31/2021 11:55:40 - INFO - __main__ - Step 125027: {'lr': 3.431372015973624e-05, 'samples': 24005184, 'steps': 125026, 'loss/train': 1.2371039390563965} 08/31/2021 11:55:40 - INFO - __main__ - Step 125028: {'lr': 3.431103691110543e-05, 'samples': 24005376, 'steps': 125027, 'loss/train': 0.9228162169456482} 08/31/2021 11:55:40 - INFO - __main__ - Step 125029: {'lr': 3.430835375966068e-05, 'samples': 24005568, 'steps': 125028, 'loss/train': 1.0704267024993896} 08/31/2021 11:55:41 - INFO - __main__ - Step 125030: {'lr': 3.430567070540325e-05, 'samples': 24005760, 'steps': 125029, 'loss/train': 1.8503154516220093} 08/31/2021 11:55:41 - INFO - __main__ - Step 125031: {'lr': 3.430298774833435e-05, 'samples': 24005952, 'steps': 125030, 'loss/train': 0.6316514015197754} 08/31/2021 11:55:43 - INFO - __main__ - Step 125032: {'lr': 3.43003048884552e-05, 'samples': 24006144, 'steps': 125031, 'loss/train': 0.4914039373397827} 08/31/2021 11:55:43 - INFO - __main__ - Step 125033: {'lr': 3.429762212576701e-05, 'samples': 24006336, 'steps': 125032, 'loss/train': 1.1006563901901245} 08/31/2021 11:55:43 - INFO - __main__ - Step 125034: {'lr': 3.4294939460270984e-05, 'samples': 24006528, 'steps': 125033, 'loss/train': 0.6392338871955872} 08/31/2021 11:55:44 - INFO - __main__ - Step 125035: {'lr': 3.4292256891968326e-05, 'samples': 24006720, 'steps': 125034, 'loss/train': 1.6101032495498657} 08/31/2021 11:55:44 - INFO - __main__ - Step 125036: {'lr': 3.4289574420860226e-05, 'samples': 24006912, 'steps': 125035, 'loss/train': 1.1509569883346558} 08/31/2021 11:55:46 - INFO - __main__ - Step 125037: {'lr': 3.428689204694793e-05, 'samples': 24007104, 'steps': 125036, 'loss/train': 1.0739167928695679} 08/31/2021 11:55:46 - INFO - __main__ - Step 125038: {'lr': 3.428420977023264e-05, 'samples': 24007296, 'steps': 125037, 'loss/train': 0.878434419631958} 08/31/2021 11:55:47 - INFO - __main__ - Step 125039: {'lr': 3.428152759071557e-05, 'samples': 24007488, 'steps': 125038, 'loss/train': 0.6977106928825378} 08/31/2021 11:55:47 - INFO - __main__ - Step 125040: {'lr': 3.427884550839788e-05, 'samples': 24007680, 'steps': 125039, 'loss/train': 2.1582276821136475} 08/31/2021 11:55:47 - INFO - __main__ - Step 125041: {'lr': 3.427616352328089e-05, 'samples': 24007872, 'steps': 125040, 'loss/train': 0.5518671274185181} 08/31/2021 11:55:49 - INFO - __main__ - Step 125042: {'lr': 3.427348163536567e-05, 'samples': 24008064, 'steps': 125041, 'loss/train': 1.0608799457550049} 08/31/2021 11:55:50 - INFO - __main__ - Step 125043: {'lr': 3.4270799844653504e-05, 'samples': 24008256, 'steps': 125042, 'loss/train': 1.1610229015350342} 08/31/2021 11:55:50 - INFO - __main__ - Step 125044: {'lr': 3.426811815114558e-05, 'samples': 24008448, 'steps': 125043, 'loss/train': 1.4871939420700073} 08/31/2021 11:55:51 - INFO - __main__ - Step 125045: {'lr': 3.42654365548431e-05, 'samples': 24008640, 'steps': 125044, 'loss/train': 0.31216180324554443} 08/31/2021 11:55:51 - INFO - __main__ - Step 125046: {'lr': 3.42627550557473e-05, 'samples': 24008832, 'steps': 125045, 'loss/train': 0.11449024081230164} 08/31/2021 11:55:53 - INFO - __main__ - Step 125047: {'lr': 3.426007365385936e-05, 'samples': 24009024, 'steps': 125046, 'loss/train': 1.098288893699646} 08/31/2021 11:55:53 - INFO - __main__ - Step 125048: {'lr': 3.4257392349180516e-05, 'samples': 24009216, 'steps': 125047, 'loss/train': 1.174813985824585} 08/31/2021 11:55:53 - INFO - __main__ - Step 125049: {'lr': 3.425471114171197e-05, 'samples': 24009408, 'steps': 125048, 'loss/train': 0.7297993898391724} 08/31/2021 11:55:54 - INFO - __main__ - Step 125050: {'lr': 3.4252030031454886e-05, 'samples': 24009600, 'steps': 125049, 'loss/train': 1.1622925996780396} 08/31/2021 11:55:54 - INFO - __main__ - Step 125051: {'lr': 3.424934901841054e-05, 'samples': 24009792, 'steps': 125050, 'loss/train': 1.131774663925171} 08/31/2021 11:55:55 - INFO - __main__ - Step 125052: {'lr': 3.424666810258009e-05, 'samples': 24009984, 'steps': 125051, 'loss/train': 0.8381006121635437} 08/31/2021 11:55:57 - INFO - __main__ - Step 125053: {'lr': 3.424398728396477e-05, 'samples': 24010176, 'steps': 125052, 'loss/train': 1.2760915756225586} 08/31/2021 11:55:57 - INFO - __main__ - Step 125054: {'lr': 3.42413065625658e-05, 'samples': 24010368, 'steps': 125053, 'loss/train': 1.0638922452926636} 08/31/2021 11:55:58 - INFO - __main__ - Step 125055: {'lr': 3.4238625938384396e-05, 'samples': 24010560, 'steps': 125054, 'loss/train': 1.039216160774231} 08/31/2021 11:55:58 - INFO - __main__ - Step 125056: {'lr': 3.4235945411421695e-05, 'samples': 24010752, 'steps': 125055, 'loss/train': 2.226033926010132} 08/31/2021 11:55:58 - INFO - __main__ - Step 125057: {'lr': 3.423326498167895e-05, 'samples': 24010944, 'steps': 125056, 'loss/train': 1.582883358001709} 08/31/2021 11:56:00 - INFO - __main__ - Step 125058: {'lr': 3.423058464915735e-05, 'samples': 24011136, 'steps': 125057, 'loss/train': 1.0064111948013306} 08/31/2021 11:56:00 - INFO - __main__ - Step 125059: {'lr': 3.422790441385812e-05, 'samples': 24011328, 'steps': 125058, 'loss/train': 0.10433712601661682} 08/31/2021 11:56:01 - INFO - __main__ - Step 125060: {'lr': 3.422522427578248e-05, 'samples': 24011520, 'steps': 125059, 'loss/train': 0.8022900819778442} 08/31/2021 11:56:01 - INFO - __main__ - Step 125061: {'lr': 3.422254423493162e-05, 'samples': 24011712, 'steps': 125060, 'loss/train': 0.8803631663322449} 08/31/2021 11:56:01 - INFO - __main__ - Step 125062: {'lr': 3.421986429130675e-05, 'samples': 24011904, 'steps': 125061, 'loss/train': 1.664159893989563} 08/31/2021 11:56:03 - INFO - __main__ - Step 125063: {'lr': 3.421718444490907e-05, 'samples': 24012096, 'steps': 125062, 'loss/train': 0.6902055144309998} 08/31/2021 11:56:04 - INFO - __main__ - Step 125064: {'lr': 3.4214504695739805e-05, 'samples': 24012288, 'steps': 125063, 'loss/train': 0.8596655130386353} 08/31/2021 11:56:04 - INFO - __main__ - Step 125065: {'lr': 3.421182504380016e-05, 'samples': 24012480, 'steps': 125064, 'loss/train': 0.8965148329734802} 08/31/2021 11:56:04 - INFO - __main__ - Step 125066: {'lr': 3.4209145489091346e-05, 'samples': 24012672, 'steps': 125065, 'loss/train': 1.850062370300293} 08/31/2021 11:56:05 - INFO - __main__ - Step 125067: {'lr': 3.4206466031614535e-05, 'samples': 24012864, 'steps': 125066, 'loss/train': 1.2980494499206543} 08/31/2021 11:56:05 - INFO - __main__ - Step 125068: {'lr': 3.420378667137103e-05, 'samples': 24013056, 'steps': 125067, 'loss/train': 1.1443629264831543} 08/31/2021 11:56:06 - INFO - __main__ - Step 125069: {'lr': 3.420110740836191e-05, 'samples': 24013248, 'steps': 125068, 'loss/train': 1.0863008499145508} 08/31/2021 11:56:07 - INFO - __main__ - Step 125070: {'lr': 3.419842824258845e-05, 'samples': 24013440, 'steps': 125069, 'loss/train': 1.0556005239486694} 08/31/2021 11:56:07 - INFO - __main__ - Step 125071: {'lr': 3.419574917405183e-05, 'samples': 24013632, 'steps': 125070, 'loss/train': 1.1288764476776123} 08/31/2021 11:56:08 - INFO - __main__ - Step 125072: {'lr': 3.419307020275331e-05, 'samples': 24013824, 'steps': 125071, 'loss/train': 0.7566120624542236} 08/31/2021 11:56:08 - INFO - __main__ - Step 125073: {'lr': 3.4190391328694035e-05, 'samples': 24014016, 'steps': 125072, 'loss/train': 1.4276070594787598} 08/31/2021 11:56:09 - INFO - __main__ - Step 125074: {'lr': 3.418771255187525e-05, 'samples': 24014208, 'steps': 125073, 'loss/train': 0.4960659146308899} 08/31/2021 11:56:10 - INFO - __main__ - Step 125075: {'lr': 3.4185033872298127e-05, 'samples': 24014400, 'steps': 125074, 'loss/train': 1.0801417827606201} 08/31/2021 11:56:10 - INFO - __main__ - Step 125076: {'lr': 3.418235528996391e-05, 'samples': 24014592, 'steps': 125075, 'loss/train': 0.4998991787433624} 08/31/2021 11:56:10 - INFO - __main__ - Step 125077: {'lr': 3.41796768048738e-05, 'samples': 24014784, 'steps': 125076, 'loss/train': 1.4823719263076782} 08/31/2021 11:56:11 - INFO - __main__ - Step 125078: {'lr': 3.417699841702901e-05, 'samples': 24014976, 'steps': 125077, 'loss/train': 1.1125059127807617} 08/31/2021 11:56:12 - INFO - __main__ - Step 125079: {'lr': 3.417432012643071e-05, 'samples': 24015168, 'steps': 125078, 'loss/train': 1.131155014038086} 08/31/2021 11:56:13 - INFO - __main__ - Step 125080: {'lr': 3.4171641933080147e-05, 'samples': 24015360, 'steps': 125079, 'loss/train': 0.0383625291287899} 08/31/2021 11:56:13 - INFO - __main__ - Step 125081: {'lr': 3.4168963836978513e-05, 'samples': 24015552, 'steps': 125080, 'loss/train': 1.0422552824020386} 08/31/2021 11:56:14 - INFO - __main__ - Step 125082: {'lr': 3.416628583812706e-05, 'samples': 24015744, 'steps': 125081, 'loss/train': 1.0836819410324097} 08/31/2021 11:56:14 - INFO - __main__ - Step 125083: {'lr': 3.4163607936526896e-05, 'samples': 24015936, 'steps': 125082, 'loss/train': 0.04034655913710594} 08/31/2021 11:56:15 - INFO - __main__ - Step 125084: {'lr': 3.416093013217928e-05, 'samples': 24016128, 'steps': 125083, 'loss/train': 0.029413918033242226} 08/31/2021 11:56:16 - INFO - __main__ - Step 125085: {'lr': 3.415825242508541e-05, 'samples': 24016320, 'steps': 125084, 'loss/train': 0.37262535095214844} 08/31/2021 11:56:16 - INFO - __main__ - Step 125086: {'lr': 3.41555748152465e-05, 'samples': 24016512, 'steps': 125085, 'loss/train': 1.3813951015472412} 08/31/2021 11:56:17 - INFO - __main__ - Step 125087: {'lr': 3.415289730266377e-05, 'samples': 24016704, 'steps': 125086, 'loss/train': 0.9339478015899658} 08/31/2021 11:56:17 - INFO - __main__ - Step 125088: {'lr': 3.4150219887338437e-05, 'samples': 24016896, 'steps': 125087, 'loss/train': 1.5079823732376099} 08/31/2021 11:56:19 - INFO - __main__ - Step 125089: {'lr': 3.414754256927163e-05, 'samples': 24017088, 'steps': 125088, 'loss/train': 1.5155091285705566} 08/31/2021 11:56:19 - INFO - __main__ - Step 125090: {'lr': 3.414486534846464e-05, 'samples': 24017280, 'steps': 125089, 'loss/train': 1.0681473016738892} 08/31/2021 11:56:19 - INFO - __main__ - Step 125091: {'lr': 3.4142188224918656e-05, 'samples': 24017472, 'steps': 125090, 'loss/train': 0.7710675597190857} 08/31/2021 11:56:20 - INFO - __main__ - Step 125092: {'lr': 3.413951119863484e-05, 'samples': 24017664, 'steps': 125091, 'loss/train': 1.5503965616226196} 08/31/2021 11:56:20 - INFO - __main__ - Step 125093: {'lr': 3.4136834269614444e-05, 'samples': 24017856, 'steps': 125092, 'loss/train': 0.7194474935531616} 08/31/2021 11:56:22 - INFO - __main__ - Step 125094: {'lr': 3.4134157437858664e-05, 'samples': 24018048, 'steps': 125093, 'loss/train': 0.3191338777542114} 08/31/2021 11:56:22 - INFO - __main__ - Step 125095: {'lr': 3.413148070336874e-05, 'samples': 24018240, 'steps': 125094, 'loss/train': 0.88329017162323} 08/31/2021 11:56:23 - INFO - __main__ - Step 125096: {'lr': 3.4128804066145794e-05, 'samples': 24018432, 'steps': 125095, 'loss/train': 1.3980528116226196} 08/31/2021 11:56:23 - INFO - __main__ - Step 125097: {'lr': 3.4126127526191096e-05, 'samples': 24018624, 'steps': 125096, 'loss/train': 1.4979280233383179} 08/31/2021 11:56:23 - INFO - __main__ - Step 125098: {'lr': 3.412345108350581e-05, 'samples': 24018816, 'steps': 125097, 'loss/train': 0.05274965241551399} 08/31/2021 11:56:24 - INFO - __main__ - Step 125099: {'lr': 3.4120774738091164e-05, 'samples': 24019008, 'steps': 125098, 'loss/train': 1.2851402759552002} 08/31/2021 11:56:26 - INFO - __main__ - Step 125100: {'lr': 3.41180984899484e-05, 'samples': 24019200, 'steps': 125099, 'loss/train': 0.9434321522712708} 08/31/2021 11:56:26 - INFO - __main__ - Step 125101: {'lr': 3.411542233907866e-05, 'samples': 24019392, 'steps': 125100, 'loss/train': 1.4223006963729858} 08/31/2021 11:56:26 - INFO - __main__ - Step 125102: {'lr': 3.411274628548317e-05, 'samples': 24019584, 'steps': 125101, 'loss/train': 5.720510959625244} 08/31/2021 11:56:27 - INFO - __main__ - Step 125103: {'lr': 3.4110070329163165e-05, 'samples': 24019776, 'steps': 125102, 'loss/train': 0.8952626585960388} 08/31/2021 11:56:27 - INFO - __main__ - Step 125104: {'lr': 3.4107394470119815e-05, 'samples': 24019968, 'steps': 125103, 'loss/train': 0.6932654976844788} 08/31/2021 11:56:29 - INFO - __main__ - Step 125105: {'lr': 3.4104718708354357e-05, 'samples': 24020160, 'steps': 125104, 'loss/train': 0.9936050176620483} 08/31/2021 11:56:29 - INFO - __main__ - Step 125106: {'lr': 3.410204304386799e-05, 'samples': 24020352, 'steps': 125105, 'loss/train': 1.1888070106506348} 08/31/2021 11:56:30 - INFO - __main__ - Step 125107: {'lr': 3.40993674766619e-05, 'samples': 24020544, 'steps': 125106, 'loss/train': 1.5590819120407104} 08/31/2021 11:56:30 - INFO - __main__ - Step 125108: {'lr': 3.409669200673729e-05, 'samples': 24020736, 'steps': 125107, 'loss/train': 1.065636157989502} 08/31/2021 11:56:30 - INFO - __main__ - Step 125109: {'lr': 3.409401663409545e-05, 'samples': 24020928, 'steps': 125108, 'loss/train': 1.4129445552825928} 08/31/2021 11:56:32 - INFO - __main__ - Step 125110: {'lr': 3.4091341358737456e-05, 'samples': 24021120, 'steps': 125109, 'loss/train': 1.585582971572876} 08/31/2021 11:56:32 - INFO - __main__ - Step 125111: {'lr': 3.4088666180664557e-05, 'samples': 24021312, 'steps': 125110, 'loss/train': 1.4868272542953491} 08/31/2021 11:56:33 - INFO - __main__ - Step 125112: {'lr': 3.4085991099878006e-05, 'samples': 24021504, 'steps': 125111, 'loss/train': 1.6068670749664307} 08/31/2021 11:56:33 - INFO - __main__ - Step 125113: {'lr': 3.4083316116378935e-05, 'samples': 24021696, 'steps': 125112, 'loss/train': 1.1297980546951294} 08/31/2021 11:56:33 - INFO - __main__ - Step 125114: {'lr': 3.408064123016863e-05, 'samples': 24021888, 'steps': 125113, 'loss/train': 0.9944567084312439} 08/31/2021 11:56:35 - INFO - __main__ - Step 125115: {'lr': 3.407796644124822e-05, 'samples': 24022080, 'steps': 125114, 'loss/train': 0.8428311347961426} 08/31/2021 11:56:35 - INFO - __main__ - Step 125116: {'lr': 3.407529174961896e-05, 'samples': 24022272, 'steps': 125115, 'loss/train': 0.528693437576294} 08/31/2021 11:56:36 - INFO - __main__ - Step 125117: {'lr': 3.407261715528207e-05, 'samples': 24022464, 'steps': 125116, 'loss/train': 0.7042139172554016} 08/31/2021 11:56:36 - INFO - __main__ - Step 125118: {'lr': 3.406994265823868e-05, 'samples': 24022656, 'steps': 125117, 'loss/train': 0.42466190457344055} 08/31/2021 11:56:37 - INFO - __main__ - Step 125119: {'lr': 3.406726825849007e-05, 'samples': 24022848, 'steps': 125118, 'loss/train': 0.988142192363739} 08/31/2021 11:56:38 - INFO - __main__ - Step 125120: {'lr': 3.406459395603742e-05, 'samples': 24023040, 'steps': 125119, 'loss/train': 1.35422682762146} 08/31/2021 11:56:39 - INFO - __main__ - Step 125121: {'lr': 3.4061919750881906e-05, 'samples': 24023232, 'steps': 125120, 'loss/train': 1.405818223953247} 08/31/2021 11:56:39 - INFO - __main__ - Step 125122: {'lr': 3.405924564302484e-05, 'samples': 24023424, 'steps': 125121, 'loss/train': 0.9901419281959534} 08/31/2021 11:56:39 - INFO - __main__ - Step 125123: {'lr': 3.405657163246728e-05, 'samples': 24023616, 'steps': 125122, 'loss/train': 0.9847617149353027} 08/31/2021 11:56:40 - INFO - __main__ - Step 125124: {'lr': 3.40538977192105e-05, 'samples': 24023808, 'steps': 125123, 'loss/train': 0.9680397510528564} 08/31/2021 11:56:40 - INFO - __main__ - Step 125125: {'lr': 3.405122390325569e-05, 'samples': 24024000, 'steps': 125124, 'loss/train': 0.2832673192024231} 08/31/2021 11:56:41 - INFO - __main__ - Step 125126: {'lr': 3.4048550184604096e-05, 'samples': 24024192, 'steps': 125125, 'loss/train': 1.2388750314712524} 08/31/2021 11:56:42 - INFO - __main__ - Step 125127: {'lr': 3.404587656325686e-05, 'samples': 24024384, 'steps': 125126, 'loss/train': 1.1300936937332153} 08/31/2021 11:56:42 - INFO - __main__ - Step 125128: {'lr': 3.4043203039215235e-05, 'samples': 24024576, 'steps': 125127, 'loss/train': 1.701317310333252} 08/31/2021 11:56:43 - INFO - __main__ - Step 125129: {'lr': 3.404052961248042e-05, 'samples': 24024768, 'steps': 125128, 'loss/train': 1.3737071752548218} 08/31/2021 11:56:43 - INFO - __main__ - Step 125130: {'lr': 3.4037856283053584e-05, 'samples': 24024960, 'steps': 125129, 'loss/train': 1.9825345277786255} 08/31/2021 11:56:45 - INFO - __main__ - Step 125131: {'lr': 3.4035183050935976e-05, 'samples': 24025152, 'steps': 125130, 'loss/train': 1.4000027179718018} 08/31/2021 11:56:45 - INFO - __main__ - Step 125132: {'lr': 3.403250991612877e-05, 'samples': 24025344, 'steps': 125131, 'loss/train': 3.5020318031311035} 08/31/2021 11:56:45 - INFO - __main__ - Step 125133: {'lr': 3.4029836878633174e-05, 'samples': 24025536, 'steps': 125132, 'loss/train': 0.7969339489936829} 08/31/2021 11:56:46 - INFO - __main__ - Step 125134: {'lr': 3.4027163938450425e-05, 'samples': 24025728, 'steps': 125133, 'loss/train': 0.9887712597846985} 08/31/2021 11:56:46 - INFO - __main__ - Step 125135: {'lr': 3.4024491095581754e-05, 'samples': 24025920, 'steps': 125134, 'loss/train': 0.5734519362449646} 08/31/2021 11:56:47 - INFO - __main__ - Step 125136: {'lr': 3.402181835002824e-05, 'samples': 24026112, 'steps': 125135, 'loss/train': 0.7339955568313599} 08/31/2021 11:56:48 - INFO - __main__ - Step 125137: {'lr': 3.401914570179118e-05, 'samples': 24026304, 'steps': 125136, 'loss/train': 1.276680588722229} 08/31/2021 11:56:48 - INFO - __main__ - Step 125138: {'lr': 3.4016473150871755e-05, 'samples': 24026496, 'steps': 125137, 'loss/train': 0.8585313558578491} 08/31/2021 11:56:49 - INFO - __main__ - Step 125139: {'lr': 3.4013800697271196e-05, 'samples': 24026688, 'steps': 125138, 'loss/train': 1.009971261024475} 08/31/2021 11:56:49 - INFO - __main__ - Step 125140: {'lr': 3.401112834099066e-05, 'samples': 24026880, 'steps': 125139, 'loss/train': 1.4754389524459839} 08/31/2021 11:56:51 - INFO - __main__ - Step 125141: {'lr': 3.400845608203138e-05, 'samples': 24027072, 'steps': 125140, 'loss/train': 0.09510697424411774} 08/31/2021 11:56:52 - INFO - __main__ - Step 125142: {'lr': 3.400578392039455e-05, 'samples': 24027264, 'steps': 125141, 'loss/train': 0.9417356848716736} 08/31/2021 11:56:52 - INFO - __main__ - Step 125143: {'lr': 3.4003111856081404e-05, 'samples': 24027456, 'steps': 125142, 'loss/train': 0.6283369064331055} 08/31/2021 11:56:52 - INFO - __main__ - Step 125144: {'lr': 3.40004398890931e-05, 'samples': 24027648, 'steps': 125143, 'loss/train': 1.5136330127716064} 08/31/2021 11:56:53 - INFO - __main__ - Step 125145: {'lr': 3.399776801943089e-05, 'samples': 24027840, 'steps': 125144, 'loss/train': 1.1206811666488647} 08/31/2021 11:56:53 - INFO - __main__ - Step 125146: {'lr': 3.399509624709593e-05, 'samples': 24028032, 'steps': 125145, 'loss/train': 0.4590497314929962} 08/31/2021 11:56:54 - INFO - __main__ - Step 125147: {'lr': 3.399242457208945e-05, 'samples': 24028224, 'steps': 125146, 'loss/train': 1.7252637147903442} 08/31/2021 11:56:55 - INFO - __main__ - Step 125148: {'lr': 3.398975299441265e-05, 'samples': 24028416, 'steps': 125147, 'loss/train': 1.3132933378219604} 08/31/2021 11:56:55 - INFO - __main__ - Step 125149: {'lr': 3.398708151406679e-05, 'samples': 24028608, 'steps': 125148, 'loss/train': 1.2006725072860718} 08/31/2021 11:56:56 - INFO - __main__ - Step 125150: {'lr': 3.3984410131052965e-05, 'samples': 24028800, 'steps': 125149, 'loss/train': 0.8293009996414185} 08/31/2021 11:56:56 - INFO - __main__ - Step 125151: {'lr': 3.398173884537242e-05, 'samples': 24028992, 'steps': 125150, 'loss/train': 1.2271171808242798} 08/31/2021 11:56:57 - INFO - __main__ - Step 125152: {'lr': 3.397906765702638e-05, 'samples': 24029184, 'steps': 125151, 'loss/train': 1.2017568349838257} 08/31/2021 11:56:58 - INFO - __main__ - Step 125153: {'lr': 3.397639656601606e-05, 'samples': 24029376, 'steps': 125152, 'loss/train': 1.1773852109909058} 08/31/2021 11:56:58 - INFO - __main__ - Step 125154: {'lr': 3.39737255723426e-05, 'samples': 24029568, 'steps': 125153, 'loss/train': 0.7894925475120544} 08/31/2021 11:56:59 - INFO - __main__ - Step 125155: {'lr': 3.3971054676007276e-05, 'samples': 24029760, 'steps': 125154, 'loss/train': 0.67523193359375} 08/31/2021 11:56:59 - INFO - __main__ - Step 125156: {'lr': 3.396838387701126e-05, 'samples': 24029952, 'steps': 125155, 'loss/train': 1.1643933057785034} 08/31/2021 11:57:01 - INFO - __main__ - Step 125157: {'lr': 3.396571317535574e-05, 'samples': 24030144, 'steps': 125156, 'loss/train': 1.0702259540557861} 08/31/2021 11:57:01 - INFO - __main__ - Step 125158: {'lr': 3.396304257104196e-05, 'samples': 24030336, 'steps': 125157, 'loss/train': 1.6118483543395996} 08/31/2021 11:57:01 - INFO - __main__ - Step 125159: {'lr': 3.3960372064071074e-05, 'samples': 24030528, 'steps': 125158, 'loss/train': 0.6791336536407471} 08/31/2021 11:57:02 - INFO - __main__ - Step 125160: {'lr': 3.395770165444431e-05, 'samples': 24030720, 'steps': 125159, 'loss/train': 1.9206697940826416} 08/31/2021 11:57:02 - INFO - __main__ - Step 125161: {'lr': 3.3955031342162904e-05, 'samples': 24030912, 'steps': 125160, 'loss/train': 1.2519692182540894} 08/31/2021 11:57:04 - INFO - __main__ - Step 125162: {'lr': 3.3952361127228046e-05, 'samples': 24031104, 'steps': 125161, 'loss/train': 0.4376288652420044} 08/31/2021 11:57:05 - INFO - __main__ - Step 125163: {'lr': 3.39496910096409e-05, 'samples': 24031296, 'steps': 125162, 'loss/train': 0.7759473919868469} 08/31/2021 11:57:05 - INFO - __main__ - Step 125164: {'lr': 3.3947020989402665e-05, 'samples': 24031488, 'steps': 125163, 'loss/train': 0.7311112284660339} 08/31/2021 11:57:05 - INFO - __main__ - Step 125165: {'lr': 3.394435106651458e-05, 'samples': 24031680, 'steps': 125164, 'loss/train': 0.9099812507629395} 08/31/2021 11:57:06 - INFO - __main__ - Step 125166: {'lr': 3.3941681240977826e-05, 'samples': 24031872, 'steps': 125165, 'loss/train': 1.467870831489563} 08/31/2021 11:57:07 - INFO - __main__ - Step 125167: {'lr': 3.39390115127936e-05, 'samples': 24032064, 'steps': 125166, 'loss/train': 1.4117670059204102} 08/31/2021 11:57:08 - INFO - __main__ - Step 125168: {'lr': 3.393634188196315e-05, 'samples': 24032256, 'steps': 125167, 'loss/train': 1.1655104160308838} 08/31/2021 11:57:08 - INFO - __main__ - Step 125169: {'lr': 3.393367234848766e-05, 'samples': 24032448, 'steps': 125168, 'loss/train': 0.025835832580924034} 08/31/2021 11:57:08 - INFO - __main__ - Step 125170: {'lr': 3.393100291236831e-05, 'samples': 24032640, 'steps': 125169, 'loss/train': 0.7297099232673645} 08/31/2021 11:57:09 - INFO - __main__ - Step 125171: {'lr': 3.392833357360631e-05, 'samples': 24032832, 'steps': 125170, 'loss/train': 0.09381867200136185} 08/31/2021 11:57:10 - INFO - __main__ - Step 125172: {'lr': 3.3925664332202874e-05, 'samples': 24033024, 'steps': 125171, 'loss/train': 0.70738285779953} 08/31/2021 11:57:11 - INFO - __main__ - Step 125173: {'lr': 3.3922995188159194e-05, 'samples': 24033216, 'steps': 125172, 'loss/train': 0.9875332117080688} 08/31/2021 11:57:11 - INFO - __main__ - Step 125174: {'lr': 3.392032614147647e-05, 'samples': 24033408, 'steps': 125173, 'loss/train': 1.1258186101913452} 08/31/2021 11:57:12 - INFO - __main__ - Step 125175: {'lr': 3.3917657192155975e-05, 'samples': 24033600, 'steps': 125174, 'loss/train': 0.02031215839087963} 08/31/2021 11:57:12 - INFO - __main__ - Step 125176: {'lr': 3.391498834019879e-05, 'samples': 24033792, 'steps': 125175, 'loss/train': 0.8549923896789551} 08/31/2021 11:57:14 - INFO - __main__ - Step 125177: {'lr': 3.39123195856062e-05, 'samples': 24033984, 'steps': 125176, 'loss/train': 1.7356672286987305} 08/31/2021 11:57:14 - INFO - __main__ - Step 125178: {'lr': 3.390965092837936e-05, 'samples': 24034176, 'steps': 125177, 'loss/train': 0.6067407131195068} 08/31/2021 11:57:15 - INFO - __main__ - Step 125179: {'lr': 3.3906982368519495e-05, 'samples': 24034368, 'steps': 125178, 'loss/train': 0.7766013741493225} 08/31/2021 11:57:15 - INFO - __main__ - Step 125180: {'lr': 3.3904313906027825e-05, 'samples': 24034560, 'steps': 125179, 'loss/train': 1.421514630317688} 08/31/2021 11:57:15 - INFO - __main__ - Step 125181: {'lr': 3.390164554090553e-05, 'samples': 24034752, 'steps': 125180, 'loss/train': 1.2290406227111816} 08/31/2021 11:57:17 - INFO - __main__ - Step 125182: {'lr': 3.389897727315383e-05, 'samples': 24034944, 'steps': 125181, 'loss/train': 0.49950188398361206} 08/31/2021 11:57:17 - INFO - __main__ - Step 125183: {'lr': 3.389630910277389e-05, 'samples': 24035136, 'steps': 125182, 'loss/train': 0.44099685549736023} 08/31/2021 11:57:18 - INFO - __main__ - Step 125184: {'lr': 3.389364102976697e-05, 'samples': 24035328, 'steps': 125183, 'loss/train': 1.268776297569275} 08/31/2021 11:57:18 - INFO - __main__ - Step 125185: {'lr': 3.389097305413422e-05, 'samples': 24035520, 'steps': 125184, 'loss/train': 1.3225919008255005} 08/31/2021 11:57:18 - INFO - __main__ - Step 125186: {'lr': 3.388830517587693e-05, 'samples': 24035712, 'steps': 125185, 'loss/train': 0.02407940663397312} 08/31/2021 11:57:20 - INFO - __main__ - Step 125187: {'lr': 3.388563739499617e-05, 'samples': 24035904, 'steps': 125186, 'loss/train': 0.8074035048484802} 08/31/2021 11:57:21 - INFO - __main__ - Step 125188: {'lr': 3.388296971149321e-05, 'samples': 24036096, 'steps': 125187, 'loss/train': 1.1321405172348022} 08/31/2021 11:57:21 - INFO - __main__ - Step 125189: {'lr': 3.3880302125369245e-05, 'samples': 24036288, 'steps': 125188, 'loss/train': 1.4731069803237915} 08/31/2021 11:57:21 - INFO - __main__ - Step 125190: {'lr': 3.387763463662549e-05, 'samples': 24036480, 'steps': 125189, 'loss/train': 0.01547360047698021} 08/31/2021 11:57:22 - INFO - __main__ - Step 125191: {'lr': 3.387496724526312e-05, 'samples': 24036672, 'steps': 125190, 'loss/train': 0.5767116546630859} 08/31/2021 11:57:22 - INFO - __main__ - Step 125192: {'lr': 3.387229995128338e-05, 'samples': 24036864, 'steps': 125191, 'loss/train': 0.02313918061554432} 08/31/2021 11:57:24 - INFO - __main__ - Step 125193: {'lr': 3.3869632754687436e-05, 'samples': 24037056, 'steps': 125192, 'loss/train': 0.9898794293403625} 08/31/2021 11:57:24 - INFO - __main__ - Step 125194: {'lr': 3.386696565547648e-05, 'samples': 24037248, 'steps': 125193, 'loss/train': 1.0231846570968628} 08/31/2021 11:57:24 - INFO - __main__ - Step 125195: {'lr': 3.386429865365176e-05, 'samples': 24037440, 'steps': 125194, 'loss/train': 1.0840511322021484} 08/31/2021 11:57:25 - INFO - __main__ - Step 125196: {'lr': 3.3861631749214444e-05, 'samples': 24037632, 'steps': 125195, 'loss/train': 1.087722897529602} 08/31/2021 11:57:25 - INFO - __main__ - Step 125197: {'lr': 3.385896494216578e-05, 'samples': 24037824, 'steps': 125196, 'loss/train': 0.5310579538345337} 08/31/2021 11:57:25 - INFO - __main__ - Step 125198: {'lr': 3.385629823250691e-05, 'samples': 24038016, 'steps': 125197, 'loss/train': 0.031455617398023605} 08/31/2021 11:57:27 - INFO - __main__ - Step 125199: {'lr': 3.3853631620239024e-05, 'samples': 24038208, 'steps': 125198, 'loss/train': 0.9469236135482788} 08/31/2021 11:57:27 - INFO - __main__ - Step 125200: {'lr': 3.385096510536339e-05, 'samples': 24038400, 'steps': 125199, 'loss/train': 0.9007676839828491} 08/31/2021 11:57:28 - INFO - __main__ - Step 125201: {'lr': 3.384829868788114e-05, 'samples': 24038592, 'steps': 125200, 'loss/train': 0.29762256145477295} 08/31/2021 11:57:28 - INFO - __main__ - Step 125202: {'lr': 3.384563236779353e-05, 'samples': 24038784, 'steps': 125201, 'loss/train': 1.5844906568527222} 08/31/2021 11:57:28 - INFO - __main__ - Step 125203: {'lr': 3.384296614510174e-05, 'samples': 24038976, 'steps': 125202, 'loss/train': 1.0832221508026123} 08/31/2021 11:57:30 - INFO - __main__ - Step 125204: {'lr': 3.384030001980698e-05, 'samples': 24039168, 'steps': 125203, 'loss/train': 1.0861661434173584} 08/31/2021 11:57:30 - INFO - __main__ - Step 125205: {'lr': 3.383763399191045e-05, 'samples': 24039360, 'steps': 125204, 'loss/train': 1.6225281953811646} 08/31/2021 11:57:31 - INFO - __main__ - Step 125206: {'lr': 3.383496806141334e-05, 'samples': 24039552, 'steps': 125205, 'loss/train': 1.0354022979736328} 08/31/2021 11:57:31 - INFO - __main__ - Step 125207: {'lr': 3.383230222831685e-05, 'samples': 24039744, 'steps': 125206, 'loss/train': 2.2664549350738525} 08/31/2021 11:57:31 - INFO - __main__ - Step 125208: {'lr': 3.3829636492622243e-05, 'samples': 24039936, 'steps': 125207, 'loss/train': 0.5605131387710571} 08/31/2021 11:57:33 - INFO - __main__ - Step 125209: {'lr': 3.382697085433062e-05, 'samples': 24040128, 'steps': 125208, 'loss/train': 0.5899118781089783} 08/31/2021 11:57:33 - INFO - __main__ - Step 125210: {'lr': 3.3824305313443215e-05, 'samples': 24040320, 'steps': 125209, 'loss/train': 1.3774152994155884} 08/31/2021 11:57:34 - INFO - __main__ - Step 125211: {'lr': 3.3821639869961257e-05, 'samples': 24040512, 'steps': 125210, 'loss/train': 0.579396665096283} 08/31/2021 11:57:34 - INFO - __main__ - Step 125212: {'lr': 3.381897452388594e-05, 'samples': 24040704, 'steps': 125211, 'loss/train': 0.9058932662010193} 08/31/2021 11:57:34 - INFO - __main__ - Step 125213: {'lr': 3.381630927521845e-05, 'samples': 24040896, 'steps': 125212, 'loss/train': 0.32922670245170593} 08/31/2021 11:57:37 - INFO - __main__ - Step 125214: {'lr': 3.381364412395998e-05, 'samples': 24041088, 'steps': 125213, 'loss/train': 0.7287160158157349} 08/31/2021 11:57:37 - INFO - __main__ - Step 125215: {'lr': 3.3810979070111744e-05, 'samples': 24041280, 'steps': 125214, 'loss/train': 0.7316281199455261} 08/31/2021 11:57:38 - INFO - __main__ - Step 125216: {'lr': 3.3808314113674963e-05, 'samples': 24041472, 'steps': 125215, 'loss/train': 1.7517890930175781} 08/31/2021 11:57:38 - INFO - __main__ - Step 125217: {'lr': 3.380564925465082e-05, 'samples': 24041664, 'steps': 125216, 'loss/train': 1.852966070175171} 08/31/2021 11:57:38 - INFO - __main__ - Step 125218: {'lr': 3.380298449304051e-05, 'samples': 24041856, 'steps': 125217, 'loss/train': 0.924676775932312} 08/31/2021 11:57:40 - INFO - __main__ - Step 125219: {'lr': 3.3800319828845294e-05, 'samples': 24042048, 'steps': 125218, 'loss/train': 1.2473785877227783} 08/31/2021 11:57:40 - INFO - __main__ - Step 125220: {'lr': 3.379765526206624e-05, 'samples': 24042240, 'steps': 125219, 'loss/train': 0.29984647035598755} 08/31/2021 11:57:40 - INFO - __main__ - Step 125221: {'lr': 3.379499079270465e-05, 'samples': 24042432, 'steps': 125220, 'loss/train': 1.0503228902816772} 08/31/2021 11:57:41 - INFO - __main__ - Step 125222: {'lr': 3.3792326420761715e-05, 'samples': 24042624, 'steps': 125221, 'loss/train': 0.6221190094947815} 08/31/2021 11:57:41 - INFO - __main__ - Step 125223: {'lr': 3.37896621462386e-05, 'samples': 24042816, 'steps': 125222, 'loss/train': 0.9299901127815247} 08/31/2021 11:57:43 - INFO - __main__ - Step 125224: {'lr': 3.378699796913653e-05, 'samples': 24043008, 'steps': 125223, 'loss/train': 1.3945330381393433} 08/31/2021 11:57:43 - INFO - __main__ - Step 125225: {'lr': 3.3784333889456706e-05, 'samples': 24043200, 'steps': 125224, 'loss/train': 0.7954702377319336} 08/31/2021 11:57:44 - INFO - __main__ - Step 125226: {'lr': 3.378166990720033e-05, 'samples': 24043392, 'steps': 125225, 'loss/train': 0.9760582447052002} 08/31/2021 11:57:44 - INFO - __main__ - Step 125227: {'lr': 3.377900602236858e-05, 'samples': 24043584, 'steps': 125226, 'loss/train': 1.2449705600738525} 08/31/2021 11:57:44 - INFO - __main__ - Step 125228: {'lr': 3.3776342234962676e-05, 'samples': 24043776, 'steps': 125227, 'loss/train': 0.03781403601169586} 08/31/2021 11:57:46 - INFO - __main__ - Step 125229: {'lr': 3.3773678544983836e-05, 'samples': 24043968, 'steps': 125228, 'loss/train': 0.8161830902099609} 08/31/2021 11:57:47 - INFO - __main__ - Step 125230: {'lr': 3.3771014952433286e-05, 'samples': 24044160, 'steps': 125229, 'loss/train': 0.6630384922027588} 08/31/2021 11:57:47 - INFO - __main__ - Step 125231: {'lr': 3.3768351457312105e-05, 'samples': 24044352, 'steps': 125230, 'loss/train': 1.528714895248413} 08/31/2021 11:57:47 - INFO - __main__ - Step 125232: {'lr': 3.37656880596216e-05, 'samples': 24044544, 'steps': 125231, 'loss/train': 1.1177207231521606} 08/31/2021 11:57:48 - INFO - __main__ - Step 125233: {'lr': 3.376302475936291e-05, 'samples': 24044736, 'steps': 125232, 'loss/train': 0.150278702378273} 08/31/2021 11:57:49 - INFO - __main__ - Step 125234: {'lr': 3.3760361556537275e-05, 'samples': 24044928, 'steps': 125233, 'loss/train': 1.3700255155563354} 08/31/2021 11:57:50 - INFO - __main__ - Step 125235: {'lr': 3.37576984511459e-05, 'samples': 24045120, 'steps': 125234, 'loss/train': 1.0380749702453613} 08/31/2021 11:57:50 - INFO - __main__ - Step 125236: {'lr': 3.3755035443189946e-05, 'samples': 24045312, 'steps': 125235, 'loss/train': 0.7871172428131104} 08/31/2021 11:57:50 - INFO - __main__ - Step 125237: {'lr': 3.3752372532670664e-05, 'samples': 24045504, 'steps': 125236, 'loss/train': 1.1119451522827148} 08/31/2021 11:57:51 - INFO - __main__ - Step 125238: {'lr': 3.374970971958918e-05, 'samples': 24045696, 'steps': 125237, 'loss/train': 2.2713489532470703} 08/31/2021 11:57:51 - INFO - __main__ - Step 125239: {'lr': 3.374704700394679e-05, 'samples': 24045888, 'steps': 125238, 'loss/train': 0.9288473129272461} 08/31/2021 11:57:53 - INFO - __main__ - Step 125240: {'lr': 3.374438438574462e-05, 'samples': 24046080, 'steps': 125239, 'loss/train': 0.07551177591085434} 08/31/2021 11:57:53 - INFO - __main__ - Step 125241: {'lr': 3.374172186498389e-05, 'samples': 24046272, 'steps': 125240, 'loss/train': 1.0995956659317017} 08/31/2021 11:57:53 - INFO - __main__ - Step 125242: {'lr': 3.3739059441665806e-05, 'samples': 24046464, 'steps': 125241, 'loss/train': 1.2766001224517822} 08/31/2021 11:57:54 - INFO - __main__ - Step 125243: {'lr': 3.373639711579163e-05, 'samples': 24046656, 'steps': 125242, 'loss/train': 1.3078359365463257} 08/31/2021 11:57:54 - INFO - __main__ - Step 125244: {'lr': 3.373373488736242e-05, 'samples': 24046848, 'steps': 125243, 'loss/train': 1.0033738613128662} 08/31/2021 11:57:56 - INFO - __main__ - Step 125245: {'lr': 3.373107275637946e-05, 'samples': 24047040, 'steps': 125244, 'loss/train': 1.0023897886276245} 08/31/2021 11:57:56 - INFO - __main__ - Step 125246: {'lr': 3.3728410722843966e-05, 'samples': 24047232, 'steps': 125245, 'loss/train': 1.4619743824005127} 08/31/2021 11:57:57 - INFO - __main__ - Step 125247: {'lr': 3.372574878675708e-05, 'samples': 24047424, 'steps': 125246, 'loss/train': 1.079255223274231} 08/31/2021 11:57:57 - INFO - __main__ - Step 125248: {'lr': 3.3723086948120066e-05, 'samples': 24047616, 'steps': 125247, 'loss/train': 0.6467742323875427} 08/31/2021 11:57:57 - INFO - __main__ - Step 125249: {'lr': 3.372042520693405e-05, 'samples': 24047808, 'steps': 125248, 'loss/train': 1.6401588916778564} 08/31/2021 11:57:59 - INFO - __main__ - Step 125250: {'lr': 3.371776356320031e-05, 'samples': 24048000, 'steps': 125249, 'loss/train': 1.3307530879974365} 08/31/2021 11:57:59 - INFO - __main__ - Step 125251: {'lr': 3.371510201691999e-05, 'samples': 24048192, 'steps': 125250, 'loss/train': 1.121232271194458} 08/31/2021 11:58:00 - INFO - __main__ - Step 125252: {'lr': 3.371244056809431e-05, 'samples': 24048384, 'steps': 125251, 'loss/train': 1.1188982725143433} 08/31/2021 11:58:00 - INFO - __main__ - Step 125253: {'lr': 3.370977921672447e-05, 'samples': 24048576, 'steps': 125252, 'loss/train': 1.274972915649414} 08/31/2021 11:58:00 - INFO - __main__ - Step 125254: {'lr': 3.370711796281167e-05, 'samples': 24048768, 'steps': 125253, 'loss/train': 0.9213316440582275} 08/31/2021 11:58:02 - INFO - __main__ - Step 125255: {'lr': 3.3704456806357085e-05, 'samples': 24048960, 'steps': 125254, 'loss/train': 1.327263355255127} 08/31/2021 11:58:02 - INFO - __main__ - Step 125256: {'lr': 3.3701795747362014e-05, 'samples': 24049152, 'steps': 125255, 'loss/train': 1.2036030292510986} 08/31/2021 11:58:03 - INFO - __main__ - Step 125257: {'lr': 3.369913478582751e-05, 'samples': 24049344, 'steps': 125256, 'loss/train': 1.223250150680542} 08/31/2021 11:58:03 - INFO - __main__ - Step 125258: {'lr': 3.3696473921754844e-05, 'samples': 24049536, 'steps': 125257, 'loss/train': 1.1916100978851318} 08/31/2021 11:58:03 - INFO - __main__ - Step 125259: {'lr': 3.369381315514522e-05, 'samples': 24049728, 'steps': 125258, 'loss/train': 0.6869860291481018} 08/31/2021 11:58:05 - INFO - __main__ - Step 125260: {'lr': 3.36911524859998e-05, 'samples': 24049920, 'steps': 125259, 'loss/train': 0.9496067762374878} 08/31/2021 11:58:05 - INFO - __main__ - Step 125261: {'lr': 3.368849191431983e-05, 'samples': 24050112, 'steps': 125260, 'loss/train': 1.4158387184143066} 08/31/2021 11:58:06 - INFO - __main__ - Step 125262: {'lr': 3.3685831440106454e-05, 'samples': 24050304, 'steps': 125261, 'loss/train': 1.3049590587615967} 08/31/2021 11:58:06 - INFO - __main__ - Step 125263: {'lr': 3.368317106336094e-05, 'samples': 24050496, 'steps': 125262, 'loss/train': 0.9009478688240051} 08/31/2021 11:58:06 - INFO - __main__ - Step 125264: {'lr': 3.368051078408443e-05, 'samples': 24050688, 'steps': 125263, 'loss/train': 1.430585265159607} 08/31/2021 11:58:08 - INFO - __main__ - Step 125265: {'lr': 3.367785060227816e-05, 'samples': 24050880, 'steps': 125264, 'loss/train': 0.6796979904174805} 08/31/2021 11:58:09 - INFO - __main__ - Step 125266: {'lr': 3.367519051794329e-05, 'samples': 24051072, 'steps': 125265, 'loss/train': 1.0067954063415527} 08/31/2021 11:58:09 - INFO - __main__ - Step 125267: {'lr': 3.3672530531081074e-05, 'samples': 24051264, 'steps': 125266, 'loss/train': 0.7126761674880981} 08/31/2021 11:58:10 - INFO - __main__ - Step 125268: {'lr': 3.3669870641692664e-05, 'samples': 24051456, 'steps': 125267, 'loss/train': 0.9628982543945312} 08/31/2021 11:58:10 - INFO - __main__ - Step 125269: {'lr': 3.366721084977925e-05, 'samples': 24051648, 'steps': 125268, 'loss/train': 1.6804676055908203} 08/31/2021 11:58:12 - INFO - __main__ - Step 125270: {'lr': 3.3664551155342145e-05, 'samples': 24051840, 'steps': 125269, 'loss/train': 1.0304094552993774} 08/31/2021 11:58:12 - INFO - __main__ - Step 125271: {'lr': 3.3661891558382366e-05, 'samples': 24052032, 'steps': 125270, 'loss/train': 0.6665109992027283} 08/31/2021 11:58:13 - INFO - __main__ - Step 125272: {'lr': 3.3659232058901227e-05, 'samples': 24052224, 'steps': 125271, 'loss/train': 1.259332299232483} 08/31/2021 11:58:13 - INFO - __main__ - Step 125273: {'lr': 3.3656572656899864e-05, 'samples': 24052416, 'steps': 125272, 'loss/train': 0.6541005373001099} 08/31/2021 11:58:13 - INFO - __main__ - Step 125274: {'lr': 3.365391335237955e-05, 'samples': 24052608, 'steps': 125273, 'loss/train': 1.0842795372009277} 08/31/2021 11:58:14 - INFO - __main__ - Step 125275: {'lr': 3.365125414534142e-05, 'samples': 24052800, 'steps': 125274, 'loss/train': 0.050361763685941696} 08/31/2021 11:58:16 - INFO - __main__ - Step 125276: {'lr': 3.364859503578671e-05, 'samples': 24052992, 'steps': 125275, 'loss/train': 1.369575023651123} 08/31/2021 11:58:16 - INFO - __main__ - Step 125277: {'lr': 3.36459360237166e-05, 'samples': 24053184, 'steps': 125276, 'loss/train': 1.2122759819030762} 08/31/2021 11:58:17 - INFO - __main__ - Step 125278: {'lr': 3.364327710913229e-05, 'samples': 24053376, 'steps': 125277, 'loss/train': 1.166411280632019} 08/31/2021 11:58:17 - INFO - __main__ - Step 125279: {'lr': 3.364061829203499e-05, 'samples': 24053568, 'steps': 125278, 'loss/train': 1.2719064950942993} 08/31/2021 11:58:17 - INFO - __main__ - Step 125280: {'lr': 3.363795957242588e-05, 'samples': 24053760, 'steps': 125279, 'loss/train': 1.2676013708114624} 08/31/2021 11:58:19 - INFO - __main__ - Step 125281: {'lr': 3.363530095030617e-05, 'samples': 24053952, 'steps': 125280, 'loss/train': 0.06364522129297256} 08/31/2021 11:58:19 - INFO - __main__ - Step 125282: {'lr': 3.363264242567704e-05, 'samples': 24054144, 'steps': 125281, 'loss/train': 0.5025896430015564} 08/31/2021 11:58:20 - INFO - __main__ - Step 125283: {'lr': 3.362998399853978e-05, 'samples': 24054336, 'steps': 125282, 'loss/train': 0.9250074625015259} 08/31/2021 11:58:20 - INFO - __main__ - Step 125284: {'lr': 3.362732566889545e-05, 'samples': 24054528, 'steps': 125283, 'loss/train': 1.080807089805603} 08/31/2021 11:58:20 - INFO - __main__ - Step 125285: {'lr': 3.3624667436745305e-05, 'samples': 24054720, 'steps': 125284, 'loss/train': 1.1305112838745117} 08/31/2021 11:58:22 - INFO - __main__ - Step 125286: {'lr': 3.362200930209053e-05, 'samples': 24054912, 'steps': 125285, 'loss/train': 0.19492238759994507} 08/31/2021 11:58:22 - INFO - __main__ - Step 125287: {'lr': 3.3619351264932375e-05, 'samples': 24055104, 'steps': 125286, 'loss/train': 1.3891597986221313} 08/31/2021 11:58:23 - INFO - __main__ - Step 125288: {'lr': 3.361669332527198e-05, 'samples': 24055296, 'steps': 125287, 'loss/train': 0.9337748885154724} 08/31/2021 11:58:23 - INFO - __main__ - Step 125289: {'lr': 3.3614035483110537e-05, 'samples': 24055488, 'steps': 125288, 'loss/train': 0.8431785106658936} 08/31/2021 11:58:24 - INFO - __main__ - Step 125290: {'lr': 3.36113777384493e-05, 'samples': 24055680, 'steps': 125289, 'loss/train': 1.240801453590393} 08/31/2021 11:58:25 - INFO - __main__ - Step 125291: {'lr': 3.360872009128946e-05, 'samples': 24055872, 'steps': 125290, 'loss/train': 1.3647617101669312} 08/31/2021 11:58:26 - INFO - __main__ - Step 125292: {'lr': 3.360606254163215e-05, 'samples': 24056064, 'steps': 125291, 'loss/train': 1.6067278385162354} 08/31/2021 11:58:26 - INFO - __main__ - Step 125293: {'lr': 3.360340508947862e-05, 'samples': 24056256, 'steps': 125292, 'loss/train': 1.1977179050445557} 08/31/2021 11:58:26 - INFO - __main__ - Step 125294: {'lr': 3.360074773483007e-05, 'samples': 24056448, 'steps': 125293, 'loss/train': 1.1596035957336426} 08/31/2021 11:58:27 - INFO - __main__ - Step 125295: {'lr': 3.3598090477687665e-05, 'samples': 24056640, 'steps': 125294, 'loss/train': 0.03625313192605972} 08/31/2021 11:58:28 - INFO - __main__ - Step 125296: {'lr': 3.359543331805265e-05, 'samples': 24056832, 'steps': 125295, 'loss/train': 0.9393741488456726} 08/31/2021 11:58:29 - INFO - __main__ - Step 125297: {'lr': 3.3592776255926217e-05, 'samples': 24057024, 'steps': 125296, 'loss/train': 1.2154152393341064} 08/31/2021 11:58:29 - INFO - __main__ - Step 125298: {'lr': 3.3590119291309505e-05, 'samples': 24057216, 'steps': 125297, 'loss/train': 1.236836552619934} 08/31/2021 11:58:29 - INFO - __main__ - Step 125299: {'lr': 3.358746242420374e-05, 'samples': 24057408, 'steps': 125298, 'loss/train': 1.5805805921554565} 08/31/2021 11:58:30 - INFO - __main__ - Step 125300: {'lr': 3.358480565461011e-05, 'samples': 24057600, 'steps': 125299, 'loss/train': 0.6021457314491272} 08/31/2021 11:58:30 - INFO - __main__ - Step 125301: {'lr': 3.358214898252987e-05, 'samples': 24057792, 'steps': 125300, 'loss/train': 0.781407356262207} 08/31/2021 11:58:31 - INFO - __main__ - Step 125302: {'lr': 3.3579492407964126e-05, 'samples': 24057984, 'steps': 125301, 'loss/train': 1.4812058210372925} 08/31/2021 11:58:32 - INFO - __main__ - Step 125303: {'lr': 3.357683593091415e-05, 'samples': 24058176, 'steps': 125302, 'loss/train': 0.3056199550628662} 08/31/2021 11:58:32 - INFO - __main__ - Step 125304: {'lr': 3.357417955138109e-05, 'samples': 24058368, 'steps': 125303, 'loss/train': 1.2320795059204102} 08/31/2021 11:58:33 - INFO - __main__ - Step 125305: {'lr': 3.3571523269366186e-05, 'samples': 24058560, 'steps': 125304, 'loss/train': 0.557941734790802} 08/31/2021 11:58:33 - INFO - __main__ - Step 125306: {'lr': 3.3568867084870614e-05, 'samples': 24058752, 'steps': 125305, 'loss/train': 1.301986575126648} 08/31/2021 11:58:34 - INFO - __main__ - Step 125307: {'lr': 3.356621099789556e-05, 'samples': 24058944, 'steps': 125306, 'loss/train': 1.0278732776641846} 08/31/2021 11:58:35 - INFO - __main__ - Step 125308: {'lr': 3.3563555008442244e-05, 'samples': 24059136, 'steps': 125307, 'loss/train': 1.3028113842010498} 08/31/2021 11:58:35 - INFO - __main__ - Step 125309: {'lr': 3.356089911651183e-05, 'samples': 24059328, 'steps': 125308, 'loss/train': 1.5186221599578857} 08/31/2021 11:58:36 - INFO - __main__ - Step 125310: {'lr': 3.355824332210561e-05, 'samples': 24059520, 'steps': 125309, 'loss/train': 0.3656485676765442} 08/31/2021 11:58:36 - INFO - __main__ - Step 125311: {'lr': 3.355558762522465e-05, 'samples': 24059712, 'steps': 125310, 'loss/train': 0.929407000541687} 08/31/2021 11:58:38 - INFO - __main__ - Step 125312: {'lr': 3.355293202587018e-05, 'samples': 24059904, 'steps': 125311, 'loss/train': 1.210306167602539} 08/31/2021 11:58:39 - INFO - __main__ - Step 125313: {'lr': 3.355027652404344e-05, 'samples': 24060096, 'steps': 125312, 'loss/train': 1.5626602172851562} 08/31/2021 11:58:39 - INFO - __main__ - Step 125314: {'lr': 3.3547621119745605e-05, 'samples': 24060288, 'steps': 125313, 'loss/train': 0.27851977944374084} 08/31/2021 11:58:40 - INFO - __main__ - Step 125315: {'lr': 3.354496581297786e-05, 'samples': 24060480, 'steps': 125314, 'loss/train': 0.24807743728160858} 08/31/2021 11:58:40 - INFO - __main__ - Step 125316: {'lr': 3.354231060374141e-05, 'samples': 24060672, 'steps': 125315, 'loss/train': 0.24118217825889587} 08/31/2021 11:58:40 - INFO - __main__ - Step 125317: {'lr': 3.353965549203747e-05, 'samples': 24060864, 'steps': 125316, 'loss/train': 0.790408194065094} 08/31/2021 11:58:42 - INFO - __main__ - Step 125318: {'lr': 3.353700047786723e-05, 'samples': 24061056, 'steps': 125317, 'loss/train': 1.339882254600525} 08/31/2021 11:58:43 - INFO - __main__ - Step 125319: {'lr': 3.353434556123186e-05, 'samples': 24061248, 'steps': 125318, 'loss/train': 0.7160989046096802} 08/31/2021 11:58:43 - INFO - __main__ - Step 125320: {'lr': 3.3531690742132554e-05, 'samples': 24061440, 'steps': 125319, 'loss/train': 1.6909079551696777} 08/31/2021 11:58:43 - INFO - __main__ - Step 125321: {'lr': 3.3529036020570556e-05, 'samples': 24061632, 'steps': 125320, 'loss/train': 1.037003517150879} 08/31/2021 11:58:44 - INFO - __main__ - Step 125322: {'lr': 3.352638139654704e-05, 'samples': 24061824, 'steps': 125321, 'loss/train': 0.6366975903511047} 08/31/2021 11:58:46 - INFO - __main__ - Step 125323: {'lr': 3.3523726870063194e-05, 'samples': 24062016, 'steps': 125322, 'loss/train': 0.9470219612121582} 08/31/2021 11:58:46 - INFO - __main__ - Step 125324: {'lr': 3.3521072441120234e-05, 'samples': 24062208, 'steps': 125323, 'loss/train': 0.6184588074684143} 08/31/2021 11:58:46 - INFO - __main__ - Step 125325: {'lr': 3.351841810971931e-05, 'samples': 24062400, 'steps': 125324, 'loss/train': 0.6758098602294922} 08/31/2021 11:58:47 - INFO - __main__ - Step 125326: {'lr': 3.351576387586167e-05, 'samples': 24062592, 'steps': 125325, 'loss/train': 1.0646919012069702} 08/31/2021 11:58:47 - INFO - __main__ - Step 125327: {'lr': 3.3513109739548465e-05, 'samples': 24062784, 'steps': 125326, 'loss/train': 1.401407241821289} 08/31/2021 11:58:47 - INFO - __main__ - Step 125328: {'lr': 3.35104557007809e-05, 'samples': 24062976, 'steps': 125327, 'loss/train': 0.9280609488487244} 08/31/2021 11:58:49 - INFO - __main__ - Step 125329: {'lr': 3.3507801759560194e-05, 'samples': 24063168, 'steps': 125328, 'loss/train': 0.06236818805336952} 08/31/2021 11:58:50 - INFO - __main__ - Step 125330: {'lr': 3.350514791588752e-05, 'samples': 24063360, 'steps': 125329, 'loss/train': 0.36527010798454285} 08/31/2021 11:58:50 - INFO - __main__ - Step 125331: {'lr': 3.3502494169764115e-05, 'samples': 24063552, 'steps': 125330, 'loss/train': 1.0125267505645752} 08/31/2021 11:58:50 - INFO - __main__ - Step 125332: {'lr': 3.349984052119112e-05, 'samples': 24063744, 'steps': 125331, 'loss/train': 0.7135643362998962} 08/31/2021 11:58:51 - INFO - __main__ - Step 125333: {'lr': 3.349718697016976e-05, 'samples': 24063936, 'steps': 125332, 'loss/train': 0.5892207622528076} 08/31/2021 11:58:52 - INFO - __main__ - Step 125334: {'lr': 3.349453351670123e-05, 'samples': 24064128, 'steps': 125333, 'loss/train': 1.837188959121704} 08/31/2021 11:58:53 - INFO - __main__ - Step 125335: {'lr': 3.349188016078672e-05, 'samples': 24064320, 'steps': 125334, 'loss/train': 0.579458475112915} 08/31/2021 11:58:53 - INFO - __main__ - Step 125336: {'lr': 3.348922690242742e-05, 'samples': 24064512, 'steps': 125335, 'loss/train': 0.9179442524909973} 08/31/2021 11:58:54 - INFO - __main__ - Step 125337: {'lr': 3.3486573741624615e-05, 'samples': 24064704, 'steps': 125336, 'loss/train': 0.329723060131073} 08/31/2021 11:58:54 - INFO - __main__ - Step 125338: {'lr': 3.348392067837935e-05, 'samples': 24064896, 'steps': 125337, 'loss/train': 0.8967582583427429} 08/31/2021 11:58:56 - INFO - __main__ - Step 125339: {'lr': 3.348126771269289e-05, 'samples': 24065088, 'steps': 125338, 'loss/train': 0.9419573545455933} 08/31/2021 11:58:56 - INFO - __main__ - Step 125340: {'lr': 3.347861484456641e-05, 'samples': 24065280, 'steps': 125339, 'loss/train': 1.249276041984558} 08/31/2021 11:58:56 - INFO - __main__ - Step 125341: {'lr': 3.347596207400114e-05, 'samples': 24065472, 'steps': 125340, 'loss/train': 5.616274833679199} 08/31/2021 11:58:57 - INFO - __main__ - Step 125342: {'lr': 3.347330940099827e-05, 'samples': 24065664, 'steps': 125341, 'loss/train': 0.5329294204711914} 08/31/2021 11:58:57 - INFO - __main__ - Step 125343: {'lr': 3.347065682555897e-05, 'samples': 24065856, 'steps': 125342, 'loss/train': 0.7266084551811218} 08/31/2021 11:58:57 - INFO - __main__ - Step 125344: {'lr': 3.346800434768446e-05, 'samples': 24066048, 'steps': 125343, 'loss/train': 1.6936925649642944} 08/31/2021 11:58:59 - INFO - __main__ - Step 125345: {'lr': 3.346535196737593e-05, 'samples': 24066240, 'steps': 125344, 'loss/train': 1.0864810943603516} 08/31/2021 11:58:59 - INFO - __main__ - Step 125346: {'lr': 3.346269968463456e-05, 'samples': 24066432, 'steps': 125345, 'loss/train': 1.2975765466690063} 08/31/2021 11:59:00 - INFO - __main__ - Step 125347: {'lr': 3.346004749946158e-05, 'samples': 24066624, 'steps': 125346, 'loss/train': 1.4887539148330688} 08/31/2021 11:59:00 - INFO - __main__ - Step 125348: {'lr': 3.345739541185813e-05, 'samples': 24066816, 'steps': 125347, 'loss/train': 0.8100529313087463} 08/31/2021 11:59:00 - INFO - __main__ - Step 125349: {'lr': 3.3454743421825445e-05, 'samples': 24067008, 'steps': 125348, 'loss/train': 1.3111087083816528} 08/31/2021 11:59:02 - INFO - __main__ - Step 125350: {'lr': 3.3452091529364706e-05, 'samples': 24067200, 'steps': 125349, 'loss/train': 1.083025574684143} 08/31/2021 11:59:03 - INFO - __main__ - Step 125351: {'lr': 3.34494397344772e-05, 'samples': 24067392, 'steps': 125350, 'loss/train': 1.454925537109375} 08/31/2021 11:59:03 - INFO - __main__ - Step 125352: {'lr': 3.3446788037163943e-05, 'samples': 24067584, 'steps': 125351, 'loss/train': 1.2827575206756592} 08/31/2021 11:59:03 - INFO - __main__ - Step 125353: {'lr': 3.344413643742625e-05, 'samples': 24067776, 'steps': 125352, 'loss/train': 0.8662033081054688} 08/31/2021 11:59:04 - INFO - __main__ - Step 125354: {'lr': 3.344148493526525e-05, 'samples': 24067968, 'steps': 125353, 'loss/train': 1.091468334197998} 08/31/2021 11:59:04 - INFO - __main__ - Step 125355: {'lr': 3.3438833530682194e-05, 'samples': 24068160, 'steps': 125354, 'loss/train': 1.4675978422164917} 08/31/2021 11:59:06 - INFO - __main__ - Step 125356: {'lr': 3.343618222367828e-05, 'samples': 24068352, 'steps': 125355, 'loss/train': 1.2688405513763428} 08/31/2021 11:59:06 - INFO - __main__ - Step 125357: {'lr': 3.343353101425467e-05, 'samples': 24068544, 'steps': 125356, 'loss/train': 0.3059135973453522} 08/31/2021 11:59:06 - INFO - __main__ - Step 125358: {'lr': 3.343087990241256e-05, 'samples': 24068736, 'steps': 125357, 'loss/train': 0.9545403718948364} 08/31/2021 11:59:07 - INFO - __main__ - Step 125359: {'lr': 3.342822888815314e-05, 'samples': 24068928, 'steps': 125358, 'loss/train': 0.02862859144806862} 08/31/2021 11:59:09 - INFO - __main__ - Step 125360: {'lr': 3.3425577971477636e-05, 'samples': 24069120, 'steps': 125359, 'loss/train': 0.2922322452068329} 08/31/2021 11:59:10 - INFO - __main__ - Step 125361: {'lr': 3.342292715238723e-05, 'samples': 24069312, 'steps': 125360, 'loss/train': 1.6834207773208618} 08/31/2021 11:59:10 - INFO - __main__ - Step 125362: {'lr': 3.342027643088311e-05, 'samples': 24069504, 'steps': 125361, 'loss/train': 0.28512290120124817} 08/31/2021 11:59:11 - INFO - __main__ - Step 125363: {'lr': 3.3417625806966444e-05, 'samples': 24069696, 'steps': 125362, 'loss/train': 0.24678368866443634} 08/31/2021 11:59:11 - INFO - __main__ - Step 125364: {'lr': 3.3414975280638525e-05, 'samples': 24069888, 'steps': 125363, 'loss/train': 0.1846407949924469} 08/31/2021 11:59:11 - INFO - __main__ - Step 125365: {'lr': 3.341232485190043e-05, 'samples': 24070080, 'steps': 125364, 'loss/train': 1.4530731439590454} 08/31/2021 11:59:12 - INFO - __main__ - Step 125366: {'lr': 3.3409674520753385e-05, 'samples': 24070272, 'steps': 125365, 'loss/train': 0.9130125045776367} 08/31/2021 11:59:13 - INFO - __main__ - Step 125367: {'lr': 3.3407024287198636e-05, 'samples': 24070464, 'steps': 125366, 'loss/train': 0.7792665958404541} 08/31/2021 11:59:14 - INFO - __main__ - Step 125368: {'lr': 3.340437415123729e-05, 'samples': 24070656, 'steps': 125367, 'loss/train': 0.8287553787231445} 08/31/2021 11:59:14 - INFO - __main__ - Step 125369: {'lr': 3.3401724112870625e-05, 'samples': 24070848, 'steps': 125368, 'loss/train': 0.3506665527820587} 08/31/2021 11:59:14 - INFO - __main__ - Step 125370: {'lr': 3.339907417209978e-05, 'samples': 24071040, 'steps': 125369, 'loss/train': 0.9648920893669128} 08/31/2021 11:59:15 - INFO - __main__ - Step 125371: {'lr': 3.339642432892598e-05, 'samples': 24071232, 'steps': 125370, 'loss/train': 0.9993234276771545} 08/31/2021 11:59:16 - INFO - __main__ - Step 125372: {'lr': 3.339377458335041e-05, 'samples': 24071424, 'steps': 125371, 'loss/train': 0.537565290927887} 08/31/2021 11:59:17 - INFO - __main__ - Step 125373: {'lr': 3.339112493537425e-05, 'samples': 24071616, 'steps': 125372, 'loss/train': 1.1766940355300903} 08/31/2021 11:59:17 - INFO - __main__ - Step 125374: {'lr': 3.338847538499873e-05, 'samples': 24071808, 'steps': 125373, 'loss/train': 0.8889238834381104} 08/31/2021 11:59:17 - INFO - __main__ - Step 125375: {'lr': 3.3385825932225004e-05, 'samples': 24072000, 'steps': 125374, 'loss/train': 0.02933392859995365} 08/31/2021 11:59:18 - INFO - __main__ - Step 125376: {'lr': 3.3383176577054284e-05, 'samples': 24072192, 'steps': 125375, 'loss/train': 0.6987015008926392} 08/31/2021 11:59:20 - INFO - __main__ - Step 125377: {'lr': 3.338052731948782e-05, 'samples': 24072384, 'steps': 125376, 'loss/train': 1.2454345226287842} 08/31/2021 11:59:20 - INFO - __main__ - Step 125378: {'lr': 3.337787815952667e-05, 'samples': 24072576, 'steps': 125377, 'loss/train': 0.6154746413230896} 08/31/2021 11:59:21 - INFO - __main__ - Step 125379: {'lr': 3.337522909717214e-05, 'samples': 24072768, 'steps': 125378, 'loss/train': 1.3498976230621338} 08/31/2021 11:59:21 - INFO - __main__ - Step 125380: {'lr': 3.337258013242536e-05, 'samples': 24072960, 'steps': 125379, 'loss/train': 1.2442883253097534} 08/31/2021 11:59:21 - INFO - __main__ - Step 125381: {'lr': 3.336993126528759e-05, 'samples': 24073152, 'steps': 125380, 'loss/train': 1.1039224863052368} 08/31/2021 11:59:22 - INFO - __main__ - Step 125382: {'lr': 3.336728249575996e-05, 'samples': 24073344, 'steps': 125381, 'loss/train': 0.9895538091659546} 08/31/2021 11:59:23 - INFO - __main__ - Step 125383: {'lr': 3.336463382384369e-05, 'samples': 24073536, 'steps': 125382, 'loss/train': 0.027258766815066338} 08/31/2021 11:59:24 - INFO - __main__ - Step 125384: {'lr': 3.336198524953998e-05, 'samples': 24073728, 'steps': 125383, 'loss/train': 1.0358763933181763} 08/31/2021 11:59:24 - INFO - __main__ - Step 125385: {'lr': 3.3359336772849994e-05, 'samples': 24073920, 'steps': 125384, 'loss/train': 1.509063482284546} 08/31/2021 11:59:24 - INFO - __main__ - Step 125386: {'lr': 3.3356688393774984e-05, 'samples': 24074112, 'steps': 125385, 'loss/train': 0.4673680067062378} 08/31/2021 11:59:25 - INFO - __main__ - Step 125387: {'lr': 3.3354040112316076e-05, 'samples': 24074304, 'steps': 125386, 'loss/train': 1.1796714067459106} 08/31/2021 11:59:26 - INFO - __main__ - Step 125388: {'lr': 3.335139192847453e-05, 'samples': 24074496, 'steps': 125387, 'loss/train': 0.6134635210037231} 08/31/2021 11:59:27 - INFO - __main__ - Step 125389: {'lr': 3.334874384225148e-05, 'samples': 24074688, 'steps': 125388, 'loss/train': 1.1888587474822998} 08/31/2021 11:59:27 - INFO - __main__ - Step 125390: {'lr': 3.334609585364815e-05, 'samples': 24074880, 'steps': 125389, 'loss/train': 0.9645047783851624} 08/31/2021 11:59:27 - INFO - __main__ - Step 125391: {'lr': 3.334344796266575e-05, 'samples': 24075072, 'steps': 125390, 'loss/train': 1.2403522729873657} 08/31/2021 11:59:28 - INFO - __main__ - Step 125392: {'lr': 3.334080016930544e-05, 'samples': 24075264, 'steps': 125391, 'loss/train': 0.7810295820236206} 08/31/2021 11:59:29 - INFO - __main__ - Step 125393: {'lr': 3.333815247356839e-05, 'samples': 24075456, 'steps': 125392, 'loss/train': 1.048749327659607} 08/31/2021 11:59:30 - INFO - __main__ - Step 125394: {'lr': 3.333550487545583e-05, 'samples': 24075648, 'steps': 125393, 'loss/train': 0.9181644320487976} 08/31/2021 11:59:30 - INFO - __main__ - Step 125395: {'lr': 3.3332857374968966e-05, 'samples': 24075840, 'steps': 125394, 'loss/train': 0.8881483674049377} 08/31/2021 11:59:30 - INFO - __main__ - Step 125396: {'lr': 3.3330209972108976e-05, 'samples': 24076032, 'steps': 125395, 'loss/train': 0.8404076099395752} 08/31/2021 11:59:31 - INFO - __main__ - Step 125397: {'lr': 3.3327562666877034e-05, 'samples': 24076224, 'steps': 125396, 'loss/train': 1.624829888343811} 08/31/2021 11:59:32 - INFO - __main__ - Step 125398: {'lr': 3.3324915459274353e-05, 'samples': 24076416, 'steps': 125397, 'loss/train': 1.1418126821517944} 08/31/2021 11:59:33 - INFO - __main__ - Step 125399: {'lr': 3.332226834930211e-05, 'samples': 24076608, 'steps': 125398, 'loss/train': 0.7108935713768005} 08/31/2021 11:59:33 - INFO - __main__ - Step 125400: {'lr': 3.331962133696151e-05, 'samples': 24076800, 'steps': 125399, 'loss/train': 1.21806001663208} 08/31/2021 11:59:33 - INFO - __main__ - Step 125401: {'lr': 3.331697442225376e-05, 'samples': 24076992, 'steps': 125400, 'loss/train': 0.6979010105133057} 08/31/2021 11:59:34 - INFO - __main__ - Step 125402: {'lr': 3.331432760518005e-05, 'samples': 24077184, 'steps': 125401, 'loss/train': 1.1060289144515991} 08/31/2021 11:59:35 - INFO - __main__ - Step 125403: {'lr': 3.331168088574152e-05, 'samples': 24077376, 'steps': 125402, 'loss/train': 0.6695877909660339} 08/31/2021 11:59:36 - INFO - __main__ - Step 125404: {'lr': 3.33090342639395e-05, 'samples': 24077568, 'steps': 125403, 'loss/train': 0.7520373463630676} 08/31/2021 11:59:36 - INFO - __main__ - Step 125405: {'lr': 3.330638773977501e-05, 'samples': 24077760, 'steps': 125404, 'loss/train': 1.3900282382965088} 08/31/2021 11:59:36 - INFO - __main__ - Step 125406: {'lr': 3.3303741313249314e-05, 'samples': 24077952, 'steps': 125405, 'loss/train': 0.29393523931503296} 08/31/2021 11:59:37 - INFO - __main__ - Step 125407: {'lr': 3.330109498436362e-05, 'samples': 24078144, 'steps': 125406, 'loss/train': 1.1509051322937012} 08/31/2021 11:59:38 - INFO - __main__ - Step 125408: {'lr': 3.32984487531191e-05, 'samples': 24078336, 'steps': 125407, 'loss/train': 1.8527055978775024} 08/31/2021 11:59:39 - INFO - __main__ - Step 125409: {'lr': 3.329580261951695e-05, 'samples': 24078528, 'steps': 125408, 'loss/train': 1.4375194311141968} 08/31/2021 11:59:39 - INFO - __main__ - Step 125410: {'lr': 3.329315658355839e-05, 'samples': 24078720, 'steps': 125409, 'loss/train': 1.7125389575958252} 08/31/2021 11:59:39 - INFO - __main__ - Step 125411: {'lr': 3.329051064524455e-05, 'samples': 24078912, 'steps': 125410, 'loss/train': 1.0354100465774536} 08/31/2021 11:59:40 - INFO - __main__ - Step 125412: {'lr': 3.3287864804576686e-05, 'samples': 24079104, 'steps': 125411, 'loss/train': 0.9001603126525879} 08/31/2021 11:59:41 - INFO - __main__ - Step 125413: {'lr': 3.328521906155599e-05, 'samples': 24079296, 'steps': 125412, 'loss/train': 0.8784932494163513} 08/31/2021 11:59:41 - INFO - __main__ - Step 125414: {'lr': 3.32825734161836e-05, 'samples': 24079488, 'steps': 125413, 'loss/train': 1.248055100440979} 08/31/2021 11:59:42 - INFO - __main__ - Step 125415: {'lr': 3.327992786846073e-05, 'samples': 24079680, 'steps': 125414, 'loss/train': 1.197890043258667} 08/31/2021 11:59:42 - INFO - __main__ - Step 125416: {'lr': 3.3277282418388595e-05, 'samples': 24079872, 'steps': 125415, 'loss/train': 0.8180666565895081} 08/31/2021 11:59:42 - INFO - __main__ - Step 125417: {'lr': 3.3274637065968365e-05, 'samples': 24080064, 'steps': 125416, 'loss/train': 1.0411702394485474} 08/31/2021 11:59:44 - INFO - __main__ - Step 125418: {'lr': 3.3271991811201303e-05, 'samples': 24080256, 'steps': 125417, 'loss/train': 1.1691948175430298} 08/31/2021 11:59:44 - INFO - __main__ - Step 125419: {'lr': 3.326934665408848e-05, 'samples': 24080448, 'steps': 125418, 'loss/train': 0.6270464658737183} 08/31/2021 11:59:45 - INFO - __main__ - Step 125420: {'lr': 3.326670159463116e-05, 'samples': 24080640, 'steps': 125419, 'loss/train': 0.8773064613342285} 08/31/2021 11:59:45 - INFO - __main__ - Step 125421: {'lr': 3.32640566328305e-05, 'samples': 24080832, 'steps': 125420, 'loss/train': 1.4836716651916504} 08/31/2021 11:59:46 - INFO - __main__ - Step 125422: {'lr': 3.3261411768687715e-05, 'samples': 24081024, 'steps': 125421, 'loss/train': 0.9037099480628967} 08/31/2021 11:59:46 - INFO - __main__ - Step 125423: {'lr': 3.325876700220401e-05, 'samples': 24081216, 'steps': 125422, 'loss/train': 1.557035207748413} 08/31/2021 11:59:48 - INFO - __main__ - Step 125424: {'lr': 3.325612233338054e-05, 'samples': 24081408, 'steps': 125423, 'loss/train': 0.9485271573066711} 08/31/2021 11:59:48 - INFO - __main__ - Step 125425: {'lr': 3.3253477762218515e-05, 'samples': 24081600, 'steps': 125424, 'loss/train': 1.9640703201293945} 08/31/2021 11:59:48 - INFO - __main__ - Step 125426: {'lr': 3.325083328871914e-05, 'samples': 24081792, 'steps': 125425, 'loss/train': 1.5021005868911743} 08/31/2021 11:59:49 - INFO - __main__ - Step 125427: {'lr': 3.3248188912883584e-05, 'samples': 24081984, 'steps': 125426, 'loss/train': 0.961524248123169} 08/31/2021 11:59:49 - INFO - __main__ - Step 125428: {'lr': 3.3245544634713045e-05, 'samples': 24082176, 'steps': 125427, 'loss/train': 1.0108568668365479} 08/31/2021 11:59:51 - INFO - __main__ - Step 125429: {'lr': 3.3242900454208746e-05, 'samples': 24082368, 'steps': 125428, 'loss/train': 0.6197198033332825} 08/31/2021 11:59:51 - INFO - __main__ - Step 125430: {'lr': 3.3240256371371845e-05, 'samples': 24082560, 'steps': 125429, 'loss/train': 1.107252836227417} 08/31/2021 11:59:51 - INFO - __main__ - Step 125431: {'lr': 3.323761238620357e-05, 'samples': 24082752, 'steps': 125430, 'loss/train': 0.41939103603363037} 08/31/2021 11:59:52 - INFO - __main__ - Step 125432: {'lr': 3.3234968498705056e-05, 'samples': 24082944, 'steps': 125431, 'loss/train': 0.3270242512226105} 08/31/2021 11:59:52 - INFO - __main__ - Step 125433: {'lr': 3.323232470887749e-05, 'samples': 24083136, 'steps': 125432, 'loss/train': 0.7857603430747986} 08/31/2021 11:59:54 - INFO - __main__ - Step 125434: {'lr': 3.322968101672211e-05, 'samples': 24083328, 'steps': 125433, 'loss/train': 0.9755373597145081} 08/31/2021 11:59:55 - INFO - __main__ - Step 125435: {'lr': 3.322703742224009e-05, 'samples': 24083520, 'steps': 125434, 'loss/train': 0.9517489075660706} 08/31/2021 11:59:55 - INFO - __main__ - Step 125436: {'lr': 3.322439392543264e-05, 'samples': 24083712, 'steps': 125435, 'loss/train': 1.5291566848754883} 08/31/2021 11:59:55 - INFO - __main__ - Step 125437: {'lr': 3.322175052630092e-05, 'samples': 24083904, 'steps': 125436, 'loss/train': 0.13014595210552216} 08/31/2021 11:59:56 - INFO - __main__ - Step 125438: {'lr': 3.321910722484611e-05, 'samples': 24084096, 'steps': 125437, 'loss/train': 0.8799564242362976} 08/31/2021 11:59:58 - INFO - __main__ - Step 125439: {'lr': 3.3216464021069454e-05, 'samples': 24084288, 'steps': 125438, 'loss/train': 0.4950043857097626} 08/31/2021 11:59:58 - INFO - __main__ - Step 125440: {'lr': 3.32138209149721e-05, 'samples': 24084480, 'steps': 125439, 'loss/train': 0.31253352761268616} 08/31/2021 11:59:59 - INFO - __main__ - Step 125441: {'lr': 3.3211177906555255e-05, 'samples': 24084672, 'steps': 125440, 'loss/train': 1.3047913312911987} 08/31/2021 11:59:59 - INFO - __main__ - Step 125442: {'lr': 3.3208534995820104e-05, 'samples': 24084864, 'steps': 125441, 'loss/train': 0.7584900856018066} 08/31/2021 11:59:59 - INFO - __main__ - Step 125443: {'lr': 3.320589218276784e-05, 'samples': 24085056, 'steps': 125442, 'loss/train': 0.6391401290893555} 08/31/2021 12:00:00 - INFO - __main__ - Step 125444: {'lr': 3.320324946739975e-05, 'samples': 24085248, 'steps': 125443, 'loss/train': 0.8941583037376404} 08/31/2021 12:00:00 - INFO - __main__ - Step 125445: {'lr': 3.320060684971682e-05, 'samples': 24085440, 'steps': 125444, 'loss/train': 1.7282212972640991} 08/31/2021 12:00:01 - INFO - __main__ - Step 125446: {'lr': 3.3197964329720386e-05, 'samples': 24085632, 'steps': 125445, 'loss/train': 1.7344050407409668} 08/31/2021 12:00:02 - INFO - __main__ - Step 125447: {'lr': 3.319532190741159e-05, 'samples': 24085824, 'steps': 125446, 'loss/train': 0.07900524139404297} 08/31/2021 12:00:02 - INFO - __main__ - Step 125448: {'lr': 3.319267958279165e-05, 'samples': 24086016, 'steps': 125447, 'loss/train': 1.5781787633895874} 08/31/2021 12:00:03 - INFO - __main__ - Step 125449: {'lr': 3.3190037355861737e-05, 'samples': 24086208, 'steps': 125448, 'loss/train': 1.3264039754867554} 08/31/2021 12:00:03 - INFO - __main__ - Step 125450: {'lr': 3.3187395226623035e-05, 'samples': 24086400, 'steps': 125449, 'loss/train': 0.9326038956642151} 08/31/2021 12:00:05 - INFO - __main__ - Step 125451: {'lr': 3.318475319507674e-05, 'samples': 24086592, 'steps': 125450, 'loss/train': 0.07527569681406021} 08/31/2021 12:00:05 - INFO - __main__ - Step 125452: {'lr': 3.3182111261224086e-05, 'samples': 24086784, 'steps': 125451, 'loss/train': 0.5838937163352966} 08/31/2021 12:00:05 - INFO - __main__ - Step 125453: {'lr': 3.3179469425066197e-05, 'samples': 24086976, 'steps': 125452, 'loss/train': 1.3187439441680908} 08/31/2021 12:00:06 - INFO - __main__ - Step 125454: {'lr': 3.3176827686604295e-05, 'samples': 24087168, 'steps': 125453, 'loss/train': 0.07360490411520004} 08/31/2021 12:00:06 - INFO - __main__ - Step 125455: {'lr': 3.3174186045839634e-05, 'samples': 24087360, 'steps': 125454, 'loss/train': 0.990588366985321} 08/31/2021 12:00:08 - INFO - __main__ - Step 125456: {'lr': 3.317154450277329e-05, 'samples': 24087552, 'steps': 125455, 'loss/train': 1.2875406742095947} 08/31/2021 12:00:09 - INFO - __main__ - Step 125457: {'lr': 3.3168903057406494e-05, 'samples': 24087744, 'steps': 125456, 'loss/train': 0.8114908337593079} 08/31/2021 12:00:09 - INFO - __main__ - Step 125458: {'lr': 3.3166261709740434e-05, 'samples': 24087936, 'steps': 125457, 'loss/train': 1.082610845565796} 08/31/2021 12:00:09 - INFO - __main__ - Step 125459: {'lr': 3.316362045977633e-05, 'samples': 24088128, 'steps': 125458, 'loss/train': 1.4974220991134644} 08/31/2021 12:00:10 - INFO - __main__ - Step 125460: {'lr': 3.316097930751535e-05, 'samples': 24088320, 'steps': 125459, 'loss/train': 1.3645931482315063} 08/31/2021 12:00:10 - INFO - __main__ - Step 125461: {'lr': 3.3158338252958666e-05, 'samples': 24088512, 'steps': 125460, 'loss/train': 1.3974518775939941} 08/31/2021 12:00:10 - INFO - __main__ - Step 125462: {'lr': 3.315569729610751e-05, 'samples': 24088704, 'steps': 125461, 'loss/train': 1.1271263360977173} 08/31/2021 12:00:12 - INFO - __main__ - Step 125463: {'lr': 3.315305643696304e-05, 'samples': 24088896, 'steps': 125462, 'loss/train': 1.2471303939819336} 08/31/2021 12:00:13 - INFO - __main__ - Step 125464: {'lr': 3.3150415675526456e-05, 'samples': 24089088, 'steps': 125463, 'loss/train': 0.8764406442642212} 08/31/2021 12:00:13 - INFO - __main__ - Step 125465: {'lr': 3.314777501179897e-05, 'samples': 24089280, 'steps': 125464, 'loss/train': 1.1508312225341797} 08/31/2021 12:00:14 - INFO - __main__ - Step 125466: {'lr': 3.3145134445781767e-05, 'samples': 24089472, 'steps': 125465, 'loss/train': 1.7271796464920044} 08/31/2021 12:00:14 - INFO - __main__ - Step 125467: {'lr': 3.3142493977475985e-05, 'samples': 24089664, 'steps': 125466, 'loss/train': 1.158717155456543} 08/31/2021 12:00:14 - INFO - __main__ - Step 125468: {'lr': 3.3139853606882846e-05, 'samples': 24089856, 'steps': 125467, 'loss/train': 0.6696993112564087} 08/31/2021 12:00:15 - INFO - __main__ - Step 125469: {'lr': 3.3137213334003544e-05, 'samples': 24090048, 'steps': 125468, 'loss/train': 0.47764548659324646} 08/31/2021 12:00:16 - INFO - __main__ - Step 125470: {'lr': 3.3134573158839276e-05, 'samples': 24090240, 'steps': 125469, 'loss/train': 0.015396478585898876} 08/31/2021 12:00:17 - INFO - __main__ - Step 125471: {'lr': 3.313193308139123e-05, 'samples': 24090432, 'steps': 125470, 'loss/train': 1.6579259634017944} 08/31/2021 12:00:17 - INFO - __main__ - Step 125472: {'lr': 3.312929310166057e-05, 'samples': 24090624, 'steps': 125471, 'loss/train': 0.23900997638702393} 08/31/2021 12:00:17 - INFO - __main__ - Step 125473: {'lr': 3.31266532196485e-05, 'samples': 24090816, 'steps': 125472, 'loss/train': 0.8176262974739075} 08/31/2021 12:00:18 - INFO - __main__ - Step 125474: {'lr': 3.312401343535623e-05, 'samples': 24091008, 'steps': 125473, 'loss/train': 1.4310896396636963} 08/31/2021 12:00:19 - INFO - __main__ - Step 125475: {'lr': 3.3121373748784936e-05, 'samples': 24091200, 'steps': 125474, 'loss/train': 0.9646130800247192} 08/31/2021 12:00:20 - INFO - __main__ - Step 125476: {'lr': 3.3118734159935824e-05, 'samples': 24091392, 'steps': 125475, 'loss/train': 1.2639816999435425} 08/31/2021 12:00:20 - INFO - __main__ - Step 125477: {'lr': 3.311609466881005e-05, 'samples': 24091584, 'steps': 125476, 'loss/train': 0.9907174706459045} 08/31/2021 12:00:21 - INFO - __main__ - Step 125478: {'lr': 3.3113455275408796e-05, 'samples': 24091776, 'steps': 125477, 'loss/train': 0.03883222118020058} 08/31/2021 12:00:21 - INFO - __main__ - Step 125479: {'lr': 3.3110815979733285e-05, 'samples': 24091968, 'steps': 125478, 'loss/train': 1.2984037399291992} 08/31/2021 12:00:23 - INFO - __main__ - Step 125480: {'lr': 3.310817678178468e-05, 'samples': 24092160, 'steps': 125479, 'loss/train': 0.4704536199569702} 08/31/2021 12:00:23 - INFO - __main__ - Step 125481: {'lr': 3.3105537681564185e-05, 'samples': 24092352, 'steps': 125480, 'loss/train': 0.6904109716415405} 08/31/2021 12:00:23 - INFO - __main__ - Step 125482: {'lr': 3.310289867907299e-05, 'samples': 24092544, 'steps': 125481, 'loss/train': 0.8541130423545837} 08/31/2021 12:00:24 - INFO - __main__ - Step 125483: {'lr': 3.3100259774312275e-05, 'samples': 24092736, 'steps': 125482, 'loss/train': 0.8583686947822571} 08/31/2021 12:00:24 - INFO - __main__ - Step 125484: {'lr': 3.309762096728325e-05, 'samples': 24092928, 'steps': 125483, 'loss/train': 0.8509299159049988} 08/31/2021 12:00:24 - INFO - __main__ - Step 125485: {'lr': 3.30949822579871e-05, 'samples': 24093120, 'steps': 125484, 'loss/train': 0.5434356331825256} 08/31/2021 12:00:26 - INFO - __main__ - Step 125486: {'lr': 3.309234364642496e-05, 'samples': 24093312, 'steps': 125485, 'loss/train': 1.0094704627990723} 08/31/2021 12:00:26 - INFO - __main__ - Step 125487: {'lr': 3.308970513259815e-05, 'samples': 24093504, 'steps': 125486, 'loss/train': 0.47113603353500366} 08/31/2021 12:00:27 - INFO - __main__ - Step 125488: {'lr': 3.308706671650774e-05, 'samples': 24093696, 'steps': 125487, 'loss/train': 1.2057219743728638} 08/31/2021 12:00:27 - INFO - __main__ - Step 125489: {'lr': 3.3084428398154926e-05, 'samples': 24093888, 'steps': 125488, 'loss/train': 1.5477535724639893} 08/31/2021 12:00:27 - INFO - __main__ - Step 125490: {'lr': 3.3081790177540896e-05, 'samples': 24094080, 'steps': 125489, 'loss/train': 0.3829644024372101} 08/31/2021 12:00:29 - INFO - __main__ - Step 125491: {'lr': 3.3079152054666885e-05, 'samples': 24094272, 'steps': 125490, 'loss/train': 0.8083349466323853} 08/31/2021 12:00:30 - INFO - __main__ - Step 125492: {'lr': 3.307651402953407e-05, 'samples': 24094464, 'steps': 125491, 'loss/train': 0.6521884799003601} 08/31/2021 12:00:30 - INFO - __main__ - Step 125493: {'lr': 3.307387610214363e-05, 'samples': 24094656, 'steps': 125492, 'loss/train': 0.3377072513103485} 08/31/2021 12:00:31 - INFO - __main__ - Step 125494: {'lr': 3.3071238272496754e-05, 'samples': 24094848, 'steps': 125493, 'loss/train': 1.2748054265975952} 08/31/2021 12:00:31 - INFO - __main__ - Step 125495: {'lr': 3.306860054059463e-05, 'samples': 24095040, 'steps': 125494, 'loss/train': 0.9594864845275879} 08/31/2021 12:00:32 - INFO - __main__ - Step 125496: {'lr': 3.306596290643843e-05, 'samples': 24095232, 'steps': 125495, 'loss/train': 1.3936244249343872} 08/31/2021 12:00:33 - INFO - __main__ - Step 125497: {'lr': 3.306332537002937e-05, 'samples': 24095424, 'steps': 125496, 'loss/train': 1.4581774473190308} 08/31/2021 12:00:33 - INFO - __main__ - Step 125498: {'lr': 3.306068793136868e-05, 'samples': 24095616, 'steps': 125497, 'loss/train': 1.2444688081741333} 08/31/2021 12:00:34 - INFO - __main__ - Step 125499: {'lr': 3.3058050590457436e-05, 'samples': 24095808, 'steps': 125498, 'loss/train': 0.959376871585846} 08/31/2021 12:00:34 - INFO - __main__ - Step 125500: {'lr': 3.305541334729692e-05, 'samples': 24096000, 'steps': 125499, 'loss/train': 1.5923891067504883} 08/31/2021 12:00:34 - INFO - __main__ - Step 125501: {'lr': 3.305277620188826e-05, 'samples': 24096192, 'steps': 125500, 'loss/train': 1.5042698383331299} 08/31/2021 12:00:36 - INFO - __main__ - Step 125502: {'lr': 3.305013915423266e-05, 'samples': 24096384, 'steps': 125501, 'loss/train': 1.2879688739776611} 08/31/2021 12:00:36 - INFO - __main__ - Step 125503: {'lr': 3.3047502204331334e-05, 'samples': 24096576, 'steps': 125502, 'loss/train': 0.9400025010108948} 08/31/2021 12:00:37 - INFO - __main__ - Step 125504: {'lr': 3.3044865352185454e-05, 'samples': 24096768, 'steps': 125503, 'loss/train': 1.0540590286254883} 08/31/2021 12:00:37 - INFO - __main__ - Step 125505: {'lr': 3.304222859779621e-05, 'samples': 24096960, 'steps': 125504, 'loss/train': 0.750474750995636} 08/31/2021 12:00:37 - INFO - __main__ - Step 125506: {'lr': 3.303959194116479e-05, 'samples': 24097152, 'steps': 125505, 'loss/train': 0.044378623366355896} 08/31/2021 12:00:39 - INFO - __main__ - Step 125507: {'lr': 3.30369553822924e-05, 'samples': 24097344, 'steps': 125506, 'loss/train': 1.2976399660110474} 08/31/2021 12:00:39 - INFO - __main__ - Step 125508: {'lr': 3.30343189211802e-05, 'samples': 24097536, 'steps': 125507, 'loss/train': 1.0621702671051025} 08/31/2021 12:00:40 - INFO - __main__ - Step 125509: {'lr': 3.303168255782937e-05, 'samples': 24097728, 'steps': 125508, 'loss/train': 1.5046290159225464} 08/31/2021 12:00:40 - INFO - __main__ - Step 125510: {'lr': 3.302904629224113e-05, 'samples': 24097920, 'steps': 125509, 'loss/train': 1.262737512588501} 08/31/2021 12:00:40 - INFO - __main__ - Step 125511: {'lr': 3.302641012441665e-05, 'samples': 24098112, 'steps': 125510, 'loss/train': 1.0015668869018555} 08/31/2021 12:00:42 - INFO - __main__ - Step 125512: {'lr': 3.302377405435716e-05, 'samples': 24098304, 'steps': 125511, 'loss/train': 1.0428228378295898} 08/31/2021 12:00:43 - INFO - __main__ - Step 125513: {'lr': 3.3021138082063776e-05, 'samples': 24098496, 'steps': 125512, 'loss/train': 0.6521764397621155} 08/31/2021 12:00:43 - INFO - __main__ - Step 125514: {'lr': 3.301850220753772e-05, 'samples': 24098688, 'steps': 125513, 'loss/train': 1.0406360626220703} 08/31/2021 12:00:43 - INFO - __main__ - Step 125515: {'lr': 3.3015866430780164e-05, 'samples': 24098880, 'steps': 125514, 'loss/train': 0.04975995421409607} 08/31/2021 12:00:44 - INFO - __main__ - Step 125516: {'lr': 3.3013230751792325e-05, 'samples': 24099072, 'steps': 125515, 'loss/train': 0.8622643351554871} 08/31/2021 12:00:44 - INFO - __main__ - Step 125517: {'lr': 3.301059517057539e-05, 'samples': 24099264, 'steps': 125516, 'loss/train': 1.4383634328842163} 08/31/2021 12:00:46 - INFO - __main__ - Step 125518: {'lr': 3.3007959687130495e-05, 'samples': 24099456, 'steps': 125517, 'loss/train': 1.0937408208847046} 08/31/2021 12:00:46 - INFO - __main__ - Step 125519: {'lr': 3.300532430145889e-05, 'samples': 24099648, 'steps': 125518, 'loss/train': 1.0051723718643188} 08/31/2021 12:00:46 - INFO - __main__ - Step 125520: {'lr': 3.3002689013561734e-05, 'samples': 24099840, 'steps': 125519, 'loss/train': 0.9710441827774048} 08/31/2021 12:00:47 - INFO - __main__ - Step 125521: {'lr': 3.300005382344021e-05, 'samples': 24100032, 'steps': 125520, 'loss/train': 1.1730128526687622} 08/31/2021 12:00:47 - INFO - __main__ - Step 125522: {'lr': 3.299741873109552e-05, 'samples': 24100224, 'steps': 125521, 'loss/train': 0.6937710642814636} 08/31/2021 12:00:49 - INFO - __main__ - Step 125523: {'lr': 3.299478373652884e-05, 'samples': 24100416, 'steps': 125522, 'loss/train': 0.7401873469352722} 08/31/2021 12:00:49 - INFO - __main__ - Step 125524: {'lr': 3.299214883974136e-05, 'samples': 24100608, 'steps': 125523, 'loss/train': 1.4137156009674072} 08/31/2021 12:00:50 - INFO - __main__ - Step 125525: {'lr': 3.298951404073433e-05, 'samples': 24100800, 'steps': 125524, 'loss/train': 0.5637046098709106} 08/31/2021 12:00:50 - INFO - __main__ - Step 125526: {'lr': 3.2986879339508807e-05, 'samples': 24100992, 'steps': 125525, 'loss/train': 1.0288522243499756} 08/31/2021 12:00:50 - INFO - __main__ - Step 125527: {'lr': 3.298424473606606e-05, 'samples': 24101184, 'steps': 125526, 'loss/train': 0.03242384269833565} 08/31/2021 12:00:52 - INFO - __main__ - Step 125528: {'lr': 3.298161023040727e-05, 'samples': 24101376, 'steps': 125527, 'loss/train': 0.6954149603843689} 08/31/2021 12:00:52 - INFO - __main__ - Step 125529: {'lr': 3.297897582253362e-05, 'samples': 24101568, 'steps': 125528, 'loss/train': 1.037130355834961} 08/31/2021 12:00:53 - INFO - __main__ - Step 125530: {'lr': 3.297634151244627e-05, 'samples': 24101760, 'steps': 125529, 'loss/train': 0.8198282718658447} 08/31/2021 12:00:53 - INFO - __main__ - Step 125531: {'lr': 3.2973707300146455e-05, 'samples': 24101952, 'steps': 125530, 'loss/train': 0.7831602692604065} 08/31/2021 12:00:53 - INFO - __main__ - Step 125532: {'lr': 3.2971073185635334e-05, 'samples': 24102144, 'steps': 125531, 'loss/train': 0.8504701256752014} 08/31/2021 12:00:55 - INFO - __main__ - Step 125533: {'lr': 3.296843916891409e-05, 'samples': 24102336, 'steps': 125532, 'loss/train': 0.034942302852869034} 08/31/2021 12:00:55 - INFO - __main__ - Step 125534: {'lr': 3.2965805249983935e-05, 'samples': 24102528, 'steps': 125533, 'loss/train': 1.0714784860610962} 08/31/2021 12:00:56 - INFO - __main__ - Step 125535: {'lr': 3.296317142884603e-05, 'samples': 24102720, 'steps': 125534, 'loss/train': 0.04878661036491394} 08/31/2021 12:00:56 - INFO - __main__ - Step 125536: {'lr': 3.296053770550156e-05, 'samples': 24102912, 'steps': 125535, 'loss/train': 0.8006073236465454} 08/31/2021 12:00:56 - INFO - __main__ - Step 125537: {'lr': 3.295790407995172e-05, 'samples': 24103104, 'steps': 125536, 'loss/train': 1.1204771995544434} 08/31/2021 12:00:58 - INFO - __main__ - Step 125538: {'lr': 3.2955270552197716e-05, 'samples': 24103296, 'steps': 125537, 'loss/train': 1.0039869546890259} 08/31/2021 12:00:58 - INFO - __main__ - Step 125539: {'lr': 3.295263712224078e-05, 'samples': 24103488, 'steps': 125538, 'loss/train': 0.7532219290733337} 08/31/2021 12:00:59 - INFO - __main__ - Step 125540: {'lr': 3.295000379008198e-05, 'samples': 24103680, 'steps': 125539, 'loss/train': 1.2768275737762451} 08/31/2021 12:00:59 - INFO - __main__ - Step 125541: {'lr': 3.294737055572253e-05, 'samples': 24103872, 'steps': 125540, 'loss/train': 1.3201502561569214} 08/31/2021 12:00:59 - INFO - __main__ - Step 125542: {'lr': 3.294473741916368e-05, 'samples': 24104064, 'steps': 125541, 'loss/train': 0.9634878039360046} 08/31/2021 12:01:01 - INFO - __main__ - Step 125543: {'lr': 3.294210438040654e-05, 'samples': 24104256, 'steps': 125542, 'loss/train': 0.6577454805374146} 08/31/2021 12:01:02 - INFO - __main__ - Step 125544: {'lr': 3.293947143945236e-05, 'samples': 24104448, 'steps': 125543, 'loss/train': 1.3125628232955933} 08/31/2021 12:01:02 - INFO - __main__ - Step 125545: {'lr': 3.293683859630231e-05, 'samples': 24104640, 'steps': 125544, 'loss/train': 1.028838872909546} 08/31/2021 12:01:03 - INFO - __main__ - Step 125546: {'lr': 3.293420585095758e-05, 'samples': 24104832, 'steps': 125545, 'loss/train': 1.1629482507705688} 08/31/2021 12:01:03 - INFO - __main__ - Step 125547: {'lr': 3.293157320341933e-05, 'samples': 24105024, 'steps': 125546, 'loss/train': 1.0376979112625122} 08/31/2021 12:01:05 - INFO - __main__ - Step 125548: {'lr': 3.2928940653688785e-05, 'samples': 24105216, 'steps': 125547, 'loss/train': 1.3856650590896606} 08/31/2021 12:01:05 - INFO - __main__ - Step 125549: {'lr': 3.292630820176709e-05, 'samples': 24105408, 'steps': 125548, 'loss/train': 1.2720184326171875} 08/31/2021 12:01:06 - INFO - __main__ - Step 125550: {'lr': 3.292367584765546e-05, 'samples': 24105600, 'steps': 125549, 'loss/train': 0.9834702014923096} 08/31/2021 12:01:06 - INFO - __main__ - Step 125551: {'lr': 3.292104359135506e-05, 'samples': 24105792, 'steps': 125550, 'loss/train': 0.3639441728591919} 08/31/2021 12:01:06 - INFO - __main__ - Step 125552: {'lr': 3.2918411432867165e-05, 'samples': 24105984, 'steps': 125551, 'loss/train': 0.9143790602684021} 08/31/2021 12:01:08 - INFO - __main__ - Step 125553: {'lr': 3.291577937219281e-05, 'samples': 24106176, 'steps': 125552, 'loss/train': 1.0215175151824951} 08/31/2021 12:01:08 - INFO - __main__ - Step 125554: {'lr': 3.291314740933326e-05, 'samples': 24106368, 'steps': 125553, 'loss/train': 0.6919206976890564} 08/31/2021 12:01:08 - INFO - __main__ - Step 125555: {'lr': 3.29105155442897e-05, 'samples': 24106560, 'steps': 125554, 'loss/train': 1.1515560150146484} 08/31/2021 12:01:09 - INFO - __main__ - Step 125556: {'lr': 3.29078837770633e-05, 'samples': 24106752, 'steps': 125555, 'loss/train': 0.7702175378799438} 08/31/2021 12:01:09 - INFO - __main__ - Step 125557: {'lr': 3.290525210765527e-05, 'samples': 24106944, 'steps': 125556, 'loss/train': 0.8851260542869568} 08/31/2021 12:01:10 - INFO - __main__ - Step 125558: {'lr': 3.290262053606677e-05, 'samples': 24107136, 'steps': 125557, 'loss/train': 1.6139206886291504} 08/31/2021 12:01:11 - INFO - __main__ - Step 125559: {'lr': 3.289998906229902e-05, 'samples': 24107328, 'steps': 125558, 'loss/train': 1.3458030223846436} 08/31/2021 12:01:11 - INFO - __main__ - Step 125560: {'lr': 3.289735768635316e-05, 'samples': 24107520, 'steps': 125559, 'loss/train': 1.1327482461929321} 08/31/2021 12:01:12 - INFO - __main__ - Step 125561: {'lr': 3.289472640823041e-05, 'samples': 24107712, 'steps': 125560, 'loss/train': 1.2975751161575317} 08/31/2021 12:01:12 - INFO - __main__ - Step 125562: {'lr': 3.289209522793196e-05, 'samples': 24107904, 'steps': 125561, 'loss/train': 0.5471131205558777} 08/31/2021 12:01:12 - INFO - __main__ - Step 125563: {'lr': 3.288946414545896e-05, 'samples': 24108096, 'steps': 125562, 'loss/train': 1.1759272813796997} 08/31/2021 12:01:14 - INFO - __main__ - Step 125564: {'lr': 3.288683316081264e-05, 'samples': 24108288, 'steps': 125563, 'loss/train': 0.918860912322998} 08/31/2021 12:01:15 - INFO - __main__ - Step 125565: {'lr': 3.2884202273994137e-05, 'samples': 24108480, 'steps': 125564, 'loss/train': 1.6649813652038574} 08/31/2021 12:01:15 - INFO - __main__ - Step 125566: {'lr': 3.288157148500473e-05, 'samples': 24108672, 'steps': 125565, 'loss/train': 1.4941978454589844} 08/31/2021 12:01:15 - INFO - __main__ - Step 125567: {'lr': 3.287894079384548e-05, 'samples': 24108864, 'steps': 125566, 'loss/train': 0.7739073038101196} 08/31/2021 12:01:16 - INFO - __main__ - Step 125568: {'lr': 3.287631020051765e-05, 'samples': 24109056, 'steps': 125567, 'loss/train': 0.9682999849319458} 08/31/2021 12:01:18 - INFO - __main__ - Step 125569: {'lr': 3.287367970502239e-05, 'samples': 24109248, 'steps': 125568, 'loss/train': 1.5811359882354736} 08/31/2021 12:01:18 - INFO - __main__ - Step 125570: {'lr': 3.287104930736087e-05, 'samples': 24109440, 'steps': 125569, 'loss/train': 1.1306151151657104} 08/31/2021 12:01:18 - INFO - __main__ - Step 125571: {'lr': 3.286841900753434e-05, 'samples': 24109632, 'steps': 125570, 'loss/train': 0.5903180241584778} 08/31/2021 12:01:19 - INFO - __main__ - Step 125572: {'lr': 3.2865788805543946e-05, 'samples': 24109824, 'steps': 125571, 'loss/train': 0.7880277633666992} 08/31/2021 12:01:19 - INFO - __main__ - Step 125573: {'lr': 3.286315870139087e-05, 'samples': 24110016, 'steps': 125572, 'loss/train': 0.4349365532398224} 08/31/2021 12:01:21 - INFO - __main__ - Step 125574: {'lr': 3.2860528695076305e-05, 'samples': 24110208, 'steps': 125573, 'loss/train': 0.1661103367805481} 08/31/2021 12:01:21 - INFO - __main__ - Step 125575: {'lr': 3.2857898786601446e-05, 'samples': 24110400, 'steps': 125574, 'loss/train': 1.0956720113754272} 08/31/2021 12:01:22 - INFO - __main__ - Step 125576: {'lr': 3.285526897596744e-05, 'samples': 24110592, 'steps': 125575, 'loss/train': 1.085409164428711} 08/31/2021 12:01:22 - INFO - __main__ - Step 125577: {'lr': 3.2852639263175527e-05, 'samples': 24110784, 'steps': 125576, 'loss/train': 0.5536487698554993} 08/31/2021 12:01:22 - INFO - __main__ - Step 125578: {'lr': 3.285000964822685e-05, 'samples': 24110976, 'steps': 125577, 'loss/train': 1.053206443786621} 08/31/2021 12:01:24 - INFO - __main__ - Step 125579: {'lr': 3.284738013112265e-05, 'samples': 24111168, 'steps': 125578, 'loss/train': 0.29382190108299255} 08/31/2021 12:01:24 - INFO - __main__ - Step 125580: {'lr': 3.2844750711864044e-05, 'samples': 24111360, 'steps': 125579, 'loss/train': 1.2603060007095337} 08/31/2021 12:01:24 - INFO - __main__ - Step 125581: {'lr': 3.284212139045223e-05, 'samples': 24111552, 'steps': 125580, 'loss/train': 0.9952676892280579} 08/31/2021 12:01:25 - INFO - __main__ - Step 125582: {'lr': 3.283949216688839e-05, 'samples': 24111744, 'steps': 125581, 'loss/train': 1.0551323890686035} 08/31/2021 12:01:25 - INFO - __main__ - Step 125583: {'lr': 3.283686304117375e-05, 'samples': 24111936, 'steps': 125582, 'loss/train': 1.7147186994552612} 08/31/2021 12:01:27 - INFO - __main__ - Step 125584: {'lr': 3.2834234013309454e-05, 'samples': 24112128, 'steps': 125583, 'loss/train': 1.3734387159347534} 08/31/2021 12:01:27 - INFO - __main__ - Step 125585: {'lr': 3.283160508329669e-05, 'samples': 24112320, 'steps': 125584, 'loss/train': 1.2970703840255737} 08/31/2021 12:01:27 - INFO - __main__ - Step 125586: {'lr': 3.282897625113668e-05, 'samples': 24112512, 'steps': 125585, 'loss/train': 1.2229211330413818} 08/31/2021 12:01:28 - INFO - __main__ - Step 125587: {'lr': 3.282634751683056e-05, 'samples': 24112704, 'steps': 125586, 'loss/train': 0.2116260677576065} 08/31/2021 12:01:28 - INFO - __main__ - Step 125588: {'lr': 3.282371888037955e-05, 'samples': 24112896, 'steps': 125587, 'loss/train': 1.1568588018417358} 08/31/2021 12:01:29 - INFO - __main__ - Step 125589: {'lr': 3.2821090341784824e-05, 'samples': 24113088, 'steps': 125588, 'loss/train': 0.2810206711292267} 08/31/2021 12:01:30 - INFO - __main__ - Step 125590: {'lr': 3.281846190104754e-05, 'samples': 24113280, 'steps': 125589, 'loss/train': 0.5452426075935364} 08/31/2021 12:01:31 - INFO - __main__ - Step 125591: {'lr': 3.281583355816892e-05, 'samples': 24113472, 'steps': 125590, 'loss/train': 1.0853338241577148} 08/31/2021 12:01:31 - INFO - __main__ - Step 125592: {'lr': 3.281320531315013e-05, 'samples': 24113664, 'steps': 125591, 'loss/train': 0.6054130792617798} 08/31/2021 12:01:31 - INFO - __main__ - Step 125593: {'lr': 3.281057716599242e-05, 'samples': 24113856, 'steps': 125592, 'loss/train': 1.2976893186569214} 08/31/2021 12:01:32 - INFO - __main__ - Step 125594: {'lr': 3.2807949116696876e-05, 'samples': 24114048, 'steps': 125593, 'loss/train': 1.503633975982666} 08/31/2021 12:01:33 - INFO - __main__ - Step 125595: {'lr': 3.280532116526469e-05, 'samples': 24114240, 'steps': 125594, 'loss/train': 0.866003155708313} 08/31/2021 12:01:33 - INFO - __main__ - Step 125596: {'lr': 3.280269331169708e-05, 'samples': 24114432, 'steps': 125595, 'loss/train': 1.2318135499954224} 08/31/2021 12:01:34 - INFO - __main__ - Step 125597: {'lr': 3.280006555599524e-05, 'samples': 24114624, 'steps': 125596, 'loss/train': 1.8663806915283203} 08/31/2021 12:01:34 - INFO - __main__ - Step 125598: {'lr': 3.279743789816031e-05, 'samples': 24114816, 'steps': 125597, 'loss/train': 1.3619163036346436} 08/31/2021 12:01:34 - INFO - __main__ - Step 125599: {'lr': 3.279481033819354e-05, 'samples': 24115008, 'steps': 125598, 'loss/train': 1.069794774055481} 08/31/2021 12:01:37 - INFO - __main__ - Step 125600: {'lr': 3.2792182876096035e-05, 'samples': 24115200, 'steps': 125599, 'loss/train': 0.4667503237724304} 08/31/2021 12:01:37 - INFO - __main__ - Step 125601: {'lr': 3.278955551186904e-05, 'samples': 24115392, 'steps': 125600, 'loss/train': 0.7268730401992798} 08/31/2021 12:01:38 - INFO - __main__ - Step 125602: {'lr': 3.278692824551374e-05, 'samples': 24115584, 'steps': 125601, 'loss/train': 0.046677034348249435} 08/31/2021 12:01:38 - INFO - __main__ - Step 125603: {'lr': 3.2784301077031284e-05, 'samples': 24115776, 'steps': 125602, 'loss/train': 1.026534914970398} 08/31/2021 12:01:38 - INFO - __main__ - Step 125604: {'lr': 3.278167400642285e-05, 'samples': 24115968, 'steps': 125603, 'loss/train': 1.6146228313446045} 08/31/2021 12:01:39 - INFO - __main__ - Step 125605: {'lr': 3.2779047033689666e-05, 'samples': 24116160, 'steps': 125604, 'loss/train': 0.015994202345609665} 08/31/2021 12:01:40 - INFO - __main__ - Step 125606: {'lr': 3.277642015883295e-05, 'samples': 24116352, 'steps': 125605, 'loss/train': 0.013920247554779053} 08/31/2021 12:01:41 - INFO - __main__ - Step 125607: {'lr': 3.277379338185374e-05, 'samples': 24116544, 'steps': 125606, 'loss/train': 0.4861597418785095} 08/31/2021 12:01:41 - INFO - __main__ - Step 125608: {'lr': 3.277116670275335e-05, 'samples': 24116736, 'steps': 125607, 'loss/train': 1.1826757192611694} 08/31/2021 12:01:42 - INFO - __main__ - Step 125609: {'lr': 3.276854012153288e-05, 'samples': 24116928, 'steps': 125608, 'loss/train': 0.8907474875450134} 08/31/2021 12:01:42 - INFO - __main__ - Step 125610: {'lr': 3.276591363819356e-05, 'samples': 24117120, 'steps': 125609, 'loss/train': 0.5730138421058655} 08/31/2021 12:01:43 - INFO - __main__ - Step 125611: {'lr': 3.276328725273658e-05, 'samples': 24117312, 'steps': 125610, 'loss/train': 0.04425438493490219} 08/31/2021 12:01:44 - INFO - __main__ - Step 125612: {'lr': 3.276066096516311e-05, 'samples': 24117504, 'steps': 125611, 'loss/train': 0.855826199054718} 08/31/2021 12:01:44 - INFO - __main__ - Step 125613: {'lr': 3.2758034775474344e-05, 'samples': 24117696, 'steps': 125612, 'loss/train': 1.0346027612686157} 08/31/2021 12:01:45 - INFO - __main__ - Step 125614: {'lr': 3.275540868367144e-05, 'samples': 24117888, 'steps': 125613, 'loss/train': 0.9295983910560608} 08/31/2021 12:01:45 - INFO - __main__ - Step 125615: {'lr': 3.275278268975559e-05, 'samples': 24118080, 'steps': 125614, 'loss/train': 0.38229113817214966} 08/31/2021 12:01:46 - INFO - __main__ - Step 125616: {'lr': 3.2750156793728e-05, 'samples': 24118272, 'steps': 125615, 'loss/train': 1.206154465675354} 08/31/2021 12:01:47 - INFO - __main__ - Step 125617: {'lr': 3.274753099558983e-05, 'samples': 24118464, 'steps': 125616, 'loss/train': 0.5045633316040039} 08/31/2021 12:01:47 - INFO - __main__ - Step 125618: {'lr': 3.2744905295342295e-05, 'samples': 24118656, 'steps': 125617, 'loss/train': 0.9948684573173523} 08/31/2021 12:01:48 - INFO - __main__ - Step 125619: {'lr': 3.274227969298657e-05, 'samples': 24118848, 'steps': 125618, 'loss/train': 1.2151886224746704} 08/31/2021 12:01:48 - INFO - __main__ - Step 125620: {'lr': 3.2739654188523786e-05, 'samples': 24119040, 'steps': 125619, 'loss/train': 0.8856202960014343} 08/31/2021 12:01:50 - INFO - __main__ - Step 125621: {'lr': 3.273702878195517e-05, 'samples': 24119232, 'steps': 125620, 'loss/train': 0.6791606545448303} 08/31/2021 12:01:50 - INFO - __main__ - Step 125622: {'lr': 3.273440347328188e-05, 'samples': 24119424, 'steps': 125621, 'loss/train': 1.137162685394287} 08/31/2021 12:01:50 - INFO - __main__ - Step 125623: {'lr': 3.2731778262505116e-05, 'samples': 24119616, 'steps': 125622, 'loss/train': 1.6218899488449097} 08/31/2021 12:01:51 - INFO - __main__ - Step 125624: {'lr': 3.272915314962604e-05, 'samples': 24119808, 'steps': 125623, 'loss/train': 1.5628013610839844} 08/31/2021 12:01:51 - INFO - __main__ - Step 125625: {'lr': 3.2726528134645884e-05, 'samples': 24120000, 'steps': 125624, 'loss/train': 1.0705077648162842} 08/31/2021 12:01:51 - INFO - __main__ - Step 125626: {'lr': 3.27239032175658e-05, 'samples': 24120192, 'steps': 125625, 'loss/train': 0.7466346025466919} 08/31/2021 12:01:53 - INFO - __main__ - Step 125627: {'lr': 3.272127839838696e-05, 'samples': 24120384, 'steps': 125626, 'loss/train': 0.4822697043418884} 08/31/2021 12:01:54 - INFO - __main__ - Step 125628: {'lr': 3.2718653677110576e-05, 'samples': 24120576, 'steps': 125627, 'loss/train': 0.04936998337507248} 08/31/2021 12:01:54 - INFO - __main__ - Step 125629: {'lr': 3.27160290537378e-05, 'samples': 24120768, 'steps': 125628, 'loss/train': 0.30082306265830994} 08/31/2021 12:01:54 - INFO - __main__ - Step 125630: {'lr': 3.2713404528269846e-05, 'samples': 24120960, 'steps': 125629, 'loss/train': 1.5780619382858276} 08/31/2021 12:01:55 - INFO - __main__ - Step 125631: {'lr': 3.271078010070786e-05, 'samples': 24121152, 'steps': 125630, 'loss/train': 0.611416220664978} 08/31/2021 12:01:56 - INFO - __main__ - Step 125632: {'lr': 3.2708155771053045e-05, 'samples': 24121344, 'steps': 125631, 'loss/train': 0.03899114578962326} 08/31/2021 12:01:57 - INFO - __main__ - Step 125633: {'lr': 3.2705531539306635e-05, 'samples': 24121536, 'steps': 125632, 'loss/train': 0.6479595303535461} 08/31/2021 12:01:57 - INFO - __main__ - Step 125634: {'lr': 3.270290740546972e-05, 'samples': 24121728, 'steps': 125633, 'loss/train': 1.395885705947876} 08/31/2021 12:01:58 - INFO - __main__ - Step 125635: {'lr': 3.27002833695435e-05, 'samples': 24121920, 'steps': 125634, 'loss/train': 0.4237719476222992} 08/31/2021 12:01:58 - INFO - __main__ - Step 125636: {'lr': 3.2697659431529193e-05, 'samples': 24122112, 'steps': 125635, 'loss/train': 0.8783606290817261} 08/31/2021 12:01:58 - INFO - __main__ - Step 125637: {'lr': 3.2695035591427976e-05, 'samples': 24122304, 'steps': 125636, 'loss/train': 1.2325170040130615} 08/31/2021 12:02:00 - INFO - __main__ - Step 125638: {'lr': 3.2692411849241015e-05, 'samples': 24122496, 'steps': 125637, 'loss/train': 0.44461312890052795} 08/31/2021 12:02:00 - INFO - __main__ - Step 125639: {'lr': 3.2689788204969485e-05, 'samples': 24122688, 'steps': 125638, 'loss/train': 1.476796269416809} 08/31/2021 12:02:01 - INFO - __main__ - Step 125640: {'lr': 3.26871646586146e-05, 'samples': 24122880, 'steps': 125639, 'loss/train': 0.6183615326881409} 08/31/2021 12:02:01 - INFO - __main__ - Step 125641: {'lr': 3.2684541210177525e-05, 'samples': 24123072, 'steps': 125640, 'loss/train': 1.4313338994979858} 08/31/2021 12:02:01 - INFO - __main__ - Step 125642: {'lr': 3.268191785965943e-05, 'samples': 24123264, 'steps': 125641, 'loss/train': 0.7676453590393066} 08/31/2021 12:02:03 - INFO - __main__ - Step 125643: {'lr': 3.267929460706154e-05, 'samples': 24123456, 'steps': 125642, 'loss/train': 0.8852528929710388} 08/31/2021 12:02:03 - INFO - __main__ - Step 125644: {'lr': 3.267667145238498e-05, 'samples': 24123648, 'steps': 125643, 'loss/train': 0.1296599805355072} 08/31/2021 12:02:04 - INFO - __main__ - Step 125645: {'lr': 3.2674048395630954e-05, 'samples': 24123840, 'steps': 125644, 'loss/train': 1.4057475328445435} 08/31/2021 12:02:04 - INFO - __main__ - Step 125646: {'lr': 3.267142543680071e-05, 'samples': 24124032, 'steps': 125645, 'loss/train': 1.041488766670227} 08/31/2021 12:02:04 - INFO - __main__ - Step 125647: {'lr': 3.266880257589533e-05, 'samples': 24124224, 'steps': 125646, 'loss/train': 1.7744417190551758} 08/31/2021 12:02:06 - INFO - __main__ - Step 125648: {'lr': 3.2666179812916e-05, 'samples': 24124416, 'steps': 125647, 'loss/train': 1.5154409408569336} 08/31/2021 12:02:06 - INFO - __main__ - Step 125649: {'lr': 3.266355714786395e-05, 'samples': 24124608, 'steps': 125648, 'loss/train': 0.8299384117126465} 08/31/2021 12:02:07 - INFO - __main__ - Step 125650: {'lr': 3.266093458074035e-05, 'samples': 24124800, 'steps': 125649, 'loss/train': 1.155440092086792} 08/31/2021 12:02:07 - INFO - __main__ - Step 125651: {'lr': 3.265831211154638e-05, 'samples': 24124992, 'steps': 125650, 'loss/train': 0.7528833150863647} 08/31/2021 12:02:07 - INFO - __main__ - Step 125652: {'lr': 3.265568974028324e-05, 'samples': 24125184, 'steps': 125651, 'loss/train': 0.24670164287090302} 08/31/2021 12:02:10 - INFO - __main__ - Step 125653: {'lr': 3.265306746695207e-05, 'samples': 24125376, 'steps': 125652, 'loss/train': 0.9684351682662964} 08/31/2021 12:02:10 - INFO - __main__ - Step 125654: {'lr': 3.2650445291554085e-05, 'samples': 24125568, 'steps': 125653, 'loss/train': 1.3701491355895996} 08/31/2021 12:02:10 - INFO - __main__ - Step 125655: {'lr': 3.2647823214090436e-05, 'samples': 24125760, 'steps': 125654, 'loss/train': 1.1078969240188599} 08/31/2021 12:02:11 - INFO - __main__ - Step 125656: {'lr': 3.264520123456233e-05, 'samples': 24125952, 'steps': 125655, 'loss/train': 0.28994661569595337} 08/31/2021 12:02:11 - INFO - __main__ - Step 125657: {'lr': 3.264257935297096e-05, 'samples': 24126144, 'steps': 125656, 'loss/train': 1.4181346893310547} 08/31/2021 12:02:13 - INFO - __main__ - Step 125658: {'lr': 3.263995756931748e-05, 'samples': 24126336, 'steps': 125657, 'loss/train': 0.7743427753448486} 08/31/2021 12:02:13 - INFO - __main__ - Step 125659: {'lr': 3.263733588360307e-05, 'samples': 24126528, 'steps': 125658, 'loss/train': 0.8791504502296448} 08/31/2021 12:02:14 - INFO - __main__ - Step 125660: {'lr': 3.263471429582898e-05, 'samples': 24126720, 'steps': 125659, 'loss/train': 0.8462323546409607} 08/31/2021 12:02:14 - INFO - __main__ - Step 125661: {'lr': 3.26320928059963e-05, 'samples': 24126912, 'steps': 125660, 'loss/train': 0.8660026788711548} 08/31/2021 12:02:14 - INFO - __main__ - Step 125662: {'lr': 3.2629471414106246e-05, 'samples': 24127104, 'steps': 125661, 'loss/train': 1.4580765962600708} 08/31/2021 12:02:15 - INFO - __main__ - Step 125663: {'lr': 3.262685012015998e-05, 'samples': 24127296, 'steps': 125662, 'loss/train': 1.0928418636322021} 08/31/2021 12:02:17 - INFO - __main__ - Step 125664: {'lr': 3.26242289241587e-05, 'samples': 24127488, 'steps': 125663, 'loss/train': 0.9417195916175842} 08/31/2021 12:02:17 - INFO - __main__ - Step 125665: {'lr': 3.2621607826103575e-05, 'samples': 24127680, 'steps': 125664, 'loss/train': 1.8977266550064087} 08/31/2021 12:02:18 - INFO - __main__ - Step 125666: {'lr': 3.2618986825995816e-05, 'samples': 24127872, 'steps': 125665, 'loss/train': 1.4416875839233398} 08/31/2021 12:02:18 - INFO - __main__ - Step 125667: {'lr': 3.26163659238366e-05, 'samples': 24128064, 'steps': 125666, 'loss/train': 0.6133119463920593} 08/31/2021 12:02:18 - INFO - __main__ - Step 125668: {'lr': 3.2613745119627085e-05, 'samples': 24128256, 'steps': 125667, 'loss/train': 0.8093478083610535} 08/31/2021 12:02:19 - INFO - __main__ - Step 125669: {'lr': 3.2611124413368445e-05, 'samples': 24128448, 'steps': 125668, 'loss/train': 0.12791870534420013} 08/31/2021 12:02:20 - INFO - __main__ - Step 125670: {'lr': 3.260850380506189e-05, 'samples': 24128640, 'steps': 125669, 'loss/train': 0.06899328529834747} 08/31/2021 12:02:20 - INFO - __main__ - Step 125671: {'lr': 3.260588329470859e-05, 'samples': 24128832, 'steps': 125670, 'loss/train': 1.1859010457992554} 08/31/2021 12:02:21 - INFO - __main__ - Step 125672: {'lr': 3.260326288230972e-05, 'samples': 24129024, 'steps': 125671, 'loss/train': 0.11593236029148102} 08/31/2021 12:02:21 - INFO - __main__ - Step 125673: {'lr': 3.2600642567866543e-05, 'samples': 24129216, 'steps': 125672, 'loss/train': 1.2826184034347534} 08/31/2021 12:02:21 - INFO - __main__ - Step 125674: {'lr': 3.259802235138007e-05, 'samples': 24129408, 'steps': 125673, 'loss/train': 1.475209355354309} 08/31/2021 12:02:23 - INFO - __main__ - Step 125675: {'lr': 3.2595402232851595e-05, 'samples': 24129600, 'steps': 125674, 'loss/train': 1.1835087537765503} 08/31/2021 12:02:24 - INFO - __main__ - Step 125676: {'lr': 3.259278221228229e-05, 'samples': 24129792, 'steps': 125675, 'loss/train': 1.0897605419158936} 08/31/2021 12:02:24 - INFO - __main__ - Step 125677: {'lr': 3.259016228967329e-05, 'samples': 24129984, 'steps': 125676, 'loss/train': 1.4458211660385132} 08/31/2021 12:02:24 - INFO - __main__ - Step 125678: {'lr': 3.258754246502582e-05, 'samples': 24130176, 'steps': 125677, 'loss/train': 0.8054088354110718} 08/31/2021 12:02:25 - INFO - __main__ - Step 125679: {'lr': 3.258492273834107e-05, 'samples': 24130368, 'steps': 125678, 'loss/train': 0.8246374130249023} 08/31/2021 12:02:26 - INFO - __main__ - Step 125680: {'lr': 3.258230310962018e-05, 'samples': 24130560, 'steps': 125679, 'loss/train': 0.45626896619796753} 08/31/2021 12:02:27 - INFO - __main__ - Step 125681: {'lr': 3.2579683578864345e-05, 'samples': 24130752, 'steps': 125680, 'loss/train': 0.6637920141220093} 08/31/2021 12:02:27 - INFO - __main__ - Step 125682: {'lr': 3.2577064146074754e-05, 'samples': 24130944, 'steps': 125681, 'loss/train': 0.0500800684094429} 08/31/2021 12:02:28 - INFO - __main__ - Step 125683: {'lr': 3.25744448112526e-05, 'samples': 24131136, 'steps': 125682, 'loss/train': 0.16765744984149933} 08/31/2021 12:02:28 - INFO - __main__ - Step 125684: {'lr': 3.257182557439903e-05, 'samples': 24131328, 'steps': 125683, 'loss/train': 0.7095734477043152} 08/31/2021 12:02:30 - INFO - __main__ - Step 125685: {'lr': 3.256920643551523e-05, 'samples': 24131520, 'steps': 125684, 'loss/train': 0.4776986539363861} 08/31/2021 12:02:30 - INFO - __main__ - Step 125686: {'lr': 3.256658739460241e-05, 'samples': 24131712, 'steps': 125685, 'loss/train': 0.7051326036453247} 08/31/2021 12:02:30 - INFO - __main__ - Step 125687: {'lr': 3.256396845166176e-05, 'samples': 24131904, 'steps': 125686, 'loss/train': 1.360384464263916} 08/31/2021 12:02:31 - INFO - __main__ - Step 125688: {'lr': 3.2561349606694406e-05, 'samples': 24132096, 'steps': 125687, 'loss/train': 0.6340116262435913} 08/31/2021 12:02:31 - INFO - __main__ - Step 125689: {'lr': 3.2558730859701544e-05, 'samples': 24132288, 'steps': 125688, 'loss/train': 0.6949107646942139} 08/31/2021 12:02:33 - INFO - __main__ - Step 125690: {'lr': 3.255611221068436e-05, 'samples': 24132480, 'steps': 125689, 'loss/train': 1.0626509189605713} 08/31/2021 12:02:33 - INFO - __main__ - Step 125691: {'lr': 3.2553493659644025e-05, 'samples': 24132672, 'steps': 125690, 'loss/train': 1.0276979207992554} 08/31/2021 12:02:33 - INFO - __main__ - Step 125692: {'lr': 3.255087520658173e-05, 'samples': 24132864, 'steps': 125691, 'loss/train': 1.2895249128341675} 08/31/2021 12:02:34 - INFO - __main__ - Step 125693: {'lr': 3.2548256851498675e-05, 'samples': 24133056, 'steps': 125692, 'loss/train': 0.6074228882789612} 08/31/2021 12:02:34 - INFO - __main__ - Step 125694: {'lr': 3.254563859439602e-05, 'samples': 24133248, 'steps': 125693, 'loss/train': 1.70565664768219} 08/31/2021 12:02:36 - INFO - __main__ - Step 125695: {'lr': 3.2543020435274936e-05, 'samples': 24133440, 'steps': 125694, 'loss/train': 1.2646853923797607} 08/31/2021 12:02:37 - INFO - __main__ - Step 125696: {'lr': 3.2540402374136604e-05, 'samples': 24133632, 'steps': 125695, 'loss/train': 0.9331364035606384} 08/31/2021 12:02:37 - INFO - __main__ - Step 125697: {'lr': 3.253778441098221e-05, 'samples': 24133824, 'steps': 125696, 'loss/train': 0.7705808281898499} 08/31/2021 12:02:37 - INFO - __main__ - Step 125698: {'lr': 3.2535166545812954e-05, 'samples': 24134016, 'steps': 125697, 'loss/train': 1.3690892457962036} 08/31/2021 12:02:38 - INFO - __main__ - Step 125699: {'lr': 3.253254877862996e-05, 'samples': 24134208, 'steps': 125698, 'loss/train': 0.9656137228012085} 08/31/2021 12:02:38 - INFO - __main__ - Step 125700: {'lr': 3.252993110943453e-05, 'samples': 24134400, 'steps': 125699, 'loss/train': 1.3665095567703247} 08/31/2021 12:02:40 - INFO - __main__ - Step 125701: {'lr': 3.2527313538227684e-05, 'samples': 24134592, 'steps': 125700, 'loss/train': 1.0221389532089233} 08/31/2021 12:02:40 - INFO - __main__ - Step 125702: {'lr': 3.252469606501071e-05, 'samples': 24134784, 'steps': 125701, 'loss/train': 0.3530429005622864} 08/31/2021 12:02:40 - INFO - __main__ - Step 125703: {'lr': 3.2522078689784714e-05, 'samples': 24134976, 'steps': 125702, 'loss/train': 0.029353752732276917} 08/31/2021 12:02:41 - INFO - __main__ - Step 125704: {'lr': 3.251946141255094e-05, 'samples': 24135168, 'steps': 125703, 'loss/train': 1.5398081541061401} 08/31/2021 12:02:41 - INFO - __main__ - Step 125705: {'lr': 3.251684423331053e-05, 'samples': 24135360, 'steps': 125704, 'loss/train': 1.2894165515899658} 08/31/2021 12:02:43 - INFO - __main__ - Step 125706: {'lr': 3.2514227152064676e-05, 'samples': 24135552, 'steps': 125705, 'loss/train': 0.04178394377231598} 08/31/2021 12:02:44 - INFO - __main__ - Step 125707: {'lr': 3.2511610168814543e-05, 'samples': 24135744, 'steps': 125706, 'loss/train': 1.2498654127120972} 08/31/2021 12:02:44 - INFO - __main__ - Step 125708: {'lr': 3.2508993283561326e-05, 'samples': 24135936, 'steps': 125707, 'loss/train': 1.0208970308303833} 08/31/2021 12:02:44 - INFO - __main__ - Step 125709: {'lr': 3.2506376496306194e-05, 'samples': 24136128, 'steps': 125708, 'loss/train': 1.0594409704208374} 08/31/2021 12:02:45 - INFO - __main__ - Step 125710: {'lr': 3.250375980705036e-05, 'samples': 24136320, 'steps': 125709, 'loss/train': 1.4120334386825562} 08/31/2021 12:02:46 - INFO - __main__ - Step 125711: {'lr': 3.250114321579495e-05, 'samples': 24136512, 'steps': 125710, 'loss/train': 1.5979174375534058} 08/31/2021 12:02:47 - INFO - __main__ - Step 125712: {'lr': 3.249852672254119e-05, 'samples': 24136704, 'steps': 125711, 'loss/train': 1.5139851570129395} 08/31/2021 12:02:47 - INFO - __main__ - Step 125713: {'lr': 3.249591032729027e-05, 'samples': 24136896, 'steps': 125712, 'loss/train': 1.3148009777069092} 08/31/2021 12:02:48 - INFO - __main__ - Step 125714: {'lr': 3.249329403004331e-05, 'samples': 24137088, 'steps': 125713, 'loss/train': 1.5327115058898926} 08/31/2021 12:02:48 - INFO - __main__ - Step 125715: {'lr': 3.249067783080148e-05, 'samples': 24137280, 'steps': 125714, 'loss/train': 1.228061318397522} 08/31/2021 12:02:48 - INFO - __main__ - Step 125716: {'lr': 3.2488061729566e-05, 'samples': 24137472, 'steps': 125715, 'loss/train': 1.2494449615478516} 08/31/2021 12:02:50 - INFO - __main__ - Step 125717: {'lr': 3.248544572633807e-05, 'samples': 24137664, 'steps': 125716, 'loss/train': 2.504237413406372} 08/31/2021 12:02:51 - INFO - __main__ - Step 125718: {'lr': 3.2482829821118834e-05, 'samples': 24137856, 'steps': 125717, 'loss/train': 0.8579521775245667} 08/31/2021 12:02:51 - INFO - __main__ - Step 125719: {'lr': 3.2480214013909466e-05, 'samples': 24138048, 'steps': 125718, 'loss/train': 0.814227283000946} 08/31/2021 12:02:52 - INFO - __main__ - Step 125720: {'lr': 3.247759830471117e-05, 'samples': 24138240, 'steps': 125719, 'loss/train': 0.33943021297454834} 08/31/2021 12:02:52 - INFO - __main__ - Step 125721: {'lr': 3.2474982693525086e-05, 'samples': 24138432, 'steps': 125720, 'loss/train': 5.735555648803711} 08/31/2021 12:02:52 - INFO - __main__ - Step 125722: {'lr': 3.247236718035243e-05, 'samples': 24138624, 'steps': 125721, 'loss/train': 5.678689002990723} 08/31/2021 12:02:53 - INFO - __main__ - Step 125723: {'lr': 3.246975176519446e-05, 'samples': 24138816, 'steps': 125722, 'loss/train': 5.776236534118652} 08/31/2021 12:02:54 - INFO - __main__ - Step 125724: {'lr': 3.2467136448052157e-05, 'samples': 24139008, 'steps': 125723, 'loss/train': 1.5098364353179932} 08/31/2021 12:02:55 - INFO - __main__ - Step 125725: {'lr': 3.246452122892682e-05, 'samples': 24139200, 'steps': 125724, 'loss/train': 1.3092973232269287} 08/31/2021 12:02:55 - INFO - __main__ - Step 125726: {'lr': 3.246190610781963e-05, 'samples': 24139392, 'steps': 125725, 'loss/train': 1.5242671966552734} 08/31/2021 12:02:55 - INFO - __main__ - Step 125727: {'lr': 3.2459291084731726e-05, 'samples': 24139584, 'steps': 125726, 'loss/train': 1.0340322256088257} 08/31/2021 12:02:56 - INFO - __main__ - Step 125728: {'lr': 3.2456676159664326e-05, 'samples': 24139776, 'steps': 125727, 'loss/train': 1.3490692377090454} 08/31/2021 12:02:57 - INFO - __main__ - Step 125729: {'lr': 3.245406133261858e-05, 'samples': 24139968, 'steps': 125728, 'loss/train': 0.8110262751579285} 08/31/2021 12:02:58 - INFO - __main__ - Step 125730: {'lr': 3.24514466035957e-05, 'samples': 24140160, 'steps': 125729, 'loss/train': 1.2168611288070679} 08/31/2021 12:02:58 - INFO - __main__ - Step 125731: {'lr': 3.244883197259682e-05, 'samples': 24140352, 'steps': 125730, 'loss/train': 0.7773024439811707} 08/31/2021 12:02:58 - INFO - __main__ - Step 125732: {'lr': 3.2446217439623145e-05, 'samples': 24140544, 'steps': 125731, 'loss/train': 0.8877666592597961} 08/31/2021 12:02:59 - INFO - __main__ - Step 125733: {'lr': 3.244360300467583e-05, 'samples': 24140736, 'steps': 125732, 'loss/train': 1.0571980476379395} 08/31/2021 12:03:00 - INFO - __main__ - Step 125734: {'lr': 3.244098866775613e-05, 'samples': 24140928, 'steps': 125733, 'loss/train': 0.0946299359202385} 08/31/2021 12:03:01 - INFO - __main__ - Step 125735: {'lr': 3.243837442886513e-05, 'samples': 24141120, 'steps': 125734, 'loss/train': 1.115682601928711} 08/31/2021 12:03:01 - INFO - __main__ - Step 125736: {'lr': 3.2435760288004046e-05, 'samples': 24141312, 'steps': 125735, 'loss/train': 1.2719789743423462} 08/31/2021 12:03:02 - INFO - __main__ - Step 125737: {'lr': 3.243314624517402e-05, 'samples': 24141504, 'steps': 125736, 'loss/train': 0.7943173050880432} 08/31/2021 12:03:02 - INFO - __main__ - Step 125738: {'lr': 3.243053230037629e-05, 'samples': 24141696, 'steps': 125737, 'loss/train': 0.09155856817960739} 08/31/2021 12:03:02 - INFO - __main__ - Step 125739: {'lr': 3.242791845361198e-05, 'samples': 24141888, 'steps': 125738, 'loss/train': 0.6896782517433167} 08/31/2021 12:03:04 - INFO - __main__ - Step 125740: {'lr': 3.2425304704882306e-05, 'samples': 24142080, 'steps': 125739, 'loss/train': 1.0476032495498657} 08/31/2021 12:03:04 - INFO - __main__ - Step 125741: {'lr': 3.242269105418844e-05, 'samples': 24142272, 'steps': 125740, 'loss/train': 0.9603878855705261} 08/31/2021 12:03:05 - INFO - __main__ - Step 125742: {'lr': 3.242007750153153e-05, 'samples': 24142464, 'steps': 125741, 'loss/train': 0.6384961009025574} 08/31/2021 12:03:05 - INFO - __main__ - Step 125743: {'lr': 3.2417464046912785e-05, 'samples': 24142656, 'steps': 125742, 'loss/train': 0.12199132144451141} 08/31/2021 12:03:05 - INFO - __main__ - Step 125744: {'lr': 3.241485069033337e-05, 'samples': 24142848, 'steps': 125743, 'loss/train': 1.8076170682907104} 08/31/2021 12:03:07 - INFO - __main__ - Step 125745: {'lr': 3.241223743179453e-05, 'samples': 24143040, 'steps': 125744, 'loss/train': 0.8447962403297424} 08/31/2021 12:03:07 - INFO - __main__ - Step 125746: {'lr': 3.2409624271297316e-05, 'samples': 24143232, 'steps': 125745, 'loss/train': 1.5712050199508667} 08/31/2021 12:03:08 - INFO - __main__ - Step 125747: {'lr': 3.2407011208842987e-05, 'samples': 24143424, 'steps': 125746, 'loss/train': 1.086759328842163} 08/31/2021 12:03:08 - INFO - __main__ - Step 125748: {'lr': 3.240439824443267e-05, 'samples': 24143616, 'steps': 125747, 'loss/train': 1.2054001092910767} 08/31/2021 12:03:08 - INFO - __main__ - Step 125749: {'lr': 3.24017853780676e-05, 'samples': 24143808, 'steps': 125748, 'loss/train': 0.8761179447174072} 08/31/2021 12:03:10 - INFO - __main__ - Step 125750: {'lr': 3.239917260974892e-05, 'samples': 24144000, 'steps': 125749, 'loss/train': 1.056016206741333} 08/31/2021 12:03:11 - INFO - __main__ - Step 125751: {'lr': 3.239655993947779e-05, 'samples': 24144192, 'steps': 125750, 'loss/train': 0.08158742636442184} 08/31/2021 12:03:11 - INFO - __main__ - Step 125752: {'lr': 3.239394736725546e-05, 'samples': 24144384, 'steps': 125751, 'loss/train': 0.11172538995742798} 08/31/2021 12:03:12 - INFO - __main__ - Step 125753: {'lr': 3.239133489308302e-05, 'samples': 24144576, 'steps': 125752, 'loss/train': 1.6584452390670776} 08/31/2021 12:03:12 - INFO - __main__ - Step 125754: {'lr': 3.238872251696171e-05, 'samples': 24144768, 'steps': 125753, 'loss/train': 0.7149726152420044} 08/31/2021 12:03:13 - INFO - __main__ - Step 125755: {'lr': 3.238611023889265e-05, 'samples': 24144960, 'steps': 125754, 'loss/train': 1.0768892765045166} 08/31/2021 12:03:14 - INFO - __main__ - Step 125756: {'lr': 3.238349805887714e-05, 'samples': 24145152, 'steps': 125755, 'loss/train': 1.4192596673965454} 08/31/2021 12:03:14 - INFO - __main__ - Step 125757: {'lr': 3.238088597691621e-05, 'samples': 24145344, 'steps': 125756, 'loss/train': 1.1939173936843872} 08/31/2021 12:03:15 - INFO - __main__ - Step 125758: {'lr': 3.2378273993011074e-05, 'samples': 24145536, 'steps': 125757, 'loss/train': 0.46928247809410095} 08/31/2021 12:03:15 - INFO - __main__ - Step 125759: {'lr': 3.237566210716295e-05, 'samples': 24145728, 'steps': 125758, 'loss/train': 0.721493124961853} 08/31/2021 12:03:17 - INFO - __main__ - Step 125760: {'lr': 3.237305031937299e-05, 'samples': 24145920, 'steps': 125759, 'loss/train': 1.587860107421875} 08/31/2021 12:03:17 - INFO - __main__ - Step 125761: {'lr': 3.237043862964237e-05, 'samples': 24146112, 'steps': 125760, 'loss/train': 1.118680715560913} 08/31/2021 12:03:17 - INFO - __main__ - Step 125762: {'lr': 3.236782703797228e-05, 'samples': 24146304, 'steps': 125761, 'loss/train': 1.2346758842468262} 08/31/2021 12:03:18 - INFO - __main__ - Step 125763: {'lr': 3.2365215544363864e-05, 'samples': 24146496, 'steps': 125762, 'loss/train': 0.48469144105911255} 08/31/2021 12:03:18 - INFO - __main__ - Step 125764: {'lr': 3.236260414881836e-05, 'samples': 24146688, 'steps': 125763, 'loss/train': 0.8882089853286743} 08/31/2021 12:03:20 - INFO - __main__ - Step 125765: {'lr': 3.23599928513369e-05, 'samples': 24146880, 'steps': 125764, 'loss/train': 1.2432594299316406} 08/31/2021 12:03:21 - INFO - __main__ - Step 125766: {'lr': 3.235738165192065e-05, 'samples': 24147072, 'steps': 125765, 'loss/train': 0.6446200013160706} 08/31/2021 12:03:21 - INFO - __main__ - Step 125767: {'lr': 3.2354770550570876e-05, 'samples': 24147264, 'steps': 125766, 'loss/train': 0.014988083392381668} 08/31/2021 12:03:22 - INFO - __main__ - Step 125768: {'lr': 3.235215954728862e-05, 'samples': 24147456, 'steps': 125767, 'loss/train': 0.014922108501195908} 08/31/2021 12:03:22 - INFO - __main__ - Step 125769: {'lr': 3.234954864207512e-05, 'samples': 24147648, 'steps': 125768, 'loss/train': 1.3539127111434937} 08/31/2021 12:03:22 - INFO - __main__ - Step 125770: {'lr': 3.234693783493156e-05, 'samples': 24147840, 'steps': 125769, 'loss/train': 0.8340188264846802} 08/31/2021 12:03:24 - INFO - __main__ - Step 125771: {'lr': 3.234432712585911e-05, 'samples': 24148032, 'steps': 125770, 'loss/train': 1.9429408311843872} 08/31/2021 12:03:24 - INFO - __main__ - Step 125772: {'lr': 3.2341716514858954e-05, 'samples': 24148224, 'steps': 125771, 'loss/train': 0.9017981290817261} 08/31/2021 12:03:25 - INFO - __main__ - Step 125773: {'lr': 3.233910600193224e-05, 'samples': 24148416, 'steps': 125772, 'loss/train': 0.692733645439148} 08/31/2021 12:03:25 - INFO - __main__ - Step 125774: {'lr': 3.2336495587080187e-05, 'samples': 24148608, 'steps': 125773, 'loss/train': 1.018841028213501} 08/31/2021 12:03:25 - INFO - __main__ - Step 125775: {'lr': 3.233388527030395e-05, 'samples': 24148800, 'steps': 125774, 'loss/train': 1.4780470132827759} 08/31/2021 12:03:27 - INFO - __main__ - Step 125776: {'lr': 3.2331275051604715e-05, 'samples': 24148992, 'steps': 125775, 'loss/train': 0.10042077302932739} 08/31/2021 12:03:27 - INFO - __main__ - Step 125777: {'lr': 3.232866493098363e-05, 'samples': 24149184, 'steps': 125776, 'loss/train': 0.8074818849563599} 08/31/2021 12:03:28 - INFO - __main__ - Step 125778: {'lr': 3.23260549084419e-05, 'samples': 24149376, 'steps': 125777, 'loss/train': 0.7637161612510681} 08/31/2021 12:03:28 - INFO - __main__ - Step 125779: {'lr': 3.232344498398068e-05, 'samples': 24149568, 'steps': 125778, 'loss/train': 1.2512763738632202} 08/31/2021 12:03:28 - INFO - __main__ - Step 125780: {'lr': 3.232083515760117e-05, 'samples': 24149760, 'steps': 125779, 'loss/train': 0.4390775263309479} 08/31/2021 12:03:30 - INFO - __main__ - Step 125781: {'lr': 3.231822542930457e-05, 'samples': 24149952, 'steps': 125780, 'loss/train': 1.3531224727630615} 08/31/2021 12:03:30 - INFO - __main__ - Step 125782: {'lr': 3.231561579909198e-05, 'samples': 24150144, 'steps': 125781, 'loss/train': 0.5964276194572449} 08/31/2021 12:03:31 - INFO - __main__ - Step 125783: {'lr': 3.2313006266964595e-05, 'samples': 24150336, 'steps': 125782, 'loss/train': 1.5600534677505493} 08/31/2021 12:03:31 - INFO - __main__ - Step 125784: {'lr': 3.231039683292364e-05, 'samples': 24150528, 'steps': 125783, 'loss/train': 0.6302226781845093} 08/31/2021 12:03:31 - INFO - __main__ - Step 125785: {'lr': 3.230778749697025e-05, 'samples': 24150720, 'steps': 125784, 'loss/train': 1.3873372077941895} 08/31/2021 12:03:33 - INFO - __main__ - Step 125786: {'lr': 3.2305178259105586e-05, 'samples': 24150912, 'steps': 125785, 'loss/train': 1.2080038785934448} 08/31/2021 12:03:33 - INFO - __main__ - Step 125787: {'lr': 3.230256911933088e-05, 'samples': 24151104, 'steps': 125786, 'loss/train': 1.2953459024429321} 08/31/2021 12:03:34 - INFO - __main__ - Step 125788: {'lr': 3.229996007764727e-05, 'samples': 24151296, 'steps': 125787, 'loss/train': 1.5835046768188477} 08/31/2021 12:03:34 - INFO - __main__ - Step 125789: {'lr': 3.229735113405593e-05, 'samples': 24151488, 'steps': 125788, 'loss/train': 0.9858545064926147} 08/31/2021 12:03:34 - INFO - __main__ - Step 125790: {'lr': 3.229474228855805e-05, 'samples': 24151680, 'steps': 125789, 'loss/train': 0.1339004784822464} 08/31/2021 12:03:36 - INFO - __main__ - Step 125791: {'lr': 3.229213354115479e-05, 'samples': 24151872, 'steps': 125790, 'loss/train': 1.1687079668045044} 08/31/2021 12:03:36 - INFO - __main__ - Step 125792: {'lr': 3.228952489184736e-05, 'samples': 24152064, 'steps': 125791, 'loss/train': 0.9782292246818542} 08/31/2021 12:03:37 - INFO - __main__ - Step 125793: {'lr': 3.2286916340636876e-05, 'samples': 24152256, 'steps': 125792, 'loss/train': 0.6838768720626831} 08/31/2021 12:03:37 - INFO - __main__ - Step 125794: {'lr': 3.228430788752465e-05, 'samples': 24152448, 'steps': 125793, 'loss/train': 0.5282577276229858} 08/31/2021 12:03:37 - INFO - __main__ - Step 125795: {'lr': 3.2281699532511674e-05, 'samples': 24152640, 'steps': 125794, 'loss/train': 1.7154885530471802} 08/31/2021 12:03:39 - INFO - __main__ - Step 125796: {'lr': 3.2279091275599194e-05, 'samples': 24152832, 'steps': 125795, 'loss/train': 1.6209970712661743} 08/31/2021 12:03:39 - INFO - __main__ - Step 125797: {'lr': 3.227648311678841e-05, 'samples': 24153024, 'steps': 125796, 'loss/train': 0.4984807074069977} 08/31/2021 12:03:40 - INFO - __main__ - Step 125798: {'lr': 3.227387505608048e-05, 'samples': 24153216, 'steps': 125797, 'loss/train': 1.0968742370605469} 08/31/2021 12:03:40 - INFO - __main__ - Step 125799: {'lr': 3.227126709347658e-05, 'samples': 24153408, 'steps': 125798, 'loss/train': 0.5025144815444946} 08/31/2021 12:03:40 - INFO - __main__ - Step 125800: {'lr': 3.226865922897787e-05, 'samples': 24153600, 'steps': 125799, 'loss/train': 0.5854341983795166} 08/31/2021 12:03:42 - INFO - __main__ - Step 125801: {'lr': 3.226605146258557e-05, 'samples': 24153792, 'steps': 125800, 'loss/train': 1.2422999143600464} 08/31/2021 12:03:43 - INFO - __main__ - Step 125802: {'lr': 3.226344379430082e-05, 'samples': 24153984, 'steps': 125801, 'loss/train': 1.3774096965789795} 08/31/2021 12:03:43 - INFO - __main__ - Step 125803: {'lr': 3.226083622412479e-05, 'samples': 24154176, 'steps': 125802, 'loss/train': 1.5123403072357178} 08/31/2021 12:03:43 - INFO - __main__ - Step 125804: {'lr': 3.225822875205869e-05, 'samples': 24154368, 'steps': 125803, 'loss/train': 0.8340136408805847} 08/31/2021 12:03:44 - INFO - __main__ - Step 125805: {'lr': 3.225562137810364e-05, 'samples': 24154560, 'steps': 125804, 'loss/train': 0.7254128456115723} 08/31/2021 12:03:44 - INFO - __main__ - Step 125806: {'lr': 3.2253014102260895e-05, 'samples': 24154752, 'steps': 125805, 'loss/train': 0.7868300676345825} 08/31/2021 12:03:45 - INFO - __main__ - Step 125807: {'lr': 3.2250406924531544e-05, 'samples': 24154944, 'steps': 125806, 'loss/train': 0.31904536485671997} 08/31/2021 12:03:46 - INFO - __main__ - Step 125808: {'lr': 3.224779984491685e-05, 'samples': 24155136, 'steps': 125807, 'loss/train': 0.4001975655555725} 08/31/2021 12:03:46 - INFO - __main__ - Step 125809: {'lr': 3.22451928634179e-05, 'samples': 24155328, 'steps': 125808, 'loss/train': 1.3189209699630737} 08/31/2021 12:03:47 - INFO - __main__ - Step 125810: {'lr': 3.2242585980035905e-05, 'samples': 24155520, 'steps': 125809, 'loss/train': 1.3929897546768188} 08/31/2021 12:03:47 - INFO - __main__ - Step 125811: {'lr': 3.2239979194772033e-05, 'samples': 24155712, 'steps': 125810, 'loss/train': 0.9775086045265198} 08/31/2021 12:03:49 - INFO - __main__ - Step 125812: {'lr': 3.223737250762748e-05, 'samples': 24155904, 'steps': 125811, 'loss/train': 0.05397461727261543} 08/31/2021 12:03:49 - INFO - __main__ - Step 125813: {'lr': 3.2234765918603385e-05, 'samples': 24156096, 'steps': 125812, 'loss/train': 1.2851448059082031} 08/31/2021 12:03:49 - INFO - __main__ - Step 125814: {'lr': 3.2232159427700966e-05, 'samples': 24156288, 'steps': 125813, 'loss/train': 1.3504745960235596} 08/31/2021 12:03:50 - INFO - __main__ - Step 125815: {'lr': 3.2229553034921365e-05, 'samples': 24156480, 'steps': 125814, 'loss/train': 1.1632875204086304} 08/31/2021 12:03:50 - INFO - __main__ - Step 125816: {'lr': 3.222694674026577e-05, 'samples': 24156672, 'steps': 125815, 'loss/train': 1.0323652029037476} 08/31/2021 12:03:52 - INFO - __main__ - Step 125817: {'lr': 3.222434054373535e-05, 'samples': 24156864, 'steps': 125816, 'loss/train': 1.0359139442443848} 08/31/2021 12:03:53 - INFO - __main__ - Step 125818: {'lr': 3.2221734445331275e-05, 'samples': 24157056, 'steps': 125817, 'loss/train': 0.6827239990234375} 08/31/2021 12:03:53 - INFO - __main__ - Step 125819: {'lr': 3.221912844505473e-05, 'samples': 24157248, 'steps': 125818, 'loss/train': 1.1122758388519287} 08/31/2021 12:03:53 - INFO - __main__ - Step 125820: {'lr': 3.2216522542906885e-05, 'samples': 24157440, 'steps': 125819, 'loss/train': 1.7071664333343506} 08/31/2021 12:03:54 - INFO - __main__ - Step 125821: {'lr': 3.221391673888899e-05, 'samples': 24157632, 'steps': 125820, 'loss/train': 1.3739593029022217} 08/31/2021 12:03:55 - INFO - __main__ - Step 125822: {'lr': 3.221131103300207e-05, 'samples': 24157824, 'steps': 125821, 'loss/train': 1.2730307579040527} 08/31/2021 12:03:56 - INFO - __main__ - Step 125823: {'lr': 3.220870542524737e-05, 'samples': 24158016, 'steps': 125822, 'loss/train': 1.0839190483093262} 08/31/2021 12:03:56 - INFO - __main__ - Step 125824: {'lr': 3.220609991562606e-05, 'samples': 24158208, 'steps': 125823, 'loss/train': 0.9995583295822144} 08/31/2021 12:03:56 - INFO - __main__ - Step 125825: {'lr': 3.220349450413934e-05, 'samples': 24158400, 'steps': 125824, 'loss/train': 1.3559516668319702} 08/31/2021 12:03:57 - INFO - __main__ - Step 125826: {'lr': 3.220088919078834e-05, 'samples': 24158592, 'steps': 125825, 'loss/train': 1.475358247756958} 08/31/2021 12:03:58 - INFO - __main__ - Step 125827: {'lr': 3.219828397557428e-05, 'samples': 24158784, 'steps': 125826, 'loss/train': 1.2942805290222168} 08/31/2021 12:03:59 - INFO - __main__ - Step 125828: {'lr': 3.2195678858498304e-05, 'samples': 24158976, 'steps': 125827, 'loss/train': 1.078782320022583} 08/31/2021 12:03:59 - INFO - __main__ - Step 125829: {'lr': 3.21930738395616e-05, 'samples': 24159168, 'steps': 125828, 'loss/train': 1.4147508144378662} 08/31/2021 12:03:59 - INFO - __main__ - Step 125830: {'lr': 3.2190468918765344e-05, 'samples': 24159360, 'steps': 125829, 'loss/train': 0.26746460795402527} 08/31/2021 12:04:00 - INFO - __main__ - Step 125831: {'lr': 3.2187864096110686e-05, 'samples': 24159552, 'steps': 125830, 'loss/train': 0.6815896034240723} 08/31/2021 12:04:01 - INFO - __main__ - Step 125832: {'lr': 3.21852593715988e-05, 'samples': 24159744, 'steps': 125831, 'loss/train': 1.4181630611419678} 08/31/2021 12:04:01 - INFO - __main__ - Step 125833: {'lr': 3.218265474523091e-05, 'samples': 24159936, 'steps': 125832, 'loss/train': 0.03679288923740387} 08/31/2021 12:04:02 - INFO - __main__ - Step 125834: {'lr': 3.218005021700815e-05, 'samples': 24160128, 'steps': 125833, 'loss/train': 0.43594905734062195} 08/31/2021 12:04:02 - INFO - __main__ - Step 125835: {'lr': 3.217744578693174e-05, 'samples': 24160320, 'steps': 125834, 'loss/train': 1.0935468673706055} 08/31/2021 12:04:03 - INFO - __main__ - Step 125836: {'lr': 3.217484145500274e-05, 'samples': 24160512, 'steps': 125835, 'loss/train': 1.209703803062439} 08/31/2021 12:04:04 - INFO - __main__ - Step 125837: {'lr': 3.2172237221222425e-05, 'samples': 24160704, 'steps': 125836, 'loss/train': 1.3685530424118042} 08/31/2021 12:04:05 - INFO - __main__ - Step 125838: {'lr': 3.216963308559193e-05, 'samples': 24160896, 'steps': 125837, 'loss/train': 0.04806911200284958} 08/31/2021 12:04:05 - INFO - __main__ - Step 125839: {'lr': 3.216702904811242e-05, 'samples': 24161088, 'steps': 125838, 'loss/train': 1.6340266466140747} 08/31/2021 12:04:05 - INFO - __main__ - Step 125840: {'lr': 3.2164425108785114e-05, 'samples': 24161280, 'steps': 125839, 'loss/train': 1.243589162826538} 08/31/2021 12:04:06 - INFO - __main__ - Step 125841: {'lr': 3.2161821267611134e-05, 'samples': 24161472, 'steps': 125840, 'loss/train': 1.7207419872283936} 08/31/2021 12:04:06 - INFO - __main__ - Step 125842: {'lr': 3.21592175245917e-05, 'samples': 24161664, 'steps': 125841, 'loss/train': 0.6138210892677307} 08/31/2021 12:04:07 - INFO - __main__ - Step 125843: {'lr': 3.215661387972793e-05, 'samples': 24161856, 'steps': 125842, 'loss/train': 0.9011722207069397} 08/31/2021 12:04:08 - INFO - __main__ - Step 125844: {'lr': 3.215401033302104e-05, 'samples': 24162048, 'steps': 125843, 'loss/train': 0.5668893456459045} 08/31/2021 12:04:08 - INFO - __main__ - Step 125845: {'lr': 3.215140688447221e-05, 'samples': 24162240, 'steps': 125844, 'loss/train': 0.9018459320068359} 08/31/2021 12:04:09 - INFO - __main__ - Step 125846: {'lr': 3.214880353408256e-05, 'samples': 24162432, 'steps': 125845, 'loss/train': 0.6370794177055359} 08/31/2021 12:04:09 - INFO - __main__ - Step 125847: {'lr': 3.214620028185333e-05, 'samples': 24162624, 'steps': 125846, 'loss/train': 1.3489892482757568} 08/31/2021 12:04:10 - INFO - __main__ - Step 125848: {'lr': 3.2143597127785695e-05, 'samples': 24162816, 'steps': 125847, 'loss/train': 0.8950036764144897} 08/31/2021 12:04:11 - INFO - __main__ - Step 125849: {'lr': 3.214099407188076e-05, 'samples': 24163008, 'steps': 125848, 'loss/train': 1.1126596927642822} 08/31/2021 12:04:11 - INFO - __main__ - Step 125850: {'lr': 3.2138391114139715e-05, 'samples': 24163200, 'steps': 125849, 'loss/train': 0.9080826640129089} 08/31/2021 12:04:12 - INFO - __main__ - Step 125851: {'lr': 3.213578825456376e-05, 'samples': 24163392, 'steps': 125850, 'loss/train': 1.1006799936294556} 08/31/2021 12:04:12 - INFO - __main__ - Step 125852: {'lr': 3.2133185493154025e-05, 'samples': 24163584, 'steps': 125851, 'loss/train': 0.8508709073066711} 08/31/2021 12:04:14 - INFO - __main__ - Step 125853: {'lr': 3.213058282991174e-05, 'samples': 24163776, 'steps': 125852, 'loss/train': 0.9543342590332031} 08/31/2021 12:04:14 - INFO - __main__ - Step 125854: {'lr': 3.212798026483807e-05, 'samples': 24163968, 'steps': 125853, 'loss/train': 1.0923258066177368} 08/31/2021 12:04:15 - INFO - __main__ - Step 125855: {'lr': 3.212537779793415e-05, 'samples': 24164160, 'steps': 125854, 'loss/train': 1.4742374420166016} 08/31/2021 12:04:15 - INFO - __main__ - Step 125856: {'lr': 3.2122775429201164e-05, 'samples': 24164352, 'steps': 125855, 'loss/train': 0.11752788722515106} 08/31/2021 12:04:15 - INFO - __main__ - Step 125857: {'lr': 3.2120173158640297e-05, 'samples': 24164544, 'steps': 125856, 'loss/train': 1.369403600692749} 08/31/2021 12:04:17 - INFO - __main__ - Step 125858: {'lr': 3.211757098625273e-05, 'samples': 24164736, 'steps': 125857, 'loss/train': 0.9964123368263245} 08/31/2021 12:04:17 - INFO - __main__ - Step 125859: {'lr': 3.211496891203961e-05, 'samples': 24164928, 'steps': 125858, 'loss/train': 0.5389411449432373} 08/31/2021 12:04:18 - INFO - __main__ - Step 125860: {'lr': 3.211236693600214e-05, 'samples': 24165120, 'steps': 125859, 'loss/train': 0.9241765737533569} 08/31/2021 12:04:18 - INFO - __main__ - Step 125861: {'lr': 3.2109765058141534e-05, 'samples': 24165312, 'steps': 125860, 'loss/train': 1.4402320384979248} 08/31/2021 12:04:18 - INFO - __main__ - Step 125862: {'lr': 3.210716327845883e-05, 'samples': 24165504, 'steps': 125861, 'loss/train': 1.3399258852005005} 08/31/2021 12:04:20 - INFO - __main__ - Step 125863: {'lr': 3.210456159695527e-05, 'samples': 24165696, 'steps': 125862, 'loss/train': 0.8254004120826721} 08/31/2021 12:04:20 - INFO - __main__ - Step 125864: {'lr': 3.2101960013632056e-05, 'samples': 24165888, 'steps': 125863, 'loss/train': 1.1991069316864014} 08/31/2021 12:04:21 - INFO - __main__ - Step 125865: {'lr': 3.209935852849033e-05, 'samples': 24166080, 'steps': 125864, 'loss/train': 1.250570297241211} 08/31/2021 12:04:21 - INFO - __main__ - Step 125866: {'lr': 3.209675714153126e-05, 'samples': 24166272, 'steps': 125865, 'loss/train': 1.4365030527114868} 08/31/2021 12:04:21 - INFO - __main__ - Step 125867: {'lr': 3.2094155852756016e-05, 'samples': 24166464, 'steps': 125866, 'loss/train': 1.2159837484359741} 08/31/2021 12:04:22 - INFO - __main__ - Step 125868: {'lr': 3.2091554662165815e-05, 'samples': 24166656, 'steps': 125867, 'loss/train': 1.0812926292419434} 08/31/2021 12:04:24 - INFO - __main__ - Step 125869: {'lr': 3.2088953569761796e-05, 'samples': 24166848, 'steps': 125868, 'loss/train': 1.2492293119430542} 08/31/2021 12:04:24 - INFO - __main__ - Step 125870: {'lr': 3.20863525755451e-05, 'samples': 24167040, 'steps': 125869, 'loss/train': 0.8476707935333252} 08/31/2021 12:04:24 - INFO - __main__ - Step 125871: {'lr': 3.208375167951697e-05, 'samples': 24167232, 'steps': 125870, 'loss/train': 1.0945104360580444} 08/31/2021 12:04:25 - INFO - __main__ - Step 125872: {'lr': 3.208115088167851e-05, 'samples': 24167424, 'steps': 125871, 'loss/train': 1.4621508121490479} 08/31/2021 12:04:25 - INFO - __main__ - Step 125873: {'lr': 3.207855018203093e-05, 'samples': 24167616, 'steps': 125872, 'loss/train': 1.080385684967041} 08/31/2021 12:04:27 - INFO - __main__ - Step 125874: {'lr': 3.2075949580575386e-05, 'samples': 24167808, 'steps': 125873, 'loss/train': 1.6063693761825562} 08/31/2021 12:04:27 - INFO - __main__ - Step 125875: {'lr': 3.207334907731313e-05, 'samples': 24168000, 'steps': 125874, 'loss/train': 0.7732508778572083} 08/31/2021 12:04:28 - INFO - __main__ - Step 125876: {'lr': 3.207074867224519e-05, 'samples': 24168192, 'steps': 125875, 'loss/train': 0.8418322801589966} 08/31/2021 12:04:28 - INFO - __main__ - Step 125877: {'lr': 3.206814836537281e-05, 'samples': 24168384, 'steps': 125876, 'loss/train': 1.0063748359680176} 08/31/2021 12:04:28 - INFO - __main__ - Step 125878: {'lr': 3.2065548156697156e-05, 'samples': 24168576, 'steps': 125877, 'loss/train': 1.2262648344039917} 08/31/2021 12:04:30 - INFO - __main__ - Step 125879: {'lr': 3.2062948046219395e-05, 'samples': 24168768, 'steps': 125878, 'loss/train': 0.8716806769371033} 08/31/2021 12:04:30 - INFO - __main__ - Step 125880: {'lr': 3.2060348033940725e-05, 'samples': 24168960, 'steps': 125879, 'loss/train': 0.9030430912971497} 08/31/2021 12:04:31 - INFO - __main__ - Step 125881: {'lr': 3.205774811986231e-05, 'samples': 24169152, 'steps': 125880, 'loss/train': 0.3724319040775299} 08/31/2021 12:04:31 - INFO - __main__ - Step 125882: {'lr': 3.205514830398529e-05, 'samples': 24169344, 'steps': 125881, 'loss/train': 0.9955357909202576} 08/31/2021 12:04:31 - INFO - __main__ - Step 125883: {'lr': 3.205254858631085e-05, 'samples': 24169536, 'steps': 125882, 'loss/train': 1.5430454015731812} 08/31/2021 12:04:33 - INFO - __main__ - Step 125884: {'lr': 3.2049948966840185e-05, 'samples': 24169728, 'steps': 125883, 'loss/train': 0.7524218559265137} 08/31/2021 12:04:34 - INFO - __main__ - Step 125885: {'lr': 3.204734944557444e-05, 'samples': 24169920, 'steps': 125884, 'loss/train': 0.9837575554847717} 08/31/2021 12:04:34 - INFO - __main__ - Step 125886: {'lr': 3.2044750022514805e-05, 'samples': 24170112, 'steps': 125885, 'loss/train': 0.7696859240531921} 08/31/2021 12:04:34 - INFO - __main__ - Step 125887: {'lr': 3.204215069766245e-05, 'samples': 24170304, 'steps': 125886, 'loss/train': 0.7215332388877869} 08/31/2021 12:04:35 - INFO - __main__ - Step 125888: {'lr': 3.203955147101856e-05, 'samples': 24170496, 'steps': 125887, 'loss/train': 0.9355888962745667} 08/31/2021 12:04:36 - INFO - __main__ - Step 125889: {'lr': 3.203695234258427e-05, 'samples': 24170688, 'steps': 125888, 'loss/train': 0.0910048708319664} 08/31/2021 12:04:37 - INFO - __main__ - Step 125890: {'lr': 3.203435331236074e-05, 'samples': 24170880, 'steps': 125889, 'loss/train': 1.3876068592071533} 08/31/2021 12:04:37 - INFO - __main__ - Step 125891: {'lr': 3.203175438034916e-05, 'samples': 24171072, 'steps': 125890, 'loss/train': 1.4718751907348633} 08/31/2021 12:04:37 - INFO - __main__ - Step 125892: {'lr': 3.2029155546550725e-05, 'samples': 24171264, 'steps': 125891, 'loss/train': 1.3853217363357544} 08/31/2021 12:04:38 - INFO - __main__ - Step 125893: {'lr': 3.2026556810966585e-05, 'samples': 24171456, 'steps': 125892, 'loss/train': 0.33634045720100403} 08/31/2021 12:04:39 - INFO - __main__ - Step 125894: {'lr': 3.2023958173597934e-05, 'samples': 24171648, 'steps': 125893, 'loss/train': 0.5022333860397339} 08/31/2021 12:04:40 - INFO - __main__ - Step 125895: {'lr': 3.202135963444591e-05, 'samples': 24171840, 'steps': 125894, 'loss/train': 0.3410131335258484} 08/31/2021 12:04:40 - INFO - __main__ - Step 125896: {'lr': 3.201876119351169e-05, 'samples': 24172032, 'steps': 125895, 'loss/train': 1.545192837715149} 08/31/2021 12:04:40 - INFO - __main__ - Step 125897: {'lr': 3.2016162850796446e-05, 'samples': 24172224, 'steps': 125896, 'loss/train': 0.4060196578502655} 08/31/2021 12:04:41 - INFO - __main__ - Step 125898: {'lr': 3.201356460630137e-05, 'samples': 24172416, 'steps': 125897, 'loss/train': 0.05258385092020035} 08/31/2021 12:04:42 - INFO - __main__ - Step 125899: {'lr': 3.20109664600276e-05, 'samples': 24172608, 'steps': 125898, 'loss/train': 1.2868826389312744} 08/31/2021 12:04:43 - INFO - __main__ - Step 125900: {'lr': 3.200836841197635e-05, 'samples': 24172800, 'steps': 125899, 'loss/train': 1.4021308422088623} 08/31/2021 12:04:43 - INFO - __main__ - Step 125901: {'lr': 3.2005770462148754e-05, 'samples': 24172992, 'steps': 125900, 'loss/train': 1.2511072158813477} 08/31/2021 12:04:44 - INFO - __main__ - Step 125902: {'lr': 3.200317261054605e-05, 'samples': 24173184, 'steps': 125901, 'loss/train': 0.9430012106895447} 08/31/2021 12:04:44 - INFO - __main__ - Step 125903: {'lr': 3.2000574857169284e-05, 'samples': 24173376, 'steps': 125902, 'loss/train': 1.6190060377120972} 08/31/2021 12:04:45 - INFO - __main__ - Step 125904: {'lr': 3.199797720201972e-05, 'samples': 24173568, 'steps': 125903, 'loss/train': 1.3520749807357788} 08/31/2021 12:04:46 - INFO - __main__ - Step 125905: {'lr': 3.1995379645098495e-05, 'samples': 24173760, 'steps': 125904, 'loss/train': 0.7880485653877258} 08/31/2021 12:04:46 - INFO - __main__ - Step 125906: {'lr': 3.199278218640678e-05, 'samples': 24173952, 'steps': 125905, 'loss/train': 1.024257779121399} 08/31/2021 12:04:47 - INFO - __main__ - Step 125907: {'lr': 3.1990184825945764e-05, 'samples': 24174144, 'steps': 125906, 'loss/train': 0.9255952835083008} 08/31/2021 12:04:47 - INFO - __main__ - Step 125908: {'lr': 3.1987587563716584e-05, 'samples': 24174336, 'steps': 125907, 'loss/train': 1.4530200958251953} 08/31/2021 12:04:48 - INFO - __main__ - Step 125909: {'lr': 3.1984990399720444e-05, 'samples': 24174528, 'steps': 125908, 'loss/train': 0.6261360049247742} 08/31/2021 12:04:49 - INFO - __main__ - Step 125910: {'lr': 3.198239333395852e-05, 'samples': 24174720, 'steps': 125909, 'loss/train': 0.8780340552330017} 08/31/2021 12:04:49 - INFO - __main__ - Step 125911: {'lr': 3.1979796366431946e-05, 'samples': 24174912, 'steps': 125910, 'loss/train': 1.4518628120422363} 08/31/2021 12:04:50 - INFO - __main__ - Step 125912: {'lr': 3.1977199497141926e-05, 'samples': 24175104, 'steps': 125911, 'loss/train': 0.8771794438362122} 08/31/2021 12:04:50 - INFO - __main__ - Step 125913: {'lr': 3.1974602726089594e-05, 'samples': 24175296, 'steps': 125912, 'loss/train': 0.41259321570396423} 08/31/2021 12:04:52 - INFO - __main__ - Step 125914: {'lr': 3.197200605327616e-05, 'samples': 24175488, 'steps': 125913, 'loss/train': 1.6757338047027588} 08/31/2021 12:04:52 - INFO - __main__ - Step 125915: {'lr': 3.196940947870283e-05, 'samples': 24175680, 'steps': 125914, 'loss/train': 0.8961406946182251} 08/31/2021 12:04:53 - INFO - __main__ - Step 125916: {'lr': 3.196681300237067e-05, 'samples': 24175872, 'steps': 125915, 'loss/train': 1.5978469848632812} 08/31/2021 12:04:53 - INFO - __main__ - Step 125917: {'lr': 3.196421662428089e-05, 'samples': 24176064, 'steps': 125916, 'loss/train': 1.1647130250930786} 08/31/2021 12:04:53 - INFO - __main__ - Step 125918: {'lr': 3.196162034443467e-05, 'samples': 24176256, 'steps': 125917, 'loss/train': 1.064445972442627} 08/31/2021 12:04:54 - INFO - __main__ - Step 125919: {'lr': 3.195902416283317e-05, 'samples': 24176448, 'steps': 125918, 'loss/train': 1.0480692386627197} 08/31/2021 12:04:55 - INFO - __main__ - Step 125920: {'lr': 3.195642807947757e-05, 'samples': 24176640, 'steps': 125919, 'loss/train': 0.888758659362793} 08/31/2021 12:04:55 - INFO - __main__ - Step 125921: {'lr': 3.195383209436906e-05, 'samples': 24176832, 'steps': 125920, 'loss/train': 0.5052844882011414} 08/31/2021 12:04:56 - INFO - __main__ - Step 125922: {'lr': 3.195123620750878e-05, 'samples': 24177024, 'steps': 125921, 'loss/train': 0.8276864886283875} 08/31/2021 12:04:56 - INFO - __main__ - Step 125923: {'lr': 3.194864041889789e-05, 'samples': 24177216, 'steps': 125922, 'loss/train': 1.2199134826660156} 08/31/2021 12:04:56 - INFO - __main__ - Step 125924: {'lr': 3.19460447285376e-05, 'samples': 24177408, 'steps': 125923, 'loss/train': 1.6370563507080078} 08/31/2021 12:04:58 - INFO - __main__ - Step 125925: {'lr': 3.1943449136429046e-05, 'samples': 24177600, 'steps': 125924, 'loss/train': 1.6942527294158936} 08/31/2021 12:04:59 - INFO - __main__ - Step 125926: {'lr': 3.194085364257343e-05, 'samples': 24177792, 'steps': 125925, 'loss/train': 0.7418444156646729} 08/31/2021 12:04:59 - INFO - __main__ - Step 125927: {'lr': 3.193825824697189e-05, 'samples': 24177984, 'steps': 125926, 'loss/train': 1.1809731721878052} 08/31/2021 12:05:00 - INFO - __main__ - Step 125928: {'lr': 3.1935662949625574e-05, 'samples': 24178176, 'steps': 125927, 'loss/train': 1.8019299507141113} 08/31/2021 12:05:00 - INFO - __main__ - Step 125929: {'lr': 3.193306775053578e-05, 'samples': 24178368, 'steps': 125928, 'loss/train': 1.211064100265503} 08/31/2021 12:05:02 - INFO - __main__ - Step 125930: {'lr': 3.19304726497035e-05, 'samples': 24178560, 'steps': 125929, 'loss/train': 1.0871624946594238} 08/31/2021 12:05:02 - INFO - __main__ - Step 125931: {'lr': 3.192787764712998e-05, 'samples': 24178752, 'steps': 125930, 'loss/train': 0.029974503442645073} 08/31/2021 12:05:03 - INFO - __main__ - Step 125932: {'lr': 3.192528274281642e-05, 'samples': 24178944, 'steps': 125931, 'loss/train': 0.014794224873185158} 08/31/2021 12:05:03 - INFO - __main__ - Step 125933: {'lr': 3.192268793676395e-05, 'samples': 24179136, 'steps': 125932, 'loss/train': 0.5945993661880493} 08/31/2021 12:05:03 - INFO - __main__ - Step 125934: {'lr': 3.192009322897374e-05, 'samples': 24179328, 'steps': 125933, 'loss/train': 1.0964546203613281} 08/31/2021 12:05:04 - INFO - __main__ - Step 125935: {'lr': 3.191749861944698e-05, 'samples': 24179520, 'steps': 125934, 'loss/train': 1.131288766860962} 08/31/2021 12:05:05 - INFO - __main__ - Step 125936: {'lr': 3.191490410818484e-05, 'samples': 24179712, 'steps': 125935, 'loss/train': 1.7022124528884888} 08/31/2021 12:05:06 - INFO - __main__ - Step 125937: {'lr': 3.191230969518846e-05, 'samples': 24179904, 'steps': 125936, 'loss/train': 0.5672616362571716} 08/31/2021 12:05:06 - INFO - __main__ - Step 125938: {'lr': 3.1909715380459056e-05, 'samples': 24180096, 'steps': 125937, 'loss/train': 0.4897533059120178} 08/31/2021 12:05:06 - INFO - __main__ - Step 125939: {'lr': 3.1907121163997744e-05, 'samples': 24180288, 'steps': 125938, 'loss/train': 1.1763806343078613} 08/31/2021 12:05:07 - INFO - __main__ - Step 125940: {'lr': 3.190452704580574e-05, 'samples': 24180480, 'steps': 125939, 'loss/train': 0.9171193242073059} 08/31/2021 12:05:09 - INFO - __main__ - Step 125941: {'lr': 3.190193302588418e-05, 'samples': 24180672, 'steps': 125940, 'loss/train': 1.141249656677246} 08/31/2021 12:05:09 - INFO - __main__ - Step 125942: {'lr': 3.189933910423429e-05, 'samples': 24180864, 'steps': 125941, 'loss/train': 1.270871877670288} 08/31/2021 12:05:10 - INFO - __main__ - Step 125943: {'lr': 3.1896745280857123e-05, 'samples': 24181056, 'steps': 125942, 'loss/train': 1.7545218467712402} 08/31/2021 12:05:10 - INFO - __main__ - Step 125944: {'lr': 3.189415155575395e-05, 'samples': 24181248, 'steps': 125943, 'loss/train': 0.1685589700937271} 08/31/2021 12:05:10 - INFO - __main__ - Step 125945: {'lr': 3.1891557928925896e-05, 'samples': 24181440, 'steps': 125944, 'loss/train': 1.1341445446014404} 08/31/2021 12:05:12 - INFO - __main__ - Step 125946: {'lr': 3.188896440037412e-05, 'samples': 24181632, 'steps': 125945, 'loss/train': 1.2046760320663452} 08/31/2021 12:05:12 - INFO - __main__ - Step 125947: {'lr': 3.188637097009983e-05, 'samples': 24181824, 'steps': 125946, 'loss/train': 0.8280325531959534} 08/31/2021 12:05:13 - INFO - __main__ - Step 125948: {'lr': 3.1883777638104185e-05, 'samples': 24182016, 'steps': 125947, 'loss/train': 1.1607673168182373} 08/31/2021 12:05:13 - INFO - __main__ - Step 125949: {'lr': 3.1881184404388334e-05, 'samples': 24182208, 'steps': 125948, 'loss/train': 2.0278728008270264} 08/31/2021 12:05:13 - INFO - __main__ - Step 125950: {'lr': 3.187859126895346e-05, 'samples': 24182400, 'steps': 125949, 'loss/train': 1.7064772844314575} 08/31/2021 12:05:14 - INFO - __main__ - Step 125951: {'lr': 3.187599823180071e-05, 'samples': 24182592, 'steps': 125950, 'loss/train': 0.8238695859909058} 08/31/2021 12:05:15 - INFO - __main__ - Step 125952: {'lr': 3.187340529293129e-05, 'samples': 24182784, 'steps': 125951, 'loss/train': 0.9052900671958923} 08/31/2021 12:05:16 - INFO - __main__ - Step 125953: {'lr': 3.1870812452346324e-05, 'samples': 24182976, 'steps': 125952, 'loss/train': 1.6296175718307495} 08/31/2021 12:05:16 - INFO - __main__ - Step 125954: {'lr': 3.1868219710047025e-05, 'samples': 24183168, 'steps': 125953, 'loss/train': 2.2814242839813232} 08/31/2021 12:05:17 - INFO - __main__ - Step 125955: {'lr': 3.186562706603452e-05, 'samples': 24183360, 'steps': 125954, 'loss/train': 1.8169255256652832} 08/31/2021 12:05:17 - INFO - __main__ - Step 125956: {'lr': 3.186303452031009e-05, 'samples': 24183552, 'steps': 125955, 'loss/train': 0.6092727780342102} 08/31/2021 12:05:18 - INFO - __main__ - Step 125957: {'lr': 3.186044207287472e-05, 'samples': 24183744, 'steps': 125956, 'loss/train': 1.3918540477752686} 08/31/2021 12:05:19 - INFO - __main__ - Step 125958: {'lr': 3.185784972372968e-05, 'samples': 24183936, 'steps': 125957, 'loss/train': 1.540930986404419} 08/31/2021 12:05:19 - INFO - __main__ - Step 125959: {'lr': 3.185525747287613e-05, 'samples': 24184128, 'steps': 125958, 'loss/train': 0.9289793968200684} 08/31/2021 12:05:20 - INFO - __main__ - Step 125960: {'lr': 3.1852665320315225e-05, 'samples': 24184320, 'steps': 125959, 'loss/train': 2.4651291370391846} 08/31/2021 12:05:20 - INFO - __main__ - Step 125961: {'lr': 3.185007326604814e-05, 'samples': 24184512, 'steps': 125960, 'loss/train': 0.8377465009689331} 08/31/2021 12:05:21 - INFO - __main__ - Step 125962: {'lr': 3.184748131007606e-05, 'samples': 24184704, 'steps': 125961, 'loss/train': 1.5910817384719849} 08/31/2021 12:05:22 - INFO - __main__ - Step 125963: {'lr': 3.1844889452400135e-05, 'samples': 24184896, 'steps': 125962, 'loss/train': 1.4527031183242798} 08/31/2021 12:05:22 - INFO - __main__ - Step 125964: {'lr': 3.1842297693021524e-05, 'samples': 24185088, 'steps': 125963, 'loss/train': 1.5072230100631714} 08/31/2021 12:05:23 - INFO - __main__ - Step 125965: {'lr': 3.183970603194142e-05, 'samples': 24185280, 'steps': 125964, 'loss/train': 1.2462515830993652} 08/31/2021 12:05:23 - INFO - __main__ - Step 125966: {'lr': 3.183711446916099e-05, 'samples': 24185472, 'steps': 125965, 'loss/train': 1.0038553476333618} 08/31/2021 12:05:24 - INFO - __main__ - Step 125967: {'lr': 3.183452300468137e-05, 'samples': 24185664, 'steps': 125966, 'loss/train': 0.8164885640144348} 08/31/2021 12:05:25 - INFO - __main__ - Step 125968: {'lr': 3.183193163850376e-05, 'samples': 24185856, 'steps': 125967, 'loss/train': 1.2800941467285156} 08/31/2021 12:05:25 - INFO - __main__ - Step 125969: {'lr': 3.182934037062934e-05, 'samples': 24186048, 'steps': 125968, 'loss/train': 0.9933526515960693} 08/31/2021 12:05:26 - INFO - __main__ - Step 125970: {'lr': 3.182674920105924e-05, 'samples': 24186240, 'steps': 125969, 'loss/train': 0.7365004420280457} 08/31/2021 12:05:26 - INFO - __main__ - Step 125971: {'lr': 3.182415812979461e-05, 'samples': 24186432, 'steps': 125970, 'loss/train': 0.9053400754928589} 08/31/2021 12:05:26 - INFO - __main__ - Step 125972: {'lr': 3.182156715683668e-05, 'samples': 24186624, 'steps': 125971, 'loss/train': 1.0289931297302246} 08/31/2021 12:05:28 - INFO - __main__ - Step 125973: {'lr': 3.181897628218655e-05, 'samples': 24186816, 'steps': 125972, 'loss/train': 1.299984097480774} 08/31/2021 12:05:28 - INFO - __main__ - Step 125974: {'lr': 3.1816385505845455e-05, 'samples': 24187008, 'steps': 125973, 'loss/train': 5.446741104125977} 08/31/2021 12:05:29 - INFO - __main__ - Step 125975: {'lr': 3.181379482781449e-05, 'samples': 24187200, 'steps': 125974, 'loss/train': 0.49651092290878296} 08/31/2021 12:05:29 - INFO - __main__ - Step 125976: {'lr': 3.181120424809489e-05, 'samples': 24187392, 'steps': 125975, 'loss/train': 1.276349425315857} 08/31/2021 12:05:29 - INFO - __main__ - Step 125977: {'lr': 3.180861376668778e-05, 'samples': 24187584, 'steps': 125976, 'loss/train': 1.2445247173309326} 08/31/2021 12:05:32 - INFO - __main__ - Step 125978: {'lr': 3.180602338359437e-05, 'samples': 24187776, 'steps': 125977, 'loss/train': 1.3444793224334717} 08/31/2021 12:05:32 - INFO - __main__ - Step 125979: {'lr': 3.180343309881578e-05, 'samples': 24187968, 'steps': 125978, 'loss/train': 1.017822504043579} 08/31/2021 12:05:32 - INFO - __main__ - Step 125980: {'lr': 3.180084291235319e-05, 'samples': 24188160, 'steps': 125979, 'loss/train': 1.1115707159042358} 08/31/2021 12:05:33 - INFO - __main__ - Step 125981: {'lr': 3.1798252824207814e-05, 'samples': 24188352, 'steps': 125980, 'loss/train': 0.5742868185043335} 08/31/2021 12:05:33 - INFO - __main__ - Step 125982: {'lr': 3.179566283438076e-05, 'samples': 24188544, 'steps': 125981, 'loss/train': 0.04486232250928879} 08/31/2021 12:05:34 - INFO - __main__ - Step 125983: {'lr': 3.17930729428732e-05, 'samples': 24188736, 'steps': 125982, 'loss/train': 0.9576754570007324} 08/31/2021 12:05:35 - INFO - __main__ - Step 125984: {'lr': 3.17904831496863e-05, 'samples': 24188928, 'steps': 125983, 'loss/train': 1.5032954216003418} 08/31/2021 12:05:35 - INFO - __main__ - Step 125985: {'lr': 3.178789345482125e-05, 'samples': 24189120, 'steps': 125984, 'loss/train': 1.4214556217193604} 08/31/2021 12:05:36 - INFO - __main__ - Step 125986: {'lr': 3.178530385827921e-05, 'samples': 24189312, 'steps': 125985, 'loss/train': 1.0692826509475708} 08/31/2021 12:05:36 - INFO - __main__ - Step 125987: {'lr': 3.1782714360061334e-05, 'samples': 24189504, 'steps': 125986, 'loss/train': 1.2223929166793823} 08/31/2021 12:05:38 - INFO - __main__ - Step 125988: {'lr': 3.1780124960168824e-05, 'samples': 24189696, 'steps': 125987, 'loss/train': 1.1476508378982544} 08/31/2021 12:05:38 - INFO - __main__ - Step 125989: {'lr': 3.1777535658602805e-05, 'samples': 24189888, 'steps': 125988, 'loss/train': 0.3982355296611786} 08/31/2021 12:05:39 - INFO - __main__ - Step 125990: {'lr': 3.1774946455364464e-05, 'samples': 24190080, 'steps': 125989, 'loss/train': 1.2421048879623413} 08/31/2021 12:05:39 - INFO - __main__ - Step 125991: {'lr': 3.177235735045497e-05, 'samples': 24190272, 'steps': 125990, 'loss/train': 1.696962833404541} 08/31/2021 12:05:39 - INFO - __main__ - Step 125992: {'lr': 3.1769768343875516e-05, 'samples': 24190464, 'steps': 125991, 'loss/train': 1.1297669410705566} 08/31/2021 12:05:41 - INFO - __main__ - Step 125993: {'lr': 3.176717943562721e-05, 'samples': 24190656, 'steps': 125992, 'loss/train': 0.785526692867279} 08/31/2021 12:05:41 - INFO - __main__ - Step 125994: {'lr': 3.1764590625711244e-05, 'samples': 24190848, 'steps': 125993, 'loss/train': 1.2115064859390259} 08/31/2021 12:05:42 - INFO - __main__ - Step 125995: {'lr': 3.176200191412876e-05, 'samples': 24191040, 'steps': 125994, 'loss/train': 1.4482316970825195} 08/31/2021 12:05:42 - INFO - __main__ - Step 125996: {'lr': 3.175941330088097e-05, 'samples': 24191232, 'steps': 125995, 'loss/train': 0.8974596858024597} 08/31/2021 12:05:42 - INFO - __main__ - Step 125997: {'lr': 3.175682478596903e-05, 'samples': 24191424, 'steps': 125996, 'loss/train': 1.7327890396118164} 08/31/2021 12:05:44 - INFO - __main__ - Step 125998: {'lr': 3.175423636939409e-05, 'samples': 24191616, 'steps': 125997, 'loss/train': 1.0689609050750732} 08/31/2021 12:05:44 - INFO - __main__ - Step 125999: {'lr': 3.175164805115732e-05, 'samples': 24191808, 'steps': 125998, 'loss/train': 1.0251033306121826} 08/31/2021 12:05:45 - INFO - __main__ - Step 126000: {'lr': 3.174905983125989e-05, 'samples': 24192000, 'steps': 125999, 'loss/train': 0.5479863286018372} 08/31/2021 12:05:45 - INFO - __main__ - Step 126001: {'lr': 3.174647170970296e-05, 'samples': 24192192, 'steps': 126000, 'loss/train': 0.8922865986824036} 08/31/2021 12:05:45 - INFO - __main__ - Step 126002: {'lr': 3.1743883686487704e-05, 'samples': 24192384, 'steps': 126001, 'loss/train': 1.0023273229599} 08/31/2021 12:05:46 - INFO - __main__ - Step 126003: {'lr': 3.174129576161533e-05, 'samples': 24192576, 'steps': 126002, 'loss/train': 0.2085873931646347} 08/31/2021 12:05:47 - INFO - __main__ - Step 126004: {'lr': 3.173870793508693e-05, 'samples': 24192768, 'steps': 126003, 'loss/train': 0.7137475609779358} 08/31/2021 12:05:48 - INFO - __main__ - Step 126005: {'lr': 3.17361202069037e-05, 'samples': 24192960, 'steps': 126004, 'loss/train': 0.3153257668018341} 08/31/2021 12:05:48 - INFO - __main__ - Step 126006: {'lr': 3.173353257706677e-05, 'samples': 24193152, 'steps': 126005, 'loss/train': 0.14061497151851654} 08/31/2021 12:05:48 - INFO - __main__ - Step 126007: {'lr': 3.173094504557739e-05, 'samples': 24193344, 'steps': 126006, 'loss/train': 2.597489595413208} 08/31/2021 12:05:49 - INFO - __main__ - Step 126008: {'lr': 3.1728357612436644e-05, 'samples': 24193536, 'steps': 126007, 'loss/train': 1.304693579673767} 08/31/2021 12:05:50 - INFO - __main__ - Step 126009: {'lr': 3.172577027764573e-05, 'samples': 24193728, 'steps': 126008, 'loss/train': 0.9563648700714111} 08/31/2021 12:05:51 - INFO - __main__ - Step 126010: {'lr': 3.172318304120583e-05, 'samples': 24193920, 'steps': 126009, 'loss/train': 0.7785175442695618} 08/31/2021 12:05:51 - INFO - __main__ - Step 126011: {'lr': 3.17205959031181e-05, 'samples': 24194112, 'steps': 126010, 'loss/train': 0.8346177339553833} 08/31/2021 12:05:52 - INFO - __main__ - Step 126012: {'lr': 3.171800886338369e-05, 'samples': 24194304, 'steps': 126011, 'loss/train': 0.09855272620916367} 08/31/2021 12:05:52 - INFO - __main__ - Step 126013: {'lr': 3.17154219220038e-05, 'samples': 24194496, 'steps': 126012, 'loss/train': 5.9585771560668945} 08/31/2021 12:05:52 - INFO - __main__ - Step 126014: {'lr': 3.1712835078979596e-05, 'samples': 24194688, 'steps': 126013, 'loss/train': 0.8017387986183167} 08/31/2021 12:05:54 - INFO - __main__ - Step 126015: {'lr': 3.1710248334312186e-05, 'samples': 24194880, 'steps': 126014, 'loss/train': 0.8926730155944824} 08/31/2021 12:05:54 - INFO - __main__ - Step 126016: {'lr': 3.1707661688002763e-05, 'samples': 24195072, 'steps': 126015, 'loss/train': 1.101283073425293} 08/31/2021 12:05:55 - INFO - __main__ - Step 126017: {'lr': 3.1705075140052494e-05, 'samples': 24195264, 'steps': 126016, 'loss/train': 1.5684893131256104} 08/31/2021 12:05:55 - INFO - __main__ - Step 126018: {'lr': 3.170248869046255e-05, 'samples': 24195456, 'steps': 126017, 'loss/train': 1.3764533996582031} 08/31/2021 12:05:55 - INFO - __main__ - Step 126019: {'lr': 3.169990233923412e-05, 'samples': 24195648, 'steps': 126018, 'loss/train': 1.23967707157135} 08/31/2021 12:05:57 - INFO - __main__ - Step 126020: {'lr': 3.169731608636831e-05, 'samples': 24195840, 'steps': 126019, 'loss/train': 1.7071980237960815} 08/31/2021 12:05:57 - INFO - __main__ - Step 126021: {'lr': 3.169472993186634e-05, 'samples': 24196032, 'steps': 126020, 'loss/train': 1.598314642906189} 08/31/2021 12:05:58 - INFO - __main__ - Step 126022: {'lr': 3.169214387572936e-05, 'samples': 24196224, 'steps': 126021, 'loss/train': 0.7566908597946167} 08/31/2021 12:05:58 - INFO - __main__ - Step 126023: {'lr': 3.1689557917958524e-05, 'samples': 24196416, 'steps': 126022, 'loss/train': 1.2588789463043213} 08/31/2021 12:05:58 - INFO - __main__ - Step 126024: {'lr': 3.1686972058555e-05, 'samples': 24196608, 'steps': 126023, 'loss/train': 0.7444194555282593} 08/31/2021 12:06:00 - INFO - __main__ - Step 126025: {'lr': 3.168438629752002e-05, 'samples': 24196800, 'steps': 126024, 'loss/train': 0.5770907402038574} 08/31/2021 12:06:00 - INFO - __main__ - Step 126026: {'lr': 3.168180063485462e-05, 'samples': 24196992, 'steps': 126025, 'loss/train': 0.8967384696006775} 08/31/2021 12:06:01 - INFO - __main__ - Step 126027: {'lr': 3.167921507056004e-05, 'samples': 24197184, 'steps': 126026, 'loss/train': 1.2864240407943726} 08/31/2021 12:06:01 - INFO - __main__ - Step 126028: {'lr': 3.1676629604637434e-05, 'samples': 24197376, 'steps': 126027, 'loss/train': 0.12584403157234192} 08/31/2021 12:06:02 - INFO - __main__ - Step 126029: {'lr': 3.1674044237087973e-05, 'samples': 24197568, 'steps': 126028, 'loss/train': 1.0880208015441895} 08/31/2021 12:06:03 - INFO - __main__ - Step 126030: {'lr': 3.167145896791282e-05, 'samples': 24197760, 'steps': 126029, 'loss/train': 0.8225848078727722} 08/31/2021 12:06:03 - INFO - __main__ - Step 126031: {'lr': 3.166887379711314e-05, 'samples': 24197952, 'steps': 126030, 'loss/train': 1.4289268255233765} 08/31/2021 12:06:04 - INFO - __main__ - Step 126032: {'lr': 3.16662887246901e-05, 'samples': 24198144, 'steps': 126031, 'loss/train': 0.9179690480232239} 08/31/2021 12:06:04 - INFO - __main__ - Step 126033: {'lr': 3.166370375064484e-05, 'samples': 24198336, 'steps': 126032, 'loss/train': 0.7954608798027039} 08/31/2021 12:06:05 - INFO - __main__ - Step 126034: {'lr': 3.166111887497858e-05, 'samples': 24198528, 'steps': 126033, 'loss/train': 1.1316193342208862} 08/31/2021 12:06:05 - INFO - __main__ - Step 126035: {'lr': 3.1658534097692425e-05, 'samples': 24198720, 'steps': 126034, 'loss/train': 1.1503880023956299} 08/31/2021 12:06:07 - INFO - __main__ - Step 126036: {'lr': 3.1655949418787635e-05, 'samples': 24198912, 'steps': 126035, 'loss/train': 0.9449710845947266} 08/31/2021 12:06:08 - INFO - __main__ - Step 126037: {'lr': 3.165336483826523e-05, 'samples': 24199104, 'steps': 126036, 'loss/train': 0.9752064943313599} 08/31/2021 12:06:08 - INFO - __main__ - Step 126038: {'lr': 3.1650780356126455e-05, 'samples': 24199296, 'steps': 126037, 'loss/train': 1.2039339542388916} 08/31/2021 12:06:08 - INFO - __main__ - Step 126039: {'lr': 3.164819597237248e-05, 'samples': 24199488, 'steps': 126038, 'loss/train': 1.6892110109329224} 08/31/2021 12:06:09 - INFO - __main__ - Step 126040: {'lr': 3.1645611687004447e-05, 'samples': 24199680, 'steps': 126039, 'loss/train': 1.288237452507019} 08/31/2021 12:06:10 - INFO - __main__ - Step 126041: {'lr': 3.164302750002354e-05, 'samples': 24199872, 'steps': 126040, 'loss/train': 1.1438852548599243} 08/31/2021 12:06:11 - INFO - __main__ - Step 126042: {'lr': 3.1640443411430933e-05, 'samples': 24200064, 'steps': 126041, 'loss/train': 1.2821354866027832} 08/31/2021 12:06:11 - INFO - __main__ - Step 126043: {'lr': 3.1637859421227735e-05, 'samples': 24200256, 'steps': 126042, 'loss/train': 1.0255392789840698} 08/31/2021 12:06:11 - INFO - __main__ - Step 126044: {'lr': 3.163527552941517e-05, 'samples': 24200448, 'steps': 126043, 'loss/train': 0.7175987362861633} 08/31/2021 12:06:12 - INFO - __main__ - Step 126045: {'lr': 3.16326917359944e-05, 'samples': 24200640, 'steps': 126044, 'loss/train': 0.7670524716377258} 08/31/2021 12:06:13 - INFO - __main__ - Step 126046: {'lr': 3.163010804096653e-05, 'samples': 24200832, 'steps': 126045, 'loss/train': 1.8156436681747437} 08/31/2021 12:06:14 - INFO - __main__ - Step 126047: {'lr': 3.162752444433278e-05, 'samples': 24201024, 'steps': 126046, 'loss/train': 1.348867654800415} 08/31/2021 12:06:14 - INFO - __main__ - Step 126048: {'lr': 3.16249409460943e-05, 'samples': 24201216, 'steps': 126047, 'loss/train': 0.7924460172653198} 08/31/2021 12:06:14 - INFO - __main__ - Step 126049: {'lr': 3.162235754625226e-05, 'samples': 24201408, 'steps': 126048, 'loss/train': 1.0357475280761719} 08/31/2021 12:06:15 - INFO - __main__ - Step 126050: {'lr': 3.161977424480786e-05, 'samples': 24201600, 'steps': 126049, 'loss/train': 0.07808154821395874} 08/31/2021 12:06:16 - INFO - __main__ - Step 126051: {'lr': 3.161719104176217e-05, 'samples': 24201792, 'steps': 126050, 'loss/train': 0.03953181579709053} 08/31/2021 12:06:17 - INFO - __main__ - Step 126052: {'lr': 3.161460793711637e-05, 'samples': 24201984, 'steps': 126051, 'loss/train': 0.7967867851257324} 08/31/2021 12:06:17 - INFO - __main__ - Step 126053: {'lr': 3.16120249308717e-05, 'samples': 24202176, 'steps': 126052, 'loss/train': 0.9062150716781616} 08/31/2021 12:06:18 - INFO - __main__ - Step 126054: {'lr': 3.160944202302926e-05, 'samples': 24202368, 'steps': 126053, 'loss/train': 1.0261117219924927} 08/31/2021 12:06:18 - INFO - __main__ - Step 126055: {'lr': 3.160685921359027e-05, 'samples': 24202560, 'steps': 126054, 'loss/train': 0.39351311326026917} 08/31/2021 12:06:20 - INFO - __main__ - Step 126056: {'lr': 3.160427650255582e-05, 'samples': 24202752, 'steps': 126055, 'loss/train': 1.0932433605194092} 08/31/2021 12:06:20 - INFO - __main__ - Step 126057: {'lr': 3.1601693889927116e-05, 'samples': 24202944, 'steps': 126056, 'loss/train': 1.2811027765274048} 08/31/2021 12:06:20 - INFO - __main__ - Step 126058: {'lr': 3.1599111375705344e-05, 'samples': 24203136, 'steps': 126057, 'loss/train': 1.3789172172546387} 08/31/2021 12:06:21 - INFO - __main__ - Step 126059: {'lr': 3.159652895989162e-05, 'samples': 24203328, 'steps': 126058, 'loss/train': 1.4063986539840698} 08/31/2021 12:06:21 - INFO - __main__ - Step 126060: {'lr': 3.159394664248713e-05, 'samples': 24203520, 'steps': 126059, 'loss/train': 1.1537840366363525} 08/31/2021 12:06:23 - INFO - __main__ - Step 126061: {'lr': 3.159136442349306e-05, 'samples': 24203712, 'steps': 126060, 'loss/train': 0.9698110222816467} 08/31/2021 12:06:23 - INFO - __main__ - Step 126062: {'lr': 3.158878230291054e-05, 'samples': 24203904, 'steps': 126061, 'loss/train': 1.6952722072601318} 08/31/2021 12:06:23 - INFO - __main__ - Step 126063: {'lr': 3.15862002807408e-05, 'samples': 24204096, 'steps': 126062, 'loss/train': 1.365910530090332} 08/31/2021 12:06:24 - INFO - __main__ - Step 126064: {'lr': 3.1583618356984864e-05, 'samples': 24204288, 'steps': 126063, 'loss/train': 1.267305612564087} 08/31/2021 12:06:24 - INFO - __main__ - Step 126065: {'lr': 3.158103653164402e-05, 'samples': 24204480, 'steps': 126064, 'loss/train': 0.5237897038459778} 08/31/2021 12:06:24 - INFO - __main__ - Step 126066: {'lr': 3.157845480471938e-05, 'samples': 24204672, 'steps': 126065, 'loss/train': 1.2774155139923096} 08/31/2021 12:06:26 - INFO - __main__ - Step 126067: {'lr': 3.15758731762121e-05, 'samples': 24204864, 'steps': 126066, 'loss/train': 0.9012647867202759} 08/31/2021 12:06:27 - INFO - __main__ - Step 126068: {'lr': 3.157329164612338e-05, 'samples': 24205056, 'steps': 126067, 'loss/train': 0.4331851303577423} 08/31/2021 12:06:27 - INFO - __main__ - Step 126069: {'lr': 3.157071021445434e-05, 'samples': 24205248, 'steps': 126068, 'loss/train': 1.1619521379470825} 08/31/2021 12:06:27 - INFO - __main__ - Step 126070: {'lr': 3.156812888120619e-05, 'samples': 24205440, 'steps': 126069, 'loss/train': 1.124711036682129} 08/31/2021 12:06:28 - INFO - __main__ - Step 126071: {'lr': 3.156554764638009e-05, 'samples': 24205632, 'steps': 126070, 'loss/train': 0.7616201043128967} 08/31/2021 12:06:29 - INFO - __main__ - Step 126072: {'lr': 3.156296650997714e-05, 'samples': 24205824, 'steps': 126071, 'loss/train': 0.2639034390449524} 08/31/2021 12:06:30 - INFO - __main__ - Step 126073: {'lr': 3.1560385471998575e-05, 'samples': 24206016, 'steps': 126072, 'loss/train': 1.1338011026382446} 08/31/2021 12:06:30 - INFO - __main__ - Step 126074: {'lr': 3.155780453244553e-05, 'samples': 24206208, 'steps': 126073, 'loss/train': 1.2759060859680176} 08/31/2021 12:06:30 - INFO - __main__ - Step 126075: {'lr': 3.1555223691319135e-05, 'samples': 24206400, 'steps': 126074, 'loss/train': 0.9603128433227539} 08/31/2021 12:06:31 - INFO - __main__ - Step 126076: {'lr': 3.155264294862062e-05, 'samples': 24206592, 'steps': 126075, 'loss/train': 1.5395783185958862} 08/31/2021 12:06:32 - INFO - __main__ - Step 126077: {'lr': 3.1550062304351146e-05, 'samples': 24206784, 'steps': 126076, 'loss/train': 0.855886697769165} 08/31/2021 12:06:33 - INFO - __main__ - Step 126078: {'lr': 3.15474817585118e-05, 'samples': 24206976, 'steps': 126077, 'loss/train': 0.9970945715904236} 08/31/2021 12:06:33 - INFO - __main__ - Step 126079: {'lr': 3.15449013111038e-05, 'samples': 24207168, 'steps': 126078, 'loss/train': 0.06428773701190948} 08/31/2021 12:06:34 - INFO - __main__ - Step 126080: {'lr': 3.154232096212828e-05, 'samples': 24207360, 'steps': 126079, 'loss/train': 1.3827235698699951} 08/31/2021 12:06:34 - INFO - __main__ - Step 126081: {'lr': 3.153974071158641e-05, 'samples': 24207552, 'steps': 126080, 'loss/train': 1.4516758918762207} 08/31/2021 12:06:35 - INFO - __main__ - Step 126082: {'lr': 3.153716055947936e-05, 'samples': 24207744, 'steps': 126081, 'loss/train': 0.3499924838542938} 08/31/2021 12:06:36 - INFO - __main__ - Step 126083: {'lr': 3.153458050580832e-05, 'samples': 24207936, 'steps': 126082, 'loss/train': 1.0123262405395508} 08/31/2021 12:06:36 - INFO - __main__ - Step 126084: {'lr': 3.153200055057443e-05, 'samples': 24208128, 'steps': 126083, 'loss/train': 1.4724769592285156} 08/31/2021 12:06:37 - INFO - __main__ - Step 126085: {'lr': 3.152942069377881e-05, 'samples': 24208320, 'steps': 126084, 'loss/train': 1.1318070888519287} 08/31/2021 12:06:37 - INFO - __main__ - Step 126086: {'lr': 3.1526840935422686e-05, 'samples': 24208512, 'steps': 126085, 'loss/train': 0.11569003015756607} 08/31/2021 12:06:39 - INFO - __main__ - Step 126087: {'lr': 3.1524261275507196e-05, 'samples': 24208704, 'steps': 126086, 'loss/train': 1.0416185855865479} 08/31/2021 12:06:40 - INFO - __main__ - Step 126088: {'lr': 3.152168171403352e-05, 'samples': 24208896, 'steps': 126087, 'loss/train': 1.4124501943588257} 08/31/2021 12:06:40 - INFO - __main__ - Step 126089: {'lr': 3.151910225100277e-05, 'samples': 24209088, 'steps': 126088, 'loss/train': 0.9769337773323059} 08/31/2021 12:06:40 - INFO - __main__ - Step 126090: {'lr': 3.151652288641621e-05, 'samples': 24209280, 'steps': 126089, 'loss/train': 0.363267719745636} 08/31/2021 12:06:41 - INFO - __main__ - Step 126091: {'lr': 3.1513943620274876e-05, 'samples': 24209472, 'steps': 126090, 'loss/train': 0.9747678637504578} 08/31/2021 12:06:41 - INFO - __main__ - Step 126092: {'lr': 3.1511364452580017e-05, 'samples': 24209664, 'steps': 126091, 'loss/train': 1.2808177471160889} 08/31/2021 12:06:42 - INFO - __main__ - Step 126093: {'lr': 3.150878538333274e-05, 'samples': 24209856, 'steps': 126092, 'loss/train': 1.4977678060531616} 08/31/2021 12:06:43 - INFO - __main__ - Step 126094: {'lr': 3.1506206412534213e-05, 'samples': 24210048, 'steps': 126093, 'loss/train': 1.8142309188842773} 08/31/2021 12:06:43 - INFO - __main__ - Step 126095: {'lr': 3.1503627540185655e-05, 'samples': 24210240, 'steps': 126094, 'loss/train': 0.6106458902359009} 08/31/2021 12:06:44 - INFO - __main__ - Step 126096: {'lr': 3.1501048766288176e-05, 'samples': 24210432, 'steps': 126095, 'loss/train': 0.36148741841316223} 08/31/2021 12:06:44 - INFO - __main__ - Step 126097: {'lr': 3.149847009084294e-05, 'samples': 24210624, 'steps': 126096, 'loss/train': 1.3620131015777588} 08/31/2021 12:06:45 - INFO - __main__ - Step 126098: {'lr': 3.149589151385113e-05, 'samples': 24210816, 'steps': 126097, 'loss/train': 0.87690669298172} 08/31/2021 12:06:46 - INFO - __main__ - Step 126099: {'lr': 3.1493313035313916e-05, 'samples': 24211008, 'steps': 126098, 'loss/train': 0.22943370044231415} 08/31/2021 12:06:46 - INFO - __main__ - Step 126100: {'lr': 3.149073465523242e-05, 'samples': 24211200, 'steps': 126099, 'loss/train': 0.9830504655838013} 08/31/2021 12:06:47 - INFO - __main__ - Step 126101: {'lr': 3.148815637360783e-05, 'samples': 24211392, 'steps': 126100, 'loss/train': 0.3594772219657898} 08/31/2021 12:06:47 - INFO - __main__ - Step 126102: {'lr': 3.148557819044131e-05, 'samples': 24211584, 'steps': 126101, 'loss/train': 1.2901169061660767} 08/31/2021 12:06:48 - INFO - __main__ - Step 126103: {'lr': 3.148300010573407e-05, 'samples': 24211776, 'steps': 126102, 'loss/train': 1.0929571390151978} 08/31/2021 12:06:49 - INFO - __main__ - Step 126104: {'lr': 3.148042211948718e-05, 'samples': 24211968, 'steps': 126103, 'loss/train': 0.9632997512817383} 08/31/2021 12:06:49 - INFO - __main__ - Step 126105: {'lr': 3.147784423170183e-05, 'samples': 24212160, 'steps': 126104, 'loss/train': 1.550794005393982} 08/31/2021 12:06:50 - INFO - __main__ - Step 126106: {'lr': 3.1475266442379166e-05, 'samples': 24212352, 'steps': 126105, 'loss/train': 0.8924317359924316} 08/31/2021 12:06:50 - INFO - __main__ - Step 126107: {'lr': 3.14726887515204e-05, 'samples': 24212544, 'steps': 126106, 'loss/train': 1.1627858877182007} 08/31/2021 12:06:51 - INFO - __main__ - Step 126108: {'lr': 3.147011115912668e-05, 'samples': 24212736, 'steps': 126107, 'loss/train': 0.7421066761016846} 08/31/2021 12:06:52 - INFO - __main__ - Step 126109: {'lr': 3.146753366519914e-05, 'samples': 24212928, 'steps': 126108, 'loss/train': 1.6062957048416138} 08/31/2021 12:06:52 - INFO - __main__ - Step 126110: {'lr': 3.146495626973894e-05, 'samples': 24213120, 'steps': 126109, 'loss/train': 1.4826371669769287} 08/31/2021 12:06:53 - INFO - __main__ - Step 126111: {'lr': 3.1462378972747286e-05, 'samples': 24213312, 'steps': 126110, 'loss/train': 1.0449081659317017} 08/31/2021 12:06:53 - INFO - __main__ - Step 126112: {'lr': 3.1459801774225305e-05, 'samples': 24213504, 'steps': 126111, 'loss/train': 1.3933969736099243} 08/31/2021 12:06:54 - INFO - __main__ - Step 126113: {'lr': 3.145722467417417e-05, 'samples': 24213696, 'steps': 126112, 'loss/train': 1.07786226272583} 08/31/2021 12:06:55 - INFO - __main__ - Step 126114: {'lr': 3.145464767259501e-05, 'samples': 24213888, 'steps': 126113, 'loss/train': 0.9314649701118469} 08/31/2021 12:06:55 - INFO - __main__ - Step 126115: {'lr': 3.145207076948903e-05, 'samples': 24214080, 'steps': 126114, 'loss/train': 0.5617341995239258} 08/31/2021 12:06:56 - INFO - __main__ - Step 126116: {'lr': 3.1449493964857384e-05, 'samples': 24214272, 'steps': 126115, 'loss/train': 2.0186822414398193} 08/31/2021 12:06:56 - INFO - __main__ - Step 126117: {'lr': 3.1446917258701276e-05, 'samples': 24214464, 'steps': 126116, 'loss/train': 1.069927453994751} 08/31/2021 12:06:56 - INFO - __main__ - Step 126118: {'lr': 3.1444340651021753e-05, 'samples': 24214656, 'steps': 126117, 'loss/train': 1.2531325817108154} 08/31/2021 12:06:58 - INFO - __main__ - Step 126119: {'lr': 3.144176414182004e-05, 'samples': 24214848, 'steps': 126118, 'loss/train': 1.4348224401474} 08/31/2021 12:06:59 - INFO - __main__ - Step 126120: {'lr': 3.1439187731097305e-05, 'samples': 24215040, 'steps': 126119, 'loss/train': 0.030784612521529198} 08/31/2021 12:06:59 - INFO - __main__ - Step 126121: {'lr': 3.1436611418854675e-05, 'samples': 24215232, 'steps': 126120, 'loss/train': 1.4020802974700928} 08/31/2021 12:06:59 - INFO - __main__ - Step 126122: {'lr': 3.143403520509336e-05, 'samples': 24215424, 'steps': 126121, 'loss/train': 0.6625276207923889} 08/31/2021 12:07:00 - INFO - __main__ - Step 126123: {'lr': 3.143145908981449e-05, 'samples': 24215616, 'steps': 126122, 'loss/train': 1.3421157598495483} 08/31/2021 12:07:01 - INFO - __main__ - Step 126124: {'lr': 3.142888307301922e-05, 'samples': 24215808, 'steps': 126123, 'loss/train': 0.023151792585849762} 08/31/2021 12:07:02 - INFO - __main__ - Step 126125: {'lr': 3.142630715470873e-05, 'samples': 24216000, 'steps': 126124, 'loss/train': 1.2174612283706665} 08/31/2021 12:07:02 - INFO - __main__ - Step 126126: {'lr': 3.142373133488416e-05, 'samples': 24216192, 'steps': 126125, 'loss/train': 0.44214925169944763} 08/31/2021 12:07:03 - INFO - __main__ - Step 126127: {'lr': 3.142115561354672e-05, 'samples': 24216384, 'steps': 126126, 'loss/train': 0.31276869773864746} 08/31/2021 12:07:03 - INFO - __main__ - Step 126128: {'lr': 3.14185799906975e-05, 'samples': 24216576, 'steps': 126127, 'loss/train': 1.098191261291504} 08/31/2021 12:07:04 - INFO - __main__ - Step 126129: {'lr': 3.141600446633772e-05, 'samples': 24216768, 'steps': 126128, 'loss/train': 1.504098892211914} 08/31/2021 12:07:05 - INFO - __main__ - Step 126130: {'lr': 3.1413429040468536e-05, 'samples': 24216960, 'steps': 126129, 'loss/train': 1.3168781995773315} 08/31/2021 12:07:05 - INFO - __main__ - Step 126131: {'lr': 3.141085371309105e-05, 'samples': 24217152, 'steps': 126130, 'loss/train': 1.4140704870224} 08/31/2021 12:07:06 - INFO - __main__ - Step 126132: {'lr': 3.140827848420647e-05, 'samples': 24217344, 'steps': 126131, 'loss/train': 0.7479905486106873} 08/31/2021 12:07:06 - INFO - __main__ - Step 126133: {'lr': 3.140570335381595e-05, 'samples': 24217536, 'steps': 126132, 'loss/train': 1.6451361179351807} 08/31/2021 12:07:07 - INFO - __main__ - Step 126134: {'lr': 3.140312832192063e-05, 'samples': 24217728, 'steps': 126133, 'loss/train': 0.8640357255935669} 08/31/2021 12:07:08 - INFO - __main__ - Step 126135: {'lr': 3.1400553388521684e-05, 'samples': 24217920, 'steps': 126134, 'loss/train': 0.9832580089569092} 08/31/2021 12:07:08 - INFO - __main__ - Step 126136: {'lr': 3.139797855362031e-05, 'samples': 24218112, 'steps': 126135, 'loss/train': 1.6096646785736084} 08/31/2021 12:07:09 - INFO - __main__ - Step 126137: {'lr': 3.1395403817217587e-05, 'samples': 24218304, 'steps': 126136, 'loss/train': 1.199477195739746} 08/31/2021 12:07:09 - INFO - __main__ - Step 126138: {'lr': 3.139282917931477e-05, 'samples': 24218496, 'steps': 126137, 'loss/train': 0.818260908126831} 08/31/2021 12:07:11 - INFO - __main__ - Step 126139: {'lr': 3.139025463991294e-05, 'samples': 24218688, 'steps': 126138, 'loss/train': 0.9323980808258057} 08/31/2021 12:07:11 - INFO - __main__ - Step 126140: {'lr': 3.138768019901328e-05, 'samples': 24218880, 'steps': 126139, 'loss/train': 1.4834829568862915} 08/31/2021 12:07:12 - INFO - __main__ - Step 126141: {'lr': 3.138510585661697e-05, 'samples': 24219072, 'steps': 126140, 'loss/train': 1.0593425035476685} 08/31/2021 12:07:12 - INFO - __main__ - Step 126142: {'lr': 3.138253161272517e-05, 'samples': 24219264, 'steps': 126141, 'loss/train': 1.7252408266067505} 08/31/2021 12:07:13 - INFO - __main__ - Step 126143: {'lr': 3.1379957467339014e-05, 'samples': 24219456, 'steps': 126142, 'loss/train': 0.972536027431488} 08/31/2021 12:07:14 - INFO - __main__ - Step 126144: {'lr': 3.137738342045973e-05, 'samples': 24219648, 'steps': 126143, 'loss/train': 1.0841140747070312} 08/31/2021 12:07:15 - INFO - __main__ - Step 126145: {'lr': 3.137480947208837e-05, 'samples': 24219840, 'steps': 126144, 'loss/train': 1.1456665992736816} 08/31/2021 12:07:15 - INFO - __main__ - Step 126146: {'lr': 3.137223562222616e-05, 'samples': 24220032, 'steps': 126145, 'loss/train': 0.03420507535338402} 08/31/2021 12:07:15 - INFO - __main__ - Step 126147: {'lr': 3.1369661870874227e-05, 'samples': 24220224, 'steps': 126146, 'loss/train': 1.7428159713745117} 08/31/2021 12:07:16 - INFO - __main__ - Step 126148: {'lr': 3.1367088218033776e-05, 'samples': 24220416, 'steps': 126147, 'loss/train': 0.4199146032333374} 08/31/2021 12:07:16 - INFO - __main__ - Step 126149: {'lr': 3.1364514663705906e-05, 'samples': 24220608, 'steps': 126148, 'loss/train': 0.7671105861663818} 08/31/2021 12:07:18 - INFO - __main__ - Step 126150: {'lr': 3.136194120789185e-05, 'samples': 24220800, 'steps': 126149, 'loss/train': 1.0947445631027222} 08/31/2021 12:07:18 - INFO - __main__ - Step 126151: {'lr': 3.135936785059271e-05, 'samples': 24220992, 'steps': 126150, 'loss/train': 0.5262719392776489} 08/31/2021 12:07:19 - INFO - __main__ - Step 126152: {'lr': 3.135679459180965e-05, 'samples': 24221184, 'steps': 126151, 'loss/train': 1.1161316633224487} 08/31/2021 12:07:19 - INFO - __main__ - Step 126153: {'lr': 3.1354221431543876e-05, 'samples': 24221376, 'steps': 126152, 'loss/train': 1.046293020248413} 08/31/2021 12:07:19 - INFO - __main__ - Step 126154: {'lr': 3.135164836979651e-05, 'samples': 24221568, 'steps': 126153, 'loss/train': 1.097204566001892} 08/31/2021 12:07:21 - INFO - __main__ - Step 126155: {'lr': 3.13490754065687e-05, 'samples': 24221760, 'steps': 126154, 'loss/train': 1.1193712949752808} 08/31/2021 12:07:21 - INFO - __main__ - Step 126156: {'lr': 3.134650254186164e-05, 'samples': 24221952, 'steps': 126155, 'loss/train': 0.552289605140686} 08/31/2021 12:07:22 - INFO - __main__ - Step 126157: {'lr': 3.134392977567649e-05, 'samples': 24222144, 'steps': 126156, 'loss/train': 0.92288738489151} 08/31/2021 12:07:22 - INFO - __main__ - Step 126158: {'lr': 3.134135710801436e-05, 'samples': 24222336, 'steps': 126157, 'loss/train': 1.1457042694091797} 08/31/2021 12:07:22 - INFO - __main__ - Step 126159: {'lr': 3.1338784538876454e-05, 'samples': 24222528, 'steps': 126158, 'loss/train': 1.034361481666565} 08/31/2021 12:07:24 - INFO - __main__ - Step 126160: {'lr': 3.133621206826392e-05, 'samples': 24222720, 'steps': 126159, 'loss/train': 0.4596173167228699} 08/31/2021 12:07:24 - INFO - __main__ - Step 126161: {'lr': 3.133363969617789e-05, 'samples': 24222912, 'steps': 126160, 'loss/train': 0.8694223761558533} 08/31/2021 12:07:25 - INFO - __main__ - Step 126162: {'lr': 3.1331067422619566e-05, 'samples': 24223104, 'steps': 126161, 'loss/train': 1.033234715461731} 08/31/2021 12:07:25 - INFO - __main__ - Step 126163: {'lr': 3.132849524759007e-05, 'samples': 24223296, 'steps': 126162, 'loss/train': 1.0095833539962769} 08/31/2021 12:07:25 - INFO - __main__ - Step 126164: {'lr': 3.132592317109059e-05, 'samples': 24223488, 'steps': 126163, 'loss/train': 1.5572601556777954} 08/31/2021 12:07:27 - INFO - __main__ - Step 126165: {'lr': 3.13233511931223e-05, 'samples': 24223680, 'steps': 126164, 'loss/train': 0.9813728928565979} 08/31/2021 12:07:27 - INFO - __main__ - Step 126166: {'lr': 3.1320779313686295e-05, 'samples': 24223872, 'steps': 126165, 'loss/train': 1.161023497581482} 08/31/2021 12:07:28 - INFO - __main__ - Step 126167: {'lr': 3.1318207532783805e-05, 'samples': 24224064, 'steps': 126166, 'loss/train': 0.5713685750961304} 08/31/2021 12:07:28 - INFO - __main__ - Step 126168: {'lr': 3.131563585041594e-05, 'samples': 24224256, 'steps': 126167, 'loss/train': 0.8949052691459656} 08/31/2021 12:07:28 - INFO - __main__ - Step 126169: {'lr': 3.1313064266583866e-05, 'samples': 24224448, 'steps': 126168, 'loss/train': 1.0259979963302612} 08/31/2021 12:07:30 - INFO - __main__ - Step 126170: {'lr': 3.131049278128875e-05, 'samples': 24224640, 'steps': 126169, 'loss/train': 0.6999557614326477} 08/31/2021 12:07:30 - INFO - __main__ - Step 126171: {'lr': 3.1307921394531816e-05, 'samples': 24224832, 'steps': 126170, 'loss/train': 1.0086621046066284} 08/31/2021 12:07:31 - INFO - __main__ - Step 126172: {'lr': 3.1305350106314104e-05, 'samples': 24225024, 'steps': 126171, 'loss/train': 1.2771614789962769} 08/31/2021 12:07:31 - INFO - __main__ - Step 126173: {'lr': 3.1302778916636824e-05, 'samples': 24225216, 'steps': 126172, 'loss/train': 1.2598568201065063} 08/31/2021 12:07:32 - INFO - __main__ - Step 126174: {'lr': 3.1300207825501134e-05, 'samples': 24225408, 'steps': 126173, 'loss/train': 0.7038533687591553} 08/31/2021 12:07:33 - INFO - __main__ - Step 126175: {'lr': 3.129763683290821e-05, 'samples': 24225600, 'steps': 126174, 'loss/train': 0.5451686978340149} 08/31/2021 12:07:33 - INFO - __main__ - Step 126176: {'lr': 3.129506593885917e-05, 'samples': 24225792, 'steps': 126175, 'loss/train': 1.4702025651931763} 08/31/2021 12:07:34 - INFO - __main__ - Step 126177: {'lr': 3.129249514335522e-05, 'samples': 24225984, 'steps': 126176, 'loss/train': 0.5377085208892822} 08/31/2021 12:07:34 - INFO - __main__ - Step 126178: {'lr': 3.12899244463975e-05, 'samples': 24226176, 'steps': 126177, 'loss/train': 1.0107207298278809} 08/31/2021 12:07:35 - INFO - __main__ - Step 126179: {'lr': 3.1287353847987146e-05, 'samples': 24226368, 'steps': 126178, 'loss/train': 1.48512864112854} 08/31/2021 12:07:36 - INFO - __main__ - Step 126180: {'lr': 3.1284783348125347e-05, 'samples': 24226560, 'steps': 126179, 'loss/train': 1.462816596031189} 08/31/2021 12:07:36 - INFO - __main__ - Step 126181: {'lr': 3.128221294681324e-05, 'samples': 24226752, 'steps': 126180, 'loss/train': 0.7899371385574341} 08/31/2021 12:07:37 - INFO - __main__ - Step 126182: {'lr': 3.1279642644052004e-05, 'samples': 24226944, 'steps': 126181, 'loss/train': 0.9060743451118469} 08/31/2021 12:07:37 - INFO - __main__ - Step 126183: {'lr': 3.127707243984279e-05, 'samples': 24227136, 'steps': 126182, 'loss/train': 0.1289769858121872} 08/31/2021 12:07:38 - INFO - __main__ - Step 126184: {'lr': 3.12745023341868e-05, 'samples': 24227328, 'steps': 126183, 'loss/train': 1.3407566547393799} 08/31/2021 12:07:39 - INFO - __main__ - Step 126185: {'lr': 3.127193232708508e-05, 'samples': 24227520, 'steps': 126184, 'loss/train': 1.004827857017517} 08/31/2021 12:07:39 - INFO - __main__ - Step 126186: {'lr': 3.1269362418538866e-05, 'samples': 24227712, 'steps': 126185, 'loss/train': 1.469292163848877} 08/31/2021 12:07:40 - INFO - __main__ - Step 126187: {'lr': 3.126679260854931e-05, 'samples': 24227904, 'steps': 126186, 'loss/train': 0.12998537719249725} 08/31/2021 12:07:40 - INFO - __main__ - Step 126188: {'lr': 3.1264222897117556e-05, 'samples': 24228096, 'steps': 126187, 'loss/train': 0.4429567754268646} 08/31/2021 12:07:41 - INFO - __main__ - Step 126189: {'lr': 3.126165328424474e-05, 'samples': 24228288, 'steps': 126188, 'loss/train': 1.351796269416809} 08/31/2021 12:07:42 - INFO - __main__ - Step 126190: {'lr': 3.1259083769932085e-05, 'samples': 24228480, 'steps': 126189, 'loss/train': 0.3647633194923401} 08/31/2021 12:07:43 - INFO - __main__ - Step 126191: {'lr': 3.12565143541807e-05, 'samples': 24228672, 'steps': 126190, 'loss/train': 1.0799658298492432} 08/31/2021 12:07:43 - INFO - __main__ - Step 126192: {'lr': 3.125394503699175e-05, 'samples': 24228864, 'steps': 126191, 'loss/train': 0.7263137698173523} 08/31/2021 12:07:44 - INFO - __main__ - Step 126193: {'lr': 3.125137581836637e-05, 'samples': 24229056, 'steps': 126192, 'loss/train': 0.3277387320995331} 08/31/2021 12:07:44 - INFO - __main__ - Step 126194: {'lr': 3.1248806698305794e-05, 'samples': 24229248, 'steps': 126193, 'loss/train': 0.8575543165206909} 08/31/2021 12:07:44 - INFO - __main__ - Step 126195: {'lr': 3.124623767681109e-05, 'samples': 24229440, 'steps': 126194, 'loss/train': 0.12652336061000824} 08/31/2021 12:07:47 - INFO - __main__ - Step 126196: {'lr': 3.124366875388349e-05, 'samples': 24229632, 'steps': 126195, 'loss/train': 0.4413832724094391} 08/31/2021 12:07:48 - INFO - __main__ - Step 126197: {'lr': 3.124109992952409e-05, 'samples': 24229824, 'steps': 126196, 'loss/train': 1.1292942762374878} 08/31/2021 12:07:48 - INFO - __main__ - Step 126198: {'lr': 3.1238531203734125e-05, 'samples': 24230016, 'steps': 126197, 'loss/train': 1.733124017715454} 08/31/2021 12:07:48 - INFO - __main__ - Step 126199: {'lr': 3.123596257651467e-05, 'samples': 24230208, 'steps': 126198, 'loss/train': 1.7407546043395996} 08/31/2021 12:07:49 - INFO - __main__ - Step 126200: {'lr': 3.1233394047866904e-05, 'samples': 24230400, 'steps': 126199, 'loss/train': 0.8501937389373779} 08/31/2021 12:07:49 - INFO - __main__ - Step 126201: {'lr': 3.1230825617792006e-05, 'samples': 24230592, 'steps': 126200, 'loss/train': 0.8832343816757202} 08/31/2021 12:07:49 - INFO - __main__ - Step 126202: {'lr': 3.1228257286291115e-05, 'samples': 24230784, 'steps': 126201, 'loss/train': 0.11853835731744766} 08/31/2021 12:07:51 - INFO - __main__ - Step 126203: {'lr': 3.12256890533654e-05, 'samples': 24230976, 'steps': 126202, 'loss/train': 0.14061309397220612} 08/31/2021 12:07:51 - INFO - __main__ - Step 126204: {'lr': 3.122312091901599e-05, 'samples': 24231168, 'steps': 126203, 'loss/train': 1.2519487142562866} 08/31/2021 12:07:52 - INFO - __main__ - Step 126205: {'lr': 3.12205528832441e-05, 'samples': 24231360, 'steps': 126204, 'loss/train': 1.0402827262878418} 08/31/2021 12:07:52 - INFO - __main__ - Step 126206: {'lr': 3.121798494605083e-05, 'samples': 24231552, 'steps': 126205, 'loss/train': 0.043465130031108856} 08/31/2021 12:07:52 - INFO - __main__ - Step 126207: {'lr': 3.121541710743736e-05, 'samples': 24231744, 'steps': 126206, 'loss/train': 1.1963437795639038} 08/31/2021 12:07:53 - INFO - __main__ - Step 126208: {'lr': 3.121284936740487e-05, 'samples': 24231936, 'steps': 126207, 'loss/train': 0.2293480485677719} 08/31/2021 12:07:54 - INFO - __main__ - Step 126209: {'lr': 3.121028172595447e-05, 'samples': 24232128, 'steps': 126208, 'loss/train': 0.3290797770023346} 08/31/2021 12:07:55 - INFO - __main__ - Step 126210: {'lr': 3.120771418308735e-05, 'samples': 24232320, 'steps': 126209, 'loss/train': 1.2664321660995483} 08/31/2021 12:07:55 - INFO - __main__ - Step 126211: {'lr': 3.1205146738804705e-05, 'samples': 24232512, 'steps': 126210, 'loss/train': 1.0923376083374023} 08/31/2021 12:07:56 - INFO - __main__ - Step 126212: {'lr': 3.1202579393107585e-05, 'samples': 24232704, 'steps': 126211, 'loss/train': 1.3727757930755615} 08/31/2021 12:07:56 - INFO - __main__ - Step 126213: {'lr': 3.120001214599724e-05, 'samples': 24232896, 'steps': 126212, 'loss/train': 0.6788654327392578} 08/31/2021 12:07:57 - INFO - __main__ - Step 126214: {'lr': 3.119744499747476e-05, 'samples': 24233088, 'steps': 126213, 'loss/train': 1.0623372793197632} 08/31/2021 12:07:58 - INFO - __main__ - Step 126215: {'lr': 3.1194877947541334e-05, 'samples': 24233280, 'steps': 126214, 'loss/train': 1.2871159315109253} 08/31/2021 12:07:58 - INFO - __main__ - Step 126216: {'lr': 3.1192310996198157e-05, 'samples': 24233472, 'steps': 126215, 'loss/train': 0.816771388053894} 08/31/2021 12:07:59 - INFO - __main__ - Step 126217: {'lr': 3.11897441434463e-05, 'samples': 24233664, 'steps': 126216, 'loss/train': 0.47637906670570374} 08/31/2021 12:07:59 - INFO - __main__ - Step 126218: {'lr': 3.1187177389287e-05, 'samples': 24233856, 'steps': 126217, 'loss/train': 1.421665906906128} 08/31/2021 12:07:59 - INFO - __main__ - Step 126219: {'lr': 3.1184610733721366e-05, 'samples': 24234048, 'steps': 126218, 'loss/train': 1.2748339176177979} 08/31/2021 12:08:01 - INFO - __main__ - Step 126220: {'lr': 3.1182044176750576e-05, 'samples': 24234240, 'steps': 126219, 'loss/train': 0.6224848628044128} 08/31/2021 12:08:01 - INFO - __main__ - Step 126221: {'lr': 3.117947771837579e-05, 'samples': 24234432, 'steps': 126220, 'loss/train': 1.0690799951553345} 08/31/2021 12:08:02 - INFO - __main__ - Step 126222: {'lr': 3.117691135859813e-05, 'samples': 24234624, 'steps': 126221, 'loss/train': 1.0393365621566772} 08/31/2021 12:08:02 - INFO - __main__ - Step 126223: {'lr': 3.117434509741879e-05, 'samples': 24234816, 'steps': 126222, 'loss/train': 1.013081669807434} 08/31/2021 12:08:02 - INFO - __main__ - Step 126224: {'lr': 3.117177893483897e-05, 'samples': 24235008, 'steps': 126223, 'loss/train': 0.5848268270492554} 08/31/2021 12:08:04 - INFO - __main__ - Step 126225: {'lr': 3.116921287085972e-05, 'samples': 24235200, 'steps': 126224, 'loss/train': 0.43294206261634827} 08/31/2021 12:08:04 - INFO - __main__ - Step 126226: {'lr': 3.116664690548224e-05, 'samples': 24235392, 'steps': 126225, 'loss/train': 0.9363869428634644} 08/31/2021 12:08:05 - INFO - __main__ - Step 126227: {'lr': 3.116408103870769e-05, 'samples': 24235584, 'steps': 126226, 'loss/train': 1.6637887954711914} 08/31/2021 12:08:05 - INFO - __main__ - Step 126228: {'lr': 3.116151527053723e-05, 'samples': 24235776, 'steps': 126227, 'loss/train': 1.45010244846344} 08/31/2021 12:08:05 - INFO - __main__ - Step 126229: {'lr': 3.1158949600972015e-05, 'samples': 24235968, 'steps': 126228, 'loss/train': 1.1221925020217896} 08/31/2021 12:08:07 - INFO - __main__ - Step 126230: {'lr': 3.11563840300132e-05, 'samples': 24236160, 'steps': 126229, 'loss/train': 1.0455540418624878} 08/31/2021 12:08:07 - INFO - __main__ - Step 126231: {'lr': 3.1153818557661944e-05, 'samples': 24236352, 'steps': 126230, 'loss/train': 1.5220987796783447} 08/31/2021 12:08:08 - INFO - __main__ - Step 126232: {'lr': 3.11512531839194e-05, 'samples': 24236544, 'steps': 126231, 'loss/train': 1.3470244407653809} 08/31/2021 12:08:08 - INFO - __main__ - Step 126233: {'lr': 3.1148687908786724e-05, 'samples': 24236736, 'steps': 126232, 'loss/train': 0.982172966003418} 08/31/2021 12:08:08 - INFO - __main__ - Step 126234: {'lr': 3.114612273226508e-05, 'samples': 24236928, 'steps': 126233, 'loss/train': 1.0747568607330322} 08/31/2021 12:08:10 - INFO - __main__ - Step 126235: {'lr': 3.1143557654355585e-05, 'samples': 24237120, 'steps': 126234, 'loss/train': 0.9551039934158325} 08/31/2021 12:08:10 - INFO - __main__ - Step 126236: {'lr': 3.114099267505946e-05, 'samples': 24237312, 'steps': 126235, 'loss/train': 0.6564048528671265} 08/31/2021 12:08:11 - INFO - __main__ - Step 126237: {'lr': 3.113842779437781e-05, 'samples': 24237504, 'steps': 126236, 'loss/train': 0.43631210923194885} 08/31/2021 12:08:11 - INFO - __main__ - Step 126238: {'lr': 3.113586301231186e-05, 'samples': 24237696, 'steps': 126237, 'loss/train': 1.5934945344924927} 08/31/2021 12:08:11 - INFO - __main__ - Step 126239: {'lr': 3.1133298328862666e-05, 'samples': 24237888, 'steps': 126238, 'loss/train': 1.0369675159454346} 08/31/2021 12:08:13 - INFO - __main__ - Step 126240: {'lr': 3.1130733744031444e-05, 'samples': 24238080, 'steps': 126239, 'loss/train': 1.198024034500122} 08/31/2021 12:08:14 - INFO - __main__ - Step 126241: {'lr': 3.1128169257819305e-05, 'samples': 24238272, 'steps': 126240, 'loss/train': 1.343414306640625} 08/31/2021 12:08:14 - INFO - __main__ - Step 126242: {'lr': 3.112560487022745e-05, 'samples': 24238464, 'steps': 126241, 'loss/train': 1.0795783996582031} 08/31/2021 12:08:14 - INFO - __main__ - Step 126243: {'lr': 3.112304058125704e-05, 'samples': 24238656, 'steps': 126242, 'loss/train': 0.7833538055419922} 08/31/2021 12:08:15 - INFO - __main__ - Step 126244: {'lr': 3.112047639090918e-05, 'samples': 24238848, 'steps': 126243, 'loss/train': 0.699166476726532} 08/31/2021 12:08:15 - INFO - __main__ - Step 126245: {'lr': 3.111791229918506e-05, 'samples': 24239040, 'steps': 126244, 'loss/train': 0.9669849872589111} 08/31/2021 12:08:17 - INFO - __main__ - Step 126246: {'lr': 3.111534830608584e-05, 'samples': 24239232, 'steps': 126245, 'loss/train': 1.0247377157211304} 08/31/2021 12:08:18 - INFO - __main__ - Step 126247: {'lr': 3.1112784411612667e-05, 'samples': 24239424, 'steps': 126246, 'loss/train': 0.3209729492664337} 08/31/2021 12:08:18 - INFO - __main__ - Step 126248: {'lr': 3.111022061576671e-05, 'samples': 24239616, 'steps': 126247, 'loss/train': 0.377175897359848} 08/31/2021 12:08:18 - INFO - __main__ - Step 126249: {'lr': 3.1107656918549084e-05, 'samples': 24239808, 'steps': 126248, 'loss/train': 1.463005542755127} 08/31/2021 12:08:19 - INFO - __main__ - Step 126250: {'lr': 3.110509331996103e-05, 'samples': 24240000, 'steps': 126249, 'loss/train': 1.3265633583068848} 08/31/2021 12:08:20 - INFO - __main__ - Step 126251: {'lr': 3.1102529820003586e-05, 'samples': 24240192, 'steps': 126250, 'loss/train': 0.4967729449272156} 08/31/2021 12:08:21 - INFO - __main__ - Step 126252: {'lr': 3.109996641867799e-05, 'samples': 24240384, 'steps': 126251, 'loss/train': 1.3898406028747559} 08/31/2021 12:08:21 - INFO - __main__ - Step 126253: {'lr': 3.1097403115985326e-05, 'samples': 24240576, 'steps': 126252, 'loss/train': 1.365987777709961} 08/31/2021 12:08:22 - INFO - __main__ - Step 126254: {'lr': 3.1094839911926824e-05, 'samples': 24240768, 'steps': 126253, 'loss/train': 1.320935845375061} 08/31/2021 12:08:22 - INFO - __main__ - Step 126255: {'lr': 3.1092276806503615e-05, 'samples': 24240960, 'steps': 126254, 'loss/train': 0.8261982798576355} 08/31/2021 12:08:24 - INFO - __main__ - Step 126256: {'lr': 3.108971379971684e-05, 'samples': 24241152, 'steps': 126255, 'loss/train': 1.9428811073303223} 08/31/2021 12:08:24 - INFO - __main__ - Step 126257: {'lr': 3.108715089156766e-05, 'samples': 24241344, 'steps': 126256, 'loss/train': 1.333645224571228} 08/31/2021 12:08:25 - INFO - __main__ - Step 126258: {'lr': 3.108458808205725e-05, 'samples': 24241536, 'steps': 126257, 'loss/train': 1.2245200872421265} 08/31/2021 12:08:25 - INFO - __main__ - Step 126259: {'lr': 3.1082025371186704e-05, 'samples': 24241728, 'steps': 126258, 'loss/train': 0.28147855401039124} 08/31/2021 12:08:25 - INFO - __main__ - Step 126260: {'lr': 3.1079462758957264e-05, 'samples': 24241920, 'steps': 126259, 'loss/train': 0.9551907777786255} 08/31/2021 12:08:26 - INFO - __main__ - Step 126261: {'lr': 3.107690024537008e-05, 'samples': 24242112, 'steps': 126260, 'loss/train': 0.9121264815330505} 08/31/2021 12:08:27 - INFO - __main__ - Step 126262: {'lr': 3.107433783042618e-05, 'samples': 24242304, 'steps': 126261, 'loss/train': 0.04286094754934311} 08/31/2021 12:08:28 - INFO - __main__ - Step 126263: {'lr': 3.107177551412685e-05, 'samples': 24242496, 'steps': 126262, 'loss/train': 1.2163562774658203} 08/31/2021 12:08:28 - INFO - __main__ - Step 126264: {'lr': 3.1069213296473166e-05, 'samples': 24242688, 'steps': 126263, 'loss/train': 1.4109265804290771} 08/31/2021 12:08:28 - INFO - __main__ - Step 126265: {'lr': 3.106665117746635e-05, 'samples': 24242880, 'steps': 126264, 'loss/train': 1.7608683109283447} 08/31/2021 12:08:29 - INFO - __main__ - Step 126266: {'lr': 3.1064089157107484e-05, 'samples': 24243072, 'steps': 126265, 'loss/train': 0.7750070095062256} 08/31/2021 12:08:30 - INFO - __main__ - Step 126267: {'lr': 3.106152723539779e-05, 'samples': 24243264, 'steps': 126266, 'loss/train': 1.2683322429656982} 08/31/2021 12:08:31 - INFO - __main__ - Step 126268: {'lr': 3.105896541233838e-05, 'samples': 24243456, 'steps': 126267, 'loss/train': 0.9467313885688782} 08/31/2021 12:08:31 - INFO - __main__ - Step 126269: {'lr': 3.1056403687930444e-05, 'samples': 24243648, 'steps': 126268, 'loss/train': 1.507084608078003} 08/31/2021 12:08:31 - INFO - __main__ - Step 126270: {'lr': 3.10538420621751e-05, 'samples': 24243840, 'steps': 126269, 'loss/train': 1.2097464799880981} 08/31/2021 12:08:32 - INFO - __main__ - Step 126271: {'lr': 3.10512805350735e-05, 'samples': 24244032, 'steps': 126270, 'loss/train': 0.8844565749168396} 08/31/2021 12:08:34 - INFO - __main__ - Step 126272: {'lr': 3.104871910662688e-05, 'samples': 24244224, 'steps': 126271, 'loss/train': 5.937644958496094} 08/31/2021 12:08:34 - INFO - __main__ - Step 126273: {'lr': 3.104615777683628e-05, 'samples': 24244416, 'steps': 126272, 'loss/train': 1.1404764652252197} 08/31/2021 12:08:34 - INFO - __main__ - Step 126274: {'lr': 3.1043596545702905e-05, 'samples': 24244608, 'steps': 126273, 'loss/train': 0.7979607582092285} 08/31/2021 12:08:35 - INFO - __main__ - Step 126275: {'lr': 3.104103541322789e-05, 'samples': 24244800, 'steps': 126274, 'loss/train': 0.0349033884704113} 08/31/2021 12:08:35 - INFO - __main__ - Step 126276: {'lr': 3.103847437941243e-05, 'samples': 24244992, 'steps': 126275, 'loss/train': 1.0696970224380493} 08/31/2021 12:08:35 - INFO - __main__ - Step 126277: {'lr': 3.103591344425763e-05, 'samples': 24245184, 'steps': 126276, 'loss/train': 1.4046217203140259} 08/31/2021 12:08:37 - INFO - __main__ - Step 126278: {'lr': 3.103335260776469e-05, 'samples': 24245376, 'steps': 126277, 'loss/train': 0.029136529192328453} 08/31/2021 12:08:37 - INFO - __main__ - Step 126279: {'lr': 3.103079186993471e-05, 'samples': 24245568, 'steps': 126278, 'loss/train': 0.9551433324813843} 08/31/2021 12:08:38 - INFO - __main__ - Step 126280: {'lr': 3.1028231230768896e-05, 'samples': 24245760, 'steps': 126279, 'loss/train': 0.5884934067726135} 08/31/2021 12:08:38 - INFO - __main__ - Step 126281: {'lr': 3.10256706902684e-05, 'samples': 24245952, 'steps': 126280, 'loss/train': 0.9806548953056335} 08/31/2021 12:08:38 - INFO - __main__ - Step 126282: {'lr': 3.102311024843435e-05, 'samples': 24246144, 'steps': 126281, 'loss/train': 1.5281562805175781} 08/31/2021 12:08:40 - INFO - __main__ - Step 126283: {'lr': 3.102054990526795e-05, 'samples': 24246336, 'steps': 126282, 'loss/train': 1.2541887760162354} 08/31/2021 12:08:40 - INFO - __main__ - Step 126284: {'lr': 3.101798966077024e-05, 'samples': 24246528, 'steps': 126283, 'loss/train': 1.4347732067108154} 08/31/2021 12:08:41 - INFO - __main__ - Step 126285: {'lr': 3.1015429514942486e-05, 'samples': 24246720, 'steps': 126284, 'loss/train': 1.227134108543396} 08/31/2021 12:08:41 - INFO - __main__ - Step 126286: {'lr': 3.101286946778578e-05, 'samples': 24246912, 'steps': 126285, 'loss/train': 1.4364582300186157} 08/31/2021 12:08:41 - INFO - __main__ - Step 126287: {'lr': 3.1010309519301285e-05, 'samples': 24247104, 'steps': 126286, 'loss/train': 0.9918610453605652} 08/31/2021 12:08:43 - INFO - __main__ - Step 126288: {'lr': 3.1007749669490185e-05, 'samples': 24247296, 'steps': 126287, 'loss/train': 0.8944292664527893} 08/31/2021 12:08:43 - INFO - __main__ - Step 126289: {'lr': 3.1005189918353605e-05, 'samples': 24247488, 'steps': 126288, 'loss/train': 1.814610481262207} 08/31/2021 12:08:44 - INFO - __main__ - Step 126290: {'lr': 3.10026302658927e-05, 'samples': 24247680, 'steps': 126289, 'loss/train': 1.0718621015548706} 08/31/2021 12:08:44 - INFO - __main__ - Step 126291: {'lr': 3.100007071210864e-05, 'samples': 24247872, 'steps': 126290, 'loss/train': 1.60822331905365} 08/31/2021 12:08:44 - INFO - __main__ - Step 126292: {'lr': 3.099751125700256e-05, 'samples': 24248064, 'steps': 126291, 'loss/train': 1.230438470840454} 08/31/2021 12:08:46 - INFO - __main__ - Step 126293: {'lr': 3.099495190057564e-05, 'samples': 24248256, 'steps': 126292, 'loss/train': 1.0863018035888672} 08/31/2021 12:08:46 - INFO - __main__ - Step 126294: {'lr': 3.099239264282905e-05, 'samples': 24248448, 'steps': 126293, 'loss/train': 0.733691394329071} 08/31/2021 12:08:47 - INFO - __main__ - Step 126295: {'lr': 3.0989833483763857e-05, 'samples': 24248640, 'steps': 126294, 'loss/train': 1.2074694633483887} 08/31/2021 12:08:47 - INFO - __main__ - Step 126296: {'lr': 3.0987274423381256e-05, 'samples': 24248832, 'steps': 126295, 'loss/train': 0.8502759337425232} 08/31/2021 12:08:47 - INFO - __main__ - Step 126297: {'lr': 3.098471546168244e-05, 'samples': 24249024, 'steps': 126296, 'loss/train': 1.2471526861190796} 08/31/2021 12:08:48 - INFO - __main__ - Step 126298: {'lr': 3.098215659866852e-05, 'samples': 24249216, 'steps': 126297, 'loss/train': 1.0137014389038086} 08/31/2021 12:08:49 - INFO - __main__ - Step 126299: {'lr': 3.097959783434065e-05, 'samples': 24249408, 'steps': 126298, 'loss/train': 2.0462136268615723} 08/31/2021 12:08:50 - INFO - __main__ - Step 126300: {'lr': 3.097703916870001e-05, 'samples': 24249600, 'steps': 126299, 'loss/train': 1.3203496932983398} 08/31/2021 12:08:50 - INFO - __main__ - Step 126301: {'lr': 3.097448060174771e-05, 'samples': 24249792, 'steps': 126300, 'loss/train': 1.6746602058410645} 08/31/2021 12:08:50 - INFO - __main__ - Step 126302: {'lr': 3.097192213348496e-05, 'samples': 24249984, 'steps': 126301, 'loss/train': 1.0494104623794556} 08/31/2021 12:08:51 - INFO - __main__ - Step 126303: {'lr': 3.096936376391285e-05, 'samples': 24250176, 'steps': 126302, 'loss/train': 1.4107787609100342} 08/31/2021 12:08:53 - INFO - __main__ - Step 126304: {'lr': 3.096680549303257e-05, 'samples': 24250368, 'steps': 126303, 'loss/train': 0.7485347390174866} 08/31/2021 12:08:54 - INFO - __main__ - Step 126305: {'lr': 3.096424732084535e-05, 'samples': 24250560, 'steps': 126304, 'loss/train': 1.7451372146606445} 08/31/2021 12:08:54 - INFO - __main__ - Step 126306: {'lr': 3.096168924735218e-05, 'samples': 24250752, 'steps': 126305, 'loss/train': 0.2690673768520355} 08/31/2021 12:08:55 - INFO - __main__ - Step 126307: {'lr': 3.0959131272554316e-05, 'samples': 24250944, 'steps': 126306, 'loss/train': 0.6973205208778381} 08/31/2021 12:08:55 - INFO - __main__ - Step 126308: {'lr': 3.095657339645286e-05, 'samples': 24251136, 'steps': 126307, 'loss/train': 0.9808471202850342} 08/31/2021 12:08:55 - INFO - __main__ - Step 126309: {'lr': 3.095401561904901e-05, 'samples': 24251328, 'steps': 126308, 'loss/train': 1.1764020919799805} 08/31/2021 12:08:57 - INFO - __main__ - Step 126310: {'lr': 3.0951457940343905e-05, 'samples': 24251520, 'steps': 126309, 'loss/train': 0.09417541325092316} 08/31/2021 12:08:58 - INFO - __main__ - Step 126311: {'lr': 3.0948900360338676e-05, 'samples': 24251712, 'steps': 126310, 'loss/train': 1.649341344833374} 08/31/2021 12:08:58 - INFO - __main__ - Step 126312: {'lr': 3.09463428790345e-05, 'samples': 24251904, 'steps': 126311, 'loss/train': 0.9577928781509399} 08/31/2021 12:08:58 - INFO - __main__ - Step 126313: {'lr': 3.094378549643254e-05, 'samples': 24252096, 'steps': 126312, 'loss/train': 1.3155206441879272} 08/31/2021 12:08:59 - INFO - __main__ - Step 126314: {'lr': 3.094122821253389e-05, 'samples': 24252288, 'steps': 126313, 'loss/train': 1.3329321146011353} 08/31/2021 12:09:00 - INFO - __main__ - Step 126315: {'lr': 3.0938671027339774e-05, 'samples': 24252480, 'steps': 126314, 'loss/train': 1.08218514919281} 08/31/2021 12:09:01 - INFO - __main__ - Step 126316: {'lr': 3.0936113940851305e-05, 'samples': 24252672, 'steps': 126315, 'loss/train': 0.9551630616188049} 08/31/2021 12:09:01 - INFO - __main__ - Step 126317: {'lr': 3.093355695306965e-05, 'samples': 24252864, 'steps': 126316, 'loss/train': 0.92430579662323} 08/31/2021 12:09:01 - INFO - __main__ - Step 126318: {'lr': 3.0931000063995934e-05, 'samples': 24253056, 'steps': 126317, 'loss/train': 0.7849688529968262} 08/31/2021 12:09:02 - INFO - __main__ - Step 126319: {'lr': 3.0928443273631396e-05, 'samples': 24253248, 'steps': 126318, 'loss/train': 0.9246754050254822} 08/31/2021 12:09:04 - INFO - __main__ - Step 126320: {'lr': 3.092588658197706e-05, 'samples': 24253440, 'steps': 126319, 'loss/train': 0.9250596761703491} 08/31/2021 12:09:04 - INFO - __main__ - Step 126321: {'lr': 3.092332998903416e-05, 'samples': 24253632, 'steps': 126320, 'loss/train': 0.09569375962018967} 08/31/2021 12:09:04 - INFO - __main__ - Step 126322: {'lr': 3.092077349480379e-05, 'samples': 24253824, 'steps': 126321, 'loss/train': 1.133458137512207} 08/31/2021 12:09:05 - INFO - __main__ - Step 126323: {'lr': 3.091821709928716e-05, 'samples': 24254016, 'steps': 126322, 'loss/train': 1.701581597328186} 08/31/2021 12:09:05 - INFO - __main__ - Step 126324: {'lr': 3.0915660802485394e-05, 'samples': 24254208, 'steps': 126323, 'loss/train': 0.7581154108047485} 08/31/2021 12:09:05 - INFO - __main__ - Step 126325: {'lr': 3.0913104604399666e-05, 'samples': 24254400, 'steps': 126324, 'loss/train': 0.015300135128200054} 08/31/2021 12:09:07 - INFO - __main__ - Step 126326: {'lr': 3.091054850503111e-05, 'samples': 24254592, 'steps': 126325, 'loss/train': 1.1720995903015137} 08/31/2021 12:09:07 - INFO - __main__ - Step 126327: {'lr': 3.090799250438087e-05, 'samples': 24254784, 'steps': 126326, 'loss/train': 1.5845776796340942} 08/31/2021 12:09:08 - INFO - __main__ - Step 126328: {'lr': 3.0905436602450126e-05, 'samples': 24254976, 'steps': 126327, 'loss/train': 0.9397422671318054} 08/31/2021 12:09:08 - INFO - __main__ - Step 126329: {'lr': 3.090288079923997e-05, 'samples': 24255168, 'steps': 126328, 'loss/train': 1.472130537033081} 08/31/2021 12:09:08 - INFO - __main__ - Step 126330: {'lr': 3.090032509475163e-05, 'samples': 24255360, 'steps': 126329, 'loss/train': 0.8243421316146851} 08/31/2021 12:09:09 - INFO - __main__ - Step 126331: {'lr': 3.089776948898621e-05, 'samples': 24255552, 'steps': 126330, 'loss/train': 0.9065550565719604} 08/31/2021 12:09:10 - INFO - __main__ - Step 126332: {'lr': 3.0895213981944944e-05, 'samples': 24255744, 'steps': 126331, 'loss/train': 0.9031916856765747} 08/31/2021 12:09:11 - INFO - __main__ - Step 126333: {'lr': 3.0892658573628854e-05, 'samples': 24255936, 'steps': 126332, 'loss/train': 1.1792153120040894} 08/31/2021 12:09:11 - INFO - __main__ - Step 126334: {'lr': 3.089010326403913e-05, 'samples': 24256128, 'steps': 126333, 'loss/train': 0.030114077031612396} 08/31/2021 12:09:12 - INFO - __main__ - Step 126335: {'lr': 3.088754805317695e-05, 'samples': 24256320, 'steps': 126334, 'loss/train': 1.5717518329620361} 08/31/2021 12:09:12 - INFO - __main__ - Step 126336: {'lr': 3.088499294104349e-05, 'samples': 24256512, 'steps': 126335, 'loss/train': 1.503434658050537} 08/31/2021 12:09:13 - INFO - __main__ - Step 126337: {'lr': 3.088243792763984e-05, 'samples': 24256704, 'steps': 126336, 'loss/train': 0.3133431673049927} 08/31/2021 12:09:14 - INFO - __main__ - Step 126338: {'lr': 3.087988301296721e-05, 'samples': 24256896, 'steps': 126337, 'loss/train': 1.00360107421875} 08/31/2021 12:09:14 - INFO - __main__ - Step 126339: {'lr': 3.087732819702668e-05, 'samples': 24257088, 'steps': 126338, 'loss/train': 0.8878884315490723} 08/31/2021 12:09:15 - INFO - __main__ - Step 126340: {'lr': 3.087477347981948e-05, 'samples': 24257280, 'steps': 126339, 'loss/train': 0.861524760723114} 08/31/2021 12:09:15 - INFO - __main__ - Step 126341: {'lr': 3.087221886134672e-05, 'samples': 24257472, 'steps': 126340, 'loss/train': 1.3701422214508057} 08/31/2021 12:09:16 - INFO - __main__ - Step 126342: {'lr': 3.0869664341609535e-05, 'samples': 24257664, 'steps': 126341, 'loss/train': 1.3897119760513306} 08/31/2021 12:09:17 - INFO - __main__ - Step 126343: {'lr': 3.086710992060912e-05, 'samples': 24257856, 'steps': 126342, 'loss/train': 1.3528647422790527} 08/31/2021 12:09:17 - INFO - __main__ - Step 126344: {'lr': 3.086455559834661e-05, 'samples': 24258048, 'steps': 126343, 'loss/train': 0.6607017517089844} 08/31/2021 12:09:18 - INFO - __main__ - Step 126345: {'lr': 3.08620013748232e-05, 'samples': 24258240, 'steps': 126344, 'loss/train': 0.31082361936569214} 08/31/2021 12:09:18 - INFO - __main__ - Step 126346: {'lr': 3.085944725003992e-05, 'samples': 24258432, 'steps': 126345, 'loss/train': 1.1131891012191772} 08/31/2021 12:09:19 - INFO - __main__ - Step 126347: {'lr': 3.085689322399801e-05, 'samples': 24258624, 'steps': 126346, 'loss/train': 0.8318479061126709} 08/31/2021 12:09:20 - INFO - __main__ - Step 126348: {'lr': 3.085433929669859e-05, 'samples': 24258816, 'steps': 126347, 'loss/train': 1.2284948825836182} 08/31/2021 12:09:20 - INFO - __main__ - Step 126349: {'lr': 3.0851785468142825e-05, 'samples': 24259008, 'steps': 126348, 'loss/train': 1.4467251300811768} 08/31/2021 12:09:21 - INFO - __main__ - Step 126350: {'lr': 3.0849231738331875e-05, 'samples': 24259200, 'steps': 126349, 'loss/train': 1.6014727354049683} 08/31/2021 12:09:21 - INFO - __main__ - Step 126351: {'lr': 3.0846678107266854e-05, 'samples': 24259392, 'steps': 126350, 'loss/train': 1.1253368854522705} 08/31/2021 12:09:23 - INFO - __main__ - Step 126352: {'lr': 3.0844124574948953e-05, 'samples': 24259584, 'steps': 126351, 'loss/train': 1.1950461864471436} 08/31/2021 12:09:23 - INFO - __main__ - Step 126353: {'lr': 3.084157114137931e-05, 'samples': 24259776, 'steps': 126352, 'loss/train': 1.2545137405395508} 08/31/2021 12:09:23 - INFO - __main__ - Step 126354: {'lr': 3.083901780655909e-05, 'samples': 24259968, 'steps': 126353, 'loss/train': 0.49975350499153137} 08/31/2021 12:09:24 - INFO - __main__ - Step 126355: {'lr': 3.083646457048941e-05, 'samples': 24260160, 'steps': 126354, 'loss/train': 0.32977980375289917} 08/31/2021 12:09:24 - INFO - __main__ - Step 126356: {'lr': 3.0833911433171436e-05, 'samples': 24260352, 'steps': 126355, 'loss/train': 0.8957878351211548} 08/31/2021 12:09:26 - INFO - __main__ - Step 126357: {'lr': 3.083135839460632e-05, 'samples': 24260544, 'steps': 126356, 'loss/train': 0.8531312346458435} 08/31/2021 12:09:27 - INFO - __main__ - Step 126358: {'lr': 3.082880545479519e-05, 'samples': 24260736, 'steps': 126357, 'loss/train': 1.0606651306152344} 08/31/2021 12:09:27 - INFO - __main__ - Step 126359: {'lr': 3.0826252613739306e-05, 'samples': 24260928, 'steps': 126358, 'loss/train': 0.5777668356895447} 08/31/2021 12:09:27 - INFO - __main__ - Step 126360: {'lr': 3.082369987143965e-05, 'samples': 24261120, 'steps': 126359, 'loss/train': 0.35884490609169006} 08/31/2021 12:09:28 - INFO - __main__ - Step 126361: {'lr': 3.082114722789747e-05, 'samples': 24261312, 'steps': 126360, 'loss/train': 0.9349576234817505} 08/31/2021 12:09:28 - INFO - __main__ - Step 126362: {'lr': 3.0818594683113905e-05, 'samples': 24261504, 'steps': 126361, 'loss/train': 0.4837777018547058} 08/31/2021 12:09:29 - INFO - __main__ - Step 126363: {'lr': 3.0816042237090085e-05, 'samples': 24261696, 'steps': 126362, 'loss/train': 0.09026055783033371} 08/31/2021 12:09:30 - INFO - __main__ - Step 126364: {'lr': 3.081348988982718e-05, 'samples': 24261888, 'steps': 126363, 'loss/train': 1.4578450918197632} 08/31/2021 12:09:30 - INFO - __main__ - Step 126365: {'lr': 3.0810937641326335e-05, 'samples': 24262080, 'steps': 126364, 'loss/train': 1.0486652851104736} 08/31/2021 12:09:31 - INFO - __main__ - Step 126366: {'lr': 3.080838549158871e-05, 'samples': 24262272, 'steps': 126365, 'loss/train': 1.2665561437606812} 08/31/2021 12:09:31 - INFO - __main__ - Step 126367: {'lr': 3.080583344061544e-05, 'samples': 24262464, 'steps': 126366, 'loss/train': 0.5665788650512695} 08/31/2021 12:09:33 - INFO - __main__ - Step 126368: {'lr': 3.0803281488407666e-05, 'samples': 24262656, 'steps': 126367, 'loss/train': 1.173264503479004} 08/31/2021 12:09:33 - INFO - __main__ - Step 126369: {'lr': 3.080072963496655e-05, 'samples': 24262848, 'steps': 126368, 'loss/train': 1.3899502754211426} 08/31/2021 12:09:33 - INFO - __main__ - Step 126370: {'lr': 3.079817788029324e-05, 'samples': 24263040, 'steps': 126369, 'loss/train': 1.006237506866455} 08/31/2021 12:09:34 - INFO - __main__ - Step 126371: {'lr': 3.079562622438889e-05, 'samples': 24263232, 'steps': 126370, 'loss/train': 1.15015709400177} 08/31/2021 12:09:34 - INFO - __main__ - Step 126372: {'lr': 3.079307466725473e-05, 'samples': 24263424, 'steps': 126371, 'loss/train': 1.2791792154312134} 08/31/2021 12:09:36 - INFO - __main__ - Step 126373: {'lr': 3.0790523208891754e-05, 'samples': 24263616, 'steps': 126372, 'loss/train': 0.60917067527771} 08/31/2021 12:09:36 - INFO - __main__ - Step 126374: {'lr': 3.0787971849301184e-05, 'samples': 24263808, 'steps': 126373, 'loss/train': 0.8826882243156433} 08/31/2021 12:09:37 - INFO - __main__ - Step 126375: {'lr': 3.0785420588484156e-05, 'samples': 24264000, 'steps': 126374, 'loss/train': 1.0885488986968994} 08/31/2021 12:09:37 - INFO - __main__ - Step 126376: {'lr': 3.0782869426441876e-05, 'samples': 24264192, 'steps': 126375, 'loss/train': 0.03453841805458069} 08/31/2021 12:09:37 - INFO - __main__ - Step 126377: {'lr': 3.078031836317541e-05, 'samples': 24264384, 'steps': 126376, 'loss/train': 0.9521519541740417} 08/31/2021 12:09:39 - INFO - __main__ - Step 126378: {'lr': 3.077776739868596e-05, 'samples': 24264576, 'steps': 126377, 'loss/train': 0.03693851828575134} 08/31/2021 12:09:39 - INFO - __main__ - Step 126379: {'lr': 3.0775216532974686e-05, 'samples': 24264768, 'steps': 126378, 'loss/train': 1.7109438180923462} 08/31/2021 12:09:40 - INFO - __main__ - Step 126380: {'lr': 3.077266576604271e-05, 'samples': 24264960, 'steps': 126379, 'loss/train': 0.6640716195106506} 08/31/2021 12:09:40 - INFO - __main__ - Step 126381: {'lr': 3.0770115097891184e-05, 'samples': 24265152, 'steps': 126380, 'loss/train': 1.0409165620803833} 08/31/2021 12:09:40 - INFO - __main__ - Step 126382: {'lr': 3.076756452852125e-05, 'samples': 24265344, 'steps': 126381, 'loss/train': 1.7233229875564575} 08/31/2021 12:09:41 - INFO - __main__ - Step 126383: {'lr': 3.0765014057934085e-05, 'samples': 24265536, 'steps': 126382, 'loss/train': 1.4037271738052368} 08/31/2021 12:09:42 - INFO - __main__ - Step 126384: {'lr': 3.076246368613081e-05, 'samples': 24265728, 'steps': 126383, 'loss/train': 1.0723642110824585} 08/31/2021 12:09:43 - INFO - __main__ - Step 126385: {'lr': 3.075991341311257e-05, 'samples': 24265920, 'steps': 126384, 'loss/train': 1.0645742416381836} 08/31/2021 12:09:43 - INFO - __main__ - Step 126386: {'lr': 3.075736323888062e-05, 'samples': 24266112, 'steps': 126385, 'loss/train': 0.7826767563819885} 08/31/2021 12:09:43 - INFO - __main__ - Step 126387: {'lr': 3.075481316343595e-05, 'samples': 24266304, 'steps': 126386, 'loss/train': 1.1421496868133545} 08/31/2021 12:09:44 - INFO - __main__ - Step 126388: {'lr': 3.075226318677976e-05, 'samples': 24266496, 'steps': 126387, 'loss/train': 0.9192206263542175} 08/31/2021 12:09:45 - INFO - __main__ - Step 126389: {'lr': 3.074971330891324e-05, 'samples': 24266688, 'steps': 126388, 'loss/train': 0.8886140584945679} 08/31/2021 12:09:46 - INFO - __main__ - Step 126390: {'lr': 3.07471635298375e-05, 'samples': 24266880, 'steps': 126389, 'loss/train': 1.371193289756775} 08/31/2021 12:09:46 - INFO - __main__ - Step 126391: {'lr': 3.074461384955371e-05, 'samples': 24267072, 'steps': 126390, 'loss/train': 1.4790408611297607} 08/31/2021 12:09:46 - INFO - __main__ - Step 126392: {'lr': 3.074206426806303e-05, 'samples': 24267264, 'steps': 126391, 'loss/train': 0.02704140730202198} 08/31/2021 12:09:47 - INFO - __main__ - Step 126393: {'lr': 3.0739514785366575e-05, 'samples': 24267456, 'steps': 126392, 'loss/train': 1.1162110567092896} 08/31/2021 12:09:49 - INFO - __main__ - Step 126394: {'lr': 3.0736965401465534e-05, 'samples': 24267648, 'steps': 126393, 'loss/train': 1.1052719354629517} 08/31/2021 12:09:49 - INFO - __main__ - Step 126395: {'lr': 3.0734416116360994e-05, 'samples': 24267840, 'steps': 126394, 'loss/train': 0.9058762192726135} 08/31/2021 12:09:49 - INFO - __main__ - Step 126396: {'lr': 3.073186693005417e-05, 'samples': 24268032, 'steps': 126395, 'loss/train': 1.2009873390197754} 08/31/2021 12:09:50 - INFO - __main__ - Step 126397: {'lr': 3.072931784254618e-05, 'samples': 24268224, 'steps': 126396, 'loss/train': 1.3662889003753662} 08/31/2021 12:09:50 - INFO - __main__ - Step 126398: {'lr': 3.0726768853838184e-05, 'samples': 24268416, 'steps': 126397, 'loss/train': 2.346780776977539} 08/31/2021 12:09:52 - INFO - __main__ - Step 126399: {'lr': 3.0724219963931346e-05, 'samples': 24268608, 'steps': 126398, 'loss/train': 1.4909064769744873} 08/31/2021 12:09:52 - INFO - __main__ - Step 126400: {'lr': 3.072167117282676e-05, 'samples': 24268800, 'steps': 126399, 'loss/train': 0.851594865322113} 08/31/2021 12:09:53 - INFO - __main__ - Step 126401: {'lr': 3.071912248052561e-05, 'samples': 24268992, 'steps': 126400, 'loss/train': 0.5816754698753357} 08/31/2021 12:09:53 - INFO - __main__ - Step 126402: {'lr': 3.071657388702903e-05, 'samples': 24269184, 'steps': 126401, 'loss/train': 1.1265376806259155} 08/31/2021 12:09:53 - INFO - __main__ - Step 126403: {'lr': 3.0714025392338166e-05, 'samples': 24269376, 'steps': 126402, 'loss/train': 1.4657419919967651} 08/31/2021 12:09:54 - INFO - __main__ - Step 126404: {'lr': 3.0711476996454214e-05, 'samples': 24269568, 'steps': 126403, 'loss/train': 0.9077283143997192} 08/31/2021 12:09:55 - INFO - __main__ - Step 126405: {'lr': 3.070892869937825e-05, 'samples': 24269760, 'steps': 126404, 'loss/train': 0.4958125054836273} 08/31/2021 12:09:56 - INFO - __main__ - Step 126406: {'lr': 3.070638050111146e-05, 'samples': 24269952, 'steps': 126405, 'loss/train': 1.5631400346755981} 08/31/2021 12:09:56 - INFO - __main__ - Step 126407: {'lr': 3.070383240165503e-05, 'samples': 24270144, 'steps': 126406, 'loss/train': 0.7756015062332153} 08/31/2021 12:09:56 - INFO - __main__ - Step 126408: {'lr': 3.070128440101003e-05, 'samples': 24270336, 'steps': 126407, 'loss/train': 1.7204562425613403} 08/31/2021 12:09:57 - INFO - __main__ - Step 126409: {'lr': 3.0698736499177675e-05, 'samples': 24270528, 'steps': 126408, 'loss/train': 0.8752058744430542} 08/31/2021 12:09:58 - INFO - __main__ - Step 126410: {'lr': 3.069618869615906e-05, 'samples': 24270720, 'steps': 126409, 'loss/train': 0.8633173704147339} 08/31/2021 12:09:59 - INFO - __main__ - Step 126411: {'lr': 3.0693640991955375e-05, 'samples': 24270912, 'steps': 126410, 'loss/train': 1.3363639116287231} 08/31/2021 12:09:59 - INFO - __main__ - Step 126412: {'lr': 3.0691093386567754e-05, 'samples': 24271104, 'steps': 126411, 'loss/train': 1.0828070640563965} 08/31/2021 12:09:59 - INFO - __main__ - Step 126413: {'lr': 3.068854587999737e-05, 'samples': 24271296, 'steps': 126412, 'loss/train': 0.8171151280403137} 08/31/2021 12:10:00 - INFO - __main__ - Step 126414: {'lr': 3.068599847224532e-05, 'samples': 24271488, 'steps': 126413, 'loss/train': 0.817888617515564} 08/31/2021 12:10:03 - INFO - __main__ - Step 126415: {'lr': 3.0683451163312754e-05, 'samples': 24271680, 'steps': 126414, 'loss/train': 1.211552381515503} 08/31/2021 12:10:03 - INFO - __main__ - Step 126416: {'lr': 3.068090395320083e-05, 'samples': 24271872, 'steps': 126415, 'loss/train': 1.1231637001037598} 08/31/2021 12:10:03 - INFO - __main__ - Step 126417: {'lr': 3.0678356841910757e-05, 'samples': 24272064, 'steps': 126416, 'loss/train': 0.2208603024482727} 08/31/2021 12:10:04 - INFO - __main__ - Step 126418: {'lr': 3.0675809829443596e-05, 'samples': 24272256, 'steps': 126417, 'loss/train': 1.1659469604492188} 08/31/2021 12:10:04 - INFO - __main__ - Step 126419: {'lr': 3.067326291580053e-05, 'samples': 24272448, 'steps': 126418, 'loss/train': 0.765969455242157} 08/31/2021 12:10:04 - INFO - __main__ - Step 126420: {'lr': 3.067071610098271e-05, 'samples': 24272640, 'steps': 126419, 'loss/train': 2.7573797702789307} 08/31/2021 12:10:06 - INFO - __main__ - Step 126421: {'lr': 3.066816938499128e-05, 'samples': 24272832, 'steps': 126420, 'loss/train': 2.6577563285827637} 08/31/2021 12:10:06 - INFO - __main__ - Step 126422: {'lr': 3.066562276782739e-05, 'samples': 24273024, 'steps': 126421, 'loss/train': 1.3000588417053223} 08/31/2021 12:10:07 - INFO - __main__ - Step 126423: {'lr': 3.066307624949219e-05, 'samples': 24273216, 'steps': 126422, 'loss/train': 1.1391741037368774} 08/31/2021 12:10:07 - INFO - __main__ - Step 126424: {'lr': 3.0660529829986824e-05, 'samples': 24273408, 'steps': 126423, 'loss/train': 1.5162925720214844} 08/31/2021 12:10:07 - INFO - __main__ - Step 126425: {'lr': 3.0657983509312424e-05, 'samples': 24273600, 'steps': 126424, 'loss/train': 1.5928701162338257} 08/31/2021 12:10:09 - INFO - __main__ - Step 126426: {'lr': 3.065543728747022e-05, 'samples': 24273792, 'steps': 126425, 'loss/train': 0.9257159233093262} 08/31/2021 12:10:09 - INFO - __main__ - Step 126427: {'lr': 3.065289116446124e-05, 'samples': 24273984, 'steps': 126426, 'loss/train': 1.2034651041030884} 08/31/2021 12:10:10 - INFO - __main__ - Step 126428: {'lr': 3.0650345140286664e-05, 'samples': 24274176, 'steps': 126427, 'loss/train': 0.939012348651886} 08/31/2021 12:10:10 - INFO - __main__ - Step 126429: {'lr': 3.0647799214947674e-05, 'samples': 24274368, 'steps': 126428, 'loss/train': 1.1225953102111816} 08/31/2021 12:10:10 - INFO - __main__ - Step 126430: {'lr': 3.06452533884454e-05, 'samples': 24274560, 'steps': 126429, 'loss/train': 0.41309499740600586} 08/31/2021 12:10:12 - INFO - __main__ - Step 126431: {'lr': 3.0642707660780976e-05, 'samples': 24274752, 'steps': 126430, 'loss/train': 1.1864111423492432} 08/31/2021 12:10:12 - INFO - __main__ - Step 126432: {'lr': 3.064016203195558e-05, 'samples': 24274944, 'steps': 126431, 'loss/train': 0.6360637545585632} 08/31/2021 12:10:13 - INFO - __main__ - Step 126433: {'lr': 3.0637616501970336e-05, 'samples': 24275136, 'steps': 126432, 'loss/train': 0.5600802898406982} 08/31/2021 12:10:13 - INFO - __main__ - Step 126434: {'lr': 3.063507107082639e-05, 'samples': 24275328, 'steps': 126433, 'loss/train': 1.4424245357513428} 08/31/2021 12:10:13 - INFO - __main__ - Step 126435: {'lr': 3.06325257385249e-05, 'samples': 24275520, 'steps': 126434, 'loss/train': 1.0992255210876465} 08/31/2021 12:10:15 - INFO - __main__ - Step 126436: {'lr': 3.062998050506702e-05, 'samples': 24275712, 'steps': 126435, 'loss/train': 1.1606062650680542} 08/31/2021 12:10:16 - INFO - __main__ - Step 126437: {'lr': 3.062743537045387e-05, 'samples': 24275904, 'steps': 126436, 'loss/train': 1.3288735151290894} 08/31/2021 12:10:16 - INFO - __main__ - Step 126438: {'lr': 3.062489033468663e-05, 'samples': 24276096, 'steps': 126437, 'loss/train': 1.2777376174926758} 08/31/2021 12:10:16 - INFO - __main__ - Step 126439: {'lr': 3.0622345397766424e-05, 'samples': 24276288, 'steps': 126438, 'loss/train': 0.03758031502366066} 08/31/2021 12:10:17 - INFO - __main__ - Step 126440: {'lr': 3.061980055969446e-05, 'samples': 24276480, 'steps': 126439, 'loss/train': 0.6576685309410095} 08/31/2021 12:10:18 - INFO - __main__ - Step 126441: {'lr': 3.0617255820471755e-05, 'samples': 24276672, 'steps': 126440, 'loss/train': 1.3224208354949951} 08/31/2021 12:10:19 - INFO - __main__ - Step 126442: {'lr': 3.0614711180099534e-05, 'samples': 24276864, 'steps': 126441, 'loss/train': 0.36404862999916077} 08/31/2021 12:10:19 - INFO - __main__ - Step 126443: {'lr': 3.0612166638578964e-05, 'samples': 24277056, 'steps': 126442, 'loss/train': 0.9526755213737488} 08/31/2021 12:10:19 - INFO - __main__ - Step 126444: {'lr': 3.060962219591115e-05, 'samples': 24277248, 'steps': 126443, 'loss/train': 0.5583053231239319} 08/31/2021 12:10:20 - INFO - __main__ - Step 126445: {'lr': 3.060707785209724e-05, 'samples': 24277440, 'steps': 126444, 'loss/train': 1.2317100763320923} 08/31/2021 12:10:20 - INFO - __main__ - Step 126446: {'lr': 3.0604533607138416e-05, 'samples': 24277632, 'steps': 126445, 'loss/train': 1.2115782499313354} 08/31/2021 12:10:21 - INFO - __main__ - Step 126447: {'lr': 3.060198946103579e-05, 'samples': 24277824, 'steps': 126446, 'loss/train': 1.7711678743362427} 08/31/2021 12:10:22 - INFO - __main__ - Step 126448: {'lr': 3.059944541379053e-05, 'samples': 24278016, 'steps': 126447, 'loss/train': 1.1383450031280518} 08/31/2021 12:10:22 - INFO - __main__ - Step 126449: {'lr': 3.059690146540378e-05, 'samples': 24278208, 'steps': 126448, 'loss/train': 1.1996715068817139} 08/31/2021 12:10:23 - INFO - __main__ - Step 126450: {'lr': 3.0594357615876675e-05, 'samples': 24278400, 'steps': 126449, 'loss/train': 1.1525713205337524} 08/31/2021 12:10:23 - INFO - __main__ - Step 126451: {'lr': 3.059181386521037e-05, 'samples': 24278592, 'steps': 126450, 'loss/train': 1.5001938343048096} 08/31/2021 12:10:25 - INFO - __main__ - Step 126452: {'lr': 3.058927021340599e-05, 'samples': 24278784, 'steps': 126451, 'loss/train': 1.084297776222229} 08/31/2021 12:10:25 - INFO - __main__ - Step 126453: {'lr': 3.058672666046477e-05, 'samples': 24278976, 'steps': 126452, 'loss/train': 1.3960537910461426} 08/31/2021 12:10:25 - INFO - __main__ - Step 126454: {'lr': 3.058418320638773e-05, 'samples': 24279168, 'steps': 126453, 'loss/train': 1.059391736984253} 08/31/2021 12:10:26 - INFO - __main__ - Step 126455: {'lr': 3.058163985117607e-05, 'samples': 24279360, 'steps': 126454, 'loss/train': 1.2791266441345215} 08/31/2021 12:10:26 - INFO - __main__ - Step 126456: {'lr': 3.0579096594830936e-05, 'samples': 24279552, 'steps': 126455, 'loss/train': 1.141499638557434} 08/31/2021 12:10:27 - INFO - __main__ - Step 126457: {'lr': 3.0576553437353495e-05, 'samples': 24279744, 'steps': 126456, 'loss/train': 1.2407978773117065} 08/31/2021 12:10:28 - INFO - __main__ - Step 126458: {'lr': 3.0574010378744856e-05, 'samples': 24279936, 'steps': 126457, 'loss/train': 1.1337366104125977} 08/31/2021 12:10:28 - INFO - __main__ - Step 126459: {'lr': 3.057146741900615e-05, 'samples': 24280128, 'steps': 126458, 'loss/train': 0.2186560183763504} 08/31/2021 12:10:29 - INFO - __main__ - Step 126460: {'lr': 3.0568924558138615e-05, 'samples': 24280320, 'steps': 126459, 'loss/train': 0.21492968499660492} 08/31/2021 12:10:29 - INFO - __main__ - Step 126461: {'lr': 3.0566381796143297e-05, 'samples': 24280512, 'steps': 126460, 'loss/train': 1.1804628372192383} 08/31/2021 12:10:31 - INFO - __main__ - Step 126462: {'lr': 3.056383913302138e-05, 'samples': 24280704, 'steps': 126461, 'loss/train': 1.1619778871536255} 08/31/2021 12:10:31 - INFO - __main__ - Step 126463: {'lr': 3.056129656877404e-05, 'samples': 24280896, 'steps': 126462, 'loss/train': 1.2021403312683105} 08/31/2021 12:10:32 - INFO - __main__ - Step 126464: {'lr': 3.0558754103402364e-05, 'samples': 24281088, 'steps': 126463, 'loss/train': 1.363518476486206} 08/31/2021 12:10:32 - INFO - __main__ - Step 126465: {'lr': 3.055621173690754e-05, 'samples': 24281280, 'steps': 126464, 'loss/train': 0.3585512936115265} 08/31/2021 12:10:32 - INFO - __main__ - Step 126466: {'lr': 3.055366946929075e-05, 'samples': 24281472, 'steps': 126465, 'loss/train': 1.1557773351669312} 08/31/2021 12:10:33 - INFO - __main__ - Step 126467: {'lr': 3.055112730055304e-05, 'samples': 24281664, 'steps': 126466, 'loss/train': 1.7182857990264893} 08/31/2021 12:10:35 - INFO - __main__ - Step 126468: {'lr': 3.0548585230695617e-05, 'samples': 24281856, 'steps': 126467, 'loss/train': 1.2479453086853027} 08/31/2021 12:10:35 - INFO - __main__ - Step 126469: {'lr': 3.05460432597196e-05, 'samples': 24282048, 'steps': 126468, 'loss/train': 1.3996518850326538} 08/31/2021 12:10:35 - INFO - __main__ - Step 126470: {'lr': 3.0543501387626155e-05, 'samples': 24282240, 'steps': 126469, 'loss/train': 1.152727723121643} 08/31/2021 12:10:36 - INFO - __main__ - Step 126471: {'lr': 3.0540959614416415e-05, 'samples': 24282432, 'steps': 126470, 'loss/train': 1.2375409603118896} 08/31/2021 12:10:36 - INFO - __main__ - Step 126472: {'lr': 3.053841794009154e-05, 'samples': 24282624, 'steps': 126471, 'loss/train': 1.4009387493133545} 08/31/2021 12:10:38 - INFO - __main__ - Step 126473: {'lr': 3.053587636465266e-05, 'samples': 24282816, 'steps': 126472, 'loss/train': 0.2663150429725647} 08/31/2021 12:10:38 - INFO - __main__ - Step 126474: {'lr': 3.053333488810092e-05, 'samples': 24283008, 'steps': 126473, 'loss/train': 1.1368277072906494} 08/31/2021 12:10:38 - INFO - __main__ - Step 126475: {'lr': 3.05307935104375e-05, 'samples': 24283200, 'steps': 126474, 'loss/train': 1.5020948648452759} 08/31/2021 12:10:39 - INFO - __main__ - Step 126476: {'lr': 3.0528252231663503e-05, 'samples': 24283392, 'steps': 126475, 'loss/train': 0.8958207368850708} 08/31/2021 12:10:39 - INFO - __main__ - Step 126477: {'lr': 3.0525711051780095e-05, 'samples': 24283584, 'steps': 126476, 'loss/train': 1.2763313055038452} 08/31/2021 12:10:41 - INFO - __main__ - Step 126478: {'lr': 3.052316997078841e-05, 'samples': 24283776, 'steps': 126477, 'loss/train': 1.191843032836914} 08/31/2021 12:10:41 - INFO - __main__ - Step 126479: {'lr': 3.0520628988689596e-05, 'samples': 24283968, 'steps': 126478, 'loss/train': 1.3414663076400757} 08/31/2021 12:10:41 - INFO - __main__ - Step 126480: {'lr': 3.0518088105484844e-05, 'samples': 24284160, 'steps': 126479, 'loss/train': 1.0859254598617554} 08/31/2021 12:10:42 - INFO - __main__ - Step 126481: {'lr': 3.0515547321175203e-05, 'samples': 24284352, 'steps': 126480, 'loss/train': 1.5092402696609497} 08/31/2021 12:10:42 - INFO - __main__ - Step 126482: {'lr': 3.051300663576187e-05, 'samples': 24284544, 'steps': 126481, 'loss/train': 0.7042089700698853} 08/31/2021 12:10:44 - INFO - __main__ - Step 126483: {'lr': 3.051046604924601e-05, 'samples': 24284736, 'steps': 126482, 'loss/train': 0.023875853046774864} 08/31/2021 12:10:44 - INFO - __main__ - Step 126484: {'lr': 3.0507925561628734e-05, 'samples': 24284928, 'steps': 126483, 'loss/train': 0.7116216421127319} 08/31/2021 12:10:44 - INFO - __main__ - Step 126485: {'lr': 3.050538517291121e-05, 'samples': 24285120, 'steps': 126484, 'loss/train': 0.7580385208129883} 08/31/2021 12:10:45 - INFO - __main__ - Step 126486: {'lr': 3.0502844883094544e-05, 'samples': 24285312, 'steps': 126485, 'loss/train': 1.5945074558258057} 08/31/2021 12:10:45 - INFO - __main__ - Step 126487: {'lr': 3.050030469217993e-05, 'samples': 24285504, 'steps': 126486, 'loss/train': 1.295282244682312} 08/31/2021 12:10:46 - INFO - __main__ - Step 126488: {'lr': 3.049776460016848e-05, 'samples': 24285696, 'steps': 126487, 'loss/train': 1.928945779800415} 08/31/2021 12:10:47 - INFO - __main__ - Step 126489: {'lr': 3.0495224607061362e-05, 'samples': 24285888, 'steps': 126488, 'loss/train': 1.6516774892807007} 08/31/2021 12:10:47 - INFO - __main__ - Step 126490: {'lr': 3.049268471285971e-05, 'samples': 24286080, 'steps': 126489, 'loss/train': 0.23029597103595734} 08/31/2021 12:10:48 - INFO - __main__ - Step 126491: {'lr': 3.049014491756466e-05, 'samples': 24286272, 'steps': 126490, 'loss/train': 1.6719497442245483} 08/31/2021 12:10:48 - INFO - __main__ - Step 126492: {'lr': 3.0487605221177385e-05, 'samples': 24286464, 'steps': 126491, 'loss/train': 0.5048422813415527} 08/31/2021 12:10:48 - INFO - __main__ - Step 126493: {'lr': 3.0485065623699044e-05, 'samples': 24286656, 'steps': 126492, 'loss/train': 0.8964467644691467} 08/31/2021 12:10:50 - INFO - __main__ - Step 126494: {'lr': 3.0482526125130666e-05, 'samples': 24286848, 'steps': 126493, 'loss/train': 1.2260674238204956} 08/31/2021 12:10:50 - INFO - __main__ - Step 126495: {'lr': 3.0479986725473502e-05, 'samples': 24287040, 'steps': 126494, 'loss/train': 1.2793500423431396} 08/31/2021 12:10:51 - INFO - __main__ - Step 126496: {'lr': 3.047744742472866e-05, 'samples': 24287232, 'steps': 126495, 'loss/train': 0.7965200543403625} 08/31/2021 12:10:51 - INFO - __main__ - Step 126497: {'lr': 3.0474908222897307e-05, 'samples': 24287424, 'steps': 126496, 'loss/train': 1.3242361545562744} 08/31/2021 12:10:51 - INFO - __main__ - Step 126498: {'lr': 3.0472369119980552e-05, 'samples': 24287616, 'steps': 126497, 'loss/train': 1.5945779085159302} 08/31/2021 12:10:53 - INFO - __main__ - Step 126499: {'lr': 3.046983011597959e-05, 'samples': 24287808, 'steps': 126498, 'loss/train': 1.3730825185775757} 08/31/2021 12:10:53 - INFO - __main__ - Step 126500: {'lr': 3.0467291210895504e-05, 'samples': 24288000, 'steps': 126499, 'loss/train': 0.8848044276237488} 08/31/2021 12:10:54 - INFO - __main__ - Step 126501: {'lr': 3.0464752404729485e-05, 'samples': 24288192, 'steps': 126500, 'loss/train': 0.9421635866165161} 08/31/2021 12:10:54 - INFO - __main__ - Step 126502: {'lr': 3.046221369748267e-05, 'samples': 24288384, 'steps': 126501, 'loss/train': 0.5309396982192993} 08/31/2021 12:10:54 - INFO - __main__ - Step 126503: {'lr': 3.0459675089156175e-05, 'samples': 24288576, 'steps': 126502, 'loss/train': 0.8161946535110474} 08/31/2021 12:10:56 - INFO - __main__ - Step 126504: {'lr': 3.045713657975116e-05, 'samples': 24288768, 'steps': 126503, 'loss/train': 0.27762025594711304} 08/31/2021 12:10:56 - INFO - __main__ - Step 126505: {'lr': 3.0454598169268793e-05, 'samples': 24288960, 'steps': 126504, 'loss/train': 0.4824623763561249} 08/31/2021 12:10:57 - INFO - __main__ - Step 126506: {'lr': 3.0452059857710184e-05, 'samples': 24289152, 'steps': 126505, 'loss/train': 0.9565205574035645} 08/31/2021 12:10:57 - INFO - __main__ - Step 126507: {'lr': 3.0449521645076526e-05, 'samples': 24289344, 'steps': 126506, 'loss/train': 1.2591205835342407} 08/31/2021 12:10:57 - INFO - __main__ - Step 126508: {'lr': 3.0446983531368906e-05, 'samples': 24289536, 'steps': 126507, 'loss/train': 0.8394396901130676} 08/31/2021 12:10:59 - INFO - __main__ - Step 126509: {'lr': 3.0444445516588453e-05, 'samples': 24289728, 'steps': 126508, 'loss/train': 1.1546227931976318} 08/31/2021 12:10:59 - INFO - __main__ - Step 126510: {'lr': 3.044190760073637e-05, 'samples': 24289920, 'steps': 126509, 'loss/train': 0.8787557482719421} 08/31/2021 12:11:00 - INFO - __main__ - Step 126511: {'lr': 3.043936978381376e-05, 'samples': 24290112, 'steps': 126510, 'loss/train': 1.1054497957229614} 08/31/2021 12:11:00 - INFO - __main__ - Step 126512: {'lr': 3.043683206582179e-05, 'samples': 24290304, 'steps': 126511, 'loss/train': 0.8942064642906189} 08/31/2021 12:11:00 - INFO - __main__ - Step 126513: {'lr': 3.04342944467616e-05, 'samples': 24290496, 'steps': 126512, 'loss/train': 1.068841814994812} 08/31/2021 12:11:02 - INFO - __main__ - Step 126514: {'lr': 3.043175692663433e-05, 'samples': 24290688, 'steps': 126513, 'loss/train': 1.1965214014053345} 08/31/2021 12:11:02 - INFO - __main__ - Step 126515: {'lr': 3.0429219505441113e-05, 'samples': 24290880, 'steps': 126514, 'loss/train': 2.194746732711792} 08/31/2021 12:11:03 - INFO - __main__ - Step 126516: {'lr': 3.042668218318309e-05, 'samples': 24291072, 'steps': 126515, 'loss/train': 1.0512652397155762} 08/31/2021 12:11:03 - INFO - __main__ - Step 126517: {'lr': 3.0424144959861428e-05, 'samples': 24291264, 'steps': 126516, 'loss/train': 1.0712019205093384} 08/31/2021 12:11:03 - INFO - __main__ - Step 126518: {'lr': 3.0421607835477262e-05, 'samples': 24291456, 'steps': 126517, 'loss/train': 1.0105485916137695} 08/31/2021 12:11:04 - INFO - __main__ - Step 126519: {'lr': 3.0419070810031786e-05, 'samples': 24291648, 'steps': 126518, 'loss/train': 1.2368028163909912} 08/31/2021 12:11:05 - INFO - __main__ - Step 126520: {'lr': 3.0416533883526026e-05, 'samples': 24291840, 'steps': 126519, 'loss/train': 1.4144548177719116} 08/31/2021 12:11:06 - INFO - __main__ - Step 126521: {'lr': 3.0413997055961206e-05, 'samples': 24292032, 'steps': 126520, 'loss/train': 0.7458842992782593} 08/31/2021 12:11:06 - INFO - __main__ - Step 126522: {'lr': 3.0411460327338436e-05, 'samples': 24292224, 'steps': 126521, 'loss/train': 1.5495070219039917} 08/31/2021 12:11:06 - INFO - __main__ - Step 126523: {'lr': 3.040892369765888e-05, 'samples': 24292416, 'steps': 126522, 'loss/train': 1.4486258029937744} 08/31/2021 12:11:07 - INFO - __main__ - Step 126524: {'lr': 3.040638716692365e-05, 'samples': 24292608, 'steps': 126523, 'loss/train': 0.34999021887779236} 08/31/2021 12:11:09 - INFO - __main__ - Step 126525: {'lr': 3.0403850735133937e-05, 'samples': 24292800, 'steps': 126524, 'loss/train': 1.3445382118225098} 08/31/2021 12:11:09 - INFO - __main__ - Step 126526: {'lr': 3.0401314402290853e-05, 'samples': 24292992, 'steps': 126525, 'loss/train': 0.4908510148525238} 08/31/2021 12:11:10 - INFO - __main__ - Step 126527: {'lr': 3.039877816839556e-05, 'samples': 24293184, 'steps': 126526, 'loss/train': 0.8097022771835327} 08/31/2021 12:11:10 - INFO - __main__ - Step 126528: {'lr': 3.039624203344918e-05, 'samples': 24293376, 'steps': 126527, 'loss/train': 0.7446460127830505} 08/31/2021 12:11:10 - INFO - __main__ - Step 126529: {'lr': 3.0393705997452863e-05, 'samples': 24293568, 'steps': 126528, 'loss/train': 1.0394344329833984} 08/31/2021 12:11:12 - INFO - __main__ - Step 126530: {'lr': 3.0391170060407814e-05, 'samples': 24293760, 'steps': 126529, 'loss/train': 1.1259737014770508} 08/31/2021 12:11:12 - INFO - __main__ - Step 126531: {'lr': 3.0388634222315054e-05, 'samples': 24293952, 'steps': 126530, 'loss/train': 0.742363452911377} 08/31/2021 12:11:13 - INFO - __main__ - Step 126532: {'lr': 3.0386098483175777e-05, 'samples': 24294144, 'steps': 126531, 'loss/train': 1.2027699947357178} 08/31/2021 12:11:13 - INFO - __main__ - Step 126533: {'lr': 3.038356284299115e-05, 'samples': 24294336, 'steps': 126532, 'loss/train': 2.0723438262939453} 08/31/2021 12:11:13 - INFO - __main__ - Step 126534: {'lr': 3.0381027301762287e-05, 'samples': 24294528, 'steps': 126533, 'loss/train': 1.555507779121399} 08/31/2021 12:11:15 - INFO - __main__ - Step 126535: {'lr': 3.0378491859490375e-05, 'samples': 24294720, 'steps': 126534, 'loss/train': 1.2973631620407104} 08/31/2021 12:11:15 - INFO - __main__ - Step 126536: {'lr': 3.03759565161765e-05, 'samples': 24294912, 'steps': 126535, 'loss/train': 0.9424852728843689} 08/31/2021 12:11:16 - INFO - __main__ - Step 126537: {'lr': 3.0373421271821828e-05, 'samples': 24295104, 'steps': 126536, 'loss/train': 0.28099310398101807} 08/31/2021 12:11:16 - INFO - __main__ - Step 126538: {'lr': 3.037088612642752e-05, 'samples': 24295296, 'steps': 126537, 'loss/train': 0.6807056069374084} 08/31/2021 12:11:16 - INFO - __main__ - Step 126539: {'lr': 3.0368351079994694e-05, 'samples': 24295488, 'steps': 126538, 'loss/train': 1.101047158241272} 08/31/2021 12:11:18 - INFO - __main__ - Step 126540: {'lr': 3.036581613252448e-05, 'samples': 24295680, 'steps': 126539, 'loss/train': 0.03839891776442528} 08/31/2021 12:11:18 - INFO - __main__ - Step 126541: {'lr': 3.0363281284018136e-05, 'samples': 24295872, 'steps': 126540, 'loss/train': 1.172528862953186} 08/31/2021 12:11:19 - INFO - __main__ - Step 126542: {'lr': 3.0360746534476626e-05, 'samples': 24296064, 'steps': 126541, 'loss/train': 1.0765794515609741} 08/31/2021 12:11:19 - INFO - __main__ - Step 126543: {'lr': 3.035821188390117e-05, 'samples': 24296256, 'steps': 126542, 'loss/train': 0.522047221660614} 08/31/2021 12:11:19 - INFO - __main__ - Step 126544: {'lr': 3.0355677332292914e-05, 'samples': 24296448, 'steps': 126543, 'loss/train': 1.1916519403457642} 08/31/2021 12:11:21 - INFO - __main__ - Step 126545: {'lr': 3.0353142879653017e-05, 'samples': 24296640, 'steps': 126544, 'loss/train': 0.48995670676231384} 08/31/2021 12:11:22 - INFO - __main__ - Step 126546: {'lr': 3.0350608525982594e-05, 'samples': 24296832, 'steps': 126545, 'loss/train': 0.7060710787773132} 08/31/2021 12:11:22 - INFO - __main__ - Step 126547: {'lr': 3.0348074271282804e-05, 'samples': 24297024, 'steps': 126546, 'loss/train': 1.193400502204895} 08/31/2021 12:11:22 - INFO - __main__ - Step 126548: {'lr': 3.034554011555479e-05, 'samples': 24297216, 'steps': 126547, 'loss/train': 0.021939465776085854} 08/31/2021 12:11:23 - INFO - __main__ - Step 126549: {'lr': 3.0343006058799666e-05, 'samples': 24297408, 'steps': 126548, 'loss/train': 1.257240891456604} 08/31/2021 12:11:24 - INFO - __main__ - Step 126550: {'lr': 3.034047210101859e-05, 'samples': 24297600, 'steps': 126549, 'loss/train': 0.5829569697380066} 08/31/2021 12:11:25 - INFO - __main__ - Step 126551: {'lr': 3.033793824221279e-05, 'samples': 24297792, 'steps': 126550, 'loss/train': 0.9925984740257263} 08/31/2021 12:11:25 - INFO - __main__ - Step 126552: {'lr': 3.0335404482383256e-05, 'samples': 24297984, 'steps': 126551, 'loss/train': 1.0441874265670776} 08/31/2021 12:11:25 - INFO - __main__ - Step 126553: {'lr': 3.0332870821531188e-05, 'samples': 24298176, 'steps': 126552, 'loss/train': 0.07238594442605972} 08/31/2021 12:11:26 - INFO - __main__ - Step 126554: {'lr': 3.0330337259657755e-05, 'samples': 24298368, 'steps': 126553, 'loss/train': 1.140491008758545} 08/31/2021 12:11:26 - INFO - __main__ - Step 126555: {'lr': 3.0327803796764086e-05, 'samples': 24298560, 'steps': 126554, 'loss/train': 0.7955000996589661} 08/31/2021 12:11:27 - INFO - __main__ - Step 126556: {'lr': 3.03252704328513e-05, 'samples': 24298752, 'steps': 126555, 'loss/train': 0.7758916616439819} 08/31/2021 12:11:28 - INFO - __main__ - Step 126557: {'lr': 3.0322737167920556e-05, 'samples': 24298944, 'steps': 126556, 'loss/train': 1.0653119087219238} 08/31/2021 12:11:28 - INFO - __main__ - Step 126558: {'lr': 3.0320204001973023e-05, 'samples': 24299136, 'steps': 126557, 'loss/train': 0.9582400918006897} 08/31/2021 12:11:29 - INFO - __main__ - Step 126559: {'lr': 3.031767093500981e-05, 'samples': 24299328, 'steps': 126558, 'loss/train': 0.789329469203949} 08/31/2021 12:11:29 - INFO - __main__ - Step 126560: {'lr': 3.031513796703206e-05, 'samples': 24299520, 'steps': 126559, 'loss/train': 1.0129350423812866} 08/31/2021 12:11:30 - INFO - __main__ - Step 126561: {'lr': 3.03126050980409e-05, 'samples': 24299712, 'steps': 126560, 'loss/train': 0.2922462522983551} 08/31/2021 12:11:31 - INFO - __main__ - Step 126562: {'lr': 3.0310072328037564e-05, 'samples': 24299904, 'steps': 126561, 'loss/train': 0.40515121817588806} 08/31/2021 12:11:31 - INFO - __main__ - Step 126563: {'lr': 3.030753965702304e-05, 'samples': 24300096, 'steps': 126562, 'loss/train': 0.6676551103591919} 08/31/2021 12:11:32 - INFO - __main__ - Step 126564: {'lr': 3.030500708499859e-05, 'samples': 24300288, 'steps': 126563, 'loss/train': 1.2064601182937622} 08/31/2021 12:11:32 - INFO - __main__ - Step 126565: {'lr': 3.030247461196528e-05, 'samples': 24300480, 'steps': 126564, 'loss/train': 0.9235922694206238} 08/31/2021 12:11:33 - INFO - __main__ - Step 126566: {'lr': 3.0299942237924317e-05, 'samples': 24300672, 'steps': 126565, 'loss/train': 1.3980177640914917} 08/31/2021 12:11:34 - INFO - __main__ - Step 126567: {'lr': 3.0297409962876775e-05, 'samples': 24300864, 'steps': 126566, 'loss/train': 0.8494446277618408} 08/31/2021 12:11:34 - INFO - __main__ - Step 126568: {'lr': 3.0294877786823854e-05, 'samples': 24301056, 'steps': 126567, 'loss/train': 0.9326618313789368} 08/31/2021 12:11:35 - INFO - __main__ - Step 126569: {'lr': 3.029234570976666e-05, 'samples': 24301248, 'steps': 126568, 'loss/train': 0.9105665683746338} 08/31/2021 12:11:35 - INFO - __main__ - Step 126570: {'lr': 3.0289813731706333e-05, 'samples': 24301440, 'steps': 126569, 'loss/train': 1.4457887411117554} 08/31/2021 12:11:37 - INFO - __main__ - Step 126571: {'lr': 3.0287281852644038e-05, 'samples': 24301632, 'steps': 126570, 'loss/train': 1.2434946298599243} 08/31/2021 12:11:37 - INFO - __main__ - Step 126572: {'lr': 3.0284750072580913e-05, 'samples': 24301824, 'steps': 126571, 'loss/train': 1.5827360153198242} 08/31/2021 12:11:37 - INFO - __main__ - Step 126573: {'lr': 3.0282218391518095e-05, 'samples': 24302016, 'steps': 126572, 'loss/train': 1.4333535432815552} 08/31/2021 12:11:38 - INFO - __main__ - Step 126574: {'lr': 3.0279686809456752e-05, 'samples': 24302208, 'steps': 126573, 'loss/train': 1.1353181600570679} 08/31/2021 12:11:38 - INFO - __main__ - Step 126575: {'lr': 3.0277155326397938e-05, 'samples': 24302400, 'steps': 126574, 'loss/train': 1.2030547857284546} 08/31/2021 12:11:40 - INFO - __main__ - Step 126576: {'lr': 3.0274623942342842e-05, 'samples': 24302592, 'steps': 126575, 'loss/train': 1.1206111907958984} 08/31/2021 12:11:41 - INFO - __main__ - Step 126577: {'lr': 3.0272092657292637e-05, 'samples': 24302784, 'steps': 126576, 'loss/train': 1.8294525146484375} 08/31/2021 12:11:41 - INFO - __main__ - Step 126578: {'lr': 3.026956147124843e-05, 'samples': 24302976, 'steps': 126577, 'loss/train': 0.9386070966720581} 08/31/2021 12:11:41 - INFO - __main__ - Step 126579: {'lr': 3.026703038421136e-05, 'samples': 24303168, 'steps': 126578, 'loss/train': 1.5675592422485352} 08/31/2021 12:11:42 - INFO - __main__ - Step 126580: {'lr': 3.026449939618256e-05, 'samples': 24303360, 'steps': 126579, 'loss/train': 1.1421613693237305} 08/31/2021 12:11:43 - INFO - __main__ - Step 126581: {'lr': 3.02619685071632e-05, 'samples': 24303552, 'steps': 126580, 'loss/train': 1.6546339988708496} 08/31/2021 12:11:44 - INFO - __main__ - Step 126582: {'lr': 3.025943771715442e-05, 'samples': 24303744, 'steps': 126581, 'loss/train': 0.8676419854164124} 08/31/2021 12:11:44 - INFO - __main__ - Step 126583: {'lr': 3.0256907026157327e-05, 'samples': 24303936, 'steps': 126582, 'loss/train': 0.8366042375564575} 08/31/2021 12:11:44 - INFO - __main__ - Step 126584: {'lr': 3.0254376434173087e-05, 'samples': 24304128, 'steps': 126583, 'loss/train': 0.9857186675071716} 08/31/2021 12:11:45 - INFO - __main__ - Step 126585: {'lr': 3.025184594120284e-05, 'samples': 24304320, 'steps': 126584, 'loss/train': 0.17976535856723785} 08/31/2021 12:11:46 - INFO - __main__ - Step 126586: {'lr': 3.0249315547247692e-05, 'samples': 24304512, 'steps': 126585, 'loss/train': 0.8892723917961121} 08/31/2021 12:11:47 - INFO - __main__ - Step 126587: {'lr': 3.0246785252308894e-05, 'samples': 24304704, 'steps': 126586, 'loss/train': 1.1469117403030396} 08/31/2021 12:11:47 - INFO - __main__ - Step 126588: {'lr': 3.024425505638745e-05, 'samples': 24304896, 'steps': 126587, 'loss/train': 0.03937893360853195} 08/31/2021 12:11:48 - INFO - __main__ - Step 126589: {'lr': 3.0241724959484544e-05, 'samples': 24305088, 'steps': 126588, 'loss/train': 1.1577268838882446} 08/31/2021 12:11:48 - INFO - __main__ - Step 126590: {'lr': 3.0239194961601323e-05, 'samples': 24305280, 'steps': 126589, 'loss/train': 1.1454017162322998} 08/31/2021 12:11:49 - INFO - __main__ - Step 126591: {'lr': 3.023666506273895e-05, 'samples': 24305472, 'steps': 126590, 'loss/train': 1.1311314105987549} 08/31/2021 12:11:50 - INFO - __main__ - Step 126592: {'lr': 3.0234135262898534e-05, 'samples': 24305664, 'steps': 126591, 'loss/train': 1.128748893737793} 08/31/2021 12:11:50 - INFO - __main__ - Step 126593: {'lr': 3.0231605562081212e-05, 'samples': 24305856, 'steps': 126592, 'loss/train': 1.2126977443695068} 08/31/2021 12:11:51 - INFO - __main__ - Step 126594: {'lr': 3.022907596028815e-05, 'samples': 24306048, 'steps': 126593, 'loss/train': 1.0873538255691528} 08/31/2021 12:11:51 - INFO - __main__ - Step 126595: {'lr': 3.022654645752046e-05, 'samples': 24306240, 'steps': 126594, 'loss/train': 1.0167373418807983} 08/31/2021 12:11:51 - INFO - __main__ - Step 126596: {'lr': 3.0224017053779308e-05, 'samples': 24306432, 'steps': 126595, 'loss/train': 0.513393759727478} 08/31/2021 12:11:53 - INFO - __main__ - Step 126597: {'lr': 3.0221487749065828e-05, 'samples': 24306624, 'steps': 126596, 'loss/train': 0.6335095763206482} 08/31/2021 12:11:54 - INFO - __main__ - Step 126598: {'lr': 3.0218958543381138e-05, 'samples': 24306816, 'steps': 126597, 'loss/train': 1.8494399785995483} 08/31/2021 12:11:54 - INFO - __main__ - Step 126599: {'lr': 3.0216429436726424e-05, 'samples': 24307008, 'steps': 126598, 'loss/train': 1.5069291591644287} 08/31/2021 12:11:55 - INFO - __main__ - Step 126600: {'lr': 3.021390042910277e-05, 'samples': 24307200, 'steps': 126599, 'loss/train': 0.8350443840026855} 08/31/2021 12:11:55 - INFO - __main__ - Step 126601: {'lr': 3.02113715205114e-05, 'samples': 24307392, 'steps': 126600, 'loss/train': 0.5412091016769409} 08/31/2021 12:11:57 - INFO - __main__ - Step 126602: {'lr': 3.020884271095334e-05, 'samples': 24307584, 'steps': 126601, 'loss/train': 0.2901706099510193} 08/31/2021 12:11:57 - INFO - __main__ - Step 126603: {'lr': 3.020631400042978e-05, 'samples': 24307776, 'steps': 126602, 'loss/train': 5.708464622497559} 08/31/2021 12:11:57 - INFO - __main__ - Step 126604: {'lr': 3.020378538894189e-05, 'samples': 24307968, 'steps': 126603, 'loss/train': 0.3112248182296753} 08/31/2021 12:11:58 - INFO - __main__ - Step 126605: {'lr': 3.0201256876490752e-05, 'samples': 24308160, 'steps': 126604, 'loss/train': 1.3088171482086182} 08/31/2021 12:11:58 - INFO - __main__ - Step 126606: {'lr': 3.019872846307753e-05, 'samples': 24308352, 'steps': 126605, 'loss/train': 0.9755785465240479} 08/31/2021 12:11:58 - INFO - __main__ - Step 126607: {'lr': 3.019620014870339e-05, 'samples': 24308544, 'steps': 126606, 'loss/train': 1.2038196325302124} 08/31/2021 12:12:00 - INFO - __main__ - Step 126608: {'lr': 3.0193671933369443e-05, 'samples': 24308736, 'steps': 126607, 'loss/train': 0.7908373475074768} 08/31/2021 12:12:00 - INFO - __main__ - Step 126609: {'lr': 3.0191143817076855e-05, 'samples': 24308928, 'steps': 126608, 'loss/train': 0.3375353515148163} 08/31/2021 12:12:01 - INFO - __main__ - Step 126610: {'lr': 3.0188615799826736e-05, 'samples': 24309120, 'steps': 126609, 'loss/train': 0.32986873388290405} 08/31/2021 12:12:01 - INFO - __main__ - Step 126611: {'lr': 3.0186087881620223e-05, 'samples': 24309312, 'steps': 126610, 'loss/train': 1.3734737634658813} 08/31/2021 12:12:01 - INFO - __main__ - Step 126612: {'lr': 3.0183560062458455e-05, 'samples': 24309504, 'steps': 126611, 'loss/train': 0.4649313688278198} 08/31/2021 12:12:03 - INFO - __main__ - Step 126613: {'lr': 3.0181032342342595e-05, 'samples': 24309696, 'steps': 126612, 'loss/train': 0.4712401330471039} 08/31/2021 12:12:03 - INFO - __main__ - Step 126614: {'lr': 3.017850472127384e-05, 'samples': 24309888, 'steps': 126613, 'loss/train': 1.3151872158050537} 08/31/2021 12:12:04 - INFO - __main__ - Step 126615: {'lr': 3.0175977199253192e-05, 'samples': 24310080, 'steps': 126614, 'loss/train': 1.4905918836593628} 08/31/2021 12:12:04 - INFO - __main__ - Step 126616: {'lr': 3.0173449776281863e-05, 'samples': 24310272, 'steps': 126615, 'loss/train': 1.6799499988555908} 08/31/2021 12:12:04 - INFO - __main__ - Step 126617: {'lr': 3.017092245236097e-05, 'samples': 24310464, 'steps': 126616, 'loss/train': 0.2226598560810089} 08/31/2021 12:12:06 - INFO - __main__ - Step 126618: {'lr': 3.016839522749168e-05, 'samples': 24310656, 'steps': 126617, 'loss/train': 0.6348881125450134} 08/31/2021 12:12:07 - INFO - __main__ - Step 126619: {'lr': 3.0165868101675126e-05, 'samples': 24310848, 'steps': 126618, 'loss/train': 1.321343183517456} 08/31/2021 12:12:07 - INFO - __main__ - Step 126620: {'lr': 3.016334107491242e-05, 'samples': 24311040, 'steps': 126619, 'loss/train': 1.0137346982955933} 08/31/2021 12:12:07 - INFO - __main__ - Step 126621: {'lr': 3.016081414720473e-05, 'samples': 24311232, 'steps': 126620, 'loss/train': 0.8158113956451416} 08/31/2021 12:12:08 - INFO - __main__ - Step 126622: {'lr': 3.015828731855319e-05, 'samples': 24311424, 'steps': 126621, 'loss/train': 0.022838737815618515} 08/31/2021 12:12:10 - INFO - __main__ - Step 126623: {'lr': 3.0155760588958912e-05, 'samples': 24311616, 'steps': 126622, 'loss/train': 1.410731554031372} 08/31/2021 12:12:10 - INFO - __main__ - Step 126624: {'lr': 3.0153233958423094e-05, 'samples': 24311808, 'steps': 126623, 'loss/train': 0.8785025477409363} 08/31/2021 12:12:11 - INFO - __main__ - Step 126625: {'lr': 3.015070742694681e-05, 'samples': 24312000, 'steps': 126624, 'loss/train': 0.9675759077072144} 08/31/2021 12:12:11 - INFO - __main__ - Step 126626: {'lr': 3.0148180994531232e-05, 'samples': 24312192, 'steps': 126625, 'loss/train': 0.06251513212919235} 08/31/2021 12:12:11 - INFO - __main__ - Step 126627: {'lr': 3.014565466117747e-05, 'samples': 24312384, 'steps': 126626, 'loss/train': 1.2297815084457397} 08/31/2021 12:12:13 - INFO - __main__ - Step 126628: {'lr': 3.0143128426886766e-05, 'samples': 24312576, 'steps': 126627, 'loss/train': 1.5382962226867676} 08/31/2021 12:12:14 - INFO - __main__ - Step 126629: {'lr': 3.01406022916601e-05, 'samples': 24312768, 'steps': 126628, 'loss/train': 0.9327265620231628} 08/31/2021 12:12:14 - INFO - __main__ - Step 126630: {'lr': 3.013807625549872e-05, 'samples': 24312960, 'steps': 126629, 'loss/train': 1.2529197931289673} 08/31/2021 12:12:15 - INFO - __main__ - Step 126631: {'lr': 3.0135550318403703e-05, 'samples': 24313152, 'steps': 126630, 'loss/train': 0.9217675924301147} 08/31/2021 12:12:15 - INFO - __main__ - Step 126632: {'lr': 3.013302448037622e-05, 'samples': 24313344, 'steps': 126631, 'loss/train': 0.10440744459629059} 08/31/2021 12:12:15 - INFO - __main__ - Step 126633: {'lr': 3.0130498741417378e-05, 'samples': 24313536, 'steps': 126632, 'loss/train': 1.2064036130905151} 08/31/2021 12:12:17 - INFO - __main__ - Step 126634: {'lr': 3.012797310152837e-05, 'samples': 24313728, 'steps': 126633, 'loss/train': 1.1481581926345825} 08/31/2021 12:12:18 - INFO - __main__ - Step 126635: {'lr': 3.0125447560710312e-05, 'samples': 24313920, 'steps': 126634, 'loss/train': 0.7017837762832642} 08/31/2021 12:12:18 - INFO - __main__ - Step 126636: {'lr': 3.0122922118964306e-05, 'samples': 24314112, 'steps': 126635, 'loss/train': 0.17624735832214355} 08/31/2021 12:12:18 - INFO - __main__ - Step 126637: {'lr': 3.0120396776291554e-05, 'samples': 24314304, 'steps': 126636, 'loss/train': 0.8641523122787476} 08/31/2021 12:12:19 - INFO - __main__ - Step 126638: {'lr': 3.011787153269313e-05, 'samples': 24314496, 'steps': 126637, 'loss/train': 2.1675925254821777} 08/31/2021 12:12:20 - INFO - __main__ - Step 126639: {'lr': 3.0115346388170207e-05, 'samples': 24314688, 'steps': 126638, 'loss/train': 1.1288824081420898} 08/31/2021 12:12:21 - INFO - __main__ - Step 126640: {'lr': 3.0112821342723918e-05, 'samples': 24314880, 'steps': 126639, 'loss/train': 0.7470429539680481} 08/31/2021 12:12:21 - INFO - __main__ - Step 126641: {'lr': 3.011029639635546e-05, 'samples': 24315072, 'steps': 126640, 'loss/train': 1.3028457164764404} 08/31/2021 12:12:22 - INFO - __main__ - Step 126642: {'lr': 3.0107771549065825e-05, 'samples': 24315264, 'steps': 126641, 'loss/train': 0.6593828201293945} 08/31/2021 12:12:22 - INFO - __main__ - Step 126643: {'lr': 3.0105246800856272e-05, 'samples': 24315456, 'steps': 126642, 'loss/train': 0.035106491297483444} 08/31/2021 12:12:23 - INFO - __main__ - Step 126644: {'lr': 3.010272215172788e-05, 'samples': 24315648, 'steps': 126643, 'loss/train': 1.0825374126434326} 08/31/2021 12:12:24 - INFO - __main__ - Step 126645: {'lr': 3.0100197601681813e-05, 'samples': 24315840, 'steps': 126644, 'loss/train': 0.775976836681366} 08/31/2021 12:12:24 - INFO - __main__ - Step 126646: {'lr': 3.0097673150719207e-05, 'samples': 24316032, 'steps': 126645, 'loss/train': 1.485134243965149} 08/31/2021 12:12:25 - INFO - __main__ - Step 126647: {'lr': 3.0095148798841205e-05, 'samples': 24316224, 'steps': 126646, 'loss/train': 1.1461808681488037} 08/31/2021 12:12:25 - INFO - __main__ - Step 126648: {'lr': 3.0092624546048913e-05, 'samples': 24316416, 'steps': 126647, 'loss/train': 1.1630854606628418} 08/31/2021 12:12:26 - INFO - __main__ - Step 126649: {'lr': 3.00901003923435e-05, 'samples': 24316608, 'steps': 126648, 'loss/train': 1.590530276298523} 08/31/2021 12:12:27 - INFO - __main__ - Step 126650: {'lr': 3.00875763377261e-05, 'samples': 24316800, 'steps': 126649, 'loss/train': 1.4758962392807007} 08/31/2021 12:12:27 - INFO - __main__ - Step 126651: {'lr': 3.0085052382197857e-05, 'samples': 24316992, 'steps': 126650, 'loss/train': 1.248497486114502} 08/31/2021 12:12:28 - INFO - __main__ - Step 126652: {'lr': 3.0082528525759878e-05, 'samples': 24317184, 'steps': 126651, 'loss/train': 1.1025058031082153} 08/31/2021 12:12:28 - INFO - __main__ - Step 126653: {'lr': 3.008000476841333e-05, 'samples': 24317376, 'steps': 126652, 'loss/train': 1.0959928035736084} 08/31/2021 12:12:30 - INFO - __main__ - Step 126654: {'lr': 3.0077481110159317e-05, 'samples': 24317568, 'steps': 126653, 'loss/train': 1.2374402284622192} 08/31/2021 12:12:30 - INFO - __main__ - Step 126655: {'lr': 3.0074957550999067e-05, 'samples': 24317760, 'steps': 126654, 'loss/train': 1.9189810752868652} 08/31/2021 12:12:30 - INFO - __main__ - Step 126656: {'lr': 3.0072434090933574e-05, 'samples': 24317952, 'steps': 126655, 'loss/train': 1.039239525794983} 08/31/2021 12:12:31 - INFO - __main__ - Step 126657: {'lr': 3.006991072996407e-05, 'samples': 24318144, 'steps': 126656, 'loss/train': 1.1019554138183594} 08/31/2021 12:12:31 - INFO - __main__ - Step 126658: {'lr': 3.0067387468091678e-05, 'samples': 24318336, 'steps': 126657, 'loss/train': 1.3006036281585693} 08/31/2021 12:12:31 - INFO - __main__ - Step 126659: {'lr': 3.0064864305317517e-05, 'samples': 24318528, 'steps': 126658, 'loss/train': 1.6737011671066284} 08/31/2021 12:12:33 - INFO - __main__ - Step 126660: {'lr': 3.0062341241642725e-05, 'samples': 24318720, 'steps': 126659, 'loss/train': 1.380990982055664} 08/31/2021 12:12:33 - INFO - __main__ - Step 126661: {'lr': 3.0059818277068467e-05, 'samples': 24318912, 'steps': 126660, 'loss/train': 0.9147193431854248} 08/31/2021 12:12:34 - INFO - __main__ - Step 126662: {'lr': 3.0057295411595854e-05, 'samples': 24319104, 'steps': 126661, 'loss/train': 1.2723195552825928} 08/31/2021 12:12:34 - INFO - __main__ - Step 126663: {'lr': 3.005477264522602e-05, 'samples': 24319296, 'steps': 126662, 'loss/train': 1.4481652975082397} 08/31/2021 12:12:34 - INFO - __main__ - Step 126664: {'lr': 3.0052249977960105e-05, 'samples': 24319488, 'steps': 126663, 'loss/train': 0.2149558961391449} 08/31/2021 12:12:36 - INFO - __main__ - Step 126665: {'lr': 3.004972740979928e-05, 'samples': 24319680, 'steps': 126664, 'loss/train': 1.1649099588394165} 08/31/2021 12:12:36 - INFO - __main__ - Step 126666: {'lr': 3.0047204940744617e-05, 'samples': 24319872, 'steps': 126665, 'loss/train': 0.96324223279953} 08/31/2021 12:12:37 - INFO - __main__ - Step 126667: {'lr': 3.0044682570797317e-05, 'samples': 24320064, 'steps': 126666, 'loss/train': 0.971881091594696} 08/31/2021 12:12:37 - INFO - __main__ - Step 126668: {'lr': 3.0042160299958543e-05, 'samples': 24320256, 'steps': 126667, 'loss/train': 1.3881409168243408} 08/31/2021 12:12:37 - INFO - __main__ - Step 126669: {'lr': 3.0039638128229323e-05, 'samples': 24320448, 'steps': 126668, 'loss/train': 0.949047863483429} 08/31/2021 12:12:39 - INFO - __main__ - Step 126670: {'lr': 3.0037116055610825e-05, 'samples': 24320640, 'steps': 126669, 'loss/train': 0.544196605682373} 08/31/2021 12:12:39 - INFO - __main__ - Step 126671: {'lr': 3.0034594082104237e-05, 'samples': 24320832, 'steps': 126670, 'loss/train': 0.9813421964645386} 08/31/2021 12:12:40 - INFO - __main__ - Step 126672: {'lr': 3.003207220771065e-05, 'samples': 24321024, 'steps': 126671, 'loss/train': 0.9247685074806213} 08/31/2021 12:12:40 - INFO - __main__ - Step 126673: {'lr': 3.002955043243122e-05, 'samples': 24321216, 'steps': 126672, 'loss/train': 1.2872732877731323} 08/31/2021 12:12:40 - INFO - __main__ - Step 126674: {'lr': 3.0027028756267088e-05, 'samples': 24321408, 'steps': 126673, 'loss/train': 0.5850187540054321} 08/31/2021 12:12:42 - INFO - __main__ - Step 126675: {'lr': 3.0024507179219367e-05, 'samples': 24321600, 'steps': 126674, 'loss/train': 0.7568371295928955} 08/31/2021 12:12:42 - INFO - __main__ - Step 126676: {'lr': 3.0021985701289223e-05, 'samples': 24321792, 'steps': 126675, 'loss/train': 2.064277410507202} 08/31/2021 12:12:43 - INFO - __main__ - Step 126677: {'lr': 3.0019464322477763e-05, 'samples': 24321984, 'steps': 126676, 'loss/train': 1.202153205871582} 08/31/2021 12:12:43 - INFO - __main__ - Step 126678: {'lr': 3.0016943042786153e-05, 'samples': 24322176, 'steps': 126677, 'loss/train': 1.1173371076583862} 08/31/2021 12:12:44 - INFO - __main__ - Step 126679: {'lr': 3.0014421862215507e-05, 'samples': 24322368, 'steps': 126678, 'loss/train': 0.1985144168138504} 08/31/2021 12:12:45 - INFO - __main__ - Step 126680: {'lr': 3.001190078076696e-05, 'samples': 24322560, 'steps': 126679, 'loss/train': 0.04244539514183998} 08/31/2021 12:12:45 - INFO - __main__ - Step 126681: {'lr': 3.0009379798441676e-05, 'samples': 24322752, 'steps': 126680, 'loss/train': 0.9981503486633301} 08/31/2021 12:12:46 - INFO - __main__ - Step 126682: {'lr': 3.0006858915240798e-05, 'samples': 24322944, 'steps': 126681, 'loss/train': 1.0810590982437134} 08/31/2021 12:12:46 - INFO - __main__ - Step 126683: {'lr': 3.0004338131165404e-05, 'samples': 24323136, 'steps': 126682, 'loss/train': 0.9093999862670898} 08/31/2021 12:12:46 - INFO - __main__ - Step 126684: {'lr': 3.0001817446216663e-05, 'samples': 24323328, 'steps': 126683, 'loss/train': 1.557750940322876} 08/31/2021 12:12:49 - INFO - __main__ - Step 126685: {'lr': 2.999929686039568e-05, 'samples': 24323520, 'steps': 126684, 'loss/train': 1.5905060768127441} 08/31/2021 12:12:49 - INFO - __main__ - Step 126686: {'lr': 2.9996776373703653e-05, 'samples': 24323712, 'steps': 126685, 'loss/train': 1.4896091222763062} 08/31/2021 12:12:49 - INFO - __main__ - Step 126687: {'lr': 2.9994255986141665e-05, 'samples': 24323904, 'steps': 126686, 'loss/train': 0.8606840968132019} 08/31/2021 12:12:50 - INFO - __main__ - Step 126688: {'lr': 2.999173569771088e-05, 'samples': 24324096, 'steps': 126687, 'loss/train': 1.1103743314743042} 08/31/2021 12:12:50 - INFO - __main__ - Step 126689: {'lr': 2.998921550841241e-05, 'samples': 24324288, 'steps': 126688, 'loss/train': 0.9398612380027771} 08/31/2021 12:12:51 - INFO - __main__ - Step 126690: {'lr': 2.998669541824742e-05, 'samples': 24324480, 'steps': 126689, 'loss/train': 0.03459569811820984} 08/31/2021 12:12:52 - INFO - __main__ - Step 126691: {'lr': 2.9984175427217013e-05, 'samples': 24324672, 'steps': 126690, 'loss/train': 0.7726894617080688} 08/31/2021 12:12:52 - INFO - __main__ - Step 126692: {'lr': 2.9981655535322337e-05, 'samples': 24324864, 'steps': 126691, 'loss/train': 0.02132337912917137} 08/31/2021 12:12:53 - INFO - __main__ - Step 126693: {'lr': 2.9979135742564557e-05, 'samples': 24325056, 'steps': 126692, 'loss/train': 0.05377115681767464} 08/31/2021 12:12:53 - INFO - __main__ - Step 126694: {'lr': 2.9976616048944776e-05, 'samples': 24325248, 'steps': 126693, 'loss/train': 0.987058699131012} 08/31/2021 12:12:53 - INFO - __main__ - Step 126695: {'lr': 2.9974096454464195e-05, 'samples': 24325440, 'steps': 126694, 'loss/train': 0.44301703572273254} 08/31/2021 12:12:55 - INFO - __main__ - Step 126696: {'lr': 2.997157695912381e-05, 'samples': 24325632, 'steps': 126695, 'loss/train': 0.8339049220085144} 08/31/2021 12:12:55 - INFO - __main__ - Step 126697: {'lr': 2.9969057562924866e-05, 'samples': 24325824, 'steps': 126696, 'loss/train': 0.7421275973320007} 08/31/2021 12:12:56 - INFO - __main__ - Step 126698: {'lr': 2.9966538265868452e-05, 'samples': 24326016, 'steps': 126697, 'loss/train': 0.8039317727088928} 08/31/2021 12:12:56 - INFO - __main__ - Step 126699: {'lr': 2.9964019067955734e-05, 'samples': 24326208, 'steps': 126698, 'loss/train': 1.3274235725402832} 08/31/2021 12:12:56 - INFO - __main__ - Step 126700: {'lr': 2.9961499969187816e-05, 'samples': 24326400, 'steps': 126699, 'loss/train': 1.3339120149612427} 08/31/2021 12:12:58 - INFO - __main__ - Step 126701: {'lr': 2.995898096956587e-05, 'samples': 24326592, 'steps': 126700, 'loss/train': 1.2498774528503418} 08/31/2021 12:12:58 - INFO - __main__ - Step 126702: {'lr': 2.9956462069091e-05, 'samples': 24326784, 'steps': 126701, 'loss/train': 1.4804686307907104} 08/31/2021 12:12:58 - INFO - __main__ - Step 126703: {'lr': 2.995394326776435e-05, 'samples': 24326976, 'steps': 126702, 'loss/train': 1.161383032798767} 08/31/2021 12:12:59 - INFO - __main__ - Step 126704: {'lr': 2.9951424565587082e-05, 'samples': 24327168, 'steps': 126703, 'loss/train': 1.1326534748077393} 08/31/2021 12:12:59 - INFO - __main__ - Step 126705: {'lr': 2.994890596256028e-05, 'samples': 24327360, 'steps': 126704, 'loss/train': 1.3492577075958252} 08/31/2021 12:13:01 - INFO - __main__ - Step 126706: {'lr': 2.994638745868511e-05, 'samples': 24327552, 'steps': 126705, 'loss/train': 1.2925190925598145} 08/31/2021 12:13:01 - INFO - __main__ - Step 126707: {'lr': 2.994386905396271e-05, 'samples': 24327744, 'steps': 126706, 'loss/train': 0.8776991367340088} 08/31/2021 12:13:01 - INFO - __main__ - Step 126708: {'lr': 2.994135074839424e-05, 'samples': 24327936, 'steps': 126707, 'loss/train': 0.5930081605911255} 08/31/2021 12:13:02 - INFO - __main__ - Step 126709: {'lr': 2.9938832541980766e-05, 'samples': 24328128, 'steps': 126708, 'loss/train': 0.6454353332519531} 08/31/2021 12:13:02 - INFO - __main__ - Step 126710: {'lr': 2.9936314434723473e-05, 'samples': 24328320, 'steps': 126709, 'loss/train': 1.3150287866592407} 08/31/2021 12:13:04 - INFO - __main__ - Step 126711: {'lr': 2.9933796426623445e-05, 'samples': 24328512, 'steps': 126710, 'loss/train': 0.616178035736084} 08/31/2021 12:13:04 - INFO - __main__ - Step 126712: {'lr': 2.9931278517681874e-05, 'samples': 24328704, 'steps': 126711, 'loss/train': 0.7612518072128296} 08/31/2021 12:13:05 - INFO - __main__ - Step 126713: {'lr': 2.9928760707899875e-05, 'samples': 24328896, 'steps': 126712, 'loss/train': 2.045429229736328} 08/31/2021 12:13:05 - INFO - __main__ - Step 126714: {'lr': 2.9926242997278584e-05, 'samples': 24329088, 'steps': 126713, 'loss/train': 0.07215698063373566} 08/31/2021 12:13:05 - INFO - __main__ - Step 126715: {'lr': 2.992372538581911e-05, 'samples': 24329280, 'steps': 126714, 'loss/train': 0.9312136173248291} 08/31/2021 12:13:07 - INFO - __main__ - Step 126716: {'lr': 2.992120787352265e-05, 'samples': 24329472, 'steps': 126715, 'loss/train': 0.5959091782569885} 08/31/2021 12:13:07 - INFO - __main__ - Step 126717: {'lr': 2.9918690460390252e-05, 'samples': 24329664, 'steps': 126716, 'loss/train': 0.9970260858535767} 08/31/2021 12:13:08 - INFO - __main__ - Step 126718: {'lr': 2.9916173146423116e-05, 'samples': 24329856, 'steps': 126717, 'loss/train': 0.7696940302848816} 08/31/2021 12:13:08 - INFO - __main__ - Step 126719: {'lr': 2.9913655931622375e-05, 'samples': 24330048, 'steps': 126718, 'loss/train': 1.568131685256958} 08/31/2021 12:13:08 - INFO - __main__ - Step 126720: {'lr': 2.9911138815989115e-05, 'samples': 24330240, 'steps': 126719, 'loss/train': 1.0676660537719727} 08/31/2021 12:13:10 - INFO - __main__ - Step 126721: {'lr': 2.99086217995245e-05, 'samples': 24330432, 'steps': 126720, 'loss/train': 1.0727367401123047} 08/31/2021 12:13:11 - INFO - __main__ - Step 126722: {'lr': 2.9906104882229723e-05, 'samples': 24330624, 'steps': 126721, 'loss/train': 0.6506007313728333} 08/31/2021 12:13:11 - INFO - __main__ - Step 126723: {'lr': 2.9903588064105815e-05, 'samples': 24330816, 'steps': 126722, 'loss/train': 1.4783506393432617} 08/31/2021 12:13:11 - INFO - __main__ - Step 126724: {'lr': 2.9901071345153964e-05, 'samples': 24331008, 'steps': 126723, 'loss/train': 0.24302329123020172} 08/31/2021 12:13:12 - INFO - __main__ - Step 126725: {'lr': 2.989855472537528e-05, 'samples': 24331200, 'steps': 126724, 'loss/train': 1.166365146636963} 08/31/2021 12:13:12 - INFO - __main__ - Step 126726: {'lr': 2.989603820477091e-05, 'samples': 24331392, 'steps': 126725, 'loss/train': 4.392709732055664} 08/31/2021 12:13:13 - INFO - __main__ - Step 126727: {'lr': 2.989352178334198e-05, 'samples': 24331584, 'steps': 126726, 'loss/train': 4.535285472869873} 08/31/2021 12:13:14 - INFO - __main__ - Step 126728: {'lr': 2.9891005461089638e-05, 'samples': 24331776, 'steps': 126727, 'loss/train': 1.1088447570800781} 08/31/2021 12:13:14 - INFO - __main__ - Step 126729: {'lr': 2.9888489238015015e-05, 'samples': 24331968, 'steps': 126728, 'loss/train': 0.6635997295379639} 08/31/2021 12:13:15 - INFO - __main__ - Step 126730: {'lr': 2.9885973114119252e-05, 'samples': 24332160, 'steps': 126729, 'loss/train': 1.2861512899398804} 08/31/2021 12:13:15 - INFO - __main__ - Step 126731: {'lr': 2.988345708940346e-05, 'samples': 24332352, 'steps': 126730, 'loss/train': 0.7531489133834839} 08/31/2021 12:13:15 - INFO - __main__ - Step 126732: {'lr': 2.9880941163868775e-05, 'samples': 24332544, 'steps': 126731, 'loss/train': 1.3401042222976685} 08/31/2021 12:13:17 - INFO - __main__ - Step 126733: {'lr': 2.987842533751636e-05, 'samples': 24332736, 'steps': 126732, 'loss/train': 1.1977431774139404} 08/31/2021 12:13:18 - INFO - __main__ - Step 126734: {'lr': 2.9875909610347335e-05, 'samples': 24332928, 'steps': 126733, 'loss/train': 0.9870639443397522} 08/31/2021 12:13:18 - INFO - __main__ - Step 126735: {'lr': 2.9873393982362858e-05, 'samples': 24333120, 'steps': 126734, 'loss/train': 1.5737959146499634} 08/31/2021 12:13:18 - INFO - __main__ - Step 126736: {'lr': 2.987087845356401e-05, 'samples': 24333312, 'steps': 126735, 'loss/train': 1.4655736684799194} 08/31/2021 12:13:19 - INFO - __main__ - Step 126737: {'lr': 2.9868363023951932e-05, 'samples': 24333504, 'steps': 126736, 'loss/train': 1.070149540901184} 08/31/2021 12:13:19 - INFO - __main__ - Step 126738: {'lr': 2.9865847693527765e-05, 'samples': 24333696, 'steps': 126737, 'loss/train': 2.1005139350891113} 08/31/2021 12:13:21 - INFO - __main__ - Step 126739: {'lr': 2.9863332462292643e-05, 'samples': 24333888, 'steps': 126738, 'loss/train': 2.60744309425354} 08/31/2021 12:13:22 - INFO - __main__ - Step 126740: {'lr': 2.986081733024773e-05, 'samples': 24334080, 'steps': 126739, 'loss/train': 0.915643036365509} 08/31/2021 12:13:22 - INFO - __main__ - Step 126741: {'lr': 2.9858302297394112e-05, 'samples': 24334272, 'steps': 126740, 'loss/train': 1.038708209991455} 08/31/2021 12:13:22 - INFO - __main__ - Step 126742: {'lr': 2.9855787363732984e-05, 'samples': 24334464, 'steps': 126741, 'loss/train': 0.7988740801811218} 08/31/2021 12:13:23 - INFO - __main__ - Step 126743: {'lr': 2.9853272529265397e-05, 'samples': 24334656, 'steps': 126742, 'loss/train': 0.8774010539054871} 08/31/2021 12:13:24 - INFO - __main__ - Step 126744: {'lr': 2.9850757793992572e-05, 'samples': 24334848, 'steps': 126743, 'loss/train': 1.0841717720031738} 08/31/2021 12:13:25 - INFO - __main__ - Step 126745: {'lr': 2.9848243157915565e-05, 'samples': 24335040, 'steps': 126744, 'loss/train': 1.4355701208114624} 08/31/2021 12:13:25 - INFO - __main__ - Step 126746: {'lr': 2.9845728621035546e-05, 'samples': 24335232, 'steps': 126745, 'loss/train': 0.31796449422836304} 08/31/2021 12:13:25 - INFO - __main__ - Step 126747: {'lr': 2.9843214183353645e-05, 'samples': 24335424, 'steps': 126746, 'loss/train': 1.3985201120376587} 08/31/2021 12:13:26 - INFO - __main__ - Step 126748: {'lr': 2.9840699844871005e-05, 'samples': 24335616, 'steps': 126747, 'loss/train': 1.3925005197525024} 08/31/2021 12:13:27 - INFO - __main__ - Step 126749: {'lr': 2.983818560558879e-05, 'samples': 24335808, 'steps': 126748, 'loss/train': 0.9643600583076477} 08/31/2021 12:13:28 - INFO - __main__ - Step 126750: {'lr': 2.9835671465508058e-05, 'samples': 24336000, 'steps': 126749, 'loss/train': 0.9487358927726746} 08/31/2021 12:13:28 - INFO - __main__ - Step 126751: {'lr': 2.983315742462997e-05, 'samples': 24336192, 'steps': 126750, 'loss/train': 0.3542172908782959} 08/31/2021 12:13:28 - INFO - __main__ - Step 126752: {'lr': 2.9830643482955638e-05, 'samples': 24336384, 'steps': 126751, 'loss/train': 1.0285279750823975} 08/31/2021 12:13:29 - INFO - __main__ - Step 126753: {'lr': 2.9828129640486256e-05, 'samples': 24336576, 'steps': 126752, 'loss/train': 0.7502598166465759} 08/31/2021 12:13:30 - INFO - __main__ - Step 126754: {'lr': 2.9825615897222908e-05, 'samples': 24336768, 'steps': 126753, 'loss/train': 0.9069353342056274} 08/31/2021 12:13:31 - INFO - __main__ - Step 126755: {'lr': 2.9823102253166728e-05, 'samples': 24336960, 'steps': 126754, 'loss/train': 0.27436932921409607} 08/31/2021 12:13:31 - INFO - __main__ - Step 126756: {'lr': 2.982058870831886e-05, 'samples': 24337152, 'steps': 126755, 'loss/train': 1.5522009134292603} 08/31/2021 12:13:31 - INFO - __main__ - Step 126757: {'lr': 2.981807526268046e-05, 'samples': 24337344, 'steps': 126756, 'loss/train': 0.9435010552406311} 08/31/2021 12:13:32 - INFO - __main__ - Step 126758: {'lr': 2.981556191625262e-05, 'samples': 24337536, 'steps': 126757, 'loss/train': 0.6940932273864746} 08/31/2021 12:13:33 - INFO - __main__ - Step 126759: {'lr': 2.9813048669036473e-05, 'samples': 24337728, 'steps': 126758, 'loss/train': 1.0226720571517944} 08/31/2021 12:13:34 - INFO - __main__ - Step 126760: {'lr': 2.9810535521033216e-05, 'samples': 24337920, 'steps': 126759, 'loss/train': 0.8800832629203796} 08/31/2021 12:13:34 - INFO - __main__ - Step 126761: {'lr': 2.98080224722439e-05, 'samples': 24338112, 'steps': 126760, 'loss/train': 1.3821624517440796} 08/31/2021 12:13:34 - INFO - __main__ - Step 126762: {'lr': 2.980550952266975e-05, 'samples': 24338304, 'steps': 126761, 'loss/train': 0.9547317028045654} 08/31/2021 12:13:35 - INFO - __main__ - Step 126763: {'lr': 2.980299667231179e-05, 'samples': 24338496, 'steps': 126762, 'loss/train': 1.0237843990325928} 08/31/2021 12:13:36 - INFO - __main__ - Step 126764: {'lr': 2.9800483921171184e-05, 'samples': 24338688, 'steps': 126763, 'loss/train': 0.998512327671051} 08/31/2021 12:13:37 - INFO - __main__ - Step 126765: {'lr': 2.9797971269249103e-05, 'samples': 24338880, 'steps': 126764, 'loss/train': 0.8649911880493164} 08/31/2021 12:13:37 - INFO - __main__ - Step 126766: {'lr': 2.9795458716546652e-05, 'samples': 24339072, 'steps': 126765, 'loss/train': 0.7881050109863281} 08/31/2021 12:13:37 - INFO - __main__ - Step 126767: {'lr': 2.9792946263064974e-05, 'samples': 24339264, 'steps': 126766, 'loss/train': 2.4044954776763916} 08/31/2021 12:13:38 - INFO - __main__ - Step 126768: {'lr': 2.9790433908805202e-05, 'samples': 24339456, 'steps': 126767, 'loss/train': 0.5393710732460022} 08/31/2021 12:13:39 - INFO - __main__ - Step 126769: {'lr': 2.9787921653768452e-05, 'samples': 24339648, 'steps': 126768, 'loss/train': 1.0061464309692383} 08/31/2021 12:13:40 - INFO - __main__ - Step 126770: {'lr': 2.9785409497955856e-05, 'samples': 24339840, 'steps': 126769, 'loss/train': 0.42040008306503296} 08/31/2021 12:13:40 - INFO - __main__ - Step 126771: {'lr': 2.9782897441368585e-05, 'samples': 24340032, 'steps': 126770, 'loss/train': 0.3590715527534485} 08/31/2021 12:13:41 - INFO - __main__ - Step 126772: {'lr': 2.9780385484007717e-05, 'samples': 24340224, 'steps': 126771, 'loss/train': 0.8360016345977783} 08/31/2021 12:13:41 - INFO - __main__ - Step 126773: {'lr': 2.9777873625874418e-05, 'samples': 24340416, 'steps': 126772, 'loss/train': 0.032544929534196854} 08/31/2021 12:13:41 - INFO - __main__ - Step 126774: {'lr': 2.9775361866969802e-05, 'samples': 24340608, 'steps': 126773, 'loss/train': 1.2974199056625366} 08/31/2021 12:13:43 - INFO - __main__ - Step 126775: {'lr': 2.977285020729503e-05, 'samples': 24340800, 'steps': 126774, 'loss/train': 0.7496685981750488} 08/31/2021 12:13:44 - INFO - __main__ - Step 126776: {'lr': 2.9770338646851248e-05, 'samples': 24340992, 'steps': 126775, 'loss/train': 0.6883405447006226} 08/31/2021 12:13:44 - INFO - __main__ - Step 126777: {'lr': 2.9767827185639502e-05, 'samples': 24341184, 'steps': 126776, 'loss/train': 1.3904786109924316} 08/31/2021 12:13:44 - INFO - __main__ - Step 126778: {'lr': 2.9765315823660986e-05, 'samples': 24341376, 'steps': 126777, 'loss/train': 1.2793045043945312} 08/31/2021 12:13:45 - INFO - __main__ - Step 126779: {'lr': 2.976280456091682e-05, 'samples': 24341568, 'steps': 126778, 'loss/train': 0.5269986391067505} 08/31/2021 12:13:46 - INFO - __main__ - Step 126780: {'lr': 2.9760293397408128e-05, 'samples': 24341760, 'steps': 126779, 'loss/train': 1.194718599319458} 08/31/2021 12:13:47 - INFO - __main__ - Step 126781: {'lr': 2.9757782333136058e-05, 'samples': 24341952, 'steps': 126780, 'loss/train': 1.41891348361969} 08/31/2021 12:13:47 - INFO - __main__ - Step 126782: {'lr': 2.9755271368101715e-05, 'samples': 24342144, 'steps': 126781, 'loss/train': 1.2520172595977783} 08/31/2021 12:13:47 - INFO - __main__ - Step 126783: {'lr': 2.9752760502306243e-05, 'samples': 24342336, 'steps': 126782, 'loss/train': 0.8862004280090332} 08/31/2021 12:13:48 - INFO - __main__ - Step 126784: {'lr': 2.97502497357508e-05, 'samples': 24342528, 'steps': 126783, 'loss/train': 0.8424531817436218} 08/31/2021 12:13:49 - INFO - __main__ - Step 126785: {'lr': 2.97477390684365e-05, 'samples': 24342720, 'steps': 126784, 'loss/train': 1.5402506589889526} 08/31/2021 12:13:50 - INFO - __main__ - Step 126786: {'lr': 2.9745228500364457e-05, 'samples': 24342912, 'steps': 126785, 'loss/train': 0.8405744433403015} 08/31/2021 12:13:50 - INFO - __main__ - Step 126787: {'lr': 2.9742718031535804e-05, 'samples': 24343104, 'steps': 126786, 'loss/train': 0.4380267858505249} 08/31/2021 12:13:51 - INFO - __main__ - Step 126788: {'lr': 2.9740207661951762e-05, 'samples': 24343296, 'steps': 126787, 'loss/train': 1.1738299131393433} 08/31/2021 12:13:51 - INFO - __main__ - Step 126789: {'lr': 2.9737697391613333e-05, 'samples': 24343488, 'steps': 126788, 'loss/train': 0.9398635029792786} 08/31/2021 12:13:53 - INFO - __main__ - Step 126790: {'lr': 2.973518722052168e-05, 'samples': 24343680, 'steps': 126789, 'loss/train': 0.9755653142929077} 08/31/2021 12:13:53 - INFO - __main__ - Step 126791: {'lr': 2.9732677148677946e-05, 'samples': 24343872, 'steps': 126790, 'loss/train': 0.38450533151626587} 08/31/2021 12:13:54 - INFO - __main__ - Step 126792: {'lr': 2.9730167176083288e-05, 'samples': 24344064, 'steps': 126791, 'loss/train': 1.7002475261688232} 08/31/2021 12:13:54 - INFO - __main__ - Step 126793: {'lr': 2.9727657302738797e-05, 'samples': 24344256, 'steps': 126792, 'loss/train': 0.12320737540721893} 08/31/2021 12:13:55 - INFO - __main__ - Step 126794: {'lr': 2.9725147528645635e-05, 'samples': 24344448, 'steps': 126793, 'loss/train': 1.1209756135940552} 08/31/2021 12:13:55 - INFO - __main__ - Step 126795: {'lr': 2.972263785380494e-05, 'samples': 24344640, 'steps': 126794, 'loss/train': 0.7459725737571716} 08/31/2021 12:13:57 - INFO - __main__ - Step 126796: {'lr': 2.9720128278217794e-05, 'samples': 24344832, 'steps': 126795, 'loss/train': 1.316280484199524} 08/31/2021 12:13:57 - INFO - __main__ - Step 126797: {'lr': 2.9717618801885394e-05, 'samples': 24345024, 'steps': 126796, 'loss/train': 0.8757609128952026} 08/31/2021 12:13:57 - INFO - __main__ - Step 126798: {'lr': 2.9715109424808874e-05, 'samples': 24345216, 'steps': 126797, 'loss/train': 1.0045760869979858} 08/31/2021 12:13:58 - INFO - __main__ - Step 126799: {'lr': 2.971260014698926e-05, 'samples': 24345408, 'steps': 126798, 'loss/train': 1.0987541675567627} 08/31/2021 12:13:58 - INFO - __main__ - Step 126800: {'lr': 2.971009096842775e-05, 'samples': 24345600, 'steps': 126799, 'loss/train': 0.7736284136772156} 08/31/2021 12:14:00 - INFO - __main__ - Step 126801: {'lr': 2.9707581889125506e-05, 'samples': 24345792, 'steps': 126800, 'loss/train': 0.6118500828742981} 08/31/2021 12:14:00 - INFO - __main__ - Step 126802: {'lr': 2.9705072909083587e-05, 'samples': 24345984, 'steps': 126801, 'loss/train': 1.534575343132019} 08/31/2021 12:14:01 - INFO - __main__ - Step 126803: {'lr': 2.970256402830318e-05, 'samples': 24346176, 'steps': 126802, 'loss/train': 1.742428183555603} 08/31/2021 12:14:01 - INFO - __main__ - Step 126804: {'lr': 2.97000552467854e-05, 'samples': 24346368, 'steps': 126803, 'loss/train': 0.9528268575668335} 08/31/2021 12:14:01 - INFO - __main__ - Step 126805: {'lr': 2.9697546564531387e-05, 'samples': 24346560, 'steps': 126804, 'loss/train': 1.5854278802871704} 08/31/2021 12:14:02 - INFO - __main__ - Step 126806: {'lr': 2.9695037981542244e-05, 'samples': 24346752, 'steps': 126805, 'loss/train': 0.9629868268966675} 08/31/2021 12:14:03 - INFO - __main__ - Step 126807: {'lr': 2.9692529497819115e-05, 'samples': 24346944, 'steps': 126806, 'loss/train': 0.47307997941970825} 08/31/2021 12:14:04 - INFO - __main__ - Step 126808: {'lr': 2.9690021113363135e-05, 'samples': 24347136, 'steps': 126807, 'loss/train': 0.6109221577644348} 08/31/2021 12:14:04 - INFO - __main__ - Step 126809: {'lr': 2.9687512828175473e-05, 'samples': 24347328, 'steps': 126808, 'loss/train': 0.8791258335113525} 08/31/2021 12:14:05 - INFO - __main__ - Step 126810: {'lr': 2.9685004642257178e-05, 'samples': 24347520, 'steps': 126809, 'loss/train': 0.8429422378540039} 08/31/2021 12:14:05 - INFO - __main__ - Step 126811: {'lr': 2.9682496555609424e-05, 'samples': 24347712, 'steps': 126810, 'loss/train': 0.8358221650123596} 08/31/2021 12:14:06 - INFO - __main__ - Step 126812: {'lr': 2.967998856823334e-05, 'samples': 24347904, 'steps': 126811, 'loss/train': 1.0168498754501343} 08/31/2021 12:14:07 - INFO - __main__ - Step 126813: {'lr': 2.9677480680130042e-05, 'samples': 24348096, 'steps': 126812, 'loss/train': 1.259710669517517} 08/31/2021 12:14:07 - INFO - __main__ - Step 126814: {'lr': 2.9674972891300695e-05, 'samples': 24348288, 'steps': 126813, 'loss/train': 1.2956724166870117} 08/31/2021 12:14:08 - INFO - __main__ - Step 126815: {'lr': 2.967246520174638e-05, 'samples': 24348480, 'steps': 126814, 'loss/train': 1.184836745262146} 08/31/2021 12:14:08 - INFO - __main__ - Step 126816: {'lr': 2.966995761146826e-05, 'samples': 24348672, 'steps': 126815, 'loss/train': 1.0517785549163818} 08/31/2021 12:14:09 - INFO - __main__ - Step 126817: {'lr': 2.9667450120467455e-05, 'samples': 24348864, 'steps': 126816, 'loss/train': 1.5696622133255005} 08/31/2021 12:14:10 - INFO - __main__ - Step 126818: {'lr': 2.9664942728745094e-05, 'samples': 24349056, 'steps': 126817, 'loss/train': 1.1704164743423462} 08/31/2021 12:14:10 - INFO - __main__ - Step 126819: {'lr': 2.9662435436302316e-05, 'samples': 24349248, 'steps': 126818, 'loss/train': 1.0348093509674072} 08/31/2021 12:14:11 - INFO - __main__ - Step 126820: {'lr': 2.965992824314029e-05, 'samples': 24349440, 'steps': 126819, 'loss/train': 1.1372228860855103} 08/31/2021 12:14:11 - INFO - __main__ - Step 126821: {'lr': 2.9657421149260066e-05, 'samples': 24349632, 'steps': 126820, 'loss/train': 0.030123203992843628} 08/31/2021 12:14:13 - INFO - __main__ - Step 126822: {'lr': 2.9654914154662786e-05, 'samples': 24349824, 'steps': 126821, 'loss/train': 0.43876737356185913} 08/31/2021 12:14:13 - INFO - __main__ - Step 126823: {'lr': 2.9652407259349616e-05, 'samples': 24350016, 'steps': 126822, 'loss/train': 1.0221301317214966} 08/31/2021 12:14:13 - INFO - __main__ - Step 126824: {'lr': 2.9649900463321668e-05, 'samples': 24350208, 'steps': 126823, 'loss/train': 0.9152700901031494} 08/31/2021 12:14:14 - INFO - __main__ - Step 126825: {'lr': 2.964739376658007e-05, 'samples': 24350400, 'steps': 126824, 'loss/train': 1.6725763082504272} 08/31/2021 12:14:14 - INFO - __main__ - Step 126826: {'lr': 2.9644887169125973e-05, 'samples': 24350592, 'steps': 126825, 'loss/train': 1.1914324760437012} 08/31/2021 12:14:16 - INFO - __main__ - Step 126827: {'lr': 2.964238067096045e-05, 'samples': 24350784, 'steps': 126826, 'loss/train': 1.5142558813095093} 08/31/2021 12:14:16 - INFO - __main__ - Step 126828: {'lr': 2.96398742720847e-05, 'samples': 24350976, 'steps': 126827, 'loss/train': 1.0903451442718506} 08/31/2021 12:14:16 - INFO - __main__ - Step 126829: {'lr': 2.963736797249983e-05, 'samples': 24351168, 'steps': 126828, 'loss/train': 0.81073397397995} 08/31/2021 12:14:17 - INFO - __main__ - Step 126830: {'lr': 2.963486177220695e-05, 'samples': 24351360, 'steps': 126829, 'loss/train': 1.1496461629867554} 08/31/2021 12:14:17 - INFO - __main__ - Step 126831: {'lr': 2.9632355671207255e-05, 'samples': 24351552, 'steps': 126830, 'loss/train': 0.7942066192626953} 08/31/2021 12:14:19 - INFO - __main__ - Step 126832: {'lr': 2.9629849669501773e-05, 'samples': 24351744, 'steps': 126831, 'loss/train': 0.9586020708084106} 08/31/2021 12:14:19 - INFO - __main__ - Step 126833: {'lr': 2.962734376709167e-05, 'samples': 24351936, 'steps': 126832, 'loss/train': 0.9571279287338257} 08/31/2021 12:14:19 - INFO - __main__ - Step 126834: {'lr': 2.962483796397808e-05, 'samples': 24352128, 'steps': 126833, 'loss/train': 0.7762262225151062} 08/31/2021 12:14:20 - INFO - __main__ - Step 126835: {'lr': 2.9622332260162145e-05, 'samples': 24352320, 'steps': 126834, 'loss/train': 1.4512617588043213} 08/31/2021 12:14:20 - INFO - __main__ - Step 126836: {'lr': 2.9619826655645e-05, 'samples': 24352512, 'steps': 126835, 'loss/train': 0.5532622933387756} 08/31/2021 12:14:21 - INFO - __main__ - Step 126837: {'lr': 2.9617321150427728e-05, 'samples': 24352704, 'steps': 126836, 'loss/train': 1.5315781831741333} 08/31/2021 12:14:22 - INFO - __main__ - Step 126838: {'lr': 2.9614815744511526e-05, 'samples': 24352896, 'steps': 126837, 'loss/train': 0.8075491189956665} 08/31/2021 12:14:22 - INFO - __main__ - Step 126839: {'lr': 2.9612310437897472e-05, 'samples': 24353088, 'steps': 126838, 'loss/train': 1.0040242671966553} 08/31/2021 12:14:23 - INFO - __main__ - Step 126840: {'lr': 2.9609805230586705e-05, 'samples': 24353280, 'steps': 126839, 'loss/train': 1.2337404489517212} 08/31/2021 12:14:23 - INFO - __main__ - Step 126841: {'lr': 2.9607300122580365e-05, 'samples': 24353472, 'steps': 126840, 'loss/train': 0.9440397024154663} 08/31/2021 12:14:25 - INFO - __main__ - Step 126842: {'lr': 2.9604795113879563e-05, 'samples': 24353664, 'steps': 126841, 'loss/train': 1.4456121921539307} 08/31/2021 12:14:25 - INFO - __main__ - Step 126843: {'lr': 2.960229020448549e-05, 'samples': 24353856, 'steps': 126842, 'loss/train': 1.4850022792816162} 08/31/2021 12:14:25 - INFO - __main__ - Step 126844: {'lr': 2.9599785394399197e-05, 'samples': 24354048, 'steps': 126843, 'loss/train': 1.0902974605560303} 08/31/2021 12:14:26 - INFO - __main__ - Step 126845: {'lr': 2.959728068362183e-05, 'samples': 24354240, 'steps': 126844, 'loss/train': 1.3056840896606445} 08/31/2021 12:14:26 - INFO - __main__ - Step 126846: {'lr': 2.9594776072154523e-05, 'samples': 24354432, 'steps': 126845, 'loss/train': 0.7013342976570129} 08/31/2021 12:14:26 - INFO - __main__ - Step 126847: {'lr': 2.9592271559998413e-05, 'samples': 24354624, 'steps': 126846, 'loss/train': 0.9922957420349121} 08/31/2021 12:14:28 - INFO - __main__ - Step 126848: {'lr': 2.9589767147154613e-05, 'samples': 24354816, 'steps': 126847, 'loss/train': 1.462178349494934} 08/31/2021 12:14:29 - INFO - __main__ - Step 126849: {'lr': 2.9587262833624256e-05, 'samples': 24355008, 'steps': 126848, 'loss/train': 1.0201873779296875} 08/31/2021 12:14:29 - INFO - __main__ - Step 126850: {'lr': 2.9584758619408513e-05, 'samples': 24355200, 'steps': 126849, 'loss/train': 1.2614881992340088} 08/31/2021 12:14:29 - INFO - __main__ - Step 126851: {'lr': 2.9582254504508436e-05, 'samples': 24355392, 'steps': 126850, 'loss/train': 0.028479725122451782} 08/31/2021 12:14:30 - INFO - __main__ - Step 126852: {'lr': 2.9579750488925223e-05, 'samples': 24355584, 'steps': 126851, 'loss/train': 0.7324482798576355} 08/31/2021 12:14:31 - INFO - __main__ - Step 126853: {'lr': 2.957724657265995e-05, 'samples': 24355776, 'steps': 126852, 'loss/train': 0.10345040261745453} 08/31/2021 12:14:32 - INFO - __main__ - Step 126854: {'lr': 2.9574742755713785e-05, 'samples': 24355968, 'steps': 126853, 'loss/train': 1.3870197534561157} 08/31/2021 12:14:32 - INFO - __main__ - Step 126855: {'lr': 2.957223903808784e-05, 'samples': 24356160, 'steps': 126854, 'loss/train': 1.6537147760391235} 08/31/2021 12:14:32 - INFO - __main__ - Step 126856: {'lr': 2.9569735419783306e-05, 'samples': 24356352, 'steps': 126855, 'loss/train': 1.5633710622787476} 08/31/2021 12:14:33 - INFO - __main__ - Step 126857: {'lr': 2.9567231900801184e-05, 'samples': 24356544, 'steps': 126856, 'loss/train': 0.18838179111480713} 08/31/2021 12:14:34 - INFO - __main__ - Step 126858: {'lr': 2.9564728481142637e-05, 'samples': 24356736, 'steps': 126857, 'loss/train': 0.9348413348197937} 08/31/2021 12:14:35 - INFO - __main__ - Step 126859: {'lr': 2.9562225160808864e-05, 'samples': 24356928, 'steps': 126858, 'loss/train': 1.3629982471466064} 08/31/2021 12:14:35 - INFO - __main__ - Step 126860: {'lr': 2.9559721939800916e-05, 'samples': 24357120, 'steps': 126859, 'loss/train': 0.8589869737625122} 08/31/2021 12:14:35 - INFO - __main__ - Step 126861: {'lr': 2.9557218818119984e-05, 'samples': 24357312, 'steps': 126860, 'loss/train': 1.1999967098236084} 08/31/2021 12:14:36 - INFO - __main__ - Step 126862: {'lr': 2.9554715795767157e-05, 'samples': 24357504, 'steps': 126861, 'loss/train': 1.3360267877578735} 08/31/2021 12:14:37 - INFO - __main__ - Step 126863: {'lr': 2.9552212872743566e-05, 'samples': 24357696, 'steps': 126862, 'loss/train': 0.7959015369415283} 08/31/2021 12:14:38 - INFO - __main__ - Step 126864: {'lr': 2.9549710049050353e-05, 'samples': 24357888, 'steps': 126863, 'loss/train': 1.514204502105713} 08/31/2021 12:14:38 - INFO - __main__ - Step 126865: {'lr': 2.9547207324688657e-05, 'samples': 24358080, 'steps': 126864, 'loss/train': 1.042284607887268} 08/31/2021 12:14:39 - INFO - __main__ - Step 126866: {'lr': 2.9544704699659558e-05, 'samples': 24358272, 'steps': 126865, 'loss/train': 1.1939449310302734} 08/31/2021 12:14:39 - INFO - __main__ - Step 126867: {'lr': 2.954220217396422e-05, 'samples': 24358464, 'steps': 126866, 'loss/train': 1.3733012676239014} 08/31/2021 12:14:40 - INFO - __main__ - Step 126868: {'lr': 2.9539699747603787e-05, 'samples': 24358656, 'steps': 126867, 'loss/train': 1.4140924215316772} 08/31/2021 12:14:41 - INFO - __main__ - Step 126869: {'lr': 2.9537197420579337e-05, 'samples': 24358848, 'steps': 126868, 'loss/train': 0.16395601630210876} 08/31/2021 12:14:41 - INFO - __main__ - Step 126870: {'lr': 2.9534695192892092e-05, 'samples': 24359040, 'steps': 126869, 'loss/train': 0.09837259352207184} 08/31/2021 12:14:42 - INFO - __main__ - Step 126871: {'lr': 2.953219306454305e-05, 'samples': 24359232, 'steps': 126870, 'loss/train': 1.1092629432678223} 08/31/2021 12:14:42 - INFO - __main__ - Step 126872: {'lr': 2.9529691035533406e-05, 'samples': 24359424, 'steps': 126871, 'loss/train': 0.7218989133834839} 08/31/2021 12:14:43 - INFO - __main__ - Step 126873: {'lr': 2.9527189105864272e-05, 'samples': 24359616, 'steps': 126872, 'loss/train': 0.6203154921531677} 08/31/2021 12:14:44 - INFO - __main__ - Step 126874: {'lr': 2.9524687275536782e-05, 'samples': 24359808, 'steps': 126873, 'loss/train': 1.320036768913269} 08/31/2021 12:14:44 - INFO - __main__ - Step 126875: {'lr': 2.9522185544552077e-05, 'samples': 24360000, 'steps': 126874, 'loss/train': 0.9598104953765869} 08/31/2021 12:14:44 - INFO - __main__ - Step 126876: {'lr': 2.9519683912911265e-05, 'samples': 24360192, 'steps': 126875, 'loss/train': 1.1367202997207642} 08/31/2021 12:14:45 - INFO - __main__ - Step 126877: {'lr': 2.9517182380615488e-05, 'samples': 24360384, 'steps': 126876, 'loss/train': 1.2427208423614502} 08/31/2021 12:14:46 - INFO - __main__ - Step 126878: {'lr': 2.951468094766585e-05, 'samples': 24360576, 'steps': 126877, 'loss/train': 0.9461178779602051} 08/31/2021 12:14:47 - INFO - __main__ - Step 126879: {'lr': 2.9512179614063522e-05, 'samples': 24360768, 'steps': 126878, 'loss/train': 0.45950037240982056} 08/31/2021 12:14:47 - INFO - __main__ - Step 126880: {'lr': 2.9509678379809583e-05, 'samples': 24360960, 'steps': 126879, 'loss/train': 1.0843260288238525} 08/31/2021 12:14:48 - INFO - __main__ - Step 126881: {'lr': 2.9507177244905202e-05, 'samples': 24361152, 'steps': 126880, 'loss/train': 0.6965442895889282} 08/31/2021 12:14:48 - INFO - __main__ - Step 126882: {'lr': 2.950467620935146e-05, 'samples': 24361344, 'steps': 126881, 'loss/train': 2.185896873474121} 08/31/2021 12:14:48 - INFO - __main__ - Step 126883: {'lr': 2.9502175273149577e-05, 'samples': 24361536, 'steps': 126882, 'loss/train': 1.0887740850448608} 08/31/2021 12:14:50 - INFO - __main__ - Step 126884: {'lr': 2.9499674436300556e-05, 'samples': 24361728, 'steps': 126883, 'loss/train': 1.1049549579620361} 08/31/2021 12:14:50 - INFO - __main__ - Step 126885: {'lr': 2.949717369880556e-05, 'samples': 24361920, 'steps': 126884, 'loss/train': 1.1120731830596924} 08/31/2021 12:14:51 - INFO - __main__ - Step 126886: {'lr': 2.949467306066575e-05, 'samples': 24362112, 'steps': 126885, 'loss/train': 0.8497724533081055} 08/31/2021 12:14:51 - INFO - __main__ - Step 126887: {'lr': 2.9492172521882242e-05, 'samples': 24362304, 'steps': 126886, 'loss/train': 0.7821617126464844} 08/31/2021 12:14:51 - INFO - __main__ - Step 126888: {'lr': 2.9489672082456147e-05, 'samples': 24362496, 'steps': 126887, 'loss/train': 0.36353230476379395} 08/31/2021 12:14:53 - INFO - __main__ - Step 126889: {'lr': 2.948717174238863e-05, 'samples': 24362688, 'steps': 126888, 'loss/train': 1.2477335929870605} 08/31/2021 12:14:54 - INFO - __main__ - Step 126890: {'lr': 2.9484671501680772e-05, 'samples': 24362880, 'steps': 126889, 'loss/train': 5.177891254425049} 08/31/2021 12:14:54 - INFO - __main__ - Step 126891: {'lr': 2.948217136033371e-05, 'samples': 24363072, 'steps': 126890, 'loss/train': 1.062410831451416} 08/31/2021 12:14:54 - INFO - __main__ - Step 126892: {'lr': 2.9479671318348584e-05, 'samples': 24363264, 'steps': 126891, 'loss/train': 1.3610914945602417} 08/31/2021 12:14:55 - INFO - __main__ - Step 126893: {'lr': 2.947717137572653e-05, 'samples': 24363456, 'steps': 126892, 'loss/train': 0.9913597702980042} 08/31/2021 12:14:55 - INFO - __main__ - Step 126894: {'lr': 2.9474671532468633e-05, 'samples': 24363648, 'steps': 126893, 'loss/train': 0.9532074332237244} 08/31/2021 12:14:56 - INFO - __main__ - Step 126895: {'lr': 2.947217178857606e-05, 'samples': 24363840, 'steps': 126894, 'loss/train': 1.4727861881256104} 08/31/2021 12:14:57 - INFO - __main__ - Step 126896: {'lr': 2.946967214404994e-05, 'samples': 24364032, 'steps': 126895, 'loss/train': 0.8086778521537781} 08/31/2021 12:14:57 - INFO - __main__ - Step 126897: {'lr': 2.9467172598891394e-05, 'samples': 24364224, 'steps': 126896, 'loss/train': 0.8190977573394775} 08/31/2021 12:14:58 - INFO - __main__ - Step 126898: {'lr': 2.946467315310153e-05, 'samples': 24364416, 'steps': 126897, 'loss/train': 1.0513311624526978} 08/31/2021 12:14:58 - INFO - __main__ - Step 126899: {'lr': 2.9462173806681453e-05, 'samples': 24364608, 'steps': 126898, 'loss/train': 0.27825912833213806} 08/31/2021 12:14:59 - INFO - __main__ - Step 126900: {'lr': 2.945967455963233e-05, 'samples': 24364800, 'steps': 126899, 'loss/train': 1.1366794109344482} 08/31/2021 12:15:00 - INFO - __main__ - Step 126901: {'lr': 2.945717541195528e-05, 'samples': 24364992, 'steps': 126900, 'loss/train': 0.7472174763679504} 08/31/2021 12:15:00 - INFO - __main__ - Step 126902: {'lr': 2.94546763636514e-05, 'samples': 24365184, 'steps': 126901, 'loss/train': 1.636419653892517} 08/31/2021 12:15:01 - INFO - __main__ - Step 126903: {'lr': 2.9452177414721865e-05, 'samples': 24365376, 'steps': 126902, 'loss/train': 0.6718434691429138} 08/31/2021 12:15:01 - INFO - __main__ - Step 126904: {'lr': 2.9449678565167752e-05, 'samples': 24365568, 'steps': 126903, 'loss/train': 0.9131006002426147} 08/31/2021 12:15:03 - INFO - __main__ - Step 126905: {'lr': 2.9447179814990234e-05, 'samples': 24365760, 'steps': 126904, 'loss/train': 1.0677199363708496} 08/31/2021 12:15:03 - INFO - __main__ - Step 126906: {'lr': 2.9444681164190385e-05, 'samples': 24365952, 'steps': 126905, 'loss/train': 1.7394770383834839} 08/31/2021 12:15:04 - INFO - __main__ - Step 126907: {'lr': 2.9442182612769375e-05, 'samples': 24366144, 'steps': 126906, 'loss/train': 1.9673726558685303} 08/31/2021 12:15:04 - INFO - __main__ - Step 126908: {'lr': 2.9439684160728315e-05, 'samples': 24366336, 'steps': 126907, 'loss/train': 1.3005741834640503} 08/31/2021 12:15:05 - INFO - __main__ - Step 126909: {'lr': 2.943718580806834e-05, 'samples': 24366528, 'steps': 126908, 'loss/train': 0.8064794540405273} 08/31/2021 12:15:05 - INFO - __main__ - Step 126910: {'lr': 2.9434687554790618e-05, 'samples': 24366720, 'steps': 126909, 'loss/train': 1.691694736480713} 08/31/2021 12:15:06 - INFO - __main__ - Step 126911: {'lr': 2.9432189400896146e-05, 'samples': 24366912, 'steps': 126910, 'loss/train': 1.174290657043457} 08/31/2021 12:15:07 - INFO - __main__ - Step 126912: {'lr': 2.942969134638615e-05, 'samples': 24367104, 'steps': 126911, 'loss/train': 0.49671363830566406} 08/31/2021 12:15:07 - INFO - __main__ - Step 126913: {'lr': 2.942719339126171e-05, 'samples': 24367296, 'steps': 126912, 'loss/train': 0.5895089507102966} 08/31/2021 12:15:08 - INFO - __main__ - Step 126914: {'lr': 2.9424695535523987e-05, 'samples': 24367488, 'steps': 126913, 'loss/train': 1.3141486644744873} 08/31/2021 12:15:08 - INFO - __main__ - Step 126915: {'lr': 2.9422197779174098e-05, 'samples': 24367680, 'steps': 126914, 'loss/train': 0.9385744333267212} 08/31/2021 12:15:09 - INFO - __main__ - Step 126916: {'lr': 2.941970012221315e-05, 'samples': 24367872, 'steps': 126915, 'loss/train': 1.2579541206359863} 08/31/2021 12:15:10 - INFO - __main__ - Step 126917: {'lr': 2.9417202564642282e-05, 'samples': 24368064, 'steps': 126916, 'loss/train': 1.0178272724151611} 08/31/2021 12:15:10 - INFO - __main__ - Step 126918: {'lr': 2.941470510646263e-05, 'samples': 24368256, 'steps': 126917, 'loss/train': 1.333056092262268} 08/31/2021 12:15:11 - INFO - __main__ - Step 126919: {'lr': 2.941220774767528e-05, 'samples': 24368448, 'steps': 126918, 'loss/train': 1.4586461782455444} 08/31/2021 12:15:11 - INFO - __main__ - Step 126920: {'lr': 2.940971048828142e-05, 'samples': 24368640, 'steps': 126919, 'loss/train': 0.8062208890914917} 08/31/2021 12:15:12 - INFO - __main__ - Step 126921: {'lr': 2.940721332828211e-05, 'samples': 24368832, 'steps': 126920, 'loss/train': 0.682733952999115} 08/31/2021 12:15:13 - INFO - __main__ - Step 126922: {'lr': 2.9404716267678543e-05, 'samples': 24369024, 'steps': 126921, 'loss/train': 0.04681452736258507} 08/31/2021 12:15:13 - INFO - __main__ - Step 126923: {'lr': 2.9402219306471773e-05, 'samples': 24369216, 'steps': 126922, 'loss/train': 1.0897154808044434} 08/31/2021 12:15:14 - INFO - __main__ - Step 126924: {'lr': 2.939972244466302e-05, 'samples': 24369408, 'steps': 126923, 'loss/train': 1.4534457921981812} 08/31/2021 12:15:14 - INFO - __main__ - Step 126925: {'lr': 2.9397225682253308e-05, 'samples': 24369600, 'steps': 126924, 'loss/train': 0.5091270804405212} 08/31/2021 12:15:15 - INFO - __main__ - Step 126926: {'lr': 2.939472901924381e-05, 'samples': 24369792, 'steps': 126925, 'loss/train': 1.0106619596481323} 08/31/2021 12:15:16 - INFO - __main__ - Step 126927: {'lr': 2.9392232455635604e-05, 'samples': 24369984, 'steps': 126926, 'loss/train': 0.20784640312194824} 08/31/2021 12:15:16 - INFO - __main__ - Step 126928: {'lr': 2.9389735991429883e-05, 'samples': 24370176, 'steps': 126927, 'loss/train': 1.3420398235321045} 08/31/2021 12:15:17 - INFO - __main__ - Step 126929: {'lr': 2.9387239626627733e-05, 'samples': 24370368, 'steps': 126928, 'loss/train': 0.4639500081539154} 08/31/2021 12:15:17 - INFO - __main__ - Step 126930: {'lr': 2.9384743361230286e-05, 'samples': 24370560, 'steps': 126929, 'loss/train': 1.549561858177185} 08/31/2021 12:15:18 - INFO - __main__ - Step 126931: {'lr': 2.938224719523869e-05, 'samples': 24370752, 'steps': 126930, 'loss/train': 1.5735541582107544} 08/31/2021 12:15:19 - INFO - __main__ - Step 126932: {'lr': 2.937975112865404e-05, 'samples': 24370944, 'steps': 126931, 'loss/train': 1.6340305805206299} 08/31/2021 12:15:19 - INFO - __main__ - Step 126933: {'lr': 2.937725516147746e-05, 'samples': 24371136, 'steps': 126932, 'loss/train': 0.7499722242355347} 08/31/2021 12:15:20 - INFO - __main__ - Step 126934: {'lr': 2.9374759293710084e-05, 'samples': 24371328, 'steps': 126933, 'loss/train': 1.1470189094543457} 08/31/2021 12:15:20 - INFO - __main__ - Step 126935: {'lr': 2.9372263525353048e-05, 'samples': 24371520, 'steps': 126934, 'loss/train': 0.3275110423564911} 08/31/2021 12:15:22 - INFO - __main__ - Step 126936: {'lr': 2.9369767856407465e-05, 'samples': 24371712, 'steps': 126935, 'loss/train': 1.2818886041641235} 08/31/2021 12:15:22 - INFO - __main__ - Step 126937: {'lr': 2.9367272286874497e-05, 'samples': 24371904, 'steps': 126936, 'loss/train': 0.8075474500656128} 08/31/2021 12:15:22 - INFO - __main__ - Step 126938: {'lr': 2.93647768167552e-05, 'samples': 24372096, 'steps': 126937, 'loss/train': 0.01984340324997902} 08/31/2021 12:15:23 - INFO - __main__ - Step 126939: {'lr': 2.9362281446050714e-05, 'samples': 24372288, 'steps': 126938, 'loss/train': 1.0126501321792603} 08/31/2021 12:15:23 - INFO - __main__ - Step 126940: {'lr': 2.9359786174762177e-05, 'samples': 24372480, 'steps': 126939, 'loss/train': 0.6496513485908508} 08/31/2021 12:15:25 - INFO - __main__ - Step 126941: {'lr': 2.9357291002890723e-05, 'samples': 24372672, 'steps': 126940, 'loss/train': 0.7076900005340576} 08/31/2021 12:15:25 - INFO - __main__ - Step 126942: {'lr': 2.9354795930437468e-05, 'samples': 24372864, 'steps': 126941, 'loss/train': 0.9602379202842712} 08/31/2021 12:15:26 - INFO - __main__ - Step 126943: {'lr': 2.9352300957403543e-05, 'samples': 24373056, 'steps': 126942, 'loss/train': 1.5029100179672241} 08/31/2021 12:15:26 - INFO - __main__ - Step 126944: {'lr': 2.9349806083790066e-05, 'samples': 24373248, 'steps': 126943, 'loss/train': 1.5641577243804932} 08/31/2021 12:15:26 - INFO - __main__ - Step 126945: {'lr': 2.934731130959814e-05, 'samples': 24373440, 'steps': 126944, 'loss/train': 1.1132469177246094} 08/31/2021 12:15:28 - INFO - __main__ - Step 126946: {'lr': 2.9344816634828935e-05, 'samples': 24373632, 'steps': 126945, 'loss/train': 1.6248921155929565} 08/31/2021 12:15:28 - INFO - __main__ - Step 126947: {'lr': 2.9342322059483562e-05, 'samples': 24373824, 'steps': 126946, 'loss/train': 1.2020446062088013} 08/31/2021 12:15:28 - INFO - __main__ - Step 126948: {'lr': 2.93398275835631e-05, 'samples': 24374016, 'steps': 126947, 'loss/train': 0.8441605567932129} 08/31/2021 12:15:29 - INFO - __main__ - Step 126949: {'lr': 2.9337333207068718e-05, 'samples': 24374208, 'steps': 126948, 'loss/train': 1.046392560005188} 08/31/2021 12:15:29 - INFO - __main__ - Step 126950: {'lr': 2.933483893000158e-05, 'samples': 24374400, 'steps': 126949, 'loss/train': 0.9179834127426147} 08/31/2021 12:15:31 - INFO - __main__ - Step 126951: {'lr': 2.933234475236271e-05, 'samples': 24374592, 'steps': 126950, 'loss/train': 0.08512169867753983} 08/31/2021 12:15:31 - INFO - __main__ - Step 126952: {'lr': 2.932985067415328e-05, 'samples': 24374784, 'steps': 126951, 'loss/train': 0.3823365569114685} 08/31/2021 12:15:31 - INFO - __main__ - Step 126953: {'lr': 2.9327356695374425e-05, 'samples': 24374976, 'steps': 126952, 'loss/train': 0.2521805763244629} 08/31/2021 12:15:32 - INFO - __main__ - Step 126954: {'lr': 2.9324862816027252e-05, 'samples': 24375168, 'steps': 126953, 'loss/train': 1.367676854133606} 08/31/2021 12:15:32 - INFO - __main__ - Step 126955: {'lr': 2.9322369036112878e-05, 'samples': 24375360, 'steps': 126954, 'loss/train': 0.2381327897310257} 08/31/2021 12:15:35 - INFO - __main__ - Step 126956: {'lr': 2.9319875355632463e-05, 'samples': 24375552, 'steps': 126955, 'loss/train': 1.2678264379501343} 08/31/2021 12:15:36 - INFO - __main__ - Step 126957: {'lr': 2.9317381774587093e-05, 'samples': 24375744, 'steps': 126956, 'loss/train': 1.094943642616272} 08/31/2021 12:15:36 - INFO - __main__ - Step 126958: {'lr': 2.9314888292977905e-05, 'samples': 24375936, 'steps': 126957, 'loss/train': 1.01229727268219} 08/31/2021 12:15:36 - INFO - __main__ - Step 126959: {'lr': 2.9312394910806005e-05, 'samples': 24376128, 'steps': 126958, 'loss/train': 0.7592513561248779} 08/31/2021 12:15:37 - INFO - __main__ - Step 126960: {'lr': 2.9309901628072567e-05, 'samples': 24376320, 'steps': 126959, 'loss/train': 0.4459931254386902} 08/31/2021 12:15:37 - INFO - __main__ - Step 126961: {'lr': 2.9307408444778666e-05, 'samples': 24376512, 'steps': 126960, 'loss/train': 1.0812662839889526} 08/31/2021 12:15:37 - INFO - __main__ - Step 126962: {'lr': 2.9304915360925444e-05, 'samples': 24376704, 'steps': 126961, 'loss/train': 0.515920877456665} 08/31/2021 12:15:39 - INFO - __main__ - Step 126963: {'lr': 2.9302422376514008e-05, 'samples': 24376896, 'steps': 126962, 'loss/train': 0.7773873209953308} 08/31/2021 12:15:39 - INFO - __main__ - Step 126964: {'lr': 2.929992949154556e-05, 'samples': 24377088, 'steps': 126963, 'loss/train': 1.6323422193527222} 08/31/2021 12:15:40 - INFO - __main__ - Step 126965: {'lr': 2.9297436706021115e-05, 'samples': 24377280, 'steps': 126964, 'loss/train': 0.9093336462974548} 08/31/2021 12:15:40 - INFO - __main__ - Step 126966: {'lr': 2.9294944019941815e-05, 'samples': 24377472, 'steps': 126965, 'loss/train': 1.076063871383667} 08/31/2021 12:15:40 - INFO - __main__ - Step 126967: {'lr': 2.9292451433308832e-05, 'samples': 24377664, 'steps': 126966, 'loss/train': 0.24501699209213257} 08/31/2021 12:15:42 - INFO - __main__ - Step 126968: {'lr': 2.928995894612324e-05, 'samples': 24377856, 'steps': 126967, 'loss/train': 1.8254132270812988} 08/31/2021 12:15:42 - INFO - __main__ - Step 126969: {'lr': 2.928746655838621e-05, 'samples': 24378048, 'steps': 126968, 'loss/train': 1.2429757118225098} 08/31/2021 12:15:43 - INFO - __main__ - Step 126970: {'lr': 2.9284974270098824e-05, 'samples': 24378240, 'steps': 126969, 'loss/train': 1.2866326570510864} 08/31/2021 12:15:43 - INFO - __main__ - Step 126971: {'lr': 2.9282482081262247e-05, 'samples': 24378432, 'steps': 126970, 'loss/train': 0.9593545794487} 08/31/2021 12:15:43 - INFO - __main__ - Step 126972: {'lr': 2.927998999187756e-05, 'samples': 24378624, 'steps': 126971, 'loss/train': 1.0875498056411743} 08/31/2021 12:15:45 - INFO - __main__ - Step 126973: {'lr': 2.9277498001945902e-05, 'samples': 24378816, 'steps': 126972, 'loss/train': 1.0222598314285278} 08/31/2021 12:15:45 - INFO - __main__ - Step 126974: {'lr': 2.927500611146841e-05, 'samples': 24379008, 'steps': 126973, 'loss/train': 1.5606918334960938} 08/31/2021 12:15:46 - INFO - __main__ - Step 126975: {'lr': 2.927251432044617e-05, 'samples': 24379200, 'steps': 126974, 'loss/train': 1.1055803298950195} 08/31/2021 12:15:46 - INFO - __main__ - Step 126976: {'lr': 2.9270022628880343e-05, 'samples': 24379392, 'steps': 126975, 'loss/train': 0.9911119937896729} 08/31/2021 12:15:47 - INFO - __main__ - Step 126977: {'lr': 2.9267531036772098e-05, 'samples': 24379584, 'steps': 126976, 'loss/train': 1.0531470775604248} 08/31/2021 12:15:47 - INFO - __main__ - Step 126978: {'lr': 2.9265039544122434e-05, 'samples': 24379776, 'steps': 126977, 'loss/train': 1.2192410230636597} 08/31/2021 12:15:49 - INFO - __main__ - Step 126979: {'lr': 2.9262548150932544e-05, 'samples': 24379968, 'steps': 126978, 'loss/train': 1.5870314836502075} 08/31/2021 12:15:49 - INFO - __main__ - Step 126980: {'lr': 2.9260056857203537e-05, 'samples': 24380160, 'steps': 126979, 'loss/train': 0.8230273723602295} 08/31/2021 12:15:50 - INFO - __main__ - Step 126981: {'lr': 2.9257565662936554e-05, 'samples': 24380352, 'steps': 126980, 'loss/train': 0.9177281856536865} 08/31/2021 12:15:50 - INFO - __main__ - Step 126982: {'lr': 2.9255074568132702e-05, 'samples': 24380544, 'steps': 126981, 'loss/train': 0.9832282662391663} 08/31/2021 12:15:50 - INFO - __main__ - Step 126983: {'lr': 2.925258357279309e-05, 'samples': 24380736, 'steps': 126982, 'loss/train': 0.6923620700836182} 08/31/2021 12:15:51 - INFO - __main__ - Step 126984: {'lr': 2.9250092676918887e-05, 'samples': 24380928, 'steps': 126983, 'loss/train': 0.12573480606079102} 08/31/2021 12:15:52 - INFO - __main__ - Step 126985: {'lr': 2.9247601880511176e-05, 'samples': 24381120, 'steps': 126984, 'loss/train': 0.12032240629196167} 08/31/2021 12:15:53 - INFO - __main__ - Step 126986: {'lr': 2.9245111183571066e-05, 'samples': 24381312, 'steps': 126985, 'loss/train': 0.12734350562095642} 08/31/2021 12:15:53 - INFO - __main__ - Step 126987: {'lr': 2.9242620586099723e-05, 'samples': 24381504, 'steps': 126986, 'loss/train': 1.1428561210632324} 08/31/2021 12:15:54 - INFO - __main__ - Step 126988: {'lr': 2.9240130088098254e-05, 'samples': 24381696, 'steps': 126987, 'loss/train': 0.8919844627380371} 08/31/2021 12:15:54 - INFO - __main__ - Step 126989: {'lr': 2.9237639689567746e-05, 'samples': 24381888, 'steps': 126988, 'loss/train': 0.7923468947410583} 08/31/2021 12:15:56 - INFO - __main__ - Step 126990: {'lr': 2.923514939050939e-05, 'samples': 24382080, 'steps': 126989, 'loss/train': 1.2578346729278564} 08/31/2021 12:15:56 - INFO - __main__ - Step 126991: {'lr': 2.92326591909243e-05, 'samples': 24382272, 'steps': 126990, 'loss/train': 0.7652275562286377} 08/31/2021 12:15:56 - INFO - __main__ - Step 126992: {'lr': 2.9230169090813525e-05, 'samples': 24382464, 'steps': 126991, 'loss/train': 0.8166741728782654} 08/31/2021 12:15:57 - INFO - __main__ - Step 126993: {'lr': 2.9227679090178205e-05, 'samples': 24382656, 'steps': 126992, 'loss/train': 1.075087308883667} 08/31/2021 12:15:57 - INFO - __main__ - Step 126994: {'lr': 2.9225189189019508e-05, 'samples': 24382848, 'steps': 126993, 'loss/train': 1.349003553390503} 08/31/2021 12:15:59 - INFO - __main__ - Step 126995: {'lr': 2.9222699387338542e-05, 'samples': 24383040, 'steps': 126994, 'loss/train': 0.7484654784202576} 08/31/2021 12:15:59 - INFO - __main__ - Step 126996: {'lr': 2.922020968513639e-05, 'samples': 24383232, 'steps': 126995, 'loss/train': 0.9076228141784668} 08/31/2021 12:16:00 - INFO - __main__ - Step 126997: {'lr': 2.9217720082414216e-05, 'samples': 24383424, 'steps': 126996, 'loss/train': 0.8728421330451965} 08/31/2021 12:16:00 - INFO - __main__ - Step 126998: {'lr': 2.9215230579173136e-05, 'samples': 24383616, 'steps': 126997, 'loss/train': 0.9966721534729004} 08/31/2021 12:16:00 - INFO - __main__ - Step 126999: {'lr': 2.921274117541428e-05, 'samples': 24383808, 'steps': 126998, 'loss/train': 0.6196162700653076} 08/31/2021 12:16:02 - INFO - __main__ - Step 127000: {'lr': 2.921025187113874e-05, 'samples': 24384000, 'steps': 126999, 'loss/train': 0.283081591129303} 08/31/2021 12:16:03 - INFO - __main__ - Step 127001: {'lr': 2.920776266634767e-05, 'samples': 24384192, 'steps': 127000, 'loss/train': 1.1450045108795166} 08/31/2021 12:16:03 - INFO - __main__ - Step 127002: {'lr': 2.9205273561042162e-05, 'samples': 24384384, 'steps': 127001, 'loss/train': 1.125765085220337} 08/31/2021 12:16:04 - INFO - __main__ - Step 127003: {'lr': 2.920278455522335e-05, 'samples': 24384576, 'steps': 127002, 'loss/train': 1.5394788980484009} 08/31/2021 12:16:04 - INFO - __main__ - Step 127004: {'lr': 2.92002956488924e-05, 'samples': 24384768, 'steps': 127003, 'loss/train': 1.4593499898910522} 08/31/2021 12:16:04 - INFO - __main__ - Step 127005: {'lr': 2.919780684205034e-05, 'samples': 24384960, 'steps': 127004, 'loss/train': 0.07693520933389664} 08/31/2021 12:16:06 - INFO - __main__ - Step 127006: {'lr': 2.919531813469836e-05, 'samples': 24385152, 'steps': 127005, 'loss/train': 0.2817646265029907} 08/31/2021 12:16:06 - INFO - __main__ - Step 127007: {'lr': 2.919282952683755e-05, 'samples': 24385344, 'steps': 127006, 'loss/train': 1.2846229076385498} 08/31/2021 12:16:07 - INFO - __main__ - Step 127008: {'lr': 2.919034101846904e-05, 'samples': 24385536, 'steps': 127007, 'loss/train': 1.0276713371276855} 08/31/2021 12:16:07 - INFO - __main__ - Step 127009: {'lr': 2.9187852609593946e-05, 'samples': 24385728, 'steps': 127008, 'loss/train': 1.1795034408569336} 08/31/2021 12:16:07 - INFO - __main__ - Step 127010: {'lr': 2.918536430021343e-05, 'samples': 24385920, 'steps': 127009, 'loss/train': 0.6349626183509827} 08/31/2021 12:16:09 - INFO - __main__ - Step 127011: {'lr': 2.9182876090328548e-05, 'samples': 24386112, 'steps': 127010, 'loss/train': 1.0735929012298584} 08/31/2021 12:16:10 - INFO - __main__ - Step 127012: {'lr': 2.9180387979940464e-05, 'samples': 24386304, 'steps': 127011, 'loss/train': 1.1932145357131958} 08/31/2021 12:16:10 - INFO - __main__ - Step 127013: {'lr': 2.917789996905029e-05, 'samples': 24386496, 'steps': 127012, 'loss/train': 2.1155683994293213} 08/31/2021 12:16:10 - INFO - __main__ - Step 127014: {'lr': 2.9175412057659167e-05, 'samples': 24386688, 'steps': 127013, 'loss/train': 0.4749632477760315} 08/31/2021 12:16:11 - INFO - __main__ - Step 127015: {'lr': 2.9172924245768174e-05, 'samples': 24386880, 'steps': 127014, 'loss/train': 1.411847472190857} 08/31/2021 12:16:12 - INFO - __main__ - Step 127016: {'lr': 2.9170436533378476e-05, 'samples': 24387072, 'steps': 127015, 'loss/train': 1.2114965915679932} 08/31/2021 12:16:13 - INFO - __main__ - Step 127017: {'lr': 2.9167948920491155e-05, 'samples': 24387264, 'steps': 127016, 'loss/train': 0.9544795155525208} 08/31/2021 12:16:13 - INFO - __main__ - Step 127018: {'lr': 2.916546140710738e-05, 'samples': 24387456, 'steps': 127017, 'loss/train': 0.9219777584075928} 08/31/2021 12:16:13 - INFO - __main__ - Step 127019: {'lr': 2.916297399322823e-05, 'samples': 24387648, 'steps': 127018, 'loss/train': 1.5357592105865479} 08/31/2021 12:16:14 - INFO - __main__ - Step 127020: {'lr': 2.916048667885479e-05, 'samples': 24387840, 'steps': 127019, 'loss/train': 0.962684690952301} 08/31/2021 12:16:15 - INFO - __main__ - Step 127021: {'lr': 2.9157999463988255e-05, 'samples': 24388032, 'steps': 127020, 'loss/train': 1.0182983875274658} 08/31/2021 12:16:16 - INFO - __main__ - Step 127022: {'lr': 2.915551234862973e-05, 'samples': 24388224, 'steps': 127021, 'loss/train': 0.9981505274772644} 08/31/2021 12:16:16 - INFO - __main__ - Step 127023: {'lr': 2.9153025332780304e-05, 'samples': 24388416, 'steps': 127022, 'loss/train': 1.3939646482467651} 08/31/2021 12:16:17 - INFO - __main__ - Step 127024: {'lr': 2.9150538416441135e-05, 'samples': 24388608, 'steps': 127023, 'loss/train': 0.5535985231399536} 08/31/2021 12:16:17 - INFO - __main__ - Step 127025: {'lr': 2.914805159961331e-05, 'samples': 24388800, 'steps': 127024, 'loss/train': 1.2444818019866943} 08/31/2021 12:16:18 - INFO - __main__ - Step 127026: {'lr': 2.914556488229797e-05, 'samples': 24388992, 'steps': 127025, 'loss/train': 1.2819818258285522} 08/31/2021 12:16:19 - INFO - __main__ - Step 127027: {'lr': 2.914307826449622e-05, 'samples': 24389184, 'steps': 127026, 'loss/train': 1.2123161554336548} 08/31/2021 12:16:19 - INFO - __main__ - Step 127028: {'lr': 2.9140591746209198e-05, 'samples': 24389376, 'steps': 127027, 'loss/train': 0.9459618926048279} 08/31/2021 12:16:19 - INFO - __main__ - Step 127029: {'lr': 2.913810532743802e-05, 'samples': 24389568, 'steps': 127028, 'loss/train': 0.6344403028488159} 08/31/2021 12:16:20 - INFO - __main__ - Step 127030: {'lr': 2.913561900818379e-05, 'samples': 24389760, 'steps': 127029, 'loss/train': 1.275793194770813} 08/31/2021 12:16:21 - INFO - __main__ - Step 127031: {'lr': 2.91331327884477e-05, 'samples': 24389952, 'steps': 127030, 'loss/train': 0.39314866065979004} 08/31/2021 12:16:22 - INFO - __main__ - Step 127032: {'lr': 2.9130646668230788e-05, 'samples': 24390144, 'steps': 127031, 'loss/train': 0.8313872218132019} 08/31/2021 12:16:22 - INFO - __main__ - Step 127033: {'lr': 2.912816064753415e-05, 'samples': 24390336, 'steps': 127032, 'loss/train': 0.48814162611961365} 08/31/2021 12:16:22 - INFO - __main__ - Step 127034: {'lr': 2.9125674726358993e-05, 'samples': 24390528, 'steps': 127033, 'loss/train': 1.1622543334960938} 08/31/2021 12:16:23 - INFO - __main__ - Step 127035: {'lr': 2.9123188904706387e-05, 'samples': 24390720, 'steps': 127034, 'loss/train': 0.8808600306510925} 08/31/2021 12:16:23 - INFO - __main__ - Step 127036: {'lr': 2.9120703182577452e-05, 'samples': 24390912, 'steps': 127035, 'loss/train': 0.9156303405761719} 08/31/2021 12:16:25 - INFO - __main__ - Step 127037: {'lr': 2.9118217559973348e-05, 'samples': 24391104, 'steps': 127036, 'loss/train': 0.6031377911567688} 08/31/2021 12:16:25 - INFO - __main__ - Step 127038: {'lr': 2.9115732036895133e-05, 'samples': 24391296, 'steps': 127037, 'loss/train': 0.9701217412948608} 08/31/2021 12:16:25 - INFO - __main__ - Step 127039: {'lr': 2.9113246613343998e-05, 'samples': 24391488, 'steps': 127038, 'loss/train': 1.3069112300872803} 08/31/2021 12:16:26 - INFO - __main__ - Step 127040: {'lr': 2.9110761289320996e-05, 'samples': 24391680, 'steps': 127039, 'loss/train': 1.1879045963287354} 08/31/2021 12:16:26 - INFO - __main__ - Step 127041: {'lr': 2.9108276064827272e-05, 'samples': 24391872, 'steps': 127040, 'loss/train': 0.5864691138267517} 08/31/2021 12:16:28 - INFO - __main__ - Step 127042: {'lr': 2.9105790939863985e-05, 'samples': 24392064, 'steps': 127041, 'loss/train': 1.3037198781967163} 08/31/2021 12:16:29 - INFO - __main__ - Step 127043: {'lr': 2.9103305914432192e-05, 'samples': 24392256, 'steps': 127042, 'loss/train': 1.122502326965332} 08/31/2021 12:16:29 - INFO - __main__ - Step 127044: {'lr': 2.9100820988533032e-05, 'samples': 24392448, 'steps': 127043, 'loss/train': 1.847256064414978} 08/31/2021 12:16:29 - INFO - __main__ - Step 127045: {'lr': 2.9098336162167698e-05, 'samples': 24392640, 'steps': 127044, 'loss/train': 0.300042986869812} 08/31/2021 12:16:30 - INFO - __main__ - Step 127046: {'lr': 2.9095851435337218e-05, 'samples': 24392832, 'steps': 127045, 'loss/train': 1.692435622215271} 08/31/2021 12:16:31 - INFO - __main__ - Step 127047: {'lr': 2.9093366808042698e-05, 'samples': 24393024, 'steps': 127046, 'loss/train': 2.57340931892395} 08/31/2021 12:16:32 - INFO - __main__ - Step 127048: {'lr': 2.9090882280285337e-05, 'samples': 24393216, 'steps': 127047, 'loss/train': 0.7802187204360962} 08/31/2021 12:16:32 - INFO - __main__ - Step 127049: {'lr': 2.9088397852066182e-05, 'samples': 24393408, 'steps': 127048, 'loss/train': 0.2733924686908722} 08/31/2021 12:16:32 - INFO - __main__ - Step 127050: {'lr': 2.908591352338641e-05, 'samples': 24393600, 'steps': 127049, 'loss/train': 1.2380577325820923} 08/31/2021 12:16:33 - INFO - __main__ - Step 127051: {'lr': 2.9083429294247092e-05, 'samples': 24393792, 'steps': 127050, 'loss/train': 0.965810239315033} 08/31/2021 12:16:34 - INFO - __main__ - Step 127052: {'lr': 2.9080945164649376e-05, 'samples': 24393984, 'steps': 127051, 'loss/train': 0.8854663968086243} 08/31/2021 12:16:35 - INFO - __main__ - Step 127053: {'lr': 2.9078461134594392e-05, 'samples': 24394176, 'steps': 127052, 'loss/train': 1.297512412071228} 08/31/2021 12:16:35 - INFO - __main__ - Step 127054: {'lr': 2.9075977204083252e-05, 'samples': 24394368, 'steps': 127053, 'loss/train': 0.5222097635269165} 08/31/2021 12:16:35 - INFO - __main__ - Step 127055: {'lr': 2.9073493373117044e-05, 'samples': 24394560, 'steps': 127054, 'loss/train': 0.6528173685073853} 08/31/2021 12:16:36 - INFO - __main__ - Step 127056: {'lr': 2.9071009641696983e-05, 'samples': 24394752, 'steps': 127055, 'loss/train': 1.235667109489441} 08/31/2021 12:16:37 - INFO - __main__ - Step 127057: {'lr': 2.9068526009824043e-05, 'samples': 24394944, 'steps': 127056, 'loss/train': 1.322479009628296} 08/31/2021 12:16:38 - INFO - __main__ - Step 127058: {'lr': 2.9066042477499416e-05, 'samples': 24395136, 'steps': 127057, 'loss/train': 1.075101613998413} 08/31/2021 12:16:38 - INFO - __main__ - Step 127059: {'lr': 2.9063559044724243e-05, 'samples': 24395328, 'steps': 127058, 'loss/train': 0.03199780359864235} 08/31/2021 12:16:39 - INFO - __main__ - Step 127060: {'lr': 2.9061075711499602e-05, 'samples': 24395520, 'steps': 127059, 'loss/train': 1.0476139783859253} 08/31/2021 12:16:39 - INFO - __main__ - Step 127061: {'lr': 2.9058592477826635e-05, 'samples': 24395712, 'steps': 127060, 'loss/train': 1.0865747928619385} 08/31/2021 12:16:39 - INFO - __main__ - Step 127062: {'lr': 2.9056109343706477e-05, 'samples': 24395904, 'steps': 127061, 'loss/train': 1.2235417366027832} 08/31/2021 12:16:42 - INFO - __main__ - Step 127063: {'lr': 2.9053626309140212e-05, 'samples': 24396096, 'steps': 127062, 'loss/train': 0.9350935220718384} 08/31/2021 12:16:42 - INFO - __main__ - Step 127064: {'lr': 2.9051143374128952e-05, 'samples': 24396288, 'steps': 127063, 'loss/train': 0.015575992874801159} 08/31/2021 12:16:42 - INFO - __main__ - Step 127065: {'lr': 2.904866053867386e-05, 'samples': 24396480, 'steps': 127064, 'loss/train': 1.2937458753585815} 08/31/2021 12:16:43 - INFO - __main__ - Step 127066: {'lr': 2.904617780277605e-05, 'samples': 24396672, 'steps': 127065, 'loss/train': 1.7321361303329468} 08/31/2021 12:16:43 - INFO - __main__ - Step 127067: {'lr': 2.9043695166436652e-05, 'samples': 24396864, 'steps': 127066, 'loss/train': 1.47464919090271} 08/31/2021 12:16:44 - INFO - __main__ - Step 127068: {'lr': 2.90412126296567e-05, 'samples': 24397056, 'steps': 127067, 'loss/train': 1.075374960899353} 08/31/2021 12:16:45 - INFO - __main__ - Step 127069: {'lr': 2.9038730192437384e-05, 'samples': 24397248, 'steps': 127068, 'loss/train': 1.5672647953033447} 08/31/2021 12:16:46 - INFO - __main__ - Step 127070: {'lr': 2.903624785477979e-05, 'samples': 24397440, 'steps': 127069, 'loss/train': 0.3057308495044708} 08/31/2021 12:16:46 - INFO - __main__ - Step 127071: {'lr': 2.9033765616685055e-05, 'samples': 24397632, 'steps': 127070, 'loss/train': 0.6051345467567444} 08/31/2021 12:16:46 - INFO - __main__ - Step 127072: {'lr': 2.9031283478154284e-05, 'samples': 24397824, 'steps': 127071, 'loss/train': 0.6404445171356201} 08/31/2021 12:16:47 - INFO - __main__ - Step 127073: {'lr': 2.9028801439188625e-05, 'samples': 24398016, 'steps': 127072, 'loss/train': 1.270448088645935} 08/31/2021 12:16:49 - INFO - __main__ - Step 127074: {'lr': 2.9026319499789177e-05, 'samples': 24398208, 'steps': 127073, 'loss/train': 1.7335301637649536} 08/31/2021 12:16:49 - INFO - __main__ - Step 127075: {'lr': 2.902383765995706e-05, 'samples': 24398400, 'steps': 127074, 'loss/train': 0.7003459930419922} 08/31/2021 12:16:49 - INFO - __main__ - Step 127076: {'lr': 2.9021355919693405e-05, 'samples': 24398592, 'steps': 127075, 'loss/train': 0.9900745749473572} 08/31/2021 12:16:50 - INFO - __main__ - Step 127077: {'lr': 2.9018874278999297e-05, 'samples': 24398784, 'steps': 127076, 'loss/train': 0.021274570375680923} 08/31/2021 12:16:50 - INFO - __main__ - Step 127078: {'lr': 2.901639273787593e-05, 'samples': 24398976, 'steps': 127077, 'loss/train': 0.3489575684070587} 08/31/2021 12:16:52 - INFO - __main__ - Step 127079: {'lr': 2.901391129632433e-05, 'samples': 24399168, 'steps': 127078, 'loss/train': 1.1928976774215698} 08/31/2021 12:16:52 - INFO - __main__ - Step 127080: {'lr': 2.9011429954345636e-05, 'samples': 24399360, 'steps': 127079, 'loss/train': 1.0019865036010742} 08/31/2021 12:16:52 - INFO - __main__ - Step 127081: {'lr': 2.9008948711940985e-05, 'samples': 24399552, 'steps': 127080, 'loss/train': 0.7765504121780396} 08/31/2021 12:16:53 - INFO - __main__ - Step 127082: {'lr': 2.900646756911149e-05, 'samples': 24399744, 'steps': 127081, 'loss/train': 0.8063684701919556} 08/31/2021 12:16:53 - INFO - __main__ - Step 127083: {'lr': 2.9003986525858254e-05, 'samples': 24399936, 'steps': 127082, 'loss/train': 0.9221667051315308} 08/31/2021 12:16:54 - INFO - __main__ - Step 127084: {'lr': 2.9001505582182425e-05, 'samples': 24400128, 'steps': 127083, 'loss/train': 1.0851072072982788} 08/31/2021 12:16:55 - INFO - __main__ - Step 127085: {'lr': 2.8999024738085107e-05, 'samples': 24400320, 'steps': 127084, 'loss/train': 1.489195704460144} 08/31/2021 12:16:55 - INFO - __main__ - Step 127086: {'lr': 2.899654399356744e-05, 'samples': 24400512, 'steps': 127085, 'loss/train': 0.7808653712272644} 08/31/2021 12:16:56 - INFO - __main__ - Step 127087: {'lr': 2.89940633486305e-05, 'samples': 24400704, 'steps': 127086, 'loss/train': 0.64222252368927} 08/31/2021 12:16:56 - INFO - __main__ - Step 127088: {'lr': 2.8991582803275435e-05, 'samples': 24400896, 'steps': 127087, 'loss/train': 1.425873041152954} 08/31/2021 12:16:58 - INFO - __main__ - Step 127089: {'lr': 2.8989102357503376e-05, 'samples': 24401088, 'steps': 127088, 'loss/train': 1.3665138483047485} 08/31/2021 12:16:58 - INFO - __main__ - Step 127090: {'lr': 2.8986622011315382e-05, 'samples': 24401280, 'steps': 127089, 'loss/train': 1.1563334465026855} 08/31/2021 12:16:58 - INFO - __main__ - Step 127091: {'lr': 2.898414176471262e-05, 'samples': 24401472, 'steps': 127090, 'loss/train': 0.018488915637135506} 08/31/2021 12:16:59 - INFO - __main__ - Step 127092: {'lr': 2.8981661617696192e-05, 'samples': 24401664, 'steps': 127091, 'loss/train': 3.626390218734741} 08/31/2021 12:16:59 - INFO - __main__ - Step 127093: {'lr': 2.8979181570267188e-05, 'samples': 24401856, 'steps': 127092, 'loss/train': 1.3471099138259888} 08/31/2021 12:16:59 - INFO - __main__ - Step 127094: {'lr': 2.897670162242677e-05, 'samples': 24402048, 'steps': 127093, 'loss/train': 1.484773874282837} 08/31/2021 12:17:01 - INFO - __main__ - Step 127095: {'lr': 2.897422177417605e-05, 'samples': 24402240, 'steps': 127094, 'loss/train': 0.9732048511505127} 08/31/2021 12:17:02 - INFO - __main__ - Step 127096: {'lr': 2.897174202551614e-05, 'samples': 24402432, 'steps': 127095, 'loss/train': 1.0220870971679688} 08/31/2021 12:17:02 - INFO - __main__ - Step 127097: {'lr': 2.896926237644812e-05, 'samples': 24402624, 'steps': 127096, 'loss/train': 1.2135120630264282} 08/31/2021 12:17:02 - INFO - __main__ - Step 127098: {'lr': 2.896678282697318e-05, 'samples': 24402816, 'steps': 127097, 'loss/train': 1.747521162033081} 08/31/2021 12:17:03 - INFO - __main__ - Step 127099: {'lr': 2.8964303377092354e-05, 'samples': 24403008, 'steps': 127098, 'loss/train': 1.2313302755355835} 08/31/2021 12:17:04 - INFO - __main__ - Step 127100: {'lr': 2.896182402680689e-05, 'samples': 24403200, 'steps': 127099, 'loss/train': 1.6005654335021973} 08/31/2021 12:17:05 - INFO - __main__ - Step 127101: {'lr': 2.8959344776117752e-05, 'samples': 24403392, 'steps': 127100, 'loss/train': 1.168081521987915} 08/31/2021 12:17:05 - INFO - __main__ - Step 127102: {'lr': 2.8956865625026115e-05, 'samples': 24403584, 'steps': 127101, 'loss/train': 0.8004124760627747} 08/31/2021 12:17:05 - INFO - __main__ - Step 127103: {'lr': 2.895438657353311e-05, 'samples': 24403776, 'steps': 127102, 'loss/train': 0.6674171686172485} 08/31/2021 12:17:06 - INFO - __main__ - Step 127104: {'lr': 2.895190762163985e-05, 'samples': 24403968, 'steps': 127103, 'loss/train': 0.40212762355804443} 08/31/2021 12:17:07 - INFO - __main__ - Step 127105: {'lr': 2.8949428769347447e-05, 'samples': 24404160, 'steps': 127104, 'loss/train': 0.4651987850666046} 08/31/2021 12:17:08 - INFO - __main__ - Step 127106: {'lr': 2.8946950016657037e-05, 'samples': 24404352, 'steps': 127105, 'loss/train': 1.0624504089355469} 08/31/2021 12:17:08 - INFO - __main__ - Step 127107: {'lr': 2.8944471363569703e-05, 'samples': 24404544, 'steps': 127106, 'loss/train': 0.7102231383323669} 08/31/2021 12:17:08 - INFO - __main__ - Step 127108: {'lr': 2.8941992810086583e-05, 'samples': 24404736, 'steps': 127107, 'loss/train': 0.6479968428611755} 08/31/2021 12:17:09 - INFO - __main__ - Step 127109: {'lr': 2.8939514356208784e-05, 'samples': 24404928, 'steps': 127108, 'loss/train': 1.4954700469970703} 08/31/2021 12:17:10 - INFO - __main__ - Step 127110: {'lr': 2.893703600193742e-05, 'samples': 24405120, 'steps': 127109, 'loss/train': 1.2045553922653198} 08/31/2021 12:17:11 - INFO - __main__ - Step 127111: {'lr': 2.8934557747273633e-05, 'samples': 24405312, 'steps': 127110, 'loss/train': 1.365433931350708} 08/31/2021 12:17:11 - INFO - __main__ - Step 127112: {'lr': 2.893207959221855e-05, 'samples': 24405504, 'steps': 127111, 'loss/train': 1.4973480701446533} 08/31/2021 12:17:12 - INFO - __main__ - Step 127113: {'lr': 2.8929601536773237e-05, 'samples': 24405696, 'steps': 127112, 'loss/train': 1.0748835802078247} 08/31/2021 12:17:12 - INFO - __main__ - Step 127114: {'lr': 2.8927123580938823e-05, 'samples': 24405888, 'steps': 127113, 'loss/train': 1.0483074188232422} 08/31/2021 12:17:14 - INFO - __main__ - Step 127115: {'lr': 2.8924645724716454e-05, 'samples': 24406080, 'steps': 127114, 'loss/train': 0.34381040930747986} 08/31/2021 12:17:14 - INFO - __main__ - Step 127116: {'lr': 2.8922167968107205e-05, 'samples': 24406272, 'steps': 127115, 'loss/train': 0.9274441003799438} 08/31/2021 12:17:15 - INFO - __main__ - Step 127117: {'lr': 2.8919690311112216e-05, 'samples': 24406464, 'steps': 127116, 'loss/train': 0.8314812183380127} 08/31/2021 12:17:15 - INFO - __main__ - Step 127118: {'lr': 2.8917212753732632e-05, 'samples': 24406656, 'steps': 127117, 'loss/train': 1.2325955629348755} 08/31/2021 12:17:15 - INFO - __main__ - Step 127119: {'lr': 2.8914735295969495e-05, 'samples': 24406848, 'steps': 127118, 'loss/train': 1.611397624015808} 08/31/2021 12:17:16 - INFO - __main__ - Step 127120: {'lr': 2.891225793782401e-05, 'samples': 24407040, 'steps': 127119, 'loss/train': 1.8461869955062866} 08/31/2021 12:17:18 - INFO - __main__ - Step 127121: {'lr': 2.8909780679297226e-05, 'samples': 24407232, 'steps': 127120, 'loss/train': 1.6717784404754639} 08/31/2021 12:17:18 - INFO - __main__ - Step 127122: {'lr': 2.8907303520390282e-05, 'samples': 24407424, 'steps': 127121, 'loss/train': 1.2757387161254883} 08/31/2021 12:17:19 - INFO - __main__ - Step 127123: {'lr': 2.8904826461104315e-05, 'samples': 24407616, 'steps': 127122, 'loss/train': 0.9571276903152466} 08/31/2021 12:17:19 - INFO - __main__ - Step 127124: {'lr': 2.890234950144041e-05, 'samples': 24407808, 'steps': 127123, 'loss/train': 1.0850719213485718} 08/31/2021 12:17:19 - INFO - __main__ - Step 127125: {'lr': 2.8899872641399732e-05, 'samples': 24408000, 'steps': 127124, 'loss/train': 1.1704518795013428} 08/31/2021 12:17:21 - INFO - __main__ - Step 127126: {'lr': 2.8897395880983334e-05, 'samples': 24408192, 'steps': 127125, 'loss/train': 1.9372072219848633} 08/31/2021 12:17:21 - INFO - __main__ - Step 127127: {'lr': 2.889491922019233e-05, 'samples': 24408384, 'steps': 127126, 'loss/train': 0.340789258480072} 08/31/2021 12:17:22 - INFO - __main__ - Step 127128: {'lr': 2.889244265902788e-05, 'samples': 24408576, 'steps': 127127, 'loss/train': 1.3891857862472534} 08/31/2021 12:17:22 - INFO - __main__ - Step 127129: {'lr': 2.8889966197491068e-05, 'samples': 24408768, 'steps': 127128, 'loss/train': 1.0403767824172974} 08/31/2021 12:17:22 - INFO - __main__ - Step 127130: {'lr': 2.8887489835583065e-05, 'samples': 24408960, 'steps': 127129, 'loss/train': 1.224873423576355} 08/31/2021 12:17:24 - INFO - __main__ - Step 127131: {'lr': 2.888501357330492e-05, 'samples': 24409152, 'steps': 127130, 'loss/train': 0.789702296257019} 08/31/2021 12:17:25 - INFO - __main__ - Step 127132: {'lr': 2.8882537410657773e-05, 'samples': 24409344, 'steps': 127131, 'loss/train': 1.448828935623169} 08/31/2021 12:17:25 - INFO - __main__ - Step 127133: {'lr': 2.8880061347642733e-05, 'samples': 24409536, 'steps': 127132, 'loss/train': 0.7968491315841675} 08/31/2021 12:17:25 - INFO - __main__ - Step 127134: {'lr': 2.887758538426094e-05, 'samples': 24409728, 'steps': 127133, 'loss/train': 1.1877731084823608} 08/31/2021 12:17:26 - INFO - __main__ - Step 127135: {'lr': 2.8875109520513505e-05, 'samples': 24409920, 'steps': 127134, 'loss/train': 0.06296803802251816} 08/31/2021 12:17:26 - INFO - __main__ - Step 127136: {'lr': 2.8872633756401505e-05, 'samples': 24410112, 'steps': 127135, 'loss/train': 5.237190246582031} 08/31/2021 12:17:28 - INFO - __main__ - Step 127137: {'lr': 2.8870158091926113e-05, 'samples': 24410304, 'steps': 127136, 'loss/train': 1.35642409324646} 08/31/2021 12:17:28 - INFO - __main__ - Step 127138: {'lr': 2.8867682527088405e-05, 'samples': 24410496, 'steps': 127137, 'loss/train': 0.9091556072235107} 08/31/2021 12:17:29 - INFO - __main__ - Step 127139: {'lr': 2.8865207061889555e-05, 'samples': 24410688, 'steps': 127138, 'loss/train': 1.2742879390716553} 08/31/2021 12:17:29 - INFO - __main__ - Step 127140: {'lr': 2.886273169633058e-05, 'samples': 24410880, 'steps': 127139, 'loss/train': 1.132509469985962} 08/31/2021 12:17:29 - INFO - __main__ - Step 127141: {'lr': 2.8860256430412652e-05, 'samples': 24411072, 'steps': 127140, 'loss/train': 0.6419981122016907} 08/31/2021 12:17:31 - INFO - __main__ - Step 127142: {'lr': 2.885778126413685e-05, 'samples': 24411264, 'steps': 127141, 'loss/train': 1.3355789184570312} 08/31/2021 12:17:31 - INFO - __main__ - Step 127143: {'lr': 2.8855306197504344e-05, 'samples': 24411456, 'steps': 127142, 'loss/train': 0.19429385662078857} 08/31/2021 12:17:32 - INFO - __main__ - Step 127144: {'lr': 2.885283123051624e-05, 'samples': 24411648, 'steps': 127143, 'loss/train': 1.1149591207504272} 08/31/2021 12:17:32 - INFO - __main__ - Step 127145: {'lr': 2.8850356363173623e-05, 'samples': 24411840, 'steps': 127144, 'loss/train': 1.4268733263015747} 08/31/2021 12:17:32 - INFO - __main__ - Step 127146: {'lr': 2.8847881595477603e-05, 'samples': 24412032, 'steps': 127145, 'loss/train': 1.0668566226959229} 08/31/2021 12:17:34 - INFO - __main__ - Step 127147: {'lr': 2.8845406927429347e-05, 'samples': 24412224, 'steps': 127146, 'loss/train': 1.7556169033050537} 08/31/2021 12:17:35 - INFO - __main__ - Step 127148: {'lr': 2.8842932359029933e-05, 'samples': 24412416, 'steps': 127147, 'loss/train': 1.7559070587158203} 08/31/2021 12:17:35 - INFO - __main__ - Step 127149: {'lr': 2.8840457890280446e-05, 'samples': 24412608, 'steps': 127148, 'loss/train': 1.4354345798492432} 08/31/2021 12:17:35 - INFO - __main__ - Step 127150: {'lr': 2.883798352118208e-05, 'samples': 24412800, 'steps': 127149, 'loss/train': 1.6811286211013794} 08/31/2021 12:17:36 - INFO - __main__ - Step 127151: {'lr': 2.883550925173589e-05, 'samples': 24412992, 'steps': 127150, 'loss/train': 1.2425071001052856} 08/31/2021 12:17:36 - INFO - __main__ - Step 127152: {'lr': 2.8833035081943044e-05, 'samples': 24413184, 'steps': 127151, 'loss/train': 0.22558633983135223} 08/31/2021 12:17:37 - INFO - __main__ - Step 127153: {'lr': 2.883056101180459e-05, 'samples': 24413376, 'steps': 127152, 'loss/train': 0.07001151144504547} 08/31/2021 12:17:38 - INFO - __main__ - Step 127154: {'lr': 2.8828087041321673e-05, 'samples': 24413568, 'steps': 127153, 'loss/train': 1.2238205671310425} 08/31/2021 12:17:38 - INFO - __main__ - Step 127155: {'lr': 2.8825613170495396e-05, 'samples': 24413760, 'steps': 127154, 'loss/train': 0.7591708302497864} 08/31/2021 12:17:39 - INFO - __main__ - Step 127156: {'lr': 2.8823139399326875e-05, 'samples': 24413952, 'steps': 127155, 'loss/train': 0.7139841914176941} 08/31/2021 12:17:39 - INFO - __main__ - Step 127157: {'lr': 2.8820665727817245e-05, 'samples': 24414144, 'steps': 127156, 'loss/train': 0.265872061252594} 08/31/2021 12:17:40 - INFO - __main__ - Step 127158: {'lr': 2.8818192155967622e-05, 'samples': 24414336, 'steps': 127157, 'loss/train': 1.0367982387542725} 08/31/2021 12:17:41 - INFO - __main__ - Step 127159: {'lr': 2.8815718683779078e-05, 'samples': 24414528, 'steps': 127158, 'loss/train': 1.3945449590682983} 08/31/2021 12:17:41 - INFO - __main__ - Step 127160: {'lr': 2.881324531125279e-05, 'samples': 24414720, 'steps': 127159, 'loss/train': 4.857459545135498} 08/31/2021 12:17:42 - INFO - __main__ - Step 127161: {'lr': 2.8810772038389832e-05, 'samples': 24414912, 'steps': 127160, 'loss/train': 0.5351719856262207} 08/31/2021 12:17:42 - INFO - __main__ - Step 127162: {'lr': 2.880829886519132e-05, 'samples': 24415104, 'steps': 127161, 'loss/train': 1.746351957321167} 08/31/2021 12:17:42 - INFO - __main__ - Step 127163: {'lr': 2.8805825791658385e-05, 'samples': 24415296, 'steps': 127162, 'loss/train': 0.9542415738105774} 08/31/2021 12:17:44 - INFO - __main__ - Step 127164: {'lr': 2.8803352817792118e-05, 'samples': 24415488, 'steps': 127163, 'loss/train': 0.4161917567253113} 08/31/2021 12:17:44 - INFO - __main__ - Step 127165: {'lr': 2.880087994359365e-05, 'samples': 24415680, 'steps': 127164, 'loss/train': 1.4609960317611694} 08/31/2021 12:17:45 - INFO - __main__ - Step 127166: {'lr': 2.879840716906415e-05, 'samples': 24415872, 'steps': 127165, 'loss/train': 1.1550955772399902} 08/31/2021 12:17:45 - INFO - __main__ - Step 127167: {'lr': 2.879593449420462e-05, 'samples': 24416064, 'steps': 127166, 'loss/train': 0.9912044405937195} 08/31/2021 12:17:45 - INFO - __main__ - Step 127168: {'lr': 2.8793461919016217e-05, 'samples': 24416256, 'steps': 127167, 'loss/train': 1.0018572807312012} 08/31/2021 12:17:47 - INFO - __main__ - Step 127169: {'lr': 2.8790989443500087e-05, 'samples': 24416448, 'steps': 127168, 'loss/train': 1.5141206979751587} 08/31/2021 12:17:47 - INFO - __main__ - Step 127170: {'lr': 2.878851706765731e-05, 'samples': 24416640, 'steps': 127169, 'loss/train': 0.9301643967628479} 08/31/2021 12:17:48 - INFO - __main__ - Step 127171: {'lr': 2.8786044791489025e-05, 'samples': 24416832, 'steps': 127170, 'loss/train': 0.9372004270553589} 08/31/2021 12:17:48 - INFO - __main__ - Step 127172: {'lr': 2.878357261499631e-05, 'samples': 24417024, 'steps': 127171, 'loss/train': 1.2372629642486572} 08/31/2021 12:17:48 - INFO - __main__ - Step 127173: {'lr': 2.8781100538180338e-05, 'samples': 24417216, 'steps': 127172, 'loss/train': 1.3998730182647705} 08/31/2021 12:17:50 - INFO - __main__ - Step 127174: {'lr': 2.877862856104216e-05, 'samples': 24417408, 'steps': 127173, 'loss/train': 1.220428705215454} 08/31/2021 12:17:51 - INFO - __main__ - Step 127175: {'lr': 2.8776156683582938e-05, 'samples': 24417600, 'steps': 127174, 'loss/train': 0.9948217868804932} 08/31/2021 12:17:51 - INFO - __main__ - Step 127176: {'lr': 2.877368490580376e-05, 'samples': 24417792, 'steps': 127175, 'loss/train': 0.4585324227809906} 08/31/2021 12:17:52 - INFO - __main__ - Step 127177: {'lr': 2.8771213227705735e-05, 'samples': 24417984, 'steps': 127176, 'loss/train': 0.7853823304176331} 08/31/2021 12:17:52 - INFO - __main__ - Step 127178: {'lr': 2.876874164929e-05, 'samples': 24418176, 'steps': 127177, 'loss/train': 1.012842059135437} 08/31/2021 12:17:54 - INFO - __main__ - Step 127179: {'lr': 2.8766270170557718e-05, 'samples': 24418368, 'steps': 127178, 'loss/train': 0.6917595863342285} 08/31/2021 12:17:54 - INFO - __main__ - Step 127180: {'lr': 2.8763798791509865e-05, 'samples': 24418560, 'steps': 127179, 'loss/train': 0.6288398504257202} 08/31/2021 12:17:54 - INFO - __main__ - Step 127181: {'lr': 2.8761327512147662e-05, 'samples': 24418752, 'steps': 127180, 'loss/train': 0.8213021159172058} 08/31/2021 12:17:55 - INFO - __main__ - Step 127182: {'lr': 2.875885633247216e-05, 'samples': 24418944, 'steps': 127181, 'loss/train': 0.684292197227478} 08/31/2021 12:17:55 - INFO - __main__ - Step 127183: {'lr': 2.8756385252484503e-05, 'samples': 24419136, 'steps': 127182, 'loss/train': 0.7455624341964722} 08/31/2021 12:17:55 - INFO - __main__ - Step 127184: {'lr': 2.8753914272185822e-05, 'samples': 24419328, 'steps': 127183, 'loss/train': 1.6312648057937622} 08/31/2021 12:17:57 - INFO - __main__ - Step 127185: {'lr': 2.8751443391577204e-05, 'samples': 24419520, 'steps': 127184, 'loss/train': 1.495376467704773} 08/31/2021 12:17:57 - INFO - __main__ - Step 127186: {'lr': 2.8748972610659786e-05, 'samples': 24419712, 'steps': 127185, 'loss/train': 0.560723602771759} 08/31/2021 12:17:58 - INFO - __main__ - Step 127187: {'lr': 2.874650192943465e-05, 'samples': 24419904, 'steps': 127186, 'loss/train': 0.6399481296539307} 08/31/2021 12:17:58 - INFO - __main__ - Step 127188: {'lr': 2.8744031347902933e-05, 'samples': 24420096, 'steps': 127187, 'loss/train': 1.022985577583313} 08/31/2021 12:17:59 - INFO - __main__ - Step 127189: {'lr': 2.8741560866065747e-05, 'samples': 24420288, 'steps': 127188, 'loss/train': 0.8572661876678467} 08/31/2021 12:18:00 - INFO - __main__ - Step 127190: {'lr': 2.8739090483924173e-05, 'samples': 24420480, 'steps': 127189, 'loss/train': 1.4588589668273926} 08/31/2021 12:18:01 - INFO - __main__ - Step 127191: {'lr': 2.873662020147938e-05, 'samples': 24420672, 'steps': 127190, 'loss/train': 1.1152206659317017} 08/31/2021 12:18:01 - INFO - __main__ - Step 127192: {'lr': 2.8734150018732503e-05, 'samples': 24420864, 'steps': 127191, 'loss/train': 1.2643027305603027} 08/31/2021 12:18:01 - INFO - __main__ - Step 127193: {'lr': 2.873167993568454e-05, 'samples': 24421056, 'steps': 127192, 'loss/train': 0.47167977690696716} 08/31/2021 12:18:02 - INFO - __main__ - Step 127194: {'lr': 2.872920995233666e-05, 'samples': 24421248, 'steps': 127193, 'loss/train': 1.1835283041000366} 08/31/2021 12:18:03 - INFO - __main__ - Step 127195: {'lr': 2.8726740068689998e-05, 'samples': 24421440, 'steps': 127194, 'loss/train': 0.994583010673523} 08/31/2021 12:18:04 - INFO - __main__ - Step 127196: {'lr': 2.872427028474564e-05, 'samples': 24421632, 'steps': 127195, 'loss/train': 0.5458894968032837} 08/31/2021 12:18:04 - INFO - __main__ - Step 127197: {'lr': 2.8721800600504723e-05, 'samples': 24421824, 'steps': 127196, 'loss/train': 0.4155597984790802} 08/31/2021 12:18:04 - INFO - __main__ - Step 127198: {'lr': 2.8719331015968353e-05, 'samples': 24422016, 'steps': 127197, 'loss/train': 0.7992055416107178} 08/31/2021 12:18:05 - INFO - __main__ - Step 127199: {'lr': 2.8716861531137616e-05, 'samples': 24422208, 'steps': 127198, 'loss/train': 1.2100701332092285} 08/31/2021 12:18:06 - INFO - __main__ - Step 127200: {'lr': 2.8714392146013652e-05, 'samples': 24422400, 'steps': 127199, 'loss/train': 1.5601190328598022} 08/31/2021 12:18:07 - INFO - __main__ - Step 127201: {'lr': 2.8711922860597596e-05, 'samples': 24422592, 'steps': 127200, 'loss/train': 0.4855767786502838} 08/31/2021 12:18:07 - INFO - __main__ - Step 127202: {'lr': 2.87094536748905e-05, 'samples': 24422784, 'steps': 127201, 'loss/train': 0.9251610636711121} 08/31/2021 12:18:07 - INFO - __main__ - Step 127203: {'lr': 2.8706984588893535e-05, 'samples': 24422976, 'steps': 127202, 'loss/train': 1.9918242692947388} 08/31/2021 12:18:08 - INFO - __main__ - Step 127204: {'lr': 2.8704515602607757e-05, 'samples': 24423168, 'steps': 127203, 'loss/train': 0.8770478963851929} 08/31/2021 12:18:09 - INFO - __main__ - Step 127205: {'lr': 2.8702046716034325e-05, 'samples': 24423360, 'steps': 127204, 'loss/train': 1.1524931192398071} 08/31/2021 12:18:10 - INFO - __main__ - Step 127206: {'lr': 2.8699577929174407e-05, 'samples': 24423552, 'steps': 127205, 'loss/train': 0.468049556016922} 08/31/2021 12:18:10 - INFO - __main__ - Step 127207: {'lr': 2.869710924202898e-05, 'samples': 24423744, 'steps': 127206, 'loss/train': 1.4471795558929443} 08/31/2021 12:18:11 - INFO - __main__ - Step 127208: {'lr': 2.8694640654599202e-05, 'samples': 24423936, 'steps': 127207, 'loss/train': 1.5021713972091675} 08/31/2021 12:18:11 - INFO - __main__ - Step 127209: {'lr': 2.8692172166886215e-05, 'samples': 24424128, 'steps': 127208, 'loss/train': 1.2234907150268555} 08/31/2021 12:18:11 - INFO - __main__ - Step 127210: {'lr': 2.868970377889113e-05, 'samples': 24424320, 'steps': 127209, 'loss/train': 0.774277925491333} 08/31/2021 12:18:13 - INFO - __main__ - Step 127211: {'lr': 2.8687235490615054e-05, 'samples': 24424512, 'steps': 127210, 'loss/train': 0.1736205518245697} 08/31/2021 12:18:13 - INFO - __main__ - Step 127212: {'lr': 2.8684767302059074e-05, 'samples': 24424704, 'steps': 127211, 'loss/train': 1.100007176399231} 08/31/2021 12:18:14 - INFO - __main__ - Step 127213: {'lr': 2.868229921322432e-05, 'samples': 24424896, 'steps': 127212, 'loss/train': 1.1664087772369385} 08/31/2021 12:18:14 - INFO - __main__ - Step 127214: {'lr': 2.8679831224111942e-05, 'samples': 24425088, 'steps': 127213, 'loss/train': 0.9838763475418091} 08/31/2021 12:18:14 - INFO - __main__ - Step 127215: {'lr': 2.8677363334722982e-05, 'samples': 24425280, 'steps': 127214, 'loss/train': 1.313584566116333} 08/31/2021 12:18:16 - INFO - __main__ - Step 127216: {'lr': 2.867489554505859e-05, 'samples': 24425472, 'steps': 127215, 'loss/train': 1.0368950366973877} 08/31/2021 12:18:16 - INFO - __main__ - Step 127217: {'lr': 2.8672427855119893e-05, 'samples': 24425664, 'steps': 127216, 'loss/train': 1.7986531257629395} 08/31/2021 12:18:17 - INFO - __main__ - Step 127218: {'lr': 2.866996026490798e-05, 'samples': 24425856, 'steps': 127217, 'loss/train': 1.3194024562835693} 08/31/2021 12:18:17 - INFO - __main__ - Step 127219: {'lr': 2.8667492774424013e-05, 'samples': 24426048, 'steps': 127218, 'loss/train': 0.3668210804462433} 08/31/2021 12:18:17 - INFO - __main__ - Step 127220: {'lr': 2.8665025383668997e-05, 'samples': 24426240, 'steps': 127219, 'loss/train': 1.1170287132263184} 08/31/2021 12:18:19 - INFO - __main__ - Step 127221: {'lr': 2.866255809264412e-05, 'samples': 24426432, 'steps': 127220, 'loss/train': 0.9764971137046814} 08/31/2021 12:18:19 - INFO - __main__ - Step 127222: {'lr': 2.8660090901350493e-05, 'samples': 24426624, 'steps': 127221, 'loss/train': 1.3185579776763916} 08/31/2021 12:18:20 - INFO - __main__ - Step 127223: {'lr': 2.8657623809789174e-05, 'samples': 24426816, 'steps': 127222, 'loss/train': 1.4205255508422852} 08/31/2021 12:18:20 - INFO - __main__ - Step 127224: {'lr': 2.8655156817961353e-05, 'samples': 24427008, 'steps': 127223, 'loss/train': 0.9643725752830505} 08/31/2021 12:18:20 - INFO - __main__ - Step 127225: {'lr': 2.8652689925868087e-05, 'samples': 24427200, 'steps': 127224, 'loss/train': 1.4192230701446533} 08/31/2021 12:18:22 - INFO - __main__ - Step 127226: {'lr': 2.8650223133510484e-05, 'samples': 24427392, 'steps': 127225, 'loss/train': 0.7522954344749451} 08/31/2021 12:18:22 - INFO - __main__ - Step 127227: {'lr': 2.8647756440889712e-05, 'samples': 24427584, 'steps': 127226, 'loss/train': 0.9665332436561584} 08/31/2021 12:18:23 - INFO - __main__ - Step 127228: {'lr': 2.8645289848006823e-05, 'samples': 24427776, 'steps': 127227, 'loss/train': 0.11548146605491638} 08/31/2021 12:18:23 - INFO - __main__ - Step 127229: {'lr': 2.8642823354862958e-05, 'samples': 24427968, 'steps': 127228, 'loss/train': 1.2432217597961426} 08/31/2021 12:18:23 - INFO - __main__ - Step 127230: {'lr': 2.8640356961459225e-05, 'samples': 24428160, 'steps': 127229, 'loss/train': 0.6184619665145874} 08/31/2021 12:18:25 - INFO - __main__ - Step 127231: {'lr': 2.8637890667796708e-05, 'samples': 24428352, 'steps': 127230, 'loss/train': 1.3106895685195923} 08/31/2021 12:18:26 - INFO - __main__ - Step 127232: {'lr': 2.863542447387657e-05, 'samples': 24428544, 'steps': 127231, 'loss/train': 1.6130417585372925} 08/31/2021 12:18:26 - INFO - __main__ - Step 127233: {'lr': 2.8632958379699924e-05, 'samples': 24428736, 'steps': 127232, 'loss/train': 1.504380702972412} 08/31/2021 12:18:27 - INFO - __main__ - Step 127234: {'lr': 2.8630492385267797e-05, 'samples': 24428928, 'steps': 127233, 'loss/train': 1.3682734966278076} 08/31/2021 12:18:27 - INFO - __main__ - Step 127235: {'lr': 2.8628026490581383e-05, 'samples': 24429120, 'steps': 127234, 'loss/train': 1.598172664642334} 08/31/2021 12:18:27 - INFO - __main__ - Step 127236: {'lr': 2.8625560695641735e-05, 'samples': 24429312, 'steps': 127235, 'loss/train': 1.32379150390625} 08/31/2021 12:18:29 - INFO - __main__ - Step 127237: {'lr': 2.8623095000450015e-05, 'samples': 24429504, 'steps': 127236, 'loss/train': 1.2594267129898071} 08/31/2021 12:18:29 - INFO - __main__ - Step 127238: {'lr': 2.8620629405007287e-05, 'samples': 24429696, 'steps': 127237, 'loss/train': 0.5852039456367493} 08/31/2021 12:18:29 - INFO - __main__ - Step 127239: {'lr': 2.861816390931471e-05, 'samples': 24429888, 'steps': 127238, 'loss/train': 0.11441013216972351} 08/31/2021 12:18:30 - INFO - __main__ - Step 127240: {'lr': 2.8615698513373367e-05, 'samples': 24430080, 'steps': 127239, 'loss/train': 1.2047368288040161} 08/31/2021 12:18:30 - INFO - __main__ - Step 127241: {'lr': 2.861323321718437e-05, 'samples': 24430272, 'steps': 127240, 'loss/train': 0.9454599022865295} 08/31/2021 12:18:32 - INFO - __main__ - Step 127242: {'lr': 2.8610768020748827e-05, 'samples': 24430464, 'steps': 127241, 'loss/train': 1.4809935092926025} 08/31/2021 12:18:32 - INFO - __main__ - Step 127243: {'lr': 2.860830292406788e-05, 'samples': 24430656, 'steps': 127242, 'loss/train': 0.991710901260376} 08/31/2021 12:18:32 - INFO - __main__ - Step 127244: {'lr': 2.8605837927142607e-05, 'samples': 24430848, 'steps': 127243, 'loss/train': 1.0571640729904175} 08/31/2021 12:18:33 - INFO - __main__ - Step 127245: {'lr': 2.8603373029974095e-05, 'samples': 24431040, 'steps': 127244, 'loss/train': 0.6552612781524658} 08/31/2021 12:18:33 - INFO - __main__ - Step 127246: {'lr': 2.860090823256359e-05, 'samples': 24431232, 'steps': 127245, 'loss/train': 1.2933481931686401} 08/31/2021 12:18:35 - INFO - __main__ - Step 127247: {'lr': 2.8598443534912004e-05, 'samples': 24431424, 'steps': 127246, 'loss/train': 0.29536932706832886} 08/31/2021 12:18:35 - INFO - __main__ - Step 127248: {'lr': 2.8595978937020567e-05, 'samples': 24431616, 'steps': 127247, 'loss/train': 1.4548903703689575} 08/31/2021 12:18:35 - INFO - __main__ - Step 127249: {'lr': 2.8593514438890357e-05, 'samples': 24431808, 'steps': 127248, 'loss/train': 1.232560396194458} 08/31/2021 12:18:36 - INFO - __main__ - Step 127250: {'lr': 2.859105004052248e-05, 'samples': 24432000, 'steps': 127249, 'loss/train': 1.6606559753417969} 08/31/2021 12:18:36 - INFO - __main__ - Step 127251: {'lr': 2.858858574191808e-05, 'samples': 24432192, 'steps': 127250, 'loss/train': 1.223811388015747} 08/31/2021 12:18:38 - INFO - __main__ - Step 127252: {'lr': 2.8586121543078242e-05, 'samples': 24432384, 'steps': 127251, 'loss/train': 1.6675872802734375} 08/31/2021 12:18:38 - INFO - __main__ - Step 127253: {'lr': 2.8583657444004098e-05, 'samples': 24432576, 'steps': 127252, 'loss/train': 1.2426093816757202} 08/31/2021 12:18:38 - INFO - __main__ - Step 127254: {'lr': 2.8581193444696703e-05, 'samples': 24432768, 'steps': 127253, 'loss/train': 0.7697678208351135} 08/31/2021 12:18:39 - INFO - __main__ - Step 127255: {'lr': 2.8578729545157222e-05, 'samples': 24432960, 'steps': 127254, 'loss/train': 0.14171843230724335} 08/31/2021 12:18:39 - INFO - __main__ - Step 127256: {'lr': 2.857626574538677e-05, 'samples': 24433152, 'steps': 127255, 'loss/train': 0.7660688161849976} 08/31/2021 12:18:41 - INFO - __main__ - Step 127257: {'lr': 2.85738020453864e-05, 'samples': 24433344, 'steps': 127256, 'loss/train': 1.798753023147583} 08/31/2021 12:18:41 - INFO - __main__ - Step 127258: {'lr': 2.8571338445157274e-05, 'samples': 24433536, 'steps': 127257, 'loss/train': 1.1058540344238281} 08/31/2021 12:18:42 - INFO - __main__ - Step 127259: {'lr': 2.8568874944700507e-05, 'samples': 24433728, 'steps': 127258, 'loss/train': 1.316343903541565} 08/31/2021 12:18:42 - INFO - __main__ - Step 127260: {'lr': 2.8566411544017205e-05, 'samples': 24433920, 'steps': 127259, 'loss/train': 0.5878032445907593} 08/31/2021 12:18:42 - INFO - __main__ - Step 127261: {'lr': 2.8563948243108428e-05, 'samples': 24434112, 'steps': 127260, 'loss/train': 0.42140325903892517} 08/31/2021 12:18:44 - INFO - __main__ - Step 127262: {'lr': 2.856148504197531e-05, 'samples': 24434304, 'steps': 127261, 'loss/train': 1.3341275453567505} 08/31/2021 12:18:44 - INFO - __main__ - Step 127263: {'lr': 2.855902194061899e-05, 'samples': 24434496, 'steps': 127262, 'loss/train': 0.8174812197685242} 08/31/2021 12:18:45 - INFO - __main__ - Step 127264: {'lr': 2.855655893904055e-05, 'samples': 24434688, 'steps': 127263, 'loss/train': 1.221163034439087} 08/31/2021 12:18:45 - INFO - __main__ - Step 127265: {'lr': 2.8554096037241102e-05, 'samples': 24434880, 'steps': 127264, 'loss/train': 1.5673332214355469} 08/31/2021 12:18:45 - INFO - __main__ - Step 127266: {'lr': 2.855163323522175e-05, 'samples': 24435072, 'steps': 127265, 'loss/train': 0.7382287383079529} 08/31/2021 12:18:46 - INFO - __main__ - Step 127267: {'lr': 2.8549170532983616e-05, 'samples': 24435264, 'steps': 127266, 'loss/train': 1.09009850025177} 08/31/2021 12:18:47 - INFO - __main__ - Step 127268: {'lr': 2.8546707930527826e-05, 'samples': 24435456, 'steps': 127267, 'loss/train': 1.2990533113479614} 08/31/2021 12:18:48 - INFO - __main__ - Step 127269: {'lr': 2.854424542785547e-05, 'samples': 24435648, 'steps': 127268, 'loss/train': 1.4769723415374756} 08/31/2021 12:18:48 - INFO - __main__ - Step 127270: {'lr': 2.8541783024967653e-05, 'samples': 24435840, 'steps': 127269, 'loss/train': 1.0575424432754517} 08/31/2021 12:18:48 - INFO - __main__ - Step 127271: {'lr': 2.853932072186549e-05, 'samples': 24436032, 'steps': 127270, 'loss/train': 1.5587878227233887} 08/31/2021 12:18:49 - INFO - __main__ - Step 127272: {'lr': 2.853685851855009e-05, 'samples': 24436224, 'steps': 127271, 'loss/train': 0.6304783821105957} 08/31/2021 12:18:50 - INFO - __main__ - Step 127273: {'lr': 2.853439641502262e-05, 'samples': 24436416, 'steps': 127272, 'loss/train': 0.4698789715766907} 08/31/2021 12:18:51 - INFO - __main__ - Step 127274: {'lr': 2.853193441128407e-05, 'samples': 24436608, 'steps': 127273, 'loss/train': 0.9825586080551147} 08/31/2021 12:18:51 - INFO - __main__ - Step 127275: {'lr': 2.852947250733562e-05, 'samples': 24436800, 'steps': 127274, 'loss/train': 0.6732597351074219} 08/31/2021 12:18:51 - INFO - __main__ - Step 127276: {'lr': 2.8527010703178398e-05, 'samples': 24436992, 'steps': 127275, 'loss/train': 0.6279469132423401} 08/31/2021 12:18:52 - INFO - __main__ - Step 127277: {'lr': 2.852454899881346e-05, 'samples': 24437184, 'steps': 127276, 'loss/train': 0.6027832627296448} 08/31/2021 12:18:53 - INFO - __main__ - Step 127278: {'lr': 2.8522087394241948e-05, 'samples': 24437376, 'steps': 127277, 'loss/train': 1.1516759395599365} 08/31/2021 12:18:54 - INFO - __main__ - Step 127279: {'lr': 2.8519625889464967e-05, 'samples': 24437568, 'steps': 127278, 'loss/train': 0.810108482837677} 08/31/2021 12:18:54 - INFO - __main__ - Step 127280: {'lr': 2.8517164484483632e-05, 'samples': 24437760, 'steps': 127279, 'loss/train': 1.200150489807129} 08/31/2021 12:18:55 - INFO - __main__ - Step 127281: {'lr': 2.8514703179299024e-05, 'samples': 24437952, 'steps': 127280, 'loss/train': 1.294153094291687} 08/31/2021 12:18:55 - INFO - __main__ - Step 127282: {'lr': 2.851224197391228e-05, 'samples': 24438144, 'steps': 127281, 'loss/train': 1.0464059114456177} 08/31/2021 12:18:57 - INFO - __main__ - Step 127283: {'lr': 2.8509780868324507e-05, 'samples': 24438336, 'steps': 127282, 'loss/train': 0.9147828221321106} 08/31/2021 12:18:58 - INFO - __main__ - Step 127284: {'lr': 2.8507319862536824e-05, 'samples': 24438528, 'steps': 127283, 'loss/train': 1.0894266366958618} 08/31/2021 12:18:58 - INFO - __main__ - Step 127285: {'lr': 2.8504858956550307e-05, 'samples': 24438720, 'steps': 127284, 'loss/train': 1.219125747680664} 08/31/2021 12:18:58 - INFO - __main__ - Step 127286: {'lr': 2.8502398150366093e-05, 'samples': 24438912, 'steps': 127285, 'loss/train': 1.0711396932601929} 08/31/2021 12:18:59 - INFO - __main__ - Step 127287: {'lr': 2.8499937443985326e-05, 'samples': 24439104, 'steps': 127286, 'loss/train': 0.3398311734199524} 08/31/2021 12:18:59 - INFO - __main__ - Step 127288: {'lr': 2.8497476837408997e-05, 'samples': 24439296, 'steps': 127287, 'loss/train': 1.0837727785110474} 08/31/2021 12:19:01 - INFO - __main__ - Step 127289: {'lr': 2.8495016330638306e-05, 'samples': 24439488, 'steps': 127288, 'loss/train': 0.7773801684379578} 08/31/2021 12:19:01 - INFO - __main__ - Step 127290: {'lr': 2.849255592367436e-05, 'samples': 24439680, 'steps': 127289, 'loss/train': 0.9004471898078918} 08/31/2021 12:19:02 - INFO - __main__ - Step 127291: {'lr': 2.849009561651822e-05, 'samples': 24439872, 'steps': 127290, 'loss/train': 1.2592023611068726} 08/31/2021 12:19:02 - INFO - __main__ - Step 127292: {'lr': 2.8487635409171043e-05, 'samples': 24440064, 'steps': 127291, 'loss/train': 1.5575839281082153} 08/31/2021 12:19:02 - INFO - __main__ - Step 127293: {'lr': 2.8485175301633916e-05, 'samples': 24440256, 'steps': 127292, 'loss/train': 1.3366013765335083} 08/31/2021 12:19:04 - INFO - __main__ - Step 127294: {'lr': 2.8482715293907946e-05, 'samples': 24440448, 'steps': 127293, 'loss/train': 1.2572803497314453} 08/31/2021 12:19:05 - INFO - __main__ - Step 127295: {'lr': 2.8480255385994248e-05, 'samples': 24440640, 'steps': 127294, 'loss/train': 0.7752285003662109} 08/31/2021 12:19:05 - INFO - __main__ - Step 127296: {'lr': 2.8477795577893954e-05, 'samples': 24440832, 'steps': 127295, 'loss/train': 1.0208044052124023} 08/31/2021 12:19:05 - INFO - __main__ - Step 127297: {'lr': 2.8475335869608128e-05, 'samples': 24441024, 'steps': 127296, 'loss/train': 0.6157379150390625} 08/31/2021 12:19:06 - INFO - __main__ - Step 127298: {'lr': 2.847287626113787e-05, 'samples': 24441216, 'steps': 127297, 'loss/train': 1.4124032258987427} 08/31/2021 12:19:06 - INFO - __main__ - Step 127299: {'lr': 2.8470416752484353e-05, 'samples': 24441408, 'steps': 127298, 'loss/train': 1.2438796758651733} 08/31/2021 12:19:08 - INFO - __main__ - Step 127300: {'lr': 2.846795734364868e-05, 'samples': 24441600, 'steps': 127299, 'loss/train': 0.04248446971178055} 08/31/2021 12:19:08 - INFO - __main__ - Step 127301: {'lr': 2.8465498034631886e-05, 'samples': 24441792, 'steps': 127300, 'loss/train': 0.8593860864639282} 08/31/2021 12:19:08 - INFO - __main__ - Step 127302: {'lr': 2.8463038825435107e-05, 'samples': 24441984, 'steps': 127301, 'loss/train': 1.2213239669799805} 08/31/2021 12:19:09 - INFO - __main__ - Step 127303: {'lr': 2.8460579716059477e-05, 'samples': 24442176, 'steps': 127302, 'loss/train': 0.07456905394792557} 08/31/2021 12:19:09 - INFO - __main__ - Step 127304: {'lr': 2.845812070650608e-05, 'samples': 24442368, 'steps': 127303, 'loss/train': 1.2385594844818115} 08/31/2021 12:19:11 - INFO - __main__ - Step 127305: {'lr': 2.8455661796776056e-05, 'samples': 24442560, 'steps': 127304, 'loss/train': 1.051216959953308} 08/31/2021 12:19:12 - INFO - __main__ - Step 127306: {'lr': 2.8453202986870456e-05, 'samples': 24442752, 'steps': 127305, 'loss/train': 1.2545802593231201} 08/31/2021 12:19:12 - INFO - __main__ - Step 127307: {'lr': 2.8450744276790454e-05, 'samples': 24442944, 'steps': 127306, 'loss/train': 0.663882315158844} 08/31/2021 12:19:12 - INFO - __main__ - Step 127308: {'lr': 2.844828566653712e-05, 'samples': 24443136, 'steps': 127307, 'loss/train': 1.0700695514678955} 08/31/2021 12:19:13 - INFO - __main__ - Step 127309: {'lr': 2.8445827156111576e-05, 'samples': 24443328, 'steps': 127308, 'loss/train': 1.177101969718933} 08/31/2021 12:19:13 - INFO - __main__ - Step 127310: {'lr': 2.8443368745514926e-05, 'samples': 24443520, 'steps': 127309, 'loss/train': 1.0845756530761719} 08/31/2021 12:19:15 - INFO - __main__ - Step 127311: {'lr': 2.844091043474825e-05, 'samples': 24443712, 'steps': 127310, 'loss/train': 0.037873122841119766} 08/31/2021 12:19:15 - INFO - __main__ - Step 127312: {'lr': 2.8438452223812696e-05, 'samples': 24443904, 'steps': 127311, 'loss/train': 1.2129249572753906} 08/31/2021 12:19:15 - INFO - __main__ - Step 127313: {'lr': 2.8435994112709416e-05, 'samples': 24444096, 'steps': 127312, 'loss/train': 1.0288453102111816} 08/31/2021 12:19:16 - INFO - __main__ - Step 127314: {'lr': 2.8433536101439395e-05, 'samples': 24444288, 'steps': 127313, 'loss/train': 1.3896901607513428} 08/31/2021 12:19:16 - INFO - __main__ - Step 127315: {'lr': 2.8431078190003818e-05, 'samples': 24444480, 'steps': 127314, 'loss/train': 1.1271824836730957} 08/31/2021 12:19:18 - INFO - __main__ - Step 127316: {'lr': 2.842862037840377e-05, 'samples': 24444672, 'steps': 127315, 'loss/train': 0.048548366874456406} 08/31/2021 12:19:18 - INFO - __main__ - Step 127317: {'lr': 2.842616266664036e-05, 'samples': 24444864, 'steps': 127316, 'loss/train': 0.2597517669200897} 08/31/2021 12:19:18 - INFO - __main__ - Step 127318: {'lr': 2.84237050547147e-05, 'samples': 24445056, 'steps': 127317, 'loss/train': 1.0104156732559204} 08/31/2021 12:19:19 - INFO - __main__ - Step 127319: {'lr': 2.8421247542627897e-05, 'samples': 24445248, 'steps': 127318, 'loss/train': 1.5833899974822998} 08/31/2021 12:19:19 - INFO - __main__ - Step 127320: {'lr': 2.8418790130381067e-05, 'samples': 24445440, 'steps': 127319, 'loss/train': 1.0656200647354126} 08/31/2021 12:19:21 - INFO - __main__ - Step 127321: {'lr': 2.8416332817975314e-05, 'samples': 24445632, 'steps': 127320, 'loss/train': 1.1196812391281128} 08/31/2021 12:19:21 - INFO - __main__ - Step 127322: {'lr': 2.8413875605411755e-05, 'samples': 24445824, 'steps': 127321, 'loss/train': 0.8306446075439453} 08/31/2021 12:19:22 - INFO - __main__ - Step 127323: {'lr': 2.8411418492691465e-05, 'samples': 24446016, 'steps': 127322, 'loss/train': 0.7190727591514587} 08/31/2021 12:19:22 - INFO - __main__ - Step 127324: {'lr': 2.8408961479815588e-05, 'samples': 24446208, 'steps': 127323, 'loss/train': 1.265997290611267} 08/31/2021 12:19:22 - INFO - __main__ - Step 127325: {'lr': 2.8406504566785257e-05, 'samples': 24446400, 'steps': 127324, 'loss/train': 1.0626498460769653} 08/31/2021 12:19:24 - INFO - __main__ - Step 127326: {'lr': 2.8404047753601476e-05, 'samples': 24446592, 'steps': 127325, 'loss/train': 0.8994238376617432} 08/31/2021 12:19:24 - INFO - __main__ - Step 127327: {'lr': 2.8401591040265407e-05, 'samples': 24446784, 'steps': 127326, 'loss/train': 1.0593721866607666} 08/31/2021 12:19:25 - INFO - __main__ - Step 127328: {'lr': 2.8399134426778188e-05, 'samples': 24446976, 'steps': 127327, 'loss/train': 1.038048505783081} 08/31/2021 12:19:25 - INFO - __main__ - Step 127329: {'lr': 2.839667791314088e-05, 'samples': 24447168, 'steps': 127328, 'loss/train': 2.1672163009643555} 08/31/2021 12:19:25 - INFO - __main__ - Step 127330: {'lr': 2.839422149935461e-05, 'samples': 24447360, 'steps': 127329, 'loss/train': 0.8018353581428528} 08/31/2021 12:19:27 - INFO - __main__ - Step 127331: {'lr': 2.839176518542047e-05, 'samples': 24447552, 'steps': 127330, 'loss/train': 0.5020496249198914} 08/31/2021 12:19:27 - INFO - __main__ - Step 127332: {'lr': 2.838930897133962e-05, 'samples': 24447744, 'steps': 127331, 'loss/train': 1.0701643228530884} 08/31/2021 12:19:28 - INFO - __main__ - Step 127333: {'lr': 2.8386852857113093e-05, 'samples': 24447936, 'steps': 127332, 'loss/train': 1.1049901247024536} 08/31/2021 12:19:28 - INFO - __main__ - Step 127334: {'lr': 2.838439684274205e-05, 'samples': 24448128, 'steps': 127333, 'loss/train': 1.311015248298645} 08/31/2021 12:19:28 - INFO - __main__ - Step 127335: {'lr': 2.8381940928227574e-05, 'samples': 24448320, 'steps': 127334, 'loss/train': 0.04434870183467865} 08/31/2021 12:19:29 - INFO - __main__ - Step 127336: {'lr': 2.83794851135708e-05, 'samples': 24448512, 'steps': 127335, 'loss/train': 1.3400932550430298} 08/31/2021 12:19:31 - INFO - __main__ - Step 127337: {'lr': 2.837702939877279e-05, 'samples': 24448704, 'steps': 127336, 'loss/train': 1.6864503622055054} 08/31/2021 12:19:32 - INFO - __main__ - Step 127338: {'lr': 2.8374573783834678e-05, 'samples': 24448896, 'steps': 127337, 'loss/train': 0.7625594139099121} 08/31/2021 12:19:32 - INFO - __main__ - Step 127339: {'lr': 2.8372118268757545e-05, 'samples': 24449088, 'steps': 127338, 'loss/train': 0.9887428283691406} 08/31/2021 12:19:32 - INFO - __main__ - Step 127340: {'lr': 2.8369662853542504e-05, 'samples': 24449280, 'steps': 127339, 'loss/train': 0.7119572758674622} 08/31/2021 12:19:33 - INFO - __main__ - Step 127341: {'lr': 2.8367207538190692e-05, 'samples': 24449472, 'steps': 127340, 'loss/train': 1.1742401123046875} 08/31/2021 12:19:34 - INFO - __main__ - Step 127342: {'lr': 2.836475232270319e-05, 'samples': 24449664, 'steps': 127341, 'loss/train': 0.0674685388803482} 08/31/2021 12:19:35 - INFO - __main__ - Step 127343: {'lr': 2.836229720708111e-05, 'samples': 24449856, 'steps': 127342, 'loss/train': 1.3453474044799805} 08/31/2021 12:19:35 - INFO - __main__ - Step 127344: {'lr': 2.8359842191325563e-05, 'samples': 24450048, 'steps': 127343, 'loss/train': 1.045963168144226} 08/31/2021 12:19:35 - INFO - __main__ - Step 127345: {'lr': 2.8357387275437657e-05, 'samples': 24450240, 'steps': 127344, 'loss/train': 0.7443755269050598} 08/31/2021 12:19:36 - INFO - __main__ - Step 127346: {'lr': 2.8354932459418476e-05, 'samples': 24450432, 'steps': 127345, 'loss/train': 0.7600359916687012} 08/31/2021 12:19:38 - INFO - __main__ - Step 127347: {'lr': 2.8352477743269213e-05, 'samples': 24450624, 'steps': 127346, 'loss/train': 1.2396501302719116} 08/31/2021 12:19:38 - INFO - __main__ - Step 127348: {'lr': 2.8350023126990836e-05, 'samples': 24450816, 'steps': 127347, 'loss/train': 1.1828067302703857} 08/31/2021 12:19:39 - INFO - __main__ - Step 127349: {'lr': 2.8347568610584546e-05, 'samples': 24451008, 'steps': 127348, 'loss/train': 1.3620834350585938} 08/31/2021 12:19:39 - INFO - __main__ - Step 127350: {'lr': 2.834511419405139e-05, 'samples': 24451200, 'steps': 127349, 'loss/train': 1.1294467449188232} 08/31/2021 12:19:39 - INFO - __main__ - Step 127351: {'lr': 2.8342659877392512e-05, 'samples': 24451392, 'steps': 127350, 'loss/train': 1.1073635816574097} 08/31/2021 12:19:40 - INFO - __main__ - Step 127352: {'lr': 2.834020566060902e-05, 'samples': 24451584, 'steps': 127351, 'loss/train': 1.0333751440048218} 08/31/2021 12:19:41 - INFO - __main__ - Step 127353: {'lr': 2.8337751543701996e-05, 'samples': 24451776, 'steps': 127352, 'loss/train': 1.7335360050201416} 08/31/2021 12:19:41 - INFO - __main__ - Step 127354: {'lr': 2.8335297526672576e-05, 'samples': 24451968, 'steps': 127353, 'loss/train': 0.7543516755104065} 08/31/2021 12:19:42 - INFO - __main__ - Step 127355: {'lr': 2.8332843609521848e-05, 'samples': 24452160, 'steps': 127354, 'loss/train': 0.7534977793693542} 08/31/2021 12:19:42 - INFO - __main__ - Step 127356: {'lr': 2.8330389792250887e-05, 'samples': 24452352, 'steps': 127355, 'loss/train': 1.4733281135559082} 08/31/2021 12:19:42 - INFO - __main__ - Step 127357: {'lr': 2.8327936074860865e-05, 'samples': 24452544, 'steps': 127356, 'loss/train': 0.29937902092933655} 08/31/2021 12:19:44 - INFO - __main__ - Step 127358: {'lr': 2.8325482457352918e-05, 'samples': 24452736, 'steps': 127357, 'loss/train': 1.0382192134857178} 08/31/2021 12:19:44 - INFO - __main__ - Step 127359: {'lr': 2.8323028939728018e-05, 'samples': 24452928, 'steps': 127358, 'loss/train': 1.0539690256118774} 08/31/2021 12:19:45 - INFO - __main__ - Step 127360: {'lr': 2.832057552198733e-05, 'samples': 24453120, 'steps': 127359, 'loss/train': 1.531311273574829} 08/31/2021 12:19:45 - INFO - __main__ - Step 127361: {'lr': 2.8318122204131992e-05, 'samples': 24453312, 'steps': 127360, 'loss/train': 0.5703170895576477} 08/31/2021 12:19:45 - INFO - __main__ - Step 127362: {'lr': 2.8315668986163086e-05, 'samples': 24453504, 'steps': 127361, 'loss/train': 0.8557013273239136} 08/31/2021 12:19:47 - INFO - __main__ - Step 127363: {'lr': 2.8313215868081692e-05, 'samples': 24453696, 'steps': 127362, 'loss/train': 1.295740008354187} 08/31/2021 12:19:48 - INFO - __main__ - Step 127364: {'lr': 2.8310762849888955e-05, 'samples': 24453888, 'steps': 127363, 'loss/train': 1.0422428846359253} 08/31/2021 12:19:48 - INFO - __main__ - Step 127365: {'lr': 2.830830993158598e-05, 'samples': 24454080, 'steps': 127364, 'loss/train': 1.52804696559906} 08/31/2021 12:19:48 - INFO - __main__ - Step 127366: {'lr': 2.830585711317385e-05, 'samples': 24454272, 'steps': 127365, 'loss/train': 0.7775812149047852} 08/31/2021 12:19:49 - INFO - __main__ - Step 127367: {'lr': 2.8303404394653675e-05, 'samples': 24454464, 'steps': 127366, 'loss/train': 1.1279523372650146} 08/31/2021 12:19:50 - INFO - __main__ - Step 127368: {'lr': 2.8300951776026597e-05, 'samples': 24454656, 'steps': 127367, 'loss/train': 1.2060115337371826} 08/31/2021 12:19:51 - INFO - __main__ - Step 127369: {'lr': 2.8298499257293692e-05, 'samples': 24454848, 'steps': 127368, 'loss/train': 0.8902783989906311} 08/31/2021 12:19:51 - INFO - __main__ - Step 127370: {'lr': 2.8296046838456048e-05, 'samples': 24455040, 'steps': 127369, 'loss/train': 0.8479355573654175} 08/31/2021 12:19:52 - INFO - __main__ - Step 127371: {'lr': 2.829359451951477e-05, 'samples': 24455232, 'steps': 127370, 'loss/train': 1.5706984996795654} 08/31/2021 12:19:52 - INFO - __main__ - Step 127372: {'lr': 2.8291142300470975e-05, 'samples': 24455424, 'steps': 127371, 'loss/train': 0.13674433529376984} 08/31/2021 12:19:52 - INFO - __main__ - Step 127373: {'lr': 2.8288690181325764e-05, 'samples': 24455616, 'steps': 127372, 'loss/train': 0.10298022627830505} 08/31/2021 12:19:55 - INFO - __main__ - Step 127374: {'lr': 2.8286238162080257e-05, 'samples': 24455808, 'steps': 127373, 'loss/train': 1.248202919960022} 08/31/2021 12:19:56 - INFO - __main__ - Step 127375: {'lr': 2.828378624273556e-05, 'samples': 24456000, 'steps': 127374, 'loss/train': 1.1567429304122925} 08/31/2021 12:19:56 - INFO - __main__ - Step 127376: {'lr': 2.8281334423292755e-05, 'samples': 24456192, 'steps': 127375, 'loss/train': 1.4893901348114014} 08/31/2021 12:19:56 - INFO - __main__ - Step 127377: {'lr': 2.8278882703752952e-05, 'samples': 24456384, 'steps': 127376, 'loss/train': 1.454003930091858} 08/31/2021 12:19:57 - INFO - __main__ - Step 127378: {'lr': 2.8276431084117288e-05, 'samples': 24456576, 'steps': 127377, 'loss/train': 1.2826223373413086} 08/31/2021 12:19:57 - INFO - __main__ - Step 127379: {'lr': 2.827397956438682e-05, 'samples': 24456768, 'steps': 127378, 'loss/train': 0.47968071699142456} 08/31/2021 12:19:57 - INFO - __main__ - Step 127380: {'lr': 2.8271528144562685e-05, 'samples': 24456960, 'steps': 127379, 'loss/train': 0.8943039774894714} 08/31/2021 12:19:58 - INFO - __main__ - Step 127381: {'lr': 2.8269076824646023e-05, 'samples': 24457152, 'steps': 127380, 'loss/train': 0.765661895275116} 08/31/2021 12:19:59 - INFO - __main__ - Step 127382: {'lr': 2.8266625604637857e-05, 'samples': 24457344, 'steps': 127381, 'loss/train': 0.8901207447052002} 08/31/2021 12:20:00 - INFO - __main__ - Step 127383: {'lr': 2.82641744845393e-05, 'samples': 24457536, 'steps': 127382, 'loss/train': 0.9185438752174377} 08/31/2021 12:20:00 - INFO - __main__ - Step 127384: {'lr': 2.826172346435152e-05, 'samples': 24457728, 'steps': 127383, 'loss/train': 1.524666428565979} 08/31/2021 12:20:01 - INFO - __main__ - Step 127385: {'lr': 2.8259272544075566e-05, 'samples': 24457920, 'steps': 127384, 'loss/train': 2.002349615097046} 08/31/2021 12:20:01 - INFO - __main__ - Step 127386: {'lr': 2.825682172371255e-05, 'samples': 24458112, 'steps': 127385, 'loss/train': 1.6151279211044312} 08/31/2021 12:20:02 - INFO - __main__ - Step 127387: {'lr': 2.8254371003263614e-05, 'samples': 24458304, 'steps': 127386, 'loss/train': 1.2252494096755981} 08/31/2021 12:20:03 - INFO - __main__ - Step 127388: {'lr': 2.8251920382729805e-05, 'samples': 24458496, 'steps': 127387, 'loss/train': 0.6775874495506287} 08/31/2021 12:20:03 - INFO - __main__ - Step 127389: {'lr': 2.82494698621123e-05, 'samples': 24458688, 'steps': 127388, 'loss/train': 1.2838045358657837} 08/31/2021 12:20:04 - INFO - __main__ - Step 127390: {'lr': 2.8247019441412143e-05, 'samples': 24458880, 'steps': 127389, 'loss/train': 0.6294790506362915} 08/31/2021 12:20:04 - INFO - __main__ - Step 127391: {'lr': 2.8244569120630447e-05, 'samples': 24459072, 'steps': 127390, 'loss/train': 1.131807565689087} 08/31/2021 12:20:06 - INFO - __main__ - Step 127392: {'lr': 2.8242118899768325e-05, 'samples': 24459264, 'steps': 127391, 'loss/train': 1.3438374996185303} 08/31/2021 12:20:07 - INFO - __main__ - Step 127393: {'lr': 2.823966877882689e-05, 'samples': 24459456, 'steps': 127392, 'loss/train': 1.3073372840881348} 08/31/2021 12:20:07 - INFO - __main__ - Step 127394: {'lr': 2.8237218757807297e-05, 'samples': 24459648, 'steps': 127393, 'loss/train': 0.9331986308097839} 08/31/2021 12:20:07 - INFO - __main__ - Step 127395: {'lr': 2.8234768836710528e-05, 'samples': 24459840, 'steps': 127394, 'loss/train': 1.1364613771438599} 08/31/2021 12:20:08 - INFO - __main__ - Step 127396: {'lr': 2.8232319015537772e-05, 'samples': 24460032, 'steps': 127395, 'loss/train': 0.12742911279201508} 08/31/2021 12:20:08 - INFO - __main__ - Step 127397: {'lr': 2.8229869294290082e-05, 'samples': 24460224, 'steps': 127396, 'loss/train': 0.8621346950531006} 08/31/2021 12:20:10 - INFO - __main__ - Step 127398: {'lr': 2.82274196729686e-05, 'samples': 24460416, 'steps': 127397, 'loss/train': 1.2677650451660156} 08/31/2021 12:20:10 - INFO - __main__ - Step 127399: {'lr': 2.8224970151574435e-05, 'samples': 24460608, 'steps': 127398, 'loss/train': 0.7742742300033569} 08/31/2021 12:20:10 - INFO - __main__ - Step 127400: {'lr': 2.822252073010867e-05, 'samples': 24460800, 'steps': 127399, 'loss/train': 0.20948287844657898} 08/31/2021 12:20:11 - INFO - __main__ - Step 127401: {'lr': 2.8220071408572412e-05, 'samples': 24460992, 'steps': 127400, 'loss/train': 0.8951740264892578} 08/31/2021 12:20:11 - INFO - __main__ - Step 127402: {'lr': 2.8217622186966747e-05, 'samples': 24461184, 'steps': 127401, 'loss/train': 1.0979703664779663} 08/31/2021 12:20:13 - INFO - __main__ - Step 127403: {'lr': 2.8215173065292837e-05, 'samples': 24461376, 'steps': 127402, 'loss/train': 1.734687328338623} 08/31/2021 12:20:13 - INFO - __main__ - Step 127404: {'lr': 2.8212724043551714e-05, 'samples': 24461568, 'steps': 127403, 'loss/train': 0.4186893701553345} 08/31/2021 12:20:13 - INFO - __main__ - Step 127405: {'lr': 2.821027512174454e-05, 'samples': 24461760, 'steps': 127404, 'loss/train': 1.4271323680877686} 08/31/2021 12:20:14 - INFO - __main__ - Step 127406: {'lr': 2.820782629987237e-05, 'samples': 24461952, 'steps': 127405, 'loss/train': 0.026118505746126175} 08/31/2021 12:20:14 - INFO - __main__ - Step 127407: {'lr': 2.8205377577936343e-05, 'samples': 24462144, 'steps': 127406, 'loss/train': 0.5211718082427979} 08/31/2021 12:20:16 - INFO - __main__ - Step 127408: {'lr': 2.8202928955937624e-05, 'samples': 24462336, 'steps': 127407, 'loss/train': 1.5132691860198975} 08/31/2021 12:20:16 - INFO - __main__ - Step 127409: {'lr': 2.8200480433877158e-05, 'samples': 24462528, 'steps': 127408, 'loss/train': 1.2980042695999146} 08/31/2021 12:20:17 - INFO - __main__ - Step 127410: {'lr': 2.8198032011756137e-05, 'samples': 24462720, 'steps': 127409, 'loss/train': 0.6746751666069031} 08/31/2021 12:20:17 - INFO - __main__ - Step 127411: {'lr': 2.819558368957567e-05, 'samples': 24462912, 'steps': 127410, 'loss/train': 1.6750391721725464} 08/31/2021 12:20:17 - INFO - __main__ - Step 127412: {'lr': 2.819313546733687e-05, 'samples': 24463104, 'steps': 127411, 'loss/train': 1.1455280780792236} 08/31/2021 12:20:18 - INFO - __main__ - Step 127413: {'lr': 2.8190687345040794e-05, 'samples': 24463296, 'steps': 127412, 'loss/train': 1.6856660842895508} 08/31/2021 12:20:19 - INFO - __main__ - Step 127414: {'lr': 2.8188239322688574e-05, 'samples': 24463488, 'steps': 127413, 'loss/train': 0.9861769676208496} 08/31/2021 12:20:20 - INFO - __main__ - Step 127415: {'lr': 2.8185791400281326e-05, 'samples': 24463680, 'steps': 127414, 'loss/train': 1.3791924715042114} 08/31/2021 12:20:20 - INFO - __main__ - Step 127416: {'lr': 2.81833435778201e-05, 'samples': 24463872, 'steps': 127415, 'loss/train': 0.9758820533752441} 08/31/2021 12:20:20 - INFO - __main__ - Step 127417: {'lr': 2.818089585530606e-05, 'samples': 24464064, 'steps': 127416, 'loss/train': 0.828004777431488} 08/31/2021 12:20:21 - INFO - __main__ - Step 127418: {'lr': 2.8178448232740296e-05, 'samples': 24464256, 'steps': 127417, 'loss/train': 1.0267022848129272} 08/31/2021 12:20:22 - INFO - __main__ - Step 127419: {'lr': 2.8176000710123884e-05, 'samples': 24464448, 'steps': 127418, 'loss/train': 1.4435319900512695} 08/31/2021 12:20:23 - INFO - __main__ - Step 127420: {'lr': 2.8173553287457963e-05, 'samples': 24464640, 'steps': 127419, 'loss/train': 0.8755067586898804} 08/31/2021 12:20:23 - INFO - __main__ - Step 127421: {'lr': 2.8171105964743648e-05, 'samples': 24464832, 'steps': 127420, 'loss/train': 0.7283047437667847} 08/31/2021 12:20:23 - INFO - __main__ - Step 127422: {'lr': 2.816865874198196e-05, 'samples': 24465024, 'steps': 127421, 'loss/train': 1.9589378833770752} 08/31/2021 12:20:24 - INFO - __main__ - Step 127423: {'lr': 2.816621161917407e-05, 'samples': 24465216, 'steps': 127422, 'loss/train': 0.8960983753204346} 08/31/2021 12:20:25 - INFO - __main__ - Step 127424: {'lr': 2.8163764596321055e-05, 'samples': 24465408, 'steps': 127423, 'loss/train': 1.3842836618423462} 08/31/2021 12:20:26 - INFO - __main__ - Step 127425: {'lr': 2.8161317673424004e-05, 'samples': 24465600, 'steps': 127424, 'loss/train': 0.8818144798278809} 08/31/2021 12:20:26 - INFO - __main__ - Step 127426: {'lr': 2.8158870850484048e-05, 'samples': 24465792, 'steps': 127425, 'loss/train': 0.1310902237892151} 08/31/2021 12:20:26 - INFO - __main__ - Step 127427: {'lr': 2.81564241275023e-05, 'samples': 24465984, 'steps': 127426, 'loss/train': 1.9247609376907349} 08/31/2021 12:20:27 - INFO - __main__ - Step 127428: {'lr': 2.8153977504479815e-05, 'samples': 24466176, 'steps': 127427, 'loss/train': 1.3765627145767212} 08/31/2021 12:20:28 - INFO - __main__ - Step 127429: {'lr': 2.8151530981417762e-05, 'samples': 24466368, 'steps': 127428, 'loss/train': 0.773208737373352} 08/31/2021 12:20:29 - INFO - __main__ - Step 127430: {'lr': 2.814908455831719e-05, 'samples': 24466560, 'steps': 127429, 'loss/train': 1.0520991086959839} 08/31/2021 12:20:29 - INFO - __main__ - Step 127431: {'lr': 2.8146638235179213e-05, 'samples': 24466752, 'steps': 127430, 'loss/train': 1.094279170036316} 08/31/2021 12:20:29 - INFO - __main__ - Step 127432: {'lr': 2.814419201200491e-05, 'samples': 24466944, 'steps': 127431, 'loss/train': 0.12969328463077545} 08/31/2021 12:20:30 - INFO - __main__ - Step 127433: {'lr': 2.814174588879545e-05, 'samples': 24467136, 'steps': 127432, 'loss/train': 0.94764244556427} 08/31/2021 12:20:31 - INFO - __main__ - Step 127434: {'lr': 2.8139299865551944e-05, 'samples': 24467328, 'steps': 127433, 'loss/train': 1.0359708070755005} 08/31/2021 12:20:32 - INFO - __main__ - Step 127435: {'lr': 2.8136853942275388e-05, 'samples': 24467520, 'steps': 127434, 'loss/train': 0.6794063448905945} 08/31/2021 12:20:32 - INFO - __main__ - Step 127436: {'lr': 2.813440811896692e-05, 'samples': 24467712, 'steps': 127435, 'loss/train': 0.03771759197115898} 08/31/2021 12:20:33 - INFO - __main__ - Step 127437: {'lr': 2.813196239562768e-05, 'samples': 24467904, 'steps': 127436, 'loss/train': 1.4730459451675415} 08/31/2021 12:20:33 - INFO - __main__ - Step 127438: {'lr': 2.812951677225878e-05, 'samples': 24468096, 'steps': 127437, 'loss/train': 0.9148225784301758} 08/31/2021 12:20:33 - INFO - __main__ - Step 127439: {'lr': 2.812707124886127e-05, 'samples': 24468288, 'steps': 127438, 'loss/train': 1.299135684967041} 08/31/2021 12:20:35 - INFO - __main__ - Step 127440: {'lr': 2.8124625825436263e-05, 'samples': 24468480, 'steps': 127439, 'loss/train': 1.1635558605194092} 08/31/2021 12:20:36 - INFO - __main__ - Step 127441: {'lr': 2.8122180501984896e-05, 'samples': 24468672, 'steps': 127440, 'loss/train': 1.3126978874206543} 08/31/2021 12:20:36 - INFO - __main__ - Step 127442: {'lr': 2.8119735278508252e-05, 'samples': 24468864, 'steps': 127441, 'loss/train': 1.0275423526763916} 08/31/2021 12:20:36 - INFO - __main__ - Step 127443: {'lr': 2.811729015500744e-05, 'samples': 24469056, 'steps': 127442, 'loss/train': 0.47238320112228394} 08/31/2021 12:20:37 - INFO - __main__ - Step 127444: {'lr': 2.811484513148352e-05, 'samples': 24469248, 'steps': 127443, 'loss/train': 1.5213209390640259} 08/31/2021 12:20:38 - INFO - __main__ - Step 127445: {'lr': 2.811240020793765e-05, 'samples': 24469440, 'steps': 127444, 'loss/train': 0.313298761844635} 08/31/2021 12:20:39 - INFO - __main__ - Step 127446: {'lr': 2.8109955384370918e-05, 'samples': 24469632, 'steps': 127445, 'loss/train': 0.53531414270401} 08/31/2021 12:20:39 - INFO - __main__ - Step 127447: {'lr': 2.81075106607844e-05, 'samples': 24469824, 'steps': 127446, 'loss/train': 0.7993572950363159} 08/31/2021 12:20:39 - INFO - __main__ - Step 127448: {'lr': 2.810506603717927e-05, 'samples': 24470016, 'steps': 127447, 'loss/train': 1.1650917530059814} 08/31/2021 12:20:40 - INFO - __main__ - Step 127449: {'lr': 2.8102621513556525e-05, 'samples': 24470208, 'steps': 127448, 'loss/train': 1.509726643562317} 08/31/2021 12:20:40 - INFO - __main__ - Step 127450: {'lr': 2.81001770899173e-05, 'samples': 24470400, 'steps': 127449, 'loss/train': 0.8054672479629517} 08/31/2021 12:20:42 - INFO - __main__ - Step 127451: {'lr': 2.8097732766262736e-05, 'samples': 24470592, 'steps': 127450, 'loss/train': 5.813623905181885} 08/31/2021 12:20:43 - INFO - __main__ - Step 127452: {'lr': 2.8095288542593882e-05, 'samples': 24470784, 'steps': 127451, 'loss/train': 0.11206912994384766} 08/31/2021 12:20:43 - INFO - __main__ - Step 127453: {'lr': 2.8092844418911884e-05, 'samples': 24470976, 'steps': 127452, 'loss/train': 1.3363032341003418} 08/31/2021 12:20:43 - INFO - __main__ - Step 127454: {'lr': 2.809040039521782e-05, 'samples': 24471168, 'steps': 127453, 'loss/train': 1.7242727279663086} 08/31/2021 12:20:44 - INFO - __main__ - Step 127455: {'lr': 2.80879564715128e-05, 'samples': 24471360, 'steps': 127454, 'loss/train': 1.184707760810852} 08/31/2021 12:20:45 - INFO - __main__ - Step 127456: {'lr': 2.8085512647797934e-05, 'samples': 24471552, 'steps': 127455, 'loss/train': 1.3737725019454956} 08/31/2021 12:20:46 - INFO - __main__ - Step 127457: {'lr': 2.8083068924074305e-05, 'samples': 24471744, 'steps': 127456, 'loss/train': 1.241891860961914} 08/31/2021 12:20:46 - INFO - __main__ - Step 127458: {'lr': 2.8080625300342998e-05, 'samples': 24471936, 'steps': 127457, 'loss/train': 0.02573312446475029} 08/31/2021 12:20:46 - INFO - __main__ - Step 127459: {'lr': 2.8078181776605176e-05, 'samples': 24472128, 'steps': 127458, 'loss/train': 0.04269551485776901} 08/31/2021 12:20:47 - INFO - __main__ - Step 127460: {'lr': 2.8075738352861868e-05, 'samples': 24472320, 'steps': 127459, 'loss/train': 0.6530751585960388} 08/31/2021 12:20:48 - INFO - __main__ - Step 127461: {'lr': 2.8073295029114265e-05, 'samples': 24472512, 'steps': 127460, 'loss/train': 0.8609323501586914} 08/31/2021 12:20:49 - INFO - __main__ - Step 127462: {'lr': 2.8070851805363367e-05, 'samples': 24472704, 'steps': 127461, 'loss/train': 1.5465444326400757} 08/31/2021 12:20:49 - INFO - __main__ - Step 127463: {'lr': 2.8068408681610312e-05, 'samples': 24472896, 'steps': 127462, 'loss/train': 0.32615119218826294} 08/31/2021 12:20:50 - INFO - __main__ - Step 127464: {'lr': 2.8065965657856212e-05, 'samples': 24473088, 'steps': 127463, 'loss/train': 1.3820017576217651} 08/31/2021 12:20:50 - INFO - __main__ - Step 127465: {'lr': 2.8063522734102175e-05, 'samples': 24473280, 'steps': 127464, 'loss/train': 1.1330592632293701} 08/31/2021 12:20:51 - INFO - __main__ - Step 127466: {'lr': 2.8061079910349284e-05, 'samples': 24473472, 'steps': 127465, 'loss/train': 0.8881824612617493} 08/31/2021 12:20:52 - INFO - __main__ - Step 127467: {'lr': 2.8058637186598625e-05, 'samples': 24473664, 'steps': 127466, 'loss/train': 1.478516936302185} 08/31/2021 12:20:52 - INFO - __main__ - Step 127468: {'lr': 2.8056194562851355e-05, 'samples': 24473856, 'steps': 127467, 'loss/train': 0.7783406972885132} 08/31/2021 12:20:53 - INFO - __main__ - Step 127469: {'lr': 2.805375203910851e-05, 'samples': 24474048, 'steps': 127468, 'loss/train': 0.7782106995582581} 08/31/2021 12:20:53 - INFO - __main__ - Step 127470: {'lr': 2.8051309615371223e-05, 'samples': 24474240, 'steps': 127469, 'loss/train': 1.4073131084442139} 08/31/2021 12:20:54 - INFO - __main__ - Step 127471: {'lr': 2.8048867291640608e-05, 'samples': 24474432, 'steps': 127470, 'loss/train': 0.8074182271957397} 08/31/2021 12:20:55 - INFO - __main__ - Step 127472: {'lr': 2.8046425067917742e-05, 'samples': 24474624, 'steps': 127471, 'loss/train': 1.3073891401290894} 08/31/2021 12:20:55 - INFO - __main__ - Step 127473: {'lr': 2.8043982944203712e-05, 'samples': 24474816, 'steps': 127472, 'loss/train': 0.9831952452659607} 08/31/2021 12:20:56 - INFO - __main__ - Step 127474: {'lr': 2.8041540920499654e-05, 'samples': 24475008, 'steps': 127473, 'loss/train': 0.7061221599578857} 08/31/2021 12:20:56 - INFO - __main__ - Step 127475: {'lr': 2.8039098996806704e-05, 'samples': 24475200, 'steps': 127474, 'loss/train': 0.9673574566841125} 08/31/2021 12:20:57 - INFO - __main__ - Step 127476: {'lr': 2.8036657173125868e-05, 'samples': 24475392, 'steps': 127475, 'loss/train': 0.9642332792282104} 08/31/2021 12:20:58 - INFO - __main__ - Step 127477: {'lr': 2.803421544945828e-05, 'samples': 24475584, 'steps': 127476, 'loss/train': 1.395702838897705} 08/31/2021 12:20:58 - INFO - __main__ - Step 127478: {'lr': 2.8031773825805046e-05, 'samples': 24475776, 'steps': 127477, 'loss/train': 1.308801293373108} 08/31/2021 12:20:58 - INFO - __main__ - Step 127479: {'lr': 2.8029332302167254e-05, 'samples': 24475968, 'steps': 127478, 'loss/train': 1.177123785018921} 08/31/2021 12:20:59 - INFO - __main__ - Step 127480: {'lr': 2.802689087854604e-05, 'samples': 24476160, 'steps': 127479, 'loss/train': 0.8434399962425232} 08/31/2021 12:21:00 - INFO - __main__ - Step 127481: {'lr': 2.8024449554942488e-05, 'samples': 24476352, 'steps': 127480, 'loss/train': 0.9023901224136353} 08/31/2021 12:21:01 - INFO - __main__ - Step 127482: {'lr': 2.802200833135768e-05, 'samples': 24476544, 'steps': 127481, 'loss/train': 1.4881548881530762} 08/31/2021 12:21:01 - INFO - __main__ - Step 127483: {'lr': 2.8019567207792752e-05, 'samples': 24476736, 'steps': 127482, 'loss/train': 0.8773223161697388} 08/31/2021 12:21:01 - INFO - __main__ - Step 127484: {'lr': 2.801712618424876e-05, 'samples': 24476928, 'steps': 127483, 'loss/train': 1.0113385915756226} 08/31/2021 12:21:02 - INFO - __main__ - Step 127485: {'lr': 2.801468526072684e-05, 'samples': 24477120, 'steps': 127484, 'loss/train': 1.1405636072158813} 08/31/2021 12:21:03 - INFO - __main__ - Step 127486: {'lr': 2.8012244437228053e-05, 'samples': 24477312, 'steps': 127485, 'loss/train': 1.0966119766235352} 08/31/2021 12:21:04 - INFO - __main__ - Step 127487: {'lr': 2.8009803713753555e-05, 'samples': 24477504, 'steps': 127486, 'loss/train': 1.1643660068511963} 08/31/2021 12:21:04 - INFO - __main__ - Step 127488: {'lr': 2.800736309030444e-05, 'samples': 24477696, 'steps': 127487, 'loss/train': 1.0238591432571411} 08/31/2021 12:21:05 - INFO - __main__ - Step 127489: {'lr': 2.800492256688175e-05, 'samples': 24477888, 'steps': 127488, 'loss/train': 1.9242502450942993} 08/31/2021 12:21:05 - INFO - __main__ - Step 127490: {'lr': 2.8002482143486608e-05, 'samples': 24478080, 'steps': 127489, 'loss/train': 1.246412754058838} 08/31/2021 12:21:05 - INFO - __main__ - Step 127491: {'lr': 2.8000041820120114e-05, 'samples': 24478272, 'steps': 127490, 'loss/train': 1.432100534439087} 08/31/2021 12:21:07 - INFO - __main__ - Step 127492: {'lr': 2.7997601596783386e-05, 'samples': 24478464, 'steps': 127491, 'loss/train': 3.6561546325683594} 08/31/2021 12:21:07 - INFO - __main__ - Step 127493: {'lr': 2.7995161473477498e-05, 'samples': 24478656, 'steps': 127492, 'loss/train': 1.313124656677246} 08/31/2021 12:21:08 - INFO - __main__ - Step 127494: {'lr': 2.799272145020357e-05, 'samples': 24478848, 'steps': 127493, 'loss/train': 1.8019773960113525} 08/31/2021 12:21:08 - INFO - __main__ - Step 127495: {'lr': 2.7990281526962703e-05, 'samples': 24479040, 'steps': 127494, 'loss/train': 1.1612653732299805} 08/31/2021 12:21:08 - INFO - __main__ - Step 127496: {'lr': 2.7987841703755985e-05, 'samples': 24479232, 'steps': 127495, 'loss/train': 1.5535417795181274} 08/31/2021 12:21:10 - INFO - __main__ - Step 127497: {'lr': 2.7985401980584524e-05, 'samples': 24479424, 'steps': 127496, 'loss/train': 0.10876692831516266} 08/31/2021 12:21:11 - INFO - __main__ - Step 127498: {'lr': 2.798296235744943e-05, 'samples': 24479616, 'steps': 127497, 'loss/train': 1.2213962078094482} 08/31/2021 12:21:11 - INFO - __main__ - Step 127499: {'lr': 2.7980522834351764e-05, 'samples': 24479808, 'steps': 127498, 'loss/train': 1.259295105934143} 08/31/2021 12:21:11 - INFO - __main__ - Step 127500: {'lr': 2.7978083411292656e-05, 'samples': 24480000, 'steps': 127499, 'loss/train': 0.9156262874603271} 08/31/2021 12:21:12 - INFO - __main__ - Step 127501: {'lr': 2.797564408827319e-05, 'samples': 24480192, 'steps': 127500, 'loss/train': 0.7790224552154541} 08/31/2021 12:21:14 - INFO - __main__ - Step 127502: {'lr': 2.7973204865294533e-05, 'samples': 24480384, 'steps': 127501, 'loss/train': 0.88121497631073} 08/31/2021 12:21:14 - INFO - __main__ - Step 127503: {'lr': 2.7970765742357684e-05, 'samples': 24480576, 'steps': 127502, 'loss/train': 1.7655091285705566} 08/31/2021 12:21:15 - INFO - __main__ - Step 127504: {'lr': 2.7968326719463753e-05, 'samples': 24480768, 'steps': 127503, 'loss/train': 0.872642993927002} 08/31/2021 12:21:15 - INFO - __main__ - Step 127505: {'lr': 2.796588779661388e-05, 'samples': 24480960, 'steps': 127504, 'loss/train': 1.3039278984069824} 08/31/2021 12:21:15 - INFO - __main__ - Step 127506: {'lr': 2.7963448973809173e-05, 'samples': 24481152, 'steps': 127505, 'loss/train': 0.8243951797485352} 08/31/2021 12:21:17 - INFO - __main__ - Step 127507: {'lr': 2.796101025105069e-05, 'samples': 24481344, 'steps': 127506, 'loss/train': 0.4539342224597931} 08/31/2021 12:21:17 - INFO - __main__ - Step 127508: {'lr': 2.7958571628339534e-05, 'samples': 24481536, 'steps': 127507, 'loss/train': 0.7652111053466797} 08/31/2021 12:21:18 - INFO - __main__ - Step 127509: {'lr': 2.7956133105676852e-05, 'samples': 24481728, 'steps': 127508, 'loss/train': 1.5394576787948608} 08/31/2021 12:21:18 - INFO - __main__ - Step 127510: {'lr': 2.795369468306369e-05, 'samples': 24481920, 'steps': 127509, 'loss/train': 0.9119434356689453} 08/31/2021 12:21:18 - INFO - __main__ - Step 127511: {'lr': 2.7951256360501164e-05, 'samples': 24482112, 'steps': 127510, 'loss/train': 1.1050595045089722} 08/31/2021 12:21:20 - INFO - __main__ - Step 127512: {'lr': 2.7948818137990383e-05, 'samples': 24482304, 'steps': 127511, 'loss/train': 0.6824491024017334} 08/31/2021 12:21:20 - INFO - __main__ - Step 127513: {'lr': 2.794638001553243e-05, 'samples': 24482496, 'steps': 127512, 'loss/train': 1.1274206638336182} 08/31/2021 12:21:21 - INFO - __main__ - Step 127514: {'lr': 2.7943941993128442e-05, 'samples': 24482688, 'steps': 127513, 'loss/train': 1.3932647705078125} 08/31/2021 12:21:21 - INFO - __main__ - Step 127515: {'lr': 2.79415040707795e-05, 'samples': 24482880, 'steps': 127514, 'loss/train': 1.277159333229065} 08/31/2021 12:21:21 - INFO - __main__ - Step 127516: {'lr': 2.793906624848666e-05, 'samples': 24483072, 'steps': 127515, 'loss/train': 1.4895079135894775} 08/31/2021 12:21:23 - INFO - __main__ - Step 127517: {'lr': 2.7936628526251036e-05, 'samples': 24483264, 'steps': 127516, 'loss/train': 1.2771373987197876} 08/31/2021 12:21:23 - INFO - __main__ - Step 127518: {'lr': 2.793419090407376e-05, 'samples': 24483456, 'steps': 127517, 'loss/train': 1.306132435798645} 08/31/2021 12:21:24 - INFO - __main__ - Step 127519: {'lr': 2.7931753381955888e-05, 'samples': 24483648, 'steps': 127518, 'loss/train': 0.13651186227798462} 08/31/2021 12:21:24 - INFO - __main__ - Step 127520: {'lr': 2.792931595989856e-05, 'samples': 24483840, 'steps': 127519, 'loss/train': 0.13852857053279877} 08/31/2021 12:21:24 - INFO - __main__ - Step 127521: {'lr': 2.792687863790286e-05, 'samples': 24484032, 'steps': 127520, 'loss/train': 0.040602993220090866} 08/31/2021 12:21:25 - INFO - __main__ - Step 127522: {'lr': 2.7924441415969866e-05, 'samples': 24484224, 'steps': 127521, 'loss/train': 0.3941003978252411} 08/31/2021 12:21:26 - INFO - __main__ - Step 127523: {'lr': 2.792200429410069e-05, 'samples': 24484416, 'steps': 127522, 'loss/train': 0.9019134044647217} 08/31/2021 12:21:27 - INFO - __main__ - Step 127524: {'lr': 2.7919567272296443e-05, 'samples': 24484608, 'steps': 127523, 'loss/train': 1.5465283393859863} 08/31/2021 12:21:27 - INFO - __main__ - Step 127525: {'lr': 2.7917130350558205e-05, 'samples': 24484800, 'steps': 127524, 'loss/train': 1.909233808517456} 08/31/2021 12:21:27 - INFO - __main__ - Step 127526: {'lr': 2.7914693528887064e-05, 'samples': 24484992, 'steps': 127525, 'loss/train': 0.898641049861908} 08/31/2021 12:21:28 - INFO - __main__ - Step 127527: {'lr': 2.791225680728418e-05, 'samples': 24485184, 'steps': 127526, 'loss/train': 0.7858968377113342} 08/31/2021 12:21:29 - INFO - __main__ - Step 127528: {'lr': 2.7909820185750557e-05, 'samples': 24485376, 'steps': 127527, 'loss/train': 0.9248895049095154} 08/31/2021 12:21:30 - INFO - __main__ - Step 127529: {'lr': 2.790738366428744e-05, 'samples': 24485568, 'steps': 127528, 'loss/train': 0.7790018320083618} 08/31/2021 12:21:30 - INFO - __main__ - Step 127530: {'lr': 2.7904947242895744e-05, 'samples': 24485760, 'steps': 127529, 'loss/train': 0.23949085175991058} 08/31/2021 12:21:30 - INFO - __main__ - Step 127531: {'lr': 2.7902510921576668e-05, 'samples': 24485952, 'steps': 127530, 'loss/train': 1.5129035711288452} 08/31/2021 12:21:31 - INFO - __main__ - Step 127532: {'lr': 2.790007470033129e-05, 'samples': 24486144, 'steps': 127531, 'loss/train': 0.8528985381126404} 08/31/2021 12:21:32 - INFO - __main__ - Step 127533: {'lr': 2.7897638579160695e-05, 'samples': 24486336, 'steps': 127532, 'loss/train': 0.8591138124465942} 08/31/2021 12:21:33 - INFO - __main__ - Step 127534: {'lr': 2.789520255806602e-05, 'samples': 24486528, 'steps': 127533, 'loss/train': 1.0623724460601807} 08/31/2021 12:21:33 - INFO - __main__ - Step 127535: {'lr': 2.7892766637048318e-05, 'samples': 24486720, 'steps': 127534, 'loss/train': 1.934555172920227} 08/31/2021 12:21:33 - INFO - __main__ - Step 127536: {'lr': 2.7890330816108728e-05, 'samples': 24486912, 'steps': 127535, 'loss/train': 1.0041424036026} 08/31/2021 12:21:34 - INFO - __main__ - Step 127537: {'lr': 2.7887895095248307e-05, 'samples': 24487104, 'steps': 127536, 'loss/train': 1.380353331565857} 08/31/2021 12:21:35 - INFO - __main__ - Step 127538: {'lr': 2.788545947446819e-05, 'samples': 24487296, 'steps': 127537, 'loss/train': 0.9932690858840942} 08/31/2021 12:21:36 - INFO - __main__ - Step 127539: {'lr': 2.788302395376946e-05, 'samples': 24487488, 'steps': 127538, 'loss/train': 1.87589430809021} 08/31/2021 12:21:36 - INFO - __main__ - Step 127540: {'lr': 2.7880588533153202e-05, 'samples': 24487680, 'steps': 127539, 'loss/train': 1.0766956806182861} 08/31/2021 12:21:37 - INFO - __main__ - Step 127541: {'lr': 2.787815321262052e-05, 'samples': 24487872, 'steps': 127540, 'loss/train': 4.446885585784912} 08/31/2021 12:21:37 - INFO - __main__ - Step 127542: {'lr': 2.787571799217259e-05, 'samples': 24488064, 'steps': 127541, 'loss/train': 1.1550391912460327} 08/31/2021 12:21:37 - INFO - __main__ - Step 127543: {'lr': 2.7873282871810345e-05, 'samples': 24488256, 'steps': 127542, 'loss/train': 1.1044831275939941} 08/31/2021 12:21:39 - INFO - __main__ - Step 127544: {'lr': 2.7870847851534988e-05, 'samples': 24488448, 'steps': 127543, 'loss/train': 0.9599141478538513} 08/31/2021 12:21:39 - INFO - __main__ - Step 127545: {'lr': 2.786841293134762e-05, 'samples': 24488640, 'steps': 127544, 'loss/train': 0.055557478219270706} 08/31/2021 12:21:40 - INFO - __main__ - Step 127546: {'lr': 2.78659781112493e-05, 'samples': 24488832, 'steps': 127545, 'loss/train': 1.9027154445648193} 08/31/2021 12:21:40 - INFO - __main__ - Step 127547: {'lr': 2.7863543391241143e-05, 'samples': 24489024, 'steps': 127546, 'loss/train': 1.031003475189209} 08/31/2021 12:21:40 - INFO - __main__ - Step 127548: {'lr': 2.7861108771324223e-05, 'samples': 24489216, 'steps': 127547, 'loss/train': 0.9541719555854797} 08/31/2021 12:21:42 - INFO - __main__ - Step 127549: {'lr': 2.785867425149968e-05, 'samples': 24489408, 'steps': 127548, 'loss/train': 0.6113027334213257} 08/31/2021 12:21:43 - INFO - __main__ - Step 127550: {'lr': 2.7856239831768603e-05, 'samples': 24489600, 'steps': 127549, 'loss/train': 0.4578629434108734} 08/31/2021 12:21:43 - INFO - __main__ - Step 127551: {'lr': 2.785380551213207e-05, 'samples': 24489792, 'steps': 127550, 'loss/train': 1.1963226795196533} 08/31/2021 12:21:43 - INFO - __main__ - Step 127552: {'lr': 2.785137129259116e-05, 'samples': 24489984, 'steps': 127551, 'loss/train': 1.1186625957489014} 08/31/2021 12:21:44 - INFO - __main__ - Step 127553: {'lr': 2.7848937173147014e-05, 'samples': 24490176, 'steps': 127552, 'loss/train': 1.557511806488037} 08/31/2021 12:21:46 - INFO - __main__ - Step 127554: {'lr': 2.784650315380072e-05, 'samples': 24490368, 'steps': 127553, 'loss/train': 0.6789438724517822} 08/31/2021 12:21:46 - INFO - __main__ - Step 127555: {'lr': 2.7844069234553403e-05, 'samples': 24490560, 'steps': 127554, 'loss/train': 0.673700749874115} 08/31/2021 12:21:47 - INFO - __main__ - Step 127556: {'lr': 2.7841635415406076e-05, 'samples': 24490752, 'steps': 127555, 'loss/train': 0.20152972638607025} 08/31/2021 12:21:47 - INFO - __main__ - Step 127557: {'lr': 2.7839201696359866e-05, 'samples': 24490944, 'steps': 127556, 'loss/train': 1.0349282026290894} 08/31/2021 12:21:47 - INFO - __main__ - Step 127558: {'lr': 2.783676807741589e-05, 'samples': 24491136, 'steps': 127557, 'loss/train': 0.06608276814222336} 08/31/2021 12:21:48 - INFO - __main__ - Step 127559: {'lr': 2.7834334558575232e-05, 'samples': 24491328, 'steps': 127558, 'loss/train': 0.9591110944747925} 08/31/2021 12:21:49 - INFO - __main__ - Step 127560: {'lr': 2.7831901139839024e-05, 'samples': 24491520, 'steps': 127559, 'loss/train': 1.4866316318511963} 08/31/2021 12:21:50 - INFO - __main__ - Step 127561: {'lr': 2.7829467821208293e-05, 'samples': 24491712, 'steps': 127560, 'loss/train': 1.5990456342697144} 08/31/2021 12:21:50 - INFO - __main__ - Step 127562: {'lr': 2.782703460268421e-05, 'samples': 24491904, 'steps': 127561, 'loss/train': 0.6393904685974121} 08/31/2021 12:21:51 - INFO - __main__ - Step 127563: {'lr': 2.7824601484267798e-05, 'samples': 24492096, 'steps': 127562, 'loss/train': 0.041179802268743515} 08/31/2021 12:21:51 - INFO - __main__ - Step 127564: {'lr': 2.7822168465960222e-05, 'samples': 24492288, 'steps': 127563, 'loss/train': 0.41015246510505676} 08/31/2021 12:21:52 - INFO - __main__ - Step 127565: {'lr': 2.7819735547762542e-05, 'samples': 24492480, 'steps': 127564, 'loss/train': 0.7611097693443298} 08/31/2021 12:21:53 - INFO - __main__ - Step 127566: {'lr': 2.7817302729675863e-05, 'samples': 24492672, 'steps': 127565, 'loss/train': 1.1630455255508423} 08/31/2021 12:21:53 - INFO - __main__ - Step 127567: {'lr': 2.781487001170127e-05, 'samples': 24492864, 'steps': 127566, 'loss/train': 1.087517261505127} 08/31/2021 12:21:54 - INFO - __main__ - Step 127568: {'lr': 2.7812437393839874e-05, 'samples': 24493056, 'steps': 127567, 'loss/train': 0.6488544344902039} 08/31/2021 12:21:54 - INFO - __main__ - Step 127569: {'lr': 2.781000487609281e-05, 'samples': 24493248, 'steps': 127568, 'loss/train': 0.7661134600639343} 08/31/2021 12:21:56 - INFO - __main__ - Step 127570: {'lr': 2.7807572458461077e-05, 'samples': 24493440, 'steps': 127569, 'loss/train': 1.1584523916244507} 08/31/2021 12:21:56 - INFO - __main__ - Step 127571: {'lr': 2.7805140140945844e-05, 'samples': 24493632, 'steps': 127570, 'loss/train': 0.5327625870704651} 08/31/2021 12:21:57 - INFO - __main__ - Step 127572: {'lr': 2.7802707923548164e-05, 'samples': 24493824, 'steps': 127571, 'loss/train': 0.8491370677947998} 08/31/2021 12:21:57 - INFO - __main__ - Step 127573: {'lr': 2.7800275806269175e-05, 'samples': 24494016, 'steps': 127572, 'loss/train': 1.1347942352294922} 08/31/2021 12:21:57 - INFO - __main__ - Step 127574: {'lr': 2.7797843789109932e-05, 'samples': 24494208, 'steps': 127573, 'loss/train': 0.49997302889823914} 08/31/2021 12:21:58 - INFO - __main__ - Step 127575: {'lr': 2.7795411872071575e-05, 'samples': 24494400, 'steps': 127574, 'loss/train': 0.07956212759017944} 08/31/2021 12:21:59 - INFO - __main__ - Step 127576: {'lr': 2.7792980055155155e-05, 'samples': 24494592, 'steps': 127575, 'loss/train': 0.7728403210639954} 08/31/2021 12:22:00 - INFO - __main__ - Step 127577: {'lr': 2.779054833836181e-05, 'samples': 24494784, 'steps': 127576, 'loss/train': 0.985445499420166} 08/31/2021 12:22:00 - INFO - __main__ - Step 127578: {'lr': 2.7788116721692596e-05, 'samples': 24494976, 'steps': 127577, 'loss/train': 0.19762814044952393} 08/31/2021 12:22:00 - INFO - __main__ - Step 127579: {'lr': 2.7785685205148625e-05, 'samples': 24495168, 'steps': 127578, 'loss/train': 0.9457530379295349} 08/31/2021 12:22:01 - INFO - __main__ - Step 127580: {'lr': 2.7783253788731006e-05, 'samples': 24495360, 'steps': 127579, 'loss/train': 0.36633697152137756} 08/31/2021 12:22:02 - INFO - __main__ - Step 127581: {'lr': 2.778082247244082e-05, 'samples': 24495552, 'steps': 127580, 'loss/train': 0.6611180305480957} 08/31/2021 12:22:03 - INFO - __main__ - Step 127582: {'lr': 2.7778391256279207e-05, 'samples': 24495744, 'steps': 127581, 'loss/train': 0.4526366889476776} 08/31/2021 12:22:03 - INFO - __main__ - Step 127583: {'lr': 2.7775960140247193e-05, 'samples': 24495936, 'steps': 127582, 'loss/train': 2.0124549865722656} 08/31/2021 12:22:03 - INFO - __main__ - Step 127584: {'lr': 2.7773529124345887e-05, 'samples': 24496128, 'steps': 127583, 'loss/train': 0.7682247757911682} 08/31/2021 12:22:04 - INFO - __main__ - Step 127585: {'lr': 2.7771098208576402e-05, 'samples': 24496320, 'steps': 127584, 'loss/train': 2.1529312133789062} 08/31/2021 12:22:05 - INFO - __main__ - Step 127586: {'lr': 2.7768667392939845e-05, 'samples': 24496512, 'steps': 127585, 'loss/train': 1.1121861934661865} 08/31/2021 12:22:06 - INFO - __main__ - Step 127587: {'lr': 2.7766236677437273e-05, 'samples': 24496704, 'steps': 127586, 'loss/train': 0.3160262107849121} 08/31/2021 12:22:06 - INFO - __main__ - Step 127588: {'lr': 2.7763806062069825e-05, 'samples': 24496896, 'steps': 127587, 'loss/train': 0.3719593286514282} 08/31/2021 12:22:06 - INFO - __main__ - Step 127589: {'lr': 2.776137554683858e-05, 'samples': 24497088, 'steps': 127588, 'loss/train': 1.1027904748916626} 08/31/2021 12:22:07 - INFO - __main__ - Step 127590: {'lr': 2.7758945131744624e-05, 'samples': 24497280, 'steps': 127589, 'loss/train': 0.31057825684547424} 08/31/2021 12:22:08 - INFO - __main__ - Step 127591: {'lr': 2.7756514816789035e-05, 'samples': 24497472, 'steps': 127590, 'loss/train': 0.7097955346107483} 08/31/2021 12:22:09 - INFO - __main__ - Step 127592: {'lr': 2.7754084601972955e-05, 'samples': 24497664, 'steps': 127591, 'loss/train': 0.038989052176475525} 08/31/2021 12:22:09 - INFO - __main__ - Step 127593: {'lr': 2.7751654487297466e-05, 'samples': 24497856, 'steps': 127592, 'loss/train': 0.5567734837532043} 08/31/2021 12:22:09 - INFO - __main__ - Step 127594: {'lr': 2.7749224472763678e-05, 'samples': 24498048, 'steps': 127593, 'loss/train': 1.1668059825897217} 08/31/2021 12:22:10 - INFO - __main__ - Step 127595: {'lr': 2.7746794558372617e-05, 'samples': 24498240, 'steps': 127594, 'loss/train': 1.2965620756149292} 08/31/2021 12:22:11 - INFO - __main__ - Step 127596: {'lr': 2.7744364744125423e-05, 'samples': 24498432, 'steps': 127595, 'loss/train': 1.0432708263397217} 08/31/2021 12:22:12 - INFO - __main__ - Step 127597: {'lr': 2.7741935030023173e-05, 'samples': 24498624, 'steps': 127596, 'loss/train': 0.38969096541404724} 08/31/2021 12:22:12 - INFO - __main__ - Step 127598: {'lr': 2.7739505416067013e-05, 'samples': 24498816, 'steps': 127597, 'loss/train': 1.2516344785690308} 08/31/2021 12:22:13 - INFO - __main__ - Step 127599: {'lr': 2.7737075902257965e-05, 'samples': 24499008, 'steps': 127598, 'loss/train': 1.8194557428359985} 08/31/2021 12:22:13 - INFO - __main__ - Step 127600: {'lr': 2.7734646488597193e-05, 'samples': 24499200, 'steps': 127599, 'loss/train': 1.1228578090667725} 08/31/2021 12:22:13 - INFO - __main__ - Step 127601: {'lr': 2.7732217175085727e-05, 'samples': 24499392, 'steps': 127600, 'loss/train': 1.2492969036102295} 08/31/2021 12:22:15 - INFO - __main__ - Step 127602: {'lr': 2.7729787961724706e-05, 'samples': 24499584, 'steps': 127601, 'loss/train': 0.6079663634300232} 08/31/2021 12:22:15 - INFO - __main__ - Step 127603: {'lr': 2.7727358848515238e-05, 'samples': 24499776, 'steps': 127602, 'loss/train': 1.140242576599121} 08/31/2021 12:22:16 - INFO - __main__ - Step 127604: {'lr': 2.7724929835458353e-05, 'samples': 24499968, 'steps': 127603, 'loss/train': 0.936471164226532} 08/31/2021 12:22:16 - INFO - __main__ - Step 127605: {'lr': 2.7722500922555266e-05, 'samples': 24500160, 'steps': 127604, 'loss/train': 1.1423143148422241} 08/31/2021 12:22:16 - INFO - __main__ - Step 127606: {'lr': 2.7720072109806928e-05, 'samples': 24500352, 'steps': 127605, 'loss/train': 1.2446335554122925} 08/31/2021 12:22:18 - INFO - __main__ - Step 127607: {'lr': 2.77176433972145e-05, 'samples': 24500544, 'steps': 127606, 'loss/train': 0.9514675140380859} 08/31/2021 12:22:19 - INFO - __main__ - Step 127608: {'lr': 2.7715214784779065e-05, 'samples': 24500736, 'steps': 127607, 'loss/train': 1.1188602447509766} 08/31/2021 12:22:19 - INFO - __main__ - Step 127609: {'lr': 2.7712786272501705e-05, 'samples': 24500928, 'steps': 127608, 'loss/train': 2.266231060028076} 08/31/2021 12:22:19 - INFO - __main__ - Step 127610: {'lr': 2.7710357860383563e-05, 'samples': 24501120, 'steps': 127609, 'loss/train': 1.4947421550750732} 08/31/2021 12:22:20 - INFO - __main__ - Step 127611: {'lr': 2.7707929548425687e-05, 'samples': 24501312, 'steps': 127610, 'loss/train': 1.8584620952606201} 08/31/2021 12:22:22 - INFO - __main__ - Step 127612: {'lr': 2.770550133662919e-05, 'samples': 24501504, 'steps': 127611, 'loss/train': 0.8899317383766174} 08/31/2021 12:22:22 - INFO - __main__ - Step 127613: {'lr': 2.7703073224995185e-05, 'samples': 24501696, 'steps': 127612, 'loss/train': 1.8047751188278198} 08/31/2021 12:22:22 - INFO - __main__ - Step 127614: {'lr': 2.770064521352472e-05, 'samples': 24501888, 'steps': 127613, 'loss/train': 1.4293348789215088} 08/31/2021 12:22:23 - INFO - __main__ - Step 127615: {'lr': 2.769821730221894e-05, 'samples': 24502080, 'steps': 127614, 'loss/train': 1.1413886547088623} 08/31/2021 12:22:23 - INFO - __main__ - Step 127616: {'lr': 2.7695789491078925e-05, 'samples': 24502272, 'steps': 127615, 'loss/train': 0.9993831515312195} 08/31/2021 12:22:25 - INFO - __main__ - Step 127617: {'lr': 2.769336178010573e-05, 'samples': 24502464, 'steps': 127616, 'loss/train': 1.5330078601837158} 08/31/2021 12:22:26 - INFO - __main__ - Step 127618: {'lr': 2.7690934169300493e-05, 'samples': 24502656, 'steps': 127617, 'loss/train': 0.5320110321044922} 08/31/2021 12:22:26 - INFO - __main__ - Step 127619: {'lr': 2.7688506658664266e-05, 'samples': 24502848, 'steps': 127618, 'loss/train': 0.8323863744735718} 08/31/2021 12:22:26 - INFO - __main__ - Step 127620: {'lr': 2.768607924819816e-05, 'samples': 24503040, 'steps': 127619, 'loss/train': 1.246673822402954} 08/31/2021 12:22:27 - INFO - __main__ - Step 127621: {'lr': 2.7683651937903285e-05, 'samples': 24503232, 'steps': 127620, 'loss/train': 1.6413325071334839} 08/31/2021 12:22:28 - INFO - __main__ - Step 127622: {'lr': 2.7681224727780728e-05, 'samples': 24503424, 'steps': 127621, 'loss/train': 0.09945593029260635} 08/31/2021 12:22:29 - INFO - __main__ - Step 127623: {'lr': 2.7678797617831597e-05, 'samples': 24503616, 'steps': 127622, 'loss/train': 1.0106641054153442} 08/31/2021 12:22:29 - INFO - __main__ - Step 127624: {'lr': 2.7676370608056946e-05, 'samples': 24503808, 'steps': 127623, 'loss/train': 1.7215492725372314} 08/31/2021 12:22:29 - INFO - __main__ - Step 127625: {'lr': 2.767394369845791e-05, 'samples': 24504000, 'steps': 127624, 'loss/train': 0.8906261920928955} 08/31/2021 12:22:30 - INFO - __main__ - Step 127626: {'lr': 2.76715168890356e-05, 'samples': 24504192, 'steps': 127625, 'loss/train': 1.2348332405090332} 08/31/2021 12:22:30 - INFO - __main__ - Step 127627: {'lr': 2.7669090179791022e-05, 'samples': 24504384, 'steps': 127626, 'loss/train': 1.28792142868042} 08/31/2021 12:22:31 - INFO - __main__ - Step 127628: {'lr': 2.7666663570725338e-05, 'samples': 24504576, 'steps': 127627, 'loss/train': 0.9707030653953552} 08/31/2021 12:22:32 - INFO - __main__ - Step 127629: {'lr': 2.7664237061839625e-05, 'samples': 24504768, 'steps': 127628, 'loss/train': 0.9356208443641663} 08/31/2021 12:22:32 - INFO - __main__ - Step 127630: {'lr': 2.7661810653134943e-05, 'samples': 24504960, 'steps': 127629, 'loss/train': 0.26329392194747925} 08/31/2021 12:22:33 - INFO - __main__ - Step 127631: {'lr': 2.765938434461246e-05, 'samples': 24505152, 'steps': 127630, 'loss/train': 0.5082934498786926} 08/31/2021 12:22:33 - INFO - __main__ - Step 127632: {'lr': 2.7656958136273196e-05, 'samples': 24505344, 'steps': 127631, 'loss/train': 1.0236523151397705} 08/31/2021 12:22:34 - INFO - __main__ - Step 127633: {'lr': 2.7654532028118294e-05, 'samples': 24505536, 'steps': 127632, 'loss/train': 0.10687540471553802} 08/31/2021 12:22:35 - INFO - __main__ - Step 127634: {'lr': 2.765210602014881e-05, 'samples': 24505728, 'steps': 127633, 'loss/train': 1.3254432678222656} 08/31/2021 12:22:35 - INFO - __main__ - Step 127635: {'lr': 2.7649680112365875e-05, 'samples': 24505920, 'steps': 127634, 'loss/train': 1.3082871437072754} 08/31/2021 12:22:36 - INFO - __main__ - Step 127636: {'lr': 2.764725430477055e-05, 'samples': 24506112, 'steps': 127635, 'loss/train': 1.1246147155761719} 08/31/2021 12:22:36 - INFO - __main__ - Step 127637: {'lr': 2.7644828597364003e-05, 'samples': 24506304, 'steps': 127636, 'loss/train': 1.0837786197662354} 08/31/2021 12:22:38 - INFO - __main__ - Step 127638: {'lr': 2.7642402990147224e-05, 'samples': 24506496, 'steps': 127637, 'loss/train': 0.18143756687641144} 08/31/2021 12:22:38 - INFO - __main__ - Step 127639: {'lr': 2.7639977483121332e-05, 'samples': 24506688, 'steps': 127638, 'loss/train': 1.7747983932495117} 08/31/2021 12:22:38 - INFO - __main__ - Step 127640: {'lr': 2.7637552076287433e-05, 'samples': 24506880, 'steps': 127639, 'loss/train': 1.0399307012557983} 08/31/2021 12:22:39 - INFO - __main__ - Step 127641: {'lr': 2.7635126769646608e-05, 'samples': 24507072, 'steps': 127640, 'loss/train': 0.5263694524765015} 08/31/2021 12:22:39 - INFO - __main__ - Step 127642: {'lr': 2.7632701563199996e-05, 'samples': 24507264, 'steps': 127641, 'loss/train': 1.4061810970306396} 08/31/2021 12:22:40 - INFO - __main__ - Step 127643: {'lr': 2.7630276456948627e-05, 'samples': 24507456, 'steps': 127642, 'loss/train': 1.1010329723358154} 08/31/2021 12:22:41 - INFO - __main__ - Step 127644: {'lr': 2.762785145089364e-05, 'samples': 24507648, 'steps': 127643, 'loss/train': 1.3485333919525146} 08/31/2021 12:22:41 - INFO - __main__ - Step 127645: {'lr': 2.762542654503611e-05, 'samples': 24507840, 'steps': 127644, 'loss/train': 0.8753349184989929} 08/31/2021 12:22:42 - INFO - __main__ - Step 127646: {'lr': 2.7623001739377153e-05, 'samples': 24508032, 'steps': 127645, 'loss/train': 0.8913441896438599} 08/31/2021 12:22:42 - INFO - __main__ - Step 127647: {'lr': 2.7620577033917793e-05, 'samples': 24508224, 'steps': 127646, 'loss/train': 1.4920315742492676} 08/31/2021 12:22:44 - INFO - __main__ - Step 127648: {'lr': 2.7618152428659198e-05, 'samples': 24508416, 'steps': 127647, 'loss/train': 0.9158163666725159} 08/31/2021 12:22:44 - INFO - __main__ - Step 127649: {'lr': 2.7615727923602423e-05, 'samples': 24508608, 'steps': 127648, 'loss/train': 1.443796157836914} 08/31/2021 12:22:44 - INFO - __main__ - Step 127650: {'lr': 2.7613303518748632e-05, 'samples': 24508800, 'steps': 127649, 'loss/train': 0.9736207127571106} 08/31/2021 12:22:45 - INFO - __main__ - Step 127651: {'lr': 2.76108792140988e-05, 'samples': 24508992, 'steps': 127650, 'loss/train': 1.6114708185195923} 08/31/2021 12:22:45 - INFO - __main__ - Step 127652: {'lr': 2.7608455009654087e-05, 'samples': 24509184, 'steps': 127651, 'loss/train': 1.2670533657073975} 08/31/2021 12:22:47 - INFO - __main__ - Step 127653: {'lr': 2.7606030905415552e-05, 'samples': 24509376, 'steps': 127652, 'loss/train': 0.7931572198867798} 08/31/2021 12:22:47 - INFO - __main__ - Step 127654: {'lr': 2.7603606901384305e-05, 'samples': 24509568, 'steps': 127653, 'loss/train': 0.7069640159606934} 08/31/2021 12:22:47 - INFO - __main__ - Step 127655: {'lr': 2.7601182997561453e-05, 'samples': 24509760, 'steps': 127654, 'loss/train': 0.7913182973861694} 08/31/2021 12:22:48 - INFO - __main__ - Step 127656: {'lr': 2.759875919394808e-05, 'samples': 24509952, 'steps': 127655, 'loss/train': 0.553725004196167} 08/31/2021 12:22:48 - INFO - __main__ - Step 127657: {'lr': 2.759633549054527e-05, 'samples': 24510144, 'steps': 127656, 'loss/train': 1.1317777633666992} 08/31/2021 12:22:48 - INFO - __main__ - Step 127658: {'lr': 2.7593911887354108e-05, 'samples': 24510336, 'steps': 127657, 'loss/train': 1.2245838642120361} 08/31/2021 12:22:50 - INFO - __main__ - Step 127659: {'lr': 2.7591488384375697e-05, 'samples': 24510528, 'steps': 127658, 'loss/train': 1.0390167236328125} 08/31/2021 12:22:50 - INFO - __main__ - Step 127660: {'lr': 2.758906498161115e-05, 'samples': 24510720, 'steps': 127659, 'loss/train': 1.5660737752914429} 08/31/2021 12:22:51 - INFO - __main__ - Step 127661: {'lr': 2.7586641679061526e-05, 'samples': 24510912, 'steps': 127660, 'loss/train': 0.6333101391792297} 08/31/2021 12:22:51 - INFO - __main__ - Step 127662: {'lr': 2.758421847672793e-05, 'samples': 24511104, 'steps': 127661, 'loss/train': 0.8191064596176147} 08/31/2021 12:22:51 - INFO - __main__ - Step 127663: {'lr': 2.7581795374611502e-05, 'samples': 24511296, 'steps': 127662, 'loss/train': 1.6138300895690918} 08/31/2021 12:22:53 - INFO - __main__ - Step 127664: {'lr': 2.7579372372713242e-05, 'samples': 24511488, 'steps': 127663, 'loss/train': 1.14967942237854} 08/31/2021 12:22:54 - INFO - __main__ - Step 127665: {'lr': 2.7576949471034257e-05, 'samples': 24511680, 'steps': 127664, 'loss/train': 0.022872235625982285} 08/31/2021 12:22:54 - INFO - __main__ - Step 127666: {'lr': 2.757452666957569e-05, 'samples': 24511872, 'steps': 127665, 'loss/train': 0.8065320253372192} 08/31/2021 12:22:54 - INFO - __main__ - Step 127667: {'lr': 2.7572103968338617e-05, 'samples': 24512064, 'steps': 127666, 'loss/train': 0.8091719746589661} 08/31/2021 12:22:55 - INFO - __main__ - Step 127668: {'lr': 2.75696813673241e-05, 'samples': 24512256, 'steps': 127667, 'loss/train': 1.083047866821289} 08/31/2021 12:22:57 - INFO - __main__ - Step 127669: {'lr': 2.7567258866533273e-05, 'samples': 24512448, 'steps': 127668, 'loss/train': 0.9525759220123291} 08/31/2021 12:22:57 - INFO - __main__ - Step 127670: {'lr': 2.7564836465967193e-05, 'samples': 24512640, 'steps': 127669, 'loss/train': 1.0879199504852295} 08/31/2021 12:22:57 - INFO - __main__ - Step 127671: {'lr': 2.7562414165626963e-05, 'samples': 24512832, 'steps': 127670, 'loss/train': 1.1217212677001953} 08/31/2021 12:22:58 - INFO - __main__ - Step 127672: {'lr': 2.7559991965513703e-05, 'samples': 24513024, 'steps': 127671, 'loss/train': 1.0909844636917114} 08/31/2021 12:22:58 - INFO - __main__ - Step 127673: {'lr': 2.7557569865628435e-05, 'samples': 24513216, 'steps': 127672, 'loss/train': 1.3746662139892578} 08/31/2021 12:22:58 - INFO - __main__ - Step 127674: {'lr': 2.7555147865972324e-05, 'samples': 24513408, 'steps': 127673, 'loss/train': 0.26387256383895874} 08/31/2021 12:23:00 - INFO - __main__ - Step 127675: {'lr': 2.7552725966546426e-05, 'samples': 24513600, 'steps': 127674, 'loss/train': 0.8266962170600891} 08/31/2021 12:23:01 - INFO - __main__ - Step 127676: {'lr': 2.755030416735188e-05, 'samples': 24513792, 'steps': 127675, 'loss/train': 1.4641236066818237} 08/31/2021 12:23:01 - INFO - __main__ - Step 127677: {'lr': 2.7547882468389686e-05, 'samples': 24513984, 'steps': 127676, 'loss/train': 1.1614290475845337} 08/31/2021 12:23:01 - INFO - __main__ - Step 127678: {'lr': 2.7545460869661005e-05, 'samples': 24514176, 'steps': 127677, 'loss/train': 0.02745029516518116} 08/31/2021 12:23:02 - INFO - __main__ - Step 127679: {'lr': 2.7543039371166867e-05, 'samples': 24514368, 'steps': 127678, 'loss/train': 1.0704091787338257} 08/31/2021 12:23:02 - INFO - __main__ - Step 127680: {'lr': 2.754061797290844e-05, 'samples': 24514560, 'steps': 127679, 'loss/train': 0.866989254951477} 08/31/2021 12:23:04 - INFO - __main__ - Step 127681: {'lr': 2.7538196674886744e-05, 'samples': 24514752, 'steps': 127680, 'loss/train': 0.44667190313339233} 08/31/2021 12:23:04 - INFO - __main__ - Step 127682: {'lr': 2.7535775477102925e-05, 'samples': 24514944, 'steps': 127681, 'loss/train': 0.7175554633140564} 08/31/2021 12:23:04 - INFO - __main__ - Step 127683: {'lr': 2.7533354379558063e-05, 'samples': 24515136, 'steps': 127682, 'loss/train': 1.2745518684387207} 08/31/2021 12:23:05 - INFO - __main__ - Step 127684: {'lr': 2.753093338225321e-05, 'samples': 24515328, 'steps': 127683, 'loss/train': 0.6611955761909485} 08/31/2021 12:23:05 - INFO - __main__ - Step 127685: {'lr': 2.7528512485189507e-05, 'samples': 24515520, 'steps': 127684, 'loss/train': 1.7843964099884033} 08/31/2021 12:23:07 - INFO - __main__ - Step 127686: {'lr': 2.7526091688368033e-05, 'samples': 24515712, 'steps': 127685, 'loss/train': 0.9178572297096252} 08/31/2021 12:23:07 - INFO - __main__ - Step 127687: {'lr': 2.7523670991789845e-05, 'samples': 24515904, 'steps': 127686, 'loss/train': 0.7664132714271545} 08/31/2021 12:23:08 - INFO - __main__ - Step 127688: {'lr': 2.7521250395456054e-05, 'samples': 24516096, 'steps': 127687, 'loss/train': 1.4920426607131958} 08/31/2021 12:23:08 - INFO - __main__ - Step 127689: {'lr': 2.751882989936777e-05, 'samples': 24516288, 'steps': 127688, 'loss/train': 1.0196453332901} 08/31/2021 12:23:08 - INFO - __main__ - Step 127690: {'lr': 2.751640950352613e-05, 'samples': 24516480, 'steps': 127689, 'loss/train': 0.054647307842969894} 08/31/2021 12:23:10 - INFO - __main__ - Step 127691: {'lr': 2.7513989207932078e-05, 'samples': 24516672, 'steps': 127690, 'loss/train': 0.7365359663963318} 08/31/2021 12:23:10 - INFO - __main__ - Step 127692: {'lr': 2.7511569012586806e-05, 'samples': 24516864, 'steps': 127691, 'loss/train': 1.2433030605316162} 08/31/2021 12:23:11 - INFO - __main__ - Step 127693: {'lr': 2.75091489174914e-05, 'samples': 24517056, 'steps': 127692, 'loss/train': 0.7024067640304565} 08/31/2021 12:23:11 - INFO - __main__ - Step 127694: {'lr': 2.750672892264694e-05, 'samples': 24517248, 'steps': 127693, 'loss/train': 0.6932097673416138} 08/31/2021 12:23:11 - INFO - __main__ - Step 127695: {'lr': 2.750430902805448e-05, 'samples': 24517440, 'steps': 127694, 'loss/train': 1.2014739513397217} 08/31/2021 12:23:13 - INFO - __main__ - Step 127696: {'lr': 2.750188923371519e-05, 'samples': 24517632, 'steps': 127695, 'loss/train': 0.7643026113510132} 08/31/2021 12:23:14 - INFO - __main__ - Step 127697: {'lr': 2.749946953963009e-05, 'samples': 24517824, 'steps': 127696, 'loss/train': 1.135172963142395} 08/31/2021 12:23:14 - INFO - __main__ - Step 127698: {'lr': 2.7497049945800294e-05, 'samples': 24518016, 'steps': 127697, 'loss/train': 1.4730485677719116} 08/31/2021 12:23:15 - INFO - __main__ - Step 127699: {'lr': 2.7494630452226887e-05, 'samples': 24518208, 'steps': 127698, 'loss/train': 0.6562841534614563} 08/31/2021 12:23:15 - INFO - __main__ - Step 127700: {'lr': 2.7492211058910976e-05, 'samples': 24518400, 'steps': 127699, 'loss/train': 0.5679681301116943} 08/31/2021 12:23:17 - INFO - __main__ - Step 127701: {'lr': 2.7489791765853646e-05, 'samples': 24518592, 'steps': 127700, 'loss/train': 1.103931188583374} 08/31/2021 12:23:17 - INFO - __main__ - Step 127702: {'lr': 2.7487372573056e-05, 'samples': 24518784, 'steps': 127701, 'loss/train': 1.7779574394226074} 08/31/2021 12:23:17 - INFO - __main__ - Step 127703: {'lr': 2.748495348051913e-05, 'samples': 24518976, 'steps': 127702, 'loss/train': 1.414669156074524} 08/31/2021 12:23:18 - INFO - __main__ - Step 127704: {'lr': 2.748253448824406e-05, 'samples': 24519168, 'steps': 127703, 'loss/train': 0.8239871859550476} 08/31/2021 12:23:18 - INFO - __main__ - Step 127705: {'lr': 2.7480115596231952e-05, 'samples': 24519360, 'steps': 127704, 'loss/train': 1.4820317029953003} 08/31/2021 12:23:19 - INFO - __main__ - Step 127706: {'lr': 2.7477696804483838e-05, 'samples': 24519552, 'steps': 127705, 'loss/train': 1.4688431024551392} 08/31/2021 12:23:20 - INFO - __main__ - Step 127707: {'lr': 2.747527811300085e-05, 'samples': 24519744, 'steps': 127706, 'loss/train': 1.2210111618041992} 08/31/2021 12:23:21 - INFO - __main__ - Step 127708: {'lr': 2.7472859521784076e-05, 'samples': 24519936, 'steps': 127707, 'loss/train': 0.954957902431488} 08/31/2021 12:23:21 - INFO - __main__ - Step 127709: {'lr': 2.7470441030834597e-05, 'samples': 24520128, 'steps': 127708, 'loss/train': 1.071467399597168} 08/31/2021 12:23:22 - INFO - __main__ - Step 127710: {'lr': 2.7468022640153494e-05, 'samples': 24520320, 'steps': 127709, 'loss/train': 1.0775374174118042} 08/31/2021 12:23:22 - INFO - __main__ - Step 127711: {'lr': 2.746560434974188e-05, 'samples': 24520512, 'steps': 127710, 'loss/train': 1.0585815906524658} 08/31/2021 12:23:23 - INFO - __main__ - Step 127712: {'lr': 2.7463186159600807e-05, 'samples': 24520704, 'steps': 127711, 'loss/train': 1.0439740419387817} 08/31/2021 12:23:24 - INFO - __main__ - Step 127713: {'lr': 2.7460768069731414e-05, 'samples': 24520896, 'steps': 127712, 'loss/train': 1.7045619487762451} 08/31/2021 12:23:24 - INFO - __main__ - Step 127714: {'lr': 2.7458350080134753e-05, 'samples': 24521088, 'steps': 127713, 'loss/train': 1.3734153509140015} 08/31/2021 12:23:24 - INFO - __main__ - Step 127715: {'lr': 2.745593219081191e-05, 'samples': 24521280, 'steps': 127714, 'loss/train': 0.6231333613395691} 08/31/2021 12:23:25 - INFO - __main__ - Step 127716: {'lr': 2.7453514401764023e-05, 'samples': 24521472, 'steps': 127715, 'loss/train': 1.1481558084487915} 08/31/2021 12:23:27 - INFO - __main__ - Step 127717: {'lr': 2.7451096712992173e-05, 'samples': 24521664, 'steps': 127716, 'loss/train': 0.6340656876564026} 08/31/2021 12:23:27 - INFO - __main__ - Step 127718: {'lr': 2.744867912449739e-05, 'samples': 24521856, 'steps': 127717, 'loss/train': 0.9269693493843079} 08/31/2021 12:23:27 - INFO - __main__ - Step 127719: {'lr': 2.7446261636280777e-05, 'samples': 24522048, 'steps': 127718, 'loss/train': 0.8627325892448425} 08/31/2021 12:23:28 - INFO - __main__ - Step 127720: {'lr': 2.744384424834348e-05, 'samples': 24522240, 'steps': 127719, 'loss/train': 1.2913107872009277} 08/31/2021 12:23:28 - INFO - __main__ - Step 127721: {'lr': 2.7441426960686523e-05, 'samples': 24522432, 'steps': 127720, 'loss/train': 1.0622400045394897} 08/31/2021 12:23:30 - INFO - __main__ - Step 127722: {'lr': 2.7439009773311042e-05, 'samples': 24522624, 'steps': 127721, 'loss/train': 1.1147942543029785} 08/31/2021 12:23:31 - INFO - __main__ - Step 127723: {'lr': 2.7436592686218093e-05, 'samples': 24522816, 'steps': 127722, 'loss/train': 1.01043701171875} 08/31/2021 12:23:31 - INFO - __main__ - Step 127724: {'lr': 2.7434175699408786e-05, 'samples': 24523008, 'steps': 127723, 'loss/train': 0.8896768093109131} 08/31/2021 12:23:31 - INFO - __main__ - Step 127725: {'lr': 2.7431758812884206e-05, 'samples': 24523200, 'steps': 127724, 'loss/train': 1.5588839054107666} 08/31/2021 12:23:32 - INFO - __main__ - Step 127726: {'lr': 2.742934202664543e-05, 'samples': 24523392, 'steps': 127725, 'loss/train': 1.0176361799240112} 08/31/2021 12:23:32 - INFO - __main__ - Step 127727: {'lr': 2.7426925340693577e-05, 'samples': 24523584, 'steps': 127726, 'loss/train': 0.6946849226951599} 08/31/2021 12:23:34 - INFO - __main__ - Step 127728: {'lr': 2.742450875502972e-05, 'samples': 24523776, 'steps': 127727, 'loss/train': 0.39753687381744385} 08/31/2021 12:23:34 - INFO - __main__ - Step 127729: {'lr': 2.742209226965492e-05, 'samples': 24523968, 'steps': 127728, 'loss/train': 0.7059069871902466} 08/31/2021 12:23:34 - INFO - __main__ - Step 127730: {'lr': 2.7419675884570367e-05, 'samples': 24524160, 'steps': 127729, 'loss/train': 1.0043153762817383} 08/31/2021 12:23:35 - INFO - __main__ - Step 127731: {'lr': 2.7417259599777007e-05, 'samples': 24524352, 'steps': 127730, 'loss/train': 0.8786953091621399} 08/31/2021 12:23:35 - INFO - __main__ - Step 127732: {'lr': 2.7414843415276003e-05, 'samples': 24524544, 'steps': 127731, 'loss/train': 1.1047875881195068} 08/31/2021 12:23:35 - INFO - __main__ - Step 127733: {'lr': 2.741242733106844e-05, 'samples': 24524736, 'steps': 127732, 'loss/train': 1.064132571220398} 08/31/2021 12:23:37 - INFO - __main__ - Step 127734: {'lr': 2.7410011347155373e-05, 'samples': 24524928, 'steps': 127733, 'loss/train': 1.2269248962402344} 08/31/2021 12:23:37 - INFO - __main__ - Step 127735: {'lr': 2.7407595463537965e-05, 'samples': 24525120, 'steps': 127734, 'loss/train': 0.5967408418655396} 08/31/2021 12:23:38 - INFO - __main__ - Step 127736: {'lr': 2.7405179680217217e-05, 'samples': 24525312, 'steps': 127735, 'loss/train': 1.122274398803711} 08/31/2021 12:23:38 - INFO - __main__ - Step 127737: {'lr': 2.7402763997194298e-05, 'samples': 24525504, 'steps': 127736, 'loss/train': 2.0148704051971436} 08/31/2021 12:23:38 - INFO - __main__ - Step 127738: {'lr': 2.7400348414470227e-05, 'samples': 24525696, 'steps': 127737, 'loss/train': 1.111167073249817} 08/31/2021 12:23:40 - INFO - __main__ - Step 127739: {'lr': 2.739793293204615e-05, 'samples': 24525888, 'steps': 127738, 'loss/train': 1.4649056196212769} 08/31/2021 12:23:40 - INFO - __main__ - Step 127740: {'lr': 2.7395517549923116e-05, 'samples': 24526080, 'steps': 127739, 'loss/train': 1.0167509317398071} 08/31/2021 12:23:41 - INFO - __main__ - Step 127741: {'lr': 2.739310226810221e-05, 'samples': 24526272, 'steps': 127740, 'loss/train': 0.6218547224998474} 08/31/2021 12:23:41 - INFO - __main__ - Step 127742: {'lr': 2.739068708658457e-05, 'samples': 24526464, 'steps': 127741, 'loss/train': 1.0286681652069092} 08/31/2021 12:23:41 - INFO - __main__ - Step 127743: {'lr': 2.7388272005371222e-05, 'samples': 24526656, 'steps': 127742, 'loss/train': 0.6095077395439148} 08/31/2021 12:23:43 - INFO - __main__ - Step 127744: {'lr': 2.7385857024463362e-05, 'samples': 24526848, 'steps': 127743, 'loss/train': 1.1551746129989624} 08/31/2021 12:23:44 - INFO - __main__ - Step 127745: {'lr': 2.738344214386193e-05, 'samples': 24527040, 'steps': 127744, 'loss/train': 1.7559945583343506} 08/31/2021 12:23:44 - INFO - __main__ - Step 127746: {'lr': 2.7381027363568094e-05, 'samples': 24527232, 'steps': 127745, 'loss/train': 1.0602089166641235} 08/31/2021 12:23:44 - INFO - __main__ - Step 127747: {'lr': 2.7378612683582936e-05, 'samples': 24527424, 'steps': 127746, 'loss/train': 0.9649516940116882} 08/31/2021 12:23:45 - INFO - __main__ - Step 127748: {'lr': 2.7376198103907512e-05, 'samples': 24527616, 'steps': 127747, 'loss/train': 0.9311361312866211} 08/31/2021 12:23:46 - INFO - __main__ - Step 127749: {'lr': 2.7373783624542958e-05, 'samples': 24527808, 'steps': 127748, 'loss/train': 1.7367582321166992} 08/31/2021 12:23:47 - INFO - __main__ - Step 127750: {'lr': 2.7371369245490357e-05, 'samples': 24528000, 'steps': 127749, 'loss/train': 1.1168150901794434} 08/31/2021 12:23:47 - INFO - __main__ - Step 127751: {'lr': 2.7368954966750764e-05, 'samples': 24528192, 'steps': 127750, 'loss/train': 0.5194077491760254} 08/31/2021 12:23:48 - INFO - __main__ - Step 127752: {'lr': 2.736654078832529e-05, 'samples': 24528384, 'steps': 127751, 'loss/train': 0.8655303120613098} 08/31/2021 12:23:48 - INFO - __main__ - Step 127753: {'lr': 2.7364126710215014e-05, 'samples': 24528576, 'steps': 127752, 'loss/train': 1.6527631282806396} 08/31/2021 12:23:48 - INFO - __main__ - Step 127754: {'lr': 2.7361712732421023e-05, 'samples': 24528768, 'steps': 127753, 'loss/train': 1.0438313484191895} 08/31/2021 12:23:50 - INFO - __main__ - Step 127755: {'lr': 2.7359298854944396e-05, 'samples': 24528960, 'steps': 127754, 'loss/train': 1.1666913032531738} 08/31/2021 12:23:51 - INFO - __main__ - Step 127756: {'lr': 2.735688507778625e-05, 'samples': 24529152, 'steps': 127755, 'loss/train': 0.30515074729919434} 08/31/2021 12:23:51 - INFO - __main__ - Step 127757: {'lr': 2.7354471400947712e-05, 'samples': 24529344, 'steps': 127756, 'loss/train': 0.6759889721870422} 08/31/2021 12:23:51 - INFO - __main__ - Step 127758: {'lr': 2.735205782442976e-05, 'samples': 24529536, 'steps': 127757, 'loss/train': 0.8449047803878784} 08/31/2021 12:23:52 - INFO - __main__ - Step 127759: {'lr': 2.734964434823353e-05, 'samples': 24529728, 'steps': 127758, 'loss/train': 0.9342355728149414} 08/31/2021 12:23:53 - INFO - __main__ - Step 127760: {'lr': 2.7347230972360108e-05, 'samples': 24529920, 'steps': 127759, 'loss/train': 0.9906396269798279} 08/31/2021 12:23:54 - INFO - __main__ - Step 127761: {'lr': 2.7344817696810603e-05, 'samples': 24530112, 'steps': 127760, 'loss/train': 1.411024570465088} 08/31/2021 12:23:54 - INFO - __main__ - Step 127762: {'lr': 2.7342404521586096e-05, 'samples': 24530304, 'steps': 127761, 'loss/train': 1.495758056640625} 08/31/2021 12:23:55 - INFO - __main__ - Step 127763: {'lr': 2.733999144668764e-05, 'samples': 24530496, 'steps': 127762, 'loss/train': 2.2609312534332275} 08/31/2021 12:23:55 - INFO - __main__ - Step 127764: {'lr': 2.7337578472116348e-05, 'samples': 24530688, 'steps': 127763, 'loss/train': 0.9358375668525696} 08/31/2021 12:23:56 - INFO - __main__ - Step 127765: {'lr': 2.733516559787333e-05, 'samples': 24530880, 'steps': 127764, 'loss/train': 1.4742149114608765} 08/31/2021 12:23:57 - INFO - __main__ - Step 127766: {'lr': 2.733275282395964e-05, 'samples': 24531072, 'steps': 127765, 'loss/train': 1.0052669048309326} 08/31/2021 12:23:57 - INFO - __main__ - Step 127767: {'lr': 2.733034015037636e-05, 'samples': 24531264, 'steps': 127766, 'loss/train': 1.0082350969314575} 08/31/2021 12:23:58 - INFO - __main__ - Step 127768: {'lr': 2.7327927577124628e-05, 'samples': 24531456, 'steps': 127767, 'loss/train': 1.1570786237716675} 08/31/2021 12:23:58 - INFO - __main__ - Step 127769: {'lr': 2.732551510420547e-05, 'samples': 24531648, 'steps': 127768, 'loss/train': 1.489938735961914} 08/31/2021 12:23:58 - INFO - __main__ - Step 127770: {'lr': 2.7323102731620004e-05, 'samples': 24531840, 'steps': 127769, 'loss/train': 1.229895830154419} 08/31/2021 12:24:00 - INFO - __main__ - Step 127771: {'lr': 2.7320690459369356e-05, 'samples': 24532032, 'steps': 127770, 'loss/train': 1.372313141822815} 08/31/2021 12:24:01 - INFO - __main__ - Step 127772: {'lr': 2.7318278287454534e-05, 'samples': 24532224, 'steps': 127771, 'loss/train': 0.2963157892227173} 08/31/2021 12:24:01 - INFO - __main__ - Step 127773: {'lr': 2.7315866215876644e-05, 'samples': 24532416, 'steps': 127772, 'loss/train': 0.018080299720168114} 08/31/2021 12:24:01 - INFO - __main__ - Step 127774: {'lr': 2.73134542446368e-05, 'samples': 24532608, 'steps': 127773, 'loss/train': 1.72126305103302} 08/31/2021 12:24:02 - INFO - __main__ - Step 127775: {'lr': 2.731104237373605e-05, 'samples': 24532800, 'steps': 127774, 'loss/train': 0.9291210174560547} 08/31/2021 12:24:02 - INFO - __main__ - Step 127776: {'lr': 2.730863060317554e-05, 'samples': 24532992, 'steps': 127775, 'loss/train': 1.2754151821136475} 08/31/2021 12:24:04 - INFO - __main__ - Step 127777: {'lr': 2.7306218932956317e-05, 'samples': 24533184, 'steps': 127776, 'loss/train': 0.5791270732879639} 08/31/2021 12:24:04 - INFO - __main__ - Step 127778: {'lr': 2.730380736307947e-05, 'samples': 24533376, 'steps': 127777, 'loss/train': 0.08198866993188858} 08/31/2021 12:24:05 - INFO - __main__ - Step 127779: {'lr': 2.7301395893546104e-05, 'samples': 24533568, 'steps': 127778, 'loss/train': 1.7229329347610474} 08/31/2021 12:24:05 - INFO - __main__ - Step 127780: {'lr': 2.7298984524357278e-05, 'samples': 24533760, 'steps': 127779, 'loss/train': 0.41597744822502136} 08/31/2021 12:24:05 - INFO - __main__ - Step 127781: {'lr': 2.72965732555141e-05, 'samples': 24533952, 'steps': 127780, 'loss/train': 1.494132161140442} 08/31/2021 12:24:07 - INFO - __main__ - Step 127782: {'lr': 2.7294162087017626e-05, 'samples': 24534144, 'steps': 127781, 'loss/train': 1.1108648777008057} 08/31/2021 12:24:07 - INFO - __main__ - Step 127783: {'lr': 2.729175101886899e-05, 'samples': 24534336, 'steps': 127782, 'loss/train': 1.1543915271759033} 08/31/2021 12:24:08 - INFO - __main__ - Step 127784: {'lr': 2.728934005106931e-05, 'samples': 24534528, 'steps': 127783, 'loss/train': 1.325249433517456} 08/31/2021 12:24:08 - INFO - __main__ - Step 127785: {'lr': 2.7286929183619552e-05, 'samples': 24534720, 'steps': 127784, 'loss/train': 1.119673252105713} 08/31/2021 12:24:08 - INFO - __main__ - Step 127786: {'lr': 2.728451841652088e-05, 'samples': 24534912, 'steps': 127785, 'loss/train': 0.6555264592170715} 08/31/2021 12:24:10 - INFO - __main__ - Step 127787: {'lr': 2.7282107749774354e-05, 'samples': 24535104, 'steps': 127786, 'loss/train': 1.648876428604126} 08/31/2021 12:24:11 - INFO - __main__ - Step 127788: {'lr': 2.727969718338108e-05, 'samples': 24535296, 'steps': 127787, 'loss/train': 0.7257781028747559} 08/31/2021 12:24:11 - INFO - __main__ - Step 127789: {'lr': 2.7277286717342143e-05, 'samples': 24535488, 'steps': 127788, 'loss/train': 1.317873239517212} 08/31/2021 12:24:11 - INFO - __main__ - Step 127790: {'lr': 2.7274876351658623e-05, 'samples': 24535680, 'steps': 127789, 'loss/train': 1.0929722785949707} 08/31/2021 12:24:12 - INFO - __main__ - Step 127791: {'lr': 2.7272466086331604e-05, 'samples': 24535872, 'steps': 127790, 'loss/train': 0.9270573854446411} 08/31/2021 12:24:13 - INFO - __main__ - Step 127792: {'lr': 2.727005592136217e-05, 'samples': 24536064, 'steps': 127791, 'loss/train': 0.040641847997903824} 08/31/2021 12:24:14 - INFO - __main__ - Step 127793: {'lr': 2.72676458567514e-05, 'samples': 24536256, 'steps': 127792, 'loss/train': 1.905371069908142} 08/31/2021 12:24:14 - INFO - __main__ - Step 127794: {'lr': 2.7265235892500406e-05, 'samples': 24536448, 'steps': 127793, 'loss/train': 0.500027060508728} 08/31/2021 12:24:15 - INFO - __main__ - Step 127795: {'lr': 2.7262826028610273e-05, 'samples': 24536640, 'steps': 127794, 'loss/train': 0.03467907756567001} 08/31/2021 12:24:15 - INFO - __main__ - Step 127796: {'lr': 2.726041626508205e-05, 'samples': 24536832, 'steps': 127795, 'loss/train': 1.0294760465621948} 08/31/2021 12:24:15 - INFO - __main__ - Step 127797: {'lr': 2.725800660191691e-05, 'samples': 24537024, 'steps': 127796, 'loss/train': 0.5049868822097778} 08/31/2021 12:24:17 - INFO - __main__ - Step 127798: {'lr': 2.7255597039115814e-05, 'samples': 24537216, 'steps': 127797, 'loss/train': 0.9047576189041138} 08/31/2021 12:24:17 - INFO - __main__ - Step 127799: {'lr': 2.725318757667994e-05, 'samples': 24537408, 'steps': 127798, 'loss/train': 1.81851327419281} 08/31/2021 12:24:18 - INFO - __main__ - Step 127800: {'lr': 2.7250778214610305e-05, 'samples': 24537600, 'steps': 127799, 'loss/train': 1.1440411806106567} 08/31/2021 12:24:18 - INFO - __main__ - Step 127801: {'lr': 2.7248368952908055e-05, 'samples': 24537792, 'steps': 127800, 'loss/train': 1.4332389831542969} 08/31/2021 12:24:18 - INFO - __main__ - Step 127802: {'lr': 2.724595979157424e-05, 'samples': 24537984, 'steps': 127801, 'loss/train': 0.7205010056495667} 08/31/2021 12:24:20 - INFO - __main__ - Step 127803: {'lr': 2.7243550730609967e-05, 'samples': 24538176, 'steps': 127802, 'loss/train': 1.3860952854156494} 08/31/2021 12:24:20 - INFO - __main__ - Step 127804: {'lr': 2.7241141770016298e-05, 'samples': 24538368, 'steps': 127803, 'loss/train': 1.0528151988983154} 08/31/2021 12:24:21 - INFO - __main__ - Step 127805: {'lr': 2.723873290979434e-05, 'samples': 24538560, 'steps': 127804, 'loss/train': 1.1374469995498657} 08/31/2021 12:24:21 - INFO - __main__ - Step 127806: {'lr': 2.7236324149945175e-05, 'samples': 24538752, 'steps': 127805, 'loss/train': 1.080045461654663} 08/31/2021 12:24:21 - INFO - __main__ - Step 127807: {'lr': 2.7233915490469886e-05, 'samples': 24538944, 'steps': 127806, 'loss/train': 1.0054353475570679} 08/31/2021 12:24:24 - INFO - __main__ - Step 127808: {'lr': 2.7231506931369553e-05, 'samples': 24539136, 'steps': 127807, 'loss/train': 0.7158104777336121} 08/31/2021 12:24:24 - INFO - __main__ - Step 127809: {'lr': 2.7229098472645263e-05, 'samples': 24539328, 'steps': 127808, 'loss/train': 1.1927093267440796} 08/31/2021 12:24:24 - INFO - __main__ - Step 127810: {'lr': 2.7226690114298125e-05, 'samples': 24539520, 'steps': 127809, 'loss/train': 1.351447343826294} 08/31/2021 12:24:25 - INFO - __main__ - Step 127811: {'lr': 2.722428185632922e-05, 'samples': 24539712, 'steps': 127810, 'loss/train': 1.1440578699111938} 08/31/2021 12:24:25 - INFO - __main__ - Step 127812: {'lr': 2.7221873698739603e-05, 'samples': 24539904, 'steps': 127811, 'loss/train': 0.9887166023254395} 08/31/2021 12:24:27 - INFO - __main__ - Step 127813: {'lr': 2.7219465641530354e-05, 'samples': 24540096, 'steps': 127812, 'loss/train': 1.0211530923843384} 08/31/2021 12:24:27 - INFO - __main__ - Step 127814: {'lr': 2.7217057684702562e-05, 'samples': 24540288, 'steps': 127813, 'loss/train': 0.9982213377952576} 08/31/2021 12:24:28 - INFO - __main__ - Step 127815: {'lr': 2.7214649828257333e-05, 'samples': 24540480, 'steps': 127814, 'loss/train': 0.6239774823188782} 08/31/2021 12:24:28 - INFO - __main__ - Step 127816: {'lr': 2.7212242072195747e-05, 'samples': 24540672, 'steps': 127815, 'loss/train': 0.8610590696334839} 08/31/2021 12:24:28 - INFO - __main__ - Step 127817: {'lr': 2.7209834416518892e-05, 'samples': 24540864, 'steps': 127816, 'loss/train': 1.4064186811447144} 08/31/2021 12:24:29 - INFO - __main__ - Step 127818: {'lr': 2.7207426861227845e-05, 'samples': 24541056, 'steps': 127817, 'loss/train': 1.0853701829910278} 08/31/2021 12:24:30 - INFO - __main__ - Step 127819: {'lr': 2.7205019406323694e-05, 'samples': 24541248, 'steps': 127818, 'loss/train': 0.9937841296195984} 08/31/2021 12:24:31 - INFO - __main__ - Step 127820: {'lr': 2.720261205180752e-05, 'samples': 24541440, 'steps': 127819, 'loss/train': 1.1396808624267578} 08/31/2021 12:24:31 - INFO - __main__ - Step 127821: {'lr': 2.720020479768043e-05, 'samples': 24541632, 'steps': 127820, 'loss/train': 0.9969758987426758} 08/31/2021 12:24:31 - INFO - __main__ - Step 127822: {'lr': 2.7197797643943477e-05, 'samples': 24541824, 'steps': 127821, 'loss/train': 0.6767765879631042} 08/31/2021 12:24:32 - INFO - __main__ - Step 127823: {'lr': 2.719539059059775e-05, 'samples': 24542016, 'steps': 127822, 'loss/train': 1.152971625328064} 08/31/2021 12:24:33 - INFO - __main__ - Step 127824: {'lr': 2.7192983637644386e-05, 'samples': 24542208, 'steps': 127823, 'loss/train': 1.8066457509994507} 08/31/2021 12:24:34 - INFO - __main__ - Step 127825: {'lr': 2.7190576785084408e-05, 'samples': 24542400, 'steps': 127824, 'loss/train': 0.0182834230363369} 08/31/2021 12:24:34 - INFO - __main__ - Step 127826: {'lr': 2.7188170032918875e-05, 'samples': 24542592, 'steps': 127825, 'loss/train': 0.017097489908337593} 08/31/2021 12:24:35 - INFO - __main__ - Step 127827: {'lr': 2.7185763381148948e-05, 'samples': 24542784, 'steps': 127826, 'loss/train': 1.1181159019470215} 08/31/2021 12:24:35 - INFO - __main__ - Step 127828: {'lr': 2.7183356829775658e-05, 'samples': 24542976, 'steps': 127827, 'loss/train': 1.2322558164596558} 08/31/2021 12:24:35 - INFO - __main__ - Step 127829: {'lr': 2.7180950378800113e-05, 'samples': 24543168, 'steps': 127828, 'loss/train': 1.4761135578155518} 08/31/2021 12:24:37 - INFO - __main__ - Step 127830: {'lr': 2.7178544028223396e-05, 'samples': 24543360, 'steps': 127829, 'loss/train': 0.8372765183448792} 08/31/2021 12:24:38 - INFO - __main__ - Step 127831: {'lr': 2.717613777804659e-05, 'samples': 24543552, 'steps': 127830, 'loss/train': 1.2881635427474976} 08/31/2021 12:24:38 - INFO - __main__ - Step 127832: {'lr': 2.7173731628270804e-05, 'samples': 24543744, 'steps': 127831, 'loss/train': 0.6071122288703918} 08/31/2021 12:24:38 - INFO - __main__ - Step 127833: {'lr': 2.7171325578897065e-05, 'samples': 24543936, 'steps': 127832, 'loss/train': 0.4627515375614166} 08/31/2021 12:24:39 - INFO - __main__ - Step 127834: {'lr': 2.7168919629926485e-05, 'samples': 24544128, 'steps': 127833, 'loss/train': 1.332680106163025} 08/31/2021 12:24:40 - INFO - __main__ - Step 127835: {'lr': 2.7166513781360145e-05, 'samples': 24544320, 'steps': 127834, 'loss/train': 0.6535868048667908} 08/31/2021 12:24:41 - INFO - __main__ - Step 127836: {'lr': 2.716410803319916e-05, 'samples': 24544512, 'steps': 127835, 'loss/train': 1.0622800588607788} 08/31/2021 12:24:41 - INFO - __main__ - Step 127837: {'lr': 2.7161702385444575e-05, 'samples': 24544704, 'steps': 127836, 'loss/train': 0.945151150226593} 08/31/2021 12:24:41 - INFO - __main__ - Step 127838: {'lr': 2.7159296838097565e-05, 'samples': 24544896, 'steps': 127837, 'loss/train': 1.4349777698516846} 08/31/2021 12:24:42 - INFO - __main__ - Step 127839: {'lr': 2.7156891391159066e-05, 'samples': 24545088, 'steps': 127838, 'loss/train': 0.8809890151023865} 08/31/2021 12:24:43 - INFO - __main__ - Step 127840: {'lr': 2.715448604463022e-05, 'samples': 24545280, 'steps': 127839, 'loss/train': 1.3800002336502075} 08/31/2021 12:24:44 - INFO - __main__ - Step 127841: {'lr': 2.715208079851214e-05, 'samples': 24545472, 'steps': 127840, 'loss/train': 0.13693803548812866} 08/31/2021 12:24:44 - INFO - __main__ - Step 127842: {'lr': 2.7149675652805877e-05, 'samples': 24545664, 'steps': 127841, 'loss/train': 0.9385958909988403} 08/31/2021 12:24:45 - INFO - __main__ - Step 127843: {'lr': 2.7147270607512543e-05, 'samples': 24545856, 'steps': 127842, 'loss/train': 0.5486356019973755} 08/31/2021 12:24:45 - INFO - __main__ - Step 127844: {'lr': 2.7144865662633217e-05, 'samples': 24546048, 'steps': 127843, 'loss/train': 1.1142282485961914} 08/31/2021 12:24:47 - INFO - __main__ - Step 127845: {'lr': 2.7142460818168985e-05, 'samples': 24546240, 'steps': 127844, 'loss/train': 0.4330473244190216} 08/31/2021 12:24:47 - INFO - __main__ - Step 127846: {'lr': 2.71400560741209e-05, 'samples': 24546432, 'steps': 127845, 'loss/train': 1.0001333951950073} 08/31/2021 12:24:47 - INFO - __main__ - Step 127847: {'lr': 2.7137651430490074e-05, 'samples': 24546624, 'steps': 127846, 'loss/train': 1.0424158573150635} 08/31/2021 12:24:48 - INFO - __main__ - Step 127848: {'lr': 2.7135246887277586e-05, 'samples': 24546816, 'steps': 127847, 'loss/train': 0.7443348169326782} 08/31/2021 12:24:48 - INFO - __main__ - Step 127849: {'lr': 2.7132842444484497e-05, 'samples': 24547008, 'steps': 127848, 'loss/train': 1.311255693435669} 08/31/2021 12:24:49 - INFO - __main__ - Step 127850: {'lr': 2.7130438102111937e-05, 'samples': 24547200, 'steps': 127849, 'loss/train': 0.18047061562538147} 08/31/2021 12:24:50 - INFO - __main__ - Step 127851: {'lr': 2.7128033860160994e-05, 'samples': 24547392, 'steps': 127850, 'loss/train': 0.31575778126716614} 08/31/2021 12:24:50 - INFO - __main__ - Step 127852: {'lr': 2.7125629718632665e-05, 'samples': 24547584, 'steps': 127851, 'loss/train': 1.1361523866653442} 08/31/2021 12:24:51 - INFO - __main__ - Step 127853: {'lr': 2.712322567752812e-05, 'samples': 24547776, 'steps': 127852, 'loss/train': 1.8511731624603271} 08/31/2021 12:24:51 - INFO - __main__ - Step 127854: {'lr': 2.7120821736848378e-05, 'samples': 24547968, 'steps': 127853, 'loss/train': 1.482954502105713} 08/31/2021 12:24:53 - INFO - __main__ - Step 127855: {'lr': 2.7118417896594584e-05, 'samples': 24548160, 'steps': 127854, 'loss/train': 0.8753784894943237} 08/31/2021 12:24:53 - INFO - __main__ - Step 127856: {'lr': 2.711601415676776e-05, 'samples': 24548352, 'steps': 127855, 'loss/train': 0.15902704000473022} 08/31/2021 12:24:53 - INFO - __main__ - Step 127857: {'lr': 2.7113610517369047e-05, 'samples': 24548544, 'steps': 127856, 'loss/train': 1.145486831665039} 08/31/2021 12:24:54 - INFO - __main__ - Step 127858: {'lr': 2.7111206978399472e-05, 'samples': 24548736, 'steps': 127857, 'loss/train': 1.6469342708587646} 08/31/2021 12:24:54 - INFO - __main__ - Step 127859: {'lr': 2.710880353986017e-05, 'samples': 24548928, 'steps': 127858, 'loss/train': 0.5227428078651428} 08/31/2021 12:24:54 - INFO - __main__ - Step 127860: {'lr': 2.71064002017522e-05, 'samples': 24549120, 'steps': 127859, 'loss/train': 1.03214430809021} 08/31/2021 12:24:56 - INFO - __main__ - Step 127861: {'lr': 2.7103996964076643e-05, 'samples': 24549312, 'steps': 127860, 'loss/train': 1.0465303659439087} 08/31/2021 12:24:57 - INFO - __main__ - Step 127862: {'lr': 2.710159382683458e-05, 'samples': 24549504, 'steps': 127861, 'loss/train': 0.9319697022438049} 08/31/2021 12:24:57 - INFO - __main__ - Step 127863: {'lr': 2.7099190790027178e-05, 'samples': 24549696, 'steps': 127862, 'loss/train': 1.326040506362915} 08/31/2021 12:24:57 - INFO - __main__ - Step 127864: {'lr': 2.709678785365535e-05, 'samples': 24549888, 'steps': 127863, 'loss/train': 0.03920028731226921} 08/31/2021 12:24:58 - INFO - __main__ - Step 127865: {'lr': 2.7094385017720297e-05, 'samples': 24550080, 'steps': 127864, 'loss/train': 1.023303747177124} 08/31/2021 12:25:00 - INFO - __main__ - Step 127866: {'lr': 2.7091982282223065e-05, 'samples': 24550272, 'steps': 127865, 'loss/train': 1.1335150003433228} 08/31/2021 12:25:01 - INFO - __main__ - Step 127867: {'lr': 2.708957964716474e-05, 'samples': 24550464, 'steps': 127866, 'loss/train': 1.1754518747329712} 08/31/2021 12:25:01 - INFO - __main__ - Step 127868: {'lr': 2.7087177112546434e-05, 'samples': 24550656, 'steps': 127867, 'loss/train': 1.3718459606170654} 08/31/2021 12:25:01 - INFO - __main__ - Step 127869: {'lr': 2.70847746783692e-05, 'samples': 24550848, 'steps': 127868, 'loss/train': 0.4368383288383484} 08/31/2021 12:25:02 - INFO - __main__ - Step 127870: {'lr': 2.7082372344634095e-05, 'samples': 24551040, 'steps': 127869, 'loss/train': 1.6017323732376099} 08/31/2021 12:25:02 - INFO - __main__ - Step 127871: {'lr': 2.7079970111342277e-05, 'samples': 24551232, 'steps': 127870, 'loss/train': 0.6571933627128601} 08/31/2021 12:25:04 - INFO - __main__ - Step 127872: {'lr': 2.7077567978494754e-05, 'samples': 24551424, 'steps': 127871, 'loss/train': 0.01663084514439106} 08/31/2021 12:25:04 - INFO - __main__ - Step 127873: {'lr': 2.707516594609269e-05, 'samples': 24551616, 'steps': 127872, 'loss/train': 1.3912090063095093} 08/31/2021 12:25:04 - INFO - __main__ - Step 127874: {'lr': 2.707276401413708e-05, 'samples': 24551808, 'steps': 127873, 'loss/train': 0.48898541927337646} 08/31/2021 12:25:05 - INFO - __main__ - Step 127875: {'lr': 2.7070362182629038e-05, 'samples': 24552000, 'steps': 127874, 'loss/train': 1.141385555267334} 08/31/2021 12:25:05 - INFO - __main__ - Step 127876: {'lr': 2.7067960451569645e-05, 'samples': 24552192, 'steps': 127875, 'loss/train': 1.2767267227172852} 08/31/2021 12:25:07 - INFO - __main__ - Step 127877: {'lr': 2.7065558820959985e-05, 'samples': 24552384, 'steps': 127876, 'loss/train': 1.0999293327331543} 08/31/2021 12:25:07 - INFO - __main__ - Step 127878: {'lr': 2.7063157290801167e-05, 'samples': 24552576, 'steps': 127877, 'loss/train': 1.125583291053772} 08/31/2021 12:25:07 - INFO - __main__ - Step 127879: {'lr': 2.7060755861094243e-05, 'samples': 24552768, 'steps': 127878, 'loss/train': 0.4427562952041626} 08/31/2021 12:25:08 - INFO - __main__ - Step 127880: {'lr': 2.7058354531840274e-05, 'samples': 24552960, 'steps': 127879, 'loss/train': 1.5550061464309692} 08/31/2021 12:25:08 - INFO - __main__ - Step 127881: {'lr': 2.7055953303040394e-05, 'samples': 24553152, 'steps': 127880, 'loss/train': 1.1545119285583496} 08/31/2021 12:25:08 - INFO - __main__ - Step 127882: {'lr': 2.7053552174695656e-05, 'samples': 24553344, 'steps': 127881, 'loss/train': 1.3246474266052246} 08/31/2021 12:25:10 - INFO - __main__ - Step 127883: {'lr': 2.7051151146807173e-05, 'samples': 24553536, 'steps': 127882, 'loss/train': 0.13944308459758759} 08/31/2021 12:25:10 - INFO - __main__ - Step 127884: {'lr': 2.704875021937603e-05, 'samples': 24553728, 'steps': 127883, 'loss/train': 1.210443139076233} 08/31/2021 12:25:11 - INFO - __main__ - Step 127885: {'lr': 2.704634939240322e-05, 'samples': 24553920, 'steps': 127884, 'loss/train': 1.3577208518981934} 08/31/2021 12:25:11 - INFO - __main__ - Step 127886: {'lr': 2.7043948665889885e-05, 'samples': 24554112, 'steps': 127885, 'loss/train': 0.8537651896476746} 08/31/2021 12:25:11 - INFO - __main__ - Step 127887: {'lr': 2.7041548039837105e-05, 'samples': 24554304, 'steps': 127886, 'loss/train': 1.2200047969818115} 08/31/2021 12:25:13 - INFO - __main__ - Step 127888: {'lr': 2.7039147514245993e-05, 'samples': 24554496, 'steps': 127887, 'loss/train': 1.7146967649459839} 08/31/2021 12:25:13 - INFO - __main__ - Step 127889: {'lr': 2.7036747089117577e-05, 'samples': 24554688, 'steps': 127888, 'loss/train': 0.9493033289909363} 08/31/2021 12:25:14 - INFO - __main__ - Step 127890: {'lr': 2.703434676445296e-05, 'samples': 24554880, 'steps': 127889, 'loss/train': 1.57619309425354} 08/31/2021 12:25:14 - INFO - __main__ - Step 127891: {'lr': 2.7031946540253233e-05, 'samples': 24555072, 'steps': 127890, 'loss/train': 1.070142149925232} 08/31/2021 12:25:14 - INFO - __main__ - Step 127892: {'lr': 2.7029546416519445e-05, 'samples': 24555264, 'steps': 127891, 'loss/train': 0.6576780676841736} 08/31/2021 12:25:16 - INFO - __main__ - Step 127893: {'lr': 2.702714639325274e-05, 'samples': 24555456, 'steps': 127892, 'loss/train': 0.35417431592941284} 08/31/2021 12:25:17 - INFO - __main__ - Step 127894: {'lr': 2.702474647045414e-05, 'samples': 24555648, 'steps': 127893, 'loss/train': 1.4235750436782837} 08/31/2021 12:25:17 - INFO - __main__ - Step 127895: {'lr': 2.7022346648124806e-05, 'samples': 24555840, 'steps': 127894, 'loss/train': 1.2681248188018799} 08/31/2021 12:25:17 - INFO - __main__ - Step 127896: {'lr': 2.701994692626572e-05, 'samples': 24556032, 'steps': 127895, 'loss/train': 1.1589232683181763} 08/31/2021 12:25:18 - INFO - __main__ - Step 127897: {'lr': 2.701754730487799e-05, 'samples': 24556224, 'steps': 127896, 'loss/train': 0.9820989966392517} 08/31/2021 12:25:18 - INFO - __main__ - Step 127898: {'lr': 2.7015147783962718e-05, 'samples': 24556416, 'steps': 127897, 'loss/train': 1.687895655632019} 08/31/2021 12:25:20 - INFO - __main__ - Step 127899: {'lr': 2.7012748363520996e-05, 'samples': 24556608, 'steps': 127898, 'loss/train': 0.6262807846069336} 08/31/2021 12:25:20 - INFO - __main__ - Step 127900: {'lr': 2.7010349043553874e-05, 'samples': 24556800, 'steps': 127899, 'loss/train': 1.431890606880188} 08/31/2021 12:25:20 - INFO - __main__ - Step 127901: {'lr': 2.7007949824062434e-05, 'samples': 24556992, 'steps': 127900, 'loss/train': 1.0192527770996094} 08/31/2021 12:25:21 - INFO - __main__ - Step 127902: {'lr': 2.7005550705047787e-05, 'samples': 24557184, 'steps': 127901, 'loss/train': 0.9361275434494019} 08/31/2021 12:25:21 - INFO - __main__ - Step 127903: {'lr': 2.700315168651099e-05, 'samples': 24557376, 'steps': 127902, 'loss/train': 1.2379975318908691} 08/31/2021 12:25:22 - INFO - __main__ - Step 127904: {'lr': 2.700075276845315e-05, 'samples': 24557568, 'steps': 127903, 'loss/train': 0.24907277524471283} 08/31/2021 12:25:23 - INFO - __main__ - Step 127905: {'lr': 2.6998353950875297e-05, 'samples': 24557760, 'steps': 127904, 'loss/train': 1.52702796459198} 08/31/2021 12:25:23 - INFO - __main__ - Step 127906: {'lr': 2.6995955233778624e-05, 'samples': 24557952, 'steps': 127905, 'loss/train': 1.5429786443710327} 08/31/2021 12:25:24 - INFO - __main__ - Step 127907: {'lr': 2.6993556617164074e-05, 'samples': 24558144, 'steps': 127906, 'loss/train': 0.9835460186004639} 08/31/2021 12:25:24 - INFO - __main__ - Step 127908: {'lr': 2.699115810103278e-05, 'samples': 24558336, 'steps': 127907, 'loss/train': 1.02785325050354} 08/31/2021 12:25:25 - INFO - __main__ - Step 127909: {'lr': 2.6988759685385833e-05, 'samples': 24558528, 'steps': 127908, 'loss/train': 0.10985877364873886} 08/31/2021 12:25:26 - INFO - __main__ - Step 127910: {'lr': 2.698636137022431e-05, 'samples': 24558720, 'steps': 127909, 'loss/train': 1.2127602100372314} 08/31/2021 12:25:26 - INFO - __main__ - Step 127911: {'lr': 2.6983963155549296e-05, 'samples': 24558912, 'steps': 127910, 'loss/train': 0.14466239511966705} 08/31/2021 12:25:27 - INFO - __main__ - Step 127912: {'lr': 2.6981565041361873e-05, 'samples': 24559104, 'steps': 127911, 'loss/train': 1.2865277528762817} 08/31/2021 12:25:27 - INFO - __main__ - Step 127913: {'lr': 2.6979167027663094e-05, 'samples': 24559296, 'steps': 127912, 'loss/train': 1.135999083518982} 08/31/2021 12:25:28 - INFO - __main__ - Step 127914: {'lr': 2.697676911445407e-05, 'samples': 24559488, 'steps': 127913, 'loss/train': 1.6191202402114868} 08/31/2021 12:25:29 - INFO - __main__ - Step 127915: {'lr': 2.6974371301735885e-05, 'samples': 24559680, 'steps': 127914, 'loss/train': 1.6346487998962402} 08/31/2021 12:25:29 - INFO - __main__ - Step 127916: {'lr': 2.697197358950959e-05, 'samples': 24559872, 'steps': 127915, 'loss/train': 1.5931434631347656} 08/31/2021 12:25:30 - INFO - __main__ - Step 127917: {'lr': 2.6969575977776272e-05, 'samples': 24560064, 'steps': 127916, 'loss/train': 1.3466154336929321} 08/31/2021 12:25:30 - INFO - __main__ - Step 127918: {'lr': 2.6967178466537095e-05, 'samples': 24560256, 'steps': 127917, 'loss/train': 0.41319382190704346} 08/31/2021 12:25:32 - INFO - __main__ - Step 127919: {'lr': 2.6964781055793004e-05, 'samples': 24560448, 'steps': 127918, 'loss/train': 1.220940113067627} 08/31/2021 12:25:32 - INFO - __main__ - Step 127920: {'lr': 2.696238374554516e-05, 'samples': 24560640, 'steps': 127919, 'loss/train': 1.222179651260376} 08/31/2021 12:25:33 - INFO - __main__ - Step 127921: {'lr': 2.6959986535794595e-05, 'samples': 24560832, 'steps': 127920, 'loss/train': 0.9230613112449646} 08/31/2021 12:25:33 - INFO - __main__ - Step 127922: {'lr': 2.6957589426542445e-05, 'samples': 24561024, 'steps': 127921, 'loss/train': 1.0503653287887573} 08/31/2021 12:25:33 - INFO - __main__ - Step 127923: {'lr': 2.6955192417789735e-05, 'samples': 24561216, 'steps': 127922, 'loss/train': 1.5614044666290283} 08/31/2021 12:25:35 - INFO - __main__ - Step 127924: {'lr': 2.695279550953761e-05, 'samples': 24561408, 'steps': 127923, 'loss/train': 0.5918868184089661} 08/31/2021 12:25:35 - INFO - __main__ - Step 127925: {'lr': 2.6950398701787088e-05, 'samples': 24561600, 'steps': 127924, 'loss/train': 1.1867681741714478} 08/31/2021 12:25:36 - INFO - __main__ - Step 127926: {'lr': 2.6948001994539283e-05, 'samples': 24561792, 'steps': 127925, 'loss/train': 1.4044499397277832} 08/31/2021 12:25:36 - INFO - __main__ - Step 127927: {'lr': 2.6945605387795253e-05, 'samples': 24561984, 'steps': 127926, 'loss/train': 1.1213796138763428} 08/31/2021 12:25:36 - INFO - __main__ - Step 127928: {'lr': 2.6943208881556104e-05, 'samples': 24562176, 'steps': 127927, 'loss/train': 1.1184085607528687} 08/31/2021 12:25:38 - INFO - __main__ - Step 127929: {'lr': 2.694081247582289e-05, 'samples': 24562368, 'steps': 127928, 'loss/train': 1.0415102243423462} 08/31/2021 12:25:38 - INFO - __main__ - Step 127930: {'lr': 2.6938416170596725e-05, 'samples': 24562560, 'steps': 127929, 'loss/train': 1.2755311727523804} 08/31/2021 12:25:39 - INFO - __main__ - Step 127931: {'lr': 2.6936019965878662e-05, 'samples': 24562752, 'steps': 127930, 'loss/train': 0.728635847568512} 08/31/2021 12:25:39 - INFO - __main__ - Step 127932: {'lr': 2.693362386166981e-05, 'samples': 24562944, 'steps': 127931, 'loss/train': 1.3135650157928467} 08/31/2021 12:25:39 - INFO - __main__ - Step 127933: {'lr': 2.6931227857971196e-05, 'samples': 24563136, 'steps': 127932, 'loss/train': 1.0180919170379639} 08/31/2021 12:25:40 - INFO - __main__ - Step 127934: {'lr': 2.6928831954783934e-05, 'samples': 24563328, 'steps': 127933, 'loss/train': 1.3487948179244995} 08/31/2021 12:25:41 - INFO - __main__ - Step 127935: {'lr': 2.69264361521091e-05, 'samples': 24563520, 'steps': 127934, 'loss/train': 0.7517749071121216} 08/31/2021 12:25:42 - INFO - __main__ - Step 127936: {'lr': 2.6924040449947755e-05, 'samples': 24563712, 'steps': 127935, 'loss/train': 0.02860945463180542} 08/31/2021 12:25:42 - INFO - __main__ - Step 127937: {'lr': 2.6921644848301007e-05, 'samples': 24563904, 'steps': 127936, 'loss/train': 1.118308186531067} 08/31/2021 12:25:42 - INFO - __main__ - Step 127938: {'lr': 2.6919249347169937e-05, 'samples': 24564096, 'steps': 127937, 'loss/train': 0.7777813076972961} 08/31/2021 12:25:43 - INFO - __main__ - Step 127939: {'lr': 2.6916853946555576e-05, 'samples': 24564288, 'steps': 127938, 'loss/train': 0.8363321423530579} 08/31/2021 12:25:44 - INFO - __main__ - Step 127940: {'lr': 2.6914458646459055e-05, 'samples': 24564480, 'steps': 127939, 'loss/train': 1.1736496686935425} 08/31/2021 12:25:45 - INFO - __main__ - Step 127941: {'lr': 2.6912063446881435e-05, 'samples': 24564672, 'steps': 127940, 'loss/train': 1.5038623809814453} 08/31/2021 12:25:45 - INFO - __main__ - Step 127942: {'lr': 2.6909668347823824e-05, 'samples': 24564864, 'steps': 127941, 'loss/train': 0.9282258152961731} 08/31/2021 12:25:45 - INFO - __main__ - Step 127943: {'lr': 2.6907273349287248e-05, 'samples': 24565056, 'steps': 127942, 'loss/train': 1.1534128189086914} 08/31/2021 12:25:46 - INFO - __main__ - Step 127944: {'lr': 2.690487845127282e-05, 'samples': 24565248, 'steps': 127943, 'loss/train': 1.1061168909072876} 08/31/2021 12:25:47 - INFO - __main__ - Step 127945: {'lr': 2.6902483653781644e-05, 'samples': 24565440, 'steps': 127944, 'loss/train': 0.7859259843826294} 08/31/2021 12:25:48 - INFO - __main__ - Step 127946: {'lr': 2.6900088956814727e-05, 'samples': 24565632, 'steps': 127945, 'loss/train': 1.067828893661499} 08/31/2021 12:25:48 - INFO - __main__ - Step 127947: {'lr': 2.6897694360373175e-05, 'samples': 24565824, 'steps': 127946, 'loss/train': 1.0047874450683594} 08/31/2021 12:25:48 - INFO - __main__ - Step 127948: {'lr': 2.68952998644581e-05, 'samples': 24566016, 'steps': 127947, 'loss/train': 0.5020110607147217} 08/31/2021 12:25:49 - INFO - __main__ - Step 127949: {'lr': 2.6892905469070554e-05, 'samples': 24566208, 'steps': 127948, 'loss/train': 0.5091714859008789} 08/31/2021 12:25:51 - INFO - __main__ - Step 127950: {'lr': 2.6890511174211624e-05, 'samples': 24566400, 'steps': 127949, 'loss/train': 1.920092225074768} 08/31/2021 12:25:51 - INFO - __main__ - Step 127951: {'lr': 2.688811697988239e-05, 'samples': 24566592, 'steps': 127950, 'loss/train': 1.145453929901123} 08/31/2021 12:25:51 - INFO - __main__ - Step 127952: {'lr': 2.6885722886083903e-05, 'samples': 24566784, 'steps': 127951, 'loss/train': 0.028429381549358368} 08/31/2021 12:25:52 - INFO - __main__ - Step 127953: {'lr': 2.6883328892817305e-05, 'samples': 24566976, 'steps': 127952, 'loss/train': 0.7880368828773499} 08/31/2021 12:25:52 - INFO - __main__ - Step 127954: {'lr': 2.6880935000083597e-05, 'samples': 24567168, 'steps': 127953, 'loss/train': 0.7080494165420532} 08/31/2021 12:25:53 - INFO - __main__ - Step 127955: {'lr': 2.6878541207883938e-05, 'samples': 24567360, 'steps': 127954, 'loss/train': 0.9827033281326294} 08/31/2021 12:25:54 - INFO - __main__ - Step 127956: {'lr': 2.6876147516219334e-05, 'samples': 24567552, 'steps': 127955, 'loss/train': 0.029269041493535042} 08/31/2021 12:25:54 - INFO - __main__ - Step 127957: {'lr': 2.6873753925090894e-05, 'samples': 24567744, 'steps': 127956, 'loss/train': 0.588756263256073} 08/31/2021 12:25:55 - INFO - __main__ - Step 127958: {'lr': 2.6871360434499725e-05, 'samples': 24567936, 'steps': 127957, 'loss/train': 2.0346782207489014} 08/31/2021 12:25:55 - INFO - __main__ - Step 127959: {'lr': 2.686896704444691e-05, 'samples': 24568128, 'steps': 127958, 'loss/train': 1.234499216079712} 08/31/2021 12:25:56 - INFO - __main__ - Step 127960: {'lr': 2.6866573754933426e-05, 'samples': 24568320, 'steps': 127959, 'loss/train': 0.7619072794914246} 08/31/2021 12:25:57 - INFO - __main__ - Step 127961: {'lr': 2.686418056596046e-05, 'samples': 24568512, 'steps': 127960, 'loss/train': 1.5388315916061401} 08/31/2021 12:25:58 - INFO - __main__ - Step 127962: {'lr': 2.6861787477529016e-05, 'samples': 24568704, 'steps': 127961, 'loss/train': 1.2052668333053589} 08/31/2021 12:25:58 - INFO - __main__ - Step 127963: {'lr': 2.6859394489640225e-05, 'samples': 24568896, 'steps': 127962, 'loss/train': 1.0224859714508057} 08/31/2021 12:25:58 - INFO - __main__ - Step 127964: {'lr': 2.685700160229515e-05, 'samples': 24569088, 'steps': 127963, 'loss/train': 0.5219686627388} 08/31/2021 12:25:59 - INFO - __main__ - Step 127965: {'lr': 2.685460881549487e-05, 'samples': 24569280, 'steps': 127964, 'loss/train': 0.7551433444023132} 08/31/2021 12:26:00 - INFO - __main__ - Step 127966: {'lr': 2.6852216129240437e-05, 'samples': 24569472, 'steps': 127965, 'loss/train': 1.3428599834442139} 08/31/2021 12:26:01 - INFO - __main__ - Step 127967: {'lr': 2.6849823543532963e-05, 'samples': 24569664, 'steps': 127966, 'loss/train': 0.8265788555145264} 08/31/2021 12:26:01 - INFO - __main__ - Step 127968: {'lr': 2.6847431058373534e-05, 'samples': 24569856, 'steps': 127967, 'loss/train': 1.5487844944000244} 08/31/2021 12:26:01 - INFO - __main__ - Step 127969: {'lr': 2.684503867376317e-05, 'samples': 24570048, 'steps': 127968, 'loss/train': 1.0437736511230469} 08/31/2021 12:26:02 - INFO - __main__ - Step 127970: {'lr': 2.684264638970302e-05, 'samples': 24570240, 'steps': 127969, 'loss/train': 1.0083671808242798} 08/31/2021 12:26:04 - INFO - __main__ - Step 127971: {'lr': 2.6840254206194127e-05, 'samples': 24570432, 'steps': 127970, 'loss/train': 1.2476255893707275} 08/31/2021 12:26:04 - INFO - __main__ - Step 127972: {'lr': 2.6837862123237634e-05, 'samples': 24570624, 'steps': 127971, 'loss/train': 0.5048549175262451} 08/31/2021 12:26:04 - INFO - __main__ - Step 127973: {'lr': 2.6835470140834483e-05, 'samples': 24570816, 'steps': 127972, 'loss/train': 1.491449236869812} 08/31/2021 12:26:05 - INFO - __main__ - Step 127974: {'lr': 2.6833078258985815e-05, 'samples': 24571008, 'steps': 127973, 'loss/train': 0.3416673541069031} 08/31/2021 12:26:05 - INFO - __main__ - Step 127975: {'lr': 2.683068647769274e-05, 'samples': 24571200, 'steps': 127974, 'loss/train': 0.741439700126648} 08/31/2021 12:26:07 - INFO - __main__ - Step 127976: {'lr': 2.682829479695631e-05, 'samples': 24571392, 'steps': 127975, 'loss/train': 0.8948115706443787} 08/31/2021 12:26:08 - INFO - __main__ - Step 127977: {'lr': 2.682590321677761e-05, 'samples': 24571584, 'steps': 127976, 'loss/train': 1.3631798028945923} 08/31/2021 12:26:08 - INFO - __main__ - Step 127978: {'lr': 2.682351173715772e-05, 'samples': 24571776, 'steps': 127977, 'loss/train': 1.2025452852249146} 08/31/2021 12:26:08 - INFO - __main__ - Step 127979: {'lr': 2.6821120358097694e-05, 'samples': 24571968, 'steps': 127978, 'loss/train': 0.024744125083088875} 08/31/2021 12:26:09 - INFO - __main__ - Step 127980: {'lr': 2.6818729079598648e-05, 'samples': 24572160, 'steps': 127979, 'loss/train': 0.2257481813430786} 08/31/2021 12:26:10 - INFO - __main__ - Step 127981: {'lr': 2.6816337901661603e-05, 'samples': 24572352, 'steps': 127980, 'loss/train': 1.5504471063613892} 08/31/2021 12:26:11 - INFO - __main__ - Step 127982: {'lr': 2.68139468242877e-05, 'samples': 24572544, 'steps': 127981, 'loss/train': 0.7253997325897217} 08/31/2021 12:26:11 - INFO - __main__ - Step 127983: {'lr': 2.681155584747799e-05, 'samples': 24572736, 'steps': 127982, 'loss/train': 1.3504170179367065} 08/31/2021 12:26:11 - INFO - __main__ - Step 127984: {'lr': 2.6809164971233536e-05, 'samples': 24572928, 'steps': 127983, 'loss/train': 0.9873936772346497} 08/31/2021 12:26:12 - INFO - __main__ - Step 127985: {'lr': 2.680677419555544e-05, 'samples': 24573120, 'steps': 127984, 'loss/train': 1.1330583095550537} 08/31/2021 12:26:14 - INFO - __main__ - Step 127986: {'lr': 2.6804383520444812e-05, 'samples': 24573312, 'steps': 127985, 'loss/train': 1.0430718660354614} 08/31/2021 12:26:14 - INFO - __main__ - Step 127987: {'lr': 2.680199294590263e-05, 'samples': 24573504, 'steps': 127986, 'loss/train': 1.3117564916610718} 08/31/2021 12:26:14 - INFO - __main__ - Step 127988: {'lr': 2.679960247193003e-05, 'samples': 24573696, 'steps': 127987, 'loss/train': 1.0874015092849731} 08/31/2021 12:26:15 - INFO - __main__ - Step 127989: {'lr': 2.679721209852809e-05, 'samples': 24573888, 'steps': 127988, 'loss/train': 1.3102773427963257} 08/31/2021 12:26:15 - INFO - __main__ - Step 127990: {'lr': 2.6794821825697895e-05, 'samples': 24574080, 'steps': 127989, 'loss/train': 0.941106915473938} 08/31/2021 12:26:15 - INFO - __main__ - Step 127991: {'lr': 2.6792431653440473e-05, 'samples': 24574272, 'steps': 127990, 'loss/train': 0.6807027459144592} 08/31/2021 12:26:17 - INFO - __main__ - Step 127992: {'lr': 2.6790041581756965e-05, 'samples': 24574464, 'steps': 127991, 'loss/train': 1.1366883516311646} 08/31/2021 12:26:17 - INFO - __main__ - Step 127993: {'lr': 2.6787651610648417e-05, 'samples': 24574656, 'steps': 127992, 'loss/train': 1.4050127267837524} 08/31/2021 12:26:18 - INFO - __main__ - Step 127994: {'lr': 2.678526174011589e-05, 'samples': 24574848, 'steps': 127993, 'loss/train': 1.0710053443908691} 08/31/2021 12:26:18 - INFO - __main__ - Step 127995: {'lr': 2.6782871970160494e-05, 'samples': 24575040, 'steps': 127994, 'loss/train': 1.0545339584350586} 08/31/2021 12:26:19 - INFO - __main__ - Step 127996: {'lr': 2.6780482300783283e-05, 'samples': 24575232, 'steps': 127995, 'loss/train': 0.20565351843833923} 08/31/2021 12:26:20 - INFO - __main__ - Step 127997: {'lr': 2.6778092731985366e-05, 'samples': 24575424, 'steps': 127996, 'loss/train': 0.2373465895652771} 08/31/2021 12:26:21 - INFO - __main__ - Step 127998: {'lr': 2.677570326376777e-05, 'samples': 24575616, 'steps': 127997, 'loss/train': 1.4285016059875488} 08/31/2021 12:26:21 - INFO - __main__ - Step 127999: {'lr': 2.677331389613166e-05, 'samples': 24575808, 'steps': 127998, 'loss/train': 0.5591681599617004} 08/31/2021 12:26:21 - INFO - __main__ - Step 128000: {'lr': 2.6770924629077987e-05, 'samples': 24576000, 'steps': 127999, 'loss/train': 1.5392731428146362} 08/31/2021 12:26:22 - INFO - __main__ - Step 128001: {'lr': 2.6768535462607907e-05, 'samples': 24576192, 'steps': 128000, 'loss/train': 1.106195092201233} 08/31/2021 12:26:22 - INFO - __main__ - Step 128002: {'lr': 2.676614639672248e-05, 'samples': 24576384, 'steps': 128001, 'loss/train': 0.14737625420093536} 08/31/2021 12:26:23 - INFO - __main__ - Step 128003: {'lr': 2.676375743142276e-05, 'samples': 24576576, 'steps': 128002, 'loss/train': 0.1927085667848587} 08/31/2021 12:26:24 - INFO - __main__ - Step 128004: {'lr': 2.676136856670988e-05, 'samples': 24576768, 'steps': 128003, 'loss/train': 1.2335556745529175} 08/31/2021 12:26:24 - INFO - __main__ - Step 128005: {'lr': 2.6758979802584848e-05, 'samples': 24576960, 'steps': 128004, 'loss/train': 0.6571184992790222} 08/31/2021 12:26:25 - INFO - __main__ - Step 128006: {'lr': 2.6756591139048796e-05, 'samples': 24577152, 'steps': 128005, 'loss/train': 1.3925573825836182} 08/31/2021 12:26:25 - INFO - __main__ - Step 128007: {'lr': 2.6754202576102782e-05, 'samples': 24577344, 'steps': 128006, 'loss/train': 1.3994697332382202} 08/31/2021 12:26:26 - INFO - __main__ - Step 128008: {'lr': 2.6751814113747887e-05, 'samples': 24577536, 'steps': 128007, 'loss/train': 1.3885525465011597} 08/31/2021 12:26:27 - INFO - __main__ - Step 128009: {'lr': 2.674942575198516e-05, 'samples': 24577728, 'steps': 128008, 'loss/train': 0.040081460028886795} 08/31/2021 12:26:27 - INFO - __main__ - Step 128010: {'lr': 2.6747037490815695e-05, 'samples': 24577920, 'steps': 128009, 'loss/train': 1.6512248516082764} 08/31/2021 12:26:28 - INFO - __main__ - Step 128011: {'lr': 2.6744649330240567e-05, 'samples': 24578112, 'steps': 128010, 'loss/train': 0.9628117680549622} 08/31/2021 12:26:28 - INFO - __main__ - Step 128012: {'lr': 2.674226127026086e-05, 'samples': 24578304, 'steps': 128011, 'loss/train': 0.737774670124054} 08/31/2021 12:26:30 - INFO - __main__ - Step 128013: {'lr': 2.673987331087771e-05, 'samples': 24578496, 'steps': 128012, 'loss/train': 1.2615206241607666} 08/31/2021 12:26:30 - INFO - __main__ - Step 128014: {'lr': 2.6737485452092064e-05, 'samples': 24578688, 'steps': 128013, 'loss/train': 1.309565544128418} 08/31/2021 12:26:31 - INFO - __main__ - Step 128015: {'lr': 2.673509769390506e-05, 'samples': 24578880, 'steps': 128014, 'loss/train': 0.7488287091255188} 08/31/2021 12:26:31 - INFO - __main__ - Step 128016: {'lr': 2.6732710036317804e-05, 'samples': 24579072, 'steps': 128015, 'loss/train': 0.05746966600418091} 08/31/2021 12:26:31 - INFO - __main__ - Step 128017: {'lr': 2.6730322479331297e-05, 'samples': 24579264, 'steps': 128016, 'loss/train': 0.8012877702713013} 08/31/2021 12:26:33 - INFO - __main__ - Step 128018: {'lr': 2.672793502294671e-05, 'samples': 24579456, 'steps': 128017, 'loss/train': 0.7656237483024597} 08/31/2021 12:26:33 - INFO - __main__ - Step 128019: {'lr': 2.6725547667165035e-05, 'samples': 24579648, 'steps': 128018, 'loss/train': 1.619171142578125} 08/31/2021 12:26:34 - INFO - __main__ - Step 128020: {'lr': 2.6723160411987385e-05, 'samples': 24579840, 'steps': 128019, 'loss/train': 1.28300142288208} 08/31/2021 12:26:34 - INFO - __main__ - Step 128021: {'lr': 2.6720773257414844e-05, 'samples': 24580032, 'steps': 128020, 'loss/train': 0.9857181310653687} 08/31/2021 12:26:34 - INFO - __main__ - Step 128022: {'lr': 2.671838620344849e-05, 'samples': 24580224, 'steps': 128021, 'loss/train': 1.2020609378814697} 08/31/2021 12:26:36 - INFO - __main__ - Step 128023: {'lr': 2.6715999250089358e-05, 'samples': 24580416, 'steps': 128022, 'loss/train': 1.3263251781463623} 08/31/2021 12:26:36 - INFO - __main__ - Step 128024: {'lr': 2.6713612397338575e-05, 'samples': 24580608, 'steps': 128023, 'loss/train': 0.8307929039001465} 08/31/2021 12:26:37 - INFO - __main__ - Step 128025: {'lr': 2.671122564519718e-05, 'samples': 24580800, 'steps': 128024, 'loss/train': 1.5330228805541992} 08/31/2021 12:26:37 - INFO - __main__ - Step 128026: {'lr': 2.6708838993666302e-05, 'samples': 24580992, 'steps': 128025, 'loss/train': 0.5417883396148682} 08/31/2021 12:26:37 - INFO - __main__ - Step 128027: {'lr': 2.670645244274694e-05, 'samples': 24581184, 'steps': 128026, 'loss/train': 2.1676230430603027} 08/31/2021 12:26:38 - INFO - __main__ - Step 128028: {'lr': 2.670406599244021e-05, 'samples': 24581376, 'steps': 128027, 'loss/train': 1.45456862449646} 08/31/2021 12:26:40 - INFO - __main__ - Step 128029: {'lr': 2.670167964274717e-05, 'samples': 24581568, 'steps': 128028, 'loss/train': 0.8731246590614319} 08/31/2021 12:26:40 - INFO - __main__ - Step 128030: {'lr': 2.6699293393668918e-05, 'samples': 24581760, 'steps': 128029, 'loss/train': 2.030411958694458} 08/31/2021 12:26:41 - INFO - __main__ - Step 128031: {'lr': 2.6696907245206515e-05, 'samples': 24581952, 'steps': 128030, 'loss/train': 1.2579134702682495} 08/31/2021 12:26:41 - INFO - __main__ - Step 128032: {'lr': 2.6694521197361015e-05, 'samples': 24582144, 'steps': 128031, 'loss/train': 0.5012804865837097} 08/31/2021 12:26:41 - INFO - __main__ - Step 128033: {'lr': 2.669213525013356e-05, 'samples': 24582336, 'steps': 128032, 'loss/train': 1.337976098060608} 08/31/2021 12:26:43 - INFO - __main__ - Step 128034: {'lr': 2.6689749403525145e-05, 'samples': 24582528, 'steps': 128033, 'loss/train': 1.4959977865219116} 08/31/2021 12:26:43 - INFO - __main__ - Step 128035: {'lr': 2.6687363657536905e-05, 'samples': 24582720, 'steps': 128034, 'loss/train': 0.6695931553840637} 08/31/2021 12:26:44 - INFO - __main__ - Step 128036: {'lr': 2.66849780121699e-05, 'samples': 24582912, 'steps': 128035, 'loss/train': 0.8688541650772095} 08/31/2021 12:26:44 - INFO - __main__ - Step 128037: {'lr': 2.6682592467425187e-05, 'samples': 24583104, 'steps': 128036, 'loss/train': 0.9317513704299927} 08/31/2021 12:26:44 - INFO - __main__ - Step 128038: {'lr': 2.6680207023303843e-05, 'samples': 24583296, 'steps': 128037, 'loss/train': 0.8997873663902283} 08/31/2021 12:26:46 - INFO - __main__ - Step 128039: {'lr': 2.6677821679807008e-05, 'samples': 24583488, 'steps': 128038, 'loss/train': 1.1844899654388428} 08/31/2021 12:26:47 - INFO - __main__ - Step 128040: {'lr': 2.667543643693565e-05, 'samples': 24583680, 'steps': 128039, 'loss/train': 0.7861410975456238} 08/31/2021 12:26:47 - INFO - __main__ - Step 128041: {'lr': 2.6673051294690914e-05, 'samples': 24583872, 'steps': 128040, 'loss/train': 0.08958674222230911} 08/31/2021 12:26:47 - INFO - __main__ - Step 128042: {'lr': 2.6670666253073823e-05, 'samples': 24584064, 'steps': 128041, 'loss/train': 0.11551019549369812} 08/31/2021 12:26:48 - INFO - __main__ - Step 128043: {'lr': 2.6668281312085513e-05, 'samples': 24584256, 'steps': 128042, 'loss/train': 0.46493399143218994} 08/31/2021 12:26:49 - INFO - __main__ - Step 128044: {'lr': 2.6665896471727015e-05, 'samples': 24584448, 'steps': 128043, 'loss/train': 1.1409331560134888} 08/31/2021 12:26:50 - INFO - __main__ - Step 128045: {'lr': 2.666351173199941e-05, 'samples': 24584640, 'steps': 128044, 'loss/train': 1.5132417678833008} 08/31/2021 12:26:50 - INFO - __main__ - Step 128046: {'lr': 2.6661127092903775e-05, 'samples': 24584832, 'steps': 128045, 'loss/train': 0.7973120212554932} 08/31/2021 12:26:50 - INFO - __main__ - Step 128047: {'lr': 2.6658742554441202e-05, 'samples': 24585024, 'steps': 128046, 'loss/train': 0.7264021039009094} 08/31/2021 12:26:51 - INFO - __main__ - Step 128048: {'lr': 2.6656358116612767e-05, 'samples': 24585216, 'steps': 128047, 'loss/train': 0.6241686344146729} 08/31/2021 12:26:52 - INFO - __main__ - Step 128049: {'lr': 2.6653973779419527e-05, 'samples': 24585408, 'steps': 128048, 'loss/train': 1.5256537199020386} 08/31/2021 12:26:53 - INFO - __main__ - Step 128050: {'lr': 2.6651589542862536e-05, 'samples': 24585600, 'steps': 128049, 'loss/train': 1.4136251211166382} 08/31/2021 12:26:53 - INFO - __main__ - Step 128051: {'lr': 2.6649205406942904e-05, 'samples': 24585792, 'steps': 128050, 'loss/train': 1.2136963605880737} 08/31/2021 12:26:53 - INFO - __main__ - Step 128052: {'lr': 2.6646821371661717e-05, 'samples': 24585984, 'steps': 128051, 'loss/train': 0.5443635582923889} 08/31/2021 12:26:54 - INFO - __main__ - Step 128053: {'lr': 2.6644437437020052e-05, 'samples': 24586176, 'steps': 128052, 'loss/train': 1.1331263780593872} 08/31/2021 12:26:54 - INFO - __main__ - Step 128054: {'lr': 2.664205360301891e-05, 'samples': 24586368, 'steps': 128053, 'loss/train': 1.5000884532928467} 08/31/2021 12:26:56 - INFO - __main__ - Step 128055: {'lr': 2.6639669869659407e-05, 'samples': 24586560, 'steps': 128054, 'loss/train': 1.360031008720398} 08/31/2021 12:26:56 - INFO - __main__ - Step 128056: {'lr': 2.6637286236942615e-05, 'samples': 24586752, 'steps': 128055, 'loss/train': 0.1343701034784317} 08/31/2021 12:26:56 - INFO - __main__ - Step 128057: {'lr': 2.6634902704869624e-05, 'samples': 24586944, 'steps': 128056, 'loss/train': 1.4071600437164307} 08/31/2021 12:26:57 - INFO - __main__ - Step 128058: {'lr': 2.6632519273441512e-05, 'samples': 24587136, 'steps': 128057, 'loss/train': 0.7799910306930542} 08/31/2021 12:26:57 - INFO - __main__ - Step 128059: {'lr': 2.663013594265934e-05, 'samples': 24587328, 'steps': 128058, 'loss/train': 1.8083113431930542} 08/31/2021 12:26:59 - INFO - __main__ - Step 128060: {'lr': 2.6627752712524157e-05, 'samples': 24587520, 'steps': 128059, 'loss/train': 0.58033287525177} 08/31/2021 12:26:59 - INFO - __main__ - Step 128061: {'lr': 2.6625369583037073e-05, 'samples': 24587712, 'steps': 128060, 'loss/train': 1.4901477098464966} 08/31/2021 12:26:59 - INFO - __main__ - Step 128062: {'lr': 2.6622986554199174e-05, 'samples': 24587904, 'steps': 128061, 'loss/train': 0.22997142374515533} 08/31/2021 12:27:00 - INFO - __main__ - Step 128063: {'lr': 2.6620603626011486e-05, 'samples': 24588096, 'steps': 128062, 'loss/train': 0.6705421805381775} 08/31/2021 12:27:00 - INFO - __main__ - Step 128064: {'lr': 2.6618220798475117e-05, 'samples': 24588288, 'steps': 128063, 'loss/train': 1.2392336130142212} 08/31/2021 12:27:02 - INFO - __main__ - Step 128065: {'lr': 2.6615838071591124e-05, 'samples': 24588480, 'steps': 128064, 'loss/train': 0.5937451720237732} 08/31/2021 12:27:02 - INFO - __main__ - Step 128066: {'lr': 2.661345544536062e-05, 'samples': 24588672, 'steps': 128065, 'loss/train': 0.036035433411598206} 08/31/2021 12:27:02 - INFO - __main__ - Step 128067: {'lr': 2.6611072919784624e-05, 'samples': 24588864, 'steps': 128066, 'loss/train': 1.073364019393921} 08/31/2021 12:27:03 - INFO - __main__ - Step 128068: {'lr': 2.6608690494864225e-05, 'samples': 24589056, 'steps': 128067, 'loss/train': 1.2142481803894043} 08/31/2021 12:27:03 - INFO - __main__ - Step 128069: {'lr': 2.66063081706005e-05, 'samples': 24589248, 'steps': 128068, 'loss/train': 1.3281344175338745} 08/31/2021 12:27:05 - INFO - __main__ - Step 128070: {'lr': 2.660392594699454e-05, 'samples': 24589440, 'steps': 128069, 'loss/train': 0.8977369070053101} 08/31/2021 12:27:05 - INFO - __main__ - Step 128071: {'lr': 2.6601543824047363e-05, 'samples': 24589632, 'steps': 128070, 'loss/train': 0.11847811937332153} 08/31/2021 12:27:05 - INFO - __main__ - Step 128072: {'lr': 2.6599161801760115e-05, 'samples': 24589824, 'steps': 128071, 'loss/train': 0.6995453834533691} 08/31/2021 12:27:06 - INFO - __main__ - Step 128073: {'lr': 2.659677988013384e-05, 'samples': 24590016, 'steps': 128072, 'loss/train': 0.9573497176170349} 08/31/2021 12:27:06 - INFO - __main__ - Step 128074: {'lr': 2.6594398059169607e-05, 'samples': 24590208, 'steps': 128073, 'loss/train': 0.05001874640583992} 08/31/2021 12:27:08 - INFO - __main__ - Step 128075: {'lr': 2.6592016338868486e-05, 'samples': 24590400, 'steps': 128074, 'loss/train': 1.9940211772918701} 08/31/2021 12:27:08 - INFO - __main__ - Step 128076: {'lr': 2.6589634719231535e-05, 'samples': 24590592, 'steps': 128075, 'loss/train': 0.07646622508764267} 08/31/2021 12:27:08 - INFO - __main__ - Step 128077: {'lr': 2.658725320025987e-05, 'samples': 24590784, 'steps': 128076, 'loss/train': 1.0003103017807007} 08/31/2021 12:27:09 - INFO - __main__ - Step 128078: {'lr': 2.658487178195454e-05, 'samples': 24590976, 'steps': 128077, 'loss/train': 1.0728042125701904} 08/31/2021 12:27:09 - INFO - __main__ - Step 128079: {'lr': 2.658249046431663e-05, 'samples': 24591168, 'steps': 128078, 'loss/train': 1.2046949863433838} 08/31/2021 12:27:09 - INFO - __main__ - Step 128080: {'lr': 2.658010924734722e-05, 'samples': 24591360, 'steps': 128079, 'loss/train': 1.2445329427719116} 08/31/2021 12:27:11 - INFO - __main__ - Step 128081: {'lr': 2.6577728131047335e-05, 'samples': 24591552, 'steps': 128080, 'loss/train': 1.6394469738006592} 08/31/2021 12:27:12 - INFO - __main__ - Step 128082: {'lr': 2.657534711541809e-05, 'samples': 24591744, 'steps': 128081, 'loss/train': 1.0439380407333374} 08/31/2021 12:27:12 - INFO - __main__ - Step 128083: {'lr': 2.6572966200460513e-05, 'samples': 24591936, 'steps': 128082, 'loss/train': 3.216385841369629} 08/31/2021 12:27:13 - INFO - __main__ - Step 128084: {'lr': 2.657058538617574e-05, 'samples': 24592128, 'steps': 128083, 'loss/train': 1.575386881828308} 08/31/2021 12:27:13 - INFO - __main__ - Step 128085: {'lr': 2.6568204672564796e-05, 'samples': 24592320, 'steps': 128084, 'loss/train': 1.1501224040985107} 08/31/2021 12:27:13 - INFO - __main__ - Step 128086: {'lr': 2.656582405962879e-05, 'samples': 24592512, 'steps': 128085, 'loss/train': 0.9702486395835876} 08/31/2021 12:27:15 - INFO - __main__ - Step 128087: {'lr': 2.6563443547368755e-05, 'samples': 24592704, 'steps': 128086, 'loss/train': 1.708641529083252} 08/31/2021 12:27:15 - INFO - __main__ - Step 128088: {'lr': 2.6561063135785796e-05, 'samples': 24592896, 'steps': 128087, 'loss/train': 0.04468837007880211} 08/31/2021 12:27:16 - INFO - __main__ - Step 128089: {'lr': 2.655868282488097e-05, 'samples': 24593088, 'steps': 128088, 'loss/train': 1.42624831199646} 08/31/2021 12:27:16 - INFO - __main__ - Step 128090: {'lr': 2.6556302614655358e-05, 'samples': 24593280, 'steps': 128089, 'loss/train': 1.2189688682556152} 08/31/2021 12:27:16 - INFO - __main__ - Step 128091: {'lr': 2.6553922505110016e-05, 'samples': 24593472, 'steps': 128090, 'loss/train': 1.31711745262146} 08/31/2021 12:27:18 - INFO - __main__ - Step 128092: {'lr': 2.6551542496246056e-05, 'samples': 24593664, 'steps': 128091, 'loss/train': 0.8574485182762146} 08/31/2021 12:27:18 - INFO - __main__ - Step 128093: {'lr': 2.6549162588064556e-05, 'samples': 24593856, 'steps': 128092, 'loss/train': 1.1758196353912354} 08/31/2021 12:27:19 - INFO - __main__ - Step 128094: {'lr': 2.654678278056649e-05, 'samples': 24594048, 'steps': 128093, 'loss/train': 1.2095773220062256} 08/31/2021 12:27:19 - INFO - __main__ - Step 128095: {'lr': 2.6544403073753027e-05, 'samples': 24594240, 'steps': 128094, 'loss/train': 1.0211868286132812} 08/31/2021 12:27:19 - INFO - __main__ - Step 128096: {'lr': 2.6542023467625186e-05, 'samples': 24594432, 'steps': 128095, 'loss/train': 1.2990005016326904} 08/31/2021 12:27:21 - INFO - __main__ - Step 128097: {'lr': 2.6539643962184058e-05, 'samples': 24594624, 'steps': 128096, 'loss/train': 0.9764524698257446} 08/31/2021 12:27:22 - INFO - __main__ - Step 128098: {'lr': 2.6537264557430718e-05, 'samples': 24594816, 'steps': 128097, 'loss/train': 0.8677225708961487} 08/31/2021 12:27:22 - INFO - __main__ - Step 128099: {'lr': 2.653488525336625e-05, 'samples': 24595008, 'steps': 128098, 'loss/train': 0.7687577605247498} 08/31/2021 12:27:22 - INFO - __main__ - Step 128100: {'lr': 2.6532506049991715e-05, 'samples': 24595200, 'steps': 128099, 'loss/train': 1.085805892944336} 08/31/2021 12:27:23 - INFO - __main__ - Step 128101: {'lr': 2.653012694730819e-05, 'samples': 24595392, 'steps': 128100, 'loss/train': 0.9596242904663086} 08/31/2021 12:27:24 - INFO - __main__ - Step 128102: {'lr': 2.6527747945316733e-05, 'samples': 24595584, 'steps': 128101, 'loss/train': 1.472562551498413} 08/31/2021 12:27:24 - INFO - __main__ - Step 128103: {'lr': 2.6525369044018422e-05, 'samples': 24595776, 'steps': 128102, 'loss/train': 0.21039898693561554} 08/31/2021 12:27:25 - INFO - __main__ - Step 128104: {'lr': 2.6522990243414314e-05, 'samples': 24595968, 'steps': 128103, 'loss/train': 0.5036184191703796} 08/31/2021 12:27:25 - INFO - __main__ - Step 128105: {'lr': 2.652061154350552e-05, 'samples': 24596160, 'steps': 128104, 'loss/train': 1.1241379976272583} 08/31/2021 12:27:26 - INFO - __main__ - Step 128106: {'lr': 2.6518232944293093e-05, 'samples': 24596352, 'steps': 128105, 'loss/train': 0.08945723623037338} 08/31/2021 12:27:26 - INFO - __main__ - Step 128107: {'lr': 2.651585444577814e-05, 'samples': 24596544, 'steps': 128106, 'loss/train': 1.8504979610443115} 08/31/2021 12:27:27 - INFO - __main__ - Step 128108: {'lr': 2.6513476047961642e-05, 'samples': 24596736, 'steps': 128107, 'loss/train': 1.0983017683029175} 08/31/2021 12:27:28 - INFO - __main__ - Step 128109: {'lr': 2.6511097750844732e-05, 'samples': 24596928, 'steps': 128108, 'loss/train': 1.1097911596298218} 08/31/2021 12:27:28 - INFO - __main__ - Step 128110: {'lr': 2.650871955442849e-05, 'samples': 24597120, 'steps': 128109, 'loss/train': 1.065792441368103} 08/31/2021 12:27:29 - INFO - __main__ - Step 128111: {'lr': 2.6506341458713945e-05, 'samples': 24597312, 'steps': 128110, 'loss/train': 1.0314795970916748} 08/31/2021 12:27:29 - INFO - __main__ - Step 128112: {'lr': 2.6503963463702208e-05, 'samples': 24597504, 'steps': 128111, 'loss/train': 1.0475908517837524} 08/31/2021 12:27:31 - INFO - __main__ - Step 128113: {'lr': 2.650158556939433e-05, 'samples': 24597696, 'steps': 128112, 'loss/train': 1.717187523841858} 08/31/2021 12:27:31 - INFO - __main__ - Step 128114: {'lr': 2.6499207775791372e-05, 'samples': 24597888, 'steps': 128113, 'loss/train': 1.413445234298706} 08/31/2021 12:27:32 - INFO - __main__ - Step 128115: {'lr': 2.649683008289444e-05, 'samples': 24598080, 'steps': 128114, 'loss/train': 0.7648918032646179} 08/31/2021 12:27:32 - INFO - __main__ - Step 128116: {'lr': 2.649445249070459e-05, 'samples': 24598272, 'steps': 128115, 'loss/train': 0.9934906363487244} 08/31/2021 12:27:32 - INFO - __main__ - Step 128117: {'lr': 2.6492074999222876e-05, 'samples': 24598464, 'steps': 128116, 'loss/train': 1.2505122423171997} 08/31/2021 12:27:34 - INFO - __main__ - Step 128118: {'lr': 2.6489697608450407e-05, 'samples': 24598656, 'steps': 128117, 'loss/train': 1.1625791788101196} 08/31/2021 12:27:34 - INFO - __main__ - Step 128119: {'lr': 2.6487320318388214e-05, 'samples': 24598848, 'steps': 128118, 'loss/train': 1.3168513774871826} 08/31/2021 12:27:35 - INFO - __main__ - Step 128120: {'lr': 2.648494312903743e-05, 'samples': 24599040, 'steps': 128119, 'loss/train': 0.9059047698974609} 08/31/2021 12:27:35 - INFO - __main__ - Step 128121: {'lr': 2.648256604039906e-05, 'samples': 24599232, 'steps': 128120, 'loss/train': 0.8246642351150513} 08/31/2021 12:27:35 - INFO - __main__ - Step 128122: {'lr': 2.648018905247418e-05, 'samples': 24599424, 'steps': 128121, 'loss/train': 1.1239204406738281} 08/31/2021 12:27:37 - INFO - __main__ - Step 128123: {'lr': 2.6477812165263875e-05, 'samples': 24599616, 'steps': 128122, 'loss/train': 0.7551497220993042} 08/31/2021 12:27:38 - INFO - __main__ - Step 128124: {'lr': 2.6475435378769203e-05, 'samples': 24599808, 'steps': 128123, 'loss/train': 0.044240355491638184} 08/31/2021 12:27:38 - INFO - __main__ - Step 128125: {'lr': 2.647305869299127e-05, 'samples': 24600000, 'steps': 128124, 'loss/train': 0.4736280143260956} 08/31/2021 12:27:38 - INFO - __main__ - Step 128126: {'lr': 2.647068210793113e-05, 'samples': 24600192, 'steps': 128125, 'loss/train': 1.2059956789016724} 08/31/2021 12:27:39 - INFO - __main__ - Step 128127: {'lr': 2.6468305623589846e-05, 'samples': 24600384, 'steps': 128126, 'loss/train': 0.7242588996887207} 08/31/2021 12:27:40 - INFO - __main__ - Step 128128: {'lr': 2.646592923996849e-05, 'samples': 24600576, 'steps': 128127, 'loss/train': 1.6658079624176025} 08/31/2021 12:27:41 - INFO - __main__ - Step 128129: {'lr': 2.646355295706815e-05, 'samples': 24600768, 'steps': 128128, 'loss/train': 1.2885674238204956} 08/31/2021 12:27:41 - INFO - __main__ - Step 128130: {'lr': 2.6461176774889878e-05, 'samples': 24600960, 'steps': 128129, 'loss/train': 1.3649858236312866} 08/31/2021 12:27:41 - INFO - __main__ - Step 128131: {'lr': 2.6458800693434786e-05, 'samples': 24601152, 'steps': 128130, 'loss/train': 0.7462334632873535} 08/31/2021 12:27:42 - INFO - __main__ - Step 128132: {'lr': 2.6456424712703875e-05, 'samples': 24601344, 'steps': 128131, 'loss/train': 1.1545255184173584} 08/31/2021 12:27:44 - INFO - __main__ - Step 128133: {'lr': 2.6454048832698225e-05, 'samples': 24601536, 'steps': 128132, 'loss/train': 0.29453232884407043} 08/31/2021 12:27:44 - INFO - __main__ - Step 128134: {'lr': 2.6451673053418972e-05, 'samples': 24601728, 'steps': 128133, 'loss/train': 2.0233254432678223} 08/31/2021 12:27:45 - INFO - __main__ - Step 128135: {'lr': 2.6449297374867122e-05, 'samples': 24601920, 'steps': 128134, 'loss/train': 1.2392452955245972} 08/31/2021 12:27:45 - INFO - __main__ - Step 128136: {'lr': 2.6446921797043777e-05, 'samples': 24602112, 'steps': 128135, 'loss/train': 1.1349300146102905} 08/31/2021 12:27:45 - INFO - __main__ - Step 128137: {'lr': 2.644454631994997e-05, 'samples': 24602304, 'steps': 128136, 'loss/train': 1.3157507181167603} 08/31/2021 12:27:46 - INFO - __main__ - Step 128138: {'lr': 2.6442170943586836e-05, 'samples': 24602496, 'steps': 128137, 'loss/train': 0.9458330273628235} 08/31/2021 12:27:47 - INFO - __main__ - Step 128139: {'lr': 2.6439795667955403e-05, 'samples': 24602688, 'steps': 128138, 'loss/train': 1.0338457822799683} 08/31/2021 12:27:48 - INFO - __main__ - Step 128140: {'lr': 2.643742049305675e-05, 'samples': 24602880, 'steps': 128139, 'loss/train': 0.2839575409889221} 08/31/2021 12:27:48 - INFO - __main__ - Step 128141: {'lr': 2.643504541889194e-05, 'samples': 24603072, 'steps': 128140, 'loss/train': 0.5272822380065918} 08/31/2021 12:27:48 - INFO - __main__ - Step 128142: {'lr': 2.6432670445462077e-05, 'samples': 24603264, 'steps': 128141, 'loss/train': 1.144065260887146} 08/31/2021 12:27:49 - INFO - __main__ - Step 128143: {'lr': 2.6430295572768188e-05, 'samples': 24603456, 'steps': 128142, 'loss/train': 0.7181456685066223} 08/31/2021 12:27:50 - INFO - __main__ - Step 128144: {'lr': 2.6427920800811328e-05, 'samples': 24603648, 'steps': 128143, 'loss/train': 1.2477585077285767} 08/31/2021 12:27:51 - INFO - __main__ - Step 128145: {'lr': 2.6425546129592608e-05, 'samples': 24603840, 'steps': 128144, 'loss/train': 0.8979610204696655} 08/31/2021 12:27:51 - INFO - __main__ - Step 128146: {'lr': 2.642317155911311e-05, 'samples': 24604032, 'steps': 128145, 'loss/train': 0.9248569011688232} 08/31/2021 12:27:52 - INFO - __main__ - Step 128147: {'lr': 2.6420797089373866e-05, 'samples': 24604224, 'steps': 128146, 'loss/train': 0.47076019644737244} 08/31/2021 12:27:52 - INFO - __main__ - Step 128148: {'lr': 2.641842272037595e-05, 'samples': 24604416, 'steps': 128147, 'loss/train': 1.2531194686889648} 08/31/2021 12:27:54 - INFO - __main__ - Step 128149: {'lr': 2.641604845212045e-05, 'samples': 24604608, 'steps': 128148, 'loss/train': 1.0829174518585205} 08/31/2021 12:27:54 - INFO - __main__ - Step 128150: {'lr': 2.641367428460842e-05, 'samples': 24604800, 'steps': 128149, 'loss/train': 1.097316026687622} 08/31/2021 12:27:54 - INFO - __main__ - Step 128151: {'lr': 2.6411300217840966e-05, 'samples': 24604992, 'steps': 128150, 'loss/train': 0.19770316779613495} 08/31/2021 12:27:55 - INFO - __main__ - Step 128152: {'lr': 2.6408926251819092e-05, 'samples': 24605184, 'steps': 128151, 'loss/train': 0.03279957175254822} 08/31/2021 12:27:55 - INFO - __main__ - Step 128153: {'lr': 2.640655238654399e-05, 'samples': 24605376, 'steps': 128152, 'loss/train': 1.1793992519378662} 08/31/2021 12:27:57 - INFO - __main__ - Step 128154: {'lr': 2.6404178622016578e-05, 'samples': 24605568, 'steps': 128153, 'loss/train': 0.6700789332389832} 08/31/2021 12:27:57 - INFO - __main__ - Step 128155: {'lr': 2.640180495823799e-05, 'samples': 24605760, 'steps': 128154, 'loss/train': 0.43961942195892334} 08/31/2021 12:27:58 - INFO - __main__ - Step 128156: {'lr': 2.639943139520931e-05, 'samples': 24605952, 'steps': 128155, 'loss/train': 2.019544839859009} 08/31/2021 12:27:58 - INFO - __main__ - Step 128157: {'lr': 2.639705793293157e-05, 'samples': 24606144, 'steps': 128156, 'loss/train': 1.181984305381775} 08/31/2021 12:27:58 - INFO - __main__ - Step 128158: {'lr': 2.6394684571405898e-05, 'samples': 24606336, 'steps': 128157, 'loss/train': 1.6755834817886353} 08/31/2021 12:28:00 - INFO - __main__ - Step 128159: {'lr': 2.63923113106333e-05, 'samples': 24606528, 'steps': 128158, 'loss/train': 0.5862439870834351} 08/31/2021 12:28:00 - INFO - __main__ - Step 128160: {'lr': 2.6389938150614913e-05, 'samples': 24606720, 'steps': 128159, 'loss/train': 0.9798414707183838} 08/31/2021 12:28:01 - INFO - __main__ - Step 128161: {'lr': 2.6387565091351733e-05, 'samples': 24606912, 'steps': 128160, 'loss/train': 1.0092477798461914} 08/31/2021 12:28:01 - INFO - __main__ - Step 128162: {'lr': 2.6385192132844877e-05, 'samples': 24607104, 'steps': 128161, 'loss/train': 1.5395489931106567} 08/31/2021 12:28:01 - INFO - __main__ - Step 128163: {'lr': 2.638281927509542e-05, 'samples': 24607296, 'steps': 128162, 'loss/train': 0.4872092306613922} 08/31/2021 12:28:03 - INFO - __main__ - Step 128164: {'lr': 2.638044651810445e-05, 'samples': 24607488, 'steps': 128163, 'loss/train': 0.43630215525627136} 08/31/2021 12:28:03 - INFO - __main__ - Step 128165: {'lr': 2.6378073861872938e-05, 'samples': 24607680, 'steps': 128164, 'loss/train': 0.9968579411506653} 08/31/2021 12:28:04 - INFO - __main__ - Step 128166: {'lr': 2.6375701306402044e-05, 'samples': 24607872, 'steps': 128165, 'loss/train': 1.5251818895339966} 08/31/2021 12:28:04 - INFO - __main__ - Step 128167: {'lr': 2.6373328851692774e-05, 'samples': 24608064, 'steps': 128166, 'loss/train': 0.9581352472305298} 08/31/2021 12:28:04 - INFO - __main__ - Step 128168: {'lr': 2.6370956497746262e-05, 'samples': 24608256, 'steps': 128167, 'loss/train': 1.347447395324707} 08/31/2021 12:28:06 - INFO - __main__ - Step 128169: {'lr': 2.6368584244563538e-05, 'samples': 24608448, 'steps': 128168, 'loss/train': 1.5965189933776855} 08/31/2021 12:28:07 - INFO - __main__ - Step 128170: {'lr': 2.636621209214568e-05, 'samples': 24608640, 'steps': 128169, 'loss/train': 0.8936231136322021} 08/31/2021 12:28:07 - INFO - __main__ - Step 128171: {'lr': 2.6363840040493748e-05, 'samples': 24608832, 'steps': 128170, 'loss/train': 0.11704196035861969} 08/31/2021 12:28:07 - INFO - __main__ - Step 128172: {'lr': 2.636146808960882e-05, 'samples': 24609024, 'steps': 128171, 'loss/train': 1.3499113321304321} 08/31/2021 12:28:08 - INFO - __main__ - Step 128173: {'lr': 2.6359096239491954e-05, 'samples': 24609216, 'steps': 128172, 'loss/train': 1.4938961267471313} 08/31/2021 12:28:08 - INFO - __main__ - Step 128174: {'lr': 2.6356724490144258e-05, 'samples': 24609408, 'steps': 128173, 'loss/train': 1.5844727754592896} 08/31/2021 12:28:10 - INFO - __main__ - Step 128175: {'lr': 2.6354352841566788e-05, 'samples': 24609600, 'steps': 128174, 'loss/train': 0.8706318736076355} 08/31/2021 12:28:10 - INFO - __main__ - Step 128176: {'lr': 2.635198129376057e-05, 'samples': 24609792, 'steps': 128175, 'loss/train': 0.9488800764083862} 08/31/2021 12:28:11 - INFO - __main__ - Step 128177: {'lr': 2.6349609846726684e-05, 'samples': 24609984, 'steps': 128176, 'loss/train': 1.313227891921997} 08/31/2021 12:28:11 - INFO - __main__ - Step 128178: {'lr': 2.634723850046622e-05, 'samples': 24610176, 'steps': 128177, 'loss/train': 1.2185062170028687} 08/31/2021 12:28:11 - INFO - __main__ - Step 128179: {'lr': 2.6344867254980226e-05, 'samples': 24610368, 'steps': 128178, 'loss/train': 1.5592650175094604} 08/31/2021 12:28:13 - INFO - __main__ - Step 128180: {'lr': 2.6342496110269815e-05, 'samples': 24610560, 'steps': 128179, 'loss/train': 1.0313338041305542} 08/31/2021 12:28:14 - INFO - __main__ - Step 128181: {'lr': 2.6340125066335985e-05, 'samples': 24610752, 'steps': 128180, 'loss/train': 1.7764261960983276} 08/31/2021 12:28:14 - INFO - __main__ - Step 128182: {'lr': 2.6337754123179876e-05, 'samples': 24610944, 'steps': 128181, 'loss/train': 1.0026662349700928} 08/31/2021 12:28:14 - INFO - __main__ - Step 128183: {'lr': 2.633538328080251e-05, 'samples': 24611136, 'steps': 128182, 'loss/train': 0.26498860120773315} 08/31/2021 12:28:15 - INFO - __main__ - Step 128184: {'lr': 2.6333012539204948e-05, 'samples': 24611328, 'steps': 128183, 'loss/train': 1.3347796201705933} 08/31/2021 12:28:15 - INFO - __main__ - Step 128185: {'lr': 2.6330641898388298e-05, 'samples': 24611520, 'steps': 128184, 'loss/train': 1.4017943143844604} 08/31/2021 12:28:17 - INFO - __main__ - Step 128186: {'lr': 2.6328271358353613e-05, 'samples': 24611712, 'steps': 128185, 'loss/train': 1.3736313581466675} 08/31/2021 12:28:17 - INFO - __main__ - Step 128187: {'lr': 2.6325900919102e-05, 'samples': 24611904, 'steps': 128186, 'loss/train': 1.346834659576416} 08/31/2021 12:28:18 - INFO - __main__ - Step 128188: {'lr': 2.6323530580634443e-05, 'samples': 24612096, 'steps': 128187, 'loss/train': 0.9766103029251099} 08/31/2021 12:28:18 - INFO - __main__ - Step 128189: {'lr': 2.6321160342952065e-05, 'samples': 24612288, 'steps': 128188, 'loss/train': 0.5224843621253967} 08/31/2021 12:28:18 - INFO - __main__ - Step 128190: {'lr': 2.6318790206055905e-05, 'samples': 24612480, 'steps': 128189, 'loss/train': 0.5626285076141357} 08/31/2021 12:28:20 - INFO - __main__ - Step 128191: {'lr': 2.6316420169947036e-05, 'samples': 24612672, 'steps': 128190, 'loss/train': 0.8653233051300049} 08/31/2021 12:28:21 - INFO - __main__ - Step 128192: {'lr': 2.6314050234626547e-05, 'samples': 24612864, 'steps': 128191, 'loss/train': 1.2293825149536133} 08/31/2021 12:28:21 - INFO - __main__ - Step 128193: {'lr': 2.631168040009549e-05, 'samples': 24613056, 'steps': 128192, 'loss/train': 1.3543823957443237} 08/31/2021 12:28:22 - INFO - __main__ - Step 128194: {'lr': 2.6309310666354948e-05, 'samples': 24613248, 'steps': 128193, 'loss/train': 0.7462486624717712} 08/31/2021 12:28:22 - INFO - __main__ - Step 128195: {'lr': 2.6306941033405972e-05, 'samples': 24613440, 'steps': 128194, 'loss/train': 1.0410642623901367} 08/31/2021 12:28:23 - INFO - __main__ - Step 128196: {'lr': 2.6304571501249625e-05, 'samples': 24613632, 'steps': 128195, 'loss/train': 0.9311575293540955} 08/31/2021 12:28:24 - INFO - __main__ - Step 128197: {'lr': 2.630220206988701e-05, 'samples': 24613824, 'steps': 128196, 'loss/train': 1.4348080158233643} 08/31/2021 12:28:24 - INFO - __main__ - Step 128198: {'lr': 2.6299832739319158e-05, 'samples': 24614016, 'steps': 128197, 'loss/train': 2.1424641609191895} 08/31/2021 12:28:25 - INFO - __main__ - Step 128199: {'lr': 2.629746350954715e-05, 'samples': 24614208, 'steps': 128198, 'loss/train': 0.7346981167793274} 08/31/2021 12:28:25 - INFO - __main__ - Step 128200: {'lr': 2.6295094380572064e-05, 'samples': 24614400, 'steps': 128199, 'loss/train': 0.32140734791755676} 08/31/2021 12:28:26 - INFO - __main__ - Step 128201: {'lr': 2.629272535239499e-05, 'samples': 24614592, 'steps': 128200, 'loss/train': 1.2168681621551514} 08/31/2021 12:28:27 - INFO - __main__ - Step 128202: {'lr': 2.6290356425016926e-05, 'samples': 24614784, 'steps': 128201, 'loss/train': 1.0691392421722412} 08/31/2021 12:28:27 - INFO - __main__ - Step 128203: {'lr': 2.628798759843895e-05, 'samples': 24614976, 'steps': 128202, 'loss/train': 1.2765194177627563} 08/31/2021 12:28:28 - INFO - __main__ - Step 128204: {'lr': 2.6285618872662176e-05, 'samples': 24615168, 'steps': 128203, 'loss/train': 1.0439032316207886} 08/31/2021 12:28:28 - INFO - __main__ - Step 128205: {'lr': 2.6283250247687656e-05, 'samples': 24615360, 'steps': 128204, 'loss/train': 1.1877588033676147} 08/31/2021 12:28:29 - INFO - __main__ - Step 128206: {'lr': 2.6280881723516447e-05, 'samples': 24615552, 'steps': 128205, 'loss/train': 1.4563567638397217} 08/31/2021 12:28:30 - INFO - __main__ - Step 128207: {'lr': 2.6278513300149603e-05, 'samples': 24615744, 'steps': 128206, 'loss/train': 0.9335158467292786} 08/31/2021 12:28:30 - INFO - __main__ - Step 128208: {'lr': 2.6276144977588234e-05, 'samples': 24615936, 'steps': 128207, 'loss/train': 1.1267861127853394} 08/31/2021 12:28:31 - INFO - __main__ - Step 128209: {'lr': 2.6273776755833367e-05, 'samples': 24616128, 'steps': 128208, 'loss/train': 1.196508765220642} 08/31/2021 12:28:31 - INFO - __main__ - Step 128210: {'lr': 2.6271408634886084e-05, 'samples': 24616320, 'steps': 128209, 'loss/train': 0.7770538926124573} 08/31/2021 12:28:31 - INFO - __main__ - Step 128211: {'lr': 2.626904061474744e-05, 'samples': 24616512, 'steps': 128210, 'loss/train': 1.4669370651245117} 08/31/2021 12:28:34 - INFO - __main__ - Step 128212: {'lr': 2.626667269541852e-05, 'samples': 24616704, 'steps': 128211, 'loss/train': 0.9479297995567322} 08/31/2021 12:28:34 - INFO - __main__ - Step 128213: {'lr': 2.6264304876900403e-05, 'samples': 24616896, 'steps': 128212, 'loss/train': 0.8847278356552124} 08/31/2021 12:28:34 - INFO - __main__ - Step 128214: {'lr': 2.6261937159194172e-05, 'samples': 24617088, 'steps': 128213, 'loss/train': 1.077571988105774} 08/31/2021 12:28:35 - INFO - __main__ - Step 128215: {'lr': 2.6259569542300827e-05, 'samples': 24617280, 'steps': 128214, 'loss/train': 1.3602818250656128} 08/31/2021 12:28:35 - INFO - __main__ - Step 128216: {'lr': 2.625720202622145e-05, 'samples': 24617472, 'steps': 128215, 'loss/train': 0.8495202660560608} 08/31/2021 12:28:35 - INFO - __main__ - Step 128217: {'lr': 2.6254834610957124e-05, 'samples': 24617664, 'steps': 128216, 'loss/train': 0.01786595582962036} 08/31/2021 12:28:37 - INFO - __main__ - Step 128218: {'lr': 2.625246729650893e-05, 'samples': 24617856, 'steps': 128217, 'loss/train': 0.01677766442298889} 08/31/2021 12:28:38 - INFO - __main__ - Step 128219: {'lr': 2.6250100082877926e-05, 'samples': 24618048, 'steps': 128218, 'loss/train': 0.5330199599266052} 08/31/2021 12:28:38 - INFO - __main__ - Step 128220: {'lr': 2.6247732970065137e-05, 'samples': 24618240, 'steps': 128219, 'loss/train': 0.0528552383184433} 08/31/2021 12:28:39 - INFO - __main__ - Step 128221: {'lr': 2.6245365958071698e-05, 'samples': 24618432, 'steps': 128220, 'loss/train': 0.9726338386535645} 08/31/2021 12:28:39 - INFO - __main__ - Step 128222: {'lr': 2.6242999046898642e-05, 'samples': 24618624, 'steps': 128221, 'loss/train': 1.4273806810379028} 08/31/2021 12:28:39 - INFO - __main__ - Step 128223: {'lr': 2.6240632236547047e-05, 'samples': 24618816, 'steps': 128222, 'loss/train': 1.6348774433135986} 08/31/2021 12:28:41 - INFO - __main__ - Step 128224: {'lr': 2.623826552701794e-05, 'samples': 24619008, 'steps': 128223, 'loss/train': 0.9219800233840942} 08/31/2021 12:28:41 - INFO - __main__ - Step 128225: {'lr': 2.6235898918312435e-05, 'samples': 24619200, 'steps': 128224, 'loss/train': 1.2274761199951172} 08/31/2021 12:28:42 - INFO - __main__ - Step 128226: {'lr': 2.6233532410431583e-05, 'samples': 24619392, 'steps': 128225, 'loss/train': 0.28709661960601807} 08/31/2021 12:28:42 - INFO - __main__ - Step 128227: {'lr': 2.6231166003376467e-05, 'samples': 24619584, 'steps': 128226, 'loss/train': 1.3137842416763306} 08/31/2021 12:28:42 - INFO - __main__ - Step 128228: {'lr': 2.622879969714817e-05, 'samples': 24619776, 'steps': 128227, 'loss/train': 0.6025923490524292} 08/31/2021 12:28:44 - INFO - __main__ - Step 128229: {'lr': 2.6226433491747665e-05, 'samples': 24619968, 'steps': 128228, 'loss/train': 0.4397137463092804} 08/31/2021 12:28:44 - INFO - __main__ - Step 128230: {'lr': 2.6224067387176058e-05, 'samples': 24620160, 'steps': 128229, 'loss/train': 1.2607499361038208} 08/31/2021 12:28:45 - INFO - __main__ - Step 128231: {'lr': 2.6221701383434464e-05, 'samples': 24620352, 'steps': 128230, 'loss/train': 0.6377385854721069} 08/31/2021 12:28:45 - INFO - __main__ - Step 128232: {'lr': 2.621933548052391e-05, 'samples': 24620544, 'steps': 128231, 'loss/train': 1.2237955331802368} 08/31/2021 12:28:45 - INFO - __main__ - Step 128233: {'lr': 2.6216969678445474e-05, 'samples': 24620736, 'steps': 128232, 'loss/train': 1.0942902565002441} 08/31/2021 12:28:47 - INFO - __main__ - Step 128234: {'lr': 2.6214603977200213e-05, 'samples': 24620928, 'steps': 128233, 'loss/train': 1.2904607057571411} 08/31/2021 12:28:47 - INFO - __main__ - Step 128235: {'lr': 2.6212238376789183e-05, 'samples': 24621120, 'steps': 128234, 'loss/train': 0.8327655792236328} 08/31/2021 12:28:47 - INFO - __main__ - Step 128236: {'lr': 2.620987287721349e-05, 'samples': 24621312, 'steps': 128235, 'loss/train': 0.8693088889122009} 08/31/2021 12:28:48 - INFO - __main__ - Step 128237: {'lr': 2.620750747847417e-05, 'samples': 24621504, 'steps': 128236, 'loss/train': 0.2467796802520752} 08/31/2021 12:28:48 - INFO - __main__ - Step 128238: {'lr': 2.6205142180572295e-05, 'samples': 24621696, 'steps': 128237, 'loss/train': 1.21482253074646} 08/31/2021 12:28:50 - INFO - __main__ - Step 128239: {'lr': 2.6202776983508925e-05, 'samples': 24621888, 'steps': 128238, 'loss/train': 1.0270051956176758} 08/31/2021 12:28:50 - INFO - __main__ - Step 128240: {'lr': 2.6200411887285112e-05, 'samples': 24622080, 'steps': 128239, 'loss/train': 1.2775229215621948} 08/31/2021 12:28:50 - INFO - __main__ - Step 128241: {'lr': 2.6198046891901998e-05, 'samples': 24622272, 'steps': 128240, 'loss/train': 1.4626072645187378} 08/31/2021 12:28:51 - INFO - __main__ - Step 128242: {'lr': 2.6195681997360555e-05, 'samples': 24622464, 'steps': 128241, 'loss/train': 0.8408472537994385} 08/31/2021 12:28:51 - INFO - __main__ - Step 128243: {'lr': 2.6193317203661888e-05, 'samples': 24622656, 'steps': 128242, 'loss/train': 0.8708190321922302} 08/31/2021 12:28:53 - INFO - __main__ - Step 128244: {'lr': 2.6190952510807053e-05, 'samples': 24622848, 'steps': 128243, 'loss/train': 0.9369232058525085} 08/31/2021 12:28:54 - INFO - __main__ - Step 128245: {'lr': 2.618858791879711e-05, 'samples': 24623040, 'steps': 128244, 'loss/train': 1.0253130197525024} 08/31/2021 12:28:54 - INFO - __main__ - Step 128246: {'lr': 2.618622342763316e-05, 'samples': 24623232, 'steps': 128245, 'loss/train': 0.7077862620353699} 08/31/2021 12:28:54 - INFO - __main__ - Step 128247: {'lr': 2.618385903731621e-05, 'samples': 24623424, 'steps': 128246, 'loss/train': 1.2640239000320435} 08/31/2021 12:28:55 - INFO - __main__ - Step 128248: {'lr': 2.6181494747847368e-05, 'samples': 24623616, 'steps': 128247, 'loss/train': 0.3288132846355438} 08/31/2021 12:28:56 - INFO - __main__ - Step 128249: {'lr': 2.6179130559227717e-05, 'samples': 24623808, 'steps': 128248, 'loss/train': 1.0007357597351074} 08/31/2021 12:28:57 - INFO - __main__ - Step 128250: {'lr': 2.617676647145828e-05, 'samples': 24624000, 'steps': 128249, 'loss/train': 1.32724928855896} 08/31/2021 12:28:57 - INFO - __main__ - Step 128251: {'lr': 2.6174402484540143e-05, 'samples': 24624192, 'steps': 128250, 'loss/train': 1.3964672088623047} 08/31/2021 12:28:57 - INFO - __main__ - Step 128252: {'lr': 2.6172038598474334e-05, 'samples': 24624384, 'steps': 128251, 'loss/train': 1.8357338905334473} 08/31/2021 12:28:58 - INFO - __main__ - Step 128253: {'lr': 2.616967481326199e-05, 'samples': 24624576, 'steps': 128252, 'loss/train': 0.746232807636261} 08/31/2021 12:29:00 - INFO - __main__ - Step 128254: {'lr': 2.6167311128904136e-05, 'samples': 24624768, 'steps': 128253, 'loss/train': 1.0274451971054077} 08/31/2021 12:29:01 - INFO - __main__ - Step 128255: {'lr': 2.6164947545401858e-05, 'samples': 24624960, 'steps': 128254, 'loss/train': 0.36972948908805847} 08/31/2021 12:29:01 - INFO - __main__ - Step 128256: {'lr': 2.616258406275618e-05, 'samples': 24625152, 'steps': 128255, 'loss/train': 1.2866052389144897} 08/31/2021 12:29:02 - INFO - __main__ - Step 128257: {'lr': 2.6160220680968156e-05, 'samples': 24625344, 'steps': 128256, 'loss/train': 1.3630707263946533} 08/31/2021 12:29:02 - INFO - __main__ - Step 128258: {'lr': 2.6157857400038927e-05, 'samples': 24625536, 'steps': 128257, 'loss/train': 2.0853636264801025} 08/31/2021 12:29:02 - INFO - __main__ - Step 128259: {'lr': 2.615549421996946e-05, 'samples': 24625728, 'steps': 128258, 'loss/train': 0.6651605367660522} 08/31/2021 12:29:03 - INFO - __main__ - Step 128260: {'lr': 2.6153131140760928e-05, 'samples': 24625920, 'steps': 128259, 'loss/train': 0.6323053240776062} 08/31/2021 12:29:03 - INFO - __main__ - Step 128261: {'lr': 2.6150768162414295e-05, 'samples': 24626112, 'steps': 128260, 'loss/train': 0.5281704664230347} 08/31/2021 12:29:04 - INFO - __main__ - Step 128262: {'lr': 2.6148405284930705e-05, 'samples': 24626304, 'steps': 128261, 'loss/train': 0.43113815784454346} 08/31/2021 12:29:05 - INFO - __main__ - Step 128263: {'lr': 2.614604250831118e-05, 'samples': 24626496, 'steps': 128262, 'loss/train': 0.8024452328681946} 08/31/2021 12:29:05 - INFO - __main__ - Step 128264: {'lr': 2.6143679832556776e-05, 'samples': 24626688, 'steps': 128263, 'loss/train': 0.9199917316436768} 08/31/2021 12:29:06 - INFO - __main__ - Step 128265: {'lr': 2.6141317257668578e-05, 'samples': 24626880, 'steps': 128264, 'loss/train': 1.3840196132659912} 08/31/2021 12:29:06 - INFO - __main__ - Step 128266: {'lr': 2.613895478364767e-05, 'samples': 24627072, 'steps': 128265, 'loss/train': 0.717995285987854} 08/31/2021 12:29:08 - INFO - __main__ - Step 128267: {'lr': 2.61365924104951e-05, 'samples': 24627264, 'steps': 128266, 'loss/train': 0.34629857540130615} 08/31/2021 12:29:08 - INFO - __main__ - Step 128268: {'lr': 2.613423013821195e-05, 'samples': 24627456, 'steps': 128267, 'loss/train': 0.7041712999343872} 08/31/2021 12:29:09 - INFO - __main__ - Step 128269: {'lr': 2.6131867966799228e-05, 'samples': 24627648, 'steps': 128268, 'loss/train': 0.5039876103401184} 08/31/2021 12:29:09 - INFO - __main__ - Step 128270: {'lr': 2.612950589625801e-05, 'samples': 24627840, 'steps': 128269, 'loss/train': 0.8438795208930969} 08/31/2021 12:29:09 - INFO - __main__ - Step 128271: {'lr': 2.612714392658941e-05, 'samples': 24628032, 'steps': 128270, 'loss/train': 0.7693229913711548} 08/31/2021 12:29:11 - INFO - __main__ - Step 128272: {'lr': 2.612478205779445e-05, 'samples': 24628224, 'steps': 128271, 'loss/train': 1.0216634273529053} 08/31/2021 12:29:11 - INFO - __main__ - Step 128273: {'lr': 2.6122420289874214e-05, 'samples': 24628416, 'steps': 128272, 'loss/train': 0.7629050016403198} 08/31/2021 12:29:12 - INFO - __main__ - Step 128274: {'lr': 2.6120058622829763e-05, 'samples': 24628608, 'steps': 128273, 'loss/train': 1.4208794832229614} 08/31/2021 12:29:12 - INFO - __main__ - Step 128275: {'lr': 2.6117697056662144e-05, 'samples': 24628800, 'steps': 128274, 'loss/train': 1.7124978303909302} 08/31/2021 12:29:12 - INFO - __main__ - Step 128276: {'lr': 2.611533559137244e-05, 'samples': 24628992, 'steps': 128275, 'loss/train': 1.3105770349502563} 08/31/2021 12:29:14 - INFO - __main__ - Step 128277: {'lr': 2.611297422696171e-05, 'samples': 24629184, 'steps': 128276, 'loss/train': 1.0243842601776123} 08/31/2021 12:29:15 - INFO - __main__ - Step 128278: {'lr': 2.6110612963431036e-05, 'samples': 24629376, 'steps': 128277, 'loss/train': 0.9407681226730347} 08/31/2021 12:29:15 - INFO - __main__ - Step 128279: {'lr': 2.610825180078144e-05, 'samples': 24629568, 'steps': 128278, 'loss/train': 0.5209394693374634} 08/31/2021 12:29:15 - INFO - __main__ - Step 128280: {'lr': 2.6105890739014037e-05, 'samples': 24629760, 'steps': 128279, 'loss/train': 0.021485311910510063} 08/31/2021 12:29:16 - INFO - __main__ - Step 128281: {'lr': 2.6103529778129908e-05, 'samples': 24629952, 'steps': 128280, 'loss/train': 0.041064489632844925} 08/31/2021 12:29:16 - INFO - __main__ - Step 128282: {'lr': 2.6101168918130026e-05, 'samples': 24630144, 'steps': 128281, 'loss/train': 1.2181742191314697} 08/31/2021 12:29:16 - INFO - __main__ - Step 128283: {'lr': 2.6098808159015498e-05, 'samples': 24630336, 'steps': 128282, 'loss/train': 0.540031909942627} 08/31/2021 12:29:18 - INFO - __main__ - Step 128284: {'lr': 2.6096447500787378e-05, 'samples': 24630528, 'steps': 128283, 'loss/train': 1.0392447710037231} 08/31/2021 12:29:18 - INFO - __main__ - Step 128285: {'lr': 2.6094086943446753e-05, 'samples': 24630720, 'steps': 128284, 'loss/train': 0.9309743046760559} 08/31/2021 12:29:19 - INFO - __main__ - Step 128286: {'lr': 2.609172648699468e-05, 'samples': 24630912, 'steps': 128285, 'loss/train': 1.504777431488037} 08/31/2021 12:29:19 - INFO - __main__ - Step 128287: {'lr': 2.608936613143223e-05, 'samples': 24631104, 'steps': 128286, 'loss/train': 0.8929216861724854} 08/31/2021 12:29:19 - INFO - __main__ - Step 128288: {'lr': 2.608700587676044e-05, 'samples': 24631296, 'steps': 128287, 'loss/train': 1.5275846719741821} 08/31/2021 12:29:21 - INFO - __main__ - Step 128289: {'lr': 2.608464572298039e-05, 'samples': 24631488, 'steps': 128288, 'loss/train': 0.9763026833534241} 08/31/2021 12:29:21 - INFO - __main__ - Step 128290: {'lr': 2.608228567009316e-05, 'samples': 24631680, 'steps': 128289, 'loss/train': 0.15648242831230164} 08/31/2021 12:29:22 - INFO - __main__ - Step 128291: {'lr': 2.607992571809978e-05, 'samples': 24631872, 'steps': 128290, 'loss/train': 1.1026785373687744} 08/31/2021 12:29:22 - INFO - __main__ - Step 128292: {'lr': 2.607756586700133e-05, 'samples': 24632064, 'steps': 128291, 'loss/train': 1.1746858358383179} 08/31/2021 12:29:22 - INFO - __main__ - Step 128293: {'lr': 2.6075206116798868e-05, 'samples': 24632256, 'steps': 128292, 'loss/train': 1.0519205331802368} 08/31/2021 12:29:24 - INFO - __main__ - Step 128294: {'lr': 2.607284646749347e-05, 'samples': 24632448, 'steps': 128293, 'loss/train': 0.10055689513683319} 08/31/2021 12:29:24 - INFO - __main__ - Step 128295: {'lr': 2.6070486919086254e-05, 'samples': 24632640, 'steps': 128294, 'loss/train': 0.02614084631204605} 08/31/2021 12:29:25 - INFO - __main__ - Step 128296: {'lr': 2.6068127471578162e-05, 'samples': 24632832, 'steps': 128295, 'loss/train': 0.7897856831550598} 08/31/2021 12:29:25 - INFO - __main__ - Step 128297: {'lr': 2.606576812497033e-05, 'samples': 24633024, 'steps': 128296, 'loss/train': 1.04976487159729} 08/31/2021 12:29:26 - INFO - __main__ - Step 128298: {'lr': 2.6063408879263785e-05, 'samples': 24633216, 'steps': 128297, 'loss/train': 1.5406343936920166} 08/31/2021 12:29:28 - INFO - __main__ - Step 128299: {'lr': 2.6061049734459637e-05, 'samples': 24633408, 'steps': 128298, 'loss/train': 1.186537742614746} 08/31/2021 12:29:28 - INFO - __main__ - Step 128300: {'lr': 2.6058690690558912e-05, 'samples': 24633600, 'steps': 128299, 'loss/train': 0.5553722977638245} 08/31/2021 12:29:29 - INFO - __main__ - Step 128301: {'lr': 2.6056331747562668e-05, 'samples': 24633792, 'steps': 128300, 'loss/train': 0.8054728507995605} 08/31/2021 12:29:29 - INFO - __main__ - Step 128302: {'lr': 2.6053972905472012e-05, 'samples': 24633984, 'steps': 128301, 'loss/train': 1.3373149633407593} 08/31/2021 12:29:29 - INFO - __main__ - Step 128303: {'lr': 2.6051614164287947e-05, 'samples': 24634176, 'steps': 128302, 'loss/train': 0.9592128992080688} 08/31/2021 12:29:31 - INFO - __main__ - Step 128304: {'lr': 2.6049255524011605e-05, 'samples': 24634368, 'steps': 128303, 'loss/train': 1.0565130710601807} 08/31/2021 12:29:32 - INFO - __main__ - Step 128305: {'lr': 2.6046896984643992e-05, 'samples': 24634560, 'steps': 128304, 'loss/train': 1.6061210632324219} 08/31/2021 12:29:32 - INFO - __main__ - Step 128306: {'lr': 2.6044538546186213e-05, 'samples': 24634752, 'steps': 128305, 'loss/train': 0.12644755840301514} 08/31/2021 12:29:32 - INFO - __main__ - Step 128307: {'lr': 2.604218020863927e-05, 'samples': 24634944, 'steps': 128306, 'loss/train': 0.030044496059417725} 08/31/2021 12:29:33 - INFO - __main__ - Step 128308: {'lr': 2.6039821972004356e-05, 'samples': 24635136, 'steps': 128307, 'loss/train': 1.1393331289291382} 08/31/2021 12:29:34 - INFO - __main__ - Step 128309: {'lr': 2.603746383628236e-05, 'samples': 24635328, 'steps': 128308, 'loss/train': 0.8925001621246338} 08/31/2021 12:29:35 - INFO - __main__ - Step 128310: {'lr': 2.6035105801474444e-05, 'samples': 24635520, 'steps': 128309, 'loss/train': 1.2724965810775757} 08/31/2021 12:29:35 - INFO - __main__ - Step 128311: {'lr': 2.603274786758167e-05, 'samples': 24635712, 'steps': 128310, 'loss/train': 0.04280470311641693} 08/31/2021 12:29:35 - INFO - __main__ - Step 128312: {'lr': 2.6030390034605057e-05, 'samples': 24635904, 'steps': 128311, 'loss/train': 0.8018776178359985} 08/31/2021 12:29:36 - INFO - __main__ - Step 128313: {'lr': 2.602803230254569e-05, 'samples': 24636096, 'steps': 128312, 'loss/train': 0.9493119120597839} 08/31/2021 12:29:38 - INFO - __main__ - Step 128314: {'lr': 2.6025674671404653e-05, 'samples': 24636288, 'steps': 128313, 'loss/train': 1.0246306657791138} 08/31/2021 12:29:38 - INFO - __main__ - Step 128315: {'lr': 2.6023317141182972e-05, 'samples': 24636480, 'steps': 128314, 'loss/train': 0.8517926335334778} 08/31/2021 12:29:39 - INFO - __main__ - Step 128316: {'lr': 2.6020959711881758e-05, 'samples': 24636672, 'steps': 128315, 'loss/train': 1.3065378665924072} 08/31/2021 12:29:39 - INFO - __main__ - Step 128317: {'lr': 2.601860238350201e-05, 'samples': 24636864, 'steps': 128316, 'loss/train': 0.7010395526885986} 08/31/2021 12:29:39 - INFO - __main__ - Step 128318: {'lr': 2.6016245156044865e-05, 'samples': 24637056, 'steps': 128317, 'loss/train': 0.014091520570218563} 08/31/2021 12:29:40 - INFO - __main__ - Step 128319: {'lr': 2.6013888029511294e-05, 'samples': 24637248, 'steps': 128318, 'loss/train': 1.301416277885437} 08/31/2021 12:29:41 - INFO - __main__ - Step 128320: {'lr': 2.6011531003902438e-05, 'samples': 24637440, 'steps': 128319, 'loss/train': 1.1686371564865112} 08/31/2021 12:29:42 - INFO - __main__ - Step 128321: {'lr': 2.6009174079219323e-05, 'samples': 24637632, 'steps': 128320, 'loss/train': 0.9791694283485413} 08/31/2021 12:29:42 - INFO - __main__ - Step 128322: {'lr': 2.6006817255463083e-05, 'samples': 24637824, 'steps': 128321, 'loss/train': 0.16936680674552917} 08/31/2021 12:29:42 - INFO - __main__ - Step 128323: {'lr': 2.6004460532634638e-05, 'samples': 24638016, 'steps': 128322, 'loss/train': 0.797237753868103} 08/31/2021 12:29:43 - INFO - __main__ - Step 128324: {'lr': 2.6002103910735152e-05, 'samples': 24638208, 'steps': 128323, 'loss/train': 0.6155885457992554} 08/31/2021 12:29:44 - INFO - __main__ - Step 128325: {'lr': 2.5999747389765656e-05, 'samples': 24638400, 'steps': 128324, 'loss/train': 0.2820413112640381} 08/31/2021 12:29:45 - INFO - __main__ - Step 128326: {'lr': 2.5997390969727196e-05, 'samples': 24638592, 'steps': 128325, 'loss/train': 0.8249484896659851} 08/31/2021 12:29:45 - INFO - __main__ - Step 128327: {'lr': 2.599503465062089e-05, 'samples': 24638784, 'steps': 128326, 'loss/train': 1.7635078430175781} 08/31/2021 12:29:46 - INFO - __main__ - Step 128328: {'lr': 2.5992678432447737e-05, 'samples': 24638976, 'steps': 128327, 'loss/train': 0.9501560926437378} 08/31/2021 12:29:46 - INFO - __main__ - Step 128329: {'lr': 2.599032231520884e-05, 'samples': 24639168, 'steps': 128328, 'loss/train': 0.3230530023574829} 08/31/2021 12:29:48 - INFO - __main__ - Step 128330: {'lr': 2.5987966298905235e-05, 'samples': 24639360, 'steps': 128329, 'loss/train': 0.8505322933197021} 08/31/2021 12:29:48 - INFO - __main__ - Step 128331: {'lr': 2.5985610383538e-05, 'samples': 24639552, 'steps': 128330, 'loss/train': 0.5874243974685669} 08/31/2021 12:29:49 - INFO - __main__ - Step 128332: {'lr': 2.598325456910819e-05, 'samples': 24639744, 'steps': 128331, 'loss/train': 0.5660507678985596} 08/31/2021 12:29:49 - INFO - __main__ - Step 128333: {'lr': 2.5980898855616886e-05, 'samples': 24639936, 'steps': 128332, 'loss/train': 0.0655752569437027} 08/31/2021 12:29:49 - INFO - __main__ - Step 128334: {'lr': 2.5978543243065116e-05, 'samples': 24640128, 'steps': 128333, 'loss/train': 2.056405544281006} 08/31/2021 12:29:50 - INFO - __main__ - Step 128335: {'lr': 2.5976187731453992e-05, 'samples': 24640320, 'steps': 128334, 'loss/train': 0.9637230634689331} 08/31/2021 12:29:50 - INFO - __main__ - Step 128336: {'lr': 2.5973832320784512e-05, 'samples': 24640512, 'steps': 128335, 'loss/train': 1.4985100030899048} 08/31/2021 12:29:52 - INFO - __main__ - Step 128337: {'lr': 2.5971477011057785e-05, 'samples': 24640704, 'steps': 128336, 'loss/train': 0.7909607887268066} 08/31/2021 12:29:52 - INFO - __main__ - Step 128338: {'lr': 2.5969121802274814e-05, 'samples': 24640896, 'steps': 128337, 'loss/train': 0.9105224013328552} 08/31/2021 12:29:53 - INFO - __main__ - Step 128339: {'lr': 2.5966766694436733e-05, 'samples': 24641088, 'steps': 128338, 'loss/train': 1.0445706844329834} 08/31/2021 12:29:53 - INFO - __main__ - Step 128340: {'lr': 2.5964411687544543e-05, 'samples': 24641280, 'steps': 128339, 'loss/train': 1.5268206596374512} 08/31/2021 12:29:53 - INFO - __main__ - Step 128341: {'lr': 2.5962056781599354e-05, 'samples': 24641472, 'steps': 128340, 'loss/train': 1.9555678367614746} 08/31/2021 12:29:55 - INFO - __main__ - Step 128342: {'lr': 2.595970197660219e-05, 'samples': 24641664, 'steps': 128341, 'loss/train': 1.3692560195922852} 08/31/2021 12:29:56 - INFO - __main__ - Step 128343: {'lr': 2.5957347272554137e-05, 'samples': 24641856, 'steps': 128342, 'loss/train': 1.1340055465698242} 08/31/2021 12:29:56 - INFO - __main__ - Step 128344: {'lr': 2.595499266945625e-05, 'samples': 24642048, 'steps': 128343, 'loss/train': 1.3633859157562256} 08/31/2021 12:29:57 - INFO - __main__ - Step 128345: {'lr': 2.5952638167309556e-05, 'samples': 24642240, 'steps': 128344, 'loss/train': 1.5852681398391724} 08/31/2021 12:29:57 - INFO - __main__ - Step 128346: {'lr': 2.595028376611519e-05, 'samples': 24642432, 'steps': 128345, 'loss/train': 0.5688503384590149} 08/31/2021 12:29:57 - INFO - __main__ - Step 128347: {'lr': 2.5947929465874127e-05, 'samples': 24642624, 'steps': 128346, 'loss/train': 1.1821025609970093} 08/31/2021 12:29:59 - INFO - __main__ - Step 128348: {'lr': 2.5945575266587502e-05, 'samples': 24642816, 'steps': 128347, 'loss/train': 0.060343023389577866} 08/31/2021 12:30:00 - INFO - __main__ - Step 128349: {'lr': 2.594322116825637e-05, 'samples': 24643008, 'steps': 128348, 'loss/train': 1.1212660074234009} 08/31/2021 12:30:00 - INFO - __main__ - Step 128350: {'lr': 2.5940867170881732e-05, 'samples': 24643200, 'steps': 128349, 'loss/train': 1.137160062789917} 08/31/2021 12:30:01 - INFO - __main__ - Step 128351: {'lr': 2.593851327446467e-05, 'samples': 24643392, 'steps': 128350, 'loss/train': 1.8224620819091797} 08/31/2021 12:30:01 - INFO - __main__ - Step 128352: {'lr': 2.5936159479006265e-05, 'samples': 24643584, 'steps': 128351, 'loss/train': 1.137592077255249} 08/31/2021 12:30:02 - INFO - __main__ - Step 128353: {'lr': 2.5933805784507576e-05, 'samples': 24643776, 'steps': 128352, 'loss/train': 0.07287617772817612} 08/31/2021 12:30:03 - INFO - __main__ - Step 128354: {'lr': 2.5931452190969622e-05, 'samples': 24643968, 'steps': 128353, 'loss/train': 1.0137994289398193} 08/31/2021 12:30:03 - INFO - __main__ - Step 128355: {'lr': 2.5929098698393522e-05, 'samples': 24644160, 'steps': 128354, 'loss/train': 0.42753538489341736} 08/31/2021 12:30:04 - INFO - __main__ - Step 128356: {'lr': 2.5926745306780324e-05, 'samples': 24644352, 'steps': 128355, 'loss/train': 0.7704229950904846} 08/31/2021 12:30:04 - INFO - __main__ - Step 128357: {'lr': 2.5924392016131058e-05, 'samples': 24644544, 'steps': 128356, 'loss/train': 1.225146770477295} 08/31/2021 12:30:04 - INFO - __main__ - Step 128358: {'lr': 2.592203882644681e-05, 'samples': 24644736, 'steps': 128357, 'loss/train': 1.2470462322235107} 08/31/2021 12:30:06 - INFO - __main__ - Step 128359: {'lr': 2.5919685737728655e-05, 'samples': 24644928, 'steps': 128358, 'loss/train': 0.4377114176750183} 08/31/2021 12:30:07 - INFO - __main__ - Step 128360: {'lr': 2.5917332749977596e-05, 'samples': 24645120, 'steps': 128359, 'loss/train': 1.145416259765625} 08/31/2021 12:30:07 - INFO - __main__ - Step 128361: {'lr': 2.5914979863194743e-05, 'samples': 24645312, 'steps': 128360, 'loss/train': 0.6510590314865112} 08/31/2021 12:30:08 - INFO - __main__ - Step 128362: {'lr': 2.5912627077381207e-05, 'samples': 24645504, 'steps': 128361, 'loss/train': 0.976822018623352} 08/31/2021 12:30:08 - INFO - __main__ - Step 128363: {'lr': 2.59102743925379e-05, 'samples': 24645696, 'steps': 128362, 'loss/train': 1.0875803232192993} 08/31/2021 12:30:09 - INFO - __main__ - Step 128364: {'lr': 2.5907921808665998e-05, 'samples': 24645888, 'steps': 128363, 'loss/train': 0.7644721269607544} 08/31/2021 12:30:10 - INFO - __main__ - Step 128365: {'lr': 2.5905569325766513e-05, 'samples': 24646080, 'steps': 128364, 'loss/train': 1.380749225616455} 08/31/2021 12:30:10 - INFO - __main__ - Step 128366: {'lr': 2.590321694384054e-05, 'samples': 24646272, 'steps': 128365, 'loss/train': 1.1767942905426025} 08/31/2021 12:30:11 - INFO - __main__ - Step 128367: {'lr': 2.5900864662889102e-05, 'samples': 24646464, 'steps': 128366, 'loss/train': 0.3237529397010803} 08/31/2021 12:30:11 - INFO - __main__ - Step 128368: {'lr': 2.589851248291328e-05, 'samples': 24646656, 'steps': 128367, 'loss/train': 1.3456884622573853} 08/31/2021 12:30:12 - INFO - __main__ - Step 128369: {'lr': 2.5896160403914127e-05, 'samples': 24646848, 'steps': 128368, 'loss/train': 0.6002887487411499} 08/31/2021 12:30:13 - INFO - __main__ - Step 128370: {'lr': 2.58938084258927e-05, 'samples': 24647040, 'steps': 128369, 'loss/train': 1.222939133644104} 08/31/2021 12:30:13 - INFO - __main__ - Step 128371: {'lr': 2.5891456548850056e-05, 'samples': 24647232, 'steps': 128370, 'loss/train': 0.03176073729991913} 08/31/2021 12:30:14 - INFO - __main__ - Step 128372: {'lr': 2.5889104772787274e-05, 'samples': 24647424, 'steps': 128371, 'loss/train': 0.22067412734031677} 08/31/2021 12:30:14 - INFO - __main__ - Step 128373: {'lr': 2.5886753097705412e-05, 'samples': 24647616, 'steps': 128372, 'loss/train': 0.5519348382949829} 08/31/2021 12:30:16 - INFO - __main__ - Step 128374: {'lr': 2.588440152360552e-05, 'samples': 24647808, 'steps': 128373, 'loss/train': 1.0193955898284912} 08/31/2021 12:30:16 - INFO - __main__ - Step 128375: {'lr': 2.588205005048866e-05, 'samples': 24648000, 'steps': 128374, 'loss/train': 1.3682559728622437} 08/31/2021 12:30:17 - INFO - __main__ - Step 128376: {'lr': 2.5879698678355934e-05, 'samples': 24648192, 'steps': 128375, 'loss/train': 0.4251197576522827} 08/31/2021 12:30:17 - INFO - __main__ - Step 128377: {'lr': 2.5877347407208317e-05, 'samples': 24648384, 'steps': 128376, 'loss/train': 0.7437137365341187} 08/31/2021 12:30:17 - INFO - __main__ - Step 128378: {'lr': 2.5874996237046895e-05, 'samples': 24648576, 'steps': 128377, 'loss/train': 1.3002315759658813} 08/31/2021 12:30:18 - INFO - __main__ - Step 128379: {'lr': 2.5872645167872745e-05, 'samples': 24648768, 'steps': 128378, 'loss/train': 1.101934790611267} 08/31/2021 12:30:19 - INFO - __main__ - Step 128380: {'lr': 2.5870294199686922e-05, 'samples': 24648960, 'steps': 128379, 'loss/train': 1.5017973184585571} 08/31/2021 12:30:20 - INFO - __main__ - Step 128381: {'lr': 2.5867943332490486e-05, 'samples': 24649152, 'steps': 128380, 'loss/train': 1.0312035083770752} 08/31/2021 12:30:20 - INFO - __main__ - Step 128382: {'lr': 2.5865592566284514e-05, 'samples': 24649344, 'steps': 128381, 'loss/train': 0.7916816473007202} 08/31/2021 12:30:20 - INFO - __main__ - Step 128383: {'lr': 2.5863241901070006e-05, 'samples': 24649536, 'steps': 128382, 'loss/train': 0.960401177406311} 08/31/2021 12:30:21 - INFO - __main__ - Step 128384: {'lr': 2.5860891336848104e-05, 'samples': 24649728, 'steps': 128383, 'loss/train': 0.855481743812561} 08/31/2021 12:30:22 - INFO - __main__ - Step 128385: {'lr': 2.5858540873619803e-05, 'samples': 24649920, 'steps': 128384, 'loss/train': 1.2355778217315674} 08/31/2021 12:30:23 - INFO - __main__ - Step 128386: {'lr': 2.5856190511386185e-05, 'samples': 24650112, 'steps': 128385, 'loss/train': 1.3831557035446167} 08/31/2021 12:30:23 - INFO - __main__ - Step 128387: {'lr': 2.5853840250148337e-05, 'samples': 24650304, 'steps': 128386, 'loss/train': 0.02071128599345684} 08/31/2021 12:30:24 - INFO - __main__ - Step 128388: {'lr': 2.5851490089907252e-05, 'samples': 24650496, 'steps': 128387, 'loss/train': 0.6482241749763489} 08/31/2021 12:30:24 - INFO - __main__ - Step 128389: {'lr': 2.5849140030664103e-05, 'samples': 24650688, 'steps': 128388, 'loss/train': 0.9329248666763306} 08/31/2021 12:30:26 - INFO - __main__ - Step 128390: {'lr': 2.58467900724198e-05, 'samples': 24650880, 'steps': 128389, 'loss/train': 1.0794928073883057} 08/31/2021 12:30:26 - INFO - __main__ - Step 128391: {'lr': 2.5844440215175485e-05, 'samples': 24651072, 'steps': 128390, 'loss/train': 0.038296740502119064} 08/31/2021 12:30:26 - INFO - __main__ - Step 128392: {'lr': 2.584209045893221e-05, 'samples': 24651264, 'steps': 128391, 'loss/train': 0.9440321922302246} 08/31/2021 12:30:27 - INFO - __main__ - Step 128393: {'lr': 2.5839740803691032e-05, 'samples': 24651456, 'steps': 128392, 'loss/train': 1.6060960292816162} 08/31/2021 12:30:27 - INFO - __main__ - Step 128394: {'lr': 2.5837391249453002e-05, 'samples': 24651648, 'steps': 128393, 'loss/train': 0.7846848368644714} 08/31/2021 12:30:29 - INFO - __main__ - Step 128395: {'lr': 2.5835041796219178e-05, 'samples': 24651840, 'steps': 128394, 'loss/train': 1.894286870956421} 08/31/2021 12:30:29 - INFO - __main__ - Step 128396: {'lr': 2.583269244399064e-05, 'samples': 24652032, 'steps': 128395, 'loss/train': 0.7875388860702515} 08/31/2021 12:30:30 - INFO - __main__ - Step 128397: {'lr': 2.583034319276842e-05, 'samples': 24652224, 'steps': 128396, 'loss/train': 1.36574125289917} 08/31/2021 12:30:30 - INFO - __main__ - Step 128398: {'lr': 2.5827994042553595e-05, 'samples': 24652416, 'steps': 128397, 'loss/train': 0.7488158941268921} 08/31/2021 12:30:30 - INFO - __main__ - Step 128399: {'lr': 2.582564499334722e-05, 'samples': 24652608, 'steps': 128398, 'loss/train': 2.053311824798584} 08/31/2021 12:30:32 - INFO - __main__ - Step 128400: {'lr': 2.5823296045150406e-05, 'samples': 24652800, 'steps': 128399, 'loss/train': 1.0426334142684937} 08/31/2021 12:30:32 - INFO - __main__ - Step 128401: {'lr': 2.58209471979641e-05, 'samples': 24652992, 'steps': 128400, 'loss/train': 1.1164617538452148} 08/31/2021 12:30:33 - INFO - __main__ - Step 128402: {'lr': 2.581859845178941e-05, 'samples': 24653184, 'steps': 128401, 'loss/train': 0.09307631850242615} 08/31/2021 12:30:33 - INFO - __main__ - Step 128403: {'lr': 2.581624980662739e-05, 'samples': 24653376, 'steps': 128402, 'loss/train': 0.9475941061973572} 08/31/2021 12:30:33 - INFO - __main__ - Step 128404: {'lr': 2.581390126247912e-05, 'samples': 24653568, 'steps': 128403, 'loss/train': 0.726416289806366} 08/31/2021 12:30:35 - INFO - __main__ - Step 128405: {'lr': 2.5811552819345636e-05, 'samples': 24653760, 'steps': 128404, 'loss/train': 1.5113660097122192} 08/31/2021 12:30:35 - INFO - __main__ - Step 128406: {'lr': 2.5809204477228037e-05, 'samples': 24653952, 'steps': 128405, 'loss/train': 1.1319329738616943} 08/31/2021 12:30:36 - INFO - __main__ - Step 128407: {'lr': 2.580685623612733e-05, 'samples': 24654144, 'steps': 128406, 'loss/train': 1.0175342559814453} 08/31/2021 12:30:36 - INFO - __main__ - Step 128408: {'lr': 2.5804508096044593e-05, 'samples': 24654336, 'steps': 128407, 'loss/train': 1.7237849235534668} 08/31/2021 12:30:36 - INFO - __main__ - Step 128409: {'lr': 2.5802160056980884e-05, 'samples': 24654528, 'steps': 128408, 'loss/train': 0.8158770799636841} 08/31/2021 12:30:38 - INFO - __main__ - Step 128410: {'lr': 2.5799812118937256e-05, 'samples': 24654720, 'steps': 128409, 'loss/train': 1.129488468170166} 08/31/2021 12:30:39 - INFO - __main__ - Step 128411: {'lr': 2.5797464281914845e-05, 'samples': 24654912, 'steps': 128410, 'loss/train': 1.02532160282135} 08/31/2021 12:30:39 - INFO - __main__ - Step 128412: {'lr': 2.579511654591457e-05, 'samples': 24655104, 'steps': 128411, 'loss/train': 1.1100393533706665} 08/31/2021 12:30:39 - INFO - __main__ - Step 128413: {'lr': 2.579276891093757e-05, 'samples': 24655296, 'steps': 128412, 'loss/train': 1.4231421947479248} 08/31/2021 12:30:40 - INFO - __main__ - Step 128414: {'lr': 2.5790421376984868e-05, 'samples': 24655488, 'steps': 128413, 'loss/train': 0.8039520382881165} 08/31/2021 12:30:41 - INFO - __main__ - Step 128415: {'lr': 2.578807394405755e-05, 'samples': 24655680, 'steps': 128414, 'loss/train': 1.1708320379257202} 08/31/2021 12:30:42 - INFO - __main__ - Step 128416: {'lr': 2.5785726612156668e-05, 'samples': 24655872, 'steps': 128415, 'loss/train': 0.5352175235748291} 08/31/2021 12:30:42 - INFO - __main__ - Step 128417: {'lr': 2.578337938128328e-05, 'samples': 24656064, 'steps': 128416, 'loss/train': 0.7575077414512634} 08/31/2021 12:30:42 - INFO - __main__ - Step 128418: {'lr': 2.5781032251438434e-05, 'samples': 24656256, 'steps': 128417, 'loss/train': 0.02013835310935974} 08/31/2021 12:30:43 - INFO - __main__ - Step 128419: {'lr': 2.577868522262322e-05, 'samples': 24656448, 'steps': 128418, 'loss/train': 1.1930285692214966} 08/31/2021 12:30:44 - INFO - __main__ - Step 128420: {'lr': 2.5776338294838637e-05, 'samples': 24656640, 'steps': 128419, 'loss/train': 1.1577998399734497} 08/31/2021 12:30:45 - INFO - __main__ - Step 128421: {'lr': 2.577399146808579e-05, 'samples': 24656832, 'steps': 128420, 'loss/train': 1.8136701583862305} 08/31/2021 12:30:45 - INFO - __main__ - Step 128422: {'lr': 2.5771644742365763e-05, 'samples': 24657024, 'steps': 128421, 'loss/train': 1.0906827449798584} 08/31/2021 12:30:46 - INFO - __main__ - Step 128423: {'lr': 2.5769298117679556e-05, 'samples': 24657216, 'steps': 128422, 'loss/train': 0.7081475257873535} 08/31/2021 12:30:46 - INFO - __main__ - Step 128424: {'lr': 2.57669515940282e-05, 'samples': 24657408, 'steps': 128423, 'loss/train': 1.0912814140319824} 08/31/2021 12:30:47 - INFO - __main__ - Step 128425: {'lr': 2.5764605171412825e-05, 'samples': 24657600, 'steps': 128424, 'loss/train': 0.6645078063011169} 08/31/2021 12:30:48 - INFO - __main__ - Step 128426: {'lr': 2.5762258849834462e-05, 'samples': 24657792, 'steps': 128425, 'loss/train': 0.5831193923950195} 08/31/2021 12:30:48 - INFO - __main__ - Step 128427: {'lr': 2.575991262929414e-05, 'samples': 24657984, 'steps': 128426, 'loss/train': 1.6017874479293823} 08/31/2021 12:30:49 - INFO - __main__ - Step 128428: {'lr': 2.575756650979294e-05, 'samples': 24658176, 'steps': 128427, 'loss/train': 1.2656333446502686} 08/31/2021 12:30:49 - INFO - __main__ - Step 128429: {'lr': 2.5755220491331942e-05, 'samples': 24658368, 'steps': 128428, 'loss/train': 1.6682909727096558} 08/31/2021 12:30:49 - INFO - __main__ - Step 128430: {'lr': 2.575287457391218e-05, 'samples': 24658560, 'steps': 128429, 'loss/train': 0.23640497028827667} 08/31/2021 12:30:51 - INFO - __main__ - Step 128431: {'lr': 2.5750528757534697e-05, 'samples': 24658752, 'steps': 128430, 'loss/train': 1.1849206686019897} 08/31/2021 12:30:52 - INFO - __main__ - Step 128432: {'lr': 2.5748183042200586e-05, 'samples': 24658944, 'steps': 128431, 'loss/train': 0.43785932660102844} 08/31/2021 12:30:52 - INFO - __main__ - Step 128433: {'lr': 2.5745837427910923e-05, 'samples': 24659136, 'steps': 128432, 'loss/train': 0.2520965039730072} 08/31/2021 12:30:52 - INFO - __main__ - Step 128434: {'lr': 2.5743491914666655e-05, 'samples': 24659328, 'steps': 128433, 'loss/train': 0.7909784913063049} 08/31/2021 12:30:53 - INFO - __main__ - Step 128435: {'lr': 2.574114650246895e-05, 'samples': 24659520, 'steps': 128434, 'loss/train': 0.9841282367706299} 08/31/2021 12:30:54 - INFO - __main__ - Step 128436: {'lr': 2.57388011913188e-05, 'samples': 24659712, 'steps': 128435, 'loss/train': 0.38229596614837646} 08/31/2021 12:30:55 - INFO - __main__ - Step 128437: {'lr': 2.5736455981217268e-05, 'samples': 24659904, 'steps': 128436, 'loss/train': 1.2792059183120728} 08/31/2021 12:30:55 - INFO - __main__ - Step 128438: {'lr': 2.5734110872165457e-05, 'samples': 24660096, 'steps': 128437, 'loss/train': 0.18441657721996307} 08/31/2021 12:30:56 - INFO - __main__ - Step 128439: {'lr': 2.573176586416437e-05, 'samples': 24660288, 'steps': 128438, 'loss/train': 0.7300541400909424} 08/31/2021 12:30:56 - INFO - __main__ - Step 128440: {'lr': 2.5729420957215118e-05, 'samples': 24660480, 'steps': 128439, 'loss/train': 0.8723936080932617} 08/31/2021 12:30:58 - INFO - __main__ - Step 128441: {'lr': 2.5727076151318723e-05, 'samples': 24660672, 'steps': 128440, 'loss/train': 0.35537758469581604} 08/31/2021 12:30:58 - INFO - __main__ - Step 128442: {'lr': 2.572473144647622e-05, 'samples': 24660864, 'steps': 128441, 'loss/train': 0.9066984057426453} 08/31/2021 12:30:58 - INFO - __main__ - Step 128443: {'lr': 2.572238684268871e-05, 'samples': 24661056, 'steps': 128442, 'loss/train': 1.4285260438919067} 08/31/2021 12:30:59 - INFO - __main__ - Step 128444: {'lr': 2.5720042339957283e-05, 'samples': 24661248, 'steps': 128443, 'loss/train': 0.25692218542099} 08/31/2021 12:30:59 - INFO - __main__ - Step 128445: {'lr': 2.5717697938282907e-05, 'samples': 24661440, 'steps': 128444, 'loss/train': 0.06563454121351242} 08/31/2021 12:31:01 - INFO - __main__ - Step 128446: {'lr': 2.571535363766664e-05, 'samples': 24661632, 'steps': 128445, 'loss/train': 0.22241900861263275} 08/31/2021 12:31:01 - INFO - __main__ - Step 128447: {'lr': 2.5713009438109615e-05, 'samples': 24661824, 'steps': 128446, 'loss/train': 1.4301810264587402} 08/31/2021 12:31:02 - INFO - __main__ - Step 128448: {'lr': 2.571066533961283e-05, 'samples': 24662016, 'steps': 128447, 'loss/train': 0.58310467004776} 08/31/2021 12:31:02 - INFO - __main__ - Step 128449: {'lr': 2.570832134217735e-05, 'samples': 24662208, 'steps': 128448, 'loss/train': 1.2514190673828125} 08/31/2021 12:31:02 - INFO - __main__ - Step 128450: {'lr': 2.5705977445804246e-05, 'samples': 24662400, 'steps': 128449, 'loss/train': 0.5769045948982239} 08/31/2021 12:31:04 - INFO - __main__ - Step 128451: {'lr': 2.570363365049455e-05, 'samples': 24662592, 'steps': 128450, 'loss/train': 0.7367063760757446} 08/31/2021 12:31:05 - INFO - __main__ - Step 128452: {'lr': 2.5701289956249346e-05, 'samples': 24662784, 'steps': 128451, 'loss/train': 1.198620080947876} 08/31/2021 12:31:05 - INFO - __main__ - Step 128453: {'lr': 2.5698946363069687e-05, 'samples': 24662976, 'steps': 128452, 'loss/train': 0.023619653657078743} 08/31/2021 12:31:05 - INFO - __main__ - Step 128454: {'lr': 2.5696602870956627e-05, 'samples': 24663168, 'steps': 128453, 'loss/train': 0.015378025360405445} 08/31/2021 12:31:06 - INFO - __main__ - Step 128455: {'lr': 2.569425947991122e-05, 'samples': 24663360, 'steps': 128454, 'loss/train': 0.8558805584907532} 08/31/2021 12:31:06 - INFO - __main__ - Step 128456: {'lr': 2.569191618993455e-05, 'samples': 24663552, 'steps': 128455, 'loss/train': 1.334718942642212} 08/31/2021 12:31:08 - INFO - __main__ - Step 128457: {'lr': 2.5689573001027588e-05, 'samples': 24663744, 'steps': 128456, 'loss/train': 1.2305147647857666} 08/31/2021 12:31:08 - INFO - __main__ - Step 128458: {'lr': 2.568722991319147e-05, 'samples': 24663936, 'steps': 128457, 'loss/train': 0.5985679030418396} 08/31/2021 12:31:08 - INFO - __main__ - Step 128459: {'lr': 2.5684886926427202e-05, 'samples': 24664128, 'steps': 128458, 'loss/train': 0.6730086803436279} 08/31/2021 12:31:09 - INFO - __main__ - Step 128460: {'lr': 2.568254404073586e-05, 'samples': 24664320, 'steps': 128459, 'loss/train': 0.8902522325515747} 08/31/2021 12:31:09 - INFO - __main__ - Step 128461: {'lr': 2.568020125611853e-05, 'samples': 24664512, 'steps': 128460, 'loss/train': 0.5214142799377441} 08/31/2021 12:31:11 - INFO - __main__ - Step 128462: {'lr': 2.5677858572576205e-05, 'samples': 24664704, 'steps': 128461, 'loss/train': 1.9596956968307495} 08/31/2021 12:31:11 - INFO - __main__ - Step 128463: {'lr': 2.5675515990110005e-05, 'samples': 24664896, 'steps': 128462, 'loss/train': 0.5593770146369934} 08/31/2021 12:31:11 - INFO - __main__ - Step 128464: {'lr': 2.5673173508720947e-05, 'samples': 24665088, 'steps': 128463, 'loss/train': 0.27353212237358093} 08/31/2021 12:31:12 - INFO - __main__ - Step 128465: {'lr': 2.5670831128410093e-05, 'samples': 24665280, 'steps': 128464, 'loss/train': 2.1582815647125244} 08/31/2021 12:31:12 - INFO - __main__ - Step 128466: {'lr': 2.5668488849178496e-05, 'samples': 24665472, 'steps': 128465, 'loss/train': 0.9683800339698792} 08/31/2021 12:31:15 - INFO - __main__ - Step 128467: {'lr': 2.5666146671027206e-05, 'samples': 24665664, 'steps': 128466, 'loss/train': 1.4927674531936646} 08/31/2021 12:31:15 - INFO - __main__ - Step 128468: {'lr': 2.566380459395731e-05, 'samples': 24665856, 'steps': 128467, 'loss/train': 0.7842102646827698} 08/31/2021 12:31:15 - INFO - __main__ - Step 128469: {'lr': 2.566146261796984e-05, 'samples': 24666048, 'steps': 128468, 'loss/train': 0.9260064363479614} 08/31/2021 12:31:16 - INFO - __main__ - Step 128470: {'lr': 2.5659120743065895e-05, 'samples': 24666240, 'steps': 128469, 'loss/train': 1.1134605407714844} 08/31/2021 12:31:16 - INFO - __main__ - Step 128471: {'lr': 2.5656778969246426e-05, 'samples': 24666432, 'steps': 128470, 'loss/train': 0.023548085242509842} 08/31/2021 12:31:16 - INFO - __main__ - Step 128472: {'lr': 2.5654437296512568e-05, 'samples': 24666624, 'steps': 128471, 'loss/train': 1.1840696334838867} 08/31/2021 12:31:18 - INFO - __main__ - Step 128473: {'lr': 2.5652095724865376e-05, 'samples': 24666816, 'steps': 128472, 'loss/train': 1.2585266828536987} 08/31/2021 12:31:19 - INFO - __main__ - Step 128474: {'lr': 2.564975425430585e-05, 'samples': 24667008, 'steps': 128473, 'loss/train': 1.7522356510162354} 08/31/2021 12:31:19 - INFO - __main__ - Step 128475: {'lr': 2.5647412884835103e-05, 'samples': 24667200, 'steps': 128474, 'loss/train': 0.5187458992004395} 08/31/2021 12:31:20 - INFO - __main__ - Step 128476: {'lr': 2.5645071616454157e-05, 'samples': 24667392, 'steps': 128475, 'loss/train': 0.5646568536758423} 08/31/2021 12:31:20 - INFO - __main__ - Step 128477: {'lr': 2.56427304491641e-05, 'samples': 24667584, 'steps': 128476, 'loss/train': 0.4416674077510834} 08/31/2021 12:31:21 - INFO - __main__ - Step 128478: {'lr': 2.564038938296595e-05, 'samples': 24667776, 'steps': 128477, 'loss/train': 1.4045292139053345} 08/31/2021 12:31:22 - INFO - __main__ - Step 128479: {'lr': 2.56380484178608e-05, 'samples': 24667968, 'steps': 128478, 'loss/train': 0.3356371223926544} 08/31/2021 12:31:22 - INFO - __main__ - Step 128480: {'lr': 2.563570755384967e-05, 'samples': 24668160, 'steps': 128479, 'loss/train': 1.2736403942108154} 08/31/2021 12:31:23 - INFO - __main__ - Step 128481: {'lr': 2.5633366790933614e-05, 'samples': 24668352, 'steps': 128480, 'loss/train': 0.8795889019966125} 08/31/2021 12:31:23 - INFO - __main__ - Step 128482: {'lr': 2.563102612911372e-05, 'samples': 24668544, 'steps': 128481, 'loss/train': 1.0298659801483154} 08/31/2021 12:31:25 - INFO - __main__ - Step 128483: {'lr': 2.5628685568391068e-05, 'samples': 24668736, 'steps': 128482, 'loss/train': 0.3738105595111847} 08/31/2021 12:31:25 - INFO - __main__ - Step 128484: {'lr': 2.56263451087666e-05, 'samples': 24668928, 'steps': 128483, 'loss/train': 1.3370039463043213} 08/31/2021 12:31:26 - INFO - __main__ - Step 128485: {'lr': 2.5624004750241457e-05, 'samples': 24669120, 'steps': 128484, 'loss/train': 1.6272213459014893} 08/31/2021 12:31:26 - INFO - __main__ - Step 128486: {'lr': 2.562166449281669e-05, 'samples': 24669312, 'steps': 128485, 'loss/train': 1.0293159484863281} 08/31/2021 12:31:26 - INFO - __main__ - Step 128487: {'lr': 2.5619324336493304e-05, 'samples': 24669504, 'steps': 128486, 'loss/train': 0.818382203578949} 08/31/2021 12:31:27 - INFO - __main__ - Step 128488: {'lr': 2.5616984281272433e-05, 'samples': 24669696, 'steps': 128487, 'loss/train': 1.6396340131759644} 08/31/2021 12:31:28 - INFO - __main__ - Step 128489: {'lr': 2.5614644327155045e-05, 'samples': 24669888, 'steps': 128488, 'loss/train': 0.7501763701438904} 08/31/2021 12:31:29 - INFO - __main__ - Step 128490: {'lr': 2.5612304474142257e-05, 'samples': 24670080, 'steps': 128489, 'loss/train': 0.4212241470813751} 08/31/2021 12:31:29 - INFO - __main__ - Step 128491: {'lr': 2.560996472223509e-05, 'samples': 24670272, 'steps': 128490, 'loss/train': 0.28078025579452515} 08/31/2021 12:31:29 - INFO - __main__ - Step 128492: {'lr': 2.5607625071434605e-05, 'samples': 24670464, 'steps': 128491, 'loss/train': 1.0444175004959106} 08/31/2021 12:31:30 - INFO - __main__ - Step 128493: {'lr': 2.560528552174188e-05, 'samples': 24670656, 'steps': 128492, 'loss/train': 1.381928563117981} 08/31/2021 12:31:31 - INFO - __main__ - Step 128494: {'lr': 2.560294607315794e-05, 'samples': 24670848, 'steps': 128493, 'loss/train': 0.8344809412956238} 08/31/2021 12:31:32 - INFO - __main__ - Step 128495: {'lr': 2.5600606725683846e-05, 'samples': 24671040, 'steps': 128494, 'loss/train': 1.0989089012145996} 08/31/2021 12:31:32 - INFO - __main__ - Step 128496: {'lr': 2.5598267479320676e-05, 'samples': 24671232, 'steps': 128495, 'loss/train': 0.9040486812591553} 08/31/2021 12:31:33 - INFO - __main__ - Step 128497: {'lr': 2.5595928334069486e-05, 'samples': 24671424, 'steps': 128496, 'loss/train': 1.1866132020950317} 08/31/2021 12:31:33 - INFO - __main__ - Step 128498: {'lr': 2.5593589289931275e-05, 'samples': 24671616, 'steps': 128497, 'loss/train': 1.2161579132080078} 08/31/2021 12:31:34 - INFO - __main__ - Step 128499: {'lr': 2.5591250346907124e-05, 'samples': 24671808, 'steps': 128498, 'loss/train': 0.33025938272476196} 08/31/2021 12:31:35 - INFO - __main__ - Step 128500: {'lr': 2.5588911504998118e-05, 'samples': 24672000, 'steps': 128499, 'loss/train': 1.0825763940811157} 08/31/2021 12:31:35 - INFO - __main__ - Step 128501: {'lr': 2.5586572764205258e-05, 'samples': 24672192, 'steps': 128500, 'loss/train': 1.0051648616790771} 08/31/2021 12:31:36 - INFO - __main__ - Step 128502: {'lr': 2.558423412452962e-05, 'samples': 24672384, 'steps': 128501, 'loss/train': 2.7819430828094482} 08/31/2021 12:31:36 - INFO - __main__ - Step 128503: {'lr': 2.5581895585972293e-05, 'samples': 24672576, 'steps': 128502, 'loss/train': 1.068503975868225} 08/31/2021 12:31:36 - INFO - __main__ - Step 128504: {'lr': 2.5579557148534272e-05, 'samples': 24672768, 'steps': 128503, 'loss/train': 1.4651776552200317} 08/31/2021 12:31:38 - INFO - __main__ - Step 128505: {'lr': 2.557721881221664e-05, 'samples': 24672960, 'steps': 128504, 'loss/train': 0.43979284167289734} 08/31/2021 12:31:38 - INFO - __main__ - Step 128506: {'lr': 2.557488057702048e-05, 'samples': 24673152, 'steps': 128505, 'loss/train': 1.2505043745040894} 08/31/2021 12:31:39 - INFO - __main__ - Step 128507: {'lr': 2.5572542442946794e-05, 'samples': 24673344, 'steps': 128506, 'loss/train': 1.1990578174591064} 08/31/2021 12:31:39 - INFO - __main__ - Step 128508: {'lr': 2.557020440999666e-05, 'samples': 24673536, 'steps': 128507, 'loss/train': 0.9723806977272034} 08/31/2021 12:31:40 - INFO - __main__ - Step 128509: {'lr': 2.556786647817111e-05, 'samples': 24673728, 'steps': 128508, 'loss/train': 0.8816303014755249} 08/31/2021 12:31:41 - INFO - __main__ - Step 128510: {'lr': 2.5565528647471274e-05, 'samples': 24673920, 'steps': 128509, 'loss/train': 1.2702112197875977} 08/31/2021 12:31:41 - INFO - __main__ - Step 128511: {'lr': 2.556319091789813e-05, 'samples': 24674112, 'steps': 128510, 'loss/train': 1.0441032648086548} 08/31/2021 12:31:42 - INFO - __main__ - Step 128512: {'lr': 2.5560853289452706e-05, 'samples': 24674304, 'steps': 128511, 'loss/train': 1.5226943492889404} 08/31/2021 12:31:42 - INFO - __main__ - Step 128513: {'lr': 2.5558515762136136e-05, 'samples': 24674496, 'steps': 128512, 'loss/train': 1.240639090538025} 08/31/2021 12:31:43 - INFO - __main__ - Step 128514: {'lr': 2.555617833594942e-05, 'samples': 24674688, 'steps': 128513, 'loss/train': 0.861934244632721} 08/31/2021 12:31:44 - INFO - __main__ - Step 128515: {'lr': 2.5553841010893614e-05, 'samples': 24674880, 'steps': 128514, 'loss/train': 0.42583581805229187} 08/31/2021 12:31:44 - INFO - __main__ - Step 128516: {'lr': 2.55515037869698e-05, 'samples': 24675072, 'steps': 128515, 'loss/train': 1.2173638343811035} 08/31/2021 12:31:45 - INFO - __main__ - Step 128517: {'lr': 2.5549166664179e-05, 'samples': 24675264, 'steps': 128516, 'loss/train': 1.5533719062805176} 08/31/2021 12:31:45 - INFO - __main__ - Step 128518: {'lr': 2.5546829642522307e-05, 'samples': 24675456, 'steps': 128517, 'loss/train': 0.580409824848175} 08/31/2021 12:31:45 - INFO - __main__ - Step 128519: {'lr': 2.554449272200071e-05, 'samples': 24675648, 'steps': 128518, 'loss/train': 1.7179412841796875} 08/31/2021 12:31:47 - INFO - __main__ - Step 128520: {'lr': 2.5542155902615328e-05, 'samples': 24675840, 'steps': 128519, 'loss/train': 1.604787826538086} 08/31/2021 12:31:48 - INFO - __main__ - Step 128521: {'lr': 2.553981918436718e-05, 'samples': 24676032, 'steps': 128520, 'loss/train': 1.1402523517608643} 08/31/2021 12:31:48 - INFO - __main__ - Step 128522: {'lr': 2.5537482567257353e-05, 'samples': 24676224, 'steps': 128521, 'loss/train': 0.6205437183380127} 08/31/2021 12:31:49 - INFO - __main__ - Step 128523: {'lr': 2.55351460512869e-05, 'samples': 24676416, 'steps': 128522, 'loss/train': 1.0449583530426025} 08/31/2021 12:31:49 - INFO - __main__ - Step 128524: {'lr': 2.5532809636456794e-05, 'samples': 24676608, 'steps': 128523, 'loss/train': 0.6160322427749634} 08/31/2021 12:31:50 - INFO - __main__ - Step 128525: {'lr': 2.5530473322768144e-05, 'samples': 24676800, 'steps': 128524, 'loss/train': 1.2001129388809204} 08/31/2021 12:31:51 - INFO - __main__ - Step 128526: {'lr': 2.5528137110221977e-05, 'samples': 24676992, 'steps': 128525, 'loss/train': 1.7102760076522827} 08/31/2021 12:31:51 - INFO - __main__ - Step 128527: {'lr': 2.5525800998819404e-05, 'samples': 24677184, 'steps': 128526, 'loss/train': 1.4471116065979004} 08/31/2021 12:31:52 - INFO - __main__ - Step 128528: {'lr': 2.5523464988561425e-05, 'samples': 24677376, 'steps': 128527, 'loss/train': 1.38385808467865} 08/31/2021 12:31:52 - INFO - __main__ - Step 128529: {'lr': 2.552112907944909e-05, 'samples': 24677568, 'steps': 128528, 'loss/train': 0.9931847453117371} 08/31/2021 12:31:52 - INFO - __main__ - Step 128530: {'lr': 2.5518793271483487e-05, 'samples': 24677760, 'steps': 128529, 'loss/train': 1.307805061340332} 08/31/2021 12:31:54 - INFO - __main__ - Step 128531: {'lr': 2.551645756466567e-05, 'samples': 24677952, 'steps': 128530, 'loss/train': 1.1626592874526978} 08/31/2021 12:31:54 - INFO - __main__ - Step 128532: {'lr': 2.551412195899666e-05, 'samples': 24678144, 'steps': 128531, 'loss/train': 1.312718391418457} 08/31/2021 12:31:55 - INFO - __main__ - Step 128533: {'lr': 2.551178645447752e-05, 'samples': 24678336, 'steps': 128532, 'loss/train': 1.2895889282226562} 08/31/2021 12:31:55 - INFO - __main__ - Step 128534: {'lr': 2.55094510511093e-05, 'samples': 24678528, 'steps': 128533, 'loss/train': 0.9512801170349121} 08/31/2021 12:31:56 - INFO - __main__ - Step 128535: {'lr': 2.5507115748893057e-05, 'samples': 24678720, 'steps': 128534, 'loss/train': 0.5694384574890137} 08/31/2021 12:31:57 - INFO - __main__ - Step 128536: {'lr': 2.5504780547829843e-05, 'samples': 24678912, 'steps': 128535, 'loss/train': 1.7281527519226074} 08/31/2021 12:31:58 - INFO - __main__ - Step 128537: {'lr': 2.5502445447920768e-05, 'samples': 24679104, 'steps': 128536, 'loss/train': 1.963592290878296} 08/31/2021 12:31:58 - INFO - __main__ - Step 128538: {'lr': 2.550011044916678e-05, 'samples': 24679296, 'steps': 128537, 'loss/train': 0.031408537179231644} 08/31/2021 12:31:58 - INFO - __main__ - Step 128539: {'lr': 2.549777555156896e-05, 'samples': 24679488, 'steps': 128538, 'loss/train': 0.8099808692932129} 08/31/2021 12:31:59 - INFO - __main__ - Step 128540: {'lr': 2.5495440755128384e-05, 'samples': 24679680, 'steps': 128539, 'loss/train': 1.713266134262085} 08/31/2021 12:32:00 - INFO - __main__ - Step 128541: {'lr': 2.5493106059846115e-05, 'samples': 24679872, 'steps': 128540, 'loss/train': 1.2539128065109253} 08/31/2021 12:32:01 - INFO - __main__ - Step 128542: {'lr': 2.5490771465723177e-05, 'samples': 24680064, 'steps': 128541, 'loss/train': 0.943754255771637} 08/31/2021 12:32:01 - INFO - __main__ - Step 128543: {'lr': 2.5488436972760626e-05, 'samples': 24680256, 'steps': 128542, 'loss/train': 0.3300863206386566} 08/31/2021 12:32:02 - INFO - __main__ - Step 128544: {'lr': 2.548610258095954e-05, 'samples': 24680448, 'steps': 128543, 'loss/train': 1.6797739267349243} 08/31/2021 12:32:02 - INFO - __main__ - Step 128545: {'lr': 2.5483768290320923e-05, 'samples': 24680640, 'steps': 128544, 'loss/train': 1.2140461206436157} 08/31/2021 12:32:02 - INFO - __main__ - Step 128546: {'lr': 2.5481434100845885e-05, 'samples': 24680832, 'steps': 128545, 'loss/train': 0.499855101108551} 08/31/2021 12:32:04 - INFO - __main__ - Step 128547: {'lr': 2.547910001253545e-05, 'samples': 24681024, 'steps': 128546, 'loss/train': 0.44274091720581055} 08/31/2021 12:32:04 - INFO - __main__ - Step 128548: {'lr': 2.5476766025390646e-05, 'samples': 24681216, 'steps': 128547, 'loss/train': 0.6296291947364807} 08/31/2021 12:32:05 - INFO - __main__ - Step 128549: {'lr': 2.5474432139412555e-05, 'samples': 24681408, 'steps': 128548, 'loss/train': 1.2809216976165771} 08/31/2021 12:32:05 - INFO - __main__ - Step 128550: {'lr': 2.5472098354602263e-05, 'samples': 24681600, 'steps': 128549, 'loss/train': 0.7680162191390991} 08/31/2021 12:32:06 - INFO - __main__ - Step 128551: {'lr': 2.5469764670960737e-05, 'samples': 24681792, 'steps': 128550, 'loss/train': 1.1142075061798096} 08/31/2021 12:32:07 - INFO - __main__ - Step 128552: {'lr': 2.5467431088489062e-05, 'samples': 24681984, 'steps': 128551, 'loss/train': 0.7041236758232117} 08/31/2021 12:32:07 - INFO - __main__ - Step 128553: {'lr': 2.546509760718832e-05, 'samples': 24682176, 'steps': 128552, 'loss/train': 1.4201138019561768} 08/31/2021 12:32:08 - INFO - __main__ - Step 128554: {'lr': 2.546276422705951e-05, 'samples': 24682368, 'steps': 128553, 'loss/train': 1.9810574054718018} 08/31/2021 12:32:08 - INFO - __main__ - Step 128555: {'lr': 2.546043094810374e-05, 'samples': 24682560, 'steps': 128554, 'loss/train': 1.0148223638534546} 08/31/2021 12:32:08 - INFO - __main__ - Step 128556: {'lr': 2.5458097770322013e-05, 'samples': 24682752, 'steps': 128555, 'loss/train': 0.8443467617034912} 08/31/2021 12:32:10 - INFO - __main__ - Step 128557: {'lr': 2.5455764693715413e-05, 'samples': 24682944, 'steps': 128556, 'loss/train': 1.2908838987350464} 08/31/2021 12:32:11 - INFO - __main__ - Step 128558: {'lr': 2.5453431718284987e-05, 'samples': 24683136, 'steps': 128557, 'loss/train': 0.9635647535324097} 08/31/2021 12:32:11 - INFO - __main__ - Step 128559: {'lr': 2.5451098844031766e-05, 'samples': 24683328, 'steps': 128558, 'loss/train': 0.5518450140953064} 08/31/2021 12:32:11 - INFO - __main__ - Step 128560: {'lr': 2.5448766070956837e-05, 'samples': 24683520, 'steps': 128559, 'loss/train': 0.952751100063324} 08/31/2021 12:32:12 - INFO - __main__ - Step 128561: {'lr': 2.544643339906119e-05, 'samples': 24683712, 'steps': 128560, 'loss/train': 0.03526269644498825} 08/31/2021 12:32:13 - INFO - __main__ - Step 128562: {'lr': 2.5444100828345946e-05, 'samples': 24683904, 'steps': 128561, 'loss/train': 1.133959412574768} 08/31/2021 12:32:14 - INFO - __main__ - Step 128563: {'lr': 2.544176835881212e-05, 'samples': 24684096, 'steps': 128562, 'loss/train': 0.3511902689933777} 08/31/2021 12:32:14 - INFO - __main__ - Step 128564: {'lr': 2.5439435990460807e-05, 'samples': 24684288, 'steps': 128563, 'loss/train': 0.8469938039779663} 08/31/2021 12:32:14 - INFO - __main__ - Step 128565: {'lr': 2.5437103723293e-05, 'samples': 24684480, 'steps': 128564, 'loss/train': 0.8668572902679443} 08/31/2021 12:32:15 - INFO - __main__ - Step 128566: {'lr': 2.5434771557309722e-05, 'samples': 24684672, 'steps': 128565, 'loss/train': 1.6705212593078613} 08/31/2021 12:32:17 - INFO - __main__ - Step 128567: {'lr': 2.5432439492512116e-05, 'samples': 24684864, 'steps': 128566, 'loss/train': 0.7186943888664246} 08/31/2021 12:32:17 - INFO - __main__ - Step 128568: {'lr': 2.5430107528901153e-05, 'samples': 24685056, 'steps': 128567, 'loss/train': 1.0944069623947144} 08/31/2021 12:32:17 - INFO - __main__ - Step 128569: {'lr': 2.5427775666477943e-05, 'samples': 24685248, 'steps': 128568, 'loss/train': 1.0823687314987183} 08/31/2021 12:32:18 - INFO - __main__ - Step 128570: {'lr': 2.5425443905243484e-05, 'samples': 24685440, 'steps': 128569, 'loss/train': 1.169461727142334} 08/31/2021 12:32:18 - INFO - __main__ - Step 128571: {'lr': 2.5423112245198888e-05, 'samples': 24685632, 'steps': 128570, 'loss/train': 1.648895502090454} 08/31/2021 12:32:20 - INFO - __main__ - Step 128572: {'lr': 2.5420780686345153e-05, 'samples': 24685824, 'steps': 128571, 'loss/train': 0.9718995690345764} 08/31/2021 12:32:21 - INFO - __main__ - Step 128573: {'lr': 2.541844922868336e-05, 'samples': 24686016, 'steps': 128572, 'loss/train': 1.936331033706665} 08/31/2021 12:32:21 - INFO - __main__ - Step 128574: {'lr': 2.541611787221454e-05, 'samples': 24686208, 'steps': 128573, 'loss/train': 1.1353297233581543} 08/31/2021 12:32:21 - INFO - __main__ - Step 128575: {'lr': 2.5413786616939743e-05, 'samples': 24686400, 'steps': 128574, 'loss/train': 1.3058158159255981} 08/31/2021 12:32:22 - INFO - __main__ - Step 128576: {'lr': 2.5411455462860028e-05, 'samples': 24686592, 'steps': 128575, 'loss/train': 1.0936084985733032} 08/31/2021 12:32:22 - INFO - __main__ - Step 128577: {'lr': 2.5409124409976502e-05, 'samples': 24686784, 'steps': 128576, 'loss/train': 1.5720797777175903} 08/31/2021 12:32:24 - INFO - __main__ - Step 128578: {'lr': 2.5406793458290113e-05, 'samples': 24686976, 'steps': 128577, 'loss/train': 1.2417418956756592} 08/31/2021 12:32:24 - INFO - __main__ - Step 128579: {'lr': 2.5404462607801966e-05, 'samples': 24687168, 'steps': 128578, 'loss/train': 0.7539939880371094} 08/31/2021 12:32:24 - INFO - __main__ - Step 128580: {'lr': 2.540213185851309e-05, 'samples': 24687360, 'steps': 128579, 'loss/train': 0.6423864960670471} 08/31/2021 12:32:25 - INFO - __main__ - Step 128581: {'lr': 2.539980121042454e-05, 'samples': 24687552, 'steps': 128580, 'loss/train': 0.6202634572982788} 08/31/2021 12:32:25 - INFO - __main__ - Step 128582: {'lr': 2.5397470663537398e-05, 'samples': 24687744, 'steps': 128581, 'loss/train': 0.20548009872436523} 08/31/2021 12:32:27 - INFO - __main__ - Step 128583: {'lr': 2.5395140217852662e-05, 'samples': 24687936, 'steps': 128582, 'loss/train': 1.1891660690307617} 08/31/2021 12:32:27 - INFO - __main__ - Step 128584: {'lr': 2.539280987337142e-05, 'samples': 24688128, 'steps': 128583, 'loss/train': 0.9530397057533264} 08/31/2021 12:32:28 - INFO - __main__ - Step 128585: {'lr': 2.539047963009472e-05, 'samples': 24688320, 'steps': 128584, 'loss/train': 1.1036304235458374} 08/31/2021 12:32:28 - INFO - __main__ - Step 128586: {'lr': 2.538814948802359e-05, 'samples': 24688512, 'steps': 128585, 'loss/train': 0.02495679073035717} 08/31/2021 12:32:28 - INFO - __main__ - Step 128587: {'lr': 2.538581944715912e-05, 'samples': 24688704, 'steps': 128586, 'loss/train': 1.0998669862747192} 08/31/2021 12:32:30 - INFO - __main__ - Step 128588: {'lr': 2.53834895075023e-05, 'samples': 24688896, 'steps': 128587, 'loss/train': 0.7666682004928589} 08/31/2021 12:32:30 - INFO - __main__ - Step 128589: {'lr': 2.5381159669054243e-05, 'samples': 24689088, 'steps': 128588, 'loss/train': 0.9061687588691711} 08/31/2021 12:32:31 - INFO - __main__ - Step 128590: {'lr': 2.537882993181595e-05, 'samples': 24689280, 'steps': 128589, 'loss/train': 0.18434667587280273} 08/31/2021 12:32:31 - INFO - __main__ - Step 128591: {'lr': 2.5376500295788557e-05, 'samples': 24689472, 'steps': 128590, 'loss/train': 1.1216408014297485} 08/31/2021 12:32:31 - INFO - __main__ - Step 128592: {'lr': 2.537417076097298e-05, 'samples': 24689664, 'steps': 128591, 'loss/train': 1.1646878719329834} 08/31/2021 12:32:33 - INFO - __main__ - Step 128593: {'lr': 2.5371841327370332e-05, 'samples': 24689856, 'steps': 128592, 'loss/train': 0.8793534636497498} 08/31/2021 12:32:33 - INFO - __main__ - Step 128594: {'lr': 2.5369511994981693e-05, 'samples': 24690048, 'steps': 128593, 'loss/train': 1.5855227708816528} 08/31/2021 12:32:34 - INFO - __main__ - Step 128595: {'lr': 2.536718276380806e-05, 'samples': 24690240, 'steps': 128594, 'loss/train': 0.8017975091934204} 08/31/2021 12:32:34 - INFO - __main__ - Step 128596: {'lr': 2.5364853633850523e-05, 'samples': 24690432, 'steps': 128595, 'loss/train': 0.9173851609230042} 08/31/2021 12:32:34 - INFO - __main__ - Step 128597: {'lr': 2.5362524605110097e-05, 'samples': 24690624, 'steps': 128596, 'loss/train': 0.83515465259552} 08/31/2021 12:32:36 - INFO - __main__ - Step 128598: {'lr': 2.5360195677587877e-05, 'samples': 24690816, 'steps': 128597, 'loss/train': 0.929119348526001} 08/31/2021 12:32:37 - INFO - __main__ - Step 128599: {'lr': 2.5357866851284883e-05, 'samples': 24691008, 'steps': 128598, 'loss/train': 0.9806526899337769} 08/31/2021 12:32:37 - INFO - __main__ - Step 128600: {'lr': 2.5355538126202145e-05, 'samples': 24691200, 'steps': 128599, 'loss/train': 0.9829933643341064} 08/31/2021 12:32:37 - INFO - __main__ - Step 128601: {'lr': 2.535320950234074e-05, 'samples': 24691392, 'steps': 128600, 'loss/train': 0.04819704592227936} 08/31/2021 12:32:38 - INFO - __main__ - Step 128602: {'lr': 2.535088097970173e-05, 'samples': 24691584, 'steps': 128601, 'loss/train': 1.1583383083343506} 08/31/2021 12:32:39 - INFO - __main__ - Step 128603: {'lr': 2.5348552558286136e-05, 'samples': 24691776, 'steps': 128602, 'loss/train': 1.3849259614944458} 08/31/2021 12:32:39 - INFO - __main__ - Step 128604: {'lr': 2.5346224238095073e-05, 'samples': 24691968, 'steps': 128603, 'loss/train': 1.0731035470962524} 08/31/2021 12:32:40 - INFO - __main__ - Step 128605: {'lr': 2.5343896019129482e-05, 'samples': 24692160, 'steps': 128604, 'loss/train': 0.8835998773574829} 08/31/2021 12:32:40 - INFO - __main__ - Step 128606: {'lr': 2.534156790139047e-05, 'samples': 24692352, 'steps': 128605, 'loss/train': 1.1558362245559692} 08/31/2021 12:32:41 - INFO - __main__ - Step 128607: {'lr': 2.5339239884879073e-05, 'samples': 24692544, 'steps': 128606, 'loss/train': 1.0265758037567139} 08/31/2021 12:32:42 - INFO - __main__ - Step 128608: {'lr': 2.533691196959634e-05, 'samples': 24692736, 'steps': 128607, 'loss/train': 1.1670247316360474} 08/31/2021 12:32:42 - INFO - __main__ - Step 128609: {'lr': 2.533458415554335e-05, 'samples': 24692928, 'steps': 128608, 'loss/train': 1.2406286001205444} 08/31/2021 12:32:43 - INFO - __main__ - Step 128610: {'lr': 2.5332256442721107e-05, 'samples': 24693120, 'steps': 128609, 'loss/train': 0.5096627473831177} 08/31/2021 12:32:43 - INFO - __main__ - Step 128611: {'lr': 2.5329928831130693e-05, 'samples': 24693312, 'steps': 128610, 'loss/train': 0.5337117910385132} 08/31/2021 12:32:43 - INFO - __main__ - Step 128612: {'lr': 2.5327601320773136e-05, 'samples': 24693504, 'steps': 128611, 'loss/train': 1.04403817653656} 08/31/2021 12:32:45 - INFO - __main__ - Step 128613: {'lr': 2.5325273911649515e-05, 'samples': 24693696, 'steps': 128612, 'loss/train': 0.7419015169143677} 08/31/2021 12:32:45 - INFO - __main__ - Step 128614: {'lr': 2.5322946603760833e-05, 'samples': 24693888, 'steps': 128613, 'loss/train': 1.3149234056472778} 08/31/2021 12:32:46 - INFO - __main__ - Step 128615: {'lr': 2.5320619397108197e-05, 'samples': 24694080, 'steps': 128614, 'loss/train': 0.9173691272735596} 08/31/2021 12:32:46 - INFO - __main__ - Step 128616: {'lr': 2.5318292291692607e-05, 'samples': 24694272, 'steps': 128615, 'loss/train': 1.1604773998260498} 08/31/2021 12:32:46 - INFO - __main__ - Step 128617: {'lr': 2.531596528751512e-05, 'samples': 24694464, 'steps': 128616, 'loss/train': 1.2636686563491821} 08/31/2021 12:32:47 - INFO - __main__ - Step 128618: {'lr': 2.5313638384576843e-05, 'samples': 24694656, 'steps': 128617, 'loss/train': 1.6951669454574585} 08/31/2021 12:32:48 - INFO - __main__ - Step 128619: {'lr': 2.5311311582878722e-05, 'samples': 24694848, 'steps': 128618, 'loss/train': 0.8337243795394897} 08/31/2021 12:32:49 - INFO - __main__ - Step 128620: {'lr': 2.5308984882421866e-05, 'samples': 24695040, 'steps': 128619, 'loss/train': 1.577532172203064} 08/31/2021 12:32:49 - INFO - __main__ - Step 128621: {'lr': 2.53066582832073e-05, 'samples': 24695232, 'steps': 128620, 'loss/train': 1.3222447633743286} 08/31/2021 12:32:50 - INFO - __main__ - Step 128622: {'lr': 2.5304331785236113e-05, 'samples': 24695424, 'steps': 128621, 'loss/train': 1.1116913557052612} 08/31/2021 12:32:50 - INFO - __main__ - Step 128623: {'lr': 2.5302005388509296e-05, 'samples': 24695616, 'steps': 128622, 'loss/train': 0.41955330967903137} 08/31/2021 12:32:52 - INFO - __main__ - Step 128624: {'lr': 2.5299679093027965e-05, 'samples': 24695808, 'steps': 128623, 'loss/train': 0.7421395182609558} 08/31/2021 12:32:53 - INFO - __main__ - Step 128625: {'lr': 2.5297352898793092e-05, 'samples': 24696000, 'steps': 128624, 'loss/train': 1.2471956014633179} 08/31/2021 12:32:53 - INFO - __main__ - Step 128626: {'lr': 2.5295026805805782e-05, 'samples': 24696192, 'steps': 128625, 'loss/train': 1.3594274520874023} 08/31/2021 12:32:53 - INFO - __main__ - Step 128627: {'lr': 2.5292700814067065e-05, 'samples': 24696384, 'steps': 128626, 'loss/train': 0.05088101699948311} 08/31/2021 12:32:54 - INFO - __main__ - Step 128628: {'lr': 2.5290374923577997e-05, 'samples': 24696576, 'steps': 128627, 'loss/train': 1.0506978034973145} 08/31/2021 12:32:56 - INFO - __main__ - Step 128629: {'lr': 2.52880491343396e-05, 'samples': 24696768, 'steps': 128628, 'loss/train': 1.228644847869873} 08/31/2021 12:32:56 - INFO - __main__ - Step 128630: {'lr': 2.5285723446352963e-05, 'samples': 24696960, 'steps': 128629, 'loss/train': 0.014693095348775387} 08/31/2021 12:32:56 - INFO - __main__ - Step 128631: {'lr': 2.528339785961914e-05, 'samples': 24697152, 'steps': 128630, 'loss/train': 1.099122166633606} 08/31/2021 12:32:57 - INFO - __main__ - Step 128632: {'lr': 2.5281072374139126e-05, 'samples': 24697344, 'steps': 128631, 'loss/train': 0.5486332774162292} 08/31/2021 12:32:57 - INFO - __main__ - Step 128633: {'lr': 2.5278746989913976e-05, 'samples': 24697536, 'steps': 128632, 'loss/train': 0.6326882243156433} 08/31/2021 12:32:57 - INFO - __main__ - Step 128634: {'lr': 2.5276421706944748e-05, 'samples': 24697728, 'steps': 128633, 'loss/train': 1.234531283378601} 08/31/2021 12:32:59 - INFO - __main__ - Step 128635: {'lr': 2.527409652523252e-05, 'samples': 24697920, 'steps': 128634, 'loss/train': 0.683285653591156} 08/31/2021 12:32:59 - INFO - __main__ - Step 128636: {'lr': 2.5271771444778296e-05, 'samples': 24698112, 'steps': 128635, 'loss/train': 0.17626431584358215} 08/31/2021 12:33:00 - INFO - __main__ - Step 128637: {'lr': 2.5269446465583157e-05, 'samples': 24698304, 'steps': 128636, 'loss/train': 0.6419238448143005} 08/31/2021 12:33:00 - INFO - __main__ - Step 128638: {'lr': 2.526712158764813e-05, 'samples': 24698496, 'steps': 128637, 'loss/train': 0.28425389528274536} 08/31/2021 12:33:00 - INFO - __main__ - Step 128639: {'lr': 2.5264796810974265e-05, 'samples': 24698688, 'steps': 128638, 'loss/train': 1.1725385189056396} 08/31/2021 12:33:02 - INFO - __main__ - Step 128640: {'lr': 2.5262472135562627e-05, 'samples': 24698880, 'steps': 128639, 'loss/train': 1.0944665670394897} 08/31/2021 12:33:02 - INFO - __main__ - Step 128641: {'lr': 2.526014756141423e-05, 'samples': 24699072, 'steps': 128640, 'loss/train': 1.5485998392105103} 08/31/2021 12:33:03 - INFO - __main__ - Step 128642: {'lr': 2.525782308853017e-05, 'samples': 24699264, 'steps': 128641, 'loss/train': 1.3998013734817505} 08/31/2021 12:33:03 - INFO - __main__ - Step 128643: {'lr': 2.525549871691146e-05, 'samples': 24699456, 'steps': 128642, 'loss/train': 0.8266299962997437} 08/31/2021 12:33:03 - INFO - __main__ - Step 128644: {'lr': 2.5253174446559195e-05, 'samples': 24699648, 'steps': 128643, 'loss/train': 0.40047359466552734} 08/31/2021 12:33:05 - INFO - __main__ - Step 128645: {'lr': 2.5250850277474315e-05, 'samples': 24699840, 'steps': 128644, 'loss/train': 1.432289481163025} 08/31/2021 12:33:06 - INFO - __main__ - Step 128646: {'lr': 2.5248526209657953e-05, 'samples': 24700032, 'steps': 128645, 'loss/train': 0.6692060828208923} 08/31/2021 12:33:06 - INFO - __main__ - Step 128647: {'lr': 2.524620224311114e-05, 'samples': 24700224, 'steps': 128646, 'loss/train': 1.3052321672439575} 08/31/2021 12:33:06 - INFO - __main__ - Step 128648: {'lr': 2.5243878377834927e-05, 'samples': 24700416, 'steps': 128647, 'loss/train': 0.3294527232646942} 08/31/2021 12:33:07 - INFO - __main__ - Step 128649: {'lr': 2.5241554613830347e-05, 'samples': 24700608, 'steps': 128648, 'loss/train': 0.1381421834230423} 08/31/2021 12:33:07 - INFO - __main__ - Step 128650: {'lr': 2.5239230951098452e-05, 'samples': 24700800, 'steps': 128649, 'loss/train': 0.9526499509811401} 08/31/2021 12:33:08 - INFO - __main__ - Step 128651: {'lr': 2.5236907389640297e-05, 'samples': 24700992, 'steps': 128650, 'loss/train': 1.1043591499328613} 08/31/2021 12:33:09 - INFO - __main__ - Step 128652: {'lr': 2.5234583929456904e-05, 'samples': 24701184, 'steps': 128651, 'loss/train': 0.7097930312156677} 08/31/2021 12:33:09 - INFO - __main__ - Step 128653: {'lr': 2.5232260570549365e-05, 'samples': 24701376, 'steps': 128652, 'loss/train': 0.8518379330635071} 08/31/2021 12:33:10 - INFO - __main__ - Step 128654: {'lr': 2.5229937312918672e-05, 'samples': 24701568, 'steps': 128653, 'loss/train': 1.2664872407913208} 08/31/2021 12:33:10 - INFO - __main__ - Step 128655: {'lr': 2.5227614156565936e-05, 'samples': 24701760, 'steps': 128654, 'loss/train': 1.1028543710708618} 08/31/2021 12:33:12 - INFO - __main__ - Step 128656: {'lr': 2.522529110149213e-05, 'samples': 24701952, 'steps': 128655, 'loss/train': 0.8908427357673645} 08/31/2021 12:33:12 - INFO - __main__ - Step 128657: {'lr': 2.5222968147698366e-05, 'samples': 24702144, 'steps': 128656, 'loss/train': 1.0718562602996826} 08/31/2021 12:33:13 - INFO - __main__ - Step 128658: {'lr': 2.5220645295185724e-05, 'samples': 24702336, 'steps': 128657, 'loss/train': 0.9896541833877563} 08/31/2021 12:33:13 - INFO - __main__ - Step 128659: {'lr': 2.521832254395512e-05, 'samples': 24702528, 'steps': 128658, 'loss/train': 0.02139332890510559} 08/31/2021 12:33:13 - INFO - __main__ - Step 128660: {'lr': 2.5215999894007664e-05, 'samples': 24702720, 'steps': 128659, 'loss/train': 0.06839247792959213} 08/31/2021 12:33:14 - INFO - __main__ - Step 128661: {'lr': 2.521367734534444e-05, 'samples': 24702912, 'steps': 128660, 'loss/train': 1.2036442756652832} 08/31/2021 12:33:15 - INFO - __main__ - Step 128662: {'lr': 2.5211354897966442e-05, 'samples': 24703104, 'steps': 128661, 'loss/train': 1.173874020576477} 08/31/2021 12:33:16 - INFO - __main__ - Step 128663: {'lr': 2.5209032551874735e-05, 'samples': 24703296, 'steps': 128662, 'loss/train': 1.3052645921707153} 08/31/2021 12:33:16 - INFO - __main__ - Step 128664: {'lr': 2.520671030707039e-05, 'samples': 24703488, 'steps': 128663, 'loss/train': 1.3295053243637085} 08/31/2021 12:33:16 - INFO - __main__ - Step 128665: {'lr': 2.5204388163554414e-05, 'samples': 24703680, 'steps': 128664, 'loss/train': 0.9939286112785339} 08/31/2021 12:33:17 - INFO - __main__ - Step 128666: {'lr': 2.5202066121327862e-05, 'samples': 24703872, 'steps': 128665, 'loss/train': 0.2509550452232361} 08/31/2021 12:33:18 - INFO - __main__ - Step 128667: {'lr': 2.519974418039181e-05, 'samples': 24704064, 'steps': 128666, 'loss/train': 2.0974948406219482} 08/31/2021 12:33:19 - INFO - __main__ - Step 128668: {'lr': 2.5197422340747288e-05, 'samples': 24704256, 'steps': 128667, 'loss/train': 0.7841095924377441} 08/31/2021 12:33:19 - INFO - __main__ - Step 128669: {'lr': 2.5195100602395384e-05, 'samples': 24704448, 'steps': 128668, 'loss/train': 1.0545499324798584} 08/31/2021 12:33:19 - INFO - __main__ - Step 128670: {'lr': 2.5192778965337033e-05, 'samples': 24704640, 'steps': 128669, 'loss/train': 1.4657484292984009} 08/31/2021 12:33:20 - INFO - __main__ - Step 128671: {'lr': 2.519045742957335e-05, 'samples': 24704832, 'steps': 128670, 'loss/train': 1.0339059829711914} 08/31/2021 12:33:21 - INFO - __main__ - Step 128672: {'lr': 2.518813599510539e-05, 'samples': 24705024, 'steps': 128671, 'loss/train': 0.8913497924804688} 08/31/2021 12:33:22 - INFO - __main__ - Step 128673: {'lr': 2.5185814661934202e-05, 'samples': 24705216, 'steps': 128672, 'loss/train': 1.0115199089050293} 08/31/2021 12:33:22 - INFO - __main__ - Step 128674: {'lr': 2.5183493430060794e-05, 'samples': 24705408, 'steps': 128673, 'loss/train': 0.4879664182662964} 08/31/2021 12:33:23 - INFO - __main__ - Step 128675: {'lr': 2.5181172299486244e-05, 'samples': 24705600, 'steps': 128674, 'loss/train': 0.22868500649929047} 08/31/2021 12:33:23 - INFO - __main__ - Step 128676: {'lr': 2.5178851270211577e-05, 'samples': 24705792, 'steps': 128675, 'loss/train': 1.0361754894256592} 08/31/2021 12:33:25 - INFO - __main__ - Step 128677: {'lr': 2.5176530342237852e-05, 'samples': 24705984, 'steps': 128676, 'loss/train': 0.8732356429100037} 08/31/2021 12:33:25 - INFO - __main__ - Step 128678: {'lr': 2.517420951556612e-05, 'samples': 24706176, 'steps': 128677, 'loss/train': 1.1180496215820312} 08/31/2021 12:33:25 - INFO - __main__ - Step 128679: {'lr': 2.5171888790197412e-05, 'samples': 24706368, 'steps': 128678, 'loss/train': 1.4607192277908325} 08/31/2021 12:33:26 - INFO - __main__ - Step 128680: {'lr': 2.5169568166132834e-05, 'samples': 24706560, 'steps': 128679, 'loss/train': 1.6201651096343994} 08/31/2021 12:33:26 - INFO - __main__ - Step 128681: {'lr': 2.5167247643373332e-05, 'samples': 24706752, 'steps': 128680, 'loss/train': 0.6282582879066467} 08/31/2021 12:33:26 - INFO - __main__ - Step 128682: {'lr': 2.5164927221920014e-05, 'samples': 24706944, 'steps': 128681, 'loss/train': 2.041522741317749} 08/31/2021 12:33:29 - INFO - __main__ - Step 128683: {'lr': 2.5162606901773883e-05, 'samples': 24707136, 'steps': 128682, 'loss/train': 1.191840410232544} 08/31/2021 12:33:29 - INFO - __main__ - Step 128684: {'lr': 2.5160286682936047e-05, 'samples': 24707328, 'steps': 128683, 'loss/train': 1.0671989917755127} 08/31/2021 12:33:29 - INFO - __main__ - Step 128685: {'lr': 2.5157966565407475e-05, 'samples': 24707520, 'steps': 128684, 'loss/train': 1.553269624710083} 08/31/2021 12:33:30 - INFO - __main__ - Step 128686: {'lr': 2.515564654918928e-05, 'samples': 24707712, 'steps': 128685, 'loss/train': 0.8516875505447388} 08/31/2021 12:33:30 - INFO - __main__ - Step 128687: {'lr': 2.5153326634282465e-05, 'samples': 24707904, 'steps': 128686, 'loss/train': 1.2368885278701782} 08/31/2021 12:33:32 - INFO - __main__ - Step 128688: {'lr': 2.5151006820688105e-05, 'samples': 24708096, 'steps': 128687, 'loss/train': 1.8286069631576538} 08/31/2021 12:33:32 - INFO - __main__ - Step 128689: {'lr': 2.514868710840723e-05, 'samples': 24708288, 'steps': 128688, 'loss/train': 0.7151369452476501} 08/31/2021 12:33:32 - INFO - __main__ - Step 128690: {'lr': 2.5146367497440898e-05, 'samples': 24708480, 'steps': 128689, 'loss/train': 5.3857526779174805} 08/31/2021 12:33:33 - INFO - __main__ - Step 128691: {'lr': 2.514404798779016e-05, 'samples': 24708672, 'steps': 128690, 'loss/train': 0.059405840933322906} 08/31/2021 12:33:33 - INFO - __main__ - Step 128692: {'lr': 2.5141728579456015e-05, 'samples': 24708864, 'steps': 128691, 'loss/train': 1.129270076751709} 08/31/2021 12:33:35 - INFO - __main__ - Step 128693: {'lr': 2.5139409272439545e-05, 'samples': 24709056, 'steps': 128692, 'loss/train': 1.5321519374847412} 08/31/2021 12:33:35 - INFO - __main__ - Step 128694: {'lr': 2.513709006674178e-05, 'samples': 24709248, 'steps': 128693, 'loss/train': 0.6932922601699829} 08/31/2021 12:33:36 - INFO - __main__ - Step 128695: {'lr': 2.5134770962363774e-05, 'samples': 24709440, 'steps': 128694, 'loss/train': 0.9009413719177246} 08/31/2021 12:33:36 - INFO - __main__ - Step 128696: {'lr': 2.513245195930655e-05, 'samples': 24709632, 'steps': 128695, 'loss/train': 1.0909830331802368} 08/31/2021 12:33:37 - INFO - __main__ - Step 128697: {'lr': 2.51301330575712e-05, 'samples': 24709824, 'steps': 128696, 'loss/train': 0.8812494874000549} 08/31/2021 12:33:37 - INFO - __main__ - Step 128698: {'lr': 2.5127814257158737e-05, 'samples': 24710016, 'steps': 128697, 'loss/train': 0.9785636067390442} 08/31/2021 12:33:38 - INFO - __main__ - Step 128699: {'lr': 2.51254955580702e-05, 'samples': 24710208, 'steps': 128698, 'loss/train': 0.9693348407745361} 08/31/2021 12:33:39 - INFO - __main__ - Step 128700: {'lr': 2.5123176960306665e-05, 'samples': 24710400, 'steps': 128699, 'loss/train': 1.1893280744552612} 08/31/2021 12:33:39 - INFO - __main__ - Step 128701: {'lr': 2.5120858463869188e-05, 'samples': 24710592, 'steps': 128700, 'loss/train': 0.03622279688715935} 08/31/2021 12:33:40 - INFO - __main__ - Step 128702: {'lr': 2.5118540068758743e-05, 'samples': 24710784, 'steps': 128701, 'loss/train': 1.2262141704559326} 08/31/2021 12:33:40 - INFO - __main__ - Step 128703: {'lr': 2.5116221774976382e-05, 'samples': 24710976, 'steps': 128702, 'loss/train': 0.919350802898407} 08/31/2021 12:33:41 - INFO - __main__ - Step 128704: {'lr': 2.5113903582523218e-05, 'samples': 24711168, 'steps': 128703, 'loss/train': 1.409263253211975} 08/31/2021 12:33:42 - INFO - __main__ - Step 128705: {'lr': 2.5111585491400246e-05, 'samples': 24711360, 'steps': 128704, 'loss/train': 1.4287233352661133} 08/31/2021 12:33:42 - INFO - __main__ - Step 128706: {'lr': 2.5109267501608524e-05, 'samples': 24711552, 'steps': 128705, 'loss/train': 1.0022492408752441} 08/31/2021 12:33:43 - INFO - __main__ - Step 128707: {'lr': 2.5106949613149104e-05, 'samples': 24711744, 'steps': 128706, 'loss/train': 1.7199184894561768} 08/31/2021 12:33:44 - INFO - __main__ - Step 128708: {'lr': 2.510463182602302e-05, 'samples': 24711936, 'steps': 128707, 'loss/train': 1.1213445663452148} 08/31/2021 12:33:45 - INFO - __main__ - Step 128709: {'lr': 2.5102314140231312e-05, 'samples': 24712128, 'steps': 128708, 'loss/train': 0.9175735712051392} 08/31/2021 12:33:45 - INFO - __main__ - Step 128710: {'lr': 2.5099996555775023e-05, 'samples': 24712320, 'steps': 128709, 'loss/train': 1.3165580034255981} 08/31/2021 12:33:45 - INFO - __main__ - Step 128711: {'lr': 2.5097679072655228e-05, 'samples': 24712512, 'steps': 128710, 'loss/train': 1.1978965997695923} 08/31/2021 12:33:46 - INFO - __main__ - Step 128712: {'lr': 2.509536169087298e-05, 'samples': 24712704, 'steps': 128711, 'loss/train': 0.8009169697761536} 08/31/2021 12:33:46 - INFO - __main__ - Step 128713: {'lr': 2.5093044410429227e-05, 'samples': 24712896, 'steps': 128712, 'loss/train': 0.5067023634910583} 08/31/2021 12:33:48 - INFO - __main__ - Step 128714: {'lr': 2.5090727231325105e-05, 'samples': 24713088, 'steps': 128713, 'loss/train': 0.7974307537078857} 08/31/2021 12:33:48 - INFO - __main__ - Step 128715: {'lr': 2.5088410153561614e-05, 'samples': 24713280, 'steps': 128714, 'loss/train': 1.0742162466049194} 08/31/2021 12:33:48 - INFO - __main__ - Step 128716: {'lr': 2.5086093177139835e-05, 'samples': 24713472, 'steps': 128715, 'loss/train': 1.339911699295044} 08/31/2021 12:33:49 - INFO - __main__ - Step 128717: {'lr': 2.5083776302060768e-05, 'samples': 24713664, 'steps': 128716, 'loss/train': 0.9104018807411194} 08/31/2021 12:33:49 - INFO - __main__ - Step 128718: {'lr': 2.5081459528325496e-05, 'samples': 24713856, 'steps': 128717, 'loss/train': 0.038727015256881714} 08/31/2021 12:33:51 - INFO - __main__ - Step 128719: {'lr': 2.5079142855935043e-05, 'samples': 24714048, 'steps': 128718, 'loss/train': 1.0529520511627197} 08/31/2021 12:33:51 - INFO - __main__ - Step 128720: {'lr': 2.507682628489047e-05, 'samples': 24714240, 'steps': 128719, 'loss/train': 1.2880946397781372} 08/31/2021 12:33:51 - INFO - __main__ - Step 128721: {'lr': 2.50745098151928e-05, 'samples': 24714432, 'steps': 128720, 'loss/train': 0.7223376631736755} 08/31/2021 12:33:52 - INFO - __main__ - Step 128722: {'lr': 2.5072193446843085e-05, 'samples': 24714624, 'steps': 128721, 'loss/train': 1.1360138654708862} 08/31/2021 12:33:52 - INFO - __main__ - Step 128723: {'lr': 2.5069877179842353e-05, 'samples': 24714816, 'steps': 128722, 'loss/train': 1.6251684427261353} 08/31/2021 12:33:54 - INFO - __main__ - Step 128724: {'lr': 2.5067561014191692e-05, 'samples': 24715008, 'steps': 128723, 'loss/train': 0.7415406107902527} 08/31/2021 12:33:55 - INFO - __main__ - Step 128725: {'lr': 2.506524494989215e-05, 'samples': 24715200, 'steps': 128724, 'loss/train': 1.7360206842422485} 08/31/2021 12:33:55 - INFO - __main__ - Step 128726: {'lr': 2.5062928986944677e-05, 'samples': 24715392, 'steps': 128725, 'loss/train': 0.6607796549797058} 08/31/2021 12:33:55 - INFO - __main__ - Step 128727: {'lr': 2.5060613125350408e-05, 'samples': 24715584, 'steps': 128726, 'loss/train': 0.964201033115387} 08/31/2021 12:33:56 - INFO - __main__ - Step 128728: {'lr': 2.505829736511034e-05, 'samples': 24715776, 'steps': 128727, 'loss/train': 1.1744354963302612} 08/31/2021 12:33:56 - INFO - __main__ - Step 128729: {'lr': 2.5055981706225527e-05, 'samples': 24715968, 'steps': 128728, 'loss/train': 1.214237928390503} 08/31/2021 12:33:58 - INFO - __main__ - Step 128730: {'lr': 2.5053666148697e-05, 'samples': 24716160, 'steps': 128729, 'loss/train': 1.5112504959106445} 08/31/2021 12:33:58 - INFO - __main__ - Step 128731: {'lr': 2.5051350692525842e-05, 'samples': 24716352, 'steps': 128730, 'loss/train': 1.2849048376083374} 08/31/2021 12:33:59 - INFO - __main__ - Step 128732: {'lr': 2.504903533771308e-05, 'samples': 24716544, 'steps': 128731, 'loss/train': 0.6166523098945618} 08/31/2021 12:33:59 - INFO - __main__ - Step 128733: {'lr': 2.5046720084259734e-05, 'samples': 24716736, 'steps': 128732, 'loss/train': 1.3700300455093384} 08/31/2021 12:33:59 - INFO - __main__ - Step 128734: {'lr': 2.5044404932166892e-05, 'samples': 24716928, 'steps': 128733, 'loss/train': 0.015204677358269691} 08/31/2021 12:34:00 - INFO - __main__ - Step 128735: {'lr': 2.5042089881435555e-05, 'samples': 24717120, 'steps': 128734, 'loss/train': 1.435721755027771} 08/31/2021 12:34:01 - INFO - __main__ - Step 128736: {'lr': 2.5039774932066774e-05, 'samples': 24717312, 'steps': 128735, 'loss/train': 1.1407570838928223} 08/31/2021 12:34:02 - INFO - __main__ - Step 128737: {'lr': 2.5037460084061602e-05, 'samples': 24717504, 'steps': 128736, 'loss/train': 1.0170096158981323} 08/31/2021 12:34:02 - INFO - __main__ - Step 128738: {'lr': 2.5035145337421073e-05, 'samples': 24717696, 'steps': 128737, 'loss/train': 0.04206245392560959} 08/31/2021 12:34:03 - INFO - __main__ - Step 128739: {'lr': 2.5032830692146292e-05, 'samples': 24717888, 'steps': 128738, 'loss/train': 1.0750075578689575} 08/31/2021 12:34:03 - INFO - __main__ - Step 128740: {'lr': 2.5030516148238203e-05, 'samples': 24718080, 'steps': 128739, 'loss/train': 0.8529367446899414} 08/31/2021 12:34:05 - INFO - __main__ - Step 128741: {'lr': 2.502820170569789e-05, 'samples': 24718272, 'steps': 128740, 'loss/train': 1.1761549711227417} 08/31/2021 12:34:06 - INFO - __main__ - Step 128742: {'lr': 2.502588736452638e-05, 'samples': 24718464, 'steps': 128741, 'loss/train': 1.2271219491958618} 08/31/2021 12:34:06 - INFO - __main__ - Step 128743: {'lr': 2.5023573124724753e-05, 'samples': 24718656, 'steps': 128742, 'loss/train': 0.7055894136428833} 08/31/2021 12:34:06 - INFO - __main__ - Step 128744: {'lr': 2.5021258986294036e-05, 'samples': 24718848, 'steps': 128743, 'loss/train': 1.48353111743927} 08/31/2021 12:34:07 - INFO - __main__ - Step 128745: {'lr': 2.501894494923526e-05, 'samples': 24719040, 'steps': 128744, 'loss/train': 0.5928045511245728} 08/31/2021 12:34:07 - INFO - __main__ - Step 128746: {'lr': 2.501663101354948e-05, 'samples': 24719232, 'steps': 128745, 'loss/train': 0.7895068526268005} 08/31/2021 12:34:08 - INFO - __main__ - Step 128747: {'lr': 2.5014317179237717e-05, 'samples': 24719424, 'steps': 128746, 'loss/train': 0.3675670027732849} 08/31/2021 12:34:09 - INFO - __main__ - Step 128748: {'lr': 2.5012003446301028e-05, 'samples': 24719616, 'steps': 128747, 'loss/train': 1.1035188436508179} 08/31/2021 12:34:09 - INFO - __main__ - Step 128749: {'lr': 2.50096898147405e-05, 'samples': 24719808, 'steps': 128748, 'loss/train': 1.069900393486023} 08/31/2021 12:34:10 - INFO - __main__ - Step 128750: {'lr': 2.5007376284557098e-05, 'samples': 24720000, 'steps': 128749, 'loss/train': 1.0974085330963135} 08/31/2021 12:34:10 - INFO - __main__ - Step 128751: {'lr': 2.500506285575191e-05, 'samples': 24720192, 'steps': 128750, 'loss/train': 1.0611631870269775} 08/31/2021 12:34:12 - INFO - __main__ - Step 128752: {'lr': 2.5002749528326014e-05, 'samples': 24720384, 'steps': 128751, 'loss/train': 0.9473064541816711} 08/31/2021 12:34:12 - INFO - __main__ - Step 128753: {'lr': 2.5000436302280354e-05, 'samples': 24720576, 'steps': 128752, 'loss/train': 1.381663203239441} 08/31/2021 12:34:12 - INFO - __main__ - Step 128754: {'lr': 2.4998123177616043e-05, 'samples': 24720768, 'steps': 128753, 'loss/train': 1.2412285804748535} 08/31/2021 12:34:13 - INFO - __main__ - Step 128755: {'lr': 2.499581015433411e-05, 'samples': 24720960, 'steps': 128754, 'loss/train': 1.5879281759262085} 08/31/2021 12:34:13 - INFO - __main__ - Step 128756: {'lr': 2.4993497232435574e-05, 'samples': 24721152, 'steps': 128755, 'loss/train': 0.42969194054603577} 08/31/2021 12:34:15 - INFO - __main__ - Step 128757: {'lr': 2.4991184411921496e-05, 'samples': 24721344, 'steps': 128756, 'loss/train': 0.7049104571342468} 08/31/2021 12:34:15 - INFO - __main__ - Step 128758: {'lr': 2.498887169279293e-05, 'samples': 24721536, 'steps': 128757, 'loss/train': 0.6682202219963074} 08/31/2021 12:34:15 - INFO - __main__ - Step 128759: {'lr': 2.49865590750509e-05, 'samples': 24721728, 'steps': 128758, 'loss/train': 0.7663105130195618} 08/31/2021 12:34:16 - INFO - __main__ - Step 128760: {'lr': 2.498424655869644e-05, 'samples': 24721920, 'steps': 128759, 'loss/train': 1.0649884939193726} 08/31/2021 12:34:16 - INFO - __main__ - Step 128761: {'lr': 2.4981934143730624e-05, 'samples': 24722112, 'steps': 128760, 'loss/train': 1.0256694555282593} 08/31/2021 12:34:18 - INFO - __main__ - Step 128762: {'lr': 2.4979621830154482e-05, 'samples': 24722304, 'steps': 128761, 'loss/train': 1.3385010957717896} 08/31/2021 12:34:18 - INFO - __main__ - Step 128763: {'lr': 2.497730961796904e-05, 'samples': 24722496, 'steps': 128762, 'loss/train': 1.348799228668213} 08/31/2021 12:34:18 - INFO - __main__ - Step 128764: {'lr': 2.497499750717533e-05, 'samples': 24722688, 'steps': 128763, 'loss/train': 1.130948781967163} 08/31/2021 12:34:19 - INFO - __main__ - Step 128765: {'lr': 2.4972685497774485e-05, 'samples': 24722880, 'steps': 128764, 'loss/train': 1.7228502035140991} 08/31/2021 12:34:19 - INFO - __main__ - Step 128766: {'lr': 2.497037358976742e-05, 'samples': 24723072, 'steps': 128765, 'loss/train': 0.021756375208497047} 08/31/2021 12:34:21 - INFO - __main__ - Step 128767: {'lr': 2.496806178315525e-05, 'samples': 24723264, 'steps': 128766, 'loss/train': 0.8779261708259583} 08/31/2021 12:34:21 - INFO - __main__ - Step 128768: {'lr': 2.4965750077939e-05, 'samples': 24723456, 'steps': 128767, 'loss/train': 1.2539259195327759} 08/31/2021 12:34:21 - INFO - __main__ - Step 128769: {'lr': 2.4963438474119692e-05, 'samples': 24723648, 'steps': 128768, 'loss/train': 2.268608808517456} 08/31/2021 12:34:22 - INFO - __main__ - Step 128770: {'lr': 2.4961126971698387e-05, 'samples': 24723840, 'steps': 128769, 'loss/train': 0.9033258557319641} 08/31/2021 12:34:22 - INFO - __main__ - Step 128771: {'lr': 2.4958815570676112e-05, 'samples': 24724032, 'steps': 128770, 'loss/train': 0.8834319710731506} 08/31/2021 12:34:24 - INFO - __main__ - Step 128772: {'lr': 2.4956504271053946e-05, 'samples': 24724224, 'steps': 128771, 'loss/train': 0.22681882977485657} 08/31/2021 12:34:24 - INFO - __main__ - Step 128773: {'lr': 2.4954193072832894e-05, 'samples': 24724416, 'steps': 128772, 'loss/train': 1.0349825620651245} 08/31/2021 12:34:24 - INFO - __main__ - Step 128774: {'lr': 2.495188197601403e-05, 'samples': 24724608, 'steps': 128773, 'loss/train': 1.0264062881469727} 08/31/2021 12:34:25 - INFO - __main__ - Step 128775: {'lr': 2.4949570980598358e-05, 'samples': 24724800, 'steps': 128774, 'loss/train': 0.6765866875648499} 08/31/2021 12:34:25 - INFO - __main__ - Step 128776: {'lr': 2.494726008658693e-05, 'samples': 24724992, 'steps': 128775, 'loss/train': 1.273537278175354} 08/31/2021 12:34:26 - INFO - __main__ - Step 128777: {'lr': 2.4944949293980805e-05, 'samples': 24725184, 'steps': 128776, 'loss/train': 0.4809015095233917} 08/31/2021 12:34:27 - INFO - __main__ - Step 128778: {'lr': 2.494263860278101e-05, 'samples': 24725376, 'steps': 128777, 'loss/train': 1.2028377056121826} 08/31/2021 12:34:27 - INFO - __main__ - Step 128779: {'lr': 2.494032801298865e-05, 'samples': 24725568, 'steps': 128778, 'loss/train': 1.207876205444336} 08/31/2021 12:34:28 - INFO - __main__ - Step 128780: {'lr': 2.4938017524604646e-05, 'samples': 24725760, 'steps': 128779, 'loss/train': 0.11308693885803223} 08/31/2021 12:34:28 - INFO - __main__ - Step 128781: {'lr': 2.4935707137630103e-05, 'samples': 24725952, 'steps': 128780, 'loss/train': 1.4654935598373413} 08/31/2021 12:34:28 - INFO - __main__ - Step 128782: {'lr': 2.4933396852066054e-05, 'samples': 24726144, 'steps': 128781, 'loss/train': 0.9167124032974243} 08/31/2021 12:34:30 - INFO - __main__ - Step 128783: {'lr': 2.493108666791355e-05, 'samples': 24726336, 'steps': 128782, 'loss/train': 1.6921437978744507} 08/31/2021 12:34:31 - INFO - __main__ - Step 128784: {'lr': 2.4928776585173618e-05, 'samples': 24726528, 'steps': 128783, 'loss/train': 2.1449708938598633} 08/31/2021 12:34:31 - INFO - __main__ - Step 128785: {'lr': 2.4926466603847287e-05, 'samples': 24726720, 'steps': 128784, 'loss/train': 0.4242994487285614} 08/31/2021 12:34:32 - INFO - __main__ - Step 128786: {'lr': 2.492415672393564e-05, 'samples': 24726912, 'steps': 128785, 'loss/train': 0.7665435671806335} 08/31/2021 12:34:32 - INFO - __main__ - Step 128787: {'lr': 2.4921846945439695e-05, 'samples': 24727104, 'steps': 128786, 'loss/train': 0.13825511932373047} 08/31/2021 12:34:34 - INFO - __main__ - Step 128788: {'lr': 2.4919537268360494e-05, 'samples': 24727296, 'steps': 128787, 'loss/train': 1.3347373008728027} 08/31/2021 12:34:34 - INFO - __main__ - Step 128789: {'lr': 2.491722769269905e-05, 'samples': 24727488, 'steps': 128788, 'loss/train': 1.0739942789077759} 08/31/2021 12:34:34 - INFO - __main__ - Step 128790: {'lr': 2.4914918218456455e-05, 'samples': 24727680, 'steps': 128789, 'loss/train': 0.5068960189819336} 08/31/2021 12:34:35 - INFO - __main__ - Step 128791: {'lr': 2.491260884563373e-05, 'samples': 24727872, 'steps': 128790, 'loss/train': 0.02831999398767948} 08/31/2021 12:34:35 - INFO - __main__ - Step 128792: {'lr': 2.4910299574231938e-05, 'samples': 24728064, 'steps': 128791, 'loss/train': 1.1513751745224} 08/31/2021 12:34:36 - INFO - __main__ - Step 128793: {'lr': 2.4907990404252067e-05, 'samples': 24728256, 'steps': 128792, 'loss/train': 0.014790354296565056} 08/31/2021 12:34:38 - INFO - __main__ - Step 128794: {'lr': 2.490568133569515e-05, 'samples': 24728448, 'steps': 128793, 'loss/train': 1.431888222694397} 08/31/2021 12:34:38 - INFO - __main__ - Step 128795: {'lr': 2.49033723685623e-05, 'samples': 24728640, 'steps': 128794, 'loss/train': 1.4292521476745605} 08/31/2021 12:34:39 - INFO - __main__ - Step 128796: {'lr': 2.4901063502854482e-05, 'samples': 24728832, 'steps': 128795, 'loss/train': 0.04453135281801224} 08/31/2021 12:34:39 - INFO - __main__ - Step 128797: {'lr': 2.489875473857278e-05, 'samples': 24729024, 'steps': 128796, 'loss/train': 0.8697612881660461} 08/31/2021 12:34:39 - INFO - __main__ - Step 128798: {'lr': 2.4896446075718254e-05, 'samples': 24729216, 'steps': 128797, 'loss/train': 1.0930894613265991} 08/31/2021 12:34:41 - INFO - __main__ - Step 128799: {'lr': 2.489413751429187e-05, 'samples': 24729408, 'steps': 128798, 'loss/train': 1.2325029373168945} 08/31/2021 12:34:41 - INFO - __main__ - Step 128800: {'lr': 2.489182905429474e-05, 'samples': 24729600, 'steps': 128799, 'loss/train': 1.1541322469711304} 08/31/2021 12:34:42 - INFO - __main__ - Step 128801: {'lr': 2.488952069572789e-05, 'samples': 24729792, 'steps': 128800, 'loss/train': 0.8627209663391113} 08/31/2021 12:34:42 - INFO - __main__ - Step 128802: {'lr': 2.4887212438592322e-05, 'samples': 24729984, 'steps': 128801, 'loss/train': 1.0904043912887573} 08/31/2021 12:34:42 - INFO - __main__ - Step 128803: {'lr': 2.4884904282889113e-05, 'samples': 24730176, 'steps': 128802, 'loss/train': 1.632261872291565} 08/31/2021 12:34:43 - INFO - __main__ - Step 128804: {'lr': 2.48825962286193e-05, 'samples': 24730368, 'steps': 128803, 'loss/train': 0.525570273399353} 08/31/2021 12:34:44 - INFO - __main__ - Step 128805: {'lr': 2.4880288275783896e-05, 'samples': 24730560, 'steps': 128804, 'loss/train': 1.2365968227386475} 08/31/2021 12:34:45 - INFO - __main__ - Step 128806: {'lr': 2.487798042438402e-05, 'samples': 24730752, 'steps': 128805, 'loss/train': 1.1767922639846802} 08/31/2021 12:34:45 - INFO - __main__ - Step 128807: {'lr': 2.487567267442062e-05, 'samples': 24730944, 'steps': 128806, 'loss/train': 1.6287178993225098} 08/31/2021 12:34:45 - INFO - __main__ - Step 128808: {'lr': 2.4873365025894738e-05, 'samples': 24731136, 'steps': 128807, 'loss/train': 1.3399125337600708} 08/31/2021 12:34:46 - INFO - __main__ - Step 128809: {'lr': 2.487105747880747e-05, 'samples': 24731328, 'steps': 128808, 'loss/train': 1.0575528144836426} 08/31/2021 12:34:47 - INFO - __main__ - Step 128810: {'lr': 2.4868750033159803e-05, 'samples': 24731520, 'steps': 128809, 'loss/train': 1.176546573638916} 08/31/2021 12:34:48 - INFO - __main__ - Step 128811: {'lr': 2.486644268895283e-05, 'samples': 24731712, 'steps': 128810, 'loss/train': 1.1777563095092773} 08/31/2021 12:34:48 - INFO - __main__ - Step 128812: {'lr': 2.486413544618754e-05, 'samples': 24731904, 'steps': 128811, 'loss/train': 1.0321849584579468} 08/31/2021 12:34:49 - INFO - __main__ - Step 128813: {'lr': 2.4861828304865026e-05, 'samples': 24732096, 'steps': 128812, 'loss/train': 1.7657731771469116} 08/31/2021 12:34:49 - INFO - __main__ - Step 128814: {'lr': 2.4859521264986277e-05, 'samples': 24732288, 'steps': 128813, 'loss/train': 0.03980354219675064} 08/31/2021 12:34:51 - INFO - __main__ - Step 128815: {'lr': 2.4857214326552358e-05, 'samples': 24732480, 'steps': 128814, 'loss/train': 1.1122301816940308} 08/31/2021 12:34:51 - INFO - __main__ - Step 128816: {'lr': 2.4854907489564316e-05, 'samples': 24732672, 'steps': 128815, 'loss/train': 0.21133174002170563} 08/31/2021 12:34:52 - INFO - __main__ - Step 128817: {'lr': 2.4852600754023153e-05, 'samples': 24732864, 'steps': 128816, 'loss/train': 1.1994467973709106} 08/31/2021 12:34:52 - INFO - __main__ - Step 128818: {'lr': 2.485029411992995e-05, 'samples': 24733056, 'steps': 128817, 'loss/train': 0.909763514995575} 08/31/2021 12:34:52 - INFO - __main__ - Step 128819: {'lr': 2.4847987587285765e-05, 'samples': 24733248, 'steps': 128818, 'loss/train': 0.14862175285816193} 08/31/2021 12:34:54 - INFO - __main__ - Step 128820: {'lr': 2.4845681156091567e-05, 'samples': 24733440, 'steps': 128819, 'loss/train': 1.431134819984436} 08/31/2021 12:34:54 - INFO - __main__ - Step 128821: {'lr': 2.4843374826348435e-05, 'samples': 24733632, 'steps': 128820, 'loss/train': 0.922430157661438} 08/31/2021 12:34:55 - INFO - __main__ - Step 128822: {'lr': 2.4841068598057405e-05, 'samples': 24733824, 'steps': 128821, 'loss/train': 1.4831645488739014} 08/31/2021 12:34:55 - INFO - __main__ - Step 128823: {'lr': 2.4838762471219495e-05, 'samples': 24734016, 'steps': 128822, 'loss/train': 0.9816734790802002} 08/31/2021 12:34:55 - INFO - __main__ - Step 128824: {'lr': 2.4836456445835766e-05, 'samples': 24734208, 'steps': 128823, 'loss/train': 0.8273258209228516} 08/31/2021 12:34:57 - INFO - __main__ - Step 128825: {'lr': 2.483415052190727e-05, 'samples': 24734400, 'steps': 128824, 'loss/train': 1.5992484092712402} 08/31/2021 12:34:57 - INFO - __main__ - Step 128826: {'lr': 2.483184469943503e-05, 'samples': 24734592, 'steps': 128825, 'loss/train': 0.6503230333328247} 08/31/2021 12:34:58 - INFO - __main__ - Step 128827: {'lr': 2.482953897842008e-05, 'samples': 24734784, 'steps': 128826, 'loss/train': 1.0719261169433594} 08/31/2021 12:34:58 - INFO - __main__ - Step 128828: {'lr': 2.482723335886347e-05, 'samples': 24734976, 'steps': 128827, 'loss/train': 1.0437350273132324} 08/31/2021 12:34:58 - INFO - __main__ - Step 128829: {'lr': 2.4824927840766232e-05, 'samples': 24735168, 'steps': 128828, 'loss/train': 0.6379813551902771} 08/31/2021 12:35:00 - INFO - __main__ - Step 128830: {'lr': 2.4822622424129416e-05, 'samples': 24735360, 'steps': 128829, 'loss/train': 1.2548454999923706} 08/31/2021 12:35:00 - INFO - __main__ - Step 128831: {'lr': 2.4820317108954048e-05, 'samples': 24735552, 'steps': 128830, 'loss/train': 0.4193175435066223} 08/31/2021 12:35:01 - INFO - __main__ - Step 128832: {'lr': 2.4818011895241162e-05, 'samples': 24735744, 'steps': 128831, 'loss/train': 0.7507947683334351} 08/31/2021 12:35:01 - INFO - __main__ - Step 128833: {'lr': 2.481570678299186e-05, 'samples': 24735936, 'steps': 128832, 'loss/train': 0.4547192454338074} 08/31/2021 12:35:01 - INFO - __main__ - Step 128834: {'lr': 2.481340177220706e-05, 'samples': 24736128, 'steps': 128833, 'loss/train': 0.8271521925926208} 08/31/2021 12:35:03 - INFO - __main__ - Step 128835: {'lr': 2.481109686288788e-05, 'samples': 24736320, 'steps': 128834, 'loss/train': 0.9786778092384338} 08/31/2021 12:35:04 - INFO - __main__ - Step 128836: {'lr': 2.4808792055035363e-05, 'samples': 24736512, 'steps': 128835, 'loss/train': 0.5139637589454651} 08/31/2021 12:35:04 - INFO - __main__ - Step 128837: {'lr': 2.4806487348650486e-05, 'samples': 24736704, 'steps': 128836, 'loss/train': 0.6418637633323669} 08/31/2021 12:35:05 - INFO - __main__ - Step 128838: {'lr': 2.4804182743734362e-05, 'samples': 24736896, 'steps': 128837, 'loss/train': 3.266192674636841} 08/31/2021 12:35:05 - INFO - __main__ - Step 128839: {'lr': 2.480187824028801e-05, 'samples': 24737088, 'steps': 128838, 'loss/train': 0.024027550593018532} 08/31/2021 12:35:05 - INFO - __main__ - Step 128840: {'lr': 2.479957383831244e-05, 'samples': 24737280, 'steps': 128839, 'loss/train': 0.09294242411851883} 08/31/2021 12:35:06 - INFO - __main__ - Step 128841: {'lr': 2.47972695378087e-05, 'samples': 24737472, 'steps': 128840, 'loss/train': 0.6652626991271973} 08/31/2021 12:35:07 - INFO - __main__ - Step 128842: {'lr': 2.479496533877784e-05, 'samples': 24737664, 'steps': 128841, 'loss/train': 0.6034200191497803} 08/31/2021 12:35:08 - INFO - __main__ - Step 128843: {'lr': 2.47926612412209e-05, 'samples': 24737856, 'steps': 128842, 'loss/train': 1.0725085735321045} 08/31/2021 12:35:08 - INFO - __main__ - Step 128844: {'lr': 2.4790357245138895e-05, 'samples': 24738048, 'steps': 128843, 'loss/train': 0.551476776599884} 08/31/2021 12:35:08 - INFO - __main__ - Step 128845: {'lr': 2.4788053350532885e-05, 'samples': 24738240, 'steps': 128844, 'loss/train': 0.7418286204338074} 08/31/2021 12:35:09 - INFO - __main__ - Step 128846: {'lr': 2.4785749557403952e-05, 'samples': 24738432, 'steps': 128845, 'loss/train': 0.3795192241668701} 08/31/2021 12:35:10 - INFO - __main__ - Step 128847: {'lr': 2.4783445865753067e-05, 'samples': 24738624, 'steps': 128846, 'loss/train': 1.0031342506408691} 08/31/2021 12:35:11 - INFO - __main__ - Step 128848: {'lr': 2.478114227558126e-05, 'samples': 24738816, 'steps': 128847, 'loss/train': 1.0119596719741821} 08/31/2021 12:35:11 - INFO - __main__ - Step 128849: {'lr': 2.477883878688958e-05, 'samples': 24739008, 'steps': 128848, 'loss/train': 0.6433451771736145} 08/31/2021 12:35:11 - INFO - __main__ - Step 128850: {'lr': 2.477653539967911e-05, 'samples': 24739200, 'steps': 128849, 'loss/train': 1.3007503747940063} 08/31/2021 12:35:12 - INFO - __main__ - Step 128851: {'lr': 2.477423211395083e-05, 'samples': 24739392, 'steps': 128850, 'loss/train': 0.11728158593177795} 08/31/2021 12:35:14 - INFO - __main__ - Step 128852: {'lr': 2.477192892970584e-05, 'samples': 24739584, 'steps': 128851, 'loss/train': 1.4539850950241089} 08/31/2021 12:35:14 - INFO - __main__ - Step 128853: {'lr': 2.4769625846945116e-05, 'samples': 24739776, 'steps': 128852, 'loss/train': 1.4538570642471313} 08/31/2021 12:35:14 - INFO - __main__ - Step 128854: {'lr': 2.476732286566971e-05, 'samples': 24739968, 'steps': 128853, 'loss/train': 1.3086100816726685} 08/31/2021 12:35:15 - INFO - __main__ - Step 128855: {'lr': 2.476501998588071e-05, 'samples': 24740160, 'steps': 128854, 'loss/train': 0.4688953757286072} 08/31/2021 12:35:15 - INFO - __main__ - Step 128856: {'lr': 2.4762717207579084e-05, 'samples': 24740352, 'steps': 128855, 'loss/train': 0.5551912784576416} 08/31/2021 12:35:17 - INFO - __main__ - Step 128857: {'lr': 2.476041453076594e-05, 'samples': 24740544, 'steps': 128856, 'loss/train': 1.7764198780059814} 08/31/2021 12:35:17 - INFO - __main__ - Step 128858: {'lr': 2.4758111955442254e-05, 'samples': 24740736, 'steps': 128857, 'loss/train': 0.04187450557947159} 08/31/2021 12:35:18 - INFO - __main__ - Step 128859: {'lr': 2.4755809481609075e-05, 'samples': 24740928, 'steps': 128858, 'loss/train': 0.8237946033477783} 08/31/2021 12:35:18 - INFO - __main__ - Step 128860: {'lr': 2.475350710926752e-05, 'samples': 24741120, 'steps': 128859, 'loss/train': 0.9489622712135315} 08/31/2021 12:35:18 - INFO - __main__ - Step 128861: {'lr': 2.4751204838418502e-05, 'samples': 24741312, 'steps': 128860, 'loss/train': 0.9038130640983582} 08/31/2021 12:35:19 - INFO - __main__ - Step 128862: {'lr': 2.47489026690631e-05, 'samples': 24741504, 'steps': 128861, 'loss/train': 0.5608307719230652} 08/31/2021 12:35:20 - INFO - __main__ - Step 128863: {'lr': 2.47466006012024e-05, 'samples': 24741696, 'steps': 128862, 'loss/train': 0.6439523100852966} 08/31/2021 12:35:21 - INFO - __main__ - Step 128864: {'lr': 2.4744298634837375e-05, 'samples': 24741888, 'steps': 128863, 'loss/train': 0.9314361810684204} 08/31/2021 12:35:21 - INFO - __main__ - Step 128865: {'lr': 2.4741996769969134e-05, 'samples': 24742080, 'steps': 128864, 'loss/train': 1.0779080390930176} 08/31/2021 12:35:21 - INFO - __main__ - Step 128866: {'lr': 2.4739695006598643e-05, 'samples': 24742272, 'steps': 128865, 'loss/train': 1.591404676437378} 08/31/2021 12:35:22 - INFO - __main__ - Step 128867: {'lr': 2.4737393344726965e-05, 'samples': 24742464, 'steps': 128866, 'loss/train': 1.4265367984771729} 08/31/2021 12:35:23 - INFO - __main__ - Step 128868: {'lr': 2.473509178435515e-05, 'samples': 24742656, 'steps': 128867, 'loss/train': 0.9695351719856262} 08/31/2021 12:35:24 - INFO - __main__ - Step 128869: {'lr': 2.473279032548423e-05, 'samples': 24742848, 'steps': 128868, 'loss/train': 1.4611399173736572} 08/31/2021 12:35:24 - INFO - __main__ - Step 128870: {'lr': 2.4730488968115223e-05, 'samples': 24743040, 'steps': 128869, 'loss/train': 0.9309729337692261} 08/31/2021 12:35:24 - INFO - __main__ - Step 128871: {'lr': 2.472818771224922e-05, 'samples': 24743232, 'steps': 128870, 'loss/train': 1.4556719064712524} 08/31/2021 12:35:25 - INFO - __main__ - Step 128872: {'lr': 2.4725886557887183e-05, 'samples': 24743424, 'steps': 128871, 'loss/train': 1.211801528930664} 08/31/2021 12:35:26 - INFO - __main__ - Step 128873: {'lr': 2.4723585505030232e-05, 'samples': 24743616, 'steps': 128872, 'loss/train': 0.9548770189285278} 08/31/2021 12:35:27 - INFO - __main__ - Step 128874: {'lr': 2.4721284553679335e-05, 'samples': 24743808, 'steps': 128873, 'loss/train': 0.033523328602313995} 08/31/2021 12:35:27 - INFO - __main__ - Step 128875: {'lr': 2.4718983703835517e-05, 'samples': 24744000, 'steps': 128874, 'loss/train': 1.3434040546417236} 08/31/2021 12:35:27 - INFO - __main__ - Step 128876: {'lr': 2.471668295549989e-05, 'samples': 24744192, 'steps': 128875, 'loss/train': 1.296844244003296} 08/31/2021 12:35:28 - INFO - __main__ - Step 128877: {'lr': 2.4714382308673428e-05, 'samples': 24744384, 'steps': 128876, 'loss/train': 0.9128938317298889} 08/31/2021 12:35:29 - INFO - __main__ - Step 128878: {'lr': 2.471208176335718e-05, 'samples': 24744576, 'steps': 128877, 'loss/train': 1.353492259979248} 08/31/2021 12:35:30 - INFO - __main__ - Step 128879: {'lr': 2.4709781319552205e-05, 'samples': 24744768, 'steps': 128878, 'loss/train': 1.4298286437988281} 08/31/2021 12:35:30 - INFO - __main__ - Step 128880: {'lr': 2.470748097725953e-05, 'samples': 24744960, 'steps': 128879, 'loss/train': 0.7636908888816833} 08/31/2021 12:35:31 - INFO - __main__ - Step 128881: {'lr': 2.4705180736480176e-05, 'samples': 24745152, 'steps': 128880, 'loss/train': 1.3856661319732666} 08/31/2021 12:35:31 - INFO - __main__ - Step 128882: {'lr': 2.4702880597215178e-05, 'samples': 24745344, 'steps': 128881, 'loss/train': 1.4035396575927734} 08/31/2021 12:35:32 - INFO - __main__ - Step 128883: {'lr': 2.4700580559465615e-05, 'samples': 24745536, 'steps': 128882, 'loss/train': 1.3893027305603027} 08/31/2021 12:35:33 - INFO - __main__ - Step 128884: {'lr': 2.4698280623232483e-05, 'samples': 24745728, 'steps': 128883, 'loss/train': 1.8374024629592896} 08/31/2021 12:35:33 - INFO - __main__ - Step 128885: {'lr': 2.4695980788516815e-05, 'samples': 24745920, 'steps': 128884, 'loss/train': 1.350350022315979} 08/31/2021 12:35:34 - INFO - __main__ - Step 128886: {'lr': 2.4693681055319717e-05, 'samples': 24746112, 'steps': 128885, 'loss/train': 0.08240918070077896} 08/31/2021 12:35:34 - INFO - __main__ - Step 128887: {'lr': 2.4691381423642133e-05, 'samples': 24746304, 'steps': 128886, 'loss/train': 1.497563362121582} 08/31/2021 12:35:36 - INFO - __main__ - Step 128888: {'lr': 2.468908189348512e-05, 'samples': 24746496, 'steps': 128887, 'loss/train': 0.9003134369850159} 08/31/2021 12:35:36 - INFO - __main__ - Step 128889: {'lr': 2.4686782464849733e-05, 'samples': 24746688, 'steps': 128888, 'loss/train': 0.944500744342804} 08/31/2021 12:35:36 - INFO - __main__ - Step 128890: {'lr': 2.4684483137737024e-05, 'samples': 24746880, 'steps': 128889, 'loss/train': 0.8158571124076843} 08/31/2021 12:35:37 - INFO - __main__ - Step 128891: {'lr': 2.4682183912147994e-05, 'samples': 24747072, 'steps': 128890, 'loss/train': 1.3128671646118164} 08/31/2021 12:35:37 - INFO - __main__ - Step 128892: {'lr': 2.4679884788083696e-05, 'samples': 24747264, 'steps': 128891, 'loss/train': 1.6515873670578003} 08/31/2021 12:35:37 - INFO - __main__ - Step 128893: {'lr': 2.4677585765545157e-05, 'samples': 24747456, 'steps': 128892, 'loss/train': 0.9907174706459045} 08/31/2021 12:35:39 - INFO - __main__ - Step 128894: {'lr': 2.4675286844533433e-05, 'samples': 24747648, 'steps': 128893, 'loss/train': 0.5924416184425354} 08/31/2021 12:35:39 - INFO - __main__ - Step 128895: {'lr': 2.4672988025049552e-05, 'samples': 24747840, 'steps': 128894, 'loss/train': 0.9207948446273804} 08/31/2021 12:35:40 - INFO - __main__ - Step 128896: {'lr': 2.467068930709454e-05, 'samples': 24748032, 'steps': 128895, 'loss/train': 0.718095064163208} 08/31/2021 12:35:40 - INFO - __main__ - Step 128897: {'lr': 2.466839069066945e-05, 'samples': 24748224, 'steps': 128896, 'loss/train': 2.1981911659240723} 08/31/2021 12:35:40 - INFO - __main__ - Step 128898: {'lr': 2.4666092175775283e-05, 'samples': 24748416, 'steps': 128897, 'loss/train': 1.2778428792953491} 08/31/2021 12:35:42 - INFO - __main__ - Step 128899: {'lr': 2.4663793762413096e-05, 'samples': 24748608, 'steps': 128898, 'loss/train': 0.6115961670875549} 08/31/2021 12:35:42 - INFO - __main__ - Step 128900: {'lr': 2.466149545058399e-05, 'samples': 24748800, 'steps': 128899, 'loss/train': 1.0695019960403442} 08/31/2021 12:35:43 - INFO - __main__ - Step 128901: {'lr': 2.4659197240288893e-05, 'samples': 24748992, 'steps': 128900, 'loss/train': 1.1169824600219727} 08/31/2021 12:35:43 - INFO - __main__ - Step 128902: {'lr': 2.465689913152888e-05, 'samples': 24749184, 'steps': 128901, 'loss/train': 1.355039358139038} 08/31/2021 12:35:43 - INFO - __main__ - Step 128903: {'lr': 2.465460112430498e-05, 'samples': 24749376, 'steps': 128902, 'loss/train': 0.7486348152160645} 08/31/2021 12:35:45 - INFO - __main__ - Step 128904: {'lr': 2.465230321861825e-05, 'samples': 24749568, 'steps': 128903, 'loss/train': 1.4343059062957764} 08/31/2021 12:35:46 - INFO - __main__ - Step 128905: {'lr': 2.465000541446971e-05, 'samples': 24749760, 'steps': 128904, 'loss/train': 0.1371082067489624} 08/31/2021 12:35:46 - INFO - __main__ - Step 128906: {'lr': 2.4647707711860394e-05, 'samples': 24749952, 'steps': 128905, 'loss/train': 1.3864939212799072} 08/31/2021 12:35:47 - INFO - __main__ - Step 128907: {'lr': 2.4645410110791354e-05, 'samples': 24750144, 'steps': 128906, 'loss/train': 0.7499850988388062} 08/31/2021 12:35:47 - INFO - __main__ - Step 128908: {'lr': 2.4643112611263618e-05, 'samples': 24750336, 'steps': 128907, 'loss/train': 1.227717638015747} 08/31/2021 12:35:48 - INFO - __main__ - Step 128909: {'lr': 2.464081521327821e-05, 'samples': 24750528, 'steps': 128908, 'loss/train': 1.2816609144210815} 08/31/2021 12:35:49 - INFO - __main__ - Step 128910: {'lr': 2.4638517916836188e-05, 'samples': 24750720, 'steps': 128909, 'loss/train': 1.2242085933685303} 08/31/2021 12:35:49 - INFO - __main__ - Step 128911: {'lr': 2.4636220721938552e-05, 'samples': 24750912, 'steps': 128910, 'loss/train': 0.8109873533248901} 08/31/2021 12:35:49 - INFO - __main__ - Step 128912: {'lr': 2.463392362858638e-05, 'samples': 24751104, 'steps': 128911, 'loss/train': 1.0942115783691406} 08/31/2021 12:35:50 - INFO - __main__ - Step 128913: {'lr': 2.4631626636780702e-05, 'samples': 24751296, 'steps': 128912, 'loss/train': 1.4754947423934937} 08/31/2021 12:35:51 - INFO - __main__ - Step 128914: {'lr': 2.4629329746522518e-05, 'samples': 24751488, 'steps': 128913, 'loss/train': 0.23773907124996185} 08/31/2021 12:35:52 - INFO - __main__ - Step 128915: {'lr': 2.462703295781285e-05, 'samples': 24751680, 'steps': 128914, 'loss/train': 0.9894925951957703} 08/31/2021 12:35:52 - INFO - __main__ - Step 128916: {'lr': 2.4624736270652787e-05, 'samples': 24751872, 'steps': 128915, 'loss/train': 1.2569531202316284} 08/31/2021 12:35:52 - INFO - __main__ - Step 128917: {'lr': 2.4622439685043324e-05, 'samples': 24752064, 'steps': 128916, 'loss/train': 1.0199346542358398} 08/31/2021 12:35:53 - INFO - __main__ - Step 128918: {'lr': 2.462014320098552e-05, 'samples': 24752256, 'steps': 128917, 'loss/train': 1.2650688886642456} 08/31/2021 12:35:54 - INFO - __main__ - Step 128919: {'lr': 2.4617846818480394e-05, 'samples': 24752448, 'steps': 128918, 'loss/train': 0.9087944030761719} 08/31/2021 12:35:55 - INFO - __main__ - Step 128920: {'lr': 2.4615550537529008e-05, 'samples': 24752640, 'steps': 128919, 'loss/train': 0.9679981470108032} 08/31/2021 12:35:55 - INFO - __main__ - Step 128921: {'lr': 2.461325435813236e-05, 'samples': 24752832, 'steps': 128920, 'loss/train': 1.611863136291504} 08/31/2021 12:35:55 - INFO - __main__ - Step 128922: {'lr': 2.46109582802915e-05, 'samples': 24753024, 'steps': 128921, 'loss/train': 1.3703281879425049} 08/31/2021 12:35:56 - INFO - __main__ - Step 128923: {'lr': 2.460866230400749e-05, 'samples': 24753216, 'steps': 128922, 'loss/train': 0.4010482430458069} 08/31/2021 12:35:57 - INFO - __main__ - Step 128924: {'lr': 2.4606366429281325e-05, 'samples': 24753408, 'steps': 128923, 'loss/train': 1.071388840675354} 08/31/2021 12:35:58 - INFO - __main__ - Step 128925: {'lr': 2.460407065611403e-05, 'samples': 24753600, 'steps': 128924, 'loss/train': 1.3593683242797852} 08/31/2021 12:35:58 - INFO - __main__ - Step 128926: {'lr': 2.460177498450669e-05, 'samples': 24753792, 'steps': 128925, 'loss/train': 0.8416380286216736} 08/31/2021 12:35:59 - INFO - __main__ - Step 128927: {'lr': 2.4599479414460336e-05, 'samples': 24753984, 'steps': 128926, 'loss/train': 0.9086191654205322} 08/31/2021 12:35:59 - INFO - __main__ - Step 128928: {'lr': 2.459718394597596e-05, 'samples': 24754176, 'steps': 128927, 'loss/train': 0.9749922752380371} 08/31/2021 12:36:00 - INFO - __main__ - Step 128929: {'lr': 2.459488857905459e-05, 'samples': 24754368, 'steps': 128928, 'loss/train': 1.2807469367980957} 08/31/2021 12:36:01 - INFO - __main__ - Step 128930: {'lr': 2.4592593313697286e-05, 'samples': 24754560, 'steps': 128929, 'loss/train': 0.1709841787815094} 08/31/2021 12:36:01 - INFO - __main__ - Step 128931: {'lr': 2.4590298149905098e-05, 'samples': 24754752, 'steps': 128930, 'loss/train': 1.3879107236862183} 08/31/2021 12:36:02 - INFO - __main__ - Step 128932: {'lr': 2.4588003087679027e-05, 'samples': 24754944, 'steps': 128931, 'loss/train': 1.0060280561447144} 08/31/2021 12:36:02 - INFO - __main__ - Step 128933: {'lr': 2.4585708127020155e-05, 'samples': 24755136, 'steps': 128932, 'loss/train': 1.006612777709961} 08/31/2021 12:36:03 - INFO - __main__ - Step 128934: {'lr': 2.4583413267929455e-05, 'samples': 24755328, 'steps': 128933, 'loss/train': 1.310767412185669} 08/31/2021 12:36:04 - INFO - __main__ - Step 128935: {'lr': 2.4581118510408007e-05, 'samples': 24755520, 'steps': 128934, 'loss/train': 1.302735686302185} 08/31/2021 12:36:04 - INFO - __main__ - Step 128936: {'lr': 2.457882385445681e-05, 'samples': 24755712, 'steps': 128935, 'loss/train': 1.3572278022766113} 08/31/2021 12:36:04 - INFO - __main__ - Step 128937: {'lr': 2.4576529300076977e-05, 'samples': 24755904, 'steps': 128936, 'loss/train': 1.430019497871399} 08/31/2021 12:36:05 - INFO - __main__ - Step 128938: {'lr': 2.457423484726942e-05, 'samples': 24756096, 'steps': 128937, 'loss/train': 1.2315342426300049} 08/31/2021 12:36:07 - INFO - __main__ - Step 128939: {'lr': 2.4571940496035254e-05, 'samples': 24756288, 'steps': 128938, 'loss/train': 1.392462134361267} 08/31/2021 12:36:07 - INFO - __main__ - Step 128940: {'lr': 2.4569646246375476e-05, 'samples': 24756480, 'steps': 128939, 'loss/train': 1.3940547704696655} 08/31/2021 12:36:08 - INFO - __main__ - Step 128941: {'lr': 2.456735209829114e-05, 'samples': 24756672, 'steps': 128940, 'loss/train': 0.9956183433532715} 08/31/2021 12:36:08 - INFO - __main__ - Step 128942: {'lr': 2.4565058051783273e-05, 'samples': 24756864, 'steps': 128941, 'loss/train': 0.014506984502077103} 08/31/2021 12:36:08 - INFO - __main__ - Step 128943: {'lr': 2.456276410685293e-05, 'samples': 24757056, 'steps': 128942, 'loss/train': 1.386566162109375} 08/31/2021 12:36:09 - INFO - __main__ - Step 128944: {'lr': 2.4560470263501112e-05, 'samples': 24757248, 'steps': 128943, 'loss/train': 1.0475308895111084} 08/31/2021 12:36:09 - INFO - __main__ - Step 128945: {'lr': 2.455817652172887e-05, 'samples': 24757440, 'steps': 128944, 'loss/train': 0.059400524944067} 08/31/2021 12:36:10 - INFO - __main__ - Step 128946: {'lr': 2.4555882881537235e-05, 'samples': 24757632, 'steps': 128945, 'loss/train': 0.8623344898223877} 08/31/2021 12:36:11 - INFO - __main__ - Step 128947: {'lr': 2.4553589342927257e-05, 'samples': 24757824, 'steps': 128946, 'loss/train': 1.292273998260498} 08/31/2021 12:36:11 - INFO - __main__ - Step 128948: {'lr': 2.4551295905899968e-05, 'samples': 24758016, 'steps': 128947, 'loss/train': 0.6934801936149597} 08/31/2021 12:36:11 - INFO - __main__ - Step 128949: {'lr': 2.4549002570456365e-05, 'samples': 24758208, 'steps': 128948, 'loss/train': 1.1945987939834595} 08/31/2021 12:36:12 - INFO - __main__ - Step 128950: {'lr': 2.45467093365975e-05, 'samples': 24758400, 'steps': 128949, 'loss/train': 0.7694916129112244} 08/31/2021 12:36:13 - INFO - __main__ - Step 128951: {'lr': 2.4544416204324403e-05, 'samples': 24758592, 'steps': 128950, 'loss/train': 1.0382745265960693} 08/31/2021 12:36:14 - INFO - __main__ - Step 128952: {'lr': 2.4542123173638105e-05, 'samples': 24758784, 'steps': 128951, 'loss/train': 1.0830459594726562} 08/31/2021 12:36:14 - INFO - __main__ - Step 128953: {'lr': 2.4539830244539652e-05, 'samples': 24758976, 'steps': 128952, 'loss/train': 1.6460942029953003} 08/31/2021 12:36:14 - INFO - __main__ - Step 128954: {'lr': 2.4537537417030076e-05, 'samples': 24759168, 'steps': 128953, 'loss/train': 1.2626605033874512} 08/31/2021 12:36:15 - INFO - __main__ - Step 128955: {'lr': 2.4535244691110403e-05, 'samples': 24759360, 'steps': 128954, 'loss/train': 1.1060763597488403} 08/31/2021 12:36:17 - INFO - __main__ - Step 128956: {'lr': 2.4532952066781662e-05, 'samples': 24759552, 'steps': 128955, 'loss/train': 0.9956223964691162} 08/31/2021 12:36:17 - INFO - __main__ - Step 128957: {'lr': 2.4530659544044905e-05, 'samples': 24759744, 'steps': 128956, 'loss/train': 0.861132800579071} 08/31/2021 12:36:18 - INFO - __main__ - Step 128958: {'lr': 2.4528367122901157e-05, 'samples': 24759936, 'steps': 128957, 'loss/train': 0.3559553623199463} 08/31/2021 12:36:18 - INFO - __main__ - Step 128959: {'lr': 2.4526074803351507e-05, 'samples': 24760128, 'steps': 128958, 'loss/train': 1.211857795715332} 08/31/2021 12:36:19 - INFO - __main__ - Step 128960: {'lr': 2.4523782585396838e-05, 'samples': 24760320, 'steps': 128959, 'loss/train': 0.1728380024433136} 08/31/2021 12:36:20 - INFO - __main__ - Step 128961: {'lr': 2.4521490469038316e-05, 'samples': 24760512, 'steps': 128960, 'loss/train': 1.4303160905838013} 08/31/2021 12:36:20 - INFO - __main__ - Step 128962: {'lr': 2.4519198454276914e-05, 'samples': 24760704, 'steps': 128961, 'loss/train': 1.5687264204025269} 08/31/2021 12:36:21 - INFO - __main__ - Step 128963: {'lr': 2.451690654111369e-05, 'samples': 24760896, 'steps': 128962, 'loss/train': 1.4439973831176758} 08/31/2021 12:36:21 - INFO - __main__ - Step 128964: {'lr': 2.4514614729549632e-05, 'samples': 24761088, 'steps': 128963, 'loss/train': 1.1907808780670166} 08/31/2021 12:36:22 - INFO - __main__ - Step 128965: {'lr': 2.4512323019585864e-05, 'samples': 24761280, 'steps': 128964, 'loss/train': 1.1510097980499268} 08/31/2021 12:36:23 - INFO - __main__ - Step 128966: {'lr': 2.451003141122332e-05, 'samples': 24761472, 'steps': 128965, 'loss/train': 1.388168215751648} 08/31/2021 12:36:24 - INFO - __main__ - Step 128967: {'lr': 2.4507739904463088e-05, 'samples': 24761664, 'steps': 128966, 'loss/train': 0.9264713525772095} 08/31/2021 12:36:24 - INFO - __main__ - Step 128968: {'lr': 2.4505448499306192e-05, 'samples': 24761856, 'steps': 128967, 'loss/train': 1.2810759544372559} 08/31/2021 12:36:24 - INFO - __main__ - Step 128969: {'lr': 2.450315719575369e-05, 'samples': 24762048, 'steps': 128968, 'loss/train': 0.32112571597099304} 08/31/2021 12:36:25 - INFO - __main__ - Step 128970: {'lr': 2.4500865993806605e-05, 'samples': 24762240, 'steps': 128969, 'loss/train': 1.2272684574127197} 08/31/2021 12:36:26 - INFO - __main__ - Step 128971: {'lr': 2.449857489346591e-05, 'samples': 24762432, 'steps': 128970, 'loss/train': 1.661487102508545} 08/31/2021 12:36:26 - INFO - __main__ - Step 128972: {'lr': 2.4496283894732657e-05, 'samples': 24762624, 'steps': 128971, 'loss/train': 0.7400380373001099} 08/31/2021 12:36:27 - INFO - __main__ - Step 128973: {'lr': 2.4493992997607905e-05, 'samples': 24762816, 'steps': 128972, 'loss/train': 1.274100422859192} 08/31/2021 12:36:27 - INFO - __main__ - Step 128974: {'lr': 2.4491702202092707e-05, 'samples': 24763008, 'steps': 128973, 'loss/train': 1.2684575319290161} 08/31/2021 12:36:28 - INFO - __main__ - Step 128975: {'lr': 2.4489411508188035e-05, 'samples': 24763200, 'steps': 128974, 'loss/train': 0.8668593764305115} 08/31/2021 12:36:29 - INFO - __main__ - Step 128976: {'lr': 2.4487120915894974e-05, 'samples': 24763392, 'steps': 128975, 'loss/train': 1.3714841604232788} 08/31/2021 12:36:29 - INFO - __main__ - Step 128977: {'lr': 2.4484830425214543e-05, 'samples': 24763584, 'steps': 128976, 'loss/train': 1.3877851963043213} 08/31/2021 12:36:30 - INFO - __main__ - Step 128978: {'lr': 2.448254003614775e-05, 'samples': 24763776, 'steps': 128977, 'loss/train': 1.0118207931518555} 08/31/2021 12:36:30 - INFO - __main__ - Step 128979: {'lr': 2.4480249748695645e-05, 'samples': 24763968, 'steps': 128978, 'loss/train': 1.122448444366455} 08/31/2021 12:36:30 - INFO - __main__ - Step 128980: {'lr': 2.447795956285928e-05, 'samples': 24764160, 'steps': 128979, 'loss/train': 0.9962159395217896} 08/31/2021 12:36:32 - INFO - __main__ - Step 128981: {'lr': 2.447566947863969e-05, 'samples': 24764352, 'steps': 128980, 'loss/train': 0.9145288467407227} 08/31/2021 12:36:32 - INFO - __main__ - Step 128982: {'lr': 2.447337949603784e-05, 'samples': 24764544, 'steps': 128981, 'loss/train': 0.9202829003334045} 08/31/2021 12:36:33 - INFO - __main__ - Step 128983: {'lr': 2.4471089615054814e-05, 'samples': 24764736, 'steps': 128982, 'loss/train': 0.9509902000427246} 08/31/2021 12:36:33 - INFO - __main__ - Step 128984: {'lr': 2.446879983569164e-05, 'samples': 24764928, 'steps': 128983, 'loss/train': 0.5576459169387817} 08/31/2021 12:36:33 - INFO - __main__ - Step 128985: {'lr': 2.4466510157949318e-05, 'samples': 24765120, 'steps': 128984, 'loss/train': 0.5778570175170898} 08/31/2021 12:36:35 - INFO - __main__ - Step 128986: {'lr': 2.4464220581828927e-05, 'samples': 24765312, 'steps': 128985, 'loss/train': 0.5065199136734009} 08/31/2021 12:36:35 - INFO - __main__ - Step 128987: {'lr': 2.446193110733147e-05, 'samples': 24765504, 'steps': 128986, 'loss/train': 1.5251924991607666} 08/31/2021 12:36:36 - INFO - __main__ - Step 128988: {'lr': 2.4459641734458e-05, 'samples': 24765696, 'steps': 128987, 'loss/train': 1.3274770975112915} 08/31/2021 12:36:36 - INFO - __main__ - Step 128989: {'lr': 2.445735246320954e-05, 'samples': 24765888, 'steps': 128988, 'loss/train': 0.5195930004119873} 08/31/2021 12:36:36 - INFO - __main__ - Step 128990: {'lr': 2.44550632935871e-05, 'samples': 24766080, 'steps': 128989, 'loss/train': 1.3735041618347168} 08/31/2021 12:36:38 - INFO - __main__ - Step 128991: {'lr': 2.4452774225591724e-05, 'samples': 24766272, 'steps': 128990, 'loss/train': 0.9793298840522766} 08/31/2021 12:36:38 - INFO - __main__ - Step 128992: {'lr': 2.445048525922447e-05, 'samples': 24766464, 'steps': 128991, 'loss/train': 1.2022331953048706} 08/31/2021 12:36:39 - INFO - __main__ - Step 128993: {'lr': 2.444819639448631e-05, 'samples': 24766656, 'steps': 128992, 'loss/train': 1.2433849573135376} 08/31/2021 12:36:39 - INFO - __main__ - Step 128994: {'lr': 2.4445907631378384e-05, 'samples': 24766848, 'steps': 128993, 'loss/train': 1.3494176864624023} 08/31/2021 12:36:40 - INFO - __main__ - Step 128995: {'lr': 2.4443618969901605e-05, 'samples': 24767040, 'steps': 128994, 'loss/train': 0.897021472454071} 08/31/2021 12:36:40 - INFO - __main__ - Step 128996: {'lr': 2.4441330410057057e-05, 'samples': 24767232, 'steps': 128995, 'loss/train': 1.1917110681533813} 08/31/2021 12:36:41 - INFO - __main__ - Step 128997: {'lr': 2.4439041951845763e-05, 'samples': 24767424, 'steps': 128996, 'loss/train': 1.5612093210220337} 08/31/2021 12:36:42 - INFO - __main__ - Step 128998: {'lr': 2.443675359526873e-05, 'samples': 24767616, 'steps': 128997, 'loss/train': 0.9378796219825745} 08/31/2021 12:36:42 - INFO - __main__ - Step 128999: {'lr': 2.4434465340327032e-05, 'samples': 24767808, 'steps': 128998, 'loss/train': 1.2641206979751587} 08/31/2021 12:36:42 - INFO - __main__ - Step 129000: {'lr': 2.4432177187021704e-05, 'samples': 24768000, 'steps': 128999, 'loss/train': 0.4861343502998352} 08/31/2021 12:36:43 - INFO - __main__ - Step 129001: {'lr': 2.442988913535374e-05, 'samples': 24768192, 'steps': 129000, 'loss/train': 1.384161353111267} 08/31/2021 12:36:44 - INFO - __main__ - Step 129002: {'lr': 2.4427601185324167e-05, 'samples': 24768384, 'steps': 129001, 'loss/train': 1.2627958059310913} 08/31/2021 12:36:45 - INFO - __main__ - Step 129003: {'lr': 2.4425313336934067e-05, 'samples': 24768576, 'steps': 129002, 'loss/train': 0.6910108923912048} 08/31/2021 12:36:45 - INFO - __main__ - Step 129004: {'lr': 2.4423025590184417e-05, 'samples': 24768768, 'steps': 129003, 'loss/train': 1.6129807233810425} 08/31/2021 12:36:46 - INFO - __main__ - Step 129005: {'lr': 2.4420737945076265e-05, 'samples': 24768960, 'steps': 129004, 'loss/train': 1.1505937576293945} 08/31/2021 12:36:46 - INFO - __main__ - Step 129006: {'lr': 2.441845040161067e-05, 'samples': 24769152, 'steps': 129005, 'loss/train': 0.1067984476685524} 08/31/2021 12:36:47 - INFO - __main__ - Step 129007: {'lr': 2.4416162959788683e-05, 'samples': 24769344, 'steps': 129006, 'loss/train': 1.1851894855499268} 08/31/2021 12:36:48 - INFO - __main__ - Step 129008: {'lr': 2.4413875619611254e-05, 'samples': 24769536, 'steps': 129007, 'loss/train': 2.206167697906494} 08/31/2021 12:36:48 - INFO - __main__ - Step 129009: {'lr': 2.441158838107943e-05, 'samples': 24769728, 'steps': 129008, 'loss/train': 0.7596660852432251} 08/31/2021 12:36:49 - INFO - __main__ - Step 129010: {'lr': 2.4409301244194272e-05, 'samples': 24769920, 'steps': 129009, 'loss/train': 1.167356014251709} 08/31/2021 12:36:49 - INFO - __main__ - Step 129011: {'lr': 2.44070142089568e-05, 'samples': 24770112, 'steps': 129010, 'loss/train': 1.7330678701400757} 08/31/2021 12:36:49 - INFO - __main__ - Step 129012: {'lr': 2.440472727536805e-05, 'samples': 24770304, 'steps': 129011, 'loss/train': 0.8645986914634705} 08/31/2021 12:36:51 - INFO - __main__ - Step 129013: {'lr': 2.440244044342904e-05, 'samples': 24770496, 'steps': 129012, 'loss/train': 0.9972091913223267} 08/31/2021 12:36:52 - INFO - __main__ - Step 129014: {'lr': 2.4400153713140832e-05, 'samples': 24770688, 'steps': 129013, 'loss/train': 2.3614978790283203} 08/31/2021 12:36:52 - INFO - __main__ - Step 129015: {'lr': 2.439786708450442e-05, 'samples': 24770880, 'steps': 129014, 'loss/train': 0.8969359993934631} 08/31/2021 12:36:53 - INFO - __main__ - Step 129016: {'lr': 2.4395580557520836e-05, 'samples': 24771072, 'steps': 129015, 'loss/train': 0.9568330645561218} 08/31/2021 12:36:53 - INFO - __main__ - Step 129017: {'lr': 2.439329413219113e-05, 'samples': 24771264, 'steps': 129016, 'loss/train': 1.0046403408050537} 08/31/2021 12:36:55 - INFO - __main__ - Step 129018: {'lr': 2.439100780851633e-05, 'samples': 24771456, 'steps': 129017, 'loss/train': 0.2446299046278} 08/31/2021 12:36:55 - INFO - __main__ - Step 129019: {'lr': 2.4388721586497464e-05, 'samples': 24771648, 'steps': 129018, 'loss/train': 1.810529112815857} 08/31/2021 12:36:55 - INFO - __main__ - Step 129020: {'lr': 2.438643546613556e-05, 'samples': 24771840, 'steps': 129019, 'loss/train': 1.405701756477356} 08/31/2021 12:36:56 - INFO - __main__ - Step 129021: {'lr': 2.438414944743167e-05, 'samples': 24772032, 'steps': 129020, 'loss/train': 2.8162219524383545} 08/31/2021 12:36:56 - INFO - __main__ - Step 129022: {'lr': 2.4381863530386766e-05, 'samples': 24772224, 'steps': 129021, 'loss/train': 1.2025548219680786} 08/31/2021 12:36:56 - INFO - __main__ - Step 129023: {'lr': 2.4379577715001934e-05, 'samples': 24772416, 'steps': 129022, 'loss/train': 1.6837705373764038} 08/31/2021 12:36:58 - INFO - __main__ - Step 129024: {'lr': 2.437729200127817e-05, 'samples': 24772608, 'steps': 129023, 'loss/train': 1.202710747718811} 08/31/2021 12:36:58 - INFO - __main__ - Step 129025: {'lr': 2.4375006389216497e-05, 'samples': 24772800, 'steps': 129024, 'loss/train': 1.1787060499191284} 08/31/2021 12:36:59 - INFO - __main__ - Step 129026: {'lr': 2.4372720878817976e-05, 'samples': 24772992, 'steps': 129025, 'loss/train': 0.9328480958938599} 08/31/2021 12:36:59 - INFO - __main__ - Step 129027: {'lr': 2.4370435470083637e-05, 'samples': 24773184, 'steps': 129026, 'loss/train': 0.5525894165039062} 08/31/2021 12:36:59 - INFO - __main__ - Step 129028: {'lr': 2.4368150163014497e-05, 'samples': 24773376, 'steps': 129027, 'loss/train': 1.0009022951126099} 08/31/2021 12:37:01 - INFO - __main__ - Step 129029: {'lr': 2.4365864957611562e-05, 'samples': 24773568, 'steps': 129028, 'loss/train': 1.4392277002334595} 08/31/2021 12:37:01 - INFO - __main__ - Step 129030: {'lr': 2.436357985387591e-05, 'samples': 24773760, 'steps': 129029, 'loss/train': 1.4680638313293457} 08/31/2021 12:37:02 - INFO - __main__ - Step 129031: {'lr': 2.4361294851808546e-05, 'samples': 24773952, 'steps': 129030, 'loss/train': 0.46282267570495605} 08/31/2021 12:37:02 - INFO - __main__ - Step 129032: {'lr': 2.4359009951410493e-05, 'samples': 24774144, 'steps': 129031, 'loss/train': 1.12897789478302} 08/31/2021 12:37:02 - INFO - __main__ - Step 129033: {'lr': 2.435672515268278e-05, 'samples': 24774336, 'steps': 129032, 'loss/train': 0.7857578992843628} 08/31/2021 12:37:04 - INFO - __main__ - Step 129034: {'lr': 2.4354440455626515e-05, 'samples': 24774528, 'steps': 129033, 'loss/train': 0.925315260887146} 08/31/2021 12:37:04 - INFO - __main__ - Step 129035: {'lr': 2.4352155860242586e-05, 'samples': 24774720, 'steps': 129034, 'loss/train': 0.9512762427330017} 08/31/2021 12:37:05 - INFO - __main__ - Step 129036: {'lr': 2.4349871366532105e-05, 'samples': 24774912, 'steps': 129035, 'loss/train': 1.9910123348236084} 08/31/2021 12:37:05 - INFO - __main__ - Step 129037: {'lr': 2.43475869744961e-05, 'samples': 24775104, 'steps': 129036, 'loss/train': 1.0183285474777222} 08/31/2021 12:37:06 - INFO - __main__ - Step 129038: {'lr': 2.4345302684135594e-05, 'samples': 24775296, 'steps': 129037, 'loss/train': 0.9673921465873718} 08/31/2021 12:37:07 - INFO - __main__ - Step 129039: {'lr': 2.434301849545159e-05, 'samples': 24775488, 'steps': 129038, 'loss/train': 2.0265438556671143} 08/31/2021 12:37:08 - INFO - __main__ - Step 129040: {'lr': 2.434073440844514e-05, 'samples': 24775680, 'steps': 129039, 'loss/train': 1.2479327917099} 08/31/2021 12:37:08 - INFO - __main__ - Step 129041: {'lr': 2.43384504231173e-05, 'samples': 24775872, 'steps': 129040, 'loss/train': 0.6615082621574402} 08/31/2021 12:37:08 - INFO - __main__ - Step 129042: {'lr': 2.4336166539469046e-05, 'samples': 24776064, 'steps': 129041, 'loss/train': 0.9227544069290161} 08/31/2021 12:37:09 - INFO - __main__ - Step 129043: {'lr': 2.433388275750145e-05, 'samples': 24776256, 'steps': 129042, 'loss/train': 1.08894681930542} 08/31/2021 12:37:09 - INFO - __main__ - Step 129044: {'lr': 2.4331599077215493e-05, 'samples': 24776448, 'steps': 129043, 'loss/train': 5.725462913513184} 08/31/2021 12:37:11 - INFO - __main__ - Step 129045: {'lr': 2.4329315498612282e-05, 'samples': 24776640, 'steps': 129044, 'loss/train': 0.7636604309082031} 08/31/2021 12:37:11 - INFO - __main__ - Step 129046: {'lr': 2.4327032021692758e-05, 'samples': 24776832, 'steps': 129045, 'loss/train': 1.3824015855789185} 08/31/2021 12:37:11 - INFO - __main__ - Step 129047: {'lr': 2.4324748646458008e-05, 'samples': 24777024, 'steps': 129046, 'loss/train': 1.370682954788208} 08/31/2021 12:37:12 - INFO - __main__ - Step 129048: {'lr': 2.432246537290911e-05, 'samples': 24777216, 'steps': 129047, 'loss/train': 1.0003443956375122} 08/31/2021 12:37:12 - INFO - __main__ - Step 129049: {'lr': 2.432018220104695e-05, 'samples': 24777408, 'steps': 129048, 'loss/train': 1.6551384925842285} 08/31/2021 12:37:14 - INFO - __main__ - Step 129050: {'lr': 2.4317899130872652e-05, 'samples': 24777600, 'steps': 129049, 'loss/train': 0.6728475093841553} 08/31/2021 12:37:14 - INFO - __main__ - Step 129051: {'lr': 2.43156161623872e-05, 'samples': 24777792, 'steps': 129050, 'loss/train': 1.2570077180862427} 08/31/2021 12:37:15 - INFO - __main__ - Step 129052: {'lr': 2.4313333295591683e-05, 'samples': 24777984, 'steps': 129051, 'loss/train': 0.839067816734314} 08/31/2021 12:37:15 - INFO - __main__ - Step 129053: {'lr': 2.4311050530487074e-05, 'samples': 24778176, 'steps': 129052, 'loss/train': 1.0967893600463867} 08/31/2021 12:37:15 - INFO - __main__ - Step 129054: {'lr': 2.430876786707442e-05, 'samples': 24778368, 'steps': 129053, 'loss/train': 0.8881956934928894} 08/31/2021 12:37:16 - INFO - __main__ - Step 129055: {'lr': 2.4306485305354758e-05, 'samples': 24778560, 'steps': 129054, 'loss/train': 1.2854745388031006} 08/31/2021 12:37:17 - INFO - __main__ - Step 129056: {'lr': 2.4304202845329136e-05, 'samples': 24778752, 'steps': 129055, 'loss/train': 0.037004128098487854} 08/31/2021 12:37:18 - INFO - __main__ - Step 129057: {'lr': 2.430192048699853e-05, 'samples': 24778944, 'steps': 129056, 'loss/train': 1.7525399923324585} 08/31/2021 12:37:18 - INFO - __main__ - Step 129058: {'lr': 2.429963823036399e-05, 'samples': 24779136, 'steps': 129057, 'loss/train': 0.03818429261445999} 08/31/2021 12:37:19 - INFO - __main__ - Step 129059: {'lr': 2.4297356075426575e-05, 'samples': 24779328, 'steps': 129058, 'loss/train': 1.1266627311706543} 08/31/2021 12:37:19 - INFO - __main__ - Step 129060: {'lr': 2.429507402218728e-05, 'samples': 24779520, 'steps': 129059, 'loss/train': 1.0297139883041382} 08/31/2021 12:37:20 - INFO - __main__ - Step 129061: {'lr': 2.4292792070647163e-05, 'samples': 24779712, 'steps': 129060, 'loss/train': 1.532414436340332} 08/31/2021 12:37:21 - INFO - __main__ - Step 129062: {'lr': 2.429051022080722e-05, 'samples': 24779904, 'steps': 129061, 'loss/train': 1.5995277166366577} 08/31/2021 12:37:21 - INFO - __main__ - Step 129063: {'lr': 2.4288228472668483e-05, 'samples': 24780096, 'steps': 129062, 'loss/train': 1.4063512086868286} 08/31/2021 12:37:22 - INFO - __main__ - Step 129064: {'lr': 2.4285946826231976e-05, 'samples': 24780288, 'steps': 129063, 'loss/train': 1.0141379833221436} 08/31/2021 12:37:22 - INFO - __main__ - Step 129065: {'lr': 2.4283665281498725e-05, 'samples': 24780480, 'steps': 129064, 'loss/train': 1.2651770114898682} 08/31/2021 12:37:24 - INFO - __main__ - Step 129066: {'lr': 2.4281383838469784e-05, 'samples': 24780672, 'steps': 129065, 'loss/train': 0.6079915165901184} 08/31/2021 12:37:25 - INFO - __main__ - Step 129067: {'lr': 2.4279102497146183e-05, 'samples': 24780864, 'steps': 129066, 'loss/train': 1.284511685371399} 08/31/2021 12:37:25 - INFO - __main__ - Step 129068: {'lr': 2.427682125752892e-05, 'samples': 24781056, 'steps': 129067, 'loss/train': 0.9762563705444336} 08/31/2021 12:37:25 - INFO - __main__ - Step 129069: {'lr': 2.427454011961905e-05, 'samples': 24781248, 'steps': 129068, 'loss/train': 1.0066590309143066} 08/31/2021 12:37:26 - INFO - __main__ - Step 129070: {'lr': 2.427225908341757e-05, 'samples': 24781440, 'steps': 129069, 'loss/train': 1.3347786664962769} 08/31/2021 12:37:27 - INFO - __main__ - Step 129071: {'lr': 2.4269978148925566e-05, 'samples': 24781632, 'steps': 129070, 'loss/train': 0.28098922967910767} 08/31/2021 12:37:28 - INFO - __main__ - Step 129072: {'lr': 2.426769731614398e-05, 'samples': 24781824, 'steps': 129071, 'loss/train': 1.577874779701233} 08/31/2021 12:37:28 - INFO - __main__ - Step 129073: {'lr': 2.4265416585073917e-05, 'samples': 24782016, 'steps': 129072, 'loss/train': 1.211063027381897} 08/31/2021 12:37:28 - INFO - __main__ - Step 129074: {'lr': 2.426313595571636e-05, 'samples': 24782208, 'steps': 129073, 'loss/train': 0.6990932822227478} 08/31/2021 12:37:29 - INFO - __main__ - Step 129075: {'lr': 2.426085542807241e-05, 'samples': 24782400, 'steps': 129074, 'loss/train': 1.6517866849899292} 08/31/2021 12:37:29 - INFO - __main__ - Step 129076: {'lr': 2.4258575002142956e-05, 'samples': 24782592, 'steps': 129075, 'loss/train': 0.1990957409143448} 08/31/2021 12:37:31 - INFO - __main__ - Step 129077: {'lr': 2.4256294677929142e-05, 'samples': 24782784, 'steps': 129076, 'loss/train': 0.5457962155342102} 08/31/2021 12:37:31 - INFO - __main__ - Step 129078: {'lr': 2.4254014455431933e-05, 'samples': 24782976, 'steps': 129077, 'loss/train': 0.5925906896591187} 08/31/2021 12:37:32 - INFO - __main__ - Step 129079: {'lr': 2.4251734334652414e-05, 'samples': 24783168, 'steps': 129078, 'loss/train': 1.1123342514038086} 08/31/2021 12:37:32 - INFO - __main__ - Step 129080: {'lr': 2.4249454315591557e-05, 'samples': 24783360, 'steps': 129079, 'loss/train': 0.7489051222801208} 08/31/2021 12:37:32 - INFO - __main__ - Step 129081: {'lr': 2.4247174398250415e-05, 'samples': 24783552, 'steps': 129080, 'loss/train': 1.009765625} 08/31/2021 12:37:34 - INFO - __main__ - Step 129082: {'lr': 2.424489458262999e-05, 'samples': 24783744, 'steps': 129081, 'loss/train': 0.8466401696205139} 08/31/2021 12:37:34 - INFO - __main__ - Step 129083: {'lr': 2.4242614868731362e-05, 'samples': 24783936, 'steps': 129082, 'loss/train': 2.328583240509033} 08/31/2021 12:37:35 - INFO - __main__ - Step 129084: {'lr': 2.424033525655553e-05, 'samples': 24784128, 'steps': 129083, 'loss/train': 0.7291422486305237} 08/31/2021 12:37:35 - INFO - __main__ - Step 129085: {'lr': 2.4238055746103494e-05, 'samples': 24784320, 'steps': 129084, 'loss/train': 1.437821865081787} 08/31/2021 12:37:35 - INFO - __main__ - Step 129086: {'lr': 2.4235776337376337e-05, 'samples': 24784512, 'steps': 129085, 'loss/train': 1.3688862323760986} 08/31/2021 12:37:37 - INFO - __main__ - Step 129087: {'lr': 2.4233497030375028e-05, 'samples': 24784704, 'steps': 129086, 'loss/train': 1.1951299905776978} 08/31/2021 12:37:38 - INFO - __main__ - Step 129088: {'lr': 2.423121782510068e-05, 'samples': 24784896, 'steps': 129087, 'loss/train': 1.6537306308746338} 08/31/2021 12:37:38 - INFO - __main__ - Step 129089: {'lr': 2.422893872155421e-05, 'samples': 24785088, 'steps': 129088, 'loss/train': 0.6001047492027283} 08/31/2021 12:37:38 - INFO - __main__ - Step 129090: {'lr': 2.42266597197367e-05, 'samples': 24785280, 'steps': 129089, 'loss/train': 0.8297795057296753} 08/31/2021 12:37:39 - INFO - __main__ - Step 129091: {'lr': 2.422438081964917e-05, 'samples': 24785472, 'steps': 129090, 'loss/train': 0.9324296116828918} 08/31/2021 12:37:40 - INFO - __main__ - Step 129092: {'lr': 2.422210202129266e-05, 'samples': 24785664, 'steps': 129091, 'loss/train': 1.8562504053115845} 08/31/2021 12:37:41 - INFO - __main__ - Step 129093: {'lr': 2.4219823324668184e-05, 'samples': 24785856, 'steps': 129092, 'loss/train': 0.7068737149238586} 08/31/2021 12:37:41 - INFO - __main__ - Step 129094: {'lr': 2.4217544729776774e-05, 'samples': 24786048, 'steps': 129093, 'loss/train': 1.8744794130325317} 08/31/2021 12:37:41 - INFO - __main__ - Step 129095: {'lr': 2.4215266236619432e-05, 'samples': 24786240, 'steps': 129094, 'loss/train': 1.5270811319351196} 08/31/2021 12:37:42 - INFO - __main__ - Step 129096: {'lr': 2.421298784519724e-05, 'samples': 24786432, 'steps': 129095, 'loss/train': 1.2685545682907104} 08/31/2021 12:37:43 - INFO - __main__ - Step 129097: {'lr': 2.4210709555511163e-05, 'samples': 24786624, 'steps': 129096, 'loss/train': 1.5310213565826416} 08/31/2021 12:37:44 - INFO - __main__ - Step 129098: {'lr': 2.420843136756229e-05, 'samples': 24786816, 'steps': 129097, 'loss/train': 0.063420869410038} 08/31/2021 12:37:44 - INFO - __main__ - Step 129099: {'lr': 2.420615328135159e-05, 'samples': 24787008, 'steps': 129098, 'loss/train': 1.9723175764083862} 08/31/2021 12:37:44 - INFO - __main__ - Step 129100: {'lr': 2.4203875296880117e-05, 'samples': 24787200, 'steps': 129099, 'loss/train': 0.7161493301391602} 08/31/2021 12:37:45 - INFO - __main__ - Step 129101: {'lr': 2.4201597414148873e-05, 'samples': 24787392, 'steps': 129100, 'loss/train': 0.7691848874092102} 08/31/2021 12:37:46 - INFO - __main__ - Step 129102: {'lr': 2.4199319633158967e-05, 'samples': 24787584, 'steps': 129101, 'loss/train': 0.861649215221405} 08/31/2021 12:37:47 - INFO - __main__ - Step 129103: {'lr': 2.4197041953911342e-05, 'samples': 24787776, 'steps': 129102, 'loss/train': 1.0734080076217651} 08/31/2021 12:37:47 - INFO - __main__ - Step 129104: {'lr': 2.4194764376407024e-05, 'samples': 24787968, 'steps': 129103, 'loss/train': 0.9909712672233582} 08/31/2021 12:37:48 - INFO - __main__ - Step 129105: {'lr': 2.4192486900647044e-05, 'samples': 24788160, 'steps': 129104, 'loss/train': 2.617457866668701} 08/31/2021 12:37:48 - INFO - __main__ - Step 129106: {'lr': 2.4190209526632478e-05, 'samples': 24788352, 'steps': 129105, 'loss/train': 1.3454517126083374} 08/31/2021 12:37:48 - INFO - __main__ - Step 129107: {'lr': 2.4187932254364303e-05, 'samples': 24788544, 'steps': 129106, 'loss/train': 0.6967808604240417} 08/31/2021 12:37:50 - INFO - __main__ - Step 129108: {'lr': 2.4185655083843544e-05, 'samples': 24788736, 'steps': 129107, 'loss/train': 1.3919191360473633} 08/31/2021 12:37:50 - INFO - __main__ - Step 129109: {'lr': 2.4183378015071257e-05, 'samples': 24788928, 'steps': 129108, 'loss/train': 1.1073449850082397} 08/31/2021 12:37:51 - INFO - __main__ - Step 129110: {'lr': 2.4181101048048466e-05, 'samples': 24789120, 'steps': 129109, 'loss/train': 0.7206791043281555} 08/31/2021 12:37:51 - INFO - __main__ - Step 129111: {'lr': 2.417882418277617e-05, 'samples': 24789312, 'steps': 129110, 'loss/train': 0.5764203667640686} 08/31/2021 12:37:51 - INFO - __main__ - Step 129112: {'lr': 2.417654741925543e-05, 'samples': 24789504, 'steps': 129111, 'loss/train': 0.8162277936935425} 08/31/2021 12:37:53 - INFO - __main__ - Step 129113: {'lr': 2.4174270757487238e-05, 'samples': 24789696, 'steps': 129112, 'loss/train': 0.9493865966796875} 08/31/2021 12:37:53 - INFO - __main__ - Step 129114: {'lr': 2.4171994197472652e-05, 'samples': 24789888, 'steps': 129113, 'loss/train': 0.034919656813144684} 08/31/2021 12:37:54 - INFO - __main__ - Step 129115: {'lr': 2.41697177392127e-05, 'samples': 24790080, 'steps': 129114, 'loss/train': 0.8166111707687378} 08/31/2021 12:37:54 - INFO - __main__ - Step 129116: {'lr': 2.416744138270838e-05, 'samples': 24790272, 'steps': 129115, 'loss/train': 1.1736700534820557} 08/31/2021 12:37:54 - INFO - __main__ - Step 129117: {'lr': 2.4165165127960686e-05, 'samples': 24790464, 'steps': 129116, 'loss/train': 0.7492461204528809} 08/31/2021 12:37:57 - INFO - __main__ - Step 129118: {'lr': 2.416288897497071e-05, 'samples': 24790656, 'steps': 129117, 'loss/train': 1.3019973039627075} 08/31/2021 12:37:57 - INFO - __main__ - Step 129119: {'lr': 2.4160612923739444e-05, 'samples': 24790848, 'steps': 129118, 'loss/train': 1.4873378276824951} 08/31/2021 12:37:58 - INFO - __main__ - Step 129120: {'lr': 2.4158336974267918e-05, 'samples': 24791040, 'steps': 129119, 'loss/train': 1.5378646850585938} 08/31/2021 12:37:58 - INFO - __main__ - Step 129121: {'lr': 2.4156061126557162e-05, 'samples': 24791232, 'steps': 129120, 'loss/train': 1.4754629135131836} 08/31/2021 12:37:58 - INFO - __main__ - Step 129122: {'lr': 2.4153785380608195e-05, 'samples': 24791424, 'steps': 129121, 'loss/train': 1.3275312185287476} 08/31/2021 12:37:59 - INFO - __main__ - Step 129123: {'lr': 2.415150973642205e-05, 'samples': 24791616, 'steps': 129122, 'loss/train': 1.0774867534637451} 08/31/2021 12:38:01 - INFO - __main__ - Step 129124: {'lr': 2.4149234193999753e-05, 'samples': 24791808, 'steps': 129123, 'loss/train': 0.06584704667329788} 08/31/2021 12:38:01 - INFO - __main__ - Step 129125: {'lr': 2.414695875334233e-05, 'samples': 24792000, 'steps': 129124, 'loss/train': 0.9585034251213074} 08/31/2021 12:38:02 - INFO - __main__ - Step 129126: {'lr': 2.414468341445081e-05, 'samples': 24792192, 'steps': 129125, 'loss/train': 0.18899337947368622} 08/31/2021 12:38:02 - INFO - __main__ - Step 129127: {'lr': 2.4142408177326185e-05, 'samples': 24792384, 'steps': 129126, 'loss/train': 0.8036778569221497} 08/31/2021 12:38:02 - INFO - __main__ - Step 129128: {'lr': 2.4140133041969574e-05, 'samples': 24792576, 'steps': 129127, 'loss/train': 1.2196052074432373} 08/31/2021 12:38:03 - INFO - __main__ - Step 129129: {'lr': 2.4137858008381862e-05, 'samples': 24792768, 'steps': 129128, 'loss/train': 1.5306912660598755} 08/31/2021 12:38:04 - INFO - __main__ - Step 129130: {'lr': 2.4135583076564162e-05, 'samples': 24792960, 'steps': 129129, 'loss/train': 1.2162103652954102} 08/31/2021 12:38:05 - INFO - __main__ - Step 129131: {'lr': 2.4133308246517494e-05, 'samples': 24793152, 'steps': 129130, 'loss/train': 0.6102274656295776} 08/31/2021 12:38:05 - INFO - __main__ - Step 129132: {'lr': 2.4131033518242862e-05, 'samples': 24793344, 'steps': 129131, 'loss/train': 1.0726850032806396} 08/31/2021 12:38:06 - INFO - __main__ - Step 129133: {'lr': 2.412875889174129e-05, 'samples': 24793536, 'steps': 129132, 'loss/train': 1.0021294355392456} 08/31/2021 12:38:06 - INFO - __main__ - Step 129134: {'lr': 2.412648436701384e-05, 'samples': 24793728, 'steps': 129133, 'loss/train': 0.9834833741188049} 08/31/2021 12:38:08 - INFO - __main__ - Step 129135: {'lr': 2.4124209944061476e-05, 'samples': 24793920, 'steps': 129134, 'loss/train': 1.7925738096237183} 08/31/2021 12:38:08 - INFO - __main__ - Step 129136: {'lr': 2.4121935622885284e-05, 'samples': 24794112, 'steps': 129135, 'loss/train': 1.1226961612701416} 08/31/2021 12:38:08 - INFO - __main__ - Step 129137: {'lr': 2.411966140348626e-05, 'samples': 24794304, 'steps': 129136, 'loss/train': 0.708220899105072} 08/31/2021 12:38:09 - INFO - __main__ - Step 129138: {'lr': 2.4117387285865432e-05, 'samples': 24794496, 'steps': 129137, 'loss/train': 1.2394497394561768} 08/31/2021 12:38:09 - INFO - __main__ - Step 129139: {'lr': 2.41151132700238e-05, 'samples': 24794688, 'steps': 129138, 'loss/train': 0.015577039681375027} 08/31/2021 12:38:10 - INFO - __main__ - Step 129140: {'lr': 2.4112839355962453e-05, 'samples': 24794880, 'steps': 129139, 'loss/train': 0.0157927256077528} 08/31/2021 12:38:11 - INFO - __main__ - Step 129141: {'lr': 2.411056554368235e-05, 'samples': 24795072, 'steps': 129140, 'loss/train': 1.0712066888809204} 08/31/2021 12:38:12 - INFO - __main__ - Step 129142: {'lr': 2.410829183318458e-05, 'samples': 24795264, 'steps': 129141, 'loss/train': 1.179998517036438} 08/31/2021 12:38:12 - INFO - __main__ - Step 129143: {'lr': 2.410601822447009e-05, 'samples': 24795456, 'steps': 129142, 'loss/train': 1.314565658569336} 08/31/2021 12:38:12 - INFO - __main__ - Step 129144: {'lr': 2.4103744717539927e-05, 'samples': 24795648, 'steps': 129143, 'loss/train': 1.0533885955810547} 08/31/2021 12:38:13 - INFO - __main__ - Step 129145: {'lr': 2.410147131239515e-05, 'samples': 24795840, 'steps': 129144, 'loss/train': 1.2404452562332153} 08/31/2021 12:38:13 - INFO - __main__ - Step 129146: {'lr': 2.409919800903676e-05, 'samples': 24796032, 'steps': 129145, 'loss/train': 1.0494143962860107} 08/31/2021 12:38:15 - INFO - __main__ - Step 129147: {'lr': 2.4096924807465807e-05, 'samples': 24796224, 'steps': 129146, 'loss/train': 0.05584919825196266} 08/31/2021 12:38:15 - INFO - __main__ - Step 129148: {'lr': 2.409465170768327e-05, 'samples': 24796416, 'steps': 129147, 'loss/train': 0.9460616111755371} 08/31/2021 12:38:15 - INFO - __main__ - Step 129149: {'lr': 2.4092378709690193e-05, 'samples': 24796608, 'steps': 129148, 'loss/train': 1.2458791732788086} 08/31/2021 12:38:16 - INFO - __main__ - Step 129150: {'lr': 2.4090105813487612e-05, 'samples': 24796800, 'steps': 129149, 'loss/train': 1.0900019407272339} 08/31/2021 12:38:16 - INFO - __main__ - Step 129151: {'lr': 2.4087833019076548e-05, 'samples': 24796992, 'steps': 129150, 'loss/train': 1.4481459856033325} 08/31/2021 12:38:18 - INFO - __main__ - Step 129152: {'lr': 2.4085560326458007e-05, 'samples': 24797184, 'steps': 129151, 'loss/train': 1.367394208908081} 08/31/2021 12:38:18 - INFO - __main__ - Step 129153: {'lr': 2.4083287735633036e-05, 'samples': 24797376, 'steps': 129152, 'loss/train': 1.0076578855514526} 08/31/2021 12:38:19 - INFO - __main__ - Step 129154: {'lr': 2.4081015246602638e-05, 'samples': 24797568, 'steps': 129153, 'loss/train': 1.3607125282287598} 08/31/2021 12:38:19 - INFO - __main__ - Step 129155: {'lr': 2.4078742859367924e-05, 'samples': 24797760, 'steps': 129154, 'loss/train': 0.9804057478904724} 08/31/2021 12:38:19 - INFO - __main__ - Step 129156: {'lr': 2.4076470573929756e-05, 'samples': 24797952, 'steps': 129155, 'loss/train': 0.9084828495979309} 08/31/2021 12:38:21 - INFO - __main__ - Step 129157: {'lr': 2.4074198390289264e-05, 'samples': 24798144, 'steps': 129156, 'loss/train': 1.7142337560653687} 08/31/2021 12:38:21 - INFO - __main__ - Step 129158: {'lr': 2.4071926308447454e-05, 'samples': 24798336, 'steps': 129157, 'loss/train': 1.687713384628296} 08/31/2021 12:38:22 - INFO - __main__ - Step 129159: {'lr': 2.4069654328405355e-05, 'samples': 24798528, 'steps': 129158, 'loss/train': 0.1945844143629074} 08/31/2021 12:38:22 - INFO - __main__ - Step 129160: {'lr': 2.406738245016396e-05, 'samples': 24798720, 'steps': 129159, 'loss/train': 1.1345113515853882} 08/31/2021 12:38:22 - INFO - __main__ - Step 129161: {'lr': 2.4065110673724357e-05, 'samples': 24798912, 'steps': 129160, 'loss/train': 1.2720892429351807} 08/31/2021 12:38:23 - INFO - __main__ - Step 129162: {'lr': 2.4062838999087484e-05, 'samples': 24799104, 'steps': 129161, 'loss/train': 1.378760814666748} 08/31/2021 12:38:24 - INFO - __main__ - Step 129163: {'lr': 2.4060567426254427e-05, 'samples': 24799296, 'steps': 129162, 'loss/train': 1.0507419109344482} 08/31/2021 12:38:25 - INFO - __main__ - Step 129164: {'lr': 2.4058295955226183e-05, 'samples': 24799488, 'steps': 129163, 'loss/train': 1.2267470359802246} 08/31/2021 12:38:25 - INFO - __main__ - Step 129165: {'lr': 2.405602458600381e-05, 'samples': 24799680, 'steps': 129164, 'loss/train': 0.5721819996833801} 08/31/2021 12:38:25 - INFO - __main__ - Step 129166: {'lr': 2.405375331858828e-05, 'samples': 24799872, 'steps': 129165, 'loss/train': 1.2053065299987793} 08/31/2021 12:38:26 - INFO - __main__ - Step 129167: {'lr': 2.4051482152980668e-05, 'samples': 24800064, 'steps': 129166, 'loss/train': 0.11118648201227188} 08/31/2021 12:38:28 - INFO - __main__ - Step 129168: {'lr': 2.4049211089181954e-05, 'samples': 24800256, 'steps': 129167, 'loss/train': 1.4141144752502441} 08/31/2021 12:38:28 - INFO - __main__ - Step 129169: {'lr': 2.4046940127193216e-05, 'samples': 24800448, 'steps': 129168, 'loss/train': 1.4006472826004028} 08/31/2021 12:38:29 - INFO - __main__ - Step 129170: {'lr': 2.4044669267015402e-05, 'samples': 24800640, 'steps': 129169, 'loss/train': 0.5890710949897766} 08/31/2021 12:38:29 - INFO - __main__ - Step 129171: {'lr': 2.4042398508649587e-05, 'samples': 24800832, 'steps': 129170, 'loss/train': 1.2001291513442993} 08/31/2021 12:38:29 - INFO - __main__ - Step 129172: {'lr': 2.4040127852096775e-05, 'samples': 24801024, 'steps': 129171, 'loss/train': 1.1683478355407715} 08/31/2021 12:38:31 - INFO - __main__ - Step 129173: {'lr': 2.4037857297357968e-05, 'samples': 24801216, 'steps': 129172, 'loss/train': 0.9776538610458374} 08/31/2021 12:38:32 - INFO - __main__ - Step 129174: {'lr': 2.4035586844434242e-05, 'samples': 24801408, 'steps': 129173, 'loss/train': 0.1950436532497406} 08/31/2021 12:38:32 - INFO - __main__ - Step 129175: {'lr': 2.40333164933266e-05, 'samples': 24801600, 'steps': 129174, 'loss/train': 0.5192476511001587} 08/31/2021 12:38:33 - INFO - __main__ - Step 129176: {'lr': 2.4031046244036043e-05, 'samples': 24801792, 'steps': 129175, 'loss/train': 0.11026698350906372} 08/31/2021 12:38:33 - INFO - __main__ - Step 129177: {'lr': 2.402877609656362e-05, 'samples': 24801984, 'steps': 129176, 'loss/train': 1.3135696649551392} 08/31/2021 12:38:33 - INFO - __main__ - Step 129178: {'lr': 2.4026506050910333e-05, 'samples': 24802176, 'steps': 129177, 'loss/train': 0.7690919637680054} 08/31/2021 12:38:35 - INFO - __main__ - Step 129179: {'lr': 2.4024236107077214e-05, 'samples': 24802368, 'steps': 129178, 'loss/train': 1.2131294012069702} 08/31/2021 12:38:35 - INFO - __main__ - Step 129180: {'lr': 2.402196626506528e-05, 'samples': 24802560, 'steps': 129179, 'loss/train': 1.225521206855774} 08/31/2021 12:38:36 - INFO - __main__ - Step 129181: {'lr': 2.4019696524875596e-05, 'samples': 24802752, 'steps': 129180, 'loss/train': 0.7415277361869812} 08/31/2021 12:38:36 - INFO - __main__ - Step 129182: {'lr': 2.4017426886509154e-05, 'samples': 24802944, 'steps': 129181, 'loss/train': 1.1143749952316284} 08/31/2021 12:38:36 - INFO - __main__ - Step 129183: {'lr': 2.4015157349966955e-05, 'samples': 24803136, 'steps': 129182, 'loss/train': 0.2106696367263794} 08/31/2021 12:38:38 - INFO - __main__ - Step 129184: {'lr': 2.4012887915250026e-05, 'samples': 24803328, 'steps': 129183, 'loss/train': 1.5337108373641968} 08/31/2021 12:38:38 - INFO - __main__ - Step 129185: {'lr': 2.4010618582359423e-05, 'samples': 24803520, 'steps': 129184, 'loss/train': 1.1398184299468994} 08/31/2021 12:38:39 - INFO - __main__ - Step 129186: {'lr': 2.4008349351296116e-05, 'samples': 24803712, 'steps': 129185, 'loss/train': 0.932699978351593} 08/31/2021 12:38:39 - INFO - __main__ - Step 129187: {'lr': 2.400608022206119e-05, 'samples': 24803904, 'steps': 129186, 'loss/train': 1.0981981754302979} 08/31/2021 12:38:39 - INFO - __main__ - Step 129188: {'lr': 2.400381119465561e-05, 'samples': 24804096, 'steps': 129187, 'loss/train': 1.0004600286483765} 08/31/2021 12:38:41 - INFO - __main__ - Step 129189: {'lr': 2.4001542269080438e-05, 'samples': 24804288, 'steps': 129188, 'loss/train': 0.9370355606079102} 08/31/2021 12:38:41 - INFO - __main__ - Step 129190: {'lr': 2.399927344533667e-05, 'samples': 24804480, 'steps': 129189, 'loss/train': 1.1678858995437622} 08/31/2021 12:38:42 - INFO - __main__ - Step 129191: {'lr': 2.3997004723425363e-05, 'samples': 24804672, 'steps': 129190, 'loss/train': 1.0955475568771362} 08/31/2021 12:38:42 - INFO - __main__ - Step 129192: {'lr': 2.3994736103347514e-05, 'samples': 24804864, 'steps': 129191, 'loss/train': 1.4386065006256104} 08/31/2021 12:38:42 - INFO - __main__ - Step 129193: {'lr': 2.399246758510415e-05, 'samples': 24805056, 'steps': 129192, 'loss/train': 0.7059824466705322} 08/31/2021 12:38:44 - INFO - __main__ - Step 129194: {'lr': 2.399019916869627e-05, 'samples': 24805248, 'steps': 129193, 'loss/train': 1.200064778327942} 08/31/2021 12:38:45 - INFO - __main__ - Step 129195: {'lr': 2.3987930854124985e-05, 'samples': 24805440, 'steps': 129194, 'loss/train': 0.6199830770492554} 08/31/2021 12:38:45 - INFO - __main__ - Step 129196: {'lr': 2.398566264139121e-05, 'samples': 24805632, 'steps': 129195, 'loss/train': 0.4608039855957031} 08/31/2021 12:38:45 - INFO - __main__ - Step 129197: {'lr': 2.3983394530496e-05, 'samples': 24805824, 'steps': 129196, 'loss/train': 0.29489219188690186} 08/31/2021 12:38:46 - INFO - __main__ - Step 129198: {'lr': 2.398112652144038e-05, 'samples': 24806016, 'steps': 129197, 'loss/train': 0.8500293493270874} 08/31/2021 12:38:47 - INFO - __main__ - Step 129199: {'lr': 2.3978858614225386e-05, 'samples': 24806208, 'steps': 129198, 'loss/train': 0.3531606197357178} 08/31/2021 12:38:48 - INFO - __main__ - Step 129200: {'lr': 2.3976590808852032e-05, 'samples': 24806400, 'steps': 129199, 'loss/train': 1.3314217329025269} 08/31/2021 12:38:48 - INFO - __main__ - Step 129201: {'lr': 2.397432310532133e-05, 'samples': 24806592, 'steps': 129200, 'loss/train': 1.640243649482727} 08/31/2021 12:38:48 - INFO - __main__ - Step 129202: {'lr': 2.3972055503634322e-05, 'samples': 24806784, 'steps': 129201, 'loss/train': 1.3046352863311768} 08/31/2021 12:38:49 - INFO - __main__ - Step 129203: {'lr': 2.3969788003792013e-05, 'samples': 24806976, 'steps': 129202, 'loss/train': 0.7029430866241455} 08/31/2021 12:38:49 - INFO - __main__ - Step 129204: {'lr': 2.3967520605795408e-05, 'samples': 24807168, 'steps': 129203, 'loss/train': 1.1280854940414429} 08/31/2021 12:38:51 - INFO - __main__ - Step 129205: {'lr': 2.396525330964558e-05, 'samples': 24807360, 'steps': 129204, 'loss/train': 0.714605987071991} 08/31/2021 12:38:52 - INFO - __main__ - Step 129206: {'lr': 2.396298611534356e-05, 'samples': 24807552, 'steps': 129205, 'loss/train': 0.8764872550964355} 08/31/2021 12:38:52 - INFO - __main__ - Step 129207: {'lr': 2.3960719022890264e-05, 'samples': 24807744, 'steps': 129206, 'loss/train': 0.9117839932441711} 08/31/2021 12:38:52 - INFO - __main__ - Step 129208: {'lr': 2.3958452032286805e-05, 'samples': 24807936, 'steps': 129207, 'loss/train': 0.7233015894889832} 08/31/2021 12:38:53 - INFO - __main__ - Step 129209: {'lr': 2.3956185143534177e-05, 'samples': 24808128, 'steps': 129208, 'loss/train': 2.177595376968384} 08/31/2021 12:38:53 - INFO - __main__ - Step 129210: {'lr': 2.395391835663338e-05, 'samples': 24808320, 'steps': 129209, 'loss/train': 2.2047247886657715} 08/31/2021 12:38:55 - INFO - __main__ - Step 129211: {'lr': 2.3951651671585474e-05, 'samples': 24808512, 'steps': 129210, 'loss/train': 0.6936132311820984} 08/31/2021 12:38:55 - INFO - __main__ - Step 129212: {'lr': 2.394938508839148e-05, 'samples': 24808704, 'steps': 129211, 'loss/train': 0.6021459102630615} 08/31/2021 12:38:55 - INFO - __main__ - Step 129213: {'lr': 2.39471186070524e-05, 'samples': 24808896, 'steps': 129212, 'loss/train': 0.475209504365921} 08/31/2021 12:38:56 - INFO - __main__ - Step 129214: {'lr': 2.3944852227569232e-05, 'samples': 24809088, 'steps': 129213, 'loss/train': 0.26971906423568726} 08/31/2021 12:38:56 - INFO - __main__ - Step 129215: {'lr': 2.394258594994306e-05, 'samples': 24809280, 'steps': 129214, 'loss/train': 0.7639831304550171} 08/31/2021 12:38:58 - INFO - __main__ - Step 129216: {'lr': 2.394031977417485e-05, 'samples': 24809472, 'steps': 129215, 'loss/train': 0.8790462613105774} 08/31/2021 12:38:58 - INFO - __main__ - Step 129217: {'lr': 2.3938053700265694e-05, 'samples': 24809664, 'steps': 129216, 'loss/train': 1.353265643119812} 08/31/2021 12:38:58 - INFO - __main__ - Step 129218: {'lr': 2.393578772821653e-05, 'samples': 24809856, 'steps': 129217, 'loss/train': 1.879994511604309} 08/31/2021 12:38:59 - INFO - __main__ - Step 129219: {'lr': 2.3933521858028385e-05, 'samples': 24810048, 'steps': 129218, 'loss/train': 0.7515380382537842} 08/31/2021 12:38:59 - INFO - __main__ - Step 129220: {'lr': 2.393125608970234e-05, 'samples': 24810240, 'steps': 129219, 'loss/train': 1.297676682472229} 08/31/2021 12:39:01 - INFO - __main__ - Step 129221: {'lr': 2.3928990423239345e-05, 'samples': 24810432, 'steps': 129220, 'loss/train': 0.7173519134521484} 08/31/2021 12:39:01 - INFO - __main__ - Step 129222: {'lr': 2.3926724858640475e-05, 'samples': 24810624, 'steps': 129221, 'loss/train': 1.382613182067871} 08/31/2021 12:39:02 - INFO - __main__ - Step 129223: {'lr': 2.3924459395906763e-05, 'samples': 24810816, 'steps': 129222, 'loss/train': 0.9743108749389648} 08/31/2021 12:39:02 - INFO - __main__ - Step 129224: {'lr': 2.3922194035039174e-05, 'samples': 24811008, 'steps': 129223, 'loss/train': 0.8673029541969299} 08/31/2021 12:39:02 - INFO - __main__ - Step 129225: {'lr': 2.391992877603874e-05, 'samples': 24811200, 'steps': 129224, 'loss/train': 2.0300650596618652} 08/31/2021 12:39:03 - INFO - __main__ - Step 129226: {'lr': 2.3917663618906516e-05, 'samples': 24811392, 'steps': 129225, 'loss/train': 1.1925270557403564} 08/31/2021 12:39:05 - INFO - __main__ - Step 129227: {'lr': 2.3915398563643498e-05, 'samples': 24811584, 'steps': 129226, 'loss/train': 1.1625884771347046} 08/31/2021 12:39:05 - INFO - __main__ - Step 129228: {'lr': 2.391313361025077e-05, 'samples': 24811776, 'steps': 129227, 'loss/train': 0.7981674075126648} 08/31/2021 12:39:06 - INFO - __main__ - Step 129229: {'lr': 2.391086875872925e-05, 'samples': 24811968, 'steps': 129228, 'loss/train': 1.197098970413208} 08/31/2021 12:39:06 - INFO - __main__ - Step 129230: {'lr': 2.3908604009079988e-05, 'samples': 24812160, 'steps': 129229, 'loss/train': 2.266278028488159} 08/31/2021 12:39:06 - INFO - __main__ - Step 129231: {'lr': 2.390633936130404e-05, 'samples': 24812352, 'steps': 129230, 'loss/train': 1.309936285018921} 08/31/2021 12:39:08 - INFO - __main__ - Step 129232: {'lr': 2.390407481540238e-05, 'samples': 24812544, 'steps': 129231, 'loss/train': 1.3019802570343018} 08/31/2021 12:39:08 - INFO - __main__ - Step 129233: {'lr': 2.3901810371376066e-05, 'samples': 24812736, 'steps': 129232, 'loss/train': 0.8867675065994263} 08/31/2021 12:39:09 - INFO - __main__ - Step 129234: {'lr': 2.3899546029226116e-05, 'samples': 24812928, 'steps': 129233, 'loss/train': 1.4179234504699707} 08/31/2021 12:39:09 - INFO - __main__ - Step 129235: {'lr': 2.3897281788953535e-05, 'samples': 24813120, 'steps': 129234, 'loss/train': 0.9294089674949646} 08/31/2021 12:39:10 - INFO - __main__ - Step 129236: {'lr': 2.3895017650559377e-05, 'samples': 24813312, 'steps': 129235, 'loss/train': 1.2140142917633057} 08/31/2021 12:39:11 - INFO - __main__ - Step 129237: {'lr': 2.3892753614044583e-05, 'samples': 24813504, 'steps': 129236, 'loss/train': 0.6322422623634338} 08/31/2021 12:39:11 - INFO - __main__ - Step 129238: {'lr': 2.3890489679410264e-05, 'samples': 24813696, 'steps': 129237, 'loss/train': 0.519905686378479} 08/31/2021 12:39:12 - INFO - __main__ - Step 129239: {'lr': 2.3888225846657425e-05, 'samples': 24813888, 'steps': 129238, 'loss/train': 0.42412838339805603} 08/31/2021 12:39:12 - INFO - __main__ - Step 129240: {'lr': 2.388596211578703e-05, 'samples': 24814080, 'steps': 129239, 'loss/train': 1.2625044584274292} 08/31/2021 12:39:13 - INFO - __main__ - Step 129241: {'lr': 2.3883698486800136e-05, 'samples': 24814272, 'steps': 129240, 'loss/train': 1.0592120885849} 08/31/2021 12:39:13 - INFO - __main__ - Step 129242: {'lr': 2.3881434959697746e-05, 'samples': 24814464, 'steps': 129241, 'loss/train': 1.3979235887527466} 08/31/2021 12:39:14 - INFO - __main__ - Step 129243: {'lr': 2.3879171534480907e-05, 'samples': 24814656, 'steps': 129242, 'loss/train': 0.6403436660766602} 08/31/2021 12:39:15 - INFO - __main__ - Step 129244: {'lr': 2.38769082111506e-05, 'samples': 24814848, 'steps': 129243, 'loss/train': 1.5161755084991455} 08/31/2021 12:39:15 - INFO - __main__ - Step 129245: {'lr': 2.38746449897079e-05, 'samples': 24815040, 'steps': 129244, 'loss/train': 0.7527511715888977} 08/31/2021 12:39:16 - INFO - __main__ - Step 129246: {'lr': 2.3872381870153782e-05, 'samples': 24815232, 'steps': 129245, 'loss/train': 1.655515432357788} 08/31/2021 12:39:16 - INFO - __main__ - Step 129247: {'lr': 2.387011885248927e-05, 'samples': 24815424, 'steps': 129246, 'loss/train': 0.5799820423126221} 08/31/2021 12:39:18 - INFO - __main__ - Step 129248: {'lr': 2.3867855936715392e-05, 'samples': 24815616, 'steps': 129247, 'loss/train': 1.61942458152771} 08/31/2021 12:39:18 - INFO - __main__ - Step 129249: {'lr': 2.386559312283318e-05, 'samples': 24815808, 'steps': 129248, 'loss/train': 1.0273003578186035} 08/31/2021 12:39:18 - INFO - __main__ - Step 129250: {'lr': 2.386333041084368e-05, 'samples': 24816000, 'steps': 129249, 'loss/train': 0.8622131943702698} 08/31/2021 12:39:19 - INFO - __main__ - Step 129251: {'lr': 2.3861067800747842e-05, 'samples': 24816192, 'steps': 129250, 'loss/train': 1.0699666738510132} 08/31/2021 12:39:19 - INFO - __main__ - Step 129252: {'lr': 2.3858805292546694e-05, 'samples': 24816384, 'steps': 129251, 'loss/train': 0.8314140439033508} 08/31/2021 12:39:21 - INFO - __main__ - Step 129253: {'lr': 2.3856542886241285e-05, 'samples': 24816576, 'steps': 129252, 'loss/train': 0.06447199732065201} 08/31/2021 12:39:21 - INFO - __main__ - Step 129254: {'lr': 2.3854280581832642e-05, 'samples': 24816768, 'steps': 129253, 'loss/train': 1.3987784385681152} 08/31/2021 12:39:21 - INFO - __main__ - Step 129255: {'lr': 2.385201837932177e-05, 'samples': 24816960, 'steps': 129254, 'loss/train': 1.2878555059432983} 08/31/2021 12:39:22 - INFO - __main__ - Step 129256: {'lr': 2.3849756278709665e-05, 'samples': 24817152, 'steps': 129255, 'loss/train': 0.3596722483634949} 08/31/2021 12:39:22 - INFO - __main__ - Step 129257: {'lr': 2.3847494279997412e-05, 'samples': 24817344, 'steps': 129256, 'loss/train': 1.3178179264068604} 08/31/2021 12:39:23 - INFO - __main__ - Step 129258: {'lr': 2.384523238318595e-05, 'samples': 24817536, 'steps': 129257, 'loss/train': 1.560067057609558} 08/31/2021 12:39:24 - INFO - __main__ - Step 129259: {'lr': 2.3842970588276362e-05, 'samples': 24817728, 'steps': 129258, 'loss/train': 0.6509994864463806} 08/31/2021 12:39:24 - INFO - __main__ - Step 129260: {'lr': 2.3840708895269626e-05, 'samples': 24817920, 'steps': 129259, 'loss/train': 1.2438079118728638} 08/31/2021 12:39:25 - INFO - __main__ - Step 129261: {'lr': 2.383844730416676e-05, 'samples': 24818112, 'steps': 129260, 'loss/train': 0.3740115761756897} 08/31/2021 12:39:25 - INFO - __main__ - Step 129262: {'lr': 2.3836185814968826e-05, 'samples': 24818304, 'steps': 129261, 'loss/train': 0.34066399931907654} 08/31/2021 12:39:26 - INFO - __main__ - Step 129263: {'lr': 2.3833924427676874e-05, 'samples': 24818496, 'steps': 129262, 'loss/train': 1.0988584756851196} 08/31/2021 12:39:27 - INFO - __main__ - Step 129264: {'lr': 2.3831663142291794e-05, 'samples': 24818688, 'steps': 129263, 'loss/train': 1.5456597805023193} 08/31/2021 12:39:27 - INFO - __main__ - Step 129265: {'lr': 2.3829401958814695e-05, 'samples': 24818880, 'steps': 129264, 'loss/train': 1.3880566358566284} 08/31/2021 12:39:28 - INFO - __main__ - Step 129266: {'lr': 2.3827140877246552e-05, 'samples': 24819072, 'steps': 129265, 'loss/train': 1.5325864553451538} 08/31/2021 12:39:28 - INFO - __main__ - Step 129267: {'lr': 2.3824879897588443e-05, 'samples': 24819264, 'steps': 129266, 'loss/train': 1.0069308280944824} 08/31/2021 12:39:28 - INFO - __main__ - Step 129268: {'lr': 2.3822619019841313e-05, 'samples': 24819456, 'steps': 129267, 'loss/train': 0.9500262141227722} 08/31/2021 12:39:30 - INFO - __main__ - Step 129269: {'lr': 2.3820358244006246e-05, 'samples': 24819648, 'steps': 129268, 'loss/train': 1.44821035861969} 08/31/2021 12:39:30 - INFO - __main__ - Step 129270: {'lr': 2.381809757008424e-05, 'samples': 24819840, 'steps': 129269, 'loss/train': 1.5849297046661377} 08/31/2021 12:39:31 - INFO - __main__ - Step 129271: {'lr': 2.3815836998076294e-05, 'samples': 24820032, 'steps': 129270, 'loss/train': 0.46102026104927063} 08/31/2021 12:39:31 - INFO - __main__ - Step 129272: {'lr': 2.3813576527983466e-05, 'samples': 24820224, 'steps': 129271, 'loss/train': 0.9572209119796753} 08/31/2021 12:39:31 - INFO - __main__ - Step 129273: {'lr': 2.3811316159806722e-05, 'samples': 24820416, 'steps': 129272, 'loss/train': 1.561899185180664} 08/31/2021 12:39:33 - INFO - __main__ - Step 129274: {'lr': 2.380905589354712e-05, 'samples': 24820608, 'steps': 129273, 'loss/train': 1.1897681951522827} 08/31/2021 12:39:34 - INFO - __main__ - Step 129275: {'lr': 2.380679572920566e-05, 'samples': 24820800, 'steps': 129274, 'loss/train': 0.7930536270141602} 08/31/2021 12:39:34 - INFO - __main__ - Step 129276: {'lr': 2.3804535666783423e-05, 'samples': 24820992, 'steps': 129275, 'loss/train': 0.015421700663864613} 08/31/2021 12:39:34 - INFO - __main__ - Step 129277: {'lr': 2.3802275706281322e-05, 'samples': 24821184, 'steps': 129276, 'loss/train': 0.6242919564247131} 08/31/2021 12:39:35 - INFO - __main__ - Step 129278: {'lr': 2.380001584770042e-05, 'samples': 24821376, 'steps': 129277, 'loss/train': 1.4407644271850586} 08/31/2021 12:39:35 - INFO - __main__ - Step 129279: {'lr': 2.379775609104176e-05, 'samples': 24821568, 'steps': 129278, 'loss/train': 0.6662120223045349} 08/31/2021 12:39:37 - INFO - __main__ - Step 129280: {'lr': 2.3795496436306324e-05, 'samples': 24821760, 'steps': 129279, 'loss/train': 0.8513929843902588} 08/31/2021 12:39:38 - INFO - __main__ - Step 129281: {'lr': 2.379323688349516e-05, 'samples': 24821952, 'steps': 129280, 'loss/train': 0.9060041308403015} 08/31/2021 12:39:38 - INFO - __main__ - Step 129282: {'lr': 2.3790977432609244e-05, 'samples': 24822144, 'steps': 129281, 'loss/train': 1.2533667087554932} 08/31/2021 12:39:39 - INFO - __main__ - Step 129283: {'lr': 2.3788718083649658e-05, 'samples': 24822336, 'steps': 129282, 'loss/train': 1.394429087638855} 08/31/2021 12:39:39 - INFO - __main__ - Step 129284: {'lr': 2.378645883661737e-05, 'samples': 24822528, 'steps': 129283, 'loss/train': 1.4552351236343384} 08/31/2021 12:39:39 - INFO - __main__ - Step 129285: {'lr': 2.3784199691513408e-05, 'samples': 24822720, 'steps': 129284, 'loss/train': 1.452352523803711} 08/31/2021 12:39:41 - INFO - __main__ - Step 129286: {'lr': 2.37819406483388e-05, 'samples': 24822912, 'steps': 129285, 'loss/train': 1.3944075107574463} 08/31/2021 12:39:41 - INFO - __main__ - Step 129287: {'lr': 2.3779681707094546e-05, 'samples': 24823104, 'steps': 129286, 'loss/train': 1.0400288105010986} 08/31/2021 12:39:42 - INFO - __main__ - Step 129288: {'lr': 2.37774228677817e-05, 'samples': 24823296, 'steps': 129287, 'loss/train': 0.6472147107124329} 08/31/2021 12:39:42 - INFO - __main__ - Step 129289: {'lr': 2.3775164130401234e-05, 'samples': 24823488, 'steps': 129288, 'loss/train': 1.8294143676757812} 08/31/2021 12:39:42 - INFO - __main__ - Step 129290: {'lr': 2.3772905494954254e-05, 'samples': 24823680, 'steps': 129289, 'loss/train': 1.1068906784057617} 08/31/2021 12:39:44 - INFO - __main__ - Step 129291: {'lr': 2.3770646961441655e-05, 'samples': 24823872, 'steps': 129290, 'loss/train': 1.2706698179244995} 08/31/2021 12:39:45 - INFO - __main__ - Step 129292: {'lr': 2.3768388529864514e-05, 'samples': 24824064, 'steps': 129291, 'loss/train': 1.0138847827911377} 08/31/2021 12:39:45 - INFO - __main__ - Step 129293: {'lr': 2.3766130200223835e-05, 'samples': 24824256, 'steps': 129292, 'loss/train': 1.0300073623657227} 08/31/2021 12:39:45 - INFO - __main__ - Step 129294: {'lr': 2.3763871972520667e-05, 'samples': 24824448, 'steps': 129293, 'loss/train': 0.7305964827537537} 08/31/2021 12:39:46 - INFO - __main__ - Step 129295: {'lr': 2.3761613846755986e-05, 'samples': 24824640, 'steps': 129294, 'loss/train': 0.037432558834552765} 08/31/2021 12:39:46 - INFO - __main__ - Step 129296: {'lr': 2.3759355822930843e-05, 'samples': 24824832, 'steps': 129295, 'loss/train': 0.014731242321431637} 08/31/2021 12:39:47 - INFO - __main__ - Step 129297: {'lr': 2.3757097901046244e-05, 'samples': 24825024, 'steps': 129296, 'loss/train': 0.7239058017730713} 08/31/2021 12:39:48 - INFO - __main__ - Step 129298: {'lr': 2.3754840081103206e-05, 'samples': 24825216, 'steps': 129297, 'loss/train': 0.4926353394985199} 08/31/2021 12:39:48 - INFO - __main__ - Step 129299: {'lr': 2.3752582363102737e-05, 'samples': 24825408, 'steps': 129298, 'loss/train': 0.352556049823761} 08/31/2021 12:39:49 - INFO - __main__ - Step 129300: {'lr': 2.375032474704586e-05, 'samples': 24825600, 'steps': 129299, 'loss/train': 0.9334772229194641} 08/31/2021 12:39:49 - INFO - __main__ - Step 129301: {'lr': 2.374806723293363e-05, 'samples': 24825792, 'steps': 129300, 'loss/train': 0.8829889297485352} 08/31/2021 12:39:51 - INFO - __main__ - Step 129302: {'lr': 2.3745809820766988e-05, 'samples': 24825984, 'steps': 129301, 'loss/train': 0.2052306979894638} 08/31/2021 12:39:51 - INFO - __main__ - Step 129303: {'lr': 2.3743552510547052e-05, 'samples': 24826176, 'steps': 129302, 'loss/train': 1.8674864768981934} 08/31/2021 12:39:51 - INFO - __main__ - Step 129304: {'lr': 2.3741295302274758e-05, 'samples': 24826368, 'steps': 129303, 'loss/train': 1.5607730150222778} 08/31/2021 12:39:52 - INFO - __main__ - Step 129305: {'lr': 2.3739038195951106e-05, 'samples': 24826560, 'steps': 129304, 'loss/train': 1.3322114944458008} 08/31/2021 12:39:52 - INFO - __main__ - Step 129306: {'lr': 2.3736781191577183e-05, 'samples': 24826752, 'steps': 129305, 'loss/train': 1.002746820449829} 08/31/2021 12:39:52 - INFO - __main__ - Step 129307: {'lr': 2.3734524289153958e-05, 'samples': 24826944, 'steps': 129306, 'loss/train': 0.49737125635147095} 08/31/2021 12:39:54 - INFO - __main__ - Step 129308: {'lr': 2.3732267488682458e-05, 'samples': 24827136, 'steps': 129307, 'loss/train': 0.8594589233398438} 08/31/2021 12:39:54 - INFO - __main__ - Step 129309: {'lr': 2.3730010790163737e-05, 'samples': 24827328, 'steps': 129308, 'loss/train': 0.6834598779678345} 08/31/2021 12:39:55 - INFO - __main__ - Step 129310: {'lr': 2.372775419359874e-05, 'samples': 24827520, 'steps': 129309, 'loss/train': 1.2453398704528809} 08/31/2021 12:39:55 - INFO - __main__ - Step 129311: {'lr': 2.3725497698988546e-05, 'samples': 24827712, 'steps': 129310, 'loss/train': 0.8706222772598267} 08/31/2021 12:39:55 - INFO - __main__ - Step 129312: {'lr': 2.372324130633416e-05, 'samples': 24827904, 'steps': 129311, 'loss/train': 0.8156164884567261} 08/31/2021 12:39:57 - INFO - __main__ - Step 129313: {'lr': 2.3720985015636575e-05, 'samples': 24828096, 'steps': 129312, 'loss/train': 1.11766517162323} 08/31/2021 12:39:57 - INFO - __main__ - Step 129314: {'lr': 2.371872882689685e-05, 'samples': 24828288, 'steps': 129313, 'loss/train': 1.0399153232574463} 08/31/2021 12:39:58 - INFO - __main__ - Step 129315: {'lr': 2.371647274011596e-05, 'samples': 24828480, 'steps': 129314, 'loss/train': 0.6856369376182556} 08/31/2021 12:39:58 - INFO - __main__ - Step 129316: {'lr': 2.371421675529492e-05, 'samples': 24828672, 'steps': 129315, 'loss/train': 0.6899302005767822} 08/31/2021 12:39:59 - INFO - __main__ - Step 129317: {'lr': 2.3711960872434825e-05, 'samples': 24828864, 'steps': 129316, 'loss/train': 1.8773363828659058} 08/31/2021 12:40:01 - INFO - __main__ - Step 129318: {'lr': 2.3709705091536555e-05, 'samples': 24829056, 'steps': 129317, 'loss/train': 0.9085730314254761} 08/31/2021 12:40:01 - INFO - __main__ - Step 129319: {'lr': 2.3707449412601224e-05, 'samples': 24829248, 'steps': 129318, 'loss/train': 1.4356777667999268} 08/31/2021 12:40:01 - INFO - __main__ - Step 129320: {'lr': 2.370519383562983e-05, 'samples': 24829440, 'steps': 129319, 'loss/train': 1.113917350769043} 08/31/2021 12:40:02 - INFO - __main__ - Step 129321: {'lr': 2.3702938360623373e-05, 'samples': 24829632, 'steps': 129320, 'loss/train': 1.014870285987854} 08/31/2021 12:40:02 - INFO - __main__ - Step 129322: {'lr': 2.3700682987582878e-05, 'samples': 24829824, 'steps': 129321, 'loss/train': 1.251439094543457} 08/31/2021 12:40:04 - INFO - __main__ - Step 129323: {'lr': 2.3698427716509375e-05, 'samples': 24830016, 'steps': 129322, 'loss/train': 0.038891490548849106} 08/31/2021 12:40:04 - INFO - __main__ - Step 129324: {'lr': 2.369617254740386e-05, 'samples': 24830208, 'steps': 129323, 'loss/train': 0.5638042092323303} 08/31/2021 12:40:04 - INFO - __main__ - Step 129325: {'lr': 2.3693917480267363e-05, 'samples': 24830400, 'steps': 129324, 'loss/train': 0.5960632562637329} 08/31/2021 12:40:05 - INFO - __main__ - Step 129326: {'lr': 2.3691662515100883e-05, 'samples': 24830592, 'steps': 129325, 'loss/train': 1.4556416273117065} 08/31/2021 12:40:05 - INFO - __main__ - Step 129327: {'lr': 2.3689407651905443e-05, 'samples': 24830784, 'steps': 129326, 'loss/train': 0.9794168472290039} 08/31/2021 12:40:07 - INFO - __main__ - Step 129328: {'lr': 2.3687152890682074e-05, 'samples': 24830976, 'steps': 129327, 'loss/train': 1.0812106132507324} 08/31/2021 12:40:07 - INFO - __main__ - Step 129329: {'lr': 2.3684898231431802e-05, 'samples': 24831168, 'steps': 129328, 'loss/train': 2.196727752685547} 08/31/2021 12:40:07 - INFO - __main__ - Step 129330: {'lr': 2.368264367415565e-05, 'samples': 24831360, 'steps': 129329, 'loss/train': 1.2638152837753296} 08/31/2021 12:40:08 - INFO - __main__ - Step 129331: {'lr': 2.368038921885454e-05, 'samples': 24831552, 'steps': 129330, 'loss/train': 0.9309611916542053} 08/31/2021 12:40:08 - INFO - __main__ - Step 129332: {'lr': 2.367813486552958e-05, 'samples': 24831744, 'steps': 129331, 'loss/train': 1.658789873123169} 08/31/2021 12:40:10 - INFO - __main__ - Step 129333: {'lr': 2.3675880614181744e-05, 'samples': 24831936, 'steps': 129332, 'loss/train': 1.011043667793274} 08/31/2021 12:40:10 - INFO - __main__ - Step 129334: {'lr': 2.3673626464812082e-05, 'samples': 24832128, 'steps': 129333, 'loss/train': 0.410015732049942} 08/31/2021 12:40:11 - INFO - __main__ - Step 129335: {'lr': 2.3671372417421592e-05, 'samples': 24832320, 'steps': 129334, 'loss/train': 0.026670129969716072} 08/31/2021 12:40:11 - INFO - __main__ - Step 129336: {'lr': 2.366911847201128e-05, 'samples': 24832512, 'steps': 129335, 'loss/train': 0.9973690509796143} 08/31/2021 12:40:11 - INFO - __main__ - Step 129337: {'lr': 2.3666864628582168e-05, 'samples': 24832704, 'steps': 129336, 'loss/train': 0.9135482907295227} 08/31/2021 12:40:12 - INFO - __main__ - Step 129338: {'lr': 2.3664610887135286e-05, 'samples': 24832896, 'steps': 129337, 'loss/train': 0.8844901323318481} 08/31/2021 12:40:14 - INFO - __main__ - Step 129339: {'lr': 2.366235724767163e-05, 'samples': 24833088, 'steps': 129338, 'loss/train': 0.014398625120520592} 08/31/2021 12:40:14 - INFO - __main__ - Step 129340: {'lr': 2.36601037101922e-05, 'samples': 24833280, 'steps': 129339, 'loss/train': 0.9193519949913025} 08/31/2021 12:40:15 - INFO - __main__ - Step 129341: {'lr': 2.365785027469808e-05, 'samples': 24833472, 'steps': 129340, 'loss/train': 1.2804523706436157} 08/31/2021 12:40:15 - INFO - __main__ - Step 129342: {'lr': 2.365559694119021e-05, 'samples': 24833664, 'steps': 129341, 'loss/train': 1.3613543510437012} 08/31/2021 12:40:15 - INFO - __main__ - Step 129343: {'lr': 2.3653343709669652e-05, 'samples': 24833856, 'steps': 129342, 'loss/train': 0.9038904309272766} 08/31/2021 12:40:17 - INFO - __main__ - Step 129344: {'lr': 2.3651090580137423e-05, 'samples': 24834048, 'steps': 129343, 'loss/train': 0.794877827167511} 08/31/2021 12:40:17 - INFO - __main__ - Step 129345: {'lr': 2.3648837552594504e-05, 'samples': 24834240, 'steps': 129344, 'loss/train': 1.14812433719635} 08/31/2021 12:40:18 - INFO - __main__ - Step 129346: {'lr': 2.3646584627041917e-05, 'samples': 24834432, 'steps': 129345, 'loss/train': 1.2263518571853638} 08/31/2021 12:40:18 - INFO - __main__ - Step 129347: {'lr': 2.3644331803480663e-05, 'samples': 24834624, 'steps': 129346, 'loss/train': 1.2690885066986084} 08/31/2021 12:40:18 - INFO - __main__ - Step 129348: {'lr': 2.364207908191182e-05, 'samples': 24834816, 'steps': 129347, 'loss/train': 1.131392002105713} 08/31/2021 12:40:19 - INFO - __main__ - Step 129349: {'lr': 2.363982646233634e-05, 'samples': 24835008, 'steps': 129348, 'loss/train': 1.1526755094528198} 08/31/2021 12:40:20 - INFO - __main__ - Step 129350: {'lr': 2.363757394475527e-05, 'samples': 24835200, 'steps': 129349, 'loss/train': 1.1882822513580322} 08/31/2021 12:40:21 - INFO - __main__ - Step 129351: {'lr': 2.3635321529169585e-05, 'samples': 24835392, 'steps': 129350, 'loss/train': 0.2978793978691101} 08/31/2021 12:40:21 - INFO - __main__ - Step 129352: {'lr': 2.3633069215580366e-05, 'samples': 24835584, 'steps': 129351, 'loss/train': 0.7633166313171387} 08/31/2021 12:40:21 - INFO - __main__ - Step 129353: {'lr': 2.3630817003988587e-05, 'samples': 24835776, 'steps': 129352, 'loss/train': 0.9962397217750549} 08/31/2021 12:40:22 - INFO - __main__ - Step 129354: {'lr': 2.362856489439527e-05, 'samples': 24835968, 'steps': 129353, 'loss/train': 1.1935579776763916} 08/31/2021 12:40:23 - INFO - __main__ - Step 129355: {'lr': 2.3626312886801423e-05, 'samples': 24836160, 'steps': 129354, 'loss/train': 1.2672135829925537} 08/31/2021 12:40:24 - INFO - __main__ - Step 129356: {'lr': 2.3624060981208062e-05, 'samples': 24836352, 'steps': 129355, 'loss/train': 1.5162912607192993} 08/31/2021 12:40:24 - INFO - __main__ - Step 129357: {'lr': 2.362180917761625e-05, 'samples': 24836544, 'steps': 129356, 'loss/train': 1.3755459785461426} 08/31/2021 12:40:24 - INFO - __main__ - Step 129358: {'lr': 2.3619557476026925e-05, 'samples': 24836736, 'steps': 129357, 'loss/train': 1.1720197200775146} 08/31/2021 12:40:25 - INFO - __main__ - Step 129359: {'lr': 2.361730587644112e-05, 'samples': 24836928, 'steps': 129358, 'loss/train': 0.44984257221221924} 08/31/2021 12:40:26 - INFO - __main__ - Step 129360: {'lr': 2.3615054378859885e-05, 'samples': 24837120, 'steps': 129359, 'loss/train': 0.9231493473052979} 08/31/2021 12:40:27 - INFO - __main__ - Step 129361: {'lr': 2.361280298328419e-05, 'samples': 24837312, 'steps': 129360, 'loss/train': 1.168134331703186} 08/31/2021 12:40:27 - INFO - __main__ - Step 129362: {'lr': 2.36105516897151e-05, 'samples': 24837504, 'steps': 129361, 'loss/train': 1.2068514823913574} 08/31/2021 12:40:28 - INFO - __main__ - Step 129363: {'lr': 2.3608300498153574e-05, 'samples': 24837696, 'steps': 129362, 'loss/train': 1.5707560777664185} 08/31/2021 12:40:28 - INFO - __main__ - Step 129364: {'lr': 2.3606049408600672e-05, 'samples': 24837888, 'steps': 129363, 'loss/train': 0.6001960039138794} 08/31/2021 12:40:28 - INFO - __main__ - Step 129365: {'lr': 2.3603798421057365e-05, 'samples': 24838080, 'steps': 129364, 'loss/train': 1.2034748792648315} 08/31/2021 12:40:30 - INFO - __main__ - Step 129366: {'lr': 2.3601547535524735e-05, 'samples': 24838272, 'steps': 129365, 'loss/train': 1.5075984001159668} 08/31/2021 12:40:31 - INFO - __main__ - Step 129367: {'lr': 2.359929675200373e-05, 'samples': 24838464, 'steps': 129366, 'loss/train': 0.9141397476196289} 08/31/2021 12:40:31 - INFO - __main__ - Step 129368: {'lr': 2.359704607049537e-05, 'samples': 24838656, 'steps': 129367, 'loss/train': 0.052585288882255554} 08/31/2021 12:40:31 - INFO - __main__ - Step 129369: {'lr': 2.3594795491000713e-05, 'samples': 24838848, 'steps': 129368, 'loss/train': 1.9448152780532837} 08/31/2021 12:40:32 - INFO - __main__ - Step 129370: {'lr': 2.3592545013520734e-05, 'samples': 24839040, 'steps': 129369, 'loss/train': 1.1920970678329468} 08/31/2021 12:40:32 - INFO - __main__ - Step 129371: {'lr': 2.359029463805651e-05, 'samples': 24839232, 'steps': 129370, 'loss/train': 0.014162632636725903} 08/31/2021 12:40:33 - INFO - __main__ - Step 129372: {'lr': 2.3588044364608983e-05, 'samples': 24839424, 'steps': 129371, 'loss/train': 1.4593496322631836} 08/31/2021 12:40:34 - INFO - __main__ - Step 129373: {'lr': 2.358579419317916e-05, 'samples': 24839616, 'steps': 129372, 'loss/train': 0.6285390257835388} 08/31/2021 12:40:34 - INFO - __main__ - Step 129374: {'lr': 2.358354412376809e-05, 'samples': 24839808, 'steps': 129373, 'loss/train': 1.0986049175262451} 08/31/2021 12:40:35 - INFO - __main__ - Step 129375: {'lr': 2.3581294156376805e-05, 'samples': 24840000, 'steps': 129374, 'loss/train': 1.2549326419830322} 08/31/2021 12:40:35 - INFO - __main__ - Step 129376: {'lr': 2.357904429100627e-05, 'samples': 24840192, 'steps': 129375, 'loss/train': 1.1246638298034668} 08/31/2021 12:40:36 - INFO - __main__ - Step 129377: {'lr': 2.3576794527657512e-05, 'samples': 24840384, 'steps': 129376, 'loss/train': 1.2856804132461548} 08/31/2021 12:40:37 - INFO - __main__ - Step 129378: {'lr': 2.3574544866331566e-05, 'samples': 24840576, 'steps': 129377, 'loss/train': 0.5243107080459595} 08/31/2021 12:40:37 - INFO - __main__ - Step 129379: {'lr': 2.357229530702945e-05, 'samples': 24840768, 'steps': 129378, 'loss/train': 0.7851836085319519} 08/31/2021 12:40:38 - INFO - __main__ - Step 129380: {'lr': 2.357004584975217e-05, 'samples': 24840960, 'steps': 129379, 'loss/train': 1.4188058376312256} 08/31/2021 12:40:38 - INFO - __main__ - Step 129381: {'lr': 2.3567796494500722e-05, 'samples': 24841152, 'steps': 129380, 'loss/train': 1.4056028127670288} 08/31/2021 12:40:38 - INFO - __main__ - Step 129382: {'lr': 2.356554724127613e-05, 'samples': 24841344, 'steps': 129381, 'loss/train': 1.1918920278549194} 08/31/2021 12:40:40 - INFO - __main__ - Step 129383: {'lr': 2.35632980900794e-05, 'samples': 24841536, 'steps': 129382, 'loss/train': 1.2950353622436523} 08/31/2021 12:40:40 - INFO - __main__ - Step 129384: {'lr': 2.3561049040911608e-05, 'samples': 24841728, 'steps': 129383, 'loss/train': 1.1624170541763306} 08/31/2021 12:40:41 - INFO - __main__ - Step 129385: {'lr': 2.3558800093773675e-05, 'samples': 24841920, 'steps': 129384, 'loss/train': 0.12436118721961975} 08/31/2021 12:40:41 - INFO - __main__ - Step 129386: {'lr': 2.3556551248666623e-05, 'samples': 24842112, 'steps': 129385, 'loss/train': 1.783010482788086} 08/31/2021 12:40:41 - INFO - __main__ - Step 129387: {'lr': 2.355430250559151e-05, 'samples': 24842304, 'steps': 129386, 'loss/train': 0.4403316378593445} 08/31/2021 12:40:43 - INFO - __main__ - Step 129388: {'lr': 2.3552053864549367e-05, 'samples': 24842496, 'steps': 129387, 'loss/train': 1.2968589067459106} 08/31/2021 12:40:43 - INFO - __main__ - Step 129389: {'lr': 2.3549805325541128e-05, 'samples': 24842688, 'steps': 129388, 'loss/train': 0.5941014289855957} 08/31/2021 12:40:44 - INFO - __main__ - Step 129390: {'lr': 2.3547556888567883e-05, 'samples': 24842880, 'steps': 129389, 'loss/train': 0.7880716323852539} 08/31/2021 12:40:44 - INFO - __main__ - Step 129391: {'lr': 2.3545308553630602e-05, 'samples': 24843072, 'steps': 129390, 'loss/train': 0.5203719139099121} 08/31/2021 12:40:44 - INFO - __main__ - Step 129392: {'lr': 2.354306032073031e-05, 'samples': 24843264, 'steps': 129391, 'loss/train': 1.2358111143112183} 08/31/2021 12:40:46 - INFO - __main__ - Step 129393: {'lr': 2.3540812189868005e-05, 'samples': 24843456, 'steps': 129392, 'loss/train': 1.0566452741622925} 08/31/2021 12:40:47 - INFO - __main__ - Step 129394: {'lr': 2.3538564161044745e-05, 'samples': 24843648, 'steps': 129393, 'loss/train': 0.6416962742805481} 08/31/2021 12:40:47 - INFO - __main__ - Step 129395: {'lr': 2.35363162342615e-05, 'samples': 24843840, 'steps': 129394, 'loss/train': 1.3064792156219482} 08/31/2021 12:40:48 - INFO - __main__ - Step 129396: {'lr': 2.35340684095193e-05, 'samples': 24844032, 'steps': 129395, 'loss/train': 1.2102242708206177} 08/31/2021 12:40:48 - INFO - __main__ - Step 129397: {'lr': 2.3531820686819195e-05, 'samples': 24844224, 'steps': 129396, 'loss/train': 0.9545333385467529} 08/31/2021 12:40:48 - INFO - __main__ - Step 129398: {'lr': 2.35295730661621e-05, 'samples': 24844416, 'steps': 129397, 'loss/train': 1.5551986694335938} 08/31/2021 12:40:50 - INFO - __main__ - Step 129399: {'lr': 2.3527325547549107e-05, 'samples': 24844608, 'steps': 129398, 'loss/train': 1.2773209810256958} 08/31/2021 12:40:50 - INFO - __main__ - Step 129400: {'lr': 2.3525078130981203e-05, 'samples': 24844800, 'steps': 129399, 'loss/train': 0.021303188055753708} 08/31/2021 12:40:51 - INFO - __main__ - Step 129401: {'lr': 2.3522830816459395e-05, 'samples': 24844992, 'steps': 129400, 'loss/train': 0.8211870193481445} 08/31/2021 12:40:51 - INFO - __main__ - Step 129402: {'lr': 2.3520583603984707e-05, 'samples': 24845184, 'steps': 129401, 'loss/train': 0.3930756747722626} 08/31/2021 12:40:51 - INFO - __main__ - Step 129403: {'lr': 2.3518336493558167e-05, 'samples': 24845376, 'steps': 129402, 'loss/train': 0.917085587978363} 08/31/2021 12:40:53 - INFO - __main__ - Step 129404: {'lr': 2.3516089485180747e-05, 'samples': 24845568, 'steps': 129403, 'loss/train': 0.9620290398597717} 08/31/2021 12:40:54 - INFO - __main__ - Step 129405: {'lr': 2.3513842578853473e-05, 'samples': 24845760, 'steps': 129404, 'loss/train': 0.8218140006065369} 08/31/2021 12:40:54 - INFO - __main__ - Step 129406: {'lr': 2.35115957745774e-05, 'samples': 24845952, 'steps': 129405, 'loss/train': 0.92705237865448} 08/31/2021 12:40:54 - INFO - __main__ - Step 129407: {'lr': 2.350934907235347e-05, 'samples': 24846144, 'steps': 129406, 'loss/train': 0.545157253742218} 08/31/2021 12:40:55 - INFO - __main__ - Step 129408: {'lr': 2.3507102472182768e-05, 'samples': 24846336, 'steps': 129407, 'loss/train': 1.108681082725525} 08/31/2021 12:40:56 - INFO - __main__ - Step 129409: {'lr': 2.3504855974066235e-05, 'samples': 24846528, 'steps': 129408, 'loss/train': 1.4477760791778564} 08/31/2021 12:40:57 - INFO - __main__ - Step 129410: {'lr': 2.350260957800496e-05, 'samples': 24846720, 'steps': 129409, 'loss/train': 1.2018427848815918} 08/31/2021 12:40:57 - INFO - __main__ - Step 129411: {'lr': 2.350036328399993e-05, 'samples': 24846912, 'steps': 129410, 'loss/train': 1.656285047531128} 08/31/2021 12:40:57 - INFO - __main__ - Step 129412: {'lr': 2.3498117092052103e-05, 'samples': 24847104, 'steps': 129411, 'loss/train': 1.5391291379928589} 08/31/2021 12:40:58 - INFO - __main__ - Step 129413: {'lr': 2.3495871002162523e-05, 'samples': 24847296, 'steps': 129412, 'loss/train': 1.2063640356063843} 08/31/2021 12:40:58 - INFO - __main__ - Step 129414: {'lr': 2.349362501433222e-05, 'samples': 24847488, 'steps': 129413, 'loss/train': 0.4161178171634674} 08/31/2021 12:41:00 - INFO - __main__ - Step 129415: {'lr': 2.3491379128562196e-05, 'samples': 24847680, 'steps': 129414, 'loss/train': 1.6921639442443848} 08/31/2021 12:41:00 - INFO - __main__ - Step 129416: {'lr': 2.3489133344853447e-05, 'samples': 24847872, 'steps': 129415, 'loss/train': 0.027877414599061012} 08/31/2021 12:41:01 - INFO - __main__ - Step 129417: {'lr': 2.3486887663207002e-05, 'samples': 24848064, 'steps': 129416, 'loss/train': 1.3266589641571045} 08/31/2021 12:41:01 - INFO - __main__ - Step 129418: {'lr': 2.3484642083623887e-05, 'samples': 24848256, 'steps': 129417, 'loss/train': 1.457440972328186} 08/31/2021 12:41:02 - INFO - __main__ - Step 129419: {'lr': 2.348239660610507e-05, 'samples': 24848448, 'steps': 129418, 'loss/train': 0.039930034428834915} 08/31/2021 12:41:03 - INFO - __main__ - Step 129420: {'lr': 2.3480151230651614e-05, 'samples': 24848640, 'steps': 129419, 'loss/train': 0.10342476516962051} 08/31/2021 12:41:04 - INFO - __main__ - Step 129421: {'lr': 2.3477905957264512e-05, 'samples': 24848832, 'steps': 129420, 'loss/train': 0.8134994506835938} 08/31/2021 12:41:04 - INFO - __main__ - Step 129422: {'lr': 2.3475660785944735e-05, 'samples': 24849024, 'steps': 129421, 'loss/train': 1.1298984289169312} 08/31/2021 12:41:04 - INFO - __main__ - Step 129423: {'lr': 2.347341571669337e-05, 'samples': 24849216, 'steps': 129422, 'loss/train': 0.6764848232269287} 08/31/2021 12:41:05 - INFO - __main__ - Step 129424: {'lr': 2.3471170749511413e-05, 'samples': 24849408, 'steps': 129423, 'loss/train': 2.7019095420837402} 08/31/2021 12:41:07 - INFO - __main__ - Step 129425: {'lr': 2.3468925884399806e-05, 'samples': 24849600, 'steps': 129424, 'loss/train': 0.5854904055595398} 08/31/2021 12:41:08 - INFO - __main__ - Step 129426: {'lr': 2.3466681121359606e-05, 'samples': 24849792, 'steps': 129425, 'loss/train': 1.238860845565796} 08/31/2021 12:41:08 - INFO - __main__ - Step 129427: {'lr': 2.3464436460391813e-05, 'samples': 24849984, 'steps': 129426, 'loss/train': 2.693300724029541} 08/31/2021 12:41:08 - INFO - __main__ - Step 129428: {'lr': 2.3462191901497453e-05, 'samples': 24850176, 'steps': 129427, 'loss/train': 2.4564414024353027} 08/31/2021 12:41:09 - INFO - __main__ - Step 129429: {'lr': 2.3459947444677553e-05, 'samples': 24850368, 'steps': 129428, 'loss/train': 2.576869249343872} 08/31/2021 12:41:09 - INFO - __main__ - Step 129430: {'lr': 2.3457703089933085e-05, 'samples': 24850560, 'steps': 129429, 'loss/train': 0.9459638595581055} 08/31/2021 12:41:09 - INFO - __main__ - Step 129431: {'lr': 2.3455458837265076e-05, 'samples': 24850752, 'steps': 129430, 'loss/train': 2.891655921936035} 08/31/2021 12:41:11 - INFO - __main__ - Step 129432: {'lr': 2.345321468667455e-05, 'samples': 24850944, 'steps': 129431, 'loss/train': 1.468691110610962} 08/31/2021 12:41:11 - INFO - __main__ - Step 129433: {'lr': 2.3450970638162538e-05, 'samples': 24851136, 'steps': 129432, 'loss/train': 1.082324743270874} 08/31/2021 12:41:12 - INFO - __main__ - Step 129434: {'lr': 2.3448726691729984e-05, 'samples': 24851328, 'steps': 129433, 'loss/train': 0.9890090823173523} 08/31/2021 12:41:12 - INFO - __main__ - Step 129435: {'lr': 2.3446482847377965e-05, 'samples': 24851520, 'steps': 129434, 'loss/train': 0.7857682108879089} 08/31/2021 12:41:12 - INFO - __main__ - Step 129436: {'lr': 2.344423910510743e-05, 'samples': 24851712, 'steps': 129435, 'loss/train': 0.790455162525177} 08/31/2021 12:41:14 - INFO - __main__ - Step 129437: {'lr': 2.3441995464919457e-05, 'samples': 24851904, 'steps': 129436, 'loss/train': 0.9601499438285828} 08/31/2021 12:41:14 - INFO - __main__ - Step 129438: {'lr': 2.343975192681505e-05, 'samples': 24852096, 'steps': 129437, 'loss/train': 1.9048209190368652} 08/31/2021 12:41:15 - INFO - __main__ - Step 129439: {'lr': 2.3437508490795178e-05, 'samples': 24852288, 'steps': 129438, 'loss/train': 1.1026630401611328} 08/31/2021 12:41:15 - INFO - __main__ - Step 129440: {'lr': 2.3435265156860842e-05, 'samples': 24852480, 'steps': 129439, 'loss/train': 0.9256119132041931} 08/31/2021 12:41:15 - INFO - __main__ - Step 129441: {'lr': 2.3433021925013092e-05, 'samples': 24852672, 'steps': 129440, 'loss/train': 0.6214708089828491} 08/31/2021 12:41:16 - INFO - __main__ - Step 129442: {'lr': 2.3430778795252904e-05, 'samples': 24852864, 'steps': 129441, 'loss/train': 1.5246970653533936} 08/31/2021 12:41:17 - INFO - __main__ - Step 129443: {'lr': 2.342853576758133e-05, 'samples': 24853056, 'steps': 129442, 'loss/train': 1.0617148876190186} 08/31/2021 12:41:18 - INFO - __main__ - Step 129444: {'lr': 2.3426292841999374e-05, 'samples': 24853248, 'steps': 129443, 'loss/train': 0.6972574591636658} 08/31/2021 12:41:18 - INFO - __main__ - Step 129445: {'lr': 2.3424050018508003e-05, 'samples': 24853440, 'steps': 129444, 'loss/train': 0.8683950901031494} 08/31/2021 12:41:18 - INFO - __main__ - Step 129446: {'lr': 2.342180729710827e-05, 'samples': 24853632, 'steps': 129445, 'loss/train': 0.8247022032737732} 08/31/2021 12:41:19 - INFO - __main__ - Step 129447: {'lr': 2.3419564677801182e-05, 'samples': 24853824, 'steps': 129446, 'loss/train': 1.6389501094818115} 08/31/2021 12:41:20 - INFO - __main__ - Step 129448: {'lr': 2.3417322160587757e-05, 'samples': 24854016, 'steps': 129447, 'loss/train': 0.7310343384742737} 08/31/2021 12:41:21 - INFO - __main__ - Step 129449: {'lr': 2.341507974546897e-05, 'samples': 24854208, 'steps': 129448, 'loss/train': 1.1517333984375} 08/31/2021 12:41:21 - INFO - __main__ - Step 129450: {'lr': 2.341283743244585e-05, 'samples': 24854400, 'steps': 129449, 'loss/train': 0.8613404631614685} 08/31/2021 12:41:21 - INFO - __main__ - Step 129451: {'lr': 2.341059522151945e-05, 'samples': 24854592, 'steps': 129450, 'loss/train': 1.3479830026626587} 08/31/2021 12:41:22 - INFO - __main__ - Step 129452: {'lr': 2.3408353112690713e-05, 'samples': 24854784, 'steps': 129451, 'loss/train': 0.04522758722305298} 08/31/2021 12:41:24 - INFO - __main__ - Step 129453: {'lr': 2.3406111105960663e-05, 'samples': 24854976, 'steps': 129452, 'loss/train': 0.793739914894104} 08/31/2021 12:41:25 - INFO - __main__ - Step 129454: {'lr': 2.3403869201330336e-05, 'samples': 24855168, 'steps': 129453, 'loss/train': 1.3219534158706665} 08/31/2021 12:41:25 - INFO - __main__ - Step 129455: {'lr': 2.3401627398800696e-05, 'samples': 24855360, 'steps': 129454, 'loss/train': 0.7423906922340393} 08/31/2021 12:41:25 - INFO - __main__ - Step 129456: {'lr': 2.3399385698372828e-05, 'samples': 24855552, 'steps': 129455, 'loss/train': 0.38241931796073914} 08/31/2021 12:41:26 - INFO - __main__ - Step 129457: {'lr': 2.3397144100047673e-05, 'samples': 24855744, 'steps': 129456, 'loss/train': 0.40709391236305237} 08/31/2021 12:41:27 - INFO - __main__ - Step 129458: {'lr': 2.339490260382626e-05, 'samples': 24855936, 'steps': 129457, 'loss/train': 0.5989523530006409} 08/31/2021 12:41:28 - INFO - __main__ - Step 129459: {'lr': 2.3392661209709647e-05, 'samples': 24856128, 'steps': 129458, 'loss/train': 1.440442681312561} 08/31/2021 12:41:28 - INFO - __main__ - Step 129460: {'lr': 2.3390419917698776e-05, 'samples': 24856320, 'steps': 129459, 'loss/train': 0.7725304365158081} 08/31/2021 12:41:28 - INFO - __main__ - Step 129461: {'lr': 2.3388178727794666e-05, 'samples': 24856512, 'steps': 129460, 'loss/train': 1.2718192338943481} 08/31/2021 12:41:29 - INFO - __main__ - Step 129462: {'lr': 2.3385937639998383e-05, 'samples': 24856704, 'steps': 129461, 'loss/train': 1.3051438331604004} 08/31/2021 12:41:30 - INFO - __main__ - Step 129463: {'lr': 2.3383696654310892e-05, 'samples': 24856896, 'steps': 129462, 'loss/train': 0.027803761884570122} 08/31/2021 12:41:31 - INFO - __main__ - Step 129464: {'lr': 2.338145577073325e-05, 'samples': 24857088, 'steps': 129463, 'loss/train': 0.9627647995948792} 08/31/2021 12:41:31 - INFO - __main__ - Step 129465: {'lr': 2.3379214989266374e-05, 'samples': 24857280, 'steps': 129464, 'loss/train': 1.351100206375122} 08/31/2021 12:41:32 - INFO - __main__ - Step 129466: {'lr': 2.3376974309911343e-05, 'samples': 24857472, 'steps': 129465, 'loss/train': 1.0505410432815552} 08/31/2021 12:41:32 - INFO - __main__ - Step 129467: {'lr': 2.337473373266913e-05, 'samples': 24857664, 'steps': 129466, 'loss/train': 1.1323391199111938} 08/31/2021 12:41:34 - INFO - __main__ - Step 129468: {'lr': 2.337249325754079e-05, 'samples': 24857856, 'steps': 129467, 'loss/train': 1.3032310009002686} 08/31/2021 12:41:34 - INFO - __main__ - Step 129469: {'lr': 2.3370252884527265e-05, 'samples': 24858048, 'steps': 129468, 'loss/train': 0.6134136915206909} 08/31/2021 12:41:35 - INFO - __main__ - Step 129470: {'lr': 2.336801261362964e-05, 'samples': 24858240, 'steps': 129469, 'loss/train': 1.0020169019699097} 08/31/2021 12:41:35 - INFO - __main__ - Step 129471: {'lr': 2.3365772444848886e-05, 'samples': 24858432, 'steps': 129470, 'loss/train': 1.1701582670211792} 08/31/2021 12:41:35 - INFO - __main__ - Step 129472: {'lr': 2.336353237818603e-05, 'samples': 24858624, 'steps': 129471, 'loss/train': 1.231192708015442} 08/31/2021 12:41:36 - INFO - __main__ - Step 129473: {'lr': 2.3361292413642042e-05, 'samples': 24858816, 'steps': 129472, 'loss/train': 0.04981658607721329} 08/31/2021 12:41:37 - INFO - __main__ - Step 129474: {'lr': 2.335905255121798e-05, 'samples': 24859008, 'steps': 129473, 'loss/train': 1.3860722780227661} 08/31/2021 12:41:38 - INFO - __main__ - Step 129475: {'lr': 2.3356812790914866e-05, 'samples': 24859200, 'steps': 129474, 'loss/train': 1.3128321170806885} 08/31/2021 12:41:38 - INFO - __main__ - Step 129476: {'lr': 2.335457313273365e-05, 'samples': 24859392, 'steps': 129475, 'loss/train': 0.10730087012052536} 08/31/2021 12:41:38 - INFO - __main__ - Step 129477: {'lr': 2.335233357667535e-05, 'samples': 24859584, 'steps': 129476, 'loss/train': 1.2703180313110352} 08/31/2021 12:41:39 - INFO - __main__ - Step 129478: {'lr': 2.3350094122741e-05, 'samples': 24859776, 'steps': 129477, 'loss/train': 1.026807427406311} 08/31/2021 12:41:40 - INFO - __main__ - Step 129479: {'lr': 2.334785477093157e-05, 'samples': 24859968, 'steps': 129478, 'loss/train': 1.7621395587921143} 08/31/2021 12:41:41 - INFO - __main__ - Step 129480: {'lr': 2.3345615521248114e-05, 'samples': 24860160, 'steps': 129479, 'loss/train': 0.47925347089767456} 08/31/2021 12:41:41 - INFO - __main__ - Step 129481: {'lr': 2.334337637369166e-05, 'samples': 24860352, 'steps': 129480, 'loss/train': 0.8403249382972717} 08/31/2021 12:41:41 - INFO - __main__ - Step 129482: {'lr': 2.334113732826315e-05, 'samples': 24860544, 'steps': 129481, 'loss/train': 1.0235469341278076} 08/31/2021 12:41:42 - INFO - __main__ - Step 129483: {'lr': 2.3338898384963616e-05, 'samples': 24860736, 'steps': 129482, 'loss/train': 1.422820806503296} 08/31/2021 12:41:43 - INFO - __main__ - Step 129484: {'lr': 2.3336659543794103e-05, 'samples': 24860928, 'steps': 129483, 'loss/train': 1.2859878540039062} 08/31/2021 12:41:44 - INFO - __main__ - Step 129485: {'lr': 2.333442080475559e-05, 'samples': 24861120, 'steps': 129484, 'loss/train': 1.2153027057647705} 08/31/2021 12:41:44 - INFO - __main__ - Step 129486: {'lr': 2.333218216784913e-05, 'samples': 24861312, 'steps': 129485, 'loss/train': 1.3011554479599} 08/31/2021 12:41:45 - INFO - __main__ - Step 129487: {'lr': 2.332994363307564e-05, 'samples': 24861504, 'steps': 129486, 'loss/train': 1.268437385559082} 08/31/2021 12:41:45 - INFO - __main__ - Step 129488: {'lr': 2.332770520043617e-05, 'samples': 24861696, 'steps': 129487, 'loss/train': 0.507434606552124} 08/31/2021 12:41:47 - INFO - __main__ - Step 129489: {'lr': 2.3325466869931754e-05, 'samples': 24861888, 'steps': 129488, 'loss/train': 1.1032168865203857} 08/31/2021 12:41:47 - INFO - __main__ - Step 129490: {'lr': 2.332322864156339e-05, 'samples': 24862080, 'steps': 129489, 'loss/train': 0.9511846303939819} 08/31/2021 12:41:47 - INFO - __main__ - Step 129491: {'lr': 2.332099051533207e-05, 'samples': 24862272, 'steps': 129490, 'loss/train': 0.961800754070282} 08/31/2021 12:41:48 - INFO - __main__ - Step 129492: {'lr': 2.3318752491238828e-05, 'samples': 24862464, 'steps': 129491, 'loss/train': 1.2168552875518799} 08/31/2021 12:41:48 - INFO - __main__ - Step 129493: {'lr': 2.331651456928463e-05, 'samples': 24862656, 'steps': 129492, 'loss/train': 1.457838535308838} 08/31/2021 12:41:48 - INFO - __main__ - Step 129494: {'lr': 2.3314276749470536e-05, 'samples': 24862848, 'steps': 129493, 'loss/train': 0.22192084789276123} 08/31/2021 12:41:50 - INFO - __main__ - Step 129495: {'lr': 2.3312039031797515e-05, 'samples': 24863040, 'steps': 129494, 'loss/train': 1.2410593032836914} 08/31/2021 12:41:50 - INFO - __main__ - Step 129496: {'lr': 2.3309801416266625e-05, 'samples': 24863232, 'steps': 129495, 'loss/train': 1.597487449645996} 08/31/2021 12:41:51 - INFO - __main__ - Step 129497: {'lr': 2.330756390287886e-05, 'samples': 24863424, 'steps': 129496, 'loss/train': 1.173707127571106} 08/31/2021 12:41:51 - INFO - __main__ - Step 129498: {'lr': 2.3305326491635165e-05, 'samples': 24863616, 'steps': 129497, 'loss/train': 1.166792631149292} 08/31/2021 12:41:51 - INFO - __main__ - Step 129499: {'lr': 2.330308918253657e-05, 'samples': 24863808, 'steps': 129498, 'loss/train': 1.1324793100357056} 08/31/2021 12:41:53 - INFO - __main__ - Step 129500: {'lr': 2.3300851975584124e-05, 'samples': 24864000, 'steps': 129499, 'loss/train': 0.3405092656612396} 08/31/2021 12:41:54 - INFO - __main__ - Step 129501: {'lr': 2.3298614870778834e-05, 'samples': 24864192, 'steps': 129500, 'loss/train': 0.7963554263114929} 08/31/2021 12:41:54 - INFO - __main__ - Step 129502: {'lr': 2.3296377868121665e-05, 'samples': 24864384, 'steps': 129501, 'loss/train': 1.3062101602554321} 08/31/2021 12:41:54 - INFO - __main__ - Step 129503: {'lr': 2.3294140967613675e-05, 'samples': 24864576, 'steps': 129502, 'loss/train': 1.202423095703125} 08/31/2021 12:41:55 - INFO - __main__ - Step 129504: {'lr': 2.3291904169255835e-05, 'samples': 24864768, 'steps': 129503, 'loss/train': 0.4745238721370697} 08/31/2021 12:41:57 - INFO - __main__ - Step 129505: {'lr': 2.3289667473049142e-05, 'samples': 24864960, 'steps': 129504, 'loss/train': 0.051839932799339294} 08/31/2021 12:41:57 - INFO - __main__ - Step 129506: {'lr': 2.3287430878994653e-05, 'samples': 24865152, 'steps': 129505, 'loss/train': 1.2647939920425415} 08/31/2021 12:41:57 - INFO - __main__ - Step 129507: {'lr': 2.328519438709334e-05, 'samples': 24865344, 'steps': 129506, 'loss/train': 1.5000371932983398} 08/31/2021 12:41:58 - INFO - __main__ - Step 129508: {'lr': 2.3282957997346282e-05, 'samples': 24865536, 'steps': 129507, 'loss/train': 0.920199453830719} 08/31/2021 12:41:58 - INFO - __main__ - Step 129509: {'lr': 2.3280721709754344e-05, 'samples': 24865728, 'steps': 129508, 'loss/train': 0.7046656608581543} 08/31/2021 12:42:00 - INFO - __main__ - Step 129510: {'lr': 2.3278485524318632e-05, 'samples': 24865920, 'steps': 129509, 'loss/train': 1.3087046146392822} 08/31/2021 12:42:00 - INFO - __main__ - Step 129511: {'lr': 2.327624944104015e-05, 'samples': 24866112, 'steps': 129510, 'loss/train': 1.9431493282318115} 08/31/2021 12:42:01 - INFO - __main__ - Step 129512: {'lr': 2.327401345991989e-05, 'samples': 24866304, 'steps': 129511, 'loss/train': 0.0653441995382309} 08/31/2021 12:42:01 - INFO - __main__ - Step 129513: {'lr': 2.327177758095883e-05, 'samples': 24866496, 'steps': 129512, 'loss/train': 0.6766096353530884} 08/31/2021 12:42:01 - INFO - __main__ - Step 129514: {'lr': 2.326954180415805e-05, 'samples': 24866688, 'steps': 129513, 'loss/train': 1.0750138759613037} 08/31/2021 12:42:03 - INFO - __main__ - Step 129515: {'lr': 2.3267306129518496e-05, 'samples': 24866880, 'steps': 129514, 'loss/train': 0.6373239159584045} 08/31/2021 12:42:04 - INFO - __main__ - Step 129516: {'lr': 2.326507055704119e-05, 'samples': 24867072, 'steps': 129515, 'loss/train': 0.8863856196403503} 08/31/2021 12:42:04 - INFO - __main__ - Step 129517: {'lr': 2.3262835086727137e-05, 'samples': 24867264, 'steps': 129516, 'loss/train': 0.8120957016944885} 08/31/2021 12:42:04 - INFO - __main__ - Step 129518: {'lr': 2.3260599718577385e-05, 'samples': 24867456, 'steps': 129517, 'loss/train': 0.6389244198799133} 08/31/2021 12:42:05 - INFO - __main__ - Step 129519: {'lr': 2.325836445259291e-05, 'samples': 24867648, 'steps': 129518, 'loss/train': 1.2713422775268555} 08/31/2021 12:42:06 - INFO - __main__ - Step 129520: {'lr': 2.3256129288774713e-05, 'samples': 24867840, 'steps': 129519, 'loss/train': 0.11727359145879745} 08/31/2021 12:42:07 - INFO - __main__ - Step 129521: {'lr': 2.325389422712379e-05, 'samples': 24868032, 'steps': 129520, 'loss/train': 1.566212773323059} 08/31/2021 12:42:07 - INFO - __main__ - Step 129522: {'lr': 2.325165926764114e-05, 'samples': 24868224, 'steps': 129521, 'loss/train': 0.9377590417861938} 08/31/2021 12:42:08 - INFO - __main__ - Step 129523: {'lr': 2.324942441032782e-05, 'samples': 24868416, 'steps': 129522, 'loss/train': 1.4215161800384521} 08/31/2021 12:42:08 - INFO - __main__ - Step 129524: {'lr': 2.3247189655184796e-05, 'samples': 24868608, 'steps': 129523, 'loss/train': 1.0375020503997803} 08/31/2021 12:42:08 - INFO - __main__ - Step 129525: {'lr': 2.3244955002213103e-05, 'samples': 24868800, 'steps': 129524, 'loss/train': 0.9318720102310181} 08/31/2021 12:42:09 - INFO - __main__ - Step 129526: {'lr': 2.3242720451413736e-05, 'samples': 24868992, 'steps': 129525, 'loss/train': 0.9328993558883667} 08/31/2021 12:42:10 - INFO - __main__ - Step 129527: {'lr': 2.324048600278769e-05, 'samples': 24869184, 'steps': 129526, 'loss/train': 1.1419254541397095} 08/31/2021 12:42:11 - INFO - __main__ - Step 129528: {'lr': 2.3238251656335975e-05, 'samples': 24869376, 'steps': 129527, 'loss/train': 0.8782927393913269} 08/31/2021 12:42:11 - INFO - __main__ - Step 129529: {'lr': 2.3236017412059607e-05, 'samples': 24869568, 'steps': 129528, 'loss/train': 0.9757421612739563} 08/31/2021 12:42:12 - INFO - __main__ - Step 129530: {'lr': 2.323378326995962e-05, 'samples': 24869760, 'steps': 129529, 'loss/train': 0.937271237373352} 08/31/2021 12:42:12 - INFO - __main__ - Step 129531: {'lr': 2.3231549230036954e-05, 'samples': 24869952, 'steps': 129530, 'loss/train': 0.9421999454498291} 08/31/2021 12:42:13 - INFO - __main__ - Step 129532: {'lr': 2.322931529229272e-05, 'samples': 24870144, 'steps': 129531, 'loss/train': 0.45131129026412964} 08/31/2021 12:42:14 - INFO - __main__ - Step 129533: {'lr': 2.3227081456727807e-05, 'samples': 24870336, 'steps': 129532, 'loss/train': 1.1229599714279175} 08/31/2021 12:42:14 - INFO - __main__ - Step 129534: {'lr': 2.3224847723343267e-05, 'samples': 24870528, 'steps': 129533, 'loss/train': 1.2647383213043213} 08/31/2021 12:42:15 - INFO - __main__ - Step 129535: {'lr': 2.3222614092140104e-05, 'samples': 24870720, 'steps': 129534, 'loss/train': 0.9159778952598572} 08/31/2021 12:42:15 - INFO - __main__ - Step 129536: {'lr': 2.3220380563119342e-05, 'samples': 24870912, 'steps': 129535, 'loss/train': 1.3086906671524048} 08/31/2021 12:42:17 - INFO - __main__ - Step 129537: {'lr': 2.321814713628198e-05, 'samples': 24871104, 'steps': 129536, 'loss/train': 1.171301245689392} 08/31/2021 12:42:17 - INFO - __main__ - Step 129538: {'lr': 2.3215913811629018e-05, 'samples': 24871296, 'steps': 129537, 'loss/train': 1.0873398780822754} 08/31/2021 12:42:17 - INFO - __main__ - Step 129539: {'lr': 2.3213680589161457e-05, 'samples': 24871488, 'steps': 129538, 'loss/train': 1.3040121793746948} 08/31/2021 12:42:18 - INFO - __main__ - Step 129540: {'lr': 2.321144746888032e-05, 'samples': 24871680, 'steps': 129539, 'loss/train': 1.5526236295700073} 08/31/2021 12:42:18 - INFO - __main__ - Step 129541: {'lr': 2.3209214450786607e-05, 'samples': 24871872, 'steps': 129540, 'loss/train': 0.04224548116326332} 08/31/2021 12:42:18 - INFO - __main__ - Step 129542: {'lr': 2.320698153488132e-05, 'samples': 24872064, 'steps': 129541, 'loss/train': 1.0717487335205078} 08/31/2021 12:42:21 - INFO - __main__ - Step 129543: {'lr': 2.3204748721165457e-05, 'samples': 24872256, 'steps': 129542, 'loss/train': 0.9568458795547485} 08/31/2021 12:42:21 - INFO - __main__ - Step 129544: {'lr': 2.3202516009640045e-05, 'samples': 24872448, 'steps': 129543, 'loss/train': 0.19556471705436707} 08/31/2021 12:42:22 - INFO - __main__ - Step 129545: {'lr': 2.3200283400306137e-05, 'samples': 24872640, 'steps': 129544, 'loss/train': 0.18255272507667542} 08/31/2021 12:42:22 - INFO - __main__ - Step 129546: {'lr': 2.3198050893164625e-05, 'samples': 24872832, 'steps': 129545, 'loss/train': 0.8434755802154541} 08/31/2021 12:42:23 - INFO - __main__ - Step 129547: {'lr': 2.319581848821656e-05, 'samples': 24873024, 'steps': 129546, 'loss/train': 1.8607388734817505} 08/31/2021 12:42:23 - INFO - __main__ - Step 129548: {'lr': 2.3193586185462966e-05, 'samples': 24873216, 'steps': 129547, 'loss/train': 0.5031372904777527} 08/31/2021 12:42:24 - INFO - __main__ - Step 129549: {'lr': 2.319135398490485e-05, 'samples': 24873408, 'steps': 129548, 'loss/train': 1.1335012912750244} 08/31/2021 12:42:25 - INFO - __main__ - Step 129550: {'lr': 2.3189121886543208e-05, 'samples': 24873600, 'steps': 129549, 'loss/train': 0.772670328617096} 08/31/2021 12:42:25 - INFO - __main__ - Step 129551: {'lr': 2.3186889890379065e-05, 'samples': 24873792, 'steps': 129550, 'loss/train': 1.1113146543502808} 08/31/2021 12:42:26 - INFO - __main__ - Step 129552: {'lr': 2.3184657996413395e-05, 'samples': 24873984, 'steps': 129551, 'loss/train': 0.7806320786476135} 08/31/2021 12:42:26 - INFO - __main__ - Step 129553: {'lr': 2.3182426204647193e-05, 'samples': 24874176, 'steps': 129552, 'loss/train': 0.4444372355937958} 08/31/2021 12:42:27 - INFO - __main__ - Step 129554: {'lr': 2.318019451508152e-05, 'samples': 24874368, 'steps': 129553, 'loss/train': 0.3789837062358856} 08/31/2021 12:42:28 - INFO - __main__ - Step 129555: {'lr': 2.3177962927717345e-05, 'samples': 24874560, 'steps': 129554, 'loss/train': 1.3267152309417725} 08/31/2021 12:42:28 - INFO - __main__ - Step 129556: {'lr': 2.3175731442555664e-05, 'samples': 24874752, 'steps': 129555, 'loss/train': 1.377309799194336} 08/31/2021 12:42:29 - INFO - __main__ - Step 129557: {'lr': 2.3173500059597507e-05, 'samples': 24874944, 'steps': 129556, 'loss/train': 0.893856406211853} 08/31/2021 12:42:29 - INFO - __main__ - Step 129558: {'lr': 2.3171268778843873e-05, 'samples': 24875136, 'steps': 129557, 'loss/train': 1.1684547662734985} 08/31/2021 12:42:31 - INFO - __main__ - Step 129559: {'lr': 2.3169037600295817e-05, 'samples': 24875328, 'steps': 129558, 'loss/train': 0.8776229619979858} 08/31/2021 12:42:32 - INFO - __main__ - Step 129560: {'lr': 2.3166806523954252e-05, 'samples': 24875520, 'steps': 129559, 'loss/train': 0.987561821937561} 08/31/2021 12:42:32 - INFO - __main__ - Step 129561: {'lr': 2.316457554982021e-05, 'samples': 24875712, 'steps': 129560, 'loss/train': 1.2544350624084473} 08/31/2021 12:42:32 - INFO - __main__ - Step 129562: {'lr': 2.3162344677894715e-05, 'samples': 24875904, 'steps': 129561, 'loss/train': 0.5186513662338257} 08/31/2021 12:42:33 - INFO - __main__ - Step 129563: {'lr': 2.3160113908178766e-05, 'samples': 24876096, 'steps': 129562, 'loss/train': 1.0001225471496582} 08/31/2021 12:42:34 - INFO - __main__ - Step 129564: {'lr': 2.3157883240673388e-05, 'samples': 24876288, 'steps': 129563, 'loss/train': 0.47394201159477234} 08/31/2021 12:42:34 - INFO - __main__ - Step 129565: {'lr': 2.315565267537953e-05, 'samples': 24876480, 'steps': 129564, 'loss/train': 0.621992826461792} 08/31/2021 12:42:35 - INFO - __main__ - Step 129566: {'lr': 2.315342221229827e-05, 'samples': 24876672, 'steps': 129565, 'loss/train': 2.031883478164673} 08/31/2021 12:42:35 - INFO - __main__ - Step 129567: {'lr': 2.3151191851430554e-05, 'samples': 24876864, 'steps': 129566, 'loss/train': 0.8969055414199829} 08/31/2021 12:42:36 - INFO - __main__ - Step 129568: {'lr': 2.3148961592777405e-05, 'samples': 24877056, 'steps': 129567, 'loss/train': 1.1429567337036133} 08/31/2021 12:42:37 - INFO - __main__ - Step 129569: {'lr': 2.3146731436339856e-05, 'samples': 24877248, 'steps': 129568, 'loss/train': 1.2347439527511597} 08/31/2021 12:42:38 - INFO - __main__ - Step 129570: {'lr': 2.3144501382118878e-05, 'samples': 24877440, 'steps': 129569, 'loss/train': 1.321021556854248} 08/31/2021 12:42:38 - INFO - __main__ - Step 129571: {'lr': 2.314227143011549e-05, 'samples': 24877632, 'steps': 129570, 'loss/train': 0.08208773285150528} 08/31/2021 12:42:38 - INFO - __main__ - Step 129572: {'lr': 2.314004158033073e-05, 'samples': 24877824, 'steps': 129571, 'loss/train': 1.2184077501296997} 08/31/2021 12:42:39 - INFO - __main__ - Step 129573: {'lr': 2.3137811832765532e-05, 'samples': 24878016, 'steps': 129572, 'loss/train': 1.2068065404891968} 08/31/2021 12:42:39 - INFO - __main__ - Step 129574: {'lr': 2.3135582187420927e-05, 'samples': 24878208, 'steps': 129573, 'loss/train': 1.0789129734039307} 08/31/2021 12:42:41 - INFO - __main__ - Step 129575: {'lr': 2.3133352644297946e-05, 'samples': 24878400, 'steps': 129574, 'loss/train': 1.250240445137024} 08/31/2021 12:42:41 - INFO - __main__ - Step 129576: {'lr': 2.3131123203397553e-05, 'samples': 24878592, 'steps': 129575, 'loss/train': 0.9271091222763062} 08/31/2021 12:42:42 - INFO - __main__ - Step 129577: {'lr': 2.312889386472078e-05, 'samples': 24878784, 'steps': 129576, 'loss/train': 0.948242723941803} 08/31/2021 12:42:42 - INFO - __main__ - Step 129578: {'lr': 2.3126664628268652e-05, 'samples': 24878976, 'steps': 129577, 'loss/train': 1.0497432947158813} 08/31/2021 12:42:42 - INFO - __main__ - Step 129579: {'lr': 2.312443549404211e-05, 'samples': 24879168, 'steps': 129578, 'loss/train': 0.9307330250740051} 08/31/2021 12:42:44 - INFO - __main__ - Step 129580: {'lr': 2.3122206462042216e-05, 'samples': 24879360, 'steps': 129579, 'loss/train': 1.1549605131149292} 08/31/2021 12:42:44 - INFO - __main__ - Step 129581: {'lr': 2.3119977532269964e-05, 'samples': 24879552, 'steps': 129580, 'loss/train': 0.42888373136520386} 08/31/2021 12:42:45 - INFO - __main__ - Step 129582: {'lr': 2.311774870472633e-05, 'samples': 24879744, 'steps': 129581, 'loss/train': 1.1316643953323364} 08/31/2021 12:42:45 - INFO - __main__ - Step 129583: {'lr': 2.311551997941236e-05, 'samples': 24879936, 'steps': 129582, 'loss/train': 0.6846608519554138} 08/31/2021 12:42:45 - INFO - __main__ - Step 129584: {'lr': 2.3113291356329004e-05, 'samples': 24880128, 'steps': 129583, 'loss/train': 1.4526833295822144} 08/31/2021 12:42:47 - INFO - __main__ - Step 129585: {'lr': 2.3111062835477313e-05, 'samples': 24880320, 'steps': 129584, 'loss/train': 1.0366003513336182} 08/31/2021 12:42:47 - INFO - __main__ - Step 129586: {'lr': 2.310883441685832e-05, 'samples': 24880512, 'steps': 129585, 'loss/train': 1.0613205432891846} 08/31/2021 12:42:47 - INFO - __main__ - Step 129587: {'lr': 2.3106606100472937e-05, 'samples': 24880704, 'steps': 129586, 'loss/train': 1.3732554912567139} 08/31/2021 12:42:48 - INFO - __main__ - Step 129588: {'lr': 2.3104377886322248e-05, 'samples': 24880896, 'steps': 129587, 'loss/train': 1.3380922079086304} 08/31/2021 12:42:48 - INFO - __main__ - Step 129589: {'lr': 2.3102149774407195e-05, 'samples': 24881088, 'steps': 129588, 'loss/train': 0.7269207835197449} 08/31/2021 12:42:50 - INFO - __main__ - Step 129590: {'lr': 2.3099921764728805e-05, 'samples': 24881280, 'steps': 129589, 'loss/train': 1.015445351600647} 08/31/2021 12:42:50 - INFO - __main__ - Step 129591: {'lr': 2.3097693857288106e-05, 'samples': 24881472, 'steps': 129590, 'loss/train': 1.0554745197296143} 08/31/2021 12:42:51 - INFO - __main__ - Step 129592: {'lr': 2.3095466052086068e-05, 'samples': 24881664, 'steps': 129591, 'loss/train': 0.9512748122215271} 08/31/2021 12:42:51 - INFO - __main__ - Step 129593: {'lr': 2.309323834912372e-05, 'samples': 24881856, 'steps': 129592, 'loss/train': 0.8309445381164551} 08/31/2021 12:42:51 - INFO - __main__ - Step 129594: {'lr': 2.309101074840206e-05, 'samples': 24882048, 'steps': 129593, 'loss/train': 1.4577088356018066} 08/31/2021 12:42:53 - INFO - __main__ - Step 129595: {'lr': 2.3088783249922084e-05, 'samples': 24882240, 'steps': 129594, 'loss/train': 0.6007694005966187} 08/31/2021 12:42:54 - INFO - __main__ - Step 129596: {'lr': 2.3086555853684826e-05, 'samples': 24882432, 'steps': 129595, 'loss/train': 1.344856858253479} 08/31/2021 12:42:54 - INFO - __main__ - Step 129597: {'lr': 2.3084328559691225e-05, 'samples': 24882624, 'steps': 129596, 'loss/train': 1.289972186088562} 08/31/2021 12:42:54 - INFO - __main__ - Step 129598: {'lr': 2.3082101367942364e-05, 'samples': 24882816, 'steps': 129597, 'loss/train': 1.4744794368743896} 08/31/2021 12:42:55 - INFO - __main__ - Step 129599: {'lr': 2.3079874278439216e-05, 'samples': 24883008, 'steps': 129598, 'loss/train': 1.2702642679214478} 08/31/2021 12:42:55 - INFO - __main__ - Step 129600: {'lr': 2.307764729118275e-05, 'samples': 24883200, 'steps': 129599, 'loss/train': 1.0486063957214355} 08/31/2021 12:42:56 - INFO - __main__ - Step 129601: {'lr': 2.3075420406173997e-05, 'samples': 24883392, 'steps': 129600, 'loss/train': 1.2000499963760376} 08/31/2021 12:42:57 - INFO - __main__ - Step 129602: {'lr': 2.307319362341395e-05, 'samples': 24883584, 'steps': 129601, 'loss/train': 1.5326917171478271} 08/31/2021 12:42:57 - INFO - __main__ - Step 129603: {'lr': 2.3070966942903616e-05, 'samples': 24883776, 'steps': 129602, 'loss/train': 0.1280316412448883} 08/31/2021 12:42:58 - INFO - __main__ - Step 129604: {'lr': 2.3068740364644015e-05, 'samples': 24883968, 'steps': 129603, 'loss/train': 0.11402454972267151} 08/31/2021 12:42:58 - INFO - __main__ - Step 129605: {'lr': 2.306651388863612e-05, 'samples': 24884160, 'steps': 129604, 'loss/train': 1.3475444316864014} 08/31/2021 12:42:59 - INFO - __main__ - Step 129606: {'lr': 2.306428751488096e-05, 'samples': 24884352, 'steps': 129605, 'loss/train': 1.4969322681427002} 08/31/2021 12:43:00 - INFO - __main__ - Step 129607: {'lr': 2.3062061243379533e-05, 'samples': 24884544, 'steps': 129606, 'loss/train': 1.2163230180740356} 08/31/2021 12:43:00 - INFO - __main__ - Step 129608: {'lr': 2.305983507413284e-05, 'samples': 24884736, 'steps': 129607, 'loss/train': 1.2689473628997803} 08/31/2021 12:43:01 - INFO - __main__ - Step 129609: {'lr': 2.305760900714188e-05, 'samples': 24884928, 'steps': 129608, 'loss/train': 0.5687886476516724} 08/31/2021 12:43:01 - INFO - __main__ - Step 129610: {'lr': 2.3055383042407673e-05, 'samples': 24885120, 'steps': 129609, 'loss/train': 0.5632338523864746} 08/31/2021 12:43:02 - INFO - __main__ - Step 129611: {'lr': 2.30531571799312e-05, 'samples': 24885312, 'steps': 129610, 'loss/train': 0.6952797174453735} 08/31/2021 12:43:03 - INFO - __main__ - Step 129612: {'lr': 2.3050931419713456e-05, 'samples': 24885504, 'steps': 129611, 'loss/train': 0.8310686349868774} 08/31/2021 12:43:03 - INFO - __main__ - Step 129613: {'lr': 2.3048705761755522e-05, 'samples': 24885696, 'steps': 129612, 'loss/train': 1.2982388734817505} 08/31/2021 12:43:04 - INFO - __main__ - Step 129614: {'lr': 2.304648020605829e-05, 'samples': 24885888, 'steps': 129613, 'loss/train': 0.5227447748184204} 08/31/2021 12:43:04 - INFO - __main__ - Step 129615: {'lr': 2.304425475262281e-05, 'samples': 24886080, 'steps': 129614, 'loss/train': 1.2453093528747559} 08/31/2021 12:43:06 - INFO - __main__ - Step 129616: {'lr': 2.3042029401450086e-05, 'samples': 24886272, 'steps': 129615, 'loss/train': 1.1207536458969116} 08/31/2021 12:43:07 - INFO - __main__ - Step 129617: {'lr': 2.3039804152541144e-05, 'samples': 24886464, 'steps': 129616, 'loss/train': 1.6875941753387451} 08/31/2021 12:43:07 - INFO - __main__ - Step 129618: {'lr': 2.3037579005896925e-05, 'samples': 24886656, 'steps': 129617, 'loss/train': 1.166262149810791} 08/31/2021 12:43:08 - INFO - __main__ - Step 129619: {'lr': 2.3035353961518484e-05, 'samples': 24886848, 'steps': 129618, 'loss/train': 0.7102818489074707} 08/31/2021 12:43:08 - INFO - __main__ - Step 129620: {'lr': 2.3033129019406823e-05, 'samples': 24887040, 'steps': 129619, 'loss/train': 0.09513915330171585} 08/31/2021 12:43:08 - INFO - __main__ - Step 129621: {'lr': 2.303090417956294e-05, 'samples': 24887232, 'steps': 129620, 'loss/train': 1.2568167448043823} 08/31/2021 12:43:09 - INFO - __main__ - Step 129622: {'lr': 2.3028679441987804e-05, 'samples': 24887424, 'steps': 129621, 'loss/train': 0.014389317482709885} 08/31/2021 12:43:10 - INFO - __main__ - Step 129623: {'lr': 2.3026454806682444e-05, 'samples': 24887616, 'steps': 129622, 'loss/train': 1.0422931909561157} 08/31/2021 12:43:11 - INFO - __main__ - Step 129624: {'lr': 2.302423027364789e-05, 'samples': 24887808, 'steps': 129623, 'loss/train': 0.4060728847980499} 08/31/2021 12:43:11 - INFO - __main__ - Step 129625: {'lr': 2.302200584288508e-05, 'samples': 24888000, 'steps': 129624, 'loss/train': 1.4907140731811523} 08/31/2021 12:43:11 - INFO - __main__ - Step 129626: {'lr': 2.3019781514395127e-05, 'samples': 24888192, 'steps': 129625, 'loss/train': 0.5727269649505615} 08/31/2021 12:43:12 - INFO - __main__ - Step 129627: {'lr': 2.301755728817889e-05, 'samples': 24888384, 'steps': 129626, 'loss/train': 0.7838255167007446} 08/31/2021 12:43:13 - INFO - __main__ - Step 129628: {'lr': 2.3015333164237456e-05, 'samples': 24888576, 'steps': 129627, 'loss/train': 0.7291986346244812} 08/31/2021 12:43:14 - INFO - __main__ - Step 129629: {'lr': 2.3013109142571792e-05, 'samples': 24888768, 'steps': 129628, 'loss/train': 0.7026932835578918} 08/31/2021 12:43:14 - INFO - __main__ - Step 129630: {'lr': 2.3010885223182925e-05, 'samples': 24888960, 'steps': 129629, 'loss/train': 1.5523678064346313} 08/31/2021 12:43:14 - INFO - __main__ - Step 129631: {'lr': 2.3008661406071856e-05, 'samples': 24889152, 'steps': 129630, 'loss/train': 0.6572027802467346} 08/31/2021 12:43:15 - INFO - __main__ - Step 129632: {'lr': 2.3006437691239585e-05, 'samples': 24889344, 'steps': 129631, 'loss/train': 0.22238773107528687} 08/31/2021 12:43:16 - INFO - __main__ - Step 129633: {'lr': 2.300421407868711e-05, 'samples': 24889536, 'steps': 129632, 'loss/train': 1.2563762664794922} 08/31/2021 12:43:17 - INFO - __main__ - Step 129634: {'lr': 2.3001990568415425e-05, 'samples': 24889728, 'steps': 129633, 'loss/train': 1.4323139190673828} 08/31/2021 12:43:17 - INFO - __main__ - Step 129635: {'lr': 2.299976716042554e-05, 'samples': 24889920, 'steps': 129634, 'loss/train': 1.1964287757873535} 08/31/2021 12:43:17 - INFO - __main__ - Step 129636: {'lr': 2.2997543854718472e-05, 'samples': 24890112, 'steps': 129635, 'loss/train': 0.7370455861091614} 08/31/2021 12:43:18 - INFO - __main__ - Step 129637: {'lr': 2.299532065129517e-05, 'samples': 24890304, 'steps': 129636, 'loss/train': 0.039228782057762146} 08/31/2021 12:43:19 - INFO - __main__ - Step 129638: {'lr': 2.2993097550156715e-05, 'samples': 24890496, 'steps': 129637, 'loss/train': 1.5302317142486572} 08/31/2021 12:43:20 - INFO - __main__ - Step 129639: {'lr': 2.299087455130411e-05, 'samples': 24890688, 'steps': 129638, 'loss/train': 1.296187162399292} 08/31/2021 12:43:20 - INFO - __main__ - Step 129640: {'lr': 2.2988651654738235e-05, 'samples': 24890880, 'steps': 129639, 'loss/train': 1.6071165800094604} 08/31/2021 12:43:20 - INFO - __main__ - Step 129641: {'lr': 2.2986428860460206e-05, 'samples': 24891072, 'steps': 129640, 'loss/train': 1.1519113779067993} 08/31/2021 12:43:21 - INFO - __main__ - Step 129642: {'lr': 2.2984206168470966e-05, 'samples': 24891264, 'steps': 129641, 'loss/train': 0.8659083247184753} 08/31/2021 12:43:22 - INFO - __main__ - Step 129643: {'lr': 2.2981983578771543e-05, 'samples': 24891456, 'steps': 129642, 'loss/train': 1.5419050455093384} 08/31/2021 12:43:23 - INFO - __main__ - Step 129644: {'lr': 2.2979761091362932e-05, 'samples': 24891648, 'steps': 129643, 'loss/train': 1.1885900497436523} 08/31/2021 12:43:23 - INFO - __main__ - Step 129645: {'lr': 2.2977538706246163e-05, 'samples': 24891840, 'steps': 129644, 'loss/train': 0.7203637361526489} 08/31/2021 12:43:23 - INFO - __main__ - Step 129646: {'lr': 2.2975316423422182e-05, 'samples': 24892032, 'steps': 129645, 'loss/train': 1.5229054689407349} 08/31/2021 12:43:24 - INFO - __main__ - Step 129647: {'lr': 2.297309424289204e-05, 'samples': 24892224, 'steps': 129646, 'loss/train': 0.5026252269744873} 08/31/2021 12:43:24 - INFO - __main__ - Step 129648: {'lr': 2.2970872164656707e-05, 'samples': 24892416, 'steps': 129647, 'loss/train': 1.8152371644973755} 08/31/2021 12:43:25 - INFO - __main__ - Step 129649: {'lr': 2.2968650188717215e-05, 'samples': 24892608, 'steps': 129648, 'loss/train': 0.937084436416626} 08/31/2021 12:43:26 - INFO - __main__ - Step 129650: {'lr': 2.2966428315074532e-05, 'samples': 24892800, 'steps': 129649, 'loss/train': 1.7277911901474} 08/31/2021 12:43:26 - INFO - __main__ - Step 129651: {'lr': 2.296420654372966e-05, 'samples': 24892992, 'steps': 129650, 'loss/train': 1.1030771732330322} 08/31/2021 12:43:26 - INFO - __main__ - Step 129652: {'lr': 2.2961984874683624e-05, 'samples': 24893184, 'steps': 129651, 'loss/train': 0.6978541612625122} 08/31/2021 12:43:27 - INFO - __main__ - Step 129653: {'lr': 2.2959763307937475e-05, 'samples': 24893376, 'steps': 129652, 'loss/train': 1.1173279285430908} 08/31/2021 12:43:28 - INFO - __main__ - Step 129654: {'lr': 2.295754184349208e-05, 'samples': 24893568, 'steps': 129653, 'loss/train': 1.1140638589859009} 08/31/2021 12:43:29 - INFO - __main__ - Step 129655: {'lr': 2.2955320481348548e-05, 'samples': 24893760, 'steps': 129654, 'loss/train': 1.278401255607605} 08/31/2021 12:43:29 - INFO - __main__ - Step 129656: {'lr': 2.2953099221507816e-05, 'samples': 24893952, 'steps': 129655, 'loss/train': 0.15683911740779877} 08/31/2021 12:43:29 - INFO - __main__ - Step 129657: {'lr': 2.295087806397092e-05, 'samples': 24894144, 'steps': 129656, 'loss/train': 0.32542550563812256} 08/31/2021 12:43:30 - INFO - __main__ - Step 129658: {'lr': 2.2948657008738854e-05, 'samples': 24894336, 'steps': 129657, 'loss/train': 0.8405487537384033} 08/31/2021 12:43:31 - INFO - __main__ - Step 129659: {'lr': 2.294643605581262e-05, 'samples': 24894528, 'steps': 129658, 'loss/train': 1.0648043155670166} 08/31/2021 12:43:32 - INFO - __main__ - Step 129660: {'lr': 2.2944215205193214e-05, 'samples': 24894720, 'steps': 129659, 'loss/train': 0.9295650124549866} 08/31/2021 12:43:32 - INFO - __main__ - Step 129661: {'lr': 2.2941994456881666e-05, 'samples': 24894912, 'steps': 129660, 'loss/train': 0.972571611404419} 08/31/2021 12:43:32 - INFO - __main__ - Step 129662: {'lr': 2.2939773810878918e-05, 'samples': 24895104, 'steps': 129661, 'loss/train': 1.308258056640625} 08/31/2021 12:43:33 - INFO - __main__ - Step 129663: {'lr': 2.2937553267186023e-05, 'samples': 24895296, 'steps': 129662, 'loss/train': 1.210972785949707} 08/31/2021 12:43:35 - INFO - __main__ - Step 129664: {'lr': 2.2935332825803955e-05, 'samples': 24895488, 'steps': 129663, 'loss/train': 0.5816935896873474} 08/31/2021 12:43:35 - INFO - __main__ - Step 129665: {'lr': 2.2933112486733716e-05, 'samples': 24895680, 'steps': 129664, 'loss/train': 1.0539155006408691} 08/31/2021 12:43:35 - INFO - __main__ - Step 129666: {'lr': 2.2930892249976383e-05, 'samples': 24895872, 'steps': 129665, 'loss/train': 0.2776884138584137} 08/31/2021 12:43:36 - INFO - __main__ - Step 129667: {'lr': 2.2928672115532817e-05, 'samples': 24896064, 'steps': 129666, 'loss/train': 1.1940611600875854} 08/31/2021 12:43:36 - INFO - __main__ - Step 129668: {'lr': 2.2926452083404102e-05, 'samples': 24896256, 'steps': 129667, 'loss/train': 1.4896066188812256} 08/31/2021 12:43:38 - INFO - __main__ - Step 129669: {'lr': 2.292423215359121e-05, 'samples': 24896448, 'steps': 129668, 'loss/train': 0.9141209125518799} 08/31/2021 12:43:39 - INFO - __main__ - Step 129670: {'lr': 2.292201232609517e-05, 'samples': 24896640, 'steps': 129669, 'loss/train': 1.5130192041397095} 08/31/2021 12:43:39 - INFO - __main__ - Step 129671: {'lr': 2.291979260091695e-05, 'samples': 24896832, 'steps': 129670, 'loss/train': 0.044288791716098785} 08/31/2021 12:43:39 - INFO - __main__ - Step 129672: {'lr': 2.2917572978057576e-05, 'samples': 24897024, 'steps': 129671, 'loss/train': 1.0828794240951538} 08/31/2021 12:43:40 - INFO - __main__ - Step 129673: {'lr': 2.2915353457518052e-05, 'samples': 24897216, 'steps': 129672, 'loss/train': 1.5713353157043457} 08/31/2021 12:43:41 - INFO - __main__ - Step 129674: {'lr': 2.291313403929937e-05, 'samples': 24897408, 'steps': 129673, 'loss/train': 0.8173502683639526} 08/31/2021 12:43:42 - INFO - __main__ - Step 129675: {'lr': 2.2910914723402508e-05, 'samples': 24897600, 'steps': 129674, 'loss/train': 1.1460683345794678} 08/31/2021 12:43:42 - INFO - __main__ - Step 129676: {'lr': 2.2908695509828463e-05, 'samples': 24897792, 'steps': 129675, 'loss/train': 0.5445994734764099} 08/31/2021 12:43:42 - INFO - __main__ - Step 129677: {'lr': 2.290647639857829e-05, 'samples': 24897984, 'steps': 129676, 'loss/train': 0.8210194110870361} 08/31/2021 12:43:43 - INFO - __main__ - Step 129678: {'lr': 2.2904257389652933e-05, 'samples': 24898176, 'steps': 129677, 'loss/train': 1.0662095546722412} 08/31/2021 12:43:44 - INFO - __main__ - Step 129679: {'lr': 2.2902038483053443e-05, 'samples': 24898368, 'steps': 129678, 'loss/train': 1.1838511228561401} 08/31/2021 12:43:45 - INFO - __main__ - Step 129680: {'lr': 2.28998196787808e-05, 'samples': 24898560, 'steps': 129679, 'loss/train': 1.1536059379577637} 08/31/2021 12:43:45 - INFO - __main__ - Step 129681: {'lr': 2.2897600976835965e-05, 'samples': 24898752, 'steps': 129680, 'loss/train': 1.3514899015426636} 08/31/2021 12:43:45 - INFO - __main__ - Step 129682: {'lr': 2.289538237721997e-05, 'samples': 24898944, 'steps': 129681, 'loss/train': 1.3087420463562012} 08/31/2021 12:43:46 - INFO - __main__ - Step 129683: {'lr': 2.2893163879933816e-05, 'samples': 24899136, 'steps': 129682, 'loss/train': 1.906488060951233} 08/31/2021 12:43:47 - INFO - __main__ - Step 129684: {'lr': 2.289094548497847e-05, 'samples': 24899328, 'steps': 129683, 'loss/train': 0.9279462099075317} 08/31/2021 12:43:48 - INFO - __main__ - Step 129685: {'lr': 2.2888727192354993e-05, 'samples': 24899520, 'steps': 129684, 'loss/train': 0.9273397922515869} 08/31/2021 12:43:48 - INFO - __main__ - Step 129686: {'lr': 2.2886509002064348e-05, 'samples': 24899712, 'steps': 129685, 'loss/train': 0.5880603194236755} 08/31/2021 12:43:48 - INFO - __main__ - Step 129687: {'lr': 2.2884290914107514e-05, 'samples': 24899904, 'steps': 129686, 'loss/train': 0.9715700149536133} 08/31/2021 12:43:49 - INFO - __main__ - Step 129688: {'lr': 2.2882072928485515e-05, 'samples': 24900096, 'steps': 129687, 'loss/train': 1.3883144855499268} 08/31/2021 12:43:50 - INFO - __main__ - Step 129689: {'lr': 2.2879855045199377e-05, 'samples': 24900288, 'steps': 129688, 'loss/train': 1.1937239170074463} 08/31/2021 12:43:51 - INFO - __main__ - Step 129690: {'lr': 2.2877637264250045e-05, 'samples': 24900480, 'steps': 129689, 'loss/train': 0.7291993498802185} 08/31/2021 12:43:51 - INFO - __main__ - Step 129691: {'lr': 2.2875419585638546e-05, 'samples': 24900672, 'steps': 129690, 'loss/train': 1.114617109298706} 08/31/2021 12:43:52 - INFO - __main__ - Step 129692: {'lr': 2.2873202009365906e-05, 'samples': 24900864, 'steps': 129691, 'loss/train': 0.3881365656852722} 08/31/2021 12:43:52 - INFO - __main__ - Step 129693: {'lr': 2.2870984535433126e-05, 'samples': 24901056, 'steps': 129692, 'loss/train': 1.2116557359695435} 08/31/2021 12:43:53 - INFO - __main__ - Step 129694: {'lr': 2.286876716384112e-05, 'samples': 24901248, 'steps': 129693, 'loss/train': 0.7891581058502197} 08/31/2021 12:43:54 - INFO - __main__ - Step 129695: {'lr': 2.2866549894590943e-05, 'samples': 24901440, 'steps': 129694, 'loss/train': 0.9162992835044861} 08/31/2021 12:43:54 - INFO - __main__ - Step 129696: {'lr': 2.2864332727683594e-05, 'samples': 24901632, 'steps': 129695, 'loss/train': 1.2731560468673706} 08/31/2021 12:43:55 - INFO - __main__ - Step 129697: {'lr': 2.2862115663120075e-05, 'samples': 24901824, 'steps': 129696, 'loss/train': 1.4187182188034058} 08/31/2021 12:43:55 - INFO - __main__ - Step 129698: {'lr': 2.285989870090141e-05, 'samples': 24902016, 'steps': 129697, 'loss/train': 0.9744827151298523} 08/31/2021 12:43:56 - INFO - __main__ - Step 129699: {'lr': 2.2857681841028545e-05, 'samples': 24902208, 'steps': 129698, 'loss/train': 0.3116452097892761} 08/31/2021 12:43:57 - INFO - __main__ - Step 129700: {'lr': 2.2855465083502503e-05, 'samples': 24902400, 'steps': 129699, 'loss/train': 0.8963713049888611} 08/31/2021 12:43:57 - INFO - __main__ - Step 129701: {'lr': 2.2853248428324258e-05, 'samples': 24902592, 'steps': 129700, 'loss/train': 2.7407240867614746} 08/31/2021 12:43:58 - INFO - __main__ - Step 129702: {'lr': 2.2851031875494867e-05, 'samples': 24902784, 'steps': 129701, 'loss/train': 1.3236417770385742} 08/31/2021 12:43:58 - INFO - __main__ - Step 129703: {'lr': 2.2848815425015297e-05, 'samples': 24902976, 'steps': 129702, 'loss/train': 0.6328637003898621} 08/31/2021 12:43:58 - INFO - __main__ - Step 129704: {'lr': 2.284659907688655e-05, 'samples': 24903168, 'steps': 129703, 'loss/train': 1.1398158073425293} 08/31/2021 12:44:00 - INFO - __main__ - Step 129705: {'lr': 2.2844382831109594e-05, 'samples': 24903360, 'steps': 129704, 'loss/train': 0.9000804424285889} 08/31/2021 12:44:00 - INFO - __main__ - Step 129706: {'lr': 2.284216668768546e-05, 'samples': 24903552, 'steps': 129705, 'loss/train': 1.0617091655731201} 08/31/2021 12:44:01 - INFO - __main__ - Step 129707: {'lr': 2.2839950646615206e-05, 'samples': 24903744, 'steps': 129706, 'loss/train': 0.6432323455810547} 08/31/2021 12:44:01 - INFO - __main__ - Step 129708: {'lr': 2.283773470789971e-05, 'samples': 24903936, 'steps': 129707, 'loss/train': 0.7556250691413879} 08/31/2021 12:44:01 - INFO - __main__ - Step 129709: {'lr': 2.2835518871540007e-05, 'samples': 24904128, 'steps': 129708, 'loss/train': 0.5325307846069336} 08/31/2021 12:44:03 - INFO - __main__ - Step 129710: {'lr': 2.283330313753712e-05, 'samples': 24904320, 'steps': 129709, 'loss/train': 1.0127370357513428} 08/31/2021 12:44:04 - INFO - __main__ - Step 129711: {'lr': 2.283108750589205e-05, 'samples': 24904512, 'steps': 129710, 'loss/train': 1.4991687536239624} 08/31/2021 12:44:04 - INFO - __main__ - Step 129712: {'lr': 2.2828871976605798e-05, 'samples': 24904704, 'steps': 129711, 'loss/train': 1.5965099334716797} 08/31/2021 12:44:05 - INFO - __main__ - Step 129713: {'lr': 2.282665654967933e-05, 'samples': 24904896, 'steps': 129712, 'loss/train': 1.2551006078720093} 08/31/2021 12:44:05 - INFO - __main__ - Step 129714: {'lr': 2.282444122511368e-05, 'samples': 24905088, 'steps': 129713, 'loss/train': 1.5436105728149414} 08/31/2021 12:44:05 - INFO - __main__ - Step 129715: {'lr': 2.282222600290984e-05, 'samples': 24905280, 'steps': 129714, 'loss/train': 1.7489477396011353} 08/31/2021 12:44:07 - INFO - __main__ - Step 129716: {'lr': 2.2820010883068787e-05, 'samples': 24905472, 'steps': 129715, 'loss/train': 0.984527587890625} 08/31/2021 12:44:07 - INFO - __main__ - Step 129717: {'lr': 2.2817795865591517e-05, 'samples': 24905664, 'steps': 129716, 'loss/train': 1.1620776653289795} 08/31/2021 12:44:08 - INFO - __main__ - Step 129718: {'lr': 2.281558095047906e-05, 'samples': 24905856, 'steps': 129717, 'loss/train': 1.1141494512557983} 08/31/2021 12:44:08 - INFO - __main__ - Step 129719: {'lr': 2.2813366137732383e-05, 'samples': 24906048, 'steps': 129718, 'loss/train': 1.3644171953201294} 08/31/2021 12:44:08 - INFO - __main__ - Step 129720: {'lr': 2.2811151427352573e-05, 'samples': 24906240, 'steps': 129719, 'loss/train': 1.237324595451355} 08/31/2021 12:44:10 - INFO - __main__ - Step 129721: {'lr': 2.2808936819340458e-05, 'samples': 24906432, 'steps': 129720, 'loss/train': 0.183201864361763} 08/31/2021 12:44:11 - INFO - __main__ - Step 129722: {'lr': 2.280672231369718e-05, 'samples': 24906624, 'steps': 129721, 'loss/train': 1.003313660621643} 08/31/2021 12:44:11 - INFO - __main__ - Step 129723: {'lr': 2.2804507910423654e-05, 'samples': 24906816, 'steps': 129722, 'loss/train': 1.128064513206482} 08/31/2021 12:44:12 - INFO - __main__ - Step 129724: {'lr': 2.2802293609520936e-05, 'samples': 24907008, 'steps': 129723, 'loss/train': 1.683417797088623} 08/31/2021 12:44:12 - INFO - __main__ - Step 129725: {'lr': 2.2800079410989966e-05, 'samples': 24907200, 'steps': 129724, 'loss/train': 0.7358629107475281} 08/31/2021 12:44:13 - INFO - __main__ - Step 129726: {'lr': 2.27978653148318e-05, 'samples': 24907392, 'steps': 129725, 'loss/train': 1.0688506364822388} 08/31/2021 12:44:14 - INFO - __main__ - Step 129727: {'lr': 2.279565132104741e-05, 'samples': 24907584, 'steps': 129726, 'loss/train': 0.9539937973022461} 08/31/2021 12:44:14 - INFO - __main__ - Step 129728: {'lr': 2.279343742963777e-05, 'samples': 24907776, 'steps': 129727, 'loss/train': 1.6616110801696777} 08/31/2021 12:44:15 - INFO - __main__ - Step 129729: {'lr': 2.279122364060393e-05, 'samples': 24907968, 'steps': 129728, 'loss/train': 0.8361775279045105} 08/31/2021 12:44:15 - INFO - __main__ - Step 129730: {'lr': 2.2789009953946838e-05, 'samples': 24908160, 'steps': 129729, 'loss/train': 1.186217188835144} 08/31/2021 12:44:16 - INFO - __main__ - Step 129731: {'lr': 2.278679636966752e-05, 'samples': 24908352, 'steps': 129730, 'loss/train': 2.051852226257324} 08/31/2021 12:44:17 - INFO - __main__ - Step 129732: {'lr': 2.2784582887766968e-05, 'samples': 24908544, 'steps': 129731, 'loss/train': 1.3725135326385498} 08/31/2021 12:44:17 - INFO - __main__ - Step 129733: {'lr': 2.278236950824622e-05, 'samples': 24908736, 'steps': 129732, 'loss/train': 1.1540697813034058} 08/31/2021 12:44:18 - INFO - __main__ - Step 129734: {'lr': 2.2780156231106186e-05, 'samples': 24908928, 'steps': 129733, 'loss/train': 0.7236178517341614} 08/31/2021 12:44:18 - INFO - __main__ - Step 129735: {'lr': 2.2777943056347923e-05, 'samples': 24909120, 'steps': 129734, 'loss/train': 1.3535977602005005} 08/31/2021 12:44:18 - INFO - __main__ - Step 129736: {'lr': 2.277572998397237e-05, 'samples': 24909312, 'steps': 129735, 'loss/train': 0.02324850484728813} 08/31/2021 12:44:20 - INFO - __main__ - Step 129737: {'lr': 2.2773517013980615e-05, 'samples': 24909504, 'steps': 129736, 'loss/train': 0.6928743720054626} 08/31/2021 12:44:21 - INFO - __main__ - Step 129738: {'lr': 2.2771304146373572e-05, 'samples': 24909696, 'steps': 129737, 'loss/train': 1.2704744338989258} 08/31/2021 12:44:21 - INFO - __main__ - Step 129739: {'lr': 2.2769091381152298e-05, 'samples': 24909888, 'steps': 129738, 'loss/train': 1.2120999097824097} 08/31/2021 12:44:21 - INFO - __main__ - Step 129740: {'lr': 2.276687871831773e-05, 'samples': 24910080, 'steps': 129739, 'loss/train': 1.3256580829620361} 08/31/2021 12:44:22 - INFO - __main__ - Step 129741: {'lr': 2.276466615787093e-05, 'samples': 24910272, 'steps': 129740, 'loss/train': 1.4486699104309082} 08/31/2021 12:44:23 - INFO - __main__ - Step 129742: {'lr': 2.2762453699812864e-05, 'samples': 24910464, 'steps': 129741, 'loss/train': 0.7615713477134705} 08/31/2021 12:44:24 - INFO - __main__ - Step 129743: {'lr': 2.2760241344144504e-05, 'samples': 24910656, 'steps': 129742, 'loss/train': 0.20970195531845093} 08/31/2021 12:44:24 - INFO - __main__ - Step 129744: {'lr': 2.2758029090866937e-05, 'samples': 24910848, 'steps': 129743, 'loss/train': 1.474588394165039} 08/31/2021 12:44:24 - INFO - __main__ - Step 129745: {'lr': 2.2755816939981078e-05, 'samples': 24911040, 'steps': 129744, 'loss/train': 2.937105655670166} 08/31/2021 12:44:25 - INFO - __main__ - Step 129746: {'lr': 2.2753604891487895e-05, 'samples': 24911232, 'steps': 129745, 'loss/train': 0.028435640037059784} 08/31/2021 12:44:25 - INFO - __main__ - Step 129747: {'lr': 2.2751392945388443e-05, 'samples': 24911424, 'steps': 129746, 'loss/train': 0.9205775856971741} 08/31/2021 12:44:27 - INFO - __main__ - Step 129748: {'lr': 2.2749181101683724e-05, 'samples': 24911616, 'steps': 129747, 'loss/train': 0.43681997060775757} 08/31/2021 12:44:27 - INFO - __main__ - Step 129749: {'lr': 2.2746969360374707e-05, 'samples': 24911808, 'steps': 129748, 'loss/train': 0.3267833888530731} 08/31/2021 12:44:27 - INFO - __main__ - Step 129750: {'lr': 2.2744757721462395e-05, 'samples': 24912000, 'steps': 129749, 'loss/train': 0.7508440017700195} 08/31/2021 12:44:28 - INFO - __main__ - Step 129751: {'lr': 2.274254618494781e-05, 'samples': 24912192, 'steps': 129750, 'loss/train': 0.16247354447841644} 08/31/2021 12:44:28 - INFO - __main__ - Step 129752: {'lr': 2.2740334750831898e-05, 'samples': 24912384, 'steps': 129751, 'loss/train': 0.7956932187080383} 08/31/2021 12:44:30 - INFO - __main__ - Step 129753: {'lr': 2.2738123419115685e-05, 'samples': 24912576, 'steps': 129752, 'loss/train': 0.9558124542236328} 08/31/2021 12:44:30 - INFO - __main__ - Step 129754: {'lr': 2.2735912189800175e-05, 'samples': 24912768, 'steps': 129753, 'loss/train': 0.8982917666435242} 08/31/2021 12:44:30 - INFO - __main__ - Step 129755: {'lr': 2.2733701062886414e-05, 'samples': 24912960, 'steps': 129754, 'loss/train': 0.6264254450798035} 08/31/2021 12:44:31 - INFO - __main__ - Step 129756: {'lr': 2.2731490038375295e-05, 'samples': 24913152, 'steps': 129755, 'loss/train': 0.9108054041862488} 08/31/2021 12:44:31 - INFO - __main__ - Step 129757: {'lr': 2.2729279116267847e-05, 'samples': 24913344, 'steps': 129756, 'loss/train': 1.0649783611297607} 08/31/2021 12:44:33 - INFO - __main__ - Step 129758: {'lr': 2.2727068296565067e-05, 'samples': 24913536, 'steps': 129757, 'loss/train': 1.3264451026916504} 08/31/2021 12:44:33 - INFO - __main__ - Step 129759: {'lr': 2.2724857579267983e-05, 'samples': 24913728, 'steps': 129758, 'loss/train': 1.3302068710327148} 08/31/2021 12:44:34 - INFO - __main__ - Step 129760: {'lr': 2.2722646964377562e-05, 'samples': 24913920, 'steps': 129759, 'loss/train': 1.132641315460205} 08/31/2021 12:44:34 - INFO - __main__ - Step 129761: {'lr': 2.272043645189481e-05, 'samples': 24914112, 'steps': 129760, 'loss/train': 0.020865723490715027} 08/31/2021 12:44:34 - INFO - __main__ - Step 129762: {'lr': 2.2718226041820724e-05, 'samples': 24914304, 'steps': 129761, 'loss/train': 1.355579137802124} 08/31/2021 12:44:35 - INFO - __main__ - Step 129763: {'lr': 2.2716015734156298e-05, 'samples': 24914496, 'steps': 129762, 'loss/train': 0.8378161787986755} 08/31/2021 12:44:36 - INFO - __main__ - Step 129764: {'lr': 2.2713805528902537e-05, 'samples': 24914688, 'steps': 129763, 'loss/train': 1.8098440170288086} 08/31/2021 12:44:37 - INFO - __main__ - Step 129765: {'lr': 2.271159542606041e-05, 'samples': 24914880, 'steps': 129764, 'loss/train': 1.3850505352020264} 08/31/2021 12:44:37 - INFO - __main__ - Step 129766: {'lr': 2.2709385425631002e-05, 'samples': 24915072, 'steps': 129765, 'loss/train': 0.9193862080574036} 08/31/2021 12:44:37 - INFO - __main__ - Step 129767: {'lr': 2.270717552761517e-05, 'samples': 24915264, 'steps': 129766, 'loss/train': 1.3325786590576172} 08/31/2021 12:44:38 - INFO - __main__ - Step 129768: {'lr': 2.2704965732013972e-05, 'samples': 24915456, 'steps': 129767, 'loss/train': 1.0226843357086182} 08/31/2021 12:44:39 - INFO - __main__ - Step 129769: {'lr': 2.2702756038828433e-05, 'samples': 24915648, 'steps': 129768, 'loss/train': 0.03602733835577965} 08/31/2021 12:44:40 - INFO - __main__ - Step 129770: {'lr': 2.2700546448059494e-05, 'samples': 24915840, 'steps': 129769, 'loss/train': 0.8566151261329651} 08/31/2021 12:44:40 - INFO - __main__ - Step 129771: {'lr': 2.2698336959708215e-05, 'samples': 24916032, 'steps': 129770, 'loss/train': 1.378869652748108} 08/31/2021 12:44:40 - INFO - __main__ - Step 129772: {'lr': 2.269612757377554e-05, 'samples': 24916224, 'steps': 129771, 'loss/train': 1.6244174242019653} 08/31/2021 12:44:41 - INFO - __main__ - Step 129773: {'lr': 2.269391829026249e-05, 'samples': 24916416, 'steps': 129772, 'loss/train': 1.583437204360962} 08/31/2021 12:44:42 - INFO - __main__ - Step 129774: {'lr': 2.2691709109170037e-05, 'samples': 24916608, 'steps': 129773, 'loss/train': 1.070204734802246} 08/31/2021 12:44:43 - INFO - __main__ - Step 129775: {'lr': 2.2689500030499217e-05, 'samples': 24916800, 'steps': 129774, 'loss/train': 1.3924607038497925} 08/31/2021 12:44:43 - INFO - __main__ - Step 129776: {'lr': 2.2687291054251018e-05, 'samples': 24916992, 'steps': 129775, 'loss/train': 0.670365035533905} 08/31/2021 12:44:44 - INFO - __main__ - Step 129777: {'lr': 2.268508218042639e-05, 'samples': 24917184, 'steps': 129776, 'loss/train': 1.2249504327774048} 08/31/2021 12:44:44 - INFO - __main__ - Step 129778: {'lr': 2.268287340902636e-05, 'samples': 24917376, 'steps': 129777, 'loss/train': 1.0334627628326416} 08/31/2021 12:44:46 - INFO - __main__ - Step 129779: {'lr': 2.26806647400519e-05, 'samples': 24917568, 'steps': 129778, 'loss/train': 1.1792271137237549} 08/31/2021 12:44:47 - INFO - __main__ - Step 129780: {'lr': 2.267845617350406e-05, 'samples': 24917760, 'steps': 129779, 'loss/train': 1.017337679862976} 08/31/2021 12:44:47 - INFO - __main__ - Step 129781: {'lr': 2.2676247709383758e-05, 'samples': 24917952, 'steps': 129780, 'loss/train': 0.3861156702041626} 08/31/2021 12:44:48 - INFO - __main__ - Step 129782: {'lr': 2.267403934769205e-05, 'samples': 24918144, 'steps': 129781, 'loss/train': 0.47666046023368835} 08/31/2021 12:44:48 - INFO - __main__ - Step 129783: {'lr': 2.2671831088429908e-05, 'samples': 24918336, 'steps': 129782, 'loss/train': 0.8429394364356995} 08/31/2021 12:44:48 - INFO - __main__ - Step 129784: {'lr': 2.2669622931598356e-05, 'samples': 24918528, 'steps': 129783, 'loss/train': 0.8678949475288391} 08/31/2021 12:44:50 - INFO - __main__ - Step 129785: {'lr': 2.266741487719834e-05, 'samples': 24918720, 'steps': 129784, 'loss/train': 0.05093615874648094} 08/31/2021 12:44:50 - INFO - __main__ - Step 129786: {'lr': 2.2665206925230857e-05, 'samples': 24918912, 'steps': 129785, 'loss/train': 0.733457624912262} 08/31/2021 12:44:51 - INFO - __main__ - Step 129787: {'lr': 2.266299907569702e-05, 'samples': 24919104, 'steps': 129786, 'loss/train': 0.7901662588119507} 08/31/2021 12:44:51 - INFO - __main__ - Step 129788: {'lr': 2.2660791328597637e-05, 'samples': 24919296, 'steps': 129787, 'loss/train': 1.0122935771942139} 08/31/2021 12:44:51 - INFO - __main__ - Step 129789: {'lr': 2.265858368393381e-05, 'samples': 24919488, 'steps': 129788, 'loss/train': 1.0320849418640137} 08/31/2021 12:44:53 - INFO - __main__ - Step 129790: {'lr': 2.2656376141706542e-05, 'samples': 24919680, 'steps': 129789, 'loss/train': 1.4154770374298096} 08/31/2021 12:44:54 - INFO - __main__ - Step 129791: {'lr': 2.265416870191678e-05, 'samples': 24919872, 'steps': 129790, 'loss/train': 0.552355170249939} 08/31/2021 12:44:54 - INFO - __main__ - Step 129792: {'lr': 2.2651961364565545e-05, 'samples': 24920064, 'steps': 129791, 'loss/train': 1.2096781730651855} 08/31/2021 12:44:54 - INFO - __main__ - Step 129793: {'lr': 2.264975412965381e-05, 'samples': 24920256, 'steps': 129792, 'loss/train': 5.701938152313232} 08/31/2021 12:44:55 - INFO - __main__ - Step 129794: {'lr': 2.2647546997182604e-05, 'samples': 24920448, 'steps': 129793, 'loss/train': 0.824589192867279} 08/31/2021 12:44:55 - INFO - __main__ - Step 129795: {'lr': 2.26453399671529e-05, 'samples': 24920640, 'steps': 129794, 'loss/train': 0.08097100257873535} 08/31/2021 12:44:57 - INFO - __main__ - Step 129796: {'lr': 2.2643133039565695e-05, 'samples': 24920832, 'steps': 129795, 'loss/train': 0.5326731204986572} 08/31/2021 12:44:57 - INFO - __main__ - Step 129797: {'lr': 2.2640926214422013e-05, 'samples': 24921024, 'steps': 129796, 'loss/train': 1.0495249032974243} 08/31/2021 12:44:57 - INFO - __main__ - Step 129798: {'lr': 2.2638719491722774e-05, 'samples': 24921216, 'steps': 129797, 'loss/train': 0.9991697072982788} 08/31/2021 12:44:58 - INFO - __main__ - Step 129799: {'lr': 2.263651287146906e-05, 'samples': 24921408, 'steps': 129798, 'loss/train': 2.097609043121338} 08/31/2021 12:44:58 - INFO - __main__ - Step 129800: {'lr': 2.2634306353661816e-05, 'samples': 24921600, 'steps': 129799, 'loss/train': 0.895542323589325} 08/31/2021 12:45:00 - INFO - __main__ - Step 129801: {'lr': 2.2632099938302093e-05, 'samples': 24921792, 'steps': 129800, 'loss/train': 1.1158177852630615} 08/31/2021 12:45:00 - INFO - __main__ - Step 129802: {'lr': 2.262989362539078e-05, 'samples': 24921984, 'steps': 129801, 'loss/train': 1.5438529253005981} 08/31/2021 12:45:00 - INFO - __main__ - Step 129803: {'lr': 2.2627687414928933e-05, 'samples': 24922176, 'steps': 129802, 'loss/train': 1.4168267250061035} 08/31/2021 12:45:01 - INFO - __main__ - Step 129804: {'lr': 2.2625481306917523e-05, 'samples': 24922368, 'steps': 129803, 'loss/train': 0.7409371137619019} 08/31/2021 12:45:01 - INFO - __main__ - Step 129805: {'lr': 2.2623275301357577e-05, 'samples': 24922560, 'steps': 129804, 'loss/train': 1.0758100748062134} 08/31/2021 12:45:03 - INFO - __main__ - Step 129806: {'lr': 2.2621069398250095e-05, 'samples': 24922752, 'steps': 129805, 'loss/train': 1.3279896974563599} 08/31/2021 12:45:04 - INFO - __main__ - Step 129807: {'lr': 2.261886359759602e-05, 'samples': 24922944, 'steps': 129806, 'loss/train': 1.422957420349121} 08/31/2021 12:45:04 - INFO - __main__ - Step 129808: {'lr': 2.2616657899396404e-05, 'samples': 24923136, 'steps': 129807, 'loss/train': 0.012996964156627655} 08/31/2021 12:45:05 - INFO - __main__ - Step 129809: {'lr': 2.2614452303652195e-05, 'samples': 24923328, 'steps': 129808, 'loss/train': 0.01346148457378149} 08/31/2021 12:45:05 - INFO - __main__ - Step 129810: {'lr': 2.2612246810364416e-05, 'samples': 24923520, 'steps': 129809, 'loss/train': 0.917452335357666} 08/31/2021 12:45:05 - INFO - __main__ - Step 129811: {'lr': 2.2610041419534044e-05, 'samples': 24923712, 'steps': 129810, 'loss/train': 1.7122594118118286} 08/31/2021 12:45:06 - INFO - __main__ - Step 129812: {'lr': 2.2607836131162075e-05, 'samples': 24923904, 'steps': 129811, 'loss/train': 1.2145334482192993} 08/31/2021 12:45:07 - INFO - __main__ - Step 129813: {'lr': 2.2605630945249505e-05, 'samples': 24924096, 'steps': 129812, 'loss/train': 1.3522824048995972} 08/31/2021 12:45:08 - INFO - __main__ - Step 129814: {'lr': 2.2603425861797368e-05, 'samples': 24924288, 'steps': 129813, 'loss/train': 1.0201674699783325} 08/31/2021 12:45:08 - INFO - __main__ - Step 129815: {'lr': 2.26012208808066e-05, 'samples': 24924480, 'steps': 129814, 'loss/train': 1.4328906536102295} 08/31/2021 12:45:08 - INFO - __main__ - Step 129816: {'lr': 2.259901600227818e-05, 'samples': 24924672, 'steps': 129815, 'loss/train': 1.0115236043930054} 08/31/2021 12:45:09 - INFO - __main__ - Step 129817: {'lr': 2.2596811226213153e-05, 'samples': 24924864, 'steps': 129816, 'loss/train': 0.1712029129266739} 08/31/2021 12:45:10 - INFO - __main__ - Step 129818: {'lr': 2.2594606552612503e-05, 'samples': 24925056, 'steps': 129817, 'loss/train': 0.9424749612808228} 08/31/2021 12:45:11 - INFO - __main__ - Step 129819: {'lr': 2.2592401981477188e-05, 'samples': 24925248, 'steps': 129818, 'loss/train': 0.8611513376235962} 08/31/2021 12:45:11 - INFO - __main__ - Step 129820: {'lr': 2.259019751280825e-05, 'samples': 24925440, 'steps': 129819, 'loss/train': 0.8137322664260864} 08/31/2021 12:45:11 - INFO - __main__ - Step 129821: {'lr': 2.2587993146606643e-05, 'samples': 24925632, 'steps': 129820, 'loss/train': 0.43686407804489136} 08/31/2021 12:45:12 - INFO - __main__ - Step 129822: {'lr': 2.258578888287338e-05, 'samples': 24925824, 'steps': 129821, 'loss/train': 0.23892563581466675} 08/31/2021 12:45:14 - INFO - __main__ - Step 129823: {'lr': 2.2583584721609456e-05, 'samples': 24926016, 'steps': 129822, 'loss/train': 1.0143591165542603} 08/31/2021 12:45:14 - INFO - __main__ - Step 129824: {'lr': 2.258138066281587e-05, 'samples': 24926208, 'steps': 129823, 'loss/train': 1.5137611627578735} 08/31/2021 12:45:14 - INFO - __main__ - Step 129825: {'lr': 2.2579176706493593e-05, 'samples': 24926400, 'steps': 129824, 'loss/train': 0.13025251030921936} 08/31/2021 12:45:15 - INFO - __main__ - Step 129826: {'lr': 2.2576972852643623e-05, 'samples': 24926592, 'steps': 129825, 'loss/train': 0.9293731451034546} 08/31/2021 12:45:15 - INFO - __main__ - Step 129827: {'lr': 2.257476910126699e-05, 'samples': 24926784, 'steps': 129826, 'loss/train': 0.014614290557801723} 08/31/2021 12:45:15 - INFO - __main__ - Step 129828: {'lr': 2.2572565452364663e-05, 'samples': 24926976, 'steps': 129827, 'loss/train': 1.7016384601593018} 08/31/2021 12:45:17 - INFO - __main__ - Step 129829: {'lr': 2.2570361905937614e-05, 'samples': 24927168, 'steps': 129828, 'loss/train': 1.0255835056304932} 08/31/2021 12:45:17 - INFO - __main__ - Step 129830: {'lr': 2.2568158461986844e-05, 'samples': 24927360, 'steps': 129829, 'loss/train': 1.1879150867462158} 08/31/2021 12:45:18 - INFO - __main__ - Step 129831: {'lr': 2.256595512051332e-05, 'samples': 24927552, 'steps': 129830, 'loss/train': 1.2019809484481812} 08/31/2021 12:45:18 - INFO - __main__ - Step 129832: {'lr': 2.2563751881518103e-05, 'samples': 24927744, 'steps': 129831, 'loss/train': 0.6271658539772034} 08/31/2021 12:45:19 - INFO - __main__ - Step 129833: {'lr': 2.2561548745002132e-05, 'samples': 24927936, 'steps': 129832, 'loss/train': 1.1804596185684204} 08/31/2021 12:45:21 - INFO - __main__ - Step 129834: {'lr': 2.2559345710966434e-05, 'samples': 24928128, 'steps': 129833, 'loss/train': 0.9917665123939514} 08/31/2021 12:45:21 - INFO - __main__ - Step 129835: {'lr': 2.2557142779411982e-05, 'samples': 24928320, 'steps': 129834, 'loss/train': 0.8802825808525085} 08/31/2021 12:45:22 - INFO - __main__ - Step 129836: {'lr': 2.255493995033975e-05, 'samples': 24928512, 'steps': 129835, 'loss/train': 1.1419609785079956} 08/31/2021 12:45:22 - INFO - __main__ - Step 129837: {'lr': 2.2552737223750786e-05, 'samples': 24928704, 'steps': 129836, 'loss/train': 0.29461294412612915} 08/31/2021 12:45:22 - INFO - __main__ - Step 129838: {'lr': 2.255053459964601e-05, 'samples': 24928896, 'steps': 129837, 'loss/train': 0.4171856641769409} 08/31/2021 12:45:24 - INFO - __main__ - Step 129839: {'lr': 2.254833207802648e-05, 'samples': 24929088, 'steps': 129838, 'loss/train': 0.5448221564292908} 08/31/2021 12:45:24 - INFO - __main__ - Step 129840: {'lr': 2.254612965889316e-05, 'samples': 24929280, 'steps': 129839, 'loss/train': 0.6760474443435669} 08/31/2021 12:45:25 - INFO - __main__ - Step 129841: {'lr': 2.2543927342247084e-05, 'samples': 24929472, 'steps': 129840, 'loss/train': 1.2327476739883423} 08/31/2021 12:45:25 - INFO - __main__ - Step 129842: {'lr': 2.2541725128089162e-05, 'samples': 24929664, 'steps': 129841, 'loss/train': 0.11095544695854187} 08/31/2021 12:45:25 - INFO - __main__ - Step 129843: {'lr': 2.2539523016420428e-05, 'samples': 24929856, 'steps': 129842, 'loss/train': 1.3868204355239868} 08/31/2021 12:45:27 - INFO - __main__ - Step 129844: {'lr': 2.2537321007241873e-05, 'samples': 24930048, 'steps': 129843, 'loss/train': 1.1761000156402588} 08/31/2021 12:45:27 - INFO - __main__ - Step 129845: {'lr': 2.2535119100554502e-05, 'samples': 24930240, 'steps': 129844, 'loss/train': 0.916885256767273} 08/31/2021 12:45:28 - INFO - __main__ - Step 129846: {'lr': 2.2532917296359283e-05, 'samples': 24930432, 'steps': 129845, 'loss/train': 0.14134858548641205} 08/31/2021 12:45:28 - INFO - __main__ - Step 129847: {'lr': 2.253071559465722e-05, 'samples': 24930624, 'steps': 129846, 'loss/train': 1.5979324579238892} 08/31/2021 12:45:28 - INFO - __main__ - Step 129848: {'lr': 2.2528513995449307e-05, 'samples': 24930816, 'steps': 129847, 'loss/train': 0.7573588490486145} 08/31/2021 12:45:30 - INFO - __main__ - Step 129849: {'lr': 2.2526312498736544e-05, 'samples': 24931008, 'steps': 129848, 'loss/train': 1.046080470085144} 08/31/2021 12:45:30 - INFO - __main__ - Step 129850: {'lr': 2.2524111104519905e-05, 'samples': 24931200, 'steps': 129849, 'loss/train': 0.8772863745689392} 08/31/2021 12:45:31 - INFO - __main__ - Step 129851: {'lr': 2.252190981280042e-05, 'samples': 24931392, 'steps': 129850, 'loss/train': 1.1345641613006592} 08/31/2021 12:45:31 - INFO - __main__ - Step 129852: {'lr': 2.251970862357902e-05, 'samples': 24931584, 'steps': 129851, 'loss/train': 1.248888611793518} 08/31/2021 12:45:31 - INFO - __main__ - Step 129853: {'lr': 2.2517507536856748e-05, 'samples': 24931776, 'steps': 129852, 'loss/train': 0.719467282295227} 08/31/2021 12:45:32 - INFO - __main__ - Step 129854: {'lr': 2.2515306552634562e-05, 'samples': 24931968, 'steps': 129853, 'loss/train': 1.0532867908477783} 08/31/2021 12:45:33 - INFO - __main__ - Step 129855: {'lr': 2.2513105670913523e-05, 'samples': 24932160, 'steps': 129854, 'loss/train': 0.6482477188110352} 08/31/2021 12:45:34 - INFO - __main__ - Step 129856: {'lr': 2.2510904891694524e-05, 'samples': 24932352, 'steps': 129855, 'loss/train': 0.8806301355361938} 08/31/2021 12:45:34 - INFO - __main__ - Step 129857: {'lr': 2.2508704214978583e-05, 'samples': 24932544, 'steps': 129856, 'loss/train': 1.0302079916000366} 08/31/2021 12:45:34 - INFO - __main__ - Step 129858: {'lr': 2.250650364076673e-05, 'samples': 24932736, 'steps': 129857, 'loss/train': 1.008447289466858} 08/31/2021 12:45:35 - INFO - __main__ - Step 129859: {'lr': 2.2504303169059908e-05, 'samples': 24932928, 'steps': 129858, 'loss/train': 0.7815046310424805} 08/31/2021 12:45:36 - INFO - __main__ - Step 129860: {'lr': 2.2502102799859177e-05, 'samples': 24933120, 'steps': 129859, 'loss/train': 1.3319839239120483} 08/31/2021 12:45:36 - INFO - __main__ - Step 129861: {'lr': 2.249990253316547e-05, 'samples': 24933312, 'steps': 129860, 'loss/train': 0.9222644567489624} 08/31/2021 12:45:37 - INFO - __main__ - Step 129862: {'lr': 2.249770236897977e-05, 'samples': 24933504, 'steps': 129861, 'loss/train': 0.7302632927894592} 08/31/2021 12:45:37 - INFO - __main__ - Step 129863: {'lr': 2.2495502307303127e-05, 'samples': 24933696, 'steps': 129862, 'loss/train': 1.0505914688110352} 08/31/2021 12:45:37 - INFO - __main__ - Step 129864: {'lr': 2.2493302348136487e-05, 'samples': 24933888, 'steps': 129863, 'loss/train': 0.855465829372406} 08/31/2021 12:45:39 - INFO - __main__ - Step 129865: {'lr': 2.249110249148087e-05, 'samples': 24934080, 'steps': 129864, 'loss/train': 0.7734538316726685} 08/31/2021 12:45:39 - INFO - __main__ - Step 129866: {'lr': 2.2488902737337254e-05, 'samples': 24934272, 'steps': 129865, 'loss/train': 1.497399926185608} 08/31/2021 12:45:40 - INFO - __main__ - Step 129867: {'lr': 2.2486703085706606e-05, 'samples': 24934464, 'steps': 129866, 'loss/train': 1.2638704776763916} 08/31/2021 12:45:40 - INFO - __main__ - Step 129868: {'lr': 2.2484503536589984e-05, 'samples': 24934656, 'steps': 129867, 'loss/train': 1.6190061569213867} 08/31/2021 12:45:41 - INFO - __main__ - Step 129869: {'lr': 2.2482304089988303e-05, 'samples': 24934848, 'steps': 129868, 'loss/train': 1.4787819385528564} 08/31/2021 12:45:42 - INFO - __main__ - Step 129870: {'lr': 2.248010474590259e-05, 'samples': 24935040, 'steps': 129869, 'loss/train': 1.2743638753890991} 08/31/2021 12:45:43 - INFO - __main__ - Step 129871: {'lr': 2.247790550433382e-05, 'samples': 24935232, 'steps': 129870, 'loss/train': 1.5213589668273926} 08/31/2021 12:45:43 - INFO - __main__ - Step 129872: {'lr': 2.2475706365282984e-05, 'samples': 24935424, 'steps': 129871, 'loss/train': 0.7582831382751465} 08/31/2021 12:45:43 - INFO - __main__ - Step 129873: {'lr': 2.2473507328751085e-05, 'samples': 24935616, 'steps': 129872, 'loss/train': 1.035507082939148} 08/31/2021 12:45:44 - INFO - __main__ - Step 129874: {'lr': 2.2471308394739127e-05, 'samples': 24935808, 'steps': 129873, 'loss/train': 0.025850117206573486} 08/31/2021 12:45:45 - INFO - __main__ - Step 129875: {'lr': 2.2469109563248103e-05, 'samples': 24936000, 'steps': 129874, 'loss/train': 0.9200968742370605} 08/31/2021 12:45:46 - INFO - __main__ - Step 129876: {'lr': 2.246691083427896e-05, 'samples': 24936192, 'steps': 129875, 'loss/train': 1.0298256874084473} 08/31/2021 12:45:46 - INFO - __main__ - Step 129877: {'lr': 2.246471220783272e-05, 'samples': 24936384, 'steps': 129876, 'loss/train': 1.0461504459381104} 08/31/2021 12:45:46 - INFO - __main__ - Step 129878: {'lr': 2.2462513683910362e-05, 'samples': 24936576, 'steps': 129877, 'loss/train': 1.6428437232971191} 08/31/2021 12:45:47 - INFO - __main__ - Step 129879: {'lr': 2.246031526251291e-05, 'samples': 24936768, 'steps': 129878, 'loss/train': 0.9556052088737488} 08/31/2021 12:45:47 - INFO - __main__ - Step 129880: {'lr': 2.2458116943641305e-05, 'samples': 24936960, 'steps': 129879, 'loss/train': 0.34130623936653137} 08/31/2021 12:45:49 - INFO - __main__ - Step 129881: {'lr': 2.2455918727296602e-05, 'samples': 24937152, 'steps': 129880, 'loss/train': 1.3153482675552368} 08/31/2021 12:45:49 - INFO - __main__ - Step 129882: {'lr': 2.2453720613479722e-05, 'samples': 24937344, 'steps': 129881, 'loss/train': 1.0871645212173462} 08/31/2021 12:45:49 - INFO - __main__ - Step 129883: {'lr': 2.2451522602191688e-05, 'samples': 24937536, 'steps': 129882, 'loss/train': 1.1451447010040283} 08/31/2021 12:45:50 - INFO - __main__ - Step 129884: {'lr': 2.244932469343347e-05, 'samples': 24937728, 'steps': 129883, 'loss/train': 0.8954248428344727} 08/31/2021 12:45:50 - INFO - __main__ - Step 129885: {'lr': 2.24471268872061e-05, 'samples': 24937920, 'steps': 129884, 'loss/train': 1.4458987712860107} 08/31/2021 12:45:52 - INFO - __main__ - Step 129886: {'lr': 2.2444929183510517e-05, 'samples': 24938112, 'steps': 129885, 'loss/train': 0.6614665389060974} 08/31/2021 12:45:52 - INFO - __main__ - Step 129887: {'lr': 2.2442731582347748e-05, 'samples': 24938304, 'steps': 129886, 'loss/train': 1.1853501796722412} 08/31/2021 12:45:52 - INFO - __main__ - Step 129888: {'lr': 2.2440534083718767e-05, 'samples': 24938496, 'steps': 129887, 'loss/train': 0.8110096454620361} 08/31/2021 12:45:53 - INFO - __main__ - Step 129889: {'lr': 2.24383366876246e-05, 'samples': 24938688, 'steps': 129888, 'loss/train': 0.556505560874939} 08/31/2021 12:45:53 - INFO - __main__ - Step 129890: {'lr': 2.243613939406616e-05, 'samples': 24938880, 'steps': 129889, 'loss/train': 1.264197826385498} 08/31/2021 12:45:55 - INFO - __main__ - Step 129891: {'lr': 2.243394220304451e-05, 'samples': 24939072, 'steps': 129890, 'loss/train': 1.0608187913894653} 08/31/2021 12:45:56 - INFO - __main__ - Step 129892: {'lr': 2.2431745114560614e-05, 'samples': 24939264, 'steps': 129891, 'loss/train': 1.1713405847549438} 08/31/2021 12:45:56 - INFO - __main__ - Step 129893: {'lr': 2.2429548128615472e-05, 'samples': 24939456, 'steps': 129892, 'loss/train': 0.9291002750396729} 08/31/2021 12:45:56 - INFO - __main__ - Step 129894: {'lr': 2.2427351245210032e-05, 'samples': 24939648, 'steps': 129893, 'loss/train': 1.5807298421859741} 08/31/2021 12:45:57 - INFO - __main__ - Step 129895: {'lr': 2.2425154464345397e-05, 'samples': 24939840, 'steps': 129894, 'loss/train': 1.7302758693695068} 08/31/2021 12:45:58 - INFO - __main__ - Step 129896: {'lr': 2.242295778602241e-05, 'samples': 24940032, 'steps': 129895, 'loss/train': 0.8980351090431213} 08/31/2021 12:45:59 - INFO - __main__ - Step 129897: {'lr': 2.2420761210242113e-05, 'samples': 24940224, 'steps': 129896, 'loss/train': 1.2248444557189941} 08/31/2021 12:45:59 - INFO - __main__ - Step 129898: {'lr': 2.2418564737005543e-05, 'samples': 24940416, 'steps': 129897, 'loss/train': 0.7771587371826172} 08/31/2021 12:45:59 - INFO - __main__ - Step 129899: {'lr': 2.241636836631364e-05, 'samples': 24940608, 'steps': 129898, 'loss/train': 0.8661409616470337} 08/31/2021 12:46:00 - INFO - __main__ - Step 129900: {'lr': 2.24141720981674e-05, 'samples': 24940800, 'steps': 129899, 'loss/train': 0.036622852087020874} 08/31/2021 12:46:01 - INFO - __main__ - Step 129901: {'lr': 2.2411975932567828e-05, 'samples': 24940992, 'steps': 129900, 'loss/train': 1.0309088230133057} 08/31/2021 12:46:02 - INFO - __main__ - Step 129902: {'lr': 2.2409779869515922e-05, 'samples': 24941184, 'steps': 129901, 'loss/train': 1.5718107223510742} 08/31/2021 12:46:02 - INFO - __main__ - Step 129903: {'lr': 2.2407583909012624e-05, 'samples': 24941376, 'steps': 129902, 'loss/train': 1.0183382034301758} 08/31/2021 12:46:03 - INFO - __main__ - Step 129904: {'lr': 2.2405388051058988e-05, 'samples': 24941568, 'steps': 129903, 'loss/train': 2.8508658409118652} 08/31/2021 12:46:03 - INFO - __main__ - Step 129905: {'lr': 2.240319229565596e-05, 'samples': 24941760, 'steps': 129904, 'loss/train': 0.3018209934234619} 08/31/2021 12:46:03 - INFO - __main__ - Step 129906: {'lr': 2.240099664280454e-05, 'samples': 24941952, 'steps': 129905, 'loss/train': 1.2454898357391357} 08/31/2021 12:46:05 - INFO - __main__ - Step 129907: {'lr': 2.239880109250572e-05, 'samples': 24942144, 'steps': 129906, 'loss/train': 0.10358443856239319} 08/31/2021 12:46:05 - INFO - __main__ - Step 129908: {'lr': 2.2396605644760536e-05, 'samples': 24942336, 'steps': 129907, 'loss/train': 0.2454233169555664} 08/31/2021 12:46:06 - INFO - __main__ - Step 129909: {'lr': 2.23944102995699e-05, 'samples': 24942528, 'steps': 129908, 'loss/train': 0.7266861200332642} 08/31/2021 12:46:06 - INFO - __main__ - Step 129910: {'lr': 2.239221505693481e-05, 'samples': 24942720, 'steps': 129909, 'loss/train': 0.8867957592010498} 08/31/2021 12:46:06 - INFO - __main__ - Step 129911: {'lr': 2.23900199168563e-05, 'samples': 24942912, 'steps': 129910, 'loss/train': 0.9436824917793274} 08/31/2021 12:46:08 - INFO - __main__ - Step 129912: {'lr': 2.23878248793353e-05, 'samples': 24943104, 'steps': 129911, 'loss/train': 2.288759469985962} 08/31/2021 12:46:08 - INFO - __main__ - Step 129913: {'lr': 2.238562994437285e-05, 'samples': 24943296, 'steps': 129912, 'loss/train': 0.9039745330810547} 08/31/2021 12:46:09 - INFO - __main__ - Step 129914: {'lr': 2.2383435111969914e-05, 'samples': 24943488, 'steps': 129913, 'loss/train': 0.9021856784820557} 08/31/2021 12:46:09 - INFO - __main__ - Step 129915: {'lr': 2.2381240382127494e-05, 'samples': 24943680, 'steps': 129914, 'loss/train': 0.8346924781799316} 08/31/2021 12:46:09 - INFO - __main__ - Step 129916: {'lr': 2.2379045754846588e-05, 'samples': 24943872, 'steps': 129915, 'loss/train': 0.842574417591095} 08/31/2021 12:46:11 - INFO - __main__ - Step 129917: {'lr': 2.237685123012817e-05, 'samples': 24944064, 'steps': 129916, 'loss/train': 0.977997362613678} 08/31/2021 12:46:11 - INFO - __main__ - Step 129918: {'lr': 2.237465680797321e-05, 'samples': 24944256, 'steps': 129917, 'loss/train': 1.419831395149231} 08/31/2021 12:46:12 - INFO - __main__ - Step 129919: {'lr': 2.2372462488382734e-05, 'samples': 24944448, 'steps': 129918, 'loss/train': 1.0072628259658813} 08/31/2021 12:46:12 - INFO - __main__ - Step 129920: {'lr': 2.2370268271357712e-05, 'samples': 24944640, 'steps': 129919, 'loss/train': 1.2490917444229126} 08/31/2021 12:46:12 - INFO - __main__ - Step 129921: {'lr': 2.236807415689912e-05, 'samples': 24944832, 'steps': 129920, 'loss/train': 0.39084193110466003} 08/31/2021 12:46:14 - INFO - __main__ - Step 129922: {'lr': 2.236588014500804e-05, 'samples': 24945024, 'steps': 129921, 'loss/train': 1.359136939048767} 08/31/2021 12:46:14 - INFO - __main__ - Step 129923: {'lr': 2.23636862356853e-05, 'samples': 24945216, 'steps': 129922, 'loss/train': 1.1102229356765747} 08/31/2021 12:46:15 - INFO - __main__ - Step 129924: {'lr': 2.2361492428931983e-05, 'samples': 24945408, 'steps': 129923, 'loss/train': 1.1611354351043701} 08/31/2021 12:46:15 - INFO - __main__ - Step 129925: {'lr': 2.2359298724749066e-05, 'samples': 24945600, 'steps': 129924, 'loss/train': 1.263629674911499} 08/31/2021 12:46:16 - INFO - __main__ - Step 129926: {'lr': 2.2357105123137544e-05, 'samples': 24945792, 'steps': 129925, 'loss/train': 1.8689100742340088} 08/31/2021 12:46:18 - INFO - __main__ - Step 129927: {'lr': 2.235491162409839e-05, 'samples': 24945984, 'steps': 129926, 'loss/train': 2.486269950866699} 08/31/2021 12:46:18 - INFO - __main__ - Step 129928: {'lr': 2.2352718227632603e-05, 'samples': 24946176, 'steps': 129927, 'loss/train': 1.1464556455612183} 08/31/2021 12:46:19 - INFO - __main__ - Step 129929: {'lr': 2.235052493374118e-05, 'samples': 24946368, 'steps': 129928, 'loss/train': 1.6604223251342773} 08/31/2021 12:46:19 - INFO - __main__ - Step 129930: {'lr': 2.2348331742425065e-05, 'samples': 24946560, 'steps': 129929, 'loss/train': 0.5339186191558838} 08/31/2021 12:46:19 - INFO - __main__ - Step 129931: {'lr': 2.2346138653685317e-05, 'samples': 24946752, 'steps': 129930, 'loss/train': 0.48361822962760925} 08/31/2021 12:46:20 - INFO - __main__ - Step 129932: {'lr': 2.2343945667522848e-05, 'samples': 24946944, 'steps': 129931, 'loss/train': 1.395129919052124} 08/31/2021 12:46:20 - INFO - __main__ - Step 129933: {'lr': 2.2341752783938712e-05, 'samples': 24947136, 'steps': 129932, 'loss/train': 0.6685793995857239} 08/31/2021 12:46:22 - INFO - __main__ - Step 129934: {'lr': 2.2339560002933857e-05, 'samples': 24947328, 'steps': 129933, 'loss/train': 1.4676485061645508} 08/31/2021 12:46:22 - INFO - __main__ - Step 129935: {'lr': 2.2337367324509334e-05, 'samples': 24947520, 'steps': 129934, 'loss/train': 0.9423326849937439} 08/31/2021 12:46:22 - INFO - __main__ - Step 129936: {'lr': 2.2335174748666033e-05, 'samples': 24947712, 'steps': 129935, 'loss/train': 0.2894798219203949} 08/31/2021 12:46:23 - INFO - __main__ - Step 129937: {'lr': 2.2332982275405006e-05, 'samples': 24947904, 'steps': 129936, 'loss/train': 1.1683998107910156} 08/31/2021 12:46:23 - INFO - __main__ - Step 129938: {'lr': 2.23307899047272e-05, 'samples': 24948096, 'steps': 129937, 'loss/train': 0.43280553817749023} 08/31/2021 12:46:25 - INFO - __main__ - Step 129939: {'lr': 2.232859763663364e-05, 'samples': 24948288, 'steps': 129938, 'loss/train': 1.4647749662399292} 08/31/2021 12:46:25 - INFO - __main__ - Step 129940: {'lr': 2.2326405471125272e-05, 'samples': 24948480, 'steps': 129939, 'loss/train': 1.0207525491714478} 08/31/2021 12:46:25 - INFO - __main__ - Step 129941: {'lr': 2.232421340820315e-05, 'samples': 24948672, 'steps': 129940, 'loss/train': 1.3918293714523315} 08/31/2021 12:46:26 - INFO - __main__ - Step 129942: {'lr': 2.232202144786821e-05, 'samples': 24948864, 'steps': 129941, 'loss/train': 1.3305519819259644} 08/31/2021 12:46:26 - INFO - __main__ - Step 129943: {'lr': 2.2319829590121466e-05, 'samples': 24949056, 'steps': 129942, 'loss/train': 1.3788236379623413} 08/31/2021 12:46:28 - INFO - __main__ - Step 129944: {'lr': 2.231763783496388e-05, 'samples': 24949248, 'steps': 129943, 'loss/train': 1.0107452869415283} 08/31/2021 12:46:29 - INFO - __main__ - Step 129945: {'lr': 2.231544618239645e-05, 'samples': 24949440, 'steps': 129944, 'loss/train': 1.144790768623352} 08/31/2021 12:46:29 - INFO - __main__ - Step 129946: {'lr': 2.2313254632420148e-05, 'samples': 24949632, 'steps': 129945, 'loss/train': 1.7052499055862427} 08/31/2021 12:46:30 - INFO - __main__ - Step 129947: {'lr': 2.2311063185036007e-05, 'samples': 24949824, 'steps': 129946, 'loss/train': 1.3328828811645508} 08/31/2021 12:46:30 - INFO - __main__ - Step 129948: {'lr': 2.2308871840244994e-05, 'samples': 24950016, 'steps': 129947, 'loss/train': 0.026288896799087524} 08/31/2021 12:46:30 - INFO - __main__ - Step 129949: {'lr': 2.2306680598048134e-05, 'samples': 24950208, 'steps': 129948, 'loss/train': 0.8476039171218872} 08/31/2021 12:46:32 - INFO - __main__ - Step 129950: {'lr': 2.2304489458446292e-05, 'samples': 24950400, 'steps': 129949, 'loss/train': 0.9605615735054016} 08/31/2021 12:46:32 - INFO - __main__ - Step 129951: {'lr': 2.2302298421440575e-05, 'samples': 24950592, 'steps': 129950, 'loss/train': 0.41819313168525696} 08/31/2021 12:46:33 - INFO - __main__ - Step 129952: {'lr': 2.2300107487031903e-05, 'samples': 24950784, 'steps': 129951, 'loss/train': 1.3729432821273804} 08/31/2021 12:46:33 - INFO - __main__ - Step 129953: {'lr': 2.2297916655221295e-05, 'samples': 24950976, 'steps': 129952, 'loss/train': 1.1001582145690918} 08/31/2021 12:46:33 - INFO - __main__ - Step 129954: {'lr': 2.229572592600973e-05, 'samples': 24951168, 'steps': 129953, 'loss/train': 0.786538302898407} 08/31/2021 12:46:35 - INFO - __main__ - Step 129955: {'lr': 2.2293535299398203e-05, 'samples': 24951360, 'steps': 129954, 'loss/train': 0.7270215153694153} 08/31/2021 12:46:35 - INFO - __main__ - Step 129956: {'lr': 2.229134477538769e-05, 'samples': 24951552, 'steps': 129955, 'loss/train': 1.327033519744873} 08/31/2021 12:46:36 - INFO - __main__ - Step 129957: {'lr': 2.2289154353979186e-05, 'samples': 24951744, 'steps': 129956, 'loss/train': 1.3125890493392944} 08/31/2021 12:46:36 - INFO - __main__ - Step 129958: {'lr': 2.228696403517369e-05, 'samples': 24951936, 'steps': 129957, 'loss/train': 0.6246667504310608} 08/31/2021 12:46:37 - INFO - __main__ - Step 129959: {'lr': 2.228477381897215e-05, 'samples': 24952128, 'steps': 129958, 'loss/train': 1.0541152954101562} 08/31/2021 12:46:38 - INFO - __main__ - Step 129960: {'lr': 2.2282583705375587e-05, 'samples': 24952320, 'steps': 129959, 'loss/train': 1.9379491806030273} 08/31/2021 12:46:39 - INFO - __main__ - Step 129961: {'lr': 2.2280393694384978e-05, 'samples': 24952512, 'steps': 129960, 'loss/train': 0.9874123930931091} 08/31/2021 12:46:39 - INFO - __main__ - Step 129962: {'lr': 2.2278203786001345e-05, 'samples': 24952704, 'steps': 129961, 'loss/train': 0.8753560781478882} 08/31/2021 12:46:39 - INFO - __main__ - Step 129963: {'lr': 2.2276013980225606e-05, 'samples': 24952896, 'steps': 129962, 'loss/train': 1.5885815620422363} 08/31/2021 12:46:40 - INFO - __main__ - Step 129964: {'lr': 2.227382427705879e-05, 'samples': 24953088, 'steps': 129963, 'loss/train': 1.0275533199310303} 08/31/2021 12:46:41 - INFO - __main__ - Step 129965: {'lr': 2.2271634676501866e-05, 'samples': 24953280, 'steps': 129964, 'loss/train': 1.1079308986663818} 08/31/2021 12:46:42 - INFO - __main__ - Step 129966: {'lr': 2.226944517855581e-05, 'samples': 24953472, 'steps': 129965, 'loss/train': 1.0493834018707275} 08/31/2021 12:46:42 - INFO - __main__ - Step 129967: {'lr': 2.226725578322167e-05, 'samples': 24953664, 'steps': 129966, 'loss/train': 0.6369730234146118} 08/31/2021 12:46:42 - INFO - __main__ - Step 129968: {'lr': 2.2265066490500363e-05, 'samples': 24953856, 'steps': 129967, 'loss/train': 0.9013452529907227} 08/31/2021 12:46:43 - INFO - __main__ - Step 129969: {'lr': 2.2262877300392893e-05, 'samples': 24954048, 'steps': 129968, 'loss/train': 0.9150780439376831} 08/31/2021 12:46:44 - INFO - __main__ - Step 129970: {'lr': 2.2260688212900284e-05, 'samples': 24954240, 'steps': 129969, 'loss/train': 1.553712010383606} 08/31/2021 12:46:45 - INFO - __main__ - Step 129971: {'lr': 2.2258499228023476e-05, 'samples': 24954432, 'steps': 129970, 'loss/train': 0.4659154415130615} 08/31/2021 12:46:45 - INFO - __main__ - Step 129972: {'lr': 2.2256310345763474e-05, 'samples': 24954624, 'steps': 129971, 'loss/train': 0.7306496500968933} 08/31/2021 12:46:45 - INFO - __main__ - Step 129973: {'lr': 2.2254121566121248e-05, 'samples': 24954816, 'steps': 129972, 'loss/train': 1.47039794921875} 08/31/2021 12:46:46 - INFO - __main__ - Step 129974: {'lr': 2.2251932889097827e-05, 'samples': 24955008, 'steps': 129973, 'loss/train': 0.8323994278907776} 08/31/2021 12:46:47 - INFO - __main__ - Step 129975: {'lr': 2.2249744314694175e-05, 'samples': 24955200, 'steps': 129974, 'loss/train': 0.9925358295440674} 08/31/2021 12:46:47 - INFO - __main__ - Step 129976: {'lr': 2.22475558429113e-05, 'samples': 24955392, 'steps': 129975, 'loss/train': 1.2103910446166992} 08/31/2021 12:46:48 - INFO - __main__ - Step 129977: {'lr': 2.224536747375011e-05, 'samples': 24955584, 'steps': 129976, 'loss/train': 1.0703315734863281} 08/31/2021 12:46:48 - INFO - __main__ - Step 129978: {'lr': 2.2243179207211665e-05, 'samples': 24955776, 'steps': 129977, 'loss/train': 1.096541404724121} 08/31/2021 12:46:49 - INFO - __main__ - Step 129979: {'lr': 2.2240991043296938e-05, 'samples': 24955968, 'steps': 129978, 'loss/train': 1.4806960821151733} 08/31/2021 12:46:50 - INFO - __main__ - Step 129980: {'lr': 2.2238802982006868e-05, 'samples': 24956160, 'steps': 129979, 'loss/train': 1.3053653240203857} 08/31/2021 12:46:51 - INFO - __main__ - Step 129981: {'lr': 2.223661502334251e-05, 'samples': 24956352, 'steps': 129980, 'loss/train': 1.4152902364730835} 08/31/2021 12:46:51 - INFO - __main__ - Step 129982: {'lr': 2.223442716730481e-05, 'samples': 24956544, 'steps': 129981, 'loss/train': 0.03447209298610687} 08/31/2021 12:46:51 - INFO - __main__ - Step 129983: {'lr': 2.2232239413894766e-05, 'samples': 24956736, 'steps': 129982, 'loss/train': 0.7985231280326843} 08/31/2021 12:46:52 - INFO - __main__ - Step 129984: {'lr': 2.2230051763113353e-05, 'samples': 24956928, 'steps': 129983, 'loss/train': 1.165177345275879} 08/31/2021 12:46:53 - INFO - __main__ - Step 129985: {'lr': 2.2227864214961562e-05, 'samples': 24957120, 'steps': 129984, 'loss/train': 1.9976322650909424} 08/31/2021 12:46:54 - INFO - __main__ - Step 129986: {'lr': 2.2225676769440373e-05, 'samples': 24957312, 'steps': 129985, 'loss/train': 1.2387374639511108} 08/31/2021 12:46:54 - INFO - __main__ - Step 129987: {'lr': 2.2223489426550808e-05, 'samples': 24957504, 'steps': 129986, 'loss/train': 0.3622918725013733} 08/31/2021 12:46:54 - INFO - __main__ - Step 129988: {'lr': 2.2221302186293813e-05, 'samples': 24957696, 'steps': 129987, 'loss/train': 1.2958757877349854} 08/31/2021 12:46:55 - INFO - __main__ - Step 129989: {'lr': 2.2219115048670415e-05, 'samples': 24957888, 'steps': 129988, 'loss/train': 1.0468167066574097} 08/31/2021 12:46:56 - INFO - __main__ - Step 129990: {'lr': 2.2216928013681524e-05, 'samples': 24958080, 'steps': 129989, 'loss/train': 1.345779299736023} 08/31/2021 12:46:57 - INFO - __main__ - Step 129991: {'lr': 2.2214741081328178e-05, 'samples': 24958272, 'steps': 129990, 'loss/train': 0.17852360010147095} 08/31/2021 12:46:57 - INFO - __main__ - Step 129992: {'lr': 2.2212554251611366e-05, 'samples': 24958464, 'steps': 129991, 'loss/train': 0.21756182610988617} 08/31/2021 12:46:58 - INFO - __main__ - Step 129993: {'lr': 2.2210367524532037e-05, 'samples': 24958656, 'steps': 129992, 'loss/train': 0.733695387840271} 08/31/2021 12:46:58 - INFO - __main__ - Step 129994: {'lr': 2.2208180900091217e-05, 'samples': 24958848, 'steps': 129993, 'loss/train': 0.9148220419883728} 08/31/2021 12:46:58 - INFO - __main__ - Step 129995: {'lr': 2.220599437828988e-05, 'samples': 24959040, 'steps': 129994, 'loss/train': 0.559565544128418} 08/31/2021 12:47:00 - INFO - __main__ - Step 129996: {'lr': 2.220380795912899e-05, 'samples': 24959232, 'steps': 129995, 'loss/train': 1.0683279037475586} 08/31/2021 12:47:01 - INFO - __main__ - Step 129997: {'lr': 2.220162164260958e-05, 'samples': 24959424, 'steps': 129996, 'loss/train': 0.8073109984397888} 08/31/2021 12:47:01 - INFO - __main__ - Step 129998: {'lr': 2.219943542873257e-05, 'samples': 24959616, 'steps': 129997, 'loss/train': 0.8426086902618408} 08/31/2021 12:47:01 - INFO - __main__ - Step 129999: {'lr': 2.2197249317499003e-05, 'samples': 24959808, 'steps': 129998, 'loss/train': 0.4863441288471222} 08/31/2021 12:47:02 - INFO - __main__ - Step 130000: {'lr': 2.219506330890983e-05, 'samples': 24960000, 'steps': 129999, 'loss/train': 1.4958635568618774} 08/31/2021 12:47:03 - INFO - __main__ - Step 130001: {'lr': 2.219287740296605e-05, 'samples': 24960192, 'steps': 130000, 'loss/train': 0.12163034081459045} 08/31/2021 12:47:04 - INFO - __main__ - Step 130002: {'lr': 2.2190691599668687e-05, 'samples': 24960384, 'steps': 130001, 'loss/train': 0.9403402805328369} 08/31/2021 12:47:04 - INFO - __main__ - Step 130003: {'lr': 2.2188505899018635e-05, 'samples': 24960576, 'steps': 130002, 'loss/train': 0.9743923544883728} 08/31/2021 12:47:05 - INFO - __main__ - Step 130004: {'lr': 2.2186320301016915e-05, 'samples': 24960768, 'steps': 130003, 'loss/train': 0.22311361134052277} 08/31/2021 12:47:05 - INFO - __main__ - Step 130005: {'lr': 2.218413480566456e-05, 'samples': 24960960, 'steps': 130004, 'loss/train': 0.02277664840221405} 08/31/2021 12:47:07 - INFO - __main__ - Step 130006: {'lr': 2.2181949412962476e-05, 'samples': 24961152, 'steps': 130005, 'loss/train': 1.29865562915802} 08/31/2021 12:47:07 - INFO - __main__ - Step 130007: {'lr': 2.2179764122911727e-05, 'samples': 24961344, 'steps': 130006, 'loss/train': 0.8215172290802002} 08/31/2021 12:47:08 - INFO - __main__ - Step 130008: {'lr': 2.2177578935513225e-05, 'samples': 24961536, 'steps': 130007, 'loss/train': 1.388997197151184} 08/31/2021 12:47:08 - INFO - __main__ - Step 130009: {'lr': 2.217539385076803e-05, 'samples': 24961728, 'steps': 130008, 'loss/train': 0.019815411418676376} 08/31/2021 12:47:08 - INFO - __main__ - Step 130010: {'lr': 2.2173208868677073e-05, 'samples': 24961920, 'steps': 130009, 'loss/train': 0.01400890201330185} 08/31/2021 12:47:09 - INFO - __main__ - Step 130011: {'lr': 2.217102398924134e-05, 'samples': 24962112, 'steps': 130010, 'loss/train': 0.6405187845230103} 08/31/2021 12:47:10 - INFO - __main__ - Step 130012: {'lr': 2.2168839212461878e-05, 'samples': 24962304, 'steps': 130011, 'loss/train': 0.09311574697494507} 08/31/2021 12:47:11 - INFO - __main__ - Step 130013: {'lr': 2.2166654538339575e-05, 'samples': 24962496, 'steps': 130012, 'loss/train': 1.2492375373840332} 08/31/2021 12:47:11 - INFO - __main__ - Step 130014: {'lr': 2.216446996687546e-05, 'samples': 24962688, 'steps': 130013, 'loss/train': 1.0144455432891846} 08/31/2021 12:47:11 - INFO - __main__ - Step 130015: {'lr': 2.2162285498070533e-05, 'samples': 24962880, 'steps': 130014, 'loss/train': 0.5554249286651611} 08/31/2021 12:47:12 - INFO - __main__ - Step 130016: {'lr': 2.2160101131925735e-05, 'samples': 24963072, 'steps': 130015, 'loss/train': 1.2313284873962402} 08/31/2021 12:47:12 - INFO - __main__ - Step 130017: {'lr': 2.2157916868442126e-05, 'samples': 24963264, 'steps': 130016, 'loss/train': 0.7650792002677917} 08/31/2021 12:47:14 - INFO - __main__ - Step 130018: {'lr': 2.2155732707620614e-05, 'samples': 24963456, 'steps': 130017, 'loss/train': 1.698449969291687} 08/31/2021 12:47:14 - INFO - __main__ - Step 130019: {'lr': 2.2153548649462203e-05, 'samples': 24963648, 'steps': 130018, 'loss/train': 1.7125952243804932} 08/31/2021 12:47:15 - INFO - __main__ - Step 130020: {'lr': 2.2151364693967918e-05, 'samples': 24963840, 'steps': 130019, 'loss/train': 1.653120756149292} 08/31/2021 12:47:15 - INFO - __main__ - Step 130021: {'lr': 2.214918084113868e-05, 'samples': 24964032, 'steps': 130020, 'loss/train': 0.6401932239532471} 08/31/2021 12:47:15 - INFO - __main__ - Step 130022: {'lr': 2.2146997090975508e-05, 'samples': 24964224, 'steps': 130021, 'loss/train': 0.025058845058083534} 08/31/2021 12:47:17 - INFO - __main__ - Step 130023: {'lr': 2.2144813443479462e-05, 'samples': 24964416, 'steps': 130022, 'loss/train': 1.2031974792480469} 08/31/2021 12:47:17 - INFO - __main__ - Step 130024: {'lr': 2.2142629898651372e-05, 'samples': 24964608, 'steps': 130023, 'loss/train': 0.8566749095916748} 08/31/2021 12:47:18 - INFO - __main__ - Step 130025: {'lr': 2.2140446456492298e-05, 'samples': 24964800, 'steps': 130024, 'loss/train': 0.637906014919281} 08/31/2021 12:47:18 - INFO - __main__ - Step 130026: {'lr': 2.2138263117003232e-05, 'samples': 24964992, 'steps': 130025, 'loss/train': 1.6705118417739868} 08/31/2021 12:47:18 - INFO - __main__ - Step 130027: {'lr': 2.213607988018515e-05, 'samples': 24965184, 'steps': 130026, 'loss/train': 1.7512567043304443} 08/31/2021 12:47:19 - INFO - __main__ - Step 130028: {'lr': 2.2133896746039024e-05, 'samples': 24965376, 'steps': 130027, 'loss/train': 0.9888471961021423} 08/31/2021 12:47:20 - INFO - __main__ - Step 130029: {'lr': 2.213171371456585e-05, 'samples': 24965568, 'steps': 130028, 'loss/train': 1.3261992931365967} 08/31/2021 12:47:21 - INFO - __main__ - Step 130030: {'lr': 2.2129530785766628e-05, 'samples': 24965760, 'steps': 130029, 'loss/train': 1.2211135625839233} 08/31/2021 12:47:21 - INFO - __main__ - Step 130031: {'lr': 2.21273479596423e-05, 'samples': 24965952, 'steps': 130030, 'loss/train': 1.262805461883545} 08/31/2021 12:47:21 - INFO - __main__ - Step 130032: {'lr': 2.21251652361939e-05, 'samples': 24966144, 'steps': 130031, 'loss/train': 1.0048080682754517} 08/31/2021 12:47:22 - INFO - __main__ - Step 130033: {'lr': 2.2122982615422364e-05, 'samples': 24966336, 'steps': 130032, 'loss/train': 0.9803496599197388} 08/31/2021 12:47:23 - INFO - __main__ - Step 130034: {'lr': 2.2120800097328724e-05, 'samples': 24966528, 'steps': 130033, 'loss/train': 1.0774654150009155} 08/31/2021 12:47:24 - INFO - __main__ - Step 130035: {'lr': 2.2118617681913922e-05, 'samples': 24966720, 'steps': 130034, 'loss/train': 1.1579210758209229} 08/31/2021 12:47:24 - INFO - __main__ - Step 130036: {'lr': 2.2116435369178927e-05, 'samples': 24966912, 'steps': 130035, 'loss/train': 0.6799599528312683} 08/31/2021 12:47:24 - INFO - __main__ - Step 130037: {'lr': 2.211425315912477e-05, 'samples': 24967104, 'steps': 130036, 'loss/train': 0.6132146120071411} 08/31/2021 12:47:25 - INFO - __main__ - Step 130038: {'lr': 2.211207105175242e-05, 'samples': 24967296, 'steps': 130037, 'loss/train': 1.4625616073608398} 08/31/2021 12:47:26 - INFO - __main__ - Step 130039: {'lr': 2.210988904706282e-05, 'samples': 24967488, 'steps': 130038, 'loss/train': 0.7320932745933533} 08/31/2021 12:47:27 - INFO - __main__ - Step 130040: {'lr': 2.2107707145057026e-05, 'samples': 24967680, 'steps': 130039, 'loss/train': 1.4759578704833984} 08/31/2021 12:47:27 - INFO - __main__ - Step 130041: {'lr': 2.2105525345735954e-05, 'samples': 24967872, 'steps': 130040, 'loss/train': 1.0968823432922363} 08/31/2021 12:47:27 - INFO - __main__ - Step 130042: {'lr': 2.2103343649100633e-05, 'samples': 24968064, 'steps': 130041, 'loss/train': 1.301031470298767} 08/31/2021 12:47:28 - INFO - __main__ - Step 130043: {'lr': 2.210116205515203e-05, 'samples': 24968256, 'steps': 130042, 'loss/train': 1.2216163873672485} 08/31/2021 12:47:29 - INFO - __main__ - Step 130044: {'lr': 2.209898056389112e-05, 'samples': 24968448, 'steps': 130043, 'loss/train': 1.561483383178711} 08/31/2021 12:47:30 - INFO - __main__ - Step 130045: {'lr': 2.2096799175318926e-05, 'samples': 24968640, 'steps': 130044, 'loss/train': 1.6402703523635864} 08/31/2021 12:47:30 - INFO - __main__ - Step 130046: {'lr': 2.209461788943637e-05, 'samples': 24968832, 'steps': 130045, 'loss/train': 1.0668492317199707} 08/31/2021 12:47:30 - INFO - __main__ - Step 130047: {'lr': 2.2092436706244474e-05, 'samples': 24969024, 'steps': 130046, 'loss/train': 0.18102458119392395} 08/31/2021 12:47:31 - INFO - __main__ - Step 130048: {'lr': 2.209025562574418e-05, 'samples': 24969216, 'steps': 130047, 'loss/train': 1.2417186498641968} 08/31/2021 12:47:33 - INFO - __main__ - Step 130049: {'lr': 2.2088074647936523e-05, 'samples': 24969408, 'steps': 130048, 'loss/train': 1.1889625787734985} 08/31/2021 12:47:33 - INFO - __main__ - Step 130050: {'lr': 2.208589377282244e-05, 'samples': 24969600, 'steps': 130049, 'loss/train': 0.7992772459983826} 08/31/2021 12:47:33 - INFO - __main__ - Step 130051: {'lr': 2.208371300040296e-05, 'samples': 24969792, 'steps': 130050, 'loss/train': 1.3122992515563965} 08/31/2021 12:47:34 - INFO - __main__ - Step 130052: {'lr': 2.2081532330679026e-05, 'samples': 24969984, 'steps': 130051, 'loss/train': 1.2053890228271484} 08/31/2021 12:47:34 - INFO - __main__ - Step 130053: {'lr': 2.207935176365164e-05, 'samples': 24970176, 'steps': 130052, 'loss/train': 1.2788584232330322} 08/31/2021 12:47:35 - INFO - __main__ - Step 130054: {'lr': 2.207717129932177e-05, 'samples': 24970368, 'steps': 130053, 'loss/train': 1.262012004852295} 08/31/2021 12:47:37 - INFO - __main__ - Step 130055: {'lr': 2.2074990937690413e-05, 'samples': 24970560, 'steps': 130054, 'loss/train': 1.0488191843032837} 08/31/2021 12:47:37 - INFO - __main__ - Step 130056: {'lr': 2.2072810678758604e-05, 'samples': 24970752, 'steps': 130055, 'loss/train': 1.2439353466033936} 08/31/2021 12:47:37 - INFO - __main__ - Step 130057: {'lr': 2.2070630522527223e-05, 'samples': 24970944, 'steps': 130056, 'loss/train': 0.8640844821929932} 08/31/2021 12:47:38 - INFO - __main__ - Step 130058: {'lr': 2.2068450468997302e-05, 'samples': 24971136, 'steps': 130057, 'loss/train': 1.0202786922454834} 08/31/2021 12:47:38 - INFO - __main__ - Step 130059: {'lr': 2.206627051816981e-05, 'samples': 24971328, 'steps': 130058, 'loss/train': 0.3639979660511017} 08/31/2021 12:47:39 - INFO - __main__ - Step 130060: {'lr': 2.206409067004575e-05, 'samples': 24971520, 'steps': 130059, 'loss/train': 4.2548508644104} 08/31/2021 12:47:40 - INFO - __main__ - Step 130061: {'lr': 2.206191092462609e-05, 'samples': 24971712, 'steps': 130060, 'loss/train': 4.253814220428467} 08/31/2021 12:47:41 - INFO - __main__ - Step 130062: {'lr': 2.2059731281911826e-05, 'samples': 24971904, 'steps': 130061, 'loss/train': 1.511710524559021} 08/31/2021 12:47:41 - INFO - __main__ - Step 130063: {'lr': 2.205755174190391e-05, 'samples': 24972096, 'steps': 130062, 'loss/train': 1.115268349647522} 08/31/2021 12:47:41 - INFO - __main__ - Step 130064: {'lr': 2.205537230460336e-05, 'samples': 24972288, 'steps': 130063, 'loss/train': 1.7358620166778564} 08/31/2021 12:47:42 - INFO - __main__ - Step 130065: {'lr': 2.2053192970011126e-05, 'samples': 24972480, 'steps': 130064, 'loss/train': 1.167072057723999} 08/31/2021 12:47:43 - INFO - __main__ - Step 130066: {'lr': 2.2051013738128205e-05, 'samples': 24972672, 'steps': 130065, 'loss/train': 1.3867409229278564} 08/31/2021 12:47:44 - INFO - __main__ - Step 130067: {'lr': 2.20488346089556e-05, 'samples': 24972864, 'steps': 130066, 'loss/train': 0.9967930912971497} 08/31/2021 12:47:44 - INFO - __main__ - Step 130068: {'lr': 2.2046655582494245e-05, 'samples': 24973056, 'steps': 130067, 'loss/train': 1.4776228666305542} 08/31/2021 12:47:44 - INFO - __main__ - Step 130069: {'lr': 2.2044476658745177e-05, 'samples': 24973248, 'steps': 130068, 'loss/train': 0.7380586862564087} 08/31/2021 12:47:45 - INFO - __main__ - Step 130070: {'lr': 2.204229783770939e-05, 'samples': 24973440, 'steps': 130069, 'loss/train': 1.410060167312622} 08/31/2021 12:47:45 - INFO - __main__ - Step 130071: {'lr': 2.2040119119387774e-05, 'samples': 24973632, 'steps': 130070, 'loss/train': 2.0797581672668457} 08/31/2021 12:47:47 - INFO - __main__ - Step 130072: {'lr': 2.2037940503781357e-05, 'samples': 24973824, 'steps': 130071, 'loss/train': 0.8578277230262756} 08/31/2021 12:47:47 - INFO - __main__ - Step 130073: {'lr': 2.2035761990891136e-05, 'samples': 24974016, 'steps': 130072, 'loss/train': 1.4993796348571777} 08/31/2021 12:47:47 - INFO - __main__ - Step 130074: {'lr': 2.203358358071808e-05, 'samples': 24974208, 'steps': 130073, 'loss/train': 0.7763151526451111} 08/31/2021 12:47:48 - INFO - __main__ - Step 130075: {'lr': 2.2031405273263167e-05, 'samples': 24974400, 'steps': 130074, 'loss/train': 1.071811556816101} 08/31/2021 12:47:48 - INFO - __main__ - Step 130076: {'lr': 2.202922706852739e-05, 'samples': 24974592, 'steps': 130075, 'loss/train': 0.6724839806556702} 08/31/2021 12:47:50 - INFO - __main__ - Step 130077: {'lr': 2.2027048966511724e-05, 'samples': 24974784, 'steps': 130076, 'loss/train': 0.9637497067451477} 08/31/2021 12:47:50 - INFO - __main__ - Step 130078: {'lr': 2.2024870967217142e-05, 'samples': 24974976, 'steps': 130077, 'loss/train': 1.0383938550949097} 08/31/2021 12:47:51 - INFO - __main__ - Step 130079: {'lr': 2.2022693070644668e-05, 'samples': 24975168, 'steps': 130078, 'loss/train': 1.3142402172088623} 08/31/2021 12:47:51 - INFO - __main__ - Step 130080: {'lr': 2.2020515276795217e-05, 'samples': 24975360, 'steps': 130079, 'loss/train': 0.3933994770050049} 08/31/2021 12:47:51 - INFO - __main__ - Step 130081: {'lr': 2.201833758566982e-05, 'samples': 24975552, 'steps': 130080, 'loss/train': 1.7868317365646362} 08/31/2021 12:47:53 - INFO - __main__ - Step 130082: {'lr': 2.2016159997269442e-05, 'samples': 24975744, 'steps': 130081, 'loss/train': 1.143869161605835} 08/31/2021 12:47:53 - INFO - __main__ - Step 130083: {'lr': 2.2013982511595087e-05, 'samples': 24975936, 'steps': 130082, 'loss/train': 0.06466683745384216} 08/31/2021 12:47:54 - INFO - __main__ - Step 130084: {'lr': 2.2011805128647698e-05, 'samples': 24976128, 'steps': 130083, 'loss/train': 0.278189480304718} 08/31/2021 12:47:54 - INFO - __main__ - Step 130085: {'lr': 2.200962784842825e-05, 'samples': 24976320, 'steps': 130084, 'loss/train': 0.5463922023773193} 08/31/2021 12:47:54 - INFO - __main__ - Step 130086: {'lr': 2.200745067093776e-05, 'samples': 24976512, 'steps': 130085, 'loss/train': 1.1963765621185303} 08/31/2021 12:47:56 - INFO - __main__ - Step 130087: {'lr': 2.200527359617721e-05, 'samples': 24976704, 'steps': 130086, 'loss/train': 0.7572259902954102} 08/31/2021 12:47:56 - INFO - __main__ - Step 130088: {'lr': 2.200309662414754e-05, 'samples': 24976896, 'steps': 130087, 'loss/train': 0.26034972071647644} 08/31/2021 12:47:57 - INFO - __main__ - Step 130089: {'lr': 2.2000919754849745e-05, 'samples': 24977088, 'steps': 130088, 'loss/train': 1.0640232563018799} 08/31/2021 12:47:57 - INFO - __main__ - Step 130090: {'lr': 2.1998742988284858e-05, 'samples': 24977280, 'steps': 130089, 'loss/train': 1.0334354639053345} 08/31/2021 12:47:57 - INFO - __main__ - Step 130091: {'lr': 2.1996566324453794e-05, 'samples': 24977472, 'steps': 130090, 'loss/train': 0.7014325857162476} 08/31/2021 12:47:58 - INFO - __main__ - Step 130092: {'lr': 2.1994389763357548e-05, 'samples': 24977664, 'steps': 130091, 'loss/train': 1.1977869272232056} 08/31/2021 12:47:59 - INFO - __main__ - Step 130093: {'lr': 2.199221330499712e-05, 'samples': 24977856, 'steps': 130092, 'loss/train': 1.0648951530456543} 08/31/2021 12:48:00 - INFO - __main__ - Step 130094: {'lr': 2.1990036949373487e-05, 'samples': 24978048, 'steps': 130093, 'loss/train': 1.0972076654434204} 08/31/2021 12:48:00 - INFO - __main__ - Step 130095: {'lr': 2.1987860696487644e-05, 'samples': 24978240, 'steps': 130094, 'loss/train': 0.9557018876075745} 08/31/2021 12:48:00 - INFO - __main__ - Step 130096: {'lr': 2.1985684546340535e-05, 'samples': 24978432, 'steps': 130095, 'loss/train': 0.8443024158477783} 08/31/2021 12:48:01 - INFO - __main__ - Step 130097: {'lr': 2.1983508498933186e-05, 'samples': 24978624, 'steps': 130096, 'loss/train': 0.6374942660331726} 08/31/2021 12:48:02 - INFO - __main__ - Step 130098: {'lr': 2.1981332554266543e-05, 'samples': 24978816, 'steps': 130097, 'loss/train': 0.6540296077728271} 08/31/2021 12:48:03 - INFO - __main__ - Step 130099: {'lr': 2.1979156712341547e-05, 'samples': 24979008, 'steps': 130098, 'loss/train': 1.599787712097168} 08/31/2021 12:48:03 - INFO - __main__ - Step 130100: {'lr': 2.1976980973159255e-05, 'samples': 24979200, 'steps': 130099, 'loss/train': 0.640713632106781} 08/31/2021 12:48:04 - INFO - __main__ - Step 130101: {'lr': 2.197480533672061e-05, 'samples': 24979392, 'steps': 130100, 'loss/train': 1.1258333921432495} 08/31/2021 12:48:04 - INFO - __main__ - Step 130102: {'lr': 2.197262980302661e-05, 'samples': 24979584, 'steps': 130101, 'loss/train': 0.9974682331085205} 08/31/2021 12:48:05 - INFO - __main__ - Step 130103: {'lr': 2.1970454372078202e-05, 'samples': 24979776, 'steps': 130102, 'loss/train': 1.8691291809082031} 08/31/2021 12:48:06 - INFO - __main__ - Step 130104: {'lr': 2.196827904387641e-05, 'samples': 24979968, 'steps': 130103, 'loss/train': 1.0518518686294556} 08/31/2021 12:48:06 - INFO - __main__ - Step 130105: {'lr': 2.1966103818422178e-05, 'samples': 24980160, 'steps': 130104, 'loss/train': 1.5133249759674072} 08/31/2021 12:48:07 - INFO - __main__ - Step 130106: {'lr': 2.1963928695716506e-05, 'samples': 24980352, 'steps': 130105, 'loss/train': 0.3523746430873871} 08/31/2021 12:48:07 - INFO - __main__ - Step 130107: {'lr': 2.1961753675760366e-05, 'samples': 24980544, 'steps': 130106, 'loss/train': 0.5472533702850342} 08/31/2021 12:48:09 - INFO - __main__ - Step 130108: {'lr': 2.1959578758554754e-05, 'samples': 24980736, 'steps': 130107, 'loss/train': 1.3349803686141968} 08/31/2021 12:48:09 - INFO - __main__ - Step 130109: {'lr': 2.1957403944100618e-05, 'samples': 24980928, 'steps': 130108, 'loss/train': 1.638136863708496} 08/31/2021 12:48:10 - INFO - __main__ - Step 130110: {'lr': 2.195522923239901e-05, 'samples': 24981120, 'steps': 130109, 'loss/train': 0.9725954532623291} 08/31/2021 12:48:10 - INFO - __main__ - Step 130111: {'lr': 2.1953054623450817e-05, 'samples': 24981312, 'steps': 130110, 'loss/train': 1.4388248920440674} 08/31/2021 12:48:10 - INFO - __main__ - Step 130112: {'lr': 2.1950880117257043e-05, 'samples': 24981504, 'steps': 130111, 'loss/train': 1.6149309873580933} 08/31/2021 12:48:12 - INFO - __main__ - Step 130113: {'lr': 2.1948705713818686e-05, 'samples': 24981696, 'steps': 130112, 'loss/train': 0.8692101240158081} 08/31/2021 12:48:12 - INFO - __main__ - Step 130114: {'lr': 2.1946531413136738e-05, 'samples': 24981888, 'steps': 130113, 'loss/train': 1.3878953456878662} 08/31/2021 12:48:13 - INFO - __main__ - Step 130115: {'lr': 2.194435721521215e-05, 'samples': 24982080, 'steps': 130114, 'loss/train': 0.6511244177818298} 08/31/2021 12:48:13 - INFO - __main__ - Step 130116: {'lr': 2.1942183120045922e-05, 'samples': 24982272, 'steps': 130115, 'loss/train': 1.2299108505249023} 08/31/2021 12:48:13 - INFO - __main__ - Step 130117: {'lr': 2.194000912763905e-05, 'samples': 24982464, 'steps': 130116, 'loss/train': 1.5246233940124512} 08/31/2021 12:48:15 - INFO - __main__ - Step 130118: {'lr': 2.1937835237992447e-05, 'samples': 24982656, 'steps': 130117, 'loss/train': 1.1007177829742432} 08/31/2021 12:48:15 - INFO - __main__ - Step 130119: {'lr': 2.1935661451107177e-05, 'samples': 24982848, 'steps': 130118, 'loss/train': 1.2073911428451538} 08/31/2021 12:48:16 - INFO - __main__ - Step 130120: {'lr': 2.1933487766984146e-05, 'samples': 24983040, 'steps': 130119, 'loss/train': 1.6752129793167114} 08/31/2021 12:48:16 - INFO - __main__ - Step 130121: {'lr': 2.1931314185624383e-05, 'samples': 24983232, 'steps': 130120, 'loss/train': 1.2929160594940186} 08/31/2021 12:48:16 - INFO - __main__ - Step 130122: {'lr': 2.192914070702884e-05, 'samples': 24983424, 'steps': 130121, 'loss/train': 1.1352344751358032} 08/31/2021 12:48:18 - INFO - __main__ - Step 130123: {'lr': 2.192696733119856e-05, 'samples': 24983616, 'steps': 130122, 'loss/train': 0.6729252338409424} 08/31/2021 12:48:18 - INFO - __main__ - Step 130124: {'lr': 2.1924794058134413e-05, 'samples': 24983808, 'steps': 130123, 'loss/train': 1.150181770324707} 08/31/2021 12:48:19 - INFO - __main__ - Step 130125: {'lr': 2.1922620887837445e-05, 'samples': 24984000, 'steps': 130124, 'loss/train': 1.2349226474761963} 08/31/2021 12:48:19 - INFO - __main__ - Step 130126: {'lr': 2.1920447820308637e-05, 'samples': 24984192, 'steps': 130125, 'loss/train': 1.1770319938659668} 08/31/2021 12:48:19 - INFO - __main__ - Step 130127: {'lr': 2.1918274855548954e-05, 'samples': 24984384, 'steps': 130126, 'loss/train': 0.888517439365387} 08/31/2021 12:48:21 - INFO - __main__ - Step 130128: {'lr': 2.1916101993559338e-05, 'samples': 24984576, 'steps': 130127, 'loss/train': 0.8193866610527039} 08/31/2021 12:48:21 - INFO - __main__ - Step 130129: {'lr': 2.191392923434085e-05, 'samples': 24984768, 'steps': 130128, 'loss/train': 1.4324750900268555} 08/31/2021 12:48:22 - INFO - __main__ - Step 130130: {'lr': 2.1911756577894404e-05, 'samples': 24984960, 'steps': 130129, 'loss/train': 0.7227679491043091} 08/31/2021 12:48:22 - INFO - __main__ - Step 130131: {'lr': 2.1909584024220996e-05, 'samples': 24985152, 'steps': 130130, 'loss/train': 0.655450701713562} 08/31/2021 12:48:22 - INFO - __main__ - Step 130132: {'lr': 2.190741157332163e-05, 'samples': 24985344, 'steps': 130131, 'loss/train': 1.1974354982376099} 08/31/2021 12:48:24 - INFO - __main__ - Step 130133: {'lr': 2.190523922519727e-05, 'samples': 24985536, 'steps': 130132, 'loss/train': 0.6445699334144592} 08/31/2021 12:48:24 - INFO - __main__ - Step 130134: {'lr': 2.190306697984887e-05, 'samples': 24985728, 'steps': 130133, 'loss/train': 1.1991910934448242} 08/31/2021 12:48:24 - INFO - __main__ - Step 130135: {'lr': 2.1900894837277417e-05, 'samples': 24985920, 'steps': 130134, 'loss/train': 1.1617990732192993} 08/31/2021 12:48:25 - INFO - __main__ - Step 130136: {'lr': 2.1898722797483923e-05, 'samples': 24986112, 'steps': 130135, 'loss/train': 0.19889110326766968} 08/31/2021 12:48:25 - INFO - __main__ - Step 130137: {'lr': 2.1896550860469376e-05, 'samples': 24986304, 'steps': 130136, 'loss/train': 1.296097755432129} 08/31/2021 12:48:26 - INFO - __main__ - Step 130138: {'lr': 2.1894379026234702e-05, 'samples': 24986496, 'steps': 130137, 'loss/train': 0.9037672281265259} 08/31/2021 12:48:27 - INFO - __main__ - Step 130139: {'lr': 2.1892207294780892e-05, 'samples': 24986688, 'steps': 130138, 'loss/train': 0.5930368900299072} 08/31/2021 12:48:27 - INFO - __main__ - Step 130140: {'lr': 2.189003566610892e-05, 'samples': 24986880, 'steps': 130139, 'loss/train': 1.0222675800323486} 08/31/2021 12:48:28 - INFO - __main__ - Step 130141: {'lr': 2.1887864140219788e-05, 'samples': 24987072, 'steps': 130140, 'loss/train': 0.5398276448249817} 08/31/2021 12:48:28 - INFO - __main__ - Step 130142: {'lr': 2.1885692717114462e-05, 'samples': 24987264, 'steps': 130141, 'loss/train': 0.8900841474533081} 08/31/2021 12:48:28 - INFO - __main__ - Step 130143: {'lr': 2.188352139679392e-05, 'samples': 24987456, 'steps': 130142, 'loss/train': 1.6865090131759644} 08/31/2021 12:48:30 - INFO - __main__ - Step 130144: {'lr': 2.188135017925913e-05, 'samples': 24987648, 'steps': 130143, 'loss/train': 1.1958171129226685} 08/31/2021 12:48:30 - INFO - __main__ - Step 130145: {'lr': 2.1879179064511118e-05, 'samples': 24987840, 'steps': 130144, 'loss/train': 1.1148549318313599} 08/31/2021 12:48:31 - INFO - __main__ - Step 130146: {'lr': 2.18770080525508e-05, 'samples': 24988032, 'steps': 130145, 'loss/train': 0.9504675269126892} 08/31/2021 12:48:31 - INFO - __main__ - Step 130147: {'lr': 2.187483714337918e-05, 'samples': 24988224, 'steps': 130146, 'loss/train': 0.5332855582237244} 08/31/2021 12:48:31 - INFO - __main__ - Step 130148: {'lr': 2.187266633699725e-05, 'samples': 24988416, 'steps': 130147, 'loss/train': 1.23764967918396} 08/31/2021 12:48:33 - INFO - __main__ - Step 130149: {'lr': 2.1870495633405986e-05, 'samples': 24988608, 'steps': 130148, 'loss/train': 1.1817009449005127} 08/31/2021 12:48:33 - INFO - __main__ - Step 130150: {'lr': 2.1868325032606385e-05, 'samples': 24988800, 'steps': 130149, 'loss/train': 1.3897305727005005} 08/31/2021 12:48:34 - INFO - __main__ - Step 130151: {'lr': 2.1866154534599364e-05, 'samples': 24988992, 'steps': 130150, 'loss/train': 0.22844068706035614} 08/31/2021 12:48:34 - INFO - __main__ - Step 130152: {'lr': 2.186398413938592e-05, 'samples': 24989184, 'steps': 130151, 'loss/train': 1.1189457178115845} 08/31/2021 12:48:34 - INFO - __main__ - Step 130153: {'lr': 2.1861813846967062e-05, 'samples': 24989376, 'steps': 130152, 'loss/train': 0.7668017148971558} 08/31/2021 12:48:36 - INFO - __main__ - Step 130154: {'lr': 2.185964365734372e-05, 'samples': 24989568, 'steps': 130153, 'loss/train': 1.135193943977356} 08/31/2021 12:48:37 - INFO - __main__ - Step 130155: {'lr': 2.185747357051693e-05, 'samples': 24989760, 'steps': 130154, 'loss/train': 0.5034915804862976} 08/31/2021 12:48:37 - INFO - __main__ - Step 130156: {'lr': 2.185530358648763e-05, 'samples': 24989952, 'steps': 130155, 'loss/train': 0.017187096178531647} 08/31/2021 12:48:37 - INFO - __main__ - Step 130157: {'lr': 2.1853133705256823e-05, 'samples': 24990144, 'steps': 130156, 'loss/train': 1.1090465784072876} 08/31/2021 12:48:38 - INFO - __main__ - Step 130158: {'lr': 2.185096392682545e-05, 'samples': 24990336, 'steps': 130157, 'loss/train': 1.8329174518585205} 08/31/2021 12:48:38 - INFO - __main__ - Step 130159: {'lr': 2.1848794251194543e-05, 'samples': 24990528, 'steps': 130158, 'loss/train': 0.4776659309864044} 08/31/2021 12:48:40 - INFO - __main__ - Step 130160: {'lr': 2.1846624678365012e-05, 'samples': 24990720, 'steps': 130159, 'loss/train': 3.8491852283477783} 08/31/2021 12:48:40 - INFO - __main__ - Step 130161: {'lr': 2.1844455208337888e-05, 'samples': 24990912, 'steps': 130160, 'loss/train': 1.2419047355651855} 08/31/2021 12:48:40 - INFO - __main__ - Step 130162: {'lr': 2.184228584111414e-05, 'samples': 24991104, 'steps': 130161, 'loss/train': 0.9873648285865784} 08/31/2021 12:48:41 - INFO - __main__ - Step 130163: {'lr': 2.184011657669474e-05, 'samples': 24991296, 'steps': 130162, 'loss/train': 1.1346659660339355} 08/31/2021 12:48:41 - INFO - __main__ - Step 130164: {'lr': 2.1837947415080688e-05, 'samples': 24991488, 'steps': 130163, 'loss/train': 0.6445803046226501} 08/31/2021 12:48:42 - INFO - __main__ - Step 130165: {'lr': 2.18357783562729e-05, 'samples': 24991680, 'steps': 130164, 'loss/train': 0.530106782913208} 08/31/2021 12:48:44 - INFO - __main__ - Step 130166: {'lr': 2.1833609400272404e-05, 'samples': 24991872, 'steps': 130165, 'loss/train': 1.491105079650879} 08/31/2021 12:48:44 - INFO - __main__ - Step 130167: {'lr': 2.1831440547080137e-05, 'samples': 24992064, 'steps': 130166, 'loss/train': 1.054945707321167} 08/31/2021 12:48:45 - INFO - __main__ - Step 130168: {'lr': 2.1829271796697108e-05, 'samples': 24992256, 'steps': 130167, 'loss/train': 0.5251586437225342} 08/31/2021 12:48:45 - INFO - __main__ - Step 130169: {'lr': 2.1827103149124312e-05, 'samples': 24992448, 'steps': 130168, 'loss/train': 0.7103725075721741} 08/31/2021 12:48:45 - INFO - __main__ - Step 130170: {'lr': 2.1824934604362688e-05, 'samples': 24992640, 'steps': 130169, 'loss/train': 0.8492947816848755} 08/31/2021 12:48:47 - INFO - __main__ - Step 130171: {'lr': 2.1822766162413215e-05, 'samples': 24992832, 'steps': 130170, 'loss/train': 0.5603757500648499} 08/31/2021 12:48:47 - INFO - __main__ - Step 130172: {'lr': 2.182059782327689e-05, 'samples': 24993024, 'steps': 130171, 'loss/train': 1.2670271396636963} 08/31/2021 12:48:48 - INFO - __main__ - Step 130173: {'lr': 2.1818429586954707e-05, 'samples': 24993216, 'steps': 130172, 'loss/train': 0.5513246655464172} 08/31/2021 12:48:48 - INFO - __main__ - Step 130174: {'lr': 2.181626145344759e-05, 'samples': 24993408, 'steps': 130173, 'loss/train': 1.47847318649292} 08/31/2021 12:48:48 - INFO - __main__ - Step 130175: {'lr': 2.181409342275656e-05, 'samples': 24993600, 'steps': 130174, 'loss/train': 1.5900074243545532} 08/31/2021 12:48:50 - INFO - __main__ - Step 130176: {'lr': 2.1811925494882562e-05, 'samples': 24993792, 'steps': 130175, 'loss/train': 0.8743640780448914} 08/31/2021 12:48:50 - INFO - __main__ - Step 130177: {'lr': 2.1809757669826653e-05, 'samples': 24993984, 'steps': 130176, 'loss/train': 0.8073685765266418} 08/31/2021 12:48:51 - INFO - __main__ - Step 130178: {'lr': 2.180758994758969e-05, 'samples': 24994176, 'steps': 130177, 'loss/train': 1.0900459289550781} 08/31/2021 12:48:51 - INFO - __main__ - Step 130179: {'lr': 2.1805422328172703e-05, 'samples': 24994368, 'steps': 130178, 'loss/train': 0.2800152003765106} 08/31/2021 12:48:51 - INFO - __main__ - Step 130180: {'lr': 2.1803254811576662e-05, 'samples': 24994560, 'steps': 130179, 'loss/train': 1.5909290313720703} 08/31/2021 12:48:53 - INFO - __main__ - Step 130181: {'lr': 2.1801087397802567e-05, 'samples': 24994752, 'steps': 130180, 'loss/train': 0.9383271932601929} 08/31/2021 12:48:53 - INFO - __main__ - Step 130182: {'lr': 2.1798920086851388e-05, 'samples': 24994944, 'steps': 130181, 'loss/train': 1.4321397542953491} 08/31/2021 12:48:54 - INFO - __main__ - Step 130183: {'lr': 2.1796752878724068e-05, 'samples': 24995136, 'steps': 130182, 'loss/train': 0.7190226912498474} 08/31/2021 12:48:54 - INFO - __main__ - Step 130184: {'lr': 2.179458577342164e-05, 'samples': 24995328, 'steps': 130183, 'loss/train': 1.147687554359436} 08/31/2021 12:48:54 - INFO - __main__ - Step 130185: {'lr': 2.179241877094504e-05, 'samples': 24995520, 'steps': 130184, 'loss/train': 0.5025222897529602} 08/31/2021 12:48:56 - INFO - __main__ - Step 130186: {'lr': 2.179025187129524e-05, 'samples': 24995712, 'steps': 130185, 'loss/train': 1.5102291107177734} 08/31/2021 12:48:56 - INFO - __main__ - Step 130187: {'lr': 2.1788085074473245e-05, 'samples': 24995904, 'steps': 130186, 'loss/train': 0.8756471276283264} 08/31/2021 12:48:57 - INFO - __main__ - Step 130188: {'lr': 2.1785918380480024e-05, 'samples': 24996096, 'steps': 130187, 'loss/train': 0.9601650834083557} 08/31/2021 12:48:57 - INFO - __main__ - Step 130189: {'lr': 2.1783751789316548e-05, 'samples': 24996288, 'steps': 130188, 'loss/train': 1.4265097379684448} 08/31/2021 12:48:57 - INFO - __main__ - Step 130190: {'lr': 2.178158530098376e-05, 'samples': 24996480, 'steps': 130189, 'loss/train': 0.7944222688674927} 08/31/2021 12:48:59 - INFO - __main__ - Step 130191: {'lr': 2.177941891548274e-05, 'samples': 24996672, 'steps': 130190, 'loss/train': 1.0539324283599854} 08/31/2021 12:48:59 - INFO - __main__ - Step 130192: {'lr': 2.1777252632814355e-05, 'samples': 24996864, 'steps': 130191, 'loss/train': 0.9941632151603699} 08/31/2021 12:49:00 - INFO - __main__ - Step 130193: {'lr': 2.17750864529796e-05, 'samples': 24997056, 'steps': 130192, 'loss/train': 1.058935523033142} 08/31/2021 12:49:00 - INFO - __main__ - Step 130194: {'lr': 2.177292037597947e-05, 'samples': 24997248, 'steps': 130193, 'loss/train': 0.646669864654541} 08/31/2021 12:49:00 - INFO - __main__ - Step 130195: {'lr': 2.1770754401814947e-05, 'samples': 24997440, 'steps': 130194, 'loss/train': 0.5618597269058228} 08/31/2021 12:49:02 - INFO - __main__ - Step 130196: {'lr': 2.1768588530486995e-05, 'samples': 24997632, 'steps': 130195, 'loss/train': 1.4879264831542969} 08/31/2021 12:49:02 - INFO - __main__ - Step 130197: {'lr': 2.1766422761996612e-05, 'samples': 24997824, 'steps': 130196, 'loss/train': 1.2593295574188232} 08/31/2021 12:49:03 - INFO - __main__ - Step 130198: {'lr': 2.1764257096344746e-05, 'samples': 24998016, 'steps': 130197, 'loss/train': 1.4914394617080688} 08/31/2021 12:49:03 - INFO - __main__ - Step 130199: {'lr': 2.176209153353237e-05, 'samples': 24998208, 'steps': 130198, 'loss/train': 0.5751422047615051} 08/31/2021 12:49:03 - INFO - __main__ - Step 130200: {'lr': 2.1759926073560477e-05, 'samples': 24998400, 'steps': 130199, 'loss/train': 1.2975797653198242} 08/31/2021 12:49:04 - INFO - __main__ - Step 130201: {'lr': 2.175776071643007e-05, 'samples': 24998592, 'steps': 130200, 'loss/train': 1.634691596031189} 08/31/2021 12:49:05 - INFO - __main__ - Step 130202: {'lr': 2.1755595462142062e-05, 'samples': 24998784, 'steps': 130201, 'loss/train': 1.681723952293396} 08/31/2021 12:49:06 - INFO - __main__ - Step 130203: {'lr': 2.1753430310697458e-05, 'samples': 24998976, 'steps': 130202, 'loss/train': 1.457748293876648} 08/31/2021 12:49:06 - INFO - __main__ - Step 130204: {'lr': 2.1751265262097307e-05, 'samples': 24999168, 'steps': 130203, 'loss/train': 0.830829381942749} 08/31/2021 12:49:07 - INFO - __main__ - Step 130205: {'lr': 2.1749100316342447e-05, 'samples': 24999360, 'steps': 130204, 'loss/train': 1.0769115686416626} 08/31/2021 12:49:07 - INFO - __main__ - Step 130206: {'lr': 2.1746935473433927e-05, 'samples': 24999552, 'steps': 130205, 'loss/train': 0.11324234306812286} 08/31/2021 12:49:09 - INFO - __main__ - Step 130207: {'lr': 2.174477073337272e-05, 'samples': 24999744, 'steps': 130206, 'loss/train': 1.1462962627410889} 08/31/2021 12:49:09 - INFO - __main__ - Step 130208: {'lr': 2.17426060961598e-05, 'samples': 24999936, 'steps': 130207, 'loss/train': 1.394501805305481} 08/31/2021 12:49:09 - INFO - __main__ - Step 130209: {'lr': 2.174044156179614e-05, 'samples': 25000128, 'steps': 130208, 'loss/train': 0.8350774049758911} 08/31/2021 12:49:10 - INFO - __main__ - Step 130210: {'lr': 2.1738277130282702e-05, 'samples': 25000320, 'steps': 130209, 'loss/train': 0.9570454955101013} 08/31/2021 12:49:10 - INFO - __main__ - Step 130211: {'lr': 2.1736112801620495e-05, 'samples': 25000512, 'steps': 130210, 'loss/train': 0.9845556020736694} 08/31/2021 12:49:12 - INFO - __main__ - Step 130212: {'lr': 2.173394857581046e-05, 'samples': 25000704, 'steps': 130211, 'loss/train': 1.074091911315918} 08/31/2021 12:49:12 - INFO - __main__ - Step 130213: {'lr': 2.1731784452853565e-05, 'samples': 25000896, 'steps': 130212, 'loss/train': 0.11562529951334} 08/31/2021 12:49:12 - INFO - __main__ - Step 130214: {'lr': 2.172962043275084e-05, 'samples': 25001088, 'steps': 130213, 'loss/train': 0.814224898815155} 08/31/2021 12:49:13 - INFO - __main__ - Step 130215: {'lr': 2.1727456515503203e-05, 'samples': 25001280, 'steps': 130214, 'loss/train': 1.152268409729004} 08/31/2021 12:49:13 - INFO - __main__ - Step 130216: {'lr': 2.172529270111165e-05, 'samples': 25001472, 'steps': 130215, 'loss/train': 0.7705377340316772} 08/31/2021 12:49:13 - INFO - __main__ - Step 130217: {'lr': 2.172312898957718e-05, 'samples': 25001664, 'steps': 130216, 'loss/train': 1.0924561023712158} 08/31/2021 12:49:16 - INFO - __main__ - Step 130218: {'lr': 2.1720965380900764e-05, 'samples': 25001856, 'steps': 130217, 'loss/train': 0.9877186417579651} 08/31/2021 12:49:16 - INFO - __main__ - Step 130219: {'lr': 2.1718801875083323e-05, 'samples': 25002048, 'steps': 130218, 'loss/train': 0.7643334269523621} 08/31/2021 12:49:17 - INFO - __main__ - Step 130220: {'lr': 2.1716638472125877e-05, 'samples': 25002240, 'steps': 130219, 'loss/train': 1.5217673778533936} 08/31/2021 12:49:17 - INFO - __main__ - Step 130221: {'lr': 2.1714475172029402e-05, 'samples': 25002432, 'steps': 130220, 'loss/train': 0.49022188782691956} 08/31/2021 12:49:17 - INFO - __main__ - Step 130222: {'lr': 2.1712311974794842e-05, 'samples': 25002624, 'steps': 130221, 'loss/train': 1.0827257633209229} 08/31/2021 12:49:19 - INFO - __main__ - Step 130223: {'lr': 2.171014888042319e-05, 'samples': 25002816, 'steps': 130222, 'loss/train': 0.8127891421318054} 08/31/2021 12:49:19 - INFO - __main__ - Step 130224: {'lr': 2.170798588891543e-05, 'samples': 25003008, 'steps': 130223, 'loss/train': 1.2502093315124512} 08/31/2021 12:49:20 - INFO - __main__ - Step 130225: {'lr': 2.170582300027252e-05, 'samples': 25003200, 'steps': 130224, 'loss/train': 0.4460681974887848} 08/31/2021 12:49:20 - INFO - __main__ - Step 130226: {'lr': 2.1703660214495435e-05, 'samples': 25003392, 'steps': 130225, 'loss/train': 1.068556785583496} 08/31/2021 12:49:20 - INFO - __main__ - Step 130227: {'lr': 2.170149753158518e-05, 'samples': 25003584, 'steps': 130226, 'loss/train': 1.60588538646698} 08/31/2021 12:49:22 - INFO - __main__ - Step 130228: {'lr': 2.169933495154269e-05, 'samples': 25003776, 'steps': 130227, 'loss/train': 1.005850911140442} 08/31/2021 12:49:22 - INFO - __main__ - Step 130229: {'lr': 2.1697172474368977e-05, 'samples': 25003968, 'steps': 130228, 'loss/train': 0.418399840593338} 08/31/2021 12:49:23 - INFO - __main__ - Step 130230: {'lr': 2.1695010100065e-05, 'samples': 25004160, 'steps': 130229, 'loss/train': 1.121224284172058} 08/31/2021 12:49:23 - INFO - __main__ - Step 130231: {'lr': 2.1692847828631734e-05, 'samples': 25004352, 'steps': 130230, 'loss/train': 0.4578295350074768} 08/31/2021 12:49:23 - INFO - __main__ - Step 130232: {'lr': 2.1690685660070124e-05, 'samples': 25004544, 'steps': 130231, 'loss/train': 1.4148645401000977} 08/31/2021 12:49:25 - INFO - __main__ - Step 130233: {'lr': 2.168852359438117e-05, 'samples': 25004736, 'steps': 130232, 'loss/train': 0.759617805480957} 08/31/2021 12:49:25 - INFO - __main__ - Step 130234: {'lr': 2.168636163156587e-05, 'samples': 25004928, 'steps': 130233, 'loss/train': 0.8613464832305908} 08/31/2021 12:49:26 - INFO - __main__ - Step 130235: {'lr': 2.168419977162514e-05, 'samples': 25005120, 'steps': 130234, 'loss/train': 0.8450548648834229} 08/31/2021 12:49:26 - INFO - __main__ - Step 130236: {'lr': 2.168203801455998e-05, 'samples': 25005312, 'steps': 130235, 'loss/train': 1.0485622882843018} 08/31/2021 12:49:26 - INFO - __main__ - Step 130237: {'lr': 2.1679876360371387e-05, 'samples': 25005504, 'steps': 130236, 'loss/train': 1.1384505033493042} 08/31/2021 12:49:28 - INFO - __main__ - Step 130238: {'lr': 2.1677714809060334e-05, 'samples': 25005696, 'steps': 130237, 'loss/train': 1.3951821327209473} 08/31/2021 12:49:28 - INFO - __main__ - Step 130239: {'lr': 2.1675553360627738e-05, 'samples': 25005888, 'steps': 130238, 'loss/train': 1.3251292705535889} 08/31/2021 12:49:29 - INFO - __main__ - Step 130240: {'lr': 2.167339201507465e-05, 'samples': 25006080, 'steps': 130239, 'loss/train': 1.4936257600784302} 08/31/2021 12:49:29 - INFO - __main__ - Step 130241: {'lr': 2.167123077240199e-05, 'samples': 25006272, 'steps': 130240, 'loss/train': 0.0921272486448288} 08/31/2021 12:49:29 - INFO - __main__ - Step 130242: {'lr': 2.1669069632610755e-05, 'samples': 25006464, 'steps': 130241, 'loss/train': 1.5976009368896484} 08/31/2021 12:49:31 - INFO - __main__ - Step 130243: {'lr': 2.1666908595701917e-05, 'samples': 25006656, 'steps': 130242, 'loss/train': 0.04508930817246437} 08/31/2021 12:49:31 - INFO - __main__ - Step 130244: {'lr': 2.1664747661676475e-05, 'samples': 25006848, 'steps': 130243, 'loss/train': 1.4442925453186035} 08/31/2021 12:49:32 - INFO - __main__ - Step 130245: {'lr': 2.1662586830535347e-05, 'samples': 25007040, 'steps': 130244, 'loss/train': 0.6255927085876465} 08/31/2021 12:49:32 - INFO - __main__ - Step 130246: {'lr': 2.1660426102279528e-05, 'samples': 25007232, 'steps': 130245, 'loss/train': 1.0701649188995361} 08/31/2021 12:49:32 - INFO - __main__ - Step 130247: {'lr': 2.1658265476910022e-05, 'samples': 25007424, 'steps': 130246, 'loss/train': 0.6499451398849487} 08/31/2021 12:49:34 - INFO - __main__ - Step 130248: {'lr': 2.165610495442774e-05, 'samples': 25007616, 'steps': 130247, 'loss/train': 1.7594656944274902} 08/31/2021 12:49:35 - INFO - __main__ - Step 130249: {'lr': 2.1653944534833713e-05, 'samples': 25007808, 'steps': 130248, 'loss/train': 0.8464271426200867} 08/31/2021 12:49:35 - INFO - __main__ - Step 130250: {'lr': 2.1651784218128885e-05, 'samples': 25008000, 'steps': 130249, 'loss/train': 1.2392138242721558} 08/31/2021 12:49:35 - INFO - __main__ - Step 130251: {'lr': 2.164962400431425e-05, 'samples': 25008192, 'steps': 130250, 'loss/train': 1.1959867477416992} 08/31/2021 12:49:36 - INFO - __main__ - Step 130252: {'lr': 2.1647463893390784e-05, 'samples': 25008384, 'steps': 130251, 'loss/train': 1.4903664588928223} 08/31/2021 12:49:37 - INFO - __main__ - Step 130253: {'lr': 2.164530388535943e-05, 'samples': 25008576, 'steps': 130252, 'loss/train': 0.0458698645234108} 08/31/2021 12:49:38 - INFO - __main__ - Step 130254: {'lr': 2.1643143980221157e-05, 'samples': 25008768, 'steps': 130253, 'loss/train': 1.30815589427948} 08/31/2021 12:49:38 - INFO - __main__ - Step 130255: {'lr': 2.1640984177976995e-05, 'samples': 25008960, 'steps': 130254, 'loss/train': 1.2024527788162231} 08/31/2021 12:49:38 - INFO - __main__ - Step 130256: {'lr': 2.1638824478627862e-05, 'samples': 25009152, 'steps': 130255, 'loss/train': 1.1601718664169312} 08/31/2021 12:49:39 - INFO - __main__ - Step 130257: {'lr': 2.163666488217475e-05, 'samples': 25009344, 'steps': 130256, 'loss/train': 1.2799980640411377} 08/31/2021 12:49:40 - INFO - __main__ - Step 130258: {'lr': 2.163450538861869e-05, 'samples': 25009536, 'steps': 130257, 'loss/train': 0.9943130016326904} 08/31/2021 12:49:41 - INFO - __main__ - Step 130259: {'lr': 2.1632345997960547e-05, 'samples': 25009728, 'steps': 130258, 'loss/train': 1.147007942199707} 08/31/2021 12:49:41 - INFO - __main__ - Step 130260: {'lr': 2.1630186710201337e-05, 'samples': 25009920, 'steps': 130259, 'loss/train': 0.6408644914627075} 08/31/2021 12:49:41 - INFO - __main__ - Step 130261: {'lr': 2.162802752534207e-05, 'samples': 25010112, 'steps': 130260, 'loss/train': 1.0570852756500244} 08/31/2021 12:49:42 - INFO - __main__ - Step 130262: {'lr': 2.1625868443383657e-05, 'samples': 25010304, 'steps': 130261, 'loss/train': 5.75823974609375} 08/31/2021 12:49:42 - INFO - __main__ - Step 130263: {'lr': 2.1623709464327123e-05, 'samples': 25010496, 'steps': 130262, 'loss/train': 1.1028039455413818} 08/31/2021 12:49:44 - INFO - __main__ - Step 130264: {'lr': 2.1621550588173417e-05, 'samples': 25010688, 'steps': 130263, 'loss/train': 1.2079073190689087} 08/31/2021 12:49:45 - INFO - __main__ - Step 130265: {'lr': 2.1619391814923504e-05, 'samples': 25010880, 'steps': 130264, 'loss/train': 0.11455662548542023} 08/31/2021 12:49:45 - INFO - __main__ - Step 130266: {'lr': 2.1617233144578364e-05, 'samples': 25011072, 'steps': 130265, 'loss/train': 0.8316991925239563} 08/31/2021 12:49:45 - INFO - __main__ - Step 130267: {'lr': 2.161507457713899e-05, 'samples': 25011264, 'steps': 130266, 'loss/train': 0.5273160338401794} 08/31/2021 12:49:46 - INFO - __main__ - Step 130268: {'lr': 2.161291611260635e-05, 'samples': 25011456, 'steps': 130267, 'loss/train': 0.8987966775894165} 08/31/2021 12:49:46 - INFO - __main__ - Step 130269: {'lr': 2.1610757750981395e-05, 'samples': 25011648, 'steps': 130268, 'loss/train': 1.1684483289718628} 08/31/2021 12:49:48 - INFO - __main__ - Step 130270: {'lr': 2.1608599492265153e-05, 'samples': 25011840, 'steps': 130269, 'loss/train': 1.369310736656189} 08/31/2021 12:49:48 - INFO - __main__ - Step 130271: {'lr': 2.1606441336458504e-05, 'samples': 25012032, 'steps': 130270, 'loss/train': 0.5968428254127502} 08/31/2021 12:49:49 - INFO - __main__ - Step 130272: {'lr': 2.1604283283562452e-05, 'samples': 25012224, 'steps': 130271, 'loss/train': 0.6425419449806213} 08/31/2021 12:49:49 - INFO - __main__ - Step 130273: {'lr': 2.1602125333578027e-05, 'samples': 25012416, 'steps': 130272, 'loss/train': 0.5112605094909668} 08/31/2021 12:49:50 - INFO - __main__ - Step 130274: {'lr': 2.159996748650614e-05, 'samples': 25012608, 'steps': 130273, 'loss/train': 1.369454264640808} 08/31/2021 12:49:51 - INFO - __main__ - Step 130275: {'lr': 2.1597809742347762e-05, 'samples': 25012800, 'steps': 130274, 'loss/train': 1.3940188884735107} 08/31/2021 12:49:51 - INFO - __main__ - Step 130276: {'lr': 2.1595652101103895e-05, 'samples': 25012992, 'steps': 130275, 'loss/train': 1.427605390548706} 08/31/2021 12:49:52 - INFO - __main__ - Step 130277: {'lr': 2.1593494562775513e-05, 'samples': 25013184, 'steps': 130276, 'loss/train': 0.9687768816947937} 08/31/2021 12:49:52 - INFO - __main__ - Step 130278: {'lr': 2.159133712736358e-05, 'samples': 25013376, 'steps': 130277, 'loss/train': 0.3814876675605774} 08/31/2021 12:49:53 - INFO - __main__ - Step 130279: {'lr': 2.1589179794869073e-05, 'samples': 25013568, 'steps': 130278, 'loss/train': 0.6589537858963013} 08/31/2021 12:49:54 - INFO - __main__ - Step 130280: {'lr': 2.1587022565292935e-05, 'samples': 25013760, 'steps': 130279, 'loss/train': 0.7355848550796509} 08/31/2021 12:49:55 - INFO - __main__ - Step 130281: {'lr': 2.158486543863622e-05, 'samples': 25013952, 'steps': 130280, 'loss/train': 1.057401418685913} 08/31/2021 12:49:55 - INFO - __main__ - Step 130282: {'lr': 2.1582708414899788e-05, 'samples': 25014144, 'steps': 130281, 'loss/train': 0.03350967913866043} 08/31/2021 12:49:56 - INFO - __main__ - Step 130283: {'lr': 2.1580551494084666e-05, 'samples': 25014336, 'steps': 130282, 'loss/train': 1.0545110702514648} 08/31/2021 12:49:56 - INFO - __main__ - Step 130284: {'lr': 2.1578394676191826e-05, 'samples': 25014528, 'steps': 130283, 'loss/train': 0.054730482399463654} 08/31/2021 12:49:58 - INFO - __main__ - Step 130285: {'lr': 2.1576237961222238e-05, 'samples': 25014720, 'steps': 130284, 'loss/train': 1.2139480113983154} 08/31/2021 12:49:58 - INFO - __main__ - Step 130286: {'lr': 2.1574081349176876e-05, 'samples': 25014912, 'steps': 130285, 'loss/train': 5.6946702003479} 08/31/2021 12:49:59 - INFO - __main__ - Step 130287: {'lr': 2.1571924840056684e-05, 'samples': 25015104, 'steps': 130286, 'loss/train': 0.202443465590477} 08/31/2021 12:49:59 - INFO - __main__ - Step 130288: {'lr': 2.1569768433862687e-05, 'samples': 25015296, 'steps': 130287, 'loss/train': 0.7293799519538879} 08/31/2021 12:49:59 - INFO - __main__ - Step 130289: {'lr': 2.1567612130595797e-05, 'samples': 25015488, 'steps': 130288, 'loss/train': 1.0677260160446167} 08/31/2021 12:50:00 - INFO - __main__ - Step 130290: {'lr': 2.156545593025705e-05, 'samples': 25015680, 'steps': 130289, 'loss/train': 0.5316203236579895} 08/31/2021 12:50:01 - INFO - __main__ - Step 130291: {'lr': 2.1563299832847356e-05, 'samples': 25015872, 'steps': 130290, 'loss/train': 0.6440563201904297} 08/31/2021 12:50:02 - INFO - __main__ - Step 130292: {'lr': 2.156114383836777e-05, 'samples': 25016064, 'steps': 130291, 'loss/train': 0.8678550720214844} 08/31/2021 12:50:02 - INFO - __main__ - Step 130293: {'lr': 2.155898794681918e-05, 'samples': 25016256, 'steps': 130292, 'loss/train': 1.2953274250030518} 08/31/2021 12:50:02 - INFO - __main__ - Step 130294: {'lr': 2.155683215820256e-05, 'samples': 25016448, 'steps': 130293, 'loss/train': 0.46723130345344543} 08/31/2021 12:50:03 - INFO - __main__ - Step 130295: {'lr': 2.155467647251891e-05, 'samples': 25016640, 'steps': 130294, 'loss/train': 1.8730242252349854} 08/31/2021 12:50:04 - INFO - __main__ - Step 130296: {'lr': 2.1552520889769194e-05, 'samples': 25016832, 'steps': 130295, 'loss/train': 1.4688289165496826} 08/31/2021 12:50:05 - INFO - __main__ - Step 130297: {'lr': 2.155036540995442e-05, 'samples': 25017024, 'steps': 130296, 'loss/train': 0.49808868765830994} 08/31/2021 12:50:05 - INFO - __main__ - Step 130298: {'lr': 2.15482100330755e-05, 'samples': 25017216, 'steps': 130297, 'loss/train': 1.6470297574996948} 08/31/2021 12:50:05 - INFO - __main__ - Step 130299: {'lr': 2.1546054759133432e-05, 'samples': 25017408, 'steps': 130298, 'loss/train': 1.5184253454208374} 08/31/2021 12:50:06 - INFO - __main__ - Step 130300: {'lr': 2.154389958812916e-05, 'samples': 25017600, 'steps': 130299, 'loss/train': 1.113327145576477} 08/31/2021 12:50:07 - INFO - __main__ - Step 130301: {'lr': 2.1541744520063716e-05, 'samples': 25017792, 'steps': 130300, 'loss/train': 1.6809587478637695} 08/31/2021 12:50:08 - INFO - __main__ - Step 130302: {'lr': 2.153958955493804e-05, 'samples': 25017984, 'steps': 130301, 'loss/train': 1.0784705877304077} 08/31/2021 12:50:08 - INFO - __main__ - Step 130303: {'lr': 2.1537434692753127e-05, 'samples': 25018176, 'steps': 130302, 'loss/train': 1.110229253768921} 08/31/2021 12:50:08 - INFO - __main__ - Step 130304: {'lr': 2.153527993350987e-05, 'samples': 25018368, 'steps': 130303, 'loss/train': 0.7914119362831116} 08/31/2021 12:50:09 - INFO - __main__ - Step 130305: {'lr': 2.1533125277209327e-05, 'samples': 25018560, 'steps': 130304, 'loss/train': 0.5205180048942566} 08/31/2021 12:50:10 - INFO - __main__ - Step 130306: {'lr': 2.1530970723852404e-05, 'samples': 25018752, 'steps': 130305, 'loss/train': 0.9701566100120544} 08/31/2021 12:50:11 - INFO - __main__ - Step 130307: {'lr': 2.1528816273440084e-05, 'samples': 25018944, 'steps': 130306, 'loss/train': 0.8412493467330933} 08/31/2021 12:50:11 - INFO - __main__ - Step 130308: {'lr': 2.1526661925973384e-05, 'samples': 25019136, 'steps': 130307, 'loss/train': 2.0547242164611816} 08/31/2021 12:50:11 - INFO - __main__ - Step 130309: {'lr': 2.1524507681453225e-05, 'samples': 25019328, 'steps': 130308, 'loss/train': 0.8941518068313599} 08/31/2021 12:50:12 - INFO - __main__ - Step 130310: {'lr': 2.1522353539880607e-05, 'samples': 25019520, 'steps': 130309, 'loss/train': 0.8679894208908081} 08/31/2021 12:50:12 - INFO - __main__ - Step 130311: {'lr': 2.15201995012565e-05, 'samples': 25019712, 'steps': 130310, 'loss/train': 0.6671223640441895} 08/31/2021 12:50:14 - INFO - __main__ - Step 130312: {'lr': 2.1518045565581845e-05, 'samples': 25019904, 'steps': 130311, 'loss/train': 0.9340175986289978} 08/31/2021 12:50:14 - INFO - __main__ - Step 130313: {'lr': 2.1515891732857646e-05, 'samples': 25020096, 'steps': 130312, 'loss/train': 1.5028076171875} 08/31/2021 12:50:14 - INFO - __main__ - Step 130314: {'lr': 2.15137380030849e-05, 'samples': 25020288, 'steps': 130313, 'loss/train': 1.0538716316223145} 08/31/2021 12:50:15 - INFO - __main__ - Step 130315: {'lr': 2.151158437626452e-05, 'samples': 25020480, 'steps': 130314, 'loss/train': 1.7190669775009155} 08/31/2021 12:50:15 - INFO - __main__ - Step 130316: {'lr': 2.1509430852397454e-05, 'samples': 25020672, 'steps': 130315, 'loss/train': 1.156561255455017} 08/31/2021 12:50:17 - INFO - __main__ - Step 130317: {'lr': 2.150727743148473e-05, 'samples': 25020864, 'steps': 130316, 'loss/train': 1.364508867263794} 08/31/2021 12:50:17 - INFO - __main__ - Step 130318: {'lr': 2.1505124113527315e-05, 'samples': 25021056, 'steps': 130317, 'loss/train': 0.19604943692684174} 08/31/2021 12:50:17 - INFO - __main__ - Step 130319: {'lr': 2.1502970898526125e-05, 'samples': 25021248, 'steps': 130318, 'loss/train': 0.7593467235565186} 08/31/2021 12:50:18 - INFO - __main__ - Step 130320: {'lr': 2.150081778648222e-05, 'samples': 25021440, 'steps': 130319, 'loss/train': 0.0276924017816782} 08/31/2021 12:50:18 - INFO - __main__ - Step 130321: {'lr': 2.149866477739648e-05, 'samples': 25021632, 'steps': 130320, 'loss/train': 0.7623590230941772} 08/31/2021 12:50:20 - INFO - __main__ - Step 130322: {'lr': 2.149651187126994e-05, 'samples': 25021824, 'steps': 130321, 'loss/train': 1.4358872175216675} 08/31/2021 12:50:20 - INFO - __main__ - Step 130323: {'lr': 2.1494359068103543e-05, 'samples': 25022016, 'steps': 130322, 'loss/train': 0.2179599404335022} 08/31/2021 12:50:20 - INFO - __main__ - Step 130324: {'lr': 2.1492206367898254e-05, 'samples': 25022208, 'steps': 130323, 'loss/train': 0.7116377949714661} 08/31/2021 12:50:21 - INFO - __main__ - Step 130325: {'lr': 2.1490053770655076e-05, 'samples': 25022400, 'steps': 130324, 'loss/train': 0.20019686222076416} 08/31/2021 12:50:21 - INFO - __main__ - Step 130326: {'lr': 2.1487901276374956e-05, 'samples': 25022592, 'steps': 130325, 'loss/train': 1.4332619905471802} 08/31/2021 12:50:24 - INFO - __main__ - Step 130327: {'lr': 2.1485748885058833e-05, 'samples': 25022784, 'steps': 130326, 'loss/train': 1.791642665863037} 08/31/2021 12:50:24 - INFO - __main__ - Step 130328: {'lr': 2.1483596596707706e-05, 'samples': 25022976, 'steps': 130327, 'loss/train': 1.147060513496399} 08/31/2021 12:50:24 - INFO - __main__ - Step 130329: {'lr': 2.1481444411322548e-05, 'samples': 25023168, 'steps': 130328, 'loss/train': 0.017556557431817055} 08/31/2021 12:50:25 - INFO - __main__ - Step 130330: {'lr': 2.1479292328904304e-05, 'samples': 25023360, 'steps': 130329, 'loss/train': 0.6992771625518799} 08/31/2021 12:50:25 - INFO - __main__ - Step 130331: {'lr': 2.1477140349454e-05, 'samples': 25023552, 'steps': 130330, 'loss/train': 0.5686824917793274} 08/31/2021 12:50:26 - INFO - __main__ - Step 130332: {'lr': 2.147498847297255e-05, 'samples': 25023744, 'steps': 130331, 'loss/train': 1.0798308849334717} 08/31/2021 12:50:27 - INFO - __main__ - Step 130333: {'lr': 2.1472836699460957e-05, 'samples': 25023936, 'steps': 130332, 'loss/train': 1.4077779054641724} 08/31/2021 12:50:28 - INFO - __main__ - Step 130334: {'lr': 2.147068502892016e-05, 'samples': 25024128, 'steps': 130333, 'loss/train': 0.9722586274147034} 08/31/2021 12:50:28 - INFO - __main__ - Step 130335: {'lr': 2.1468533461351165e-05, 'samples': 25024320, 'steps': 130334, 'loss/train': 0.9842684864997864} 08/31/2021 12:50:28 - INFO - __main__ - Step 130336: {'lr': 2.1466381996754907e-05, 'samples': 25024512, 'steps': 130335, 'loss/train': 1.3291329145431519} 08/31/2021 12:50:29 - INFO - __main__ - Step 130337: {'lr': 2.1464230635132364e-05, 'samples': 25024704, 'steps': 130336, 'loss/train': 1.3718388080596924} 08/31/2021 12:50:30 - INFO - __main__ - Step 130338: {'lr': 2.1462079376484534e-05, 'samples': 25024896, 'steps': 130337, 'loss/train': 1.0836390256881714} 08/31/2021 12:50:31 - INFO - __main__ - Step 130339: {'lr': 2.1459928220812386e-05, 'samples': 25025088, 'steps': 130338, 'loss/train': 1.5503844022750854} 08/31/2021 12:50:31 - INFO - __main__ - Step 130340: {'lr': 2.1457777168116836e-05, 'samples': 25025280, 'steps': 130339, 'loss/train': 0.7485823035240173} 08/31/2021 12:50:31 - INFO - __main__ - Step 130341: {'lr': 2.1455626218398887e-05, 'samples': 25025472, 'steps': 130340, 'loss/train': 1.381367564201355} 08/31/2021 12:50:32 - INFO - __main__ - Step 130342: {'lr': 2.145347537165951e-05, 'samples': 25025664, 'steps': 130341, 'loss/train': 0.785659909248352} 08/31/2021 12:50:33 - INFO - __main__ - Step 130343: {'lr': 2.145132462789967e-05, 'samples': 25025856, 'steps': 130342, 'loss/train': 0.9265235066413879} 08/31/2021 12:50:34 - INFO - __main__ - Step 130344: {'lr': 2.144917398712032e-05, 'samples': 25026048, 'steps': 130343, 'loss/train': 0.8290516138076782} 08/31/2021 12:50:34 - INFO - __main__ - Step 130345: {'lr': 2.144702344932245e-05, 'samples': 25026240, 'steps': 130344, 'loss/train': 0.8390898704528809} 08/31/2021 12:50:34 - INFO - __main__ - Step 130346: {'lr': 2.1444873014507036e-05, 'samples': 25026432, 'steps': 130345, 'loss/train': 1.1099457740783691} 08/31/2021 12:50:35 - INFO - __main__ - Step 130347: {'lr': 2.1442722682675024e-05, 'samples': 25026624, 'steps': 130346, 'loss/train': 0.9451988339424133} 08/31/2021 12:50:35 - INFO - __main__ - Step 130348: {'lr': 2.144057245382741e-05, 'samples': 25026816, 'steps': 130347, 'loss/train': 0.9917973279953003} 08/31/2021 12:50:37 - INFO - __main__ - Step 130349: {'lr': 2.143842232796514e-05, 'samples': 25027008, 'steps': 130348, 'loss/train': 0.883570671081543} 08/31/2021 12:50:37 - INFO - __main__ - Step 130350: {'lr': 2.1436272305089182e-05, 'samples': 25027200, 'steps': 130349, 'loss/train': 2.314418077468872} 08/31/2021 12:50:38 - INFO - __main__ - Step 130351: {'lr': 2.1434122385200537e-05, 'samples': 25027392, 'steps': 130350, 'loss/train': 0.8475767970085144} 08/31/2021 12:50:38 - INFO - __main__ - Step 130352: {'lr': 2.143197256830015e-05, 'samples': 25027584, 'steps': 130351, 'loss/train': 1.1255706548690796} 08/31/2021 12:50:38 - INFO - __main__ - Step 130353: {'lr': 2.142982285438899e-05, 'samples': 25027776, 'steps': 130352, 'loss/train': 1.1824363470077515} 08/31/2021 12:50:40 - INFO - __main__ - Step 130354: {'lr': 2.1427673243468004e-05, 'samples': 25027968, 'steps': 130353, 'loss/train': 0.5792552828788757} 08/31/2021 12:50:40 - INFO - __main__ - Step 130355: {'lr': 2.142552373553819e-05, 'samples': 25028160, 'steps': 130354, 'loss/train': 0.9174904227256775} 08/31/2021 12:50:41 - INFO - __main__ - Step 130356: {'lr': 2.1423374330600487e-05, 'samples': 25028352, 'steps': 130355, 'loss/train': 0.7225592136383057} 08/31/2021 12:50:41 - INFO - __main__ - Step 130357: {'lr': 2.14212250286559e-05, 'samples': 25028544, 'steps': 130356, 'loss/train': 0.6466533541679382} 08/31/2021 12:50:41 - INFO - __main__ - Step 130358: {'lr': 2.141907582970537e-05, 'samples': 25028736, 'steps': 130357, 'loss/train': 0.6212326288223267} 08/31/2021 12:50:43 - INFO - __main__ - Step 130359: {'lr': 2.1416926733749896e-05, 'samples': 25028928, 'steps': 130358, 'loss/train': 0.4535503685474396} 08/31/2021 12:50:43 - INFO - __main__ - Step 130360: {'lr': 2.1414777740790425e-05, 'samples': 25029120, 'steps': 130359, 'loss/train': 1.248249888420105} 08/31/2021 12:50:44 - INFO - __main__ - Step 130361: {'lr': 2.1412628850827898e-05, 'samples': 25029312, 'steps': 130360, 'loss/train': 0.9285014867782593} 08/31/2021 12:50:44 - INFO - __main__ - Step 130362: {'lr': 2.141048006386334e-05, 'samples': 25029504, 'steps': 130361, 'loss/train': 0.8862007856369019} 08/31/2021 12:50:44 - INFO - __main__ - Step 130363: {'lr': 2.14083313798977e-05, 'samples': 25029696, 'steps': 130362, 'loss/train': 1.4965511560440063} 08/31/2021 12:50:46 - INFO - __main__ - Step 130364: {'lr': 2.1406182798931917e-05, 'samples': 25029888, 'steps': 130363, 'loss/train': 1.9552819728851318} 08/31/2021 12:50:46 - INFO - __main__ - Step 130365: {'lr': 2.140403432096705e-05, 'samples': 25030080, 'steps': 130364, 'loss/train': 1.4282976388931274} 08/31/2021 12:50:47 - INFO - __main__ - Step 130366: {'lr': 2.1401885946003924e-05, 'samples': 25030272, 'steps': 130365, 'loss/train': 1.2362662553787231} 08/31/2021 12:50:47 - INFO - __main__ - Step 130367: {'lr': 2.13997376740436e-05, 'samples': 25030464, 'steps': 130366, 'loss/train': 0.6588882207870483} 08/31/2021 12:50:47 - INFO - __main__ - Step 130368: {'lr': 2.1397589505087024e-05, 'samples': 25030656, 'steps': 130367, 'loss/train': 0.5094380974769592} 08/31/2021 12:50:48 - INFO - __main__ - Step 130369: {'lr': 2.139544143913516e-05, 'samples': 25030848, 'steps': 130368, 'loss/train': 1.5613094568252563} 08/31/2021 12:50:50 - INFO - __main__ - Step 130370: {'lr': 2.1393293476188985e-05, 'samples': 25031040, 'steps': 130369, 'loss/train': 0.9740723967552185} 08/31/2021 12:50:50 - INFO - __main__ - Step 130371: {'lr': 2.139114561624947e-05, 'samples': 25031232, 'steps': 130370, 'loss/train': 1.39156973361969} 08/31/2021 12:50:50 - INFO - __main__ - Step 130372: {'lr': 2.138899785931758e-05, 'samples': 25031424, 'steps': 130371, 'loss/train': 0.8717807531356812} 08/31/2021 12:50:51 - INFO - __main__ - Step 130373: {'lr': 2.138685020539427e-05, 'samples': 25031616, 'steps': 130372, 'loss/train': 1.0250097513198853} 08/31/2021 12:50:51 - INFO - __main__ - Step 130374: {'lr': 2.1384702654480502e-05, 'samples': 25031808, 'steps': 130373, 'loss/train': 0.33319345116615295} 08/31/2021 12:50:53 - INFO - __main__ - Step 130375: {'lr': 2.138255520657728e-05, 'samples': 25032000, 'steps': 130374, 'loss/train': 1.305631399154663} 08/31/2021 12:50:53 - INFO - __main__ - Step 130376: {'lr': 2.1380407861685545e-05, 'samples': 25032192, 'steps': 130375, 'loss/train': 0.6917910575866699} 08/31/2021 12:50:53 - INFO - __main__ - Step 130377: {'lr': 2.13782606198063e-05, 'samples': 25032384, 'steps': 130376, 'loss/train': 0.7303351163864136} 08/31/2021 12:50:54 - INFO - __main__ - Step 130378: {'lr': 2.1376113480940458e-05, 'samples': 25032576, 'steps': 130377, 'loss/train': 0.7267049551010132} 08/31/2021 12:50:54 - INFO - __main__ - Step 130379: {'lr': 2.1373966445089043e-05, 'samples': 25032768, 'steps': 130378, 'loss/train': 0.9764220714569092} 08/31/2021 12:50:55 - INFO - __main__ - Step 130380: {'lr': 2.137181951225295e-05, 'samples': 25032960, 'steps': 130379, 'loss/train': 1.5385011434555054} 08/31/2021 12:50:57 - INFO - __main__ - Step 130381: {'lr': 2.13696726824332e-05, 'samples': 25033152, 'steps': 130380, 'loss/train': 1.5550339221954346} 08/31/2021 12:50:57 - INFO - __main__ - Step 130382: {'lr': 2.136752595563074e-05, 'samples': 25033344, 'steps': 130381, 'loss/train': 0.9510478377342224} 08/31/2021 12:50:57 - INFO - __main__ - Step 130383: {'lr': 2.136537933184654e-05, 'samples': 25033536, 'steps': 130382, 'loss/train': 1.089210033416748} 08/31/2021 12:50:58 - INFO - __main__ - Step 130384: {'lr': 2.13632328110816e-05, 'samples': 25033728, 'steps': 130383, 'loss/train': 1.177748680114746} 08/31/2021 12:50:58 - INFO - __main__ - Step 130385: {'lr': 2.136108639333684e-05, 'samples': 25033920, 'steps': 130384, 'loss/train': 0.9705494046211243} 08/31/2021 12:51:00 - INFO - __main__ - Step 130386: {'lr': 2.135894007861325e-05, 'samples': 25034112, 'steps': 130385, 'loss/train': 0.9446346759796143} 08/31/2021 12:51:00 - INFO - __main__ - Step 130387: {'lr': 2.1356793866911777e-05, 'samples': 25034304, 'steps': 130386, 'loss/train': 0.13160179555416107} 08/31/2021 12:51:00 - INFO - __main__ - Step 130388: {'lr': 2.1354647758233424e-05, 'samples': 25034496, 'steps': 130387, 'loss/train': 0.7091240882873535} 08/31/2021 12:51:01 - INFO - __main__ - Step 130389: {'lr': 2.1352501752579106e-05, 'samples': 25034688, 'steps': 130388, 'loss/train': 1.4405173063278198} 08/31/2021 12:51:01 - INFO - __main__ - Step 130390: {'lr': 2.135035584994985e-05, 'samples': 25034880, 'steps': 130389, 'loss/train': 1.3017712831497192} 08/31/2021 12:51:02 - INFO - __main__ - Step 130391: {'lr': 2.1348210050346596e-05, 'samples': 25035072, 'steps': 130390, 'loss/train': 0.7520878911018372} 08/31/2021 12:51:03 - INFO - __main__ - Step 130392: {'lr': 2.134606435377037e-05, 'samples': 25035264, 'steps': 130391, 'loss/train': 1.3312492370605469} 08/31/2021 12:51:03 - INFO - __main__ - Step 130393: {'lr': 2.1343918760222014e-05, 'samples': 25035456, 'steps': 130392, 'loss/train': 1.1090092658996582} 08/31/2021 12:51:04 - INFO - __main__ - Step 130394: {'lr': 2.1341773269702547e-05, 'samples': 25035648, 'steps': 130393, 'loss/train': 1.375731110572815} 08/31/2021 12:51:04 - INFO - __main__ - Step 130395: {'lr': 2.133962788221297e-05, 'samples': 25035840, 'steps': 130394, 'loss/train': 1.1797044277191162} 08/31/2021 12:51:05 - INFO - __main__ - Step 130396: {'lr': 2.1337482597754225e-05, 'samples': 25036032, 'steps': 130395, 'loss/train': 1.7977041006088257} 08/31/2021 12:51:06 - INFO - __main__ - Step 130397: {'lr': 2.133533741632726e-05, 'samples': 25036224, 'steps': 130396, 'loss/train': 0.3447456955909729} 08/31/2021 12:51:06 - INFO - __main__ - Step 130398: {'lr': 2.13331923379331e-05, 'samples': 25036416, 'steps': 130397, 'loss/train': 2.626160144805908} 08/31/2021 12:51:07 - INFO - __main__ - Step 130399: {'lr': 2.1331047362572658e-05, 'samples': 25036608, 'steps': 130398, 'loss/train': 1.0568169355392456} 08/31/2021 12:51:07 - INFO - __main__ - Step 130400: {'lr': 2.132890249024691e-05, 'samples': 25036800, 'steps': 130399, 'loss/train': 0.7367308139801025} 08/31/2021 12:51:09 - INFO - __main__ - Step 130401: {'lr': 2.1326757720956826e-05, 'samples': 25036992, 'steps': 130400, 'loss/train': 1.061782717704773} 08/31/2021 12:51:09 - INFO - __main__ - Step 130402: {'lr': 2.13246130547034e-05, 'samples': 25037184, 'steps': 130401, 'loss/train': 0.472034752368927} 08/31/2021 12:51:09 - INFO - __main__ - Step 130403: {'lr': 2.1322468491487558e-05, 'samples': 25037376, 'steps': 130402, 'loss/train': 1.0686708688735962} 08/31/2021 12:51:10 - INFO - __main__ - Step 130404: {'lr': 2.132032403131029e-05, 'samples': 25037568, 'steps': 130403, 'loss/train': 0.039087578654289246} 08/31/2021 12:51:10 - INFO - __main__ - Step 130405: {'lr': 2.1318179674172545e-05, 'samples': 25037760, 'steps': 130404, 'loss/train': 0.6552825570106506} 08/31/2021 12:51:12 - INFO - __main__ - Step 130406: {'lr': 2.1316035420075348e-05, 'samples': 25037952, 'steps': 130405, 'loss/train': 0.03601484373211861} 08/31/2021 12:51:12 - INFO - __main__ - Step 130407: {'lr': 2.1313891269019587e-05, 'samples': 25038144, 'steps': 130406, 'loss/train': 1.020229458808899} 08/31/2021 12:51:12 - INFO - __main__ - Step 130408: {'lr': 2.1311747221006234e-05, 'samples': 25038336, 'steps': 130407, 'loss/train': 0.9341754913330078} 08/31/2021 12:51:13 - INFO - __main__ - Step 130409: {'lr': 2.130960327603629e-05, 'samples': 25038528, 'steps': 130408, 'loss/train': 1.3388383388519287} 08/31/2021 12:51:13 - INFO - __main__ - Step 130410: {'lr': 2.130745943411072e-05, 'samples': 25038720, 'steps': 130409, 'loss/train': 1.25486421585083} 08/31/2021 12:51:15 - INFO - __main__ - Step 130411: {'lr': 2.1305315695230476e-05, 'samples': 25038912, 'steps': 130410, 'loss/train': 1.3888037204742432} 08/31/2021 12:51:15 - INFO - __main__ - Step 130412: {'lr': 2.1303172059396498e-05, 'samples': 25039104, 'steps': 130411, 'loss/train': 0.7041043639183044} 08/31/2021 12:51:15 - INFO - __main__ - Step 130413: {'lr': 2.130102852660981e-05, 'samples': 25039296, 'steps': 130412, 'loss/train': 1.0757179260253906} 08/31/2021 12:51:16 - INFO - __main__ - Step 130414: {'lr': 2.1298885096871363e-05, 'samples': 25039488, 'steps': 130413, 'loss/train': 1.1890064477920532} 08/31/2021 12:51:16 - INFO - __main__ - Step 130415: {'lr': 2.1296741770182066e-05, 'samples': 25039680, 'steps': 130414, 'loss/train': 1.1647064685821533} 08/31/2021 12:51:16 - INFO - __main__ - Step 130416: {'lr': 2.1294598546542977e-05, 'samples': 25039872, 'steps': 130415, 'loss/train': 1.8008122444152832} 08/31/2021 12:51:18 - INFO - __main__ - Step 130417: {'lr': 2.1292455425954983e-05, 'samples': 25040064, 'steps': 130416, 'loss/train': 1.3456016778945923} 08/31/2021 12:51:18 - INFO - __main__ - Step 130418: {'lr': 2.129031240841908e-05, 'samples': 25040256, 'steps': 130417, 'loss/train': 1.0317109823226929} 08/31/2021 12:51:19 - INFO - __main__ - Step 130419: {'lr': 2.1288169493936278e-05, 'samples': 25040448, 'steps': 130418, 'loss/train': 0.685626208782196} 08/31/2021 12:51:19 - INFO - __main__ - Step 130420: {'lr': 2.1286026682507453e-05, 'samples': 25040640, 'steps': 130419, 'loss/train': 0.474901407957077} 08/31/2021 12:51:19 - INFO - __main__ - Step 130421: {'lr': 2.1283883974133637e-05, 'samples': 25040832, 'steps': 130420, 'loss/train': 0.5436543822288513} 08/31/2021 12:51:21 - INFO - __main__ - Step 130422: {'lr': 2.128174136881575e-05, 'samples': 25041024, 'steps': 130421, 'loss/train': 0.7533198595046997} 08/31/2021 12:51:22 - INFO - __main__ - Step 130423: {'lr': 2.1279598866554783e-05, 'samples': 25041216, 'steps': 130422, 'loss/train': 0.8525075316429138} 08/31/2021 12:51:22 - INFO - __main__ - Step 130424: {'lr': 2.1277456467351713e-05, 'samples': 25041408, 'steps': 130423, 'loss/train': 0.9864185452461243} 08/31/2021 12:51:22 - INFO - __main__ - Step 130425: {'lr': 2.1275314171207484e-05, 'samples': 25041600, 'steps': 130424, 'loss/train': 1.1015636920928955} 08/31/2021 12:51:23 - INFO - __main__ - Step 130426: {'lr': 2.127317197812306e-05, 'samples': 25041792, 'steps': 130425, 'loss/train': 1.5577523708343506} 08/31/2021 12:51:24 - INFO - __main__ - Step 130427: {'lr': 2.1271029888099425e-05, 'samples': 25041984, 'steps': 130426, 'loss/train': 0.05310121551156044} 08/31/2021 12:51:25 - INFO - __main__ - Step 130428: {'lr': 2.126888790113754e-05, 'samples': 25042176, 'steps': 130427, 'loss/train': 1.1269755363464355} 08/31/2021 12:51:25 - INFO - __main__ - Step 130429: {'lr': 2.1266746017238354e-05, 'samples': 25042368, 'steps': 130428, 'loss/train': 0.99509596824646} 08/31/2021 12:51:25 - INFO - __main__ - Step 130430: {'lr': 2.1264604236402834e-05, 'samples': 25042560, 'steps': 130429, 'loss/train': 1.2992753982543945} 08/31/2021 12:51:26 - INFO - __main__ - Step 130431: {'lr': 2.1262462558631955e-05, 'samples': 25042752, 'steps': 130430, 'loss/train': 0.8715959787368774} 08/31/2021 12:51:27 - INFO - __main__ - Step 130432: {'lr': 2.1260320983926718e-05, 'samples': 25042944, 'steps': 130431, 'loss/train': 0.7644163370132446} 08/31/2021 12:51:27 - INFO - __main__ - Step 130433: {'lr': 2.1258179512288063e-05, 'samples': 25043136, 'steps': 130432, 'loss/train': 1.5075905323028564} 08/31/2021 12:51:28 - INFO - __main__ - Step 130434: {'lr': 2.1256038143716905e-05, 'samples': 25043328, 'steps': 130433, 'loss/train': 1.369523048400879} 08/31/2021 12:51:28 - INFO - __main__ - Step 130435: {'lr': 2.1253896878214245e-05, 'samples': 25043520, 'steps': 130434, 'loss/train': 1.1966809034347534} 08/31/2021 12:51:28 - INFO - __main__ - Step 130436: {'lr': 2.125175571578103e-05, 'samples': 25043712, 'steps': 130435, 'loss/train': 0.9940434098243713} 08/31/2021 12:51:31 - INFO - __main__ - Step 130437: {'lr': 2.124961465641828e-05, 'samples': 25043904, 'steps': 130436, 'loss/train': 1.1105068922042847} 08/31/2021 12:51:31 - INFO - __main__ - Step 130438: {'lr': 2.124747370012689e-05, 'samples': 25044096, 'steps': 130437, 'loss/train': 0.929588794708252} 08/31/2021 12:51:31 - INFO - __main__ - Step 130439: {'lr': 2.1245332846907883e-05, 'samples': 25044288, 'steps': 130438, 'loss/train': 1.2108877897262573} 08/31/2021 12:51:32 - INFO - __main__ - Step 130440: {'lr': 2.1243192096762203e-05, 'samples': 25044480, 'steps': 130439, 'loss/train': 0.3517093062400818} 08/31/2021 12:51:32 - INFO - __main__ - Step 130441: {'lr': 2.1241051449690796e-05, 'samples': 25044672, 'steps': 130440, 'loss/train': 1.3894811868667603} 08/31/2021 12:51:34 - INFO - __main__ - Step 130442: {'lr': 2.123891090569463e-05, 'samples': 25044864, 'steps': 130441, 'loss/train': 0.5270617604255676} 08/31/2021 12:51:34 - INFO - __main__ - Step 130443: {'lr': 2.1236770464774707e-05, 'samples': 25045056, 'steps': 130442, 'loss/train': 1.3338327407836914} 08/31/2021 12:51:34 - INFO - __main__ - Step 130444: {'lr': 2.1234630126931943e-05, 'samples': 25045248, 'steps': 130443, 'loss/train': 0.8839319348335266} 08/31/2021 12:51:35 - INFO - __main__ - Step 130445: {'lr': 2.1232489892167335e-05, 'samples': 25045440, 'steps': 130444, 'loss/train': 1.119483232498169} 08/31/2021 12:51:35 - INFO - __main__ - Step 130446: {'lr': 2.123034976048188e-05, 'samples': 25045632, 'steps': 130445, 'loss/train': 1.272417664527893} 08/31/2021 12:51:37 - INFO - __main__ - Step 130447: {'lr': 2.1228209731876476e-05, 'samples': 25045824, 'steps': 130446, 'loss/train': 0.17729131877422333} 08/31/2021 12:51:37 - INFO - __main__ - Step 130448: {'lr': 2.1226069806352084e-05, 'samples': 25046016, 'steps': 130447, 'loss/train': 0.6672789454460144} 08/31/2021 12:51:37 - INFO - __main__ - Step 130449: {'lr': 2.1223929983909705e-05, 'samples': 25046208, 'steps': 130448, 'loss/train': 1.0495163202285767} 08/31/2021 12:51:38 - INFO - __main__ - Step 130450: {'lr': 2.122179026455029e-05, 'samples': 25046400, 'steps': 130449, 'loss/train': 0.24733862280845642} 08/31/2021 12:51:38 - INFO - __main__ - Step 130451: {'lr': 2.1219650648274802e-05, 'samples': 25046592, 'steps': 130450, 'loss/train': 0.9745417833328247} 08/31/2021 12:51:40 - INFO - __main__ - Step 130452: {'lr': 2.1217511135084216e-05, 'samples': 25046784, 'steps': 130451, 'loss/train': 0.6804589033126831} 08/31/2021 12:51:40 - INFO - __main__ - Step 130453: {'lr': 2.1215371724979478e-05, 'samples': 25046976, 'steps': 130452, 'loss/train': 0.8272500038146973} 08/31/2021 12:51:41 - INFO - __main__ - Step 130454: {'lr': 2.121323241796158e-05, 'samples': 25047168, 'steps': 130453, 'loss/train': 0.5549460053443909} 08/31/2021 12:51:41 - INFO - __main__ - Step 130455: {'lr': 2.1211093214031445e-05, 'samples': 25047360, 'steps': 130454, 'loss/train': 0.03887557610869408} 08/31/2021 12:51:41 - INFO - __main__ - Step 130456: {'lr': 2.120895411319007e-05, 'samples': 25047552, 'steps': 130455, 'loss/train': 1.5579166412353516} 08/31/2021 12:51:42 - INFO - __main__ - Step 130457: {'lr': 2.1206815115438427e-05, 'samples': 25047744, 'steps': 130456, 'loss/train': 1.1497013568878174} 08/31/2021 12:51:43 - INFO - __main__ - Step 130458: {'lr': 2.120467622077746e-05, 'samples': 25047936, 'steps': 130457, 'loss/train': 0.7497419118881226} 08/31/2021 12:51:43 - INFO - __main__ - Step 130459: {'lr': 2.120253742920811e-05, 'samples': 25048128, 'steps': 130458, 'loss/train': 1.0448397397994995} 08/31/2021 12:51:44 - INFO - __main__ - Step 130460: {'lr': 2.120039874073143e-05, 'samples': 25048320, 'steps': 130459, 'loss/train': 1.6069926023483276} 08/31/2021 12:51:44 - INFO - __main__ - Step 130461: {'lr': 2.1198260155348286e-05, 'samples': 25048512, 'steps': 130460, 'loss/train': 1.2753229141235352} 08/31/2021 12:51:44 - INFO - __main__ - Step 130462: {'lr': 2.1196121673059647e-05, 'samples': 25048704, 'steps': 130461, 'loss/train': 0.5923123955726624} 08/31/2021 12:51:46 - INFO - __main__ - Step 130463: {'lr': 2.1193983293866515e-05, 'samples': 25048896, 'steps': 130462, 'loss/train': 0.8177291750907898} 08/31/2021 12:51:47 - INFO - __main__ - Step 130464: {'lr': 2.1191845017769856e-05, 'samples': 25049088, 'steps': 130463, 'loss/train': 1.0620085000991821} 08/31/2021 12:51:47 - INFO - __main__ - Step 130465: {'lr': 2.1189706844770618e-05, 'samples': 25049280, 'steps': 130464, 'loss/train': 0.8207418918609619} 08/31/2021 12:51:47 - INFO - __main__ - Step 130466: {'lr': 2.118756877486977e-05, 'samples': 25049472, 'steps': 130465, 'loss/train': 1.21746826171875} 08/31/2021 12:51:48 - INFO - __main__ - Step 130467: {'lr': 2.1185430808068257e-05, 'samples': 25049664, 'steps': 130466, 'loss/train': 1.4107720851898193} 08/31/2021 12:51:50 - INFO - __main__ - Step 130468: {'lr': 2.1183292944367078e-05, 'samples': 25049856, 'steps': 130467, 'loss/train': 0.4230881929397583} 08/31/2021 12:51:50 - INFO - __main__ - Step 130469: {'lr': 2.118115518376715e-05, 'samples': 25050048, 'steps': 130468, 'loss/train': 0.01626436971127987} 08/31/2021 12:51:50 - INFO - __main__ - Step 130470: {'lr': 2.1179017526269466e-05, 'samples': 25050240, 'steps': 130469, 'loss/train': 0.8699305653572083} 08/31/2021 12:51:51 - INFO - __main__ - Step 130471: {'lr': 2.117687997187501e-05, 'samples': 25050432, 'steps': 130470, 'loss/train': 1.3393279314041138} 08/31/2021 12:51:51 - INFO - __main__ - Step 130472: {'lr': 2.1174742520584712e-05, 'samples': 25050624, 'steps': 130471, 'loss/train': 1.5882352590560913} 08/31/2021 12:51:51 - INFO - __main__ - Step 130473: {'lr': 2.117260517239958e-05, 'samples': 25050816, 'steps': 130472, 'loss/train': 1.5676218271255493} 08/31/2021 12:51:53 - INFO - __main__ - Step 130474: {'lr': 2.1170467927320496e-05, 'samples': 25051008, 'steps': 130473, 'loss/train': 0.8231293559074402} 08/31/2021 12:51:54 - INFO - __main__ - Step 130475: {'lr': 2.1168330785348465e-05, 'samples': 25051200, 'steps': 130474, 'loss/train': 0.15199148654937744} 08/31/2021 12:51:54 - INFO - __main__ - Step 130476: {'lr': 2.1166193746484487e-05, 'samples': 25051392, 'steps': 130475, 'loss/train': 1.401096224784851} 08/31/2021 12:51:54 - INFO - __main__ - Step 130477: {'lr': 2.1164056810729443e-05, 'samples': 25051584, 'steps': 130476, 'loss/train': 0.42771849036216736} 08/31/2021 12:51:55 - INFO - __main__ - Step 130478: {'lr': 2.1161919978084364e-05, 'samples': 25051776, 'steps': 130477, 'loss/train': 1.4723560810089111} 08/31/2021 12:51:56 - INFO - __main__ - Step 130479: {'lr': 2.1159783248550198e-05, 'samples': 25051968, 'steps': 130478, 'loss/train': 1.6723085641860962} 08/31/2021 12:51:56 - INFO - __main__ - Step 130480: {'lr': 2.1157646622127907e-05, 'samples': 25052160, 'steps': 130479, 'loss/train': 0.408561110496521} 08/31/2021 12:51:57 - INFO - __main__ - Step 130481: {'lr': 2.1155510098818443e-05, 'samples': 25052352, 'steps': 130480, 'loss/train': 0.7017853856086731} 08/31/2021 12:51:57 - INFO - __main__ - Step 130482: {'lr': 2.1153373678622773e-05, 'samples': 25052544, 'steps': 130481, 'loss/train': 1.2990778684616089} 08/31/2021 12:51:57 - INFO - __main__ - Step 130483: {'lr': 2.115123736154187e-05, 'samples': 25052736, 'steps': 130482, 'loss/train': 1.2639238834381104} 08/31/2021 12:51:59 - INFO - __main__ - Step 130484: {'lr': 2.1149101147576677e-05, 'samples': 25052928, 'steps': 130483, 'loss/train': 0.35408899188041687} 08/31/2021 12:51:59 - INFO - __main__ - Step 130485: {'lr': 2.1146965036728165e-05, 'samples': 25053120, 'steps': 130484, 'loss/train': 1.2647674083709717} 08/31/2021 12:52:00 - INFO - __main__ - Step 130486: {'lr': 2.1144829028997337e-05, 'samples': 25053312, 'steps': 130485, 'loss/train': 0.7508593797683716} 08/31/2021 12:52:00 - INFO - __main__ - Step 130487: {'lr': 2.1142693124385105e-05, 'samples': 25053504, 'steps': 130486, 'loss/train': 0.43544241786003113} 08/31/2021 12:52:00 - INFO - __main__ - Step 130488: {'lr': 2.1140557322892413e-05, 'samples': 25053696, 'steps': 130487, 'loss/train': 1.062964916229248} 08/31/2021 12:52:02 - INFO - __main__ - Step 130489: {'lr': 2.113842162452026e-05, 'samples': 25053888, 'steps': 130488, 'loss/train': 1.069999098777771} 08/31/2021 12:52:03 - INFO - __main__ - Step 130490: {'lr': 2.1136286029269618e-05, 'samples': 25054080, 'steps': 130489, 'loss/train': 1.0757688283920288} 08/31/2021 12:52:03 - INFO - __main__ - Step 130491: {'lr': 2.1134150537141432e-05, 'samples': 25054272, 'steps': 130490, 'loss/train': 0.02939789369702339} 08/31/2021 12:52:04 - INFO - __main__ - Step 130492: {'lr': 2.1132015148136645e-05, 'samples': 25054464, 'steps': 130491, 'loss/train': 1.0513161420822144} 08/31/2021 12:52:04 - INFO - __main__ - Step 130493: {'lr': 2.112987986225626e-05, 'samples': 25054656, 'steps': 130492, 'loss/train': 1.3506234884262085} 08/31/2021 12:52:04 - INFO - __main__ - Step 130494: {'lr': 2.112774467950121e-05, 'samples': 25054848, 'steps': 130493, 'loss/train': 0.8863911032676697} 08/31/2021 12:52:06 - INFO - __main__ - Step 130495: {'lr': 2.1125609599872475e-05, 'samples': 25055040, 'steps': 130494, 'loss/train': 0.9647382497787476} 08/31/2021 12:52:07 - INFO - __main__ - Step 130496: {'lr': 2.1123474623370998e-05, 'samples': 25055232, 'steps': 130495, 'loss/train': 0.3838026523590088} 08/31/2021 12:52:07 - INFO - __main__ - Step 130497: {'lr': 2.1121339749997748e-05, 'samples': 25055424, 'steps': 130496, 'loss/train': 0.015012558549642563} 08/31/2021 12:52:07 - INFO - __main__ - Step 130498: {'lr': 2.1119204979753696e-05, 'samples': 25055616, 'steps': 130497, 'loss/train': 1.2125067710876465} 08/31/2021 12:52:08 - INFO - __main__ - Step 130499: {'lr': 2.111707031263982e-05, 'samples': 25055808, 'steps': 130498, 'loss/train': 5.722552299499512} 08/31/2021 12:52:08 - INFO - __main__ - Step 130500: {'lr': 2.1114935748657083e-05, 'samples': 25056000, 'steps': 130499, 'loss/train': 1.203477144241333} 08/31/2021 12:52:09 - INFO - __main__ - Step 130501: {'lr': 2.1112801287806378e-05, 'samples': 25056192, 'steps': 130500, 'loss/train': 1.1237123012542725} 08/31/2021 12:52:10 - INFO - __main__ - Step 130502: {'lr': 2.111066693008873e-05, 'samples': 25056384, 'steps': 130501, 'loss/train': 1.0390530824661255} 08/31/2021 12:52:10 - INFO - __main__ - Step 130503: {'lr': 2.1108532675505056e-05, 'samples': 25056576, 'steps': 130502, 'loss/train': 1.0203931331634521} 08/31/2021 12:52:11 - INFO - __main__ - Step 130504: {'lr': 2.1106398524056353e-05, 'samples': 25056768, 'steps': 130503, 'loss/train': 1.3568034172058105} 08/31/2021 12:52:11 - INFO - __main__ - Step 130505: {'lr': 2.1104264475743595e-05, 'samples': 25056960, 'steps': 130504, 'loss/train': 1.28110933303833} 08/31/2021 12:52:12 - INFO - __main__ - Step 130506: {'lr': 2.1102130530567697e-05, 'samples': 25057152, 'steps': 130505, 'loss/train': 1.2606918811798096} 08/31/2021 12:52:13 - INFO - __main__ - Step 130507: {'lr': 2.109999668852966e-05, 'samples': 25057344, 'steps': 130506, 'loss/train': 1.3865493535995483} 08/31/2021 12:52:13 - INFO - __main__ - Step 130508: {'lr': 2.1097862949630453e-05, 'samples': 25057536, 'steps': 130507, 'loss/train': 1.3603343963623047} 08/31/2021 12:52:14 - INFO - __main__ - Step 130509: {'lr': 2.1095729313870994e-05, 'samples': 25057728, 'steps': 130508, 'loss/train': 0.7417513132095337} 08/31/2021 12:52:14 - INFO - __main__ - Step 130510: {'lr': 2.1093595781252278e-05, 'samples': 25057920, 'steps': 130509, 'loss/train': 0.1472581923007965} 08/31/2021 12:52:16 - INFO - __main__ - Step 130511: {'lr': 2.1091462351775225e-05, 'samples': 25058112, 'steps': 130510, 'loss/train': 1.727036952972412} 08/31/2021 12:52:16 - INFO - __main__ - Step 130512: {'lr': 2.1089329025440862e-05, 'samples': 25058304, 'steps': 130511, 'loss/train': 1.3190127611160278} 08/31/2021 12:52:16 - INFO - __main__ - Step 130513: {'lr': 2.1087195802250132e-05, 'samples': 25058496, 'steps': 130512, 'loss/train': 0.03784957155585289} 08/31/2021 12:52:17 - INFO - __main__ - Step 130514: {'lr': 2.108506268220395e-05, 'samples': 25058688, 'steps': 130513, 'loss/train': 0.8024255633354187} 08/31/2021 12:52:17 - INFO - __main__ - Step 130515: {'lr': 2.1082929665303313e-05, 'samples': 25058880, 'steps': 130514, 'loss/train': 0.6449271440505981} 08/31/2021 12:52:17 - INFO - __main__ - Step 130516: {'lr': 2.108079675154917e-05, 'samples': 25059072, 'steps': 130515, 'loss/train': 1.1969459056854248} 08/31/2021 12:52:19 - INFO - __main__ - Step 130517: {'lr': 2.1078663940942488e-05, 'samples': 25059264, 'steps': 130516, 'loss/train': 0.5407078266143799} 08/31/2021 12:52:19 - INFO - __main__ - Step 130518: {'lr': 2.1076531233484214e-05, 'samples': 25059456, 'steps': 130517, 'loss/train': 0.5357000827789307} 08/31/2021 12:52:20 - INFO - __main__ - Step 130519: {'lr': 2.1074398629175345e-05, 'samples': 25059648, 'steps': 130518, 'loss/train': 1.3111646175384521} 08/31/2021 12:52:20 - INFO - __main__ - Step 130520: {'lr': 2.1072266128016797e-05, 'samples': 25059840, 'steps': 130519, 'loss/train': 1.1608556509017944} 08/31/2021 12:52:20 - INFO - __main__ - Step 130521: {'lr': 2.1070133730009573e-05, 'samples': 25060032, 'steps': 130520, 'loss/train': 0.963837742805481} 08/31/2021 12:52:22 - INFO - __main__ - Step 130522: {'lr': 2.106800143515461e-05, 'samples': 25060224, 'steps': 130521, 'loss/train': 1.2574971914291382} 08/31/2021 12:52:22 - INFO - __main__ - Step 130523: {'lr': 2.1065869243452857e-05, 'samples': 25060416, 'steps': 130522, 'loss/train': 1.7293157577514648} 08/31/2021 12:52:23 - INFO - __main__ - Step 130524: {'lr': 2.106373715490531e-05, 'samples': 25060608, 'steps': 130523, 'loss/train': 0.9794546365737915} 08/31/2021 12:52:23 - INFO - __main__ - Step 130525: {'lr': 2.1061605169512915e-05, 'samples': 25060800, 'steps': 130524, 'loss/train': 1.8118318319320679} 08/31/2021 12:52:23 - INFO - __main__ - Step 130526: {'lr': 2.1059473287276615e-05, 'samples': 25060992, 'steps': 130525, 'loss/train': 0.8617438673973083} 08/31/2021 12:52:25 - INFO - __main__ - Step 130527: {'lr': 2.1057341508197408e-05, 'samples': 25061184, 'steps': 130526, 'loss/train': 1.136638879776001} 08/31/2021 12:52:25 - INFO - __main__ - Step 130528: {'lr': 2.1055209832276213e-05, 'samples': 25061376, 'steps': 130527, 'loss/train': 0.5734898447990417} 08/31/2021 12:52:26 - INFO - __main__ - Step 130529: {'lr': 2.1053078259514e-05, 'samples': 25061568, 'steps': 130528, 'loss/train': 0.5329816341400146} 08/31/2021 12:52:26 - INFO - __main__ - Step 130530: {'lr': 2.1050946789911733e-05, 'samples': 25061760, 'steps': 130529, 'loss/train': 1.0928171873092651} 08/31/2021 12:52:26 - INFO - __main__ - Step 130531: {'lr': 2.1048815423470397e-05, 'samples': 25061952, 'steps': 130530, 'loss/train': 1.0548975467681885} 08/31/2021 12:52:28 - INFO - __main__ - Step 130532: {'lr': 2.1046684160190897e-05, 'samples': 25062144, 'steps': 130531, 'loss/train': 1.3173774480819702} 08/31/2021 12:52:29 - INFO - __main__ - Step 130533: {'lr': 2.1044553000074268e-05, 'samples': 25062336, 'steps': 130532, 'loss/train': 1.3330652713775635} 08/31/2021 12:52:29 - INFO - __main__ - Step 130534: {'lr': 2.1042421943121393e-05, 'samples': 25062528, 'steps': 130533, 'loss/train': 1.2260687351226807} 08/31/2021 12:52:29 - INFO - __main__ - Step 130535: {'lr': 2.10402909893333e-05, 'samples': 25062720, 'steps': 130534, 'loss/train': 0.5771952271461487} 08/31/2021 12:52:30 - INFO - __main__ - Step 130536: {'lr': 2.1038160138710903e-05, 'samples': 25062912, 'steps': 130535, 'loss/train': 1.1766972541809082} 08/31/2021 12:52:31 - INFO - __main__ - Step 130537: {'lr': 2.103602939125518e-05, 'samples': 25063104, 'steps': 130536, 'loss/train': 0.9063034057617188} 08/31/2021 12:52:32 - INFO - __main__ - Step 130538: {'lr': 2.1033898746967094e-05, 'samples': 25063296, 'steps': 130537, 'loss/train': 1.2133644819259644} 08/31/2021 12:52:32 - INFO - __main__ - Step 130539: {'lr': 2.1031768205847624e-05, 'samples': 25063488, 'steps': 130538, 'loss/train': 1.6914891004562378} 08/31/2021 12:52:33 - INFO - __main__ - Step 130540: {'lr': 2.1029637767897682e-05, 'samples': 25063680, 'steps': 130539, 'loss/train': 0.5855492353439331} 08/31/2021 12:52:33 - INFO - __main__ - Step 130541: {'lr': 2.1027507433118237e-05, 'samples': 25063872, 'steps': 130540, 'loss/train': 0.4974498450756073} 08/31/2021 12:52:33 - INFO - __main__ - Step 130542: {'lr': 2.1025377201510294e-05, 'samples': 25064064, 'steps': 130541, 'loss/train': 0.860036313533783} 08/31/2021 12:52:35 - INFO - __main__ - Step 130543: {'lr': 2.1023247073074763e-05, 'samples': 25064256, 'steps': 130542, 'loss/train': 1.0184861421585083} 08/31/2021 12:52:35 - INFO - __main__ - Step 130544: {'lr': 2.1021117047812622e-05, 'samples': 25064448, 'steps': 130543, 'loss/train': 0.9430063962936401} 08/31/2021 12:52:36 - INFO - __main__ - Step 130545: {'lr': 2.1018987125724837e-05, 'samples': 25064640, 'steps': 130544, 'loss/train': 1.651286244392395} 08/31/2021 12:52:36 - INFO - __main__ - Step 130546: {'lr': 2.1016857306812353e-05, 'samples': 25064832, 'steps': 130545, 'loss/train': 1.4888982772827148} 08/31/2021 12:52:37 - INFO - __main__ - Step 130547: {'lr': 2.1014727591076143e-05, 'samples': 25065024, 'steps': 130546, 'loss/train': 1.7539235353469849} 08/31/2021 12:52:39 - INFO - __main__ - Step 130548: {'lr': 2.1012597978517178e-05, 'samples': 25065216, 'steps': 130547, 'loss/train': 1.2440931797027588} 08/31/2021 12:52:39 - INFO - __main__ - Step 130549: {'lr': 2.1010468469136375e-05, 'samples': 25065408, 'steps': 130548, 'loss/train': 1.2147573232650757} 08/31/2021 12:52:40 - INFO - __main__ - Step 130550: {'lr': 2.1008339062934785e-05, 'samples': 25065600, 'steps': 130549, 'loss/train': 1.444398045539856} 08/31/2021 12:52:40 - INFO - __main__ - Step 130551: {'lr': 2.100620975991327e-05, 'samples': 25065792, 'steps': 130550, 'loss/train': 1.3857249021530151} 08/31/2021 12:52:40 - INFO - __main__ - Step 130552: {'lr': 2.10040805600728e-05, 'samples': 25065984, 'steps': 130551, 'loss/train': 0.8211533427238464} 08/31/2021 12:52:42 - INFO - __main__ - Step 130553: {'lr': 2.100195146341438e-05, 'samples': 25066176, 'steps': 130552, 'loss/train': 1.3239972591400146} 08/31/2021 12:52:42 - INFO - __main__ - Step 130554: {'lr': 2.0999822469938923e-05, 'samples': 25066368, 'steps': 130553, 'loss/train': 1.1349021196365356} 08/31/2021 12:52:43 - INFO - __main__ - Step 130555: {'lr': 2.0997693579647426e-05, 'samples': 25066560, 'steps': 130554, 'loss/train': 1.3374656438827515} 08/31/2021 12:52:43 - INFO - __main__ - Step 130556: {'lr': 2.0995564792540832e-05, 'samples': 25066752, 'steps': 130555, 'loss/train': 0.6483178734779358} 08/31/2021 12:52:43 - INFO - __main__ - Step 130557: {'lr': 2.099343610862009e-05, 'samples': 25066944, 'steps': 130556, 'loss/train': 0.405491441488266} 08/31/2021 12:52:44 - INFO - __main__ - Step 130558: {'lr': 2.0991307527886195e-05, 'samples': 25067136, 'steps': 130557, 'loss/train': 0.2944786250591278} 08/31/2021 12:52:45 - INFO - __main__ - Step 130559: {'lr': 2.0989179050340064e-05, 'samples': 25067328, 'steps': 130558, 'loss/train': 0.9439830780029297} 08/31/2021 12:52:46 - INFO - __main__ - Step 130560: {'lr': 2.0987050675982695e-05, 'samples': 25067520, 'steps': 130559, 'loss/train': 1.0016456842422485} 08/31/2021 12:52:46 - INFO - __main__ - Step 130561: {'lr': 2.098492240481506e-05, 'samples': 25067712, 'steps': 130560, 'loss/train': 0.8985704183578491} 08/31/2021 12:52:46 - INFO - __main__ - Step 130562: {'lr': 2.0982794236838048e-05, 'samples': 25067904, 'steps': 130561, 'loss/train': 1.3510804176330566} 08/31/2021 12:52:47 - INFO - __main__ - Step 130563: {'lr': 2.0980666172052633e-05, 'samples': 25068096, 'steps': 130562, 'loss/train': 1.1251729726791382} 08/31/2021 12:52:48 - INFO - __main__ - Step 130564: {'lr': 2.0978538210459837e-05, 'samples': 25068288, 'steps': 130563, 'loss/train': 1.25784170627594} 08/31/2021 12:52:49 - INFO - __main__ - Step 130565: {'lr': 2.097641035206055e-05, 'samples': 25068480, 'steps': 130564, 'loss/train': 1.2826215028762817} 08/31/2021 12:52:49 - INFO - __main__ - Step 130566: {'lr': 2.0974282596855743e-05, 'samples': 25068672, 'steps': 130565, 'loss/train': 0.9807735681533813} 08/31/2021 12:52:49 - INFO - __main__ - Step 130567: {'lr': 2.0972154944846418e-05, 'samples': 25068864, 'steps': 130566, 'loss/train': 1.1724110841751099} 08/31/2021 12:52:50 - INFO - __main__ - Step 130568: {'lr': 2.0970027396033485e-05, 'samples': 25069056, 'steps': 130567, 'loss/train': 0.7412738800048828} 08/31/2021 12:52:51 - INFO - __main__ - Step 130569: {'lr': 2.096789995041795e-05, 'samples': 25069248, 'steps': 130568, 'loss/train': 1.5256386995315552} 08/31/2021 12:52:52 - INFO - __main__ - Step 130570: {'lr': 2.0965772608000726e-05, 'samples': 25069440, 'steps': 130569, 'loss/train': 1.3509005308151245} 08/31/2021 12:52:52 - INFO - __main__ - Step 130571: {'lr': 2.0963645368782787e-05, 'samples': 25069632, 'steps': 130570, 'loss/train': 0.8445542454719543} 08/31/2021 12:52:53 - INFO - __main__ - Step 130572: {'lr': 2.0961518232765154e-05, 'samples': 25069824, 'steps': 130571, 'loss/train': 0.08473118394613266} 08/31/2021 12:52:53 - INFO - __main__ - Step 130573: {'lr': 2.0959391199948663e-05, 'samples': 25070016, 'steps': 130572, 'loss/train': 0.8611633777618408} 08/31/2021 12:52:54 - INFO - __main__ - Step 130574: {'lr': 2.095726427033434e-05, 'samples': 25070208, 'steps': 130573, 'loss/train': 1.0328396558761597} 08/31/2021 12:52:55 - INFO - __main__ - Step 130575: {'lr': 2.095513744392316e-05, 'samples': 25070400, 'steps': 130574, 'loss/train': 1.0828200578689575} 08/31/2021 12:52:55 - INFO - __main__ - Step 130576: {'lr': 2.0953010720716037e-05, 'samples': 25070592, 'steps': 130575, 'loss/train': 1.339656114578247} 08/31/2021 12:52:56 - INFO - __main__ - Step 130577: {'lr': 2.0950884100713968e-05, 'samples': 25070784, 'steps': 130576, 'loss/train': 1.03886878490448} 08/31/2021 12:52:56 - INFO - __main__ - Step 130578: {'lr': 2.0948757583917897e-05, 'samples': 25070976, 'steps': 130577, 'loss/train': 1.176534652709961} 08/31/2021 12:52:57 - INFO - __main__ - Step 130579: {'lr': 2.0946631170328773e-05, 'samples': 25071168, 'steps': 130578, 'loss/train': 1.354075312614441} 08/31/2021 12:52:58 - INFO - __main__ - Step 130580: {'lr': 2.094450485994756e-05, 'samples': 25071360, 'steps': 130579, 'loss/train': 1.771194338798523} 08/31/2021 12:52:58 - INFO - __main__ - Step 130581: {'lr': 2.0942378652775236e-05, 'samples': 25071552, 'steps': 130580, 'loss/train': 0.08701037615537643} 08/31/2021 12:52:59 - INFO - __main__ - Step 130582: {'lr': 2.094025254881271e-05, 'samples': 25071744, 'steps': 130581, 'loss/train': 1.0308880805969238} 08/31/2021 12:52:59 - INFO - __main__ - Step 130583: {'lr': 2.0938126548061044e-05, 'samples': 25071936, 'steps': 130582, 'loss/train': 1.0819127559661865} 08/31/2021 12:52:59 - INFO - __main__ - Step 130584: {'lr': 2.0936000650521064e-05, 'samples': 25072128, 'steps': 130583, 'loss/train': 0.729222297668457} 08/31/2021 12:53:01 - INFO - __main__ - Step 130585: {'lr': 2.0933874856193804e-05, 'samples': 25072320, 'steps': 130584, 'loss/train': 1.4902608394622803} 08/31/2021 12:53:01 - INFO - __main__ - Step 130586: {'lr': 2.0931749165080198e-05, 'samples': 25072512, 'steps': 130585, 'loss/train': 1.196743369102478} 08/31/2021 12:53:02 - INFO - __main__ - Step 130587: {'lr': 2.09296235771812e-05, 'samples': 25072704, 'steps': 130586, 'loss/train': 0.6849516034126282} 08/31/2021 12:53:02 - INFO - __main__ - Step 130588: {'lr': 2.0927498092497804e-05, 'samples': 25072896, 'steps': 130587, 'loss/train': 0.9221607446670532} 08/31/2021 12:53:02 - INFO - __main__ - Step 130589: {'lr': 2.0925372711030926e-05, 'samples': 25073088, 'steps': 130588, 'loss/train': 0.5920138359069824} 08/31/2021 12:53:04 - INFO - __main__ - Step 130590: {'lr': 2.092324743278154e-05, 'samples': 25073280, 'steps': 130589, 'loss/train': 1.4852906465530396} 08/31/2021 12:53:04 - INFO - __main__ - Step 130591: {'lr': 2.0921122257750586e-05, 'samples': 25073472, 'steps': 130590, 'loss/train': 0.8452675342559814} 08/31/2021 12:53:05 - INFO - __main__ - Step 130592: {'lr': 2.0918997185939066e-05, 'samples': 25073664, 'steps': 130591, 'loss/train': 0.7253001928329468} 08/31/2021 12:53:05 - INFO - __main__ - Step 130593: {'lr': 2.091687221734789e-05, 'samples': 25073856, 'steps': 130592, 'loss/train': 0.4128674864768982} 08/31/2021 12:53:06 - INFO - __main__ - Step 130594: {'lr': 2.0914747351978097e-05, 'samples': 25074048, 'steps': 130593, 'loss/train': 0.026934027671813965} 08/31/2021 12:53:07 - INFO - __main__ - Step 130595: {'lr': 2.0912622589830536e-05, 'samples': 25074240, 'steps': 130594, 'loss/train': 0.9524664282798767} 08/31/2021 12:53:08 - INFO - __main__ - Step 130596: {'lr': 2.0910497930906215e-05, 'samples': 25074432, 'steps': 130595, 'loss/train': 0.1666812002658844} 08/31/2021 12:53:08 - INFO - __main__ - Step 130597: {'lr': 2.0908373375206096e-05, 'samples': 25074624, 'steps': 130596, 'loss/train': 1.3597017526626587} 08/31/2021 12:53:08 - INFO - __main__ - Step 130598: {'lr': 2.090624892273113e-05, 'samples': 25074816, 'steps': 130597, 'loss/train': 0.47291773557662964} 08/31/2021 12:53:09 - INFO - __main__ - Step 130599: {'lr': 2.090412457348226e-05, 'samples': 25075008, 'steps': 130598, 'loss/train': 0.8656840920448303} 08/31/2021 12:53:11 - INFO - __main__ - Step 130600: {'lr': 2.090200032746045e-05, 'samples': 25075200, 'steps': 130599, 'loss/train': 1.390604019165039} 08/31/2021 12:53:11 - INFO - __main__ - Step 130601: {'lr': 2.0899876184666654e-05, 'samples': 25075392, 'steps': 130600, 'loss/train': 1.0621376037597656} 08/31/2021 12:53:12 - INFO - __main__ - Step 130602: {'lr': 2.0897752145101867e-05, 'samples': 25075584, 'steps': 130601, 'loss/train': 1.078648328781128} 08/31/2021 12:53:12 - INFO - __main__ - Step 130603: {'lr': 2.0895628208767005e-05, 'samples': 25075776, 'steps': 130602, 'loss/train': 0.9414917826652527} 08/31/2021 12:53:12 - INFO - __main__ - Step 130604: {'lr': 2.0893504375663036e-05, 'samples': 25075968, 'steps': 130603, 'loss/train': 0.748302161693573} 08/31/2021 12:53:13 - INFO - __main__ - Step 130605: {'lr': 2.0891380645790936e-05, 'samples': 25076160, 'steps': 130604, 'loss/train': 1.131574034690857} 08/31/2021 12:53:15 - INFO - __main__ - Step 130606: {'lr': 2.088925701915162e-05, 'samples': 25076352, 'steps': 130605, 'loss/train': 0.2900896668434143} 08/31/2021 12:53:15 - INFO - __main__ - Step 130607: {'lr': 2.0887133495746113e-05, 'samples': 25076544, 'steps': 130606, 'loss/train': 0.42809927463531494} 08/31/2021 12:53:16 - INFO - __main__ - Step 130608: {'lr': 2.0885010075575307e-05, 'samples': 25076736, 'steps': 130607, 'loss/train': 1.6850519180297852} 08/31/2021 12:53:16 - INFO - __main__ - Step 130609: {'lr': 2.0882886758640168e-05, 'samples': 25076928, 'steps': 130608, 'loss/train': 0.9147545099258423} 08/31/2021 12:53:16 - INFO - __main__ - Step 130610: {'lr': 2.0880763544941673e-05, 'samples': 25077120, 'steps': 130609, 'loss/train': 1.1683787107467651} 08/31/2021 12:53:17 - INFO - __main__ - Step 130611: {'lr': 2.0878640434480763e-05, 'samples': 25077312, 'steps': 130610, 'loss/train': 0.12623396515846252} 08/31/2021 12:53:18 - INFO - __main__ - Step 130612: {'lr': 2.087651742725838e-05, 'samples': 25077504, 'steps': 130611, 'loss/train': 0.015871873125433922} 08/31/2021 12:53:18 - INFO - __main__ - Step 130613: {'lr': 2.0874394523275526e-05, 'samples': 25077696, 'steps': 130612, 'loss/train': 0.7662180662155151} 08/31/2021 12:53:19 - INFO - __main__ - Step 130614: {'lr': 2.0872271722533142e-05, 'samples': 25077888, 'steps': 130613, 'loss/train': 0.7606503963470459} 08/31/2021 12:53:19 - INFO - __main__ - Step 130615: {'lr': 2.0870149025032174e-05, 'samples': 25078080, 'steps': 130614, 'loss/train': 0.6582725048065186} 08/31/2021 12:53:20 - INFO - __main__ - Step 130616: {'lr': 2.086802643077357e-05, 'samples': 25078272, 'steps': 130615, 'loss/train': 1.4835937023162842} 08/31/2021 12:53:21 - INFO - __main__ - Step 130617: {'lr': 2.0865903939758292e-05, 'samples': 25078464, 'steps': 130616, 'loss/train': 0.7422000169754028} 08/31/2021 12:53:22 - INFO - __main__ - Step 130618: {'lr': 2.0863781551987316e-05, 'samples': 25078656, 'steps': 130617, 'loss/train': 1.3553416728973389} 08/31/2021 12:53:22 - INFO - __main__ - Step 130619: {'lr': 2.0861659267461585e-05, 'samples': 25078848, 'steps': 130618, 'loss/train': 1.0606510639190674} 08/31/2021 12:53:22 - INFO - __main__ - Step 130620: {'lr': 2.0859537086182045e-05, 'samples': 25079040, 'steps': 130619, 'loss/train': 0.091830313205719} 08/31/2021 12:53:23 - INFO - __main__ - Step 130621: {'lr': 2.0857415008149723e-05, 'samples': 25079232, 'steps': 130620, 'loss/train': 0.8337193131446838} 08/31/2021 12:53:23 - INFO - __main__ - Step 130622: {'lr': 2.0855293033365445e-05, 'samples': 25079424, 'steps': 130621, 'loss/train': 0.9274906516075134} 08/31/2021 12:53:25 - INFO - __main__ - Step 130623: {'lr': 2.085317116183025e-05, 'samples': 25079616, 'steps': 130622, 'loss/train': 1.5090667009353638} 08/31/2021 12:53:25 - INFO - __main__ - Step 130624: {'lr': 2.0851049393545068e-05, 'samples': 25079808, 'steps': 130623, 'loss/train': 1.198656439781189} 08/31/2021 12:53:25 - INFO - __main__ - Step 130625: {'lr': 2.084892772851088e-05, 'samples': 25080000, 'steps': 130624, 'loss/train': 1.9099379777908325} 08/31/2021 12:53:26 - INFO - __main__ - Step 130626: {'lr': 2.084680616672863e-05, 'samples': 25080192, 'steps': 130625, 'loss/train': 1.7355117797851562} 08/31/2021 12:53:26 - INFO - __main__ - Step 130627: {'lr': 2.084468470819928e-05, 'samples': 25080384, 'steps': 130626, 'loss/train': 1.497765064239502} 08/31/2021 12:53:28 - INFO - __main__ - Step 130628: {'lr': 2.0842563352923753e-05, 'samples': 25080576, 'steps': 130627, 'loss/train': 1.394958734512329} 08/31/2021 12:53:28 - INFO - __main__ - Step 130629: {'lr': 2.084044210090305e-05, 'samples': 25080768, 'steps': 130628, 'loss/train': 1.6102869510650635} 08/31/2021 12:53:29 - INFO - __main__ - Step 130630: {'lr': 2.0838320952138113e-05, 'samples': 25080960, 'steps': 130629, 'loss/train': 0.6893580555915833} 08/31/2021 12:53:29 - INFO - __main__ - Step 130631: {'lr': 2.0836199906629883e-05, 'samples': 25081152, 'steps': 130630, 'loss/train': 1.2415927648544312} 08/31/2021 12:53:29 - INFO - __main__ - Step 130632: {'lr': 2.0834078964379304e-05, 'samples': 25081344, 'steps': 130631, 'loss/train': 1.7552655935287476} 08/31/2021 12:53:30 - INFO - __main__ - Step 130633: {'lr': 2.083195812538738e-05, 'samples': 25081536, 'steps': 130632, 'loss/train': 1.247274398803711} 08/31/2021 12:53:31 - INFO - __main__ - Step 130634: {'lr': 2.0829837389655078e-05, 'samples': 25081728, 'steps': 130633, 'loss/train': 0.14343994855880737} 08/31/2021 12:53:32 - INFO - __main__ - Step 130635: {'lr': 2.0827716757183285e-05, 'samples': 25081920, 'steps': 130634, 'loss/train': 1.1850850582122803} 08/31/2021 12:53:32 - INFO - __main__ - Step 130636: {'lr': 2.082559622797295e-05, 'samples': 25082112, 'steps': 130635, 'loss/train': 1.2279759645462036} 08/31/2021 12:53:33 - INFO - __main__ - Step 130637: {'lr': 2.0823475802025092e-05, 'samples': 25082304, 'steps': 130636, 'loss/train': 0.7091848254203796} 08/31/2021 12:53:33 - INFO - __main__ - Step 130638: {'lr': 2.0821355479340638e-05, 'samples': 25082496, 'steps': 130637, 'loss/train': 0.8902133107185364} 08/31/2021 12:53:33 - INFO - __main__ - Step 130639: {'lr': 2.081923525992055e-05, 'samples': 25082688, 'steps': 130638, 'loss/train': 0.0444239117205143} 08/31/2021 12:53:35 - INFO - __main__ - Step 130640: {'lr': 2.0817115143765776e-05, 'samples': 25082880, 'steps': 130639, 'loss/train': 2.092519760131836} 08/31/2021 12:53:36 - INFO - __main__ - Step 130641: {'lr': 2.0814995130877256e-05, 'samples': 25083072, 'steps': 130640, 'loss/train': 0.7458337545394897} 08/31/2021 12:53:36 - INFO - __main__ - Step 130642: {'lr': 2.0812875221255967e-05, 'samples': 25083264, 'steps': 130641, 'loss/train': 1.250641942024231} 08/31/2021 12:53:37 - INFO - __main__ - Step 130643: {'lr': 2.0810755414902878e-05, 'samples': 25083456, 'steps': 130642, 'loss/train': 1.2815076112747192} 08/31/2021 12:53:37 - INFO - __main__ - Step 130644: {'lr': 2.08086357118189e-05, 'samples': 25083648, 'steps': 130643, 'loss/train': 1.6264711618423462} 08/31/2021 12:53:38 - INFO - __main__ - Step 130645: {'lr': 2.0806516112005042e-05, 'samples': 25083840, 'steps': 130644, 'loss/train': 1.0484263896942139} 08/31/2021 12:53:39 - INFO - __main__ - Step 130646: {'lr': 2.0804396615462213e-05, 'samples': 25084032, 'steps': 130645, 'loss/train': 0.7824153304100037} 08/31/2021 12:53:39 - INFO - __main__ - Step 130647: {'lr': 2.0802277222191385e-05, 'samples': 25084224, 'steps': 130646, 'loss/train': 0.7911007404327393} 08/31/2021 12:53:40 - INFO - __main__ - Step 130648: {'lr': 2.080015793219356e-05, 'samples': 25084416, 'steps': 130647, 'loss/train': 0.8463982939720154} 08/31/2021 12:53:40 - INFO - __main__ - Step 130649: {'lr': 2.079803874546962e-05, 'samples': 25084608, 'steps': 130648, 'loss/train': 1.3596960306167603} 08/31/2021 12:53:41 - INFO - __main__ - Step 130650: {'lr': 2.0795919662020518e-05, 'samples': 25084800, 'steps': 130649, 'loss/train': 1.0964514017105103} 08/31/2021 12:53:42 - INFO - __main__ - Step 130651: {'lr': 2.0793800681847276e-05, 'samples': 25084992, 'steps': 130650, 'loss/train': 0.9272884726524353} 08/31/2021 12:53:42 - INFO - __main__ - Step 130652: {'lr': 2.079168180495078e-05, 'samples': 25085184, 'steps': 130651, 'loss/train': 1.200942873954773} 08/31/2021 12:53:43 - INFO - __main__ - Step 130653: {'lr': 2.0789563031332003e-05, 'samples': 25085376, 'steps': 130652, 'loss/train': 1.172011375427246} 08/31/2021 12:53:43 - INFO - __main__ - Step 130654: {'lr': 2.0787444360991948e-05, 'samples': 25085568, 'steps': 130653, 'loss/train': 1.3693525791168213} 08/31/2021 12:53:45 - INFO - __main__ - Step 130655: {'lr': 2.0785325793931524e-05, 'samples': 25085760, 'steps': 130654, 'loss/train': 1.0856777429580688} 08/31/2021 12:53:45 - INFO - __main__ - Step 130656: {'lr': 2.078320733015168e-05, 'samples': 25085952, 'steps': 130655, 'loss/train': 0.9588282108306885} 08/31/2021 12:53:45 - INFO - __main__ - Step 130657: {'lr': 2.0781088969653388e-05, 'samples': 25086144, 'steps': 130656, 'loss/train': 1.6840804815292358} 08/31/2021 12:53:46 - INFO - __main__ - Step 130658: {'lr': 2.0778970712437616e-05, 'samples': 25086336, 'steps': 130657, 'loss/train': 1.1797274351119995} 08/31/2021 12:53:46 - INFO - __main__ - Step 130659: {'lr': 2.077685255850528e-05, 'samples': 25086528, 'steps': 130658, 'loss/train': 1.0963081121444702} 08/31/2021 12:53:47 - INFO - __main__ - Step 130660: {'lr': 2.0774734507857383e-05, 'samples': 25086720, 'steps': 130659, 'loss/train': 0.036629267036914825} 08/31/2021 12:53:48 - INFO - __main__ - Step 130661: {'lr': 2.0772616560494893e-05, 'samples': 25086912, 'steps': 130660, 'loss/train': 0.9928030371665955} 08/31/2021 12:53:48 - INFO - __main__ - Step 130662: {'lr': 2.0770498716418673e-05, 'samples': 25087104, 'steps': 130661, 'loss/train': 1.4827721118927002} 08/31/2021 12:53:49 - INFO - __main__ - Step 130663: {'lr': 2.076838097562972e-05, 'samples': 25087296, 'steps': 130662, 'loss/train': 0.9438251256942749} 08/31/2021 12:53:49 - INFO - __main__ - Step 130664: {'lr': 2.0766263338129003e-05, 'samples': 25087488, 'steps': 130663, 'loss/train': 1.1962209939956665} 08/31/2021 12:53:49 - INFO - __main__ - Step 130665: {'lr': 2.0764145803917472e-05, 'samples': 25087680, 'steps': 130664, 'loss/train': 1.2417880296707153} 08/31/2021 12:53:51 - INFO - __main__ - Step 130666: {'lr': 2.0762028372996093e-05, 'samples': 25087872, 'steps': 130665, 'loss/train': 0.5995838046073914} 08/31/2021 12:53:52 - INFO - __main__ - Step 130667: {'lr': 2.0759911045365788e-05, 'samples': 25088064, 'steps': 130666, 'loss/train': 0.9041934609413147} 08/31/2021 12:53:52 - INFO - __main__ - Step 130668: {'lr': 2.075779382102755e-05, 'samples': 25088256, 'steps': 130667, 'loss/train': 0.6026833057403564} 08/31/2021 12:53:52 - INFO - __main__ - Step 130669: {'lr': 2.0755676699982294e-05, 'samples': 25088448, 'steps': 130668, 'loss/train': 0.849205493927002} 08/31/2021 12:53:53 - INFO - __main__ - Step 130670: {'lr': 2.0753559682231e-05, 'samples': 25088640, 'steps': 130669, 'loss/train': 0.9962905645370483} 08/31/2021 12:53:54 - INFO - __main__ - Step 130671: {'lr': 2.0751442767774605e-05, 'samples': 25088832, 'steps': 130670, 'loss/train': 0.5621396899223328} 08/31/2021 12:53:55 - INFO - __main__ - Step 130672: {'lr': 2.074932595661408e-05, 'samples': 25089024, 'steps': 130671, 'loss/train': 1.0504969358444214} 08/31/2021 12:53:55 - INFO - __main__ - Step 130673: {'lr': 2.074720924875037e-05, 'samples': 25089216, 'steps': 130672, 'loss/train': 0.947629988193512} 08/31/2021 12:53:55 - INFO - __main__ - Step 130674: {'lr': 2.074509264418442e-05, 'samples': 25089408, 'steps': 130673, 'loss/train': 1.2070724964141846} 08/31/2021 12:53:56 - INFO - __main__ - Step 130675: {'lr': 2.074297614291726e-05, 'samples': 25089600, 'steps': 130674, 'loss/train': 0.6033847332000732} 08/31/2021 12:53:57 - INFO - __main__ - Step 130676: {'lr': 2.0740859744949713e-05, 'samples': 25089792, 'steps': 130675, 'loss/train': 1.4167068004608154} 08/31/2021 12:53:58 - INFO - __main__ - Step 130677: {'lr': 2.0738743450282816e-05, 'samples': 25089984, 'steps': 130676, 'loss/train': 0.9288438558578491} 08/31/2021 12:53:58 - INFO - __main__ - Step 130678: {'lr': 2.073662725891748e-05, 'samples': 25090176, 'steps': 130677, 'loss/train': 1.4403282403945923} 08/31/2021 12:53:58 - INFO - __main__ - Step 130679: {'lr': 2.0734511170854704e-05, 'samples': 25090368, 'steps': 130678, 'loss/train': 1.0434834957122803} 08/31/2021 12:53:59 - INFO - __main__ - Step 130680: {'lr': 2.0732395186095403e-05, 'samples': 25090560, 'steps': 130679, 'loss/train': 0.8241150975227356} 08/31/2021 12:54:00 - INFO - __main__ - Step 130681: {'lr': 2.0730279304640552e-05, 'samples': 25090752, 'steps': 130680, 'loss/train': 0.7973100543022156} 08/31/2021 12:54:01 - INFO - __main__ - Step 130682: {'lr': 2.0728163526491124e-05, 'samples': 25090944, 'steps': 130681, 'loss/train': 1.3459997177124023} 08/31/2021 12:54:01 - INFO - __main__ - Step 130683: {'lr': 2.0726047851648026e-05, 'samples': 25091136, 'steps': 130682, 'loss/train': 1.4849402904510498} 08/31/2021 12:54:01 - INFO - __main__ - Step 130684: {'lr': 2.072393228011221e-05, 'samples': 25091328, 'steps': 130683, 'loss/train': 1.231571912765503} 08/31/2021 12:54:02 - INFO - __main__ - Step 130685: {'lr': 2.0721816811884704e-05, 'samples': 25091520, 'steps': 130684, 'loss/train': 1.3880615234375} 08/31/2021 12:54:03 - INFO - __main__ - Step 130686: {'lr': 2.071970144696636e-05, 'samples': 25091712, 'steps': 130685, 'loss/train': 1.0453273057937622} 08/31/2021 12:54:04 - INFO - __main__ - Step 130687: {'lr': 2.071758618535821e-05, 'samples': 25091904, 'steps': 130686, 'loss/train': 1.049162745475769} 08/31/2021 12:54:04 - INFO - __main__ - Step 130688: {'lr': 2.07154710270612e-05, 'samples': 25092096, 'steps': 130687, 'loss/train': 1.428672432899475} 08/31/2021 12:54:04 - INFO - __main__ - Step 130689: {'lr': 2.071335597207624e-05, 'samples': 25092288, 'steps': 130688, 'loss/train': 0.855199933052063} 08/31/2021 12:54:05 - INFO - __main__ - Step 130690: {'lr': 2.071124102040428e-05, 'samples': 25092480, 'steps': 130689, 'loss/train': 0.8475576043128967} 08/31/2021 12:54:05 - INFO - __main__ - Step 130691: {'lr': 2.0709126172046316e-05, 'samples': 25092672, 'steps': 130690, 'loss/train': 0.9722261428833008} 08/31/2021 12:54:07 - INFO - __main__ - Step 130692: {'lr': 2.0707011427003292e-05, 'samples': 25092864, 'steps': 130691, 'loss/train': 0.9836976528167725} 08/31/2021 12:54:08 - INFO - __main__ - Step 130693: {'lr': 2.0704896785276122e-05, 'samples': 25093056, 'steps': 130692, 'loss/train': 1.5449661016464233} 08/31/2021 12:54:08 - INFO - __main__ - Step 130694: {'lr': 2.070278224686581e-05, 'samples': 25093248, 'steps': 130693, 'loss/train': 0.9101911783218384} 08/31/2021 12:54:08 - INFO - __main__ - Step 130695: {'lr': 2.0700667811773266e-05, 'samples': 25093440, 'steps': 130694, 'loss/train': 1.2594016790390015} 08/31/2021 12:54:09 - INFO - __main__ - Step 130696: {'lr': 2.0698553479999467e-05, 'samples': 25093632, 'steps': 130695, 'loss/train': 1.4255796670913696} 08/31/2021 12:54:10 - INFO - __main__ - Step 130697: {'lr': 2.069643925154538e-05, 'samples': 25093824, 'steps': 130696, 'loss/train': 0.8941681981086731} 08/31/2021 12:54:11 - INFO - __main__ - Step 130698: {'lr': 2.0694325126411923e-05, 'samples': 25094016, 'steps': 130697, 'loss/train': 1.167417049407959} 08/31/2021 12:54:11 - INFO - __main__ - Step 130699: {'lr': 2.0692211104600066e-05, 'samples': 25094208, 'steps': 130698, 'loss/train': 1.0043846368789673} 08/31/2021 12:54:12 - INFO - __main__ - Step 130700: {'lr': 2.0690097186110756e-05, 'samples': 25094400, 'steps': 130699, 'loss/train': 1.368117332458496} 08/31/2021 12:54:12 - INFO - __main__ - Step 130701: {'lr': 2.0687983370944936e-05, 'samples': 25094592, 'steps': 130700, 'loss/train': 0.07677077502012253} 08/31/2021 12:54:14 - INFO - __main__ - Step 130702: {'lr': 2.0685869659103658e-05, 'samples': 25094784, 'steps': 130701, 'loss/train': 0.06178319454193115} 08/31/2021 12:54:14 - INFO - __main__ - Step 130703: {'lr': 2.0683756050587697e-05, 'samples': 25094976, 'steps': 130702, 'loss/train': 1.2484025955200195} 08/31/2021 12:54:15 - INFO - __main__ - Step 130704: {'lr': 2.0681642545398145e-05, 'samples': 25095168, 'steps': 130703, 'loss/train': 2.1254987716674805} 08/31/2021 12:54:15 - INFO - __main__ - Step 130705: {'lr': 2.067952914353588e-05, 'samples': 25095360, 'steps': 130704, 'loss/train': 1.8713985681533813} 08/31/2021 12:54:15 - INFO - __main__ - Step 130706: {'lr': 2.0677415845001878e-05, 'samples': 25095552, 'steps': 130705, 'loss/train': 1.354704737663269} 08/31/2021 12:54:16 - INFO - __main__ - Step 130707: {'lr': 2.0675302649797084e-05, 'samples': 25095744, 'steps': 130706, 'loss/train': 1.0280933380126953} 08/31/2021 12:54:17 - INFO - __main__ - Step 130708: {'lr': 2.0673189557922493e-05, 'samples': 25095936, 'steps': 130707, 'loss/train': 1.2220962047576904} 08/31/2021 12:54:18 - INFO - __main__ - Step 130709: {'lr': 2.0671076569379e-05, 'samples': 25096128, 'steps': 130708, 'loss/train': 0.7367117404937744} 08/31/2021 12:54:18 - INFO - __main__ - Step 130710: {'lr': 2.0668963684167597e-05, 'samples': 25096320, 'steps': 130709, 'loss/train': 1.060173511505127} 08/31/2021 12:54:19 - INFO - __main__ - Step 130711: {'lr': 2.0666850902289203e-05, 'samples': 25096512, 'steps': 130710, 'loss/train': 0.46089258790016174} 08/31/2021 12:54:19 - INFO - __main__ - Step 130712: {'lr': 2.066473822374479e-05, 'samples': 25096704, 'steps': 130711, 'loss/train': 0.04737171530723572} 08/31/2021 12:54:20 - INFO - __main__ - Step 130713: {'lr': 2.0662625648535326e-05, 'samples': 25096896, 'steps': 130712, 'loss/train': 0.49783289432525635} 08/31/2021 12:54:21 - INFO - __main__ - Step 130714: {'lr': 2.0660513176661707e-05, 'samples': 25097088, 'steps': 130713, 'loss/train': 1.0163240432739258} 08/31/2021 12:54:21 - INFO - __main__ - Step 130715: {'lr': 2.0658400808125006e-05, 'samples': 25097280, 'steps': 130714, 'loss/train': 0.07504038512706757} 08/31/2021 12:54:22 - INFO - __main__ - Step 130716: {'lr': 2.0656288542926033e-05, 'samples': 25097472, 'steps': 130715, 'loss/train': 1.2556453943252563} 08/31/2021 12:54:22 - INFO - __main__ - Step 130717: {'lr': 2.065417638106579e-05, 'samples': 25097664, 'steps': 130716, 'loss/train': 0.5208114385604858} 08/31/2021 12:54:24 - INFO - __main__ - Step 130718: {'lr': 2.065206432254524e-05, 'samples': 25097856, 'steps': 130717, 'loss/train': 0.8038511872291565} 08/31/2021 12:54:24 - INFO - __main__ - Step 130719: {'lr': 2.064995236736533e-05, 'samples': 25098048, 'steps': 130718, 'loss/train': 1.4176734685897827} 08/31/2021 12:54:24 - INFO - __main__ - Step 130720: {'lr': 2.064784051552701e-05, 'samples': 25098240, 'steps': 130719, 'loss/train': 0.8291353583335876} 08/31/2021 12:54:25 - INFO - __main__ - Step 130721: {'lr': 2.0645728767031246e-05, 'samples': 25098432, 'steps': 130720, 'loss/train': 0.6210416555404663} 08/31/2021 12:54:25 - INFO - __main__ - Step 130722: {'lr': 2.0643617121878954e-05, 'samples': 25098624, 'steps': 130721, 'loss/train': 1.2457423210144043} 08/31/2021 12:54:25 - INFO - __main__ - Step 130723: {'lr': 2.0641505580071136e-05, 'samples': 25098816, 'steps': 130722, 'loss/train': 0.41202253103256226} 08/31/2021 12:54:27 - INFO - __main__ - Step 130724: {'lr': 2.0639394141608704e-05, 'samples': 25099008, 'steps': 130723, 'loss/train': 0.34803640842437744} 08/31/2021 12:54:28 - INFO - __main__ - Step 130725: {'lr': 2.0637282806492602e-05, 'samples': 25099200, 'steps': 130724, 'loss/train': 1.2256335020065308} 08/31/2021 12:54:28 - INFO - __main__ - Step 130726: {'lr': 2.063517157472383e-05, 'samples': 25099392, 'steps': 130725, 'loss/train': 1.4076073169708252} 08/31/2021 12:54:28 - INFO - __main__ - Step 130727: {'lr': 2.0633060446303308e-05, 'samples': 25099584, 'steps': 130726, 'loss/train': 1.5666041374206543} 08/31/2021 12:54:29 - INFO - __main__ - Step 130728: {'lr': 2.0630949421232002e-05, 'samples': 25099776, 'steps': 130727, 'loss/train': 1.7214618921279907} 08/31/2021 12:54:30 - INFO - __main__ - Step 130729: {'lr': 2.0628838499510832e-05, 'samples': 25099968, 'steps': 130728, 'loss/train': 0.8752143383026123} 08/31/2021 12:54:30 - INFO - __main__ - Step 130730: {'lr': 2.0626727681140766e-05, 'samples': 25100160, 'steps': 130729, 'loss/train': 0.9539189338684082} 08/31/2021 12:54:31 - INFO - __main__ - Step 130731: {'lr': 2.0624616966122777e-05, 'samples': 25100352, 'steps': 130730, 'loss/train': 1.2915631532669067} 08/31/2021 12:54:31 - INFO - __main__ - Step 130732: {'lr': 2.062250635445778e-05, 'samples': 25100544, 'steps': 130731, 'loss/train': 1.0720458030700684} 08/31/2021 12:54:31 - INFO - __main__ - Step 130733: {'lr': 2.0620395846146723e-05, 'samples': 25100736, 'steps': 130732, 'loss/train': 0.7548136115074158} 08/31/2021 12:54:33 - INFO - __main__ - Step 130734: {'lr': 2.06182854411906e-05, 'samples': 25100928, 'steps': 130733, 'loss/train': 1.1498470306396484} 08/31/2021 12:54:33 - INFO - __main__ - Step 130735: {'lr': 2.0616175139590328e-05, 'samples': 25101120, 'steps': 130734, 'loss/train': 0.7740845084190369} 08/31/2021 12:54:34 - INFO - __main__ - Step 130736: {'lr': 2.061406494134688e-05, 'samples': 25101312, 'steps': 130735, 'loss/train': 0.9405759572982788} 08/31/2021 12:54:34 - INFO - __main__ - Step 130737: {'lr': 2.061195484646117e-05, 'samples': 25101504, 'steps': 130736, 'loss/train': 1.1694345474243164} 08/31/2021 12:54:34 - INFO - __main__ - Step 130738: {'lr': 2.0609844854934197e-05, 'samples': 25101696, 'steps': 130737, 'loss/train': 1.1194076538085938} 08/31/2021 12:54:36 - INFO - __main__ - Step 130739: {'lr': 2.0607734966766877e-05, 'samples': 25101888, 'steps': 130738, 'loss/train': 1.0760198831558228} 08/31/2021 12:54:36 - INFO - __main__ - Step 130740: {'lr': 2.0605625181960187e-05, 'samples': 25102080, 'steps': 130739, 'loss/train': 0.056265272200107574} 08/31/2021 12:54:37 - INFO - __main__ - Step 130741: {'lr': 2.0603515500515036e-05, 'samples': 25102272, 'steps': 130740, 'loss/train': 0.950266420841217} 08/31/2021 12:54:37 - INFO - __main__ - Step 130742: {'lr': 2.0601405922432455e-05, 'samples': 25102464, 'steps': 130741, 'loss/train': 1.0090404748916626} 08/31/2021 12:54:37 - INFO - __main__ - Step 130743: {'lr': 2.05992964477133e-05, 'samples': 25102656, 'steps': 130742, 'loss/train': 1.1220506429672241} 08/31/2021 12:54:39 - INFO - __main__ - Step 130744: {'lr': 2.0597187076358575e-05, 'samples': 25102848, 'steps': 130743, 'loss/train': 1.2798517942428589} 08/31/2021 12:54:40 - INFO - __main__ - Step 130745: {'lr': 2.0595077808369196e-05, 'samples': 25103040, 'steps': 130744, 'loss/train': 1.0549209117889404} 08/31/2021 12:54:40 - INFO - __main__ - Step 130746: {'lr': 2.0592968643746158e-05, 'samples': 25103232, 'steps': 130745, 'loss/train': 1.2698625326156616} 08/31/2021 12:54:41 - INFO - __main__ - Step 130747: {'lr': 2.059085958249038e-05, 'samples': 25103424, 'steps': 130746, 'loss/train': 0.12030596286058426} 08/31/2021 12:54:41 - INFO - __main__ - Step 130748: {'lr': 2.0588750624602802e-05, 'samples': 25103616, 'steps': 130747, 'loss/train': 1.2633907794952393} 08/31/2021 12:54:42 - INFO - __main__ - Step 130749: {'lr': 2.05866417700844e-05, 'samples': 25103808, 'steps': 130748, 'loss/train': 1.04026198387146} 08/31/2021 12:54:43 - INFO - __main__ - Step 130750: {'lr': 2.058453301893612e-05, 'samples': 25104000, 'steps': 130749, 'loss/train': 1.1164944171905518} 08/31/2021 12:54:43 - INFO - __main__ - Step 130751: {'lr': 2.0582424371158925e-05, 'samples': 25104192, 'steps': 130750, 'loss/train': 0.9225056767463684} 08/31/2021 12:54:43 - INFO - __main__ - Step 130752: {'lr': 2.0580315826753736e-05, 'samples': 25104384, 'steps': 130751, 'loss/train': 0.6647772789001465} 08/31/2021 12:54:44 - INFO - __main__ - Step 130753: {'lr': 2.0578207385721526e-05, 'samples': 25104576, 'steps': 130752, 'loss/train': 1.006380319595337} 08/31/2021 12:54:45 - INFO - __main__ - Step 130754: {'lr': 2.0576099048063236e-05, 'samples': 25104768, 'steps': 130753, 'loss/train': 1.3926990032196045} 08/31/2021 12:54:46 - INFO - __main__ - Step 130755: {'lr': 2.0573990813779836e-05, 'samples': 25104960, 'steps': 130754, 'loss/train': 0.48499342799186707} 08/31/2021 12:54:46 - INFO - __main__ - Step 130756: {'lr': 2.057188268287222e-05, 'samples': 25105152, 'steps': 130755, 'loss/train': 0.4959973692893982} 08/31/2021 12:54:46 - INFO - __main__ - Step 130757: {'lr': 2.0569774655341378e-05, 'samples': 25105344, 'steps': 130756, 'loss/train': 1.0025970935821533} 08/31/2021 12:54:47 - INFO - __main__ - Step 130758: {'lr': 2.0567666731188263e-05, 'samples': 25105536, 'steps': 130757, 'loss/train': 0.9650082588195801} 08/31/2021 12:54:48 - INFO - __main__ - Step 130759: {'lr': 2.056555891041381e-05, 'samples': 25105728, 'steps': 130758, 'loss/train': 1.2736384868621826} 08/31/2021 12:54:49 - INFO - __main__ - Step 130760: {'lr': 2.0563451193018974e-05, 'samples': 25105920, 'steps': 130759, 'loss/train': 0.1563195437192917} 08/31/2021 12:54:49 - INFO - __main__ - Step 130761: {'lr': 2.0561343579004716e-05, 'samples': 25106112, 'steps': 130760, 'loss/train': 1.2694510221481323} 08/31/2021 12:54:50 - INFO - __main__ - Step 130762: {'lr': 2.0559236068371984e-05, 'samples': 25106304, 'steps': 130761, 'loss/train': 0.8010717630386353} 08/31/2021 12:54:50 - INFO - __main__ - Step 130763: {'lr': 2.0557128661121694e-05, 'samples': 25106496, 'steps': 130762, 'loss/train': 1.3305073976516724} 08/31/2021 12:54:51 - INFO - __main__ - Step 130764: {'lr': 2.0555021357254844e-05, 'samples': 25106688, 'steps': 130763, 'loss/train': 0.2592681646347046} 08/31/2021 12:54:52 - INFO - __main__ - Step 130765: {'lr': 2.0552914156772323e-05, 'samples': 25106880, 'steps': 130764, 'loss/train': 1.4330207109451294} 08/31/2021 12:54:52 - INFO - __main__ - Step 130766: {'lr': 2.0550807059675157e-05, 'samples': 25107072, 'steps': 130765, 'loss/train': 0.9162783622741699} 08/31/2021 12:54:53 - INFO - __main__ - Step 130767: {'lr': 2.0548700065964238e-05, 'samples': 25107264, 'steps': 130766, 'loss/train': 2.091822862625122} 08/31/2021 12:54:53 - INFO - __main__ - Step 130768: {'lr': 2.054659317564056e-05, 'samples': 25107456, 'steps': 130767, 'loss/train': 1.3025684356689453} 08/31/2021 12:54:54 - INFO - __main__ - Step 130769: {'lr': 2.054448638870507e-05, 'samples': 25107648, 'steps': 130768, 'loss/train': 1.3811479806900024} 08/31/2021 12:54:55 - INFO - __main__ - Step 130770: {'lr': 2.0542379705158626e-05, 'samples': 25107840, 'steps': 130769, 'loss/train': 1.255185842514038} 08/31/2021 12:54:55 - INFO - __main__ - Step 130771: {'lr': 2.0540273125002283e-05, 'samples': 25108032, 'steps': 130770, 'loss/train': 1.665639877319336} 08/31/2021 12:54:56 - INFO - __main__ - Step 130772: {'lr': 2.0538166648236933e-05, 'samples': 25108224, 'steps': 130771, 'loss/train': 0.655951738357544} 08/31/2021 12:54:56 - INFO - __main__ - Step 130773: {'lr': 2.0536060274863545e-05, 'samples': 25108416, 'steps': 130772, 'loss/train': 1.3195414543151855} 08/31/2021 12:54:56 - INFO - __main__ - Step 130774: {'lr': 2.053395400488309e-05, 'samples': 25108608, 'steps': 130773, 'loss/train': 1.2361198663711548} 08/31/2021 12:54:58 - INFO - __main__ - Step 130775: {'lr': 2.053184783829648e-05, 'samples': 25108800, 'steps': 130774, 'loss/train': 1.1533523797988892} 08/31/2021 12:54:58 - INFO - __main__ - Step 130776: {'lr': 2.0529741775104664e-05, 'samples': 25108992, 'steps': 130775, 'loss/train': 0.02595873363316059} 08/31/2021 12:54:59 - INFO - __main__ - Step 130777: {'lr': 2.0527635815308615e-05, 'samples': 25109184, 'steps': 130776, 'loss/train': 0.750632107257843} 08/31/2021 12:54:59 - INFO - __main__ - Step 130778: {'lr': 2.0525529958909274e-05, 'samples': 25109376, 'steps': 130777, 'loss/train': 0.059328075498342514} 08/31/2021 12:54:59 - INFO - __main__ - Step 130779: {'lr': 2.052342420590758e-05, 'samples': 25109568, 'steps': 130778, 'loss/train': 0.8726428151130676} 08/31/2021 12:55:01 - INFO - __main__ - Step 130780: {'lr': 2.0521318556304513e-05, 'samples': 25109760, 'steps': 130779, 'loss/train': 0.998401403427124} 08/31/2021 12:55:02 - INFO - __main__ - Step 130781: {'lr': 2.0519213010100984e-05, 'samples': 25109952, 'steps': 130780, 'loss/train': 0.04560933634638786} 08/31/2021 12:55:02 - INFO - __main__ - Step 130782: {'lr': 2.0517107567297992e-05, 'samples': 25110144, 'steps': 130781, 'loss/train': 0.0613100565969944} 08/31/2021 12:55:02 - INFO - __main__ - Step 130783: {'lr': 2.051500222789643e-05, 'samples': 25110336, 'steps': 130782, 'loss/train': 1.2220613956451416} 08/31/2021 12:55:03 - INFO - __main__ - Step 130784: {'lr': 2.0512896991897235e-05, 'samples': 25110528, 'steps': 130783, 'loss/train': 0.8038278818130493} 08/31/2021 12:55:04 - INFO - __main__ - Step 130785: {'lr': 2.051079185930141e-05, 'samples': 25110720, 'steps': 130784, 'loss/train': 0.3624303638935089} 08/31/2021 12:55:05 - INFO - __main__ - Step 130786: {'lr': 2.050868683010987e-05, 'samples': 25110912, 'steps': 130785, 'loss/train': 0.8163852691650391} 08/31/2021 12:55:05 - INFO - __main__ - Step 130787: {'lr': 2.0506581904323585e-05, 'samples': 25111104, 'steps': 130786, 'loss/train': 1.1001346111297607} 08/31/2021 12:55:05 - INFO - __main__ - Step 130788: {'lr': 2.0504477081943503e-05, 'samples': 25111296, 'steps': 130787, 'loss/train': 1.4239660501480103} 08/31/2021 12:55:06 - INFO - __main__ - Step 130789: {'lr': 2.0502372362970534e-05, 'samples': 25111488, 'steps': 130788, 'loss/train': 0.901962399482727} 08/31/2021 12:55:06 - INFO - __main__ - Step 130790: {'lr': 2.0500267747405654e-05, 'samples': 25111680, 'steps': 130789, 'loss/train': 0.9008606672286987} 08/31/2021 12:55:08 - INFO - __main__ - Step 130791: {'lr': 2.0498163235249833e-05, 'samples': 25111872, 'steps': 130790, 'loss/train': 4.005881309509277} 08/31/2021 12:55:08 - INFO - __main__ - Step 130792: {'lr': 2.049605882650399e-05, 'samples': 25112064, 'steps': 130791, 'loss/train': 1.523616909980774} 08/31/2021 12:55:08 - INFO - __main__ - Step 130793: {'lr': 2.0493954521169088e-05, 'samples': 25112256, 'steps': 130792, 'loss/train': 0.9523834586143494} 08/31/2021 12:55:09 - INFO - __main__ - Step 130794: {'lr': 2.0491850319246053e-05, 'samples': 25112448, 'steps': 130793, 'loss/train': 0.6855899691581726} 08/31/2021 12:55:09 - INFO - __main__ - Step 130795: {'lr': 2.048974622073588e-05, 'samples': 25112640, 'steps': 130794, 'loss/train': 0.03288421779870987} 08/31/2021 12:55:11 - INFO - __main__ - Step 130796: {'lr': 2.048764222563951e-05, 'samples': 25112832, 'steps': 130795, 'loss/train': 0.9938204884529114} 08/31/2021 12:55:12 - INFO - __main__ - Step 130797: {'lr': 2.0485538333957803e-05, 'samples': 25113024, 'steps': 130796, 'loss/train': 0.660838782787323} 08/31/2021 12:55:12 - INFO - __main__ - Step 130798: {'lr': 2.0483434545691792e-05, 'samples': 25113216, 'steps': 130797, 'loss/train': 1.0487276315689087} 08/31/2021 12:55:12 - INFO - __main__ - Step 130799: {'lr': 2.0481330860842388e-05, 'samples': 25113408, 'steps': 130798, 'loss/train': 0.08547279238700867} 08/31/2021 12:55:13 - INFO - __main__ - Step 130800: {'lr': 2.0479227279410568e-05, 'samples': 25113600, 'steps': 130799, 'loss/train': 1.2889647483825684} 08/31/2021 12:55:15 - INFO - __main__ - Step 130801: {'lr': 2.047712380139727e-05, 'samples': 25113792, 'steps': 130800, 'loss/train': 0.9292389750480652} 08/31/2021 12:55:15 - INFO - __main__ - Step 130802: {'lr': 2.0475020426803437e-05, 'samples': 25113984, 'steps': 130801, 'loss/train': 1.1406270265579224} 08/31/2021 12:55:16 - INFO - __main__ - Step 130803: {'lr': 2.0472917155630017e-05, 'samples': 25114176, 'steps': 130802, 'loss/train': 1.5648568868637085} 08/31/2021 12:55:16 - INFO - __main__ - Step 130804: {'lr': 2.047081398787795e-05, 'samples': 25114368, 'steps': 130803, 'loss/train': 1.7650943994522095} 08/31/2021 12:55:16 - INFO - __main__ - Step 130805: {'lr': 2.0468710923548212e-05, 'samples': 25114560, 'steps': 130804, 'loss/train': 0.8937423229217529} 08/31/2021 12:55:18 - INFO - __main__ - Step 130806: {'lr': 2.0466607962641714e-05, 'samples': 25114752, 'steps': 130805, 'loss/train': 0.6479842066764832} 08/31/2021 12:55:18 - INFO - __main__ - Step 130807: {'lr': 2.0464505105159432e-05, 'samples': 25114944, 'steps': 130806, 'loss/train': 1.0224297046661377} 08/31/2021 12:55:19 - INFO - __main__ - Step 130808: {'lr': 2.0462402351102334e-05, 'samples': 25115136, 'steps': 130807, 'loss/train': 1.0626022815704346} 08/31/2021 12:55:19 - INFO - __main__ - Step 130809: {'lr': 2.046029970047128e-05, 'samples': 25115328, 'steps': 130808, 'loss/train': 0.12915295362472534} 08/31/2021 12:55:20 - INFO - __main__ - Step 130810: {'lr': 2.04581971532673e-05, 'samples': 25115520, 'steps': 130809, 'loss/train': 1.4744272232055664} 08/31/2021 12:55:20 - INFO - __main__ - Step 130811: {'lr': 2.0456094709491306e-05, 'samples': 25115712, 'steps': 130810, 'loss/train': 1.624212622642517} 08/31/2021 12:55:21 - INFO - __main__ - Step 130812: {'lr': 2.045399236914425e-05, 'samples': 25115904, 'steps': 130811, 'loss/train': 0.975640594959259} 08/31/2021 12:55:22 - INFO - __main__ - Step 130813: {'lr': 2.045189013222709e-05, 'samples': 25116096, 'steps': 130812, 'loss/train': 1.0365824699401855} 08/31/2021 12:55:22 - INFO - __main__ - Step 130814: {'lr': 2.0449787998740756e-05, 'samples': 25116288, 'steps': 130813, 'loss/train': 0.33477067947387695} 08/31/2021 12:55:23 - INFO - __main__ - Step 130815: {'lr': 2.0447685968686207e-05, 'samples': 25116480, 'steps': 130814, 'loss/train': 0.8983657956123352} 08/31/2021 12:55:23 - INFO - __main__ - Step 130816: {'lr': 2.0445584042064397e-05, 'samples': 25116672, 'steps': 130815, 'loss/train': 1.0200529098510742} 08/31/2021 12:55:25 - INFO - __main__ - Step 130817: {'lr': 2.0443482218876264e-05, 'samples': 25116864, 'steps': 130816, 'loss/train': 1.068611979484558} 08/31/2021 12:55:25 - INFO - __main__ - Step 130818: {'lr': 2.0441380499122725e-05, 'samples': 25117056, 'steps': 130817, 'loss/train': 1.171821117401123} 08/31/2021 12:55:25 - INFO - __main__ - Step 130819: {'lr': 2.0439278882804835e-05, 'samples': 25117248, 'steps': 130818, 'loss/train': 1.5753592252731323} 08/31/2021 12:55:26 - INFO - __main__ - Step 130820: {'lr': 2.0437177369923427e-05, 'samples': 25117440, 'steps': 130819, 'loss/train': 0.2376108169555664} 08/31/2021 12:55:26 - INFO - __main__ - Step 130821: {'lr': 2.0435075960479443e-05, 'samples': 25117632, 'steps': 130820, 'loss/train': 1.3102809190750122} 08/31/2021 12:55:28 - INFO - __main__ - Step 130822: {'lr': 2.0432974654473913e-05, 'samples': 25117824, 'steps': 130821, 'loss/train': 0.45102447271347046} 08/31/2021 12:55:28 - INFO - __main__ - Step 130823: {'lr': 2.043087345190772e-05, 'samples': 25118016, 'steps': 130822, 'loss/train': 1.1611542701721191} 08/31/2021 12:55:28 - INFO - __main__ - Step 130824: {'lr': 2.0428772352781843e-05, 'samples': 25118208, 'steps': 130823, 'loss/train': 0.24876289069652557} 08/31/2021 12:55:29 - INFO - __main__ - Step 130825: {'lr': 2.042667135709722e-05, 'samples': 25118400, 'steps': 130824, 'loss/train': 0.9659014344215393} 08/31/2021 12:55:29 - INFO - __main__ - Step 130826: {'lr': 2.0424570464854797e-05, 'samples': 25118592, 'steps': 130825, 'loss/train': 0.4953783452510834} 08/31/2021 12:55:30 - INFO - __main__ - Step 130827: {'lr': 2.0422469676055516e-05, 'samples': 25118784, 'steps': 130826, 'loss/train': 1.4367026090621948} 08/31/2021 12:55:31 - INFO - __main__ - Step 130828: {'lr': 2.042036899070032e-05, 'samples': 25118976, 'steps': 130827, 'loss/train': 1.6240371465682983} 08/31/2021 12:55:31 - INFO - __main__ - Step 130829: {'lr': 2.041826840879016e-05, 'samples': 25119168, 'steps': 130828, 'loss/train': 0.8891953229904175} 08/31/2021 12:55:32 - INFO - __main__ - Step 130830: {'lr': 2.0416167930326053e-05, 'samples': 25119360, 'steps': 130829, 'loss/train': 0.8053823709487915} 08/31/2021 12:55:32 - INFO - __main__ - Step 130831: {'lr': 2.0414067555308808e-05, 'samples': 25119552, 'steps': 130830, 'loss/train': 0.4881621301174164} 08/31/2021 12:55:34 - INFO - __main__ - Step 130832: {'lr': 2.0411967283739453e-05, 'samples': 25119744, 'steps': 130831, 'loss/train': 1.0942983627319336} 08/31/2021 12:55:34 - INFO - __main__ - Step 130833: {'lr': 2.040986711561893e-05, 'samples': 25119936, 'steps': 130832, 'loss/train': 1.5913947820663452} 08/31/2021 12:55:34 - INFO - __main__ - Step 130834: {'lr': 2.0407767050948155e-05, 'samples': 25120128, 'steps': 130833, 'loss/train': 0.9678110480308533} 08/31/2021 12:55:35 - INFO - __main__ - Step 130835: {'lr': 2.040566708972813e-05, 'samples': 25120320, 'steps': 130834, 'loss/train': 0.5516170859336853} 08/31/2021 12:55:35 - INFO - __main__ - Step 130836: {'lr': 2.040356723195974e-05, 'samples': 25120512, 'steps': 130835, 'loss/train': 1.3519213199615479} 08/31/2021 12:55:35 - INFO - __main__ - Step 130837: {'lr': 2.0401467477643987e-05, 'samples': 25120704, 'steps': 130836, 'loss/train': 0.24681498110294342} 08/31/2021 12:55:37 - INFO - __main__ - Step 130838: {'lr': 2.0399367826781755e-05, 'samples': 25120896, 'steps': 130837, 'loss/train': 0.5636736750602722} 08/31/2021 12:55:37 - INFO - __main__ - Step 130839: {'lr': 2.039726827937405e-05, 'samples': 25121088, 'steps': 130838, 'loss/train': 0.7194997668266296} 08/31/2021 12:55:38 - INFO - __main__ - Step 130840: {'lr': 2.039516883542178e-05, 'samples': 25121280, 'steps': 130839, 'loss/train': 1.495559811592102} 08/31/2021 12:55:38 - INFO - __main__ - Step 130841: {'lr': 2.0393069494925974e-05, 'samples': 25121472, 'steps': 130840, 'loss/train': 0.9582447409629822} 08/31/2021 12:55:38 - INFO - __main__ - Step 130842: {'lr': 2.039097025788744e-05, 'samples': 25121664, 'steps': 130841, 'loss/train': 1.0764211416244507} 08/31/2021 12:55:40 - INFO - __main__ - Step 130843: {'lr': 2.038887112430718e-05, 'samples': 25121856, 'steps': 130842, 'loss/train': 1.0857263803482056} 08/31/2021 12:55:41 - INFO - __main__ - Step 130844: {'lr': 2.0386772094186184e-05, 'samples': 25122048, 'steps': 130843, 'loss/train': 1.271585464477539} 08/31/2021 12:55:41 - INFO - __main__ - Step 130845: {'lr': 2.0384673167525347e-05, 'samples': 25122240, 'steps': 130844, 'loss/train': 0.8718922734260559} 08/31/2021 12:55:41 - INFO - __main__ - Step 130846: {'lr': 2.0382574344325638e-05, 'samples': 25122432, 'steps': 130845, 'loss/train': 1.2424544095993042} 08/31/2021 12:55:42 - INFO - __main__ - Step 130847: {'lr': 2.0380475624588e-05, 'samples': 25122624, 'steps': 130846, 'loss/train': 1.2818163633346558} 08/31/2021 12:55:43 - INFO - __main__ - Step 130848: {'lr': 2.0378377008313352e-05, 'samples': 25122816, 'steps': 130847, 'loss/train': 1.0562535524368286} 08/31/2021 12:55:43 - INFO - __main__ - Step 130849: {'lr': 2.0376278495502693e-05, 'samples': 25123008, 'steps': 130848, 'loss/train': 0.5435746908187866} 08/31/2021 12:55:44 - INFO - __main__ - Step 130850: {'lr': 2.0374180086156936e-05, 'samples': 25123200, 'steps': 130849, 'loss/train': 1.251164197921753} 08/31/2021 12:55:44 - INFO - __main__ - Step 130851: {'lr': 2.0372081780277053e-05, 'samples': 25123392, 'steps': 130850, 'loss/train': 0.2751312553882599} 08/31/2021 12:55:44 - INFO - __main__ - Step 130852: {'lr': 2.036998357786396e-05, 'samples': 25123584, 'steps': 130851, 'loss/train': 1.342559814453125} 08/31/2021 12:55:47 - INFO - __main__ - Step 130853: {'lr': 2.0367885478918575e-05, 'samples': 25123776, 'steps': 130852, 'loss/train': 1.0195107460021973} 08/31/2021 12:55:47 - INFO - __main__ - Step 130854: {'lr': 2.0365787483441895e-05, 'samples': 25123968, 'steps': 130853, 'loss/train': 1.7264750003814697} 08/31/2021 12:55:48 - INFO - __main__ - Step 130855: {'lr': 2.0363689591434836e-05, 'samples': 25124160, 'steps': 130854, 'loss/train': 1.4145439863204956} 08/31/2021 12:55:48 - INFO - __main__ - Step 130856: {'lr': 2.036159180289837e-05, 'samples': 25124352, 'steps': 130855, 'loss/train': 0.2678127884864807} 08/31/2021 12:55:48 - INFO - __main__ - Step 130857: {'lr': 2.0359494117833417e-05, 'samples': 25124544, 'steps': 130856, 'loss/train': 0.031562689691782} 08/31/2021 12:55:50 - INFO - __main__ - Step 130858: {'lr': 2.035739653624094e-05, 'samples': 25124736, 'steps': 130857, 'loss/train': 1.516649603843689} 08/31/2021 12:55:51 - INFO - __main__ - Step 130859: {'lr': 2.035529905812186e-05, 'samples': 25124928, 'steps': 130858, 'loss/train': 0.59999680519104} 08/31/2021 12:55:51 - INFO - __main__ - Step 130860: {'lr': 2.0353201683477153e-05, 'samples': 25125120, 'steps': 130859, 'loss/train': 0.03782159835100174} 08/31/2021 12:55:51 - INFO - __main__ - Step 130861: {'lr': 2.0351104412307754e-05, 'samples': 25125312, 'steps': 130860, 'loss/train': 1.3974409103393555} 08/31/2021 12:55:52 - INFO - __main__ - Step 130862: {'lr': 2.034900724461458e-05, 'samples': 25125504, 'steps': 130861, 'loss/train': 0.03106727823615074} 08/31/2021 12:55:53 - INFO - __main__ - Step 130863: {'lr': 2.0346910180398665e-05, 'samples': 25125696, 'steps': 130862, 'loss/train': 0.5819363594055176} 08/31/2021 12:55:54 - INFO - __main__ - Step 130864: {'lr': 2.0344813219660835e-05, 'samples': 25125888, 'steps': 130863, 'loss/train': 0.04159141331911087} 08/31/2021 12:55:54 - INFO - __main__ - Step 130865: {'lr': 2.0342716362402092e-05, 'samples': 25126080, 'steps': 130864, 'loss/train': 0.8984884023666382} 08/31/2021 12:55:54 - INFO - __main__ - Step 130866: {'lr': 2.034061960862338e-05, 'samples': 25126272, 'steps': 130865, 'loss/train': 0.683559775352478} 08/31/2021 12:55:55 - INFO - __main__ - Step 130867: {'lr': 2.0338522958325638e-05, 'samples': 25126464, 'steps': 130866, 'loss/train': 1.426298975944519} 08/31/2021 12:55:55 - INFO - __main__ - Step 130868: {'lr': 2.0336426411509817e-05, 'samples': 25126656, 'steps': 130867, 'loss/train': 0.48112204670906067} 08/31/2021 12:55:57 - INFO - __main__ - Step 130869: {'lr': 2.0334329968176855e-05, 'samples': 25126848, 'steps': 130868, 'loss/train': 1.5078104734420776} 08/31/2021 12:55:57 - INFO - __main__ - Step 130870: {'lr': 2.03322336283277e-05, 'samples': 25127040, 'steps': 130869, 'loss/train': 0.8479809761047363} 08/31/2021 12:55:58 - INFO - __main__ - Step 130871: {'lr': 2.0330137391963295e-05, 'samples': 25127232, 'steps': 130870, 'loss/train': 1.3326197862625122} 08/31/2021 12:55:58 - INFO - __main__ - Step 130872: {'lr': 2.0328041259084578e-05, 'samples': 25127424, 'steps': 130871, 'loss/train': 1.5176177024841309} 08/31/2021 12:55:58 - INFO - __main__ - Step 130873: {'lr': 2.0325945229692527e-05, 'samples': 25127616, 'steps': 130872, 'loss/train': 0.8367297649383545} 08/31/2021 12:56:00 - INFO - __main__ - Step 130874: {'lr': 2.032384930378803e-05, 'samples': 25127808, 'steps': 130873, 'loss/train': 0.8142839074134827} 08/31/2021 12:56:00 - INFO - __main__ - Step 130875: {'lr': 2.032175348137208e-05, 'samples': 25128000, 'steps': 130874, 'loss/train': 1.1320385932922363} 08/31/2021 12:56:01 - INFO - __main__ - Step 130876: {'lr': 2.0319657762445652e-05, 'samples': 25128192, 'steps': 130875, 'loss/train': 1.2579960823059082} 08/31/2021 12:56:01 - INFO - __main__ - Step 130877: {'lr': 2.0317562147009584e-05, 'samples': 25128384, 'steps': 130876, 'loss/train': 0.9380027055740356} 08/31/2021 12:56:01 - INFO - __main__ - Step 130878: {'lr': 2.0315466635064893e-05, 'samples': 25128576, 'steps': 130877, 'loss/train': 0.17462068796157837} 08/31/2021 12:56:03 - INFO - __main__ - Step 130879: {'lr': 2.0313371226612503e-05, 'samples': 25128768, 'steps': 130878, 'loss/train': 1.2026853561401367} 08/31/2021 12:56:03 - INFO - __main__ - Step 130880: {'lr': 2.0311275921653356e-05, 'samples': 25128960, 'steps': 130879, 'loss/train': 0.9984855055809021} 08/31/2021 12:56:03 - INFO - __main__ - Step 130881: {'lr': 2.030918072018842e-05, 'samples': 25129152, 'steps': 130880, 'loss/train': 1.5729047060012817} 08/31/2021 12:56:04 - INFO - __main__ - Step 130882: {'lr': 2.0307085622218585e-05, 'samples': 25129344, 'steps': 130881, 'loss/train': 0.5664176940917969} 08/31/2021 12:56:04 - INFO - __main__ - Step 130883: {'lr': 2.0304990627744878e-05, 'samples': 25129536, 'steps': 130882, 'loss/train': 0.7484526634216309} 08/31/2021 12:56:06 - INFO - __main__ - Step 130884: {'lr': 2.030289573676816e-05, 'samples': 25129728, 'steps': 130883, 'loss/train': 0.40990665555000305} 08/31/2021 12:56:07 - INFO - __main__ - Step 130885: {'lr': 2.0300800949289462e-05, 'samples': 25129920, 'steps': 130884, 'loss/train': 1.3358532190322876} 08/31/2021 12:56:07 - INFO - __main__ - Step 130886: {'lr': 2.0298706265309634e-05, 'samples': 25130112, 'steps': 130885, 'loss/train': 1.6425628662109375} 08/31/2021 12:56:07 - INFO - __main__ - Step 130887: {'lr': 2.0296611684829687e-05, 'samples': 25130304, 'steps': 130886, 'loss/train': 0.2325555980205536} 08/31/2021 12:56:08 - INFO - __main__ - Step 130888: {'lr': 2.029451720785053e-05, 'samples': 25130496, 'steps': 130887, 'loss/train': 0.14954626560211182} 08/31/2021 12:56:10 - INFO - __main__ - Step 130889: {'lr': 2.029242283437313e-05, 'samples': 25130688, 'steps': 130888, 'loss/train': 1.3471342325210571} 08/31/2021 12:56:10 - INFO - __main__ - Step 130890: {'lr': 2.029032856439844e-05, 'samples': 25130880, 'steps': 130889, 'loss/train': 0.9714161157608032} 08/31/2021 12:56:10 - INFO - __main__ - Step 130891: {'lr': 2.0288234397927374e-05, 'samples': 25131072, 'steps': 130890, 'loss/train': 1.065360188484192} 08/31/2021 12:56:11 - INFO - __main__ - Step 130892: {'lr': 2.0286140334960844e-05, 'samples': 25131264, 'steps': 130891, 'loss/train': 1.2124934196472168} 08/31/2021 12:56:11 - INFO - __main__ - Step 130893: {'lr': 2.028404637549988e-05, 'samples': 25131456, 'steps': 130892, 'loss/train': 0.38914650678634644} 08/31/2021 12:56:11 - INFO - __main__ - Step 130894: {'lr': 2.0281952519545343e-05, 'samples': 25131648, 'steps': 130893, 'loss/train': 0.42502453923225403} 08/31/2021 12:56:13 - INFO - __main__ - Step 130895: {'lr': 2.0279858767098232e-05, 'samples': 25131840, 'steps': 130894, 'loss/train': 1.3113603591918945} 08/31/2021 12:56:13 - INFO - __main__ - Step 130896: {'lr': 2.0277765118159485e-05, 'samples': 25132032, 'steps': 130895, 'loss/train': 1.3605012893676758} 08/31/2021 12:56:14 - INFO - __main__ - Step 130897: {'lr': 2.0275671572729998e-05, 'samples': 25132224, 'steps': 130896, 'loss/train': 1.2511767148971558} 08/31/2021 12:56:14 - INFO - __main__ - Step 130898: {'lr': 2.0273578130810766e-05, 'samples': 25132416, 'steps': 130897, 'loss/train': 1.2585153579711914} 08/31/2021 12:56:14 - INFO - __main__ - Step 130899: {'lr': 2.0271484792402734e-05, 'samples': 25132608, 'steps': 130898, 'loss/train': 1.3543959856033325} 08/31/2021 12:56:16 - INFO - __main__ - Step 130900: {'lr': 2.0269391557506787e-05, 'samples': 25132800, 'steps': 130899, 'loss/train': 0.937189519405365} 08/31/2021 12:56:16 - INFO - __main__ - Step 130901: {'lr': 2.0267298426123932e-05, 'samples': 25132992, 'steps': 130900, 'loss/train': 1.4234745502471924} 08/31/2021 12:56:17 - INFO - __main__ - Step 130902: {'lr': 2.0265205398255075e-05, 'samples': 25133184, 'steps': 130901, 'loss/train': 0.7739402651786804} 08/31/2021 12:56:17 - INFO - __main__ - Step 130903: {'lr': 2.0263112473901224e-05, 'samples': 25133376, 'steps': 130902, 'loss/train': 0.9090767502784729} 08/31/2021 12:56:17 - INFO - __main__ - Step 130904: {'lr': 2.0261019653063232e-05, 'samples': 25133568, 'steps': 130903, 'loss/train': 1.2482874393463135} 08/31/2021 12:56:19 - INFO - __main__ - Step 130905: {'lr': 2.025892693574208e-05, 'samples': 25133760, 'steps': 130904, 'loss/train': 1.3409892320632935} 08/31/2021 12:56:20 - INFO - __main__ - Step 130906: {'lr': 2.02568343219387e-05, 'samples': 25133952, 'steps': 130905, 'loss/train': 1.2088367938995361} 08/31/2021 12:56:20 - INFO - __main__ - Step 130907: {'lr': 2.025474181165404e-05, 'samples': 25134144, 'steps': 130906, 'loss/train': 1.2457774877548218} 08/31/2021 12:56:20 - INFO - __main__ - Step 130908: {'lr': 2.025264940488905e-05, 'samples': 25134336, 'steps': 130907, 'loss/train': 0.2613670825958252} 08/31/2021 12:56:21 - INFO - __main__ - Step 130909: {'lr': 2.0250557101644697e-05, 'samples': 25134528, 'steps': 130908, 'loss/train': 1.1589076519012451} 08/31/2021 12:56:23 - INFO - __main__ - Step 130910: {'lr': 2.0248464901921864e-05, 'samples': 25134720, 'steps': 130909, 'loss/train': 1.0248792171478271} 08/31/2021 12:56:23 - INFO - __main__ - Step 130911: {'lr': 2.024637280572153e-05, 'samples': 25134912, 'steps': 130910, 'loss/train': 1.3226748704910278} 08/31/2021 12:56:24 - INFO - __main__ - Step 130912: {'lr': 2.0244280813044663e-05, 'samples': 25135104, 'steps': 130911, 'loss/train': 0.9566175937652588} 08/31/2021 12:56:24 - INFO - __main__ - Step 130913: {'lr': 2.0242188923892152e-05, 'samples': 25135296, 'steps': 130912, 'loss/train': 0.4216385781764984} 08/31/2021 12:56:24 - INFO - __main__ - Step 130914: {'lr': 2.0240097138264967e-05, 'samples': 25135488, 'steps': 130913, 'loss/train': 1.1306889057159424} 08/31/2021 12:56:26 - INFO - __main__ - Step 130915: {'lr': 2.0238005456164056e-05, 'samples': 25135680, 'steps': 130914, 'loss/train': 1.48357355594635} 08/31/2021 12:56:26 - INFO - __main__ - Step 130916: {'lr': 2.0235913877590355e-05, 'samples': 25135872, 'steps': 130915, 'loss/train': 1.1713908910751343} 08/31/2021 12:56:27 - INFO - __main__ - Step 130917: {'lr': 2.0233822402544842e-05, 'samples': 25136064, 'steps': 130916, 'loss/train': 1.1277517080307007} 08/31/2021 12:56:27 - INFO - __main__ - Step 130918: {'lr': 2.0231731031028405e-05, 'samples': 25136256, 'steps': 130917, 'loss/train': 0.47450774908065796} 08/31/2021 12:56:27 - INFO - __main__ - Step 130919: {'lr': 2.0229639763041984e-05, 'samples': 25136448, 'steps': 130918, 'loss/train': 1.0159728527069092} 08/31/2021 12:56:28 - INFO - __main__ - Step 130920: {'lr': 2.0227548598586553e-05, 'samples': 25136640, 'steps': 130919, 'loss/train': 1.561635136604309} 08/31/2021 12:56:29 - INFO - __main__ - Step 130921: {'lr': 2.0225457537663027e-05, 'samples': 25136832, 'steps': 130920, 'loss/train': 0.7688378691673279} 08/31/2021 12:56:30 - INFO - __main__ - Step 130922: {'lr': 2.0223366580272352e-05, 'samples': 25137024, 'steps': 130921, 'loss/train': 0.11571763455867767} 08/31/2021 12:56:30 - INFO - __main__ - Step 130923: {'lr': 2.0221275726415524e-05, 'samples': 25137216, 'steps': 130922, 'loss/train': 1.1631280183792114} 08/31/2021 12:56:31 - INFO - __main__ - Step 130924: {'lr': 2.0219184976093403e-05, 'samples': 25137408, 'steps': 130923, 'loss/train': 1.7238225936889648} 08/31/2021 12:56:31 - INFO - __main__ - Step 130925: {'lr': 2.021709432930699e-05, 'samples': 25137600, 'steps': 130924, 'loss/train': 0.021272825077176094} 08/31/2021 12:56:33 - INFO - __main__ - Step 130926: {'lr': 2.02150037860572e-05, 'samples': 25137792, 'steps': 130925, 'loss/train': 0.8928818702697754} 08/31/2021 12:56:34 - INFO - __main__ - Step 130927: {'lr': 2.021291334634501e-05, 'samples': 25137984, 'steps': 130926, 'loss/train': 1.1765333414077759} 08/31/2021 12:56:34 - INFO - __main__ - Step 130928: {'lr': 2.0210823010171296e-05, 'samples': 25138176, 'steps': 130927, 'loss/train': 1.1212332248687744} 08/31/2021 12:56:34 - INFO - __main__ - Step 130929: {'lr': 2.020873277753707e-05, 'samples': 25138368, 'steps': 130928, 'loss/train': 1.3459093570709229} 08/31/2021 12:56:35 - INFO - __main__ - Step 130930: {'lr': 2.020664264844327e-05, 'samples': 25138560, 'steps': 130929, 'loss/train': 2.1971051692962646} 08/31/2021 12:56:35 - INFO - __main__ - Step 130931: {'lr': 2.0204552622890782e-05, 'samples': 25138752, 'steps': 130930, 'loss/train': 0.015526069328188896} 08/31/2021 12:56:35 - INFO - __main__ - Step 130932: {'lr': 2.020246270088058e-05, 'samples': 25138944, 'steps': 130931, 'loss/train': 0.0644112154841423} 08/31/2021 12:56:37 - INFO - __main__ - Step 130933: {'lr': 2.0200372882413582e-05, 'samples': 25139136, 'steps': 130932, 'loss/train': 0.5244756937026978} 08/31/2021 12:56:38 - INFO - __main__ - Step 130934: {'lr': 2.0198283167490756e-05, 'samples': 25139328, 'steps': 130933, 'loss/train': 1.3538060188293457} 08/31/2021 12:56:38 - INFO - __main__ - Step 130935: {'lr': 2.0196193556113046e-05, 'samples': 25139520, 'steps': 130934, 'loss/train': 1.210605263710022} 08/31/2021 12:56:38 - INFO - __main__ - Step 130936: {'lr': 2.019410404828137e-05, 'samples': 25139712, 'steps': 130935, 'loss/train': 1.1271737813949585} 08/31/2021 12:56:39 - INFO - __main__ - Step 130937: {'lr': 2.0192014643996698e-05, 'samples': 25139904, 'steps': 130936, 'loss/train': 0.9597265720367432} 08/31/2021 12:56:40 - INFO - __main__ - Step 130938: {'lr': 2.0189925343259946e-05, 'samples': 25140096, 'steps': 130937, 'loss/train': 0.6483666896820068} 08/31/2021 12:56:41 - INFO - __main__ - Step 130939: {'lr': 2.0187836146072087e-05, 'samples': 25140288, 'steps': 130938, 'loss/train': 1.2737561464309692} 08/31/2021 12:56:41 - INFO - __main__ - Step 130940: {'lr': 2.0185747052434034e-05, 'samples': 25140480, 'steps': 130939, 'loss/train': 1.186821699142456} 08/31/2021 12:56:41 - INFO - __main__ - Step 130941: {'lr': 2.0183658062346734e-05, 'samples': 25140672, 'steps': 130940, 'loss/train': 1.4985469579696655} 08/31/2021 12:56:42 - INFO - __main__ - Step 130942: {'lr': 2.0181569175811126e-05, 'samples': 25140864, 'steps': 130941, 'loss/train': 1.1084880828857422} 08/31/2021 12:56:42 - INFO - __main__ - Step 130943: {'lr': 2.017948039282816e-05, 'samples': 25141056, 'steps': 130942, 'loss/train': 0.565825879573822} 08/31/2021 12:56:44 - INFO - __main__ - Step 130944: {'lr': 2.0177391713398802e-05, 'samples': 25141248, 'steps': 130943, 'loss/train': 0.5205629467964172} 08/31/2021 12:56:44 - INFO - __main__ - Step 130945: {'lr': 2.0175303137523942e-05, 'samples': 25141440, 'steps': 130944, 'loss/train': 1.4209561347961426} 08/31/2021 12:56:45 - INFO - __main__ - Step 130946: {'lr': 2.0173214665204552e-05, 'samples': 25141632, 'steps': 130945, 'loss/train': 1.148586392402649} 08/31/2021 12:56:45 - INFO - __main__ - Step 130947: {'lr': 2.017112629644155e-05, 'samples': 25141824, 'steps': 130946, 'loss/train': 0.9176810383796692} 08/31/2021 12:56:45 - INFO - __main__ - Step 130948: {'lr': 2.0169038031235902e-05, 'samples': 25142016, 'steps': 130947, 'loss/train': 1.7057256698608398} 08/31/2021 12:56:47 - INFO - __main__ - Step 130949: {'lr': 2.016694986958853e-05, 'samples': 25142208, 'steps': 130948, 'loss/train': 0.7322721481323242} 08/31/2021 12:56:47 - INFO - __main__ - Step 130950: {'lr': 2.0164861811500373e-05, 'samples': 25142400, 'steps': 130949, 'loss/train': 1.644776701927185} 08/31/2021 12:56:48 - INFO - __main__ - Step 130951: {'lr': 2.0162773856972403e-05, 'samples': 25142592, 'steps': 130950, 'loss/train': 0.7415956258773804} 08/31/2021 12:56:48 - INFO - __main__ - Step 130952: {'lr': 2.016068600600554e-05, 'samples': 25142784, 'steps': 130951, 'loss/train': 1.2726109027862549} 08/31/2021 12:56:48 - INFO - __main__ - Step 130953: {'lr': 2.0158598258600726e-05, 'samples': 25142976, 'steps': 130952, 'loss/train': 1.5726292133331299} 08/31/2021 12:56:51 - INFO - __main__ - Step 130954: {'lr': 2.015651061475887e-05, 'samples': 25143168, 'steps': 130953, 'loss/train': 0.9520285725593567} 08/31/2021 12:56:51 - INFO - __main__ - Step 130955: {'lr': 2.0154423074480984e-05, 'samples': 25143360, 'steps': 130954, 'loss/train': 0.886926531791687} 08/31/2021 12:56:51 - INFO - __main__ - Step 130956: {'lr': 2.0152335637767944e-05, 'samples': 25143552, 'steps': 130955, 'loss/train': 0.4040420651435852} 08/31/2021 12:56:52 - INFO - __main__ - Step 130957: {'lr': 2.0150248304620783e-05, 'samples': 25143744, 'steps': 130956, 'loss/train': 0.387114554643631} 08/31/2021 12:56:52 - INFO - __main__ - Step 130958: {'lr': 2.0148161075040307e-05, 'samples': 25143936, 'steps': 130957, 'loss/train': 1.2104177474975586} 08/31/2021 12:56:52 - INFO - __main__ - Step 130959: {'lr': 2.0146073949027538e-05, 'samples': 25144128, 'steps': 130958, 'loss/train': 0.45083510875701904} 08/31/2021 12:56:54 - INFO - __main__ - Step 130960: {'lr': 2.014398692658337e-05, 'samples': 25144320, 'steps': 130959, 'loss/train': 0.8526514172554016} 08/31/2021 12:56:54 - INFO - __main__ - Step 130961: {'lr': 2.0141900007708797e-05, 'samples': 25144512, 'steps': 130960, 'loss/train': 0.907301664352417} 08/31/2021 12:56:55 - INFO - __main__ - Step 130962: {'lr': 2.013981319240474e-05, 'samples': 25144704, 'steps': 130961, 'loss/train': 0.6486315131187439} 08/31/2021 12:56:55 - INFO - __main__ - Step 130963: {'lr': 2.0137726480672136e-05, 'samples': 25144896, 'steps': 130962, 'loss/train': 1.0564615726470947} 08/31/2021 12:56:55 - INFO - __main__ - Step 130964: {'lr': 2.0135639872511936e-05, 'samples': 25145088, 'steps': 130963, 'loss/train': 1.3424789905548096} 08/31/2021 12:56:57 - INFO - __main__ - Step 130965: {'lr': 2.0133553367925052e-05, 'samples': 25145280, 'steps': 130964, 'loss/train': 0.09444470703601837} 08/31/2021 12:56:58 - INFO - __main__ - Step 130966: {'lr': 2.0131466966912425e-05, 'samples': 25145472, 'steps': 130965, 'loss/train': 1.4478029012680054} 08/31/2021 12:56:58 - INFO - __main__ - Step 130967: {'lr': 2.0129380669475034e-05, 'samples': 25145664, 'steps': 130966, 'loss/train': 0.8592185378074646} 08/31/2021 12:56:58 - INFO - __main__ - Step 130968: {'lr': 2.0127294475613818e-05, 'samples': 25145856, 'steps': 130967, 'loss/train': 0.4401715397834778} 08/31/2021 12:56:59 - INFO - __main__ - Step 130969: {'lr': 2.0125208385329664e-05, 'samples': 25146048, 'steps': 130968, 'loss/train': 0.9174424409866333} 08/31/2021 12:56:59 - INFO - __main__ - Step 130970: {'lr': 2.01231223986236e-05, 'samples': 25146240, 'steps': 130969, 'loss/train': 1.2535550594329834} 08/31/2021 12:57:01 - INFO - __main__ - Step 130971: {'lr': 2.012103651549646e-05, 'samples': 25146432, 'steps': 130970, 'loss/train': 1.2120758295059204} 08/31/2021 12:57:01 - INFO - __main__ - Step 130972: {'lr': 2.0118950735949243e-05, 'samples': 25146624, 'steps': 130971, 'loss/train': 1.296610951423645} 08/31/2021 12:57:01 - INFO - __main__ - Step 130973: {'lr': 2.0116865059982863e-05, 'samples': 25146816, 'steps': 130972, 'loss/train': 1.4056187868118286} 08/31/2021 12:57:02 - INFO - __main__ - Step 130974: {'lr': 2.0114779487598296e-05, 'samples': 25147008, 'steps': 130973, 'loss/train': 1.3383209705352783} 08/31/2021 12:57:02 - INFO - __main__ - Step 130975: {'lr': 2.0112694018796452e-05, 'samples': 25147200, 'steps': 130974, 'loss/train': 1.3184298276901245} 08/31/2021 12:57:04 - INFO - __main__ - Step 130976: {'lr': 2.0110608653578278e-05, 'samples': 25147392, 'steps': 130975, 'loss/train': 0.02847759798169136} 08/31/2021 12:57:04 - INFO - __main__ - Step 130977: {'lr': 2.0108523391944715e-05, 'samples': 25147584, 'steps': 130976, 'loss/train': 1.4332674741744995} 08/31/2021 12:57:05 - INFO - __main__ - Step 130978: {'lr': 2.0106438233896712e-05, 'samples': 25147776, 'steps': 130977, 'loss/train': 0.8120675683021545} 08/31/2021 12:57:05 - INFO - __main__ - Step 130979: {'lr': 2.010435317943518e-05, 'samples': 25147968, 'steps': 130978, 'loss/train': 1.2041624784469604} 08/31/2021 12:57:05 - INFO - __main__ - Step 130980: {'lr': 2.0102268228561122e-05, 'samples': 25148160, 'steps': 130979, 'loss/train': 0.9360025525093079} 08/31/2021 12:57:07 - INFO - __main__ - Step 130981: {'lr': 2.0100183381275396e-05, 'samples': 25148352, 'steps': 130980, 'loss/train': 0.9918233156204224} 08/31/2021 12:57:07 - INFO - __main__ - Step 130982: {'lr': 2.0098098637579e-05, 'samples': 25148544, 'steps': 130981, 'loss/train': 1.2224949598312378} 08/31/2021 12:57:08 - INFO - __main__ - Step 130983: {'lr': 2.0096013997472823e-05, 'samples': 25148736, 'steps': 130982, 'loss/train': 0.9623422622680664} 08/31/2021 12:57:08 - INFO - __main__ - Step 130984: {'lr': 2.0093929460957922e-05, 'samples': 25148928, 'steps': 130983, 'loss/train': 1.2975637912750244} 08/31/2021 12:57:08 - INFO - __main__ - Step 130985: {'lr': 2.0091845028035072e-05, 'samples': 25149120, 'steps': 130984, 'loss/train': 1.1206432580947876} 08/31/2021 12:57:10 - INFO - __main__ - Step 130986: {'lr': 2.00897606987053e-05, 'samples': 25149312, 'steps': 130985, 'loss/train': 1.138375997543335} 08/31/2021 12:57:10 - INFO - __main__ - Step 130987: {'lr': 2.0087676472969552e-05, 'samples': 25149504, 'steps': 130986, 'loss/train': 1.4007686376571655} 08/31/2021 12:57:11 - INFO - __main__ - Step 130988: {'lr': 2.008559235082871e-05, 'samples': 25149696, 'steps': 130987, 'loss/train': 1.6872538328170776} 08/31/2021 12:57:11 - INFO - __main__ - Step 130989: {'lr': 2.0083508332283785e-05, 'samples': 25149888, 'steps': 130988, 'loss/train': 0.7605876326560974} 08/31/2021 12:57:11 - INFO - __main__ - Step 130990: {'lr': 2.008142441733568e-05, 'samples': 25150080, 'steps': 130989, 'loss/train': 0.7712982296943665} 08/31/2021 12:57:13 - INFO - __main__ - Step 130991: {'lr': 2.007934060598532e-05, 'samples': 25150272, 'steps': 130990, 'loss/train': 1.0170750617980957} 08/31/2021 12:57:13 - INFO - __main__ - Step 130992: {'lr': 2.007725689823367e-05, 'samples': 25150464, 'steps': 130991, 'loss/train': 1.1341978311538696} 08/31/2021 12:57:14 - INFO - __main__ - Step 130993: {'lr': 2.007517329408165e-05, 'samples': 25150656, 'steps': 130992, 'loss/train': 1.4300496578216553} 08/31/2021 12:57:14 - INFO - __main__ - Step 130994: {'lr': 2.007308979353023e-05, 'samples': 25150848, 'steps': 130993, 'loss/train': 1.605709433555603} 08/31/2021 12:57:14 - INFO - __main__ - Step 130995: {'lr': 2.0071006396580326e-05, 'samples': 25151040, 'steps': 130994, 'loss/train': 1.2581133842468262} 08/31/2021 12:57:15 - INFO - __main__ - Step 130996: {'lr': 2.0068923103232855e-05, 'samples': 25151232, 'steps': 130995, 'loss/train': 1.065282940864563} 08/31/2021 12:57:16 - INFO - __main__ - Step 130997: {'lr': 2.0066839913488844e-05, 'samples': 25151424, 'steps': 130996, 'loss/train': 1.2436084747314453} 08/31/2021 12:57:17 - INFO - __main__ - Step 130998: {'lr': 2.0064756827349122e-05, 'samples': 25151616, 'steps': 130997, 'loss/train': 1.935076117515564} 08/31/2021 12:57:17 - INFO - __main__ - Step 130999: {'lr': 2.0062673844814666e-05, 'samples': 25151808, 'steps': 130998, 'loss/train': 1.2306827306747437} 08/31/2021 12:57:18 - INFO - __main__ - Step 131000: {'lr': 2.0060590965886417e-05, 'samples': 25152000, 'steps': 130999, 'loss/train': 1.2315900325775146} 08/31/2021 12:57:18 - INFO - __main__ - Step 131001: {'lr': 2.0058508190565316e-05, 'samples': 25152192, 'steps': 131000, 'loss/train': 1.7808823585510254} 08/31/2021 12:57:19 - INFO - __main__ - Step 131002: {'lr': 2.005642551885231e-05, 'samples': 25152384, 'steps': 131001, 'loss/train': 1.1540148258209229} 08/31/2021 12:57:20 - INFO - __main__ - Step 131003: {'lr': 2.0054342950748344e-05, 'samples': 25152576, 'steps': 131002, 'loss/train': 1.050506830215454} 08/31/2021 12:57:20 - INFO - __main__ - Step 131004: {'lr': 2.0052260486254332e-05, 'samples': 25152768, 'steps': 131003, 'loss/train': 1.2738711833953857} 08/31/2021 12:57:21 - INFO - __main__ - Step 131005: {'lr': 2.0050178125371216e-05, 'samples': 25152960, 'steps': 131004, 'loss/train': 1.1527197360992432} 08/31/2021 12:57:21 - INFO - __main__ - Step 131006: {'lr': 2.0048095868099942e-05, 'samples': 25153152, 'steps': 131005, 'loss/train': 0.5937321186065674} 08/31/2021 12:57:22 - INFO - __main__ - Step 131007: {'lr': 2.0046013714441452e-05, 'samples': 25153344, 'steps': 131006, 'loss/train': 1.1596819162368774} 08/31/2021 12:57:23 - INFO - __main__ - Step 131008: {'lr': 2.004393166439669e-05, 'samples': 25153536, 'steps': 131007, 'loss/train': 1.752025842666626} 08/31/2021 12:57:23 - INFO - __main__ - Step 131009: {'lr': 2.0041849717966575e-05, 'samples': 25153728, 'steps': 131008, 'loss/train': 1.0399892330169678} 08/31/2021 12:57:24 - INFO - __main__ - Step 131010: {'lr': 2.003976787515205e-05, 'samples': 25153920, 'steps': 131009, 'loss/train': 0.8703221082687378} 08/31/2021 12:57:24 - INFO - __main__ - Step 131011: {'lr': 2.003768613595411e-05, 'samples': 25154112, 'steps': 131010, 'loss/train': 1.323843002319336} 08/31/2021 12:57:25 - INFO - __main__ - Step 131012: {'lr': 2.003560450037359e-05, 'samples': 25154304, 'steps': 131011, 'loss/train': 1.409071922302246} 08/31/2021 12:57:26 - INFO - __main__ - Step 131013: {'lr': 2.003352296841146e-05, 'samples': 25154496, 'steps': 131012, 'loss/train': 0.6470920443534851} 08/31/2021 12:57:26 - INFO - __main__ - Step 131014: {'lr': 2.0031441540068697e-05, 'samples': 25154688, 'steps': 131013, 'loss/train': 1.6582087278366089} 08/31/2021 12:57:27 - INFO - __main__ - Step 131015: {'lr': 2.002936021534621e-05, 'samples': 25154880, 'steps': 131014, 'loss/train': 0.8363853693008423} 08/31/2021 12:57:27 - INFO - __main__ - Step 131016: {'lr': 2.0027278994244946e-05, 'samples': 25155072, 'steps': 131015, 'loss/train': 1.4516921043395996} 08/31/2021 12:57:29 - INFO - __main__ - Step 131017: {'lr': 2.0025197876765848e-05, 'samples': 25155264, 'steps': 131016, 'loss/train': 0.10746018588542938} 08/31/2021 12:57:29 - INFO - __main__ - Step 131018: {'lr': 2.0023116862909836e-05, 'samples': 25155456, 'steps': 131017, 'loss/train': 0.5421817302703857} 08/31/2021 12:57:30 - INFO - __main__ - Step 131019: {'lr': 2.0021035952677874e-05, 'samples': 25155648, 'steps': 131018, 'loss/train': 0.6946099996566772} 08/31/2021 12:57:30 - INFO - __main__ - Step 131020: {'lr': 2.0018955146070882e-05, 'samples': 25155840, 'steps': 131019, 'loss/train': 1.0230215787887573} 08/31/2021 12:57:30 - INFO - __main__ - Step 131021: {'lr': 2.0016874443089806e-05, 'samples': 25156032, 'steps': 131020, 'loss/train': 0.5719457268714905} 08/31/2021 12:57:32 - INFO - __main__ - Step 131022: {'lr': 2.0014793843735557e-05, 'samples': 25156224, 'steps': 131021, 'loss/train': 1.0559381246566772} 08/31/2021 12:57:33 - INFO - __main__ - Step 131023: {'lr': 2.001271334800911e-05, 'samples': 25156416, 'steps': 131022, 'loss/train': 0.9297559857368469} 08/31/2021 12:57:33 - INFO - __main__ - Step 131024: {'lr': 2.0010632955911408e-05, 'samples': 25156608, 'steps': 131023, 'loss/train': 1.2912871837615967} 08/31/2021 12:57:34 - INFO - __main__ - Step 131025: {'lr': 2.0008552667443337e-05, 'samples': 25156800, 'steps': 131024, 'loss/train': 1.9357982873916626} 08/31/2021 12:57:34 - INFO - __main__ - Step 131026: {'lr': 2.000647248260587e-05, 'samples': 25156992, 'steps': 131025, 'loss/train': 1.741366982460022} 08/31/2021 12:57:34 - INFO - __main__ - Step 131027: {'lr': 2.0004392401399924e-05, 'samples': 25157184, 'steps': 131026, 'loss/train': 1.16107976436615} 08/31/2021 12:57:36 - INFO - __main__ - Step 131028: {'lr': 2.000231242382644e-05, 'samples': 25157376, 'steps': 131027, 'loss/train': 1.4541481733322144} 08/31/2021 12:57:36 - INFO - __main__ - Step 131029: {'lr': 2.0000232549886393e-05, 'samples': 25157568, 'steps': 131028, 'loss/train': 1.473079800605774} 08/31/2021 12:57:36 - INFO - __main__ - Step 131030: {'lr': 1.999815277958067e-05, 'samples': 25157760, 'steps': 131029, 'loss/train': 0.9653043746948242} 08/31/2021 12:57:37 - INFO - __main__ - Step 131031: {'lr': 1.999607311291024e-05, 'samples': 25157952, 'steps': 131030, 'loss/train': 0.8214676380157471} 08/31/2021 12:57:37 - INFO - __main__ - Step 131032: {'lr': 1.999399354987605e-05, 'samples': 25158144, 'steps': 131031, 'loss/train': 0.4261110723018646} 08/31/2021 12:57:39 - INFO - __main__ - Step 131033: {'lr': 1.9991914090478984e-05, 'samples': 25158336, 'steps': 131032, 'loss/train': 0.9644579887390137} 08/31/2021 12:57:39 - INFO - __main__ - Step 131034: {'lr': 1.998983473472002e-05, 'samples': 25158528, 'steps': 131033, 'loss/train': 1.075848937034607} 08/31/2021 12:57:40 - INFO - __main__ - Step 131035: {'lr': 1.9987755482600094e-05, 'samples': 25158720, 'steps': 131034, 'loss/train': 0.9917967319488525} 08/31/2021 12:57:40 - INFO - __main__ - Step 131036: {'lr': 1.998567633412013e-05, 'samples': 25158912, 'steps': 131035, 'loss/train': 0.982349693775177} 08/31/2021 12:57:40 - INFO - __main__ - Step 131037: {'lr': 1.9983597289281092e-05, 'samples': 25159104, 'steps': 131036, 'loss/train': 1.6312490701675415} 08/31/2021 12:57:42 - INFO - __main__ - Step 131038: {'lr': 1.998151834808393e-05, 'samples': 25159296, 'steps': 131037, 'loss/train': 0.024367032572627068} 08/31/2021 12:57:42 - INFO - __main__ - Step 131039: {'lr': 1.997943951052947e-05, 'samples': 25159488, 'steps': 131038, 'loss/train': 1.2820193767547607} 08/31/2021 12:57:43 - INFO - __main__ - Step 131040: {'lr': 1.997736077661877e-05, 'samples': 25159680, 'steps': 131039, 'loss/train': 0.15156647562980652} 08/31/2021 12:57:43 - INFO - __main__ - Step 131041: {'lr': 1.9975282146352693e-05, 'samples': 25159872, 'steps': 131040, 'loss/train': 0.44765883684158325} 08/31/2021 12:57:43 - INFO - __main__ - Step 131042: {'lr': 1.9973203619732207e-05, 'samples': 25160064, 'steps': 131041, 'loss/train': 1.3359376192092896} 08/31/2021 12:57:46 - INFO - __main__ - Step 131043: {'lr': 1.9971125196758257e-05, 'samples': 25160256, 'steps': 131042, 'loss/train': 1.264840841293335} 08/31/2021 12:57:46 - INFO - __main__ - Step 131044: {'lr': 1.9969046877431758e-05, 'samples': 25160448, 'steps': 131043, 'loss/train': 0.5138098001480103} 08/31/2021 12:57:47 - INFO - __main__ - Step 131045: {'lr': 1.996696866175368e-05, 'samples': 25160640, 'steps': 131044, 'loss/train': 0.2426205724477768} 08/31/2021 12:57:47 - INFO - __main__ - Step 131046: {'lr': 1.9964890549724917e-05, 'samples': 25160832, 'steps': 131045, 'loss/train': 1.323272943496704} 08/31/2021 12:57:48 - INFO - __main__ - Step 131047: {'lr': 1.9962812541346408e-05, 'samples': 25161024, 'steps': 131046, 'loss/train': 1.0126605033874512} 08/31/2021 12:57:48 - INFO - __main__ - Step 131048: {'lr': 1.9960734636619128e-05, 'samples': 25161216, 'steps': 131047, 'loss/train': 0.6944910883903503} 08/31/2021 12:57:48 - INFO - __main__ - Step 131049: {'lr': 1.9958656835543988e-05, 'samples': 25161408, 'steps': 131048, 'loss/train': 0.0755966305732727} 08/31/2021 12:57:50 - INFO - __main__ - Step 131050: {'lr': 1.9956579138121933e-05, 'samples': 25161600, 'steps': 131049, 'loss/train': 0.12111032009124756} 08/31/2021 12:57:51 - INFO - __main__ - Step 131051: {'lr': 1.9954501544353936e-05, 'samples': 25161792, 'steps': 131050, 'loss/train': 1.749932885169983} 08/31/2021 12:57:51 - INFO - __main__ - Step 131052: {'lr': 1.995242405424083e-05, 'samples': 25161984, 'steps': 131051, 'loss/train': 0.5649233460426331} 08/31/2021 12:57:51 - INFO - __main__ - Step 131053: {'lr': 1.9950346667783642e-05, 'samples': 25162176, 'steps': 131052, 'loss/train': 0.9528427720069885} 08/31/2021 12:57:52 - INFO - __main__ - Step 131054: {'lr': 1.994826938498326e-05, 'samples': 25162368, 'steps': 131053, 'loss/train': 1.2035537958145142} 08/31/2021 12:57:53 - INFO - __main__ - Step 131055: {'lr': 1.9946192205840624e-05, 'samples': 25162560, 'steps': 131054, 'loss/train': 1.4784271717071533} 08/31/2021 12:57:53 - INFO - __main__ - Step 131056: {'lr': 1.994411513035671e-05, 'samples': 25162752, 'steps': 131055, 'loss/train': 1.5584766864776611} 08/31/2021 12:57:54 - INFO - __main__ - Step 131057: {'lr': 1.9942038158532405e-05, 'samples': 25162944, 'steps': 131056, 'loss/train': 0.30655473470687866} 08/31/2021 12:57:54 - INFO - __main__ - Step 131058: {'lr': 1.993996129036868e-05, 'samples': 25163136, 'steps': 131057, 'loss/train': 1.28763747215271} 08/31/2021 12:57:55 - INFO - __main__ - Step 131059: {'lr': 1.993788452586645e-05, 'samples': 25163328, 'steps': 131058, 'loss/train': 0.9722513556480408} 08/31/2021 12:57:56 - INFO - __main__ - Step 131060: {'lr': 1.993580786502669e-05, 'samples': 25163520, 'steps': 131059, 'loss/train': 0.035696204751729965} 08/31/2021 12:57:57 - INFO - __main__ - Step 131061: {'lr': 1.9933731307850283e-05, 'samples': 25163712, 'steps': 131060, 'loss/train': 1.5800234079360962} 08/31/2021 12:57:57 - INFO - __main__ - Step 131062: {'lr': 1.9931654854338178e-05, 'samples': 25163904, 'steps': 131061, 'loss/train': 0.8000059723854065} 08/31/2021 12:57:57 - INFO - __main__ - Step 131063: {'lr': 1.9929578504491315e-05, 'samples': 25164096, 'steps': 131062, 'loss/train': 0.8055357336997986} 08/31/2021 12:57:58 - INFO - __main__ - Step 131064: {'lr': 1.9927502258310636e-05, 'samples': 25164288, 'steps': 131063, 'loss/train': 1.2061926126480103} 08/31/2021 12:57:58 - INFO - __main__ - Step 131065: {'lr': 1.9925426115797148e-05, 'samples': 25164480, 'steps': 131064, 'loss/train': 1.3850618600845337} 08/31/2021 12:58:00 - INFO - __main__ - Step 131066: {'lr': 1.9923350076951645e-05, 'samples': 25164672, 'steps': 131065, 'loss/train': 1.3618272542953491} 08/31/2021 12:58:00 - INFO - __main__ - Step 131067: {'lr': 1.9921274141775135e-05, 'samples': 25164864, 'steps': 131066, 'loss/train': 1.8139152526855469} 08/31/2021 12:58:01 - INFO - __main__ - Step 131068: {'lr': 1.9919198310268533e-05, 'samples': 25165056, 'steps': 131067, 'loss/train': 1.2414898872375488} 08/31/2021 12:58:01 - INFO - __main__ - Step 131069: {'lr': 1.9917122582432807e-05, 'samples': 25165248, 'steps': 131068, 'loss/train': 0.5592487454414368} 08/31/2021 12:58:01 - INFO - __main__ - Step 131070: {'lr': 1.9915046958268872e-05, 'samples': 25165440, 'steps': 131069, 'loss/train': 0.015159614384174347} 08/31/2021 12:58:03 - INFO - __main__ - Step 131071: {'lr': 1.9912971437777677e-05, 'samples': 25165632, 'steps': 131070, 'loss/train': 0.03729252889752388} 08/31/2021 12:58:03 - INFO - __main__ - Step 131072: {'lr': 1.9910896020960134e-05, 'samples': 25165824, 'steps': 131071, 'loss/train': 0.8610358834266663} 08/31/2021 12:58:04 - INFO - __main__ - Step 131073: {'lr': 1.9908820707817187e-05, 'samples': 25166016, 'steps': 131072, 'loss/train': 1.2008740901947021} 08/31/2021 12:58:04 - INFO - __main__ - Step 131074: {'lr': 1.990674549834978e-05, 'samples': 25166208, 'steps': 131073, 'loss/train': 0.20226719975471497} 08/31/2021 12:58:04 - INFO - __main__ - Step 131075: {'lr': 1.9904670392558833e-05, 'samples': 25166400, 'steps': 131074, 'loss/train': 1.1486353874206543} 08/31/2021 12:58:05 - INFO - __main__ - Step 131076: {'lr': 1.990259539044531e-05, 'samples': 25166592, 'steps': 131075, 'loss/train': 1.722658634185791} 08/31/2021 12:58:07 - INFO - __main__ - Step 131077: {'lr': 1.990052049201016e-05, 'samples': 25166784, 'steps': 131076, 'loss/train': 0.9132430553436279} 08/31/2021 12:58:07 - INFO - __main__ - Step 131078: {'lr': 1.989844569725424e-05, 'samples': 25166976, 'steps': 131077, 'loss/train': 1.2723197937011719} 08/31/2021 12:58:08 - INFO - __main__ - Step 131079: {'lr': 1.9896371006178525e-05, 'samples': 25167168, 'steps': 131078, 'loss/train': 0.9375641942024231} 08/31/2021 12:58:08 - INFO - __main__ - Step 131080: {'lr': 1.9894296418783958e-05, 'samples': 25167360, 'steps': 131079, 'loss/train': 0.03340418264269829} 08/31/2021 12:58:08 - INFO - __main__ - Step 131081: {'lr': 1.989222193507148e-05, 'samples': 25167552, 'steps': 131080, 'loss/train': 0.9029726982116699} 08/31/2021 12:58:10 - INFO - __main__ - Step 131082: {'lr': 1.989014755504201e-05, 'samples': 25167744, 'steps': 131081, 'loss/train': 0.8921838998794556} 08/31/2021 12:58:10 - INFO - __main__ - Step 131083: {'lr': 1.988807327869649e-05, 'samples': 25167936, 'steps': 131082, 'loss/train': 1.0857138633728027} 08/31/2021 12:58:11 - INFO - __main__ - Step 131084: {'lr': 1.9885999106035863e-05, 'samples': 25168128, 'steps': 131083, 'loss/train': 1.241766095161438} 08/31/2021 12:58:11 - INFO - __main__ - Step 131085: {'lr': 1.9883925037061045e-05, 'samples': 25168320, 'steps': 131084, 'loss/train': 0.7733120322227478} 08/31/2021 12:58:11 - INFO - __main__ - Step 131086: {'lr': 1.9881851071772984e-05, 'samples': 25168512, 'steps': 131085, 'loss/train': 1.2824220657348633} 08/31/2021 12:58:13 - INFO - __main__ - Step 131087: {'lr': 1.9879777210172645e-05, 'samples': 25168704, 'steps': 131086, 'loss/train': 1.2979680299758911} 08/31/2021 12:58:13 - INFO - __main__ - Step 131088: {'lr': 1.9877703452260865e-05, 'samples': 25168896, 'steps': 131087, 'loss/train': 1.1468069553375244} 08/31/2021 12:58:14 - INFO - __main__ - Step 131089: {'lr': 1.987562979803867e-05, 'samples': 25169088, 'steps': 131088, 'loss/train': 0.40278199315071106} 08/31/2021 12:58:14 - INFO - __main__ - Step 131090: {'lr': 1.9873556247506946e-05, 'samples': 25169280, 'steps': 131089, 'loss/train': 0.8459850549697876} 08/31/2021 12:58:14 - INFO - __main__ - Step 131091: {'lr': 1.9871482800666667e-05, 'samples': 25169472, 'steps': 131090, 'loss/train': 0.7519699335098267} 08/31/2021 12:58:16 - INFO - __main__ - Step 131092: {'lr': 1.986940945751875e-05, 'samples': 25169664, 'steps': 131091, 'loss/train': 1.8404275178909302} 08/31/2021 12:58:17 - INFO - __main__ - Step 131093: {'lr': 1.986733621806411e-05, 'samples': 25169856, 'steps': 131092, 'loss/train': 1.4743320941925049} 08/31/2021 12:58:17 - INFO - __main__ - Step 131094: {'lr': 1.9865263082303687e-05, 'samples': 25170048, 'steps': 131093, 'loss/train': 1.1285557746887207} 08/31/2021 12:58:17 - INFO - __main__ - Step 131095: {'lr': 1.9863190050238455e-05, 'samples': 25170240, 'steps': 131094, 'loss/train': 1.0932064056396484} 08/31/2021 12:58:18 - INFO - __main__ - Step 131096: {'lr': 1.9861117121869276e-05, 'samples': 25170432, 'steps': 131095, 'loss/train': 1.0770721435546875} 08/31/2021 12:58:18 - INFO - __main__ - Step 131097: {'lr': 1.9859044297197177e-05, 'samples': 25170624, 'steps': 131096, 'loss/train': 1.426342248916626} 08/31/2021 12:58:19 - INFO - __main__ - Step 131098: {'lr': 1.9856971576223043e-05, 'samples': 25170816, 'steps': 131097, 'loss/train': 2.6846885681152344} 08/31/2021 12:58:20 - INFO - __main__ - Step 131099: {'lr': 1.9854898958947792e-05, 'samples': 25171008, 'steps': 131098, 'loss/train': 1.1172157526016235} 08/31/2021 12:58:20 - INFO - __main__ - Step 131100: {'lr': 1.985282644537234e-05, 'samples': 25171200, 'steps': 131099, 'loss/train': 0.5195804238319397} 08/31/2021 12:58:21 - INFO - __main__ - Step 131101: {'lr': 1.9850754035497688e-05, 'samples': 25171392, 'steps': 131100, 'loss/train': 1.1470144987106323} 08/31/2021 12:58:21 - INFO - __main__ - Step 131102: {'lr': 1.984868172932472e-05, 'samples': 25171584, 'steps': 131101, 'loss/train': 0.9390278458595276} 08/31/2021 12:58:23 - INFO - __main__ - Step 131103: {'lr': 1.984660952685438e-05, 'samples': 25171776, 'steps': 131102, 'loss/train': 0.30480918288230896} 08/31/2021 12:58:24 - INFO - __main__ - Step 131104: {'lr': 1.9844537428087616e-05, 'samples': 25171968, 'steps': 131103, 'loss/train': 1.4129729270935059} 08/31/2021 12:58:24 - INFO - __main__ - Step 131105: {'lr': 1.9842465433025343e-05, 'samples': 25172160, 'steps': 131104, 'loss/train': 1.1256834268569946} 08/31/2021 12:58:24 - INFO - __main__ - Step 131106: {'lr': 1.98403935416685e-05, 'samples': 25172352, 'steps': 131105, 'loss/train': 1.4150904417037964} 08/31/2021 12:58:25 - INFO - __main__ - Step 131107: {'lr': 1.9838321754018034e-05, 'samples': 25172544, 'steps': 131106, 'loss/train': 0.9986889362335205} 08/31/2021 12:58:25 - INFO - __main__ - Step 131108: {'lr': 1.983625007007486e-05, 'samples': 25172736, 'steps': 131107, 'loss/train': 1.2903237342834473} 08/31/2021 12:58:27 - INFO - __main__ - Step 131109: {'lr': 1.9834178489839984e-05, 'samples': 25172928, 'steps': 131108, 'loss/train': 0.5345264673233032} 08/31/2021 12:58:27 - INFO - __main__ - Step 131110: {'lr': 1.9832107013314228e-05, 'samples': 25173120, 'steps': 131109, 'loss/train': 1.1840872764587402} 08/31/2021 12:58:28 - INFO - __main__ - Step 131111: {'lr': 1.983003564049854e-05, 'samples': 25173312, 'steps': 131110, 'loss/train': 0.9951485395431519} 08/31/2021 12:58:28 - INFO - __main__ - Step 131112: {'lr': 1.982796437139392e-05, 'samples': 25173504, 'steps': 131111, 'loss/train': 0.791452169418335} 08/31/2021 12:58:28 - INFO - __main__ - Step 131113: {'lr': 1.9825893206001256e-05, 'samples': 25173696, 'steps': 131112, 'loss/train': 1.143983006477356} 08/31/2021 12:58:29 - INFO - __main__ - Step 131114: {'lr': 1.982382214432149e-05, 'samples': 25173888, 'steps': 131113, 'loss/train': 1.4505186080932617} 08/31/2021 12:58:30 - INFO - __main__ - Step 131115: {'lr': 1.982175118635557e-05, 'samples': 25174080, 'steps': 131114, 'loss/train': 0.03324364125728607} 08/31/2021 12:58:31 - INFO - __main__ - Step 131116: {'lr': 1.9819680332104405e-05, 'samples': 25174272, 'steps': 131115, 'loss/train': 1.1738017797470093} 08/31/2021 12:58:31 - INFO - __main__ - Step 131117: {'lr': 1.9817609581568945e-05, 'samples': 25174464, 'steps': 131116, 'loss/train': 1.1328654289245605} 08/31/2021 12:58:31 - INFO - __main__ - Step 131118: {'lr': 1.9815538934750105e-05, 'samples': 25174656, 'steps': 131117, 'loss/train': 0.19864684343338013} 08/31/2021 12:58:32 - INFO - __main__ - Step 131119: {'lr': 1.9813468391648853e-05, 'samples': 25174848, 'steps': 131118, 'loss/train': 1.2879382371902466} 08/31/2021 12:58:33 - INFO - __main__ - Step 131120: {'lr': 1.9811397952266135e-05, 'samples': 25175040, 'steps': 131119, 'loss/train': 0.5568637847900391} 08/31/2021 12:58:34 - INFO - __main__ - Step 131121: {'lr': 1.9809327616602785e-05, 'samples': 25175232, 'steps': 131120, 'loss/train': 0.7139479517936707} 08/31/2021 12:58:34 - INFO - __main__ - Step 131122: {'lr': 1.9807257384659828e-05, 'samples': 25175424, 'steps': 131121, 'loss/train': 0.9324393272399902} 08/31/2021 12:58:34 - INFO - __main__ - Step 131123: {'lr': 1.980518725643815e-05, 'samples': 25175616, 'steps': 131122, 'loss/train': 0.2500758767127991} 08/31/2021 12:58:35 - INFO - __main__ - Step 131124: {'lr': 1.980311723193873e-05, 'samples': 25175808, 'steps': 131123, 'loss/train': 1.3293319940567017} 08/31/2021 12:58:36 - INFO - __main__ - Step 131125: {'lr': 1.9801047311162447e-05, 'samples': 25176000, 'steps': 131124, 'loss/train': 1.1942812204360962} 08/31/2021 12:58:37 - INFO - __main__ - Step 131126: {'lr': 1.9798977494110275e-05, 'samples': 25176192, 'steps': 131125, 'loss/train': 1.2581473588943481} 08/31/2021 12:58:37 - INFO - __main__ - Step 131127: {'lr': 1.9796907780783108e-05, 'samples': 25176384, 'steps': 131126, 'loss/train': 1.0409643650054932} 08/31/2021 12:58:37 - INFO - __main__ - Step 131128: {'lr': 1.9794838171181912e-05, 'samples': 25176576, 'steps': 131127, 'loss/train': 0.8970348834991455} 08/31/2021 12:58:38 - INFO - __main__ - Step 131129: {'lr': 1.979276866530763e-05, 'samples': 25176768, 'steps': 131128, 'loss/train': 0.21760885417461395} 08/31/2021 12:58:40 - INFO - __main__ - Step 131130: {'lr': 1.9790699263161154e-05, 'samples': 25176960, 'steps': 131129, 'loss/train': 1.5566450357437134} 08/31/2021 12:58:40 - INFO - __main__ - Step 131131: {'lr': 1.9788629964743454e-05, 'samples': 25177152, 'steps': 131130, 'loss/train': 1.9181549549102783} 08/31/2021 12:58:41 - INFO - __main__ - Step 131132: {'lr': 1.9786560770055472e-05, 'samples': 25177344, 'steps': 131131, 'loss/train': 1.340335726737976} 08/31/2021 12:58:41 - INFO - __main__ - Step 131133: {'lr': 1.978449167909807e-05, 'samples': 25177536, 'steps': 131132, 'loss/train': 1.31034517288208} 08/31/2021 12:58:41 - INFO - __main__ - Step 131134: {'lr': 1.978242269187222e-05, 'samples': 25177728, 'steps': 131133, 'loss/train': 1.2546663284301758} 08/31/2021 12:58:43 - INFO - __main__ - Step 131135: {'lr': 1.9780353808378866e-05, 'samples': 25177920, 'steps': 131134, 'loss/train': 1.060758352279663} 08/31/2021 12:58:43 - INFO - __main__ - Step 131136: {'lr': 1.977828502861895e-05, 'samples': 25178112, 'steps': 131135, 'loss/train': 0.49923038482666016} 08/31/2021 12:58:44 - INFO - __main__ - Step 131137: {'lr': 1.9776216352593357e-05, 'samples': 25178304, 'steps': 131136, 'loss/train': 0.8577482104301453} 08/31/2021 12:58:44 - INFO - __main__ - Step 131138: {'lr': 1.9774147780303064e-05, 'samples': 25178496, 'steps': 131137, 'loss/train': 0.29237887263298035} 08/31/2021 12:58:44 - INFO - __main__ - Step 131139: {'lr': 1.9772079311748985e-05, 'samples': 25178688, 'steps': 131138, 'loss/train': 1.6401492357254028} 08/31/2021 12:58:46 - INFO - __main__ - Step 131140: {'lr': 1.9770010946932036e-05, 'samples': 25178880, 'steps': 131139, 'loss/train': 1.4864602088928223} 08/31/2021 12:58:46 - INFO - __main__ - Step 131141: {'lr': 1.976794268585319e-05, 'samples': 25179072, 'steps': 131140, 'loss/train': 0.8364846706390381} 08/31/2021 12:58:47 - INFO - __main__ - Step 131142: {'lr': 1.9765874528513362e-05, 'samples': 25179264, 'steps': 131141, 'loss/train': 1.3819128274917603} 08/31/2021 12:58:47 - INFO - __main__ - Step 131143: {'lr': 1.9763806474913466e-05, 'samples': 25179456, 'steps': 131142, 'loss/train': 1.5747017860412598} 08/31/2021 12:58:47 - INFO - __main__ - Step 131144: {'lr': 1.9761738525054445e-05, 'samples': 25179648, 'steps': 131143, 'loss/train': 1.2630705833435059} 08/31/2021 12:58:49 - INFO - __main__ - Step 131145: {'lr': 1.9759670678937275e-05, 'samples': 25179840, 'steps': 131144, 'loss/train': 1.6751471757888794} 08/31/2021 12:58:49 - INFO - __main__ - Step 131146: {'lr': 1.9757602936562813e-05, 'samples': 25180032, 'steps': 131145, 'loss/train': 0.3742235004901886} 08/31/2021 12:58:50 - INFO - __main__ - Step 131147: {'lr': 1.9755535297932004e-05, 'samples': 25180224, 'steps': 131146, 'loss/train': 1.5379406213760376} 08/31/2021 12:58:50 - INFO - __main__ - Step 131148: {'lr': 1.975346776304582e-05, 'samples': 25180416, 'steps': 131147, 'loss/train': 1.2055343389511108} 08/31/2021 12:58:50 - INFO - __main__ - Step 131149: {'lr': 1.9751400331905146e-05, 'samples': 25180608, 'steps': 131148, 'loss/train': 1.175503134727478} 08/31/2021 12:58:52 - INFO - __main__ - Step 131150: {'lr': 1.9749333004510956e-05, 'samples': 25180800, 'steps': 131149, 'loss/train': 1.0192252397537231} 08/31/2021 12:58:52 - INFO - __main__ - Step 131151: {'lr': 1.9747265780864137e-05, 'samples': 25180992, 'steps': 131150, 'loss/train': 0.9328149557113647} 08/31/2021 12:58:53 - INFO - __main__ - Step 131152: {'lr': 1.9745198660965663e-05, 'samples': 25181184, 'steps': 131151, 'loss/train': 1.1739211082458496} 08/31/2021 12:58:53 - INFO - __main__ - Step 131153: {'lr': 1.9743131644816474e-05, 'samples': 25181376, 'steps': 131152, 'loss/train': 1.2057294845581055} 08/31/2021 12:58:53 - INFO - __main__ - Step 131154: {'lr': 1.9741064732417434e-05, 'samples': 25181568, 'steps': 131153, 'loss/train': 1.145856261253357} 08/31/2021 12:58:54 - INFO - __main__ - Step 131155: {'lr': 1.9738997923769542e-05, 'samples': 25181760, 'steps': 131154, 'loss/train': 1.3518226146697998} 08/31/2021 12:58:55 - INFO - __main__ - Step 131156: {'lr': 1.973693121887371e-05, 'samples': 25181952, 'steps': 131155, 'loss/train': 1.7307589054107666} 08/31/2021 12:58:56 - INFO - __main__ - Step 131157: {'lr': 1.9734864617730857e-05, 'samples': 25182144, 'steps': 131156, 'loss/train': 1.1704350709915161} 08/31/2021 12:58:56 - INFO - __main__ - Step 131158: {'lr': 1.9732798120341928e-05, 'samples': 25182336, 'steps': 131157, 'loss/train': 0.45825517177581787} 08/31/2021 12:58:57 - INFO - __main__ - Step 131159: {'lr': 1.9730731726707864e-05, 'samples': 25182528, 'steps': 131158, 'loss/train': 0.7339199781417847} 08/31/2021 12:58:57 - INFO - __main__ - Step 131160: {'lr': 1.9728665436829552e-05, 'samples': 25182720, 'steps': 131159, 'loss/train': 1.4584455490112305} 08/31/2021 12:58:58 - INFO - __main__ - Step 131161: {'lr': 1.9726599250707965e-05, 'samples': 25182912, 'steps': 131160, 'loss/train': 0.8967645764350891} 08/31/2021 12:58:59 - INFO - __main__ - Step 131162: {'lr': 1.9724533168343994e-05, 'samples': 25183104, 'steps': 131161, 'loss/train': 0.6230436563491821} 08/31/2021 12:58:59 - INFO - __main__ - Step 131163: {'lr': 1.972246718973861e-05, 'samples': 25183296, 'steps': 131162, 'loss/train': 0.7594031691551208} 08/31/2021 12:59:00 - INFO - __main__ - Step 131164: {'lr': 1.9720401314892722e-05, 'samples': 25183488, 'steps': 131163, 'loss/train': 0.40317896008491516} 08/31/2021 12:59:00 - INFO - __main__ - Step 131165: {'lr': 1.971833554380728e-05, 'samples': 25183680, 'steps': 131164, 'loss/train': 0.7380844950675964} 08/31/2021 12:59:01 - INFO - __main__ - Step 131166: {'lr': 1.9716269876483173e-05, 'samples': 25183872, 'steps': 131165, 'loss/train': 1.0299041271209717} 08/31/2021 12:59:02 - INFO - __main__ - Step 131167: {'lr': 1.9714204312921397e-05, 'samples': 25184064, 'steps': 131166, 'loss/train': 1.138177752494812} 08/31/2021 12:59:02 - INFO - __main__ - Step 131168: {'lr': 1.971213885312284e-05, 'samples': 25184256, 'steps': 131167, 'loss/train': 0.18796181678771973} 08/31/2021 12:59:03 - INFO - __main__ - Step 131169: {'lr': 1.971007349708842e-05, 'samples': 25184448, 'steps': 131168, 'loss/train': 1.4162362813949585} 08/31/2021 12:59:03 - INFO - __main__ - Step 131170: {'lr': 1.970800824481911e-05, 'samples': 25184640, 'steps': 131169, 'loss/train': 0.25045615434646606} 08/31/2021 12:59:05 - INFO - __main__ - Step 131171: {'lr': 1.9705943096315793e-05, 'samples': 25184832, 'steps': 131170, 'loss/train': 1.436246395111084} 08/31/2021 12:59:05 - INFO - __main__ - Step 131172: {'lr': 1.970387805157947e-05, 'samples': 25185024, 'steps': 131171, 'loss/train': 1.160253643989563} 08/31/2021 12:59:05 - INFO - __main__ - Step 131173: {'lr': 1.9701813110611004e-05, 'samples': 25185216, 'steps': 131172, 'loss/train': 1.1149920225143433} 08/31/2021 12:59:06 - INFO - __main__ - Step 131174: {'lr': 1.9699748273411338e-05, 'samples': 25185408, 'steps': 131173, 'loss/train': 0.6576778888702393} 08/31/2021 12:59:06 - INFO - __main__ - Step 131175: {'lr': 1.9697683539981413e-05, 'samples': 25185600, 'steps': 131174, 'loss/train': 1.1101559400558472} 08/31/2021 12:59:06 - INFO - __main__ - Step 131176: {'lr': 1.969561891032215e-05, 'samples': 25185792, 'steps': 131175, 'loss/train': 1.319810390472412} 08/31/2021 12:59:08 - INFO - __main__ - Step 131177: {'lr': 1.9693554384434487e-05, 'samples': 25185984, 'steps': 131176, 'loss/train': 1.0890214443206787} 08/31/2021 12:59:08 - INFO - __main__ - Step 131178: {'lr': 1.969148996231937e-05, 'samples': 25186176, 'steps': 131177, 'loss/train': 0.6965711712837219} 08/31/2021 12:59:09 - INFO - __main__ - Step 131179: {'lr': 1.9689425643977686e-05, 'samples': 25186368, 'steps': 131178, 'loss/train': 1.2476152181625366} 08/31/2021 12:59:09 - INFO - __main__ - Step 131180: {'lr': 1.9687361429410438e-05, 'samples': 25186560, 'steps': 131179, 'loss/train': 1.231711506843567} 08/31/2021 12:59:09 - INFO - __main__ - Step 131181: {'lr': 1.9685297318618485e-05, 'samples': 25186752, 'steps': 131180, 'loss/train': 1.3995981216430664} 08/31/2021 12:59:11 - INFO - __main__ - Step 131182: {'lr': 1.9683233311602766e-05, 'samples': 25186944, 'steps': 131181, 'loss/train': 1.498978614807129} 08/31/2021 12:59:11 - INFO - __main__ - Step 131183: {'lr': 1.968116940836426e-05, 'samples': 25187136, 'steps': 131182, 'loss/train': 1.401146411895752} 08/31/2021 12:59:12 - INFO - __main__ - Step 131184: {'lr': 1.9679105608903847e-05, 'samples': 25187328, 'steps': 131183, 'loss/train': 0.4440532922744751} 08/31/2021 12:59:12 - INFO - __main__ - Step 131185: {'lr': 1.9677041913222477e-05, 'samples': 25187520, 'steps': 131184, 'loss/train': 0.8529733419418335} 08/31/2021 12:59:13 - INFO - __main__ - Step 131186: {'lr': 1.967497832132112e-05, 'samples': 25187712, 'steps': 131185, 'loss/train': 1.2991727590560913} 08/31/2021 12:59:15 - INFO - __main__ - Step 131187: {'lr': 1.9672914833200605e-05, 'samples': 25187904, 'steps': 131186, 'loss/train': 0.3058815002441406} 08/31/2021 12:59:15 - INFO - __main__ - Step 131188: {'lr': 1.9670851448861937e-05, 'samples': 25188096, 'steps': 131187, 'loss/train': 1.2076789140701294} 08/31/2021 12:59:16 - INFO - __main__ - Step 131189: {'lr': 1.966878816830603e-05, 'samples': 25188288, 'steps': 131188, 'loss/train': 1.2077780961990356} 08/31/2021 12:59:16 - INFO - __main__ - Step 131190: {'lr': 1.9666724991533825e-05, 'samples': 25188480, 'steps': 131189, 'loss/train': 0.9025377035140991} 08/31/2021 12:59:16 - INFO - __main__ - Step 131191: {'lr': 1.9664661918546213e-05, 'samples': 25188672, 'steps': 131190, 'loss/train': 1.3213813304901123} 08/31/2021 12:59:18 - INFO - __main__ - Step 131192: {'lr': 1.966259894934416e-05, 'samples': 25188864, 'steps': 131191, 'loss/train': 0.12273682653903961} 08/31/2021 12:59:18 - INFO - __main__ - Step 131193: {'lr': 1.9660536083928593e-05, 'samples': 25189056, 'steps': 131192, 'loss/train': 0.6653515100479126} 08/31/2021 12:59:19 - INFO - __main__ - Step 131194: {'lr': 1.965847332230042e-05, 'samples': 25189248, 'steps': 131193, 'loss/train': 1.1180044412612915} 08/31/2021 12:59:19 - INFO - __main__ - Step 131195: {'lr': 1.965641066446061e-05, 'samples': 25189440, 'steps': 131194, 'loss/train': 0.8302361965179443} 08/31/2021 12:59:19 - INFO - __main__ - Step 131196: {'lr': 1.9654348110410057e-05, 'samples': 25189632, 'steps': 131195, 'loss/train': 0.880930483341217} 08/31/2021 12:59:20 - INFO - __main__ - Step 131197: {'lr': 1.9652285660149677e-05, 'samples': 25189824, 'steps': 131196, 'loss/train': 1.6170378923416138} 08/31/2021 12:59:22 - INFO - __main__ - Step 131198: {'lr': 1.9650223313680437e-05, 'samples': 25190016, 'steps': 131197, 'loss/train': 1.5537488460540771} 08/31/2021 12:59:22 - INFO - __main__ - Step 131199: {'lr': 1.9648161071003312e-05, 'samples': 25190208, 'steps': 131198, 'loss/train': 0.6250969767570496} 08/31/2021 12:59:22 - INFO - __main__ - Step 131200: {'lr': 1.9646098932119104e-05, 'samples': 25190400, 'steps': 131199, 'loss/train': 1.1331162452697754} 08/31/2021 12:59:23 - INFO - __main__ - Step 131201: {'lr': 1.9644036897028815e-05, 'samples': 25190592, 'steps': 131200, 'loss/train': 1.510670781135559} 08/31/2021 12:59:23 - INFO - __main__ - Step 131202: {'lr': 1.9641974965733388e-05, 'samples': 25190784, 'steps': 131201, 'loss/train': 1.099523901939392} 08/31/2021 12:59:24 - INFO - __main__ - Step 131203: {'lr': 1.963991313823371e-05, 'samples': 25190976, 'steps': 131202, 'loss/train': 0.015877071768045425} 08/31/2021 12:59:25 - INFO - __main__ - Step 131204: {'lr': 1.9637851414530755e-05, 'samples': 25191168, 'steps': 131203, 'loss/train': 1.3876457214355469} 08/31/2021 12:59:26 - INFO - __main__ - Step 131205: {'lr': 1.963578979462541e-05, 'samples': 25191360, 'steps': 131204, 'loss/train': 1.7422549724578857} 08/31/2021 12:59:26 - INFO - __main__ - Step 131206: {'lr': 1.9633728278518614e-05, 'samples': 25191552, 'steps': 131205, 'loss/train': 1.9196792840957642} 08/31/2021 12:59:26 - INFO - __main__ - Step 131207: {'lr': 1.963166686621132e-05, 'samples': 25191744, 'steps': 131206, 'loss/train': 1.4847724437713623} 08/31/2021 12:59:27 - INFO - __main__ - Step 131208: {'lr': 1.9629605557704432e-05, 'samples': 25191936, 'steps': 131207, 'loss/train': 0.48591315746307373} 08/31/2021 12:59:28 - INFO - __main__ - Step 131209: {'lr': 1.9627544352998906e-05, 'samples': 25192128, 'steps': 131208, 'loss/train': 0.3111222982406616} 08/31/2021 12:59:29 - INFO - __main__ - Step 131210: {'lr': 1.962548325209565e-05, 'samples': 25192320, 'steps': 131209, 'loss/train': 1.4204260110855103} 08/31/2021 12:59:29 - INFO - __main__ - Step 131211: {'lr': 1.9623422254995582e-05, 'samples': 25192512, 'steps': 131210, 'loss/train': 1.4477571249008179} 08/31/2021 12:59:30 - INFO - __main__ - Step 131212: {'lr': 1.9621361361699702e-05, 'samples': 25192704, 'steps': 131211, 'loss/train': 0.16273616254329681} 08/31/2021 12:59:30 - INFO - __main__ - Step 131213: {'lr': 1.9619300572208842e-05, 'samples': 25192896, 'steps': 131212, 'loss/train': 1.7212384939193726} 08/31/2021 12:59:31 - INFO - __main__ - Step 131214: {'lr': 1.9617239886523974e-05, 'samples': 25193088, 'steps': 131213, 'loss/train': 0.8268502950668335} 08/31/2021 12:59:32 - INFO - __main__ - Step 131215: {'lr': 1.9615179304645985e-05, 'samples': 25193280, 'steps': 131214, 'loss/train': 1.3774433135986328} 08/31/2021 12:59:32 - INFO - __main__ - Step 131216: {'lr': 1.9613118826575878e-05, 'samples': 25193472, 'steps': 131215, 'loss/train': 1.1249815225601196} 08/31/2021 12:59:32 - INFO - __main__ - Step 131217: {'lr': 1.9611058452314534e-05, 'samples': 25193664, 'steps': 131216, 'loss/train': 1.4883910417556763} 08/31/2021 12:59:33 - INFO - __main__ - Step 131218: {'lr': 1.9608998181862903e-05, 'samples': 25193856, 'steps': 131217, 'loss/train': 1.8146615028381348} 08/31/2021 12:59:33 - INFO - __main__ - Step 131219: {'lr': 1.960693801522187e-05, 'samples': 25194048, 'steps': 131218, 'loss/train': 2.2000458240509033} 08/31/2021 12:59:35 - INFO - __main__ - Step 131220: {'lr': 1.9604877952392434e-05, 'samples': 25194240, 'steps': 131219, 'loss/train': 1.112648606300354} 08/31/2021 12:59:35 - INFO - __main__ - Step 131221: {'lr': 1.960281799337546e-05, 'samples': 25194432, 'steps': 131220, 'loss/train': 1.2606332302093506} 08/31/2021 12:59:35 - INFO - __main__ - Step 131222: {'lr': 1.9600758138171916e-05, 'samples': 25194624, 'steps': 131221, 'loss/train': 0.8326414823532104} 08/31/2021 12:59:36 - INFO - __main__ - Step 131223: {'lr': 1.9598698386782715e-05, 'samples': 25194816, 'steps': 131222, 'loss/train': 0.9322099089622498} 08/31/2021 12:59:36 - INFO - __main__ - Step 131224: {'lr': 1.959663873920878e-05, 'samples': 25195008, 'steps': 131223, 'loss/train': 1.4266961812973022} 08/31/2021 12:59:38 - INFO - __main__ - Step 131225: {'lr': 1.959457919545102e-05, 'samples': 25195200, 'steps': 131224, 'loss/train': 1.249472975730896} 08/31/2021 12:59:38 - INFO - __main__ - Step 131226: {'lr': 1.9592519755510463e-05, 'samples': 25195392, 'steps': 131225, 'loss/train': 1.0559613704681396} 08/31/2021 12:59:39 - INFO - __main__ - Step 131227: {'lr': 1.959046041938792e-05, 'samples': 25195584, 'steps': 131226, 'loss/train': 0.40048274397850037} 08/31/2021 12:59:39 - INFO - __main__ - Step 131228: {'lr': 1.9588401187084326e-05, 'samples': 25195776, 'steps': 131227, 'loss/train': 0.9711436629295349} 08/31/2021 12:59:39 - INFO - __main__ - Step 131229: {'lr': 1.958634205860066e-05, 'samples': 25195968, 'steps': 131228, 'loss/train': 0.6297467947006226} 08/31/2021 12:59:41 - INFO - __main__ - Step 131230: {'lr': 1.958428303393786e-05, 'samples': 25196160, 'steps': 131229, 'loss/train': 1.1290489435195923} 08/31/2021 12:59:41 - INFO - __main__ - Step 131231: {'lr': 1.958222411309679e-05, 'samples': 25196352, 'steps': 131230, 'loss/train': 1.2303704023361206} 08/31/2021 12:59:42 - INFO - __main__ - Step 131232: {'lr': 1.9580165296078422e-05, 'samples': 25196544, 'steps': 131231, 'loss/train': 0.5392962694168091} 08/31/2021 12:59:42 - INFO - __main__ - Step 131233: {'lr': 1.9578106582883698e-05, 'samples': 25196736, 'steps': 131232, 'loss/train': 0.6763576865196228} 08/31/2021 12:59:42 - INFO - __main__ - Step 131234: {'lr': 1.9576047973513505e-05, 'samples': 25196928, 'steps': 131233, 'loss/train': 1.1137974262237549} 08/31/2021 12:59:44 - INFO - __main__ - Step 131235: {'lr': 1.957398946796879e-05, 'samples': 25197120, 'steps': 131234, 'loss/train': 0.26580846309661865} 08/31/2021 12:59:44 - INFO - __main__ - Step 131236: {'lr': 1.9571931066250492e-05, 'samples': 25197312, 'steps': 131235, 'loss/train': 0.9047799706459045} 08/31/2021 12:59:45 - INFO - __main__ - Step 131237: {'lr': 1.9569872768359504e-05, 'samples': 25197504, 'steps': 131236, 'loss/train': 1.3342738151550293} 08/31/2021 12:59:45 - INFO - __main__ - Step 131238: {'lr': 1.9567814574296793e-05, 'samples': 25197696, 'steps': 131237, 'loss/train': 0.9637651443481445} 08/31/2021 12:59:45 - INFO - __main__ - Step 131239: {'lr': 1.9565756484063308e-05, 'samples': 25197888, 'steps': 131238, 'loss/train': 0.8488596081733704} 08/31/2021 12:59:46 - INFO - __main__ - Step 131240: {'lr': 1.9563698497659878e-05, 'samples': 25198080, 'steps': 131239, 'loss/train': 0.6492935419082642} 08/31/2021 12:59:48 - INFO - __main__ - Step 131241: {'lr': 1.95616406150875e-05, 'samples': 25198272, 'steps': 131240, 'loss/train': 1.0332577228546143} 08/31/2021 12:59:48 - INFO - __main__ - Step 131242: {'lr': 1.9559582836347094e-05, 'samples': 25198464, 'steps': 131241, 'loss/train': 1.1262980699539185} 08/31/2021 12:59:49 - INFO - __main__ - Step 131243: {'lr': 1.9557525161439603e-05, 'samples': 25198656, 'steps': 131242, 'loss/train': 1.1439099311828613} 08/31/2021 12:59:49 - INFO - __main__ - Step 131244: {'lr': 1.9555467590365917e-05, 'samples': 25198848, 'steps': 131243, 'loss/train': 1.6834267377853394} 08/31/2021 12:59:50 - INFO - __main__ - Step 131245: {'lr': 1.9553410123126975e-05, 'samples': 25199040, 'steps': 131244, 'loss/train': 1.5142199993133545} 08/31/2021 12:59:51 - INFO - __main__ - Step 131246: {'lr': 1.9551352759723724e-05, 'samples': 25199232, 'steps': 131245, 'loss/train': 1.0318325757980347} 08/31/2021 12:59:51 - INFO - __main__ - Step 131247: {'lr': 1.954929550015705e-05, 'samples': 25199424, 'steps': 131246, 'loss/train': 1.095658540725708} 08/31/2021 12:59:52 - INFO - __main__ - Step 131248: {'lr': 1.9547238344427925e-05, 'samples': 25199616, 'steps': 131247, 'loss/train': 1.2103649377822876} 08/31/2021 12:59:52 - INFO - __main__ - Step 131249: {'lr': 1.9545181292537267e-05, 'samples': 25199808, 'steps': 131248, 'loss/train': 0.6736786365509033} 08/31/2021 12:59:52 - INFO - __main__ - Step 131250: {'lr': 1.954312434448599e-05, 'samples': 25200000, 'steps': 131249, 'loss/train': 1.3020573854446411} 08/31/2021 12:59:54 - INFO - __main__ - Step 131251: {'lr': 1.9541067500275038e-05, 'samples': 25200192, 'steps': 131250, 'loss/train': 0.6466085910797119} 08/31/2021 12:59:54 - INFO - __main__ - Step 131252: {'lr': 1.95390107599053e-05, 'samples': 25200384, 'steps': 131251, 'loss/train': 1.42609441280365} 08/31/2021 12:59:55 - INFO - __main__ - Step 131253: {'lr': 1.9536954123377776e-05, 'samples': 25200576, 'steps': 131252, 'loss/train': 1.4324183464050293} 08/31/2021 12:59:55 - INFO - __main__ - Step 131254: {'lr': 1.9534897590693323e-05, 'samples': 25200768, 'steps': 131253, 'loss/train': 1.2895307540893555} 08/31/2021 12:59:55 - INFO - __main__ - Step 131255: {'lr': 1.953284116185286e-05, 'samples': 25200960, 'steps': 131254, 'loss/train': 0.31957316398620605} 08/31/2021 12:59:57 - INFO - __main__ - Step 131256: {'lr': 1.9530784836857356e-05, 'samples': 25201152, 'steps': 131255, 'loss/train': 0.624036431312561} 08/31/2021 12:59:58 - INFO - __main__ - Step 131257: {'lr': 1.952872861570773e-05, 'samples': 25201344, 'steps': 131256, 'loss/train': 0.50701504945755} 08/31/2021 12:59:58 - INFO - __main__ - Step 131258: {'lr': 1.9526672498404897e-05, 'samples': 25201536, 'steps': 131257, 'loss/train': 1.1963226795196533} 08/31/2021 12:59:58 - INFO - __main__ - Step 131259: {'lr': 1.952461648494977e-05, 'samples': 25201728, 'steps': 131258, 'loss/train': 0.44256648421287537} 08/31/2021 12:59:59 - INFO - __main__ - Step 131260: {'lr': 1.9522560575343324e-05, 'samples': 25201920, 'steps': 131259, 'loss/train': 1.2913122177124023} 08/31/2021 13:00:00 - INFO - __main__ - Step 131261: {'lr': 1.9520504769586446e-05, 'samples': 25202112, 'steps': 131260, 'loss/train': 0.05465083569288254} 08/31/2021 13:00:01 - INFO - __main__ - Step 131262: {'lr': 1.951844906768005e-05, 'samples': 25202304, 'steps': 131261, 'loss/train': 0.03659140318632126} 08/31/2021 13:00:01 - INFO - __main__ - Step 131263: {'lr': 1.951639346962511e-05, 'samples': 25202496, 'steps': 131262, 'loss/train': 1.232497215270996} 08/31/2021 13:00:01 - INFO - __main__ - Step 131264: {'lr': 1.9514337975422513e-05, 'samples': 25202688, 'steps': 131263, 'loss/train': 1.4324840307235718} 08/31/2021 13:00:02 - INFO - __main__ - Step 131265: {'lr': 1.9512282585073206e-05, 'samples': 25202880, 'steps': 131264, 'loss/train': 1.1894725561141968} 08/31/2021 13:00:02 - INFO - __main__ - Step 131266: {'lr': 1.9510227298578154e-05, 'samples': 25203072, 'steps': 131265, 'loss/train': 0.7992984056472778} 08/31/2021 13:00:04 - INFO - __main__ - Step 131267: {'lr': 1.9508172115938194e-05, 'samples': 25203264, 'steps': 131266, 'loss/train': 1.0934209823608398} 08/31/2021 13:00:04 - INFO - __main__ - Step 131268: {'lr': 1.9506117037154297e-05, 'samples': 25203456, 'steps': 131267, 'loss/train': 0.4906558692455292} 08/31/2021 13:00:05 - INFO - __main__ - Step 131269: {'lr': 1.950406206222738e-05, 'samples': 25203648, 'steps': 131268, 'loss/train': 0.27249234914779663} 08/31/2021 13:00:05 - INFO - __main__ - Step 131270: {'lr': 1.9502007191158355e-05, 'samples': 25203840, 'steps': 131269, 'loss/train': 1.0035589933395386} 08/31/2021 13:00:05 - INFO - __main__ - Step 131271: {'lr': 1.9499952423948198e-05, 'samples': 25204032, 'steps': 131270, 'loss/train': 1.1227532625198364} 08/31/2021 13:00:07 - INFO - __main__ - Step 131272: {'lr': 1.9497897760597792e-05, 'samples': 25204224, 'steps': 131271, 'loss/train': 1.4977611303329468} 08/31/2021 13:00:07 - INFO - __main__ - Step 131273: {'lr': 1.9495843201108087e-05, 'samples': 25204416, 'steps': 131272, 'loss/train': 1.6837029457092285} 08/31/2021 13:00:08 - INFO - __main__ - Step 131274: {'lr': 1.9493788745479996e-05, 'samples': 25204608, 'steps': 131273, 'loss/train': 0.10720111429691315} 08/31/2021 13:00:08 - INFO - __main__ - Step 131275: {'lr': 1.9491734393714434e-05, 'samples': 25204800, 'steps': 131274, 'loss/train': 0.446735143661499} 08/31/2021 13:00:08 - INFO - __main__ - Step 131276: {'lr': 1.948968014581237e-05, 'samples': 25204992, 'steps': 131275, 'loss/train': 1.5727946758270264} 08/31/2021 13:00:10 - INFO - __main__ - Step 131277: {'lr': 1.9487626001774674e-05, 'samples': 25205184, 'steps': 131276, 'loss/train': 1.1630960702896118} 08/31/2021 13:00:10 - INFO - __main__ - Step 131278: {'lr': 1.9485571961602304e-05, 'samples': 25205376, 'steps': 131277, 'loss/train': 1.2057974338531494} 08/31/2021 13:00:11 - INFO - __main__ - Step 131279: {'lr': 1.948351802529616e-05, 'samples': 25205568, 'steps': 131278, 'loss/train': 0.8820315599441528} 08/31/2021 13:00:11 - INFO - __main__ - Step 131280: {'lr': 1.9481464192857264e-05, 'samples': 25205760, 'steps': 131279, 'loss/train': 0.6911544799804688} 08/31/2021 13:00:11 - INFO - __main__ - Step 131281: {'lr': 1.947941046428639e-05, 'samples': 25205952, 'steps': 131280, 'loss/train': 0.03741549700498581} 08/31/2021 13:00:13 - INFO - __main__ - Step 131282: {'lr': 1.9477356839584543e-05, 'samples': 25206144, 'steps': 131281, 'loss/train': 0.5632384419441223} 08/31/2021 13:00:13 - INFO - __main__ - Step 131283: {'lr': 1.9475303318752662e-05, 'samples': 25206336, 'steps': 131282, 'loss/train': 0.9302883744239807} 08/31/2021 13:00:14 - INFO - __main__ - Step 131284: {'lr': 1.947324990179161e-05, 'samples': 25206528, 'steps': 131283, 'loss/train': 1.074255108833313} 08/31/2021 13:00:14 - INFO - __main__ - Step 131285: {'lr': 1.947119658870239e-05, 'samples': 25206720, 'steps': 131284, 'loss/train': 0.36662858724594116} 08/31/2021 13:00:14 - INFO - __main__ - Step 131286: {'lr': 1.9469143379485882e-05, 'samples': 25206912, 'steps': 131285, 'loss/train': 0.3273441195487976} 08/31/2021 13:00:16 - INFO - __main__ - Step 131287: {'lr': 1.9467090274143035e-05, 'samples': 25207104, 'steps': 131286, 'loss/train': 1.066410779953003} 08/31/2021 13:00:16 - INFO - __main__ - Step 131288: {'lr': 1.9465037272674734e-05, 'samples': 25207296, 'steps': 131287, 'loss/train': 1.060265302658081} 08/31/2021 13:00:17 - INFO - __main__ - Step 131289: {'lr': 1.9462984375081953e-05, 'samples': 25207488, 'steps': 131288, 'loss/train': 1.1759023666381836} 08/31/2021 13:00:17 - INFO - __main__ - Step 131290: {'lr': 1.9460931581365583e-05, 'samples': 25207680, 'steps': 131289, 'loss/train': 0.8197064995765686} 08/31/2021 13:00:17 - INFO - __main__ - Step 131291: {'lr': 1.945887889152656e-05, 'samples': 25207872, 'steps': 131290, 'loss/train': 1.9513806104660034} 08/31/2021 13:00:18 - INFO - __main__ - Step 131292: {'lr': 1.9456826305565805e-05, 'samples': 25208064, 'steps': 131291, 'loss/train': 1.0159194469451904} 08/31/2021 13:00:20 - INFO - __main__ - Step 131293: {'lr': 1.945477382348429e-05, 'samples': 25208256, 'steps': 131292, 'loss/train': 0.5487342476844788} 08/31/2021 13:00:21 - INFO - __main__ - Step 131294: {'lr': 1.9452721445282844e-05, 'samples': 25208448, 'steps': 131293, 'loss/train': 0.1001901924610138} 08/31/2021 13:00:21 - INFO - __main__ - Step 131295: {'lr': 1.9450669170962472e-05, 'samples': 25208640, 'steps': 131294, 'loss/train': 2.5829997062683105} 08/31/2021 13:00:21 - INFO - __main__ - Step 131296: {'lr': 1.9448617000524054e-05, 'samples': 25208832, 'steps': 131295, 'loss/train': 1.0214158296585083} 08/31/2021 13:00:22 - INFO - __main__ - Step 131297: {'lr': 1.9446564933968512e-05, 'samples': 25209024, 'steps': 131296, 'loss/train': 1.9435888528823853} 08/31/2021 13:00:22 - INFO - __main__ - Step 131298: {'lr': 1.9444512971296817e-05, 'samples': 25209216, 'steps': 131297, 'loss/train': 1.006466269493103} 08/31/2021 13:00:23 - INFO - __main__ - Step 131299: {'lr': 1.9442461112509857e-05, 'samples': 25209408, 'steps': 131298, 'loss/train': 0.884372889995575} 08/31/2021 13:00:24 - INFO - __main__ - Step 131300: {'lr': 1.9440409357608575e-05, 'samples': 25209600, 'steps': 131299, 'loss/train': 1.4331649541854858} 08/31/2021 13:00:24 - INFO - __main__ - Step 131301: {'lr': 1.9438357706593884e-05, 'samples': 25209792, 'steps': 131300, 'loss/train': 0.8913733959197998} 08/31/2021 13:00:25 - INFO - __main__ - Step 131302: {'lr': 1.9436306159466704e-05, 'samples': 25209984, 'steps': 131301, 'loss/train': 0.4316030740737915} 08/31/2021 13:00:25 - INFO - __main__ - Step 131303: {'lr': 1.943425471622798e-05, 'samples': 25210176, 'steps': 131302, 'loss/train': 0.5959780216217041} 08/31/2021 13:00:26 - INFO - __main__ - Step 131304: {'lr': 1.9432203376878594e-05, 'samples': 25210368, 'steps': 131303, 'loss/train': 1.1667661666870117} 08/31/2021 13:00:27 - INFO - __main__ - Step 131305: {'lr': 1.943015214141952e-05, 'samples': 25210560, 'steps': 131304, 'loss/train': 0.9842581152915955} 08/31/2021 13:00:27 - INFO - __main__ - Step 131306: {'lr': 1.9428101009851678e-05, 'samples': 25210752, 'steps': 131305, 'loss/train': 1.1074970960617065} 08/31/2021 13:00:28 - INFO - __main__ - Step 131307: {'lr': 1.9426049982176008e-05, 'samples': 25210944, 'steps': 131306, 'loss/train': 0.7243608832359314} 08/31/2021 13:00:28 - INFO - __main__ - Step 131308: {'lr': 1.9423999058393343e-05, 'samples': 25211136, 'steps': 131307, 'loss/train': 0.6364304423332214} 08/31/2021 13:00:29 - INFO - __main__ - Step 131309: {'lr': 1.9421948238504684e-05, 'samples': 25211328, 'steps': 131308, 'loss/train': 1.7906769514083862} 08/31/2021 13:00:30 - INFO - __main__ - Step 131310: {'lr': 1.9419897522510917e-05, 'samples': 25211520, 'steps': 131309, 'loss/train': 1.5847384929656982} 08/31/2021 13:00:30 - INFO - __main__ - Step 131311: {'lr': 1.9417846910413012e-05, 'samples': 25211712, 'steps': 131310, 'loss/train': 1.2366372346878052} 08/31/2021 13:00:31 - INFO - __main__ - Step 131312: {'lr': 1.9415796402211834e-05, 'samples': 25211904, 'steps': 131311, 'loss/train': 0.7272616028785706} 08/31/2021 13:00:31 - INFO - __main__ - Step 131313: {'lr': 1.9413745997908377e-05, 'samples': 25212096, 'steps': 131312, 'loss/train': 0.9577257037162781} 08/31/2021 13:00:32 - INFO - __main__ - Step 131314: {'lr': 1.9411695697503506e-05, 'samples': 25212288, 'steps': 131313, 'loss/train': 1.5096808671951294} 08/31/2021 13:00:33 - INFO - __main__ - Step 131315: {'lr': 1.9409645500998163e-05, 'samples': 25212480, 'steps': 131314, 'loss/train': 1.6685402393341064} 08/31/2021 13:00:33 - INFO - __main__ - Step 131316: {'lr': 1.940759540839329e-05, 'samples': 25212672, 'steps': 131315, 'loss/train': 1.3441040515899658} 08/31/2021 13:00:34 - INFO - __main__ - Step 131317: {'lr': 1.940554541968978e-05, 'samples': 25212864, 'steps': 131316, 'loss/train': 1.0882939100265503} 08/31/2021 13:00:34 - INFO - __main__ - Step 131318: {'lr': 1.940349553488857e-05, 'samples': 25213056, 'steps': 131317, 'loss/train': 0.934256911277771} 08/31/2021 13:00:36 - INFO - __main__ - Step 131319: {'lr': 1.940144575399061e-05, 'samples': 25213248, 'steps': 131318, 'loss/train': 1.151047945022583} 08/31/2021 13:00:36 - INFO - __main__ - Step 131320: {'lr': 1.9399396076996838e-05, 'samples': 25213440, 'steps': 131319, 'loss/train': 0.72756427526474} 08/31/2021 13:00:36 - INFO - __main__ - Step 131321: {'lr': 1.9397346503908093e-05, 'samples': 25213632, 'steps': 131320, 'loss/train': 0.8381215333938599} 08/31/2021 13:00:37 - INFO - __main__ - Step 131322: {'lr': 1.939529703472534e-05, 'samples': 25213824, 'steps': 131321, 'loss/train': 0.9596248269081116} 08/31/2021 13:00:37 - INFO - __main__ - Step 131323: {'lr': 1.93932476694495e-05, 'samples': 25214016, 'steps': 131322, 'loss/train': 1.0853649377822876} 08/31/2021 13:00:39 - INFO - __main__ - Step 131324: {'lr': 1.9391198408081513e-05, 'samples': 25214208, 'steps': 131323, 'loss/train': 1.5511562824249268} 08/31/2021 13:00:39 - INFO - __main__ - Step 131325: {'lr': 1.9389149250622295e-05, 'samples': 25214400, 'steps': 131324, 'loss/train': 1.599514126777649} 08/31/2021 13:00:40 - INFO - __main__ - Step 131326: {'lr': 1.9387100197072765e-05, 'samples': 25214592, 'steps': 131325, 'loss/train': 1.2123384475708008} 08/31/2021 13:00:40 - INFO - __main__ - Step 131327: {'lr': 1.9385051247433866e-05, 'samples': 25214784, 'steps': 131326, 'loss/train': 0.013674934394657612} 08/31/2021 13:00:40 - INFO - __main__ - Step 131328: {'lr': 1.9383002401706486e-05, 'samples': 25214976, 'steps': 131327, 'loss/train': 1.4008764028549194} 08/31/2021 13:00:41 - INFO - __main__ - Step 131329: {'lr': 1.9380953659891566e-05, 'samples': 25215168, 'steps': 131328, 'loss/train': 0.7388639450073242} 08/31/2021 13:00:43 - INFO - __main__ - Step 131330: {'lr': 1.937890502199005e-05, 'samples': 25215360, 'steps': 131329, 'loss/train': 0.661536455154419} 08/31/2021 13:00:43 - INFO - __main__ - Step 131331: {'lr': 1.9376856488002803e-05, 'samples': 25215552, 'steps': 131330, 'loss/train': 0.9670343995094299} 08/31/2021 13:00:43 - INFO - __main__ - Step 131332: {'lr': 1.937480805793082e-05, 'samples': 25215744, 'steps': 131331, 'loss/train': 0.9820422530174255} 08/31/2021 13:00:44 - INFO - __main__ - Step 131333: {'lr': 1.937275973177502e-05, 'samples': 25215936, 'steps': 131332, 'loss/train': 1.5092463493347168} 08/31/2021 13:00:44 - INFO - __main__ - Step 131334: {'lr': 1.9370711509536258e-05, 'samples': 25216128, 'steps': 131333, 'loss/train': 0.7994511127471924} 08/31/2021 13:00:44 - INFO - __main__ - Step 131335: {'lr': 1.9368663391215484e-05, 'samples': 25216320, 'steps': 131334, 'loss/train': 0.8042701482772827} 08/31/2021 13:00:46 - INFO - __main__ - Step 131336: {'lr': 1.936661537681364e-05, 'samples': 25216512, 'steps': 131335, 'loss/train': 0.07014908641576767} 08/31/2021 13:00:46 - INFO - __main__ - Step 131337: {'lr': 1.936456746633164e-05, 'samples': 25216704, 'steps': 131336, 'loss/train': 0.1228032037615776} 08/31/2021 13:00:47 - INFO - __main__ - Step 131338: {'lr': 1.93625196597704e-05, 'samples': 25216896, 'steps': 131337, 'loss/train': 1.260357141494751} 08/31/2021 13:00:47 - INFO - __main__ - Step 131339: {'lr': 1.9360471957130865e-05, 'samples': 25217088, 'steps': 131338, 'loss/train': 1.304681420326233} 08/31/2021 13:00:47 - INFO - __main__ - Step 131340: {'lr': 1.9358424358413924e-05, 'samples': 25217280, 'steps': 131339, 'loss/train': 0.7630854249000549} 08/31/2021 13:00:49 - INFO - __main__ - Step 131341: {'lr': 1.9356376863620516e-05, 'samples': 25217472, 'steps': 131340, 'loss/train': 0.9680873155593872} 08/31/2021 13:00:49 - INFO - __main__ - Step 131342: {'lr': 1.9354329472751593e-05, 'samples': 25217664, 'steps': 131341, 'loss/train': 0.8446415066719055} 08/31/2021 13:00:50 - INFO - __main__ - Step 131343: {'lr': 1.9352282185808036e-05, 'samples': 25217856, 'steps': 131342, 'loss/train': 1.3434873819351196} 08/31/2021 13:00:50 - INFO - __main__ - Step 131344: {'lr': 1.9350235002790762e-05, 'samples': 25218048, 'steps': 131343, 'loss/train': 0.04198303073644638} 08/31/2021 13:00:50 - INFO - __main__ - Step 131345: {'lr': 1.9348187923700772e-05, 'samples': 25218240, 'steps': 131344, 'loss/train': 0.9544201493263245} 08/31/2021 13:00:52 - INFO - __main__ - Step 131346: {'lr': 1.93461409485389e-05, 'samples': 25218432, 'steps': 131345, 'loss/train': 0.7406468987464905} 08/31/2021 13:00:52 - INFO - __main__ - Step 131347: {'lr': 1.9344094077306085e-05, 'samples': 25218624, 'steps': 131346, 'loss/train': 1.1107474565505981} 08/31/2021 13:00:53 - INFO - __main__ - Step 131348: {'lr': 1.9342047310003248e-05, 'samples': 25218816, 'steps': 131347, 'loss/train': 2.18233585357666} 08/31/2021 13:00:53 - INFO - __main__ - Step 131349: {'lr': 1.934000064663133e-05, 'samples': 25219008, 'steps': 131348, 'loss/train': 0.5487648248672485} 08/31/2021 13:00:53 - INFO - __main__ - Step 131350: {'lr': 1.9337954087191272e-05, 'samples': 25219200, 'steps': 131349, 'loss/train': 0.7036305665969849} 08/31/2021 13:00:56 - INFO - __main__ - Step 131351: {'lr': 1.9335907631683943e-05, 'samples': 25219392, 'steps': 131350, 'loss/train': 1.2562875747680664} 08/31/2021 13:00:56 - INFO - __main__ - Step 131352: {'lr': 1.9333861280110304e-05, 'samples': 25219584, 'steps': 131351, 'loss/train': 1.0704559087753296} 08/31/2021 13:00:57 - INFO - __main__ - Step 131353: {'lr': 1.9331815032471277e-05, 'samples': 25219776, 'steps': 131352, 'loss/train': 0.8410050272941589} 08/31/2021 13:00:57 - INFO - __main__ - Step 131354: {'lr': 1.932976888876778e-05, 'samples': 25219968, 'steps': 131353, 'loss/train': 0.8125171065330505} 08/31/2021 13:00:57 - INFO - __main__ - Step 131355: {'lr': 1.932772284900072e-05, 'samples': 25220160, 'steps': 131354, 'loss/train': 1.1985892057418823} 08/31/2021 13:00:58 - INFO - __main__ - Step 131356: {'lr': 1.9325676913171053e-05, 'samples': 25220352, 'steps': 131355, 'loss/train': 0.028204578906297684} 08/31/2021 13:00:59 - INFO - __main__ - Step 131357: {'lr': 1.932363108127966e-05, 'samples': 25220544, 'steps': 131356, 'loss/train': 1.1443387269973755} 08/31/2021 13:01:00 - INFO - __main__ - Step 131358: {'lr': 1.9321585353327482e-05, 'samples': 25220736, 'steps': 131357, 'loss/train': 0.9765328168869019} 08/31/2021 13:01:00 - INFO - __main__ - Step 131359: {'lr': 1.9319539729315412e-05, 'samples': 25220928, 'steps': 131358, 'loss/train': 0.7953677773475647} 08/31/2021 13:01:00 - INFO - __main__ - Step 131360: {'lr': 1.931749420924442e-05, 'samples': 25221120, 'steps': 131359, 'loss/train': 0.857541024684906} 08/31/2021 13:01:01 - INFO - __main__ - Step 131361: {'lr': 1.9315448793115393e-05, 'samples': 25221312, 'steps': 131360, 'loss/train': 1.1110862493515015} 08/31/2021 13:01:02 - INFO - __main__ - Step 131362: {'lr': 1.9313403480929277e-05, 'samples': 25221504, 'steps': 131361, 'loss/train': 1.0926216840744019} 08/31/2021 13:01:02 - INFO - __main__ - Step 131363: {'lr': 1.9311358272686985e-05, 'samples': 25221696, 'steps': 131362, 'loss/train': 0.3616166412830353} 08/31/2021 13:01:03 - INFO - __main__ - Step 131364: {'lr': 1.930931316838941e-05, 'samples': 25221888, 'steps': 131363, 'loss/train': 0.9076149463653564} 08/31/2021 13:01:03 - INFO - __main__ - Step 131365: {'lr': 1.9307268168037516e-05, 'samples': 25222080, 'steps': 131364, 'loss/train': 1.2186788320541382} 08/31/2021 13:01:03 - INFO - __main__ - Step 131366: {'lr': 1.93052232716322e-05, 'samples': 25222272, 'steps': 131365, 'loss/train': 0.7274965643882751} 08/31/2021 13:01:05 - INFO - __main__ - Step 131367: {'lr': 1.9303178479174455e-05, 'samples': 25222464, 'steps': 131366, 'loss/train': 1.345460057258606} 08/31/2021 13:01:06 - INFO - __main__ - Step 131368: {'lr': 1.930113379066506e-05, 'samples': 25222656, 'steps': 131367, 'loss/train': 1.3180925846099854} 08/31/2021 13:01:06 - INFO - __main__ - Step 131369: {'lr': 1.929908920610504e-05, 'samples': 25222848, 'steps': 131368, 'loss/train': 0.8113399744033813} 08/31/2021 13:01:06 - INFO - __main__ - Step 131370: {'lr': 1.929704472549529e-05, 'samples': 25223040, 'steps': 131369, 'loss/train': 0.026739176362752914} 08/31/2021 13:01:07 - INFO - __main__ - Step 131371: {'lr': 1.9295000348836717e-05, 'samples': 25223232, 'steps': 131370, 'loss/train': 1.4307239055633545} 08/31/2021 13:01:08 - INFO - __main__ - Step 131372: {'lr': 1.929295607613027e-05, 'samples': 25223424, 'steps': 131371, 'loss/train': 0.4099525511264801} 08/31/2021 13:01:09 - INFO - __main__ - Step 131373: {'lr': 1.9290911907376864e-05, 'samples': 25223616, 'steps': 131372, 'loss/train': 1.108115553855896} 08/31/2021 13:01:09 - INFO - __main__ - Step 131374: {'lr': 1.9288867842577385e-05, 'samples': 25223808, 'steps': 131373, 'loss/train': 1.2182633876800537} 08/31/2021 13:01:09 - INFO - __main__ - Step 131375: {'lr': 1.9286823881732807e-05, 'samples': 25224000, 'steps': 131374, 'loss/train': 1.2049956321716309} 08/31/2021 13:01:10 - INFO - __main__ - Step 131376: {'lr': 1.928478002484402e-05, 'samples': 25224192, 'steps': 131375, 'loss/train': 0.4687861204147339} 08/31/2021 13:01:12 - INFO - __main__ - Step 131377: {'lr': 1.928273627191193e-05, 'samples': 25224384, 'steps': 131376, 'loss/train': 0.8567109107971191} 08/31/2021 13:01:12 - INFO - __main__ - Step 131378: {'lr': 1.928069262293755e-05, 'samples': 25224576, 'steps': 131377, 'loss/train': 1.030451774597168} 08/31/2021 13:01:13 - INFO - __main__ - Step 131379: {'lr': 1.9278649077921677e-05, 'samples': 25224768, 'steps': 131378, 'loss/train': 1.1162306070327759} 08/31/2021 13:01:13 - INFO - __main__ - Step 131380: {'lr': 1.9276605636865284e-05, 'samples': 25224960, 'steps': 131379, 'loss/train': 0.014418056234717369} 08/31/2021 13:01:13 - INFO - __main__ - Step 131381: {'lr': 1.927456229976929e-05, 'samples': 25225152, 'steps': 131380, 'loss/train': 0.01439997274428606} 08/31/2021 13:01:14 - INFO - __main__ - Step 131382: {'lr': 1.927251906663463e-05, 'samples': 25225344, 'steps': 131381, 'loss/train': 1.1741567850112915} 08/31/2021 13:01:15 - INFO - __main__ - Step 131383: {'lr': 1.92704759374622e-05, 'samples': 25225536, 'steps': 131382, 'loss/train': 0.816978394985199} 08/31/2021 13:01:16 - INFO - __main__ - Step 131384: {'lr': 1.9268432912252913e-05, 'samples': 25225728, 'steps': 131383, 'loss/train': 1.8672860860824585} 08/31/2021 13:01:16 - INFO - __main__ - Step 131385: {'lr': 1.9266389991007744e-05, 'samples': 25225920, 'steps': 131384, 'loss/train': 1.320701241493225} 08/31/2021 13:01:17 - INFO - __main__ - Step 131386: {'lr': 1.9264347173727575e-05, 'samples': 25226112, 'steps': 131385, 'loss/train': 1.3062803745269775} 08/31/2021 13:01:17 - INFO - __main__ - Step 131387: {'lr': 1.9262304460413328e-05, 'samples': 25226304, 'steps': 131386, 'loss/train': 1.29225754737854} 08/31/2021 13:01:17 - INFO - __main__ - Step 131388: {'lr': 1.9260261851065914e-05, 'samples': 25226496, 'steps': 131387, 'loss/train': 1.6062870025634766} 08/31/2021 13:01:19 - INFO - __main__ - Step 131389: {'lr': 1.9258219345686306e-05, 'samples': 25226688, 'steps': 131388, 'loss/train': 0.8816962242126465} 08/31/2021 13:01:19 - INFO - __main__ - Step 131390: {'lr': 1.9256176944275367e-05, 'samples': 25226880, 'steps': 131389, 'loss/train': 1.1115446090698242} 08/31/2021 13:01:20 - INFO - __main__ - Step 131391: {'lr': 1.925413464683401e-05, 'samples': 25227072, 'steps': 131390, 'loss/train': 1.484300971031189} 08/31/2021 13:01:20 - INFO - __main__ - Step 131392: {'lr': 1.925209245336318e-05, 'samples': 25227264, 'steps': 131391, 'loss/train': 1.868764877319336} 08/31/2021 13:01:20 - INFO - __main__ - Step 131393: {'lr': 1.925005036386382e-05, 'samples': 25227456, 'steps': 131392, 'loss/train': 1.5137618780136108} 08/31/2021 13:01:22 - INFO - __main__ - Step 131394: {'lr': 1.924800837833679e-05, 'samples': 25227648, 'steps': 131393, 'loss/train': 0.7880067229270935} 08/31/2021 13:01:22 - INFO - __main__ - Step 131395: {'lr': 1.924596649678309e-05, 'samples': 25227840, 'steps': 131394, 'loss/train': 1.2961167097091675} 08/31/2021 13:01:23 - INFO - __main__ - Step 131396: {'lr': 1.9243924719203552e-05, 'samples': 25228032, 'steps': 131395, 'loss/train': 1.0061383247375488} 08/31/2021 13:01:23 - INFO - __main__ - Step 131397: {'lr': 1.9241883045599178e-05, 'samples': 25228224, 'steps': 131396, 'loss/train': 0.07880664616823196} 08/31/2021 13:01:23 - INFO - __main__ - Step 131398: {'lr': 1.9239841475970826e-05, 'samples': 25228416, 'steps': 131397, 'loss/train': 0.749455451965332} 08/31/2021 13:01:25 - INFO - __main__ - Step 131399: {'lr': 1.9237800010319467e-05, 'samples': 25228608, 'steps': 131398, 'loss/train': 1.3368544578552246} 08/31/2021 13:01:25 - INFO - __main__ - Step 131400: {'lr': 1.9235758648645964e-05, 'samples': 25228800, 'steps': 131399, 'loss/train': 0.9990726709365845} 08/31/2021 13:01:25 - INFO - __main__ - Step 131401: {'lr': 1.923371739095131e-05, 'samples': 25228992, 'steps': 131400, 'loss/train': 1.2529720067977905} 08/31/2021 13:01:26 - INFO - __main__ - Step 131402: {'lr': 1.9231676237236373e-05, 'samples': 25229184, 'steps': 131401, 'loss/train': 0.775249719619751} 08/31/2021 13:01:26 - INFO - __main__ - Step 131403: {'lr': 1.9229635187502065e-05, 'samples': 25229376, 'steps': 131402, 'loss/train': 0.8219654560089111} 08/31/2021 13:01:28 - INFO - __main__ - Step 131404: {'lr': 1.92275942417493e-05, 'samples': 25229568, 'steps': 131403, 'loss/train': 1.1156878471374512} 08/31/2021 13:01:29 - INFO - __main__ - Step 131405: {'lr': 1.9225553399979057e-05, 'samples': 25229760, 'steps': 131404, 'loss/train': 1.478028416633606} 08/31/2021 13:01:29 - INFO - __main__ - Step 131406: {'lr': 1.9223512662192187e-05, 'samples': 25229952, 'steps': 131405, 'loss/train': 1.444187045097351} 08/31/2021 13:01:30 - INFO - __main__ - Step 131407: {'lr': 1.922147202838967e-05, 'samples': 25230144, 'steps': 131406, 'loss/train': 0.8565012216567993} 08/31/2021 13:01:30 - INFO - __main__ - Step 131408: {'lr': 1.921943149857236e-05, 'samples': 25230336, 'steps': 131407, 'loss/train': 0.8025078177452087} 08/31/2021 13:01:31 - INFO - __main__ - Step 131409: {'lr': 1.921739107274123e-05, 'samples': 25230528, 'steps': 131408, 'loss/train': 0.9224165678024292} 08/31/2021 13:01:32 - INFO - __main__ - Step 131410: {'lr': 1.9215350750897197e-05, 'samples': 25230720, 'steps': 131409, 'loss/train': 1.447042465209961} 08/31/2021 13:01:32 - INFO - __main__ - Step 131411: {'lr': 1.921331053304115e-05, 'samples': 25230912, 'steps': 131410, 'loss/train': 1.0059400796890259} 08/31/2021 13:01:33 - INFO - __main__ - Step 131412: {'lr': 1.9211270419174032e-05, 'samples': 25231104, 'steps': 131411, 'loss/train': 1.5076048374176025} 08/31/2021 13:01:33 - INFO - __main__ - Step 131413: {'lr': 1.9209230409296757e-05, 'samples': 25231296, 'steps': 131412, 'loss/train': 1.4175831079483032} 08/31/2021 13:01:34 - INFO - __main__ - Step 131414: {'lr': 1.9207190503410272e-05, 'samples': 25231488, 'steps': 131413, 'loss/train': 0.3060467839241028} 08/31/2021 13:01:35 - INFO - __main__ - Step 131415: {'lr': 1.9205150701515435e-05, 'samples': 25231680, 'steps': 131414, 'loss/train': 0.035549089312553406} 08/31/2021 13:01:35 - INFO - __main__ - Step 131416: {'lr': 1.9203111003613188e-05, 'samples': 25231872, 'steps': 131415, 'loss/train': 1.407283067703247} 08/31/2021 13:01:36 - INFO - __main__ - Step 131417: {'lr': 1.920107140970445e-05, 'samples': 25232064, 'steps': 131416, 'loss/train': 0.302338182926178} 08/31/2021 13:01:36 - INFO - __main__ - Step 131418: {'lr': 1.9199031919790165e-05, 'samples': 25232256, 'steps': 131417, 'loss/train': 0.784270703792572} 08/31/2021 13:01:36 - INFO - __main__ - Step 131419: {'lr': 1.919699253387122e-05, 'samples': 25232448, 'steps': 131418, 'loss/train': 1.095293402671814} 08/31/2021 13:01:38 - INFO - __main__ - Step 131420: {'lr': 1.919495325194856e-05, 'samples': 25232640, 'steps': 131419, 'loss/train': 0.9550548791885376} 08/31/2021 13:01:39 - INFO - __main__ - Step 131421: {'lr': 1.91929140740231e-05, 'samples': 25232832, 'steps': 131420, 'loss/train': 0.06802935153245926} 08/31/2021 13:01:39 - INFO - __main__ - Step 131422: {'lr': 1.9190875000095726e-05, 'samples': 25233024, 'steps': 131421, 'loss/train': 1.0011060237884521} 08/31/2021 13:01:39 - INFO - __main__ - Step 131423: {'lr': 1.918883603016741e-05, 'samples': 25233216, 'steps': 131422, 'loss/train': 0.9002324938774109} 08/31/2021 13:01:40 - INFO - __main__ - Step 131424: {'lr': 1.9186797164239017e-05, 'samples': 25233408, 'steps': 131423, 'loss/train': 1.3122313022613525} 08/31/2021 13:01:41 - INFO - __main__ - Step 131425: {'lr': 1.9184758402311514e-05, 'samples': 25233600, 'steps': 131424, 'loss/train': 0.542738676071167} 08/31/2021 13:01:42 - INFO - __main__ - Step 131426: {'lr': 1.9182719744385792e-05, 'samples': 25233792, 'steps': 131425, 'loss/train': 1.1756796836853027} 08/31/2021 13:01:42 - INFO - __main__ - Step 131427: {'lr': 1.9180681190462763e-05, 'samples': 25233984, 'steps': 131426, 'loss/train': 1.3151060342788696} 08/31/2021 13:01:42 - INFO - __main__ - Step 131428: {'lr': 1.91786427405434e-05, 'samples': 25234176, 'steps': 131427, 'loss/train': 1.191281795501709} 08/31/2021 13:01:43 - INFO - __main__ - Step 131429: {'lr': 1.917660439462854e-05, 'samples': 25234368, 'steps': 131428, 'loss/train': 1.2196485996246338} 08/31/2021 13:01:44 - INFO - __main__ - Step 131430: {'lr': 1.9174566152719147e-05, 'samples': 25234560, 'steps': 131429, 'loss/train': 1.5571438074111938} 08/31/2021 13:01:45 - INFO - __main__ - Step 131431: {'lr': 1.9172528014816114e-05, 'samples': 25234752, 'steps': 131430, 'loss/train': 1.6805018186569214} 08/31/2021 13:01:45 - INFO - __main__ - Step 131432: {'lr': 1.9170489980920415e-05, 'samples': 25234944, 'steps': 131431, 'loss/train': 1.2482548952102661} 08/31/2021 13:01:45 - INFO - __main__ - Step 131433: {'lr': 1.91684520510329e-05, 'samples': 25235136, 'steps': 131432, 'loss/train': 0.9811516404151917} 08/31/2021 13:01:46 - INFO - __main__ - Step 131434: {'lr': 1.916641422515453e-05, 'samples': 25235328, 'steps': 131433, 'loss/train': 0.9132153391838074} 08/31/2021 13:01:47 - INFO - __main__ - Step 131435: {'lr': 1.91643765032862e-05, 'samples': 25235520, 'steps': 131434, 'loss/train': 0.17886999249458313} 08/31/2021 13:01:48 - INFO - __main__ - Step 131436: {'lr': 1.9162338885428844e-05, 'samples': 25235712, 'steps': 131435, 'loss/train': 1.269834280014038} 08/31/2021 13:01:48 - INFO - __main__ - Step 131437: {'lr': 1.9160301371583392e-05, 'samples': 25235904, 'steps': 131436, 'loss/train': 1.2884948253631592} 08/31/2021 13:01:48 - INFO - __main__ - Step 131438: {'lr': 1.9158263961750744e-05, 'samples': 25236096, 'steps': 131437, 'loss/train': 0.2939697802066803} 08/31/2021 13:01:49 - INFO - __main__ - Step 131439: {'lr': 1.9156226655931807e-05, 'samples': 25236288, 'steps': 131438, 'loss/train': 0.5089491009712219} 08/31/2021 13:01:50 - INFO - __main__ - Step 131440: {'lr': 1.9154189454127503e-05, 'samples': 25236480, 'steps': 131439, 'loss/train': 1.4216402769088745} 08/31/2021 13:01:51 - INFO - __main__ - Step 131441: {'lr': 1.9152152356338824e-05, 'samples': 25236672, 'steps': 131440, 'loss/train': 0.9824399352073669} 08/31/2021 13:01:51 - INFO - __main__ - Step 131442: {'lr': 1.9150115362566557e-05, 'samples': 25236864, 'steps': 131441, 'loss/train': 1.0272762775421143} 08/31/2021 13:01:51 - INFO - __main__ - Step 131443: {'lr': 1.914807847281172e-05, 'samples': 25237056, 'steps': 131442, 'loss/train': 1.339723825454712} 08/31/2021 13:01:52 - INFO - __main__ - Step 131444: {'lr': 1.9146041687075178e-05, 'samples': 25237248, 'steps': 131443, 'loss/train': 1.2965408563613892} 08/31/2021 13:01:53 - INFO - __main__ - Step 131445: {'lr': 1.9144005005357845e-05, 'samples': 25237440, 'steps': 131444, 'loss/train': 1.5547974109649658} 08/31/2021 13:01:54 - INFO - __main__ - Step 131446: {'lr': 1.9141968427660694e-05, 'samples': 25237632, 'steps': 131445, 'loss/train': 0.4965728521347046} 08/31/2021 13:01:54 - INFO - __main__ - Step 131447: {'lr': 1.9139931953984587e-05, 'samples': 25237824, 'steps': 131446, 'loss/train': 1.7228446006774902} 08/31/2021 13:01:54 - INFO - __main__ - Step 131448: {'lr': 1.9137895584330488e-05, 'samples': 25238016, 'steps': 131447, 'loss/train': 0.9824356436729431} 08/31/2021 13:01:55 - INFO - __main__ - Step 131449: {'lr': 1.9135859318699266e-05, 'samples': 25238208, 'steps': 131448, 'loss/train': 1.361454963684082} 08/31/2021 13:01:55 - INFO - __main__ - Step 131450: {'lr': 1.913382315709189e-05, 'samples': 25238400, 'steps': 131449, 'loss/train': 1.146398901939392} 08/31/2021 13:01:56 - INFO - __main__ - Step 131451: {'lr': 1.9131787099509217e-05, 'samples': 25238592, 'steps': 131450, 'loss/train': 1.326545000076294} 08/31/2021 13:01:57 - INFO - __main__ - Step 131452: {'lr': 1.9129751145952224e-05, 'samples': 25238784, 'steps': 131451, 'loss/train': 1.1271824836730957} 08/31/2021 13:01:57 - INFO - __main__ - Step 131453: {'lr': 1.9127715296421793e-05, 'samples': 25238976, 'steps': 131452, 'loss/train': 1.0077625513076782} 08/31/2021 13:01:58 - INFO - __main__ - Step 131454: {'lr': 1.91256795509189e-05, 'samples': 25239168, 'steps': 131453, 'loss/train': 0.9024725556373596} 08/31/2021 13:01:58 - INFO - __main__ - Step 131455: {'lr': 1.9123643909444376e-05, 'samples': 25239360, 'steps': 131454, 'loss/train': 1.2546401023864746} 08/31/2021 13:02:00 - INFO - __main__ - Step 131456: {'lr': 1.9121608371999166e-05, 'samples': 25239552, 'steps': 131455, 'loss/train': 1.2282414436340332} 08/31/2021 13:02:00 - INFO - __main__ - Step 131457: {'lr': 1.9119572938584184e-05, 'samples': 25239744, 'steps': 131456, 'loss/train': 0.5301862359046936} 08/31/2021 13:02:00 - INFO - __main__ - Step 131458: {'lr': 1.9117537609200376e-05, 'samples': 25239936, 'steps': 131457, 'loss/train': 1.3871561288833618} 08/31/2021 13:02:01 - INFO - __main__ - Step 131459: {'lr': 1.9115502383848653e-05, 'samples': 25240128, 'steps': 131458, 'loss/train': 0.7109888792037964} 08/31/2021 13:02:01 - INFO - __main__ - Step 131460: {'lr': 1.911346726252991e-05, 'samples': 25240320, 'steps': 131459, 'loss/train': 0.7068521976470947} 08/31/2021 13:02:03 - INFO - __main__ - Step 131461: {'lr': 1.911143224524506e-05, 'samples': 25240512, 'steps': 131460, 'loss/train': 1.5487148761749268} 08/31/2021 13:02:04 - INFO - __main__ - Step 131462: {'lr': 1.9109397331995044e-05, 'samples': 25240704, 'steps': 131461, 'loss/train': 1.093898057937622} 08/31/2021 13:02:04 - INFO - __main__ - Step 131463: {'lr': 1.910736252278078e-05, 'samples': 25240896, 'steps': 131462, 'loss/train': 1.313724398612976} 08/31/2021 13:02:04 - INFO - __main__ - Step 131464: {'lr': 1.9105327817603186e-05, 'samples': 25241088, 'steps': 131463, 'loss/train': 0.5239164233207703} 08/31/2021 13:02:05 - INFO - __main__ - Step 131465: {'lr': 1.9103293216463147e-05, 'samples': 25241280, 'steps': 131464, 'loss/train': 0.5046544075012207} 08/31/2021 13:02:06 - INFO - __main__ - Step 131466: {'lr': 1.9101258719361607e-05, 'samples': 25241472, 'steps': 131465, 'loss/train': 1.4738126993179321} 08/31/2021 13:02:07 - INFO - __main__ - Step 131467: {'lr': 1.9099224326299484e-05, 'samples': 25241664, 'steps': 131466, 'loss/train': 0.6424815654754639} 08/31/2021 13:02:07 - INFO - __main__ - Step 131468: {'lr': 1.9097190037277724e-05, 'samples': 25241856, 'steps': 131467, 'loss/train': 1.206281304359436} 08/31/2021 13:02:07 - INFO - __main__ - Step 131469: {'lr': 1.9095155852297152e-05, 'samples': 25242048, 'steps': 131468, 'loss/train': 1.1715060472488403} 08/31/2021 13:02:08 - INFO - __main__ - Step 131470: {'lr': 1.9093121771358772e-05, 'samples': 25242240, 'steps': 131469, 'loss/train': 1.1346626281738281} 08/31/2021 13:02:08 - INFO - __main__ - Step 131471: {'lr': 1.9091087794463445e-05, 'samples': 25242432, 'steps': 131470, 'loss/train': 0.9957359433174133} 08/31/2021 13:02:10 - INFO - __main__ - Step 131472: {'lr': 1.9089053921612116e-05, 'samples': 25242624, 'steps': 131471, 'loss/train': 0.6758021712303162} 08/31/2021 13:02:10 - INFO - __main__ - Step 131473: {'lr': 1.9087020152805696e-05, 'samples': 25242816, 'steps': 131472, 'loss/train': 0.8677831888198853} 08/31/2021 13:02:10 - INFO - __main__ - Step 131474: {'lr': 1.9084986488045103e-05, 'samples': 25243008, 'steps': 131473, 'loss/train': 1.2250317335128784} 08/31/2021 13:02:11 - INFO - __main__ - Step 131475: {'lr': 1.9082952927331226e-05, 'samples': 25243200, 'steps': 131474, 'loss/train': 1.2594821453094482} 08/31/2021 13:02:11 - INFO - __main__ - Step 131476: {'lr': 1.9080919470665035e-05, 'samples': 25243392, 'steps': 131475, 'loss/train': 1.0713942050933838} 08/31/2021 13:02:13 - INFO - __main__ - Step 131477: {'lr': 1.9078886118047424e-05, 'samples': 25243584, 'steps': 131476, 'loss/train': 1.074426293373108} 08/31/2021 13:02:13 - INFO - __main__ - Step 131478: {'lr': 1.90768528694793e-05, 'samples': 25243776, 'steps': 131477, 'loss/train': 0.21918080747127533} 08/31/2021 13:02:13 - INFO - __main__ - Step 131479: {'lr': 1.9074819724961555e-05, 'samples': 25243968, 'steps': 131478, 'loss/train': 1.0483150482177734} 08/31/2021 13:02:14 - INFO - __main__ - Step 131480: {'lr': 1.9072786684495165e-05, 'samples': 25244160, 'steps': 131479, 'loss/train': 0.1133427619934082} 08/31/2021 13:02:14 - INFO - __main__ - Step 131481: {'lr': 1.907075374808104e-05, 'samples': 25244352, 'steps': 131480, 'loss/train': 0.7100790739059448} 08/31/2021 13:02:16 - INFO - __main__ - Step 131482: {'lr': 1.906872091572004e-05, 'samples': 25244544, 'steps': 131481, 'loss/train': 1.203416347503662} 08/31/2021 13:02:16 - INFO - __main__ - Step 131483: {'lr': 1.9066688187413113e-05, 'samples': 25244736, 'steps': 131482, 'loss/train': 0.6446158289909363} 08/31/2021 13:02:16 - INFO - __main__ - Step 131484: {'lr': 1.9064655563161142e-05, 'samples': 25244928, 'steps': 131483, 'loss/train': 2.1110968589782715} 08/31/2021 13:02:17 - INFO - __main__ - Step 131485: {'lr': 1.9062623042965105e-05, 'samples': 25245120, 'steps': 131484, 'loss/train': 0.971061646938324} 08/31/2021 13:02:17 - INFO - __main__ - Step 131486: {'lr': 1.9060590626825887e-05, 'samples': 25245312, 'steps': 131485, 'loss/train': 0.8739195466041565} 08/31/2021 13:02:19 - INFO - __main__ - Step 131487: {'lr': 1.9058558314744374e-05, 'samples': 25245504, 'steps': 131486, 'loss/train': 0.7072663307189941} 08/31/2021 13:02:19 - INFO - __main__ - Step 131488: {'lr': 1.9056526106721537e-05, 'samples': 25245696, 'steps': 131487, 'loss/train': 1.2761892080307007} 08/31/2021 13:02:19 - INFO - __main__ - Step 131489: {'lr': 1.9054494002758243e-05, 'samples': 25245888, 'steps': 131488, 'loss/train': 0.9847620129585266} 08/31/2021 13:02:20 - INFO - __main__ - Step 131490: {'lr': 1.9052462002855457e-05, 'samples': 25246080, 'steps': 131489, 'loss/train': 0.8828835487365723} 08/31/2021 13:02:20 - INFO - __main__ - Step 131491: {'lr': 1.9050430107014073e-05, 'samples': 25246272, 'steps': 131490, 'loss/train': 1.0590747594833374} 08/31/2021 13:02:22 - INFO - __main__ - Step 131492: {'lr': 1.9048398315234973e-05, 'samples': 25246464, 'steps': 131491, 'loss/train': 1.2799712419509888} 08/31/2021 13:02:22 - INFO - __main__ - Step 131493: {'lr': 1.9046366627519102e-05, 'samples': 25246656, 'steps': 131492, 'loss/train': 1.4774481058120728} 08/31/2021 13:02:23 - INFO - __main__ - Step 131494: {'lr': 1.9044335043867405e-05, 'samples': 25246848, 'steps': 131493, 'loss/train': 1.034644603729248} 08/31/2021 13:02:23 - INFO - __main__ - Step 131495: {'lr': 1.9042303564280773e-05, 'samples': 25247040, 'steps': 131494, 'loss/train': 0.31312912702560425} 08/31/2021 13:02:23 - INFO - __main__ - Step 131496: {'lr': 1.9040272188760088e-05, 'samples': 25247232, 'steps': 131495, 'loss/train': 0.5666816234588623} 08/31/2021 13:02:24 - INFO - __main__ - Step 131497: {'lr': 1.90382409173063e-05, 'samples': 25247424, 'steps': 131496, 'loss/train': 1.3275477886199951} 08/31/2021 13:02:25 - INFO - __main__ - Step 131498: {'lr': 1.903620974992032e-05, 'samples': 25247616, 'steps': 131497, 'loss/train': 1.148062825202942} 08/31/2021 13:02:26 - INFO - __main__ - Step 131499: {'lr': 1.9034178686603038e-05, 'samples': 25247808, 'steps': 131498, 'loss/train': 1.171595811843872} 08/31/2021 13:02:26 - INFO - __main__ - Step 131500: {'lr': 1.9032147727355397e-05, 'samples': 25248000, 'steps': 131499, 'loss/train': 1.1153804063796997} 08/31/2021 13:02:26 - INFO - __main__ - Step 131501: {'lr': 1.9030116872178316e-05, 'samples': 25248192, 'steps': 131500, 'loss/train': 1.872138261795044} 08/31/2021 13:02:27 - INFO - __main__ - Step 131502: {'lr': 1.9028086121072708e-05, 'samples': 25248384, 'steps': 131501, 'loss/train': 1.5848087072372437} 08/31/2021 13:02:29 - INFO - __main__ - Step 131503: {'lr': 1.9026055474039462e-05, 'samples': 25248576, 'steps': 131502, 'loss/train': 0.6094589829444885} 08/31/2021 13:02:29 - INFO - __main__ - Step 131504: {'lr': 1.902402493107952e-05, 'samples': 25248768, 'steps': 131503, 'loss/train': 1.2069737911224365} 08/31/2021 13:02:29 - INFO - __main__ - Step 131505: {'lr': 1.902199449219377e-05, 'samples': 25248960, 'steps': 131504, 'loss/train': 0.17757387459278107} 08/31/2021 13:02:30 - INFO - __main__ - Step 131506: {'lr': 1.901996415738319e-05, 'samples': 25249152, 'steps': 131505, 'loss/train': 0.8029006123542786} 08/31/2021 13:02:30 - INFO - __main__ - Step 131507: {'lr': 1.9017933926648606e-05, 'samples': 25249344, 'steps': 131506, 'loss/train': 1.0351245403289795} 08/31/2021 13:02:32 - INFO - __main__ - Step 131508: {'lr': 1.9015903799991048e-05, 'samples': 25249536, 'steps': 131507, 'loss/train': 1.1240767240524292} 08/31/2021 13:02:32 - INFO - __main__ - Step 131509: {'lr': 1.9013873777411288e-05, 'samples': 25249728, 'steps': 131508, 'loss/train': 1.0204904079437256} 08/31/2021 13:02:32 - INFO - __main__ - Step 131510: {'lr': 1.9011843858910332e-05, 'samples': 25249920, 'steps': 131509, 'loss/train': 0.7764908075332642} 08/31/2021 13:02:33 - INFO - __main__ - Step 131511: {'lr': 1.9009814044489064e-05, 'samples': 25250112, 'steps': 131510, 'loss/train': 0.7654092311859131} 08/31/2021 13:02:33 - INFO - __main__ - Step 131512: {'lr': 1.900778433414843e-05, 'samples': 25250304, 'steps': 131511, 'loss/train': 1.4800602197647095} 08/31/2021 13:02:36 - INFO - __main__ - Step 131513: {'lr': 1.900575472788929e-05, 'samples': 25250496, 'steps': 131512, 'loss/train': 1.0107862949371338} 08/31/2021 13:02:36 - INFO - __main__ - Step 131514: {'lr': 1.9003725225712614e-05, 'samples': 25250688, 'steps': 131513, 'loss/train': 0.34577611088752747} 08/31/2021 13:02:36 - INFO - __main__ - Step 131515: {'lr': 1.9001695827619292e-05, 'samples': 25250880, 'steps': 131514, 'loss/train': 0.46163299679756165} 08/31/2021 13:02:37 - INFO - __main__ - Step 131516: {'lr': 1.8999666533610266e-05, 'samples': 25251072, 'steps': 131515, 'loss/train': 0.9148538708686829} 08/31/2021 13:02:37 - INFO - __main__ - Step 131517: {'lr': 1.8997637343686397e-05, 'samples': 25251264, 'steps': 131516, 'loss/train': 0.3702308237552643} 08/31/2021 13:02:37 - INFO - __main__ - Step 131518: {'lr': 1.899560825784863e-05, 'samples': 25251456, 'steps': 131517, 'loss/train': 0.9469389319419861} 08/31/2021 13:02:39 - INFO - __main__ - Step 131519: {'lr': 1.8993579276097877e-05, 'samples': 25251648, 'steps': 131518, 'loss/train': 1.1917145252227783} 08/31/2021 13:02:40 - INFO - __main__ - Step 131520: {'lr': 1.899155039843506e-05, 'samples': 25251840, 'steps': 131519, 'loss/train': 0.8308886885643005} 08/31/2021 13:02:40 - INFO - __main__ - Step 131521: {'lr': 1.898952162486109e-05, 'samples': 25252032, 'steps': 131520, 'loss/train': 0.852427065372467} 08/31/2021 13:02:41 - INFO - __main__ - Step 131522: {'lr': 1.898749295537691e-05, 'samples': 25252224, 'steps': 131521, 'loss/train': 0.5713297724723816} 08/31/2021 13:02:41 - INFO - __main__ - Step 131523: {'lr': 1.898546438998336e-05, 'samples': 25252416, 'steps': 131522, 'loss/train': 0.32903924584388733} 08/31/2021 13:02:42 - INFO - __main__ - Step 131524: {'lr': 1.8983435928681375e-05, 'samples': 25252608, 'steps': 131523, 'loss/train': 1.3474252223968506} 08/31/2021 13:02:43 - INFO - __main__ - Step 131525: {'lr': 1.8981407571471903e-05, 'samples': 25252800, 'steps': 131524, 'loss/train': 1.0433751344680786} 08/31/2021 13:02:43 - INFO - __main__ - Step 131526: {'lr': 1.8979379318355862e-05, 'samples': 25252992, 'steps': 131525, 'loss/train': 0.14977586269378662} 08/31/2021 13:02:44 - INFO - __main__ - Step 131527: {'lr': 1.8977351169334132e-05, 'samples': 25253184, 'steps': 131526, 'loss/train': 1.2161545753479004} 08/31/2021 13:02:44 - INFO - __main__ - Step 131528: {'lr': 1.897532312440764e-05, 'samples': 25253376, 'steps': 131527, 'loss/train': 1.8970867395401} 08/31/2021 13:02:44 - INFO - __main__ - Step 131529: {'lr': 1.897329518357732e-05, 'samples': 25253568, 'steps': 131528, 'loss/train': 0.8475462198257446} 08/31/2021 13:02:46 - INFO - __main__ - Step 131530: {'lr': 1.8971267346844067e-05, 'samples': 25253760, 'steps': 131529, 'loss/train': 0.3972298502922058} 08/31/2021 13:02:46 - INFO - __main__ - Step 131531: {'lr': 1.8969239614208765e-05, 'samples': 25253952, 'steps': 131530, 'loss/train': 0.6781216263771057} 08/31/2021 13:02:47 - INFO - __main__ - Step 131532: {'lr': 1.896721198567239e-05, 'samples': 25254144, 'steps': 131531, 'loss/train': 0.3866705298423767} 08/31/2021 13:02:47 - INFO - __main__ - Step 131533: {'lr': 1.8965184461235825e-05, 'samples': 25254336, 'steps': 131532, 'loss/train': 1.2263758182525635} 08/31/2021 13:02:48 - INFO - __main__ - Step 131534: {'lr': 1.896315704089996e-05, 'samples': 25254528, 'steps': 131533, 'loss/train': 0.9753411412239075} 08/31/2021 13:02:48 - INFO - __main__ - Step 131535: {'lr': 1.8961129724665794e-05, 'samples': 25254720, 'steps': 131534, 'loss/train': 0.017487213015556335} 08/31/2021 13:02:50 - INFO - __main__ - Step 131536: {'lr': 1.8959102512534105e-05, 'samples': 25254912, 'steps': 131535, 'loss/train': 1.0066906213760376} 08/31/2021 13:02:50 - INFO - __main__ - Step 131537: {'lr': 1.895707540450592e-05, 'samples': 25255104, 'steps': 131536, 'loss/train': 0.946069598197937} 08/31/2021 13:02:50 - INFO - __main__ - Step 131538: {'lr': 1.895504840058207e-05, 'samples': 25255296, 'steps': 131537, 'loss/train': 0.8744807839393616} 08/31/2021 13:02:51 - INFO - __main__ - Step 131539: {'lr': 1.8953021500763558e-05, 'samples': 25255488, 'steps': 131538, 'loss/train': 1.3692265748977661} 08/31/2021 13:02:51 - INFO - __main__ - Step 131540: {'lr': 1.895099470505121e-05, 'samples': 25255680, 'steps': 131539, 'loss/train': 1.1088149547576904} 08/31/2021 13:02:53 - INFO - __main__ - Step 131541: {'lr': 1.8948968013446004e-05, 'samples': 25255872, 'steps': 131540, 'loss/train': 0.2403874546289444} 08/31/2021 13:02:53 - INFO - __main__ - Step 131542: {'lr': 1.89469414259488e-05, 'samples': 25256064, 'steps': 131541, 'loss/train': 1.339847445487976} 08/31/2021 13:02:54 - INFO - __main__ - Step 131543: {'lr': 1.8944914942560565e-05, 'samples': 25256256, 'steps': 131542, 'loss/train': 1.9600017070770264} 08/31/2021 13:02:54 - INFO - __main__ - Step 131544: {'lr': 1.8942888563282163e-05, 'samples': 25256448, 'steps': 131543, 'loss/train': 0.149077907204628} 08/31/2021 13:02:54 - INFO - __main__ - Step 131545: {'lr': 1.8940862288114536e-05, 'samples': 25256640, 'steps': 131544, 'loss/train': 1.2331202030181885} 08/31/2021 13:02:55 - INFO - __main__ - Step 131546: {'lr': 1.89388361170586e-05, 'samples': 25256832, 'steps': 131545, 'loss/train': 1.3268064260482788} 08/31/2021 13:02:56 - INFO - __main__ - Step 131547: {'lr': 1.8936810050115272e-05, 'samples': 25257024, 'steps': 131546, 'loss/train': 1.1912111043930054} 08/31/2021 13:02:57 - INFO - __main__ - Step 131548: {'lr': 1.893478408728544e-05, 'samples': 25257216, 'steps': 131547, 'loss/train': 0.8632481694221497} 08/31/2021 13:02:57 - INFO - __main__ - Step 131549: {'lr': 1.8932758228570046e-05, 'samples': 25257408, 'steps': 131548, 'loss/train': 0.9506227374076843} 08/31/2021 13:02:57 - INFO - __main__ - Step 131550: {'lr': 1.893073247396998e-05, 'samples': 25257600, 'steps': 131549, 'loss/train': 0.32960498332977295} 08/31/2021 13:02:58 - INFO - __main__ - Step 131551: {'lr': 1.892870682348613e-05, 'samples': 25257792, 'steps': 131550, 'loss/train': 0.6276203393936157} 08/31/2021 13:02:59 - INFO - __main__ - Step 131552: {'lr': 1.8926681277119467e-05, 'samples': 25257984, 'steps': 131551, 'loss/train': 0.9465570449829102} 08/31/2021 13:03:00 - INFO - __main__ - Step 131553: {'lr': 1.892465583487085e-05, 'samples': 25258176, 'steps': 131552, 'loss/train': 1.2721741199493408} 08/31/2021 13:03:00 - INFO - __main__ - Step 131554: {'lr': 1.8922630496741228e-05, 'samples': 25258368, 'steps': 131553, 'loss/train': 1.104870319366455} 08/31/2021 13:03:00 - INFO - __main__ - Step 131555: {'lr': 1.892060526273151e-05, 'samples': 25258560, 'steps': 131554, 'loss/train': 1.5936329364776611} 08/31/2021 13:03:01 - INFO - __main__ - Step 131556: {'lr': 1.891858013284259e-05, 'samples': 25258752, 'steps': 131555, 'loss/train': 1.1538864374160767} 08/31/2021 13:03:03 - INFO - __main__ - Step 131557: {'lr': 1.8916555107075405e-05, 'samples': 25258944, 'steps': 131556, 'loss/train': 0.7421497702598572} 08/31/2021 13:03:03 - INFO - __main__ - Step 131558: {'lr': 1.891453018543085e-05, 'samples': 25259136, 'steps': 131557, 'loss/train': 0.8892826437950134} 08/31/2021 13:03:03 - INFO - __main__ - Step 131559: {'lr': 1.8912505367909837e-05, 'samples': 25259328, 'steps': 131558, 'loss/train': 0.3439786732196808} 08/31/2021 13:03:04 - INFO - __main__ - Step 131560: {'lr': 1.8910480654513285e-05, 'samples': 25259520, 'steps': 131559, 'loss/train': 0.7167330980300903} 08/31/2021 13:03:04 - INFO - __main__ - Step 131561: {'lr': 1.8908456045242107e-05, 'samples': 25259712, 'steps': 131560, 'loss/train': 1.0801771879196167} 08/31/2021 13:03:06 - INFO - __main__ - Step 131562: {'lr': 1.8906431540097247e-05, 'samples': 25259904, 'steps': 131561, 'loss/train': 0.7216428518295288} 08/31/2021 13:03:06 - INFO - __main__ - Step 131563: {'lr': 1.8904407139079565e-05, 'samples': 25260096, 'steps': 131562, 'loss/train': 0.6042594313621521} 08/31/2021 13:03:07 - INFO - __main__ - Step 131564: {'lr': 1.890238284218998e-05, 'samples': 25260288, 'steps': 131563, 'loss/train': 0.8407897353172302} 08/31/2021 13:03:07 - INFO - __main__ - Step 131565: {'lr': 1.8900358649429405e-05, 'samples': 25260480, 'steps': 131564, 'loss/train': 0.8008368611335754} 08/31/2021 13:03:07 - INFO - __main__ - Step 131566: {'lr': 1.8898334560798757e-05, 'samples': 25260672, 'steps': 131565, 'loss/train': 0.8809247016906738} 08/31/2021 13:03:09 - INFO - __main__ - Step 131567: {'lr': 1.8896310576298952e-05, 'samples': 25260864, 'steps': 131566, 'loss/train': 0.7596621513366699} 08/31/2021 13:03:10 - INFO - __main__ - Step 131568: {'lr': 1.8894286695930934e-05, 'samples': 25261056, 'steps': 131567, 'loss/train': 1.2426811456680298} 08/31/2021 13:03:10 - INFO - __main__ - Step 131569: {'lr': 1.889226291969556e-05, 'samples': 25261248, 'steps': 131568, 'loss/train': 1.1381150484085083} 08/31/2021 13:03:10 - INFO - __main__ - Step 131570: {'lr': 1.8890239247593755e-05, 'samples': 25261440, 'steps': 131569, 'loss/train': 1.101392388343811} 08/31/2021 13:03:11 - INFO - __main__ - Step 131571: {'lr': 1.8888215679626454e-05, 'samples': 25261632, 'steps': 131570, 'loss/train': 0.8995649814605713} 08/31/2021 13:03:12 - INFO - __main__ - Step 131572: {'lr': 1.8886192215794573e-05, 'samples': 25261824, 'steps': 131571, 'loss/train': 1.1079918146133423} 08/31/2021 13:03:13 - INFO - __main__ - Step 131573: {'lr': 1.8884168856098975e-05, 'samples': 25262016, 'steps': 131572, 'loss/train': 0.8051966428756714} 08/31/2021 13:03:13 - INFO - __main__ - Step 131574: {'lr': 1.8882145600540633e-05, 'samples': 25262208, 'steps': 131573, 'loss/train': 0.8841822147369385} 08/31/2021 13:03:14 - INFO - __main__ - Step 131575: {'lr': 1.8880122449120463e-05, 'samples': 25262400, 'steps': 131574, 'loss/train': 0.8203006982803345} 08/31/2021 13:03:14 - INFO - __main__ - Step 131576: {'lr': 1.8878099401839293e-05, 'samples': 25262592, 'steps': 131575, 'loss/train': 1.1136817932128906} 08/31/2021 13:03:14 - INFO - __main__ - Step 131577: {'lr': 1.88760764586981e-05, 'samples': 25262784, 'steps': 131576, 'loss/train': 1.2815639972686768} 08/31/2021 13:03:16 - INFO - __main__ - Step 131578: {'lr': 1.887405361969777e-05, 'samples': 25262976, 'steps': 131577, 'loss/train': 0.7100486755371094} 08/31/2021 13:03:16 - INFO - __main__ - Step 131579: {'lr': 1.8872030884839243e-05, 'samples': 25263168, 'steps': 131578, 'loss/train': 1.091153621673584} 08/31/2021 13:03:16 - INFO - __main__ - Step 131580: {'lr': 1.887000825412338e-05, 'samples': 25263360, 'steps': 131579, 'loss/train': 0.8713892698287964} 08/31/2021 13:03:17 - INFO - __main__ - Step 131581: {'lr': 1.8867985727551163e-05, 'samples': 25263552, 'steps': 131580, 'loss/train': 0.9360098838806152} 08/31/2021 13:03:17 - INFO - __main__ - Step 131582: {'lr': 1.886596330512344e-05, 'samples': 25263744, 'steps': 131581, 'loss/train': 1.0433664321899414} 08/31/2021 13:03:19 - INFO - __main__ - Step 131583: {'lr': 1.8863940986841133e-05, 'samples': 25263936, 'steps': 131582, 'loss/train': 0.8927053213119507} 08/31/2021 13:03:20 - INFO - __main__ - Step 131584: {'lr': 1.8861918772705182e-05, 'samples': 25264128, 'steps': 131583, 'loss/train': 0.06903412193059921} 08/31/2021 13:03:20 - INFO - __main__ - Step 131585: {'lr': 1.885989666271651e-05, 'samples': 25264320, 'steps': 131584, 'loss/train': 0.9663461446762085} 08/31/2021 13:03:20 - INFO - __main__ - Step 131586: {'lr': 1.885787465687597e-05, 'samples': 25264512, 'steps': 131585, 'loss/train': 1.3599786758422852} 08/31/2021 13:03:21 - INFO - __main__ - Step 131587: {'lr': 1.8855852755184505e-05, 'samples': 25264704, 'steps': 131586, 'loss/train': 1.2224762439727783} 08/31/2021 13:03:22 - INFO - __main__ - Step 131588: {'lr': 1.8853830957643037e-05, 'samples': 25264896, 'steps': 131587, 'loss/train': 0.7595423460006714} 08/31/2021 13:03:23 - INFO - __main__ - Step 131589: {'lr': 1.8851809264252507e-05, 'samples': 25265088, 'steps': 131588, 'loss/train': 1.0258293151855469} 08/31/2021 13:03:23 - INFO - __main__ - Step 131590: {'lr': 1.8849787675013747e-05, 'samples': 25265280, 'steps': 131589, 'loss/train': 1.2092690467834473} 08/31/2021 13:03:23 - INFO - __main__ - Step 131591: {'lr': 1.88477661899277e-05, 'samples': 25265472, 'steps': 131590, 'loss/train': 1.079766035079956} 08/31/2021 13:03:24 - INFO - __main__ - Step 131592: {'lr': 1.8845744808995285e-05, 'samples': 25265664, 'steps': 131591, 'loss/train': 0.7859076857566833} 08/31/2021 13:03:25 - INFO - __main__ - Step 131593: {'lr': 1.8843723532217415e-05, 'samples': 25265856, 'steps': 131592, 'loss/train': 0.9720360040664673} 08/31/2021 13:03:26 - INFO - __main__ - Step 131594: {'lr': 1.884170235959498e-05, 'samples': 25266048, 'steps': 131593, 'loss/train': 1.0309385061264038} 08/31/2021 13:03:26 - INFO - __main__ - Step 131595: {'lr': 1.8839681291128924e-05, 'samples': 25266240, 'steps': 131594, 'loss/train': 1.4899457693099976} 08/31/2021 13:03:26 - INFO - __main__ - Step 131596: {'lr': 1.8837660326820132e-05, 'samples': 25266432, 'steps': 131595, 'loss/train': 0.2560465633869171} 08/31/2021 13:03:27 - INFO - __main__ - Step 131597: {'lr': 1.8835639466669526e-05, 'samples': 25266624, 'steps': 131596, 'loss/train': 0.15306755900382996} 08/31/2021 13:03:28 - INFO - __main__ - Step 131598: {'lr': 1.883361871067801e-05, 'samples': 25266816, 'steps': 131597, 'loss/train': 1.1069250106811523} 08/31/2021 13:03:29 - INFO - __main__ - Step 131599: {'lr': 1.8831598058846488e-05, 'samples': 25267008, 'steps': 131598, 'loss/train': 1.4937527179718018} 08/31/2021 13:03:29 - INFO - __main__ - Step 131600: {'lr': 1.8829577511175894e-05, 'samples': 25267200, 'steps': 131599, 'loss/train': 0.05086797848343849} 08/31/2021 13:03:30 - INFO - __main__ - Step 131601: {'lr': 1.8827557067667146e-05, 'samples': 25267392, 'steps': 131600, 'loss/train': 0.36275383830070496} 08/31/2021 13:03:30 - INFO - __main__ - Step 131602: {'lr': 1.8825536728321157e-05, 'samples': 25267584, 'steps': 131601, 'loss/train': 1.154735803604126} 08/31/2021 13:03:31 - INFO - __main__ - Step 131603: {'lr': 1.8823516493138764e-05, 'samples': 25267776, 'steps': 131602, 'loss/train': 1.0955216884613037} 08/31/2021 13:03:32 - INFO - __main__ - Step 131604: {'lr': 1.882149636212094e-05, 'samples': 25267968, 'steps': 131603, 'loss/train': 1.1673110723495483} 08/31/2021 13:03:32 - INFO - __main__ - Step 131605: {'lr': 1.8819476335268566e-05, 'samples': 25268160, 'steps': 131604, 'loss/train': 1.0828592777252197} 08/31/2021 13:03:33 - INFO - __main__ - Step 131606: {'lr': 1.8817456412582563e-05, 'samples': 25268352, 'steps': 131605, 'loss/train': 0.9416930079460144} 08/31/2021 13:03:33 - INFO - __main__ - Step 131607: {'lr': 1.8815436594063872e-05, 'samples': 25268544, 'steps': 131606, 'loss/train': 1.7520791292190552} 08/31/2021 13:03:35 - INFO - __main__ - Step 131608: {'lr': 1.8813416879713358e-05, 'samples': 25268736, 'steps': 131607, 'loss/train': 1.2054895162582397} 08/31/2021 13:03:35 - INFO - __main__ - Step 131609: {'lr': 1.881139726953196e-05, 'samples': 25268928, 'steps': 131608, 'loss/train': 0.8240613341331482} 08/31/2021 13:03:35 - INFO - __main__ - Step 131610: {'lr': 1.8809377763520598e-05, 'samples': 25269120, 'steps': 131609, 'loss/train': 0.27126622200012207} 08/31/2021 13:03:36 - INFO - __main__ - Step 131611: {'lr': 1.8807358361680128e-05, 'samples': 25269312, 'steps': 131610, 'loss/train': 1.0511103868484497} 08/31/2021 13:03:36 - INFO - __main__ - Step 131612: {'lr': 1.8805339064011524e-05, 'samples': 25269504, 'steps': 131611, 'loss/train': 1.3166985511779785} 08/31/2021 13:03:36 - INFO - __main__ - Step 131613: {'lr': 1.8803319870515643e-05, 'samples': 25269696, 'steps': 131612, 'loss/train': 1.2093411684036255} 08/31/2021 13:03:38 - INFO - __main__ - Step 131614: {'lr': 1.8801300781193465e-05, 'samples': 25269888, 'steps': 131613, 'loss/train': 0.6008991003036499} 08/31/2021 13:03:38 - INFO - __main__ - Step 131615: {'lr': 1.8799281796045842e-05, 'samples': 25270080, 'steps': 131614, 'loss/train': 1.3482565879821777} 08/31/2021 13:03:39 - INFO - __main__ - Step 131616: {'lr': 1.8797262915073664e-05, 'samples': 25270272, 'steps': 131615, 'loss/train': 0.7928593158721924} 08/31/2021 13:03:39 - INFO - __main__ - Step 131617: {'lr': 1.8795244138277877e-05, 'samples': 25270464, 'steps': 131616, 'loss/train': 0.5573998689651489} 08/31/2021 13:03:39 - INFO - __main__ - Step 131618: {'lr': 1.8793225465659368e-05, 'samples': 25270656, 'steps': 131617, 'loss/train': 0.6858179569244385} 08/31/2021 13:03:41 - INFO - __main__ - Step 131619: {'lr': 1.879120689721908e-05, 'samples': 25270848, 'steps': 131618, 'loss/train': 0.4828231632709503} 08/31/2021 13:03:41 - INFO - __main__ - Step 131620: {'lr': 1.8789188432957933e-05, 'samples': 25271040, 'steps': 131619, 'loss/train': 1.1449414491653442} 08/31/2021 13:03:42 - INFO - __main__ - Step 131621: {'lr': 1.878717007287678e-05, 'samples': 25271232, 'steps': 131620, 'loss/train': 1.6502212285995483} 08/31/2021 13:03:42 - INFO - __main__ - Step 131622: {'lr': 1.878515181697657e-05, 'samples': 25271424, 'steps': 131621, 'loss/train': 0.9510946869850159} 08/31/2021 13:03:42 - INFO - __main__ - Step 131623: {'lr': 1.878313366525819e-05, 'samples': 25271616, 'steps': 131622, 'loss/train': 1.4965453147888184} 08/31/2021 13:03:45 - INFO - __main__ - Step 131624: {'lr': 1.878111561772258e-05, 'samples': 25271808, 'steps': 131623, 'loss/train': 1.5236653089523315} 08/31/2021 13:03:45 - INFO - __main__ - Step 131625: {'lr': 1.8779097674370664e-05, 'samples': 25272000, 'steps': 131624, 'loss/train': 1.2285466194152832} 08/31/2021 13:03:45 - INFO - __main__ - Step 131626: {'lr': 1.877707983520327e-05, 'samples': 25272192, 'steps': 131625, 'loss/train': 1.174685001373291} 08/31/2021 13:03:46 - INFO - __main__ - Step 131627: {'lr': 1.8775062100221367e-05, 'samples': 25272384, 'steps': 131626, 'loss/train': 1.1014639139175415} 08/31/2021 13:03:46 - INFO - __main__ - Step 131628: {'lr': 1.8773044469425847e-05, 'samples': 25272576, 'steps': 131627, 'loss/train': 1.3369444608688354} 08/31/2021 13:03:47 - INFO - __main__ - Step 131629: {'lr': 1.8771026942817627e-05, 'samples': 25272768, 'steps': 131628, 'loss/train': 0.9976130723953247} 08/31/2021 13:03:48 - INFO - __main__ - Step 131630: {'lr': 1.8769009520397616e-05, 'samples': 25272960, 'steps': 131629, 'loss/train': 1.2053574323654175} 08/31/2021 13:03:48 - INFO - __main__ - Step 131631: {'lr': 1.876699220216671e-05, 'samples': 25273152, 'steps': 131630, 'loss/train': 0.9192081689834595} 08/31/2021 13:03:49 - INFO - __main__ - Step 131632: {'lr': 1.876497498812585e-05, 'samples': 25273344, 'steps': 131631, 'loss/train': 1.0107464790344238} 08/31/2021 13:03:49 - INFO - __main__ - Step 131633: {'lr': 1.8762957878275895e-05, 'samples': 25273536, 'steps': 131632, 'loss/train': 1.3323684930801392} 08/31/2021 13:03:50 - INFO - __main__ - Step 131634: {'lr': 1.8760940872617816e-05, 'samples': 25273728, 'steps': 131633, 'loss/train': 0.39117079973220825} 08/31/2021 13:03:51 - INFO - __main__ - Step 131635: {'lr': 1.8758923971152473e-05, 'samples': 25273920, 'steps': 131634, 'loss/train': 0.8596590757369995} 08/31/2021 13:03:51 - INFO - __main__ - Step 131636: {'lr': 1.8756907173880816e-05, 'samples': 25274112, 'steps': 131635, 'loss/train': 0.16783539950847626} 08/31/2021 13:03:52 - INFO - __main__ - Step 131637: {'lr': 1.87548904808037e-05, 'samples': 25274304, 'steps': 131636, 'loss/train': 1.6361044645309448} 08/31/2021 13:03:52 - INFO - __main__ - Step 131638: {'lr': 1.875287389192207e-05, 'samples': 25274496, 'steps': 131637, 'loss/train': 0.3970697820186615} 08/31/2021 13:03:54 - INFO - __main__ - Step 131639: {'lr': 1.875085740723684e-05, 'samples': 25274688, 'steps': 131638, 'loss/train': 0.7394572496414185} 08/31/2021 13:03:54 - INFO - __main__ - Step 131640: {'lr': 1.8748841026748868e-05, 'samples': 25274880, 'steps': 131639, 'loss/train': 0.6860698461532593} 08/31/2021 13:03:54 - INFO - __main__ - Step 131641: {'lr': 1.8746824750459133e-05, 'samples': 25275072, 'steps': 131640, 'loss/train': 1.4418460130691528} 08/31/2021 13:03:55 - INFO - __main__ - Step 131642: {'lr': 1.8744808578368495e-05, 'samples': 25275264, 'steps': 131641, 'loss/train': 0.5493262410163879} 08/31/2021 13:03:55 - INFO - __main__ - Step 131643: {'lr': 1.8742792510477864e-05, 'samples': 25275456, 'steps': 131642, 'loss/train': 0.22179396450519562} 08/31/2021 13:03:57 - INFO - __main__ - Step 131644: {'lr': 1.8740776546788187e-05, 'samples': 25275648, 'steps': 131643, 'loss/train': 1.011042833328247} 08/31/2021 13:03:57 - INFO - __main__ - Step 131645: {'lr': 1.8738760687300323e-05, 'samples': 25275840, 'steps': 131644, 'loss/train': 0.9681269526481628} 08/31/2021 13:03:58 - INFO - __main__ - Step 131646: {'lr': 1.873674493201524e-05, 'samples': 25276032, 'steps': 131645, 'loss/train': 0.9655916690826416} 08/31/2021 13:03:58 - INFO - __main__ - Step 131647: {'lr': 1.873472928093381e-05, 'samples': 25276224, 'steps': 131646, 'loss/train': 1.2429683208465576} 08/31/2021 13:03:58 - INFO - __main__ - Step 131648: {'lr': 1.873271373405694e-05, 'samples': 25276416, 'steps': 131647, 'loss/train': 1.3187648057937622} 08/31/2021 13:04:00 - INFO - __main__ - Step 131649: {'lr': 1.873069829138552e-05, 'samples': 25276608, 'steps': 131648, 'loss/train': 1.828810453414917} 08/31/2021 13:04:01 - INFO - __main__ - Step 131650: {'lr': 1.872868295292049e-05, 'samples': 25276800, 'steps': 131649, 'loss/train': 1.2250607013702393} 08/31/2021 13:04:01 - INFO - __main__ - Step 131651: {'lr': 1.8726667718662717e-05, 'samples': 25276992, 'steps': 131650, 'loss/train': 1.190058946609497} 08/31/2021 13:04:01 - INFO - __main__ - Step 131652: {'lr': 1.8724652588613165e-05, 'samples': 25277184, 'steps': 131651, 'loss/train': 0.6890652179718018} 08/31/2021 13:04:02 - INFO - __main__ - Step 131653: {'lr': 1.8722637562772706e-05, 'samples': 25277376, 'steps': 131652, 'loss/train': 0.07395198941230774} 08/31/2021 13:04:02 - INFO - __main__ - Step 131654: {'lr': 1.8720622641142272e-05, 'samples': 25277568, 'steps': 131653, 'loss/train': 1.1620861291885376} 08/31/2021 13:04:03 - INFO - __main__ - Step 131655: {'lr': 1.8718607823722756e-05, 'samples': 25277760, 'steps': 131654, 'loss/train': 0.8776035904884338} 08/31/2021 13:04:04 - INFO - __main__ - Step 131656: {'lr': 1.8716593110515045e-05, 'samples': 25277952, 'steps': 131655, 'loss/train': 0.12004655599594116} 08/31/2021 13:04:04 - INFO - __main__ - Step 131657: {'lr': 1.8714578501520085e-05, 'samples': 25278144, 'steps': 131656, 'loss/train': 1.3529340028762817} 08/31/2021 13:04:05 - INFO - __main__ - Step 131658: {'lr': 1.8712563996738817e-05, 'samples': 25278336, 'steps': 131657, 'loss/train': 1.3801542520523071} 08/31/2021 13:04:05 - INFO - __main__ - Step 131659: {'lr': 1.8710549596172048e-05, 'samples': 25278528, 'steps': 131658, 'loss/train': 0.672512412071228} 08/31/2021 13:04:07 - INFO - __main__ - Step 131660: {'lr': 1.8708535299820723e-05, 'samples': 25278720, 'steps': 131659, 'loss/train': 1.1958507299423218} 08/31/2021 13:04:07 - INFO - __main__ - Step 131661: {'lr': 1.870652110768578e-05, 'samples': 25278912, 'steps': 131660, 'loss/train': 1.5000067949295044} 08/31/2021 13:04:07 - INFO - __main__ - Step 131662: {'lr': 1.8704507019768085e-05, 'samples': 25279104, 'steps': 131661, 'loss/train': 1.5912786722183228} 08/31/2021 13:04:08 - INFO - __main__ - Step 131663: {'lr': 1.8702493036068608e-05, 'samples': 25279296, 'steps': 131662, 'loss/train': 1.3726383447647095} 08/31/2021 13:04:08 - INFO - __main__ - Step 131664: {'lr': 1.870047915658818e-05, 'samples': 25279488, 'steps': 131663, 'loss/train': 1.0664663314819336} 08/31/2021 13:04:10 - INFO - __main__ - Step 131665: {'lr': 1.8698465381327773e-05, 'samples': 25279680, 'steps': 131664, 'loss/train': 0.6507893204689026} 08/31/2021 13:04:10 - INFO - __main__ - Step 131666: {'lr': 1.869645171028825e-05, 'samples': 25279872, 'steps': 131665, 'loss/train': 0.6386256814002991} 08/31/2021 13:04:11 - INFO - __main__ - Step 131667: {'lr': 1.8694438143470548e-05, 'samples': 25280064, 'steps': 131666, 'loss/train': 1.3732908964157104} 08/31/2021 13:04:11 - INFO - __main__ - Step 131668: {'lr': 1.8692424680875562e-05, 'samples': 25280256, 'steps': 131667, 'loss/train': 0.6650460362434387} 08/31/2021 13:04:11 - INFO - __main__ - Step 131669: {'lr': 1.869041132250421e-05, 'samples': 25280448, 'steps': 131668, 'loss/train': 0.08342922478914261} 08/31/2021 13:04:13 - INFO - __main__ - Step 131670: {'lr': 1.8688398068357426e-05, 'samples': 25280640, 'steps': 131669, 'loss/train': 0.4072195589542389} 08/31/2021 13:04:13 - INFO - __main__ - Step 131671: {'lr': 1.8686384918436023e-05, 'samples': 25280832, 'steps': 131670, 'loss/train': 0.6280738115310669} 08/31/2021 13:04:14 - INFO - __main__ - Step 131672: {'lr': 1.8684371872740967e-05, 'samples': 25281024, 'steps': 131671, 'loss/train': 0.920154333114624} 08/31/2021 13:04:14 - INFO - __main__ - Step 131673: {'lr': 1.868235893127318e-05, 'samples': 25281216, 'steps': 131672, 'loss/train': 0.7261195778846741} 08/31/2021 13:04:14 - INFO - __main__ - Step 131674: {'lr': 1.8680346094033546e-05, 'samples': 25281408, 'steps': 131673, 'loss/train': 1.368589997291565} 08/31/2021 13:04:17 - INFO - __main__ - Step 131675: {'lr': 1.867833336102298e-05, 'samples': 25281600, 'steps': 131674, 'loss/train': 0.7448432445526123} 08/31/2021 13:04:17 - INFO - __main__ - Step 131676: {'lr': 1.8676320732242403e-05, 'samples': 25281792, 'steps': 131675, 'loss/train': 0.6297868490219116} 08/31/2021 13:04:17 - INFO - __main__ - Step 131677: {'lr': 1.867430820769267e-05, 'samples': 25281984, 'steps': 131676, 'loss/train': 1.3447574377059937} 08/31/2021 13:04:18 - INFO - __main__ - Step 131678: {'lr': 1.8672295787374754e-05, 'samples': 25282176, 'steps': 131677, 'loss/train': 0.4969567060470581} 08/31/2021 13:04:18 - INFO - __main__ - Step 131679: {'lr': 1.8670283471289518e-05, 'samples': 25282368, 'steps': 131678, 'loss/train': 1.1528180837631226} 08/31/2021 13:04:18 - INFO - __main__ - Step 131680: {'lr': 1.8668271259437873e-05, 'samples': 25282560, 'steps': 131679, 'loss/train': 2.3111326694488525} 08/31/2021 13:04:20 - INFO - __main__ - Step 131681: {'lr': 1.8666259151820768e-05, 'samples': 25282752, 'steps': 131680, 'loss/train': 1.1875450611114502} 08/31/2021 13:04:21 - INFO - __main__ - Step 131682: {'lr': 1.8664247148439033e-05, 'samples': 25282944, 'steps': 131681, 'loss/train': 1.2389073371887207} 08/31/2021 13:04:21 - INFO - __main__ - Step 131683: {'lr': 1.8662235249293697e-05, 'samples': 25283136, 'steps': 131682, 'loss/train': 0.4727897346019745} 08/31/2021 13:04:22 - INFO - __main__ - Step 131684: {'lr': 1.8660223454385533e-05, 'samples': 25283328, 'steps': 131683, 'loss/train': 1.189122200012207} 08/31/2021 13:04:22 - INFO - __main__ - Step 131685: {'lr': 1.8658211763715514e-05, 'samples': 25283520, 'steps': 131684, 'loss/train': 0.8666350245475769} 08/31/2021 13:04:23 - INFO - __main__ - Step 131686: {'lr': 1.8656200177284503e-05, 'samples': 25283712, 'steps': 131685, 'loss/train': 1.3545305728912354} 08/31/2021 13:04:24 - INFO - __main__ - Step 131687: {'lr': 1.865418869509347e-05, 'samples': 25283904, 'steps': 131686, 'loss/train': 1.0562182664871216} 08/31/2021 13:04:24 - INFO - __main__ - Step 131688: {'lr': 1.8652177317143275e-05, 'samples': 25284096, 'steps': 131687, 'loss/train': 0.9767323136329651} 08/31/2021 13:04:25 - INFO - __main__ - Step 131689: {'lr': 1.8650166043434837e-05, 'samples': 25284288, 'steps': 131688, 'loss/train': 0.9835411310195923} 08/31/2021 13:04:25 - INFO - __main__ - Step 131690: {'lr': 1.8648154873969093e-05, 'samples': 25284480, 'steps': 131689, 'loss/train': 1.4391686916351318} 08/31/2021 13:04:27 - INFO - __main__ - Step 131691: {'lr': 1.864614380874688e-05, 'samples': 25284672, 'steps': 131690, 'loss/train': 0.6187803149223328} 08/31/2021 13:04:27 - INFO - __main__ - Step 131692: {'lr': 1.864413284776917e-05, 'samples': 25284864, 'steps': 131691, 'loss/train': 1.2644567489624023} 08/31/2021 13:04:27 - INFO - __main__ - Step 131693: {'lr': 1.864212199103685e-05, 'samples': 25285056, 'steps': 131692, 'loss/train': 0.5333980917930603} 08/31/2021 13:04:28 - INFO - __main__ - Step 131694: {'lr': 1.8640111238550778e-05, 'samples': 25285248, 'steps': 131693, 'loss/train': 0.678080677986145} 08/31/2021 13:04:28 - INFO - __main__ - Step 131695: {'lr': 1.863810059031193e-05, 'samples': 25285440, 'steps': 131694, 'loss/train': 1.5749187469482422} 08/31/2021 13:04:29 - INFO - __main__ - Step 131696: {'lr': 1.8636090046321246e-05, 'samples': 25285632, 'steps': 131695, 'loss/train': 1.1558773517608643} 08/31/2021 13:04:30 - INFO - __main__ - Step 131697: {'lr': 1.863407960657951e-05, 'samples': 25285824, 'steps': 131696, 'loss/train': 0.7730397582054138} 08/31/2021 13:04:30 - INFO - __main__ - Step 131698: {'lr': 1.8632069271087683e-05, 'samples': 25286016, 'steps': 131697, 'loss/train': 1.1873044967651367} 08/31/2021 13:04:31 - INFO - __main__ - Step 131699: {'lr': 1.863005903984666e-05, 'samples': 25286208, 'steps': 131698, 'loss/train': 1.8714076280593872} 08/31/2021 13:04:31 - INFO - __main__ - Step 131700: {'lr': 1.8628048912857382e-05, 'samples': 25286400, 'steps': 131699, 'loss/train': 1.1712727546691895} 08/31/2021 13:04:33 - INFO - __main__ - Step 131701: {'lr': 1.862603889012074e-05, 'samples': 25286592, 'steps': 131700, 'loss/train': 1.1564762592315674} 08/31/2021 13:04:33 - INFO - __main__ - Step 131702: {'lr': 1.862402897163762e-05, 'samples': 25286784, 'steps': 131701, 'loss/train': 0.6452180743217468} 08/31/2021 13:04:33 - INFO - __main__ - Step 131703: {'lr': 1.8622019157408938e-05, 'samples': 25286976, 'steps': 131702, 'loss/train': 0.8876054286956787} 08/31/2021 13:04:34 - INFO - __main__ - Step 131704: {'lr': 1.8620009447435636e-05, 'samples': 25287168, 'steps': 131703, 'loss/train': 1.002543568611145} 08/31/2021 13:04:34 - INFO - __main__ - Step 131705: {'lr': 1.861799984171855e-05, 'samples': 25287360, 'steps': 131704, 'loss/train': 0.7925943732261658} 08/31/2021 13:04:34 - INFO - __main__ - Step 131706: {'lr': 1.8615990340258653e-05, 'samples': 25287552, 'steps': 131705, 'loss/train': 0.8185167908668518} 08/31/2021 13:04:36 - INFO - __main__ - Step 131707: {'lr': 1.86139809430568e-05, 'samples': 25287744, 'steps': 131706, 'loss/train': 0.8772414922714233} 08/31/2021 13:04:36 - INFO - __main__ - Step 131708: {'lr': 1.8611971650113913e-05, 'samples': 25287936, 'steps': 131707, 'loss/train': 0.9859028458595276} 08/31/2021 13:04:37 - INFO - __main__ - Step 131709: {'lr': 1.8609962461430928e-05, 'samples': 25288128, 'steps': 131708, 'loss/train': 0.9596881866455078} 08/31/2021 13:04:37 - INFO - __main__ - Step 131710: {'lr': 1.860795337700874e-05, 'samples': 25288320, 'steps': 131709, 'loss/train': 1.3205097913742065} 08/31/2021 13:04:38 - INFO - __main__ - Step 131711: {'lr': 1.860594439684821e-05, 'samples': 25288512, 'steps': 131710, 'loss/train': 0.7795997858047485} 08/31/2021 13:04:39 - INFO - __main__ - Step 131712: {'lr': 1.8603935520950242e-05, 'samples': 25288704, 'steps': 131711, 'loss/train': 0.7666590213775635} 08/31/2021 13:04:39 - INFO - __main__ - Step 131713: {'lr': 1.8601926749315794e-05, 'samples': 25288896, 'steps': 131712, 'loss/train': 1.0515611171722412} 08/31/2021 13:04:40 - INFO - __main__ - Step 131714: {'lr': 1.859991808194575e-05, 'samples': 25289088, 'steps': 131713, 'loss/train': 1.3788083791732788} 08/31/2021 13:04:40 - INFO - __main__ - Step 131715: {'lr': 1.859790951884102e-05, 'samples': 25289280, 'steps': 131714, 'loss/train': 1.1267465353012085} 08/31/2021 13:04:40 - INFO - __main__ - Step 131716: {'lr': 1.8595901060002474e-05, 'samples': 25289472, 'steps': 131715, 'loss/train': 0.9403360486030579} 08/31/2021 13:04:42 - INFO - __main__ - Step 131717: {'lr': 1.8593892705431075e-05, 'samples': 25289664, 'steps': 131716, 'loss/train': 0.7771868705749512} 08/31/2021 13:04:43 - INFO - __main__ - Step 131718: {'lr': 1.8591884455127662e-05, 'samples': 25289856, 'steps': 131717, 'loss/train': 0.6962317824363708} 08/31/2021 13:04:43 - INFO - __main__ - Step 131719: {'lr': 1.8589876309093202e-05, 'samples': 25290048, 'steps': 131718, 'loss/train': 0.46848252415657043} 08/31/2021 13:04:43 - INFO - __main__ - Step 131720: {'lr': 1.8587868267328556e-05, 'samples': 25290240, 'steps': 131719, 'loss/train': 1.0215702056884766} 08/31/2021 13:04:44 - INFO - __main__ - Step 131721: {'lr': 1.858586032983467e-05, 'samples': 25290432, 'steps': 131720, 'loss/train': 1.0135396718978882} 08/31/2021 13:04:45 - INFO - __main__ - Step 131722: {'lr': 1.8583852496612404e-05, 'samples': 25290624, 'steps': 131721, 'loss/train': 1.1998095512390137} 08/31/2021 13:04:46 - INFO - __main__ - Step 131723: {'lr': 1.8581844767662727e-05, 'samples': 25290816, 'steps': 131722, 'loss/train': 0.488182932138443} 08/31/2021 13:04:46 - INFO - __main__ - Step 131724: {'lr': 1.8579837142986472e-05, 'samples': 25291008, 'steps': 131723, 'loss/train': 1.1065458059310913} 08/31/2021 13:04:46 - INFO - __main__ - Step 131725: {'lr': 1.8577829622584557e-05, 'samples': 25291200, 'steps': 131724, 'loss/train': 0.9838674664497375} 08/31/2021 13:04:47 - INFO - __main__ - Step 131726: {'lr': 1.8575822206457897e-05, 'samples': 25291392, 'steps': 131725, 'loss/train': 0.637261152267456} 08/31/2021 13:04:48 - INFO - __main__ - Step 131727: {'lr': 1.857381489460741e-05, 'samples': 25291584, 'steps': 131726, 'loss/train': 0.641273558139801} 08/31/2021 13:04:49 - INFO - __main__ - Step 131728: {'lr': 1.857180768703398e-05, 'samples': 25291776, 'steps': 131727, 'loss/train': 1.0958280563354492} 08/31/2021 13:04:49 - INFO - __main__ - Step 131729: {'lr': 1.8569800583738556e-05, 'samples': 25291968, 'steps': 131728, 'loss/train': 1.5348825454711914} 08/31/2021 13:04:49 - INFO - __main__ - Step 131730: {'lr': 1.8567793584721964e-05, 'samples': 25292160, 'steps': 131729, 'loss/train': 1.2945749759674072} 08/31/2021 13:04:50 - INFO - __main__ - Step 131731: {'lr': 1.856578668998518e-05, 'samples': 25292352, 'steps': 131730, 'loss/train': 1.1522568464279175} 08/31/2021 13:04:52 - INFO - __main__ - Step 131732: {'lr': 1.8563779899529064e-05, 'samples': 25292544, 'steps': 131731, 'loss/train': 1.0408339500427246} 08/31/2021 13:04:52 - INFO - __main__ - Step 131733: {'lr': 1.856177321335456e-05, 'samples': 25292736, 'steps': 131732, 'loss/train': 1.1315371990203857} 08/31/2021 13:04:53 - INFO - __main__ - Step 131734: {'lr': 1.8559766631462525e-05, 'samples': 25292928, 'steps': 131733, 'loss/train': 1.0357104539871216} 08/31/2021 13:04:53 - INFO - __main__ - Step 131735: {'lr': 1.855776015385391e-05, 'samples': 25293120, 'steps': 131734, 'loss/train': 0.6499470472335815} 08/31/2021 13:04:53 - INFO - __main__ - Step 131736: {'lr': 1.8555753780529593e-05, 'samples': 25293312, 'steps': 131735, 'loss/train': 1.6419777870178223} 08/31/2021 13:04:55 - INFO - __main__ - Step 131737: {'lr': 1.8553747511490498e-05, 'samples': 25293504, 'steps': 131736, 'loss/train': 1.1428794860839844} 08/31/2021 13:04:55 - INFO - __main__ - Step 131738: {'lr': 1.855174134673751e-05, 'samples': 25293696, 'steps': 131737, 'loss/train': 0.9391089081764221} 08/31/2021 13:04:56 - INFO - __main__ - Step 131739: {'lr': 1.8549735286271517e-05, 'samples': 25293888, 'steps': 131738, 'loss/train': 1.1466186046600342} 08/31/2021 13:04:56 - INFO - __main__ - Step 131740: {'lr': 1.8547729330093437e-05, 'samples': 25294080, 'steps': 131739, 'loss/train': 1.28644859790802} 08/31/2021 13:04:56 - INFO - __main__ - Step 131741: {'lr': 1.8545723478204184e-05, 'samples': 25294272, 'steps': 131740, 'loss/train': 0.48498305678367615} 08/31/2021 13:04:59 - INFO - __main__ - Step 131742: {'lr': 1.8543717730604647e-05, 'samples': 25294464, 'steps': 131741, 'loss/train': 0.9942724108695984} 08/31/2021 13:05:00 - INFO - __main__ - Step 131743: {'lr': 1.8541712087295743e-05, 'samples': 25294656, 'steps': 131742, 'loss/train': 0.827109694480896} 08/31/2021 13:05:00 - INFO - __main__ - Step 131744: {'lr': 1.8539706548278383e-05, 'samples': 25294848, 'steps': 131743, 'loss/train': 1.7568817138671875} 08/31/2021 13:05:00 - INFO - __main__ - Step 131745: {'lr': 1.8537701113553464e-05, 'samples': 25295040, 'steps': 131744, 'loss/train': 1.7375001907348633} 08/31/2021 13:05:01 - INFO - __main__ - Step 131746: {'lr': 1.8535695783121864e-05, 'samples': 25295232, 'steps': 131745, 'loss/train': 0.5250818729400635} 08/31/2021 13:05:01 - INFO - __main__ - Step 131747: {'lr': 1.8533690556984507e-05, 'samples': 25295424, 'steps': 131746, 'loss/train': 1.7448956966400146} 08/31/2021 13:05:01 - INFO - __main__ - Step 131748: {'lr': 1.8531685435142302e-05, 'samples': 25295616, 'steps': 131747, 'loss/train': 1.044323444366455} 08/31/2021 13:05:02 - INFO - __main__ - Step 131749: {'lr': 1.8529680417596173e-05, 'samples': 25295808, 'steps': 131748, 'loss/train': 0.8806884288787842} 08/31/2021 13:05:03 - INFO - __main__ - Step 131750: {'lr': 1.852767550434703e-05, 'samples': 25296000, 'steps': 131749, 'loss/train': 1.404626488685608} 08/31/2021 13:05:04 - INFO - __main__ - Step 131751: {'lr': 1.852567069539568e-05, 'samples': 25296192, 'steps': 131750, 'loss/train': 1.259677529335022} 08/31/2021 13:05:04 - INFO - __main__ - Step 131752: {'lr': 1.8523665990743093e-05, 'samples': 25296384, 'steps': 131751, 'loss/train': 1.0780576467514038} 08/31/2021 13:05:05 - INFO - __main__ - Step 131753: {'lr': 1.8521661390390187e-05, 'samples': 25296576, 'steps': 131752, 'loss/train': 0.8593553304672241} 08/31/2021 13:05:05 - INFO - __main__ - Step 131754: {'lr': 1.8519656894337848e-05, 'samples': 25296768, 'steps': 131753, 'loss/train': 0.6523478031158447} 08/31/2021 13:05:06 - INFO - __main__ - Step 131755: {'lr': 1.8517652502586968e-05, 'samples': 25296960, 'steps': 131754, 'loss/train': 3.7937989234924316} 08/31/2021 13:05:07 - INFO - __main__ - Step 131756: {'lr': 1.8515648215138485e-05, 'samples': 25297152, 'steps': 131755, 'loss/train': 1.6670417785644531} 08/31/2021 13:05:07 - INFO - __main__ - Step 131757: {'lr': 1.8513644031993267e-05, 'samples': 25297344, 'steps': 131756, 'loss/train': 0.029019517824053764} 08/31/2021 13:05:08 - INFO - __main__ - Step 131758: {'lr': 1.851163995315222e-05, 'samples': 25297536, 'steps': 131757, 'loss/train': 0.943729043006897} 08/31/2021 13:05:08 - INFO - __main__ - Step 131759: {'lr': 1.850963597861627e-05, 'samples': 25297728, 'steps': 131758, 'loss/train': 0.5350311398506165} 08/31/2021 13:05:09 - INFO - __main__ - Step 131760: {'lr': 1.8507632108386268e-05, 'samples': 25297920, 'steps': 131759, 'loss/train': 1.181399941444397} 08/31/2021 13:05:10 - INFO - __main__ - Step 131761: {'lr': 1.8505628342463194e-05, 'samples': 25298112, 'steps': 131760, 'loss/train': 1.1955400705337524} 08/31/2021 13:05:10 - INFO - __main__ - Step 131762: {'lr': 1.85036246808479e-05, 'samples': 25298304, 'steps': 131761, 'loss/train': 1.2744126319885254} 08/31/2021 13:05:11 - INFO - __main__ - Step 131763: {'lr': 1.8501621123541314e-05, 'samples': 25298496, 'steps': 131762, 'loss/train': 0.8276621699333191} 08/31/2021 13:05:11 - INFO - __main__ - Step 131764: {'lr': 1.8499617670544337e-05, 'samples': 25298688, 'steps': 131763, 'loss/train': 0.6547128558158875} 08/31/2021 13:05:12 - INFO - __main__ - Step 131765: {'lr': 1.849761432185784e-05, 'samples': 25298880, 'steps': 131764, 'loss/train': 0.8926920294761658} 08/31/2021 13:05:13 - INFO - __main__ - Step 131766: {'lr': 1.849561107748274e-05, 'samples': 25299072, 'steps': 131765, 'loss/train': 1.0828673839569092} 08/31/2021 13:05:13 - INFO - __main__ - Step 131767: {'lr': 1.8493607937419943e-05, 'samples': 25299264, 'steps': 131766, 'loss/train': 0.9927840232849121} 08/31/2021 13:05:14 - INFO - __main__ - Step 131768: {'lr': 1.8491604901670372e-05, 'samples': 25299456, 'steps': 131767, 'loss/train': 0.3546469509601593} 08/31/2021 13:05:14 - INFO - __main__ - Step 131769: {'lr': 1.8489601970234888e-05, 'samples': 25299648, 'steps': 131768, 'loss/train': 1.2972393035888672} 08/31/2021 13:05:14 - INFO - __main__ - Step 131770: {'lr': 1.8487599143114432e-05, 'samples': 25299840, 'steps': 131769, 'loss/train': 1.4895068407058716} 08/31/2021 13:05:16 - INFO - __main__ - Step 131771: {'lr': 1.8485596420309892e-05, 'samples': 25300032, 'steps': 131770, 'loss/train': 1.0237774848937988} 08/31/2021 13:05:16 - INFO - __main__ - Step 131772: {'lr': 1.848359380182216e-05, 'samples': 25300224, 'steps': 131771, 'loss/train': 1.2900614738464355} 08/31/2021 13:05:17 - INFO - __main__ - Step 131773: {'lr': 1.8481591287652143e-05, 'samples': 25300416, 'steps': 131772, 'loss/train': 1.0973302125930786} 08/31/2021 13:05:17 - INFO - __main__ - Step 131774: {'lr': 1.8479588877800767e-05, 'samples': 25300608, 'steps': 131773, 'loss/train': 1.3589774370193481} 08/31/2021 13:05:17 - INFO - __main__ - Step 131775: {'lr': 1.847758657226889e-05, 'samples': 25300800, 'steps': 131774, 'loss/train': 0.9509859681129456} 08/31/2021 13:05:19 - INFO - __main__ - Step 131776: {'lr': 1.8475584371057452e-05, 'samples': 25300992, 'steps': 131775, 'loss/train': 1.3541969060897827} 08/31/2021 13:05:19 - INFO - __main__ - Step 131777: {'lr': 1.84735822741674e-05, 'samples': 25301184, 'steps': 131776, 'loss/train': 0.4974057674407959} 08/31/2021 13:05:20 - INFO - __main__ - Step 131778: {'lr': 1.847158028159954e-05, 'samples': 25301376, 'steps': 131777, 'loss/train': 1.1758034229278564} 08/31/2021 13:05:20 - INFO - __main__ - Step 131779: {'lr': 1.846957839335478e-05, 'samples': 25301568, 'steps': 131778, 'loss/train': 1.364460825920105} 08/31/2021 13:05:20 - INFO - __main__ - Step 131780: {'lr': 1.8467576609434073e-05, 'samples': 25301760, 'steps': 131779, 'loss/train': 1.2574814558029175} 08/31/2021 13:05:22 - INFO - __main__ - Step 131781: {'lr': 1.8465574929838302e-05, 'samples': 25301952, 'steps': 131780, 'loss/train': 0.34518706798553467} 08/31/2021 13:05:22 - INFO - __main__ - Step 131782: {'lr': 1.8463573354568385e-05, 'samples': 25302144, 'steps': 131781, 'loss/train': 0.3911146819591522} 08/31/2021 13:05:23 - INFO - __main__ - Step 131783: {'lr': 1.8461571883625184e-05, 'samples': 25302336, 'steps': 131782, 'loss/train': 0.7971075773239136} 08/31/2021 13:05:23 - INFO - __main__ - Step 131784: {'lr': 1.845957051700964e-05, 'samples': 25302528, 'steps': 131783, 'loss/train': 1.332853078842163} 08/31/2021 13:05:23 - INFO - __main__ - Step 131785: {'lr': 1.845756925472264e-05, 'samples': 25302720, 'steps': 131784, 'loss/train': 0.22847849130630493} 08/31/2021 13:05:25 - INFO - __main__ - Step 131786: {'lr': 1.84555680967651e-05, 'samples': 25302912, 'steps': 131785, 'loss/train': 1.425586223602295} 08/31/2021 13:05:26 - INFO - __main__ - Step 131787: {'lr': 1.8453567043137886e-05, 'samples': 25303104, 'steps': 131786, 'loss/train': 1.5519636869430542} 08/31/2021 13:05:26 - INFO - __main__ - Step 131788: {'lr': 1.8451566093841938e-05, 'samples': 25303296, 'steps': 131787, 'loss/train': 1.0737649202346802} 08/31/2021 13:05:27 - INFO - __main__ - Step 131789: {'lr': 1.8449565248878115e-05, 'samples': 25303488, 'steps': 131788, 'loss/train': 0.8551395535469055} 08/31/2021 13:05:27 - INFO - __main__ - Step 131790: {'lr': 1.8447564508247362e-05, 'samples': 25303680, 'steps': 131789, 'loss/train': 1.2165961265563965} 08/31/2021 13:05:29 - INFO - __main__ - Step 131791: {'lr': 1.844556387195062e-05, 'samples': 25303872, 'steps': 131790, 'loss/train': 0.9070677757263184} 08/31/2021 13:05:29 - INFO - __main__ - Step 131792: {'lr': 1.8443563339988674e-05, 'samples': 25304064, 'steps': 131791, 'loss/train': 1.3923656940460205} 08/31/2021 13:05:30 - INFO - __main__ - Step 131793: {'lr': 1.8441562912362487e-05, 'samples': 25304256, 'steps': 131792, 'loss/train': 0.8707395792007446} 08/31/2021 13:05:30 - INFO - __main__ - Step 131794: {'lr': 1.843956258907295e-05, 'samples': 25304448, 'steps': 131793, 'loss/train': 0.8881861567497253} 08/31/2021 13:05:30 - INFO - __main__ - Step 131795: {'lr': 1.843756237012098e-05, 'samples': 25304640, 'steps': 131794, 'loss/train': 1.1399791240692139} 08/31/2021 13:05:32 - INFO - __main__ - Step 131796: {'lr': 1.843556225550749e-05, 'samples': 25304832, 'steps': 131795, 'loss/train': 1.0305781364440918} 08/31/2021 13:05:32 - INFO - __main__ - Step 131797: {'lr': 1.843356224523335e-05, 'samples': 25305024, 'steps': 131796, 'loss/train': 1.494309902191162} 08/31/2021 13:05:33 - INFO - __main__ - Step 131798: {'lr': 1.843156233929946e-05, 'samples': 25305216, 'steps': 131797, 'loss/train': 1.3151922225952148} 08/31/2021 13:05:33 - INFO - __main__ - Step 131799: {'lr': 1.842956253770675e-05, 'samples': 25305408, 'steps': 131798, 'loss/train': 0.9067145586013794} 08/31/2021 13:05:33 - INFO - __main__ - Step 131800: {'lr': 1.84275628404561e-05, 'samples': 25305600, 'steps': 131799, 'loss/train': 1.1569750308990479} 08/31/2021 13:05:35 - INFO - __main__ - Step 131801: {'lr': 1.8425563247548405e-05, 'samples': 25305792, 'steps': 131800, 'loss/train': 1.0904388427734375} 08/31/2021 13:05:35 - INFO - __main__ - Step 131802: {'lr': 1.84235637589846e-05, 'samples': 25305984, 'steps': 131801, 'loss/train': 1.3148430585861206} 08/31/2021 13:05:36 - INFO - __main__ - Step 131803: {'lr': 1.8421564374765555e-05, 'samples': 25306176, 'steps': 131802, 'loss/train': 0.985233724117279} 08/31/2021 13:05:36 - INFO - __main__ - Step 131804: {'lr': 1.8419565094892234e-05, 'samples': 25306368, 'steps': 131803, 'loss/train': 0.7877020835876465} 08/31/2021 13:05:36 - INFO - __main__ - Step 131805: {'lr': 1.8417565919365413e-05, 'samples': 25306560, 'steps': 131804, 'loss/train': 0.464682012796402} 08/31/2021 13:05:37 - INFO - __main__ - Step 131806: {'lr': 1.841556684818607e-05, 'samples': 25306752, 'steps': 131805, 'loss/train': 0.883034348487854} 08/31/2021 13:05:38 - INFO - __main__ - Step 131807: {'lr': 1.841356788135512e-05, 'samples': 25306944, 'steps': 131806, 'loss/train': 0.3965457081794739} 08/31/2021 13:05:39 - INFO - __main__ - Step 131808: {'lr': 1.841156901887342e-05, 'samples': 25307136, 'steps': 131807, 'loss/train': 1.247413992881775} 08/31/2021 13:05:39 - INFO - __main__ - Step 131809: {'lr': 1.8409570260741914e-05, 'samples': 25307328, 'steps': 131808, 'loss/train': 1.0068439245224} 08/31/2021 13:05:39 - INFO - __main__ - Step 131810: {'lr': 1.8407571606961466e-05, 'samples': 25307520, 'steps': 131809, 'loss/train': 0.5521835684776306} 08/31/2021 13:05:40 - INFO - __main__ - Step 131811: {'lr': 1.8405573057532987e-05, 'samples': 25307712, 'steps': 131810, 'loss/train': 1.0518819093704224} 08/31/2021 13:05:41 - INFO - __main__ - Step 131812: {'lr': 1.8403574612457398e-05, 'samples': 25307904, 'steps': 131811, 'loss/train': 1.0325313806533813} 08/31/2021 13:05:42 - INFO - __main__ - Step 131813: {'lr': 1.840157627173558e-05, 'samples': 25308096, 'steps': 131812, 'loss/train': 2.0194408893585205} 08/31/2021 13:05:42 - INFO - __main__ - Step 131814: {'lr': 1.839957803536846e-05, 'samples': 25308288, 'steps': 131813, 'loss/train': 0.940601110458374} 08/31/2021 13:05:42 - INFO - __main__ - Step 131815: {'lr': 1.839757990335689e-05, 'samples': 25308480, 'steps': 131814, 'loss/train': 1.638780117034912} 08/31/2021 13:05:43 - INFO - __main__ - Step 131816: {'lr': 1.8395581875701782e-05, 'samples': 25308672, 'steps': 131815, 'loss/train': 1.0521742105484009} 08/31/2021 13:05:44 - INFO - __main__ - Step 131817: {'lr': 1.839358395240412e-05, 'samples': 25308864, 'steps': 131816, 'loss/train': 1.6174448728561401} 08/31/2021 13:05:44 - INFO - __main__ - Step 131818: {'lr': 1.8391586133464698e-05, 'samples': 25309056, 'steps': 131817, 'loss/train': 0.1107160896062851} 08/31/2021 13:05:45 - INFO - __main__ - Step 131819: {'lr': 1.8389588418884438e-05, 'samples': 25309248, 'steps': 131818, 'loss/train': 0.11799108237028122} 08/31/2021 13:05:45 - INFO - __main__ - Step 131820: {'lr': 1.8387590808664255e-05, 'samples': 25309440, 'steps': 131819, 'loss/train': 1.606724739074707} 08/31/2021 13:05:46 - INFO - __main__ - Step 131821: {'lr': 1.8385593302805066e-05, 'samples': 25309632, 'steps': 131820, 'loss/train': 1.0274717807769775} 08/31/2021 13:05:47 - INFO - __main__ - Step 131822: {'lr': 1.8383595901307726e-05, 'samples': 25309824, 'steps': 131821, 'loss/train': 2.0161545276641846} 08/31/2021 13:05:47 - INFO - __main__ - Step 131823: {'lr': 1.8381598604173183e-05, 'samples': 25310016, 'steps': 131822, 'loss/train': 1.2886611223220825} 08/31/2021 13:05:48 - INFO - __main__ - Step 131824: {'lr': 1.8379601411402326e-05, 'samples': 25310208, 'steps': 131823, 'loss/train': 0.7717037796974182} 08/31/2021 13:05:48 - INFO - __main__ - Step 131825: {'lr': 1.837760432299601e-05, 'samples': 25310400, 'steps': 131824, 'loss/train': 0.8509222269058228} 08/31/2021 13:05:49 - INFO - __main__ - Step 131826: {'lr': 1.8375607338955213e-05, 'samples': 25310592, 'steps': 131825, 'loss/train': 0.9371386170387268} 08/31/2021 13:05:50 - INFO - __main__ - Step 131827: {'lr': 1.8373610459280767e-05, 'samples': 25310784, 'steps': 131826, 'loss/train': 1.0521347522735596} 08/31/2021 13:05:50 - INFO - __main__ - Step 131828: {'lr': 1.837161368397361e-05, 'samples': 25310976, 'steps': 131827, 'loss/train': 1.2721225023269653} 08/31/2021 13:05:51 - INFO - __main__ - Step 131829: {'lr': 1.8369617013034635e-05, 'samples': 25311168, 'steps': 131828, 'loss/train': 0.10660392791032791} 08/31/2021 13:05:51 - INFO - __main__ - Step 131830: {'lr': 1.836762044646473e-05, 'samples': 25311360, 'steps': 131829, 'loss/train': 1.319942593574524} 08/31/2021 13:05:52 - INFO - __main__ - Step 131831: {'lr': 1.8365623984264833e-05, 'samples': 25311552, 'steps': 131830, 'loss/train': 1.4461944103240967} 08/31/2021 13:05:53 - INFO - __main__ - Step 131832: {'lr': 1.8363627626435758e-05, 'samples': 25311744, 'steps': 131831, 'loss/train': 0.8748642206192017} 08/31/2021 13:05:54 - INFO - __main__ - Step 131833: {'lr': 1.83616313729785e-05, 'samples': 25311936, 'steps': 131832, 'loss/train': 0.8115811347961426} 08/31/2021 13:05:54 - INFO - __main__ - Step 131834: {'lr': 1.835963522389389e-05, 'samples': 25312128, 'steps': 131833, 'loss/train': 0.9582714438438416} 08/31/2021 13:05:54 - INFO - __main__ - Step 131835: {'lr': 1.8357639179182846e-05, 'samples': 25312320, 'steps': 131834, 'loss/train': 1.4967325925827026} 08/31/2021 13:05:55 - INFO - __main__ - Step 131836: {'lr': 1.835564323884628e-05, 'samples': 25312512, 'steps': 131835, 'loss/train': 1.519133448600769} 08/31/2021 13:05:57 - INFO - __main__ - Step 131837: {'lr': 1.8353647402885114e-05, 'samples': 25312704, 'steps': 131836, 'loss/train': 1.7651339769363403} 08/31/2021 13:05:57 - INFO - __main__ - Step 131838: {'lr': 1.835165167130018e-05, 'samples': 25312896, 'steps': 131837, 'loss/train': 0.8838798403739929} 08/31/2021 13:05:58 - INFO - __main__ - Step 131839: {'lr': 1.8349656044092444e-05, 'samples': 25313088, 'steps': 131838, 'loss/train': 0.10564310848712921} 08/31/2021 13:05:58 - INFO - __main__ - Step 131840: {'lr': 1.8347660521262772e-05, 'samples': 25313280, 'steps': 131839, 'loss/train': 1.0151491165161133} 08/31/2021 13:05:58 - INFO - __main__ - Step 131841: {'lr': 1.8345665102812077e-05, 'samples': 25313472, 'steps': 131840, 'loss/train': 0.9036964774131775} 08/31/2021 13:05:59 - INFO - __main__ - Step 131842: {'lr': 1.8343669788741245e-05, 'samples': 25313664, 'steps': 131841, 'loss/train': 1.0353273153305054} 08/31/2021 13:06:00 - INFO - __main__ - Step 131843: {'lr': 1.834167457905117e-05, 'samples': 25313856, 'steps': 131842, 'loss/train': 0.7681055665016174} 08/31/2021 13:06:01 - INFO - __main__ - Step 131844: {'lr': 1.833967947374282e-05, 'samples': 25314048, 'steps': 131843, 'loss/train': 0.6928333640098572} 08/31/2021 13:06:01 - INFO - __main__ - Step 131845: {'lr': 1.8337684472816974e-05, 'samples': 25314240, 'steps': 131844, 'loss/train': 0.9135525822639465} 08/31/2021 13:06:01 - INFO - __main__ - Step 131846: {'lr': 1.83356895762746e-05, 'samples': 25314432, 'steps': 131845, 'loss/train': 0.8174239993095398} 08/31/2021 13:06:02 - INFO - __main__ - Step 131847: {'lr': 1.833369478411659e-05, 'samples': 25314624, 'steps': 131846, 'loss/train': 0.11710334569215775} 08/31/2021 13:06:03 - INFO - __main__ - Step 131848: {'lr': 1.8331700096343858e-05, 'samples': 25314816, 'steps': 131847, 'loss/train': 1.1519416570663452} 08/31/2021 13:06:04 - INFO - __main__ - Step 131849: {'lr': 1.8329705512957263e-05, 'samples': 25315008, 'steps': 131848, 'loss/train': 0.7741390466690063} 08/31/2021 13:06:04 - INFO - __main__ - Step 131850: {'lr': 1.832771103395775e-05, 'samples': 25315200, 'steps': 131849, 'loss/train': 0.5730804800987244} 08/31/2021 13:06:04 - INFO - __main__ - Step 131851: {'lr': 1.832571665934618e-05, 'samples': 25315392, 'steps': 131850, 'loss/train': 0.6938723921775818} 08/31/2021 13:06:05 - INFO - __main__ - Step 131852: {'lr': 1.8323722389123472e-05, 'samples': 25315584, 'steps': 131851, 'loss/train': 1.1297687292099} 08/31/2021 13:06:06 - INFO - __main__ - Step 131853: {'lr': 1.8321728223290534e-05, 'samples': 25315776, 'steps': 131852, 'loss/train': 0.830743670463562} 08/31/2021 13:06:07 - INFO - __main__ - Step 131854: {'lr': 1.8319734161848233e-05, 'samples': 25315968, 'steps': 131853, 'loss/train': 1.0943827629089355} 08/31/2021 13:06:07 - INFO - __main__ - Step 131855: {'lr': 1.8317740204797485e-05, 'samples': 25316160, 'steps': 131854, 'loss/train': 0.931821346282959} 08/31/2021 13:06:07 - INFO - __main__ - Step 131856: {'lr': 1.83157463521392e-05, 'samples': 25316352, 'steps': 131855, 'loss/train': 0.6704630851745605} 08/31/2021 13:06:08 - INFO - __main__ - Step 131857: {'lr': 1.8313752603874246e-05, 'samples': 25316544, 'steps': 131856, 'loss/train': 1.4012349843978882} 08/31/2021 13:06:09 - INFO - __main__ - Step 131858: {'lr': 1.831175896000359e-05, 'samples': 25316736, 'steps': 131857, 'loss/train': 0.18886610865592957} 08/31/2021 13:06:10 - INFO - __main__ - Step 131859: {'lr': 1.8309765420528036e-05, 'samples': 25316928, 'steps': 131858, 'loss/train': 1.619593620300293} 08/31/2021 13:06:10 - INFO - __main__ - Step 131860: {'lr': 1.830777198544853e-05, 'samples': 25317120, 'steps': 131859, 'loss/train': 0.5824800133705139} 08/31/2021 13:06:10 - INFO - __main__ - Step 131861: {'lr': 1.8305778654765985e-05, 'samples': 25317312, 'steps': 131860, 'loss/train': 1.0646495819091797} 08/31/2021 13:06:11 - INFO - __main__ - Step 131862: {'lr': 1.830378542848124e-05, 'samples': 25317504, 'steps': 131861, 'loss/train': 1.5593448877334595} 08/31/2021 13:06:12 - INFO - __main__ - Step 131863: {'lr': 1.830179230659526e-05, 'samples': 25317696, 'steps': 131862, 'loss/train': 1.0492231845855713} 08/31/2021 13:06:13 - INFO - __main__ - Step 131864: {'lr': 1.8299799289108938e-05, 'samples': 25317888, 'steps': 131863, 'loss/train': 1.3179553747177124} 08/31/2021 13:06:13 - INFO - __main__ - Step 131865: {'lr': 1.8297806376023102e-05, 'samples': 25318080, 'steps': 131864, 'loss/train': 1.932267427444458} 08/31/2021 13:06:13 - INFO - __main__ - Step 131866: {'lr': 1.8295813567338725e-05, 'samples': 25318272, 'steps': 131865, 'loss/train': 0.3276195824146271} 08/31/2021 13:06:14 - INFO - __main__ - Step 131867: {'lr': 1.82938208630567e-05, 'samples': 25318464, 'steps': 131866, 'loss/train': 1.42850661277771} 08/31/2021 13:06:15 - INFO - __main__ - Step 131868: {'lr': 1.829182826317788e-05, 'samples': 25318656, 'steps': 131867, 'loss/train': 1.2787572145462036} 08/31/2021 13:06:16 - INFO - __main__ - Step 131869: {'lr': 1.8289835767703183e-05, 'samples': 25318848, 'steps': 131868, 'loss/train': 0.05446436628699303} 08/31/2021 13:06:16 - INFO - __main__ - Step 131870: {'lr': 1.8287843376633528e-05, 'samples': 25319040, 'steps': 131869, 'loss/train': 0.9248924255371094} 08/31/2021 13:06:16 - INFO - __main__ - Step 131871: {'lr': 1.8285851089969803e-05, 'samples': 25319232, 'steps': 131870, 'loss/train': 1.3064881563186646} 08/31/2021 13:06:17 - INFO - __main__ - Step 131872: {'lr': 1.828385890771289e-05, 'samples': 25319424, 'steps': 131871, 'loss/train': 0.8027585744857788} 08/31/2021 13:06:18 - INFO - __main__ - Step 131873: {'lr': 1.8281866829863687e-05, 'samples': 25319616, 'steps': 131872, 'loss/train': 1.6912832260131836} 08/31/2021 13:06:19 - INFO - __main__ - Step 131874: {'lr': 1.82798748564231e-05, 'samples': 25319808, 'steps': 131873, 'loss/train': 0.9747156500816345} 08/31/2021 13:06:19 - INFO - __main__ - Step 131875: {'lr': 1.8277882987391996e-05, 'samples': 25320000, 'steps': 131874, 'loss/train': 0.8705294728279114} 08/31/2021 13:06:20 - INFO - __main__ - Step 131876: {'lr': 1.8275891222771347e-05, 'samples': 25320192, 'steps': 131875, 'loss/train': 1.1811177730560303} 08/31/2021 13:06:20 - INFO - __main__ - Step 131877: {'lr': 1.827389956256198e-05, 'samples': 25320384, 'steps': 131876, 'loss/train': 1.3139936923980713} 08/31/2021 13:06:22 - INFO - __main__ - Step 131878: {'lr': 1.8271908006764814e-05, 'samples': 25320576, 'steps': 131877, 'loss/train': 0.9512071013450623} 08/31/2021 13:06:22 - INFO - __main__ - Step 131879: {'lr': 1.8269916555380767e-05, 'samples': 25320768, 'steps': 131878, 'loss/train': 0.6927428841590881} 08/31/2021 13:06:22 - INFO - __main__ - Step 131880: {'lr': 1.8267925208410725e-05, 'samples': 25320960, 'steps': 131879, 'loss/train': 0.8673160672187805} 08/31/2021 13:06:23 - INFO - __main__ - Step 131881: {'lr': 1.8265933965855574e-05, 'samples': 25321152, 'steps': 131880, 'loss/train': 1.0751535892486572} 08/31/2021 13:06:23 - INFO - __main__ - Step 131882: {'lr': 1.8263942827716206e-05, 'samples': 25321344, 'steps': 131881, 'loss/train': 1.9137312173843384} 08/31/2021 13:06:23 - INFO - __main__ - Step 131883: {'lr': 1.8261951793993565e-05, 'samples': 25321536, 'steps': 131882, 'loss/train': 0.34456828236579895} 08/31/2021 13:06:25 - INFO - __main__ - Step 131884: {'lr': 1.825996086468848e-05, 'samples': 25321728, 'steps': 131883, 'loss/train': 0.772774338722229} 08/31/2021 13:06:25 - INFO - __main__ - Step 131885: {'lr': 1.8257970039801897e-05, 'samples': 25321920, 'steps': 131884, 'loss/train': 1.192674994468689} 08/31/2021 13:06:26 - INFO - __main__ - Step 131886: {'lr': 1.8255979319334676e-05, 'samples': 25322112, 'steps': 131885, 'loss/train': 1.2905186414718628} 08/31/2021 13:06:26 - INFO - __main__ - Step 131887: {'lr': 1.825398870328773e-05, 'samples': 25322304, 'steps': 131886, 'loss/train': 1.314591646194458} 08/31/2021 13:06:26 - INFO - __main__ - Step 131888: {'lr': 1.8251998191661982e-05, 'samples': 25322496, 'steps': 131887, 'loss/train': 0.3121417164802551} 08/31/2021 13:06:28 - INFO - __main__ - Step 131889: {'lr': 1.825000778445829e-05, 'samples': 25322688, 'steps': 131888, 'loss/train': 0.6919518113136292} 08/31/2021 13:06:29 - INFO - __main__ - Step 131890: {'lr': 1.8248017481677593e-05, 'samples': 25322880, 'steps': 131889, 'loss/train': 0.8329818248748779} 08/31/2021 13:06:29 - INFO - __main__ - Step 131891: {'lr': 1.8246027283320756e-05, 'samples': 25323072, 'steps': 131890, 'loss/train': 0.02999107725918293} 08/31/2021 13:06:29 - INFO - __main__ - Step 131892: {'lr': 1.8244037189388664e-05, 'samples': 25323264, 'steps': 131891, 'loss/train': 1.3988515138626099} 08/31/2021 13:06:30 - INFO - __main__ - Step 131893: {'lr': 1.8242047199882233e-05, 'samples': 25323456, 'steps': 131892, 'loss/train': 1.9560707807540894} 08/31/2021 13:06:32 - INFO - __main__ - Step 131894: {'lr': 1.824005731480241e-05, 'samples': 25323648, 'steps': 131893, 'loss/train': 0.03980223461985588} 08/31/2021 13:06:32 - INFO - __main__ - Step 131895: {'lr': 1.823806753415e-05, 'samples': 25323840, 'steps': 131894, 'loss/train': 1.646135926246643} 08/31/2021 13:06:33 - INFO - __main__ - Step 131896: {'lr': 1.8236077857925944e-05, 'samples': 25324032, 'steps': 131895, 'loss/train': 0.17047570645809174} 08/31/2021 13:06:33 - INFO - __main__ - Step 131897: {'lr': 1.8234088286131127e-05, 'samples': 25324224, 'steps': 131896, 'loss/train': 0.5310418605804443} 08/31/2021 13:06:33 - INFO - __main__ - Step 131898: {'lr': 1.8232098818766474e-05, 'samples': 25324416, 'steps': 131897, 'loss/train': 0.231237530708313} 08/31/2021 13:06:35 - INFO - __main__ - Step 131899: {'lr': 1.823010945583284e-05, 'samples': 25324608, 'steps': 131898, 'loss/train': 0.996228039264679} 08/31/2021 13:06:35 - INFO - __main__ - Step 131900: {'lr': 1.822812019733114e-05, 'samples': 25324800, 'steps': 131899, 'loss/train': 1.4879076480865479} 08/31/2021 13:06:36 - INFO - __main__ - Step 131901: {'lr': 1.822613104326229e-05, 'samples': 25324992, 'steps': 131900, 'loss/train': 0.5595437288284302} 08/31/2021 13:06:36 - INFO - __main__ - Step 131902: {'lr': 1.8224141993627153e-05, 'samples': 25325184, 'steps': 131901, 'loss/train': 2.071753978729248} 08/31/2021 13:06:36 - INFO - __main__ - Step 131903: {'lr': 1.8222153048426643e-05, 'samples': 25325376, 'steps': 131902, 'loss/train': 0.8396314978599548} 08/31/2021 13:06:37 - INFO - __main__ - Step 131904: {'lr': 1.822016420766165e-05, 'samples': 25325568, 'steps': 131903, 'loss/train': 0.12467140704393387} 08/31/2021 13:06:38 - INFO - __main__ - Step 131905: {'lr': 1.8218175471333116e-05, 'samples': 25325760, 'steps': 131904, 'loss/train': 1.967727780342102} 08/31/2021 13:06:39 - INFO - __main__ - Step 131906: {'lr': 1.8216186839441874e-05, 'samples': 25325952, 'steps': 131905, 'loss/train': 0.28121018409729004} 08/31/2021 13:06:39 - INFO - __main__ - Step 131907: {'lr': 1.821419831198881e-05, 'samples': 25326144, 'steps': 131906, 'loss/train': 0.9496452212333679} 08/31/2021 13:06:39 - INFO - __main__ - Step 131908: {'lr': 1.8212209888974874e-05, 'samples': 25326336, 'steps': 131907, 'loss/train': 1.4320323467254639} 08/31/2021 13:06:40 - INFO - __main__ - Step 131909: {'lr': 1.8210221570400946e-05, 'samples': 25326528, 'steps': 131908, 'loss/train': 1.507162094116211} 08/31/2021 13:06:41 - INFO - __main__ - Step 131910: {'lr': 1.8208233356267895e-05, 'samples': 25326720, 'steps': 131909, 'loss/train': 0.030145088210701942} 08/31/2021 13:06:42 - INFO - __main__ - Step 131911: {'lr': 1.820624524657666e-05, 'samples': 25326912, 'steps': 131910, 'loss/train': 1.751104474067688} 08/31/2021 13:06:42 - INFO - __main__ - Step 131912: {'lr': 1.82042572413281e-05, 'samples': 25327104, 'steps': 131911, 'loss/train': 0.9363206624984741} 08/31/2021 13:06:42 - INFO - __main__ - Step 131913: {'lr': 1.820226934052313e-05, 'samples': 25327296, 'steps': 131912, 'loss/train': 1.4959410429000854} 08/31/2021 13:06:43 - INFO - __main__ - Step 131914: {'lr': 1.8200281544162643e-05, 'samples': 25327488, 'steps': 131913, 'loss/train': 0.24432319402694702} 08/31/2021 13:06:43 - INFO - __main__ - Step 131915: {'lr': 1.819829385224753e-05, 'samples': 25327680, 'steps': 131914, 'loss/train': 0.9779714345932007} 08/31/2021 13:06:45 - INFO - __main__ - Step 131916: {'lr': 1.8196306264778722e-05, 'samples': 25327872, 'steps': 131915, 'loss/train': 1.4786949157714844} 08/31/2021 13:06:45 - INFO - __main__ - Step 131917: {'lr': 1.8194318781757036e-05, 'samples': 25328064, 'steps': 131916, 'loss/train': 2.1118342876434326} 08/31/2021 13:06:45 - INFO - __main__ - Step 131918: {'lr': 1.819233140318341e-05, 'samples': 25328256, 'steps': 131917, 'loss/train': 1.4267336130142212} 08/31/2021 13:06:46 - INFO - __main__ - Step 131919: {'lr': 1.8190344129058763e-05, 'samples': 25328448, 'steps': 131918, 'loss/train': 1.3442505598068237} 08/31/2021 13:06:46 - INFO - __main__ - Step 131920: {'lr': 1.818835695938395e-05, 'samples': 25328640, 'steps': 131919, 'loss/train': 1.372559905052185} 08/31/2021 13:06:48 - INFO - __main__ - Step 131921: {'lr': 1.818636989415992e-05, 'samples': 25328832, 'steps': 131920, 'loss/train': 0.9554638862609863} 08/31/2021 13:06:48 - INFO - __main__ - Step 131922: {'lr': 1.8184382933387505e-05, 'samples': 25329024, 'steps': 131921, 'loss/train': 1.2904787063598633} 08/31/2021 13:06:48 - INFO - __main__ - Step 131923: {'lr': 1.818239607706762e-05, 'samples': 25329216, 'steps': 131922, 'loss/train': 1.3049747943878174} 08/31/2021 13:06:49 - INFO - __main__ - Step 131924: {'lr': 1.8180409325201208e-05, 'samples': 25329408, 'steps': 131923, 'loss/train': 1.1019060611724854} 08/31/2021 13:06:49 - INFO - __main__ - Step 131925: {'lr': 1.8178422677789102e-05, 'samples': 25329600, 'steps': 131924, 'loss/train': 1.0787475109100342} 08/31/2021 13:06:51 - INFO - __main__ - Step 131926: {'lr': 1.8176436134832276e-05, 'samples': 25329792, 'steps': 131925, 'loss/train': 1.3290789127349854} 08/31/2021 13:06:51 - INFO - __main__ - Step 131927: {'lr': 1.8174449696331502e-05, 'samples': 25329984, 'steps': 131926, 'loss/train': 0.8928592801094055} 08/31/2021 13:06:51 - INFO - __main__ - Step 131928: {'lr': 1.8172463362287757e-05, 'samples': 25330176, 'steps': 131927, 'loss/train': 1.6578936576843262} 08/31/2021 13:06:52 - INFO - __main__ - Step 131929: {'lr': 1.8170477132701923e-05, 'samples': 25330368, 'steps': 131928, 'loss/train': 1.3159708976745605} 08/31/2021 13:06:52 - INFO - __main__ - Step 131930: {'lr': 1.8168491007574923e-05, 'samples': 25330560, 'steps': 131929, 'loss/train': 0.02117948792874813} 08/31/2021 13:06:54 - INFO - __main__ - Step 131931: {'lr': 1.8166504986907585e-05, 'samples': 25330752, 'steps': 131930, 'loss/train': 0.543733537197113} 08/31/2021 13:06:54 - INFO - __main__ - Step 131932: {'lr': 1.816451907070085e-05, 'samples': 25330944, 'steps': 131931, 'loss/train': 0.799592912197113} 08/31/2021 13:06:55 - INFO - __main__ - Step 131933: {'lr': 1.8162533258955615e-05, 'samples': 25331136, 'steps': 131932, 'loss/train': 1.2676640748977661} 08/31/2021 13:06:55 - INFO - __main__ - Step 131934: {'lr': 1.8160547551672764e-05, 'samples': 25331328, 'steps': 131933, 'loss/train': 1.354422926902771} 08/31/2021 13:06:55 - INFO - __main__ - Step 131935: {'lr': 1.815856194885318e-05, 'samples': 25331520, 'steps': 131934, 'loss/train': 1.1891041994094849} 08/31/2021 13:06:56 - INFO - __main__ - Step 131936: {'lr': 1.8156576450497786e-05, 'samples': 25331712, 'steps': 131935, 'loss/train': 0.6445114016532898} 08/31/2021 13:06:57 - INFO - __main__ - Step 131937: {'lr': 1.8154591056607465e-05, 'samples': 25331904, 'steps': 131936, 'loss/train': 1.029517412185669} 08/31/2021 13:06:58 - INFO - __main__ - Step 131938: {'lr': 1.8152605767183138e-05, 'samples': 25332096, 'steps': 131937, 'loss/train': 1.4513412714004517} 08/31/2021 13:06:58 - INFO - __main__ - Step 131939: {'lr': 1.8150620582225637e-05, 'samples': 25332288, 'steps': 131938, 'loss/train': 0.4006287157535553} 08/31/2021 13:06:58 - INFO - __main__ - Step 131940: {'lr': 1.814863550173587e-05, 'samples': 25332480, 'steps': 131939, 'loss/train': 1.4558185338974} 08/31/2021 13:06:59 - INFO - __main__ - Step 131941: {'lr': 1.8146650525714763e-05, 'samples': 25332672, 'steps': 131940, 'loss/train': 1.1596015691757202} 08/31/2021 13:07:00 - INFO - __main__ - Step 131942: {'lr': 1.81446656541632e-05, 'samples': 25332864, 'steps': 131941, 'loss/train': 1.3395531177520752} 08/31/2021 13:07:01 - INFO - __main__ - Step 131943: {'lr': 1.8142680887082068e-05, 'samples': 25333056, 'steps': 131942, 'loss/train': 1.0052437782287598} 08/31/2021 13:07:01 - INFO - __main__ - Step 131944: {'lr': 1.814069622447226e-05, 'samples': 25333248, 'steps': 131943, 'loss/train': 1.7181785106658936} 08/31/2021 13:07:01 - INFO - __main__ - Step 131945: {'lr': 1.8138711666334683e-05, 'samples': 25333440, 'steps': 131944, 'loss/train': 1.3754898309707642} 08/31/2021 13:07:02 - INFO - __main__ - Step 131946: {'lr': 1.8136727212670233e-05, 'samples': 25333632, 'steps': 131945, 'loss/train': 1.1497331857681274} 08/31/2021 13:07:04 - INFO - __main__ - Step 131947: {'lr': 1.81347428634798e-05, 'samples': 25333824, 'steps': 131946, 'loss/train': 0.6261321902275085} 08/31/2021 13:07:04 - INFO - __main__ - Step 131948: {'lr': 1.813275861876426e-05, 'samples': 25334016, 'steps': 131947, 'loss/train': 0.3734513223171234} 08/31/2021 13:07:04 - INFO - __main__ - Step 131949: {'lr': 1.8130774478524516e-05, 'samples': 25334208, 'steps': 131948, 'loss/train': 1.264323353767395} 08/31/2021 13:07:05 - INFO - __main__ - Step 131950: {'lr': 1.8128790442761473e-05, 'samples': 25334400, 'steps': 131949, 'loss/train': 1.195310354232788} 08/31/2021 13:07:05 - INFO - __main__ - Step 131951: {'lr': 1.8126806511476024e-05, 'samples': 25334592, 'steps': 131950, 'loss/train': 1.2755868434906006} 08/31/2021 13:07:07 - INFO - __main__ - Step 131952: {'lr': 1.8124822684669084e-05, 'samples': 25334784, 'steps': 131951, 'loss/train': 1.2586033344268799} 08/31/2021 13:07:07 - INFO - __main__ - Step 131953: {'lr': 1.8122838962341514e-05, 'samples': 25334976, 'steps': 131952, 'loss/train': 1.281411051750183} 08/31/2021 13:07:07 - INFO - __main__ - Step 131954: {'lr': 1.8120855344494176e-05, 'samples': 25335168, 'steps': 131953, 'loss/train': 1.0872032642364502} 08/31/2021 13:07:08 - INFO - __main__ - Step 131955: {'lr': 1.8118871831128038e-05, 'samples': 25335360, 'steps': 131954, 'loss/train': 0.9557384848594666} 08/31/2021 13:07:08 - INFO - __main__ - Step 131956: {'lr': 1.8116888422243932e-05, 'samples': 25335552, 'steps': 131955, 'loss/train': 0.5368139743804932} 08/31/2021 13:07:10 - INFO - __main__ - Step 131957: {'lr': 1.811490511784278e-05, 'samples': 25335744, 'steps': 131956, 'loss/train': 0.8011256456375122} 08/31/2021 13:07:10 - INFO - __main__ - Step 131958: {'lr': 1.811292191792549e-05, 'samples': 25335936, 'steps': 131957, 'loss/train': 1.2924609184265137} 08/31/2021 13:07:11 - INFO - __main__ - Step 131959: {'lr': 1.8110938822492902e-05, 'samples': 25336128, 'steps': 131958, 'loss/train': 1.0768318176269531} 08/31/2021 13:07:11 - INFO - __main__ - Step 131960: {'lr': 1.8108955831545982e-05, 'samples': 25336320, 'steps': 131959, 'loss/train': 1.0578241348266602} 08/31/2021 13:07:11 - INFO - __main__ - Step 131961: {'lr': 1.810697294508559e-05, 'samples': 25336512, 'steps': 131960, 'loss/train': 2.5645670890808105} 08/31/2021 13:07:12 - INFO - __main__ - Step 131962: {'lr': 1.8104990163112596e-05, 'samples': 25336704, 'steps': 131961, 'loss/train': 0.4023345112800598} 08/31/2021 13:07:13 - INFO - __main__ - Step 131963: {'lr': 1.810300748562793e-05, 'samples': 25336896, 'steps': 131962, 'loss/train': 1.3239141702651978} 08/31/2021 13:07:14 - INFO - __main__ - Step 131964: {'lr': 1.8101024912632465e-05, 'samples': 25337088, 'steps': 131963, 'loss/train': 1.1569406986236572} 08/31/2021 13:07:14 - INFO - __main__ - Step 131965: {'lr': 1.8099042444127135e-05, 'samples': 25337280, 'steps': 131964, 'loss/train': 0.8300301432609558} 08/31/2021 13:07:14 - INFO - __main__ - Step 131966: {'lr': 1.8097060080112776e-05, 'samples': 25337472, 'steps': 131965, 'loss/train': 1.065002202987671} 08/31/2021 13:07:15 - INFO - __main__ - Step 131967: {'lr': 1.809507782059028e-05, 'samples': 25337664, 'steps': 131966, 'loss/train': 1.0129997730255127} 08/31/2021 13:07:17 - INFO - __main__ - Step 131968: {'lr': 1.809309566556058e-05, 'samples': 25337856, 'steps': 131967, 'loss/train': 0.643561065196991} 08/31/2021 13:07:17 - INFO - __main__ - Step 131969: {'lr': 1.809111361502455e-05, 'samples': 25338048, 'steps': 131968, 'loss/train': 0.7618020176887512} 08/31/2021 13:07:17 - INFO - __main__ - Step 131970: {'lr': 1.8089131668983072e-05, 'samples': 25338240, 'steps': 131969, 'loss/train': 1.3267451524734497} 08/31/2021 13:07:18 - INFO - __main__ - Step 131971: {'lr': 1.808714982743706e-05, 'samples': 25338432, 'steps': 131970, 'loss/train': 1.401771903038025} 08/31/2021 13:07:18 - INFO - __main__ - Step 131972: {'lr': 1.8085168090387404e-05, 'samples': 25338624, 'steps': 131971, 'loss/train': 0.05791059508919716} 08/31/2021 13:07:18 - INFO - __main__ - Step 131973: {'lr': 1.8083186457834994e-05, 'samples': 25338816, 'steps': 131972, 'loss/train': 1.0689334869384766} 08/31/2021 13:07:20 - INFO - __main__ - Step 131974: {'lr': 1.8081204929780714e-05, 'samples': 25339008, 'steps': 131973, 'loss/train': 1.1331626176834106} 08/31/2021 13:07:20 - INFO - __main__ - Step 131975: {'lr': 1.8079223506225484e-05, 'samples': 25339200, 'steps': 131974, 'loss/train': 3.3159594535827637} 08/31/2021 13:07:21 - INFO - __main__ - Step 131976: {'lr': 1.8077242187170163e-05, 'samples': 25339392, 'steps': 131975, 'loss/train': 1.0203572511672974} 08/31/2021 13:07:21 - INFO - __main__ - Step 131977: {'lr': 1.8075260972615638e-05, 'samples': 25339584, 'steps': 131976, 'loss/train': 1.4164282083511353} 08/31/2021 13:07:21 - INFO - __main__ - Step 131978: {'lr': 1.8073279862562854e-05, 'samples': 25339776, 'steps': 131977, 'loss/train': 1.2778255939483643} 08/31/2021 13:07:23 - INFO - __main__ - Step 131979: {'lr': 1.80712988570127e-05, 'samples': 25339968, 'steps': 131978, 'loss/train': 1.1021928787231445} 08/31/2021 13:07:23 - INFO - __main__ - Step 131980: {'lr': 1.8069317955966002e-05, 'samples': 25340160, 'steps': 131979, 'loss/train': 1.245129108428955} 08/31/2021 13:07:24 - INFO - __main__ - Step 131981: {'lr': 1.8067337159423686e-05, 'samples': 25340352, 'steps': 131980, 'loss/train': 0.7572422623634338} 08/31/2021 13:07:24 - INFO - __main__ - Step 131982: {'lr': 1.8065356467386635e-05, 'samples': 25340544, 'steps': 131981, 'loss/train': 1.72640860080719} 08/31/2021 13:07:24 - INFO - __main__ - Step 131983: {'lr': 1.8063375879855764e-05, 'samples': 25340736, 'steps': 131982, 'loss/train': 0.6899793744087219} 08/31/2021 13:07:26 - INFO - __main__ - Step 131984: {'lr': 1.8061395396831964e-05, 'samples': 25340928, 'steps': 131983, 'loss/train': 0.9550428986549377} 08/31/2021 13:07:27 - INFO - __main__ - Step 131985: {'lr': 1.805941501831612e-05, 'samples': 25341120, 'steps': 131984, 'loss/train': 0.641219973564148} 08/31/2021 13:07:27 - INFO - __main__ - Step 131986: {'lr': 1.8057434744309125e-05, 'samples': 25341312, 'steps': 131985, 'loss/train': 1.3893935680389404} 08/31/2021 13:07:27 - INFO - __main__ - Step 131987: {'lr': 1.8055454574811863e-05, 'samples': 25341504, 'steps': 131986, 'loss/train': 1.7726374864578247} 08/31/2021 13:07:28 - INFO - __main__ - Step 131988: {'lr': 1.8053474509825253e-05, 'samples': 25341696, 'steps': 131987, 'loss/train': 1.8199660778045654} 08/31/2021 13:07:29 - INFO - __main__ - Step 131989: {'lr': 1.8051494549350152e-05, 'samples': 25341888, 'steps': 131988, 'loss/train': 0.8233417868614197} 08/31/2021 13:07:30 - INFO - __main__ - Step 131990: {'lr': 1.8049514693387475e-05, 'samples': 25342080, 'steps': 131989, 'loss/train': 0.8704140782356262} 08/31/2021 13:07:30 - INFO - __main__ - Step 131991: {'lr': 1.804753494193809e-05, 'samples': 25342272, 'steps': 131990, 'loss/train': 1.0048466920852661} 08/31/2021 13:07:30 - INFO - __main__ - Step 131992: {'lr': 1.8045555295002957e-05, 'samples': 25342464, 'steps': 131991, 'loss/train': 1.162663221359253} 08/31/2021 13:07:31 - INFO - __main__ - Step 131993: {'lr': 1.804357575258289e-05, 'samples': 25342656, 'steps': 131992, 'loss/train': 0.7560819387435913} 08/31/2021 13:07:33 - INFO - __main__ - Step 131994: {'lr': 1.8041596314678804e-05, 'samples': 25342848, 'steps': 131993, 'loss/train': 1.2311252355575562} 08/31/2021 13:07:33 - INFO - __main__ - Step 131995: {'lr': 1.8039616981291586e-05, 'samples': 25343040, 'steps': 131994, 'loss/train': 0.7196819186210632} 08/31/2021 13:07:33 - INFO - __main__ - Step 131996: {'lr': 1.8037637752422148e-05, 'samples': 25343232, 'steps': 131995, 'loss/train': 0.8749643564224243} 08/31/2021 13:07:34 - INFO - __main__ - Step 131997: {'lr': 1.8035658628071355e-05, 'samples': 25343424, 'steps': 131996, 'loss/train': 1.6275252103805542} 08/31/2021 13:07:34 - INFO - __main__ - Step 131998: {'lr': 1.803367960824012e-05, 'samples': 25343616, 'steps': 131997, 'loss/train': 0.0303500946611166} 08/31/2021 13:07:35 - INFO - __main__ - Step 131999: {'lr': 1.803170069292934e-05, 'samples': 25343808, 'steps': 131998, 'loss/train': 1.2217464447021484} 08/31/2021 13:07:36 - INFO - __main__ - Step 132000: {'lr': 1.8029721882139887e-05, 'samples': 25344000, 'steps': 131999, 'loss/train': 1.1268328428268433} 08/31/2021 13:07:37 - INFO - __main__ - Step 132001: {'lr': 1.8027743175872664e-05, 'samples': 25344192, 'steps': 132000, 'loss/train': 1.5029820203781128} 08/31/2021 13:07:37 - INFO - __main__ - Step 132002: {'lr': 1.802576457412858e-05, 'samples': 25344384, 'steps': 132001, 'loss/train': 0.8923114538192749} 08/31/2021 13:07:37 - INFO - __main__ - Step 132003: {'lr': 1.8023786076908495e-05, 'samples': 25344576, 'steps': 132002, 'loss/train': 1.0533270835876465} 08/31/2021 13:07:38 - INFO - __main__ - Step 132004: {'lr': 1.80218076842133e-05, 'samples': 25344768, 'steps': 132003, 'loss/train': 0.6186535358428955} 08/31/2021 13:07:40 - INFO - __main__ - Step 132005: {'lr': 1.8019829396043908e-05, 'samples': 25344960, 'steps': 132004, 'loss/train': 0.2287035584449768} 08/31/2021 13:07:40 - INFO - __main__ - Step 132006: {'lr': 1.8017851212401238e-05, 'samples': 25345152, 'steps': 132005, 'loss/train': 1.0621304512023926} 08/31/2021 13:07:41 - INFO - __main__ - Step 132007: {'lr': 1.8015873133286093e-05, 'samples': 25345344, 'steps': 132006, 'loss/train': 1.3073925971984863} 08/31/2021 13:07:41 - INFO - __main__ - Step 132008: {'lr': 1.8013895158699415e-05, 'samples': 25345536, 'steps': 132007, 'loss/train': 1.2482023239135742} 08/31/2021 13:07:41 - INFO - __main__ - Step 132009: {'lr': 1.8011917288642126e-05, 'samples': 25345728, 'steps': 132008, 'loss/train': 0.9604420065879822} 08/31/2021 13:07:43 - INFO - __main__ - Step 132010: {'lr': 1.8009939523115055e-05, 'samples': 25345920, 'steps': 132009, 'loss/train': 0.9089906811714172} 08/31/2021 13:07:43 - INFO - __main__ - Step 132011: {'lr': 1.8007961862119144e-05, 'samples': 25346112, 'steps': 132010, 'loss/train': 1.2555314302444458} 08/31/2021 13:07:44 - INFO - __main__ - Step 132012: {'lr': 1.800598430565528e-05, 'samples': 25346304, 'steps': 132011, 'loss/train': 0.7536947131156921} 08/31/2021 13:07:44 - INFO - __main__ - Step 132013: {'lr': 1.8004006853724303e-05, 'samples': 25346496, 'steps': 132012, 'loss/train': 0.6867766976356506} 08/31/2021 13:07:44 - INFO - __main__ - Step 132014: {'lr': 1.800202950632718e-05, 'samples': 25346688, 'steps': 132013, 'loss/train': 0.6940882802009583} 08/31/2021 13:07:45 - INFO - __main__ - Step 132015: {'lr': 1.800005226346474e-05, 'samples': 25346880, 'steps': 132014, 'loss/train': 1.7167720794677734} 08/31/2021 13:07:46 - INFO - __main__ - Step 132016: {'lr': 1.7998075125137874e-05, 'samples': 25347072, 'steps': 132015, 'loss/train': 0.29256993532180786} 08/31/2021 13:07:47 - INFO - __main__ - Step 132017: {'lr': 1.799609809134753e-05, 'samples': 25347264, 'steps': 132016, 'loss/train': 0.9434778094291687} 08/31/2021 13:07:47 - INFO - __main__ - Step 132018: {'lr': 1.7994121162094562e-05, 'samples': 25347456, 'steps': 132017, 'loss/train': 0.4951990842819214} 08/31/2021 13:07:47 - INFO - __main__ - Step 132019: {'lr': 1.799214433737989e-05, 'samples': 25347648, 'steps': 132018, 'loss/train': 2.183534622192383} 08/31/2021 13:07:48 - INFO - __main__ - Step 132020: {'lr': 1.7990167617204346e-05, 'samples': 25347840, 'steps': 132019, 'loss/train': 0.9479454755783081} 08/31/2021 13:07:49 - INFO - __main__ - Step 132021: {'lr': 1.7988191001568844e-05, 'samples': 25348032, 'steps': 132020, 'loss/train': 0.9582643508911133} 08/31/2021 13:07:50 - INFO - __main__ - Step 132022: {'lr': 1.7986214490474275e-05, 'samples': 25348224, 'steps': 132021, 'loss/train': 0.894944965839386} 08/31/2021 13:07:50 - INFO - __main__ - Step 132023: {'lr': 1.798423808392155e-05, 'samples': 25348416, 'steps': 132022, 'loss/train': 0.9501608610153198} 08/31/2021 13:07:50 - INFO - __main__ - Step 132024: {'lr': 1.7982261781911562e-05, 'samples': 25348608, 'steps': 132023, 'loss/train': 0.19561190903186798} 08/31/2021 13:07:51 - INFO - __main__ - Step 132025: {'lr': 1.798028558444517e-05, 'samples': 25348800, 'steps': 132024, 'loss/train': 1.1917396783828735} 08/31/2021 13:07:52 - INFO - __main__ - Step 132026: {'lr': 1.7978309491523294e-05, 'samples': 25348992, 'steps': 132025, 'loss/train': 0.7579261064529419} 08/31/2021 13:07:53 - INFO - __main__ - Step 132027: {'lr': 1.7976333503146786e-05, 'samples': 25349184, 'steps': 132026, 'loss/train': 1.1855106353759766} 08/31/2021 13:07:53 - INFO - __main__ - Step 132028: {'lr': 1.7974357619316567e-05, 'samples': 25349376, 'steps': 132027, 'loss/train': 0.30994635820388794} 08/31/2021 13:07:53 - INFO - __main__ - Step 132029: {'lr': 1.7972381840033554e-05, 'samples': 25349568, 'steps': 132028, 'loss/train': 1.027636170387268} 08/31/2021 13:07:54 - INFO - __main__ - Step 132030: {'lr': 1.7970406165298574e-05, 'samples': 25349760, 'steps': 132029, 'loss/train': 1.141902208328247} 08/31/2021 13:07:55 - INFO - __main__ - Step 132031: {'lr': 1.796843059511255e-05, 'samples': 25349952, 'steps': 132030, 'loss/train': 1.2148540019989014} 08/31/2021 13:07:56 - INFO - __main__ - Step 132032: {'lr': 1.7966455129476367e-05, 'samples': 25350144, 'steps': 132031, 'loss/train': 1.8184515237808228} 08/31/2021 13:07:56 - INFO - __main__ - Step 132033: {'lr': 1.796447976839097e-05, 'samples': 25350336, 'steps': 132032, 'loss/train': 1.543068289756775} 08/31/2021 13:07:57 - INFO - __main__ - Step 132034: {'lr': 1.796250451185716e-05, 'samples': 25350528, 'steps': 132033, 'loss/train': 0.6932801604270935} 08/31/2021 13:07:57 - INFO - __main__ - Step 132035: {'lr': 1.796052935987588e-05, 'samples': 25350720, 'steps': 132034, 'loss/train': 1.1414021253585815} 08/31/2021 13:07:57 - INFO - __main__ - Step 132036: {'lr': 1.7958554312447973e-05, 'samples': 25350912, 'steps': 132035, 'loss/train': 1.2618736028671265} 08/31/2021 13:07:59 - INFO - __main__ - Step 132037: {'lr': 1.7956579369574372e-05, 'samples': 25351104, 'steps': 132036, 'loss/train': 1.2289899587631226} 08/31/2021 13:07:59 - INFO - __main__ - Step 132038: {'lr': 1.7954604531255968e-05, 'samples': 25351296, 'steps': 132037, 'loss/train': 0.718460738658905} 08/31/2021 13:08:00 - INFO - __main__ - Step 132039: {'lr': 1.7952629797493623e-05, 'samples': 25351488, 'steps': 132038, 'loss/train': 1.476110816001892} 08/31/2021 13:08:00 - INFO - __main__ - Step 132040: {'lr': 1.7950655168288256e-05, 'samples': 25351680, 'steps': 132039, 'loss/train': 0.521622896194458} 08/31/2021 13:08:00 - INFO - __main__ - Step 132041: {'lr': 1.7948680643640718e-05, 'samples': 25351872, 'steps': 132040, 'loss/train': 0.9688041806221008} 08/31/2021 13:08:02 - INFO - __main__ - Step 132042: {'lr': 1.7946706223551963e-05, 'samples': 25352064, 'steps': 132041, 'loss/train': 1.3171533346176147} 08/31/2021 13:08:02 - INFO - __main__ - Step 132043: {'lr': 1.7944731908022815e-05, 'samples': 25352256, 'steps': 132042, 'loss/train': 0.3775561451911926} 08/31/2021 13:08:03 - INFO - __main__ - Step 132044: {'lr': 1.7942757697054196e-05, 'samples': 25352448, 'steps': 132043, 'loss/train': 1.0249333381652832} 08/31/2021 13:08:03 - INFO - __main__ - Step 132045: {'lr': 1.794078359064699e-05, 'samples': 25352640, 'steps': 132044, 'loss/train': 0.4847047030925751} 08/31/2021 13:08:03 - INFO - __main__ - Step 132046: {'lr': 1.793880958880212e-05, 'samples': 25352832, 'steps': 132045, 'loss/train': 0.7731539011001587} 08/31/2021 13:08:04 - INFO - __main__ - Step 132047: {'lr': 1.793683569152041e-05, 'samples': 25353024, 'steps': 132046, 'loss/train': 1.0743482112884521} 08/31/2021 13:08:06 - INFO - __main__ - Step 132048: {'lr': 1.7934861898802778e-05, 'samples': 25353216, 'steps': 132047, 'loss/train': 1.3533868789672852} 08/31/2021 13:08:06 - INFO - __main__ - Step 132049: {'lr': 1.7932888210650117e-05, 'samples': 25353408, 'steps': 132048, 'loss/train': 0.6988057494163513} 08/31/2021 13:08:06 - INFO - __main__ - Step 132050: {'lr': 1.7930914627063312e-05, 'samples': 25353600, 'steps': 132049, 'loss/train': 1.1145553588867188} 08/31/2021 13:08:07 - INFO - __main__ - Step 132051: {'lr': 1.792894114804325e-05, 'samples': 25353792, 'steps': 132050, 'loss/train': 1.725775122642517} 08/31/2021 13:08:07 - INFO - __main__ - Step 132052: {'lr': 1.792696777359082e-05, 'samples': 25353984, 'steps': 132051, 'loss/train': 0.30925750732421875} 08/31/2021 13:08:08 - INFO - __main__ - Step 132053: {'lr': 1.792499450370694e-05, 'samples': 25354176, 'steps': 132052, 'loss/train': 0.01435778010636568} 08/31/2021 13:08:09 - INFO - __main__ - Step 132054: {'lr': 1.7923021338392463e-05, 'samples': 25354368, 'steps': 132053, 'loss/train': 1.189440131187439} 08/31/2021 13:08:10 - INFO - __main__ - Step 132055: {'lr': 1.7921048277648287e-05, 'samples': 25354560, 'steps': 132054, 'loss/train': 0.7543658018112183} 08/31/2021 13:08:10 - INFO - __main__ - Step 132056: {'lr': 1.7919075321475327e-05, 'samples': 25354752, 'steps': 132055, 'loss/train': 0.4443310797214508} 08/31/2021 13:08:11 - INFO - __main__ - Step 132057: {'lr': 1.7917102469874435e-05, 'samples': 25354944, 'steps': 132056, 'loss/train': 0.11626391857862473} 08/31/2021 13:08:11 - INFO - __main__ - Step 132058: {'lr': 1.7915129722846506e-05, 'samples': 25355136, 'steps': 132057, 'loss/train': 0.01628744602203369} 08/31/2021 13:08:11 - INFO - __main__ - Step 132059: {'lr': 1.7913157080392513e-05, 'samples': 25355328, 'steps': 132058, 'loss/train': 0.7844157218933105} 08/31/2021 13:08:13 - INFO - __main__ - Step 132060: {'lr': 1.7911184542513197e-05, 'samples': 25355520, 'steps': 132059, 'loss/train': 1.3089556694030762} 08/31/2021 13:08:14 - INFO - __main__ - Step 132061: {'lr': 1.7909212109209538e-05, 'samples': 25355712, 'steps': 132060, 'loss/train': 1.5029957294464111} 08/31/2021 13:08:14 - INFO - __main__ - Step 132062: {'lr': 1.7907239780482392e-05, 'samples': 25355904, 'steps': 132061, 'loss/train': 1.439388632774353} 08/31/2021 13:08:14 - INFO - __main__ - Step 132063: {'lr': 1.790526755633268e-05, 'samples': 25356096, 'steps': 132062, 'loss/train': 0.9028120040893555} 08/31/2021 13:08:15 - INFO - __main__ - Step 132064: {'lr': 1.790329543676125e-05, 'samples': 25356288, 'steps': 132063, 'loss/train': 0.411072701215744} 08/31/2021 13:08:16 - INFO - __main__ - Step 132065: {'lr': 1.7901323421769035e-05, 'samples': 25356480, 'steps': 132064, 'loss/train': 2.2220680713653564} 08/31/2021 13:08:17 - INFO - __main__ - Step 132066: {'lr': 1.7899351511356883e-05, 'samples': 25356672, 'steps': 132065, 'loss/train': 1.4511758089065552} 08/31/2021 13:08:17 - INFO - __main__ - Step 132067: {'lr': 1.7897379705525714e-05, 'samples': 25356864, 'steps': 132066, 'loss/train': 0.9590438604354858} 08/31/2021 13:08:17 - INFO - __main__ - Step 132068: {'lr': 1.7895408004276388e-05, 'samples': 25357056, 'steps': 132067, 'loss/train': 1.3590677976608276} 08/31/2021 13:08:18 - INFO - __main__ - Step 132069: {'lr': 1.789343640760982e-05, 'samples': 25357248, 'steps': 132068, 'loss/train': 1.5393295288085938} 08/31/2021 13:08:19 - INFO - __main__ - Step 132070: {'lr': 1.78914649155269e-05, 'samples': 25357440, 'steps': 132069, 'loss/train': 1.5891082286834717} 08/31/2021 13:08:20 - INFO - __main__ - Step 132071: {'lr': 1.7889493528028487e-05, 'samples': 25357632, 'steps': 132070, 'loss/train': 0.9373564124107361} 08/31/2021 13:08:20 - INFO - __main__ - Step 132072: {'lr': 1.78875222451155e-05, 'samples': 25357824, 'steps': 132071, 'loss/train': 1.2613180875778198} 08/31/2021 13:08:21 - INFO - __main__ - Step 132073: {'lr': 1.7885551066788852e-05, 'samples': 25358016, 'steps': 132072, 'loss/train': 0.8408697843551636} 08/31/2021 13:08:21 - INFO - __main__ - Step 132074: {'lr': 1.7883579993049347e-05, 'samples': 25358208, 'steps': 132073, 'loss/train': 1.1794465780258179} 08/31/2021 13:08:22 - INFO - __main__ - Step 132075: {'lr': 1.7881609023897933e-05, 'samples': 25358400, 'steps': 132074, 'loss/train': 1.2594718933105469} 08/31/2021 13:08:23 - INFO - __main__ - Step 132076: {'lr': 1.7879638159335464e-05, 'samples': 25358592, 'steps': 132075, 'loss/train': 0.8499360680580139} 08/31/2021 13:08:23 - INFO - __main__ - Step 132077: {'lr': 1.787766739936286e-05, 'samples': 25358784, 'steps': 132076, 'loss/train': 0.8126567006111145} 08/31/2021 13:08:24 - INFO - __main__ - Step 132078: {'lr': 1.7875696743980986e-05, 'samples': 25358976, 'steps': 132077, 'loss/train': 1.565531849861145} 08/31/2021 13:08:24 - INFO - __main__ - Step 132079: {'lr': 1.787372619319075e-05, 'samples': 25359168, 'steps': 132078, 'loss/train': 0.043038446456193924} 08/31/2021 13:08:25 - INFO - __main__ - Step 132080: {'lr': 1.787175574699304e-05, 'samples': 25359360, 'steps': 132079, 'loss/train': 1.2209177017211914} 08/31/2021 13:08:26 - INFO - __main__ - Step 132081: {'lr': 1.7869785405388724e-05, 'samples': 25359552, 'steps': 132080, 'loss/train': 1.0173060894012451} 08/31/2021 13:08:26 - INFO - __main__ - Step 132082: {'lr': 1.786781516837868e-05, 'samples': 25359744, 'steps': 132081, 'loss/train': 0.5659456849098206} 08/31/2021 13:08:27 - INFO - __main__ - Step 132083: {'lr': 1.786584503596386e-05, 'samples': 25359936, 'steps': 132082, 'loss/train': 1.2194715738296509} 08/31/2021 13:08:27 - INFO - __main__ - Step 132084: {'lr': 1.786387500814507e-05, 'samples': 25360128, 'steps': 132083, 'loss/train': 1.274359941482544} 08/31/2021 13:08:29 - INFO - __main__ - Step 132085: {'lr': 1.786190508492325e-05, 'samples': 25360320, 'steps': 132084, 'loss/train': 1.1999635696411133} 08/31/2021 13:08:29 - INFO - __main__ - Step 132086: {'lr': 1.7859935266299336e-05, 'samples': 25360512, 'steps': 132085, 'loss/train': 0.026103589683771133} 08/31/2021 13:08:30 - INFO - __main__ - Step 132087: {'lr': 1.7857965552274093e-05, 'samples': 25360704, 'steps': 132086, 'loss/train': 0.014782857149839401} 08/31/2021 13:08:30 - INFO - __main__ - Step 132088: {'lr': 1.7855995942848453e-05, 'samples': 25360896, 'steps': 132087, 'loss/train': 1.1820029020309448} 08/31/2021 13:08:31 - INFO - __main__ - Step 132089: {'lr': 1.7854026438023336e-05, 'samples': 25361088, 'steps': 132088, 'loss/train': 0.8676671385765076} 08/31/2021 13:08:31 - INFO - __main__ - Step 132090: {'lr': 1.78520570377996e-05, 'samples': 25361280, 'steps': 132089, 'loss/train': 0.40853652358055115} 08/31/2021 13:08:31 - INFO - __main__ - Step 132091: {'lr': 1.7850087742178168e-05, 'samples': 25361472, 'steps': 132090, 'loss/train': 0.6597349643707275} 08/31/2021 13:08:33 - INFO - __main__ - Step 132092: {'lr': 1.7848118551159892e-05, 'samples': 25361664, 'steps': 132091, 'loss/train': 0.8600306510925293} 08/31/2021 13:08:33 - INFO - __main__ - Step 132093: {'lr': 1.7846149464745666e-05, 'samples': 25361856, 'steps': 132092, 'loss/train': 1.5928908586502075} 08/31/2021 13:08:34 - INFO - __main__ - Step 132094: {'lr': 1.78441804829364e-05, 'samples': 25362048, 'steps': 132093, 'loss/train': 0.46450507640838623} 08/31/2021 13:08:34 - INFO - __main__ - Step 132095: {'lr': 1.7842211605732932e-05, 'samples': 25362240, 'steps': 132094, 'loss/train': 1.2204965353012085} 08/31/2021 13:08:34 - INFO - __main__ - Step 132096: {'lr': 1.7840242833136207e-05, 'samples': 25362432, 'steps': 132095, 'loss/train': 0.23931194841861725} 08/31/2021 13:08:36 - INFO - __main__ - Step 132097: {'lr': 1.7838274165147078e-05, 'samples': 25362624, 'steps': 132096, 'loss/train': 0.9516996741294861} 08/31/2021 13:08:36 - INFO - __main__ - Step 132098: {'lr': 1.783630560176644e-05, 'samples': 25362816, 'steps': 132097, 'loss/train': 1.19821035861969} 08/31/2021 13:08:37 - INFO - __main__ - Step 132099: {'lr': 1.7834337142995178e-05, 'samples': 25363008, 'steps': 132098, 'loss/train': 0.9888350963592529} 08/31/2021 13:08:37 - INFO - __main__ - Step 132100: {'lr': 1.7832368788834236e-05, 'samples': 25363200, 'steps': 132099, 'loss/train': 1.2288217544555664} 08/31/2021 13:08:37 - INFO - __main__ - Step 132101: {'lr': 1.783040053928439e-05, 'samples': 25363392, 'steps': 132100, 'loss/train': 1.436952829360962} 08/31/2021 13:08:38 - INFO - __main__ - Step 132102: {'lr': 1.7828432394346588e-05, 'samples': 25363584, 'steps': 132101, 'loss/train': 1.1327636241912842} 08/31/2021 13:08:40 - INFO - __main__ - Step 132103: {'lr': 1.7826464354021714e-05, 'samples': 25363776, 'steps': 132102, 'loss/train': 0.945466935634613} 08/31/2021 13:08:40 - INFO - __main__ - Step 132104: {'lr': 1.782449641831066e-05, 'samples': 25363968, 'steps': 132103, 'loss/train': 1.472208857536316} 08/31/2021 13:08:40 - INFO - __main__ - Step 132105: {'lr': 1.7822528587214282e-05, 'samples': 25364160, 'steps': 132104, 'loss/train': 1.1381628513336182} 08/31/2021 13:08:41 - INFO - __main__ - Step 132106: {'lr': 1.7820560860733526e-05, 'samples': 25364352, 'steps': 132105, 'loss/train': 1.238558053970337} 08/31/2021 13:08:41 - INFO - __main__ - Step 132107: {'lr': 1.7818593238869197e-05, 'samples': 25364544, 'steps': 132106, 'loss/train': 0.10631534457206726} 08/31/2021 13:08:43 - INFO - __main__ - Step 132108: {'lr': 1.7816625721622265e-05, 'samples': 25364736, 'steps': 132107, 'loss/train': 0.652539849281311} 08/31/2021 13:08:43 - INFO - __main__ - Step 132109: {'lr': 1.7814658308993563e-05, 'samples': 25364928, 'steps': 132108, 'loss/train': 1.1952540874481201} 08/31/2021 13:08:43 - INFO - __main__ - Step 132110: {'lr': 1.7812691000983983e-05, 'samples': 25365120, 'steps': 132109, 'loss/train': 0.7235144972801208} 08/31/2021 13:08:44 - INFO - __main__ - Step 132111: {'lr': 1.7810723797594434e-05, 'samples': 25365312, 'steps': 132110, 'loss/train': 0.9591858983039856} 08/31/2021 13:08:44 - INFO - __main__ - Step 132112: {'lr': 1.7808756698825784e-05, 'samples': 25365504, 'steps': 132111, 'loss/train': 1.558395504951477} 08/31/2021 13:08:46 - INFO - __main__ - Step 132113: {'lr': 1.780678970467897e-05, 'samples': 25365696, 'steps': 132112, 'loss/train': 1.368787407875061} 08/31/2021 13:08:46 - INFO - __main__ - Step 132114: {'lr': 1.7804822815154804e-05, 'samples': 25365888, 'steps': 132113, 'loss/train': 0.02079012431204319} 08/31/2021 13:08:47 - INFO - __main__ - Step 132115: {'lr': 1.7802856030254196e-05, 'samples': 25366080, 'steps': 132114, 'loss/train': 0.8791067004203796} 08/31/2021 13:08:47 - INFO - __main__ - Step 132116: {'lr': 1.7800889349978033e-05, 'samples': 25366272, 'steps': 132115, 'loss/train': 0.9455243349075317} 08/31/2021 13:08:47 - INFO - __main__ - Step 132117: {'lr': 1.779892277432721e-05, 'samples': 25366464, 'steps': 132116, 'loss/train': 2.8863718509674072} 08/31/2021 13:08:49 - INFO - __main__ - Step 132118: {'lr': 1.779695630330261e-05, 'samples': 25366656, 'steps': 132117, 'loss/train': 0.6968713998794556} 08/31/2021 13:08:49 - INFO - __main__ - Step 132119: {'lr': 1.7794989936905093e-05, 'samples': 25366848, 'steps': 132118, 'loss/train': 0.1914796084165573} 08/31/2021 13:08:50 - INFO - __main__ - Step 132120: {'lr': 1.7793023675135607e-05, 'samples': 25367040, 'steps': 132119, 'loss/train': 1.4613986015319824} 08/31/2021 13:08:50 - INFO - __main__ - Step 132121: {'lr': 1.7791057517994978e-05, 'samples': 25367232, 'steps': 132120, 'loss/train': 1.0408047437667847} 08/31/2021 13:08:50 - INFO - __main__ - Step 132122: {'lr': 1.778909146548413e-05, 'samples': 25367424, 'steps': 132121, 'loss/train': 0.4713900089263916} 08/31/2021 13:08:52 - INFO - __main__ - Step 132123: {'lr': 1.778712551760392e-05, 'samples': 25367616, 'steps': 132122, 'loss/train': 1.1069258451461792} 08/31/2021 13:08:52 - INFO - __main__ - Step 132124: {'lr': 1.778515967435526e-05, 'samples': 25367808, 'steps': 132123, 'loss/train': 1.4021835327148438} 08/31/2021 13:08:53 - INFO - __main__ - Step 132125: {'lr': 1.778319393573902e-05, 'samples': 25368000, 'steps': 132124, 'loss/train': 1.7543859481811523} 08/31/2021 13:08:53 - INFO - __main__ - Step 132126: {'lr': 1.7781228301756102e-05, 'samples': 25368192, 'steps': 132125, 'loss/train': 1.1589523553848267} 08/31/2021 13:08:53 - INFO - __main__ - Step 132127: {'lr': 1.7779262772407407e-05, 'samples': 25368384, 'steps': 132126, 'loss/train': 1.185052752494812} 08/31/2021 13:08:54 - INFO - __main__ - Step 132128: {'lr': 1.777729734769373e-05, 'samples': 25368576, 'steps': 132127, 'loss/train': 0.8802003264427185} 08/31/2021 13:08:56 - INFO - __main__ - Step 132129: {'lr': 1.7775332027616052e-05, 'samples': 25368768, 'steps': 132128, 'loss/train': 1.030491590499878} 08/31/2021 13:08:56 - INFO - __main__ - Step 132130: {'lr': 1.7773366812175202e-05, 'samples': 25368960, 'steps': 132129, 'loss/train': 0.3040693402290344} 08/31/2021 13:08:56 - INFO - __main__ - Step 132131: {'lr': 1.777140170137212e-05, 'samples': 25369152, 'steps': 132130, 'loss/train': 1.3125056028366089} 08/31/2021 13:08:57 - INFO - __main__ - Step 132132: {'lr': 1.7769436695207643e-05, 'samples': 25369344, 'steps': 132131, 'loss/train': 1.1125195026397705} 08/31/2021 13:08:57 - INFO - __main__ - Step 132133: {'lr': 1.776747179368268e-05, 'samples': 25369536, 'steps': 132132, 'loss/train': 0.7219323515892029} 08/31/2021 13:08:59 - INFO - __main__ - Step 132134: {'lr': 1.7765506996798104e-05, 'samples': 25369728, 'steps': 132133, 'loss/train': 1.3189913034439087} 08/31/2021 13:08:59 - INFO - __main__ - Step 132135: {'lr': 1.776354230455479e-05, 'samples': 25369920, 'steps': 132134, 'loss/train': 1.154052495956421} 08/31/2021 13:09:00 - INFO - __main__ - Step 132136: {'lr': 1.7761577716953664e-05, 'samples': 25370112, 'steps': 132135, 'loss/train': 1.376076102256775} 08/31/2021 13:09:00 - INFO - __main__ - Step 132137: {'lr': 1.775961323399558e-05, 'samples': 25370304, 'steps': 132136, 'loss/train': 1.3484033346176147} 08/31/2021 13:09:00 - INFO - __main__ - Step 132138: {'lr': 1.775764885568143e-05, 'samples': 25370496, 'steps': 132137, 'loss/train': 1.0756407976150513} 08/31/2021 13:09:01 - INFO - __main__ - Step 132139: {'lr': 1.77556845820121e-05, 'samples': 25370688, 'steps': 132138, 'loss/train': 1.4087798595428467} 08/31/2021 13:09:02 - INFO - __main__ - Step 132140: {'lr': 1.7753720412988532e-05, 'samples': 25370880, 'steps': 132139, 'loss/train': 1.9035162925720215} 08/31/2021 13:09:03 - INFO - __main__ - Step 132141: {'lr': 1.775175634861148e-05, 'samples': 25371072, 'steps': 132140, 'loss/train': 1.225500464439392} 08/31/2021 13:09:03 - INFO - __main__ - Step 132142: {'lr': 1.7749792388881942e-05, 'samples': 25371264, 'steps': 132141, 'loss/train': 0.7402002215385437} 08/31/2021 13:09:03 - INFO - __main__ - Step 132143: {'lr': 1.7747828533800746e-05, 'samples': 25371456, 'steps': 132142, 'loss/train': 1.0800021886825562} 08/31/2021 13:09:04 - INFO - __main__ - Step 132144: {'lr': 1.7745864783368786e-05, 'samples': 25371648, 'steps': 132143, 'loss/train': 0.5513300895690918} 08/31/2021 13:09:05 - INFO - __main__ - Step 132145: {'lr': 1.7743901137586947e-05, 'samples': 25371840, 'steps': 132144, 'loss/train': 0.662759006023407} 08/31/2021 13:09:06 - INFO - __main__ - Step 132146: {'lr': 1.7741937596456147e-05, 'samples': 25372032, 'steps': 132145, 'loss/train': 1.0111407041549683} 08/31/2021 13:09:06 - INFO - __main__ - Step 132147: {'lr': 1.7739974159977244e-05, 'samples': 25372224, 'steps': 132146, 'loss/train': 0.615362286567688} 08/31/2021 13:09:07 - INFO - __main__ - Step 132148: {'lr': 1.77380108281511e-05, 'samples': 25372416, 'steps': 132147, 'loss/train': 0.9670476317405701} 08/31/2021 13:09:07 - INFO - __main__ - Step 132149: {'lr': 1.773604760097866e-05, 'samples': 25372608, 'steps': 132148, 'loss/train': 0.9643779993057251} 08/31/2021 13:09:09 - INFO - __main__ - Step 132150: {'lr': 1.7734084478460756e-05, 'samples': 25372800, 'steps': 132149, 'loss/train': 0.5625936388969421} 08/31/2021 13:09:09 - INFO - __main__ - Step 132151: {'lr': 1.773212146059827e-05, 'samples': 25372992, 'steps': 132150, 'loss/train': 0.8629644513130188} 08/31/2021 13:09:10 - INFO - __main__ - Step 132152: {'lr': 1.7730158547392156e-05, 'samples': 25373184, 'steps': 132151, 'loss/train': 1.1626073122024536} 08/31/2021 13:09:10 - INFO - __main__ - Step 132153: {'lr': 1.772819573884324e-05, 'samples': 25373376, 'steps': 132152, 'loss/train': 0.05176611244678497} 08/31/2021 13:09:10 - INFO - __main__ - Step 132154: {'lr': 1.772623303495238e-05, 'samples': 25373568, 'steps': 132153, 'loss/train': 1.1801438331604004} 08/31/2021 13:09:11 - INFO - __main__ - Step 132155: {'lr': 1.77242704357205e-05, 'samples': 25373760, 'steps': 132154, 'loss/train': 0.8672313094139099} 08/31/2021 13:09:14 - INFO - __main__ - Step 132156: {'lr': 1.7722307941148486e-05, 'samples': 25373952, 'steps': 132155, 'loss/train': 1.5765104293823242} 08/31/2021 13:09:14 - INFO - __main__ - Step 132157: {'lr': 1.772034555123722e-05, 'samples': 25374144, 'steps': 132156, 'loss/train': 0.8606321215629578} 08/31/2021 13:09:15 - INFO - __main__ - Step 132158: {'lr': 1.771838326598757e-05, 'samples': 25374336, 'steps': 132157, 'loss/train': 0.13878756761550903} 08/31/2021 13:09:15 - INFO - __main__ - Step 132159: {'lr': 1.7716421085400446e-05, 'samples': 25374528, 'steps': 132158, 'loss/train': 0.137595996260643} 08/31/2021 13:09:15 - INFO - __main__ - Step 132160: {'lr': 1.7714459009476712e-05, 'samples': 25374720, 'steps': 132159, 'loss/train': 1.0864466428756714} 08/31/2021 13:09:16 - INFO - __main__ - Step 132161: {'lr': 1.7712497038217258e-05, 'samples': 25374912, 'steps': 132160, 'loss/train': 0.7940661311149597} 08/31/2021 13:09:17 - INFO - __main__ - Step 132162: {'lr': 1.7710535171622992e-05, 'samples': 25375104, 'steps': 132161, 'loss/train': 0.2850620746612549} 08/31/2021 13:09:17 - INFO - __main__ - Step 132163: {'lr': 1.7708573409694757e-05, 'samples': 25375296, 'steps': 132162, 'loss/train': 0.030084097757935524} 08/31/2021 13:09:18 - INFO - __main__ - Step 132164: {'lr': 1.770661175243346e-05, 'samples': 25375488, 'steps': 132163, 'loss/train': 1.4779822826385498} 08/31/2021 13:09:18 - INFO - __main__ - Step 132165: {'lr': 1.7704650199839968e-05, 'samples': 25375680, 'steps': 132164, 'loss/train': 1.1569730043411255} 08/31/2021 13:09:19 - INFO - __main__ - Step 132166: {'lr': 1.7702688751915165e-05, 'samples': 25375872, 'steps': 132165, 'loss/train': 1.1733366250991821} 08/31/2021 13:09:20 - INFO - __main__ - Step 132167: {'lr': 1.770072740865997e-05, 'samples': 25376064, 'steps': 132166, 'loss/train': 1.0793793201446533} 08/31/2021 13:09:21 - INFO - __main__ - Step 132168: {'lr': 1.7698766170075208e-05, 'samples': 25376256, 'steps': 132167, 'loss/train': 0.9237277507781982} 08/31/2021 13:09:21 - INFO - __main__ - Step 132169: {'lr': 1.7696805036161832e-05, 'samples': 25376448, 'steps': 132168, 'loss/train': 1.2569035291671753} 08/31/2021 13:09:21 - INFO - __main__ - Step 132170: {'lr': 1.7694844006920675e-05, 'samples': 25376640, 'steps': 132169, 'loss/train': 1.21005380153656} 08/31/2021 13:09:22 - INFO - __main__ - Step 132171: {'lr': 1.7692883082352617e-05, 'samples': 25376832, 'steps': 132170, 'loss/train': 1.8407313823699951} 08/31/2021 13:09:22 - INFO - __main__ - Step 132172: {'lr': 1.7690922262458607e-05, 'samples': 25377024, 'steps': 132171, 'loss/train': 1.0085023641586304} 08/31/2021 13:09:24 - INFO - __main__ - Step 132173: {'lr': 1.768896154723948e-05, 'samples': 25377216, 'steps': 132172, 'loss/train': 0.9486353993415833} 08/31/2021 13:09:24 - INFO - __main__ - Step 132174: {'lr': 1.768700093669612e-05, 'samples': 25377408, 'steps': 132173, 'loss/train': 0.06295021623373032} 08/31/2021 13:09:25 - INFO - __main__ - Step 132175: {'lr': 1.7685040430829387e-05, 'samples': 25377600, 'steps': 132174, 'loss/train': 1.2630504369735718} 08/31/2021 13:09:25 - INFO - __main__ - Step 132176: {'lr': 1.7683080029640196e-05, 'samples': 25377792, 'steps': 132175, 'loss/train': 0.8460376858711243} 08/31/2021 13:09:25 - INFO - __main__ - Step 132177: {'lr': 1.7681119733129413e-05, 'samples': 25377984, 'steps': 132176, 'loss/train': 1.2282644510269165} 08/31/2021 13:09:27 - INFO - __main__ - Step 132178: {'lr': 1.767915954129795e-05, 'samples': 25378176, 'steps': 132177, 'loss/train': 0.8595513105392456} 08/31/2021 13:09:27 - INFO - __main__ - Step 132179: {'lr': 1.767719945414667e-05, 'samples': 25378368, 'steps': 132178, 'loss/train': 0.5558918118476868} 08/31/2021 13:09:27 - INFO - __main__ - Step 132180: {'lr': 1.7675239471676456e-05, 'samples': 25378560, 'steps': 132179, 'loss/train': 1.305293083190918} 08/31/2021 13:09:28 - INFO - __main__ - Step 132181: {'lr': 1.7673279593888174e-05, 'samples': 25378752, 'steps': 132180, 'loss/train': 0.4577755331993103} 08/31/2021 13:09:28 - INFO - __main__ - Step 132182: {'lr': 1.7671319820782766e-05, 'samples': 25378944, 'steps': 132181, 'loss/train': 1.0001603364944458} 08/31/2021 13:09:30 - INFO - __main__ - Step 132183: {'lr': 1.7669360152361062e-05, 'samples': 25379136, 'steps': 132182, 'loss/train': 0.9641929268836975} 08/31/2021 13:09:30 - INFO - __main__ - Step 132184: {'lr': 1.7667400588623984e-05, 'samples': 25379328, 'steps': 132183, 'loss/train': 1.038386583328247} 08/31/2021 13:09:30 - INFO - __main__ - Step 132185: {'lr': 1.766544112957236e-05, 'samples': 25379520, 'steps': 132184, 'loss/train': 1.386222243309021} 08/31/2021 13:09:31 - INFO - __main__ - Step 132186: {'lr': 1.76634817752071e-05, 'samples': 25379712, 'steps': 132185, 'loss/train': 0.3552995026111603} 08/31/2021 13:09:31 - INFO - __main__ - Step 132187: {'lr': 1.7661522525529107e-05, 'samples': 25379904, 'steps': 132186, 'loss/train': 1.810056209564209} 08/31/2021 13:09:33 - INFO - __main__ - Step 132188: {'lr': 1.765956338053923e-05, 'samples': 25380096, 'steps': 132187, 'loss/train': 1.45790433883667} 08/31/2021 13:09:33 - INFO - __main__ - Step 132189: {'lr': 1.765760434023836e-05, 'samples': 25380288, 'steps': 132188, 'loss/train': 1.6108059883117676} 08/31/2021 13:09:34 - INFO - __main__ - Step 132190: {'lr': 1.7655645404627412e-05, 'samples': 25380480, 'steps': 132189, 'loss/train': 1.6698259115219116} 08/31/2021 13:09:34 - INFO - __main__ - Step 132191: {'lr': 1.765368657370722e-05, 'samples': 25380672, 'steps': 132190, 'loss/train': 1.3380992412567139} 08/31/2021 13:09:34 - INFO - __main__ - Step 132192: {'lr': 1.7651727847478703e-05, 'samples': 25380864, 'steps': 132191, 'loss/train': 1.5472652912139893} 08/31/2021 13:09:36 - INFO - __main__ - Step 132193: {'lr': 1.7649769225942746e-05, 'samples': 25381056, 'steps': 132192, 'loss/train': 0.7346754670143127} 08/31/2021 13:09:36 - INFO - __main__ - Step 132194: {'lr': 1.764781070910021e-05, 'samples': 25381248, 'steps': 132193, 'loss/train': 2.019416093826294} 08/31/2021 13:09:37 - INFO - __main__ - Step 132195: {'lr': 1.764585229695201e-05, 'samples': 25381440, 'steps': 132194, 'loss/train': 1.3132222890853882} 08/31/2021 13:09:37 - INFO - __main__ - Step 132196: {'lr': 1.7643893989498976e-05, 'samples': 25381632, 'steps': 132195, 'loss/train': 0.9554259777069092} 08/31/2021 13:09:38 - INFO - __main__ - Step 132197: {'lr': 1.7641935786742003e-05, 'samples': 25381824, 'steps': 132196, 'loss/train': 1.6236168146133423} 08/31/2021 13:09:38 - INFO - __main__ - Step 132198: {'lr': 1.7639977688682002e-05, 'samples': 25382016, 'steps': 132197, 'loss/train': 0.2114720195531845} 08/31/2021 13:09:39 - INFO - __main__ - Step 132199: {'lr': 1.7638019695319834e-05, 'samples': 25382208, 'steps': 132198, 'loss/train': 0.4183099865913391} 08/31/2021 13:09:40 - INFO - __main__ - Step 132200: {'lr': 1.7636061806656417e-05, 'samples': 25382400, 'steps': 132199, 'loss/train': 0.024595215916633606} 08/31/2021 13:09:40 - INFO - __main__ - Step 132201: {'lr': 1.763410402269258e-05, 'samples': 25382592, 'steps': 132200, 'loss/train': 1.0389316082000732} 08/31/2021 13:09:41 - INFO - __main__ - Step 132202: {'lr': 1.7632146343429216e-05, 'samples': 25382784, 'steps': 132201, 'loss/train': 3.6777093410491943} 08/31/2021 13:09:41 - INFO - __main__ - Step 132203: {'lr': 1.763018876886724e-05, 'samples': 25382976, 'steps': 132202, 'loss/train': 1.503636360168457} 08/31/2021 13:09:43 - INFO - __main__ - Step 132204: {'lr': 1.7628231299007536e-05, 'samples': 25383168, 'steps': 132203, 'loss/train': 2.24448561668396} 08/31/2021 13:09:43 - INFO - __main__ - Step 132205: {'lr': 1.7626273933850938e-05, 'samples': 25383360, 'steps': 132204, 'loss/train': 1.2551050186157227} 08/31/2021 13:09:44 - INFO - __main__ - Step 132206: {'lr': 1.7624316673398366e-05, 'samples': 25383552, 'steps': 132205, 'loss/train': 0.013111389242112637} 08/31/2021 13:09:44 - INFO - __main__ - Step 132207: {'lr': 1.7622359517650705e-05, 'samples': 25383744, 'steps': 132206, 'loss/train': 1.0586297512054443} 08/31/2021 13:09:44 - INFO - __main__ - Step 132208: {'lr': 1.7620402466608814e-05, 'samples': 25383936, 'steps': 132207, 'loss/train': 1.1486642360687256} 08/31/2021 13:09:45 - INFO - __main__ - Step 132209: {'lr': 1.7618445520273556e-05, 'samples': 25384128, 'steps': 132208, 'loss/train': 1.1108026504516602} 08/31/2021 13:09:46 - INFO - __main__ - Step 132210: {'lr': 1.7616488678645874e-05, 'samples': 25384320, 'steps': 132209, 'loss/train': 0.7800815105438232} 08/31/2021 13:09:47 - INFO - __main__ - Step 132211: {'lr': 1.7614531941726603e-05, 'samples': 25384512, 'steps': 132210, 'loss/train': 0.8637086153030396} 08/31/2021 13:09:47 - INFO - __main__ - Step 132212: {'lr': 1.7612575309516626e-05, 'samples': 25384704, 'steps': 132211, 'loss/train': 0.5105915069580078} 08/31/2021 13:09:48 - INFO - __main__ - Step 132213: {'lr': 1.7610618782016836e-05, 'samples': 25384896, 'steps': 132212, 'loss/train': 0.828393816947937} 08/31/2021 13:09:48 - INFO - __main__ - Step 132214: {'lr': 1.7608662359228146e-05, 'samples': 25385088, 'steps': 132213, 'loss/train': 1.215999960899353} 08/31/2021 13:09:50 - INFO - __main__ - Step 132215: {'lr': 1.7606706041151387e-05, 'samples': 25385280, 'steps': 132214, 'loss/train': 0.7819182872772217} 08/31/2021 13:09:51 - INFO - __main__ - Step 132216: {'lr': 1.7604749827787452e-05, 'samples': 25385472, 'steps': 132215, 'loss/train': 1.01192307472229} 08/31/2021 13:09:51 - INFO - __main__ - Step 132217: {'lr': 1.7602793719137228e-05, 'samples': 25385664, 'steps': 132216, 'loss/train': 1.35538649559021} 08/31/2021 13:09:51 - INFO - __main__ - Step 132218: {'lr': 1.76008377152016e-05, 'samples': 25385856, 'steps': 132217, 'loss/train': 1.2208737134933472} 08/31/2021 13:09:52 - INFO - __main__ - Step 132219: {'lr': 1.759888181598146e-05, 'samples': 25386048, 'steps': 132218, 'loss/train': 1.3837937116622925} 08/31/2021 13:09:53 - INFO - __main__ - Step 132220: {'lr': 1.7596926021477695e-05, 'samples': 25386240, 'steps': 132219, 'loss/train': 1.3171483278274536} 08/31/2021 13:09:54 - INFO - __main__ - Step 132221: {'lr': 1.7594970331691192e-05, 'samples': 25386432, 'steps': 132220, 'loss/train': 0.021025588735938072} 08/31/2021 13:09:54 - INFO - __main__ - Step 132222: {'lr': 1.7593014746622755e-05, 'samples': 25386624, 'steps': 132221, 'loss/train': 0.014930391684174538} 08/31/2021 13:09:55 - INFO - __main__ - Step 132223: {'lr': 1.7591059266273328e-05, 'samples': 25386816, 'steps': 132222, 'loss/train': 1.1902422904968262} 08/31/2021 13:09:55 - INFO - __main__ - Step 132224: {'lr': 1.7589103890643776e-05, 'samples': 25387008, 'steps': 132223, 'loss/train': 1.3094537258148193} 08/31/2021 13:09:56 - INFO - __main__ - Step 132225: {'lr': 1.758714861973501e-05, 'samples': 25387200, 'steps': 132224, 'loss/train': 1.0978955030441284} 08/31/2021 13:09:57 - INFO - __main__ - Step 132226: {'lr': 1.7585193453547864e-05, 'samples': 25387392, 'steps': 132225, 'loss/train': 0.7505710124969482} 08/31/2021 13:09:58 - INFO - __main__ - Step 132227: {'lr': 1.7583238392083256e-05, 'samples': 25387584, 'steps': 132226, 'loss/train': 1.0895344018936157} 08/31/2021 13:09:58 - INFO - __main__ - Step 132228: {'lr': 1.7581283435342044e-05, 'samples': 25387776, 'steps': 132227, 'loss/train': 1.4739412069320679} 08/31/2021 13:09:58 - INFO - __main__ - Step 132229: {'lr': 1.7579328583325142e-05, 'samples': 25387968, 'steps': 132228, 'loss/train': 0.8880707621574402} 08/31/2021 13:09:59 - INFO - __main__ - Step 132230: {'lr': 1.757737383603339e-05, 'samples': 25388160, 'steps': 132229, 'loss/train': 0.8216544985771179} 08/31/2021 13:10:01 - INFO - __main__ - Step 132231: {'lr': 1.7575419193467695e-05, 'samples': 25388352, 'steps': 132230, 'loss/train': 0.47931912541389465} 08/31/2021 13:10:01 - INFO - __main__ - Step 132232: {'lr': 1.7573464655628924e-05, 'samples': 25388544, 'steps': 132231, 'loss/train': 2.210458993911743} 08/31/2021 13:10:01 - INFO - __main__ - Step 132233: {'lr': 1.757151022251796e-05, 'samples': 25388736, 'steps': 132232, 'loss/train': 0.01600511372089386} 08/31/2021 13:10:02 - INFO - __main__ - Step 132234: {'lr': 1.7569555894135723e-05, 'samples': 25388928, 'steps': 132233, 'loss/train': 0.39043113589286804} 08/31/2021 13:10:02 - INFO - __main__ - Step 132235: {'lr': 1.7567601670483048e-05, 'samples': 25389120, 'steps': 132234, 'loss/train': 0.41035211086273193} 08/31/2021 13:10:02 - INFO - __main__ - Step 132236: {'lr': 1.7565647551560786e-05, 'samples': 25389312, 'steps': 132235, 'loss/train': 1.2868627309799194} 08/31/2021 13:10:03 - INFO - __main__ - Step 132237: {'lr': 1.756369353736989e-05, 'samples': 25389504, 'steps': 132236, 'loss/train': 1.918114185333252} 08/31/2021 13:10:04 - INFO - __main__ - Step 132238: {'lr': 1.7561739627911187e-05, 'samples': 25389696, 'steps': 132237, 'loss/train': 1.1424071788787842} 08/31/2021 13:10:05 - INFO - __main__ - Step 132239: {'lr': 1.755978582318557e-05, 'samples': 25389888, 'steps': 132238, 'loss/train': 1.223218321800232} 08/31/2021 13:10:05 - INFO - __main__ - Step 132240: {'lr': 1.755783212319395e-05, 'samples': 25390080, 'steps': 132239, 'loss/train': 0.9785767197608948} 08/31/2021 13:10:06 - INFO - __main__ - Step 132241: {'lr': 1.7555878527937163e-05, 'samples': 25390272, 'steps': 132240, 'loss/train': 1.8328460454940796} 08/31/2021 13:10:06 - INFO - __main__ - Step 132242: {'lr': 1.7553925037416125e-05, 'samples': 25390464, 'steps': 132241, 'loss/train': 0.18283025920391083} 08/31/2021 13:10:08 - INFO - __main__ - Step 132243: {'lr': 1.7551971651631694e-05, 'samples': 25390656, 'steps': 132242, 'loss/train': 1.1267623901367188} 08/31/2021 13:10:08 - INFO - __main__ - Step 132244: {'lr': 1.7550018370584757e-05, 'samples': 25390848, 'steps': 132243, 'loss/train': 0.9555949568748474} 08/31/2021 13:10:09 - INFO - __main__ - Step 132245: {'lr': 1.754806519427621e-05, 'samples': 25391040, 'steps': 132244, 'loss/train': 5.4882121086120605} 08/31/2021 13:10:09 - INFO - __main__ - Step 132246: {'lr': 1.7546112122706903e-05, 'samples': 25391232, 'steps': 132245, 'loss/train': 1.005050539970398} 08/31/2021 13:10:10 - INFO - __main__ - Step 132247: {'lr': 1.754415915587773e-05, 'samples': 25391424, 'steps': 132246, 'loss/train': 0.5500733256340027} 08/31/2021 13:10:10 - INFO - __main__ - Step 132248: {'lr': 1.754220629378961e-05, 'samples': 25391616, 'steps': 132247, 'loss/train': 0.014655143022537231} 08/31/2021 13:10:12 - INFO - __main__ - Step 132249: {'lr': 1.754025353644334e-05, 'samples': 25391808, 'steps': 132248, 'loss/train': 1.262817144393921} 08/31/2021 13:10:12 - INFO - __main__ - Step 132250: {'lr': 1.753830088383987e-05, 'samples': 25392000, 'steps': 132249, 'loss/train': 1.0775270462036133} 08/31/2021 13:10:12 - INFO - __main__ - Step 132251: {'lr': 1.7536348335980028e-05, 'samples': 25392192, 'steps': 132250, 'loss/train': 0.5657910108566284} 08/31/2021 13:10:13 - INFO - __main__ - Step 132252: {'lr': 1.7534395892864734e-05, 'samples': 25392384, 'steps': 132251, 'loss/train': 0.5288230180740356} 08/31/2021 13:10:13 - INFO - __main__ - Step 132253: {'lr': 1.7532443554494848e-05, 'samples': 25392576, 'steps': 132252, 'loss/train': 1.1339304447174072} 08/31/2021 13:10:13 - INFO - __main__ - Step 132254: {'lr': 1.7530491320871256e-05, 'samples': 25392768, 'steps': 132253, 'loss/train': 0.7770466208457947} 08/31/2021 13:10:15 - INFO - __main__ - Step 132255: {'lr': 1.7528539191994847e-05, 'samples': 25392960, 'steps': 132254, 'loss/train': 1.0525366067886353} 08/31/2021 13:10:15 - INFO - __main__ - Step 132256: {'lr': 1.752658716786648e-05, 'samples': 25393152, 'steps': 132255, 'loss/train': 1.3945335149765015} 08/31/2021 13:10:16 - INFO - __main__ - Step 132257: {'lr': 1.7524635248487046e-05, 'samples': 25393344, 'steps': 132256, 'loss/train': 0.8133344054222107} 08/31/2021 13:10:16 - INFO - __main__ - Step 132258: {'lr': 1.7522683433857432e-05, 'samples': 25393536, 'steps': 132257, 'loss/train': 0.5832732915878296} 08/31/2021 13:10:16 - INFO - __main__ - Step 132259: {'lr': 1.75207317239785e-05, 'samples': 25393728, 'steps': 132258, 'loss/train': 1.3158690929412842} 08/31/2021 13:10:18 - INFO - __main__ - Step 132260: {'lr': 1.7518780118851165e-05, 'samples': 25393920, 'steps': 132259, 'loss/train': 1.1896307468414307} 08/31/2021 13:10:19 - INFO - __main__ - Step 132261: {'lr': 1.7516828618476283e-05, 'samples': 25394112, 'steps': 132260, 'loss/train': 1.1791819334030151} 08/31/2021 13:10:19 - INFO - __main__ - Step 132262: {'lr': 1.751487722285472e-05, 'samples': 25394304, 'steps': 132261, 'loss/train': 1.4744664430618286} 08/31/2021 13:10:19 - INFO - __main__ - Step 132263: {'lr': 1.751292593198736e-05, 'samples': 25394496, 'steps': 132262, 'loss/train': 1.5898922681808472} 08/31/2021 13:10:20 - INFO - __main__ - Step 132264: {'lr': 1.751097474587507e-05, 'samples': 25394688, 'steps': 132263, 'loss/train': 0.027370410040020943} 08/31/2021 13:10:21 - INFO - __main__ - Step 132265: {'lr': 1.7509023664518758e-05, 'samples': 25394880, 'steps': 132264, 'loss/train': 0.38548916578292847} 08/31/2021 13:10:21 - INFO - __main__ - Step 132266: {'lr': 1.750707268791929e-05, 'samples': 25395072, 'steps': 132265, 'loss/train': 1.1933939456939697} 08/31/2021 13:10:22 - INFO - __main__ - Step 132267: {'lr': 1.7505121816077552e-05, 'samples': 25395264, 'steps': 132266, 'loss/train': 1.6178719997406006} 08/31/2021 13:10:22 - INFO - __main__ - Step 132268: {'lr': 1.750317104899443e-05, 'samples': 25395456, 'steps': 132267, 'loss/train': 1.213036060333252} 08/31/2021 13:10:23 - INFO - __main__ - Step 132269: {'lr': 1.7501220386670763e-05, 'samples': 25395648, 'steps': 132268, 'loss/train': 1.6015173196792603} 08/31/2021 13:10:25 - INFO - __main__ - Step 132270: {'lr': 1.749926982910749e-05, 'samples': 25395840, 'steps': 132269, 'loss/train': 1.4665342569351196} 08/31/2021 13:10:25 - INFO - __main__ - Step 132271: {'lr': 1.7497319376305444e-05, 'samples': 25396032, 'steps': 132270, 'loss/train': 0.9549723267555237} 08/31/2021 13:10:25 - INFO - __main__ - Step 132272: {'lr': 1.7495369028265514e-05, 'samples': 25396224, 'steps': 132271, 'loss/train': 1.2000964879989624} 08/31/2021 13:10:26 - INFO - __main__ - Step 132273: {'lr': 1.7493418784988584e-05, 'samples': 25396416, 'steps': 132272, 'loss/train': 1.5023152828216553} 08/31/2021 13:10:26 - INFO - __main__ - Step 132274: {'lr': 1.749146864647552e-05, 'samples': 25396608, 'steps': 132273, 'loss/train': 0.6494394540786743} 08/31/2021 13:10:26 - INFO - __main__ - Step 132275: {'lr': 1.7489518612727268e-05, 'samples': 25396800, 'steps': 132274, 'loss/train': 1.3486822843551636} 08/31/2021 13:10:28 - INFO - __main__ - Step 132276: {'lr': 1.74875686837446e-05, 'samples': 25396992, 'steps': 132275, 'loss/train': 1.2015708684921265} 08/31/2021 13:10:28 - INFO - __main__ - Step 132277: {'lr': 1.748561885952846e-05, 'samples': 25397184, 'steps': 132276, 'loss/train': 1.3662586212158203} 08/31/2021 13:10:29 - INFO - __main__ - Step 132278: {'lr': 1.7483669140079705e-05, 'samples': 25397376, 'steps': 132277, 'loss/train': 1.4724196195602417} 08/31/2021 13:10:29 - INFO - __main__ - Step 132279: {'lr': 1.748171952539923e-05, 'samples': 25397568, 'steps': 132278, 'loss/train': 0.9349621534347534} 08/31/2021 13:10:29 - INFO - __main__ - Step 132280: {'lr': 1.7479770015487895e-05, 'samples': 25397760, 'steps': 132279, 'loss/train': 1.4363421201705933} 08/31/2021 13:10:31 - INFO - __main__ - Step 132281: {'lr': 1.7477820610346584e-05, 'samples': 25397952, 'steps': 132280, 'loss/train': 1.6474270820617676} 08/31/2021 13:10:31 - INFO - __main__ - Step 132282: {'lr': 1.7475871309976187e-05, 'samples': 25398144, 'steps': 132281, 'loss/train': 0.9621062278747559} 08/31/2021 13:10:32 - INFO - __main__ - Step 132283: {'lr': 1.7473922114377565e-05, 'samples': 25398336, 'steps': 132282, 'loss/train': 1.3609102964401245} 08/31/2021 13:10:32 - INFO - __main__ - Step 132284: {'lr': 1.7471973023551606e-05, 'samples': 25398528, 'steps': 132283, 'loss/train': 1.0316293239593506} 08/31/2021 13:10:32 - INFO - __main__ - Step 132285: {'lr': 1.74700240374992e-05, 'samples': 25398720, 'steps': 132284, 'loss/train': 1.35094153881073} 08/31/2021 13:10:34 - INFO - __main__ - Step 132286: {'lr': 1.74680751562212e-05, 'samples': 25398912, 'steps': 132285, 'loss/train': 0.9477662444114685} 08/31/2021 13:10:34 - INFO - __main__ - Step 132287: {'lr': 1.7466126379718507e-05, 'samples': 25399104, 'steps': 132286, 'loss/train': 1.2130157947540283} 08/31/2021 13:10:35 - INFO - __main__ - Step 132288: {'lr': 1.7464177707992023e-05, 'samples': 25399296, 'steps': 132287, 'loss/train': 1.0420597791671753} 08/31/2021 13:10:35 - INFO - __main__ - Step 132289: {'lr': 1.7462229141042563e-05, 'samples': 25399488, 'steps': 132288, 'loss/train': 1.3569573163986206} 08/31/2021 13:10:35 - INFO - __main__ - Step 132290: {'lr': 1.7460280678871037e-05, 'samples': 25399680, 'steps': 132289, 'loss/train': 1.4488805532455444} 08/31/2021 13:10:37 - INFO - __main__ - Step 132291: {'lr': 1.745833232147831e-05, 'samples': 25399872, 'steps': 132290, 'loss/train': 0.8549573421478271} 08/31/2021 13:10:37 - INFO - __main__ - Step 132292: {'lr': 1.7456384068865267e-05, 'samples': 25400064, 'steps': 132291, 'loss/train': 1.6054373979568481} 08/31/2021 13:10:38 - INFO - __main__ - Step 132293: {'lr': 1.7454435921032797e-05, 'samples': 25400256, 'steps': 132292, 'loss/train': 0.933591902256012} 08/31/2021 13:10:38 - INFO - __main__ - Step 132294: {'lr': 1.745248787798176e-05, 'samples': 25400448, 'steps': 132293, 'loss/train': 1.1529887914657593} 08/31/2021 13:10:38 - INFO - __main__ - Step 132295: {'lr': 1.7450539939713044e-05, 'samples': 25400640, 'steps': 132294, 'loss/train': 1.3218142986297607} 08/31/2021 13:10:39 - INFO - __main__ - Step 132296: {'lr': 1.744859210622754e-05, 'samples': 25400832, 'steps': 132295, 'loss/train': 0.5738968849182129} 08/31/2021 13:10:40 - INFO - __main__ - Step 132297: {'lr': 1.7446644377526078e-05, 'samples': 25401024, 'steps': 132296, 'loss/train': 1.106308102607727} 08/31/2021 13:10:41 - INFO - __main__ - Step 132298: {'lr': 1.7444696753609602e-05, 'samples': 25401216, 'steps': 132297, 'loss/train': 0.6509388089179993} 08/31/2021 13:10:41 - INFO - __main__ - Step 132299: {'lr': 1.7442749234478942e-05, 'samples': 25401408, 'steps': 132298, 'loss/train': 0.2584482729434967} 08/31/2021 13:10:41 - INFO - __main__ - Step 132300: {'lr': 1.7440801820134993e-05, 'samples': 25401600, 'steps': 132299, 'loss/train': 1.5064761638641357} 08/31/2021 13:10:42 - INFO - __main__ - Step 132301: {'lr': 1.7438854510578695e-05, 'samples': 25401792, 'steps': 132300, 'loss/train': 0.9077162742614746} 08/31/2021 13:10:43 - INFO - __main__ - Step 132302: {'lr': 1.7436907305810795e-05, 'samples': 25401984, 'steps': 132301, 'loss/train': 1.1547911167144775} 08/31/2021 13:10:44 - INFO - __main__ - Step 132303: {'lr': 1.743496020583224e-05, 'samples': 25402176, 'steps': 132302, 'loss/train': 1.3364146947860718} 08/31/2021 13:10:44 - INFO - __main__ - Step 132304: {'lr': 1.7433013210643917e-05, 'samples': 25402368, 'steps': 132303, 'loss/train': 0.37265846133232117} 08/31/2021 13:10:44 - INFO - __main__ - Step 132305: {'lr': 1.7431066320246657e-05, 'samples': 25402560, 'steps': 132304, 'loss/train': 1.5714921951293945} 08/31/2021 13:10:45 - INFO - __main__ - Step 132306: {'lr': 1.7429119534641407e-05, 'samples': 25402752, 'steps': 132305, 'loss/train': 0.1620970219373703} 08/31/2021 13:10:46 - INFO - __main__ - Step 132307: {'lr': 1.7427172853828972e-05, 'samples': 25402944, 'steps': 132306, 'loss/train': 1.2574787139892578} 08/31/2021 13:10:47 - INFO - __main__ - Step 132308: {'lr': 1.742522627781029e-05, 'samples': 25403136, 'steps': 132307, 'loss/train': 1.2497663497924805} 08/31/2021 13:10:47 - INFO - __main__ - Step 132309: {'lr': 1.74232798065862e-05, 'samples': 25403328, 'steps': 132308, 'loss/train': 0.9899647235870361} 08/31/2021 13:10:47 - INFO - __main__ - Step 132310: {'lr': 1.7421333440157587e-05, 'samples': 25403520, 'steps': 132309, 'loss/train': 0.17465147376060486} 08/31/2021 13:10:48 - INFO - __main__ - Step 132311: {'lr': 1.7419387178525342e-05, 'samples': 25403712, 'steps': 132310, 'loss/train': 0.9713019132614136} 08/31/2021 13:10:49 - INFO - __main__ - Step 132312: {'lr': 1.741744102169035e-05, 'samples': 25403904, 'steps': 132311, 'loss/train': 1.142426609992981} 08/31/2021 13:10:50 - INFO - __main__ - Step 132313: {'lr': 1.7415494969653445e-05, 'samples': 25404096, 'steps': 132312, 'loss/train': 0.7627654075622559} 08/31/2021 13:10:50 - INFO - __main__ - Step 132314: {'lr': 1.7413549022415544e-05, 'samples': 25404288, 'steps': 132313, 'loss/train': 1.4121720790863037} 08/31/2021 13:10:51 - INFO - __main__ - Step 132315: {'lr': 1.741160317997753e-05, 'samples': 25404480, 'steps': 132314, 'loss/train': 1.0958441495895386} 08/31/2021 13:10:51 - INFO - __main__ - Step 132316: {'lr': 1.7409657442340215e-05, 'samples': 25404672, 'steps': 132315, 'loss/train': 1.3302652835845947} 08/31/2021 13:10:51 - INFO - __main__ - Step 132317: {'lr': 1.740771180950454e-05, 'samples': 25404864, 'steps': 132316, 'loss/train': 5.70594596862793} 08/31/2021 13:10:53 - INFO - __main__ - Step 132318: {'lr': 1.7405766281471365e-05, 'samples': 25405056, 'steps': 132317, 'loss/train': 1.1673681735992432} 08/31/2021 13:10:53 - INFO - __main__ - Step 132319: {'lr': 1.7403820858241547e-05, 'samples': 25405248, 'steps': 132318, 'loss/train': 1.2338413000106812} 08/31/2021 13:10:54 - INFO - __main__ - Step 132320: {'lr': 1.740187553981598e-05, 'samples': 25405440, 'steps': 132319, 'loss/train': 1.2875038385391235} 08/31/2021 13:10:54 - INFO - __main__ - Step 132321: {'lr': 1.7399930326195523e-05, 'samples': 25405632, 'steps': 132320, 'loss/train': 0.7035874128341675} 08/31/2021 13:10:54 - INFO - __main__ - Step 132322: {'lr': 1.739798521738109e-05, 'samples': 25405824, 'steps': 132321, 'loss/train': 1.4881101846694946} 08/31/2021 13:10:57 - INFO - __main__ - Step 132323: {'lr': 1.7396040213373542e-05, 'samples': 25406016, 'steps': 132322, 'loss/train': 0.7079686522483826} 08/31/2021 13:10:57 - INFO - __main__ - Step 132324: {'lr': 1.7394095314173742e-05, 'samples': 25406208, 'steps': 132323, 'loss/train': 1.0865124464035034} 08/31/2021 13:10:58 - INFO - __main__ - Step 132325: {'lr': 1.7392150519782574e-05, 'samples': 25406400, 'steps': 132324, 'loss/train': 1.3383129835128784} 08/31/2021 13:10:58 - INFO - __main__ - Step 132326: {'lr': 1.73902058302009e-05, 'samples': 25406592, 'steps': 132325, 'loss/train': 0.06538328528404236} 08/31/2021 13:10:58 - INFO - __main__ - Step 132327: {'lr': 1.738826124542961e-05, 'samples': 25406784, 'steps': 132326, 'loss/train': 0.6963896155357361} 08/31/2021 13:11:00 - INFO - __main__ - Step 132328: {'lr': 1.7386316765469645e-05, 'samples': 25406976, 'steps': 132327, 'loss/train': 0.6939786672592163} 08/31/2021 13:11:00 - INFO - __main__ - Step 132329: {'lr': 1.7384372390321756e-05, 'samples': 25407168, 'steps': 132328, 'loss/train': 0.23120397329330444} 08/31/2021 13:11:01 - INFO - __main__ - Step 132330: {'lr': 1.7382428119986887e-05, 'samples': 25407360, 'steps': 132329, 'loss/train': 0.8070390820503235} 08/31/2021 13:11:01 - INFO - __main__ - Step 132331: {'lr': 1.7380483954465898e-05, 'samples': 25407552, 'steps': 132330, 'loss/train': 0.9849674105644226} 08/31/2021 13:11:01 - INFO - __main__ - Step 132332: {'lr': 1.7378539893759675e-05, 'samples': 25407744, 'steps': 132331, 'loss/train': 1.0758885145187378} 08/31/2021 13:11:03 - INFO - __main__ - Step 132333: {'lr': 1.7376595937869084e-05, 'samples': 25407936, 'steps': 132332, 'loss/train': 1.340358018875122} 08/31/2021 13:11:03 - INFO - __main__ - Step 132334: {'lr': 1.7374652086795033e-05, 'samples': 25408128, 'steps': 132333, 'loss/train': 2.2254672050476074} 08/31/2021 13:11:04 - INFO - __main__ - Step 132335: {'lr': 1.7372708340538364e-05, 'samples': 25408320, 'steps': 132334, 'loss/train': 1.348252296447754} 08/31/2021 13:11:04 - INFO - __main__ - Step 132336: {'lr': 1.7370764699099956e-05, 'samples': 25408512, 'steps': 132335, 'loss/train': 1.2156471014022827} 08/31/2021 13:11:04 - INFO - __main__ - Step 132337: {'lr': 1.7368821162480702e-05, 'samples': 25408704, 'steps': 132336, 'loss/train': 0.14870233833789825} 08/31/2021 13:11:06 - INFO - __main__ - Step 132338: {'lr': 1.7366877730681464e-05, 'samples': 25408896, 'steps': 132337, 'loss/train': 0.7671893835067749} 08/31/2021 13:11:06 - INFO - __main__ - Step 132339: {'lr': 1.7364934403703126e-05, 'samples': 25409088, 'steps': 132338, 'loss/train': 1.2169948816299438} 08/31/2021 13:11:07 - INFO - __main__ - Step 132340: {'lr': 1.736299118154655e-05, 'samples': 25409280, 'steps': 132339, 'loss/train': 0.8080489039421082} 08/31/2021 13:11:07 - INFO - __main__ - Step 132341: {'lr': 1.7361048064212626e-05, 'samples': 25409472, 'steps': 132340, 'loss/train': 0.9458043575286865} 08/31/2021 13:11:07 - INFO - __main__ - Step 132342: {'lr': 1.735910505170224e-05, 'samples': 25409664, 'steps': 132341, 'loss/train': 0.6467437744140625} 08/31/2021 13:11:09 - INFO - __main__ - Step 132343: {'lr': 1.735716214401625e-05, 'samples': 25409856, 'steps': 132342, 'loss/train': 0.14107750356197357} 08/31/2021 13:11:09 - INFO - __main__ - Step 132344: {'lr': 1.7355219341155498e-05, 'samples': 25410048, 'steps': 132343, 'loss/train': 1.540535569190979} 08/31/2021 13:11:10 - INFO - __main__ - Step 132345: {'lr': 1.735327664312092e-05, 'samples': 25410240, 'steps': 132344, 'loss/train': 0.5040462017059326} 08/31/2021 13:11:10 - INFO - __main__ - Step 132346: {'lr': 1.735133404991335e-05, 'samples': 25410432, 'steps': 132345, 'loss/train': 1.3105627298355103} 08/31/2021 13:11:10 - INFO - __main__ - Step 132347: {'lr': 1.73493915615337e-05, 'samples': 25410624, 'steps': 132346, 'loss/train': 0.6944913268089294} 08/31/2021 13:11:12 - INFO - __main__ - Step 132348: {'lr': 1.734744917798281e-05, 'samples': 25410816, 'steps': 132347, 'loss/train': 1.185723066329956} 08/31/2021 13:11:12 - INFO - __main__ - Step 132349: {'lr': 1.7345506899261566e-05, 'samples': 25411008, 'steps': 132348, 'loss/train': 1.531542420387268} 08/31/2021 13:11:13 - INFO - __main__ - Step 132350: {'lr': 1.7343564725370853e-05, 'samples': 25411200, 'steps': 132349, 'loss/train': 0.5930538773536682} 08/31/2021 13:11:13 - INFO - __main__ - Step 132351: {'lr': 1.7341622656311533e-05, 'samples': 25411392, 'steps': 132350, 'loss/train': 0.04256840795278549} 08/31/2021 13:11:13 - INFO - __main__ - Step 132352: {'lr': 1.733968069208447e-05, 'samples': 25411584, 'steps': 132351, 'loss/train': 0.8785917162895203} 08/31/2021 13:11:14 - INFO - __main__ - Step 132353: {'lr': 1.73377388326906e-05, 'samples': 25411776, 'steps': 132352, 'loss/train': 1.9613115787506104} 08/31/2021 13:11:15 - INFO - __main__ - Step 132354: {'lr': 1.733579707813071e-05, 'samples': 25411968, 'steps': 132353, 'loss/train': 0.6515935659408569} 08/31/2021 13:11:16 - INFO - __main__ - Step 132355: {'lr': 1.7333855428405792e-05, 'samples': 25412160, 'steps': 132354, 'loss/train': 1.50082266330719} 08/31/2021 13:11:16 - INFO - __main__ - Step 132356: {'lr': 1.73319138835166e-05, 'samples': 25412352, 'steps': 132355, 'loss/train': 1.3185299634933472} 08/31/2021 13:11:16 - INFO - __main__ - Step 132357: {'lr': 1.732997244346407e-05, 'samples': 25412544, 'steps': 132356, 'loss/train': 0.8405503034591675} 08/31/2021 13:11:17 - INFO - __main__ - Step 132358: {'lr': 1.7328031108249044e-05, 'samples': 25412736, 'steps': 132357, 'loss/train': 1.4338995218276978} 08/31/2021 13:11:18 - INFO - __main__ - Step 132359: {'lr': 1.7326089877872404e-05, 'samples': 25412928, 'steps': 132358, 'loss/train': 0.9920307993888855} 08/31/2021 13:11:19 - INFO - __main__ - Step 132360: {'lr': 1.7324148752335067e-05, 'samples': 25413120, 'steps': 132359, 'loss/train': 0.48997464776039124} 08/31/2021 13:11:19 - INFO - __main__ - Step 132361: {'lr': 1.732220773163787e-05, 'samples': 25413312, 'steps': 132360, 'loss/train': 5.454607009887695} 08/31/2021 13:11:19 - INFO - __main__ - Step 132362: {'lr': 1.7320266815781695e-05, 'samples': 25413504, 'steps': 132361, 'loss/train': 0.02591767907142639} 08/31/2021 13:11:20 - INFO - __main__ - Step 132363: {'lr': 1.7318326004767404e-05, 'samples': 25413696, 'steps': 132362, 'loss/train': 1.6097369194030762} 08/31/2021 13:11:21 - INFO - __main__ - Step 132364: {'lr': 1.7316385298595917e-05, 'samples': 25413888, 'steps': 132363, 'loss/train': 0.9138402342796326} 08/31/2021 13:11:22 - INFO - __main__ - Step 132365: {'lr': 1.7314444697268034e-05, 'samples': 25414080, 'steps': 132364, 'loss/train': 1.5464547872543335} 08/31/2021 13:11:22 - INFO - __main__ - Step 132366: {'lr': 1.73125042007847e-05, 'samples': 25414272, 'steps': 132365, 'loss/train': 1.2177784442901611} 08/31/2021 13:11:22 - INFO - __main__ - Step 132367: {'lr': 1.731056380914675e-05, 'samples': 25414464, 'steps': 132366, 'loss/train': 1.276582956314087} 08/31/2021 13:11:23 - INFO - __main__ - Step 132368: {'lr': 1.7308623522355073e-05, 'samples': 25414656, 'steps': 132367, 'loss/train': 1.5846447944641113} 08/31/2021 13:11:24 - INFO - __main__ - Step 132369: {'lr': 1.730668334041058e-05, 'samples': 25414848, 'steps': 132368, 'loss/train': 1.1525070667266846} 08/31/2021 13:11:25 - INFO - __main__ - Step 132370: {'lr': 1.7304743263314078e-05, 'samples': 25415040, 'steps': 132369, 'loss/train': 1.4078577756881714} 08/31/2021 13:11:25 - INFO - __main__ - Step 132371: {'lr': 1.7302803291066455e-05, 'samples': 25415232, 'steps': 132370, 'loss/train': 0.3065521717071533} 08/31/2021 13:11:26 - INFO - __main__ - Step 132372: {'lr': 1.7300863423668602e-05, 'samples': 25415424, 'steps': 132371, 'loss/train': 0.8439841866493225} 08/31/2021 13:11:26 - INFO - __main__ - Step 132373: {'lr': 1.7298923661121373e-05, 'samples': 25415616, 'steps': 132372, 'loss/train': 0.7247838377952576} 08/31/2021 13:11:26 - INFO - __main__ - Step 132374: {'lr': 1.7296984003425666e-05, 'samples': 25415808, 'steps': 132373, 'loss/train': 0.8557842373847961} 08/31/2021 13:11:28 - INFO - __main__ - Step 132375: {'lr': 1.7295044450582358e-05, 'samples': 25416000, 'steps': 132374, 'loss/train': 1.2313013076782227} 08/31/2021 13:11:28 - INFO - __main__ - Step 132376: {'lr': 1.729310500259229e-05, 'samples': 25416192, 'steps': 132375, 'loss/train': 1.4255541563034058} 08/31/2021 13:11:29 - INFO - __main__ - Step 132377: {'lr': 1.7291165659456375e-05, 'samples': 25416384, 'steps': 132376, 'loss/train': 0.4733959436416626} 08/31/2021 13:11:29 - INFO - __main__ - Step 132378: {'lr': 1.7289226421175476e-05, 'samples': 25416576, 'steps': 132377, 'loss/train': 1.3813477754592896} 08/31/2021 13:11:29 - INFO - __main__ - Step 132379: {'lr': 1.7287287287750446e-05, 'samples': 25416768, 'steps': 132378, 'loss/train': 0.6151334047317505} 08/31/2021 13:11:31 - INFO - __main__ - Step 132380: {'lr': 1.7285348259182182e-05, 'samples': 25416960, 'steps': 132379, 'loss/train': 0.7821133732795715} 08/31/2021 13:11:32 - INFO - __main__ - Step 132381: {'lr': 1.728340933547157e-05, 'samples': 25417152, 'steps': 132380, 'loss/train': 1.2034125328063965} 08/31/2021 13:11:32 - INFO - __main__ - Step 132382: {'lr': 1.7281470516619464e-05, 'samples': 25417344, 'steps': 132381, 'loss/train': 0.9475719928741455} 08/31/2021 13:11:33 - INFO - __main__ - Step 132383: {'lr': 1.7279531802626704e-05, 'samples': 25417536, 'steps': 132382, 'loss/train': 1.1976335048675537} 08/31/2021 13:11:33 - INFO - __main__ - Step 132384: {'lr': 1.7277593193494227e-05, 'samples': 25417728, 'steps': 132383, 'loss/train': 1.5421711206436157} 08/31/2021 13:11:35 - INFO - __main__ - Step 132385: {'lr': 1.7275654689222847e-05, 'samples': 25417920, 'steps': 132384, 'loss/train': 1.2625643014907837} 08/31/2021 13:11:35 - INFO - __main__ - Step 132386: {'lr': 1.7273716289813472e-05, 'samples': 25418112, 'steps': 132385, 'loss/train': 1.6833018064498901} 08/31/2021 13:11:35 - INFO - __main__ - Step 132387: {'lr': 1.727177799526697e-05, 'samples': 25418304, 'steps': 132386, 'loss/train': 0.7482150197029114} 08/31/2021 13:11:36 - INFO - __main__ - Step 132388: {'lr': 1.726983980558419e-05, 'samples': 25418496, 'steps': 132387, 'loss/train': 1.1452285051345825} 08/31/2021 13:11:36 - INFO - __main__ - Step 132389: {'lr': 1.726790172076606e-05, 'samples': 25418688, 'steps': 132388, 'loss/train': 1.4206792116165161} 08/31/2021 13:11:36 - INFO - __main__ - Step 132390: {'lr': 1.7265963740813405e-05, 'samples': 25418880, 'steps': 132389, 'loss/train': 2.0827043056488037} 08/31/2021 13:11:38 - INFO - __main__ - Step 132391: {'lr': 1.7264025865727145e-05, 'samples': 25419072, 'steps': 132390, 'loss/train': 1.223651647567749} 08/31/2021 13:11:39 - INFO - __main__ - Step 132392: {'lr': 1.7262088095508083e-05, 'samples': 25419264, 'steps': 132391, 'loss/train': 1.242371916770935} 08/31/2021 13:11:39 - INFO - __main__ - Step 132393: {'lr': 1.7260150430157162e-05, 'samples': 25419456, 'steps': 132392, 'loss/train': 1.0554343461990356} 08/31/2021 13:11:39 - INFO - __main__ - Step 132394: {'lr': 1.7258212869675215e-05, 'samples': 25419648, 'steps': 132393, 'loss/train': 0.8926951289176941} 08/31/2021 13:11:40 - INFO - __main__ - Step 132395: {'lr': 1.7256275414063133e-05, 'samples': 25419840, 'steps': 132394, 'loss/train': 1.2834275960922241} 08/31/2021 13:11:41 - INFO - __main__ - Step 132396: {'lr': 1.7254338063321827e-05, 'samples': 25420032, 'steps': 132395, 'loss/train': 1.5407702922821045} 08/31/2021 13:11:42 - INFO - __main__ - Step 132397: {'lr': 1.725240081745205e-05, 'samples': 25420224, 'steps': 132396, 'loss/train': 1.1189574003219604} 08/31/2021 13:11:42 - INFO - __main__ - Step 132398: {'lr': 1.7250463676454775e-05, 'samples': 25420416, 'steps': 132397, 'loss/train': 0.2496461421251297} 08/31/2021 13:11:43 - INFO - __main__ - Step 132399: {'lr': 1.7248526640330857e-05, 'samples': 25420608, 'steps': 132398, 'loss/train': 0.8023409247398376} 08/31/2021 13:11:43 - INFO - __main__ - Step 132400: {'lr': 1.7246589709081162e-05, 'samples': 25420800, 'steps': 132399, 'loss/train': 0.7031792402267456} 08/31/2021 13:11:45 - INFO - __main__ - Step 132401: {'lr': 1.7244652882706546e-05, 'samples': 25420992, 'steps': 132400, 'loss/train': 0.8470281958580017} 08/31/2021 13:11:45 - INFO - __main__ - Step 132402: {'lr': 1.72427161612079e-05, 'samples': 25421184, 'steps': 132401, 'loss/train': 1.010957956314087} 08/31/2021 13:11:45 - INFO - __main__ - Step 132403: {'lr': 1.724077954458611e-05, 'samples': 25421376, 'steps': 132402, 'loss/train': 0.7791709303855896} 08/31/2021 13:11:46 - INFO - __main__ - Step 132404: {'lr': 1.723884303284201e-05, 'samples': 25421568, 'steps': 132403, 'loss/train': 1.3770378828048706} 08/31/2021 13:11:46 - INFO - __main__ - Step 132405: {'lr': 1.723690662597652e-05, 'samples': 25421760, 'steps': 132404, 'loss/train': 1.4026705026626587} 08/31/2021 13:11:48 - INFO - __main__ - Step 132406: {'lr': 1.7234970323990463e-05, 'samples': 25421952, 'steps': 132405, 'loss/train': 1.2530182600021362} 08/31/2021 13:11:48 - INFO - __main__ - Step 132407: {'lr': 1.7233034126884762e-05, 'samples': 25422144, 'steps': 132406, 'loss/train': 1.1628696918487549} 08/31/2021 13:11:48 - INFO - __main__ - Step 132408: {'lr': 1.723109803466025e-05, 'samples': 25422336, 'steps': 132407, 'loss/train': 0.7533965110778809} 08/31/2021 13:11:49 - INFO - __main__ - Step 132409: {'lr': 1.7229162047317836e-05, 'samples': 25422528, 'steps': 132408, 'loss/train': 1.3072155714035034} 08/31/2021 13:11:49 - INFO - __main__ - Step 132410: {'lr': 1.7227226164858362e-05, 'samples': 25422720, 'steps': 132409, 'loss/train': 1.1239449977874756} 08/31/2021 13:11:51 - INFO - __main__ - Step 132411: {'lr': 1.7225290387282683e-05, 'samples': 25422912, 'steps': 132410, 'loss/train': 0.9965342879295349} 08/31/2021 13:11:51 - INFO - __main__ - Step 132412: {'lr': 1.7223354714591715e-05, 'samples': 25423104, 'steps': 132411, 'loss/train': 0.950621485710144} 08/31/2021 13:11:51 - INFO - __main__ - Step 132413: {'lr': 1.7221419146786293e-05, 'samples': 25423296, 'steps': 132412, 'loss/train': 1.2501213550567627} 08/31/2021 13:11:52 - INFO - __main__ - Step 132414: {'lr': 1.721948368386733e-05, 'samples': 25423488, 'steps': 132413, 'loss/train': 1.0609062910079956} 08/31/2021 13:11:52 - INFO - __main__ - Step 132415: {'lr': 1.7217548325835662e-05, 'samples': 25423680, 'steps': 132414, 'loss/train': 1.088341236114502} 08/31/2021 13:11:53 - INFO - __main__ - Step 132416: {'lr': 1.721561307269218e-05, 'samples': 25423872, 'steps': 132415, 'loss/train': 0.7542844414710999} 08/31/2021 13:11:54 - INFO - __main__ - Step 132417: {'lr': 1.7213677924437733e-05, 'samples': 25424064, 'steps': 132416, 'loss/train': 1.4155305624008179} 08/31/2021 13:11:54 - INFO - __main__ - Step 132418: {'lr': 1.7211742881073245e-05, 'samples': 25424256, 'steps': 132417, 'loss/train': 0.2086460441350937} 08/31/2021 13:11:55 - INFO - __main__ - Step 132419: {'lr': 1.720980794259952e-05, 'samples': 25424448, 'steps': 132418, 'loss/train': 1.08530592918396} 08/31/2021 13:11:55 - INFO - __main__ - Step 132420: {'lr': 1.720787310901753e-05, 'samples': 25424640, 'steps': 132419, 'loss/train': 1.379035472869873} 08/31/2021 13:11:56 - INFO - __main__ - Step 132421: {'lr': 1.7205938380328023e-05, 'samples': 25424832, 'steps': 132420, 'loss/train': 1.4404031038284302} 08/31/2021 13:11:57 - INFO - __main__ - Step 132422: {'lr': 1.7204003756531917e-05, 'samples': 25425024, 'steps': 132421, 'loss/train': 1.4716806411743164} 08/31/2021 13:11:57 - INFO - __main__ - Step 132423: {'lr': 1.7202069237630124e-05, 'samples': 25425216, 'steps': 132422, 'loss/train': 4.2769341468811035} 08/31/2021 13:11:58 - INFO - __main__ - Step 132424: {'lr': 1.7200134823623455e-05, 'samples': 25425408, 'steps': 132423, 'loss/train': 0.9066454172134399} 08/31/2021 13:11:58 - INFO - __main__ - Step 132425: {'lr': 1.7198200514512848e-05, 'samples': 25425600, 'steps': 132424, 'loss/train': 1.5845087766647339} 08/31/2021 13:11:59 - INFO - __main__ - Step 132426: {'lr': 1.719626631029911e-05, 'samples': 25425792, 'steps': 132425, 'loss/train': 0.8425942063331604} 08/31/2021 13:12:00 - INFO - __main__ - Step 132427: {'lr': 1.7194332210983154e-05, 'samples': 25425984, 'steps': 132426, 'loss/train': 1.3468836545944214} 08/31/2021 13:12:01 - INFO - __main__ - Step 132428: {'lr': 1.7192398216565846e-05, 'samples': 25426176, 'steps': 132427, 'loss/train': 1.2541533708572388} 08/31/2021 13:12:01 - INFO - __main__ - Step 132429: {'lr': 1.7190464327048043e-05, 'samples': 25426368, 'steps': 132428, 'loss/train': 0.515836775302887} 08/31/2021 13:12:02 - INFO - __main__ - Step 132430: {'lr': 1.7188530542430608e-05, 'samples': 25426560, 'steps': 132429, 'loss/train': 0.49122512340545654} 08/31/2021 13:12:02 - INFO - __main__ - Step 132431: {'lr': 1.7186596862714483e-05, 'samples': 25426752, 'steps': 132430, 'loss/train': 1.1085309982299805} 08/31/2021 13:12:02 - INFO - __main__ - Step 132432: {'lr': 1.7184663287900472e-05, 'samples': 25426944, 'steps': 132431, 'loss/train': 1.3306777477264404} 08/31/2021 13:12:03 - INFO - __main__ - Step 132433: {'lr': 1.7182729817989434e-05, 'samples': 25427136, 'steps': 132432, 'loss/train': 0.015084311366081238} 08/31/2021 13:12:05 - INFO - __main__ - Step 132434: {'lr': 1.7180796452982262e-05, 'samples': 25427328, 'steps': 132433, 'loss/train': 0.661960244178772} 08/31/2021 13:12:05 - INFO - __main__ - Step 132435: {'lr': 1.717886319287984e-05, 'samples': 25427520, 'steps': 132434, 'loss/train': 1.2111306190490723} 08/31/2021 13:12:06 - INFO - __main__ - Step 132436: {'lr': 1.7176930037683002e-05, 'samples': 25427712, 'steps': 132435, 'loss/train': 1.0462530851364136} 08/31/2021 13:12:06 - INFO - __main__ - Step 132437: {'lr': 1.7174996987392666e-05, 'samples': 25427904, 'steps': 132436, 'loss/train': 1.2441422939300537} 08/31/2021 13:12:06 - INFO - __main__ - Step 132438: {'lr': 1.7173064042009688e-05, 'samples': 25428096, 'steps': 132437, 'loss/train': 1.3513572216033936} 08/31/2021 13:12:08 - INFO - __main__ - Step 132439: {'lr': 1.7171131201534932e-05, 'samples': 25428288, 'steps': 132438, 'loss/train': 0.5004510879516602} 08/31/2021 13:12:09 - INFO - __main__ - Step 132440: {'lr': 1.7169198465969287e-05, 'samples': 25428480, 'steps': 132439, 'loss/train': 1.3013763427734375} 08/31/2021 13:12:09 - INFO - __main__ - Step 132441: {'lr': 1.7167265835313584e-05, 'samples': 25428672, 'steps': 132440, 'loss/train': 0.029652360826730728} 08/31/2021 13:12:09 - INFO - __main__ - Step 132442: {'lr': 1.7165333309568763e-05, 'samples': 25428864, 'steps': 132441, 'loss/train': 0.8704500794410706} 08/31/2021 13:12:10 - INFO - __main__ - Step 132443: {'lr': 1.7163400888735638e-05, 'samples': 25429056, 'steps': 132442, 'loss/train': 0.5859773755073547} 08/31/2021 13:12:12 - INFO - __main__ - Step 132444: {'lr': 1.7161468572815057e-05, 'samples': 25429248, 'steps': 132443, 'loss/train': 1.2007899284362793} 08/31/2021 13:12:12 - INFO - __main__ - Step 132445: {'lr': 1.7159536361807947e-05, 'samples': 25429440, 'steps': 132444, 'loss/train': 0.7802404761314392} 08/31/2021 13:12:13 - INFO - __main__ - Step 132446: {'lr': 1.7157604255715138e-05, 'samples': 25429632, 'steps': 132445, 'loss/train': 0.9427681565284729} 08/31/2021 13:12:13 - INFO - __main__ - Step 132447: {'lr': 1.7155672254537513e-05, 'samples': 25429824, 'steps': 132446, 'loss/train': 1.0632797479629517} 08/31/2021 13:12:13 - INFO - __main__ - Step 132448: {'lr': 1.7153740358275964e-05, 'samples': 25430016, 'steps': 132447, 'loss/train': 0.9616114497184753} 08/31/2021 13:12:14 - INFO - __main__ - Step 132449: {'lr': 1.7151808566931355e-05, 'samples': 25430208, 'steps': 132448, 'loss/train': 3.8644001483917236} 08/31/2021 13:12:15 - INFO - __main__ - Step 132450: {'lr': 1.714987688050454e-05, 'samples': 25430400, 'steps': 132449, 'loss/train': 0.975092887878418} 08/31/2021 13:12:16 - INFO - __main__ - Step 132451: {'lr': 1.714794529899641e-05, 'samples': 25430592, 'steps': 132450, 'loss/train': 1.5097519159317017} 08/31/2021 13:12:16 - INFO - __main__ - Step 132452: {'lr': 1.7146013822407796e-05, 'samples': 25430784, 'steps': 132451, 'loss/train': 0.6139572858810425} 08/31/2021 13:12:17 - INFO - __main__ - Step 132453: {'lr': 1.7144082450739647e-05, 'samples': 25430976, 'steps': 132452, 'loss/train': 1.3084362745285034} 08/31/2021 13:12:17 - INFO - __main__ - Step 132454: {'lr': 1.714215118399276e-05, 'samples': 25431168, 'steps': 132453, 'loss/train': 0.3736152946949005} 08/31/2021 13:12:17 - INFO - __main__ - Step 132455: {'lr': 1.7140220022168e-05, 'samples': 25431360, 'steps': 132454, 'loss/train': 1.6419059038162231} 08/31/2021 13:12:19 - INFO - __main__ - Step 132456: {'lr': 1.7138288965266284e-05, 'samples': 25431552, 'steps': 132455, 'loss/train': 1.2442446947097778} 08/31/2021 13:12:19 - INFO - __main__ - Step 132457: {'lr': 1.7136358013288445e-05, 'samples': 25431744, 'steps': 132456, 'loss/train': 1.4431698322296143} 08/31/2021 13:12:20 - INFO - __main__ - Step 132458: {'lr': 1.7134427166235366e-05, 'samples': 25431936, 'steps': 132457, 'loss/train': 1.1426676511764526} 08/31/2021 13:12:20 - INFO - __main__ - Step 132459: {'lr': 1.713249642410794e-05, 'samples': 25432128, 'steps': 132458, 'loss/train': 1.0307555198669434} 08/31/2021 13:12:20 - INFO - __main__ - Step 132460: {'lr': 1.7130565786906997e-05, 'samples': 25432320, 'steps': 132459, 'loss/train': 1.1539853811264038} 08/31/2021 13:12:22 - INFO - __main__ - Step 132461: {'lr': 1.7128635254633455e-05, 'samples': 25432512, 'steps': 132460, 'loss/train': 1.02139151096344} 08/31/2021 13:12:23 - INFO - __main__ - Step 132462: {'lr': 1.712670482728815e-05, 'samples': 25432704, 'steps': 132461, 'loss/train': 1.3090342283248901} 08/31/2021 13:12:23 - INFO - __main__ - Step 132463: {'lr': 1.7124774504871933e-05, 'samples': 25432896, 'steps': 132462, 'loss/train': 1.3236479759216309} 08/31/2021 13:12:23 - INFO - __main__ - Step 132464: {'lr': 1.712284428738575e-05, 'samples': 25433088, 'steps': 132463, 'loss/train': 1.1816585063934326} 08/31/2021 13:12:24 - INFO - __main__ - Step 132465: {'lr': 1.7120914174830388e-05, 'samples': 25433280, 'steps': 132464, 'loss/train': 0.02496233955025673} 08/31/2021 13:12:24 - INFO - __main__ - Step 132466: {'lr': 1.7118984167206753e-05, 'samples': 25433472, 'steps': 132465, 'loss/train': 0.02504626289010048} 08/31/2021 13:12:26 - INFO - __main__ - Step 132467: {'lr': 1.7117054264515708e-05, 'samples': 25433664, 'steps': 132466, 'loss/train': 0.5438580513000488} 08/31/2021 13:12:26 - INFO - __main__ - Step 132468: {'lr': 1.7115124466758113e-05, 'samples': 25433856, 'steps': 132467, 'loss/train': 1.156949520111084} 08/31/2021 13:12:26 - INFO - __main__ - Step 132469: {'lr': 1.711319477393486e-05, 'samples': 25434048, 'steps': 132468, 'loss/train': 1.3412002325057983} 08/31/2021 13:12:27 - INFO - __main__ - Step 132470: {'lr': 1.7111265186046803e-05, 'samples': 25434240, 'steps': 132469, 'loss/train': 1.1021307706832886} 08/31/2021 13:12:27 - INFO - __main__ - Step 132471: {'lr': 1.7109335703094807e-05, 'samples': 25434432, 'steps': 132470, 'loss/train': 1.698154330253601} 08/31/2021 13:12:29 - INFO - __main__ - Step 132472: {'lr': 1.710740632507976e-05, 'samples': 25434624, 'steps': 132471, 'loss/train': 1.6191385984420776} 08/31/2021 13:12:29 - INFO - __main__ - Step 132473: {'lr': 1.7105477052002522e-05, 'samples': 25434816, 'steps': 132472, 'loss/train': 1.2951922416687012} 08/31/2021 13:12:30 - INFO - __main__ - Step 132474: {'lr': 1.7103547883863978e-05, 'samples': 25435008, 'steps': 132473, 'loss/train': 1.4411588907241821} 08/31/2021 13:12:30 - INFO - __main__ - Step 132475: {'lr': 1.7101618820664966e-05, 'samples': 25435200, 'steps': 132474, 'loss/train': 1.304004430770874} 08/31/2021 13:12:30 - INFO - __main__ - Step 132476: {'lr': 1.7099689862406397e-05, 'samples': 25435392, 'steps': 132475, 'loss/train': 1.1717230081558228} 08/31/2021 13:12:32 - INFO - __main__ - Step 132477: {'lr': 1.709776100908908e-05, 'samples': 25435584, 'steps': 132476, 'loss/train': 0.9870477318763733} 08/31/2021 13:12:32 - INFO - __main__ - Step 132478: {'lr': 1.709583226071393e-05, 'samples': 25435776, 'steps': 132477, 'loss/train': 0.57301265001297} 08/31/2021 13:12:32 - INFO - __main__ - Step 132479: {'lr': 1.7093903617281803e-05, 'samples': 25435968, 'steps': 132478, 'loss/train': 1.1280417442321777} 08/31/2021 13:12:33 - INFO - __main__ - Step 132480: {'lr': 1.7091975078793566e-05, 'samples': 25436160, 'steps': 132479, 'loss/train': 1.9728193283081055} 08/31/2021 13:12:33 - INFO - __main__ - Step 132481: {'lr': 1.7090046645250102e-05, 'samples': 25436352, 'steps': 132480, 'loss/train': 0.819196879863739} 08/31/2021 13:12:35 - INFO - __main__ - Step 132482: {'lr': 1.7088118316652245e-05, 'samples': 25436544, 'steps': 132481, 'loss/train': 1.2790729999542236} 08/31/2021 13:12:35 - INFO - __main__ - Step 132483: {'lr': 1.7086190093000913e-05, 'samples': 25436736, 'steps': 132482, 'loss/train': 0.16295237839221954} 08/31/2021 13:12:36 - INFO - __main__ - Step 132484: {'lr': 1.708426197429694e-05, 'samples': 25436928, 'steps': 132483, 'loss/train': 1.5884724855422974} 08/31/2021 13:12:36 - INFO - __main__ - Step 132485: {'lr': 1.7082333960541208e-05, 'samples': 25437120, 'steps': 132484, 'loss/train': 1.2150534391403198} 08/31/2021 13:12:36 - INFO - __main__ - Step 132486: {'lr': 1.7080406051734553e-05, 'samples': 25437312, 'steps': 132485, 'loss/train': 1.3138381242752075} 08/31/2021 13:12:38 - INFO - __main__ - Step 132487: {'lr': 1.7078478247877892e-05, 'samples': 25437504, 'steps': 132486, 'loss/train': 1.1078059673309326} 08/31/2021 13:12:39 - INFO - __main__ - Step 132488: {'lr': 1.7076550548972087e-05, 'samples': 25437696, 'steps': 132487, 'loss/train': 1.0169568061828613} 08/31/2021 13:12:39 - INFO - __main__ - Step 132489: {'lr': 1.7074622955017994e-05, 'samples': 25437888, 'steps': 132488, 'loss/train': 0.7661387920379639} 08/31/2021 13:12:40 - INFO - __main__ - Step 132490: {'lr': 1.7072695466016504e-05, 'samples': 25438080, 'steps': 132489, 'loss/train': 0.2770631015300751} 08/31/2021 13:12:40 - INFO - __main__ - Step 132491: {'lr': 1.7070768081968447e-05, 'samples': 25438272, 'steps': 132490, 'loss/train': 1.162792444229126} 08/31/2021 13:12:40 - INFO - __main__ - Step 132492: {'lr': 1.7068840802874685e-05, 'samples': 25438464, 'steps': 132491, 'loss/train': 1.5503718852996826} 08/31/2021 13:12:42 - INFO - __main__ - Step 132493: {'lr': 1.7066913628736107e-05, 'samples': 25438656, 'steps': 132492, 'loss/train': 1.1618767976760864} 08/31/2021 13:12:42 - INFO - __main__ - Step 132494: {'lr': 1.7064986559553602e-05, 'samples': 25438848, 'steps': 132493, 'loss/train': 0.8834751844406128} 08/31/2021 13:12:43 - INFO - __main__ - Step 132495: {'lr': 1.7063059595328e-05, 'samples': 25439040, 'steps': 132494, 'loss/train': 1.2529090642929077} 08/31/2021 13:12:43 - INFO - __main__ - Step 132496: {'lr': 1.706113273606022e-05, 'samples': 25439232, 'steps': 132495, 'loss/train': 1.2169641256332397} 08/31/2021 13:12:43 - INFO - __main__ - Step 132497: {'lr': 1.7059205981751062e-05, 'samples': 25439424, 'steps': 132496, 'loss/train': 1.083116054534912} 08/31/2021 13:12:45 - INFO - __main__ - Step 132498: {'lr': 1.7057279332401447e-05, 'samples': 25439616, 'steps': 132497, 'loss/train': 1.3286712169647217} 08/31/2021 13:12:45 - INFO - __main__ - Step 132499: {'lr': 1.7055352788012235e-05, 'samples': 25439808, 'steps': 132498, 'loss/train': 1.0804661512374878} 08/31/2021 13:12:46 - INFO - __main__ - Step 132500: {'lr': 1.7053426348584283e-05, 'samples': 25440000, 'steps': 132499, 'loss/train': 0.9551786184310913} 08/31/2021 13:12:46 - INFO - __main__ - Step 132501: {'lr': 1.7051500014118455e-05, 'samples': 25440192, 'steps': 132500, 'loss/train': 0.7856772541999817} 08/31/2021 13:12:46 - INFO - __main__ - Step 132502: {'lr': 1.7049573784615635e-05, 'samples': 25440384, 'steps': 132501, 'loss/train': 1.0067270994186401} 08/31/2021 13:12:48 - INFO - __main__ - Step 132503: {'lr': 1.7047647660076714e-05, 'samples': 25440576, 'steps': 132502, 'loss/train': 1.5372272729873657} 08/31/2021 13:12:48 - INFO - __main__ - Step 132504: {'lr': 1.70457216405025e-05, 'samples': 25440768, 'steps': 132503, 'loss/train': 0.8553293943405151} 08/31/2021 13:12:49 - INFO - __main__ - Step 132505: {'lr': 1.7043795725893874e-05, 'samples': 25440960, 'steps': 132504, 'loss/train': 1.1184444427490234} 08/31/2021 13:12:49 - INFO - __main__ - Step 132506: {'lr': 1.704186991625173e-05, 'samples': 25441152, 'steps': 132505, 'loss/train': 1.0536341667175293} 08/31/2021 13:12:49 - INFO - __main__ - Step 132507: {'lr': 1.7039944211576924e-05, 'samples': 25441344, 'steps': 132506, 'loss/train': 1.2493973970413208} 08/31/2021 13:12:51 - INFO - __main__ - Step 132508: {'lr': 1.703801861187032e-05, 'samples': 25441536, 'steps': 132507, 'loss/train': 0.576326847076416} 08/31/2021 13:12:52 - INFO - __main__ - Step 132509: {'lr': 1.703609311713278e-05, 'samples': 25441728, 'steps': 132508, 'loss/train': 1.4244951009750366} 08/31/2021 13:12:52 - INFO - __main__ - Step 132510: {'lr': 1.7034167727365213e-05, 'samples': 25441920, 'steps': 132509, 'loss/train': 0.5717307925224304} 08/31/2021 13:12:52 - INFO - __main__ - Step 132511: {'lr': 1.703224244256843e-05, 'samples': 25442112, 'steps': 132510, 'loss/train': 0.9145869612693787} 08/31/2021 13:12:53 - INFO - __main__ - Step 132512: {'lr': 1.7030317262743317e-05, 'samples': 25442304, 'steps': 132511, 'loss/train': 1.3858134746551514} 08/31/2021 13:12:53 - INFO - __main__ - Step 132513: {'lr': 1.7028392187890762e-05, 'samples': 25442496, 'steps': 132512, 'loss/train': 0.8863492608070374} 08/31/2021 13:12:55 - INFO - __main__ - Step 132514: {'lr': 1.7026467218011627e-05, 'samples': 25442688, 'steps': 132513, 'loss/train': 1.1683549880981445} 08/31/2021 13:12:55 - INFO - __main__ - Step 132515: {'lr': 1.702454235310677e-05, 'samples': 25442880, 'steps': 132514, 'loss/train': 1.432168960571289} 08/31/2021 13:12:55 - INFO - __main__ - Step 132516: {'lr': 1.7022617593177026e-05, 'samples': 25443072, 'steps': 132515, 'loss/train': 1.3293757438659668} 08/31/2021 13:12:56 - INFO - __main__ - Step 132517: {'lr': 1.7020692938223365e-05, 'samples': 25443264, 'steps': 132516, 'loss/train': 1.6736254692077637} 08/31/2021 13:12:56 - INFO - __main__ - Step 132518: {'lr': 1.7018768388246536e-05, 'samples': 25443456, 'steps': 132517, 'loss/train': 0.9100214838981628} 08/31/2021 13:12:58 - INFO - __main__ - Step 132519: {'lr': 1.7016843943247457e-05, 'samples': 25443648, 'steps': 132518, 'loss/train': 0.9311344623565674} 08/31/2021 13:12:58 - INFO - __main__ - Step 132520: {'lr': 1.7014919603227013e-05, 'samples': 25443840, 'steps': 132519, 'loss/train': 0.9634706377983093} 08/31/2021 13:12:59 - INFO - __main__ - Step 132521: {'lr': 1.7012995368186012e-05, 'samples': 25444032, 'steps': 132520, 'loss/train': 1.196479082107544} 08/31/2021 13:12:59 - INFO - __main__ - Step 132522: {'lr': 1.7011071238125398e-05, 'samples': 25444224, 'steps': 132521, 'loss/train': 0.6561198830604553} 08/31/2021 13:12:59 - INFO - __main__ - Step 132523: {'lr': 1.7009147213045972e-05, 'samples': 25444416, 'steps': 132522, 'loss/train': 1.4742902517318726} 08/31/2021 13:13:00 - INFO - __main__ - Step 132524: {'lr': 1.7007223292948654e-05, 'samples': 25444608, 'steps': 132523, 'loss/train': 0.5861828327178955} 08/31/2021 13:13:01 - INFO - __main__ - Step 132525: {'lr': 1.7005299477834245e-05, 'samples': 25444800, 'steps': 132524, 'loss/train': 0.1375482678413391} 08/31/2021 13:13:02 - INFO - __main__ - Step 132526: {'lr': 1.7003375767703693e-05, 'samples': 25444992, 'steps': 132525, 'loss/train': 0.5504838228225708} 08/31/2021 13:13:02 - INFO - __main__ - Step 132527: {'lr': 1.70014521625578e-05, 'samples': 25445184, 'steps': 132526, 'loss/train': 0.7223042249679565} 08/31/2021 13:13:02 - INFO - __main__ - Step 132528: {'lr': 1.6999528662397483e-05, 'samples': 25445376, 'steps': 132527, 'loss/train': 1.1692672967910767} 08/31/2021 13:13:03 - INFO - __main__ - Step 132529: {'lr': 1.699760526722355e-05, 'samples': 25445568, 'steps': 132528, 'loss/train': 1.2205506563186646} 08/31/2021 13:13:04 - INFO - __main__ - Step 132530: {'lr': 1.6995681977036965e-05, 'samples': 25445760, 'steps': 132529, 'loss/train': 1.1953078508377075} 08/31/2021 13:13:05 - INFO - __main__ - Step 132531: {'lr': 1.6993758791838483e-05, 'samples': 25445952, 'steps': 132530, 'loss/train': 1.3964343070983887} 08/31/2021 13:13:05 - INFO - __main__ - Step 132532: {'lr': 1.6991835711629016e-05, 'samples': 25446144, 'steps': 132531, 'loss/train': 0.9876559972763062} 08/31/2021 13:13:05 - INFO - __main__ - Step 132533: {'lr': 1.698991273640943e-05, 'samples': 25446336, 'steps': 132532, 'loss/train': 0.8139815330505371} 08/31/2021 13:13:06 - INFO - __main__ - Step 132534: {'lr': 1.698798986618061e-05, 'samples': 25446528, 'steps': 132533, 'loss/train': 1.113516926765442} 08/31/2021 13:13:08 - INFO - __main__ - Step 132535: {'lr': 1.6986067100943386e-05, 'samples': 25446720, 'steps': 132534, 'loss/train': 0.7361987233161926} 08/31/2021 13:13:08 - INFO - __main__ - Step 132536: {'lr': 1.698414444069865e-05, 'samples': 25446912, 'steps': 132535, 'loss/train': 0.6798702478408813} 08/31/2021 13:13:08 - INFO - __main__ - Step 132537: {'lr': 1.6982221885447263e-05, 'samples': 25447104, 'steps': 132536, 'loss/train': 1.6267006397247314} 08/31/2021 13:13:09 - INFO - __main__ - Step 132538: {'lr': 1.698029943519011e-05, 'samples': 25447296, 'steps': 132537, 'loss/train': 1.0801386833190918} 08/31/2021 13:13:09 - INFO - __main__ - Step 132539: {'lr': 1.6978377089928028e-05, 'samples': 25447488, 'steps': 132538, 'loss/train': 0.014603971503674984} 08/31/2021 13:13:09 - INFO - __main__ - Step 132540: {'lr': 1.697645484966187e-05, 'samples': 25447680, 'steps': 132539, 'loss/train': 0.6964989304542542} 08/31/2021 13:13:11 - INFO - __main__ - Step 132541: {'lr': 1.697453271439256e-05, 'samples': 25447872, 'steps': 132540, 'loss/train': 0.4300418198108673} 08/31/2021 13:13:11 - INFO - __main__ - Step 132542: {'lr': 1.69726106841209e-05, 'samples': 25448064, 'steps': 132541, 'loss/train': 1.3444193601608276} 08/31/2021 13:13:12 - INFO - __main__ - Step 132543: {'lr': 1.697068875884783e-05, 'samples': 25448256, 'steps': 132542, 'loss/train': 0.7575052976608276} 08/31/2021 13:13:12 - INFO - __main__ - Step 132544: {'lr': 1.696876693857416e-05, 'samples': 25448448, 'steps': 132543, 'loss/train': 0.9837804436683655} 08/31/2021 13:13:12 - INFO - __main__ - Step 132545: {'lr': 1.6966845223300746e-05, 'samples': 25448640, 'steps': 132544, 'loss/train': 1.1449038982391357} 08/31/2021 13:13:15 - INFO - __main__ - Step 132546: {'lr': 1.696492361302848e-05, 'samples': 25448832, 'steps': 132545, 'loss/train': 1.331628680229187} 08/31/2021 13:13:15 - INFO - __main__ - Step 132547: {'lr': 1.6963002107758223e-05, 'samples': 25449024, 'steps': 132546, 'loss/train': 0.6173689365386963} 08/31/2021 13:13:15 - INFO - __main__ - Step 132548: {'lr': 1.6961080707490833e-05, 'samples': 25449216, 'steps': 132547, 'loss/train': 1.5326507091522217} 08/31/2021 13:13:16 - INFO - __main__ - Step 132549: {'lr': 1.6959159412227198e-05, 'samples': 25449408, 'steps': 132548, 'loss/train': 1.0859209299087524} 08/31/2021 13:13:16 - INFO - __main__ - Step 132550: {'lr': 1.6957238221968153e-05, 'samples': 25449600, 'steps': 132549, 'loss/train': 2.083207368850708} 08/31/2021 13:13:17 - INFO - __main__ - Step 132551: {'lr': 1.695531713671458e-05, 'samples': 25449792, 'steps': 132550, 'loss/train': 0.02587173879146576} 08/31/2021 13:13:18 - INFO - __main__ - Step 132552: {'lr': 1.695339615646735e-05, 'samples': 25449984, 'steps': 132551, 'loss/train': 0.7323774695396423} 08/31/2021 13:13:18 - INFO - __main__ - Step 132553: {'lr': 1.6951475281227343e-05, 'samples': 25450176, 'steps': 132552, 'loss/train': 1.2892696857452393} 08/31/2021 13:13:19 - INFO - __main__ - Step 132554: {'lr': 1.6949554510995392e-05, 'samples': 25450368, 'steps': 132553, 'loss/train': 1.200670599937439} 08/31/2021 13:13:19 - INFO - __main__ - Step 132555: {'lr': 1.694763384577236e-05, 'samples': 25450560, 'steps': 132554, 'loss/train': 1.2148199081420898} 08/31/2021 13:13:20 - INFO - __main__ - Step 132556: {'lr': 1.6945713285559162e-05, 'samples': 25450752, 'steps': 132555, 'loss/train': 1.1933364868164062} 08/31/2021 13:13:21 - INFO - __main__ - Step 132557: {'lr': 1.694379283035663e-05, 'samples': 25450944, 'steps': 132556, 'loss/train': 0.8660454750061035} 08/31/2021 13:13:22 - INFO - __main__ - Step 132558: {'lr': 1.6941872480165625e-05, 'samples': 25451136, 'steps': 132557, 'loss/train': 1.7282418012619019} 08/31/2021 13:13:22 - INFO - __main__ - Step 132559: {'lr': 1.6939952234986983e-05, 'samples': 25451328, 'steps': 132558, 'loss/train': 0.23541627824306488} 08/31/2021 13:13:22 - INFO - __main__ - Step 132560: {'lr': 1.6938032094821615e-05, 'samples': 25451520, 'steps': 132559, 'loss/train': 1.4278825521469116} 08/31/2021 13:13:23 - INFO - __main__ - Step 132561: {'lr': 1.6936112059670383e-05, 'samples': 25451712, 'steps': 132560, 'loss/train': 0.03181655332446098} 08/31/2021 13:13:24 - INFO - __main__ - Step 132562: {'lr': 1.693419212953415e-05, 'samples': 25451904, 'steps': 132561, 'loss/train': 1.6893452405929565} 08/31/2021 13:13:25 - INFO - __main__ - Step 132563: {'lr': 1.693227230441374e-05, 'samples': 25452096, 'steps': 132562, 'loss/train': 0.3235730826854706} 08/31/2021 13:13:25 - INFO - __main__ - Step 132564: {'lr': 1.693035258431008e-05, 'samples': 25452288, 'steps': 132563, 'loss/train': 0.024283666163682938} 08/31/2021 13:13:26 - INFO - __main__ - Step 132565: {'lr': 1.6928432969224e-05, 'samples': 25452480, 'steps': 132564, 'loss/train': 0.014859400689601898} 08/31/2021 13:13:26 - INFO - __main__ - Step 132566: {'lr': 1.6926513459156357e-05, 'samples': 25452672, 'steps': 132565, 'loss/train': 1.3422049283981323} 08/31/2021 13:13:26 - INFO - __main__ - Step 132567: {'lr': 1.6924594054108066e-05, 'samples': 25452864, 'steps': 132566, 'loss/train': 1.3217719793319702} 08/31/2021 13:13:28 - INFO - __main__ - Step 132568: {'lr': 1.692267475407991e-05, 'samples': 25453056, 'steps': 132567, 'loss/train': 1.690409779548645} 08/31/2021 13:13:28 - INFO - __main__ - Step 132569: {'lr': 1.6920755559072827e-05, 'samples': 25453248, 'steps': 132568, 'loss/train': 1.5577198266983032} 08/31/2021 13:13:29 - INFO - __main__ - Step 132570: {'lr': 1.6918836469087707e-05, 'samples': 25453440, 'steps': 132569, 'loss/train': 1.4147676229476929} 08/31/2021 13:13:29 - INFO - __main__ - Step 132571: {'lr': 1.69169174841253e-05, 'samples': 25453632, 'steps': 132570, 'loss/train': 0.646503210067749} 08/31/2021 13:13:29 - INFO - __main__ - Step 132572: {'lr': 1.691499860418655e-05, 'samples': 25453824, 'steps': 132571, 'loss/train': 1.5060263872146606} 08/31/2021 13:13:31 - INFO - __main__ - Step 132573: {'lr': 1.6913079829272288e-05, 'samples': 25454016, 'steps': 132572, 'loss/train': 0.7364210486412048} 08/31/2021 13:13:32 - INFO - __main__ - Step 132574: {'lr': 1.6911161159383403e-05, 'samples': 25454208, 'steps': 132573, 'loss/train': 0.907476007938385} 08/31/2021 13:13:32 - INFO - __main__ - Step 132575: {'lr': 1.6909242594520756e-05, 'samples': 25454400, 'steps': 132574, 'loss/train': 0.66709303855896} 08/31/2021 13:13:32 - INFO - __main__ - Step 132576: {'lr': 1.690732413468521e-05, 'samples': 25454592, 'steps': 132575, 'loss/train': 0.08037982136011124} 08/31/2021 13:13:33 - INFO - __main__ - Step 132577: {'lr': 1.690540577987762e-05, 'samples': 25454784, 'steps': 132576, 'loss/train': 0.03868050500750542} 08/31/2021 13:13:34 - INFO - __main__ - Step 132578: {'lr': 1.690348753009885e-05, 'samples': 25454976, 'steps': 132577, 'loss/train': 1.6449425220489502} 08/31/2021 13:13:35 - INFO - __main__ - Step 132579: {'lr': 1.6901569385349785e-05, 'samples': 25455168, 'steps': 132578, 'loss/train': 1.2636600732803345} 08/31/2021 13:13:35 - INFO - __main__ - Step 132580: {'lr': 1.689965134563126e-05, 'samples': 25455360, 'steps': 132579, 'loss/train': 1.8274486064910889} 08/31/2021 13:13:35 - INFO - __main__ - Step 132581: {'lr': 1.6897733410944166e-05, 'samples': 25455552, 'steps': 132580, 'loss/train': 1.1206389665603638} 08/31/2021 13:13:36 - INFO - __main__ - Step 132582: {'lr': 1.689581558128936e-05, 'samples': 25455744, 'steps': 132581, 'loss/train': 1.1174678802490234} 08/31/2021 13:13:37 - INFO - __main__ - Step 132583: {'lr': 1.68938978566677e-05, 'samples': 25455936, 'steps': 132582, 'loss/train': 0.11519349366426468} 08/31/2021 13:13:38 - INFO - __main__ - Step 132584: {'lr': 1.689198023708008e-05, 'samples': 25456128, 'steps': 132583, 'loss/train': 1.58677339553833} 08/31/2021 13:13:38 - INFO - __main__ - Step 132585: {'lr': 1.68900627225273e-05, 'samples': 25456320, 'steps': 132584, 'loss/train': 1.1958508491516113} 08/31/2021 13:13:39 - INFO - __main__ - Step 132586: {'lr': 1.6888145313010277e-05, 'samples': 25456512, 'steps': 132585, 'loss/train': 0.4312027096748352} 08/31/2021 13:13:39 - INFO - __main__ - Step 132587: {'lr': 1.6886228008529846e-05, 'samples': 25456704, 'steps': 132586, 'loss/train': 1.180896282196045} 08/31/2021 13:13:41 - INFO - __main__ - Step 132588: {'lr': 1.6884310809086895e-05, 'samples': 25456896, 'steps': 132587, 'loss/train': 1.0264525413513184} 08/31/2021 13:13:41 - INFO - __main__ - Step 132589: {'lr': 1.6882393714682254e-05, 'samples': 25457088, 'steps': 132588, 'loss/train': 1.0239768028259277} 08/31/2021 13:13:41 - INFO - __main__ - Step 132590: {'lr': 1.688047672531684e-05, 'samples': 25457280, 'steps': 132589, 'loss/train': 0.6905226707458496} 08/31/2021 13:13:42 - INFO - __main__ - Step 132591: {'lr': 1.687855984099146e-05, 'samples': 25457472, 'steps': 132590, 'loss/train': 1.1448607444763184} 08/31/2021 13:13:42 - INFO - __main__ - Step 132592: {'lr': 1.6876643061707026e-05, 'samples': 25457664, 'steps': 132591, 'loss/train': 1.2671812772750854} 08/31/2021 13:13:44 - INFO - __main__ - Step 132593: {'lr': 1.6874726387464347e-05, 'samples': 25457856, 'steps': 132592, 'loss/train': 0.9826638102531433} 08/31/2021 13:13:44 - INFO - __main__ - Step 132594: {'lr': 1.6872809818264334e-05, 'samples': 25458048, 'steps': 132593, 'loss/train': 1.0181097984313965} 08/31/2021 13:13:44 - INFO - __main__ - Step 132595: {'lr': 1.6870893354107852e-05, 'samples': 25458240, 'steps': 132594, 'loss/train': 0.07204203307628632} 08/31/2021 13:13:45 - INFO - __main__ - Step 132596: {'lr': 1.6868976994995734e-05, 'samples': 25458432, 'steps': 132595, 'loss/train': 1.4266154766082764} 08/31/2021 13:13:45 - INFO - __main__ - Step 132597: {'lr': 1.686706074092889e-05, 'samples': 25458624, 'steps': 132596, 'loss/train': 1.6348943710327148} 08/31/2021 13:13:47 - INFO - __main__ - Step 132598: {'lr': 1.6865144591908134e-05, 'samples': 25458816, 'steps': 132597, 'loss/train': 0.9185813069343567} 08/31/2021 13:13:48 - INFO - __main__ - Step 132599: {'lr': 1.686322854793432e-05, 'samples': 25459008, 'steps': 132598, 'loss/train': 1.2206405401229858} 08/31/2021 13:13:48 - INFO - __main__ - Step 132600: {'lr': 1.686131260900836e-05, 'samples': 25459200, 'steps': 132599, 'loss/train': 1.397230863571167} 08/31/2021 13:13:48 - INFO - __main__ - Step 132601: {'lr': 1.6859396775131098e-05, 'samples': 25459392, 'steps': 132600, 'loss/train': 0.8250610828399658} 08/31/2021 13:13:49 - INFO - __main__ - Step 132602: {'lr': 1.6857481046303358e-05, 'samples': 25459584, 'steps': 132601, 'loss/train': 0.5416764616966248} 08/31/2021 13:13:49 - INFO - __main__ - Step 132603: {'lr': 1.6855565422526058e-05, 'samples': 25459776, 'steps': 132602, 'loss/train': 1.4546617269515991} 08/31/2021 13:13:51 - INFO - __main__ - Step 132604: {'lr': 1.685364990380006e-05, 'samples': 25459968, 'steps': 132603, 'loss/train': 0.8546978831291199} 08/31/2021 13:13:51 - INFO - __main__ - Step 132605: {'lr': 1.6851734490126196e-05, 'samples': 25460160, 'steps': 132604, 'loss/train': 1.2365617752075195} 08/31/2021 13:13:51 - INFO - __main__ - Step 132606: {'lr': 1.6849819181505355e-05, 'samples': 25460352, 'steps': 132605, 'loss/train': 0.9951386451721191} 08/31/2021 13:13:52 - INFO - __main__ - Step 132607: {'lr': 1.6847903977938366e-05, 'samples': 25460544, 'steps': 132606, 'loss/train': 0.624778687953949} 08/31/2021 13:13:52 - INFO - __main__ - Step 132608: {'lr': 1.684598887942612e-05, 'samples': 25460736, 'steps': 132607, 'loss/train': 1.3648779392242432} 08/31/2021 13:13:54 - INFO - __main__ - Step 132609: {'lr': 1.684407388596948e-05, 'samples': 25460928, 'steps': 132608, 'loss/train': 1.1597422361373901} 08/31/2021 13:13:54 - INFO - __main__ - Step 132610: {'lr': 1.68421589975693e-05, 'samples': 25461120, 'steps': 132609, 'loss/train': 1.9365590810775757} 08/31/2021 13:13:54 - INFO - __main__ - Step 132611: {'lr': 1.6840244214226503e-05, 'samples': 25461312, 'steps': 132610, 'loss/train': 1.0810768604278564} 08/31/2021 13:13:55 - INFO - __main__ - Step 132612: {'lr': 1.6838329535941832e-05, 'samples': 25461504, 'steps': 132611, 'loss/train': 1.590673565864563} 08/31/2021 13:13:55 - INFO - __main__ - Step 132613: {'lr': 1.6836414962716206e-05, 'samples': 25461696, 'steps': 132612, 'loss/train': 0.18582656979560852} 08/31/2021 13:13:57 - INFO - __main__ - Step 132614: {'lr': 1.6834500494550513e-05, 'samples': 25461888, 'steps': 132613, 'loss/train': 0.7352038621902466} 08/31/2021 13:13:57 - INFO - __main__ - Step 132615: {'lr': 1.683258613144559e-05, 'samples': 25462080, 'steps': 132614, 'loss/train': 1.2011363506317139} 08/31/2021 13:13:57 - INFO - __main__ - Step 132616: {'lr': 1.6830671873402288e-05, 'samples': 25462272, 'steps': 132615, 'loss/train': 0.23391714692115784} 08/31/2021 13:13:58 - INFO - __main__ - Step 132617: {'lr': 1.68287577204215e-05, 'samples': 25462464, 'steps': 132616, 'loss/train': 1.2624627351760864} 08/31/2021 13:13:58 - INFO - __main__ - Step 132618: {'lr': 1.682684367250409e-05, 'samples': 25462656, 'steps': 132617, 'loss/train': 1.2834486961364746} 08/31/2021 13:13:59 - INFO - __main__ - Step 132619: {'lr': 1.6824929729650886e-05, 'samples': 25462848, 'steps': 132618, 'loss/train': 0.19186565279960632} 08/31/2021 13:14:00 - INFO - __main__ - Step 132620: {'lr': 1.6823015891862775e-05, 'samples': 25463040, 'steps': 132619, 'loss/train': 2.547053813934326} 08/31/2021 13:14:01 - INFO - __main__ - Step 132621: {'lr': 1.682110215914062e-05, 'samples': 25463232, 'steps': 132620, 'loss/train': 1.655973196029663} 08/31/2021 13:14:01 - INFO - __main__ - Step 132622: {'lr': 1.6819188531485287e-05, 'samples': 25463424, 'steps': 132621, 'loss/train': 0.7408429980278015} 08/31/2021 13:14:01 - INFO - __main__ - Step 132623: {'lr': 1.6817275008897624e-05, 'samples': 25463616, 'steps': 132622, 'loss/train': 1.1636948585510254} 08/31/2021 13:14:02 - INFO - __main__ - Step 132624: {'lr': 1.681536159137853e-05, 'samples': 25463808, 'steps': 132623, 'loss/train': 1.4753354787826538} 08/31/2021 13:14:04 - INFO - __main__ - Step 132625: {'lr': 1.6813448278928805e-05, 'samples': 25464000, 'steps': 132624, 'loss/train': 0.897736132144928} 08/31/2021 13:14:04 - INFO - __main__ - Step 132626: {'lr': 1.681153507154934e-05, 'samples': 25464192, 'steps': 132625, 'loss/train': 1.1357053518295288} 08/31/2021 13:14:04 - INFO - __main__ - Step 132627: {'lr': 1.680962196924099e-05, 'samples': 25464384, 'steps': 132626, 'loss/train': 0.026649637147784233} 08/31/2021 13:14:05 - INFO - __main__ - Step 132628: {'lr': 1.6807708972004622e-05, 'samples': 25464576, 'steps': 132627, 'loss/train': 0.11577365547418594} 08/31/2021 13:14:05 - INFO - __main__ - Step 132629: {'lr': 1.680579607984112e-05, 'samples': 25464768, 'steps': 132628, 'loss/train': 0.8639793992042542} 08/31/2021 13:14:05 - INFO - __main__ - Step 132630: {'lr': 1.6803883292751314e-05, 'samples': 25464960, 'steps': 132629, 'loss/train': 1.0203571319580078} 08/31/2021 13:14:06 - INFO - __main__ - Step 132631: {'lr': 1.68019706107361e-05, 'samples': 25465152, 'steps': 132630, 'loss/train': 1.2064002752304077} 08/31/2021 13:14:07 - INFO - __main__ - Step 132632: {'lr': 1.6800058033796307e-05, 'samples': 25465344, 'steps': 132631, 'loss/train': 0.014345110394060612} 08/31/2021 13:14:08 - INFO - __main__ - Step 132633: {'lr': 1.679814556193279e-05, 'samples': 25465536, 'steps': 132632, 'loss/train': 0.10205437988042831} 08/31/2021 13:14:08 - INFO - __main__ - Step 132634: {'lr': 1.6796233195146447e-05, 'samples': 25465728, 'steps': 132633, 'loss/train': 0.5281869173049927} 08/31/2021 13:14:08 - INFO - __main__ - Step 132635: {'lr': 1.6794320933438135e-05, 'samples': 25465920, 'steps': 132634, 'loss/train': 0.7994007468223572} 08/31/2021 13:14:09 - INFO - __main__ - Step 132636: {'lr': 1.6792408776808682e-05, 'samples': 25466112, 'steps': 132635, 'loss/train': 1.1637706756591797} 08/31/2021 13:14:10 - INFO - __main__ - Step 132637: {'lr': 1.679049672525898e-05, 'samples': 25466304, 'steps': 132636, 'loss/train': 1.1991581916809082} 08/31/2021 13:14:11 - INFO - __main__ - Step 132638: {'lr': 1.678858477878992e-05, 'samples': 25466496, 'steps': 132637, 'loss/train': 0.7170588970184326} 08/31/2021 13:14:11 - INFO - __main__ - Step 132639: {'lr': 1.6786672937402296e-05, 'samples': 25466688, 'steps': 132638, 'loss/train': 1.6263378858566284} 08/31/2021 13:14:11 - INFO - __main__ - Step 132640: {'lr': 1.678476120109698e-05, 'samples': 25466880, 'steps': 132639, 'loss/train': 1.1577621698379517} 08/31/2021 13:14:12 - INFO - __main__ - Step 132641: {'lr': 1.6782849569874858e-05, 'samples': 25467072, 'steps': 132640, 'loss/train': 1.2105348110198975} 08/31/2021 13:14:12 - INFO - __main__ - Step 132642: {'lr': 1.6780938043736788e-05, 'samples': 25467264, 'steps': 132641, 'loss/train': 1.75361967086792} 08/31/2021 13:14:14 - INFO - __main__ - Step 132643: {'lr': 1.677902662268363e-05, 'samples': 25467456, 'steps': 132642, 'loss/train': 1.154466152191162} 08/31/2021 13:14:14 - INFO - __main__ - Step 132644: {'lr': 1.6777115306716244e-05, 'samples': 25467648, 'steps': 132643, 'loss/train': 0.025473589077591896} 08/31/2021 13:14:15 - INFO - __main__ - Step 132645: {'lr': 1.6775204095835496e-05, 'samples': 25467840, 'steps': 132644, 'loss/train': 0.849587082862854} 08/31/2021 13:14:15 - INFO - __main__ - Step 132646: {'lr': 1.677329299004224e-05, 'samples': 25468032, 'steps': 132645, 'loss/train': 1.8968403339385986} 08/31/2021 13:14:15 - INFO - __main__ - Step 132647: {'lr': 1.6771381989337337e-05, 'samples': 25468224, 'steps': 132646, 'loss/train': 1.8917391300201416} 08/31/2021 13:14:17 - INFO - __main__ - Step 132648: {'lr': 1.676947109372165e-05, 'samples': 25468416, 'steps': 132647, 'loss/train': 0.14194267988204956} 08/31/2021 13:14:18 - INFO - __main__ - Step 132649: {'lr': 1.676756030319604e-05, 'samples': 25468608, 'steps': 132648, 'loss/train': 1.5914634466171265} 08/31/2021 13:14:18 - INFO - __main__ - Step 132650: {'lr': 1.6765649617761364e-05, 'samples': 25468800, 'steps': 132649, 'loss/train': 1.272989273071289} 08/31/2021 13:14:18 - INFO - __main__ - Step 132651: {'lr': 1.6763739037418514e-05, 'samples': 25468992, 'steps': 132650, 'loss/train': 0.9925878047943115} 08/31/2021 13:14:19 - INFO - __main__ - Step 132652: {'lr': 1.676182856216832e-05, 'samples': 25469184, 'steps': 132651, 'loss/train': 0.747560977935791} 08/31/2021 13:14:21 - INFO - __main__ - Step 132653: {'lr': 1.6759918192011613e-05, 'samples': 25469376, 'steps': 132652, 'loss/train': 2.177821159362793} 08/31/2021 13:14:21 - INFO - __main__ - Step 132654: {'lr': 1.6758007926949314e-05, 'samples': 25469568, 'steps': 132653, 'loss/train': 0.5781207084655762} 08/31/2021 13:14:22 - INFO - __main__ - Step 132655: {'lr': 1.6756097766982254e-05, 'samples': 25469760, 'steps': 132654, 'loss/train': 1.5386555194854736} 08/31/2021 13:14:22 - INFO - __main__ - Step 132656: {'lr': 1.6754187712111262e-05, 'samples': 25469952, 'steps': 132655, 'loss/train': 1.252708911895752} 08/31/2021 13:14:22 - INFO - __main__ - Step 132657: {'lr': 1.6752277762337285e-05, 'samples': 25470144, 'steps': 132656, 'loss/train': 0.831396758556366} 08/31/2021 13:14:23 - INFO - __main__ - Step 132658: {'lr': 1.6750367917661103e-05, 'samples': 25470336, 'steps': 132657, 'loss/train': 0.03599590063095093} 08/31/2021 13:14:25 - INFO - __main__ - Step 132659: {'lr': 1.6748458178083597e-05, 'samples': 25470528, 'steps': 132658, 'loss/train': 0.5339445471763611} 08/31/2021 13:14:25 - INFO - __main__ - Step 132660: {'lr': 1.6746548543605662e-05, 'samples': 25470720, 'steps': 132659, 'loss/train': 1.4143062829971313} 08/31/2021 13:14:25 - INFO - __main__ - Step 132661: {'lr': 1.6744639014228126e-05, 'samples': 25470912, 'steps': 132660, 'loss/train': 1.756982445716858} 08/31/2021 13:14:26 - INFO - __main__ - Step 132662: {'lr': 1.674272958995185e-05, 'samples': 25471104, 'steps': 132661, 'loss/train': 0.10975468158721924} 08/31/2021 13:14:26 - INFO - __main__ - Step 132663: {'lr': 1.6740820270777696e-05, 'samples': 25471296, 'steps': 132662, 'loss/train': 0.05647706240415573} 08/31/2021 13:14:28 - INFO - __main__ - Step 132664: {'lr': 1.673891105670658e-05, 'samples': 25471488, 'steps': 132663, 'loss/train': 1.3339323997497559} 08/31/2021 13:14:28 - INFO - __main__ - Step 132665: {'lr': 1.6737001947739278e-05, 'samples': 25471680, 'steps': 132664, 'loss/train': 1.22152578830719} 08/31/2021 13:14:28 - INFO - __main__ - Step 132666: {'lr': 1.673509294387665e-05, 'samples': 25471872, 'steps': 132665, 'loss/train': 0.6892866492271423} 08/31/2021 13:14:29 - INFO - __main__ - Step 132667: {'lr': 1.6733184045119616e-05, 'samples': 25472064, 'steps': 132666, 'loss/train': 0.32620763778686523} 08/31/2021 13:14:29 - INFO - __main__ - Step 132668: {'lr': 1.6731275251469003e-05, 'samples': 25472256, 'steps': 132667, 'loss/train': 0.5267593860626221} 08/31/2021 13:14:31 - INFO - __main__ - Step 132669: {'lr': 1.6729366562925676e-05, 'samples': 25472448, 'steps': 132668, 'loss/train': 0.6081627607345581} 08/31/2021 13:14:31 - INFO - __main__ - Step 132670: {'lr': 1.6727457979490517e-05, 'samples': 25472640, 'steps': 132669, 'loss/train': 1.5098130702972412} 08/31/2021 13:14:32 - INFO - __main__ - Step 132671: {'lr': 1.6725549501164338e-05, 'samples': 25472832, 'steps': 132670, 'loss/train': 1.0526916980743408} 08/31/2021 13:14:32 - INFO - __main__ - Step 132672: {'lr': 1.6723641127948053e-05, 'samples': 25473024, 'steps': 132671, 'loss/train': 0.4167754650115967} 08/31/2021 13:14:32 - INFO - __main__ - Step 132673: {'lr': 1.6721732859842464e-05, 'samples': 25473216, 'steps': 132672, 'loss/train': 1.3213881254196167} 08/31/2021 13:14:34 - INFO - __main__ - Step 132674: {'lr': 1.671982469684849e-05, 'samples': 25473408, 'steps': 132673, 'loss/train': 1.0486574172973633} 08/31/2021 13:14:34 - INFO - __main__ - Step 132675: {'lr': 1.6717916638966963e-05, 'samples': 25473600, 'steps': 132674, 'loss/train': 1.3210711479187012} 08/31/2021 13:14:35 - INFO - __main__ - Step 132676: {'lr': 1.6716008686198713e-05, 'samples': 25473792, 'steps': 132675, 'loss/train': 0.8296697735786438} 08/31/2021 13:14:35 - INFO - __main__ - Step 132677: {'lr': 1.671410083854466e-05, 'samples': 25473984, 'steps': 132676, 'loss/train': 1.6746710538864136} 08/31/2021 13:14:35 - INFO - __main__ - Step 132678: {'lr': 1.6712193096005662e-05, 'samples': 25474176, 'steps': 132677, 'loss/train': 0.9646174311637878} 08/31/2021 13:14:37 - INFO - __main__ - Step 132679: {'lr': 1.6710285458582524e-05, 'samples': 25474368, 'steps': 132678, 'loss/train': 0.9854786992073059} 08/31/2021 13:14:37 - INFO - __main__ - Step 132680: {'lr': 1.670837792627611e-05, 'samples': 25474560, 'steps': 132679, 'loss/train': 1.1383848190307617} 08/31/2021 13:14:38 - INFO - __main__ - Step 132681: {'lr': 1.67064704990873e-05, 'samples': 25474752, 'steps': 132680, 'loss/train': 0.939037024974823} 08/31/2021 13:14:38 - INFO - __main__ - Step 132682: {'lr': 1.670456317701696e-05, 'samples': 25474944, 'steps': 132681, 'loss/train': 1.1413325071334839} 08/31/2021 13:14:38 - INFO - __main__ - Step 132683: {'lr': 1.6702655960065956e-05, 'samples': 25475136, 'steps': 132682, 'loss/train': 0.92618328332901} 08/31/2021 13:14:40 - INFO - __main__ - Step 132684: {'lr': 1.6700748848235137e-05, 'samples': 25475328, 'steps': 132683, 'loss/train': 1.1017911434173584} 08/31/2021 13:14:41 - INFO - __main__ - Step 132685: {'lr': 1.669884184152534e-05, 'samples': 25475520, 'steps': 132684, 'loss/train': 0.7717119455337524} 08/31/2021 13:14:41 - INFO - __main__ - Step 132686: {'lr': 1.6696934939937458e-05, 'samples': 25475712, 'steps': 132685, 'loss/train': 0.9664143919944763} 08/31/2021 13:14:41 - INFO - __main__ - Step 132687: {'lr': 1.6695028143472347e-05, 'samples': 25475904, 'steps': 132686, 'loss/train': 1.2278869152069092} 08/31/2021 13:14:42 - INFO - __main__ - Step 132688: {'lr': 1.6693121452130838e-05, 'samples': 25476096, 'steps': 132687, 'loss/train': 0.9861881136894226} 08/31/2021 13:14:42 - INFO - __main__ - Step 132689: {'lr': 1.6691214865913852e-05, 'samples': 25476288, 'steps': 132688, 'loss/train': 0.3261675536632538} 08/31/2021 13:14:43 - INFO - __main__ - Step 132690: {'lr': 1.668930838482216e-05, 'samples': 25476480, 'steps': 132689, 'loss/train': 1.565305471420288} 08/31/2021 13:14:44 - INFO - __main__ - Step 132691: {'lr': 1.6687402008856683e-05, 'samples': 25476672, 'steps': 132690, 'loss/train': 0.7844839692115784} 08/31/2021 13:14:44 - INFO - __main__ - Step 132692: {'lr': 1.6685495738018253e-05, 'samples': 25476864, 'steps': 132691, 'loss/train': 0.22274866700172424} 08/31/2021 13:14:45 - INFO - __main__ - Step 132693: {'lr': 1.668358957230773e-05, 'samples': 25477056, 'steps': 132692, 'loss/train': 1.4266213178634644} 08/31/2021 13:14:45 - INFO - __main__ - Step 132694: {'lr': 1.6681683511725997e-05, 'samples': 25477248, 'steps': 132693, 'loss/train': 0.23988832533359528} 08/31/2021 13:14:47 - INFO - __main__ - Step 132695: {'lr': 1.6679777556273868e-05, 'samples': 25477440, 'steps': 132694, 'loss/train': 0.2556403577327728} 08/31/2021 13:14:47 - INFO - __main__ - Step 132696: {'lr': 1.6677871705952253e-05, 'samples': 25477632, 'steps': 132695, 'loss/train': 0.025346236303448677} 08/31/2021 13:14:48 - INFO - __main__ - Step 132697: {'lr': 1.6675965960761986e-05, 'samples': 25477824, 'steps': 132696, 'loss/train': 1.3559954166412354} 08/31/2021 13:14:48 - INFO - __main__ - Step 132698: {'lr': 1.6674060320703927e-05, 'samples': 25478016, 'steps': 132697, 'loss/train': 2.215343713760376} 08/31/2021 13:14:48 - INFO - __main__ - Step 132699: {'lr': 1.6672154785778937e-05, 'samples': 25478208, 'steps': 132698, 'loss/train': 1.2210838794708252} 08/31/2021 13:14:49 - INFO - __main__ - Step 132700: {'lr': 1.6670249355987933e-05, 'samples': 25478400, 'steps': 132699, 'loss/train': 0.4354223310947418} 08/31/2021 13:14:51 - INFO - __main__ - Step 132701: {'lr': 1.6668344031331662e-05, 'samples': 25478592, 'steps': 132700, 'loss/train': 1.004975438117981} 08/31/2021 13:14:52 - INFO - __main__ - Step 132702: {'lr': 1.6666438811811014e-05, 'samples': 25478784, 'steps': 132701, 'loss/train': 1.1736820936203003} 08/31/2021 13:14:52 - INFO - __main__ - Step 132703: {'lr': 1.6664533697426874e-05, 'samples': 25478976, 'steps': 132702, 'loss/train': 1.2875841856002808} 08/31/2021 13:14:52 - INFO - __main__ - Step 132704: {'lr': 1.666262868818011e-05, 'samples': 25479168, 'steps': 132703, 'loss/train': 1.032370686531067} 08/31/2021 13:14:53 - INFO - __main__ - Step 132705: {'lr': 1.6660723784071573e-05, 'samples': 25479360, 'steps': 132704, 'loss/train': 0.7216379046440125} 08/31/2021 13:14:53 - INFO - __main__ - Step 132706: {'lr': 1.6658818985102075e-05, 'samples': 25479552, 'steps': 132705, 'loss/train': 2.572618246078491} 08/31/2021 13:14:53 - INFO - __main__ - Step 132707: {'lr': 1.6656914291272558e-05, 'samples': 25479744, 'steps': 132706, 'loss/train': 2.622011423110962} 08/31/2021 13:14:55 - INFO - __main__ - Step 132708: {'lr': 1.6655009702583794e-05, 'samples': 25479936, 'steps': 132707, 'loss/train': 2.5733797550201416} 08/31/2021 13:14:55 - INFO - __main__ - Step 132709: {'lr': 1.6653105219036708e-05, 'samples': 25480128, 'steps': 132708, 'loss/train': 0.9294471740722656} 08/31/2021 13:14:56 - INFO - __main__ - Step 132710: {'lr': 1.6651200840632123e-05, 'samples': 25480320, 'steps': 132709, 'loss/train': 1.3976681232452393} 08/31/2021 13:14:56 - INFO - __main__ - Step 132711: {'lr': 1.6649296567370938e-05, 'samples': 25480512, 'steps': 132710, 'loss/train': 1.0152428150177002} 08/31/2021 13:14:57 - INFO - __main__ - Step 132712: {'lr': 1.6647392399253947e-05, 'samples': 25480704, 'steps': 132711, 'loss/train': 1.152410626411438} 08/31/2021 13:14:59 - INFO - __main__ - Step 132713: {'lr': 1.6645488336282044e-05, 'samples': 25480896, 'steps': 132712, 'loss/train': 1.135151743888855} 08/31/2021 13:14:59 - INFO - __main__ - Step 132714: {'lr': 1.664358437845609e-05, 'samples': 25481088, 'steps': 132713, 'loss/train': 0.8688608407974243} 08/31/2021 13:15:00 - INFO - __main__ - Step 132715: {'lr': 1.6641680525776914e-05, 'samples': 25481280, 'steps': 132714, 'loss/train': 1.0072641372680664} 08/31/2021 13:15:00 - INFO - __main__ - Step 132716: {'lr': 1.6639776778245436e-05, 'samples': 25481472, 'steps': 132715, 'loss/train': 0.03011825866997242} 08/31/2021 13:15:00 - INFO - __main__ - Step 132717: {'lr': 1.663787313586243e-05, 'samples': 25481664, 'steps': 132716, 'loss/train': 1.6714916229248047} 08/31/2021 13:15:02 - INFO - __main__ - Step 132718: {'lr': 1.6635969598628812e-05, 'samples': 25481856, 'steps': 132717, 'loss/train': 0.9577465653419495} 08/31/2021 13:15:02 - INFO - __main__ - Step 132719: {'lr': 1.6634066166545418e-05, 'samples': 25482048, 'steps': 132718, 'loss/train': 0.4181990623474121} 08/31/2021 13:15:03 - INFO - __main__ - Step 132720: {'lr': 1.6632162839613134e-05, 'samples': 25482240, 'steps': 132719, 'loss/train': 1.1045907735824585} 08/31/2021 13:15:03 - INFO - __main__ - Step 132721: {'lr': 1.6630259617832795e-05, 'samples': 25482432, 'steps': 132720, 'loss/train': 1.2359747886657715} 08/31/2021 13:15:03 - INFO - __main__ - Step 132722: {'lr': 1.6628356501205283e-05, 'samples': 25482624, 'steps': 132721, 'loss/train': 0.5064986944198608} 08/31/2021 13:15:05 - INFO - __main__ - Step 132723: {'lr': 1.662645348973138e-05, 'samples': 25482816, 'steps': 132722, 'loss/train': 1.4076215028762817} 08/31/2021 13:15:06 - INFO - __main__ - Step 132724: {'lr': 1.6624550583412028e-05, 'samples': 25483008, 'steps': 132723, 'loss/train': 2.7425572872161865} 08/31/2021 13:15:06 - INFO - __main__ - Step 132725: {'lr': 1.6622647782248036e-05, 'samples': 25483200, 'steps': 132724, 'loss/train': 1.2304966449737549} 08/31/2021 13:15:06 - INFO - __main__ - Step 132726: {'lr': 1.6620745086240285e-05, 'samples': 25483392, 'steps': 132725, 'loss/train': 1.4983140230178833} 08/31/2021 13:15:07 - INFO - __main__ - Step 132727: {'lr': 1.6618842495389614e-05, 'samples': 25483584, 'steps': 132726, 'loss/train': 1.520374059677124} 08/31/2021 13:15:07 - INFO - __main__ - Step 132728: {'lr': 1.6616940009696907e-05, 'samples': 25483776, 'steps': 132727, 'loss/train': 0.015461372211575508} 08/31/2021 13:15:07 - INFO - __main__ - Step 132729: {'lr': 1.6615037629163e-05, 'samples': 25483968, 'steps': 132728, 'loss/train': 0.3641390800476074} 08/31/2021 13:15:09 - INFO - __main__ - Step 132730: {'lr': 1.661313535378875e-05, 'samples': 25484160, 'steps': 132729, 'loss/train': 0.016102589666843414} 08/31/2021 13:15:09 - INFO - __main__ - Step 132731: {'lr': 1.661123318357502e-05, 'samples': 25484352, 'steps': 132730, 'loss/train': 0.4762518107891083} 08/31/2021 13:15:10 - INFO - __main__ - Step 132732: {'lr': 1.660933111852267e-05, 'samples': 25484544, 'steps': 132731, 'loss/train': 0.1289970427751541} 08/31/2021 13:15:10 - INFO - __main__ - Step 132733: {'lr': 1.6607429158632587e-05, 'samples': 25484736, 'steps': 132732, 'loss/train': 1.4705473184585571} 08/31/2021 13:15:10 - INFO - __main__ - Step 132734: {'lr': 1.6605527303905548e-05, 'samples': 25484928, 'steps': 132733, 'loss/train': 1.2316579818725586} 08/31/2021 13:15:12 - INFO - __main__ - Step 132735: {'lr': 1.660362555434247e-05, 'samples': 25485120, 'steps': 132734, 'loss/train': 0.8667098879814148} 08/31/2021 13:15:13 - INFO - __main__ - Step 132736: {'lr': 1.660172390994419e-05, 'samples': 25485312, 'steps': 132735, 'loss/train': 1.2647298574447632} 08/31/2021 13:15:13 - INFO - __main__ - Step 132737: {'lr': 1.6599822370711586e-05, 'samples': 25485504, 'steps': 132736, 'loss/train': 1.4661344289779663} 08/31/2021 13:15:13 - INFO - __main__ - Step 132738: {'lr': 1.65979209366455e-05, 'samples': 25485696, 'steps': 132737, 'loss/train': 0.5033321976661682} 08/31/2021 13:15:14 - INFO - __main__ - Step 132739: {'lr': 1.659601960774676e-05, 'samples': 25485888, 'steps': 132738, 'loss/train': 1.1426807641983032} 08/31/2021 13:15:14 - INFO - __main__ - Step 132740: {'lr': 1.659411838401628e-05, 'samples': 25486080, 'steps': 132739, 'loss/train': 0.8567484021186829} 08/31/2021 13:15:15 - INFO - __main__ - Step 132741: {'lr': 1.6592217265454874e-05, 'samples': 25486272, 'steps': 132740, 'loss/train': 1.4895254373550415} 08/31/2021 13:15:16 - INFO - __main__ - Step 132742: {'lr': 1.659031625206342e-05, 'samples': 25486464, 'steps': 132741, 'loss/train': 0.7392835021018982} 08/31/2021 13:15:16 - INFO - __main__ - Step 132743: {'lr': 1.6588415343842782e-05, 'samples': 25486656, 'steps': 132742, 'loss/train': 0.7849463224411011} 08/31/2021 13:15:17 - INFO - __main__ - Step 132744: {'lr': 1.6586514540793795e-05, 'samples': 25486848, 'steps': 132743, 'loss/train': 0.07620344310998917} 08/31/2021 13:15:17 - INFO - __main__ - Step 132745: {'lr': 1.6584613842917346e-05, 'samples': 25487040, 'steps': 132744, 'loss/train': 1.5112804174423218} 08/31/2021 13:15:20 - INFO - __main__ - Step 132746: {'lr': 1.6582713250214236e-05, 'samples': 25487232, 'steps': 132745, 'loss/train': 2.7764787673950195} 08/31/2021 13:15:20 - INFO - __main__ - Step 132747: {'lr': 1.658081276268536e-05, 'samples': 25487424, 'steps': 132746, 'loss/train': 1.033995509147644} 08/31/2021 13:15:20 - INFO - __main__ - Step 132748: {'lr': 1.6578912380331574e-05, 'samples': 25487616, 'steps': 132747, 'loss/train': 0.950683057308197} 08/31/2021 13:15:21 - INFO - __main__ - Step 132749: {'lr': 1.657701210315371e-05, 'samples': 25487808, 'steps': 132748, 'loss/train': 0.6105360984802246} 08/31/2021 13:15:21 - INFO - __main__ - Step 132750: {'lr': 1.657511193115266e-05, 'samples': 25488000, 'steps': 132749, 'loss/train': 1.7564136981964111} 08/31/2021 13:15:21 - INFO - __main__ - Step 132751: {'lr': 1.657321186432925e-05, 'samples': 25488192, 'steps': 132750, 'loss/train': 0.951071560382843} 08/31/2021 13:15:22 - INFO - __main__ - Step 132752: {'lr': 1.657131190268435e-05, 'samples': 25488384, 'steps': 132751, 'loss/train': 0.8193097710609436} 08/31/2021 13:15:23 - INFO - __main__ - Step 132753: {'lr': 1.6569412046218814e-05, 'samples': 25488576, 'steps': 132752, 'loss/train': 1.3192079067230225} 08/31/2021 13:15:24 - INFO - __main__ - Step 132754: {'lr': 1.65675122949335e-05, 'samples': 25488768, 'steps': 132753, 'loss/train': 1.5109819173812866} 08/31/2021 13:15:24 - INFO - __main__ - Step 132755: {'lr': 1.6565612648829276e-05, 'samples': 25488960, 'steps': 132754, 'loss/train': 0.28220516443252563} 08/31/2021 13:15:24 - INFO - __main__ - Step 132756: {'lr': 1.656371310790697e-05, 'samples': 25489152, 'steps': 132755, 'loss/train': 0.9885551929473877} 08/31/2021 13:15:25 - INFO - __main__ - Step 132757: {'lr': 1.656181367216744e-05, 'samples': 25489344, 'steps': 132756, 'loss/train': 1.6672366857528687} 08/31/2021 13:15:27 - INFO - __main__ - Step 132758: {'lr': 1.655991434161158e-05, 'samples': 25489536, 'steps': 132757, 'loss/train': 0.9562859535217285} 08/31/2021 13:15:27 - INFO - __main__ - Step 132759: {'lr': 1.655801511624025e-05, 'samples': 25489728, 'steps': 132758, 'loss/train': 0.7122150659561157} 08/31/2021 13:15:28 - INFO - __main__ - Step 132760: {'lr': 1.655611599605425e-05, 'samples': 25489920, 'steps': 132759, 'loss/train': 0.015696285292506218} 08/31/2021 13:15:28 - INFO - __main__ - Step 132761: {'lr': 1.6554216981054443e-05, 'samples': 25490112, 'steps': 132760, 'loss/train': 1.2230011224746704} 08/31/2021 13:15:28 - INFO - __main__ - Step 132762: {'lr': 1.655231807124172e-05, 'samples': 25490304, 'steps': 132761, 'loss/train': 1.4853569269180298} 08/31/2021 13:15:29 - INFO - __main__ - Step 132763: {'lr': 1.6550419266616907e-05, 'samples': 25490496, 'steps': 132762, 'loss/train': 0.7356501817703247} 08/31/2021 13:15:29 - INFO - __main__ - Step 132764: {'lr': 1.654852056718087e-05, 'samples': 25490688, 'steps': 132763, 'loss/train': 2.8738534450531006} 08/31/2021 13:15:30 - INFO - __main__ - Step 132765: {'lr': 1.6546621972934467e-05, 'samples': 25490880, 'steps': 132764, 'loss/train': 1.391295313835144} 08/31/2021 13:15:31 - INFO - __main__ - Step 132766: {'lr': 1.654472348387856e-05, 'samples': 25491072, 'steps': 132765, 'loss/train': 0.6364267468452454} 08/31/2021 13:15:31 - INFO - __main__ - Step 132767: {'lr': 1.6542825100014007e-05, 'samples': 25491264, 'steps': 132766, 'loss/train': 0.9010512232780457} 08/31/2021 13:15:32 - INFO - __main__ - Step 132768: {'lr': 1.6540926821341646e-05, 'samples': 25491456, 'steps': 132767, 'loss/train': 0.3869361877441406} 08/31/2021 13:15:32 - INFO - __main__ - Step 132769: {'lr': 1.653902864786233e-05, 'samples': 25491648, 'steps': 132768, 'loss/train': 0.821161150932312} 08/31/2021 13:15:34 - INFO - __main__ - Step 132770: {'lr': 1.6537130579576924e-05, 'samples': 25491840, 'steps': 132769, 'loss/train': 0.6173614859580994} 08/31/2021 13:15:34 - INFO - __main__ - Step 132771: {'lr': 1.6535232616486318e-05, 'samples': 25492032, 'steps': 132770, 'loss/train': 1.54310142993927} 08/31/2021 13:15:35 - INFO - __main__ - Step 132772: {'lr': 1.653333475859134e-05, 'samples': 25492224, 'steps': 132771, 'loss/train': 0.9808894991874695} 08/31/2021 13:15:35 - INFO - __main__ - Step 132773: {'lr': 1.6531437005892825e-05, 'samples': 25492416, 'steps': 132772, 'loss/train': 1.4119348526000977} 08/31/2021 13:15:35 - INFO - __main__ - Step 132774: {'lr': 1.6529539358391605e-05, 'samples': 25492608, 'steps': 132773, 'loss/train': 1.1473692655563354} 08/31/2021 13:15:37 - INFO - __main__ - Step 132775: {'lr': 1.6527641816088597e-05, 'samples': 25492800, 'steps': 132774, 'loss/train': 1.0304780006408691} 08/31/2021 13:15:38 - INFO - __main__ - Step 132776: {'lr': 1.652574437898463e-05, 'samples': 25492992, 'steps': 132775, 'loss/train': 1.6613705158233643} 08/31/2021 13:15:38 - INFO - __main__ - Step 132777: {'lr': 1.652384704708057e-05, 'samples': 25493184, 'steps': 132776, 'loss/train': 1.0349153280258179} 08/31/2021 13:15:38 - INFO - __main__ - Step 132778: {'lr': 1.6521949820377246e-05, 'samples': 25493376, 'steps': 132777, 'loss/train': 0.39701759815216064} 08/31/2021 13:15:39 - INFO - __main__ - Step 132779: {'lr': 1.652005269887552e-05, 'samples': 25493568, 'steps': 132778, 'loss/train': 0.6843747496604919} 08/31/2021 13:15:40 - INFO - __main__ - Step 132780: {'lr': 1.651815568257628e-05, 'samples': 25493760, 'steps': 132779, 'loss/train': 1.0329792499542236} 08/31/2021 13:15:41 - INFO - __main__ - Step 132781: {'lr': 1.651625877148033e-05, 'samples': 25493952, 'steps': 132780, 'loss/train': 0.6331466436386108} 08/31/2021 13:15:41 - INFO - __main__ - Step 132782: {'lr': 1.651436196558856e-05, 'samples': 25494144, 'steps': 132781, 'loss/train': 0.038114387542009354} 08/31/2021 13:15:41 - INFO - __main__ - Step 132783: {'lr': 1.651246526490183e-05, 'samples': 25494336, 'steps': 132782, 'loss/train': 0.6163533329963684} 08/31/2021 13:15:42 - INFO - __main__ - Step 132784: {'lr': 1.6510568669420967e-05, 'samples': 25494528, 'steps': 132783, 'loss/train': 1.005976676940918} 08/31/2021 13:15:44 - INFO - __main__ - Step 132785: {'lr': 1.6508672179146892e-05, 'samples': 25494720, 'steps': 132784, 'loss/train': 0.916138231754303} 08/31/2021 13:15:44 - INFO - __main__ - Step 132786: {'lr': 1.6506775794080358e-05, 'samples': 25494912, 'steps': 132785, 'loss/train': 0.3942014276981354} 08/31/2021 13:15:45 - INFO - __main__ - Step 132787: {'lr': 1.6504879514222248e-05, 'samples': 25495104, 'steps': 132786, 'loss/train': 0.07703419029712677} 08/31/2021 13:15:45 - INFO - __main__ - Step 132788: {'lr': 1.650298333957348e-05, 'samples': 25495296, 'steps': 132787, 'loss/train': 0.6643555164337158} 08/31/2021 13:15:45 - INFO - __main__ - Step 132789: {'lr': 1.650108727013483e-05, 'samples': 25495488, 'steps': 132788, 'loss/train': 1.1588153839111328} 08/31/2021 13:15:46 - INFO - __main__ - Step 132790: {'lr': 1.6499191305907184e-05, 'samples': 25495680, 'steps': 132789, 'loss/train': 0.855225145816803} 08/31/2021 13:15:47 - INFO - __main__ - Step 132791: {'lr': 1.6497295446891407e-05, 'samples': 25495872, 'steps': 132790, 'loss/train': 0.24920664727687836} 08/31/2021 13:15:47 - INFO - __main__ - Step 132792: {'lr': 1.649539969308836e-05, 'samples': 25496064, 'steps': 132791, 'loss/train': 1.0016567707061768} 08/31/2021 13:15:48 - INFO - __main__ - Step 132793: {'lr': 1.649350404449887e-05, 'samples': 25496256, 'steps': 132792, 'loss/train': 1.1981548070907593} 08/31/2021 13:15:48 - INFO - __main__ - Step 132794: {'lr': 1.64916085011238e-05, 'samples': 25496448, 'steps': 132793, 'loss/train': 1.1278852224349976} 08/31/2021 13:15:49 - INFO - __main__ - Step 132795: {'lr': 1.648971306296404e-05, 'samples': 25496640, 'steps': 132794, 'loss/train': 1.2774745225906372} 08/31/2021 13:15:50 - INFO - __main__ - Step 132796: {'lr': 1.6487817730020365e-05, 'samples': 25496832, 'steps': 132795, 'loss/train': 1.3051139116287231} 08/31/2021 13:15:50 - INFO - __main__ - Step 132797: {'lr': 1.6485922502293693e-05, 'samples': 25497024, 'steps': 132796, 'loss/train': 1.0015239715576172} 08/31/2021 13:15:51 - INFO - __main__ - Step 132798: {'lr': 1.648402737978488e-05, 'samples': 25497216, 'steps': 132797, 'loss/train': 0.869419515132904} 08/31/2021 13:15:51 - INFO - __main__ - Step 132799: {'lr': 1.6482132362494794e-05, 'samples': 25497408, 'steps': 132798, 'loss/train': 0.990629255771637} 08/31/2021 13:15:51 - INFO - __main__ - Step 132800: {'lr': 1.6480237450424206e-05, 'samples': 25497600, 'steps': 132799, 'loss/train': 0.2933792173862457} 08/31/2021 13:15:53 - INFO - __main__ - Step 132801: {'lr': 1.6478342643574006e-05, 'samples': 25497792, 'steps': 132800, 'loss/train': 1.3503533601760864} 08/31/2021 13:15:53 - INFO - __main__ - Step 132802: {'lr': 1.6476447941945082e-05, 'samples': 25497984, 'steps': 132801, 'loss/train': 0.8380788564682007} 08/31/2021 13:15:54 - INFO - __main__ - Step 132803: {'lr': 1.647455334553827e-05, 'samples': 25498176, 'steps': 132802, 'loss/train': 0.651513934135437} 08/31/2021 13:15:54 - INFO - __main__ - Step 132804: {'lr': 1.6472658854354423e-05, 'samples': 25498368, 'steps': 132803, 'loss/train': 0.9971417784690857} 08/31/2021 13:15:54 - INFO - __main__ - Step 132805: {'lr': 1.647076446839438e-05, 'samples': 25498560, 'steps': 132804, 'loss/train': 0.3231918215751648} 08/31/2021 13:15:56 - INFO - __main__ - Step 132806: {'lr': 1.6468870187658996e-05, 'samples': 25498752, 'steps': 132805, 'loss/train': 0.3826143741607666} 08/31/2021 13:15:56 - INFO - __main__ - Step 132807: {'lr': 1.6466976012149137e-05, 'samples': 25498944, 'steps': 132806, 'loss/train': 1.2439213991165161} 08/31/2021 13:15:57 - INFO - __main__ - Step 132808: {'lr': 1.646508194186569e-05, 'samples': 25499136, 'steps': 132807, 'loss/train': 0.7626299858093262} 08/31/2021 13:15:57 - INFO - __main__ - Step 132809: {'lr': 1.646318797680943e-05, 'samples': 25499328, 'steps': 132808, 'loss/train': 1.2731568813323975} 08/31/2021 13:15:57 - INFO - __main__ - Step 132810: {'lr': 1.6461294116981272e-05, 'samples': 25499520, 'steps': 132809, 'loss/train': 1.0252643823623657} 08/31/2021 13:15:59 - INFO - __main__ - Step 132811: {'lr': 1.6459400362382054e-05, 'samples': 25499712, 'steps': 132810, 'loss/train': 1.0231057405471802} 08/31/2021 13:16:00 - INFO - __main__ - Step 132812: {'lr': 1.6457506713012687e-05, 'samples': 25499904, 'steps': 132811, 'loss/train': 0.6148893237113953} 08/31/2021 13:16:00 - INFO - __main__ - Step 132813: {'lr': 1.6455613168873895e-05, 'samples': 25500096, 'steps': 132812, 'loss/train': 1.3728728294372559} 08/31/2021 13:16:00 - INFO - __main__ - Step 132814: {'lr': 1.6453719729966594e-05, 'samples': 25500288, 'steps': 132813, 'loss/train': 0.9231902956962585} 08/31/2021 13:16:01 - INFO - __main__ - Step 132815: {'lr': 1.6451826396291668e-05, 'samples': 25500480, 'steps': 132814, 'loss/train': 0.9499009251594543} 08/31/2021 13:16:01 - INFO - __main__ - Step 132816: {'lr': 1.644993316784993e-05, 'samples': 25500672, 'steps': 132815, 'loss/train': 0.4080013930797577} 08/31/2021 13:16:03 - INFO - __main__ - Step 132817: {'lr': 1.644804004464226e-05, 'samples': 25500864, 'steps': 132816, 'loss/train': 0.04665510356426239} 08/31/2021 13:16:03 - INFO - __main__ - Step 132818: {'lr': 1.6446147026669493e-05, 'samples': 25501056, 'steps': 132817, 'loss/train': 0.8354954123497009} 08/31/2021 13:16:03 - INFO - __main__ - Step 132819: {'lr': 1.6444254113932466e-05, 'samples': 25501248, 'steps': 132818, 'loss/train': 0.5652424097061157} 08/31/2021 13:16:04 - INFO - __main__ - Step 132820: {'lr': 1.6442361306432092e-05, 'samples': 25501440, 'steps': 132819, 'loss/train': 0.15153849124908447} 08/31/2021 13:16:04 - INFO - __main__ - Step 132821: {'lr': 1.6440468604169172e-05, 'samples': 25501632, 'steps': 132820, 'loss/train': 1.4504715204238892} 08/31/2021 13:16:06 - INFO - __main__ - Step 132822: {'lr': 1.6438576007144547e-05, 'samples': 25501824, 'steps': 132821, 'loss/train': 0.1846799999475479} 08/31/2021 13:16:06 - INFO - __main__ - Step 132823: {'lr': 1.6436683515359126e-05, 'samples': 25502016, 'steps': 132822, 'loss/train': 0.2158709019422531} 08/31/2021 13:16:06 - INFO - __main__ - Step 132824: {'lr': 1.6434791128813714e-05, 'samples': 25502208, 'steps': 132823, 'loss/train': 1.2638254165649414} 08/31/2021 13:16:07 - INFO - __main__ - Step 132825: {'lr': 1.6432898847509204e-05, 'samples': 25502400, 'steps': 132824, 'loss/train': 0.3559437394142151} 08/31/2021 13:16:07 - INFO - __main__ - Step 132826: {'lr': 1.643100667144645e-05, 'samples': 25502592, 'steps': 132825, 'loss/train': 0.6460146903991699} 08/31/2021 13:16:09 - INFO - __main__ - Step 132827: {'lr': 1.6429114600626238e-05, 'samples': 25502784, 'steps': 132826, 'loss/train': 1.349920630455017} 08/31/2021 13:16:10 - INFO - __main__ - Step 132828: {'lr': 1.6427222635049475e-05, 'samples': 25502976, 'steps': 132827, 'loss/train': 0.8822859525680542} 08/31/2021 13:16:10 - INFO - __main__ - Step 132829: {'lr': 1.6425330774716973e-05, 'samples': 25503168, 'steps': 132828, 'loss/train': 0.9546352028846741} 08/31/2021 13:16:10 - INFO - __main__ - Step 132830: {'lr': 1.6423439019629642e-05, 'samples': 25503360, 'steps': 132829, 'loss/train': 1.2183443307876587} 08/31/2021 13:16:11 - INFO - __main__ - Step 132831: {'lr': 1.6421547369788293e-05, 'samples': 25503552, 'steps': 132830, 'loss/train': 1.5172613859176636} 08/31/2021 13:16:12 - INFO - __main__ - Step 132832: {'lr': 1.6419655825193807e-05, 'samples': 25503744, 'steps': 132831, 'loss/train': 1.230709195137024} 08/31/2021 13:16:13 - INFO - __main__ - Step 132833: {'lr': 1.6417764385846996e-05, 'samples': 25503936, 'steps': 132832, 'loss/train': 0.6632413268089294} 08/31/2021 13:16:13 - INFO - __main__ - Step 132834: {'lr': 1.6415873051748742e-05, 'samples': 25504128, 'steps': 132833, 'loss/train': 1.3570613861083984} 08/31/2021 13:16:13 - INFO - __main__ - Step 132835: {'lr': 1.641398182289991e-05, 'samples': 25504320, 'steps': 132834, 'loss/train': 1.3571697473526} 08/31/2021 13:16:14 - INFO - __main__ - Step 132836: {'lr': 1.64120906993013e-05, 'samples': 25504512, 'steps': 132835, 'loss/train': 0.3315354287624359} 08/31/2021 13:16:15 - INFO - __main__ - Step 132837: {'lr': 1.6410199680953806e-05, 'samples': 25504704, 'steps': 132836, 'loss/train': 1.401477575302124} 08/31/2021 13:16:16 - INFO - __main__ - Step 132838: {'lr': 1.6408308767858286e-05, 'samples': 25504896, 'steps': 132837, 'loss/train': 0.11882489919662476} 08/31/2021 13:16:16 - INFO - __main__ - Step 132839: {'lr': 1.640641796001563e-05, 'samples': 25505088, 'steps': 132838, 'loss/train': 1.4106892347335815} 08/31/2021 13:16:16 - INFO - __main__ - Step 132840: {'lr': 1.6404527257426583e-05, 'samples': 25505280, 'steps': 132839, 'loss/train': 0.4108990430831909} 08/31/2021 13:16:17 - INFO - __main__ - Step 132841: {'lr': 1.6402636660092037e-05, 'samples': 25505472, 'steps': 132840, 'loss/train': 0.9856218695640564} 08/31/2021 13:16:18 - INFO - __main__ - Step 132842: {'lr': 1.6400746168012874e-05, 'samples': 25505664, 'steps': 132841, 'loss/train': 1.306099772453308} 08/31/2021 13:16:19 - INFO - __main__ - Step 132843: {'lr': 1.639885578118991e-05, 'samples': 25505856, 'steps': 132842, 'loss/train': 0.9920179843902588} 08/31/2021 13:16:19 - INFO - __main__ - Step 132844: {'lr': 1.639696549962405e-05, 'samples': 25506048, 'steps': 132843, 'loss/train': 1.163411259651184} 08/31/2021 13:16:19 - INFO - __main__ - Step 132845: {'lr': 1.6395075323316077e-05, 'samples': 25506240, 'steps': 132844, 'loss/train': 0.7386772632598877} 08/31/2021 13:16:20 - INFO - __main__ - Step 132846: {'lr': 1.6393185252266906e-05, 'samples': 25506432, 'steps': 132845, 'loss/train': 1.6108760833740234} 08/31/2021 13:16:21 - INFO - __main__ - Step 132847: {'lr': 1.6391295286477344e-05, 'samples': 25506624, 'steps': 132846, 'loss/train': 0.9918278455734253} 08/31/2021 13:16:22 - INFO - __main__ - Step 132848: {'lr': 1.6389405425948274e-05, 'samples': 25506816, 'steps': 132847, 'loss/train': 1.6432379484176636} 08/31/2021 13:16:22 - INFO - __main__ - Step 132849: {'lr': 1.638751567068053e-05, 'samples': 25507008, 'steps': 132848, 'loss/train': 0.857351541519165} 08/31/2021 13:16:22 - INFO - __main__ - Step 132850: {'lr': 1.6385626020674975e-05, 'samples': 25507200, 'steps': 132849, 'loss/train': 1.1693212985992432} 08/31/2021 13:16:23 - INFO - __main__ - Step 132851: {'lr': 1.6383736475932416e-05, 'samples': 25507392, 'steps': 132850, 'loss/train': 1.202022910118103} 08/31/2021 13:16:25 - INFO - __main__ - Step 132852: {'lr': 1.638184703645379e-05, 'samples': 25507584, 'steps': 132851, 'loss/train': 0.5954596400260925} 08/31/2021 13:16:25 - INFO - __main__ - Step 132853: {'lr': 1.6379957702239907e-05, 'samples': 25507776, 'steps': 132852, 'loss/train': 0.7366405129432678} 08/31/2021 13:16:25 - INFO - __main__ - Step 132854: {'lr': 1.637806847329157e-05, 'samples': 25507968, 'steps': 132853, 'loss/train': 1.0225818157196045} 08/31/2021 13:16:26 - INFO - __main__ - Step 132855: {'lr': 1.6376179349609664e-05, 'samples': 25508160, 'steps': 132854, 'loss/train': 0.8562270402908325} 08/31/2021 13:16:26 - INFO - __main__ - Step 132856: {'lr': 1.637429033119506e-05, 'samples': 25508352, 'steps': 132855, 'loss/train': 1.1332961320877075} 08/31/2021 13:16:26 - INFO - __main__ - Step 132857: {'lr': 1.6372401418048604e-05, 'samples': 25508544, 'steps': 132856, 'loss/train': 0.7507267594337463} 08/31/2021 13:16:27 - INFO - __main__ - Step 132858: {'lr': 1.637051261017114e-05, 'samples': 25508736, 'steps': 132857, 'loss/train': 1.004202127456665} 08/31/2021 13:16:28 - INFO - __main__ - Step 132859: {'lr': 1.6368623907563494e-05, 'samples': 25508928, 'steps': 132858, 'loss/train': 0.02505623735487461} 08/31/2021 13:16:29 - INFO - __main__ - Step 132860: {'lr': 1.6366735310226562e-05, 'samples': 25509120, 'steps': 132859, 'loss/train': 1.1875962018966675} 08/31/2021 13:16:29 - INFO - __main__ - Step 132861: {'lr': 1.6364846818161167e-05, 'samples': 25509312, 'steps': 132860, 'loss/train': 0.7763640284538269} 08/31/2021 13:16:29 - INFO - __main__ - Step 132862: {'lr': 1.6362958431368175e-05, 'samples': 25509504, 'steps': 132861, 'loss/train': 1.0163990259170532} 08/31/2021 13:16:30 - INFO - __main__ - Step 132863: {'lr': 1.636107014984842e-05, 'samples': 25509696, 'steps': 132862, 'loss/train': 0.8232265710830688} 08/31/2021 13:16:31 - INFO - __main__ - Step 132864: {'lr': 1.6359181973602755e-05, 'samples': 25509888, 'steps': 132863, 'loss/train': 1.2781109809875488} 08/31/2021 13:16:32 - INFO - __main__ - Step 132865: {'lr': 1.635729390263205e-05, 'samples': 25510080, 'steps': 132864, 'loss/train': 0.9699838161468506} 08/31/2021 13:16:32 - INFO - __main__ - Step 132866: {'lr': 1.6355405936937156e-05, 'samples': 25510272, 'steps': 132865, 'loss/train': 0.743224024772644} 08/31/2021 13:16:32 - INFO - __main__ - Step 132867: {'lr': 1.6353518076518887e-05, 'samples': 25510464, 'steps': 132866, 'loss/train': 1.8713819980621338} 08/31/2021 13:16:33 - INFO - __main__ - Step 132868: {'lr': 1.6351630321378124e-05, 'samples': 25510656, 'steps': 132867, 'loss/train': 1.1927763223648071} 08/31/2021 13:16:35 - INFO - __main__ - Step 132869: {'lr': 1.6349742671515705e-05, 'samples': 25510848, 'steps': 132868, 'loss/train': 0.47272592782974243} 08/31/2021 13:16:35 - INFO - __main__ - Step 132870: {'lr': 1.6347855126932515e-05, 'samples': 25511040, 'steps': 132869, 'loss/train': 1.5070281028747559} 08/31/2021 13:16:35 - INFO - __main__ - Step 132871: {'lr': 1.634596768762933e-05, 'samples': 25511232, 'steps': 132870, 'loss/train': 1.2973105907440186} 08/31/2021 13:16:36 - INFO - __main__ - Step 132872: {'lr': 1.634408035360707e-05, 'samples': 25511424, 'steps': 132871, 'loss/train': 0.7439392805099487} 08/31/2021 13:16:36 - INFO - __main__ - Step 132873: {'lr': 1.6342193124866566e-05, 'samples': 25511616, 'steps': 132872, 'loss/train': 0.6683859825134277} 08/31/2021 13:16:36 - INFO - __main__ - Step 132874: {'lr': 1.634030600140865e-05, 'samples': 25511808, 'steps': 132873, 'loss/train': 0.30799227952957153} 08/31/2021 13:16:38 - INFO - __main__ - Step 132875: {'lr': 1.633841898323421e-05, 'samples': 25512000, 'steps': 132874, 'loss/train': 1.0438847541809082} 08/31/2021 13:16:38 - INFO - __main__ - Step 132876: {'lr': 1.6336532070344053e-05, 'samples': 25512192, 'steps': 132875, 'loss/train': 1.2695891857147217} 08/31/2021 13:16:39 - INFO - __main__ - Step 132877: {'lr': 1.6334645262739033e-05, 'samples': 25512384, 'steps': 132876, 'loss/train': 1.030837059020996} 08/31/2021 13:16:39 - INFO - __main__ - Step 132878: {'lr': 1.6332758560420046e-05, 'samples': 25512576, 'steps': 132877, 'loss/train': 0.8812182545661926} 08/31/2021 13:16:39 - INFO - __main__ - Step 132879: {'lr': 1.6330871963387895e-05, 'samples': 25512768, 'steps': 132878, 'loss/train': 1.4265224933624268} 08/31/2021 13:16:42 - INFO - __main__ - Step 132880: {'lr': 1.632898547164352e-05, 'samples': 25512960, 'steps': 132879, 'loss/train': 1.6560636758804321} 08/31/2021 13:16:42 - INFO - __main__ - Step 132881: {'lr': 1.632709908518762e-05, 'samples': 25513152, 'steps': 132880, 'loss/train': 1.206221580505371} 08/31/2021 13:16:43 - INFO - __main__ - Step 132882: {'lr': 1.6325212804021133e-05, 'samples': 25513344, 'steps': 132881, 'loss/train': 1.335288643836975} 08/31/2021 13:16:43 - INFO - __main__ - Step 132883: {'lr': 1.6323326628144897e-05, 'samples': 25513536, 'steps': 132882, 'loss/train': 0.7798947691917419} 08/31/2021 13:16:43 - INFO - __main__ - Step 132884: {'lr': 1.6321440557559768e-05, 'samples': 25513728, 'steps': 132883, 'loss/train': 1.0946415662765503} 08/31/2021 13:16:44 - INFO - __main__ - Step 132885: {'lr': 1.6319554592266612e-05, 'samples': 25513920, 'steps': 132884, 'loss/train': 5.748834133148193} 08/31/2021 13:16:45 - INFO - __main__ - Step 132886: {'lr': 1.6317668732266228e-05, 'samples': 25514112, 'steps': 132885, 'loss/train': 5.702356815338135} 08/31/2021 13:16:46 - INFO - __main__ - Step 132887: {'lr': 1.6315782977559506e-05, 'samples': 25514304, 'steps': 132886, 'loss/train': 0.03480235114693642} 08/31/2021 13:16:46 - INFO - __main__ - Step 132888: {'lr': 1.6313897328147308e-05, 'samples': 25514496, 'steps': 132887, 'loss/train': 0.6225733757019043} 08/31/2021 13:16:46 - INFO - __main__ - Step 132889: {'lr': 1.631201178403044e-05, 'samples': 25514688, 'steps': 132888, 'loss/train': 1.4535459280014038} 08/31/2021 13:16:47 - INFO - __main__ - Step 132890: {'lr': 1.6310126345209785e-05, 'samples': 25514880, 'steps': 132889, 'loss/train': 0.981541633605957} 08/31/2021 13:16:47 - INFO - __main__ - Step 132891: {'lr': 1.6308241011686154e-05, 'samples': 25515072, 'steps': 132890, 'loss/train': 1.2266327142715454} 08/31/2021 13:16:49 - INFO - __main__ - Step 132892: {'lr': 1.630635578346046e-05, 'samples': 25515264, 'steps': 132891, 'loss/train': 0.8917490243911743} 08/31/2021 13:16:49 - INFO - __main__ - Step 132893: {'lr': 1.6304470660533532e-05, 'samples': 25515456, 'steps': 132892, 'loss/train': 0.7666779160499573} 08/31/2021 13:16:50 - INFO - __main__ - Step 132894: {'lr': 1.6302585642906153e-05, 'samples': 25515648, 'steps': 132893, 'loss/train': 0.7404078245162964} 08/31/2021 13:16:50 - INFO - __main__ - Step 132895: {'lr': 1.6300700730579237e-05, 'samples': 25515840, 'steps': 132894, 'loss/train': 1.5172970294952393} 08/31/2021 13:16:50 - INFO - __main__ - Step 132896: {'lr': 1.6298815923553644e-05, 'samples': 25516032, 'steps': 132895, 'loss/train': 3.6159257888793945} 08/31/2021 13:16:52 - INFO - __main__ - Step 132897: {'lr': 1.629693122183018e-05, 'samples': 25516224, 'steps': 132896, 'loss/train': 1.0132941007614136} 08/31/2021 13:16:52 - INFO - __main__ - Step 132898: {'lr': 1.6295046625409705e-05, 'samples': 25516416, 'steps': 132897, 'loss/train': 1.0062177181243896} 08/31/2021 13:16:53 - INFO - __main__ - Step 132899: {'lr': 1.6293162134293077e-05, 'samples': 25516608, 'steps': 132898, 'loss/train': 0.9267546534538269} 08/31/2021 13:16:53 - INFO - __main__ - Step 132900: {'lr': 1.6291277748481133e-05, 'samples': 25516800, 'steps': 132899, 'loss/train': 0.8355501890182495} 08/31/2021 13:16:53 - INFO - __main__ - Step 132901: {'lr': 1.6289393467974757e-05, 'samples': 25516992, 'steps': 132900, 'loss/train': 1.2986979484558105} 08/31/2021 13:16:55 - INFO - __main__ - Step 132902: {'lr': 1.6287509292774754e-05, 'samples': 25517184, 'steps': 132901, 'loss/train': 1.1151037216186523} 08/31/2021 13:16:55 - INFO - __main__ - Step 132903: {'lr': 1.6285625222882016e-05, 'samples': 25517376, 'steps': 132902, 'loss/train': 1.3261823654174805} 08/31/2021 13:16:56 - INFO - __main__ - Step 132904: {'lr': 1.6283741258297348e-05, 'samples': 25517568, 'steps': 132903, 'loss/train': 1.659006953239441} 08/31/2021 13:16:56 - INFO - __main__ - Step 132905: {'lr': 1.6281857399021632e-05, 'samples': 25517760, 'steps': 132904, 'loss/train': 1.3106513023376465} 08/31/2021 13:16:56 - INFO - __main__ - Step 132906: {'lr': 1.6279973645055735e-05, 'samples': 25517952, 'steps': 132905, 'loss/train': 0.7998859286308289} 08/31/2021 13:16:57 - INFO - __main__ - Step 132907: {'lr': 1.627808999640043e-05, 'samples': 25518144, 'steps': 132906, 'loss/train': 1.168097972869873} 08/31/2021 13:16:58 - INFO - __main__ - Step 132908: {'lr': 1.6276206453056634e-05, 'samples': 25518336, 'steps': 132907, 'loss/train': 1.175557017326355} 08/31/2021 13:16:59 - INFO - __main__ - Step 132909: {'lr': 1.6274323015025156e-05, 'samples': 25518528, 'steps': 132908, 'loss/train': 1.3970876932144165} 08/31/2021 13:16:59 - INFO - __main__ - Step 132910: {'lr': 1.627243968230685e-05, 'samples': 25518720, 'steps': 132909, 'loss/train': 1.725611925125122} 08/31/2021 13:16:59 - INFO - __main__ - Step 132911: {'lr': 1.6270556454902608e-05, 'samples': 25518912, 'steps': 132910, 'loss/train': 1.415062665939331} 08/31/2021 13:17:00 - INFO - __main__ - Step 132912: {'lr': 1.6268673332813206e-05, 'samples': 25519104, 'steps': 132911, 'loss/train': 1.429530143737793} 08/31/2021 13:17:01 - INFO - __main__ - Step 132913: {'lr': 1.626679031603956e-05, 'samples': 25519296, 'steps': 132912, 'loss/train': 1.537095546722412} 08/31/2021 13:17:02 - INFO - __main__ - Step 132914: {'lr': 1.6264907404582502e-05, 'samples': 25519488, 'steps': 132913, 'loss/train': 1.6711138486862183} 08/31/2021 13:17:02 - INFO - __main__ - Step 132915: {'lr': 1.6263024598442837e-05, 'samples': 25519680, 'steps': 132914, 'loss/train': 1.3647352457046509} 08/31/2021 13:17:03 - INFO - __main__ - Step 132916: {'lr': 1.6261141897621483e-05, 'samples': 25519872, 'steps': 132915, 'loss/train': 1.594516396522522} 08/31/2021 13:17:03 - INFO - __main__ - Step 132917: {'lr': 1.6259259302119217e-05, 'samples': 25520064, 'steps': 132916, 'loss/train': 0.7424989938735962} 08/31/2021 13:17:04 - INFO - __main__ - Step 132918: {'lr': 1.6257376811936953e-05, 'samples': 25520256, 'steps': 132917, 'loss/train': 1.4505232572555542} 08/31/2021 13:17:05 - INFO - __main__ - Step 132919: {'lr': 1.6255494427075497e-05, 'samples': 25520448, 'steps': 132918, 'loss/train': 1.132247805595398} 08/31/2021 13:17:05 - INFO - __main__ - Step 132920: {'lr': 1.6253612147535734e-05, 'samples': 25520640, 'steps': 132919, 'loss/train': 1.2341619729995728} 08/31/2021 13:17:05 - INFO - __main__ - Step 132921: {'lr': 1.6251729973318473e-05, 'samples': 25520832, 'steps': 132920, 'loss/train': 0.6515551209449768} 08/31/2021 13:17:06 - INFO - __main__ - Step 132922: {'lr': 1.624984790442455e-05, 'samples': 25521024, 'steps': 132921, 'loss/train': 1.7675418853759766} 08/31/2021 13:17:07 - INFO - __main__ - Step 132923: {'lr': 1.624796594085484e-05, 'samples': 25521216, 'steps': 132922, 'loss/train': 0.9921515583992004} 08/31/2021 13:17:08 - INFO - __main__ - Step 132924: {'lr': 1.624608408261022e-05, 'samples': 25521408, 'steps': 132923, 'loss/train': 0.1023264154791832} 08/31/2021 13:17:08 - INFO - __main__ - Step 132925: {'lr': 1.6244202329691483e-05, 'samples': 25521600, 'steps': 132924, 'loss/train': 1.8444336652755737} 08/31/2021 13:17:08 - INFO - __main__ - Step 132926: {'lr': 1.624232068209949e-05, 'samples': 25521792, 'steps': 132925, 'loss/train': 0.5820978879928589} 08/31/2021 13:17:09 - INFO - __main__ - Step 132927: {'lr': 1.6240439139835112e-05, 'samples': 25521984, 'steps': 132926, 'loss/train': 0.3573245704174042} 08/31/2021 13:17:09 - INFO - __main__ - Step 132928: {'lr': 1.6238557702899198e-05, 'samples': 25522176, 'steps': 132927, 'loss/train': 1.3038309812545776} 08/31/2021 13:17:11 - INFO - __main__ - Step 132929: {'lr': 1.6236676371292557e-05, 'samples': 25522368, 'steps': 132928, 'loss/train': 1.1069995164871216} 08/31/2021 13:17:11 - INFO - __main__ - Step 132930: {'lr': 1.6234795145016078e-05, 'samples': 25522560, 'steps': 132929, 'loss/train': 0.8448144793510437} 08/31/2021 13:17:12 - INFO - __main__ - Step 132931: {'lr': 1.6232914024070593e-05, 'samples': 25522752, 'steps': 132930, 'loss/train': 1.609850525856018} 08/31/2021 13:17:12 - INFO - __main__ - Step 132932: {'lr': 1.6231033008456965e-05, 'samples': 25522944, 'steps': 132931, 'loss/train': 1.12027907371521} 08/31/2021 13:17:12 - INFO - __main__ - Step 132933: {'lr': 1.6229152098176047e-05, 'samples': 25523136, 'steps': 132932, 'loss/train': 1.2694156169891357} 08/31/2021 13:17:14 - INFO - __main__ - Step 132934: {'lr': 1.6227271293228624e-05, 'samples': 25523328, 'steps': 132933, 'loss/train': 0.6712038516998291} 08/31/2021 13:17:15 - INFO - __main__ - Step 132935: {'lr': 1.622539059361558e-05, 'samples': 25523520, 'steps': 132934, 'loss/train': 0.8354972004890442} 08/31/2021 13:17:15 - INFO - __main__ - Step 132936: {'lr': 1.6223509999337805e-05, 'samples': 25523712, 'steps': 132935, 'loss/train': 0.7666239738464355} 08/31/2021 13:17:16 - INFO - __main__ - Step 132937: {'lr': 1.6221629510396074e-05, 'samples': 25523904, 'steps': 132936, 'loss/train': 1.3671300411224365} 08/31/2021 13:17:16 - INFO - __main__ - Step 132938: {'lr': 1.6219749126791278e-05, 'samples': 25524096, 'steps': 132937, 'loss/train': 1.5689003467559814} 08/31/2021 13:17:17 - INFO - __main__ - Step 132939: {'lr': 1.621786884852425e-05, 'samples': 25524288, 'steps': 132938, 'loss/train': 1.268702745437622} 08/31/2021 13:17:18 - INFO - __main__ - Step 132940: {'lr': 1.6215988675595843e-05, 'samples': 25524480, 'steps': 132939, 'loss/train': 0.9784115552902222} 08/31/2021 13:17:18 - INFO - __main__ - Step 132941: {'lr': 1.62141086080069e-05, 'samples': 25524672, 'steps': 132940, 'loss/train': 1.1866328716278076} 08/31/2021 13:17:19 - INFO - __main__ - Step 132942: {'lr': 1.6212228645758302e-05, 'samples': 25524864, 'steps': 132941, 'loss/train': 1.3269206285476685} 08/31/2021 13:17:19 - INFO - __main__ - Step 132943: {'lr': 1.621034878885083e-05, 'samples': 25525056, 'steps': 132942, 'loss/train': 0.8881602883338928} 08/31/2021 13:17:20 - INFO - __main__ - Step 132944: {'lr': 1.6208469037285402e-05, 'samples': 25525248, 'steps': 132943, 'loss/train': 0.656046986579895} 08/31/2021 13:17:21 - INFO - __main__ - Step 132945: {'lr': 1.6206589391062787e-05, 'samples': 25525440, 'steps': 132944, 'loss/train': 0.670252799987793} 08/31/2021 13:17:21 - INFO - __main__ - Step 132946: {'lr': 1.620470985018391e-05, 'samples': 25525632, 'steps': 132945, 'loss/train': 0.40123215317726135} 08/31/2021 13:17:21 - INFO - __main__ - Step 132947: {'lr': 1.6202830414649623e-05, 'samples': 25525824, 'steps': 132946, 'loss/train': 0.3962286114692688} 08/31/2021 13:17:22 - INFO - __main__ - Step 132948: {'lr': 1.620095108446068e-05, 'samples': 25526016, 'steps': 132947, 'loss/train': 0.7565471529960632} 08/31/2021 13:17:23 - INFO - __main__ - Step 132949: {'lr': 1.619907185961797e-05, 'samples': 25526208, 'steps': 132948, 'loss/train': 1.7272534370422363} 08/31/2021 13:17:24 - INFO - __main__ - Step 132950: {'lr': 1.6197192740122352e-05, 'samples': 25526400, 'steps': 132949, 'loss/train': 1.147633671760559} 08/31/2021 13:17:24 - INFO - __main__ - Step 132951: {'lr': 1.6195313725974686e-05, 'samples': 25526592, 'steps': 132950, 'loss/train': 2.0864450931549072} 08/31/2021 13:17:24 - INFO - __main__ - Step 132952: {'lr': 1.6193434817175804e-05, 'samples': 25526784, 'steps': 132951, 'loss/train': 1.658768892288208} 08/31/2021 13:17:25 - INFO - __main__ - Step 132953: {'lr': 1.6191556013726544e-05, 'samples': 25526976, 'steps': 132952, 'loss/train': 1.5742021799087524} 08/31/2021 13:17:26 - INFO - __main__ - Step 132954: {'lr': 1.618967731562779e-05, 'samples': 25527168, 'steps': 132953, 'loss/train': 1.494529128074646} 08/31/2021 13:17:27 - INFO - __main__ - Step 132955: {'lr': 1.6187798722880315e-05, 'samples': 25527360, 'steps': 132954, 'loss/train': 1.4707657098770142} 08/31/2021 13:17:27 - INFO - __main__ - Step 132956: {'lr': 1.618592023548504e-05, 'samples': 25527552, 'steps': 132955, 'loss/train': 1.7669003009796143} 08/31/2021 13:17:28 - INFO - __main__ - Step 132957: {'lr': 1.6184041853442773e-05, 'samples': 25527744, 'steps': 132956, 'loss/train': 0.9933500289916992} 08/31/2021 13:17:28 - INFO - __main__ - Step 132958: {'lr': 1.6182163576754394e-05, 'samples': 25527936, 'steps': 132957, 'loss/train': 0.8260201215744019} 08/31/2021 13:17:28 - INFO - __main__ - Step 132959: {'lr': 1.6180285405420713e-05, 'samples': 25528128, 'steps': 132958, 'loss/train': 1.257975697517395} 08/31/2021 13:17:30 - INFO - __main__ - Step 132960: {'lr': 1.6178407339442565e-05, 'samples': 25528320, 'steps': 132959, 'loss/train': 0.9482972621917725} 08/31/2021 13:17:30 - INFO - __main__ - Step 132961: {'lr': 1.617652937882083e-05, 'samples': 25528512, 'steps': 132960, 'loss/train': 0.9067929983139038} 08/31/2021 13:17:31 - INFO - __main__ - Step 132962: {'lr': 1.6174651523556322e-05, 'samples': 25528704, 'steps': 132961, 'loss/train': 0.3703506588935852} 08/31/2021 13:17:31 - INFO - __main__ - Step 132963: {'lr': 1.6172773773649924e-05, 'samples': 25528896, 'steps': 132962, 'loss/train': 1.0685434341430664} 08/31/2021 13:17:32 - INFO - __main__ - Step 132964: {'lr': 1.617089612910247e-05, 'samples': 25529088, 'steps': 132963, 'loss/train': 1.0893765687942505} 08/31/2021 13:17:33 - INFO - __main__ - Step 132965: {'lr': 1.616901858991479e-05, 'samples': 25529280, 'steps': 132964, 'loss/train': 0.9320083260536194} 08/31/2021 13:17:33 - INFO - __main__ - Step 132966: {'lr': 1.616714115608775e-05, 'samples': 25529472, 'steps': 132965, 'loss/train': 1.3206291198730469} 08/31/2021 13:17:34 - INFO - __main__ - Step 132967: {'lr': 1.6165263827622206e-05, 'samples': 25529664, 'steps': 132966, 'loss/train': 1.0772291421890259} 08/31/2021 13:17:34 - INFO - __main__ - Step 132968: {'lr': 1.6163386604518965e-05, 'samples': 25529856, 'steps': 132967, 'loss/train': 1.2919964790344238} 08/31/2021 13:17:35 - INFO - __main__ - Step 132969: {'lr': 1.6161509486778914e-05, 'samples': 25530048, 'steps': 132968, 'loss/train': 1.566672921180725} 08/31/2021 13:17:36 - INFO - __main__ - Step 132970: {'lr': 1.6159632474402887e-05, 'samples': 25530240, 'steps': 132969, 'loss/train': 1.2634724378585815} 08/31/2021 13:17:37 - INFO - __main__ - Step 132971: {'lr': 1.6157755567391684e-05, 'samples': 25530432, 'steps': 132970, 'loss/train': 1.3216159343719482} 08/31/2021 13:17:37 - INFO - __main__ - Step 132972: {'lr': 1.6155878765746203e-05, 'samples': 25530624, 'steps': 132971, 'loss/train': 0.300143301486969} 08/31/2021 13:17:37 - INFO - __main__ - Step 132973: {'lr': 1.6154002069467266e-05, 'samples': 25530816, 'steps': 132972, 'loss/train': 5.7156805992126465} 08/31/2021 13:17:38 - INFO - __main__ - Step 132974: {'lr': 1.6152125478555742e-05, 'samples': 25531008, 'steps': 132973, 'loss/train': 0.8453990817070007} 08/31/2021 13:17:39 - INFO - __main__ - Step 132975: {'lr': 1.615024899301243e-05, 'samples': 25531200, 'steps': 132974, 'loss/train': 1.0595769882202148} 08/31/2021 13:17:40 - INFO - __main__ - Step 132976: {'lr': 1.6148372612838247e-05, 'samples': 25531392, 'steps': 132975, 'loss/train': 0.9565206170082092} 08/31/2021 13:17:40 - INFO - __main__ - Step 132977: {'lr': 1.6146496338033974e-05, 'samples': 25531584, 'steps': 132976, 'loss/train': 0.7084358930587769} 08/31/2021 13:17:40 - INFO - __main__ - Step 132978: {'lr': 1.6144620168600495e-05, 'samples': 25531776, 'steps': 132977, 'loss/train': 1.1332552433013916} 08/31/2021 13:17:41 - INFO - __main__ - Step 132979: {'lr': 1.6142744104538615e-05, 'samples': 25531968, 'steps': 132978, 'loss/train': 0.5287306904792786} 08/31/2021 13:17:42 - INFO - __main__ - Step 132980: {'lr': 1.614086814584928e-05, 'samples': 25532160, 'steps': 132979, 'loss/train': 0.41246119141578674} 08/31/2021 13:17:43 - INFO - __main__ - Step 132981: {'lr': 1.6138992292533183e-05, 'samples': 25532352, 'steps': 132980, 'loss/train': 0.9702345132827759} 08/31/2021 13:17:43 - INFO - __main__ - Step 132982: {'lr': 1.6137116544591267e-05, 'samples': 25532544, 'steps': 132981, 'loss/train': 1.3768903017044067} 08/31/2021 13:17:43 - INFO - __main__ - Step 132983: {'lr': 1.6135240902024366e-05, 'samples': 25532736, 'steps': 132982, 'loss/train': 0.964661180973053} 08/31/2021 13:17:44 - INFO - __main__ - Step 132984: {'lr': 1.6133365364833314e-05, 'samples': 25532928, 'steps': 132983, 'loss/train': 0.02866338938474655} 08/31/2021 13:17:44 - INFO - __main__ - Step 132985: {'lr': 1.6131489933018968e-05, 'samples': 25533120, 'steps': 132984, 'loss/train': 1.3525580167770386} 08/31/2021 13:17:46 - INFO - __main__ - Step 132986: {'lr': 1.612961460658216e-05, 'samples': 25533312, 'steps': 132985, 'loss/train': 1.2618591785430908} 08/31/2021 13:17:46 - INFO - __main__ - Step 132987: {'lr': 1.6127739385523727e-05, 'samples': 25533504, 'steps': 132986, 'loss/train': 1.5267142057418823} 08/31/2021 13:17:47 - INFO - __main__ - Step 132988: {'lr': 1.6125864269844527e-05, 'samples': 25533696, 'steps': 132987, 'loss/train': 0.7211452722549438} 08/31/2021 13:17:47 - INFO - __main__ - Step 132989: {'lr': 1.612398925954539e-05, 'samples': 25533888, 'steps': 132988, 'loss/train': 2.041076898574829} 08/31/2021 13:17:47 - INFO - __main__ - Step 132990: {'lr': 1.612211435462721e-05, 'samples': 25534080, 'steps': 132989, 'loss/train': 0.7021141648292542} 08/31/2021 13:17:50 - INFO - __main__ - Step 132991: {'lr': 1.6120239555090816e-05, 'samples': 25534272, 'steps': 132990, 'loss/train': 0.824471652507782} 08/31/2021 13:17:50 - INFO - __main__ - Step 132992: {'lr': 1.6118364860936986e-05, 'samples': 25534464, 'steps': 132991, 'loss/train': 1.6092137098312378} 08/31/2021 13:17:50 - INFO - __main__ - Step 132993: {'lr': 1.6116490272166607e-05, 'samples': 25534656, 'steps': 132992, 'loss/train': 0.977749228477478} 08/31/2021 13:17:51 - INFO - __main__ - Step 132994: {'lr': 1.6114615788780568e-05, 'samples': 25534848, 'steps': 132993, 'loss/train': 1.3147035837173462} 08/31/2021 13:17:51 - INFO - __main__ - Step 132995: {'lr': 1.6112741410779647e-05, 'samples': 25535040, 'steps': 132994, 'loss/train': 0.5619283318519592} 08/31/2021 13:17:53 - INFO - __main__ - Step 132996: {'lr': 1.6110867138164702e-05, 'samples': 25535232, 'steps': 132995, 'loss/train': 0.9874855279922485} 08/31/2021 13:17:53 - INFO - __main__ - Step 132997: {'lr': 1.6108992970936597e-05, 'samples': 25535424, 'steps': 132996, 'loss/train': 1.226456642150879} 08/31/2021 13:17:53 - INFO - __main__ - Step 132998: {'lr': 1.6107118909096193e-05, 'samples': 25535616, 'steps': 132997, 'loss/train': 0.9673541784286499} 08/31/2021 13:17:54 - INFO - __main__ - Step 132999: {'lr': 1.6105244952644288e-05, 'samples': 25535808, 'steps': 132998, 'loss/train': 0.749098002910614} 08/31/2021 13:17:54 - INFO - __main__ - Step 133000: {'lr': 1.6103371101581778e-05, 'samples': 25536000, 'steps': 132999, 'loss/train': 2.019491195678711} 08/31/2021 13:17:56 - INFO - __main__ - Step 133001: {'lr': 1.610149735590949e-05, 'samples': 25536192, 'steps': 133000, 'loss/train': 0.6757680177688599} 08/31/2021 13:17:56 - INFO - __main__ - Step 133002: {'lr': 1.609962371562823e-05, 'samples': 25536384, 'steps': 133001, 'loss/train': 1.1945383548736572} 08/31/2021 13:17:57 - INFO - __main__ - Step 133003: {'lr': 1.6097750180738864e-05, 'samples': 25536576, 'steps': 133002, 'loss/train': 0.2117302268743515} 08/31/2021 13:17:57 - INFO - __main__ - Step 133004: {'lr': 1.6095876751242246e-05, 'samples': 25536768, 'steps': 133003, 'loss/train': 1.5847421884536743} 08/31/2021 13:17:57 - INFO - __main__ - Step 133005: {'lr': 1.6094003427139237e-05, 'samples': 25536960, 'steps': 133004, 'loss/train': 0.8865092992782593} 08/31/2021 13:17:59 - INFO - __main__ - Step 133006: {'lr': 1.6092130208430644e-05, 'samples': 25537152, 'steps': 133005, 'loss/train': 0.06766858696937561} 08/31/2021 13:17:59 - INFO - __main__ - Step 133007: {'lr': 1.6090257095117327e-05, 'samples': 25537344, 'steps': 133006, 'loss/train': 1.2956748008728027} 08/31/2021 13:18:00 - INFO - __main__ - Step 133008: {'lr': 1.608838408720012e-05, 'samples': 25537536, 'steps': 133007, 'loss/train': 1.402992606163025} 08/31/2021 13:18:00 - INFO - __main__ - Step 133009: {'lr': 1.608651118467988e-05, 'samples': 25537728, 'steps': 133008, 'loss/train': 1.2606052160263062} 08/31/2021 13:18:00 - INFO - __main__ - Step 133010: {'lr': 1.608463838755747e-05, 'samples': 25537920, 'steps': 133009, 'loss/train': 0.2954171299934387} 08/31/2021 13:18:02 - INFO - __main__ - Step 133011: {'lr': 1.6082765695833696e-05, 'samples': 25538112, 'steps': 133010, 'loss/train': 1.157786250114441} 08/31/2021 13:18:02 - INFO - __main__ - Step 133012: {'lr': 1.6080893109509415e-05, 'samples': 25538304, 'steps': 133011, 'loss/train': 1.0464714765548706} 08/31/2021 13:18:03 - INFO - __main__ - Step 133013: {'lr': 1.607902062858549e-05, 'samples': 25538496, 'steps': 133012, 'loss/train': 0.9930911064147949} 08/31/2021 13:18:03 - INFO - __main__ - Step 133014: {'lr': 1.607714825306278e-05, 'samples': 25538688, 'steps': 133013, 'loss/train': 1.1973382234573364} 08/31/2021 13:18:03 - INFO - __main__ - Step 133015: {'lr': 1.607527598294206e-05, 'samples': 25538880, 'steps': 133014, 'loss/train': 1.1468974351882935} 08/31/2021 13:18:04 - INFO - __main__ - Step 133016: {'lr': 1.6073403818224197e-05, 'samples': 25539072, 'steps': 133015, 'loss/train': 1.3062593936920166} 08/31/2021 13:18:05 - INFO - __main__ - Step 133017: {'lr': 1.6071531758910047e-05, 'samples': 25539264, 'steps': 133016, 'loss/train': 0.966299295425415} 08/31/2021 13:18:06 - INFO - __main__ - Step 133018: {'lr': 1.606965980500047e-05, 'samples': 25539456, 'steps': 133017, 'loss/train': 1.1235196590423584} 08/31/2021 13:18:06 - INFO - __main__ - Step 133019: {'lr': 1.60677879564963e-05, 'samples': 25539648, 'steps': 133018, 'loss/train': 1.408588171005249} 08/31/2021 13:18:07 - INFO - __main__ - Step 133020: {'lr': 1.606591621339837e-05, 'samples': 25539840, 'steps': 133019, 'loss/train': 1.3752700090408325} 08/31/2021 13:18:07 - INFO - __main__ - Step 133021: {'lr': 1.606404457570751e-05, 'samples': 25540032, 'steps': 133020, 'loss/train': 0.9711338877677917} 08/31/2021 13:18:08 - INFO - __main__ - Step 133022: {'lr': 1.606217304342461e-05, 'samples': 25540224, 'steps': 133021, 'loss/train': 0.8740226626396179} 08/31/2021 13:18:09 - INFO - __main__ - Step 133023: {'lr': 1.6060301616550477e-05, 'samples': 25540416, 'steps': 133022, 'loss/train': 1.2621647119522095} 08/31/2021 13:18:09 - INFO - __main__ - Step 133024: {'lr': 1.605843029508594e-05, 'samples': 25540608, 'steps': 133023, 'loss/train': 0.8351239562034607} 08/31/2021 13:18:10 - INFO - __main__ - Step 133025: {'lr': 1.605655907903189e-05, 'samples': 25540800, 'steps': 133024, 'loss/train': 0.8865216374397278} 08/31/2021 13:18:10 - INFO - __main__ - Step 133026: {'lr': 1.605468796838913e-05, 'samples': 25540992, 'steps': 133025, 'loss/train': 0.13135859370231628} 08/31/2021 13:18:10 - INFO - __main__ - Step 133027: {'lr': 1.6052816963158552e-05, 'samples': 25541184, 'steps': 133026, 'loss/train': 0.6605619788169861} 08/31/2021 13:18:12 - INFO - __main__ - Step 133028: {'lr': 1.6050946063340953e-05, 'samples': 25541376, 'steps': 133027, 'loss/train': 1.3837717771530151} 08/31/2021 13:18:13 - INFO - __main__ - Step 133029: {'lr': 1.6049075268937176e-05, 'samples': 25541568, 'steps': 133028, 'loss/train': 0.04296363517642021} 08/31/2021 13:18:13 - INFO - __main__ - Step 133030: {'lr': 1.6047204579948072e-05, 'samples': 25541760, 'steps': 133029, 'loss/train': 0.46493101119995117} 08/31/2021 13:18:13 - INFO - __main__ - Step 133031: {'lr': 1.604533399637448e-05, 'samples': 25541952, 'steps': 133030, 'loss/train': 0.8827170133590698} 08/31/2021 13:18:14 - INFO - __main__ - Step 133032: {'lr': 1.6043463518217256e-05, 'samples': 25542144, 'steps': 133031, 'loss/train': 0.849598228931427} 08/31/2021 13:18:15 - INFO - __main__ - Step 133033: {'lr': 1.6041593145477234e-05, 'samples': 25542336, 'steps': 133032, 'loss/train': 1.4411696195602417} 08/31/2021 13:18:16 - INFO - __main__ - Step 133034: {'lr': 1.603972287815525e-05, 'samples': 25542528, 'steps': 133033, 'loss/train': 1.1860034465789795} 08/31/2021 13:18:16 - INFO - __main__ - Step 133035: {'lr': 1.6037852716252188e-05, 'samples': 25542720, 'steps': 133034, 'loss/train': 1.443688988685608} 08/31/2021 13:18:17 - INFO - __main__ - Step 133036: {'lr': 1.6035982659768827e-05, 'samples': 25542912, 'steps': 133035, 'loss/train': 1.383911371231079} 08/31/2021 13:18:17 - INFO - __main__ - Step 133037: {'lr': 1.6034112708706056e-05, 'samples': 25543104, 'steps': 133036, 'loss/train': 0.6005426049232483} 08/31/2021 13:18:18 - INFO - __main__ - Step 133038: {'lr': 1.6032242863064706e-05, 'samples': 25543296, 'steps': 133037, 'loss/train': 0.6631565093994141} 08/31/2021 13:18:19 - INFO - __main__ - Step 133039: {'lr': 1.603037312284561e-05, 'samples': 25543488, 'steps': 133038, 'loss/train': 1.2987698316574097} 08/31/2021 13:18:19 - INFO - __main__ - Step 133040: {'lr': 1.602850348804963e-05, 'samples': 25543680, 'steps': 133039, 'loss/train': 1.1817854642868042} 08/31/2021 13:18:20 - INFO - __main__ - Step 133041: {'lr': 1.6026633958677623e-05, 'samples': 25543872, 'steps': 133040, 'loss/train': 1.5133553743362427} 08/31/2021 13:18:20 - INFO - __main__ - Step 133042: {'lr': 1.602476453473037e-05, 'samples': 25544064, 'steps': 133041, 'loss/train': 1.1228373050689697} 08/31/2021 13:18:20 - INFO - __main__ - Step 133043: {'lr': 1.6022895216208756e-05, 'samples': 25544256, 'steps': 133042, 'loss/train': 1.0084257125854492} 08/31/2021 13:18:22 - INFO - __main__ - Step 133044: {'lr': 1.6021026003113587e-05, 'samples': 25544448, 'steps': 133043, 'loss/train': 0.5792876482009888} 08/31/2021 13:18:23 - INFO - __main__ - Step 133045: {'lr': 1.6019156895445753e-05, 'samples': 25544640, 'steps': 133044, 'loss/train': 1.4172323942184448} 08/31/2021 13:18:23 - INFO - __main__ - Step 133046: {'lr': 1.6017287893206083e-05, 'samples': 25544832, 'steps': 133045, 'loss/train': 1.648047685623169} 08/31/2021 13:18:23 - INFO - __main__ - Step 133047: {'lr': 1.6015418996395415e-05, 'samples': 25545024, 'steps': 133046, 'loss/train': 1.3241995573043823} 08/31/2021 13:18:24 - INFO - __main__ - Step 133048: {'lr': 1.6013550205014576e-05, 'samples': 25545216, 'steps': 133047, 'loss/train': 1.4332125186920166} 08/31/2021 13:18:25 - INFO - __main__ - Step 133049: {'lr': 1.60116815190644e-05, 'samples': 25545408, 'steps': 133048, 'loss/train': 0.2687512934207916} 08/31/2021 13:18:26 - INFO - __main__ - Step 133050: {'lr': 1.600981293854578e-05, 'samples': 25545600, 'steps': 133049, 'loss/train': 0.44589465856552124} 08/31/2021 13:18:26 - INFO - __main__ - Step 133051: {'lr': 1.600794446345952e-05, 'samples': 25545792, 'steps': 133050, 'loss/train': 0.9720704555511475} 08/31/2021 13:18:26 - INFO - __main__ - Step 133052: {'lr': 1.600607609380647e-05, 'samples': 25545984, 'steps': 133051, 'loss/train': 0.5807254910469055} 08/31/2021 13:18:27 - INFO - __main__ - Step 133053: {'lr': 1.6004207829587474e-05, 'samples': 25546176, 'steps': 133052, 'loss/train': 1.1686676740646362} 08/31/2021 13:18:28 - INFO - __main__ - Step 133054: {'lr': 1.6002339670803417e-05, 'samples': 25546368, 'steps': 133053, 'loss/train': 1.3450031280517578} 08/31/2021 13:18:29 - INFO - __main__ - Step 133055: {'lr': 1.600047161745505e-05, 'samples': 25546560, 'steps': 133054, 'loss/train': 1.163941740989685} 08/31/2021 13:18:29 - INFO - __main__ - Step 133056: {'lr': 1.5998603669543256e-05, 'samples': 25546752, 'steps': 133055, 'loss/train': 0.1125459223985672} 08/31/2021 13:18:29 - INFO - __main__ - Step 133057: {'lr': 1.599673582706887e-05, 'samples': 25546944, 'steps': 133056, 'loss/train': 1.1668990850448608} 08/31/2021 13:18:30 - INFO - __main__ - Step 133058: {'lr': 1.5994868090032756e-05, 'samples': 25547136, 'steps': 133057, 'loss/train': 1.4011939764022827} 08/31/2021 13:18:32 - INFO - __main__ - Step 133059: {'lr': 1.599300045843574e-05, 'samples': 25547328, 'steps': 133058, 'loss/train': 0.5910780429840088} 08/31/2021 13:18:32 - INFO - __main__ - Step 133060: {'lr': 1.5991132932278663e-05, 'samples': 25547520, 'steps': 133059, 'loss/train': 0.5708005428314209} 08/31/2021 13:18:32 - INFO - __main__ - Step 133061: {'lr': 1.5989265511562378e-05, 'samples': 25547712, 'steps': 133060, 'loss/train': 1.3380110263824463} 08/31/2021 13:18:33 - INFO - __main__ - Step 133062: {'lr': 1.5987398196287722e-05, 'samples': 25547904, 'steps': 133061, 'loss/train': 1.2279852628707886} 08/31/2021 13:18:33 - INFO - __main__ - Step 133063: {'lr': 1.5985530986455526e-05, 'samples': 25548096, 'steps': 133062, 'loss/train': 0.8966739177703857} 08/31/2021 13:18:35 - INFO - __main__ - Step 133064: {'lr': 1.598366388206665e-05, 'samples': 25548288, 'steps': 133063, 'loss/train': 1.119570016860962} 08/31/2021 13:18:35 - INFO - __main__ - Step 133065: {'lr': 1.5981796883121903e-05, 'samples': 25548480, 'steps': 133064, 'loss/train': 1.5052191019058228} 08/31/2021 13:18:35 - INFO - __main__ - Step 133066: {'lr': 1.5979929989622167e-05, 'samples': 25548672, 'steps': 133065, 'loss/train': 1.1786842346191406} 08/31/2021 13:18:36 - INFO - __main__ - Step 133067: {'lr': 1.597806320156825e-05, 'samples': 25548864, 'steps': 133066, 'loss/train': 1.415910005569458} 08/31/2021 13:18:36 - INFO - __main__ - Step 133068: {'lr': 1.5976196518961038e-05, 'samples': 25549056, 'steps': 133067, 'loss/train': 1.5231059789657593} 08/31/2021 13:18:36 - INFO - __main__ - Step 133069: {'lr': 1.5974329941801314e-05, 'samples': 25549248, 'steps': 133068, 'loss/train': 1.0693405866622925} 08/31/2021 13:18:38 - INFO - __main__ - Step 133070: {'lr': 1.597246347008996e-05, 'samples': 25549440, 'steps': 133069, 'loss/train': 0.9305183291435242} 08/31/2021 13:18:39 - INFO - __main__ - Step 133071: {'lr': 1.5970597103827782e-05, 'samples': 25549632, 'steps': 133070, 'loss/train': 1.2646514177322388} 08/31/2021 13:18:39 - INFO - __main__ - Step 133072: {'lr': 1.5968730843015643e-05, 'samples': 25549824, 'steps': 133071, 'loss/train': 1.120604157447815} 08/31/2021 13:18:39 - INFO - __main__ - Step 133073: {'lr': 1.5966864687654404e-05, 'samples': 25550016, 'steps': 133072, 'loss/train': 0.3950046896934509} 08/31/2021 13:18:40 - INFO - __main__ - Step 133074: {'lr': 1.5964998637744867e-05, 'samples': 25550208, 'steps': 133073, 'loss/train': 1.6575922966003418} 08/31/2021 13:18:40 - INFO - __main__ - Step 133075: {'lr': 1.596313269328789e-05, 'samples': 25550400, 'steps': 133074, 'loss/train': 0.02615266479551792} 08/31/2021 13:18:42 - INFO - __main__ - Step 133076: {'lr': 1.596126685428431e-05, 'samples': 25550592, 'steps': 133075, 'loss/train': 0.014594016596674919} 08/31/2021 13:18:42 - INFO - __main__ - Step 133077: {'lr': 1.595940112073499e-05, 'samples': 25550784, 'steps': 133076, 'loss/train': 0.6978694796562195} 08/31/2021 13:18:43 - INFO - __main__ - Step 133078: {'lr': 1.595753549264073e-05, 'samples': 25550976, 'steps': 133077, 'loss/train': 1.547931432723999} 08/31/2021 13:18:43 - INFO - __main__ - Step 133079: {'lr': 1.5955669970002418e-05, 'samples': 25551168, 'steps': 133078, 'loss/train': 1.076642394065857} 08/31/2021 13:18:43 - INFO - __main__ - Step 133080: {'lr': 1.5953804552820834e-05, 'samples': 25551360, 'steps': 133079, 'loss/train': 0.5803061723709106} 08/31/2021 13:18:45 - INFO - __main__ - Step 133081: {'lr': 1.595193924109692e-05, 'samples': 25551552, 'steps': 133080, 'loss/train': 1.5928605794906616} 08/31/2021 13:18:46 - INFO - __main__ - Step 133082: {'lr': 1.5950074034831398e-05, 'samples': 25551744, 'steps': 133081, 'loss/train': 1.4006222486495972} 08/31/2021 13:18:46 - INFO - __main__ - Step 133083: {'lr': 1.5948208934025182e-05, 'samples': 25551936, 'steps': 133082, 'loss/train': 0.12214445322751999} 08/31/2021 13:18:46 - INFO - __main__ - Step 133084: {'lr': 1.594634393867908e-05, 'samples': 25552128, 'steps': 133083, 'loss/train': 0.28870266675949097} 08/31/2021 13:18:47 - INFO - __main__ - Step 133085: {'lr': 1.5944479048793925e-05, 'samples': 25552320, 'steps': 133084, 'loss/train': 1.0805459022521973} 08/31/2021 13:18:47 - INFO - __main__ - Step 133086: {'lr': 1.5942614264370605e-05, 'samples': 25552512, 'steps': 133085, 'loss/train': 1.6561002731323242} 08/31/2021 13:18:49 - INFO - __main__ - Step 133087: {'lr': 1.594074958540992e-05, 'samples': 25552704, 'steps': 133086, 'loss/train': 1.0030999183654785} 08/31/2021 13:18:49 - INFO - __main__ - Step 133088: {'lr': 1.593888501191271e-05, 'samples': 25552896, 'steps': 133087, 'loss/train': 1.4449125528335571} 08/31/2021 13:18:49 - INFO - __main__ - Step 133089: {'lr': 1.5937020543879853e-05, 'samples': 25553088, 'steps': 133088, 'loss/train': 1.1223450899124146} 08/31/2021 13:18:50 - INFO - __main__ - Step 133090: {'lr': 1.5935156181312138e-05, 'samples': 25553280, 'steps': 133089, 'loss/train': 1.8454749584197998} 08/31/2021 13:18:50 - INFO - __main__ - Step 133091: {'lr': 1.5933291924210447e-05, 'samples': 25553472, 'steps': 133090, 'loss/train': 1.3701342344284058} 08/31/2021 13:18:51 - INFO - __main__ - Step 133092: {'lr': 1.5931427772575585e-05, 'samples': 25553664, 'steps': 133091, 'loss/train': 1.804470181465149} 08/31/2021 13:18:52 - INFO - __main__ - Step 133093: {'lr': 1.5929563726408415e-05, 'samples': 25553856, 'steps': 133092, 'loss/train': 0.6889517903327942} 08/31/2021 13:18:52 - INFO - __main__ - Step 133094: {'lr': 1.5927699785709792e-05, 'samples': 25554048, 'steps': 133093, 'loss/train': 0.7066673040390015} 08/31/2021 13:18:53 - INFO - __main__ - Step 133095: {'lr': 1.5925835950480554e-05, 'samples': 25554240, 'steps': 133094, 'loss/train': 0.6091188788414001} 08/31/2021 13:18:53 - INFO - __main__ - Step 133096: {'lr': 1.5923972220721477e-05, 'samples': 25554432, 'steps': 133095, 'loss/train': 1.3480314016342163} 08/31/2021 13:18:55 - INFO - __main__ - Step 133097: {'lr': 1.592210859643345e-05, 'samples': 25554624, 'steps': 133096, 'loss/train': 1.6463117599487305} 08/31/2021 13:18:55 - INFO - __main__ - Step 133098: {'lr': 1.592024507761733e-05, 'samples': 25554816, 'steps': 133097, 'loss/train': 1.6055923700332642} 08/31/2021 13:18:56 - INFO - __main__ - Step 133099: {'lr': 1.5918381664273925e-05, 'samples': 25555008, 'steps': 133098, 'loss/train': 0.7513397336006165} 08/31/2021 13:18:56 - INFO - __main__ - Step 133100: {'lr': 1.5916518356404063e-05, 'samples': 25555200, 'steps': 133099, 'loss/train': 0.6339359879493713} 08/31/2021 13:18:57 - INFO - __main__ - Step 133101: {'lr': 1.591465515400864e-05, 'samples': 25555392, 'steps': 133100, 'loss/train': 1.1859712600708008} 08/31/2021 13:18:57 - INFO - __main__ - Step 133102: {'lr': 1.5912792057088455e-05, 'samples': 25555584, 'steps': 133101, 'loss/train': 0.9125182628631592} 08/31/2021 13:18:59 - INFO - __main__ - Step 133103: {'lr': 1.591092906564434e-05, 'samples': 25555776, 'steps': 133102, 'loss/train': 0.9094395041465759} 08/31/2021 13:18:59 - INFO - __main__ - Step 133104: {'lr': 1.5909066179677135e-05, 'samples': 25555968, 'steps': 133103, 'loss/train': 0.5619605779647827} 08/31/2021 13:19:00 - INFO - __main__ - Step 133105: {'lr': 1.590720339918772e-05, 'samples': 25556160, 'steps': 133104, 'loss/train': 1.4330768585205078} 08/31/2021 13:19:00 - INFO - __main__ - Step 133106: {'lr': 1.5905340724176904e-05, 'samples': 25556352, 'steps': 133105, 'loss/train': 0.5620306134223938} 08/31/2021 13:19:00 - INFO - __main__ - Step 133107: {'lr': 1.5903478154645517e-05, 'samples': 25556544, 'steps': 133106, 'loss/train': 0.40502652525901794} 08/31/2021 13:19:02 - INFO - __main__ - Step 133108: {'lr': 1.590161569059445e-05, 'samples': 25556736, 'steps': 133107, 'loss/train': 0.9422721862792969} 08/31/2021 13:19:02 - INFO - __main__ - Step 133109: {'lr': 1.589975333202445e-05, 'samples': 25556928, 'steps': 133108, 'loss/train': 0.25985342264175415} 08/31/2021 13:19:03 - INFO - __main__ - Step 133110: {'lr': 1.5897891078936438e-05, 'samples': 25557120, 'steps': 133109, 'loss/train': 1.3157563209533691} 08/31/2021 13:19:03 - INFO - __main__ - Step 133111: {'lr': 1.5896028931331213e-05, 'samples': 25557312, 'steps': 133110, 'loss/train': 1.4977202415466309} 08/31/2021 13:19:04 - INFO - __main__ - Step 133112: {'lr': 1.589416688920964e-05, 'samples': 25557504, 'steps': 133111, 'loss/train': 0.49280819296836853} 08/31/2021 13:19:05 - INFO - __main__ - Step 133113: {'lr': 1.589230495257252e-05, 'samples': 25557696, 'steps': 133112, 'loss/train': 0.027467289939522743} 08/31/2021 13:19:06 - INFO - __main__ - Step 133114: {'lr': 1.589044312142071e-05, 'samples': 25557888, 'steps': 133113, 'loss/train': 1.1428358554840088} 08/31/2021 13:19:06 - INFO - __main__ - Step 133115: {'lr': 1.588858139575508e-05, 'samples': 25558080, 'steps': 133114, 'loss/train': 1.1229939460754395} 08/31/2021 13:19:06 - INFO - __main__ - Step 133116: {'lr': 1.588671977557643e-05, 'samples': 25558272, 'steps': 133115, 'loss/train': 0.6466689109802246} 08/31/2021 13:19:07 - INFO - __main__ - Step 133117: {'lr': 1.588485826088559e-05, 'samples': 25558464, 'steps': 133116, 'loss/train': 0.485779732465744} 08/31/2021 13:19:08 - INFO - __main__ - Step 133118: {'lr': 1.5882996851683456e-05, 'samples': 25558656, 'steps': 133117, 'loss/train': 1.1870605945587158} 08/31/2021 13:19:09 - INFO - __main__ - Step 133119: {'lr': 1.58811355479708e-05, 'samples': 25558848, 'steps': 133118, 'loss/train': 1.5845528841018677} 08/31/2021 13:19:09 - INFO - __main__ - Step 133120: {'lr': 1.5879274349748508e-05, 'samples': 25559040, 'steps': 133119, 'loss/train': 1.3143134117126465} 08/31/2021 13:19:09 - INFO - __main__ - Step 133121: {'lr': 1.5877413257017413e-05, 'samples': 25559232, 'steps': 133120, 'loss/train': 1.4859458208084106} 08/31/2021 13:19:10 - INFO - __main__ - Step 133122: {'lr': 1.5875552269778353e-05, 'samples': 25559424, 'steps': 133121, 'loss/train': 1.3051753044128418} 08/31/2021 13:19:11 - INFO - __main__ - Step 133123: {'lr': 1.5873691388032158e-05, 'samples': 25559616, 'steps': 133122, 'loss/train': 0.8792126178741455} 08/31/2021 13:19:12 - INFO - __main__ - Step 133124: {'lr': 1.587183061177963e-05, 'samples': 25559808, 'steps': 133123, 'loss/train': 0.5130163431167603} 08/31/2021 13:19:12 - INFO - __main__ - Step 133125: {'lr': 1.5869969941021662e-05, 'samples': 25560000, 'steps': 133124, 'loss/train': 0.028198199346661568} 08/31/2021 13:19:12 - INFO - __main__ - Step 133126: {'lr': 1.5868109375759055e-05, 'samples': 25560192, 'steps': 133125, 'loss/train': 0.5702282190322876} 08/31/2021 13:19:13 - INFO - __main__ - Step 133127: {'lr': 1.586624891599267e-05, 'samples': 25560384, 'steps': 133126, 'loss/train': 1.1850422620773315} 08/31/2021 13:19:14 - INFO - __main__ - Step 133128: {'lr': 1.586438856172334e-05, 'samples': 25560576, 'steps': 133127, 'loss/train': 0.9808973670005798} 08/31/2021 13:19:15 - INFO - __main__ - Step 133129: {'lr': 1.586252831295193e-05, 'samples': 25560768, 'steps': 133128, 'loss/train': 0.43573659658432007} 08/31/2021 13:19:15 - INFO - __main__ - Step 133130: {'lr': 1.586066816967921e-05, 'samples': 25560960, 'steps': 133129, 'loss/train': 1.6058162450790405} 08/31/2021 13:19:15 - INFO - __main__ - Step 133131: {'lr': 1.58588081319061e-05, 'samples': 25561152, 'steps': 133130, 'loss/train': 1.337120771408081} 08/31/2021 13:19:16 - INFO - __main__ - Step 133132: {'lr': 1.5856948199633375e-05, 'samples': 25561344, 'steps': 133131, 'loss/train': 0.7371697425842285} 08/31/2021 13:19:17 - INFO - __main__ - Step 133133: {'lr': 1.5855088372861898e-05, 'samples': 25561536, 'steps': 133132, 'loss/train': 1.5126267671585083} 08/31/2021 13:19:17 - INFO - __main__ - Step 133134: {'lr': 1.5853228651592498e-05, 'samples': 25561728, 'steps': 133133, 'loss/train': 1.1075774431228638} 08/31/2021 13:19:18 - INFO - __main__ - Step 133135: {'lr': 1.585136903582607e-05, 'samples': 25561920, 'steps': 133134, 'loss/train': 0.9839053153991699} 08/31/2021 13:19:18 - INFO - __main__ - Step 133136: {'lr': 1.5849509525563353e-05, 'samples': 25562112, 'steps': 133135, 'loss/train': 0.9421538710594177} 08/31/2021 13:19:19 - INFO - __main__ - Step 133137: {'lr': 1.5847650120805246e-05, 'samples': 25562304, 'steps': 133136, 'loss/train': 1.176024317741394} 08/31/2021 13:19:20 - INFO - __main__ - Step 133138: {'lr': 1.5845790821552576e-05, 'samples': 25562496, 'steps': 133137, 'loss/train': 0.8560023903846741} 08/31/2021 13:19:21 - INFO - __main__ - Step 133139: {'lr': 1.5843931627806174e-05, 'samples': 25562688, 'steps': 133138, 'loss/train': 1.0460091829299927} 08/31/2021 13:19:21 - INFO - __main__ - Step 133140: {'lr': 1.5842072539566878e-05, 'samples': 25562880, 'steps': 133139, 'loss/train': 0.7816322445869446} 08/31/2021 13:19:21 - INFO - __main__ - Step 133141: {'lr': 1.5840213556835543e-05, 'samples': 25563072, 'steps': 133140, 'loss/train': 0.8643243312835693} 08/31/2021 13:19:22 - INFO - __main__ - Step 133142: {'lr': 1.5838354679612977e-05, 'samples': 25563264, 'steps': 133141, 'loss/train': 1.847041368484497} 08/31/2021 13:19:23 - INFO - __main__ - Step 133143: {'lr': 1.583649590790004e-05, 'samples': 25563456, 'steps': 133142, 'loss/train': 1.869654893875122} 08/31/2021 13:19:24 - INFO - __main__ - Step 133144: {'lr': 1.5834637241697565e-05, 'samples': 25563648, 'steps': 133143, 'loss/train': 0.10631473362445831} 08/31/2021 13:19:24 - INFO - __main__ - Step 133145: {'lr': 1.583277868100641e-05, 'samples': 25563840, 'steps': 133144, 'loss/train': 1.436293363571167} 08/31/2021 13:19:24 - INFO - __main__ - Step 133146: {'lr': 1.5830920225827355e-05, 'samples': 25564032, 'steps': 133145, 'loss/train': 0.193791002035141} 08/31/2021 13:19:25 - INFO - __main__ - Step 133147: {'lr': 1.5829061876161317e-05, 'samples': 25564224, 'steps': 133146, 'loss/train': 0.5592283010482788} 08/31/2021 13:19:25 - INFO - __main__ - Step 133148: {'lr': 1.5827203632009095e-05, 'samples': 25564416, 'steps': 133147, 'loss/train': 1.2534153461456299} 08/31/2021 13:19:27 - INFO - __main__ - Step 133149: {'lr': 1.58253454933715e-05, 'samples': 25564608, 'steps': 133148, 'loss/train': 0.8382843136787415} 08/31/2021 13:19:27 - INFO - __main__ - Step 133150: {'lr': 1.5823487460249365e-05, 'samples': 25564800, 'steps': 133149, 'loss/train': 5.716484546661377} 08/31/2021 13:19:27 - INFO - __main__ - Step 133151: {'lr': 1.582162953264357e-05, 'samples': 25564992, 'steps': 133150, 'loss/train': 1.0208004713058472} 08/31/2021 13:19:28 - INFO - __main__ - Step 133152: {'lr': 1.5819771710554958e-05, 'samples': 25565184, 'steps': 133151, 'loss/train': 0.3191080391407013} 08/31/2021 13:19:28 - INFO - __main__ - Step 133153: {'lr': 1.5817913993984302e-05, 'samples': 25565376, 'steps': 133152, 'loss/train': 1.2532461881637573} 08/31/2021 13:19:30 - INFO - __main__ - Step 133154: {'lr': 1.5816056382932515e-05, 'samples': 25565568, 'steps': 133153, 'loss/train': 1.141135334968567} 08/31/2021 13:19:31 - INFO - __main__ - Step 133155: {'lr': 1.5814198877400376e-05, 'samples': 25565760, 'steps': 133154, 'loss/train': 1.0278732776641846} 08/31/2021 13:19:31 - INFO - __main__ - Step 133156: {'lr': 1.5812341477388748e-05, 'samples': 25565952, 'steps': 133155, 'loss/train': 0.960385799407959} 08/31/2021 13:19:31 - INFO - __main__ - Step 133157: {'lr': 1.581048418289849e-05, 'samples': 25566144, 'steps': 133156, 'loss/train': 1.6610697507858276} 08/31/2021 13:19:32 - INFO - __main__ - Step 133158: {'lr': 1.5808626993930403e-05, 'samples': 25566336, 'steps': 133157, 'loss/train': 0.9390696883201599} 08/31/2021 13:19:32 - INFO - __main__ - Step 133159: {'lr': 1.5806769910485325e-05, 'samples': 25566528, 'steps': 133158, 'loss/train': 1.379446029663086} 08/31/2021 13:19:34 - INFO - __main__ - Step 133160: {'lr': 1.5804912932564086e-05, 'samples': 25566720, 'steps': 133159, 'loss/train': 0.9893514513969421} 08/31/2021 13:19:34 - INFO - __main__ - Step 133161: {'lr': 1.5803056060167577e-05, 'samples': 25566912, 'steps': 133160, 'loss/train': 0.8738182187080383} 08/31/2021 13:19:35 - INFO - __main__ - Step 133162: {'lr': 1.5801199293296597e-05, 'samples': 25567104, 'steps': 133161, 'loss/train': 1.1335760354995728} 08/31/2021 13:19:35 - INFO - __main__ - Step 133163: {'lr': 1.5799342631951984e-05, 'samples': 25567296, 'steps': 133162, 'loss/train': 1.5694172382354736} 08/31/2021 13:19:35 - INFO - __main__ - Step 133164: {'lr': 1.5797486076134544e-05, 'samples': 25567488, 'steps': 133163, 'loss/train': 1.3497314453125} 08/31/2021 13:19:37 - INFO - __main__ - Step 133165: {'lr': 1.5795629625845158e-05, 'samples': 25567680, 'steps': 133164, 'loss/train': 2.066452980041504} 08/31/2021 13:19:37 - INFO - __main__ - Step 133166: {'lr': 1.579377328108464e-05, 'samples': 25567872, 'steps': 133165, 'loss/train': 0.5922706723213196} 08/31/2021 13:19:38 - INFO - __main__ - Step 133167: {'lr': 1.5791917041853843e-05, 'samples': 25568064, 'steps': 133166, 'loss/train': 0.9630373120307922} 08/31/2021 13:19:38 - INFO - __main__ - Step 133168: {'lr': 1.5790060908153575e-05, 'samples': 25568256, 'steps': 133167, 'loss/train': 1.1056861877441406} 08/31/2021 13:19:38 - INFO - __main__ - Step 133169: {'lr': 1.5788204879984697e-05, 'samples': 25568448, 'steps': 133168, 'loss/train': 1.158974289894104} 08/31/2021 13:19:40 - INFO - __main__ - Step 133170: {'lr': 1.5786348957348068e-05, 'samples': 25568640, 'steps': 133169, 'loss/train': 1.7029634714126587} 08/31/2021 13:19:40 - INFO - __main__ - Step 133171: {'lr': 1.5784493140244467e-05, 'samples': 25568832, 'steps': 133170, 'loss/train': 1.0356725454330444} 08/31/2021 13:19:41 - INFO - __main__ - Step 133172: {'lr': 1.578263742867475e-05, 'samples': 25569024, 'steps': 133171, 'loss/train': 1.5869768857955933} 08/31/2021 13:19:41 - INFO - __main__ - Step 133173: {'lr': 1.5780781822639785e-05, 'samples': 25569216, 'steps': 133172, 'loss/train': 1.401530146598816} 08/31/2021 13:19:41 - INFO - __main__ - Step 133174: {'lr': 1.577892632214037e-05, 'samples': 25569408, 'steps': 133173, 'loss/train': 0.8402954339981079} 08/31/2021 13:19:42 - INFO - __main__ - Step 133175: {'lr': 1.5777070927177422e-05, 'samples': 25569600, 'steps': 133174, 'loss/train': 0.2784228026866913} 08/31/2021 13:19:43 - INFO - __main__ - Step 133176: {'lr': 1.577521563775164e-05, 'samples': 25569792, 'steps': 133175, 'loss/train': 1.0125077962875366} 08/31/2021 13:19:44 - INFO - __main__ - Step 133177: {'lr': 1.577336045386396e-05, 'samples': 25569984, 'steps': 133176, 'loss/train': 1.0108357667922974} 08/31/2021 13:19:44 - INFO - __main__ - Step 133178: {'lr': 1.5771505375515167e-05, 'samples': 25570176, 'steps': 133177, 'loss/train': 0.7730053663253784} 08/31/2021 13:19:45 - INFO - __main__ - Step 133179: {'lr': 1.5769650402706144e-05, 'samples': 25570368, 'steps': 133178, 'loss/train': 0.18133175373077393} 08/31/2021 13:19:45 - INFO - __main__ - Step 133180: {'lr': 1.576779553543767e-05, 'samples': 25570560, 'steps': 133179, 'loss/train': 1.1086715459823608} 08/31/2021 13:19:46 - INFO - __main__ - Step 133181: {'lr': 1.5765940773710628e-05, 'samples': 25570752, 'steps': 133180, 'loss/train': 1.1021742820739746} 08/31/2021 13:19:47 - INFO - __main__ - Step 133182: {'lr': 1.576408611752586e-05, 'samples': 25570944, 'steps': 133181, 'loss/train': 1.305356740951538} 08/31/2021 13:19:47 - INFO - __main__ - Step 133183: {'lr': 1.576223156688414e-05, 'samples': 25571136, 'steps': 133182, 'loss/train': 1.163826584815979} 08/31/2021 13:19:48 - INFO - __main__ - Step 133184: {'lr': 1.576037712178638e-05, 'samples': 25571328, 'steps': 133183, 'loss/train': 0.7907370924949646} 08/31/2021 13:19:48 - INFO - __main__ - Step 133185: {'lr': 1.575852278223336e-05, 'samples': 25571520, 'steps': 133184, 'loss/train': 1.0330804586410522} 08/31/2021 13:19:50 - INFO - __main__ - Step 133186: {'lr': 1.5756668548225938e-05, 'samples': 25571712, 'steps': 133185, 'loss/train': 1.2205212116241455} 08/31/2021 13:19:50 - INFO - __main__ - Step 133187: {'lr': 1.575481441976495e-05, 'samples': 25571904, 'steps': 133186, 'loss/train': 0.8337960839271545} 08/31/2021 13:19:50 - INFO - __main__ - Step 133188: {'lr': 1.575296039685123e-05, 'samples': 25572096, 'steps': 133187, 'loss/train': 0.934981644153595} 08/31/2021 13:19:51 - INFO - __main__ - Step 133189: {'lr': 1.575110647948563e-05, 'samples': 25572288, 'steps': 133188, 'loss/train': 1.1430370807647705} 08/31/2021 13:19:51 - INFO - __main__ - Step 133190: {'lr': 1.574925266766894e-05, 'samples': 25572480, 'steps': 133189, 'loss/train': 0.9051540493965149} 08/31/2021 13:19:53 - INFO - __main__ - Step 133191: {'lr': 1.574739896140204e-05, 'samples': 25572672, 'steps': 133190, 'loss/train': 1.2919645309448242} 08/31/2021 13:19:53 - INFO - __main__ - Step 133192: {'lr': 1.574554536068573e-05, 'samples': 25572864, 'steps': 133191, 'loss/train': 1.2511802911758423} 08/31/2021 13:19:53 - INFO - __main__ - Step 133193: {'lr': 1.5743691865520853e-05, 'samples': 25573056, 'steps': 133192, 'loss/train': 1.129152536392212} 08/31/2021 13:19:54 - INFO - __main__ - Step 133194: {'lr': 1.5741838475908266e-05, 'samples': 25573248, 'steps': 133193, 'loss/train': 0.4410587251186371} 08/31/2021 13:19:54 - INFO - __main__ - Step 133195: {'lr': 1.57399851918488e-05, 'samples': 25573440, 'steps': 133194, 'loss/train': 1.5254343748092651} 08/31/2021 13:19:56 - INFO - __main__ - Step 133196: {'lr': 1.5738132013343288e-05, 'samples': 25573632, 'steps': 133195, 'loss/train': 1.5962028503417969} 08/31/2021 13:19:56 - INFO - __main__ - Step 133197: {'lr': 1.5736278940392533e-05, 'samples': 25573824, 'steps': 133196, 'loss/train': 1.5695226192474365} 08/31/2021 13:19:57 - INFO - __main__ - Step 133198: {'lr': 1.57344259729974e-05, 'samples': 25574016, 'steps': 133197, 'loss/train': 1.5255045890808105} 08/31/2021 13:19:57 - INFO - __main__ - Step 133199: {'lr': 1.573257311115872e-05, 'samples': 25574208, 'steps': 133198, 'loss/train': 0.48876920342445374} 08/31/2021 13:19:57 - INFO - __main__ - Step 133200: {'lr': 1.5730720354877355e-05, 'samples': 25574400, 'steps': 133199, 'loss/train': 1.2793649435043335} 08/31/2021 13:19:58 - INFO - __main__ - Step 133201: {'lr': 1.5728867704154075e-05, 'samples': 25574592, 'steps': 133200, 'loss/train': 1.8483785390853882} 08/31/2021 13:19:59 - INFO - __main__ - Step 133202: {'lr': 1.5727015158989834e-05, 'samples': 25574784, 'steps': 133201, 'loss/train': 1.2770215272903442} 08/31/2021 13:20:00 - INFO - __main__ - Step 133203: {'lr': 1.5725162719385315e-05, 'samples': 25574976, 'steps': 133202, 'loss/train': 1.397596001625061} 08/31/2021 13:20:00 - INFO - __main__ - Step 133204: {'lr': 1.5723310385341417e-05, 'samples': 25575168, 'steps': 133203, 'loss/train': 0.4459487199783325} 08/31/2021 13:20:01 - INFO - __main__ - Step 133205: {'lr': 1.5721458156858993e-05, 'samples': 25575360, 'steps': 133204, 'loss/train': 0.9258748292922974} 08/31/2021 13:20:01 - INFO - __main__ - Step 133206: {'lr': 1.571960603393885e-05, 'samples': 25575552, 'steps': 133205, 'loss/train': 2.4411144256591797} 08/31/2021 13:20:01 - INFO - __main__ - Step 133207: {'lr': 1.5717754016581874e-05, 'samples': 25575744, 'steps': 133206, 'loss/train': 1.0816833972930908} 08/31/2021 13:20:04 - INFO - __main__ - Step 133208: {'lr': 1.571590210478882e-05, 'samples': 25575936, 'steps': 133207, 'loss/train': 0.525618314743042} 08/31/2021 13:20:04 - INFO - __main__ - Step 133209: {'lr': 1.57140502985606e-05, 'samples': 25576128, 'steps': 133208, 'loss/train': 1.5296506881713867} 08/31/2021 13:20:04 - INFO - __main__ - Step 133210: {'lr': 1.5712198597897992e-05, 'samples': 25576320, 'steps': 133209, 'loss/train': 0.2090606689453125} 08/31/2021 13:20:05 - INFO - __main__ - Step 133211: {'lr': 1.5710347002801856e-05, 'samples': 25576512, 'steps': 133210, 'loss/train': 0.6998056769371033} 08/31/2021 13:20:05 - INFO - __main__ - Step 133212: {'lr': 1.5708495513273025e-05, 'samples': 25576704, 'steps': 133211, 'loss/train': 1.0862787961959839} 08/31/2021 13:20:07 - INFO - __main__ - Step 133213: {'lr': 1.5706644129312332e-05, 'samples': 25576896, 'steps': 133212, 'loss/train': 0.36769899725914} 08/31/2021 13:20:07 - INFO - __main__ - Step 133214: {'lr': 1.570479285092061e-05, 'samples': 25577088, 'steps': 133213, 'loss/train': 0.4914008677005768} 08/31/2021 13:20:08 - INFO - __main__ - Step 133215: {'lr': 1.5702941678098688e-05, 'samples': 25577280, 'steps': 133214, 'loss/train': 0.014834461733698845} 08/31/2021 13:20:08 - INFO - __main__ - Step 133216: {'lr': 1.5701090610847456e-05, 'samples': 25577472, 'steps': 133215, 'loss/train': 2.2263576984405518} 08/31/2021 13:20:08 - INFO - __main__ - Step 133217: {'lr': 1.569923964916764e-05, 'samples': 25577664, 'steps': 133216, 'loss/train': 1.3287712335586548} 08/31/2021 13:20:09 - INFO - __main__ - Step 133218: {'lr': 1.5697388793060123e-05, 'samples': 25577856, 'steps': 133217, 'loss/train': 0.3953101336956024} 08/31/2021 13:20:10 - INFO - __main__ - Step 133219: {'lr': 1.569553804252577e-05, 'samples': 25578048, 'steps': 133218, 'loss/train': 1.3780306577682495} 08/31/2021 13:20:11 - INFO - __main__ - Step 133220: {'lr': 1.5693687397565383e-05, 'samples': 25578240, 'steps': 133219, 'loss/train': 1.1503572463989258} 08/31/2021 13:20:11 - INFO - __main__ - Step 133221: {'lr': 1.569183685817982e-05, 'samples': 25578432, 'steps': 133220, 'loss/train': 1.4250156879425049} 08/31/2021 13:20:12 - INFO - __main__ - Step 133222: {'lr': 1.568998642436989e-05, 'samples': 25578624, 'steps': 133221, 'loss/train': 0.039960119873285294} 08/31/2021 13:20:12 - INFO - __main__ - Step 133223: {'lr': 1.5688136096136425e-05, 'samples': 25578816, 'steps': 133222, 'loss/train': 1.226887583732605} 08/31/2021 13:20:13 - INFO - __main__ - Step 133224: {'lr': 1.5686285873480282e-05, 'samples': 25579008, 'steps': 133223, 'loss/train': 0.5792240500450134} 08/31/2021 13:20:14 - INFO - __main__ - Step 133225: {'lr': 1.5684435756402273e-05, 'samples': 25579200, 'steps': 133224, 'loss/train': 1.1688885688781738} 08/31/2021 13:20:14 - INFO - __main__ - Step 133226: {'lr': 1.568258574490325e-05, 'samples': 25579392, 'steps': 133225, 'loss/train': 1.0531953573226929} 08/31/2021 13:20:15 - INFO - __main__ - Step 133227: {'lr': 1.5680735838984077e-05, 'samples': 25579584, 'steps': 133226, 'loss/train': 1.2983402013778687} 08/31/2021 13:20:15 - INFO - __main__ - Step 133228: {'lr': 1.5678886038645507e-05, 'samples': 25579776, 'steps': 133227, 'loss/train': 0.647650957107544} 08/31/2021 13:20:16 - INFO - __main__ - Step 133229: {'lr': 1.5677036343888422e-05, 'samples': 25579968, 'steps': 133228, 'loss/train': 0.8898724317550659} 08/31/2021 13:20:17 - INFO - __main__ - Step 133230: {'lr': 1.567518675471366e-05, 'samples': 25580160, 'steps': 133229, 'loss/train': 1.5447102785110474} 08/31/2021 13:20:17 - INFO - __main__ - Step 133231: {'lr': 1.5673337271122025e-05, 'samples': 25580352, 'steps': 133230, 'loss/train': 1.0653718709945679} 08/31/2021 13:20:18 - INFO - __main__ - Step 133232: {'lr': 1.5671487893114374e-05, 'samples': 25580544, 'steps': 133231, 'loss/train': 1.6197972297668457} 08/31/2021 13:20:18 - INFO - __main__ - Step 133233: {'lr': 1.566963862069151e-05, 'samples': 25580736, 'steps': 133232, 'loss/train': 1.0780665874481201} 08/31/2021 13:20:20 - INFO - __main__ - Step 133234: {'lr': 1.566778945385433e-05, 'samples': 25580928, 'steps': 133233, 'loss/train': 1.0813621282577515} 08/31/2021 13:20:20 - INFO - __main__ - Step 133235: {'lr': 1.5665940392603604e-05, 'samples': 25581120, 'steps': 133234, 'loss/train': 0.9239577054977417} 08/31/2021 13:20:20 - INFO - __main__ - Step 133236: {'lr': 1.5664091436940198e-05, 'samples': 25581312, 'steps': 133235, 'loss/train': 0.6348330974578857} 08/31/2021 13:20:21 - INFO - __main__ - Step 133237: {'lr': 1.5662242586864967e-05, 'samples': 25581504, 'steps': 133236, 'loss/train': 1.3323487043380737} 08/31/2021 13:20:21 - INFO - __main__ - Step 133238: {'lr': 1.566039384237866e-05, 'samples': 25581696, 'steps': 133237, 'loss/train': 1.6923000812530518} 08/31/2021 13:20:21 - INFO - __main__ - Step 133239: {'lr': 1.56585452034822e-05, 'samples': 25581888, 'steps': 133238, 'loss/train': 0.7538448572158813} 08/31/2021 13:20:23 - INFO - __main__ - Step 133240: {'lr': 1.565669667017636e-05, 'samples': 25582080, 'steps': 133239, 'loss/train': 0.9701834321022034} 08/31/2021 13:20:23 - INFO - __main__ - Step 133241: {'lr': 1.5654848242461995e-05, 'samples': 25582272, 'steps': 133240, 'loss/train': 1.1531343460083008} 08/31/2021 13:20:24 - INFO - __main__ - Step 133242: {'lr': 1.565299992033997e-05, 'samples': 25582464, 'steps': 133241, 'loss/train': 1.1373977661132812} 08/31/2021 13:20:24 - INFO - __main__ - Step 133243: {'lr': 1.565115170381104e-05, 'samples': 25582656, 'steps': 133242, 'loss/train': 0.7207934260368347} 08/31/2021 13:20:24 - INFO - __main__ - Step 133244: {'lr': 1.564930359287611e-05, 'samples': 25582848, 'steps': 133243, 'loss/train': 0.9809173345565796} 08/31/2021 13:20:26 - INFO - __main__ - Step 133245: {'lr': 1.5647455587535997e-05, 'samples': 25583040, 'steps': 133244, 'loss/train': 0.3564890921115875} 08/31/2021 13:20:26 - INFO - __main__ - Step 133246: {'lr': 1.5645607687791523e-05, 'samples': 25583232, 'steps': 133245, 'loss/train': 1.6854417324066162} 08/31/2021 13:20:27 - INFO - __main__ - Step 133247: {'lr': 1.56437598936435e-05, 'samples': 25583424, 'steps': 133246, 'loss/train': 0.8780203461647034} 08/31/2021 13:20:27 - INFO - __main__ - Step 133248: {'lr': 1.564191220509284e-05, 'samples': 25583616, 'steps': 133247, 'loss/train': 1.0273056030273438} 08/31/2021 13:20:28 - INFO - __main__ - Step 133249: {'lr': 1.5640064622140266e-05, 'samples': 25583808, 'steps': 133248, 'loss/train': 1.3600654602050781} 08/31/2021 13:20:29 - INFO - __main__ - Step 133250: {'lr': 1.5638217144786664e-05, 'samples': 25584000, 'steps': 133249, 'loss/train': 1.0324665307998657} 08/31/2021 13:20:29 - INFO - __main__ - Step 133251: {'lr': 1.5636369773032873e-05, 'samples': 25584192, 'steps': 133250, 'loss/train': 0.6045049428939819} 08/31/2021 13:20:30 - INFO - __main__ - Step 133252: {'lr': 1.5634522506879716e-05, 'samples': 25584384, 'steps': 133251, 'loss/train': 1.1255254745483398} 08/31/2021 13:20:30 - INFO - __main__ - Step 133253: {'lr': 1.5632675346328033e-05, 'samples': 25584576, 'steps': 133252, 'loss/train': 1.170507788658142} 08/31/2021 13:20:30 - INFO - __main__ - Step 133254: {'lr': 1.563082829137863e-05, 'samples': 25584768, 'steps': 133253, 'loss/train': 1.4062790870666504} 08/31/2021 13:20:32 - INFO - __main__ - Step 133255: {'lr': 1.562898134203239e-05, 'samples': 25584960, 'steps': 133254, 'loss/train': 1.4513192176818848} 08/31/2021 13:20:32 - INFO - __main__ - Step 133256: {'lr': 1.562713449829009e-05, 'samples': 25585152, 'steps': 133255, 'loss/train': 0.9991311430931091} 08/31/2021 13:20:33 - INFO - __main__ - Step 133257: {'lr': 1.5625287760152597e-05, 'samples': 25585344, 'steps': 133256, 'loss/train': 1.295015573501587} 08/31/2021 13:20:33 - INFO - __main__ - Step 133258: {'lr': 1.5623441127620708e-05, 'samples': 25585536, 'steps': 133257, 'loss/train': 0.9931759238243103} 08/31/2021 13:20:33 - INFO - __main__ - Step 133259: {'lr': 1.5621594600695342e-05, 'samples': 25585728, 'steps': 133258, 'loss/train': 1.1124205589294434} 08/31/2021 13:20:35 - INFO - __main__ - Step 133260: {'lr': 1.5619748179377225e-05, 'samples': 25585920, 'steps': 133259, 'loss/train': 0.842469334602356} 08/31/2021 13:20:36 - INFO - __main__ - Step 133261: {'lr': 1.561790186366724e-05, 'samples': 25586112, 'steps': 133260, 'loss/train': 1.3148987293243408} 08/31/2021 13:20:36 - INFO - __main__ - Step 133262: {'lr': 1.561605565356622e-05, 'samples': 25586304, 'steps': 133261, 'loss/train': 0.5031174421310425} 08/31/2021 13:20:37 - INFO - __main__ - Step 133263: {'lr': 1.561420954907497e-05, 'samples': 25586496, 'steps': 133262, 'loss/train': 0.6803701519966125} 08/31/2021 13:20:37 - INFO - __main__ - Step 133264: {'lr': 1.5612363550194352e-05, 'samples': 25586688, 'steps': 133263, 'loss/train': 1.2166638374328613} 08/31/2021 13:20:37 - INFO - __main__ - Step 133265: {'lr': 1.5610517656925173e-05, 'samples': 25586880, 'steps': 133264, 'loss/train': 0.809307873249054} 08/31/2021 13:20:39 - INFO - __main__ - Step 133266: {'lr': 1.5608671869268286e-05, 'samples': 25587072, 'steps': 133265, 'loss/train': 1.2125741243362427} 08/31/2021 13:20:39 - INFO - __main__ - Step 133267: {'lr': 1.5606826187224506e-05, 'samples': 25587264, 'steps': 133266, 'loss/train': 1.7819461822509766} 08/31/2021 13:20:40 - INFO - __main__ - Step 133268: {'lr': 1.5604980610794685e-05, 'samples': 25587456, 'steps': 133267, 'loss/train': 0.888332188129425} 08/31/2021 13:20:40 - INFO - __main__ - Step 133269: {'lr': 1.560313513997963e-05, 'samples': 25587648, 'steps': 133268, 'loss/train': 0.8099421262741089} 08/31/2021 13:20:40 - INFO - __main__ - Step 133270: {'lr': 1.560128977478023e-05, 'samples': 25587840, 'steps': 133269, 'loss/train': 1.022723913192749} 08/31/2021 13:20:42 - INFO - __main__ - Step 133271: {'lr': 1.5599444515197235e-05, 'samples': 25588032, 'steps': 133270, 'loss/train': 0.8771501183509827} 08/31/2021 13:20:42 - INFO - __main__ - Step 133272: {'lr': 1.5597599361231534e-05, 'samples': 25588224, 'steps': 133271, 'loss/train': 1.2820852994918823} 08/31/2021 13:20:43 - INFO - __main__ - Step 133273: {'lr': 1.5595754312883903e-05, 'samples': 25588416, 'steps': 133272, 'loss/train': 0.6997729539871216} 08/31/2021 13:20:43 - INFO - __main__ - Step 133274: {'lr': 1.559390937015523e-05, 'samples': 25588608, 'steps': 133273, 'loss/train': 3.3707666397094727} 08/31/2021 13:20:43 - INFO - __main__ - Step 133275: {'lr': 1.559206453304632e-05, 'samples': 25588800, 'steps': 133274, 'loss/train': 0.13947291672229767} 08/31/2021 13:20:45 - INFO - __main__ - Step 133276: {'lr': 1.5590219801558002e-05, 'samples': 25588992, 'steps': 133275, 'loss/train': 0.7506359815597534} 08/31/2021 13:20:45 - INFO - __main__ - Step 133277: {'lr': 1.5588375175691116e-05, 'samples': 25589184, 'steps': 133276, 'loss/train': 1.4493199586868286} 08/31/2021 13:20:46 - INFO - __main__ - Step 133278: {'lr': 1.558653065544649e-05, 'samples': 25589376, 'steps': 133277, 'loss/train': 1.162975549697876} 08/31/2021 13:20:46 - INFO - __main__ - Step 133279: {'lr': 1.5584686240824957e-05, 'samples': 25589568, 'steps': 133278, 'loss/train': 0.5540499687194824} 08/31/2021 13:20:46 - INFO - __main__ - Step 133280: {'lr': 1.558284193182735e-05, 'samples': 25589760, 'steps': 133279, 'loss/train': 0.1571320742368698} 08/31/2021 13:20:48 - INFO - __main__ - Step 133281: {'lr': 1.5580997728454478e-05, 'samples': 25589952, 'steps': 133280, 'loss/train': 0.7745110988616943} 08/31/2021 13:20:49 - INFO - __main__ - Step 133282: {'lr': 1.557915363070722e-05, 'samples': 25590144, 'steps': 133281, 'loss/train': 1.3602914810180664} 08/31/2021 13:20:49 - INFO - __main__ - Step 133283: {'lr': 1.5577309638586418e-05, 'samples': 25590336, 'steps': 133282, 'loss/train': 0.8636868596076965} 08/31/2021 13:20:49 - INFO - __main__ - Step 133284: {'lr': 1.5575465752092786e-05, 'samples': 25590528, 'steps': 133283, 'loss/train': 0.6026525497436523} 08/31/2021 13:20:50 - INFO - __main__ - Step 133285: {'lr': 1.5573621971227276e-05, 'samples': 25590720, 'steps': 133284, 'loss/train': 1.344260573387146} 08/31/2021 13:20:51 - INFO - __main__ - Step 133286: {'lr': 1.5571778295990658e-05, 'samples': 25590912, 'steps': 133285, 'loss/train': 1.255312204360962} 08/31/2021 13:20:52 - INFO - __main__ - Step 133287: {'lr': 1.5569934726383768e-05, 'samples': 25591104, 'steps': 133286, 'loss/train': 1.4683773517608643} 08/31/2021 13:20:52 - INFO - __main__ - Step 133288: {'lr': 1.5568091262407463e-05, 'samples': 25591296, 'steps': 133287, 'loss/train': 0.9474493861198425} 08/31/2021 13:20:52 - INFO - __main__ - Step 133289: {'lr': 1.5566247904062553e-05, 'samples': 25591488, 'steps': 133288, 'loss/train': 1.0440107583999634} 08/31/2021 13:20:53 - INFO - __main__ - Step 133290: {'lr': 1.5564404651349868e-05, 'samples': 25591680, 'steps': 133289, 'loss/train': 0.1920274943113327} 08/31/2021 13:20:53 - INFO - __main__ - Step 133291: {'lr': 1.556256150427024e-05, 'samples': 25591872, 'steps': 133290, 'loss/train': 0.8939681649208069} 08/31/2021 13:20:55 - INFO - __main__ - Step 133292: {'lr': 1.556071846282453e-05, 'samples': 25592064, 'steps': 133291, 'loss/train': 0.7648151516914368} 08/31/2021 13:20:55 - INFO - __main__ - Step 133293: {'lr': 1.5558875527013518e-05, 'samples': 25592256, 'steps': 133292, 'loss/train': 1.016098141670227} 08/31/2021 13:20:55 - INFO - __main__ - Step 133294: {'lr': 1.555703269683806e-05, 'samples': 25592448, 'steps': 133293, 'loss/train': 1.1705195903778076} 08/31/2021 13:20:56 - INFO - __main__ - Step 133295: {'lr': 1.555518997229899e-05, 'samples': 25592640, 'steps': 133294, 'loss/train': 0.7986893057823181} 08/31/2021 13:20:56 - INFO - __main__ - Step 133296: {'lr': 1.5553347353397197e-05, 'samples': 25592832, 'steps': 133295, 'loss/train': 0.5384398698806763} 08/31/2021 13:20:58 - INFO - __main__ - Step 133297: {'lr': 1.5551504840133372e-05, 'samples': 25593024, 'steps': 133296, 'loss/train': 1.0442756414413452} 08/31/2021 13:20:58 - INFO - __main__ - Step 133298: {'lr': 1.5549662432508437e-05, 'samples': 25593216, 'steps': 133297, 'loss/train': 1.3009836673736572} 08/31/2021 13:20:58 - INFO - __main__ - Step 133299: {'lr': 1.5547820130523222e-05, 'samples': 25593408, 'steps': 133298, 'loss/train': 1.4413707256317139} 08/31/2021 13:20:59 - INFO - __main__ - Step 133300: {'lr': 1.554597793417853e-05, 'samples': 25593600, 'steps': 133299, 'loss/train': 1.8367950916290283} 08/31/2021 13:20:59 - INFO - __main__ - Step 133301: {'lr': 1.5544135843475194e-05, 'samples': 25593792, 'steps': 133300, 'loss/train': 1.3322696685791016} 08/31/2021 13:21:01 - INFO - __main__ - Step 133302: {'lr': 1.5542293858414047e-05, 'samples': 25593984, 'steps': 133301, 'loss/train': 1.1636497974395752} 08/31/2021 13:21:01 - INFO - __main__ - Step 133303: {'lr': 1.5540451978995924e-05, 'samples': 25594176, 'steps': 133302, 'loss/train': 1.5852404832839966} 08/31/2021 13:21:02 - INFO - __main__ - Step 133304: {'lr': 1.553861020522168e-05, 'samples': 25594368, 'steps': 133303, 'loss/train': 0.8248928785324097} 08/31/2021 13:21:02 - INFO - __main__ - Step 133305: {'lr': 1.55367685370921e-05, 'samples': 25594560, 'steps': 133304, 'loss/train': 1.6777687072753906} 08/31/2021 13:21:02 - INFO - __main__ - Step 133306: {'lr': 1.553492697460804e-05, 'samples': 25594752, 'steps': 133305, 'loss/train': 1.4632692337036133} 08/31/2021 13:21:03 - INFO - __main__ - Step 133307: {'lr': 1.553308551777033e-05, 'samples': 25594944, 'steps': 133306, 'loss/train': 1.5960420370101929} 08/31/2021 13:21:04 - INFO - __main__ - Step 133308: {'lr': 1.5531244166579778e-05, 'samples': 25595136, 'steps': 133307, 'loss/train': 1.1982227563858032} 08/31/2021 13:21:05 - INFO - __main__ - Step 133309: {'lr': 1.5529402921037243e-05, 'samples': 25595328, 'steps': 133308, 'loss/train': 1.1411781311035156} 08/31/2021 13:21:05 - INFO - __main__ - Step 133310: {'lr': 1.552756178114359e-05, 'samples': 25595520, 'steps': 133309, 'loss/train': 0.5044041872024536} 08/31/2021 13:21:05 - INFO - __main__ - Step 133311: {'lr': 1.5525720746899535e-05, 'samples': 25595712, 'steps': 133310, 'loss/train': 1.0522737503051758} 08/31/2021 13:21:06 - INFO - __main__ - Step 133312: {'lr': 1.5523879818305996e-05, 'samples': 25595904, 'steps': 133311, 'loss/train': 1.5081818103790283} 08/31/2021 13:21:07 - INFO - __main__ - Step 133313: {'lr': 1.5522038995363753e-05, 'samples': 25596096, 'steps': 133312, 'loss/train': 1.3623758554458618} 08/31/2021 13:21:08 - INFO - __main__ - Step 133314: {'lr': 1.552019827807369e-05, 'samples': 25596288, 'steps': 133313, 'loss/train': 1.0909630060195923} 08/31/2021 13:21:08 - INFO - __main__ - Step 133315: {'lr': 1.5518357666436584e-05, 'samples': 25596480, 'steps': 133314, 'loss/train': 1.1810030937194824} 08/31/2021 13:21:08 - INFO - __main__ - Step 133316: {'lr': 1.5516517160453298e-05, 'samples': 25596672, 'steps': 133315, 'loss/train': 0.6412582993507385} 08/31/2021 13:21:09 - INFO - __main__ - Step 133317: {'lr': 1.5514676760124636e-05, 'samples': 25596864, 'steps': 133316, 'loss/train': 0.09911559522151947} 08/31/2021 13:21:11 - INFO - __main__ - Step 133318: {'lr': 1.551283646545146e-05, 'samples': 25597056, 'steps': 133317, 'loss/train': 1.199545979499817} 08/31/2021 13:21:11 - INFO - __main__ - Step 133319: {'lr': 1.551099627643457e-05, 'samples': 25597248, 'steps': 133318, 'loss/train': 1.433982253074646} 08/31/2021 13:21:12 - INFO - __main__ - Step 133320: {'lr': 1.55091561930748e-05, 'samples': 25597440, 'steps': 133319, 'loss/train': 0.3305588364601135} 08/31/2021 13:21:12 - INFO - __main__ - Step 133321: {'lr': 1.5507316215373018e-05, 'samples': 25597632, 'steps': 133320, 'loss/train': 1.3166838884353638} 08/31/2021 13:21:12 - INFO - __main__ - Step 133322: {'lr': 1.5505476343329992e-05, 'samples': 25597824, 'steps': 133321, 'loss/train': 1.3303487300872803} 08/31/2021 13:21:14 - INFO - __main__ - Step 133323: {'lr': 1.5503636576946646e-05, 'samples': 25598016, 'steps': 133322, 'loss/train': 1.162926435470581} 08/31/2021 13:21:14 - INFO - __main__ - Step 133324: {'lr': 1.5501796916223664e-05, 'samples': 25598208, 'steps': 133323, 'loss/train': 0.7307211756706238} 08/31/2021 13:21:15 - INFO - __main__ - Step 133325: {'lr': 1.5499957361161997e-05, 'samples': 25598400, 'steps': 133324, 'loss/train': 0.031966470181941986} 08/31/2021 13:21:15 - INFO - __main__ - Step 133326: {'lr': 1.5498117911762395e-05, 'samples': 25598592, 'steps': 133325, 'loss/train': 1.060373306274414} 08/31/2021 13:21:15 - INFO - __main__ - Step 133327: {'lr': 1.5496278568025742e-05, 'samples': 25598784, 'steps': 133326, 'loss/train': 1.4277453422546387} 08/31/2021 13:21:17 - INFO - __main__ - Step 133328: {'lr': 1.5494439329952844e-05, 'samples': 25598976, 'steps': 133327, 'loss/train': 1.0011013746261597} 08/31/2021 13:21:17 - INFO - __main__ - Step 133329: {'lr': 1.549260019754453e-05, 'samples': 25599168, 'steps': 133328, 'loss/train': 0.668699324131012} 08/31/2021 13:21:18 - INFO - __main__ - Step 133330: {'lr': 1.5490761170801643e-05, 'samples': 25599360, 'steps': 133329, 'loss/train': 0.9025237560272217} 08/31/2021 13:21:18 - INFO - __main__ - Step 133331: {'lr': 1.5488922249724978e-05, 'samples': 25599552, 'steps': 133330, 'loss/train': 1.0539295673370361} 08/31/2021 13:21:18 - INFO - __main__ - Step 133332: {'lr': 1.54870834343154e-05, 'samples': 25599744, 'steps': 133331, 'loss/train': 1.0991853475570679} 08/31/2021 13:21:20 - INFO - __main__ - Step 133333: {'lr': 1.5485244724573717e-05, 'samples': 25599936, 'steps': 133332, 'loss/train': 1.181051254272461} 08/31/2021 13:21:20 - INFO - __main__ - Step 133334: {'lr': 1.5483406120500782e-05, 'samples': 25600128, 'steps': 133333, 'loss/train': 1.2912929058074951} 08/31/2021 13:21:21 - INFO - __main__ - Step 133335: {'lr': 1.5481567622097376e-05, 'samples': 25600320, 'steps': 133334, 'loss/train': 0.7869198322296143} 08/31/2021 13:21:21 - INFO - __main__ - Step 133336: {'lr': 1.5479729229364385e-05, 'samples': 25600512, 'steps': 133335, 'loss/train': 1.1346253156661987} 08/31/2021 13:21:21 - INFO - __main__ - Step 133337: {'lr': 1.5477890942302618e-05, 'samples': 25600704, 'steps': 133336, 'loss/train': 1.0576494932174683} 08/31/2021 13:21:22 - INFO - __main__ - Step 133338: {'lr': 1.547605276091288e-05, 'samples': 25600896, 'steps': 133337, 'loss/train': 1.6991603374481201} 08/31/2021 13:21:23 - INFO - __main__ - Step 133339: {'lr': 1.5474214685196027e-05, 'samples': 25601088, 'steps': 133338, 'loss/train': 0.40581807494163513} 08/31/2021 13:21:24 - INFO - __main__ - Step 133340: {'lr': 1.5472376715152837e-05, 'samples': 25601280, 'steps': 133339, 'loss/train': 1.2988148927688599} 08/31/2021 13:21:24 - INFO - __main__ - Step 133341: {'lr': 1.54705388507842e-05, 'samples': 25601472, 'steps': 133340, 'loss/train': 1.1683995723724365} 08/31/2021 13:21:25 - INFO - __main__ - Step 133342: {'lr': 1.546870109209092e-05, 'samples': 25601664, 'steps': 133341, 'loss/train': 1.078940510749817} 08/31/2021 13:21:25 - INFO - __main__ - Step 133343: {'lr': 1.5466863439073804e-05, 'samples': 25601856, 'steps': 133342, 'loss/train': 1.2307764291763306} 08/31/2021 13:21:26 - INFO - __main__ - Step 133344: {'lr': 1.546502589173371e-05, 'samples': 25602048, 'steps': 133343, 'loss/train': 0.9591652154922485} 08/31/2021 13:21:27 - INFO - __main__ - Step 133345: {'lr': 1.546318845007147e-05, 'samples': 25602240, 'steps': 133344, 'loss/train': 1.1017873287200928} 08/31/2021 13:21:27 - INFO - __main__ - Step 133346: {'lr': 1.546135111408789e-05, 'samples': 25602432, 'steps': 133345, 'loss/train': 1.5447006225585938} 08/31/2021 13:21:28 - INFO - __main__ - Step 133347: {'lr': 1.5459513883783805e-05, 'samples': 25602624, 'steps': 133346, 'loss/train': 0.16773346066474915} 08/31/2021 13:21:28 - INFO - __main__ - Step 133348: {'lr': 1.5457676759160015e-05, 'samples': 25602816, 'steps': 133347, 'loss/train': 1.3904801607131958} 08/31/2021 13:21:30 - INFO - __main__ - Step 133349: {'lr': 1.5455839740217416e-05, 'samples': 25603008, 'steps': 133348, 'loss/train': 1.294264554977417} 08/31/2021 13:21:30 - INFO - __main__ - Step 133350: {'lr': 1.545400282695683e-05, 'samples': 25603200, 'steps': 133349, 'loss/train': 0.2168796807527542} 08/31/2021 13:21:30 - INFO - __main__ - Step 133351: {'lr': 1.5452166019378987e-05, 'samples': 25603392, 'steps': 133350, 'loss/train': 2.044985294342041} 08/31/2021 13:21:31 - INFO - __main__ - Step 133352: {'lr': 1.54503293174848e-05, 'samples': 25603584, 'steps': 133351, 'loss/train': 0.8698183298110962} 08/31/2021 13:21:31 - INFO - __main__ - Step 133353: {'lr': 1.5448492721275075e-05, 'samples': 25603776, 'steps': 133352, 'loss/train': 1.1001572608947754} 08/31/2021 13:21:33 - INFO - __main__ - Step 133354: {'lr': 1.5446656230750645e-05, 'samples': 25603968, 'steps': 133353, 'loss/train': 2.254279851913452} 08/31/2021 13:21:33 - INFO - __main__ - Step 133355: {'lr': 1.5444819845912313e-05, 'samples': 25604160, 'steps': 133354, 'loss/train': 1.4139041900634766} 08/31/2021 13:21:34 - INFO - __main__ - Step 133356: {'lr': 1.5442983566760937e-05, 'samples': 25604352, 'steps': 133355, 'loss/train': 1.647843360900879} 08/31/2021 13:21:34 - INFO - __main__ - Step 133357: {'lr': 1.544114739329733e-05, 'samples': 25604544, 'steps': 133356, 'loss/train': 1.356298804283142} 08/31/2021 13:21:34 - INFO - __main__ - Step 133358: {'lr': 1.5439311325522344e-05, 'samples': 25604736, 'steps': 133357, 'loss/train': 0.9679225087165833} 08/31/2021 13:21:36 - INFO - __main__ - Step 133359: {'lr': 1.543747536343676e-05, 'samples': 25604928, 'steps': 133358, 'loss/train': 0.6705908179283142} 08/31/2021 13:21:36 - INFO - __main__ - Step 133360: {'lr': 1.543563950704144e-05, 'samples': 25605120, 'steps': 133359, 'loss/train': 1.4727569818496704} 08/31/2021 13:21:37 - INFO - __main__ - Step 133361: {'lr': 1.5433803756337185e-05, 'samples': 25605312, 'steps': 133360, 'loss/train': 0.741021990776062} 08/31/2021 13:21:37 - INFO - __main__ - Step 133362: {'lr': 1.5431968111324856e-05, 'samples': 25605504, 'steps': 133361, 'loss/train': 0.87348473072052} 08/31/2021 13:21:37 - INFO - __main__ - Step 133363: {'lr': 1.5430132572005263e-05, 'samples': 25605696, 'steps': 133362, 'loss/train': 1.053489089012146} 08/31/2021 13:21:39 - INFO - __main__ - Step 133364: {'lr': 1.542829713837926e-05, 'samples': 25605888, 'steps': 133363, 'loss/train': 1.5433175563812256} 08/31/2021 13:21:39 - INFO - __main__ - Step 133365: {'lr': 1.54264618104476e-05, 'samples': 25606080, 'steps': 133364, 'loss/train': 0.3625783324241638} 08/31/2021 13:21:40 - INFO - __main__ - Step 133366: {'lr': 1.542462658821117e-05, 'samples': 25606272, 'steps': 133365, 'loss/train': 1.3337281942367554} 08/31/2021 13:21:40 - INFO - __main__ - Step 133367: {'lr': 1.5422791471670777e-05, 'samples': 25606464, 'steps': 133366, 'loss/train': 0.8882291913032532} 08/31/2021 13:21:40 - INFO - __main__ - Step 133368: {'lr': 1.542095646082728e-05, 'samples': 25606656, 'steps': 133367, 'loss/train': 0.6079397797584534} 08/31/2021 13:21:43 - INFO - __main__ - Step 133369: {'lr': 1.5419121555681454e-05, 'samples': 25606848, 'steps': 133368, 'loss/train': 0.9912706613540649} 08/31/2021 13:21:43 - INFO - __main__ - Step 133370: {'lr': 1.541728675623416e-05, 'samples': 25607040, 'steps': 133369, 'loss/train': 1.574821949005127} 08/31/2021 13:21:44 - INFO - __main__ - Step 133371: {'lr': 1.5415452062486207e-05, 'samples': 25607232, 'steps': 133370, 'loss/train': 0.14786961674690247} 08/31/2021 13:21:44 - INFO - __main__ - Step 133372: {'lr': 1.5413617474438452e-05, 'samples': 25607424, 'steps': 133371, 'loss/train': 0.6584704518318176} 08/31/2021 13:21:44 - INFO - __main__ - Step 133373: {'lr': 1.54117829920917e-05, 'samples': 25607616, 'steps': 133372, 'loss/train': 0.751528263092041} 08/31/2021 13:21:46 - INFO - __main__ - Step 133374: {'lr': 1.5409948615446758e-05, 'samples': 25607808, 'steps': 133373, 'loss/train': 0.7292612791061401} 08/31/2021 13:21:46 - INFO - __main__ - Step 133375: {'lr': 1.5408114344504482e-05, 'samples': 25608000, 'steps': 133374, 'loss/train': 0.9006589651107788} 08/31/2021 13:21:47 - INFO - __main__ - Step 133376: {'lr': 1.540628017926568e-05, 'samples': 25608192, 'steps': 133375, 'loss/train': 1.2883120775222778} 08/31/2021 13:21:47 - INFO - __main__ - Step 133377: {'lr': 1.540444611973124e-05, 'samples': 25608384, 'steps': 133376, 'loss/train': 0.8450829386711121} 08/31/2021 13:21:47 - INFO - __main__ - Step 133378: {'lr': 1.5402612165901913e-05, 'samples': 25608576, 'steps': 133377, 'loss/train': 1.8434361219406128} 08/31/2021 13:21:49 - INFO - __main__ - Step 133379: {'lr': 1.540077831777853e-05, 'samples': 25608768, 'steps': 133378, 'loss/train': 0.30267998576164246} 08/31/2021 13:21:49 - INFO - __main__ - Step 133380: {'lr': 1.539894457536192e-05, 'samples': 25608960, 'steps': 133379, 'loss/train': 0.13938243687152863} 08/31/2021 13:21:50 - INFO - __main__ - Step 133381: {'lr': 1.5397110938652953e-05, 'samples': 25609152, 'steps': 133380, 'loss/train': 0.6264378428459167} 08/31/2021 13:21:50 - INFO - __main__ - Step 133382: {'lr': 1.5395277407652426e-05, 'samples': 25609344, 'steps': 133381, 'loss/train': 0.510922908782959} 08/31/2021 13:21:50 - INFO - __main__ - Step 133383: {'lr': 1.5393443982361143e-05, 'samples': 25609536, 'steps': 133382, 'loss/train': 0.7614489197731018} 08/31/2021 13:21:52 - INFO - __main__ - Step 133384: {'lr': 1.5391610662779972e-05, 'samples': 25609728, 'steps': 133383, 'loss/train': 1.1794512271881104} 08/31/2021 13:21:52 - INFO - __main__ - Step 133385: {'lr': 1.5389777448909735e-05, 'samples': 25609920, 'steps': 133384, 'loss/train': 0.40751636028289795} 08/31/2021 13:21:53 - INFO - __main__ - Step 133386: {'lr': 1.538794434075122e-05, 'samples': 25610112, 'steps': 133385, 'loss/train': 0.7025924921035767} 08/31/2021 13:21:53 - INFO - __main__ - Step 133387: {'lr': 1.538611133830528e-05, 'samples': 25610304, 'steps': 133386, 'loss/train': 0.6127324104309082} 08/31/2021 13:21:53 - INFO - __main__ - Step 133388: {'lr': 1.5384278441572754e-05, 'samples': 25610496, 'steps': 133387, 'loss/train': 2.1663146018981934} 08/31/2021 13:21:55 - INFO - __main__ - Step 133389: {'lr': 1.538244565055444e-05, 'samples': 25610688, 'steps': 133388, 'loss/train': 1.380137324333191} 08/31/2021 13:21:56 - INFO - __main__ - Step 133390: {'lr': 1.53806129652512e-05, 'samples': 25610880, 'steps': 133389, 'loss/train': 1.2016136646270752} 08/31/2021 13:21:56 - INFO - __main__ - Step 133391: {'lr': 1.5378780385663816e-05, 'samples': 25611072, 'steps': 133390, 'loss/train': 0.19683073461055756} 08/31/2021 13:21:57 - INFO - __main__ - Step 133392: {'lr': 1.5376947911793143e-05, 'samples': 25611264, 'steps': 133391, 'loss/train': 0.9723666310310364} 08/31/2021 13:21:57 - INFO - __main__ - Step 133393: {'lr': 1.537511554363996e-05, 'samples': 25611456, 'steps': 133392, 'loss/train': 1.2083433866500854} 08/31/2021 13:21:57 - INFO - __main__ - Step 133394: {'lr': 1.5373283281205158e-05, 'samples': 25611648, 'steps': 133393, 'loss/train': 0.623252272605896} 08/31/2021 13:21:58 - INFO - __main__ - Step 133395: {'lr': 1.537145112448954e-05, 'samples': 25611840, 'steps': 133394, 'loss/train': 0.03627051040530205} 08/31/2021 13:21:59 - INFO - __main__ - Step 133396: {'lr': 1.5369619073493906e-05, 'samples': 25612032, 'steps': 133395, 'loss/train': 0.015062697231769562} 08/31/2021 13:22:00 - INFO - __main__ - Step 133397: {'lr': 1.5367787128219124e-05, 'samples': 25612224, 'steps': 133396, 'loss/train': 0.7581158876419067} 08/31/2021 13:22:00 - INFO - __main__ - Step 133398: {'lr': 1.5365955288665967e-05, 'samples': 25612416, 'steps': 133397, 'loss/train': 1.0361859798431396} 08/31/2021 13:22:00 - INFO - __main__ - Step 133399: {'lr': 1.5364123554835295e-05, 'samples': 25612608, 'steps': 133398, 'loss/train': 0.698231041431427} 08/31/2021 13:22:01 - INFO - __main__ - Step 133400: {'lr': 1.5362291926727945e-05, 'samples': 25612800, 'steps': 133399, 'loss/train': 1.3650740385055542} 08/31/2021 13:22:02 - INFO - __main__ - Step 133401: {'lr': 1.5360460404344717e-05, 'samples': 25612992, 'steps': 133400, 'loss/train': 0.025919845327734947} 08/31/2021 13:22:03 - INFO - __main__ - Step 133402: {'lr': 1.5358628987686447e-05, 'samples': 25613184, 'steps': 133401, 'loss/train': 0.7470222115516663} 08/31/2021 13:22:03 - INFO - __main__ - Step 133403: {'lr': 1.5356797676753965e-05, 'samples': 25613376, 'steps': 133402, 'loss/train': 1.0022085905075073} 08/31/2021 13:22:03 - INFO - __main__ - Step 133404: {'lr': 1.5354966471548105e-05, 'samples': 25613568, 'steps': 133403, 'loss/train': 1.48042631149292} 08/31/2021 13:22:04 - INFO - __main__ - Step 133405: {'lr': 1.535313537206967e-05, 'samples': 25613760, 'steps': 133404, 'loss/train': 1.2420440912246704} 08/31/2021 13:22:05 - INFO - __main__ - Step 133406: {'lr': 1.535130437831947e-05, 'samples': 25613952, 'steps': 133405, 'loss/train': 1.9405862092971802} 08/31/2021 13:22:06 - INFO - __main__ - Step 133407: {'lr': 1.534947349029836e-05, 'samples': 25614144, 'steps': 133406, 'loss/train': 0.961824357509613} 08/31/2021 13:22:06 - INFO - __main__ - Step 133408: {'lr': 1.534764270800715e-05, 'samples': 25614336, 'steps': 133407, 'loss/train': 1.274599552154541} 08/31/2021 13:22:06 - INFO - __main__ - Step 133409: {'lr': 1.5345812031446665e-05, 'samples': 25614528, 'steps': 133408, 'loss/train': 1.1633535623550415} 08/31/2021 13:22:07 - INFO - __main__ - Step 133410: {'lr': 1.5343981460617745e-05, 'samples': 25614720, 'steps': 133409, 'loss/train': 1.5940260887145996} 08/31/2021 13:22:08 - INFO - __main__ - Step 133411: {'lr': 1.534215099552119e-05, 'samples': 25614912, 'steps': 133410, 'loss/train': 1.1714540719985962} 08/31/2021 13:22:09 - INFO - __main__ - Step 133412: {'lr': 1.534032063615787e-05, 'samples': 25615104, 'steps': 133411, 'loss/train': 1.1921734809875488} 08/31/2021 13:22:09 - INFO - __main__ - Step 133413: {'lr': 1.5338490382528575e-05, 'samples': 25615296, 'steps': 133412, 'loss/train': 0.9519694447517395} 08/31/2021 13:22:09 - INFO - __main__ - Step 133414: {'lr': 1.533666023463412e-05, 'samples': 25615488, 'steps': 133413, 'loss/train': 0.8607778549194336} 08/31/2021 13:22:10 - INFO - __main__ - Step 133415: {'lr': 1.5334830192475362e-05, 'samples': 25615680, 'steps': 133414, 'loss/train': 1.295594334602356} 08/31/2021 13:22:10 - INFO - __main__ - Step 133416: {'lr': 1.533300025605308e-05, 'samples': 25615872, 'steps': 133415, 'loss/train': 1.165617823600769} 08/31/2021 13:22:12 - INFO - __main__ - Step 133417: {'lr': 1.533117042536819e-05, 'samples': 25616064, 'steps': 133416, 'loss/train': 1.2775996923446655} 08/31/2021 13:22:12 - INFO - __main__ - Step 133418: {'lr': 1.5329340700421412e-05, 'samples': 25616256, 'steps': 133417, 'loss/train': 1.3924888372421265} 08/31/2021 13:22:12 - INFO - __main__ - Step 133419: {'lr': 1.532751108121361e-05, 'samples': 25616448, 'steps': 133418, 'loss/train': 0.48433613777160645} 08/31/2021 13:22:13 - INFO - __main__ - Step 133420: {'lr': 1.5325681567745608e-05, 'samples': 25616640, 'steps': 133419, 'loss/train': 0.5529074668884277} 08/31/2021 13:22:13 - INFO - __main__ - Step 133421: {'lr': 1.532385216001822e-05, 'samples': 25616832, 'steps': 133420, 'loss/train': 1.088370680809021} 08/31/2021 13:22:15 - INFO - __main__ - Step 133422: {'lr': 1.5322022858032304e-05, 'samples': 25617024, 'steps': 133421, 'loss/train': 1.296316385269165} 08/31/2021 13:22:16 - INFO - __main__ - Step 133423: {'lr': 1.532019366178866e-05, 'samples': 25617216, 'steps': 133422, 'loss/train': 1.314935326576233} 08/31/2021 13:22:16 - INFO - __main__ - Step 133424: {'lr': 1.53183645712881e-05, 'samples': 25617408, 'steps': 133423, 'loss/train': 0.48522689938545227} 08/31/2021 13:22:16 - INFO - __main__ - Step 133425: {'lr': 1.5316535586531482e-05, 'samples': 25617600, 'steps': 133424, 'loss/train': 1.2291597127914429} 08/31/2021 13:22:17 - INFO - __main__ - Step 133426: {'lr': 1.531470670751961e-05, 'samples': 25617792, 'steps': 133425, 'loss/train': 1.819654107093811} 08/31/2021 13:22:18 - INFO - __main__ - Step 133427: {'lr': 1.531287793425329e-05, 'samples': 25617984, 'steps': 133426, 'loss/train': 0.6426457762718201} 08/31/2021 13:22:19 - INFO - __main__ - Step 133428: {'lr': 1.531104926673338e-05, 'samples': 25618176, 'steps': 133427, 'loss/train': 1.70699942111969} 08/31/2021 13:22:19 - INFO - __main__ - Step 133429: {'lr': 1.5309220704960687e-05, 'samples': 25618368, 'steps': 133428, 'loss/train': 0.9813247919082642} 08/31/2021 13:22:19 - INFO - __main__ - Step 133430: {'lr': 1.530739224893604e-05, 'samples': 25618560, 'steps': 133429, 'loss/train': 1.4619883298873901} 08/31/2021 13:22:20 - INFO - __main__ - Step 133431: {'lr': 1.5305563898660307e-05, 'samples': 25618752, 'steps': 133430, 'loss/train': 1.208426594734192} 08/31/2021 13:22:21 - INFO - __main__ - Step 133432: {'lr': 1.5303735654134204e-05, 'samples': 25618944, 'steps': 133431, 'loss/train': 1.1311231851577759} 08/31/2021 13:22:22 - INFO - __main__ - Step 133433: {'lr': 1.530190751535865e-05, 'samples': 25619136, 'steps': 133432, 'loss/train': 0.020977938547730446} 08/31/2021 13:22:22 - INFO - __main__ - Step 133434: {'lr': 1.5300079482334416e-05, 'samples': 25619328, 'steps': 133433, 'loss/train': 0.8126009702682495} 08/31/2021 13:22:23 - INFO - __main__ - Step 133435: {'lr': 1.5298251555062342e-05, 'samples': 25619520, 'steps': 133434, 'loss/train': 0.9586541056632996} 08/31/2021 13:22:23 - INFO - __main__ - Step 133436: {'lr': 1.529642373354326e-05, 'samples': 25619712, 'steps': 133435, 'loss/train': 0.9973469972610474} 08/31/2021 13:22:24 - INFO - __main__ - Step 133437: {'lr': 1.5294596017777968e-05, 'samples': 25619904, 'steps': 133436, 'loss/train': 1.2531332969665527} 08/31/2021 13:22:25 - INFO - __main__ - Step 133438: {'lr': 1.5292768407767332e-05, 'samples': 25620096, 'steps': 133437, 'loss/train': 0.0971861258149147} 08/31/2021 13:22:25 - INFO - __main__ - Step 133439: {'lr': 1.5290940903512158e-05, 'samples': 25620288, 'steps': 133438, 'loss/train': 0.9718774557113647} 08/31/2021 13:22:26 - INFO - __main__ - Step 133440: {'lr': 1.528911350501325e-05, 'samples': 25620480, 'steps': 133439, 'loss/train': 0.48072680830955505} 08/31/2021 13:22:26 - INFO - __main__ - Step 133441: {'lr': 1.5287286212271434e-05, 'samples': 25620672, 'steps': 133440, 'loss/train': 0.6824583411216736} 08/31/2021 13:22:28 - INFO - __main__ - Step 133442: {'lr': 1.528545902528755e-05, 'samples': 25620864, 'steps': 133441, 'loss/train': 1.1724169254302979} 08/31/2021 13:22:28 - INFO - __main__ - Step 133443: {'lr': 1.528363194406243e-05, 'samples': 25621056, 'steps': 133442, 'loss/train': 0.9920544624328613} 08/31/2021 13:22:28 - INFO - __main__ - Step 133444: {'lr': 1.5281804968596935e-05, 'samples': 25621248, 'steps': 133443, 'loss/train': 1.9264678955078125} 08/31/2021 13:22:29 - INFO - __main__ - Step 133445: {'lr': 1.5279978098891756e-05, 'samples': 25621440, 'steps': 133444, 'loss/train': 0.2632112503051758} 08/31/2021 13:22:29 - INFO - __main__ - Step 133446: {'lr': 1.5278151334947837e-05, 'samples': 25621632, 'steps': 133445, 'loss/train': 0.03364523500204086} 08/31/2021 13:22:31 - INFO - __main__ - Step 133447: {'lr': 1.5276324676765956e-05, 'samples': 25621824, 'steps': 133446, 'loss/train': 0.09768558293581009} 08/31/2021 13:22:31 - INFO - __main__ - Step 133448: {'lr': 1.527449812434692e-05, 'samples': 25622016, 'steps': 133447, 'loss/train': 0.5530911684036255} 08/31/2021 13:22:31 - INFO - __main__ - Step 133449: {'lr': 1.5272671677691584e-05, 'samples': 25622208, 'steps': 133448, 'loss/train': 1.5611586570739746} 08/31/2021 13:22:32 - INFO - __main__ - Step 133450: {'lr': 1.527084533680076e-05, 'samples': 25622400, 'steps': 133449, 'loss/train': 0.6410748362541199} 08/31/2021 13:22:32 - INFO - __main__ - Step 133451: {'lr': 1.5269019101675275e-05, 'samples': 25622592, 'steps': 133450, 'loss/train': 1.1178843975067139} 08/31/2021 13:22:34 - INFO - __main__ - Step 133452: {'lr': 1.5267192972315937e-05, 'samples': 25622784, 'steps': 133451, 'loss/train': 1.9099003076553345} 08/31/2021 13:22:34 - INFO - __main__ - Step 133453: {'lr': 1.5265366948723574e-05, 'samples': 25622976, 'steps': 133452, 'loss/train': 1.2367204427719116} 08/31/2021 13:22:35 - INFO - __main__ - Step 133454: {'lr': 1.5263541030899053e-05, 'samples': 25623168, 'steps': 133453, 'loss/train': 1.2152245044708252} 08/31/2021 13:22:35 - INFO - __main__ - Step 133455: {'lr': 1.526171521884312e-05, 'samples': 25623360, 'steps': 133454, 'loss/train': 1.3350849151611328} 08/31/2021 13:22:35 - INFO - __main__ - Step 133456: {'lr': 1.5259889512556634e-05, 'samples': 25623552, 'steps': 133455, 'loss/train': 1.2033250331878662} 08/31/2021 13:22:36 - INFO - __main__ - Step 133457: {'lr': 1.525806391204046e-05, 'samples': 25623744, 'steps': 133456, 'loss/train': 0.8816814422607422} 08/31/2021 13:22:37 - INFO - __main__ - Step 133458: {'lr': 1.5256238417295371e-05, 'samples': 25623936, 'steps': 133457, 'loss/train': 1.5038267374038696} 08/31/2021 13:22:38 - INFO - __main__ - Step 133459: {'lr': 1.52544130283222e-05, 'samples': 25624128, 'steps': 133458, 'loss/train': 1.3969130516052246} 08/31/2021 13:22:38 - INFO - __main__ - Step 133460: {'lr': 1.5252587745121727e-05, 'samples': 25624320, 'steps': 133459, 'loss/train': 1.5236960649490356} 08/31/2021 13:22:38 - INFO - __main__ - Step 133461: {'lr': 1.5250762567694836e-05, 'samples': 25624512, 'steps': 133460, 'loss/train': 1.7669471502304077} 08/31/2021 13:22:39 - INFO - __main__ - Step 133462: {'lr': 1.5248937496042337e-05, 'samples': 25624704, 'steps': 133461, 'loss/train': 1.0176464319229126} 08/31/2021 13:22:40 - INFO - __main__ - Step 133463: {'lr': 1.5247112530165058e-05, 'samples': 25624896, 'steps': 133462, 'loss/train': 0.8652136921882629} 08/31/2021 13:22:41 - INFO - __main__ - Step 133464: {'lr': 1.5245287670063779e-05, 'samples': 25625088, 'steps': 133463, 'loss/train': 1.6036268472671509} 08/31/2021 13:22:41 - INFO - __main__ - Step 133465: {'lr': 1.5243462915739359e-05, 'samples': 25625280, 'steps': 133464, 'loss/train': 1.3685917854309082} 08/31/2021 13:22:42 - INFO - __main__ - Step 133466: {'lr': 1.5241638267192603e-05, 'samples': 25625472, 'steps': 133465, 'loss/train': 0.18703840672969818} 08/31/2021 13:22:42 - INFO - __main__ - Step 133467: {'lr': 1.5239813724424345e-05, 'samples': 25625664, 'steps': 133466, 'loss/train': 0.6366928219795227} 08/31/2021 13:22:43 - INFO - __main__ - Step 133468: {'lr': 1.5237989287435417e-05, 'samples': 25625856, 'steps': 133467, 'loss/train': 0.8384929299354553} 08/31/2021 13:22:44 - INFO - __main__ - Step 133469: {'lr': 1.5236164956226622e-05, 'samples': 25626048, 'steps': 133468, 'loss/train': 0.060063835233449936} 08/31/2021 13:22:44 - INFO - __main__ - Step 133470: {'lr': 1.5234340730798795e-05, 'samples': 25626240, 'steps': 133469, 'loss/train': 1.0590170621871948} 08/31/2021 13:22:45 - INFO - __main__ - Step 133471: {'lr': 1.5232516611152797e-05, 'samples': 25626432, 'steps': 133470, 'loss/train': 1.0180473327636719} 08/31/2021 13:22:45 - INFO - __main__ - Step 133472: {'lr': 1.5230692597289348e-05, 'samples': 25626624, 'steps': 133471, 'loss/train': 0.90153568983078} 08/31/2021 13:22:45 - INFO - __main__ - Step 133473: {'lr': 1.5228868689209335e-05, 'samples': 25626816, 'steps': 133472, 'loss/train': 0.4660535454750061} 08/31/2021 13:22:47 - INFO - __main__ - Step 133474: {'lr': 1.5227044886913566e-05, 'samples': 25627008, 'steps': 133473, 'loss/train': 0.9408097863197327} 08/31/2021 13:22:48 - INFO - __main__ - Step 133475: {'lr': 1.5225221190402871e-05, 'samples': 25627200, 'steps': 133474, 'loss/train': 0.9003305435180664} 08/31/2021 13:22:48 - INFO - __main__ - Step 133476: {'lr': 1.5223397599678057e-05, 'samples': 25627392, 'steps': 133475, 'loss/train': 0.6881799101829529} 08/31/2021 13:22:49 - INFO - __main__ - Step 133477: {'lr': 1.5221574114739956e-05, 'samples': 25627584, 'steps': 133476, 'loss/train': 0.6239263415336609} 08/31/2021 13:22:49 - INFO - __main__ - Step 133478: {'lr': 1.5219750735589427e-05, 'samples': 25627776, 'steps': 133477, 'loss/train': 1.2715418338775635} 08/31/2021 13:22:49 - INFO - __main__ - Step 133479: {'lr': 1.5217927462227222e-05, 'samples': 25627968, 'steps': 133478, 'loss/train': 1.2378427982330322} 08/31/2021 13:22:51 - INFO - __main__ - Step 133480: {'lr': 1.5216104294654198e-05, 'samples': 25628160, 'steps': 133479, 'loss/train': 0.06948547810316086} 08/31/2021 13:22:52 - INFO - __main__ - Step 133481: {'lr': 1.5214281232871191e-05, 'samples': 25628352, 'steps': 133480, 'loss/train': 0.6243177652359009} 08/31/2021 13:22:52 - INFO - __main__ - Step 133482: {'lr': 1.5212458276878976e-05, 'samples': 25628544, 'steps': 133481, 'loss/train': 1.1340476274490356} 08/31/2021 13:22:53 - INFO - __main__ - Step 133483: {'lr': 1.5210635426678443e-05, 'samples': 25628736, 'steps': 133482, 'loss/train': 0.6093908548355103} 08/31/2021 13:22:53 - INFO - __main__ - Step 133484: {'lr': 1.5208812682270396e-05, 'samples': 25628928, 'steps': 133483, 'loss/train': 0.547685980796814} 08/31/2021 13:22:54 - INFO - __main__ - Step 133485: {'lr': 1.5206990043655583e-05, 'samples': 25629120, 'steps': 133484, 'loss/train': 0.08688563108444214} 08/31/2021 13:22:55 - INFO - __main__ - Step 133486: {'lr': 1.5205167510834894e-05, 'samples': 25629312, 'steps': 133485, 'loss/train': 1.083031177520752} 08/31/2021 13:22:55 - INFO - __main__ - Step 133487: {'lr': 1.5203345083809133e-05, 'samples': 25629504, 'steps': 133486, 'loss/train': 0.593252420425415} 08/31/2021 13:22:56 - INFO - __main__ - Step 133488: {'lr': 1.5201522762579106e-05, 'samples': 25629696, 'steps': 133487, 'loss/train': 1.015474557876587} 08/31/2021 13:22:56 - INFO - __main__ - Step 133489: {'lr': 1.5199700547145673e-05, 'samples': 25629888, 'steps': 133488, 'loss/train': 1.0707402229309082} 08/31/2021 13:22:57 - INFO - __main__ - Step 133490: {'lr': 1.519787843750961e-05, 'samples': 25630080, 'steps': 133489, 'loss/train': 0.6996455192565918} 08/31/2021 13:22:58 - INFO - __main__ - Step 133491: {'lr': 1.5196056433671778e-05, 'samples': 25630272, 'steps': 133490, 'loss/train': 1.2082676887512207} 08/31/2021 13:22:58 - INFO - __main__ - Step 133492: {'lr': 1.5194234535632955e-05, 'samples': 25630464, 'steps': 133491, 'loss/train': 1.1206350326538086} 08/31/2021 13:22:59 - INFO - __main__ - Step 133493: {'lr': 1.5192412743394002e-05, 'samples': 25630656, 'steps': 133492, 'loss/train': 0.7370386719703674} 08/31/2021 13:22:59 - INFO - __main__ - Step 133494: {'lr': 1.5190591056955722e-05, 'samples': 25630848, 'steps': 133493, 'loss/train': 0.287455290555954} 08/31/2021 13:23:00 - INFO - __main__ - Step 133495: {'lr': 1.5188769476318976e-05, 'samples': 25631040, 'steps': 133494, 'loss/train': 1.0711488723754883} 08/31/2021 13:23:01 - INFO - __main__ - Step 133496: {'lr': 1.5186948001484513e-05, 'samples': 25631232, 'steps': 133495, 'loss/train': 1.0952811241149902} 08/31/2021 13:23:01 - INFO - __main__ - Step 133497: {'lr': 1.5185126632453194e-05, 'samples': 25631424, 'steps': 133496, 'loss/train': 1.0774106979370117} 08/31/2021 13:23:02 - INFO - __main__ - Step 133498: {'lr': 1.5183305369225825e-05, 'samples': 25631616, 'steps': 133497, 'loss/train': 0.030268212780356407} 08/31/2021 13:23:02 - INFO - __main__ - Step 133499: {'lr': 1.5181484211803238e-05, 'samples': 25631808, 'steps': 133498, 'loss/train': 1.401606798171997} 08/31/2021 13:23:02 - INFO - __main__ - Step 133500: {'lr': 1.5179663160186263e-05, 'samples': 25632000, 'steps': 133499, 'loss/train': 0.6298530101776123} 08/31/2021 13:23:04 - INFO - __main__ - Step 133501: {'lr': 1.5177842214375681e-05, 'samples': 25632192, 'steps': 133500, 'loss/train': 0.8463252782821655} 08/31/2021 13:23:04 - INFO - __main__ - Step 133502: {'lr': 1.5176021374372351e-05, 'samples': 25632384, 'steps': 133501, 'loss/train': 1.1058390140533447} 08/31/2021 13:23:05 - INFO - __main__ - Step 133503: {'lr': 1.5174200640177105e-05, 'samples': 25632576, 'steps': 133502, 'loss/train': 1.3209456205368042} 08/31/2021 13:23:05 - INFO - __main__ - Step 133504: {'lr': 1.517238001179072e-05, 'samples': 25632768, 'steps': 133503, 'loss/train': 0.945050835609436} 08/31/2021 13:23:07 - INFO - __main__ - Step 133505: {'lr': 1.517055948921403e-05, 'samples': 25632960, 'steps': 133504, 'loss/train': 1.522569179534912} 08/31/2021 13:23:07 - INFO - __main__ - Step 133506: {'lr': 1.5168739072447896e-05, 'samples': 25633152, 'steps': 133505, 'loss/train': 1.5299782752990723} 08/31/2021 13:23:07 - INFO - __main__ - Step 133507: {'lr': 1.5166918761493092e-05, 'samples': 25633344, 'steps': 133506, 'loss/train': 0.0417826846241951} 08/31/2021 13:23:08 - INFO - __main__ - Step 133508: {'lr': 1.5165098556350426e-05, 'samples': 25633536, 'steps': 133507, 'loss/train': 0.5724194645881653} 08/31/2021 13:23:08 - INFO - __main__ - Step 133509: {'lr': 1.5163278457020758e-05, 'samples': 25633728, 'steps': 133508, 'loss/train': 1.1076141595840454} 08/31/2021 13:23:08 - INFO - __main__ - Step 133510: {'lr': 1.516145846350489e-05, 'samples': 25633920, 'steps': 133509, 'loss/train': 1.2929904460906982} 08/31/2021 13:23:10 - INFO - __main__ - Step 133511: {'lr': 1.515963857580363e-05, 'samples': 25634112, 'steps': 133510, 'loss/train': 0.39087530970573425} 08/31/2021 13:23:10 - INFO - __main__ - Step 133512: {'lr': 1.5157818793917839e-05, 'samples': 25634304, 'steps': 133511, 'loss/train': 1.0007232427597046} 08/31/2021 13:23:11 - INFO - __main__ - Step 133513: {'lr': 1.5155999117848291e-05, 'samples': 25634496, 'steps': 133512, 'loss/train': 1.3877710103988647} 08/31/2021 13:23:11 - INFO - __main__ - Step 133514: {'lr': 1.5154179547595847e-05, 'samples': 25634688, 'steps': 133513, 'loss/train': 1.1362162828445435} 08/31/2021 13:23:11 - INFO - __main__ - Step 133515: {'lr': 1.5152360083161288e-05, 'samples': 25634880, 'steps': 133514, 'loss/train': 0.4263059198856354} 08/31/2021 13:23:13 - INFO - __main__ - Step 133516: {'lr': 1.5150540724545469e-05, 'samples': 25635072, 'steps': 133515, 'loss/train': 0.8736369609832764} 08/31/2021 13:23:13 - INFO - __main__ - Step 133517: {'lr': 1.51487214717492e-05, 'samples': 25635264, 'steps': 133516, 'loss/train': 0.9401931762695312} 08/31/2021 13:23:14 - INFO - __main__ - Step 133518: {'lr': 1.5146902324773282e-05, 'samples': 25635456, 'steps': 133517, 'loss/train': 5.417137145996094} 08/31/2021 13:23:14 - INFO - __main__ - Step 133519: {'lr': 1.5145083283618522e-05, 'samples': 25635648, 'steps': 133518, 'loss/train': 1.1271865367889404} 08/31/2021 13:23:14 - INFO - __main__ - Step 133520: {'lr': 1.514326434828578e-05, 'samples': 25635840, 'steps': 133519, 'loss/train': 0.9414848685264587} 08/31/2021 13:23:16 - INFO - __main__ - Step 133521: {'lr': 1.5141445518775859e-05, 'samples': 25636032, 'steps': 133520, 'loss/train': 0.41329705715179443} 08/31/2021 13:23:16 - INFO - __main__ - Step 133522: {'lr': 1.5139626795089595e-05, 'samples': 25636224, 'steps': 133521, 'loss/train': 0.8336197733879089} 08/31/2021 13:23:17 - INFO - __main__ - Step 133523: {'lr': 1.5137808177227763e-05, 'samples': 25636416, 'steps': 133522, 'loss/train': 1.4041352272033691} 08/31/2021 13:23:17 - INFO - __main__ - Step 133524: {'lr': 1.5135989665191225e-05, 'samples': 25636608, 'steps': 133523, 'loss/train': 0.31525319814682007} 08/31/2021 13:23:17 - INFO - __main__ - Step 133525: {'lr': 1.5134171258980783e-05, 'samples': 25636800, 'steps': 133524, 'loss/train': 1.2675169706344604} 08/31/2021 13:23:19 - INFO - __main__ - Step 133526: {'lr': 1.5132352958597245e-05, 'samples': 25636992, 'steps': 133525, 'loss/train': 0.73614501953125} 08/31/2021 13:23:19 - INFO - __main__ - Step 133527: {'lr': 1.513053476404147e-05, 'samples': 25637184, 'steps': 133526, 'loss/train': 0.7813015580177307} 08/31/2021 13:23:20 - INFO - __main__ - Step 133528: {'lr': 1.5128716675314263e-05, 'samples': 25637376, 'steps': 133527, 'loss/train': 1.4344658851623535} 08/31/2021 13:23:20 - INFO - __main__ - Step 133529: {'lr': 1.5126898692416402e-05, 'samples': 25637568, 'steps': 133528, 'loss/train': 0.9177961945533752} 08/31/2021 13:23:21 - INFO - __main__ - Step 133530: {'lr': 1.5125080815348747e-05, 'samples': 25637760, 'steps': 133529, 'loss/train': 1.1076499223709106} 08/31/2021 13:23:23 - INFO - __main__ - Step 133531: {'lr': 1.51232630441121e-05, 'samples': 25637952, 'steps': 133530, 'loss/train': 1.2759809494018555} 08/31/2021 13:23:23 - INFO - __main__ - Step 133532: {'lr': 1.51214453787073e-05, 'samples': 25638144, 'steps': 133531, 'loss/train': 0.29565638303756714} 08/31/2021 13:23:23 - INFO - __main__ - Step 133533: {'lr': 1.5119627819135118e-05, 'samples': 25638336, 'steps': 133532, 'loss/train': 0.3014872968196869} 08/31/2021 13:23:24 - INFO - __main__ - Step 133534: {'lr': 1.5117810365396444e-05, 'samples': 25638528, 'steps': 133533, 'loss/train': 1.1464375257492065} 08/31/2021 13:23:24 - INFO - __main__ - Step 133535: {'lr': 1.511599301749203e-05, 'samples': 25638720, 'steps': 133534, 'loss/train': 1.3214759826660156} 08/31/2021 13:23:26 - INFO - __main__ - Step 133536: {'lr': 1.5114175775422761e-05, 'samples': 25638912, 'steps': 133535, 'loss/train': 1.1678626537322998} 08/31/2021 13:23:27 - INFO - __main__ - Step 133537: {'lr': 1.5112358639189388e-05, 'samples': 25639104, 'steps': 133536, 'loss/train': 0.04775552451610565} 08/31/2021 13:23:27 - INFO - __main__ - Step 133538: {'lr': 1.5110541608792772e-05, 'samples': 25639296, 'steps': 133537, 'loss/train': 0.09104207158088684} 08/31/2021 13:23:27 - INFO - __main__ - Step 133539: {'lr': 1.5108724684233771e-05, 'samples': 25639488, 'steps': 133538, 'loss/train': 1.4316136837005615} 08/31/2021 13:23:28 - INFO - __main__ - Step 133540: {'lr': 1.5106907865513109e-05, 'samples': 25639680, 'steps': 133539, 'loss/train': 0.8693036437034607} 08/31/2021 13:23:28 - INFO - __main__ - Step 133541: {'lr': 1.5105091152631645e-05, 'samples': 25639872, 'steps': 133540, 'loss/train': 0.8750746846199036} 08/31/2021 13:23:29 - INFO - __main__ - Step 133542: {'lr': 1.5103274545590185e-05, 'samples': 25640064, 'steps': 133541, 'loss/train': 1.2972218990325928} 08/31/2021 13:23:30 - INFO - __main__ - Step 133543: {'lr': 1.5101458044389588e-05, 'samples': 25640256, 'steps': 133542, 'loss/train': 1.4069921970367432} 08/31/2021 13:23:30 - INFO - __main__ - Step 133544: {'lr': 1.509964164903066e-05, 'samples': 25640448, 'steps': 133543, 'loss/train': 1.7391031980514526} 08/31/2021 13:23:31 - INFO - __main__ - Step 133545: {'lr': 1.5097825359514178e-05, 'samples': 25640640, 'steps': 133544, 'loss/train': 0.7880404591560364} 08/31/2021 13:23:31 - INFO - __main__ - Step 133546: {'lr': 1.5096009175841003e-05, 'samples': 25640832, 'steps': 133545, 'loss/train': 1.4231091737747192} 08/31/2021 13:23:33 - INFO - __main__ - Step 133547: {'lr': 1.5094193098011939e-05, 'samples': 25641024, 'steps': 133546, 'loss/train': 1.355384111404419} 08/31/2021 13:23:33 - INFO - __main__ - Step 133548: {'lr': 1.5092377126027818e-05, 'samples': 25641216, 'steps': 133547, 'loss/train': 1.0059003829956055} 08/31/2021 13:23:33 - INFO - __main__ - Step 133549: {'lr': 1.5090561259889447e-05, 'samples': 25641408, 'steps': 133548, 'loss/train': 1.1965287923812866} 08/31/2021 13:23:34 - INFO - __main__ - Step 133550: {'lr': 1.5088745499597628e-05, 'samples': 25641600, 'steps': 133549, 'loss/train': 1.2096428871154785} 08/31/2021 13:23:34 - INFO - __main__ - Step 133551: {'lr': 1.5086929845153224e-05, 'samples': 25641792, 'steps': 133550, 'loss/train': 0.6778693795204163} 08/31/2021 13:23:36 - INFO - __main__ - Step 133552: {'lr': 1.508511429655704e-05, 'samples': 25641984, 'steps': 133551, 'loss/train': 1.2019761800765991} 08/31/2021 13:23:36 - INFO - __main__ - Step 133553: {'lr': 1.508329885380985e-05, 'samples': 25642176, 'steps': 133552, 'loss/train': 0.19665472209453583} 08/31/2021 13:23:37 - INFO - __main__ - Step 133554: {'lr': 1.5081483516912493e-05, 'samples': 25642368, 'steps': 133553, 'loss/train': 1.1125764846801758} 08/31/2021 13:23:37 - INFO - __main__ - Step 133555: {'lr': 1.5079668285865795e-05, 'samples': 25642560, 'steps': 133554, 'loss/train': 0.8683192729949951} 08/31/2021 13:23:37 - INFO - __main__ - Step 133556: {'lr': 1.5077853160670563e-05, 'samples': 25642752, 'steps': 133555, 'loss/train': 1.4048914909362793} 08/31/2021 13:23:38 - INFO - __main__ - Step 133557: {'lr': 1.5076038141327659e-05, 'samples': 25642944, 'steps': 133556, 'loss/train': 0.8935145139694214} 08/31/2021 13:23:39 - INFO - __main__ - Step 133558: {'lr': 1.507422322783783e-05, 'samples': 25643136, 'steps': 133557, 'loss/train': 1.2985762357711792} 08/31/2021 13:23:40 - INFO - __main__ - Step 133559: {'lr': 1.5072408420201939e-05, 'samples': 25643328, 'steps': 133558, 'loss/train': 0.22447055578231812} 08/31/2021 13:23:40 - INFO - __main__ - Step 133560: {'lr': 1.5070593718420817e-05, 'samples': 25643520, 'steps': 133559, 'loss/train': 1.2651329040527344} 08/31/2021 13:23:40 - INFO - __main__ - Step 133561: {'lr': 1.5068779122495241e-05, 'samples': 25643712, 'steps': 133560, 'loss/train': 0.7631379961967468} 08/31/2021 13:23:41 - INFO - __main__ - Step 133562: {'lr': 1.5066964632426045e-05, 'samples': 25643904, 'steps': 133561, 'loss/train': 1.453335165977478} 08/31/2021 13:23:42 - INFO - __main__ - Step 133563: {'lr': 1.506515024821406e-05, 'samples': 25644096, 'steps': 133562, 'loss/train': 1.3176920413970947} 08/31/2021 13:23:43 - INFO - __main__ - Step 133564: {'lr': 1.5063335969860093e-05, 'samples': 25644288, 'steps': 133563, 'loss/train': 0.6743218898773193} 08/31/2021 13:23:43 - INFO - __main__ - Step 133565: {'lr': 1.5061521797365002e-05, 'samples': 25644480, 'steps': 133564, 'loss/train': 1.622207760810852} 08/31/2021 13:23:44 - INFO - __main__ - Step 133566: {'lr': 1.5059707730729511e-05, 'samples': 25644672, 'steps': 133565, 'loss/train': 0.927506148815155} 08/31/2021 13:23:44 - INFO - __main__ - Step 133567: {'lr': 1.5057893769954505e-05, 'samples': 25644864, 'steps': 133566, 'loss/train': 1.3416376113891602} 08/31/2021 13:23:45 - INFO - __main__ - Step 133568: {'lr': 1.5056079915040793e-05, 'samples': 25645056, 'steps': 133567, 'loss/train': 1.4649384021759033} 08/31/2021 13:23:46 - INFO - __main__ - Step 133569: {'lr': 1.5054266165989177e-05, 'samples': 25645248, 'steps': 133568, 'loss/train': 1.128834843635559} 08/31/2021 13:23:46 - INFO - __main__ - Step 133570: {'lr': 1.505245252280049e-05, 'samples': 25645440, 'steps': 133569, 'loss/train': 0.9206117987632751} 08/31/2021 13:23:47 - INFO - __main__ - Step 133571: {'lr': 1.5050638985475512e-05, 'samples': 25645632, 'steps': 133570, 'loss/train': 1.0635675191879272} 08/31/2021 13:23:47 - INFO - __main__ - Step 133572: {'lr': 1.5048825554015127e-05, 'samples': 25645824, 'steps': 133571, 'loss/train': 0.5101133584976196} 08/31/2021 13:23:48 - INFO - __main__ - Step 133573: {'lr': 1.5047012228420088e-05, 'samples': 25646016, 'steps': 133572, 'loss/train': 1.3025126457214355} 08/31/2021 13:23:49 - INFO - __main__ - Step 133574: {'lr': 1.5045199008691251e-05, 'samples': 25646208, 'steps': 133573, 'loss/train': 1.3943040370941162} 08/31/2021 13:23:49 - INFO - __main__ - Step 133575: {'lr': 1.5043385894829425e-05, 'samples': 25646400, 'steps': 133574, 'loss/train': 1.1169425249099731} 08/31/2021 13:23:49 - INFO - __main__ - Step 133576: {'lr': 1.5041572886835442e-05, 'samples': 25646592, 'steps': 133575, 'loss/train': 0.7477241158485413} 08/31/2021 13:23:50 - INFO - __main__ - Step 133577: {'lr': 1.5039759984710078e-05, 'samples': 25646784, 'steps': 133576, 'loss/train': 0.7482873797416687} 08/31/2021 13:23:51 - INFO - __main__ - Step 133578: {'lr': 1.5037947188454166e-05, 'samples': 25646976, 'steps': 133577, 'loss/train': 0.3222084641456604} 08/31/2021 13:23:52 - INFO - __main__ - Step 133579: {'lr': 1.5036134498068593e-05, 'samples': 25647168, 'steps': 133578, 'loss/train': 0.41833391785621643} 08/31/2021 13:23:52 - INFO - __main__ - Step 133580: {'lr': 1.5034321913554055e-05, 'samples': 25647360, 'steps': 133579, 'loss/train': 0.13312748074531555} 08/31/2021 13:23:53 - INFO - __main__ - Step 133581: {'lr': 1.5032509434911411e-05, 'samples': 25647552, 'steps': 133580, 'loss/train': 0.694831132888794} 08/31/2021 13:23:53 - INFO - __main__ - Step 133582: {'lr': 1.5030697062141524e-05, 'samples': 25647744, 'steps': 133581, 'loss/train': 0.8977597951889038} 08/31/2021 13:23:53 - INFO - __main__ - Step 133583: {'lr': 1.5028884795245167e-05, 'samples': 25647936, 'steps': 133582, 'loss/train': 1.4107458591461182} 08/31/2021 13:23:55 - INFO - __main__ - Step 133584: {'lr': 1.5027072634223148e-05, 'samples': 25648128, 'steps': 133583, 'loss/train': 0.3122031092643738} 08/31/2021 13:23:55 - INFO - __main__ - Step 133585: {'lr': 1.5025260579076328e-05, 'samples': 25648320, 'steps': 133584, 'loss/train': 0.493100106716156} 08/31/2021 13:23:56 - INFO - __main__ - Step 133586: {'lr': 1.5023448629805509e-05, 'samples': 25648512, 'steps': 133585, 'loss/train': 0.8793270587921143} 08/31/2021 13:23:56 - INFO - __main__ - Step 133587: {'lr': 1.5021636786411469e-05, 'samples': 25648704, 'steps': 133586, 'loss/train': 0.8435383439064026} 08/31/2021 13:23:56 - INFO - __main__ - Step 133588: {'lr': 1.501982504889507e-05, 'samples': 25648896, 'steps': 133587, 'loss/train': 0.07600463181734085} 08/31/2021 13:23:58 - INFO - __main__ - Step 133589: {'lr': 1.5018013417257115e-05, 'samples': 25649088, 'steps': 133588, 'loss/train': 0.4975973069667816} 08/31/2021 13:23:58 - INFO - __main__ - Step 133590: {'lr': 1.501620189149841e-05, 'samples': 25649280, 'steps': 133589, 'loss/train': 1.1454589366912842} 08/31/2021 13:23:59 - INFO - __main__ - Step 133591: {'lr': 1.5014390471619787e-05, 'samples': 25649472, 'steps': 133590, 'loss/train': 0.18466193974018097} 08/31/2021 13:23:59 - INFO - __main__ - Step 133592: {'lr': 1.5012579157622081e-05, 'samples': 25649664, 'steps': 133591, 'loss/train': 0.6461879014968872} 08/31/2021 13:23:59 - INFO - __main__ - Step 133593: {'lr': 1.5010767949506065e-05, 'samples': 25649856, 'steps': 133592, 'loss/train': 1.095251441001892} 08/31/2021 13:24:01 - INFO - __main__ - Step 133594: {'lr': 1.5008956847272549e-05, 'samples': 25650048, 'steps': 133593, 'loss/train': 1.4087632894515991} 08/31/2021 13:24:02 - INFO - __main__ - Step 133595: {'lr': 1.500714585092236e-05, 'samples': 25650240, 'steps': 133594, 'loss/train': 2.3836312294006348} 08/31/2021 13:24:02 - INFO - __main__ - Step 133596: {'lr': 1.5005334960456363e-05, 'samples': 25650432, 'steps': 133595, 'loss/train': 0.9541352987289429} 08/31/2021 13:24:03 - INFO - __main__ - Step 133597: {'lr': 1.5003524175875306e-05, 'samples': 25650624, 'steps': 133596, 'loss/train': 1.188979983329773} 08/31/2021 13:24:03 - INFO - __main__ - Step 133598: {'lr': 1.5001713497180047e-05, 'samples': 25650816, 'steps': 133597, 'loss/train': 1.2278543710708618} 08/31/2021 13:24:04 - INFO - __main__ - Step 133599: {'lr': 1.4999902924371367e-05, 'samples': 25651008, 'steps': 133598, 'loss/train': 1.0782719850540161} 08/31/2021 13:24:05 - INFO - __main__ - Step 133600: {'lr': 1.4998092457450124e-05, 'samples': 25651200, 'steps': 133599, 'loss/train': 0.9625149369239807} 08/31/2021 13:24:05 - INFO - __main__ - Step 133601: {'lr': 1.4996282096417125e-05, 'samples': 25651392, 'steps': 133600, 'loss/train': 0.9267165064811707} 08/31/2021 13:24:06 - INFO - __main__ - Step 133602: {'lr': 1.4994471841273144e-05, 'samples': 25651584, 'steps': 133601, 'loss/train': 0.6958125829696655} 08/31/2021 13:24:06 - INFO - __main__ - Step 133603: {'lr': 1.4992661692019072e-05, 'samples': 25651776, 'steps': 133602, 'loss/train': 1.0226038694381714} 08/31/2021 13:24:07 - INFO - __main__ - Step 133604: {'lr': 1.4990851648655629e-05, 'samples': 25651968, 'steps': 133603, 'loss/train': 1.0367153882980347} 08/31/2021 13:24:08 - INFO - __main__ - Step 133605: {'lr': 1.4989041711183732e-05, 'samples': 25652160, 'steps': 133604, 'loss/train': 0.03601199388504028} 08/31/2021 13:24:08 - INFO - __main__ - Step 133606: {'lr': 1.4987231879604157e-05, 'samples': 25652352, 'steps': 133605, 'loss/train': 1.0105222463607788} 08/31/2021 13:24:09 - INFO - __main__ - Step 133607: {'lr': 1.4985422153917654e-05, 'samples': 25652544, 'steps': 133606, 'loss/train': 1.128440022468567} 08/31/2021 13:24:09 - INFO - __main__ - Step 133608: {'lr': 1.4983612534125113e-05, 'samples': 25652736, 'steps': 133607, 'loss/train': 1.2909168004989624} 08/31/2021 13:24:09 - INFO - __main__ - Step 133609: {'lr': 1.4981803020227336e-05, 'samples': 25652928, 'steps': 133608, 'loss/train': 1.1563806533813477} 08/31/2021 13:24:11 - INFO - __main__ - Step 133610: {'lr': 1.497999361222513e-05, 'samples': 25653120, 'steps': 133609, 'loss/train': 0.03560074791312218} 08/31/2021 13:24:11 - INFO - __main__ - Step 133611: {'lr': 1.4978184310119297e-05, 'samples': 25653312, 'steps': 133610, 'loss/train': 0.8303470611572266} 08/31/2021 13:24:12 - INFO - __main__ - Step 133612: {'lr': 1.4976375113910672e-05, 'samples': 25653504, 'steps': 133611, 'loss/train': 1.3350043296813965} 08/31/2021 13:24:12 - INFO - __main__ - Step 133613: {'lr': 1.4974566023600089e-05, 'samples': 25653696, 'steps': 133612, 'loss/train': 1.648766040802002} 08/31/2021 13:24:12 - INFO - __main__ - Step 133614: {'lr': 1.4972757039188322e-05, 'samples': 25653888, 'steps': 133613, 'loss/train': 0.8153301477432251} 08/31/2021 13:24:14 - INFO - __main__ - Step 133615: {'lr': 1.4970948160676206e-05, 'samples': 25654080, 'steps': 133614, 'loss/train': 0.3742519021034241} 08/31/2021 13:24:14 - INFO - __main__ - Step 133616: {'lr': 1.4969139388064545e-05, 'samples': 25654272, 'steps': 133615, 'loss/train': 1.3050169944763184} 08/31/2021 13:24:15 - INFO - __main__ - Step 133617: {'lr': 1.4967330721354171e-05, 'samples': 25654464, 'steps': 133616, 'loss/train': 0.4691176116466522} 08/31/2021 13:24:15 - INFO - __main__ - Step 133618: {'lr': 1.496552216054589e-05, 'samples': 25654656, 'steps': 133617, 'loss/train': 1.1820991039276123} 08/31/2021 13:24:15 - INFO - __main__ - Step 133619: {'lr': 1.4963713705640564e-05, 'samples': 25654848, 'steps': 133618, 'loss/train': 0.9905062913894653} 08/31/2021 13:24:17 - INFO - __main__ - Step 133620: {'lr': 1.4961905356638911e-05, 'samples': 25655040, 'steps': 133619, 'loss/train': 0.623635470867157} 08/31/2021 13:24:18 - INFO - __main__ - Step 133621: {'lr': 1.4960097113541793e-05, 'samples': 25655232, 'steps': 133620, 'loss/train': 1.2062488794326782} 08/31/2021 13:24:18 - INFO - __main__ - Step 133622: {'lr': 1.4958288976350043e-05, 'samples': 25655424, 'steps': 133621, 'loss/train': 1.3253583908081055} 08/31/2021 13:24:18 - INFO - __main__ - Step 133623: {'lr': 1.4956480945064467e-05, 'samples': 25655616, 'steps': 133622, 'loss/train': 0.7387759685516357} 08/31/2021 13:24:19 - INFO - __main__ - Step 133624: {'lr': 1.4954673019685866e-05, 'samples': 25655808, 'steps': 133623, 'loss/train': 0.7526107430458069} 08/31/2021 13:24:19 - INFO - __main__ - Step 133625: {'lr': 1.495286520021505e-05, 'samples': 25656000, 'steps': 133624, 'loss/train': 1.353166103363037} 08/31/2021 13:24:19 - INFO - __main__ - Step 133626: {'lr': 1.4951057486652846e-05, 'samples': 25656192, 'steps': 133625, 'loss/train': 1.459228754043579} 08/31/2021 13:24:21 - INFO - __main__ - Step 133627: {'lr': 1.4949249879000092e-05, 'samples': 25656384, 'steps': 133626, 'loss/train': 1.245855689048767} 08/31/2021 13:24:21 - INFO - __main__ - Step 133628: {'lr': 1.4947442377257563e-05, 'samples': 25656576, 'steps': 133627, 'loss/train': 1.055046796798706} 08/31/2021 13:24:22 - INFO - __main__ - Step 133629: {'lr': 1.4945634981426093e-05, 'samples': 25656768, 'steps': 133628, 'loss/train': 0.5734484791755676} 08/31/2021 13:24:22 - INFO - __main__ - Step 133630: {'lr': 1.4943827691506485e-05, 'samples': 25656960, 'steps': 133629, 'loss/train': 0.32798638939857483} 08/31/2021 13:24:22 - INFO - __main__ - Step 133631: {'lr': 1.494202050749957e-05, 'samples': 25657152, 'steps': 133630, 'loss/train': 0.9571786522865295} 08/31/2021 13:24:24 - INFO - __main__ - Step 133632: {'lr': 1.4940213429406185e-05, 'samples': 25657344, 'steps': 133631, 'loss/train': 0.6744823455810547} 08/31/2021 13:24:24 - INFO - __main__ - Step 133633: {'lr': 1.4938406457227078e-05, 'samples': 25657536, 'steps': 133632, 'loss/train': 0.7882258892059326} 08/31/2021 13:24:25 - INFO - __main__ - Step 133634: {'lr': 1.4936599590963079e-05, 'samples': 25657728, 'steps': 133633, 'loss/train': 1.5602859258651733} 08/31/2021 13:24:25 - INFO - __main__ - Step 133635: {'lr': 1.4934792830615051e-05, 'samples': 25657920, 'steps': 133634, 'loss/train': 1.2670974731445312} 08/31/2021 13:24:25 - INFO - __main__ - Step 133636: {'lr': 1.4932986176183772e-05, 'samples': 25658112, 'steps': 133635, 'loss/train': 1.2782831192016602} 08/31/2021 13:24:27 - INFO - __main__ - Step 133637: {'lr': 1.4931179627670045e-05, 'samples': 25658304, 'steps': 133636, 'loss/train': 1.6459413766860962} 08/31/2021 13:24:27 - INFO - __main__ - Step 133638: {'lr': 1.492937318507473e-05, 'samples': 25658496, 'steps': 133637, 'loss/train': 0.9117157459259033} 08/31/2021 13:24:28 - INFO - __main__ - Step 133639: {'lr': 1.4927566848398577e-05, 'samples': 25658688, 'steps': 133638, 'loss/train': 0.1732519567012787} 08/31/2021 13:24:28 - INFO - __main__ - Step 133640: {'lr': 1.4925760617642448e-05, 'samples': 25658880, 'steps': 133639, 'loss/train': 0.9906898736953735} 08/31/2021 13:24:28 - INFO - __main__ - Step 133641: {'lr': 1.4923954492807146e-05, 'samples': 25659072, 'steps': 133640, 'loss/train': 1.659228801727295} 08/31/2021 13:24:30 - INFO - __main__ - Step 133642: {'lr': 1.4922148473893504e-05, 'samples': 25659264, 'steps': 133641, 'loss/train': 1.7916207313537598} 08/31/2021 13:24:30 - INFO - __main__ - Step 133643: {'lr': 1.49203425609023e-05, 'samples': 25659456, 'steps': 133642, 'loss/train': 2.1002144813537598} 08/31/2021 13:24:31 - INFO - __main__ - Step 133644: {'lr': 1.4918536753834339e-05, 'samples': 25659648, 'steps': 133643, 'loss/train': 1.3328205347061157} 08/31/2021 13:24:31 - INFO - __main__ - Step 133645: {'lr': 1.491673105269048e-05, 'samples': 25659840, 'steps': 133644, 'loss/train': 1.6845535039901733} 08/31/2021 13:24:31 - INFO - __main__ - Step 133646: {'lr': 1.4914925457471556e-05, 'samples': 25660032, 'steps': 133645, 'loss/train': 1.2313257455825806} 08/31/2021 13:24:33 - INFO - __main__ - Step 133647: {'lr': 1.4913119968178291e-05, 'samples': 25660224, 'steps': 133646, 'loss/train': 0.1542082130908966} 08/31/2021 13:24:33 - INFO - __main__ - Step 133648: {'lr': 1.4911314584811543e-05, 'samples': 25660416, 'steps': 133647, 'loss/train': 0.3362574875354767} 08/31/2021 13:24:34 - INFO - __main__ - Step 133649: {'lr': 1.4909509307372144e-05, 'samples': 25660608, 'steps': 133648, 'loss/train': 1.1560590267181396} 08/31/2021 13:24:34 - INFO - __main__ - Step 133650: {'lr': 1.4907704135860872e-05, 'samples': 25660800, 'steps': 133649, 'loss/train': 0.6670631170272827} 08/31/2021 13:24:34 - INFO - __main__ - Step 133651: {'lr': 1.490589907027859e-05, 'samples': 25660992, 'steps': 133650, 'loss/train': 0.8541924357414246} 08/31/2021 13:24:35 - INFO - __main__ - Step 133652: {'lr': 1.4904094110626042e-05, 'samples': 25661184, 'steps': 133651, 'loss/train': 1.444818139076233} 08/31/2021 13:24:37 - INFO - __main__ - Step 133653: {'lr': 1.4902289256904122e-05, 'samples': 25661376, 'steps': 133652, 'loss/train': 0.8102551102638245} 08/31/2021 13:24:37 - INFO - __main__ - Step 133654: {'lr': 1.4900484509113576e-05, 'samples': 25661568, 'steps': 133653, 'loss/train': 0.5211743116378784} 08/31/2021 13:24:38 - INFO - __main__ - Step 133655: {'lr': 1.4898679867255265e-05, 'samples': 25661760, 'steps': 133654, 'loss/train': 0.992896556854248} 08/31/2021 13:24:38 - INFO - __main__ - Step 133656: {'lr': 1.4896875331329968e-05, 'samples': 25661952, 'steps': 133655, 'loss/train': 1.1035808324813843} 08/31/2021 13:24:38 - INFO - __main__ - Step 133657: {'lr': 1.4895070901338515e-05, 'samples': 25662144, 'steps': 133656, 'loss/train': 1.351718544960022} 08/31/2021 13:24:40 - INFO - __main__ - Step 133658: {'lr': 1.4893266577281711e-05, 'samples': 25662336, 'steps': 133657, 'loss/train': 0.044750966131687164} 08/31/2021 13:24:40 - INFO - __main__ - Step 133659: {'lr': 1.489146235916039e-05, 'samples': 25662528, 'steps': 133658, 'loss/train': 1.2551904916763306} 08/31/2021 13:24:41 - INFO - __main__ - Step 133660: {'lr': 1.4889658246975357e-05, 'samples': 25662720, 'steps': 133659, 'loss/train': 1.4634283781051636} 08/31/2021 13:24:41 - INFO - __main__ - Step 133661: {'lr': 1.4887854240727388e-05, 'samples': 25662912, 'steps': 133660, 'loss/train': 0.4410581886768341} 08/31/2021 13:24:41 - INFO - __main__ - Step 133662: {'lr': 1.4886050340417318e-05, 'samples': 25663104, 'steps': 133661, 'loss/train': 1.0456396341323853} 08/31/2021 13:24:43 - INFO - __main__ - Step 133663: {'lr': 1.4884246546045976e-05, 'samples': 25663296, 'steps': 133662, 'loss/train': 1.449378490447998} 08/31/2021 13:24:43 - INFO - __main__ - Step 133664: {'lr': 1.488244285761417e-05, 'samples': 25663488, 'steps': 133663, 'loss/train': 0.6206154227256775} 08/31/2021 13:24:44 - INFO - __main__ - Step 133665: {'lr': 1.4880639275122704e-05, 'samples': 25663680, 'steps': 133664, 'loss/train': 1.059290885925293} 08/31/2021 13:24:44 - INFO - __main__ - Step 133666: {'lr': 1.4878835798572383e-05, 'samples': 25663872, 'steps': 133665, 'loss/train': 1.114816665649414} 08/31/2021 13:24:44 - INFO - __main__ - Step 133667: {'lr': 1.4877032427964038e-05, 'samples': 25664064, 'steps': 133666, 'loss/train': 2.364403009414673} 08/31/2021 13:24:46 - INFO - __main__ - Step 133668: {'lr': 1.4875229163298476e-05, 'samples': 25664256, 'steps': 133667, 'loss/train': 0.27500465512275696} 08/31/2021 13:24:46 - INFO - __main__ - Step 133669: {'lr': 1.4873426004576502e-05, 'samples': 25664448, 'steps': 133668, 'loss/train': 1.2027119398117065} 08/31/2021 13:24:47 - INFO - __main__ - Step 133670: {'lr': 1.4871622951798946e-05, 'samples': 25664640, 'steps': 133669, 'loss/train': 1.2478495836257935} 08/31/2021 13:24:47 - INFO - __main__ - Step 133671: {'lr': 1.4869820004966589e-05, 'samples': 25664832, 'steps': 133670, 'loss/train': 1.0901570320129395} 08/31/2021 13:24:47 - INFO - __main__ - Step 133672: {'lr': 1.486801716408029e-05, 'samples': 25665024, 'steps': 133671, 'loss/train': 1.4760432243347168} 08/31/2021 13:24:49 - INFO - __main__ - Step 133673: {'lr': 1.486621442914085e-05, 'samples': 25665216, 'steps': 133672, 'loss/train': 0.6128779053688049} 08/31/2021 13:24:49 - INFO - __main__ - Step 133674: {'lr': 1.4864411800149024e-05, 'samples': 25665408, 'steps': 133673, 'loss/train': 0.7613729238510132} 08/31/2021 13:24:50 - INFO - __main__ - Step 133675: {'lr': 1.486260927710567e-05, 'samples': 25665600, 'steps': 133674, 'loss/train': 1.1941593885421753} 08/31/2021 13:24:50 - INFO - __main__ - Step 133676: {'lr': 1.4860806860011594e-05, 'samples': 25665792, 'steps': 133675, 'loss/train': 0.6107636094093323} 08/31/2021 13:24:50 - INFO - __main__ - Step 133677: {'lr': 1.4859004548867628e-05, 'samples': 25665984, 'steps': 133676, 'loss/train': 1.5542978048324585} 08/31/2021 13:24:52 - INFO - __main__ - Step 133678: {'lr': 1.4857202343674548e-05, 'samples': 25666176, 'steps': 133677, 'loss/train': 1.1973315477371216} 08/31/2021 13:24:52 - INFO - __main__ - Step 133679: {'lr': 1.4855400244433187e-05, 'samples': 25666368, 'steps': 133678, 'loss/train': 1.2163422107696533} 08/31/2021 13:24:53 - INFO - __main__ - Step 133680: {'lr': 1.4853598251144379e-05, 'samples': 25666560, 'steps': 133679, 'loss/train': 1.4442180395126343} 08/31/2021 13:24:53 - INFO - __main__ - Step 133681: {'lr': 1.4851796363808872e-05, 'samples': 25666752, 'steps': 133680, 'loss/train': 0.7578200697898865} 08/31/2021 13:24:53 - INFO - __main__ - Step 133682: {'lr': 1.4849994582427556e-05, 'samples': 25666944, 'steps': 133681, 'loss/train': 1.2982399463653564} 08/31/2021 13:24:54 - INFO - __main__ - Step 133683: {'lr': 1.4848192907001178e-05, 'samples': 25667136, 'steps': 133682, 'loss/train': 0.9705727696418762} 08/31/2021 13:24:55 - INFO - __main__ - Step 133684: {'lr': 1.4846391337530574e-05, 'samples': 25667328, 'steps': 133683, 'loss/train': 1.3523870706558228} 08/31/2021 13:24:56 - INFO - __main__ - Step 133685: {'lr': 1.4844589874016573e-05, 'samples': 25667520, 'steps': 133684, 'loss/train': 0.3457080125808716} 08/31/2021 13:24:56 - INFO - __main__ - Step 133686: {'lr': 1.4842788516459981e-05, 'samples': 25667712, 'steps': 133685, 'loss/train': 1.5005435943603516} 08/31/2021 13:24:56 - INFO - __main__ - Step 133687: {'lr': 1.4840987264861606e-05, 'samples': 25667904, 'steps': 133686, 'loss/train': 1.4287123680114746} 08/31/2021 13:24:57 - INFO - __main__ - Step 133688: {'lr': 1.483918611922222e-05, 'samples': 25668096, 'steps': 133687, 'loss/train': 0.4857077896595001} 08/31/2021 13:24:58 - INFO - __main__ - Step 133689: {'lr': 1.4837385079542659e-05, 'samples': 25668288, 'steps': 133688, 'loss/train': 0.7684820294380188} 08/31/2021 13:24:59 - INFO - __main__ - Step 133690: {'lr': 1.4835584145823783e-05, 'samples': 25668480, 'steps': 133689, 'loss/train': 0.9934816360473633} 08/31/2021 13:24:59 - INFO - __main__ - Step 133691: {'lr': 1.483378331806634e-05, 'samples': 25668672, 'steps': 133690, 'loss/train': 1.676377773284912} 08/31/2021 13:24:59 - INFO - __main__ - Step 133692: {'lr': 1.4831982596271164e-05, 'samples': 25668864, 'steps': 133691, 'loss/train': 0.06239357590675354} 08/31/2021 13:25:00 - INFO - __main__ - Step 133693: {'lr': 1.4830181980439061e-05, 'samples': 25669056, 'steps': 133692, 'loss/train': 0.7078191041946411} 08/31/2021 13:25:01 - INFO - __main__ - Step 133694: {'lr': 1.4828381470570861e-05, 'samples': 25669248, 'steps': 133693, 'loss/train': 1.0757293701171875} 08/31/2021 13:25:02 - INFO - __main__ - Step 133695: {'lr': 1.4826581066667372e-05, 'samples': 25669440, 'steps': 133694, 'loss/train': 0.7387930750846863} 08/31/2021 13:25:02 - INFO - __main__ - Step 133696: {'lr': 1.4824780768729369e-05, 'samples': 25669632, 'steps': 133695, 'loss/train': 1.1571569442749023} 08/31/2021 13:25:02 - INFO - __main__ - Step 133697: {'lr': 1.482298057675771e-05, 'samples': 25669824, 'steps': 133696, 'loss/train': 0.34389403462409973} 08/31/2021 13:25:03 - INFO - __main__ - Step 133698: {'lr': 1.4821180490753205e-05, 'samples': 25670016, 'steps': 133697, 'loss/train': 0.8401527404785156} 08/31/2021 13:25:04 - INFO - __main__ - Step 133699: {'lr': 1.481938051071663e-05, 'samples': 25670208, 'steps': 133698, 'loss/train': 0.7030476927757263} 08/31/2021 13:25:05 - INFO - __main__ - Step 133700: {'lr': 1.4817580636648842e-05, 'samples': 25670400, 'steps': 133699, 'loss/train': 0.11916325986385345} 08/31/2021 13:25:05 - INFO - __main__ - Step 133701: {'lr': 1.4815780868550593e-05, 'samples': 25670592, 'steps': 133700, 'loss/train': 0.3461253046989441} 08/31/2021 13:25:06 - INFO - __main__ - Step 133702: {'lr': 1.4813981206422716e-05, 'samples': 25670784, 'steps': 133701, 'loss/train': 0.9666547179222107} 08/31/2021 13:25:06 - INFO - __main__ - Step 133703: {'lr': 1.4812181650266043e-05, 'samples': 25670976, 'steps': 133702, 'loss/train': 0.5517534017562866} 08/31/2021 13:25:08 - INFO - __main__ - Step 133704: {'lr': 1.4810382200081351e-05, 'samples': 25671168, 'steps': 133703, 'loss/train': 0.8491969108581543} 08/31/2021 13:25:08 - INFO - __main__ - Step 133705: {'lr': 1.4808582855869501e-05, 'samples': 25671360, 'steps': 133704, 'loss/train': 1.4096887111663818} 08/31/2021 13:25:09 - INFO - __main__ - Step 133706: {'lr': 1.4806783617631242e-05, 'samples': 25671552, 'steps': 133705, 'loss/train': 0.8029904365539551} 08/31/2021 13:25:09 - INFO - __main__ - Step 133707: {'lr': 1.4804984485367434e-05, 'samples': 25671744, 'steps': 133706, 'loss/train': 1.3079698085784912} 08/31/2021 13:25:10 - INFO - __main__ - Step 133708: {'lr': 1.4803185459078882e-05, 'samples': 25671936, 'steps': 133707, 'loss/train': 1.5634803771972656} 08/31/2021 13:25:11 - INFO - __main__ - Step 133709: {'lr': 1.4801386538766365e-05, 'samples': 25672128, 'steps': 133708, 'loss/train': 0.039481740444898605} 08/31/2021 13:25:12 - INFO - __main__ - Step 133710: {'lr': 1.4799587724430741e-05, 'samples': 25672320, 'steps': 133709, 'loss/train': 0.64275062084198} 08/31/2021 13:25:12 - INFO - __main__ - Step 133711: {'lr': 1.4797789016072761e-05, 'samples': 25672512, 'steps': 133710, 'loss/train': 0.08309046924114227} 08/31/2021 13:25:13 - INFO - __main__ - Step 133712: {'lr': 1.4795990413693283e-05, 'samples': 25672704, 'steps': 133711, 'loss/train': 1.6394656896591187} 08/31/2021 13:25:13 - INFO - __main__ - Step 133713: {'lr': 1.4794191917293143e-05, 'samples': 25672896, 'steps': 133712, 'loss/train': 1.6707448959350586} 08/31/2021 13:25:13 - INFO - __main__ - Step 133714: {'lr': 1.479239352687306e-05, 'samples': 25673088, 'steps': 133713, 'loss/train': 0.8615806698799133} 08/31/2021 13:25:15 - INFO - __main__ - Step 133715: {'lr': 1.4790595242433925e-05, 'samples': 25673280, 'steps': 133714, 'loss/train': 0.016733217984437943} 08/31/2021 13:25:16 - INFO - __main__ - Step 133716: {'lr': 1.4788797063976483e-05, 'samples': 25673472, 'steps': 133715, 'loss/train': 1.2835655212402344} 08/31/2021 13:25:16 - INFO - __main__ - Step 133717: {'lr': 1.47869989915016e-05, 'samples': 25673664, 'steps': 133716, 'loss/train': 1.4242275953292847} 08/31/2021 13:25:16 - INFO - __main__ - Step 133718: {'lr': 1.4785201025010048e-05, 'samples': 25673856, 'steps': 133717, 'loss/train': 2.2359437942504883} 08/31/2021 13:25:17 - INFO - __main__ - Step 133719: {'lr': 1.4783403164502663e-05, 'samples': 25674048, 'steps': 133718, 'loss/train': 1.313494086265564} 08/31/2021 13:25:17 - INFO - __main__ - Step 133720: {'lr': 1.4781605409980248e-05, 'samples': 25674240, 'steps': 133719, 'loss/train': 0.6598533391952515} 08/31/2021 13:25:19 - INFO - __main__ - Step 133721: {'lr': 1.4779807761443637e-05, 'samples': 25674432, 'steps': 133720, 'loss/train': 0.6661882400512695} 08/31/2021 13:25:19 - INFO - __main__ - Step 133722: {'lr': 1.4778010218893578e-05, 'samples': 25674624, 'steps': 133721, 'loss/train': 1.0214526653289795} 08/31/2021 13:25:20 - INFO - __main__ - Step 133723: {'lr': 1.4776212782330933e-05, 'samples': 25674816, 'steps': 133722, 'loss/train': 1.5367090702056885} 08/31/2021 13:25:20 - INFO - __main__ - Step 133724: {'lr': 1.4774415451756506e-05, 'samples': 25675008, 'steps': 133723, 'loss/train': 1.1633731126785278} 08/31/2021 13:25:20 - INFO - __main__ - Step 133725: {'lr': 1.4772618227171074e-05, 'samples': 25675200, 'steps': 133724, 'loss/train': 1.4434473514556885} 08/31/2021 13:25:21 - INFO - __main__ - Step 133726: {'lr': 1.4770821108575499e-05, 'samples': 25675392, 'steps': 133725, 'loss/train': 1.1907827854156494} 08/31/2021 13:25:22 - INFO - __main__ - Step 133727: {'lr': 1.4769024095970584e-05, 'samples': 25675584, 'steps': 133726, 'loss/train': 0.890010416507721} 08/31/2021 13:25:23 - INFO - __main__ - Step 133728: {'lr': 1.476722718935708e-05, 'samples': 25675776, 'steps': 133727, 'loss/train': 1.4705795049667358} 08/31/2021 13:25:23 - INFO - __main__ - Step 133729: {'lr': 1.4765430388735818e-05, 'samples': 25675968, 'steps': 133728, 'loss/train': 1.72560715675354} 08/31/2021 13:25:23 - INFO - __main__ - Step 133730: {'lr': 1.476363369410766e-05, 'samples': 25676160, 'steps': 133729, 'loss/train': 0.5732669234275818} 08/31/2021 13:25:24 - INFO - __main__ - Step 133731: {'lr': 1.4761837105473352e-05, 'samples': 25676352, 'steps': 133730, 'loss/train': 0.2860322892665863} 08/31/2021 13:25:25 - INFO - __main__ - Step 133732: {'lr': 1.4760040622833731e-05, 'samples': 25676544, 'steps': 133731, 'loss/train': 0.7274993658065796} 08/31/2021 13:25:26 - INFO - __main__ - Step 133733: {'lr': 1.47582442461896e-05, 'samples': 25676736, 'steps': 133732, 'loss/train': 0.7072908878326416} 08/31/2021 13:25:26 - INFO - __main__ - Step 133734: {'lr': 1.4756447975541793e-05, 'samples': 25676928, 'steps': 133733, 'loss/train': 1.4207220077514648} 08/31/2021 13:25:26 - INFO - __main__ - Step 133735: {'lr': 1.4754651810891084e-05, 'samples': 25677120, 'steps': 133734, 'loss/train': 1.5560486316680908} 08/31/2021 13:25:27 - INFO - __main__ - Step 133736: {'lr': 1.475285575223831e-05, 'samples': 25677312, 'steps': 133735, 'loss/train': 1.002142071723938} 08/31/2021 13:25:28 - INFO - __main__ - Step 133737: {'lr': 1.475105979958427e-05, 'samples': 25677504, 'steps': 133736, 'loss/train': 0.7582975029945374} 08/31/2021 13:25:29 - INFO - __main__ - Step 133738: {'lr': 1.4749263952929775e-05, 'samples': 25677696, 'steps': 133737, 'loss/train': 0.5103844404220581} 08/31/2021 13:25:29 - INFO - __main__ - Step 133739: {'lr': 1.4747468212275628e-05, 'samples': 25677888, 'steps': 133738, 'loss/train': 1.1298636198043823} 08/31/2021 13:25:29 - INFO - __main__ - Step 133740: {'lr': 1.474567257762266e-05, 'samples': 25678080, 'steps': 133739, 'loss/train': 0.5989558100700378} 08/31/2021 13:25:30 - INFO - __main__ - Step 133741: {'lr': 1.4743877048971649e-05, 'samples': 25678272, 'steps': 133740, 'loss/train': 1.2142874002456665} 08/31/2021 13:25:31 - INFO - __main__ - Step 133742: {'lr': 1.47420816263234e-05, 'samples': 25678464, 'steps': 133741, 'loss/train': 0.7871203422546387} 08/31/2021 13:25:32 - INFO - __main__ - Step 133743: {'lr': 1.4740286309678747e-05, 'samples': 25678656, 'steps': 133742, 'loss/train': 1.2692477703094482} 08/31/2021 13:25:32 - INFO - __main__ - Step 133744: {'lr': 1.4738491099038492e-05, 'samples': 25678848, 'steps': 133743, 'loss/train': 0.9601889848709106} 08/31/2021 13:25:32 - INFO - __main__ - Step 133745: {'lr': 1.4736695994403443e-05, 'samples': 25679040, 'steps': 133744, 'loss/train': 1.1832213401794434} 08/31/2021 13:25:33 - INFO - __main__ - Step 133746: {'lr': 1.4734900995774403e-05, 'samples': 25679232, 'steps': 133745, 'loss/train': 0.1791093796491623} 08/31/2021 13:25:34 - INFO - __main__ - Step 133747: {'lr': 1.4733106103152205e-05, 'samples': 25679424, 'steps': 133746, 'loss/train': 1.036108374595642} 08/31/2021 13:25:35 - INFO - __main__ - Step 133748: {'lr': 1.4731311316537626e-05, 'samples': 25679616, 'steps': 133747, 'loss/train': 0.839022159576416} 08/31/2021 13:25:35 - INFO - __main__ - Step 133749: {'lr': 1.4729516635931473e-05, 'samples': 25679808, 'steps': 133748, 'loss/train': 0.7041990160942078} 08/31/2021 13:25:35 - INFO - __main__ - Step 133750: {'lr': 1.4727722061334602e-05, 'samples': 25680000, 'steps': 133749, 'loss/train': 0.762380063533783} 08/31/2021 13:25:36 - INFO - __main__ - Step 133751: {'lr': 1.4725927592747768e-05, 'samples': 25680192, 'steps': 133750, 'loss/train': 1.589146375656128} 08/31/2021 13:25:37 - INFO - __main__ - Step 133752: {'lr': 1.4724133230171798e-05, 'samples': 25680384, 'steps': 133751, 'loss/train': 1.0896987915039062} 08/31/2021 13:25:38 - INFO - __main__ - Step 133753: {'lr': 1.472233897360753e-05, 'samples': 25680576, 'steps': 133752, 'loss/train': 1.0656667947769165} 08/31/2021 13:25:38 - INFO - __main__ - Step 133754: {'lr': 1.4720544823055738e-05, 'samples': 25680768, 'steps': 133753, 'loss/train': 0.9959344267845154} 08/31/2021 13:25:38 - INFO - __main__ - Step 133755: {'lr': 1.4718750778517227e-05, 'samples': 25680960, 'steps': 133754, 'loss/train': 0.8535874485969543} 08/31/2021 13:25:39 - INFO - __main__ - Step 133756: {'lr': 1.4716956839992802e-05, 'samples': 25681152, 'steps': 133755, 'loss/train': 0.7178798913955688} 08/31/2021 13:25:39 - INFO - __main__ - Step 133757: {'lr': 1.4715163007483295e-05, 'samples': 25681344, 'steps': 133756, 'loss/train': 0.5984070301055908} 08/31/2021 13:25:41 - INFO - __main__ - Step 133758: {'lr': 1.4713369280989513e-05, 'samples': 25681536, 'steps': 133757, 'loss/train': 0.5639480948448181} 08/31/2021 13:25:42 - INFO - __main__ - Step 133759: {'lr': 1.4711575660512233e-05, 'samples': 25681728, 'steps': 133758, 'loss/train': 0.28335821628570557} 08/31/2021 13:25:42 - INFO - __main__ - Step 133760: {'lr': 1.4709782146052314e-05, 'samples': 25681920, 'steps': 133759, 'loss/train': 1.0333820581436157} 08/31/2021 13:25:42 - INFO - __main__ - Step 133761: {'lr': 1.4707988737610506e-05, 'samples': 25682112, 'steps': 133760, 'loss/train': 1.03218412399292} 08/31/2021 13:25:43 - INFO - __main__ - Step 133762: {'lr': 1.4706195435187669e-05, 'samples': 25682304, 'steps': 133761, 'loss/train': 1.026646375656128} 08/31/2021 13:25:44 - INFO - __main__ - Step 133763: {'lr': 1.4704402238784581e-05, 'samples': 25682496, 'steps': 133762, 'loss/train': 1.0831375122070312} 08/31/2021 13:25:45 - INFO - __main__ - Step 133764: {'lr': 1.4702609148402102e-05, 'samples': 25682688, 'steps': 133763, 'loss/train': 0.5944473743438721} 08/31/2021 13:25:45 - INFO - __main__ - Step 133765: {'lr': 1.4700816164040982e-05, 'samples': 25682880, 'steps': 133764, 'loss/train': 0.31155136227607727} 08/31/2021 13:25:46 - INFO - __main__ - Step 133766: {'lr': 1.4699023285701996e-05, 'samples': 25683072, 'steps': 133765, 'loss/train': 0.5607770681381226} 08/31/2021 13:25:46 - INFO - __main__ - Step 133767: {'lr': 1.4697230513386033e-05, 'samples': 25683264, 'steps': 133766, 'loss/train': 0.2801413834095001} 08/31/2021 13:25:46 - INFO - __main__ - Step 133768: {'lr': 1.4695437847093845e-05, 'samples': 25683456, 'steps': 133767, 'loss/train': 1.1908578872680664} 08/31/2021 13:25:48 - INFO - __main__ - Step 133769: {'lr': 1.469364528682629e-05, 'samples': 25683648, 'steps': 133768, 'loss/train': 6.242255687713623} 08/31/2021 13:25:48 - INFO - __main__ - Step 133770: {'lr': 1.4691852832584118e-05, 'samples': 25683840, 'steps': 133769, 'loss/train': 0.8352270126342773} 08/31/2021 13:25:49 - INFO - __main__ - Step 133771: {'lr': 1.469006048436819e-05, 'samples': 25684032, 'steps': 133770, 'loss/train': 1.1234400272369385} 08/31/2021 13:25:49 - INFO - __main__ - Step 133772: {'lr': 1.4688268242179282e-05, 'samples': 25684224, 'steps': 133771, 'loss/train': 0.3384072780609131} 08/31/2021 13:25:49 - INFO - __main__ - Step 133773: {'lr': 1.4686476106018198e-05, 'samples': 25684416, 'steps': 133772, 'loss/train': 0.8124551177024841} 08/31/2021 13:25:51 - INFO - __main__ - Step 133774: {'lr': 1.4684684075885773e-05, 'samples': 25684608, 'steps': 133773, 'loss/train': 0.3760450482368469} 08/31/2021 13:25:51 - INFO - __main__ - Step 133775: {'lr': 1.4682892151782811e-05, 'samples': 25684800, 'steps': 133774, 'loss/train': 1.078417420387268} 08/31/2021 13:25:52 - INFO - __main__ - Step 133776: {'lr': 1.468110033371009e-05, 'samples': 25684992, 'steps': 133775, 'loss/train': 1.1109963655471802} 08/31/2021 13:25:52 - INFO - __main__ - Step 133777: {'lr': 1.4679308621668441e-05, 'samples': 25685184, 'steps': 133776, 'loss/train': 0.9525126814842224} 08/31/2021 13:25:52 - INFO - __main__ - Step 133778: {'lr': 1.4677517015658642e-05, 'samples': 25685376, 'steps': 133777, 'loss/train': 1.5444153547286987} 08/31/2021 13:25:54 - INFO - __main__ - Step 133779: {'lr': 1.4675725515681526e-05, 'samples': 25685568, 'steps': 133778, 'loss/train': 1.2218371629714966} 08/31/2021 13:25:54 - INFO - __main__ - Step 133780: {'lr': 1.4673934121737925e-05, 'samples': 25685760, 'steps': 133779, 'loss/train': 0.11520854383707047} 08/31/2021 13:25:55 - INFO - __main__ - Step 133781: {'lr': 1.467214283382859e-05, 'samples': 25685952, 'steps': 133780, 'loss/train': 1.0239462852478027} 08/31/2021 13:25:55 - INFO - __main__ - Step 133782: {'lr': 1.467035165195435e-05, 'samples': 25686144, 'steps': 133781, 'loss/train': 1.0161083936691284} 08/31/2021 13:25:55 - INFO - __main__ - Step 133783: {'lr': 1.4668560576116042e-05, 'samples': 25686336, 'steps': 133782, 'loss/train': 0.9686822891235352} 08/31/2021 13:25:56 - INFO - __main__ - Step 133784: {'lr': 1.4666769606314439e-05, 'samples': 25686528, 'steps': 133783, 'loss/train': 1.2115949392318726} 08/31/2021 13:25:57 - INFO - __main__ - Step 133785: {'lr': 1.466497874255035e-05, 'samples': 25686720, 'steps': 133784, 'loss/train': 0.9367055296897888} 08/31/2021 13:25:58 - INFO - __main__ - Step 133786: {'lr': 1.4663187984824633e-05, 'samples': 25686912, 'steps': 133785, 'loss/train': 1.0710437297821045} 08/31/2021 13:25:58 - INFO - __main__ - Step 133787: {'lr': 1.466139733313801e-05, 'samples': 25687104, 'steps': 133786, 'loss/train': 1.2186928987503052} 08/31/2021 13:25:58 - INFO - __main__ - Step 133788: {'lr': 1.4659606787491341e-05, 'samples': 25687296, 'steps': 133787, 'loss/train': 0.03834880515933037} 08/31/2021 13:25:59 - INFO - __main__ - Step 133789: {'lr': 1.4657816347885433e-05, 'samples': 25687488, 'steps': 133788, 'loss/train': 1.3457728624343872} 08/31/2021 13:26:00 - INFO - __main__ - Step 133790: {'lr': 1.4656026014321062e-05, 'samples': 25687680, 'steps': 133789, 'loss/train': 0.915091872215271} 08/31/2021 13:26:01 - INFO - __main__ - Step 133791: {'lr': 1.4654235786799059e-05, 'samples': 25687872, 'steps': 133790, 'loss/train': 0.9740999341011047} 08/31/2021 13:26:01 - INFO - __main__ - Step 133792: {'lr': 1.465244566532023e-05, 'samples': 25688064, 'steps': 133791, 'loss/train': 1.7368662357330322} 08/31/2021 13:26:02 - INFO - __main__ - Step 133793: {'lr': 1.4650655649885353e-05, 'samples': 25688256, 'steps': 133792, 'loss/train': 0.7962510585784912} 08/31/2021 13:26:02 - INFO - __main__ - Step 133794: {'lr': 1.4648865740495287e-05, 'samples': 25688448, 'steps': 133793, 'loss/train': 0.848756730556488} 08/31/2021 13:26:03 - INFO - __main__ - Step 133795: {'lr': 1.4647075937150811e-05, 'samples': 25688640, 'steps': 133794, 'loss/train': 1.07673978805542} 08/31/2021 13:26:04 - INFO - __main__ - Step 133796: {'lr': 1.46452862398527e-05, 'samples': 25688832, 'steps': 133795, 'loss/train': 0.8274459838867188} 08/31/2021 13:26:04 - INFO - __main__ - Step 133797: {'lr': 1.4643496648601873e-05, 'samples': 25689024, 'steps': 133796, 'loss/train': 1.503578782081604} 08/31/2021 13:26:04 - INFO - __main__ - Step 133798: {'lr': 1.4641707163398993e-05, 'samples': 25689216, 'steps': 133797, 'loss/train': 0.49059155583381653} 08/31/2021 13:26:05 - INFO - __main__ - Step 133799: {'lr': 1.463991778424492e-05, 'samples': 25689408, 'steps': 133798, 'loss/train': 0.5916198492050171} 08/31/2021 13:26:07 - INFO - __main__ - Step 133800: {'lr': 1.4638128511140465e-05, 'samples': 25689600, 'steps': 133799, 'loss/train': 1.4703295230865479} 08/31/2021 13:26:07 - INFO - __main__ - Step 133801: {'lr': 1.4636339344086453e-05, 'samples': 25689792, 'steps': 133800, 'loss/train': 1.3162026405334473} 08/31/2021 13:26:08 - INFO - __main__ - Step 133802: {'lr': 1.4634550283083665e-05, 'samples': 25689984, 'steps': 133801, 'loss/train': 1.0435508489608765} 08/31/2021 13:26:08 - INFO - __main__ - Step 133803: {'lr': 1.4632761328132932e-05, 'samples': 25690176, 'steps': 133802, 'loss/train': 0.3366127610206604} 08/31/2021 13:26:09 - INFO - __main__ - Step 133804: {'lr': 1.4630972479235032e-05, 'samples': 25690368, 'steps': 133803, 'loss/train': 1.1229010820388794} 08/31/2021 13:26:09 - INFO - __main__ - Step 133805: {'lr': 1.46291837363908e-05, 'samples': 25690560, 'steps': 133804, 'loss/train': 1.257763385772705} 08/31/2021 13:26:11 - INFO - __main__ - Step 133806: {'lr': 1.462739509960101e-05, 'samples': 25690752, 'steps': 133805, 'loss/train': 1.137481689453125} 08/31/2021 13:26:11 - INFO - __main__ - Step 133807: {'lr': 1.4625606568866495e-05, 'samples': 25690944, 'steps': 133806, 'loss/train': 0.6122399568557739} 08/31/2021 13:26:11 - INFO - __main__ - Step 133808: {'lr': 1.4623818144188062e-05, 'samples': 25691136, 'steps': 133807, 'loss/train': 1.5644736289978027} 08/31/2021 13:26:12 - INFO - __main__ - Step 133809: {'lr': 1.4622029825566485e-05, 'samples': 25691328, 'steps': 133808, 'loss/train': 1.599181056022644} 08/31/2021 13:26:12 - INFO - __main__ - Step 133810: {'lr': 1.4620241613002599e-05, 'samples': 25691520, 'steps': 133809, 'loss/train': 0.77004075050354} 08/31/2021 13:26:12 - INFO - __main__ - Step 133811: {'lr': 1.4618453506497182e-05, 'samples': 25691712, 'steps': 133810, 'loss/train': 0.37908610701560974} 08/31/2021 13:26:14 - INFO - __main__ - Step 133812: {'lr': 1.4616665506051064e-05, 'samples': 25691904, 'steps': 133811, 'loss/train': 1.145087718963623} 08/31/2021 13:26:14 - INFO - __main__ - Step 133813: {'lr': 1.4614877611665051e-05, 'samples': 25692096, 'steps': 133812, 'loss/train': 1.383881688117981} 08/31/2021 13:26:15 - INFO - __main__ - Step 133814: {'lr': 1.4613089823339947e-05, 'samples': 25692288, 'steps': 133813, 'loss/train': 1.7503759860992432} 08/31/2021 13:26:15 - INFO - __main__ - Step 133815: {'lr': 1.4611302141076533e-05, 'samples': 25692480, 'steps': 133814, 'loss/train': 0.8972203135490417} 08/31/2021 13:26:16 - INFO - __main__ - Step 133816: {'lr': 1.4609514564875637e-05, 'samples': 25692672, 'steps': 133815, 'loss/train': 0.11408060044050217} 08/31/2021 13:26:18 - INFO - __main__ - Step 133817: {'lr': 1.4607727094738067e-05, 'samples': 25692864, 'steps': 133816, 'loss/train': 1.3396117687225342} 08/31/2021 13:26:18 - INFO - __main__ - Step 133818: {'lr': 1.4605939730664625e-05, 'samples': 25693056, 'steps': 133817, 'loss/train': 0.3756476640701294} 08/31/2021 13:26:19 - INFO - __main__ - Step 133819: {'lr': 1.4604152472656118e-05, 'samples': 25693248, 'steps': 133818, 'loss/train': 0.2976696789264679} 08/31/2021 13:26:19 - INFO - __main__ - Step 133820: {'lr': 1.460236532071335e-05, 'samples': 25693440, 'steps': 133819, 'loss/train': 0.8844327330589294} 08/31/2021 13:26:19 - INFO - __main__ - Step 133821: {'lr': 1.4600578274837128e-05, 'samples': 25693632, 'steps': 133820, 'loss/train': 0.03330213949084282} 08/31/2021 13:26:21 - INFO - __main__ - Step 133822: {'lr': 1.4598791335028255e-05, 'samples': 25693824, 'steps': 133821, 'loss/train': 0.5651299953460693} 08/31/2021 13:26:21 - INFO - __main__ - Step 133823: {'lr': 1.4597004501287509e-05, 'samples': 25694016, 'steps': 133822, 'loss/train': 1.4217456579208374} 08/31/2021 13:26:22 - INFO - __main__ - Step 133824: {'lr': 1.4595217773615749e-05, 'samples': 25694208, 'steps': 133823, 'loss/train': 0.7049552798271179} 08/31/2021 13:26:22 - INFO - __main__ - Step 133825: {'lr': 1.4593431152013725e-05, 'samples': 25694400, 'steps': 133824, 'loss/train': 0.9391055107116699} 08/31/2021 13:26:22 - INFO - __main__ - Step 133826: {'lr': 1.459164463648227e-05, 'samples': 25694592, 'steps': 133825, 'loss/train': 1.624624252319336} 08/31/2021 13:26:24 - INFO - __main__ - Step 133827: {'lr': 1.458985822702219e-05, 'samples': 25694784, 'steps': 133826, 'loss/train': 0.5601223707199097} 08/31/2021 13:26:24 - INFO - __main__ - Step 133828: {'lr': 1.4588071923634317e-05, 'samples': 25694976, 'steps': 133827, 'loss/train': 1.0728837251663208} 08/31/2021 13:26:25 - INFO - __main__ - Step 133829: {'lr': 1.4586285726319399e-05, 'samples': 25695168, 'steps': 133828, 'loss/train': 0.4636390507221222} 08/31/2021 13:26:25 - INFO - __main__ - Step 133830: {'lr': 1.458449963507827e-05, 'samples': 25695360, 'steps': 133829, 'loss/train': 1.0166599750518799} 08/31/2021 13:26:25 - INFO - __main__ - Step 133831: {'lr': 1.4582713649911734e-05, 'samples': 25695552, 'steps': 133830, 'loss/train': 1.0318344831466675} 08/31/2021 13:26:27 - INFO - __main__ - Step 133832: {'lr': 1.4580927770820568e-05, 'samples': 25695744, 'steps': 133831, 'loss/train': 0.8202124238014221} 08/31/2021 13:26:27 - INFO - __main__ - Step 133833: {'lr': 1.4579141997805635e-05, 'samples': 25695936, 'steps': 133832, 'loss/train': 0.9103860855102539} 08/31/2021 13:26:28 - INFO - __main__ - Step 133834: {'lr': 1.4577356330867735e-05, 'samples': 25696128, 'steps': 133833, 'loss/train': 0.7689291834831238} 08/31/2021 13:26:28 - INFO - __main__ - Step 133835: {'lr': 1.4575570770007623e-05, 'samples': 25696320, 'steps': 133834, 'loss/train': 1.0112255811691284} 08/31/2021 13:26:28 - INFO - __main__ - Step 133836: {'lr': 1.4573785315226101e-05, 'samples': 25696512, 'steps': 133835, 'loss/train': 0.8651677966117859} 08/31/2021 13:26:30 - INFO - __main__ - Step 133837: {'lr': 1.457199996652403e-05, 'samples': 25696704, 'steps': 133836, 'loss/train': 1.0573848485946655} 08/31/2021 13:26:30 - INFO - __main__ - Step 133838: {'lr': 1.457021472390216e-05, 'samples': 25696896, 'steps': 133837, 'loss/train': 1.0646995306015015} 08/31/2021 13:26:31 - INFO - __main__ - Step 133839: {'lr': 1.456842958736132e-05, 'samples': 25697088, 'steps': 133838, 'loss/train': 1.5651183128356934} 08/31/2021 13:26:31 - INFO - __main__ - Step 133840: {'lr': 1.456664455690232e-05, 'samples': 25697280, 'steps': 133839, 'loss/train': 0.9016221761703491} 08/31/2021 13:26:32 - INFO - __main__ - Step 133841: {'lr': 1.4564859632525961e-05, 'samples': 25697472, 'steps': 133840, 'loss/train': 0.6812661290168762} 08/31/2021 13:26:32 - INFO - __main__ - Step 133842: {'lr': 1.4563074814233025e-05, 'samples': 25697664, 'steps': 133841, 'loss/train': 0.2878810465335846} 08/31/2021 13:26:33 - INFO - __main__ - Step 133843: {'lr': 1.4561290102024337e-05, 'samples': 25697856, 'steps': 133842, 'loss/train': 0.6159115433692932} 08/31/2021 13:26:34 - INFO - __main__ - Step 133844: {'lr': 1.455950549590071e-05, 'samples': 25698048, 'steps': 133843, 'loss/train': 0.5344672203063965} 08/31/2021 13:26:34 - INFO - __main__ - Step 133845: {'lr': 1.4557720995862944e-05, 'samples': 25698240, 'steps': 133844, 'loss/train': 0.025209661573171616} 08/31/2021 13:26:35 - INFO - __main__ - Step 133846: {'lr': 1.4555936601911818e-05, 'samples': 25698432, 'steps': 133845, 'loss/train': 1.3438514471054077} 08/31/2021 13:26:35 - INFO - __main__ - Step 133847: {'lr': 1.4554152314048164e-05, 'samples': 25698624, 'steps': 133846, 'loss/train': 0.30501314997673035} 08/31/2021 13:26:36 - INFO - __main__ - Step 133848: {'lr': 1.4552368132272815e-05, 'samples': 25698816, 'steps': 133847, 'loss/train': 1.7272138595581055} 08/31/2021 13:26:37 - INFO - __main__ - Step 133849: {'lr': 1.455058405658649e-05, 'samples': 25699008, 'steps': 133848, 'loss/train': 0.719954252243042} 08/31/2021 13:26:37 - INFO - __main__ - Step 133850: {'lr': 1.4548800086990027e-05, 'samples': 25699200, 'steps': 133849, 'loss/train': 1.0516667366027832} 08/31/2021 13:26:38 - INFO - __main__ - Step 133851: {'lr': 1.4547016223484255e-05, 'samples': 25699392, 'steps': 133850, 'loss/train': 1.3319299221038818} 08/31/2021 13:26:38 - INFO - __main__ - Step 133852: {'lr': 1.454523246606998e-05, 'samples': 25699584, 'steps': 133851, 'loss/train': 0.38303452730178833} 08/31/2021 13:26:40 - INFO - __main__ - Step 133853: {'lr': 1.4543448814747978e-05, 'samples': 25699776, 'steps': 133852, 'loss/train': 1.2797008752822876} 08/31/2021 13:26:40 - INFO - __main__ - Step 133854: {'lr': 1.4541665269519056e-05, 'samples': 25699968, 'steps': 133853, 'loss/train': 1.2093976736068726} 08/31/2021 13:26:41 - INFO - __main__ - Step 133855: {'lr': 1.4539881830384045e-05, 'samples': 25700160, 'steps': 133854, 'loss/train': 1.4037457704544067} 08/31/2021 13:26:41 - INFO - __main__ - Step 133856: {'lr': 1.4538098497343694e-05, 'samples': 25700352, 'steps': 133855, 'loss/train': 1.25920832157135} 08/31/2021 13:26:41 - INFO - __main__ - Step 133857: {'lr': 1.4536315270398864e-05, 'samples': 25700544, 'steps': 133856, 'loss/train': 0.6960939764976501} 08/31/2021 13:26:43 - INFO - __main__ - Step 133858: {'lr': 1.453453214955036e-05, 'samples': 25700736, 'steps': 133857, 'loss/train': 1.5384488105773926} 08/31/2021 13:26:43 - INFO - __main__ - Step 133859: {'lr': 1.4532749134798934e-05, 'samples': 25700928, 'steps': 133858, 'loss/train': 0.3720972537994385} 08/31/2021 13:26:44 - INFO - __main__ - Step 133860: {'lr': 1.4530966226145414e-05, 'samples': 25701120, 'steps': 133859, 'loss/train': 1.3932762145996094} 08/31/2021 13:26:44 - INFO - __main__ - Step 133861: {'lr': 1.4529183423590663e-05, 'samples': 25701312, 'steps': 133860, 'loss/train': 1.1282538175582886} 08/31/2021 13:26:44 - INFO - __main__ - Step 133862: {'lr': 1.4527400727135375e-05, 'samples': 25701504, 'steps': 133861, 'loss/train': 0.7890235781669617} 08/31/2021 13:26:45 - INFO - __main__ - Step 133863: {'lr': 1.4525618136780411e-05, 'samples': 25701696, 'steps': 133862, 'loss/train': 0.6080608367919922} 08/31/2021 13:26:46 - INFO - __main__ - Step 133864: {'lr': 1.4523835652526602e-05, 'samples': 25701888, 'steps': 133863, 'loss/train': 1.1164313554763794} 08/31/2021 13:26:47 - INFO - __main__ - Step 133865: {'lr': 1.4522053274374669e-05, 'samples': 25702080, 'steps': 133864, 'loss/train': 0.975724458694458} 08/31/2021 13:26:47 - INFO - __main__ - Step 133866: {'lr': 1.4520271002325503e-05, 'samples': 25702272, 'steps': 133865, 'loss/train': 0.8340816497802734} 08/31/2021 13:26:48 - INFO - __main__ - Step 133867: {'lr': 1.451848883637985e-05, 'samples': 25702464, 'steps': 133866, 'loss/train': 1.4741219282150269} 08/31/2021 13:26:48 - INFO - __main__ - Step 133868: {'lr': 1.451670677653852e-05, 'samples': 25702656, 'steps': 133867, 'loss/train': 0.7119646668434143} 08/31/2021 13:26:50 - INFO - __main__ - Step 133869: {'lr': 1.4514924822802367e-05, 'samples': 25702848, 'steps': 133868, 'loss/train': 1.0479552745819092} 08/31/2021 13:26:51 - INFO - __main__ - Step 133870: {'lr': 1.4513142975172117e-05, 'samples': 25703040, 'steps': 133869, 'loss/train': 0.9054616689682007} 08/31/2021 13:26:51 - INFO - __main__ - Step 133871: {'lr': 1.4511361233648629e-05, 'samples': 25703232, 'steps': 133870, 'loss/train': 0.049875617027282715} 08/31/2021 13:26:51 - INFO - __main__ - Step 133872: {'lr': 1.450957959823268e-05, 'samples': 25703424, 'steps': 133871, 'loss/train': 1.3100056648254395} 08/31/2021 13:26:52 - INFO - __main__ - Step 133873: {'lr': 1.4507798068925076e-05, 'samples': 25703616, 'steps': 133872, 'loss/train': 1.2059276103973389} 08/31/2021 13:26:53 - INFO - __main__ - Step 133874: {'lr': 1.450601664572665e-05, 'samples': 25703808, 'steps': 133873, 'loss/train': 0.9334031343460083} 08/31/2021 13:26:54 - INFO - __main__ - Step 133875: {'lr': 1.4504235328638204e-05, 'samples': 25704000, 'steps': 133874, 'loss/train': 1.1990234851837158} 08/31/2021 13:26:54 - INFO - __main__ - Step 133876: {'lr': 1.4502454117660464e-05, 'samples': 25704192, 'steps': 133875, 'loss/train': 1.4587029218673706} 08/31/2021 13:26:54 - INFO - __main__ - Step 133877: {'lr': 1.4500673012794285e-05, 'samples': 25704384, 'steps': 133876, 'loss/train': 0.9098203778266907} 08/31/2021 13:26:55 - INFO - __main__ - Step 133878: {'lr': 1.4498892014040477e-05, 'samples': 25704576, 'steps': 133877, 'loss/train': 0.7168487310409546} 08/31/2021 13:26:56 - INFO - __main__ - Step 133879: {'lr': 1.4497111121399842e-05, 'samples': 25704768, 'steps': 133878, 'loss/train': 1.0969079732894897} 08/31/2021 13:26:57 - INFO - __main__ - Step 133880: {'lr': 1.4495330334873185e-05, 'samples': 25704960, 'steps': 133879, 'loss/train': 0.03138911724090576} 08/31/2021 13:26:57 - INFO - __main__ - Step 133881: {'lr': 1.4493549654461257e-05, 'samples': 25705152, 'steps': 133880, 'loss/train': 1.385289192199707} 08/31/2021 13:26:58 - INFO - __main__ - Step 133882: {'lr': 1.4491769080164946e-05, 'samples': 25705344, 'steps': 133881, 'loss/train': 1.2323521375656128} 08/31/2021 13:26:58 - INFO - __main__ - Step 133883: {'lr': 1.4489988611984973e-05, 'samples': 25705536, 'steps': 133882, 'loss/train': 0.9949129223823547} 08/31/2021 13:26:58 - INFO - __main__ - Step 133884: {'lr': 1.4488208249922197e-05, 'samples': 25705728, 'steps': 133883, 'loss/train': 1.5171540975570679} 08/31/2021 13:27:00 - INFO - __main__ - Step 133885: {'lr': 1.4486427993977397e-05, 'samples': 25705920, 'steps': 133884, 'loss/train': 0.2894859313964844} 08/31/2021 13:27:00 - INFO - __main__ - Step 133886: {'lr': 1.4484647844151377e-05, 'samples': 25706112, 'steps': 133885, 'loss/train': 1.0293354988098145} 08/31/2021 13:27:00 - INFO - __main__ - Step 133887: {'lr': 1.4482867800444944e-05, 'samples': 25706304, 'steps': 133886, 'loss/train': 0.7399027943611145} 08/31/2021 13:27:01 - INFO - __main__ - Step 133888: {'lr': 1.4481087862858927e-05, 'samples': 25706496, 'steps': 133887, 'loss/train': 0.9190332889556885} 08/31/2021 13:27:01 - INFO - __main__ - Step 133889: {'lr': 1.4479308031394079e-05, 'samples': 25706688, 'steps': 133888, 'loss/train': 1.2081636190414429} 08/31/2021 13:27:03 - INFO - __main__ - Step 133890: {'lr': 1.4477528306051201e-05, 'samples': 25706880, 'steps': 133889, 'loss/train': 0.836489200592041} 08/31/2021 13:27:03 - INFO - __main__ - Step 133891: {'lr': 1.447574868683113e-05, 'samples': 25707072, 'steps': 133890, 'loss/train': 0.09502846002578735} 08/31/2021 13:27:04 - INFO - __main__ - Step 133892: {'lr': 1.447396917373464e-05, 'samples': 25707264, 'steps': 133891, 'loss/train': 1.4192264080047607} 08/31/2021 13:27:04 - INFO - __main__ - Step 133893: {'lr': 1.4472189766762538e-05, 'samples': 25707456, 'steps': 133892, 'loss/train': 0.7112581729888916} 08/31/2021 13:27:04 - INFO - __main__ - Step 133894: {'lr': 1.447041046591563e-05, 'samples': 25707648, 'steps': 133893, 'loss/train': 0.03521667793393135} 08/31/2021 13:27:06 - INFO - __main__ - Step 133895: {'lr': 1.4468631271194742e-05, 'samples': 25707840, 'steps': 133894, 'loss/train': 1.1194809675216675} 08/31/2021 13:27:06 - INFO - __main__ - Step 133896: {'lr': 1.446685218260066e-05, 'samples': 25708032, 'steps': 133895, 'loss/train': 0.1714014708995819} 08/31/2021 13:27:07 - INFO - __main__ - Step 133897: {'lr': 1.4465073200134154e-05, 'samples': 25708224, 'steps': 133896, 'loss/train': 1.0605838298797607} 08/31/2021 13:27:07 - INFO - __main__ - Step 133898: {'lr': 1.4463294323796062e-05, 'samples': 25708416, 'steps': 133897, 'loss/train': 0.24497562646865845} 08/31/2021 13:27:07 - INFO - __main__ - Step 133899: {'lr': 1.4461515553587185e-05, 'samples': 25708608, 'steps': 133898, 'loss/train': 0.255725234746933} 08/31/2021 13:27:09 - INFO - __main__ - Step 133900: {'lr': 1.4459736889508302e-05, 'samples': 25708800, 'steps': 133899, 'loss/train': 1.2468633651733398} 08/31/2021 13:27:09 - INFO - __main__ - Step 133901: {'lr': 1.4457958331560245e-05, 'samples': 25708992, 'steps': 133900, 'loss/train': 1.1589902639389038} 08/31/2021 13:27:10 - INFO - __main__ - Step 133902: {'lr': 1.445617987974379e-05, 'samples': 25709184, 'steps': 133901, 'loss/train': 1.6826034784317017} 08/31/2021 13:27:10 - INFO - __main__ - Step 133903: {'lr': 1.4454401534059746e-05, 'samples': 25709376, 'steps': 133902, 'loss/train': 0.8087226152420044} 08/31/2021 13:27:10 - INFO - __main__ - Step 133904: {'lr': 1.4452623294508888e-05, 'samples': 25709568, 'steps': 133903, 'loss/train': 1.1301268339157104} 08/31/2021 13:27:12 - INFO - __main__ - Step 133905: {'lr': 1.4450845161092074e-05, 'samples': 25709760, 'steps': 133904, 'loss/train': 1.0848108530044556} 08/31/2021 13:27:12 - INFO - __main__ - Step 133906: {'lr': 1.4449067133810057e-05, 'samples': 25709952, 'steps': 133905, 'loss/train': 1.0648152828216553} 08/31/2021 13:27:13 - INFO - __main__ - Step 133907: {'lr': 1.4447289212663667e-05, 'samples': 25710144, 'steps': 133906, 'loss/train': 1.490342378616333} 08/31/2021 13:27:13 - INFO - __main__ - Step 133908: {'lr': 1.4445511397653682e-05, 'samples': 25710336, 'steps': 133907, 'loss/train': 1.9067281484603882} 08/31/2021 13:27:13 - INFO - __main__ - Step 133909: {'lr': 1.4443733688780908e-05, 'samples': 25710528, 'steps': 133908, 'loss/train': 1.2796932458877563} 08/31/2021 13:27:14 - INFO - __main__ - Step 133910: {'lr': 1.4441956086046177e-05, 'samples': 25710720, 'steps': 133909, 'loss/train': 2.0548593997955322} 08/31/2021 13:27:15 - INFO - __main__ - Step 133911: {'lr': 1.4440178589450237e-05, 'samples': 25710912, 'steps': 133910, 'loss/train': 0.6977881193161011} 08/31/2021 13:27:16 - INFO - __main__ - Step 133912: {'lr': 1.443840119899395e-05, 'samples': 25711104, 'steps': 133911, 'loss/train': 1.940940260887146} 08/31/2021 13:27:16 - INFO - __main__ - Step 133913: {'lr': 1.4436623914678065e-05, 'samples': 25711296, 'steps': 133912, 'loss/train': 0.4772181808948517} 08/31/2021 13:27:16 - INFO - __main__ - Step 133914: {'lr': 1.4434846736503415e-05, 'samples': 25711488, 'steps': 133913, 'loss/train': 1.155395269393921} 08/31/2021 13:27:17 - INFO - __main__ - Step 133915: {'lr': 1.4433069664470805e-05, 'samples': 25711680, 'steps': 133914, 'loss/train': 0.019519057124853134} 08/31/2021 13:27:18 - INFO - __main__ - Step 133916: {'lr': 1.4431292698580984e-05, 'samples': 25711872, 'steps': 133915, 'loss/train': 0.4530227482318878} 08/31/2021 13:27:19 - INFO - __main__ - Step 133917: {'lr': 1.442951583883481e-05, 'samples': 25712064, 'steps': 133916, 'loss/train': 1.397700548171997} 08/31/2021 13:27:19 - INFO - __main__ - Step 133918: {'lr': 1.4427739085233038e-05, 'samples': 25712256, 'steps': 133917, 'loss/train': 0.9209086894989014} 08/31/2021 13:27:19 - INFO - __main__ - Step 133919: {'lr': 1.4425962437776497e-05, 'samples': 25712448, 'steps': 133918, 'loss/train': 1.3910001516342163} 08/31/2021 13:27:20 - INFO - __main__ - Step 133920: {'lr': 1.442418589646599e-05, 'samples': 25712640, 'steps': 133919, 'loss/train': 1.5056121349334717} 08/31/2021 13:27:22 - INFO - __main__ - Step 133921: {'lr': 1.4422409461302299e-05, 'samples': 25712832, 'steps': 133920, 'loss/train': 1.1223440170288086} 08/31/2021 13:27:23 - INFO - __main__ - Step 133922: {'lr': 1.4420633132286254e-05, 'samples': 25713024, 'steps': 133921, 'loss/train': 1.4742071628570557} 08/31/2021 13:27:23 - INFO - __main__ - Step 133923: {'lr': 1.4418856909418604e-05, 'samples': 25713216, 'steps': 133922, 'loss/train': 0.5604012608528137} 08/31/2021 13:27:23 - INFO - __main__ - Step 133924: {'lr': 1.441708079270021e-05, 'samples': 25713408, 'steps': 133923, 'loss/train': 3.0126590728759766} 08/31/2021 13:27:24 - INFO - __main__ - Step 133925: {'lr': 1.441530478213185e-05, 'samples': 25713600, 'steps': 133924, 'loss/train': 0.3043610155582428} 08/31/2021 13:27:24 - INFO - __main__ - Step 133926: {'lr': 1.4413528877714298e-05, 'samples': 25713792, 'steps': 133925, 'loss/train': 0.5927107930183411} 08/31/2021 13:27:26 - INFO - __main__ - Step 133927: {'lr': 1.4411753079448365e-05, 'samples': 25713984, 'steps': 133926, 'loss/train': 1.065164566040039} 08/31/2021 13:27:27 - INFO - __main__ - Step 133928: {'lr': 1.4409977387334932e-05, 'samples': 25714176, 'steps': 133927, 'loss/train': 0.03962339460849762} 08/31/2021 13:27:27 - INFO - __main__ - Step 133929: {'lr': 1.4408201801374671e-05, 'samples': 25714368, 'steps': 133928, 'loss/train': 1.3032842874526978} 08/31/2021 13:27:28 - INFO - __main__ - Step 133930: {'lr': 1.440642632156844e-05, 'samples': 25714560, 'steps': 133929, 'loss/train': 1.1249518394470215} 08/31/2021 13:27:28 - INFO - __main__ - Step 133931: {'lr': 1.4404650947917042e-05, 'samples': 25714752, 'steps': 133930, 'loss/train': 1.29035484790802} 08/31/2021 13:27:30 - INFO - __main__ - Step 133932: {'lr': 1.4402875680421257e-05, 'samples': 25714944, 'steps': 133931, 'loss/train': 0.3861016035079956} 08/31/2021 13:27:30 - INFO - __main__ - Step 133933: {'lr': 1.4401100519081917e-05, 'samples': 25715136, 'steps': 133932, 'loss/train': 1.0893144607543945} 08/31/2021 13:27:30 - INFO - __main__ - Step 133934: {'lr': 1.4399325463899799e-05, 'samples': 25715328, 'steps': 133933, 'loss/train': 1.0018150806427002} 08/31/2021 13:27:31 - INFO - __main__ - Step 133935: {'lr': 1.4397550514875707e-05, 'samples': 25715520, 'steps': 133934, 'loss/train': 1.6110875606536865} 08/31/2021 13:27:31 - INFO - __main__ - Step 133936: {'lr': 1.4395775672010447e-05, 'samples': 25715712, 'steps': 133935, 'loss/train': 5.711424350738525} 08/31/2021 13:27:31 - INFO - __main__ - Step 133937: {'lr': 1.4394000935304824e-05, 'samples': 25715904, 'steps': 133936, 'loss/train': 1.477947473526001} 08/31/2021 13:27:33 - INFO - __main__ - Step 133938: {'lr': 1.4392226304759615e-05, 'samples': 25716096, 'steps': 133937, 'loss/train': 0.10255740582942963} 08/31/2021 13:27:34 - INFO - __main__ - Step 133939: {'lr': 1.4390451780375625e-05, 'samples': 25716288, 'steps': 133938, 'loss/train': 1.6300199031829834} 08/31/2021 13:27:34 - INFO - __main__ - Step 133940: {'lr': 1.4388677362153685e-05, 'samples': 25716480, 'steps': 133939, 'loss/train': 0.5945849418640137} 08/31/2021 13:27:34 - INFO - __main__ - Step 133941: {'lr': 1.4386903050094575e-05, 'samples': 25716672, 'steps': 133940, 'loss/train': 1.1669542789459229} 08/31/2021 13:27:35 - INFO - __main__ - Step 133942: {'lr': 1.4385128844199097e-05, 'samples': 25716864, 'steps': 133941, 'loss/train': 1.1605827808380127} 08/31/2021 13:27:36 - INFO - __main__ - Step 133943: {'lr': 1.4383354744468031e-05, 'samples': 25717056, 'steps': 133942, 'loss/train': 0.8980934619903564} 08/31/2021 13:27:36 - INFO - __main__ - Step 133944: {'lr': 1.4381580750902179e-05, 'samples': 25717248, 'steps': 133943, 'loss/train': 1.2838249206542969} 08/31/2021 13:27:37 - INFO - __main__ - Step 133945: {'lr': 1.4379806863502348e-05, 'samples': 25717440, 'steps': 133944, 'loss/train': 1.2141305208206177} 08/31/2021 13:27:37 - INFO - __main__ - Step 133946: {'lr': 1.4378033082269343e-05, 'samples': 25717632, 'steps': 133945, 'loss/train': 0.5347815155982971} 08/31/2021 13:27:38 - INFO - __main__ - Step 133947: {'lr': 1.4376259407203967e-05, 'samples': 25717824, 'steps': 133946, 'loss/train': 0.241819366812706} 08/31/2021 13:27:38 - INFO - __main__ - Step 133948: {'lr': 1.4374485838307027e-05, 'samples': 25718016, 'steps': 133947, 'loss/train': 5.148413181304932} 08/31/2021 13:27:39 - INFO - __main__ - Step 133949: {'lr': 1.4372712375579272e-05, 'samples': 25718208, 'steps': 133948, 'loss/train': 1.42860746383667} 08/31/2021 13:27:40 - INFO - __main__ - Step 133950: {'lr': 1.4370939019021561e-05, 'samples': 25718400, 'steps': 133949, 'loss/train': 1.2170265913009644} 08/31/2021 13:27:40 - INFO - __main__ - Step 133951: {'lr': 1.4369165768634673e-05, 'samples': 25718592, 'steps': 133950, 'loss/train': 1.0800561904907227} 08/31/2021 13:27:41 - INFO - __main__ - Step 133952: {'lr': 1.4367392624419384e-05, 'samples': 25718784, 'steps': 133951, 'loss/train': 0.9843407273292542} 08/31/2021 13:27:41 - INFO - __main__ - Step 133953: {'lr': 1.4365619586376527e-05, 'samples': 25718976, 'steps': 133952, 'loss/train': 1.4110382795333862} 08/31/2021 13:27:42 - INFO - __main__ - Step 133954: {'lr': 1.4363846654506879e-05, 'samples': 25719168, 'steps': 133953, 'loss/train': 0.9605429172515869} 08/31/2021 13:27:43 - INFO - __main__ - Step 133955: {'lr': 1.4362073828811273e-05, 'samples': 25719360, 'steps': 133954, 'loss/train': 1.1775565147399902} 08/31/2021 13:27:43 - INFO - __main__ - Step 133956: {'lr': 1.4360301109290459e-05, 'samples': 25719552, 'steps': 133955, 'loss/train': 1.0575616359710693} 08/31/2021 13:27:44 - INFO - __main__ - Step 133957: {'lr': 1.4358528495945266e-05, 'samples': 25719744, 'steps': 133956, 'loss/train': 0.3116568326950073} 08/31/2021 13:27:44 - INFO - __main__ - Step 133958: {'lr': 1.4356755988776448e-05, 'samples': 25719936, 'steps': 133957, 'loss/train': 1.4318175315856934} 08/31/2021 13:27:45 - INFO - __main__ - Step 133959: {'lr': 1.4354983587784864e-05, 'samples': 25720128, 'steps': 133958, 'loss/train': 1.11808443069458} 08/31/2021 13:27:46 - INFO - __main__ - Step 133960: {'lr': 1.4353211292971292e-05, 'samples': 25720320, 'steps': 133959, 'loss/train': 0.8063327670097351} 08/31/2021 13:27:46 - INFO - __main__ - Step 133961: {'lr': 1.4351439104336534e-05, 'samples': 25720512, 'steps': 133960, 'loss/train': 1.4537502527236938} 08/31/2021 13:27:47 - INFO - __main__ - Step 133962: {'lr': 1.4349667021881369e-05, 'samples': 25720704, 'steps': 133961, 'loss/train': 0.16520880162715912} 08/31/2021 13:27:47 - INFO - __main__ - Step 133963: {'lr': 1.4347895045606602e-05, 'samples': 25720896, 'steps': 133962, 'loss/train': 0.06105928122997284} 08/31/2021 13:27:48 - INFO - __main__ - Step 133964: {'lr': 1.4346123175513037e-05, 'samples': 25721088, 'steps': 133963, 'loss/train': 0.7237550616264343} 08/31/2021 13:27:49 - INFO - __main__ - Step 133965: {'lr': 1.434435141160148e-05, 'samples': 25721280, 'steps': 133964, 'loss/train': 1.0230860710144043} 08/31/2021 13:27:49 - INFO - __main__ - Step 133966: {'lr': 1.434257975387271e-05, 'samples': 25721472, 'steps': 133965, 'loss/train': 0.687899112701416} 08/31/2021 13:27:50 - INFO - __main__ - Step 133967: {'lr': 1.4340808202327555e-05, 'samples': 25721664, 'steps': 133966, 'loss/train': 0.8890346884727478} 08/31/2021 13:27:50 - INFO - __main__ - Step 133968: {'lr': 1.4339036756966766e-05, 'samples': 25721856, 'steps': 133967, 'loss/train': 1.5814716815948486} 08/31/2021 13:27:52 - INFO - __main__ - Step 133969: {'lr': 1.4337265417791234e-05, 'samples': 25722048, 'steps': 133968, 'loss/train': 1.5557900667190552} 08/31/2021 13:27:52 - INFO - __main__ - Step 133970: {'lr': 1.4335494184801651e-05, 'samples': 25722240, 'steps': 133969, 'loss/train': 0.6294816136360168} 08/31/2021 13:27:53 - INFO - __main__ - Step 133971: {'lr': 1.4333723057998876e-05, 'samples': 25722432, 'steps': 133970, 'loss/train': 1.0021278858184814} 08/31/2021 13:27:53 - INFO - __main__ - Step 133972: {'lr': 1.4331952037383662e-05, 'samples': 25722624, 'steps': 133971, 'loss/train': 1.0377628803253174} 08/31/2021 13:27:53 - INFO - __main__ - Step 133973: {'lr': 1.4330181122956838e-05, 'samples': 25722816, 'steps': 133972, 'loss/train': 1.4400898218154907} 08/31/2021 13:27:54 - INFO - __main__ - Step 133974: {'lr': 1.4328410314719209e-05, 'samples': 25723008, 'steps': 133973, 'loss/train': 0.3158864378929138} 08/31/2021 13:27:55 - INFO - __main__ - Step 133975: {'lr': 1.4326639612671554e-05, 'samples': 25723200, 'steps': 133974, 'loss/train': 1.1460660696029663} 08/31/2021 13:27:55 - INFO - __main__ - Step 133976: {'lr': 1.4324869016814679e-05, 'samples': 25723392, 'steps': 133975, 'loss/train': 0.7965340614318848} 08/31/2021 13:27:56 - INFO - __main__ - Step 133977: {'lr': 1.4323098527149386e-05, 'samples': 25723584, 'steps': 133976, 'loss/train': 1.5639325380325317} 08/31/2021 13:27:56 - INFO - __main__ - Step 133978: {'lr': 1.4321328143676454e-05, 'samples': 25723776, 'steps': 133977, 'loss/train': 0.6728888154029846} 08/31/2021 13:27:57 - INFO - __main__ - Step 133979: {'lr': 1.4319557866396715e-05, 'samples': 25723968, 'steps': 133978, 'loss/train': 1.099599003791809} 08/31/2021 13:27:59 - INFO - __main__ - Step 133980: {'lr': 1.4317787695310918e-05, 'samples': 25724160, 'steps': 133979, 'loss/train': 1.4903552532196045} 08/31/2021 13:27:59 - INFO - __main__ - Step 133981: {'lr': 1.4316017630419926e-05, 'samples': 25724352, 'steps': 133980, 'loss/train': 1.3547861576080322} 08/31/2021 13:28:00 - INFO - __main__ - Step 133982: {'lr': 1.4314247671724511e-05, 'samples': 25724544, 'steps': 133981, 'loss/train': 1.7538777589797974} 08/31/2021 13:28:00 - INFO - __main__ - Step 133983: {'lr': 1.4312477819225428e-05, 'samples': 25724736, 'steps': 133982, 'loss/train': 1.9129875898361206} 08/31/2021 13:28:00 - INFO - __main__ - Step 133984: {'lr': 1.4310708072923506e-05, 'samples': 25724928, 'steps': 133983, 'loss/train': 0.8514574766159058} 08/31/2021 13:28:02 - INFO - __main__ - Step 133985: {'lr': 1.4308938432819523e-05, 'samples': 25725120, 'steps': 133984, 'loss/train': 1.2439615726470947} 08/31/2021 13:28:02 - INFO - __main__ - Step 133986: {'lr': 1.430716889891434e-05, 'samples': 25725312, 'steps': 133985, 'loss/train': 0.285548597574234} 08/31/2021 13:28:03 - INFO - __main__ - Step 133987: {'lr': 1.430539947120868e-05, 'samples': 25725504, 'steps': 133986, 'loss/train': 0.5838121771812439} 08/31/2021 13:28:03 - INFO - __main__ - Step 133988: {'lr': 1.4303630149703373e-05, 'samples': 25725696, 'steps': 133987, 'loss/train': 0.9789837598800659} 08/31/2021 13:28:03 - INFO - __main__ - Step 133989: {'lr': 1.4301860934399197e-05, 'samples': 25725888, 'steps': 133988, 'loss/train': 0.18642744421958923} 08/31/2021 13:28:05 - INFO - __main__ - Step 133990: {'lr': 1.4300091825296985e-05, 'samples': 25726080, 'steps': 133989, 'loss/train': 0.8940081000328064} 08/31/2021 13:28:05 - INFO - __main__ - Step 133991: {'lr': 1.4298322822397514e-05, 'samples': 25726272, 'steps': 133990, 'loss/train': 1.992714285850525} 08/31/2021 13:28:06 - INFO - __main__ - Step 133992: {'lr': 1.4296553925701589e-05, 'samples': 25726464, 'steps': 133991, 'loss/train': 1.5958880186080933} 08/31/2021 13:28:06 - INFO - __main__ - Step 133993: {'lr': 1.4294785135209987e-05, 'samples': 25726656, 'steps': 133992, 'loss/train': 1.2651140689849854} 08/31/2021 13:28:06 - INFO - __main__ - Step 133994: {'lr': 1.4293016450923513e-05, 'samples': 25726848, 'steps': 133993, 'loss/train': 1.6079096794128418} 08/31/2021 13:28:08 - INFO - __main__ - Step 133995: {'lr': 1.4291247872843e-05, 'samples': 25727040, 'steps': 133994, 'loss/train': 1.0694379806518555} 08/31/2021 13:28:08 - INFO - __main__ - Step 133996: {'lr': 1.4289479400969224e-05, 'samples': 25727232, 'steps': 133995, 'loss/train': 1.2407829761505127} 08/31/2021 13:28:09 - INFO - __main__ - Step 133997: {'lr': 1.4287711035302936e-05, 'samples': 25727424, 'steps': 133996, 'loss/train': 0.9682730436325073} 08/31/2021 13:28:09 - INFO - __main__ - Step 133998: {'lr': 1.4285942775844968e-05, 'samples': 25727616, 'steps': 133997, 'loss/train': 1.2827622890472412} 08/31/2021 13:28:09 - INFO - __main__ - Step 133999: {'lr': 1.4284174622596125e-05, 'samples': 25727808, 'steps': 133998, 'loss/train': 1.0694972276687622} 08/31/2021 13:28:11 - INFO - __main__ - Step 134000: {'lr': 1.4282406575557184e-05, 'samples': 25728000, 'steps': 133999, 'loss/train': 1.1499154567718506} 08/31/2021 13:28:12 - INFO - __main__ - Step 134001: {'lr': 1.428063863472895e-05, 'samples': 25728192, 'steps': 134000, 'loss/train': 1.346893072128296} 08/31/2021 13:28:12 - INFO - __main__ - Step 134002: {'lr': 1.4278870800112226e-05, 'samples': 25728384, 'steps': 134001, 'loss/train': 1.088355302810669} 08/31/2021 13:28:12 - INFO - __main__ - Step 134003: {'lr': 1.427710307170782e-05, 'samples': 25728576, 'steps': 134002, 'loss/train': 0.3555222153663635} 08/31/2021 13:28:13 - INFO - __main__ - Step 134004: {'lr': 1.4275335449516509e-05, 'samples': 25728768, 'steps': 134003, 'loss/train': 0.036698535084724426} 08/31/2021 13:28:13 - INFO - __main__ - Step 134005: {'lr': 1.4273567933539094e-05, 'samples': 25728960, 'steps': 134004, 'loss/train': 1.2225992679595947} 08/31/2021 13:28:15 - INFO - __main__ - Step 134006: {'lr': 1.4271800523776356e-05, 'samples': 25729152, 'steps': 134005, 'loss/train': 0.8732820153236389} 08/31/2021 13:28:15 - INFO - __main__ - Step 134007: {'lr': 1.4270033220229128e-05, 'samples': 25729344, 'steps': 134006, 'loss/train': 0.6042932868003845} 08/31/2021 13:28:16 - INFO - __main__ - Step 134008: {'lr': 1.4268266022898186e-05, 'samples': 25729536, 'steps': 134007, 'loss/train': 0.7135217785835266} 08/31/2021 13:28:16 - INFO - __main__ - Step 134009: {'lr': 1.4266498931784332e-05, 'samples': 25729728, 'steps': 134008, 'loss/train': 1.0701647996902466} 08/31/2021 13:28:16 - INFO - __main__ - Step 134010: {'lr': 1.4264731946888349e-05, 'samples': 25729920, 'steps': 134009, 'loss/train': 0.03307119384407997} 08/31/2021 13:28:18 - INFO - __main__ - Step 134011: {'lr': 1.4262965068211036e-05, 'samples': 25730112, 'steps': 134010, 'loss/train': 0.03478221222758293} 08/31/2021 13:28:19 - INFO - __main__ - Step 134012: {'lr': 1.4261198295753203e-05, 'samples': 25730304, 'steps': 134011, 'loss/train': 1.6246601343154907} 08/31/2021 13:28:19 - INFO - __main__ - Step 134013: {'lr': 1.4259431629515624e-05, 'samples': 25730496, 'steps': 134012, 'loss/train': 0.9590060114860535} 08/31/2021 13:28:19 - INFO - __main__ - Step 134014: {'lr': 1.4257665069499104e-05, 'samples': 25730688, 'steps': 134013, 'loss/train': 1.5462430715560913} 08/31/2021 13:28:20 - INFO - __main__ - Step 134015: {'lr': 1.425589861570442e-05, 'samples': 25730880, 'steps': 134014, 'loss/train': 1.6239044666290283} 08/31/2021 13:28:20 - INFO - __main__ - Step 134016: {'lr': 1.4254132268132435e-05, 'samples': 25731072, 'steps': 134015, 'loss/train': 0.805440366268158} 08/31/2021 13:28:21 - INFO - __main__ - Step 134017: {'lr': 1.425236602678387e-05, 'samples': 25731264, 'steps': 134016, 'loss/train': 1.4702144861221313} 08/31/2021 13:28:22 - INFO - __main__ - Step 134018: {'lr': 1.4250599891659555e-05, 'samples': 25731456, 'steps': 134017, 'loss/train': 1.5623865127563477} 08/31/2021 13:28:22 - INFO - __main__ - Step 134019: {'lr': 1.4248833862760296e-05, 'samples': 25731648, 'steps': 134018, 'loss/train': 1.5484055280685425} 08/31/2021 13:28:23 - INFO - __main__ - Step 134020: {'lr': 1.4247067940086871e-05, 'samples': 25731840, 'steps': 134019, 'loss/train': 1.091684341430664} 08/31/2021 13:28:23 - INFO - __main__ - Step 134021: {'lr': 1.4245302123640059e-05, 'samples': 25732032, 'steps': 134020, 'loss/train': 0.9743327498435974} 08/31/2021 13:28:25 - INFO - __main__ - Step 134022: {'lr': 1.4243536413420744e-05, 'samples': 25732224, 'steps': 134021, 'loss/train': 0.3837025463581085} 08/31/2021 13:28:25 - INFO - __main__ - Step 134023: {'lr': 1.4241770809429593e-05, 'samples': 25732416, 'steps': 134022, 'loss/train': 0.4508083760738373} 08/31/2021 13:28:26 - INFO - __main__ - Step 134024: {'lr': 1.424000531166747e-05, 'samples': 25732608, 'steps': 134023, 'loss/train': 1.2909282445907593} 08/31/2021 13:28:26 - INFO - __main__ - Step 134025: {'lr': 1.4238239920135176e-05, 'samples': 25732800, 'steps': 134024, 'loss/train': 1.2007209062576294} 08/31/2021 13:28:26 - INFO - __main__ - Step 134026: {'lr': 1.4236474634833463e-05, 'samples': 25732992, 'steps': 134025, 'loss/train': 0.914893627166748} 08/31/2021 13:28:28 - INFO - __main__ - Step 134027: {'lr': 1.423470945576319e-05, 'samples': 25733184, 'steps': 134026, 'loss/train': 1.006440281867981} 08/31/2021 13:28:28 - INFO - __main__ - Step 134028: {'lr': 1.4232944382925106e-05, 'samples': 25733376, 'steps': 134027, 'loss/train': 1.3801337480545044} 08/31/2021 13:28:29 - INFO - __main__ - Step 134029: {'lr': 1.4231179416320017e-05, 'samples': 25733568, 'steps': 134028, 'loss/train': 1.3717920780181885} 08/31/2021 13:28:29 - INFO - __main__ - Step 134030: {'lr': 1.42294145559487e-05, 'samples': 25733760, 'steps': 134029, 'loss/train': 0.579491913318634} 08/31/2021 13:28:29 - INFO - __main__ - Step 134031: {'lr': 1.4227649801811987e-05, 'samples': 25733952, 'steps': 134030, 'loss/train': 0.2733210325241089} 08/31/2021 13:28:30 - INFO - __main__ - Step 134032: {'lr': 1.4225885153910684e-05, 'samples': 25734144, 'steps': 134031, 'loss/train': 0.6709097623825073} 08/31/2021 13:28:32 - INFO - __main__ - Step 134033: {'lr': 1.4224120612245566e-05, 'samples': 25734336, 'steps': 134032, 'loss/train': 1.1710140705108643} 08/31/2021 13:28:33 - INFO - __main__ - Step 134034: {'lr': 1.4222356176817387e-05, 'samples': 25734528, 'steps': 134033, 'loss/train': 1.2369800806045532} 08/31/2021 13:28:33 - INFO - __main__ - Step 134035: {'lr': 1.4220591847626974e-05, 'samples': 25734720, 'steps': 134034, 'loss/train': 1.2504981756210327} 08/31/2021 13:28:33 - INFO - __main__ - Step 134036: {'lr': 1.4218827624675134e-05, 'samples': 25734912, 'steps': 134035, 'loss/train': 1.4451936483383179} 08/31/2021 13:28:34 - INFO - __main__ - Step 134037: {'lr': 1.4217063507962647e-05, 'samples': 25735104, 'steps': 134036, 'loss/train': 0.6051578521728516} 08/31/2021 13:28:35 - INFO - __main__ - Step 134038: {'lr': 1.4215299497490314e-05, 'samples': 25735296, 'steps': 134037, 'loss/train': 1.2492882013320923} 08/31/2021 13:28:36 - INFO - __main__ - Step 134039: {'lr': 1.4213535593258914e-05, 'samples': 25735488, 'steps': 134038, 'loss/train': 1.332126259803772} 08/31/2021 13:28:36 - INFO - __main__ - Step 134040: {'lr': 1.4211771795269279e-05, 'samples': 25735680, 'steps': 134039, 'loss/train': 1.0374078750610352} 08/31/2021 13:28:36 - INFO - __main__ - Step 134041: {'lr': 1.4210008103522159e-05, 'samples': 25735872, 'steps': 134040, 'loss/train': 1.083688735961914} 08/31/2021 13:28:37 - INFO - __main__ - Step 134042: {'lr': 1.4208244518018387e-05, 'samples': 25736064, 'steps': 134041, 'loss/train': 0.37880411744117737} 08/31/2021 13:28:38 - INFO - __main__ - Step 134043: {'lr': 1.420648103875874e-05, 'samples': 25736256, 'steps': 134042, 'loss/train': 1.2880210876464844} 08/31/2021 13:28:39 - INFO - __main__ - Step 134044: {'lr': 1.4204717665744049e-05, 'samples': 25736448, 'steps': 134043, 'loss/train': 1.0330339670181274} 08/31/2021 13:28:39 - INFO - __main__ - Step 134045: {'lr': 1.4202954398975038e-05, 'samples': 25736640, 'steps': 134044, 'loss/train': 0.9681956171989441} 08/31/2021 13:28:39 - INFO - __main__ - Step 134046: {'lr': 1.4201191238452537e-05, 'samples': 25736832, 'steps': 134045, 'loss/train': 0.7008526921272278} 08/31/2021 13:28:40 - INFO - __main__ - Step 134047: {'lr': 1.4199428184177326e-05, 'samples': 25737024, 'steps': 134046, 'loss/train': 0.7497484087944031} 08/31/2021 13:28:41 - INFO - __main__ - Step 134048: {'lr': 1.4197665236150237e-05, 'samples': 25737216, 'steps': 134047, 'loss/train': 1.2474091053009033} 08/31/2021 13:28:42 - INFO - __main__ - Step 134049: {'lr': 1.4195902394372045e-05, 'samples': 25737408, 'steps': 134048, 'loss/train': 1.2207483053207397} 08/31/2021 13:28:42 - INFO - __main__ - Step 134050: {'lr': 1.419413965884353e-05, 'samples': 25737600, 'steps': 134049, 'loss/train': 0.058942534029483795} 08/31/2021 13:28:42 - INFO - __main__ - Step 134051: {'lr': 1.4192377029565496e-05, 'samples': 25737792, 'steps': 134050, 'loss/train': 1.0161707401275635} 08/31/2021 13:28:43 - INFO - __main__ - Step 134052: {'lr': 1.4190614506538719e-05, 'samples': 25737984, 'steps': 134051, 'loss/train': 0.7184758186340332} 08/31/2021 13:28:43 - INFO - __main__ - Step 134053: {'lr': 1.4188852089764031e-05, 'samples': 25738176, 'steps': 134052, 'loss/train': 1.0925480127334595} 08/31/2021 13:28:45 - INFO - __main__ - Step 134054: {'lr': 1.4187089779242212e-05, 'samples': 25738368, 'steps': 134053, 'loss/train': 1.922190546989441} 08/31/2021 13:28:45 - INFO - __main__ - Step 134055: {'lr': 1.4185327574974094e-05, 'samples': 25738560, 'steps': 134054, 'loss/train': 1.1181024312973022} 08/31/2021 13:28:45 - INFO - __main__ - Step 134056: {'lr': 1.418356547696037e-05, 'samples': 25738752, 'steps': 134055, 'loss/train': 0.8621811270713806} 08/31/2021 13:28:46 - INFO - __main__ - Step 134057: {'lr': 1.4181803485201899e-05, 'samples': 25738944, 'steps': 134056, 'loss/train': 0.8512356281280518} 08/31/2021 13:28:46 - INFO - __main__ - Step 134058: {'lr': 1.418004159969946e-05, 'samples': 25739136, 'steps': 134057, 'loss/train': 1.6501435041427612} 08/31/2021 13:28:48 - INFO - __main__ - Step 134059: {'lr': 1.4178279820453887e-05, 'samples': 25739328, 'steps': 134058, 'loss/train': 1.0908584594726562} 08/31/2021 13:28:49 - INFO - __main__ - Step 134060: {'lr': 1.4176518147465927e-05, 'samples': 25739520, 'steps': 134059, 'loss/train': 1.5773149728775024} 08/31/2021 13:28:49 - INFO - __main__ - Step 134061: {'lr': 1.4174756580736387e-05, 'samples': 25739712, 'steps': 134060, 'loss/train': 1.3639942407608032} 08/31/2021 13:28:49 - INFO - __main__ - Step 134062: {'lr': 1.4172995120266042e-05, 'samples': 25739904, 'steps': 134061, 'loss/train': 1.0998146533966064} 08/31/2021 13:28:50 - INFO - __main__ - Step 134063: {'lr': 1.4171233766055724e-05, 'samples': 25740096, 'steps': 134062, 'loss/train': 0.6659956574440002} 08/31/2021 13:28:50 - INFO - __main__ - Step 134064: {'lr': 1.4169472518106214e-05, 'samples': 25740288, 'steps': 134063, 'loss/train': 0.013751199468970299} 08/31/2021 13:28:52 - INFO - __main__ - Step 134065: {'lr': 1.4167711376418313e-05, 'samples': 25740480, 'steps': 134064, 'loss/train': 1.433364987373352} 08/31/2021 13:28:53 - INFO - __main__ - Step 134066: {'lr': 1.41659503409928e-05, 'samples': 25740672, 'steps': 134065, 'loss/train': 0.9113729596138} 08/31/2021 13:28:53 - INFO - __main__ - Step 134067: {'lr': 1.416418941183048e-05, 'samples': 25740864, 'steps': 134066, 'loss/train': 0.6782418489456177} 08/31/2021 13:28:54 - INFO - __main__ - Step 134068: {'lr': 1.4162428588932103e-05, 'samples': 25741056, 'steps': 134067, 'loss/train': 0.5690387487411499} 08/31/2021 13:28:54 - INFO - __main__ - Step 134069: {'lr': 1.41606678722985e-05, 'samples': 25741248, 'steps': 134068, 'loss/train': 1.195669412612915} 08/31/2021 13:28:54 - INFO - __main__ - Step 134070: {'lr': 1.4158907261930477e-05, 'samples': 25741440, 'steps': 134069, 'loss/train': 1.1232990026474} 08/31/2021 13:28:56 - INFO - __main__ - Step 134071: {'lr': 1.4157146757828809e-05, 'samples': 25741632, 'steps': 134070, 'loss/train': 1.6673372983932495} 08/31/2021 13:28:56 - INFO - __main__ - Step 134072: {'lr': 1.4155386359994276e-05, 'samples': 25741824, 'steps': 134071, 'loss/train': 1.0157716274261475} 08/31/2021 13:28:56 - INFO - __main__ - Step 134073: {'lr': 1.4153626068427683e-05, 'samples': 25742016, 'steps': 134072, 'loss/train': 1.454504132270813} 08/31/2021 13:28:57 - INFO - __main__ - Step 134074: {'lr': 1.4151865883129861e-05, 'samples': 25742208, 'steps': 134073, 'loss/train': 0.8291450142860413} 08/31/2021 13:28:57 - INFO - __main__ - Step 134075: {'lr': 1.4150105804101532e-05, 'samples': 25742400, 'steps': 134074, 'loss/train': 0.7247427105903625} 08/31/2021 13:28:59 - INFO - __main__ - Step 134076: {'lr': 1.4148345831343584e-05, 'samples': 25742592, 'steps': 134075, 'loss/train': 1.3867154121398926} 08/31/2021 13:28:59 - INFO - __main__ - Step 134077: {'lr': 1.4146585964856713e-05, 'samples': 25742784, 'steps': 134076, 'loss/train': 1.4382261037826538} 08/31/2021 13:29:00 - INFO - __main__ - Step 134078: {'lr': 1.4144826204641747e-05, 'samples': 25742976, 'steps': 134077, 'loss/train': 1.5294368267059326} 08/31/2021 13:29:00 - INFO - __main__ - Step 134079: {'lr': 1.4143066550699469e-05, 'samples': 25743168, 'steps': 134078, 'loss/train': 1.3007407188415527} 08/31/2021 13:29:00 - INFO - __main__ - Step 134080: {'lr': 1.4141307003030706e-05, 'samples': 25743360, 'steps': 134079, 'loss/train': 1.2106245756149292} 08/31/2021 13:29:02 - INFO - __main__ - Step 134081: {'lr': 1.4139547561636213e-05, 'samples': 25743552, 'steps': 134080, 'loss/train': 0.8901041746139526} 08/31/2021 13:29:02 - INFO - __main__ - Step 134082: {'lr': 1.4137788226516818e-05, 'samples': 25743744, 'steps': 134081, 'loss/train': 0.03547782078385353} 08/31/2021 13:29:03 - INFO - __main__ - Step 134083: {'lr': 1.41360289976733e-05, 'samples': 25743936, 'steps': 134082, 'loss/train': 1.1739144325256348} 08/31/2021 13:29:03 - INFO - __main__ - Step 134084: {'lr': 1.4134269875106438e-05, 'samples': 25744128, 'steps': 134083, 'loss/train': 0.7887212038040161} 08/31/2021 13:29:03 - INFO - __main__ - Step 134085: {'lr': 1.4132510858817032e-05, 'samples': 25744320, 'steps': 134084, 'loss/train': 1.3120924234390259} 08/31/2021 13:29:05 - INFO - __main__ - Step 134086: {'lr': 1.4130751948805865e-05, 'samples': 25744512, 'steps': 134085, 'loss/train': 1.0111675262451172} 08/31/2021 13:29:05 - INFO - __main__ - Step 134087: {'lr': 1.4128993145073764e-05, 'samples': 25744704, 'steps': 134086, 'loss/train': 1.621893286705017} 08/31/2021 13:29:06 - INFO - __main__ - Step 134088: {'lr': 1.4127234447621483e-05, 'samples': 25744896, 'steps': 134087, 'loss/train': 0.10486330837011337} 08/31/2021 13:29:06 - INFO - __main__ - Step 134089: {'lr': 1.4125475856449853e-05, 'samples': 25745088, 'steps': 134088, 'loss/train': 1.5764689445495605} 08/31/2021 13:29:06 - INFO - __main__ - Step 134090: {'lr': 1.4123717371559652e-05, 'samples': 25745280, 'steps': 134089, 'loss/train': 1.3870952129364014} 08/31/2021 13:29:07 - INFO - __main__ - Step 134091: {'lr': 1.4121958992951628e-05, 'samples': 25745472, 'steps': 134090, 'loss/train': 1.495348334312439} 08/31/2021 13:29:09 - INFO - __main__ - Step 134092: {'lr': 1.4120200720626642e-05, 'samples': 25745664, 'steps': 134091, 'loss/train': 1.0541410446166992} 08/31/2021 13:29:09 - INFO - __main__ - Step 134093: {'lr': 1.4118442554585415e-05, 'samples': 25745856, 'steps': 134092, 'loss/train': 1.8526042699813843} 08/31/2021 13:29:09 - INFO - __main__ - Step 134094: {'lr': 1.4116684494828807e-05, 'samples': 25746048, 'steps': 134093, 'loss/train': 1.9283519983291626} 08/31/2021 13:29:10 - INFO - __main__ - Step 134095: {'lr': 1.411492654135757e-05, 'samples': 25746240, 'steps': 134094, 'loss/train': 1.0234739780426025} 08/31/2021 13:29:10 - INFO - __main__ - Step 134096: {'lr': 1.4113168694172508e-05, 'samples': 25746432, 'steps': 134095, 'loss/train': 0.7627898454666138} 08/31/2021 13:29:12 - INFO - __main__ - Step 134097: {'lr': 1.4111410953274422e-05, 'samples': 25746624, 'steps': 134096, 'loss/train': 0.9245980978012085} 08/31/2021 13:29:12 - INFO - __main__ - Step 134098: {'lr': 1.4109653318664067e-05, 'samples': 25746816, 'steps': 134097, 'loss/train': 0.812269926071167} 08/31/2021 13:29:12 - INFO - __main__ - Step 134099: {'lr': 1.4107895790342273e-05, 'samples': 25747008, 'steps': 134098, 'loss/train': 1.3456385135650635} 08/31/2021 13:29:13 - INFO - __main__ - Step 134100: {'lr': 1.4106138368309845e-05, 'samples': 25747200, 'steps': 134099, 'loss/train': 1.2759580612182617} 08/31/2021 13:29:13 - INFO - __main__ - Step 134101: {'lr': 1.4104381052567534e-05, 'samples': 25747392, 'steps': 134100, 'loss/train': 1.4623993635177612} 08/31/2021 13:29:15 - INFO - __main__ - Step 134102: {'lr': 1.410262384311614e-05, 'samples': 25747584, 'steps': 134101, 'loss/train': 1.4240933656692505} 08/31/2021 13:29:15 - INFO - __main__ - Step 134103: {'lr': 1.4100866739956503e-05, 'samples': 25747776, 'steps': 134102, 'loss/train': 1.3922090530395508} 08/31/2021 13:29:16 - INFO - __main__ - Step 134104: {'lr': 1.409910974308934e-05, 'samples': 25747968, 'steps': 134103, 'loss/train': 1.4394421577453613} 08/31/2021 13:29:16 - INFO - __main__ - Step 134105: {'lr': 1.4097352852515482e-05, 'samples': 25748160, 'steps': 134104, 'loss/train': 1.1211748123168945} 08/31/2021 13:29:16 - INFO - __main__ - Step 134106: {'lr': 1.409559606823571e-05, 'samples': 25748352, 'steps': 134105, 'loss/train': 1.0612303018569946} 08/31/2021 13:29:18 - INFO - __main__ - Step 134107: {'lr': 1.4093839390250856e-05, 'samples': 25748544, 'steps': 134106, 'loss/train': 1.7813142538070679} 08/31/2021 13:29:18 - INFO - __main__ - Step 134108: {'lr': 1.4092082818561642e-05, 'samples': 25748736, 'steps': 134107, 'loss/train': 0.8589538335800171} 08/31/2021 13:29:19 - INFO - __main__ - Step 134109: {'lr': 1.4090326353168897e-05, 'samples': 25748928, 'steps': 134108, 'loss/train': 1.1675986051559448} 08/31/2021 13:29:19 - INFO - __main__ - Step 134110: {'lr': 1.408856999407343e-05, 'samples': 25749120, 'steps': 134109, 'loss/train': 1.0787039995193481} 08/31/2021 13:29:19 - INFO - __main__ - Step 134111: {'lr': 1.4086813741275989e-05, 'samples': 25749312, 'steps': 134110, 'loss/train': 1.5801762342453003} 08/31/2021 13:29:21 - INFO - __main__ - Step 134112: {'lr': 1.4085057594777407e-05, 'samples': 25749504, 'steps': 134111, 'loss/train': 0.9044137597084045} 08/31/2021 13:29:21 - INFO - __main__ - Step 134113: {'lr': 1.4083301554578431e-05, 'samples': 25749696, 'steps': 134112, 'loss/train': 0.8373737931251526} 08/31/2021 13:29:21 - INFO - __main__ - Step 134114: {'lr': 1.4081545620679925e-05, 'samples': 25749888, 'steps': 134113, 'loss/train': 1.1658488512039185} 08/31/2021 13:29:22 - INFO - __main__ - Step 134115: {'lr': 1.4079789793082609e-05, 'samples': 25750080, 'steps': 134114, 'loss/train': 0.9780802726745605} 08/31/2021 13:29:22 - INFO - __main__ - Step 134116: {'lr': 1.4078034071787289e-05, 'samples': 25750272, 'steps': 134115, 'loss/train': 1.1169980764389038} 08/31/2021 13:29:22 - INFO - __main__ - Step 134117: {'lr': 1.4076278456794822e-05, 'samples': 25750464, 'steps': 134116, 'loss/train': 0.9913887977600098} 08/31/2021 13:29:24 - INFO - __main__ - Step 134118: {'lr': 1.4074522948105878e-05, 'samples': 25750656, 'steps': 134117, 'loss/train': 1.1462187767028809} 08/31/2021 13:29:24 - INFO - __main__ - Step 134119: {'lr': 1.4072767545721344e-05, 'samples': 25750848, 'steps': 134118, 'loss/train': 0.8807044625282288} 08/31/2021 13:29:25 - INFO - __main__ - Step 134120: {'lr': 1.4071012249641967e-05, 'samples': 25751040, 'steps': 134119, 'loss/train': 1.365315556526184} 08/31/2021 13:29:25 - INFO - __main__ - Step 134121: {'lr': 1.4069257059868556e-05, 'samples': 25751232, 'steps': 134120, 'loss/train': 1.1101815700531006} 08/31/2021 13:29:25 - INFO - __main__ - Step 134122: {'lr': 1.4067501976401887e-05, 'samples': 25751424, 'steps': 134121, 'loss/train': 1.4595311880111694} 08/31/2021 13:29:27 - INFO - __main__ - Step 134123: {'lr': 1.4065746999242763e-05, 'samples': 25751616, 'steps': 134122, 'loss/train': 1.0273560285568237} 08/31/2021 13:29:27 - INFO - __main__ - Step 134124: {'lr': 1.406399212839199e-05, 'samples': 25751808, 'steps': 134123, 'loss/train': 1.0159839391708374} 08/31/2021 13:29:28 - INFO - __main__ - Step 134125: {'lr': 1.4062237363850316e-05, 'samples': 25752000, 'steps': 134124, 'loss/train': 1.5150035619735718} 08/31/2021 13:29:28 - INFO - __main__ - Step 134126: {'lr': 1.4060482705618577e-05, 'samples': 25752192, 'steps': 134125, 'loss/train': 0.5761393904685974} 08/31/2021 13:29:28 - INFO - __main__ - Step 134127: {'lr': 1.4058728153697548e-05, 'samples': 25752384, 'steps': 134126, 'loss/train': 1.0490463972091675} 08/31/2021 13:29:30 - INFO - __main__ - Step 134128: {'lr': 1.4056973708088006e-05, 'samples': 25752576, 'steps': 134127, 'loss/train': 0.041505854576826096} 08/31/2021 13:29:30 - INFO - __main__ - Step 134129: {'lr': 1.4055219368790728e-05, 'samples': 25752768, 'steps': 134128, 'loss/train': 0.5390510559082031} 08/31/2021 13:29:31 - INFO - __main__ - Step 134130: {'lr': 1.4053465135806603e-05, 'samples': 25752960, 'steps': 134129, 'loss/train': 1.1779048442840576} 08/31/2021 13:29:31 - INFO - __main__ - Step 134131: {'lr': 1.4051711009136297e-05, 'samples': 25753152, 'steps': 134130, 'loss/train': 1.189618468284607} 08/31/2021 13:29:31 - INFO - __main__ - Step 134132: {'lr': 1.4049956988780644e-05, 'samples': 25753344, 'steps': 134131, 'loss/train': 1.0762978792190552} 08/31/2021 13:29:33 - INFO - __main__ - Step 134133: {'lr': 1.4048203074740417e-05, 'samples': 25753536, 'steps': 134132, 'loss/train': 0.8541330695152283} 08/31/2021 13:29:33 - INFO - __main__ - Step 134134: {'lr': 1.4046449267016453e-05, 'samples': 25753728, 'steps': 134133, 'loss/train': 0.3194895386695862} 08/31/2021 13:29:34 - INFO - __main__ - Step 134135: {'lr': 1.4044695565609528e-05, 'samples': 25753920, 'steps': 134134, 'loss/train': 1.1648937463760376} 08/31/2021 13:29:34 - INFO - __main__ - Step 134136: {'lr': 1.4042941970520418e-05, 'samples': 25754112, 'steps': 134135, 'loss/train': 1.017809271812439} 08/31/2021 13:29:34 - INFO - __main__ - Step 134137: {'lr': 1.40411884817499e-05, 'samples': 25754304, 'steps': 134136, 'loss/train': 0.5152575969696045} 08/31/2021 13:29:36 - INFO - __main__ - Step 134138: {'lr': 1.4039435099298781e-05, 'samples': 25754496, 'steps': 134137, 'loss/train': 0.9672126770019531} 08/31/2021 13:29:36 - INFO - __main__ - Step 134139: {'lr': 1.4037681823167864e-05, 'samples': 25754688, 'steps': 134138, 'loss/train': 1.1165252923965454} 08/31/2021 13:29:37 - INFO - __main__ - Step 134140: {'lr': 1.4035928653357926e-05, 'samples': 25754880, 'steps': 134139, 'loss/train': 1.1631126403808594} 08/31/2021 13:29:37 - INFO - __main__ - Step 134141: {'lr': 1.4034175589869747e-05, 'samples': 25755072, 'steps': 134140, 'loss/train': 0.1594776213169098} 08/31/2021 13:29:38 - INFO - __main__ - Step 134142: {'lr': 1.4032422632704157e-05, 'samples': 25755264, 'steps': 134141, 'loss/train': 0.3393835127353668} 08/31/2021 13:29:41 - INFO - __main__ - Step 134143: {'lr': 1.4030669781861905e-05, 'samples': 25755456, 'steps': 134142, 'loss/train': 1.3727355003356934} 08/31/2021 13:29:41 - INFO - __main__ - Step 134144: {'lr': 1.4028917037343797e-05, 'samples': 25755648, 'steps': 134143, 'loss/train': 0.8917512893676758} 08/31/2021 13:29:41 - INFO - __main__ - Step 134145: {'lr': 1.402716439915061e-05, 'samples': 25755840, 'steps': 134144, 'loss/train': 1.072547435760498} 08/31/2021 13:29:42 - INFO - __main__ - Step 134146: {'lr': 1.4025411867283123e-05, 'samples': 25756032, 'steps': 134145, 'loss/train': 1.1707096099853516} 08/31/2021 13:29:42 - INFO - __main__ - Step 134147: {'lr': 1.4023659441742165e-05, 'samples': 25756224, 'steps': 134146, 'loss/train': 0.8819438219070435} 08/31/2021 13:29:42 - INFO - __main__ - Step 134148: {'lr': 1.4021907122528487e-05, 'samples': 25756416, 'steps': 134147, 'loss/train': 0.4898705780506134} 08/31/2021 13:29:43 - INFO - __main__ - Step 134149: {'lr': 1.4020154909642896e-05, 'samples': 25756608, 'steps': 134148, 'loss/train': 1.220049262046814} 08/31/2021 13:29:44 - INFO - __main__ - Step 134150: {'lr': 1.4018402803086195e-05, 'samples': 25756800, 'steps': 134149, 'loss/train': 0.3544555902481079} 08/31/2021 13:29:45 - INFO - __main__ - Step 134151: {'lr': 1.401665080285916e-05, 'samples': 25756992, 'steps': 134150, 'loss/train': 0.930743932723999} 08/31/2021 13:29:45 - INFO - __main__ - Step 134152: {'lr': 1.401489890896257e-05, 'samples': 25757184, 'steps': 134151, 'loss/train': 1.1133466958999634} 08/31/2021 13:29:45 - INFO - __main__ - Step 134153: {'lr': 1.401314712139723e-05, 'samples': 25757376, 'steps': 134152, 'loss/train': 0.6381483674049377} 08/31/2021 13:29:46 - INFO - __main__ - Step 134154: {'lr': 1.4011395440163916e-05, 'samples': 25757568, 'steps': 134153, 'loss/train': 2.662372589111328} 08/31/2021 13:29:46 - INFO - __main__ - Step 134155: {'lr': 1.4009643865263432e-05, 'samples': 25757760, 'steps': 134154, 'loss/train': 1.2496564388275146} 08/31/2021 13:29:48 - INFO - __main__ - Step 134156: {'lr': 1.4007892396696586e-05, 'samples': 25757952, 'steps': 134155, 'loss/train': 1.0255811214447021} 08/31/2021 13:29:48 - INFO - __main__ - Step 134157: {'lr': 1.4006141034464155e-05, 'samples': 25758144, 'steps': 134156, 'loss/train': 1.0101091861724854} 08/31/2021 13:29:48 - INFO - __main__ - Step 134158: {'lr': 1.4004389778566857e-05, 'samples': 25758336, 'steps': 134157, 'loss/train': 0.6801526546478271} 08/31/2021 13:29:49 - INFO - __main__ - Step 134159: {'lr': 1.4002638629005582e-05, 'samples': 25758528, 'steps': 134158, 'loss/train': 1.5179706811904907} 08/31/2021 13:29:49 - INFO - __main__ - Step 134160: {'lr': 1.4000887585781052e-05, 'samples': 25758720, 'steps': 134159, 'loss/train': 1.0272860527038574} 08/31/2021 13:29:50 - INFO - __main__ - Step 134161: {'lr': 1.3999136648894073e-05, 'samples': 25758912, 'steps': 134160, 'loss/train': 1.678289532661438} 08/31/2021 13:29:51 - INFO - __main__ - Step 134162: {'lr': 1.3997385818345449e-05, 'samples': 25759104, 'steps': 134161, 'loss/train': 1.015372633934021} 08/31/2021 13:29:51 - INFO - __main__ - Step 134163: {'lr': 1.3995635094135983e-05, 'samples': 25759296, 'steps': 134162, 'loss/train': 1.377720832824707} 08/31/2021 13:29:52 - INFO - __main__ - Step 134164: {'lr': 1.3993884476266427e-05, 'samples': 25759488, 'steps': 134163, 'loss/train': 0.9445418119430542} 08/31/2021 13:29:52 - INFO - __main__ - Step 134165: {'lr': 1.3992133964737585e-05, 'samples': 25759680, 'steps': 134164, 'loss/train': 0.4801546335220337} 08/31/2021 13:29:54 - INFO - __main__ - Step 134166: {'lr': 1.3990383559550235e-05, 'samples': 25759872, 'steps': 134165, 'loss/train': 0.1846817433834076} 08/31/2021 13:29:54 - INFO - __main__ - Step 134167: {'lr': 1.398863326070518e-05, 'samples': 25760064, 'steps': 134166, 'loss/train': 1.7310189008712769} 08/31/2021 13:29:54 - INFO - __main__ - Step 134168: {'lr': 1.39868830682032e-05, 'samples': 25760256, 'steps': 134167, 'loss/train': 0.035112496465444565} 08/31/2021 13:29:55 - INFO - __main__ - Step 134169: {'lr': 1.3985132982045095e-05, 'samples': 25760448, 'steps': 134168, 'loss/train': 1.3099056482315063} 08/31/2021 13:29:55 - INFO - __main__ - Step 134170: {'lr': 1.3983383002231704e-05, 'samples': 25760640, 'steps': 134169, 'loss/train': 1.1306108236312866} 08/31/2021 13:29:57 - INFO - __main__ - Step 134171: {'lr': 1.3981633128763687e-05, 'samples': 25760832, 'steps': 134170, 'loss/train': 0.9796966314315796} 08/31/2021 13:29:57 - INFO - __main__ - Step 134172: {'lr': 1.3979883361641938e-05, 'samples': 25761024, 'steps': 134171, 'loss/train': 0.8758986592292786} 08/31/2021 13:29:57 - INFO - __main__ - Step 134173: {'lr': 1.3978133700867202e-05, 'samples': 25761216, 'steps': 134172, 'loss/train': 0.8218146562576294} 08/31/2021 13:29:58 - INFO - __main__ - Step 134174: {'lr': 1.3976384146440257e-05, 'samples': 25761408, 'steps': 134173, 'loss/train': 1.6010570526123047} 08/31/2021 13:29:58 - INFO - __main__ - Step 134175: {'lr': 1.3974634698361937e-05, 'samples': 25761600, 'steps': 134174, 'loss/train': 1.1673918962478638} 08/31/2021 13:30:00 - INFO - __main__ - Step 134176: {'lr': 1.3972885356632992e-05, 'samples': 25761792, 'steps': 134175, 'loss/train': 0.24983252584934235} 08/31/2021 13:30:00 - INFO - __main__ - Step 134177: {'lr': 1.3971136121254224e-05, 'samples': 25761984, 'steps': 134176, 'loss/train': 0.48003658652305603} 08/31/2021 13:30:01 - INFO - __main__ - Step 134178: {'lr': 1.3969386992226413e-05, 'samples': 25762176, 'steps': 134177, 'loss/train': 0.03207722306251526} 08/31/2021 13:30:01 - INFO - __main__ - Step 134179: {'lr': 1.3967637969550362e-05, 'samples': 25762368, 'steps': 134178, 'loss/train': 0.6681519746780396} 08/31/2021 13:30:01 - INFO - __main__ - Step 134180: {'lr': 1.3965889053226849e-05, 'samples': 25762560, 'steps': 134179, 'loss/train': 1.1432191133499146} 08/31/2021 13:30:03 - INFO - __main__ - Step 134181: {'lr': 1.3964140243256651e-05, 'samples': 25762752, 'steps': 134180, 'loss/train': 1.2029273509979248} 08/31/2021 13:30:03 - INFO - __main__ - Step 134182: {'lr': 1.39623915396406e-05, 'samples': 25762944, 'steps': 134181, 'loss/train': 1.219319462776184} 08/31/2021 13:30:04 - INFO - __main__ - Step 134183: {'lr': 1.396064294237942e-05, 'samples': 25763136, 'steps': 134182, 'loss/train': 1.045623779296875} 08/31/2021 13:30:04 - INFO - __main__ - Step 134184: {'lr': 1.3958894451473997e-05, 'samples': 25763328, 'steps': 134183, 'loss/train': 1.4586750268936157} 08/31/2021 13:30:04 - INFO - __main__ - Step 134185: {'lr': 1.3957146066924998e-05, 'samples': 25763520, 'steps': 134184, 'loss/train': 2.17751407623291} 08/31/2021 13:30:06 - INFO - __main__ - Step 134186: {'lr': 1.3955397788733281e-05, 'samples': 25763712, 'steps': 134185, 'loss/train': 1.1423527002334595} 08/31/2021 13:30:06 - INFO - __main__ - Step 134187: {'lr': 1.39536496168996e-05, 'samples': 25763904, 'steps': 134186, 'loss/train': 0.6312567591667175} 08/31/2021 13:30:07 - INFO - __main__ - Step 134188: {'lr': 1.3951901551424783e-05, 'samples': 25764096, 'steps': 134187, 'loss/train': 1.5936245918273926} 08/31/2021 13:30:07 - INFO - __main__ - Step 134189: {'lr': 1.3950153592309583e-05, 'samples': 25764288, 'steps': 134188, 'loss/train': 0.9030722975730896} 08/31/2021 13:30:07 - INFO - __main__ - Step 134190: {'lr': 1.3948405739554804e-05, 'samples': 25764480, 'steps': 134189, 'loss/train': 1.3515303134918213} 08/31/2021 13:30:08 - INFO - __main__ - Step 134191: {'lr': 1.3946657993161222e-05, 'samples': 25764672, 'steps': 134190, 'loss/train': 0.8461074233055115} 08/31/2021 13:30:09 - INFO - __main__ - Step 134192: {'lr': 1.3944910353129642e-05, 'samples': 25764864, 'steps': 134191, 'loss/train': 0.701447606086731} 08/31/2021 13:30:10 - INFO - __main__ - Step 134193: {'lr': 1.3943162819460842e-05, 'samples': 25765056, 'steps': 134192, 'loss/train': 0.45972275733947754} 08/31/2021 13:30:10 - INFO - __main__ - Step 134194: {'lr': 1.3941415392155627e-05, 'samples': 25765248, 'steps': 134193, 'loss/train': 0.686692476272583} 08/31/2021 13:30:10 - INFO - __main__ - Step 134195: {'lr': 1.3939668071214744e-05, 'samples': 25765440, 'steps': 134194, 'loss/train': 0.8856986165046692} 08/31/2021 13:30:11 - INFO - __main__ - Step 134196: {'lr': 1.3937920856639003e-05, 'samples': 25765632, 'steps': 134195, 'loss/train': 1.5241581201553345} 08/31/2021 13:30:13 - INFO - __main__ - Step 134197: {'lr': 1.3936173748429259e-05, 'samples': 25765824, 'steps': 134196, 'loss/train': 0.7775217890739441} 08/31/2021 13:30:13 - INFO - __main__ - Step 134198: {'lr': 1.3934426746586183e-05, 'samples': 25766016, 'steps': 134197, 'loss/train': 1.1858805418014526} 08/31/2021 13:30:14 - INFO - __main__ - Step 134199: {'lr': 1.3932679851110602e-05, 'samples': 25766208, 'steps': 134198, 'loss/train': 1.1856402158737183} 08/31/2021 13:30:14 - INFO - __main__ - Step 134200: {'lr': 1.3930933062003299e-05, 'samples': 25766400, 'steps': 134199, 'loss/train': 0.5748852491378784} 08/31/2021 13:30:14 - INFO - __main__ - Step 134201: {'lr': 1.3929186379265101e-05, 'samples': 25766592, 'steps': 134200, 'loss/train': 5.652193546295166} 08/31/2021 13:30:15 - INFO - __main__ - Step 134202: {'lr': 1.3927439802896762e-05, 'samples': 25766784, 'steps': 134201, 'loss/train': 0.29972073435783386} 08/31/2021 13:30:16 - INFO - __main__ - Step 134203: {'lr': 1.3925693332899058e-05, 'samples': 25766976, 'steps': 134202, 'loss/train': 1.4049577713012695} 08/31/2021 13:30:17 - INFO - __main__ - Step 134204: {'lr': 1.3923946969272822e-05, 'samples': 25767168, 'steps': 134203, 'loss/train': 1.4085367918014526} 08/31/2021 13:30:17 - INFO - __main__ - Step 134205: {'lr': 1.3922200712018801e-05, 'samples': 25767360, 'steps': 134204, 'loss/train': 0.8909313678741455} 08/31/2021 13:30:17 - INFO - __main__ - Step 134206: {'lr': 1.3920454561137775e-05, 'samples': 25767552, 'steps': 134205, 'loss/train': 1.739959478378296} 08/31/2021 13:30:18 - INFO - __main__ - Step 134207: {'lr': 1.3918708516630573e-05, 'samples': 25767744, 'steps': 134206, 'loss/train': 1.1607028245925903} 08/31/2021 13:30:19 - INFO - __main__ - Step 134208: {'lr': 1.391696257849795e-05, 'samples': 25767936, 'steps': 134207, 'loss/train': 1.6813935041427612} 08/31/2021 13:30:20 - INFO - __main__ - Step 134209: {'lr': 1.3915216746740705e-05, 'samples': 25768128, 'steps': 134208, 'loss/train': 1.0380011796951294} 08/31/2021 13:30:20 - INFO - __main__ - Step 134210: {'lr': 1.391347102135962e-05, 'samples': 25768320, 'steps': 134209, 'loss/train': 0.6415022015571594} 08/31/2021 13:30:20 - INFO - __main__ - Step 134211: {'lr': 1.3911725402355496e-05, 'samples': 25768512, 'steps': 134210, 'loss/train': 1.5075411796569824} 08/31/2021 13:30:21 - INFO - __main__ - Step 134212: {'lr': 1.3909979889729084e-05, 'samples': 25768704, 'steps': 134211, 'loss/train': 0.35817351937294006} 08/31/2021 13:30:22 - INFO - __main__ - Step 134213: {'lr': 1.3908234483481219e-05, 'samples': 25768896, 'steps': 134212, 'loss/train': 1.0335274934768677} 08/31/2021 13:30:23 - INFO - __main__ - Step 134214: {'lr': 1.3906489183612619e-05, 'samples': 25769088, 'steps': 134213, 'loss/train': 0.23553994297981262} 08/31/2021 13:30:23 - INFO - __main__ - Step 134215: {'lr': 1.3904743990124146e-05, 'samples': 25769280, 'steps': 134214, 'loss/train': 0.05082910880446434} 08/31/2021 13:30:23 - INFO - __main__ - Step 134216: {'lr': 1.3902998903016523e-05, 'samples': 25769472, 'steps': 134215, 'loss/train': 0.7642512917518616} 08/31/2021 13:30:24 - INFO - __main__ - Step 134217: {'lr': 1.390125392229058e-05, 'samples': 25769664, 'steps': 134216, 'loss/train': 0.14260554313659668} 08/31/2021 13:30:25 - INFO - __main__ - Step 134218: {'lr': 1.3899509047947095e-05, 'samples': 25769856, 'steps': 134217, 'loss/train': 1.420874834060669} 08/31/2021 13:30:26 - INFO - __main__ - Step 134219: {'lr': 1.3897764279986847e-05, 'samples': 25770048, 'steps': 134218, 'loss/train': 0.803453266620636} 08/31/2021 13:30:26 - INFO - __main__ - Step 134220: {'lr': 1.389601961841061e-05, 'samples': 25770240, 'steps': 134219, 'loss/train': 1.597219467163086} 08/31/2021 13:30:27 - INFO - __main__ - Step 134221: {'lr': 1.3894275063219192e-05, 'samples': 25770432, 'steps': 134220, 'loss/train': 1.4460275173187256} 08/31/2021 13:30:27 - INFO - __main__ - Step 134222: {'lr': 1.3892530614413368e-05, 'samples': 25770624, 'steps': 134221, 'loss/train': 0.870245099067688} 08/31/2021 13:30:27 - INFO - __main__ - Step 134223: {'lr': 1.3890786271993915e-05, 'samples': 25770816, 'steps': 134222, 'loss/train': 0.9480368494987488} 08/31/2021 13:30:29 - INFO - __main__ - Step 134224: {'lr': 1.3889042035961697e-05, 'samples': 25771008, 'steps': 134223, 'loss/train': 1.744614601135254} 08/31/2021 13:30:29 - INFO - __main__ - Step 134225: {'lr': 1.3887297906317375e-05, 'samples': 25771200, 'steps': 134224, 'loss/train': 1.1440634727478027} 08/31/2021 13:30:30 - INFO - __main__ - Step 134226: {'lr': 1.3885553883061786e-05, 'samples': 25771392, 'steps': 134225, 'loss/train': 0.7348378300666809} 08/31/2021 13:30:30 - INFO - __main__ - Step 134227: {'lr': 1.3883809966195731e-05, 'samples': 25771584, 'steps': 134226, 'loss/train': 0.7022705674171448} 08/31/2021 13:30:30 - INFO - __main__ - Step 134228: {'lr': 1.3882066155719991e-05, 'samples': 25771776, 'steps': 134227, 'loss/train': 0.3659065067768097} 08/31/2021 13:30:32 - INFO - __main__ - Step 134229: {'lr': 1.3880322451635342e-05, 'samples': 25771968, 'steps': 134228, 'loss/train': 1.0882855653762817} 08/31/2021 13:30:33 - INFO - __main__ - Step 134230: {'lr': 1.3878578853942586e-05, 'samples': 25772160, 'steps': 134229, 'loss/train': 0.04342398792505264} 08/31/2021 13:30:33 - INFO - __main__ - Step 134231: {'lr': 1.3876835362642504e-05, 'samples': 25772352, 'steps': 134230, 'loss/train': 0.5977839827537537} 08/31/2021 13:30:33 - INFO - __main__ - Step 134232: {'lr': 1.3875091977735871e-05, 'samples': 25772544, 'steps': 134231, 'loss/train': 0.13463374972343445} 08/31/2021 13:30:34 - INFO - __main__ - Step 134233: {'lr': 1.3873348699223465e-05, 'samples': 25772736, 'steps': 134232, 'loss/train': 0.1073799729347229} 08/31/2021 13:30:35 - INFO - __main__ - Step 134234: {'lr': 1.387160552710609e-05, 'samples': 25772928, 'steps': 134233, 'loss/train': 0.837090015411377} 08/31/2021 13:30:36 - INFO - __main__ - Step 134235: {'lr': 1.3869862461384525e-05, 'samples': 25773120, 'steps': 134234, 'loss/train': 1.1218916177749634} 08/31/2021 13:30:36 - INFO - __main__ - Step 134236: {'lr': 1.3868119502059573e-05, 'samples': 25773312, 'steps': 134235, 'loss/train': 0.6358454823493958} 08/31/2021 13:30:37 - INFO - __main__ - Step 134237: {'lr': 1.3866376649131984e-05, 'samples': 25773504, 'steps': 134236, 'loss/train': 0.8987962007522583} 08/31/2021 13:30:37 - INFO - __main__ - Step 134238: {'lr': 1.386463390260259e-05, 'samples': 25773696, 'steps': 134237, 'loss/train': 1.3594970703125} 08/31/2021 13:30:38 - INFO - __main__ - Step 134239: {'lr': 1.3862891262472144e-05, 'samples': 25773888, 'steps': 134238, 'loss/train': 0.7853448390960693} 08/31/2021 13:30:39 - INFO - __main__ - Step 134240: {'lr': 1.3861148728741418e-05, 'samples': 25774080, 'steps': 134239, 'loss/train': 0.5920731425285339} 08/31/2021 13:30:39 - INFO - __main__ - Step 134241: {'lr': 1.385940630141122e-05, 'samples': 25774272, 'steps': 134240, 'loss/train': 1.1657017469406128} 08/31/2021 13:30:40 - INFO - __main__ - Step 134242: {'lr': 1.3857663980482299e-05, 'samples': 25774464, 'steps': 134241, 'loss/train': 1.5234954357147217} 08/31/2021 13:30:40 - INFO - __main__ - Step 134243: {'lr': 1.3855921765955514e-05, 'samples': 25774656, 'steps': 134242, 'loss/train': 0.023163115605711937} 08/31/2021 13:30:42 - INFO - __main__ - Step 134244: {'lr': 1.3854179657831589e-05, 'samples': 25774848, 'steps': 134243, 'loss/train': 1.3211910724639893} 08/31/2021 13:30:42 - INFO - __main__ - Step 134245: {'lr': 1.3852437656111327e-05, 'samples': 25775040, 'steps': 134244, 'loss/train': 0.6069966554641724} 08/31/2021 13:30:42 - INFO - __main__ - Step 134246: {'lr': 1.3850695760795507e-05, 'samples': 25775232, 'steps': 134245, 'loss/train': 0.9046920537948608} 08/31/2021 13:30:43 - INFO - __main__ - Step 134247: {'lr': 1.3848953971884932e-05, 'samples': 25775424, 'steps': 134246, 'loss/train': 1.5640171766281128} 08/31/2021 13:30:43 - INFO - __main__ - Step 134248: {'lr': 1.3847212289380351e-05, 'samples': 25775616, 'steps': 134247, 'loss/train': 0.8097342848777771} 08/31/2021 13:30:43 - INFO - __main__ - Step 134249: {'lr': 1.3845470713282599e-05, 'samples': 25775808, 'steps': 134248, 'loss/train': 1.409356951713562} 08/31/2021 13:30:45 - INFO - __main__ - Step 134250: {'lr': 1.3843729243592424e-05, 'samples': 25776000, 'steps': 134249, 'loss/train': 1.3188982009887695} 08/31/2021 13:30:45 - INFO - __main__ - Step 134251: {'lr': 1.384198788031063e-05, 'samples': 25776192, 'steps': 134250, 'loss/train': 0.9134495854377747} 08/31/2021 13:30:46 - INFO - __main__ - Step 134252: {'lr': 1.3840246623437997e-05, 'samples': 25776384, 'steps': 134251, 'loss/train': 1.5156692266464233} 08/31/2021 13:30:46 - INFO - __main__ - Step 134253: {'lr': 1.3838505472975271e-05, 'samples': 25776576, 'steps': 134252, 'loss/train': 0.5992476940155029} 08/31/2021 13:30:46 - INFO - __main__ - Step 134254: {'lr': 1.3836764428923287e-05, 'samples': 25776768, 'steps': 134253, 'loss/train': 0.6292665004730225} 08/31/2021 13:30:48 - INFO - __main__ - Step 134255: {'lr': 1.3835023491282823e-05, 'samples': 25776960, 'steps': 134254, 'loss/train': 0.963375985622406} 08/31/2021 13:30:49 - INFO - __main__ - Step 134256: {'lr': 1.3833282660054652e-05, 'samples': 25777152, 'steps': 134255, 'loss/train': 0.5294374227523804} 08/31/2021 13:30:49 - INFO - __main__ - Step 134257: {'lr': 1.3831541935239555e-05, 'samples': 25777344, 'steps': 134256, 'loss/train': 0.7211654186248779} 08/31/2021 13:30:50 - INFO - __main__ - Step 134258: {'lr': 1.3829801316838309e-05, 'samples': 25777536, 'steps': 134257, 'loss/train': 0.9057498574256897} 08/31/2021 13:30:50 - INFO - __main__ - Step 134259: {'lr': 1.3828060804851716e-05, 'samples': 25777728, 'steps': 134258, 'loss/train': 1.3285856246948242} 08/31/2021 13:30:51 - INFO - __main__ - Step 134260: {'lr': 1.3826320399280557e-05, 'samples': 25777920, 'steps': 134259, 'loss/train': 1.0870798826217651} 08/31/2021 13:30:52 - INFO - __main__ - Step 134261: {'lr': 1.3824580100125605e-05, 'samples': 25778112, 'steps': 134260, 'loss/train': 1.0470986366271973} 08/31/2021 13:30:52 - INFO - __main__ - Step 134262: {'lr': 1.382283990738767e-05, 'samples': 25778304, 'steps': 134261, 'loss/train': 0.9798967838287354} 08/31/2021 13:30:52 - INFO - __main__ - Step 134263: {'lr': 1.3821099821067496e-05, 'samples': 25778496, 'steps': 134262, 'loss/train': 0.9841079711914062} 08/31/2021 13:30:53 - INFO - __main__ - Step 134264: {'lr': 1.3819359841165946e-05, 'samples': 25778688, 'steps': 134263, 'loss/train': 1.735277771949768} 08/31/2021 13:30:54 - INFO - __main__ - Step 134265: {'lr': 1.3817619967683714e-05, 'samples': 25778880, 'steps': 134264, 'loss/train': 0.4790014326572418} 08/31/2021 13:30:55 - INFO - __main__ - Step 134266: {'lr': 1.3815880200621605e-05, 'samples': 25779072, 'steps': 134265, 'loss/train': 0.5825933218002319} 08/31/2021 13:30:55 - INFO - __main__ - Step 134267: {'lr': 1.3814140539980424e-05, 'samples': 25779264, 'steps': 134266, 'loss/train': 0.03938307985663414} 08/31/2021 13:30:56 - INFO - __main__ - Step 134268: {'lr': 1.3812400985760947e-05, 'samples': 25779456, 'steps': 134267, 'loss/train': 0.488651305437088} 08/31/2021 13:30:56 - INFO - __main__ - Step 134269: {'lr': 1.3810661537963953e-05, 'samples': 25779648, 'steps': 134268, 'loss/train': 1.4857581853866577} 08/31/2021 13:30:58 - INFO - __main__ - Step 134270: {'lr': 1.3808922196590217e-05, 'samples': 25779840, 'steps': 134269, 'loss/train': 1.296458125114441} 08/31/2021 13:30:58 - INFO - __main__ - Step 134271: {'lr': 1.3807182961640574e-05, 'samples': 25780032, 'steps': 134270, 'loss/train': 1.2334132194519043} 08/31/2021 13:30:58 - INFO - __main__ - Step 134272: {'lr': 1.3805443833115745e-05, 'samples': 25780224, 'steps': 134271, 'loss/train': 1.176151990890503} 08/31/2021 13:30:59 - INFO - __main__ - Step 134273: {'lr': 1.3803704811016533e-05, 'samples': 25780416, 'steps': 134272, 'loss/train': 1.2767260074615479} 08/31/2021 13:30:59 - INFO - __main__ - Step 134274: {'lr': 1.3801965895343716e-05, 'samples': 25780608, 'steps': 134273, 'loss/train': 1.4748531579971313} 08/31/2021 13:31:01 - INFO - __main__ - Step 134275: {'lr': 1.3800227086098127e-05, 'samples': 25780800, 'steps': 134274, 'loss/train': 0.7514586448669434} 08/31/2021 13:31:01 - INFO - __main__ - Step 134276: {'lr': 1.3798488383280488e-05, 'samples': 25780992, 'steps': 134275, 'loss/train': 1.3687794208526611} 08/31/2021 13:31:01 - INFO - __main__ - Step 134277: {'lr': 1.3796749786891604e-05, 'samples': 25781184, 'steps': 134276, 'loss/train': 1.64370858669281} 08/31/2021 13:31:02 - INFO - __main__ - Step 134278: {'lr': 1.3795011296932281e-05, 'samples': 25781376, 'steps': 134277, 'loss/train': 0.967503547668457} 08/31/2021 13:31:02 - INFO - __main__ - Step 134279: {'lr': 1.3793272913403265e-05, 'samples': 25781568, 'steps': 134278, 'loss/train': 0.2732384204864502} 08/31/2021 13:31:04 - INFO - __main__ - Step 134280: {'lr': 1.3791534636305365e-05, 'samples': 25781760, 'steps': 134279, 'loss/train': 0.9034435153007507} 08/31/2021 13:31:05 - INFO - __main__ - Step 134281: {'lr': 1.3789796465639326e-05, 'samples': 25781952, 'steps': 134280, 'loss/train': 1.046358346939087} 08/31/2021 13:31:05 - INFO - __main__ - Step 134282: {'lr': 1.3788058401405984e-05, 'samples': 25782144, 'steps': 134281, 'loss/train': 0.2880307137966156} 08/31/2021 13:31:06 - INFO - __main__ - Step 134283: {'lr': 1.3786320443606088e-05, 'samples': 25782336, 'steps': 134282, 'loss/train': 0.2820749282836914} 08/31/2021 13:31:06 - INFO - __main__ - Step 134284: {'lr': 1.3784582592240442e-05, 'samples': 25782528, 'steps': 134283, 'loss/train': 0.26489993929862976} 08/31/2021 13:31:06 - INFO - __main__ - Step 134285: {'lr': 1.3782844847309795e-05, 'samples': 25782720, 'steps': 134284, 'loss/train': 0.9002701044082642} 08/31/2021 13:31:07 - INFO - __main__ - Step 134286: {'lr': 1.378110720881498e-05, 'samples': 25782912, 'steps': 134285, 'loss/train': 1.3396071195602417} 08/31/2021 13:31:08 - INFO - __main__ - Step 134287: {'lr': 1.3779369676756747e-05, 'samples': 25783104, 'steps': 134286, 'loss/train': 0.5203828811645508} 08/31/2021 13:31:09 - INFO - __main__ - Step 134288: {'lr': 1.3777632251135874e-05, 'samples': 25783296, 'steps': 134287, 'loss/train': 1.4297280311584473} 08/31/2021 13:31:09 - INFO - __main__ - Step 134289: {'lr': 1.3775894931953165e-05, 'samples': 25783488, 'steps': 134288, 'loss/train': 1.4907417297363281} 08/31/2021 13:31:09 - INFO - __main__ - Step 134290: {'lr': 1.3774157719209369e-05, 'samples': 25783680, 'steps': 134289, 'loss/train': 1.832869291305542} 08/31/2021 13:31:10 - INFO - __main__ - Step 134291: {'lr': 1.3772420612905345e-05, 'samples': 25783872, 'steps': 134290, 'loss/train': 1.0561851263046265} 08/31/2021 13:31:12 - INFO - __main__ - Step 134292: {'lr': 1.377068361304179e-05, 'samples': 25784064, 'steps': 134291, 'loss/train': 0.9779056310653687} 08/31/2021 13:31:12 - INFO - __main__ - Step 134293: {'lr': 1.3768946719619507e-05, 'samples': 25784256, 'steps': 134292, 'loss/train': 0.6658474206924438} 08/31/2021 13:31:12 - INFO - __main__ - Step 134294: {'lr': 1.3767209932639302e-05, 'samples': 25784448, 'steps': 134293, 'loss/train': 1.396601676940918} 08/31/2021 13:31:13 - INFO - __main__ - Step 134295: {'lr': 1.376547325210195e-05, 'samples': 25784640, 'steps': 134294, 'loss/train': 0.016028624027967453} 08/31/2021 13:31:13 - INFO - __main__ - Step 134296: {'lr': 1.3763736678008233e-05, 'samples': 25784832, 'steps': 134295, 'loss/train': 1.160826563835144} 08/31/2021 13:31:13 - INFO - __main__ - Step 134297: {'lr': 1.3762000210358921e-05, 'samples': 25785024, 'steps': 134296, 'loss/train': 1.838824987411499} 08/31/2021 13:31:15 - INFO - __main__ - Step 134298: {'lr': 1.3760263849154826e-05, 'samples': 25785216, 'steps': 134297, 'loss/train': 0.05145488306879997} 08/31/2021 13:31:15 - INFO - __main__ - Step 134299: {'lr': 1.3758527594396691e-05, 'samples': 25785408, 'steps': 134298, 'loss/train': 1.065260410308838} 08/31/2021 13:31:16 - INFO - __main__ - Step 134300: {'lr': 1.3756791446085327e-05, 'samples': 25785600, 'steps': 134299, 'loss/train': 1.3627976179122925} 08/31/2021 13:31:16 - INFO - __main__ - Step 134301: {'lr': 1.3755055404221505e-05, 'samples': 25785792, 'steps': 134300, 'loss/train': 1.011783242225647} 08/31/2021 13:31:16 - INFO - __main__ - Step 134302: {'lr': 1.3753319468806036e-05, 'samples': 25785984, 'steps': 134301, 'loss/train': 0.09029596298933029} 08/31/2021 13:31:18 - INFO - __main__ - Step 134303: {'lr': 1.3751583639839638e-05, 'samples': 25786176, 'steps': 134302, 'loss/train': 0.9809414148330688} 08/31/2021 13:31:18 - INFO - __main__ - Step 134304: {'lr': 1.3749847917323143e-05, 'samples': 25786368, 'steps': 134303, 'loss/train': 1.1186907291412354} 08/31/2021 13:31:19 - INFO - __main__ - Step 134305: {'lr': 1.3748112301257331e-05, 'samples': 25786560, 'steps': 134304, 'loss/train': 0.8487678170204163} 08/31/2021 13:31:19 - INFO - __main__ - Step 134306: {'lr': 1.3746376791642951e-05, 'samples': 25786752, 'steps': 134305, 'loss/train': 0.8629310131072998} 08/31/2021 13:31:19 - INFO - __main__ - Step 134307: {'lr': 1.3744641388480805e-05, 'samples': 25786944, 'steps': 134306, 'loss/train': 0.8686432242393494} 08/31/2021 13:31:22 - INFO - __main__ - Step 134308: {'lr': 1.3742906091771702e-05, 'samples': 25787136, 'steps': 134307, 'loss/train': 1.1582921743392944} 08/31/2021 13:31:22 - INFO - __main__ - Step 134309: {'lr': 1.3741170901516386e-05, 'samples': 25787328, 'steps': 134308, 'loss/train': 1.148606300354004} 08/31/2021 13:31:22 - INFO - __main__ - Step 134310: {'lr': 1.3739435817715668e-05, 'samples': 25787520, 'steps': 134309, 'loss/train': 0.4764087200164795} 08/31/2021 13:31:23 - INFO - __main__ - Step 134311: {'lr': 1.3737700840370293e-05, 'samples': 25787712, 'steps': 134310, 'loss/train': 0.05308147519826889} 08/31/2021 13:31:23 - INFO - __main__ - Step 134312: {'lr': 1.3735965969481095e-05, 'samples': 25787904, 'steps': 134311, 'loss/train': 1.0300203561782837} 08/31/2021 13:31:23 - INFO - __main__ - Step 134313: {'lr': 1.3734231205048826e-05, 'samples': 25788096, 'steps': 134312, 'loss/train': 0.822835385799408} 08/31/2021 13:31:26 - INFO - __main__ - Step 134314: {'lr': 1.373249654707423e-05, 'samples': 25788288, 'steps': 134313, 'loss/train': 1.2228420972824097} 08/31/2021 13:31:26 - INFO - __main__ - Step 134315: {'lr': 1.3730761995558144e-05, 'samples': 25788480, 'steps': 134314, 'loss/train': 0.514564573764801} 08/31/2021 13:31:27 - INFO - __main__ - Step 134316: {'lr': 1.3729027550501316e-05, 'samples': 25788672, 'steps': 134315, 'loss/train': 0.24107952415943146} 08/31/2021 13:31:27 - INFO - __main__ - Step 134317: {'lr': 1.372729321190455e-05, 'samples': 25788864, 'steps': 134316, 'loss/train': 0.24600741267204285} 08/31/2021 13:31:27 - INFO - __main__ - Step 134318: {'lr': 1.3725558979768627e-05, 'samples': 25789056, 'steps': 134317, 'loss/train': 0.2678154706954956} 08/31/2021 13:31:28 - INFO - __main__ - Step 134319: {'lr': 1.3723824854094318e-05, 'samples': 25789248, 'steps': 134318, 'loss/train': 1.0418546199798584} 08/31/2021 13:31:29 - INFO - __main__ - Step 134320: {'lr': 1.3722090834882407e-05, 'samples': 25789440, 'steps': 134319, 'loss/train': 0.8838269114494324} 08/31/2021 13:31:30 - INFO - __main__ - Step 134321: {'lr': 1.3720356922133665e-05, 'samples': 25789632, 'steps': 134320, 'loss/train': 1.222793698310852} 08/31/2021 13:31:30 - INFO - __main__ - Step 134322: {'lr': 1.37186231158489e-05, 'samples': 25789824, 'steps': 134321, 'loss/train': 1.9736827611923218} 08/31/2021 13:31:31 - INFO - __main__ - Step 134323: {'lr': 1.3716889416028916e-05, 'samples': 25790016, 'steps': 134322, 'loss/train': 0.21173685789108276} 08/31/2021 13:31:31 - INFO - __main__ - Step 134324: {'lr': 1.3715155822674408e-05, 'samples': 25790208, 'steps': 134323, 'loss/train': 0.5855308771133423} 08/31/2021 13:31:32 - INFO - __main__ - Step 134325: {'lr': 1.3713422335786207e-05, 'samples': 25790400, 'steps': 134324, 'loss/train': 0.031103147193789482} 08/31/2021 13:31:33 - INFO - __main__ - Step 134326: {'lr': 1.3711688955365092e-05, 'samples': 25790592, 'steps': 134325, 'loss/train': 1.2878062725067139} 08/31/2021 13:31:33 - INFO - __main__ - Step 134327: {'lr': 1.370995568141184e-05, 'samples': 25790784, 'steps': 134326, 'loss/train': 2.025738000869751} 08/31/2021 13:31:34 - INFO - __main__ - Step 134328: {'lr': 1.3708222513927226e-05, 'samples': 25790976, 'steps': 134327, 'loss/train': 1.7528306245803833} 08/31/2021 13:31:34 - INFO - __main__ - Step 134329: {'lr': 1.3706489452912057e-05, 'samples': 25791168, 'steps': 134328, 'loss/train': 1.0827993154525757} 08/31/2021 13:31:34 - INFO - __main__ - Step 134330: {'lr': 1.3704756498367111e-05, 'samples': 25791360, 'steps': 134329, 'loss/train': 1.131163477897644} 08/31/2021 13:31:36 - INFO - __main__ - Step 134331: {'lr': 1.3703023650293133e-05, 'samples': 25791552, 'steps': 134330, 'loss/train': 0.4764939248561859} 08/31/2021 13:31:36 - INFO - __main__ - Step 134332: {'lr': 1.3701290908690933e-05, 'samples': 25791744, 'steps': 134331, 'loss/train': 0.23619355261325836} 08/31/2021 13:31:37 - INFO - __main__ - Step 134333: {'lr': 1.3699558273561286e-05, 'samples': 25791936, 'steps': 134332, 'loss/train': 0.6868372559547424} 08/31/2021 13:31:37 - INFO - __main__ - Step 134334: {'lr': 1.3697825744904995e-05, 'samples': 25792128, 'steps': 134333, 'loss/train': 0.6681116819381714} 08/31/2021 13:31:37 - INFO - __main__ - Step 134335: {'lr': 1.3696093322722785e-05, 'samples': 25792320, 'steps': 134334, 'loss/train': 1.660552740097046} 08/31/2021 13:31:39 - INFO - __main__ - Step 134336: {'lr': 1.3694361007015488e-05, 'samples': 25792512, 'steps': 134335, 'loss/train': 0.796769917011261} 08/31/2021 13:31:39 - INFO - __main__ - Step 134337: {'lr': 1.3692628797783851e-05, 'samples': 25792704, 'steps': 134336, 'loss/train': 0.055550746619701385} 08/31/2021 13:31:40 - INFO - __main__ - Step 134338: {'lr': 1.3690896695028682e-05, 'samples': 25792896, 'steps': 134337, 'loss/train': 1.5760921239852905} 08/31/2021 13:31:40 - INFO - __main__ - Step 134339: {'lr': 1.3689164698750728e-05, 'samples': 25793088, 'steps': 134338, 'loss/train': 0.9655138254165649} 08/31/2021 13:31:40 - INFO - __main__ - Step 134340: {'lr': 1.3687432808950795e-05, 'samples': 25793280, 'steps': 134339, 'loss/train': 0.10991653800010681} 08/31/2021 13:31:42 - INFO - __main__ - Step 134341: {'lr': 1.368570102562966e-05, 'samples': 25793472, 'steps': 134340, 'loss/train': 0.7838238477706909} 08/31/2021 13:31:43 - INFO - __main__ - Step 134342: {'lr': 1.3683969348788129e-05, 'samples': 25793664, 'steps': 134341, 'loss/train': 1.366860270500183} 08/31/2021 13:31:43 - INFO - __main__ - Step 134343: {'lr': 1.368223777842692e-05, 'samples': 25793856, 'steps': 134342, 'loss/train': 0.9767485857009888} 08/31/2021 13:31:43 - INFO - __main__ - Step 134344: {'lr': 1.368050631454687e-05, 'samples': 25794048, 'steps': 134343, 'loss/train': 0.7906805872917175} 08/31/2021 13:31:44 - INFO - __main__ - Step 134345: {'lr': 1.3678774957148754e-05, 'samples': 25794240, 'steps': 134344, 'loss/train': 1.0137253999710083} 08/31/2021 13:31:45 - INFO - __main__ - Step 134346: {'lr': 1.3677043706233294e-05, 'samples': 25794432, 'steps': 134345, 'loss/train': 1.270689845085144} 08/31/2021 13:31:46 - INFO - __main__ - Step 134347: {'lr': 1.3675312561801323e-05, 'samples': 25794624, 'steps': 134346, 'loss/train': 1.5794813632965088} 08/31/2021 13:31:46 - INFO - __main__ - Step 134348: {'lr': 1.3673581523853618e-05, 'samples': 25794816, 'steps': 134347, 'loss/train': 1.1348458528518677} 08/31/2021 13:31:46 - INFO - __main__ - Step 134349: {'lr': 1.3671850592390956e-05, 'samples': 25795008, 'steps': 134348, 'loss/train': 1.0508997440338135} 08/31/2021 13:31:47 - INFO - __main__ - Step 134350: {'lr': 1.3670119767414085e-05, 'samples': 25795200, 'steps': 134349, 'loss/train': 0.4883619248867035} 08/31/2021 13:31:48 - INFO - __main__ - Step 134351: {'lr': 1.366838904892384e-05, 'samples': 25795392, 'steps': 134350, 'loss/train': 0.9491161108016968} 08/31/2021 13:31:49 - INFO - __main__ - Step 134352: {'lr': 1.3666658436920942e-05, 'samples': 25795584, 'steps': 134351, 'loss/train': 2.0850136280059814} 08/31/2021 13:31:49 - INFO - __main__ - Step 134353: {'lr': 1.3664927931406223e-05, 'samples': 25795776, 'steps': 134352, 'loss/train': 1.5330947637557983} 08/31/2021 13:31:49 - INFO - __main__ - Step 134354: {'lr': 1.3663197532380433e-05, 'samples': 25795968, 'steps': 134353, 'loss/train': 1.3492822647094727} 08/31/2021 13:31:50 - INFO - __main__ - Step 134355: {'lr': 1.366146723984435e-05, 'samples': 25796160, 'steps': 134354, 'loss/train': 1.444348931312561} 08/31/2021 13:31:50 - INFO - __main__ - Step 134356: {'lr': 1.3659737053798776e-05, 'samples': 25796352, 'steps': 134355, 'loss/train': 0.3084888160228729} 08/31/2021 13:31:52 - INFO - __main__ - Step 134357: {'lr': 1.365800697424449e-05, 'samples': 25796544, 'steps': 134356, 'loss/train': 1.0399093627929688} 08/31/2021 13:31:52 - INFO - __main__ - Step 134358: {'lr': 1.3656277001182243e-05, 'samples': 25796736, 'steps': 134357, 'loss/train': 0.032224737107753754} 08/31/2021 13:31:52 - INFO - __main__ - Step 134359: {'lr': 1.3654547134612866e-05, 'samples': 25796928, 'steps': 134358, 'loss/train': 1.0201036930084229} 08/31/2021 13:31:53 - INFO - __main__ - Step 134360: {'lr': 1.3652817374537052e-05, 'samples': 25797120, 'steps': 134359, 'loss/train': 1.0186392068862915} 08/31/2021 13:31:53 - INFO - __main__ - Step 134361: {'lr': 1.3651087720955662e-05, 'samples': 25797312, 'steps': 134360, 'loss/train': 0.5073656439781189} 08/31/2021 13:31:55 - INFO - __main__ - Step 134362: {'lr': 1.364935817386942e-05, 'samples': 25797504, 'steps': 134361, 'loss/train': 1.188845157623291} 08/31/2021 13:31:56 - INFO - __main__ - Step 134363: {'lr': 1.3647628733279154e-05, 'samples': 25797696, 'steps': 134362, 'loss/train': 1.1047420501708984} 08/31/2021 13:31:56 - INFO - __main__ - Step 134364: {'lr': 1.3645899399185591e-05, 'samples': 25797888, 'steps': 134363, 'loss/train': 1.018005132675171} 08/31/2021 13:31:56 - INFO - __main__ - Step 134365: {'lr': 1.364417017158956e-05, 'samples': 25798080, 'steps': 134364, 'loss/train': 0.948668360710144} 08/31/2021 13:31:57 - INFO - __main__ - Step 134366: {'lr': 1.364244105049181e-05, 'samples': 25798272, 'steps': 134365, 'loss/train': 1.2347251176834106} 08/31/2021 13:31:58 - INFO - __main__ - Step 134367: {'lr': 1.3640712035893149e-05, 'samples': 25798464, 'steps': 134366, 'loss/train': 1.6269859075546265} 08/31/2021 13:31:59 - INFO - __main__ - Step 134368: {'lr': 1.3638983127794296e-05, 'samples': 25798656, 'steps': 134367, 'loss/train': 0.5833604335784912} 08/31/2021 13:31:59 - INFO - __main__ - Step 134369: {'lr': 1.3637254326196113e-05, 'samples': 25798848, 'steps': 134368, 'loss/train': 1.399059772491455} 08/31/2021 13:31:59 - INFO - __main__ - Step 134370: {'lr': 1.3635525631099294e-05, 'samples': 25799040, 'steps': 134369, 'loss/train': 1.390829086303711} 08/31/2021 13:32:00 - INFO - __main__ - Step 134371: {'lr': 1.3633797042504698e-05, 'samples': 25799232, 'steps': 134370, 'loss/train': 0.9078798294067383} 08/31/2021 13:32:02 - INFO - __main__ - Step 134372: {'lr': 1.3632068560413075e-05, 'samples': 25799424, 'steps': 134371, 'loss/train': 1.3031758069992065} 08/31/2021 13:32:02 - INFO - __main__ - Step 134373: {'lr': 1.3630340184825174e-05, 'samples': 25799616, 'steps': 134372, 'loss/train': 1.2861998081207275} 08/31/2021 13:32:02 - INFO - __main__ - Step 134374: {'lr': 1.3628611915741773e-05, 'samples': 25799808, 'steps': 134373, 'loss/train': 1.2913012504577637} 08/31/2021 13:32:03 - INFO - __main__ - Step 134375: {'lr': 1.3626883753163704e-05, 'samples': 25800000, 'steps': 134374, 'loss/train': 1.188162088394165} 08/31/2021 13:32:03 - INFO - __main__ - Step 134376: {'lr': 1.362515569709169e-05, 'samples': 25800192, 'steps': 134375, 'loss/train': 1.2286262512207031} 08/31/2021 13:32:03 - INFO - __main__ - Step 134377: {'lr': 1.3623427747526535e-05, 'samples': 25800384, 'steps': 134376, 'loss/train': 0.013866838067770004} 08/31/2021 13:32:05 - INFO - __main__ - Step 134378: {'lr': 1.3621699904469043e-05, 'samples': 25800576, 'steps': 134377, 'loss/train': 0.06650219112634659} 08/31/2021 13:32:05 - INFO - __main__ - Step 134379: {'lr': 1.3619972167919937e-05, 'samples': 25800768, 'steps': 134378, 'loss/train': 0.585355281829834} 08/31/2021 13:32:06 - INFO - __main__ - Step 134380: {'lr': 1.361824453788002e-05, 'samples': 25800960, 'steps': 134379, 'loss/train': 0.372515469789505} 08/31/2021 13:32:06 - INFO - __main__ - Step 134381: {'lr': 1.3616517014350099e-05, 'samples': 25801152, 'steps': 134380, 'loss/train': 0.9479262232780457} 08/31/2021 13:32:06 - INFO - __main__ - Step 134382: {'lr': 1.3614789597330896e-05, 'samples': 25801344, 'steps': 134381, 'loss/train': 1.0925382375717163} 08/31/2021 13:32:08 - INFO - __main__ - Step 134383: {'lr': 1.3613062286823241e-05, 'samples': 25801536, 'steps': 134382, 'loss/train': 1.2094693183898926} 08/31/2021 13:32:09 - INFO - __main__ - Step 134384: {'lr': 1.3611335082827886e-05, 'samples': 25801728, 'steps': 134383, 'loss/train': 1.1501463651657104} 08/31/2021 13:32:09 - INFO - __main__ - Step 134385: {'lr': 1.3609607985345662e-05, 'samples': 25801920, 'steps': 134384, 'loss/train': 0.4669777750968933} 08/31/2021 13:32:09 - INFO - __main__ - Step 134386: {'lr': 1.3607880994377263e-05, 'samples': 25802112, 'steps': 134385, 'loss/train': 0.824126124382019} 08/31/2021 13:32:10 - INFO - __main__ - Step 134387: {'lr': 1.3606154109923497e-05, 'samples': 25802304, 'steps': 134386, 'loss/train': 2.292834758758545} 08/31/2021 13:32:10 - INFO - __main__ - Step 134388: {'lr': 1.3604427331985164e-05, 'samples': 25802496, 'steps': 134387, 'loss/train': 0.9932125210762024} 08/31/2021 13:32:12 - INFO - __main__ - Step 134389: {'lr': 1.3602700660563017e-05, 'samples': 25802688, 'steps': 134388, 'loss/train': 1.2156485319137573} 08/31/2021 13:32:12 - INFO - __main__ - Step 134390: {'lr': 1.3600974095657858e-05, 'samples': 25802880, 'steps': 134389, 'loss/train': 0.11394283920526505} 08/31/2021 13:32:12 - INFO - __main__ - Step 134391: {'lr': 1.3599247637270439e-05, 'samples': 25803072, 'steps': 134390, 'loss/train': 1.041619062423706} 08/31/2021 13:32:13 - INFO - __main__ - Step 134392: {'lr': 1.3597521285401537e-05, 'samples': 25803264, 'steps': 134391, 'loss/train': 0.9590613842010498} 08/31/2021 13:32:13 - INFO - __main__ - Step 134393: {'lr': 1.3595795040051955e-05, 'samples': 25803456, 'steps': 134392, 'loss/train': 0.5973158478736877} 08/31/2021 13:32:15 - INFO - __main__ - Step 134394: {'lr': 1.3594068901222473e-05, 'samples': 25803648, 'steps': 134393, 'loss/train': 1.3811193704605103} 08/31/2021 13:32:15 - INFO - __main__ - Step 134395: {'lr': 1.3592342868913865e-05, 'samples': 25803840, 'steps': 134394, 'loss/train': 0.9401912689208984} 08/31/2021 13:32:16 - INFO - __main__ - Step 134396: {'lr': 1.3590616943126882e-05, 'samples': 25804032, 'steps': 134395, 'loss/train': 0.048860661685466766} 08/31/2021 13:32:16 - INFO - __main__ - Step 134397: {'lr': 1.3588891123862302e-05, 'samples': 25804224, 'steps': 134396, 'loss/train': 0.7757488489151001} 08/31/2021 13:32:16 - INFO - __main__ - Step 134398: {'lr': 1.3587165411120928e-05, 'samples': 25804416, 'steps': 134397, 'loss/train': 0.6522145867347717} 08/31/2021 13:32:18 - INFO - __main__ - Step 134399: {'lr': 1.3585439804903594e-05, 'samples': 25804608, 'steps': 134398, 'loss/train': 1.105654001235962} 08/31/2021 13:32:18 - INFO - __main__ - Step 134400: {'lr': 1.3583714305210936e-05, 'samples': 25804800, 'steps': 134399, 'loss/train': 1.0318080186843872} 08/31/2021 13:32:19 - INFO - __main__ - Step 134401: {'lr': 1.3581988912043846e-05, 'samples': 25804992, 'steps': 134400, 'loss/train': 0.48139292001724243} 08/31/2021 13:32:19 - INFO - __main__ - Step 134402: {'lr': 1.3580263625403044e-05, 'samples': 25805184, 'steps': 134401, 'loss/train': 1.523836374282837} 08/31/2021 13:32:20 - INFO - __main__ - Step 134403: {'lr': 1.3578538445289335e-05, 'samples': 25805376, 'steps': 134402, 'loss/train': 0.6668751835823059} 08/31/2021 13:32:21 - INFO - __main__ - Step 134404: {'lr': 1.3576813371703467e-05, 'samples': 25805568, 'steps': 134403, 'loss/train': 1.3880343437194824} 08/31/2021 13:32:22 - INFO - __main__ - Step 134405: {'lr': 1.3575088404646274e-05, 'samples': 25805760, 'steps': 134404, 'loss/train': 1.437640905380249} 08/31/2021 13:32:22 - INFO - __main__ - Step 134406: {'lr': 1.3573363544118478e-05, 'samples': 25805952, 'steps': 134405, 'loss/train': 1.31838858127594} 08/31/2021 13:32:22 - INFO - __main__ - Step 134407: {'lr': 1.3571638790120856e-05, 'samples': 25806144, 'steps': 134406, 'loss/train': 0.9146428108215332} 08/31/2021 13:32:23 - INFO - __main__ - Step 134408: {'lr': 1.3569914142654238e-05, 'samples': 25806336, 'steps': 134407, 'loss/train': 1.1997863054275513} 08/31/2021 13:32:24 - INFO - __main__ - Step 134409: {'lr': 1.356818960171935e-05, 'samples': 25806528, 'steps': 134408, 'loss/train': 1.183909296989441} 08/31/2021 13:32:25 - INFO - __main__ - Step 134410: {'lr': 1.3566465167316994e-05, 'samples': 25806720, 'steps': 134409, 'loss/train': 1.3403520584106445} 08/31/2021 13:32:25 - INFO - __main__ - Step 134411: {'lr': 1.3564740839447947e-05, 'samples': 25806912, 'steps': 134410, 'loss/train': 1.8986001014709473} 08/31/2021 13:32:25 - INFO - __main__ - Step 134412: {'lr': 1.3563016618113017e-05, 'samples': 25807104, 'steps': 134411, 'loss/train': 0.3145422339439392} 08/31/2021 13:32:26 - INFO - __main__ - Step 134413: {'lr': 1.3561292503312894e-05, 'samples': 25807296, 'steps': 134412, 'loss/train': 0.8417456150054932} 08/31/2021 13:32:26 - INFO - __main__ - Step 134414: {'lr': 1.3559568495048413e-05, 'samples': 25807488, 'steps': 134413, 'loss/train': 1.0840330123901367} 08/31/2021 13:32:28 - INFO - __main__ - Step 134415: {'lr': 1.3557844593320323e-05, 'samples': 25807680, 'steps': 134414, 'loss/train': 1.011874794960022} 08/31/2021 13:32:28 - INFO - __main__ - Step 134416: {'lr': 1.3556120798129429e-05, 'samples': 25807872, 'steps': 134415, 'loss/train': 1.220414638519287} 08/31/2021 13:32:28 - INFO - __main__ - Step 134417: {'lr': 1.3554397109476507e-05, 'samples': 25808064, 'steps': 134416, 'loss/train': 0.022013360634446144} 08/31/2021 13:32:29 - INFO - __main__ - Step 134418: {'lr': 1.3552673527362336e-05, 'samples': 25808256, 'steps': 134417, 'loss/train': 0.693495512008667} 08/31/2021 13:32:29 - INFO - __main__ - Step 134419: {'lr': 1.3550950051787663e-05, 'samples': 25808448, 'steps': 134418, 'loss/train': 0.9891164302825928} 08/31/2021 13:32:31 - INFO - __main__ - Step 134420: {'lr': 1.3549226682753296e-05, 'samples': 25808640, 'steps': 134419, 'loss/train': 0.41076934337615967} 08/31/2021 13:32:32 - INFO - __main__ - Step 134421: {'lr': 1.3547503420259983e-05, 'samples': 25808832, 'steps': 134420, 'loss/train': 0.2961575388908386} 08/31/2021 13:32:32 - INFO - __main__ - Step 134422: {'lr': 1.3545780264308527e-05, 'samples': 25809024, 'steps': 134421, 'loss/train': 1.1125514507293701} 08/31/2021 13:32:32 - INFO - __main__ - Step 134423: {'lr': 1.3544057214899679e-05, 'samples': 25809216, 'steps': 134422, 'loss/train': 1.7688384056091309} 08/31/2021 13:32:33 - INFO - __main__ - Step 134424: {'lr': 1.3542334272034245e-05, 'samples': 25809408, 'steps': 134423, 'loss/train': 1.2539355754852295} 08/31/2021 13:32:34 - INFO - __main__ - Step 134425: {'lr': 1.3540611435712974e-05, 'samples': 25809600, 'steps': 134424, 'loss/train': 1.6216052770614624} 08/31/2021 13:32:35 - INFO - __main__ - Step 134426: {'lr': 1.3538888705936697e-05, 'samples': 25809792, 'steps': 134425, 'loss/train': 1.3228037357330322} 08/31/2021 13:32:35 - INFO - __main__ - Step 134427: {'lr': 1.3537166082706137e-05, 'samples': 25809984, 'steps': 134426, 'loss/train': 0.44239529967308044} 08/31/2021 13:32:35 - INFO - __main__ - Step 134428: {'lr': 1.3535443566022044e-05, 'samples': 25810176, 'steps': 134427, 'loss/train': 1.1063587665557861} 08/31/2021 13:32:36 - INFO - __main__ - Step 134429: {'lr': 1.3533721155885248e-05, 'samples': 25810368, 'steps': 134428, 'loss/train': 0.914074182510376} 08/31/2021 13:32:37 - INFO - __main__ - Step 134430: {'lr': 1.3531998852296501e-05, 'samples': 25810560, 'steps': 134429, 'loss/train': 0.6317549347877502} 08/31/2021 13:32:38 - INFO - __main__ - Step 134431: {'lr': 1.3530276655256607e-05, 'samples': 25810752, 'steps': 134430, 'loss/train': 1.4275950193405151} 08/31/2021 13:32:38 - INFO - __main__ - Step 134432: {'lr': 1.3528554564766287e-05, 'samples': 25810944, 'steps': 134431, 'loss/train': 0.99756920337677} 08/31/2021 13:32:38 - INFO - __main__ - Step 134433: {'lr': 1.3526832580826375e-05, 'samples': 25811136, 'steps': 134432, 'loss/train': 1.5944019556045532} 08/31/2021 13:32:39 - INFO - __main__ - Step 134434: {'lr': 1.3525110703437621e-05, 'samples': 25811328, 'steps': 134433, 'loss/train': 1.2932484149932861} 08/31/2021 13:32:40 - INFO - __main__ - Step 134435: {'lr': 1.35233889326008e-05, 'samples': 25811520, 'steps': 134434, 'loss/train': 1.2138556241989136} 08/31/2021 13:32:41 - INFO - __main__ - Step 134436: {'lr': 1.352166726831669e-05, 'samples': 25811712, 'steps': 134435, 'loss/train': 0.6655473709106445} 08/31/2021 13:32:41 - INFO - __main__ - Step 134437: {'lr': 1.3519945710586067e-05, 'samples': 25811904, 'steps': 134436, 'loss/train': 1.319716453552246} 08/31/2021 13:32:42 - INFO - __main__ - Step 134438: {'lr': 1.3518224259409711e-05, 'samples': 25812096, 'steps': 134437, 'loss/train': 0.8992127180099487} 08/31/2021 13:32:42 - INFO - __main__ - Step 134439: {'lr': 1.3516502914788426e-05, 'samples': 25812288, 'steps': 134438, 'loss/train': 0.7963042259216309} 08/31/2021 13:32:42 - INFO - __main__ - Step 134440: {'lr': 1.3514781676722932e-05, 'samples': 25812480, 'steps': 134439, 'loss/train': 0.7300517559051514} 08/31/2021 13:32:44 - INFO - __main__ - Step 134441: {'lr': 1.3513060545214034e-05, 'samples': 25812672, 'steps': 134440, 'loss/train': 0.3075793385505676} 08/31/2021 13:32:44 - INFO - __main__ - Step 134442: {'lr': 1.3511339520262484e-05, 'samples': 25812864, 'steps': 134441, 'loss/train': 0.7031787633895874} 08/31/2021 13:32:44 - INFO - __main__ - Step 134443: {'lr': 1.3509618601869055e-05, 'samples': 25813056, 'steps': 134442, 'loss/train': 0.6728659868240356} 08/31/2021 13:32:45 - INFO - __main__ - Step 134444: {'lr': 1.3507897790034584e-05, 'samples': 25813248, 'steps': 134443, 'loss/train': 0.4835737347602844} 08/31/2021 13:32:45 - INFO - __main__ - Step 134445: {'lr': 1.350617708475979e-05, 'samples': 25813440, 'steps': 134444, 'loss/train': 1.4857960939407349} 08/31/2021 13:32:47 - INFO - __main__ - Step 134446: {'lr': 1.3504456486045453e-05, 'samples': 25813632, 'steps': 134445, 'loss/train': 0.7926630973815918} 08/31/2021 13:32:47 - INFO - __main__ - Step 134447: {'lr': 1.3502735993892373e-05, 'samples': 25813824, 'steps': 134446, 'loss/train': 1.1393322944641113} 08/31/2021 13:32:48 - INFO - __main__ - Step 134448: {'lr': 1.3501015608301303e-05, 'samples': 25814016, 'steps': 134447, 'loss/train': 0.8489059805870056} 08/31/2021 13:32:48 - INFO - __main__ - Step 134449: {'lr': 1.349929532927302e-05, 'samples': 25814208, 'steps': 134448, 'loss/train': 0.19484208524227142} 08/31/2021 13:32:48 - INFO - __main__ - Step 134450: {'lr': 1.34975751568083e-05, 'samples': 25814400, 'steps': 134449, 'loss/train': 1.2542155981063843} 08/31/2021 13:32:50 - INFO - __main__ - Step 134451: {'lr': 1.349585509090795e-05, 'samples': 25814592, 'steps': 134450, 'loss/train': 1.1947839260101318} 08/31/2021 13:32:50 - INFO - __main__ - Step 134452: {'lr': 1.3494135131572688e-05, 'samples': 25814784, 'steps': 134451, 'loss/train': 1.5899388790130615} 08/31/2021 13:32:51 - INFO - __main__ - Step 134453: {'lr': 1.3492415278803377e-05, 'samples': 25814976, 'steps': 134452, 'loss/train': 0.6256320476531982} 08/31/2021 13:32:51 - INFO - __main__ - Step 134454: {'lr': 1.3490695532600682e-05, 'samples': 25815168, 'steps': 134453, 'loss/train': 1.463537335395813} 08/31/2021 13:32:51 - INFO - __main__ - Step 134455: {'lr': 1.3488975892965439e-05, 'samples': 25815360, 'steps': 134454, 'loss/train': 1.3890820741653442} 08/31/2021 13:32:53 - INFO - __main__ - Step 134456: {'lr': 1.348725635989842e-05, 'samples': 25815552, 'steps': 134455, 'loss/train': 0.10739913582801819} 08/31/2021 13:32:53 - INFO - __main__ - Step 134457: {'lr': 1.3485536933400377e-05, 'samples': 25815744, 'steps': 134456, 'loss/train': 0.6229374408721924} 08/31/2021 13:32:54 - INFO - __main__ - Step 134458: {'lr': 1.3483817613472116e-05, 'samples': 25815936, 'steps': 134457, 'loss/train': 1.2981632947921753} 08/31/2021 13:32:54 - INFO - __main__ - Step 134459: {'lr': 1.3482098400114384e-05, 'samples': 25816128, 'steps': 134458, 'loss/train': 1.348510980606079} 08/31/2021 13:32:54 - INFO - __main__ - Step 134460: {'lr': 1.3480379293327987e-05, 'samples': 25816320, 'steps': 134459, 'loss/train': 0.6424626111984253} 08/31/2021 13:32:55 - INFO - __main__ - Step 134461: {'lr': 1.3478660293113675e-05, 'samples': 25816512, 'steps': 134460, 'loss/train': 0.9592819809913635} 08/31/2021 13:32:56 - INFO - __main__ - Step 134462: {'lr': 1.3476941399472226e-05, 'samples': 25816704, 'steps': 134461, 'loss/train': 2.0402960777282715} 08/31/2021 13:32:57 - INFO - __main__ - Step 134463: {'lr': 1.3475222612404414e-05, 'samples': 25816896, 'steps': 134462, 'loss/train': 0.5045626759529114} 08/31/2021 13:32:57 - INFO - __main__ - Step 134464: {'lr': 1.347350393191102e-05, 'samples': 25817088, 'steps': 134463, 'loss/train': 0.38385868072509766} 08/31/2021 13:32:58 - INFO - __main__ - Step 134465: {'lr': 1.3471785357992816e-05, 'samples': 25817280, 'steps': 134464, 'loss/train': 1.1613019704818726} 08/31/2021 13:32:58 - INFO - __main__ - Step 134466: {'lr': 1.3470066890650611e-05, 'samples': 25817472, 'steps': 134465, 'loss/train': 1.1770503520965576} 08/31/2021 13:32:59 - INFO - __main__ - Step 134467: {'lr': 1.34683485298851e-05, 'samples': 25817664, 'steps': 134466, 'loss/train': 1.1411583423614502} 08/31/2021 13:33:00 - INFO - __main__ - Step 134468: {'lr': 1.3466630275697111e-05, 'samples': 25817856, 'steps': 134467, 'loss/train': 1.032971978187561} 08/31/2021 13:33:00 - INFO - __main__ - Step 134469: {'lr': 1.3464912128087426e-05, 'samples': 25818048, 'steps': 134468, 'loss/train': 1.3441811800003052} 08/31/2021 13:33:01 - INFO - __main__ - Step 134470: {'lr': 1.3463194087056763e-05, 'samples': 25818240, 'steps': 134469, 'loss/train': 0.31833118200302124} 08/31/2021 13:33:01 - INFO - __main__ - Step 134471: {'lr': 1.3461476152605956e-05, 'samples': 25818432, 'steps': 134470, 'loss/train': 1.1933516263961792} 08/31/2021 13:33:03 - INFO - __main__ - Step 134472: {'lr': 1.3459758324735755e-05, 'samples': 25818624, 'steps': 134471, 'loss/train': 0.5610837340354919} 08/31/2021 13:33:03 - INFO - __main__ - Step 134473: {'lr': 1.3458040603446936e-05, 'samples': 25818816, 'steps': 134472, 'loss/train': 1.3380132913589478} 08/31/2021 13:33:04 - INFO - __main__ - Step 134474: {'lr': 1.3456322988740277e-05, 'samples': 25819008, 'steps': 134473, 'loss/train': 0.5563392639160156} 08/31/2021 13:33:04 - INFO - __main__ - Step 134475: {'lr': 1.3454605480616556e-05, 'samples': 25819200, 'steps': 134474, 'loss/train': 1.2366242408752441} 08/31/2021 13:33:04 - INFO - __main__ - Step 134476: {'lr': 1.345288807907652e-05, 'samples': 25819392, 'steps': 134475, 'loss/train': 1.3628097772598267} 08/31/2021 13:33:06 - INFO - __main__ - Step 134477: {'lr': 1.3451170784120975e-05, 'samples': 25819584, 'steps': 134476, 'loss/train': 1.2931536436080933} 08/31/2021 13:33:06 - INFO - __main__ - Step 134478: {'lr': 1.34494535957507e-05, 'samples': 25819776, 'steps': 134477, 'loss/train': 0.551205039024353} 08/31/2021 13:33:07 - INFO - __main__ - Step 134479: {'lr': 1.3447736513966413e-05, 'samples': 25819968, 'steps': 134478, 'loss/train': 0.8314157128334045} 08/31/2021 13:33:07 - INFO - __main__ - Step 134480: {'lr': 1.3446019538768977e-05, 'samples': 25820160, 'steps': 134479, 'loss/train': 0.9709104895591736} 08/31/2021 13:33:07 - INFO - __main__ - Step 134481: {'lr': 1.3444302670159086e-05, 'samples': 25820352, 'steps': 134480, 'loss/train': 1.4277395009994507} 08/31/2021 13:33:09 - INFO - __main__ - Step 134482: {'lr': 1.3442585908137545e-05, 'samples': 25820544, 'steps': 134481, 'loss/train': 0.9301655292510986} 08/31/2021 13:33:09 - INFO - __main__ - Step 134483: {'lr': 1.3440869252705101e-05, 'samples': 25820736, 'steps': 134482, 'loss/train': 0.3151218593120575} 08/31/2021 13:33:10 - INFO - __main__ - Step 134484: {'lr': 1.3439152703862589e-05, 'samples': 25820928, 'steps': 134483, 'loss/train': 0.06252598762512207} 08/31/2021 13:33:10 - INFO - __main__ - Step 134485: {'lr': 1.3437436261610703e-05, 'samples': 25821120, 'steps': 134484, 'loss/train': 1.1897178888320923} 08/31/2021 13:33:10 - INFO - __main__ - Step 134486: {'lr': 1.3435719925950302e-05, 'samples': 25821312, 'steps': 134485, 'loss/train': 0.8515534996986389} 08/31/2021 13:33:12 - INFO - __main__ - Step 134487: {'lr': 1.343400369688208e-05, 'samples': 25821504, 'steps': 134486, 'loss/train': 1.1880955696105957} 08/31/2021 13:33:12 - INFO - __main__ - Step 134488: {'lr': 1.3432287574406843e-05, 'samples': 25821696, 'steps': 134487, 'loss/train': 1.0908123254776} 08/31/2021 13:33:13 - INFO - __main__ - Step 134489: {'lr': 1.3430571558525394e-05, 'samples': 25821888, 'steps': 134488, 'loss/train': 0.3796444833278656} 08/31/2021 13:33:13 - INFO - __main__ - Step 134490: {'lr': 1.3428855649238458e-05, 'samples': 25822080, 'steps': 134489, 'loss/train': 0.8148689270019531} 08/31/2021 13:33:13 - INFO - __main__ - Step 134491: {'lr': 1.3427139846546837e-05, 'samples': 25822272, 'steps': 134490, 'loss/train': 1.0697050094604492} 08/31/2021 13:33:14 - INFO - __main__ - Step 134492: {'lr': 1.342542415045131e-05, 'samples': 25822464, 'steps': 134491, 'loss/train': 0.9435605406761169} 08/31/2021 13:33:15 - INFO - __main__ - Step 134493: {'lr': 1.3423708560952652e-05, 'samples': 25822656, 'steps': 134492, 'loss/train': 0.8403096199035645} 08/31/2021 13:33:16 - INFO - __main__ - Step 134494: {'lr': 1.3421993078051586e-05, 'samples': 25822848, 'steps': 134493, 'loss/train': 0.03321538493037224} 08/31/2021 13:33:16 - INFO - __main__ - Step 134495: {'lr': 1.3420277701748917e-05, 'samples': 25823040, 'steps': 134494, 'loss/train': 1.1099960803985596} 08/31/2021 13:33:16 - INFO - __main__ - Step 134496: {'lr': 1.3418562432045423e-05, 'samples': 25823232, 'steps': 134495, 'loss/train': 1.1129261255264282} 08/31/2021 13:33:17 - INFO - __main__ - Step 134497: {'lr': 1.3416847268941879e-05, 'samples': 25823424, 'steps': 134496, 'loss/train': 0.2818503975868225} 08/31/2021 13:33:18 - INFO - __main__ - Step 134498: {'lr': 1.3415132212439062e-05, 'samples': 25823616, 'steps': 134497, 'loss/train': 1.2242255210876465} 08/31/2021 13:33:19 - INFO - __main__ - Step 134499: {'lr': 1.3413417262537726e-05, 'samples': 25823808, 'steps': 134498, 'loss/train': 0.5858686566352844} 08/31/2021 13:33:19 - INFO - __main__ - Step 134500: {'lr': 1.3411702419238642e-05, 'samples': 25824000, 'steps': 134499, 'loss/train': 1.1228643655776978} 08/31/2021 13:33:20 - INFO - __main__ - Step 134501: {'lr': 1.3409987682542618e-05, 'samples': 25824192, 'steps': 134500, 'loss/train': 1.5511223077774048} 08/31/2021 13:33:20 - INFO - __main__ - Step 134502: {'lr': 1.3408273052450377e-05, 'samples': 25824384, 'steps': 134501, 'loss/train': 1.1477477550506592} 08/31/2021 13:33:21 - INFO - __main__ - Step 134503: {'lr': 1.340655852896272e-05, 'samples': 25824576, 'steps': 134502, 'loss/train': 1.2474828958511353} 08/31/2021 13:33:22 - INFO - __main__ - Step 134504: {'lr': 1.3404844112080427e-05, 'samples': 25824768, 'steps': 134503, 'loss/train': 1.1470563411712646} 08/31/2021 13:33:22 - INFO - __main__ - Step 134505: {'lr': 1.3403129801804276e-05, 'samples': 25824960, 'steps': 134504, 'loss/train': 1.1331827640533447} 08/31/2021 13:33:23 - INFO - __main__ - Step 134506: {'lr': 1.3401415598135041e-05, 'samples': 25825152, 'steps': 134505, 'loss/train': 0.4027944505214691} 08/31/2021 13:33:23 - INFO - __main__ - Step 134507: {'lr': 1.3399701501073447e-05, 'samples': 25825344, 'steps': 134506, 'loss/train': 1.2190877199172974} 08/31/2021 13:33:23 - INFO - __main__ - Step 134508: {'lr': 1.3397987510620296e-05, 'samples': 25825536, 'steps': 134507, 'loss/train': 1.7393404245376587} 08/31/2021 13:33:25 - INFO - __main__ - Step 134509: {'lr': 1.339627362677634e-05, 'samples': 25825728, 'steps': 134508, 'loss/train': 1.3117800951004028} 08/31/2021 13:33:25 - INFO - __main__ - Step 134510: {'lr': 1.339455984954241e-05, 'samples': 25825920, 'steps': 134509, 'loss/train': 2.013531446456909} 08/31/2021 13:33:26 - INFO - __main__ - Step 134511: {'lr': 1.3392846178919228e-05, 'samples': 25826112, 'steps': 134510, 'loss/train': 0.6886078715324402} 08/31/2021 13:33:26 - INFO - __main__ - Step 134512: {'lr': 1.339113261490757e-05, 'samples': 25826304, 'steps': 134511, 'loss/train': 1.336059808731079} 08/31/2021 13:33:26 - INFO - __main__ - Step 134513: {'lr': 1.3389419157508216e-05, 'samples': 25826496, 'steps': 134512, 'loss/train': 1.6197097301483154} 08/31/2021 13:33:28 - INFO - __main__ - Step 134514: {'lr': 1.3387705806721939e-05, 'samples': 25826688, 'steps': 134513, 'loss/train': 1.2544735670089722} 08/31/2021 13:33:28 - INFO - __main__ - Step 134515: {'lr': 1.3385992562549493e-05, 'samples': 25826880, 'steps': 134514, 'loss/train': 0.7579228281974792} 08/31/2021 13:33:29 - INFO - __main__ - Step 134516: {'lr': 1.3384279424991708e-05, 'samples': 25827072, 'steps': 134515, 'loss/train': 0.3974343240261078} 08/31/2021 13:33:29 - INFO - __main__ - Step 134517: {'lr': 1.3382566394049278e-05, 'samples': 25827264, 'steps': 134516, 'loss/train': 0.6439520716667175} 08/31/2021 13:33:29 - INFO - __main__ - Step 134518: {'lr': 1.3380853469723036e-05, 'samples': 25827456, 'steps': 134517, 'loss/train': 0.8257202506065369} 08/31/2021 13:33:31 - INFO - __main__ - Step 134519: {'lr': 1.3379140652013733e-05, 'samples': 25827648, 'steps': 134518, 'loss/train': 0.35513025522232056} 08/31/2021 13:33:31 - INFO - __main__ - Step 134520: {'lr': 1.3377427940922144e-05, 'samples': 25827840, 'steps': 134519, 'loss/train': 0.11087910830974579} 08/31/2021 13:33:32 - INFO - __main__ - Step 134521: {'lr': 1.3375715336449018e-05, 'samples': 25828032, 'steps': 134520, 'loss/train': 0.8857956528663635} 08/31/2021 13:33:32 - INFO - __main__ - Step 134522: {'lr': 1.3374002838595162e-05, 'samples': 25828224, 'steps': 134521, 'loss/train': 1.1518886089324951} 08/31/2021 13:33:33 - INFO - __main__ - Step 134523: {'lr': 1.3372290447361296e-05, 'samples': 25828416, 'steps': 134522, 'loss/train': 0.8938639760017395} 08/31/2021 13:33:34 - INFO - __main__ - Step 134524: {'lr': 1.3370578162748253e-05, 'samples': 25828608, 'steps': 134523, 'loss/train': 1.0835877656936646} 08/31/2021 13:33:35 - INFO - __main__ - Step 134525: {'lr': 1.3368865984756756e-05, 'samples': 25828800, 'steps': 134524, 'loss/train': 1.2315317392349243} 08/31/2021 13:33:35 - INFO - __main__ - Step 134526: {'lr': 1.3367153913387609e-05, 'samples': 25828992, 'steps': 134525, 'loss/train': 0.7502816319465637} 08/31/2021 13:33:35 - INFO - __main__ - Step 134527: {'lr': 1.336544194864156e-05, 'samples': 25829184, 'steps': 134526, 'loss/train': 0.9027553200721741} 08/31/2021 13:33:36 - INFO - __main__ - Step 134528: {'lr': 1.3363730090519388e-05, 'samples': 25829376, 'steps': 134527, 'loss/train': 1.265799641609192} 08/31/2021 13:33:36 - INFO - __main__ - Step 134529: {'lr': 1.336201833902187e-05, 'samples': 25829568, 'steps': 134528, 'loss/train': 1.5015642642974854} 08/31/2021 13:33:38 - INFO - __main__ - Step 134530: {'lr': 1.3360306694149781e-05, 'samples': 25829760, 'steps': 134529, 'loss/train': 0.1228683739900589} 08/31/2021 13:33:39 - INFO - __main__ - Step 134531: {'lr': 1.3358595155903903e-05, 'samples': 25829952, 'steps': 134530, 'loss/train': 0.7940695881843567} 08/31/2021 13:33:39 - INFO - __main__ - Step 134532: {'lr': 1.3356883724284952e-05, 'samples': 25830144, 'steps': 134531, 'loss/train': 0.8757079243659973} 08/31/2021 13:33:39 - INFO - __main__ - Step 134533: {'lr': 1.3355172399293792e-05, 'samples': 25830336, 'steps': 134532, 'loss/train': 1.0327568054199219} 08/31/2021 13:33:40 - INFO - __main__ - Step 134534: {'lr': 1.3353461180931115e-05, 'samples': 25830528, 'steps': 134533, 'loss/train': 1.0691388845443726} 08/31/2021 13:33:41 - INFO - __main__ - Step 134535: {'lr': 1.3351750069197699e-05, 'samples': 25830720, 'steps': 134534, 'loss/train': 0.6037465333938599} 08/31/2021 13:33:42 - INFO - __main__ - Step 134536: {'lr': 1.3350039064094349e-05, 'samples': 25830912, 'steps': 134535, 'loss/train': 0.028610071167349815} 08/31/2021 13:33:42 - INFO - __main__ - Step 134537: {'lr': 1.3348328165621815e-05, 'samples': 25831104, 'steps': 134536, 'loss/train': 0.46074366569519043} 08/31/2021 13:33:43 - INFO - __main__ - Step 134538: {'lr': 1.3346617373780873e-05, 'samples': 25831296, 'steps': 134537, 'loss/train': 1.175595998764038} 08/31/2021 13:33:43 - INFO - __main__ - Step 134539: {'lr': 1.33449066885723e-05, 'samples': 25831488, 'steps': 134538, 'loss/train': 0.36922991275787354} 08/31/2021 13:33:44 - INFO - __main__ - Step 134540: {'lr': 1.3343196109996847e-05, 'samples': 25831680, 'steps': 134539, 'loss/train': 0.8215514421463013} 08/31/2021 13:33:45 - INFO - __main__ - Step 134541: {'lr': 1.3341485638055289e-05, 'samples': 25831872, 'steps': 134540, 'loss/train': 1.0331188440322876} 08/31/2021 13:33:45 - INFO - __main__ - Step 134542: {'lr': 1.3339775272748433e-05, 'samples': 25832064, 'steps': 134541, 'loss/train': 1.3777318000793457} 08/31/2021 13:33:45 - INFO - __main__ - Step 134543: {'lr': 1.3338065014077e-05, 'samples': 25832256, 'steps': 134542, 'loss/train': 1.1665059328079224} 08/31/2021 13:33:46 - INFO - __main__ - Step 134544: {'lr': 1.3336354862041794e-05, 'samples': 25832448, 'steps': 134543, 'loss/train': 1.1048457622528076} 08/31/2021 13:33:47 - INFO - __main__ - Step 134545: {'lr': 1.3334644816643565e-05, 'samples': 25832640, 'steps': 134544, 'loss/train': 1.0778334140777588} 08/31/2021 13:33:48 - INFO - __main__ - Step 134546: {'lr': 1.333293487788309e-05, 'samples': 25832832, 'steps': 134545, 'loss/train': 1.0911800861358643} 08/31/2021 13:33:48 - INFO - __main__ - Step 134547: {'lr': 1.3331225045761203e-05, 'samples': 25833024, 'steps': 134546, 'loss/train': 2.0573487281799316} 08/31/2021 13:33:49 - INFO - __main__ - Step 134548: {'lr': 1.3329515320278568e-05, 'samples': 25833216, 'steps': 134547, 'loss/train': 0.8564510345458984} 08/31/2021 13:33:49 - INFO - __main__ - Step 134549: {'lr': 1.3327805701435992e-05, 'samples': 25833408, 'steps': 134548, 'loss/train': 1.1969163417816162} 08/31/2021 13:33:49 - INFO - __main__ - Step 134550: {'lr': 1.3326096189234248e-05, 'samples': 25833600, 'steps': 134549, 'loss/train': 1.3200289011001587} 08/31/2021 13:33:51 - INFO - __main__ - Step 134551: {'lr': 1.3324386783674147e-05, 'samples': 25833792, 'steps': 134550, 'loss/train': 1.1921426057815552} 08/31/2021 13:33:51 - INFO - __main__ - Step 134552: {'lr': 1.3322677484756379e-05, 'samples': 25833984, 'steps': 134551, 'loss/train': 0.5277830958366394} 08/31/2021 13:33:52 - INFO - __main__ - Step 134553: {'lr': 1.3320968292481806e-05, 'samples': 25834176, 'steps': 134552, 'loss/train': 0.030479371547698975} 08/31/2021 13:33:52 - INFO - __main__ - Step 134554: {'lr': 1.331925920685112e-05, 'samples': 25834368, 'steps': 134553, 'loss/train': 1.310226321220398} 08/31/2021 13:33:52 - INFO - __main__ - Step 134555: {'lr': 1.3317550227865127e-05, 'samples': 25834560, 'steps': 134554, 'loss/train': 1.1006675958633423} 08/31/2021 13:33:54 - INFO - __main__ - Step 134556: {'lr': 1.3315841355524605e-05, 'samples': 25834752, 'steps': 134555, 'loss/train': 0.022071512416005135} 08/31/2021 13:33:54 - INFO - __main__ - Step 134557: {'lr': 1.3314132589830303e-05, 'samples': 25834944, 'steps': 134556, 'loss/train': 0.9663659334182739} 08/31/2021 13:33:55 - INFO - __main__ - Step 134558: {'lr': 1.3312423930783024e-05, 'samples': 25835136, 'steps': 134557, 'loss/train': 1.2647104263305664} 08/31/2021 13:33:55 - INFO - __main__ - Step 134559: {'lr': 1.331071537838352e-05, 'samples': 25835328, 'steps': 134558, 'loss/train': 0.11665669083595276} 08/31/2021 13:33:55 - INFO - __main__ - Step 134560: {'lr': 1.3309006932632539e-05, 'samples': 25835520, 'steps': 134559, 'loss/train': 1.1235517263412476} 08/31/2021 13:33:57 - INFO - __main__ - Step 134561: {'lr': 1.3307298593530858e-05, 'samples': 25835712, 'steps': 134560, 'loss/train': 1.3197507858276367} 08/31/2021 13:33:57 - INFO - __main__ - Step 134562: {'lr': 1.3305590361079255e-05, 'samples': 25835904, 'steps': 134561, 'loss/train': 1.4014098644256592} 08/31/2021 13:33:58 - INFO - __main__ - Step 134563: {'lr': 1.3303882235278508e-05, 'samples': 25836096, 'steps': 134562, 'loss/train': 1.3501735925674438} 08/31/2021 13:33:58 - INFO - __main__ - Step 134564: {'lr': 1.3302174216129364e-05, 'samples': 25836288, 'steps': 134563, 'loss/train': 1.1522103548049927} 08/31/2021 13:33:59 - INFO - __main__ - Step 134565: {'lr': 1.330046630363263e-05, 'samples': 25836480, 'steps': 134564, 'loss/train': 1.2522155046463013} 08/31/2021 13:34:00 - INFO - __main__ - Step 134566: {'lr': 1.3298758497789026e-05, 'samples': 25836672, 'steps': 134565, 'loss/train': 1.1086757183074951} 08/31/2021 13:34:01 - INFO - __main__ - Step 134567: {'lr': 1.3297050798599358e-05, 'samples': 25836864, 'steps': 134566, 'loss/train': 1.1807193756103516} 08/31/2021 13:34:01 - INFO - __main__ - Step 134568: {'lr': 1.3295343206064402e-05, 'samples': 25837056, 'steps': 134567, 'loss/train': 0.9575470685958862} 08/31/2021 13:34:01 - INFO - __main__ - Step 134569: {'lr': 1.329363572018491e-05, 'samples': 25837248, 'steps': 134568, 'loss/train': 0.07983656972646713} 08/31/2021 13:34:02 - INFO - __main__ - Step 134570: {'lr': 1.3291928340961684e-05, 'samples': 25837440, 'steps': 134569, 'loss/train': 1.3979287147521973} 08/31/2021 13:34:03 - INFO - __main__ - Step 134571: {'lr': 1.329022106839542e-05, 'samples': 25837632, 'steps': 134570, 'loss/train': 1.2825361490249634} 08/31/2021 13:34:04 - INFO - __main__ - Step 134572: {'lr': 1.3288513902486921e-05, 'samples': 25837824, 'steps': 134571, 'loss/train': 1.0814695358276367} 08/31/2021 13:34:04 - INFO - __main__ - Step 134573: {'lr': 1.3286806843236992e-05, 'samples': 25838016, 'steps': 134572, 'loss/train': 0.7359470129013062} 08/31/2021 13:34:04 - INFO - __main__ - Step 134574: {'lr': 1.3285099890646357e-05, 'samples': 25838208, 'steps': 134573, 'loss/train': 0.5673866271972656} 08/31/2021 13:34:05 - INFO - __main__ - Step 134575: {'lr': 1.328339304471579e-05, 'samples': 25838400, 'steps': 134574, 'loss/train': 0.9659433960914612} 08/31/2021 13:34:06 - INFO - __main__ - Step 134576: {'lr': 1.32816863054461e-05, 'samples': 25838592, 'steps': 134575, 'loss/train': 0.12455343455076218} 08/31/2021 13:34:07 - INFO - __main__ - Step 134577: {'lr': 1.3279979672838032e-05, 'samples': 25838784, 'steps': 134576, 'loss/train': 0.8475257754325867} 08/31/2021 13:34:07 - INFO - __main__ - Step 134578: {'lr': 1.327827314689234e-05, 'samples': 25838976, 'steps': 134577, 'loss/train': 1.3809924125671387} 08/31/2021 13:34:07 - INFO - __main__ - Step 134579: {'lr': 1.3276566727609795e-05, 'samples': 25839168, 'steps': 134578, 'loss/train': 0.7923104166984558} 08/31/2021 13:34:08 - INFO - __main__ - Step 134580: {'lr': 1.327486041499118e-05, 'samples': 25839360, 'steps': 134579, 'loss/train': 0.8423756957054138} 08/31/2021 13:34:10 - INFO - __main__ - Step 134581: {'lr': 1.3273154209037297e-05, 'samples': 25839552, 'steps': 134580, 'loss/train': 1.4909114837646484} 08/31/2021 13:34:10 - INFO - __main__ - Step 134582: {'lr': 1.3271448109748867e-05, 'samples': 25839744, 'steps': 134581, 'loss/train': 0.706905722618103} 08/31/2021 13:34:11 - INFO - __main__ - Step 134583: {'lr': 1.3269742117126643e-05, 'samples': 25839936, 'steps': 134582, 'loss/train': 0.9231031537055969} 08/31/2021 13:34:11 - INFO - __main__ - Step 134584: {'lr': 1.3268036231171426e-05, 'samples': 25840128, 'steps': 134583, 'loss/train': 2.568499803543091} 08/31/2021 13:34:12 - INFO - __main__ - Step 134585: {'lr': 1.3266330451883969e-05, 'samples': 25840320, 'steps': 134584, 'loss/train': 1.2869038581848145} 08/31/2021 13:34:13 - INFO - __main__ - Step 134586: {'lr': 1.3264624779265072e-05, 'samples': 25840512, 'steps': 134585, 'loss/train': 0.030968179926276207} 08/31/2021 13:34:14 - INFO - __main__ - Step 134587: {'lr': 1.3262919213315461e-05, 'samples': 25840704, 'steps': 134586, 'loss/train': 1.4960037469863892} 08/31/2021 13:34:14 - INFO - __main__ - Step 134588: {'lr': 1.326121375403594e-05, 'samples': 25840896, 'steps': 134587, 'loss/train': 1.2075605392456055} 08/31/2021 13:34:14 - INFO - __main__ - Step 134589: {'lr': 1.3259508401427256e-05, 'samples': 25841088, 'steps': 134588, 'loss/train': 1.5824766159057617} 08/31/2021 13:34:15 - INFO - __main__ - Step 134590: {'lr': 1.3257803155490189e-05, 'samples': 25841280, 'steps': 134589, 'loss/train': 1.1429675817489624} 08/31/2021 13:34:15 - INFO - __main__ - Step 134591: {'lr': 1.3256098016225515e-05, 'samples': 25841472, 'steps': 134590, 'loss/train': 1.0325384140014648} 08/31/2021 13:34:16 - INFO - __main__ - Step 134592: {'lr': 1.3254392983634011e-05, 'samples': 25841664, 'steps': 134591, 'loss/train': 0.6065639853477478} 08/31/2021 13:34:17 - INFO - __main__ - Step 134593: {'lr': 1.3252688057716373e-05, 'samples': 25841856, 'steps': 134592, 'loss/train': 0.9532577991485596} 08/31/2021 13:34:17 - INFO - __main__ - Step 134594: {'lr': 1.3250983238473457e-05, 'samples': 25842048, 'steps': 134593, 'loss/train': 0.8003973960876465} 08/31/2021 13:34:18 - INFO - __main__ - Step 134595: {'lr': 1.324927852590596e-05, 'samples': 25842240, 'steps': 134594, 'loss/train': 0.5656938552856445} 08/31/2021 13:34:18 - INFO - __main__ - Step 134596: {'lr': 1.3247573920014717e-05, 'samples': 25842432, 'steps': 134595, 'loss/train': 0.9400280117988586} 08/31/2021 13:34:19 - INFO - __main__ - Step 134597: {'lr': 1.3245869420800444e-05, 'samples': 25842624, 'steps': 134596, 'loss/train': 0.5258284211158752} 08/31/2021 13:34:20 - INFO - __main__ - Step 134598: {'lr': 1.3244165028263921e-05, 'samples': 25842816, 'steps': 134597, 'loss/train': 0.32799309492111206} 08/31/2021 13:34:20 - INFO - __main__ - Step 134599: {'lr': 1.3242460742405926e-05, 'samples': 25843008, 'steps': 134598, 'loss/train': 1.5113422870635986} 08/31/2021 13:34:21 - INFO - __main__ - Step 134600: {'lr': 1.3240756563227235e-05, 'samples': 25843200, 'steps': 134599, 'loss/train': 1.2846819162368774} 08/31/2021 13:34:21 - INFO - __main__ - Step 134601: {'lr': 1.3239052490728626e-05, 'samples': 25843392, 'steps': 134600, 'loss/train': 1.303511381149292} 08/31/2021 13:34:23 - INFO - __main__ - Step 134602: {'lr': 1.323734852491082e-05, 'samples': 25843584, 'steps': 134601, 'loss/train': 1.424614667892456} 08/31/2021 13:34:23 - INFO - __main__ - Step 134603: {'lr': 1.3235644665774649e-05, 'samples': 25843776, 'steps': 134602, 'loss/train': 1.0310808420181274} 08/31/2021 13:34:23 - INFO - __main__ - Step 134604: {'lr': 1.3233940913320807e-05, 'samples': 25843968, 'steps': 134603, 'loss/train': 1.1162810325622559} 08/31/2021 13:34:24 - INFO - __main__ - Step 134605: {'lr': 1.3232237267550101e-05, 'samples': 25844160, 'steps': 134604, 'loss/train': 1.3771334886550903} 08/31/2021 13:34:24 - INFO - __main__ - Step 134606: {'lr': 1.3230533728463278e-05, 'samples': 25844352, 'steps': 134605, 'loss/train': 0.8888475298881531} 08/31/2021 13:34:24 - INFO - __main__ - Step 134607: {'lr': 1.3228830296061146e-05, 'samples': 25844544, 'steps': 134606, 'loss/train': 1.681575059890747} 08/31/2021 13:34:26 - INFO - __main__ - Step 134608: {'lr': 1.322712697034445e-05, 'samples': 25844736, 'steps': 134607, 'loss/train': 0.2701950669288635} 08/31/2021 13:34:27 - INFO - __main__ - Step 134609: {'lr': 1.3225423751313942e-05, 'samples': 25844928, 'steps': 134608, 'loss/train': 1.4456281661987305} 08/31/2021 13:34:27 - INFO - __main__ - Step 134610: {'lr': 1.3223720638970427e-05, 'samples': 25845120, 'steps': 134609, 'loss/train': 1.3963900804519653} 08/31/2021 13:34:27 - INFO - __main__ - Step 134611: {'lr': 1.3222017633314625e-05, 'samples': 25845312, 'steps': 134610, 'loss/train': 2.2522809505462646} 08/31/2021 13:34:28 - INFO - __main__ - Step 134612: {'lr': 1.3220314734347344e-05, 'samples': 25845504, 'steps': 134611, 'loss/train': 0.3060915470123291} 08/31/2021 13:34:29 - INFO - __main__ - Step 134613: {'lr': 1.321861194206933e-05, 'samples': 25845696, 'steps': 134612, 'loss/train': 0.5765758752822876} 08/31/2021 13:34:30 - INFO - __main__ - Step 134614: {'lr': 1.321690925648139e-05, 'samples': 25845888, 'steps': 134613, 'loss/train': 1.1796988248825073} 08/31/2021 13:34:30 - INFO - __main__ - Step 134615: {'lr': 1.3215206677584218e-05, 'samples': 25846080, 'steps': 134614, 'loss/train': 1.0129297971725464} 08/31/2021 13:34:30 - INFO - __main__ - Step 134616: {'lr': 1.3213504205378617e-05, 'samples': 25846272, 'steps': 134615, 'loss/train': 0.08304611593484879} 08/31/2021 13:34:31 - INFO - __main__ - Step 134617: {'lr': 1.3211801839865367e-05, 'samples': 25846464, 'steps': 134616, 'loss/train': 1.33170747756958} 08/31/2021 13:34:32 - INFO - __main__ - Step 134618: {'lr': 1.3210099581045215e-05, 'samples': 25846656, 'steps': 134617, 'loss/train': 0.17397044599056244} 08/31/2021 13:34:33 - INFO - __main__ - Step 134619: {'lr': 1.3208397428918967e-05, 'samples': 25846848, 'steps': 134618, 'loss/train': 1.4122259616851807} 08/31/2021 13:34:33 - INFO - __main__ - Step 134620: {'lr': 1.3206695383487343e-05, 'samples': 25847040, 'steps': 134619, 'loss/train': 0.42388683557510376} 08/31/2021 13:34:34 - INFO - __main__ - Step 134621: {'lr': 1.3204993444751123e-05, 'samples': 25847232, 'steps': 134620, 'loss/train': 0.7644489407539368} 08/31/2021 13:34:34 - INFO - __main__ - Step 134622: {'lr': 1.3203291612711082e-05, 'samples': 25847424, 'steps': 134621, 'loss/train': 3.4937448501586914} 08/31/2021 13:34:35 - INFO - __main__ - Step 134623: {'lr': 1.320158988736797e-05, 'samples': 25847616, 'steps': 134622, 'loss/train': 1.1739516258239746} 08/31/2021 13:34:36 - INFO - __main__ - Step 134624: {'lr': 1.3199888268722593e-05, 'samples': 25847808, 'steps': 134623, 'loss/train': 1.1342331171035767} 08/31/2021 13:34:36 - INFO - __main__ - Step 134625: {'lr': 1.3198186756775671e-05, 'samples': 25848000, 'steps': 134624, 'loss/train': 1.1858975887298584} 08/31/2021 13:34:37 - INFO - __main__ - Step 134626: {'lr': 1.319648535152801e-05, 'samples': 25848192, 'steps': 134625, 'loss/train': 1.303472876548767} 08/31/2021 13:34:37 - INFO - __main__ - Step 134627: {'lr': 1.3194784052980385e-05, 'samples': 25848384, 'steps': 134626, 'loss/train': 1.4650691747665405} 08/31/2021 13:34:38 - INFO - __main__ - Step 134628: {'lr': 1.3193082861133493e-05, 'samples': 25848576, 'steps': 134627, 'loss/train': 1.3606209754943848} 08/31/2021 13:34:39 - INFO - __main__ - Step 134629: {'lr': 1.3191381775988137e-05, 'samples': 25848768, 'steps': 134628, 'loss/train': 0.891791582107544} 08/31/2021 13:34:39 - INFO - __main__ - Step 134630: {'lr': 1.3189680797545122e-05, 'samples': 25848960, 'steps': 134629, 'loss/train': 1.4199479818344116} 08/31/2021 13:34:40 - INFO - __main__ - Step 134631: {'lr': 1.318797992580517e-05, 'samples': 25849152, 'steps': 134630, 'loss/train': 1.3548189401626587} 08/31/2021 13:34:40 - INFO - __main__ - Step 134632: {'lr': 1.3186279160769032e-05, 'samples': 25849344, 'steps': 134631, 'loss/train': 1.3058186769485474} 08/31/2021 13:34:42 - INFO - __main__ - Step 134633: {'lr': 1.318457850243754e-05, 'samples': 25849536, 'steps': 134632, 'loss/train': 0.41225215792655945} 08/31/2021 13:34:43 - INFO - __main__ - Step 134634: {'lr': 1.3182877950811411e-05, 'samples': 25849728, 'steps': 134633, 'loss/train': 0.7644600868225098} 08/31/2021 13:34:43 - INFO - __main__ - Step 134635: {'lr': 1.3181177505891428e-05, 'samples': 25849920, 'steps': 134634, 'loss/train': 0.4401724338531494} 08/31/2021 13:34:43 - INFO - __main__ - Step 134636: {'lr': 1.317947716767834e-05, 'samples': 25850112, 'steps': 134635, 'loss/train': 0.09695792198181152} 08/31/2021 13:34:44 - INFO - __main__ - Step 134637: {'lr': 1.317777693617292e-05, 'samples': 25850304, 'steps': 134636, 'loss/train': 0.9785136580467224} 08/31/2021 13:34:44 - INFO - __main__ - Step 134638: {'lr': 1.3176076811375947e-05, 'samples': 25850496, 'steps': 134637, 'loss/train': 1.1004153490066528} 08/31/2021 13:34:45 - INFO - __main__ - Step 134639: {'lr': 1.3174376793288173e-05, 'samples': 25850688, 'steps': 134638, 'loss/train': 0.9612694382667542} 08/31/2021 13:34:46 - INFO - __main__ - Step 134640: {'lr': 1.31726768819104e-05, 'samples': 25850880, 'steps': 134639, 'loss/train': 1.1641355752944946} 08/31/2021 13:34:46 - INFO - __main__ - Step 134641: {'lr': 1.317097707724338e-05, 'samples': 25851072, 'steps': 134640, 'loss/train': 0.8199245929718018} 08/31/2021 13:34:47 - INFO - __main__ - Step 134642: {'lr': 1.3169277379287803e-05, 'samples': 25851264, 'steps': 134641, 'loss/train': 1.1277422904968262} 08/31/2021 13:34:47 - INFO - __main__ - Step 134643: {'lr': 1.3167577788044532e-05, 'samples': 25851456, 'steps': 134642, 'loss/train': 1.4477523565292358} 08/31/2021 13:34:49 - INFO - __main__ - Step 134644: {'lr': 1.3165878303514289e-05, 'samples': 25851648, 'steps': 134643, 'loss/train': 0.5343971848487854} 08/31/2021 13:34:49 - INFO - __main__ - Step 134645: {'lr': 1.3164178925697824e-05, 'samples': 25851840, 'steps': 134644, 'loss/train': 1.3935662508010864} 08/31/2021 13:34:50 - INFO - __main__ - Step 134646: {'lr': 1.3162479654595938e-05, 'samples': 25852032, 'steps': 134645, 'loss/train': 0.5249430537223816} 08/31/2021 13:34:50 - INFO - __main__ - Step 134647: {'lr': 1.3160780490209384e-05, 'samples': 25852224, 'steps': 134646, 'loss/train': 0.7075803875923157} 08/31/2021 13:34:50 - INFO - __main__ - Step 134648: {'lr': 1.3159081432538939e-05, 'samples': 25852416, 'steps': 134647, 'loss/train': 0.13423852622509003} 08/31/2021 13:34:52 - INFO - __main__ - Step 134649: {'lr': 1.315738248158535e-05, 'samples': 25852608, 'steps': 134648, 'loss/train': 1.1554158926010132} 08/31/2021 13:34:52 - INFO - __main__ - Step 134650: {'lr': 1.3155683637349398e-05, 'samples': 25852800, 'steps': 134649, 'loss/train': 0.9494422674179077} 08/31/2021 13:34:53 - INFO - __main__ - Step 134651: {'lr': 1.3153984899831827e-05, 'samples': 25852992, 'steps': 134650, 'loss/train': 0.9152935743331909} 08/31/2021 13:34:53 - INFO - __main__ - Step 134652: {'lr': 1.315228626903342e-05, 'samples': 25853184, 'steps': 134651, 'loss/train': 1.000503420829773} 08/31/2021 13:34:53 - INFO - __main__ - Step 134653: {'lr': 1.3150587744954923e-05, 'samples': 25853376, 'steps': 134652, 'loss/train': 0.5895446538925171} 08/31/2021 13:34:55 - INFO - __main__ - Step 134654: {'lr': 1.3148889327597169e-05, 'samples': 25853568, 'steps': 134653, 'loss/train': 0.7341774702072144} 08/31/2021 13:34:55 - INFO - __main__ - Step 134655: {'lr': 1.3147191016960853e-05, 'samples': 25853760, 'steps': 134654, 'loss/train': 1.2366610765457153} 08/31/2021 13:34:56 - INFO - __main__ - Step 134656: {'lr': 1.3145492813046722e-05, 'samples': 25853952, 'steps': 134655, 'loss/train': 1.2397648096084595} 08/31/2021 13:34:56 - INFO - __main__ - Step 134657: {'lr': 1.3143794715855584e-05, 'samples': 25854144, 'steps': 134656, 'loss/train': 1.4445247650146484} 08/31/2021 13:34:56 - INFO - __main__ - Step 134658: {'lr': 1.3142096725388214e-05, 'samples': 25854336, 'steps': 134657, 'loss/train': 1.1910719871520996} 08/31/2021 13:34:58 - INFO - __main__ - Step 134659: {'lr': 1.3140398841645362e-05, 'samples': 25854528, 'steps': 134658, 'loss/train': 0.19825078547000885} 08/31/2021 13:34:58 - INFO - __main__ - Step 134660: {'lr': 1.3138701064627778e-05, 'samples': 25854720, 'steps': 134659, 'loss/train': 0.5975753664970398} 08/31/2021 13:34:58 - INFO - __main__ - Step 134661: {'lr': 1.3137003394336239e-05, 'samples': 25854912, 'steps': 134660, 'loss/train': 1.4408894777297974} 08/31/2021 13:34:59 - INFO - __main__ - Step 134662: {'lr': 1.313530583077152e-05, 'samples': 25855104, 'steps': 134661, 'loss/train': 0.09894844889640808} 08/31/2021 13:34:59 - INFO - __main__ - Step 134663: {'lr': 1.3133608373934374e-05, 'samples': 25855296, 'steps': 134662, 'loss/train': 0.9839416742324829} 08/31/2021 13:35:00 - INFO - __main__ - Step 134664: {'lr': 1.3131911023825577e-05, 'samples': 25855488, 'steps': 134663, 'loss/train': 1.0251071453094482} 08/31/2021 13:35:01 - INFO - __main__ - Step 134665: {'lr': 1.3130213780445877e-05, 'samples': 25855680, 'steps': 134664, 'loss/train': 1.3706101179122925} 08/31/2021 13:35:01 - INFO - __main__ - Step 134666: {'lr': 1.3128516643796023e-05, 'samples': 25855872, 'steps': 134665, 'loss/train': 0.1512562781572342} 08/31/2021 13:35:02 - INFO - __main__ - Step 134667: {'lr': 1.312681961387685e-05, 'samples': 25856064, 'steps': 134666, 'loss/train': 0.09754925221204758} 08/31/2021 13:35:02 - INFO - __main__ - Step 134668: {'lr': 1.3125122690689079e-05, 'samples': 25856256, 'steps': 134667, 'loss/train': 0.8018911480903625} 08/31/2021 13:35:02 - INFO - __main__ - Step 134669: {'lr': 1.3123425874233458e-05, 'samples': 25856448, 'steps': 134668, 'loss/train': 0.9505114555358887} 08/31/2021 13:35:04 - INFO - __main__ - Step 134670: {'lr': 1.3121729164510766e-05, 'samples': 25856640, 'steps': 134669, 'loss/train': 1.1401817798614502} 08/31/2021 13:35:04 - INFO - __main__ - Step 134671: {'lr': 1.312003256152175e-05, 'samples': 25856832, 'steps': 134670, 'loss/train': 1.5705527067184448} 08/31/2021 13:35:05 - INFO - __main__ - Step 134672: {'lr': 1.311833606526719e-05, 'samples': 25857024, 'steps': 134671, 'loss/train': 1.7453452348709106} 08/31/2021 13:35:05 - INFO - __main__ - Step 134673: {'lr': 1.311663967574786e-05, 'samples': 25857216, 'steps': 134672, 'loss/train': 1.0740983486175537} 08/31/2021 13:35:05 - INFO - __main__ - Step 134674: {'lr': 1.311494339296454e-05, 'samples': 25857408, 'steps': 134673, 'loss/train': 1.097761631011963} 08/31/2021 13:35:07 - INFO - __main__ - Step 134675: {'lr': 1.311324721691795e-05, 'samples': 25857600, 'steps': 134674, 'loss/train': 1.0969617366790771} 08/31/2021 13:35:08 - INFO - __main__ - Step 134676: {'lr': 1.3111551147608868e-05, 'samples': 25857792, 'steps': 134675, 'loss/train': 1.0811767578125} 08/31/2021 13:35:08 - INFO - __main__ - Step 134677: {'lr': 1.3109855185038072e-05, 'samples': 25857984, 'steps': 134676, 'loss/train': 1.5654906034469604} 08/31/2021 13:35:08 - INFO - __main__ - Step 134678: {'lr': 1.3108159329206337e-05, 'samples': 25858176, 'steps': 134677, 'loss/train': 0.10041885077953339} 08/31/2021 13:35:09 - INFO - __main__ - Step 134679: {'lr': 1.3106463580114386e-05, 'samples': 25858368, 'steps': 134678, 'loss/train': 1.2360855340957642} 08/31/2021 13:35:11 - INFO - __main__ - Step 134680: {'lr': 1.3104767937763024e-05, 'samples': 25858560, 'steps': 134679, 'loss/train': 1.1212047338485718} 08/31/2021 13:35:11 - INFO - __main__ - Step 134681: {'lr': 1.3103072402153027e-05, 'samples': 25858752, 'steps': 134680, 'loss/train': 1.3637763261795044} 08/31/2021 13:35:12 - INFO - __main__ - Step 134682: {'lr': 1.3101376973285089e-05, 'samples': 25858944, 'steps': 134681, 'loss/train': 0.05839700251817703} 08/31/2021 13:35:12 - INFO - __main__ - Step 134683: {'lr': 1.3099681651160018e-05, 'samples': 25859136, 'steps': 134682, 'loss/train': 1.389381766319275} 08/31/2021 13:35:12 - INFO - __main__ - Step 134684: {'lr': 1.3097986435778559e-05, 'samples': 25859328, 'steps': 134683, 'loss/train': 0.2720562815666199} 08/31/2021 13:35:14 - INFO - __main__ - Step 134685: {'lr': 1.3096291327141518e-05, 'samples': 25859520, 'steps': 134684, 'loss/train': 0.39599373936653137} 08/31/2021 13:35:14 - INFO - __main__ - Step 134686: {'lr': 1.3094596325249619e-05, 'samples': 25859712, 'steps': 134685, 'loss/train': 1.8447004556655884} 08/31/2021 13:35:15 - INFO - __main__ - Step 134687: {'lr': 1.3092901430103638e-05, 'samples': 25859904, 'steps': 134686, 'loss/train': 1.0666364431381226} 08/31/2021 13:35:15 - INFO - __main__ - Step 134688: {'lr': 1.309120664170435e-05, 'samples': 25860096, 'steps': 134687, 'loss/train': 0.7346758842468262} 08/31/2021 13:35:15 - INFO - __main__ - Step 134689: {'lr': 1.3089511960052508e-05, 'samples': 25860288, 'steps': 134688, 'loss/train': 1.033431053161621} 08/31/2021 13:35:16 - INFO - __main__ - Step 134690: {'lr': 1.308781738514886e-05, 'samples': 25860480, 'steps': 134689, 'loss/train': 1.021572470664978} 08/31/2021 13:35:18 - INFO - __main__ - Step 134691: {'lr': 1.3086122916994208e-05, 'samples': 25860672, 'steps': 134690, 'loss/train': 1.1399463415145874} 08/31/2021 13:35:18 - INFO - __main__ - Step 134692: {'lr': 1.3084428555589279e-05, 'samples': 25860864, 'steps': 134691, 'loss/train': 1.208047866821289} 08/31/2021 13:35:19 - INFO - __main__ - Step 134693: {'lr': 1.3082734300934872e-05, 'samples': 25861056, 'steps': 134692, 'loss/train': 0.9834259748458862} 08/31/2021 13:35:19 - INFO - __main__ - Step 134694: {'lr': 1.3081040153031688e-05, 'samples': 25861248, 'steps': 134693, 'loss/train': 1.5740807056427002} 08/31/2021 13:35:19 - INFO - __main__ - Step 134695: {'lr': 1.3079346111880607e-05, 'samples': 25861440, 'steps': 134694, 'loss/train': 1.8107465505599976} 08/31/2021 13:35:21 - INFO - __main__ - Step 134696: {'lr': 1.3077652177482246e-05, 'samples': 25861632, 'steps': 134695, 'loss/train': 0.02900439314544201} 08/31/2021 13:35:22 - INFO - __main__ - Step 134697: {'lr': 1.3075958349837463e-05, 'samples': 25861824, 'steps': 134696, 'loss/train': 0.7486181855201721} 08/31/2021 13:35:22 - INFO - __main__ - Step 134698: {'lr': 1.3074264628947008e-05, 'samples': 25862016, 'steps': 134697, 'loss/train': 0.7964855432510376} 08/31/2021 13:35:22 - INFO - __main__ - Step 134699: {'lr': 1.3072571014811602e-05, 'samples': 25862208, 'steps': 134698, 'loss/train': 1.370654582977295} 08/31/2021 13:35:23 - INFO - __main__ - Step 134700: {'lr': 1.3070877507432049e-05, 'samples': 25862400, 'steps': 134699, 'loss/train': 0.04370516911149025} 08/31/2021 13:35:25 - INFO - __main__ - Step 134701: {'lr': 1.3069184106809128e-05, 'samples': 25862592, 'steps': 134700, 'loss/train': 0.8245744705200195} 08/31/2021 13:35:25 - INFO - __main__ - Step 134702: {'lr': 1.3067490812943562e-05, 'samples': 25862784, 'steps': 134701, 'loss/train': 1.8585851192474365} 08/31/2021 13:35:25 - INFO - __main__ - Step 134703: {'lr': 1.3065797625836124e-05, 'samples': 25862976, 'steps': 134702, 'loss/train': 0.9212478995323181} 08/31/2021 13:35:26 - INFO - __main__ - Step 134704: {'lr': 1.3064104545487565e-05, 'samples': 25863168, 'steps': 134703, 'loss/train': 0.24159961938858032} 08/31/2021 13:35:26 - INFO - __main__ - Step 134705: {'lr': 1.3062411571898691e-05, 'samples': 25863360, 'steps': 134704, 'loss/train': 0.3117086887359619} 08/31/2021 13:35:28 - INFO - __main__ - Step 134706: {'lr': 1.3060718705070223e-05, 'samples': 25863552, 'steps': 134705, 'loss/train': 1.2154514789581299} 08/31/2021 13:35:28 - INFO - __main__ - Step 134707: {'lr': 1.305902594500294e-05, 'samples': 25863744, 'steps': 134706, 'loss/train': 1.0902936458587646} 08/31/2021 13:35:28 - INFO - __main__ - Step 134708: {'lr': 1.3057333291697644e-05, 'samples': 25863936, 'steps': 134707, 'loss/train': 0.787688672542572} 08/31/2021 13:35:29 - INFO - __main__ - Step 134709: {'lr': 1.3055640745155028e-05, 'samples': 25864128, 'steps': 134708, 'loss/train': 1.3551042079925537} 08/31/2021 13:35:29 - INFO - __main__ - Step 134710: {'lr': 1.3053948305375874e-05, 'samples': 25864320, 'steps': 134709, 'loss/train': 0.9321849346160889} 08/31/2021 13:35:29 - INFO - __main__ - Step 134711: {'lr': 1.3052255972360954e-05, 'samples': 25864512, 'steps': 134710, 'loss/train': 0.9161659479141235} 08/31/2021 13:35:31 - INFO - __main__ - Step 134712: {'lr': 1.3050563746111022e-05, 'samples': 25864704, 'steps': 134711, 'loss/train': 1.0476118326187134} 08/31/2021 13:35:31 - INFO - __main__ - Step 134713: {'lr': 1.3048871626626879e-05, 'samples': 25864896, 'steps': 134712, 'loss/train': 0.7804982662200928} 08/31/2021 13:35:32 - INFO - __main__ - Step 134714: {'lr': 1.304717961390925e-05, 'samples': 25865088, 'steps': 134713, 'loss/train': 1.325108289718628} 08/31/2021 13:35:32 - INFO - __main__ - Step 134715: {'lr': 1.304548770795888e-05, 'samples': 25865280, 'steps': 134714, 'loss/train': 1.2857307195663452} 08/31/2021 13:35:32 - INFO - __main__ - Step 134716: {'lr': 1.3043795908776579e-05, 'samples': 25865472, 'steps': 134715, 'loss/train': 0.9818091988563538} 08/31/2021 13:35:34 - INFO - __main__ - Step 134717: {'lr': 1.3042104216363065e-05, 'samples': 25865664, 'steps': 134716, 'loss/train': 1.2376952171325684} 08/31/2021 13:35:35 - INFO - __main__ - Step 134718: {'lr': 1.3040412630719145e-05, 'samples': 25865856, 'steps': 134717, 'loss/train': 0.016429685056209564} 08/31/2021 13:35:35 - INFO - __main__ - Step 134719: {'lr': 1.3038721151845567e-05, 'samples': 25866048, 'steps': 134718, 'loss/train': 0.7056258320808411} 08/31/2021 13:35:35 - INFO - __main__ - Step 134720: {'lr': 1.3037029779743054e-05, 'samples': 25866240, 'steps': 134719, 'loss/train': 0.6008236408233643} 08/31/2021 13:35:36 - INFO - __main__ - Step 134721: {'lr': 1.3035338514412409e-05, 'samples': 25866432, 'steps': 134720, 'loss/train': 1.3668699264526367} 08/31/2021 13:35:36 - INFO - __main__ - Step 134722: {'lr': 1.3033647355854439e-05, 'samples': 25866624, 'steps': 134721, 'loss/train': 1.3989235162734985} 08/31/2021 13:35:37 - INFO - __main__ - Step 134723: {'lr': 1.3031956304069808e-05, 'samples': 25866816, 'steps': 134722, 'loss/train': 1.0909385681152344} 08/31/2021 13:35:38 - INFO - __main__ - Step 134724: {'lr': 1.3030265359059296e-05, 'samples': 25867008, 'steps': 134723, 'loss/train': 1.3275814056396484} 08/31/2021 13:35:38 - INFO - __main__ - Step 134725: {'lr': 1.3028574520823732e-05, 'samples': 25867200, 'steps': 134724, 'loss/train': 0.49529895186424255} 08/31/2021 13:35:39 - INFO - __main__ - Step 134726: {'lr': 1.3026883789363786e-05, 'samples': 25867392, 'steps': 134725, 'loss/train': 0.5733328461647034} 08/31/2021 13:35:39 - INFO - __main__ - Step 134727: {'lr': 1.3025193164680316e-05, 'samples': 25867584, 'steps': 134726, 'loss/train': 0.892710268497467} 08/31/2021 13:35:41 - INFO - __main__ - Step 134728: {'lr': 1.3023502646774017e-05, 'samples': 25867776, 'steps': 134727, 'loss/train': 1.0920850038528442} 08/31/2021 13:35:41 - INFO - __main__ - Step 134729: {'lr': 1.3021812235645664e-05, 'samples': 25867968, 'steps': 134728, 'loss/train': 1.115380883216858} 08/31/2021 13:35:41 - INFO - __main__ - Step 134730: {'lr': 1.3020121931296036e-05, 'samples': 25868160, 'steps': 134729, 'loss/train': 0.6577576398849487} 08/31/2021 13:35:42 - INFO - __main__ - Step 134731: {'lr': 1.3018431733725882e-05, 'samples': 25868352, 'steps': 134730, 'loss/train': 0.3858601152896881} 08/31/2021 13:35:42 - INFO - __main__ - Step 134732: {'lr': 1.3016741642935953e-05, 'samples': 25868544, 'steps': 134731, 'loss/train': 1.3838517665863037} 08/31/2021 13:35:44 - INFO - __main__ - Step 134733: {'lr': 1.3015051658927051e-05, 'samples': 25868736, 'steps': 134732, 'loss/train': 0.3690360486507416} 08/31/2021 13:35:44 - INFO - __main__ - Step 134734: {'lr': 1.3013361781699873e-05, 'samples': 25868928, 'steps': 134733, 'loss/train': 0.7570438981056213} 08/31/2021 13:35:44 - INFO - __main__ - Step 134735: {'lr': 1.3011672011255277e-05, 'samples': 25869120, 'steps': 134734, 'loss/train': 1.1121149063110352} 08/31/2021 13:35:45 - INFO - __main__ - Step 134736: {'lr': 1.3009982347593929e-05, 'samples': 25869312, 'steps': 134735, 'loss/train': 0.8757562637329102} 08/31/2021 13:35:45 - INFO - __main__ - Step 134737: {'lr': 1.3008292790716608e-05, 'samples': 25869504, 'steps': 134736, 'loss/train': 1.450682520866394} 08/31/2021 13:35:47 - INFO - __main__ - Step 134738: {'lr': 1.3006603340624118e-05, 'samples': 25869696, 'steps': 134737, 'loss/train': 0.8763914108276367} 08/31/2021 13:35:47 - INFO - __main__ - Step 134739: {'lr': 1.300491399731718e-05, 'samples': 25869888, 'steps': 134738, 'loss/train': 0.6117350459098816} 08/31/2021 13:35:47 - INFO - __main__ - Step 134740: {'lr': 1.3003224760796572e-05, 'samples': 25870080, 'steps': 134739, 'loss/train': 1.0363754034042358} 08/31/2021 13:35:48 - INFO - __main__ - Step 134741: {'lr': 1.3001535631063071e-05, 'samples': 25870272, 'steps': 134740, 'loss/train': 1.2511614561080933} 08/31/2021 13:35:48 - INFO - __main__ - Step 134742: {'lr': 1.2999846608117399e-05, 'samples': 25870464, 'steps': 134741, 'loss/train': 0.8590592741966248} 08/31/2021 13:35:50 - INFO - __main__ - Step 134743: {'lr': 1.299815769196036e-05, 'samples': 25870656, 'steps': 134742, 'loss/train': 1.0073162317276} 08/31/2021 13:35:51 - INFO - __main__ - Step 134744: {'lr': 1.2996468882592677e-05, 'samples': 25870848, 'steps': 134743, 'loss/train': 1.226581335067749} 08/31/2021 13:35:51 - INFO - __main__ - Step 134745: {'lr': 1.2994780180015125e-05, 'samples': 25871040, 'steps': 134744, 'loss/train': 0.6814026832580566} 08/31/2021 13:35:51 - INFO - __main__ - Step 134746: {'lr': 1.2993091584228483e-05, 'samples': 25871232, 'steps': 134745, 'loss/train': 4.182211399078369} 08/31/2021 13:35:52 - INFO - __main__ - Step 134747: {'lr': 1.2991403095233473e-05, 'samples': 25871424, 'steps': 134746, 'loss/train': 1.0173418521881104} 08/31/2021 13:35:52 - INFO - __main__ - Step 134748: {'lr': 1.2989714713030953e-05, 'samples': 25871616, 'steps': 134747, 'loss/train': 0.9182088971138} 08/31/2021 13:35:53 - INFO - __main__ - Step 134749: {'lr': 1.2988026437621537e-05, 'samples': 25871808, 'steps': 134748, 'loss/train': 0.8126563429832458} 08/31/2021 13:35:54 - INFO - __main__ - Step 134750: {'lr': 1.2986338269006082e-05, 'samples': 25872000, 'steps': 134749, 'loss/train': 0.2734830677509308} 08/31/2021 13:35:54 - INFO - __main__ - Step 134751: {'lr': 1.2984650207185312e-05, 'samples': 25872192, 'steps': 134750, 'loss/train': 0.9403783679008484} 08/31/2021 13:35:55 - INFO - __main__ - Step 134752: {'lr': 1.2982962252160003e-05, 'samples': 25872384, 'steps': 134751, 'loss/train': 1.409220576286316} 08/31/2021 13:35:55 - INFO - __main__ - Step 134753: {'lr': 1.2981274403930932e-05, 'samples': 25872576, 'steps': 134752, 'loss/train': 1.3212097883224487} 08/31/2021 13:35:57 - INFO - __main__ - Step 134754: {'lr': 1.297958666249882e-05, 'samples': 25872768, 'steps': 134753, 'loss/train': 0.4856830835342407} 08/31/2021 13:35:57 - INFO - __main__ - Step 134755: {'lr': 1.2977899027864449e-05, 'samples': 25872960, 'steps': 134754, 'loss/train': 0.3085143268108368} 08/31/2021 13:35:57 - INFO - __main__ - Step 134756: {'lr': 1.297621150002859e-05, 'samples': 25873152, 'steps': 134755, 'loss/train': 0.7577073574066162} 08/31/2021 13:35:58 - INFO - __main__ - Step 134757: {'lr': 1.2974524078991995e-05, 'samples': 25873344, 'steps': 134756, 'loss/train': 1.3338292837142944} 08/31/2021 13:35:58 - INFO - __main__ - Step 134758: {'lr': 1.2972836764755413e-05, 'samples': 25873536, 'steps': 134757, 'loss/train': 1.3606348037719727} 08/31/2021 13:36:00 - INFO - __main__ - Step 134759: {'lr': 1.2971149557319623e-05, 'samples': 25873728, 'steps': 134758, 'loss/train': 0.9875754714012146} 08/31/2021 13:36:00 - INFO - __main__ - Step 134760: {'lr': 1.2969462456685372e-05, 'samples': 25873920, 'steps': 134759, 'loss/train': 1.1606351137161255} 08/31/2021 13:36:00 - INFO - __main__ - Step 134761: {'lr': 1.296777546285341e-05, 'samples': 25874112, 'steps': 134760, 'loss/train': 1.2880805730819702} 08/31/2021 13:36:01 - INFO - __main__ - Step 134762: {'lr': 1.296608857582457e-05, 'samples': 25874304, 'steps': 134761, 'loss/train': 1.216770887374878} 08/31/2021 13:36:01 - INFO - __main__ - Step 134763: {'lr': 1.2964401795599489e-05, 'samples': 25874496, 'steps': 134762, 'loss/train': 0.6767458915710449} 08/31/2021 13:36:03 - INFO - __main__ - Step 134764: {'lr': 1.2962715122179003e-05, 'samples': 25874688, 'steps': 134763, 'loss/train': 0.9389819502830505} 08/31/2021 13:36:03 - INFO - __main__ - Step 134765: {'lr': 1.2961028555563858e-05, 'samples': 25874880, 'steps': 134764, 'loss/train': 1.213462233543396} 08/31/2021 13:36:04 - INFO - __main__ - Step 134766: {'lr': 1.2959342095754833e-05, 'samples': 25875072, 'steps': 134765, 'loss/train': 1.2815078496932983} 08/31/2021 13:36:04 - INFO - __main__ - Step 134767: {'lr': 1.2957655742752649e-05, 'samples': 25875264, 'steps': 134766, 'loss/train': 0.7019373178482056} 08/31/2021 13:36:04 - INFO - __main__ - Step 134768: {'lr': 1.2955969496558111e-05, 'samples': 25875456, 'steps': 134767, 'loss/train': 0.27290743589401245} 08/31/2021 13:36:06 - INFO - __main__ - Step 134769: {'lr': 1.2954283357171943e-05, 'samples': 25875648, 'steps': 134768, 'loss/train': 1.3668566942214966} 08/31/2021 13:36:06 - INFO - __main__ - Step 134770: {'lr': 1.2952597324594916e-05, 'samples': 25875840, 'steps': 134769, 'loss/train': 0.548560619354248} 08/31/2021 13:36:07 - INFO - __main__ - Step 134771: {'lr': 1.2950911398827786e-05, 'samples': 25876032, 'steps': 134770, 'loss/train': 1.3626948595046997} 08/31/2021 13:36:07 - INFO - __main__ - Step 134772: {'lr': 1.2949225579871327e-05, 'samples': 25876224, 'steps': 134771, 'loss/train': 0.6894376873970032} 08/31/2021 13:36:07 - INFO - __main__ - Step 134773: {'lr': 1.2947539867726288e-05, 'samples': 25876416, 'steps': 134772, 'loss/train': 0.7417399287223816} 08/31/2021 13:36:08 - INFO - __main__ - Step 134774: {'lr': 1.294585426239342e-05, 'samples': 25876608, 'steps': 134773, 'loss/train': 1.4267773628234863} 08/31/2021 13:36:09 - INFO - __main__ - Step 134775: {'lr': 1.2944168763873526e-05, 'samples': 25876800, 'steps': 134774, 'loss/train': 0.707836389541626} 08/31/2021 13:36:10 - INFO - __main__ - Step 134776: {'lr': 1.2942483372167302e-05, 'samples': 25876992, 'steps': 134775, 'loss/train': 1.1609420776367188} 08/31/2021 13:36:10 - INFO - __main__ - Step 134777: {'lr': 1.2940798087275523e-05, 'samples': 25877184, 'steps': 134776, 'loss/train': 0.6463212370872498} 08/31/2021 13:36:11 - INFO - __main__ - Step 134778: {'lr': 1.2939112909198996e-05, 'samples': 25877376, 'steps': 134777, 'loss/train': 0.9460791945457458} 08/31/2021 13:36:11 - INFO - __main__ - Step 134779: {'lr': 1.2937427837938415e-05, 'samples': 25877568, 'steps': 134778, 'loss/train': 1.4628733396530151} 08/31/2021 13:36:13 - INFO - __main__ - Step 134780: {'lr': 1.2935742873494582e-05, 'samples': 25877760, 'steps': 134779, 'loss/train': 1.6721142530441284} 08/31/2021 13:36:13 - INFO - __main__ - Step 134781: {'lr': 1.293405801586825e-05, 'samples': 25877952, 'steps': 134780, 'loss/train': 1.1478135585784912} 08/31/2021 13:36:14 - INFO - __main__ - Step 134782: {'lr': 1.2932373265060165e-05, 'samples': 25878144, 'steps': 134781, 'loss/train': 0.9930755496025085} 08/31/2021 13:36:14 - INFO - __main__ - Step 134783: {'lr': 1.2930688621071107e-05, 'samples': 25878336, 'steps': 134782, 'loss/train': 2.018254041671753} 08/31/2021 13:36:14 - INFO - __main__ - Step 134784: {'lr': 1.2929004083901824e-05, 'samples': 25878528, 'steps': 134783, 'loss/train': 1.5991333723068237} 08/31/2021 13:36:16 - INFO - __main__ - Step 134785: {'lr': 1.2927319653553066e-05, 'samples': 25878720, 'steps': 134784, 'loss/train': 0.21578674018383026} 08/31/2021 13:36:16 - INFO - __main__ - Step 134786: {'lr': 1.292563533002558e-05, 'samples': 25878912, 'steps': 134785, 'loss/train': 0.503788411617279} 08/31/2021 13:36:17 - INFO - __main__ - Step 134787: {'lr': 1.2923951113320175e-05, 'samples': 25879104, 'steps': 134786, 'loss/train': 1.6632508039474487} 08/31/2021 13:36:17 - INFO - __main__ - Step 134788: {'lr': 1.2922267003437571e-05, 'samples': 25879296, 'steps': 134787, 'loss/train': 0.8144688010215759} 08/31/2021 13:36:17 - INFO - __main__ - Step 134789: {'lr': 1.2920583000378573e-05, 'samples': 25879488, 'steps': 134788, 'loss/train': 1.5373247861862183} 08/31/2021 13:36:19 - INFO - __main__ - Step 134790: {'lr': 1.2918899104143844e-05, 'samples': 25879680, 'steps': 134789, 'loss/train': 0.42922160029411316} 08/31/2021 13:36:20 - INFO - __main__ - Step 134791: {'lr': 1.2917215314734221e-05, 'samples': 25879872, 'steps': 134790, 'loss/train': 0.2903388738632202} 08/31/2021 13:36:20 - INFO - __main__ - Step 134792: {'lr': 1.2915531632150423e-05, 'samples': 25880064, 'steps': 134791, 'loss/train': 0.8242303133010864} 08/31/2021 13:36:20 - INFO - __main__ - Step 134793: {'lr': 1.2913848056393258e-05, 'samples': 25880256, 'steps': 134792, 'loss/train': 0.7699919939041138} 08/31/2021 13:36:21 - INFO - __main__ - Step 134794: {'lr': 1.2912164587463442e-05, 'samples': 25880448, 'steps': 134793, 'loss/train': 1.1129153966903687} 08/31/2021 13:36:21 - INFO - __main__ - Step 134795: {'lr': 1.291048122536173e-05, 'samples': 25880640, 'steps': 134794, 'loss/train': 0.036999836564064026} 08/31/2021 13:36:23 - INFO - __main__ - Step 134796: {'lr': 1.2908797970088926e-05, 'samples': 25880832, 'steps': 134795, 'loss/train': 1.4060944318771362} 08/31/2021 13:36:23 - INFO - __main__ - Step 134797: {'lr': 1.2907114821645749e-05, 'samples': 25881024, 'steps': 134796, 'loss/train': 0.6361302733421326} 08/31/2021 13:36:23 - INFO - __main__ - Step 134798: {'lr': 1.290543178003295e-05, 'samples': 25881216, 'steps': 134797, 'loss/train': 0.16543559730052948} 08/31/2021 13:36:24 - INFO - __main__ - Step 134799: {'lr': 1.2903748845251306e-05, 'samples': 25881408, 'steps': 134798, 'loss/train': 1.029945731163025} 08/31/2021 13:36:24 - INFO - __main__ - Step 134800: {'lr': 1.2902066017301595e-05, 'samples': 25881600, 'steps': 134799, 'loss/train': 0.24959677457809448} 08/31/2021 13:36:26 - INFO - __main__ - Step 134801: {'lr': 1.2900383296184538e-05, 'samples': 25881792, 'steps': 134800, 'loss/train': 1.0173321962356567} 08/31/2021 13:36:27 - INFO - __main__ - Step 134802: {'lr': 1.2898700681900966e-05, 'samples': 25881984, 'steps': 134801, 'loss/train': 0.5438124537467957} 08/31/2021 13:36:27 - INFO - __main__ - Step 134803: {'lr': 1.2897018174451519e-05, 'samples': 25882176, 'steps': 134802, 'loss/train': 0.9117380976676941} 08/31/2021 13:36:27 - INFO - __main__ - Step 134804: {'lr': 1.289533577383703e-05, 'samples': 25882368, 'steps': 134803, 'loss/train': 1.2294780015945435} 08/31/2021 13:36:28 - INFO - __main__ - Step 134805: {'lr': 1.2893653480058248e-05, 'samples': 25882560, 'steps': 134804, 'loss/train': 1.3957781791687012} 08/31/2021 13:36:30 - INFO - __main__ - Step 134806: {'lr': 1.2891971293115923e-05, 'samples': 25882752, 'steps': 134805, 'loss/train': 0.35347187519073486} 08/31/2021 13:36:30 - INFO - __main__ - Step 134807: {'lr': 1.2890289213010803e-05, 'samples': 25882944, 'steps': 134806, 'loss/train': 0.5821369290351868} 08/31/2021 13:36:30 - INFO - __main__ - Step 134808: {'lr': 1.2888607239743666e-05, 'samples': 25883136, 'steps': 134807, 'loss/train': 0.9446862936019897} 08/31/2021 13:36:31 - INFO - __main__ - Step 134809: {'lr': 1.288692537331529e-05, 'samples': 25883328, 'steps': 134808, 'loss/train': 0.7899047136306763} 08/31/2021 13:36:31 - INFO - __main__ - Step 134810: {'lr': 1.2885243613726366e-05, 'samples': 25883520, 'steps': 134809, 'loss/train': 0.029971731826663017} 08/31/2021 13:36:31 - INFO - __main__ - Step 134811: {'lr': 1.288356196097773e-05, 'samples': 25883712, 'steps': 134810, 'loss/train': 0.028725415468215942} 08/31/2021 13:36:33 - INFO - __main__ - Step 134812: {'lr': 1.2881880415070074e-05, 'samples': 25883904, 'steps': 134811, 'loss/train': 1.0676791667938232} 08/31/2021 13:36:33 - INFO - __main__ - Step 134813: {'lr': 1.2880198976004203e-05, 'samples': 25884096, 'steps': 134812, 'loss/train': 0.6067134141921997} 08/31/2021 13:36:34 - INFO - __main__ - Step 134814: {'lr': 1.2878517643780841e-05, 'samples': 25884288, 'steps': 134813, 'loss/train': 0.978752076625824} 08/31/2021 13:36:34 - INFO - __main__ - Step 134815: {'lr': 1.287683641840076e-05, 'samples': 25884480, 'steps': 134814, 'loss/train': 1.5388201475143433} 08/31/2021 13:36:34 - INFO - __main__ - Step 134816: {'lr': 1.2875155299864771e-05, 'samples': 25884672, 'steps': 134815, 'loss/train': 1.0877543687820435} 08/31/2021 13:36:36 - INFO - __main__ - Step 134817: {'lr': 1.2873474288173536e-05, 'samples': 25884864, 'steps': 134816, 'loss/train': 0.6316667199134827} 08/31/2021 13:36:36 - INFO - __main__ - Step 134818: {'lr': 1.2871793383327835e-05, 'samples': 25885056, 'steps': 134817, 'loss/train': 1.1788498163223267} 08/31/2021 13:36:37 - INFO - __main__ - Step 134819: {'lr': 1.287011258532847e-05, 'samples': 25885248, 'steps': 134818, 'loss/train': 0.9746288061141968} 08/31/2021 13:36:37 - INFO - __main__ - Step 134820: {'lr': 1.2868431894176164e-05, 'samples': 25885440, 'steps': 134819, 'loss/train': 0.9640511274337769} 08/31/2021 13:36:37 - INFO - __main__ - Step 134821: {'lr': 1.2866751309871665e-05, 'samples': 25885632, 'steps': 134820, 'loss/train': 0.9947443604469299} 08/31/2021 13:36:39 - INFO - __main__ - Step 134822: {'lr': 1.2865070832415782e-05, 'samples': 25885824, 'steps': 134821, 'loss/train': 1.1200354099273682} 08/31/2021 13:36:39 - INFO - __main__ - Step 134823: {'lr': 1.2863390461809204e-05, 'samples': 25886016, 'steps': 134822, 'loss/train': 1.134986162185669} 08/31/2021 13:36:40 - INFO - __main__ - Step 134824: {'lr': 1.2861710198052739e-05, 'samples': 25886208, 'steps': 134823, 'loss/train': 0.5820491313934326} 08/31/2021 13:36:40 - INFO - __main__ - Step 134825: {'lr': 1.2860030041147135e-05, 'samples': 25886400, 'steps': 134824, 'loss/train': 0.9469838738441467} 08/31/2021 13:36:41 - INFO - __main__ - Step 134826: {'lr': 1.2858349991093144e-05, 'samples': 25886592, 'steps': 134825, 'loss/train': 0.5998824834823608} 08/31/2021 13:36:42 - INFO - __main__ - Step 134827: {'lr': 1.2856670047891512e-05, 'samples': 25886784, 'steps': 134826, 'loss/train': 0.6825779676437378} 08/31/2021 13:36:43 - INFO - __main__ - Step 134828: {'lr': 1.2854990211543044e-05, 'samples': 25886976, 'steps': 134827, 'loss/train': 0.6368111968040466} 08/31/2021 13:36:43 - INFO - __main__ - Step 134829: {'lr': 1.2853310482048409e-05, 'samples': 25887168, 'steps': 134828, 'loss/train': 0.8370376229286194} 08/31/2021 13:36:43 - INFO - __main__ - Step 134830: {'lr': 1.2851630859408437e-05, 'samples': 25887360, 'steps': 134829, 'loss/train': 0.7693741321563721} 08/31/2021 13:36:44 - INFO - __main__ - Step 134831: {'lr': 1.284995134362385e-05, 'samples': 25887552, 'steps': 134830, 'loss/train': 0.903826117515564} 08/31/2021 13:36:45 - INFO - __main__ - Step 134832: {'lr': 1.2848271934695398e-05, 'samples': 25887744, 'steps': 134831, 'loss/train': 0.8915457725524902} 08/31/2021 13:36:46 - INFO - __main__ - Step 134833: {'lr': 1.2846592632623888e-05, 'samples': 25887936, 'steps': 134832, 'loss/train': 1.5935856103897095} 08/31/2021 13:36:46 - INFO - __main__ - Step 134834: {'lr': 1.2844913437410011e-05, 'samples': 25888128, 'steps': 134833, 'loss/train': 1.0969737768173218} 08/31/2021 13:36:46 - INFO - __main__ - Step 134835: {'lr': 1.28432343490546e-05, 'samples': 25888320, 'steps': 134834, 'loss/train': 0.2651102542877197} 08/31/2021 13:36:47 - INFO - __main__ - Step 134836: {'lr': 1.2841555367558322e-05, 'samples': 25888512, 'steps': 134835, 'loss/train': 1.0437512397766113} 08/31/2021 13:36:49 - INFO - __main__ - Step 134837: {'lr': 1.283987649292201e-05, 'samples': 25888704, 'steps': 134836, 'loss/train': 1.325509786605835} 08/31/2021 13:36:49 - INFO - __main__ - Step 134838: {'lr': 1.2838197725146384e-05, 'samples': 25888896, 'steps': 134837, 'loss/train': 0.15164631605148315} 08/31/2021 13:36:49 - INFO - __main__ - Step 134839: {'lr': 1.2836519064232221e-05, 'samples': 25889088, 'steps': 134838, 'loss/train': 1.2256436347961426} 08/31/2021 13:36:50 - INFO - __main__ - Step 134840: {'lr': 1.2834840510180245e-05, 'samples': 25889280, 'steps': 134839, 'loss/train': 0.4111160337924957} 08/31/2021 13:36:50 - INFO - __main__ - Step 134841: {'lr': 1.2833162062991232e-05, 'samples': 25889472, 'steps': 134840, 'loss/train': 0.0270161684602499} 08/31/2021 13:36:51 - INFO - __main__ - Step 134842: {'lr': 1.2831483722665931e-05, 'samples': 25889664, 'steps': 134841, 'loss/train': 0.645725667476654} 08/31/2021 13:36:53 - INFO - __main__ - Step 134843: {'lr': 1.2829805489205092e-05, 'samples': 25889856, 'steps': 134842, 'loss/train': 0.11568017303943634} 08/31/2021 13:36:53 - INFO - __main__ - Step 134844: {'lr': 1.2828127362609522e-05, 'samples': 25890048, 'steps': 134843, 'loss/train': 0.5389666557312012} 08/31/2021 13:36:54 - INFO - __main__ - Step 134845: {'lr': 1.2826449342879908e-05, 'samples': 25890240, 'steps': 134844, 'loss/train': 1.3230286836624146} 08/31/2021 13:36:54 - INFO - __main__ - Step 134846: {'lr': 1.2824771430017035e-05, 'samples': 25890432, 'steps': 134845, 'loss/train': 0.0851123109459877} 08/31/2021 13:36:54 - INFO - __main__ - Step 134847: {'lr': 1.2823093624021676e-05, 'samples': 25890624, 'steps': 134846, 'loss/train': 0.46151623129844666} 08/31/2021 13:36:56 - INFO - __main__ - Step 134848: {'lr': 1.2821415924894554e-05, 'samples': 25890816, 'steps': 134847, 'loss/train': 0.6650587320327759} 08/31/2021 13:36:56 - INFO - __main__ - Step 134849: {'lr': 1.2819738332636444e-05, 'samples': 25891008, 'steps': 134848, 'loss/train': 0.6410316824913025} 08/31/2021 13:36:57 - INFO - __main__ - Step 134850: {'lr': 1.2818060847248125e-05, 'samples': 25891200, 'steps': 134849, 'loss/train': 1.1281464099884033} 08/31/2021 13:36:57 - INFO - __main__ - Step 134851: {'lr': 1.281638346873032e-05, 'samples': 25891392, 'steps': 134850, 'loss/train': 1.5215479135513306} 08/31/2021 13:36:57 - INFO - __main__ - Step 134852: {'lr': 1.2814706197083775e-05, 'samples': 25891584, 'steps': 134851, 'loss/train': 0.8027695417404175} 08/31/2021 13:36:59 - INFO - __main__ - Step 134853: {'lr': 1.281302903230927e-05, 'samples': 25891776, 'steps': 134852, 'loss/train': 1.1338740587234497} 08/31/2021 13:37:00 - INFO - __main__ - Step 134854: {'lr': 1.2811351974407553e-05, 'samples': 25891968, 'steps': 134853, 'loss/train': 1.2187618017196655} 08/31/2021 13:37:00 - INFO - __main__ - Step 134855: {'lr': 1.2809675023379375e-05, 'samples': 25892160, 'steps': 134854, 'loss/train': 1.1116313934326172} 08/31/2021 13:37:01 - INFO - __main__ - Step 134856: {'lr': 1.280799817922551e-05, 'samples': 25892352, 'steps': 134855, 'loss/train': 0.943446695804596} 08/31/2021 13:37:01 - INFO - __main__ - Step 134857: {'lr': 1.2806321441946683e-05, 'samples': 25892544, 'steps': 134856, 'loss/train': 1.103811264038086} 08/31/2021 13:37:03 - INFO - __main__ - Step 134858: {'lr': 1.2804644811543698e-05, 'samples': 25892736, 'steps': 134857, 'loss/train': 1.0657577514648438} 08/31/2021 13:37:03 - INFO - __main__ - Step 134859: {'lr': 1.2802968288017247e-05, 'samples': 25892928, 'steps': 134858, 'loss/train': 1.1953426599502563} 08/31/2021 13:37:04 - INFO - __main__ - Step 134860: {'lr': 1.2801291871368137e-05, 'samples': 25893120, 'steps': 134859, 'loss/train': 0.6291793584823608} 08/31/2021 13:37:04 - INFO - __main__ - Step 134861: {'lr': 1.2799615561597145e-05, 'samples': 25893312, 'steps': 134860, 'loss/train': 1.02617609500885} 08/31/2021 13:37:04 - INFO - __main__ - Step 134862: {'lr': 1.2797939358704936e-05, 'samples': 25893504, 'steps': 134861, 'loss/train': 0.016934145241975784} 08/31/2021 13:37:05 - INFO - __main__ - Step 134863: {'lr': 1.2796263262692315e-05, 'samples': 25893696, 'steps': 134862, 'loss/train': 1.112435221672058} 08/31/2021 13:37:06 - INFO - __main__ - Step 134864: {'lr': 1.2794587273560033e-05, 'samples': 25893888, 'steps': 134863, 'loss/train': 1.0264614820480347} 08/31/2021 13:37:07 - INFO - __main__ - Step 134865: {'lr': 1.2792911391308865e-05, 'samples': 25894080, 'steps': 134864, 'loss/train': 1.6190121173858643} 08/31/2021 13:37:07 - INFO - __main__ - Step 134866: {'lr': 1.2791235615939535e-05, 'samples': 25894272, 'steps': 134865, 'loss/train': 0.5305461883544922} 08/31/2021 13:37:07 - INFO - __main__ - Step 134867: {'lr': 1.2789559947452845e-05, 'samples': 25894464, 'steps': 134866, 'loss/train': 0.04089860990643501} 08/31/2021 13:37:08 - INFO - __main__ - Step 134868: {'lr': 1.278788438584949e-05, 'samples': 25894656, 'steps': 134867, 'loss/train': 0.9458931684494019} 08/31/2021 13:37:09 - INFO - __main__ - Step 134869: {'lr': 1.2786208931130249e-05, 'samples': 25894848, 'steps': 134868, 'loss/train': 1.4061436653137207} 08/31/2021 13:37:10 - INFO - __main__ - Step 134870: {'lr': 1.2784533583295898e-05, 'samples': 25895040, 'steps': 134869, 'loss/train': 0.9264611601829529} 08/31/2021 13:37:10 - INFO - __main__ - Step 134871: {'lr': 1.2782858342347186e-05, 'samples': 25895232, 'steps': 134870, 'loss/train': 0.7891765236854553} 08/31/2021 13:37:10 - INFO - __main__ - Step 134872: {'lr': 1.2781183208284864e-05, 'samples': 25895424, 'steps': 134871, 'loss/train': 0.657232403755188} 08/31/2021 13:37:11 - INFO - __main__ - Step 134873: {'lr': 1.2779508181109651e-05, 'samples': 25895616, 'steps': 134872, 'loss/train': 0.7523829936981201} 08/31/2021 13:37:11 - INFO - __main__ - Step 134874: {'lr': 1.2777833260822353e-05, 'samples': 25895808, 'steps': 134873, 'loss/train': 0.9380407929420471} 08/31/2021 13:37:13 - INFO - __main__ - Step 134875: {'lr': 1.2776158447423692e-05, 'samples': 25896000, 'steps': 134874, 'loss/train': 0.022234953939914703} 08/31/2021 13:37:13 - INFO - __main__ - Step 134876: {'lr': 1.2774483740914416e-05, 'samples': 25896192, 'steps': 134875, 'loss/train': 1.4557607173919678} 08/31/2021 13:37:13 - INFO - __main__ - Step 134877: {'lr': 1.2772809141295333e-05, 'samples': 25896384, 'steps': 134876, 'loss/train': 0.7248380780220032} 08/31/2021 13:37:14 - INFO - __main__ - Step 134878: {'lr': 1.2771134648567134e-05, 'samples': 25896576, 'steps': 134877, 'loss/train': 1.1733741760253906} 08/31/2021 13:37:14 - INFO - __main__ - Step 134879: {'lr': 1.2769460262730598e-05, 'samples': 25896768, 'steps': 134878, 'loss/train': 0.5903931856155396} 08/31/2021 13:37:16 - INFO - __main__ - Step 134880: {'lr': 1.27677859837865e-05, 'samples': 25896960, 'steps': 134879, 'loss/train': 1.386906385421753} 08/31/2021 13:37:16 - INFO - __main__ - Step 134881: {'lr': 1.2766111811735564e-05, 'samples': 25897152, 'steps': 134880, 'loss/train': 0.848814845085144} 08/31/2021 13:37:16 - INFO - __main__ - Step 134882: {'lr': 1.2764437746578567e-05, 'samples': 25897344, 'steps': 134881, 'loss/train': 0.9149420857429504} 08/31/2021 13:37:17 - INFO - __main__ - Step 134883: {'lr': 1.2762763788316284e-05, 'samples': 25897536, 'steps': 134882, 'loss/train': 0.2998458445072174} 08/31/2021 13:37:17 - INFO - __main__ - Step 134884: {'lr': 1.276108993694941e-05, 'samples': 25897728, 'steps': 134883, 'loss/train': 0.7542358040809631} 08/31/2021 13:37:19 - INFO - __main__ - Step 134885: {'lr': 1.2759416192478724e-05, 'samples': 25897920, 'steps': 134884, 'loss/train': 1.0610017776489258} 08/31/2021 13:37:19 - INFO - __main__ - Step 134886: {'lr': 1.2757742554904972e-05, 'samples': 25898112, 'steps': 134885, 'loss/train': 1.233044147491455} 08/31/2021 13:37:20 - INFO - __main__ - Step 134887: {'lr': 1.2756069024228934e-05, 'samples': 25898304, 'steps': 134886, 'loss/train': 0.5737478733062744} 08/31/2021 13:37:20 - INFO - __main__ - Step 134888: {'lr': 1.275439560045133e-05, 'samples': 25898496, 'steps': 134887, 'loss/train': 0.9323203563690186} 08/31/2021 13:37:20 - INFO - __main__ - Step 134889: {'lr': 1.2752722283572966e-05, 'samples': 25898688, 'steps': 134888, 'loss/train': 0.7678218483924866} 08/31/2021 13:37:21 - INFO - __main__ - Step 134890: {'lr': 1.2751049073594533e-05, 'samples': 25898880, 'steps': 134889, 'loss/train': 1.8123705387115479} 08/31/2021 13:37:22 - INFO - __main__ - Step 134891: {'lr': 1.2749375970516841e-05, 'samples': 25899072, 'steps': 134890, 'loss/train': 1.3383066654205322} 08/31/2021 13:37:23 - INFO - __main__ - Step 134892: {'lr': 1.2747702974340609e-05, 'samples': 25899264, 'steps': 134891, 'loss/train': 0.3811250329017639} 08/31/2021 13:37:23 - INFO - __main__ - Step 134893: {'lr': 1.2746030085066613e-05, 'samples': 25899456, 'steps': 134892, 'loss/train': 1.042890191078186} 08/31/2021 13:37:23 - INFO - __main__ - Step 134894: {'lr': 1.2744357302695576e-05, 'samples': 25899648, 'steps': 134893, 'loss/train': 0.7450363039970398} 08/31/2021 13:37:24 - INFO - __main__ - Step 134895: {'lr': 1.2742684627228274e-05, 'samples': 25899840, 'steps': 134894, 'loss/train': 0.8037164211273193} 08/31/2021 13:37:25 - INFO - __main__ - Step 134896: {'lr': 1.2741012058665514e-05, 'samples': 25900032, 'steps': 134895, 'loss/train': 0.12539148330688477} 08/31/2021 13:37:26 - INFO - __main__ - Step 134897: {'lr': 1.2739339597007932e-05, 'samples': 25900224, 'steps': 134896, 'loss/train': 1.4182567596435547} 08/31/2021 13:37:26 - INFO - __main__ - Step 134898: {'lr': 1.2737667242256363e-05, 'samples': 25900416, 'steps': 134897, 'loss/train': 1.282386302947998} 08/31/2021 13:37:27 - INFO - __main__ - Step 134899: {'lr': 1.2735994994411527e-05, 'samples': 25900608, 'steps': 134898, 'loss/train': 1.4534419775009155} 08/31/2021 13:37:27 - INFO - __main__ - Step 134900: {'lr': 1.2734322853474173e-05, 'samples': 25900800, 'steps': 134899, 'loss/train': 0.7371295094490051} 08/31/2021 13:37:29 - INFO - __main__ - Step 134901: {'lr': 1.2732650819445107e-05, 'samples': 25900992, 'steps': 134900, 'loss/train': 0.9319902658462524} 08/31/2021 13:37:29 - INFO - __main__ - Step 134902: {'lr': 1.2730978892325024e-05, 'samples': 25901184, 'steps': 134901, 'loss/train': 0.9457505941390991} 08/31/2021 13:37:29 - INFO - __main__ - Step 134903: {'lr': 1.2729307072114699e-05, 'samples': 25901376, 'steps': 134902, 'loss/train': 0.7003709077835083} 08/31/2021 13:37:30 - INFO - __main__ - Step 134904: {'lr': 1.2727635358814909e-05, 'samples': 25901568, 'steps': 134903, 'loss/train': 0.8763464093208313} 08/31/2021 13:37:30 - INFO - __main__ - Step 134905: {'lr': 1.2725963752426379e-05, 'samples': 25901760, 'steps': 134904, 'loss/train': 0.803741991519928} 08/31/2021 13:37:31 - INFO - __main__ - Step 134906: {'lr': 1.2724292252949853e-05, 'samples': 25901952, 'steps': 134905, 'loss/train': 1.579577088356018} 08/31/2021 13:37:33 - INFO - __main__ - Step 134907: {'lr': 1.2722620860386114e-05, 'samples': 25902144, 'steps': 134906, 'loss/train': 0.9306337833404541} 08/31/2021 13:37:33 - INFO - __main__ - Step 134908: {'lr': 1.272094957473588e-05, 'samples': 25902336, 'steps': 134907, 'loss/train': 1.3396044969558716} 08/31/2021 13:37:33 - INFO - __main__ - Step 134909: {'lr': 1.2719278395999956e-05, 'samples': 25902528, 'steps': 134908, 'loss/train': 0.8541350960731506} 08/31/2021 13:37:34 - INFO - __main__ - Step 134910: {'lr': 1.2717607324179064e-05, 'samples': 25902720, 'steps': 134909, 'loss/train': 0.9926028847694397} 08/31/2021 13:37:34 - INFO - __main__ - Step 134911: {'lr': 1.2715936359273956e-05, 'samples': 25902912, 'steps': 134910, 'loss/train': 1.2597821950912476} 08/31/2021 13:37:36 - INFO - __main__ - Step 134912: {'lr': 1.2714265501285349e-05, 'samples': 25903104, 'steps': 134911, 'loss/train': 1.583380103111267} 08/31/2021 13:37:37 - INFO - __main__ - Step 134913: {'lr': 1.2712594750214052e-05, 'samples': 25903296, 'steps': 134912, 'loss/train': 1.0295665264129639} 08/31/2021 13:37:37 - INFO - __main__ - Step 134914: {'lr': 1.2710924106060812e-05, 'samples': 25903488, 'steps': 134913, 'loss/train': 0.015620178543031216} 08/31/2021 13:37:37 - INFO - __main__ - Step 134915: {'lr': 1.2709253568826352e-05, 'samples': 25903680, 'steps': 134914, 'loss/train': 1.3283530473709106} 08/31/2021 13:37:38 - INFO - __main__ - Step 134916: {'lr': 1.2707583138511448e-05, 'samples': 25903872, 'steps': 134915, 'loss/train': 1.4027349948883057} 08/31/2021 13:37:38 - INFO - __main__ - Step 134917: {'lr': 1.2705912815116821e-05, 'samples': 25904064, 'steps': 134916, 'loss/train': 1.0621964931488037} 08/31/2021 13:37:40 - INFO - __main__ - Step 134918: {'lr': 1.270424259864328e-05, 'samples': 25904256, 'steps': 134917, 'loss/train': 0.48073527216911316} 08/31/2021 13:37:41 - INFO - __main__ - Step 134919: {'lr': 1.2702572489091541e-05, 'samples': 25904448, 'steps': 134918, 'loss/train': 1.077742338180542} 08/31/2021 13:37:41 - INFO - __main__ - Step 134920: {'lr': 1.2700902486462356e-05, 'samples': 25904640, 'steps': 134919, 'loss/train': 0.8520567417144775} 08/31/2021 13:37:41 - INFO - __main__ - Step 134921: {'lr': 1.2699232590756476e-05, 'samples': 25904832, 'steps': 134920, 'loss/train': 0.46169668436050415} 08/31/2021 13:37:42 - INFO - __main__ - Step 134922: {'lr': 1.269756280197465e-05, 'samples': 25905024, 'steps': 134921, 'loss/train': 0.5872787833213806} 08/31/2021 13:37:42 - INFO - __main__ - Step 134923: {'lr': 1.2695893120117707e-05, 'samples': 25905216, 'steps': 134922, 'loss/train': 0.6826679110527039} 08/31/2021 13:37:43 - INFO - __main__ - Step 134924: {'lr': 1.2694223545186262e-05, 'samples': 25905408, 'steps': 134923, 'loss/train': 1.3082784414291382} 08/31/2021 13:37:44 - INFO - __main__ - Step 134925: {'lr': 1.2692554077181173e-05, 'samples': 25905600, 'steps': 134924, 'loss/train': 0.7076417803764343} 08/31/2021 13:37:44 - INFO - __main__ - Step 134926: {'lr': 1.2690884716103135e-05, 'samples': 25905792, 'steps': 134925, 'loss/train': 1.072828769683838} 08/31/2021 13:37:45 - INFO - __main__ - Step 134927: {'lr': 1.2689215461952924e-05, 'samples': 25905984, 'steps': 134926, 'loss/train': 1.1817137002944946} 08/31/2021 13:37:45 - INFO - __main__ - Step 134928: {'lr': 1.2687546314731291e-05, 'samples': 25906176, 'steps': 134927, 'loss/train': 0.7703794836997986} 08/31/2021 13:37:46 - INFO - __main__ - Step 134929: {'lr': 1.2685877274438984e-05, 'samples': 25906368, 'steps': 134928, 'loss/train': 1.2584385871887207} 08/31/2021 13:37:47 - INFO - __main__ - Step 134930: {'lr': 1.2684208341076781e-05, 'samples': 25906560, 'steps': 134929, 'loss/train': 1.4302079677581787} 08/31/2021 13:37:47 - INFO - __main__ - Step 134931: {'lr': 1.2682539514645402e-05, 'samples': 25906752, 'steps': 134930, 'loss/train': 0.942008376121521} 08/31/2021 13:37:47 - INFO - __main__ - Step 134932: {'lr': 1.26808707951456e-05, 'samples': 25906944, 'steps': 134931, 'loss/train': 0.7446770071983337} 08/31/2021 13:37:48 - INFO - __main__ - Step 134933: {'lr': 1.2679202182578148e-05, 'samples': 25907136, 'steps': 134932, 'loss/train': 1.212363362312317} 08/31/2021 13:37:50 - INFO - __main__ - Step 134934: {'lr': 1.267753367694377e-05, 'samples': 25907328, 'steps': 134933, 'loss/train': 1.1569191217422485} 08/31/2021 13:37:50 - INFO - __main__ - Step 134935: {'lr': 1.2675865278243243e-05, 'samples': 25907520, 'steps': 134934, 'loss/train': 1.3055236339569092} 08/31/2021 13:37:50 - INFO - __main__ - Step 134936: {'lr': 1.2674196986477288e-05, 'samples': 25907712, 'steps': 134935, 'loss/train': 1.1263800859451294} 08/31/2021 13:37:51 - INFO - __main__ - Step 134937: {'lr': 1.2672528801646738e-05, 'samples': 25907904, 'steps': 134936, 'loss/train': 0.875171422958374} 08/31/2021 13:37:51 - INFO - __main__ - Step 134938: {'lr': 1.2670860723752231e-05, 'samples': 25908096, 'steps': 134937, 'loss/train': 2.4144511222839355} 08/31/2021 13:37:53 - INFO - __main__ - Step 134939: {'lr': 1.26691927527946e-05, 'samples': 25908288, 'steps': 134938, 'loss/train': 1.1688488721847534} 08/31/2021 13:37:53 - INFO - __main__ - Step 134940: {'lr': 1.266752488877454e-05, 'samples': 25908480, 'steps': 134939, 'loss/train': 1.431863784790039} 08/31/2021 13:37:53 - INFO - __main__ - Step 134941: {'lr': 1.2665857131692853e-05, 'samples': 25908672, 'steps': 134940, 'loss/train': 1.0062862634658813} 08/31/2021 13:37:54 - INFO - __main__ - Step 134942: {'lr': 1.2664189481550236e-05, 'samples': 25908864, 'steps': 134941, 'loss/train': 0.28394386172294617} 08/31/2021 13:37:54 - INFO - __main__ - Step 134943: {'lr': 1.266252193834752e-05, 'samples': 25909056, 'steps': 134942, 'loss/train': 1.3758968114852905} 08/31/2021 13:37:56 - INFO - __main__ - Step 134944: {'lr': 1.2660854502085373e-05, 'samples': 25909248, 'steps': 134943, 'loss/train': 1.134063482284546} 08/31/2021 13:37:56 - INFO - __main__ - Step 134945: {'lr': 1.2659187172764597e-05, 'samples': 25909440, 'steps': 134944, 'loss/train': 0.5068577527999878} 08/31/2021 13:37:57 - INFO - __main__ - Step 134946: {'lr': 1.2657519950385914e-05, 'samples': 25909632, 'steps': 134945, 'loss/train': 0.020056625828146935} 08/31/2021 13:37:57 - INFO - __main__ - Step 134947: {'lr': 1.2655852834950104e-05, 'samples': 25909824, 'steps': 134946, 'loss/train': 1.4857362508773804} 08/31/2021 13:37:57 - INFO - __main__ - Step 134948: {'lr': 1.2654185826457914e-05, 'samples': 25910016, 'steps': 134947, 'loss/train': 1.4587501287460327} 08/31/2021 13:37:58 - INFO - __main__ - Step 134949: {'lr': 1.2652518924910067e-05, 'samples': 25910208, 'steps': 134948, 'loss/train': 0.10597378760576248} 08/31/2021 13:38:00 - INFO - __main__ - Step 134950: {'lr': 1.2650852130307367e-05, 'samples': 25910400, 'steps': 134949, 'loss/train': 1.5555261373519897} 08/31/2021 13:38:00 - INFO - __main__ - Step 134951: {'lr': 1.2649185442650507e-05, 'samples': 25910592, 'steps': 134950, 'loss/train': 0.3055545687675476} 08/31/2021 13:38:01 - INFO - __main__ - Step 134952: {'lr': 1.2647518861940266e-05, 'samples': 25910784, 'steps': 134951, 'loss/train': 0.6483296155929565} 08/31/2021 13:38:01 - INFO - __main__ - Step 134953: {'lr': 1.2645852388177365e-05, 'samples': 25910976, 'steps': 134952, 'loss/train': 1.3124116659164429} 08/31/2021 13:38:01 - INFO - __main__ - Step 134954: {'lr': 1.2644186021362608e-05, 'samples': 25911168, 'steps': 134953, 'loss/train': 0.6144459247589111} 08/31/2021 13:38:03 - INFO - __main__ - Step 134955: {'lr': 1.264251976149669e-05, 'samples': 25911360, 'steps': 134954, 'loss/train': 0.03500929847359657} 08/31/2021 13:38:03 - INFO - __main__ - Step 134956: {'lr': 1.2640853608580416e-05, 'samples': 25911552, 'steps': 134955, 'loss/train': 0.02781478315591812} 08/31/2021 13:38:04 - INFO - __main__ - Step 134957: {'lr': 1.2639187562614507e-05, 'samples': 25911744, 'steps': 134956, 'loss/train': 1.2886415719985962} 08/31/2021 13:38:04 - INFO - __main__ - Step 134958: {'lr': 1.2637521623599713e-05, 'samples': 25911936, 'steps': 134957, 'loss/train': 1.5246490240097046} 08/31/2021 13:38:04 - INFO - __main__ - Step 134959: {'lr': 1.2635855791536782e-05, 'samples': 25912128, 'steps': 134958, 'loss/train': 1.021024465560913} 08/31/2021 13:38:05 - INFO - __main__ - Step 134960: {'lr': 1.2634190066426466e-05, 'samples': 25912320, 'steps': 134959, 'loss/train': 0.9542465209960938} 08/31/2021 13:38:06 - INFO - __main__ - Step 134961: {'lr': 1.263252444826954e-05, 'samples': 25912512, 'steps': 134960, 'loss/train': 1.147379755973816} 08/31/2021 13:38:07 - INFO - __main__ - Step 134962: {'lr': 1.2630858937066725e-05, 'samples': 25912704, 'steps': 134961, 'loss/train': 0.9335348010063171} 08/31/2021 13:38:07 - INFO - __main__ - Step 134963: {'lr': 1.26291935328188e-05, 'samples': 25912896, 'steps': 134962, 'loss/train': 0.8712024092674255} 08/31/2021 13:38:07 - INFO - __main__ - Step 134964: {'lr': 1.2627528235526514e-05, 'samples': 25913088, 'steps': 134963, 'loss/train': 1.067775011062622} 08/31/2021 13:38:08 - INFO - __main__ - Step 134965: {'lr': 1.262586304519056e-05, 'samples': 25913280, 'steps': 134964, 'loss/train': 1.180693507194519} 08/31/2021 13:38:10 - INFO - __main__ - Step 134966: {'lr': 1.2624197961811745e-05, 'samples': 25913472, 'steps': 134965, 'loss/train': 0.5253954529762268} 08/31/2021 13:38:10 - INFO - __main__ - Step 134967: {'lr': 1.262253298539079e-05, 'samples': 25913664, 'steps': 134966, 'loss/train': 1.0103015899658203} 08/31/2021 13:38:11 - INFO - __main__ - Step 134968: {'lr': 1.2620868115928469e-05, 'samples': 25913856, 'steps': 134967, 'loss/train': 0.9938967227935791} 08/31/2021 13:38:11 - INFO - __main__ - Step 134969: {'lr': 1.2619203353425506e-05, 'samples': 25914048, 'steps': 134968, 'loss/train': 0.626036524772644} 08/31/2021 13:38:11 - INFO - __main__ - Step 134970: {'lr': 1.261753869788268e-05, 'samples': 25914240, 'steps': 134969, 'loss/train': 0.2636701166629791} 08/31/2021 13:38:13 - INFO - __main__ - Step 134971: {'lr': 1.2615874149300737e-05, 'samples': 25914432, 'steps': 134970, 'loss/train': 0.9797124862670898} 08/31/2021 13:38:13 - INFO - __main__ - Step 134972: {'lr': 1.2614209707680401e-05, 'samples': 25914624, 'steps': 134971, 'loss/train': 1.2257986068725586} 08/31/2021 13:38:14 - INFO - __main__ - Step 134973: {'lr': 1.2612545373022449e-05, 'samples': 25914816, 'steps': 134972, 'loss/train': 1.8402411937713623} 08/31/2021 13:38:14 - INFO - __main__ - Step 134974: {'lr': 1.261088114532763e-05, 'samples': 25915008, 'steps': 134973, 'loss/train': 1.1689127683639526} 08/31/2021 13:38:14 - INFO - __main__ - Step 134975: {'lr': 1.2609217024596664e-05, 'samples': 25915200, 'steps': 134974, 'loss/train': 1.2012503147125244} 08/31/2021 13:38:16 - INFO - __main__ - Step 134976: {'lr': 1.260755301083033e-05, 'samples': 25915392, 'steps': 134975, 'loss/train': 0.29330113530158997} 08/31/2021 13:38:16 - INFO - __main__ - Step 134977: {'lr': 1.2605889104029406e-05, 'samples': 25915584, 'steps': 134976, 'loss/train': 0.5287946462631226} 08/31/2021 13:38:17 - INFO - __main__ - Step 134978: {'lr': 1.2604225304194584e-05, 'samples': 25915776, 'steps': 134977, 'loss/train': 0.36041468381881714} 08/31/2021 13:38:17 - INFO - __main__ - Step 134979: {'lr': 1.2602561611326613e-05, 'samples': 25915968, 'steps': 134978, 'loss/train': 0.2099851816892624} 08/31/2021 13:38:17 - INFO - __main__ - Step 134980: {'lr': 1.2600898025426272e-05, 'samples': 25916160, 'steps': 134979, 'loss/train': 0.9283639192581177} 08/31/2021 13:38:18 - INFO - __main__ - Step 134981: {'lr': 1.259923454649431e-05, 'samples': 25916352, 'steps': 134980, 'loss/train': 0.6088719367980957} 08/31/2021 13:38:19 - INFO - __main__ - Step 134982: {'lr': 1.2597571174531447e-05, 'samples': 25916544, 'steps': 134981, 'loss/train': 0.3546682298183441} 08/31/2021 13:38:20 - INFO - __main__ - Step 134983: {'lr': 1.259590790953849e-05, 'samples': 25916736, 'steps': 134982, 'loss/train': 0.9410812854766846} 08/31/2021 13:38:20 - INFO - __main__ - Step 134984: {'lr': 1.2594244751516133e-05, 'samples': 25916928, 'steps': 134983, 'loss/train': 1.2180992364883423} 08/31/2021 13:38:21 - INFO - __main__ - Step 134985: {'lr': 1.2592581700465122e-05, 'samples': 25917120, 'steps': 134984, 'loss/train': 1.041689157485962} 08/31/2021 13:38:21 - INFO - __main__ - Step 134986: {'lr': 1.2590918756386266e-05, 'samples': 25917312, 'steps': 134985, 'loss/train': 0.3143776059150696} 08/31/2021 13:38:23 - INFO - __main__ - Step 134987: {'lr': 1.2589255919280257e-05, 'samples': 25917504, 'steps': 134986, 'loss/train': 0.02481113001704216} 08/31/2021 13:38:23 - INFO - __main__ - Step 134988: {'lr': 1.25875931891479e-05, 'samples': 25917696, 'steps': 134987, 'loss/train': 1.4638080596923828} 08/31/2021 13:38:23 - INFO - __main__ - Step 134989: {'lr': 1.258593056598989e-05, 'samples': 25917888, 'steps': 134988, 'loss/train': 1.2014254331588745} 08/31/2021 13:38:24 - INFO - __main__ - Step 134990: {'lr': 1.2584268049807001e-05, 'samples': 25918080, 'steps': 134989, 'loss/train': 1.1715530157089233} 08/31/2021 13:38:24 - INFO - __main__ - Step 134991: {'lr': 1.2582605640599987e-05, 'samples': 25918272, 'steps': 134990, 'loss/train': 1.0717719793319702} 08/31/2021 13:38:26 - INFO - __main__ - Step 134992: {'lr': 1.2580943338369565e-05, 'samples': 25918464, 'steps': 134991, 'loss/train': 1.1733522415161133} 08/31/2021 13:38:26 - INFO - __main__ - Step 134993: {'lr': 1.2579281143116516e-05, 'samples': 25918656, 'steps': 134992, 'loss/train': 1.1917712688446045} 08/31/2021 13:38:26 - INFO - __main__ - Step 134994: {'lr': 1.257761905484156e-05, 'samples': 25918848, 'steps': 134993, 'loss/train': 0.7310028672218323} 08/31/2021 13:38:27 - INFO - __main__ - Step 134995: {'lr': 1.2575957073545503e-05, 'samples': 25919040, 'steps': 134994, 'loss/train': 0.4511786699295044} 08/31/2021 13:38:27 - INFO - __main__ - Step 134996: {'lr': 1.2574295199229007e-05, 'samples': 25919232, 'steps': 134995, 'loss/train': 1.5375640392303467} 08/31/2021 13:38:29 - INFO - __main__ - Step 134997: {'lr': 1.257263343189291e-05, 'samples': 25919424, 'steps': 134996, 'loss/train': 1.601319432258606} 08/31/2021 13:38:30 - INFO - __main__ - Step 134998: {'lr': 1.2570971771537903e-05, 'samples': 25919616, 'steps': 134997, 'loss/train': 0.5697882771492004} 08/31/2021 13:38:30 - INFO - __main__ - Step 134999: {'lr': 1.2569310218164765e-05, 'samples': 25919808, 'steps': 134998, 'loss/train': 1.9707053899765015} 08/31/2021 13:38:30 - INFO - __main__ - Step 135000: {'lr': 1.2567648771774215e-05, 'samples': 25920000, 'steps': 134999, 'loss/train': 0.10141287744045258} 08/31/2021 13:38:31 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 13:47:16 - INFO - __main__ - Step 135000: {'loss/eval': 0.95810866355896, 'perplexity': 2.6067614555358887} 08/31/2021 13:47:16 - INFO - __main__ - Saving model checkpoint 08/31/2021 13:48:17 - INFO - __main__ - Step 135001: {'lr': 1.2565987432367032e-05, 'samples': 25920192, 'steps': 135000, 'loss/train': 0.5847126245498657} 08/31/2021 13:48:17 - INFO - __main__ - Step 135002: {'lr': 1.2564326199943937e-05, 'samples': 25920384, 'steps': 135001, 'loss/train': 1.295280933380127} 08/31/2021 13:48:19 - INFO - __main__ - Step 135003: {'lr': 1.2562665074505708e-05, 'samples': 25920576, 'steps': 135002, 'loss/train': 1.0055044889450073} 08/31/2021 13:48:19 - INFO - __main__ - Step 135004: {'lr': 1.2561004056053093e-05, 'samples': 25920768, 'steps': 135003, 'loss/train': 0.7044036984443665} 08/31/2021 13:48:19 - INFO - __main__ - Step 135005: {'lr': 1.2559343144586816e-05, 'samples': 25920960, 'steps': 135004, 'loss/train': 1.0922901630401611} 08/31/2021 13:48:20 - INFO - __main__ - Step 135006: {'lr': 1.2557682340107624e-05, 'samples': 25921152, 'steps': 135005, 'loss/train': 1.342663288116455} 08/31/2021 13:48:20 - INFO - __main__ - Step 135007: {'lr': 1.2556021642616267e-05, 'samples': 25921344, 'steps': 135006, 'loss/train': 0.9880815148353577} 08/31/2021 13:48:22 - INFO - __main__ - Step 135008: {'lr': 1.2554361052113522e-05, 'samples': 25921536, 'steps': 135007, 'loss/train': 1.2763948440551758} 08/31/2021 13:48:22 - INFO - __main__ - Step 135009: {'lr': 1.2552700568600084e-05, 'samples': 25921728, 'steps': 135008, 'loss/train': 1.220281958580017} 08/31/2021 13:48:22 - INFO - __main__ - Step 135010: {'lr': 1.2551040192076784e-05, 'samples': 25921920, 'steps': 135009, 'loss/train': 0.7884277105331421} 08/31/2021 13:48:23 - INFO - __main__ - Step 135011: {'lr': 1.2549379922544291e-05, 'samples': 25922112, 'steps': 135010, 'loss/train': 0.906453549861908} 08/31/2021 13:48:23 - INFO - __main__ - Step 135012: {'lr': 1.2547719760003379e-05, 'samples': 25922304, 'steps': 135011, 'loss/train': 1.132835030555725} 08/31/2021 13:48:25 - INFO - __main__ - Step 135013: {'lr': 1.2546059704454798e-05, 'samples': 25922496, 'steps': 135012, 'loss/train': 1.252988338470459} 08/31/2021 13:48:25 - INFO - __main__ - Step 135014: {'lr': 1.2544399755899328e-05, 'samples': 25922688, 'steps': 135013, 'loss/train': 1.0422799587249756} 08/31/2021 13:48:25 - INFO - __main__ - Step 135015: {'lr': 1.2542739914337658e-05, 'samples': 25922880, 'steps': 135014, 'loss/train': 0.9178308248519897} 08/31/2021 13:48:26 - INFO - __main__ - Step 135016: {'lr': 1.2541080179770569e-05, 'samples': 25923072, 'steps': 135015, 'loss/train': 0.08996499329805374} 08/31/2021 13:48:26 - INFO - __main__ - Step 135017: {'lr': 1.2539420552198866e-05, 'samples': 25923264, 'steps': 135016, 'loss/train': 0.6197190880775452} 08/31/2021 13:48:28 - INFO - __main__ - Step 135018: {'lr': 1.2537761031623184e-05, 'samples': 25923456, 'steps': 135017, 'loss/train': 0.8901882171630859} 08/31/2021 13:48:29 - INFO - __main__ - Step 135019: {'lr': 1.2536101618044305e-05, 'samples': 25923648, 'steps': 135018, 'loss/train': 1.019192099571228} 08/31/2021 13:48:29 - INFO - __main__ - Step 135020: {'lr': 1.2534442311463001e-05, 'samples': 25923840, 'steps': 135019, 'loss/train': 1.094631552696228} 08/31/2021 13:48:30 - INFO - __main__ - Step 135021: {'lr': 1.2532783111880025e-05, 'samples': 25924032, 'steps': 135020, 'loss/train': 1.2211658954620361} 08/31/2021 13:48:30 - INFO - __main__ - Step 135022: {'lr': 1.2531124019296125e-05, 'samples': 25924224, 'steps': 135021, 'loss/train': 0.1391332745552063} 08/31/2021 13:48:30 - INFO - __main__ - Step 135023: {'lr': 1.2529465033712023e-05, 'samples': 25924416, 'steps': 135022, 'loss/train': 1.0264549255371094} 08/31/2021 13:48:32 - INFO - __main__ - Step 135024: {'lr': 1.2527806155128469e-05, 'samples': 25924608, 'steps': 135023, 'loss/train': 0.04002552852034569} 08/31/2021 13:48:32 - INFO - __main__ - Step 135025: {'lr': 1.2526147383546238e-05, 'samples': 25924800, 'steps': 135024, 'loss/train': 0.0735788568854332} 08/31/2021 13:48:33 - INFO - __main__ - Step 135026: {'lr': 1.2524488718966054e-05, 'samples': 25924992, 'steps': 135025, 'loss/train': 0.451819509267807} 08/31/2021 13:48:33 - INFO - __main__ - Step 135027: {'lr': 1.2522830161388666e-05, 'samples': 25925184, 'steps': 135026, 'loss/train': 0.03557639941573143} 08/31/2021 13:48:33 - INFO - __main__ - Step 135028: {'lr': 1.2521171710814822e-05, 'samples': 25925376, 'steps': 135027, 'loss/train': 1.108849048614502} 08/31/2021 13:48:35 - INFO - __main__ - Step 135029: {'lr': 1.2519513367245273e-05, 'samples': 25925568, 'steps': 135028, 'loss/train': 1.1850371360778809} 08/31/2021 13:48:35 - INFO - __main__ - Step 135030: {'lr': 1.2517855130680766e-05, 'samples': 25925760, 'steps': 135029, 'loss/train': 1.0195956230163574} 08/31/2021 13:48:36 - INFO - __main__ - Step 135031: {'lr': 1.251619700112211e-05, 'samples': 25925952, 'steps': 135030, 'loss/train': 0.09627507627010345} 08/31/2021 13:48:36 - INFO - __main__ - Step 135032: {'lr': 1.251453897856994e-05, 'samples': 25926144, 'steps': 135031, 'loss/train': 1.1204866170883179} 08/31/2021 13:48:37 - INFO - __main__ - Step 135033: {'lr': 1.2512881063025033e-05, 'samples': 25926336, 'steps': 135032, 'loss/train': 1.05014967918396} 08/31/2021 13:48:38 - INFO - __main__ - Step 135034: {'lr': 1.2511223254488197e-05, 'samples': 25926528, 'steps': 135033, 'loss/train': 0.5600053668022156} 08/31/2021 13:48:39 - INFO - __main__ - Step 135035: {'lr': 1.2509565552960122e-05, 'samples': 25926720, 'steps': 135034, 'loss/train': 1.481569528579712} 08/31/2021 13:48:39 - INFO - __main__ - Step 135036: {'lr': 1.2507907958441561e-05, 'samples': 25926912, 'steps': 135035, 'loss/train': 1.4082988500595093} 08/31/2021 13:48:39 - INFO - __main__ - Step 135037: {'lr': 1.2506250470933262e-05, 'samples': 25927104, 'steps': 135036, 'loss/train': 0.4196387529373169} 08/31/2021 13:48:40 - INFO - __main__ - Step 135038: {'lr': 1.2504593090436e-05, 'samples': 25927296, 'steps': 135037, 'loss/train': 1.3567572832107544} 08/31/2021 13:48:40 - INFO - __main__ - Step 135039: {'lr': 1.25029358169505e-05, 'samples': 25927488, 'steps': 135038, 'loss/train': 0.991367757320404} 08/31/2021 13:48:42 - INFO - __main__ - Step 135040: {'lr': 1.2501278650477537e-05, 'samples': 25927680, 'steps': 135039, 'loss/train': 1.1579450368881226} 08/31/2021 13:48:42 - INFO - __main__ - Step 135041: {'lr': 1.2499621591017807e-05, 'samples': 25927872, 'steps': 135040, 'loss/train': 1.0819120407104492} 08/31/2021 13:48:42 - INFO - __main__ - Step 135042: {'lr': 1.2497964638572085e-05, 'samples': 25928064, 'steps': 135041, 'loss/train': 1.610607385635376} 08/31/2021 13:48:43 - INFO - __main__ - Step 135043: {'lr': 1.249630779314112e-05, 'samples': 25928256, 'steps': 135042, 'loss/train': 0.6706324219703674} 08/31/2021 13:48:43 - INFO - __main__ - Step 135044: {'lr': 1.2494651054725693e-05, 'samples': 25928448, 'steps': 135043, 'loss/train': 0.9356200098991394} 08/31/2021 13:48:45 - INFO - __main__ - Step 135045: {'lr': 1.2492994423326465e-05, 'samples': 25928640, 'steps': 135044, 'loss/train': 1.5729444026947021} 08/31/2021 13:48:45 - INFO - __main__ - Step 135046: {'lr': 1.2491337898944217e-05, 'samples': 25928832, 'steps': 135045, 'loss/train': 0.6674590706825256} 08/31/2021 13:48:45 - INFO - __main__ - Step 135047: {'lr': 1.2489681481579723e-05, 'samples': 25929024, 'steps': 135046, 'loss/train': 0.6019974946975708} 08/31/2021 13:48:46 - INFO - __main__ - Step 135048: {'lr': 1.2488025171233707e-05, 'samples': 25929216, 'steps': 135047, 'loss/train': 1.259133219718933} 08/31/2021 13:48:46 - INFO - __main__ - Step 135049: {'lr': 1.2486368967906946e-05, 'samples': 25929408, 'steps': 135048, 'loss/train': 0.7393923401832581} 08/31/2021 13:48:48 - INFO - __main__ - Step 135050: {'lr': 1.2484712871600135e-05, 'samples': 25929600, 'steps': 135049, 'loss/train': 1.2644290924072266} 08/31/2021 13:48:48 - INFO - __main__ - Step 135051: {'lr': 1.2483056882314076e-05, 'samples': 25929792, 'steps': 135050, 'loss/train': 1.000166654586792} 08/31/2021 13:48:48 - INFO - __main__ - Step 135052: {'lr': 1.2481401000049463e-05, 'samples': 25929984, 'steps': 135051, 'loss/train': 0.6489465236663818} 08/31/2021 13:48:49 - INFO - __main__ - Step 135053: {'lr': 1.2479745224807049e-05, 'samples': 25930176, 'steps': 135052, 'loss/train': 1.4047845602035522} 08/31/2021 13:48:49 - INFO - __main__ - Step 135054: {'lr': 1.2478089556587635e-05, 'samples': 25930368, 'steps': 135053, 'loss/train': 0.8808494210243225} 08/31/2021 13:48:51 - INFO - __main__ - Step 135055: {'lr': 1.2476433995391916e-05, 'samples': 25930560, 'steps': 135054, 'loss/train': 0.9921820759773254} 08/31/2021 13:48:51 - INFO - __main__ - Step 135056: {'lr': 1.2474778541220644e-05, 'samples': 25930752, 'steps': 135055, 'loss/train': 1.4560922384262085} 08/31/2021 13:48:51 - INFO - __main__ - Step 135057: {'lr': 1.2473123194074564e-05, 'samples': 25930944, 'steps': 135056, 'loss/train': 0.520300030708313} 08/31/2021 13:48:52 - INFO - __main__ - Step 135058: {'lr': 1.2471467953954486e-05, 'samples': 25931136, 'steps': 135057, 'loss/train': 0.9288191795349121} 08/31/2021 13:48:52 - INFO - __main__ - Step 135059: {'lr': 1.2469812820861044e-05, 'samples': 25931328, 'steps': 135058, 'loss/train': 1.3324579000473022} 08/31/2021 13:48:52 - INFO - __main__ - Step 135060: {'lr': 1.2468157794795042e-05, 'samples': 25931520, 'steps': 135059, 'loss/train': 0.8088751435279846} 08/31/2021 13:48:54 - INFO - __main__ - Step 135061: {'lr': 1.2466502875757236e-05, 'samples': 25931712, 'steps': 135060, 'loss/train': 0.9418694972991943} 08/31/2021 13:48:54 - INFO - __main__ - Step 135062: {'lr': 1.2464848063748341e-05, 'samples': 25931904, 'steps': 135061, 'loss/train': 0.16677074134349823} 08/31/2021 13:48:55 - INFO - __main__ - Step 135063: {'lr': 1.2463193358769137e-05, 'samples': 25932096, 'steps': 135062, 'loss/train': 1.5509059429168701} 08/31/2021 13:48:55 - INFO - __main__ - Step 135064: {'lr': 1.2461538760820346e-05, 'samples': 25932288, 'steps': 135063, 'loss/train': 1.0805401802062988} 08/31/2021 13:48:55 - INFO - __main__ - Step 135065: {'lr': 1.2459884269902716e-05, 'samples': 25932480, 'steps': 135064, 'loss/train': 1.455168604850769} 08/31/2021 13:48:57 - INFO - __main__ - Step 135066: {'lr': 1.2458229886016998e-05, 'samples': 25932672, 'steps': 135065, 'loss/train': 1.0773295164108276} 08/31/2021 13:48:58 - INFO - __main__ - Step 135067: {'lr': 1.245657560916394e-05, 'samples': 25932864, 'steps': 135066, 'loss/train': 0.391264945268631} 08/31/2021 13:48:58 - INFO - __main__ - Step 135068: {'lr': 1.2454921439344291e-05, 'samples': 25933056, 'steps': 135067, 'loss/train': 1.327908992767334} 08/31/2021 13:48:59 - INFO - __main__ - Step 135069: {'lr': 1.2453267376558774e-05, 'samples': 25933248, 'steps': 135068, 'loss/train': 0.9115989804267883} 08/31/2021 13:48:59 - INFO - __main__ - Step 135070: {'lr': 1.2451613420808138e-05, 'samples': 25933440, 'steps': 135069, 'loss/train': 0.1871924251317978} 08/31/2021 13:49:01 - INFO - __main__ - Step 135071: {'lr': 1.2449959572093189e-05, 'samples': 25933632, 'steps': 135070, 'loss/train': 0.2188451886177063} 08/31/2021 13:49:01 - INFO - __main__ - Step 135072: {'lr': 1.244830583041459e-05, 'samples': 25933824, 'steps': 135071, 'loss/train': 1.3994861841201782} 08/31/2021 13:49:02 - INFO - __main__ - Step 135073: {'lr': 1.2446652195773123e-05, 'samples': 25934016, 'steps': 135072, 'loss/train': 1.1477171182632446} 08/31/2021 13:49:02 - INFO - __main__ - Step 135074: {'lr': 1.2444998668169533e-05, 'samples': 25934208, 'steps': 135073, 'loss/train': 0.45672446489334106} 08/31/2021 13:49:02 - INFO - __main__ - Step 135075: {'lr': 1.2443345247604542e-05, 'samples': 25934400, 'steps': 135074, 'loss/train': 0.8511075377464294} 08/31/2021 13:49:04 - INFO - __main__ - Step 135076: {'lr': 1.244169193407893e-05, 'samples': 25934592, 'steps': 135075, 'loss/train': 1.2083284854888916} 08/31/2021 13:49:04 - INFO - __main__ - Step 135077: {'lr': 1.2440038727593418e-05, 'samples': 25934784, 'steps': 135076, 'loss/train': 1.0299961566925049} 08/31/2021 13:49:05 - INFO - __main__ - Step 135078: {'lr': 1.2438385628148751e-05, 'samples': 25934976, 'steps': 135077, 'loss/train': 0.5738905668258667} 08/31/2021 13:49:05 - INFO - __main__ - Step 135079: {'lr': 1.2436732635745711e-05, 'samples': 25935168, 'steps': 135078, 'loss/train': 0.25847145915031433} 08/31/2021 13:49:05 - INFO - __main__ - Step 135080: {'lr': 1.2435079750384992e-05, 'samples': 25935360, 'steps': 135079, 'loss/train': 1.503548264503479} 08/31/2021 13:49:07 - INFO - __main__ - Step 135081: {'lr': 1.2433426972067341e-05, 'samples': 25935552, 'steps': 135080, 'loss/train': 0.5497274994850159} 08/31/2021 13:49:08 - INFO - __main__ - Step 135082: {'lr': 1.2431774300793564e-05, 'samples': 25935744, 'steps': 135081, 'loss/train': 1.444219946861267} 08/31/2021 13:49:08 - INFO - __main__ - Step 135083: {'lr': 1.2430121736564325e-05, 'samples': 25935936, 'steps': 135082, 'loss/train': 0.9467884302139282} 08/31/2021 13:49:08 - INFO - __main__ - Step 135084: {'lr': 1.2428469279380433e-05, 'samples': 25936128, 'steps': 135083, 'loss/train': 1.2912037372589111} 08/31/2021 13:49:09 - INFO - __main__ - Step 135085: {'lr': 1.2426816929242634e-05, 'samples': 25936320, 'steps': 135084, 'loss/train': 1.2202513217926025} 08/31/2021 13:49:09 - INFO - __main__ - Step 135086: {'lr': 1.2425164686151596e-05, 'samples': 25936512, 'steps': 135085, 'loss/train': 0.6695200800895691} 08/31/2021 13:49:10 - INFO - __main__ - Step 135087: {'lr': 1.2423512550108151e-05, 'samples': 25936704, 'steps': 135086, 'loss/train': 0.9979379177093506} 08/31/2021 13:49:11 - INFO - __main__ - Step 135088: {'lr': 1.2421860521112966e-05, 'samples': 25936896, 'steps': 135087, 'loss/train': 0.9536484479904175} 08/31/2021 13:49:11 - INFO - __main__ - Step 135089: {'lr': 1.2420208599166843e-05, 'samples': 25937088, 'steps': 135088, 'loss/train': 0.954595148563385} 08/31/2021 13:49:12 - INFO - __main__ - Step 135090: {'lr': 1.2418556784270508e-05, 'samples': 25937280, 'steps': 135089, 'loss/train': 1.3432284593582153} 08/31/2021 13:49:12 - INFO - __main__ - Step 135091: {'lr': 1.2416905076424706e-05, 'samples': 25937472, 'steps': 135090, 'loss/train': 1.3575445413589478} 08/31/2021 13:49:13 - INFO - __main__ - Step 135092: {'lr': 1.2415253475630161e-05, 'samples': 25937664, 'steps': 135091, 'loss/train': 1.289048433303833} 08/31/2021 13:49:14 - INFO - __main__ - Step 135093: {'lr': 1.2413601981887652e-05, 'samples': 25937856, 'steps': 135092, 'loss/train': 1.1327389478683472} 08/31/2021 13:49:14 - INFO - __main__ - Step 135094: {'lr': 1.2411950595197923e-05, 'samples': 25938048, 'steps': 135093, 'loss/train': 1.4358850717544556} 08/31/2021 13:49:15 - INFO - __main__ - Step 135095: {'lr': 1.2410299315561673e-05, 'samples': 25938240, 'steps': 135094, 'loss/train': 0.8376724720001221} 08/31/2021 13:49:15 - INFO - __main__ - Step 135096: {'lr': 1.2408648142979707e-05, 'samples': 25938432, 'steps': 135095, 'loss/train': 1.383860468864441} 08/31/2021 13:49:16 - INFO - __main__ - Step 135097: {'lr': 1.2406997077452742e-05, 'samples': 25938624, 'steps': 135096, 'loss/train': 0.8688620328903198} 08/31/2021 13:49:17 - INFO - __main__ - Step 135098: {'lr': 1.2405346118981504e-05, 'samples': 25938816, 'steps': 135097, 'loss/train': 1.0019851922988892} 08/31/2021 13:49:17 - INFO - __main__ - Step 135099: {'lr': 1.240369526756674e-05, 'samples': 25939008, 'steps': 135098, 'loss/train': 1.465795636177063} 08/31/2021 13:49:18 - INFO - __main__ - Step 135100: {'lr': 1.24020445232092e-05, 'samples': 25939200, 'steps': 135099, 'loss/train': 1.3120460510253906} 08/31/2021 13:49:18 - INFO - __main__ - Step 135101: {'lr': 1.2400393885909633e-05, 'samples': 25939392, 'steps': 135100, 'loss/train': 0.7722108364105225} 08/31/2021 13:49:19 - INFO - __main__ - Step 135102: {'lr': 1.239874335566879e-05, 'samples': 25939584, 'steps': 135101, 'loss/train': 1.2657901048660278} 08/31/2021 13:49:20 - INFO - __main__ - Step 135103: {'lr': 1.239709293248742e-05, 'samples': 25939776, 'steps': 135102, 'loss/train': 1.1315782070159912} 08/31/2021 13:49:20 - INFO - __main__ - Step 135104: {'lr': 1.2395442616366243e-05, 'samples': 25939968, 'steps': 135103, 'loss/train': 1.145440936088562} 08/31/2021 13:49:20 - INFO - __main__ - Step 135105: {'lr': 1.239379240730601e-05, 'samples': 25940160, 'steps': 135104, 'loss/train': 1.1973475217819214} 08/31/2021 13:49:21 - INFO - __main__ - Step 135106: {'lr': 1.2392142305307469e-05, 'samples': 25940352, 'steps': 135105, 'loss/train': 1.3332366943359375} 08/31/2021 13:49:22 - INFO - __main__ - Step 135107: {'lr': 1.2390492310371343e-05, 'samples': 25940544, 'steps': 135106, 'loss/train': 1.9037635326385498} 08/31/2021 13:49:23 - INFO - __main__ - Step 135108: {'lr': 1.2388842422498464e-05, 'samples': 25940736, 'steps': 135107, 'loss/train': 0.22820039093494415} 08/31/2021 13:49:23 - INFO - __main__ - Step 135109: {'lr': 1.2387192641689444e-05, 'samples': 25940928, 'steps': 135108, 'loss/train': 0.2251032292842865} 08/31/2021 13:49:23 - INFO - __main__ - Step 135110: {'lr': 1.2385542967945113e-05, 'samples': 25941120, 'steps': 135109, 'loss/train': 0.9486038088798523} 08/31/2021 13:49:24 - INFO - __main__ - Step 135111: {'lr': 1.2383893401266166e-05, 'samples': 25941312, 'steps': 135110, 'loss/train': 1.0857573747634888} 08/31/2021 13:49:25 - INFO - __main__ - Step 135112: {'lr': 1.2382243941653382e-05, 'samples': 25941504, 'steps': 135111, 'loss/train': 0.6676401495933533} 08/31/2021 13:49:26 - INFO - __main__ - Step 135113: {'lr': 1.238059458910748e-05, 'samples': 25941696, 'steps': 135112, 'loss/train': 1.2957991361618042} 08/31/2021 13:49:26 - INFO - __main__ - Step 135114: {'lr': 1.2378945343629238e-05, 'samples': 25941888, 'steps': 135113, 'loss/train': 1.5895969867706299} 08/31/2021 13:49:26 - INFO - __main__ - Step 135115: {'lr': 1.237729620521935e-05, 'samples': 25942080, 'steps': 135114, 'loss/train': 0.7808403968811035} 08/31/2021 13:49:27 - INFO - __main__ - Step 135116: {'lr': 1.2375647173878596e-05, 'samples': 25942272, 'steps': 135115, 'loss/train': 2.3144378662109375} 08/31/2021 13:49:27 - INFO - __main__ - Step 135117: {'lr': 1.2373998249607721e-05, 'samples': 25942464, 'steps': 135116, 'loss/train': 1.2586122751235962} 08/31/2021 13:49:29 - INFO - __main__ - Step 135118: {'lr': 1.2372349432407449e-05, 'samples': 25942656, 'steps': 135117, 'loss/train': 0.9701846837997437} 08/31/2021 13:49:30 - INFO - __main__ - Step 135119: {'lr': 1.2370700722278555e-05, 'samples': 25942848, 'steps': 135118, 'loss/train': 0.9523749947547913} 08/31/2021 13:49:30 - INFO - __main__ - Step 135120: {'lr': 1.2369052119221736e-05, 'samples': 25943040, 'steps': 135119, 'loss/train': 0.9477087259292603} 08/31/2021 13:49:31 - INFO - __main__ - Step 135121: {'lr': 1.2367403623237738e-05, 'samples': 25943232, 'steps': 135120, 'loss/train': 0.79234379529953} 08/31/2021 13:49:31 - INFO - __main__ - Step 135122: {'lr': 1.2365755234327341e-05, 'samples': 25943424, 'steps': 135121, 'loss/train': 0.3893331289291382} 08/31/2021 13:49:33 - INFO - __main__ - Step 135123: {'lr': 1.2364106952491267e-05, 'samples': 25943616, 'steps': 135122, 'loss/train': 0.7882274389266968} 08/31/2021 13:49:34 - INFO - __main__ - Step 135124: {'lr': 1.2362458777730235e-05, 'samples': 25943808, 'steps': 135123, 'loss/train': 0.8979265689849854} 08/31/2021 13:49:34 - INFO - __main__ - Step 135125: {'lr': 1.2360810710045024e-05, 'samples': 25944000, 'steps': 135124, 'loss/train': 0.9814817309379578} 08/31/2021 13:49:34 - INFO - __main__ - Step 135126: {'lr': 1.235916274943638e-05, 'samples': 25944192, 'steps': 135125, 'loss/train': 0.051934950053691864} 08/31/2021 13:49:35 - INFO - __main__ - Step 135127: {'lr': 1.2357514895905003e-05, 'samples': 25944384, 'steps': 135126, 'loss/train': 1.605682611465454} 08/31/2021 13:49:36 - INFO - __main__ - Step 135128: {'lr': 1.2355867149451694e-05, 'samples': 25944576, 'steps': 135127, 'loss/train': 0.83848637342453} 08/31/2021 13:49:37 - INFO - __main__ - Step 135129: {'lr': 1.2354219510077147e-05, 'samples': 25944768, 'steps': 135128, 'loss/train': 1.647765874862671} 08/31/2021 13:49:37 - INFO - __main__ - Step 135130: {'lr': 1.235257197778214e-05, 'samples': 25944960, 'steps': 135129, 'loss/train': 1.033066749572754} 08/31/2021 13:49:38 - INFO - __main__ - Step 135131: {'lr': 1.2350924552567394e-05, 'samples': 25945152, 'steps': 135130, 'loss/train': 0.3684243857860565} 08/31/2021 13:49:38 - INFO - __main__ - Step 135132: {'lr': 1.2349277234433632e-05, 'samples': 25945344, 'steps': 135131, 'loss/train': 1.3116579055786133} 08/31/2021 13:49:38 - INFO - __main__ - Step 135133: {'lr': 1.2347630023381628e-05, 'samples': 25945536, 'steps': 135132, 'loss/train': 0.014180202037096024} 08/31/2021 13:49:40 - INFO - __main__ - Step 135134: {'lr': 1.2345982919412108e-05, 'samples': 25945728, 'steps': 135133, 'loss/train': 0.229545459151268} 08/31/2021 13:49:40 - INFO - __main__ - Step 135135: {'lr': 1.2344335922525845e-05, 'samples': 25945920, 'steps': 135134, 'loss/train': 1.3559370040893555} 08/31/2021 13:49:41 - INFO - __main__ - Step 135136: {'lr': 1.2342689032723537e-05, 'samples': 25946112, 'steps': 135135, 'loss/train': 0.12494873255491257} 08/31/2021 13:49:41 - INFO - __main__ - Step 135137: {'lr': 1.2341042250005929e-05, 'samples': 25946304, 'steps': 135136, 'loss/train': 1.0929995775222778} 08/31/2021 13:49:41 - INFO - __main__ - Step 135138: {'lr': 1.2339395574373801e-05, 'samples': 25946496, 'steps': 135137, 'loss/train': 1.1427260637283325} 08/31/2021 13:49:43 - INFO - __main__ - Step 135139: {'lr': 1.2337749005827876e-05, 'samples': 25946688, 'steps': 135138, 'loss/train': 0.8987998366355896} 08/31/2021 13:49:43 - INFO - __main__ - Step 135140: {'lr': 1.2336102544368926e-05, 'samples': 25946880, 'steps': 135139, 'loss/train': 0.4926239550113678} 08/31/2021 13:49:44 - INFO - __main__ - Step 135141: {'lr': 1.2334456189997623e-05, 'samples': 25947072, 'steps': 135140, 'loss/train': 1.5413826704025269} 08/31/2021 13:49:44 - INFO - __main__ - Step 135142: {'lr': 1.233280994271474e-05, 'samples': 25947264, 'steps': 135141, 'loss/train': 0.5975807309150696} 08/31/2021 13:49:44 - INFO - __main__ - Step 135143: {'lr': 1.2331163802521029e-05, 'samples': 25947456, 'steps': 135142, 'loss/train': 2.004133462905884} 08/31/2021 13:49:45 - INFO - __main__ - Step 135144: {'lr': 1.2329517769417237e-05, 'samples': 25947648, 'steps': 135143, 'loss/train': 1.2830023765563965} 08/31/2021 13:49:47 - INFO - __main__ - Step 135145: {'lr': 1.2327871843404087e-05, 'samples': 25947840, 'steps': 135144, 'loss/train': 0.6626518368721008} 08/31/2021 13:49:47 - INFO - __main__ - Step 135146: {'lr': 1.2326226024482329e-05, 'samples': 25948032, 'steps': 135145, 'loss/train': 0.5103579759597778} 08/31/2021 13:49:47 - INFO - __main__ - Step 135147: {'lr': 1.2324580312652738e-05, 'samples': 25948224, 'steps': 135146, 'loss/train': 1.3120161294937134} 08/31/2021 13:49:48 - INFO - __main__ - Step 135148: {'lr': 1.2322934707915983e-05, 'samples': 25948416, 'steps': 135147, 'loss/train': 0.03559241443872452} 08/31/2021 13:49:48 - INFO - __main__ - Step 135149: {'lr': 1.2321289210272868e-05, 'samples': 25948608, 'steps': 135148, 'loss/train': 1.1234523057937622} 08/31/2021 13:49:50 - INFO - __main__ - Step 135150: {'lr': 1.2319643819724113e-05, 'samples': 25948800, 'steps': 135149, 'loss/train': 0.8895851969718933} 08/31/2021 13:49:50 - INFO - __main__ - Step 135151: {'lr': 1.2317998536270441e-05, 'samples': 25948992, 'steps': 135150, 'loss/train': 0.3027028441429138} 08/31/2021 13:49:51 - INFO - __main__ - Step 135152: {'lr': 1.2316353359912657e-05, 'samples': 25949184, 'steps': 135151, 'loss/train': 0.9967992901802063} 08/31/2021 13:49:51 - INFO - __main__ - Step 135153: {'lr': 1.2314708290651427e-05, 'samples': 25949376, 'steps': 135152, 'loss/train': 0.7995474934577942} 08/31/2021 13:49:51 - INFO - __main__ - Step 135154: {'lr': 1.2313063328487501e-05, 'samples': 25949568, 'steps': 135153, 'loss/train': 1.1142281293869019} 08/31/2021 13:49:53 - INFO - __main__ - Step 135155: {'lr': 1.2311418473421654e-05, 'samples': 25949760, 'steps': 135154, 'loss/train': 0.4142695963382721} 08/31/2021 13:49:53 - INFO - __main__ - Step 135156: {'lr': 1.230977372545461e-05, 'samples': 25949952, 'steps': 135155, 'loss/train': 0.9498004913330078} 08/31/2021 13:49:54 - INFO - __main__ - Step 135157: {'lr': 1.2308129084587144e-05, 'samples': 25950144, 'steps': 135156, 'loss/train': 0.4130115509033203} 08/31/2021 13:49:54 - INFO - __main__ - Step 135158: {'lr': 1.2306484550819924e-05, 'samples': 25950336, 'steps': 135157, 'loss/train': 1.0773324966430664} 08/31/2021 13:49:54 - INFO - __main__ - Step 135159: {'lr': 1.2304840124153755e-05, 'samples': 25950528, 'steps': 135158, 'loss/train': 1.2184414863586426} 08/31/2021 13:49:55 - INFO - __main__ - Step 135160: {'lr': 1.2303195804589357e-05, 'samples': 25950720, 'steps': 135159, 'loss/train': 1.143226981163025} 08/31/2021 13:49:56 - INFO - __main__ - Step 135161: {'lr': 1.230155159212748e-05, 'samples': 25950912, 'steps': 135160, 'loss/train': 0.7334540486335754} 08/31/2021 13:49:57 - INFO - __main__ - Step 135162: {'lr': 1.2299907486768847e-05, 'samples': 25951104, 'steps': 135161, 'loss/train': 1.1132172346115112} 08/31/2021 13:49:57 - INFO - __main__ - Step 135163: {'lr': 1.2298263488514205e-05, 'samples': 25951296, 'steps': 135162, 'loss/train': 1.2369848489761353} 08/31/2021 13:49:57 - INFO - __main__ - Step 135164: {'lr': 1.2296619597364278e-05, 'samples': 25951488, 'steps': 135163, 'loss/train': 0.3868286609649658} 08/31/2021 13:49:58 - INFO - __main__ - Step 135165: {'lr': 1.2294975813319898e-05, 'samples': 25951680, 'steps': 135164, 'loss/train': 0.2655794620513916} 08/31/2021 13:49:59 - INFO - __main__ - Step 135166: {'lr': 1.2293332136381675e-05, 'samples': 25951872, 'steps': 135165, 'loss/train': 0.6930956840515137} 08/31/2021 13:50:00 - INFO - __main__ - Step 135167: {'lr': 1.2291688566550413e-05, 'samples': 25952064, 'steps': 135166, 'loss/train': 0.185203418135643} 08/31/2021 13:50:00 - INFO - __main__ - Step 135168: {'lr': 1.2290045103826863e-05, 'samples': 25952256, 'steps': 135167, 'loss/train': 0.7779014706611633} 08/31/2021 13:50:00 - INFO - __main__ - Step 135169: {'lr': 1.228840174821172e-05, 'samples': 25952448, 'steps': 135168, 'loss/train': 0.8729860186576843} 08/31/2021 13:50:01 - INFO - __main__ - Step 135170: {'lr': 1.2286758499705785e-05, 'samples': 25952640, 'steps': 135169, 'loss/train': 1.2571845054626465} 08/31/2021 13:50:02 - INFO - __main__ - Step 135171: {'lr': 1.2285115358309756e-05, 'samples': 25952832, 'steps': 135170, 'loss/train': 0.861625075340271} 08/31/2021 13:50:03 - INFO - __main__ - Step 135172: {'lr': 1.228347232402438e-05, 'samples': 25953024, 'steps': 135171, 'loss/train': 1.4049310684204102} 08/31/2021 13:50:03 - INFO - __main__ - Step 135173: {'lr': 1.2281829396850409e-05, 'samples': 25953216, 'steps': 135172, 'loss/train': 1.2179782390594482} 08/31/2021 13:50:03 - INFO - __main__ - Step 135174: {'lr': 1.2280186576788588e-05, 'samples': 25953408, 'steps': 135173, 'loss/train': 0.9385330677032471} 08/31/2021 13:50:04 - INFO - __main__ - Step 135175: {'lr': 1.2278543863839642e-05, 'samples': 25953600, 'steps': 135174, 'loss/train': 1.2916452884674072} 08/31/2021 13:50:06 - INFO - __main__ - Step 135176: {'lr': 1.227690125800432e-05, 'samples': 25953792, 'steps': 135175, 'loss/train': 1.2642546892166138} 08/31/2021 13:50:06 - INFO - __main__ - Step 135177: {'lr': 1.2275258759283342e-05, 'samples': 25953984, 'steps': 135176, 'loss/train': 1.1323866844177246} 08/31/2021 13:50:07 - INFO - __main__ - Step 135178: {'lr': 1.2273616367677459e-05, 'samples': 25954176, 'steps': 135177, 'loss/train': 1.050181269645691} 08/31/2021 13:50:07 - INFO - __main__ - Step 135179: {'lr': 1.2271974083187476e-05, 'samples': 25954368, 'steps': 135178, 'loss/train': 1.1518354415893555} 08/31/2021 13:50:07 - INFO - __main__ - Step 135180: {'lr': 1.227033190581403e-05, 'samples': 25954560, 'steps': 135179, 'loss/train': 1.3626152276992798} 08/31/2021 13:50:08 - INFO - __main__ - Step 135181: {'lr': 1.22686898355579e-05, 'samples': 25954752, 'steps': 135180, 'loss/train': 1.078855037689209} 08/31/2021 13:50:09 - INFO - __main__ - Step 135182: {'lr': 1.2267047872419834e-05, 'samples': 25954944, 'steps': 135181, 'loss/train': 1.647154450416565} 08/31/2021 13:50:10 - INFO - __main__ - Step 135183: {'lr': 1.2265406016400554e-05, 'samples': 25955136, 'steps': 135182, 'loss/train': 0.03980905935168266} 08/31/2021 13:50:10 - INFO - __main__ - Step 135184: {'lr': 1.226376426750081e-05, 'samples': 25955328, 'steps': 135183, 'loss/train': 0.8089078068733215} 08/31/2021 13:50:11 - INFO - __main__ - Step 135185: {'lr': 1.2262122625721377e-05, 'samples': 25955520, 'steps': 135184, 'loss/train': 2.4551334381103516} 08/31/2021 13:50:11 - INFO - __main__ - Step 135186: {'lr': 1.2260481091062925e-05, 'samples': 25955712, 'steps': 135185, 'loss/train': 0.897700309753418} 08/31/2021 13:50:13 - INFO - __main__ - Step 135187: {'lr': 1.2258839663526256e-05, 'samples': 25955904, 'steps': 135186, 'loss/train': 1.232636570930481} 08/31/2021 13:50:13 - INFO - __main__ - Step 135188: {'lr': 1.2257198343112091e-05, 'samples': 25956096, 'steps': 135187, 'loss/train': 2.114802598953247} 08/31/2021 13:50:13 - INFO - __main__ - Step 135189: {'lr': 1.2255557129821154e-05, 'samples': 25956288, 'steps': 135188, 'loss/train': 1.2367507219314575} 08/31/2021 13:50:14 - INFO - __main__ - Step 135190: {'lr': 1.2253916023654193e-05, 'samples': 25956480, 'steps': 135189, 'loss/train': 0.8576448559761047} 08/31/2021 13:50:14 - INFO - __main__ - Step 135191: {'lr': 1.2252275024611958e-05, 'samples': 25956672, 'steps': 135190, 'loss/train': 1.5988577604293823} 08/31/2021 13:50:16 - INFO - __main__ - Step 135192: {'lr': 1.2250634132695198e-05, 'samples': 25956864, 'steps': 135191, 'loss/train': 0.5790119767189026} 08/31/2021 13:50:16 - INFO - __main__ - Step 135193: {'lr': 1.2248993347904607e-05, 'samples': 25957056, 'steps': 135192, 'loss/train': 1.1838741302490234} 08/31/2021 13:50:17 - INFO - __main__ - Step 135194: {'lr': 1.2247352670240936e-05, 'samples': 25957248, 'steps': 135193, 'loss/train': 1.6013941764831543} 08/31/2021 13:50:17 - INFO - __main__ - Step 135195: {'lr': 1.2245712099704958e-05, 'samples': 25957440, 'steps': 135194, 'loss/train': 1.0882177352905273} 08/31/2021 13:50:17 - INFO - __main__ - Step 135196: {'lr': 1.2244071636297399e-05, 'samples': 25957632, 'steps': 135195, 'loss/train': 1.2207039594650269} 08/31/2021 13:50:18 - INFO - __main__ - Step 135197: {'lr': 1.2242431280018978e-05, 'samples': 25957824, 'steps': 135196, 'loss/train': 1.6615660190582275} 08/31/2021 13:50:19 - INFO - __main__ - Step 135198: {'lr': 1.2240791030870446e-05, 'samples': 25958016, 'steps': 135197, 'loss/train': 1.188749074935913} 08/31/2021 13:50:20 - INFO - __main__ - Step 135199: {'lr': 1.223915088885255e-05, 'samples': 25958208, 'steps': 135198, 'loss/train': 0.6514670848846436} 08/31/2021 13:50:20 - INFO - __main__ - Step 135200: {'lr': 1.2237510853966044e-05, 'samples': 25958400, 'steps': 135199, 'loss/train': 0.8518381714820862} 08/31/2021 13:50:20 - INFO - __main__ - Step 135201: {'lr': 1.2235870926211617e-05, 'samples': 25958592, 'steps': 135200, 'loss/train': 1.1854814291000366} 08/31/2021 13:50:21 - INFO - __main__ - Step 135202: {'lr': 1.2234231105590048e-05, 'samples': 25958784, 'steps': 135201, 'loss/train': 1.4947155714035034} 08/31/2021 13:50:22 - INFO - __main__ - Step 135203: {'lr': 1.223259139210206e-05, 'samples': 25958976, 'steps': 135202, 'loss/train': 1.0930116176605225} 08/31/2021 13:50:23 - INFO - __main__ - Step 135204: {'lr': 1.22309517857484e-05, 'samples': 25959168, 'steps': 135203, 'loss/train': 1.340291976928711} 08/31/2021 13:50:23 - INFO - __main__ - Step 135205: {'lr': 1.222931228652982e-05, 'samples': 25959360, 'steps': 135204, 'loss/train': 0.8456391096115112} 08/31/2021 13:50:23 - INFO - __main__ - Step 135206: {'lr': 1.2227672894447067e-05, 'samples': 25959552, 'steps': 135205, 'loss/train': 1.3996912240982056} 08/31/2021 13:50:24 - INFO - __main__ - Step 135207: {'lr': 1.2226033609500809e-05, 'samples': 25959744, 'steps': 135206, 'loss/train': 0.45606955885887146} 08/31/2021 13:50:25 - INFO - __main__ - Step 135208: {'lr': 1.2224394431691849e-05, 'samples': 25959936, 'steps': 135207, 'loss/train': 0.8882371187210083} 08/31/2021 13:50:26 - INFO - __main__ - Step 135209: {'lr': 1.222275536102091e-05, 'samples': 25960128, 'steps': 135208, 'loss/train': 0.9221521019935608} 08/31/2021 13:50:26 - INFO - __main__ - Step 135210: {'lr': 1.2221116397488712e-05, 'samples': 25960320, 'steps': 135209, 'loss/train': 1.294640064239502} 08/31/2021 13:50:27 - INFO - __main__ - Step 135211: {'lr': 1.2219477541096008e-05, 'samples': 25960512, 'steps': 135210, 'loss/train': 1.0174139738082886} 08/31/2021 13:50:27 - INFO - __main__ - Step 135212: {'lr': 1.2217838791843544e-05, 'samples': 25960704, 'steps': 135211, 'loss/train': 1.6296641826629639} 08/31/2021 13:50:28 - INFO - __main__ - Step 135213: {'lr': 1.221620014973207e-05, 'samples': 25960896, 'steps': 135212, 'loss/train': 1.1576857566833496} 08/31/2021 13:50:29 - INFO - __main__ - Step 135214: {'lr': 1.2214561614762281e-05, 'samples': 25961088, 'steps': 135213, 'loss/train': 0.8884902596473694} 08/31/2021 13:50:29 - INFO - __main__ - Step 135215: {'lr': 1.2212923186934955e-05, 'samples': 25961280, 'steps': 135214, 'loss/train': 0.8976929783821106} 08/31/2021 13:50:30 - INFO - __main__ - Step 135216: {'lr': 1.2211284866250811e-05, 'samples': 25961472, 'steps': 135215, 'loss/train': 0.9872651696205139} 08/31/2021 13:50:30 - INFO - __main__ - Step 135217: {'lr': 1.2209646652710599e-05, 'samples': 25961664, 'steps': 135216, 'loss/train': 0.7335270643234253} 08/31/2021 13:50:31 - INFO - __main__ - Step 135218: {'lr': 1.2208008546315042e-05, 'samples': 25961856, 'steps': 135217, 'loss/train': 1.3432867527008057} 08/31/2021 13:50:32 - INFO - __main__ - Step 135219: {'lr': 1.2206370547064916e-05, 'samples': 25962048, 'steps': 135218, 'loss/train': 0.3869296908378601} 08/31/2021 13:50:32 - INFO - __main__ - Step 135220: {'lr': 1.2204732654960914e-05, 'samples': 25962240, 'steps': 135219, 'loss/train': 0.24645739793777466} 08/31/2021 13:50:32 - INFO - __main__ - Step 135221: {'lr': 1.220309487000379e-05, 'samples': 25962432, 'steps': 135220, 'loss/train': 1.145858645439148} 08/31/2021 13:50:33 - INFO - __main__ - Step 135222: {'lr': 1.220145719219426e-05, 'samples': 25962624, 'steps': 135221, 'loss/train': 0.8632984161376953} 08/31/2021 13:50:34 - INFO - __main__ - Step 135223: {'lr': 1.2199819621533103e-05, 'samples': 25962816, 'steps': 135222, 'loss/train': 0.7886062264442444} 08/31/2021 13:50:35 - INFO - __main__ - Step 135224: {'lr': 1.2198182158021042e-05, 'samples': 25963008, 'steps': 135223, 'loss/train': 0.8695926070213318} 08/31/2021 13:50:35 - INFO - __main__ - Step 135225: {'lr': 1.21965448016588e-05, 'samples': 25963200, 'steps': 135224, 'loss/train': 0.9810973405838013} 08/31/2021 13:50:36 - INFO - __main__ - Step 135226: {'lr': 1.2194907552447121e-05, 'samples': 25963392, 'steps': 135225, 'loss/train': 1.16903555393219} 08/31/2021 13:50:36 - INFO - __main__ - Step 135227: {'lr': 1.2193270410386758e-05, 'samples': 25963584, 'steps': 135226, 'loss/train': 1.422183871269226} 08/31/2021 13:50:36 - INFO - __main__ - Step 135228: {'lr': 1.2191633375478434e-05, 'samples': 25963776, 'steps': 135227, 'loss/train': 1.2097529172897339} 08/31/2021 13:50:38 - INFO - __main__ - Step 135229: {'lr': 1.2189996447722896e-05, 'samples': 25963968, 'steps': 135228, 'loss/train': 0.6010813117027283} 08/31/2021 13:50:38 - INFO - __main__ - Step 135230: {'lr': 1.2188359627120866e-05, 'samples': 25964160, 'steps': 135229, 'loss/train': 0.3402290642261505} 08/31/2021 13:50:39 - INFO - __main__ - Step 135231: {'lr': 1.2186722913673093e-05, 'samples': 25964352, 'steps': 135230, 'loss/train': 2.3051464557647705} 08/31/2021 13:50:39 - INFO - __main__ - Step 135232: {'lr': 1.2185086307380355e-05, 'samples': 25964544, 'steps': 135231, 'loss/train': 0.5090730786323547} 08/31/2021 13:50:39 - INFO - __main__ - Step 135233: {'lr': 1.218344980824329e-05, 'samples': 25964736, 'steps': 135232, 'loss/train': 0.8256719708442688} 08/31/2021 13:50:41 - INFO - __main__ - Step 135234: {'lr': 1.2181813416262732e-05, 'samples': 25964928, 'steps': 135233, 'loss/train': 1.353358268737793} 08/31/2021 13:50:42 - INFO - __main__ - Step 135235: {'lr': 1.2180177131439347e-05, 'samples': 25965120, 'steps': 135234, 'loss/train': 0.6881215572357178} 08/31/2021 13:50:42 - INFO - __main__ - Step 135236: {'lr': 1.217854095377391e-05, 'samples': 25965312, 'steps': 135235, 'loss/train': 1.345011830329895} 08/31/2021 13:50:43 - INFO - __main__ - Step 135237: {'lr': 1.217690488326717e-05, 'samples': 25965504, 'steps': 135236, 'loss/train': 1.05215585231781} 08/31/2021 13:50:43 - INFO - __main__ - Step 135238: {'lr': 1.2175268919919823e-05, 'samples': 25965696, 'steps': 135237, 'loss/train': 0.03218398988246918} 08/31/2021 13:50:44 - INFO - __main__ - Step 135239: {'lr': 1.2173633063732648e-05, 'samples': 25965888, 'steps': 135238, 'loss/train': 1.67313814163208} 08/31/2021 13:50:45 - INFO - __main__ - Step 135240: {'lr': 1.2171997314706362e-05, 'samples': 25966080, 'steps': 135239, 'loss/train': 0.6874971985816956} 08/31/2021 13:50:45 - INFO - __main__ - Step 135241: {'lr': 1.217036167284169e-05, 'samples': 25966272, 'steps': 135240, 'loss/train': 0.9183773994445801} 08/31/2021 13:50:45 - INFO - __main__ - Step 135242: {'lr': 1.216872613813938e-05, 'samples': 25966464, 'steps': 135241, 'loss/train': 0.10538221150636673} 08/31/2021 13:50:46 - INFO - __main__ - Step 135243: {'lr': 1.2167090710600182e-05, 'samples': 25966656, 'steps': 135242, 'loss/train': 0.8372104167938232} 08/31/2021 13:50:47 - INFO - __main__ - Step 135244: {'lr': 1.2165455390224844e-05, 'samples': 25966848, 'steps': 135243, 'loss/train': 0.8334383368492126} 08/31/2021 13:50:48 - INFO - __main__ - Step 135245: {'lr': 1.2163820177014062e-05, 'samples': 25967040, 'steps': 135244, 'loss/train': 0.6432454586029053} 08/31/2021 13:50:48 - INFO - __main__ - Step 135246: {'lr': 1.2162185070968612e-05, 'samples': 25967232, 'steps': 135245, 'loss/train': 1.3460206985473633} 08/31/2021 13:50:49 - INFO - __main__ - Step 135247: {'lr': 1.2160550072089216e-05, 'samples': 25967424, 'steps': 135246, 'loss/train': 0.06586403399705887} 08/31/2021 13:50:49 - INFO - __main__ - Step 135248: {'lr': 1.2158915180376568e-05, 'samples': 25967616, 'steps': 135247, 'loss/train': 0.9783697128295898} 08/31/2021 13:50:51 - INFO - __main__ - Step 135249: {'lr': 1.2157280395831471e-05, 'samples': 25967808, 'steps': 135248, 'loss/train': 0.9183861017227173} 08/31/2021 13:50:51 - INFO - __main__ - Step 135250: {'lr': 1.2155645718454622e-05, 'samples': 25968000, 'steps': 135249, 'loss/train': 1.2433491945266724} 08/31/2021 13:50:51 - INFO - __main__ - Step 135251: {'lr': 1.215401114824674e-05, 'samples': 25968192, 'steps': 135250, 'loss/train': 0.7603632807731628} 08/31/2021 13:50:52 - INFO - __main__ - Step 135252: {'lr': 1.2152376685208633e-05, 'samples': 25968384, 'steps': 135251, 'loss/train': 0.8820310831069946} 08/31/2021 13:50:52 - INFO - __main__ - Step 135253: {'lr': 1.2150742329340964e-05, 'samples': 25968576, 'steps': 135252, 'loss/train': 1.2928459644317627} 08/31/2021 13:50:54 - INFO - __main__ - Step 135254: {'lr': 1.2149108080644539e-05, 'samples': 25968768, 'steps': 135253, 'loss/train': 1.408215880393982} 08/31/2021 13:50:54 - INFO - __main__ - Step 135255: {'lr': 1.2147473939120024e-05, 'samples': 25968960, 'steps': 135254, 'loss/train': 1.7055983543395996} 08/31/2021 13:50:55 - INFO - __main__ - Step 135256: {'lr': 1.2145839904768197e-05, 'samples': 25969152, 'steps': 135255, 'loss/train': 0.7801231145858765} 08/31/2021 13:50:55 - INFO - __main__ - Step 135257: {'lr': 1.2144205977589778e-05, 'samples': 25969344, 'steps': 135256, 'loss/train': 0.3386366367340088} 08/31/2021 13:50:55 - INFO - __main__ - Step 135258: {'lr': 1.214257215758552e-05, 'samples': 25969536, 'steps': 135257, 'loss/train': 1.2511820793151855} 08/31/2021 13:50:56 - INFO - __main__ - Step 135259: {'lr': 1.2140938444756167e-05, 'samples': 25969728, 'steps': 135258, 'loss/train': 0.5424294471740723} 08/31/2021 13:50:57 - INFO - __main__ - Step 135260: {'lr': 1.2139304839102417e-05, 'samples': 25969920, 'steps': 135259, 'loss/train': 1.3849934339523315} 08/31/2021 13:50:58 - INFO - __main__ - Step 135261: {'lr': 1.2137671340625018e-05, 'samples': 25970112, 'steps': 135260, 'loss/train': 0.958315908908844} 08/31/2021 13:50:58 - INFO - __main__ - Step 135262: {'lr': 1.2136037949324718e-05, 'samples': 25970304, 'steps': 135261, 'loss/train': 1.3560997247695923} 08/31/2021 13:50:58 - INFO - __main__ - Step 135263: {'lr': 1.2134404665202242e-05, 'samples': 25970496, 'steps': 135262, 'loss/train': 0.7954093813896179} 08/31/2021 13:50:59 - INFO - __main__ - Step 135264: {'lr': 1.2132771488258337e-05, 'samples': 25970688, 'steps': 135263, 'loss/train': 1.501652717590332} 08/31/2021 13:51:00 - INFO - __main__ - Step 135265: {'lr': 1.2131138418493753e-05, 'samples': 25970880, 'steps': 135264, 'loss/train': 0.910464882850647} 08/31/2021 13:51:01 - INFO - __main__ - Step 135266: {'lr': 1.2129505455909184e-05, 'samples': 25971072, 'steps': 135265, 'loss/train': 0.06375640630722046} 08/31/2021 13:51:01 - INFO - __main__ - Step 135267: {'lr': 1.212787260050538e-05, 'samples': 25971264, 'steps': 135266, 'loss/train': 1.4110760688781738} 08/31/2021 13:51:01 - INFO - __main__ - Step 135268: {'lr': 1.2126239852283116e-05, 'samples': 25971456, 'steps': 135267, 'loss/train': 1.4932804107666016} 08/31/2021 13:51:02 - INFO - __main__ - Step 135269: {'lr': 1.2124607211243088e-05, 'samples': 25971648, 'steps': 135268, 'loss/train': 1.6122275590896606} 08/31/2021 13:51:03 - INFO - __main__ - Step 135270: {'lr': 1.2122974677386017e-05, 'samples': 25971840, 'steps': 135269, 'loss/train': 1.3611736297607422} 08/31/2021 13:51:04 - INFO - __main__ - Step 135271: {'lr': 1.2121342250712708e-05, 'samples': 25972032, 'steps': 135270, 'loss/train': 1.3618324995040894} 08/31/2021 13:51:04 - INFO - __main__ - Step 135272: {'lr': 1.2119709931223828e-05, 'samples': 25972224, 'steps': 135271, 'loss/train': 0.9819878339767456} 08/31/2021 13:51:04 - INFO - __main__ - Step 135273: {'lr': 1.2118077718920151e-05, 'samples': 25972416, 'steps': 135272, 'loss/train': 0.4769948124885559} 08/31/2021 13:51:05 - INFO - __main__ - Step 135274: {'lr': 1.2116445613802374e-05, 'samples': 25972608, 'steps': 135273, 'loss/train': 1.0648865699768066} 08/31/2021 13:51:06 - INFO - __main__ - Step 135275: {'lr': 1.2114813615871273e-05, 'samples': 25972800, 'steps': 135274, 'loss/train': 0.15385757386684418} 08/31/2021 13:51:07 - INFO - __main__ - Step 135276: {'lr': 1.211318172512757e-05, 'samples': 25972992, 'steps': 135275, 'loss/train': 0.865536093711853} 08/31/2021 13:51:07 - INFO - __main__ - Step 135277: {'lr': 1.2111549941571958e-05, 'samples': 25973184, 'steps': 135276, 'loss/train': 0.3808380961418152} 08/31/2021 13:51:07 - INFO - __main__ - Step 135278: {'lr': 1.2109918265205245e-05, 'samples': 25973376, 'steps': 135277, 'loss/train': 0.6086004376411438} 08/31/2021 13:51:08 - INFO - __main__ - Step 135279: {'lr': 1.210828669602812e-05, 'samples': 25973568, 'steps': 135278, 'loss/train': 0.8719783425331116} 08/31/2021 13:51:08 - INFO - __main__ - Step 135280: {'lr': 1.2106655234041337e-05, 'samples': 25973760, 'steps': 135279, 'loss/train': 0.8611515760421753} 08/31/2021 13:51:10 - INFO - __main__ - Step 135281: {'lr': 1.2105023879245613e-05, 'samples': 25973952, 'steps': 135280, 'loss/train': 1.0178543329238892} 08/31/2021 13:51:10 - INFO - __main__ - Step 135282: {'lr': 1.2103392631641701e-05, 'samples': 25974144, 'steps': 135281, 'loss/train': 0.3133571445941925} 08/31/2021 13:51:11 - INFO - __main__ - Step 135283: {'lr': 1.2101761491230324e-05, 'samples': 25974336, 'steps': 135282, 'loss/train': 0.841295599937439} 08/31/2021 13:51:11 - INFO - __main__ - Step 135284: {'lr': 1.2100130458012226e-05, 'samples': 25974528, 'steps': 135283, 'loss/train': 0.8057140707969666} 08/31/2021 13:51:12 - INFO - __main__ - Step 135285: {'lr': 1.209849953198816e-05, 'samples': 25974720, 'steps': 135284, 'loss/train': 0.01543563511222601} 08/31/2021 13:51:12 - INFO - __main__ - Step 135286: {'lr': 1.2096868713158848e-05, 'samples': 25974912, 'steps': 135285, 'loss/train': 0.9831545948982239} 08/31/2021 13:51:14 - INFO - __main__ - Step 135287: {'lr': 1.2095238001524982e-05, 'samples': 25975104, 'steps': 135286, 'loss/train': 0.9865095615386963} 08/31/2021 13:51:14 - INFO - __main__ - Step 135288: {'lr': 1.2093607397087341e-05, 'samples': 25975296, 'steps': 135287, 'loss/train': 0.9056826233863831} 08/31/2021 13:51:15 - INFO - __main__ - Step 135289: {'lr': 1.2091976899846646e-05, 'samples': 25975488, 'steps': 135288, 'loss/train': 1.0195527076721191} 08/31/2021 13:51:15 - INFO - __main__ - Step 135290: {'lr': 1.2090346509803618e-05, 'samples': 25975680, 'steps': 135289, 'loss/train': 0.9014675617218018} 08/31/2021 13:51:15 - INFO - __main__ - Step 135291: {'lr': 1.2088716226959035e-05, 'samples': 25975872, 'steps': 135290, 'loss/train': 1.605044960975647} 08/31/2021 13:51:17 - INFO - __main__ - Step 135292: {'lr': 1.208708605131359e-05, 'samples': 25976064, 'steps': 135291, 'loss/train': 1.052655577659607} 08/31/2021 13:51:17 - INFO - __main__ - Step 135293: {'lr': 1.2085455982868033e-05, 'samples': 25976256, 'steps': 135292, 'loss/train': 1.6200830936431885} 08/31/2021 13:51:18 - INFO - __main__ - Step 135294: {'lr': 1.2083826021623112e-05, 'samples': 25976448, 'steps': 135293, 'loss/train': 0.8136848211288452} 08/31/2021 13:51:18 - INFO - __main__ - Step 135295: {'lr': 1.2082196167579524e-05, 'samples': 25976640, 'steps': 135294, 'loss/train': 1.3371738195419312} 08/31/2021 13:51:18 - INFO - __main__ - Step 135296: {'lr': 1.2080566420738042e-05, 'samples': 25976832, 'steps': 135295, 'loss/train': 1.1116037368774414} 08/31/2021 13:51:20 - INFO - __main__ - Step 135297: {'lr': 1.2078936781099392e-05, 'samples': 25977024, 'steps': 135296, 'loss/train': 1.4539421796798706} 08/31/2021 13:51:20 - INFO - __main__ - Step 135298: {'lr': 1.2077307248664294e-05, 'samples': 25977216, 'steps': 135297, 'loss/train': 1.1846081018447876} 08/31/2021 13:51:21 - INFO - __main__ - Step 135299: {'lr': 1.2075677823433495e-05, 'samples': 25977408, 'steps': 135298, 'loss/train': 1.1211909055709839} 08/31/2021 13:51:21 - INFO - __main__ - Step 135300: {'lr': 1.2074048505407747e-05, 'samples': 25977600, 'steps': 135299, 'loss/train': 1.211804747581482} 08/31/2021 13:51:21 - INFO - __main__ - Step 135301: {'lr': 1.2072419294587717e-05, 'samples': 25977792, 'steps': 135300, 'loss/train': 1.3994780778884888} 08/31/2021 13:51:23 - INFO - __main__ - Step 135302: {'lr': 1.2070790190974207e-05, 'samples': 25977984, 'steps': 135301, 'loss/train': 0.6817181706428528} 08/31/2021 13:51:23 - INFO - __main__ - Step 135303: {'lr': 1.2069161194567913e-05, 'samples': 25978176, 'steps': 135302, 'loss/train': 0.6908401846885681} 08/31/2021 13:51:24 - INFO - __main__ - Step 135304: {'lr': 1.2067532305369611e-05, 'samples': 25978368, 'steps': 135303, 'loss/train': 1.1789066791534424} 08/31/2021 13:51:24 - INFO - __main__ - Step 135305: {'lr': 1.2065903523379968e-05, 'samples': 25978560, 'steps': 135304, 'loss/train': 1.2520020008087158} 08/31/2021 13:51:24 - INFO - __main__ - Step 135306: {'lr': 1.2064274848599788e-05, 'samples': 25978752, 'steps': 135305, 'loss/train': 1.1296567916870117} 08/31/2021 13:51:26 - INFO - __main__ - Step 135307: {'lr': 1.2062646281029765e-05, 'samples': 25978944, 'steps': 135306, 'loss/train': 1.222183346748352} 08/31/2021 13:51:26 - INFO - __main__ - Step 135308: {'lr': 1.2061017820670622e-05, 'samples': 25979136, 'steps': 135307, 'loss/train': 0.7917917370796204} 08/31/2021 13:51:27 - INFO - __main__ - Step 135309: {'lr': 1.2059389467523135e-05, 'samples': 25979328, 'steps': 135308, 'loss/train': 1.1727606058120728} 08/31/2021 13:51:27 - INFO - __main__ - Step 135310: {'lr': 1.2057761221588025e-05, 'samples': 25979520, 'steps': 135309, 'loss/train': 0.2780689597129822} 08/31/2021 13:51:27 - INFO - __main__ - Step 135311: {'lr': 1.2056133082865989e-05, 'samples': 25979712, 'steps': 135310, 'loss/train': 0.8995164632797241} 08/31/2021 13:51:29 - INFO - __main__ - Step 135312: {'lr': 1.20545050513578e-05, 'samples': 25979904, 'steps': 135311, 'loss/train': 1.115626573562622} 08/31/2021 13:51:30 - INFO - __main__ - Step 135313: {'lr': 1.205287712706421e-05, 'samples': 25980096, 'steps': 135312, 'loss/train': 0.7814537882804871} 08/31/2021 13:51:30 - INFO - __main__ - Step 135314: {'lr': 1.2051249309985912e-05, 'samples': 25980288, 'steps': 135313, 'loss/train': 1.0369129180908203} 08/31/2021 13:51:30 - INFO - __main__ - Step 135315: {'lr': 1.2049621600123629e-05, 'samples': 25980480, 'steps': 135314, 'loss/train': 1.368950605392456} 08/31/2021 13:51:31 - INFO - __main__ - Step 135316: {'lr': 1.2047993997478108e-05, 'samples': 25980672, 'steps': 135315, 'loss/train': 0.679037868976593} 08/31/2021 13:51:32 - INFO - __main__ - Step 135317: {'lr': 1.20463665020501e-05, 'samples': 25980864, 'steps': 135316, 'loss/train': 0.1012226790189743} 08/31/2021 13:51:33 - INFO - __main__ - Step 135318: {'lr': 1.2044739113840325e-05, 'samples': 25981056, 'steps': 135317, 'loss/train': 0.6072991490364075} 08/31/2021 13:51:33 - INFO - __main__ - Step 135319: {'lr': 1.2043111832849508e-05, 'samples': 25981248, 'steps': 135318, 'loss/train': 0.5934938788414001} 08/31/2021 13:51:33 - INFO - __main__ - Step 135320: {'lr': 1.2041484659078394e-05, 'samples': 25981440, 'steps': 135319, 'loss/train': 0.44539836049079895} 08/31/2021 13:51:34 - INFO - __main__ - Step 135321: {'lr': 1.2039857592527736e-05, 'samples': 25981632, 'steps': 135320, 'loss/train': 1.0777233839035034} 08/31/2021 13:51:34 - INFO - __main__ - Step 135322: {'lr': 1.2038230633198228e-05, 'samples': 25981824, 'steps': 135321, 'loss/train': 1.7089381217956543} 08/31/2021 13:51:36 - INFO - __main__ - Step 135323: {'lr': 1.2036603781090617e-05, 'samples': 25982016, 'steps': 135322, 'loss/train': 0.8378220796585083} 08/31/2021 13:51:36 - INFO - __main__ - Step 135324: {'lr': 1.2034977036205652e-05, 'samples': 25982208, 'steps': 135323, 'loss/train': 1.2047396898269653} 08/31/2021 13:51:36 - INFO - __main__ - Step 135325: {'lr': 1.2033350398544057e-05, 'samples': 25982400, 'steps': 135324, 'loss/train': 1.1075797080993652} 08/31/2021 13:51:37 - INFO - __main__ - Step 135326: {'lr': 1.2031723868106553e-05, 'samples': 25982592, 'steps': 135325, 'loss/train': 1.547101616859436} 08/31/2021 13:51:37 - INFO - __main__ - Step 135327: {'lr': 1.2030097444893917e-05, 'samples': 25982784, 'steps': 135326, 'loss/train': 1.1544299125671387} 08/31/2021 13:51:39 - INFO - __main__ - Step 135328: {'lr': 1.2028471128906814e-05, 'samples': 25982976, 'steps': 135327, 'loss/train': 1.0245444774627686} 08/31/2021 13:51:39 - INFO - __main__ - Step 135329: {'lr': 1.2026844920146024e-05, 'samples': 25983168, 'steps': 135328, 'loss/train': 1.2596732378005981} 08/31/2021 13:51:39 - INFO - __main__ - Step 135330: {'lr': 1.2025218818612238e-05, 'samples': 25983360, 'steps': 135329, 'loss/train': 1.1912055015563965} 08/31/2021 13:51:40 - INFO - __main__ - Step 135331: {'lr': 1.2023592824306234e-05, 'samples': 25983552, 'steps': 135330, 'loss/train': 1.0282995700836182} 08/31/2021 13:51:40 - INFO - __main__ - Step 135332: {'lr': 1.2021966937228734e-05, 'samples': 25983744, 'steps': 135331, 'loss/train': 0.9262438416481018} 08/31/2021 13:51:42 - INFO - __main__ - Step 135333: {'lr': 1.202034115738046e-05, 'samples': 25983936, 'steps': 135332, 'loss/train': 0.7954532504081726} 08/31/2021 13:51:42 - INFO - __main__ - Step 135334: {'lr': 1.2018715484762133e-05, 'samples': 25984128, 'steps': 135333, 'loss/train': 1.248502492904663} 08/31/2021 13:51:42 - INFO - __main__ - Step 135335: {'lr': 1.2017089919374501e-05, 'samples': 25984320, 'steps': 135334, 'loss/train': 1.3142528533935547} 08/31/2021 13:51:43 - INFO - __main__ - Step 135336: {'lr': 1.2015464461218317e-05, 'samples': 25984512, 'steps': 135335, 'loss/train': 1.0501773357391357} 08/31/2021 13:51:43 - INFO - __main__ - Step 135337: {'lr': 1.2013839110294273e-05, 'samples': 25984704, 'steps': 135336, 'loss/train': 1.1777276992797852} 08/31/2021 13:51:46 - INFO - __main__ - Step 135338: {'lr': 1.2012213866603144e-05, 'samples': 25984896, 'steps': 135337, 'loss/train': 0.8620834350585938} 08/31/2021 13:51:47 - INFO - __main__ - Step 135339: {'lr': 1.20105887301456e-05, 'samples': 25985088, 'steps': 135338, 'loss/train': 2.041901111602783} 08/31/2021 13:51:47 - INFO - __main__ - Step 135340: {'lr': 1.2008963700922471e-05, 'samples': 25985280, 'steps': 135339, 'loss/train': 0.1335698664188385} 08/31/2021 13:51:47 - INFO - __main__ - Step 135341: {'lr': 1.2007338778934395e-05, 'samples': 25985472, 'steps': 135340, 'loss/train': 1.3439264297485352} 08/31/2021 13:51:48 - INFO - __main__ - Step 135342: {'lr': 1.2005713964182152e-05, 'samples': 25985664, 'steps': 135341, 'loss/train': 1.213950753211975} 08/31/2021 13:51:48 - INFO - __main__ - Step 135343: {'lr': 1.2004089256666434e-05, 'samples': 25985856, 'steps': 135342, 'loss/train': 0.987919270992279} 08/31/2021 13:51:48 - INFO - __main__ - Step 135344: {'lr': 1.2002464656388019e-05, 'samples': 25986048, 'steps': 135343, 'loss/train': 1.7213250398635864} 08/31/2021 13:51:49 - INFO - __main__ - Step 135345: {'lr': 1.2000840163347625e-05, 'samples': 25986240, 'steps': 135344, 'loss/train': 1.705340027809143} 08/31/2021 13:51:50 - INFO - __main__ - Step 135346: {'lr': 1.1999215777545979e-05, 'samples': 25986432, 'steps': 135345, 'loss/train': 1.734053611755371} 08/31/2021 13:51:51 - INFO - __main__ - Step 135347: {'lr': 1.1997591498983801e-05, 'samples': 25986624, 'steps': 135346, 'loss/train': 1.2942407131195068} 08/31/2021 13:51:51 - INFO - __main__ - Step 135348: {'lr': 1.1995967327661839e-05, 'samples': 25986816, 'steps': 135347, 'loss/train': 0.6217086315155029} 08/31/2021 13:51:51 - INFO - __main__ - Step 135349: {'lr': 1.1994343263580843e-05, 'samples': 25987008, 'steps': 135348, 'loss/train': 1.2089475393295288} 08/31/2021 13:51:52 - INFO - __main__ - Step 135350: {'lr': 1.1992719306741506e-05, 'samples': 25987200, 'steps': 135349, 'loss/train': 1.450238585472107} 08/31/2021 13:51:54 - INFO - __main__ - Step 135351: {'lr': 1.1991095457144551e-05, 'samples': 25987392, 'steps': 135350, 'loss/train': 0.9087597131729126} 08/31/2021 13:51:55 - INFO - __main__ - Step 135352: {'lr': 1.1989471714790784e-05, 'samples': 25987584, 'steps': 135351, 'loss/train': 0.6026846170425415} 08/31/2021 13:51:55 - INFO - __main__ - Step 135353: {'lr': 1.1987848079680896e-05, 'samples': 25987776, 'steps': 135352, 'loss/train': 1.121694564819336} 08/31/2021 13:51:55 - INFO - __main__ - Step 135354: {'lr': 1.1986224551815583e-05, 'samples': 25987968, 'steps': 135353, 'loss/train': 1.536765456199646} 08/31/2021 13:51:56 - INFO - __main__ - Step 135355: {'lr': 1.1984601131195593e-05, 'samples': 25988160, 'steps': 135354, 'loss/train': 0.2460363358259201} 08/31/2021 13:51:56 - INFO - __main__ - Step 135356: {'lr': 1.1982977817821677e-05, 'samples': 25988352, 'steps': 135355, 'loss/train': 0.25305891036987305} 08/31/2021 13:51:56 - INFO - __main__ - Step 135357: {'lr': 1.1981354611694556e-05, 'samples': 25988544, 'steps': 135356, 'loss/train': 0.24126741290092468} 08/31/2021 13:51:58 - INFO - __main__ - Step 135358: {'lr': 1.197973151281498e-05, 'samples': 25988736, 'steps': 135357, 'loss/train': 0.2822088897228241} 08/31/2021 13:51:58 - INFO - __main__ - Step 135359: {'lr': 1.197810852118364e-05, 'samples': 25988928, 'steps': 135358, 'loss/train': 0.25511616468429565} 08/31/2021 13:51:59 - INFO - __main__ - Step 135360: {'lr': 1.1976485636801315e-05, 'samples': 25989120, 'steps': 135359, 'loss/train': 0.5817497968673706} 08/31/2021 13:51:59 - INFO - __main__ - Step 135361: {'lr': 1.19748628596687e-05, 'samples': 25989312, 'steps': 135360, 'loss/train': 1.0211386680603027} 08/31/2021 13:51:59 - INFO - __main__ - Step 135362: {'lr': 1.1973240189786516e-05, 'samples': 25989504, 'steps': 135361, 'loss/train': 0.7044249176979065} 08/31/2021 13:52:01 - INFO - __main__ - Step 135363: {'lr': 1.197161762715554e-05, 'samples': 25989696, 'steps': 135362, 'loss/train': 1.1893327236175537} 08/31/2021 13:52:02 - INFO - __main__ - Step 135364: {'lr': 1.1969995171776493e-05, 'samples': 25989888, 'steps': 135363, 'loss/train': 0.7347602844238281} 08/31/2021 13:52:02 - INFO - __main__ - Step 135365: {'lr': 1.196837282365007e-05, 'samples': 25990080, 'steps': 135364, 'loss/train': 1.143248438835144} 08/31/2021 13:52:02 - INFO - __main__ - Step 135366: {'lr': 1.1966750582777076e-05, 'samples': 25990272, 'steps': 135365, 'loss/train': 0.9627304673194885} 08/31/2021 13:52:03 - INFO - __main__ - Step 135367: {'lr': 1.1965128449158146e-05, 'samples': 25990464, 'steps': 135366, 'loss/train': 0.9386674165725708} 08/31/2021 13:52:04 - INFO - __main__ - Step 135368: {'lr': 1.1963506422794063e-05, 'samples': 25990656, 'steps': 135367, 'loss/train': 1.1628038883209229} 08/31/2021 13:52:05 - INFO - __main__ - Step 135369: {'lr': 1.1961884503685544e-05, 'samples': 25990848, 'steps': 135368, 'loss/train': 0.8105248212814331} 08/31/2021 13:52:05 - INFO - __main__ - Step 135370: {'lr': 1.196026269183334e-05, 'samples': 25991040, 'steps': 135369, 'loss/train': 0.7575625777244568} 08/31/2021 13:52:05 - INFO - __main__ - Step 135371: {'lr': 1.1958640987238146e-05, 'samples': 25991232, 'steps': 135370, 'loss/train': 0.8058751821517944} 08/31/2021 13:52:06 - INFO - __main__ - Step 135372: {'lr': 1.1957019389900736e-05, 'samples': 25991424, 'steps': 135371, 'loss/train': 1.4368258714675903} 08/31/2021 13:52:07 - INFO - __main__ - Step 135373: {'lr': 1.1955397899821807e-05, 'samples': 25991616, 'steps': 135372, 'loss/train': 0.6112279891967773} 08/31/2021 13:52:07 - INFO - __main__ - Step 135374: {'lr': 1.1953776517002107e-05, 'samples': 25991808, 'steps': 135373, 'loss/train': 1.3743611574172974} 08/31/2021 13:52:08 - INFO - __main__ - Step 135375: {'lr': 1.1952155241442358e-05, 'samples': 25992000, 'steps': 135374, 'loss/train': 1.0179674625396729} 08/31/2021 13:52:08 - INFO - __main__ - Step 135376: {'lr': 1.1950534073143309e-05, 'samples': 25992192, 'steps': 135375, 'loss/train': 0.3368813395500183} 08/31/2021 13:52:09 - INFO - __main__ - Step 135377: {'lr': 1.194891301210571e-05, 'samples': 25992384, 'steps': 135376, 'loss/train': 0.611271858215332} 08/31/2021 13:52:10 - INFO - __main__ - Step 135378: {'lr': 1.19472920583302e-05, 'samples': 25992576, 'steps': 135377, 'loss/train': 1.4750791788101196} 08/31/2021 13:52:11 - INFO - __main__ - Step 135379: {'lr': 1.1945671211817582e-05, 'samples': 25992768, 'steps': 135378, 'loss/train': 0.6494746208190918} 08/31/2021 13:52:11 - INFO - __main__ - Step 135380: {'lr': 1.194405047256858e-05, 'samples': 25992960, 'steps': 135379, 'loss/train': 1.4337958097457886} 08/31/2021 13:52:11 - INFO - __main__ - Step 135381: {'lr': 1.1942429840583884e-05, 'samples': 25993152, 'steps': 135380, 'loss/train': 0.9182725548744202} 08/31/2021 13:52:12 - INFO - __main__ - Step 135382: {'lr': 1.1940809315864275e-05, 'samples': 25993344, 'steps': 135381, 'loss/train': 1.1706888675689697} 08/31/2021 13:52:13 - INFO - __main__ - Step 135383: {'lr': 1.1939188898410474e-05, 'samples': 25993536, 'steps': 135382, 'loss/train': 0.054677754640579224} 08/31/2021 13:52:14 - INFO - __main__ - Step 135384: {'lr': 1.1937568588223202e-05, 'samples': 25993728, 'steps': 135383, 'loss/train': 0.8151829242706299} 08/31/2021 13:52:14 - INFO - __main__ - Step 135385: {'lr': 1.193594838530318e-05, 'samples': 25993920, 'steps': 135384, 'loss/train': 0.9156138896942139} 08/31/2021 13:52:14 - INFO - __main__ - Step 135386: {'lr': 1.1934328289651131e-05, 'samples': 25994112, 'steps': 135385, 'loss/train': 1.2987697124481201} 08/31/2021 13:52:15 - INFO - __main__ - Step 135387: {'lr': 1.1932708301267858e-05, 'samples': 25994304, 'steps': 135386, 'loss/train': 0.7932918071746826} 08/31/2021 13:52:15 - INFO - __main__ - Step 135388: {'lr': 1.1931088420153974e-05, 'samples': 25994496, 'steps': 135387, 'loss/train': 1.3739945888519287} 08/31/2021 13:52:17 - INFO - __main__ - Step 135389: {'lr': 1.192946864631031e-05, 'samples': 25994688, 'steps': 135388, 'loss/train': 0.13975946605205536} 08/31/2021 13:52:17 - INFO - __main__ - Step 135390: {'lr': 1.1927848979737505e-05, 'samples': 25994880, 'steps': 135389, 'loss/train': 0.6885928511619568} 08/31/2021 13:52:17 - INFO - __main__ - Step 135391: {'lr': 1.1926229420436362e-05, 'samples': 25995072, 'steps': 135390, 'loss/train': 0.7253674268722534} 08/31/2021 13:52:18 - INFO - __main__ - Step 135392: {'lr': 1.1924609968407579e-05, 'samples': 25995264, 'steps': 135391, 'loss/train': 0.6955854296684265} 08/31/2021 13:52:18 - INFO - __main__ - Step 135393: {'lr': 1.1922990623651902e-05, 'samples': 25995456, 'steps': 135392, 'loss/train': 1.333552360534668} 08/31/2021 13:52:20 - INFO - __main__ - Step 135394: {'lr': 1.1921371386170054e-05, 'samples': 25995648, 'steps': 135393, 'loss/train': 1.0990331172943115} 08/31/2021 13:52:21 - INFO - __main__ - Step 135395: {'lr': 1.1919752255962756e-05, 'samples': 25995840, 'steps': 135394, 'loss/train': 0.02431901916861534} 08/31/2021 13:52:21 - INFO - __main__ - Step 135396: {'lr': 1.1918133233030731e-05, 'samples': 25996032, 'steps': 135395, 'loss/train': 0.14994870126247406} 08/31/2021 13:52:22 - INFO - __main__ - Step 135397: {'lr': 1.1916514317374755e-05, 'samples': 25996224, 'steps': 135396, 'loss/train': 1.5008786916732788} 08/31/2021 13:52:22 - INFO - __main__ - Step 135398: {'lr': 1.1914895508995521e-05, 'samples': 25996416, 'steps': 135397, 'loss/train': 1.1124699115753174} 08/31/2021 13:52:24 - INFO - __main__ - Step 135399: {'lr': 1.1913276807893753e-05, 'samples': 25996608, 'steps': 135398, 'loss/train': 1.1588373184204102} 08/31/2021 13:52:25 - INFO - __main__ - Step 135400: {'lr': 1.191165821407017e-05, 'samples': 25996800, 'steps': 135399, 'loss/train': 0.5562711358070374} 08/31/2021 13:52:25 - INFO - __main__ - Step 135401: {'lr': 1.1910039727525524e-05, 'samples': 25996992, 'steps': 135400, 'loss/train': 0.6385455131530762} 08/31/2021 13:52:25 - INFO - __main__ - Step 135402: {'lr': 1.1908421348260563e-05, 'samples': 25997184, 'steps': 135401, 'loss/train': 0.744884192943573} 08/31/2021 13:52:26 - INFO - __main__ - Step 135403: {'lr': 1.1906803076275951e-05, 'samples': 25997376, 'steps': 135402, 'loss/train': 0.6908078193664551} 08/31/2021 13:52:26 - INFO - __main__ - Step 135404: {'lr': 1.1905184911572498e-05, 'samples': 25997568, 'steps': 135403, 'loss/train': 0.36409565806388855} 08/31/2021 13:52:28 - INFO - __main__ - Step 135405: {'lr': 1.1903566854150866e-05, 'samples': 25997760, 'steps': 135404, 'loss/train': 0.4338217079639435} 08/31/2021 13:52:28 - INFO - __main__ - Step 135406: {'lr': 1.1901948904011834e-05, 'samples': 25997952, 'steps': 135405, 'loss/train': 0.10278147459030151} 08/31/2021 13:52:29 - INFO - __main__ - Step 135407: {'lr': 1.1900331061156094e-05, 'samples': 25998144, 'steps': 135406, 'loss/train': 1.2089622020721436} 08/31/2021 13:52:29 - INFO - __main__ - Step 135408: {'lr': 1.1898713325584399e-05, 'samples': 25998336, 'steps': 135407, 'loss/train': 0.028183748945593834} 08/31/2021 13:52:29 - INFO - __main__ - Step 135409: {'lr': 1.1897095697297522e-05, 'samples': 25998528, 'steps': 135408, 'loss/train': 1.4156417846679688} 08/31/2021 13:52:30 - INFO - __main__ - Step 135410: {'lr': 1.1895478176296076e-05, 'samples': 25998720, 'steps': 135409, 'loss/train': 0.9774297475814819} 08/31/2021 13:52:32 - INFO - __main__ - Step 135411: {'lr': 1.1893860762580866e-05, 'samples': 25998912, 'steps': 135410, 'loss/train': 0.016734689474105835} 08/31/2021 13:52:32 - INFO - __main__ - Step 135412: {'lr': 1.1892243456152613e-05, 'samples': 25999104, 'steps': 135411, 'loss/train': 1.7223577499389648} 08/31/2021 13:52:32 - INFO - __main__ - Step 135413: {'lr': 1.1890626257012038e-05, 'samples': 25999296, 'steps': 135412, 'loss/train': 1.3831521272659302} 08/31/2021 13:52:33 - INFO - __main__ - Step 135414: {'lr': 1.1889009165159865e-05, 'samples': 25999488, 'steps': 135413, 'loss/train': 1.2410578727722168} 08/31/2021 13:52:33 - INFO - __main__ - Step 135415: {'lr': 1.188739218059684e-05, 'samples': 25999680, 'steps': 135414, 'loss/train': 0.14750953018665314} 08/31/2021 13:52:34 - INFO - __main__ - Step 135416: {'lr': 1.188577530332366e-05, 'samples': 25999872, 'steps': 135415, 'loss/train': 1.5374103784561157} 08/31/2021 13:52:35 - INFO - __main__ - Step 135417: {'lr': 1.18841585333411e-05, 'samples': 26000064, 'steps': 135416, 'loss/train': 1.015044093132019} 08/31/2021 13:52:35 - INFO - __main__ - Step 135418: {'lr': 1.1882541870649854e-05, 'samples': 26000256, 'steps': 135417, 'loss/train': 0.7238296866416931} 08/31/2021 13:52:36 - INFO - __main__ - Step 135419: {'lr': 1.1880925315250645e-05, 'samples': 26000448, 'steps': 135418, 'loss/train': 1.0754591226577759} 08/31/2021 13:52:36 - INFO - __main__ - Step 135420: {'lr': 1.187930886714425e-05, 'samples': 26000640, 'steps': 135419, 'loss/train': 1.677863359451294} 08/31/2021 13:52:37 - INFO - __main__ - Step 135421: {'lr': 1.187769252633139e-05, 'samples': 26000832, 'steps': 135420, 'loss/train': 1.0365169048309326} 08/31/2021 13:52:38 - INFO - __main__ - Step 135422: {'lr': 1.1876076292812704e-05, 'samples': 26001024, 'steps': 135421, 'loss/train': 1.7270702123641968} 08/31/2021 13:52:38 - INFO - __main__ - Step 135423: {'lr': 1.1874460166589024e-05, 'samples': 26001216, 'steps': 135422, 'loss/train': 1.75205659866333} 08/31/2021 13:52:39 - INFO - __main__ - Step 135424: {'lr': 1.1872844147661015e-05, 'samples': 26001408, 'steps': 135423, 'loss/train': 1.3984736204147339} 08/31/2021 13:52:39 - INFO - __main__ - Step 135425: {'lr': 1.187122823602943e-05, 'samples': 26001600, 'steps': 135424, 'loss/train': 0.797023355960846} 08/31/2021 13:52:40 - INFO - __main__ - Step 135426: {'lr': 1.1869612431694987e-05, 'samples': 26001792, 'steps': 135425, 'loss/train': 0.916237473487854} 08/31/2021 13:52:41 - INFO - __main__ - Step 135427: {'lr': 1.1867996734658438e-05, 'samples': 26001984, 'steps': 135426, 'loss/train': 1.6123321056365967} 08/31/2021 13:52:41 - INFO - __main__ - Step 135428: {'lr': 1.1866381144920475e-05, 'samples': 26002176, 'steps': 135427, 'loss/train': 0.11090461909770966} 08/31/2021 13:52:42 - INFO - __main__ - Step 135429: {'lr': 1.1864765662481874e-05, 'samples': 26002368, 'steps': 135428, 'loss/train': 0.8732405304908752} 08/31/2021 13:52:42 - INFO - __main__ - Step 135430: {'lr': 1.1863150287343305e-05, 'samples': 26002560, 'steps': 135429, 'loss/train': 1.1438523530960083} 08/31/2021 13:52:43 - INFO - __main__ - Step 135431: {'lr': 1.1861535019505543e-05, 'samples': 26002752, 'steps': 135430, 'loss/train': 0.03990482538938522} 08/31/2021 13:52:44 - INFO - __main__ - Step 135432: {'lr': 1.1859919858969308e-05, 'samples': 26002944, 'steps': 135431, 'loss/train': 1.3212705850601196} 08/31/2021 13:52:44 - INFO - __main__ - Step 135433: {'lr': 1.1858304805735297e-05, 'samples': 26003136, 'steps': 135432, 'loss/train': 1.092806100845337} 08/31/2021 13:52:45 - INFO - __main__ - Step 135434: {'lr': 1.1856689859804315e-05, 'samples': 26003328, 'steps': 135433, 'loss/train': 1.1627041101455688} 08/31/2021 13:52:45 - INFO - __main__ - Step 135435: {'lr': 1.185507502117697e-05, 'samples': 26003520, 'steps': 135434, 'loss/train': 1.1722644567489624} 08/31/2021 13:52:46 - INFO - __main__ - Step 135436: {'lr': 1.1853460289854068e-05, 'samples': 26003712, 'steps': 135435, 'loss/train': 2.9593863487243652} 08/31/2021 13:52:47 - INFO - __main__ - Step 135437: {'lr': 1.185184566583633e-05, 'samples': 26003904, 'steps': 135436, 'loss/train': 1.0900691747665405} 08/31/2021 13:52:47 - INFO - __main__ - Step 135438: {'lr': 1.1850231149124479e-05, 'samples': 26004096, 'steps': 135437, 'loss/train': 1.4376220703125} 08/31/2021 13:52:48 - INFO - __main__ - Step 135439: {'lr': 1.1848616739719208e-05, 'samples': 26004288, 'steps': 135438, 'loss/train': 0.11021193116903305} 08/31/2021 13:52:48 - INFO - __main__ - Step 135440: {'lr': 1.1847002437621323e-05, 'samples': 26004480, 'steps': 135439, 'loss/train': 0.7997545003890991} 08/31/2021 13:52:49 - INFO - __main__ - Step 135441: {'lr': 1.1845388242831462e-05, 'samples': 26004672, 'steps': 135440, 'loss/train': 0.8545820116996765} 08/31/2021 13:52:50 - INFO - __main__ - Step 135442: {'lr': 1.1843774155350429e-05, 'samples': 26004864, 'steps': 135441, 'loss/train': 1.0244907140731812} 08/31/2021 13:52:50 - INFO - __main__ - Step 135443: {'lr': 1.1842160175178889e-05, 'samples': 26005056, 'steps': 135442, 'loss/train': 1.646393895149231} 08/31/2021 13:52:51 - INFO - __main__ - Step 135444: {'lr': 1.1840546302317596e-05, 'samples': 26005248, 'steps': 135443, 'loss/train': 1.5726298093795776} 08/31/2021 13:52:51 - INFO - __main__ - Step 135445: {'lr': 1.1838932536767295e-05, 'samples': 26005440, 'steps': 135444, 'loss/train': 1.7564034461975098} 08/31/2021 13:52:52 - INFO - __main__ - Step 135446: {'lr': 1.183731887852868e-05, 'samples': 26005632, 'steps': 135445, 'loss/train': 1.127305507659912} 08/31/2021 13:52:53 - INFO - __main__ - Step 135447: {'lr': 1.1835705327602503e-05, 'samples': 26005824, 'steps': 135446, 'loss/train': 1.0971430540084839} 08/31/2021 13:52:53 - INFO - __main__ - Step 135448: {'lr': 1.1834091883989513e-05, 'samples': 26006016, 'steps': 135447, 'loss/train': 1.5383777618408203} 08/31/2021 13:52:54 - INFO - __main__ - Step 135449: {'lr': 1.1832478547690373e-05, 'samples': 26006208, 'steps': 135448, 'loss/train': 0.5699350833892822} 08/31/2021 13:52:54 - INFO - __main__ - Step 135450: {'lr': 1.1830865318705863e-05, 'samples': 26006400, 'steps': 135449, 'loss/train': 0.1554413139820099} 08/31/2021 13:52:54 - INFO - __main__ - Step 135451: {'lr': 1.1829252197036649e-05, 'samples': 26006592, 'steps': 135450, 'loss/train': 1.0640208721160889} 08/31/2021 13:52:57 - INFO - __main__ - Step 135452: {'lr': 1.1827639182683536e-05, 'samples': 26006784, 'steps': 135451, 'loss/train': 0.920322835445404} 08/31/2021 13:52:57 - INFO - __main__ - Step 135453: {'lr': 1.1826026275647189e-05, 'samples': 26006976, 'steps': 135452, 'loss/train': 0.6215534806251526} 08/31/2021 13:52:58 - INFO - __main__ - Step 135454: {'lr': 1.1824413475928386e-05, 'samples': 26007168, 'steps': 135453, 'loss/train': 1.4959421157836914} 08/31/2021 13:52:58 - INFO - __main__ - Step 135455: {'lr': 1.1822800783527794e-05, 'samples': 26007360, 'steps': 135454, 'loss/train': 1.4500560760498047} 08/31/2021 13:52:58 - INFO - __main__ - Step 135456: {'lr': 1.1821188198446187e-05, 'samples': 26007552, 'steps': 135455, 'loss/train': 1.2807059288024902} 08/31/2021 13:52:59 - INFO - __main__ - Step 135457: {'lr': 1.181957572068429e-05, 'samples': 26007744, 'steps': 135456, 'loss/train': 0.5261930823326111} 08/31/2021 13:53:00 - INFO - __main__ - Step 135458: {'lr': 1.1817963350242794e-05, 'samples': 26007936, 'steps': 135457, 'loss/train': 1.308688759803772} 08/31/2021 13:53:01 - INFO - __main__ - Step 135459: {'lr': 1.1816351087122479e-05, 'samples': 26008128, 'steps': 135458, 'loss/train': 1.1393539905548096} 08/31/2021 13:53:01 - INFO - __main__ - Step 135460: {'lr': 1.181473893132401e-05, 'samples': 26008320, 'steps': 135459, 'loss/train': 0.8666750192642212} 08/31/2021 13:53:01 - INFO - __main__ - Step 135461: {'lr': 1.181312688284819e-05, 'samples': 26008512, 'steps': 135460, 'loss/train': 0.8582391738891602} 08/31/2021 13:53:02 - INFO - __main__ - Step 135462: {'lr': 1.181151494169566e-05, 'samples': 26008704, 'steps': 135461, 'loss/train': 0.8280017971992493} 08/31/2021 13:53:04 - INFO - __main__ - Step 135463: {'lr': 1.1809903107867198e-05, 'samples': 26008896, 'steps': 135462, 'loss/train': 0.7472933530807495} 08/31/2021 13:53:04 - INFO - __main__ - Step 135464: {'lr': 1.1808291381363522e-05, 'samples': 26009088, 'steps': 135463, 'loss/train': 1.2498418092727661} 08/31/2021 13:53:04 - INFO - __main__ - Step 135465: {'lr': 1.1806679762185329e-05, 'samples': 26009280, 'steps': 135464, 'loss/train': 1.4035779237747192} 08/31/2021 13:53:05 - INFO - __main__ - Step 135466: {'lr': 1.1805068250333395e-05, 'samples': 26009472, 'steps': 135465, 'loss/train': 1.2620737552642822} 08/31/2021 13:53:05 - INFO - __main__ - Step 135467: {'lr': 1.1803456845808413e-05, 'samples': 26009664, 'steps': 135466, 'loss/train': 0.9918597340583801} 08/31/2021 13:53:06 - INFO - __main__ - Step 135468: {'lr': 1.1801845548611106e-05, 'samples': 26009856, 'steps': 135467, 'loss/train': 0.3821341395378113} 08/31/2021 13:53:07 - INFO - __main__ - Step 135469: {'lr': 1.1800234358742223e-05, 'samples': 26010048, 'steps': 135468, 'loss/train': 0.7237244844436646} 08/31/2021 13:53:07 - INFO - __main__ - Step 135470: {'lr': 1.1798623276202486e-05, 'samples': 26010240, 'steps': 135469, 'loss/train': 0.7261438369750977} 08/31/2021 13:53:08 - INFO - __main__ - Step 135471: {'lr': 1.1797012300992616e-05, 'samples': 26010432, 'steps': 135470, 'loss/train': 0.8840712904930115} 08/31/2021 13:53:08 - INFO - __main__ - Step 135472: {'lr': 1.1795401433113306e-05, 'samples': 26010624, 'steps': 135471, 'loss/train': 1.1415796279907227} 08/31/2021 13:53:10 - INFO - __main__ - Step 135473: {'lr': 1.1793790672565336e-05, 'samples': 26010816, 'steps': 135472, 'loss/train': 0.28741925954818726} 08/31/2021 13:53:10 - INFO - __main__ - Step 135474: {'lr': 1.1792180019349452e-05, 'samples': 26011008, 'steps': 135473, 'loss/train': 0.4433160722255707} 08/31/2021 13:53:11 - INFO - __main__ - Step 135475: {'lr': 1.1790569473466295e-05, 'samples': 26011200, 'steps': 135474, 'loss/train': 1.322695016860962} 08/31/2021 13:53:11 - INFO - __main__ - Step 135476: {'lr': 1.1788959034916614e-05, 'samples': 26011392, 'steps': 135475, 'loss/train': 0.7640607953071594} 08/31/2021 13:53:11 - INFO - __main__ - Step 135477: {'lr': 1.1787348703701157e-05, 'samples': 26011584, 'steps': 135476, 'loss/train': 1.5461716651916504} 08/31/2021 13:53:13 - INFO - __main__ - Step 135478: {'lr': 1.1785738479820673e-05, 'samples': 26011776, 'steps': 135477, 'loss/train': 1.0947767496109009} 08/31/2021 13:53:13 - INFO - __main__ - Step 135479: {'lr': 1.178412836327583e-05, 'samples': 26011968, 'steps': 135478, 'loss/train': 0.6247669458389282} 08/31/2021 13:53:14 - INFO - __main__ - Step 135480: {'lr': 1.1782518354067379e-05, 'samples': 26012160, 'steps': 135479, 'loss/train': 1.0038038492202759} 08/31/2021 13:53:14 - INFO - __main__ - Step 135481: {'lr': 1.1780908452196065e-05, 'samples': 26012352, 'steps': 135480, 'loss/train': 2.923086166381836} 08/31/2021 13:53:15 - INFO - __main__ - Step 135482: {'lr': 1.1779298657662613e-05, 'samples': 26012544, 'steps': 135481, 'loss/train': 0.5322355031967163} 08/31/2021 13:53:15 - INFO - __main__ - Step 135483: {'lr': 1.1777688970467714e-05, 'samples': 26012736, 'steps': 135482, 'loss/train': 0.822715699672699} 08/31/2021 13:53:17 - INFO - __main__ - Step 135484: {'lr': 1.1776079390612093e-05, 'samples': 26012928, 'steps': 135483, 'loss/train': 1.4251656532287598} 08/31/2021 13:53:17 - INFO - __main__ - Step 135485: {'lr': 1.1774469918096525e-05, 'samples': 26013120, 'steps': 135484, 'loss/train': 1.1614363193511963} 08/31/2021 13:53:17 - INFO - __main__ - Step 135486: {'lr': 1.1772860552921677e-05, 'samples': 26013312, 'steps': 135485, 'loss/train': 1.0497878789901733} 08/31/2021 13:53:18 - INFO - __main__ - Step 135487: {'lr': 1.1771251295088325e-05, 'samples': 26013504, 'steps': 135486, 'loss/train': 1.4378329515457153} 08/31/2021 13:53:18 - INFO - __main__ - Step 135488: {'lr': 1.176964214459722e-05, 'samples': 26013696, 'steps': 135487, 'loss/train': 0.23093540966510773} 08/31/2021 13:53:20 - INFO - __main__ - Step 135489: {'lr': 1.1768033101448972e-05, 'samples': 26013888, 'steps': 135488, 'loss/train': 0.33071717619895935} 08/31/2021 13:53:20 - INFO - __main__ - Step 135490: {'lr': 1.1766424165644385e-05, 'samples': 26014080, 'steps': 135489, 'loss/train': 1.3958966732025146} 08/31/2021 13:53:20 - INFO - __main__ - Step 135491: {'lr': 1.1764815337184154e-05, 'samples': 26014272, 'steps': 135490, 'loss/train': 1.1536059379577637} 08/31/2021 13:53:21 - INFO - __main__ - Step 135492: {'lr': 1.1763206616069056e-05, 'samples': 26014464, 'steps': 135491, 'loss/train': 1.4021313190460205} 08/31/2021 13:53:21 - INFO - __main__ - Step 135493: {'lr': 1.1761598002299756e-05, 'samples': 26014656, 'steps': 135492, 'loss/train': 0.08826079219579697} 08/31/2021 13:53:23 - INFO - __main__ - Step 135494: {'lr': 1.1759989495877005e-05, 'samples': 26014848, 'steps': 135493, 'loss/train': 0.6966023445129395} 08/31/2021 13:53:23 - INFO - __main__ - Step 135495: {'lr': 1.1758381096801524e-05, 'samples': 26015040, 'steps': 135494, 'loss/train': 1.3661751747131348} 08/31/2021 13:53:24 - INFO - __main__ - Step 135496: {'lr': 1.1756772805074061e-05, 'samples': 26015232, 'steps': 135495, 'loss/train': 0.09316327422857285} 08/31/2021 13:53:24 - INFO - __main__ - Step 135497: {'lr': 1.1755164620695314e-05, 'samples': 26015424, 'steps': 135496, 'loss/train': 0.6174601912498474} 08/31/2021 13:53:24 - INFO - __main__ - Step 135498: {'lr': 1.1753556543666e-05, 'samples': 26015616, 'steps': 135497, 'loss/train': 0.33664470911026} 08/31/2021 13:53:25 - INFO - __main__ - Step 135499: {'lr': 1.1751948573986843e-05, 'samples': 26015808, 'steps': 135498, 'loss/train': 0.149013489484787} 08/31/2021 13:53:26 - INFO - __main__ - Step 135500: {'lr': 1.175034071165862e-05, 'samples': 26016000, 'steps': 135499, 'loss/train': 0.7130183577537537} 08/31/2021 13:53:27 - INFO - __main__ - Step 135501: {'lr': 1.1748732956682024e-05, 'samples': 26016192, 'steps': 135500, 'loss/train': 1.313595175743103} 08/31/2021 13:53:27 - INFO - __main__ - Step 135502: {'lr': 1.174712530905775e-05, 'samples': 26016384, 'steps': 135501, 'loss/train': 1.2069182395935059} 08/31/2021 13:53:27 - INFO - __main__ - Step 135503: {'lr': 1.1745517768786545e-05, 'samples': 26016576, 'steps': 135502, 'loss/train': 1.513695478439331} 08/31/2021 13:53:28 - INFO - __main__ - Step 135504: {'lr': 1.1743910335869135e-05, 'samples': 26016768, 'steps': 135503, 'loss/train': 0.9887766242027283} 08/31/2021 13:53:29 - INFO - __main__ - Step 135505: {'lr': 1.174230301030621e-05, 'samples': 26016960, 'steps': 135504, 'loss/train': 1.0419440269470215} 08/31/2021 13:53:30 - INFO - __main__ - Step 135506: {'lr': 1.1740695792098577e-05, 'samples': 26017152, 'steps': 135505, 'loss/train': 0.8645457029342651} 08/31/2021 13:53:30 - INFO - __main__ - Step 135507: {'lr': 1.1739088681246873e-05, 'samples': 26017344, 'steps': 135506, 'loss/train': 0.2757013440132141} 08/31/2021 13:53:30 - INFO - __main__ - Step 135508: {'lr': 1.1737481677751877e-05, 'samples': 26017536, 'steps': 135507, 'loss/train': 0.9694138765335083} 08/31/2021 13:53:31 - INFO - __main__ - Step 135509: {'lr': 1.1735874781614281e-05, 'samples': 26017728, 'steps': 135508, 'loss/train': 0.8316959738731384} 08/31/2021 13:53:33 - INFO - __main__ - Step 135510: {'lr': 1.1734267992834834e-05, 'samples': 26017920, 'steps': 135509, 'loss/train': 1.4689102172851562} 08/31/2021 13:53:33 - INFO - __main__ - Step 135511: {'lr': 1.173266131141426e-05, 'samples': 26018112, 'steps': 135510, 'loss/train': 1.2231361865997314} 08/31/2021 13:53:34 - INFO - __main__ - Step 135512: {'lr': 1.1731054737353252e-05, 'samples': 26018304, 'steps': 135511, 'loss/train': 1.626112937927246} 08/31/2021 13:53:34 - INFO - __main__ - Step 135513: {'lr': 1.1729448270652559e-05, 'samples': 26018496, 'steps': 135512, 'loss/train': 0.7272782921791077} 08/31/2021 13:53:34 - INFO - __main__ - Step 135514: {'lr': 1.1727841911312902e-05, 'samples': 26018688, 'steps': 135513, 'loss/train': 1.4493601322174072} 08/31/2021 13:53:36 - INFO - __main__ - Step 135515: {'lr': 1.1726235659335032e-05, 'samples': 26018880, 'steps': 135514, 'loss/train': 1.2946676015853882} 08/31/2021 13:53:36 - INFO - __main__ - Step 135516: {'lr': 1.1724629514719642e-05, 'samples': 26019072, 'steps': 135515, 'loss/train': 1.4449111223220825} 08/31/2021 13:53:37 - INFO - __main__ - Step 135517: {'lr': 1.1723023477467426e-05, 'samples': 26019264, 'steps': 135516, 'loss/train': 0.8137639164924622} 08/31/2021 13:53:37 - INFO - __main__ - Step 135518: {'lr': 1.1721417547579134e-05, 'samples': 26019456, 'steps': 135517, 'loss/train': 0.9757204055786133} 08/31/2021 13:53:37 - INFO - __main__ - Step 135519: {'lr': 1.1719811725055513e-05, 'samples': 26019648, 'steps': 135518, 'loss/train': 1.3968080282211304} 08/31/2021 13:53:38 - INFO - __main__ - Step 135520: {'lr': 1.1718206009897259e-05, 'samples': 26019840, 'steps': 135519, 'loss/train': 1.1704645156860352} 08/31/2021 13:53:39 - INFO - __main__ - Step 135521: {'lr': 1.1716600402105092e-05, 'samples': 26020032, 'steps': 135520, 'loss/train': 1.1644965410232544} 08/31/2021 13:53:40 - INFO - __main__ - Step 135522: {'lr': 1.1714994901679765e-05, 'samples': 26020224, 'steps': 135521, 'loss/train': 0.9943358302116394} 08/31/2021 13:53:40 - INFO - __main__ - Step 135523: {'lr': 1.1713389508621969e-05, 'samples': 26020416, 'steps': 135522, 'loss/train': 0.8903788924217224} 08/31/2021 13:53:41 - INFO - __main__ - Step 135524: {'lr': 1.1711784222932453e-05, 'samples': 26020608, 'steps': 135523, 'loss/train': 1.413872241973877} 08/31/2021 13:53:41 - INFO - __main__ - Step 135525: {'lr': 1.171017904461194e-05, 'samples': 26020800, 'steps': 135524, 'loss/train': 1.1813056468963623} 08/31/2021 13:53:42 - INFO - __main__ - Step 135526: {'lr': 1.1708573973661125e-05, 'samples': 26020992, 'steps': 135525, 'loss/train': 1.5030608177185059} 08/31/2021 13:53:43 - INFO - __main__ - Step 135527: {'lr': 1.1706969010080754e-05, 'samples': 26021184, 'steps': 135526, 'loss/train': 1.1182352304458618} 08/31/2021 13:53:43 - INFO - __main__ - Step 135528: {'lr': 1.1705364153871578e-05, 'samples': 26021376, 'steps': 135527, 'loss/train': 0.8989822864532471} 08/31/2021 13:53:44 - INFO - __main__ - Step 135529: {'lr': 1.1703759405034265e-05, 'samples': 26021568, 'steps': 135528, 'loss/train': 0.5756915807723999} 08/31/2021 13:53:44 - INFO - __main__ - Step 135530: {'lr': 1.1702154763569562e-05, 'samples': 26021760, 'steps': 135529, 'loss/train': 1.5238218307495117} 08/31/2021 13:53:46 - INFO - __main__ - Step 135531: {'lr': 1.170055022947819e-05, 'samples': 26021952, 'steps': 135530, 'loss/train': 1.0482536554336548} 08/31/2021 13:53:47 - INFO - __main__ - Step 135532: {'lr': 1.1698945802760873e-05, 'samples': 26022144, 'steps': 135531, 'loss/train': 1.3749929666519165} 08/31/2021 13:53:47 - INFO - __main__ - Step 135533: {'lr': 1.1697341483418306e-05, 'samples': 26022336, 'steps': 135532, 'loss/train': 0.016444116830825806} 08/31/2021 13:53:47 - INFO - __main__ - Step 135534: {'lr': 1.1695737271451263e-05, 'samples': 26022528, 'steps': 135533, 'loss/train': 0.014436089433729649} 08/31/2021 13:53:48 - INFO - __main__ - Step 135535: {'lr': 1.1694133166860438e-05, 'samples': 26022720, 'steps': 135534, 'loss/train': 0.4589233100414276} 08/31/2021 13:53:48 - INFO - __main__ - Step 135536: {'lr': 1.1692529169646582e-05, 'samples': 26022912, 'steps': 135535, 'loss/train': 1.244693636894226} 08/31/2021 13:53:48 - INFO - __main__ - Step 135537: {'lr': 1.169092527981036e-05, 'samples': 26023104, 'steps': 135536, 'loss/train': 1.0298221111297607} 08/31/2021 13:53:50 - INFO - __main__ - Step 135538: {'lr': 1.1689321497352552e-05, 'samples': 26023296, 'steps': 135537, 'loss/train': 0.86860591173172} 08/31/2021 13:53:50 - INFO - __main__ - Step 135539: {'lr': 1.1687717822273847e-05, 'samples': 26023488, 'steps': 135538, 'loss/train': 0.8837538957595825} 08/31/2021 13:53:51 - INFO - __main__ - Step 135540: {'lr': 1.1686114254574998e-05, 'samples': 26023680, 'steps': 135539, 'loss/train': 1.3986705541610718} 08/31/2021 13:53:51 - INFO - __main__ - Step 135541: {'lr': 1.1684510794256698e-05, 'samples': 26023872, 'steps': 135540, 'loss/train': 1.3284711837768555} 08/31/2021 13:53:51 - INFO - __main__ - Step 135542: {'lr': 1.1682907441319695e-05, 'samples': 26024064, 'steps': 135541, 'loss/train': 1.3031737804412842} 08/31/2021 13:53:53 - INFO - __main__ - Step 135543: {'lr': 1.1681304195764686e-05, 'samples': 26024256, 'steps': 135542, 'loss/train': 1.1479672193527222} 08/31/2021 13:53:53 - INFO - __main__ - Step 135544: {'lr': 1.167970105759239e-05, 'samples': 26024448, 'steps': 135543, 'loss/train': 1.309690237045288} 08/31/2021 13:53:54 - INFO - __main__ - Step 135545: {'lr': 1.1678098026803557e-05, 'samples': 26024640, 'steps': 135544, 'loss/train': 2.2014236450195312} 08/31/2021 13:53:54 - INFO - __main__ - Step 135546: {'lr': 1.1676495103398883e-05, 'samples': 26024832, 'steps': 135545, 'loss/train': 1.2559142112731934} 08/31/2021 13:53:54 - INFO - __main__ - Step 135547: {'lr': 1.1674892287379113e-05, 'samples': 26025024, 'steps': 135546, 'loss/train': 1.0487931966781616} 08/31/2021 13:53:56 - INFO - __main__ - Step 135548: {'lr': 1.1673289578744945e-05, 'samples': 26025216, 'steps': 135547, 'loss/train': 1.238650918006897} 08/31/2021 13:53:57 - INFO - __main__ - Step 135549: {'lr': 1.1671686977497126e-05, 'samples': 26025408, 'steps': 135548, 'loss/train': 0.9682182669639587} 08/31/2021 13:53:57 - INFO - __main__ - Step 135550: {'lr': 1.1670084483636378e-05, 'samples': 26025600, 'steps': 135549, 'loss/train': 0.3533182144165039} 08/31/2021 13:53:57 - INFO - __main__ - Step 135551: {'lr': 1.1668482097163396e-05, 'samples': 26025792, 'steps': 135550, 'loss/train': 1.28173828125} 08/31/2021 13:53:58 - INFO - __main__ - Step 135552: {'lr': 1.166687981807893e-05, 'samples': 26025984, 'steps': 135551, 'loss/train': 1.1891201734542847} 08/31/2021 13:53:58 - INFO - __main__ - Step 135553: {'lr': 1.1665277646383672e-05, 'samples': 26026176, 'steps': 135552, 'loss/train': 1.9385578632354736} 08/31/2021 13:54:00 - INFO - __main__ - Step 135554: {'lr': 1.166367558207837e-05, 'samples': 26026368, 'steps': 135553, 'loss/train': 0.3030216693878174} 08/31/2021 13:54:00 - INFO - __main__ - Step 135555: {'lr': 1.1662073625163777e-05, 'samples': 26026560, 'steps': 135554, 'loss/train': 0.3571227192878723} 08/31/2021 13:54:01 - INFO - __main__ - Step 135556: {'lr': 1.166047177564053e-05, 'samples': 26026752, 'steps': 135555, 'loss/train': 0.3276700973510742} 08/31/2021 13:54:01 - INFO - __main__ - Step 135557: {'lr': 1.1658870033509405e-05, 'samples': 26026944, 'steps': 135556, 'loss/train': 1.53760826587677} 08/31/2021 13:54:01 - INFO - __main__ - Step 135558: {'lr': 1.1657268398771126e-05, 'samples': 26027136, 'steps': 135557, 'loss/train': 0.4758938252925873} 08/31/2021 13:54:03 - INFO - __main__ - Step 135559: {'lr': 1.1655666871426384e-05, 'samples': 26027328, 'steps': 135558, 'loss/train': 1.479447364807129} 08/31/2021 13:54:03 - INFO - __main__ - Step 135560: {'lr': 1.1654065451475932e-05, 'samples': 26027520, 'steps': 135559, 'loss/train': 0.8717728853225708} 08/31/2021 13:54:04 - INFO - __main__ - Step 135561: {'lr': 1.1652464138920488e-05, 'samples': 26027712, 'steps': 135560, 'loss/train': 0.8230526447296143} 08/31/2021 13:54:04 - INFO - __main__ - Step 135562: {'lr': 1.1650862933760747e-05, 'samples': 26027904, 'steps': 135561, 'loss/train': 1.233272910118103} 08/31/2021 13:54:04 - INFO - __main__ - Step 135563: {'lr': 1.164926183599746e-05, 'samples': 26028096, 'steps': 135562, 'loss/train': 0.6374750733375549} 08/31/2021 13:54:06 - INFO - __main__ - Step 135564: {'lr': 1.1647660845631347e-05, 'samples': 26028288, 'steps': 135563, 'loss/train': 0.09652606397867203} 08/31/2021 13:54:07 - INFO - __main__ - Step 135565: {'lr': 1.1646059962663102e-05, 'samples': 26028480, 'steps': 135564, 'loss/train': 0.9490827918052673} 08/31/2021 13:54:07 - INFO - __main__ - Step 135566: {'lr': 1.1644459187093476e-05, 'samples': 26028672, 'steps': 135565, 'loss/train': 0.5950554013252258} 08/31/2021 13:54:07 - INFO - __main__ - Step 135567: {'lr': 1.1642858518923161e-05, 'samples': 26028864, 'steps': 135566, 'loss/train': 1.0307554006576538} 08/31/2021 13:54:08 - INFO - __main__ - Step 135568: {'lr': 1.1641257958152906e-05, 'samples': 26029056, 'steps': 135567, 'loss/train': 0.13843631744384766} 08/31/2021 13:54:09 - INFO - __main__ - Step 135569: {'lr': 1.1639657504783463e-05, 'samples': 26029248, 'steps': 135568, 'loss/train': 1.4100635051727295} 08/31/2021 13:54:10 - INFO - __main__ - Step 135570: {'lr': 1.1638057158815468e-05, 'samples': 26029440, 'steps': 135569, 'loss/train': 1.1797953844070435} 08/31/2021 13:54:10 - INFO - __main__ - Step 135571: {'lr': 1.16364569202497e-05, 'samples': 26029632, 'steps': 135570, 'loss/train': 1.2048184871673584} 08/31/2021 13:54:11 - INFO - __main__ - Step 135572: {'lr': 1.1634856789086851e-05, 'samples': 26029824, 'steps': 135571, 'loss/train': 1.33989417552948} 08/31/2021 13:54:11 - INFO - __main__ - Step 135573: {'lr': 1.163325676532767e-05, 'samples': 26030016, 'steps': 135572, 'loss/train': 1.3161542415618896} 08/31/2021 13:54:11 - INFO - __main__ - Step 135574: {'lr': 1.1631656848972855e-05, 'samples': 26030208, 'steps': 135573, 'loss/train': 1.1947941780090332} 08/31/2021 13:54:13 - INFO - __main__ - Step 135575: {'lr': 1.163005704002315e-05, 'samples': 26030400, 'steps': 135574, 'loss/train': 0.7364066243171692} 08/31/2021 13:54:14 - INFO - __main__ - Step 135576: {'lr': 1.1628457338479254e-05, 'samples': 26030592, 'steps': 135575, 'loss/train': 1.6090792417526245} 08/31/2021 13:54:14 - INFO - __main__ - Step 135577: {'lr': 1.1626857744341913e-05, 'samples': 26030784, 'steps': 135576, 'loss/train': 0.01708615943789482} 08/31/2021 13:54:15 - INFO - __main__ - Step 135578: {'lr': 1.162525825761182e-05, 'samples': 26030976, 'steps': 135577, 'loss/train': 0.4043368101119995} 08/31/2021 13:54:15 - INFO - __main__ - Step 135579: {'lr': 1.16236588782897e-05, 'samples': 26031168, 'steps': 135578, 'loss/train': 1.705482840538025} 08/31/2021 13:54:15 - INFO - __main__ - Step 135580: {'lr': 1.1622059606376274e-05, 'samples': 26031360, 'steps': 135579, 'loss/train': 1.1090043783187866} 08/31/2021 13:54:17 - INFO - __main__ - Step 135581: {'lr': 1.1620460441872288e-05, 'samples': 26031552, 'steps': 135580, 'loss/train': 0.524101734161377} 08/31/2021 13:54:17 - INFO - __main__ - Step 135582: {'lr': 1.1618861384778467e-05, 'samples': 26031744, 'steps': 135581, 'loss/train': 0.5043989419937134} 08/31/2021 13:54:18 - INFO - __main__ - Step 135583: {'lr': 1.1617262435095477e-05, 'samples': 26031936, 'steps': 135582, 'loss/train': 0.2991299331188202} 08/31/2021 13:54:18 - INFO - __main__ - Step 135584: {'lr': 1.1615663592824065e-05, 'samples': 26032128, 'steps': 135583, 'loss/train': 1.2552549839019775} 08/31/2021 13:54:18 - INFO - __main__ - Step 135585: {'lr': 1.1614064857964984e-05, 'samples': 26032320, 'steps': 135584, 'loss/train': 1.130449891090393} 08/31/2021 13:54:20 - INFO - __main__ - Step 135586: {'lr': 1.1612466230518898e-05, 'samples': 26032512, 'steps': 135585, 'loss/train': 1.6552515029907227} 08/31/2021 13:54:20 - INFO - __main__ - Step 135587: {'lr': 1.1610867710486556e-05, 'samples': 26032704, 'steps': 135586, 'loss/train': 1.031609296798706} 08/31/2021 13:54:21 - INFO - __main__ - Step 135588: {'lr': 1.160926929786868e-05, 'samples': 26032896, 'steps': 135587, 'loss/train': 1.465846061706543} 08/31/2021 13:54:21 - INFO - __main__ - Step 135589: {'lr': 1.1607670992665992e-05, 'samples': 26033088, 'steps': 135588, 'loss/train': 1.9139537811279297} 08/31/2021 13:54:21 - INFO - __main__ - Step 135590: {'lr': 1.1606072794879213e-05, 'samples': 26033280, 'steps': 135589, 'loss/train': 1.3712084293365479} 08/31/2021 13:54:23 - INFO - __main__ - Step 135591: {'lr': 1.1604474704509065e-05, 'samples': 26033472, 'steps': 135590, 'loss/train': 2.4883360862731934} 08/31/2021 13:54:23 - INFO - __main__ - Step 135592: {'lr': 1.1602876721556271e-05, 'samples': 26033664, 'steps': 135591, 'loss/train': 1.0782599449157715} 08/31/2021 13:54:24 - INFO - __main__ - Step 135593: {'lr': 1.1601278846021524e-05, 'samples': 26033856, 'steps': 135592, 'loss/train': 1.1999504566192627} 08/31/2021 13:54:24 - INFO - __main__ - Step 135594: {'lr': 1.1599681077905543e-05, 'samples': 26034048, 'steps': 135593, 'loss/train': 1.5818121433258057} 08/31/2021 13:54:24 - INFO - __main__ - Step 135595: {'lr': 1.1598083417209138e-05, 'samples': 26034240, 'steps': 135594, 'loss/train': 0.7189912796020508} 08/31/2021 13:54:26 - INFO - __main__ - Step 135596: {'lr': 1.1596485863932915e-05, 'samples': 26034432, 'steps': 135595, 'loss/train': 0.9567577838897705} 08/31/2021 13:54:26 - INFO - __main__ - Step 135597: {'lr': 1.1594888418077626e-05, 'samples': 26034624, 'steps': 135596, 'loss/train': 0.9857496619224548} 08/31/2021 13:54:27 - INFO - __main__ - Step 135598: {'lr': 1.1593291079643992e-05, 'samples': 26034816, 'steps': 135597, 'loss/train': 0.08635365217924118} 08/31/2021 13:54:27 - INFO - __main__ - Step 135599: {'lr': 1.1591693848632762e-05, 'samples': 26035008, 'steps': 135598, 'loss/train': 0.8115788698196411} 08/31/2021 13:54:27 - INFO - __main__ - Step 135600: {'lr': 1.159009672504463e-05, 'samples': 26035200, 'steps': 135599, 'loss/train': 1.351150393486023} 08/31/2021 13:54:28 - INFO - __main__ - Step 135601: {'lr': 1.1588499708880318e-05, 'samples': 26035392, 'steps': 135600, 'loss/train': 1.3694379329681396} 08/31/2021 13:54:29 - INFO - __main__ - Step 135602: {'lr': 1.1586902800140547e-05, 'samples': 26035584, 'steps': 135601, 'loss/train': 0.6049269437789917} 08/31/2021 13:54:30 - INFO - __main__ - Step 135603: {'lr': 1.158530599882604e-05, 'samples': 26035776, 'steps': 135602, 'loss/train': 1.246755838394165} 08/31/2021 13:54:30 - INFO - __main__ - Step 135604: {'lr': 1.1583709304937518e-05, 'samples': 26035968, 'steps': 135603, 'loss/train': 0.0900898426771164} 08/31/2021 13:54:30 - INFO - __main__ - Step 135605: {'lr': 1.15821127184757e-05, 'samples': 26036160, 'steps': 135604, 'loss/train': 1.2421624660491943} 08/31/2021 13:54:31 - INFO - __main__ - Step 135606: {'lr': 1.1580516239441314e-05, 'samples': 26036352, 'steps': 135605, 'loss/train': 0.7226760387420654} 08/31/2021 13:54:32 - INFO - __main__ - Step 135607: {'lr': 1.1578919867835047e-05, 'samples': 26036544, 'steps': 135606, 'loss/train': 1.333604097366333} 08/31/2021 13:54:33 - INFO - __main__ - Step 135608: {'lr': 1.1577323603657652e-05, 'samples': 26036736, 'steps': 135607, 'loss/train': 1.1433697938919067} 08/31/2021 13:54:33 - INFO - __main__ - Step 135609: {'lr': 1.1575727446909878e-05, 'samples': 26036928, 'steps': 135608, 'loss/train': 0.4965454041957855} 08/31/2021 13:54:33 - INFO - __main__ - Step 135610: {'lr': 1.1574131397592335e-05, 'samples': 26037120, 'steps': 135609, 'loss/train': 1.5166014432907104} 08/31/2021 13:54:34 - INFO - __main__ - Step 135611: {'lr': 1.157253545570583e-05, 'samples': 26037312, 'steps': 135610, 'loss/train': 1.0627000331878662} 08/31/2021 13:54:35 - INFO - __main__ - Step 135612: {'lr': 1.157093962125108e-05, 'samples': 26037504, 'steps': 135611, 'loss/train': 1.5856444835662842} 08/31/2021 13:54:36 - INFO - __main__ - Step 135613: {'lr': 1.1569343894228756e-05, 'samples': 26037696, 'steps': 135612, 'loss/train': 0.10501270741224289} 08/31/2021 13:54:36 - INFO - __main__ - Step 135614: {'lr': 1.1567748274639634e-05, 'samples': 26037888, 'steps': 135613, 'loss/train': 1.4711833000183105} 08/31/2021 13:54:37 - INFO - __main__ - Step 135615: {'lr': 1.1566152762484378e-05, 'samples': 26038080, 'steps': 135614, 'loss/train': 1.2256604433059692} 08/31/2021 13:54:37 - INFO - __main__ - Step 135616: {'lr': 1.1564557357763739e-05, 'samples': 26038272, 'steps': 135615, 'loss/train': 1.0138801336288452} 08/31/2021 13:54:39 - INFO - __main__ - Step 135617: {'lr': 1.1562962060478437e-05, 'samples': 26038464, 'steps': 135616, 'loss/train': 0.040493570268154144} 08/31/2021 13:54:40 - INFO - __main__ - Step 135618: {'lr': 1.1561366870629198e-05, 'samples': 26038656, 'steps': 135617, 'loss/train': 0.6296089887619019} 08/31/2021 13:54:40 - INFO - __main__ - Step 135619: {'lr': 1.155977178821671e-05, 'samples': 26038848, 'steps': 135618, 'loss/train': 0.1284020096063614} 08/31/2021 13:54:40 - INFO - __main__ - Step 135620: {'lr': 1.1558176813241728e-05, 'samples': 26039040, 'steps': 135619, 'loss/train': 0.922637403011322} 08/31/2021 13:54:41 - INFO - __main__ - Step 135621: {'lr': 1.1556581945704913e-05, 'samples': 26039232, 'steps': 135620, 'loss/train': 0.8508930802345276} 08/31/2021 13:54:42 - INFO - __main__ - Step 135622: {'lr': 1.1554987185607102e-05, 'samples': 26039424, 'steps': 135621, 'loss/train': 1.0023932456970215} 08/31/2021 13:54:43 - INFO - __main__ - Step 135623: {'lr': 1.1553392532948875e-05, 'samples': 26039616, 'steps': 135622, 'loss/train': 1.0385645627975464} 08/31/2021 13:54:43 - INFO - __main__ - Step 135624: {'lr': 1.155179798773101e-05, 'samples': 26039808, 'steps': 135623, 'loss/train': 0.9826934337615967} 08/31/2021 13:54:43 - INFO - __main__ - Step 135625: {'lr': 1.155020354995423e-05, 'samples': 26040000, 'steps': 135624, 'loss/train': 0.9246234893798828} 08/31/2021 13:54:44 - INFO - __main__ - Step 135626: {'lr': 1.1548609219619254e-05, 'samples': 26040192, 'steps': 135625, 'loss/train': 0.6075112819671631} 08/31/2021 13:54:44 - INFO - __main__ - Step 135627: {'lr': 1.1547014996726806e-05, 'samples': 26040384, 'steps': 135626, 'loss/train': 0.9419077634811401} 08/31/2021 13:54:46 - INFO - __main__ - Step 135628: {'lr': 1.1545420881277579e-05, 'samples': 26040576, 'steps': 135627, 'loss/train': 0.7173675894737244} 08/31/2021 13:54:46 - INFO - __main__ - Step 135629: {'lr': 1.1543826873272296e-05, 'samples': 26040768, 'steps': 135628, 'loss/train': 1.097432255744934} 08/31/2021 13:54:46 - INFO - __main__ - Step 135630: {'lr': 1.1542232972711703e-05, 'samples': 26040960, 'steps': 135629, 'loss/train': 1.4894766807556152} 08/31/2021 13:54:47 - INFO - __main__ - Step 135631: {'lr': 1.1540639179596468e-05, 'samples': 26041152, 'steps': 135630, 'loss/train': 0.6521502137184143} 08/31/2021 13:54:47 - INFO - __main__ - Step 135632: {'lr': 1.1539045493927369e-05, 'samples': 26041344, 'steps': 135631, 'loss/train': 1.0484851598739624} 08/31/2021 13:54:49 - INFO - __main__ - Step 135633: {'lr': 1.15374519157051e-05, 'samples': 26041536, 'steps': 135632, 'loss/train': 0.5527337789535522} 08/31/2021 13:54:49 - INFO - __main__ - Step 135634: {'lr': 1.1535858444930408e-05, 'samples': 26041728, 'steps': 135633, 'loss/train': 1.5396074056625366} 08/31/2021 13:54:50 - INFO - __main__ - Step 135635: {'lr': 1.1534265081603933e-05, 'samples': 26041920, 'steps': 135634, 'loss/train': 1.1116766929626465} 08/31/2021 13:54:50 - INFO - __main__ - Step 135636: {'lr': 1.1532671825726455e-05, 'samples': 26042112, 'steps': 135635, 'loss/train': 1.9446525573730469} 08/31/2021 13:54:50 - INFO - __main__ - Step 135637: {'lr': 1.1531078677298661e-05, 'samples': 26042304, 'steps': 135636, 'loss/train': 1.1679733991622925} 08/31/2021 13:54:52 - INFO - __main__ - Step 135638: {'lr': 1.152948563632128e-05, 'samples': 26042496, 'steps': 135637, 'loss/train': 1.060625672340393} 08/31/2021 13:54:52 - INFO - __main__ - Step 135639: {'lr': 1.1527892702795029e-05, 'samples': 26042688, 'steps': 135638, 'loss/train': 0.8999955058097839} 08/31/2021 13:54:53 - INFO - __main__ - Step 135640: {'lr': 1.1526299876720658e-05, 'samples': 26042880, 'steps': 135639, 'loss/train': 1.1765788793563843} 08/31/2021 13:54:53 - INFO - __main__ - Step 135641: {'lr': 1.1524707158098834e-05, 'samples': 26043072, 'steps': 135640, 'loss/train': 0.33143508434295654} 08/31/2021 13:54:53 - INFO - __main__ - Step 135642: {'lr': 1.1523114546930307e-05, 'samples': 26043264, 'steps': 135641, 'loss/train': 0.24475038051605225} 08/31/2021 13:54:55 - INFO - __main__ - Step 135643: {'lr': 1.1521522043215772e-05, 'samples': 26043456, 'steps': 135642, 'loss/train': 0.9881457686424255} 08/31/2021 13:54:55 - INFO - __main__ - Step 135644: {'lr': 1.1519929646955973e-05, 'samples': 26043648, 'steps': 135643, 'loss/train': 1.100174069404602} 08/31/2021 13:54:56 - INFO - __main__ - Step 135645: {'lr': 1.1518337358151636e-05, 'samples': 26043840, 'steps': 135644, 'loss/train': 1.081217885017395} 08/31/2021 13:54:56 - INFO - __main__ - Step 135646: {'lr': 1.1516745176803427e-05, 'samples': 26044032, 'steps': 135645, 'loss/train': 0.6882450580596924} 08/31/2021 13:54:56 - INFO - __main__ - Step 135647: {'lr': 1.1515153102912097e-05, 'samples': 26044224, 'steps': 135646, 'loss/train': 0.7818692326545715} 08/31/2021 13:54:58 - INFO - __main__ - Step 135648: {'lr': 1.1513561136478334e-05, 'samples': 26044416, 'steps': 135647, 'loss/train': 0.034507155418395996} 08/31/2021 13:54:58 - INFO - __main__ - Step 135649: {'lr': 1.1511969277502921e-05, 'samples': 26044608, 'steps': 135648, 'loss/train': 1.417065978050232} 08/31/2021 13:54:59 - INFO - __main__ - Step 135650: {'lr': 1.1510377525986492e-05, 'samples': 26044800, 'steps': 135649, 'loss/train': 0.9481050372123718} 08/31/2021 13:54:59 - INFO - __main__ - Step 135651: {'lr': 1.1508785881929856e-05, 'samples': 26044992, 'steps': 135650, 'loss/train': 1.1439781188964844} 08/31/2021 13:54:59 - INFO - __main__ - Step 135652: {'lr': 1.150719434533365e-05, 'samples': 26045184, 'steps': 135651, 'loss/train': 0.4642079472541809} 08/31/2021 13:55:01 - INFO - __main__ - Step 135653: {'lr': 1.1505602916198621e-05, 'samples': 26045376, 'steps': 135652, 'loss/train': 0.9520750045776367} 08/31/2021 13:55:01 - INFO - __main__ - Step 135654: {'lr': 1.1504011594525492e-05, 'samples': 26045568, 'steps': 135653, 'loss/train': 1.2590892314910889} 08/31/2021 13:55:02 - INFO - __main__ - Step 135655: {'lr': 1.1502420380314988e-05, 'samples': 26045760, 'steps': 135654, 'loss/train': 1.7777845859527588} 08/31/2021 13:55:02 - INFO - __main__ - Step 135656: {'lr': 1.1500829273567826e-05, 'samples': 26045952, 'steps': 135655, 'loss/train': 1.1162426471710205} 08/31/2021 13:55:02 - INFO - __main__ - Step 135657: {'lr': 1.1499238274284673e-05, 'samples': 26046144, 'steps': 135656, 'loss/train': 1.2143030166625977} 08/31/2021 13:55:05 - INFO - __main__ - Step 135658: {'lr': 1.149764738246631e-05, 'samples': 26046336, 'steps': 135657, 'loss/train': 0.8139393329620361} 08/31/2021 13:55:05 - INFO - __main__ - Step 135659: {'lr': 1.1496056598113398e-05, 'samples': 26046528, 'steps': 135658, 'loss/train': 1.2890796661376953} 08/31/2021 13:55:06 - INFO - __main__ - Step 135660: {'lr': 1.1494465921226688e-05, 'samples': 26046720, 'steps': 135659, 'loss/train': 1.107804775238037} 08/31/2021 13:55:06 - INFO - __main__ - Step 135661: {'lr': 1.1492875351806903e-05, 'samples': 26046912, 'steps': 135660, 'loss/train': 1.3168169260025024} 08/31/2021 13:55:06 - INFO - __main__ - Step 135662: {'lr': 1.1491284889854765e-05, 'samples': 26047104, 'steps': 135661, 'loss/train': 0.47864043712615967} 08/31/2021 13:55:07 - INFO - __main__ - Step 135663: {'lr': 1.1489694535370937e-05, 'samples': 26047296, 'steps': 135662, 'loss/train': 0.2613789141178131} 08/31/2021 13:55:08 - INFO - __main__ - Step 135664: {'lr': 1.1488104288356199e-05, 'samples': 26047488, 'steps': 135663, 'loss/train': 0.23760521411895752} 08/31/2021 13:55:09 - INFO - __main__ - Step 135665: {'lr': 1.1486514148811216e-05, 'samples': 26047680, 'steps': 135664, 'loss/train': 1.6611324548721313} 08/31/2021 13:55:09 - INFO - __main__ - Step 135666: {'lr': 1.1484924116736739e-05, 'samples': 26047872, 'steps': 135665, 'loss/train': 1.3225890398025513} 08/31/2021 13:55:09 - INFO - __main__ - Step 135667: {'lr': 1.1483334192133515e-05, 'samples': 26048064, 'steps': 135666, 'loss/train': 1.233636736869812} 08/31/2021 13:55:10 - INFO - __main__ - Step 135668: {'lr': 1.1481744375002185e-05, 'samples': 26048256, 'steps': 135667, 'loss/train': 1.3018475770950317} 08/31/2021 13:55:10 - INFO - __main__ - Step 135669: {'lr': 1.1480154665343496e-05, 'samples': 26048448, 'steps': 135668, 'loss/train': 0.6499327421188354} 08/31/2021 13:55:12 - INFO - __main__ - Step 135670: {'lr': 1.1478565063158197e-05, 'samples': 26048640, 'steps': 135669, 'loss/train': 0.999039351940155} 08/31/2021 13:55:13 - INFO - __main__ - Step 135671: {'lr': 1.1476975568446928e-05, 'samples': 26048832, 'steps': 135670, 'loss/train': 1.1621845960617065} 08/31/2021 13:55:13 - INFO - __main__ - Step 135672: {'lr': 1.1475386181210495e-05, 'samples': 26049024, 'steps': 135671, 'loss/train': 2.120631694793701} 08/31/2021 13:55:14 - INFO - __main__ - Step 135673: {'lr': 1.1473796901449535e-05, 'samples': 26049216, 'steps': 135672, 'loss/train': 0.8005233407020569} 08/31/2021 13:55:14 - INFO - __main__ - Step 135674: {'lr': 1.1472207729164824e-05, 'samples': 26049408, 'steps': 135673, 'loss/train': 0.9041796922683716} 08/31/2021 13:55:16 - INFO - __main__ - Step 135675: {'lr': 1.1470618664357057e-05, 'samples': 26049600, 'steps': 135674, 'loss/train': 1.3105289936065674} 08/31/2021 13:55:16 - INFO - __main__ - Step 135676: {'lr': 1.1469029707026957e-05, 'samples': 26049792, 'steps': 135675, 'loss/train': 1.1009124517440796} 08/31/2021 13:55:16 - INFO - __main__ - Step 135677: {'lr': 1.1467440857175216e-05, 'samples': 26049984, 'steps': 135676, 'loss/train': 0.4658840000629425} 08/31/2021 13:55:17 - INFO - __main__ - Step 135678: {'lr': 1.1465852114802584e-05, 'samples': 26050176, 'steps': 135677, 'loss/train': 0.9580632448196411} 08/31/2021 13:55:17 - INFO - __main__ - Step 135679: {'lr': 1.1464263479909754e-05, 'samples': 26050368, 'steps': 135678, 'loss/train': 1.2453877925872803} 08/31/2021 13:55:19 - INFO - __main__ - Step 135680: {'lr': 1.1462674952497421e-05, 'samples': 26050560, 'steps': 135679, 'loss/train': 0.03619980812072754} 08/31/2021 13:55:19 - INFO - __main__ - Step 135681: {'lr': 1.1461086532566334e-05, 'samples': 26050752, 'steps': 135680, 'loss/train': 1.8065857887268066} 08/31/2021 13:55:20 - INFO - __main__ - Step 135682: {'lr': 1.1459498220117214e-05, 'samples': 26050944, 'steps': 135681, 'loss/train': 0.8723141551017761} 08/31/2021 13:55:20 - INFO - __main__ - Step 135683: {'lr': 1.1457910015150758e-05, 'samples': 26051136, 'steps': 135682, 'loss/train': 1.3862409591674805} 08/31/2021 13:55:20 - INFO - __main__ - Step 135684: {'lr': 1.1456321917667684e-05, 'samples': 26051328, 'steps': 135683, 'loss/train': 1.728906273841858} 08/31/2021 13:55:21 - INFO - __main__ - Step 135685: {'lr': 1.1454733927668687e-05, 'samples': 26051520, 'steps': 135684, 'loss/train': 0.49557313323020935} 08/31/2021 13:55:22 - INFO - __main__ - Step 135686: {'lr': 1.1453146045154545e-05, 'samples': 26051712, 'steps': 135685, 'loss/train': 1.0490816831588745} 08/31/2021 13:55:23 - INFO - __main__ - Step 135687: {'lr': 1.1451558270125923e-05, 'samples': 26051904, 'steps': 135686, 'loss/train': 1.131506323814392} 08/31/2021 13:55:23 - INFO - __main__ - Step 135688: {'lr': 1.1449970602583543e-05, 'samples': 26052096, 'steps': 135687, 'loss/train': 0.42068853974342346} 08/31/2021 13:55:23 - INFO - __main__ - Step 135689: {'lr': 1.1448383042528127e-05, 'samples': 26052288, 'steps': 135688, 'loss/train': 0.9245850443840027} 08/31/2021 13:55:24 - INFO - __main__ - Step 135690: {'lr': 1.1446795589960396e-05, 'samples': 26052480, 'steps': 135689, 'loss/train': 1.1365045309066772} 08/31/2021 13:55:25 - INFO - __main__ - Step 135691: {'lr': 1.1445208244881044e-05, 'samples': 26052672, 'steps': 135690, 'loss/train': 0.6567499041557312} 08/31/2021 13:55:26 - INFO - __main__ - Step 135692: {'lr': 1.1443621007290822e-05, 'samples': 26052864, 'steps': 135691, 'loss/train': 1.2392407655715942} 08/31/2021 13:55:26 - INFO - __main__ - Step 135693: {'lr': 1.1442033877190395e-05, 'samples': 26053056, 'steps': 135692, 'loss/train': 0.9313551187515259} 08/31/2021 13:55:26 - INFO - __main__ - Step 135694: {'lr': 1.1440446854580511e-05, 'samples': 26053248, 'steps': 135693, 'loss/train': 1.4684902429580688} 08/31/2021 13:55:27 - INFO - __main__ - Step 135695: {'lr': 1.1438859939461893e-05, 'samples': 26053440, 'steps': 135694, 'loss/train': 1.3549891710281372} 08/31/2021 13:55:28 - INFO - __main__ - Step 135696: {'lr': 1.1437273131835234e-05, 'samples': 26053632, 'steps': 135695, 'loss/train': 1.238277554512024} 08/31/2021 13:55:29 - INFO - __main__ - Step 135697: {'lr': 1.143568643170126e-05, 'samples': 26053824, 'steps': 135696, 'loss/train': 0.20821009576320648} 08/31/2021 13:55:29 - INFO - __main__ - Step 135698: {'lr': 1.1434099839060685e-05, 'samples': 26054016, 'steps': 135697, 'loss/train': 0.6988328695297241} 08/31/2021 13:55:30 - INFO - __main__ - Step 135699: {'lr': 1.1432513353914236e-05, 'samples': 26054208, 'steps': 135698, 'loss/train': 1.2557023763656616} 08/31/2021 13:55:30 - INFO - __main__ - Step 135700: {'lr': 1.1430926976262606e-05, 'samples': 26054400, 'steps': 135699, 'loss/train': 1.0377395153045654} 08/31/2021 13:55:30 - INFO - __main__ - Step 135701: {'lr': 1.1429340706106516e-05, 'samples': 26054592, 'steps': 135700, 'loss/train': 0.952824592590332} 08/31/2021 13:55:32 - INFO - __main__ - Step 135702: {'lr': 1.1427754543446661e-05, 'samples': 26054784, 'steps': 135701, 'loss/train': 0.9559667706489563} 08/31/2021 13:55:33 - INFO - __main__ - Step 135703: {'lr': 1.1426168488283845e-05, 'samples': 26054976, 'steps': 135702, 'loss/train': 1.337860345840454} 08/31/2021 13:55:33 - INFO - __main__ - Step 135704: {'lr': 1.1424582540618678e-05, 'samples': 26055168, 'steps': 135703, 'loss/train': 1.1151987314224243} 08/31/2021 13:55:33 - INFO - __main__ - Step 135705: {'lr': 1.142299670045191e-05, 'samples': 26055360, 'steps': 135704, 'loss/train': 0.04410386085510254} 08/31/2021 13:55:34 - INFO - __main__ - Step 135706: {'lr': 1.1421410967784234e-05, 'samples': 26055552, 'steps': 135705, 'loss/train': 1.422103762626648} 08/31/2021 13:55:35 - INFO - __main__ - Step 135707: {'lr': 1.141982534261643e-05, 'samples': 26055744, 'steps': 135706, 'loss/train': 0.04570787772536278} 08/31/2021 13:55:36 - INFO - __main__ - Step 135708: {'lr': 1.1418239824949133e-05, 'samples': 26055936, 'steps': 135707, 'loss/train': 0.6915441751480103} 08/31/2021 13:55:36 - INFO - __main__ - Step 135709: {'lr': 1.1416654414783123e-05, 'samples': 26056128, 'steps': 135708, 'loss/train': 1.155859112739563} 08/31/2021 13:55:36 - INFO - __main__ - Step 135710: {'lr': 1.1415069112119065e-05, 'samples': 26056320, 'steps': 135709, 'loss/train': 1.765000820159912} 08/31/2021 13:55:37 - INFO - __main__ - Step 135711: {'lr': 1.1413483916957706e-05, 'samples': 26056512, 'steps': 135710, 'loss/train': 0.3544377386569977} 08/31/2021 13:55:38 - INFO - __main__ - Step 135712: {'lr': 1.1411898829299772e-05, 'samples': 26056704, 'steps': 135711, 'loss/train': 1.246044635772705} 08/31/2021 13:55:39 - INFO - __main__ - Step 135713: {'lr': 1.1410313849145926e-05, 'samples': 26056896, 'steps': 135712, 'loss/train': 0.7593244910240173} 08/31/2021 13:55:39 - INFO - __main__ - Step 135714: {'lr': 1.1408728976496918e-05, 'samples': 26057088, 'steps': 135713, 'loss/train': 1.4292230606079102} 08/31/2021 13:55:39 - INFO - __main__ - Step 135715: {'lr': 1.1407144211353443e-05, 'samples': 26057280, 'steps': 135714, 'loss/train': 0.5614884495735168} 08/31/2021 13:55:40 - INFO - __main__ - Step 135716: {'lr': 1.1405559553716277e-05, 'samples': 26057472, 'steps': 135715, 'loss/train': 1.4100182056427002} 08/31/2021 13:55:41 - INFO - __main__ - Step 135717: {'lr': 1.140397500358606e-05, 'samples': 26057664, 'steps': 135716, 'loss/train': 1.4959343671798706} 08/31/2021 13:55:41 - INFO - __main__ - Step 135718: {'lr': 1.1402390560963511e-05, 'samples': 26057856, 'steps': 135717, 'loss/train': 1.2084075212478638} 08/31/2021 13:55:42 - INFO - __main__ - Step 135719: {'lr': 1.1400806225849352e-05, 'samples': 26058048, 'steps': 135718, 'loss/train': 1.64512038230896} 08/31/2021 13:55:42 - INFO - __main__ - Step 135720: {'lr': 1.1399221998244336e-05, 'samples': 26058240, 'steps': 135719, 'loss/train': 1.2182163000106812} 08/31/2021 13:55:43 - INFO - __main__ - Step 135721: {'lr': 1.1397637878149154e-05, 'samples': 26058432, 'steps': 135720, 'loss/train': 1.4185032844543457} 08/31/2021 13:55:44 - INFO - __main__ - Step 135722: {'lr': 1.139605386556447e-05, 'samples': 26058624, 'steps': 135721, 'loss/train': 0.9785222411155701} 08/31/2021 13:55:45 - INFO - __main__ - Step 135723: {'lr': 1.1394469960491094e-05, 'samples': 26058816, 'steps': 135722, 'loss/train': 1.1013323068618774} 08/31/2021 13:55:45 - INFO - __main__ - Step 135724: {'lr': 1.1392886162929661e-05, 'samples': 26059008, 'steps': 135723, 'loss/train': 0.16646715998649597} 08/31/2021 13:55:45 - INFO - __main__ - Step 135725: {'lr': 1.1391302472880921e-05, 'samples': 26059200, 'steps': 135724, 'loss/train': 0.7584438920021057} 08/31/2021 13:55:46 - INFO - __main__ - Step 135726: {'lr': 1.1389718890345568e-05, 'samples': 26059392, 'steps': 135725, 'loss/train': 1.8344842195510864} 08/31/2021 13:55:46 - INFO - __main__ - Step 135727: {'lr': 1.1388135415324324e-05, 'samples': 26059584, 'steps': 135726, 'loss/train': 1.190678358078003} 08/31/2021 13:55:48 - INFO - __main__ - Step 135728: {'lr': 1.1386552047817911e-05, 'samples': 26059776, 'steps': 135727, 'loss/train': 0.5674504041671753} 08/31/2021 13:55:48 - INFO - __main__ - Step 135729: {'lr': 1.138496878782702e-05, 'samples': 26059968, 'steps': 135728, 'loss/train': 1.3332189321517944} 08/31/2021 13:55:49 - INFO - __main__ - Step 135730: {'lr': 1.1383385635352433e-05, 'samples': 26060160, 'steps': 135729, 'loss/train': 1.044137716293335} 08/31/2021 13:55:49 - INFO - __main__ - Step 135731: {'lr': 1.1381802590394785e-05, 'samples': 26060352, 'steps': 135730, 'loss/train': 0.5503758788108826} 08/31/2021 13:55:49 - INFO - __main__ - Step 135732: {'lr': 1.1380219652954799e-05, 'samples': 26060544, 'steps': 135731, 'loss/train': 1.1953940391540527} 08/31/2021 13:55:51 - INFO - __main__ - Step 135733: {'lr': 1.1378636823033195e-05, 'samples': 26060736, 'steps': 135732, 'loss/train': 2.4444808959960938} 08/31/2021 13:55:52 - INFO - __main__ - Step 135734: {'lr': 1.1377054100630723e-05, 'samples': 26060928, 'steps': 135733, 'loss/train': 1.606576681137085} 08/31/2021 13:55:52 - INFO - __main__ - Step 135735: {'lr': 1.137547148574805e-05, 'samples': 26061120, 'steps': 135734, 'loss/train': 0.8271543979644775} 08/31/2021 13:55:52 - INFO - __main__ - Step 135736: {'lr': 1.1373888978385899e-05, 'samples': 26061312, 'steps': 135735, 'loss/train': 0.037226155400276184} 08/31/2021 13:55:53 - INFO - __main__ - Step 135737: {'lr': 1.1372306578544988e-05, 'samples': 26061504, 'steps': 135736, 'loss/train': 0.04998461529612541} 08/31/2021 13:55:53 - INFO - __main__ - Step 135738: {'lr': 1.137072428622607e-05, 'samples': 26061696, 'steps': 135737, 'loss/train': 0.10567859560251236} 08/31/2021 13:55:55 - INFO - __main__ - Step 135739: {'lr': 1.136914210142978e-05, 'samples': 26061888, 'steps': 135738, 'loss/train': 0.027189629152417183} 08/31/2021 13:55:55 - INFO - __main__ - Step 135740: {'lr': 1.1367560024156899e-05, 'samples': 26062080, 'steps': 135739, 'loss/train': 1.335309386253357} 08/31/2021 13:55:55 - INFO - __main__ - Step 135741: {'lr': 1.1365978054408115e-05, 'samples': 26062272, 'steps': 135740, 'loss/train': 0.6265890598297119} 08/31/2021 13:55:56 - INFO - __main__ - Step 135742: {'lr': 1.1364396192184129e-05, 'samples': 26062464, 'steps': 135741, 'loss/train': 1.4708105325698853} 08/31/2021 13:55:56 - INFO - __main__ - Step 135743: {'lr': 1.1362814437485686e-05, 'samples': 26062656, 'steps': 135742, 'loss/train': 0.1348184496164322} 08/31/2021 13:55:58 - INFO - __main__ - Step 135744: {'lr': 1.1361232790313452e-05, 'samples': 26062848, 'steps': 135743, 'loss/train': 0.8139241933822632} 08/31/2021 13:55:58 - INFO - __main__ - Step 135745: {'lr': 1.135965125066818e-05, 'samples': 26063040, 'steps': 135744, 'loss/train': 0.7348231673240662} 08/31/2021 13:55:58 - INFO - __main__ - Step 135746: {'lr': 1.1358069818550532e-05, 'samples': 26063232, 'steps': 135745, 'loss/train': 1.0393316745758057} 08/31/2021 13:55:59 - INFO - __main__ - Step 135747: {'lr': 1.1356488493961286e-05, 'samples': 26063424, 'steps': 135746, 'loss/train': 0.507651150226593} 08/31/2021 13:55:59 - INFO - __main__ - Step 135748: {'lr': 1.1354907276901111e-05, 'samples': 26063616, 'steps': 135747, 'loss/train': 1.1054853200912476} 08/31/2021 13:56:01 - INFO - __main__ - Step 135749: {'lr': 1.1353326167370725e-05, 'samples': 26063808, 'steps': 135748, 'loss/train': 0.44447484612464905} 08/31/2021 13:56:01 - INFO - __main__ - Step 135750: {'lr': 1.135174516537088e-05, 'samples': 26064000, 'steps': 135749, 'loss/train': 0.027993610128760338} 08/31/2021 13:56:02 - INFO - __main__ - Step 135751: {'lr': 1.1350164270902214e-05, 'samples': 26064192, 'steps': 135750, 'loss/train': 1.6227251291275024} 08/31/2021 13:56:02 - INFO - __main__ - Step 135752: {'lr': 1.1348583483965502e-05, 'samples': 26064384, 'steps': 135751, 'loss/train': 1.1754783391952515} 08/31/2021 13:56:02 - INFO - __main__ - Step 135753: {'lr': 1.134700280456144e-05, 'samples': 26064576, 'steps': 135752, 'loss/train': 0.8466875553131104} 08/31/2021 13:56:04 - INFO - __main__ - Step 135754: {'lr': 1.1345422232690721e-05, 'samples': 26064768, 'steps': 135753, 'loss/train': 1.3791301250457764} 08/31/2021 13:56:04 - INFO - __main__ - Step 135755: {'lr': 1.1343841768354097e-05, 'samples': 26064960, 'steps': 135754, 'loss/train': 0.5188976526260376} 08/31/2021 13:56:05 - INFO - __main__ - Step 135756: {'lr': 1.134226141155223e-05, 'samples': 26065152, 'steps': 135755, 'loss/train': 1.7234364748001099} 08/31/2021 13:56:05 - INFO - __main__ - Step 135757: {'lr': 1.1340681162285898e-05, 'samples': 26065344, 'steps': 135756, 'loss/train': 0.9541659355163574} 08/31/2021 13:56:05 - INFO - __main__ - Step 135758: {'lr': 1.1339101020555742e-05, 'samples': 26065536, 'steps': 135757, 'loss/train': 0.726466953754425} 08/31/2021 13:56:06 - INFO - __main__ - Step 135759: {'lr': 1.1337520986362509e-05, 'samples': 26065728, 'steps': 135758, 'loss/train': 1.3215237855911255} 08/31/2021 13:56:07 - INFO - __main__ - Step 135760: {'lr': 1.1335941059706895e-05, 'samples': 26065920, 'steps': 135759, 'loss/train': 1.3708313703536987} 08/31/2021 13:56:08 - INFO - __main__ - Step 135761: {'lr': 1.1334361240589647e-05, 'samples': 26066112, 'steps': 135760, 'loss/train': 3.781679153442383} 08/31/2021 13:56:08 - INFO - __main__ - Step 135762: {'lr': 1.1332781529011433e-05, 'samples': 26066304, 'steps': 135761, 'loss/train': 0.5644209980964661} 08/31/2021 13:56:08 - INFO - __main__ - Step 135763: {'lr': 1.1331201924972972e-05, 'samples': 26066496, 'steps': 135762, 'loss/train': 1.277139663696289} 08/31/2021 13:56:09 - INFO - __main__ - Step 135764: {'lr': 1.1329622428475017e-05, 'samples': 26066688, 'steps': 135763, 'loss/train': 0.7710849642753601} 08/31/2021 13:56:10 - INFO - __main__ - Step 135765: {'lr': 1.1328043039518232e-05, 'samples': 26066880, 'steps': 135764, 'loss/train': 1.0347727537155151} 08/31/2021 13:56:11 - INFO - __main__ - Step 135766: {'lr': 1.1326463758103339e-05, 'samples': 26067072, 'steps': 135765, 'loss/train': 0.9827687740325928} 08/31/2021 13:56:11 - INFO - __main__ - Step 135767: {'lr': 1.1324884584231087e-05, 'samples': 26067264, 'steps': 135766, 'loss/train': 0.9564675688743591} 08/31/2021 13:56:12 - INFO - __main__ - Step 135768: {'lr': 1.1323305517902144e-05, 'samples': 26067456, 'steps': 135767, 'loss/train': 0.7102288007736206} 08/31/2021 13:56:12 - INFO - __main__ - Step 135769: {'lr': 1.132172655911723e-05, 'samples': 26067648, 'steps': 135768, 'loss/train': 0.6797971129417419} 08/31/2021 13:56:12 - INFO - __main__ - Step 135770: {'lr': 1.132014770787712e-05, 'samples': 26067840, 'steps': 135769, 'loss/train': 1.6464179754257202} 08/31/2021 13:56:14 - INFO - __main__ - Step 135771: {'lr': 1.1318568964182403e-05, 'samples': 26068032, 'steps': 135770, 'loss/train': 0.22742080688476562} 08/31/2021 13:56:14 - INFO - __main__ - Step 135772: {'lr': 1.1316990328033878e-05, 'samples': 26068224, 'steps': 135771, 'loss/train': 1.4351345300674438} 08/31/2021 13:56:15 - INFO - __main__ - Step 135773: {'lr': 1.1315411799432213e-05, 'samples': 26068416, 'steps': 135772, 'loss/train': 0.40624892711639404} 08/31/2021 13:56:15 - INFO - __main__ - Step 135774: {'lr': 1.1313833378378158e-05, 'samples': 26068608, 'steps': 135773, 'loss/train': 0.9084458947181702} 08/31/2021 13:56:15 - INFO - __main__ - Step 135775: {'lr': 1.1312255064872407e-05, 'samples': 26068800, 'steps': 135774, 'loss/train': 0.4831244647502899} 08/31/2021 13:56:17 - INFO - __main__ - Step 135776: {'lr': 1.131067685891568e-05, 'samples': 26068992, 'steps': 135775, 'loss/train': 0.9664528965950012} 08/31/2021 13:56:18 - INFO - __main__ - Step 135777: {'lr': 1.1309098760508646e-05, 'samples': 26069184, 'steps': 135776, 'loss/train': 1.0351275205612183} 08/31/2021 13:56:18 - INFO - __main__ - Step 135778: {'lr': 1.130752076965208e-05, 'samples': 26069376, 'steps': 135777, 'loss/train': 0.6410846710205078} 08/31/2021 13:56:18 - INFO - __main__ - Step 135779: {'lr': 1.1305942886346648e-05, 'samples': 26069568, 'steps': 135778, 'loss/train': 1.2092965841293335} 08/31/2021 13:56:19 - INFO - __main__ - Step 135780: {'lr': 1.1304365110593073e-05, 'samples': 26069760, 'steps': 135779, 'loss/train': 0.03788333386182785} 08/31/2021 13:56:19 - INFO - __main__ - Step 135781: {'lr': 1.1302787442392077e-05, 'samples': 26069952, 'steps': 135780, 'loss/train': 0.09597895294427872} 08/31/2021 13:56:21 - INFO - __main__ - Step 135782: {'lr': 1.1301209881744351e-05, 'samples': 26070144, 'steps': 135781, 'loss/train': 4.121557235717773} 08/31/2021 13:56:22 - INFO - __main__ - Step 135783: {'lr': 1.1299632428650647e-05, 'samples': 26070336, 'steps': 135782, 'loss/train': 1.4192638397216797} 08/31/2021 13:56:22 - INFO - __main__ - Step 135784: {'lr': 1.129805508311163e-05, 'samples': 26070528, 'steps': 135783, 'loss/train': 1.3985824584960938} 08/31/2021 13:56:23 - INFO - __main__ - Step 135785: {'lr': 1.1296477845128022e-05, 'samples': 26070720, 'steps': 135784, 'loss/train': 1.11838960647583} 08/31/2021 13:56:23 - INFO - __main__ - Step 135786: {'lr': 1.1294900714700545e-05, 'samples': 26070912, 'steps': 135785, 'loss/train': 1.1516879796981812} 08/31/2021 13:56:23 - INFO - __main__ - Step 135787: {'lr': 1.1293323691829893e-05, 'samples': 26071104, 'steps': 135786, 'loss/train': 0.9198745489120483} 08/31/2021 13:56:25 - INFO - __main__ - Step 135788: {'lr': 1.129174677651676e-05, 'samples': 26071296, 'steps': 135787, 'loss/train': 0.2095835953950882} 08/31/2021 13:56:25 - INFO - __main__ - Step 135789: {'lr': 1.1290169968761922e-05, 'samples': 26071488, 'steps': 135788, 'loss/train': 1.0498886108398438} 08/31/2021 13:56:26 - INFO - __main__ - Step 135790: {'lr': 1.1288593268566016e-05, 'samples': 26071680, 'steps': 135789, 'loss/train': 0.48797377943992615} 08/31/2021 13:56:26 - INFO - __main__ - Step 135791: {'lr': 1.1287016675929823e-05, 'samples': 26071872, 'steps': 135790, 'loss/train': 1.0871459245681763} 08/31/2021 13:56:26 - INFO - __main__ - Step 135792: {'lr': 1.128544019085398e-05, 'samples': 26072064, 'steps': 135791, 'loss/train': 0.692709743976593} 08/31/2021 13:56:29 - INFO - __main__ - Step 135793: {'lr': 1.1283863813339262e-05, 'samples': 26072256, 'steps': 135792, 'loss/train': 1.1628201007843018} 08/31/2021 13:56:29 - INFO - __main__ - Step 135794: {'lr': 1.1282287543386338e-05, 'samples': 26072448, 'steps': 135793, 'loss/train': 1.6491281986236572} 08/31/2021 13:56:29 - INFO - __main__ - Step 135795: {'lr': 1.1280711380995928e-05, 'samples': 26072640, 'steps': 135794, 'loss/train': 0.796941876411438} 08/31/2021 13:56:30 - INFO - __main__ - Step 135796: {'lr': 1.1279135326168755e-05, 'samples': 26072832, 'steps': 135795, 'loss/train': 1.341009497642517} 08/31/2021 13:56:30 - INFO - __main__ - Step 135797: {'lr': 1.1277559378905567e-05, 'samples': 26073024, 'steps': 135796, 'loss/train': 0.4452818036079407} 08/31/2021 13:56:32 - INFO - __main__ - Step 135798: {'lr': 1.1275983539206975e-05, 'samples': 26073216, 'steps': 135797, 'loss/train': 0.1362704634666443} 08/31/2021 13:56:32 - INFO - __main__ - Step 135799: {'lr': 1.1274407807073728e-05, 'samples': 26073408, 'steps': 135798, 'loss/train': 1.078315019607544} 08/31/2021 13:56:32 - INFO - __main__ - Step 135800: {'lr': 1.1272832182506576e-05, 'samples': 26073600, 'steps': 135799, 'loss/train': 1.409411072731018} 08/31/2021 13:56:33 - INFO - __main__ - Step 135801: {'lr': 1.1271256665506185e-05, 'samples': 26073792, 'steps': 135800, 'loss/train': 1.210559606552124} 08/31/2021 13:56:33 - INFO - __main__ - Step 135802: {'lr': 1.1269681256073277e-05, 'samples': 26073984, 'steps': 135801, 'loss/train': 1.1056382656097412} 08/31/2021 13:56:35 - INFO - __main__ - Step 135803: {'lr': 1.1268105954208573e-05, 'samples': 26074176, 'steps': 135802, 'loss/train': 1.4997990131378174} 08/31/2021 13:56:36 - INFO - __main__ - Step 135804: {'lr': 1.1266530759912797e-05, 'samples': 26074368, 'steps': 135803, 'loss/train': 1.595647931098938} 08/31/2021 13:56:36 - INFO - __main__ - Step 135805: {'lr': 1.1264955673186611e-05, 'samples': 26074560, 'steps': 135804, 'loss/train': 5.823580265045166} 08/31/2021 13:56:37 - INFO - __main__ - Step 135806: {'lr': 1.1263380694030767e-05, 'samples': 26074752, 'steps': 135805, 'loss/train': 5.788455486297607} 08/31/2021 13:56:37 - INFO - __main__ - Step 135807: {'lr': 1.1261805822445959e-05, 'samples': 26074944, 'steps': 135806, 'loss/train': 5.780632495880127} 08/31/2021 13:56:37 - INFO - __main__ - Step 135808: {'lr': 1.1260231058432879e-05, 'samples': 26075136, 'steps': 135807, 'loss/train': 0.9556735754013062} 08/31/2021 13:56:38 - INFO - __main__ - Step 135809: {'lr': 1.125865640199228e-05, 'samples': 26075328, 'steps': 135808, 'loss/train': 1.1069601774215698} 08/31/2021 13:56:39 - INFO - __main__ - Step 135810: {'lr': 1.1257081853124822e-05, 'samples': 26075520, 'steps': 135809, 'loss/train': 1.1851229667663574} 08/31/2021 13:56:40 - INFO - __main__ - Step 135811: {'lr': 1.125550741183129e-05, 'samples': 26075712, 'steps': 135810, 'loss/train': 0.41634127497673035} 08/31/2021 13:56:40 - INFO - __main__ - Step 135812: {'lr': 1.1253933078112316e-05, 'samples': 26075904, 'steps': 135811, 'loss/train': 0.1379292607307434} 08/31/2021 13:56:41 - INFO - __main__ - Step 135813: {'lr': 1.1252358851968624e-05, 'samples': 26076096, 'steps': 135812, 'loss/train': 0.049783945083618164} 08/31/2021 13:56:41 - INFO - __main__ - Step 135814: {'lr': 1.1250784733400937e-05, 'samples': 26076288, 'steps': 135813, 'loss/train': 0.5527417063713074} 08/31/2021 13:56:42 - INFO - __main__ - Step 135815: {'lr': 1.1249210722409975e-05, 'samples': 26076480, 'steps': 135814, 'loss/train': 0.31307312846183777} 08/31/2021 13:56:43 - INFO - __main__ - Step 135816: {'lr': 1.1247636818996405e-05, 'samples': 26076672, 'steps': 135815, 'loss/train': 0.8664857149124146} 08/31/2021 13:56:43 - INFO - __main__ - Step 135817: {'lr': 1.1246063023160974e-05, 'samples': 26076864, 'steps': 135816, 'loss/train': 0.04004292190074921} 08/31/2021 13:56:44 - INFO - __main__ - Step 135818: {'lr': 1.1244489334904407e-05, 'samples': 26077056, 'steps': 135817, 'loss/train': 1.4667391777038574} 08/31/2021 13:56:44 - INFO - __main__ - Step 135819: {'lr': 1.1242915754227367e-05, 'samples': 26077248, 'steps': 135818, 'loss/train': 1.3804826736450195} 08/31/2021 13:56:45 - INFO - __main__ - Step 135820: {'lr': 1.124134228113058e-05, 'samples': 26077440, 'steps': 135819, 'loss/train': 1.0692970752716064} 08/31/2021 13:56:46 - INFO - __main__ - Step 135821: {'lr': 1.123976891561479e-05, 'samples': 26077632, 'steps': 135820, 'loss/train': 1.0556182861328125} 08/31/2021 13:56:46 - INFO - __main__ - Step 135822: {'lr': 1.123819565768064e-05, 'samples': 26077824, 'steps': 135821, 'loss/train': 0.908686637878418} 08/31/2021 13:56:47 - INFO - __main__ - Step 135823: {'lr': 1.1236622507328903e-05, 'samples': 26078016, 'steps': 135822, 'loss/train': 1.186659574508667} 08/31/2021 13:56:47 - INFO - __main__ - Step 135824: {'lr': 1.1235049464560276e-05, 'samples': 26078208, 'steps': 135823, 'loss/train': 0.46425023674964905} 08/31/2021 13:56:49 - INFO - __main__ - Step 135825: {'lr': 1.1233476529375425e-05, 'samples': 26078400, 'steps': 135824, 'loss/train': 0.8611828088760376} 08/31/2021 13:56:49 - INFO - __main__ - Step 135826: {'lr': 1.123190370177507e-05, 'samples': 26078592, 'steps': 135825, 'loss/train': 0.858467698097229} 08/31/2021 13:56:49 - INFO - __main__ - Step 135827: {'lr': 1.1230330981759962e-05, 'samples': 26078784, 'steps': 135826, 'loss/train': 0.9843056201934814} 08/31/2021 13:56:50 - INFO - __main__ - Step 135828: {'lr': 1.1228758369330766e-05, 'samples': 26078976, 'steps': 135827, 'loss/train': 0.8407114148139954} 08/31/2021 13:56:50 - INFO - __main__ - Step 135829: {'lr': 1.1227185864488205e-05, 'samples': 26079168, 'steps': 135828, 'loss/train': 1.3282181024551392} 08/31/2021 13:56:50 - INFO - __main__ - Step 135830: {'lr': 1.1225613467232998e-05, 'samples': 26079360, 'steps': 135829, 'loss/train': 0.02635098248720169} 08/31/2021 13:56:52 - INFO - __main__ - Step 135831: {'lr': 1.1224041177565841e-05, 'samples': 26079552, 'steps': 135830, 'loss/train': 1.0060577392578125} 08/31/2021 13:56:52 - INFO - __main__ - Step 135832: {'lr': 1.1222468995487428e-05, 'samples': 26079744, 'steps': 135831, 'loss/train': 1.3182313442230225} 08/31/2021 13:56:53 - INFO - __main__ - Step 135833: {'lr': 1.1220896920998507e-05, 'samples': 26079936, 'steps': 135832, 'loss/train': 1.4542969465255737} 08/31/2021 13:56:53 - INFO - __main__ - Step 135834: {'lr': 1.1219324954099774e-05, 'samples': 26080128, 'steps': 135833, 'loss/train': 0.4207161068916321} 08/31/2021 13:56:53 - INFO - __main__ - Step 135835: {'lr': 1.1217753094791922e-05, 'samples': 26080320, 'steps': 135834, 'loss/train': 1.8285988569259644} 08/31/2021 13:56:55 - INFO - __main__ - Step 135836: {'lr': 1.1216181343075643e-05, 'samples': 26080512, 'steps': 135835, 'loss/train': 1.3758621215820312} 08/31/2021 13:56:55 - INFO - __main__ - Step 135837: {'lr': 1.1214609698951717e-05, 'samples': 26080704, 'steps': 135836, 'loss/train': 0.018705176189541817} 08/31/2021 13:56:56 - INFO - __main__ - Step 135838: {'lr': 1.121303816242078e-05, 'samples': 26080896, 'steps': 135837, 'loss/train': 0.023438330739736557} 08/31/2021 13:56:56 - INFO - __main__ - Step 135839: {'lr': 1.1211466733483556e-05, 'samples': 26081088, 'steps': 135838, 'loss/train': 0.7129339575767517} 08/31/2021 13:56:57 - INFO - __main__ - Step 135840: {'lr': 1.1209895412140764e-05, 'samples': 26081280, 'steps': 135839, 'loss/train': 0.6721509695053101} 08/31/2021 13:56:57 - INFO - __main__ - Step 135841: {'lr': 1.12083241983931e-05, 'samples': 26081472, 'steps': 135840, 'loss/train': 1.1851528882980347} 08/31/2021 13:56:59 - INFO - __main__ - Step 135842: {'lr': 1.1206753092241284e-05, 'samples': 26081664, 'steps': 135841, 'loss/train': 0.06419677287340164} 08/31/2021 13:57:00 - INFO - __main__ - Step 135843: {'lr': 1.1205182093686011e-05, 'samples': 26081856, 'steps': 135842, 'loss/train': 0.2807658612728119} 08/31/2021 13:57:00 - INFO - __main__ - Step 135844: {'lr': 1.1203611202728004e-05, 'samples': 26082048, 'steps': 135843, 'loss/train': 1.6373425722122192} 08/31/2021 13:57:00 - INFO - __main__ - Step 135845: {'lr': 1.1202040419367982e-05, 'samples': 26082240, 'steps': 135844, 'loss/train': 0.776153028011322} 08/31/2021 13:57:01 - INFO - __main__ - Step 135846: {'lr': 1.1200469743606612e-05, 'samples': 26082432, 'steps': 135845, 'loss/train': 0.9125943183898926} 08/31/2021 13:57:02 - INFO - __main__ - Step 135847: {'lr': 1.1198899175444643e-05, 'samples': 26082624, 'steps': 135846, 'loss/train': 1.1985512971878052} 08/31/2021 13:57:03 - INFO - __main__ - Step 135848: {'lr': 1.1197328714882743e-05, 'samples': 26082816, 'steps': 135847, 'loss/train': 0.8616971373558044} 08/31/2021 13:57:03 - INFO - __main__ - Step 135849: {'lr': 1.119575836192166e-05, 'samples': 26083008, 'steps': 135848, 'loss/train': 1.180379867553711} 08/31/2021 13:57:03 - INFO - __main__ - Step 135850: {'lr': 1.1194188116562087e-05, 'samples': 26083200, 'steps': 135849, 'loss/train': 1.0449310541152954} 08/31/2021 13:57:04 - INFO - __main__ - Step 135851: {'lr': 1.1192617978804748e-05, 'samples': 26083392, 'steps': 135850, 'loss/train': 1.3913286924362183} 08/31/2021 13:57:05 - INFO - __main__ - Step 135852: {'lr': 1.1191047948650306e-05, 'samples': 26083584, 'steps': 135851, 'loss/train': 0.5934361219406128} 08/31/2021 13:57:06 - INFO - __main__ - Step 135853: {'lr': 1.1189478026099487e-05, 'samples': 26083776, 'steps': 135852, 'loss/train': 1.4403929710388184} 08/31/2021 13:57:06 - INFO - __main__ - Step 135854: {'lr': 1.1187908211153008e-05, 'samples': 26083968, 'steps': 135853, 'loss/train': 1.1999733448028564} 08/31/2021 13:57:06 - INFO - __main__ - Step 135855: {'lr': 1.1186338503811566e-05, 'samples': 26084160, 'steps': 135854, 'loss/train': 1.0588934421539307} 08/31/2021 13:57:07 - INFO - __main__ - Step 135856: {'lr': 1.1184768904075882e-05, 'samples': 26084352, 'steps': 135855, 'loss/train': 0.8998607397079468} 08/31/2021 13:57:08 - INFO - __main__ - Step 135857: {'lr': 1.1183199411946648e-05, 'samples': 26084544, 'steps': 135856, 'loss/train': 1.164198875427246} 08/31/2021 13:57:09 - INFO - __main__ - Step 135858: {'lr': 1.118163002742459e-05, 'samples': 26084736, 'steps': 135857, 'loss/train': 0.40022432804107666} 08/31/2021 13:57:09 - INFO - __main__ - Step 135859: {'lr': 1.1180060750510396e-05, 'samples': 26084928, 'steps': 135858, 'loss/train': 1.3945691585540771} 08/31/2021 13:57:09 - INFO - __main__ - Step 135860: {'lr': 1.1178491581204791e-05, 'samples': 26085120, 'steps': 135859, 'loss/train': 0.8703439831733704} 08/31/2021 13:57:10 - INFO - __main__ - Step 135861: {'lr': 1.117692251950847e-05, 'samples': 26085312, 'steps': 135860, 'loss/train': 0.8209375143051147} 08/31/2021 13:57:11 - INFO - __main__ - Step 135862: {'lr': 1.1175353565422125e-05, 'samples': 26085504, 'steps': 135861, 'loss/train': 0.8114010095596313} 08/31/2021 13:57:12 - INFO - __main__ - Step 135863: {'lr': 1.1173784718946506e-05, 'samples': 26085696, 'steps': 135862, 'loss/train': 1.2204822301864624} 08/31/2021 13:57:12 - INFO - __main__ - Step 135864: {'lr': 1.1172215980082307e-05, 'samples': 26085888, 'steps': 135863, 'loss/train': 1.3805655241012573} 08/31/2021 13:57:12 - INFO - __main__ - Step 135865: {'lr': 1.117064734883022e-05, 'samples': 26086080, 'steps': 135864, 'loss/train': 0.6405295133590698} 08/31/2021 13:57:13 - INFO - __main__ - Step 135866: {'lr': 1.1169078825190915e-05, 'samples': 26086272, 'steps': 135865, 'loss/train': 1.246888279914856} 08/31/2021 13:57:13 - INFO - __main__ - Step 135867: {'lr': 1.1167510409165166e-05, 'samples': 26086464, 'steps': 135866, 'loss/train': 1.0165334939956665} 08/31/2021 13:57:15 - INFO - __main__ - Step 135868: {'lr': 1.116594210075364e-05, 'samples': 26086656, 'steps': 135867, 'loss/train': 0.4812604486942291} 08/31/2021 13:57:16 - INFO - __main__ - Step 135869: {'lr': 1.1164373899957059e-05, 'samples': 26086848, 'steps': 135868, 'loss/train': 1.1516451835632324} 08/31/2021 13:57:16 - INFO - __main__ - Step 135870: {'lr': 1.1162805806776117e-05, 'samples': 26087040, 'steps': 135869, 'loss/train': 0.3330908715724945} 08/31/2021 13:57:17 - INFO - __main__ - Step 135871: {'lr': 1.1161237821211534e-05, 'samples': 26087232, 'steps': 135870, 'loss/train': 1.335036039352417} 08/31/2021 13:57:17 - INFO - __main__ - Step 135872: {'lr': 1.1159669943264006e-05, 'samples': 26087424, 'steps': 135871, 'loss/train': 0.24550314247608185} 08/31/2021 13:57:17 - INFO - __main__ - Step 135873: {'lr': 1.1158102172934254e-05, 'samples': 26087616, 'steps': 135872, 'loss/train': 0.2507099211215973} 08/31/2021 13:57:19 - INFO - __main__ - Step 135874: {'lr': 1.1156534510222971e-05, 'samples': 26087808, 'steps': 135873, 'loss/train': 1.104576826095581} 08/31/2021 13:57:19 - INFO - __main__ - Step 135875: {'lr': 1.1154966955130853e-05, 'samples': 26088000, 'steps': 135874, 'loss/train': 1.4037315845489502} 08/31/2021 13:57:20 - INFO - __main__ - Step 135876: {'lr': 1.1153399507658646e-05, 'samples': 26088192, 'steps': 135875, 'loss/train': 1.3526440858840942} 08/31/2021 13:57:20 - INFO - __main__ - Step 135877: {'lr': 1.1151832167807018e-05, 'samples': 26088384, 'steps': 135876, 'loss/train': 0.9035965800285339} 08/31/2021 13:57:20 - INFO - __main__ - Step 135878: {'lr': 1.115026493557672e-05, 'samples': 26088576, 'steps': 135877, 'loss/train': 1.230609655380249} 08/31/2021 13:57:23 - INFO - __main__ - Step 135879: {'lr': 1.1148697810968416e-05, 'samples': 26088768, 'steps': 135878, 'loss/train': 0.9822601675987244} 08/31/2021 13:57:23 - INFO - __main__ - Step 135880: {'lr': 1.1147130793982802e-05, 'samples': 26088960, 'steps': 135879, 'loss/train': 0.7946138381958008} 08/31/2021 13:57:24 - INFO - __main__ - Step 135881: {'lr': 1.1145563884620625e-05, 'samples': 26089152, 'steps': 135880, 'loss/train': 0.8152989745140076} 08/31/2021 13:57:24 - INFO - __main__ - Step 135882: {'lr': 1.114399708288255e-05, 'samples': 26089344, 'steps': 135881, 'loss/train': 1.3507754802703857} 08/31/2021 13:57:24 - INFO - __main__ - Step 135883: {'lr': 1.1142430388769304e-05, 'samples': 26089536, 'steps': 135882, 'loss/train': 1.3011858463287354} 08/31/2021 13:57:25 - INFO - __main__ - Step 135884: {'lr': 1.1140863802281604e-05, 'samples': 26089728, 'steps': 135883, 'loss/train': 1.3692713975906372} 08/31/2021 13:57:25 - INFO - __main__ - Step 135885: {'lr': 1.1139297323420144e-05, 'samples': 26089920, 'steps': 135884, 'loss/train': 0.30706191062927246} 08/31/2021 13:57:27 - INFO - __main__ - Step 135886: {'lr': 1.113773095218562e-05, 'samples': 26090112, 'steps': 135885, 'loss/train': 0.7636314034461975} 08/31/2021 13:57:27 - INFO - __main__ - Step 135887: {'lr': 1.1136164688578753e-05, 'samples': 26090304, 'steps': 135886, 'loss/train': 0.4748229384422302} 08/31/2021 13:57:28 - INFO - __main__ - Step 135888: {'lr': 1.1134598532600265e-05, 'samples': 26090496, 'steps': 135887, 'loss/train': 1.3592489957809448} 08/31/2021 13:57:28 - INFO - __main__ - Step 135889: {'lr': 1.113303248425082e-05, 'samples': 26090688, 'steps': 135888, 'loss/train': 1.1897059679031372} 08/31/2021 13:57:28 - INFO - __main__ - Step 135890: {'lr': 1.1131466543531144e-05, 'samples': 26090880, 'steps': 135889, 'loss/train': 1.3694461584091187} 08/31/2021 13:57:30 - INFO - __main__ - Step 135891: {'lr': 1.1129900710441981e-05, 'samples': 26091072, 'steps': 135890, 'loss/train': 1.1392834186553955} 08/31/2021 13:57:30 - INFO - __main__ - Step 135892: {'lr': 1.1128334984983973e-05, 'samples': 26091264, 'steps': 135891, 'loss/train': 0.43681371212005615} 08/31/2021 13:57:31 - INFO - __main__ - Step 135893: {'lr': 1.112676936715784e-05, 'samples': 26091456, 'steps': 135892, 'loss/train': 1.4637322425842285} 08/31/2021 13:57:31 - INFO - __main__ - Step 135894: {'lr': 1.1125203856964305e-05, 'samples': 26091648, 'steps': 135893, 'loss/train': 0.8009015321731567} 08/31/2021 13:57:31 - INFO - __main__ - Step 135895: {'lr': 1.112363845440406e-05, 'samples': 26091840, 'steps': 135894, 'loss/train': 1.4539942741394043} 08/31/2021 13:57:33 - INFO - __main__ - Step 135896: {'lr': 1.1122073159477802e-05, 'samples': 26092032, 'steps': 135895, 'loss/train': 0.8789016604423523} 08/31/2021 13:57:34 - INFO - __main__ - Step 135897: {'lr': 1.1120507972186277e-05, 'samples': 26092224, 'steps': 135896, 'loss/train': 0.857567548751831} 08/31/2021 13:57:34 - INFO - __main__ - Step 135898: {'lr': 1.1118942892530154e-05, 'samples': 26092416, 'steps': 135897, 'loss/train': 1.42251718044281} 08/31/2021 13:57:34 - INFO - __main__ - Step 135899: {'lr': 1.111737792051018e-05, 'samples': 26092608, 'steps': 135898, 'loss/train': 0.8468984365463257} 08/31/2021 13:57:35 - INFO - __main__ - Step 135900: {'lr': 1.1115813056126995e-05, 'samples': 26092800, 'steps': 135899, 'loss/train': 0.09959083050489426} 08/31/2021 13:57:36 - INFO - __main__ - Step 135901: {'lr': 1.1114248299381346e-05, 'samples': 26092992, 'steps': 135900, 'loss/train': 1.2132288217544556} 08/31/2021 13:57:37 - INFO - __main__ - Step 135902: {'lr': 1.111268365027393e-05, 'samples': 26093184, 'steps': 135901, 'loss/train': 0.9819706678390503} 08/31/2021 13:57:37 - INFO - __main__ - Step 135903: {'lr': 1.1111119108805495e-05, 'samples': 26093376, 'steps': 135902, 'loss/train': 1.2540041208267212} 08/31/2021 13:57:38 - INFO - __main__ - Step 135904: {'lr': 1.1109554674976651e-05, 'samples': 26093568, 'steps': 135903, 'loss/train': 0.37961527705192566} 08/31/2021 13:57:38 - INFO - __main__ - Step 135905: {'lr': 1.1107990348788178e-05, 'samples': 26093760, 'steps': 135904, 'loss/train': 1.3110661506652832} 08/31/2021 13:57:38 - INFO - __main__ - Step 135906: {'lr': 1.1106426130240738e-05, 'samples': 26093952, 'steps': 135905, 'loss/train': 1.0469496250152588} 08/31/2021 13:57:40 - INFO - __main__ - Step 135907: {'lr': 1.1104862019335055e-05, 'samples': 26094144, 'steps': 135906, 'loss/train': 1.2266418933868408} 08/31/2021 13:57:40 - INFO - __main__ - Step 135908: {'lr': 1.110329801607185e-05, 'samples': 26094336, 'steps': 135907, 'loss/train': 0.3084953725337982} 08/31/2021 13:57:41 - INFO - __main__ - Step 135909: {'lr': 1.1101734120451818e-05, 'samples': 26094528, 'steps': 135908, 'loss/train': 5.184093475341797} 08/31/2021 13:57:41 - INFO - __main__ - Step 135910: {'lr': 1.110017033247565e-05, 'samples': 26094720, 'steps': 135909, 'loss/train': 0.6464161276817322} 08/31/2021 13:57:41 - INFO - __main__ - Step 135911: {'lr': 1.1098606652144045e-05, 'samples': 26094912, 'steps': 135910, 'loss/train': 1.0765959024429321} 08/31/2021 13:57:43 - INFO - __main__ - Step 135912: {'lr': 1.1097043079457747e-05, 'samples': 26095104, 'steps': 135911, 'loss/train': 0.36193013191223145} 08/31/2021 13:57:43 - INFO - __main__ - Step 135913: {'lr': 1.1095479614417425e-05, 'samples': 26095296, 'steps': 135912, 'loss/train': 1.5894120931625366} 08/31/2021 13:57:44 - INFO - __main__ - Step 135914: {'lr': 1.10939162570238e-05, 'samples': 26095488, 'steps': 135913, 'loss/train': 0.5250524878501892} 08/31/2021 13:57:44 - INFO - __main__ - Step 135915: {'lr': 1.1092353007277567e-05, 'samples': 26095680, 'steps': 135914, 'loss/train': 1.2191364765167236} 08/31/2021 13:57:44 - INFO - __main__ - Step 135916: {'lr': 1.1090789865179417e-05, 'samples': 26095872, 'steps': 135915, 'loss/train': 1.4701131582260132} 08/31/2021 13:57:46 - INFO - __main__ - Step 135917: {'lr': 1.1089226830730075e-05, 'samples': 26096064, 'steps': 135916, 'loss/train': 1.163965106010437} 08/31/2021 13:57:47 - INFO - __main__ - Step 135918: {'lr': 1.1087663903930262e-05, 'samples': 26096256, 'steps': 135917, 'loss/train': 0.7108240723609924} 08/31/2021 13:57:47 - INFO - __main__ - Step 135919: {'lr': 1.1086101084780642e-05, 'samples': 26096448, 'steps': 135918, 'loss/train': 0.9152004718780518} 08/31/2021 13:57:47 - INFO - __main__ - Step 135920: {'lr': 1.1084538373281939e-05, 'samples': 26096640, 'steps': 135919, 'loss/train': 0.6591600775718689} 08/31/2021 13:57:48 - INFO - __main__ - Step 135921: {'lr': 1.1082975769434845e-05, 'samples': 26096832, 'steps': 135920, 'loss/train': 1.2788822650909424} 08/31/2021 13:57:49 - INFO - __main__ - Step 135922: {'lr': 1.1081413273240109e-05, 'samples': 26097024, 'steps': 135921, 'loss/train': 1.4164378643035889} 08/31/2021 13:57:50 - INFO - __main__ - Step 135923: {'lr': 1.1079850884698373e-05, 'samples': 26097216, 'steps': 135922, 'loss/train': 0.8600391149520874} 08/31/2021 13:57:50 - INFO - __main__ - Step 135924: {'lr': 1.1078288603810383e-05, 'samples': 26097408, 'steps': 135923, 'loss/train': 0.8740405440330505} 08/31/2021 13:57:50 - INFO - __main__ - Step 135925: {'lr': 1.1076726430576833e-05, 'samples': 26097600, 'steps': 135924, 'loss/train': 0.028441233560442924} 08/31/2021 13:57:51 - INFO - __main__ - Step 135926: {'lr': 1.1075164364998418e-05, 'samples': 26097792, 'steps': 135925, 'loss/train': 0.2078772485256195} 08/31/2021 13:57:51 - INFO - __main__ - Step 135927: {'lr': 1.1073602407075861e-05, 'samples': 26097984, 'steps': 135926, 'loss/train': 1.2853691577911377} 08/31/2021 13:57:53 - INFO - __main__ - Step 135928: {'lr': 1.1072040556809826e-05, 'samples': 26098176, 'steps': 135927, 'loss/train': 0.20504407584667206} 08/31/2021 13:57:53 - INFO - __main__ - Step 135929: {'lr': 1.1070478814201035e-05, 'samples': 26098368, 'steps': 135928, 'loss/train': 1.125468373298645} 08/31/2021 13:57:53 - INFO - __main__ - Step 135930: {'lr': 1.106891717925021e-05, 'samples': 26098560, 'steps': 135929, 'loss/train': 0.8648994565010071} 08/31/2021 13:57:54 - INFO - __main__ - Step 135931: {'lr': 1.1067355651958072e-05, 'samples': 26098752, 'steps': 135930, 'loss/train': 1.337070107460022} 08/31/2021 13:57:54 - INFO - __main__ - Step 135932: {'lr': 1.1065794232325261e-05, 'samples': 26098944, 'steps': 135931, 'loss/train': 1.494028925895691} 08/31/2021 13:57:56 - INFO - __main__ - Step 135933: {'lr': 1.1064232920352523e-05, 'samples': 26099136, 'steps': 135932, 'loss/train': 1.2669198513031006} 08/31/2021 13:57:56 - INFO - __main__ - Step 135934: {'lr': 1.1062671716040556e-05, 'samples': 26099328, 'steps': 135933, 'loss/train': 0.40266063809394836} 08/31/2021 13:57:56 - INFO - __main__ - Step 135935: {'lr': 1.106111061939008e-05, 'samples': 26099520, 'steps': 135934, 'loss/train': 1.1411712169647217} 08/31/2021 13:57:57 - INFO - __main__ - Step 135936: {'lr': 1.1059549630401788e-05, 'samples': 26099712, 'steps': 135935, 'loss/train': 1.4567441940307617} 08/31/2021 13:57:57 - INFO - __main__ - Step 135937: {'lr': 1.1057988749076347e-05, 'samples': 26099904, 'steps': 135936, 'loss/train': 1.2228460311889648} 08/31/2021 13:57:59 - INFO - __main__ - Step 135938: {'lr': 1.1056427975414508e-05, 'samples': 26100096, 'steps': 135937, 'loss/train': 0.5227979421615601} 08/31/2021 13:57:59 - INFO - __main__ - Step 135939: {'lr': 1.1054867309416932e-05, 'samples': 26100288, 'steps': 135938, 'loss/train': 0.9493862986564636} 08/31/2021 13:57:59 - INFO - __main__ - Step 135940: {'lr': 1.1053306751084375e-05, 'samples': 26100480, 'steps': 135939, 'loss/train': 1.1231366395950317} 08/31/2021 13:58:00 - INFO - __main__ - Step 135941: {'lr': 1.105174630041747e-05, 'samples': 26100672, 'steps': 135940, 'loss/train': 1.1006968021392822} 08/31/2021 13:58:00 - INFO - __main__ - Step 135942: {'lr': 1.1050185957416997e-05, 'samples': 26100864, 'steps': 135941, 'loss/train': 0.9248676300048828} 08/31/2021 13:58:01 - INFO - __main__ - Step 135943: {'lr': 1.1048625722083622e-05, 'samples': 26101056, 'steps': 135942, 'loss/train': 1.5805636644363403} 08/31/2021 13:58:02 - INFO - __main__ - Step 135944: {'lr': 1.1047065594418038e-05, 'samples': 26101248, 'steps': 135943, 'loss/train': 1.121788740158081} 08/31/2021 13:58:02 - INFO - __main__ - Step 135945: {'lr': 1.104550557442094e-05, 'samples': 26101440, 'steps': 135944, 'loss/train': 1.7681691646575928} 08/31/2021 13:58:03 - INFO - __main__ - Step 135946: {'lr': 1.1043945662093074e-05, 'samples': 26101632, 'steps': 135945, 'loss/train': 0.9657021760940552} 08/31/2021 13:58:03 - INFO - __main__ - Step 135947: {'lr': 1.1042385857435139e-05, 'samples': 26101824, 'steps': 135946, 'loss/train': 1.5689846277236938} 08/31/2021 13:58:05 - INFO - __main__ - Step 135948: {'lr': 1.1040826160447797e-05, 'samples': 26102016, 'steps': 135947, 'loss/train': 1.255347728729248} 08/31/2021 13:58:06 - INFO - __main__ - Step 135949: {'lr': 1.1039266571131773e-05, 'samples': 26102208, 'steps': 135948, 'loss/train': 0.9237390160560608} 08/31/2021 13:58:06 - INFO - __main__ - Step 135950: {'lr': 1.1037707089487759e-05, 'samples': 26102400, 'steps': 135949, 'loss/train': 0.8855001330375671} 08/31/2021 13:58:06 - INFO - __main__ - Step 135951: {'lr': 1.1036147715516448e-05, 'samples': 26102592, 'steps': 135950, 'loss/train': 0.7468115091323853} 08/31/2021 13:58:07 - INFO - __main__ - Step 135952: {'lr': 1.103458844921859e-05, 'samples': 26102784, 'steps': 135951, 'loss/train': 1.1228997707366943} 08/31/2021 13:58:07 - INFO - __main__ - Step 135953: {'lr': 1.1033029290594855e-05, 'samples': 26102976, 'steps': 135952, 'loss/train': 0.8768501281738281} 08/31/2021 13:58:09 - INFO - __main__ - Step 135954: {'lr': 1.103147023964593e-05, 'samples': 26103168, 'steps': 135953, 'loss/train': 0.7661301493644714} 08/31/2021 13:58:09 - INFO - __main__ - Step 135955: {'lr': 1.1029911296372569e-05, 'samples': 26103360, 'steps': 135954, 'loss/train': 0.8830778002738953} 08/31/2021 13:58:09 - INFO - __main__ - Step 135956: {'lr': 1.102835246077541e-05, 'samples': 26103552, 'steps': 135955, 'loss/train': 1.0372276306152344} 08/31/2021 13:58:10 - INFO - __main__ - Step 135957: {'lr': 1.1026793732855229e-05, 'samples': 26103744, 'steps': 135956, 'loss/train': 0.8215441703796387} 08/31/2021 13:58:10 - INFO - __main__ - Step 135958: {'lr': 1.1025235112612691e-05, 'samples': 26103936, 'steps': 135957, 'loss/train': 1.6702284812927246} 08/31/2021 13:58:12 - INFO - __main__ - Step 135959: {'lr': 1.1023676600048465e-05, 'samples': 26104128, 'steps': 135958, 'loss/train': 1.1599918603897095} 08/31/2021 13:58:12 - INFO - __main__ - Step 135960: {'lr': 1.1022118195163272e-05, 'samples': 26104320, 'steps': 135959, 'loss/train': 1.0535295009613037} 08/31/2021 13:58:12 - INFO - __main__ - Step 135961: {'lr': 1.1020559897957832e-05, 'samples': 26104512, 'steps': 135960, 'loss/train': 0.7415099143981934} 08/31/2021 13:58:13 - INFO - __main__ - Step 135962: {'lr': 1.1019001708432841e-05, 'samples': 26104704, 'steps': 135961, 'loss/train': 1.1075879335403442} 08/31/2021 13:58:13 - INFO - __main__ - Step 135963: {'lr': 1.101744362658902e-05, 'samples': 26104896, 'steps': 135962, 'loss/train': 1.5462005138397217} 08/31/2021 13:58:15 - INFO - __main__ - Step 135964: {'lr': 1.1015885652427032e-05, 'samples': 26105088, 'steps': 135963, 'loss/train': 0.1771969348192215} 08/31/2021 13:58:15 - INFO - __main__ - Step 135965: {'lr': 1.1014327785947604e-05, 'samples': 26105280, 'steps': 135964, 'loss/train': 0.20835117995738983} 08/31/2021 13:58:16 - INFO - __main__ - Step 135966: {'lr': 1.1012770027151425e-05, 'samples': 26105472, 'steps': 135965, 'loss/train': 1.0148500204086304} 08/31/2021 13:58:16 - INFO - __main__ - Step 135967: {'lr': 1.1011212376039193e-05, 'samples': 26105664, 'steps': 135966, 'loss/train': 0.9892637729644775} 08/31/2021 13:58:16 - INFO - __main__ - Step 135968: {'lr': 1.1009654832611627e-05, 'samples': 26105856, 'steps': 135967, 'loss/train': 1.689041018486023} 08/31/2021 13:58:18 - INFO - __main__ - Step 135969: {'lr': 1.1008097396869448e-05, 'samples': 26106048, 'steps': 135968, 'loss/train': 1.3430795669555664} 08/31/2021 13:58:18 - INFO - __main__ - Step 135970: {'lr': 1.1006540068813297e-05, 'samples': 26106240, 'steps': 135969, 'loss/train': 1.1251952648162842} 08/31/2021 13:58:19 - INFO - __main__ - Step 135971: {'lr': 1.1004982848443951e-05, 'samples': 26106432, 'steps': 135970, 'loss/train': 0.5279806852340698} 08/31/2021 13:58:19 - INFO - __main__ - Step 135972: {'lr': 1.1003425735762073e-05, 'samples': 26106624, 'steps': 135971, 'loss/train': 0.8334513902664185} 08/31/2021 13:58:19 - INFO - __main__ - Step 135973: {'lr': 1.1001868730768334e-05, 'samples': 26106816, 'steps': 135972, 'loss/train': 1.0029033422470093} 08/31/2021 13:58:20 - INFO - __main__ - Step 135974: {'lr': 1.1000311833463478e-05, 'samples': 26107008, 'steps': 135973, 'loss/train': 0.037579286843538284} 08/31/2021 13:58:21 - INFO - __main__ - Step 135975: {'lr': 1.0998755043848174e-05, 'samples': 26107200, 'steps': 135974, 'loss/train': 1.19265878200531} 08/31/2021 13:58:22 - INFO - __main__ - Step 135976: {'lr': 1.0997198361923172e-05, 'samples': 26107392, 'steps': 135975, 'loss/train': 1.1847193241119385} 08/31/2021 13:58:22 - INFO - __main__ - Step 135977: {'lr': 1.0995641787689137e-05, 'samples': 26107584, 'steps': 135976, 'loss/train': 0.6599596738815308} 08/31/2021 13:58:22 - INFO - __main__ - Step 135978: {'lr': 1.0994085321146763e-05, 'samples': 26107776, 'steps': 135977, 'loss/train': 1.2988793849945068} 08/31/2021 13:58:23 - INFO - __main__ - Step 135979: {'lr': 1.0992528962296772e-05, 'samples': 26107968, 'steps': 135978, 'loss/train': 1.1917006969451904} 08/31/2021 13:58:24 - INFO - __main__ - Step 135980: {'lr': 1.0990972711139857e-05, 'samples': 26108160, 'steps': 135979, 'loss/train': 1.01912522315979} 08/31/2021 13:58:25 - INFO - __main__ - Step 135981: {'lr': 1.0989416567676713e-05, 'samples': 26108352, 'steps': 135980, 'loss/train': 0.6820197105407715} 08/31/2021 13:58:25 - INFO - __main__ - Step 135982: {'lr': 1.0987860531908062e-05, 'samples': 26108544, 'steps': 135981, 'loss/train': 1.0818607807159424} 08/31/2021 13:58:25 - INFO - __main__ - Step 135983: {'lr': 1.0986304603834595e-05, 'samples': 26108736, 'steps': 135982, 'loss/train': 0.5842107534408569} 08/31/2021 13:58:26 - INFO - __main__ - Step 135984: {'lr': 1.098474878345701e-05, 'samples': 26108928, 'steps': 135983, 'loss/train': 1.2170121669769287} 08/31/2021 13:58:26 - INFO - __main__ - Step 135985: {'lr': 1.0983193070776055e-05, 'samples': 26109120, 'steps': 135984, 'loss/train': 1.0872039794921875} 08/31/2021 13:58:28 - INFO - __main__ - Step 135986: {'lr': 1.098163746579231e-05, 'samples': 26109312, 'steps': 135985, 'loss/train': 0.37921640276908875} 08/31/2021 13:58:28 - INFO - __main__ - Step 135987: {'lr': 1.0980081968506584e-05, 'samples': 26109504, 'steps': 135986, 'loss/train': 1.1492871046066284} 08/31/2021 13:58:29 - INFO - __main__ - Step 135988: {'lr': 1.097852657891954e-05, 'samples': 26109696, 'steps': 135987, 'loss/train': 1.6640806198120117} 08/31/2021 13:58:29 - INFO - __main__ - Step 135989: {'lr': 1.0976971297031873e-05, 'samples': 26109888, 'steps': 135988, 'loss/train': 0.799510657787323} 08/31/2021 13:58:29 - INFO - __main__ - Step 135990: {'lr': 1.0975416122844306e-05, 'samples': 26110080, 'steps': 135989, 'loss/train': 1.3268004655838013} 08/31/2021 13:58:31 - INFO - __main__ - Step 135991: {'lr': 1.0973861056357532e-05, 'samples': 26110272, 'steps': 135990, 'loss/train': 1.3956471681594849} 08/31/2021 13:58:31 - INFO - __main__ - Step 135992: {'lr': 1.0972306097572244e-05, 'samples': 26110464, 'steps': 135991, 'loss/train': 0.3461366295814514} 08/31/2021 13:58:32 - INFO - __main__ - Step 135993: {'lr': 1.0970751246489135e-05, 'samples': 26110656, 'steps': 135992, 'loss/train': 1.4984818696975708} 08/31/2021 13:58:32 - INFO - __main__ - Step 135994: {'lr': 1.096919650310893e-05, 'samples': 26110848, 'steps': 135993, 'loss/train': 1.6792842149734497} 08/31/2021 13:58:32 - INFO - __main__ - Step 135995: {'lr': 1.0967641867432322e-05, 'samples': 26111040, 'steps': 135994, 'loss/train': 1.3320379257202148} 08/31/2021 13:58:34 - INFO - __main__ - Step 135996: {'lr': 1.0966087339460001e-05, 'samples': 26111232, 'steps': 135995, 'loss/train': 0.027634743601083755} 08/31/2021 13:58:34 - INFO - __main__ - Step 135997: {'lr': 1.0964532919192666e-05, 'samples': 26111424, 'steps': 135996, 'loss/train': 0.8122990727424622} 08/31/2021 13:58:35 - INFO - __main__ - Step 135998: {'lr': 1.0962978606631007e-05, 'samples': 26111616, 'steps': 135997, 'loss/train': 1.2365707159042358} 08/31/2021 13:58:35 - INFO - __main__ - Step 135999: {'lr': 1.0961424401775805e-05, 'samples': 26111808, 'steps': 135998, 'loss/train': 1.1458951234817505} 08/31/2021 13:58:36 - INFO - __main__ - Step 136000: {'lr': 1.095987030462764e-05, 'samples': 26112000, 'steps': 135999, 'loss/train': 0.2554669976234436} 08/31/2021 13:58:37 - INFO - __main__ - Step 136001: {'lr': 1.0958316315187289e-05, 'samples': 26112192, 'steps': 136000, 'loss/train': 0.9004533290863037} 08/31/2021 13:58:37 - INFO - __main__ - Step 136002: {'lr': 1.095676243345542e-05, 'samples': 26112384, 'steps': 136001, 'loss/train': 0.9548758268356323} 08/31/2021 13:58:38 - INFO - __main__ - Step 136003: {'lr': 1.0955208659432752e-05, 'samples': 26112576, 'steps': 136002, 'loss/train': 0.48813122510910034} 08/31/2021 13:58:38 - INFO - __main__ - Step 136004: {'lr': 1.0953654993119982e-05, 'samples': 26112768, 'steps': 136003, 'loss/train': 1.1106834411621094} 08/31/2021 13:58:38 - INFO - __main__ - Step 136005: {'lr': 1.0952101434517803e-05, 'samples': 26112960, 'steps': 136004, 'loss/train': 1.540793538093567} 08/31/2021 13:58:40 - INFO - __main__ - Step 136006: {'lr': 1.0950547983626907e-05, 'samples': 26113152, 'steps': 136005, 'loss/train': 0.5944343209266663} 08/31/2021 13:58:41 - INFO - __main__ - Step 136007: {'lr': 1.0948994640448018e-05, 'samples': 26113344, 'steps': 136006, 'loss/train': 1.368645191192627} 08/31/2021 13:58:41 - INFO - __main__ - Step 136008: {'lr': 1.09474414049818e-05, 'samples': 26113536, 'steps': 136007, 'loss/train': 1.0573604106903076} 08/31/2021 13:58:42 - INFO - __main__ - Step 136009: {'lr': 1.0945888277229005e-05, 'samples': 26113728, 'steps': 136008, 'loss/train': 1.1405364274978638} 08/31/2021 13:58:42 - INFO - __main__ - Step 136010: {'lr': 1.0944335257190296e-05, 'samples': 26113920, 'steps': 136009, 'loss/train': 1.0186824798583984} 08/31/2021 13:58:42 - INFO - __main__ - Step 136011: {'lr': 1.094278234486637e-05, 'samples': 26114112, 'steps': 136010, 'loss/train': 1.6454168558120728} 08/31/2021 13:58:44 - INFO - __main__ - Step 136012: {'lr': 1.0941229540257974e-05, 'samples': 26114304, 'steps': 136011, 'loss/train': 1.06749427318573} 08/31/2021 13:58:45 - INFO - __main__ - Step 136013: {'lr': 1.0939676843365748e-05, 'samples': 26114496, 'steps': 136012, 'loss/train': 1.0283855199813843} 08/31/2021 13:58:45 - INFO - __main__ - Step 136014: {'lr': 1.0938124254190412e-05, 'samples': 26114688, 'steps': 136013, 'loss/train': 0.49328145384788513} 08/31/2021 13:58:45 - INFO - __main__ - Step 136015: {'lr': 1.0936571772732662e-05, 'samples': 26114880, 'steps': 136014, 'loss/train': 0.41394996643066406} 08/31/2021 13:58:46 - INFO - __main__ - Step 136016: {'lr': 1.0935019398993218e-05, 'samples': 26115072, 'steps': 136015, 'loss/train': 0.2511070668697357} 08/31/2021 13:58:47 - INFO - __main__ - Step 136017: {'lr': 1.0933467132972747e-05, 'samples': 26115264, 'steps': 136016, 'loss/train': 0.9903653264045715} 08/31/2021 13:58:48 - INFO - __main__ - Step 136018: {'lr': 1.0931914974671969e-05, 'samples': 26115456, 'steps': 136017, 'loss/train': 1.0217602252960205} 08/31/2021 13:58:48 - INFO - __main__ - Step 136019: {'lr': 1.093036292409158e-05, 'samples': 26115648, 'steps': 136018, 'loss/train': 1.845375657081604} 08/31/2021 13:58:48 - INFO - __main__ - Step 136020: {'lr': 1.09288109812323e-05, 'samples': 26115840, 'steps': 136019, 'loss/train': 1.729598045349121} 08/31/2021 13:58:49 - INFO - __main__ - Step 136021: {'lr': 1.0927259146094798e-05, 'samples': 26116032, 'steps': 136020, 'loss/train': 1.834755539894104} 08/31/2021 13:58:50 - INFO - __main__ - Step 136022: {'lr': 1.0925707418679765e-05, 'samples': 26116224, 'steps': 136021, 'loss/train': 0.8583686351776123} 08/31/2021 13:58:51 - INFO - __main__ - Step 136023: {'lr': 1.092415579898795e-05, 'samples': 26116416, 'steps': 136022, 'loss/train': 0.8589347004890442} 08/31/2021 13:58:51 - INFO - __main__ - Step 136024: {'lr': 1.0922604287019994e-05, 'samples': 26116608, 'steps': 136023, 'loss/train': 0.674457311630249} 08/31/2021 13:58:51 - INFO - __main__ - Step 136025: {'lr': 1.0921052882776645e-05, 'samples': 26116800, 'steps': 136024, 'loss/train': 1.0783782005310059} 08/31/2021 13:58:52 - INFO - __main__ - Step 136026: {'lr': 1.0919501586258595e-05, 'samples': 26116992, 'steps': 136025, 'loss/train': 1.1607871055603027} 08/31/2021 13:58:53 - INFO - __main__ - Step 136027: {'lr': 1.0917950397466513e-05, 'samples': 26117184, 'steps': 136026, 'loss/train': 1.3409615755081177} 08/31/2021 13:58:54 - INFO - __main__ - Step 136028: {'lr': 1.0916399316401094e-05, 'samples': 26117376, 'steps': 136027, 'loss/train': 0.45243772864341736} 08/31/2021 13:58:54 - INFO - __main__ - Step 136029: {'lr': 1.0914848343063083e-05, 'samples': 26117568, 'steps': 136028, 'loss/train': 1.2162843942642212} 08/31/2021 13:58:54 - INFO - __main__ - Step 136030: {'lr': 1.091329747745312e-05, 'samples': 26117760, 'steps': 136029, 'loss/train': 0.9162404537200928} 08/31/2021 13:58:55 - INFO - __main__ - Step 136031: {'lr': 1.0911746719571958e-05, 'samples': 26117952, 'steps': 136030, 'loss/train': 0.6473115682601929} 08/31/2021 13:58:56 - INFO - __main__ - Step 136032: {'lr': 1.0910196069420286e-05, 'samples': 26118144, 'steps': 136031, 'loss/train': 0.8714923858642578} 08/31/2021 13:58:57 - INFO - __main__ - Step 136033: {'lr': 1.0908645526998745e-05, 'samples': 26118336, 'steps': 136032, 'loss/train': 1.0119775533676147} 08/31/2021 13:58:57 - INFO - __main__ - Step 136034: {'lr': 1.0907095092308111e-05, 'samples': 26118528, 'steps': 136033, 'loss/train': 1.1761239767074585} 08/31/2021 13:58:58 - INFO - __main__ - Step 136035: {'lr': 1.0905544765349052e-05, 'samples': 26118720, 'steps': 136034, 'loss/train': 0.8972700834274292} 08/31/2021 13:58:58 - INFO - __main__ - Step 136036: {'lr': 1.090399454612226e-05, 'samples': 26118912, 'steps': 136035, 'loss/train': 1.187947154045105} 08/31/2021 13:58:59 - INFO - __main__ - Step 136037: {'lr': 1.0902444434628427e-05, 'samples': 26119104, 'steps': 136036, 'loss/train': 1.6167421340942383} 08/31/2021 13:59:00 - INFO - __main__ - Step 136038: {'lr': 1.090089443086828e-05, 'samples': 26119296, 'steps': 136037, 'loss/train': 1.3063743114471436} 08/31/2021 13:59:00 - INFO - __main__ - Step 136039: {'lr': 1.0899344534842537e-05, 'samples': 26119488, 'steps': 136038, 'loss/train': 0.6195016503334045} 08/31/2021 13:59:00 - INFO - __main__ - Step 136040: {'lr': 1.0897794746551808e-05, 'samples': 26119680, 'steps': 136039, 'loss/train': 0.9695353507995605} 08/31/2021 13:59:01 - INFO - __main__ - Step 136041: {'lr': 1.0896245065996845e-05, 'samples': 26119872, 'steps': 136040, 'loss/train': 1.1734752655029297} 08/31/2021 13:59:02 - INFO - __main__ - Step 136042: {'lr': 1.089469549317834e-05, 'samples': 26120064, 'steps': 136041, 'loss/train': 2.0299737453460693} 08/31/2021 13:59:03 - INFO - __main__ - Step 136043: {'lr': 1.0893146028097018e-05, 'samples': 26120256, 'steps': 136042, 'loss/train': 1.2664079666137695} 08/31/2021 13:59:03 - INFO - __main__ - Step 136044: {'lr': 1.089159667075354e-05, 'samples': 26120448, 'steps': 136043, 'loss/train': 0.29546627402305603} 08/31/2021 13:59:04 - INFO - __main__ - Step 136045: {'lr': 1.089004742114863e-05, 'samples': 26120640, 'steps': 136044, 'loss/train': 5.616323947906494} 08/31/2021 13:59:04 - INFO - __main__ - Step 136046: {'lr': 1.0888498279282955e-05, 'samples': 26120832, 'steps': 136045, 'loss/train': 1.855926752090454} 08/31/2021 13:59:04 - INFO - __main__ - Step 136047: {'lr': 1.0886949245157262e-05, 'samples': 26121024, 'steps': 136046, 'loss/train': 0.03353874757885933} 08/31/2021 13:59:06 - INFO - __main__ - Step 136048: {'lr': 1.0885400318772192e-05, 'samples': 26121216, 'steps': 136047, 'loss/train': 1.3571175336837769} 08/31/2021 13:59:06 - INFO - __main__ - Step 136049: {'lr': 1.0883851500128495e-05, 'samples': 26121408, 'steps': 136048, 'loss/train': 0.8956878185272217} 08/31/2021 13:59:07 - INFO - __main__ - Step 136050: {'lr': 1.0882302789226833e-05, 'samples': 26121600, 'steps': 136049, 'loss/train': 1.1728618144989014} 08/31/2021 13:59:07 - INFO - __main__ - Step 136051: {'lr': 1.0880754186067904e-05, 'samples': 26121792, 'steps': 136050, 'loss/train': 0.48237597942352295} 08/31/2021 13:59:07 - INFO - __main__ - Step 136052: {'lr': 1.0879205690652428e-05, 'samples': 26121984, 'steps': 136051, 'loss/train': 0.44101449847221375} 08/31/2021 13:59:10 - INFO - __main__ - Step 136053: {'lr': 1.0877657302981125e-05, 'samples': 26122176, 'steps': 136052, 'loss/train': 1.5830440521240234} 08/31/2021 13:59:10 - INFO - __main__ - Step 136054: {'lr': 1.087610902305461e-05, 'samples': 26122368, 'steps': 136053, 'loss/train': 1.1036877632141113} 08/31/2021 13:59:11 - INFO - __main__ - Step 136055: {'lr': 1.0874560850873655e-05, 'samples': 26122560, 'steps': 136054, 'loss/train': 0.015302757732570171} 08/31/2021 13:59:11 - INFO - __main__ - Step 136056: {'lr': 1.087301278643893e-05, 'samples': 26122752, 'steps': 136055, 'loss/train': 0.015153826214373112} 08/31/2021 13:59:11 - INFO - __main__ - Step 136057: {'lr': 1.0871464829751126e-05, 'samples': 26122944, 'steps': 136056, 'loss/train': 1.279486894607544} 08/31/2021 13:59:12 - INFO - __main__ - Step 136058: {'lr': 1.086991698081094e-05, 'samples': 26123136, 'steps': 136057, 'loss/train': 0.9279119372367859} 08/31/2021 13:59:12 - INFO - __main__ - Step 136059: {'lr': 1.086836923961912e-05, 'samples': 26123328, 'steps': 136058, 'loss/train': 1.465741515159607} 08/31/2021 13:59:12 - INFO - __main__ - Step 136060: {'lr': 1.0866821606176274e-05, 'samples': 26123520, 'steps': 136059, 'loss/train': 1.5707703828811646} 08/31/2021 13:59:13 - INFO - __main__ - Step 136061: {'lr': 1.0865274080483185e-05, 'samples': 26123712, 'steps': 136060, 'loss/train': 1.614582896232605} 08/31/2021 13:59:15 - INFO - __main__ - Step 136062: {'lr': 1.0863726662540484e-05, 'samples': 26123904, 'steps': 136061, 'loss/train': 1.4874809980392456} 08/31/2021 13:59:15 - INFO - __main__ - Step 136063: {'lr': 1.0862179352348928e-05, 'samples': 26124096, 'steps': 136062, 'loss/train': 1.4691352844238281} 08/31/2021 13:59:16 - INFO - __main__ - Step 136064: {'lr': 1.086063214990915e-05, 'samples': 26124288, 'steps': 136063, 'loss/train': 0.5435678958892822} 08/31/2021 13:59:16 - INFO - __main__ - Step 136065: {'lr': 1.0859085055221901e-05, 'samples': 26124480, 'steps': 136064, 'loss/train': 1.0874154567718506} 08/31/2021 13:59:16 - INFO - __main__ - Step 136066: {'lr': 1.0857538068287903e-05, 'samples': 26124672, 'steps': 136065, 'loss/train': 1.7240532636642456} 08/31/2021 13:59:18 - INFO - __main__ - Step 136067: {'lr': 1.0855991189107767e-05, 'samples': 26124864, 'steps': 136066, 'loss/train': 0.924821138381958} 08/31/2021 13:59:18 - INFO - __main__ - Step 136068: {'lr': 1.0854444417682213e-05, 'samples': 26125056, 'steps': 136067, 'loss/train': 1.256434440612793} 08/31/2021 13:59:19 - INFO - __main__ - Step 136069: {'lr': 1.0852897754011964e-05, 'samples': 26125248, 'steps': 136068, 'loss/train': 1.023539423942566} 08/31/2021 13:59:19 - INFO - __main__ - Step 136070: {'lr': 1.0851351198097715e-05, 'samples': 26125440, 'steps': 136069, 'loss/train': 1.3556795120239258} 08/31/2021 13:59:19 - INFO - __main__ - Step 136071: {'lr': 1.0849804749940156e-05, 'samples': 26125632, 'steps': 136070, 'loss/train': 1.053602933883667} 08/31/2021 13:59:21 - INFO - __main__ - Step 136072: {'lr': 1.0848258409539985e-05, 'samples': 26125824, 'steps': 136071, 'loss/train': 0.9510075449943542} 08/31/2021 13:59:21 - INFO - __main__ - Step 136073: {'lr': 1.0846712176897893e-05, 'samples': 26126016, 'steps': 136072, 'loss/train': 0.8888242840766907} 08/31/2021 13:59:22 - INFO - __main__ - Step 136074: {'lr': 1.0845166052014604e-05, 'samples': 26126208, 'steps': 136073, 'loss/train': 0.8909092545509338} 08/31/2021 13:59:22 - INFO - __main__ - Step 136075: {'lr': 1.0843620034890756e-05, 'samples': 26126400, 'steps': 136074, 'loss/train': 1.2717862129211426} 08/31/2021 13:59:22 - INFO - __main__ - Step 136076: {'lr': 1.0842074125527096e-05, 'samples': 26126592, 'steps': 136075, 'loss/train': 1.1939587593078613} 08/31/2021 13:59:24 - INFO - __main__ - Step 136077: {'lr': 1.084052832392432e-05, 'samples': 26126784, 'steps': 136076, 'loss/train': 1.107470989227295} 08/31/2021 13:59:24 - INFO - __main__ - Step 136078: {'lr': 1.0838982630083122e-05, 'samples': 26126976, 'steps': 136077, 'loss/train': 0.9206457138061523} 08/31/2021 13:59:25 - INFO - __main__ - Step 136079: {'lr': 1.0837437044004195e-05, 'samples': 26127168, 'steps': 136078, 'loss/train': 0.7986466884613037} 08/31/2021 13:59:25 - INFO - __main__ - Step 136080: {'lr': 1.0835891565688205e-05, 'samples': 26127360, 'steps': 136079, 'loss/train': 0.7933855056762695} 08/31/2021 13:59:25 - INFO - __main__ - Step 136081: {'lr': 1.0834346195135874e-05, 'samples': 26127552, 'steps': 136080, 'loss/train': 0.5499264597892761} 08/31/2021 13:59:27 - INFO - __main__ - Step 136082: {'lr': 1.083280093234787e-05, 'samples': 26127744, 'steps': 136081, 'loss/train': 0.662293016910553} 08/31/2021 13:59:27 - INFO - __main__ - Step 136083: {'lr': 1.0831255777324939e-05, 'samples': 26127936, 'steps': 136082, 'loss/train': 1.3690972328186035} 08/31/2021 13:59:28 - INFO - __main__ - Step 136084: {'lr': 1.082971073006775e-05, 'samples': 26128128, 'steps': 136083, 'loss/train': 1.1352943181991577} 08/31/2021 13:59:28 - INFO - __main__ - Step 136085: {'lr': 1.0828165790577022e-05, 'samples': 26128320, 'steps': 136084, 'loss/train': 1.3927905559539795} 08/31/2021 13:59:28 - INFO - __main__ - Step 136086: {'lr': 1.0826620958853423e-05, 'samples': 26128512, 'steps': 136085, 'loss/train': 1.2530319690704346} 08/31/2021 13:59:30 - INFO - __main__ - Step 136087: {'lr': 1.0825076234897646e-05, 'samples': 26128704, 'steps': 136086, 'loss/train': 0.769302487373352} 08/31/2021 13:59:30 - INFO - __main__ - Step 136088: {'lr': 1.0823531618710385e-05, 'samples': 26128896, 'steps': 136087, 'loss/train': 0.39347976446151733} 08/31/2021 13:59:31 - INFO - __main__ - Step 136089: {'lr': 1.0821987110292364e-05, 'samples': 26129088, 'steps': 136088, 'loss/train': 0.7649248838424683} 08/31/2021 13:59:31 - INFO - __main__ - Step 136090: {'lr': 1.0820442709644273e-05, 'samples': 26129280, 'steps': 136089, 'loss/train': 1.0744357109069824} 08/31/2021 13:59:31 - INFO - __main__ - Step 136091: {'lr': 1.0818898416766809e-05, 'samples': 26129472, 'steps': 136090, 'loss/train': 0.9349331259727478} 08/31/2021 13:59:32 - INFO - __main__ - Step 136092: {'lr': 1.0817354231660636e-05, 'samples': 26129664, 'steps': 136091, 'loss/train': 0.6868820786476135} 08/31/2021 13:59:33 - INFO - __main__ - Step 136093: {'lr': 1.0815810154326506e-05, 'samples': 26129856, 'steps': 136092, 'loss/train': 0.11429249495267868} 08/31/2021 13:59:34 - INFO - __main__ - Step 136094: {'lr': 1.0814266184765053e-05, 'samples': 26130048, 'steps': 136093, 'loss/train': 0.9200506806373596} 08/31/2021 13:59:34 - INFO - __main__ - Step 136095: {'lr': 1.0812722322977003e-05, 'samples': 26130240, 'steps': 136094, 'loss/train': 0.5855004787445068} 08/31/2021 13:59:34 - INFO - __main__ - Step 136096: {'lr': 1.0811178568963077e-05, 'samples': 26130432, 'steps': 136095, 'loss/train': 1.266979694366455} 08/31/2021 13:59:35 - INFO - __main__ - Step 136097: {'lr': 1.080963492272391e-05, 'samples': 26130624, 'steps': 136096, 'loss/train': 0.47423532605171204} 08/31/2021 13:59:36 - INFO - __main__ - Step 136098: {'lr': 1.0808091384260226e-05, 'samples': 26130816, 'steps': 136097, 'loss/train': 0.9967456459999084} 08/31/2021 13:59:37 - INFO - __main__ - Step 136099: {'lr': 1.0806547953572749e-05, 'samples': 26131008, 'steps': 136098, 'loss/train': 1.1358903646469116} 08/31/2021 13:59:37 - INFO - __main__ - Step 136100: {'lr': 1.080500463066214e-05, 'samples': 26131200, 'steps': 136099, 'loss/train': 1.2103246450424194} 08/31/2021 13:59:37 - INFO - __main__ - Step 136101: {'lr': 1.0803461415529098e-05, 'samples': 26131392, 'steps': 136100, 'loss/train': 0.25759169459342957} 08/31/2021 13:59:38 - INFO - __main__ - Step 136102: {'lr': 1.0801918308174313e-05, 'samples': 26131584, 'steps': 136101, 'loss/train': 1.6870293617248535} 08/31/2021 13:59:39 - INFO - __main__ - Step 136103: {'lr': 1.080037530859851e-05, 'samples': 26131776, 'steps': 136102, 'loss/train': 0.8874404430389404} 08/31/2021 13:59:40 - INFO - __main__ - Step 136104: {'lr': 1.0798832416802379e-05, 'samples': 26131968, 'steps': 136103, 'loss/train': 0.6503305435180664} 08/31/2021 13:59:40 - INFO - __main__ - Step 136105: {'lr': 1.0797289632786589e-05, 'samples': 26132160, 'steps': 136104, 'loss/train': 0.5016418695449829} 08/31/2021 13:59:40 - INFO - __main__ - Step 136106: {'lr': 1.0795746956551888e-05, 'samples': 26132352, 'steps': 136105, 'loss/train': 0.9569925665855408} 08/31/2021 13:59:41 - INFO - __main__ - Step 136107: {'lr': 1.0794204388098889e-05, 'samples': 26132544, 'steps': 136106, 'loss/train': 0.2920747697353363} 08/31/2021 13:59:42 - INFO - __main__ - Step 136108: {'lr': 1.0792661927428338e-05, 'samples': 26132736, 'steps': 136107, 'loss/train': 1.6201319694519043} 08/31/2021 13:59:43 - INFO - __main__ - Step 136109: {'lr': 1.0791119574540903e-05, 'samples': 26132928, 'steps': 136108, 'loss/train': 1.0742288827896118} 08/31/2021 13:59:43 - INFO - __main__ - Step 136110: {'lr': 1.0789577329437334e-05, 'samples': 26133120, 'steps': 136109, 'loss/train': 1.087778091430664} 08/31/2021 13:59:43 - INFO - __main__ - Step 136111: {'lr': 1.0788035192118267e-05, 'samples': 26133312, 'steps': 136110, 'loss/train': 1.433647871017456} 08/31/2021 13:59:44 - INFO - __main__ - Step 136112: {'lr': 1.0786493162584427e-05, 'samples': 26133504, 'steps': 136111, 'loss/train': 1.6469995975494385} 08/31/2021 13:59:46 - INFO - __main__ - Step 136113: {'lr': 1.0784951240836505e-05, 'samples': 26133696, 'steps': 136112, 'loss/train': 1.0042829513549805} 08/31/2021 13:59:46 - INFO - __main__ - Step 136114: {'lr': 1.0783409426875168e-05, 'samples': 26133888, 'steps': 136113, 'loss/train': 0.9674713015556335} 08/31/2021 13:59:47 - INFO - __main__ - Step 136115: {'lr': 1.0781867720701167e-05, 'samples': 26134080, 'steps': 136114, 'loss/train': 0.8595899343490601} 08/31/2021 13:59:47 - INFO - __main__ - Step 136116: {'lr': 1.0780326122315164e-05, 'samples': 26134272, 'steps': 136115, 'loss/train': 1.1924110651016235} 08/31/2021 13:59:47 - INFO - __main__ - Step 136117: {'lr': 1.077878463171783e-05, 'samples': 26134464, 'steps': 136116, 'loss/train': 1.3803621530532837} 08/31/2021 13:59:50 - INFO - __main__ - Step 136118: {'lr': 1.0777243248909913e-05, 'samples': 26134656, 'steps': 136117, 'loss/train': 0.6447011828422546} 08/31/2021 13:59:50 - INFO - __main__ - Step 136119: {'lr': 1.0775701973892049e-05, 'samples': 26134848, 'steps': 136118, 'loss/train': 1.0011820793151855} 08/31/2021 13:59:50 - INFO - __main__ - Step 136120: {'lr': 1.0774160806665017e-05, 'samples': 26135040, 'steps': 136119, 'loss/train': 1.281524658203125} 08/31/2021 13:59:51 - INFO - __main__ - Step 136121: {'lr': 1.07726197472294e-05, 'samples': 26135232, 'steps': 136120, 'loss/train': 1.3149343729019165} 08/31/2021 13:59:51 - INFO - __main__ - Step 136122: {'lr': 1.0771078795585976e-05, 'samples': 26135424, 'steps': 136121, 'loss/train': 0.6664701104164124} 08/31/2021 13:59:51 - INFO - __main__ - Step 136123: {'lr': 1.0769537951735409e-05, 'samples': 26135616, 'steps': 136122, 'loss/train': 0.9356353878974915} 08/31/2021 13:59:52 - INFO - __main__ - Step 136124: {'lr': 1.0767997215678393e-05, 'samples': 26135808, 'steps': 136123, 'loss/train': 0.6666460037231445} 08/31/2021 13:59:53 - INFO - __main__ - Step 136125: {'lr': 1.0766456587415623e-05, 'samples': 26136000, 'steps': 136124, 'loss/train': 0.8566121459007263} 08/31/2021 13:59:54 - INFO - __main__ - Step 136126: {'lr': 1.0764916066947795e-05, 'samples': 26136192, 'steps': 136125, 'loss/train': 1.1965376138687134} 08/31/2021 13:59:54 - INFO - __main__ - Step 136127: {'lr': 1.0763375654275598e-05, 'samples': 26136384, 'steps': 136126, 'loss/train': 1.0481491088867188} 08/31/2021 13:59:54 - INFO - __main__ - Step 136128: {'lr': 1.0761835349399729e-05, 'samples': 26136576, 'steps': 136127, 'loss/train': 1.294554352760315} 08/31/2021 13:59:55 - INFO - __main__ - Step 136129: {'lr': 1.0760295152320909e-05, 'samples': 26136768, 'steps': 136128, 'loss/train': 0.648267924785614} 08/31/2021 13:59:57 - INFO - __main__ - Step 136130: {'lr': 1.0758755063039776e-05, 'samples': 26136960, 'steps': 136129, 'loss/train': 1.0869938135147095} 08/31/2021 13:59:57 - INFO - __main__ - Step 136131: {'lr': 1.0757215081557081e-05, 'samples': 26137152, 'steps': 136130, 'loss/train': 0.18948544561862946} 08/31/2021 13:59:57 - INFO - __main__ - Step 136132: {'lr': 1.0755675207873489e-05, 'samples': 26137344, 'steps': 136131, 'loss/train': 1.065220594406128} 08/31/2021 13:59:58 - INFO - __main__ - Step 136133: {'lr': 1.075413544198972e-05, 'samples': 26137536, 'steps': 136132, 'loss/train': 0.7737104296684265} 08/31/2021 13:59:58 - INFO - __main__ - Step 136134: {'lr': 1.0752595783906444e-05, 'samples': 26137728, 'steps': 136133, 'loss/train': 0.015074378810822964} 08/31/2021 13:59:59 - INFO - __main__ - Step 136135: {'lr': 1.0751056233624324e-05, 'samples': 26137920, 'steps': 136134, 'loss/train': 0.46408480405807495} 08/31/2021 14:00:00 - INFO - __main__ - Step 136136: {'lr': 1.0749516791144082e-05, 'samples': 26138112, 'steps': 136135, 'loss/train': 0.04373205825686455} 08/31/2021 14:00:01 - INFO - __main__ - Step 136137: {'lr': 1.074797745646644e-05, 'samples': 26138304, 'steps': 136136, 'loss/train': 0.5185837745666504} 08/31/2021 14:00:01 - INFO - __main__ - Step 136138: {'lr': 1.0746438229592065e-05, 'samples': 26138496, 'steps': 136137, 'loss/train': 0.5292536616325378} 08/31/2021 14:00:01 - INFO - __main__ - Step 136139: {'lr': 1.074489911052165e-05, 'samples': 26138688, 'steps': 136138, 'loss/train': 0.8551109433174133} 08/31/2021 14:00:02 - INFO - __main__ - Step 136140: {'lr': 1.0743360099255888e-05, 'samples': 26138880, 'steps': 136139, 'loss/train': 0.11937665194272995} 08/31/2021 14:00:03 - INFO - __main__ - Step 136141: {'lr': 1.0741821195795476e-05, 'samples': 26139072, 'steps': 136140, 'loss/train': 0.19565075635910034} 08/31/2021 14:00:04 - INFO - __main__ - Step 136142: {'lr': 1.0740282400141106e-05, 'samples': 26139264, 'steps': 136141, 'loss/train': 1.1497303247451782} 08/31/2021 14:00:04 - INFO - __main__ - Step 136143: {'lr': 1.073874371229347e-05, 'samples': 26139456, 'steps': 136142, 'loss/train': 1.4225250482559204} 08/31/2021 14:00:04 - INFO - __main__ - Step 136144: {'lr': 1.0737205132253264e-05, 'samples': 26139648, 'steps': 136143, 'loss/train': 0.9216533899307251} 08/31/2021 14:00:05 - INFO - __main__ - Step 136145: {'lr': 1.0735666660021181e-05, 'samples': 26139840, 'steps': 136144, 'loss/train': 0.16981159150600433} 08/31/2021 14:00:06 - INFO - __main__ - Step 136146: {'lr': 1.0734128295597916e-05, 'samples': 26140032, 'steps': 136145, 'loss/train': 1.0464295148849487} 08/31/2021 14:00:07 - INFO - __main__ - Step 136147: {'lr': 1.073259003898419e-05, 'samples': 26140224, 'steps': 136146, 'loss/train': 1.1929446458816528} 08/31/2021 14:00:07 - INFO - __main__ - Step 136148: {'lr': 1.0731051890180644e-05, 'samples': 26140416, 'steps': 136147, 'loss/train': 1.3361893892288208} 08/31/2021 14:00:08 - INFO - __main__ - Step 136149: {'lr': 1.0729513849187994e-05, 'samples': 26140608, 'steps': 136148, 'loss/train': 1.745348334312439} 08/31/2021 14:00:08 - INFO - __main__ - Step 136150: {'lr': 1.0727975916006938e-05, 'samples': 26140800, 'steps': 136149, 'loss/train': 0.7840498685836792} 08/31/2021 14:00:09 - INFO - __main__ - Step 136151: {'lr': 1.0726438090638141e-05, 'samples': 26140992, 'steps': 136150, 'loss/train': 0.3137476146221161} 08/31/2021 14:00:10 - INFO - __main__ - Step 136152: {'lr': 1.0724900373082324e-05, 'samples': 26141184, 'steps': 136151, 'loss/train': 1.5961432456970215} 08/31/2021 14:00:10 - INFO - __main__ - Step 136153: {'lr': 1.0723362763340184e-05, 'samples': 26141376, 'steps': 136152, 'loss/train': 0.6907520890235901} 08/31/2021 14:00:11 - INFO - __main__ - Step 136154: {'lr': 1.072182526141241e-05, 'samples': 26141568, 'steps': 136153, 'loss/train': 1.4391037225723267} 08/31/2021 14:00:11 - INFO - __main__ - Step 136155: {'lr': 1.0720287867299699e-05, 'samples': 26141760, 'steps': 136154, 'loss/train': 0.59975266456604} 08/31/2021 14:00:13 - INFO - __main__ - Step 136156: {'lr': 1.0718750581002717e-05, 'samples': 26141952, 'steps': 136155, 'loss/train': 0.9444692134857178} 08/31/2021 14:00:13 - INFO - __main__ - Step 136157: {'lr': 1.0717213402522157e-05, 'samples': 26142144, 'steps': 136156, 'loss/train': 1.6085920333862305} 08/31/2021 14:00:14 - INFO - __main__ - Step 136158: {'lr': 1.0715676331858743e-05, 'samples': 26142336, 'steps': 136157, 'loss/train': 0.9606636762619019} 08/31/2021 14:00:14 - INFO - __main__ - Step 136159: {'lr': 1.0714139369013164e-05, 'samples': 26142528, 'steps': 136158, 'loss/train': 1.029852032661438} 08/31/2021 14:00:14 - INFO - __main__ - Step 136160: {'lr': 1.071260251398612e-05, 'samples': 26142720, 'steps': 136159, 'loss/train': 0.8482515215873718} 08/31/2021 14:00:15 - INFO - __main__ - Step 136161: {'lr': 1.0711065766778272e-05, 'samples': 26142912, 'steps': 136160, 'loss/train': 1.0204691886901855} 08/31/2021 14:00:15 - INFO - __main__ - Step 136162: {'lr': 1.0709529127390315e-05, 'samples': 26143104, 'steps': 136161, 'loss/train': 0.015017373487353325} 08/31/2021 14:00:16 - INFO - __main__ - Step 136163: {'lr': 1.0707992595822946e-05, 'samples': 26143296, 'steps': 136162, 'loss/train': 0.8806756138801575} 08/31/2021 14:00:17 - INFO - __main__ - Step 136164: {'lr': 1.0706456172076855e-05, 'samples': 26143488, 'steps': 136163, 'loss/train': 0.6225600838661194} 08/31/2021 14:00:17 - INFO - __main__ - Step 136165: {'lr': 1.070491985615274e-05, 'samples': 26143680, 'steps': 136164, 'loss/train': 1.7356704473495483} 08/31/2021 14:00:18 - INFO - __main__ - Step 136166: {'lr': 1.0703383648051318e-05, 'samples': 26143872, 'steps': 136165, 'loss/train': 0.03637562692165375} 08/31/2021 14:00:18 - INFO - __main__ - Step 136167: {'lr': 1.0701847547773258e-05, 'samples': 26144064, 'steps': 136166, 'loss/train': 1.1419609785079956} 08/31/2021 14:00:20 - INFO - __main__ - Step 136168: {'lr': 1.0700311555319225e-05, 'samples': 26144256, 'steps': 136167, 'loss/train': 1.4659559726715088} 08/31/2021 14:00:20 - INFO - __main__ - Step 136169: {'lr': 1.069877567068997e-05, 'samples': 26144448, 'steps': 136168, 'loss/train': 0.7270077466964722} 08/31/2021 14:00:20 - INFO - __main__ - Step 136170: {'lr': 1.0697239893886129e-05, 'samples': 26144640, 'steps': 136169, 'loss/train': 1.0598124265670776} 08/31/2021 14:00:21 - INFO - __main__ - Step 136171: {'lr': 1.0695704224908453e-05, 'samples': 26144832, 'steps': 136170, 'loss/train': 0.04236077144742012} 08/31/2021 14:00:21 - INFO - __main__ - Step 136172: {'lr': 1.0694168663757609e-05, 'samples': 26145024, 'steps': 136171, 'loss/train': 1.3796987533569336} 08/31/2021 14:00:23 - INFO - __main__ - Step 136173: {'lr': 1.0692633210434233e-05, 'samples': 26145216, 'steps': 136172, 'loss/train': 0.9708512425422668} 08/31/2021 14:00:24 - INFO - __main__ - Step 136174: {'lr': 1.0691097864939075e-05, 'samples': 26145408, 'steps': 136173, 'loss/train': 1.0064491033554077} 08/31/2021 14:00:24 - INFO - __main__ - Step 136175: {'lr': 1.068956262727283e-05, 'samples': 26145600, 'steps': 136174, 'loss/train': 1.4966974258422852} 08/31/2021 14:00:24 - INFO - __main__ - Step 136176: {'lr': 1.0688027497436165e-05, 'samples': 26145792, 'steps': 136175, 'loss/train': 1.5347810983657837} 08/31/2021 14:00:25 - INFO - __main__ - Step 136177: {'lr': 1.0686492475429798e-05, 'samples': 26145984, 'steps': 136176, 'loss/train': 1.2142058610916138} 08/31/2021 14:00:26 - INFO - __main__ - Step 136178: {'lr': 1.068495756125437e-05, 'samples': 26146176, 'steps': 136177, 'loss/train': 0.998859703540802} 08/31/2021 14:00:27 - INFO - __main__ - Step 136179: {'lr': 1.0683422754910632e-05, 'samples': 26146368, 'steps': 136178, 'loss/train': 0.9954753518104553} 08/31/2021 14:00:27 - INFO - __main__ - Step 136180: {'lr': 1.0681888056399247e-05, 'samples': 26146560, 'steps': 136179, 'loss/train': 0.015532310120761395} 08/31/2021 14:00:28 - INFO - __main__ - Step 136181: {'lr': 1.068035346572091e-05, 'samples': 26146752, 'steps': 136180, 'loss/train': 1.4011348485946655} 08/31/2021 14:00:28 - INFO - __main__ - Step 136182: {'lr': 1.0678818982876315e-05, 'samples': 26146944, 'steps': 136181, 'loss/train': 0.837228536605835} 08/31/2021 14:00:28 - INFO - __main__ - Step 136183: {'lr': 1.0677284607866183e-05, 'samples': 26147136, 'steps': 136182, 'loss/train': 0.621211588382721} 08/31/2021 14:00:30 - INFO - __main__ - Step 136184: {'lr': 1.0675750340691126e-05, 'samples': 26147328, 'steps': 136183, 'loss/train': 1.1924127340316772} 08/31/2021 14:00:30 - INFO - __main__ - Step 136185: {'lr': 1.0674216181351893e-05, 'samples': 26147520, 'steps': 136184, 'loss/train': 0.5224486589431763} 08/31/2021 14:00:31 - INFO - __main__ - Step 136186: {'lr': 1.0672682129849176e-05, 'samples': 26147712, 'steps': 136185, 'loss/train': 1.5484445095062256} 08/31/2021 14:00:31 - INFO - __main__ - Step 136187: {'lr': 1.0671148186183644e-05, 'samples': 26147904, 'steps': 136186, 'loss/train': 1.0190911293029785} 08/31/2021 14:00:32 - INFO - __main__ - Step 136188: {'lr': 1.0669614350356016e-05, 'samples': 26148096, 'steps': 136187, 'loss/train': 1.5706744194030762} 08/31/2021 14:00:32 - INFO - __main__ - Step 136189: {'lr': 1.0668080622366932e-05, 'samples': 26148288, 'steps': 136188, 'loss/train': 0.5968150496482849} 08/31/2021 14:00:33 - INFO - __main__ - Step 136190: {'lr': 1.0666547002217141e-05, 'samples': 26148480, 'steps': 136189, 'loss/train': 1.7093775272369385} 08/31/2021 14:00:34 - INFO - __main__ - Step 136191: {'lr': 1.066501348990731e-05, 'samples': 26148672, 'steps': 136190, 'loss/train': 1.0741684436798096} 08/31/2021 14:00:34 - INFO - __main__ - Step 136192: {'lr': 1.0663480085438132e-05, 'samples': 26148864, 'steps': 136191, 'loss/train': 0.12423411756753922} 08/31/2021 14:00:34 - INFO - __main__ - Step 136193: {'lr': 1.06619467888103e-05, 'samples': 26149056, 'steps': 136192, 'loss/train': 1.1363747119903564} 08/31/2021 14:00:35 - INFO - __main__ - Step 136194: {'lr': 1.0660413600024538e-05, 'samples': 26149248, 'steps': 136193, 'loss/train': 1.7371633052825928} 08/31/2021 14:00:36 - INFO - __main__ - Step 136195: {'lr': 1.0658880519081454e-05, 'samples': 26149440, 'steps': 136194, 'loss/train': 0.9487323760986328} 08/31/2021 14:00:37 - INFO - __main__ - Step 136196: {'lr': 1.0657347545981772e-05, 'samples': 26149632, 'steps': 136195, 'loss/train': 1.4715906381607056} 08/31/2021 14:00:37 - INFO - __main__ - Step 136197: {'lr': 1.0655814680726211e-05, 'samples': 26149824, 'steps': 136196, 'loss/train': 1.1779696941375732} 08/31/2021 14:00:38 - INFO - __main__ - Step 136198: {'lr': 1.0654281923315468e-05, 'samples': 26150016, 'steps': 136197, 'loss/train': 0.5963000059127808} 08/31/2021 14:00:38 - INFO - __main__ - Step 136199: {'lr': 1.0652749273750179e-05, 'samples': 26150208, 'steps': 136198, 'loss/train': 1.3087642192840576} 08/31/2021 14:00:40 - INFO - __main__ - Step 136200: {'lr': 1.0651216732031094e-05, 'samples': 26150400, 'steps': 136199, 'loss/train': 1.0134668350219727} 08/31/2021 14:00:40 - INFO - __main__ - Step 136201: {'lr': 1.0649684298158852e-05, 'samples': 26150592, 'steps': 136200, 'loss/train': 0.9480619430541992} 08/31/2021 14:00:40 - INFO - __main__ - Step 136202: {'lr': 1.0648151972134201e-05, 'samples': 26150784, 'steps': 136201, 'loss/train': 1.4208120107650757} 08/31/2021 14:00:41 - INFO - __main__ - Step 136203: {'lr': 1.0646619753957781e-05, 'samples': 26150976, 'steps': 136202, 'loss/train': 1.004388689994812} 08/31/2021 14:00:41 - INFO - __main__ - Step 136204: {'lr': 1.0645087643630286e-05, 'samples': 26151168, 'steps': 136203, 'loss/train': 0.4139597713947296} 08/31/2021 14:00:43 - INFO - __main__ - Step 136205: {'lr': 1.0643555641152463e-05, 'samples': 26151360, 'steps': 136204, 'loss/train': 1.1170886754989624} 08/31/2021 14:00:43 - INFO - __main__ - Step 136206: {'lr': 1.0642023746524953e-05, 'samples': 26151552, 'steps': 136205, 'loss/train': 0.3328748345375061} 08/31/2021 14:00:43 - INFO - __main__ - Step 136207: {'lr': 1.0640491959748422e-05, 'samples': 26151744, 'steps': 136206, 'loss/train': 0.4309174716472626} 08/31/2021 14:00:44 - INFO - __main__ - Step 136208: {'lr': 1.063896028082359e-05, 'samples': 26151936, 'steps': 136207, 'loss/train': 0.8952216506004333} 08/31/2021 14:00:44 - INFO - __main__ - Step 136209: {'lr': 1.063742870975118e-05, 'samples': 26152128, 'steps': 136208, 'loss/train': 0.2944074869155884} 08/31/2021 14:00:46 - INFO - __main__ - Step 136210: {'lr': 1.0635897246531829e-05, 'samples': 26152320, 'steps': 136209, 'loss/train': 1.4174505472183228} 08/31/2021 14:00:46 - INFO - __main__ - Step 136211: {'lr': 1.063436589116626e-05, 'samples': 26152512, 'steps': 136210, 'loss/train': 1.109291434288025} 08/31/2021 14:00:46 - INFO - __main__ - Step 136212: {'lr': 1.0632834643655136e-05, 'samples': 26152704, 'steps': 136211, 'loss/train': 1.0361907482147217} 08/31/2021 14:00:47 - INFO - __main__ - Step 136213: {'lr': 1.0631303503999185e-05, 'samples': 26152896, 'steps': 136212, 'loss/train': 1.5652503967285156} 08/31/2021 14:00:47 - INFO - __main__ - Step 136214: {'lr': 1.062977247219904e-05, 'samples': 26153088, 'steps': 136213, 'loss/train': 1.1417884826660156} 08/31/2021 14:00:49 - INFO - __main__ - Step 136215: {'lr': 1.062824154825548e-05, 'samples': 26153280, 'steps': 136214, 'loss/train': 0.9067898988723755} 08/31/2021 14:00:49 - INFO - __main__ - Step 136216: {'lr': 1.0626710732169115e-05, 'samples': 26153472, 'steps': 136215, 'loss/train': 1.0735719203948975} 08/31/2021 14:00:50 - INFO - __main__ - Step 136217: {'lr': 1.0625180023940668e-05, 'samples': 26153664, 'steps': 136216, 'loss/train': 1.2282806634902954} 08/31/2021 14:00:50 - INFO - __main__ - Step 136218: {'lr': 1.0623649423570802e-05, 'samples': 26153856, 'steps': 136217, 'loss/train': 0.2654564380645752} 08/31/2021 14:00:50 - INFO - __main__ - Step 136219: {'lr': 1.0622118931060215e-05, 'samples': 26154048, 'steps': 136218, 'loss/train': 0.48200860619544983} 08/31/2021 14:00:51 - INFO - __main__ - Step 136220: {'lr': 1.0620588546409626e-05, 'samples': 26154240, 'steps': 136219, 'loss/train': 0.7340062856674194} 08/31/2021 14:00:53 - INFO - __main__ - Step 136221: {'lr': 1.0619058269619703e-05, 'samples': 26154432, 'steps': 136220, 'loss/train': 1.2712734937667847} 08/31/2021 14:00:53 - INFO - __main__ - Step 136222: {'lr': 1.0617528100691138e-05, 'samples': 26154624, 'steps': 136221, 'loss/train': 0.9907424449920654} 08/31/2021 14:00:53 - INFO - __main__ - Step 136223: {'lr': 1.0615998039624624e-05, 'samples': 26154816, 'steps': 136222, 'loss/train': 1.0642428398132324} 08/31/2021 14:00:54 - INFO - __main__ - Step 136224: {'lr': 1.0614468086420858e-05, 'samples': 26155008, 'steps': 136223, 'loss/train': 1.213613510131836} 08/31/2021 14:00:54 - INFO - __main__ - Step 136225: {'lr': 1.0612938241080505e-05, 'samples': 26155200, 'steps': 136224, 'loss/train': 1.0955533981323242} 08/31/2021 14:00:56 - INFO - __main__ - Step 136226: {'lr': 1.0611408503604259e-05, 'samples': 26155392, 'steps': 136225, 'loss/train': 0.12886884808540344} 08/31/2021 14:00:57 - INFO - __main__ - Step 136227: {'lr': 1.0609878873992867e-05, 'samples': 26155584, 'steps': 136226, 'loss/train': 0.3425733149051666} 08/31/2021 14:00:57 - INFO - __main__ - Step 136228: {'lr': 1.0608349352246915e-05, 'samples': 26155776, 'steps': 136227, 'loss/train': 1.7509833574295044} 08/31/2021 14:00:58 - INFO - __main__ - Step 136229: {'lr': 1.0606819938367179e-05, 'samples': 26155968, 'steps': 136228, 'loss/train': 1.915888786315918} 08/31/2021 14:00:58 - INFO - __main__ - Step 136230: {'lr': 1.0605290632354298e-05, 'samples': 26156160, 'steps': 136229, 'loss/train': 0.44063618779182434} 08/31/2021 14:01:00 - INFO - __main__ - Step 136231: {'lr': 1.0603761434208964e-05, 'samples': 26156352, 'steps': 136230, 'loss/train': 1.2179615497589111} 08/31/2021 14:01:01 - INFO - __main__ - Step 136232: {'lr': 1.06022323439319e-05, 'samples': 26156544, 'steps': 136231, 'loss/train': 1.4329842329025269} 08/31/2021 14:01:01 - INFO - __main__ - Step 136233: {'lr': 1.0600703361523772e-05, 'samples': 26156736, 'steps': 136232, 'loss/train': 0.7975819110870361} 08/31/2021 14:01:01 - INFO - __main__ - Step 136234: {'lr': 1.0599174486985275e-05, 'samples': 26156928, 'steps': 136233, 'loss/train': 0.5715602040290833} 08/31/2021 14:01:02 - INFO - __main__ - Step 136235: {'lr': 1.0597645720317101e-05, 'samples': 26157120, 'steps': 136234, 'loss/train': 1.517407774925232} 08/31/2021 14:01:02 - INFO - __main__ - Step 136236: {'lr': 1.0596117061519916e-05, 'samples': 26157312, 'steps': 136235, 'loss/train': 1.183908462524414} 08/31/2021 14:01:02 - INFO - __main__ - Step 136237: {'lr': 1.0594588510594445e-05, 'samples': 26157504, 'steps': 136236, 'loss/train': 5.7089056968688965} 08/31/2021 14:01:04 - INFO - __main__ - Step 136238: {'lr': 1.059306006754135e-05, 'samples': 26157696, 'steps': 136237, 'loss/train': 5.700213432312012} 08/31/2021 14:01:05 - INFO - __main__ - Step 136239: {'lr': 1.0591531732361325e-05, 'samples': 26157888, 'steps': 136238, 'loss/train': 1.36005437374115} 08/31/2021 14:01:05 - INFO - __main__ - Step 136240: {'lr': 1.0590003505055069e-05, 'samples': 26158080, 'steps': 136239, 'loss/train': 1.219834804534912} 08/31/2021 14:01:06 - INFO - __main__ - Step 136241: {'lr': 1.0588475385623298e-05, 'samples': 26158272, 'steps': 136240, 'loss/train': 0.0274792592972517} 08/31/2021 14:01:06 - INFO - __main__ - Step 136242: {'lr': 1.0586947374066625e-05, 'samples': 26158464, 'steps': 136241, 'loss/train': 0.013397992588579655} 08/31/2021 14:01:06 - INFO - __main__ - Step 136243: {'lr': 1.058541947038577e-05, 'samples': 26158656, 'steps': 136242, 'loss/train': 1.1235078573226929} 08/31/2021 14:01:08 - INFO - __main__ - Step 136244: {'lr': 1.0583891674581458e-05, 'samples': 26158848, 'steps': 136243, 'loss/train': 0.4337904453277588} 08/31/2021 14:01:08 - INFO - __main__ - Step 136245: {'lr': 1.0582363986654325e-05, 'samples': 26159040, 'steps': 136244, 'loss/train': 1.1077702045440674} 08/31/2021 14:01:09 - INFO - __main__ - Step 136246: {'lr': 1.0580836406605094e-05, 'samples': 26159232, 'steps': 136245, 'loss/train': 0.4938925802707672} 08/31/2021 14:01:09 - INFO - __main__ - Step 136247: {'lr': 1.0579308934434456e-05, 'samples': 26159424, 'steps': 136246, 'loss/train': 0.9929473400115967} 08/31/2021 14:01:09 - INFO - __main__ - Step 136248: {'lr': 1.057778157014308e-05, 'samples': 26159616, 'steps': 136247, 'loss/train': 1.3847239017486572} 08/31/2021 14:01:11 - INFO - __main__ - Step 136249: {'lr': 1.0576254313731632e-05, 'samples': 26159808, 'steps': 136248, 'loss/train': 0.8849215507507324} 08/31/2021 14:01:11 - INFO - __main__ - Step 136250: {'lr': 1.0574727165200859e-05, 'samples': 26160000, 'steps': 136249, 'loss/train': 0.8037146925926208} 08/31/2021 14:01:12 - INFO - __main__ - Step 136251: {'lr': 1.0573200124551401e-05, 'samples': 26160192, 'steps': 136250, 'loss/train': 1.266039490699768} 08/31/2021 14:01:12 - INFO - __main__ - Step 136252: {'lr': 1.0571673191783982e-05, 'samples': 26160384, 'steps': 136251, 'loss/train': 1.002215027809143} 08/31/2021 14:01:12 - INFO - __main__ - Step 136253: {'lr': 1.0570146366899263e-05, 'samples': 26160576, 'steps': 136252, 'loss/train': 0.9082233309745789} 08/31/2021 14:01:13 - INFO - __main__ - Step 136254: {'lr': 1.0568619649897998e-05, 'samples': 26160768, 'steps': 136253, 'loss/train': 0.7663305401802063} 08/31/2021 14:01:14 - INFO - __main__ - Step 136255: {'lr': 1.0567093040780767e-05, 'samples': 26160960, 'steps': 136254, 'loss/train': 1.4492809772491455} 08/31/2021 14:01:15 - INFO - __main__ - Step 136256: {'lr': 1.0565566539548293e-05, 'samples': 26161152, 'steps': 136255, 'loss/train': 0.8460142612457275} 08/31/2021 14:01:15 - INFO - __main__ - Step 136257: {'lr': 1.0564040146201299e-05, 'samples': 26161344, 'steps': 136256, 'loss/train': 2.1597397327423096} 08/31/2021 14:01:15 - INFO - __main__ - Step 136258: {'lr': 1.0562513860740447e-05, 'samples': 26161536, 'steps': 136257, 'loss/train': 1.402614712715149} 08/31/2021 14:01:16 - INFO - __main__ - Step 136259: {'lr': 1.0560987683166435e-05, 'samples': 26161728, 'steps': 136258, 'loss/train': 0.9755783081054688} 08/31/2021 14:01:18 - INFO - __main__ - Step 136260: {'lr': 1.0559461613479954e-05, 'samples': 26161920, 'steps': 136259, 'loss/train': 1.2812315225601196} 08/31/2021 14:01:18 - INFO - __main__ - Step 136261: {'lr': 1.0557935651681671e-05, 'samples': 26162112, 'steps': 136260, 'loss/train': 0.5302551984786987} 08/31/2021 14:01:18 - INFO - __main__ - Step 136262: {'lr': 1.0556409797772282e-05, 'samples': 26162304, 'steps': 136261, 'loss/train': 0.9441270232200623} 08/31/2021 14:01:19 - INFO - __main__ - Step 136263: {'lr': 1.0554884051752506e-05, 'samples': 26162496, 'steps': 136262, 'loss/train': 1.140871286392212} 08/31/2021 14:01:19 - INFO - __main__ - Step 136264: {'lr': 1.0553358413622983e-05, 'samples': 26162688, 'steps': 136263, 'loss/train': 0.060381095856428146} 08/31/2021 14:01:21 - INFO - __main__ - Step 136265: {'lr': 1.0551832883384432e-05, 'samples': 26162880, 'steps': 136264, 'loss/train': 1.2392367124557495} 08/31/2021 14:01:21 - INFO - __main__ - Step 136266: {'lr': 1.0550307461037523e-05, 'samples': 26163072, 'steps': 136265, 'loss/train': 0.755166232585907} 08/31/2021 14:01:22 - INFO - __main__ - Step 136267: {'lr': 1.0548782146582947e-05, 'samples': 26163264, 'steps': 136266, 'loss/train': 0.6518459916114807} 08/31/2021 14:01:22 - INFO - __main__ - Step 136268: {'lr': 1.0547256940021426e-05, 'samples': 26163456, 'steps': 136267, 'loss/train': 1.9317396879196167} 08/31/2021 14:01:22 - INFO - __main__ - Step 136269: {'lr': 1.0545731841353601e-05, 'samples': 26163648, 'steps': 136268, 'loss/train': 0.026541462168097496} 08/31/2021 14:01:24 - INFO - __main__ - Step 136270: {'lr': 1.0544206850580163e-05, 'samples': 26163840, 'steps': 136269, 'loss/train': 0.3988424241542816} 08/31/2021 14:01:24 - INFO - __main__ - Step 136271: {'lr': 1.0542681967701806e-05, 'samples': 26164032, 'steps': 136270, 'loss/train': 1.1316137313842773} 08/31/2021 14:01:24 - INFO - __main__ - Step 136272: {'lr': 1.0541157192719253e-05, 'samples': 26164224, 'steps': 136271, 'loss/train': 0.7303405404090881} 08/31/2021 14:01:25 - INFO - __main__ - Step 136273: {'lr': 1.0539632525633113e-05, 'samples': 26164416, 'steps': 136272, 'loss/train': 0.02843252569437027} 08/31/2021 14:01:25 - INFO - __main__ - Step 136274: {'lr': 1.0538107966444138e-05, 'samples': 26164608, 'steps': 136273, 'loss/train': 1.1989259719848633} 08/31/2021 14:01:27 - INFO - __main__ - Step 136275: {'lr': 1.053658351515302e-05, 'samples': 26164800, 'steps': 136274, 'loss/train': 1.0858962535858154} 08/31/2021 14:01:27 - INFO - __main__ - Step 136276: {'lr': 1.0535059171760397e-05, 'samples': 26164992, 'steps': 136275, 'loss/train': 1.1334233283996582} 08/31/2021 14:01:28 - INFO - __main__ - Step 136277: {'lr': 1.0533534936266992e-05, 'samples': 26165184, 'steps': 136276, 'loss/train': 0.7636027336120605} 08/31/2021 14:01:28 - INFO - __main__ - Step 136278: {'lr': 1.053201080867347e-05, 'samples': 26165376, 'steps': 136277, 'loss/train': 1.02799391746521} 08/31/2021 14:01:28 - INFO - __main__ - Step 136279: {'lr': 1.0530486788980526e-05, 'samples': 26165568, 'steps': 136278, 'loss/train': 0.9202660322189331} 08/31/2021 14:01:31 - INFO - __main__ - Step 136280: {'lr': 1.0528962877188853e-05, 'samples': 26165760, 'steps': 136279, 'loss/train': 0.8392056226730347} 08/31/2021 14:01:31 - INFO - __main__ - Step 136281: {'lr': 1.0527439073299172e-05, 'samples': 26165952, 'steps': 136280, 'loss/train': 1.4436171054840088} 08/31/2021 14:01:32 - INFO - __main__ - Step 136282: {'lr': 1.0525915377312095e-05, 'samples': 26166144, 'steps': 136281, 'loss/train': 1.3611973524093628} 08/31/2021 14:01:32 - INFO - __main__ - Step 136283: {'lr': 1.0524391789228343e-05, 'samples': 26166336, 'steps': 136282, 'loss/train': 1.4979338645935059} 08/31/2021 14:01:32 - INFO - __main__ - Step 136284: {'lr': 1.0522868309048612e-05, 'samples': 26166528, 'steps': 136283, 'loss/train': 0.22153587639331818} 08/31/2021 14:01:34 - INFO - __main__ - Step 136285: {'lr': 1.0521344936773592e-05, 'samples': 26166720, 'steps': 136284, 'loss/train': 0.027577335014939308} 08/31/2021 14:01:34 - INFO - __main__ - Step 136286: {'lr': 1.051982167240395e-05, 'samples': 26166912, 'steps': 136285, 'loss/train': 1.2081918716430664} 08/31/2021 14:01:34 - INFO - __main__ - Step 136287: {'lr': 1.0518298515940355e-05, 'samples': 26167104, 'steps': 136286, 'loss/train': 1.0899810791015625} 08/31/2021 14:01:35 - INFO - __main__ - Step 136288: {'lr': 1.0516775467383555e-05, 'samples': 26167296, 'steps': 136287, 'loss/train': 1.2058684825897217} 08/31/2021 14:01:35 - INFO - __main__ - Step 136289: {'lr': 1.0515252526734187e-05, 'samples': 26167488, 'steps': 136288, 'loss/train': 0.6725791096687317} 08/31/2021 14:01:37 - INFO - __main__ - Step 136290: {'lr': 1.0513729693992947e-05, 'samples': 26167680, 'steps': 136289, 'loss/train': 1.2193952798843384} 08/31/2021 14:01:37 - INFO - __main__ - Step 136291: {'lr': 1.0512206969160526e-05, 'samples': 26167872, 'steps': 136290, 'loss/train': 0.9257891774177551} 08/31/2021 14:01:38 - INFO - __main__ - Step 136292: {'lr': 1.051068435223762e-05, 'samples': 26168064, 'steps': 136291, 'loss/train': 0.06779837608337402} 08/31/2021 14:01:38 - INFO - __main__ - Step 136293: {'lr': 1.0509161843224896e-05, 'samples': 26168256, 'steps': 136292, 'loss/train': 0.03415927290916443} 08/31/2021 14:01:39 - INFO - __main__ - Step 136294: {'lr': 1.0507639442123046e-05, 'samples': 26168448, 'steps': 136293, 'loss/train': 1.4624664783477783} 08/31/2021 14:01:40 - INFO - __main__ - Step 136295: {'lr': 1.0506117148932793e-05, 'samples': 26168640, 'steps': 136294, 'loss/train': 0.6480190753936768} 08/31/2021 14:01:41 - INFO - __main__ - Step 136296: {'lr': 1.0504594963654745e-05, 'samples': 26168832, 'steps': 136295, 'loss/train': 0.3852432072162628} 08/31/2021 14:01:41 - INFO - __main__ - Step 136297: {'lr': 1.0503072886289627e-05, 'samples': 26169024, 'steps': 136296, 'loss/train': 0.27163639664649963} 08/31/2021 14:01:41 - INFO - __main__ - Step 136298: {'lr': 1.050155091683816e-05, 'samples': 26169216, 'steps': 136297, 'loss/train': 1.1634564399719238} 08/31/2021 14:01:42 - INFO - __main__ - Step 136299: {'lr': 1.050002905530098e-05, 'samples': 26169408, 'steps': 136298, 'loss/train': 1.1444967985153198} 08/31/2021 14:01:43 - INFO - __main__ - Step 136300: {'lr': 1.0498507301678784e-05, 'samples': 26169600, 'steps': 136299, 'loss/train': 0.5145560503005981} 08/31/2021 14:01:44 - INFO - __main__ - Step 136301: {'lr': 1.0496985655972264e-05, 'samples': 26169792, 'steps': 136300, 'loss/train': 0.9935781955718994} 08/31/2021 14:01:44 - INFO - __main__ - Step 136302: {'lr': 1.0495464118182112e-05, 'samples': 26169984, 'steps': 136301, 'loss/train': 1.5228245258331299} 08/31/2021 14:01:44 - INFO - __main__ - Step 136303: {'lr': 1.0493942688309027e-05, 'samples': 26170176, 'steps': 136302, 'loss/train': 1.3106892108917236} 08/31/2021 14:01:45 - INFO - __main__ - Step 136304: {'lr': 1.0492421366353644e-05, 'samples': 26170368, 'steps': 136303, 'loss/train': 1.153671383857727} 08/31/2021 14:01:46 - INFO - __main__ - Step 136305: {'lr': 1.0490900152316712e-05, 'samples': 26170560, 'steps': 136304, 'loss/train': 1.2290403842926025} 08/31/2021 14:01:47 - INFO - __main__ - Step 136306: {'lr': 1.0489379046198872e-05, 'samples': 26170752, 'steps': 136305, 'loss/train': 1.4770647287368774} 08/31/2021 14:01:47 - INFO - __main__ - Step 136307: {'lr': 1.0487858048000815e-05, 'samples': 26170944, 'steps': 136306, 'loss/train': 0.711826503276825} 08/31/2021 14:01:48 - INFO - __main__ - Step 136308: {'lr': 1.0486337157723264e-05, 'samples': 26171136, 'steps': 136307, 'loss/train': 1.5595262050628662} 08/31/2021 14:01:48 - INFO - __main__ - Step 136309: {'lr': 1.0484816375366829e-05, 'samples': 26171328, 'steps': 136308, 'loss/train': 1.8599318265914917} 08/31/2021 14:01:48 - INFO - __main__ - Step 136310: {'lr': 1.048329570093226e-05, 'samples': 26171520, 'steps': 136309, 'loss/train': 0.05043768137693405} 08/31/2021 14:01:50 - INFO - __main__ - Step 136311: {'lr': 1.0481775134420224e-05, 'samples': 26171712, 'steps': 136310, 'loss/train': 1.1393663883209229} 08/31/2021 14:01:51 - INFO - __main__ - Step 136312: {'lr': 1.0480254675831413e-05, 'samples': 26171904, 'steps': 136311, 'loss/train': 0.9861220121383667} 08/31/2021 14:01:51 - INFO - __main__ - Step 136313: {'lr': 1.0478734325166467e-05, 'samples': 26172096, 'steps': 136312, 'loss/train': 0.1990777850151062} 08/31/2021 14:01:52 - INFO - __main__ - Step 136314: {'lr': 1.0477214082426135e-05, 'samples': 26172288, 'steps': 136313, 'loss/train': 0.01609790325164795} 08/31/2021 14:01:52 - INFO - __main__ - Step 136315: {'lr': 1.047569394761108e-05, 'samples': 26172480, 'steps': 136314, 'loss/train': 0.01411474496126175} 08/31/2021 14:01:52 - INFO - __main__ - Step 136316: {'lr': 1.0474173920721974e-05, 'samples': 26172672, 'steps': 136315, 'loss/train': 0.7476187348365784} 08/31/2021 14:01:54 - INFO - __main__ - Step 136317: {'lr': 1.047265400175948e-05, 'samples': 26172864, 'steps': 136316, 'loss/train': 1.1959388256072998} 08/31/2021 14:01:54 - INFO - __main__ - Step 136318: {'lr': 1.0471134190724345e-05, 'samples': 26173056, 'steps': 136317, 'loss/train': 1.6199231147766113} 08/31/2021 14:01:55 - INFO - __main__ - Step 136319: {'lr': 1.0469614487617212e-05, 'samples': 26173248, 'steps': 136318, 'loss/train': 1.2953585386276245} 08/31/2021 14:01:55 - INFO - __main__ - Step 136320: {'lr': 1.0468094892438773e-05, 'samples': 26173440, 'steps': 136319, 'loss/train': 1.3639425039291382} 08/31/2021 14:01:55 - INFO - __main__ - Step 136321: {'lr': 1.046657540518975e-05, 'samples': 26173632, 'steps': 136320, 'loss/train': 1.193859577178955} 08/31/2021 14:01:56 - INFO - __main__ - Step 136322: {'lr': 1.046505602587075e-05, 'samples': 26173824, 'steps': 136321, 'loss/train': 0.8930563926696777} 08/31/2021 14:01:57 - INFO - __main__ - Step 136323: {'lr': 1.0463536754482528e-05, 'samples': 26174016, 'steps': 136322, 'loss/train': 0.8388342261314392} 08/31/2021 14:01:58 - INFO - __main__ - Step 136324: {'lr': 1.0462017591025718e-05, 'samples': 26174208, 'steps': 136323, 'loss/train': 1.1039705276489258} 08/31/2021 14:01:58 - INFO - __main__ - Step 136325: {'lr': 1.0460498535501018e-05, 'samples': 26174400, 'steps': 136324, 'loss/train': 1.3362573385238647} 08/31/2021 14:01:59 - INFO - __main__ - Step 136326: {'lr': 1.0458979587909145e-05, 'samples': 26174592, 'steps': 136325, 'loss/train': 0.03396940603852272} 08/31/2021 14:01:59 - INFO - __main__ - Step 136327: {'lr': 1.0457460748250742e-05, 'samples': 26174784, 'steps': 136326, 'loss/train': 1.0154821872711182} 08/31/2021 14:02:00 - INFO - __main__ - Step 136328: {'lr': 1.0455942016526498e-05, 'samples': 26174976, 'steps': 136327, 'loss/train': 0.9193460941314697} 08/31/2021 14:02:01 - INFO - __main__ - Step 136329: {'lr': 1.0454423392737138e-05, 'samples': 26175168, 'steps': 136328, 'loss/train': 1.395743727684021} 08/31/2021 14:02:01 - INFO - __main__ - Step 136330: {'lr': 1.0452904876883302e-05, 'samples': 26175360, 'steps': 136329, 'loss/train': 1.4389640092849731} 08/31/2021 14:02:02 - INFO - __main__ - Step 136331: {'lr': 1.0451386468965707e-05, 'samples': 26175552, 'steps': 136330, 'loss/train': 1.076033592224121} 08/31/2021 14:02:02 - INFO - __main__ - Step 136332: {'lr': 1.0449868168984995e-05, 'samples': 26175744, 'steps': 136331, 'loss/train': 0.9820614457130432} 08/31/2021 14:02:03 - INFO - __main__ - Step 136333: {'lr': 1.0448349976941913e-05, 'samples': 26175936, 'steps': 136332, 'loss/train': 1.351906180381775} 08/31/2021 14:02:04 - INFO - __main__ - Step 136334: {'lr': 1.0446831892837072e-05, 'samples': 26176128, 'steps': 136333, 'loss/train': 1.3711673021316528} 08/31/2021 14:02:04 - INFO - __main__ - Step 136335: {'lr': 1.0445313916671223e-05, 'samples': 26176320, 'steps': 136334, 'loss/train': 0.2666730284690857} 08/31/2021 14:02:05 - INFO - __main__ - Step 136336: {'lr': 1.0443796048445003e-05, 'samples': 26176512, 'steps': 136335, 'loss/train': 1.4475233554840088} 08/31/2021 14:02:05 - INFO - __main__ - Step 136337: {'lr': 1.0442278288159135e-05, 'samples': 26176704, 'steps': 136336, 'loss/train': 1.1042832136154175} 08/31/2021 14:02:07 - INFO - __main__ - Step 136338: {'lr': 1.0440760635814256e-05, 'samples': 26176896, 'steps': 136337, 'loss/train': 0.7327855825424194} 08/31/2021 14:02:08 - INFO - __main__ - Step 136339: {'lr': 1.043924309141106e-05, 'samples': 26177088, 'steps': 136338, 'loss/train': 1.1859370470046997} 08/31/2021 14:02:08 - INFO - __main__ - Step 136340: {'lr': 1.043772565495027e-05, 'samples': 26177280, 'steps': 136339, 'loss/train': 0.2507515549659729} 08/31/2021 14:02:08 - INFO - __main__ - Step 136341: {'lr': 1.0436208326432522e-05, 'samples': 26177472, 'steps': 136340, 'loss/train': 0.9264641404151917} 08/31/2021 14:02:09 - INFO - __main__ - Step 136342: {'lr': 1.043469110585854e-05, 'samples': 26177664, 'steps': 136341, 'loss/train': 1.1121342182159424} 08/31/2021 14:02:10 - INFO - __main__ - Step 136343: {'lr': 1.0433173993228962e-05, 'samples': 26177856, 'steps': 136342, 'loss/train': 0.5379639267921448} 08/31/2021 14:02:11 - INFO - __main__ - Step 136344: {'lr': 1.0431656988544536e-05, 'samples': 26178048, 'steps': 136343, 'loss/train': 0.2722971439361572} 08/31/2021 14:02:11 - INFO - __main__ - Step 136345: {'lr': 1.0430140091805872e-05, 'samples': 26178240, 'steps': 136344, 'loss/train': 1.3865177631378174} 08/31/2021 14:02:11 - INFO - __main__ - Step 136346: {'lr': 1.0428623303013723e-05, 'samples': 26178432, 'steps': 136345, 'loss/train': 1.337138295173645} 08/31/2021 14:02:12 - INFO - __main__ - Step 136347: {'lr': 1.0427106622168726e-05, 'samples': 26178624, 'steps': 136346, 'loss/train': 0.7471375465393066} 08/31/2021 14:02:13 - INFO - __main__ - Step 136348: {'lr': 1.04255900492716e-05, 'samples': 26178816, 'steps': 136347, 'loss/train': 0.6974280476570129} 08/31/2021 14:02:14 - INFO - __main__ - Step 136349: {'lr': 1.0424073584322985e-05, 'samples': 26179008, 'steps': 136348, 'loss/train': 0.507341742515564} 08/31/2021 14:02:14 - INFO - __main__ - Step 136350: {'lr': 1.0422557227323575e-05, 'samples': 26179200, 'steps': 136349, 'loss/train': 0.021647877991199493} 08/31/2021 14:02:15 - INFO - __main__ - Step 136351: {'lr': 1.0421040978274065e-05, 'samples': 26179392, 'steps': 136350, 'loss/train': 1.5653984546661377} 08/31/2021 14:02:15 - INFO - __main__ - Step 136352: {'lr': 1.0419524837175149e-05, 'samples': 26179584, 'steps': 136351, 'loss/train': 1.953431487083435} 08/31/2021 14:02:15 - INFO - __main__ - Step 136353: {'lr': 1.041800880402749e-05, 'samples': 26179776, 'steps': 136352, 'loss/train': 0.8984574675559998} 08/31/2021 14:02:17 - INFO - __main__ - Step 136354: {'lr': 1.0416492878831785e-05, 'samples': 26179968, 'steps': 136353, 'loss/train': 1.152588963508606} 08/31/2021 14:02:17 - INFO - __main__ - Step 136355: {'lr': 1.0414977061588726e-05, 'samples': 26180160, 'steps': 136354, 'loss/train': 1.6004459857940674} 08/31/2021 14:02:18 - INFO - __main__ - Step 136356: {'lr': 1.0413461352298953e-05, 'samples': 26180352, 'steps': 136355, 'loss/train': 1.3253179788589478} 08/31/2021 14:02:18 - INFO - __main__ - Step 136357: {'lr': 1.0411945750963186e-05, 'samples': 26180544, 'steps': 136356, 'loss/train': 1.7954009771347046} 08/31/2021 14:02:18 - INFO - __main__ - Step 136358: {'lr': 1.0410430257582121e-05, 'samples': 26180736, 'steps': 136357, 'loss/train': 1.0970133543014526} 08/31/2021 14:02:20 - INFO - __main__ - Step 136359: {'lr': 1.0408914872156395e-05, 'samples': 26180928, 'steps': 136358, 'loss/train': 0.9599580764770508} 08/31/2021 14:02:20 - INFO - __main__ - Step 136360: {'lr': 1.0407399594686701e-05, 'samples': 26181120, 'steps': 136359, 'loss/train': 0.2609347701072693} 08/31/2021 14:02:21 - INFO - __main__ - Step 136361: {'lr': 1.0405884425173762e-05, 'samples': 26181312, 'steps': 136360, 'loss/train': 0.5916886925697327} 08/31/2021 14:02:21 - INFO - __main__ - Step 136362: {'lr': 1.0404369363618271e-05, 'samples': 26181504, 'steps': 136361, 'loss/train': 0.8208203315734863} 08/31/2021 14:02:21 - INFO - __main__ - Step 136363: {'lr': 1.0402854410020812e-05, 'samples': 26181696, 'steps': 136362, 'loss/train': 1.3504517078399658} 08/31/2021 14:02:23 - INFO - __main__ - Step 136364: {'lr': 1.0401339564382162e-05, 'samples': 26181888, 'steps': 136363, 'loss/train': 0.9797114133834839} 08/31/2021 14:02:23 - INFO - __main__ - Step 136365: {'lr': 1.0399824826702958e-05, 'samples': 26182080, 'steps': 136364, 'loss/train': 0.35670050978660583} 08/31/2021 14:02:24 - INFO - __main__ - Step 136366: {'lr': 1.0398310196983896e-05, 'samples': 26182272, 'steps': 136365, 'loss/train': 0.9679562449455261} 08/31/2021 14:02:24 - INFO - __main__ - Step 136367: {'lr': 1.039679567522564e-05, 'samples': 26182464, 'steps': 136366, 'loss/train': 0.8579182624816895} 08/31/2021 14:02:24 - INFO - __main__ - Step 136368: {'lr': 1.0395281261428913e-05, 'samples': 26182656, 'steps': 136367, 'loss/train': 1.0762580633163452} 08/31/2021 14:02:26 - INFO - __main__ - Step 136369: {'lr': 1.039376695559438e-05, 'samples': 26182848, 'steps': 136368, 'loss/train': 0.8460057377815247} 08/31/2021 14:02:26 - INFO - __main__ - Step 136370: {'lr': 1.0392252757722709e-05, 'samples': 26183040, 'steps': 136369, 'loss/train': 0.9084726572036743} 08/31/2021 14:02:27 - INFO - __main__ - Step 136371: {'lr': 1.0390738667814592e-05, 'samples': 26183232, 'steps': 136370, 'loss/train': 1.0151296854019165} 08/31/2021 14:02:27 - INFO - __main__ - Step 136372: {'lr': 1.0389224685870697e-05, 'samples': 26183424, 'steps': 136371, 'loss/train': 1.0590693950653076} 08/31/2021 14:02:27 - INFO - __main__ - Step 136373: {'lr': 1.0387710811891744e-05, 'samples': 26183616, 'steps': 136372, 'loss/train': 0.9641314744949341} 08/31/2021 14:02:28 - INFO - __main__ - Step 136374: {'lr': 1.038619704587837e-05, 'samples': 26183808, 'steps': 136373, 'loss/train': 1.1786962747573853} 08/31/2021 14:02:29 - INFO - __main__ - Step 136375: {'lr': 1.03846833878313e-05, 'samples': 26184000, 'steps': 136374, 'loss/train': 1.1674449443817139} 08/31/2021 14:02:30 - INFO - __main__ - Step 136376: {'lr': 1.03831698377512e-05, 'samples': 26184192, 'steps': 136375, 'loss/train': 0.7605001330375671} 08/31/2021 14:02:30 - INFO - __main__ - Step 136377: {'lr': 1.0381656395638733e-05, 'samples': 26184384, 'steps': 136376, 'loss/train': 0.9963821768760681} 08/31/2021 14:02:30 - INFO - __main__ - Step 136378: {'lr': 1.0380143061494568e-05, 'samples': 26184576, 'steps': 136377, 'loss/train': 0.7288886308670044} 08/31/2021 14:02:31 - INFO - __main__ - Step 136379: {'lr': 1.0378629835319452e-05, 'samples': 26184768, 'steps': 136378, 'loss/train': 1.078757882118225} 08/31/2021 14:02:32 - INFO - __main__ - Step 136380: {'lr': 1.0377116717113998e-05, 'samples': 26184960, 'steps': 136379, 'loss/train': 1.374752163887024} 08/31/2021 14:02:33 - INFO - __main__ - Step 136381: {'lr': 1.0375603706878928e-05, 'samples': 26185152, 'steps': 136380, 'loss/train': 1.2512238025665283} 08/31/2021 14:02:33 - INFO - __main__ - Step 136382: {'lr': 1.0374090804614905e-05, 'samples': 26185344, 'steps': 136381, 'loss/train': 1.3253977298736572} 08/31/2021 14:02:33 - INFO - __main__ - Step 136383: {'lr': 1.0372578010322626e-05, 'samples': 26185536, 'steps': 136382, 'loss/train': 0.5209029912948608} 08/31/2021 14:02:34 - INFO - __main__ - Step 136384: {'lr': 1.0371065324002781e-05, 'samples': 26185728, 'steps': 136383, 'loss/train': 0.8728519678115845} 08/31/2021 14:02:35 - INFO - __main__ - Step 136385: {'lr': 1.0369552745656014e-05, 'samples': 26185920, 'steps': 136384, 'loss/train': 1.3630905151367188} 08/31/2021 14:02:36 - INFO - __main__ - Step 136386: {'lr': 1.0368040275283042e-05, 'samples': 26186112, 'steps': 136385, 'loss/train': 1.6253695487976074} 08/31/2021 14:02:36 - INFO - __main__ - Step 136387: {'lr': 1.0366527912884533e-05, 'samples': 26186304, 'steps': 136386, 'loss/train': 1.0631381273269653} 08/31/2021 14:02:36 - INFO - __main__ - Step 136388: {'lr': 1.0365015658461152e-05, 'samples': 26186496, 'steps': 136387, 'loss/train': 0.7110871076583862} 08/31/2021 14:02:37 - INFO - __main__ - Step 136389: {'lr': 1.036350351201365e-05, 'samples': 26186688, 'steps': 136388, 'loss/train': 0.7595919370651245} 08/31/2021 14:02:39 - INFO - __main__ - Step 136390: {'lr': 1.036199147354261e-05, 'samples': 26186880, 'steps': 136389, 'loss/train': 0.9309571981430054} 08/31/2021 14:02:39 - INFO - __main__ - Step 136391: {'lr': 1.0360479543048778e-05, 'samples': 26187072, 'steps': 136390, 'loss/train': 0.5049919486045837} 08/31/2021 14:02:40 - INFO - __main__ - Step 136392: {'lr': 1.0358967720532796e-05, 'samples': 26187264, 'steps': 136391, 'loss/train': 0.5233635306358337} 08/31/2021 14:02:40 - INFO - __main__ - Step 136393: {'lr': 1.0357456005995358e-05, 'samples': 26187456, 'steps': 136392, 'loss/train': 0.7502755522727966} 08/31/2021 14:02:40 - INFO - __main__ - Step 136394: {'lr': 1.0355944399437184e-05, 'samples': 26187648, 'steps': 136393, 'loss/train': 1.047042727470398} 08/31/2021 14:02:42 - INFO - __main__ - Step 136395: {'lr': 1.0354432900858912e-05, 'samples': 26187840, 'steps': 136394, 'loss/train': 0.3571058213710785} 08/31/2021 14:02:43 - INFO - __main__ - Step 136396: {'lr': 1.0352921510261209e-05, 'samples': 26188032, 'steps': 136395, 'loss/train': 0.16673050820827484} 08/31/2021 14:02:43 - INFO - __main__ - Step 136397: {'lr': 1.0351410227644797e-05, 'samples': 26188224, 'steps': 136396, 'loss/train': 0.1772405505180359} 08/31/2021 14:02:43 - INFO - __main__ - Step 136398: {'lr': 1.0349899053010342e-05, 'samples': 26188416, 'steps': 136397, 'loss/train': 0.9681556224822998} 08/31/2021 14:02:44 - INFO - __main__ - Step 136399: {'lr': 1.0348387986358537e-05, 'samples': 26188608, 'steps': 136398, 'loss/train': 1.0028162002563477} 08/31/2021 14:02:44 - INFO - __main__ - Step 136400: {'lr': 1.0346877027690049e-05, 'samples': 26188800, 'steps': 136399, 'loss/train': 1.4110630750656128} 08/31/2021 14:02:46 - INFO - __main__ - Step 136401: {'lr': 1.0345366177005544e-05, 'samples': 26188992, 'steps': 136400, 'loss/train': 0.6629957556724548} 08/31/2021 14:02:46 - INFO - __main__ - Step 136402: {'lr': 1.034385543430577e-05, 'samples': 26189184, 'steps': 136401, 'loss/train': 1.017814040184021} 08/31/2021 14:02:46 - INFO - __main__ - Step 136403: {'lr': 1.0342344799591314e-05, 'samples': 26189376, 'steps': 136402, 'loss/train': 0.9988803863525391} 08/31/2021 14:02:47 - INFO - __main__ - Step 136404: {'lr': 1.0340834272862893e-05, 'samples': 26189568, 'steps': 136403, 'loss/train': 1.5875810384750366} 08/31/2021 14:02:47 - INFO - __main__ - Step 136405: {'lr': 1.0339323854121203e-05, 'samples': 26189760, 'steps': 136404, 'loss/train': 0.800126850605011} 08/31/2021 14:02:49 - INFO - __main__ - Step 136406: {'lr': 1.033781354336691e-05, 'samples': 26189952, 'steps': 136405, 'loss/train': 0.3124520182609558} 08/31/2021 14:02:49 - INFO - __main__ - Step 136407: {'lr': 1.0336303340600706e-05, 'samples': 26190144, 'steps': 136406, 'loss/train': 0.8478519320487976} 08/31/2021 14:02:50 - INFO - __main__ - Step 136408: {'lr': 1.033479324582326e-05, 'samples': 26190336, 'steps': 136407, 'loss/train': 1.5666859149932861} 08/31/2021 14:02:50 - INFO - __main__ - Step 136409: {'lr': 1.0333283259035264e-05, 'samples': 26190528, 'steps': 136408, 'loss/train': 1.2522542476654053} 08/31/2021 14:02:50 - INFO - __main__ - Step 136410: {'lr': 1.0331773380237386e-05, 'samples': 26190720, 'steps': 136409, 'loss/train': 0.01428164355456829} 08/31/2021 14:02:51 - INFO - __main__ - Step 136411: {'lr': 1.0330263609430318e-05, 'samples': 26190912, 'steps': 136410, 'loss/train': 1.058121681213379} 08/31/2021 14:02:52 - INFO - __main__ - Step 136412: {'lr': 1.0328753946614728e-05, 'samples': 26191104, 'steps': 136411, 'loss/train': 1.248509168624878} 08/31/2021 14:02:53 - INFO - __main__ - Step 136413: {'lr': 1.0327244391791307e-05, 'samples': 26191296, 'steps': 136412, 'loss/train': 1.336148738861084} 08/31/2021 14:02:53 - INFO - __main__ - Step 136414: {'lr': 1.0325734944960725e-05, 'samples': 26191488, 'steps': 136413, 'loss/train': 1.2704967260360718} 08/31/2021 14:02:53 - INFO - __main__ - Step 136415: {'lr': 1.0324225606123672e-05, 'samples': 26191680, 'steps': 136414, 'loss/train': 0.03116881288588047} 08/31/2021 14:02:54 - INFO - __main__ - Step 136416: {'lr': 1.0322716375280843e-05, 'samples': 26191872, 'steps': 136415, 'loss/train': 1.5370709896087646} 08/31/2021 14:02:56 - INFO - __main__ - Step 136417: {'lr': 1.0321207252432908e-05, 'samples': 26192064, 'steps': 136416, 'loss/train': 0.8614838719367981} 08/31/2021 14:02:56 - INFO - __main__ - Step 136418: {'lr': 1.0319698237580499e-05, 'samples': 26192256, 'steps': 136417, 'loss/train': 1.0261279344558716} 08/31/2021 14:02:56 - INFO - __main__ - Step 136419: {'lr': 1.0318189330724342e-05, 'samples': 26192448, 'steps': 136418, 'loss/train': 0.9885805249214172} 08/31/2021 14:02:57 - INFO - __main__ - Step 136420: {'lr': 1.031668053186513e-05, 'samples': 26192640, 'steps': 136419, 'loss/train': 1.0761767625808716} 08/31/2021 14:02:57 - INFO - __main__ - Step 136421: {'lr': 1.03151718410035e-05, 'samples': 26192832, 'steps': 136420, 'loss/train': 0.025575820356607437} 08/31/2021 14:02:57 - INFO - __main__ - Step 136422: {'lr': 1.0313663258140177e-05, 'samples': 26193024, 'steps': 136421, 'loss/train': 1.54929780960083} 08/31/2021 14:02:59 - INFO - __main__ - Step 136423: {'lr': 1.0312154783275824e-05, 'samples': 26193216, 'steps': 136422, 'loss/train': 0.056757379323244095} 08/31/2021 14:03:00 - INFO - __main__ - Step 136424: {'lr': 1.0310646416411078e-05, 'samples': 26193408, 'steps': 136423, 'loss/train': 1.1329374313354492} 08/31/2021 14:03:00 - INFO - __main__ - Step 136425: {'lr': 1.0309138157546693e-05, 'samples': 26193600, 'steps': 136424, 'loss/train': 1.2153759002685547} 08/31/2021 14:03:00 - INFO - __main__ - Step 136426: {'lr': 1.0307630006683305e-05, 'samples': 26193792, 'steps': 136425, 'loss/train': 0.8510602712631226} 08/31/2021 14:03:01 - INFO - __main__ - Step 136427: {'lr': 1.030612196382158e-05, 'samples': 26193984, 'steps': 136426, 'loss/train': 1.2959479093551636} 08/31/2021 14:03:03 - INFO - __main__ - Step 136428: {'lr': 1.030461402896224e-05, 'samples': 26194176, 'steps': 136427, 'loss/train': 1.2127645015716553} 08/31/2021 14:03:03 - INFO - __main__ - Step 136429: {'lr': 1.030310620210595e-05, 'samples': 26194368, 'steps': 136428, 'loss/train': 1.4036506414413452} 08/31/2021 14:03:04 - INFO - __main__ - Step 136430: {'lr': 1.0301598483253377e-05, 'samples': 26194560, 'steps': 136429, 'loss/train': 0.08938824385404587} 08/31/2021 14:03:04 - INFO - __main__ - Step 136431: {'lr': 1.0300090872405188e-05, 'samples': 26194752, 'steps': 136430, 'loss/train': 1.133582353591919} 08/31/2021 14:03:04 - INFO - __main__ - Step 136432: {'lr': 1.0298583369562076e-05, 'samples': 26194944, 'steps': 136431, 'loss/train': 0.8289223313331604} 08/31/2021 14:03:06 - INFO - __main__ - Step 136433: {'lr': 1.0297075974724734e-05, 'samples': 26195136, 'steps': 136432, 'loss/train': 1.9804003238677979} 08/31/2021 14:03:06 - INFO - __main__ - Step 136434: {'lr': 1.029556868789383e-05, 'samples': 26195328, 'steps': 136433, 'loss/train': 0.23841352760791779} 08/31/2021 14:03:07 - INFO - __main__ - Step 136435: {'lr': 1.029406150907003e-05, 'samples': 26195520, 'steps': 136434, 'loss/train': 0.15867085754871368} 08/31/2021 14:03:07 - INFO - __main__ - Step 136436: {'lr': 1.0292554438254054e-05, 'samples': 26195712, 'steps': 136435, 'loss/train': 0.9809670448303223} 08/31/2021 14:03:07 - INFO - __main__ - Step 136437: {'lr': 1.0291047475446514e-05, 'samples': 26195904, 'steps': 136436, 'loss/train': 1.132792353630066} 08/31/2021 14:03:09 - INFO - __main__ - Step 136438: {'lr': 1.0289540620648157e-05, 'samples': 26196096, 'steps': 136437, 'loss/train': 1.6560479402542114} 08/31/2021 14:03:09 - INFO - __main__ - Step 136439: {'lr': 1.0288033873859627e-05, 'samples': 26196288, 'steps': 136438, 'loss/train': 0.9500557780265808} 08/31/2021 14:03:10 - INFO - __main__ - Step 136440: {'lr': 1.028652723508161e-05, 'samples': 26196480, 'steps': 136439, 'loss/train': 0.8488497734069824} 08/31/2021 14:03:10 - INFO - __main__ - Step 136441: {'lr': 1.0285020704314835e-05, 'samples': 26196672, 'steps': 136440, 'loss/train': 0.24960961937904358} 08/31/2021 14:03:10 - INFO - __main__ - Step 136442: {'lr': 1.028351428155988e-05, 'samples': 26196864, 'steps': 136441, 'loss/train': 1.1271151304244995} 08/31/2021 14:03:11 - INFO - __main__ - Step 136443: {'lr': 1.028200796681747e-05, 'samples': 26197056, 'steps': 136442, 'loss/train': 0.9380797743797302} 08/31/2021 14:03:13 - INFO - __main__ - Step 136444: {'lr': 1.0280501760088295e-05, 'samples': 26197248, 'steps': 136443, 'loss/train': 0.7136439681053162} 08/31/2021 14:03:13 - INFO - __main__ - Step 136445: {'lr': 1.0278995661373024e-05, 'samples': 26197440, 'steps': 136444, 'loss/train': 1.1952104568481445} 08/31/2021 14:03:14 - INFO - __main__ - Step 136446: {'lr': 1.0277489670672352e-05, 'samples': 26197632, 'steps': 136445, 'loss/train': 1.136505365371704} 08/31/2021 14:03:14 - INFO - __main__ - Step 136447: {'lr': 1.0275983787986943e-05, 'samples': 26197824, 'steps': 136446, 'loss/train': 0.8545787930488586} 08/31/2021 14:03:14 - INFO - __main__ - Step 136448: {'lr': 1.0274478013317461e-05, 'samples': 26198016, 'steps': 136447, 'loss/train': 1.007612705230713} 08/31/2021 14:03:16 - INFO - __main__ - Step 136449: {'lr': 1.0272972346664605e-05, 'samples': 26198208, 'steps': 136448, 'loss/train': 0.7505235075950623} 08/31/2021 14:03:16 - INFO - __main__ - Step 136450: {'lr': 1.0271466788029066e-05, 'samples': 26198400, 'steps': 136449, 'loss/train': 0.4248427450656891} 08/31/2021 14:03:17 - INFO - __main__ - Step 136451: {'lr': 1.0269961337411482e-05, 'samples': 26198592, 'steps': 136450, 'loss/train': 1.0488598346710205} 08/31/2021 14:03:17 - INFO - __main__ - Step 136452: {'lr': 1.0268455994812604e-05, 'samples': 26198784, 'steps': 136451, 'loss/train': 0.6169531345367432} 08/31/2021 14:03:17 - INFO - __main__ - Step 136453: {'lr': 1.0266950760233012e-05, 'samples': 26198976, 'steps': 136452, 'loss/train': 0.6799143552780151} 08/31/2021 14:03:19 - INFO - __main__ - Step 136454: {'lr': 1.0265445633673432e-05, 'samples': 26199168, 'steps': 136453, 'loss/train': 1.0638200044631958} 08/31/2021 14:03:20 - INFO - __main__ - Step 136455: {'lr': 1.0263940615134553e-05, 'samples': 26199360, 'steps': 136454, 'loss/train': 0.032623451203107834} 08/31/2021 14:03:20 - INFO - __main__ - Step 136456: {'lr': 1.0262435704617045e-05, 'samples': 26199552, 'steps': 136455, 'loss/train': 1.7352687120437622} 08/31/2021 14:03:20 - INFO - __main__ - Step 136457: {'lr': 1.0260930902121574e-05, 'samples': 26199744, 'steps': 136456, 'loss/train': 1.415131688117981} 08/31/2021 14:03:21 - INFO - __main__ - Step 136458: {'lr': 1.0259426207648831e-05, 'samples': 26199936, 'steps': 136457, 'loss/train': 0.6289129257202148} 08/31/2021 14:03:22 - INFO - __main__ - Step 136459: {'lr': 1.0257921621199484e-05, 'samples': 26200128, 'steps': 136458, 'loss/train': 0.6586426496505737} 08/31/2021 14:03:23 - INFO - __main__ - Step 136460: {'lr': 1.0256417142774227e-05, 'samples': 26200320, 'steps': 136459, 'loss/train': 0.7191643118858337} 08/31/2021 14:03:23 - INFO - __main__ - Step 136461: {'lr': 1.0254912772373725e-05, 'samples': 26200512, 'steps': 136460, 'loss/train': 1.2197821140289307} 08/31/2021 14:03:23 - INFO - __main__ - Step 136462: {'lr': 1.0253408509998701e-05, 'samples': 26200704, 'steps': 136461, 'loss/train': 1.6730276346206665} 08/31/2021 14:03:24 - INFO - __main__ - Step 136463: {'lr': 1.0251904355649766e-05, 'samples': 26200896, 'steps': 136462, 'loss/train': 1.4744794368743896} 08/31/2021 14:03:26 - INFO - __main__ - Step 136464: {'lr': 1.0250400309327612e-05, 'samples': 26201088, 'steps': 136463, 'loss/train': 0.6038145422935486} 08/31/2021 14:03:26 - INFO - __main__ - Step 136465: {'lr': 1.0248896371032906e-05, 'samples': 26201280, 'steps': 136464, 'loss/train': 1.419873833656311} 08/31/2021 14:03:26 - INFO - __main__ - Step 136466: {'lr': 1.024739254076637e-05, 'samples': 26201472, 'steps': 136465, 'loss/train': 0.34478893876075745} 08/31/2021 14:03:27 - INFO - __main__ - Step 136467: {'lr': 1.0245888818528671e-05, 'samples': 26201664, 'steps': 136466, 'loss/train': 1.4210528135299683} 08/31/2021 14:03:27 - INFO - __main__ - Step 136468: {'lr': 1.0244385204320471e-05, 'samples': 26201856, 'steps': 136467, 'loss/train': 0.04124400019645691} 08/31/2021 14:03:29 - INFO - __main__ - Step 136469: {'lr': 1.0242881698142442e-05, 'samples': 26202048, 'steps': 136468, 'loss/train': 1.1335196495056152} 08/31/2021 14:03:29 - INFO - __main__ - Step 136470: {'lr': 1.0241378299995275e-05, 'samples': 26202240, 'steps': 136469, 'loss/train': 1.0446128845214844} 08/31/2021 14:03:29 - INFO - __main__ - Step 136471: {'lr': 1.0239875009879635e-05, 'samples': 26202432, 'steps': 136470, 'loss/train': 0.5249471068382263} 08/31/2021 14:03:30 - INFO - __main__ - Step 136472: {'lr': 1.0238371827796217e-05, 'samples': 26202624, 'steps': 136471, 'loss/train': 1.5904322862625122} 08/31/2021 14:03:30 - INFO - __main__ - Step 136473: {'lr': 1.0236868753745715e-05, 'samples': 26202816, 'steps': 136472, 'loss/train': 1.6761748790740967} 08/31/2021 14:03:31 - INFO - __main__ - Step 136474: {'lr': 1.023536578772874e-05, 'samples': 26203008, 'steps': 136473, 'loss/train': 1.0273960828781128} 08/31/2021 14:03:32 - INFO - __main__ - Step 136475: {'lr': 1.0233862929746012e-05, 'samples': 26203200, 'steps': 136474, 'loss/train': 1.0033047199249268} 08/31/2021 14:03:33 - INFO - __main__ - Step 136476: {'lr': 1.0232360179798228e-05, 'samples': 26203392, 'steps': 136475, 'loss/train': 1.6463266611099243} 08/31/2021 14:03:33 - INFO - __main__ - Step 136477: {'lr': 1.0230857537886023e-05, 'samples': 26203584, 'steps': 136476, 'loss/train': 0.8079096674919128} 08/31/2021 14:03:33 - INFO - __main__ - Step 136478: {'lr': 1.0229355004010094e-05, 'samples': 26203776, 'steps': 136477, 'loss/train': 0.8109112977981567} 08/31/2021 14:03:34 - INFO - __main__ - Step 136479: {'lr': 1.0227852578171132e-05, 'samples': 26203968, 'steps': 136478, 'loss/train': 1.2174129486083984} 08/31/2021 14:03:35 - INFO - __main__ - Step 136480: {'lr': 1.0226350260369777e-05, 'samples': 26204160, 'steps': 136479, 'loss/train': 0.8869197964668274} 08/31/2021 14:03:36 - INFO - __main__ - Step 136481: {'lr': 1.022484805060675e-05, 'samples': 26204352, 'steps': 136480, 'loss/train': 1.0063902139663696} 08/31/2021 14:03:36 - INFO - __main__ - Step 136482: {'lr': 1.022334594888269e-05, 'samples': 26204544, 'steps': 136481, 'loss/train': 0.7599234580993652} 08/31/2021 14:03:37 - INFO - __main__ - Step 136483: {'lr': 1.022184395519829e-05, 'samples': 26204736, 'steps': 136482, 'loss/train': 0.9294202923774719} 08/31/2021 14:03:37 - INFO - __main__ - Step 136484: {'lr': 1.0220342069554272e-05, 'samples': 26204928, 'steps': 136483, 'loss/train': 1.3185856342315674} 08/31/2021 14:03:38 - INFO - __main__ - Step 136485: {'lr': 1.021884029195122e-05, 'samples': 26205120, 'steps': 136484, 'loss/train': 0.749701976776123} 08/31/2021 14:03:39 - INFO - __main__ - Step 136486: {'lr': 1.0217338622389883e-05, 'samples': 26205312, 'steps': 136485, 'loss/train': 1.167492389678955} 08/31/2021 14:03:39 - INFO - __main__ - Step 136487: {'lr': 1.0215837060870897e-05, 'samples': 26205504, 'steps': 136486, 'loss/train': 0.950930655002594} 08/31/2021 14:03:40 - INFO - __main__ - Step 136488: {'lr': 1.0214335607394959e-05, 'samples': 26205696, 'steps': 136487, 'loss/train': 1.4573984146118164} 08/31/2021 14:03:40 - INFO - __main__ - Step 136489: {'lr': 1.0212834261962733e-05, 'samples': 26205888, 'steps': 136488, 'loss/train': 1.1160959005355835} 08/31/2021 14:03:41 - INFO - __main__ - Step 136490: {'lr': 1.0211333024574915e-05, 'samples': 26206080, 'steps': 136489, 'loss/train': 0.7142633199691772} 08/31/2021 14:03:42 - INFO - __main__ - Step 136491: {'lr': 1.020983189523217e-05, 'samples': 26206272, 'steps': 136490, 'loss/train': 1.453456997871399} 08/31/2021 14:03:42 - INFO - __main__ - Step 136492: {'lr': 1.0208330873935161e-05, 'samples': 26206464, 'steps': 136491, 'loss/train': 0.05121898651123047} 08/31/2021 14:03:43 - INFO - __main__ - Step 136493: {'lr': 1.0206829960684589e-05, 'samples': 26206656, 'steps': 136492, 'loss/train': 0.8468356132507324} 08/31/2021 14:03:43 - INFO - __main__ - Step 136494: {'lr': 1.0205329155481113e-05, 'samples': 26206848, 'steps': 136493, 'loss/train': 1.1011344194412231} 08/31/2021 14:03:45 - INFO - __main__ - Step 136495: {'lr': 1.0203828458325432e-05, 'samples': 26207040, 'steps': 136494, 'loss/train': 1.100773811340332} 08/31/2021 14:03:45 - INFO - __main__ - Step 136496: {'lr': 1.0202327869218208e-05, 'samples': 26207232, 'steps': 136495, 'loss/train': 0.4458937644958496} 08/31/2021 14:03:46 - INFO - __main__ - Step 136497: {'lr': 1.0200827388160112e-05, 'samples': 26207424, 'steps': 136496, 'loss/train': 1.0853848457336426} 08/31/2021 14:03:46 - INFO - __main__ - Step 136498: {'lr': 1.0199327015151805e-05, 'samples': 26207616, 'steps': 136497, 'loss/train': 1.4562125205993652} 08/31/2021 14:03:46 - INFO - __main__ - Step 136499: {'lr': 1.0197826750193983e-05, 'samples': 26207808, 'steps': 136498, 'loss/train': 0.9034256339073181} 08/31/2021 14:03:47 - INFO - __main__ - Step 136500: {'lr': 1.0196326593287342e-05, 'samples': 26208000, 'steps': 136499, 'loss/train': 1.4713256359100342} 08/31/2021 14:03:49 - INFO - __main__ - Step 136501: {'lr': 1.0194826544432518e-05, 'samples': 26208192, 'steps': 136500, 'loss/train': 1.7700139284133911} 08/31/2021 14:03:49 - INFO - __main__ - Step 136502: {'lr': 1.0193326603630204e-05, 'samples': 26208384, 'steps': 136501, 'loss/train': 5.455822944641113} 08/31/2021 14:03:50 - INFO - __main__ - Step 136503: {'lr': 1.019182677088107e-05, 'samples': 26208576, 'steps': 136502, 'loss/train': 0.9989402294158936} 08/31/2021 14:03:50 - INFO - __main__ - Step 136504: {'lr': 1.0190327046185805e-05, 'samples': 26208768, 'steps': 136503, 'loss/train': 1.303774356842041} 08/31/2021 14:03:50 - INFO - __main__ - Step 136505: {'lr': 1.0188827429545078e-05, 'samples': 26208960, 'steps': 136504, 'loss/train': 1.6719279289245605} 08/31/2021 14:03:52 - INFO - __main__ - Step 136506: {'lr': 1.0187327920959556e-05, 'samples': 26209152, 'steps': 136505, 'loss/train': 1.0519665479660034} 08/31/2021 14:03:53 - INFO - __main__ - Step 136507: {'lr': 1.018582852042993e-05, 'samples': 26209344, 'steps': 136506, 'loss/train': 1.260338306427002} 08/31/2021 14:03:53 - INFO - __main__ - Step 136508: {'lr': 1.0184329227956867e-05, 'samples': 26209536, 'steps': 136507, 'loss/train': 0.35673263669013977} 08/31/2021 14:03:53 - INFO - __main__ - Step 136509: {'lr': 1.0182830043541063e-05, 'samples': 26209728, 'steps': 136508, 'loss/train': 1.136867880821228} 08/31/2021 14:03:54 - INFO - __main__ - Step 136510: {'lr': 1.0181330967183184e-05, 'samples': 26209920, 'steps': 136509, 'loss/train': 1.2389683723449707} 08/31/2021 14:03:56 - INFO - __main__ - Step 136511: {'lr': 1.0179831998883893e-05, 'samples': 26210112, 'steps': 136510, 'loss/train': 1.044731616973877} 08/31/2021 14:03:56 - INFO - __main__ - Step 136512: {'lr': 1.017833313864383e-05, 'samples': 26210304, 'steps': 136511, 'loss/train': 1.3969075679779053} 08/31/2021 14:03:57 - INFO - __main__ - Step 136513: {'lr': 1.0176834386463746e-05, 'samples': 26210496, 'steps': 136512, 'loss/train': 1.1076133251190186} 08/31/2021 14:03:57 - INFO - __main__ - Step 136514: {'lr': 1.0175335742344249e-05, 'samples': 26210688, 'steps': 136513, 'loss/train': 1.2812894582748413} 08/31/2021 14:03:57 - INFO - __main__ - Step 136515: {'lr': 1.0173837206286064e-05, 'samples': 26210880, 'steps': 136514, 'loss/train': 1.2376506328582764} 08/31/2021 14:03:58 - INFO - __main__ - Step 136516: {'lr': 1.0172338778289852e-05, 'samples': 26211072, 'steps': 136515, 'loss/train': 0.8790979385375977} 08/31/2021 14:03:59 - INFO - __main__ - Step 136517: {'lr': 1.0170840458356257e-05, 'samples': 26211264, 'steps': 136516, 'loss/train': 1.2912956476211548} 08/31/2021 14:04:00 - INFO - __main__ - Step 136518: {'lr': 1.0169342246485996e-05, 'samples': 26211456, 'steps': 136517, 'loss/train': 1.5647732019424438} 08/31/2021 14:04:00 - INFO - __main__ - Step 136519: {'lr': 1.0167844142679739e-05, 'samples': 26211648, 'steps': 136518, 'loss/train': 1.1692687273025513} 08/31/2021 14:04:00 - INFO - __main__ - Step 136520: {'lr': 1.016634614693815e-05, 'samples': 26211840, 'steps': 136519, 'loss/train': 0.9978710412979126} 08/31/2021 14:04:01 - INFO - __main__ - Step 136521: {'lr': 1.0164848259261894e-05, 'samples': 26212032, 'steps': 136520, 'loss/train': 1.4409964084625244} 08/31/2021 14:04:02 - INFO - __main__ - Step 136522: {'lr': 1.0163350479651668e-05, 'samples': 26212224, 'steps': 136521, 'loss/train': 0.8107253909111023} 08/31/2021 14:04:03 - INFO - __main__ - Step 136523: {'lr': 1.0161852808108135e-05, 'samples': 26212416, 'steps': 136522, 'loss/train': 1.3964564800262451} 08/31/2021 14:04:03 - INFO - __main__ - Step 136524: {'lr': 1.0160355244631964e-05, 'samples': 26212608, 'steps': 136523, 'loss/train': 1.3129336833953857} 08/31/2021 14:04:04 - INFO - __main__ - Step 136525: {'lr': 1.0158857789223846e-05, 'samples': 26212800, 'steps': 136524, 'loss/train': 1.6677703857421875} 08/31/2021 14:04:04 - INFO - __main__ - Step 136526: {'lr': 1.0157360441884423e-05, 'samples': 26212992, 'steps': 136525, 'loss/train': 1.2037206888198853} 08/31/2021 14:04:04 - INFO - __main__ - Step 136527: {'lr': 1.0155863202614412e-05, 'samples': 26213184, 'steps': 136526, 'loss/train': 1.2594587802886963} 08/31/2021 14:04:06 - INFO - __main__ - Step 136528: {'lr': 1.0154366071414457e-05, 'samples': 26213376, 'steps': 136527, 'loss/train': 0.9551183581352234} 08/31/2021 14:04:06 - INFO - __main__ - Step 136529: {'lr': 1.0152869048285246e-05, 'samples': 26213568, 'steps': 136528, 'loss/train': 1.776771903038025} 08/31/2021 14:04:07 - INFO - __main__ - Step 136530: {'lr': 1.0151372133227448e-05, 'samples': 26213760, 'steps': 136529, 'loss/train': 1.003071665763855} 08/31/2021 14:04:07 - INFO - __main__ - Step 136531: {'lr': 1.014987532624173e-05, 'samples': 26213952, 'steps': 136530, 'loss/train': 1.305384635925293} 08/31/2021 14:04:07 - INFO - __main__ - Step 136532: {'lr': 1.0148378627328787e-05, 'samples': 26214144, 'steps': 136531, 'loss/train': 0.7709901332855225} 08/31/2021 14:04:09 - INFO - __main__ - Step 136533: {'lr': 1.0146882036489307e-05, 'samples': 26214336, 'steps': 136532, 'loss/train': 0.1385444700717926} 08/31/2021 14:04:09 - INFO - __main__ - Step 136534: {'lr': 1.0145385553723906e-05, 'samples': 26214528, 'steps': 136533, 'loss/train': 0.6255732178688049} 08/31/2021 14:04:10 - INFO - __main__ - Step 136535: {'lr': 1.0143889179033305e-05, 'samples': 26214720, 'steps': 136534, 'loss/train': 1.021672248840332} 08/31/2021 14:04:10 - INFO - __main__ - Step 136536: {'lr': 1.014239291241817e-05, 'samples': 26214912, 'steps': 136535, 'loss/train': 0.9456694722175598} 08/31/2021 14:04:10 - INFO - __main__ - Step 136537: {'lr': 1.014089675387922e-05, 'samples': 26215104, 'steps': 136536, 'loss/train': 1.155620813369751} 08/31/2021 14:04:12 - INFO - __main__ - Step 136538: {'lr': 1.0139400703417012e-05, 'samples': 26215296, 'steps': 136537, 'loss/train': 1.451562523841858} 08/31/2021 14:04:12 - INFO - __main__ - Step 136539: {'lr': 1.0137904761032324e-05, 'samples': 26215488, 'steps': 136538, 'loss/train': 0.7212120890617371} 08/31/2021 14:04:13 - INFO - __main__ - Step 136540: {'lr': 1.0136408926725765e-05, 'samples': 26215680, 'steps': 136539, 'loss/train': 1.2692562341690063} 08/31/2021 14:04:13 - INFO - __main__ - Step 136541: {'lr': 1.0134913200498058e-05, 'samples': 26215872, 'steps': 136540, 'loss/train': 1.1419048309326172} 08/31/2021 14:04:13 - INFO - __main__ - Step 136542: {'lr': 1.013341758234984e-05, 'samples': 26216064, 'steps': 136541, 'loss/train': 0.9499338269233704} 08/31/2021 14:04:15 - INFO - __main__ - Step 136543: {'lr': 1.0131922072281835e-05, 'samples': 26216256, 'steps': 136542, 'loss/train': 0.9621681571006775} 08/31/2021 14:04:15 - INFO - __main__ - Step 136544: {'lr': 1.013042667029465e-05, 'samples': 26216448, 'steps': 136543, 'loss/train': 0.934658944606781} 08/31/2021 14:04:16 - INFO - __main__ - Step 136545: {'lr': 1.0128931376389011e-05, 'samples': 26216640, 'steps': 136544, 'loss/train': 0.9893600344657898} 08/31/2021 14:04:16 - INFO - __main__ - Step 136546: {'lr': 1.0127436190565582e-05, 'samples': 26216832, 'steps': 136545, 'loss/train': 0.7939550876617432} 08/31/2021 14:04:16 - INFO - __main__ - Step 136547: {'lr': 1.0125941112824998e-05, 'samples': 26217024, 'steps': 136546, 'loss/train': 1.3097494840621948} 08/31/2021 14:04:17 - INFO - __main__ - Step 136548: {'lr': 1.0124446143167987e-05, 'samples': 26217216, 'steps': 136547, 'loss/train': 0.7046290040016174} 08/31/2021 14:04:18 - INFO - __main__ - Step 136549: {'lr': 1.0122951281595182e-05, 'samples': 26217408, 'steps': 136548, 'loss/train': 1.233162760734558} 08/31/2021 14:04:19 - INFO - __main__ - Step 136550: {'lr': 1.0121456528107337e-05, 'samples': 26217600, 'steps': 136549, 'loss/train': 1.3383594751358032} 08/31/2021 14:04:19 - INFO - __main__ - Step 136551: {'lr': 1.0119961882705003e-05, 'samples': 26217792, 'steps': 136550, 'loss/train': 1.1352863311767578} 08/31/2021 14:04:19 - INFO - __main__ - Step 136552: {'lr': 1.0118467345388932e-05, 'samples': 26217984, 'steps': 136551, 'loss/train': 1.257391095161438} 08/31/2021 14:04:21 - INFO - __main__ - Step 136553: {'lr': 1.0116972916159762e-05, 'samples': 26218176, 'steps': 136552, 'loss/train': 1.3488185405731201} 08/31/2021 14:04:21 - INFO - __main__ - Step 136554: {'lr': 1.0115478595018185e-05, 'samples': 26218368, 'steps': 136553, 'loss/train': 1.2888450622558594} 08/31/2021 14:04:22 - INFO - __main__ - Step 136555: {'lr': 1.0113984381964869e-05, 'samples': 26218560, 'steps': 136554, 'loss/train': 1.2992256879806519} 08/31/2021 14:04:22 - INFO - __main__ - Step 136556: {'lr': 1.0112490277000509e-05, 'samples': 26218752, 'steps': 136555, 'loss/train': 0.8097231984138489} 08/31/2021 14:04:22 - INFO - __main__ - Step 136557: {'lr': 1.011099628012574e-05, 'samples': 26218944, 'steps': 136556, 'loss/train': 1.4365367889404297} 08/31/2021 14:04:23 - INFO - __main__ - Step 136558: {'lr': 1.0109502391341257e-05, 'samples': 26219136, 'steps': 136557, 'loss/train': 1.274813175201416} 08/31/2021 14:04:25 - INFO - __main__ - Step 136559: {'lr': 1.0108008610647728e-05, 'samples': 26219328, 'steps': 136558, 'loss/train': 1.8773623704910278} 08/31/2021 14:04:26 - INFO - __main__ - Step 136560: {'lr': 1.0106514938045847e-05, 'samples': 26219520, 'steps': 136559, 'loss/train': 0.9553374648094177} 08/31/2021 14:04:26 - INFO - __main__ - Step 136561: {'lr': 1.0105021373536249e-05, 'samples': 26219712, 'steps': 136560, 'loss/train': 1.2261115312576294} 08/31/2021 14:04:26 - INFO - __main__ - Step 136562: {'lr': 1.0103527917119631e-05, 'samples': 26219904, 'steps': 136561, 'loss/train': 0.6499291062355042} 08/31/2021 14:04:27 - INFO - __main__ - Step 136563: {'lr': 1.0102034568796687e-05, 'samples': 26220096, 'steps': 136562, 'loss/train': 0.5586310625076294} 08/31/2021 14:04:28 - INFO - __main__ - Step 136564: {'lr': 1.0100541328568053e-05, 'samples': 26220288, 'steps': 136563, 'loss/train': 1.3737672567367554} 08/31/2021 14:04:29 - INFO - __main__ - Step 136565: {'lr': 1.0099048196434397e-05, 'samples': 26220480, 'steps': 136564, 'loss/train': 1.064280390739441} 08/31/2021 14:04:29 - INFO - __main__ - Step 136566: {'lr': 1.009755517239641e-05, 'samples': 26220672, 'steps': 136565, 'loss/train': 0.9447168111801147} 08/31/2021 14:04:29 - INFO - __main__ - Step 136567: {'lr': 1.0096062256454764e-05, 'samples': 26220864, 'steps': 136566, 'loss/train': 0.9349693655967712} 08/31/2021 14:04:30 - INFO - __main__ - Step 136568: {'lr': 1.009456944861012e-05, 'samples': 26221056, 'steps': 136567, 'loss/train': 0.9513518214225769} 08/31/2021 14:04:31 - INFO - __main__ - Step 136569: {'lr': 1.0093076748863173e-05, 'samples': 26221248, 'steps': 136568, 'loss/train': 1.4662489891052246} 08/31/2021 14:04:32 - INFO - __main__ - Step 136570: {'lr': 1.009158415721459e-05, 'samples': 26221440, 'steps': 136569, 'loss/train': 1.3168777227401733} 08/31/2021 14:04:32 - INFO - __main__ - Step 136571: {'lr': 1.0090091673665036e-05, 'samples': 26221632, 'steps': 136570, 'loss/train': 1.2467280626296997} 08/31/2021 14:04:32 - INFO - __main__ - Step 136572: {'lr': 1.0088599298215179e-05, 'samples': 26221824, 'steps': 136571, 'loss/train': 0.7248453497886658} 08/31/2021 14:04:33 - INFO - __main__ - Step 136573: {'lr': 1.0087107030865684e-05, 'samples': 26222016, 'steps': 136572, 'loss/train': 1.2164220809936523} 08/31/2021 14:04:34 - INFO - __main__ - Step 136574: {'lr': 1.0085614871617271e-05, 'samples': 26222208, 'steps': 136573, 'loss/train': 0.8850929141044617} 08/31/2021 14:04:35 - INFO - __main__ - Step 136575: {'lr': 1.0084122820470554e-05, 'samples': 26222400, 'steps': 136574, 'loss/train': 0.6061335206031799} 08/31/2021 14:04:35 - INFO - __main__ - Step 136576: {'lr': 1.0082630877426224e-05, 'samples': 26222592, 'steps': 136575, 'loss/train': 0.9463880062103271} 08/31/2021 14:04:36 - INFO - __main__ - Step 136577: {'lr': 1.0081139042485005e-05, 'samples': 26222784, 'steps': 136576, 'loss/train': 0.031333040446043015} 08/31/2021 14:04:36 - INFO - __main__ - Step 136578: {'lr': 1.0079647315647478e-05, 'samples': 26222976, 'steps': 136577, 'loss/train': 1.159293293952942} 08/31/2021 14:04:38 - INFO - __main__ - Step 136579: {'lr': 1.0078155696914365e-05, 'samples': 26223168, 'steps': 136578, 'loss/train': 0.7756202220916748} 08/31/2021 14:04:38 - INFO - __main__ - Step 136580: {'lr': 1.0076664186286333e-05, 'samples': 26223360, 'steps': 136579, 'loss/train': 2.4103901386260986} 08/31/2021 14:04:38 - INFO - __main__ - Step 136581: {'lr': 1.0075172783764048e-05, 'samples': 26223552, 'steps': 136580, 'loss/train': 1.2353628873825073} 08/31/2021 14:04:39 - INFO - __main__ - Step 136582: {'lr': 1.0073681489348202e-05, 'samples': 26223744, 'steps': 136581, 'loss/train': 1.5478453636169434} 08/31/2021 14:04:39 - INFO - __main__ - Step 136583: {'lr': 1.0072190303039436e-05, 'samples': 26223936, 'steps': 136582, 'loss/train': 0.328782856464386} 08/31/2021 14:04:39 - INFO - __main__ - Step 136584: {'lr': 1.0070699224838442e-05, 'samples': 26224128, 'steps': 136583, 'loss/train': 1.1373940706253052} 08/31/2021 14:04:41 - INFO - __main__ - Step 136585: {'lr': 1.0069208254745888e-05, 'samples': 26224320, 'steps': 136584, 'loss/train': 0.8491857051849365} 08/31/2021 14:04:42 - INFO - __main__ - Step 136586: {'lr': 1.0067717392762466e-05, 'samples': 26224512, 'steps': 136585, 'loss/train': 1.1053756475448608} 08/31/2021 14:04:42 - INFO - __main__ - Step 136587: {'lr': 1.0066226638888815e-05, 'samples': 26224704, 'steps': 136586, 'loss/train': 1.2844377756118774} 08/31/2021 14:04:42 - INFO - __main__ - Step 136588: {'lr': 1.0064735993125601e-05, 'samples': 26224896, 'steps': 136587, 'loss/train': 1.0708253383636475} 08/31/2021 14:04:43 - INFO - __main__ - Step 136589: {'lr': 1.0063245455473546e-05, 'samples': 26225088, 'steps': 136588, 'loss/train': 0.5286826491355896} 08/31/2021 14:04:45 - INFO - __main__ - Step 136590: {'lr': 1.0061755025933317e-05, 'samples': 26225280, 'steps': 136589, 'loss/train': 1.6468628644943237} 08/31/2021 14:04:45 - INFO - __main__ - Step 136591: {'lr': 1.0060264704505496e-05, 'samples': 26225472, 'steps': 136590, 'loss/train': 1.114456295967102} 08/31/2021 14:04:46 - INFO - __main__ - Step 136592: {'lr': 1.0058774491190859e-05, 'samples': 26225664, 'steps': 136591, 'loss/train': 0.7507435083389282} 08/31/2021 14:04:46 - INFO - __main__ - Step 136593: {'lr': 1.0057284385990018e-05, 'samples': 26225856, 'steps': 136592, 'loss/train': 1.1547800302505493} 08/31/2021 14:04:46 - INFO - __main__ - Step 136594: {'lr': 1.005579438890364e-05, 'samples': 26226048, 'steps': 136593, 'loss/train': 0.9327291250228882} 08/31/2021 14:04:47 - INFO - __main__ - Step 136595: {'lr': 1.0054304499932443e-05, 'samples': 26226240, 'steps': 136594, 'loss/train': 2.599881887435913} 08/31/2021 14:04:47 - INFO - __main__ - Step 136596: {'lr': 1.0052814719077068e-05, 'samples': 26226432, 'steps': 136595, 'loss/train': 2.5296683311462402} 08/31/2021 14:04:49 - INFO - __main__ - Step 136597: {'lr': 1.0051325046338211e-05, 'samples': 26226624, 'steps': 136596, 'loss/train': 2.1563313007354736} 08/31/2021 14:04:49 - INFO - __main__ - Step 136598: {'lr': 1.0049835481716508e-05, 'samples': 26226816, 'steps': 136597, 'loss/train': 0.7986522912979126} 08/31/2021 14:04:50 - INFO - __main__ - Step 136599: {'lr': 1.0048346025212624e-05, 'samples': 26227008, 'steps': 136598, 'loss/train': 1.8620343208312988} 08/31/2021 14:04:50 - INFO - __main__ - Step 136600: {'lr': 1.0046856676827282e-05, 'samples': 26227200, 'steps': 136599, 'loss/train': 1.1881637573242188} 08/31/2021 14:04:50 - INFO - __main__ - Step 136601: {'lr': 1.004536743656112e-05, 'samples': 26227392, 'steps': 136600, 'loss/train': 0.10765385627746582} 08/31/2021 14:04:52 - INFO - __main__ - Step 136602: {'lr': 1.0043878304414805e-05, 'samples': 26227584, 'steps': 136601, 'loss/train': 0.6534295082092285} 08/31/2021 14:04:52 - INFO - __main__ - Step 136603: {'lr': 1.0042389280389031e-05, 'samples': 26227776, 'steps': 136602, 'loss/train': 0.14382430911064148} 08/31/2021 14:04:52 - INFO - __main__ - Step 136604: {'lr': 1.0040900364484461e-05, 'samples': 26227968, 'steps': 136603, 'loss/train': 1.7604540586471558} 08/31/2021 14:04:53 - INFO - __main__ - Step 136605: {'lr': 1.0039411556701738e-05, 'samples': 26228160, 'steps': 136604, 'loss/train': 1.1881554126739502} 08/31/2021 14:04:53 - INFO - __main__ - Step 136606: {'lr': 1.0037922857041554e-05, 'samples': 26228352, 'steps': 136605, 'loss/train': 0.9805086255073547} 08/31/2021 14:04:55 - INFO - __main__ - Step 136607: {'lr': 1.0036434265504574e-05, 'samples': 26228544, 'steps': 136606, 'loss/train': 1.4503308534622192} 08/31/2021 14:04:55 - INFO - __main__ - Step 136608: {'lr': 1.0034945782091493e-05, 'samples': 26228736, 'steps': 136607, 'loss/train': 0.431039035320282} 08/31/2021 14:04:56 - INFO - __main__ - Step 136609: {'lr': 1.0033457406802949e-05, 'samples': 26228928, 'steps': 136608, 'loss/train': 1.1363935470581055} 08/31/2021 14:04:56 - INFO - __main__ - Step 136610: {'lr': 1.0031969139639636e-05, 'samples': 26229120, 'steps': 136609, 'loss/train': 1.0440303087234497} 08/31/2021 14:04:56 - INFO - __main__ - Step 136611: {'lr': 1.0030480980602191e-05, 'samples': 26229312, 'steps': 136610, 'loss/train': 1.0901638269424438} 08/31/2021 14:04:58 - INFO - __main__ - Step 136612: {'lr': 1.0028992929691338e-05, 'samples': 26229504, 'steps': 136611, 'loss/train': 1.1313732862472534} 08/31/2021 14:04:58 - INFO - __main__ - Step 136613: {'lr': 1.0027504986907687e-05, 'samples': 26229696, 'steps': 136612, 'loss/train': 0.41895967721939087} 08/31/2021 14:04:59 - INFO - __main__ - Step 136614: {'lr': 1.002601715225196e-05, 'samples': 26229888, 'steps': 136613, 'loss/train': 1.15733003616333} 08/31/2021 14:04:59 - INFO - __main__ - Step 136615: {'lr': 1.0024529425724793e-05, 'samples': 26230080, 'steps': 136614, 'loss/train': 1.270963430404663} 08/31/2021 14:04:59 - INFO - __main__ - Step 136616: {'lr': 1.0023041807326883e-05, 'samples': 26230272, 'steps': 136615, 'loss/train': 1.7295763492584229} 08/31/2021 14:05:00 - INFO - __main__ - Step 136617: {'lr': 1.0021554297058922e-05, 'samples': 26230464, 'steps': 136616, 'loss/train': 0.38596493005752563} 08/31/2021 14:05:02 - INFO - __main__ - Step 136618: {'lr': 1.0020066894921493e-05, 'samples': 26230656, 'steps': 136617, 'loss/train': 0.9236137270927429} 08/31/2021 14:05:02 - INFO - __main__ - Step 136619: {'lr': 1.0018579600915346e-05, 'samples': 26230848, 'steps': 136618, 'loss/train': 0.6599118113517761} 08/31/2021 14:05:03 - INFO - __main__ - Step 136620: {'lr': 1.001709241504109e-05, 'samples': 26231040, 'steps': 136619, 'loss/train': 0.03331705555319786} 08/31/2021 14:05:03 - INFO - __main__ - Step 136621: {'lr': 1.001560533729945e-05, 'samples': 26231232, 'steps': 136620, 'loss/train': 1.0813692808151245} 08/31/2021 14:05:03 - INFO - __main__ - Step 136622: {'lr': 1.0014118367691089e-05, 'samples': 26231424, 'steps': 136621, 'loss/train': 0.13339106738567352} 08/31/2021 14:05:05 - INFO - __main__ - Step 136623: {'lr': 1.0012631506216647e-05, 'samples': 26231616, 'steps': 136622, 'loss/train': 0.30811694264411926} 08/31/2021 14:05:05 - INFO - __main__ - Step 136624: {'lr': 1.0011144752876816e-05, 'samples': 26231808, 'steps': 136623, 'loss/train': 0.8818438649177551} 08/31/2021 14:05:06 - INFO - __main__ - Step 136625: {'lr': 1.0009658107672237e-05, 'samples': 26232000, 'steps': 136624, 'loss/train': 0.9789721369743347} 08/31/2021 14:05:06 - INFO - __main__ - Step 136626: {'lr': 1.000817157060363e-05, 'samples': 26232192, 'steps': 136625, 'loss/train': 1.3122243881225586} 08/31/2021 14:05:06 - INFO - __main__ - Step 136627: {'lr': 1.0006685141671635e-05, 'samples': 26232384, 'steps': 136626, 'loss/train': 0.6785145998001099} 08/31/2021 14:05:08 - INFO - __main__ - Step 136628: {'lr': 1.0005198820876915e-05, 'samples': 26232576, 'steps': 136627, 'loss/train': 0.44234830141067505} 08/31/2021 14:05:09 - INFO - __main__ - Step 136629: {'lr': 1.000371260822014e-05, 'samples': 26232768, 'steps': 136628, 'loss/train': 1.49875807762146} 08/31/2021 14:05:09 - INFO - __main__ - Step 136630: {'lr': 1.0002226503702e-05, 'samples': 26232960, 'steps': 136629, 'loss/train': 0.25595515966415405} 08/31/2021 14:05:09 - INFO - __main__ - Step 136631: {'lr': 1.000074050732319e-05, 'samples': 26233152, 'steps': 136630, 'loss/train': 1.130332350730896} 08/31/2021 14:05:10 - INFO - __main__ - Step 136632: {'lr': 9.999254619084298e-06, 'samples': 26233344, 'steps': 136631, 'loss/train': 1.3278001546859741} 08/31/2021 14:05:10 - INFO - __main__ - Step 136633: {'lr': 9.997768838986065e-06, 'samples': 26233536, 'steps': 136632, 'loss/train': 0.6219220757484436} 08/31/2021 14:05:12 - INFO - __main__ - Step 136634: {'lr': 9.996283167029108e-06, 'samples': 26233728, 'steps': 136633, 'loss/train': 0.8788846135139465} 08/31/2021 14:05:12 - INFO - __main__ - Step 136635: {'lr': 9.994797603214117e-06, 'samples': 26233920, 'steps': 136634, 'loss/train': 1.6386970281600952} 08/31/2021 14:05:13 - INFO - __main__ - Step 136636: {'lr': 9.993312147541788e-06, 'samples': 26234112, 'steps': 136635, 'loss/train': 0.7509484887123108} 08/31/2021 14:05:13 - INFO - __main__ - Step 136637: {'lr': 9.99182680001276e-06, 'samples': 26234304, 'steps': 136636, 'loss/train': 0.3366551995277405} 08/31/2021 14:05:13 - INFO - __main__ - Step 136638: {'lr': 9.990341560627725e-06, 'samples': 26234496, 'steps': 136637, 'loss/train': 0.7065273523330688} 08/31/2021 14:05:15 - INFO - __main__ - Step 136639: {'lr': 9.988856429387321e-06, 'samples': 26234688, 'steps': 136638, 'loss/train': 1.252336025238037} 08/31/2021 14:05:15 - INFO - __main__ - Step 136640: {'lr': 9.987371406292244e-06, 'samples': 26234880, 'steps': 136639, 'loss/train': 1.3899873495101929} 08/31/2021 14:05:16 - INFO - __main__ - Step 136641: {'lr': 9.985886491343132e-06, 'samples': 26235072, 'steps': 136640, 'loss/train': 0.3321404457092285} 08/31/2021 14:05:16 - INFO - __main__ - Step 136642: {'lr': 9.984401684540706e-06, 'samples': 26235264, 'steps': 136641, 'loss/train': 1.2217687368392944} 08/31/2021 14:05:16 - INFO - __main__ - Step 136643: {'lr': 9.982916985885575e-06, 'samples': 26235456, 'steps': 136642, 'loss/train': 1.5178114175796509} 08/31/2021 14:05:18 - INFO - __main__ - Step 136644: {'lr': 9.981432395378493e-06, 'samples': 26235648, 'steps': 136643, 'loss/train': 1.3082524538040161} 08/31/2021 14:05:18 - INFO - __main__ - Step 136645: {'lr': 9.979947913020037e-06, 'samples': 26235840, 'steps': 136644, 'loss/train': 0.7629178762435913} 08/31/2021 14:05:19 - INFO - __main__ - Step 136646: {'lr': 9.978463538810905e-06, 'samples': 26236032, 'steps': 136645, 'loss/train': 1.3258544206619263} 08/31/2021 14:05:19 - INFO - __main__ - Step 136647: {'lr': 9.97697927275179e-06, 'samples': 26236224, 'steps': 136646, 'loss/train': 1.129543662071228} 08/31/2021 14:05:19 - INFO - __main__ - Step 136648: {'lr': 9.97549511484333e-06, 'samples': 26236416, 'steps': 136647, 'loss/train': 0.9325290322303772} 08/31/2021 14:05:21 - INFO - __main__ - Step 136649: {'lr': 9.97401106508622e-06, 'samples': 26236608, 'steps': 136648, 'loss/train': 1.4600175619125366} 08/31/2021 14:05:21 - INFO - __main__ - Step 136650: {'lr': 9.972527123481122e-06, 'samples': 26236800, 'steps': 136649, 'loss/train': 0.7983577251434326} 08/31/2021 14:05:22 - INFO - __main__ - Step 136651: {'lr': 9.971043290028681e-06, 'samples': 26236992, 'steps': 136650, 'loss/train': 1.1504448652267456} 08/31/2021 14:05:22 - INFO - __main__ - Step 136652: {'lr': 9.969559564729586e-06, 'samples': 26237184, 'steps': 136651, 'loss/train': 1.2583171129226685} 08/31/2021 14:05:23 - INFO - __main__ - Step 136653: {'lr': 9.968075947584503e-06, 'samples': 26237376, 'steps': 136652, 'loss/train': 1.1277081966400146} 08/31/2021 14:05:23 - INFO - __main__ - Step 136654: {'lr': 9.966592438594102e-06, 'samples': 26237568, 'steps': 136653, 'loss/train': 1.0428555011749268} 08/31/2021 14:05:25 - INFO - __main__ - Step 136655: {'lr': 9.965109037759045e-06, 'samples': 26237760, 'steps': 136654, 'loss/train': 1.300328254699707} 08/31/2021 14:05:25 - INFO - __main__ - Step 136656: {'lr': 9.963625745080029e-06, 'samples': 26237952, 'steps': 136655, 'loss/train': 0.9909394383430481} 08/31/2021 14:05:25 - INFO - __main__ - Step 136657: {'lr': 9.96214256055769e-06, 'samples': 26238144, 'steps': 136656, 'loss/train': 1.0197746753692627} 08/31/2021 14:05:26 - INFO - __main__ - Step 136658: {'lr': 9.960659484192724e-06, 'samples': 26238336, 'steps': 136657, 'loss/train': 0.9372568726539612} 08/31/2021 14:05:26 - INFO - __main__ - Step 136659: {'lr': 9.959176515985768e-06, 'samples': 26238528, 'steps': 136658, 'loss/train': 0.24530033767223358} 08/31/2021 14:05:28 - INFO - __main__ - Step 136660: {'lr': 9.957693655937488e-06, 'samples': 26238720, 'steps': 136659, 'loss/train': 0.8714911341667175} 08/31/2021 14:05:28 - INFO - __main__ - Step 136661: {'lr': 9.95621090404858e-06, 'samples': 26238912, 'steps': 136660, 'loss/train': 0.5746212601661682} 08/31/2021 14:05:29 - INFO - __main__ - Step 136662: {'lr': 9.954728260319679e-06, 'samples': 26239104, 'steps': 136661, 'loss/train': 0.715609610080719} 08/31/2021 14:05:29 - INFO - __main__ - Step 136663: {'lr': 9.953245724751481e-06, 'samples': 26239296, 'steps': 136662, 'loss/train': 1.459594964981079} 08/31/2021 14:05:29 - INFO - __main__ - Step 136664: {'lr': 9.951763297344652e-06, 'samples': 26239488, 'steps': 136663, 'loss/train': 1.0415958166122437} 08/31/2021 14:05:31 - INFO - __main__ - Step 136665: {'lr': 9.950280978099856e-06, 'samples': 26239680, 'steps': 136664, 'loss/train': 1.370864748954773} 08/31/2021 14:05:31 - INFO - __main__ - Step 136666: {'lr': 9.948798767017763e-06, 'samples': 26239872, 'steps': 136665, 'loss/train': 1.0989069938659668} 08/31/2021 14:05:31 - INFO - __main__ - Step 136667: {'lr': 9.94731666409901e-06, 'samples': 26240064, 'steps': 136666, 'loss/train': 1.686355471611023} 08/31/2021 14:05:32 - INFO - __main__ - Step 136668: {'lr': 9.945834669344317e-06, 'samples': 26240256, 'steps': 136667, 'loss/train': 1.1391017436981201} 08/31/2021 14:05:32 - INFO - __main__ - Step 136669: {'lr': 9.944352782754324e-06, 'samples': 26240448, 'steps': 136668, 'loss/train': 1.1248468160629272} 08/31/2021 14:05:33 - INFO - __main__ - Step 136670: {'lr': 9.942871004329695e-06, 'samples': 26240640, 'steps': 136669, 'loss/train': 1.0348304510116577} 08/31/2021 14:05:35 - INFO - __main__ - Step 136671: {'lr': 9.941389334071154e-06, 'samples': 26240832, 'steps': 136670, 'loss/train': 0.9382152557373047} 08/31/2021 14:05:35 - INFO - __main__ - Step 136672: {'lr': 9.939907771979257e-06, 'samples': 26241024, 'steps': 136671, 'loss/train': 0.7210066318511963} 08/31/2021 14:05:36 - INFO - __main__ - Step 136673: {'lr': 9.93842631805475e-06, 'samples': 26241216, 'steps': 136672, 'loss/train': 0.5148577094078064} 08/31/2021 14:05:36 - INFO - __main__ - Step 136674: {'lr': 9.9369449722983e-06, 'samples': 26241408, 'steps': 136673, 'loss/train': 1.3936620950698853} 08/31/2021 14:05:36 - INFO - __main__ - Step 136675: {'lr': 9.93546373471052e-06, 'samples': 26241600, 'steps': 136674, 'loss/train': 1.036892056465149} 08/31/2021 14:05:38 - INFO - __main__ - Step 136676: {'lr': 9.933982605292157e-06, 'samples': 26241792, 'steps': 136675, 'loss/train': 1.0602251291275024} 08/31/2021 14:05:38 - INFO - __main__ - Step 136677: {'lr': 9.932501584043796e-06, 'samples': 26241984, 'steps': 136676, 'loss/train': 0.08095458894968033} 08/31/2021 14:05:39 - INFO - __main__ - Step 136678: {'lr': 9.931020670966185e-06, 'samples': 26242176, 'steps': 136677, 'loss/train': 1.2734649181365967} 08/31/2021 14:05:39 - INFO - __main__ - Step 136679: {'lr': 9.929539866059933e-06, 'samples': 26242368, 'steps': 136678, 'loss/train': 1.06680428981781} 08/31/2021 14:05:40 - INFO - __main__ - Step 136680: {'lr': 9.92805916932571e-06, 'samples': 26242560, 'steps': 136679, 'loss/train': 0.3253450393676758} 08/31/2021 14:05:41 - INFO - __main__ - Step 136681: {'lr': 9.926578580764234e-06, 'samples': 26242752, 'steps': 136680, 'loss/train': 0.6045452356338501} 08/31/2021 14:05:42 - INFO - __main__ - Step 136682: {'lr': 9.925098100376117e-06, 'samples': 26242944, 'steps': 136681, 'loss/train': 0.5408456921577454} 08/31/2021 14:05:42 - INFO - __main__ - Step 136683: {'lr': 9.923617728162026e-06, 'samples': 26243136, 'steps': 136682, 'loss/train': 0.8711947202682495} 08/31/2021 14:05:42 - INFO - __main__ - Step 136684: {'lr': 9.92213746412271e-06, 'samples': 26243328, 'steps': 136683, 'loss/train': 1.5356687307357788} 08/31/2021 14:05:43 - INFO - __main__ - Step 136685: {'lr': 9.920657308258724e-06, 'samples': 26243520, 'steps': 136684, 'loss/train': 1.26564359664917} 08/31/2021 14:05:43 - INFO - __main__ - Step 136686: {'lr': 9.91917726057079e-06, 'samples': 26243712, 'steps': 136685, 'loss/train': 0.8093661069869995} 08/31/2021 14:05:45 - INFO - __main__ - Step 136687: {'lr': 9.917697321059599e-06, 'samples': 26243904, 'steps': 136686, 'loss/train': 0.32656049728393555} 08/31/2021 14:05:45 - INFO - __main__ - Step 136688: {'lr': 9.916217489725737e-06, 'samples': 26244096, 'steps': 136687, 'loss/train': 1.1802009344100952} 08/31/2021 14:05:46 - INFO - __main__ - Step 136689: {'lr': 9.914737766569953e-06, 'samples': 26244288, 'steps': 136688, 'loss/train': 1.6939678192138672} 08/31/2021 14:05:46 - INFO - __main__ - Step 136690: {'lr': 9.913258151592886e-06, 'samples': 26244480, 'steps': 136689, 'loss/train': 1.769858956336975} 08/31/2021 14:05:46 - INFO - __main__ - Step 136691: {'lr': 9.9117786447952e-06, 'samples': 26244672, 'steps': 136690, 'loss/train': 0.8561432361602783} 08/31/2021 14:05:48 - INFO - __main__ - Step 136692: {'lr': 9.910299246177562e-06, 'samples': 26244864, 'steps': 136691, 'loss/train': 1.3286062479019165} 08/31/2021 14:05:48 - INFO - __main__ - Step 136693: {'lr': 9.908819955740611e-06, 'samples': 26245056, 'steps': 136692, 'loss/train': 1.479561448097229} 08/31/2021 14:05:49 - INFO - __main__ - Step 136694: {'lr': 9.907340773485068e-06, 'samples': 26245248, 'steps': 136693, 'loss/train': 1.3042176961898804} 08/31/2021 14:05:49 - INFO - __main__ - Step 136695: {'lr': 9.905861699411572e-06, 'samples': 26245440, 'steps': 136694, 'loss/train': 0.946762204170227} 08/31/2021 14:05:49 - INFO - __main__ - Step 136696: {'lr': 9.904382733520788e-06, 'samples': 26245632, 'steps': 136695, 'loss/train': 0.43166252970695496} 08/31/2021 14:05:50 - INFO - __main__ - Step 136697: {'lr': 9.902903875813385e-06, 'samples': 26245824, 'steps': 136696, 'loss/train': 1.1342449188232422} 08/31/2021 14:05:51 - INFO - __main__ - Step 136698: {'lr': 9.901425126290054e-06, 'samples': 26246016, 'steps': 136697, 'loss/train': 0.5140171051025391} 08/31/2021 14:05:52 - INFO - __main__ - Step 136699: {'lr': 9.899946484951405e-06, 'samples': 26246208, 'steps': 136698, 'loss/train': 0.760550320148468} 08/31/2021 14:05:52 - INFO - __main__ - Step 136700: {'lr': 9.898467951798134e-06, 'samples': 26246400, 'steps': 136699, 'loss/train': 1.1967648267745972} 08/31/2021 14:05:52 - INFO - __main__ - Step 136701: {'lr': 9.896989526830907e-06, 'samples': 26246592, 'steps': 136700, 'loss/train': 1.259018063545227} 08/31/2021 14:05:53 - INFO - __main__ - Step 136702: {'lr': 9.89551121005039e-06, 'samples': 26246784, 'steps': 136701, 'loss/train': 0.17435510456562042} 08/31/2021 14:05:54 - INFO - __main__ - Step 136703: {'lr': 9.894033001457275e-06, 'samples': 26246976, 'steps': 136702, 'loss/train': 1.2267646789550781} 08/31/2021 14:05:55 - INFO - __main__ - Step 136704: {'lr': 9.892554901052175e-06, 'samples': 26247168, 'steps': 136703, 'loss/train': 1.2355791330337524} 08/31/2021 14:05:55 - INFO - __main__ - Step 136705: {'lr': 9.891076908835783e-06, 'samples': 26247360, 'steps': 136704, 'loss/train': 1.2382322549819946} 08/31/2021 14:05:56 - INFO - __main__ - Step 136706: {'lr': 9.889599024808794e-06, 'samples': 26247552, 'steps': 136705, 'loss/train': 0.19205836951732635} 08/31/2021 14:05:56 - INFO - __main__ - Step 136707: {'lr': 9.888121248971815e-06, 'samples': 26247744, 'steps': 136706, 'loss/train': 1.050704002380371} 08/31/2021 14:05:56 - INFO - __main__ - Step 136708: {'lr': 9.886643581325571e-06, 'samples': 26247936, 'steps': 136707, 'loss/train': 1.075080394744873} 08/31/2021 14:05:58 - INFO - __main__ - Step 136709: {'lr': 9.885166021870728e-06, 'samples': 26248128, 'steps': 136708, 'loss/train': 0.5197776556015015} 08/31/2021 14:05:58 - INFO - __main__ - Step 136710: {'lr': 9.883688570607869e-06, 'samples': 26248320, 'steps': 136709, 'loss/train': 1.346897840499878} 08/31/2021 14:05:58 - INFO - __main__ - Step 136711: {'lr': 9.88221122753774e-06, 'samples': 26248512, 'steps': 136710, 'loss/train': 1.6565409898757935} 08/31/2021 14:05:59 - INFO - __main__ - Step 136712: {'lr': 9.880733992660956e-06, 'samples': 26248704, 'steps': 136711, 'loss/train': 0.5709895491600037} 08/31/2021 14:05:59 - INFO - __main__ - Step 136713: {'lr': 9.879256865978237e-06, 'samples': 26248896, 'steps': 136712, 'loss/train': 1.4013038873672485} 08/31/2021 14:06:01 - INFO - __main__ - Step 136714: {'lr': 9.877779847490192e-06, 'samples': 26249088, 'steps': 136713, 'loss/train': 0.6951979398727417} 08/31/2021 14:06:01 - INFO - __main__ - Step 136715: {'lr': 9.876302937197546e-06, 'samples': 26249280, 'steps': 136714, 'loss/train': 0.9664772152900696} 08/31/2021 14:06:02 - INFO - __main__ - Step 136716: {'lr': 9.874826135100907e-06, 'samples': 26249472, 'steps': 136715, 'loss/train': 0.7658360600471497} 08/31/2021 14:06:02 - INFO - __main__ - Step 136717: {'lr': 9.873349441200968e-06, 'samples': 26249664, 'steps': 136716, 'loss/train': 0.9209664463996887} 08/31/2021 14:06:02 - INFO - __main__ - Step 136718: {'lr': 9.871872855498399e-06, 'samples': 26249856, 'steps': 136717, 'loss/train': 1.023764729499817} 08/31/2021 14:06:04 - INFO - __main__ - Step 136719: {'lr': 9.870396377993862e-06, 'samples': 26250048, 'steps': 136718, 'loss/train': 1.1567635536193848} 08/31/2021 14:06:04 - INFO - __main__ - Step 136720: {'lr': 9.868920008688054e-06, 'samples': 26250240, 'steps': 136719, 'loss/train': 1.1583410501480103} 08/31/2021 14:06:05 - INFO - __main__ - Step 136721: {'lr': 9.867443747581556e-06, 'samples': 26250432, 'steps': 136720, 'loss/train': 0.7294825911521912} 08/31/2021 14:06:05 - INFO - __main__ - Step 136722: {'lr': 9.865967594675091e-06, 'samples': 26250624, 'steps': 136721, 'loss/train': 1.6404138803482056} 08/31/2021 14:06:05 - INFO - __main__ - Step 136723: {'lr': 9.864491549969323e-06, 'samples': 26250816, 'steps': 136722, 'loss/train': 1.4152647256851196} 08/31/2021 14:06:08 - INFO - __main__ - Step 136724: {'lr': 9.863015613464892e-06, 'samples': 26251008, 'steps': 136723, 'loss/train': 1.3186836242675781} 08/31/2021 14:06:09 - INFO - __main__ - Step 136725: {'lr': 9.861539785162493e-06, 'samples': 26251200, 'steps': 136724, 'loss/train': 0.9308205246925354} 08/31/2021 14:06:09 - INFO - __main__ - Step 136726: {'lr': 9.86006406506279e-06, 'samples': 26251392, 'steps': 136725, 'loss/train': 1.8265984058380127} 08/31/2021 14:06:09 - INFO - __main__ - Step 136727: {'lr': 9.858588453166423e-06, 'samples': 26251584, 'steps': 136726, 'loss/train': 1.452441930770874} 08/31/2021 14:06:10 - INFO - __main__ - Step 136728: {'lr': 9.857112949474056e-06, 'samples': 26251776, 'steps': 136727, 'loss/train': 0.88441002368927} 08/31/2021 14:06:10 - INFO - __main__ - Step 136729: {'lr': 9.855637553986385e-06, 'samples': 26251968, 'steps': 136728, 'loss/train': 0.7612017393112183} 08/31/2021 14:06:11 - INFO - __main__ - Step 136730: {'lr': 9.854162266704047e-06, 'samples': 26252160, 'steps': 136729, 'loss/train': 0.10310240089893341} 08/31/2021 14:06:12 - INFO - __main__ - Step 136731: {'lr': 9.852687087627765e-06, 'samples': 26252352, 'steps': 136730, 'loss/train': 1.1834291219711304} 08/31/2021 14:06:12 - INFO - __main__ - Step 136732: {'lr': 9.851212016758121e-06, 'samples': 26252544, 'steps': 136731, 'loss/train': 1.3224163055419922} 08/31/2021 14:06:13 - INFO - __main__ - Step 136733: {'lr': 9.84973705409581e-06, 'samples': 26252736, 'steps': 136732, 'loss/train': 1.3501836061477661} 08/31/2021 14:06:13 - INFO - __main__ - Step 136734: {'lr': 9.848262199641522e-06, 'samples': 26252928, 'steps': 136733, 'loss/train': 1.160859227180481} 08/31/2021 14:06:15 - INFO - __main__ - Step 136735: {'lr': 9.846787453395872e-06, 'samples': 26253120, 'steps': 136734, 'loss/train': 0.29922395944595337} 08/31/2021 14:06:15 - INFO - __main__ - Step 136736: {'lr': 9.845312815359553e-06, 'samples': 26253312, 'steps': 136735, 'loss/train': 0.5881343483924866} 08/31/2021 14:06:16 - INFO - __main__ - Step 136737: {'lr': 9.843838285533258e-06, 'samples': 26253504, 'steps': 136736, 'loss/train': 0.29013165831565857} 08/31/2021 14:06:16 - INFO - __main__ - Step 136738: {'lr': 9.842363863917597e-06, 'samples': 26253696, 'steps': 136737, 'loss/train': 0.8282310962677002} 08/31/2021 14:06:16 - INFO - __main__ - Step 136739: {'lr': 9.840889550513293e-06, 'samples': 26253888, 'steps': 136738, 'loss/train': 1.2726348638534546} 08/31/2021 14:06:18 - INFO - __main__ - Step 136740: {'lr': 9.839415345320957e-06, 'samples': 26254080, 'steps': 136739, 'loss/train': 1.244856595993042} 08/31/2021 14:06:19 - INFO - __main__ - Step 136741: {'lr': 9.837941248341253e-06, 'samples': 26254272, 'steps': 136740, 'loss/train': 1.8380286693572998} 08/31/2021 14:06:19 - INFO - __main__ - Step 136742: {'lr': 9.836467259574933e-06, 'samples': 26254464, 'steps': 136741, 'loss/train': 0.6747848987579346} 08/31/2021 14:06:19 - INFO - __main__ - Step 136743: {'lr': 9.83499337902255e-06, 'samples': 26254656, 'steps': 136742, 'loss/train': 1.3263938426971436} 08/31/2021 14:06:20 - INFO - __main__ - Step 136744: {'lr': 9.833519606684826e-06, 'samples': 26254848, 'steps': 136743, 'loss/train': 0.013946606777608395} 08/31/2021 14:06:20 - INFO - __main__ - Step 136745: {'lr': 9.8320459425624e-06, 'samples': 26255040, 'steps': 136744, 'loss/train': 0.08626364916563034} 08/31/2021 14:06:21 - INFO - __main__ - Step 136746: {'lr': 9.83057238665594e-06, 'samples': 26255232, 'steps': 136745, 'loss/train': 0.7617560029029846} 08/31/2021 14:06:22 - INFO - __main__ - Step 136747: {'lr': 9.829098938966136e-06, 'samples': 26255424, 'steps': 136746, 'loss/train': 0.9621613621711731} 08/31/2021 14:06:22 - INFO - __main__ - Step 136748: {'lr': 9.8276255994936e-06, 'samples': 26255616, 'steps': 136747, 'loss/train': 0.8746775984764099} 08/31/2021 14:06:23 - INFO - __main__ - Step 136749: {'lr': 9.826152368239056e-06, 'samples': 26255808, 'steps': 136748, 'loss/train': 1.300743579864502} 08/31/2021 14:06:23 - INFO - __main__ - Step 136750: {'lr': 9.824679245203138e-06, 'samples': 26256000, 'steps': 136749, 'loss/train': 1.0565632581710815} 08/31/2021 14:06:24 - INFO - __main__ - Step 136751: {'lr': 9.823206230386517e-06, 'samples': 26256192, 'steps': 136750, 'loss/train': 0.733398973941803} 08/31/2021 14:06:25 - INFO - __main__ - Step 136752: {'lr': 9.821733323789855e-06, 'samples': 26256384, 'steps': 136751, 'loss/train': 1.2179034948349} 08/31/2021 14:06:25 - INFO - __main__ - Step 136753: {'lr': 9.820260525413848e-06, 'samples': 26256576, 'steps': 136752, 'loss/train': 0.7258653044700623} 08/31/2021 14:06:26 - INFO - __main__ - Step 136754: {'lr': 9.81878783525908e-06, 'samples': 26256768, 'steps': 136753, 'loss/train': 0.6186634302139282} 08/31/2021 14:06:26 - INFO - __main__ - Step 136755: {'lr': 9.81731525332627e-06, 'samples': 26256960, 'steps': 136754, 'loss/train': 1.0885968208312988} 08/31/2021 14:06:26 - INFO - __main__ - Step 136756: {'lr': 9.815842779616086e-06, 'samples': 26257152, 'steps': 136755, 'loss/train': 0.6996793746948242} 08/31/2021 14:06:28 - INFO - __main__ - Step 136757: {'lr': 9.814370414129136e-06, 'samples': 26257344, 'steps': 136756, 'loss/train': 1.3750312328338623} 08/31/2021 14:06:28 - INFO - __main__ - Step 136758: {'lr': 9.812898156866174e-06, 'samples': 26257536, 'steps': 136757, 'loss/train': 1.4758954048156738} 08/31/2021 14:06:29 - INFO - __main__ - Step 136759: {'lr': 9.811426007827779e-06, 'samples': 26257728, 'steps': 136758, 'loss/train': 1.344567894935608} 08/31/2021 14:06:29 - INFO - __main__ - Step 136760: {'lr': 9.809953967014645e-06, 'samples': 26257920, 'steps': 136759, 'loss/train': 0.7420482039451599} 08/31/2021 14:06:29 - INFO - __main__ - Step 136761: {'lr': 9.808482034427468e-06, 'samples': 26258112, 'steps': 136760, 'loss/train': 1.365573525428772} 08/31/2021 14:06:31 - INFO - __main__ - Step 136762: {'lr': 9.807010210066858e-06, 'samples': 26258304, 'steps': 136761, 'loss/train': 0.477032333612442} 08/31/2021 14:06:31 - INFO - __main__ - Step 136763: {'lr': 9.805538493933508e-06, 'samples': 26258496, 'steps': 136762, 'loss/train': 1.7272353172302246} 08/31/2021 14:06:32 - INFO - __main__ - Step 136764: {'lr': 9.804066886028084e-06, 'samples': 26258688, 'steps': 136763, 'loss/train': 0.4574538767337799} 08/31/2021 14:06:32 - INFO - __main__ - Step 136765: {'lr': 9.802595386351281e-06, 'samples': 26258880, 'steps': 136764, 'loss/train': 0.8703097701072693} 08/31/2021 14:06:32 - INFO - __main__ - Step 136766: {'lr': 9.801123994903654e-06, 'samples': 26259072, 'steps': 136765, 'loss/train': 2.3358495235443115} 08/31/2021 14:06:33 - INFO - __main__ - Step 136767: {'lr': 9.79965271168598e-06, 'samples': 26259264, 'steps': 136766, 'loss/train': 0.7784313559532166} 08/31/2021 14:06:34 - INFO - __main__ - Step 136768: {'lr': 9.79818153669884e-06, 'samples': 26259456, 'steps': 136767, 'loss/train': 0.7241693735122681} 08/31/2021 14:06:35 - INFO - __main__ - Step 136769: {'lr': 9.79671046994296e-06, 'samples': 26259648, 'steps': 136768, 'loss/train': 1.8287696838378906} 08/31/2021 14:06:35 - INFO - __main__ - Step 136770: {'lr': 9.795239511418946e-06, 'samples': 26259840, 'steps': 136769, 'loss/train': 0.34769484400749207} 08/31/2021 14:06:35 - INFO - __main__ - Step 136771: {'lr': 9.793768661127522e-06, 'samples': 26260032, 'steps': 136770, 'loss/train': 0.8708997964859009} 08/31/2021 14:06:36 - INFO - __main__ - Step 136772: {'lr': 9.7922979190693e-06, 'samples': 26260224, 'steps': 136771, 'loss/train': 0.9306906461715698} 08/31/2021 14:06:37 - INFO - __main__ - Step 136773: {'lr': 9.790827285244969e-06, 'samples': 26260416, 'steps': 136772, 'loss/train': 0.6428454518318176} 08/31/2021 14:06:38 - INFO - __main__ - Step 136774: {'lr': 9.789356759655171e-06, 'samples': 26260608, 'steps': 136773, 'loss/train': 1.1532065868377686} 08/31/2021 14:06:38 - INFO - __main__ - Step 136775: {'lr': 9.7878863423006e-06, 'samples': 26260800, 'steps': 136774, 'loss/train': 1.4422930479049683} 08/31/2021 14:06:39 - INFO - __main__ - Step 136776: {'lr': 9.786416033181894e-06, 'samples': 26260992, 'steps': 136775, 'loss/train': 0.27294057607650757} 08/31/2021 14:06:39 - INFO - __main__ - Step 136777: {'lr': 9.784945832299719e-06, 'samples': 26261184, 'steps': 136776, 'loss/train': 0.8576979041099548} 08/31/2021 14:06:41 - INFO - __main__ - Step 136778: {'lr': 9.78347573965474e-06, 'samples': 26261376, 'steps': 136777, 'loss/train': 1.1630361080169678} 08/31/2021 14:06:41 - INFO - __main__ - Step 136779: {'lr': 9.782005755247653e-06, 'samples': 26261568, 'steps': 136778, 'loss/train': 0.8700888752937317} 08/31/2021 14:06:42 - INFO - __main__ - Step 136780: {'lr': 9.780535879079066e-06, 'samples': 26261760, 'steps': 136779, 'loss/train': 1.839359164237976} 08/31/2021 14:06:42 - INFO - __main__ - Step 136781: {'lr': 9.779066111149648e-06, 'samples': 26261952, 'steps': 136780, 'loss/train': 0.9471275806427002} 08/31/2021 14:06:43 - INFO - __main__ - Step 136782: {'lr': 9.77759645146009e-06, 'samples': 26262144, 'steps': 136781, 'loss/train': 1.379539132118225} 08/31/2021 14:06:44 - INFO - __main__ - Step 136783: {'lr': 9.776126900011034e-06, 'samples': 26262336, 'steps': 136782, 'loss/train': 1.2154289484024048} 08/31/2021 14:06:44 - INFO - __main__ - Step 136784: {'lr': 9.774657456803143e-06, 'samples': 26262528, 'steps': 136783, 'loss/train': 0.6303895711898804} 08/31/2021 14:06:45 - INFO - __main__ - Step 136785: {'lr': 9.773188121837084e-06, 'samples': 26262720, 'steps': 136784, 'loss/train': 0.6401756405830383} 08/31/2021 14:06:45 - INFO - __main__ - Step 136786: {'lr': 9.771718895113523e-06, 'samples': 26262912, 'steps': 136785, 'loss/train': 1.368855357170105} 08/31/2021 14:06:45 - INFO - __main__ - Step 136787: {'lr': 9.770249776633128e-06, 'samples': 26263104, 'steps': 136786, 'loss/train': 1.3223611116409302} 08/31/2021 14:06:46 - INFO - __main__ - Step 136788: {'lr': 9.768780766396535e-06, 'samples': 26263296, 'steps': 136787, 'loss/train': 0.6974486112594604} 08/31/2021 14:06:47 - INFO - __main__ - Step 136789: {'lr': 9.767311864404438e-06, 'samples': 26263488, 'steps': 136788, 'loss/train': 1.2685351371765137} 08/31/2021 14:06:48 - INFO - __main__ - Step 136790: {'lr': 9.765843070657476e-06, 'samples': 26263680, 'steps': 136789, 'loss/train': 0.9977917671203613} 08/31/2021 14:06:48 - INFO - __main__ - Step 136791: {'lr': 9.764374385156316e-06, 'samples': 26263872, 'steps': 136790, 'loss/train': 0.959879457950592} 08/31/2021 14:06:48 - INFO - __main__ - Step 136792: {'lr': 9.762905807901651e-06, 'samples': 26264064, 'steps': 136791, 'loss/train': 0.9695568084716797} 08/31/2021 14:06:49 - INFO - __main__ - Step 136793: {'lr': 9.761437338894092e-06, 'samples': 26264256, 'steps': 136792, 'loss/train': 0.6796602010726929} 08/31/2021 14:06:50 - INFO - __main__ - Step 136794: {'lr': 9.759968978134303e-06, 'samples': 26264448, 'steps': 136793, 'loss/train': 0.9568487405776978} 08/31/2021 14:06:51 - INFO - __main__ - Step 136795: {'lr': 9.758500725622982e-06, 'samples': 26264640, 'steps': 136794, 'loss/train': 1.2130597829818726} 08/31/2021 14:06:51 - INFO - __main__ - Step 136796: {'lr': 9.757032581360791e-06, 'samples': 26264832, 'steps': 136795, 'loss/train': 0.764025866985321} 08/31/2021 14:06:51 - INFO - __main__ - Step 136797: {'lr': 9.755564545348345e-06, 'samples': 26265024, 'steps': 136796, 'loss/train': 1.1949704885482788} 08/31/2021 14:06:52 - INFO - __main__ - Step 136798: {'lr': 9.754096617586333e-06, 'samples': 26265216, 'steps': 136797, 'loss/train': 1.013277292251587} 08/31/2021 14:06:53 - INFO - __main__ - Step 136799: {'lr': 9.752628798075424e-06, 'samples': 26265408, 'steps': 136798, 'loss/train': 1.0324598550796509} 08/31/2021 14:06:54 - INFO - __main__ - Step 136800: {'lr': 9.751161086816285e-06, 'samples': 26265600, 'steps': 136799, 'loss/train': 1.349281668663025} 08/31/2021 14:06:54 - INFO - __main__ - Step 136801: {'lr': 9.749693483809551e-06, 'samples': 26265792, 'steps': 136800, 'loss/train': 0.4433375298976898} 08/31/2021 14:06:54 - INFO - __main__ - Step 136802: {'lr': 9.74822598905592e-06, 'samples': 26265984, 'steps': 136801, 'loss/train': 2.582216501235962} 08/31/2021 14:06:55 - INFO - __main__ - Step 136803: {'lr': 9.746758602556e-06, 'samples': 26266176, 'steps': 136802, 'loss/train': 0.6200525164604187} 08/31/2021 14:06:56 - INFO - __main__ - Step 136804: {'lr': 9.745291324310513e-06, 'samples': 26266368, 'steps': 136803, 'loss/train': 0.9247503280639648} 08/31/2021 14:06:57 - INFO - __main__ - Step 136805: {'lr': 9.743824154320096e-06, 'samples': 26266560, 'steps': 136804, 'loss/train': 1.2211620807647705} 08/31/2021 14:06:57 - INFO - __main__ - Step 136806: {'lr': 9.742357092585391e-06, 'samples': 26266752, 'steps': 136805, 'loss/train': 0.9677199721336365} 08/31/2021 14:06:57 - INFO - __main__ - Step 136807: {'lr': 9.740890139107062e-06, 'samples': 26266944, 'steps': 136806, 'loss/train': 0.8245817422866821} 08/31/2021 14:06:58 - INFO - __main__ - Step 136808: {'lr': 9.739423293885774e-06, 'samples': 26267136, 'steps': 136807, 'loss/train': 1.2150461673736572} 08/31/2021 14:07:00 - INFO - __main__ - Step 136809: {'lr': 9.737956556922223e-06, 'samples': 26267328, 'steps': 136808, 'loss/train': 0.9600165486335754} 08/31/2021 14:07:00 - INFO - __main__ - Step 136810: {'lr': 9.736489928217019e-06, 'samples': 26267520, 'steps': 136809, 'loss/train': 0.9798895716667175} 08/31/2021 14:07:01 - INFO - __main__ - Step 136811: {'lr': 9.735023407770826e-06, 'samples': 26267712, 'steps': 136810, 'loss/train': 0.8782716989517212} 08/31/2021 14:07:01 - INFO - __main__ - Step 136812: {'lr': 9.73355699558437e-06, 'samples': 26267904, 'steps': 136811, 'loss/train': 1.2414989471435547} 08/31/2021 14:07:01 - INFO - __main__ - Step 136813: {'lr': 9.73209069165823e-06, 'samples': 26268096, 'steps': 136812, 'loss/train': 0.10225731134414673} 08/31/2021 14:07:03 - INFO - __main__ - Step 136814: {'lr': 9.73062449599313e-06, 'samples': 26268288, 'steps': 136813, 'loss/train': 0.9344614148139954} 08/31/2021 14:07:03 - INFO - __main__ - Step 136815: {'lr': 9.729158408589678e-06, 'samples': 26268480, 'steps': 136814, 'loss/train': 0.7965338826179504} 08/31/2021 14:07:04 - INFO - __main__ - Step 136816: {'lr': 9.72769242944857e-06, 'samples': 26268672, 'steps': 136815, 'loss/train': 0.7575868964195251} 08/31/2021 14:07:04 - INFO - __main__ - Step 136817: {'lr': 9.726226558570444e-06, 'samples': 26268864, 'steps': 136816, 'loss/train': 0.9087347388267517} 08/31/2021 14:07:04 - INFO - __main__ - Step 136818: {'lr': 9.724760795955994e-06, 'samples': 26269056, 'steps': 136817, 'loss/train': 1.0350819826126099} 08/31/2021 14:07:06 - INFO - __main__ - Step 136819: {'lr': 9.723295141605888e-06, 'samples': 26269248, 'steps': 136818, 'loss/train': 0.6191614866256714} 08/31/2021 14:07:06 - INFO - __main__ - Step 136820: {'lr': 9.721829595520703e-06, 'samples': 26269440, 'steps': 136819, 'loss/train': 0.9082509279251099} 08/31/2021 14:07:07 - INFO - __main__ - Step 136821: {'lr': 9.720364157701168e-06, 'samples': 26269632, 'steps': 136820, 'loss/train': 1.1332378387451172} 08/31/2021 14:07:07 - INFO - __main__ - Step 136822: {'lr': 9.718898828147943e-06, 'samples': 26269824, 'steps': 136821, 'loss/train': 0.8509570956230164} 08/31/2021 14:07:07 - INFO - __main__ - Step 136823: {'lr': 9.717433606861642e-06, 'samples': 26270016, 'steps': 136822, 'loss/train': 1.2863192558288574} 08/31/2021 14:07:08 - INFO - __main__ - Step 136824: {'lr': 9.715968493842986e-06, 'samples': 26270208, 'steps': 136823, 'loss/train': 1.2566033601760864} 08/31/2021 14:07:09 - INFO - __main__ - Step 136825: {'lr': 9.714503489092614e-06, 'samples': 26270400, 'steps': 136824, 'loss/train': 0.9266888499259949} 08/31/2021 14:07:09 - INFO - __main__ - Step 136826: {'lr': 9.713038592611162e-06, 'samples': 26270592, 'steps': 136825, 'loss/train': 0.8044901490211487} 08/31/2021 14:07:10 - INFO - __main__ - Step 136827: {'lr': 9.711573804399299e-06, 'samples': 26270784, 'steps': 136826, 'loss/train': 1.5991201400756836} 08/31/2021 14:07:10 - INFO - __main__ - Step 136828: {'lr': 9.710109124457717e-06, 'samples': 26270976, 'steps': 136827, 'loss/train': 2.023033380508423} 08/31/2021 14:07:10 - INFO - __main__ - Step 136829: {'lr': 9.708644552787028e-06, 'samples': 26271168, 'steps': 136828, 'loss/train': 1.2633113861083984} 08/31/2021 14:07:12 - INFO - __main__ - Step 136830: {'lr': 9.707180089387923e-06, 'samples': 26271360, 'steps': 136829, 'loss/train': 1.1134202480316162} 08/31/2021 14:07:13 - INFO - __main__ - Step 136831: {'lr': 9.705715734261044e-06, 'samples': 26271552, 'steps': 136830, 'loss/train': 1.3665961027145386} 08/31/2021 14:07:13 - INFO - __main__ - Step 136832: {'lr': 9.704251487407112e-06, 'samples': 26271744, 'steps': 136831, 'loss/train': 1.3156343698501587} 08/31/2021 14:07:13 - INFO - __main__ - Step 136833: {'lr': 9.702787348826708e-06, 'samples': 26271936, 'steps': 136832, 'loss/train': 0.9222652912139893} 08/31/2021 14:07:14 - INFO - __main__ - Step 136834: {'lr': 9.7013233185205e-06, 'samples': 26272128, 'steps': 136833, 'loss/train': 1.0793051719665527} 08/31/2021 14:07:16 - INFO - __main__ - Step 136835: {'lr': 9.69985939648918e-06, 'samples': 26272320, 'steps': 136834, 'loss/train': 0.8546939492225647} 08/31/2021 14:07:16 - INFO - __main__ - Step 136836: {'lr': 9.698395582733389e-06, 'samples': 26272512, 'steps': 136835, 'loss/train': 0.3846048414707184} 08/31/2021 14:07:16 - INFO - __main__ - Step 136837: {'lr': 9.696931877253817e-06, 'samples': 26272704, 'steps': 136836, 'loss/train': 0.5687872171401978} 08/31/2021 14:07:17 - INFO - __main__ - Step 136838: {'lr': 9.695468280051078e-06, 'samples': 26272896, 'steps': 136837, 'loss/train': 0.23956121504306793} 08/31/2021 14:07:17 - INFO - __main__ - Step 136839: {'lr': 9.694004791125839e-06, 'samples': 26273088, 'steps': 136838, 'loss/train': 1.2590701580047607} 08/31/2021 14:07:19 - INFO - __main__ - Step 136840: {'lr': 9.69254141047879e-06, 'samples': 26273280, 'steps': 136839, 'loss/train': 1.079240083694458} 08/31/2021 14:07:19 - INFO - __main__ - Step 136841: {'lr': 9.691078138110571e-06, 'samples': 26273472, 'steps': 136840, 'loss/train': 1.4473016262054443} 08/31/2021 14:07:19 - INFO - __main__ - Step 136842: {'lr': 9.689614974021849e-06, 'samples': 26273664, 'steps': 136841, 'loss/train': 0.16869314014911652} 08/31/2021 14:07:20 - INFO - __main__ - Step 136843: {'lr': 9.688151918213289e-06, 'samples': 26273856, 'steps': 136842, 'loss/train': 1.3786448240280151} 08/31/2021 14:07:20 - INFO - __main__ - Step 136844: {'lr': 9.686688970685502e-06, 'samples': 26274048, 'steps': 136843, 'loss/train': 1.6870251893997192} 08/31/2021 14:07:22 - INFO - __main__ - Step 136845: {'lr': 9.685226131439211e-06, 'samples': 26274240, 'steps': 136844, 'loss/train': 1.473611831665039} 08/31/2021 14:07:22 - INFO - __main__ - Step 136846: {'lr': 9.683763400475081e-06, 'samples': 26274432, 'steps': 136845, 'loss/train': 0.664293646812439} 08/31/2021 14:07:22 - INFO - __main__ - Step 136847: {'lr': 9.682300777793723e-06, 'samples': 26274624, 'steps': 136846, 'loss/train': 0.7162656188011169} 08/31/2021 14:07:23 - INFO - __main__ - Step 136848: {'lr': 9.680838263395775e-06, 'samples': 26274816, 'steps': 136847, 'loss/train': 0.8324108719825745} 08/31/2021 14:07:23 - INFO - __main__ - Step 136849: {'lr': 9.679375857281959e-06, 'samples': 26275008, 'steps': 136848, 'loss/train': 1.0622605085372925} 08/31/2021 14:07:24 - INFO - __main__ - Step 136850: {'lr': 9.677913559452912e-06, 'samples': 26275200, 'steps': 136849, 'loss/train': 0.34994566440582275} 08/31/2021 14:07:25 - INFO - __main__ - Step 136851: {'lr': 9.676451369909273e-06, 'samples': 26275392, 'steps': 136850, 'loss/train': 0.6104370951652527} 08/31/2021 14:07:26 - INFO - __main__ - Step 136852: {'lr': 9.67498928865171e-06, 'samples': 26275584, 'steps': 136851, 'loss/train': 1.065885066986084} 08/31/2021 14:07:26 - INFO - __main__ - Step 136853: {'lr': 9.673527315680886e-06, 'samples': 26275776, 'steps': 136852, 'loss/train': 0.6485658288002014} 08/31/2021 14:07:26 - INFO - __main__ - Step 136854: {'lr': 9.672065450997496e-06, 'samples': 26275968, 'steps': 136853, 'loss/train': 1.6306155920028687} 08/31/2021 14:07:27 - INFO - __main__ - Step 136855: {'lr': 9.670603694602126e-06, 'samples': 26276160, 'steps': 136854, 'loss/train': 1.4368904829025269} 08/31/2021 14:07:28 - INFO - __main__ - Step 136856: {'lr': 9.669142046495494e-06, 'samples': 26276352, 'steps': 136855, 'loss/train': 1.0156036615371704} 08/31/2021 14:07:29 - INFO - __main__ - Step 136857: {'lr': 9.667680506678239e-06, 'samples': 26276544, 'steps': 136856, 'loss/train': 1.1056119203567505} 08/31/2021 14:07:29 - INFO - __main__ - Step 136858: {'lr': 9.666219075151027e-06, 'samples': 26276736, 'steps': 136857, 'loss/train': 1.1341661214828491} 08/31/2021 14:07:29 - INFO - __main__ - Step 136859: {'lr': 9.664757751914527e-06, 'samples': 26276928, 'steps': 136858, 'loss/train': 1.3439871072769165} 08/31/2021 14:07:30 - INFO - __main__ - Step 136860: {'lr': 9.663296536969346e-06, 'samples': 26277120, 'steps': 136859, 'loss/train': 1.1209487915039062} 08/31/2021 14:07:31 - INFO - __main__ - Step 136861: {'lr': 9.661835430316151e-06, 'samples': 26277312, 'steps': 136860, 'loss/train': 0.0337352529168129} 08/31/2021 14:07:32 - INFO - __main__ - Step 136862: {'lr': 9.660374431955665e-06, 'samples': 26277504, 'steps': 136861, 'loss/train': 1.6556422710418701} 08/31/2021 14:07:32 - INFO - __main__ - Step 136863: {'lr': 9.658913541888498e-06, 'samples': 26277696, 'steps': 136862, 'loss/train': 0.45732563734054565} 08/31/2021 14:07:33 - INFO - __main__ - Step 136864: {'lr': 9.657452760115287e-06, 'samples': 26277888, 'steps': 136863, 'loss/train': 1.1886848211288452} 08/31/2021 14:07:33 - INFO - __main__ - Step 136865: {'lr': 9.655992086636756e-06, 'samples': 26278080, 'steps': 136864, 'loss/train': 1.0314897298812866} 08/31/2021 14:07:34 - INFO - __main__ - Step 136866: {'lr': 9.654531521453513e-06, 'samples': 26278272, 'steps': 136865, 'loss/train': 0.8125317692756653} 08/31/2021 14:07:35 - INFO - __main__ - Step 136867: {'lr': 9.653071064566226e-06, 'samples': 26278464, 'steps': 136866, 'loss/train': 0.8930560350418091} 08/31/2021 14:07:35 - INFO - __main__ - Step 136868: {'lr': 9.651610715975561e-06, 'samples': 26278656, 'steps': 136867, 'loss/train': 0.5730277895927429} 08/31/2021 14:07:36 - INFO - __main__ - Step 136869: {'lr': 9.650150475682158e-06, 'samples': 26278848, 'steps': 136868, 'loss/train': 1.1011451482772827} 08/31/2021 14:07:36 - INFO - __main__ - Step 136870: {'lr': 9.648690343686706e-06, 'samples': 26279040, 'steps': 136869, 'loss/train': 1.2188746929168701} 08/31/2021 14:07:36 - INFO - __main__ - Step 136871: {'lr': 9.64723031998982e-06, 'samples': 26279232, 'steps': 136870, 'loss/train': 1.4335463047027588} 08/31/2021 14:07:38 - INFO - __main__ - Step 136872: {'lr': 9.645770404592219e-06, 'samples': 26279424, 'steps': 136871, 'loss/train': 1.0475994348526} 08/31/2021 14:07:38 - INFO - __main__ - Step 136873: {'lr': 9.644310597494516e-06, 'samples': 26279616, 'steps': 136872, 'loss/train': 0.7827915549278259} 08/31/2021 14:07:39 - INFO - __main__ - Step 136874: {'lr': 9.642850898697375e-06, 'samples': 26279808, 'steps': 136873, 'loss/train': 0.8206515312194824} 08/31/2021 14:07:39 - INFO - __main__ - Step 136875: {'lr': 9.641391308201463e-06, 'samples': 26280000, 'steps': 136874, 'loss/train': 1.0676180124282837} 08/31/2021 14:07:39 - INFO - __main__ - Step 136876: {'lr': 9.63993182600742e-06, 'samples': 26280192, 'steps': 136875, 'loss/train': 1.5130020380020142} 08/31/2021 14:07:41 - INFO - __main__ - Step 136877: {'lr': 9.63847245211591e-06, 'samples': 26280384, 'steps': 136876, 'loss/train': 0.5929445624351501} 08/31/2021 14:07:41 - INFO - __main__ - Step 136878: {'lr': 9.637013186527599e-06, 'samples': 26280576, 'steps': 136877, 'loss/train': 0.6332201957702637} 08/31/2021 14:07:42 - INFO - __main__ - Step 136879: {'lr': 9.635554029243127e-06, 'samples': 26280768, 'steps': 136878, 'loss/train': 1.2366242408752441} 08/31/2021 14:07:42 - INFO - __main__ - Step 136880: {'lr': 9.634094980263186e-06, 'samples': 26280960, 'steps': 136879, 'loss/train': 0.9371899366378784} 08/31/2021 14:07:42 - INFO - __main__ - Step 136881: {'lr': 9.632636039588389e-06, 'samples': 26281152, 'steps': 136880, 'loss/train': 0.9884939789772034} 08/31/2021 14:07:44 - INFO - __main__ - Step 136882: {'lr': 9.631177207219427e-06, 'samples': 26281344, 'steps': 136881, 'loss/train': 1.019355297088623} 08/31/2021 14:07:44 - INFO - __main__ - Step 136883: {'lr': 9.629718483156968e-06, 'samples': 26281536, 'steps': 136882, 'loss/train': 0.683822512626648} 08/31/2021 14:07:45 - INFO - __main__ - Step 136884: {'lr': 9.628259867401623e-06, 'samples': 26281728, 'steps': 136883, 'loss/train': 1.256101131439209} 08/31/2021 14:07:45 - INFO - __main__ - Step 136885: {'lr': 9.626801359954085e-06, 'samples': 26281920, 'steps': 136884, 'loss/train': 0.44141995906829834} 08/31/2021 14:07:45 - INFO - __main__ - Step 136886: {'lr': 9.625342960815048e-06, 'samples': 26282112, 'steps': 136885, 'loss/train': 1.561267614364624} 08/31/2021 14:07:47 - INFO - __main__ - Step 136887: {'lr': 9.623884669985068e-06, 'samples': 26282304, 'steps': 136886, 'loss/train': 1.32996666431427} 08/31/2021 14:07:48 - INFO - __main__ - Step 136888: {'lr': 9.622426487464863e-06, 'samples': 26282496, 'steps': 136887, 'loss/train': 1.5036685466766357} 08/31/2021 14:07:48 - INFO - __main__ - Step 136889: {'lr': 9.620968413255077e-06, 'samples': 26282688, 'steps': 136888, 'loss/train': 0.8608249425888062} 08/31/2021 14:07:48 - INFO - __main__ - Step 136890: {'lr': 9.6195104473564e-06, 'samples': 26282880, 'steps': 136889, 'loss/train': 1.1606084108352661} 08/31/2021 14:07:49 - INFO - __main__ - Step 136891: {'lr': 9.618052589769443e-06, 'samples': 26283072, 'steps': 136890, 'loss/train': 1.1095155477523804} 08/31/2021 14:07:50 - INFO - __main__ - Step 136892: {'lr': 9.616594840494875e-06, 'samples': 26283264, 'steps': 136891, 'loss/train': 0.5674936771392822} 08/31/2021 14:07:51 - INFO - __main__ - Step 136893: {'lr': 9.615137199533358e-06, 'samples': 26283456, 'steps': 136892, 'loss/train': 0.1885303258895874} 08/31/2021 14:07:51 - INFO - __main__ - Step 136894: {'lr': 9.613679666885562e-06, 'samples': 26283648, 'steps': 136893, 'loss/train': 1.5135669708251953} 08/31/2021 14:07:51 - INFO - __main__ - Step 136895: {'lr': 9.61222224255215e-06, 'samples': 26283840, 'steps': 136894, 'loss/train': 1.2425028085708618} 08/31/2021 14:07:52 - INFO - __main__ - Step 136896: {'lr': 9.610764926533733e-06, 'samples': 26284032, 'steps': 136895, 'loss/train': 0.992210328578949} 08/31/2021 14:07:54 - INFO - __main__ - Step 136897: {'lr': 9.609307718831006e-06, 'samples': 26284224, 'steps': 136896, 'loss/train': 0.6945163011550903} 08/31/2021 14:07:54 - INFO - __main__ - Step 136898: {'lr': 9.607850619444608e-06, 'samples': 26284416, 'steps': 136897, 'loss/train': 1.5192649364471436} 08/31/2021 14:07:54 - INFO - __main__ - Step 136899: {'lr': 9.606393628375204e-06, 'samples': 26284608, 'steps': 136898, 'loss/train': 1.6573362350463867} 08/31/2021 14:07:55 - INFO - __main__ - Step 136900: {'lr': 9.604936745623488e-06, 'samples': 26284800, 'steps': 136899, 'loss/train': 1.9075855016708374} 08/31/2021 14:07:55 - INFO - __main__ - Step 136901: {'lr': 9.603479971190044e-06, 'samples': 26284992, 'steps': 136900, 'loss/train': 1.094723105430603} 08/31/2021 14:07:55 - INFO - __main__ - Step 136902: {'lr': 9.602023305075564e-06, 'samples': 26285184, 'steps': 136901, 'loss/train': 0.7690284252166748} 08/31/2021 14:07:57 - INFO - __main__ - Step 136903: {'lr': 9.600566747280714e-06, 'samples': 26285376, 'steps': 136902, 'loss/train': 0.3237870931625366} 08/31/2021 14:07:57 - INFO - __main__ - Step 136904: {'lr': 9.599110297806135e-06, 'samples': 26285568, 'steps': 136903, 'loss/train': 0.9130926132202148} 08/31/2021 14:07:58 - INFO - __main__ - Step 136905: {'lr': 9.597653956652464e-06, 'samples': 26285760, 'steps': 136904, 'loss/train': 1.11420738697052} 08/31/2021 14:07:58 - INFO - __main__ - Step 136906: {'lr': 9.596197723820394e-06, 'samples': 26285952, 'steps': 136905, 'loss/train': 0.9157310128211975} 08/31/2021 14:07:58 - INFO - __main__ - Step 136907: {'lr': 9.594741599310564e-06, 'samples': 26286144, 'steps': 136906, 'loss/train': 0.2773191034793854} 08/31/2021 14:08:00 - INFO - __main__ - Step 136908: {'lr': 9.59328558312364e-06, 'samples': 26286336, 'steps': 136907, 'loss/train': 1.1493022441864014} 08/31/2021 14:08:00 - INFO - __main__ - Step 136909: {'lr': 9.591829675260288e-06, 'samples': 26286528, 'steps': 136908, 'loss/train': 1.1933927536010742} 08/31/2021 14:08:01 - INFO - __main__ - Step 136910: {'lr': 9.59037387572112e-06, 'samples': 26286720, 'steps': 136909, 'loss/train': 0.9715235829353333} 08/31/2021 14:08:01 - INFO - __main__ - Step 136911: {'lr': 9.588918184506829e-06, 'samples': 26286912, 'steps': 136910, 'loss/train': 1.2275774478912354} 08/31/2021 14:08:01 - INFO - __main__ - Step 136912: {'lr': 9.58746260161808e-06, 'samples': 26287104, 'steps': 136911, 'loss/train': 0.04136507213115692} 08/31/2021 14:08:03 - INFO - __main__ - Step 136913: {'lr': 9.586007127055513e-06, 'samples': 26287296, 'steps': 136912, 'loss/train': 0.8499454855918884} 08/31/2021 14:08:04 - INFO - __main__ - Step 136914: {'lr': 9.584551760819764e-06, 'samples': 26287488, 'steps': 136913, 'loss/train': 1.068343997001648} 08/31/2021 14:08:04 - INFO - __main__ - Step 136915: {'lr': 9.583096502911503e-06, 'samples': 26287680, 'steps': 136914, 'loss/train': 1.4055954217910767} 08/31/2021 14:08:04 - INFO - __main__ - Step 136916: {'lr': 9.581641353331393e-06, 'samples': 26287872, 'steps': 136915, 'loss/train': 0.8553817272186279} 08/31/2021 14:08:05 - INFO - __main__ - Step 136917: {'lr': 9.580186312080074e-06, 'samples': 26288064, 'steps': 136916, 'loss/train': 0.8664792776107788} 08/31/2021 14:08:06 - INFO - __main__ - Step 136918: {'lr': 9.57873137915824e-06, 'samples': 26288256, 'steps': 136917, 'loss/train': 0.9259514212608337} 08/31/2021 14:08:06 - INFO - __main__ - Step 136919: {'lr': 9.577276554566499e-06, 'samples': 26288448, 'steps': 136918, 'loss/train': 1.2396289110183716} 08/31/2021 14:08:07 - INFO - __main__ - Step 136920: {'lr': 9.575821838305521e-06, 'samples': 26288640, 'steps': 136919, 'loss/train': 1.2703410387039185} 08/31/2021 14:08:07 - INFO - __main__ - Step 136921: {'lr': 9.57436723037597e-06, 'samples': 26288832, 'steps': 136920, 'loss/train': 1.1764605045318604} 08/31/2021 14:08:08 - INFO - __main__ - Step 136922: {'lr': 9.572912730778511e-06, 'samples': 26289024, 'steps': 136921, 'loss/train': 0.8174595832824707} 08/31/2021 14:08:09 - INFO - __main__ - Step 136923: {'lr': 9.571458339513783e-06, 'samples': 26289216, 'steps': 136922, 'loss/train': 1.0916193723678589} 08/31/2021 14:08:10 - INFO - __main__ - Step 136924: {'lr': 9.570004056582454e-06, 'samples': 26289408, 'steps': 136923, 'loss/train': 1.5340709686279297} 08/31/2021 14:08:10 - INFO - __main__ - Step 136925: {'lr': 9.568549881985161e-06, 'samples': 26289600, 'steps': 136924, 'loss/train': 1.5894452333450317} 08/31/2021 14:08:10 - INFO - __main__ - Step 136926: {'lr': 9.567095815722598e-06, 'samples': 26289792, 'steps': 136925, 'loss/train': 1.123957633972168} 08/31/2021 14:08:11 - INFO - __main__ - Step 136927: {'lr': 9.565641857795376e-06, 'samples': 26289984, 'steps': 136926, 'loss/train': 0.8278626203536987} 08/31/2021 14:08:11 - INFO - __main__ - Step 136928: {'lr': 9.564188008204134e-06, 'samples': 26290176, 'steps': 136927, 'loss/train': 0.8379878401756287} 08/31/2021 14:08:13 - INFO - __main__ - Step 136929: {'lr': 9.562734266949591e-06, 'samples': 26290368, 'steps': 136928, 'loss/train': 0.8953128457069397} 08/31/2021 14:08:13 - INFO - __main__ - Step 136930: {'lr': 9.56128063403236e-06, 'samples': 26290560, 'steps': 136929, 'loss/train': 1.0099304914474487} 08/31/2021 14:08:13 - INFO - __main__ - Step 136931: {'lr': 9.559827109453106e-06, 'samples': 26290752, 'steps': 136930, 'loss/train': 1.274513602256775} 08/31/2021 14:08:14 - INFO - __main__ - Step 136932: {'lr': 9.558373693212468e-06, 'samples': 26290944, 'steps': 136931, 'loss/train': 1.1166208982467651} 08/31/2021 14:08:14 - INFO - __main__ - Step 136933: {'lr': 9.55692038531114e-06, 'samples': 26291136, 'steps': 136932, 'loss/train': 0.23057377338409424} 08/31/2021 14:08:16 - INFO - __main__ - Step 136934: {'lr': 9.555467185749733e-06, 'samples': 26291328, 'steps': 136933, 'loss/train': 1.1535536050796509} 08/31/2021 14:08:16 - INFO - __main__ - Step 136935: {'lr': 9.55401409452894e-06, 'samples': 26291520, 'steps': 136934, 'loss/train': 1.0016446113586426} 08/31/2021 14:08:16 - INFO - __main__ - Step 136936: {'lr': 9.552561111649372e-06, 'samples': 26291712, 'steps': 136935, 'loss/train': 1.3864147663116455} 08/31/2021 14:08:17 - INFO - __main__ - Step 136937: {'lr': 9.55110823711175e-06, 'samples': 26291904, 'steps': 136936, 'loss/train': 0.3932073712348938} 08/31/2021 14:08:17 - INFO - __main__ - Step 136938: {'lr': 9.549655470916657e-06, 'samples': 26292096, 'steps': 136937, 'loss/train': 1.5915789604187012} 08/31/2021 14:08:19 - INFO - __main__ - Step 136939: {'lr': 9.548202813064788e-06, 'samples': 26292288, 'steps': 136938, 'loss/train': 0.8667146563529968} 08/31/2021 14:08:19 - INFO - __main__ - Step 136940: {'lr': 9.546750263556808e-06, 'samples': 26292480, 'steps': 136939, 'loss/train': 1.192570447921753} 08/31/2021 14:08:19 - INFO - __main__ - Step 136941: {'lr': 9.545297822393357e-06, 'samples': 26292672, 'steps': 136940, 'loss/train': 0.9221049547195435} 08/31/2021 14:08:20 - INFO - __main__ - Step 136942: {'lr': 9.543845489575043e-06, 'samples': 26292864, 'steps': 136941, 'loss/train': 1.661003828048706} 08/31/2021 14:08:20 - INFO - __main__ - Step 136943: {'lr': 9.54239326510259e-06, 'samples': 26293056, 'steps': 136942, 'loss/train': 1.1292839050292969} 08/31/2021 14:08:22 - INFO - __main__ - Step 136944: {'lr': 9.540941148976606e-06, 'samples': 26293248, 'steps': 136943, 'loss/train': 1.619898796081543} 08/31/2021 14:08:23 - INFO - __main__ - Step 136945: {'lr': 9.53948914119776e-06, 'samples': 26293440, 'steps': 136944, 'loss/train': 0.8802909851074219} 08/31/2021 14:08:23 - INFO - __main__ - Step 136946: {'lr': 9.538037241766717e-06, 'samples': 26293632, 'steps': 136945, 'loss/train': 1.4303464889526367} 08/31/2021 14:08:23 - INFO - __main__ - Step 136947: {'lr': 9.536585450684142e-06, 'samples': 26293824, 'steps': 136946, 'loss/train': 0.46014198660850525} 08/31/2021 14:08:24 - INFO - __main__ - Step 136948: {'lr': 9.53513376795065e-06, 'samples': 26294016, 'steps': 136947, 'loss/train': 0.7125886678695679} 08/31/2021 14:08:25 - INFO - __main__ - Step 136949: {'lr': 9.533682193566928e-06, 'samples': 26294208, 'steps': 136948, 'loss/train': 0.9737594723701477} 08/31/2021 14:08:26 - INFO - __main__ - Step 136950: {'lr': 9.532230727533592e-06, 'samples': 26294400, 'steps': 136949, 'loss/train': 0.8812112808227539} 08/31/2021 14:08:26 - INFO - __main__ - Step 136951: {'lr': 9.53077936985136e-06, 'samples': 26294592, 'steps': 136950, 'loss/train': 1.3029282093048096} 08/31/2021 14:08:27 - INFO - __main__ - Step 136952: {'lr': 9.52932812052082e-06, 'samples': 26294784, 'steps': 136951, 'loss/train': 1.639562726020813} 08/31/2021 14:08:27 - INFO - __main__ - Step 136953: {'lr': 9.527876979542688e-06, 'samples': 26294976, 'steps': 136952, 'loss/train': 1.0869474411010742} 08/31/2021 14:08:29 - INFO - __main__ - Step 136954: {'lr': 9.526425946917577e-06, 'samples': 26295168, 'steps': 136953, 'loss/train': 0.5850661993026733} 08/31/2021 14:08:29 - INFO - __main__ - Step 136955: {'lr': 9.524975022646127e-06, 'samples': 26295360, 'steps': 136954, 'loss/train': 1.4375553131103516} 08/31/2021 14:08:30 - INFO - __main__ - Step 136956: {'lr': 9.523524206729001e-06, 'samples': 26295552, 'steps': 136955, 'loss/train': 0.2723069489002228} 08/31/2021 14:08:30 - INFO - __main__ - Step 136957: {'lr': 9.522073499166895e-06, 'samples': 26295744, 'steps': 136956, 'loss/train': 1.0196017026901245} 08/31/2021 14:08:30 - INFO - __main__ - Step 136958: {'lr': 9.520622899960418e-06, 'samples': 26295936, 'steps': 136957, 'loss/train': 0.9811935424804688} 08/31/2021 14:08:32 - INFO - __main__ - Step 136959: {'lr': 9.519172409110238e-06, 'samples': 26296128, 'steps': 136958, 'loss/train': 0.8022261261940002} 08/31/2021 14:08:32 - INFO - __main__ - Step 136960: {'lr': 9.517722026616993e-06, 'samples': 26296320, 'steps': 136959, 'loss/train': 1.0575522184371948} 08/31/2021 14:08:33 - INFO - __main__ - Step 136961: {'lr': 9.516271752481376e-06, 'samples': 26296512, 'steps': 136960, 'loss/train': 0.7850180864334106} 08/31/2021 14:08:33 - INFO - __main__ - Step 136962: {'lr': 9.514821586703998e-06, 'samples': 26296704, 'steps': 136961, 'loss/train': 0.7016223669052124} 08/31/2021 14:08:33 - INFO - __main__ - Step 136963: {'lr': 9.513371529285525e-06, 'samples': 26296896, 'steps': 136962, 'loss/train': 0.2998487055301666} 08/31/2021 14:08:35 - INFO - __main__ - Step 136964: {'lr': 9.511921580226651e-06, 'samples': 26297088, 'steps': 136963, 'loss/train': 0.8081721067428589} 08/31/2021 14:08:36 - INFO - __main__ - Step 136965: {'lr': 9.51047173952796e-06, 'samples': 26297280, 'steps': 136964, 'loss/train': 0.1847192943096161} 08/31/2021 14:08:36 - INFO - __main__ - Step 136966: {'lr': 9.509022007190143e-06, 'samples': 26297472, 'steps': 136965, 'loss/train': 0.8396987318992615} 08/31/2021 14:08:36 - INFO - __main__ - Step 136967: {'lr': 9.507572383213898e-06, 'samples': 26297664, 'steps': 136966, 'loss/train': 0.7658194899559021} 08/31/2021 14:08:37 - INFO - __main__ - Step 136968: {'lr': 9.506122867599775e-06, 'samples': 26297856, 'steps': 136967, 'loss/train': 0.8558367490768433} 08/31/2021 14:08:37 - INFO - __main__ - Step 136969: {'lr': 9.5046734603485e-06, 'samples': 26298048, 'steps': 136968, 'loss/train': 0.7629201412200928} 08/31/2021 14:08:39 - INFO - __main__ - Step 136970: {'lr': 9.50322416146071e-06, 'samples': 26298240, 'steps': 136969, 'loss/train': 0.05310043692588806} 08/31/2021 14:08:39 - INFO - __main__ - Step 136971: {'lr': 9.501774970937044e-06, 'samples': 26298432, 'steps': 136970, 'loss/train': 0.6204583644866943} 08/31/2021 14:08:40 - INFO - __main__ - Step 136972: {'lr': 9.500325888778166e-06, 'samples': 26298624, 'steps': 136971, 'loss/train': 1.4157230854034424} 08/31/2021 14:08:40 - INFO - __main__ - Step 136973: {'lr': 9.498876914984745e-06, 'samples': 26298816, 'steps': 136972, 'loss/train': 0.1323680728673935} 08/31/2021 14:08:40 - INFO - __main__ - Step 136974: {'lr': 9.497428049557416e-06, 'samples': 26299008, 'steps': 136973, 'loss/train': 1.2243558168411255} 08/31/2021 14:08:42 - INFO - __main__ - Step 136975: {'lr': 9.49597929249682e-06, 'samples': 26299200, 'steps': 136974, 'loss/train': 0.2238059937953949} 08/31/2021 14:08:43 - INFO - __main__ - Step 136976: {'lr': 9.49453064380365e-06, 'samples': 26299392, 'steps': 136975, 'loss/train': 0.9145449995994568} 08/31/2021 14:08:43 - INFO - __main__ - Step 136977: {'lr': 9.493082103478518e-06, 'samples': 26299584, 'steps': 136976, 'loss/train': 1.5014818906784058} 08/31/2021 14:08:44 - INFO - __main__ - Step 136978: {'lr': 9.491633671522116e-06, 'samples': 26299776, 'steps': 136977, 'loss/train': 1.8853193521499634} 08/31/2021 14:08:44 - INFO - __main__ - Step 136979: {'lr': 9.490185347935055e-06, 'samples': 26299968, 'steps': 136978, 'loss/train': 0.016063202172517776} 08/31/2021 14:08:44 - INFO - __main__ - Step 136980: {'lr': 9.488737132718e-06, 'samples': 26300160, 'steps': 136979, 'loss/train': 1.1574132442474365} 08/31/2021 14:08:46 - INFO - __main__ - Step 136981: {'lr': 9.487289025871593e-06, 'samples': 26300352, 'steps': 136980, 'loss/train': 1.6830661296844482} 08/31/2021 14:08:47 - INFO - __main__ - Step 136982: {'lr': 9.485841027396524e-06, 'samples': 26300544, 'steps': 136981, 'loss/train': 1.8325014114379883} 08/31/2021 14:08:47 - INFO - __main__ - Step 136983: {'lr': 9.484393137293406e-06, 'samples': 26300736, 'steps': 136982, 'loss/train': 1.65328049659729} 08/31/2021 14:08:47 - INFO - __main__ - Step 136984: {'lr': 9.482945355562934e-06, 'samples': 26300928, 'steps': 136983, 'loss/train': 0.24452275037765503} 08/31/2021 14:08:48 - INFO - __main__ - Step 136985: {'lr': 9.481497682205713e-06, 'samples': 26301120, 'steps': 136984, 'loss/train': 1.387468695640564} 08/31/2021 14:08:48 - INFO - __main__ - Step 136986: {'lr': 9.480050117222417e-06, 'samples': 26301312, 'steps': 136985, 'loss/train': 0.8833566308021545} 08/31/2021 14:08:48 - INFO - __main__ - Step 136987: {'lr': 9.478602660613706e-06, 'samples': 26301504, 'steps': 136986, 'loss/train': 0.01409909501671791} 08/31/2021 14:08:50 - INFO - __main__ - Step 136988: {'lr': 9.477155312380249e-06, 'samples': 26301696, 'steps': 136987, 'loss/train': 1.0896888971328735} 08/31/2021 14:08:50 - INFO - __main__ - Step 136989: {'lr': 9.475708072522681e-06, 'samples': 26301888, 'steps': 136988, 'loss/train': 0.5203022956848145} 08/31/2021 14:08:51 - INFO - __main__ - Step 136990: {'lr': 9.474260941041618e-06, 'samples': 26302080, 'steps': 136989, 'loss/train': 0.29907894134521484} 08/31/2021 14:08:51 - INFO - __main__ - Step 136991: {'lr': 9.472813917937722e-06, 'samples': 26302272, 'steps': 136990, 'loss/train': 1.013136625289917} 08/31/2021 14:08:51 - INFO - __main__ - Step 136992: {'lr': 9.47136700321169e-06, 'samples': 26302464, 'steps': 136991, 'loss/train': 1.5222663879394531} 08/31/2021 14:08:53 - INFO - __main__ - Step 136993: {'lr': 9.469920196864157e-06, 'samples': 26302656, 'steps': 136992, 'loss/train': 0.2194305956363678} 08/31/2021 14:08:53 - INFO - __main__ - Step 136994: {'lr': 9.468473498895735e-06, 'samples': 26302848, 'steps': 136993, 'loss/train': 1.7039295434951782} 08/31/2021 14:08:54 - INFO - __main__ - Step 136995: {'lr': 9.46702690930712e-06, 'samples': 26303040, 'steps': 136994, 'loss/train': 1.7691798210144043} 08/31/2021 14:08:54 - INFO - __main__ - Step 136996: {'lr': 9.465580428098974e-06, 'samples': 26303232, 'steps': 136995, 'loss/train': 0.9257674217224121} 08/31/2021 14:08:54 - INFO - __main__ - Step 136997: {'lr': 9.464134055271911e-06, 'samples': 26303424, 'steps': 136996, 'loss/train': 0.906389057636261} 08/31/2021 14:08:57 - INFO - __main__ - Step 136998: {'lr': 9.462687790826568e-06, 'samples': 26303616, 'steps': 136997, 'loss/train': 1.1418546438217163} 08/31/2021 14:08:57 - INFO - __main__ - Step 136999: {'lr': 9.461241634763667e-06, 'samples': 26303808, 'steps': 136998, 'loss/train': 1.4284428358078003} 08/31/2021 14:08:58 - INFO - __main__ - Step 137000: {'lr': 9.45979558708382e-06, 'samples': 26304000, 'steps': 136999, 'loss/train': 0.09740138053894043} 08/31/2021 14:08:58 - INFO - __main__ - Step 137001: {'lr': 9.458349647787662e-06, 'samples': 26304192, 'steps': 137000, 'loss/train': 0.2245384156703949} 08/31/2021 14:08:58 - INFO - __main__ - Step 137002: {'lr': 9.456903816875861e-06, 'samples': 26304384, 'steps': 137001, 'loss/train': 0.9194253087043762} 08/31/2021 14:09:00 - INFO - __main__ - Step 137003: {'lr': 9.455458094349084e-06, 'samples': 26304576, 'steps': 137002, 'loss/train': 2.2611284255981445} 08/31/2021 14:09:01 - INFO - __main__ - Step 137004: {'lr': 9.45401248020794e-06, 'samples': 26304768, 'steps': 137003, 'loss/train': 1.0778288841247559} 08/31/2021 14:09:01 - INFO - __main__ - Step 137005: {'lr': 9.452566974453098e-06, 'samples': 26304960, 'steps': 137004, 'loss/train': 1.0084362030029297} 08/31/2021 14:09:01 - INFO - __main__ - Step 137006: {'lr': 9.451121577085247e-06, 'samples': 26305152, 'steps': 137005, 'loss/train': 0.6776626110076904} 08/31/2021 14:09:02 - INFO - __main__ - Step 137007: {'lr': 9.449676288105002e-06, 'samples': 26305344, 'steps': 137006, 'loss/train': 0.2838146984577179} 08/31/2021 14:09:03 - INFO - __main__ - Step 137008: {'lr': 9.448231107513e-06, 'samples': 26305536, 'steps': 137007, 'loss/train': 1.3914529085159302} 08/31/2021 14:09:04 - INFO - __main__ - Step 137009: {'lr': 9.446786035309935e-06, 'samples': 26305728, 'steps': 137008, 'loss/train': 0.8737207651138306} 08/31/2021 14:09:04 - INFO - __main__ - Step 137010: {'lr': 9.445341071496416e-06, 'samples': 26305920, 'steps': 137009, 'loss/train': 0.4180663228034973} 08/31/2021 14:09:04 - INFO - __main__ - Step 137011: {'lr': 9.443896216073167e-06, 'samples': 26306112, 'steps': 137010, 'loss/train': 1.2586933374404907} 08/31/2021 14:09:05 - INFO - __main__ - Step 137012: {'lr': 9.442451469040741e-06, 'samples': 26306304, 'steps': 137011, 'loss/train': 1.1086610555648804} 08/31/2021 14:09:06 - INFO - __main__ - Step 137013: {'lr': 9.441006830399834e-06, 'samples': 26306496, 'steps': 137012, 'loss/train': 1.0612661838531494} 08/31/2021 14:09:07 - INFO - __main__ - Step 137014: {'lr': 9.439562300151112e-06, 'samples': 26306688, 'steps': 137013, 'loss/train': 0.8079712390899658} 08/31/2021 14:09:07 - INFO - __main__ - Step 137015: {'lr': 9.438117878295182e-06, 'samples': 26306880, 'steps': 137014, 'loss/train': 1.449541687965393} 08/31/2021 14:09:07 - INFO - __main__ - Step 137016: {'lr': 9.436673564832744e-06, 'samples': 26307072, 'steps': 137015, 'loss/train': 1.2375432252883911} 08/31/2021 14:09:08 - INFO - __main__ - Step 137017: {'lr': 9.43522935976443e-06, 'samples': 26307264, 'steps': 137016, 'loss/train': 0.16471655666828156} 08/31/2021 14:09:09 - INFO - __main__ - Step 137018: {'lr': 9.433785263090883e-06, 'samples': 26307456, 'steps': 137017, 'loss/train': 1.4843648672103882} 08/31/2021 14:09:10 - INFO - __main__ - Step 137019: {'lr': 9.432341274812767e-06, 'samples': 26307648, 'steps': 137018, 'loss/train': 0.8608824610710144} 08/31/2021 14:09:10 - INFO - __main__ - Step 137020: {'lr': 9.430897394930721e-06, 'samples': 26307840, 'steps': 137019, 'loss/train': 1.4750642776489258} 08/31/2021 14:09:11 - INFO - __main__ - Step 137021: {'lr': 9.42945362344541e-06, 'samples': 26308032, 'steps': 137020, 'loss/train': 1.3383355140686035} 08/31/2021 14:09:11 - INFO - __main__ - Step 137022: {'lr': 9.428009960357504e-06, 'samples': 26308224, 'steps': 137021, 'loss/train': 0.8941015005111694} 08/31/2021 14:09:12 - INFO - __main__ - Step 137023: {'lr': 9.426566405667581e-06, 'samples': 26308416, 'steps': 137022, 'loss/train': 1.6234118938446045} 08/31/2021 14:09:13 - INFO - __main__ - Step 137024: {'lr': 9.425122959376337e-06, 'samples': 26308608, 'steps': 137023, 'loss/train': 1.263909101486206} 08/31/2021 14:09:13 - INFO - __main__ - Step 137025: {'lr': 9.423679621484438e-06, 'samples': 26308800, 'steps': 137024, 'loss/train': 1.4534730911254883} 08/31/2021 14:09:14 - INFO - __main__ - Step 137026: {'lr': 9.422236391992495e-06, 'samples': 26308992, 'steps': 137025, 'loss/train': 0.5071544647216797} 08/31/2021 14:09:14 - INFO - __main__ - Step 137027: {'lr': 9.420793270901202e-06, 'samples': 26309184, 'steps': 137026, 'loss/train': 0.11551939696073532} 08/31/2021 14:09:16 - INFO - __main__ - Step 137028: {'lr': 9.419350258211168e-06, 'samples': 26309376, 'steps': 137027, 'loss/train': 0.5637770295143127} 08/31/2021 14:09:16 - INFO - __main__ - Step 137029: {'lr': 9.41790735392306e-06, 'samples': 26309568, 'steps': 137028, 'loss/train': 1.5866758823394775} 08/31/2021 14:09:16 - INFO - __main__ - Step 137030: {'lr': 9.416464558037546e-06, 'samples': 26309760, 'steps': 137029, 'loss/train': 1.1511163711547852} 08/31/2021 14:09:17 - INFO - __main__ - Step 137031: {'lr': 9.415021870555262e-06, 'samples': 26309952, 'steps': 137030, 'loss/train': 0.8858567476272583} 08/31/2021 14:09:17 - INFO - __main__ - Step 137032: {'lr': 9.413579291476848e-06, 'samples': 26310144, 'steps': 137031, 'loss/train': 1.436999797821045} 08/31/2021 14:09:19 - INFO - __main__ - Step 137033: {'lr': 9.412136820802942e-06, 'samples': 26310336, 'steps': 137032, 'loss/train': 1.021301507949829} 08/31/2021 14:09:19 - INFO - __main__ - Step 137034: {'lr': 9.410694458534264e-06, 'samples': 26310528, 'steps': 137033, 'loss/train': 1.161906361579895} 08/31/2021 14:09:19 - INFO - __main__ - Step 137035: {'lr': 9.409252204671399e-06, 'samples': 26310720, 'steps': 137034, 'loss/train': 1.3495298624038696} 08/31/2021 14:09:20 - INFO - __main__ - Step 137036: {'lr': 9.40781005921501e-06, 'samples': 26310912, 'steps': 137035, 'loss/train': 1.8157745599746704} 08/31/2021 14:09:20 - INFO - __main__ - Step 137037: {'lr': 9.40636802216574e-06, 'samples': 26311104, 'steps': 137036, 'loss/train': 1.8717275857925415} 08/31/2021 14:09:20 - INFO - __main__ - Step 137038: {'lr': 9.404926093524225e-06, 'samples': 26311296, 'steps': 137037, 'loss/train': 0.7674470543861389} 08/31/2021 14:09:22 - INFO - __main__ - Step 137039: {'lr': 9.403484273291157e-06, 'samples': 26311488, 'steps': 137038, 'loss/train': 0.2543213367462158} 08/31/2021 14:09:22 - INFO - __main__ - Step 137040: {'lr': 9.402042561467177e-06, 'samples': 26311680, 'steps': 137039, 'loss/train': 1.5773643255233765} 08/31/2021 14:09:23 - INFO - __main__ - Step 137041: {'lr': 9.400600958052923e-06, 'samples': 26311872, 'steps': 137040, 'loss/train': 1.1221411228179932} 08/31/2021 14:09:23 - INFO - __main__ - Step 137042: {'lr': 9.399159463049034e-06, 'samples': 26312064, 'steps': 137041, 'loss/train': 0.7814657688140869} 08/31/2021 14:09:23 - INFO - __main__ - Step 137043: {'lr': 9.397718076456174e-06, 'samples': 26312256, 'steps': 137042, 'loss/train': 1.1841883659362793} 08/31/2021 14:09:25 - INFO - __main__ - Step 137044: {'lr': 9.396276798274983e-06, 'samples': 26312448, 'steps': 137043, 'loss/train': 1.2550222873687744} 08/31/2021 14:09:26 - INFO - __main__ - Step 137045: {'lr': 9.394835628506127e-06, 'samples': 26312640, 'steps': 137044, 'loss/train': 1.0891644954681396} 08/31/2021 14:09:26 - INFO - __main__ - Step 137046: {'lr': 9.393394567150243e-06, 'samples': 26312832, 'steps': 137045, 'loss/train': 0.5439781546592712} 08/31/2021 14:09:26 - INFO - __main__ - Step 137047: {'lr': 9.391953614208026e-06, 'samples': 26313024, 'steps': 137046, 'loss/train': 0.762924313545227} 08/31/2021 14:09:27 - INFO - __main__ - Step 137048: {'lr': 9.390512769680032e-06, 'samples': 26313216, 'steps': 137047, 'loss/train': 0.6787318587303162} 08/31/2021 14:09:29 - INFO - __main__ - Step 137049: {'lr': 9.38907203356698e-06, 'samples': 26313408, 'steps': 137048, 'loss/train': 1.098112940788269} 08/31/2021 14:09:29 - INFO - __main__ - Step 137050: {'lr': 9.387631405869485e-06, 'samples': 26313600, 'steps': 137049, 'loss/train': 0.8499153852462769} 08/31/2021 14:09:30 - INFO - __main__ - Step 137051: {'lr': 9.386190886588208e-06, 'samples': 26313792, 'steps': 137050, 'loss/train': 0.9146212339401245} 08/31/2021 14:09:30 - INFO - __main__ - Step 137052: {'lr': 9.384750475723792e-06, 'samples': 26313984, 'steps': 137051, 'loss/train': 0.5468377470970154} 08/31/2021 14:09:30 - INFO - __main__ - Step 137053: {'lr': 9.3833101732769e-06, 'samples': 26314176, 'steps': 137052, 'loss/train': 1.5004252195358276} 08/31/2021 14:09:32 - INFO - __main__ - Step 137054: {'lr': 9.381869979248198e-06, 'samples': 26314368, 'steps': 137053, 'loss/train': 2.0889694690704346} 08/31/2021 14:09:32 - INFO - __main__ - Step 137055: {'lr': 9.380429893638298e-06, 'samples': 26314560, 'steps': 137054, 'loss/train': 1.781736969947815} 08/31/2021 14:09:33 - INFO - __main__ - Step 137056: {'lr': 9.378989916447866e-06, 'samples': 26314752, 'steps': 137055, 'loss/train': 1.2672654390335083} 08/31/2021 14:09:33 - INFO - __main__ - Step 137057: {'lr': 9.377550047677541e-06, 'samples': 26314944, 'steps': 137056, 'loss/train': 1.5691372156143188} 08/31/2021 14:09:33 - INFO - __main__ - Step 137058: {'lr': 9.37611028732796e-06, 'samples': 26315136, 'steps': 137057, 'loss/train': 0.02913958579301834} 08/31/2021 14:09:34 - INFO - __main__ - Step 137059: {'lr': 9.374670635399819e-06, 'samples': 26315328, 'steps': 137058, 'loss/train': 1.3742622137069702} 08/31/2021 14:09:35 - INFO - __main__ - Step 137060: {'lr': 9.373231091893752e-06, 'samples': 26315520, 'steps': 137059, 'loss/train': 1.1804187297821045} 08/31/2021 14:09:36 - INFO - __main__ - Step 137061: {'lr': 9.371791656810402e-06, 'samples': 26315712, 'steps': 137060, 'loss/train': 0.882184624671936} 08/31/2021 14:09:36 - INFO - __main__ - Step 137062: {'lr': 9.370352330150378e-06, 'samples': 26315904, 'steps': 137061, 'loss/train': 1.438247799873352} 08/31/2021 14:09:36 - INFO - __main__ - Step 137063: {'lr': 9.368913111914345e-06, 'samples': 26316096, 'steps': 137062, 'loss/train': 0.8649115562438965} 08/31/2021 14:09:37 - INFO - __main__ - Step 137064: {'lr': 9.367474002102998e-06, 'samples': 26316288, 'steps': 137063, 'loss/train': 1.2128304243087769} 08/31/2021 14:09:38 - INFO - __main__ - Step 137065: {'lr': 9.36603500071695e-06, 'samples': 26316480, 'steps': 137064, 'loss/train': 1.1383916139602661} 08/31/2021 14:09:39 - INFO - __main__ - Step 137066: {'lr': 9.364596107756834e-06, 'samples': 26316672, 'steps': 137065, 'loss/train': 0.03517777472734451} 08/31/2021 14:09:39 - INFO - __main__ - Step 137067: {'lr': 9.36315732322332e-06, 'samples': 26316864, 'steps': 137066, 'loss/train': 0.7035695314407349} 08/31/2021 14:09:40 - INFO - __main__ - Step 137068: {'lr': 9.361718647117073e-06, 'samples': 26317056, 'steps': 137067, 'loss/train': 0.8368270397186279} 08/31/2021 14:09:40 - INFO - __main__ - Step 137069: {'lr': 9.360280079438705e-06, 'samples': 26317248, 'steps': 137068, 'loss/train': 0.8649807572364807} 08/31/2021 14:09:41 - INFO - __main__ - Step 137070: {'lr': 9.358841620188879e-06, 'samples': 26317440, 'steps': 137069, 'loss/train': 1.4096932411193848} 08/31/2021 14:09:42 - INFO - __main__ - Step 137071: {'lr': 9.357403269368264e-06, 'samples': 26317632, 'steps': 137070, 'loss/train': 0.3511618971824646} 08/31/2021 14:09:42 - INFO - __main__ - Step 137072: {'lr': 9.35596502697747e-06, 'samples': 26317824, 'steps': 137071, 'loss/train': 1.396781086921692} 08/31/2021 14:09:43 - INFO - __main__ - Step 137073: {'lr': 9.35452689301719e-06, 'samples': 26318016, 'steps': 137072, 'loss/train': 1.003803014755249} 08/31/2021 14:09:43 - INFO - __main__ - Step 137074: {'lr': 9.353088867488064e-06, 'samples': 26318208, 'steps': 137073, 'loss/train': 0.027965355664491653} 08/31/2021 14:09:44 - INFO - __main__ - Step 137075: {'lr': 9.3516509503907e-06, 'samples': 26318400, 'steps': 137074, 'loss/train': 1.0986597537994385} 08/31/2021 14:09:45 - INFO - __main__ - Step 137076: {'lr': 9.350213141725739e-06, 'samples': 26318592, 'steps': 137075, 'loss/train': 0.9579687714576721} 08/31/2021 14:09:45 - INFO - __main__ - Step 137077: {'lr': 9.348775441493873e-06, 'samples': 26318784, 'steps': 137076, 'loss/train': 0.6112037897109985} 08/31/2021 14:09:46 - INFO - __main__ - Step 137078: {'lr': 9.347337849695742e-06, 'samples': 26318976, 'steps': 137077, 'loss/train': 0.7413927912712097} 08/31/2021 14:09:46 - INFO - __main__ - Step 137079: {'lr': 9.34590036633201e-06, 'samples': 26319168, 'steps': 137078, 'loss/train': 0.8948384523391724} 08/31/2021 14:09:48 - INFO - __main__ - Step 137080: {'lr': 9.344462991403263e-06, 'samples': 26319360, 'steps': 137079, 'loss/train': 1.1025726795196533} 08/31/2021 14:09:48 - INFO - __main__ - Step 137081: {'lr': 9.343025724910192e-06, 'samples': 26319552, 'steps': 137080, 'loss/train': 0.9626142382621765} 08/31/2021 14:09:49 - INFO - __main__ - Step 137082: {'lr': 9.341588566853465e-06, 'samples': 26319744, 'steps': 137081, 'loss/train': 1.3368756771087646} 08/31/2021 14:09:49 - INFO - __main__ - Step 137083: {'lr': 9.340151517233691e-06, 'samples': 26319936, 'steps': 137082, 'loss/train': 0.33647581934928894} 08/31/2021 14:09:49 - INFO - __main__ - Step 137084: {'lr': 9.338714576051538e-06, 'samples': 26320128, 'steps': 137083, 'loss/train': 1.2545086145401} 08/31/2021 14:09:51 - INFO - __main__ - Step 137085: {'lr': 9.337277743307642e-06, 'samples': 26320320, 'steps': 137084, 'loss/train': 0.4837310016155243} 08/31/2021 14:09:52 - INFO - __main__ - Step 137086: {'lr': 9.335841019002644e-06, 'samples': 26320512, 'steps': 137085, 'loss/train': 1.3182390928268433} 08/31/2021 14:09:52 - INFO - __main__ - Step 137087: {'lr': 9.334404403137209e-06, 'samples': 26320704, 'steps': 137086, 'loss/train': 0.013981943018734455} 08/31/2021 14:09:52 - INFO - __main__ - Step 137088: {'lr': 9.332967895712002e-06, 'samples': 26320896, 'steps': 137087, 'loss/train': 1.0472182035446167} 08/31/2021 14:09:53 - INFO - __main__ - Step 137089: {'lr': 9.331531496727635e-06, 'samples': 26321088, 'steps': 137088, 'loss/train': 0.873843789100647} 08/31/2021 14:09:53 - INFO - __main__ - Step 137090: {'lr': 9.330095206184747e-06, 'samples': 26321280, 'steps': 137089, 'loss/train': 0.8529538512229919} 08/31/2021 14:09:55 - INFO - __main__ - Step 137091: {'lr': 9.328659024084002e-06, 'samples': 26321472, 'steps': 137090, 'loss/train': 1.5508781671524048} 08/31/2021 14:09:55 - INFO - __main__ - Step 137092: {'lr': 9.327222950426068e-06, 'samples': 26321664, 'steps': 137091, 'loss/train': 1.5994471311569214} 08/31/2021 14:09:56 - INFO - __main__ - Step 137093: {'lr': 9.325786985211554e-06, 'samples': 26321856, 'steps': 137092, 'loss/train': 1.1658574342727661} 08/31/2021 14:09:56 - INFO - __main__ - Step 137094: {'lr': 9.324351128441155e-06, 'samples': 26322048, 'steps': 137093, 'loss/train': 1.0129119157791138} 08/31/2021 14:09:56 - INFO - __main__ - Step 137095: {'lr': 9.322915380115454e-06, 'samples': 26322240, 'steps': 137094, 'loss/train': 0.01536946464329958} 08/31/2021 14:09:57 - INFO - __main__ - Step 137096: {'lr': 9.321479740235172e-06, 'samples': 26322432, 'steps': 137095, 'loss/train': 0.6412767767906189} 08/31/2021 14:09:58 - INFO - __main__ - Step 137097: {'lr': 9.320044208800893e-06, 'samples': 26322624, 'steps': 137096, 'loss/train': 1.5298601388931274} 08/31/2021 14:09:59 - INFO - __main__ - Step 137098: {'lr': 9.318608785813281e-06, 'samples': 26322816, 'steps': 137097, 'loss/train': 1.13718581199646} 08/31/2021 14:09:59 - INFO - __main__ - Step 137099: {'lr': 9.317173471273005e-06, 'samples': 26323008, 'steps': 137098, 'loss/train': 0.580240786075592} 08/31/2021 14:09:59 - INFO - __main__ - Step 137100: {'lr': 9.315738265180702e-06, 'samples': 26323200, 'steps': 137099, 'loss/train': 1.5346205234527588} 08/31/2021 14:10:00 - INFO - __main__ - Step 137101: {'lr': 9.314303167537008e-06, 'samples': 26323392, 'steps': 137100, 'loss/train': 1.0818431377410889} 08/31/2021 14:10:01 - INFO - __main__ - Step 137102: {'lr': 9.312868178342593e-06, 'samples': 26323584, 'steps': 137101, 'loss/train': 1.4801260232925415} 08/31/2021 14:10:02 - INFO - __main__ - Step 137103: {'lr': 9.311433297598066e-06, 'samples': 26323776, 'steps': 137102, 'loss/train': 0.9457850456237793} 08/31/2021 14:10:02 - INFO - __main__ - Step 137104: {'lr': 9.309998525304064e-06, 'samples': 26323968, 'steps': 137103, 'loss/train': 1.1927332878112793} 08/31/2021 14:10:02 - INFO - __main__ - Step 137105: {'lr': 9.308563861461311e-06, 'samples': 26324160, 'steps': 137104, 'loss/train': 1.0684666633605957} 08/31/2021 14:10:03 - INFO - __main__ - Step 137106: {'lr': 9.307129306070362e-06, 'samples': 26324352, 'steps': 137105, 'loss/train': 1.204136610031128} 08/31/2021 14:10:03 - INFO - __main__ - Step 137107: {'lr': 9.305694859131935e-06, 'samples': 26324544, 'steps': 137106, 'loss/train': 0.7965953946113586} 08/31/2021 14:10:05 - INFO - __main__ - Step 137108: {'lr': 9.304260520646645e-06, 'samples': 26324736, 'steps': 137107, 'loss/train': 1.2588105201721191} 08/31/2021 14:10:05 - INFO - __main__ - Step 137109: {'lr': 9.30282629061513e-06, 'samples': 26324928, 'steps': 137108, 'loss/train': 0.5588743686676025} 08/31/2021 14:10:06 - INFO - __main__ - Step 137110: {'lr': 9.301392169038052e-06, 'samples': 26325120, 'steps': 137109, 'loss/train': 0.28932657837867737} 08/31/2021 14:10:06 - INFO - __main__ - Step 137111: {'lr': 9.299958155916056e-06, 'samples': 26325312, 'steps': 137110, 'loss/train': 1.0813605785369873} 08/31/2021 14:10:06 - INFO - __main__ - Step 137112: {'lr': 9.298524251249774e-06, 'samples': 26325504, 'steps': 137111, 'loss/train': 0.8638399839401245} 08/31/2021 14:10:08 - INFO - __main__ - Step 137113: {'lr': 9.297090455039874e-06, 'samples': 26325696, 'steps': 137112, 'loss/train': 1.1947712898254395} 08/31/2021 14:10:08 - INFO - __main__ - Step 137114: {'lr': 9.295656767286997e-06, 'samples': 26325888, 'steps': 137113, 'loss/train': 0.9323744177818298} 08/31/2021 14:10:09 - INFO - __main__ - Step 137115: {'lr': 9.294223187991806e-06, 'samples': 26326080, 'steps': 137114, 'loss/train': 1.4414470195770264} 08/31/2021 14:10:09 - INFO - __main__ - Step 137116: {'lr': 9.292789717154887e-06, 'samples': 26326272, 'steps': 137115, 'loss/train': 1.1493065357208252} 08/31/2021 14:10:09 - INFO - __main__ - Step 137117: {'lr': 9.291356354776931e-06, 'samples': 26326464, 'steps': 137116, 'loss/train': 1.4037786722183228} 08/31/2021 14:10:11 - INFO - __main__ - Step 137118: {'lr': 9.289923100858576e-06, 'samples': 26326656, 'steps': 137117, 'loss/train': 1.4853624105453491} 08/31/2021 14:10:11 - INFO - __main__ - Step 137119: {'lr': 9.288489955400465e-06, 'samples': 26326848, 'steps': 137118, 'loss/train': 1.8446986675262451} 08/31/2021 14:10:12 - INFO - __main__ - Step 137120: {'lr': 9.287056918403231e-06, 'samples': 26327040, 'steps': 137119, 'loss/train': 0.30306294560432434} 08/31/2021 14:10:12 - INFO - __main__ - Step 137121: {'lr': 9.285623989867541e-06, 'samples': 26327232, 'steps': 137120, 'loss/train': 0.5206472873687744} 08/31/2021 14:10:12 - INFO - __main__ - Step 137122: {'lr': 9.284191169794038e-06, 'samples': 26327424, 'steps': 137121, 'loss/train': 0.8524050712585449} 08/31/2021 14:10:14 - INFO - __main__ - Step 137123: {'lr': 9.282758458183383e-06, 'samples': 26327616, 'steps': 137122, 'loss/train': 1.1570415496826172} 08/31/2021 14:10:14 - INFO - __main__ - Step 137124: {'lr': 9.281325855036188e-06, 'samples': 26327808, 'steps': 137123, 'loss/train': 1.1634182929992676} 08/31/2021 14:10:15 - INFO - __main__ - Step 137125: {'lr': 9.279893360353093e-06, 'samples': 26328000, 'steps': 137124, 'loss/train': 1.5736380815505981} 08/31/2021 14:10:15 - INFO - __main__ - Step 137126: {'lr': 9.27846097413479e-06, 'samples': 26328192, 'steps': 137125, 'loss/train': 1.2749110460281372} 08/31/2021 14:10:15 - INFO - __main__ - Step 137127: {'lr': 9.27702869638189e-06, 'samples': 26328384, 'steps': 137126, 'loss/train': 0.06322434544563293} 08/31/2021 14:10:17 - INFO - __main__ - Step 137128: {'lr': 9.275596527095087e-06, 'samples': 26328576, 'steps': 137127, 'loss/train': 1.1293147802352905} 08/31/2021 14:10:17 - INFO - __main__ - Step 137129: {'lr': 9.274164466274937e-06, 'samples': 26328768, 'steps': 137128, 'loss/train': 1.3319181203842163} 08/31/2021 14:10:18 - INFO - __main__ - Step 137130: {'lr': 9.272732513922132e-06, 'samples': 26328960, 'steps': 137129, 'loss/train': 1.264028787612915} 08/31/2021 14:10:18 - INFO - __main__ - Step 137131: {'lr': 9.271300670037341e-06, 'samples': 26329152, 'steps': 137130, 'loss/train': 1.9951785802841187} 08/31/2021 14:10:18 - INFO - __main__ - Step 137132: {'lr': 9.269868934621173e-06, 'samples': 26329344, 'steps': 137131, 'loss/train': 1.0818345546722412} 08/31/2021 14:10:20 - INFO - __main__ - Step 137133: {'lr': 9.268437307674293e-06, 'samples': 26329536, 'steps': 137132, 'loss/train': 1.0981066226959229} 08/31/2021 14:10:21 - INFO - __main__ - Step 137134: {'lr': 9.267005789197341e-06, 'samples': 26329728, 'steps': 137133, 'loss/train': 0.7281706929206848} 08/31/2021 14:10:21 - INFO - __main__ - Step 137135: {'lr': 9.265574379190955e-06, 'samples': 26329920, 'steps': 137134, 'loss/train': 0.7514548897743225} 08/31/2021 14:10:21 - INFO - __main__ - Step 137136: {'lr': 9.264143077655773e-06, 'samples': 26330112, 'steps': 137135, 'loss/train': 1.316535472869873} 08/31/2021 14:10:22 - INFO - __main__ - Step 137137: {'lr': 9.262711884592462e-06, 'samples': 26330304, 'steps': 137136, 'loss/train': 0.9465700387954712} 08/31/2021 14:10:23 - INFO - __main__ - Step 137138: {'lr': 9.261280800001686e-06, 'samples': 26330496, 'steps': 137137, 'loss/train': 1.5000238418579102} 08/31/2021 14:10:24 - INFO - __main__ - Step 137139: {'lr': 9.259849823884031e-06, 'samples': 26330688, 'steps': 137138, 'loss/train': 0.9817028045654297} 08/31/2021 14:10:24 - INFO - __main__ - Step 137140: {'lr': 9.258418956240189e-06, 'samples': 26330880, 'steps': 137139, 'loss/train': 1.2928521633148193} 08/31/2021 14:10:24 - INFO - __main__ - Step 137141: {'lr': 9.25698819707077e-06, 'samples': 26331072, 'steps': 137140, 'loss/train': 1.1680095195770264} 08/31/2021 14:10:25 - INFO - __main__ - Step 137142: {'lr': 9.255557546376498e-06, 'samples': 26331264, 'steps': 137141, 'loss/train': 0.25031179189682007} 08/31/2021 14:10:25 - INFO - __main__ - Step 137143: {'lr': 9.254127004157897e-06, 'samples': 26331456, 'steps': 137142, 'loss/train': 1.035341501235962} 08/31/2021 14:10:27 - INFO - __main__ - Step 137144: {'lr': 9.252696570415691e-06, 'samples': 26331648, 'steps': 137143, 'loss/train': 0.02613486535847187} 08/31/2021 14:10:27 - INFO - __main__ - Step 137145: {'lr': 9.25126624515049e-06, 'samples': 26331840, 'steps': 137144, 'loss/train': 0.9482933282852173} 08/31/2021 14:10:27 - INFO - __main__ - Step 137146: {'lr': 9.249836028362962e-06, 'samples': 26332032, 'steps': 137145, 'loss/train': 1.2574297189712524} 08/31/2021 14:10:28 - INFO - __main__ - Step 137147: {'lr': 9.248405920053743e-06, 'samples': 26332224, 'steps': 137146, 'loss/train': 1.1377919912338257} 08/31/2021 14:10:28 - INFO - __main__ - Step 137148: {'lr': 9.246975920223471e-06, 'samples': 26332416, 'steps': 137147, 'loss/train': 0.896892786026001} 08/31/2021 14:10:30 - INFO - __main__ - Step 137149: {'lr': 9.245546028872814e-06, 'samples': 26332608, 'steps': 137148, 'loss/train': 1.1046209335327148} 08/31/2021 14:10:30 - INFO - __main__ - Step 137150: {'lr': 9.244116246002382e-06, 'samples': 26332800, 'steps': 137149, 'loss/train': 0.9398761987686157} 08/31/2021 14:10:31 - INFO - __main__ - Step 137151: {'lr': 9.242686571612841e-06, 'samples': 26332992, 'steps': 137150, 'loss/train': 1.0222078561782837} 08/31/2021 14:10:31 - INFO - __main__ - Step 137152: {'lr': 9.241257005704828e-06, 'samples': 26333184, 'steps': 137151, 'loss/train': 1.3744466304779053} 08/31/2021 14:10:31 - INFO - __main__ - Step 137153: {'lr': 9.239827548278983e-06, 'samples': 26333376, 'steps': 137152, 'loss/train': 1.3207043409347534} 08/31/2021 14:10:33 - INFO - __main__ - Step 137154: {'lr': 9.238398199335974e-06, 'samples': 26333568, 'steps': 137153, 'loss/train': 1.6110200881958008} 08/31/2021 14:10:33 - INFO - __main__ - Step 137155: {'lr': 9.236968958876435e-06, 'samples': 26333760, 'steps': 137154, 'loss/train': 1.4616411924362183} 08/31/2021 14:10:34 - INFO - __main__ - Step 137156: {'lr': 9.23553982690098e-06, 'samples': 26333952, 'steps': 137155, 'loss/train': 1.2118264436721802} 08/31/2021 14:10:34 - INFO - __main__ - Step 137157: {'lr': 9.2341108034103e-06, 'samples': 26334144, 'steps': 137156, 'loss/train': 1.1282254457473755} 08/31/2021 14:10:34 - INFO - __main__ - Step 137158: {'lr': 9.232681888404981e-06, 'samples': 26334336, 'steps': 137157, 'loss/train': 0.45205843448638916} 08/31/2021 14:10:36 - INFO - __main__ - Step 137159: {'lr': 9.231253081885715e-06, 'samples': 26334528, 'steps': 137158, 'loss/train': 0.11061786860227585} 08/31/2021 14:10:37 - INFO - __main__ - Step 137160: {'lr': 9.229824383853141e-06, 'samples': 26334720, 'steps': 137159, 'loss/train': 0.9227688312530518} 08/31/2021 14:10:37 - INFO - __main__ - Step 137161: {'lr': 9.22839579430787e-06, 'samples': 26334912, 'steps': 137160, 'loss/train': 1.1655875444412231} 08/31/2021 14:10:37 - INFO - __main__ - Step 137162: {'lr': 9.226967313250595e-06, 'samples': 26335104, 'steps': 137161, 'loss/train': 1.4256377220153809} 08/31/2021 14:10:38 - INFO - __main__ - Step 137163: {'lr': 9.225538940681927e-06, 'samples': 26335296, 'steps': 137162, 'loss/train': 0.8812872171401978} 08/31/2021 14:10:38 - INFO - __main__ - Step 137164: {'lr': 9.224110676602504e-06, 'samples': 26335488, 'steps': 137163, 'loss/train': 0.7157670259475708} 08/31/2021 14:10:40 - INFO - __main__ - Step 137165: {'lr': 9.222682521012966e-06, 'samples': 26335680, 'steps': 137164, 'loss/train': 1.4680050611495972} 08/31/2021 14:10:41 - INFO - __main__ - Step 137166: {'lr': 9.221254473914004e-06, 'samples': 26335872, 'steps': 137165, 'loss/train': 0.0850464329123497} 08/31/2021 14:10:41 - INFO - __main__ - Step 137167: {'lr': 9.21982653530623e-06, 'samples': 26336064, 'steps': 137166, 'loss/train': 0.09693989902734756} 08/31/2021 14:10:41 - INFO - __main__ - Step 137168: {'lr': 9.218398705190285e-06, 'samples': 26336256, 'steps': 137167, 'loss/train': 0.9533519744873047} 08/31/2021 14:10:42 - INFO - __main__ - Step 137169: {'lr': 9.216970983566803e-06, 'samples': 26336448, 'steps': 137168, 'loss/train': 1.067888617515564} 08/31/2021 14:10:43 - INFO - __main__ - Step 137170: {'lr': 9.215543370436452e-06, 'samples': 26336640, 'steps': 137169, 'loss/train': 1.2458775043487549} 08/31/2021 14:10:44 - INFO - __main__ - Step 137171: {'lr': 9.214115865799843e-06, 'samples': 26336832, 'steps': 137170, 'loss/train': 1.2993762493133545} 08/31/2021 14:10:44 - INFO - __main__ - Step 137172: {'lr': 9.212688469657643e-06, 'samples': 26337024, 'steps': 137171, 'loss/train': 1.7387787103652954} 08/31/2021 14:10:44 - INFO - __main__ - Step 137173: {'lr': 9.211261182010488e-06, 'samples': 26337216, 'steps': 137172, 'loss/train': 1.6329702138900757} 08/31/2021 14:10:45 - INFO - __main__ - Step 137174: {'lr': 9.209834002859018e-06, 'samples': 26337408, 'steps': 137173, 'loss/train': 1.331343173980713} 08/31/2021 14:10:46 - INFO - __main__ - Step 137175: {'lr': 9.2084069322039e-06, 'samples': 26337600, 'steps': 137174, 'loss/train': 0.20318882167339325} 08/31/2021 14:10:47 - INFO - __main__ - Step 137176: {'lr': 9.206979970045742e-06, 'samples': 26337792, 'steps': 137175, 'loss/train': 0.8464070558547974} 08/31/2021 14:10:47 - INFO - __main__ - Step 137177: {'lr': 9.205553116385212e-06, 'samples': 26337984, 'steps': 137176, 'loss/train': 0.817768931388855} 08/31/2021 14:10:47 - INFO - __main__ - Step 137178: {'lr': 9.204126371222921e-06, 'samples': 26338176, 'steps': 137177, 'loss/train': 0.8676208257675171} 08/31/2021 14:10:48 - INFO - __main__ - Step 137179: {'lr': 9.20269973455956e-06, 'samples': 26338368, 'steps': 137178, 'loss/train': 0.2004457712173462} 08/31/2021 14:10:50 - INFO - __main__ - Step 137180: {'lr': 9.201273206395743e-06, 'samples': 26338560, 'steps': 137179, 'loss/train': 0.8477285504341125} 08/31/2021 14:10:50 - INFO - __main__ - Step 137181: {'lr': 9.199846786732108e-06, 'samples': 26338752, 'steps': 137180, 'loss/train': 1.3989988565444946} 08/31/2021 14:10:51 - INFO - __main__ - Step 137182: {'lr': 9.198420475569346e-06, 'samples': 26338944, 'steps': 137181, 'loss/train': 1.3778764009475708} 08/31/2021 14:10:51 - INFO - __main__ - Step 137183: {'lr': 9.196994272908016e-06, 'samples': 26339136, 'steps': 137182, 'loss/train': 1.1840217113494873} 08/31/2021 14:10:51 - INFO - __main__ - Step 137184: {'lr': 9.195568178748809e-06, 'samples': 26339328, 'steps': 137183, 'loss/train': 0.44391342997550964} 08/31/2021 14:10:52 - INFO - __main__ - Step 137185: {'lr': 9.194142193092392e-06, 'samples': 26339520, 'steps': 137184, 'loss/train': 1.2590813636779785} 08/31/2021 14:10:52 - INFO - __main__ - Step 137186: {'lr': 9.192716315939349e-06, 'samples': 26339712, 'steps': 137185, 'loss/train': 0.028192982077598572} 08/31/2021 14:10:54 - INFO - __main__ - Step 137187: {'lr': 9.191290547290343e-06, 'samples': 26339904, 'steps': 137186, 'loss/train': 0.2507881820201874} 08/31/2021 14:10:54 - INFO - __main__ - Step 137188: {'lr': 9.189864887146044e-06, 'samples': 26340096, 'steps': 137187, 'loss/train': 1.1764335632324219} 08/31/2021 14:10:54 - INFO - __main__ - Step 137189: {'lr': 9.188439335507087e-06, 'samples': 26340288, 'steps': 137188, 'loss/train': 1.4606590270996094} 08/31/2021 14:10:55 - INFO - __main__ - Step 137190: {'lr': 9.187013892374085e-06, 'samples': 26340480, 'steps': 137189, 'loss/train': 0.33993202447891235} 08/31/2021 14:10:55 - INFO - __main__ - Step 137191: {'lr': 9.185588557747704e-06, 'samples': 26340672, 'steps': 137190, 'loss/train': 1.1841908693313599} 08/31/2021 14:10:57 - INFO - __main__ - Step 137192: {'lr': 9.18416333162858e-06, 'samples': 26340864, 'steps': 137191, 'loss/train': 1.6123371124267578} 08/31/2021 14:10:57 - INFO - __main__ - Step 137193: {'lr': 9.182738214017355e-06, 'samples': 26341056, 'steps': 137192, 'loss/train': 0.46613505482673645} 08/31/2021 14:10:57 - INFO - __main__ - Step 137194: {'lr': 9.181313204914665e-06, 'samples': 26341248, 'steps': 137193, 'loss/train': 1.2080186605453491} 08/31/2021 14:10:58 - INFO - __main__ - Step 137195: {'lr': 9.179888304321205e-06, 'samples': 26341440, 'steps': 137194, 'loss/train': 1.697615146636963} 08/31/2021 14:10:58 - INFO - __main__ - Step 137196: {'lr': 9.178463512237528e-06, 'samples': 26341632, 'steps': 137195, 'loss/train': 0.13128973543643951} 08/31/2021 14:11:00 - INFO - __main__ - Step 137197: {'lr': 9.17703882866433e-06, 'samples': 26341824, 'steps': 137196, 'loss/train': 1.0667463541030884} 08/31/2021 14:11:00 - INFO - __main__ - Step 137198: {'lr': 9.17561425360222e-06, 'samples': 26342016, 'steps': 137197, 'loss/train': 0.1369190812110901} 08/31/2021 14:11:01 - INFO - __main__ - Step 137199: {'lr': 9.174189787051896e-06, 'samples': 26342208, 'steps': 137198, 'loss/train': 1.4719306230545044} 08/31/2021 14:11:01 - INFO - __main__ - Step 137200: {'lr': 9.172765429013935e-06, 'samples': 26342400, 'steps': 137199, 'loss/train': 1.6536377668380737} 08/31/2021 14:11:01 - INFO - __main__ - Step 137201: {'lr': 9.171341179489035e-06, 'samples': 26342592, 'steps': 137200, 'loss/train': 0.20283611118793488} 08/31/2021 14:11:02 - INFO - __main__ - Step 137202: {'lr': 9.169917038477805e-06, 'samples': 26342784, 'steps': 137201, 'loss/train': 1.0577143430709839} 08/31/2021 14:11:03 - INFO - __main__ - Step 137203: {'lr': 9.168493005980882e-06, 'samples': 26342976, 'steps': 137202, 'loss/train': 2.4425859451293945} 08/31/2021 14:11:04 - INFO - __main__ - Step 137204: {'lr': 9.167069081998936e-06, 'samples': 26343168, 'steps': 137203, 'loss/train': 0.9534773230552673} 08/31/2021 14:11:04 - INFO - __main__ - Step 137205: {'lr': 9.165645266532573e-06, 'samples': 26343360, 'steps': 137204, 'loss/train': 0.047175705432891846} 08/31/2021 14:11:05 - INFO - __main__ - Step 137206: {'lr': 9.164221559582464e-06, 'samples': 26343552, 'steps': 137205, 'loss/train': 0.6027367115020752} 08/31/2021 14:11:05 - INFO - __main__ - Step 137207: {'lr': 9.162797961149244e-06, 'samples': 26343744, 'steps': 137206, 'loss/train': 0.20518314838409424} 08/31/2021 14:11:07 - INFO - __main__ - Step 137208: {'lr': 9.161374471233552e-06, 'samples': 26343936, 'steps': 137207, 'loss/train': 0.5814328193664551} 08/31/2021 14:11:07 - INFO - __main__ - Step 137209: {'lr': 9.159951089836055e-06, 'samples': 26344128, 'steps': 137208, 'loss/train': 0.6859725713729858} 08/31/2021 14:11:07 - INFO - __main__ - Step 137210: {'lr': 9.158527816957334e-06, 'samples': 26344320, 'steps': 137209, 'loss/train': 1.3365455865859985} 08/31/2021 14:11:08 - INFO - __main__ - Step 137211: {'lr': 9.157104652598059e-06, 'samples': 26344512, 'steps': 137210, 'loss/train': 0.4479696452617645} 08/31/2021 14:11:08 - INFO - __main__ - Step 137212: {'lr': 9.155681596758892e-06, 'samples': 26344704, 'steps': 137211, 'loss/train': 1.1086500883102417} 08/31/2021 14:11:10 - INFO - __main__ - Step 137213: {'lr': 9.154258649440445e-06, 'samples': 26344896, 'steps': 137212, 'loss/train': 1.2085539102554321} 08/31/2021 14:11:10 - INFO - __main__ - Step 137214: {'lr': 9.152835810643384e-06, 'samples': 26345088, 'steps': 137213, 'loss/train': 0.6455954909324646} 08/31/2021 14:11:11 - INFO - __main__ - Step 137215: {'lr': 9.15141308036832e-06, 'samples': 26345280, 'steps': 137214, 'loss/train': 1.2066645622253418} 08/31/2021 14:11:11 - INFO - __main__ - Step 137216: {'lr': 9.14999045861592e-06, 'samples': 26345472, 'steps': 137215, 'loss/train': 1.050813913345337} 08/31/2021 14:11:11 - INFO - __main__ - Step 137217: {'lr': 9.14856794538685e-06, 'samples': 26345664, 'steps': 137216, 'loss/train': 0.7255371809005737} 08/31/2021 14:11:12 - INFO - __main__ - Step 137218: {'lr': 9.14714554068169e-06, 'samples': 26345856, 'steps': 137217, 'loss/train': 0.7213227152824402} 08/31/2021 14:11:14 - INFO - __main__ - Step 137219: {'lr': 9.145723244501108e-06, 'samples': 26346048, 'steps': 137218, 'loss/train': 0.7415085434913635} 08/31/2021 14:11:14 - INFO - __main__ - Step 137220: {'lr': 9.144301056845744e-06, 'samples': 26346240, 'steps': 137219, 'loss/train': 0.9756975173950195} 08/31/2021 14:11:14 - INFO - __main__ - Step 137221: {'lr': 9.142878977716235e-06, 'samples': 26346432, 'steps': 137220, 'loss/train': 0.34638768434524536} 08/31/2021 14:11:15 - INFO - __main__ - Step 137222: {'lr': 9.141457007113274e-06, 'samples': 26346624, 'steps': 137221, 'loss/train': 0.5260291695594788} 08/31/2021 14:11:15 - INFO - __main__ - Step 137223: {'lr': 9.140035145037417e-06, 'samples': 26346816, 'steps': 137222, 'loss/train': 1.0959136486053467} 08/31/2021 14:11:16 - INFO - __main__ - Step 137224: {'lr': 9.138613391489358e-06, 'samples': 26347008, 'steps': 137223, 'loss/train': 1.3772777318954468} 08/31/2021 14:11:17 - INFO - __main__ - Step 137225: {'lr': 9.13719174646971e-06, 'samples': 26347200, 'steps': 137224, 'loss/train': 0.8717830777168274} 08/31/2021 14:11:17 - INFO - __main__ - Step 137226: {'lr': 9.135770209979133e-06, 'samples': 26347392, 'steps': 137225, 'loss/train': 1.5793265104293823} 08/31/2021 14:11:18 - INFO - __main__ - Step 137227: {'lr': 9.13434878201827e-06, 'samples': 26347584, 'steps': 137226, 'loss/train': 1.473512887954712} 08/31/2021 14:11:18 - INFO - __main__ - Step 137228: {'lr': 9.132927462587731e-06, 'samples': 26347776, 'steps': 137227, 'loss/train': 0.23162288963794708} 08/31/2021 14:11:19 - INFO - __main__ - Step 137229: {'lr': 9.131506251688182e-06, 'samples': 26347968, 'steps': 137228, 'loss/train': 1.150462031364441} 08/31/2021 14:11:20 - INFO - __main__ - Step 137230: {'lr': 9.130085149320289e-06, 'samples': 26348160, 'steps': 137229, 'loss/train': 0.8937686681747437} 08/31/2021 14:11:20 - INFO - __main__ - Step 137231: {'lr': 9.128664155484633e-06, 'samples': 26348352, 'steps': 137230, 'loss/train': 2.1113030910491943} 08/31/2021 14:11:21 - INFO - __main__ - Step 137232: {'lr': 9.127243270181884e-06, 'samples': 26348544, 'steps': 137231, 'loss/train': 1.296486496925354} 08/31/2021 14:11:21 - INFO - __main__ - Step 137233: {'lr': 9.125822493412677e-06, 'samples': 26348736, 'steps': 137232, 'loss/train': 0.965594470500946} 08/31/2021 14:11:23 - INFO - __main__ - Step 137234: {'lr': 9.12440182517768e-06, 'samples': 26348928, 'steps': 137233, 'loss/train': 1.327548861503601} 08/31/2021 14:11:23 - INFO - __main__ - Step 137235: {'lr': 9.122981265477504e-06, 'samples': 26349120, 'steps': 137234, 'loss/train': 1.198433518409729} 08/31/2021 14:11:24 - INFO - __main__ - Step 137236: {'lr': 9.121560814312813e-06, 'samples': 26349312, 'steps': 137235, 'loss/train': 1.156348705291748} 08/31/2021 14:11:24 - INFO - __main__ - Step 137237: {'lr': 9.120140471684219e-06, 'samples': 26349504, 'steps': 137236, 'loss/train': 1.3093719482421875} 08/31/2021 14:11:24 - INFO - __main__ - Step 137238: {'lr': 9.11872023759236e-06, 'samples': 26349696, 'steps': 137237, 'loss/train': 0.04170307517051697} 08/31/2021 14:11:26 - INFO - __main__ - Step 137239: {'lr': 9.117300112037902e-06, 'samples': 26349888, 'steps': 137238, 'loss/train': 1.2184113264083862} 08/31/2021 14:11:26 - INFO - __main__ - Step 137240: {'lr': 9.115880095021456e-06, 'samples': 26350080, 'steps': 137239, 'loss/train': 1.2288559675216675} 08/31/2021 14:11:27 - INFO - __main__ - Step 137241: {'lr': 9.114460186543688e-06, 'samples': 26350272, 'steps': 137240, 'loss/train': 1.0928571224212646} 08/31/2021 14:11:27 - INFO - __main__ - Step 137242: {'lr': 9.113040386605209e-06, 'samples': 26350464, 'steps': 137241, 'loss/train': 1.8178060054779053} 08/31/2021 14:11:27 - INFO - __main__ - Step 137243: {'lr': 9.111620695206685e-06, 'samples': 26350656, 'steps': 137242, 'loss/train': 1.1772220134735107} 08/31/2021 14:11:29 - INFO - __main__ - Step 137244: {'lr': 9.110201112348753e-06, 'samples': 26350848, 'steps': 137243, 'loss/train': 0.9523506760597229} 08/31/2021 14:11:29 - INFO - __main__ - Step 137245: {'lr': 9.108781638032055e-06, 'samples': 26351040, 'steps': 137244, 'loss/train': 1.178557276725769} 08/31/2021 14:11:30 - INFO - __main__ - Step 137246: {'lr': 9.107362272257197e-06, 'samples': 26351232, 'steps': 137245, 'loss/train': 0.26766204833984375} 08/31/2021 14:11:30 - INFO - __main__ - Step 137247: {'lr': 9.105943015024904e-06, 'samples': 26351424, 'steps': 137246, 'loss/train': 1.244876742362976} 08/31/2021 14:11:30 - INFO - __main__ - Step 137248: {'lr': 9.104523866335702e-06, 'samples': 26351616, 'steps': 137247, 'loss/train': 1.1584999561309814} 08/31/2021 14:11:32 - INFO - __main__ - Step 137249: {'lr': 9.103104826190311e-06, 'samples': 26351808, 'steps': 137248, 'loss/train': 1.0410178899765015} 08/31/2021 14:11:33 - INFO - __main__ - Step 137250: {'lr': 9.101685894589318e-06, 'samples': 26352000, 'steps': 137249, 'loss/train': 1.1506085395812988} 08/31/2021 14:11:33 - INFO - __main__ - Step 137251: {'lr': 9.100267071533386e-06, 'samples': 26352192, 'steps': 137250, 'loss/train': 1.339738130569458} 08/31/2021 14:11:33 - INFO - __main__ - Step 137252: {'lr': 9.098848357023182e-06, 'samples': 26352384, 'steps': 137251, 'loss/train': 1.0830438137054443} 08/31/2021 14:11:34 - INFO - __main__ - Step 137253: {'lr': 9.097429751059316e-06, 'samples': 26352576, 'steps': 137252, 'loss/train': 1.2407664060592651} 08/31/2021 14:11:34 - INFO - __main__ - Step 137254: {'lr': 9.0960112536424e-06, 'samples': 26352768, 'steps': 137253, 'loss/train': 1.3878259658813477} 08/31/2021 14:11:36 - INFO - __main__ - Step 137255: {'lr': 9.094592864773126e-06, 'samples': 26352960, 'steps': 137254, 'loss/train': 0.47624287009239197} 08/31/2021 14:11:36 - INFO - __main__ - Step 137256: {'lr': 9.093174584452107e-06, 'samples': 26353152, 'steps': 137255, 'loss/train': 0.8066801428794861} 08/31/2021 14:11:36 - INFO - __main__ - Step 137257: {'lr': 9.091756412680008e-06, 'samples': 26353344, 'steps': 137256, 'loss/train': 0.6378023624420166} 08/31/2021 14:11:37 - INFO - __main__ - Step 137258: {'lr': 9.09033834945744e-06, 'samples': 26353536, 'steps': 137257, 'loss/train': 1.7041497230529785} 08/31/2021 14:11:37 - INFO - __main__ - Step 137259: {'lr': 9.088920394785038e-06, 'samples': 26353728, 'steps': 137258, 'loss/train': 0.12886656820774078} 08/31/2021 14:11:39 - INFO - __main__ - Step 137260: {'lr': 9.087502548663446e-06, 'samples': 26353920, 'steps': 137259, 'loss/train': 1.6434358358383179} 08/31/2021 14:11:39 - INFO - __main__ - Step 137261: {'lr': 9.086084811093326e-06, 'samples': 26354112, 'steps': 137260, 'loss/train': 1.002865195274353} 08/31/2021 14:11:39 - INFO - __main__ - Step 137262: {'lr': 9.084667182075262e-06, 'samples': 26354304, 'steps': 137261, 'loss/train': 0.9486191868782043} 08/31/2021 14:11:40 - INFO - __main__ - Step 137263: {'lr': 9.08324966160995e-06, 'samples': 26354496, 'steps': 137262, 'loss/train': 0.8664988875389099} 08/31/2021 14:11:40 - INFO - __main__ - Step 137264: {'lr': 9.081832249698024e-06, 'samples': 26354688, 'steps': 137263, 'loss/train': 0.8432340621948242} 08/31/2021 14:11:42 - INFO - __main__ - Step 137265: {'lr': 9.080414946340071e-06, 'samples': 26354880, 'steps': 137264, 'loss/train': 0.11837233603000641} 08/31/2021 14:11:42 - INFO - __main__ - Step 137266: {'lr': 9.078997751536783e-06, 'samples': 26355072, 'steps': 137265, 'loss/train': 0.05199039727449417} 08/31/2021 14:11:43 - INFO - __main__ - Step 137267: {'lr': 9.077580665288799e-06, 'samples': 26355264, 'steps': 137266, 'loss/train': 0.31446486711502075} 08/31/2021 14:11:43 - INFO - __main__ - Step 137268: {'lr': 9.076163687596728e-06, 'samples': 26355456, 'steps': 137267, 'loss/train': 1.3119862079620361} 08/31/2021 14:11:43 - INFO - __main__ - Step 137269: {'lr': 9.074746818461237e-06, 'samples': 26355648, 'steps': 137268, 'loss/train': 0.7072003483772278} 08/31/2021 14:11:45 - INFO - __main__ - Step 137270: {'lr': 9.073330057882939e-06, 'samples': 26355840, 'steps': 137269, 'loss/train': 0.8430429697036743} 08/31/2021 14:11:46 - INFO - __main__ - Step 137271: {'lr': 9.071913405862443e-06, 'samples': 26356032, 'steps': 137270, 'loss/train': 0.5844243764877319} 08/31/2021 14:11:46 - INFO - __main__ - Step 137272: {'lr': 9.070496862400468e-06, 'samples': 26356224, 'steps': 137271, 'loss/train': 0.7228031158447266} 08/31/2021 14:11:47 - INFO - __main__ - Step 137273: {'lr': 9.069080427497572e-06, 'samples': 26356416, 'steps': 137272, 'loss/train': 0.3413030207157135} 08/31/2021 14:11:47 - INFO - __main__ - Step 137274: {'lr': 9.067664101154476e-06, 'samples': 26356608, 'steps': 137273, 'loss/train': 0.02689608372747898} 08/31/2021 14:11:47 - INFO - __main__ - Step 137275: {'lr': 9.066247883371736e-06, 'samples': 26356800, 'steps': 137274, 'loss/train': 1.6656066179275513} 08/31/2021 14:11:50 - INFO - __main__ - Step 137276: {'lr': 9.064831774150045e-06, 'samples': 26356992, 'steps': 137275, 'loss/train': 0.8962531089782715} 08/31/2021 14:11:50 - INFO - __main__ - Step 137277: {'lr': 9.063415773490014e-06, 'samples': 26357184, 'steps': 137276, 'loss/train': 1.8825119733810425} 08/31/2021 14:11:51 - INFO - __main__ - Step 137278: {'lr': 9.06199988139228e-06, 'samples': 26357376, 'steps': 137277, 'loss/train': 0.9128627777099609} 08/31/2021 14:11:51 - INFO - __main__ - Step 137279: {'lr': 9.06058409785751e-06, 'samples': 26357568, 'steps': 137278, 'loss/train': 0.799906849861145} 08/31/2021 14:11:51 - INFO - __main__ - Step 137280: {'lr': 9.059168422886344e-06, 'samples': 26357760, 'steps': 137279, 'loss/train': 1.3452039957046509} 08/31/2021 14:11:52 - INFO - __main__ - Step 137281: {'lr': 9.057752856479362e-06, 'samples': 26357952, 'steps': 137280, 'loss/train': 1.0332659482955933} 08/31/2021 14:11:52 - INFO - __main__ - Step 137282: {'lr': 9.05633739863726e-06, 'samples': 26358144, 'steps': 137281, 'loss/train': 1.626752495765686} 08/31/2021 14:11:53 - INFO - __main__ - Step 137283: {'lr': 9.05492204936062e-06, 'samples': 26358336, 'steps': 137282, 'loss/train': 1.7119048833847046} 08/31/2021 14:11:54 - INFO - __main__ - Step 137284: {'lr': 9.053506808650136e-06, 'samples': 26358528, 'steps': 137283, 'loss/train': 0.8657079935073853} 08/31/2021 14:11:54 - INFO - __main__ - Step 137285: {'lr': 9.052091676506419e-06, 'samples': 26358720, 'steps': 137284, 'loss/train': 1.126765251159668} 08/31/2021 14:11:55 - INFO - __main__ - Step 137286: {'lr': 9.050676652930134e-06, 'samples': 26358912, 'steps': 137285, 'loss/train': 1.6193228960037231} 08/31/2021 14:11:55 - INFO - __main__ - Step 137287: {'lr': 9.049261737921866e-06, 'samples': 26359104, 'steps': 137286, 'loss/train': 1.3764171600341797} 08/31/2021 14:11:57 - INFO - __main__ - Step 137288: {'lr': 9.047846931482306e-06, 'samples': 26359296, 'steps': 137287, 'loss/train': 0.9424717426300049} 08/31/2021 14:11:57 - INFO - __main__ - Step 137289: {'lr': 9.04643223361204e-06, 'samples': 26359488, 'steps': 137288, 'loss/train': 0.2156509906053543} 08/31/2021 14:11:57 - INFO - __main__ - Step 137290: {'lr': 9.045017644311787e-06, 'samples': 26359680, 'steps': 137289, 'loss/train': 0.8033320903778076} 08/31/2021 14:11:58 - INFO - __main__ - Step 137291: {'lr': 9.043603163582104e-06, 'samples': 26359872, 'steps': 137290, 'loss/train': 1.223145842552185} 08/31/2021 14:11:58 - INFO - __main__ - Step 137292: {'lr': 9.042188791423628e-06, 'samples': 26360064, 'steps': 137291, 'loss/train': 1.0086122751235962} 08/31/2021 14:12:00 - INFO - __main__ - Step 137293: {'lr': 9.040774527837054e-06, 'samples': 26360256, 'steps': 137292, 'loss/train': 1.4116240739822388} 08/31/2021 14:12:00 - INFO - __main__ - Step 137294: {'lr': 9.039360372822964e-06, 'samples': 26360448, 'steps': 137293, 'loss/train': 1.2473324537277222} 08/31/2021 14:12:00 - INFO - __main__ - Step 137295: {'lr': 9.037946326382025e-06, 'samples': 26360640, 'steps': 137294, 'loss/train': 1.2522369623184204} 08/31/2021 14:12:01 - INFO - __main__ - Step 137296: {'lr': 9.036532388514873e-06, 'samples': 26360832, 'steps': 137295, 'loss/train': 1.3717827796936035} 08/31/2021 14:12:01 - INFO - __main__ - Step 137297: {'lr': 9.03511855922215e-06, 'samples': 26361024, 'steps': 137296, 'loss/train': 1.6884821653366089} 08/31/2021 14:12:02 - INFO - __main__ - Step 137298: {'lr': 9.033704838504492e-06, 'samples': 26361216, 'steps': 137297, 'loss/train': 1.2462687492370605} 08/31/2021 14:12:03 - INFO - __main__ - Step 137299: {'lr': 9.03229122636251e-06, 'samples': 26361408, 'steps': 137298, 'loss/train': 1.4548200368881226} 08/31/2021 14:12:03 - INFO - __main__ - Step 137300: {'lr': 9.030877722796843e-06, 'samples': 26361600, 'steps': 137299, 'loss/train': 0.8441157937049866} 08/31/2021 14:12:04 - INFO - __main__ - Step 137301: {'lr': 9.029464327808185e-06, 'samples': 26361792, 'steps': 137300, 'loss/train': 1.2920935153961182} 08/31/2021 14:12:04 - INFO - __main__ - Step 137302: {'lr': 9.028051041397089e-06, 'samples': 26361984, 'steps': 137301, 'loss/train': 0.6062043905258179} 08/31/2021 14:12:05 - INFO - __main__ - Step 137303: {'lr': 9.026637863564307e-06, 'samples': 26362176, 'steps': 137302, 'loss/train': 0.6199755668640137} 08/31/2021 14:12:06 - INFO - __main__ - Step 137304: {'lr': 9.025224794310339e-06, 'samples': 26362368, 'steps': 137303, 'loss/train': 0.4436989426612854} 08/31/2021 14:12:06 - INFO - __main__ - Step 137305: {'lr': 9.023811833635903e-06, 'samples': 26362560, 'steps': 137304, 'loss/train': 0.7575865983963013} 08/31/2021 14:12:07 - INFO - __main__ - Step 137306: {'lr': 9.022398981541613e-06, 'samples': 26362752, 'steps': 137305, 'loss/train': 1.152093529701233} 08/31/2021 14:12:07 - INFO - __main__ - Step 137307: {'lr': 9.020986238028105e-06, 'samples': 26362944, 'steps': 137306, 'loss/train': 0.5493634343147278} 08/31/2021 14:12:08 - INFO - __main__ - Step 137308: {'lr': 9.019573603096048e-06, 'samples': 26363136, 'steps': 137307, 'loss/train': 1.1907975673675537} 08/31/2021 14:12:09 - INFO - __main__ - Step 137309: {'lr': 9.018161076746023e-06, 'samples': 26363328, 'steps': 137308, 'loss/train': 1.1970458030700684} 08/31/2021 14:12:09 - INFO - __main__ - Step 137310: {'lr': 9.016748658978723e-06, 'samples': 26363520, 'steps': 137309, 'loss/train': 1.3357821702957153} 08/31/2021 14:12:10 - INFO - __main__ - Step 137311: {'lr': 9.015336349794734e-06, 'samples': 26363712, 'steps': 137310, 'loss/train': 0.5944788455963135} 08/31/2021 14:12:10 - INFO - __main__ - Step 137312: {'lr': 9.013924149194746e-06, 'samples': 26363904, 'steps': 137311, 'loss/train': 1.400904893875122} 08/31/2021 14:12:12 - INFO - __main__ - Step 137313: {'lr': 9.012512057179345e-06, 'samples': 26364096, 'steps': 137312, 'loss/train': 0.9633870124816895} 08/31/2021 14:12:12 - INFO - __main__ - Step 137314: {'lr': 9.011100073749167e-06, 'samples': 26364288, 'steps': 137313, 'loss/train': 0.9008782505989075} 08/31/2021 14:12:12 - INFO - __main__ - Step 137315: {'lr': 9.009688198904908e-06, 'samples': 26364480, 'steps': 137314, 'loss/train': 0.7916605472564697} 08/31/2021 14:12:13 - INFO - __main__ - Step 137316: {'lr': 9.008276432647178e-06, 'samples': 26364672, 'steps': 137315, 'loss/train': 0.9841888546943665} 08/31/2021 14:12:13 - INFO - __main__ - Step 137317: {'lr': 9.006864774976559e-06, 'samples': 26364864, 'steps': 137316, 'loss/train': 1.0619263648986816} 08/31/2021 14:12:13 - INFO - __main__ - Step 137318: {'lr': 9.005453225893745e-06, 'samples': 26365056, 'steps': 137317, 'loss/train': 0.8378309011459351} 08/31/2021 14:12:15 - INFO - __main__ - Step 137319: {'lr': 9.00404178539932e-06, 'samples': 26365248, 'steps': 137318, 'loss/train': 1.1442135572433472} 08/31/2021 14:12:16 - INFO - __main__ - Step 137320: {'lr': 9.002630453494004e-06, 'samples': 26365440, 'steps': 137319, 'loss/train': 1.521405816078186} 08/31/2021 14:12:16 - INFO - __main__ - Step 137321: {'lr': 9.001219230178354e-06, 'samples': 26365632, 'steps': 137320, 'loss/train': 1.6585596799850464} 08/31/2021 14:12:16 - INFO - __main__ - Step 137322: {'lr': 8.999808115453034e-06, 'samples': 26365824, 'steps': 137321, 'loss/train': 1.07442307472229} 08/31/2021 14:12:17 - INFO - __main__ - Step 137323: {'lr': 8.998397109318684e-06, 'samples': 26366016, 'steps': 137322, 'loss/train': 1.1886248588562012} 08/31/2021 14:12:19 - INFO - __main__ - Step 137324: {'lr': 8.99698621177597e-06, 'samples': 26366208, 'steps': 137323, 'loss/train': 1.2271785736083984} 08/31/2021 14:12:19 - INFO - __main__ - Step 137325: {'lr': 8.995575422825448e-06, 'samples': 26366400, 'steps': 137324, 'loss/train': 0.38231360912323} 08/31/2021 14:12:19 - INFO - __main__ - Step 137326: {'lr': 8.994164742467837e-06, 'samples': 26366592, 'steps': 137325, 'loss/train': 1.3163648843765259} 08/31/2021 14:12:20 - INFO - __main__ - Step 137327: {'lr': 8.992754170703721e-06, 'samples': 26366784, 'steps': 137326, 'loss/train': 0.7804548144340515} 08/31/2021 14:12:20 - INFO - __main__ - Step 137328: {'lr': 8.991343707533738e-06, 'samples': 26366976, 'steps': 137327, 'loss/train': 0.932404637336731} 08/31/2021 14:12:22 - INFO - __main__ - Step 137329: {'lr': 8.989933352958557e-06, 'samples': 26367168, 'steps': 137328, 'loss/train': 1.436943769454956} 08/31/2021 14:12:22 - INFO - __main__ - Step 137330: {'lr': 8.988523106978813e-06, 'samples': 26367360, 'steps': 137329, 'loss/train': 1.3551969528198242} 08/31/2021 14:12:22 - INFO - __main__ - Step 137331: {'lr': 8.98711296959509e-06, 'samples': 26367552, 'steps': 137330, 'loss/train': 1.245566725730896} 08/31/2021 14:12:23 - INFO - __main__ - Step 137332: {'lr': 8.985702940808054e-06, 'samples': 26367744, 'steps': 137331, 'loss/train': 1.0817281007766724} 08/31/2021 14:12:23 - INFO - __main__ - Step 137333: {'lr': 8.984293020618373e-06, 'samples': 26367936, 'steps': 137332, 'loss/train': 0.7237882614135742} 08/31/2021 14:12:23 - INFO - __main__ - Step 137334: {'lr': 8.982883209026598e-06, 'samples': 26368128, 'steps': 137333, 'loss/train': 0.41609179973602295} 08/31/2021 14:12:25 - INFO - __main__ - Step 137335: {'lr': 8.981473506033456e-06, 'samples': 26368320, 'steps': 137334, 'loss/train': 1.2830123901367188} 08/31/2021 14:12:26 - INFO - __main__ - Step 137336: {'lr': 8.980063911639524e-06, 'samples': 26368512, 'steps': 137335, 'loss/train': 1.334858775138855} 08/31/2021 14:12:26 - INFO - __main__ - Step 137337: {'lr': 8.978654425845472e-06, 'samples': 26368704, 'steps': 137336, 'loss/train': 1.0196971893310547} 08/31/2021 14:12:26 - INFO - __main__ - Step 137338: {'lr': 8.977245048651911e-06, 'samples': 26368896, 'steps': 137337, 'loss/train': 1.726772665977478} 08/31/2021 14:12:27 - INFO - __main__ - Step 137339: {'lr': 8.975835780059477e-06, 'samples': 26369088, 'steps': 137338, 'loss/train': 1.0928922891616821} 08/31/2021 14:12:28 - INFO - __main__ - Step 137340: {'lr': 8.97442662006881e-06, 'samples': 26369280, 'steps': 137339, 'loss/train': 1.694893479347229} 08/31/2021 14:12:29 - INFO - __main__ - Step 137341: {'lr': 8.973017568680547e-06, 'samples': 26369472, 'steps': 137340, 'loss/train': 0.026996435597538948} 08/31/2021 14:12:29 - INFO - __main__ - Step 137342: {'lr': 8.971608625895356e-06, 'samples': 26369664, 'steps': 137341, 'loss/train': 1.5939353704452515} 08/31/2021 14:12:30 - INFO - __main__ - Step 137343: {'lr': 8.970199791713818e-06, 'samples': 26369856, 'steps': 137342, 'loss/train': 1.4185676574707031} 08/31/2021 14:12:30 - INFO - __main__ - Step 137344: {'lr': 8.9687910661366e-06, 'samples': 26370048, 'steps': 137343, 'loss/train': 1.4191917181015015} 08/31/2021 14:12:32 - INFO - __main__ - Step 137345: {'lr': 8.967382449164313e-06, 'samples': 26370240, 'steps': 137344, 'loss/train': 1.2140414714813232} 08/31/2021 14:12:32 - INFO - __main__ - Step 137346: {'lr': 8.965973940797595e-06, 'samples': 26370432, 'steps': 137345, 'loss/train': 0.020735297352075577} 08/31/2021 14:12:32 - INFO - __main__ - Step 137347: {'lr': 8.964565541037084e-06, 'samples': 26370624, 'steps': 137346, 'loss/train': 0.8915252685546875} 08/31/2021 14:12:33 - INFO - __main__ - Step 137348: {'lr': 8.963157249883447e-06, 'samples': 26370816, 'steps': 137347, 'loss/train': 0.9862776398658752} 08/31/2021 14:12:33 - INFO - __main__ - Step 137349: {'lr': 8.961749067337266e-06, 'samples': 26371008, 'steps': 137348, 'loss/train': 1.2332656383514404} 08/31/2021 14:12:35 - INFO - __main__ - Step 137350: {'lr': 8.960340993399208e-06, 'samples': 26371200, 'steps': 137349, 'loss/train': 1.4090162515640259} 08/31/2021 14:12:36 - INFO - __main__ - Step 137351: {'lr': 8.95893302806991e-06, 'samples': 26371392, 'steps': 137350, 'loss/train': 1.137356162071228} 08/31/2021 14:12:36 - INFO - __main__ - Step 137352: {'lr': 8.957525171349983e-06, 'samples': 26371584, 'steps': 137351, 'loss/train': 1.2933822870254517} 08/31/2021 14:12:36 - INFO - __main__ - Step 137353: {'lr': 8.956117423240096e-06, 'samples': 26371776, 'steps': 137352, 'loss/train': 0.9175847768783569} 08/31/2021 14:12:37 - INFO - __main__ - Step 137354: {'lr': 8.954709783740855e-06, 'samples': 26371968, 'steps': 137353, 'loss/train': 0.6619874238967896} 08/31/2021 14:12:37 - INFO - __main__ - Step 137355: {'lr': 8.953302252852902e-06, 'samples': 26372160, 'steps': 137354, 'loss/train': 0.49822431802749634} 08/31/2021 14:12:38 - INFO - __main__ - Step 137356: {'lr': 8.951894830576873e-06, 'samples': 26372352, 'steps': 137355, 'loss/train': 1.1551051139831543} 08/31/2021 14:12:39 - INFO - __main__ - Step 137357: {'lr': 8.950487516913407e-06, 'samples': 26372544, 'steps': 137356, 'loss/train': 1.373050570487976} 08/31/2021 14:12:39 - INFO - __main__ - Step 137358: {'lr': 8.949080311863117e-06, 'samples': 26372736, 'steps': 137357, 'loss/train': 1.0765461921691895} 08/31/2021 14:12:40 - INFO - __main__ - Step 137359: {'lr': 8.947673215426666e-06, 'samples': 26372928, 'steps': 137358, 'loss/train': 0.5035256147384644} 08/31/2021 14:12:40 - INFO - __main__ - Step 137360: {'lr': 8.946266227604666e-06, 'samples': 26373120, 'steps': 137359, 'loss/train': 0.3355332314968109} 08/31/2021 14:12:42 - INFO - __main__ - Step 137361: {'lr': 8.944859348397754e-06, 'samples': 26373312, 'steps': 137360, 'loss/train': 1.1770856380462646} 08/31/2021 14:12:43 - INFO - __main__ - Step 137362: {'lr': 8.943452577806571e-06, 'samples': 26373504, 'steps': 137361, 'loss/train': 2.117063283920288} 08/31/2021 14:12:43 - INFO - __main__ - Step 137363: {'lr': 8.942045915831753e-06, 'samples': 26373696, 'steps': 137362, 'loss/train': 1.1015511751174927} 08/31/2021 14:12:43 - INFO - __main__ - Step 137364: {'lr': 8.940639362473913e-06, 'samples': 26373888, 'steps': 137363, 'loss/train': 0.14342133700847626} 08/31/2021 14:12:44 - INFO - __main__ - Step 137365: {'lr': 8.939232917733713e-06, 'samples': 26374080, 'steps': 137364, 'loss/train': 0.6595999598503113} 08/31/2021 14:12:44 - INFO - __main__ - Step 137366: {'lr': 8.937826581611769e-06, 'samples': 26374272, 'steps': 137365, 'loss/train': 0.7586504817008972} 08/31/2021 14:12:46 - INFO - __main__ - Step 137367: {'lr': 8.936420354108743e-06, 'samples': 26374464, 'steps': 137366, 'loss/train': 0.012766626663506031} 08/31/2021 14:12:46 - INFO - __main__ - Step 137368: {'lr': 8.93501423522522e-06, 'samples': 26374656, 'steps': 137367, 'loss/train': 0.7874898910522461} 08/31/2021 14:12:47 - INFO - __main__ - Step 137369: {'lr': 8.933608224961865e-06, 'samples': 26374848, 'steps': 137368, 'loss/train': 1.4949830770492554} 08/31/2021 14:12:47 - INFO - __main__ - Step 137370: {'lr': 8.932202323319343e-06, 'samples': 26375040, 'steps': 137369, 'loss/train': 0.32920920848846436} 08/31/2021 14:12:47 - INFO - __main__ - Step 137371: {'lr': 8.930796530298212e-06, 'samples': 26375232, 'steps': 137370, 'loss/train': 0.8182644844055176} 08/31/2021 14:12:48 - INFO - __main__ - Step 137372: {'lr': 8.929390845899165e-06, 'samples': 26375424, 'steps': 137371, 'loss/train': 0.9368362426757812} 08/31/2021 14:12:49 - INFO - __main__ - Step 137373: {'lr': 8.927985270122785e-06, 'samples': 26375616, 'steps': 137372, 'loss/train': 0.4932907819747925} 08/31/2021 14:12:50 - INFO - __main__ - Step 137374: {'lr': 8.926579802969764e-06, 'samples': 26375808, 'steps': 137373, 'loss/train': 1.0767449140548706} 08/31/2021 14:12:50 - INFO - __main__ - Step 137375: {'lr': 8.925174444440687e-06, 'samples': 26376000, 'steps': 137374, 'loss/train': 1.316799521446228} 08/31/2021 14:12:50 - INFO - __main__ - Step 137376: {'lr': 8.923769194536218e-06, 'samples': 26376192, 'steps': 137375, 'loss/train': 1.2516939640045166} 08/31/2021 14:12:51 - INFO - __main__ - Step 137377: {'lr': 8.92236405325697e-06, 'samples': 26376384, 'steps': 137376, 'loss/train': 1.0058785676956177} 08/31/2021 14:12:52 - INFO - __main__ - Step 137378: {'lr': 8.920959020603581e-06, 'samples': 26376576, 'steps': 137377, 'loss/train': 1.2988179922103882} 08/31/2021 14:12:53 - INFO - __main__ - Step 137379: {'lr': 8.919554096576687e-06, 'samples': 26376768, 'steps': 137378, 'loss/train': 1.2343114614486694} 08/31/2021 14:12:53 - INFO - __main__ - Step 137380: {'lr': 8.91814928117693e-06, 'samples': 26376960, 'steps': 137379, 'loss/train': 0.019484633579850197} 08/31/2021 14:12:53 - INFO - __main__ - Step 137381: {'lr': 8.916744574404945e-06, 'samples': 26377152, 'steps': 137380, 'loss/train': 1.0792043209075928} 08/31/2021 14:12:54 - INFO - __main__ - Step 137382: {'lr': 8.915339976261316e-06, 'samples': 26377344, 'steps': 137381, 'loss/train': 1.2652539014816284} 08/31/2021 14:12:56 - INFO - __main__ - Step 137383: {'lr': 8.913935486746765e-06, 'samples': 26377536, 'steps': 137382, 'loss/train': 0.025403831154108047} 08/31/2021 14:12:56 - INFO - __main__ - Step 137384: {'lr': 8.912531105861876e-06, 'samples': 26377728, 'steps': 137383, 'loss/train': 0.9241026639938354} 08/31/2021 14:12:57 - INFO - __main__ - Step 137385: {'lr': 8.911126833607258e-06, 'samples': 26377920, 'steps': 137384, 'loss/train': 0.9417691826820374} 08/31/2021 14:12:57 - INFO - __main__ - Step 137386: {'lr': 8.90972266998355e-06, 'samples': 26378112, 'steps': 137385, 'loss/train': 1.051901936531067} 08/31/2021 14:12:57 - INFO - __main__ - Step 137387: {'lr': 8.908318614991417e-06, 'samples': 26378304, 'steps': 137386, 'loss/train': 1.0999215841293335} 08/31/2021 14:12:59 - INFO - __main__ - Step 137388: {'lr': 8.906914668631472e-06, 'samples': 26378496, 'steps': 137387, 'loss/train': 1.162155270576477} 08/31/2021 14:12:59 - INFO - __main__ - Step 137389: {'lr': 8.905510830904351e-06, 'samples': 26378688, 'steps': 137388, 'loss/train': 0.4062736928462982} 08/31/2021 14:13:00 - INFO - __main__ - Step 137390: {'lr': 8.904107101810693e-06, 'samples': 26378880, 'steps': 137389, 'loss/train': 1.1403709650039673} 08/31/2021 14:13:00 - INFO - __main__ - Step 137391: {'lr': 8.90270348135111e-06, 'samples': 26379072, 'steps': 137390, 'loss/train': 0.9011493921279907} 08/31/2021 14:13:00 - INFO - __main__ - Step 137392: {'lr': 8.901299969526266e-06, 'samples': 26379264, 'steps': 137391, 'loss/train': 1.6263041496276855} 08/31/2021 14:13:02 - INFO - __main__ - Step 137393: {'lr': 8.899896566336745e-06, 'samples': 26379456, 'steps': 137392, 'loss/train': 1.073427677154541} 08/31/2021 14:13:02 - INFO - __main__ - Step 137394: {'lr': 8.898493271783242e-06, 'samples': 26379648, 'steps': 137393, 'loss/train': 0.027354946359992027} 08/31/2021 14:13:03 - INFO - __main__ - Step 137395: {'lr': 8.897090085866338e-06, 'samples': 26379840, 'steps': 137394, 'loss/train': 0.9120197892189026} 08/31/2021 14:13:03 - INFO - __main__ - Step 137396: {'lr': 8.8956870085867e-06, 'samples': 26380032, 'steps': 137395, 'loss/train': 0.6525387167930603} 08/31/2021 14:13:03 - INFO - __main__ - Step 137397: {'lr': 8.894284039944966e-06, 'samples': 26380224, 'steps': 137396, 'loss/train': 1.1140146255493164} 08/31/2021 14:13:05 - INFO - __main__ - Step 137398: {'lr': 8.89288117994172e-06, 'samples': 26380416, 'steps': 137397, 'loss/train': 1.1570650339126587} 08/31/2021 14:13:06 - INFO - __main__ - Step 137399: {'lr': 8.891478428577627e-06, 'samples': 26380608, 'steps': 137398, 'loss/train': 1.1457843780517578} 08/31/2021 14:13:06 - INFO - __main__ - Step 137400: {'lr': 8.890075785853297e-06, 'samples': 26380800, 'steps': 137399, 'loss/train': 1.0424283742904663} 08/31/2021 14:13:06 - INFO - __main__ - Step 137401: {'lr': 8.888673251769396e-06, 'samples': 26380992, 'steps': 137400, 'loss/train': 1.0447708368301392} 08/31/2021 14:13:07 - INFO - __main__ - Step 137402: {'lr': 8.887270826326537e-06, 'samples': 26381184, 'steps': 137401, 'loss/train': 0.6041352152824402} 08/31/2021 14:13:08 - INFO - __main__ - Step 137403: {'lr': 8.88586850952533e-06, 'samples': 26381376, 'steps': 137402, 'loss/train': 1.0886013507843018} 08/31/2021 14:13:09 - INFO - __main__ - Step 137404: {'lr': 8.88446630136644e-06, 'samples': 26381568, 'steps': 137403, 'loss/train': 1.394614577293396} 08/31/2021 14:13:09 - INFO - __main__ - Step 137405: {'lr': 8.883064201850506e-06, 'samples': 26381760, 'steps': 137404, 'loss/train': 0.6270605325698853} 08/31/2021 14:13:09 - INFO - __main__ - Step 137406: {'lr': 8.881662210978136e-06, 'samples': 26381952, 'steps': 137405, 'loss/train': 1.8501808643341064} 08/31/2021 14:13:10 - INFO - __main__ - Step 137407: {'lr': 8.880260328749973e-06, 'samples': 26382144, 'steps': 137406, 'loss/train': 1.3715018033981323} 08/31/2021 14:13:10 - INFO - __main__ - Step 137408: {'lr': 8.878858555166624e-06, 'samples': 26382336, 'steps': 137407, 'loss/train': 0.9948136210441589} 08/31/2021 14:13:12 - INFO - __main__ - Step 137409: {'lr': 8.877456890228758e-06, 'samples': 26382528, 'steps': 137408, 'loss/train': 0.9651528596878052} 08/31/2021 14:13:12 - INFO - __main__ - Step 137410: {'lr': 8.876055333937012e-06, 'samples': 26382720, 'steps': 137409, 'loss/train': 0.8517574071884155} 08/31/2021 14:13:12 - INFO - __main__ - Step 137411: {'lr': 8.874653886291967e-06, 'samples': 26382912, 'steps': 137410, 'loss/train': 1.018829107284546} 08/31/2021 14:13:13 - INFO - __main__ - Step 137412: {'lr': 8.873252547294264e-06, 'samples': 26383104, 'steps': 137411, 'loss/train': 1.1283565759658813} 08/31/2021 14:13:13 - INFO - __main__ - Step 137413: {'lr': 8.871851316944569e-06, 'samples': 26383296, 'steps': 137412, 'loss/train': 0.48635146021842957} 08/31/2021 14:13:15 - INFO - __main__ - Step 137414: {'lr': 8.870450195243518e-06, 'samples': 26383488, 'steps': 137413, 'loss/train': 1.2959483861923218} 08/31/2021 14:13:15 - INFO - __main__ - Step 137415: {'lr': 8.869049182191696e-06, 'samples': 26383680, 'steps': 137414, 'loss/train': 0.020100567489862442} 08/31/2021 14:13:16 - INFO - __main__ - Step 137416: {'lr': 8.867648277789769e-06, 'samples': 26383872, 'steps': 137415, 'loss/train': 0.9537292718887329} 08/31/2021 14:13:16 - INFO - __main__ - Step 137417: {'lr': 8.866247482038348e-06, 'samples': 26384064, 'steps': 137416, 'loss/train': 0.2051837146282196} 08/31/2021 14:13:16 - INFO - __main__ - Step 137418: {'lr': 8.864846794938069e-06, 'samples': 26384256, 'steps': 137417, 'loss/train': 0.7853779792785645} 08/31/2021 14:13:17 - INFO - __main__ - Step 137419: {'lr': 8.863446216489573e-06, 'samples': 26384448, 'steps': 137418, 'loss/train': 0.7266358733177185} 08/31/2021 14:13:19 - INFO - __main__ - Step 137420: {'lr': 8.862045746693498e-06, 'samples': 26384640, 'steps': 137419, 'loss/train': 1.1173005104064941} 08/31/2021 14:13:19 - INFO - __main__ - Step 137421: {'lr': 8.860645385550481e-06, 'samples': 26384832, 'steps': 137420, 'loss/train': 0.029757505282759666} 08/31/2021 14:13:19 - INFO - __main__ - Step 137422: {'lr': 8.859245133061105e-06, 'samples': 26385024, 'steps': 137421, 'loss/train': 1.5048943758010864} 08/31/2021 14:13:20 - INFO - __main__ - Step 137423: {'lr': 8.857844989226039e-06, 'samples': 26385216, 'steps': 137422, 'loss/train': 0.9558699727058411} 08/31/2021 14:13:20 - INFO - __main__ - Step 137424: {'lr': 8.856444954045945e-06, 'samples': 26385408, 'steps': 137423, 'loss/train': 1.0604643821716309} 08/31/2021 14:13:22 - INFO - __main__ - Step 137425: {'lr': 8.85504502752138e-06, 'samples': 26385600, 'steps': 137424, 'loss/train': 0.4018380045890808} 08/31/2021 14:13:22 - INFO - __main__ - Step 137426: {'lr': 8.85364520965301e-06, 'samples': 26385792, 'steps': 137425, 'loss/train': 0.7565121650695801} 08/31/2021 14:13:22 - INFO - __main__ - Step 137427: {'lr': 8.852245500441474e-06, 'samples': 26385984, 'steps': 137426, 'loss/train': 0.6992577314376831} 08/31/2021 14:13:23 - INFO - __main__ - Step 137428: {'lr': 8.850845899887383e-06, 'samples': 26386176, 'steps': 137427, 'loss/train': 0.2588779330253601} 08/31/2021 14:13:23 - INFO - __main__ - Step 137429: {'lr': 8.849446407991401e-06, 'samples': 26386368, 'steps': 137428, 'loss/train': 0.5418378710746765} 08/31/2021 14:13:25 - INFO - __main__ - Step 137430: {'lr': 8.848047024754114e-06, 'samples': 26386560, 'steps': 137429, 'loss/train': 1.0014395713806152} 08/31/2021 14:13:25 - INFO - __main__ - Step 137431: {'lr': 8.846647750176184e-06, 'samples': 26386752, 'steps': 137430, 'loss/train': 1.0588054656982422} 08/31/2021 14:13:25 - INFO - __main__ - Step 137432: {'lr': 8.845248584258252e-06, 'samples': 26386944, 'steps': 137431, 'loss/train': 1.392325758934021} 08/31/2021 14:13:26 - INFO - __main__ - Step 137433: {'lr': 8.843849527000902e-06, 'samples': 26387136, 'steps': 137432, 'loss/train': 0.9238703846931458} 08/31/2021 14:13:26 - INFO - __main__ - Step 137434: {'lr': 8.842450578404798e-06, 'samples': 26387328, 'steps': 137433, 'loss/train': 0.1333402395248413} 08/31/2021 14:13:29 - INFO - __main__ - Step 137435: {'lr': 8.84105173847058e-06, 'samples': 26387520, 'steps': 137434, 'loss/train': 1.0656710863113403} 08/31/2021 14:13:29 - INFO - __main__ - Step 137436: {'lr': 8.839653007198856e-06, 'samples': 26387712, 'steps': 137435, 'loss/train': 2.0115787982940674} 08/31/2021 14:13:29 - INFO - __main__ - Step 137437: {'lr': 8.838254384590294e-06, 'samples': 26387904, 'steps': 137436, 'loss/train': 0.18690678477287292} 08/31/2021 14:13:30 - INFO - __main__ - Step 137438: {'lr': 8.83685587064545e-06, 'samples': 26388096, 'steps': 137437, 'loss/train': 0.8867598176002502} 08/31/2021 14:13:30 - INFO - __main__ - Step 137439: {'lr': 8.835457465364988e-06, 'samples': 26388288, 'steps': 137438, 'loss/train': 0.5516486167907715} 08/31/2021 14:13:30 - INFO - __main__ - Step 137440: {'lr': 8.834059168749575e-06, 'samples': 26388480, 'steps': 137439, 'loss/train': 0.3202012777328491} 08/31/2021 14:13:32 - INFO - __main__ - Step 137441: {'lr': 8.832660980799795e-06, 'samples': 26388672, 'steps': 137440, 'loss/train': 0.9080960750579834} 08/31/2021 14:13:32 - INFO - __main__ - Step 137442: {'lr': 8.831262901516313e-06, 'samples': 26388864, 'steps': 137441, 'loss/train': 0.91461181640625} 08/31/2021 14:13:33 - INFO - __main__ - Step 137443: {'lr': 8.829864930899739e-06, 'samples': 26389056, 'steps': 137442, 'loss/train': 0.8293910622596741} 08/31/2021 14:13:33 - INFO - __main__ - Step 137444: {'lr': 8.828467068950713e-06, 'samples': 26389248, 'steps': 137443, 'loss/train': 0.759073793888092} 08/31/2021 14:13:33 - INFO - __main__ - Step 137445: {'lr': 8.827069315669844e-06, 'samples': 26389440, 'steps': 137444, 'loss/train': 0.9474891424179077} 08/31/2021 14:13:35 - INFO - __main__ - Step 137446: {'lr': 8.825671671057773e-06, 'samples': 26389632, 'steps': 137445, 'loss/train': 0.7496025562286377} 08/31/2021 14:13:35 - INFO - __main__ - Step 137447: {'lr': 8.824274135115135e-06, 'samples': 26389824, 'steps': 137446, 'loss/train': 0.9233171939849854} 08/31/2021 14:13:36 - INFO - __main__ - Step 137448: {'lr': 8.82287670784257e-06, 'samples': 26390016, 'steps': 137447, 'loss/train': 1.0366160869598389} 08/31/2021 14:13:36 - INFO - __main__ - Step 137449: {'lr': 8.821479389240688e-06, 'samples': 26390208, 'steps': 137448, 'loss/train': 0.7070068120956421} 08/31/2021 14:13:36 - INFO - __main__ - Step 137450: {'lr': 8.820082179310102e-06, 'samples': 26390400, 'steps': 137449, 'loss/train': 0.9805232286453247} 08/31/2021 14:13:38 - INFO - __main__ - Step 137451: {'lr': 8.818685078051531e-06, 'samples': 26390592, 'steps': 137450, 'loss/train': 1.4700454473495483} 08/31/2021 14:13:39 - INFO - __main__ - Step 137452: {'lr': 8.817288085465502e-06, 'samples': 26390784, 'steps': 137451, 'loss/train': 0.7351756691932678} 08/31/2021 14:13:39 - INFO - __main__ - Step 137453: {'lr': 8.815891201552655e-06, 'samples': 26390976, 'steps': 137452, 'loss/train': 1.2322313785552979} 08/31/2021 14:13:39 - INFO - __main__ - Step 137454: {'lr': 8.814494426313685e-06, 'samples': 26391168, 'steps': 137453, 'loss/train': 0.4763143062591553} 08/31/2021 14:13:40 - INFO - __main__ - Step 137455: {'lr': 8.813097759749145e-06, 'samples': 26391360, 'steps': 137454, 'loss/train': 1.4622325897216797} 08/31/2021 14:13:40 - INFO - __main__ - Step 137456: {'lr': 8.811701201859729e-06, 'samples': 26391552, 'steps': 137455, 'loss/train': 0.022100288420915604} 08/31/2021 14:13:42 - INFO - __main__ - Step 137457: {'lr': 8.81030475264602e-06, 'samples': 26391744, 'steps': 137456, 'loss/train': 0.017409635707736015} 08/31/2021 14:13:42 - INFO - __main__ - Step 137458: {'lr': 8.808908412108685e-06, 'samples': 26391936, 'steps': 137457, 'loss/train': 0.271014541387558} 08/31/2021 14:13:43 - INFO - __main__ - Step 137459: {'lr': 8.807512180248334e-06, 'samples': 26392128, 'steps': 137458, 'loss/train': 1.060482382774353} 08/31/2021 14:13:43 - INFO - __main__ - Step 137460: {'lr': 8.806116057065578e-06, 'samples': 26392320, 'steps': 137459, 'loss/train': 1.4265649318695068} 08/31/2021 14:13:43 - INFO - __main__ - Step 137461: {'lr': 8.804720042561082e-06, 'samples': 26392512, 'steps': 137460, 'loss/train': 1.3033939599990845} 08/31/2021 14:13:44 - INFO - __main__ - Step 137462: {'lr': 8.80332413673543e-06, 'samples': 26392704, 'steps': 137461, 'loss/train': 0.9865532517433167} 08/31/2021 14:13:45 - INFO - __main__ - Step 137463: {'lr': 8.801928339589288e-06, 'samples': 26392896, 'steps': 137462, 'loss/train': 0.645957887172699} 08/31/2021 14:13:46 - INFO - __main__ - Step 137464: {'lr': 8.800532651123323e-06, 'samples': 26393088, 'steps': 137463, 'loss/train': 0.869663417339325} 08/31/2021 14:13:46 - INFO - __main__ - Step 137465: {'lr': 8.799137071338087e-06, 'samples': 26393280, 'steps': 137464, 'loss/train': 1.2001014947891235} 08/31/2021 14:13:47 - INFO - __main__ - Step 137466: {'lr': 8.797741600234222e-06, 'samples': 26393472, 'steps': 137465, 'loss/train': 1.1122266054153442} 08/31/2021 14:13:47 - INFO - __main__ - Step 137467: {'lr': 8.796346237812364e-06, 'samples': 26393664, 'steps': 137466, 'loss/train': 0.6040441393852234} 08/31/2021 14:13:48 - INFO - __main__ - Step 137468: {'lr': 8.79495098407318e-06, 'samples': 26393856, 'steps': 137467, 'loss/train': 0.37660548090934753} 08/31/2021 14:13:49 - INFO - __main__ - Step 137469: {'lr': 8.793555839017253e-06, 'samples': 26394048, 'steps': 137468, 'loss/train': 0.7601471543312073} 08/31/2021 14:13:49 - INFO - __main__ - Step 137470: {'lr': 8.792160802645222e-06, 'samples': 26394240, 'steps': 137469, 'loss/train': 1.0827053785324097} 08/31/2021 14:13:50 - INFO - __main__ - Step 137471: {'lr': 8.790765874957724e-06, 'samples': 26394432, 'steps': 137470, 'loss/train': 0.6004214882850647} 08/31/2021 14:13:50 - INFO - __main__ - Step 137472: {'lr': 8.789371055955398e-06, 'samples': 26394624, 'steps': 137471, 'loss/train': 1.4046761989593506} 08/31/2021 14:13:51 - INFO - __main__ - Step 137473: {'lr': 8.787976345638827e-06, 'samples': 26394816, 'steps': 137472, 'loss/train': 1.0912773609161377} 08/31/2021 14:13:52 - INFO - __main__ - Step 137474: {'lr': 8.786581744008704e-06, 'samples': 26395008, 'steps': 137473, 'loss/train': 1.3546842336654663} 08/31/2021 14:13:52 - INFO - __main__ - Step 137475: {'lr': 8.785187251065613e-06, 'samples': 26395200, 'steps': 137474, 'loss/train': 1.5220081806182861} 08/31/2021 14:13:53 - INFO - __main__ - Step 137476: {'lr': 8.783792866810191e-06, 'samples': 26395392, 'steps': 137475, 'loss/train': 0.9795123934745789} 08/31/2021 14:13:53 - INFO - __main__ - Step 137477: {'lr': 8.782398591243079e-06, 'samples': 26395584, 'steps': 137476, 'loss/train': 1.2449673414230347} 08/31/2021 14:13:53 - INFO - __main__ - Step 137478: {'lr': 8.781004424364913e-06, 'samples': 26395776, 'steps': 137477, 'loss/train': 0.1020173579454422} 08/31/2021 14:13:55 - INFO - __main__ - Step 137479: {'lr': 8.779610366176304e-06, 'samples': 26395968, 'steps': 137478, 'loss/train': 1.0542247295379639} 08/31/2021 14:13:55 - INFO - __main__ - Step 137480: {'lr': 8.778216416677864e-06, 'samples': 26396160, 'steps': 137479, 'loss/train': 0.6909669041633606} 08/31/2021 14:13:56 - INFO - __main__ - Step 137481: {'lr': 8.77682257587023e-06, 'samples': 26396352, 'steps': 137480, 'loss/train': 0.6118659377098083} 08/31/2021 14:13:56 - INFO - __main__ - Step 137482: {'lr': 8.775428843754041e-06, 'samples': 26396544, 'steps': 137481, 'loss/train': 0.17818531394004822} 08/31/2021 14:13:56 - INFO - __main__ - Step 137483: {'lr': 8.774035220329907e-06, 'samples': 26396736, 'steps': 137482, 'loss/train': 0.3876377046108246} 08/31/2021 14:13:58 - INFO - __main__ - Step 137484: {'lr': 8.772641705598494e-06, 'samples': 26396928, 'steps': 137483, 'loss/train': 1.0638587474822998} 08/31/2021 14:13:58 - INFO - __main__ - Step 137485: {'lr': 8.771248299560386e-06, 'samples': 26397120, 'steps': 137484, 'loss/train': 0.022044869139790535} 08/31/2021 14:13:59 - INFO - __main__ - Step 137486: {'lr': 8.769855002216249e-06, 'samples': 26397312, 'steps': 137485, 'loss/train': 1.1556848287582397} 08/31/2021 14:13:59 - INFO - __main__ - Step 137487: {'lr': 8.768461813566692e-06, 'samples': 26397504, 'steps': 137486, 'loss/train': 0.9792554378509521} 08/31/2021 14:13:59 - INFO - __main__ - Step 137488: {'lr': 8.767068733612327e-06, 'samples': 26397696, 'steps': 137487, 'loss/train': 1.9462530612945557} 08/31/2021 14:14:02 - INFO - __main__ - Step 137489: {'lr': 8.76567576235382e-06, 'samples': 26397888, 'steps': 137488, 'loss/train': 0.6523086428642273} 08/31/2021 14:14:03 - INFO - __main__ - Step 137490: {'lr': 8.764282899791754e-06, 'samples': 26398080, 'steps': 137489, 'loss/train': 1.1967191696166992} 08/31/2021 14:14:03 - INFO - __main__ - Step 137491: {'lr': 8.762890145926822e-06, 'samples': 26398272, 'steps': 137490, 'loss/train': 0.054679833352565765} 08/31/2021 14:14:03 - INFO - __main__ - Step 137492: {'lr': 8.761497500759579e-06, 'samples': 26398464, 'steps': 137491, 'loss/train': 0.04461647942662239} 08/31/2021 14:14:04 - INFO - __main__ - Step 137493: {'lr': 8.760104964290693e-06, 'samples': 26398656, 'steps': 137492, 'loss/train': 1.1293222904205322} 08/31/2021 14:14:04 - INFO - __main__ - Step 137494: {'lr': 8.758712536520746e-06, 'samples': 26398848, 'steps': 137493, 'loss/train': 1.277435064315796} 08/31/2021 14:14:05 - INFO - __main__ - Step 137495: {'lr': 8.757320217450432e-06, 'samples': 26399040, 'steps': 137494, 'loss/train': 0.1240464374423027} 08/31/2021 14:14:06 - INFO - __main__ - Step 137496: {'lr': 8.755928007080333e-06, 'samples': 26399232, 'steps': 137495, 'loss/train': 0.638839066028595} 08/31/2021 14:14:06 - INFO - __main__ - Step 137497: {'lr': 8.754535905411115e-06, 'samples': 26399424, 'steps': 137496, 'loss/train': 1.6478580236434937} 08/31/2021 14:14:07 - INFO - __main__ - Step 137498: {'lr': 8.753143912443363e-06, 'samples': 26399616, 'steps': 137497, 'loss/train': 1.2150920629501343} 08/31/2021 14:14:07 - INFO - __main__ - Step 137499: {'lr': 8.751752028177712e-06, 'samples': 26399808, 'steps': 137498, 'loss/train': 0.8289036154747009} 08/31/2021 14:14:09 - INFO - __main__ - Step 137500: {'lr': 8.750360252614802e-06, 'samples': 26400000, 'steps': 137499, 'loss/train': 1.3412877321243286} 08/31/2021 14:14:09 - INFO - __main__ - Step 137501: {'lr': 8.748968585755273e-06, 'samples': 26400192, 'steps': 137500, 'loss/train': 0.9648398756980896} 08/31/2021 14:14:10 - INFO - __main__ - Step 137502: {'lr': 8.747577027599735e-06, 'samples': 26400384, 'steps': 137501, 'loss/train': 0.719387412071228} 08/31/2021 14:14:10 - INFO - __main__ - Step 137503: {'lr': 8.746185578148796e-06, 'samples': 26400576, 'steps': 137502, 'loss/train': 0.12658379971981049} 08/31/2021 14:14:10 - INFO - __main__ - Step 137504: {'lr': 8.744794237403125e-06, 'samples': 26400768, 'steps': 137503, 'loss/train': 0.09996070712804794} 08/31/2021 14:14:12 - INFO - __main__ - Step 137505: {'lr': 8.743403005363331e-06, 'samples': 26400960, 'steps': 137504, 'loss/train': 1.0104299783706665} 08/31/2021 14:14:12 - INFO - __main__ - Step 137506: {'lr': 8.742011882030026e-06, 'samples': 26401152, 'steps': 137505, 'loss/train': 0.6455112099647522} 08/31/2021 14:14:13 - INFO - __main__ - Step 137507: {'lr': 8.740620867403848e-06, 'samples': 26401344, 'steps': 137506, 'loss/train': 0.887427568435669} 08/31/2021 14:14:13 - INFO - __main__ - Step 137508: {'lr': 8.739229961485406e-06, 'samples': 26401536, 'steps': 137507, 'loss/train': 1.245548129081726} 08/31/2021 14:14:13 - INFO - __main__ - Step 137509: {'lr': 8.737839164275368e-06, 'samples': 26401728, 'steps': 137508, 'loss/train': 1.380118489265442} 08/31/2021 14:14:15 - INFO - __main__ - Step 137510: {'lr': 8.736448475774317e-06, 'samples': 26401920, 'steps': 137509, 'loss/train': 1.441588282585144} 08/31/2021 14:14:15 - INFO - __main__ - Step 137511: {'lr': 8.735057895982918e-06, 'samples': 26402112, 'steps': 137510, 'loss/train': 1.1110941171646118} 08/31/2021 14:14:16 - INFO - __main__ - Step 137512: {'lr': 8.733667424901754e-06, 'samples': 26402304, 'steps': 137511, 'loss/train': 0.9378008842468262} 08/31/2021 14:14:16 - INFO - __main__ - Step 137513: {'lr': 8.73227706253149e-06, 'samples': 26402496, 'steps': 137512, 'loss/train': 0.24831271171569824} 08/31/2021 14:14:16 - INFO - __main__ - Step 137514: {'lr': 8.73088680887274e-06, 'samples': 26402688, 'steps': 137513, 'loss/train': 1.251060128211975} 08/31/2021 14:14:18 - INFO - __main__ - Step 137515: {'lr': 8.72949666392614e-06, 'samples': 26402880, 'steps': 137514, 'loss/train': 0.7135395407676697} 08/31/2021 14:14:18 - INFO - __main__ - Step 137516: {'lr': 8.728106627692327e-06, 'samples': 26403072, 'steps': 137515, 'loss/train': 1.229561448097229} 08/31/2021 14:14:19 - INFO - __main__ - Step 137517: {'lr': 8.72671670017186e-06, 'samples': 26403264, 'steps': 137516, 'loss/train': 1.980827808380127} 08/31/2021 14:14:19 - INFO - __main__ - Step 137518: {'lr': 8.725326881365431e-06, 'samples': 26403456, 'steps': 137517, 'loss/train': 0.7146044373512268} 08/31/2021 14:14:19 - INFO - __main__ - Step 137519: {'lr': 8.723937171273649e-06, 'samples': 26403648, 'steps': 137518, 'loss/train': 0.20503777265548706} 08/31/2021 14:14:21 - INFO - __main__ - Step 137520: {'lr': 8.722547569897126e-06, 'samples': 26403840, 'steps': 137519, 'loss/train': 1.0234086513519287} 08/31/2021 14:14:21 - INFO - __main__ - Step 137521: {'lr': 8.721158077236502e-06, 'samples': 26404032, 'steps': 137520, 'loss/train': 0.8876119256019592} 08/31/2021 14:14:22 - INFO - __main__ - Step 137522: {'lr': 8.719768693292413e-06, 'samples': 26404224, 'steps': 137521, 'loss/train': 0.7116934657096863} 08/31/2021 14:14:22 - INFO - __main__ - Step 137523: {'lr': 8.71837941806547e-06, 'samples': 26404416, 'steps': 137522, 'loss/train': 1.338726282119751} 08/31/2021 14:14:22 - INFO - __main__ - Step 137524: {'lr': 8.716990251556284e-06, 'samples': 26404608, 'steps': 137523, 'loss/train': 0.8864347338676453} 08/31/2021 14:14:24 - INFO - __main__ - Step 137525: {'lr': 8.715601193765522e-06, 'samples': 26404800, 'steps': 137524, 'loss/train': 1.275450587272644} 08/31/2021 14:14:24 - INFO - __main__ - Step 137526: {'lr': 8.714212244693764e-06, 'samples': 26404992, 'steps': 137525, 'loss/train': 0.9219276905059814} 08/31/2021 14:14:25 - INFO - __main__ - Step 137527: {'lr': 8.712823404341708e-06, 'samples': 26405184, 'steps': 137526, 'loss/train': 1.1059553623199463} 08/31/2021 14:14:25 - INFO - __main__ - Step 137528: {'lr': 8.711434672709878e-06, 'samples': 26405376, 'steps': 137527, 'loss/train': 1.0411300659179688} 08/31/2021 14:14:25 - INFO - __main__ - Step 137529: {'lr': 8.71004604979897e-06, 'samples': 26405568, 'steps': 137528, 'loss/train': 0.5210100412368774} 08/31/2021 14:14:27 - INFO - __main__ - Step 137530: {'lr': 8.708657535609593e-06, 'samples': 26405760, 'steps': 137529, 'loss/train': 1.6403692960739136} 08/31/2021 14:14:27 - INFO - __main__ - Step 137531: {'lr': 8.70726913014236e-06, 'samples': 26405952, 'steps': 137530, 'loss/train': 2.0623011589050293} 08/31/2021 14:14:28 - INFO - __main__ - Step 137532: {'lr': 8.705880833397934e-06, 'samples': 26406144, 'steps': 137531, 'loss/train': 1.6509828567504883} 08/31/2021 14:14:28 - INFO - __main__ - Step 137533: {'lr': 8.704492645376872e-06, 'samples': 26406336, 'steps': 137532, 'loss/train': 0.9216323494911194} 08/31/2021 14:14:28 - INFO - __main__ - Step 137534: {'lr': 8.703104566079866e-06, 'samples': 26406528, 'steps': 137533, 'loss/train': 1.902545690536499} 08/31/2021 14:14:30 - INFO - __main__ - Step 137535: {'lr': 8.70171659550753e-06, 'samples': 26406720, 'steps': 137534, 'loss/train': 0.822589635848999} 08/31/2021 14:14:30 - INFO - __main__ - Step 137536: {'lr': 8.700328733660473e-06, 'samples': 26406912, 'steps': 137535, 'loss/train': 0.729074239730835} 08/31/2021 14:14:31 - INFO - __main__ - Step 137537: {'lr': 8.698940980539333e-06, 'samples': 26407104, 'steps': 137536, 'loss/train': 0.5989245772361755} 08/31/2021 14:14:31 - INFO - __main__ - Step 137538: {'lr': 8.69755333614472e-06, 'samples': 26407296, 'steps': 137537, 'loss/train': 1.4361540079116821} 08/31/2021 14:14:31 - INFO - __main__ - Step 137539: {'lr': 8.696165800477246e-06, 'samples': 26407488, 'steps': 137538, 'loss/train': 0.5063298344612122} 08/31/2021 14:14:32 - INFO - __main__ - Step 137540: {'lr': 8.694778373537576e-06, 'samples': 26407680, 'steps': 137539, 'loss/train': 0.8906072378158569} 08/31/2021 14:14:33 - INFO - __main__ - Step 137541: {'lr': 8.693391055326294e-06, 'samples': 26407872, 'steps': 137540, 'loss/train': 1.0003445148468018} 08/31/2021 14:14:34 - INFO - __main__ - Step 137542: {'lr': 8.692003845844066e-06, 'samples': 26408064, 'steps': 137541, 'loss/train': 1.3522895574569702} 08/31/2021 14:14:34 - INFO - __main__ - Step 137543: {'lr': 8.6906167450915e-06, 'samples': 26408256, 'steps': 137542, 'loss/train': 1.002514362335205} 08/31/2021 14:14:35 - INFO - __main__ - Step 137544: {'lr': 8.689229753069183e-06, 'samples': 26408448, 'steps': 137543, 'loss/train': 1.6325891017913818} 08/31/2021 14:14:35 - INFO - __main__ - Step 137545: {'lr': 8.687842869777806e-06, 'samples': 26408640, 'steps': 137544, 'loss/train': 1.3476099967956543} 08/31/2021 14:14:37 - INFO - __main__ - Step 137546: {'lr': 8.686456095217954e-06, 'samples': 26408832, 'steps': 137545, 'loss/train': 0.3979732096195221} 08/31/2021 14:14:38 - INFO - __main__ - Step 137547: {'lr': 8.685069429390264e-06, 'samples': 26409024, 'steps': 137546, 'loss/train': 1.1970417499542236} 08/31/2021 14:14:38 - INFO - __main__ - Step 137548: {'lr': 8.6836828722954e-06, 'samples': 26409216, 'steps': 137547, 'loss/train': 0.7557559609413147} 08/31/2021 14:14:38 - INFO - __main__ - Step 137549: {'lr': 8.682296423933894e-06, 'samples': 26409408, 'steps': 137548, 'loss/train': 1.3341929912567139} 08/31/2021 14:14:39 - INFO - __main__ - Step 137550: {'lr': 8.680910084306437e-06, 'samples': 26409600, 'steps': 137549, 'loss/train': 0.022352075204253197} 08/31/2021 14:14:40 - INFO - __main__ - Step 137551: {'lr': 8.67952385341364e-06, 'samples': 26409792, 'steps': 137550, 'loss/train': 0.8485139012336731} 08/31/2021 14:14:41 - INFO - __main__ - Step 137552: {'lr': 8.678137731256114e-06, 'samples': 26409984, 'steps': 137551, 'loss/train': 1.245911717414856} 08/31/2021 14:14:41 - INFO - __main__ - Step 137553: {'lr': 8.676751717834497e-06, 'samples': 26410176, 'steps': 137552, 'loss/train': 1.41502046585083} 08/31/2021 14:14:41 - INFO - __main__ - Step 137554: {'lr': 8.675365813149428e-06, 'samples': 26410368, 'steps': 137553, 'loss/train': 0.5143777132034302} 08/31/2021 14:14:42 - INFO - __main__ - Step 137555: {'lr': 8.673980017201488e-06, 'samples': 26410560, 'steps': 137554, 'loss/train': 0.6266703009605408} 08/31/2021 14:14:44 - INFO - __main__ - Step 137556: {'lr': 8.672594329991345e-06, 'samples': 26410752, 'steps': 137555, 'loss/train': 2.4301204681396484} 08/31/2021 14:14:44 - INFO - __main__ - Step 137557: {'lr': 8.67120875151961e-06, 'samples': 26410944, 'steps': 137556, 'loss/train': 0.7890470623970032} 08/31/2021 14:14:44 - INFO - __main__ - Step 137558: {'lr': 8.669823281786893e-06, 'samples': 26411136, 'steps': 137557, 'loss/train': 1.5144792795181274} 08/31/2021 14:14:45 - INFO - __main__ - Step 137559: {'lr': 8.66843792079386e-06, 'samples': 26411328, 'steps': 137558, 'loss/train': 0.015003887005150318} 08/31/2021 14:14:45 - INFO - __main__ - Step 137560: {'lr': 8.667052668541092e-06, 'samples': 26411520, 'steps': 137559, 'loss/train': 1.0865174531936646} 08/31/2021 14:14:46 - INFO - __main__ - Step 137561: {'lr': 8.665667525029202e-06, 'samples': 26411712, 'steps': 137560, 'loss/train': 0.5586851239204407} 08/31/2021 14:14:47 - INFO - __main__ - Step 137562: {'lr': 8.664282490258857e-06, 'samples': 26411904, 'steps': 137561, 'loss/train': 1.1828076839447021} 08/31/2021 14:14:48 - INFO - __main__ - Step 137563: {'lr': 8.662897564230637e-06, 'samples': 26412096, 'steps': 137562, 'loss/train': 1.0130246877670288} 08/31/2021 14:14:48 - INFO - __main__ - Step 137564: {'lr': 8.661512746945211e-06, 'samples': 26412288, 'steps': 137563, 'loss/train': 0.5922673940658569} 08/31/2021 14:14:48 - INFO - __main__ - Step 137565: {'lr': 8.660128038403187e-06, 'samples': 26412480, 'steps': 137564, 'loss/train': 1.150524616241455} 08/31/2021 14:14:49 - INFO - __main__ - Step 137566: {'lr': 8.658743438605176e-06, 'samples': 26412672, 'steps': 137565, 'loss/train': 1.4294437170028687} 08/31/2021 14:14:50 - INFO - __main__ - Step 137567: {'lr': 8.657358947551819e-06, 'samples': 26412864, 'steps': 137566, 'loss/train': 1.056625485420227} 08/31/2021 14:14:50 - INFO - __main__ - Step 137568: {'lr': 8.655974565243724e-06, 'samples': 26413056, 'steps': 137567, 'loss/train': 0.8197417855262756} 08/31/2021 14:14:51 - INFO - __main__ - Step 137569: {'lr': 8.65459029168153e-06, 'samples': 26413248, 'steps': 137568, 'loss/train': 0.9281201362609863} 08/31/2021 14:14:51 - INFO - __main__ - Step 137570: {'lr': 8.653206126865847e-06, 'samples': 26413440, 'steps': 137569, 'loss/train': 1.3370585441589355} 08/31/2021 14:14:52 - INFO - __main__ - Step 137571: {'lr': 8.651822070797317e-06, 'samples': 26413632, 'steps': 137570, 'loss/train': 1.0762572288513184} 08/31/2021 14:14:53 - INFO - __main__ - Step 137572: {'lr': 8.650438123476573e-06, 'samples': 26413824, 'steps': 137571, 'loss/train': 0.7636512517929077} 08/31/2021 14:14:54 - INFO - __main__ - Step 137573: {'lr': 8.649054284904201e-06, 'samples': 26414016, 'steps': 137572, 'loss/train': 0.707177996635437} 08/31/2021 14:14:54 - INFO - __main__ - Step 137574: {'lr': 8.64767055508081e-06, 'samples': 26414208, 'steps': 137573, 'loss/train': 1.2165011167526245} 08/31/2021 14:14:54 - INFO - __main__ - Step 137575: {'lr': 8.64628693400707e-06, 'samples': 26414400, 'steps': 137574, 'loss/train': 1.0481866598129272} 08/31/2021 14:14:55 - INFO - __main__ - Step 137576: {'lr': 8.644903421683587e-06, 'samples': 26414592, 'steps': 137575, 'loss/train': 1.2967779636383057} 08/31/2021 14:14:55 - INFO - __main__ - Step 137577: {'lr': 8.643520018111e-06, 'samples': 26414784, 'steps': 137576, 'loss/train': 1.2502398490905762} 08/31/2021 14:14:56 - INFO - __main__ - Step 137578: {'lr': 8.642136723289923e-06, 'samples': 26414976, 'steps': 137577, 'loss/train': 0.529225766658783} 08/31/2021 14:14:57 - INFO - __main__ - Step 137579: {'lr': 8.640753537220935e-06, 'samples': 26415168, 'steps': 137578, 'loss/train': 1.5240949392318726} 08/31/2021 14:14:57 - INFO - __main__ - Step 137580: {'lr': 8.639370459904733e-06, 'samples': 26415360, 'steps': 137579, 'loss/train': 1.054141879081726} 08/31/2021 14:14:58 - INFO - __main__ - Step 137581: {'lr': 8.637987491341897e-06, 'samples': 26415552, 'steps': 137580, 'loss/train': 1.0391509532928467} 08/31/2021 14:14:58 - INFO - __main__ - Step 137582: {'lr': 8.636604631533068e-06, 'samples': 26415744, 'steps': 137581, 'loss/train': 0.9442814588546753} 08/31/2021 14:14:59 - INFO - __main__ - Step 137583: {'lr': 8.635221880478855e-06, 'samples': 26415936, 'steps': 137582, 'loss/train': 0.9670712947845459} 08/31/2021 14:15:00 - INFO - __main__ - Step 137584: {'lr': 8.63383923817987e-06, 'samples': 26416128, 'steps': 137583, 'loss/train': 1.3884015083312988} 08/31/2021 14:15:00 - INFO - __main__ - Step 137585: {'lr': 8.632456704636804e-06, 'samples': 26416320, 'steps': 137584, 'loss/train': 0.4014505445957184} 08/31/2021 14:15:01 - INFO - __main__ - Step 137586: {'lr': 8.631074279850187e-06, 'samples': 26416512, 'steps': 137585, 'loss/train': 1.4622092247009277} 08/31/2021 14:15:01 - INFO - __main__ - Step 137587: {'lr': 8.629691963820685e-06, 'samples': 26416704, 'steps': 137586, 'loss/train': 1.4494061470031738} 08/31/2021 14:15:02 - INFO - __main__ - Step 137588: {'lr': 8.628309756548935e-06, 'samples': 26416896, 'steps': 137587, 'loss/train': 0.9327896237373352} 08/31/2021 14:15:03 - INFO - __main__ - Step 137589: {'lr': 8.626927658035522e-06, 'samples': 26417088, 'steps': 137588, 'loss/train': 1.1816364526748657} 08/31/2021 14:15:03 - INFO - __main__ - Step 137590: {'lr': 8.62554566828111e-06, 'samples': 26417280, 'steps': 137589, 'loss/train': 1.3016034364700317} 08/31/2021 14:15:03 - INFO - __main__ - Step 137591: {'lr': 8.624163787286282e-06, 'samples': 26417472, 'steps': 137590, 'loss/train': 2.5162296295166016} 08/31/2021 14:15:04 - INFO - __main__ - Step 137592: {'lr': 8.622782015051678e-06, 'samples': 26417664, 'steps': 137591, 'loss/train': 1.4095399379730225} 08/31/2021 14:15:05 - INFO - __main__ - Step 137593: {'lr': 8.621400351577962e-06, 'samples': 26417856, 'steps': 137592, 'loss/train': 0.9601641893386841} 08/31/2021 14:15:06 - INFO - __main__ - Step 137594: {'lr': 8.620018796865691e-06, 'samples': 26418048, 'steps': 137593, 'loss/train': 1.670885682106018} 08/31/2021 14:15:06 - INFO - __main__ - Step 137595: {'lr': 8.618637350915503e-06, 'samples': 26418240, 'steps': 137594, 'loss/train': 1.560470461845398} 08/31/2021 14:15:06 - INFO - __main__ - Step 137596: {'lr': 8.617256013728037e-06, 'samples': 26418432, 'steps': 137595, 'loss/train': 1.0114474296569824} 08/31/2021 14:15:07 - INFO - __main__ - Step 137597: {'lr': 8.61587478530393e-06, 'samples': 26418624, 'steps': 137596, 'loss/train': 0.8311586380004883} 08/31/2021 14:15:09 - INFO - __main__ - Step 137598: {'lr': 8.614493665643763e-06, 'samples': 26418816, 'steps': 137597, 'loss/train': 1.3938493728637695} 08/31/2021 14:15:10 - INFO - __main__ - Step 137599: {'lr': 8.613112654748233e-06, 'samples': 26419008, 'steps': 137598, 'loss/train': 1.108654260635376} 08/31/2021 14:15:10 - INFO - __main__ - Step 137600: {'lr': 8.611731752617868e-06, 'samples': 26419200, 'steps': 137599, 'loss/train': 0.6544046401977539} 08/31/2021 14:15:10 - INFO - __main__ - Step 137601: {'lr': 8.610350959253332e-06, 'samples': 26419392, 'steps': 137600, 'loss/train': 1.7409628629684448} 08/31/2021 14:15:11 - INFO - __main__ - Step 137602: {'lr': 8.608970274655264e-06, 'samples': 26419584, 'steps': 137601, 'loss/train': 1.676414966583252} 08/31/2021 14:15:11 - INFO - __main__ - Step 137603: {'lr': 8.607589698824247e-06, 'samples': 26419776, 'steps': 137602, 'loss/train': 0.015601446852087975} 08/31/2021 14:15:11 - INFO - __main__ - Step 137604: {'lr': 8.60620923176092e-06, 'samples': 26419968, 'steps': 137603, 'loss/train': 0.03531767427921295} 08/31/2021 14:15:13 - INFO - __main__ - Step 137605: {'lr': 8.604828873465919e-06, 'samples': 26420160, 'steps': 137604, 'loss/train': 1.5509833097457886} 08/31/2021 14:15:14 - INFO - __main__ - Step 137606: {'lr': 8.603448623939857e-06, 'samples': 26420352, 'steps': 137605, 'loss/train': 0.022399546578526497} 08/31/2021 14:15:14 - INFO - __main__ - Step 137607: {'lr': 8.602068483183373e-06, 'samples': 26420544, 'steps': 137606, 'loss/train': 0.9205188155174255} 08/31/2021 14:15:14 - INFO - __main__ - Step 137608: {'lr': 8.600688451197047e-06, 'samples': 26420736, 'steps': 137607, 'loss/train': 1.1767961978912354} 08/31/2021 14:15:15 - INFO - __main__ - Step 137609: {'lr': 8.599308527981548e-06, 'samples': 26420928, 'steps': 137608, 'loss/train': 0.8675088286399841} 08/31/2021 14:15:17 - INFO - __main__ - Step 137610: {'lr': 8.597928713537456e-06, 'samples': 26421120, 'steps': 137609, 'loss/train': 1.3378665447235107} 08/31/2021 14:15:17 - INFO - __main__ - Step 137611: {'lr': 8.596549007865411e-06, 'samples': 26421312, 'steps': 137610, 'loss/train': 0.8222572803497314} 08/31/2021 14:15:17 - INFO - __main__ - Step 137612: {'lr': 8.59516941096608e-06, 'samples': 26421504, 'steps': 137611, 'loss/train': 0.7318958044052124} 08/31/2021 14:15:18 - INFO - __main__ - Step 137613: {'lr': 8.593789922840018e-06, 'samples': 26421696, 'steps': 137612, 'loss/train': 0.014480894431471825} 08/31/2021 14:15:18 - INFO - __main__ - Step 137614: {'lr': 8.592410543487833e-06, 'samples': 26421888, 'steps': 137613, 'loss/train': 0.33230262994766235} 08/31/2021 14:15:18 - INFO - __main__ - Step 137615: {'lr': 8.591031272910222e-06, 'samples': 26422080, 'steps': 137614, 'loss/train': 1.3753303289413452} 08/31/2021 14:15:20 - INFO - __main__ - Step 137616: {'lr': 8.589652111107738e-06, 'samples': 26422272, 'steps': 137615, 'loss/train': 1.5447094440460205} 08/31/2021 14:15:20 - INFO - __main__ - Step 137617: {'lr': 8.588273058081047e-06, 'samples': 26422464, 'steps': 137616, 'loss/train': 1.5525988340377808} 08/31/2021 14:15:21 - INFO - __main__ - Step 137618: {'lr': 8.586894113830761e-06, 'samples': 26422656, 'steps': 137617, 'loss/train': 0.8067243099212646} 08/31/2021 14:15:21 - INFO - __main__ - Step 137619: {'lr': 8.585515278357492e-06, 'samples': 26422848, 'steps': 137618, 'loss/train': 1.1143829822540283} 08/31/2021 14:15:22 - INFO - __main__ - Step 137620: {'lr': 8.584136551661847e-06, 'samples': 26423040, 'steps': 137619, 'loss/train': 0.6601740121841431} 08/31/2021 14:15:23 - INFO - __main__ - Step 137621: {'lr': 8.582757933744495e-06, 'samples': 26423232, 'steps': 137620, 'loss/train': 1.453024983406067} 08/31/2021 14:15:23 - INFO - __main__ - Step 137622: {'lr': 8.58137942460599e-06, 'samples': 26423424, 'steps': 137621, 'loss/train': 1.0405669212341309} 08/31/2021 14:15:24 - INFO - __main__ - Step 137623: {'lr': 8.580001024247025e-06, 'samples': 26423616, 'steps': 137622, 'loss/train': 0.20143456757068634} 08/31/2021 14:15:24 - INFO - __main__ - Step 137624: {'lr': 8.578622732668156e-06, 'samples': 26423808, 'steps': 137623, 'loss/train': 1.3227715492248535} 08/31/2021 14:15:24 - INFO - __main__ - Step 137625: {'lr': 8.57724454987005e-06, 'samples': 26424000, 'steps': 137624, 'loss/train': 0.9914579391479492} 08/31/2021 14:15:26 - INFO - __main__ - Step 137626: {'lr': 8.575866475853344e-06, 'samples': 26424192, 'steps': 137625, 'loss/train': 0.7895910143852234} 08/31/2021 14:15:26 - INFO - __main__ - Step 137627: {'lr': 8.574488510618594e-06, 'samples': 26424384, 'steps': 137626, 'loss/train': 0.9996975660324097} 08/31/2021 14:15:27 - INFO - __main__ - Step 137628: {'lr': 8.573110654166466e-06, 'samples': 26424576, 'steps': 137627, 'loss/train': 1.0900938510894775} 08/31/2021 14:15:27 - INFO - __main__ - Step 137629: {'lr': 8.571732906497542e-06, 'samples': 26424768, 'steps': 137628, 'loss/train': 1.1565275192260742} 08/31/2021 14:15:27 - INFO - __main__ - Step 137630: {'lr': 8.57035526761249e-06, 'samples': 26424960, 'steps': 137629, 'loss/train': 1.1035741567611694} 08/31/2021 14:15:29 - INFO - __main__ - Step 137631: {'lr': 8.568977737511918e-06, 'samples': 26425152, 'steps': 137630, 'loss/train': 0.8972672820091248} 08/31/2021 14:15:29 - INFO - __main__ - Step 137632: {'lr': 8.56760031619641e-06, 'samples': 26425344, 'steps': 137631, 'loss/train': 0.5144270658493042} 08/31/2021 14:15:30 - INFO - __main__ - Step 137633: {'lr': 8.566223003666635e-06, 'samples': 26425536, 'steps': 137632, 'loss/train': 0.8078806400299072} 08/31/2021 14:15:30 - INFO - __main__ - Step 137634: {'lr': 8.564845799923199e-06, 'samples': 26425728, 'steps': 137633, 'loss/train': 1.5242785215377808} 08/31/2021 14:15:30 - INFO - __main__ - Step 137635: {'lr': 8.563468704966716e-06, 'samples': 26425920, 'steps': 137634, 'loss/train': 0.965874433517456} 08/31/2021 14:15:32 - INFO - __main__ - Step 137636: {'lr': 8.562091718797793e-06, 'samples': 26426112, 'steps': 137635, 'loss/train': 1.6708590984344482} 08/31/2021 14:15:32 - INFO - __main__ - Step 137637: {'lr': 8.560714841417072e-06, 'samples': 26426304, 'steps': 137636, 'loss/train': 1.6292731761932373} 08/31/2021 14:15:33 - INFO - __main__ - Step 137638: {'lr': 8.559338072825162e-06, 'samples': 26426496, 'steps': 137637, 'loss/train': 1.3712533712387085} 08/31/2021 14:15:33 - INFO - __main__ - Step 137639: {'lr': 8.55796141302273e-06, 'samples': 26426688, 'steps': 137638, 'loss/train': 1.0089163780212402} 08/31/2021 14:15:33 - INFO - __main__ - Step 137640: {'lr': 8.556584862010331e-06, 'samples': 26426880, 'steps': 137639, 'loss/train': 1.0654702186584473} 08/31/2021 14:15:35 - INFO - __main__ - Step 137641: {'lr': 8.555208419788601e-06, 'samples': 26427072, 'steps': 137640, 'loss/train': 1.1437480449676514} 08/31/2021 14:15:35 - INFO - __main__ - Step 137642: {'lr': 8.553832086358182e-06, 'samples': 26427264, 'steps': 137641, 'loss/train': 1.2462714910507202} 08/31/2021 14:15:36 - INFO - __main__ - Step 137643: {'lr': 8.552455861719655e-06, 'samples': 26427456, 'steps': 137642, 'loss/train': 1.1124719381332397} 08/31/2021 14:15:36 - INFO - __main__ - Step 137644: {'lr': 8.551079745873686e-06, 'samples': 26427648, 'steps': 137643, 'loss/train': 0.6093056201934814} 08/31/2021 14:15:36 - INFO - __main__ - Step 137645: {'lr': 8.549703738820858e-06, 'samples': 26427840, 'steps': 137644, 'loss/train': 1.592491626739502} 08/31/2021 14:15:38 - INFO - __main__ - Step 137646: {'lr': 8.54832784056181e-06, 'samples': 26428032, 'steps': 137645, 'loss/train': 1.5315300226211548} 08/31/2021 14:15:38 - INFO - __main__ - Step 137647: {'lr': 8.54695205109718e-06, 'samples': 26428224, 'steps': 137646, 'loss/train': 0.8120851516723633} 08/31/2021 14:15:39 - INFO - __main__ - Step 137648: {'lr': 8.54557637042755e-06, 'samples': 26428416, 'steps': 137647, 'loss/train': 1.5944969654083252} 08/31/2021 14:15:39 - INFO - __main__ - Step 137649: {'lr': 8.544200798553559e-06, 'samples': 26428608, 'steps': 137648, 'loss/train': 2.105113983154297} 08/31/2021 14:15:39 - INFO - __main__ - Step 137650: {'lr': 8.542825335475817e-06, 'samples': 26428800, 'steps': 137649, 'loss/train': 0.48026156425476074} 08/31/2021 14:15:41 - INFO - __main__ - Step 137651: {'lr': 8.541449981194965e-06, 'samples': 26428992, 'steps': 137650, 'loss/train': 1.2301888465881348} 08/31/2021 14:15:42 - INFO - __main__ - Step 137652: {'lr': 8.540074735711639e-06, 'samples': 26429184, 'steps': 137651, 'loss/train': 1.5117647647857666} 08/31/2021 14:15:42 - INFO - __main__ - Step 137653: {'lr': 8.538699599026395e-06, 'samples': 26429376, 'steps': 137652, 'loss/train': 0.8263023495674133} 08/31/2021 14:15:43 - INFO - __main__ - Step 137654: {'lr': 8.537324571139898e-06, 'samples': 26429568, 'steps': 137653, 'loss/train': 0.5741651058197021} 08/31/2021 14:15:43 - INFO - __main__ - Step 137655: {'lr': 8.535949652052732e-06, 'samples': 26429760, 'steps': 137654, 'loss/train': 1.1904124021530151} 08/31/2021 14:15:43 - INFO - __main__ - Step 137656: {'lr': 8.534574841765563e-06, 'samples': 26429952, 'steps': 137655, 'loss/train': 0.9884685277938843} 08/31/2021 14:15:45 - INFO - __main__ - Step 137657: {'lr': 8.533200140278975e-06, 'samples': 26430144, 'steps': 137656, 'loss/train': 1.3029946088790894} 08/31/2021 14:15:45 - INFO - __main__ - Step 137658: {'lr': 8.531825547593602e-06, 'samples': 26430336, 'steps': 137657, 'loss/train': 0.02869676798582077} 08/31/2021 14:15:46 - INFO - __main__ - Step 137659: {'lr': 8.530451063710088e-06, 'samples': 26430528, 'steps': 137658, 'loss/train': 1.0675108432769775} 08/31/2021 14:15:46 - INFO - __main__ - Step 137660: {'lr': 8.529076688628984e-06, 'samples': 26430720, 'steps': 137659, 'loss/train': 1.172094702720642} 08/31/2021 14:15:46 - INFO - __main__ - Step 137661: {'lr': 8.527702422350985e-06, 'samples': 26430912, 'steps': 137660, 'loss/train': 1.4245216846466064} 08/31/2021 14:15:48 - INFO - __main__ - Step 137662: {'lr': 8.526328264876676e-06, 'samples': 26431104, 'steps': 137661, 'loss/train': 0.9959913492202759} 08/31/2021 14:15:49 - INFO - __main__ - Step 137663: {'lr': 8.524954216206666e-06, 'samples': 26431296, 'steps': 137662, 'loss/train': 0.1869577169418335} 08/31/2021 14:15:49 - INFO - __main__ - Step 137664: {'lr': 8.523580276341591e-06, 'samples': 26431488, 'steps': 137663, 'loss/train': 0.9991393685340881} 08/31/2021 14:15:49 - INFO - __main__ - Step 137665: {'lr': 8.522206445282038e-06, 'samples': 26431680, 'steps': 137664, 'loss/train': 1.0137994289398193} 08/31/2021 14:15:50 - INFO - __main__ - Step 137666: {'lr': 8.520832723028727e-06, 'samples': 26431872, 'steps': 137665, 'loss/train': 0.0229586623609066} 08/31/2021 14:15:52 - INFO - __main__ - Step 137667: {'lr': 8.519459109582128e-06, 'samples': 26432064, 'steps': 137666, 'loss/train': 0.5769227743148804} 08/31/2021 14:15:52 - INFO - __main__ - Step 137668: {'lr': 8.518085604942965e-06, 'samples': 26432256, 'steps': 137667, 'loss/train': 1.3744721412658691} 08/31/2021 14:15:53 - INFO - __main__ - Step 137669: {'lr': 8.516712209111822e-06, 'samples': 26432448, 'steps': 137668, 'loss/train': 1.665040373802185} 08/31/2021 14:15:53 - INFO - __main__ - Step 137670: {'lr': 8.515338922089333e-06, 'samples': 26432640, 'steps': 137669, 'loss/train': 0.6829737424850464} 08/31/2021 14:15:53 - INFO - __main__ - Step 137671: {'lr': 8.513965743876084e-06, 'samples': 26432832, 'steps': 137670, 'loss/train': 0.7210585474967957} 08/31/2021 14:15:54 - INFO - __main__ - Step 137672: {'lr': 8.512592674472714e-06, 'samples': 26433024, 'steps': 137671, 'loss/train': 1.1612640619277954} 08/31/2021 14:15:55 - INFO - __main__ - Step 137673: {'lr': 8.511219713879859e-06, 'samples': 26433216, 'steps': 137672, 'loss/train': 1.1423966884613037} 08/31/2021 14:15:56 - INFO - __main__ - Step 137674: {'lr': 8.50984686209813e-06, 'samples': 26433408, 'steps': 137673, 'loss/train': 1.1567803621292114} 08/31/2021 14:15:56 - INFO - __main__ - Step 137675: {'lr': 8.508474119128112e-06, 'samples': 26433600, 'steps': 137674, 'loss/train': 2.474090814590454} 08/31/2021 14:15:57 - INFO - __main__ - Step 137676: {'lr': 8.50710148497047e-06, 'samples': 26433792, 'steps': 137675, 'loss/train': 0.33404356241226196} 08/31/2021 14:15:57 - INFO - __main__ - Step 137677: {'lr': 8.505728959625787e-06, 'samples': 26433984, 'steps': 137676, 'loss/train': 1.4103524684906006} 08/31/2021 14:15:58 - INFO - __main__ - Step 137678: {'lr': 8.504356543094699e-06, 'samples': 26434176, 'steps': 137677, 'loss/train': 0.8057489991188049} 08/31/2021 14:15:59 - INFO - __main__ - Step 137679: {'lr': 8.502984235377848e-06, 'samples': 26434368, 'steps': 137678, 'loss/train': 1.2357864379882812} 08/31/2021 14:15:59 - INFO - __main__ - Step 137680: {'lr': 8.501612036475815e-06, 'samples': 26434560, 'steps': 137679, 'loss/train': 1.0853651762008667} 08/31/2021 14:16:00 - INFO - __main__ - Step 137681: {'lr': 8.50023994638921e-06, 'samples': 26434752, 'steps': 137680, 'loss/train': 0.9264227747917175} 08/31/2021 14:16:00 - INFO - __main__ - Step 137682: {'lr': 8.498867965118673e-06, 'samples': 26434944, 'steps': 137681, 'loss/train': 0.4426684081554413} 08/31/2021 14:16:01 - INFO - __main__ - Step 137683: {'lr': 8.497496092664813e-06, 'samples': 26435136, 'steps': 137682, 'loss/train': 1.0120388269424438} 08/31/2021 14:16:02 - INFO - __main__ - Step 137684: {'lr': 8.49612432902827e-06, 'samples': 26435328, 'steps': 137683, 'loss/train': 0.8305454254150391} 08/31/2021 14:16:02 - INFO - __main__ - Step 137685: {'lr': 8.494752674209655e-06, 'samples': 26435520, 'steps': 137684, 'loss/train': 1.62162184715271} 08/31/2021 14:16:03 - INFO - __main__ - Step 137686: {'lr': 8.493381128209548e-06, 'samples': 26435712, 'steps': 137685, 'loss/train': 0.9342922568321228} 08/31/2021 14:16:03 - INFO - __main__ - Step 137687: {'lr': 8.492009691028619e-06, 'samples': 26435904, 'steps': 137686, 'loss/train': 0.9828928709030151} 08/31/2021 14:16:04 - INFO - __main__ - Step 137688: {'lr': 8.490638362667446e-06, 'samples': 26436096, 'steps': 137687, 'loss/train': 0.7422245740890503} 08/31/2021 14:16:05 - INFO - __main__ - Step 137689: {'lr': 8.489267143126672e-06, 'samples': 26436288, 'steps': 137688, 'loss/train': 0.9929532408714294} 08/31/2021 14:16:05 - INFO - __main__ - Step 137690: {'lr': 8.487896032406933e-06, 'samples': 26436480, 'steps': 137689, 'loss/train': 0.9467689990997314} 08/31/2021 14:16:06 - INFO - __main__ - Step 137691: {'lr': 8.486525030508784e-06, 'samples': 26436672, 'steps': 137690, 'loss/train': 0.3629458546638489} 08/31/2021 14:16:06 - INFO - __main__ - Step 137692: {'lr': 8.485154137432894e-06, 'samples': 26436864, 'steps': 137691, 'loss/train': 0.662987470626831} 08/31/2021 14:16:08 - INFO - __main__ - Step 137693: {'lr': 8.483783353179896e-06, 'samples': 26437056, 'steps': 137692, 'loss/train': 1.1600910425186157} 08/31/2021 14:16:08 - INFO - __main__ - Step 137694: {'lr': 8.482412677750351e-06, 'samples': 26437248, 'steps': 137693, 'loss/train': 0.9596710801124573} 08/31/2021 14:16:08 - INFO - __main__ - Step 137695: {'lr': 8.481042111144921e-06, 'samples': 26437440, 'steps': 137694, 'loss/train': 1.048988938331604} 08/31/2021 14:16:09 - INFO - __main__ - Step 137696: {'lr': 8.47967165336419e-06, 'samples': 26437632, 'steps': 137695, 'loss/train': 0.4137499928474426} 08/31/2021 14:16:09 - INFO - __main__ - Step 137697: {'lr': 8.47830130440877e-06, 'samples': 26437824, 'steps': 137696, 'loss/train': 0.8600102663040161} 08/31/2021 14:16:11 - INFO - __main__ - Step 137698: {'lr': 8.476931064279324e-06, 'samples': 26438016, 'steps': 137697, 'loss/train': 1.3927726745605469} 08/31/2021 14:16:11 - INFO - __main__ - Step 137699: {'lr': 8.475560932976467e-06, 'samples': 26438208, 'steps': 137698, 'loss/train': 0.05402198061347008} 08/31/2021 14:16:11 - INFO - __main__ - Step 137700: {'lr': 8.47419091050075e-06, 'samples': 26438400, 'steps': 137699, 'loss/train': 0.9988745450973511} 08/31/2021 14:16:12 - INFO - __main__ - Step 137701: {'lr': 8.47282099685287e-06, 'samples': 26438592, 'steps': 137700, 'loss/train': 1.2769434452056885} 08/31/2021 14:16:12 - INFO - __main__ - Step 137702: {'lr': 8.471451192033409e-06, 'samples': 26438784, 'steps': 137701, 'loss/train': 2.0245156288146973} 08/31/2021 14:16:13 - INFO - __main__ - Step 137703: {'lr': 8.470081496042946e-06, 'samples': 26438976, 'steps': 137702, 'loss/train': 0.9698352813720703} 08/31/2021 14:16:14 - INFO - __main__ - Step 137704: {'lr': 8.468711908882183e-06, 'samples': 26439168, 'steps': 137703, 'loss/train': 0.7485955953598022} 08/31/2021 14:16:15 - INFO - __main__ - Step 137705: {'lr': 8.467342430551666e-06, 'samples': 26439360, 'steps': 137704, 'loss/train': 1.2088967561721802} 08/31/2021 14:16:15 - INFO - __main__ - Step 137706: {'lr': 8.465973061052067e-06, 'samples': 26439552, 'steps': 137705, 'loss/train': 0.9896559119224548} 08/31/2021 14:16:15 - INFO - __main__ - Step 137707: {'lr': 8.464603800383968e-06, 'samples': 26439744, 'steps': 137706, 'loss/train': 1.3095097541809082} 08/31/2021 14:16:16 - INFO - __main__ - Step 137708: {'lr': 8.46323464854798e-06, 'samples': 26439936, 'steps': 137707, 'loss/train': 1.438126564025879} 08/31/2021 14:16:18 - INFO - __main__ - Step 137709: {'lr': 8.461865605544712e-06, 'samples': 26440128, 'steps': 137708, 'loss/train': 0.3584428131580353} 08/31/2021 14:16:19 - INFO - __main__ - Step 137710: {'lr': 8.460496671374828e-06, 'samples': 26440320, 'steps': 137709, 'loss/train': 0.329754501581192} 08/31/2021 14:16:19 - INFO - __main__ - Step 137711: {'lr': 8.459127846038889e-06, 'samples': 26440512, 'steps': 137710, 'loss/train': 0.55806964635849} 08/31/2021 14:16:19 - INFO - __main__ - Step 137712: {'lr': 8.457759129537557e-06, 'samples': 26440704, 'steps': 137711, 'loss/train': 0.9912816286087036} 08/31/2021 14:16:20 - INFO - __main__ - Step 137713: {'lr': 8.456390521871415e-06, 'samples': 26440896, 'steps': 137712, 'loss/train': 1.5186725854873657} 08/31/2021 14:16:21 - INFO - __main__ - Step 137714: {'lr': 8.45502202304113e-06, 'samples': 26441088, 'steps': 137713, 'loss/train': 1.0651333332061768} 08/31/2021 14:16:22 - INFO - __main__ - Step 137715: {'lr': 8.45365363304726e-06, 'samples': 26441280, 'steps': 137714, 'loss/train': 1.203354001045227} 08/31/2021 14:16:22 - INFO - __main__ - Step 137716: {'lr': 8.452285351890437e-06, 'samples': 26441472, 'steps': 137715, 'loss/train': 1.06034255027771} 08/31/2021 14:16:23 - INFO - __main__ - Step 137717: {'lr': 8.450917179571306e-06, 'samples': 26441664, 'steps': 137716, 'loss/train': 0.6335015892982483} 08/31/2021 14:16:23 - INFO - __main__ - Step 137718: {'lr': 8.449549116090472e-06, 'samples': 26441856, 'steps': 137717, 'loss/train': 0.7903050780296326} 08/31/2021 14:16:23 - INFO - __main__ - Step 137719: {'lr': 8.44818116144852e-06, 'samples': 26442048, 'steps': 137718, 'loss/train': 1.5354704856872559} 08/31/2021 14:16:25 - INFO - __main__ - Step 137720: {'lr': 8.446813315646146e-06, 'samples': 26442240, 'steps': 137719, 'loss/train': 0.8349136710166931} 08/31/2021 14:16:26 - INFO - __main__ - Step 137721: {'lr': 8.445445578683847e-06, 'samples': 26442432, 'steps': 137720, 'loss/train': 0.7198027968406677} 08/31/2021 14:16:26 - INFO - __main__ - Step 137722: {'lr': 8.444077950562318e-06, 'samples': 26442624, 'steps': 137721, 'loss/train': 1.3504451513290405} 08/31/2021 14:16:26 - INFO - __main__ - Step 137723: {'lr': 8.442710431282169e-06, 'samples': 26442816, 'steps': 137722, 'loss/train': 0.30621474981307983} 08/31/2021 14:16:27 - INFO - __main__ - Step 137724: {'lr': 8.441343020844011e-06, 'samples': 26443008, 'steps': 137723, 'loss/train': 0.060263048857450485} 08/31/2021 14:16:28 - INFO - __main__ - Step 137725: {'lr': 8.439975719248454e-06, 'samples': 26443200, 'steps': 137724, 'loss/train': 1.35194993019104} 08/31/2021 14:16:29 - INFO - __main__ - Step 137726: {'lr': 8.438608526496111e-06, 'samples': 26443392, 'steps': 137725, 'loss/train': 1.1932828426361084} 08/31/2021 14:16:29 - INFO - __main__ - Step 137727: {'lr': 8.43724144258759e-06, 'samples': 26443584, 'steps': 137726, 'loss/train': 0.9534711837768555} 08/31/2021 14:16:29 - INFO - __main__ - Step 137728: {'lr': 8.43587446752353e-06, 'samples': 26443776, 'steps': 137727, 'loss/train': 0.8910331726074219} 08/31/2021 14:16:30 - INFO - __main__ - Step 137729: {'lr': 8.434507601304542e-06, 'samples': 26443968, 'steps': 137728, 'loss/train': 0.9178865551948547} 08/31/2021 14:16:31 - INFO - __main__ - Step 137730: {'lr': 8.433140843931236e-06, 'samples': 26444160, 'steps': 137729, 'loss/train': 0.7600228786468506} 08/31/2021 14:16:32 - INFO - __main__ - Step 137731: {'lr': 8.431774195404224e-06, 'samples': 26444352, 'steps': 137730, 'loss/train': 1.198730707168579} 08/31/2021 14:16:32 - INFO - __main__ - Step 137732: {'lr': 8.430407655724143e-06, 'samples': 26444544, 'steps': 137731, 'loss/train': 1.4662939310073853} 08/31/2021 14:16:32 - INFO - __main__ - Step 137733: {'lr': 8.429041224891604e-06, 'samples': 26444736, 'steps': 137732, 'loss/train': 1.3252626657485962} 08/31/2021 14:16:33 - INFO - __main__ - Step 137734: {'lr': 8.42767490290719e-06, 'samples': 26444928, 'steps': 137733, 'loss/train': 0.04835597798228264} 08/31/2021 14:16:34 - INFO - __main__ - Step 137735: {'lr': 8.42630868977154e-06, 'samples': 26445120, 'steps': 137734, 'loss/train': 1.110512614250183} 08/31/2021 14:16:34 - INFO - __main__ - Step 137736: {'lr': 8.424942585485263e-06, 'samples': 26445312, 'steps': 137735, 'loss/train': 1.3782449960708618} 08/31/2021 14:16:35 - INFO - __main__ - Step 137737: {'lr': 8.42357659004897e-06, 'samples': 26445504, 'steps': 137736, 'loss/train': 0.7945201396942139} 08/31/2021 14:16:35 - INFO - __main__ - Step 137738: {'lr': 8.422210703463302e-06, 'samples': 26445696, 'steps': 137737, 'loss/train': 1.08865487575531} 08/31/2021 14:16:36 - INFO - __main__ - Step 137739: {'lr': 8.420844925728838e-06, 'samples': 26445888, 'steps': 137738, 'loss/train': 0.07364034652709961} 08/31/2021 14:16:37 - INFO - __main__ - Step 137740: {'lr': 8.419479256846247e-06, 'samples': 26446080, 'steps': 137739, 'loss/train': 1.1244242191314697} 08/31/2021 14:16:37 - INFO - __main__ - Step 137741: {'lr': 8.418113696816083e-06, 'samples': 26446272, 'steps': 137740, 'loss/train': 1.1199073791503906} 08/31/2021 14:16:38 - INFO - __main__ - Step 137742: {'lr': 8.416748245638984e-06, 'samples': 26446464, 'steps': 137741, 'loss/train': 1.3976585865020752} 08/31/2021 14:16:38 - INFO - __main__ - Step 137743: {'lr': 8.415382903315588e-06, 'samples': 26446656, 'steps': 137742, 'loss/train': 1.2119165658950806} 08/31/2021 14:16:38 - INFO - __main__ - Step 137744: {'lr': 8.414017669846507e-06, 'samples': 26446848, 'steps': 137743, 'loss/train': 1.2442753314971924} 08/31/2021 14:16:40 - INFO - __main__ - Step 137745: {'lr': 8.412652545232325e-06, 'samples': 26447040, 'steps': 137744, 'loss/train': 1.5385866165161133} 08/31/2021 14:16:41 - INFO - __main__ - Step 137746: {'lr': 8.41128752947365e-06, 'samples': 26447232, 'steps': 137745, 'loss/train': 1.0809115171432495} 08/31/2021 14:16:41 - INFO - __main__ - Step 137747: {'lr': 8.409922622571175e-06, 'samples': 26447424, 'steps': 137746, 'loss/train': 0.977703332901001} 08/31/2021 14:16:41 - INFO - __main__ - Step 137748: {'lr': 8.408557824525432e-06, 'samples': 26447616, 'steps': 137747, 'loss/train': 0.8792280554771423} 08/31/2021 14:16:42 - INFO - __main__ - Step 137749: {'lr': 8.407193135337055e-06, 'samples': 26447808, 'steps': 137748, 'loss/train': 0.47295308113098145} 08/31/2021 14:16:43 - INFO - __main__ - Step 137750: {'lr': 8.405828555006683e-06, 'samples': 26448000, 'steps': 137749, 'loss/train': 1.1115046739578247} 08/31/2021 14:16:44 - INFO - __main__ - Step 137751: {'lr': 8.404464083534901e-06, 'samples': 26448192, 'steps': 137750, 'loss/train': 0.6958625912666321} 08/31/2021 14:16:44 - INFO - __main__ - Step 137752: {'lr': 8.403099720922347e-06, 'samples': 26448384, 'steps': 137751, 'loss/train': 1.3012239933013916} 08/31/2021 14:16:44 - INFO - __main__ - Step 137753: {'lr': 8.40173546716963e-06, 'samples': 26448576, 'steps': 137752, 'loss/train': 0.8217292428016663} 08/31/2021 14:16:45 - INFO - __main__ - Step 137754: {'lr': 8.400371322277362e-06, 'samples': 26448768, 'steps': 137753, 'loss/train': 1.4139846563339233} 08/31/2021 14:16:45 - INFO - __main__ - Step 137755: {'lr': 8.399007286246153e-06, 'samples': 26448960, 'steps': 137754, 'loss/train': 0.5448324680328369} 08/31/2021 14:16:47 - INFO - __main__ - Step 137756: {'lr': 8.39764335907664e-06, 'samples': 26449152, 'steps': 137755, 'loss/train': 0.8644280433654785} 08/31/2021 14:16:47 - INFO - __main__ - Step 137757: {'lr': 8.396279540769409e-06, 'samples': 26449344, 'steps': 137756, 'loss/train': 0.20428815484046936} 08/31/2021 14:16:48 - INFO - __main__ - Step 137758: {'lr': 8.394915831325095e-06, 'samples': 26449536, 'steps': 137757, 'loss/train': 1.0199521780014038} 08/31/2021 14:16:48 - INFO - __main__ - Step 137759: {'lr': 8.393552230744283e-06, 'samples': 26449728, 'steps': 137758, 'loss/train': 1.555783987045288} 08/31/2021 14:16:48 - INFO - __main__ - Step 137760: {'lr': 8.39218873902764e-06, 'samples': 26449920, 'steps': 137759, 'loss/train': 0.01710410602390766} 08/31/2021 14:16:49 - INFO - __main__ - Step 137761: {'lr': 8.390825356175746e-06, 'samples': 26450112, 'steps': 137760, 'loss/train': 0.8427161574363708} 08/31/2021 14:16:51 - INFO - __main__ - Step 137762: {'lr': 8.389462082189187e-06, 'samples': 26450304, 'steps': 137761, 'loss/train': 1.0395594835281372} 08/31/2021 14:16:51 - INFO - __main__ - Step 137763: {'lr': 8.388098917068626e-06, 'samples': 26450496, 'steps': 137762, 'loss/train': 0.6653743386268616} 08/31/2021 14:16:52 - INFO - __main__ - Step 137764: {'lr': 8.386735860814649e-06, 'samples': 26450688, 'steps': 137763, 'loss/train': 1.3072799444198608} 08/31/2021 14:16:52 - INFO - __main__ - Step 137765: {'lr': 8.385372913427892e-06, 'samples': 26450880, 'steps': 137764, 'loss/train': 1.3234153985977173} 08/31/2021 14:16:52 - INFO - __main__ - Step 137766: {'lr': 8.384010074908965e-06, 'samples': 26451072, 'steps': 137765, 'loss/train': 1.6435543298721313} 08/31/2021 14:16:54 - INFO - __main__ - Step 137767: {'lr': 8.382647345258454e-06, 'samples': 26451264, 'steps': 137766, 'loss/train': 1.6358033418655396} 08/31/2021 14:16:54 - INFO - __main__ - Step 137768: {'lr': 8.381284724476995e-06, 'samples': 26451456, 'steps': 137767, 'loss/train': 1.7309247255325317} 08/31/2021 14:16:55 - INFO - __main__ - Step 137769: {'lr': 8.3799222125652e-06, 'samples': 26451648, 'steps': 137768, 'loss/train': 0.04470596835017204} 08/31/2021 14:16:55 - INFO - __main__ - Step 137770: {'lr': 8.378559809523705e-06, 'samples': 26451840, 'steps': 137769, 'loss/train': 0.9764460325241089} 08/31/2021 14:16:55 - INFO - __main__ - Step 137771: {'lr': 8.377197515353097e-06, 'samples': 26452032, 'steps': 137770, 'loss/train': 0.4986412227153778} 08/31/2021 14:16:57 - INFO - __main__ - Step 137772: {'lr': 8.375835330053982e-06, 'samples': 26452224, 'steps': 137771, 'loss/train': 0.4892279803752899} 08/31/2021 14:16:57 - INFO - __main__ - Step 137773: {'lr': 8.374473253627001e-06, 'samples': 26452416, 'steps': 137772, 'loss/train': 1.3194727897644043} 08/31/2021 14:16:58 - INFO - __main__ - Step 137774: {'lr': 8.373111286072765e-06, 'samples': 26452608, 'steps': 137773, 'loss/train': 0.21856863796710968} 08/31/2021 14:16:58 - INFO - __main__ - Step 137775: {'lr': 8.371749427391857e-06, 'samples': 26452800, 'steps': 137774, 'loss/train': 0.9928450584411621} 08/31/2021 14:16:58 - INFO - __main__ - Step 137776: {'lr': 8.370387677584912e-06, 'samples': 26452992, 'steps': 137775, 'loss/train': 1.1418365240097046} 08/31/2021 14:16:59 - INFO - __main__ - Step 137777: {'lr': 8.369026036652517e-06, 'samples': 26453184, 'steps': 137776, 'loss/train': 0.8929877281188965} 08/31/2021 14:17:00 - INFO - __main__ - Step 137778: {'lr': 8.367664504595334e-06, 'samples': 26453376, 'steps': 137777, 'loss/train': 1.049172282218933} 08/31/2021 14:17:01 - INFO - __main__ - Step 137779: {'lr': 8.36630308141395e-06, 'samples': 26453568, 'steps': 137778, 'loss/train': 1.3275271654129028} 08/31/2021 14:17:01 - INFO - __main__ - Step 137780: {'lr': 8.364941767109003e-06, 'samples': 26453760, 'steps': 137779, 'loss/train': 1.3446667194366455} 08/31/2021 14:17:01 - INFO - __main__ - Step 137781: {'lr': 8.363580561681045e-06, 'samples': 26453952, 'steps': 137780, 'loss/train': 1.1506917476654053} 08/31/2021 14:17:02 - INFO - __main__ - Step 137782: {'lr': 8.362219465130745e-06, 'samples': 26454144, 'steps': 137781, 'loss/train': 0.028792236000299454} 08/31/2021 14:17:03 - INFO - __main__ - Step 137783: {'lr': 8.36085847745871e-06, 'samples': 26454336, 'steps': 137782, 'loss/train': 1.6097818613052368} 08/31/2021 14:17:04 - INFO - __main__ - Step 137784: {'lr': 8.359497598665555e-06, 'samples': 26454528, 'steps': 137783, 'loss/train': 0.4324381649494171} 08/31/2021 14:17:04 - INFO - __main__ - Step 137785: {'lr': 8.358136828751888e-06, 'samples': 26454720, 'steps': 137784, 'loss/train': 1.146303653717041} 08/31/2021 14:17:04 - INFO - __main__ - Step 137786: {'lr': 8.356776167718267e-06, 'samples': 26454912, 'steps': 137785, 'loss/train': 0.7561516165733337} 08/31/2021 14:17:05 - INFO - __main__ - Step 137787: {'lr': 8.355415615565381e-06, 'samples': 26455104, 'steps': 137786, 'loss/train': 1.1958152055740356} 08/31/2021 14:17:06 - INFO - __main__ - Step 137788: {'lr': 8.354055172293817e-06, 'samples': 26455296, 'steps': 137787, 'loss/train': 0.26270467042922974} 08/31/2021 14:17:07 - INFO - __main__ - Step 137789: {'lr': 8.352694837904184e-06, 'samples': 26455488, 'steps': 137788, 'loss/train': 1.8051031827926636} 08/31/2021 14:17:07 - INFO - __main__ - Step 137790: {'lr': 8.351334612397093e-06, 'samples': 26455680, 'steps': 137789, 'loss/train': 2.084731101989746} 08/31/2021 14:17:07 - INFO - __main__ - Step 137791: {'lr': 8.349974495773182e-06, 'samples': 26455872, 'steps': 137790, 'loss/train': 0.8444560766220093} 08/31/2021 14:17:08 - INFO - __main__ - Step 137792: {'lr': 8.348614488033008e-06, 'samples': 26456064, 'steps': 137791, 'loss/train': 1.1832430362701416} 08/31/2021 14:17:09 - INFO - __main__ - Step 137793: {'lr': 8.347254589177234e-06, 'samples': 26456256, 'steps': 137792, 'loss/train': 0.9415512084960938} 08/31/2021 14:17:10 - INFO - __main__ - Step 137794: {'lr': 8.345894799206471e-06, 'samples': 26456448, 'steps': 137793, 'loss/train': 0.05188370123505592} 08/31/2021 14:17:10 - INFO - __main__ - Step 137795: {'lr': 8.344535118121333e-06, 'samples': 26456640, 'steps': 137794, 'loss/train': 1.4635906219482422} 08/31/2021 14:17:10 - INFO - __main__ - Step 137796: {'lr': 8.343175545922399e-06, 'samples': 26456832, 'steps': 137795, 'loss/train': 0.926505982875824} 08/31/2021 14:17:11 - INFO - __main__ - Step 137797: {'lr': 8.34181608261031e-06, 'samples': 26457024, 'steps': 137796, 'loss/train': 0.7027201652526855} 08/31/2021 14:17:12 - INFO - __main__ - Step 137798: {'lr': 8.340456728185647e-06, 'samples': 26457216, 'steps': 137797, 'loss/train': 1.2953964471817017} 08/31/2021 14:17:13 - INFO - __main__ - Step 137799: {'lr': 8.33909748264905e-06, 'samples': 26457408, 'steps': 137798, 'loss/train': 1.714833378791809} 08/31/2021 14:17:13 - INFO - __main__ - Step 137800: {'lr': 8.337738346001128e-06, 'samples': 26457600, 'steps': 137799, 'loss/train': 0.7179170250892639} 08/31/2021 14:17:13 - INFO - __main__ - Step 137801: {'lr': 8.336379318242521e-06, 'samples': 26457792, 'steps': 137800, 'loss/train': 0.9133622050285339} 08/31/2021 14:17:14 - INFO - __main__ - Step 137802: {'lr': 8.335020399373784e-06, 'samples': 26457984, 'steps': 137801, 'loss/train': 5.676061153411865} 08/31/2021 14:17:16 - INFO - __main__ - Step 137803: {'lr': 8.333661589395553e-06, 'samples': 26458176, 'steps': 137802, 'loss/train': 0.5976901650428772} 08/31/2021 14:17:16 - INFO - __main__ - Step 137804: {'lr': 8.332302888308441e-06, 'samples': 26458368, 'steps': 137803, 'loss/train': 0.5111067891120911} 08/31/2021 14:17:16 - INFO - __main__ - Step 137805: {'lr': 8.330944296113085e-06, 'samples': 26458560, 'steps': 137804, 'loss/train': 1.2162845134735107} 08/31/2021 14:17:17 - INFO - __main__ - Step 137806: {'lr': 8.329585812810097e-06, 'samples': 26458752, 'steps': 137805, 'loss/train': 1.6610558032989502} 08/31/2021 14:17:17 - INFO - __main__ - Step 137807: {'lr': 8.328227438400032e-06, 'samples': 26458944, 'steps': 137806, 'loss/train': 1.494006872177124} 08/31/2021 14:17:17 - INFO - __main__ - Step 137808: {'lr': 8.326869172883555e-06, 'samples': 26459136, 'steps': 137807, 'loss/train': 1.4645764827728271} 08/31/2021 14:17:19 - INFO - __main__ - Step 137809: {'lr': 8.32551101626125e-06, 'samples': 26459328, 'steps': 137808, 'loss/train': 0.013694532215595245} 08/31/2021 14:17:19 - INFO - __main__ - Step 137810: {'lr': 8.324152968533755e-06, 'samples': 26459520, 'steps': 137809, 'loss/train': 1.177771806716919} 08/31/2021 14:17:20 - INFO - __main__ - Step 137811: {'lr': 8.322795029701651e-06, 'samples': 26459712, 'steps': 137810, 'loss/train': 0.8921011686325073} 08/31/2021 14:17:20 - INFO - __main__ - Step 137812: {'lr': 8.321437199765552e-06, 'samples': 26459904, 'steps': 137811, 'loss/train': 1.0711846351623535} 08/31/2021 14:17:20 - INFO - __main__ - Step 137813: {'lr': 8.320079478726123e-06, 'samples': 26460096, 'steps': 137812, 'loss/train': 0.7430490255355835} 08/31/2021 14:17:21 - INFO - __main__ - Step 137814: {'lr': 8.318721866583917e-06, 'samples': 26460288, 'steps': 137813, 'loss/train': 1.0493758916854858} 08/31/2021 14:17:23 - INFO - __main__ - Step 137815: {'lr': 8.317364363339547e-06, 'samples': 26460480, 'steps': 137814, 'loss/train': 1.4688750505447388} 08/31/2021 14:17:23 - INFO - __main__ - Step 137816: {'lr': 8.316006968993678e-06, 'samples': 26460672, 'steps': 137815, 'loss/train': 0.5713168382644653} 08/31/2021 14:17:24 - INFO - __main__ - Step 137817: {'lr': 8.314649683546893e-06, 'samples': 26460864, 'steps': 137816, 'loss/train': 1.0902013778686523} 08/31/2021 14:17:24 - INFO - __main__ - Step 137818: {'lr': 8.313292506999775e-06, 'samples': 26461056, 'steps': 137817, 'loss/train': 1.166909098625183} 08/31/2021 14:17:25 - INFO - __main__ - Step 137819: {'lr': 8.311935439352964e-06, 'samples': 26461248, 'steps': 137818, 'loss/train': 1.4144484996795654} 08/31/2021 14:17:26 - INFO - __main__ - Step 137820: {'lr': 8.31057848060704e-06, 'samples': 26461440, 'steps': 137819, 'loss/train': 0.6310644149780273} 08/31/2021 14:17:27 - INFO - __main__ - Step 137821: {'lr': 8.30922163076267e-06, 'samples': 26461632, 'steps': 137820, 'loss/train': 0.9532647132873535} 08/31/2021 14:17:27 - INFO - __main__ - Step 137822: {'lr': 8.30786488982041e-06, 'samples': 26461824, 'steps': 137821, 'loss/train': 0.04855028912425041} 08/31/2021 14:17:27 - INFO - __main__ - Step 137823: {'lr': 8.306508257780926e-06, 'samples': 26462016, 'steps': 137822, 'loss/train': 1.2721662521362305} 08/31/2021 14:17:28 - INFO - __main__ - Step 137824: {'lr': 8.305151734644773e-06, 'samples': 26462208, 'steps': 137823, 'loss/train': 1.483591914176941} 08/31/2021 14:17:29 - INFO - __main__ - Step 137825: {'lr': 8.303795320412616e-06, 'samples': 26462400, 'steps': 137824, 'loss/train': 1.2476081848144531} 08/31/2021 14:17:30 - INFO - __main__ - Step 137826: {'lr': 8.302439015085012e-06, 'samples': 26462592, 'steps': 137825, 'loss/train': 1.7247939109802246} 08/31/2021 14:17:30 - INFO - __main__ - Step 137827: {'lr': 8.301082818662626e-06, 'samples': 26462784, 'steps': 137826, 'loss/train': 0.0979970172047615} 08/31/2021 14:17:30 - INFO - __main__ - Step 137828: {'lr': 8.29972673114604e-06, 'samples': 26462976, 'steps': 137827, 'loss/train': 0.944573700428009} 08/31/2021 14:17:31 - INFO - __main__ - Step 137829: {'lr': 8.298370752535866e-06, 'samples': 26463168, 'steps': 137828, 'loss/train': 1.0372931957244873} 08/31/2021 14:17:32 - INFO - __main__ - Step 137830: {'lr': 8.297014882832687e-06, 'samples': 26463360, 'steps': 137829, 'loss/train': 1.3349841833114624} 08/31/2021 14:17:33 - INFO - __main__ - Step 137831: {'lr': 8.295659122037168e-06, 'samples': 26463552, 'steps': 137830, 'loss/train': 1.0219535827636719} 08/31/2021 14:17:33 - INFO - __main__ - Step 137832: {'lr': 8.294303470149894e-06, 'samples': 26463744, 'steps': 137831, 'loss/train': 0.7195739150047302} 08/31/2021 14:17:33 - INFO - __main__ - Step 137833: {'lr': 8.292947927171473e-06, 'samples': 26463936, 'steps': 137832, 'loss/train': 0.16723798215389252} 08/31/2021 14:17:34 - INFO - __main__ - Step 137834: {'lr': 8.291592493102517e-06, 'samples': 26464128, 'steps': 137833, 'loss/train': 1.3260185718536377} 08/31/2021 14:17:35 - INFO - __main__ - Step 137835: {'lr': 8.290237167943637e-06, 'samples': 26464320, 'steps': 137834, 'loss/train': 1.5195821523666382} 08/31/2021 14:17:36 - INFO - __main__ - Step 137836: {'lr': 8.288881951695443e-06, 'samples': 26464512, 'steps': 137835, 'loss/train': 1.338195562362671} 08/31/2021 14:17:36 - INFO - __main__ - Step 137837: {'lr': 8.287526844358572e-06, 'samples': 26464704, 'steps': 137836, 'loss/train': 1.2841672897338867} 08/31/2021 14:17:36 - INFO - __main__ - Step 137838: {'lr': 8.286171845933583e-06, 'samples': 26464896, 'steps': 137837, 'loss/train': 1.2961955070495605} 08/31/2021 14:17:37 - INFO - __main__ - Step 137839: {'lr': 8.284816956421138e-06, 'samples': 26465088, 'steps': 137838, 'loss/train': 0.8433132767677307} 08/31/2021 14:17:38 - INFO - __main__ - Step 137840: {'lr': 8.283462175821821e-06, 'samples': 26465280, 'steps': 137839, 'loss/train': 1.4552626609802246} 08/31/2021 14:17:39 - INFO - __main__ - Step 137841: {'lr': 8.28210750413627e-06, 'samples': 26465472, 'steps': 137840, 'loss/train': 1.0171819925308228} 08/31/2021 14:17:39 - INFO - __main__ - Step 137842: {'lr': 8.280752941365044e-06, 'samples': 26465664, 'steps': 137841, 'loss/train': 0.2871382534503937} 08/31/2021 14:17:39 - INFO - __main__ - Step 137843: {'lr': 8.279398487508776e-06, 'samples': 26465856, 'steps': 137842, 'loss/train': 0.8420055508613586} 08/31/2021 14:17:40 - INFO - __main__ - Step 137844: {'lr': 8.278044142568081e-06, 'samples': 26466048, 'steps': 137843, 'loss/train': 1.9617599248886108} 08/31/2021 14:17:40 - INFO - __main__ - Step 137845: {'lr': 8.276689906543566e-06, 'samples': 26466240, 'steps': 137844, 'loss/train': 0.714175283908844} 08/31/2021 14:17:42 - INFO - __main__ - Step 137846: {'lr': 8.275335779435845e-06, 'samples': 26466432, 'steps': 137845, 'loss/train': 0.78179532289505} 08/31/2021 14:17:42 - INFO - __main__ - Step 137847: {'lr': 8.273981761245525e-06, 'samples': 26466624, 'steps': 137846, 'loss/train': 0.8847718238830566} 08/31/2021 14:17:43 - INFO - __main__ - Step 137848: {'lr': 8.272627851973246e-06, 'samples': 26466816, 'steps': 137847, 'loss/train': 0.2438337355852127} 08/31/2021 14:17:43 - INFO - __main__ - Step 137849: {'lr': 8.271274051619566e-06, 'samples': 26467008, 'steps': 137848, 'loss/train': 0.7315258383750916} 08/31/2021 14:17:43 - INFO - __main__ - Step 137850: {'lr': 8.269920360185118e-06, 'samples': 26467200, 'steps': 137849, 'loss/train': 0.2883305847644806} 08/31/2021 14:17:45 - INFO - __main__ - Step 137851: {'lr': 8.268566777670516e-06, 'samples': 26467392, 'steps': 137850, 'loss/train': 1.2078912258148193} 08/31/2021 14:17:45 - INFO - __main__ - Step 137852: {'lr': 8.267213304076371e-06, 'samples': 26467584, 'steps': 137851, 'loss/train': 1.0486798286437988} 08/31/2021 14:17:46 - INFO - __main__ - Step 137853: {'lr': 8.265859939403292e-06, 'samples': 26467776, 'steps': 137852, 'loss/train': 1.2111798524856567} 08/31/2021 14:17:46 - INFO - __main__ - Step 137854: {'lr': 8.264506683651918e-06, 'samples': 26467968, 'steps': 137853, 'loss/train': 1.1224968433380127} 08/31/2021 14:17:46 - INFO - __main__ - Step 137855: {'lr': 8.263153536822804e-06, 'samples': 26468160, 'steps': 137854, 'loss/train': 0.028000634163618088} 08/31/2021 14:17:48 - INFO - __main__ - Step 137856: {'lr': 8.261800498916561e-06, 'samples': 26468352, 'steps': 137855, 'loss/train': 1.0704271793365479} 08/31/2021 14:17:48 - INFO - __main__ - Step 137857: {'lr': 8.260447569933827e-06, 'samples': 26468544, 'steps': 137856, 'loss/train': 1.1408072710037231} 08/31/2021 14:17:49 - INFO - __main__ - Step 137858: {'lr': 8.259094749875213e-06, 'samples': 26468736, 'steps': 137857, 'loss/train': 1.2327251434326172} 08/31/2021 14:17:49 - INFO - __main__ - Step 137859: {'lr': 8.257742038741327e-06, 'samples': 26468928, 'steps': 137858, 'loss/train': 1.0025591850280762} 08/31/2021 14:17:49 - INFO - __main__ - Step 137860: {'lr': 8.256389436532757e-06, 'samples': 26469120, 'steps': 137859, 'loss/train': 0.8661543130874634} 08/31/2021 14:17:51 - INFO - __main__ - Step 137861: {'lr': 8.255036943250139e-06, 'samples': 26469312, 'steps': 137860, 'loss/train': 1.1628789901733398} 08/31/2021 14:17:51 - INFO - __main__ - Step 137862: {'lr': 8.253684558894053e-06, 'samples': 26469504, 'steps': 137861, 'loss/train': 1.13626229763031} 08/31/2021 14:17:52 - INFO - __main__ - Step 137863: {'lr': 8.252332283465142e-06, 'samples': 26469696, 'steps': 137862, 'loss/train': 0.7273203134536743} 08/31/2021 14:17:52 - INFO - __main__ - Step 137864: {'lr': 8.250980116964013e-06, 'samples': 26469888, 'steps': 137863, 'loss/train': 1.448756217956543} 08/31/2021 14:17:52 - INFO - __main__ - Step 137865: {'lr': 8.249628059391251e-06, 'samples': 26470080, 'steps': 137864, 'loss/train': 1.021598219871521} 08/31/2021 14:17:53 - INFO - __main__ - Step 137866: {'lr': 8.248276110747465e-06, 'samples': 26470272, 'steps': 137865, 'loss/train': 1.2360535860061646} 08/31/2021 14:17:54 - INFO - __main__ - Step 137867: {'lr': 8.246924271033268e-06, 'samples': 26470464, 'steps': 137866, 'loss/train': 0.9481722712516785} 08/31/2021 14:17:55 - INFO - __main__ - Step 137868: {'lr': 8.245572540249324e-06, 'samples': 26470656, 'steps': 137867, 'loss/train': 0.13094380497932434} 08/31/2021 14:17:55 - INFO - __main__ - Step 137869: {'lr': 8.244220918396162e-06, 'samples': 26470848, 'steps': 137868, 'loss/train': 0.7773883938789368} 08/31/2021 14:17:56 - INFO - __main__ - Step 137870: {'lr': 8.242869405474418e-06, 'samples': 26471040, 'steps': 137869, 'loss/train': 0.9145850539207458} 08/31/2021 14:17:56 - INFO - __main__ - Step 137871: {'lr': 8.241518001484705e-06, 'samples': 26471232, 'steps': 137870, 'loss/train': 0.8995262384414673} 08/31/2021 14:17:58 - INFO - __main__ - Step 137872: {'lr': 8.24016670642766e-06, 'samples': 26471424, 'steps': 137871, 'loss/train': 0.6188240647315979} 08/31/2021 14:17:58 - INFO - __main__ - Step 137873: {'lr': 8.238815520303838e-06, 'samples': 26471616, 'steps': 137872, 'loss/train': 1.3111636638641357} 08/31/2021 14:17:59 - INFO - __main__ - Step 137874: {'lr': 8.237464443113879e-06, 'samples': 26471808, 'steps': 137873, 'loss/train': 0.8782071471214294} 08/31/2021 14:17:59 - INFO - __main__ - Step 137875: {'lr': 8.236113474858393e-06, 'samples': 26472000, 'steps': 137874, 'loss/train': 1.4443230628967285} 08/31/2021 14:18:00 - INFO - __main__ - Step 137876: {'lr': 8.234762615537988e-06, 'samples': 26472192, 'steps': 137875, 'loss/train': 1.3290222883224487} 08/31/2021 14:18:01 - INFO - __main__ - Step 137877: {'lr': 8.23341186515325e-06, 'samples': 26472384, 'steps': 137876, 'loss/train': 1.511953592300415} 08/31/2021 14:18:01 - INFO - __main__ - Step 137878: {'lr': 8.232061223704817e-06, 'samples': 26472576, 'steps': 137877, 'loss/train': 1.0968351364135742} 08/31/2021 14:18:02 - INFO - __main__ - Step 137879: {'lr': 8.2307106911933e-06, 'samples': 26472768, 'steps': 137878, 'loss/train': 4.352260589599609} 08/31/2021 14:18:02 - INFO - __main__ - Step 137880: {'lr': 8.229360267619279e-06, 'samples': 26472960, 'steps': 137879, 'loss/train': 0.6947383284568787} 08/31/2021 14:18:02 - INFO - __main__ - Step 137881: {'lr': 8.228009952983395e-06, 'samples': 26473152, 'steps': 137880, 'loss/train': 1.0299348831176758} 08/31/2021 14:18:04 - INFO - __main__ - Step 137882: {'lr': 8.22665974728623e-06, 'samples': 26473344, 'steps': 137881, 'loss/train': 0.941663384437561} 08/31/2021 14:18:04 - INFO - __main__ - Step 137883: {'lr': 8.225309650528395e-06, 'samples': 26473536, 'steps': 137882, 'loss/train': 1.0453014373779297} 08/31/2021 14:18:05 - INFO - __main__ - Step 137884: {'lr': 8.223959662710501e-06, 'samples': 26473728, 'steps': 137883, 'loss/train': 0.026144256815314293} 08/31/2021 14:18:05 - INFO - __main__ - Step 137885: {'lr': 8.222609783833157e-06, 'samples': 26473920, 'steps': 137884, 'loss/train': 0.5221273303031921} 08/31/2021 14:18:05 - INFO - __main__ - Step 137886: {'lr': 8.221260013896976e-06, 'samples': 26474112, 'steps': 137885, 'loss/train': 0.9247213006019592} 08/31/2021 14:18:07 - INFO - __main__ - Step 137887: {'lr': 8.219910352902565e-06, 'samples': 26474304, 'steps': 137886, 'loss/train': 1.5858163833618164} 08/31/2021 14:18:07 - INFO - __main__ - Step 137888: {'lr': 8.21856080085054e-06, 'samples': 26474496, 'steps': 137887, 'loss/train': 1.1094905138015747} 08/31/2021 14:18:08 - INFO - __main__ - Step 137889: {'lr': 8.217211357741506e-06, 'samples': 26474688, 'steps': 137888, 'loss/train': 1.2786527872085571} 08/31/2021 14:18:08 - INFO - __main__ - Step 137890: {'lr': 8.215862023576049e-06, 'samples': 26474880, 'steps': 137889, 'loss/train': 1.3388943672180176} 08/31/2021 14:18:08 - INFO - __main__ - Step 137891: {'lr': 8.214512798354806e-06, 'samples': 26475072, 'steps': 137890, 'loss/train': 2.0755438804626465} 08/31/2021 14:18:10 - INFO - __main__ - Step 137892: {'lr': 8.213163682078361e-06, 'samples': 26475264, 'steps': 137891, 'loss/train': 0.8213968276977539} 08/31/2021 14:18:10 - INFO - __main__ - Step 137893: {'lr': 8.211814674747354e-06, 'samples': 26475456, 'steps': 137892, 'loss/train': 1.2222874164581299} 08/31/2021 14:18:11 - INFO - __main__ - Step 137894: {'lr': 8.210465776362364e-06, 'samples': 26475648, 'steps': 137893, 'loss/train': 0.6724554300308228} 08/31/2021 14:18:11 - INFO - __main__ - Step 137895: {'lr': 8.209116986924004e-06, 'samples': 26475840, 'steps': 137894, 'loss/train': 1.05482816696167} 08/31/2021 14:18:11 - INFO - __main__ - Step 137896: {'lr': 8.207768306432883e-06, 'samples': 26476032, 'steps': 137895, 'loss/train': 0.5795413255691528} 08/31/2021 14:18:13 - INFO - __main__ - Step 137897: {'lr': 8.206419734889614e-06, 'samples': 26476224, 'steps': 137896, 'loss/train': 1.5769702196121216} 08/31/2021 14:18:13 - INFO - __main__ - Step 137898: {'lr': 8.205071272294807e-06, 'samples': 26476416, 'steps': 137897, 'loss/train': 1.0522546768188477} 08/31/2021 14:18:14 - INFO - __main__ - Step 137899: {'lr': 8.203722918649042e-06, 'samples': 26476608, 'steps': 137898, 'loss/train': 1.1735068559646606} 08/31/2021 14:18:14 - INFO - __main__ - Step 137900: {'lr': 8.20237467395296e-06, 'samples': 26476800, 'steps': 137899, 'loss/train': 0.7109626531600952} 08/31/2021 14:18:14 - INFO - __main__ - Step 137901: {'lr': 8.201026538207146e-06, 'samples': 26476992, 'steps': 137900, 'loss/train': 0.15308955311775208} 08/31/2021 14:18:16 - INFO - __main__ - Step 137902: {'lr': 8.199678511412234e-06, 'samples': 26477184, 'steps': 137901, 'loss/train': 1.3728405237197876} 08/31/2021 14:18:16 - INFO - __main__ - Step 137903: {'lr': 8.198330593568808e-06, 'samples': 26477376, 'steps': 137902, 'loss/train': 1.6964962482452393} 08/31/2021 14:18:17 - INFO - __main__ - Step 137904: {'lr': 8.196982784677482e-06, 'samples': 26477568, 'steps': 137903, 'loss/train': 1.0547387599945068} 08/31/2021 14:18:17 - INFO - __main__ - Step 137905: {'lr': 8.195635084738862e-06, 'samples': 26477760, 'steps': 137904, 'loss/train': 0.8396760821342468} 08/31/2021 14:18:17 - INFO - __main__ - Step 137906: {'lr': 8.19428749375356e-06, 'samples': 26477952, 'steps': 137905, 'loss/train': 1.194657564163208} 08/31/2021 14:18:18 - INFO - __main__ - Step 137907: {'lr': 8.192940011722189e-06, 'samples': 26478144, 'steps': 137906, 'loss/train': 0.7581983208656311} 08/31/2021 14:18:19 - INFO - __main__ - Step 137908: {'lr': 8.191592638645384e-06, 'samples': 26478336, 'steps': 137907, 'loss/train': 0.6377593278884888} 08/31/2021 14:18:20 - INFO - __main__ - Step 137909: {'lr': 8.190245374523674e-06, 'samples': 26478528, 'steps': 137908, 'loss/train': 1.2478355169296265} 08/31/2021 14:18:20 - INFO - __main__ - Step 137910: {'lr': 8.1888982193577e-06, 'samples': 26478720, 'steps': 137909, 'loss/train': 0.11025796830654144} 08/31/2021 14:18:20 - INFO - __main__ - Step 137911: {'lr': 8.187551173148095e-06, 'samples': 26478912, 'steps': 137910, 'loss/train': 0.5282986164093018} 08/31/2021 14:18:21 - INFO - __main__ - Step 137912: {'lr': 8.186204235895417e-06, 'samples': 26479104, 'steps': 137911, 'loss/train': 1.321696162223816} 08/31/2021 14:18:22 - INFO - __main__ - Step 137913: {'lr': 8.184857407600332e-06, 'samples': 26479296, 'steps': 137912, 'loss/train': 1.2839473485946655} 08/31/2021 14:18:23 - INFO - __main__ - Step 137914: {'lr': 8.183510688263424e-06, 'samples': 26479488, 'steps': 137913, 'loss/train': 1.2316709756851196} 08/31/2021 14:18:23 - INFO - __main__ - Step 137915: {'lr': 8.182164077885273e-06, 'samples': 26479680, 'steps': 137914, 'loss/train': 1.3245569467544556} 08/31/2021 14:18:23 - INFO - __main__ - Step 137916: {'lr': 8.18081757646652e-06, 'samples': 26479872, 'steps': 137915, 'loss/train': 1.1033309698104858} 08/31/2021 14:18:24 - INFO - __main__ - Step 137917: {'lr': 8.179471184007748e-06, 'samples': 26480064, 'steps': 137916, 'loss/train': 0.5577165484428406} 08/31/2021 14:18:25 - INFO - __main__ - Step 137918: {'lr': 8.178124900509593e-06, 'samples': 26480256, 'steps': 137917, 'loss/train': 0.8349224328994751} 08/31/2021 14:18:26 - INFO - __main__ - Step 137919: {'lr': 8.17677872597264e-06, 'samples': 26480448, 'steps': 137918, 'loss/train': 0.9840165972709656} 08/31/2021 14:18:26 - INFO - __main__ - Step 137920: {'lr': 8.175432660397496e-06, 'samples': 26480640, 'steps': 137919, 'loss/train': 0.7006881833076477} 08/31/2021 14:18:26 - INFO - __main__ - Step 137921: {'lr': 8.174086703784779e-06, 'samples': 26480832, 'steps': 137920, 'loss/train': 1.1035104990005493} 08/31/2021 14:18:27 - INFO - __main__ - Step 137922: {'lr': 8.172740856135092e-06, 'samples': 26481024, 'steps': 137921, 'loss/train': 1.102339267730713} 08/31/2021 14:18:29 - INFO - __main__ - Step 137923: {'lr': 8.171395117449022e-06, 'samples': 26481216, 'steps': 137922, 'loss/train': 0.6311558485031128} 08/31/2021 14:18:29 - INFO - __main__ - Step 137924: {'lr': 8.170049487727177e-06, 'samples': 26481408, 'steps': 137923, 'loss/train': 1.0944768190383911} 08/31/2021 14:18:30 - INFO - __main__ - Step 137925: {'lr': 8.16870396697017e-06, 'samples': 26481600, 'steps': 137924, 'loss/train': 1.3281614780426025} 08/31/2021 14:18:30 - INFO - __main__ - Step 137926: {'lr': 8.167358555178639e-06, 'samples': 26481792, 'steps': 137925, 'loss/train': 0.9858726859092712} 08/31/2021 14:18:30 - INFO - __main__ - Step 137927: {'lr': 8.166013252353167e-06, 'samples': 26481984, 'steps': 137926, 'loss/train': 0.5501434803009033} 08/31/2021 14:18:32 - INFO - __main__ - Step 137928: {'lr': 8.164668058494334e-06, 'samples': 26482176, 'steps': 137927, 'loss/train': 0.03523164987564087} 08/31/2021 14:18:32 - INFO - __main__ - Step 137929: {'lr': 8.163322973602782e-06, 'samples': 26482368, 'steps': 137928, 'loss/train': 1.2346526384353638} 08/31/2021 14:18:32 - INFO - __main__ - Step 137930: {'lr': 8.161977997679093e-06, 'samples': 26482560, 'steps': 137929, 'loss/train': 0.9884077310562134} 08/31/2021 14:18:33 - INFO - __main__ - Step 137931: {'lr': 8.160633130723904e-06, 'samples': 26482752, 'steps': 137930, 'loss/train': 0.5812830924987793} 08/31/2021 14:18:33 - INFO - __main__ - Step 137932: {'lr': 8.1592883727378e-06, 'samples': 26482944, 'steps': 137931, 'loss/train': 1.1453698873519897} 08/31/2021 14:18:35 - INFO - __main__ - Step 137933: {'lr': 8.157943723721389e-06, 'samples': 26483136, 'steps': 137932, 'loss/train': 0.7791799902915955} 08/31/2021 14:18:35 - INFO - __main__ - Step 137934: {'lr': 8.156599183675256e-06, 'samples': 26483328, 'steps': 137933, 'loss/train': 2.005204439163208} 08/31/2021 14:18:36 - INFO - __main__ - Step 137935: {'lr': 8.155254752600067e-06, 'samples': 26483520, 'steps': 137934, 'loss/train': 1.3503196239471436} 08/31/2021 14:18:36 - INFO - __main__ - Step 137936: {'lr': 8.153910430496375e-06, 'samples': 26483712, 'steps': 137935, 'loss/train': 0.26796087622642517} 08/31/2021 14:18:36 - INFO - __main__ - Step 137937: {'lr': 8.152566217364793e-06, 'samples': 26483904, 'steps': 137936, 'loss/train': 0.9669865965843201} 08/31/2021 14:18:38 - INFO - __main__ - Step 137938: {'lr': 8.15122211320593e-06, 'samples': 26484096, 'steps': 137937, 'loss/train': 0.7927748560905457} 08/31/2021 14:18:38 - INFO - __main__ - Step 137939: {'lr': 8.149878118020371e-06, 'samples': 26484288, 'steps': 137938, 'loss/train': 0.7678341269493103} 08/31/2021 14:18:39 - INFO - __main__ - Step 137940: {'lr': 8.14853423180878e-06, 'samples': 26484480, 'steps': 137939, 'loss/train': 1.4607573747634888} 08/31/2021 14:18:39 - INFO - __main__ - Step 137941: {'lr': 8.147190454571712e-06, 'samples': 26484672, 'steps': 137940, 'loss/train': 1.4270108938217163} 08/31/2021 14:18:40 - INFO - __main__ - Step 137942: {'lr': 8.14584678630978e-06, 'samples': 26484864, 'steps': 137941, 'loss/train': 0.9132266044616699} 08/31/2021 14:18:40 - INFO - __main__ - Step 137943: {'lr': 8.14450322702362e-06, 'samples': 26485056, 'steps': 137942, 'loss/train': 0.7960871458053589} 08/31/2021 14:18:41 - INFO - __main__ - Step 137944: {'lr': 8.143159776713788e-06, 'samples': 26485248, 'steps': 137943, 'loss/train': 1.5366250276565552} 08/31/2021 14:18:42 - INFO - __main__ - Step 137945: {'lr': 8.141816435380923e-06, 'samples': 26485440, 'steps': 137944, 'loss/train': 0.6130669116973877} 08/31/2021 14:18:42 - INFO - __main__ - Step 137946: {'lr': 8.140473203025633e-06, 'samples': 26485632, 'steps': 137945, 'loss/train': 1.6407690048217773} 08/31/2021 14:18:42 - INFO - __main__ - Step 137947: {'lr': 8.139130079648505e-06, 'samples': 26485824, 'steps': 137946, 'loss/train': 1.0436218976974487} 08/31/2021 14:18:43 - INFO - __main__ - Step 137948: {'lr': 8.137787065250202e-06, 'samples': 26486016, 'steps': 137947, 'loss/train': 1.5075687170028687} 08/31/2021 14:18:44 - INFO - __main__ - Step 137949: {'lr': 8.136444159831225e-06, 'samples': 26486208, 'steps': 137948, 'loss/train': 1.4318902492523193} 08/31/2021 14:18:45 - INFO - __main__ - Step 137950: {'lr': 8.135101363392266e-06, 'samples': 26486400, 'steps': 137949, 'loss/train': 1.5159275531768799} 08/31/2021 14:18:45 - INFO - __main__ - Step 137951: {'lr': 8.133758675933856e-06, 'samples': 26486592, 'steps': 137950, 'loss/train': 0.8776724934577942} 08/31/2021 14:18:46 - INFO - __main__ - Step 137952: {'lr': 8.132416097456686e-06, 'samples': 26486784, 'steps': 137951, 'loss/train': 0.049523040652275085} 08/31/2021 14:18:46 - INFO - __main__ - Step 137953: {'lr': 8.131073627961283e-06, 'samples': 26486976, 'steps': 137952, 'loss/train': 1.1316158771514893} 08/31/2021 14:18:48 - INFO - __main__ - Step 137954: {'lr': 8.129731267448287e-06, 'samples': 26487168, 'steps': 137953, 'loss/train': 1.274627447128296} 08/31/2021 14:18:48 - INFO - __main__ - Step 137955: {'lr': 8.128389015918309e-06, 'samples': 26487360, 'steps': 137954, 'loss/train': 0.10477359592914581} 08/31/2021 14:18:48 - INFO - __main__ - Step 137956: {'lr': 8.127046873371958e-06, 'samples': 26487552, 'steps': 137955, 'loss/train': 1.0820952653884888} 08/31/2021 14:18:49 - INFO - __main__ - Step 137957: {'lr': 8.125704839809816e-06, 'samples': 26487744, 'steps': 137956, 'loss/train': 1.3836089372634888} 08/31/2021 14:18:49 - INFO - __main__ - Step 137958: {'lr': 8.124362915232497e-06, 'samples': 26487936, 'steps': 137957, 'loss/train': 1.182869791984558} 08/31/2021 14:18:51 - INFO - __main__ - Step 137959: {'lr': 8.123021099640637e-06, 'samples': 26488128, 'steps': 137958, 'loss/train': 0.9494001865386963} 08/31/2021 14:18:51 - INFO - __main__ - Step 137960: {'lr': 8.121679393034765e-06, 'samples': 26488320, 'steps': 137959, 'loss/train': 0.5355151295661926} 08/31/2021 14:18:52 - INFO - __main__ - Step 137961: {'lr': 8.120337795415573e-06, 'samples': 26488512, 'steps': 137960, 'loss/train': 1.3158222436904907} 08/31/2021 14:18:52 - INFO - __main__ - Step 137962: {'lr': 8.118996306783616e-06, 'samples': 26488704, 'steps': 137961, 'loss/train': 1.041413426399231} 08/31/2021 14:18:52 - INFO - __main__ - Step 137963: {'lr': 8.117654927139505e-06, 'samples': 26488896, 'steps': 137962, 'loss/train': 0.15075114369392395} 08/31/2021 14:18:53 - INFO - __main__ - Step 137964: {'lr': 8.116313656483825e-06, 'samples': 26489088, 'steps': 137963, 'loss/train': 1.752458095550537} 08/31/2021 14:18:54 - INFO - __main__ - Step 137965: {'lr': 8.114972494817242e-06, 'samples': 26489280, 'steps': 137964, 'loss/train': 0.4046863913536072} 08/31/2021 14:18:55 - INFO - __main__ - Step 137966: {'lr': 8.11363144214028e-06, 'samples': 26489472, 'steps': 137965, 'loss/train': 1.0642430782318115} 08/31/2021 14:18:55 - INFO - __main__ - Step 137967: {'lr': 8.112290498453607e-06, 'samples': 26489664, 'steps': 137966, 'loss/train': 0.8257198929786682} 08/31/2021 14:18:55 - INFO - __main__ - Step 137968: {'lr': 8.110949663757777e-06, 'samples': 26489856, 'steps': 137967, 'loss/train': 1.0585780143737793} 08/31/2021 14:18:56 - INFO - __main__ - Step 137969: {'lr': 8.10960893805343e-06, 'samples': 26490048, 'steps': 137968, 'loss/train': 0.1813739538192749} 08/31/2021 14:18:57 - INFO - __main__ - Step 137970: {'lr': 8.108268321341179e-06, 'samples': 26490240, 'steps': 137969, 'loss/train': 1.1707062721252441} 08/31/2021 14:18:58 - INFO - __main__ - Step 137971: {'lr': 8.106927813621601e-06, 'samples': 26490432, 'steps': 137970, 'loss/train': 0.09791078418493271} 08/31/2021 14:18:58 - INFO - __main__ - Step 137972: {'lr': 8.105587414895283e-06, 'samples': 26490624, 'steps': 137971, 'loss/train': 1.2584589719772339} 08/31/2021 14:18:59 - INFO - __main__ - Step 137973: {'lr': 8.104247125162889e-06, 'samples': 26490816, 'steps': 137972, 'loss/train': 0.18262635171413422} 08/31/2021 14:18:59 - INFO - __main__ - Step 137974: {'lr': 8.102906944424976e-06, 'samples': 26491008, 'steps': 137973, 'loss/train': 0.7556247711181641} 08/31/2021 14:19:01 - INFO - __main__ - Step 137975: {'lr': 8.101566872682181e-06, 'samples': 26491200, 'steps': 137974, 'loss/train': 1.0565766096115112} 08/31/2021 14:19:01 - INFO - __main__ - Step 137976: {'lr': 8.10022690993506e-06, 'samples': 26491392, 'steps': 137975, 'loss/train': 0.7603344917297363} 08/31/2021 14:19:02 - INFO - __main__ - Step 137977: {'lr': 8.09888705618425e-06, 'samples': 26491584, 'steps': 137976, 'loss/train': 1.5337575674057007} 08/31/2021 14:19:02 - INFO - __main__ - Step 137978: {'lr': 8.097547311430364e-06, 'samples': 26491776, 'steps': 137977, 'loss/train': 1.055983543395996} 08/31/2021 14:19:02 - INFO - __main__ - Step 137979: {'lr': 8.096207675673955e-06, 'samples': 26491968, 'steps': 137978, 'loss/train': 1.3021748065948486} 08/31/2021 14:19:04 - INFO - __main__ - Step 137980: {'lr': 8.09486814891569e-06, 'samples': 26492160, 'steps': 137979, 'loss/train': 1.3479586839675903} 08/31/2021 14:19:04 - INFO - __main__ - Step 137981: {'lr': 8.093528731156153e-06, 'samples': 26492352, 'steps': 137980, 'loss/train': 1.108056664466858} 08/31/2021 14:19:05 - INFO - __main__ - Step 137982: {'lr': 8.092189422395897e-06, 'samples': 26492544, 'steps': 137981, 'loss/train': 0.6440226435661316} 08/31/2021 14:19:05 - INFO - __main__ - Step 137983: {'lr': 8.090850222635614e-06, 'samples': 26492736, 'steps': 137982, 'loss/train': 0.6865552067756653} 08/31/2021 14:19:05 - INFO - __main__ - Step 137984: {'lr': 8.089511131875838e-06, 'samples': 26492928, 'steps': 137983, 'loss/train': 0.07411405444145203} 08/31/2021 14:19:07 - INFO - __main__ - Step 137985: {'lr': 8.088172150117201e-06, 'samples': 26493120, 'steps': 137984, 'loss/train': 1.4263050556182861} 08/31/2021 14:19:07 - INFO - __main__ - Step 137986: {'lr': 8.086833277360289e-06, 'samples': 26493312, 'steps': 137985, 'loss/train': 1.272342324256897} 08/31/2021 14:19:08 - INFO - __main__ - Step 137987: {'lr': 8.085494513605713e-06, 'samples': 26493504, 'steps': 137986, 'loss/train': 0.6403383612632751} 08/31/2021 14:19:08 - INFO - __main__ - Step 137988: {'lr': 8.084155858854108e-06, 'samples': 26493696, 'steps': 137987, 'loss/train': 1.1713937520980835} 08/31/2021 14:19:08 - INFO - __main__ - Step 137989: {'lr': 8.08281731310606e-06, 'samples': 26493888, 'steps': 137988, 'loss/train': 0.4616750478744507} 08/31/2021 14:19:09 - INFO - __main__ - Step 137990: {'lr': 8.081478876362126e-06, 'samples': 26494080, 'steps': 137989, 'loss/train': 1.0815640687942505} 08/31/2021 14:19:10 - INFO - __main__ - Step 137991: {'lr': 8.080140548622966e-06, 'samples': 26494272, 'steps': 137990, 'loss/train': 1.2376854419708252} 08/31/2021 14:19:11 - INFO - __main__ - Step 137992: {'lr': 8.07880232988914e-06, 'samples': 26494464, 'steps': 137991, 'loss/train': 0.4413733184337616} 08/31/2021 14:19:11 - INFO - __main__ - Step 137993: {'lr': 8.077464220161285e-06, 'samples': 26494656, 'steps': 137992, 'loss/train': 1.9090380668640137} 08/31/2021 14:19:12 - INFO - __main__ - Step 137994: {'lr': 8.076126219439984e-06, 'samples': 26494848, 'steps': 137993, 'loss/train': 0.522222638130188} 08/31/2021 14:19:12 - INFO - __main__ - Step 137995: {'lr': 8.074788327725873e-06, 'samples': 26495040, 'steps': 137994, 'loss/train': 0.9807718992233276} 08/31/2021 14:19:14 - INFO - __main__ - Step 137996: {'lr': 8.073450545019484e-06, 'samples': 26495232, 'steps': 137995, 'loss/train': 0.9817153811454773} 08/31/2021 14:19:14 - INFO - __main__ - Step 137997: {'lr': 8.072112871321508e-06, 'samples': 26495424, 'steps': 137996, 'loss/train': 1.495188593864441} 08/31/2021 14:19:14 - INFO - __main__ - Step 137998: {'lr': 8.070775306632472e-06, 'samples': 26495616, 'steps': 137997, 'loss/train': 0.9587782025337219} 08/31/2021 14:19:15 - INFO - __main__ - Step 137999: {'lr': 8.069437850953043e-06, 'samples': 26495808, 'steps': 137998, 'loss/train': 1.142530083656311} 08/31/2021 14:19:15 - INFO - __main__ - Step 138000: {'lr': 8.068100504283776e-06, 'samples': 26496000, 'steps': 137999, 'loss/train': 0.7437384128570557} 08/31/2021 14:19:17 - INFO - __main__ - Step 138001: {'lr': 8.066763266625281e-06, 'samples': 26496192, 'steps': 138000, 'loss/train': 1.4336061477661133} 08/31/2021 14:19:17 - INFO - __main__ - Step 138002: {'lr': 8.0654261379782e-06, 'samples': 26496384, 'steps': 138001, 'loss/train': 0.25630834698677063} 08/31/2021 14:19:17 - INFO - __main__ - Step 138003: {'lr': 8.064089118343082e-06, 'samples': 26496576, 'steps': 138002, 'loss/train': 1.0862873792648315} 08/31/2021 14:19:18 - INFO - __main__ - Step 138004: {'lr': 8.062752207720541e-06, 'samples': 26496768, 'steps': 138003, 'loss/train': 0.6976785063743591} 08/31/2021 14:19:18 - INFO - __main__ - Step 138005: {'lr': 8.061415406111217e-06, 'samples': 26496960, 'steps': 138004, 'loss/train': 0.6435213685035706} 08/31/2021 14:19:18 - INFO - __main__ - Step 138006: {'lr': 8.060078713515661e-06, 'samples': 26497152, 'steps': 138005, 'loss/train': 0.7382898330688477} 08/31/2021 14:19:20 - INFO - __main__ - Step 138007: {'lr': 8.058742129934515e-06, 'samples': 26497344, 'steps': 138006, 'loss/train': 1.1412850618362427} 08/31/2021 14:19:20 - INFO - __main__ - Step 138008: {'lr': 8.05740565536836e-06, 'samples': 26497536, 'steps': 138007, 'loss/train': 0.4108055531978607} 08/31/2021 14:19:21 - INFO - __main__ - Step 138009: {'lr': 8.056069289817807e-06, 'samples': 26497728, 'steps': 138008, 'loss/train': 1.0739864110946655} 08/31/2021 14:19:21 - INFO - __main__ - Step 138010: {'lr': 8.05473303328344e-06, 'samples': 26497920, 'steps': 138009, 'loss/train': 0.478058397769928} 08/31/2021 14:19:21 - INFO - __main__ - Step 138011: {'lr': 8.053396885765896e-06, 'samples': 26498112, 'steps': 138010, 'loss/train': 1.4465885162353516} 08/31/2021 14:19:23 - INFO - __main__ - Step 138012: {'lr': 8.052060847265757e-06, 'samples': 26498304, 'steps': 138011, 'loss/train': 1.3194721937179565} 08/31/2021 14:19:23 - INFO - __main__ - Step 138013: {'lr': 8.050724917783635e-06, 'samples': 26498496, 'steps': 138012, 'loss/train': 1.4982355833053589} 08/31/2021 14:19:24 - INFO - __main__ - Step 138014: {'lr': 8.049389097320087e-06, 'samples': 26498688, 'steps': 138013, 'loss/train': 0.9182791709899902} 08/31/2021 14:19:24 - INFO - __main__ - Step 138015: {'lr': 8.048053385875803e-06, 'samples': 26498880, 'steps': 138014, 'loss/train': 1.2505854368209839} 08/31/2021 14:19:24 - INFO - __main__ - Step 138016: {'lr': 8.046717783451312e-06, 'samples': 26499072, 'steps': 138015, 'loss/train': 1.446272850036621} 08/31/2021 14:19:26 - INFO - __main__ - Step 138017: {'lr': 8.045382290047225e-06, 'samples': 26499264, 'steps': 138016, 'loss/train': 1.0930356979370117} 08/31/2021 14:19:26 - INFO - __main__ - Step 138018: {'lr': 8.044046905664155e-06, 'samples': 26499456, 'steps': 138017, 'loss/train': 0.9265615344047546} 08/31/2021 14:19:27 - INFO - __main__ - Step 138019: {'lr': 8.042711630302707e-06, 'samples': 26499648, 'steps': 138018, 'loss/train': 1.3869876861572266} 08/31/2021 14:19:27 - INFO - __main__ - Step 138020: {'lr': 8.041376463963496e-06, 'samples': 26499840, 'steps': 138019, 'loss/train': 1.4635299444198608} 08/31/2021 14:19:27 - INFO - __main__ - Step 138021: {'lr': 8.040041406647075e-06, 'samples': 26500032, 'steps': 138020, 'loss/train': 1.424762487411499} 08/31/2021 14:19:29 - INFO - __main__ - Step 138022: {'lr': 8.038706458354084e-06, 'samples': 26500224, 'steps': 138021, 'loss/train': 1.2082453966140747} 08/31/2021 14:19:30 - INFO - __main__ - Step 138023: {'lr': 8.037371619085132e-06, 'samples': 26500416, 'steps': 138022, 'loss/train': 1.3143229484558105} 08/31/2021 14:19:30 - INFO - __main__ - Step 138024: {'lr': 8.036036888840804e-06, 'samples': 26500608, 'steps': 138023, 'loss/train': 0.9564450979232788} 08/31/2021 14:19:30 - INFO - __main__ - Step 138025: {'lr': 8.034702267621708e-06, 'samples': 26500800, 'steps': 138024, 'loss/train': 0.6852734088897705} 08/31/2021 14:19:31 - INFO - __main__ - Step 138026: {'lr': 8.033367755428428e-06, 'samples': 26500992, 'steps': 138025, 'loss/train': 0.6536286473274231} 08/31/2021 14:19:33 - INFO - __main__ - Step 138027: {'lr': 8.032033352261576e-06, 'samples': 26501184, 'steps': 138026, 'loss/train': 1.5310028791427612} 08/31/2021 14:19:33 - INFO - __main__ - Step 138028: {'lr': 8.030699058121788e-06, 'samples': 26501376, 'steps': 138027, 'loss/train': 0.9928538799285889} 08/31/2021 14:19:34 - INFO - __main__ - Step 138029: {'lr': 8.02936487300962e-06, 'samples': 26501568, 'steps': 138028, 'loss/train': 0.93239825963974} 08/31/2021 14:19:34 - INFO - __main__ - Step 138030: {'lr': 8.028030796925684e-06, 'samples': 26501760, 'steps': 138029, 'loss/train': 1.1392461061477661} 08/31/2021 14:19:34 - INFO - __main__ - Step 138031: {'lr': 8.026696829870589e-06, 'samples': 26501952, 'steps': 138030, 'loss/train': 1.6676374673843384} 08/31/2021 14:19:36 - INFO - __main__ - Step 138032: {'lr': 8.025362971844918e-06, 'samples': 26502144, 'steps': 138031, 'loss/train': 0.7619530558586121} 08/31/2021 14:19:36 - INFO - __main__ - Step 138033: {'lr': 8.024029222849284e-06, 'samples': 26502336, 'steps': 138032, 'loss/train': 0.8350004553794861} 08/31/2021 14:19:37 - INFO - __main__ - Step 138034: {'lr': 8.022695582884266e-06, 'samples': 26502528, 'steps': 138033, 'loss/train': 1.9292240142822266} 08/31/2021 14:19:37 - INFO - __main__ - Step 138035: {'lr': 8.021362051950532e-06, 'samples': 26502720, 'steps': 138034, 'loss/train': 1.7556695938110352} 08/31/2021 14:19:37 - INFO - __main__ - Step 138036: {'lr': 8.02002863004861e-06, 'samples': 26502912, 'steps': 138035, 'loss/train': 1.0186551809310913} 08/31/2021 14:19:39 - INFO - __main__ - Step 138037: {'lr': 8.018695317179137e-06, 'samples': 26503104, 'steps': 138036, 'loss/train': 0.2224869281053543} 08/31/2021 14:19:40 - INFO - __main__ - Step 138038: {'lr': 8.017362113342697e-06, 'samples': 26503296, 'steps': 138037, 'loss/train': 0.8923025727272034} 08/31/2021 14:19:40 - INFO - __main__ - Step 138039: {'lr': 8.0160290185399e-06, 'samples': 26503488, 'steps': 138038, 'loss/train': 1.0949784517288208} 08/31/2021 14:19:40 - INFO - __main__ - Step 138040: {'lr': 8.014696032771356e-06, 'samples': 26503680, 'steps': 138039, 'loss/train': 0.7597271203994751} 08/31/2021 14:19:41 - INFO - __main__ - Step 138041: {'lr': 8.01336315603765e-06, 'samples': 26503872, 'steps': 138040, 'loss/train': 0.060289569199085236} 08/31/2021 14:19:41 - INFO - __main__ - Step 138042: {'lr': 8.01203038833942e-06, 'samples': 26504064, 'steps': 138041, 'loss/train': 0.3384858965873718} 08/31/2021 14:19:43 - INFO - __main__ - Step 138043: {'lr': 8.010697729677218e-06, 'samples': 26504256, 'steps': 138042, 'loss/train': 0.3742740750312805} 08/31/2021 14:19:43 - INFO - __main__ - Step 138044: {'lr': 8.009365180051658e-06, 'samples': 26504448, 'steps': 138043, 'loss/train': 1.2779549360275269} 08/31/2021 14:19:43 - INFO - __main__ - Step 138045: {'lr': 8.008032739463322e-06, 'samples': 26504640, 'steps': 138044, 'loss/train': 1.3709417581558228} 08/31/2021 14:19:44 - INFO - __main__ - Step 138046: {'lr': 8.006700407912848e-06, 'samples': 26504832, 'steps': 138045, 'loss/train': 1.4479482173919678} 08/31/2021 14:19:44 - INFO - __main__ - Step 138047: {'lr': 8.005368185400818e-06, 'samples': 26505024, 'steps': 138046, 'loss/train': 1.4733084440231323} 08/31/2021 14:19:46 - INFO - __main__ - Step 138048: {'lr': 8.004036071927844e-06, 'samples': 26505216, 'steps': 138047, 'loss/train': 1.2569587230682373} 08/31/2021 14:19:47 - INFO - __main__ - Step 138049: {'lr': 8.002704067494509e-06, 'samples': 26505408, 'steps': 138048, 'loss/train': 1.1532158851623535} 08/31/2021 14:19:47 - INFO - __main__ - Step 138050: {'lr': 8.001372172101422e-06, 'samples': 26505600, 'steps': 138049, 'loss/train': 0.4805707037448883} 08/31/2021 14:19:47 - INFO - __main__ - Step 138051: {'lr': 8.000040385749196e-06, 'samples': 26505792, 'steps': 138050, 'loss/train': 0.06671552360057831} 08/31/2021 14:19:48 - INFO - __main__ - Step 138052: {'lr': 7.998708708438384e-06, 'samples': 26505984, 'steps': 138051, 'loss/train': 0.42989930510520935} 08/31/2021 14:19:49 - INFO - __main__ - Step 138053: {'lr': 7.997377140169681e-06, 'samples': 26506176, 'steps': 138052, 'loss/train': 1.2530784606933594} 08/31/2021 14:19:50 - INFO - __main__ - Step 138054: {'lr': 7.996045680943587e-06, 'samples': 26506368, 'steps': 138053, 'loss/train': 1.2045871019363403} 08/31/2021 14:19:50 - INFO - __main__ - Step 138055: {'lr': 7.994714330760738e-06, 'samples': 26506560, 'steps': 138054, 'loss/train': 0.49901705980300903} 08/31/2021 14:19:51 - INFO - __main__ - Step 138056: {'lr': 7.99338308962172e-06, 'samples': 26506752, 'steps': 138055, 'loss/train': 1.3452903032302856} 08/31/2021 14:19:51 - INFO - __main__ - Step 138057: {'lr': 7.992051957527169e-06, 'samples': 26506944, 'steps': 138056, 'loss/train': 0.19387251138687134} 08/31/2021 14:19:52 - INFO - __main__ - Step 138058: {'lr': 7.990720934477668e-06, 'samples': 26507136, 'steps': 138057, 'loss/train': 0.02746669016778469} 08/31/2021 14:19:53 - INFO - __main__ - Step 138059: {'lr': 7.989390020473802e-06, 'samples': 26507328, 'steps': 138058, 'loss/train': 1.001076102256775} 08/31/2021 14:19:53 - INFO - __main__ - Step 138060: {'lr': 7.98805921551618e-06, 'samples': 26507520, 'steps': 138059, 'loss/train': 0.844495415687561} 08/31/2021 14:19:54 - INFO - __main__ - Step 138061: {'lr': 7.986728519605413e-06, 'samples': 26507712, 'steps': 138060, 'loss/train': 1.6391905546188354} 08/31/2021 14:19:54 - INFO - __main__ - Step 138062: {'lr': 7.985397932742083e-06, 'samples': 26507904, 'steps': 138061, 'loss/train': 0.7636439800262451} 08/31/2021 14:19:55 - INFO - __main__ - Step 138063: {'lr': 7.984067454926802e-06, 'samples': 26508096, 'steps': 138062, 'loss/train': 0.8237028121948242} 08/31/2021 14:19:56 - INFO - __main__ - Step 138064: {'lr': 7.982737086160209e-06, 'samples': 26508288, 'steps': 138063, 'loss/train': 1.4664177894592285} 08/31/2021 14:19:56 - INFO - __main__ - Step 138065: {'lr': 7.981406826442827e-06, 'samples': 26508480, 'steps': 138064, 'loss/train': 0.6248974800109863} 08/31/2021 14:19:57 - INFO - __main__ - Step 138066: {'lr': 7.980076675775272e-06, 'samples': 26508672, 'steps': 138065, 'loss/train': 0.4311424493789673} 08/31/2021 14:19:57 - INFO - __main__ - Step 138067: {'lr': 7.97874663415818e-06, 'samples': 26508864, 'steps': 138066, 'loss/train': 1.0357247591018677} 08/31/2021 14:19:58 - INFO - __main__ - Step 138068: {'lr': 7.977416701592104e-06, 'samples': 26509056, 'steps': 138067, 'loss/train': 0.7866696715354919} 08/31/2021 14:19:59 - INFO - __main__ - Step 138069: {'lr': 7.976086878077687e-06, 'samples': 26509248, 'steps': 138068, 'loss/train': 0.5712602138519287} 08/31/2021 14:19:59 - INFO - __main__ - Step 138070: {'lr': 7.97475716361551e-06, 'samples': 26509440, 'steps': 138069, 'loss/train': 0.09826850891113281} 08/31/2021 14:20:00 - INFO - __main__ - Step 138071: {'lr': 7.97342755820618e-06, 'samples': 26509632, 'steps': 138070, 'loss/train': 1.1138277053833008} 08/31/2021 14:20:00 - INFO - __main__ - Step 138072: {'lr': 7.972098061850258e-06, 'samples': 26509824, 'steps': 138071, 'loss/train': 1.4029219150543213} 08/31/2021 14:20:00 - INFO - __main__ - Step 138073: {'lr': 7.970768674548407e-06, 'samples': 26510016, 'steps': 138072, 'loss/train': 0.7509499788284302} 08/31/2021 14:20:02 - INFO - __main__ - Step 138074: {'lr': 7.969439396301182e-06, 'samples': 26510208, 'steps': 138073, 'loss/train': 0.24070405960083008} 08/31/2021 14:20:02 - INFO - __main__ - Step 138075: {'lr': 7.968110227109221e-06, 'samples': 26510400, 'steps': 138074, 'loss/train': 0.8985793590545654} 08/31/2021 14:20:03 - INFO - __main__ - Step 138076: {'lr': 7.96678116697308e-06, 'samples': 26510592, 'steps': 138075, 'loss/train': 1.0105663537979126} 08/31/2021 14:20:03 - INFO - __main__ - Step 138077: {'lr': 7.965452215893342e-06, 'samples': 26510784, 'steps': 138076, 'loss/train': 1.623579502105713} 08/31/2021 14:20:03 - INFO - __main__ - Step 138078: {'lr': 7.964123373870646e-06, 'samples': 26510976, 'steps': 138077, 'loss/train': 1.5055569410324097} 08/31/2021 14:20:06 - INFO - __main__ - Step 138079: {'lr': 7.962794640905602e-06, 'samples': 26511168, 'steps': 138078, 'loss/train': 0.8710694909095764} 08/31/2021 14:20:06 - INFO - __main__ - Step 138080: {'lr': 7.961466016998764e-06, 'samples': 26511360, 'steps': 138079, 'loss/train': 1.4693598747253418} 08/31/2021 14:20:06 - INFO - __main__ - Step 138081: {'lr': 7.960137502150772e-06, 'samples': 26511552, 'steps': 138080, 'loss/train': 0.16357043385505676} 08/31/2021 14:20:07 - INFO - __main__ - Step 138082: {'lr': 7.958809096362207e-06, 'samples': 26511744, 'steps': 138081, 'loss/train': 1.2448207139968872} 08/31/2021 14:20:07 - INFO - __main__ - Step 138083: {'lr': 7.957480799633654e-06, 'samples': 26511936, 'steps': 138082, 'loss/train': 1.1141494512557983} 08/31/2021 14:20:09 - INFO - __main__ - Step 138084: {'lr': 7.956152611965723e-06, 'samples': 26512128, 'steps': 138083, 'loss/train': 0.957197368144989} 08/31/2021 14:20:09 - INFO - __main__ - Step 138085: {'lr': 7.954824533359023e-06, 'samples': 26512320, 'steps': 138084, 'loss/train': 0.11119341850280762} 08/31/2021 14:20:09 - INFO - __main__ - Step 138086: {'lr': 7.953496563814166e-06, 'samples': 26512512, 'steps': 138085, 'loss/train': 0.815924882888794} 08/31/2021 14:20:10 - INFO - __main__ - Step 138087: {'lr': 7.952168703331708e-06, 'samples': 26512704, 'steps': 138086, 'loss/train': 0.9658098220825195} 08/31/2021 14:20:10 - INFO - __main__ - Step 138088: {'lr': 7.950840951912285e-06, 'samples': 26512896, 'steps': 138087, 'loss/train': 0.7118780016899109} 08/31/2021 14:20:11 - INFO - __main__ - Step 138089: {'lr': 7.949513309556456e-06, 'samples': 26513088, 'steps': 138088, 'loss/train': 1.2873003482818604} 08/31/2021 14:20:12 - INFO - __main__ - Step 138090: {'lr': 7.948185776264854e-06, 'samples': 26513280, 'steps': 138089, 'loss/train': 1.1441540718078613} 08/31/2021 14:20:12 - INFO - __main__ - Step 138091: {'lr': 7.946858352038038e-06, 'samples': 26513472, 'steps': 138090, 'loss/train': 1.2596232891082764} 08/31/2021 14:20:13 - INFO - __main__ - Step 138092: {'lr': 7.945531036876647e-06, 'samples': 26513664, 'steps': 138091, 'loss/train': 0.8677181601524353} 08/31/2021 14:20:13 - INFO - __main__ - Step 138093: {'lr': 7.944203830781288e-06, 'samples': 26513856, 'steps': 138092, 'loss/train': 0.9053903222084045} 08/31/2021 14:20:14 - INFO - __main__ - Step 138094: {'lr': 7.942876733752491e-06, 'samples': 26514048, 'steps': 138093, 'loss/train': 0.5919709205627441} 08/31/2021 14:20:15 - INFO - __main__ - Step 138095: {'lr': 7.941549745790922e-06, 'samples': 26514240, 'steps': 138094, 'loss/train': 1.479598045349121} 08/31/2021 14:20:15 - INFO - __main__ - Step 138096: {'lr': 7.940222866897162e-06, 'samples': 26514432, 'steps': 138095, 'loss/train': 0.423482745885849} 08/31/2021 14:20:16 - INFO - __main__ - Step 138097: {'lr': 7.938896097071824e-06, 'samples': 26514624, 'steps': 138096, 'loss/train': 2.9005179405212402} 08/31/2021 14:20:16 - INFO - __main__ - Step 138098: {'lr': 7.937569436315462e-06, 'samples': 26514816, 'steps': 138097, 'loss/train': 0.20723311603069305} 08/31/2021 14:20:17 - INFO - __main__ - Step 138099: {'lr': 7.936242884628686e-06, 'samples': 26515008, 'steps': 138098, 'loss/train': 1.5796797275543213} 08/31/2021 14:20:18 - INFO - __main__ - Step 138100: {'lr': 7.934916442012109e-06, 'samples': 26515200, 'steps': 138099, 'loss/train': 2.071326494216919} 08/31/2021 14:20:19 - INFO - __main__ - Step 138101: {'lr': 7.933590108466337e-06, 'samples': 26515392, 'steps': 138100, 'loss/train': 1.1148161888122559} 08/31/2021 14:20:19 - INFO - __main__ - Step 138102: {'lr': 7.93226388399193e-06, 'samples': 26515584, 'steps': 138101, 'loss/train': 0.8130154609680176} 08/31/2021 14:20:19 - INFO - __main__ - Step 138103: {'lr': 7.930937768589524e-06, 'samples': 26515776, 'steps': 138102, 'loss/train': 0.5078411102294922} 08/31/2021 14:20:20 - INFO - __main__ - Step 138104: {'lr': 7.929611762259702e-06, 'samples': 26515968, 'steps': 138103, 'loss/train': 0.8592841029167175} 08/31/2021 14:20:21 - INFO - __main__ - Step 138105: {'lr': 7.928285865003048e-06, 'samples': 26516160, 'steps': 138104, 'loss/train': 0.31111419200897217} 08/31/2021 14:20:22 - INFO - __main__ - Step 138106: {'lr': 7.926960076820172e-06, 'samples': 26516352, 'steps': 138105, 'loss/train': 1.1322141885757446} 08/31/2021 14:20:22 - INFO - __main__ - Step 138107: {'lr': 7.925634397711685e-06, 'samples': 26516544, 'steps': 138106, 'loss/train': 0.9907863140106201} 08/31/2021 14:20:22 - INFO - __main__ - Step 138108: {'lr': 7.924308827678166e-06, 'samples': 26516736, 'steps': 138107, 'loss/train': 0.12913979589939117} 08/31/2021 14:20:23 - INFO - __main__ - Step 138109: {'lr': 7.922983366720231e-06, 'samples': 26516928, 'steps': 138108, 'loss/train': 1.4236773252487183} 08/31/2021 14:20:23 - INFO - __main__ - Step 138110: {'lr': 7.92165801483849e-06, 'samples': 26517120, 'steps': 138109, 'loss/train': 1.1335241794586182} 08/31/2021 14:20:25 - INFO - __main__ - Step 138111: {'lr': 7.920332772033467e-06, 'samples': 26517312, 'steps': 138110, 'loss/train': 0.18773117661476135} 08/31/2021 14:20:26 - INFO - __main__ - Step 138112: {'lr': 7.91900763830583e-06, 'samples': 26517504, 'steps': 138111, 'loss/train': 0.9293282628059387} 08/31/2021 14:20:26 - INFO - __main__ - Step 138113: {'lr': 7.917682613656135e-06, 'samples': 26517696, 'steps': 138112, 'loss/train': 1.194385290145874} 08/31/2021 14:20:26 - INFO - __main__ - Step 138114: {'lr': 7.916357698084992e-06, 'samples': 26517888, 'steps': 138113, 'loss/train': 0.034883763641119} 08/31/2021 14:20:27 - INFO - __main__ - Step 138115: {'lr': 7.91503289159301e-06, 'samples': 26518080, 'steps': 138114, 'loss/train': 0.4723198711872101} 08/31/2021 14:20:28 - INFO - __main__ - Step 138116: {'lr': 7.913708194180803e-06, 'samples': 26518272, 'steps': 138115, 'loss/train': 0.13312482833862305} 08/31/2021 14:20:29 - INFO - __main__ - Step 138117: {'lr': 7.912383605848922e-06, 'samples': 26518464, 'steps': 138116, 'loss/train': 0.6853460669517517} 08/31/2021 14:20:29 - INFO - __main__ - Step 138118: {'lr': 7.91105912659798e-06, 'samples': 26518656, 'steps': 138117, 'loss/train': 1.1259874105453491} 08/31/2021 14:20:29 - INFO - __main__ - Step 138119: {'lr': 7.909734756428589e-06, 'samples': 26518848, 'steps': 138118, 'loss/train': 1.7057455778121948} 08/31/2021 14:20:30 - INFO - __main__ - Step 138120: {'lr': 7.908410495341328e-06, 'samples': 26519040, 'steps': 138119, 'loss/train': 0.8175914883613586} 08/31/2021 14:20:31 - INFO - __main__ - Step 138121: {'lr': 7.907086343336812e-06, 'samples': 26519232, 'steps': 138120, 'loss/train': 1.2214298248291016} 08/31/2021 14:20:32 - INFO - __main__ - Step 138122: {'lr': 7.905762300415592e-06, 'samples': 26519424, 'steps': 138121, 'loss/train': 0.7448965907096863} 08/31/2021 14:20:32 - INFO - __main__ - Step 138123: {'lr': 7.904438366578364e-06, 'samples': 26519616, 'steps': 138122, 'loss/train': 0.5639537572860718} 08/31/2021 14:20:33 - INFO - __main__ - Step 138124: {'lr': 7.903114541825628e-06, 'samples': 26519808, 'steps': 138123, 'loss/train': 0.11295859515666962} 08/31/2021 14:20:33 - INFO - __main__ - Step 138125: {'lr': 7.901790826158022e-06, 'samples': 26520000, 'steps': 138124, 'loss/train': 1.923285722732544} 08/31/2021 14:20:34 - INFO - __main__ - Step 138126: {'lr': 7.900467219576102e-06, 'samples': 26520192, 'steps': 138125, 'loss/train': 1.088587999343872} 08/31/2021 14:20:35 - INFO - __main__ - Step 138127: {'lr': 7.899143722080532e-06, 'samples': 26520384, 'steps': 138126, 'loss/train': 1.2229658365249634} 08/31/2021 14:20:35 - INFO - __main__ - Step 138128: {'lr': 7.89782033367184e-06, 'samples': 26520576, 'steps': 138127, 'loss/train': 0.7314300537109375} 08/31/2021 14:20:36 - INFO - __main__ - Step 138129: {'lr': 7.896497054350665e-06, 'samples': 26520768, 'steps': 138128, 'loss/train': 0.5595418214797974} 08/31/2021 14:20:36 - INFO - __main__ - Step 138130: {'lr': 7.895173884117591e-06, 'samples': 26520960, 'steps': 138129, 'loss/train': 1.3727110624313354} 08/31/2021 14:20:36 - INFO - __main__ - Step 138131: {'lr': 7.893850822973226e-06, 'samples': 26521152, 'steps': 138130, 'loss/train': 1.4219119548797607} 08/31/2021 14:20:38 - INFO - __main__ - Step 138132: {'lr': 7.892527870918153e-06, 'samples': 26521344, 'steps': 138131, 'loss/train': 0.33631443977355957} 08/31/2021 14:20:38 - INFO - __main__ - Step 138133: {'lr': 7.891205027952958e-06, 'samples': 26521536, 'steps': 138132, 'loss/train': 0.8726900815963745} 08/31/2021 14:20:39 - INFO - __main__ - Step 138134: {'lr': 7.889882294078277e-06, 'samples': 26521728, 'steps': 138133, 'loss/train': 1.1439521312713623} 08/31/2021 14:20:39 - INFO - __main__ - Step 138135: {'lr': 7.888559669294664e-06, 'samples': 26521920, 'steps': 138134, 'loss/train': 0.40922537446022034} 08/31/2021 14:20:39 - INFO - __main__ - Step 138136: {'lr': 7.887237153602761e-06, 'samples': 26522112, 'steps': 138135, 'loss/train': 1.2280879020690918} 08/31/2021 14:20:41 - INFO - __main__ - Step 138137: {'lr': 7.885914747003093e-06, 'samples': 26522304, 'steps': 138136, 'loss/train': 0.7823338508605957} 08/31/2021 14:20:42 - INFO - __main__ - Step 138138: {'lr': 7.884592449496298e-06, 'samples': 26522496, 'steps': 138137, 'loss/train': 1.486575722694397} 08/31/2021 14:20:42 - INFO - __main__ - Step 138139: {'lr': 7.883270261082987e-06, 'samples': 26522688, 'steps': 138138, 'loss/train': 0.21158885955810547} 08/31/2021 14:20:43 - INFO - __main__ - Step 138140: {'lr': 7.881948181763715e-06, 'samples': 26522880, 'steps': 138139, 'loss/train': 1.238552212715149} 08/31/2021 14:20:43 - INFO - __main__ - Step 138141: {'lr': 7.880626211539121e-06, 'samples': 26523072, 'steps': 138140, 'loss/train': 0.9035411477088928} 08/31/2021 14:20:44 - INFO - __main__ - Step 138142: {'lr': 7.87930435040976e-06, 'samples': 26523264, 'steps': 138141, 'loss/train': 1.7531278133392334} 08/31/2021 14:20:45 - INFO - __main__ - Step 138143: {'lr': 7.87798259837627e-06, 'samples': 26523456, 'steps': 138142, 'loss/train': 0.6090061068534851} 08/31/2021 14:20:45 - INFO - __main__ - Step 138144: {'lr': 7.876660955439208e-06, 'samples': 26523648, 'steps': 138143, 'loss/train': 0.8392309546470642} 08/31/2021 14:20:46 - INFO - __main__ - Step 138145: {'lr': 7.875339421599181e-06, 'samples': 26523840, 'steps': 138144, 'loss/train': 1.0926207304000854} 08/31/2021 14:20:46 - INFO - __main__ - Step 138146: {'lr': 7.874017996856803e-06, 'samples': 26524032, 'steps': 138145, 'loss/train': 0.7564529776573181} 08/31/2021 14:20:48 - INFO - __main__ - Step 138147: {'lr': 7.872696681212654e-06, 'samples': 26524224, 'steps': 138146, 'loss/train': 1.4281907081604004} 08/31/2021 14:20:48 - INFO - __main__ - Step 138148: {'lr': 7.871375474667347e-06, 'samples': 26524416, 'steps': 138147, 'loss/train': 0.2640836536884308} 08/31/2021 14:20:48 - INFO - __main__ - Step 138149: {'lr': 7.870054377221436e-06, 'samples': 26524608, 'steps': 138148, 'loss/train': 0.5592570304870605} 08/31/2021 14:20:49 - INFO - __main__ - Step 138150: {'lr': 7.868733388875587e-06, 'samples': 26524800, 'steps': 138149, 'loss/train': 0.7768367528915405} 08/31/2021 14:20:49 - INFO - __main__ - Step 138151: {'lr': 7.867412509630329e-06, 'samples': 26524992, 'steps': 138150, 'loss/train': 0.969119668006897} 08/31/2021 14:20:51 - INFO - __main__ - Step 138152: {'lr': 7.86609173948627e-06, 'samples': 26525184, 'steps': 138151, 'loss/train': 0.9035494327545166} 08/31/2021 14:20:51 - INFO - __main__ - Step 138153: {'lr': 7.864771078443994e-06, 'samples': 26525376, 'steps': 138152, 'loss/train': 0.9781997203826904} 08/31/2021 14:20:51 - INFO - __main__ - Step 138154: {'lr': 7.86345052650414e-06, 'samples': 26525568, 'steps': 138153, 'loss/train': 0.7298212051391602} 08/31/2021 14:20:52 - INFO - __main__ - Step 138155: {'lr': 7.862130083667263e-06, 'samples': 26525760, 'steps': 138154, 'loss/train': 1.1030353307724} 08/31/2021 14:20:52 - INFO - __main__ - Step 138156: {'lr': 7.860809749934e-06, 'samples': 26525952, 'steps': 138155, 'loss/train': 1.277014136314392} 08/31/2021 14:20:54 - INFO - __main__ - Step 138157: {'lr': 7.85948952530488e-06, 'samples': 26526144, 'steps': 138156, 'loss/train': 0.025863565504550934} 08/31/2021 14:20:54 - INFO - __main__ - Step 138158: {'lr': 7.85816940978057e-06, 'samples': 26526336, 'steps': 138157, 'loss/train': 0.7514743804931641} 08/31/2021 14:20:54 - INFO - __main__ - Step 138159: {'lr': 7.856849403361621e-06, 'samples': 26526528, 'steps': 138158, 'loss/train': 1.3476732969284058} 08/31/2021 14:20:55 - INFO - __main__ - Step 138160: {'lr': 7.855529506048647e-06, 'samples': 26526720, 'steps': 138159, 'loss/train': 1.437893271446228} 08/31/2021 14:20:55 - INFO - __main__ - Step 138161: {'lr': 7.854209717842232e-06, 'samples': 26526912, 'steps': 138160, 'loss/train': 1.1826919317245483} 08/31/2021 14:20:57 - INFO - __main__ - Step 138162: {'lr': 7.852890038742955e-06, 'samples': 26527104, 'steps': 138161, 'loss/train': 1.0292695760726929} 08/31/2021 14:20:57 - INFO - __main__ - Step 138163: {'lr': 7.851570468751485e-06, 'samples': 26527296, 'steps': 138162, 'loss/train': 1.9241619110107422} 08/31/2021 14:20:57 - INFO - __main__ - Step 138164: {'lr': 7.85025100786832e-06, 'samples': 26527488, 'steps': 138163, 'loss/train': 1.3305710554122925} 08/31/2021 14:20:58 - INFO - __main__ - Step 138165: {'lr': 7.848931656094072e-06, 'samples': 26527680, 'steps': 138164, 'loss/train': 0.18290603160858154} 08/31/2021 14:20:58 - INFO - __main__ - Step 138166: {'lr': 7.847612413429406e-06, 'samples': 26527872, 'steps': 138165, 'loss/train': 0.7073690891265869} 08/31/2021 14:20:58 - INFO - __main__ - Step 138167: {'lr': 7.846293279874823e-06, 'samples': 26528064, 'steps': 138166, 'loss/train': 1.2366567850112915} 08/31/2021 14:21:00 - INFO - __main__ - Step 138168: {'lr': 7.844974255430987e-06, 'samples': 26528256, 'steps': 138167, 'loss/train': 1.459188461303711} 08/31/2021 14:21:00 - INFO - __main__ - Step 138169: {'lr': 7.843655340098483e-06, 'samples': 26528448, 'steps': 138168, 'loss/train': 1.1592350006103516} 08/31/2021 14:21:01 - INFO - __main__ - Step 138170: {'lr': 7.842336533877865e-06, 'samples': 26528640, 'steps': 138169, 'loss/train': 1.2890149354934692} 08/31/2021 14:21:01 - INFO - __main__ - Step 138171: {'lr': 7.84101783676977e-06, 'samples': 26528832, 'steps': 138170, 'loss/train': 0.9264544248580933} 08/31/2021 14:21:01 - INFO - __main__ - Step 138172: {'lr': 7.839699248774757e-06, 'samples': 26529024, 'steps': 138171, 'loss/train': 1.2293150424957275} 08/31/2021 14:21:03 - INFO - __main__ - Step 138173: {'lr': 7.83838076989346e-06, 'samples': 26529216, 'steps': 138172, 'loss/train': 0.27675187587738037} 08/31/2021 14:21:04 - INFO - __main__ - Step 138174: {'lr': 7.837062400126437e-06, 'samples': 26529408, 'steps': 138173, 'loss/train': 0.4162711501121521} 08/31/2021 14:21:04 - INFO - __main__ - Step 138175: {'lr': 7.835744139474299e-06, 'samples': 26529600, 'steps': 138174, 'loss/train': 0.5704209208488464} 08/31/2021 14:21:04 - INFO - __main__ - Step 138176: {'lr': 7.834425987937655e-06, 'samples': 26529792, 'steps': 138175, 'loss/train': 0.5665481090545654} 08/31/2021 14:21:05 - INFO - __main__ - Step 138177: {'lr': 7.833107945517087e-06, 'samples': 26529984, 'steps': 138176, 'loss/train': 0.9450284242630005} 08/31/2021 14:21:06 - INFO - __main__ - Step 138178: {'lr': 7.83179001221318e-06, 'samples': 26530176, 'steps': 138177, 'loss/train': 1.0520278215408325} 08/31/2021 14:21:06 - INFO - __main__ - Step 138179: {'lr': 7.830472188026516e-06, 'samples': 26530368, 'steps': 138178, 'loss/train': 0.14441658556461334} 08/31/2021 14:21:07 - INFO - __main__ - Step 138180: {'lr': 7.829154472957706e-06, 'samples': 26530560, 'steps': 138179, 'loss/train': 0.7708942890167236} 08/31/2021 14:21:07 - INFO - __main__ - Step 138181: {'lr': 7.827836867007333e-06, 'samples': 26530752, 'steps': 138180, 'loss/train': 0.5252980589866638} 08/31/2021 14:21:08 - INFO - __main__ - Step 138182: {'lr': 7.826519370176006e-06, 'samples': 26530944, 'steps': 138181, 'loss/train': 0.8220847845077515} 08/31/2021 14:21:09 - INFO - __main__ - Step 138183: {'lr': 7.825201982464309e-06, 'samples': 26531136, 'steps': 138182, 'loss/train': 1.271022915840149} 08/31/2021 14:21:10 - INFO - __main__ - Step 138184: {'lr': 7.823884703872852e-06, 'samples': 26531328, 'steps': 138183, 'loss/train': 1.3145191669464111} 08/31/2021 14:21:10 - INFO - __main__ - Step 138185: {'lr': 7.822567534402219e-06, 'samples': 26531520, 'steps': 138184, 'loss/train': 0.6967894434928894} 08/31/2021 14:21:10 - INFO - __main__ - Step 138186: {'lr': 7.821250474052965e-06, 'samples': 26531712, 'steps': 138185, 'loss/train': 1.4310882091522217} 08/31/2021 14:21:11 - INFO - __main__ - Step 138187: {'lr': 7.819933522825757e-06, 'samples': 26531904, 'steps': 138186, 'loss/train': 0.8410872220993042} 08/31/2021 14:21:13 - INFO - __main__ - Step 138188: {'lr': 7.818616680721147e-06, 'samples': 26532096, 'steps': 138187, 'loss/train': 0.38398268818855286} 08/31/2021 14:21:13 - INFO - __main__ - Step 138189: {'lr': 7.817299947739692e-06, 'samples': 26532288, 'steps': 138188, 'loss/train': 0.963235080242157} 08/31/2021 14:21:14 - INFO - __main__ - Step 138190: {'lr': 7.815983323882087e-06, 'samples': 26532480, 'steps': 138189, 'loss/train': 1.0924124717712402} 08/31/2021 14:21:14 - INFO - __main__ - Step 138191: {'lr': 7.81466680914883e-06, 'samples': 26532672, 'steps': 138190, 'loss/train': 1.147268533706665} 08/31/2021 14:21:14 - INFO - __main__ - Step 138192: {'lr': 7.813350403540559e-06, 'samples': 26532864, 'steps': 138191, 'loss/train': 0.6029126048088074} 08/31/2021 14:21:15 - INFO - __main__ - Step 138193: {'lr': 7.812034107057831e-06, 'samples': 26533056, 'steps': 138192, 'loss/train': 0.8049808740615845} 08/31/2021 14:21:16 - INFO - __main__ - Step 138194: {'lr': 7.810717919701282e-06, 'samples': 26533248, 'steps': 138193, 'loss/train': 1.8925690650939941} 08/31/2021 14:21:16 - INFO - __main__ - Step 138195: {'lr': 7.809401841471469e-06, 'samples': 26533440, 'steps': 138194, 'loss/train': 1.3519834280014038} 08/31/2021 14:21:17 - INFO - __main__ - Step 138196: {'lr': 7.808085872369003e-06, 'samples': 26533632, 'steps': 138195, 'loss/train': 0.28218981623649597} 08/31/2021 14:21:17 - INFO - __main__ - Step 138197: {'lr': 7.806770012394493e-06, 'samples': 26533824, 'steps': 138196, 'loss/train': 1.5442439317703247} 08/31/2021 14:21:18 - INFO - __main__ - Step 138198: {'lr': 7.805454261548495e-06, 'samples': 26534016, 'steps': 138197, 'loss/train': 0.29173213243484497} 08/31/2021 14:21:19 - INFO - __main__ - Step 138199: {'lr': 7.804138619831647e-06, 'samples': 26534208, 'steps': 138198, 'loss/train': 0.8166682720184326} 08/31/2021 14:21:20 - INFO - __main__ - Step 138200: {'lr': 7.802823087244504e-06, 'samples': 26534400, 'steps': 138199, 'loss/train': 0.023731723427772522} 08/31/2021 14:21:20 - INFO - __main__ - Step 138201: {'lr': 7.801507663787676e-06, 'samples': 26534592, 'steps': 138200, 'loss/train': 0.17726388573646545} 08/31/2021 14:21:20 - INFO - __main__ - Step 138202: {'lr': 7.800192349461749e-06, 'samples': 26534784, 'steps': 138201, 'loss/train': 0.9192658066749573} 08/31/2021 14:21:21 - INFO - __main__ - Step 138203: {'lr': 7.798877144267302e-06, 'samples': 26534976, 'steps': 138202, 'loss/train': 1.312537670135498} 08/31/2021 14:21:22 - INFO - __main__ - Step 138204: {'lr': 7.797562048204976e-06, 'samples': 26535168, 'steps': 138203, 'loss/train': 0.8727708458900452} 08/31/2021 14:21:23 - INFO - __main__ - Step 138205: {'lr': 7.796247061275324e-06, 'samples': 26535360, 'steps': 138204, 'loss/train': 1.699552059173584} 08/31/2021 14:21:23 - INFO - __main__ - Step 138206: {'lr': 7.79493218347893e-06, 'samples': 26535552, 'steps': 138205, 'loss/train': 0.8342668414115906} 08/31/2021 14:21:23 - INFO - __main__ - Step 138207: {'lr': 7.793617414816406e-06, 'samples': 26535744, 'steps': 138206, 'loss/train': 1.299940586090088} 08/31/2021 14:21:24 - INFO - __main__ - Step 138208: {'lr': 7.792302755288332e-06, 'samples': 26535936, 'steps': 138207, 'loss/train': 0.7104889750480652} 08/31/2021 14:21:25 - INFO - __main__ - Step 138209: {'lr': 7.790988204895321e-06, 'samples': 26536128, 'steps': 138208, 'loss/train': 1.0800623893737793} 08/31/2021 14:21:26 - INFO - __main__ - Step 138210: {'lr': 7.789673763637956e-06, 'samples': 26536320, 'steps': 138209, 'loss/train': 0.6938000321388245} 08/31/2021 14:21:26 - INFO - __main__ - Step 138211: {'lr': 7.788359431516818e-06, 'samples': 26536512, 'steps': 138210, 'loss/train': 0.7193331718444824} 08/31/2021 14:21:26 - INFO - __main__ - Step 138212: {'lr': 7.787045208532517e-06, 'samples': 26536704, 'steps': 138211, 'loss/train': 1.1234403848648071} 08/31/2021 14:21:27 - INFO - __main__ - Step 138213: {'lr': 7.78573109468561e-06, 'samples': 26536896, 'steps': 138212, 'loss/train': 0.9241198897361755} 08/31/2021 14:21:28 - INFO - __main__ - Step 138214: {'lr': 7.784417089976737e-06, 'samples': 26537088, 'steps': 138213, 'loss/train': 1.0837794542312622} 08/31/2021 14:21:29 - INFO - __main__ - Step 138215: {'lr': 7.783103194406477e-06, 'samples': 26537280, 'steps': 138214, 'loss/train': 0.5560059547424316} 08/31/2021 14:21:29 - INFO - __main__ - Step 138216: {'lr': 7.781789407975386e-06, 'samples': 26537472, 'steps': 138215, 'loss/train': 0.02414887771010399} 08/31/2021 14:21:29 - INFO - __main__ - Step 138217: {'lr': 7.780475730684133e-06, 'samples': 26537664, 'steps': 138216, 'loss/train': 0.9506255984306335} 08/31/2021 14:21:30 - INFO - __main__ - Step 138218: {'lr': 7.779162162533215e-06, 'samples': 26537856, 'steps': 138217, 'loss/train': 0.6111323237419128} 08/31/2021 14:21:31 - INFO - __main__ - Step 138219: {'lr': 7.777848703523272e-06, 'samples': 26538048, 'steps': 138218, 'loss/train': 0.942855179309845} 08/31/2021 14:21:31 - INFO - __main__ - Step 138220: {'lr': 7.776535353654912e-06, 'samples': 26538240, 'steps': 138219, 'loss/train': 1.2170482873916626} 08/31/2021 14:21:32 - INFO - __main__ - Step 138221: {'lr': 7.775222112928692e-06, 'samples': 26538432, 'steps': 138220, 'loss/train': 1.1483757495880127} 08/31/2021 14:21:32 - INFO - __main__ - Step 138222: {'lr': 7.773908981345224e-06, 'samples': 26538624, 'steps': 138221, 'loss/train': 0.6829834580421448} 08/31/2021 14:21:33 - INFO - __main__ - Step 138223: {'lr': 7.772595958905088e-06, 'samples': 26538816, 'steps': 138222, 'loss/train': 0.0877617746591568} 08/31/2021 14:21:33 - INFO - __main__ - Step 138224: {'lr': 7.771283045608895e-06, 'samples': 26539008, 'steps': 138223, 'loss/train': 1.5903520584106445} 08/31/2021 14:21:35 - INFO - __main__ - Step 138225: {'lr': 7.769970241457202e-06, 'samples': 26539200, 'steps': 138224, 'loss/train': 1.617939829826355} 08/31/2021 14:21:36 - INFO - __main__ - Step 138226: {'lr': 7.768657546450648e-06, 'samples': 26539392, 'steps': 138225, 'loss/train': 1.0986418724060059} 08/31/2021 14:21:36 - INFO - __main__ - Step 138227: {'lr': 7.767344960589784e-06, 'samples': 26539584, 'steps': 138226, 'loss/train': 1.589863657951355} 08/31/2021 14:21:37 - INFO - __main__ - Step 138228: {'lr': 7.766032483875224e-06, 'samples': 26539776, 'steps': 138227, 'loss/train': 1.5570037364959717} 08/31/2021 14:21:37 - INFO - __main__ - Step 138229: {'lr': 7.76472011630755e-06, 'samples': 26539968, 'steps': 138228, 'loss/train': 1.7420177459716797} 08/31/2021 14:21:37 - INFO - __main__ - Step 138230: {'lr': 7.763407857887344e-06, 'samples': 26540160, 'steps': 138229, 'loss/train': 0.5884180068969727} 08/31/2021 14:21:38 - INFO - __main__ - Step 138231: {'lr': 7.762095708615247e-06, 'samples': 26540352, 'steps': 138230, 'loss/train': 0.7127261757850647} 08/31/2021 14:21:39 - INFO - __main__ - Step 138232: {'lr': 7.760783668491784e-06, 'samples': 26540544, 'steps': 138231, 'loss/train': 1.4284623861312866} 08/31/2021 14:21:40 - INFO - __main__ - Step 138233: {'lr': 7.759471737517565e-06, 'samples': 26540736, 'steps': 138232, 'loss/train': 0.4236446022987366} 08/31/2021 14:21:40 - INFO - __main__ - Step 138234: {'lr': 7.758159915693203e-06, 'samples': 26540928, 'steps': 138233, 'loss/train': 1.4346383810043335} 08/31/2021 14:21:40 - INFO - __main__ - Step 138235: {'lr': 7.756848203019279e-06, 'samples': 26541120, 'steps': 138234, 'loss/train': 1.074527621269226} 08/31/2021 14:21:41 - INFO - __main__ - Step 138236: {'lr': 7.75553659949635e-06, 'samples': 26541312, 'steps': 138235, 'loss/train': 0.8589544296264648} 08/31/2021 14:21:42 - INFO - __main__ - Step 138237: {'lr': 7.754225105125079e-06, 'samples': 26541504, 'steps': 138236, 'loss/train': 1.1080288887023926} 08/31/2021 14:21:43 - INFO - __main__ - Step 138238: {'lr': 7.752913719905996e-06, 'samples': 26541696, 'steps': 138237, 'loss/train': 1.1228066682815552} 08/31/2021 14:21:43 - INFO - __main__ - Step 138239: {'lr': 7.751602443839712e-06, 'samples': 26541888, 'steps': 138238, 'loss/train': 1.0766674280166626} 08/31/2021 14:21:43 - INFO - __main__ - Step 138240: {'lr': 7.750291276926807e-06, 'samples': 26542080, 'steps': 138239, 'loss/train': 1.4728788137435913} 08/31/2021 14:21:44 - INFO - __main__ - Step 138241: {'lr': 7.748980219167895e-06, 'samples': 26542272, 'steps': 138240, 'loss/train': 0.37339481711387634} 08/31/2021 14:21:46 - INFO - __main__ - Step 138242: {'lr': 7.747669270563557e-06, 'samples': 26542464, 'steps': 138241, 'loss/train': 0.7954817414283752} 08/31/2021 14:21:47 - INFO - __main__ - Step 138243: {'lr': 7.746358431114375e-06, 'samples': 26542656, 'steps': 138242, 'loss/train': 0.5824539661407471} 08/31/2021 14:21:47 - INFO - __main__ - Step 138244: {'lr': 7.74504770082099e-06, 'samples': 26542848, 'steps': 138243, 'loss/train': 1.2690244913101196} 08/31/2021 14:21:47 - INFO - __main__ - Step 138245: {'lr': 7.743737079683899e-06, 'samples': 26543040, 'steps': 138244, 'loss/train': 1.162479043006897} 08/31/2021 14:21:48 - INFO - __main__ - Step 138246: {'lr': 7.742426567703741e-06, 'samples': 26543232, 'steps': 138245, 'loss/train': 1.2388370037078857} 08/31/2021 14:21:49 - INFO - __main__ - Step 138247: {'lr': 7.74111616488113e-06, 'samples': 26543424, 'steps': 138246, 'loss/train': 0.9095354080200195} 08/31/2021 14:21:50 - INFO - __main__ - Step 138248: {'lr': 7.739805871216616e-06, 'samples': 26543616, 'steps': 138247, 'loss/train': 0.5450051426887512} 08/31/2021 14:21:50 - INFO - __main__ - Step 138249: {'lr': 7.738495686710812e-06, 'samples': 26543808, 'steps': 138248, 'loss/train': 1.44974946975708} 08/31/2021 14:21:50 - INFO - __main__ - Step 138250: {'lr': 7.7371856113643e-06, 'samples': 26544000, 'steps': 138249, 'loss/train': 1.3713352680206299} 08/31/2021 14:21:51 - INFO - __main__ - Step 138251: {'lr': 7.735875645177693e-06, 'samples': 26544192, 'steps': 138250, 'loss/train': 0.04150353744626045} 08/31/2021 14:21:51 - INFO - __main__ - Step 138252: {'lr': 7.734565788151543e-06, 'samples': 26544384, 'steps': 138251, 'loss/train': 0.8353133201599121} 08/31/2021 14:21:53 - INFO - __main__ - Step 138253: {'lr': 7.733256040286463e-06, 'samples': 26544576, 'steps': 138252, 'loss/train': 0.32088977098464966} 08/31/2021 14:21:53 - INFO - __main__ - Step 138254: {'lr': 7.731946401583034e-06, 'samples': 26544768, 'steps': 138253, 'loss/train': 1.3362714052200317} 08/31/2021 14:21:53 - INFO - __main__ - Step 138255: {'lr': 7.730636872041841e-06, 'samples': 26544960, 'steps': 138254, 'loss/train': 1.3835787773132324} 08/31/2021 14:21:54 - INFO - __main__ - Step 138256: {'lr': 7.72932745166352e-06, 'samples': 26545152, 'steps': 138255, 'loss/train': 0.47338616847991943} 08/31/2021 14:21:54 - INFO - __main__ - Step 138257: {'lr': 7.728018140448629e-06, 'samples': 26545344, 'steps': 138256, 'loss/train': 2.1737470626831055} 08/31/2021 14:21:56 - INFO - __main__ - Step 138258: {'lr': 7.72670893839772e-06, 'samples': 26545536, 'steps': 138257, 'loss/train': 0.8996680378913879} 08/31/2021 14:21:56 - INFO - __main__ - Step 138259: {'lr': 7.725399845511433e-06, 'samples': 26545728, 'steps': 138258, 'loss/train': 1.0806597471237183} 08/31/2021 14:21:57 - INFO - __main__ - Step 138260: {'lr': 7.72409086179035e-06, 'samples': 26545920, 'steps': 138259, 'loss/train': 1.593002200126648} 08/31/2021 14:21:57 - INFO - __main__ - Step 138261: {'lr': 7.722781987235028e-06, 'samples': 26546112, 'steps': 138260, 'loss/train': 0.47925469279289246} 08/31/2021 14:21:57 - INFO - __main__ - Step 138262: {'lr': 7.721473221846104e-06, 'samples': 26546304, 'steps': 138261, 'loss/train': 1.212207555770874} 08/31/2021 14:21:58 - INFO - __main__ - Step 138263: {'lr': 7.720164565624132e-06, 'samples': 26546496, 'steps': 138262, 'loss/train': 1.3353235721588135} 08/31/2021 14:21:59 - INFO - __main__ - Step 138264: {'lr': 7.718856018569725e-06, 'samples': 26546688, 'steps': 138263, 'loss/train': 0.8653287887573242} 08/31/2021 14:22:00 - INFO - __main__ - Step 138265: {'lr': 7.717547580683437e-06, 'samples': 26546880, 'steps': 138264, 'loss/train': 0.3438490331172943} 08/31/2021 14:22:00 - INFO - __main__ - Step 138266: {'lr': 7.716239251965906e-06, 'samples': 26547072, 'steps': 138265, 'loss/train': 1.1076674461364746} 08/31/2021 14:22:00 - INFO - __main__ - Step 138267: {'lr': 7.714931032417716e-06, 'samples': 26547264, 'steps': 138266, 'loss/train': 0.9093836545944214} 08/31/2021 14:22:01 - INFO - __main__ - Step 138268: {'lr': 7.713622922039392e-06, 'samples': 26547456, 'steps': 138267, 'loss/train': 0.930655300617218} 08/31/2021 14:22:02 - INFO - __main__ - Step 138269: {'lr': 7.712314920831603e-06, 'samples': 26547648, 'steps': 138268, 'loss/train': 0.9314626455307007} 08/31/2021 14:22:03 - INFO - __main__ - Step 138270: {'lr': 7.711007028794902e-06, 'samples': 26547840, 'steps': 138269, 'loss/train': 1.3170208930969238} 08/31/2021 14:22:03 - INFO - __main__ - Step 138271: {'lr': 7.70969924592993e-06, 'samples': 26548032, 'steps': 138270, 'loss/train': 0.38978540897369385} 08/31/2021 14:22:03 - INFO - __main__ - Step 138272: {'lr': 7.708391572237183e-06, 'samples': 26548224, 'steps': 138271, 'loss/train': 0.5753726959228516} 08/31/2021 14:22:04 - INFO - __main__ - Step 138273: {'lr': 7.707084007717274e-06, 'samples': 26548416, 'steps': 138272, 'loss/train': 1.0111569166183472} 08/31/2021 14:22:05 - INFO - __main__ - Step 138274: {'lr': 7.705776552370842e-06, 'samples': 26548608, 'steps': 138273, 'loss/train': 0.7047200798988342} 08/31/2021 14:22:06 - INFO - __main__ - Step 138275: {'lr': 7.704469206198439e-06, 'samples': 26548800, 'steps': 138274, 'loss/train': 1.593217134475708} 08/31/2021 14:22:06 - INFO - __main__ - Step 138276: {'lr': 7.703161969200678e-06, 'samples': 26548992, 'steps': 138275, 'loss/train': 1.8015546798706055} 08/31/2021 14:22:06 - INFO - __main__ - Step 138277: {'lr': 7.701854841378114e-06, 'samples': 26549184, 'steps': 138276, 'loss/train': 0.5451380014419556} 08/31/2021 14:22:07 - INFO - __main__ - Step 138278: {'lr': 7.700547822731357e-06, 'samples': 26549376, 'steps': 138277, 'loss/train': 0.9829657673835754} 08/31/2021 14:22:08 - INFO - __main__ - Step 138279: {'lr': 7.699240913260992e-06, 'samples': 26549568, 'steps': 138278, 'loss/train': 1.2961775064468384} 08/31/2021 14:22:09 - INFO - __main__ - Step 138280: {'lr': 7.697934112967625e-06, 'samples': 26549760, 'steps': 138279, 'loss/train': 1.0449830293655396} 08/31/2021 14:22:09 - INFO - __main__ - Step 138281: {'lr': 7.696627421851816e-06, 'samples': 26549952, 'steps': 138280, 'loss/train': 0.7214792370796204} 08/31/2021 14:22:09 - INFO - __main__ - Step 138282: {'lr': 7.695320839914171e-06, 'samples': 26550144, 'steps': 138281, 'loss/train': 0.6437833309173584} 08/31/2021 14:22:10 - INFO - __main__ - Step 138283: {'lr': 7.694014367155277e-06, 'samples': 26550336, 'steps': 138282, 'loss/train': 1.69895339012146} 08/31/2021 14:22:11 - INFO - __main__ - Step 138284: {'lr': 7.692708003575743e-06, 'samples': 26550528, 'steps': 138283, 'loss/train': 0.98427414894104} 08/31/2021 14:22:12 - INFO - __main__ - Step 138285: {'lr': 7.691401749176125e-06, 'samples': 26550720, 'steps': 138284, 'loss/train': 0.6846230626106262} 08/31/2021 14:22:12 - INFO - __main__ - Step 138286: {'lr': 7.690095603957003e-06, 'samples': 26550912, 'steps': 138285, 'loss/train': 0.9991962313652039} 08/31/2021 14:22:12 - INFO - __main__ - Step 138287: {'lr': 7.688789567918991e-06, 'samples': 26551104, 'steps': 138286, 'loss/train': 0.6650117635726929} 08/31/2021 14:22:13 - INFO - __main__ - Step 138288: {'lr': 7.687483641062697e-06, 'samples': 26551296, 'steps': 138287, 'loss/train': 0.7146084308624268} 08/31/2021 14:22:14 - INFO - __main__ - Step 138289: {'lr': 7.68617782338865e-06, 'samples': 26551488, 'steps': 138288, 'loss/train': 1.2595911026000977} 08/31/2021 14:22:15 - INFO - __main__ - Step 138290: {'lr': 7.68487211489749e-06, 'samples': 26551680, 'steps': 138289, 'loss/train': 0.5221811532974243} 08/31/2021 14:22:15 - INFO - __main__ - Step 138291: {'lr': 7.683566515589769e-06, 'samples': 26551872, 'steps': 138290, 'loss/train': 1.123990535736084} 08/31/2021 14:22:15 - INFO - __main__ - Step 138292: {'lr': 7.682261025466124e-06, 'samples': 26552064, 'steps': 138291, 'loss/train': 1.387943148612976} 08/31/2021 14:22:16 - INFO - __main__ - Step 138293: {'lr': 7.680955644527089e-06, 'samples': 26552256, 'steps': 138292, 'loss/train': 1.2801178693771362} 08/31/2021 14:22:16 - INFO - __main__ - Step 138294: {'lr': 7.679650372773268e-06, 'samples': 26552448, 'steps': 138293, 'loss/train': 0.9459583163261414} 08/31/2021 14:22:18 - INFO - __main__ - Step 138295: {'lr': 7.678345210205273e-06, 'samples': 26552640, 'steps': 138294, 'loss/train': 1.9063760042190552} 08/31/2021 14:22:18 - INFO - __main__ - Step 138296: {'lr': 7.677040156823689e-06, 'samples': 26552832, 'steps': 138295, 'loss/train': 1.2963217496871948} 08/31/2021 14:22:19 - INFO - __main__ - Step 138297: {'lr': 7.67573521262907e-06, 'samples': 26553024, 'steps': 138296, 'loss/train': 0.7161543965339661} 08/31/2021 14:22:19 - INFO - __main__ - Step 138298: {'lr': 7.674430377622054e-06, 'samples': 26553216, 'steps': 138297, 'loss/train': 1.0959839820861816} 08/31/2021 14:22:19 - INFO - __main__ - Step 138299: {'lr': 7.67312565180317e-06, 'samples': 26553408, 'steps': 138298, 'loss/train': 0.8564881682395935} 08/31/2021 14:22:21 - INFO - __main__ - Step 138300: {'lr': 7.671821035173054e-06, 'samples': 26553600, 'steps': 138299, 'loss/train': 0.7061563730239868} 08/31/2021 14:22:22 - INFO - __main__ - Step 138301: {'lr': 7.670516527732263e-06, 'samples': 26553792, 'steps': 138300, 'loss/train': 0.9389153718948364} 08/31/2021 14:22:22 - INFO - __main__ - Step 138302: {'lr': 7.669212129481407e-06, 'samples': 26553984, 'steps': 138301, 'loss/train': 1.7200602293014526} 08/31/2021 14:22:23 - INFO - __main__ - Step 138303: {'lr': 7.667907840421068e-06, 'samples': 26554176, 'steps': 138302, 'loss/train': 1.7573785781860352} 08/31/2021 14:22:23 - INFO - __main__ - Step 138304: {'lr': 7.666603660551802e-06, 'samples': 26554368, 'steps': 138303, 'loss/train': 1.6948078870773315} 08/31/2021 14:22:25 - INFO - __main__ - Step 138305: {'lr': 7.665299589874247e-06, 'samples': 26554560, 'steps': 138304, 'loss/train': 1.0680732727050781} 08/31/2021 14:22:25 - INFO - __main__ - Step 138306: {'lr': 7.663995628388986e-06, 'samples': 26554752, 'steps': 138305, 'loss/train': 1.7470362186431885} 08/31/2021 14:22:25 - INFO - __main__ - Step 138307: {'lr': 7.662691776096548e-06, 'samples': 26554944, 'steps': 138306, 'loss/train': 1.007529377937317} 08/31/2021 14:22:26 - INFO - __main__ - Step 138308: {'lr': 7.661388032997596e-06, 'samples': 26555136, 'steps': 138307, 'loss/train': 1.0271183252334595} 08/31/2021 14:22:26 - INFO - __main__ - Step 138309: {'lr': 7.660084399092659e-06, 'samples': 26555328, 'steps': 138308, 'loss/train': 0.9329100251197815} 08/31/2021 14:22:26 - INFO - __main__ - Step 138310: {'lr': 7.658780874382376e-06, 'samples': 26555520, 'steps': 138309, 'loss/train': 0.9843315482139587} 08/31/2021 14:22:28 - INFO - __main__ - Step 138311: {'lr': 7.657477458867302e-06, 'samples': 26555712, 'steps': 138310, 'loss/train': 1.5215234756469727} 08/31/2021 14:22:28 - INFO - __main__ - Step 138312: {'lr': 7.656174152548018e-06, 'samples': 26555904, 'steps': 138311, 'loss/train': 1.0001575946807861} 08/31/2021 14:22:29 - INFO - __main__ - Step 138313: {'lr': 7.654870955425136e-06, 'samples': 26556096, 'steps': 138312, 'loss/train': 0.7801823019981384} 08/31/2021 14:22:29 - INFO - __main__ - Step 138314: {'lr': 7.653567867499212e-06, 'samples': 26556288, 'steps': 138313, 'loss/train': 1.4189386367797852} 08/31/2021 14:22:29 - INFO - __main__ - Step 138315: {'lr': 7.652264888770854e-06, 'samples': 26556480, 'steps': 138314, 'loss/train': 0.2452162504196167} 08/31/2021 14:22:31 - INFO - __main__ - Step 138316: {'lr': 7.650962019240648e-06, 'samples': 26556672, 'steps': 138315, 'loss/train': 0.4462093114852905} 08/31/2021 14:22:31 - INFO - __main__ - Step 138317: {'lr': 7.649659258909175e-06, 'samples': 26556864, 'steps': 138316, 'loss/train': 1.0748488903045654} 08/31/2021 14:22:32 - INFO - __main__ - Step 138318: {'lr': 7.648356607777018e-06, 'samples': 26557056, 'steps': 138317, 'loss/train': 1.0111857652664185} 08/31/2021 14:22:32 - INFO - __main__ - Step 138319: {'lr': 7.647054065844788e-06, 'samples': 26557248, 'steps': 138318, 'loss/train': 1.4944854974746704} 08/31/2021 14:22:32 - INFO - __main__ - Step 138320: {'lr': 7.64575163311304e-06, 'samples': 26557440, 'steps': 138319, 'loss/train': 0.8436987400054932} 08/31/2021 14:22:34 - INFO - __main__ - Step 138321: {'lr': 7.644449309582385e-06, 'samples': 26557632, 'steps': 138320, 'loss/train': 0.9253023266792297} 08/31/2021 14:22:35 - INFO - __main__ - Step 138322: {'lr': 7.643147095253434e-06, 'samples': 26557824, 'steps': 138321, 'loss/train': 1.0221686363220215} 08/31/2021 14:22:35 - INFO - __main__ - Step 138323: {'lr': 7.641844990126711e-06, 'samples': 26558016, 'steps': 138322, 'loss/train': 0.45207679271698} 08/31/2021 14:22:35 - INFO - __main__ - Step 138324: {'lr': 7.640542994202832e-06, 'samples': 26558208, 'steps': 138323, 'loss/train': 1.2844899892807007} 08/31/2021 14:22:36 - INFO - __main__ - Step 138325: {'lr': 7.639241107482376e-06, 'samples': 26558400, 'steps': 138324, 'loss/train': 1.2233338356018066} 08/31/2021 14:22:37 - INFO - __main__ - Step 138326: {'lr': 7.637939329965954e-06, 'samples': 26558592, 'steps': 138325, 'loss/train': 1.1611820459365845} 08/31/2021 14:22:38 - INFO - __main__ - Step 138327: {'lr': 7.636637661654122e-06, 'samples': 26558784, 'steps': 138326, 'loss/train': 0.8598596453666687} 08/31/2021 14:22:38 - INFO - __main__ - Step 138328: {'lr': 7.63533610254749e-06, 'samples': 26558976, 'steps': 138327, 'loss/train': 0.39403918385505676} 08/31/2021 14:22:39 - INFO - __main__ - Step 138329: {'lr': 7.634034652646643e-06, 'samples': 26559168, 'steps': 138328, 'loss/train': 1.4932535886764526} 08/31/2021 14:22:39 - INFO - __main__ - Step 138330: {'lr': 7.632733311952134e-06, 'samples': 26559360, 'steps': 138329, 'loss/train': 1.1533243656158447} 08/31/2021 14:22:39 - INFO - __main__ - Step 138331: {'lr': 7.631432080464602e-06, 'samples': 26559552, 'steps': 138330, 'loss/train': 1.7058892250061035} 08/31/2021 14:22:41 - INFO - __main__ - Step 138332: {'lr': 7.6301309581846e-06, 'samples': 26559744, 'steps': 138331, 'loss/train': 1.2751924991607666} 08/31/2021 14:22:42 - INFO - __main__ - Step 138333: {'lr': 7.628829945112742e-06, 'samples': 26559936, 'steps': 138332, 'loss/train': 0.9955748915672302} 08/31/2021 14:22:42 - INFO - __main__ - Step 138334: {'lr': 7.627529041249554e-06, 'samples': 26560128, 'steps': 138333, 'loss/train': 1.3056468963623047} 08/31/2021 14:22:42 - INFO - __main__ - Step 138335: {'lr': 7.6262282465956735e-06, 'samples': 26560320, 'steps': 138334, 'loss/train': 0.6737084984779358} 08/31/2021 14:22:43 - INFO - __main__ - Step 138336: {'lr': 7.624927561151684e-06, 'samples': 26560512, 'steps': 138335, 'loss/train': 0.03079340048134327} 08/31/2021 14:22:44 - INFO - __main__ - Step 138337: {'lr': 7.623626984918142e-06, 'samples': 26560704, 'steps': 138336, 'loss/train': 0.04231710359454155} 08/31/2021 14:22:45 - INFO - __main__ - Step 138338: {'lr': 7.622326517895683e-06, 'samples': 26560896, 'steps': 138337, 'loss/train': 0.5625092387199402} 08/31/2021 14:22:45 - INFO - __main__ - Step 138339: {'lr': 7.6210261600848375e-06, 'samples': 26561088, 'steps': 138338, 'loss/train': 1.0544860363006592} 08/31/2021 14:22:45 - INFO - __main__ - Step 138340: {'lr': 7.6197259114862415e-06, 'samples': 26561280, 'steps': 138339, 'loss/train': 0.822218120098114} 08/31/2021 14:22:46 - INFO - __main__ - Step 138341: {'lr': 7.618425772100424e-06, 'samples': 26561472, 'steps': 138340, 'loss/train': 1.4434707164764404} 08/31/2021 14:22:47 - INFO - __main__ - Step 138342: {'lr': 7.6171257419280216e-06, 'samples': 26561664, 'steps': 138341, 'loss/train': 1.3747851848602295} 08/31/2021 14:22:48 - INFO - __main__ - Step 138343: {'lr': 7.615825820969618e-06, 'samples': 26561856, 'steps': 138342, 'loss/train': 0.9127642512321472} 08/31/2021 14:22:48 - INFO - __main__ - Step 138344: {'lr': 7.614526009225797e-06, 'samples': 26562048, 'steps': 138343, 'loss/train': 1.0316188335418701} 08/31/2021 14:22:48 - INFO - __main__ - Step 138345: {'lr': 7.613226306697085e-06, 'samples': 26562240, 'steps': 138344, 'loss/train': 1.3107342720031738} 08/31/2021 14:22:49 - INFO - __main__ - Step 138346: {'lr': 7.611926713384121e-06, 'samples': 26562432, 'steps': 138345, 'loss/train': 1.3397843837738037} 08/31/2021 14:22:49 - INFO - __main__ - Step 138347: {'lr': 7.610627229287514e-06, 'samples': 26562624, 'steps': 138346, 'loss/train': 0.3212953507900238} 08/31/2021 14:22:51 - INFO - __main__ - Step 138348: {'lr': 7.609327854407794e-06, 'samples': 26562816, 'steps': 138347, 'loss/train': 0.7505640387535095} 08/31/2021 14:22:51 - INFO - __main__ - Step 138349: {'lr': 7.608028588745569e-06, 'samples': 26563008, 'steps': 138348, 'loss/train': 0.9308844804763794} 08/31/2021 14:22:51 - INFO - __main__ - Step 138350: {'lr': 7.606729432301424e-06, 'samples': 26563200, 'steps': 138349, 'loss/train': 0.8570184111595154} 08/31/2021 14:22:52 - INFO - __main__ - Step 138351: {'lr': 7.6054303850759395e-06, 'samples': 26563392, 'steps': 138350, 'loss/train': 1.0596084594726562} 08/31/2021 14:22:52 - INFO - __main__ - Step 138352: {'lr': 7.604131447069729e-06, 'samples': 26563584, 'steps': 138351, 'loss/train': 0.7501675486564636} 08/31/2021 14:22:54 - INFO - __main__ - Step 138353: {'lr': 7.602832618283345e-06, 'samples': 26563776, 'steps': 138352, 'loss/train': 0.7150360941886902} 08/31/2021 14:22:55 - INFO - __main__ - Step 138354: {'lr': 7.6015338987173724e-06, 'samples': 26563968, 'steps': 138353, 'loss/train': 1.199219822883606} 08/31/2021 14:22:55 - INFO - __main__ - Step 138355: {'lr': 7.600235288372448e-06, 'samples': 26564160, 'steps': 138354, 'loss/train': 1.128949761390686} 08/31/2021 14:22:55 - INFO - __main__ - Step 138356: {'lr': 7.5989367872491e-06, 'samples': 26564352, 'steps': 138355, 'loss/train': 1.0011839866638184} 08/31/2021 14:22:56 - INFO - __main__ - Step 138357: {'lr': 7.5976383953479115e-06, 'samples': 26564544, 'steps': 138356, 'loss/train': 0.7946649789810181} 08/31/2021 14:22:57 - INFO - __main__ - Step 138358: {'lr': 7.596340112669492e-06, 'samples': 26564736, 'steps': 138357, 'loss/train': 0.02783440239727497} 08/31/2021 14:22:58 - INFO - __main__ - Step 138359: {'lr': 7.5950419392144254e-06, 'samples': 26564928, 'steps': 138358, 'loss/train': 0.12574660778045654} 08/31/2021 14:22:58 - INFO - __main__ - Step 138360: {'lr': 7.593743874983295e-06, 'samples': 26565120, 'steps': 138359, 'loss/train': 0.08989432454109192} 08/31/2021 14:22:59 - INFO - __main__ - Step 138361: {'lr': 7.592445919976681e-06, 'samples': 26565312, 'steps': 138360, 'loss/train': 1.0864673852920532} 08/31/2021 14:22:59 - INFO - __main__ - Step 138362: {'lr': 7.59114807419517e-06, 'samples': 26565504, 'steps': 138361, 'loss/train': 0.02222329005599022} 08/31/2021 14:23:01 - INFO - __main__ - Step 138363: {'lr': 7.589850337639343e-06, 'samples': 26565696, 'steps': 138362, 'loss/train': 1.143896222114563} 08/31/2021 14:23:01 - INFO - __main__ - Step 138364: {'lr': 7.588552710309809e-06, 'samples': 26565888, 'steps': 138363, 'loss/train': 0.5761902332305908} 08/31/2021 14:23:02 - INFO - __main__ - Step 138365: {'lr': 7.587255192207126e-06, 'samples': 26566080, 'steps': 138364, 'loss/train': 1.529924988746643} 08/31/2021 14:23:02 - INFO - __main__ - Step 138366: {'lr': 7.585957783331876e-06, 'samples': 26566272, 'steps': 138365, 'loss/train': 1.6003539562225342} 08/31/2021 14:23:02 - INFO - __main__ - Step 138367: {'lr': 7.584660483684669e-06, 'samples': 26566464, 'steps': 138366, 'loss/train': 0.4392293095588684} 08/31/2021 14:23:03 - INFO - __main__ - Step 138368: {'lr': 7.5833632932660325e-06, 'samples': 26566656, 'steps': 138367, 'loss/train': 1.776902437210083} 08/31/2021 14:23:04 - INFO - __main__ - Step 138369: {'lr': 7.582066212076632e-06, 'samples': 26566848, 'steps': 138368, 'loss/train': 0.9010322093963623} 08/31/2021 14:23:05 - INFO - __main__ - Step 138370: {'lr': 7.580769240116997e-06, 'samples': 26567040, 'steps': 138369, 'loss/train': 1.4785171747207642} 08/31/2021 14:23:05 - INFO - __main__ - Step 138371: {'lr': 7.579472377387708e-06, 'samples': 26567232, 'steps': 138370, 'loss/train': 0.7939892411231995} 08/31/2021 14:23:05 - INFO - __main__ - Step 138372: {'lr': 7.578175623889405e-06, 'samples': 26567424, 'steps': 138371, 'loss/train': 0.4512472450733185} 08/31/2021 14:23:06 - INFO - __main__ - Step 138373: {'lr': 7.5768789796226144e-06, 'samples': 26567616, 'steps': 138372, 'loss/train': 0.9518334865570068} 08/31/2021 14:23:07 - INFO - __main__ - Step 138374: {'lr': 7.57558244458792e-06, 'samples': 26567808, 'steps': 138373, 'loss/train': 0.9425264596939087} 08/31/2021 14:23:08 - INFO - __main__ - Step 138375: {'lr': 7.574286018785959e-06, 'samples': 26568000, 'steps': 138374, 'loss/train': 1.4399070739746094} 08/31/2021 14:23:08 - INFO - __main__ - Step 138376: {'lr': 7.572989702217259e-06, 'samples': 26568192, 'steps': 138375, 'loss/train': 1.1623481512069702} 08/31/2021 14:23:08 - INFO - __main__ - Step 138377: {'lr': 7.571693494882459e-06, 'samples': 26568384, 'steps': 138376, 'loss/train': 1.1087356805801392} 08/31/2021 14:23:09 - INFO - __main__ - Step 138378: {'lr': 7.570397396782114e-06, 'samples': 26568576, 'steps': 138377, 'loss/train': 1.5479270219802856} 08/31/2021 14:23:10 - INFO - __main__ - Step 138379: {'lr': 7.569101407916806e-06, 'samples': 26568768, 'steps': 138378, 'loss/train': 0.6883467435836792} 08/31/2021 14:23:11 - INFO - __main__ - Step 138380: {'lr': 7.567805528287092e-06, 'samples': 26568960, 'steps': 138379, 'loss/train': 2.5435070991516113} 08/31/2021 14:23:11 - INFO - __main__ - Step 138381: {'lr': 7.566509757893608e-06, 'samples': 26569152, 'steps': 138380, 'loss/train': 0.620489239692688} 08/31/2021 14:23:11 - INFO - __main__ - Step 138382: {'lr': 7.565214096736883e-06, 'samples': 26569344, 'steps': 138381, 'loss/train': 0.916387677192688} 08/31/2021 14:23:12 - INFO - __main__ - Step 138383: {'lr': 7.563918544817555e-06, 'samples': 26569536, 'steps': 138382, 'loss/train': 1.0912551879882812} 08/31/2021 14:23:13 - INFO - __main__ - Step 138384: {'lr': 7.562623102136179e-06, 'samples': 26569728, 'steps': 138383, 'loss/train': 2.2352190017700195} 08/31/2021 14:23:14 - INFO - __main__ - Step 138385: {'lr': 7.561327768693366e-06, 'samples': 26569920, 'steps': 138384, 'loss/train': 0.6106883883476257} 08/31/2021 14:23:14 - INFO - __main__ - Step 138386: {'lr': 7.5600325444896426e-06, 'samples': 26570112, 'steps': 138385, 'loss/train': 0.2660517990589142} 08/31/2021 14:23:14 - INFO - __main__ - Step 138387: {'lr': 7.558737429525647e-06, 'samples': 26570304, 'steps': 138386, 'loss/train': 0.9898456931114197} 08/31/2021 14:23:15 - INFO - __main__ - Step 138388: {'lr': 7.557442423801935e-06, 'samples': 26570496, 'steps': 138387, 'loss/train': 0.3529900312423706} 08/31/2021 14:23:16 - INFO - __main__ - Step 138389: {'lr': 7.5561475273190905e-06, 'samples': 26570688, 'steps': 138388, 'loss/train': 0.24747979640960693} 08/31/2021 14:23:17 - INFO - __main__ - Step 138390: {'lr': 7.5548527400777224e-06, 'samples': 26570880, 'steps': 138389, 'loss/train': 1.5189639329910278} 08/31/2021 14:23:17 - INFO - __main__ - Step 138391: {'lr': 7.553558062078386e-06, 'samples': 26571072, 'steps': 138390, 'loss/train': 1.293223261833191} 08/31/2021 14:23:18 - INFO - __main__ - Step 138392: {'lr': 7.55226349332172e-06, 'samples': 26571264, 'steps': 138391, 'loss/train': 0.5971612930297852} 08/31/2021 14:23:18 - INFO - __main__ - Step 138393: {'lr': 7.5509690338082244e-06, 'samples': 26571456, 'steps': 138392, 'loss/train': 1.3920031785964966} 08/31/2021 14:23:19 - INFO - __main__ - Step 138394: {'lr': 7.54967468353851e-06, 'samples': 26571648, 'steps': 138393, 'loss/train': 1.072540283203125} 08/31/2021 14:23:20 - INFO - __main__ - Step 138395: {'lr': 7.548380442513186e-06, 'samples': 26571840, 'steps': 138394, 'loss/train': 1.596229076385498} 08/31/2021 14:23:20 - INFO - __main__ - Step 138396: {'lr': 7.5470863107328095e-06, 'samples': 26572032, 'steps': 138395, 'loss/train': 0.7541782259941101} 08/31/2021 14:23:21 - INFO - __main__ - Step 138397: {'lr': 7.5457922881979616e-06, 'samples': 26572224, 'steps': 138396, 'loss/train': 0.9212921261787415} 08/31/2021 14:23:21 - INFO - __main__ - Step 138398: {'lr': 7.544498374909281e-06, 'samples': 26572416, 'steps': 138397, 'loss/train': 0.7435970306396484} 08/31/2021 14:23:21 - INFO - __main__ - Step 138399: {'lr': 7.543204570867268e-06, 'samples': 26572608, 'steps': 138398, 'loss/train': 1.2475701570510864} 08/31/2021 14:23:23 - INFO - __main__ - Step 138400: {'lr': 7.541910876072561e-06, 'samples': 26572800, 'steps': 138399, 'loss/train': 1.2016100883483887} 08/31/2021 14:23:23 - INFO - __main__ - Step 138401: {'lr': 7.540617290525742e-06, 'samples': 26572992, 'steps': 138400, 'loss/train': 0.7766984105110168} 08/31/2021 14:23:24 - INFO - __main__ - Step 138402: {'lr': 7.539323814227339e-06, 'samples': 26573184, 'steps': 138401, 'loss/train': 0.03644673526287079} 08/31/2021 14:23:24 - INFO - __main__ - Step 138403: {'lr': 7.538030447178018e-06, 'samples': 26573376, 'steps': 138402, 'loss/train': 0.12441818416118622} 08/31/2021 14:23:24 - INFO - __main__ - Step 138404: {'lr': 7.536737189378306e-06, 'samples': 26573568, 'steps': 138403, 'loss/train': 1.0972729921340942} 08/31/2021 14:23:26 - INFO - __main__ - Step 138405: {'lr': 7.535444040828815e-06, 'samples': 26573760, 'steps': 138404, 'loss/train': 0.8497645854949951} 08/31/2021 14:23:26 - INFO - __main__ - Step 138406: {'lr': 7.534151001530099e-06, 'samples': 26573952, 'steps': 138405, 'loss/train': 2.6263813972473145} 08/31/2021 14:23:27 - INFO - __main__ - Step 138407: {'lr': 7.53285807148274e-06, 'samples': 26574144, 'steps': 138406, 'loss/train': 1.4081802368164062} 08/31/2021 14:23:27 - INFO - __main__ - Step 138408: {'lr': 7.531565250687322e-06, 'samples': 26574336, 'steps': 138407, 'loss/train': 0.6654391884803772} 08/31/2021 14:23:27 - INFO - __main__ - Step 138409: {'lr': 7.530272539144456e-06, 'samples': 26574528, 'steps': 138408, 'loss/train': 0.6803383231163025} 08/31/2021 14:23:30 - INFO - __main__ - Step 138410: {'lr': 7.528979936854724e-06, 'samples': 26574720, 'steps': 138409, 'loss/train': 1.1462901830673218} 08/31/2021 14:23:30 - INFO - __main__ - Step 138411: {'lr': 7.527687443818681e-06, 'samples': 26574912, 'steps': 138410, 'loss/train': 0.49664369225502014} 08/31/2021 14:23:31 - INFO - __main__ - Step 138412: {'lr': 7.526395060036911e-06, 'samples': 26575104, 'steps': 138411, 'loss/train': 0.11340479552745819} 08/31/2021 14:23:31 - INFO - __main__ - Step 138413: {'lr': 7.525102785509996e-06, 'samples': 26575296, 'steps': 138412, 'loss/train': 1.2708778381347656} 08/31/2021 14:23:31 - INFO - __main__ - Step 138414: {'lr': 7.523810620238547e-06, 'samples': 26575488, 'steps': 138413, 'loss/train': 0.7171234488487244} 08/31/2021 14:23:33 - INFO - __main__ - Step 138415: {'lr': 7.522518564223119e-06, 'samples': 26575680, 'steps': 138414, 'loss/train': 0.6097124814987183} 08/31/2021 14:23:33 - INFO - __main__ - Step 138416: {'lr': 7.521226617464322e-06, 'samples': 26575872, 'steps': 138415, 'loss/train': 1.0754492282867432} 08/31/2021 14:23:34 - INFO - __main__ - Step 138417: {'lr': 7.519934779962684e-06, 'samples': 26576064, 'steps': 138416, 'loss/train': 0.8539055585861206} 08/31/2021 14:23:34 - INFO - __main__ - Step 138418: {'lr': 7.518643051718843e-06, 'samples': 26576256, 'steps': 138417, 'loss/train': 1.086356520652771} 08/31/2021 14:23:34 - INFO - __main__ - Step 138419: {'lr': 7.5173514327333825e-06, 'samples': 26576448, 'steps': 138418, 'loss/train': 1.4729039669036865} 08/31/2021 14:23:36 - INFO - __main__ - Step 138420: {'lr': 7.516059923006829e-06, 'samples': 26576640, 'steps': 138419, 'loss/train': 0.6749529838562012} 08/31/2021 14:23:36 - INFO - __main__ - Step 138421: {'lr': 7.514768522539822e-06, 'samples': 26576832, 'steps': 138420, 'loss/train': 1.0303139686584473} 08/31/2021 14:23:37 - INFO - __main__ - Step 138422: {'lr': 7.5134772313328884e-06, 'samples': 26577024, 'steps': 138421, 'loss/train': 0.5702428817749023} 08/31/2021 14:23:37 - INFO - __main__ - Step 138423: {'lr': 7.512186049386666e-06, 'samples': 26577216, 'steps': 138422, 'loss/train': 1.3283419609069824} 08/31/2021 14:23:37 - INFO - __main__ - Step 138424: {'lr': 7.510894976701682e-06, 'samples': 26577408, 'steps': 138423, 'loss/train': 0.6893497705459595} 08/31/2021 14:23:39 - INFO - __main__ - Step 138425: {'lr': 7.509604013278576e-06, 'samples': 26577600, 'steps': 138424, 'loss/train': 1.4028562307357788} 08/31/2021 14:23:40 - INFO - __main__ - Step 138426: {'lr': 7.5083131591178745e-06, 'samples': 26577792, 'steps': 138425, 'loss/train': 0.3797537386417389} 08/31/2021 14:23:40 - INFO - __main__ - Step 138427: {'lr': 7.5070224142202155e-06, 'samples': 26577984, 'steps': 138426, 'loss/train': 1.3705065250396729} 08/31/2021 14:23:40 - INFO - __main__ - Step 138428: {'lr': 7.505731778586128e-06, 'samples': 26578176, 'steps': 138427, 'loss/train': 1.4089205265045166} 08/31/2021 14:23:41 - INFO - __main__ - Step 138429: {'lr': 7.504441252216221e-06, 'samples': 26578368, 'steps': 138428, 'loss/train': 0.852924108505249} 08/31/2021 14:23:41 - INFO - __main__ - Step 138430: {'lr': 7.50315083511105e-06, 'samples': 26578560, 'steps': 138429, 'loss/train': 0.4322243630886078} 08/31/2021 14:23:43 - INFO - __main__ - Step 138431: {'lr': 7.501860527271254e-06, 'samples': 26578752, 'steps': 138430, 'loss/train': 0.9787453413009644} 08/31/2021 14:23:43 - INFO - __main__ - Step 138432: {'lr': 7.500570328697387e-06, 'samples': 26578944, 'steps': 138431, 'loss/train': 1.438711404800415} 08/31/2021 14:23:43 - INFO - __main__ - Step 138433: {'lr': 7.499280239389977e-06, 'samples': 26579136, 'steps': 138432, 'loss/train': 0.83104407787323} 08/31/2021 14:23:44 - INFO - __main__ - Step 138434: {'lr': 7.49799025934969e-06, 'samples': 26579328, 'steps': 138433, 'loss/train': 1.292137622833252} 08/31/2021 14:23:44 - INFO - __main__ - Step 138435: {'lr': 7.496700388577027e-06, 'samples': 26579520, 'steps': 138434, 'loss/train': 0.9580259323120117} 08/31/2021 14:23:46 - INFO - __main__ - Step 138436: {'lr': 7.495410627072624e-06, 'samples': 26579712, 'steps': 138435, 'loss/train': 0.9995452761650085} 08/31/2021 14:23:46 - INFO - __main__ - Step 138437: {'lr': 7.494120974837065e-06, 'samples': 26579904, 'steps': 138436, 'loss/train': 0.9449968338012695} 08/31/2021 14:23:46 - INFO - __main__ - Step 138438: {'lr': 7.492831431870878e-06, 'samples': 26580096, 'steps': 138437, 'loss/train': 1.2427374124526978} 08/31/2021 14:23:47 - INFO - __main__ - Step 138439: {'lr': 7.4915419981747e-06, 'samples': 26580288, 'steps': 138438, 'loss/train': 0.9850581288337708} 08/31/2021 14:23:47 - INFO - __main__ - Step 138440: {'lr': 7.490252673749087e-06, 'samples': 26580480, 'steps': 138439, 'loss/train': 0.7034879922866821} 08/31/2021 14:23:49 - INFO - __main__ - Step 138441: {'lr': 7.488963458594622e-06, 'samples': 26580672, 'steps': 138440, 'loss/train': 1.1690279245376587} 08/31/2021 14:23:49 - INFO - __main__ - Step 138442: {'lr': 7.487674352711915e-06, 'samples': 26580864, 'steps': 138441, 'loss/train': 0.47284451127052307} 08/31/2021 14:23:49 - INFO - __main__ - Step 138443: {'lr': 7.486385356101494e-06, 'samples': 26581056, 'steps': 138442, 'loss/train': 4.695614814758301} 08/31/2021 14:23:50 - INFO - __main__ - Step 138444: {'lr': 7.485096468763969e-06, 'samples': 26581248, 'steps': 138443, 'loss/train': 1.274085283279419} 08/31/2021 14:23:50 - INFO - __main__ - Step 138445: {'lr': 7.483807690699896e-06, 'samples': 26581440, 'steps': 138444, 'loss/train': 1.3004469871520996} 08/31/2021 14:23:52 - INFO - __main__ - Step 138446: {'lr': 7.482519021909939e-06, 'samples': 26581632, 'steps': 138445, 'loss/train': 0.8124523758888245} 08/31/2021 14:23:52 - INFO - __main__ - Step 138447: {'lr': 7.481230462394573e-06, 'samples': 26581824, 'steps': 138446, 'loss/train': 0.47576019167900085} 08/31/2021 14:23:52 - INFO - __main__ - Step 138448: {'lr': 7.479942012154406e-06, 'samples': 26582016, 'steps': 138447, 'loss/train': 1.7247856855392456} 08/31/2021 14:23:53 - INFO - __main__ - Step 138449: {'lr': 7.478653671190078e-06, 'samples': 26582208, 'steps': 138448, 'loss/train': 1.1072591543197632} 08/31/2021 14:23:53 - INFO - __main__ - Step 138450: {'lr': 7.4773654395020875e-06, 'samples': 26582400, 'steps': 138449, 'loss/train': 0.200394868850708} 08/31/2021 14:23:54 - INFO - __main__ - Step 138451: {'lr': 7.476077317091073e-06, 'samples': 26582592, 'steps': 138450, 'loss/train': 1.1720046997070312} 08/31/2021 14:23:55 - INFO - __main__ - Step 138452: {'lr': 7.474789303957591e-06, 'samples': 26582784, 'steps': 138451, 'loss/train': 0.1777728796005249} 08/31/2021 14:23:56 - INFO - __main__ - Step 138453: {'lr': 7.473501400102223e-06, 'samples': 26582976, 'steps': 138452, 'loss/train': 1.4478689432144165} 08/31/2021 14:23:56 - INFO - __main__ - Step 138454: {'lr': 7.472213605525552e-06, 'samples': 26583168, 'steps': 138453, 'loss/train': 1.097129225730896} 08/31/2021 14:23:56 - INFO - __main__ - Step 138455: {'lr': 7.470925920228161e-06, 'samples': 26583360, 'steps': 138454, 'loss/train': 1.1878453493118286} 08/31/2021 14:23:57 - INFO - __main__ - Step 138456: {'lr': 7.469638344210633e-06, 'samples': 26583552, 'steps': 138455, 'loss/train': 1.5525280237197876} 08/31/2021 14:23:58 - INFO - __main__ - Step 138457: {'lr': 7.468350877473551e-06, 'samples': 26583744, 'steps': 138456, 'loss/train': 0.8465132713317871} 08/31/2021 14:23:59 - INFO - __main__ - Step 138458: {'lr': 7.46706352001747e-06, 'samples': 26583936, 'steps': 138457, 'loss/train': 0.8557682633399963} 08/31/2021 14:23:59 - INFO - __main__ - Step 138459: {'lr': 7.465776271843028e-06, 'samples': 26584128, 'steps': 138458, 'loss/train': 1.3877251148223877} 08/31/2021 14:23:59 - INFO - __main__ - Step 138460: {'lr': 7.464489132950724e-06, 'samples': 26584320, 'steps': 138459, 'loss/train': 0.17450515925884247} 08/31/2021 14:24:00 - INFO - __main__ - Step 138461: {'lr': 7.463202103341171e-06, 'samples': 26584512, 'steps': 138460, 'loss/train': 1.6724449396133423} 08/31/2021 14:24:02 - INFO - __main__ - Step 138462: {'lr': 7.4619151830149774e-06, 'samples': 26584704, 'steps': 138461, 'loss/train': 0.7291633486747742} 08/31/2021 14:24:02 - INFO - __main__ - Step 138463: {'lr': 7.4606283719726995e-06, 'samples': 26584896, 'steps': 138462, 'loss/train': 0.02892475202679634} 08/31/2021 14:24:03 - INFO - __main__ - Step 138464: {'lr': 7.45934167021492e-06, 'samples': 26585088, 'steps': 138463, 'loss/train': 0.40850523114204407} 08/31/2021 14:24:03 - INFO - __main__ - Step 138465: {'lr': 7.4580550777422205e-06, 'samples': 26585280, 'steps': 138464, 'loss/train': 0.3070248067378998} 08/31/2021 14:24:03 - INFO - __main__ - Step 138466: {'lr': 7.456768594555158e-06, 'samples': 26585472, 'steps': 138465, 'loss/train': 1.0653066635131836} 08/31/2021 14:24:05 - INFO - __main__ - Step 138467: {'lr': 7.455482220654342e-06, 'samples': 26585664, 'steps': 138466, 'loss/train': 1.3427473306655884} 08/31/2021 14:24:05 - INFO - __main__ - Step 138468: {'lr': 7.454195956040355e-06, 'samples': 26585856, 'steps': 138467, 'loss/train': 1.4586877822875977} 08/31/2021 14:24:06 - INFO - __main__ - Step 138469: {'lr': 7.452909800713753e-06, 'samples': 26586048, 'steps': 138468, 'loss/train': 0.4619171619415283} 08/31/2021 14:24:06 - INFO - __main__ - Step 138470: {'lr': 7.451623754675147e-06, 'samples': 26586240, 'steps': 138469, 'loss/train': 1.205866813659668} 08/31/2021 14:24:06 - INFO - __main__ - Step 138471: {'lr': 7.45033781792509e-06, 'samples': 26586432, 'steps': 138470, 'loss/train': 0.02668064646422863} 08/31/2021 14:24:08 - INFO - __main__ - Step 138472: {'lr': 7.449051990464139e-06, 'samples': 26586624, 'steps': 138471, 'loss/train': 0.6385082006454468} 08/31/2021 14:24:08 - INFO - __main__ - Step 138473: {'lr': 7.4477662722929604e-06, 'samples': 26586816, 'steps': 138472, 'loss/train': 0.9851797223091125} 08/31/2021 14:24:09 - INFO - __main__ - Step 138474: {'lr': 7.446480663412053e-06, 'samples': 26587008, 'steps': 138473, 'loss/train': 1.1226954460144043} 08/31/2021 14:24:09 - INFO - __main__ - Step 138475: {'lr': 7.4451951638219995e-06, 'samples': 26587200, 'steps': 138474, 'loss/train': 1.1608846187591553} 08/31/2021 14:24:09 - INFO - __main__ - Step 138476: {'lr': 7.443909773523411e-06, 'samples': 26587392, 'steps': 138475, 'loss/train': 1.1411383152008057} 08/31/2021 14:24:11 - INFO - __main__ - Step 138477: {'lr': 7.442624492516842e-06, 'samples': 26587584, 'steps': 138476, 'loss/train': 0.9865260720252991} 08/31/2021 14:24:11 - INFO - __main__ - Step 138478: {'lr': 7.441339320802876e-06, 'samples': 26587776, 'steps': 138477, 'loss/train': 0.7894770503044128} 08/31/2021 14:24:12 - INFO - __main__ - Step 138479: {'lr': 7.440054258382123e-06, 'samples': 26587968, 'steps': 138478, 'loss/train': 1.0238481760025024} 08/31/2021 14:24:12 - INFO - __main__ - Step 138480: {'lr': 7.438769305255111e-06, 'samples': 26588160, 'steps': 138479, 'loss/train': 0.9658457040786743} 08/31/2021 14:24:12 - INFO - __main__ - Step 138481: {'lr': 7.437484461422478e-06, 'samples': 26588352, 'steps': 138480, 'loss/train': 0.931317150592804} 08/31/2021 14:24:14 - INFO - __main__ - Step 138482: {'lr': 7.4361997268847514e-06, 'samples': 26588544, 'steps': 138481, 'loss/train': 0.8610056042671204} 08/31/2021 14:24:14 - INFO - __main__ - Step 138483: {'lr': 7.434915101642542e-06, 'samples': 26588736, 'steps': 138482, 'loss/train': 1.2060956954956055} 08/31/2021 14:24:15 - INFO - __main__ - Step 138484: {'lr': 7.433630585696405e-06, 'samples': 26588928, 'steps': 138483, 'loss/train': 0.9524351358413696} 08/31/2021 14:24:15 - INFO - __main__ - Step 138485: {'lr': 7.432346179046923e-06, 'samples': 26589120, 'steps': 138484, 'loss/train': 1.3303133249282837} 08/31/2021 14:24:15 - INFO - __main__ - Step 138486: {'lr': 7.431061881694734e-06, 'samples': 26589312, 'steps': 138485, 'loss/train': 1.1763734817504883} 08/31/2021 14:24:17 - INFO - __main__ - Step 138487: {'lr': 7.42977769364031e-06, 'samples': 26589504, 'steps': 138486, 'loss/train': 0.49942871928215027} 08/31/2021 14:24:17 - INFO - __main__ - Step 138488: {'lr': 7.4284936148843185e-06, 'samples': 26589696, 'steps': 138487, 'loss/train': 1.0888234376907349} 08/31/2021 14:24:18 - INFO - __main__ - Step 138489: {'lr': 7.427209645427285e-06, 'samples': 26589888, 'steps': 138488, 'loss/train': 1.2295900583267212} 08/31/2021 14:24:18 - INFO - __main__ - Step 138490: {'lr': 7.425925785269822e-06, 'samples': 26590080, 'steps': 138489, 'loss/train': 0.9026725888252258} 08/31/2021 14:24:18 - INFO - __main__ - Step 138491: {'lr': 7.424642034412482e-06, 'samples': 26590272, 'steps': 138490, 'loss/train': 1.1548956632614136} 08/31/2021 14:24:20 - INFO - __main__ - Step 138492: {'lr': 7.42335839285585e-06, 'samples': 26590464, 'steps': 138491, 'loss/train': 1.571838140487671} 08/31/2021 14:24:21 - INFO - __main__ - Step 138493: {'lr': 7.422074860600509e-06, 'samples': 26590656, 'steps': 138492, 'loss/train': 0.8821226954460144} 08/31/2021 14:24:21 - INFO - __main__ - Step 138494: {'lr': 7.4207914376470395e-06, 'samples': 26590848, 'steps': 138493, 'loss/train': 0.09045945852994919} 08/31/2021 14:24:22 - INFO - __main__ - Step 138495: {'lr': 7.4195081239960275e-06, 'samples': 26591040, 'steps': 138494, 'loss/train': 1.004747986793518} 08/31/2021 14:24:22 - INFO - __main__ - Step 138496: {'lr': 7.418224919648026e-06, 'samples': 26591232, 'steps': 138495, 'loss/train': 0.3608276844024658} 08/31/2021 14:24:24 - INFO - __main__ - Step 138497: {'lr': 7.416941824603646e-06, 'samples': 26591424, 'steps': 138496, 'loss/train': 1.0916262865066528} 08/31/2021 14:24:24 - INFO - __main__ - Step 138498: {'lr': 7.4156588388634425e-06, 'samples': 26591616, 'steps': 138497, 'loss/train': 1.6313506364822388} 08/31/2021 14:24:24 - INFO - __main__ - Step 138499: {'lr': 7.414375962427999e-06, 'samples': 26591808, 'steps': 138498, 'loss/train': 1.2693204879760742} 08/31/2021 14:24:25 - INFO - __main__ - Step 138500: {'lr': 7.413093195297926e-06, 'samples': 26592000, 'steps': 138499, 'loss/train': 0.8537892699241638} 08/31/2021 14:24:25 - INFO - __main__ - Step 138501: {'lr': 7.411810537473751e-06, 'samples': 26592192, 'steps': 138500, 'loss/train': 1.4588327407836914} 08/31/2021 14:24:25 - INFO - __main__ - Step 138502: {'lr': 7.410527988956056e-06, 'samples': 26592384, 'steps': 138501, 'loss/train': 0.30420440435409546} 08/31/2021 14:24:27 - INFO - __main__ - Step 138503: {'lr': 7.409245549745425e-06, 'samples': 26592576, 'steps': 138502, 'loss/train': 0.3761359751224518} 08/31/2021 14:24:28 - INFO - __main__ - Step 138504: {'lr': 7.407963219842467e-06, 'samples': 26592768, 'steps': 138503, 'loss/train': 1.5133566856384277} 08/31/2021 14:24:28 - INFO - __main__ - Step 138505: {'lr': 7.406680999247739e-06, 'samples': 26592960, 'steps': 138504, 'loss/train': 1.0213212966918945} 08/31/2021 14:24:28 - INFO - __main__ - Step 138506: {'lr': 7.405398887961795e-06, 'samples': 26593152, 'steps': 138505, 'loss/train': 1.3570023775100708} 08/31/2021 14:24:29 - INFO - __main__ - Step 138507: {'lr': 7.404116885985246e-06, 'samples': 26593344, 'steps': 138506, 'loss/train': 1.4047515392303467} 08/31/2021 14:24:30 - INFO - __main__ - Step 138508: {'lr': 7.402834993318647e-06, 'samples': 26593536, 'steps': 138507, 'loss/train': 1.041190266609192} 08/31/2021 14:24:31 - INFO - __main__ - Step 138509: {'lr': 7.4015532099626085e-06, 'samples': 26593728, 'steps': 138508, 'loss/train': 1.1203131675720215} 08/31/2021 14:24:31 - INFO - __main__ - Step 138510: {'lr': 7.4002715359176855e-06, 'samples': 26593920, 'steps': 138509, 'loss/train': 0.8909827470779419} 08/31/2021 14:24:32 - INFO - __main__ - Step 138511: {'lr': 7.398989971184433e-06, 'samples': 26594112, 'steps': 138510, 'loss/train': 1.330594778060913} 08/31/2021 14:24:32 - INFO - __main__ - Step 138512: {'lr': 7.397708515763463e-06, 'samples': 26594304, 'steps': 138511, 'loss/train': 0.9647003412246704} 08/31/2021 14:24:34 - INFO - __main__ - Step 138513: {'lr': 7.396427169655384e-06, 'samples': 26594496, 'steps': 138512, 'loss/train': 1.3471341133117676} 08/31/2021 14:24:34 - INFO - __main__ - Step 138514: {'lr': 7.395145932860669e-06, 'samples': 26594688, 'steps': 138513, 'loss/train': 5.7054619789123535} 08/31/2021 14:24:35 - INFO - __main__ - Step 138515: {'lr': 7.393864805379985e-06, 'samples': 26594880, 'steps': 138514, 'loss/train': 1.1325323581695557} 08/31/2021 14:24:35 - INFO - __main__ - Step 138516: {'lr': 7.392583787213886e-06, 'samples': 26595072, 'steps': 138515, 'loss/train': 1.306646704673767} 08/31/2021 14:24:35 - INFO - __main__ - Step 138517: {'lr': 7.391302878362927e-06, 'samples': 26595264, 'steps': 138516, 'loss/train': 0.02774740941822529} 08/31/2021 14:24:36 - INFO - __main__ - Step 138518: {'lr': 7.390022078827718e-06, 'samples': 26595456, 'steps': 138517, 'loss/train': 1.4850250482559204} 08/31/2021 14:24:38 - INFO - __main__ - Step 138519: {'lr': 7.388741388608816e-06, 'samples': 26595648, 'steps': 138518, 'loss/train': 2.055772304534912} 08/31/2021 14:24:38 - INFO - __main__ - Step 138520: {'lr': 7.387460807706803e-06, 'samples': 26595840, 'steps': 138519, 'loss/train': 1.4249812364578247} 08/31/2021 14:24:38 - INFO - __main__ - Step 138521: {'lr': 7.386180336122261e-06, 'samples': 26596032, 'steps': 138520, 'loss/train': 1.2786444425582886} 08/31/2021 14:24:39 - INFO - __main__ - Step 138522: {'lr': 7.384899973855746e-06, 'samples': 26596224, 'steps': 138521, 'loss/train': 0.1101175844669342} 08/31/2021 14:24:39 - INFO - __main__ - Step 138523: {'lr': 7.383619720907869e-06, 'samples': 26596416, 'steps': 138522, 'loss/train': 1.1848711967468262} 08/31/2021 14:24:40 - INFO - __main__ - Step 138524: {'lr': 7.382339577279185e-06, 'samples': 26596608, 'steps': 138523, 'loss/train': 1.266825556755066} 08/31/2021 14:24:41 - INFO - __main__ - Step 138525: {'lr': 7.381059542970276e-06, 'samples': 26596800, 'steps': 138524, 'loss/train': 1.066851258277893} 08/31/2021 14:24:41 - INFO - __main__ - Step 138526: {'lr': 7.379779617981752e-06, 'samples': 26596992, 'steps': 138525, 'loss/train': 0.9779762029647827} 08/31/2021 14:24:42 - INFO - __main__ - Step 138527: {'lr': 7.378499802314115e-06, 'samples': 26597184, 'steps': 138526, 'loss/train': 1.142116665840149} 08/31/2021 14:24:42 - INFO - __main__ - Step 138528: {'lr': 7.377220095967974e-06, 'samples': 26597376, 'steps': 138527, 'loss/train': 1.203039288520813} 08/31/2021 14:24:43 - INFO - __main__ - Step 138529: {'lr': 7.3759404989439396e-06, 'samples': 26597568, 'steps': 138528, 'loss/train': 1.001206874847412} 08/31/2021 14:24:44 - INFO - __main__ - Step 138530: {'lr': 7.3746610112425394e-06, 'samples': 26597760, 'steps': 138529, 'loss/train': 0.4091060161590576} 08/31/2021 14:24:44 - INFO - __main__ - Step 138531: {'lr': 7.373381632864384e-06, 'samples': 26597952, 'steps': 138530, 'loss/train': 1.7191227674484253} 08/31/2021 14:24:45 - INFO - __main__ - Step 138532: {'lr': 7.372102363810029e-06, 'samples': 26598144, 'steps': 138531, 'loss/train': 0.47536593675613403} 08/31/2021 14:24:45 - INFO - __main__ - Step 138533: {'lr': 7.370823204080085e-06, 'samples': 26598336, 'steps': 138532, 'loss/train': 0.9865666031837463} 08/31/2021 14:24:46 - INFO - __main__ - Step 138534: {'lr': 7.369544153675078e-06, 'samples': 26598528, 'steps': 138533, 'loss/train': 0.9583120942115784} 08/31/2021 14:24:47 - INFO - __main__ - Step 138535: {'lr': 7.368265212595621e-06, 'samples': 26598720, 'steps': 138534, 'loss/train': 1.3176844120025635} 08/31/2021 14:24:47 - INFO - __main__ - Step 138536: {'lr': 7.366986380842295e-06, 'samples': 26598912, 'steps': 138535, 'loss/train': 0.5729554295539856} 08/31/2021 14:24:48 - INFO - __main__ - Step 138537: {'lr': 7.3657076584156265e-06, 'samples': 26599104, 'steps': 138536, 'loss/train': 1.2510462999343872} 08/31/2021 14:24:48 - INFO - __main__ - Step 138538: {'lr': 7.364429045316256e-06, 'samples': 26599296, 'steps': 138537, 'loss/train': 1.053519368171692} 08/31/2021 14:24:50 - INFO - __main__ - Step 138539: {'lr': 7.363150541544711e-06, 'samples': 26599488, 'steps': 138538, 'loss/train': 1.3037813901901245} 08/31/2021 14:24:50 - INFO - __main__ - Step 138540: {'lr': 7.361872147101628e-06, 'samples': 26599680, 'steps': 138539, 'loss/train': 1.149096131324768} 08/31/2021 14:24:50 - INFO - __main__ - Step 138541: {'lr': 7.360593861987508e-06, 'samples': 26599872, 'steps': 138540, 'loss/train': 0.8412821292877197} 08/31/2021 14:24:51 - INFO - __main__ - Step 138542: {'lr': 7.3593156862029605e-06, 'samples': 26600064, 'steps': 138541, 'loss/train': 1.074936866760254} 08/31/2021 14:24:51 - INFO - __main__ - Step 138543: {'lr': 7.358037619748542e-06, 'samples': 26600256, 'steps': 138542, 'loss/train': 0.7533844113349915} 08/31/2021 14:24:53 - INFO - __main__ - Step 138544: {'lr': 7.35675966262489e-06, 'samples': 26600448, 'steps': 138543, 'loss/train': 0.1510169506072998} 08/31/2021 14:24:53 - INFO - __main__ - Step 138545: {'lr': 7.355481814832504e-06, 'samples': 26600640, 'steps': 138544, 'loss/train': 0.08502095937728882} 08/31/2021 14:24:53 - INFO - __main__ - Step 138546: {'lr': 7.3542040763719955e-06, 'samples': 26600832, 'steps': 138545, 'loss/train': 1.0276857614517212} 08/31/2021 14:24:54 - INFO - __main__ - Step 138547: {'lr': 7.352926447243946e-06, 'samples': 26601024, 'steps': 138546, 'loss/train': 1.8911813497543335} 08/31/2021 14:24:54 - INFO - __main__ - Step 138548: {'lr': 7.3516489274489116e-06, 'samples': 26601216, 'steps': 138547, 'loss/train': 1.2130974531173706} 08/31/2021 14:24:56 - INFO - __main__ - Step 138549: {'lr': 7.350371516987503e-06, 'samples': 26601408, 'steps': 138548, 'loss/train': 0.9593053460121155} 08/31/2021 14:24:56 - INFO - __main__ - Step 138550: {'lr': 7.349094215860275e-06, 'samples': 26601600, 'steps': 138549, 'loss/train': 0.9207853078842163} 08/31/2021 14:24:57 - INFO - __main__ - Step 138551: {'lr': 7.347817024067782e-06, 'samples': 26601792, 'steps': 138550, 'loss/train': 0.25816553831100464} 08/31/2021 14:24:57 - INFO - __main__ - Step 138552: {'lr': 7.346539941610608e-06, 'samples': 26601984, 'steps': 138551, 'loss/train': 0.9202766418457031} 08/31/2021 14:24:57 - INFO - __main__ - Step 138553: {'lr': 7.345262968489391e-06, 'samples': 26602176, 'steps': 138552, 'loss/train': 1.4403915405273438} 08/31/2021 14:24:58 - INFO - __main__ - Step 138554: {'lr': 7.343986104704603e-06, 'samples': 26602368, 'steps': 138553, 'loss/train': 0.9713073372840881} 08/31/2021 14:24:59 - INFO - __main__ - Step 138555: {'lr': 7.34270935025691e-06, 'samples': 26602560, 'steps': 138554, 'loss/train': 1.8102762699127197} 08/31/2021 14:25:00 - INFO - __main__ - Step 138556: {'lr': 7.341432705146811e-06, 'samples': 26602752, 'steps': 138555, 'loss/train': 1.356813669204712} 08/31/2021 14:25:00 - INFO - __main__ - Step 138557: {'lr': 7.340156169374917e-06, 'samples': 26602944, 'steps': 138556, 'loss/train': 1.0441275835037231} 08/31/2021 14:25:00 - INFO - __main__ - Step 138558: {'lr': 7.338879742941839e-06, 'samples': 26603136, 'steps': 138557, 'loss/train': 1.669783353805542} 08/31/2021 14:25:01 - INFO - __main__ - Step 138559: {'lr': 7.337603425848077e-06, 'samples': 26603328, 'steps': 138558, 'loss/train': 1.271207571029663} 08/31/2021 14:25:02 - INFO - __main__ - Step 138560: {'lr': 7.336327218094269e-06, 'samples': 26603520, 'steps': 138559, 'loss/train': 1.5183278322219849} 08/31/2021 14:25:03 - INFO - __main__ - Step 138561: {'lr': 7.3350511196809684e-06, 'samples': 26603712, 'steps': 138560, 'loss/train': 1.1780234575271606} 08/31/2021 14:25:03 - INFO - __main__ - Step 138562: {'lr': 7.333775130608733e-06, 'samples': 26603904, 'steps': 138561, 'loss/train': 0.8052844405174255} 08/31/2021 14:25:04 - INFO - __main__ - Step 138563: {'lr': 7.332499250878172e-06, 'samples': 26604096, 'steps': 138562, 'loss/train': 1.6554397344589233} 08/31/2021 14:25:04 - INFO - __main__ - Step 138564: {'lr': 7.331223480489841e-06, 'samples': 26604288, 'steps': 138563, 'loss/train': 1.1496464014053345} 08/31/2021 14:25:04 - INFO - __main__ - Step 138565: {'lr': 7.329947819444294e-06, 'samples': 26604480, 'steps': 138564, 'loss/train': 0.9487141370773315} 08/31/2021 14:25:06 - INFO - __main__ - Step 138566: {'lr': 7.3286722677421424e-06, 'samples': 26604672, 'steps': 138565, 'loss/train': 0.640570878982544} 08/31/2021 14:25:06 - INFO - __main__ - Step 138567: {'lr': 7.3273968253839695e-06, 'samples': 26604864, 'steps': 138566, 'loss/train': 1.05428147315979} 08/31/2021 14:25:07 - INFO - __main__ - Step 138568: {'lr': 7.32612149237033e-06, 'samples': 26605056, 'steps': 138567, 'loss/train': 1.0101457834243774} 08/31/2021 14:25:07 - INFO - __main__ - Step 138569: {'lr': 7.324846268701752e-06, 'samples': 26605248, 'steps': 138568, 'loss/train': 0.7841916084289551} 08/31/2021 14:25:07 - INFO - __main__ - Step 138570: {'lr': 7.323571154378872e-06, 'samples': 26605440, 'steps': 138569, 'loss/train': 0.8145669102668762} 08/31/2021 14:25:10 - INFO - __main__ - Step 138571: {'lr': 7.322296149402246e-06, 'samples': 26605632, 'steps': 138570, 'loss/train': 0.46587061882019043} 08/31/2021 14:25:11 - INFO - __main__ - Step 138572: {'lr': 7.321021253772458e-06, 'samples': 26605824, 'steps': 138571, 'loss/train': 0.2474861592054367} 08/31/2021 14:25:11 - INFO - __main__ - Step 138573: {'lr': 7.3197464674900624e-06, 'samples': 26606016, 'steps': 138572, 'loss/train': 0.9976544380187988} 08/31/2021 14:25:12 - INFO - __main__ - Step 138574: {'lr': 7.318471790555642e-06, 'samples': 26606208, 'steps': 138573, 'loss/train': 0.17050594091415405} 08/31/2021 14:25:12 - INFO - __main__ - Step 138575: {'lr': 7.317197222969779e-06, 'samples': 26606400, 'steps': 138574, 'loss/train': 0.18437817692756653} 08/31/2021 14:25:12 - INFO - __main__ - Step 138576: {'lr': 7.31592276473303e-06, 'samples': 26606592, 'steps': 138575, 'loss/train': 0.17681902647018433} 08/31/2021 14:25:14 - INFO - __main__ - Step 138577: {'lr': 7.314648415846004e-06, 'samples': 26606784, 'steps': 138576, 'loss/train': 0.8230850696563721} 08/31/2021 14:25:14 - INFO - __main__ - Step 138578: {'lr': 7.3133741763092285e-06, 'samples': 26606976, 'steps': 138577, 'loss/train': 1.034103512763977} 08/31/2021 14:25:15 - INFO - __main__ - Step 138579: {'lr': 7.3121000461233155e-06, 'samples': 26607168, 'steps': 138578, 'loss/train': 0.04129399359226227} 08/31/2021 14:25:15 - INFO - __main__ - Step 138580: {'lr': 7.310826025288847e-06, 'samples': 26607360, 'steps': 138579, 'loss/train': 0.9040611386299133} 08/31/2021 14:25:15 - INFO - __main__ - Step 138581: {'lr': 7.3095521138063505e-06, 'samples': 26607552, 'steps': 138580, 'loss/train': 1.2369412183761597} 08/31/2021 14:25:17 - INFO - __main__ - Step 138582: {'lr': 7.308278311676436e-06, 'samples': 26607744, 'steps': 138581, 'loss/train': 0.8243529796600342} 08/31/2021 14:25:17 - INFO - __main__ - Step 138583: {'lr': 7.30700461889966e-06, 'samples': 26607936, 'steps': 138582, 'loss/train': 0.4880489110946655} 08/31/2021 14:25:18 - INFO - __main__ - Step 138584: {'lr': 7.305731035476604e-06, 'samples': 26608128, 'steps': 138583, 'loss/train': 1.4103398323059082} 08/31/2021 14:25:18 - INFO - __main__ - Step 138585: {'lr': 7.304457561407823e-06, 'samples': 26608320, 'steps': 138584, 'loss/train': 1.3350504636764526} 08/31/2021 14:25:18 - INFO - __main__ - Step 138586: {'lr': 7.30318419669393e-06, 'samples': 26608512, 'steps': 138585, 'loss/train': 1.472000002861023} 08/31/2021 14:25:20 - INFO - __main__ - Step 138587: {'lr': 7.301910941335477e-06, 'samples': 26608704, 'steps': 138586, 'loss/train': 1.664810061454773} 08/31/2021 14:25:20 - INFO - __main__ - Step 138588: {'lr': 7.30063779533302e-06, 'samples': 26608896, 'steps': 138587, 'loss/train': 1.2070643901824951} 08/31/2021 14:25:21 - INFO - __main__ - Step 138589: {'lr': 7.299364758687144e-06, 'samples': 26609088, 'steps': 138588, 'loss/train': 0.7222513556480408} 08/31/2021 14:25:21 - INFO - __main__ - Step 138590: {'lr': 7.298091831398457e-06, 'samples': 26609280, 'steps': 138589, 'loss/train': 1.2085038423538208} 08/31/2021 14:25:21 - INFO - __main__ - Step 138591: {'lr': 7.296819013467515e-06, 'samples': 26609472, 'steps': 138590, 'loss/train': 1.2457712888717651} 08/31/2021 14:25:22 - INFO - __main__ - Step 138592: {'lr': 7.2955463048948735e-06, 'samples': 26609664, 'steps': 138591, 'loss/train': 1.0211762189865112} 08/31/2021 14:25:23 - INFO - __main__ - Step 138593: {'lr': 7.294273705681087e-06, 'samples': 26609856, 'steps': 138592, 'loss/train': 1.3903354406356812} 08/31/2021 14:25:24 - INFO - __main__ - Step 138594: {'lr': 7.293001215826767e-06, 'samples': 26610048, 'steps': 138593, 'loss/train': 0.7903947830200195} 08/31/2021 14:25:24 - INFO - __main__ - Step 138595: {'lr': 7.291728835332468e-06, 'samples': 26610240, 'steps': 138594, 'loss/train': 1.3375827074050903} 08/31/2021 14:25:24 - INFO - __main__ - Step 138596: {'lr': 7.2904565641988e-06, 'samples': 26610432, 'steps': 138595, 'loss/train': 0.778699517250061} 08/31/2021 14:25:25 - INFO - __main__ - Step 138597: {'lr': 7.289184402426263e-06, 'samples': 26610624, 'steps': 138596, 'loss/train': 1.7047271728515625} 08/31/2021 14:25:26 - INFO - __main__ - Step 138598: {'lr': 7.287912350015497e-06, 'samples': 26610816, 'steps': 138597, 'loss/train': 0.06765022873878479} 08/31/2021 14:25:27 - INFO - __main__ - Step 138599: {'lr': 7.286640406967054e-06, 'samples': 26611008, 'steps': 138598, 'loss/train': 1.3300191164016724} 08/31/2021 14:25:27 - INFO - __main__ - Step 138600: {'lr': 7.28536857328152e-06, 'samples': 26611200, 'steps': 138599, 'loss/train': 1.1894928216934204} 08/31/2021 14:25:27 - INFO - __main__ - Step 138601: {'lr': 7.2840968489594205e-06, 'samples': 26611392, 'steps': 138600, 'loss/train': 0.9928744435310364} 08/31/2021 14:25:28 - INFO - __main__ - Step 138602: {'lr': 7.282825234001422e-06, 'samples': 26611584, 'steps': 138601, 'loss/train': 1.0658962726593018} 08/31/2021 14:25:29 - INFO - __main__ - Step 138603: {'lr': 7.281553728407997e-06, 'samples': 26611776, 'steps': 138602, 'loss/train': 0.48887163400650024} 08/31/2021 14:25:30 - INFO - __main__ - Step 138604: {'lr': 7.280282332179755e-06, 'samples': 26611968, 'steps': 138603, 'loss/train': 1.5353955030441284} 08/31/2021 14:25:30 - INFO - __main__ - Step 138605: {'lr': 7.279011045317252e-06, 'samples': 26612160, 'steps': 138604, 'loss/train': 0.40566393733024597} 08/31/2021 14:25:30 - INFO - __main__ - Step 138606: {'lr': 7.277739867821098e-06, 'samples': 26612352, 'steps': 138605, 'loss/train': 1.041555643081665} 08/31/2021 14:25:31 - INFO - __main__ - Step 138607: {'lr': 7.2764687996918765e-06, 'samples': 26612544, 'steps': 138606, 'loss/train': 1.3865807056427002} 08/31/2021 14:25:32 - INFO - __main__ - Step 138608: {'lr': 7.275197840930087e-06, 'samples': 26612736, 'steps': 138607, 'loss/train': 0.591738224029541} 08/31/2021 14:25:33 - INFO - __main__ - Step 138609: {'lr': 7.273926991536367e-06, 'samples': 26612928, 'steps': 138608, 'loss/train': 1.2207921743392944} 08/31/2021 14:25:33 - INFO - __main__ - Step 138610: {'lr': 7.272656251511273e-06, 'samples': 26613120, 'steps': 138609, 'loss/train': 1.3177969455718994} 08/31/2021 14:25:33 - INFO - __main__ - Step 138611: {'lr': 7.271385620855387e-06, 'samples': 26613312, 'steps': 138610, 'loss/train': 1.0161885023117065} 08/31/2021 14:25:34 - INFO - __main__ - Step 138612: {'lr': 7.270115099569291e-06, 'samples': 26613504, 'steps': 138611, 'loss/train': 1.5923385620117188} 08/31/2021 14:25:35 - INFO - __main__ - Step 138613: {'lr': 7.2688446876534865e-06, 'samples': 26613696, 'steps': 138612, 'loss/train': 0.8899710774421692} 08/31/2021 14:25:36 - INFO - __main__ - Step 138614: {'lr': 7.267574385108611e-06, 'samples': 26613888, 'steps': 138613, 'loss/train': 1.070660948753357} 08/31/2021 14:25:36 - INFO - __main__ - Step 138615: {'lr': 7.266304191935219e-06, 'samples': 26614080, 'steps': 138614, 'loss/train': 0.8230403065681458} 08/31/2021 14:25:36 - INFO - __main__ - Step 138616: {'lr': 7.265034108133894e-06, 'samples': 26614272, 'steps': 138615, 'loss/train': 0.5493298172950745} 08/31/2021 14:25:37 - INFO - __main__ - Step 138617: {'lr': 7.263764133705192e-06, 'samples': 26614464, 'steps': 138616, 'loss/train': 0.8671005368232727} 08/31/2021 14:25:38 - INFO - __main__ - Step 138618: {'lr': 7.262494268649694e-06, 'samples': 26614656, 'steps': 138617, 'loss/train': 0.3159775733947754} 08/31/2021 14:25:39 - INFO - __main__ - Step 138619: {'lr': 7.261224512967956e-06, 'samples': 26614848, 'steps': 138618, 'loss/train': 1.0286115407943726} 08/31/2021 14:25:39 - INFO - __main__ - Step 138620: {'lr': 7.2599548666605895e-06, 'samples': 26615040, 'steps': 138619, 'loss/train': 0.8785257339477539} 08/31/2021 14:25:39 - INFO - __main__ - Step 138621: {'lr': 7.258685329728121e-06, 'samples': 26615232, 'steps': 138620, 'loss/train': 0.9507942199707031} 08/31/2021 14:25:40 - INFO - __main__ - Step 138622: {'lr': 7.2574159021711325e-06, 'samples': 26615424, 'steps': 138621, 'loss/train': 1.0064349174499512} 08/31/2021 14:25:40 - INFO - __main__ - Step 138623: {'lr': 7.256146583990264e-06, 'samples': 26615616, 'steps': 138622, 'loss/train': 1.2693263292312622} 08/31/2021 14:25:42 - INFO - __main__ - Step 138624: {'lr': 7.254877375185987e-06, 'samples': 26615808, 'steps': 138623, 'loss/train': 1.0459569692611694} 08/31/2021 14:25:42 - INFO - __main__ - Step 138625: {'lr': 7.253608275758911e-06, 'samples': 26616000, 'steps': 138624, 'loss/train': 0.3873874545097351} 08/31/2021 14:25:42 - INFO - __main__ - Step 138626: {'lr': 7.252339285709619e-06, 'samples': 26616192, 'steps': 138625, 'loss/train': 0.9653173089027405} 08/31/2021 14:25:43 - INFO - __main__ - Step 138627: {'lr': 7.251070405038696e-06, 'samples': 26616384, 'steps': 138626, 'loss/train': 1.179315209388733} 08/31/2021 14:25:43 - INFO - __main__ - Step 138628: {'lr': 7.249801633746666e-06, 'samples': 26616576, 'steps': 138627, 'loss/train': 0.11322592198848724} 08/31/2021 14:25:45 - INFO - __main__ - Step 138629: {'lr': 7.248532971834143e-06, 'samples': 26616768, 'steps': 138628, 'loss/train': 1.0424048900604248} 08/31/2021 14:25:46 - INFO - __main__ - Step 138630: {'lr': 7.24726441930168e-06, 'samples': 26616960, 'steps': 138629, 'loss/train': 1.037876009941101} 08/31/2021 14:25:46 - INFO - __main__ - Step 138631: {'lr': 7.245995976149861e-06, 'samples': 26617152, 'steps': 138630, 'loss/train': 1.16563880443573} 08/31/2021 14:25:46 - INFO - __main__ - Step 138632: {'lr': 7.244727642379267e-06, 'samples': 26617344, 'steps': 138631, 'loss/train': 1.3908089399337769} 08/31/2021 14:25:47 - INFO - __main__ - Step 138633: {'lr': 7.243459417990428e-06, 'samples': 26617536, 'steps': 138632, 'loss/train': 0.3287881314754486} 08/31/2021 14:25:49 - INFO - __main__ - Step 138634: {'lr': 7.24219130298398e-06, 'samples': 26617728, 'steps': 138633, 'loss/train': 0.8715540170669556} 08/31/2021 14:25:49 - INFO - __main__ - Step 138635: {'lr': 7.240923297360397e-06, 'samples': 26617920, 'steps': 138634, 'loss/train': 0.9210987687110901} 08/31/2021 14:25:49 - INFO - __main__ - Step 138636: {'lr': 7.239655401120343e-06, 'samples': 26618112, 'steps': 138635, 'loss/train': 1.3549357652664185} 08/31/2021 14:25:50 - INFO - __main__ - Step 138637: {'lr': 7.2383876142643465e-06, 'samples': 26618304, 'steps': 138636, 'loss/train': 0.46798837184906006} 08/31/2021 14:25:50 - INFO - __main__ - Step 138638: {'lr': 7.237119936792991e-06, 'samples': 26618496, 'steps': 138637, 'loss/train': 0.7260758280754089} 08/31/2021 14:25:52 - INFO - __main__ - Step 138639: {'lr': 7.23585236870683e-06, 'samples': 26618688, 'steps': 138638, 'loss/train': 1.188206672668457} 08/31/2021 14:25:52 - INFO - __main__ - Step 138640: {'lr': 7.2345849100064475e-06, 'samples': 26618880, 'steps': 138639, 'loss/train': 1.0839065313339233} 08/31/2021 14:25:52 - INFO - __main__ - Step 138641: {'lr': 7.233317560692427e-06, 'samples': 26619072, 'steps': 138640, 'loss/train': 1.0380377769470215} 08/31/2021 14:25:53 - INFO - __main__ - Step 138642: {'lr': 7.232050320765321e-06, 'samples': 26619264, 'steps': 138641, 'loss/train': 1.2130117416381836} 08/31/2021 14:25:53 - INFO - __main__ - Step 138643: {'lr': 7.230783190225687e-06, 'samples': 26619456, 'steps': 138642, 'loss/train': 1.6212012767791748} 08/31/2021 14:25:54 - INFO - __main__ - Step 138644: {'lr': 7.229516169074135e-06, 'samples': 26619648, 'steps': 138643, 'loss/train': 1.3701426982879639} 08/31/2021 14:25:55 - INFO - __main__ - Step 138645: {'lr': 7.22824925731122e-06, 'samples': 26619840, 'steps': 138644, 'loss/train': 1.2711158990859985} 08/31/2021 14:25:55 - INFO - __main__ - Step 138646: {'lr': 7.2269824549374974e-06, 'samples': 26620032, 'steps': 138645, 'loss/train': 0.5282887816429138} 08/31/2021 14:25:56 - INFO - __main__ - Step 138647: {'lr': 7.225715761953605e-06, 'samples': 26620224, 'steps': 138646, 'loss/train': 1.0087205171585083} 08/31/2021 14:25:56 - INFO - __main__ - Step 138648: {'lr': 7.224449178360015e-06, 'samples': 26620416, 'steps': 138647, 'loss/train': 1.4960755109786987} 08/31/2021 14:25:56 - INFO - __main__ - Step 138649: {'lr': 7.2231827041573386e-06, 'samples': 26620608, 'steps': 138648, 'loss/train': 1.3512468338012695} 08/31/2021 14:25:58 - INFO - __main__ - Step 138650: {'lr': 7.221916339346157e-06, 'samples': 26620800, 'steps': 138649, 'loss/train': 1.2414920330047607} 08/31/2021 14:25:58 - INFO - __main__ - Step 138651: {'lr': 7.220650083927027e-06, 'samples': 26620992, 'steps': 138650, 'loss/train': 0.747437059879303} 08/31/2021 14:25:59 - INFO - __main__ - Step 138652: {'lr': 7.219383937900503e-06, 'samples': 26621184, 'steps': 138651, 'loss/train': 1.1064186096191406} 08/31/2021 14:25:59 - INFO - __main__ - Step 138653: {'lr': 7.218117901267224e-06, 'samples': 26621376, 'steps': 138652, 'loss/train': 0.43495652079582214} 08/31/2021 14:25:59 - INFO - __main__ - Step 138654: {'lr': 7.216851974027689e-06, 'samples': 26621568, 'steps': 138653, 'loss/train': 0.9526407718658447} 08/31/2021 14:26:01 - INFO - __main__ - Step 138655: {'lr': 7.215586156182508e-06, 'samples': 26621760, 'steps': 138654, 'loss/train': 1.1502195596694946} 08/31/2021 14:26:01 - INFO - __main__ - Step 138656: {'lr': 7.214320447732209e-06, 'samples': 26621952, 'steps': 138655, 'loss/train': 0.9939374327659607} 08/31/2021 14:26:02 - INFO - __main__ - Step 138657: {'lr': 7.213054848677403e-06, 'samples': 26622144, 'steps': 138656, 'loss/train': 0.7857944965362549} 08/31/2021 14:26:02 - INFO - __main__ - Step 138658: {'lr': 7.211789359018672e-06, 'samples': 26622336, 'steps': 138657, 'loss/train': 0.518613874912262} 08/31/2021 14:26:02 - INFO - __main__ - Step 138659: {'lr': 7.210523978756545e-06, 'samples': 26622528, 'steps': 138658, 'loss/train': 0.7676466703414917} 08/31/2021 14:26:04 - INFO - __main__ - Step 138660: {'lr': 7.209258707891603e-06, 'samples': 26622720, 'steps': 138659, 'loss/train': 1.1232010126113892} 08/31/2021 14:26:05 - INFO - __main__ - Step 138661: {'lr': 7.207993546424457e-06, 'samples': 26622912, 'steps': 138660, 'loss/train': 1.0762100219726562} 08/31/2021 14:26:05 - INFO - __main__ - Step 138662: {'lr': 7.2067284943556075e-06, 'samples': 26623104, 'steps': 138661, 'loss/train': 1.4946383237838745} 08/31/2021 14:26:05 - INFO - __main__ - Step 138663: {'lr': 7.205463551685665e-06, 'samples': 26623296, 'steps': 138662, 'loss/train': 0.6861204504966736} 08/31/2021 14:26:06 - INFO - __main__ - Step 138664: {'lr': 7.2041987184152115e-06, 'samples': 26623488, 'steps': 138663, 'loss/train': 0.9323287606239319} 08/31/2021 14:26:07 - INFO - __main__ - Step 138665: {'lr': 7.202933994544775e-06, 'samples': 26623680, 'steps': 138664, 'loss/train': 0.2810751795768738} 08/31/2021 14:26:08 - INFO - __main__ - Step 138666: {'lr': 7.201669380074965e-06, 'samples': 26623872, 'steps': 138665, 'loss/train': 1.2386940717697144} 08/31/2021 14:26:08 - INFO - __main__ - Step 138667: {'lr': 7.200404875006311e-06, 'samples': 26624064, 'steps': 138666, 'loss/train': 1.7312978506088257} 08/31/2021 14:26:08 - INFO - __main__ - Step 138668: {'lr': 7.199140479339422e-06, 'samples': 26624256, 'steps': 138667, 'loss/train': 0.9498113989830017} 08/31/2021 14:26:09 - INFO - __main__ - Step 138669: {'lr': 7.197876193074882e-06, 'samples': 26624448, 'steps': 138668, 'loss/train': 0.03713064640760422} 08/31/2021 14:26:10 - INFO - __main__ - Step 138670: {'lr': 7.196612016213189e-06, 'samples': 26624640, 'steps': 138669, 'loss/train': 0.8961405754089355} 08/31/2021 14:26:11 - INFO - __main__ - Step 138671: {'lr': 7.195347948754982e-06, 'samples': 26624832, 'steps': 138670, 'loss/train': 0.3593071401119232} 08/31/2021 14:26:11 - INFO - __main__ - Step 138672: {'lr': 7.194083990700789e-06, 'samples': 26625024, 'steps': 138671, 'loss/train': 1.445913553237915} 08/31/2021 14:26:12 - INFO - __main__ - Step 138673: {'lr': 7.1928201420512205e-06, 'samples': 26625216, 'steps': 138672, 'loss/train': 0.4023989140987396} 08/31/2021 14:26:12 - INFO - __main__ - Step 138674: {'lr': 7.191556402806832e-06, 'samples': 26625408, 'steps': 138673, 'loss/train': 0.8524051904678345} 08/31/2021 14:26:12 - INFO - __main__ - Step 138675: {'lr': 7.1902927729681485e-06, 'samples': 26625600, 'steps': 138674, 'loss/train': 1.296121597290039} 08/31/2021 14:26:14 - INFO - __main__ - Step 138676: {'lr': 7.189029252535784e-06, 'samples': 26625792, 'steps': 138675, 'loss/train': 0.33264806866645813} 08/31/2021 14:26:14 - INFO - __main__ - Step 138677: {'lr': 7.187765841510291e-06, 'samples': 26625984, 'steps': 138676, 'loss/train': 1.3888888359069824} 08/31/2021 14:26:15 - INFO - __main__ - Step 138678: {'lr': 7.186502539892226e-06, 'samples': 26626176, 'steps': 138677, 'loss/train': 1.070569634437561} 08/31/2021 14:26:15 - INFO - __main__ - Step 138679: {'lr': 7.185239347682199e-06, 'samples': 26626368, 'steps': 138678, 'loss/train': 0.9740250706672668} 08/31/2021 14:26:15 - INFO - __main__ - Step 138680: {'lr': 7.183976264880737e-06, 'samples': 26626560, 'steps': 138679, 'loss/train': 0.5177558660507202} 08/31/2021 14:26:17 - INFO - __main__ - Step 138681: {'lr': 7.182713291488452e-06, 'samples': 26626752, 'steps': 138680, 'loss/train': 0.7699563503265381} 08/31/2021 14:26:18 - INFO - __main__ - Step 138682: {'lr': 7.18145042750587e-06, 'samples': 26626944, 'steps': 138681, 'loss/train': 1.1147518157958984} 08/31/2021 14:26:18 - INFO - __main__ - Step 138683: {'lr': 7.180187672933603e-06, 'samples': 26627136, 'steps': 138682, 'loss/train': 1.0557138919830322} 08/31/2021 14:26:18 - INFO - __main__ - Step 138684: {'lr': 7.178925027772177e-06, 'samples': 26627328, 'steps': 138683, 'loss/train': 0.8228104710578918} 08/31/2021 14:26:19 - INFO - __main__ - Step 138685: {'lr': 7.177662492022174e-06, 'samples': 26627520, 'steps': 138684, 'loss/train': 1.0250260829925537} 08/31/2021 14:26:20 - INFO - __main__ - Step 138686: {'lr': 7.17640006568418e-06, 'samples': 26627712, 'steps': 138685, 'loss/train': 1.4639447927474976} 08/31/2021 14:26:21 - INFO - __main__ - Step 138687: {'lr': 7.175137748758748e-06, 'samples': 26627904, 'steps': 138686, 'loss/train': 1.2323683500289917} 08/31/2021 14:26:21 - INFO - __main__ - Step 138688: {'lr': 7.1738755412464884e-06, 'samples': 26628096, 'steps': 138687, 'loss/train': 0.9126355051994324} 08/31/2021 14:26:22 - INFO - __main__ - Step 138689: {'lr': 7.172613443147902e-06, 'samples': 26628288, 'steps': 138688, 'loss/train': 0.7200647592544556} 08/31/2021 14:26:22 - INFO - __main__ - Step 138690: {'lr': 7.171351454463598e-06, 'samples': 26628480, 'steps': 138689, 'loss/train': 0.3218643367290497} 08/31/2021 14:26:23 - INFO - __main__ - Step 138691: {'lr': 7.170089575194133e-06, 'samples': 26628672, 'steps': 138690, 'loss/train': 1.210363507270813} 08/31/2021 14:26:24 - INFO - __main__ - Step 138692: {'lr': 7.1688278053400615e-06, 'samples': 26628864, 'steps': 138691, 'loss/train': 0.4941786229610443} 08/31/2021 14:26:24 - INFO - __main__ - Step 138693: {'lr': 7.167566144901993e-06, 'samples': 26629056, 'steps': 138692, 'loss/train': 1.3038171529769897} 08/31/2021 14:26:24 - INFO - __main__ - Step 138694: {'lr': 7.166304593880457e-06, 'samples': 26629248, 'steps': 138693, 'loss/train': 1.4181972742080688} 08/31/2021 14:26:25 - INFO - __main__ - Step 138695: {'lr': 7.165043152276035e-06, 'samples': 26629440, 'steps': 138694, 'loss/train': 1.4056694507598877} 08/31/2021 14:26:26 - INFO - __main__ - Step 138696: {'lr': 7.16378182008931e-06, 'samples': 26629632, 'steps': 138695, 'loss/train': 0.7893381714820862} 08/31/2021 14:26:27 - INFO - __main__ - Step 138697: {'lr': 7.16252059732081e-06, 'samples': 26629824, 'steps': 138696, 'loss/train': 1.3306777477264404} 08/31/2021 14:26:27 - INFO - __main__ - Step 138698: {'lr': 7.161259483971172e-06, 'samples': 26630016, 'steps': 138697, 'loss/train': 0.9086007475852966} 08/31/2021 14:26:27 - INFO - __main__ - Step 138699: {'lr': 7.159998480040897e-06, 'samples': 26630208, 'steps': 138698, 'loss/train': 0.8970933556556702} 08/31/2021 14:26:28 - INFO - __main__ - Step 138700: {'lr': 7.158737585530567e-06, 'samples': 26630400, 'steps': 138699, 'loss/train': 1.6695635318756104} 08/31/2021 14:26:29 - INFO - __main__ - Step 138701: {'lr': 7.157476800440821e-06, 'samples': 26630592, 'steps': 138700, 'loss/train': 0.6446242332458496} 08/31/2021 14:26:30 - INFO - __main__ - Step 138702: {'lr': 7.1562161247721305e-06, 'samples': 26630784, 'steps': 138701, 'loss/train': 0.628540575504303} 08/31/2021 14:26:30 - INFO - __main__ - Step 138703: {'lr': 7.154955558525078e-06, 'samples': 26630976, 'steps': 138702, 'loss/train': 1.4797852039337158} 08/31/2021 14:26:31 - INFO - __main__ - Step 138704: {'lr': 7.153695101700275e-06, 'samples': 26631168, 'steps': 138703, 'loss/train': 0.6767775416374207} 08/31/2021 14:26:31 - INFO - __main__ - Step 138705: {'lr': 7.152434754298276e-06, 'samples': 26631360, 'steps': 138704, 'loss/train': 0.7496992945671082} 08/31/2021 14:26:31 - INFO - __main__ - Step 138706: {'lr': 7.151174516319636e-06, 'samples': 26631552, 'steps': 138705, 'loss/train': 1.0601956844329834} 08/31/2021 14:26:33 - INFO - __main__ - Step 138707: {'lr': 7.149914387764938e-06, 'samples': 26631744, 'steps': 138706, 'loss/train': 0.04198792576789856} 08/31/2021 14:26:33 - INFO - __main__ - Step 138708: {'lr': 7.148654368634738e-06, 'samples': 26631936, 'steps': 138707, 'loss/train': 0.9394069910049438} 08/31/2021 14:26:34 - INFO - __main__ - Step 138709: {'lr': 7.14739445892959e-06, 'samples': 26632128, 'steps': 138708, 'loss/train': 0.928741991519928} 08/31/2021 14:26:34 - INFO - __main__ - Step 138710: {'lr': 7.146134658650106e-06, 'samples': 26632320, 'steps': 138709, 'loss/train': 1.994808554649353} 08/31/2021 14:26:34 - INFO - __main__ - Step 138711: {'lr': 7.14487496779681e-06, 'samples': 26632512, 'steps': 138710, 'loss/train': 1.109649896621704} 08/31/2021 14:26:36 - INFO - __main__ - Step 138712: {'lr': 7.143615386370289e-06, 'samples': 26632704, 'steps': 138711, 'loss/train': 1.5756069421768188} 08/31/2021 14:26:36 - INFO - __main__ - Step 138713: {'lr': 7.142355914371096e-06, 'samples': 26632896, 'steps': 138712, 'loss/train': 2.415405750274658} 08/31/2021 14:26:37 - INFO - __main__ - Step 138714: {'lr': 7.141096551799814e-06, 'samples': 26633088, 'steps': 138713, 'loss/train': 1.0645122528076172} 08/31/2021 14:26:37 - INFO - __main__ - Step 138715: {'lr': 7.139837298657054e-06, 'samples': 26633280, 'steps': 138714, 'loss/train': 0.6805818676948547} 08/31/2021 14:26:37 - INFO - __main__ - Step 138716: {'lr': 7.138578154943287e-06, 'samples': 26633472, 'steps': 138715, 'loss/train': 0.6470072865486145} 08/31/2021 14:26:39 - INFO - __main__ - Step 138717: {'lr': 7.137319120659125e-06, 'samples': 26633664, 'steps': 138716, 'loss/train': 0.5771964192390442} 08/31/2021 14:26:39 - INFO - __main__ - Step 138718: {'lr': 7.13606019580515e-06, 'samples': 26633856, 'steps': 138717, 'loss/train': 0.6632697582244873} 08/31/2021 14:26:40 - INFO - __main__ - Step 138719: {'lr': 7.134801380381916e-06, 'samples': 26634048, 'steps': 138718, 'loss/train': 1.17970871925354} 08/31/2021 14:26:40 - INFO - __main__ - Step 138720: {'lr': 7.133542674390009e-06, 'samples': 26634240, 'steps': 138719, 'loss/train': 1.024993658065796} 08/31/2021 14:26:40 - INFO - __main__ - Step 138721: {'lr': 7.132284077829953e-06, 'samples': 26634432, 'steps': 138720, 'loss/train': 0.794422447681427} 08/31/2021 14:26:42 - INFO - __main__ - Step 138722: {'lr': 7.131025590702361e-06, 'samples': 26634624, 'steps': 138721, 'loss/train': 1.8346147537231445} 08/31/2021 14:26:43 - INFO - __main__ - Step 138723: {'lr': 7.129767213007787e-06, 'samples': 26634816, 'steps': 138722, 'loss/train': 1.147168755531311} 08/31/2021 14:26:43 - INFO - __main__ - Step 138724: {'lr': 7.1285089447467865e-06, 'samples': 26635008, 'steps': 138723, 'loss/train': 1.2147356271743774} 08/31/2021 14:26:43 - INFO - __main__ - Step 138725: {'lr': 7.127250785919914e-06, 'samples': 26635200, 'steps': 138724, 'loss/train': 1.1906893253326416} 08/31/2021 14:26:44 - INFO - __main__ - Step 138726: {'lr': 7.125992736527753e-06, 'samples': 26635392, 'steps': 138725, 'loss/train': 0.013847554102540016} 08/31/2021 14:26:44 - INFO - __main__ - Step 138727: {'lr': 7.124734796570887e-06, 'samples': 26635584, 'steps': 138726, 'loss/train': 2.7001402378082275} 08/31/2021 14:26:46 - INFO - __main__ - Step 138728: {'lr': 7.123476966049896e-06, 'samples': 26635776, 'steps': 138727, 'loss/train': 0.19459815323352814} 08/31/2021 14:26:46 - INFO - __main__ - Step 138729: {'lr': 7.122219244965311e-06, 'samples': 26635968, 'steps': 138728, 'loss/train': 1.192577838897705} 08/31/2021 14:26:47 - INFO - __main__ - Step 138730: {'lr': 7.120961633317685e-06, 'samples': 26636160, 'steps': 138729, 'loss/train': 0.24315081536769867} 08/31/2021 14:26:47 - INFO - __main__ - Step 138731: {'lr': 7.119704131107602e-06, 'samples': 26636352, 'steps': 138730, 'loss/train': 0.9991362690925598} 08/31/2021 14:26:47 - INFO - __main__ - Step 138732: {'lr': 7.118446738335616e-06, 'samples': 26636544, 'steps': 138731, 'loss/train': 1.1463816165924072} 08/31/2021 14:26:49 - INFO - __main__ - Step 138733: {'lr': 7.117189455002338e-06, 'samples': 26636736, 'steps': 138732, 'loss/train': 0.9768257141113281} 08/31/2021 14:26:49 - INFO - __main__ - Step 138734: {'lr': 7.115932281108295e-06, 'samples': 26636928, 'steps': 138733, 'loss/train': 0.9992070198059082} 08/31/2021 14:26:49 - INFO - __main__ - Step 138735: {'lr': 7.114675216654071e-06, 'samples': 26637120, 'steps': 138734, 'loss/train': 1.0745254755020142} 08/31/2021 14:26:50 - INFO - __main__ - Step 138736: {'lr': 7.11341826164022e-06, 'samples': 26637312, 'steps': 138735, 'loss/train': 1.5537623167037964} 08/31/2021 14:26:50 - INFO - __main__ - Step 138737: {'lr': 7.112161416067326e-06, 'samples': 26637504, 'steps': 138736, 'loss/train': 1.45836341381073} 08/31/2021 14:26:51 - INFO - __main__ - Step 138738: {'lr': 7.110904679935942e-06, 'samples': 26637696, 'steps': 138737, 'loss/train': 1.6953339576721191} 08/31/2021 14:26:53 - INFO - __main__ - Step 138739: {'lr': 7.109648053246626e-06, 'samples': 26637888, 'steps': 138738, 'loss/train': 1.3615117073059082} 08/31/2021 14:26:53 - INFO - __main__ - Step 138740: {'lr': 7.108391535999959e-06, 'samples': 26638080, 'steps': 138739, 'loss/train': 0.5913562178611755} 08/31/2021 14:26:53 - INFO - __main__ - Step 138741: {'lr': 7.107135128196496e-06, 'samples': 26638272, 'steps': 138740, 'loss/train': 1.3264472484588623} 08/31/2021 14:26:54 - INFO - __main__ - Step 138742: {'lr': 7.105878829836848e-06, 'samples': 26638464, 'steps': 138741, 'loss/train': 1.1851967573165894} 08/31/2021 14:26:54 - INFO - __main__ - Step 138743: {'lr': 7.104622640921516e-06, 'samples': 26638656, 'steps': 138742, 'loss/train': 1.078493595123291} 08/31/2021 14:26:56 - INFO - __main__ - Step 138744: {'lr': 7.10336656145108e-06, 'samples': 26638848, 'steps': 138743, 'loss/train': 0.9950123429298401} 08/31/2021 14:26:56 - INFO - __main__ - Step 138745: {'lr': 7.1021105914261255e-06, 'samples': 26639040, 'steps': 138744, 'loss/train': 2.0949783325195312} 08/31/2021 14:26:57 - INFO - __main__ - Step 138746: {'lr': 7.100854730847234e-06, 'samples': 26639232, 'steps': 138745, 'loss/train': 1.0981953144073486} 08/31/2021 14:26:57 - INFO - __main__ - Step 138747: {'lr': 7.0995989797149055e-06, 'samples': 26639424, 'steps': 138746, 'loss/train': 0.38638001680374146} 08/31/2021 14:26:57 - INFO - __main__ - Step 138748: {'lr': 7.098343338029778e-06, 'samples': 26639616, 'steps': 138747, 'loss/train': 0.6917972564697266} 08/31/2021 14:26:59 - INFO - __main__ - Step 138749: {'lr': 7.09708780579238e-06, 'samples': 26639808, 'steps': 138748, 'loss/train': 0.5866288542747498} 08/31/2021 14:26:59 - INFO - __main__ - Step 138750: {'lr': 7.0958323830032926e-06, 'samples': 26640000, 'steps': 138749, 'loss/train': 1.720274806022644} 08/31/2021 14:27:00 - INFO - __main__ - Step 138751: {'lr': 7.094577069663072e-06, 'samples': 26640192, 'steps': 138750, 'loss/train': 0.7537070512771606} 08/31/2021 14:27:00 - INFO - __main__ - Step 138752: {'lr': 7.093321865772301e-06, 'samples': 26640384, 'steps': 138751, 'loss/train': 1.4593360424041748} 08/31/2021 14:27:00 - INFO - __main__ - Step 138753: {'lr': 7.092066771331507e-06, 'samples': 26640576, 'steps': 138752, 'loss/train': 1.160402536392212} 08/31/2021 14:27:01 - INFO - __main__ - Step 138754: {'lr': 7.0908117863413e-06, 'samples': 26640768, 'steps': 138753, 'loss/train': 0.570995569229126} 08/31/2021 14:27:02 - INFO - __main__ - Step 138755: {'lr': 7.089556910802236e-06, 'samples': 26640960, 'steps': 138754, 'loss/train': 1.0225005149841309} 08/31/2021 14:27:03 - INFO - __main__ - Step 138756: {'lr': 7.088302144714842e-06, 'samples': 26641152, 'steps': 138755, 'loss/train': 0.9939693808555603} 08/31/2021 14:27:03 - INFO - __main__ - Step 138757: {'lr': 7.087047488079729e-06, 'samples': 26641344, 'steps': 138756, 'loss/train': 1.3754398822784424} 08/31/2021 14:27:03 - INFO - __main__ - Step 138758: {'lr': 7.085792940897423e-06, 'samples': 26641536, 'steps': 138757, 'loss/train': 1.7250478267669678} 08/31/2021 14:27:04 - INFO - __main__ - Step 138759: {'lr': 7.084538503168508e-06, 'samples': 26641728, 'steps': 138758, 'loss/train': 1.1094815731048584} 08/31/2021 14:27:05 - INFO - __main__ - Step 138760: {'lr': 7.083284174893567e-06, 'samples': 26641920, 'steps': 138759, 'loss/train': 0.9488182663917542} 08/31/2021 14:27:06 - INFO - __main__ - Step 138761: {'lr': 7.082029956073155e-06, 'samples': 26642112, 'steps': 138760, 'loss/train': 1.183990478515625} 08/31/2021 14:27:06 - INFO - __main__ - Step 138762: {'lr': 7.080775846707826e-06, 'samples': 26642304, 'steps': 138761, 'loss/train': 1.8630123138427734} 08/31/2021 14:27:06 - INFO - __main__ - Step 138763: {'lr': 7.079521846798137e-06, 'samples': 26642496, 'steps': 138762, 'loss/train': 1.0334241390228271} 08/31/2021 14:27:07 - INFO - __main__ - Step 138764: {'lr': 7.0782679563446694e-06, 'samples': 26642688, 'steps': 138763, 'loss/train': 0.5141205191612244} 08/31/2021 14:27:08 - INFO - __main__ - Step 138765: {'lr': 7.0770141753480065e-06, 'samples': 26642880, 'steps': 138764, 'loss/train': 0.9318472146987915} 08/31/2021 14:27:09 - INFO - __main__ - Step 138766: {'lr': 7.0757605038086755e-06, 'samples': 26643072, 'steps': 138765, 'loss/train': 0.41454023122787476} 08/31/2021 14:27:09 - INFO - __main__ - Step 138767: {'lr': 7.07450694172726e-06, 'samples': 26643264, 'steps': 138766, 'loss/train': 1.3296167850494385} 08/31/2021 14:27:09 - INFO - __main__ - Step 138768: {'lr': 7.0732534891043424e-06, 'samples': 26643456, 'steps': 138767, 'loss/train': 1.5153610706329346} 08/31/2021 14:27:10 - INFO - __main__ - Step 138769: {'lr': 7.072000145940449e-06, 'samples': 26643648, 'steps': 138768, 'loss/train': 0.04678737372159958} 08/31/2021 14:27:11 - INFO - __main__ - Step 138770: {'lr': 7.0707469122361645e-06, 'samples': 26643840, 'steps': 138769, 'loss/train': 1.156434178352356} 08/31/2021 14:27:12 - INFO - __main__ - Step 138771: {'lr': 7.069493787992071e-06, 'samples': 26644032, 'steps': 138770, 'loss/train': 1.317178726196289} 08/31/2021 14:27:12 - INFO - __main__ - Step 138772: {'lr': 7.068240773208695e-06, 'samples': 26644224, 'steps': 138771, 'loss/train': 0.9055550694465637} 08/31/2021 14:27:12 - INFO - __main__ - Step 138773: {'lr': 7.06698786788662e-06, 'samples': 26644416, 'steps': 138772, 'loss/train': 1.0198233127593994} 08/31/2021 14:27:13 - INFO - __main__ - Step 138774: {'lr': 7.065735072026402e-06, 'samples': 26644608, 'steps': 138773, 'loss/train': 1.0801304578781128} 08/31/2021 14:27:14 - INFO - __main__ - Step 138775: {'lr': 7.064482385628651e-06, 'samples': 26644800, 'steps': 138774, 'loss/train': 1.1489050388336182} 08/31/2021 14:27:15 - INFO - __main__ - Step 138776: {'lr': 7.063229808693867e-06, 'samples': 26644992, 'steps': 138775, 'loss/train': 0.2248600423336029} 08/31/2021 14:27:15 - INFO - __main__ - Step 138777: {'lr': 7.061977341222631e-06, 'samples': 26645184, 'steps': 138776, 'loss/train': 1.6305058002471924} 08/31/2021 14:27:15 - INFO - __main__ - Step 138778: {'lr': 7.060724983215555e-06, 'samples': 26645376, 'steps': 138777, 'loss/train': 1.7624447345733643} 08/31/2021 14:27:16 - INFO - __main__ - Step 138779: {'lr': 7.059472734673139e-06, 'samples': 26645568, 'steps': 138778, 'loss/train': 1.4735392332077026} 08/31/2021 14:27:18 - INFO - __main__ - Step 138780: {'lr': 7.0582205955959934e-06, 'samples': 26645760, 'steps': 138779, 'loss/train': 1.1616828441619873} 08/31/2021 14:27:18 - INFO - __main__ - Step 138781: {'lr': 7.056968565984645e-06, 'samples': 26645952, 'steps': 138780, 'loss/train': 1.2401955127716064} 08/31/2021 14:27:18 - INFO - __main__ - Step 138782: {'lr': 7.0557166458397326e-06, 'samples': 26646144, 'steps': 138781, 'loss/train': 0.8678509593009949} 08/31/2021 14:27:19 - INFO - __main__ - Step 138783: {'lr': 7.054464835161728e-06, 'samples': 26646336, 'steps': 138782, 'loss/train': 1.2011189460754395} 08/31/2021 14:27:19 - INFO - __main__ - Step 138784: {'lr': 7.053213133951214e-06, 'samples': 26646528, 'steps': 138783, 'loss/train': 1.263196587562561} 08/31/2021 14:27:19 - INFO - __main__ - Step 138785: {'lr': 7.051961542208801e-06, 'samples': 26646720, 'steps': 138784, 'loss/train': 1.372366189956665} 08/31/2021 14:27:21 - INFO - __main__ - Step 138786: {'lr': 7.050710059934989e-06, 'samples': 26646912, 'steps': 138785, 'loss/train': 0.08793498575687408} 08/31/2021 14:27:22 - INFO - __main__ - Step 138787: {'lr': 7.0494586871304166e-06, 'samples': 26647104, 'steps': 138786, 'loss/train': 1.171223759651184} 08/31/2021 14:27:22 - INFO - __main__ - Step 138788: {'lr': 7.0482074237955825e-06, 'samples': 26647296, 'steps': 138787, 'loss/train': 1.1092289686203003} 08/31/2021 14:27:22 - INFO - __main__ - Step 138789: {'lr': 7.0469562699310985e-06, 'samples': 26647488, 'steps': 138788, 'loss/train': 0.11509528011083603} 08/31/2021 14:27:23 - INFO - __main__ - Step 138790: {'lr': 7.045705225537491e-06, 'samples': 26647680, 'steps': 138789, 'loss/train': 0.5046916604042053} 08/31/2021 14:27:25 - INFO - __main__ - Step 138791: {'lr': 7.044454290615343e-06, 'samples': 26647872, 'steps': 138790, 'loss/train': 1.0624085664749146} 08/31/2021 14:27:25 - INFO - __main__ - Step 138792: {'lr': 7.04320346516521e-06, 'samples': 26648064, 'steps': 138791, 'loss/train': 0.9480153918266296} 08/31/2021 14:27:26 - INFO - __main__ - Step 138793: {'lr': 7.041952749187675e-06, 'samples': 26648256, 'steps': 138792, 'loss/train': 1.4587841033935547} 08/31/2021 14:27:26 - INFO - __main__ - Step 138794: {'lr': 7.040702142683292e-06, 'samples': 26648448, 'steps': 138793, 'loss/train': 1.7377816438674927} 08/31/2021 14:27:26 - INFO - __main__ - Step 138795: {'lr': 7.039451645652617e-06, 'samples': 26648640, 'steps': 138794, 'loss/train': 0.03645807132124901} 08/31/2021 14:27:28 - INFO - __main__ - Step 138796: {'lr': 7.038201258096205e-06, 'samples': 26648832, 'steps': 138795, 'loss/train': 1.2573806047439575} 08/31/2021 14:27:28 - INFO - __main__ - Step 138797: {'lr': 7.0369509800146395e-06, 'samples': 26649024, 'steps': 138796, 'loss/train': 1.7645105123519897} 08/31/2021 14:27:29 - INFO - __main__ - Step 138798: {'lr': 7.035700811408474e-06, 'samples': 26649216, 'steps': 138797, 'loss/train': 0.9605767130851746} 08/31/2021 14:27:29 - INFO - __main__ - Step 138799: {'lr': 7.034450752278265e-06, 'samples': 26649408, 'steps': 138798, 'loss/train': 1.391909122467041} 08/31/2021 14:27:29 - INFO - __main__ - Step 138800: {'lr': 7.033200802624567e-06, 'samples': 26649600, 'steps': 138799, 'loss/train': 1.2949634790420532} 08/31/2021 14:27:31 - INFO - __main__ - Step 138801: {'lr': 7.031950962447992e-06, 'samples': 26649792, 'steps': 138800, 'loss/train': 0.7397667169570923} 08/31/2021 14:27:31 - INFO - __main__ - Step 138802: {'lr': 7.030701231749037e-06, 'samples': 26649984, 'steps': 138801, 'loss/train': 0.8822352290153503} 08/31/2021 14:27:32 - INFO - __main__ - Step 138803: {'lr': 7.0294516105283146e-06, 'samples': 26650176, 'steps': 138802, 'loss/train': 0.3056892454624176} 08/31/2021 14:27:32 - INFO - __main__ - Step 138804: {'lr': 7.028202098786379e-06, 'samples': 26650368, 'steps': 138803, 'loss/train': 1.0099951028823853} 08/31/2021 14:27:32 - INFO - __main__ - Step 138805: {'lr': 7.026952696523786e-06, 'samples': 26650560, 'steps': 138804, 'loss/train': 1.0670783519744873} 08/31/2021 14:27:34 - INFO - __main__ - Step 138806: {'lr': 7.02570340374109e-06, 'samples': 26650752, 'steps': 138805, 'loss/train': 1.50533127784729} 08/31/2021 14:27:34 - INFO - __main__ - Step 138807: {'lr': 7.024454220438875e-06, 'samples': 26650944, 'steps': 138806, 'loss/train': 0.9662528038024902} 08/31/2021 14:27:35 - INFO - __main__ - Step 138808: {'lr': 7.023205146617667e-06, 'samples': 26651136, 'steps': 138807, 'loss/train': 1.4811104536056519} 08/31/2021 14:27:35 - INFO - __main__ - Step 138809: {'lr': 7.021956182278105e-06, 'samples': 26651328, 'steps': 138808, 'loss/train': 0.7458325624465942} 08/31/2021 14:27:35 - INFO - __main__ - Step 138810: {'lr': 7.0207073274206615e-06, 'samples': 26651520, 'steps': 138809, 'loss/train': 1.053127646446228} 08/31/2021 14:27:37 - INFO - __main__ - Step 138811: {'lr': 7.019458582045946e-06, 'samples': 26651712, 'steps': 138810, 'loss/train': 1.1913925409317017} 08/31/2021 14:27:37 - INFO - __main__ - Step 138812: {'lr': 7.0182099461545135e-06, 'samples': 26651904, 'steps': 138811, 'loss/train': 0.6204332113265991} 08/31/2021 14:27:38 - INFO - __main__ - Step 138813: {'lr': 7.01696141974692e-06, 'samples': 26652096, 'steps': 138812, 'loss/train': 1.0436261892318726} 08/31/2021 14:27:38 - INFO - __main__ - Step 138814: {'lr': 7.01571300282372e-06, 'samples': 26652288, 'steps': 138813, 'loss/train': 0.97084641456604} 08/31/2021 14:27:38 - INFO - __main__ - Step 138815: {'lr': 7.014464695385525e-06, 'samples': 26652480, 'steps': 138814, 'loss/train': 1.0170530080795288} 08/31/2021 14:27:40 - INFO - __main__ - Step 138816: {'lr': 7.013216497432834e-06, 'samples': 26652672, 'steps': 138815, 'loss/train': 1.2023532390594482} 08/31/2021 14:27:40 - INFO - __main__ - Step 138817: {'lr': 7.011968408966258e-06, 'samples': 26652864, 'steps': 138816, 'loss/train': 0.9136607050895691} 08/31/2021 14:27:41 - INFO - __main__ - Step 138818: {'lr': 7.010720429986322e-06, 'samples': 26653056, 'steps': 138817, 'loss/train': 0.7154010534286499} 08/31/2021 14:27:41 - INFO - __main__ - Step 138819: {'lr': 7.009472560493613e-06, 'samples': 26653248, 'steps': 138818, 'loss/train': 1.6328285932540894} 08/31/2021 14:27:41 - INFO - __main__ - Step 138820: {'lr': 7.008224800488683e-06, 'samples': 26653440, 'steps': 138819, 'loss/train': 0.03834569454193115} 08/31/2021 14:27:43 - INFO - __main__ - Step 138821: {'lr': 7.006977149972088e-06, 'samples': 26653632, 'steps': 138820, 'loss/train': 0.7589480876922607} 08/31/2021 14:27:44 - INFO - __main__ - Step 138822: {'lr': 7.005729608944439e-06, 'samples': 26653824, 'steps': 138821, 'loss/train': 1.1267366409301758} 08/31/2021 14:27:44 - INFO - __main__ - Step 138823: {'lr': 7.004482177406235e-06, 'samples': 26654016, 'steps': 138822, 'loss/train': 0.921379029750824} 08/31/2021 14:27:44 - INFO - __main__ - Step 138824: {'lr': 7.0032348553580595e-06, 'samples': 26654208, 'steps': 138823, 'loss/train': 0.9875373840332031} 08/31/2021 14:27:45 - INFO - __main__ - Step 138825: {'lr': 7.001987642800467e-06, 'samples': 26654400, 'steps': 138824, 'loss/train': 0.07072187215089798} 08/31/2021 14:27:45 - INFO - __main__ - Step 138826: {'lr': 7.000740539734041e-06, 'samples': 26654592, 'steps': 138825, 'loss/train': 1.2011874914169312} 08/31/2021 14:27:47 - INFO - __main__ - Step 138827: {'lr': 6.999493546159336e-06, 'samples': 26654784, 'steps': 138826, 'loss/train': 1.353111982345581} 08/31/2021 14:27:47 - INFO - __main__ - Step 138828: {'lr': 6.998246662076907e-06, 'samples': 26654976, 'steps': 138827, 'loss/train': 1.1707580089569092} 08/31/2021 14:27:47 - INFO - __main__ - Step 138829: {'lr': 6.99699988748731e-06, 'samples': 26655168, 'steps': 138828, 'loss/train': 0.9964688420295715} 08/31/2021 14:27:48 - INFO - __main__ - Step 138830: {'lr': 6.995753222391099e-06, 'samples': 26655360, 'steps': 138829, 'loss/train': 1.191261887550354} 08/31/2021 14:27:48 - INFO - __main__ - Step 138831: {'lr': 6.994506666788886e-06, 'samples': 26655552, 'steps': 138830, 'loss/train': 0.5746195316314697} 08/31/2021 14:27:50 - INFO - __main__ - Step 138832: {'lr': 6.993260220681169e-06, 'samples': 26655744, 'steps': 138831, 'loss/train': 1.592402696609497} 08/31/2021 14:27:50 - INFO - __main__ - Step 138833: {'lr': 6.99201388406856e-06, 'samples': 26655936, 'steps': 138832, 'loss/train': 0.7725462913513184} 08/31/2021 14:27:50 - INFO - __main__ - Step 138834: {'lr': 6.990767656951585e-06, 'samples': 26656128, 'steps': 138833, 'loss/train': 1.180240511894226} 08/31/2021 14:27:51 - INFO - __main__ - Step 138835: {'lr': 6.989521539330829e-06, 'samples': 26656320, 'steps': 138834, 'loss/train': 0.7857738733291626} 08/31/2021 14:27:51 - INFO - __main__ - Step 138836: {'lr': 6.9882755312068725e-06, 'samples': 26656512, 'steps': 138835, 'loss/train': 1.0780029296875} 08/31/2021 14:27:53 - INFO - __main__ - Step 138837: {'lr': 6.987029632580216e-06, 'samples': 26656704, 'steps': 138836, 'loss/train': 0.32724523544311523} 08/31/2021 14:27:53 - INFO - __main__ - Step 138838: {'lr': 6.985783843451471e-06, 'samples': 26656896, 'steps': 138837, 'loss/train': 0.679301917552948} 08/31/2021 14:27:53 - INFO - __main__ - Step 138839: {'lr': 6.984538163821164e-06, 'samples': 26657088, 'steps': 138838, 'loss/train': 1.2640200853347778} 08/31/2021 14:27:54 - INFO - __main__ - Step 138840: {'lr': 6.983292593689877e-06, 'samples': 26657280, 'steps': 138839, 'loss/train': 1.4355443716049194} 08/31/2021 14:27:54 - INFO - __main__ - Step 138841: {'lr': 6.982047133058167e-06, 'samples': 26657472, 'steps': 138840, 'loss/train': 1.4837311506271362} 08/31/2021 14:27:56 - INFO - __main__ - Step 138842: {'lr': 6.980801781926616e-06, 'samples': 26657664, 'steps': 138841, 'loss/train': 0.9561112523078918} 08/31/2021 14:27:57 - INFO - __main__ - Step 138843: {'lr': 6.97955654029575e-06, 'samples': 26657856, 'steps': 138842, 'loss/train': 1.603204607963562} 08/31/2021 14:27:57 - INFO - __main__ - Step 138844: {'lr': 6.978311408166127e-06, 'samples': 26658048, 'steps': 138843, 'loss/train': 1.0690515041351318} 08/31/2021 14:27:57 - INFO - __main__ - Step 138845: {'lr': 6.9770663855383555e-06, 'samples': 26658240, 'steps': 138844, 'loss/train': 1.0561527013778687} 08/31/2021 14:27:58 - INFO - __main__ - Step 138846: {'lr': 6.9758214724129634e-06, 'samples': 26658432, 'steps': 138845, 'loss/train': 0.9199580550193787} 08/31/2021 14:27:58 - INFO - __main__ - Step 138847: {'lr': 6.974576668790505e-06, 'samples': 26658624, 'steps': 138846, 'loss/train': 1.0123565196990967} 08/31/2021 14:28:00 - INFO - __main__ - Step 138848: {'lr': 6.973331974671593e-06, 'samples': 26658816, 'steps': 138847, 'loss/train': 1.5254067182540894} 08/31/2021 14:28:00 - INFO - __main__ - Step 138849: {'lr': 6.972087390056697e-06, 'samples': 26659008, 'steps': 138848, 'loss/train': 1.1207860708236694} 08/31/2021 14:28:00 - INFO - __main__ - Step 138850: {'lr': 6.970842914946457e-06, 'samples': 26659200, 'steps': 138849, 'loss/train': 1.3334859609603882} 08/31/2021 14:28:01 - INFO - __main__ - Step 138851: {'lr': 6.969598549341372e-06, 'samples': 26659392, 'steps': 138850, 'loss/train': 1.294838786125183} 08/31/2021 14:28:01 - INFO - __main__ - Step 138852: {'lr': 6.968354293242052e-06, 'samples': 26659584, 'steps': 138851, 'loss/train': 0.14306463301181793} 08/31/2021 14:28:03 - INFO - __main__ - Step 138853: {'lr': 6.9671101466490525e-06, 'samples': 26659776, 'steps': 138852, 'loss/train': 0.8245267868041992} 08/31/2021 14:28:03 - INFO - __main__ - Step 138854: {'lr': 6.965866109562929e-06, 'samples': 26659968, 'steps': 138853, 'loss/train': 0.9842295050621033} 08/31/2021 14:28:03 - INFO - __main__ - Step 138855: {'lr': 6.964622181984209e-06, 'samples': 26660160, 'steps': 138854, 'loss/train': 1.627618432044983} 08/31/2021 14:28:04 - INFO - __main__ - Step 138856: {'lr': 6.963378363913503e-06, 'samples': 26660352, 'steps': 138855, 'loss/train': 0.7250065207481384} 08/31/2021 14:28:04 - INFO - __main__ - Step 138857: {'lr': 6.962134655351337e-06, 'samples': 26660544, 'steps': 138856, 'loss/train': 0.20421555638313293} 08/31/2021 14:28:06 - INFO - __main__ - Step 138858: {'lr': 6.9608910562982686e-06, 'samples': 26660736, 'steps': 138857, 'loss/train': 1.010300874710083} 08/31/2021 14:28:06 - INFO - __main__ - Step 138859: {'lr': 6.959647566754934e-06, 'samples': 26660928, 'steps': 138858, 'loss/train': 0.7761725187301636} 08/31/2021 14:28:06 - INFO - __main__ - Step 138860: {'lr': 6.958404186721779e-06, 'samples': 26661120, 'steps': 138859, 'loss/train': 1.0480209589004517} 08/31/2021 14:28:07 - INFO - __main__ - Step 138861: {'lr': 6.957160916199412e-06, 'samples': 26661312, 'steps': 138860, 'loss/train': 0.8660493493080139} 08/31/2021 14:28:07 - INFO - __main__ - Step 138862: {'lr': 6.955917755188418e-06, 'samples': 26661504, 'steps': 138861, 'loss/train': 0.3913242816925049} 08/31/2021 14:28:09 - INFO - __main__ - Step 138863: {'lr': 6.954674703689323e-06, 'samples': 26661696, 'steps': 138862, 'loss/train': 0.9435106515884399} 08/31/2021 14:28:09 - INFO - __main__ - Step 138864: {'lr': 6.953431761702711e-06, 'samples': 26661888, 'steps': 138863, 'loss/train': 0.02758406661450863} 08/31/2021 14:28:10 - INFO - __main__ - Step 138865: {'lr': 6.952188929229136e-06, 'samples': 26662080, 'steps': 138864, 'loss/train': 0.6882776021957397} 08/31/2021 14:28:10 - INFO - __main__ - Step 138866: {'lr': 6.950946206269127e-06, 'samples': 26662272, 'steps': 138865, 'loss/train': 1.3481711149215698} 08/31/2021 14:28:10 - INFO - __main__ - Step 138867: {'lr': 6.949703592823292e-06, 'samples': 26662464, 'steps': 138866, 'loss/train': 1.0655020475387573} 08/31/2021 14:28:12 - INFO - __main__ - Step 138868: {'lr': 6.948461088892188e-06, 'samples': 26662656, 'steps': 138867, 'loss/train': 0.6219614148139954} 08/31/2021 14:28:12 - INFO - __main__ - Step 138869: {'lr': 6.947218694476315e-06, 'samples': 26662848, 'steps': 138868, 'loss/train': 0.6089937686920166} 08/31/2021 14:28:13 - INFO - __main__ - Step 138870: {'lr': 6.945976409576338e-06, 'samples': 26663040, 'steps': 138869, 'loss/train': 1.194999098777771} 08/31/2021 14:28:13 - INFO - __main__ - Step 138871: {'lr': 6.944734234192701e-06, 'samples': 26663232, 'steps': 138870, 'loss/train': 0.6954382061958313} 08/31/2021 14:28:13 - INFO - __main__ - Step 138872: {'lr': 6.943492168326043e-06, 'samples': 26663424, 'steps': 138871, 'loss/train': 1.321306586265564} 08/31/2021 14:28:15 - INFO - __main__ - Step 138873: {'lr': 6.942250211976864e-06, 'samples': 26663616, 'steps': 138872, 'loss/train': 0.8290589451789856} 08/31/2021 14:28:15 - INFO - __main__ - Step 138874: {'lr': 6.941008365145773e-06, 'samples': 26663808, 'steps': 138873, 'loss/train': 1.27084219455719} 08/31/2021 14:28:16 - INFO - __main__ - Step 138875: {'lr': 6.939766627833327e-06, 'samples': 26664000, 'steps': 138874, 'loss/train': 1.2369394302368164} 08/31/2021 14:28:16 - INFO - __main__ - Step 138876: {'lr': 6.9385250000400526e-06, 'samples': 26664192, 'steps': 138875, 'loss/train': 1.4890024662017822} 08/31/2021 14:28:17 - INFO - __main__ - Step 138877: {'lr': 6.937283481766532e-06, 'samples': 26664384, 'steps': 138876, 'loss/train': 1.0113258361816406} 08/31/2021 14:28:18 - INFO - __main__ - Step 138878: {'lr': 6.936042073013321e-06, 'samples': 26664576, 'steps': 138877, 'loss/train': 0.28605931997299194} 08/31/2021 14:28:18 - INFO - __main__ - Step 138879: {'lr': 6.934800773780975e-06, 'samples': 26664768, 'steps': 138878, 'loss/train': 1.162680983543396} 08/31/2021 14:28:19 - INFO - __main__ - Step 138880: {'lr': 6.933559584070076e-06, 'samples': 26664960, 'steps': 138879, 'loss/train': 1.2305694818496704} 08/31/2021 14:28:19 - INFO - __main__ - Step 138881: {'lr': 6.93231850388118e-06, 'samples': 26665152, 'steps': 138880, 'loss/train': 0.4875580966472626} 08/31/2021 14:28:19 - INFO - __main__ - Step 138882: {'lr': 6.931077533214786e-06, 'samples': 26665344, 'steps': 138881, 'loss/train': 1.2179231643676758} 08/31/2021 14:28:21 - INFO - __main__ - Step 138883: {'lr': 6.929836672071532e-06, 'samples': 26665536, 'steps': 138882, 'loss/train': 1.4364173412322998} 08/31/2021 14:28:22 - INFO - __main__ - Step 138884: {'lr': 6.928595920451919e-06, 'samples': 26665728, 'steps': 138883, 'loss/train': 0.42853790521621704} 08/31/2021 14:28:22 - INFO - __main__ - Step 138885: {'lr': 6.927355278356529e-06, 'samples': 26665920, 'steps': 138884, 'loss/train': 1.20649254322052} 08/31/2021 14:28:22 - INFO - __main__ - Step 138886: {'lr': 6.926114745785916e-06, 'samples': 26666112, 'steps': 138885, 'loss/train': 0.7705548405647278} 08/31/2021 14:28:23 - INFO - __main__ - Step 138887: {'lr': 6.924874322740665e-06, 'samples': 26666304, 'steps': 138886, 'loss/train': 0.996935248374939} 08/31/2021 14:28:23 - INFO - __main__ - Step 138888: {'lr': 6.923634009221303e-06, 'samples': 26666496, 'steps': 138887, 'loss/train': 0.9079403877258301} 08/31/2021 14:28:25 - INFO - __main__ - Step 138889: {'lr': 6.922393805228411e-06, 'samples': 26666688, 'steps': 138888, 'loss/train': 0.7465777397155762} 08/31/2021 14:28:25 - INFO - __main__ - Step 138890: {'lr': 6.921153710762518e-06, 'samples': 26666880, 'steps': 138889, 'loss/train': 0.8379431366920471} 08/31/2021 14:28:25 - INFO - __main__ - Step 138891: {'lr': 6.919913725824234e-06, 'samples': 26667072, 'steps': 138890, 'loss/train': 0.3576108515262604} 08/31/2021 14:28:26 - INFO - __main__ - Step 138892: {'lr': 6.918673850414087e-06, 'samples': 26667264, 'steps': 138891, 'loss/train': 0.9720203280448914} 08/31/2021 14:28:26 - INFO - __main__ - Step 138893: {'lr': 6.917434084532604e-06, 'samples': 26667456, 'steps': 138892, 'loss/train': 1.2328104972839355} 08/31/2021 14:28:28 - INFO - __main__ - Step 138894: {'lr': 6.916194428180395e-06, 'samples': 26667648, 'steps': 138893, 'loss/train': 1.3381052017211914} 08/31/2021 14:28:29 - INFO - __main__ - Step 138895: {'lr': 6.9149548813579875e-06, 'samples': 26667840, 'steps': 138894, 'loss/train': 1.9637305736541748} 08/31/2021 14:28:29 - INFO - __main__ - Step 138896: {'lr': 6.913715444065937e-06, 'samples': 26668032, 'steps': 138895, 'loss/train': 1.0802724361419678} 08/31/2021 14:28:29 - INFO - __main__ - Step 138897: {'lr': 6.912476116304828e-06, 'samples': 26668224, 'steps': 138896, 'loss/train': 1.120582103729248} 08/31/2021 14:28:30 - INFO - __main__ - Step 138898: {'lr': 6.911236898075213e-06, 'samples': 26668416, 'steps': 138897, 'loss/train': 0.624398410320282} 08/31/2021 14:28:32 - INFO - __main__ - Step 138899: {'lr': 6.909997789377648e-06, 'samples': 26668608, 'steps': 138898, 'loss/train': 0.5308095216751099} 08/31/2021 14:28:32 - INFO - __main__ - Step 138900: {'lr': 6.90875879021266e-06, 'samples': 26668800, 'steps': 138899, 'loss/train': 1.0988399982452393} 08/31/2021 14:28:33 - INFO - __main__ - Step 138901: {'lr': 6.907519900580861e-06, 'samples': 26668992, 'steps': 138900, 'loss/train': 0.01322220079600811} 08/31/2021 14:28:33 - INFO - __main__ - Step 138902: {'lr': 6.906281120482777e-06, 'samples': 26669184, 'steps': 138901, 'loss/train': 0.013074418529868126} 08/31/2021 14:28:33 - INFO - __main__ - Step 138903: {'lr': 6.905042449918991e-06, 'samples': 26669376, 'steps': 138902, 'loss/train': 0.733608067035675} 08/31/2021 14:28:34 - INFO - __main__ - Step 138904: {'lr': 6.903803888890003e-06, 'samples': 26669568, 'steps': 138903, 'loss/train': 1.2501589059829712} 08/31/2021 14:28:34 - INFO - __main__ - Step 138905: {'lr': 6.902565437396424e-06, 'samples': 26669760, 'steps': 138904, 'loss/train': 1.3051589727401733} 08/31/2021 14:28:36 - INFO - __main__ - Step 138906: {'lr': 6.901327095438809e-06, 'samples': 26669952, 'steps': 138905, 'loss/train': 0.9437527656555176} 08/31/2021 14:28:36 - INFO - __main__ - Step 138907: {'lr': 6.900088863017684e-06, 'samples': 26670144, 'steps': 138906, 'loss/train': 1.1076793670654297} 08/31/2021 14:28:37 - INFO - __main__ - Step 138908: {'lr': 6.898850740133633e-06, 'samples': 26670336, 'steps': 138907, 'loss/train': 1.2048219442367554} 08/31/2021 14:28:37 - INFO - __main__ - Step 138909: {'lr': 6.897612726787212e-06, 'samples': 26670528, 'steps': 138908, 'loss/train': 0.9873597621917725} 08/31/2021 14:28:37 - INFO - __main__ - Step 138910: {'lr': 6.896374822978974e-06, 'samples': 26670720, 'steps': 138909, 'loss/train': 1.3202643394470215} 08/31/2021 14:28:39 - INFO - __main__ - Step 138911: {'lr': 6.895137028709475e-06, 'samples': 26670912, 'steps': 138910, 'loss/train': 0.797730565071106} 08/31/2021 14:28:39 - INFO - __main__ - Step 138912: {'lr': 6.893899343979299e-06, 'samples': 26671104, 'steps': 138911, 'loss/train': 0.7317537069320679} 08/31/2021 14:28:40 - INFO - __main__ - Step 138913: {'lr': 6.892661768788944e-06, 'samples': 26671296, 'steps': 138912, 'loss/train': 1.3192393779754639} 08/31/2021 14:28:40 - INFO - __main__ - Step 138914: {'lr': 6.891424303139021e-06, 'samples': 26671488, 'steps': 138913, 'loss/train': 1.1689101457595825} 08/31/2021 14:28:40 - INFO - __main__ - Step 138915: {'lr': 6.890186947030086e-06, 'samples': 26671680, 'steps': 138914, 'loss/train': 1.880081057548523} 08/31/2021 14:28:42 - INFO - __main__ - Step 138916: {'lr': 6.888949700462693e-06, 'samples': 26671872, 'steps': 138915, 'loss/train': 0.613680899143219} 08/31/2021 14:28:42 - INFO - __main__ - Step 138917: {'lr': 6.887712563437371e-06, 'samples': 26672064, 'steps': 138916, 'loss/train': 0.7498986721038818} 08/31/2021 14:28:43 - INFO - __main__ - Step 138918: {'lr': 6.886475535954673e-06, 'samples': 26672256, 'steps': 138917, 'loss/train': 1.2401820421218872} 08/31/2021 14:28:43 - INFO - __main__ - Step 138919: {'lr': 6.885238618015183e-06, 'samples': 26672448, 'steps': 138918, 'loss/train': 1.5500609874725342} 08/31/2021 14:28:43 - INFO - __main__ - Step 138920: {'lr': 6.884001809619455e-06, 'samples': 26672640, 'steps': 138919, 'loss/train': 0.9898887872695923} 08/31/2021 14:28:45 - INFO - __main__ - Step 138921: {'lr': 6.8827651107680745e-06, 'samples': 26672832, 'steps': 138920, 'loss/train': 1.1717885732650757} 08/31/2021 14:28:45 - INFO - __main__ - Step 138922: {'lr': 6.881528521461539e-06, 'samples': 26673024, 'steps': 138921, 'loss/train': 1.4430509805679321} 08/31/2021 14:28:46 - INFO - __main__ - Step 138923: {'lr': 6.880292041700431e-06, 'samples': 26673216, 'steps': 138922, 'loss/train': 1.1718684434890747} 08/31/2021 14:28:46 - INFO - __main__ - Step 138924: {'lr': 6.879055671485334e-06, 'samples': 26673408, 'steps': 138923, 'loss/train': 1.4062914848327637} 08/31/2021 14:28:46 - INFO - __main__ - Step 138925: {'lr': 6.877819410816749e-06, 'samples': 26673600, 'steps': 138924, 'loss/train': 1.2813359498977661} 08/31/2021 14:28:47 - INFO - __main__ - Step 138926: {'lr': 6.876583259695285e-06, 'samples': 26673792, 'steps': 138925, 'loss/train': 1.364958643913269} 08/31/2021 14:28:48 - INFO - __main__ - Step 138927: {'lr': 6.875347218121497e-06, 'samples': 26673984, 'steps': 138926, 'loss/train': 1.3691563606262207} 08/31/2021 14:28:49 - INFO - __main__ - Step 138928: {'lr': 6.874111286095913e-06, 'samples': 26674176, 'steps': 138927, 'loss/train': 0.9207077622413635} 08/31/2021 14:28:49 - INFO - __main__ - Step 138929: {'lr': 6.872875463619088e-06, 'samples': 26674368, 'steps': 138928, 'loss/train': 0.6913607716560364} 08/31/2021 14:28:49 - INFO - __main__ - Step 138930: {'lr': 6.871639750691633e-06, 'samples': 26674560, 'steps': 138929, 'loss/train': 0.9464465975761414} 08/31/2021 14:28:50 - INFO - __main__ - Step 138931: {'lr': 6.870404147314047e-06, 'samples': 26674752, 'steps': 138930, 'loss/train': 1.3567739725112915} 08/31/2021 14:28:52 - INFO - __main__ - Step 138932: {'lr': 6.8691686534869126e-06, 'samples': 26674944, 'steps': 138931, 'loss/train': 2.0590834617614746} 08/31/2021 14:28:52 - INFO - __main__ - Step 138933: {'lr': 6.867933269210757e-06, 'samples': 26675136, 'steps': 138932, 'loss/train': 0.9764117002487183} 08/31/2021 14:28:52 - INFO - __main__ - Step 138934: {'lr': 6.8666979944861655e-06, 'samples': 26675328, 'steps': 138933, 'loss/train': 0.7679311037063599} 08/31/2021 14:28:53 - INFO - __main__ - Step 138935: {'lr': 6.86546282931369e-06, 'samples': 26675520, 'steps': 138934, 'loss/train': 2.1058077812194824} 08/31/2021 14:28:53 - INFO - __main__ - Step 138936: {'lr': 6.864227773693888e-06, 'samples': 26675712, 'steps': 138935, 'loss/train': 0.8861404061317444} 08/31/2021 14:28:55 - INFO - __main__ - Step 138937: {'lr': 6.862992827627312e-06, 'samples': 26675904, 'steps': 138936, 'loss/train': 0.3090359568595886} 08/31/2021 14:28:55 - INFO - __main__ - Step 138938: {'lr': 6.86175799111452e-06, 'samples': 26676096, 'steps': 138937, 'loss/train': 1.602462649345398} 08/31/2021 14:28:55 - INFO - __main__ - Step 138939: {'lr': 6.860523264156065e-06, 'samples': 26676288, 'steps': 138938, 'loss/train': 1.0805866718292236} 08/31/2021 14:28:56 - INFO - __main__ - Step 138940: {'lr': 6.859288646752504e-06, 'samples': 26676480, 'steps': 138939, 'loss/train': 0.6995750665664673} 08/31/2021 14:28:56 - INFO - __main__ - Step 138941: {'lr': 6.8580541389043905e-06, 'samples': 26676672, 'steps': 138940, 'loss/train': 0.8034732341766357} 08/31/2021 14:28:56 - INFO - __main__ - Step 138942: {'lr': 6.856819740612308e-06, 'samples': 26676864, 'steps': 138941, 'loss/train': 1.7466156482696533} 08/31/2021 14:28:58 - INFO - __main__ - Step 138943: {'lr': 6.855585451876783e-06, 'samples': 26677056, 'steps': 138942, 'loss/train': 1.0816572904586792} 08/31/2021 14:28:58 - INFO - __main__ - Step 138944: {'lr': 6.854351272698373e-06, 'samples': 26677248, 'steps': 138943, 'loss/train': 0.23840193450450897} 08/31/2021 14:28:59 - INFO - __main__ - Step 138945: {'lr': 6.853117203077658e-06, 'samples': 26677440, 'steps': 138944, 'loss/train': 0.6764670014381409} 08/31/2021 14:28:59 - INFO - __main__ - Step 138946: {'lr': 6.851883243015139e-06, 'samples': 26677632, 'steps': 138945, 'loss/train': 0.8806402087211609} 08/31/2021 14:28:59 - INFO - __main__ - Step 138947: {'lr': 6.850649392511426e-06, 'samples': 26677824, 'steps': 138946, 'loss/train': 1.3776096105575562} 08/31/2021 14:29:01 - INFO - __main__ - Step 138948: {'lr': 6.849415651567076e-06, 'samples': 26678016, 'steps': 138947, 'loss/train': 0.38449355959892273} 08/31/2021 14:29:01 - INFO - __main__ - Step 138949: {'lr': 6.848182020182614e-06, 'samples': 26678208, 'steps': 138948, 'loss/train': 0.9307416081428528} 08/31/2021 14:29:02 - INFO - __main__ - Step 138950: {'lr': 6.8469484983585965e-06, 'samples': 26678400, 'steps': 138949, 'loss/train': 1.3072363138198853} 08/31/2021 14:29:02 - INFO - __main__ - Step 138951: {'lr': 6.845715086095605e-06, 'samples': 26678592, 'steps': 138950, 'loss/train': 0.7724273800849915} 08/31/2021 14:29:02 - INFO - __main__ - Step 138952: {'lr': 6.8444817833941684e-06, 'samples': 26678784, 'steps': 138951, 'loss/train': 0.8234597444534302} 08/31/2021 14:29:04 - INFO - __main__ - Step 138953: {'lr': 6.843248590254869e-06, 'samples': 26678976, 'steps': 138952, 'loss/train': 1.3426190614700317} 08/31/2021 14:29:05 - INFO - __main__ - Step 138954: {'lr': 6.842015506678262e-06, 'samples': 26679168, 'steps': 138953, 'loss/train': 1.2741512060165405} 08/31/2021 14:29:05 - INFO - __main__ - Step 138955: {'lr': 6.840782532664875e-06, 'samples': 26679360, 'steps': 138954, 'loss/train': 0.9422931671142578} 08/31/2021 14:29:06 - INFO - __main__ - Step 138956: {'lr': 6.839549668215289e-06, 'samples': 26679552, 'steps': 138955, 'loss/train': 1.4840031862258911} 08/31/2021 14:29:06 - INFO - __main__ - Step 138957: {'lr': 6.838316913330062e-06, 'samples': 26679744, 'steps': 138956, 'loss/train': 0.3189525902271271} 08/31/2021 14:29:08 - INFO - __main__ - Step 138958: {'lr': 6.837084268009719e-06, 'samples': 26679936, 'steps': 138957, 'loss/train': 1.3711003065109253} 08/31/2021 14:29:08 - INFO - __main__ - Step 138959: {'lr': 6.835851732254816e-06, 'samples': 26680128, 'steps': 138958, 'loss/train': 0.8324748277664185} 08/31/2021 14:29:08 - INFO - __main__ - Step 138960: {'lr': 6.8346193060659645e-06, 'samples': 26680320, 'steps': 138959, 'loss/train': 1.5342319011688232} 08/31/2021 14:29:09 - INFO - __main__ - Step 138961: {'lr': 6.833386989443635e-06, 'samples': 26680512, 'steps': 138960, 'loss/train': 1.0601474046707153} 08/31/2021 14:29:09 - INFO - __main__ - Step 138962: {'lr': 6.832154782388466e-06, 'samples': 26680704, 'steps': 138961, 'loss/train': 1.1554160118103027} 08/31/2021 14:29:11 - INFO - __main__ - Step 138963: {'lr': 6.830922684900959e-06, 'samples': 26680896, 'steps': 138962, 'loss/train': 0.6643176078796387} 08/31/2021 14:29:11 - INFO - __main__ - Step 138964: {'lr': 6.829690696981694e-06, 'samples': 26681088, 'steps': 138963, 'loss/train': 1.0145988464355469} 08/31/2021 14:29:11 - INFO - __main__ - Step 138965: {'lr': 6.8284588186312e-06, 'samples': 26681280, 'steps': 138964, 'loss/train': 1.3757051229476929} 08/31/2021 14:29:12 - INFO - __main__ - Step 138966: {'lr': 6.827227049850088e-06, 'samples': 26681472, 'steps': 138965, 'loss/train': 1.733513355255127} 08/31/2021 14:29:12 - INFO - __main__ - Step 138967: {'lr': 6.825995390638828e-06, 'samples': 26681664, 'steps': 138966, 'loss/train': 1.0463882684707642} 08/31/2021 14:29:12 - INFO - __main__ - Step 138968: {'lr': 6.82476384099806e-06, 'samples': 26681856, 'steps': 138967, 'loss/train': 1.42624831199646} 08/31/2021 14:29:14 - INFO - __main__ - Step 138969: {'lr': 6.823532400928284e-06, 'samples': 26682048, 'steps': 138968, 'loss/train': 0.8278066515922546} 08/31/2021 14:29:15 - INFO - __main__ - Step 138970: {'lr': 6.8223010704300816e-06, 'samples': 26682240, 'steps': 138969, 'loss/train': 4.0081562995910645} 08/31/2021 14:29:15 - INFO - __main__ - Step 138971: {'lr': 6.821069849504008e-06, 'samples': 26682432, 'steps': 138970, 'loss/train': 3.0450546741485596} 08/31/2021 14:29:15 - INFO - __main__ - Step 138972: {'lr': 6.8198387381505915e-06, 'samples': 26682624, 'steps': 138971, 'loss/train': 0.93798828125} 08/31/2021 14:29:16 - INFO - __main__ - Step 138973: {'lr': 6.818607736370386e-06, 'samples': 26682816, 'steps': 138972, 'loss/train': 1.033695101737976} 08/31/2021 14:29:18 - INFO - __main__ - Step 138974: {'lr': 6.817376844163975e-06, 'samples': 26683008, 'steps': 138973, 'loss/train': 0.9605324864387512} 08/31/2021 14:29:18 - INFO - __main__ - Step 138975: {'lr': 6.816146061531914e-06, 'samples': 26683200, 'steps': 138974, 'loss/train': 0.346707284450531} 08/31/2021 14:29:19 - INFO - __main__ - Step 138976: {'lr': 6.81491538847473e-06, 'samples': 26683392, 'steps': 138975, 'loss/train': 1.1963152885437012} 08/31/2021 14:29:19 - INFO - __main__ - Step 138977: {'lr': 6.813684824993005e-06, 'samples': 26683584, 'steps': 138976, 'loss/train': 0.36267387866973877} 08/31/2021 14:29:19 - INFO - __main__ - Step 138978: {'lr': 6.8124543710872674e-06, 'samples': 26683776, 'steps': 138977, 'loss/train': 0.6622105836868286} 08/31/2021 14:29:20 - INFO - __main__ - Step 138979: {'lr': 6.8112240267581e-06, 'samples': 26683968, 'steps': 138978, 'loss/train': 0.9797773957252502} 08/31/2021 14:29:21 - INFO - __main__ - Step 138980: {'lr': 6.80999379200603e-06, 'samples': 26684160, 'steps': 138979, 'loss/train': 0.03535166755318642} 08/31/2021 14:29:22 - INFO - __main__ - Step 138981: {'lr': 6.808763666831641e-06, 'samples': 26684352, 'steps': 138980, 'loss/train': 1.0355437994003296} 08/31/2021 14:29:22 - INFO - __main__ - Step 138982: {'lr': 6.807533651235459e-06, 'samples': 26684544, 'steps': 138981, 'loss/train': 1.274243950843811} 08/31/2021 14:29:22 - INFO - __main__ - Step 138983: {'lr': 6.80630374521804e-06, 'samples': 26684736, 'steps': 138982, 'loss/train': 0.8167759776115417} 08/31/2021 14:29:23 - INFO - __main__ - Step 138984: {'lr': 6.805073948779994e-06, 'samples': 26684928, 'steps': 138983, 'loss/train': 0.9402085542678833} 08/31/2021 14:29:24 - INFO - __main__ - Step 138985: {'lr': 6.803844261921793e-06, 'samples': 26685120, 'steps': 138984, 'loss/train': 1.4199247360229492} 08/31/2021 14:29:25 - INFO - __main__ - Step 138986: {'lr': 6.8026146846440205e-06, 'samples': 26685312, 'steps': 138985, 'loss/train': 0.9352561831474304} 08/31/2021 14:29:25 - INFO - __main__ - Step 138987: {'lr': 6.801385216947231e-06, 'samples': 26685504, 'steps': 138986, 'loss/train': 1.2371317148208618} 08/31/2021 14:29:25 - INFO - __main__ - Step 138988: {'lr': 6.800155858832008e-06, 'samples': 26685696, 'steps': 138987, 'loss/train': 1.142781376838684} 08/31/2021 14:29:26 - INFO - __main__ - Step 138989: {'lr': 6.798926610298878e-06, 'samples': 26685888, 'steps': 138988, 'loss/train': 0.6657315492630005} 08/31/2021 14:29:27 - INFO - __main__ - Step 138990: {'lr': 6.7976974713483685e-06, 'samples': 26686080, 'steps': 138989, 'loss/train': 1.1418274641036987} 08/31/2021 14:29:28 - INFO - __main__ - Step 138991: {'lr': 6.7964684419810906e-06, 'samples': 26686272, 'steps': 138990, 'loss/train': 0.7588015794754028} 08/31/2021 14:29:28 - INFO - __main__ - Step 138992: {'lr': 6.795239522197572e-06, 'samples': 26686464, 'steps': 138991, 'loss/train': 0.6533779501914978} 08/31/2021 14:29:29 - INFO - __main__ - Step 138993: {'lr': 6.7940107119983665e-06, 'samples': 26686656, 'steps': 138992, 'loss/train': 1.004673957824707} 08/31/2021 14:29:29 - INFO - __main__ - Step 138994: {'lr': 6.792782011384002e-06, 'samples': 26686848, 'steps': 138993, 'loss/train': 0.30987706780433655} 08/31/2021 14:29:29 - INFO - __main__ - Step 138995: {'lr': 6.79155342035509e-06, 'samples': 26687040, 'steps': 138994, 'loss/train': 0.09207736700773239} 08/31/2021 14:29:31 - INFO - __main__ - Step 138996: {'lr': 6.790324938912129e-06, 'samples': 26687232, 'steps': 138995, 'loss/train': 0.8047573566436768} 08/31/2021 14:29:31 - INFO - __main__ - Step 138997: {'lr': 6.78909656705573e-06, 'samples': 26687424, 'steps': 138996, 'loss/train': 0.03817122429609299} 08/31/2021 14:29:32 - INFO - __main__ - Step 138998: {'lr': 6.787868304786393e-06, 'samples': 26687616, 'steps': 138997, 'loss/train': 0.6843875050544739} 08/31/2021 14:29:32 - INFO - __main__ - Step 138999: {'lr': 6.7866401521046724e-06, 'samples': 26687808, 'steps': 138998, 'loss/train': 0.8462677001953125} 08/31/2021 14:29:32 - INFO - __main__ - Step 139000: {'lr': 6.785412109011152e-06, 'samples': 26688000, 'steps': 138999, 'loss/train': 1.2755308151245117} 08/31/2021 14:29:34 - INFO - __main__ - Step 139001: {'lr': 6.784184175506358e-06, 'samples': 26688192, 'steps': 139000, 'loss/train': 1.70137357711792} 08/31/2021 14:29:35 - INFO - __main__ - Step 139002: {'lr': 6.782956351590874e-06, 'samples': 26688384, 'steps': 139001, 'loss/train': 1.2020893096923828} 08/31/2021 14:29:35 - INFO - __main__ - Step 139003: {'lr': 6.7817286372652274e-06, 'samples': 26688576, 'steps': 139002, 'loss/train': 0.45449867844581604} 08/31/2021 14:29:35 - INFO - __main__ - Step 139004: {'lr': 6.780501032529973e-06, 'samples': 26688768, 'steps': 139003, 'loss/train': 0.6633220314979553} 08/31/2021 14:29:36 - INFO - __main__ - Step 139005: {'lr': 6.7792735373856936e-06, 'samples': 26688960, 'steps': 139004, 'loss/train': 1.6576515436172485} 08/31/2021 14:29:38 - INFO - __main__ - Step 139006: {'lr': 6.77804615183289e-06, 'samples': 26689152, 'steps': 139005, 'loss/train': 0.324830025434494} 08/31/2021 14:29:38 - INFO - __main__ - Step 139007: {'lr': 6.77681887587217e-06, 'samples': 26689344, 'steps': 139006, 'loss/train': 1.0018051862716675} 08/31/2021 14:29:39 - INFO - __main__ - Step 139008: {'lr': 6.7755917095040645e-06, 'samples': 26689536, 'steps': 139007, 'loss/train': 0.9564769268035889} 08/31/2021 14:29:39 - INFO - __main__ - Step 139009: {'lr': 6.774364652729098e-06, 'samples': 26689728, 'steps': 139008, 'loss/train': 0.3979324996471405} 08/31/2021 14:29:40 - INFO - __main__ - Step 139010: {'lr': 6.77313770554791e-06, 'samples': 26689920, 'steps': 139009, 'loss/train': 0.8934765458106995} 08/31/2021 14:29:41 - INFO - __main__ - Step 139011: {'lr': 6.771910867960945e-06, 'samples': 26690112, 'steps': 139010, 'loss/train': 1.3621208667755127} 08/31/2021 14:29:42 - INFO - __main__ - Step 139012: {'lr': 6.770684139968814e-06, 'samples': 26690304, 'steps': 139011, 'loss/train': 0.8696244359016418} 08/31/2021 14:29:42 - INFO - __main__ - Step 139013: {'lr': 6.7694575215720425e-06, 'samples': 26690496, 'steps': 139012, 'loss/train': 0.859869658946991} 08/31/2021 14:29:42 - INFO - __main__ - Step 139014: {'lr': 6.768231012771214e-06, 'samples': 26690688, 'steps': 139013, 'loss/train': 0.7914458513259888} 08/31/2021 14:29:43 - INFO - __main__ - Step 139015: {'lr': 6.767004613566858e-06, 'samples': 26690880, 'steps': 139014, 'loss/train': 1.3070086240768433} 08/31/2021 14:29:43 - INFO - __main__ - Step 139016: {'lr': 6.7657783239595536e-06, 'samples': 26691072, 'steps': 139015, 'loss/train': 1.279539942741394} 08/31/2021 14:29:45 - INFO - __main__ - Step 139017: {'lr': 6.7645521439498316e-06, 'samples': 26691264, 'steps': 139016, 'loss/train': 0.988332986831665} 08/31/2021 14:29:45 - INFO - __main__ - Step 139018: {'lr': 6.7633260735382455e-06, 'samples': 26691456, 'steps': 139017, 'loss/train': 0.40912872552871704} 08/31/2021 14:29:46 - INFO - __main__ - Step 139019: {'lr': 6.76210011272535e-06, 'samples': 26691648, 'steps': 139018, 'loss/train': 1.3199610710144043} 08/31/2021 14:29:46 - INFO - __main__ - Step 139020: {'lr': 6.760874261511674e-06, 'samples': 26691840, 'steps': 139019, 'loss/train': 0.03610078990459442} 08/31/2021 14:29:46 - INFO - __main__ - Step 139021: {'lr': 6.759648519897826e-06, 'samples': 26692032, 'steps': 139020, 'loss/train': 0.2475282996892929} 08/31/2021 14:29:48 - INFO - __main__ - Step 139022: {'lr': 6.7584228878843355e-06, 'samples': 26692224, 'steps': 139021, 'loss/train': 1.5778355598449707} 08/31/2021 14:29:48 - INFO - __main__ - Step 139023: {'lr': 6.757197365471729e-06, 'samples': 26692416, 'steps': 139022, 'loss/train': 1.253053069114685} 08/31/2021 14:29:49 - INFO - __main__ - Step 139024: {'lr': 6.755971952660589e-06, 'samples': 26692608, 'steps': 139023, 'loss/train': 1.0084168910980225} 08/31/2021 14:29:49 - INFO - __main__ - Step 139025: {'lr': 6.754746649451443e-06, 'samples': 26692800, 'steps': 139024, 'loss/train': 1.3999650478363037} 08/31/2021 14:29:49 - INFO - __main__ - Step 139026: {'lr': 6.753521455844847e-06, 'samples': 26692992, 'steps': 139025, 'loss/train': 1.1404567956924438} 08/31/2021 14:29:51 - INFO - __main__ - Step 139027: {'lr': 6.752296371841382e-06, 'samples': 26693184, 'steps': 139026, 'loss/train': 0.5014675259590149} 08/31/2021 14:29:51 - INFO - __main__ - Step 139028: {'lr': 6.75107139744155e-06, 'samples': 26693376, 'steps': 139027, 'loss/train': 1.4681434631347656} 08/31/2021 14:29:52 - INFO - __main__ - Step 139029: {'lr': 6.749846532645959e-06, 'samples': 26693568, 'steps': 139028, 'loss/train': 0.6503331065177917} 08/31/2021 14:29:52 - INFO - __main__ - Step 139030: {'lr': 6.7486217774551106e-06, 'samples': 26693760, 'steps': 139029, 'loss/train': 0.8926692008972168} 08/31/2021 14:29:52 - INFO - __main__ - Step 139031: {'lr': 6.747397131869587e-06, 'samples': 26693952, 'steps': 139030, 'loss/train': 0.7304831743240356} 08/31/2021 14:29:53 - INFO - __main__ - Step 139032: {'lr': 6.746172595889943e-06, 'samples': 26694144, 'steps': 139031, 'loss/train': 1.0388445854187012} 08/31/2021 14:29:54 - INFO - __main__ - Step 139033: {'lr': 6.744948169516707e-06, 'samples': 26694336, 'steps': 139032, 'loss/train': 1.7859188318252563} 08/31/2021 14:29:55 - INFO - __main__ - Step 139034: {'lr': 6.743723852750461e-06, 'samples': 26694528, 'steps': 139033, 'loss/train': 1.1074365377426147} 08/31/2021 14:29:55 - INFO - __main__ - Step 139035: {'lr': 6.742499645591732e-06, 'samples': 26694720, 'steps': 139034, 'loss/train': 1.5655033588409424} 08/31/2021 14:29:56 - INFO - __main__ - Step 139036: {'lr': 6.741275548041076e-06, 'samples': 26694912, 'steps': 139035, 'loss/train': 0.026204954832792282} 08/31/2021 14:29:56 - INFO - __main__ - Step 139037: {'lr': 6.7400515600990754e-06, 'samples': 26695104, 'steps': 139036, 'loss/train': 1.5486873388290405} 08/31/2021 14:29:57 - INFO - __main__ - Step 139038: {'lr': 6.738827681766202e-06, 'samples': 26695296, 'steps': 139037, 'loss/train': 0.7654710412025452} 08/31/2021 14:29:58 - INFO - __main__ - Step 139039: {'lr': 6.737603913043094e-06, 'samples': 26695488, 'steps': 139038, 'loss/train': 1.1911606788635254} 08/31/2021 14:29:58 - INFO - __main__ - Step 139040: {'lr': 6.736380253930252e-06, 'samples': 26695680, 'steps': 139039, 'loss/train': 1.1580266952514648} 08/31/2021 14:29:59 - INFO - __main__ - Step 139041: {'lr': 6.735156704428258e-06, 'samples': 26695872, 'steps': 139040, 'loss/train': 1.5004626512527466} 08/31/2021 14:29:59 - INFO - __main__ - Step 139042: {'lr': 6.733933264537639e-06, 'samples': 26696064, 'steps': 139041, 'loss/train': 1.2674285173416138} 08/31/2021 14:30:00 - INFO - __main__ - Step 139043: {'lr': 6.732709934258951e-06, 'samples': 26696256, 'steps': 139042, 'loss/train': 0.38009950518608093} 08/31/2021 14:30:01 - INFO - __main__ - Step 139044: {'lr': 6.73148671359275e-06, 'samples': 26696448, 'steps': 139043, 'loss/train': 1.332216739654541} 08/31/2021 14:30:01 - INFO - __main__ - Step 139045: {'lr': 6.7302636025395884e-06, 'samples': 26696640, 'steps': 139044, 'loss/train': 1.4358479976654053} 08/31/2021 14:30:02 - INFO - __main__ - Step 139046: {'lr': 6.729040601100022e-06, 'samples': 26696832, 'steps': 139045, 'loss/train': 1.0087218284606934} 08/31/2021 14:30:02 - INFO - __main__ - Step 139047: {'lr': 6.727817709274581e-06, 'samples': 26697024, 'steps': 139046, 'loss/train': 0.8206421732902527} 08/31/2021 14:30:03 - INFO - __main__ - Step 139048: {'lr': 6.726594927063845e-06, 'samples': 26697216, 'steps': 139047, 'loss/train': 1.428260326385498} 08/31/2021 14:30:04 - INFO - __main__ - Step 139049: {'lr': 6.725372254468343e-06, 'samples': 26697408, 'steps': 139048, 'loss/train': 0.8535707592964172} 08/31/2021 14:30:04 - INFO - __main__ - Step 139050: {'lr': 6.724149691488657e-06, 'samples': 26697600, 'steps': 139049, 'loss/train': 1.1592776775360107} 08/31/2021 14:30:05 - INFO - __main__ - Step 139051: {'lr': 6.722927238125315e-06, 'samples': 26697792, 'steps': 139050, 'loss/train': 1.5906596183776855} 08/31/2021 14:30:05 - INFO - __main__ - Step 139052: {'lr': 6.721704894378844e-06, 'samples': 26697984, 'steps': 139051, 'loss/train': 1.43123459815979} 08/31/2021 14:30:06 - INFO - __main__ - Step 139053: {'lr': 6.720482660249827e-06, 'samples': 26698176, 'steps': 139052, 'loss/train': 0.8478413820266724} 08/31/2021 14:30:07 - INFO - __main__ - Step 139054: {'lr': 6.719260535738819e-06, 'samples': 26698368, 'steps': 139053, 'loss/train': 0.8880524039268494} 08/31/2021 14:30:07 - INFO - __main__ - Step 139055: {'lr': 6.7180385208463476e-06, 'samples': 26698560, 'steps': 139054, 'loss/train': 1.201198935508728} 08/31/2021 14:30:08 - INFO - __main__ - Step 139056: {'lr': 6.716816615572968e-06, 'samples': 26698752, 'steps': 139055, 'loss/train': 1.3064907789230347} 08/31/2021 14:30:08 - INFO - __main__ - Step 139057: {'lr': 6.715594819919235e-06, 'samples': 26698944, 'steps': 139056, 'loss/train': 0.5411515235900879} 08/31/2021 14:30:08 - INFO - __main__ - Step 139058: {'lr': 6.714373133885704e-06, 'samples': 26699136, 'steps': 139057, 'loss/train': 1.1528592109680176} 08/31/2021 14:30:11 - INFO - __main__ - Step 139059: {'lr': 6.71315155747293e-06, 'samples': 26699328, 'steps': 139058, 'loss/train': 0.6390894651412964} 08/31/2021 14:30:11 - INFO - __main__ - Step 139060: {'lr': 6.7119300906814394e-06, 'samples': 26699520, 'steps': 139059, 'loss/train': 0.5851757526397705} 08/31/2021 14:30:11 - INFO - __main__ - Step 139061: {'lr': 6.7107087335118165e-06, 'samples': 26699712, 'steps': 139060, 'loss/train': 1.1980316638946533} 08/31/2021 14:30:12 - INFO - __main__ - Step 139062: {'lr': 6.7094874859645885e-06, 'samples': 26699904, 'steps': 139061, 'loss/train': 0.39040958881378174} 08/31/2021 14:30:12 - INFO - __main__ - Step 139063: {'lr': 6.7082663480403096e-06, 'samples': 26700096, 'steps': 139062, 'loss/train': 0.026030395179986954} 08/31/2021 14:30:14 - INFO - __main__ - Step 139064: {'lr': 6.707045319739563e-06, 'samples': 26700288, 'steps': 139063, 'loss/train': 0.8393173813819885} 08/31/2021 14:30:14 - INFO - __main__ - Step 139065: {'lr': 6.705824401062821e-06, 'samples': 26700480, 'steps': 139064, 'loss/train': 1.3761703968048096} 08/31/2021 14:30:14 - INFO - __main__ - Step 139066: {'lr': 6.704603592010694e-06, 'samples': 26700672, 'steps': 139065, 'loss/train': 0.6784231066703796} 08/31/2021 14:30:15 - INFO - __main__ - Step 139067: {'lr': 6.703382892583737e-06, 'samples': 26700864, 'steps': 139066, 'loss/train': 0.7347387671470642} 08/31/2021 14:30:15 - INFO - __main__ - Step 139068: {'lr': 6.70216230278245e-06, 'samples': 26701056, 'steps': 139067, 'loss/train': 0.8298860192298889} 08/31/2021 14:30:16 - INFO - __main__ - Step 139069: {'lr': 6.700941822607443e-06, 'samples': 26701248, 'steps': 139068, 'loss/train': 1.0993518829345703} 08/31/2021 14:30:17 - INFO - __main__ - Step 139070: {'lr': 6.699721452059215e-06, 'samples': 26701440, 'steps': 139069, 'loss/train': 1.133954405784607} 08/31/2021 14:30:17 - INFO - __main__ - Step 139071: {'lr': 6.698501191138351e-06, 'samples': 26701632, 'steps': 139070, 'loss/train': 1.0508074760437012} 08/31/2021 14:30:18 - INFO - __main__ - Step 139072: {'lr': 6.697281039845377e-06, 'samples': 26701824, 'steps': 139071, 'loss/train': 1.1071654558181763} 08/31/2021 14:30:18 - INFO - __main__ - Step 139073: {'lr': 6.696060998180875e-06, 'samples': 26702016, 'steps': 139072, 'loss/train': 1.3756072521209717} 08/31/2021 14:30:20 - INFO - __main__ - Step 139074: {'lr': 6.694841066145346e-06, 'samples': 26702208, 'steps': 139073, 'loss/train': 0.17565473914146423} 08/31/2021 14:30:20 - INFO - __main__ - Step 139075: {'lr': 6.693621243739373e-06, 'samples': 26702400, 'steps': 139074, 'loss/train': 0.5230788588523865} 08/31/2021 14:30:21 - INFO - __main__ - Step 139076: {'lr': 6.69240153096351e-06, 'samples': 26702592, 'steps': 139075, 'loss/train': 0.19600491225719452} 08/31/2021 14:30:21 - INFO - __main__ - Step 139077: {'lr': 6.691181927818285e-06, 'samples': 26702784, 'steps': 139076, 'loss/train': 0.41767287254333496} 08/31/2021 14:30:21 - INFO - __main__ - Step 139078: {'lr': 6.689962434304309e-06, 'samples': 26702976, 'steps': 139077, 'loss/train': 0.03570278361439705} 08/31/2021 14:30:23 - INFO - __main__ - Step 139079: {'lr': 6.688743050422025e-06, 'samples': 26703168, 'steps': 139078, 'loss/train': 0.09400489926338196} 08/31/2021 14:30:24 - INFO - __main__ - Step 139080: {'lr': 6.687523776172072e-06, 'samples': 26703360, 'steps': 139079, 'loss/train': 0.4523180425167084} 08/31/2021 14:30:24 - INFO - __main__ - Step 139081: {'lr': 6.6863046115549495e-06, 'samples': 26703552, 'steps': 139080, 'loss/train': 0.8895333409309387} 08/31/2021 14:30:24 - INFO - __main__ - Step 139082: {'lr': 6.685085556571213e-06, 'samples': 26703744, 'steps': 139081, 'loss/train': 1.6368401050567627} 08/31/2021 14:30:25 - INFO - __main__ - Step 139083: {'lr': 6.6838666112214176e-06, 'samples': 26703936, 'steps': 139082, 'loss/train': 1.0855261087417603} 08/31/2021 14:30:26 - INFO - __main__ - Step 139084: {'lr': 6.682647775506146e-06, 'samples': 26704128, 'steps': 139083, 'loss/train': 0.9188898801803589} 08/31/2021 14:30:27 - INFO - __main__ - Step 139085: {'lr': 6.6814290494258965e-06, 'samples': 26704320, 'steps': 139084, 'loss/train': 1.3852448463439941} 08/31/2021 14:30:27 - INFO - __main__ - Step 139086: {'lr': 6.680210432981254e-06, 'samples': 26704512, 'steps': 139085, 'loss/train': 1.777424931526184} 08/31/2021 14:30:27 - INFO - __main__ - Step 139087: {'lr': 6.678991926172745e-06, 'samples': 26704704, 'steps': 139086, 'loss/train': 0.6678133606910706} 08/31/2021 14:30:28 - INFO - __main__ - Step 139088: {'lr': 6.677773529000925e-06, 'samples': 26704896, 'steps': 139087, 'loss/train': 1.0633312463760376} 08/31/2021 14:30:29 - INFO - __main__ - Step 139089: {'lr': 6.676555241466348e-06, 'samples': 26705088, 'steps': 139088, 'loss/train': 1.1863000392913818} 08/31/2021 14:30:30 - INFO - __main__ - Step 139090: {'lr': 6.67533706356957e-06, 'samples': 26705280, 'steps': 139089, 'loss/train': 1.6911002397537231} 08/31/2021 14:30:30 - INFO - __main__ - Step 139091: {'lr': 6.674118995311146e-06, 'samples': 26705472, 'steps': 139090, 'loss/train': 1.238685131072998} 08/31/2021 14:30:30 - INFO - __main__ - Step 139092: {'lr': 6.672901036691575e-06, 'samples': 26705664, 'steps': 139091, 'loss/train': 1.3195509910583496} 08/31/2021 14:30:31 - INFO - __main__ - Step 139093: {'lr': 6.671683187711469e-06, 'samples': 26705856, 'steps': 139092, 'loss/train': 0.5135192275047302} 08/31/2021 14:30:31 - INFO - __main__ - Step 139094: {'lr': 6.6704654483713265e-06, 'samples': 26706048, 'steps': 139093, 'loss/train': 0.7140141129493713} 08/31/2021 14:30:33 - INFO - __main__ - Step 139095: {'lr': 6.669247818671731e-06, 'samples': 26706240, 'steps': 139094, 'loss/train': 0.9705938100814819} 08/31/2021 14:30:33 - INFO - __main__ - Step 139096: {'lr': 6.6680302986132094e-06, 'samples': 26706432, 'steps': 139095, 'loss/train': 0.0289053525775671} 08/31/2021 14:30:34 - INFO - __main__ - Step 139097: {'lr': 6.666812888196316e-06, 'samples': 26706624, 'steps': 139096, 'loss/train': 1.3025660514831543} 08/31/2021 14:30:34 - INFO - __main__ - Step 139098: {'lr': 6.6655955874215805e-06, 'samples': 26706816, 'steps': 139097, 'loss/train': 0.9148011803627014} 08/31/2021 14:30:34 - INFO - __main__ - Step 139099: {'lr': 6.664378396289611e-06, 'samples': 26707008, 'steps': 139098, 'loss/train': 1.465965747833252} 08/31/2021 14:30:36 - INFO - __main__ - Step 139100: {'lr': 6.663161314800909e-06, 'samples': 26707200, 'steps': 139099, 'loss/train': 1.1034660339355469} 08/31/2021 14:30:36 - INFO - __main__ - Step 139101: {'lr': 6.661944342956e-06, 'samples': 26707392, 'steps': 139100, 'loss/train': 0.4329516887664795} 08/31/2021 14:30:37 - INFO - __main__ - Step 139102: {'lr': 6.660727480755496e-06, 'samples': 26707584, 'steps': 139101, 'loss/train': 1.511122703552246} 08/31/2021 14:30:37 - INFO - __main__ - Step 139103: {'lr': 6.659510728199897e-06, 'samples': 26707776, 'steps': 139102, 'loss/train': 1.7987194061279297} 08/31/2021 14:30:37 - INFO - __main__ - Step 139104: {'lr': 6.658294085289784e-06, 'samples': 26707968, 'steps': 139103, 'loss/train': 1.2240736484527588} 08/31/2021 14:30:39 - INFO - __main__ - Step 139105: {'lr': 6.657077552025714e-06, 'samples': 26708160, 'steps': 139104, 'loss/train': 1.572882890701294} 08/31/2021 14:30:39 - INFO - __main__ - Step 139106: {'lr': 6.655861128408186e-06, 'samples': 26708352, 'steps': 139105, 'loss/train': 0.5286893844604492} 08/31/2021 14:30:40 - INFO - __main__ - Step 139107: {'lr': 6.654644814437755e-06, 'samples': 26708544, 'steps': 139106, 'loss/train': 0.7946187853813171} 08/31/2021 14:30:40 - INFO - __main__ - Step 139108: {'lr': 6.653428610114975e-06, 'samples': 26708736, 'steps': 139107, 'loss/train': 0.9462073445320129} 08/31/2021 14:30:40 - INFO - __main__ - Step 139109: {'lr': 6.652212515440431e-06, 'samples': 26708928, 'steps': 139108, 'loss/train': 0.5977848768234253} 08/31/2021 14:30:42 - INFO - __main__ - Step 139110: {'lr': 6.650996530414649e-06, 'samples': 26709120, 'steps': 139109, 'loss/train': 1.5318280458450317} 08/31/2021 14:30:43 - INFO - __main__ - Step 139111: {'lr': 6.649780655038156e-06, 'samples': 26709312, 'steps': 139110, 'loss/train': 1.0313804149627686} 08/31/2021 14:30:43 - INFO - __main__ - Step 139112: {'lr': 6.648564889311509e-06, 'samples': 26709504, 'steps': 139111, 'loss/train': 1.0542943477630615} 08/31/2021 14:30:43 - INFO - __main__ - Step 139113: {'lr': 6.647349233235289e-06, 'samples': 26709696, 'steps': 139112, 'loss/train': 0.9020636677742004} 08/31/2021 14:30:44 - INFO - __main__ - Step 139114: {'lr': 6.646133686809997e-06, 'samples': 26709888, 'steps': 139113, 'loss/train': 0.9577293992042542} 08/31/2021 14:30:46 - INFO - __main__ - Step 139115: {'lr': 6.644918250036214e-06, 'samples': 26710080, 'steps': 139114, 'loss/train': 0.9929835796356201} 08/31/2021 14:30:46 - INFO - __main__ - Step 139116: {'lr': 6.6437029229144684e-06, 'samples': 26710272, 'steps': 139115, 'loss/train': 0.9738484025001526} 08/31/2021 14:30:46 - INFO - __main__ - Step 139117: {'lr': 6.642487705445344e-06, 'samples': 26710464, 'steps': 139116, 'loss/train': 1.0905908346176147} 08/31/2021 14:30:47 - INFO - __main__ - Step 139118: {'lr': 6.6412725976293386e-06, 'samples': 26710656, 'steps': 139117, 'loss/train': 0.21954357624053955} 08/31/2021 14:30:47 - INFO - __main__ - Step 139119: {'lr': 6.640057599467036e-06, 'samples': 26710848, 'steps': 139118, 'loss/train': 1.0575295686721802} 08/31/2021 14:30:47 - INFO - __main__ - Step 139120: {'lr': 6.638842710958937e-06, 'samples': 26711040, 'steps': 139119, 'loss/train': 1.4283167123794556} 08/31/2021 14:30:49 - INFO - __main__ - Step 139121: {'lr': 6.637627932105622e-06, 'samples': 26711232, 'steps': 139120, 'loss/train': 1.290663480758667} 08/31/2021 14:30:49 - INFO - __main__ - Step 139122: {'lr': 6.636413262907648e-06, 'samples': 26711424, 'steps': 139121, 'loss/train': 1.7404897212982178} 08/31/2021 14:30:50 - INFO - __main__ - Step 139123: {'lr': 6.635198703365569e-06, 'samples': 26711616, 'steps': 139122, 'loss/train': 1.115274429321289} 08/31/2021 14:30:50 - INFO - __main__ - Step 139124: {'lr': 6.6339842534798855e-06, 'samples': 26711808, 'steps': 139123, 'loss/train': 0.9652411937713623} 08/31/2021 14:30:50 - INFO - __main__ - Step 139125: {'lr': 6.63276991325118e-06, 'samples': 26712000, 'steps': 139124, 'loss/train': 1.4454913139343262} 08/31/2021 14:30:52 - INFO - __main__ - Step 139126: {'lr': 6.6315556826800075e-06, 'samples': 26712192, 'steps': 139125, 'loss/train': 1.3097727298736572} 08/31/2021 14:30:52 - INFO - __main__ - Step 139127: {'lr': 6.630341561766867e-06, 'samples': 26712384, 'steps': 139126, 'loss/train': 0.7987436652183533} 08/31/2021 14:30:53 - INFO - __main__ - Step 139128: {'lr': 6.629127550512398e-06, 'samples': 26712576, 'steps': 139127, 'loss/train': 1.1463207006454468} 08/31/2021 14:30:53 - INFO - __main__ - Step 139129: {'lr': 6.6279136489170445e-06, 'samples': 26712768, 'steps': 139128, 'loss/train': 1.4150495529174805} 08/31/2021 14:30:53 - INFO - __main__ - Step 139130: {'lr': 6.626699856981416e-06, 'samples': 26712960, 'steps': 139129, 'loss/train': 0.883536159992218} 08/31/2021 14:30:55 - INFO - __main__ - Step 139131: {'lr': 6.625486174706013e-06, 'samples': 26713152, 'steps': 139130, 'loss/train': 1.1319547891616821} 08/31/2021 14:30:56 - INFO - __main__ - Step 139132: {'lr': 6.624272602091447e-06, 'samples': 26713344, 'steps': 139131, 'loss/train': 0.9007326364517212} 08/31/2021 14:30:56 - INFO - __main__ - Step 139133: {'lr': 6.623059139138188e-06, 'samples': 26713536, 'steps': 139132, 'loss/train': 0.027170835062861443} 08/31/2021 14:30:56 - INFO - __main__ - Step 139134: {'lr': 6.621845785846848e-06, 'samples': 26713728, 'steps': 139133, 'loss/train': 0.09946437180042267} 08/31/2021 14:30:57 - INFO - __main__ - Step 139135: {'lr': 6.620632542217953e-06, 'samples': 26713920, 'steps': 139134, 'loss/train': 1.6180633306503296} 08/31/2021 14:30:57 - INFO - __main__ - Step 139136: {'lr': 6.619419408252031e-06, 'samples': 26714112, 'steps': 139135, 'loss/train': 0.7680373787879944} 08/31/2021 14:30:59 - INFO - __main__ - Step 139137: {'lr': 6.618206383949638e-06, 'samples': 26714304, 'steps': 139136, 'loss/train': 1.2013660669326782} 08/31/2021 14:30:59 - INFO - __main__ - Step 139138: {'lr': 6.616993469311355e-06, 'samples': 26714496, 'steps': 139137, 'loss/train': 0.8997955918312073} 08/31/2021 14:30:59 - INFO - __main__ - Step 139139: {'lr': 6.615780664337684e-06, 'samples': 26714688, 'steps': 139138, 'loss/train': 0.5804420113563538} 08/31/2021 14:31:00 - INFO - __main__ - Step 139140: {'lr': 6.614567969029206e-06, 'samples': 26714880, 'steps': 139139, 'loss/train': 1.1082361936569214} 08/31/2021 14:31:00 - INFO - __main__ - Step 139141: {'lr': 6.613355383386421e-06, 'samples': 26715072, 'steps': 139140, 'loss/train': 0.9803168773651123} 08/31/2021 14:31:02 - INFO - __main__ - Step 139142: {'lr': 6.612142907409885e-06, 'samples': 26715264, 'steps': 139141, 'loss/train': 0.8796402812004089} 08/31/2021 14:31:02 - INFO - __main__ - Step 139143: {'lr': 6.610930541100208e-06, 'samples': 26715456, 'steps': 139142, 'loss/train': 0.8041626811027527} 08/31/2021 14:31:03 - INFO - __main__ - Step 139144: {'lr': 6.6097182844578605e-06, 'samples': 26715648, 'steps': 139143, 'loss/train': 1.2288471460342407} 08/31/2021 14:31:03 - INFO - __main__ - Step 139145: {'lr': 6.6085061374834e-06, 'samples': 26715840, 'steps': 139144, 'loss/train': 1.2050963640213013} 08/31/2021 14:31:03 - INFO - __main__ - Step 139146: {'lr': 6.607294100177435e-06, 'samples': 26716032, 'steps': 139145, 'loss/train': 0.8881586790084839} 08/31/2021 14:31:05 - INFO - __main__ - Step 139147: {'lr': 6.6060821725404395e-06, 'samples': 26716224, 'steps': 139146, 'loss/train': 0.9967622756958008} 08/31/2021 14:31:06 - INFO - __main__ - Step 139148: {'lr': 6.604870354572995e-06, 'samples': 26716416, 'steps': 139147, 'loss/train': 0.9484602212905884} 08/31/2021 14:31:06 - INFO - __main__ - Step 139149: {'lr': 6.603658646275629e-06, 'samples': 26716608, 'steps': 139148, 'loss/train': 0.5129095911979675} 08/31/2021 14:31:06 - INFO - __main__ - Step 139150: {'lr': 6.6024470476489515e-06, 'samples': 26716800, 'steps': 139149, 'loss/train': 0.18417267501354218} 08/31/2021 14:31:07 - INFO - __main__ - Step 139151: {'lr': 6.601235558693408e-06, 'samples': 26716992, 'steps': 139150, 'loss/train': 0.39086663722991943} 08/31/2021 14:31:08 - INFO - __main__ - Step 139152: {'lr': 6.60002417940958e-06, 'samples': 26717184, 'steps': 139151, 'loss/train': 1.3216906785964966} 08/31/2021 14:31:09 - INFO - __main__ - Step 139153: {'lr': 6.598812909798052e-06, 'samples': 26717376, 'steps': 139152, 'loss/train': 1.2634971141815186} 08/31/2021 14:31:09 - INFO - __main__ - Step 139154: {'lr': 6.597601749859322e-06, 'samples': 26717568, 'steps': 139153, 'loss/train': 1.8744926452636719} 08/31/2021 14:31:09 - INFO - __main__ - Step 139155: {'lr': 6.596390699593974e-06, 'samples': 26717760, 'steps': 139154, 'loss/train': 1.1087775230407715} 08/31/2021 14:31:10 - INFO - __main__ - Step 139156: {'lr': 6.595179759002534e-06, 'samples': 26717952, 'steps': 139155, 'loss/train': 0.6512233018875122} 08/31/2021 14:31:11 - INFO - __main__ - Step 139157: {'lr': 6.593968928085531e-06, 'samples': 26718144, 'steps': 139156, 'loss/train': 1.010809063911438} 08/31/2021 14:31:12 - INFO - __main__ - Step 139158: {'lr': 6.592758206843547e-06, 'samples': 26718336, 'steps': 139157, 'loss/train': 0.847840428352356} 08/31/2021 14:31:12 - INFO - __main__ - Step 139159: {'lr': 6.591547595277109e-06, 'samples': 26718528, 'steps': 139158, 'loss/train': 0.8758864402770996} 08/31/2021 14:31:13 - INFO - __main__ - Step 139160: {'lr': 6.590337093386772e-06, 'samples': 26718720, 'steps': 139159, 'loss/train': 0.025207437574863434} 08/31/2021 14:31:13 - INFO - __main__ - Step 139161: {'lr': 6.589126701173092e-06, 'samples': 26718912, 'steps': 139160, 'loss/train': 1.4085159301757812} 08/31/2021 14:31:14 - INFO - __main__ - Step 139162: {'lr': 6.587916418636569e-06, 'samples': 26719104, 'steps': 139161, 'loss/train': 1.1294512748718262} 08/31/2021 14:31:15 - INFO - __main__ - Step 139163: {'lr': 6.586706245777757e-06, 'samples': 26719296, 'steps': 139162, 'loss/train': 0.8963776230812073} 08/31/2021 14:31:15 - INFO - __main__ - Step 139164: {'lr': 6.585496182597239e-06, 'samples': 26719488, 'steps': 139163, 'loss/train': 0.4597149193286896} 08/31/2021 14:31:15 - INFO - __main__ - Step 139165: {'lr': 6.584286229095543e-06, 'samples': 26719680, 'steps': 139164, 'loss/train': 0.7706853747367859} 08/31/2021 14:31:16 - INFO - __main__ - Step 139166: {'lr': 6.583076385273196e-06, 'samples': 26719872, 'steps': 139165, 'loss/train': 1.2363461256027222} 08/31/2021 14:31:18 - INFO - __main__ - Step 139167: {'lr': 6.58186665113078e-06, 'samples': 26720064, 'steps': 139166, 'loss/train': 1.3324637413024902} 08/31/2021 14:31:18 - INFO - __main__ - Step 139168: {'lr': 6.580657026668796e-06, 'samples': 26720256, 'steps': 139167, 'loss/train': 1.268115520477295} 08/31/2021 14:31:19 - INFO - __main__ - Step 139169: {'lr': 6.579447511887826e-06, 'samples': 26720448, 'steps': 139168, 'loss/train': 1.2260358333587646} 08/31/2021 14:31:19 - INFO - __main__ - Step 139170: {'lr': 6.578238106788398e-06, 'samples': 26720640, 'steps': 139169, 'loss/train': 1.466333270072937} 08/31/2021 14:31:19 - INFO - __main__ - Step 139171: {'lr': 6.577028811371039e-06, 'samples': 26720832, 'steps': 139170, 'loss/train': 0.6360644698143005} 08/31/2021 14:31:20 - INFO - __main__ - Step 139172: {'lr': 6.575819625636359e-06, 'samples': 26721024, 'steps': 139171, 'loss/train': 0.7845795750617981} 08/31/2021 14:31:22 - INFO - __main__ - Step 139173: {'lr': 6.574610549584831e-06, 'samples': 26721216, 'steps': 139172, 'loss/train': 0.15688060224056244} 08/31/2021 14:31:22 - INFO - __main__ - Step 139174: {'lr': 6.573401583217037e-06, 'samples': 26721408, 'steps': 139173, 'loss/train': 0.5913125872612} 08/31/2021 14:31:23 - INFO - __main__ - Step 139175: {'lr': 6.572192726533505e-06, 'samples': 26721600, 'steps': 139174, 'loss/train': 0.9484976530075073} 08/31/2021 14:31:23 - INFO - __main__ - Step 139176: {'lr': 6.570983979534789e-06, 'samples': 26721792, 'steps': 139175, 'loss/train': 0.048640765249729156} 08/31/2021 14:31:23 - INFO - __main__ - Step 139177: {'lr': 6.569775342221418e-06, 'samples': 26721984, 'steps': 139176, 'loss/train': 1.4228994846343994} 08/31/2021 14:31:25 - INFO - __main__ - Step 139178: {'lr': 6.568566814593974e-06, 'samples': 26722176, 'steps': 139177, 'loss/train': 1.239703893661499} 08/31/2021 14:31:26 - INFO - __main__ - Step 139179: {'lr': 6.567358396652956e-06, 'samples': 26722368, 'steps': 139178, 'loss/train': 1.3669469356536865} 08/31/2021 14:31:26 - INFO - __main__ - Step 139180: {'lr': 6.5661500883989476e-06, 'samples': 26722560, 'steps': 139179, 'loss/train': 0.13074655830860138} 08/31/2021 14:31:26 - INFO - __main__ - Step 139181: {'lr': 6.564941889832449e-06, 'samples': 26722752, 'steps': 139180, 'loss/train': 0.06306757032871246} 08/31/2021 14:31:27 - INFO - __main__ - Step 139182: {'lr': 6.563733800954069e-06, 'samples': 26722944, 'steps': 139181, 'loss/train': 1.132200837135315} 08/31/2021 14:31:28 - INFO - __main__ - Step 139183: {'lr': 6.562525821764281e-06, 'samples': 26723136, 'steps': 139182, 'loss/train': 1.1717151403427124} 08/31/2021 14:31:29 - INFO - __main__ - Step 139184: {'lr': 6.561317952263668e-06, 'samples': 26723328, 'steps': 139183, 'loss/train': 1.177410364151001} 08/31/2021 14:31:29 - INFO - __main__ - Step 139185: {'lr': 6.560110192452812e-06, 'samples': 26723520, 'steps': 139184, 'loss/train': 1.070828914642334} 08/31/2021 14:31:29 - INFO - __main__ - Step 139186: {'lr': 6.5589025423321565e-06, 'samples': 26723712, 'steps': 139185, 'loss/train': 1.3346712589263916} 08/31/2021 14:31:30 - INFO - __main__ - Step 139187: {'lr': 6.5576950019023415e-06, 'samples': 26723904, 'steps': 139186, 'loss/train': 1.0309566259384155} 08/31/2021 14:31:31 - INFO - __main__ - Step 139188: {'lr': 6.556487571163838e-06, 'samples': 26724096, 'steps': 139187, 'loss/train': 0.8212139010429382} 08/31/2021 14:31:32 - INFO - __main__ - Step 139189: {'lr': 6.555280250117257e-06, 'samples': 26724288, 'steps': 139188, 'loss/train': 0.6593549251556396} 08/31/2021 14:31:32 - INFO - __main__ - Step 139190: {'lr': 6.554073038763097e-06, 'samples': 26724480, 'steps': 139189, 'loss/train': 1.094002366065979} 08/31/2021 14:31:33 - INFO - __main__ - Step 139191: {'lr': 6.552865937101887e-06, 'samples': 26724672, 'steps': 139190, 'loss/train': 1.074099063873291} 08/31/2021 14:31:33 - INFO - __main__ - Step 139192: {'lr': 6.551658945134237e-06, 'samples': 26724864, 'steps': 139191, 'loss/train': 0.03362042084336281} 08/31/2021 14:31:33 - INFO - __main__ - Step 139193: {'lr': 6.550452062860646e-06, 'samples': 26725056, 'steps': 139192, 'loss/train': 0.4304243326187134} 08/31/2021 14:31:35 - INFO - __main__ - Step 139194: {'lr': 6.5492452902816415e-06, 'samples': 26725248, 'steps': 139193, 'loss/train': 0.5359959602355957} 08/31/2021 14:31:35 - INFO - __main__ - Step 139195: {'lr': 6.548038627397807e-06, 'samples': 26725440, 'steps': 139194, 'loss/train': 1.171415090560913} 08/31/2021 14:31:36 - INFO - __main__ - Step 139196: {'lr': 6.5468320742096684e-06, 'samples': 26725632, 'steps': 139195, 'loss/train': 0.7070014476776123} 08/31/2021 14:31:36 - INFO - __main__ - Step 139197: {'lr': 6.545625630717783e-06, 'samples': 26725824, 'steps': 139196, 'loss/train': 0.048267439007759094} 08/31/2021 14:31:36 - INFO - __main__ - Step 139198: {'lr': 6.5444192969226765e-06, 'samples': 26726016, 'steps': 139197, 'loss/train': 0.999333918094635} 08/31/2021 14:31:38 - INFO - __main__ - Step 139199: {'lr': 6.543213072824905e-06, 'samples': 26726208, 'steps': 139198, 'loss/train': 0.8676196336746216} 08/31/2021 14:31:38 - INFO - __main__ - Step 139200: {'lr': 6.542006958424996e-06, 'samples': 26726400, 'steps': 139199, 'loss/train': 1.2926071882247925} 08/31/2021 14:31:39 - INFO - __main__ - Step 139201: {'lr': 6.540800953723502e-06, 'samples': 26726592, 'steps': 139200, 'loss/train': 0.9864500164985657} 08/31/2021 14:31:39 - INFO - __main__ - Step 139202: {'lr': 6.539595058720954e-06, 'samples': 26726784, 'steps': 139201, 'loss/train': 1.488295555114746} 08/31/2021 14:31:39 - INFO - __main__ - Step 139203: {'lr': 6.538389273417933e-06, 'samples': 26726976, 'steps': 139202, 'loss/train': 1.2050691843032837} 08/31/2021 14:31:41 - INFO - __main__ - Step 139204: {'lr': 6.537183597814938e-06, 'samples': 26727168, 'steps': 139203, 'loss/train': 0.861312747001648} 08/31/2021 14:31:41 - INFO - __main__ - Step 139205: {'lr': 6.535978031912526e-06, 'samples': 26727360, 'steps': 139204, 'loss/train': 1.0453752279281616} 08/31/2021 14:31:42 - INFO - __main__ - Step 139206: {'lr': 6.534772575711251e-06, 'samples': 26727552, 'steps': 139205, 'loss/train': 1.3058139085769653} 08/31/2021 14:31:42 - INFO - __main__ - Step 139207: {'lr': 6.53356722921164e-06, 'samples': 26727744, 'steps': 139206, 'loss/train': 1.1407461166381836} 08/31/2021 14:31:42 - INFO - __main__ - Step 139208: {'lr': 6.532361992414277e-06, 'samples': 26727936, 'steps': 139207, 'loss/train': 1.4537463188171387} 08/31/2021 14:31:44 - INFO - __main__ - Step 139209: {'lr': 6.531156865319659e-06, 'samples': 26728128, 'steps': 139208, 'loss/train': 0.13749441504478455} 08/31/2021 14:31:44 - INFO - __main__ - Step 139210: {'lr': 6.529951847928317e-06, 'samples': 26728320, 'steps': 139209, 'loss/train': 2.1633031368255615} 08/31/2021 14:31:45 - INFO - __main__ - Step 139211: {'lr': 6.528746940240859e-06, 'samples': 26728512, 'steps': 139210, 'loss/train': 1.2347002029418945} 08/31/2021 14:31:45 - INFO - __main__ - Step 139212: {'lr': 6.527542142257814e-06, 'samples': 26728704, 'steps': 139211, 'loss/train': 0.7611432075500488} 08/31/2021 14:31:45 - INFO - __main__ - Step 139213: {'lr': 6.526337453979653e-06, 'samples': 26728896, 'steps': 139212, 'loss/train': 1.5265426635742188} 08/31/2021 14:31:46 - INFO - __main__ - Step 139214: {'lr': 6.525132875406986e-06, 'samples': 26729088, 'steps': 139213, 'loss/train': 0.49446702003479004} 08/31/2021 14:31:47 - INFO - __main__ - Step 139215: {'lr': 6.523928406540341e-06, 'samples': 26729280, 'steps': 139214, 'loss/train': 1.2273696660995483} 08/31/2021 14:31:48 - INFO - __main__ - Step 139216: {'lr': 6.5227240473802466e-06, 'samples': 26729472, 'steps': 139215, 'loss/train': 0.33706656098365784} 08/31/2021 14:31:48 - INFO - __main__ - Step 139217: {'lr': 6.521519797927255e-06, 'samples': 26729664, 'steps': 139216, 'loss/train': 1.031734585762024} 08/31/2021 14:31:49 - INFO - __main__ - Step 139218: {'lr': 6.520315658181897e-06, 'samples': 26729856, 'steps': 139217, 'loss/train': 1.262943148612976} 08/31/2021 14:31:49 - INFO - __main__ - Step 139219: {'lr': 6.519111628144753e-06, 'samples': 26730048, 'steps': 139218, 'loss/train': 0.6479405760765076} 08/31/2021 14:31:51 - INFO - __main__ - Step 139220: {'lr': 6.517907707816323e-06, 'samples': 26730240, 'steps': 139219, 'loss/train': 1.1852256059646606} 08/31/2021 14:31:51 - INFO - __main__ - Step 139221: {'lr': 6.516703897197163e-06, 'samples': 26730432, 'steps': 139220, 'loss/train': 1.4919474124908447} 08/31/2021 14:31:51 - INFO - __main__ - Step 139222: {'lr': 6.515500196287827e-06, 'samples': 26730624, 'steps': 139221, 'loss/train': 0.3785085082054138} 08/31/2021 14:31:52 - INFO - __main__ - Step 139223: {'lr': 6.514296605088871e-06, 'samples': 26730816, 'steps': 139222, 'loss/train': 1.3478608131408691} 08/31/2021 14:31:52 - INFO - __main__ - Step 139224: {'lr': 6.513093123600794e-06, 'samples': 26731008, 'steps': 139223, 'loss/train': 1.174433946609497} 08/31/2021 14:31:54 - INFO - __main__ - Step 139225: {'lr': 6.511889751824151e-06, 'samples': 26731200, 'steps': 139224, 'loss/train': 1.1152230501174927} 08/31/2021 14:31:55 - INFO - __main__ - Step 139226: {'lr': 6.510686489759527e-06, 'samples': 26731392, 'steps': 139225, 'loss/train': 0.7849432229995728} 08/31/2021 14:31:55 - INFO - __main__ - Step 139227: {'lr': 6.509483337407418e-06, 'samples': 26731584, 'steps': 139226, 'loss/train': 0.7060101628303528} 08/31/2021 14:31:55 - INFO - __main__ - Step 139228: {'lr': 6.508280294768354e-06, 'samples': 26731776, 'steps': 139227, 'loss/train': 0.6420934796333313} 08/31/2021 14:31:56 - INFO - __main__ - Step 139229: {'lr': 6.507077361842917e-06, 'samples': 26731968, 'steps': 139228, 'loss/train': 1.040677547454834} 08/31/2021 14:31:57 - INFO - __main__ - Step 139230: {'lr': 6.505874538631635e-06, 'samples': 26732160, 'steps': 139229, 'loss/train': 1.5585424900054932} 08/31/2021 14:31:58 - INFO - __main__ - Step 139231: {'lr': 6.5046718251350335e-06, 'samples': 26732352, 'steps': 139230, 'loss/train': 0.9552395939826965} 08/31/2021 14:31:58 - INFO - __main__ - Step 139232: {'lr': 6.503469221353697e-06, 'samples': 26732544, 'steps': 139231, 'loss/train': 1.1271456480026245} 08/31/2021 14:31:59 - INFO - __main__ - Step 139233: {'lr': 6.5022667272881256e-06, 'samples': 26732736, 'steps': 139232, 'loss/train': 0.7989888787269592} 08/31/2021 14:31:59 - INFO - __main__ - Step 139234: {'lr': 6.5010643429388724e-06, 'samples': 26732928, 'steps': 139233, 'loss/train': 1.0690617561340332} 08/31/2021 14:32:00 - INFO - __main__ - Step 139235: {'lr': 6.499862068306495e-06, 'samples': 26733120, 'steps': 139234, 'loss/train': 1.359787106513977} 08/31/2021 14:32:01 - INFO - __main__ - Step 139236: {'lr': 6.49865990339149e-06, 'samples': 26733312, 'steps': 139235, 'loss/train': 1.3463842868804932} 08/31/2021 14:32:01 - INFO - __main__ - Step 139237: {'lr': 6.497457848194472e-06, 'samples': 26733504, 'steps': 139236, 'loss/train': 1.3884787559509277} 08/31/2021 14:32:02 - INFO - __main__ - Step 139238: {'lr': 6.496255902715908e-06, 'samples': 26733696, 'steps': 139237, 'loss/train': 1.2891595363616943} 08/31/2021 14:32:02 - INFO - __main__ - Step 139239: {'lr': 6.495054066956413e-06, 'samples': 26733888, 'steps': 139238, 'loss/train': 1.5993572473526} 08/31/2021 14:32:04 - INFO - __main__ - Step 139240: {'lr': 6.493852340916456e-06, 'samples': 26734080, 'steps': 139239, 'loss/train': 1.3491737842559814} 08/31/2021 14:32:04 - INFO - __main__ - Step 139241: {'lr': 6.492650724596621e-06, 'samples': 26734272, 'steps': 139240, 'loss/train': 1.2138816118240356} 08/31/2021 14:32:04 - INFO - __main__ - Step 139242: {'lr': 6.491449217997436e-06, 'samples': 26734464, 'steps': 139241, 'loss/train': 0.05061035230755806} 08/31/2021 14:32:05 - INFO - __main__ - Step 139243: {'lr': 6.490247821119455e-06, 'samples': 26734656, 'steps': 139242, 'loss/train': 1.2339909076690674} 08/31/2021 14:32:05 - INFO - __main__ - Step 139244: {'lr': 6.489046533963205e-06, 'samples': 26734848, 'steps': 139243, 'loss/train': 0.9452557563781738} 08/31/2021 14:32:05 - INFO - __main__ - Step 139245: {'lr': 6.487845356529243e-06, 'samples': 26735040, 'steps': 139244, 'loss/train': 1.0037871599197388} 08/31/2021 14:32:07 - INFO - __main__ - Step 139246: {'lr': 6.4866442888180945e-06, 'samples': 26735232, 'steps': 139245, 'loss/train': 1.3577289581298828} 08/31/2021 14:32:07 - INFO - __main__ - Step 139247: {'lr': 6.485443330830287e-06, 'samples': 26735424, 'steps': 139246, 'loss/train': 1.2741270065307617} 08/31/2021 14:32:08 - INFO - __main__ - Step 139248: {'lr': 6.484242482566404e-06, 'samples': 26735616, 'steps': 139247, 'loss/train': 1.2116336822509766} 08/31/2021 14:32:08 - INFO - __main__ - Step 139249: {'lr': 6.483041744026946e-06, 'samples': 26735808, 'steps': 139248, 'loss/train': 0.2392917275428772} 08/31/2021 14:32:08 - INFO - __main__ - Step 139250: {'lr': 6.481841115212495e-06, 'samples': 26736000, 'steps': 139249, 'loss/train': 1.5363478660583496} 08/31/2021 14:32:10 - INFO - __main__ - Step 139251: {'lr': 6.48064059612355e-06, 'samples': 26736192, 'steps': 139250, 'loss/train': 0.6081355214118958} 08/31/2021 14:32:10 - INFO - __main__ - Step 139252: {'lr': 6.479440186760693e-06, 'samples': 26736384, 'steps': 139251, 'loss/train': 0.7464918494224548} 08/31/2021 14:32:11 - INFO - __main__ - Step 139253: {'lr': 6.478239887124426e-06, 'samples': 26736576, 'steps': 139252, 'loss/train': 1.0082769393920898} 08/31/2021 14:32:11 - INFO - __main__ - Step 139254: {'lr': 6.477039697215331e-06, 'samples': 26736768, 'steps': 139253, 'loss/train': 0.5049746632575989} 08/31/2021 14:32:11 - INFO - __main__ - Step 139255: {'lr': 6.4758396170338796e-06, 'samples': 26736960, 'steps': 139254, 'loss/train': 1.4682265520095825} 08/31/2021 14:32:13 - INFO - __main__ - Step 139256: {'lr': 6.4746396465806824e-06, 'samples': 26737152, 'steps': 139255, 'loss/train': 0.40450528264045715} 08/31/2021 14:32:13 - INFO - __main__ - Step 139257: {'lr': 6.473439785856239e-06, 'samples': 26737344, 'steps': 139256, 'loss/train': 0.7997118234634399} 08/31/2021 14:32:14 - INFO - __main__ - Step 139258: {'lr': 6.4722400348611325e-06, 'samples': 26737536, 'steps': 139257, 'loss/train': 0.974622905254364} 08/31/2021 14:32:14 - INFO - __main__ - Step 139259: {'lr': 6.471040393595862e-06, 'samples': 26737728, 'steps': 139258, 'loss/train': 1.5042880773544312} 08/31/2021 14:32:14 - INFO - __main__ - Step 139260: {'lr': 6.469840862060983e-06, 'samples': 26737920, 'steps': 139259, 'loss/train': 1.1723604202270508} 08/31/2021 14:32:16 - INFO - __main__ - Step 139261: {'lr': 6.468641440257023e-06, 'samples': 26738112, 'steps': 139260, 'loss/train': 1.34219491481781} 08/31/2021 14:32:16 - INFO - __main__ - Step 139262: {'lr': 6.467442128184537e-06, 'samples': 26738304, 'steps': 139261, 'loss/train': 0.3754975497722626} 08/31/2021 14:32:17 - INFO - __main__ - Step 139263: {'lr': 6.466242925844079e-06, 'samples': 26738496, 'steps': 139262, 'loss/train': 2.2911343574523926} 08/31/2021 14:32:17 - INFO - __main__ - Step 139264: {'lr': 6.465043833236178e-06, 'samples': 26738688, 'steps': 139263, 'loss/train': 0.9274251461029053} 08/31/2021 14:32:17 - INFO - __main__ - Step 139265: {'lr': 6.463844850361361e-06, 'samples': 26738880, 'steps': 139264, 'loss/train': 1.2062979936599731} 08/31/2021 14:32:19 - INFO - __main__ - Step 139266: {'lr': 6.462645977220183e-06, 'samples': 26739072, 'steps': 139265, 'loss/train': 1.183780550956726} 08/31/2021 14:32:19 - INFO - __main__ - Step 139267: {'lr': 6.461447213813171e-06, 'samples': 26739264, 'steps': 139266, 'loss/train': 1.0082979202270508} 08/31/2021 14:32:20 - INFO - __main__ - Step 139268: {'lr': 6.46024856014088e-06, 'samples': 26739456, 'steps': 139267, 'loss/train': 0.6387254595756531} 08/31/2021 14:32:20 - INFO - __main__ - Step 139269: {'lr': 6.459050016203838e-06, 'samples': 26739648, 'steps': 139268, 'loss/train': 1.7082850933074951} 08/31/2021 14:32:20 - INFO - __main__ - Step 139270: {'lr': 6.4578515820026e-06, 'samples': 26739840, 'steps': 139269, 'loss/train': 1.356748342514038} 08/31/2021 14:32:22 - INFO - __main__ - Step 139271: {'lr': 6.456653257537665e-06, 'samples': 26740032, 'steps': 139270, 'loss/train': 1.1653194427490234} 08/31/2021 14:32:22 - INFO - __main__ - Step 139272: {'lr': 6.455455042809644e-06, 'samples': 26740224, 'steps': 139271, 'loss/train': 1.1803581714630127} 08/31/2021 14:32:22 - INFO - __main__ - Step 139273: {'lr': 6.454256937819008e-06, 'samples': 26740416, 'steps': 139272, 'loss/train': 1.0304783582687378} 08/31/2021 14:32:23 - INFO - __main__ - Step 139274: {'lr': 6.453058942566342e-06, 'samples': 26740608, 'steps': 139273, 'loss/train': 1.3848479986190796} 08/31/2021 14:32:23 - INFO - __main__ - Step 139275: {'lr': 6.451861057052144e-06, 'samples': 26740800, 'steps': 139274, 'loss/train': 1.2720966339111328} 08/31/2021 14:32:25 - INFO - __main__ - Step 139276: {'lr': 6.450663281276998e-06, 'samples': 26740992, 'steps': 139275, 'loss/train': 0.9266427755355835} 08/31/2021 14:32:26 - INFO - __main__ - Step 139277: {'lr': 6.449465615241429e-06, 'samples': 26741184, 'steps': 139276, 'loss/train': 1.0193809270858765} 08/31/2021 14:32:26 - INFO - __main__ - Step 139278: {'lr': 6.448268058945966e-06, 'samples': 26741376, 'steps': 139277, 'loss/train': 0.40721073746681213} 08/31/2021 14:32:26 - INFO - __main__ - Step 139279: {'lr': 6.447070612391193e-06, 'samples': 26741568, 'steps': 139278, 'loss/train': 1.6145130395889282} 08/31/2021 14:32:27 - INFO - __main__ - Step 139280: {'lr': 6.445873275577579e-06, 'samples': 26741760, 'steps': 139279, 'loss/train': 0.7923330664634705} 08/31/2021 14:32:28 - INFO - __main__ - Step 139281: {'lr': 6.444676048505682e-06, 'samples': 26741952, 'steps': 139280, 'loss/train': 0.9166936278343201} 08/31/2021 14:32:29 - INFO - __main__ - Step 139282: {'lr': 6.443478931176056e-06, 'samples': 26742144, 'steps': 139281, 'loss/train': 0.5108067393302917} 08/31/2021 14:32:29 - INFO - __main__ - Step 139283: {'lr': 6.442281923589255e-06, 'samples': 26742336, 'steps': 139282, 'loss/train': 1.2609775066375732} 08/31/2021 14:32:29 - INFO - __main__ - Step 139284: {'lr': 6.441085025745808e-06, 'samples': 26742528, 'steps': 139283, 'loss/train': 0.8505327701568604} 08/31/2021 14:32:30 - INFO - __main__ - Step 139285: {'lr': 6.439888237646241e-06, 'samples': 26742720, 'steps': 139284, 'loss/train': 1.0050523281097412} 08/31/2021 14:32:30 - INFO - __main__ - Step 139286: {'lr': 6.43869155929111e-06, 'samples': 26742912, 'steps': 139285, 'loss/train': 1.2173759937286377} 08/31/2021 14:32:32 - INFO - __main__ - Step 139287: {'lr': 6.437494990680914e-06, 'samples': 26743104, 'steps': 139286, 'loss/train': 0.7634545564651489} 08/31/2021 14:32:32 - INFO - __main__ - Step 139288: {'lr': 6.436298531816265e-06, 'samples': 26743296, 'steps': 139287, 'loss/train': 0.8966201543807983} 08/31/2021 14:32:33 - INFO - __main__ - Step 139289: {'lr': 6.435102182697633e-06, 'samples': 26743488, 'steps': 139288, 'loss/train': 1.2612282037734985} 08/31/2021 14:32:33 - INFO - __main__ - Step 139290: {'lr': 6.4339059433256016e-06, 'samples': 26743680, 'steps': 139289, 'loss/train': 1.1658707857131958} 08/31/2021 14:32:33 - INFO - __main__ - Step 139291: {'lr': 6.432709813700699e-06, 'samples': 26743872, 'steps': 139290, 'loss/train': 0.533839762210846} 08/31/2021 14:32:35 - INFO - __main__ - Step 139292: {'lr': 6.431513793823451e-06, 'samples': 26744064, 'steps': 139291, 'loss/train': 0.4994293749332428} 08/31/2021 14:32:36 - INFO - __main__ - Step 139293: {'lr': 6.430317883694414e-06, 'samples': 26744256, 'steps': 139292, 'loss/train': 0.8652742505073547} 08/31/2021 14:32:36 - INFO - __main__ - Step 139294: {'lr': 6.429122083314115e-06, 'samples': 26744448, 'steps': 139293, 'loss/train': 0.2023274302482605} 08/31/2021 14:32:36 - INFO - __main__ - Step 139295: {'lr': 6.427926392683081e-06, 'samples': 26744640, 'steps': 139294, 'loss/train': 1.0307241678237915} 08/31/2021 14:32:37 - INFO - __main__ - Step 139296: {'lr': 6.426730811801867e-06, 'samples': 26744832, 'steps': 139295, 'loss/train': 1.132683277130127} 08/31/2021 14:32:39 - INFO - __main__ - Step 139297: {'lr': 6.425535340671001e-06, 'samples': 26745024, 'steps': 139296, 'loss/train': 0.518104612827301} 08/31/2021 14:32:39 - INFO - __main__ - Step 139298: {'lr': 6.424339979291066e-06, 'samples': 26745216, 'steps': 139297, 'loss/train': 1.1901577711105347} 08/31/2021 14:32:39 - INFO - __main__ - Step 139299: {'lr': 6.423144727662534e-06, 'samples': 26745408, 'steps': 139298, 'loss/train': 0.09378725290298462} 08/31/2021 14:32:40 - INFO - __main__ - Step 139300: {'lr': 6.421949585785986e-06, 'samples': 26745600, 'steps': 139299, 'loss/train': 1.261289358139038} 08/31/2021 14:32:40 - INFO - __main__ - Step 139301: {'lr': 6.4207545536619226e-06, 'samples': 26745792, 'steps': 139300, 'loss/train': 1.3139344453811646} 08/31/2021 14:32:42 - INFO - __main__ - Step 139302: {'lr': 6.419559631290928e-06, 'samples': 26745984, 'steps': 139301, 'loss/train': 1.0524662733078003} 08/31/2021 14:32:42 - INFO - __main__ - Step 139303: {'lr': 6.418364818673528e-06, 'samples': 26746176, 'steps': 139302, 'loss/train': 1.1747429370880127} 08/31/2021 14:32:42 - INFO - __main__ - Step 139304: {'lr': 6.41717011581025e-06, 'samples': 26746368, 'steps': 139303, 'loss/train': 0.036813415586948395} 08/31/2021 14:32:43 - INFO - __main__ - Step 139305: {'lr': 6.41597552270165e-06, 'samples': 26746560, 'steps': 139304, 'loss/train': 1.2171268463134766} 08/31/2021 14:32:43 - INFO - __main__ - Step 139306: {'lr': 6.414781039348255e-06, 'samples': 26746752, 'steps': 139305, 'loss/train': 0.4168711006641388} 08/31/2021 14:32:45 - INFO - __main__ - Step 139307: {'lr': 6.4135866657505924e-06, 'samples': 26746944, 'steps': 139306, 'loss/train': 1.1910254955291748} 08/31/2021 14:32:45 - INFO - __main__ - Step 139308: {'lr': 6.4123924019091896e-06, 'samples': 26747136, 'steps': 139307, 'loss/train': 0.7698339223861694} 08/31/2021 14:32:45 - INFO - __main__ - Step 139309: {'lr': 6.411198247824601e-06, 'samples': 26747328, 'steps': 139308, 'loss/train': 0.8153820633888245} 08/31/2021 14:32:46 - INFO - __main__ - Step 139310: {'lr': 6.4100042034973825e-06, 'samples': 26747520, 'steps': 139309, 'loss/train': 0.11453018337488174} 08/31/2021 14:32:46 - INFO - __main__ - Step 139311: {'lr': 6.408810268928062e-06, 'samples': 26747712, 'steps': 139310, 'loss/train': 1.629675030708313} 08/31/2021 14:32:46 - INFO - __main__ - Step 139312: {'lr': 6.407616444117164e-06, 'samples': 26747904, 'steps': 139311, 'loss/train': 0.991097629070282} 08/31/2021 14:32:48 - INFO - __main__ - Step 139313: {'lr': 6.406422729065248e-06, 'samples': 26748096, 'steps': 139312, 'loss/train': 0.5773939490318298} 08/31/2021 14:32:49 - INFO - __main__ - Step 139314: {'lr': 6.405229123772838e-06, 'samples': 26748288, 'steps': 139313, 'loss/train': 0.7023086547851562} 08/31/2021 14:32:49 - INFO - __main__ - Step 139315: {'lr': 6.4040356282404626e-06, 'samples': 26748480, 'steps': 139314, 'loss/train': 1.1717383861541748} 08/31/2021 14:32:49 - INFO - __main__ - Step 139316: {'lr': 6.4028422424686486e-06, 'samples': 26748672, 'steps': 139315, 'loss/train': 0.9747976660728455} 08/31/2021 14:32:50 - INFO - __main__ - Step 139317: {'lr': 6.4016489664579795e-06, 'samples': 26748864, 'steps': 139316, 'loss/train': 0.2982194125652313} 08/31/2021 14:32:51 - INFO - __main__ - Step 139318: {'lr': 6.400455800208982e-06, 'samples': 26749056, 'steps': 139317, 'loss/train': 1.3247014284133911} 08/31/2021 14:32:52 - INFO - __main__ - Step 139319: {'lr': 6.3992627437221565e-06, 'samples': 26749248, 'steps': 139318, 'loss/train': 0.7088077068328857} 08/31/2021 14:32:52 - INFO - __main__ - Step 139320: {'lr': 6.398069796998113e-06, 'samples': 26749440, 'steps': 139319, 'loss/train': 0.8076863288879395} 08/31/2021 14:32:52 - INFO - __main__ - Step 139321: {'lr': 6.396876960037296e-06, 'samples': 26749632, 'steps': 139320, 'loss/train': 0.5257509350776672} 08/31/2021 14:32:53 - INFO - __main__ - Step 139322: {'lr': 6.395684232840287e-06, 'samples': 26749824, 'steps': 139321, 'loss/train': 1.6122734546661377} 08/31/2021 14:32:53 - INFO - __main__ - Step 139323: {'lr': 6.394491615407616e-06, 'samples': 26750016, 'steps': 139322, 'loss/train': 0.9481139779090881} 08/31/2021 14:32:55 - INFO - __main__ - Step 139324: {'lr': 6.393299107739836e-06, 'samples': 26750208, 'steps': 139323, 'loss/train': 1.2285001277923584} 08/31/2021 14:32:55 - INFO - __main__ - Step 139325: {'lr': 6.392106709837475e-06, 'samples': 26750400, 'steps': 139324, 'loss/train': 0.9981048703193665} 08/31/2021 14:32:55 - INFO - __main__ - Step 139326: {'lr': 6.390914421701088e-06, 'samples': 26750592, 'steps': 139325, 'loss/train': 0.4479418098926544} 08/31/2021 14:32:56 - INFO - __main__ - Step 139327: {'lr': 6.389722243331175e-06, 'samples': 26750784, 'steps': 139326, 'loss/train': 1.4598931074142456} 08/31/2021 14:32:56 - INFO - __main__ - Step 139328: {'lr': 6.388530174728319e-06, 'samples': 26750976, 'steps': 139327, 'loss/train': 1.1121782064437866} 08/31/2021 14:32:58 - INFO - __main__ - Step 139329: {'lr': 6.387338215893018e-06, 'samples': 26751168, 'steps': 139328, 'loss/train': 0.7412741184234619} 08/31/2021 14:32:58 - INFO - __main__ - Step 139330: {'lr': 6.386146366825829e-06, 'samples': 26751360, 'steps': 139329, 'loss/train': 1.0293928384780884} 08/31/2021 14:32:58 - INFO - __main__ - Step 139331: {'lr': 6.384954627527251e-06, 'samples': 26751552, 'steps': 139330, 'loss/train': 1.263713002204895} 08/31/2021 14:32:59 - INFO - __main__ - Step 139332: {'lr': 6.383762997997894e-06, 'samples': 26751744, 'steps': 139331, 'loss/train': 0.9585579633712769} 08/31/2021 14:32:59 - INFO - __main__ - Step 139333: {'lr': 6.382571478238258e-06, 'samples': 26751936, 'steps': 139332, 'loss/train': 1.2118829488754272} 08/31/2021 14:33:00 - INFO - __main__ - Step 139334: {'lr': 6.381380068248844e-06, 'samples': 26752128, 'steps': 139333, 'loss/train': 1.1831567287445068} 08/31/2021 14:33:02 - INFO - __main__ - Step 139335: {'lr': 6.380188768030232e-06, 'samples': 26752320, 'steps': 139334, 'loss/train': 1.4099911451339722} 08/31/2021 14:33:02 - INFO - __main__ - Step 139336: {'lr': 6.378997577582951e-06, 'samples': 26752512, 'steps': 139335, 'loss/train': 0.32820484042167664} 08/31/2021 14:33:02 - INFO - __main__ - Step 139337: {'lr': 6.377806496907557e-06, 'samples': 26752704, 'steps': 139336, 'loss/train': 0.7171931266784668} 08/31/2021 14:33:03 - INFO - __main__ - Step 139338: {'lr': 6.37661552600452e-06, 'samples': 26752896, 'steps': 139337, 'loss/train': 0.7828531861305237} 08/31/2021 14:33:03 - INFO - __main__ - Step 139339: {'lr': 6.375424664874452e-06, 'samples': 26753088, 'steps': 139338, 'loss/train': 0.11231783032417297} 08/31/2021 14:33:04 - INFO - __main__ - Step 139340: {'lr': 6.374233913517852e-06, 'samples': 26753280, 'steps': 139339, 'loss/train': 1.3013464212417603} 08/31/2021 14:33:05 - INFO - __main__ - Step 139341: {'lr': 6.373043271935247e-06, 'samples': 26753472, 'steps': 139340, 'loss/train': 0.9579190611839294} 08/31/2021 14:33:05 - INFO - __main__ - Step 139342: {'lr': 6.371852740127193e-06, 'samples': 26753664, 'steps': 139341, 'loss/train': 0.12222950160503387} 08/31/2021 14:33:06 - INFO - __main__ - Step 139343: {'lr': 6.370662318094245e-06, 'samples': 26753856, 'steps': 139342, 'loss/train': 0.12061429023742676} 08/31/2021 14:33:06 - INFO - __main__ - Step 139344: {'lr': 6.369472005836901e-06, 'samples': 26754048, 'steps': 139343, 'loss/train': 1.3763256072998047} 08/31/2021 14:33:07 - INFO - __main__ - Step 139345: {'lr': 6.368281803355691e-06, 'samples': 26754240, 'steps': 139344, 'loss/train': 1.124755620956421} 08/31/2021 14:33:08 - INFO - __main__ - Step 139346: {'lr': 6.367091710651196e-06, 'samples': 26754432, 'steps': 139345, 'loss/train': 1.0525505542755127} 08/31/2021 14:33:08 - INFO - __main__ - Step 139347: {'lr': 6.365901727723972e-06, 'samples': 26754624, 'steps': 139346, 'loss/train': 1.3476362228393555} 08/31/2021 14:33:09 - INFO - __main__ - Step 139348: {'lr': 6.364711854574462e-06, 'samples': 26754816, 'steps': 139347, 'loss/train': 1.493388295173645} 08/31/2021 14:33:09 - INFO - __main__ - Step 139349: {'lr': 6.363522091203278e-06, 'samples': 26755008, 'steps': 139348, 'loss/train': 0.4639783501625061} 08/31/2021 14:33:11 - INFO - __main__ - Step 139350: {'lr': 6.362332437610918e-06, 'samples': 26755200, 'steps': 139349, 'loss/train': 0.03461616858839989} 08/31/2021 14:33:11 - INFO - __main__ - Step 139351: {'lr': 6.361142893797911e-06, 'samples': 26755392, 'steps': 139350, 'loss/train': 1.2846721410751343} 08/31/2021 14:33:11 - INFO - __main__ - Step 139352: {'lr': 6.359953459764839e-06, 'samples': 26755584, 'steps': 139351, 'loss/train': 1.019521713256836} 08/31/2021 14:33:12 - INFO - __main__ - Step 139353: {'lr': 6.358764135512202e-06, 'samples': 26755776, 'steps': 139352, 'loss/train': 0.9887486100196838} 08/31/2021 14:33:12 - INFO - __main__ - Step 139354: {'lr': 6.357574921040554e-06, 'samples': 26755968, 'steps': 139353, 'loss/train': 1.184550404548645} 08/31/2021 14:33:14 - INFO - __main__ - Step 139355: {'lr': 6.356385816350424e-06, 'samples': 26756160, 'steps': 139354, 'loss/train': 1.2358081340789795} 08/31/2021 14:33:14 - INFO - __main__ - Step 139356: {'lr': 6.355196821442338e-06, 'samples': 26756352, 'steps': 139355, 'loss/train': 0.6703292727470398} 08/31/2021 14:33:15 - INFO - __main__ - Step 139357: {'lr': 6.354007936316853e-06, 'samples': 26756544, 'steps': 139356, 'loss/train': 0.9040231704711914} 08/31/2021 14:33:15 - INFO - __main__ - Step 139358: {'lr': 6.352819160974465e-06, 'samples': 26756736, 'steps': 139357, 'loss/train': 0.8550534844398499} 08/31/2021 14:33:15 - INFO - __main__ - Step 139359: {'lr': 6.351630495415761e-06, 'samples': 26756928, 'steps': 139358, 'loss/train': 1.0655385255813599} 08/31/2021 14:33:16 - INFO - __main__ - Step 139360: {'lr': 6.350441939641266e-06, 'samples': 26757120, 'steps': 139359, 'loss/train': 1.5332697629928589} 08/31/2021 14:33:17 - INFO - __main__ - Step 139361: {'lr': 6.349253493651508e-06, 'samples': 26757312, 'steps': 139360, 'loss/train': 0.48144909739494324} 08/31/2021 14:33:18 - INFO - __main__ - Step 139362: {'lr': 6.348065157446986e-06, 'samples': 26757504, 'steps': 139361, 'loss/train': 1.0838285684585571} 08/31/2021 14:33:18 - INFO - __main__ - Step 139363: {'lr': 6.346876931028256e-06, 'samples': 26757696, 'steps': 139362, 'loss/train': 0.972919225692749} 08/31/2021 14:33:18 - INFO - __main__ - Step 139364: {'lr': 6.3456888143959e-06, 'samples': 26757888, 'steps': 139363, 'loss/train': 1.086122989654541} 08/31/2021 14:33:19 - INFO - __main__ - Step 139365: {'lr': 6.344500807550391e-06, 'samples': 26758080, 'steps': 139364, 'loss/train': 1.1056921482086182} 08/31/2021 14:33:20 - INFO - __main__ - Step 139366: {'lr': 6.343312910492282e-06, 'samples': 26758272, 'steps': 139365, 'loss/train': 1.1944160461425781} 08/31/2021 14:33:21 - INFO - __main__ - Step 139367: {'lr': 6.342125123222131e-06, 'samples': 26758464, 'steps': 139366, 'loss/train': 1.8210818767547607} 08/31/2021 14:33:21 - INFO - __main__ - Step 139368: {'lr': 6.340937445740463e-06, 'samples': 26758656, 'steps': 139367, 'loss/train': 1.4944711923599243} 08/31/2021 14:33:21 - INFO - __main__ - Step 139369: {'lr': 6.339749878047807e-06, 'samples': 26758848, 'steps': 139368, 'loss/train': 0.9247210025787354} 08/31/2021 14:33:22 - INFO - __main__ - Step 139370: {'lr': 6.338562420144689e-06, 'samples': 26759040, 'steps': 139369, 'loss/train': 2.3565971851348877} 08/31/2021 14:33:23 - INFO - __main__ - Step 139371: {'lr': 6.3373750720316645e-06, 'samples': 26759232, 'steps': 139370, 'loss/train': 1.2874425649642944} 08/31/2021 14:33:24 - INFO - __main__ - Step 139372: {'lr': 6.336187833709261e-06, 'samples': 26759424, 'steps': 139371, 'loss/train': 1.1672213077545166} 08/31/2021 14:33:24 - INFO - __main__ - Step 139373: {'lr': 6.335000705178034e-06, 'samples': 26759616, 'steps': 139372, 'loss/train': 0.848591685295105} 08/31/2021 14:33:24 - INFO - __main__ - Step 139374: {'lr': 6.333813686438456e-06, 'samples': 26759808, 'steps': 139373, 'loss/train': 0.8337839841842651} 08/31/2021 14:33:25 - INFO - __main__ - Step 139375: {'lr': 6.332626777491107e-06, 'samples': 26760000, 'steps': 139374, 'loss/train': 1.1790599822998047} 08/31/2021 14:33:26 - INFO - __main__ - Step 139376: {'lr': 6.331439978336545e-06, 'samples': 26760192, 'steps': 139375, 'loss/train': 1.6972742080688477} 08/31/2021 14:33:27 - INFO - __main__ - Step 139377: {'lr': 6.330253288975241e-06, 'samples': 26760384, 'steps': 139376, 'loss/train': 0.6514149308204651} 08/31/2021 14:33:27 - INFO - __main__ - Step 139378: {'lr': 6.329066709407777e-06, 'samples': 26760576, 'steps': 139377, 'loss/train': 1.9557826519012451} 08/31/2021 14:33:27 - INFO - __main__ - Step 139379: {'lr': 6.327880239634681e-06, 'samples': 26760768, 'steps': 139378, 'loss/train': 0.531147301197052} 08/31/2021 14:33:28 - INFO - __main__ - Step 139380: {'lr': 6.326693879656481e-06, 'samples': 26760960, 'steps': 139379, 'loss/train': 1.4077386856079102} 08/31/2021 14:33:29 - INFO - __main__ - Step 139381: {'lr': 6.3255076294737035e-06, 'samples': 26761152, 'steps': 139380, 'loss/train': 1.3218811750411987} 08/31/2021 14:33:30 - INFO - __main__ - Step 139382: {'lr': 6.324321489086904e-06, 'samples': 26761344, 'steps': 139381, 'loss/train': 0.8588424921035767} 08/31/2021 14:33:30 - INFO - __main__ - Step 139383: {'lr': 6.32313545849661e-06, 'samples': 26761536, 'steps': 139382, 'loss/train': 1.2878730297088623} 08/31/2021 14:33:30 - INFO - __main__ - Step 139384: {'lr': 6.321949537703319e-06, 'samples': 26761728, 'steps': 139383, 'loss/train': 1.1553528308868408} 08/31/2021 14:33:31 - INFO - __main__ - Step 139385: {'lr': 6.320763726707618e-06, 'samples': 26761920, 'steps': 139384, 'loss/train': 1.7207955121994019} 08/31/2021 14:33:31 - INFO - __main__ - Step 139386: {'lr': 6.3195780255100585e-06, 'samples': 26762112, 'steps': 139385, 'loss/train': 1.0229324102401733} 08/31/2021 14:33:33 - INFO - __main__ - Step 139387: {'lr': 6.3183924341110865e-06, 'samples': 26762304, 'steps': 139386, 'loss/train': 1.410069227218628} 08/31/2021 14:33:33 - INFO - __main__ - Step 139388: {'lr': 6.3172069525113115e-06, 'samples': 26762496, 'steps': 139387, 'loss/train': 0.6117561459541321} 08/31/2021 14:33:34 - INFO - __main__ - Step 139389: {'lr': 6.316021580711234e-06, 'samples': 26762688, 'steps': 139388, 'loss/train': 0.918940007686615} 08/31/2021 14:33:34 - INFO - __main__ - Step 139390: {'lr': 6.314836318711381e-06, 'samples': 26762880, 'steps': 139389, 'loss/train': 1.6634482145309448} 08/31/2021 14:33:34 - INFO - __main__ - Step 139391: {'lr': 6.313651166512308e-06, 'samples': 26763072, 'steps': 139390, 'loss/train': 0.9762263894081116} 08/31/2021 14:33:36 - INFO - __main__ - Step 139392: {'lr': 6.3124661241145685e-06, 'samples': 26763264, 'steps': 139391, 'loss/train': 1.139567255973816} 08/31/2021 14:33:36 - INFO - __main__ - Step 139393: {'lr': 6.311281191518637e-06, 'samples': 26763456, 'steps': 139392, 'loss/train': 0.7570632696151733} 08/31/2021 14:33:37 - INFO - __main__ - Step 139394: {'lr': 6.3100963687251215e-06, 'samples': 26763648, 'steps': 139393, 'loss/train': 0.7447945475578308} 08/31/2021 14:33:37 - INFO - __main__ - Step 139395: {'lr': 6.308911655734495e-06, 'samples': 26763840, 'steps': 139394, 'loss/train': 1.0304741859436035} 08/31/2021 14:33:38 - INFO - __main__ - Step 139396: {'lr': 6.307727052547285e-06, 'samples': 26764032, 'steps': 139395, 'loss/train': 0.7222923636436462} 08/31/2021 14:33:39 - INFO - __main__ - Step 139397: {'lr': 6.306542559164102e-06, 'samples': 26764224, 'steps': 139396, 'loss/train': 0.9752174615859985} 08/31/2021 14:33:40 - INFO - __main__ - Step 139398: {'lr': 6.305358175585419e-06, 'samples': 26764416, 'steps': 139397, 'loss/train': 1.0408474206924438} 08/31/2021 14:33:40 - INFO - __main__ - Step 139399: {'lr': 6.304173901811761e-06, 'samples': 26764608, 'steps': 139398, 'loss/train': 1.2016043663024902} 08/31/2021 14:33:40 - INFO - __main__ - Step 139400: {'lr': 6.302989737843712e-06, 'samples': 26764800, 'steps': 139399, 'loss/train': 1.1715755462646484} 08/31/2021 14:33:41 - INFO - __main__ - Step 139401: {'lr': 6.301805683681744e-06, 'samples': 26764992, 'steps': 139400, 'loss/train': 1.28378427028656} 08/31/2021 14:33:42 - INFO - __main__ - Step 139402: {'lr': 6.30062173932644e-06, 'samples': 26765184, 'steps': 139401, 'loss/train': 0.6096329092979431} 08/31/2021 14:33:43 - INFO - __main__ - Step 139403: {'lr': 6.299437904778299e-06, 'samples': 26765376, 'steps': 139402, 'loss/train': 0.49438679218292236} 08/31/2021 14:33:43 - INFO - __main__ - Step 139404: {'lr': 6.2982541800378765e-06, 'samples': 26765568, 'steps': 139403, 'loss/train': 0.10400351881980896} 08/31/2021 14:33:44 - INFO - __main__ - Step 139405: {'lr': 6.2970705651057005e-06, 'samples': 26765760, 'steps': 139404, 'loss/train': 1.0286608934402466} 08/31/2021 14:33:44 - INFO - __main__ - Step 139406: {'lr': 6.295887059982297e-06, 'samples': 26765952, 'steps': 139405, 'loss/train': 0.19477024674415588} 08/31/2021 14:33:45 - INFO - __main__ - Step 139407: {'lr': 6.294703664668222e-06, 'samples': 26766144, 'steps': 139406, 'loss/train': 0.7373339533805847} 08/31/2021 14:33:46 - INFO - __main__ - Step 139408: {'lr': 6.293520379164003e-06, 'samples': 26766336, 'steps': 139407, 'loss/train': 0.7132124304771423} 08/31/2021 14:33:46 - INFO - __main__ - Step 139409: {'lr': 6.292337203470139e-06, 'samples': 26766528, 'steps': 139408, 'loss/train': 0.9045260548591614} 08/31/2021 14:33:47 - INFO - __main__ - Step 139410: {'lr': 6.291154137587213e-06, 'samples': 26766720, 'steps': 139409, 'loss/train': 1.4171833992004395} 08/31/2021 14:33:47 - INFO - __main__ - Step 139411: {'lr': 6.289971181515697e-06, 'samples': 26766912, 'steps': 139410, 'loss/train': 1.1524111032485962} 08/31/2021 14:33:48 - INFO - __main__ - Step 139412: {'lr': 6.288788335256174e-06, 'samples': 26767104, 'steps': 139411, 'loss/train': 0.7734531164169312} 08/31/2021 14:33:49 - INFO - __main__ - Step 139413: {'lr': 6.2876055988091705e-06, 'samples': 26767296, 'steps': 139412, 'loss/train': 0.8968609571456909} 08/31/2021 14:33:49 - INFO - __main__ - Step 139414: {'lr': 6.286422972175215e-06, 'samples': 26767488, 'steps': 139413, 'loss/train': 1.2820122241973877} 08/31/2021 14:33:50 - INFO - __main__ - Step 139415: {'lr': 6.285240455354807e-06, 'samples': 26767680, 'steps': 139414, 'loss/train': 1.5672717094421387} 08/31/2021 14:33:50 - INFO - __main__ - Step 139416: {'lr': 6.284058048348529e-06, 'samples': 26767872, 'steps': 139415, 'loss/train': 1.174265742301941} 08/31/2021 14:33:50 - INFO - __main__ - Step 139417: {'lr': 6.282875751156908e-06, 'samples': 26768064, 'steps': 139416, 'loss/train': 1.6738494634628296} 08/31/2021 14:33:52 - INFO - __main__ - Step 139418: {'lr': 6.281693563780444e-06, 'samples': 26768256, 'steps': 139417, 'loss/train': 0.6848929524421692} 08/31/2021 14:33:52 - INFO - __main__ - Step 139419: {'lr': 6.28051148621972e-06, 'samples': 26768448, 'steps': 139418, 'loss/train': 1.1831721067428589} 08/31/2021 14:33:52 - INFO - __main__ - Step 139420: {'lr': 6.279329518475207e-06, 'samples': 26768640, 'steps': 139419, 'loss/train': 1.0954372882843018} 08/31/2021 14:33:53 - INFO - __main__ - Step 139421: {'lr': 6.278147660547462e-06, 'samples': 26768832, 'steps': 139420, 'loss/train': 1.1247849464416504} 08/31/2021 14:33:53 - INFO - __main__ - Step 139422: {'lr': 6.276965912437038e-06, 'samples': 26769024, 'steps': 139421, 'loss/train': 1.252002477645874} 08/31/2021 14:33:55 - INFO - __main__ - Step 139423: {'lr': 6.275784274144436e-06, 'samples': 26769216, 'steps': 139422, 'loss/train': 0.2652021050453186} 08/31/2021 14:33:55 - INFO - __main__ - Step 139424: {'lr': 6.274602745670211e-06, 'samples': 26769408, 'steps': 139423, 'loss/train': 0.9665874242782593} 08/31/2021 14:33:56 - INFO - __main__ - Step 139425: {'lr': 6.273421327014889e-06, 'samples': 26769600, 'steps': 139424, 'loss/train': 1.108189344406128} 08/31/2021 14:33:56 - INFO - __main__ - Step 139426: {'lr': 6.272240018178998e-06, 'samples': 26769792, 'steps': 139425, 'loss/train': 1.2847957611083984} 08/31/2021 14:33:56 - INFO - __main__ - Step 139427: {'lr': 6.271058819163094e-06, 'samples': 26769984, 'steps': 139426, 'loss/train': 1.5293374061584473} 08/31/2021 14:33:58 - INFO - __main__ - Step 139428: {'lr': 6.269877729967677e-06, 'samples': 26770176, 'steps': 139427, 'loss/train': 1.6056419610977173} 08/31/2021 14:33:58 - INFO - __main__ - Step 139429: {'lr': 6.268696750593272e-06, 'samples': 26770368, 'steps': 139428, 'loss/train': 0.8291306495666504} 08/31/2021 14:33:59 - INFO - __main__ - Step 139430: {'lr': 6.267515881040492e-06, 'samples': 26770560, 'steps': 139429, 'loss/train': 1.574182152748108} 08/31/2021 14:33:59 - INFO - __main__ - Step 139431: {'lr': 6.266335121309752e-06, 'samples': 26770752, 'steps': 139430, 'loss/train': 1.0356751680374146} 08/31/2021 14:33:59 - INFO - __main__ - Step 139432: {'lr': 6.2651544714016625e-06, 'samples': 26770944, 'steps': 139431, 'loss/train': 0.35195192694664} 08/31/2021 14:34:01 - INFO - __main__ - Step 139433: {'lr': 6.263973931316724e-06, 'samples': 26771136, 'steps': 139432, 'loss/train': 0.8415156602859497} 08/31/2021 14:34:01 - INFO - __main__ - Step 139434: {'lr': 6.262793501055491e-06, 'samples': 26771328, 'steps': 139433, 'loss/train': 1.3819732666015625} 08/31/2021 14:34:02 - INFO - __main__ - Step 139435: {'lr': 6.261613180618464e-06, 'samples': 26771520, 'steps': 139434, 'loss/train': 0.781585693359375} 08/31/2021 14:34:02 - INFO - __main__ - Step 139436: {'lr': 6.260432970006197e-06, 'samples': 26771712, 'steps': 139435, 'loss/train': 1.0703061819076538} 08/31/2021 14:34:02 - INFO - __main__ - Step 139437: {'lr': 6.259252869219218e-06, 'samples': 26771904, 'steps': 139436, 'loss/train': 0.5922010540962219} 08/31/2021 14:34:05 - INFO - __main__ - Step 139438: {'lr': 6.258072878258053e-06, 'samples': 26772096, 'steps': 139437, 'loss/train': 1.6365450620651245} 08/31/2021 14:34:05 - INFO - __main__ - Step 139439: {'lr': 6.2568929971232595e-06, 'samples': 26772288, 'steps': 139438, 'loss/train': 1.1554757356643677} 08/31/2021 14:34:06 - INFO - __main__ - Step 139440: {'lr': 6.2557132258153345e-06, 'samples': 26772480, 'steps': 139439, 'loss/train': 0.8046454191207886} 08/31/2021 14:34:06 - INFO - __main__ - Step 139441: {'lr': 6.254533564334864e-06, 'samples': 26772672, 'steps': 139440, 'loss/train': 1.2587896585464478} 08/31/2021 14:34:06 - INFO - __main__ - Step 139442: {'lr': 6.253354012682288e-06, 'samples': 26772864, 'steps': 139441, 'loss/train': 1.720376968383789} 08/31/2021 14:34:07 - INFO - __main__ - Step 139443: {'lr': 6.252174570858193e-06, 'samples': 26773056, 'steps': 139442, 'loss/train': 1.7499918937683105} 08/31/2021 14:34:07 - INFO - __main__ - Step 139444: {'lr': 6.250995238863133e-06, 'samples': 26773248, 'steps': 139443, 'loss/train': 1.2377010583877563} 08/31/2021 14:34:09 - INFO - __main__ - Step 139445: {'lr': 6.2498160166975794e-06, 'samples': 26773440, 'steps': 139444, 'loss/train': 0.670622706413269} 08/31/2021 14:34:09 - INFO - __main__ - Step 139446: {'lr': 6.248636904362115e-06, 'samples': 26773632, 'steps': 139445, 'loss/train': 1.0783029794692993} 08/31/2021 14:34:10 - INFO - __main__ - Step 139447: {'lr': 6.247457901857267e-06, 'samples': 26773824, 'steps': 139446, 'loss/train': 0.9353289008140564} 08/31/2021 14:34:10 - INFO - __main__ - Step 139448: {'lr': 6.246279009183536e-06, 'samples': 26774016, 'steps': 139447, 'loss/train': 1.140737771987915} 08/31/2021 14:34:10 - INFO - __main__ - Step 139449: {'lr': 6.245100226341477e-06, 'samples': 26774208, 'steps': 139448, 'loss/train': 1.3110084533691406} 08/31/2021 14:34:12 - INFO - __main__ - Step 139450: {'lr': 6.243921553331616e-06, 'samples': 26774400, 'steps': 139449, 'loss/train': 0.7928941249847412} 08/31/2021 14:34:12 - INFO - __main__ - Step 139451: {'lr': 6.242742990154482e-06, 'samples': 26774592, 'steps': 139450, 'loss/train': 0.9132140278816223} 08/31/2021 14:34:13 - INFO - __main__ - Step 139452: {'lr': 6.241564536810601e-06, 'samples': 26774784, 'steps': 139451, 'loss/train': 0.6876232028007507} 08/31/2021 14:34:13 - INFO - __main__ - Step 139453: {'lr': 6.240386193300502e-06, 'samples': 26774976, 'steps': 139452, 'loss/train': 0.07964076846837997} 08/31/2021 14:34:13 - INFO - __main__ - Step 139454: {'lr': 6.239207959624766e-06, 'samples': 26775168, 'steps': 139453, 'loss/train': 0.4916854202747345} 08/31/2021 14:34:15 - INFO - __main__ - Step 139455: {'lr': 6.238029835783837e-06, 'samples': 26775360, 'steps': 139454, 'loss/train': 2.5831432342529297} 08/31/2021 14:34:15 - INFO - __main__ - Step 139456: {'lr': 6.2368518217783e-06, 'samples': 26775552, 'steps': 139455, 'loss/train': 1.0680558681488037} 08/31/2021 14:34:16 - INFO - __main__ - Step 139457: {'lr': 6.235673917608681e-06, 'samples': 26775744, 'steps': 139456, 'loss/train': 1.0275100469589233} 08/31/2021 14:34:16 - INFO - __main__ - Step 139458: {'lr': 6.234496123275507e-06, 'samples': 26775936, 'steps': 139457, 'loss/train': 0.8881431818008423} 08/31/2021 14:34:16 - INFO - __main__ - Step 139459: {'lr': 6.233318438779306e-06, 'samples': 26776128, 'steps': 139458, 'loss/train': 0.7765785455703735} 08/31/2021 14:34:17 - INFO - __main__ - Step 139460: {'lr': 6.232140864120606e-06, 'samples': 26776320, 'steps': 139459, 'loss/train': 1.2946550846099854} 08/31/2021 14:34:18 - INFO - __main__ - Step 139461: {'lr': 6.230963399299933e-06, 'samples': 26776512, 'steps': 139460, 'loss/train': 0.960034191608429} 08/31/2021 14:34:19 - INFO - __main__ - Step 139462: {'lr': 6.229786044317842e-06, 'samples': 26776704, 'steps': 139461, 'loss/train': 0.3256355822086334} 08/31/2021 14:34:19 - INFO - __main__ - Step 139463: {'lr': 6.228608799174834e-06, 'samples': 26776896, 'steps': 139462, 'loss/train': 1.1654176712036133} 08/31/2021 14:34:19 - INFO - __main__ - Step 139464: {'lr': 6.227431663871463e-06, 'samples': 26777088, 'steps': 139463, 'loss/train': 1.0843077898025513} 08/31/2021 14:34:20 - INFO - __main__ - Step 139465: {'lr': 6.226254638408257e-06, 'samples': 26777280, 'steps': 139464, 'loss/train': 1.4605761766433716} 08/31/2021 14:34:21 - INFO - __main__ - Step 139466: {'lr': 6.225077722785716e-06, 'samples': 26777472, 'steps': 139465, 'loss/train': 0.7765240669250488} 08/31/2021 14:34:22 - INFO - __main__ - Step 139467: {'lr': 6.223900917004421e-06, 'samples': 26777664, 'steps': 139466, 'loss/train': 0.7554442286491394} 08/31/2021 14:34:22 - INFO - __main__ - Step 139468: {'lr': 6.222724221064874e-06, 'samples': 26777856, 'steps': 139467, 'loss/train': 0.9565156698226929} 08/31/2021 14:34:23 - INFO - __main__ - Step 139469: {'lr': 6.221547634967601e-06, 'samples': 26778048, 'steps': 139468, 'loss/train': 0.0281950943171978} 08/31/2021 14:34:23 - INFO - __main__ - Step 139470: {'lr': 6.2203711587131284e-06, 'samples': 26778240, 'steps': 139469, 'loss/train': 1.167401909828186} 08/31/2021 14:34:24 - INFO - __main__ - Step 139471: {'lr': 6.219194792301985e-06, 'samples': 26778432, 'steps': 139470, 'loss/train': 1.8758182525634766} 08/31/2021 14:34:25 - INFO - __main__ - Step 139472: {'lr': 6.218018535734726e-06, 'samples': 26778624, 'steps': 139471, 'loss/train': 0.7554894685745239} 08/31/2021 14:34:25 - INFO - __main__ - Step 139473: {'lr': 6.216842389011851e-06, 'samples': 26778816, 'steps': 139472, 'loss/train': 0.5772848129272461} 08/31/2021 14:34:26 - INFO - __main__ - Step 139474: {'lr': 6.215666352133914e-06, 'samples': 26779008, 'steps': 139473, 'loss/train': 0.7579811215400696} 08/31/2021 14:34:26 - INFO - __main__ - Step 139475: {'lr': 6.214490425101443e-06, 'samples': 26779200, 'steps': 139474, 'loss/train': 0.8855220079421997} 08/31/2021 14:34:28 - INFO - __main__ - Step 139476: {'lr': 6.213314607914966e-06, 'samples': 26779392, 'steps': 139475, 'loss/train': 0.9074305891990662} 08/31/2021 14:34:28 - INFO - __main__ - Step 139477: {'lr': 6.2121389005749815e-06, 'samples': 26779584, 'steps': 139476, 'loss/train': 1.3416975736618042} 08/31/2021 14:34:28 - INFO - __main__ - Step 139478: {'lr': 6.210963303082073e-06, 'samples': 26779776, 'steps': 139477, 'loss/train': 1.9713268280029297} 08/31/2021 14:34:29 - INFO - __main__ - Step 139479: {'lr': 6.209787815436713e-06, 'samples': 26779968, 'steps': 139478, 'loss/train': 1.1178864240646362} 08/31/2021 14:34:29 - INFO - __main__ - Step 139480: {'lr': 6.208612437639482e-06, 'samples': 26780160, 'steps': 139479, 'loss/train': 0.6718920469284058} 08/31/2021 14:34:31 - INFO - __main__ - Step 139481: {'lr': 6.20743716969091e-06, 'samples': 26780352, 'steps': 139480, 'loss/train': 0.7176570296287537} 08/31/2021 14:34:31 - INFO - __main__ - Step 139482: {'lr': 6.206262011591468e-06, 'samples': 26780544, 'steps': 139481, 'loss/train': 1.3133461475372314} 08/31/2021 14:34:31 - INFO - __main__ - Step 139483: {'lr': 6.205086963341738e-06, 'samples': 26780736, 'steps': 139482, 'loss/train': 0.964688777923584} 08/31/2021 14:34:32 - INFO - __main__ - Step 139484: {'lr': 6.203912024942248e-06, 'samples': 26780928, 'steps': 139483, 'loss/train': 0.3247435390949249} 08/31/2021 14:34:32 - INFO - __main__ - Step 139485: {'lr': 6.202737196393471e-06, 'samples': 26781120, 'steps': 139484, 'loss/train': 0.3843461573123932} 08/31/2021 14:34:32 - INFO - __main__ - Step 139486: {'lr': 6.201562477696016e-06, 'samples': 26781312, 'steps': 139485, 'loss/train': 0.9886837601661682} 08/31/2021 14:34:35 - INFO - __main__ - Step 139487: {'lr': 6.200387868850355e-06, 'samples': 26781504, 'steps': 139486, 'loss/train': 0.77735435962677} 08/31/2021 14:34:35 - INFO - __main__ - Step 139488: {'lr': 6.199213369857043e-06, 'samples': 26781696, 'steps': 139487, 'loss/train': 1.1009032726287842} 08/31/2021 14:34:36 - INFO - __main__ - Step 139489: {'lr': 6.198038980716608e-06, 'samples': 26781888, 'steps': 139488, 'loss/train': 0.09877815842628479} 08/31/2021 14:34:36 - INFO - __main__ - Step 139490: {'lr': 6.1968647014295495e-06, 'samples': 26782080, 'steps': 139489, 'loss/train': 1.9742735624313354} 08/31/2021 14:34:36 - INFO - __main__ - Step 139491: {'lr': 6.195690531996451e-06, 'samples': 26782272, 'steps': 139490, 'loss/train': 1.0055075883865356} 08/31/2021 14:34:38 - INFO - __main__ - Step 139492: {'lr': 6.19451647241781e-06, 'samples': 26782464, 'steps': 139491, 'loss/train': 0.9345741271972656} 08/31/2021 14:34:38 - INFO - __main__ - Step 139493: {'lr': 6.1933425226941566e-06, 'samples': 26782656, 'steps': 139492, 'loss/train': 1.2625515460968018} 08/31/2021 14:34:39 - INFO - __main__ - Step 139494: {'lr': 6.192168682826016e-06, 'samples': 26782848, 'steps': 139493, 'loss/train': 0.7423774003982544} 08/31/2021 14:34:39 - INFO - __main__ - Step 139495: {'lr': 6.1909949528139445e-06, 'samples': 26783040, 'steps': 139494, 'loss/train': 0.8572321534156799} 08/31/2021 14:34:39 - INFO - __main__ - Step 139496: {'lr': 6.1898213326584126e-06, 'samples': 26783232, 'steps': 139495, 'loss/train': 1.3449373245239258} 08/31/2021 14:34:41 - INFO - __main__ - Step 139497: {'lr': 6.1886478223600055e-06, 'samples': 26783424, 'steps': 139496, 'loss/train': 0.8448834419250488} 08/31/2021 14:34:41 - INFO - __main__ - Step 139498: {'lr': 6.18747442191922e-06, 'samples': 26783616, 'steps': 139497, 'loss/train': 1.4748177528381348} 08/31/2021 14:34:42 - INFO - __main__ - Step 139499: {'lr': 6.186301131336586e-06, 'samples': 26783808, 'steps': 139498, 'loss/train': 1.4547244310379028} 08/31/2021 14:34:42 - INFO - __main__ - Step 139500: {'lr': 6.185127950612657e-06, 'samples': 26784000, 'steps': 139499, 'loss/train': 0.9030929803848267} 08/31/2021 14:34:42 - INFO - __main__ - Step 139501: {'lr': 6.1839548797479605e-06, 'samples': 26784192, 'steps': 139500, 'loss/train': 0.8976370096206665} 08/31/2021 14:34:44 - INFO - __main__ - Step 139502: {'lr': 6.182781918742997e-06, 'samples': 26784384, 'steps': 139501, 'loss/train': 1.1220173835754395} 08/31/2021 14:34:44 - INFO - __main__ - Step 139503: {'lr': 6.181609067598293e-06, 'samples': 26784576, 'steps': 139502, 'loss/train': 1.3668339252471924} 08/31/2021 14:34:45 - INFO - __main__ - Step 139504: {'lr': 6.180436326314403e-06, 'samples': 26784768, 'steps': 139503, 'loss/train': 0.3233097791671753} 08/31/2021 14:34:45 - INFO - __main__ - Step 139505: {'lr': 6.179263694891857e-06, 'samples': 26784960, 'steps': 139504, 'loss/train': 0.9610109925270081} 08/31/2021 14:34:45 - INFO - __main__ - Step 139506: {'lr': 6.178091173331179e-06, 'samples': 26785152, 'steps': 139505, 'loss/train': 1.171147108078003} 08/31/2021 14:34:47 - INFO - __main__ - Step 139507: {'lr': 6.1769187616328715e-06, 'samples': 26785344, 'steps': 139506, 'loss/train': 1.2385828495025635} 08/31/2021 14:34:47 - INFO - __main__ - Step 139508: {'lr': 6.1757464597975155e-06, 'samples': 26785536, 'steps': 139507, 'loss/train': 1.0874731540679932} 08/31/2021 14:34:47 - INFO - __main__ - Step 139509: {'lr': 6.174574267825584e-06, 'samples': 26785728, 'steps': 139508, 'loss/train': 0.9160797595977783} 08/31/2021 14:34:48 - INFO - __main__ - Step 139510: {'lr': 6.173402185717631e-06, 'samples': 26785920, 'steps': 139509, 'loss/train': 1.2748130559921265} 08/31/2021 14:34:48 - INFO - __main__ - Step 139511: {'lr': 6.172230213474156e-06, 'samples': 26786112, 'steps': 139510, 'loss/train': 1.176195502281189} 08/31/2021 14:34:50 - INFO - __main__ - Step 139512: {'lr': 6.171058351095743e-06, 'samples': 26786304, 'steps': 139511, 'loss/train': 2.239197254180908} 08/31/2021 14:34:50 - INFO - __main__ - Step 139513: {'lr': 6.1698865985828636e-06, 'samples': 26786496, 'steps': 139512, 'loss/train': 1.4800888299942017} 08/31/2021 14:34:50 - INFO - __main__ - Step 139514: {'lr': 6.1687149559361e-06, 'samples': 26786688, 'steps': 139513, 'loss/train': 1.214871883392334} 08/31/2021 14:34:51 - INFO - __main__ - Step 139515: {'lr': 6.167543423155925e-06, 'samples': 26786880, 'steps': 139514, 'loss/train': 1.444785714149475} 08/31/2021 14:34:51 - INFO - __main__ - Step 139516: {'lr': 6.166372000242893e-06, 'samples': 26787072, 'steps': 139515, 'loss/train': 0.4773626923561096} 08/31/2021 14:34:51 - INFO - __main__ - Step 139517: {'lr': 6.165200687197531e-06, 'samples': 26787264, 'steps': 139516, 'loss/train': 1.0877127647399902} 08/31/2021 14:34:53 - INFO - __main__ - Step 139518: {'lr': 6.1640294840203944e-06, 'samples': 26787456, 'steps': 139517, 'loss/train': 1.0351171493530273} 08/31/2021 14:34:53 - INFO - __main__ - Step 139519: {'lr': 6.1628583907119565e-06, 'samples': 26787648, 'steps': 139518, 'loss/train': 0.5220159888267517} 08/31/2021 14:34:54 - INFO - __main__ - Step 139520: {'lr': 6.16168740727277e-06, 'samples': 26787840, 'steps': 139519, 'loss/train': 1.0929467678070068} 08/31/2021 14:34:54 - INFO - __main__ - Step 139521: {'lr': 6.160516533703392e-06, 'samples': 26788032, 'steps': 139520, 'loss/train': 1.1678787469863892} 08/31/2021 14:34:54 - INFO - __main__ - Step 139522: {'lr': 6.159345770004321e-06, 'samples': 26788224, 'steps': 139521, 'loss/train': 1.2697266340255737} 08/31/2021 14:34:56 - INFO - __main__ - Step 139523: {'lr': 6.158175116176057e-06, 'samples': 26788416, 'steps': 139522, 'loss/train': 0.9743583798408508} 08/31/2021 14:34:56 - INFO - __main__ - Step 139524: {'lr': 6.157004572219182e-06, 'samples': 26788608, 'steps': 139523, 'loss/train': 1.1609187126159668} 08/31/2021 14:34:57 - INFO - __main__ - Step 139525: {'lr': 6.1558341381341696e-06, 'samples': 26788800, 'steps': 139524, 'loss/train': 0.11566191911697388} 08/31/2021 14:34:57 - INFO - __main__ - Step 139526: {'lr': 6.154663813921602e-06, 'samples': 26788992, 'steps': 139525, 'loss/train': 0.256587415933609} 08/31/2021 14:34:57 - INFO - __main__ - Step 139527: {'lr': 6.1534935995819775e-06, 'samples': 26789184, 'steps': 139526, 'loss/train': 0.8493015170097351} 08/31/2021 14:34:59 - INFO - __main__ - Step 139528: {'lr': 6.152323495115797e-06, 'samples': 26789376, 'steps': 139527, 'loss/train': 0.9207974672317505} 08/31/2021 14:35:00 - INFO - __main__ - Step 139529: {'lr': 6.151153500523643e-06, 'samples': 26789568, 'steps': 139528, 'loss/train': 0.9249998331069946} 08/31/2021 14:35:00 - INFO - __main__ - Step 139530: {'lr': 6.149983615806015e-06, 'samples': 26789760, 'steps': 139529, 'loss/train': 1.1881065368652344} 08/31/2021 14:35:00 - INFO - __main__ - Step 139531: {'lr': 6.148813840963441e-06, 'samples': 26789952, 'steps': 139530, 'loss/train': 0.1089920923113823} 08/31/2021 14:35:01 - INFO - __main__ - Step 139532: {'lr': 6.147644175996447e-06, 'samples': 26790144, 'steps': 139531, 'loss/train': 0.8520496487617493} 08/31/2021 14:35:02 - INFO - __main__ - Step 139533: {'lr': 6.146474620905534e-06, 'samples': 26790336, 'steps': 139532, 'loss/train': 1.4114859104156494} 08/31/2021 14:35:03 - INFO - __main__ - Step 139534: {'lr': 6.145305175691285e-06, 'samples': 26790528, 'steps': 139533, 'loss/train': 0.9261849522590637} 08/31/2021 14:35:03 - INFO - __main__ - Step 139535: {'lr': 6.1441358403542255e-06, 'samples': 26790720, 'steps': 139534, 'loss/train': 1.087373971939087} 08/31/2021 14:35:03 - INFO - __main__ - Step 139536: {'lr': 6.142966614894829e-06, 'samples': 26790912, 'steps': 139535, 'loss/train': 1.1149736642837524} 08/31/2021 14:35:04 - INFO - __main__ - Step 139537: {'lr': 6.14179749931365e-06, 'samples': 26791104, 'steps': 139536, 'loss/train': 1.4427974224090576} 08/31/2021 14:35:05 - INFO - __main__ - Step 139538: {'lr': 6.1406284936111885e-06, 'samples': 26791296, 'steps': 139537, 'loss/train': 1.8570334911346436} 08/31/2021 14:35:06 - INFO - __main__ - Step 139539: {'lr': 6.139459597788027e-06, 'samples': 26791488, 'steps': 139538, 'loss/train': 1.0956887006759644} 08/31/2021 14:35:06 - INFO - __main__ - Step 139540: {'lr': 6.1382908118446655e-06, 'samples': 26791680, 'steps': 139539, 'loss/train': 1.1521131992340088} 08/31/2021 14:35:07 - INFO - __main__ - Step 139541: {'lr': 6.1371221357816035e-06, 'samples': 26791872, 'steps': 139540, 'loss/train': 0.020732499659061432} 08/31/2021 14:35:07 - INFO - __main__ - Step 139542: {'lr': 6.135953569599395e-06, 'samples': 26792064, 'steps': 139541, 'loss/train': 0.7927259802818298} 08/31/2021 14:35:09 - INFO - __main__ - Step 139543: {'lr': 6.134785113298569e-06, 'samples': 26792256, 'steps': 139542, 'loss/train': 1.0098670721054077} 08/31/2021 14:35:10 - INFO - __main__ - Step 139544: {'lr': 6.133616766879651e-06, 'samples': 26792448, 'steps': 139543, 'loss/train': 1.2056090831756592} 08/31/2021 14:35:10 - INFO - __main__ - Step 139545: {'lr': 6.132448530343171e-06, 'samples': 26792640, 'steps': 139544, 'loss/train': 1.1922770738601685} 08/31/2021 14:35:10 - INFO - __main__ - Step 139546: {'lr': 6.1312804036896265e-06, 'samples': 26792832, 'steps': 139545, 'loss/train': 1.8853399753570557} 08/31/2021 14:35:11 - INFO - __main__ - Step 139547: {'lr': 6.130112386919573e-06, 'samples': 26793024, 'steps': 139546, 'loss/train': 0.9899288415908813} 08/31/2021 14:35:11 - INFO - __main__ - Step 139548: {'lr': 6.128944480033538e-06, 'samples': 26793216, 'steps': 139547, 'loss/train': 0.9400319457054138} 08/31/2021 14:35:13 - INFO - __main__ - Step 139549: {'lr': 6.1277766830320215e-06, 'samples': 26793408, 'steps': 139548, 'loss/train': 0.9340583086013794} 08/31/2021 14:35:13 - INFO - __main__ - Step 139550: {'lr': 6.126608995915578e-06, 'samples': 26793600, 'steps': 139549, 'loss/train': 0.8251206874847412} 08/31/2021 14:35:13 - INFO - __main__ - Step 139551: {'lr': 6.1254414186847075e-06, 'samples': 26793792, 'steps': 139550, 'loss/train': 0.8896511197090149} 08/31/2021 14:35:14 - INFO - __main__ - Step 139552: {'lr': 6.124273951339965e-06, 'samples': 26793984, 'steps': 139551, 'loss/train': 1.0528788566589355} 08/31/2021 14:35:14 - INFO - __main__ - Step 139553: {'lr': 6.12310659388185e-06, 'samples': 26794176, 'steps': 139552, 'loss/train': 0.39770710468292236} 08/31/2021 14:35:16 - INFO - __main__ - Step 139554: {'lr': 6.12193934631089e-06, 'samples': 26794368, 'steps': 139553, 'loss/train': 0.28624290227890015} 08/31/2021 14:35:16 - INFO - __main__ - Step 139555: {'lr': 6.1207722086276394e-06, 'samples': 26794560, 'steps': 139554, 'loss/train': 0.08690609782934189} 08/31/2021 14:35:16 - INFO - __main__ - Step 139556: {'lr': 6.119605180832599e-06, 'samples': 26794752, 'steps': 139555, 'loss/train': 1.3962080478668213} 08/31/2021 14:35:17 - INFO - __main__ - Step 139557: {'lr': 6.1184382629262956e-06, 'samples': 26794944, 'steps': 139556, 'loss/train': 1.1307588815689087} 08/31/2021 14:35:17 - INFO - __main__ - Step 139558: {'lr': 6.117271454909257e-06, 'samples': 26795136, 'steps': 139557, 'loss/train': 0.6300581693649292} 08/31/2021 14:35:19 - INFO - __main__ - Step 139559: {'lr': 6.116104756782037e-06, 'samples': 26795328, 'steps': 139558, 'loss/train': 1.5037715435028076} 08/31/2021 14:35:19 - INFO - __main__ - Step 139560: {'lr': 6.114938168545109e-06, 'samples': 26795520, 'steps': 139559, 'loss/train': 1.0609190464019775} 08/31/2021 14:35:19 - INFO - __main__ - Step 139561: {'lr': 6.113771690199027e-06, 'samples': 26795712, 'steps': 139560, 'loss/train': 0.9772606492042542} 08/31/2021 14:35:20 - INFO - __main__ - Step 139562: {'lr': 6.112605321744374e-06, 'samples': 26795904, 'steps': 139561, 'loss/train': 1.0287009477615356} 08/31/2021 14:35:20 - INFO - __main__ - Step 139563: {'lr': 6.111439063181568e-06, 'samples': 26796096, 'steps': 139562, 'loss/train': 0.458430677652359} 08/31/2021 14:35:22 - INFO - __main__ - Step 139564: {'lr': 6.110272914511189e-06, 'samples': 26796288, 'steps': 139563, 'loss/train': 1.7236937284469604} 08/31/2021 14:35:22 - INFO - __main__ - Step 139565: {'lr': 6.109106875733739e-06, 'samples': 26796480, 'steps': 139564, 'loss/train': 1.1239759922027588} 08/31/2021 14:35:23 - INFO - __main__ - Step 139566: {'lr': 6.107940946849799e-06, 'samples': 26796672, 'steps': 139565, 'loss/train': 1.379336953163147} 08/31/2021 14:35:23 - INFO - __main__ - Step 139567: {'lr': 6.106775127859815e-06, 'samples': 26796864, 'steps': 139566, 'loss/train': 1.9004815816879272} 08/31/2021 14:35:23 - INFO - __main__ - Step 139568: {'lr': 6.105609418764396e-06, 'samples': 26797056, 'steps': 139567, 'loss/train': 1.4109846353530884} 08/31/2021 14:35:24 - INFO - __main__ - Step 139569: {'lr': 6.104443819563987e-06, 'samples': 26797248, 'steps': 139568, 'loss/train': 1.358848214149475} 08/31/2021 14:35:25 - INFO - __main__ - Step 139570: {'lr': 6.103278330259171e-06, 'samples': 26797440, 'steps': 139569, 'loss/train': 1.1830666065216064} 08/31/2021 14:35:26 - INFO - __main__ - Step 139571: {'lr': 6.102112950850475e-06, 'samples': 26797632, 'steps': 139570, 'loss/train': 1.714966893196106} 08/31/2021 14:35:26 - INFO - __main__ - Step 139572: {'lr': 6.10094768133837e-06, 'samples': 26797824, 'steps': 139571, 'loss/train': 1.1861172914505005} 08/31/2021 14:35:26 - INFO - __main__ - Step 139573: {'lr': 6.099782521723413e-06, 'samples': 26798016, 'steps': 139572, 'loss/train': 1.0998884439468384} 08/31/2021 14:35:27 - INFO - __main__ - Step 139574: {'lr': 6.098617472006157e-06, 'samples': 26798208, 'steps': 139573, 'loss/train': 0.9413632154464722} 08/31/2021 14:35:28 - INFO - __main__ - Step 139575: {'lr': 6.0974525321871035e-06, 'samples': 26798400, 'steps': 139574, 'loss/train': 1.2535444498062134} 08/31/2021 14:35:29 - INFO - __main__ - Step 139576: {'lr': 6.096287702266778e-06, 'samples': 26798592, 'steps': 139575, 'loss/train': 1.5749553442001343} 08/31/2021 14:35:29 - INFO - __main__ - Step 139577: {'lr': 6.095122982245682e-06, 'samples': 26798784, 'steps': 139576, 'loss/train': 1.3325039148330688} 08/31/2021 14:35:30 - INFO - __main__ - Step 139578: {'lr': 6.093958372124342e-06, 'samples': 26798976, 'steps': 139577, 'loss/train': 0.9954863786697388} 08/31/2021 14:35:30 - INFO - __main__ - Step 139579: {'lr': 6.09279387190334e-06, 'samples': 26799168, 'steps': 139578, 'loss/train': 1.203792691230774} 08/31/2021 14:35:31 - INFO - __main__ - Step 139580: {'lr': 6.091629481583122e-06, 'samples': 26799360, 'steps': 139579, 'loss/train': 1.303182601928711} 08/31/2021 14:35:32 - INFO - __main__ - Step 139581: {'lr': 6.090465201164269e-06, 'samples': 26799552, 'steps': 139580, 'loss/train': 0.7423280477523804} 08/31/2021 14:35:32 - INFO - __main__ - Step 139582: {'lr': 6.089301030647309e-06, 'samples': 26799744, 'steps': 139581, 'loss/train': 0.8754787445068359} 08/31/2021 14:35:33 - INFO - __main__ - Step 139583: {'lr': 6.088136970032715e-06, 'samples': 26799936, 'steps': 139582, 'loss/train': 0.5220831632614136} 08/31/2021 14:35:33 - INFO - __main__ - Step 139584: {'lr': 6.086973019321041e-06, 'samples': 26800128, 'steps': 139583, 'loss/train': 1.4351820945739746} 08/31/2021 14:35:33 - INFO - __main__ - Step 139585: {'lr': 6.0858091785128415e-06, 'samples': 26800320, 'steps': 139584, 'loss/train': 1.401675820350647} 08/31/2021 14:35:35 - INFO - __main__ - Step 139586: {'lr': 6.0846454476085885e-06, 'samples': 26800512, 'steps': 139585, 'loss/train': 1.332324504852295} 08/31/2021 14:35:35 - INFO - __main__ - Step 139587: {'lr': 6.083481826608839e-06, 'samples': 26800704, 'steps': 139586, 'loss/train': 1.1176831722259521} 08/31/2021 14:35:36 - INFO - __main__ - Step 139588: {'lr': 6.082318315514118e-06, 'samples': 26800896, 'steps': 139587, 'loss/train': 0.44268926978111267} 08/31/2021 14:35:36 - INFO - __main__ - Step 139589: {'lr': 6.081154914324955e-06, 'samples': 26801088, 'steps': 139588, 'loss/train': 0.02006641961634159} 08/31/2021 14:35:36 - INFO - __main__ - Step 139590: {'lr': 6.079991623041848e-06, 'samples': 26801280, 'steps': 139589, 'loss/train': 0.5693787932395935} 08/31/2021 14:35:38 - INFO - __main__ - Step 139591: {'lr': 6.0788284416653235e-06, 'samples': 26801472, 'steps': 139590, 'loss/train': 1.473486065864563} 08/31/2021 14:35:39 - INFO - __main__ - Step 139592: {'lr': 6.077665370195912e-06, 'samples': 26801664, 'steps': 139591, 'loss/train': 0.8381140828132629} 08/31/2021 14:35:39 - INFO - __main__ - Step 139593: {'lr': 6.0765024086341384e-06, 'samples': 26801856, 'steps': 139592, 'loss/train': 1.304916501045227} 08/31/2021 14:35:39 - INFO - __main__ - Step 139594: {'lr': 6.0753395569805304e-06, 'samples': 26802048, 'steps': 139593, 'loss/train': 1.080363154411316} 08/31/2021 14:35:40 - INFO - __main__ - Step 139595: {'lr': 6.074176815235615e-06, 'samples': 26802240, 'steps': 139594, 'loss/train': 1.3576799631118774} 08/31/2021 14:35:42 - INFO - __main__ - Step 139596: {'lr': 6.073014183399894e-06, 'samples': 26802432, 'steps': 139595, 'loss/train': 1.2872083187103271} 08/31/2021 14:35:42 - INFO - __main__ - Step 139597: {'lr': 6.07185166147392e-06, 'samples': 26802624, 'steps': 139596, 'loss/train': 0.9170641899108887} 08/31/2021 14:35:43 - INFO - __main__ - Step 139598: {'lr': 6.070689249458222e-06, 'samples': 26802816, 'steps': 139597, 'loss/train': 0.9306852221488953} 08/31/2021 14:35:43 - INFO - __main__ - Step 139599: {'lr': 6.069526947353299e-06, 'samples': 26803008, 'steps': 139598, 'loss/train': 0.5850197672843933} 08/31/2021 14:35:43 - INFO - __main__ - Step 139600: {'lr': 6.068364755159678e-06, 'samples': 26803200, 'steps': 139599, 'loss/train': 1.4699468612670898} 08/31/2021 14:35:45 - INFO - __main__ - Step 139601: {'lr': 6.067202672877886e-06, 'samples': 26803392, 'steps': 139600, 'loss/train': 1.030303955078125} 08/31/2021 14:35:46 - INFO - __main__ - Step 139602: {'lr': 6.06604070050848e-06, 'samples': 26803584, 'steps': 139601, 'loss/train': 0.31781265139579773} 08/31/2021 14:35:46 - INFO - __main__ - Step 139603: {'lr': 6.064878838051902e-06, 'samples': 26803776, 'steps': 139602, 'loss/train': 0.7814544439315796} 08/31/2021 14:35:46 - INFO - __main__ - Step 139604: {'lr': 6.063717085508763e-06, 'samples': 26803968, 'steps': 139603, 'loss/train': 1.0604372024536133} 08/31/2021 14:35:47 - INFO - __main__ - Step 139605: {'lr': 6.062555442879508e-06, 'samples': 26804160, 'steps': 139604, 'loss/train': 0.12189244478940964} 08/31/2021 14:35:47 - INFO - __main__ - Step 139606: {'lr': 6.061393910164747e-06, 'samples': 26804352, 'steps': 139605, 'loss/train': 1.2573539018630981} 08/31/2021 14:35:47 - INFO - __main__ - Step 139607: {'lr': 6.060232487364925e-06, 'samples': 26804544, 'steps': 139606, 'loss/train': 0.6165686845779419} 08/31/2021 14:35:49 - INFO - __main__ - Step 139608: {'lr': 6.059071174480623e-06, 'samples': 26804736, 'steps': 139607, 'loss/train': 1.3775477409362793} 08/31/2021 14:35:49 - INFO - __main__ - Step 139609: {'lr': 6.057909971512315e-06, 'samples': 26804928, 'steps': 139608, 'loss/train': 0.6074534058570862} 08/31/2021 14:35:50 - INFO - __main__ - Step 139610: {'lr': 6.056748878460555e-06, 'samples': 26805120, 'steps': 139609, 'loss/train': 1.0687483549118042} 08/31/2021 14:35:50 - INFO - __main__ - Step 139611: {'lr': 6.0555878953258704e-06, 'samples': 26805312, 'steps': 139610, 'loss/train': 1.574722170829773} 08/31/2021 14:35:50 - INFO - __main__ - Step 139612: {'lr': 6.054427022108761e-06, 'samples': 26805504, 'steps': 139611, 'loss/train': 1.3227858543395996} 08/31/2021 14:35:52 - INFO - __main__ - Step 139613: {'lr': 6.053266258809781e-06, 'samples': 26805696, 'steps': 139612, 'loss/train': 0.9835548400878906} 08/31/2021 14:35:52 - INFO - __main__ - Step 139614: {'lr': 6.052105605429403e-06, 'samples': 26805888, 'steps': 139613, 'loss/train': 0.5723028779029846} 08/31/2021 14:35:53 - INFO - __main__ - Step 139615: {'lr': 6.050945061968238e-06, 'samples': 26806080, 'steps': 139614, 'loss/train': 1.3906162977218628} 08/31/2021 14:35:53 - INFO - __main__ - Step 139616: {'lr': 6.049784628426702e-06, 'samples': 26806272, 'steps': 139615, 'loss/train': 1.097365379333496} 08/31/2021 14:35:53 - INFO - __main__ - Step 139617: {'lr': 6.048624304805378e-06, 'samples': 26806464, 'steps': 139616, 'loss/train': 0.5404582023620605} 08/31/2021 14:35:55 - INFO - __main__ - Step 139618: {'lr': 6.047464091104793e-06, 'samples': 26806656, 'steps': 139617, 'loss/train': 0.6452338695526123} 08/31/2021 14:35:55 - INFO - __main__ - Step 139619: {'lr': 6.046303987325446e-06, 'samples': 26806848, 'steps': 139618, 'loss/train': 0.9404325485229492} 08/31/2021 14:35:56 - INFO - __main__ - Step 139620: {'lr': 6.045143993467867e-06, 'samples': 26807040, 'steps': 139619, 'loss/train': 1.1375948190689087} 08/31/2021 14:35:56 - INFO - __main__ - Step 139621: {'lr': 6.0439841095325795e-06, 'samples': 26807232, 'steps': 139620, 'loss/train': 0.8010131120681763} 08/31/2021 14:35:56 - INFO - __main__ - Step 139622: {'lr': 6.042824335520114e-06, 'samples': 26807424, 'steps': 139621, 'loss/train': 1.0745540857315063} 08/31/2021 14:35:58 - INFO - __main__ - Step 139623: {'lr': 6.041664671430996e-06, 'samples': 26807616, 'steps': 139622, 'loss/train': 0.8098134994506836} 08/31/2021 14:35:58 - INFO - __main__ - Step 139624: {'lr': 6.040505117265727e-06, 'samples': 26807808, 'steps': 139623, 'loss/train': 0.7969546914100647} 08/31/2021 14:35:59 - INFO - __main__ - Step 139625: {'lr': 6.0393456730248595e-06, 'samples': 26808000, 'steps': 139624, 'loss/train': 1.714413046836853} 08/31/2021 14:35:59 - INFO - __main__ - Step 139626: {'lr': 6.038186338708868e-06, 'samples': 26808192, 'steps': 139625, 'loss/train': 1.3109345436096191} 08/31/2021 14:35:59 - INFO - __main__ - Step 139627: {'lr': 6.0370271143183335e-06, 'samples': 26808384, 'steps': 139626, 'loss/train': 0.17543594539165497} 08/31/2021 14:36:01 - INFO - __main__ - Step 139628: {'lr': 6.035867999853728e-06, 'samples': 26808576, 'steps': 139627, 'loss/train': 0.9624695777893066} 08/31/2021 14:36:01 - INFO - __main__ - Step 139629: {'lr': 6.0347089953156355e-06, 'samples': 26808768, 'steps': 139628, 'loss/train': 1.0849370956420898} 08/31/2021 14:36:02 - INFO - __main__ - Step 139630: {'lr': 6.033550100704526e-06, 'samples': 26808960, 'steps': 139629, 'loss/train': 1.2347866296768188} 08/31/2021 14:36:02 - INFO - __main__ - Step 139631: {'lr': 6.032391316020902e-06, 'samples': 26809152, 'steps': 139630, 'loss/train': 0.5474257469177246} 08/31/2021 14:36:02 - INFO - __main__ - Step 139632: {'lr': 6.031232641265344e-06, 'samples': 26809344, 'steps': 139631, 'loss/train': 0.8578488230705261} 08/31/2021 14:36:04 - INFO - __main__ - Step 139633: {'lr': 6.030074076438325e-06, 'samples': 26809536, 'steps': 139632, 'loss/train': 1.103855013847351} 08/31/2021 14:36:05 - INFO - __main__ - Step 139634: {'lr': 6.028915621540398e-06, 'samples': 26809728, 'steps': 139633, 'loss/train': 0.27650874853134155} 08/31/2021 14:36:05 - INFO - __main__ - Step 139635: {'lr': 6.027757276572093e-06, 'samples': 26809920, 'steps': 139634, 'loss/train': 0.2560148239135742} 08/31/2021 14:36:05 - INFO - __main__ - Step 139636: {'lr': 6.026599041533909e-06, 'samples': 26810112, 'steps': 139635, 'loss/train': 1.9044727087020874} 08/31/2021 14:36:06 - INFO - __main__ - Step 139637: {'lr': 6.025440916426372e-06, 'samples': 26810304, 'steps': 139636, 'loss/train': 1.0047763586044312} 08/31/2021 14:36:07 - INFO - __main__ - Step 139638: {'lr': 6.024282901249984e-06, 'samples': 26810496, 'steps': 139637, 'loss/train': 1.1697803735733032} 08/31/2021 14:36:08 - INFO - __main__ - Step 139639: {'lr': 6.023124996005325e-06, 'samples': 26810688, 'steps': 139638, 'loss/train': 2.2382583618164062} 08/31/2021 14:36:08 - INFO - __main__ - Step 139640: {'lr': 6.0219672006928684e-06, 'samples': 26810880, 'steps': 139639, 'loss/train': 1.6392910480499268} 08/31/2021 14:36:08 - INFO - __main__ - Step 139641: {'lr': 6.020809515313141e-06, 'samples': 26811072, 'steps': 139640, 'loss/train': 1.1336671113967896} 08/31/2021 14:36:09 - INFO - __main__ - Step 139642: {'lr': 6.0196519398667e-06, 'samples': 26811264, 'steps': 139641, 'loss/train': 1.5770591497421265} 08/31/2021 14:36:10 - INFO - __main__ - Step 139643: {'lr': 6.018494474354014e-06, 'samples': 26811456, 'steps': 139642, 'loss/train': 1.1764256954193115} 08/31/2021 14:36:11 - INFO - __main__ - Step 139644: {'lr': 6.01733711877564e-06, 'samples': 26811648, 'steps': 139643, 'loss/train': 1.118346929550171} 08/31/2021 14:36:11 - INFO - __main__ - Step 139645: {'lr': 6.016179873132077e-06, 'samples': 26811840, 'steps': 139644, 'loss/train': 1.1849250793457031} 08/31/2021 14:36:11 - INFO - __main__ - Step 139646: {'lr': 6.015022737423853e-06, 'samples': 26812032, 'steps': 139645, 'loss/train': 0.5614433884620667} 08/31/2021 14:36:12 - INFO - __main__ - Step 139647: {'lr': 6.013865711651495e-06, 'samples': 26812224, 'steps': 139646, 'loss/train': 0.823748767375946} 08/31/2021 14:36:12 - INFO - __main__ - Step 139648: {'lr': 6.01270879581553e-06, 'samples': 26812416, 'steps': 139647, 'loss/train': 1.1114639043807983} 08/31/2021 14:36:14 - INFO - __main__ - Step 139649: {'lr': 6.011551989916486e-06, 'samples': 26812608, 'steps': 139648, 'loss/train': 1.5568208694458008} 08/31/2021 14:36:14 - INFO - __main__ - Step 139650: {'lr': 6.010395293954863e-06, 'samples': 26812800, 'steps': 139649, 'loss/train': 0.7505738139152527} 08/31/2021 14:36:15 - INFO - __main__ - Step 139651: {'lr': 6.009238707931186e-06, 'samples': 26812992, 'steps': 139650, 'loss/train': 1.017371416091919} 08/31/2021 14:36:15 - INFO - __main__ - Step 139652: {'lr': 6.008082231845985e-06, 'samples': 26813184, 'steps': 139651, 'loss/train': 0.24901844561100006} 08/31/2021 14:36:15 - INFO - __main__ - Step 139653: {'lr': 6.006925865699786e-06, 'samples': 26813376, 'steps': 139652, 'loss/train': 0.6911391019821167} 08/31/2021 14:36:16 - INFO - __main__ - Step 139654: {'lr': 6.005769609493089e-06, 'samples': 26813568, 'steps': 139653, 'loss/train': 1.748773455619812} 08/31/2021 14:36:18 - INFO - __main__ - Step 139655: {'lr': 6.0046134632264495e-06, 'samples': 26813760, 'steps': 139654, 'loss/train': 0.8478034138679504} 08/31/2021 14:36:18 - INFO - __main__ - Step 139656: {'lr': 6.003457426900366e-06, 'samples': 26813952, 'steps': 139655, 'loss/train': 1.0019530057907104} 08/31/2021 14:36:19 - INFO - __main__ - Step 139657: {'lr': 6.002301500515339e-06, 'samples': 26814144, 'steps': 139656, 'loss/train': 1.116974949836731} 08/31/2021 14:36:19 - INFO - __main__ - Step 139658: {'lr': 6.0011456840718955e-06, 'samples': 26814336, 'steps': 139657, 'loss/train': 1.2471331357955933} 08/31/2021 14:36:19 - INFO - __main__ - Step 139659: {'lr': 5.9999899775705916e-06, 'samples': 26814528, 'steps': 139658, 'loss/train': 0.9523196220397949} 08/31/2021 14:36:21 - INFO - __main__ - Step 139660: {'lr': 5.998834381011925e-06, 'samples': 26814720, 'steps': 139659, 'loss/train': 1.1612285375595093} 08/31/2021 14:36:21 - INFO - __main__ - Step 139661: {'lr': 5.997678894396424e-06, 'samples': 26814912, 'steps': 139660, 'loss/train': 0.8251524567604065} 08/31/2021 14:36:22 - INFO - __main__ - Step 139662: {'lr': 5.996523517724589e-06, 'samples': 26815104, 'steps': 139661, 'loss/train': 0.049442943185567856} 08/31/2021 14:36:22 - INFO - __main__ - Step 139663: {'lr': 5.995368250996947e-06, 'samples': 26815296, 'steps': 139662, 'loss/train': 0.6637808680534363} 08/31/2021 14:36:23 - INFO - __main__ - Step 139664: {'lr': 5.9942130942140516e-06, 'samples': 26815488, 'steps': 139663, 'loss/train': 1.02317214012146} 08/31/2021 14:36:24 - INFO - __main__ - Step 139665: {'lr': 5.993058047376376e-06, 'samples': 26815680, 'steps': 139664, 'loss/train': 0.5312003493309021} 08/31/2021 14:36:25 - INFO - __main__ - Step 139666: {'lr': 5.9919031104845035e-06, 'samples': 26815872, 'steps': 139665, 'loss/train': 1.257519245147705} 08/31/2021 14:36:25 - INFO - __main__ - Step 139667: {'lr': 5.990748283538877e-06, 'samples': 26816064, 'steps': 139666, 'loss/train': 1.0313339233398438} 08/31/2021 14:36:25 - INFO - __main__ - Step 139668: {'lr': 5.98959356654008e-06, 'samples': 26816256, 'steps': 139667, 'loss/train': 1.3827160596847534} 08/31/2021 14:36:26 - INFO - __main__ - Step 139669: {'lr': 5.988438959488584e-06, 'samples': 26816448, 'steps': 139668, 'loss/train': 1.1704134941101074} 08/31/2021 14:36:27 - INFO - __main__ - Step 139670: {'lr': 5.987284462384945e-06, 'samples': 26816640, 'steps': 139669, 'loss/train': 1.5208312273025513} 08/31/2021 14:36:27 - INFO - __main__ - Step 139671: {'lr': 5.986130075229662e-06, 'samples': 26816832, 'steps': 139670, 'loss/train': 0.327883780002594} 08/31/2021 14:36:28 - INFO - __main__ - Step 139672: {'lr': 5.984975798023262e-06, 'samples': 26817024, 'steps': 139671, 'loss/train': 0.6437751650810242} 08/31/2021 14:36:28 - INFO - __main__ - Step 139673: {'lr': 5.983821630766273e-06, 'samples': 26817216, 'steps': 139672, 'loss/train': 0.9637452363967896} 08/31/2021 14:36:28 - INFO - __main__ - Step 139674: {'lr': 5.982667573459194e-06, 'samples': 26817408, 'steps': 139673, 'loss/train': 0.37188592553138733} 08/31/2021 14:36:30 - INFO - __main__ - Step 139675: {'lr': 5.98151362610258e-06, 'samples': 26817600, 'steps': 139674, 'loss/train': 1.1270246505737305} 08/31/2021 14:36:31 - INFO - __main__ - Step 139676: {'lr': 5.980359788696904e-06, 'samples': 26817792, 'steps': 139675, 'loss/train': 1.756685733795166} 08/31/2021 14:36:31 - INFO - __main__ - Step 139677: {'lr': 5.979206061242776e-06, 'samples': 26817984, 'steps': 139676, 'loss/train': 1.418411374092102} 08/31/2021 14:36:31 - INFO - __main__ - Step 139678: {'lr': 5.978052443740584e-06, 'samples': 26818176, 'steps': 139677, 'loss/train': 1.5489318370819092} 08/31/2021 14:36:32 - INFO - __main__ - Step 139679: {'lr': 5.976898936190939e-06, 'samples': 26818368, 'steps': 139678, 'loss/train': 1.3084219694137573} 08/31/2021 14:36:32 - INFO - __main__ - Step 139680: {'lr': 5.97574553859434e-06, 'samples': 26818560, 'steps': 139679, 'loss/train': 1.4007470607757568} 08/31/2021 14:36:33 - INFO - __main__ - Step 139681: {'lr': 5.974592250951316e-06, 'samples': 26818752, 'steps': 139680, 'loss/train': 1.1794754266738892} 08/31/2021 14:36:34 - INFO - __main__ - Step 139682: {'lr': 5.973439073262366e-06, 'samples': 26818944, 'steps': 139681, 'loss/train': 1.2966300249099731} 08/31/2021 14:36:34 - INFO - __main__ - Step 139683: {'lr': 5.972286005527988e-06, 'samples': 26819136, 'steps': 139682, 'loss/train': 5.43107795715332} 08/31/2021 14:36:35 - INFO - __main__ - Step 139684: {'lr': 5.9711330477487666e-06, 'samples': 26819328, 'steps': 139683, 'loss/train': 0.9972187280654907} 08/31/2021 14:36:35 - INFO - __main__ - Step 139685: {'lr': 5.969980199925174e-06, 'samples': 26819520, 'steps': 139684, 'loss/train': 1.1442679166793823} 08/31/2021 14:36:36 - INFO - __main__ - Step 139686: {'lr': 5.968827462057763e-06, 'samples': 26819712, 'steps': 139685, 'loss/train': 0.7149671316146851} 08/31/2021 14:36:37 - INFO - __main__ - Step 139687: {'lr': 5.967674834147035e-06, 'samples': 26819904, 'steps': 139686, 'loss/train': 0.9307955503463745} 08/31/2021 14:36:37 - INFO - __main__ - Step 139688: {'lr': 5.96652231619349e-06, 'samples': 26820096, 'steps': 139687, 'loss/train': 0.9732015132904053} 08/31/2021 14:36:38 - INFO - __main__ - Step 139689: {'lr': 5.9653699081976545e-06, 'samples': 26820288, 'steps': 139688, 'loss/train': 0.22115255892276764} 08/31/2021 14:36:38 - INFO - __main__ - Step 139690: {'lr': 5.964217610160055e-06, 'samples': 26820480, 'steps': 139689, 'loss/train': 1.3810453414916992} 08/31/2021 14:36:40 - INFO - __main__ - Step 139691: {'lr': 5.963065422081249e-06, 'samples': 26820672, 'steps': 139690, 'loss/train': 1.1422908306121826} 08/31/2021 14:36:40 - INFO - __main__ - Step 139692: {'lr': 5.961913343961678e-06, 'samples': 26820864, 'steps': 139691, 'loss/train': 0.9687336087226868} 08/31/2021 14:36:40 - INFO - __main__ - Step 139693: {'lr': 5.960761375801927e-06, 'samples': 26821056, 'steps': 139692, 'loss/train': 1.0465402603149414} 08/31/2021 14:36:41 - INFO - __main__ - Step 139694: {'lr': 5.959609517602493e-06, 'samples': 26821248, 'steps': 139693, 'loss/train': 1.1380579471588135} 08/31/2021 14:36:41 - INFO - __main__ - Step 139695: {'lr': 5.958457769363879e-06, 'samples': 26821440, 'steps': 139694, 'loss/train': 1.6750779151916504} 08/31/2021 14:36:43 - INFO - __main__ - Step 139696: {'lr': 5.957306131086609e-06, 'samples': 26821632, 'steps': 139695, 'loss/train': 1.3062609434127808} 08/31/2021 14:36:43 - INFO - __main__ - Step 139697: {'lr': 5.956154602771241e-06, 'samples': 26821824, 'steps': 139696, 'loss/train': 1.2335509061813354} 08/31/2021 14:36:43 - INFO - __main__ - Step 139698: {'lr': 5.955003184418273e-06, 'samples': 26822016, 'steps': 139697, 'loss/train': 1.3793197870254517} 08/31/2021 14:36:44 - INFO - __main__ - Step 139699: {'lr': 5.953851876028177e-06, 'samples': 26822208, 'steps': 139698, 'loss/train': 0.1657530516386032} 08/31/2021 14:36:44 - INFO - __main__ - Step 139700: {'lr': 5.952700677601536e-06, 'samples': 26822400, 'steps': 139699, 'loss/train': 2.194852590560913} 08/31/2021 14:36:44 - INFO - __main__ - Step 139701: {'lr': 5.951549589138822e-06, 'samples': 26822592, 'steps': 139700, 'loss/train': 1.598822832107544} 08/31/2021 14:36:46 - INFO - __main__ - Step 139702: {'lr': 5.9503986106405895e-06, 'samples': 26822784, 'steps': 139701, 'loss/train': 0.6733536124229431} 08/31/2021 14:36:47 - INFO - __main__ - Step 139703: {'lr': 5.949247742107311e-06, 'samples': 26822976, 'steps': 139702, 'loss/train': 0.9627152681350708} 08/31/2021 14:36:47 - INFO - __main__ - Step 139704: {'lr': 5.948096983539569e-06, 'samples': 26823168, 'steps': 139703, 'loss/train': 1.0849251747131348} 08/31/2021 14:36:47 - INFO - __main__ - Step 139705: {'lr': 5.946946334937836e-06, 'samples': 26823360, 'steps': 139704, 'loss/train': 1.1732808351516724} 08/31/2021 14:36:48 - INFO - __main__ - Step 139706: {'lr': 5.945795796302638e-06, 'samples': 26823552, 'steps': 139705, 'loss/train': 0.6175111532211304} 08/31/2021 14:36:50 - INFO - __main__ - Step 139707: {'lr': 5.9446453676345045e-06, 'samples': 26823744, 'steps': 139706, 'loss/train': 1.5620931386947632} 08/31/2021 14:36:51 - INFO - __main__ - Step 139708: {'lr': 5.943495048933961e-06, 'samples': 26823936, 'steps': 139707, 'loss/train': 0.8049655556678772} 08/31/2021 14:36:51 - INFO - __main__ - Step 139709: {'lr': 5.942344840201508e-06, 'samples': 26824128, 'steps': 139708, 'loss/train': 0.6339465975761414} 08/31/2021 14:36:51 - INFO - __main__ - Step 139710: {'lr': 5.941194741437672e-06, 'samples': 26824320, 'steps': 139709, 'loss/train': 0.015350564382970333} 08/31/2021 14:36:52 - INFO - __main__ - Step 139711: {'lr': 5.9400447526429535e-06, 'samples': 26824512, 'steps': 139710, 'loss/train': 1.3004616498947144} 08/31/2021 14:36:52 - INFO - __main__ - Step 139712: {'lr': 5.938894873817879e-06, 'samples': 26824704, 'steps': 139711, 'loss/train': 0.7314650416374207} 08/31/2021 14:36:53 - INFO - __main__ - Step 139713: {'lr': 5.937745104962977e-06, 'samples': 26824896, 'steps': 139712, 'loss/train': 1.0998804569244385} 08/31/2021 14:36:54 - INFO - __main__ - Step 139714: {'lr': 5.936595446078774e-06, 'samples': 26825088, 'steps': 139713, 'loss/train': 0.5371286273002625} 08/31/2021 14:36:54 - INFO - __main__ - Step 139715: {'lr': 5.93544589716577e-06, 'samples': 26825280, 'steps': 139714, 'loss/train': 0.9783300161361694} 08/31/2021 14:36:55 - INFO - __main__ - Step 139716: {'lr': 5.934296458224464e-06, 'samples': 26825472, 'steps': 139715, 'loss/train': 1.5288552045822144} 08/31/2021 14:36:55 - INFO - __main__ - Step 139717: {'lr': 5.93314712925544e-06, 'samples': 26825664, 'steps': 139716, 'loss/train': 0.46991676092147827} 08/31/2021 14:36:56 - INFO - __main__ - Step 139718: {'lr': 5.931997910259141e-06, 'samples': 26825856, 'steps': 139717, 'loss/train': 1.2692275047302246} 08/31/2021 14:36:57 - INFO - __main__ - Step 139719: {'lr': 5.930848801236122e-06, 'samples': 26826048, 'steps': 139718, 'loss/train': 1.19529390335083} 08/31/2021 14:36:57 - INFO - __main__ - Step 139720: {'lr': 5.929699802186911e-06, 'samples': 26826240, 'steps': 139719, 'loss/train': 0.8627061247825623} 08/31/2021 14:36:57 - INFO - __main__ - Step 139721: {'lr': 5.928550913112008e-06, 'samples': 26826432, 'steps': 139720, 'loss/train': 1.3447364568710327} 08/31/2021 14:36:58 - INFO - __main__ - Step 139722: {'lr': 5.927402134011911e-06, 'samples': 26826624, 'steps': 139721, 'loss/train': 0.8548375368118286} 08/31/2021 14:36:59 - INFO - __main__ - Step 139723: {'lr': 5.926253464887204e-06, 'samples': 26826816, 'steps': 139722, 'loss/train': 0.7333231568336487} 08/31/2021 14:37:00 - INFO - __main__ - Step 139724: {'lr': 5.925104905738332e-06, 'samples': 26827008, 'steps': 139723, 'loss/train': 1.6333853006362915} 08/31/2021 14:37:00 - INFO - __main__ - Step 139725: {'lr': 5.9239564565658485e-06, 'samples': 26827200, 'steps': 139724, 'loss/train': 1.080147385597229} 08/31/2021 14:37:01 - INFO - __main__ - Step 139726: {'lr': 5.922808117370254e-06, 'samples': 26827392, 'steps': 139725, 'loss/train': 1.0217186212539673} 08/31/2021 14:37:01 - INFO - __main__ - Step 139727: {'lr': 5.921659888152075e-06, 'samples': 26827584, 'steps': 139726, 'loss/train': 1.3313302993774414} 08/31/2021 14:37:02 - INFO - __main__ - Step 139728: {'lr': 5.92051176891184e-06, 'samples': 26827776, 'steps': 139727, 'loss/train': 0.6800126433372498} 08/31/2021 14:37:03 - INFO - __main__ - Step 139729: {'lr': 5.919363759650049e-06, 'samples': 26827968, 'steps': 139728, 'loss/train': 1.3982162475585938} 08/31/2021 14:37:03 - INFO - __main__ - Step 139730: {'lr': 5.918215860367227e-06, 'samples': 26828160, 'steps': 139729, 'loss/train': 0.35450446605682373} 08/31/2021 14:37:04 - INFO - __main__ - Step 139731: {'lr': 5.917068071063902e-06, 'samples': 26828352, 'steps': 139730, 'loss/train': 0.8296588659286499} 08/31/2021 14:37:04 - INFO - __main__ - Step 139732: {'lr': 5.915920391740548e-06, 'samples': 26828544, 'steps': 139731, 'loss/train': 0.8146635890007019} 08/31/2021 14:37:05 - INFO - __main__ - Step 139733: {'lr': 5.914772822397746e-06, 'samples': 26828736, 'steps': 139732, 'loss/train': 0.8627064228057861} 08/31/2021 14:37:06 - INFO - __main__ - Step 139734: {'lr': 5.913625363035969e-06, 'samples': 26828928, 'steps': 139733, 'loss/train': 0.9783971905708313} 08/31/2021 14:37:06 - INFO - __main__ - Step 139735: {'lr': 5.912478013655742e-06, 'samples': 26829120, 'steps': 139734, 'loss/train': 1.3888996839523315} 08/31/2021 14:37:07 - INFO - __main__ - Step 139736: {'lr': 5.911330774257623e-06, 'samples': 26829312, 'steps': 139735, 'loss/train': 1.3771893978118896} 08/31/2021 14:37:07 - INFO - __main__ - Step 139737: {'lr': 5.910183644842054e-06, 'samples': 26829504, 'steps': 139736, 'loss/train': 1.0351641178131104} 08/31/2021 14:37:07 - INFO - __main__ - Step 139738: {'lr': 5.909036625409592e-06, 'samples': 26829696, 'steps': 139737, 'loss/train': 0.918134868144989} 08/31/2021 14:37:09 - INFO - __main__ - Step 139739: {'lr': 5.907889715960762e-06, 'samples': 26829888, 'steps': 139738, 'loss/train': 0.7799234390258789} 08/31/2021 14:37:09 - INFO - __main__ - Step 139740: {'lr': 5.9067429164960665e-06, 'samples': 26830080, 'steps': 139739, 'loss/train': 1.7758039236068726} 08/31/2021 14:37:10 - INFO - __main__ - Step 139741: {'lr': 5.90559622701603e-06, 'samples': 26830272, 'steps': 139740, 'loss/train': 1.1589925289154053} 08/31/2021 14:37:10 - INFO - __main__ - Step 139742: {'lr': 5.904449647521154e-06, 'samples': 26830464, 'steps': 139741, 'loss/train': 0.7409001588821411} 08/31/2021 14:37:10 - INFO - __main__ - Step 139743: {'lr': 5.903303178011965e-06, 'samples': 26830656, 'steps': 139742, 'loss/train': 1.089630365371704} 08/31/2021 14:37:12 - INFO - __main__ - Step 139744: {'lr': 5.90215681848899e-06, 'samples': 26830848, 'steps': 139743, 'loss/train': 1.4593933820724487} 08/31/2021 14:37:12 - INFO - __main__ - Step 139745: {'lr': 5.90101056895273e-06, 'samples': 26831040, 'steps': 139744, 'loss/train': 0.9085595011711121} 08/31/2021 14:37:13 - INFO - __main__ - Step 139746: {'lr': 5.899864429403712e-06, 'samples': 26831232, 'steps': 139745, 'loss/train': 1.0250976085662842} 08/31/2021 14:37:13 - INFO - __main__ - Step 139747: {'lr': 5.898718399842435e-06, 'samples': 26831424, 'steps': 139746, 'loss/train': 0.9072651267051697} 08/31/2021 14:37:13 - INFO - __main__ - Step 139748: {'lr': 5.897572480269453e-06, 'samples': 26831616, 'steps': 139747, 'loss/train': 0.035171400755643845} 08/31/2021 14:37:15 - INFO - __main__ - Step 139749: {'lr': 5.89642667068524e-06, 'samples': 26831808, 'steps': 139748, 'loss/train': 1.9233683347702026} 08/31/2021 14:37:16 - INFO - __main__ - Step 139750: {'lr': 5.89528097109035e-06, 'samples': 26832000, 'steps': 139749, 'loss/train': 1.0337542295455933} 08/31/2021 14:37:16 - INFO - __main__ - Step 139751: {'lr': 5.8941353814852825e-06, 'samples': 26832192, 'steps': 139750, 'loss/train': 1.3391737937927246} 08/31/2021 14:37:16 - INFO - __main__ - Step 139752: {'lr': 5.892989901870538e-06, 'samples': 26832384, 'steps': 139751, 'loss/train': 0.8425461649894714} 08/31/2021 14:37:17 - INFO - __main__ - Step 139753: {'lr': 5.891844532246643e-06, 'samples': 26832576, 'steps': 139752, 'loss/train': 1.2153198719024658} 08/31/2021 14:37:17 - INFO - __main__ - Step 139754: {'lr': 5.890699272614097e-06, 'samples': 26832768, 'steps': 139753, 'loss/train': 0.021031932905316353} 08/31/2021 14:37:18 - INFO - __main__ - Step 139755: {'lr': 5.8895541229734566e-06, 'samples': 26832960, 'steps': 139754, 'loss/train': 1.0405329465866089} 08/31/2021 14:37:19 - INFO - __main__ - Step 139756: {'lr': 5.888409083325219e-06, 'samples': 26833152, 'steps': 139755, 'loss/train': 1.208714246749878} 08/31/2021 14:37:19 - INFO - __main__ - Step 139757: {'lr': 5.8872641536698856e-06, 'samples': 26833344, 'steps': 139756, 'loss/train': 1.6060378551483154} 08/31/2021 14:37:20 - INFO - __main__ - Step 139758: {'lr': 5.886119334007984e-06, 'samples': 26833536, 'steps': 139757, 'loss/train': 1.1261942386627197} 08/31/2021 14:37:20 - INFO - __main__ - Step 139759: {'lr': 5.8849746243400395e-06, 'samples': 26833728, 'steps': 139758, 'loss/train': 0.5982564091682434} 08/31/2021 14:37:23 - INFO - __main__ - Step 139760: {'lr': 5.883830024666553e-06, 'samples': 26833920, 'steps': 139759, 'loss/train': 1.1261866092681885} 08/31/2021 14:37:23 - INFO - __main__ - Step 139761: {'lr': 5.882685534988053e-06, 'samples': 26834112, 'steps': 139760, 'loss/train': 1.0152907371520996} 08/31/2021 14:37:24 - INFO - __main__ - Step 139762: {'lr': 5.881541155305037e-06, 'samples': 26834304, 'steps': 139761, 'loss/train': 0.013952012173831463} 08/31/2021 14:37:24 - INFO - __main__ - Step 139763: {'lr': 5.880396885618061e-06, 'samples': 26834496, 'steps': 139762, 'loss/train': 0.01439199410378933} 08/31/2021 14:37:24 - INFO - __main__ - Step 139764: {'lr': 5.879252725927598e-06, 'samples': 26834688, 'steps': 139763, 'loss/train': 0.654433012008667} 08/31/2021 14:37:25 - INFO - __main__ - Step 139765: {'lr': 5.8781086762341455e-06, 'samples': 26834880, 'steps': 139764, 'loss/train': 0.6008455753326416} 08/31/2021 14:37:25 - INFO - __main__ - Step 139766: {'lr': 5.8769647365382875e-06, 'samples': 26835072, 'steps': 139765, 'loss/train': 0.6862082481384277} 08/31/2021 14:37:27 - INFO - __main__ - Step 139767: {'lr': 5.8758209068404675e-06, 'samples': 26835264, 'steps': 139766, 'loss/train': 1.1598155498504639} 08/31/2021 14:37:27 - INFO - __main__ - Step 139768: {'lr': 5.87467718714127e-06, 'samples': 26835456, 'steps': 139767, 'loss/train': 1.1135090589523315} 08/31/2021 14:37:27 - INFO - __main__ - Step 139769: {'lr': 5.873533577441164e-06, 'samples': 26835648, 'steps': 139768, 'loss/train': 1.2967503070831299} 08/31/2021 14:37:28 - INFO - __main__ - Step 139770: {'lr': 5.872390077740653e-06, 'samples': 26835840, 'steps': 139769, 'loss/train': 1.4562386274337769} 08/31/2021 14:37:28 - INFO - __main__ - Step 139771: {'lr': 5.871246688040316e-06, 'samples': 26836032, 'steps': 139770, 'loss/train': 1.204450249671936} 08/31/2021 14:37:30 - INFO - __main__ - Step 139772: {'lr': 5.870103408340599e-06, 'samples': 26836224, 'steps': 139771, 'loss/train': 0.26958978176116943} 08/31/2021 14:37:30 - INFO - __main__ - Step 139773: {'lr': 5.868960238642057e-06, 'samples': 26836416, 'steps': 139772, 'loss/train': 0.7131580710411072} 08/31/2021 14:37:31 - INFO - __main__ - Step 139774: {'lr': 5.86781717894519e-06, 'samples': 26836608, 'steps': 139773, 'loss/train': 0.6689476370811462} 08/31/2021 14:37:31 - INFO - __main__ - Step 139775: {'lr': 5.866674229250524e-06, 'samples': 26836800, 'steps': 139774, 'loss/train': 0.07876290380954742} 08/31/2021 14:37:31 - INFO - __main__ - Step 139776: {'lr': 5.865531389558559e-06, 'samples': 26836992, 'steps': 139775, 'loss/train': 0.16976436972618103} 08/31/2021 14:37:33 - INFO - __main__ - Step 139777: {'lr': 5.864388659869824e-06, 'samples': 26837184, 'steps': 139776, 'loss/train': 0.801527202129364} 08/31/2021 14:37:33 - INFO - __main__ - Step 139778: {'lr': 5.863246040184844e-06, 'samples': 26837376, 'steps': 139777, 'loss/train': 1.196319341659546} 08/31/2021 14:37:34 - INFO - __main__ - Step 139779: {'lr': 5.862103530504092e-06, 'samples': 26837568, 'steps': 139778, 'loss/train': 1.5394411087036133} 08/31/2021 14:37:34 - INFO - __main__ - Step 139780: {'lr': 5.860961130828124e-06, 'samples': 26837760, 'steps': 139779, 'loss/train': 1.2498908042907715} 08/31/2021 14:37:34 - INFO - __main__ - Step 139781: {'lr': 5.85981884115741e-06, 'samples': 26837952, 'steps': 139780, 'loss/train': 1.6790122985839844} 08/31/2021 14:37:36 - INFO - __main__ - Step 139782: {'lr': 5.858676661492535e-06, 'samples': 26838144, 'steps': 139781, 'loss/train': 1.1161980628967285} 08/31/2021 14:37:36 - INFO - __main__ - Step 139783: {'lr': 5.85753459183394e-06, 'samples': 26838336, 'steps': 139782, 'loss/train': 0.9409764409065247} 08/31/2021 14:37:37 - INFO - __main__ - Step 139784: {'lr': 5.856392632182184e-06, 'samples': 26838528, 'steps': 139783, 'loss/train': 0.46637511253356934} 08/31/2021 14:37:37 - INFO - __main__ - Step 139785: {'lr': 5.855250782537791e-06, 'samples': 26838720, 'steps': 139784, 'loss/train': 0.7904491424560547} 08/31/2021 14:37:38 - INFO - __main__ - Step 139786: {'lr': 5.8541090429012346e-06, 'samples': 26838912, 'steps': 139785, 'loss/train': 1.4411555528640747} 08/31/2021 14:37:39 - INFO - __main__ - Step 139787: {'lr': 5.852967413273042e-06, 'samples': 26839104, 'steps': 139786, 'loss/train': 1.5509651899337769} 08/31/2021 14:37:39 - INFO - __main__ - Step 139788: {'lr': 5.8518258936537394e-06, 'samples': 26839296, 'steps': 139787, 'loss/train': 0.6165255308151245} 08/31/2021 14:37:40 - INFO - __main__ - Step 139789: {'lr': 5.850684484043856e-06, 'samples': 26839488, 'steps': 139788, 'loss/train': 1.5360766649246216} 08/31/2021 14:37:40 - INFO - __main__ - Step 139790: {'lr': 5.84954318444389e-06, 'samples': 26839680, 'steps': 139789, 'loss/train': 1.426904559135437} 08/31/2021 14:37:40 - INFO - __main__ - Step 139791: {'lr': 5.848401994854341e-06, 'samples': 26839872, 'steps': 139790, 'loss/train': 1.184859275817871} 08/31/2021 14:37:42 - INFO - __main__ - Step 139792: {'lr': 5.847260915275737e-06, 'samples': 26840064, 'steps': 139791, 'loss/train': 1.3575776815414429} 08/31/2021 14:37:42 - INFO - __main__ - Step 139793: {'lr': 5.846119945708578e-06, 'samples': 26840256, 'steps': 139792, 'loss/train': 1.4991707801818848} 08/31/2021 14:37:43 - INFO - __main__ - Step 139794: {'lr': 5.8449790861533906e-06, 'samples': 26840448, 'steps': 139793, 'loss/train': 1.22939932346344} 08/31/2021 14:37:43 - INFO - __main__ - Step 139795: {'lr': 5.843838336610674e-06, 'samples': 26840640, 'steps': 139794, 'loss/train': 0.7020621299743652} 08/31/2021 14:37:43 - INFO - __main__ - Step 139796: {'lr': 5.842697697080984e-06, 'samples': 26840832, 'steps': 139795, 'loss/train': 1.0598113536834717} 08/31/2021 14:37:45 - INFO - __main__ - Step 139797: {'lr': 5.8415571675647925e-06, 'samples': 26841024, 'steps': 139796, 'loss/train': 2.1691832542419434} 08/31/2021 14:37:45 - INFO - __main__ - Step 139798: {'lr': 5.840416748062627e-06, 'samples': 26841216, 'steps': 139797, 'loss/train': 1.1575688123703003} 08/31/2021 14:37:46 - INFO - __main__ - Step 139799: {'lr': 5.839276438575014e-06, 'samples': 26841408, 'steps': 139798, 'loss/train': 0.556932270526886} 08/31/2021 14:37:46 - INFO - __main__ - Step 139800: {'lr': 5.838136239102454e-06, 'samples': 26841600, 'steps': 139799, 'loss/train': 1.6124509572982788} 08/31/2021 14:37:47 - INFO - __main__ - Step 139801: {'lr': 5.836996149645446e-06, 'samples': 26841792, 'steps': 139800, 'loss/train': 0.9197696447372437} 08/31/2021 14:37:48 - INFO - __main__ - Step 139802: {'lr': 5.835856170204517e-06, 'samples': 26841984, 'steps': 139801, 'loss/train': 0.9787657260894775} 08/31/2021 14:37:48 - INFO - __main__ - Step 139803: {'lr': 5.834716300780197e-06, 'samples': 26842176, 'steps': 139802, 'loss/train': 1.0090179443359375} 08/31/2021 14:37:49 - INFO - __main__ - Step 139804: {'lr': 5.8335765413730094e-06, 'samples': 26842368, 'steps': 139803, 'loss/train': 1.059772253036499} 08/31/2021 14:37:49 - INFO - __main__ - Step 139805: {'lr': 5.8324368919834285e-06, 'samples': 26842560, 'steps': 139804, 'loss/train': 1.3413524627685547} 08/31/2021 14:37:49 - INFO - __main__ - Step 139806: {'lr': 5.8312973526119806e-06, 'samples': 26842752, 'steps': 139805, 'loss/train': 1.316676139831543} 08/31/2021 14:37:51 - INFO - __main__ - Step 139807: {'lr': 5.830157923259166e-06, 'samples': 26842944, 'steps': 139806, 'loss/train': 1.5774716138839722} 08/31/2021 14:37:52 - INFO - __main__ - Step 139808: {'lr': 5.82901860392554e-06, 'samples': 26843136, 'steps': 139807, 'loss/train': 0.4879215657711029} 08/31/2021 14:37:52 - INFO - __main__ - Step 139809: {'lr': 5.827879394611574e-06, 'samples': 26843328, 'steps': 139808, 'loss/train': 1.0238316059112549} 08/31/2021 14:37:52 - INFO - __main__ - Step 139810: {'lr': 5.826740295317795e-06, 'samples': 26843520, 'steps': 139809, 'loss/train': 1.8167005777359009} 08/31/2021 14:37:53 - INFO - __main__ - Step 139811: {'lr': 5.825601306044703e-06, 'samples': 26843712, 'steps': 139810, 'loss/train': 0.7654091715812683} 08/31/2021 14:37:55 - INFO - __main__ - Step 139812: {'lr': 5.824462426792854e-06, 'samples': 26843904, 'steps': 139811, 'loss/train': 0.5577923059463501} 08/31/2021 14:37:55 - INFO - __main__ - Step 139813: {'lr': 5.823323657562745e-06, 'samples': 26844096, 'steps': 139812, 'loss/train': 0.8791812658309937} 08/31/2021 14:37:55 - INFO - __main__ - Step 139814: {'lr': 5.822184998354852e-06, 'samples': 26844288, 'steps': 139813, 'loss/train': 1.708097219467163} 08/31/2021 14:37:56 - INFO - __main__ - Step 139815: {'lr': 5.821046449169726e-06, 'samples': 26844480, 'steps': 139814, 'loss/train': 1.0651977062225342} 08/31/2021 14:37:56 - INFO - __main__ - Step 139816: {'lr': 5.819908010007868e-06, 'samples': 26844672, 'steps': 139815, 'loss/train': 1.093816876411438} 08/31/2021 14:37:56 - INFO - __main__ - Step 139817: {'lr': 5.8187696808698065e-06, 'samples': 26844864, 'steps': 139816, 'loss/train': 0.10304555296897888} 08/31/2021 14:37:59 - INFO - __main__ - Step 139818: {'lr': 5.81763146175604e-06, 'samples': 26845056, 'steps': 139817, 'loss/train': 0.950945258140564} 08/31/2021 14:37:59 - INFO - __main__ - Step 139819: {'lr': 5.816493352667041e-06, 'samples': 26845248, 'steps': 139818, 'loss/train': 0.8965442776679993} 08/31/2021 14:37:59 - INFO - __main__ - Step 139820: {'lr': 5.815355353603391e-06, 'samples': 26845440, 'steps': 139819, 'loss/train': 0.6947621703147888} 08/31/2021 14:38:00 - INFO - __main__ - Step 139821: {'lr': 5.814217464565563e-06, 'samples': 26845632, 'steps': 139820, 'loss/train': 0.12645865976810455} 08/31/2021 14:38:00 - INFO - __main__ - Step 139822: {'lr': 5.813079685554084e-06, 'samples': 26845824, 'steps': 139821, 'loss/train': 1.6456800699234009} 08/31/2021 14:38:02 - INFO - __main__ - Step 139823: {'lr': 5.8119420165694824e-06, 'samples': 26846016, 'steps': 139822, 'loss/train': 1.307974100112915} 08/31/2021 14:38:02 - INFO - __main__ - Step 139824: {'lr': 5.8108044576122285e-06, 'samples': 26846208, 'steps': 139823, 'loss/train': 1.8237465620040894} 08/31/2021 14:38:03 - INFO - __main__ - Step 139825: {'lr': 5.809667008682851e-06, 'samples': 26846400, 'steps': 139824, 'loss/train': 0.6992360949516296} 08/31/2021 14:38:03 - INFO - __main__ - Step 139826: {'lr': 5.808529669781903e-06, 'samples': 26846592, 'steps': 139825, 'loss/train': 1.0857443809509277} 08/31/2021 14:38:03 - INFO - __main__ - Step 139827: {'lr': 5.807392440909831e-06, 'samples': 26846784, 'steps': 139826, 'loss/train': 0.8872742652893066} 08/31/2021 14:38:04 - INFO - __main__ - Step 139828: {'lr': 5.8062553220671885e-06, 'samples': 26846976, 'steps': 139827, 'loss/train': 0.7948470711708069} 08/31/2021 14:38:05 - INFO - __main__ - Step 139829: {'lr': 5.805118313254476e-06, 'samples': 26847168, 'steps': 139828, 'loss/train': 1.0087834596633911} 08/31/2021 14:38:06 - INFO - __main__ - Step 139830: {'lr': 5.80398141447222e-06, 'samples': 26847360, 'steps': 139829, 'loss/train': 1.4118703603744507} 08/31/2021 14:38:06 - INFO - __main__ - Step 139831: {'lr': 5.802844625720949e-06, 'samples': 26847552, 'steps': 139830, 'loss/train': 0.2664247751235962} 08/31/2021 14:38:06 - INFO - __main__ - Step 139832: {'lr': 5.801707947001106e-06, 'samples': 26847744, 'steps': 139831, 'loss/train': 1.6995563507080078} 08/31/2021 14:38:07 - INFO - __main__ - Step 139833: {'lr': 5.8005713783132744e-06, 'samples': 26847936, 'steps': 139832, 'loss/train': 2.103076457977295} 08/31/2021 14:38:08 - INFO - __main__ - Step 139834: {'lr': 5.799434919657897e-06, 'samples': 26848128, 'steps': 139833, 'loss/train': 1.546338677406311} 08/31/2021 14:38:09 - INFO - __main__ - Step 139835: {'lr': 5.798298571035559e-06, 'samples': 26848320, 'steps': 139834, 'loss/train': 0.748898446559906} 08/31/2021 14:38:09 - INFO - __main__ - Step 139836: {'lr': 5.797162332446731e-06, 'samples': 26848512, 'steps': 139835, 'loss/train': 1.1177730560302734} 08/31/2021 14:38:09 - INFO - __main__ - Step 139837: {'lr': 5.796026203891913e-06, 'samples': 26848704, 'steps': 139836, 'loss/train': 0.676557183265686} 08/31/2021 14:38:10 - INFO - __main__ - Step 139838: {'lr': 5.79489018537166e-06, 'samples': 26848896, 'steps': 139837, 'loss/train': 1.400566577911377} 08/31/2021 14:38:11 - INFO - __main__ - Step 139839: {'lr': 5.793754276886443e-06, 'samples': 26849088, 'steps': 139838, 'loss/train': 0.028915872797369957} 08/31/2021 14:38:12 - INFO - __main__ - Step 139840: {'lr': 5.792618478436817e-06, 'samples': 26849280, 'steps': 139839, 'loss/train': 1.563847541809082} 08/31/2021 14:38:12 - INFO - __main__ - Step 139841: {'lr': 5.791482790023256e-06, 'samples': 26849472, 'steps': 139840, 'loss/train': 0.04066051170229912} 08/31/2021 14:38:13 - INFO - __main__ - Step 139842: {'lr': 5.790347211646285e-06, 'samples': 26849664, 'steps': 139841, 'loss/train': 0.04400991275906563} 08/31/2021 14:38:13 - INFO - __main__ - Step 139843: {'lr': 5.789211743306405e-06, 'samples': 26849856, 'steps': 139842, 'loss/train': 1.345499038696289} 08/31/2021 14:38:15 - INFO - __main__ - Step 139844: {'lr': 5.788076385004171e-06, 'samples': 26850048, 'steps': 139843, 'loss/train': 0.03524855151772499} 08/31/2021 14:38:15 - INFO - __main__ - Step 139845: {'lr': 5.786941136740054e-06, 'samples': 26850240, 'steps': 139844, 'loss/train': 0.8743101954460144} 08/31/2021 14:38:16 - INFO - __main__ - Step 139846: {'lr': 5.7858059985145536e-06, 'samples': 26850432, 'steps': 139845, 'loss/train': 0.7339378595352173} 08/31/2021 14:38:16 - INFO - __main__ - Step 139847: {'lr': 5.784670970328198e-06, 'samples': 26850624, 'steps': 139846, 'loss/train': 1.4367122650146484} 08/31/2021 14:38:16 - INFO - __main__ - Step 139848: {'lr': 5.783536052181515e-06, 'samples': 26850816, 'steps': 139847, 'loss/train': 0.38904276490211487} 08/31/2021 14:38:18 - INFO - __main__ - Step 139849: {'lr': 5.782401244074975e-06, 'samples': 26851008, 'steps': 139848, 'loss/train': 1.5935487747192383} 08/31/2021 14:38:18 - INFO - __main__ - Step 139850: {'lr': 5.781266546009134e-06, 'samples': 26851200, 'steps': 139849, 'loss/train': 1.3879207372665405} 08/31/2021 14:38:19 - INFO - __main__ - Step 139851: {'lr': 5.780131957984492e-06, 'samples': 26851392, 'steps': 139850, 'loss/train': 1.395809292793274} 08/31/2021 14:38:19 - INFO - __main__ - Step 139852: {'lr': 5.778997480001547e-06, 'samples': 26851584, 'steps': 139851, 'loss/train': 0.9287911057472229} 08/31/2021 14:38:19 - INFO - __main__ - Step 139853: {'lr': 5.777863112060827e-06, 'samples': 26851776, 'steps': 139852, 'loss/train': 0.8991785049438477} 08/31/2021 14:38:21 - INFO - __main__ - Step 139854: {'lr': 5.776728854162833e-06, 'samples': 26851968, 'steps': 139853, 'loss/train': 0.9179829955101013} 08/31/2021 14:38:22 - INFO - __main__ - Step 139855: {'lr': 5.775594706308063e-06, 'samples': 26852160, 'steps': 139854, 'loss/train': 1.2472410202026367} 08/31/2021 14:38:22 - INFO - __main__ - Step 139856: {'lr': 5.7744606684970444e-06, 'samples': 26852352, 'steps': 139855, 'loss/train': 0.024833835661411285} 08/31/2021 14:38:22 - INFO - __main__ - Step 139857: {'lr': 5.773326740730306e-06, 'samples': 26852544, 'steps': 139856, 'loss/train': 1.0984346866607666} 08/31/2021 14:38:23 - INFO - __main__ - Step 139858: {'lr': 5.772192923008318e-06, 'samples': 26852736, 'steps': 139857, 'loss/train': 0.538139820098877} 08/31/2021 14:38:24 - INFO - __main__ - Step 139859: {'lr': 5.771059215331637e-06, 'samples': 26852928, 'steps': 139858, 'loss/train': 1.2717922925949097} 08/31/2021 14:38:25 - INFO - __main__ - Step 139860: {'lr': 5.769925617700705e-06, 'samples': 26853120, 'steps': 139859, 'loss/train': 0.3332713544368744} 08/31/2021 14:38:25 - INFO - __main__ - Step 139861: {'lr': 5.768792130116108e-06, 'samples': 26853312, 'steps': 139860, 'loss/train': 0.8688866496086121} 08/31/2021 14:38:25 - INFO - __main__ - Step 139862: {'lr': 5.7676587525783144e-06, 'samples': 26853504, 'steps': 139861, 'loss/train': 2.6626977920532227} 08/31/2021 14:38:26 - INFO - __main__ - Step 139863: {'lr': 5.766525485087826e-06, 'samples': 26853696, 'steps': 139862, 'loss/train': 0.0647977739572525} 08/31/2021 14:38:26 - INFO - __main__ - Step 139864: {'lr': 5.7653923276451965e-06, 'samples': 26853888, 'steps': 139863, 'loss/train': 1.3681720495224} 08/31/2021 14:38:28 - INFO - __main__ - Step 139865: {'lr': 5.764259280250899e-06, 'samples': 26854080, 'steps': 139864, 'loss/train': 0.8564930558204651} 08/31/2021 14:38:28 - INFO - __main__ - Step 139866: {'lr': 5.763126342905461e-06, 'samples': 26854272, 'steps': 139865, 'loss/train': 0.969614565372467} 08/31/2021 14:38:28 - INFO - __main__ - Step 139867: {'lr': 5.761993515609409e-06, 'samples': 26854464, 'steps': 139866, 'loss/train': 1.2757086753845215} 08/31/2021 14:38:29 - INFO - __main__ - Step 139868: {'lr': 5.760860798363216e-06, 'samples': 26854656, 'steps': 139867, 'loss/train': 1.2729063034057617} 08/31/2021 14:38:29 - INFO - __main__ - Step 139869: {'lr': 5.759728191167407e-06, 'samples': 26854848, 'steps': 139868, 'loss/train': 1.8788331747055054} 08/31/2021 14:38:31 - INFO - __main__ - Step 139870: {'lr': 5.758595694022484e-06, 'samples': 26855040, 'steps': 139869, 'loss/train': 1.168740153312683} 08/31/2021 14:38:31 - INFO - __main__ - Step 139871: {'lr': 5.757463306929028e-06, 'samples': 26855232, 'steps': 139870, 'loss/train': 0.5106598138809204} 08/31/2021 14:38:32 - INFO - __main__ - Step 139872: {'lr': 5.75633102988743e-06, 'samples': 26855424, 'steps': 139871, 'loss/train': 0.7418968081474304} 08/31/2021 14:38:32 - INFO - __main__ - Step 139873: {'lr': 5.75519886289827e-06, 'samples': 26855616, 'steps': 139872, 'loss/train': 1.6027555465698242} 08/31/2021 14:38:33 - INFO - __main__ - Step 139874: {'lr': 5.754066805962077e-06, 'samples': 26855808, 'steps': 139873, 'loss/train': 1.0291929244995117} 08/31/2021 14:38:34 - INFO - __main__ - Step 139875: {'lr': 5.752934859079295e-06, 'samples': 26856000, 'steps': 139874, 'loss/train': 0.3588179349899292} 08/31/2021 14:38:35 - INFO - __main__ - Step 139876: {'lr': 5.751803022250479e-06, 'samples': 26856192, 'steps': 139875, 'loss/train': 0.998870313167572} 08/31/2021 14:38:35 - INFO - __main__ - Step 139877: {'lr': 5.750671295476157e-06, 'samples': 26856384, 'steps': 139876, 'loss/train': 1.3602879047393799} 08/31/2021 14:38:35 - INFO - __main__ - Step 139878: {'lr': 5.7495396787567984e-06, 'samples': 26856576, 'steps': 139877, 'loss/train': 0.6705425977706909} 08/31/2021 14:38:36 - INFO - __main__ - Step 139879: {'lr': 5.748408172092933e-06, 'samples': 26856768, 'steps': 139878, 'loss/train': 1.6248350143432617} 08/31/2021 14:38:37 - INFO - __main__ - Step 139880: {'lr': 5.747276775485033e-06, 'samples': 26856960, 'steps': 139879, 'loss/train': 0.702822208404541} 08/31/2021 14:38:38 - INFO - __main__ - Step 139881: {'lr': 5.746145488933679e-06, 'samples': 26857152, 'steps': 139880, 'loss/train': 1.3465652465820312} 08/31/2021 14:38:38 - INFO - __main__ - Step 139882: {'lr': 5.745014312439345e-06, 'samples': 26857344, 'steps': 139881, 'loss/train': 0.7699078321456909} 08/31/2021 14:38:38 - INFO - __main__ - Step 139883: {'lr': 5.743883246002501e-06, 'samples': 26857536, 'steps': 139882, 'loss/train': 0.9625701308250427} 08/31/2021 14:38:39 - INFO - __main__ - Step 139884: {'lr': 5.74275228962376e-06, 'samples': 26857728, 'steps': 139883, 'loss/train': 2.581446409225464} 08/31/2021 14:38:40 - INFO - __main__ - Step 139885: {'lr': 5.741621443303507e-06, 'samples': 26857920, 'steps': 139884, 'loss/train': 1.483350396156311} 08/31/2021 14:38:41 - INFO - __main__ - Step 139886: {'lr': 5.7404907070423286e-06, 'samples': 26858112, 'steps': 139885, 'loss/train': 1.3738764524459839} 08/31/2021 14:38:41 - INFO - __main__ - Step 139887: {'lr': 5.739360080840722e-06, 'samples': 26858304, 'steps': 139886, 'loss/train': 0.5364328622817993} 08/31/2021 14:38:41 - INFO - __main__ - Step 139888: {'lr': 5.738229564699188e-06, 'samples': 26858496, 'steps': 139887, 'loss/train': 1.317779779434204} 08/31/2021 14:38:42 - INFO - __main__ - Step 139889: {'lr': 5.737099158618225e-06, 'samples': 26858688, 'steps': 139888, 'loss/train': 0.8225260972976685} 08/31/2021 14:38:43 - INFO - __main__ - Step 139890: {'lr': 5.7359688625983616e-06, 'samples': 26858880, 'steps': 139889, 'loss/train': 1.2338467836380005} 08/31/2021 14:38:44 - INFO - __main__ - Step 139891: {'lr': 5.7348386766400975e-06, 'samples': 26859072, 'steps': 139890, 'loss/train': 1.0376173257827759} 08/31/2021 14:38:44 - INFO - __main__ - Step 139892: {'lr': 5.733708600743959e-06, 'samples': 26859264, 'steps': 139891, 'loss/train': 1.6632601022720337} 08/31/2021 14:38:44 - INFO - __main__ - Step 139893: {'lr': 5.732578634910446e-06, 'samples': 26859456, 'steps': 139892, 'loss/train': 1.1826010942459106} 08/31/2021 14:38:45 - INFO - __main__ - Step 139894: {'lr': 5.7314487791400305e-06, 'samples': 26859648, 'steps': 139893, 'loss/train': 0.09403104335069656} 08/31/2021 14:38:45 - INFO - __main__ - Step 139895: {'lr': 5.730319033433295e-06, 'samples': 26859840, 'steps': 139894, 'loss/train': 1.2563271522521973} 08/31/2021 14:38:47 - INFO - __main__ - Step 139896: {'lr': 5.7291893977906855e-06, 'samples': 26860032, 'steps': 139895, 'loss/train': 0.7073559165000916} 08/31/2021 14:38:47 - INFO - __main__ - Step 139897: {'lr': 5.728059872212754e-06, 'samples': 26860224, 'steps': 139896, 'loss/train': 1.0382307767868042} 08/31/2021 14:38:47 - INFO - __main__ - Step 139898: {'lr': 5.726930456699975e-06, 'samples': 26860416, 'steps': 139897, 'loss/train': 1.2040050029754639} 08/31/2021 14:38:48 - INFO - __main__ - Step 139899: {'lr': 5.725801151252874e-06, 'samples': 26860608, 'steps': 139898, 'loss/train': 1.435611367225647} 08/31/2021 14:38:48 - INFO - __main__ - Step 139900: {'lr': 5.724671955871951e-06, 'samples': 26860800, 'steps': 139899, 'loss/train': 1.4247099161148071} 08/31/2021 14:38:50 - INFO - __main__ - Step 139901: {'lr': 5.723542870557735e-06, 'samples': 26860992, 'steps': 139900, 'loss/train': 1.0947297811508179} 08/31/2021 14:38:50 - INFO - __main__ - Step 139902: {'lr': 5.7224138953107245e-06, 'samples': 26861184, 'steps': 139901, 'loss/train': 1.3442950248718262} 08/31/2021 14:38:51 - INFO - __main__ - Step 139903: {'lr': 5.72128503013139e-06, 'samples': 26861376, 'steps': 139902, 'loss/train': 1.3409048318862915} 08/31/2021 14:38:51 - INFO - __main__ - Step 139904: {'lr': 5.720156275020316e-06, 'samples': 26861568, 'steps': 139903, 'loss/train': 1.202560544013977} 08/31/2021 14:38:51 - INFO - __main__ - Step 139905: {'lr': 5.719027629977946e-06, 'samples': 26861760, 'steps': 139904, 'loss/train': 1.208196759223938} 08/31/2021 14:38:53 - INFO - __main__ - Step 139906: {'lr': 5.717899095004808e-06, 'samples': 26861952, 'steps': 139905, 'loss/train': 1.0987706184387207} 08/31/2021 14:38:53 - INFO - __main__ - Step 139907: {'lr': 5.7167706701014286e-06, 'samples': 26862144, 'steps': 139906, 'loss/train': 2.396411895751953} 08/31/2021 14:38:54 - INFO - __main__ - Step 139908: {'lr': 5.715642355268308e-06, 'samples': 26862336, 'steps': 139907, 'loss/train': 1.5536082983016968} 08/31/2021 14:38:54 - INFO - __main__ - Step 139909: {'lr': 5.7145141505059454e-06, 'samples': 26862528, 'steps': 139908, 'loss/train': 1.2377731800079346} 08/31/2021 14:38:54 - INFO - __main__ - Step 139910: {'lr': 5.71338605581484e-06, 'samples': 26862720, 'steps': 139909, 'loss/train': 0.8560224771499634} 08/31/2021 14:38:56 - INFO - __main__ - Step 139911: {'lr': 5.712258071195547e-06, 'samples': 26862912, 'steps': 139910, 'loss/train': 1.3647290468215942} 08/31/2021 14:38:57 - INFO - __main__ - Step 139912: {'lr': 5.711130196648512e-06, 'samples': 26863104, 'steps': 139911, 'loss/train': 1.266637921333313} 08/31/2021 14:38:57 - INFO - __main__ - Step 139913: {'lr': 5.710002432174261e-06, 'samples': 26863296, 'steps': 139912, 'loss/train': 0.7818939685821533} 08/31/2021 14:38:58 - INFO - __main__ - Step 139914: {'lr': 5.708874777773349e-06, 'samples': 26863488, 'steps': 139913, 'loss/train': 0.7190166711807251} 08/31/2021 14:38:58 - INFO - __main__ - Step 139915: {'lr': 5.70774723344622e-06, 'samples': 26863680, 'steps': 139914, 'loss/train': 0.030011937022209167} 08/31/2021 14:38:58 - INFO - __main__ - Step 139916: {'lr': 5.70661979919343e-06, 'samples': 26863872, 'steps': 139915, 'loss/train': 0.05340634658932686} 08/31/2021 14:38:59 - INFO - __main__ - Step 139917: {'lr': 5.7054924750154505e-06, 'samples': 26864064, 'steps': 139916, 'loss/train': 0.10025538504123688} 08/31/2021 14:39:00 - INFO - __main__ - Step 139918: {'lr': 5.704365260912808e-06, 'samples': 26864256, 'steps': 139917, 'loss/train': 0.24984334409236908} 08/31/2021 14:39:01 - INFO - __main__ - Step 139919: {'lr': 5.703238156886004e-06, 'samples': 26864448, 'steps': 139918, 'loss/train': 0.9409305453300476} 08/31/2021 14:39:01 - INFO - __main__ - Step 139920: {'lr': 5.702111162935564e-06, 'samples': 26864640, 'steps': 139919, 'loss/train': 0.9080186486244202} 08/31/2021 14:39:01 - INFO - __main__ - Step 139921: {'lr': 5.700984279061988e-06, 'samples': 26864832, 'steps': 139920, 'loss/train': 0.41620829701423645} 08/31/2021 14:39:02 - INFO - __main__ - Step 139922: {'lr': 5.699857505265749e-06, 'samples': 26865024, 'steps': 139921, 'loss/train': 0.5409579873085022} 08/31/2021 14:39:04 - INFO - __main__ - Step 139923: {'lr': 5.698730841547428e-06, 'samples': 26865216, 'steps': 139922, 'loss/train': 0.9644513130187988} 08/31/2021 14:39:04 - INFO - __main__ - Step 139924: {'lr': 5.697604287907471e-06, 'samples': 26865408, 'steps': 139923, 'loss/train': 0.6911786794662476} 08/31/2021 14:39:05 - INFO - __main__ - Step 139925: {'lr': 5.6964778443464035e-06, 'samples': 26865600, 'steps': 139924, 'loss/train': 1.623923420906067} 08/31/2021 14:39:05 - INFO - __main__ - Step 139926: {'lr': 5.695351510864727e-06, 'samples': 26865792, 'steps': 139925, 'loss/train': 0.7792225480079651} 08/31/2021 14:39:05 - INFO - __main__ - Step 139927: {'lr': 5.6942252874629395e-06, 'samples': 26865984, 'steps': 139926, 'loss/train': 0.547131359577179} 08/31/2021 14:39:07 - INFO - __main__ - Step 139928: {'lr': 5.693099174141597e-06, 'samples': 26866176, 'steps': 139927, 'loss/train': 1.2807629108428955} 08/31/2021 14:39:07 - INFO - __main__ - Step 139929: {'lr': 5.691973170901144e-06, 'samples': 26866368, 'steps': 139928, 'loss/train': 1.7816362380981445} 08/31/2021 14:39:08 - INFO - __main__ - Step 139930: {'lr': 5.690847277742134e-06, 'samples': 26866560, 'steps': 139929, 'loss/train': 1.026294469833374} 08/31/2021 14:39:08 - INFO - __main__ - Step 139931: {'lr': 5.6897214946650676e-06, 'samples': 26866752, 'steps': 139930, 'loss/train': 1.0742911100387573} 08/31/2021 14:39:08 - INFO - __main__ - Step 139932: {'lr': 5.688595821670417e-06, 'samples': 26866944, 'steps': 139931, 'loss/train': 1.2668079137802124} 08/31/2021 14:39:10 - INFO - __main__ - Step 139933: {'lr': 5.687470258758737e-06, 'samples': 26867136, 'steps': 139932, 'loss/train': 1.3825476169586182} 08/31/2021 14:39:10 - INFO - __main__ - Step 139934: {'lr': 5.6863448059305266e-06, 'samples': 26867328, 'steps': 139933, 'loss/train': 0.3517351746559143} 08/31/2021 14:39:11 - INFO - __main__ - Step 139935: {'lr': 5.6852194631862585e-06, 'samples': 26867520, 'steps': 139934, 'loss/train': 1.5450630187988281} 08/31/2021 14:39:11 - INFO - __main__ - Step 139936: {'lr': 5.68409423052646e-06, 'samples': 26867712, 'steps': 139935, 'loss/train': 1.0727601051330566} 08/31/2021 14:39:11 - INFO - __main__ - Step 139937: {'lr': 5.68296910795163e-06, 'samples': 26867904, 'steps': 139936, 'loss/train': 0.7367337346076965} 08/31/2021 14:39:13 - INFO - __main__ - Step 139938: {'lr': 5.681844095462296e-06, 'samples': 26868096, 'steps': 139937, 'loss/train': 0.8378896117210388} 08/31/2021 14:39:13 - INFO - __main__ - Step 139939: {'lr': 5.680719193058959e-06, 'samples': 26868288, 'steps': 139938, 'loss/train': 0.7636024951934814} 08/31/2021 14:39:14 - INFO - __main__ - Step 139940: {'lr': 5.679594400742117e-06, 'samples': 26868480, 'steps': 139939, 'loss/train': 1.5483355522155762} 08/31/2021 14:39:14 - INFO - __main__ - Step 139941: {'lr': 5.678469718512269e-06, 'samples': 26868672, 'steps': 139940, 'loss/train': 0.10485750436782837} 08/31/2021 14:39:14 - INFO - __main__ - Step 139942: {'lr': 5.677345146369944e-06, 'samples': 26868864, 'steps': 139941, 'loss/train': 1.242423176765442} 08/31/2021 14:39:15 - INFO - __main__ - Step 139943: {'lr': 5.676220684315614e-06, 'samples': 26869056, 'steps': 139942, 'loss/train': 1.3504809141159058} 08/31/2021 14:39:16 - INFO - __main__ - Step 139944: {'lr': 5.675096332349833e-06, 'samples': 26869248, 'steps': 139943, 'loss/train': 0.3417499363422394} 08/31/2021 14:39:17 - INFO - __main__ - Step 139945: {'lr': 5.6739720904731005e-06, 'samples': 26869440, 'steps': 139944, 'loss/train': 1.279734492301941} 08/31/2021 14:39:17 - INFO - __main__ - Step 139946: {'lr': 5.67284795868589e-06, 'samples': 26869632, 'steps': 139945, 'loss/train': 0.01376214250922203} 08/31/2021 14:39:18 - INFO - __main__ - Step 139947: {'lr': 5.671723936988698e-06, 'samples': 26869824, 'steps': 139946, 'loss/train': 0.03068413957953453} 08/31/2021 14:39:18 - INFO - __main__ - Step 139948: {'lr': 5.670600025382083e-06, 'samples': 26870016, 'steps': 139947, 'loss/train': 0.8581937551498413} 08/31/2021 14:39:18 - INFO - __main__ - Step 139949: {'lr': 5.669476223866515e-06, 'samples': 26870208, 'steps': 139948, 'loss/train': 2.111264944076538} 08/31/2021 14:39:20 - INFO - __main__ - Step 139950: {'lr': 5.668352532442494e-06, 'samples': 26870400, 'steps': 139949, 'loss/train': 1.8475819826126099} 08/31/2021 14:39:21 - INFO - __main__ - Step 139951: {'lr': 5.667228951110575e-06, 'samples': 26870592, 'steps': 139950, 'loss/train': 0.6365805268287659} 08/31/2021 14:39:21 - INFO - __main__ - Step 139952: {'lr': 5.666105479871203e-06, 'samples': 26870784, 'steps': 139951, 'loss/train': 1.0540934801101685} 08/31/2021 14:39:22 - INFO - __main__ - Step 139953: {'lr': 5.664982118724932e-06, 'samples': 26870976, 'steps': 139952, 'loss/train': 1.269926905632019} 08/31/2021 14:39:22 - INFO - __main__ - Step 139954: {'lr': 5.663858867672261e-06, 'samples': 26871168, 'steps': 139953, 'loss/train': 0.9406754970550537} 08/31/2021 14:39:22 - INFO - __main__ - Step 139955: {'lr': 5.662735726713664e-06, 'samples': 26871360, 'steps': 139954, 'loss/train': 1.243701696395874} 08/31/2021 14:39:23 - INFO - __main__ - Step 139956: {'lr': 5.661612695849694e-06, 'samples': 26871552, 'steps': 139955, 'loss/train': 3.0353596210479736} 08/31/2021 14:39:24 - INFO - __main__ - Step 139957: {'lr': 5.660489775080824e-06, 'samples': 26871744, 'steps': 139956, 'loss/train': 2.7115118503570557} 08/31/2021 14:39:25 - INFO - __main__ - Step 139958: {'lr': 5.659366964407553e-06, 'samples': 26871936, 'steps': 139957, 'loss/train': 0.2624385356903076} 08/31/2021 14:39:25 - INFO - __main__ - Step 139959: {'lr': 5.658244263830381e-06, 'samples': 26872128, 'steps': 139958, 'loss/train': 1.2139990329742432} 08/31/2021 14:39:25 - INFO - __main__ - Step 139960: {'lr': 5.657121673349863e-06, 'samples': 26872320, 'steps': 139959, 'loss/train': 1.0340617895126343} 08/31/2021 14:39:26 - INFO - __main__ - Step 139961: {'lr': 5.6559991929664715e-06, 'samples': 26872512, 'steps': 139960, 'loss/train': 0.9174852967262268} 08/31/2021 14:39:28 - INFO - __main__ - Step 139962: {'lr': 5.654876822680704e-06, 'samples': 26872704, 'steps': 139961, 'loss/train': 1.5313149690628052} 08/31/2021 14:39:28 - INFO - __main__ - Step 139963: {'lr': 5.653754562493091e-06, 'samples': 26872896, 'steps': 139962, 'loss/train': 0.9247942566871643} 08/31/2021 14:39:29 - INFO - __main__ - Step 139964: {'lr': 5.65263241240413e-06, 'samples': 26873088, 'steps': 139963, 'loss/train': 0.08763296902179718} 08/31/2021 14:39:29 - INFO - __main__ - Step 139965: {'lr': 5.65151037241432e-06, 'samples': 26873280, 'steps': 139964, 'loss/train': 1.1368173360824585} 08/31/2021 14:39:29 - INFO - __main__ - Step 139966: {'lr': 5.650388442524162e-06, 'samples': 26873472, 'steps': 139965, 'loss/train': 0.6687542200088501} 08/31/2021 14:39:31 - INFO - __main__ - Step 139967: {'lr': 5.649266622734184e-06, 'samples': 26873664, 'steps': 139966, 'loss/train': 0.5760247707366943} 08/31/2021 14:39:32 - INFO - __main__ - Step 139968: {'lr': 5.648144913044856e-06, 'samples': 26873856, 'steps': 139967, 'loss/train': 0.5909320116043091} 08/31/2021 14:39:32 - INFO - __main__ - Step 139969: {'lr': 5.647023313456706e-06, 'samples': 26874048, 'steps': 139968, 'loss/train': 1.2091501951217651} 08/31/2021 14:39:32 - INFO - __main__ - Step 139970: {'lr': 5.645901823970234e-06, 'samples': 26874240, 'steps': 139969, 'loss/train': 0.07395689189434052} 08/31/2021 14:39:33 - INFO - __main__ - Step 139971: {'lr': 5.644780444585968e-06, 'samples': 26874432, 'steps': 139970, 'loss/train': 0.8817293643951416} 08/31/2021 14:39:34 - INFO - __main__ - Step 139972: {'lr': 5.6436591753043776e-06, 'samples': 26874624, 'steps': 139971, 'loss/train': 0.26256561279296875} 08/31/2021 14:39:35 - INFO - __main__ - Step 139973: {'lr': 5.642538016125992e-06, 'samples': 26874816, 'steps': 139972, 'loss/train': 0.8702676296234131} 08/31/2021 14:39:35 - INFO - __main__ - Step 139974: {'lr': 5.641416967051283e-06, 'samples': 26875008, 'steps': 139973, 'loss/train': 1.042033076286316} 08/31/2021 14:39:35 - INFO - __main__ - Step 139975: {'lr': 5.640296028080805e-06, 'samples': 26875200, 'steps': 139974, 'loss/train': 0.7719037532806396} 08/31/2021 14:39:36 - INFO - __main__ - Step 139976: {'lr': 5.63917519921503e-06, 'samples': 26875392, 'steps': 139975, 'loss/train': 1.6686888933181763} 08/31/2021 14:39:37 - INFO - __main__ - Step 139977: {'lr': 5.638054480454485e-06, 'samples': 26875584, 'steps': 139976, 'loss/train': 0.9540244936943054} 08/31/2021 14:39:38 - INFO - __main__ - Step 139978: {'lr': 5.636933871799671e-06, 'samples': 26875776, 'steps': 139977, 'loss/train': 1.3885267972946167} 08/31/2021 14:39:38 - INFO - __main__ - Step 139979: {'lr': 5.6358133732510585e-06, 'samples': 26875968, 'steps': 139978, 'loss/train': 1.3294003009796143} 08/31/2021 14:39:39 - INFO - __main__ - Step 139980: {'lr': 5.634692984809175e-06, 'samples': 26876160, 'steps': 139979, 'loss/train': 1.0863673686981201} 08/31/2021 14:39:39 - INFO - __main__ - Step 139981: {'lr': 5.633572706474549e-06, 'samples': 26876352, 'steps': 139980, 'loss/train': 0.10422805696725845} 08/31/2021 14:39:42 - INFO - __main__ - Step 139982: {'lr': 5.632452538247651e-06, 'samples': 26876544, 'steps': 139981, 'loss/train': 1.115167498588562} 08/31/2021 14:39:42 - INFO - __main__ - Step 139983: {'lr': 5.631332480128981e-06, 'samples': 26876736, 'steps': 139982, 'loss/train': 1.5220471620559692} 08/31/2021 14:39:42 - INFO - __main__ - Step 139984: {'lr': 5.6302125321190946e-06, 'samples': 26876928, 'steps': 139983, 'loss/train': 1.508513331413269} 08/31/2021 14:39:43 - INFO - __main__ - Step 139985: {'lr': 5.629092694218435e-06, 'samples': 26877120, 'steps': 139984, 'loss/train': 1.3481312990188599} 08/31/2021 14:39:43 - INFO - __main__ - Step 139986: {'lr': 5.627972966427558e-06, 'samples': 26877312, 'steps': 139985, 'loss/train': 1.5870603322982788} 08/31/2021 14:39:43 - INFO - __main__ - Step 139987: {'lr': 5.626853348746936e-06, 'samples': 26877504, 'steps': 139986, 'loss/train': 1.58332359790802} 08/31/2021 14:39:44 - INFO - __main__ - Step 139988: {'lr': 5.625733841177094e-06, 'samples': 26877696, 'steps': 139987, 'loss/train': 1.68495512008667} 08/31/2021 14:39:46 - INFO - __main__ - Step 139989: {'lr': 5.624614443718506e-06, 'samples': 26877888, 'steps': 139988, 'loss/train': 1.1397749185562134} 08/31/2021 14:39:46 - INFO - __main__ - Step 139990: {'lr': 5.6234951563716995e-06, 'samples': 26878080, 'steps': 139989, 'loss/train': 1.4846969842910767} 08/31/2021 14:39:47 - INFO - __main__ - Step 139991: {'lr': 5.622375979137201e-06, 'samples': 26878272, 'steps': 139990, 'loss/train': 0.7178364396095276} 08/31/2021 14:39:47 - INFO - __main__ - Step 139992: {'lr': 5.621256912015482e-06, 'samples': 26878464, 'steps': 139991, 'loss/train': 1.44785737991333} 08/31/2021 14:39:47 - INFO - __main__ - Step 139993: {'lr': 5.620137955007043e-06, 'samples': 26878656, 'steps': 139992, 'loss/train': 1.8248276710510254} 08/31/2021 14:39:48 - INFO - __main__ - Step 139994: {'lr': 5.619019108112383e-06, 'samples': 26878848, 'steps': 139993, 'loss/train': 1.3399075269699097} 08/31/2021 14:39:49 - INFO - __main__ - Step 139995: {'lr': 5.61790037133203e-06, 'samples': 26879040, 'steps': 139994, 'loss/train': 0.2838285565376282} 08/31/2021 14:39:50 - INFO - __main__ - Step 139996: {'lr': 5.616781744666511e-06, 'samples': 26879232, 'steps': 139995, 'loss/train': 1.2678632736206055} 08/31/2021 14:39:50 - INFO - __main__ - Step 139997: {'lr': 5.615663228116269e-06, 'samples': 26879424, 'steps': 139996, 'loss/train': 1.275313377380371} 08/31/2021 14:39:50 - INFO - __main__ - Step 139998: {'lr': 5.614544821681833e-06, 'samples': 26879616, 'steps': 139997, 'loss/train': 1.0350496768951416} 08/31/2021 14:39:51 - INFO - __main__ - Step 139999: {'lr': 5.613426525363729e-06, 'samples': 26879808, 'steps': 139998, 'loss/train': 1.2587571144104004} 08/31/2021 14:39:52 - INFO - __main__ - Step 140000: {'lr': 5.612308339162431e-06, 'samples': 26880000, 'steps': 139999, 'loss/train': 1.155480146408081} 08/31/2021 14:39:53 - INFO - __main__ - Step 140001: {'lr': 5.611190263078464e-06, 'samples': 26880192, 'steps': 140000, 'loss/train': 1.1654435396194458} 08/31/2021 14:39:53 - INFO - __main__ - Step 140002: {'lr': 5.610072297112329e-06, 'samples': 26880384, 'steps': 140001, 'loss/train': 0.6981545090675354} 08/31/2021 14:39:53 - INFO - __main__ - Step 140003: {'lr': 5.6089544412644964e-06, 'samples': 26880576, 'steps': 140002, 'loss/train': 1.1496400833129883} 08/31/2021 14:39:54 - INFO - __main__ - Step 140004: {'lr': 5.607836695535523e-06, 'samples': 26880768, 'steps': 140003, 'loss/train': 1.2916383743286133} 08/31/2021 14:39:55 - INFO - __main__ - Step 140005: {'lr': 5.606719059925908e-06, 'samples': 26880960, 'steps': 140004, 'loss/train': 0.7934474945068359} 08/31/2021 14:39:56 - INFO - __main__ - Step 140006: {'lr': 5.605601534436094e-06, 'samples': 26881152, 'steps': 140005, 'loss/train': 0.794813871383667} 08/31/2021 14:39:56 - INFO - __main__ - Step 140007: {'lr': 5.604484119066639e-06, 'samples': 26881344, 'steps': 140006, 'loss/train': 0.7597642540931702} 08/31/2021 14:39:57 - INFO - __main__ - Step 140008: {'lr': 5.603366813818039e-06, 'samples': 26881536, 'steps': 140007, 'loss/train': 0.36533650755882263} 08/31/2021 14:39:57 - INFO - __main__ - Step 140009: {'lr': 5.6022496186907966e-06, 'samples': 26881728, 'steps': 140008, 'loss/train': 1.0282018184661865} 08/31/2021 14:39:59 - INFO - __main__ - Step 140010: {'lr': 5.6011325336853824e-06, 'samples': 26881920, 'steps': 140009, 'loss/train': 0.15736816823482513} 08/31/2021 14:39:59 - INFO - __main__ - Step 140011: {'lr': 5.600015558802352e-06, 'samples': 26882112, 'steps': 140010, 'loss/train': 0.5501120090484619} 08/31/2021 14:39:59 - INFO - __main__ - Step 140012: {'lr': 5.598898694042148e-06, 'samples': 26882304, 'steps': 140011, 'loss/train': 1.0503309965133667} 08/31/2021 14:40:00 - INFO - __main__ - Step 140013: {'lr': 5.597781939405355e-06, 'samples': 26882496, 'steps': 140012, 'loss/train': 0.9153429269790649} 08/31/2021 14:40:00 - INFO - __main__ - Step 140014: {'lr': 5.596665294892389e-06, 'samples': 26882688, 'steps': 140013, 'loss/train': 0.722847580909729} 08/31/2021 14:40:00 - INFO - __main__ - Step 140015: {'lr': 5.595548760503832e-06, 'samples': 26882880, 'steps': 140014, 'loss/train': 1.4569717645645142} 08/31/2021 14:40:02 - INFO - __main__ - Step 140016: {'lr': 5.594432336240129e-06, 'samples': 26883072, 'steps': 140015, 'loss/train': 0.3468516767024994} 08/31/2021 14:40:03 - INFO - __main__ - Step 140017: {'lr': 5.59331602210178e-06, 'samples': 26883264, 'steps': 140016, 'loss/train': 0.6621467471122742} 08/31/2021 14:40:03 - INFO - __main__ - Step 140018: {'lr': 5.592199818089339e-06, 'samples': 26883456, 'steps': 140017, 'loss/train': 0.6978195905685425} 08/31/2021 14:40:03 - INFO - __main__ - Step 140019: {'lr': 5.591083724203305e-06, 'samples': 26883648, 'steps': 140018, 'loss/train': 0.25065508484840393} 08/31/2021 14:40:05 - INFO - __main__ - Step 140020: {'lr': 5.589967740444124e-06, 'samples': 26883840, 'steps': 140019, 'loss/train': 0.05221300199627876} 08/31/2021 14:40:05 - INFO - __main__ - Step 140021: {'lr': 5.58885186681235e-06, 'samples': 26884032, 'steps': 140020, 'loss/train': 1.068007230758667} 08/31/2021 14:40:06 - INFO - __main__ - Step 140022: {'lr': 5.587736103308455e-06, 'samples': 26884224, 'steps': 140021, 'loss/train': 1.7226616144180298} 08/31/2021 14:40:06 - INFO - __main__ - Step 140023: {'lr': 5.586620449932966e-06, 'samples': 26884416, 'steps': 140022, 'loss/train': 0.9439085721969604} 08/31/2021 14:40:06 - INFO - __main__ - Step 140024: {'lr': 5.585504906686356e-06, 'samples': 26884608, 'steps': 140023, 'loss/train': 1.1495715379714966} 08/31/2021 14:40:07 - INFO - __main__ - Step 140025: {'lr': 5.584389473569152e-06, 'samples': 26884800, 'steps': 140024, 'loss/train': 0.9197489023208618} 08/31/2021 14:40:09 - INFO - __main__ - Step 140026: {'lr': 5.5832741505818515e-06, 'samples': 26884992, 'steps': 140025, 'loss/train': 1.0488799810409546} 08/31/2021 14:40:09 - INFO - __main__ - Step 140027: {'lr': 5.582158937724957e-06, 'samples': 26885184, 'steps': 140026, 'loss/train': 1.6284235715866089} 08/31/2021 14:40:09 - INFO - __main__ - Step 140028: {'lr': 5.581043834998967e-06, 'samples': 26885376, 'steps': 140027, 'loss/train': 0.9570112228393555} 08/31/2021 14:40:10 - INFO - __main__ - Step 140029: {'lr': 5.57992884240438e-06, 'samples': 26885568, 'steps': 140028, 'loss/train': 0.410874605178833} 08/31/2021 14:40:10 - INFO - __main__ - Step 140030: {'lr': 5.5788139599417255e-06, 'samples': 26885760, 'steps': 140029, 'loss/train': 0.4078577160835266} 08/31/2021 14:40:11 - INFO - __main__ - Step 140031: {'lr': 5.577699187611474e-06, 'samples': 26885952, 'steps': 140030, 'loss/train': 3.7372000217437744} 08/31/2021 14:40:12 - INFO - __main__ - Step 140032: {'lr': 5.57658452541418e-06, 'samples': 26886144, 'steps': 140031, 'loss/train': 1.0348834991455078} 08/31/2021 14:40:12 - INFO - __main__ - Step 140033: {'lr': 5.575469973350261e-06, 'samples': 26886336, 'steps': 140032, 'loss/train': 1.5077179670333862} 08/31/2021 14:40:13 - INFO - __main__ - Step 140034: {'lr': 5.5743555314202724e-06, 'samples': 26886528, 'steps': 140033, 'loss/train': 1.1499706506729126} 08/31/2021 14:40:13 - INFO - __main__ - Step 140035: {'lr': 5.573241199624685e-06, 'samples': 26886720, 'steps': 140034, 'loss/train': 1.264634609222412} 08/31/2021 14:40:14 - INFO - __main__ - Step 140036: {'lr': 5.572126977964053e-06, 'samples': 26886912, 'steps': 140035, 'loss/train': 1.1076936721801758} 08/31/2021 14:40:16 - INFO - __main__ - Step 140037: {'lr': 5.5710128664388516e-06, 'samples': 26887104, 'steps': 140036, 'loss/train': 0.863541841506958} 08/31/2021 14:40:16 - INFO - __main__ - Step 140038: {'lr': 5.56989886504955e-06, 'samples': 26887296, 'steps': 140037, 'loss/train': 0.12744948267936707} 08/31/2021 14:40:16 - INFO - __main__ - Step 140039: {'lr': 5.5687849737967035e-06, 'samples': 26887488, 'steps': 140038, 'loss/train': 1.3492567539215088} 08/31/2021 14:40:17 - INFO - __main__ - Step 140040: {'lr': 5.567671192680785e-06, 'samples': 26887680, 'steps': 140039, 'loss/train': 0.8685724139213562} 08/31/2021 14:40:17 - INFO - __main__ - Step 140041: {'lr': 5.5665575217022925e-06, 'samples': 26887872, 'steps': 140040, 'loss/train': 1.3826695680618286} 08/31/2021 14:40:19 - INFO - __main__ - Step 140042: {'lr': 5.565443960861755e-06, 'samples': 26888064, 'steps': 140041, 'loss/train': 1.1278489828109741} 08/31/2021 14:40:19 - INFO - __main__ - Step 140043: {'lr': 5.564330510159643e-06, 'samples': 26888256, 'steps': 140042, 'loss/train': 1.5515379905700684} 08/31/2021 14:40:20 - INFO - __main__ - Step 140044: {'lr': 5.563217169596485e-06, 'samples': 26888448, 'steps': 140043, 'loss/train': 0.8386692404747009} 08/31/2021 14:40:20 - INFO - __main__ - Step 140045: {'lr': 5.562103939172752e-06, 'samples': 26888640, 'steps': 140044, 'loss/train': 0.18877632915973663} 08/31/2021 14:40:20 - INFO - __main__ - Step 140046: {'lr': 5.560990818889e-06, 'samples': 26888832, 'steps': 140045, 'loss/train': 1.3466020822525024} 08/31/2021 14:40:22 - INFO - __main__ - Step 140047: {'lr': 5.559877808745673e-06, 'samples': 26889024, 'steps': 140046, 'loss/train': 1.4920955896377563} 08/31/2021 14:40:22 - INFO - __main__ - Step 140048: {'lr': 5.558764908743269e-06, 'samples': 26889216, 'steps': 140047, 'loss/train': 0.031880933791399} 08/31/2021 14:40:23 - INFO - __main__ - Step 140049: {'lr': 5.557652118882344e-06, 'samples': 26889408, 'steps': 140048, 'loss/train': 1.3438390493392944} 08/31/2021 14:40:23 - INFO - __main__ - Step 140050: {'lr': 5.556539439163344e-06, 'samples': 26889600, 'steps': 140049, 'loss/train': 1.0321993827819824} 08/31/2021 14:40:24 - INFO - __main__ - Step 140051: {'lr': 5.555426869586821e-06, 'samples': 26889792, 'steps': 140050, 'loss/train': 1.3479876518249512} 08/31/2021 14:40:25 - INFO - __main__ - Step 140052: {'lr': 5.554314410153221e-06, 'samples': 26889984, 'steps': 140051, 'loss/train': 0.8940542936325073} 08/31/2021 14:40:25 - INFO - __main__ - Step 140053: {'lr': 5.553202060863099e-06, 'samples': 26890176, 'steps': 140052, 'loss/train': 1.634684443473816} 08/31/2021 14:40:26 - INFO - __main__ - Step 140054: {'lr': 5.552089821716927e-06, 'samples': 26890368, 'steps': 140053, 'loss/train': 1.2257565259933472} 08/31/2021 14:40:26 - INFO - __main__ - Step 140055: {'lr': 5.550977692715203e-06, 'samples': 26890560, 'steps': 140054, 'loss/train': 1.2851167917251587} 08/31/2021 14:40:27 - INFO - __main__ - Step 140056: {'lr': 5.549865673858428e-06, 'samples': 26890752, 'steps': 140055, 'loss/train': 1.0705586671829224} 08/31/2021 14:40:28 - INFO - __main__ - Step 140057: {'lr': 5.54875376514713e-06, 'samples': 26890944, 'steps': 140056, 'loss/train': 0.9463351964950562} 08/31/2021 14:40:29 - INFO - __main__ - Step 140058: {'lr': 5.547641966581779e-06, 'samples': 26891136, 'steps': 140057, 'loss/train': 0.8199818134307861} 08/31/2021 14:40:29 - INFO - __main__ - Step 140059: {'lr': 5.546530278162931e-06, 'samples': 26891328, 'steps': 140058, 'loss/train': 0.9950812458992004} 08/31/2021 14:40:29 - INFO - __main__ - Step 140060: {'lr': 5.545418699891003e-06, 'samples': 26891520, 'steps': 140059, 'loss/train': 1.0156047344207764} 08/31/2021 14:40:30 - INFO - __main__ - Step 140061: {'lr': 5.544307231766549e-06, 'samples': 26891712, 'steps': 140060, 'loss/train': 1.0670384168624878} 08/31/2021 14:40:31 - INFO - __main__ - Step 140062: {'lr': 5.5431958737900415e-06, 'samples': 26891904, 'steps': 140061, 'loss/train': 0.3461809754371643} 08/31/2021 14:40:32 - INFO - __main__ - Step 140063: {'lr': 5.542084625962007e-06, 'samples': 26892096, 'steps': 140062, 'loss/train': 0.579045832157135} 08/31/2021 14:40:32 - INFO - __main__ - Step 140064: {'lr': 5.540973488282947e-06, 'samples': 26892288, 'steps': 140063, 'loss/train': 0.2772906422615051} 08/31/2021 14:40:32 - INFO - __main__ - Step 140065: {'lr': 5.539862460753331e-06, 'samples': 26892480, 'steps': 140064, 'loss/train': 0.6531810760498047} 08/31/2021 14:40:33 - INFO - __main__ - Step 140066: {'lr': 5.5387515433737155e-06, 'samples': 26892672, 'steps': 140065, 'loss/train': 0.6274890303611755} 08/31/2021 14:40:34 - INFO - __main__ - Step 140067: {'lr': 5.537640736144545e-06, 'samples': 26892864, 'steps': 140066, 'loss/train': 0.6746342778205872} 08/31/2021 14:40:35 - INFO - __main__ - Step 140068: {'lr': 5.536530039066317e-06, 'samples': 26893056, 'steps': 140067, 'loss/train': 0.28139203786849976} 08/31/2021 14:40:35 - INFO - __main__ - Step 140069: {'lr': 5.5354194521395896e-06, 'samples': 26893248, 'steps': 140068, 'loss/train': 1.3006001710891724} 08/31/2021 14:40:36 - INFO - __main__ - Step 140070: {'lr': 5.534308975364832e-06, 'samples': 26893440, 'steps': 140069, 'loss/train': 1.5334694385528564} 08/31/2021 14:40:36 - INFO - __main__ - Step 140071: {'lr': 5.533198608742518e-06, 'samples': 26893632, 'steps': 140070, 'loss/train': 0.9964542984962463} 08/31/2021 14:40:36 - INFO - __main__ - Step 140072: {'lr': 5.532088352273173e-06, 'samples': 26893824, 'steps': 140071, 'loss/train': 0.10489005595445633} 08/31/2021 14:40:38 - INFO - __main__ - Step 140073: {'lr': 5.5309782059573544e-06, 'samples': 26894016, 'steps': 140072, 'loss/train': 0.31926795840263367} 08/31/2021 14:40:38 - INFO - __main__ - Step 140074: {'lr': 5.529868169795449e-06, 'samples': 26894208, 'steps': 140073, 'loss/train': 0.05219418182969093} 08/31/2021 14:40:39 - INFO - __main__ - Step 140075: {'lr': 5.528758243788012e-06, 'samples': 26894400, 'steps': 140074, 'loss/train': 1.5164211988449097} 08/31/2021 14:40:39 - INFO - __main__ - Step 140076: {'lr': 5.527648427935572e-06, 'samples': 26894592, 'steps': 140075, 'loss/train': 0.8810258507728577} 08/31/2021 14:40:39 - INFO - __main__ - Step 140077: {'lr': 5.526538722238572e-06, 'samples': 26894784, 'steps': 140076, 'loss/train': 1.1187456846237183} 08/31/2021 14:40:41 - INFO - __main__ - Step 140078: {'lr': 5.52542912669754e-06, 'samples': 26894976, 'steps': 140077, 'loss/train': 0.7843487858772278} 08/31/2021 14:40:41 - INFO - __main__ - Step 140079: {'lr': 5.524319641313003e-06, 'samples': 26895168, 'steps': 140078, 'loss/train': 1.2942761182785034} 08/31/2021 14:40:42 - INFO - __main__ - Step 140080: {'lr': 5.523210266085404e-06, 'samples': 26895360, 'steps': 140079, 'loss/train': 1.301269769668579} 08/31/2021 14:40:42 - INFO - __main__ - Step 140081: {'lr': 5.5221010010153006e-06, 'samples': 26895552, 'steps': 140080, 'loss/train': 0.9676333665847778} 08/31/2021 14:40:42 - INFO - __main__ - Step 140082: {'lr': 5.520991846103163e-06, 'samples': 26895744, 'steps': 140081, 'loss/train': 1.2968928813934326} 08/31/2021 14:40:44 - INFO - __main__ - Step 140083: {'lr': 5.519882801349491e-06, 'samples': 26895936, 'steps': 140082, 'loss/train': 1.1944141387939453} 08/31/2021 14:40:44 - INFO - __main__ - Step 140084: {'lr': 5.518773866754784e-06, 'samples': 26896128, 'steps': 140083, 'loss/train': 0.9398166537284851} 08/31/2021 14:40:45 - INFO - __main__ - Step 140085: {'lr': 5.517665042319542e-06, 'samples': 26896320, 'steps': 140084, 'loss/train': 0.9054981470108032} 08/31/2021 14:40:45 - INFO - __main__ - Step 140086: {'lr': 5.516556328044292e-06, 'samples': 26896512, 'steps': 140085, 'loss/train': 1.2082558870315552} 08/31/2021 14:40:45 - INFO - __main__ - Step 140087: {'lr': 5.515447723929479e-06, 'samples': 26896704, 'steps': 140086, 'loss/train': 1.3469841480255127} 08/31/2021 14:40:46 - INFO - __main__ - Step 140088: {'lr': 5.514339229975656e-06, 'samples': 26896896, 'steps': 140087, 'loss/train': 0.9596485495567322} 08/31/2021 14:40:47 - INFO - __main__ - Step 140089: {'lr': 5.51323084618327e-06, 'samples': 26897088, 'steps': 140088, 'loss/train': 0.9738132357597351} 08/31/2021 14:40:48 - INFO - __main__ - Step 140090: {'lr': 5.512122572552875e-06, 'samples': 26897280, 'steps': 140089, 'loss/train': 0.32741039991378784} 08/31/2021 14:40:48 - INFO - __main__ - Step 140091: {'lr': 5.511014409084942e-06, 'samples': 26897472, 'steps': 140090, 'loss/train': 0.8052855730056763} 08/31/2021 14:40:49 - INFO - __main__ - Step 140092: {'lr': 5.509906355779942e-06, 'samples': 26897664, 'steps': 140091, 'loss/train': 0.9691068530082703} 08/31/2021 14:40:49 - INFO - __main__ - Step 140093: {'lr': 5.508798412638433e-06, 'samples': 26897856, 'steps': 140092, 'loss/train': 1.2927379608154297} 08/31/2021 14:40:51 - INFO - __main__ - Step 140094: {'lr': 5.507690579660884e-06, 'samples': 26898048, 'steps': 140093, 'loss/train': 0.7015998363494873} 08/31/2021 14:40:51 - INFO - __main__ - Step 140095: {'lr': 5.506582856847797e-06, 'samples': 26898240, 'steps': 140094, 'loss/train': 0.5776347517967224} 08/31/2021 14:40:52 - INFO - __main__ - Step 140096: {'lr': 5.505475244199671e-06, 'samples': 26898432, 'steps': 140095, 'loss/train': 0.9992173910140991} 08/31/2021 14:40:52 - INFO - __main__ - Step 140097: {'lr': 5.504367741717003e-06, 'samples': 26898624, 'steps': 140096, 'loss/train': 1.3401131629943848} 08/31/2021 14:40:52 - INFO - __main__ - Step 140098: {'lr': 5.503260349400296e-06, 'samples': 26898816, 'steps': 140097, 'loss/train': 0.9017484784126282} 08/31/2021 14:40:54 - INFO - __main__ - Step 140099: {'lr': 5.502153067250076e-06, 'samples': 26899008, 'steps': 140098, 'loss/train': 0.871281087398529} 08/31/2021 14:40:54 - INFO - __main__ - Step 140100: {'lr': 5.50104589526676e-06, 'samples': 26899200, 'steps': 140099, 'loss/train': 1.393918514251709} 08/31/2021 14:40:55 - INFO - __main__ - Step 140101: {'lr': 5.499938833450929e-06, 'samples': 26899392, 'steps': 140100, 'loss/train': 1.027744174003601} 08/31/2021 14:40:55 - INFO - __main__ - Step 140102: {'lr': 5.498831881803057e-06, 'samples': 26899584, 'steps': 140101, 'loss/train': 0.7998639345169067} 08/31/2021 14:40:55 - INFO - __main__ - Step 140103: {'lr': 5.497725040323614e-06, 'samples': 26899776, 'steps': 140102, 'loss/train': 0.3161149024963379} 08/31/2021 14:40:56 - INFO - __main__ - Step 140104: {'lr': 5.496618309013129e-06, 'samples': 26899968, 'steps': 140103, 'loss/train': 0.3618987798690796} 08/31/2021 14:40:57 - INFO - __main__ - Step 140105: {'lr': 5.495511687872102e-06, 'samples': 26900160, 'steps': 140104, 'loss/train': 1.2717398405075073} 08/31/2021 14:40:58 - INFO - __main__ - Step 140106: {'lr': 5.494405176901029e-06, 'samples': 26900352, 'steps': 140105, 'loss/train': 0.5243259072303772} 08/31/2021 14:40:58 - INFO - __main__ - Step 140107: {'lr': 5.493298776100413e-06, 'samples': 26900544, 'steps': 140106, 'loss/train': 0.8852123022079468} 08/31/2021 14:40:59 - INFO - __main__ - Step 140108: {'lr': 5.492192485470726e-06, 'samples': 26900736, 'steps': 140107, 'loss/train': 1.4744528532028198} 08/31/2021 14:40:59 - INFO - __main__ - Step 140109: {'lr': 5.491086305012493e-06, 'samples': 26900928, 'steps': 140108, 'loss/train': 0.3179533779621124} 08/31/2021 14:41:01 - INFO - __main__ - Step 140110: {'lr': 5.4899802347261885e-06, 'samples': 26901120, 'steps': 140109, 'loss/train': 1.7471020221710205} 08/31/2021 14:41:01 - INFO - __main__ - Step 140111: {'lr': 5.488874274612338e-06, 'samples': 26901312, 'steps': 140110, 'loss/train': 1.359264612197876} 08/31/2021 14:41:01 - INFO - __main__ - Step 140112: {'lr': 5.487768424671441e-06, 'samples': 26901504, 'steps': 140111, 'loss/train': 1.3197792768478394} 08/31/2021 14:41:02 - INFO - __main__ - Step 140113: {'lr': 5.486662684903971e-06, 'samples': 26901696, 'steps': 140112, 'loss/train': 1.3099883794784546} 08/31/2021 14:41:02 - INFO - __main__ - Step 140114: {'lr': 5.485557055310453e-06, 'samples': 26901888, 'steps': 140113, 'loss/train': 0.34123694896698} 08/31/2021 14:41:03 - INFO - __main__ - Step 140115: {'lr': 5.484451535891333e-06, 'samples': 26902080, 'steps': 140114, 'loss/train': 1.2320683002471924} 08/31/2021 14:41:04 - INFO - __main__ - Step 140116: {'lr': 5.483346126647165e-06, 'samples': 26902272, 'steps': 140115, 'loss/train': 0.4775017201900482} 08/31/2021 14:41:04 - INFO - __main__ - Step 140117: {'lr': 5.482240827578422e-06, 'samples': 26902464, 'steps': 140116, 'loss/train': 1.3237054347991943} 08/31/2021 14:41:05 - INFO - __main__ - Step 140118: {'lr': 5.481135638685631e-06, 'samples': 26902656, 'steps': 140117, 'loss/train': 0.2926642596721649} 08/31/2021 14:41:05 - INFO - __main__ - Step 140119: {'lr': 5.480030559969235e-06, 'samples': 26902848, 'steps': 140118, 'loss/train': 0.6114553213119507} 08/31/2021 14:41:07 - INFO - __main__ - Step 140120: {'lr': 5.47892559142979e-06, 'samples': 26903040, 'steps': 140119, 'loss/train': 0.5111557841300964} 08/31/2021 14:41:07 - INFO - __main__ - Step 140121: {'lr': 5.477820733067768e-06, 'samples': 26903232, 'steps': 140120, 'loss/train': 1.635903239250183} 08/31/2021 14:41:07 - INFO - __main__ - Step 140122: {'lr': 5.47671598488364e-06, 'samples': 26903424, 'steps': 140121, 'loss/train': 1.3242725133895874} 08/31/2021 14:41:08 - INFO - __main__ - Step 140123: {'lr': 5.475611346877962e-06, 'samples': 26903616, 'steps': 140122, 'loss/train': 0.02959964983165264} 08/31/2021 14:41:08 - INFO - __main__ - Step 140124: {'lr': 5.474506819051178e-06, 'samples': 26903808, 'steps': 140123, 'loss/train': 1.252655029296875} 08/31/2021 14:41:10 - INFO - __main__ - Step 140125: {'lr': 5.473402401403815e-06, 'samples': 26904000, 'steps': 140124, 'loss/train': 0.9357893466949463} 08/31/2021 14:41:10 - INFO - __main__ - Step 140126: {'lr': 5.472298093936373e-06, 'samples': 26904192, 'steps': 140125, 'loss/train': 0.4461710751056671} 08/31/2021 14:41:11 - INFO - __main__ - Step 140127: {'lr': 5.471193896649324e-06, 'samples': 26904384, 'steps': 140126, 'loss/train': 1.448709487915039} 08/31/2021 14:41:11 - INFO - __main__ - Step 140128: {'lr': 5.470089809543194e-06, 'samples': 26904576, 'steps': 140127, 'loss/train': 1.1106977462768555} 08/31/2021 14:41:11 - INFO - __main__ - Step 140129: {'lr': 5.468985832618456e-06, 'samples': 26904768, 'steps': 140128, 'loss/train': 1.291869878768921} 08/31/2021 14:41:13 - INFO - __main__ - Step 140130: {'lr': 5.4678819658756376e-06, 'samples': 26904960, 'steps': 140129, 'loss/train': 0.6693766117095947} 08/31/2021 14:41:13 - INFO - __main__ - Step 140131: {'lr': 5.46677820931521e-06, 'samples': 26905152, 'steps': 140130, 'loss/train': 0.8174731731414795} 08/31/2021 14:41:14 - INFO - __main__ - Step 140132: {'lr': 5.465674562937672e-06, 'samples': 26905344, 'steps': 140131, 'loss/train': 0.7060282826423645} 08/31/2021 14:41:14 - INFO - __main__ - Step 140133: {'lr': 5.464571026743525e-06, 'samples': 26905536, 'steps': 140132, 'loss/train': 1.2099584341049194} 08/31/2021 14:41:14 - INFO - __main__ - Step 140134: {'lr': 5.4634676007332685e-06, 'samples': 26905728, 'steps': 140133, 'loss/train': 0.965421199798584} 08/31/2021 14:41:16 - INFO - __main__ - Step 140135: {'lr': 5.462364284907428e-06, 'samples': 26905920, 'steps': 140134, 'loss/train': 1.2651405334472656} 08/31/2021 14:41:17 - INFO - __main__ - Step 140136: {'lr': 5.46126107926645e-06, 'samples': 26906112, 'steps': 140135, 'loss/train': 1.6459052562713623} 08/31/2021 14:41:17 - INFO - __main__ - Step 140137: {'lr': 5.460157983810832e-06, 'samples': 26906304, 'steps': 140136, 'loss/train': 1.282726526260376} 08/31/2021 14:41:17 - INFO - __main__ - Step 140138: {'lr': 5.45905499854113e-06, 'samples': 26906496, 'steps': 140137, 'loss/train': 2.0336008071899414} 08/31/2021 14:41:18 - INFO - __main__ - Step 140139: {'lr': 5.457952123457788e-06, 'samples': 26906688, 'steps': 140138, 'loss/train': 1.0044468641281128} 08/31/2021 14:41:18 - INFO - __main__ - Step 140140: {'lr': 5.4568493585613335e-06, 'samples': 26906880, 'steps': 140139, 'loss/train': 1.2184827327728271} 08/31/2021 14:41:18 - INFO - __main__ - Step 140141: {'lr': 5.455746703852238e-06, 'samples': 26907072, 'steps': 140140, 'loss/train': 0.032354239374399185} 08/31/2021 14:41:20 - INFO - __main__ - Step 140142: {'lr': 5.454644159331029e-06, 'samples': 26907264, 'steps': 140141, 'loss/train': 0.05094320327043533} 08/31/2021 14:41:20 - INFO - __main__ - Step 140143: {'lr': 5.453541724998151e-06, 'samples': 26907456, 'steps': 140142, 'loss/train': 0.7231024503707886} 08/31/2021 14:41:21 - INFO - __main__ - Step 140144: {'lr': 5.452439400854159e-06, 'samples': 26907648, 'steps': 140143, 'loss/train': 0.5344494581222534} 08/31/2021 14:41:21 - INFO - __main__ - Step 140145: {'lr': 5.451337186899496e-06, 'samples': 26907840, 'steps': 140144, 'loss/train': 0.9391553401947021} 08/31/2021 14:41:21 - INFO - __main__ - Step 140146: {'lr': 5.450235083134719e-06, 'samples': 26908032, 'steps': 140145, 'loss/train': 0.7925633788108826} 08/31/2021 14:41:23 - INFO - __main__ - Step 140147: {'lr': 5.449133089560271e-06, 'samples': 26908224, 'steps': 140146, 'loss/train': 1.0794328451156616} 08/31/2021 14:41:24 - INFO - __main__ - Step 140148: {'lr': 5.448031206176679e-06, 'samples': 26908416, 'steps': 140147, 'loss/train': 1.6713165044784546} 08/31/2021 14:41:24 - INFO - __main__ - Step 140149: {'lr': 5.446929432984415e-06, 'samples': 26908608, 'steps': 140148, 'loss/train': 0.459293395280838} 08/31/2021 14:41:25 - INFO - __main__ - Step 140150: {'lr': 5.445827769984007e-06, 'samples': 26908800, 'steps': 140149, 'loss/train': 0.8945136070251465} 08/31/2021 14:41:25 - INFO - __main__ - Step 140151: {'lr': 5.444726217175927e-06, 'samples': 26908992, 'steps': 140150, 'loss/train': 1.5461329221725464} 08/31/2021 14:41:26 - INFO - __main__ - Step 140152: {'lr': 5.443624774560674e-06, 'samples': 26909184, 'steps': 140151, 'loss/train': 1.417539358139038} 08/31/2021 14:41:27 - INFO - __main__ - Step 140153: {'lr': 5.4425234421388025e-06, 'samples': 26909376, 'steps': 140152, 'loss/train': 1.227842926979065} 08/31/2021 14:41:27 - INFO - __main__ - Step 140154: {'lr': 5.441422219910702e-06, 'samples': 26909568, 'steps': 140153, 'loss/train': 3.7287545204162598} 08/31/2021 14:41:28 - INFO - __main__ - Step 140155: {'lr': 5.440321107876928e-06, 'samples': 26909760, 'steps': 140154, 'loss/train': 1.1437628269195557} 08/31/2021 14:41:28 - INFO - __main__ - Step 140156: {'lr': 5.439220106037979e-06, 'samples': 26909952, 'steps': 140155, 'loss/train': 0.9872034788131714} 08/31/2021 14:41:30 - INFO - __main__ - Step 140157: {'lr': 5.438119214394355e-06, 'samples': 26910144, 'steps': 140156, 'loss/train': 0.02780339866876602} 08/31/2021 14:41:30 - INFO - __main__ - Step 140158: {'lr': 5.437018432946528e-06, 'samples': 26910336, 'steps': 140157, 'loss/train': 0.9325017333030701} 08/31/2021 14:41:30 - INFO - __main__ - Step 140159: {'lr': 5.435917761694998e-06, 'samples': 26910528, 'steps': 140158, 'loss/train': 1.2401617765426636} 08/31/2021 14:41:31 - INFO - __main__ - Step 140160: {'lr': 5.434817200640291e-06, 'samples': 26910720, 'steps': 140159, 'loss/train': 1.1942495107650757} 08/31/2021 14:41:31 - INFO - __main__ - Step 140161: {'lr': 5.433716749782852e-06, 'samples': 26910912, 'steps': 140160, 'loss/train': 0.6990966200828552} 08/31/2021 14:41:33 - INFO - __main__ - Step 140162: {'lr': 5.4326164091232365e-06, 'samples': 26911104, 'steps': 140161, 'loss/train': 0.8970698714256287} 08/31/2021 14:41:33 - INFO - __main__ - Step 140163: {'lr': 5.431516178661888e-06, 'samples': 26911296, 'steps': 140162, 'loss/train': 0.43733927607536316} 08/31/2021 14:41:33 - INFO - __main__ - Step 140164: {'lr': 5.430416058399335e-06, 'samples': 26911488, 'steps': 140163, 'loss/train': 0.3384009301662445} 08/31/2021 14:41:34 - INFO - __main__ - Step 140165: {'lr': 5.429316048336047e-06, 'samples': 26911680, 'steps': 140164, 'loss/train': 1.678453803062439} 08/31/2021 14:41:34 - INFO - __main__ - Step 140166: {'lr': 5.4282161484725534e-06, 'samples': 26911872, 'steps': 140165, 'loss/train': 0.827141523361206} 08/31/2021 14:41:34 - INFO - __main__ - Step 140167: {'lr': 5.427116358809353e-06, 'samples': 26912064, 'steps': 140166, 'loss/train': 1.3940459489822388} 08/31/2021 14:41:36 - INFO - __main__ - Step 140168: {'lr': 5.42601667934689e-06, 'samples': 26912256, 'steps': 140167, 'loss/train': 0.5581265091896057} 08/31/2021 14:41:36 - INFO - __main__ - Step 140169: {'lr': 5.424917110085692e-06, 'samples': 26912448, 'steps': 140168, 'loss/train': 1.3505473136901855} 08/31/2021 14:41:37 - INFO - __main__ - Step 140170: {'lr': 5.423817651026258e-06, 'samples': 26912640, 'steps': 140169, 'loss/train': 0.8054404258728027} 08/31/2021 14:41:37 - INFO - __main__ - Step 140171: {'lr': 5.4227183021690605e-06, 'samples': 26912832, 'steps': 140170, 'loss/train': 1.4903945922851562} 08/31/2021 14:41:37 - INFO - __main__ - Step 140172: {'lr': 5.421619063514627e-06, 'samples': 26913024, 'steps': 140171, 'loss/train': 1.2009739875793457} 08/31/2021 14:41:39 - INFO - __main__ - Step 140173: {'lr': 5.420519935063456e-06, 'samples': 26913216, 'steps': 140172, 'loss/train': 1.0742907524108887} 08/31/2021 14:41:39 - INFO - __main__ - Step 140174: {'lr': 5.419420916815993e-06, 'samples': 26913408, 'steps': 140173, 'loss/train': 0.9947879910469055} 08/31/2021 14:41:40 - INFO - __main__ - Step 140175: {'lr': 5.418322008772791e-06, 'samples': 26913600, 'steps': 140174, 'loss/train': 0.6700765490531921} 08/31/2021 14:41:40 - INFO - __main__ - Step 140176: {'lr': 5.4172232109342965e-06, 'samples': 26913792, 'steps': 140175, 'loss/train': 0.9446481466293335} 08/31/2021 14:41:41 - INFO - __main__ - Step 140177: {'lr': 5.416124523301036e-06, 'samples': 26913984, 'steps': 140176, 'loss/train': 1.467617154121399} 08/31/2021 14:41:42 - INFO - __main__ - Step 140178: {'lr': 5.415025945873481e-06, 'samples': 26914176, 'steps': 140177, 'loss/train': 1.776228666305542} 08/31/2021 14:41:43 - INFO - __main__ - Step 140179: {'lr': 5.4139274786521585e-06, 'samples': 26914368, 'steps': 140178, 'loss/train': 1.1269235610961914} 08/31/2021 14:41:43 - INFO - __main__ - Step 140180: {'lr': 5.4128291216375695e-06, 'samples': 26914560, 'steps': 140179, 'loss/train': 1.1740044355392456} 08/31/2021 14:41:43 - INFO - __main__ - Step 140181: {'lr': 5.411730874830156e-06, 'samples': 26914752, 'steps': 140180, 'loss/train': 0.5844298601150513} 08/31/2021 14:41:44 - INFO - __main__ - Step 140182: {'lr': 5.4106327382304475e-06, 'samples': 26914944, 'steps': 140181, 'loss/train': 1.0690287351608276} 08/31/2021 14:41:45 - INFO - __main__ - Step 140183: {'lr': 5.409534711838943e-06, 'samples': 26915136, 'steps': 140182, 'loss/train': 0.661444365978241} 08/31/2021 14:41:46 - INFO - __main__ - Step 140184: {'lr': 5.408436795656113e-06, 'samples': 26915328, 'steps': 140183, 'loss/train': 0.9898407459259033} 08/31/2021 14:41:46 - INFO - __main__ - Step 140185: {'lr': 5.4073389896824584e-06, 'samples': 26915520, 'steps': 140184, 'loss/train': 1.1423671245574951} 08/31/2021 14:41:46 - INFO - __main__ - Step 140186: {'lr': 5.406241293918507e-06, 'samples': 26915712, 'steps': 140185, 'loss/train': 0.6765132546424866} 08/31/2021 14:41:47 - INFO - __main__ - Step 140187: {'lr': 5.405143708364702e-06, 'samples': 26915904, 'steps': 140186, 'loss/train': 0.7274655699729919} 08/31/2021 14:41:49 - INFO - __main__ - Step 140188: {'lr': 5.404046233021598e-06, 'samples': 26916096, 'steps': 140187, 'loss/train': 0.8055321574211121} 08/31/2021 14:41:49 - INFO - __main__ - Step 140189: {'lr': 5.402948867889612e-06, 'samples': 26916288, 'steps': 140188, 'loss/train': 0.40257731080055237} 08/31/2021 14:41:49 - INFO - __main__ - Step 140190: {'lr': 5.401851612969328e-06, 'samples': 26916480, 'steps': 140189, 'loss/train': 1.0479400157928467} 08/31/2021 14:41:50 - INFO - __main__ - Step 140191: {'lr': 5.40075446826116e-06, 'samples': 26916672, 'steps': 140190, 'loss/train': 0.8881248235702515} 08/31/2021 14:41:50 - INFO - __main__ - Step 140192: {'lr': 5.399657433765693e-06, 'samples': 26916864, 'steps': 140191, 'loss/train': 1.3296040296554565} 08/31/2021 14:41:50 - INFO - __main__ - Step 140193: {'lr': 5.398560509483314e-06, 'samples': 26917056, 'steps': 140192, 'loss/train': 0.014951234683394432} 08/31/2021 14:41:52 - INFO - __main__ - Step 140194: {'lr': 5.397463695414578e-06, 'samples': 26917248, 'steps': 140193, 'loss/train': 0.041534777730703354} 08/31/2021 14:41:52 - INFO - __main__ - Step 140195: {'lr': 5.396366991559987e-06, 'samples': 26917440, 'steps': 140194, 'loss/train': 1.0593591928482056} 08/31/2021 14:41:53 - INFO - __main__ - Step 140196: {'lr': 5.39527039792001e-06, 'samples': 26917632, 'steps': 140195, 'loss/train': 1.4073117971420288} 08/31/2021 14:41:53 - INFO - __main__ - Step 140197: {'lr': 5.39417391449512e-06, 'samples': 26917824, 'steps': 140196, 'loss/train': 1.1942740678787231} 08/31/2021 14:41:53 - INFO - __main__ - Step 140198: {'lr': 5.3930775412858734e-06, 'samples': 26918016, 'steps': 140197, 'loss/train': 0.8292860388755798} 08/31/2021 14:41:55 - INFO - __main__ - Step 140199: {'lr': 5.39198127829274e-06, 'samples': 26918208, 'steps': 140198, 'loss/train': 2.0105903148651123} 08/31/2021 14:41:55 - INFO - __main__ - Step 140200: {'lr': 5.3908851255161654e-06, 'samples': 26918400, 'steps': 140199, 'loss/train': 1.1063330173492432} 08/31/2021 14:41:56 - INFO - __main__ - Step 140201: {'lr': 5.389789082956731e-06, 'samples': 26918592, 'steps': 140200, 'loss/train': 1.0260388851165771} 08/31/2021 14:41:56 - INFO - __main__ - Step 140202: {'lr': 5.388693150614854e-06, 'samples': 26918784, 'steps': 140201, 'loss/train': 0.35329997539520264} 08/31/2021 14:41:56 - INFO - __main__ - Step 140203: {'lr': 5.38759732849109e-06, 'samples': 26918976, 'steps': 140202, 'loss/train': 0.6628485321998596} 08/31/2021 14:41:57 - INFO - __main__ - Step 140204: {'lr': 5.386501616585854e-06, 'samples': 26919168, 'steps': 140203, 'loss/train': 1.3688782453536987} 08/31/2021 14:41:59 - INFO - __main__ - Step 140205: {'lr': 5.385406014899702e-06, 'samples': 26919360, 'steps': 140204, 'loss/train': 1.5828386545181274} 08/31/2021 14:41:59 - INFO - __main__ - Step 140206: {'lr': 5.384310523433133e-06, 'samples': 26919552, 'steps': 140205, 'loss/train': 1.2536572217941284} 08/31/2021 14:42:00 - INFO - __main__ - Step 140207: {'lr': 5.3832151421865925e-06, 'samples': 26919744, 'steps': 140206, 'loss/train': 1.550559163093567} 08/31/2021 14:42:00 - INFO - __main__ - Step 140208: {'lr': 5.382119871160607e-06, 'samples': 26919936, 'steps': 140207, 'loss/train': 0.356533408164978} 08/31/2021 14:42:00 - INFO - __main__ - Step 140209: {'lr': 5.381024710355675e-06, 'samples': 26920128, 'steps': 140208, 'loss/train': 1.0870729684829712} 08/31/2021 14:42:02 - INFO - __main__ - Step 140210: {'lr': 5.3799296597722705e-06, 'samples': 26920320, 'steps': 140209, 'loss/train': 0.8723912239074707} 08/31/2021 14:42:02 - INFO - __main__ - Step 140211: {'lr': 5.378834719410891e-06, 'samples': 26920512, 'steps': 140210, 'loss/train': 1.2638726234436035} 08/31/2021 14:42:03 - INFO - __main__ - Step 140212: {'lr': 5.37773988927201e-06, 'samples': 26920704, 'steps': 140211, 'loss/train': 1.0106329917907715} 08/31/2021 14:42:03 - INFO - __main__ - Step 140213: {'lr': 5.376645169356181e-06, 'samples': 26920896, 'steps': 140212, 'loss/train': 1.0647939443588257} 08/31/2021 14:42:03 - INFO - __main__ - Step 140214: {'lr': 5.375550559663878e-06, 'samples': 26921088, 'steps': 140213, 'loss/train': 0.8604639172554016} 08/31/2021 14:42:05 - INFO - __main__ - Step 140215: {'lr': 5.374456060195543e-06, 'samples': 26921280, 'steps': 140214, 'loss/train': 0.9255848526954651} 08/31/2021 14:42:05 - INFO - __main__ - Step 140216: {'lr': 5.373361670951704e-06, 'samples': 26921472, 'steps': 140215, 'loss/train': 1.7172541618347168} 08/31/2021 14:42:06 - INFO - __main__ - Step 140217: {'lr': 5.372267391932861e-06, 'samples': 26921664, 'steps': 140216, 'loss/train': 1.3124973773956299} 08/31/2021 14:42:06 - INFO - __main__ - Step 140218: {'lr': 5.371173223139514e-06, 'samples': 26921856, 'steps': 140217, 'loss/train': 0.31722819805145264} 08/31/2021 14:42:07 - INFO - __main__ - Step 140219: {'lr': 5.370079164572106e-06, 'samples': 26922048, 'steps': 140218, 'loss/train': 1.3117233514785767} 08/31/2021 14:42:08 - INFO - __main__ - Step 140220: {'lr': 5.368985216231193e-06, 'samples': 26922240, 'steps': 140219, 'loss/train': 1.1303635835647583} 08/31/2021 14:42:09 - INFO - __main__ - Step 140221: {'lr': 5.367891378117218e-06, 'samples': 26922432, 'steps': 140220, 'loss/train': 0.8568574786186218} 08/31/2021 14:42:09 - INFO - __main__ - Step 140222: {'lr': 5.3667976502307095e-06, 'samples': 26922624, 'steps': 140221, 'loss/train': 1.4727683067321777} 08/31/2021 14:42:09 - INFO - __main__ - Step 140223: {'lr': 5.365704032572166e-06, 'samples': 26922816, 'steps': 140222, 'loss/train': 0.9885905385017395} 08/31/2021 14:42:10 - INFO - __main__ - Step 140224: {'lr': 5.364610525142033e-06, 'samples': 26923008, 'steps': 140223, 'loss/train': 0.09386587888002396} 08/31/2021 14:42:10 - INFO - __main__ - Step 140225: {'lr': 5.363517127940864e-06, 'samples': 26923200, 'steps': 140224, 'loss/train': 1.305136799812317} 08/31/2021 14:42:11 - INFO - __main__ - Step 140226: {'lr': 5.362423840969105e-06, 'samples': 26923392, 'steps': 140225, 'loss/train': 1.1008628606796265} 08/31/2021 14:42:12 - INFO - __main__ - Step 140227: {'lr': 5.361330664227254e-06, 'samples': 26923584, 'steps': 140226, 'loss/train': 0.6676291227340698} 08/31/2021 14:42:12 - INFO - __main__ - Step 140228: {'lr': 5.360237597715811e-06, 'samples': 26923776, 'steps': 140227, 'loss/train': 1.2713096141815186} 08/31/2021 14:42:13 - INFO - __main__ - Step 140229: {'lr': 5.359144641435276e-06, 'samples': 26923968, 'steps': 140228, 'loss/train': 0.7767798900604248} 08/31/2021 14:42:13 - INFO - __main__ - Step 140230: {'lr': 5.358051795386121e-06, 'samples': 26924160, 'steps': 140229, 'loss/train': 0.7462572455406189} 08/31/2021 14:42:15 - INFO - __main__ - Step 140231: {'lr': 5.356959059568872e-06, 'samples': 26924352, 'steps': 140230, 'loss/train': 1.8857707977294922} 08/31/2021 14:42:15 - INFO - __main__ - Step 140232: {'lr': 5.355866433983975e-06, 'samples': 26924544, 'steps': 140231, 'loss/train': 0.6120619773864746} 08/31/2021 14:42:15 - INFO - __main__ - Step 140233: {'lr': 5.3547739186319836e-06, 'samples': 26924736, 'steps': 140232, 'loss/train': 1.3038418292999268} 08/31/2021 14:42:16 - INFO - __main__ - Step 140234: {'lr': 5.353681513513342e-06, 'samples': 26924928, 'steps': 140233, 'loss/train': 0.9599124789237976} 08/31/2021 14:42:16 - INFO - __main__ - Step 140235: {'lr': 5.352589218628551e-06, 'samples': 26925120, 'steps': 140234, 'loss/train': 1.1828655004501343} 08/31/2021 14:42:18 - INFO - __main__ - Step 140236: {'lr': 5.351497033978137e-06, 'samples': 26925312, 'steps': 140235, 'loss/train': 1.0102125406265259} 08/31/2021 14:42:18 - INFO - __main__ - Step 140237: {'lr': 5.350404959562544e-06, 'samples': 26925504, 'steps': 140236, 'loss/train': 5.084567546844482} 08/31/2021 14:42:18 - INFO - __main__ - Step 140238: {'lr': 5.3493129953822715e-06, 'samples': 26925696, 'steps': 140237, 'loss/train': 0.864118754863739} 08/31/2021 14:42:19 - INFO - __main__ - Step 140239: {'lr': 5.34822114143782e-06, 'samples': 26925888, 'steps': 140238, 'loss/train': 0.041655849665403366} 08/31/2021 14:42:19 - INFO - __main__ - Step 140240: {'lr': 5.347129397729689e-06, 'samples': 26926080, 'steps': 140239, 'loss/train': 1.0137327909469604} 08/31/2021 14:42:21 - INFO - __main__ - Step 140241: {'lr': 5.346037764258377e-06, 'samples': 26926272, 'steps': 140240, 'loss/train': 0.7987406849861145} 08/31/2021 14:42:21 - INFO - __main__ - Step 140242: {'lr': 5.344946241024356e-06, 'samples': 26926464, 'steps': 140241, 'loss/train': 0.9938092231750488} 08/31/2021 14:42:21 - INFO - __main__ - Step 140243: {'lr': 5.343854828028127e-06, 'samples': 26926656, 'steps': 140242, 'loss/train': 1.4291775226593018} 08/31/2021 14:42:22 - INFO - __main__ - Step 140244: {'lr': 5.342763525270189e-06, 'samples': 26926848, 'steps': 140243, 'loss/train': 1.1786081790924072} 08/31/2021 14:42:22 - INFO - __main__ - Step 140245: {'lr': 5.341672332751013e-06, 'samples': 26927040, 'steps': 140244, 'loss/train': 0.030893079936504364} 08/31/2021 14:42:24 - INFO - __main__ - Step 140246: {'lr': 5.340581250471127e-06, 'samples': 26927232, 'steps': 140245, 'loss/train': 0.8382129669189453} 08/31/2021 14:42:24 - INFO - __main__ - Step 140247: {'lr': 5.3394902784310025e-06, 'samples': 26927424, 'steps': 140246, 'loss/train': 1.3494857549667358} 08/31/2021 14:42:25 - INFO - __main__ - Step 140248: {'lr': 5.338399416631112e-06, 'samples': 26927616, 'steps': 140247, 'loss/train': 1.252707600593567} 08/31/2021 14:42:25 - INFO - __main__ - Step 140249: {'lr': 5.337308665071983e-06, 'samples': 26927808, 'steps': 140248, 'loss/train': 0.025343963876366615} 08/31/2021 14:42:25 - INFO - __main__ - Step 140250: {'lr': 5.336218023754058e-06, 'samples': 26928000, 'steps': 140249, 'loss/train': 1.4001424312591553} 08/31/2021 14:42:27 - INFO - __main__ - Step 140251: {'lr': 5.335127492677866e-06, 'samples': 26928192, 'steps': 140250, 'loss/train': 1.3229073286056519} 08/31/2021 14:42:27 - INFO - __main__ - Step 140252: {'lr': 5.334037071843878e-06, 'samples': 26928384, 'steps': 140251, 'loss/train': 0.7644039988517761} 08/31/2021 14:42:27 - INFO - __main__ - Step 140253: {'lr': 5.3329467612526216e-06, 'samples': 26928576, 'steps': 140252, 'loss/train': 1.4703288078308105} 08/31/2021 14:42:28 - INFO - __main__ - Step 140254: {'lr': 5.331856560904541e-06, 'samples': 26928768, 'steps': 140253, 'loss/train': 0.6339448690414429} 08/31/2021 14:42:28 - INFO - __main__ - Step 140255: {'lr': 5.330766470800164e-06, 'samples': 26928960, 'steps': 140254, 'loss/train': 1.4171946048736572} 08/31/2021 14:42:29 - INFO - __main__ - Step 140256: {'lr': 5.329676490939989e-06, 'samples': 26929152, 'steps': 140255, 'loss/train': 1.2760076522827148} 08/31/2021 14:42:31 - INFO - __main__ - Step 140257: {'lr': 5.328586621324461e-06, 'samples': 26929344, 'steps': 140256, 'loss/train': 0.9563891887664795} 08/31/2021 14:42:31 - INFO - __main__ - Step 140258: {'lr': 5.327496861954106e-06, 'samples': 26929536, 'steps': 140257, 'loss/train': 0.6249846816062927} 08/31/2021 14:42:31 - INFO - __main__ - Step 140259: {'lr': 5.326407212829398e-06, 'samples': 26929728, 'steps': 140258, 'loss/train': 1.1115528345108032} 08/31/2021 14:42:32 - INFO - __main__ - Step 140260: {'lr': 5.325317673950836e-06, 'samples': 26929920, 'steps': 140259, 'loss/train': 0.348880797624588} 08/31/2021 14:42:32 - INFO - __main__ - Step 140261: {'lr': 5.3242282453189186e-06, 'samples': 26930112, 'steps': 140260, 'loss/train': 0.9760448932647705} 08/31/2021 14:42:34 - INFO - __main__ - Step 140262: {'lr': 5.323138926934118e-06, 'samples': 26930304, 'steps': 140261, 'loss/train': 1.6464985609054565} 08/31/2021 14:42:34 - INFO - __main__ - Step 140263: {'lr': 5.3220497187969345e-06, 'samples': 26930496, 'steps': 140262, 'loss/train': 1.0648735761642456} 08/31/2021 14:42:34 - INFO - __main__ - Step 140264: {'lr': 5.320960620907866e-06, 'samples': 26930688, 'steps': 140263, 'loss/train': 0.586311936378479} 08/31/2021 14:42:35 - INFO - __main__ - Step 140265: {'lr': 5.319871633267415e-06, 'samples': 26930880, 'steps': 140264, 'loss/train': 0.5087932348251343} 08/31/2021 14:42:35 - INFO - __main__ - Step 140266: {'lr': 5.318782755876023e-06, 'samples': 26931072, 'steps': 140265, 'loss/train': 1.1219345331192017} 08/31/2021 14:42:37 - INFO - __main__ - Step 140267: {'lr': 5.317693988734218e-06, 'samples': 26931264, 'steps': 140266, 'loss/train': 1.3147668838500977} 08/31/2021 14:42:37 - INFO - __main__ - Step 140268: {'lr': 5.3166053318425e-06, 'samples': 26931456, 'steps': 140267, 'loss/train': 1.261737585067749} 08/31/2021 14:42:38 - INFO - __main__ - Step 140269: {'lr': 5.315516785201313e-06, 'samples': 26931648, 'steps': 140268, 'loss/train': 0.6892493963241577} 08/31/2021 14:42:38 - INFO - __main__ - Step 140270: {'lr': 5.314428348811212e-06, 'samples': 26931840, 'steps': 140269, 'loss/train': 1.4876140356063843} 08/31/2021 14:42:38 - INFO - __main__ - Step 140271: {'lr': 5.313340022672642e-06, 'samples': 26932032, 'steps': 140270, 'loss/train': 1.4108701944351196} 08/31/2021 14:42:40 - INFO - __main__ - Step 140272: {'lr': 5.312251806786101e-06, 'samples': 26932224, 'steps': 140271, 'loss/train': 1.0165678262710571} 08/31/2021 14:42:40 - INFO - __main__ - Step 140273: {'lr': 5.311163701152089e-06, 'samples': 26932416, 'steps': 140272, 'loss/train': 0.2036036103963852} 08/31/2021 14:42:41 - INFO - __main__ - Step 140274: {'lr': 5.310075705771105e-06, 'samples': 26932608, 'steps': 140273, 'loss/train': 0.8039258122444153} 08/31/2021 14:42:41 - INFO - __main__ - Step 140275: {'lr': 5.308987820643596e-06, 'samples': 26932800, 'steps': 140274, 'loss/train': 1.2733615636825562} 08/31/2021 14:42:41 - INFO - __main__ - Step 140276: {'lr': 5.307900045770114e-06, 'samples': 26932992, 'steps': 140275, 'loss/train': 1.6639456748962402} 08/31/2021 14:42:44 - INFO - __main__ - Step 140277: {'lr': 5.306812381151077e-06, 'samples': 26933184, 'steps': 140276, 'loss/train': 1.215972900390625} 08/31/2021 14:42:44 - INFO - __main__ - Step 140278: {'lr': 5.305724826787039e-06, 'samples': 26933376, 'steps': 140277, 'loss/train': 1.0969222784042358} 08/31/2021 14:42:44 - INFO - __main__ - Step 140279: {'lr': 5.304637382678446e-06, 'samples': 26933568, 'steps': 140278, 'loss/train': 1.0642611980438232} 08/31/2021 14:42:45 - INFO - __main__ - Step 140280: {'lr': 5.303550048825823e-06, 'samples': 26933760, 'steps': 140279, 'loss/train': 0.821708619594574} 08/31/2021 14:42:45 - INFO - __main__ - Step 140281: {'lr': 5.302462825229642e-06, 'samples': 26933952, 'steps': 140280, 'loss/train': 2.209379196166992} 08/31/2021 14:42:45 - INFO - __main__ - Step 140282: {'lr': 5.301375711890405e-06, 'samples': 26934144, 'steps': 140281, 'loss/train': 3.930051803588867} 08/31/2021 14:42:47 - INFO - __main__ - Step 140283: {'lr': 5.300288708808582e-06, 'samples': 26934336, 'steps': 140282, 'loss/train': 0.3850114047527313} 08/31/2021 14:42:47 - INFO - __main__ - Step 140284: {'lr': 5.299201815984672e-06, 'samples': 26934528, 'steps': 140283, 'loss/train': 0.2320612072944641} 08/31/2021 14:42:48 - INFO - __main__ - Step 140285: {'lr': 5.298115033419176e-06, 'samples': 26934720, 'steps': 140284, 'loss/train': 1.1163970232009888} 08/31/2021 14:42:48 - INFO - __main__ - Step 140286: {'lr': 5.297028361112566e-06, 'samples': 26934912, 'steps': 140285, 'loss/train': 1.241227149963379} 08/31/2021 14:42:48 - INFO - __main__ - Step 140287: {'lr': 5.29594179906534e-06, 'samples': 26935104, 'steps': 140286, 'loss/train': 1.719240665435791} 08/31/2021 14:42:50 - INFO - __main__ - Step 140288: {'lr': 5.294855347277999e-06, 'samples': 26935296, 'steps': 140287, 'loss/train': 0.8067814111709595} 08/31/2021 14:42:50 - INFO - __main__ - Step 140289: {'lr': 5.293769005751014e-06, 'samples': 26935488, 'steps': 140288, 'loss/train': 1.0630053281784058} 08/31/2021 14:42:51 - INFO - __main__ - Step 140290: {'lr': 5.292682774484858e-06, 'samples': 26935680, 'steps': 140289, 'loss/train': 1.9031096696853638} 08/31/2021 14:42:51 - INFO - __main__ - Step 140291: {'lr': 5.2915966534800575e-06, 'samples': 26935872, 'steps': 140290, 'loss/train': 0.49484574794769287} 08/31/2021 14:42:51 - INFO - __main__ - Step 140292: {'lr': 5.2905106427370845e-06, 'samples': 26936064, 'steps': 140291, 'loss/train': 0.9962217211723328} 08/31/2021 14:42:53 - INFO - __main__ - Step 140293: {'lr': 5.289424742256438e-06, 'samples': 26936256, 'steps': 140292, 'loss/train': 1.2036831378936768} 08/31/2021 14:42:53 - INFO - __main__ - Step 140294: {'lr': 5.2883389520385905e-06, 'samples': 26936448, 'steps': 140293, 'loss/train': 1.272593379020691} 08/31/2021 14:42:54 - INFO - __main__ - Step 140295: {'lr': 5.287253272084069e-06, 'samples': 26936640, 'steps': 140294, 'loss/train': 0.10907404124736786} 08/31/2021 14:42:54 - INFO - __main__ - Step 140296: {'lr': 5.286167702393291e-06, 'samples': 26936832, 'steps': 140295, 'loss/train': 1.4312465190887451} 08/31/2021 14:42:54 - INFO - __main__ - Step 140297: {'lr': 5.2850822429668375e-06, 'samples': 26937024, 'steps': 140296, 'loss/train': 1.1566458940505981} 08/31/2021 14:42:56 - INFO - __main__ - Step 140298: {'lr': 5.283996893805126e-06, 'samples': 26937216, 'steps': 140297, 'loss/train': 1.0121244192123413} 08/31/2021 14:42:56 - INFO - __main__ - Step 140299: {'lr': 5.282911654908656e-06, 'samples': 26937408, 'steps': 140298, 'loss/train': 1.4418851137161255} 08/31/2021 14:42:56 - INFO - __main__ - Step 140300: {'lr': 5.2818265262779275e-06, 'samples': 26937600, 'steps': 140299, 'loss/train': 1.1428836584091187} 08/31/2021 14:42:57 - INFO - __main__ - Step 140301: {'lr': 5.2807415079134946e-06, 'samples': 26937792, 'steps': 140300, 'loss/train': 1.5570142269134521} 08/31/2021 14:42:57 - INFO - __main__ - Step 140302: {'lr': 5.279656599815718e-06, 'samples': 26937984, 'steps': 140301, 'loss/train': 1.4622241258621216} 08/31/2021 14:42:59 - INFO - __main__ - Step 140303: {'lr': 5.278571801985183e-06, 'samples': 26938176, 'steps': 140302, 'loss/train': 0.9346014261245728} 08/31/2021 14:42:59 - INFO - __main__ - Step 140304: {'lr': 5.27748711442233e-06, 'samples': 26938368, 'steps': 140303, 'loss/train': 0.6754108667373657} 08/31/2021 14:43:00 - INFO - __main__ - Step 140305: {'lr': 5.276402537127662e-06, 'samples': 26938560, 'steps': 140304, 'loss/train': 1.2942824363708496} 08/31/2021 14:43:00 - INFO - __main__ - Step 140306: {'lr': 5.275318070101676e-06, 'samples': 26938752, 'steps': 140305, 'loss/train': 0.03861255571246147} 08/31/2021 14:43:00 - INFO - __main__ - Step 140307: {'lr': 5.274233713344845e-06, 'samples': 26938944, 'steps': 140306, 'loss/train': 1.275454044342041} 08/31/2021 14:43:02 - INFO - __main__ - Step 140308: {'lr': 5.273149466857696e-06, 'samples': 26939136, 'steps': 140307, 'loss/train': 1.5902658700942993} 08/31/2021 14:43:03 - INFO - __main__ - Step 140309: {'lr': 5.272065330640674e-06, 'samples': 26939328, 'steps': 140308, 'loss/train': 0.10240952670574188} 08/31/2021 14:43:03 - INFO - __main__ - Step 140310: {'lr': 5.270981304694278e-06, 'samples': 26939520, 'steps': 140309, 'loss/train': 1.273871660232544} 08/31/2021 14:43:04 - INFO - __main__ - Step 140311: {'lr': 5.269897389019007e-06, 'samples': 26939712, 'steps': 140310, 'loss/train': 0.9263697862625122} 08/31/2021 14:43:04 - INFO - __main__ - Step 140312: {'lr': 5.268813583615334e-06, 'samples': 26939904, 'steps': 140311, 'loss/train': 0.9852545857429504} 08/31/2021 14:43:04 - INFO - __main__ - Step 140313: {'lr': 5.267729888483758e-06, 'samples': 26940096, 'steps': 140312, 'loss/train': 1.0092341899871826} 08/31/2021 14:43:06 - INFO - __main__ - Step 140314: {'lr': 5.266646303624778e-06, 'samples': 26940288, 'steps': 140313, 'loss/train': 1.3089616298675537} 08/31/2021 14:43:06 - INFO - __main__ - Step 140315: {'lr': 5.265562829038895e-06, 'samples': 26940480, 'steps': 140314, 'loss/train': 1.0227439403533936} 08/31/2021 14:43:06 - INFO - __main__ - Step 140316: {'lr': 5.264479464726524e-06, 'samples': 26940672, 'steps': 140315, 'loss/train': 0.5565036535263062} 08/31/2021 14:43:07 - INFO - __main__ - Step 140317: {'lr': 5.263396210688248e-06, 'samples': 26940864, 'steps': 140316, 'loss/train': 0.8204775452613831} 08/31/2021 14:43:07 - INFO - __main__ - Step 140318: {'lr': 5.262313066924457e-06, 'samples': 26941056, 'steps': 140317, 'loss/train': 1.3176151514053345} 08/31/2021 14:43:09 - INFO - __main__ - Step 140319: {'lr': 5.261230033435732e-06, 'samples': 26941248, 'steps': 140318, 'loss/train': 0.15352310240268707} 08/31/2021 14:43:09 - INFO - __main__ - Step 140320: {'lr': 5.260147110222491e-06, 'samples': 26941440, 'steps': 140319, 'loss/train': 1.387784719467163} 08/31/2021 14:43:10 - INFO - __main__ - Step 140321: {'lr': 5.259064297285287e-06, 'samples': 26941632, 'steps': 140320, 'loss/train': 0.16623130440711975} 08/31/2021 14:43:10 - INFO - __main__ - Step 140322: {'lr': 5.257981594624539e-06, 'samples': 26941824, 'steps': 140321, 'loss/train': 0.5164940357208252} 08/31/2021 14:43:10 - INFO - __main__ - Step 140323: {'lr': 5.2568990022407725e-06, 'samples': 26942016, 'steps': 140322, 'loss/train': 0.41190382838249207} 08/31/2021 14:43:12 - INFO - __main__ - Step 140324: {'lr': 5.255816520134488e-06, 'samples': 26942208, 'steps': 140323, 'loss/train': 0.19784680008888245} 08/31/2021 14:43:13 - INFO - __main__ - Step 140325: {'lr': 5.254734148306156e-06, 'samples': 26942400, 'steps': 140324, 'loss/train': 0.47416967153549194} 08/31/2021 14:43:13 - INFO - __main__ - Step 140326: {'lr': 5.25365188675625e-06, 'samples': 26942592, 'steps': 140325, 'loss/train': 1.0021096467971802} 08/31/2021 14:43:13 - INFO - __main__ - Step 140327: {'lr': 5.252569735485269e-06, 'samples': 26942784, 'steps': 140326, 'loss/train': 0.9818263053894043} 08/31/2021 14:43:14 - INFO - __main__ - Step 140328: {'lr': 5.25148769449374e-06, 'samples': 26942976, 'steps': 140327, 'loss/train': 0.8333150148391724} 08/31/2021 14:43:14 - INFO - __main__ - Step 140329: {'lr': 5.250405763782079e-06, 'samples': 26943168, 'steps': 140328, 'loss/train': 0.39415568113327026} 08/31/2021 14:43:15 - INFO - __main__ - Step 140330: {'lr': 5.249323943350815e-06, 'samples': 26943360, 'steps': 140329, 'loss/train': 0.6322773098945618} 08/31/2021 14:43:16 - INFO - __main__ - Step 140331: {'lr': 5.2482422332004175e-06, 'samples': 26943552, 'steps': 140330, 'loss/train': 0.9096168875694275} 08/31/2021 14:43:16 - INFO - __main__ - Step 140332: {'lr': 5.247160633331388e-06, 'samples': 26943744, 'steps': 140331, 'loss/train': 0.6139997243881226} 08/31/2021 14:43:17 - INFO - __main__ - Step 140333: {'lr': 5.246079143744226e-06, 'samples': 26943936, 'steps': 140332, 'loss/train': 1.1774442195892334} 08/31/2021 14:43:17 - INFO - __main__ - Step 140334: {'lr': 5.244997764439402e-06, 'samples': 26944128, 'steps': 140333, 'loss/train': 0.781227171421051} 08/31/2021 14:43:19 - INFO - __main__ - Step 140335: {'lr': 5.243916495417389e-06, 'samples': 26944320, 'steps': 140334, 'loss/train': 0.879625141620636} 08/31/2021 14:43:20 - INFO - __main__ - Step 140336: {'lr': 5.242835336678714e-06, 'samples': 26944512, 'steps': 140335, 'loss/train': 1.024133563041687} 08/31/2021 14:43:20 - INFO - __main__ - Step 140337: {'lr': 5.241754288223821e-06, 'samples': 26944704, 'steps': 140336, 'loss/train': 0.03476717695593834} 08/31/2021 14:43:20 - INFO - __main__ - Step 140338: {'lr': 5.24067335005321e-06, 'samples': 26944896, 'steps': 140337, 'loss/train': 0.021839689463377} 08/31/2021 14:43:21 - INFO - __main__ - Step 140339: {'lr': 5.239592522167408e-06, 'samples': 26945088, 'steps': 140338, 'loss/train': 0.08668705821037292} 08/31/2021 14:43:22 - INFO - __main__ - Step 140340: {'lr': 5.238511804566831e-06, 'samples': 26945280, 'steps': 140339, 'loss/train': 0.1139122024178505} 08/31/2021 14:43:22 - INFO - __main__ - Step 140341: {'lr': 5.237431197252063e-06, 'samples': 26945472, 'steps': 140340, 'loss/train': 1.0932799577713013} 08/31/2021 14:43:23 - INFO - __main__ - Step 140342: {'lr': 5.236350700223491e-06, 'samples': 26945664, 'steps': 140341, 'loss/train': 0.7168014049530029} 08/31/2021 14:43:23 - INFO - __main__ - Step 140343: {'lr': 5.235270313481644e-06, 'samples': 26945856, 'steps': 140342, 'loss/train': 1.131933569908142} 08/31/2021 14:43:24 - INFO - __main__ - Step 140344: {'lr': 5.234190037026992e-06, 'samples': 26946048, 'steps': 140343, 'loss/train': 1.5954298973083496} 08/31/2021 14:43:25 - INFO - __main__ - Step 140345: {'lr': 5.233109870860037e-06, 'samples': 26946240, 'steps': 140344, 'loss/train': 0.712350070476532} 08/31/2021 14:43:25 - INFO - __main__ - Step 140346: {'lr': 5.232029814981276e-06, 'samples': 26946432, 'steps': 140345, 'loss/train': 1.8859552145004272} 08/31/2021 14:43:26 - INFO - __main__ - Step 140347: {'lr': 5.23094986939121e-06, 'samples': 26946624, 'steps': 140346, 'loss/train': 0.7695039510726929} 08/31/2021 14:43:26 - INFO - __main__ - Step 140348: {'lr': 5.2298700340902565e-06, 'samples': 26946816, 'steps': 140347, 'loss/train': 0.03130421042442322} 08/31/2021 14:43:27 - INFO - __main__ - Step 140349: {'lr': 5.228790309078968e-06, 'samples': 26947008, 'steps': 140348, 'loss/train': 0.9492831230163574} 08/31/2021 14:43:28 - INFO - __main__ - Step 140350: {'lr': 5.227710694357818e-06, 'samples': 26947200, 'steps': 140349, 'loss/train': 1.4247368574142456} 08/31/2021 14:43:29 - INFO - __main__ - Step 140351: {'lr': 5.226631189927278e-06, 'samples': 26947392, 'steps': 140350, 'loss/train': 1.1908050775527954} 08/31/2021 14:43:29 - INFO - __main__ - Step 140352: {'lr': 5.2255517957878475e-06, 'samples': 26947584, 'steps': 140351, 'loss/train': 1.5423517227172852} 08/31/2021 14:43:29 - INFO - __main__ - Step 140353: {'lr': 5.224472511939999e-06, 'samples': 26947776, 'steps': 140352, 'loss/train': 0.7516454458236694} 08/31/2021 14:43:30 - INFO - __main__ - Step 140354: {'lr': 5.22339333838423e-06, 'samples': 26947968, 'steps': 140353, 'loss/train': 0.019740808755159378} 08/31/2021 14:43:31 - INFO - __main__ - Step 140355: {'lr': 5.222314275121043e-06, 'samples': 26948160, 'steps': 140354, 'loss/train': 1.4294294118881226} 08/31/2021 14:43:32 - INFO - __main__ - Step 140356: {'lr': 5.22123532215088e-06, 'samples': 26948352, 'steps': 140355, 'loss/train': 0.6094142198562622} 08/31/2021 14:43:32 - INFO - __main__ - Step 140357: {'lr': 5.220156479474242e-06, 'samples': 26948544, 'steps': 140356, 'loss/train': 0.8298439383506775} 08/31/2021 14:43:32 - INFO - __main__ - Step 140358: {'lr': 5.219077747091627e-06, 'samples': 26948736, 'steps': 140357, 'loss/train': 1.2286521196365356} 08/31/2021 14:43:33 - INFO - __main__ - Step 140359: {'lr': 5.217999125003536e-06, 'samples': 26948928, 'steps': 140358, 'loss/train': 0.9654020071029663} 08/31/2021 14:43:34 - INFO - __main__ - Step 140360: {'lr': 5.216920613210413e-06, 'samples': 26949120, 'steps': 140359, 'loss/train': 1.0855015516281128} 08/31/2021 14:43:35 - INFO - __main__ - Step 140361: {'lr': 5.215842211712785e-06, 'samples': 26949312, 'steps': 140360, 'loss/train': 0.42643770575523376} 08/31/2021 14:43:35 - INFO - __main__ - Step 140362: {'lr': 5.214763920511123e-06, 'samples': 26949504, 'steps': 140361, 'loss/train': 1.0375933647155762} 08/31/2021 14:43:36 - INFO - __main__ - Step 140363: {'lr': 5.2136857396059e-06, 'samples': 26949696, 'steps': 140362, 'loss/train': 0.047708362340927124} 08/31/2021 14:43:36 - INFO - __main__ - Step 140364: {'lr': 5.212607668997615e-06, 'samples': 26949888, 'steps': 140363, 'loss/train': 0.2890307903289795} 08/31/2021 14:43:38 - INFO - __main__ - Step 140365: {'lr': 5.211529708686741e-06, 'samples': 26950080, 'steps': 140364, 'loss/train': 0.7387940287590027} 08/31/2021 14:43:38 - INFO - __main__ - Step 140366: {'lr': 5.210451858673804e-06, 'samples': 26950272, 'steps': 140365, 'loss/train': 1.0402190685272217} 08/31/2021 14:43:39 - INFO - __main__ - Step 140367: {'lr': 5.209374118959248e-06, 'samples': 26950464, 'steps': 140366, 'loss/train': 1.3727881908416748} 08/31/2021 14:43:39 - INFO - __main__ - Step 140368: {'lr': 5.208296489543573e-06, 'samples': 26950656, 'steps': 140367, 'loss/train': 1.092840313911438} 08/31/2021 14:43:39 - INFO - __main__ - Step 140369: {'lr': 5.207218970427252e-06, 'samples': 26950848, 'steps': 140368, 'loss/train': 0.6392544507980347} 08/31/2021 14:43:40 - INFO - __main__ - Step 140370: {'lr': 5.206141561610783e-06, 'samples': 26951040, 'steps': 140369, 'loss/train': 0.36044204235076904} 08/31/2021 14:43:42 - INFO - __main__ - Step 140371: {'lr': 5.205064263094666e-06, 'samples': 26951232, 'steps': 140370, 'loss/train': 0.9198463559150696} 08/31/2021 14:43:42 - INFO - __main__ - Step 140372: {'lr': 5.203987074879346e-06, 'samples': 26951424, 'steps': 140371, 'loss/train': 0.9465748071670532} 08/31/2021 14:43:42 - INFO - __main__ - Step 140373: {'lr': 5.202909996965349e-06, 'samples': 26951616, 'steps': 140372, 'loss/train': 0.7765649557113647} 08/31/2021 14:43:43 - INFO - __main__ - Step 140374: {'lr': 5.201833029353121e-06, 'samples': 26951808, 'steps': 140373, 'loss/train': 1.106499433517456} 08/31/2021 14:43:43 - INFO - __main__ - Step 140375: {'lr': 5.200756172043186e-06, 'samples': 26952000, 'steps': 140374, 'loss/train': 1.404079556465149} 08/31/2021 14:43:45 - INFO - __main__ - Step 140376: {'lr': 5.199679425036019e-06, 'samples': 26952192, 'steps': 140375, 'loss/train': 0.7993208765983582} 08/31/2021 14:43:45 - INFO - __main__ - Step 140377: {'lr': 5.198602788332091e-06, 'samples': 26952384, 'steps': 140376, 'loss/train': 1.2689716815948486} 08/31/2021 14:43:45 - INFO - __main__ - Step 140378: {'lr': 5.197526261931901e-06, 'samples': 26952576, 'steps': 140377, 'loss/train': 0.9952148199081421} 08/31/2021 14:43:46 - INFO - __main__ - Step 140379: {'lr': 5.196449845835921e-06, 'samples': 26952768, 'steps': 140378, 'loss/train': 1.0834975242614746} 08/31/2021 14:43:46 - INFO - __main__ - Step 140380: {'lr': 5.195373540044651e-06, 'samples': 26952960, 'steps': 140379, 'loss/train': 0.737011730670929} 08/31/2021 14:43:48 - INFO - __main__ - Step 140381: {'lr': 5.194297344558535e-06, 'samples': 26953152, 'steps': 140380, 'loss/train': 0.9610611200332642} 08/31/2021 14:43:48 - INFO - __main__ - Step 140382: {'lr': 5.193221259378156e-06, 'samples': 26953344, 'steps': 140381, 'loss/train': 1.4991081953048706} 08/31/2021 14:43:49 - INFO - __main__ - Step 140383: {'lr': 5.192145284503902e-06, 'samples': 26953536, 'steps': 140382, 'loss/train': 1.1307032108306885} 08/31/2021 14:43:49 - INFO - __main__ - Step 140384: {'lr': 5.191069419936273e-06, 'samples': 26953728, 'steps': 140383, 'loss/train': 0.691015362739563} 08/31/2021 14:43:49 - INFO - __main__ - Step 140385: {'lr': 5.1899936656757685e-06, 'samples': 26953920, 'steps': 140384, 'loss/train': 0.5878123044967651} 08/31/2021 14:43:51 - INFO - __main__ - Step 140386: {'lr': 5.188918021722888e-06, 'samples': 26954112, 'steps': 140385, 'loss/train': 0.8515516519546509} 08/31/2021 14:43:51 - INFO - __main__ - Step 140387: {'lr': 5.187842488078104e-06, 'samples': 26954304, 'steps': 140386, 'loss/train': 0.5968278646469116} 08/31/2021 14:43:52 - INFO - __main__ - Step 140388: {'lr': 5.186767064741915e-06, 'samples': 26954496, 'steps': 140387, 'loss/train': 1.0574640035629272} 08/31/2021 14:43:52 - INFO - __main__ - Step 140389: {'lr': 5.185691751714766e-06, 'samples': 26954688, 'steps': 140388, 'loss/train': 1.0369341373443604} 08/31/2021 14:43:52 - INFO - __main__ - Step 140390: {'lr': 5.1846165489971846e-06, 'samples': 26954880, 'steps': 140389, 'loss/train': 2.091421127319336} 08/31/2021 14:43:53 - INFO - __main__ - Step 140391: {'lr': 5.183541456589613e-06, 'samples': 26955072, 'steps': 140390, 'loss/train': 0.46909770369529724} 08/31/2021 14:43:54 - INFO - __main__ - Step 140392: {'lr': 5.182466474492581e-06, 'samples': 26955264, 'steps': 140391, 'loss/train': 1.460213303565979} 08/31/2021 14:43:55 - INFO - __main__ - Step 140393: {'lr': 5.181391602706531e-06, 'samples': 26955456, 'steps': 140392, 'loss/train': 1.0720101594924927} 08/31/2021 14:43:55 - INFO - __main__ - Step 140394: {'lr': 5.180316841231991e-06, 'samples': 26955648, 'steps': 140393, 'loss/train': 1.1164140701293945} 08/31/2021 14:43:55 - INFO - __main__ - Step 140395: {'lr': 5.179242190069433e-06, 'samples': 26955840, 'steps': 140394, 'loss/train': 1.5317217111587524} 08/31/2021 14:43:56 - INFO - __main__ - Step 140396: {'lr': 5.178167649219329e-06, 'samples': 26956032, 'steps': 140395, 'loss/train': 0.7907448410987854} 08/31/2021 14:43:57 - INFO - __main__ - Step 140397: {'lr': 5.177093218682122e-06, 'samples': 26956224, 'steps': 140396, 'loss/train': 1.3721024990081787} 08/31/2021 14:43:58 - INFO - __main__ - Step 140398: {'lr': 5.1760188984583675e-06, 'samples': 26956416, 'steps': 140397, 'loss/train': 1.1642440557479858} 08/31/2021 14:43:58 - INFO - __main__ - Step 140399: {'lr': 5.174944688548538e-06, 'samples': 26956608, 'steps': 140398, 'loss/train': 1.1766237020492554} 08/31/2021 14:43:58 - INFO - __main__ - Step 140400: {'lr': 5.173870588953078e-06, 'samples': 26956800, 'steps': 140399, 'loss/train': 0.7467219829559326} 08/31/2021 14:43:59 - INFO - __main__ - Step 140401: {'lr': 5.172796599672486e-06, 'samples': 26956992, 'steps': 140400, 'loss/train': 0.14274337887763977} 08/31/2021 14:44:00 - INFO - __main__ - Step 140402: {'lr': 5.171722720707262e-06, 'samples': 26957184, 'steps': 140401, 'loss/train': 1.156965732574463} 08/31/2021 14:44:01 - INFO - __main__ - Step 140403: {'lr': 5.170648952057877e-06, 'samples': 26957376, 'steps': 140402, 'loss/train': 0.9565089344978333} 08/31/2021 14:44:01 - INFO - __main__ - Step 140404: {'lr': 5.169575293724832e-06, 'samples': 26957568, 'steps': 140403, 'loss/train': 1.6872652769088745} 08/31/2021 14:44:01 - INFO - __main__ - Step 140405: {'lr': 5.168501745708598e-06, 'samples': 26957760, 'steps': 140404, 'loss/train': 1.0646052360534668} 08/31/2021 14:44:02 - INFO - __main__ - Step 140406: {'lr': 5.167428308009647e-06, 'samples': 26957952, 'steps': 140405, 'loss/train': 1.2274311780929565} 08/31/2021 14:44:04 - INFO - __main__ - Step 140407: {'lr': 5.166354980628479e-06, 'samples': 26958144, 'steps': 140406, 'loss/train': 0.8190361261367798} 08/31/2021 14:44:04 - INFO - __main__ - Step 140408: {'lr': 5.165281763565594e-06, 'samples': 26958336, 'steps': 140407, 'loss/train': 0.8210251331329346} 08/31/2021 14:44:04 - INFO - __main__ - Step 140409: {'lr': 5.1642086568214615e-06, 'samples': 26958528, 'steps': 140408, 'loss/train': 1.0702028274536133} 08/31/2021 14:44:05 - INFO - __main__ - Step 140410: {'lr': 5.163135660396528e-06, 'samples': 26958720, 'steps': 140409, 'loss/train': 0.8979271650314331} 08/31/2021 14:44:05 - INFO - __main__ - Step 140411: {'lr': 5.162062774291321e-06, 'samples': 26958912, 'steps': 140410, 'loss/train': 1.5251728296279907} 08/31/2021 14:44:05 - INFO - __main__ - Step 140412: {'lr': 5.16098999850631e-06, 'samples': 26959104, 'steps': 140411, 'loss/train': 1.0411564111709595} 08/31/2021 14:44:07 - INFO - __main__ - Step 140413: {'lr': 5.159917333041969e-06, 'samples': 26959296, 'steps': 140412, 'loss/train': 1.6189203262329102} 08/31/2021 14:44:07 - INFO - __main__ - Step 140414: {'lr': 5.1588447778987966e-06, 'samples': 26959488, 'steps': 140413, 'loss/train': 0.6188381910324097} 08/31/2021 14:44:08 - INFO - __main__ - Step 140415: {'lr': 5.157772333077265e-06, 'samples': 26959680, 'steps': 140414, 'loss/train': 1.5399048328399658} 08/31/2021 14:44:08 - INFO - __main__ - Step 140416: {'lr': 5.156699998577846e-06, 'samples': 26959872, 'steps': 140415, 'loss/train': 1.326706886291504} 08/31/2021 14:44:08 - INFO - __main__ - Step 140417: {'lr': 5.155627774401067e-06, 'samples': 26960064, 'steps': 140416, 'loss/train': 1.1439228057861328} 08/31/2021 14:44:10 - INFO - __main__ - Step 140418: {'lr': 5.1545556605473724e-06, 'samples': 26960256, 'steps': 140417, 'loss/train': 1.2925034761428833} 08/31/2021 14:44:11 - INFO - __main__ - Step 140419: {'lr': 5.15348365701726e-06, 'samples': 26960448, 'steps': 140418, 'loss/train': 1.2818001508712769} 08/31/2021 14:44:11 - INFO - __main__ - Step 140420: {'lr': 5.152411763811232e-06, 'samples': 26960640, 'steps': 140419, 'loss/train': 1.2760636806488037} 08/31/2021 14:44:12 - INFO - __main__ - Step 140421: {'lr': 5.151339980929731e-06, 'samples': 26960832, 'steps': 140420, 'loss/train': 1.3619396686553955} 08/31/2021 14:44:12 - INFO - __main__ - Step 140422: {'lr': 5.150268308373257e-06, 'samples': 26961024, 'steps': 140421, 'loss/train': 1.5969773530960083} 08/31/2021 14:44:14 - INFO - __main__ - Step 140423: {'lr': 5.14919674614231e-06, 'samples': 26961216, 'steps': 140422, 'loss/train': 0.7565270662307739} 08/31/2021 14:44:14 - INFO - __main__ - Step 140424: {'lr': 5.148125294237332e-06, 'samples': 26961408, 'steps': 140423, 'loss/train': 1.0912448167800903} 08/31/2021 14:44:14 - INFO - __main__ - Step 140425: {'lr': 5.147053952658826e-06, 'samples': 26961600, 'steps': 140424, 'loss/train': 1.2370651960372925} 08/31/2021 14:44:15 - INFO - __main__ - Step 140426: {'lr': 5.145982721407316e-06, 'samples': 26961792, 'steps': 140425, 'loss/train': 0.9031437039375305} 08/31/2021 14:44:15 - INFO - __main__ - Step 140427: {'lr': 5.144911600483221e-06, 'samples': 26961984, 'steps': 140426, 'loss/train': 1.1898689270019531} 08/31/2021 14:44:16 - INFO - __main__ - Step 140428: {'lr': 5.143840589887039e-06, 'samples': 26962176, 'steps': 140427, 'loss/train': 0.7358949184417725} 08/31/2021 14:44:17 - INFO - __main__ - Step 140429: {'lr': 5.14276968961927e-06, 'samples': 26962368, 'steps': 140428, 'loss/train': 0.06547322869300842} 08/31/2021 14:44:17 - INFO - __main__ - Step 140430: {'lr': 5.141698899680414e-06, 'samples': 26962560, 'steps': 140429, 'loss/train': 0.052605949342250824} 08/31/2021 14:44:18 - INFO - __main__ - Step 140431: {'lr': 5.140628220070914e-06, 'samples': 26962752, 'steps': 140430, 'loss/train': 1.296789526939392} 08/31/2021 14:44:18 - INFO - __main__ - Step 140432: {'lr': 5.139557650791271e-06, 'samples': 26962944, 'steps': 140431, 'loss/train': 0.514613926410675} 08/31/2021 14:44:18 - INFO - __main__ - Step 140433: {'lr': 5.1384871918419565e-06, 'samples': 26963136, 'steps': 140432, 'loss/train': 1.6842056512832642} 08/31/2021 14:44:20 - INFO - __main__ - Step 140434: {'lr': 5.137416843223469e-06, 'samples': 26963328, 'steps': 140433, 'loss/train': 0.9911539554595947} 08/31/2021 14:44:21 - INFO - __main__ - Step 140435: {'lr': 5.136346604936282e-06, 'samples': 26963520, 'steps': 140434, 'loss/train': 0.682158350944519} 08/31/2021 14:44:21 - INFO - __main__ - Step 140436: {'lr': 5.135276476980893e-06, 'samples': 26963712, 'steps': 140435, 'loss/train': 0.4980538785457611} 08/31/2021 14:44:21 - INFO - __main__ - Step 140437: {'lr': 5.134206459357748e-06, 'samples': 26963904, 'steps': 140436, 'loss/train': 1.0116822719573975} 08/31/2021 14:44:22 - INFO - __main__ - Step 140438: {'lr': 5.133136552067374e-06, 'samples': 26964096, 'steps': 140437, 'loss/train': 1.0510166883468628} 08/31/2021 14:44:22 - INFO - __main__ - Step 140439: {'lr': 5.132066755110215e-06, 'samples': 26964288, 'steps': 140438, 'loss/train': 1.7061322927474976} 08/31/2021 14:44:24 - INFO - __main__ - Step 140440: {'lr': 5.130997068486742e-06, 'samples': 26964480, 'steps': 140439, 'loss/train': 0.7191047668457031} 08/31/2021 14:44:24 - INFO - __main__ - Step 140441: {'lr': 5.129927492197511e-06, 'samples': 26964672, 'steps': 140440, 'loss/train': 1.6103098392486572} 08/31/2021 14:44:25 - INFO - __main__ - Step 140442: {'lr': 5.1288580262429105e-06, 'samples': 26964864, 'steps': 140441, 'loss/train': 1.2664145231246948} 08/31/2021 14:44:25 - INFO - __main__ - Step 140443: {'lr': 5.127788670623496e-06, 'samples': 26965056, 'steps': 140442, 'loss/train': 1.3125503063201904} 08/31/2021 14:44:25 - INFO - __main__ - Step 140444: {'lr': 5.12671942533971e-06, 'samples': 26965248, 'steps': 140443, 'loss/train': 1.2591854333877563} 08/31/2021 14:44:27 - INFO - __main__ - Step 140445: {'lr': 5.125650290392053e-06, 'samples': 26965440, 'steps': 140444, 'loss/train': 0.9411742687225342} 08/31/2021 14:44:27 - INFO - __main__ - Step 140446: {'lr': 5.1245812657809976e-06, 'samples': 26965632, 'steps': 140445, 'loss/train': 1.2527425289154053} 08/31/2021 14:44:28 - INFO - __main__ - Step 140447: {'lr': 5.123512351507042e-06, 'samples': 26965824, 'steps': 140446, 'loss/train': 1.1920853853225708} 08/31/2021 14:44:28 - INFO - __main__ - Step 140448: {'lr': 5.1224435475706325e-06, 'samples': 26966016, 'steps': 140447, 'loss/train': 1.014230489730835} 08/31/2021 14:44:28 - INFO - __main__ - Step 140449: {'lr': 5.121374853972294e-06, 'samples': 26966208, 'steps': 140448, 'loss/train': 0.7352127432823181} 08/31/2021 14:44:29 - INFO - __main__ - Step 140450: {'lr': 5.120306270712472e-06, 'samples': 26966400, 'steps': 140449, 'loss/train': 0.7935500144958496} 08/31/2021 14:44:30 - INFO - __main__ - Step 140451: {'lr': 5.119237797791665e-06, 'samples': 26966592, 'steps': 140450, 'loss/train': 1.1534242630004883} 08/31/2021 14:44:30 - INFO - __main__ - Step 140452: {'lr': 5.118169435210346e-06, 'samples': 26966784, 'steps': 140451, 'loss/train': 1.760524868965149} 08/31/2021 14:44:31 - INFO - __main__ - Step 140453: {'lr': 5.117101182968986e-06, 'samples': 26966976, 'steps': 140452, 'loss/train': 1.796571135520935} 08/31/2021 14:44:31 - INFO - __main__ - Step 140454: {'lr': 5.116033041068113e-06, 'samples': 26967168, 'steps': 140453, 'loss/train': 1.3410495519638062} 08/31/2021 14:44:32 - INFO - __main__ - Step 140455: {'lr': 5.114965009508143e-06, 'samples': 26967360, 'steps': 140454, 'loss/train': 1.492177963256836} 08/31/2021 14:44:33 - INFO - __main__ - Step 140456: {'lr': 5.113897088289604e-06, 'samples': 26967552, 'steps': 140455, 'loss/train': 0.907970130443573} 08/31/2021 14:44:33 - INFO - __main__ - Step 140457: {'lr': 5.112829277412967e-06, 'samples': 26967744, 'steps': 140456, 'loss/train': 0.9419637322425842} 08/31/2021 14:44:34 - INFO - __main__ - Step 140458: {'lr': 5.111761576878704e-06, 'samples': 26967936, 'steps': 140457, 'loss/train': 1.2803295850753784} 08/31/2021 14:44:34 - INFO - __main__ - Step 140459: {'lr': 5.110693986687315e-06, 'samples': 26968128, 'steps': 140458, 'loss/train': 1.277874231338501} 08/31/2021 14:44:35 - INFO - __main__ - Step 140460: {'lr': 5.109626506839271e-06, 'samples': 26968320, 'steps': 140459, 'loss/train': 1.1944714784622192} 08/31/2021 14:44:36 - INFO - __main__ - Step 140461: {'lr': 5.108559137335045e-06, 'samples': 26968512, 'steps': 140460, 'loss/train': 1.005085825920105} 08/31/2021 14:44:36 - INFO - __main__ - Step 140462: {'lr': 5.107491878175135e-06, 'samples': 26968704, 'steps': 140461, 'loss/train': 0.5432658195495605} 08/31/2021 14:44:37 - INFO - __main__ - Step 140463: {'lr': 5.1064247293599875e-06, 'samples': 26968896, 'steps': 140462, 'loss/train': 0.8890294432640076} 08/31/2021 14:44:37 - INFO - __main__ - Step 140464: {'lr': 5.105357690890128e-06, 'samples': 26969088, 'steps': 140463, 'loss/train': 0.9020870327949524} 08/31/2021 14:44:37 - INFO - __main__ - Step 140465: {'lr': 5.104290762766e-06, 'samples': 26969280, 'steps': 140464, 'loss/train': 0.4094238579273224} 08/31/2021 14:44:39 - INFO - __main__ - Step 140466: {'lr': 5.103223944988078e-06, 'samples': 26969472, 'steps': 140465, 'loss/train': 1.2155168056488037} 08/31/2021 14:44:39 - INFO - __main__ - Step 140467: {'lr': 5.102157237556887e-06, 'samples': 26969664, 'steps': 140466, 'loss/train': 1.6051403284072876} 08/31/2021 14:44:40 - INFO - __main__ - Step 140468: {'lr': 5.1010906404728994e-06, 'samples': 26969856, 'steps': 140467, 'loss/train': 1.0587939023971558} 08/31/2021 14:44:40 - INFO - __main__ - Step 140469: {'lr': 5.10002415373656e-06, 'samples': 26970048, 'steps': 140468, 'loss/train': 0.9152467846870422} 08/31/2021 14:44:40 - INFO - __main__ - Step 140470: {'lr': 5.098957777348367e-06, 'samples': 26970240, 'steps': 140469, 'loss/train': 0.897566020488739} 08/31/2021 14:44:42 - INFO - __main__ - Step 140471: {'lr': 5.097891511308822e-06, 'samples': 26970432, 'steps': 140470, 'loss/train': 1.1401218175888062} 08/31/2021 14:44:42 - INFO - __main__ - Step 140472: {'lr': 5.096825355618395e-06, 'samples': 26970624, 'steps': 140471, 'loss/train': 0.9905244708061218} 08/31/2021 14:44:43 - INFO - __main__ - Step 140473: {'lr': 5.095759310277559e-06, 'samples': 26970816, 'steps': 140472, 'loss/train': 1.6313817501068115} 08/31/2021 14:44:43 - INFO - __main__ - Step 140474: {'lr': 5.094693375286785e-06, 'samples': 26971008, 'steps': 140473, 'loss/train': 0.3372138440608978} 08/31/2021 14:44:43 - INFO - __main__ - Step 140475: {'lr': 5.093627550646545e-06, 'samples': 26971200, 'steps': 140474, 'loss/train': 0.9806071519851685} 08/31/2021 14:44:45 - INFO - __main__ - Step 140476: {'lr': 5.09256183635734e-06, 'samples': 26971392, 'steps': 140475, 'loss/train': 0.4596703350543976} 08/31/2021 14:44:46 - INFO - __main__ - Step 140477: {'lr': 5.091496232419668e-06, 'samples': 26971584, 'steps': 140476, 'loss/train': 1.789170503616333} 08/31/2021 14:44:47 - INFO - __main__ - Step 140478: {'lr': 5.090430738833973e-06, 'samples': 26971776, 'steps': 140477, 'loss/train': 1.0779155492782593} 08/31/2021 14:44:47 - INFO - __main__ - Step 140479: {'lr': 5.089365355600756e-06, 'samples': 26971968, 'steps': 140478, 'loss/train': 1.0185414552688599} 08/31/2021 14:44:47 - INFO - __main__ - Step 140480: {'lr': 5.088300082720487e-06, 'samples': 26972160, 'steps': 140479, 'loss/train': 1.1758168935775757} 08/31/2021 14:44:48 - INFO - __main__ - Step 140481: {'lr': 5.087234920193667e-06, 'samples': 26972352, 'steps': 140480, 'loss/train': 1.009312391281128} 08/31/2021 14:44:49 - INFO - __main__ - Step 140482: {'lr': 5.0861698680207405e-06, 'samples': 26972544, 'steps': 140481, 'loss/train': 0.7999702095985413} 08/31/2021 14:44:49 - INFO - __main__ - Step 140483: {'lr': 5.0851049262022606e-06, 'samples': 26972736, 'steps': 140482, 'loss/train': 1.130928635597229} 08/31/2021 14:44:50 - INFO - __main__ - Step 140484: {'lr': 5.08404009473859e-06, 'samples': 26972928, 'steps': 140483, 'loss/train': 1.4917542934417725} 08/31/2021 14:44:50 - INFO - __main__ - Step 140485: {'lr': 5.082975373630283e-06, 'samples': 26973120, 'steps': 140484, 'loss/train': 1.1791125535964966} 08/31/2021 14:44:51 - INFO - __main__ - Step 140486: {'lr': 5.081910762877812e-06, 'samples': 26973312, 'steps': 140485, 'loss/train': 1.1971793174743652} 08/31/2021 14:44:52 - INFO - __main__ - Step 140487: {'lr': 5.0808462624816755e-06, 'samples': 26973504, 'steps': 140486, 'loss/train': 0.6412221789360046} 08/31/2021 14:44:53 - INFO - __main__ - Step 140488: {'lr': 5.0797818724422905e-06, 'samples': 26973696, 'steps': 140487, 'loss/train': 1.961761474609375} 08/31/2021 14:44:53 - INFO - __main__ - Step 140489: {'lr': 5.0787175927602125e-06, 'samples': 26973888, 'steps': 140488, 'loss/train': 1.144992470741272} 08/31/2021 14:44:53 - INFO - __main__ - Step 140490: {'lr': 5.0776534234358576e-06, 'samples': 26974080, 'steps': 140489, 'loss/train': 1.2156896591186523} 08/31/2021 14:44:54 - INFO - __main__ - Step 140491: {'lr': 5.076589364469752e-06, 'samples': 26974272, 'steps': 140490, 'loss/train': 0.653117835521698} 08/31/2021 14:44:56 - INFO - __main__ - Step 140492: {'lr': 5.075525415862342e-06, 'samples': 26974464, 'steps': 140491, 'loss/train': 0.5543687343597412} 08/31/2021 14:44:57 - INFO - __main__ - Step 140493: {'lr': 5.074461577614125e-06, 'samples': 26974656, 'steps': 140492, 'loss/train': 1.327839732170105} 08/31/2021 14:44:57 - INFO - __main__ - Step 140494: {'lr': 5.073397849725603e-06, 'samples': 26974848, 'steps': 140493, 'loss/train': 1.2909033298492432} 08/31/2021 14:44:57 - INFO - __main__ - Step 140495: {'lr': 5.07233423219719e-06, 'samples': 26975040, 'steps': 140494, 'loss/train': 0.7069305181503296} 08/31/2021 14:44:58 - INFO - __main__ - Step 140496: {'lr': 5.0712707250294145e-06, 'samples': 26975232, 'steps': 140495, 'loss/train': 1.859451413154602} 08/31/2021 14:44:58 - INFO - __main__ - Step 140497: {'lr': 5.070207328222748e-06, 'samples': 26975424, 'steps': 140496, 'loss/train': 0.25795307755470276} 08/31/2021 14:44:58 - INFO - __main__ - Step 140498: {'lr': 5.069144041777662e-06, 'samples': 26975616, 'steps': 140497, 'loss/train': 0.25829488039016724} 08/31/2021 14:45:00 - INFO - __main__ - Step 140499: {'lr': 5.068080865694658e-06, 'samples': 26975808, 'steps': 140498, 'loss/train': 0.24764356017112732} 08/31/2021 14:45:00 - INFO - __main__ - Step 140500: {'lr': 5.0670177999741775e-06, 'samples': 26976000, 'steps': 140499, 'loss/train': 0.7653399109840393} 08/31/2021 14:45:01 - INFO - __main__ - Step 140501: {'lr': 5.065954844616722e-06, 'samples': 26976192, 'steps': 140500, 'loss/train': 1.039675235748291} 08/31/2021 14:45:01 - INFO - __main__ - Step 140502: {'lr': 5.064891999622761e-06, 'samples': 26976384, 'steps': 140501, 'loss/train': 0.39682620763778687} 08/31/2021 14:45:01 - INFO - __main__ - Step 140503: {'lr': 5.063829264992797e-06, 'samples': 26976576, 'steps': 140502, 'loss/train': 1.2641377449035645} 08/31/2021 14:45:03 - INFO - __main__ - Step 140504: {'lr': 5.062766640727301e-06, 'samples': 26976768, 'steps': 140503, 'loss/train': 0.2073483020067215} 08/31/2021 14:45:03 - INFO - __main__ - Step 140505: {'lr': 5.061704126826744e-06, 'samples': 26976960, 'steps': 140504, 'loss/train': 1.1212621927261353} 08/31/2021 14:45:04 - INFO - __main__ - Step 140506: {'lr': 5.06064172329157e-06, 'samples': 26977152, 'steps': 140505, 'loss/train': 1.4151036739349365} 08/31/2021 14:45:04 - INFO - __main__ - Step 140507: {'lr': 5.059579430122307e-06, 'samples': 26977344, 'steps': 140506, 'loss/train': 0.7237140536308289} 08/31/2021 14:45:04 - INFO - __main__ - Step 140508: {'lr': 5.0585172473194275e-06, 'samples': 26977536, 'steps': 140507, 'loss/train': 1.4025715589523315} 08/31/2021 14:45:06 - INFO - __main__ - Step 140509: {'lr': 5.0574551748833746e-06, 'samples': 26977728, 'steps': 140508, 'loss/train': 1.0494937896728516} 08/31/2021 14:45:06 - INFO - __main__ - Step 140510: {'lr': 5.056393212814675e-06, 'samples': 26977920, 'steps': 140509, 'loss/train': 0.9375887513160706} 08/31/2021 14:45:07 - INFO - __main__ - Step 140511: {'lr': 5.055331361113774e-06, 'samples': 26978112, 'steps': 140510, 'loss/train': 0.47047266364097595} 08/31/2021 14:45:07 - INFO - __main__ - Step 140512: {'lr': 5.054269619781171e-06, 'samples': 26978304, 'steps': 140511, 'loss/train': 0.7831442356109619} 08/31/2021 14:45:07 - INFO - __main__ - Step 140513: {'lr': 5.053207988817338e-06, 'samples': 26978496, 'steps': 140512, 'loss/train': 0.6989448070526123} 08/31/2021 14:45:09 - INFO - __main__ - Step 140514: {'lr': 5.052146468222746e-06, 'samples': 26978688, 'steps': 140513, 'loss/train': 0.5668088793754578} 08/31/2021 14:45:09 - INFO - __main__ - Step 140515: {'lr': 5.051085057997868e-06, 'samples': 26978880, 'steps': 140514, 'loss/train': 1.1025574207305908} 08/31/2021 14:45:10 - INFO - __main__ - Step 140516: {'lr': 5.050023758143202e-06, 'samples': 26979072, 'steps': 140515, 'loss/train': 1.0158780813217163} 08/31/2021 14:45:10 - INFO - __main__ - Step 140517: {'lr': 5.048962568659221e-06, 'samples': 26979264, 'steps': 140516, 'loss/train': 0.7865222096443176} 08/31/2021 14:45:10 - INFO - __main__ - Step 140518: {'lr': 5.0479014895463695e-06, 'samples': 26979456, 'steps': 140517, 'loss/train': 1.0440932512283325} 08/31/2021 14:45:12 - INFO - __main__ - Step 140519: {'lr': 5.0468405208051736e-06, 'samples': 26979648, 'steps': 140518, 'loss/train': 0.5724754333496094} 08/31/2021 14:45:12 - INFO - __main__ - Step 140520: {'lr': 5.045779662436078e-06, 'samples': 26979840, 'steps': 140519, 'loss/train': 1.4857803583145142} 08/31/2021 14:45:13 - INFO - __main__ - Step 140521: {'lr': 5.044718914439583e-06, 'samples': 26980032, 'steps': 140520, 'loss/train': 1.190935492515564} 08/31/2021 14:45:13 - INFO - __main__ - Step 140522: {'lr': 5.04365827681616e-06, 'samples': 26980224, 'steps': 140521, 'loss/train': 1.1740188598632812} 08/31/2021 14:45:14 - INFO - __main__ - Step 140523: {'lr': 5.04259774956628e-06, 'samples': 26980416, 'steps': 140522, 'loss/train': 1.0993399620056152} 08/31/2021 14:45:14 - INFO - __main__ - Step 140524: {'lr': 5.041537332690443e-06, 'samples': 26980608, 'steps': 140523, 'loss/train': 0.9317432641983032} 08/31/2021 14:45:15 - INFO - __main__ - Step 140525: {'lr': 5.040477026189094e-06, 'samples': 26980800, 'steps': 140524, 'loss/train': 0.6558535099029541} 08/31/2021 14:45:16 - INFO - __main__ - Step 140526: {'lr': 5.039416830062732e-06, 'samples': 26980992, 'steps': 140525, 'loss/train': 1.4985687732696533} 08/31/2021 14:45:16 - INFO - __main__ - Step 140527: {'lr': 5.038356744311828e-06, 'samples': 26981184, 'steps': 140526, 'loss/train': 1.5887892246246338} 08/31/2021 14:45:17 - INFO - __main__ - Step 140528: {'lr': 5.037296768936855e-06, 'samples': 26981376, 'steps': 140527, 'loss/train': 0.8034023642539978} 08/31/2021 14:45:17 - INFO - __main__ - Step 140529: {'lr': 5.0362369039382845e-06, 'samples': 26981568, 'steps': 140528, 'loss/train': 0.9863035678863525} 08/31/2021 14:45:19 - INFO - __main__ - Step 140530: {'lr': 5.035177149316644e-06, 'samples': 26981760, 'steps': 140529, 'loss/train': 0.5623084902763367} 08/31/2021 14:45:20 - INFO - __main__ - Step 140531: {'lr': 5.034117505072349e-06, 'samples': 26981952, 'steps': 140530, 'loss/train': 0.7097702622413635} 08/31/2021 14:45:20 - INFO - __main__ - Step 140532: {'lr': 5.033057971205901e-06, 'samples': 26982144, 'steps': 140531, 'loss/train': 0.056381192058324814} 08/31/2021 14:45:21 - INFO - __main__ - Step 140533: {'lr': 5.03199854771777e-06, 'samples': 26982336, 'steps': 140532, 'loss/train': 0.052994225174188614} 08/31/2021 14:45:21 - INFO - __main__ - Step 140534: {'lr': 5.030939234608428e-06, 'samples': 26982528, 'steps': 140533, 'loss/train': 1.9342588186264038} 08/31/2021 14:45:21 - INFO - __main__ - Step 140535: {'lr': 5.029880031878404e-06, 'samples': 26982720, 'steps': 140534, 'loss/train': 1.0806101560592651} 08/31/2021 14:45:23 - INFO - __main__ - Step 140536: {'lr': 5.028820939528111e-06, 'samples': 26982912, 'steps': 140535, 'loss/train': 0.04818975180387497} 08/31/2021 14:45:23 - INFO - __main__ - Step 140537: {'lr': 5.027761957558053e-06, 'samples': 26983104, 'steps': 140536, 'loss/train': 1.288450002670288} 08/31/2021 14:45:24 - INFO - __main__ - Step 140538: {'lr': 5.026703085968698e-06, 'samples': 26983296, 'steps': 140537, 'loss/train': 0.8792682886123657} 08/31/2021 14:45:24 - INFO - __main__ - Step 140539: {'lr': 5.0256443247605476e-06, 'samples': 26983488, 'steps': 140538, 'loss/train': 0.5281175374984741} 08/31/2021 14:45:24 - INFO - __main__ - Step 140540: {'lr': 5.024585673934045e-06, 'samples': 26983680, 'steps': 140539, 'loss/train': 0.7668046355247498} 08/31/2021 14:45:26 - INFO - __main__ - Step 140541: {'lr': 5.023527133489691e-06, 'samples': 26983872, 'steps': 140540, 'loss/train': 1.02872633934021} 08/31/2021 14:45:26 - INFO - __main__ - Step 140542: {'lr': 5.022468703427957e-06, 'samples': 26984064, 'steps': 140541, 'loss/train': 0.7538052201271057} 08/31/2021 14:45:27 - INFO - __main__ - Step 140543: {'lr': 5.021410383749342e-06, 'samples': 26984256, 'steps': 140542, 'loss/train': 0.7568705677986145} 08/31/2021 14:45:27 - INFO - __main__ - Step 140544: {'lr': 5.020352174454263e-06, 'samples': 26984448, 'steps': 140543, 'loss/train': 0.9182514548301697} 08/31/2021 14:45:27 - INFO - __main__ - Step 140545: {'lr': 5.019294075543246e-06, 'samples': 26984640, 'steps': 140544, 'loss/train': 1.2799968719482422} 08/31/2021 14:45:29 - INFO - __main__ - Step 140546: {'lr': 5.018236087016764e-06, 'samples': 26984832, 'steps': 140545, 'loss/train': 1.4451990127563477} 08/31/2021 14:45:29 - INFO - __main__ - Step 140547: {'lr': 5.017178208875262e-06, 'samples': 26985024, 'steps': 140546, 'loss/train': 1.2260276079177856} 08/31/2021 14:45:30 - INFO - __main__ - Step 140548: {'lr': 5.016120441119265e-06, 'samples': 26985216, 'steps': 140547, 'loss/train': 0.6012617349624634} 08/31/2021 14:45:30 - INFO - __main__ - Step 140549: {'lr': 5.015062783749191e-06, 'samples': 26985408, 'steps': 140548, 'loss/train': 0.8952237963676453} 08/31/2021 14:45:30 - INFO - __main__ - Step 140550: {'lr': 5.0140052367655676e-06, 'samples': 26985600, 'steps': 140549, 'loss/train': 1.2118644714355469} 08/31/2021 14:45:32 - INFO - __main__ - Step 140551: {'lr': 5.012947800168866e-06, 'samples': 26985792, 'steps': 140550, 'loss/train': 0.988694965839386} 08/31/2021 14:45:32 - INFO - __main__ - Step 140552: {'lr': 5.01189047395953e-06, 'samples': 26985984, 'steps': 140551, 'loss/train': 1.1131576299667358} 08/31/2021 14:45:33 - INFO - __main__ - Step 140553: {'lr': 5.010833258138059e-06, 'samples': 26986176, 'steps': 140552, 'loss/train': 1.0013209581375122} 08/31/2021 14:45:33 - INFO - __main__ - Step 140554: {'lr': 5.009776152704926e-06, 'samples': 26986368, 'steps': 140553, 'loss/train': 0.7876563668251038} 08/31/2021 14:45:33 - INFO - __main__ - Step 140555: {'lr': 5.00871915766063e-06, 'samples': 26986560, 'steps': 140554, 'loss/train': 1.3095195293426514} 08/31/2021 14:45:35 - INFO - __main__ - Step 140556: {'lr': 5.007662273005586e-06, 'samples': 26986752, 'steps': 140555, 'loss/train': 0.8712872862815857} 08/31/2021 14:45:35 - INFO - __main__ - Step 140557: {'lr': 5.0066054987403516e-06, 'samples': 26986944, 'steps': 140556, 'loss/train': 0.41786614060401917} 08/31/2021 14:45:36 - INFO - __main__ - Step 140558: {'lr': 5.005548834865342e-06, 'samples': 26987136, 'steps': 140557, 'loss/train': 1.058273434638977} 08/31/2021 14:45:36 - INFO - __main__ - Step 140559: {'lr': 5.004492281381057e-06, 'samples': 26987328, 'steps': 140558, 'loss/train': 0.861323893070221} 08/31/2021 14:45:36 - INFO - __main__ - Step 140560: {'lr': 5.0034358382879395e-06, 'samples': 26987520, 'steps': 140559, 'loss/train': 1.2694244384765625} 08/31/2021 14:45:37 - INFO - __main__ - Step 140561: {'lr': 5.002379505586518e-06, 'samples': 26987712, 'steps': 140560, 'loss/train': 0.8476341366767883} 08/31/2021 14:45:38 - INFO - __main__ - Step 140562: {'lr': 5.001323283277237e-06, 'samples': 26987904, 'steps': 140561, 'loss/train': 0.8888031244277954} 08/31/2021 14:45:39 - INFO - __main__ - Step 140563: {'lr': 5.000267171360595e-06, 'samples': 26988096, 'steps': 140562, 'loss/train': 1.0940848588943481} 08/31/2021 14:45:39 - INFO - __main__ - Step 140564: {'lr': 4.999211169837037e-06, 'samples': 26988288, 'steps': 140563, 'loss/train': 0.826726496219635} 08/31/2021 14:45:39 - INFO - __main__ - Step 140565: {'lr': 4.998155278707034e-06, 'samples': 26988480, 'steps': 140564, 'loss/train': 0.5362545847892761} 08/31/2021 14:45:40 - INFO - __main__ - Step 140566: {'lr': 4.997099497971114e-06, 'samples': 26988672, 'steps': 140565, 'loss/train': 0.7870513796806335} 08/31/2021 14:45:41 - INFO - __main__ - Step 140567: {'lr': 4.996043827629693e-06, 'samples': 26988864, 'steps': 140566, 'loss/train': 0.9974141120910645} 08/31/2021 14:45:42 - INFO - __main__ - Step 140568: {'lr': 4.9949882676832984e-06, 'samples': 26989056, 'steps': 140567, 'loss/train': 1.4422389268875122} 08/31/2021 14:45:42 - INFO - __main__ - Step 140569: {'lr': 4.993932818132374e-06, 'samples': 26989248, 'steps': 140568, 'loss/train': 0.9703400731086731} 08/31/2021 14:45:42 - INFO - __main__ - Step 140570: {'lr': 4.99287747897742e-06, 'samples': 26989440, 'steps': 140569, 'loss/train': 1.1384209394454956} 08/31/2021 14:45:43 - INFO - __main__ - Step 140571: {'lr': 4.99182225021888e-06, 'samples': 26989632, 'steps': 140570, 'loss/train': 1.2211682796478271} 08/31/2021 14:45:44 - INFO - __main__ - Step 140572: {'lr': 4.990767131857227e-06, 'samples': 26989824, 'steps': 140571, 'loss/train': 0.12549878656864166} 08/31/2021 14:45:45 - INFO - __main__ - Step 140573: {'lr': 4.989712123892959e-06, 'samples': 26990016, 'steps': 140572, 'loss/train': 1.5157912969589233} 08/31/2021 14:45:45 - INFO - __main__ - Step 140574: {'lr': 4.988657226326576e-06, 'samples': 26990208, 'steps': 140573, 'loss/train': 0.7164226174354553} 08/31/2021 14:45:46 - INFO - __main__ - Step 140575: {'lr': 4.9876024391584955e-06, 'samples': 26990400, 'steps': 140574, 'loss/train': 0.893696129322052} 08/31/2021 14:45:46 - INFO - __main__ - Step 140576: {'lr': 4.986547762389215e-06, 'samples': 26990592, 'steps': 140575, 'loss/train': 1.032768964767456} 08/31/2021 14:45:47 - INFO - __main__ - Step 140577: {'lr': 4.985493196019236e-06, 'samples': 26990784, 'steps': 140576, 'loss/train': 1.4522801637649536} 08/31/2021 14:45:48 - INFO - __main__ - Step 140578: {'lr': 4.984438740049002e-06, 'samples': 26990976, 'steps': 140577, 'loss/train': 0.6804813146591187} 08/31/2021 14:45:48 - INFO - __main__ - Step 140579: {'lr': 4.983384394478985e-06, 'samples': 26991168, 'steps': 140578, 'loss/train': 1.1043528318405151} 08/31/2021 14:45:49 - INFO - __main__ - Step 140580: {'lr': 4.982330159309684e-06, 'samples': 26991360, 'steps': 140579, 'loss/train': 0.9707940220832825} 08/31/2021 14:45:49 - INFO - __main__ - Step 140581: {'lr': 4.981276034541571e-06, 'samples': 26991552, 'steps': 140580, 'loss/train': 0.29152601957321167} 08/31/2021 14:45:52 - INFO - __main__ - Step 140582: {'lr': 4.980222020175118e-06, 'samples': 26991744, 'steps': 140581, 'loss/train': 1.235864281654358} 08/31/2021 14:45:52 - INFO - __main__ - Step 140583: {'lr': 4.9791681162108245e-06, 'samples': 26991936, 'steps': 140582, 'loss/train': 1.271884799003601} 08/31/2021 14:45:52 - INFO - __main__ - Step 140584: {'lr': 4.9781143226490795e-06, 'samples': 26992128, 'steps': 140583, 'loss/train': 1.2576624155044556} 08/31/2021 14:45:53 - INFO - __main__ - Step 140585: {'lr': 4.977060639490438e-06, 'samples': 26992320, 'steps': 140584, 'loss/train': 0.047634195536375046} 08/31/2021 14:45:53 - INFO - __main__ - Step 140586: {'lr': 4.9760070667353714e-06, 'samples': 26992512, 'steps': 140585, 'loss/train': 0.9121295809745789} 08/31/2021 14:45:53 - INFO - __main__ - Step 140587: {'lr': 4.974953604384297e-06, 'samples': 26992704, 'steps': 140586, 'loss/train': 1.171875} 08/31/2021 14:45:55 - INFO - __main__ - Step 140588: {'lr': 4.973900252437768e-06, 'samples': 26992896, 'steps': 140587, 'loss/train': 1.023184895515442} 08/31/2021 14:45:55 - INFO - __main__ - Step 140589: {'lr': 4.972847010896175e-06, 'samples': 26993088, 'steps': 140588, 'loss/train': 0.4725334346294403} 08/31/2021 14:45:56 - INFO - __main__ - Step 140590: {'lr': 4.971793879760072e-06, 'samples': 26993280, 'steps': 140589, 'loss/train': 0.22225849330425262} 08/31/2021 14:45:56 - INFO - __main__ - Step 140591: {'lr': 4.970740859029876e-06, 'samples': 26993472, 'steps': 140590, 'loss/train': 0.9253738522529602} 08/31/2021 14:45:56 - INFO - __main__ - Step 140592: {'lr': 4.969687948706087e-06, 'samples': 26993664, 'steps': 140591, 'loss/train': 0.8560706973075867} 08/31/2021 14:45:58 - INFO - __main__ - Step 140593: {'lr': 4.968635148789175e-06, 'samples': 26993856, 'steps': 140592, 'loss/train': 1.2312471866607666} 08/31/2021 14:45:58 - INFO - __main__ - Step 140594: {'lr': 4.96758245927964e-06, 'samples': 26994048, 'steps': 140593, 'loss/train': 0.8792528510093689} 08/31/2021 14:45:59 - INFO - __main__ - Step 140595: {'lr': 4.9665298801779e-06, 'samples': 26994240, 'steps': 140594, 'loss/train': 1.5180304050445557} 08/31/2021 14:45:59 - INFO - __main__ - Step 140596: {'lr': 4.965477411484481e-06, 'samples': 26994432, 'steps': 140595, 'loss/train': 0.6611789464950562} 08/31/2021 14:45:59 - INFO - __main__ - Step 140597: {'lr': 4.964425053199828e-06, 'samples': 26994624, 'steps': 140596, 'loss/train': 1.0782650709152222} 08/31/2021 14:46:01 - INFO - __main__ - Step 140598: {'lr': 4.96337280532444e-06, 'samples': 26994816, 'steps': 140597, 'loss/train': 1.5487620830535889} 08/31/2021 14:46:01 - INFO - __main__ - Step 140599: {'lr': 4.9623206678587606e-06, 'samples': 26995008, 'steps': 140598, 'loss/train': 0.8634507656097412} 08/31/2021 14:46:02 - INFO - __main__ - Step 140600: {'lr': 4.9612686408032625e-06, 'samples': 26995200, 'steps': 140599, 'loss/train': 0.9742656350135803} 08/31/2021 14:46:02 - INFO - __main__ - Step 140601: {'lr': 4.960216724158445e-06, 'samples': 26995392, 'steps': 140600, 'loss/train': 0.8427847623825073} 08/31/2021 14:46:02 - INFO - __main__ - Step 140602: {'lr': 4.95916491792478e-06, 'samples': 26995584, 'steps': 140601, 'loss/train': 1.1963001489639282} 08/31/2021 14:46:04 - INFO - __main__ - Step 140603: {'lr': 4.958113222102739e-06, 'samples': 26995776, 'steps': 140602, 'loss/train': 0.4716929793357849} 08/31/2021 14:46:04 - INFO - __main__ - Step 140604: {'lr': 4.957061636692767e-06, 'samples': 26995968, 'steps': 140603, 'loss/train': 1.197985053062439} 08/31/2021 14:46:05 - INFO - __main__ - Step 140605: {'lr': 4.95601016169539e-06, 'samples': 26996160, 'steps': 140604, 'loss/train': 0.5484741926193237} 08/31/2021 14:46:05 - INFO - __main__ - Step 140606: {'lr': 4.954958797111025e-06, 'samples': 26996352, 'steps': 140605, 'loss/train': 1.0567137002944946} 08/31/2021 14:46:05 - INFO - __main__ - Step 140607: {'lr': 4.9539075429402e-06, 'samples': 26996544, 'steps': 140606, 'loss/train': 0.40196913480758667} 08/31/2021 14:46:07 - INFO - __main__ - Step 140608: {'lr': 4.9528563991833585e-06, 'samples': 26996736, 'steps': 140607, 'loss/train': 0.27310284972190857} 08/31/2021 14:46:07 - INFO - __main__ - Step 140609: {'lr': 4.951805365840972e-06, 'samples': 26996928, 'steps': 140608, 'loss/train': 0.9544349312782288} 08/31/2021 14:46:08 - INFO - __main__ - Step 140610: {'lr': 4.950754442913541e-06, 'samples': 26997120, 'steps': 140609, 'loss/train': 1.2063645124435425} 08/31/2021 14:46:08 - INFO - __main__ - Step 140611: {'lr': 4.949703630401509e-06, 'samples': 26997312, 'steps': 140610, 'loss/train': 0.36240509152412415} 08/31/2021 14:46:08 - INFO - __main__ - Step 140612: {'lr': 4.948652928305347e-06, 'samples': 26997504, 'steps': 140611, 'loss/train': 1.9868438243865967} 08/31/2021 14:46:10 - INFO - __main__ - Step 140613: {'lr': 4.947602336625529e-06, 'samples': 26997696, 'steps': 140612, 'loss/train': 0.9238274097442627} 08/31/2021 14:46:10 - INFO - __main__ - Step 140614: {'lr': 4.946551855362552e-06, 'samples': 26997888, 'steps': 140613, 'loss/train': 0.7698493003845215} 08/31/2021 14:46:11 - INFO - __main__ - Step 140615: {'lr': 4.94550148451689e-06, 'samples': 26998080, 'steps': 140614, 'loss/train': 1.0220253467559814} 08/31/2021 14:46:11 - INFO - __main__ - Step 140616: {'lr': 4.944451224088986e-06, 'samples': 26998272, 'steps': 140615, 'loss/train': 1.322442650794983} 08/31/2021 14:46:11 - INFO - __main__ - Step 140617: {'lr': 4.94340107407934e-06, 'samples': 26998464, 'steps': 140616, 'loss/train': 1.1174975633621216} 08/31/2021 14:46:13 - INFO - __main__ - Step 140618: {'lr': 4.942351034488424e-06, 'samples': 26998656, 'steps': 140617, 'loss/train': 1.0004068613052368} 08/31/2021 14:46:13 - INFO - __main__ - Step 140619: {'lr': 4.941301105316682e-06, 'samples': 26998848, 'steps': 140618, 'loss/train': 1.555614948272705} 08/31/2021 14:46:14 - INFO - __main__ - Step 140620: {'lr': 4.940251286564612e-06, 'samples': 26999040, 'steps': 140619, 'loss/train': 0.0328548289835453} 08/31/2021 14:46:14 - INFO - __main__ - Step 140621: {'lr': 4.939201578232716e-06, 'samples': 26999232, 'steps': 140620, 'loss/train': 1.4617652893066406} 08/31/2021 14:46:14 - INFO - __main__ - Step 140622: {'lr': 4.9381519803213815e-06, 'samples': 26999424, 'steps': 140621, 'loss/train': 0.7125672698020935} 08/31/2021 14:46:16 - INFO - __main__ - Step 140623: {'lr': 4.937102492831164e-06, 'samples': 26999616, 'steps': 140622, 'loss/train': 0.8058784008026123} 08/31/2021 14:46:16 - INFO - __main__ - Step 140624: {'lr': 4.936053115762534e-06, 'samples': 26999808, 'steps': 140623, 'loss/train': 0.14897610247135162} 08/31/2021 14:46:17 - INFO - __main__ - Step 140625: {'lr': 4.93500384911591e-06, 'samples': 27000000, 'steps': 140624, 'loss/train': 1.5205814838409424} 08/31/2021 14:46:17 - INFO - __main__ - Step 140626: {'lr': 4.93395469289179e-06, 'samples': 27000192, 'steps': 140625, 'loss/train': 1.028693437576294} 08/31/2021 14:46:17 - INFO - __main__ - Step 140627: {'lr': 4.932905647090647e-06, 'samples': 27000384, 'steps': 140626, 'loss/train': 1.0815759897232056} 08/31/2021 14:46:18 - INFO - __main__ - Step 140628: {'lr': 4.9318567117129505e-06, 'samples': 27000576, 'steps': 140627, 'loss/train': 0.9341863393783569} 08/31/2021 14:46:19 - INFO - __main__ - Step 140629: {'lr': 4.930807886759176e-06, 'samples': 27000768, 'steps': 140628, 'loss/train': 1.2471600770950317} 08/31/2021 14:46:20 - INFO - __main__ - Step 140630: {'lr': 4.92975917222982e-06, 'samples': 27000960, 'steps': 140629, 'loss/train': 0.5112261176109314} 08/31/2021 14:46:20 - INFO - __main__ - Step 140631: {'lr': 4.9287105681253e-06, 'samples': 27001152, 'steps': 140630, 'loss/train': 0.8957939743995667} 08/31/2021 14:46:20 - INFO - __main__ - Step 140632: {'lr': 4.927662074446143e-06, 'samples': 27001344, 'steps': 140631, 'loss/train': 2.04260516166687} 08/31/2021 14:46:21 - INFO - __main__ - Step 140633: {'lr': 4.926613691192794e-06, 'samples': 27001536, 'steps': 140632, 'loss/train': 1.1456689834594727} 08/31/2021 14:46:22 - INFO - __main__ - Step 140634: {'lr': 4.925565418365752e-06, 'samples': 27001728, 'steps': 140633, 'loss/train': 0.6323106288909912} 08/31/2021 14:46:23 - INFO - __main__ - Step 140635: {'lr': 4.9245172559654325e-06, 'samples': 27001920, 'steps': 140634, 'loss/train': 0.8208972811698914} 08/31/2021 14:46:23 - INFO - __main__ - Step 140636: {'lr': 4.923469203992365e-06, 'samples': 27002112, 'steps': 140635, 'loss/train': 0.37303537130355835} 08/31/2021 14:46:23 - INFO - __main__ - Step 140637: {'lr': 4.922421262447019e-06, 'samples': 27002304, 'steps': 140636, 'loss/train': 0.40270912647247314} 08/31/2021 14:46:24 - INFO - __main__ - Step 140638: {'lr': 4.921373431329812e-06, 'samples': 27002496, 'steps': 140637, 'loss/train': 1.3261783123016357} 08/31/2021 14:46:26 - INFO - __main__ - Step 140639: {'lr': 4.920325710641271e-06, 'samples': 27002688, 'steps': 140638, 'loss/train': 1.033493995666504} 08/31/2021 14:46:26 - INFO - __main__ - Step 140640: {'lr': 4.919278100381841e-06, 'samples': 27002880, 'steps': 140639, 'loss/train': 0.5361672639846802} 08/31/2021 14:46:27 - INFO - __main__ - Step 140641: {'lr': 4.9182306005520205e-06, 'samples': 27003072, 'steps': 140640, 'loss/train': 1.0948415994644165} 08/31/2021 14:46:27 - INFO - __main__ - Step 140642: {'lr': 4.9171832111522545e-06, 'samples': 27003264, 'steps': 140641, 'loss/train': 1.071539282798767} 08/31/2021 14:46:27 - INFO - __main__ - Step 140643: {'lr': 4.916135932183013e-06, 'samples': 27003456, 'steps': 140642, 'loss/train': 0.8604350090026855} 08/31/2021 14:46:29 - INFO - __main__ - Step 140644: {'lr': 4.9150887636447705e-06, 'samples': 27003648, 'steps': 140643, 'loss/train': 0.9068871140480042} 08/31/2021 14:46:29 - INFO - __main__ - Step 140645: {'lr': 4.914041705538025e-06, 'samples': 27003840, 'steps': 140644, 'loss/train': 1.3690634965896606} 08/31/2021 14:46:30 - INFO - __main__ - Step 140646: {'lr': 4.91299475786322e-06, 'samples': 27004032, 'steps': 140645, 'loss/train': 1.040719747543335} 08/31/2021 14:46:30 - INFO - __main__ - Step 140647: {'lr': 4.911947920620857e-06, 'samples': 27004224, 'steps': 140646, 'loss/train': 0.5151951313018799} 08/31/2021 14:46:30 - INFO - __main__ - Step 140648: {'lr': 4.910901193811351e-06, 'samples': 27004416, 'steps': 140647, 'loss/train': 1.3309797048568726} 08/31/2021 14:46:32 - INFO - __main__ - Step 140649: {'lr': 4.909854577435257e-06, 'samples': 27004608, 'steps': 140648, 'loss/train': 0.22550636529922485} 08/31/2021 14:46:32 - INFO - __main__ - Step 140650: {'lr': 4.908808071492965e-06, 'samples': 27004800, 'steps': 140649, 'loss/train': 0.5773230791091919} 08/31/2021 14:46:33 - INFO - __main__ - Step 140651: {'lr': 4.907761675985029e-06, 'samples': 27004992, 'steps': 140650, 'loss/train': 0.2782823145389557} 08/31/2021 14:46:33 - INFO - __main__ - Step 140652: {'lr': 4.906715390911837e-06, 'samples': 27005184, 'steps': 140651, 'loss/train': 1.3079737424850464} 08/31/2021 14:46:33 - INFO - __main__ - Step 140653: {'lr': 4.905669216273889e-06, 'samples': 27005376, 'steps': 140652, 'loss/train': 0.6486214399337769} 08/31/2021 14:46:34 - INFO - __main__ - Step 140654: {'lr': 4.904623152071686e-06, 'samples': 27005568, 'steps': 140653, 'loss/train': 1.4711922407150269} 08/31/2021 14:46:35 - INFO - __main__ - Step 140655: {'lr': 4.90357719830567e-06, 'samples': 27005760, 'steps': 140654, 'loss/train': 0.8543541431427002} 08/31/2021 14:46:36 - INFO - __main__ - Step 140656: {'lr': 4.902531354976314e-06, 'samples': 27005952, 'steps': 140655, 'loss/train': 1.0626368522644043} 08/31/2021 14:46:36 - INFO - __main__ - Step 140657: {'lr': 4.90148562208409e-06, 'samples': 27006144, 'steps': 140656, 'loss/train': 1.2175241708755493} 08/31/2021 14:46:36 - INFO - __main__ - Step 140658: {'lr': 4.900439999629469e-06, 'samples': 27006336, 'steps': 140657, 'loss/train': 1.0450260639190674} 08/31/2021 14:46:37 - INFO - __main__ - Step 140659: {'lr': 4.899394487612951e-06, 'samples': 27006528, 'steps': 140658, 'loss/train': 1.0050474405288696} 08/31/2021 14:46:39 - INFO - __main__ - Step 140660: {'lr': 4.898349086034981e-06, 'samples': 27006720, 'steps': 140659, 'loss/train': 0.3540209233760834} 08/31/2021 14:46:39 - INFO - __main__ - Step 140661: {'lr': 4.89730379489603e-06, 'samples': 27006912, 'steps': 140660, 'loss/train': 0.08322616666555405} 08/31/2021 14:46:39 - INFO - __main__ - Step 140662: {'lr': 4.896258614196569e-06, 'samples': 27007104, 'steps': 140661, 'loss/train': 0.4252365231513977} 08/31/2021 14:46:40 - INFO - __main__ - Step 140663: {'lr': 4.8952135439370715e-06, 'samples': 27007296, 'steps': 140662, 'loss/train': 0.05198923870921135} 08/31/2021 14:46:40 - INFO - __main__ - Step 140664: {'lr': 4.894168584118009e-06, 'samples': 27007488, 'steps': 140663, 'loss/train': 0.017384670674800873} 08/31/2021 14:46:40 - INFO - __main__ - Step 140665: {'lr': 4.893123734739852e-06, 'samples': 27007680, 'steps': 140664, 'loss/train': 1.0962048768997192} 08/31/2021 14:46:42 - INFO - __main__ - Step 140666: {'lr': 4.892078995803073e-06, 'samples': 27007872, 'steps': 140665, 'loss/train': 0.26890209317207336} 08/31/2021 14:46:42 - INFO - __main__ - Step 140667: {'lr': 4.891034367308145e-06, 'samples': 27008064, 'steps': 140666, 'loss/train': 1.0788630247116089} 08/31/2021 14:46:43 - INFO - __main__ - Step 140668: {'lr': 4.8899898492555106e-06, 'samples': 27008256, 'steps': 140667, 'loss/train': 1.3567838668823242} 08/31/2021 14:46:43 - INFO - __main__ - Step 140669: {'lr': 4.888945441645698e-06, 'samples': 27008448, 'steps': 140668, 'loss/train': 1.297365665435791} 08/31/2021 14:46:43 - INFO - __main__ - Step 140670: {'lr': 4.8879011444791235e-06, 'samples': 27008640, 'steps': 140669, 'loss/train': 0.3105684816837311} 08/31/2021 14:46:45 - INFO - __main__ - Step 140671: {'lr': 4.886856957756286e-06, 'samples': 27008832, 'steps': 140670, 'loss/train': 0.5502398610115051} 08/31/2021 14:46:46 - INFO - __main__ - Step 140672: {'lr': 4.88581288147763e-06, 'samples': 27009024, 'steps': 140671, 'loss/train': 1.078534483909607} 08/31/2021 14:46:46 - INFO - __main__ - Step 140673: {'lr': 4.8847689156436555e-06, 'samples': 27009216, 'steps': 140672, 'loss/train': 0.24840208888053894} 08/31/2021 14:46:46 - INFO - __main__ - Step 140674: {'lr': 4.883725060254834e-06, 'samples': 27009408, 'steps': 140673, 'loss/train': 0.57998126745224} 08/31/2021 14:46:47 - INFO - __main__ - Step 140675: {'lr': 4.88268131531161e-06, 'samples': 27009600, 'steps': 140674, 'loss/train': 0.9249763488769531} 08/31/2021 14:46:47 - INFO - __main__ - Step 140676: {'lr': 4.881637680814483e-06, 'samples': 27009792, 'steps': 140675, 'loss/train': 1.2169189453125} 08/31/2021 14:46:49 - INFO - __main__ - Step 140677: {'lr': 4.880594156763896e-06, 'samples': 27009984, 'steps': 140676, 'loss/train': 1.3986657857894897} 08/31/2021 14:46:49 - INFO - __main__ - Step 140678: {'lr': 4.879550743160349e-06, 'samples': 27010176, 'steps': 140677, 'loss/train': 0.605204164981842} 08/31/2021 14:46:49 - INFO - __main__ - Step 140679: {'lr': 4.8785074400042596e-06, 'samples': 27010368, 'steps': 140678, 'loss/train': 1.4887285232543945} 08/31/2021 14:46:50 - INFO - __main__ - Step 140680: {'lr': 4.877464247296154e-06, 'samples': 27010560, 'steps': 140679, 'loss/train': 1.413109302520752} 08/31/2021 14:46:52 - INFO - __main__ - Step 140681: {'lr': 4.876421165036477e-06, 'samples': 27010752, 'steps': 140680, 'loss/train': 0.7133712768554688} 08/31/2021 14:46:52 - INFO - __main__ - Step 140682: {'lr': 4.8753781932256995e-06, 'samples': 27010944, 'steps': 140681, 'loss/train': 0.9523550271987915} 08/31/2021 14:46:53 - INFO - __main__ - Step 140683: {'lr': 4.874335331864293e-06, 'samples': 27011136, 'steps': 140682, 'loss/train': 1.1661635637283325} 08/31/2021 14:46:53 - INFO - __main__ - Step 140684: {'lr': 4.873292580952732e-06, 'samples': 27011328, 'steps': 140683, 'loss/train': 0.5052580237388611} 08/31/2021 14:46:53 - INFO - __main__ - Step 140685: {'lr': 4.872249940491486e-06, 'samples': 27011520, 'steps': 140684, 'loss/train': 1.0782095193862915} 08/31/2021 14:46:54 - INFO - __main__ - Step 140686: {'lr': 4.871207410481027e-06, 'samples': 27011712, 'steps': 140685, 'loss/train': 0.9171977639198303} 08/31/2021 14:46:56 - INFO - __main__ - Step 140687: {'lr': 4.8701649909217995e-06, 'samples': 27011904, 'steps': 140686, 'loss/train': 1.0771117210388184} 08/31/2021 14:46:57 - INFO - __main__ - Step 140688: {'lr': 4.869122681814303e-06, 'samples': 27012096, 'steps': 140687, 'loss/train': 0.5876885652542114} 08/31/2021 14:46:57 - INFO - __main__ - Step 140689: {'lr': 4.86808048315901e-06, 'samples': 27012288, 'steps': 140688, 'loss/train': 0.3614867925643921} 08/31/2021 14:46:57 - INFO - __main__ - Step 140690: {'lr': 4.867038394956363e-06, 'samples': 27012480, 'steps': 140689, 'loss/train': 1.1314234733581543} 08/31/2021 14:46:58 - INFO - __main__ - Step 140691: {'lr': 4.865996417206864e-06, 'samples': 27012672, 'steps': 140690, 'loss/train': 0.7759506106376648} 08/31/2021 14:46:59 - INFO - __main__ - Step 140692: {'lr': 4.8649545499109545e-06, 'samples': 27012864, 'steps': 140691, 'loss/train': 1.1973880529403687} 08/31/2021 14:47:00 - INFO - __main__ - Step 140693: {'lr': 4.863912793069109e-06, 'samples': 27013056, 'steps': 140692, 'loss/train': 0.6473709940910339} 08/31/2021 14:47:00 - INFO - __main__ - Step 140694: {'lr': 4.862871146681797e-06, 'samples': 27013248, 'steps': 140693, 'loss/train': 0.4162827432155609} 08/31/2021 14:47:01 - INFO - __main__ - Step 140695: {'lr': 4.8618296107494906e-06, 'samples': 27013440, 'steps': 140694, 'loss/train': 0.9820024967193604} 08/31/2021 14:47:01 - INFO - __main__ - Step 140696: {'lr': 4.860788185272663e-06, 'samples': 27013632, 'steps': 140695, 'loss/train': 0.04597680643200874} 08/31/2021 14:47:03 - INFO - __main__ - Step 140697: {'lr': 4.859746870251786e-06, 'samples': 27013824, 'steps': 140696, 'loss/train': 1.1464459896087646} 08/31/2021 14:47:03 - INFO - __main__ - Step 140698: {'lr': 4.858705665687329e-06, 'samples': 27014016, 'steps': 140697, 'loss/train': 0.875677764415741} 08/31/2021 14:47:04 - INFO - __main__ - Step 140699: {'lr': 4.8576645715797394e-06, 'samples': 27014208, 'steps': 140698, 'loss/train': 0.6394397616386414} 08/31/2021 14:47:04 - INFO - __main__ - Step 140700: {'lr': 4.856623587929515e-06, 'samples': 27014400, 'steps': 140699, 'loss/train': 0.29722994565963745} 08/31/2021 14:47:05 - INFO - __main__ - Step 140701: {'lr': 4.855582714737128e-06, 'samples': 27014592, 'steps': 140700, 'loss/train': 0.11407126486301422} 08/31/2021 14:47:06 - INFO - __main__ - Step 140702: {'lr': 4.854541952003022e-06, 'samples': 27014784, 'steps': 140701, 'loss/train': 0.8344001770019531} 08/31/2021 14:47:06 - INFO - __main__ - Step 140703: {'lr': 4.85350129972767e-06, 'samples': 27014976, 'steps': 140702, 'loss/train': 0.8440304398536682} 08/31/2021 14:47:07 - INFO - __main__ - Step 140704: {'lr': 4.85246075791157e-06, 'samples': 27015168, 'steps': 140703, 'loss/train': 0.6153385639190674} 08/31/2021 14:47:07 - INFO - __main__ - Step 140705: {'lr': 4.8514203265551395e-06, 'samples': 27015360, 'steps': 140704, 'loss/train': 0.6856902241706848} 08/31/2021 14:47:08 - INFO - __main__ - Step 140706: {'lr': 4.850380005658878e-06, 'samples': 27015552, 'steps': 140705, 'loss/train': 1.18822181224823} 08/31/2021 14:47:09 - INFO - __main__ - Step 140707: {'lr': 4.849339795223257e-06, 'samples': 27015744, 'steps': 140706, 'loss/train': 1.063848853111267} 08/31/2021 14:47:10 - INFO - __main__ - Step 140708: {'lr': 4.848299695248748e-06, 'samples': 27015936, 'steps': 140707, 'loss/train': 1.0688210725784302} 08/31/2021 14:47:10 - INFO - __main__ - Step 140709: {'lr': 4.8472597057357955e-06, 'samples': 27016128, 'steps': 140708, 'loss/train': 0.025593075901269913} 08/31/2021 14:47:11 - INFO - __main__ - Step 140710: {'lr': 4.8462198266849e-06, 'samples': 27016320, 'steps': 140709, 'loss/train': 0.07411929965019226} 08/31/2021 14:47:11 - INFO - __main__ - Step 140711: {'lr': 4.845180058096504e-06, 'samples': 27016512, 'steps': 140710, 'loss/train': 1.2117345333099365} 08/31/2021 14:47:11 - INFO - __main__ - Step 140712: {'lr': 4.8441403999711085e-06, 'samples': 27016704, 'steps': 140711, 'loss/train': 0.9257211685180664} 08/31/2021 14:47:13 - INFO - __main__ - Step 140713: {'lr': 4.843100852309157e-06, 'samples': 27016896, 'steps': 140712, 'loss/train': 0.7678757905960083} 08/31/2021 14:47:14 - INFO - __main__ - Step 140714: {'lr': 4.842061415111093e-06, 'samples': 27017088, 'steps': 140713, 'loss/train': 1.2297444343566895} 08/31/2021 14:47:14 - INFO - __main__ - Step 140715: {'lr': 4.841022088377445e-06, 'samples': 27017280, 'steps': 140714, 'loss/train': 2.0109636783599854} 08/31/2021 14:47:14 - INFO - __main__ - Step 140716: {'lr': 4.839982872108628e-06, 'samples': 27017472, 'steps': 140715, 'loss/train': 0.023668767884373665} 08/31/2021 14:47:15 - INFO - __main__ - Step 140717: {'lr': 4.838943766305143e-06, 'samples': 27017664, 'steps': 140716, 'loss/train': 1.237769603729248} 08/31/2021 14:47:16 - INFO - __main__ - Step 140718: {'lr': 4.837904770967461e-06, 'samples': 27017856, 'steps': 140717, 'loss/train': 0.03807365521788597} 08/31/2021 14:47:17 - INFO - __main__ - Step 140719: {'lr': 4.836865886095998e-06, 'samples': 27018048, 'steps': 140718, 'loss/train': 0.3136603534221649} 08/31/2021 14:47:17 - INFO - __main__ - Step 140720: {'lr': 4.835827111691282e-06, 'samples': 27018240, 'steps': 140719, 'loss/train': 1.287680745124817} 08/31/2021 14:47:18 - INFO - __main__ - Step 140721: {'lr': 4.834788447753758e-06, 'samples': 27018432, 'steps': 140720, 'loss/train': 0.9872292876243591} 08/31/2021 14:47:18 - INFO - __main__ - Step 140722: {'lr': 4.833749894283896e-06, 'samples': 27018624, 'steps': 140721, 'loss/train': 0.8221310973167419} 08/31/2021 14:47:19 - INFO - __main__ - Step 140723: {'lr': 4.832711451282168e-06, 'samples': 27018816, 'steps': 140722, 'loss/train': 1.0690057277679443} 08/31/2021 14:47:20 - INFO - __main__ - Step 140724: {'lr': 4.831673118749019e-06, 'samples': 27019008, 'steps': 140723, 'loss/train': 0.8606598973274231} 08/31/2021 14:47:20 - INFO - __main__ - Step 140725: {'lr': 4.830634896684949e-06, 'samples': 27019200, 'steps': 140724, 'loss/train': 1.0792253017425537} 08/31/2021 14:47:21 - INFO - __main__ - Step 140726: {'lr': 4.829596785090401e-06, 'samples': 27019392, 'steps': 140725, 'loss/train': 0.2580859661102295} 08/31/2021 14:47:21 - INFO - __main__ - Step 140727: {'lr': 4.828558783965875e-06, 'samples': 27019584, 'steps': 140726, 'loss/train': 1.2458176612854004} 08/31/2021 14:47:23 - INFO - __main__ - Step 140728: {'lr': 4.827520893311788e-06, 'samples': 27019776, 'steps': 140727, 'loss/train': 1.2895928621292114} 08/31/2021 14:47:23 - INFO - __main__ - Step 140729: {'lr': 4.8264831131286655e-06, 'samples': 27019968, 'steps': 140728, 'loss/train': 0.97603839635849} 08/31/2021 14:47:23 - INFO - __main__ - Step 140730: {'lr': 4.825445443416954e-06, 'samples': 27020160, 'steps': 140729, 'loss/train': 0.03034619428217411} 08/31/2021 14:47:24 - INFO - __main__ - Step 140731: {'lr': 4.824407884177095e-06, 'samples': 27020352, 'steps': 140730, 'loss/train': 1.0672937631607056} 08/31/2021 14:47:24 - INFO - __main__ - Step 140732: {'lr': 4.823370435409563e-06, 'samples': 27020544, 'steps': 140731, 'loss/train': 1.2246869802474976} 08/31/2021 14:47:24 - INFO - __main__ - Step 140733: {'lr': 4.822333097114856e-06, 'samples': 27020736, 'steps': 140732, 'loss/train': 1.2524292469024658} 08/31/2021 14:47:26 - INFO - __main__ - Step 140734: {'lr': 4.82129586929339e-06, 'samples': 27020928, 'steps': 140733, 'loss/train': 0.2640950679779053} 08/31/2021 14:47:26 - INFO - __main__ - Step 140735: {'lr': 4.820258751945694e-06, 'samples': 27021120, 'steps': 140734, 'loss/train': 1.1685060262680054} 08/31/2021 14:47:27 - INFO - __main__ - Step 140736: {'lr': 4.819221745072211e-06, 'samples': 27021312, 'steps': 140735, 'loss/train': 0.8200099468231201} 08/31/2021 14:47:27 - INFO - __main__ - Step 140737: {'lr': 4.818184848673384e-06, 'samples': 27021504, 'steps': 140736, 'loss/train': 0.9464545845985413} 08/31/2021 14:47:27 - INFO - __main__ - Step 140738: {'lr': 4.817148062749716e-06, 'samples': 27021696, 'steps': 140737, 'loss/train': 1.1863231658935547} 08/31/2021 14:47:29 - INFO - __main__ - Step 140739: {'lr': 4.816111387301647e-06, 'samples': 27021888, 'steps': 140738, 'loss/train': 1.4097768068313599} 08/31/2021 14:47:29 - INFO - __main__ - Step 140740: {'lr': 4.815074822329651e-06, 'samples': 27022080, 'steps': 140739, 'loss/train': 0.6201263070106506} 08/31/2021 14:47:30 - INFO - __main__ - Step 140741: {'lr': 4.814038367834228e-06, 'samples': 27022272, 'steps': 140740, 'loss/train': 0.9552202820777893} 08/31/2021 14:47:30 - INFO - __main__ - Step 140742: {'lr': 4.813002023815793e-06, 'samples': 27022464, 'steps': 140741, 'loss/train': 0.8107132911682129} 08/31/2021 14:47:30 - INFO - __main__ - Step 140743: {'lr': 4.8119657902748195e-06, 'samples': 27022656, 'steps': 140742, 'loss/train': 0.4524490237236023} 08/31/2021 14:47:33 - INFO - __main__ - Step 140744: {'lr': 4.810929667211805e-06, 'samples': 27022848, 'steps': 140743, 'loss/train': 1.405205488204956} 08/31/2021 14:47:33 - INFO - __main__ - Step 140745: {'lr': 4.809893654627223e-06, 'samples': 27023040, 'steps': 140744, 'loss/train': 1.5895500183105469} 08/31/2021 14:47:34 - INFO - __main__ - Step 140746: {'lr': 4.808857752521489e-06, 'samples': 27023232, 'steps': 140745, 'loss/train': 5.7366156578063965} 08/31/2021 14:47:34 - INFO - __main__ - Step 140747: {'lr': 4.807821960895104e-06, 'samples': 27023424, 'steps': 140746, 'loss/train': 5.743420124053955} 08/31/2021 14:47:34 - INFO - __main__ - Step 140748: {'lr': 4.806786279748538e-06, 'samples': 27023616, 'steps': 140747, 'loss/train': 1.4315121173858643} 08/31/2021 14:47:35 - INFO - __main__ - Step 140749: {'lr': 4.805750709082263e-06, 'samples': 27023808, 'steps': 140748, 'loss/train': 0.9208961129188538} 08/31/2021 14:47:35 - INFO - __main__ - Step 140750: {'lr': 4.8047152488967235e-06, 'samples': 27024000, 'steps': 140749, 'loss/train': 0.2367752194404602} 08/31/2021 14:47:35 - INFO - __main__ - Step 140751: {'lr': 4.803679899192393e-06, 'samples': 27024192, 'steps': 140750, 'loss/train': 0.8138832449913025} 08/31/2021 14:47:37 - INFO - __main__ - Step 140752: {'lr': 4.802644659969741e-06, 'samples': 27024384, 'steps': 140751, 'loss/train': 0.10261662304401398} 08/31/2021 14:47:38 - INFO - __main__ - Step 140753: {'lr': 4.80160953122924e-06, 'samples': 27024576, 'steps': 140752, 'loss/train': 1.4982975721359253} 08/31/2021 14:47:38 - INFO - __main__ - Step 140754: {'lr': 4.800574512971334e-06, 'samples': 27024768, 'steps': 140753, 'loss/train': 0.5092561841011047} 08/31/2021 14:47:38 - INFO - __main__ - Step 140755: {'lr': 4.7995396051965234e-06, 'samples': 27024960, 'steps': 140754, 'loss/train': 0.8409326672554016} 08/31/2021 14:47:39 - INFO - __main__ - Step 140756: {'lr': 4.798504807905252e-06, 'samples': 27025152, 'steps': 140755, 'loss/train': 0.8644553422927856} 08/31/2021 14:47:40 - INFO - __main__ - Step 140757: {'lr': 4.797470121097991e-06, 'samples': 27025344, 'steps': 140756, 'loss/train': 0.9999712705612183} 08/31/2021 14:47:41 - INFO - __main__ - Step 140758: {'lr': 4.796435544775185e-06, 'samples': 27025536, 'steps': 140757, 'loss/train': 0.9969438314437866} 08/31/2021 14:47:41 - INFO - __main__ - Step 140759: {'lr': 4.795401078937334e-06, 'samples': 27025728, 'steps': 140758, 'loss/train': 1.1429036855697632} 08/31/2021 14:47:42 - INFO - __main__ - Step 140760: {'lr': 4.794366723584908e-06, 'samples': 27025920, 'steps': 140759, 'loss/train': 1.2897766828536987} 08/31/2021 14:47:42 - INFO - __main__ - Step 140761: {'lr': 4.793332478718354e-06, 'samples': 27026112, 'steps': 140760, 'loss/train': 0.8754449486732483} 08/31/2021 14:47:44 - INFO - __main__ - Step 140762: {'lr': 4.792298344338142e-06, 'samples': 27026304, 'steps': 140761, 'loss/train': 1.0582517385482788} 08/31/2021 14:47:44 - INFO - __main__ - Step 140763: {'lr': 4.7912643204447155e-06, 'samples': 27026496, 'steps': 140762, 'loss/train': 0.46893686056137085} 08/31/2021 14:47:44 - INFO - __main__ - Step 140764: {'lr': 4.790230407038576e-06, 'samples': 27026688, 'steps': 140763, 'loss/train': 1.1450893878936768} 08/31/2021 14:47:45 - INFO - __main__ - Step 140765: {'lr': 4.789196604120166e-06, 'samples': 27026880, 'steps': 140764, 'loss/train': 0.8169835209846497} 08/31/2021 14:47:45 - INFO - __main__ - Step 140766: {'lr': 4.788162911689986e-06, 'samples': 27027072, 'steps': 140765, 'loss/train': 1.2503222227096558} 08/31/2021 14:47:46 - INFO - __main__ - Step 140767: {'lr': 4.787129329748452e-06, 'samples': 27027264, 'steps': 140766, 'loss/train': 0.5171014070510864} 08/31/2021 14:47:47 - INFO - __main__ - Step 140768: {'lr': 4.786095858296035e-06, 'samples': 27027456, 'steps': 140767, 'loss/train': 1.1496464014053345} 08/31/2021 14:47:47 - INFO - __main__ - Step 140769: {'lr': 4.785062497333264e-06, 'samples': 27027648, 'steps': 140768, 'loss/train': 1.0126770734786987} 08/31/2021 14:47:48 - INFO - __main__ - Step 140770: {'lr': 4.784029246860528e-06, 'samples': 27027840, 'steps': 140769, 'loss/train': 0.9798951148986816} 08/31/2021 14:47:48 - INFO - __main__ - Step 140771: {'lr': 4.782996106878323e-06, 'samples': 27028032, 'steps': 140770, 'loss/train': 0.8613188862800598} 08/31/2021 14:47:49 - INFO - __main__ - Step 140772: {'lr': 4.7819630773871245e-06, 'samples': 27028224, 'steps': 140771, 'loss/train': 1.1246678829193115} 08/31/2021 14:47:50 - INFO - __main__ - Step 140773: {'lr': 4.780930158387431e-06, 'samples': 27028416, 'steps': 140772, 'loss/train': 1.0952588319778442} 08/31/2021 14:47:50 - INFO - __main__ - Step 140774: {'lr': 4.779897349879602e-06, 'samples': 27028608, 'steps': 140773, 'loss/train': 1.2764173746109009} 08/31/2021 14:47:51 - INFO - __main__ - Step 140775: {'lr': 4.778864651864195e-06, 'samples': 27028800, 'steps': 140774, 'loss/train': 0.8040238618850708} 08/31/2021 14:47:51 - INFO - __main__ - Step 140776: {'lr': 4.777832064341653e-06, 'samples': 27028992, 'steps': 140775, 'loss/train': 0.7543172836303711} 08/31/2021 14:47:52 - INFO - __main__ - Step 140777: {'lr': 4.77679958731242e-06, 'samples': 27029184, 'steps': 140776, 'loss/train': 0.9484546780586243} 08/31/2021 14:47:53 - INFO - __main__ - Step 140778: {'lr': 4.7757672207769945e-06, 'samples': 27029376, 'steps': 140777, 'loss/train': 1.1099371910095215} 08/31/2021 14:47:53 - INFO - __main__ - Step 140779: {'lr': 4.774734964735794e-06, 'samples': 27029568, 'steps': 140778, 'loss/train': 0.5182895660400391} 08/31/2021 14:47:53 - INFO - __main__ - Step 140780: {'lr': 4.7737028191893465e-06, 'samples': 27029760, 'steps': 140779, 'loss/train': 0.5816237330436707} 08/31/2021 14:47:54 - INFO - __main__ - Step 140781: {'lr': 4.772670784138067e-06, 'samples': 27029952, 'steps': 140780, 'loss/train': 1.5670158863067627} 08/31/2021 14:47:55 - INFO - __main__ - Step 140782: {'lr': 4.771638859582455e-06, 'samples': 27030144, 'steps': 140781, 'loss/train': 1.3110618591308594} 08/31/2021 14:47:56 - INFO - __main__ - Step 140783: {'lr': 4.770607045522929e-06, 'samples': 27030336, 'steps': 140782, 'loss/train': 1.6830137968063354} 08/31/2021 14:47:56 - INFO - __main__ - Step 140784: {'lr': 4.769575341960014e-06, 'samples': 27030528, 'steps': 140783, 'loss/train': 0.42824360728263855} 08/31/2021 14:47:57 - INFO - __main__ - Step 140785: {'lr': 4.768543748894155e-06, 'samples': 27030720, 'steps': 140784, 'loss/train': 0.9975303411483765} 08/31/2021 14:47:57 - INFO - __main__ - Step 140786: {'lr': 4.767512266325769e-06, 'samples': 27030912, 'steps': 140785, 'loss/train': 0.8864428400993347} 08/31/2021 14:47:57 - INFO - __main__ - Step 140787: {'lr': 4.766480894255382e-06, 'samples': 27031104, 'steps': 140786, 'loss/train': 1.011784315109253} 08/31/2021 14:47:59 - INFO - __main__ - Step 140788: {'lr': 4.7654496326834105e-06, 'samples': 27031296, 'steps': 140787, 'loss/train': 0.960119903087616} 08/31/2021 14:48:00 - INFO - __main__ - Step 140789: {'lr': 4.764418481610355e-06, 'samples': 27031488, 'steps': 140788, 'loss/train': 0.747697651386261} 08/31/2021 14:48:00 - INFO - __main__ - Step 140790: {'lr': 4.763387441036687e-06, 'samples': 27031680, 'steps': 140789, 'loss/train': 0.08593426644802094} 08/31/2021 14:48:00 - INFO - __main__ - Step 140791: {'lr': 4.762356510962823e-06, 'samples': 27031872, 'steps': 140790, 'loss/train': 0.02505047246813774} 08/31/2021 14:48:01 - INFO - __main__ - Step 140792: {'lr': 4.761325691389262e-06, 'samples': 27032064, 'steps': 140791, 'loss/train': 0.750016450881958} 08/31/2021 14:48:01 - INFO - __main__ - Step 140793: {'lr': 4.760294982316477e-06, 'samples': 27032256, 'steps': 140792, 'loss/train': 0.63509601354599} 08/31/2021 14:48:03 - INFO - __main__ - Step 140794: {'lr': 4.75926438374491e-06, 'samples': 27032448, 'steps': 140793, 'loss/train': 1.3548283576965332} 08/31/2021 14:48:03 - INFO - __main__ - Step 140795: {'lr': 4.758233895675035e-06, 'samples': 27032640, 'steps': 140794, 'loss/train': 0.7803919911384583} 08/31/2021 14:48:03 - INFO - __main__ - Step 140796: {'lr': 4.757203518107323e-06, 'samples': 27032832, 'steps': 140795, 'loss/train': 1.7083972692489624} 08/31/2021 14:48:04 - INFO - __main__ - Step 140797: {'lr': 4.756173251042217e-06, 'samples': 27033024, 'steps': 140796, 'loss/train': 0.9955477118492126} 08/31/2021 14:48:04 - INFO - __main__ - Step 140798: {'lr': 4.755143094480191e-06, 'samples': 27033216, 'steps': 140797, 'loss/train': 1.1810479164123535} 08/31/2021 14:48:05 - INFO - __main__ - Step 140799: {'lr': 4.7541130484217435e-06, 'samples': 27033408, 'steps': 140798, 'loss/train': 1.1522079706192017} 08/31/2021 14:48:06 - INFO - __main__ - Step 140800: {'lr': 4.753083112867291e-06, 'samples': 27033600, 'steps': 140799, 'loss/train': 1.427235722541809} 08/31/2021 14:48:06 - INFO - __main__ - Step 140801: {'lr': 4.752053287817332e-06, 'samples': 27033792, 'steps': 140800, 'loss/train': 1.1228229999542236} 08/31/2021 14:48:07 - INFO - __main__ - Step 140802: {'lr': 4.751023573272284e-06, 'samples': 27033984, 'steps': 140801, 'loss/train': 0.7768658995628357} 08/31/2021 14:48:07 - INFO - __main__ - Step 140803: {'lr': 4.749993969232647e-06, 'samples': 27034176, 'steps': 140802, 'loss/train': 1.2035695314407349} 08/31/2021 14:48:09 - INFO - __main__ - Step 140804: {'lr': 4.748964475698892e-06, 'samples': 27034368, 'steps': 140803, 'loss/train': 1.0918523073196411} 08/31/2021 14:48:10 - INFO - __main__ - Step 140805: {'lr': 4.747935092671435e-06, 'samples': 27034560, 'steps': 140804, 'loss/train': 1.3778501749038696} 08/31/2021 14:48:10 - INFO - __main__ - Step 140806: {'lr': 4.746905820150804e-06, 'samples': 27034752, 'steps': 140805, 'loss/train': 2.14306902885437} 08/31/2021 14:48:10 - INFO - __main__ - Step 140807: {'lr': 4.745876658137443e-06, 'samples': 27034944, 'steps': 140806, 'loss/train': 1.2055598497390747} 08/31/2021 14:48:11 - INFO - __main__ - Step 140808: {'lr': 4.744847606631769e-06, 'samples': 27035136, 'steps': 140807, 'loss/train': 1.5945595502853394} 08/31/2021 14:48:11 - INFO - __main__ - Step 140809: {'lr': 4.743818665634309e-06, 'samples': 27035328, 'steps': 140808, 'loss/train': 1.1083295345306396} 08/31/2021 14:48:13 - INFO - __main__ - Step 140810: {'lr': 4.742789835145506e-06, 'samples': 27035520, 'steps': 140809, 'loss/train': 1.798208475112915} 08/31/2021 14:48:13 - INFO - __main__ - Step 140811: {'lr': 4.741761115165805e-06, 'samples': 27035712, 'steps': 140810, 'loss/train': 1.2855067253112793} 08/31/2021 14:48:14 - INFO - __main__ - Step 140812: {'lr': 4.740732505695677e-06, 'samples': 27035904, 'steps': 140811, 'loss/train': 1.3009148836135864} 08/31/2021 14:48:14 - INFO - __main__ - Step 140813: {'lr': 4.739704006735596e-06, 'samples': 27036096, 'steps': 140812, 'loss/train': 1.1315706968307495} 08/31/2021 14:48:14 - INFO - __main__ - Step 140814: {'lr': 4.7386756182860315e-06, 'samples': 27036288, 'steps': 140813, 'loss/train': 1.1678823232650757} 08/31/2021 14:48:16 - INFO - __main__ - Step 140815: {'lr': 4.737647340347429e-06, 'samples': 27036480, 'steps': 140814, 'loss/train': 0.33191564679145813} 08/31/2021 14:48:16 - INFO - __main__ - Step 140816: {'lr': 4.736619172920231e-06, 'samples': 27036672, 'steps': 140815, 'loss/train': 1.179367184638977} 08/31/2021 14:48:17 - INFO - __main__ - Step 140817: {'lr': 4.7355911160049666e-06, 'samples': 27036864, 'steps': 140816, 'loss/train': 0.8844118714332581} 08/31/2021 14:48:17 - INFO - __main__ - Step 140818: {'lr': 4.7345631696020245e-06, 'samples': 27037056, 'steps': 140817, 'loss/train': 0.695015549659729} 08/31/2021 14:48:17 - INFO - __main__ - Step 140819: {'lr': 4.73353533371193e-06, 'samples': 27037248, 'steps': 140818, 'loss/train': 0.036401089280843735} 08/31/2021 14:48:19 - INFO - __main__ - Step 140820: {'lr': 4.732507608335101e-06, 'samples': 27037440, 'steps': 140819, 'loss/train': 0.2526075839996338} 08/31/2021 14:48:19 - INFO - __main__ - Step 140821: {'lr': 4.731479993472038e-06, 'samples': 27037632, 'steps': 140820, 'loss/train': 1.1891733407974243} 08/31/2021 14:48:20 - INFO - __main__ - Step 140822: {'lr': 4.730452489123183e-06, 'samples': 27037824, 'steps': 140821, 'loss/train': 0.7376407384872437} 08/31/2021 14:48:20 - INFO - __main__ - Step 140823: {'lr': 4.729425095288981e-06, 'samples': 27038016, 'steps': 140822, 'loss/train': 0.8196821212768555} 08/31/2021 14:48:20 - INFO - __main__ - Step 140824: {'lr': 4.728397811969931e-06, 'samples': 27038208, 'steps': 140823, 'loss/train': 1.0262550115585327} 08/31/2021 14:48:22 - INFO - __main__ - Step 140825: {'lr': 4.727370639166506e-06, 'samples': 27038400, 'steps': 140824, 'loss/train': 1.0497233867645264} 08/31/2021 14:48:22 - INFO - __main__ - Step 140826: {'lr': 4.726343576879122e-06, 'samples': 27038592, 'steps': 140825, 'loss/train': 1.0730053186416626} 08/31/2021 14:48:23 - INFO - __main__ - Step 140827: {'lr': 4.72531662510825e-06, 'samples': 27038784, 'steps': 140826, 'loss/train': 1.2498936653137207} 08/31/2021 14:48:23 - INFO - __main__ - Step 140828: {'lr': 4.724289783854363e-06, 'samples': 27038976, 'steps': 140827, 'loss/train': 1.2848875522613525} 08/31/2021 14:48:23 - INFO - __main__ - Step 140829: {'lr': 4.723263053117932e-06, 'samples': 27039168, 'steps': 140828, 'loss/train': 0.8841276168823242} 08/31/2021 14:48:25 - INFO - __main__ - Step 140830: {'lr': 4.722236432899429e-06, 'samples': 27039360, 'steps': 140829, 'loss/train': 1.1519681215286255} 08/31/2021 14:48:25 - INFO - __main__ - Step 140831: {'lr': 4.721209923199271e-06, 'samples': 27039552, 'steps': 140830, 'loss/train': 0.9840997457504272} 08/31/2021 14:48:26 - INFO - __main__ - Step 140832: {'lr': 4.720183524017984e-06, 'samples': 27039744, 'steps': 140831, 'loss/train': 0.9737780690193176} 08/31/2021 14:48:26 - INFO - __main__ - Step 140833: {'lr': 4.7191572353559584e-06, 'samples': 27039936, 'steps': 140832, 'loss/train': 1.5286388397216797} 08/31/2021 14:48:27 - INFO - __main__ - Step 140834: {'lr': 4.71813105721372e-06, 'samples': 27040128, 'steps': 140833, 'loss/train': 1.2565714120864868} 08/31/2021 14:48:28 - INFO - __main__ - Step 140835: {'lr': 4.717104989591714e-06, 'samples': 27040320, 'steps': 140834, 'loss/train': 0.5306569337844849} 08/31/2021 14:48:29 - INFO - __main__ - Step 140836: {'lr': 4.716079032490384e-06, 'samples': 27040512, 'steps': 140835, 'loss/train': 0.6199994683265686} 08/31/2021 14:48:29 - INFO - __main__ - Step 140837: {'lr': 4.715053185910201e-06, 'samples': 27040704, 'steps': 140836, 'loss/train': 0.3270125389099121} 08/31/2021 14:48:30 - INFO - __main__ - Step 140838: {'lr': 4.7140274498516375e-06, 'samples': 27040896, 'steps': 140837, 'loss/train': 0.028671378269791603} 08/31/2021 14:48:30 - INFO - __main__ - Step 140839: {'lr': 4.713001824315166e-06, 'samples': 27041088, 'steps': 140838, 'loss/train': 0.02768787369132042} 08/31/2021 14:48:30 - INFO - __main__ - Step 140840: {'lr': 4.711976309301231e-06, 'samples': 27041280, 'steps': 140839, 'loss/train': 0.14486779272556305} 08/31/2021 14:48:31 - INFO - __main__ - Step 140841: {'lr': 4.7109509048102735e-06, 'samples': 27041472, 'steps': 140840, 'loss/train': 0.7454743981361389} 08/31/2021 14:48:32 - INFO - __main__ - Step 140842: {'lr': 4.709925610842769e-06, 'samples': 27041664, 'steps': 140841, 'loss/train': 0.610084056854248} 08/31/2021 14:48:33 - INFO - __main__ - Step 140843: {'lr': 4.708900427399188e-06, 'samples': 27041856, 'steps': 140842, 'loss/train': 0.4795646667480469} 08/31/2021 14:48:33 - INFO - __main__ - Step 140844: {'lr': 4.707875354480001e-06, 'samples': 27042048, 'steps': 140843, 'loss/train': 0.9165042042732239} 08/31/2021 14:48:34 - INFO - __main__ - Step 140845: {'lr': 4.706850392085682e-06, 'samples': 27042240, 'steps': 140844, 'loss/train': 0.46955373883247375} 08/31/2021 14:48:34 - INFO - __main__ - Step 140846: {'lr': 4.705825540216646e-06, 'samples': 27042432, 'steps': 140845, 'loss/train': 1.3967695236206055} 08/31/2021 14:48:35 - INFO - __main__ - Step 140847: {'lr': 4.7048007988733655e-06, 'samples': 27042624, 'steps': 140846, 'loss/train': 0.3514711260795593} 08/31/2021 14:48:36 - INFO - __main__ - Step 140848: {'lr': 4.703776168056339e-06, 'samples': 27042816, 'steps': 140847, 'loss/train': 0.7108792066574097} 08/31/2021 14:48:36 - INFO - __main__ - Step 140849: {'lr': 4.702751647765985e-06, 'samples': 27043008, 'steps': 140848, 'loss/train': 0.9213358759880066} 08/31/2021 14:48:37 - INFO - __main__ - Step 140850: {'lr': 4.701727238002801e-06, 'samples': 27043200, 'steps': 140849, 'loss/train': 1.058321237564087} 08/31/2021 14:48:37 - INFO - __main__ - Step 140851: {'lr': 4.700702938767259e-06, 'samples': 27043392, 'steps': 140850, 'loss/train': 1.0105276107788086} 08/31/2021 14:48:39 - INFO - __main__ - Step 140852: {'lr': 4.699678750059777e-06, 'samples': 27043584, 'steps': 140851, 'loss/train': 1.3681443929672241} 08/31/2021 14:48:39 - INFO - __main__ - Step 140853: {'lr': 4.698654671880825e-06, 'samples': 27043776, 'steps': 140852, 'loss/train': 1.6887564659118652} 08/31/2021 14:48:39 - INFO - __main__ - Step 140854: {'lr': 4.697630704230877e-06, 'samples': 27043968, 'steps': 140853, 'loss/train': 1.283600926399231} 08/31/2021 14:48:40 - INFO - __main__ - Step 140855: {'lr': 4.6966068471104014e-06, 'samples': 27044160, 'steps': 140854, 'loss/train': 0.028239931911230087} 08/31/2021 14:48:40 - INFO - __main__ - Step 140856: {'lr': 4.695583100519818e-06, 'samples': 27044352, 'steps': 140855, 'loss/train': 1.2271312475204468} 08/31/2021 14:48:42 - INFO - __main__ - Step 140857: {'lr': 4.694559464459652e-06, 'samples': 27044544, 'steps': 140856, 'loss/train': 2.4276509284973145} 08/31/2021 14:48:43 - INFO - __main__ - Step 140858: {'lr': 4.6935359389303214e-06, 'samples': 27044736, 'steps': 140857, 'loss/train': 1.0692960023880005} 08/31/2021 14:48:43 - INFO - __main__ - Step 140859: {'lr': 4.692512523932296e-06, 'samples': 27044928, 'steps': 140858, 'loss/train': 1.733150601387024} 08/31/2021 14:48:43 - INFO - __main__ - Step 140860: {'lr': 4.69148921946605e-06, 'samples': 27045120, 'steps': 140859, 'loss/train': 1.4790211915969849} 08/31/2021 14:48:44 - INFO - __main__ - Step 140861: {'lr': 4.690466025531998e-06, 'samples': 27045312, 'steps': 140860, 'loss/train': 0.9240561723709106} 08/31/2021 14:48:44 - INFO - __main__ - Step 140862: {'lr': 4.689442942130667e-06, 'samples': 27045504, 'steps': 140861, 'loss/train': 1.5590800046920776} 08/31/2021 14:48:46 - INFO - __main__ - Step 140863: {'lr': 4.688419969262503e-06, 'samples': 27045696, 'steps': 140862, 'loss/train': 1.082245111465454} 08/31/2021 14:48:46 - INFO - __main__ - Step 140864: {'lr': 4.687397106927921e-06, 'samples': 27045888, 'steps': 140863, 'loss/train': 0.848443329334259} 08/31/2021 14:48:46 - INFO - __main__ - Step 140865: {'lr': 4.686374355127421e-06, 'samples': 27046080, 'steps': 140864, 'loss/train': 1.278831958770752} 08/31/2021 14:48:47 - INFO - __main__ - Step 140866: {'lr': 4.6853517138614746e-06, 'samples': 27046272, 'steps': 140865, 'loss/train': 0.9224987030029297} 08/31/2021 14:48:47 - INFO - __main__ - Step 140867: {'lr': 4.684329183130498e-06, 'samples': 27046464, 'steps': 140866, 'loss/train': 1.2408955097198486} 08/31/2021 14:48:49 - INFO - __main__ - Step 140868: {'lr': 4.683306762934991e-06, 'samples': 27046656, 'steps': 140867, 'loss/train': 1.4770370721817017} 08/31/2021 14:48:49 - INFO - __main__ - Step 140869: {'lr': 4.682284453275399e-06, 'samples': 27046848, 'steps': 140868, 'loss/train': 1.0044387578964233} 08/31/2021 14:48:49 - INFO - __main__ - Step 140870: {'lr': 4.681262254152191e-06, 'samples': 27047040, 'steps': 140869, 'loss/train': 1.2249891757965088} 08/31/2021 14:48:50 - INFO - __main__ - Step 140871: {'lr': 4.680240165565785e-06, 'samples': 27047232, 'steps': 140870, 'loss/train': 1.3614554405212402} 08/31/2021 14:48:50 - INFO - __main__ - Step 140872: {'lr': 4.67921818751671e-06, 'samples': 27047424, 'steps': 140871, 'loss/train': 0.914569616317749} 08/31/2021 14:48:52 - INFO - __main__ - Step 140873: {'lr': 4.678196320005379e-06, 'samples': 27047616, 'steps': 140872, 'loss/train': 1.0544570684432983} 08/31/2021 14:48:52 - INFO - __main__ - Step 140874: {'lr': 4.677174563032294e-06, 'samples': 27047808, 'steps': 140873, 'loss/train': 1.6498953104019165} 08/31/2021 14:48:52 - INFO - __main__ - Step 140875: {'lr': 4.67615291659787e-06, 'samples': 27048000, 'steps': 140874, 'loss/train': 0.7104867100715637} 08/31/2021 14:48:53 - INFO - __main__ - Step 140876: {'lr': 4.675131380702579e-06, 'samples': 27048192, 'steps': 140875, 'loss/train': 1.2228140830993652} 08/31/2021 14:48:53 - INFO - __main__ - Step 140877: {'lr': 4.674109955346894e-06, 'samples': 27048384, 'steps': 140876, 'loss/train': 1.4158552885055542} 08/31/2021 14:48:54 - INFO - __main__ - Step 140878: {'lr': 4.673088640531259e-06, 'samples': 27048576, 'steps': 140877, 'loss/train': 1.0496214628219604} 08/31/2021 14:48:55 - INFO - __main__ - Step 140879: {'lr': 4.672067436256172e-06, 'samples': 27048768, 'steps': 140878, 'loss/train': 0.7385228276252747} 08/31/2021 14:48:55 - INFO - __main__ - Step 140880: {'lr': 4.6710463425220506e-06, 'samples': 27048960, 'steps': 140879, 'loss/train': 0.8621196746826172} 08/31/2021 14:48:56 - INFO - __main__ - Step 140881: {'lr': 4.670025359329367e-06, 'samples': 27049152, 'steps': 140880, 'loss/train': 1.6161714792251587} 08/31/2021 14:48:56 - INFO - __main__ - Step 140882: {'lr': 4.669004486678591e-06, 'samples': 27049344, 'steps': 140881, 'loss/train': 1.033384084701538} 08/31/2021 14:48:57 - INFO - __main__ - Step 140883: {'lr': 4.667983724570168e-06, 'samples': 27049536, 'steps': 140882, 'loss/train': 1.6079176664352417} 08/31/2021 14:48:58 - INFO - __main__ - Step 140884: {'lr': 4.666963073004571e-06, 'samples': 27049728, 'steps': 140883, 'loss/train': 0.89235520362854} 08/31/2021 14:48:58 - INFO - __main__ - Step 140885: {'lr': 4.665942531982242e-06, 'samples': 27049920, 'steps': 140884, 'loss/train': 1.2744717597961426} 08/31/2021 14:48:59 - INFO - __main__ - Step 140886: {'lr': 4.664922101503683e-06, 'samples': 27050112, 'steps': 140885, 'loss/train': 0.10551092028617859} 08/31/2021 14:48:59 - INFO - __main__ - Step 140887: {'lr': 4.66390178156928e-06, 'samples': 27050304, 'steps': 140886, 'loss/train': 1.2360291481018066} 08/31/2021 14:49:01 - INFO - __main__ - Step 140888: {'lr': 4.662881572179561e-06, 'samples': 27050496, 'steps': 140887, 'loss/train': 1.1075506210327148} 08/31/2021 14:49:01 - INFO - __main__ - Step 140889: {'lr': 4.6618614733349716e-06, 'samples': 27050688, 'steps': 140888, 'loss/train': 1.2878942489624023} 08/31/2021 14:49:01 - INFO - __main__ - Step 140890: {'lr': 4.660841485035955e-06, 'samples': 27050880, 'steps': 140889, 'loss/train': 0.3043186366558075} 08/31/2021 14:49:02 - INFO - __main__ - Step 140891: {'lr': 4.659821607282983e-06, 'samples': 27051072, 'steps': 140890, 'loss/train': 1.0856599807739258} 08/31/2021 14:49:02 - INFO - __main__ - Step 140892: {'lr': 4.658801840076499e-06, 'samples': 27051264, 'steps': 140891, 'loss/train': 0.9204854965209961} 08/31/2021 14:49:02 - INFO - __main__ - Step 140893: {'lr': 4.657782183416976e-06, 'samples': 27051456, 'steps': 140892, 'loss/train': 0.41831502318382263} 08/31/2021 14:49:04 - INFO - __main__ - Step 140894: {'lr': 4.656762637304884e-06, 'samples': 27051648, 'steps': 140893, 'loss/train': 1.2740970849990845} 08/31/2021 14:49:04 - INFO - __main__ - Step 140895: {'lr': 4.655743201740642e-06, 'samples': 27051840, 'steps': 140894, 'loss/train': 1.3138972520828247} 08/31/2021 14:49:05 - INFO - __main__ - Step 140896: {'lr': 4.654723876724748e-06, 'samples': 27052032, 'steps': 140895, 'loss/train': 1.191895842552185} 08/31/2021 14:49:05 - INFO - __main__ - Step 140897: {'lr': 4.6537046622576735e-06, 'samples': 27052224, 'steps': 140896, 'loss/train': 0.9708043336868286} 08/31/2021 14:49:05 - INFO - __main__ - Step 140898: {'lr': 4.652685558339808e-06, 'samples': 27052416, 'steps': 140897, 'loss/train': 1.0584222078323364} 08/31/2021 14:49:07 - INFO - __main__ - Step 140899: {'lr': 4.651666564971679e-06, 'samples': 27052608, 'steps': 140898, 'loss/train': 1.3616151809692383} 08/31/2021 14:49:07 - INFO - __main__ - Step 140900: {'lr': 4.6506476821537305e-06, 'samples': 27052800, 'steps': 140899, 'loss/train': 1.0286318063735962} 08/31/2021 14:49:08 - INFO - __main__ - Step 140901: {'lr': 4.649628909886406e-06, 'samples': 27052992, 'steps': 140900, 'loss/train': 1.3488719463348389} 08/31/2021 14:49:08 - INFO - __main__ - Step 140902: {'lr': 4.648610248170176e-06, 'samples': 27053184, 'steps': 140901, 'loss/train': 0.5470032095909119} 08/31/2021 14:49:08 - INFO - __main__ - Step 140903: {'lr': 4.647591697005488e-06, 'samples': 27053376, 'steps': 140902, 'loss/train': 1.0868897438049316} 08/31/2021 14:49:10 - INFO - __main__ - Step 140904: {'lr': 4.646573256392811e-06, 'samples': 27053568, 'steps': 140903, 'loss/train': 1.1826626062393188} 08/31/2021 14:49:11 - INFO - __main__ - Step 140905: {'lr': 4.645554926332618e-06, 'samples': 27053760, 'steps': 140904, 'loss/train': 0.8629534244537354} 08/31/2021 14:49:11 - INFO - __main__ - Step 140906: {'lr': 4.644536706825353e-06, 'samples': 27053952, 'steps': 140905, 'loss/train': 1.8028645515441895} 08/31/2021 14:49:11 - INFO - __main__ - Step 140907: {'lr': 4.64351859787146e-06, 'samples': 27054144, 'steps': 140906, 'loss/train': 1.1850241422653198} 08/31/2021 14:49:12 - INFO - __main__ - Step 140908: {'lr': 4.642500599471411e-06, 'samples': 27054336, 'steps': 140907, 'loss/train': 1.0874847173690796} 08/31/2021 14:49:14 - INFO - __main__ - Step 140909: {'lr': 4.641482711625678e-06, 'samples': 27054528, 'steps': 140908, 'loss/train': 0.02543456479907036} 08/31/2021 14:49:14 - INFO - __main__ - Step 140910: {'lr': 4.640464934334704e-06, 'samples': 27054720, 'steps': 140909, 'loss/train': 1.5598695278167725} 08/31/2021 14:49:15 - INFO - __main__ - Step 140911: {'lr': 4.639447267598934e-06, 'samples': 27054912, 'steps': 140910, 'loss/train': 1.1145975589752197} 08/31/2021 14:49:15 - INFO - __main__ - Step 140912: {'lr': 4.63842971141884e-06, 'samples': 27055104, 'steps': 140911, 'loss/train': 1.1676398515701294} 08/31/2021 14:49:15 - INFO - __main__ - Step 140913: {'lr': 4.637412265794894e-06, 'samples': 27055296, 'steps': 140912, 'loss/train': 1.1562284231185913} 08/31/2021 14:49:16 - INFO - __main__ - Step 140914: {'lr': 4.636394930727539e-06, 'samples': 27055488, 'steps': 140913, 'loss/train': 0.47963061928749084} 08/31/2021 14:49:17 - INFO - __main__ - Step 140915: {'lr': 4.635377706217248e-06, 'samples': 27055680, 'steps': 140914, 'loss/train': 1.3895819187164307} 08/31/2021 14:49:18 - INFO - __main__ - Step 140916: {'lr': 4.634360592264463e-06, 'samples': 27055872, 'steps': 140915, 'loss/train': 0.6834474802017212} 08/31/2021 14:49:18 - INFO - __main__ - Step 140917: {'lr': 4.633343588869659e-06, 'samples': 27056064, 'steps': 140916, 'loss/train': 1.4298155307769775} 08/31/2021 14:49:19 - INFO - __main__ - Step 140918: {'lr': 4.632326696033279e-06, 'samples': 27056256, 'steps': 140917, 'loss/train': 5.695247650146484} 08/31/2021 14:49:19 - INFO - __main__ - Step 140919: {'lr': 4.631309913755766e-06, 'samples': 27056448, 'steps': 140918, 'loss/train': 1.4458554983139038} 08/31/2021 14:49:19 - INFO - __main__ - Step 140920: {'lr': 4.6302932420376474e-06, 'samples': 27056640, 'steps': 140919, 'loss/train': 1.0339025259017944} 08/31/2021 14:49:21 - INFO - __main__ - Step 140921: {'lr': 4.629276680879285e-06, 'samples': 27056832, 'steps': 140920, 'loss/train': 0.6875181198120117} 08/31/2021 14:49:21 - INFO - __main__ - Step 140922: {'lr': 4.628260230281206e-06, 'samples': 27057024, 'steps': 140921, 'loss/train': 1.1129934787750244} 08/31/2021 14:49:22 - INFO - __main__ - Step 140923: {'lr': 4.627243890243854e-06, 'samples': 27057216, 'steps': 140922, 'loss/train': 0.9363824725151062} 08/31/2021 14:49:22 - INFO - __main__ - Step 140924: {'lr': 4.6262276607676454e-06, 'samples': 27057408, 'steps': 140923, 'loss/train': 1.5347847938537598} 08/31/2021 14:49:22 - INFO - __main__ - Step 140925: {'lr': 4.625211541853108e-06, 'samples': 27057600, 'steps': 140924, 'loss/train': 0.7022480964660645} 08/31/2021 14:49:24 - INFO - __main__ - Step 140926: {'lr': 4.624195533500658e-06, 'samples': 27057792, 'steps': 140925, 'loss/train': 1.051064133644104} 08/31/2021 14:49:24 - INFO - __main__ - Step 140927: {'lr': 4.623179635710739e-06, 'samples': 27057984, 'steps': 140926, 'loss/train': 0.9219779372215271} 08/31/2021 14:49:25 - INFO - __main__ - Step 140928: {'lr': 4.622163848483823e-06, 'samples': 27058176, 'steps': 140927, 'loss/train': 0.37921303510665894} 08/31/2021 14:49:25 - INFO - __main__ - Step 140929: {'lr': 4.621148171820411e-06, 'samples': 27058368, 'steps': 140928, 'loss/train': 0.3974885940551758} 08/31/2021 14:49:25 - INFO - __main__ - Step 140930: {'lr': 4.620132605720889e-06, 'samples': 27058560, 'steps': 140929, 'loss/train': 0.7554454207420349} 08/31/2021 14:49:27 - INFO - __main__ - Step 140931: {'lr': 4.619117150185759e-06, 'samples': 27058752, 'steps': 140930, 'loss/train': 0.7880346775054932} 08/31/2021 14:49:28 - INFO - __main__ - Step 140932: {'lr': 4.618101805215491e-06, 'samples': 27058944, 'steps': 140931, 'loss/train': 1.016381025314331} 08/31/2021 14:49:28 - INFO - __main__ - Step 140933: {'lr': 4.6170865708105025e-06, 'samples': 27059136, 'steps': 140932, 'loss/train': 1.6559585332870483} 08/31/2021 14:49:28 - INFO - __main__ - Step 140934: {'lr': 4.616071446971265e-06, 'samples': 27059328, 'steps': 140933, 'loss/train': 0.8880023956298828} 08/31/2021 14:49:29 - INFO - __main__ - Step 140935: {'lr': 4.615056433698251e-06, 'samples': 27059520, 'steps': 140934, 'loss/train': 0.9508664608001709} 08/31/2021 14:49:29 - INFO - __main__ - Step 140936: {'lr': 4.6140415309919026e-06, 'samples': 27059712, 'steps': 140935, 'loss/train': 1.1086798906326294} 08/31/2021 14:49:31 - INFO - __main__ - Step 140937: {'lr': 4.613026738852666e-06, 'samples': 27059904, 'steps': 140936, 'loss/train': 1.3824464082717896} 08/31/2021 14:49:31 - INFO - __main__ - Step 140938: {'lr': 4.612012057281012e-06, 'samples': 27060096, 'steps': 140937, 'loss/train': 1.3636966943740845} 08/31/2021 14:49:32 - INFO - __main__ - Step 140939: {'lr': 4.610997486277413e-06, 'samples': 27060288, 'steps': 140938, 'loss/train': 1.1895304918289185} 08/31/2021 14:49:32 - INFO - __main__ - Step 140940: {'lr': 4.609983025842313e-06, 'samples': 27060480, 'steps': 140939, 'loss/train': 1.3011314868927002} 08/31/2021 14:49:32 - INFO - __main__ - Step 140941: {'lr': 4.608968675976155e-06, 'samples': 27060672, 'steps': 140940, 'loss/train': 1.4155596494674683} 08/31/2021 14:49:34 - INFO - __main__ - Step 140942: {'lr': 4.607954436679412e-06, 'samples': 27060864, 'steps': 140941, 'loss/train': 0.9118637442588806} 08/31/2021 14:49:35 - INFO - __main__ - Step 140943: {'lr': 4.606940307952529e-06, 'samples': 27061056, 'steps': 140942, 'loss/train': 1.4938396215438843} 08/31/2021 14:49:35 - INFO - __main__ - Step 140944: {'lr': 4.605926289796003e-06, 'samples': 27061248, 'steps': 140943, 'loss/train': 5.370386600494385} 08/31/2021 14:49:35 - INFO - __main__ - Step 140945: {'lr': 4.604912382210224e-06, 'samples': 27061440, 'steps': 140944, 'loss/train': 5.372720241546631} 08/31/2021 14:49:36 - INFO - __main__ - Step 140946: {'lr': 4.603898585195721e-06, 'samples': 27061632, 'steps': 140945, 'loss/train': 1.5795633792877197} 08/31/2021 14:49:36 - INFO - __main__ - Step 140947: {'lr': 4.602884898752907e-06, 'samples': 27061824, 'steps': 140946, 'loss/train': 1.2926205396652222} 08/31/2021 14:49:38 - INFO - __main__ - Step 140948: {'lr': 4.601871322882229e-06, 'samples': 27062016, 'steps': 140947, 'loss/train': 1.1368029117584229} 08/31/2021 14:49:38 - INFO - __main__ - Step 140949: {'lr': 4.600857857584184e-06, 'samples': 27062208, 'steps': 140948, 'loss/train': 1.3729246854782104} 08/31/2021 14:49:38 - INFO - __main__ - Step 140950: {'lr': 4.599844502859191e-06, 'samples': 27062400, 'steps': 140949, 'loss/train': 0.2277616411447525} 08/31/2021 14:49:39 - INFO - __main__ - Step 140951: {'lr': 4.598831258707719e-06, 'samples': 27062592, 'steps': 140950, 'loss/train': 0.5516777634620667} 08/31/2021 14:49:39 - INFO - __main__ - Step 140952: {'lr': 4.597818125130215e-06, 'samples': 27062784, 'steps': 140951, 'loss/train': 0.17788814008235931} 08/31/2021 14:49:42 - INFO - __main__ - Step 140953: {'lr': 4.59680510212715e-06, 'samples': 27062976, 'steps': 140952, 'loss/train': 1.0151824951171875} 08/31/2021 14:49:42 - INFO - __main__ - Step 140954: {'lr': 4.595792189698994e-06, 'samples': 27063168, 'steps': 140953, 'loss/train': 1.3125646114349365} 08/31/2021 14:49:42 - INFO - __main__ - Step 140955: {'lr': 4.594779387846193e-06, 'samples': 27063360, 'steps': 140954, 'loss/train': 0.5701683759689331} 08/31/2021 14:49:43 - INFO - __main__ - Step 140956: {'lr': 4.593766696569162e-06, 'samples': 27063552, 'steps': 140955, 'loss/train': 0.9765751361846924} 08/31/2021 14:49:43 - INFO - __main__ - Step 140957: {'lr': 4.592754115868431e-06, 'samples': 27063744, 'steps': 140956, 'loss/train': 0.015165679156780243} 08/31/2021 14:49:43 - INFO - __main__ - Step 140958: {'lr': 4.591741645744385e-06, 'samples': 27063936, 'steps': 140957, 'loss/train': 0.7272704839706421} 08/31/2021 14:49:45 - INFO - __main__ - Step 140959: {'lr': 4.590729286197554e-06, 'samples': 27064128, 'steps': 140958, 'loss/train': 1.2979841232299805} 08/31/2021 14:49:45 - INFO - __main__ - Step 140960: {'lr': 4.589717037228353e-06, 'samples': 27064320, 'steps': 140959, 'loss/train': 1.009972095489502} 08/31/2021 14:49:46 - INFO - __main__ - Step 140961: {'lr': 4.5887048988371985e-06, 'samples': 27064512, 'steps': 140960, 'loss/train': 0.9546962976455688} 08/31/2021 14:49:46 - INFO - __main__ - Step 140962: {'lr': 4.587692871024618e-06, 'samples': 27064704, 'steps': 140961, 'loss/train': 1.279528260231018} 08/31/2021 14:49:46 - INFO - __main__ - Step 140963: {'lr': 4.586680953791028e-06, 'samples': 27064896, 'steps': 140962, 'loss/train': 1.1171444654464722} 08/31/2021 14:49:48 - INFO - __main__ - Step 140964: {'lr': 4.585669147136873e-06, 'samples': 27065088, 'steps': 140963, 'loss/train': 0.3988325595855713} 08/31/2021 14:49:48 - INFO - __main__ - Step 140965: {'lr': 4.584657451062652e-06, 'samples': 27065280, 'steps': 140964, 'loss/train': 0.5145692229270935} 08/31/2021 14:49:49 - INFO - __main__ - Step 140966: {'lr': 4.58364586556878e-06, 'samples': 27065472, 'steps': 140965, 'loss/train': 1.0597256422042847} 08/31/2021 14:49:49 - INFO - __main__ - Step 140967: {'lr': 4.582634390655732e-06, 'samples': 27065664, 'steps': 140966, 'loss/train': 0.3763267397880554} 08/31/2021 14:49:49 - INFO - __main__ - Step 140968: {'lr': 4.581623026323978e-06, 'samples': 27065856, 'steps': 140967, 'loss/train': 0.4761498272418976} 08/31/2021 14:49:50 - INFO - __main__ - Step 140969: {'lr': 4.580611772573934e-06, 'samples': 27066048, 'steps': 140968, 'loss/train': 0.847897469997406} 08/31/2021 14:49:51 - INFO - __main__ - Step 140970: {'lr': 4.5796006294061e-06, 'samples': 27066240, 'steps': 140969, 'loss/train': 1.0896003246307373} 08/31/2021 14:49:52 - INFO - __main__ - Step 140971: {'lr': 4.57858959682092e-06, 'samples': 27066432, 'steps': 140970, 'loss/train': 1.1900157928466797} 08/31/2021 14:49:52 - INFO - __main__ - Step 140972: {'lr': 4.577578674818811e-06, 'samples': 27066624, 'steps': 140971, 'loss/train': 1.3658254146575928} 08/31/2021 14:49:52 - INFO - __main__ - Step 140973: {'lr': 4.5765678634003e-06, 'samples': 27066816, 'steps': 140972, 'loss/train': 1.2758471965789795} 08/31/2021 14:49:53 - INFO - __main__ - Step 140974: {'lr': 4.575557162565774e-06, 'samples': 27067008, 'steps': 140973, 'loss/train': 1.1893422603607178} 08/31/2021 14:49:54 - INFO - __main__ - Step 140975: {'lr': 4.574546572315708e-06, 'samples': 27067200, 'steps': 140974, 'loss/train': 0.9281305074691772} 08/31/2021 14:49:55 - INFO - __main__ - Step 140976: {'lr': 4.573536092650571e-06, 'samples': 27067392, 'steps': 140975, 'loss/train': 0.6443188786506653} 08/31/2021 14:49:55 - INFO - __main__ - Step 140977: {'lr': 4.572525723570809e-06, 'samples': 27067584, 'steps': 140976, 'loss/train': 0.9378043413162231} 08/31/2021 14:49:55 - INFO - __main__ - Step 140978: {'lr': 4.571515465076864e-06, 'samples': 27067776, 'steps': 140977, 'loss/train': 1.3218094110488892} 08/31/2021 14:49:56 - INFO - __main__ - Step 140979: {'lr': 4.570505317169238e-06, 'samples': 27067968, 'steps': 140978, 'loss/train': 1.4301706552505493} 08/31/2021 14:49:57 - INFO - __main__ - Step 140980: {'lr': 4.569495279848345e-06, 'samples': 27068160, 'steps': 140979, 'loss/train': 1.25212562084198} 08/31/2021 14:49:58 - INFO - __main__ - Step 140981: {'lr': 4.568485353114632e-06, 'samples': 27068352, 'steps': 140980, 'loss/train': 0.22647437453269958} 08/31/2021 14:49:58 - INFO - __main__ - Step 140982: {'lr': 4.567475536968596e-06, 'samples': 27068544, 'steps': 140981, 'loss/train': 0.42045721411705017} 08/31/2021 14:49:58 - INFO - __main__ - Step 140983: {'lr': 4.566465831410655e-06, 'samples': 27068736, 'steps': 140982, 'loss/train': 1.2849433422088623} 08/31/2021 14:49:59 - INFO - __main__ - Step 140984: {'lr': 4.5654562364412786e-06, 'samples': 27068928, 'steps': 140983, 'loss/train': 1.2882059812545776} 08/31/2021 14:50:00 - INFO - __main__ - Step 140985: {'lr': 4.564446752060914e-06, 'samples': 27069120, 'steps': 140984, 'loss/train': 1.2199442386627197} 08/31/2021 14:50:01 - INFO - __main__ - Step 140986: {'lr': 4.56343737827003e-06, 'samples': 27069312, 'steps': 140985, 'loss/train': 1.2645114660263062} 08/31/2021 14:50:01 - INFO - __main__ - Step 140987: {'lr': 4.5624281150691e-06, 'samples': 27069504, 'steps': 140986, 'loss/train': 1.0802520513534546} 08/31/2021 14:50:01 - INFO - __main__ - Step 140988: {'lr': 4.561418962458513e-06, 'samples': 27069696, 'steps': 140987, 'loss/train': 0.7540669441223145} 08/31/2021 14:50:02 - INFO - __main__ - Step 140989: {'lr': 4.560409920438796e-06, 'samples': 27069888, 'steps': 140988, 'loss/train': 1.1715776920318604} 08/31/2021 14:50:03 - INFO - __main__ - Step 140990: {'lr': 4.559400989010337e-06, 'samples': 27070080, 'steps': 140989, 'loss/train': 1.1859687566757202} 08/31/2021 14:50:04 - INFO - __main__ - Step 140991: {'lr': 4.5583921681736365e-06, 'samples': 27070272, 'steps': 140990, 'loss/train': 1.1011842489242554} 08/31/2021 14:50:04 - INFO - __main__ - Step 140992: {'lr': 4.557383457929137e-06, 'samples': 27070464, 'steps': 140991, 'loss/train': 1.4103952646255493} 08/31/2021 14:50:04 - INFO - __main__ - Step 140993: {'lr': 4.556374858277312e-06, 'samples': 27070656, 'steps': 140992, 'loss/train': 0.7481576204299927} 08/31/2021 14:50:05 - INFO - __main__ - Step 140994: {'lr': 4.555366369218578e-06, 'samples': 27070848, 'steps': 140993, 'loss/train': 1.170891284942627} 08/31/2021 14:50:05 - INFO - __main__ - Step 140995: {'lr': 4.554357990753405e-06, 'samples': 27071040, 'steps': 140994, 'loss/train': 0.9661600589752197} 08/31/2021 14:50:07 - INFO - __main__ - Step 140996: {'lr': 4.553349722882266e-06, 'samples': 27071232, 'steps': 140995, 'loss/train': 1.2091400623321533} 08/31/2021 14:50:07 - INFO - __main__ - Step 140997: {'lr': 4.552341565605578e-06, 'samples': 27071424, 'steps': 140996, 'loss/train': 0.025865601375699043} 08/31/2021 14:50:08 - INFO - __main__ - Step 140998: {'lr': 4.551333518923867e-06, 'samples': 27071616, 'steps': 140997, 'loss/train': 0.9029677510261536} 08/31/2021 14:50:08 - INFO - __main__ - Step 140999: {'lr': 4.550325582837495e-06, 'samples': 27071808, 'steps': 140998, 'loss/train': 0.8297250270843506} 08/31/2021 14:50:08 - INFO - __main__ - Step 141000: {'lr': 4.5493177573469605e-06, 'samples': 27072000, 'steps': 140999, 'loss/train': 1.8798985481262207} 08/31/2021 14:50:10 - INFO - __main__ - Step 141001: {'lr': 4.548310042452736e-06, 'samples': 27072192, 'steps': 141000, 'loss/train': 1.1377664804458618} 08/31/2021 14:50:10 - INFO - __main__ - Step 141002: {'lr': 4.547302438155238e-06, 'samples': 27072384, 'steps': 141001, 'loss/train': 1.9482123851776123} 08/31/2021 14:50:11 - INFO - __main__ - Step 141003: {'lr': 4.5462949444549374e-06, 'samples': 27072576, 'steps': 141002, 'loss/train': 0.7302410006523132} 08/31/2021 14:50:11 - INFO - __main__ - Step 141004: {'lr': 4.545287561352279e-06, 'samples': 27072768, 'steps': 141003, 'loss/train': 1.3114943504333496} 08/31/2021 14:50:11 - INFO - __main__ - Step 141005: {'lr': 4.5442802888477355e-06, 'samples': 27072960, 'steps': 141004, 'loss/train': 1.3194741010665894} 08/31/2021 14:50:14 - INFO - __main__ - Step 141006: {'lr': 4.543273126941749e-06, 'samples': 27073152, 'steps': 141005, 'loss/train': 1.0408365726470947} 08/31/2021 14:50:14 - INFO - __main__ - Step 141007: {'lr': 4.542266075634793e-06, 'samples': 27073344, 'steps': 141006, 'loss/train': 1.0546317100524902} 08/31/2021 14:50:14 - INFO - __main__ - Step 141008: {'lr': 4.541259134927284e-06, 'samples': 27073536, 'steps': 141007, 'loss/train': 0.04160531237721443} 08/31/2021 14:50:15 - INFO - __main__ - Step 141009: {'lr': 4.540252304819748e-06, 'samples': 27073728, 'steps': 141008, 'loss/train': 2.15923810005188} 08/31/2021 14:50:15 - INFO - __main__ - Step 141010: {'lr': 4.539245585312546e-06, 'samples': 27073920, 'steps': 141009, 'loss/train': 1.9607350826263428} 08/31/2021 14:50:15 - INFO - __main__ - Step 141011: {'lr': 4.5382389764061506e-06, 'samples': 27074112, 'steps': 141010, 'loss/train': 1.2152189016342163} 08/31/2021 14:50:17 - INFO - __main__ - Step 141012: {'lr': 4.537232478101061e-06, 'samples': 27074304, 'steps': 141011, 'loss/train': 0.016005661338567734} 08/31/2021 14:50:18 - INFO - __main__ - Step 141013: {'lr': 4.536226090397694e-06, 'samples': 27074496, 'steps': 141012, 'loss/train': 1.2695990800857544} 08/31/2021 14:50:18 - INFO - __main__ - Step 141014: {'lr': 4.535219813296521e-06, 'samples': 27074688, 'steps': 141013, 'loss/train': 1.0449873208999634} 08/31/2021 14:50:18 - INFO - __main__ - Step 141015: {'lr': 4.534213646798013e-06, 'samples': 27074880, 'steps': 141014, 'loss/train': 1.2181133031845093} 08/31/2021 14:50:19 - INFO - __main__ - Step 141016: {'lr': 4.533207590902561e-06, 'samples': 27075072, 'steps': 141015, 'loss/train': 0.8303196430206299} 08/31/2021 14:50:19 - INFO - __main__ - Step 141017: {'lr': 4.53220164561069e-06, 'samples': 27075264, 'steps': 141016, 'loss/train': 0.28265681862831116} 08/31/2021 14:50:21 - INFO - __main__ - Step 141018: {'lr': 4.531195810922817e-06, 'samples': 27075456, 'steps': 141017, 'loss/train': 0.6170482635498047} 08/31/2021 14:50:21 - INFO - __main__ - Step 141019: {'lr': 4.530190086839386e-06, 'samples': 27075648, 'steps': 141018, 'loss/train': 0.8296359777450562} 08/31/2021 14:50:21 - INFO - __main__ - Step 141020: {'lr': 4.5291844733608975e-06, 'samples': 27075840, 'steps': 141019, 'loss/train': 0.6571136116981506} 08/31/2021 14:50:22 - INFO - __main__ - Step 141021: {'lr': 4.52817897048774e-06, 'samples': 27076032, 'steps': 141020, 'loss/train': 1.295562744140625} 08/31/2021 14:50:22 - INFO - __main__ - Step 141022: {'lr': 4.527173578220384e-06, 'samples': 27076224, 'steps': 141021, 'loss/train': 0.8087058663368225} 08/31/2021 14:50:24 - INFO - __main__ - Step 141023: {'lr': 4.52616829655933e-06, 'samples': 27076416, 'steps': 141022, 'loss/train': 0.07715143263339996} 08/31/2021 14:50:24 - INFO - __main__ - Step 141024: {'lr': 4.525163125504967e-06, 'samples': 27076608, 'steps': 141023, 'loss/train': 1.1908320188522339} 08/31/2021 14:50:24 - INFO - __main__ - Step 141025: {'lr': 4.524158065057793e-06, 'samples': 27076800, 'steps': 141024, 'loss/train': 0.8546607494354248} 08/31/2021 14:50:25 - INFO - __main__ - Step 141026: {'lr': 4.523153115218226e-06, 'samples': 27076992, 'steps': 141025, 'loss/train': 1.0489252805709839} 08/31/2021 14:50:25 - INFO - __main__ - Step 141027: {'lr': 4.522148275986765e-06, 'samples': 27077184, 'steps': 141026, 'loss/train': 1.5732234716415405} 08/31/2021 14:50:27 - INFO - __main__ - Step 141028: {'lr': 4.521143547363826e-06, 'samples': 27077376, 'steps': 141027, 'loss/train': 1.6114412546157837} 08/31/2021 14:50:28 - INFO - __main__ - Step 141029: {'lr': 4.520138929349854e-06, 'samples': 27077568, 'steps': 141028, 'loss/train': 1.0550469160079956} 08/31/2021 14:50:28 - INFO - __main__ - Step 141030: {'lr': 4.519134421945348e-06, 'samples': 27077760, 'steps': 141029, 'loss/train': 0.060415416955947876} 08/31/2021 14:50:28 - INFO - __main__ - Step 141031: {'lr': 4.518130025150724e-06, 'samples': 27077952, 'steps': 141030, 'loss/train': 1.4417959451675415} 08/31/2021 14:50:29 - INFO - __main__ - Step 141032: {'lr': 4.517125738966455e-06, 'samples': 27078144, 'steps': 141031, 'loss/train': 0.758449137210846} 08/31/2021 14:50:31 - INFO - __main__ - Step 141033: {'lr': 4.516121563392955e-06, 'samples': 27078336, 'steps': 141032, 'loss/train': 1.4315303564071655} 08/31/2021 14:50:31 - INFO - __main__ - Step 141034: {'lr': 4.515117498430698e-06, 'samples': 27078528, 'steps': 141033, 'loss/train': 0.7445322275161743} 08/31/2021 14:50:32 - INFO - __main__ - Step 141035: {'lr': 4.514113544080156e-06, 'samples': 27078720, 'steps': 141034, 'loss/train': 0.07822960615158081} 08/31/2021 14:50:32 - INFO - __main__ - Step 141036: {'lr': 4.513109700341772e-06, 'samples': 27078912, 'steps': 141035, 'loss/train': 0.12128965556621552} 08/31/2021 14:50:32 - INFO - __main__ - Step 141037: {'lr': 4.5121059672159906e-06, 'samples': 27079104, 'steps': 141036, 'loss/train': 5.773097038269043} 08/31/2021 14:50:33 - INFO - __main__ - Step 141038: {'lr': 4.511102344703255e-06, 'samples': 27079296, 'steps': 141037, 'loss/train': 1.149479866027832} 08/31/2021 14:50:34 - INFO - __main__ - Step 141039: {'lr': 4.510098832804038e-06, 'samples': 27079488, 'steps': 141038, 'loss/train': 1.4017255306243896} 08/31/2021 14:50:35 - INFO - __main__ - Step 141040: {'lr': 4.509095431518784e-06, 'samples': 27079680, 'steps': 141039, 'loss/train': 1.1926130056381226} 08/31/2021 14:50:35 - INFO - __main__ - Step 141041: {'lr': 4.508092140847936e-06, 'samples': 27079872, 'steps': 141040, 'loss/train': 1.1718817949295044} 08/31/2021 14:50:35 - INFO - __main__ - Step 141042: {'lr': 4.507088960791967e-06, 'samples': 27080064, 'steps': 141041, 'loss/train': 0.13864639401435852} 08/31/2021 14:50:36 - INFO - __main__ - Step 141043: {'lr': 4.506085891351319e-06, 'samples': 27080256, 'steps': 141042, 'loss/train': 0.9606227874755859} 08/31/2021 14:50:37 - INFO - __main__ - Step 141044: {'lr': 4.505082932526411e-06, 'samples': 27080448, 'steps': 141043, 'loss/train': 0.07627184689044952} 08/31/2021 14:50:38 - INFO - __main__ - Step 141045: {'lr': 4.504080084317741e-06, 'samples': 27080640, 'steps': 141044, 'loss/train': 1.004162073135376} 08/31/2021 14:50:38 - INFO - __main__ - Step 141046: {'lr': 4.503077346725754e-06, 'samples': 27080832, 'steps': 141045, 'loss/train': 0.4123091995716095} 08/31/2021 14:50:38 - INFO - __main__ - Step 141047: {'lr': 4.502074719750865e-06, 'samples': 27081024, 'steps': 141046, 'loss/train': 1.2368932962417603} 08/31/2021 14:50:39 - INFO - __main__ - Step 141048: {'lr': 4.501072203393575e-06, 'samples': 27081216, 'steps': 141047, 'loss/train': 1.321123719215393} 08/31/2021 14:50:40 - INFO - __main__ - Step 141049: {'lr': 4.500069797654299e-06, 'samples': 27081408, 'steps': 141048, 'loss/train': 4.375753879547119} 08/31/2021 14:50:41 - INFO - __main__ - Step 141050: {'lr': 4.49906750253351e-06, 'samples': 27081600, 'steps': 141049, 'loss/train': 1.0354256629943848} 08/31/2021 14:50:41 - INFO - __main__ - Step 141051: {'lr': 4.498065318031652e-06, 'samples': 27081792, 'steps': 141050, 'loss/train': 1.01498544216156} 08/31/2021 14:50:41 - INFO - __main__ - Step 141052: {'lr': 4.497063244149196e-06, 'samples': 27081984, 'steps': 141051, 'loss/train': 1.1084978580474854} 08/31/2021 14:50:42 - INFO - __main__ - Step 141053: {'lr': 4.49606128088656e-06, 'samples': 27082176, 'steps': 141052, 'loss/train': 1.3224037885665894} 08/31/2021 14:50:43 - INFO - __main__ - Step 141054: {'lr': 4.495059428244213e-06, 'samples': 27082368, 'steps': 141053, 'loss/train': 1.358439326286316} 08/31/2021 14:50:44 - INFO - __main__ - Step 141055: {'lr': 4.494057686222603e-06, 'samples': 27082560, 'steps': 141054, 'loss/train': 0.8956875205039978} 08/31/2021 14:50:44 - INFO - __main__ - Step 141056: {'lr': 4.49305605482217e-06, 'samples': 27082752, 'steps': 141055, 'loss/train': 1.2187399864196777} 08/31/2021 14:50:44 - INFO - __main__ - Step 141057: {'lr': 4.492054534043389e-06, 'samples': 27082944, 'steps': 141056, 'loss/train': 1.6541465520858765} 08/31/2021 14:50:45 - INFO - __main__ - Step 141058: {'lr': 4.491053123886702e-06, 'samples': 27083136, 'steps': 141057, 'loss/train': 1.4359066486358643} 08/31/2021 14:50:45 - INFO - __main__ - Step 141059: {'lr': 4.490051824352553e-06, 'samples': 27083328, 'steps': 141058, 'loss/train': 2.1079869270324707} 08/31/2021 14:50:47 - INFO - __main__ - Step 141060: {'lr': 4.4890506354414165e-06, 'samples': 27083520, 'steps': 141059, 'loss/train': 1.7751133441925049} 08/31/2021 14:50:47 - INFO - __main__ - Step 141061: {'lr': 4.488049557153706e-06, 'samples': 27083712, 'steps': 141060, 'loss/train': 1.2179195880889893} 08/31/2021 14:50:48 - INFO - __main__ - Step 141062: {'lr': 4.4870485894898675e-06, 'samples': 27083904, 'steps': 141061, 'loss/train': 1.012152910232544} 08/31/2021 14:50:48 - INFO - __main__ - Step 141063: {'lr': 4.4860477324504265e-06, 'samples': 27084096, 'steps': 141062, 'loss/train': 0.3282642364501953} 08/31/2021 14:50:48 - INFO - __main__ - Step 141064: {'lr': 4.485046986035746e-06, 'samples': 27084288, 'steps': 141063, 'loss/train': 1.642612338066101} 08/31/2021 14:50:50 - INFO - __main__ - Step 141065: {'lr': 4.4840463502463235e-06, 'samples': 27084480, 'steps': 141064, 'loss/train': 0.7697109580039978} 08/31/2021 14:50:51 - INFO - __main__ - Step 141066: {'lr': 4.483045825082604e-06, 'samples': 27084672, 'steps': 141065, 'loss/train': 1.5200591087341309} 08/31/2021 14:50:51 - INFO - __main__ - Step 141067: {'lr': 4.48204541054506e-06, 'samples': 27084864, 'steps': 141066, 'loss/train': 0.8013108372688293} 08/31/2021 14:50:52 - INFO - __main__ - Step 141068: {'lr': 4.481045106634107e-06, 'samples': 27085056, 'steps': 141067, 'loss/train': 1.6022132635116577} 08/31/2021 14:50:52 - INFO - __main__ - Step 141069: {'lr': 4.48004491335019e-06, 'samples': 27085248, 'steps': 141068, 'loss/train': 0.728985071182251} 08/31/2021 14:50:53 - INFO - __main__ - Step 141070: {'lr': 4.479044830693779e-06, 'samples': 27085440, 'steps': 141069, 'loss/train': 0.26418593525886536} 08/31/2021 14:50:54 - INFO - __main__ - Step 141071: {'lr': 4.47804485866532e-06, 'samples': 27085632, 'steps': 141070, 'loss/train': 1.269403100013733} 08/31/2021 14:50:54 - INFO - __main__ - Step 141072: {'lr': 4.477044997265284e-06, 'samples': 27085824, 'steps': 141071, 'loss/train': 0.07739964127540588} 08/31/2021 14:50:55 - INFO - __main__ - Step 141073: {'lr': 4.476045246494087e-06, 'samples': 27086016, 'steps': 141072, 'loss/train': 0.8366784453392029} 08/31/2021 14:50:55 - INFO - __main__ - Step 141074: {'lr': 4.475045606352174e-06, 'samples': 27086208, 'steps': 141073, 'loss/train': 1.5043903589248657} 08/31/2021 14:50:56 - INFO - __main__ - Step 141075: {'lr': 4.474046076840044e-06, 'samples': 27086400, 'steps': 141074, 'loss/train': 1.2181987762451172} 08/31/2021 14:50:57 - INFO - __main__ - Step 141076: {'lr': 4.473046657958113e-06, 'samples': 27086592, 'steps': 141075, 'loss/train': 1.592395305633545} 08/31/2021 14:50:57 - INFO - __main__ - Step 141077: {'lr': 4.4720473497068535e-06, 'samples': 27086784, 'steps': 141076, 'loss/train': 1.13729727268219} 08/31/2021 14:50:58 - INFO - __main__ - Step 141078: {'lr': 4.471048152086682e-06, 'samples': 27086976, 'steps': 141077, 'loss/train': 0.9383643865585327} 08/31/2021 14:50:58 - INFO - __main__ - Step 141079: {'lr': 4.4700490650980695e-06, 'samples': 27087168, 'steps': 141078, 'loss/train': 0.295457661151886} 08/31/2021 14:50:58 - INFO - __main__ - Step 141080: {'lr': 4.469050088741461e-06, 'samples': 27087360, 'steps': 141079, 'loss/train': 0.33226630091667175} 08/31/2021 14:51:00 - INFO - __main__ - Step 141081: {'lr': 4.468051223017355e-06, 'samples': 27087552, 'steps': 141080, 'loss/train': 1.1811364889144897} 08/31/2021 14:51:00 - INFO - __main__ - Step 141082: {'lr': 4.467052467926114e-06, 'samples': 27087744, 'steps': 141081, 'loss/train': 0.8421888947486877} 08/31/2021 14:51:01 - INFO - __main__ - Step 141083: {'lr': 4.466053823468236e-06, 'samples': 27087936, 'steps': 141082, 'loss/train': 1.6961009502410889} 08/31/2021 14:51:01 - INFO - __main__ - Step 141084: {'lr': 4.465055289644166e-06, 'samples': 27088128, 'steps': 141083, 'loss/train': 1.2833454608917236} 08/31/2021 14:51:01 - INFO - __main__ - Step 141085: {'lr': 4.464056866454347e-06, 'samples': 27088320, 'steps': 141084, 'loss/train': 0.6708383560180664} 08/31/2021 14:51:03 - INFO - __main__ - Step 141086: {'lr': 4.463058553899224e-06, 'samples': 27088512, 'steps': 141085, 'loss/train': 1.2529865503311157} 08/31/2021 14:51:03 - INFO - __main__ - Step 141087: {'lr': 4.462060351979297e-06, 'samples': 27088704, 'steps': 141086, 'loss/train': 1.3180687427520752} 08/31/2021 14:51:04 - INFO - __main__ - Step 141088: {'lr': 4.4610622606949535e-06, 'samples': 27088896, 'steps': 141087, 'loss/train': 1.1497329473495483} 08/31/2021 14:51:04 - INFO - __main__ - Step 141089: {'lr': 4.460064280046666e-06, 'samples': 27089088, 'steps': 141088, 'loss/train': 0.06898976117372513} 08/31/2021 14:51:04 - INFO - __main__ - Step 141090: {'lr': 4.459066410034878e-06, 'samples': 27089280, 'steps': 141089, 'loss/train': 1.283292293548584} 08/31/2021 14:51:06 - INFO - __main__ - Step 141091: {'lr': 4.458068650660035e-06, 'samples': 27089472, 'steps': 141090, 'loss/train': 1.2947943210601807} 08/31/2021 14:51:07 - INFO - __main__ - Step 141092: {'lr': 4.457071001922636e-06, 'samples': 27089664, 'steps': 141091, 'loss/train': 1.2831774950027466} 08/31/2021 14:51:07 - INFO - __main__ - Step 141093: {'lr': 4.456073463823068e-06, 'samples': 27089856, 'steps': 141092, 'loss/train': 1.2903467416763306} 08/31/2021 14:51:07 - INFO - __main__ - Step 141094: {'lr': 4.455076036361805e-06, 'samples': 27090048, 'steps': 141093, 'loss/train': 1.111589789390564} 08/31/2021 14:51:08 - INFO - __main__ - Step 141095: {'lr': 4.4540787195393176e-06, 'samples': 27090240, 'steps': 141094, 'loss/train': 0.7218812704086304} 08/31/2021 14:51:09 - INFO - __main__ - Step 141096: {'lr': 4.453081513355994e-06, 'samples': 27090432, 'steps': 141095, 'loss/train': 1.4780023097991943} 08/31/2021 14:51:09 - INFO - __main__ - Step 141097: {'lr': 4.452084417812363e-06, 'samples': 27090624, 'steps': 141096, 'loss/train': 1.57658851146698} 08/31/2021 14:51:10 - INFO - __main__ - Step 141098: {'lr': 4.451087432908813e-06, 'samples': 27090816, 'steps': 141097, 'loss/train': 0.5405750274658203} 08/31/2021 14:51:10 - INFO - __main__ - Step 141099: {'lr': 4.450090558645814e-06, 'samples': 27091008, 'steps': 141098, 'loss/train': 1.0182610750198364} 08/31/2021 14:51:10 - INFO - __main__ - Step 141100: {'lr': 4.449093795023812e-06, 'samples': 27091200, 'steps': 141099, 'loss/train': 1.9218451976776123} 08/31/2021 14:51:12 - INFO - __main__ - Step 141101: {'lr': 4.44809714204325e-06, 'samples': 27091392, 'steps': 141100, 'loss/train': 1.0760444402694702} 08/31/2021 14:51:12 - INFO - __main__ - Step 141102: {'lr': 4.447100599704601e-06, 'samples': 27091584, 'steps': 141101, 'loss/train': 1.2441073656082153} 08/31/2021 14:51:13 - INFO - __main__ - Step 141103: {'lr': 4.446104168008308e-06, 'samples': 27091776, 'steps': 141102, 'loss/train': 5.223979473114014} 08/31/2021 14:51:13 - INFO - __main__ - Step 141104: {'lr': 4.445107846954788e-06, 'samples': 27091968, 'steps': 141103, 'loss/train': 1.263791799545288} 08/31/2021 14:51:14 - INFO - __main__ - Step 141105: {'lr': 4.444111636544512e-06, 'samples': 27092160, 'steps': 141104, 'loss/train': 1.288417100906372} 08/31/2021 14:51:14 - INFO - __main__ - Step 141106: {'lr': 4.443115536777953e-06, 'samples': 27092352, 'steps': 141105, 'loss/train': 0.5865541100502014} 08/31/2021 14:51:15 - INFO - __main__ - Step 141107: {'lr': 4.4421195476555265e-06, 'samples': 27092544, 'steps': 141106, 'loss/train': 1.0200474262237549} 08/31/2021 14:51:16 - INFO - __main__ - Step 141108: {'lr': 4.441123669177705e-06, 'samples': 27092736, 'steps': 141107, 'loss/train': 0.5371925234794617} 08/31/2021 14:51:16 - INFO - __main__ - Step 141109: {'lr': 4.440127901344932e-06, 'samples': 27092928, 'steps': 141108, 'loss/train': 1.0266358852386475} 08/31/2021 14:51:17 - INFO - __main__ - Step 141110: {'lr': 4.4391322441576236e-06, 'samples': 27093120, 'steps': 141109, 'loss/train': 1.6365195512771606} 08/31/2021 14:51:17 - INFO - __main__ - Step 141111: {'lr': 4.4381366976162516e-06, 'samples': 27093312, 'steps': 141110, 'loss/train': 0.8128007054328918} 08/31/2021 14:51:19 - INFO - __main__ - Step 141112: {'lr': 4.437141261721261e-06, 'samples': 27093504, 'steps': 141111, 'loss/train': 0.9043404459953308} 08/31/2021 14:51:19 - INFO - __main__ - Step 141113: {'lr': 4.436145936473124e-06, 'samples': 27093696, 'steps': 141112, 'loss/train': 0.02770821563899517} 08/31/2021 14:51:20 - INFO - __main__ - Step 141114: {'lr': 4.435150721872256e-06, 'samples': 27093888, 'steps': 141113, 'loss/train': 0.8150171637535095} 08/31/2021 14:51:20 - INFO - __main__ - Step 141115: {'lr': 4.434155617919127e-06, 'samples': 27094080, 'steps': 141114, 'loss/train': 0.45267927646636963} 08/31/2021 14:51:20 - INFO - __main__ - Step 141116: {'lr': 4.433160624614185e-06, 'samples': 27094272, 'steps': 141115, 'loss/train': 1.0491018295288086} 08/31/2021 14:51:22 - INFO - __main__ - Step 141117: {'lr': 4.432165741957872e-06, 'samples': 27094464, 'steps': 141116, 'loss/train': 1.4011064767837524} 08/31/2021 14:51:23 - INFO - __main__ - Step 141118: {'lr': 4.431170969950632e-06, 'samples': 27094656, 'steps': 141117, 'loss/train': 1.3114745616912842} 08/31/2021 14:51:23 - INFO - __main__ - Step 141119: {'lr': 4.430176308592909e-06, 'samples': 27094848, 'steps': 141118, 'loss/train': 1.1743574142456055} 08/31/2021 14:51:24 - INFO - __main__ - Step 141120: {'lr': 4.429181757885148e-06, 'samples': 27095040, 'steps': 141119, 'loss/train': 1.036980390548706} 08/31/2021 14:51:24 - INFO - __main__ - Step 141121: {'lr': 4.4281873178278475e-06, 'samples': 27095232, 'steps': 141120, 'loss/train': 0.9894956946372986} 08/31/2021 14:51:26 - INFO - __main__ - Step 141122: {'lr': 4.4271929884213965e-06, 'samples': 27095424, 'steps': 141121, 'loss/train': 0.6887061595916748} 08/31/2021 14:51:26 - INFO - __main__ - Step 141123: {'lr': 4.42619876966624e-06, 'samples': 27095616, 'steps': 141122, 'loss/train': 0.8423025608062744} 08/31/2021 14:51:26 - INFO - __main__ - Step 141124: {'lr': 4.425204661562876e-06, 'samples': 27095808, 'steps': 141123, 'loss/train': 1.3778084516525269} 08/31/2021 14:51:27 - INFO - __main__ - Step 141125: {'lr': 4.424210664111722e-06, 'samples': 27096000, 'steps': 141124, 'loss/train': 1.8328224420547485} 08/31/2021 14:51:27 - INFO - __main__ - Step 141126: {'lr': 4.423216777313221e-06, 'samples': 27096192, 'steps': 141125, 'loss/train': 1.1849582195281982} 08/31/2021 14:51:28 - INFO - __main__ - Step 141127: {'lr': 4.422223001167819e-06, 'samples': 27096384, 'steps': 141126, 'loss/train': 0.9250072836875916} 08/31/2021 14:51:29 - INFO - __main__ - Step 141128: {'lr': 4.421229335675986e-06, 'samples': 27096576, 'steps': 141127, 'loss/train': 1.3993276357650757} 08/31/2021 14:51:29 - INFO - __main__ - Step 141129: {'lr': 4.4202357808381664e-06, 'samples': 27096768, 'steps': 141128, 'loss/train': 0.22055020928382874} 08/31/2021 14:51:30 - INFO - __main__ - Step 141130: {'lr': 4.419242336654805e-06, 'samples': 27096960, 'steps': 141129, 'loss/train': 0.3628990948200226} 08/31/2021 14:51:30 - INFO - __main__ - Step 141131: {'lr': 4.4182490031263175e-06, 'samples': 27097152, 'steps': 141130, 'loss/train': 0.6240267157554626} 08/31/2021 14:51:30 - INFO - __main__ - Step 141132: {'lr': 4.4172557802532046e-06, 'samples': 27097344, 'steps': 141131, 'loss/train': 0.7416526675224304} 08/31/2021 14:51:32 - INFO - __main__ - Step 141133: {'lr': 4.416262668035853e-06, 'samples': 27097536, 'steps': 141132, 'loss/train': 1.3691916465759277} 08/31/2021 14:51:32 - INFO - __main__ - Step 141134: {'lr': 4.415269666474763e-06, 'samples': 27097728, 'steps': 141133, 'loss/train': 1.0431135892868042} 08/31/2021 14:51:33 - INFO - __main__ - Step 141135: {'lr': 4.4142767755703805e-06, 'samples': 27097920, 'steps': 141134, 'loss/train': 1.2659457921981812} 08/31/2021 14:51:33 - INFO - __main__ - Step 141136: {'lr': 4.41328399532312e-06, 'samples': 27098112, 'steps': 141135, 'loss/train': 0.9859736561775208} 08/31/2021 14:51:33 - INFO - __main__ - Step 141137: {'lr': 4.412291325733453e-06, 'samples': 27098304, 'steps': 141136, 'loss/train': 0.6506534218788147} 08/31/2021 14:51:35 - INFO - __main__ - Step 141138: {'lr': 4.411298766801797e-06, 'samples': 27098496, 'steps': 141137, 'loss/train': 0.8495778441429138} 08/31/2021 14:51:35 - INFO - __main__ - Step 141139: {'lr': 4.410306318528623e-06, 'samples': 27098688, 'steps': 141138, 'loss/train': 0.40480536222457886} 08/31/2021 14:51:36 - INFO - __main__ - Step 141140: {'lr': 4.409313980914376e-06, 'samples': 27098880, 'steps': 141139, 'loss/train': 1.107026219367981} 08/31/2021 14:51:36 - INFO - __main__ - Step 141141: {'lr': 4.408321753959527e-06, 'samples': 27099072, 'steps': 141140, 'loss/train': 0.5972416400909424} 08/31/2021 14:51:37 - INFO - __main__ - Step 141142: {'lr': 4.407329637664464e-06, 'samples': 27099264, 'steps': 141141, 'loss/train': 0.6579991579055786} 08/31/2021 14:51:38 - INFO - __main__ - Step 141143: {'lr': 4.406337632029689e-06, 'samples': 27099456, 'steps': 141142, 'loss/train': 0.05329102650284767} 08/31/2021 14:51:39 - INFO - __main__ - Step 141144: {'lr': 4.405345737055616e-06, 'samples': 27099648, 'steps': 141143, 'loss/train': 1.3092769384384155} 08/31/2021 14:51:39 - INFO - __main__ - Step 141145: {'lr': 4.404353952742718e-06, 'samples': 27099840, 'steps': 141144, 'loss/train': 1.7133381366729736} 08/31/2021 14:51:40 - INFO - __main__ - Step 141146: {'lr': 4.403362279091411e-06, 'samples': 27100032, 'steps': 141145, 'loss/train': 0.543860137462616} 08/31/2021 14:51:40 - INFO - __main__ - Step 141147: {'lr': 4.402370716102166e-06, 'samples': 27100224, 'steps': 141146, 'loss/train': 0.014080190099775791} 08/31/2021 14:51:40 - INFO - __main__ - Step 141148: {'lr': 4.401379263775457e-06, 'samples': 27100416, 'steps': 141147, 'loss/train': 1.4593490362167358} 08/31/2021 14:51:42 - INFO - __main__ - Step 141149: {'lr': 4.4003879221116706e-06, 'samples': 27100608, 'steps': 141148, 'loss/train': 1.237977385520935} 08/31/2021 14:51:42 - INFO - __main__ - Step 141150: {'lr': 4.3993966911112795e-06, 'samples': 27100800, 'steps': 141149, 'loss/train': 1.0407068729400635} 08/31/2021 14:51:43 - INFO - __main__ - Step 141151: {'lr': 4.3984055707747274e-06, 'samples': 27100992, 'steps': 141150, 'loss/train': 0.768760621547699} 08/31/2021 14:51:43 - INFO - __main__ - Step 141152: {'lr': 4.397414561102458e-06, 'samples': 27101184, 'steps': 141151, 'loss/train': 0.2572074830532074} 08/31/2021 14:51:43 - INFO - __main__ - Step 141153: {'lr': 4.396423662094917e-06, 'samples': 27101376, 'steps': 141152, 'loss/train': 0.6117766499519348} 08/31/2021 14:51:45 - INFO - __main__ - Step 141154: {'lr': 4.395432873752575e-06, 'samples': 27101568, 'steps': 141153, 'loss/train': 1.2039663791656494} 08/31/2021 14:51:46 - INFO - __main__ - Step 141155: {'lr': 4.394442196075848e-06, 'samples': 27101760, 'steps': 141154, 'loss/train': 1.1416125297546387} 08/31/2021 14:51:46 - INFO - __main__ - Step 141156: {'lr': 4.393451629065209e-06, 'samples': 27101952, 'steps': 141155, 'loss/train': 1.552101492881775} 08/31/2021 14:51:46 - INFO - __main__ - Step 141157: {'lr': 4.392461172721074e-06, 'samples': 27102144, 'steps': 141156, 'loss/train': 0.9841805100440979} 08/31/2021 14:51:47 - INFO - __main__ - Step 141158: {'lr': 4.391470827043942e-06, 'samples': 27102336, 'steps': 141157, 'loss/train': 0.9485619068145752} 08/31/2021 14:51:47 - INFO - __main__ - Step 141159: {'lr': 4.390480592034174e-06, 'samples': 27102528, 'steps': 141158, 'loss/train': 1.127893090248108} 08/31/2021 14:51:49 - INFO - __main__ - Step 141160: {'lr': 4.389490467692297e-06, 'samples': 27102720, 'steps': 141159, 'loss/train': 0.23853246867656708} 08/31/2021 14:51:50 - INFO - __main__ - Step 141161: {'lr': 4.388500454018729e-06, 'samples': 27102912, 'steps': 141160, 'loss/train': 0.01409537810832262} 08/31/2021 14:51:50 - INFO - __main__ - Step 141162: {'lr': 4.387510551013912e-06, 'samples': 27103104, 'steps': 141161, 'loss/train': 1.2645677328109741} 08/31/2021 14:51:50 - INFO - __main__ - Step 141163: {'lr': 4.386520758678292e-06, 'samples': 27103296, 'steps': 141162, 'loss/train': 0.9189597964286804} 08/31/2021 14:51:51 - INFO - __main__ - Step 141164: {'lr': 4.385531077012311e-06, 'samples': 27103488, 'steps': 141163, 'loss/train': 0.3238820731639862} 08/31/2021 14:51:51 - INFO - __main__ - Step 141165: {'lr': 4.384541506016415e-06, 'samples': 27103680, 'steps': 141164, 'loss/train': 0.9055489897727966} 08/31/2021 14:51:52 - INFO - __main__ - Step 141166: {'lr': 4.383552045691047e-06, 'samples': 27103872, 'steps': 141165, 'loss/train': 1.0484614372253418} 08/31/2021 14:51:53 - INFO - __main__ - Step 141167: {'lr': 4.3825626960366515e-06, 'samples': 27104064, 'steps': 141166, 'loss/train': 1.6606676578521729} 08/31/2021 14:51:53 - INFO - __main__ - Step 141168: {'lr': 4.3815734570537005e-06, 'samples': 27104256, 'steps': 141167, 'loss/train': 1.4963387250900269} 08/31/2021 14:51:54 - INFO - __main__ - Step 141169: {'lr': 4.380584328742637e-06, 'samples': 27104448, 'steps': 141168, 'loss/train': 1.4330400228500366} 08/31/2021 14:51:54 - INFO - __main__ - Step 141170: {'lr': 4.379595311103879e-06, 'samples': 27104640, 'steps': 141169, 'loss/train': 1.139687418937683} 08/31/2021 14:51:56 - INFO - __main__ - Step 141171: {'lr': 4.378606404137869e-06, 'samples': 27104832, 'steps': 141170, 'loss/train': 0.8795386552810669} 08/31/2021 14:51:56 - INFO - __main__ - Step 141172: {'lr': 4.37761760784508e-06, 'samples': 27105024, 'steps': 141171, 'loss/train': 2.1843907833099365} 08/31/2021 14:51:57 - INFO - __main__ - Step 141173: {'lr': 4.376628922225956e-06, 'samples': 27105216, 'steps': 141172, 'loss/train': 1.457844853401184} 08/31/2021 14:51:57 - INFO - __main__ - Step 141174: {'lr': 4.3756403472809126e-06, 'samples': 27105408, 'steps': 141173, 'loss/train': 2.4076077938079834} 08/31/2021 14:51:57 - INFO - __main__ - Step 141175: {'lr': 4.37465188301045e-06, 'samples': 27105600, 'steps': 141174, 'loss/train': 0.03930472955107689} 08/31/2021 14:51:59 - INFO - __main__ - Step 141176: {'lr': 4.373663529414957e-06, 'samples': 27105792, 'steps': 141175, 'loss/train': 1.2127485275268555} 08/31/2021 14:52:00 - INFO - __main__ - Step 141177: {'lr': 4.3726752864949036e-06, 'samples': 27105984, 'steps': 141176, 'loss/train': 1.1355706453323364} 08/31/2021 14:52:00 - INFO - __main__ - Step 141178: {'lr': 4.371687154250737e-06, 'samples': 27106176, 'steps': 141177, 'loss/train': 1.2112809419631958} 08/31/2021 14:52:01 - INFO - __main__ - Step 141179: {'lr': 4.3706991326828985e-06, 'samples': 27106368, 'steps': 141178, 'loss/train': 0.12790444493293762} 08/31/2021 14:52:01 - INFO - __main__ - Step 141180: {'lr': 4.369711221791805e-06, 'samples': 27106560, 'steps': 141179, 'loss/train': 0.8781802654266357} 08/31/2021 14:52:01 - INFO - __main__ - Step 141181: {'lr': 4.368723421577958e-06, 'samples': 27106752, 'steps': 141180, 'loss/train': 1.4488838911056519} 08/31/2021 14:52:03 - INFO - __main__ - Step 141182: {'lr': 4.3677357320417724e-06, 'samples': 27106944, 'steps': 141181, 'loss/train': 1.1442662477493286} 08/31/2021 14:52:03 - INFO - __main__ - Step 141183: {'lr': 4.3667481531836915e-06, 'samples': 27107136, 'steps': 141182, 'loss/train': 1.301494836807251} 08/31/2021 14:52:04 - INFO - __main__ - Step 141184: {'lr': 4.365760685004161e-06, 'samples': 27107328, 'steps': 141183, 'loss/train': 1.2189503908157349} 08/31/2021 14:52:04 - INFO - __main__ - Step 141185: {'lr': 4.364773327503624e-06, 'samples': 27107520, 'steps': 141184, 'loss/train': 1.9081752300262451} 08/31/2021 14:52:04 - INFO - __main__ - Step 141186: {'lr': 4.363786080682525e-06, 'samples': 27107712, 'steps': 141185, 'loss/train': 0.9271516799926758} 08/31/2021 14:52:06 - INFO - __main__ - Step 141187: {'lr': 4.362798944541308e-06, 'samples': 27107904, 'steps': 141186, 'loss/train': 0.7196524739265442} 08/31/2021 14:52:06 - INFO - __main__ - Step 141188: {'lr': 4.3618119190804716e-06, 'samples': 27108096, 'steps': 141187, 'loss/train': 0.38192781805992126} 08/31/2021 14:52:07 - INFO - __main__ - Step 141189: {'lr': 4.3608250043003785e-06, 'samples': 27108288, 'steps': 141188, 'loss/train': 1.3293606042861938} 08/31/2021 14:52:07 - INFO - __main__ - Step 141190: {'lr': 4.359838200201499e-06, 'samples': 27108480, 'steps': 141189, 'loss/train': 0.7512024641036987} 08/31/2021 14:52:07 - INFO - __main__ - Step 141191: {'lr': 4.358851506784306e-06, 'samples': 27108672, 'steps': 141190, 'loss/train': 0.548117995262146} 08/31/2021 14:52:09 - INFO - __main__ - Step 141192: {'lr': 4.357864924049188e-06, 'samples': 27108864, 'steps': 141191, 'loss/train': 0.49954965710639954} 08/31/2021 14:52:09 - INFO - __main__ - Step 141193: {'lr': 4.356878451996671e-06, 'samples': 27109056, 'steps': 141192, 'loss/train': 0.9129343032836914} 08/31/2021 14:52:10 - INFO - __main__ - Step 141194: {'lr': 4.355892090627117e-06, 'samples': 27109248, 'steps': 141193, 'loss/train': 1.4709184169769287} 08/31/2021 14:52:10 - INFO - __main__ - Step 141195: {'lr': 4.354905839941026e-06, 'samples': 27109440, 'steps': 141194, 'loss/train': 1.1592011451721191} 08/31/2021 14:52:11 - INFO - __main__ - Step 141196: {'lr': 4.353919699938813e-06, 'samples': 27109632, 'steps': 141195, 'loss/train': 0.8154640793800354} 08/31/2021 14:52:12 - INFO - __main__ - Step 141197: {'lr': 4.352933670620951e-06, 'samples': 27109824, 'steps': 141196, 'loss/train': 0.07863740622997284} 08/31/2021 14:52:13 - INFO - __main__ - Step 141198: {'lr': 4.3519477519878555e-06, 'samples': 27110016, 'steps': 141197, 'loss/train': 0.7353177666664124} 08/31/2021 14:52:13 - INFO - __main__ - Step 141199: {'lr': 4.350961944039972e-06, 'samples': 27110208, 'steps': 141198, 'loss/train': 0.09600857645273209} 08/31/2021 14:52:13 - INFO - __main__ - Step 141200: {'lr': 4.3499762467777705e-06, 'samples': 27110400, 'steps': 141199, 'loss/train': 1.1824777126312256} 08/31/2021 14:52:14 - INFO - __main__ - Step 141201: {'lr': 4.348990660201668e-06, 'samples': 27110592, 'steps': 141200, 'loss/train': 1.178285002708435} 08/31/2021 14:52:16 - INFO - __main__ - Step 141202: {'lr': 4.3480051843121374e-06, 'samples': 27110784, 'steps': 141201, 'loss/train': 0.03898722678422928} 08/31/2021 14:52:16 - INFO - __main__ - Step 141203: {'lr': 4.347019819109593e-06, 'samples': 27110976, 'steps': 141202, 'loss/train': 0.07194752991199493} 08/31/2021 14:52:16 - INFO - __main__ - Step 141204: {'lr': 4.346034564594509e-06, 'samples': 27111168, 'steps': 141203, 'loss/train': 0.5975526571273804} 08/31/2021 14:52:17 - INFO - __main__ - Step 141205: {'lr': 4.345049420767272e-06, 'samples': 27111360, 'steps': 141204, 'loss/train': 1.2273215055465698} 08/31/2021 14:52:17 - INFO - __main__ - Step 141206: {'lr': 4.3440643876284105e-06, 'samples': 27111552, 'steps': 141205, 'loss/train': 0.059948425740003586} 08/31/2021 14:52:18 - INFO - __main__ - Step 141207: {'lr': 4.343079465178285e-06, 'samples': 27111744, 'steps': 141206, 'loss/train': 1.511428713798523} 08/31/2021 14:52:19 - INFO - __main__ - Step 141208: {'lr': 4.342094653417394e-06, 'samples': 27111936, 'steps': 141207, 'loss/train': 0.5198903679847717} 08/31/2021 14:52:19 - INFO - __main__ - Step 141209: {'lr': 4.3411099523461565e-06, 'samples': 27112128, 'steps': 141208, 'loss/train': 0.3539642095565796} 08/31/2021 14:52:20 - INFO - __main__ - Step 141210: {'lr': 4.340125361965014e-06, 'samples': 27112320, 'steps': 141209, 'loss/train': 1.522951602935791} 08/31/2021 14:52:20 - INFO - __main__ - Step 141211: {'lr': 4.339140882274439e-06, 'samples': 27112512, 'steps': 141210, 'loss/train': 1.0901095867156982} 08/31/2021 14:52:20 - INFO - __main__ - Step 141212: {'lr': 4.338156513274849e-06, 'samples': 27112704, 'steps': 141211, 'loss/train': 0.8391990661621094} 08/31/2021 14:52:22 - INFO - __main__ - Step 141213: {'lr': 4.3371722549667146e-06, 'samples': 27112896, 'steps': 141212, 'loss/train': 1.5573575496673584} 08/31/2021 14:52:23 - INFO - __main__ - Step 141214: {'lr': 4.336188107350425e-06, 'samples': 27113088, 'steps': 141213, 'loss/train': 1.2192933559417725} 08/31/2021 14:52:23 - INFO - __main__ - Step 141215: {'lr': 4.3352040704265075e-06, 'samples': 27113280, 'steps': 141214, 'loss/train': 0.5021848082542419} 08/31/2021 14:52:23 - INFO - __main__ - Step 141216: {'lr': 4.334220144195323e-06, 'samples': 27113472, 'steps': 141215, 'loss/train': 0.025847697630524635} 08/31/2021 14:52:24 - INFO - __main__ - Step 141217: {'lr': 4.3332363286573415e-06, 'samples': 27113664, 'steps': 141216, 'loss/train': 0.12053272873163223} 08/31/2021 14:52:25 - INFO - __main__ - Step 141218: {'lr': 4.332252623813038e-06, 'samples': 27113856, 'steps': 141217, 'loss/train': 1.270939588546753} 08/31/2021 14:52:26 - INFO - __main__ - Step 141219: {'lr': 4.331269029662799e-06, 'samples': 27114048, 'steps': 141218, 'loss/train': 0.3511464595794678} 08/31/2021 14:52:26 - INFO - __main__ - Step 141220: {'lr': 4.330285546207125e-06, 'samples': 27114240, 'steps': 141219, 'loss/train': 0.25882747769355774} 08/31/2021 14:52:26 - INFO - __main__ - Step 141221: {'lr': 4.329302173446404e-06, 'samples': 27114432, 'steps': 141220, 'loss/train': 1.0333397388458252} 08/31/2021 14:52:27 - INFO - __main__ - Step 141222: {'lr': 4.3283189113811346e-06, 'samples': 27114624, 'steps': 141221, 'loss/train': 1.1507946252822876} 08/31/2021 14:52:28 - INFO - __main__ - Step 141223: {'lr': 4.327335760011736e-06, 'samples': 27114816, 'steps': 141222, 'loss/train': 0.8844454288482666} 08/31/2021 14:52:29 - INFO - __main__ - Step 141224: {'lr': 4.326352719338622e-06, 'samples': 27115008, 'steps': 141223, 'loss/train': 0.8552819490432739} 08/31/2021 14:52:29 - INFO - __main__ - Step 141225: {'lr': 4.3253697893622935e-06, 'samples': 27115200, 'steps': 141224, 'loss/train': 1.5375787019729614} 08/31/2021 14:52:30 - INFO - __main__ - Step 141226: {'lr': 4.324386970083138e-06, 'samples': 27115392, 'steps': 141225, 'loss/train': 1.0130410194396973} 08/31/2021 14:52:30 - INFO - __main__ - Step 141227: {'lr': 4.323404261501629e-06, 'samples': 27115584, 'steps': 141226, 'loss/train': 0.8651288747787476} 08/31/2021 14:52:32 - INFO - __main__ - Step 141228: {'lr': 4.322421663618209e-06, 'samples': 27115776, 'steps': 141227, 'loss/train': 0.9313284754753113} 08/31/2021 14:52:32 - INFO - __main__ - Step 141229: {'lr': 4.32143917643335e-06, 'samples': 27115968, 'steps': 141228, 'loss/train': 1.2969284057617188} 08/31/2021 14:52:33 - INFO - __main__ - Step 141230: {'lr': 4.320456799947414e-06, 'samples': 27116160, 'steps': 141229, 'loss/train': 0.4823984205722809} 08/31/2021 14:52:33 - INFO - __main__ - Step 141231: {'lr': 4.3194745341609e-06, 'samples': 27116352, 'steps': 141230, 'loss/train': 0.9857112169265747} 08/31/2021 14:52:33 - INFO - __main__ - Step 141232: {'lr': 4.318492379074224e-06, 'samples': 27116544, 'steps': 141231, 'loss/train': 1.274318814277649} 08/31/2021 14:52:35 - INFO - __main__ - Step 141233: {'lr': 4.317510334687858e-06, 'samples': 27116736, 'steps': 141232, 'loss/train': 1.0969446897506714} 08/31/2021 14:52:36 - INFO - __main__ - Step 141234: {'lr': 4.316528401002246e-06, 'samples': 27116928, 'steps': 141233, 'loss/train': 0.889795184135437} 08/31/2021 14:52:36 - INFO - __main__ - Step 141235: {'lr': 4.3155465780177765e-06, 'samples': 27117120, 'steps': 141234, 'loss/train': 1.1093920469284058} 08/31/2021 14:52:37 - INFO - __main__ - Step 141236: {'lr': 4.3145648657349765e-06, 'samples': 27117312, 'steps': 141235, 'loss/train': 0.9891477227210999} 08/31/2021 14:52:37 - INFO - __main__ - Step 141237: {'lr': 4.313583264154208e-06, 'samples': 27117504, 'steps': 141236, 'loss/train': 1.0153542757034302} 08/31/2021 14:52:37 - INFO - __main__ - Step 141238: {'lr': 4.3126017732759705e-06, 'samples': 27117696, 'steps': 141237, 'loss/train': 0.7976195216178894} 08/31/2021 14:52:39 - INFO - __main__ - Step 141239: {'lr': 4.311620393100651e-06, 'samples': 27117888, 'steps': 141238, 'loss/train': 0.9956954121589661} 08/31/2021 14:52:39 - INFO - __main__ - Step 141240: {'lr': 4.310639123628751e-06, 'samples': 27118080, 'steps': 141239, 'loss/train': 1.2206896543502808} 08/31/2021 14:52:40 - INFO - __main__ - Step 141241: {'lr': 4.309657964860686e-06, 'samples': 27118272, 'steps': 141240, 'loss/train': 1.1503506898880005} 08/31/2021 14:52:40 - INFO - __main__ - Step 141242: {'lr': 4.3086769167969e-06, 'samples': 27118464, 'steps': 141241, 'loss/train': 1.1621736288070679} 08/31/2021 14:52:40 - INFO - __main__ - Step 141243: {'lr': 4.307695979437837e-06, 'samples': 27118656, 'steps': 141242, 'loss/train': 1.3977956771850586} 08/31/2021 14:52:42 - INFO - __main__ - Step 141244: {'lr': 4.3067151527839134e-06, 'samples': 27118848, 'steps': 141243, 'loss/train': 0.67387455701828} 08/31/2021 14:52:42 - INFO - __main__ - Step 141245: {'lr': 4.305734436835601e-06, 'samples': 27119040, 'steps': 141244, 'loss/train': 1.34747314453125} 08/31/2021 14:52:43 - INFO - __main__ - Step 141246: {'lr': 4.304753831593345e-06, 'samples': 27119232, 'steps': 141245, 'loss/train': 1.1700059175491333} 08/31/2021 14:52:43 - INFO - __main__ - Step 141247: {'lr': 4.30377333705756e-06, 'samples': 27119424, 'steps': 141246, 'loss/train': 1.0990265607833862} 08/31/2021 14:52:43 - INFO - __main__ - Step 141248: {'lr': 4.302792953228718e-06, 'samples': 27119616, 'steps': 141247, 'loss/train': 0.2683170437812805} 08/31/2021 14:52:45 - INFO - __main__ - Step 141249: {'lr': 4.301812680107208e-06, 'samples': 27119808, 'steps': 141248, 'loss/train': 1.0076290369033813} 08/31/2021 14:52:46 - INFO - __main__ - Step 141250: {'lr': 4.3008325176935596e-06, 'samples': 27120000, 'steps': 141249, 'loss/train': 1.0583654642105103} 08/31/2021 14:52:46 - INFO - __main__ - Step 141251: {'lr': 4.29985246598813e-06, 'samples': 27120192, 'steps': 141250, 'loss/train': 0.9489544630050659} 08/31/2021 14:52:46 - INFO - __main__ - Step 141252: {'lr': 4.298872524991421e-06, 'samples': 27120384, 'steps': 141251, 'loss/train': 1.190711259841919} 08/31/2021 14:52:47 - INFO - __main__ - Step 141253: {'lr': 4.29789269470382e-06, 'samples': 27120576, 'steps': 141252, 'loss/train': 0.26336073875427246} 08/31/2021 14:52:47 - INFO - __main__ - Step 141254: {'lr': 4.296912975125827e-06, 'samples': 27120768, 'steps': 141253, 'loss/train': 1.702317714691162} 08/31/2021 14:52:48 - INFO - __main__ - Step 141255: {'lr': 4.295933366257832e-06, 'samples': 27120960, 'steps': 141254, 'loss/train': 0.27711185812950134} 08/31/2021 14:52:49 - INFO - __main__ - Step 141256: {'lr': 4.294953868100332e-06, 'samples': 27121152, 'steps': 141255, 'loss/train': 1.3380368947982788} 08/31/2021 14:52:49 - INFO - __main__ - Step 141257: {'lr': 4.293974480653718e-06, 'samples': 27121344, 'steps': 141256, 'loss/train': 0.3848628103733063} 08/31/2021 14:52:50 - INFO - __main__ - Step 141258: {'lr': 4.292995203918432e-06, 'samples': 27121536, 'steps': 141257, 'loss/train': 1.1333311796188354} 08/31/2021 14:52:50 - INFO - __main__ - Step 141259: {'lr': 4.292016037894919e-06, 'samples': 27121728, 'steps': 141258, 'loss/train': 1.0844718217849731} 08/31/2021 14:52:51 - INFO - __main__ - Step 141260: {'lr': 4.291036982583651e-06, 'samples': 27121920, 'steps': 141259, 'loss/train': 0.8511685729026794} 08/31/2021 14:52:52 - INFO - __main__ - Step 141261: {'lr': 4.290058037985045e-06, 'samples': 27122112, 'steps': 141260, 'loss/train': 0.7345431447029114} 08/31/2021 14:52:52 - INFO - __main__ - Step 141262: {'lr': 4.289079204099572e-06, 'samples': 27122304, 'steps': 141261, 'loss/train': 1.07416832447052} 08/31/2021 14:52:53 - INFO - __main__ - Step 141263: {'lr': 4.28810048092762e-06, 'samples': 27122496, 'steps': 141262, 'loss/train': 1.0720916986465454} 08/31/2021 14:52:53 - INFO - __main__ - Step 141264: {'lr': 4.287121868469662e-06, 'samples': 27122688, 'steps': 141263, 'loss/train': 1.0553550720214844} 08/31/2021 14:52:54 - INFO - __main__ - Step 141265: {'lr': 4.286143366726142e-06, 'samples': 27122880, 'steps': 141264, 'loss/train': 1.0131378173828125} 08/31/2021 14:52:55 - INFO - __main__ - Step 141266: {'lr': 4.2851649756975034e-06, 'samples': 27123072, 'steps': 141265, 'loss/train': 0.9392250776290894} 08/31/2021 14:52:55 - INFO - __main__ - Step 141267: {'lr': 4.284186695384163e-06, 'samples': 27123264, 'steps': 141266, 'loss/train': 1.1253107786178589} 08/31/2021 14:52:56 - INFO - __main__ - Step 141268: {'lr': 4.2832085257865915e-06, 'samples': 27123456, 'steps': 141267, 'loss/train': 1.0580949783325195} 08/31/2021 14:52:56 - INFO - __main__ - Step 141269: {'lr': 4.282230466905207e-06, 'samples': 27123648, 'steps': 141268, 'loss/train': 0.019418466836214066} 08/31/2021 14:52:56 - INFO - __main__ - Step 141270: {'lr': 4.281252518740452e-06, 'samples': 27123840, 'steps': 141269, 'loss/train': 1.5016037225723267} 08/31/2021 14:52:58 - INFO - __main__ - Step 141271: {'lr': 4.280274681292773e-06, 'samples': 27124032, 'steps': 141270, 'loss/train': 0.7410692572593689} 08/31/2021 14:52:59 - INFO - __main__ - Step 141272: {'lr': 4.279296954562612e-06, 'samples': 27124224, 'steps': 141271, 'loss/train': 0.033693164587020874} 08/31/2021 14:52:59 - INFO - __main__ - Step 141273: {'lr': 4.278319338550413e-06, 'samples': 27124416, 'steps': 141272, 'loss/train': 0.989062488079071} 08/31/2021 14:52:59 - INFO - __main__ - Step 141274: {'lr': 4.277341833256593e-06, 'samples': 27124608, 'steps': 141273, 'loss/train': 0.015181922353804111} 08/31/2021 14:53:00 - INFO - __main__ - Step 141275: {'lr': 4.276364438681624e-06, 'samples': 27124800, 'steps': 141274, 'loss/train': 0.6256765127182007} 08/31/2021 14:53:00 - INFO - __main__ - Step 141276: {'lr': 4.275387154825949e-06, 'samples': 27124992, 'steps': 141275, 'loss/train': 1.1074621677398682} 08/31/2021 14:53:01 - INFO - __main__ - Step 141277: {'lr': 4.274409981689958e-06, 'samples': 27125184, 'steps': 141276, 'loss/train': 1.3706940412521362} 08/31/2021 14:53:02 - INFO - __main__ - Step 141278: {'lr': 4.273432919274178e-06, 'samples': 27125376, 'steps': 141277, 'loss/train': 1.1254721879959106} 08/31/2021 14:53:02 - INFO - __main__ - Step 141279: {'lr': 4.27245596757897e-06, 'samples': 27125568, 'steps': 141278, 'loss/train': 1.3948312997817993} 08/31/2021 14:53:03 - INFO - __main__ - Step 141280: {'lr': 4.271479126604805e-06, 'samples': 27125760, 'steps': 141279, 'loss/train': 1.0291472673416138} 08/31/2021 14:53:03 - INFO - __main__ - Step 141281: {'lr': 4.2705023963520996e-06, 'samples': 27125952, 'steps': 141280, 'loss/train': 1.4657386541366577} 08/31/2021 14:53:05 - INFO - __main__ - Step 141282: {'lr': 4.269525776821326e-06, 'samples': 27126144, 'steps': 141281, 'loss/train': 0.45427581667900085} 08/31/2021 14:53:05 - INFO - __main__ - Step 141283: {'lr': 4.2685492680129e-06, 'samples': 27126336, 'steps': 141282, 'loss/train': 0.9401237964630127} 08/31/2021 14:53:06 - INFO - __main__ - Step 141284: {'lr': 4.2675728699272946e-06, 'samples': 27126528, 'steps': 141283, 'loss/train': 0.5551612377166748} 08/31/2021 14:53:06 - INFO - __main__ - Step 141285: {'lr': 4.266596582564925e-06, 'samples': 27126720, 'steps': 141284, 'loss/train': 0.10225971788167953} 08/31/2021 14:53:06 - INFO - __main__ - Step 141286: {'lr': 4.265620405926235e-06, 'samples': 27126912, 'steps': 141285, 'loss/train': 0.7489528656005859} 08/31/2021 14:53:09 - INFO - __main__ - Step 141287: {'lr': 4.264644340011642e-06, 'samples': 27127104, 'steps': 141286, 'loss/train': 0.036494478583335876} 08/31/2021 14:53:09 - INFO - __main__ - Step 141288: {'lr': 4.263668384821645e-06, 'samples': 27127296, 'steps': 141287, 'loss/train': 0.9458810687065125} 08/31/2021 14:53:10 - INFO - __main__ - Step 141289: {'lr': 4.262692540356633e-06, 'samples': 27127488, 'steps': 141288, 'loss/train': 0.349080353975296} 08/31/2021 14:53:10 - INFO - __main__ - Step 141290: {'lr': 4.2617168066170495e-06, 'samples': 27127680, 'steps': 141289, 'loss/train': 0.17317427694797516} 08/31/2021 14:53:10 - INFO - __main__ - Step 141291: {'lr': 4.2607411836033675e-06, 'samples': 27127872, 'steps': 141290, 'loss/train': 1.7132740020751953} 08/31/2021 14:53:12 - INFO - __main__ - Step 141292: {'lr': 4.259765671315974e-06, 'samples': 27128064, 'steps': 141291, 'loss/train': 1.5919471979141235} 08/31/2021 14:53:12 - INFO - __main__ - Step 141293: {'lr': 4.2587902697553695e-06, 'samples': 27128256, 'steps': 141292, 'loss/train': 1.2237240076065063} 08/31/2021 14:53:13 - INFO - __main__ - Step 141294: {'lr': 4.257814978921942e-06, 'samples': 27128448, 'steps': 141293, 'loss/train': 0.27356693148612976} 08/31/2021 14:53:13 - INFO - __main__ - Step 141295: {'lr': 4.256839798816137e-06, 'samples': 27128640, 'steps': 141294, 'loss/train': 0.8521941304206848} 08/31/2021 14:53:13 - INFO - __main__ - Step 141296: {'lr': 4.255864729438425e-06, 'samples': 27128832, 'steps': 141295, 'loss/train': 1.7068557739257812} 08/31/2021 14:53:15 - INFO - __main__ - Step 141297: {'lr': 4.254889770789222e-06, 'samples': 27129024, 'steps': 141296, 'loss/train': 1.0879926681518555} 08/31/2021 14:53:15 - INFO - __main__ - Step 141298: {'lr': 4.253914922868973e-06, 'samples': 27129216, 'steps': 141297, 'loss/train': 1.3844062089920044} 08/31/2021 14:53:16 - INFO - __main__ - Step 141299: {'lr': 4.252940185678123e-06, 'samples': 27129408, 'steps': 141298, 'loss/train': 0.965842604637146} 08/31/2021 14:53:16 - INFO - __main__ - Step 141300: {'lr': 4.251965559217141e-06, 'samples': 27129600, 'steps': 141299, 'loss/train': 1.1191309690475464} 08/31/2021 14:53:16 - INFO - __main__ - Step 141301: {'lr': 4.250991043486391e-06, 'samples': 27129792, 'steps': 141300, 'loss/train': 0.6570229530334473} 08/31/2021 14:53:17 - INFO - __main__ - Step 141302: {'lr': 4.250016638486342e-06, 'samples': 27129984, 'steps': 141301, 'loss/train': 1.2415858507156372} 08/31/2021 14:53:18 - INFO - __main__ - Step 141303: {'lr': 4.249042344217469e-06, 'samples': 27130176, 'steps': 141302, 'loss/train': 1.3588248491287231} 08/31/2021 14:53:19 - INFO - __main__ - Step 141304: {'lr': 4.248068160680185e-06, 'samples': 27130368, 'steps': 141303, 'loss/train': 1.1712582111358643} 08/31/2021 14:53:19 - INFO - __main__ - Step 141305: {'lr': 4.247094087874909e-06, 'samples': 27130560, 'steps': 141304, 'loss/train': 0.6097046732902527} 08/31/2021 14:53:20 - INFO - __main__ - Step 141306: {'lr': 4.246120125802111e-06, 'samples': 27130752, 'steps': 141305, 'loss/train': 0.5503610372543335} 08/31/2021 14:53:20 - INFO - __main__ - Step 141307: {'lr': 4.245146274462208e-06, 'samples': 27130944, 'steps': 141306, 'loss/train': 1.1551209688186646} 08/31/2021 14:53:20 - INFO - __main__ - Step 141308: {'lr': 4.244172533855673e-06, 'samples': 27131136, 'steps': 141307, 'loss/train': 0.014522671699523926} 08/31/2021 14:53:22 - INFO - __main__ - Step 141309: {'lr': 4.243198903982892e-06, 'samples': 27131328, 'steps': 141308, 'loss/train': 1.1023591756820679} 08/31/2021 14:53:22 - INFO - __main__ - Step 141310: {'lr': 4.242225384844367e-06, 'samples': 27131520, 'steps': 141309, 'loss/train': 0.9441372156143188} 08/31/2021 14:53:23 - INFO - __main__ - Step 141311: {'lr': 4.241251976440514e-06, 'samples': 27131712, 'steps': 141310, 'loss/train': 0.68039470911026} 08/31/2021 14:53:23 - INFO - __main__ - Step 141312: {'lr': 4.24027867877172e-06, 'samples': 27131904, 'steps': 141311, 'loss/train': 1.6052839756011963} 08/31/2021 14:53:23 - INFO - __main__ - Step 141313: {'lr': 4.2393054918384855e-06, 'samples': 27132096, 'steps': 141312, 'loss/train': 0.7851073145866394} 08/31/2021 14:53:25 - INFO - __main__ - Step 141314: {'lr': 4.2383324156412e-06, 'samples': 27132288, 'steps': 141313, 'loss/train': 1.2085700035095215} 08/31/2021 14:53:25 - INFO - __main__ - Step 141315: {'lr': 4.237359450180362e-06, 'samples': 27132480, 'steps': 141314, 'loss/train': 1.2269923686981201} 08/31/2021 14:53:26 - INFO - __main__ - Step 141316: {'lr': 4.23638659545636e-06, 'samples': 27132672, 'steps': 141315, 'loss/train': 1.4470878839492798} 08/31/2021 14:53:26 - INFO - __main__ - Step 141317: {'lr': 4.235413851469666e-06, 'samples': 27132864, 'steps': 141316, 'loss/train': 0.8526812791824341} 08/31/2021 14:53:27 - INFO - __main__ - Step 141318: {'lr': 4.234441218220669e-06, 'samples': 27133056, 'steps': 141317, 'loss/train': 1.398743987083435} 08/31/2021 14:53:28 - INFO - __main__ - Step 141319: {'lr': 4.2334686957098685e-06, 'samples': 27133248, 'steps': 141318, 'loss/train': 1.1280367374420166} 08/31/2021 14:53:28 - INFO - __main__ - Step 141320: {'lr': 4.2324962839376815e-06, 'samples': 27133440, 'steps': 141319, 'loss/train': 0.9064602255821228} 08/31/2021 14:53:29 - INFO - __main__ - Step 141321: {'lr': 4.231523982904523e-06, 'samples': 27133632, 'steps': 141320, 'loss/train': 1.157222867012024} 08/31/2021 14:53:29 - INFO - __main__ - Step 141322: {'lr': 4.230551792610837e-06, 'samples': 27133824, 'steps': 141321, 'loss/train': 1.0219216346740723} 08/31/2021 14:53:30 - INFO - __main__ - Step 141323: {'lr': 4.2295797130570965e-06, 'samples': 27134016, 'steps': 141322, 'loss/train': 1.293464183807373} 08/31/2021 14:53:31 - INFO - __main__ - Step 141324: {'lr': 4.228607744243717e-06, 'samples': 27134208, 'steps': 141323, 'loss/train': 1.014408826828003} 08/31/2021 14:53:32 - INFO - __main__ - Step 141325: {'lr': 4.227635886171116e-06, 'samples': 27134400, 'steps': 141324, 'loss/train': 1.4009627103805542} 08/31/2021 14:53:32 - INFO - __main__ - Step 141326: {'lr': 4.226664138839764e-06, 'samples': 27134592, 'steps': 141325, 'loss/train': 1.632702112197876} 08/31/2021 14:53:33 - INFO - __main__ - Step 141327: {'lr': 4.22569250225005e-06, 'samples': 27134784, 'steps': 141326, 'loss/train': 1.2777758836746216} 08/31/2021 14:53:33 - INFO - __main__ - Step 141328: {'lr': 4.224720976402474e-06, 'samples': 27134976, 'steps': 141327, 'loss/train': 1.2945945262908936} 08/31/2021 14:53:33 - INFO - __main__ - Step 141329: {'lr': 4.223749561297452e-06, 'samples': 27135168, 'steps': 141328, 'loss/train': 0.056076984852552414} 08/31/2021 14:53:35 - INFO - __main__ - Step 141330: {'lr': 4.2227782569354e-06, 'samples': 27135360, 'steps': 141329, 'loss/train': 0.05481398105621338} 08/31/2021 14:53:35 - INFO - __main__ - Step 141331: {'lr': 4.22180706331679e-06, 'samples': 27135552, 'steps': 141330, 'loss/train': 0.9662964940071106} 08/31/2021 14:53:36 - INFO - __main__ - Step 141332: {'lr': 4.220835980442011e-06, 'samples': 27135744, 'steps': 141331, 'loss/train': 1.5047844648361206} 08/31/2021 14:53:36 - INFO - __main__ - Step 141333: {'lr': 4.2198650083115634e-06, 'samples': 27135936, 'steps': 141332, 'loss/train': 0.9786416292190552} 08/31/2021 14:53:36 - INFO - __main__ - Step 141334: {'lr': 4.218894146925833e-06, 'samples': 27136128, 'steps': 141333, 'loss/train': 0.9219756126403809} 08/31/2021 14:53:38 - INFO - __main__ - Step 141335: {'lr': 4.217923396285295e-06, 'samples': 27136320, 'steps': 141334, 'loss/train': 1.6123079061508179} 08/31/2021 14:53:38 - INFO - __main__ - Step 141336: {'lr': 4.216952756390363e-06, 'samples': 27136512, 'steps': 141335, 'loss/train': 0.6371322870254517} 08/31/2021 14:53:39 - INFO - __main__ - Step 141337: {'lr': 4.215982227241483e-06, 'samples': 27136704, 'steps': 141336, 'loss/train': 0.6232897043228149} 08/31/2021 14:53:39 - INFO - __main__ - Step 141338: {'lr': 4.21501180883907e-06, 'samples': 27136896, 'steps': 141337, 'loss/train': 1.7147685289382935} 08/31/2021 14:53:40 - INFO - __main__ - Step 141339: {'lr': 4.214041501183596e-06, 'samples': 27137088, 'steps': 141338, 'loss/train': 1.662779450416565} 08/31/2021 14:53:40 - INFO - __main__ - Step 141340: {'lr': 4.213071304275451e-06, 'samples': 27137280, 'steps': 141339, 'loss/train': 1.1924108266830444} 08/31/2021 14:53:42 - INFO - __main__ - Step 141341: {'lr': 4.212101218115133e-06, 'samples': 27137472, 'steps': 141340, 'loss/train': 1.2549530267715454} 08/31/2021 14:53:42 - INFO - __main__ - Step 141342: {'lr': 4.211131242703031e-06, 'samples': 27137664, 'steps': 141341, 'loss/train': 1.255653977394104} 08/31/2021 14:53:43 - INFO - __main__ - Step 141343: {'lr': 4.210161378039618e-06, 'samples': 27137856, 'steps': 141342, 'loss/train': 0.8788290023803711} 08/31/2021 14:53:43 - INFO - __main__ - Step 141344: {'lr': 4.209191624125308e-06, 'samples': 27138048, 'steps': 141343, 'loss/train': 1.1253169775009155} 08/31/2021 14:53:43 - INFO - __main__ - Step 141345: {'lr': 4.208221980960547e-06, 'samples': 27138240, 'steps': 141344, 'loss/train': 0.9041222333908081} 08/31/2021 14:53:45 - INFO - __main__ - Step 141346: {'lr': 4.207252448545751e-06, 'samples': 27138432, 'steps': 141345, 'loss/train': 1.4745557308197021} 08/31/2021 14:53:45 - INFO - __main__ - Step 141347: {'lr': 4.206283026881391e-06, 'samples': 27138624, 'steps': 141346, 'loss/train': 1.4544627666473389} 08/31/2021 14:53:46 - INFO - __main__ - Step 141348: {'lr': 4.205313715967884e-06, 'samples': 27138816, 'steps': 141347, 'loss/train': 1.4998846054077148} 08/31/2021 14:53:46 - INFO - __main__ - Step 141349: {'lr': 4.204344515805674e-06, 'samples': 27139008, 'steps': 141348, 'loss/train': 1.263864517211914} 08/31/2021 14:53:46 - INFO - __main__ - Step 141350: {'lr': 4.203375426395206e-06, 'samples': 27139200, 'steps': 141349, 'loss/train': 1.0781919956207275} 08/31/2021 14:53:48 - INFO - __main__ - Step 141351: {'lr': 4.202406447736895e-06, 'samples': 27139392, 'steps': 141350, 'loss/train': 1.5630382299423218} 08/31/2021 14:53:48 - INFO - __main__ - Step 141352: {'lr': 4.201437579831158e-06, 'samples': 27139584, 'steps': 141351, 'loss/train': 1.3750404119491577} 08/31/2021 14:53:49 - INFO - __main__ - Step 141353: {'lr': 4.200468822678493e-06, 'samples': 27139776, 'steps': 141352, 'loss/train': 0.31141427159309387} 08/31/2021 14:53:49 - INFO - __main__ - Step 141354: {'lr': 4.199500176279291e-06, 'samples': 27139968, 'steps': 141353, 'loss/train': 0.41601207852363586} 08/31/2021 14:53:49 - INFO - __main__ - Step 141355: {'lr': 4.198531640633996e-06, 'samples': 27140160, 'steps': 141354, 'loss/train': 1.0407865047454834} 08/31/2021 14:53:51 - INFO - __main__ - Step 141356: {'lr': 4.19756321574305e-06, 'samples': 27140352, 'steps': 141355, 'loss/train': 0.8723046779632568} 08/31/2021 14:53:51 - INFO - __main__ - Step 141357: {'lr': 4.196594901606898e-06, 'samples': 27140544, 'steps': 141356, 'loss/train': 1.2957789897918701} 08/31/2021 14:53:52 - INFO - __main__ - Step 141358: {'lr': 4.195626698225957e-06, 'samples': 27140736, 'steps': 141357, 'loss/train': 1.1105012893676758} 08/31/2021 14:53:52 - INFO - __main__ - Step 141359: {'lr': 4.194658605600698e-06, 'samples': 27140928, 'steps': 141358, 'loss/train': 1.1492128372192383} 08/31/2021 14:53:52 - INFO - __main__ - Step 141360: {'lr': 4.193690623731511e-06, 'samples': 27141120, 'steps': 141359, 'loss/train': 1.671060562133789} 08/31/2021 14:53:54 - INFO - __main__ - Step 141361: {'lr': 4.192722752618866e-06, 'samples': 27141312, 'steps': 141360, 'loss/train': 1.1006232500076294} 08/31/2021 14:53:54 - INFO - __main__ - Step 141362: {'lr': 4.19175499226318e-06, 'samples': 27141504, 'steps': 141361, 'loss/train': 1.1429650783538818} 08/31/2021 14:53:55 - INFO - __main__ - Step 141363: {'lr': 4.190787342664898e-06, 'samples': 27141696, 'steps': 141362, 'loss/train': 1.098816990852356} 08/31/2021 14:53:55 - INFO - __main__ - Step 141364: {'lr': 4.189819803824463e-06, 'samples': 27141888, 'steps': 141363, 'loss/train': 0.9957700371742249} 08/31/2021 14:53:55 - INFO - __main__ - Step 141365: {'lr': 4.188852375742292e-06, 'samples': 27142080, 'steps': 141364, 'loss/train': 1.0717823505401611} 08/31/2021 14:53:57 - INFO - __main__ - Step 141366: {'lr': 4.187885058418828e-06, 'samples': 27142272, 'steps': 141365, 'loss/train': 0.9188547730445862} 08/31/2021 14:53:57 - INFO - __main__ - Step 141367: {'lr': 4.186917851854516e-06, 'samples': 27142464, 'steps': 141366, 'loss/train': 3.520718812942505} 08/31/2021 14:53:58 - INFO - __main__ - Step 141368: {'lr': 4.185950756049772e-06, 'samples': 27142656, 'steps': 141367, 'loss/train': 0.994935154914856} 08/31/2021 14:53:58 - INFO - __main__ - Step 141369: {'lr': 4.184983771005041e-06, 'samples': 27142848, 'steps': 141368, 'loss/train': 1.3041555881500244} 08/31/2021 14:53:58 - INFO - __main__ - Step 141370: {'lr': 4.184016896720793e-06, 'samples': 27143040, 'steps': 141369, 'loss/train': 0.7769006490707397} 08/31/2021 14:53:59 - INFO - __main__ - Step 141371: {'lr': 4.183050133197419e-06, 'samples': 27143232, 'steps': 141370, 'loss/train': 0.5540274381637573} 08/31/2021 14:54:00 - INFO - __main__ - Step 141372: {'lr': 4.182083480435362e-06, 'samples': 27143424, 'steps': 141371, 'loss/train': 1.945490837097168} 08/31/2021 14:54:01 - INFO - __main__ - Step 141373: {'lr': 4.181116938435065e-06, 'samples': 27143616, 'steps': 141372, 'loss/train': 1.3707950115203857} 08/31/2021 14:54:01 - INFO - __main__ - Step 141374: {'lr': 4.180150507196973e-06, 'samples': 27143808, 'steps': 141373, 'loss/train': 1.4110876321792603} 08/31/2021 14:54:01 - INFO - __main__ - Step 141375: {'lr': 4.1791841867215016e-06, 'samples': 27144000, 'steps': 141374, 'loss/train': 1.3188496828079224} 08/31/2021 14:54:02 - INFO - __main__ - Step 141376: {'lr': 4.178217977009097e-06, 'samples': 27144192, 'steps': 141375, 'loss/train': 1.284175992012024} 08/31/2021 14:54:03 - INFO - __main__ - Step 141377: {'lr': 4.177251878060229e-06, 'samples': 27144384, 'steps': 141376, 'loss/train': 1.298197865486145} 08/31/2021 14:54:04 - INFO - __main__ - Step 141378: {'lr': 4.176285889875259e-06, 'samples': 27144576, 'steps': 141377, 'loss/train': 0.8175808787345886} 08/31/2021 14:54:04 - INFO - __main__ - Step 141379: {'lr': 4.175320012454686e-06, 'samples': 27144768, 'steps': 141378, 'loss/train': 1.7863792181015015} 08/31/2021 14:54:04 - INFO - __main__ - Step 141380: {'lr': 4.1743542457989005e-06, 'samples': 27144960, 'steps': 141379, 'loss/train': 1.8877755403518677} 08/31/2021 14:54:05 - INFO - __main__ - Step 141381: {'lr': 4.173388589908372e-06, 'samples': 27145152, 'steps': 141380, 'loss/train': 1.0981968641281128} 08/31/2021 14:54:06 - INFO - __main__ - Step 141382: {'lr': 4.172423044783518e-06, 'samples': 27145344, 'steps': 141381, 'loss/train': 1.2153093814849854} 08/31/2021 14:54:07 - INFO - __main__ - Step 141383: {'lr': 4.171457610424756e-06, 'samples': 27145536, 'steps': 141382, 'loss/train': 0.6703292727470398} 08/31/2021 14:54:07 - INFO - __main__ - Step 141384: {'lr': 4.170492286832556e-06, 'samples': 27145728, 'steps': 141383, 'loss/train': 0.8643544912338257} 08/31/2021 14:54:08 - INFO - __main__ - Step 141385: {'lr': 4.169527074007335e-06, 'samples': 27145920, 'steps': 141384, 'loss/train': 0.9819678664207458} 08/31/2021 14:54:08 - INFO - __main__ - Step 141386: {'lr': 4.168561971949536e-06, 'samples': 27146112, 'steps': 141385, 'loss/train': 1.2057043313980103} 08/31/2021 14:54:10 - INFO - __main__ - Step 141387: {'lr': 4.167596980659605e-06, 'samples': 27146304, 'steps': 141386, 'loss/train': 0.9316513538360596} 08/31/2021 14:54:10 - INFO - __main__ - Step 141388: {'lr': 4.166632100137957e-06, 'samples': 27146496, 'steps': 141387, 'loss/train': 1.258375644683838} 08/31/2021 14:54:10 - INFO - __main__ - Step 141389: {'lr': 4.165667330385009e-06, 'samples': 27146688, 'steps': 141388, 'loss/train': 1.1979600191116333} 08/31/2021 14:54:11 - INFO - __main__ - Step 141390: {'lr': 4.16470267140126e-06, 'samples': 27146880, 'steps': 141389, 'loss/train': 0.6606128811836243} 08/31/2021 14:54:11 - INFO - __main__ - Step 141391: {'lr': 4.163738123187072e-06, 'samples': 27147072, 'steps': 141390, 'loss/train': 0.530278742313385} 08/31/2021 14:54:13 - INFO - __main__ - Step 141392: {'lr': 4.162773685742888e-06, 'samples': 27147264, 'steps': 141391, 'loss/train': 0.9820886254310608} 08/31/2021 14:54:14 - INFO - __main__ - Step 141393: {'lr': 4.161809359069207e-06, 'samples': 27147456, 'steps': 141392, 'loss/train': 1.1142183542251587} 08/31/2021 14:54:14 - INFO - __main__ - Step 141394: {'lr': 4.160845143166392e-06, 'samples': 27147648, 'steps': 141393, 'loss/train': 0.31644007563591003} 08/31/2021 14:54:14 - INFO - __main__ - Step 141395: {'lr': 4.159881038034913e-06, 'samples': 27147840, 'steps': 141394, 'loss/train': 0.9363583922386169} 08/31/2021 14:54:15 - INFO - __main__ - Step 141396: {'lr': 4.158917043675214e-06, 'samples': 27148032, 'steps': 141395, 'loss/train': 0.14861494302749634} 08/31/2021 14:54:16 - INFO - __main__ - Step 141397: {'lr': 4.157953160087685e-06, 'samples': 27148224, 'steps': 141396, 'loss/train': 1.285183310508728} 08/31/2021 14:54:17 - INFO - __main__ - Step 141398: {'lr': 4.156989387272797e-06, 'samples': 27148416, 'steps': 141397, 'loss/train': 1.2548812627792358} 08/31/2021 14:54:17 - INFO - __main__ - Step 141399: {'lr': 4.156025725230994e-06, 'samples': 27148608, 'steps': 141398, 'loss/train': 1.3562895059585571} 08/31/2021 14:54:17 - INFO - __main__ - Step 141400: {'lr': 4.155062173962693e-06, 'samples': 27148800, 'steps': 141399, 'loss/train': 1.326940894126892} 08/31/2021 14:54:18 - INFO - __main__ - Step 141401: {'lr': 4.1540987334683086e-06, 'samples': 27148992, 'steps': 141400, 'loss/train': 0.6315784454345703} 08/31/2021 14:54:18 - INFO - __main__ - Step 141402: {'lr': 4.153135403748287e-06, 'samples': 27149184, 'steps': 141401, 'loss/train': 1.1368396282196045} 08/31/2021 14:54:20 - INFO - __main__ - Step 141403: {'lr': 4.152172184803099e-06, 'samples': 27149376, 'steps': 141402, 'loss/train': 1.2784911394119263} 08/31/2021 14:54:20 - INFO - __main__ - Step 141404: {'lr': 4.151209076633133e-06, 'samples': 27149568, 'steps': 141403, 'loss/train': 1.7259143590927124} 08/31/2021 14:54:20 - INFO - __main__ - Step 141405: {'lr': 4.150246079238834e-06, 'samples': 27149760, 'steps': 141404, 'loss/train': 0.32423317432403564} 08/31/2021 14:54:21 - INFO - __main__ - Step 141406: {'lr': 4.149283192620645e-06, 'samples': 27149952, 'steps': 141405, 'loss/train': 0.8395460844039917} 08/31/2021 14:54:21 - INFO - __main__ - Step 141407: {'lr': 4.148320416779011e-06, 'samples': 27150144, 'steps': 141406, 'loss/train': 0.6000877022743225} 08/31/2021 14:54:23 - INFO - __main__ - Step 141408: {'lr': 4.14735775171432e-06, 'samples': 27150336, 'steps': 141407, 'loss/train': 1.0408921241760254} 08/31/2021 14:54:23 - INFO - __main__ - Step 141409: {'lr': 4.1463951974270715e-06, 'samples': 27150528, 'steps': 141408, 'loss/train': 1.3976683616638184} 08/31/2021 14:54:23 - INFO - __main__ - Step 141410: {'lr': 4.145432753917627e-06, 'samples': 27150720, 'steps': 141409, 'loss/train': 1.4275237321853638} 08/31/2021 14:54:24 - INFO - __main__ - Step 141411: {'lr': 4.144470421186486e-06, 'samples': 27150912, 'steps': 141410, 'loss/train': 0.5306147336959839} 08/31/2021 14:54:24 - INFO - __main__ - Step 141412: {'lr': 4.143508199234036e-06, 'samples': 27151104, 'steps': 141411, 'loss/train': 1.2304415702819824} 08/31/2021 14:54:26 - INFO - __main__ - Step 141413: {'lr': 4.142546088060722e-06, 'samples': 27151296, 'steps': 141412, 'loss/train': 0.8061498999595642} 08/31/2021 14:54:26 - INFO - __main__ - Step 141414: {'lr': 4.141584087666988e-06, 'samples': 27151488, 'steps': 141413, 'loss/train': 0.780316948890686} 08/31/2021 14:54:26 - INFO - __main__ - Step 141415: {'lr': 4.140622198053251e-06, 'samples': 27151680, 'steps': 141414, 'loss/train': 0.5823577046394348} 08/31/2021 14:54:27 - INFO - __main__ - Step 141416: {'lr': 4.139660419219981e-06, 'samples': 27151872, 'steps': 141415, 'loss/train': 0.8036393523216248} 08/31/2021 14:54:27 - INFO - __main__ - Step 141417: {'lr': 4.138698751167597e-06, 'samples': 27152064, 'steps': 141416, 'loss/train': 1.234724760055542} 08/31/2021 14:54:29 - INFO - __main__ - Step 141418: {'lr': 4.137737193896484e-06, 'samples': 27152256, 'steps': 141417, 'loss/train': 1.371689796447754} 08/31/2021 14:54:29 - INFO - __main__ - Step 141419: {'lr': 4.136775747407145e-06, 'samples': 27152448, 'steps': 141418, 'loss/train': 0.6526870727539062} 08/31/2021 14:54:30 - INFO - __main__ - Step 141420: {'lr': 4.135814411699967e-06, 'samples': 27152640, 'steps': 141419, 'loss/train': 0.4184701144695282} 08/31/2021 14:54:30 - INFO - __main__ - Step 141421: {'lr': 4.1348531867753945e-06, 'samples': 27152832, 'steps': 141420, 'loss/train': 0.9732409715652466} 08/31/2021 14:54:30 - INFO - __main__ - Step 141422: {'lr': 4.133892072633844e-06, 'samples': 27153024, 'steps': 141421, 'loss/train': 1.5053802728652954} 08/31/2021 14:54:32 - INFO - __main__ - Step 141423: {'lr': 4.132931069275786e-06, 'samples': 27153216, 'steps': 141422, 'loss/train': 1.3548871278762817} 08/31/2021 14:54:32 - INFO - __main__ - Step 141424: {'lr': 4.131970176701638e-06, 'samples': 27153408, 'steps': 141423, 'loss/train': 0.7093628644943237} 08/31/2021 14:54:33 - INFO - __main__ - Step 141425: {'lr': 4.1310093949118444e-06, 'samples': 27153600, 'steps': 141424, 'loss/train': 1.2670713663101196} 08/31/2021 14:54:33 - INFO - __main__ - Step 141426: {'lr': 4.130048723906793e-06, 'samples': 27153792, 'steps': 141425, 'loss/train': 1.1056559085845947} 08/31/2021 14:54:33 - INFO - __main__ - Step 141427: {'lr': 4.129088163686956e-06, 'samples': 27153984, 'steps': 141426, 'loss/train': 1.28092360496521} 08/31/2021 14:54:35 - INFO - __main__ - Step 141428: {'lr': 4.128127714252777e-06, 'samples': 27154176, 'steps': 141427, 'loss/train': 1.895949363708496} 08/31/2021 14:54:36 - INFO - __main__ - Step 141429: {'lr': 4.127167375604646e-06, 'samples': 27154368, 'steps': 141428, 'loss/train': 5.430881977081299} 08/31/2021 14:54:36 - INFO - __main__ - Step 141430: {'lr': 4.126207147743061e-06, 'samples': 27154560, 'steps': 141429, 'loss/train': 0.038448069244623184} 08/31/2021 14:54:37 - INFO - __main__ - Step 141431: {'lr': 4.125247030668383e-06, 'samples': 27154752, 'steps': 141430, 'loss/train': 1.3651045560836792} 08/31/2021 14:54:37 - INFO - __main__ - Step 141432: {'lr': 4.124287024381057e-06, 'samples': 27154944, 'steps': 141431, 'loss/train': 0.2551627457141876} 08/31/2021 14:54:37 - INFO - __main__ - Step 141433: {'lr': 4.123327128881555e-06, 'samples': 27155136, 'steps': 141432, 'loss/train': 0.6411728858947754} 08/31/2021 14:54:38 - INFO - __main__ - Step 141434: {'lr': 4.1223673441702916e-06, 'samples': 27155328, 'steps': 141433, 'loss/train': 0.8444719314575195} 08/31/2021 14:54:39 - INFO - __main__ - Step 141435: {'lr': 4.121407670247684e-06, 'samples': 27155520, 'steps': 141434, 'loss/train': 0.7232104539871216} 08/31/2021 14:54:40 - INFO - __main__ - Step 141436: {'lr': 4.120448107114177e-06, 'samples': 27155712, 'steps': 141435, 'loss/train': 1.5627230405807495} 08/31/2021 14:54:40 - INFO - __main__ - Step 141437: {'lr': 4.1194886547702145e-06, 'samples': 27155904, 'steps': 141436, 'loss/train': 0.6092380285263062} 08/31/2021 14:54:40 - INFO - __main__ - Step 141438: {'lr': 4.118529313216185e-06, 'samples': 27156096, 'steps': 141437, 'loss/train': 1.133386254310608} 08/31/2021 14:54:41 - INFO - __main__ - Step 141439: {'lr': 4.117570082452587e-06, 'samples': 27156288, 'steps': 141438, 'loss/train': 0.9301917552947998} 08/31/2021 14:54:42 - INFO - __main__ - Step 141440: {'lr': 4.1166109624798106e-06, 'samples': 27156480, 'steps': 141439, 'loss/train': 0.3310522437095642} 08/31/2021 14:54:43 - INFO - __main__ - Step 141441: {'lr': 4.1156519532982716e-06, 'samples': 27156672, 'steps': 141440, 'loss/train': 0.6395115852355957} 08/31/2021 14:54:43 - INFO - __main__ - Step 141442: {'lr': 4.114693054908441e-06, 'samples': 27156864, 'steps': 141441, 'loss/train': 1.3251934051513672} 08/31/2021 14:54:43 - INFO - __main__ - Step 141443: {'lr': 4.1137342673107366e-06, 'samples': 27157056, 'steps': 141442, 'loss/train': 0.8281594514846802} 08/31/2021 14:54:44 - INFO - __main__ - Step 141444: {'lr': 4.112775590505602e-06, 'samples': 27157248, 'steps': 141443, 'loss/train': 0.8615671992301941} 08/31/2021 14:54:45 - INFO - __main__ - Step 141445: {'lr': 4.111817024493453e-06, 'samples': 27157440, 'steps': 141444, 'loss/train': 1.1811715364456177} 08/31/2021 14:54:46 - INFO - __main__ - Step 141446: {'lr': 4.110858569274706e-06, 'samples': 27157632, 'steps': 141445, 'loss/train': 1.105509638786316} 08/31/2021 14:54:46 - INFO - __main__ - Step 141447: {'lr': 4.109900224849833e-06, 'samples': 27157824, 'steps': 141446, 'loss/train': 0.17716437578201294} 08/31/2021 14:54:46 - INFO - __main__ - Step 141448: {'lr': 4.108941991219222e-06, 'samples': 27158016, 'steps': 141447, 'loss/train': 0.991721510887146} 08/31/2021 14:54:47 - INFO - __main__ - Step 141449: {'lr': 4.1079838683833474e-06, 'samples': 27158208, 'steps': 141448, 'loss/train': 0.3525831997394562} 08/31/2021 14:54:47 - INFO - __main__ - Step 141450: {'lr': 4.107025856342595e-06, 'samples': 27158400, 'steps': 141449, 'loss/train': 0.48583292961120605} 08/31/2021 14:54:49 - INFO - __main__ - Step 141451: {'lr': 4.106067955097437e-06, 'samples': 27158592, 'steps': 141450, 'loss/train': 1.0374794006347656} 08/31/2021 14:54:50 - INFO - __main__ - Step 141452: {'lr': 4.10511016464829e-06, 'samples': 27158784, 'steps': 141451, 'loss/train': 0.8164175748825073} 08/31/2021 14:54:50 - INFO - __main__ - Step 141453: {'lr': 4.104152484995599e-06, 'samples': 27158976, 'steps': 141452, 'loss/train': 0.08743070065975189} 08/31/2021 14:54:51 - INFO - __main__ - Step 141454: {'lr': 4.10319491613978e-06, 'samples': 27159168, 'steps': 141453, 'loss/train': 1.0515451431274414} 08/31/2021 14:54:51 - INFO - __main__ - Step 141455: {'lr': 4.102237458081249e-06, 'samples': 27159360, 'steps': 141454, 'loss/train': 0.023468539118766785} 08/31/2021 14:54:52 - INFO - __main__ - Step 141456: {'lr': 4.101280110820477e-06, 'samples': 27159552, 'steps': 141455, 'loss/train': 1.080834150314331} 08/31/2021 14:54:53 - INFO - __main__ - Step 141457: {'lr': 4.100322874357882e-06, 'samples': 27159744, 'steps': 141456, 'loss/train': 1.3567296266555786} 08/31/2021 14:54:53 - INFO - __main__ - Step 141458: {'lr': 4.09936574869385e-06, 'samples': 27159936, 'steps': 141457, 'loss/train': 0.8730042576789856} 08/31/2021 14:54:54 - INFO - __main__ - Step 141459: {'lr': 4.098408733828856e-06, 'samples': 27160128, 'steps': 141458, 'loss/train': 1.4604500532150269} 08/31/2021 14:54:54 - INFO - __main__ - Step 141460: {'lr': 4.097451829763343e-06, 'samples': 27160320, 'steps': 141459, 'loss/train': 1.0737124681472778} 08/31/2021 14:54:56 - INFO - __main__ - Step 141461: {'lr': 4.0964950364977274e-06, 'samples': 27160512, 'steps': 141460, 'loss/train': 1.0224775075912476} 08/31/2021 14:54:56 - INFO - __main__ - Step 141462: {'lr': 4.0955383540324244e-06, 'samples': 27160704, 'steps': 141461, 'loss/train': 1.0683749914169312} 08/31/2021 14:54:56 - INFO - __main__ - Step 141463: {'lr': 4.094581782367879e-06, 'samples': 27160896, 'steps': 141462, 'loss/train': 1.1420438289642334} 08/31/2021 14:54:57 - INFO - __main__ - Step 141464: {'lr': 4.093625321504507e-06, 'samples': 27161088, 'steps': 141463, 'loss/train': 1.376719355583191} 08/31/2021 14:54:57 - INFO - __main__ - Step 141465: {'lr': 4.0926689714427534e-06, 'samples': 27161280, 'steps': 141464, 'loss/train': 0.21732845902442932} 08/31/2021 14:54:59 - INFO - __main__ - Step 141466: {'lr': 4.091712732183062e-06, 'samples': 27161472, 'steps': 141465, 'loss/train': 1.3448290824890137} 08/31/2021 14:54:59 - INFO - __main__ - Step 141467: {'lr': 4.090756603725848e-06, 'samples': 27161664, 'steps': 141466, 'loss/train': 1.1680599451065063} 08/31/2021 14:55:00 - INFO - __main__ - Step 141468: {'lr': 4.089800586071557e-06, 'samples': 27161856, 'steps': 141467, 'loss/train': 1.120681881904602} 08/31/2021 14:55:00 - INFO - __main__ - Step 141469: {'lr': 4.088844679220604e-06, 'samples': 27162048, 'steps': 141468, 'loss/train': 0.8147046566009521} 08/31/2021 14:55:00 - INFO - __main__ - Step 141470: {'lr': 4.087888883173407e-06, 'samples': 27162240, 'steps': 141469, 'loss/train': 1.3173240423202515} 08/31/2021 14:55:02 - INFO - __main__ - Step 141471: {'lr': 4.086933197930437e-06, 'samples': 27162432, 'steps': 141470, 'loss/train': 0.819634735584259} 08/31/2021 14:55:02 - INFO - __main__ - Step 141472: {'lr': 4.085977623492082e-06, 'samples': 27162624, 'steps': 141471, 'loss/train': 0.4268519878387451} 08/31/2021 14:55:03 - INFO - __main__ - Step 141473: {'lr': 4.085022159858787e-06, 'samples': 27162816, 'steps': 141472, 'loss/train': 0.5959492325782776} 08/31/2021 14:55:03 - INFO - __main__ - Step 141474: {'lr': 4.084066807030995e-06, 'samples': 27163008, 'steps': 141473, 'loss/train': 5.784725189208984} 08/31/2021 14:55:03 - INFO - __main__ - Step 141475: {'lr': 4.083111565009124e-06, 'samples': 27163200, 'steps': 141474, 'loss/train': 1.1076685190200806} 08/31/2021 14:55:05 - INFO - __main__ - Step 141476: {'lr': 4.082156433793588e-06, 'samples': 27163392, 'steps': 141475, 'loss/train': 1.3363862037658691} 08/31/2021 14:55:05 - INFO - __main__ - Step 141477: {'lr': 4.08120141338486e-06, 'samples': 27163584, 'steps': 141476, 'loss/train': 1.1426180601119995} 08/31/2021 14:55:06 - INFO - __main__ - Step 141478: {'lr': 4.080246503783358e-06, 'samples': 27163776, 'steps': 141477, 'loss/train': 0.7261635661125183} 08/31/2021 14:55:06 - INFO - __main__ - Step 141479: {'lr': 4.079291704989496e-06, 'samples': 27163968, 'steps': 141478, 'loss/train': 0.9181498289108276} 08/31/2021 14:55:06 - INFO - __main__ - Step 141480: {'lr': 4.078337017003692e-06, 'samples': 27164160, 'steps': 141479, 'loss/train': 1.3236110210418701} 08/31/2021 14:55:07 - INFO - __main__ - Step 141481: {'lr': 4.077382439826416e-06, 'samples': 27164352, 'steps': 141480, 'loss/train': 1.024214267730713} 08/31/2021 14:55:08 - INFO - __main__ - Step 141482: {'lr': 4.076427973458058e-06, 'samples': 27164544, 'steps': 141481, 'loss/train': 1.4764240980148315} 08/31/2021 14:55:09 - INFO - __main__ - Step 141483: {'lr': 4.075473617899062e-06, 'samples': 27164736, 'steps': 141482, 'loss/train': 1.1415938138961792} 08/31/2021 14:55:09 - INFO - __main__ - Step 141484: {'lr': 4.074519373149899e-06, 'samples': 27164928, 'steps': 141483, 'loss/train': 0.0491735078394413} 08/31/2021 14:55:09 - INFO - __main__ - Step 141485: {'lr': 4.073565239210958e-06, 'samples': 27165120, 'steps': 141484, 'loss/train': 0.516063392162323} 08/31/2021 14:55:10 - INFO - __main__ - Step 141486: {'lr': 4.072611216082656e-06, 'samples': 27165312, 'steps': 141485, 'loss/train': 0.8269872665405273} 08/31/2021 14:55:11 - INFO - __main__ - Step 141487: {'lr': 4.071657303765436e-06, 'samples': 27165504, 'steps': 141486, 'loss/train': 0.023347068578004837} 08/31/2021 14:55:12 - INFO - __main__ - Step 141488: {'lr': 4.070703502259743e-06, 'samples': 27165696, 'steps': 141487, 'loss/train': 1.2098381519317627} 08/31/2021 14:55:12 - INFO - __main__ - Step 141489: {'lr': 4.069749811565965e-06, 'samples': 27165888, 'steps': 141488, 'loss/train': 1.4358559846878052} 08/31/2021 14:55:12 - INFO - __main__ - Step 141490: {'lr': 4.068796231684602e-06, 'samples': 27166080, 'steps': 141489, 'loss/train': 1.4540725946426392} 08/31/2021 14:55:13 - INFO - __main__ - Step 141491: {'lr': 4.067842762616014e-06, 'samples': 27166272, 'steps': 141490, 'loss/train': 1.1042273044586182} 08/31/2021 14:55:14 - INFO - __main__ - Step 141492: {'lr': 4.066889404360702e-06, 'samples': 27166464, 'steps': 141491, 'loss/train': 1.4469460248947144} 08/31/2021 14:55:15 - INFO - __main__ - Step 141493: {'lr': 4.0659361569190254e-06, 'samples': 27166656, 'steps': 141492, 'loss/train': 0.5576355457305908} 08/31/2021 14:55:15 - INFO - __main__ - Step 141494: {'lr': 4.064983020291429e-06, 'samples': 27166848, 'steps': 141493, 'loss/train': 0.9735165238380432} 08/31/2021 14:55:15 - INFO - __main__ - Step 141495: {'lr': 4.064029994478385e-06, 'samples': 27167040, 'steps': 141494, 'loss/train': 1.4608025550842285} 08/31/2021 14:55:16 - INFO - __main__ - Step 141496: {'lr': 4.063077079480282e-06, 'samples': 27167232, 'steps': 141495, 'loss/train': 1.1364694833755493} 08/31/2021 14:55:17 - INFO - __main__ - Step 141497: {'lr': 4.062124275297563e-06, 'samples': 27167424, 'steps': 141496, 'loss/train': 1.3942079544067383} 08/31/2021 14:55:18 - INFO - __main__ - Step 141498: {'lr': 4.061171581930673e-06, 'samples': 27167616, 'steps': 141497, 'loss/train': 0.8585993647575378} 08/31/2021 14:55:18 - INFO - __main__ - Step 141499: {'lr': 4.06021899938e-06, 'samples': 27167808, 'steps': 141498, 'loss/train': 0.8080989718437195} 08/31/2021 14:55:19 - INFO - __main__ - Step 141500: {'lr': 4.059266527646016e-06, 'samples': 27168000, 'steps': 141499, 'loss/train': 1.2402127981185913} 08/31/2021 14:55:19 - INFO - __main__ - Step 141501: {'lr': 4.05831416672911e-06, 'samples': 27168192, 'steps': 141500, 'loss/train': 1.0669924020767212} 08/31/2021 14:55:21 - INFO - __main__ - Step 141502: {'lr': 4.0573619166297536e-06, 'samples': 27168384, 'steps': 141501, 'loss/train': 1.6344385147094727} 08/31/2021 14:55:21 - INFO - __main__ - Step 141503: {'lr': 4.0564097773483356e-06, 'samples': 27168576, 'steps': 141502, 'loss/train': 1.3676549196243286} 08/31/2021 14:55:22 - INFO - __main__ - Step 141504: {'lr': 4.055457748885299e-06, 'samples': 27168768, 'steps': 141503, 'loss/train': 1.3767086267471313} 08/31/2021 14:55:22 - INFO - __main__ - Step 141505: {'lr': 4.05450583124109e-06, 'samples': 27168960, 'steps': 141504, 'loss/train': 0.8084884285926819} 08/31/2021 14:55:22 - INFO - __main__ - Step 141506: {'lr': 4.053554024416123e-06, 'samples': 27169152, 'steps': 141505, 'loss/train': 0.8125336766242981} 08/31/2021 14:55:24 - INFO - __main__ - Step 141507: {'lr': 4.052602328410842e-06, 'samples': 27169344, 'steps': 141506, 'loss/train': 1.028220772743225} 08/31/2021 14:55:25 - INFO - __main__ - Step 141508: {'lr': 4.051650743225666e-06, 'samples': 27169536, 'steps': 141507, 'loss/train': 0.9417174458503723} 08/31/2021 14:55:25 - INFO - __main__ - Step 141509: {'lr': 4.050699268861008e-06, 'samples': 27169728, 'steps': 141508, 'loss/train': 1.3799227476119995} 08/31/2021 14:55:25 - INFO - __main__ - Step 141510: {'lr': 4.049747905317314e-06, 'samples': 27169920, 'steps': 141509, 'loss/train': 0.023525573313236237} 08/31/2021 14:55:26 - INFO - __main__ - Step 141511: {'lr': 4.048796652594999e-06, 'samples': 27170112, 'steps': 141510, 'loss/train': 1.546891689300537} 08/31/2021 14:55:26 - INFO - __main__ - Step 141512: {'lr': 4.047845510694509e-06, 'samples': 27170304, 'steps': 141511, 'loss/train': 0.9260199069976807} 08/31/2021 14:55:28 - INFO - __main__ - Step 141513: {'lr': 4.046894479616259e-06, 'samples': 27170496, 'steps': 141512, 'loss/train': 1.1401251554489136} 08/31/2021 14:55:28 - INFO - __main__ - Step 141514: {'lr': 4.045943559360693e-06, 'samples': 27170688, 'steps': 141513, 'loss/train': 0.7206896543502808} 08/31/2021 14:55:28 - INFO - __main__ - Step 141515: {'lr': 4.044992749928228e-06, 'samples': 27170880, 'steps': 141514, 'loss/train': 1.2356882095336914} 08/31/2021 14:55:29 - INFO - __main__ - Step 141516: {'lr': 4.04404205131928e-06, 'samples': 27171072, 'steps': 141515, 'loss/train': 0.7073811292648315} 08/31/2021 14:55:29 - INFO - __main__ - Step 141517: {'lr': 4.043091463534321e-06, 'samples': 27171264, 'steps': 141516, 'loss/train': 0.8411159515380859} 08/31/2021 14:55:31 - INFO - __main__ - Step 141518: {'lr': 4.0421409865737115e-06, 'samples': 27171456, 'steps': 141517, 'loss/train': 1.052378535270691} 08/31/2021 14:55:31 - INFO - __main__ - Step 141519: {'lr': 4.041190620437951e-06, 'samples': 27171648, 'steps': 141518, 'loss/train': 0.9080609083175659} 08/31/2021 14:55:31 - INFO - __main__ - Step 141520: {'lr': 4.040240365127401e-06, 'samples': 27171840, 'steps': 141519, 'loss/train': 0.7231276631355286} 08/31/2021 14:55:32 - INFO - __main__ - Step 141521: {'lr': 4.039290220642533e-06, 'samples': 27172032, 'steps': 141520, 'loss/train': 0.7842312455177307} 08/31/2021 14:55:32 - INFO - __main__ - Step 141522: {'lr': 4.038340186983791e-06, 'samples': 27172224, 'steps': 141521, 'loss/train': 1.2658708095550537} 08/31/2021 14:55:33 - INFO - __main__ - Step 141523: {'lr': 4.037390264151564e-06, 'samples': 27172416, 'steps': 141522, 'loss/train': 1.011114478111267} 08/31/2021 14:55:34 - INFO - __main__ - Step 141524: {'lr': 4.036440452146267e-06, 'samples': 27172608, 'steps': 141523, 'loss/train': 0.8660409450531006} 08/31/2021 14:55:34 - INFO - __main__ - Step 141525: {'lr': 4.035490750968401e-06, 'samples': 27172800, 'steps': 141524, 'loss/train': 1.7794831991195679} 08/31/2021 14:55:35 - INFO - __main__ - Step 141526: {'lr': 4.034541160618327e-06, 'samples': 27172992, 'steps': 141525, 'loss/train': 0.8178563117980957} 08/31/2021 14:55:35 - INFO - __main__ - Step 141527: {'lr': 4.033591681096488e-06, 'samples': 27173184, 'steps': 141526, 'loss/train': 1.0422805547714233} 08/31/2021 14:55:36 - INFO - __main__ - Step 141528: {'lr': 4.032642312403329e-06, 'samples': 27173376, 'steps': 141527, 'loss/train': 1.0959538221359253} 08/31/2021 14:55:37 - INFO - __main__ - Step 141529: {'lr': 4.0316930545392376e-06, 'samples': 27173568, 'steps': 141528, 'loss/train': 1.398078441619873} 08/31/2021 14:55:37 - INFO - __main__ - Step 141530: {'lr': 4.030743907504686e-06, 'samples': 27173760, 'steps': 141529, 'loss/train': 1.005210041999817} 08/31/2021 14:55:38 - INFO - __main__ - Step 141531: {'lr': 4.029794871300091e-06, 'samples': 27173952, 'steps': 141530, 'loss/train': 1.2875765562057495} 08/31/2021 14:55:38 - INFO - __main__ - Step 141532: {'lr': 4.028845945925868e-06, 'samples': 27174144, 'steps': 141531, 'loss/train': 1.3061859607696533} 08/31/2021 14:55:40 - INFO - __main__ - Step 141533: {'lr': 4.027897131382463e-06, 'samples': 27174336, 'steps': 141532, 'loss/train': 1.7469466924667358} 08/31/2021 14:55:40 - INFO - __main__ - Step 141534: {'lr': 4.02694842767029e-06, 'samples': 27174528, 'steps': 141533, 'loss/train': 1.4044517278671265} 08/31/2021 14:55:40 - INFO - __main__ - Step 141535: {'lr': 4.025999834789768e-06, 'samples': 27174720, 'steps': 141534, 'loss/train': 1.6030949354171753} 08/31/2021 14:55:41 - INFO - __main__ - Step 141536: {'lr': 4.025051352741366e-06, 'samples': 27174912, 'steps': 141535, 'loss/train': 0.11080013960599899} 08/31/2021 14:55:41 - INFO - __main__ - Step 141537: {'lr': 4.024102981525446e-06, 'samples': 27175104, 'steps': 141536, 'loss/train': 1.0146896839141846} 08/31/2021 14:55:42 - INFO - __main__ - Step 141538: {'lr': 4.0231547211424805e-06, 'samples': 27175296, 'steps': 141537, 'loss/train': 1.2810325622558594} 08/31/2021 14:55:43 - INFO - __main__ - Step 141539: {'lr': 4.0222065715928845e-06, 'samples': 27175488, 'steps': 141538, 'loss/train': 0.3805030584335327} 08/31/2021 14:55:43 - INFO - __main__ - Step 141540: {'lr': 4.021258532877075e-06, 'samples': 27175680, 'steps': 141539, 'loss/train': 1.423872470855713} 08/31/2021 14:55:44 - INFO - __main__ - Step 141541: {'lr': 4.020310604995498e-06, 'samples': 27175872, 'steps': 141540, 'loss/train': 0.8637069463729858} 08/31/2021 14:55:44 - INFO - __main__ - Step 141542: {'lr': 4.019362787948566e-06, 'samples': 27176064, 'steps': 141541, 'loss/train': 0.764111340045929} 08/31/2021 14:55:44 - INFO - __main__ - Step 141543: {'lr': 4.018415081736726e-06, 'samples': 27176256, 'steps': 141542, 'loss/train': 1.2887998819351196} 08/31/2021 14:55:46 - INFO - __main__ - Step 141544: {'lr': 4.017467486360393e-06, 'samples': 27176448, 'steps': 141543, 'loss/train': 1.5461010932922363} 08/31/2021 14:55:46 - INFO - __main__ - Step 141545: {'lr': 4.016520001819984e-06, 'samples': 27176640, 'steps': 141544, 'loss/train': 1.5410727262496948} 08/31/2021 14:55:47 - INFO - __main__ - Step 141546: {'lr': 4.015572628115943e-06, 'samples': 27176832, 'steps': 141545, 'loss/train': 0.9588175415992737} 08/31/2021 14:55:47 - INFO - __main__ - Step 141547: {'lr': 4.014625365248714e-06, 'samples': 27177024, 'steps': 141546, 'loss/train': 0.5364202857017517} 08/31/2021 14:55:47 - INFO - __main__ - Step 141548: {'lr': 4.013678213218685e-06, 'samples': 27177216, 'steps': 141547, 'loss/train': 1.3319801092147827} 08/31/2021 14:55:49 - INFO - __main__ - Step 141549: {'lr': 4.012731172026274e-06, 'samples': 27177408, 'steps': 141548, 'loss/train': 0.455323189496994} 08/31/2021 14:55:50 - INFO - __main__ - Step 141550: {'lr': 4.011784241671923e-06, 'samples': 27177600, 'steps': 141549, 'loss/train': 1.052556037902832} 08/31/2021 14:55:50 - INFO - __main__ - Step 141551: {'lr': 4.010837422156105e-06, 'samples': 27177792, 'steps': 141550, 'loss/train': 0.20572322607040405} 08/31/2021 14:55:51 - INFO - __main__ - Step 141552: {'lr': 4.009890713479181e-06, 'samples': 27177984, 'steps': 141551, 'loss/train': 0.9532491564750671} 08/31/2021 14:55:51 - INFO - __main__ - Step 141553: {'lr': 4.008944115641594e-06, 'samples': 27178176, 'steps': 141552, 'loss/train': 0.02016892284154892} 08/31/2021 14:55:51 - INFO - __main__ - Step 141554: {'lr': 4.007997628643817e-06, 'samples': 27178368, 'steps': 141553, 'loss/train': 0.01731075532734394} 08/31/2021 14:55:53 - INFO - __main__ - Step 141555: {'lr': 4.00705125248621e-06, 'samples': 27178560, 'steps': 141554, 'loss/train': 0.827782928943634} 08/31/2021 14:55:53 - INFO - __main__ - Step 141556: {'lr': 4.006104987169246e-06, 'samples': 27178752, 'steps': 141555, 'loss/train': 0.7836652994155884} 08/31/2021 14:55:54 - INFO - __main__ - Step 141557: {'lr': 4.005158832693312e-06, 'samples': 27178944, 'steps': 141556, 'loss/train': 0.26026657223701477} 08/31/2021 14:55:54 - INFO - __main__ - Step 141558: {'lr': 4.004212789058909e-06, 'samples': 27179136, 'steps': 141557, 'loss/train': 0.9761276245117188} 08/31/2021 14:55:54 - INFO - __main__ - Step 141559: {'lr': 4.0032668562663685e-06, 'samples': 27179328, 'steps': 141558, 'loss/train': 1.1995278596878052} 08/31/2021 14:55:56 - INFO - __main__ - Step 141560: {'lr': 4.002321034316164e-06, 'samples': 27179520, 'steps': 141559, 'loss/train': 1.3535431623458862} 08/31/2021 14:55:57 - INFO - __main__ - Step 141561: {'lr': 4.001375323208739e-06, 'samples': 27179712, 'steps': 141560, 'loss/train': 0.9089064598083496} 08/31/2021 14:55:57 - INFO - __main__ - Step 141562: {'lr': 4.000429722944482e-06, 'samples': 27179904, 'steps': 141561, 'loss/train': 1.0725407600402832} 08/31/2021 14:55:58 - INFO - __main__ - Step 141563: {'lr': 3.999484233523837e-06, 'samples': 27180096, 'steps': 141562, 'loss/train': 1.2862504720687866} 08/31/2021 14:55:58 - INFO - __main__ - Step 141564: {'lr': 3.9985388549472205e-06, 'samples': 27180288, 'steps': 141563, 'loss/train': 0.4189241826534271} 08/31/2021 14:56:00 - INFO - __main__ - Step 141565: {'lr': 3.997593587215076e-06, 'samples': 27180480, 'steps': 141564, 'loss/train': 1.0456340312957764} 08/31/2021 14:56:00 - INFO - __main__ - Step 141566: {'lr': 3.996648430327821e-06, 'samples': 27180672, 'steps': 141565, 'loss/train': 1.20233154296875} 08/31/2021 14:56:00 - INFO - __main__ - Step 141567: {'lr': 3.99570338428587e-06, 'samples': 27180864, 'steps': 141566, 'loss/train': 0.9613941311836243} 08/31/2021 14:56:01 - INFO - __main__ - Step 141568: {'lr': 3.994758449089669e-06, 'samples': 27181056, 'steps': 141567, 'loss/train': 1.4029674530029297} 08/31/2021 14:56:01 - INFO - __main__ - Step 141569: {'lr': 3.993813624739634e-06, 'samples': 27181248, 'steps': 141568, 'loss/train': 1.2030913829803467} 08/31/2021 14:56:02 - INFO - __main__ - Step 141570: {'lr': 3.992868911236181e-06, 'samples': 27181440, 'steps': 141569, 'loss/train': 1.288534164428711} 08/31/2021 14:56:03 - INFO - __main__ - Step 141571: {'lr': 3.991924308579753e-06, 'samples': 27181632, 'steps': 141570, 'loss/train': 1.6491867303848267} 08/31/2021 14:56:03 - INFO - __main__ - Step 141572: {'lr': 3.990979816770768e-06, 'samples': 27181824, 'steps': 141571, 'loss/train': 0.5715780854225159} 08/31/2021 14:56:04 - INFO - __main__ - Step 141573: {'lr': 3.990035435809641e-06, 'samples': 27182016, 'steps': 141572, 'loss/train': 1.9185597896575928} 08/31/2021 14:56:04 - INFO - __main__ - Step 141574: {'lr': 3.989091165696817e-06, 'samples': 27182208, 'steps': 141573, 'loss/train': 1.6129050254821777} 08/31/2021 14:56:06 - INFO - __main__ - Step 141575: {'lr': 3.988147006432713e-06, 'samples': 27182400, 'steps': 141574, 'loss/train': 0.8610180616378784} 08/31/2021 14:56:06 - INFO - __main__ - Step 141576: {'lr': 3.987202958017744e-06, 'samples': 27182592, 'steps': 141575, 'loss/train': 0.7976706027984619} 08/31/2021 14:56:06 - INFO - __main__ - Step 141577: {'lr': 3.986259020452354e-06, 'samples': 27182784, 'steps': 141576, 'loss/train': 0.845710813999176} 08/31/2021 14:56:07 - INFO - __main__ - Step 141578: {'lr': 3.98531519373696e-06, 'samples': 27182976, 'steps': 141577, 'loss/train': 0.8234913945198059} 08/31/2021 14:56:07 - INFO - __main__ - Step 141579: {'lr': 3.984371477871979e-06, 'samples': 27183168, 'steps': 141578, 'loss/train': 1.4793620109558105} 08/31/2021 14:56:09 - INFO - __main__ - Step 141580: {'lr': 3.983427872857881e-06, 'samples': 27183360, 'steps': 141579, 'loss/train': 1.0096278190612793} 08/31/2021 14:56:09 - INFO - __main__ - Step 141581: {'lr': 3.982484378695e-06, 'samples': 27183552, 'steps': 141580, 'loss/train': 0.9004018306732178} 08/31/2021 14:56:09 - INFO - __main__ - Step 141582: {'lr': 3.981540995383864e-06, 'samples': 27183744, 'steps': 141581, 'loss/train': 1.374771237373352} 08/31/2021 14:56:10 - INFO - __main__ - Step 141583: {'lr': 3.9805977229248054e-06, 'samples': 27183936, 'steps': 141582, 'loss/train': 0.9201149344444275} 08/31/2021 14:56:10 - INFO - __main__ - Step 141584: {'lr': 3.979654561318324e-06, 'samples': 27184128, 'steps': 141583, 'loss/train': 1.2412137985229492} 08/31/2021 14:56:12 - INFO - __main__ - Step 141585: {'lr': 3.9787115105647806e-06, 'samples': 27184320, 'steps': 141584, 'loss/train': 0.6649075150489807} 08/31/2021 14:56:12 - INFO - __main__ - Step 141586: {'lr': 3.977768570664675e-06, 'samples': 27184512, 'steps': 141585, 'loss/train': 1.2073336839675903} 08/31/2021 14:56:13 - INFO - __main__ - Step 141587: {'lr': 3.976825741618367e-06, 'samples': 27184704, 'steps': 141586, 'loss/train': 1.079513669013977} 08/31/2021 14:56:13 - INFO - __main__ - Step 141588: {'lr': 3.975883023426302e-06, 'samples': 27184896, 'steps': 141587, 'loss/train': 0.02737291529774666} 08/31/2021 14:56:13 - INFO - __main__ - Step 141589: {'lr': 3.974940416088896e-06, 'samples': 27185088, 'steps': 141588, 'loss/train': 0.9685130715370178} 08/31/2021 14:56:15 - INFO - __main__ - Step 141590: {'lr': 3.97399791960662e-06, 'samples': 27185280, 'steps': 141589, 'loss/train': 0.5997893214225769} 08/31/2021 14:56:15 - INFO - __main__ - Step 141591: {'lr': 3.9730555339798355e-06, 'samples': 27185472, 'steps': 141590, 'loss/train': 0.9278257489204407} 08/31/2021 14:56:16 - INFO - __main__ - Step 141592: {'lr': 3.972113259209015e-06, 'samples': 27185664, 'steps': 141591, 'loss/train': 1.679355263710022} 08/31/2021 14:56:16 - INFO - __main__ - Step 141593: {'lr': 3.9711710952945736e-06, 'samples': 27185856, 'steps': 141592, 'loss/train': 1.48348069190979} 08/31/2021 14:56:16 - INFO - __main__ - Step 141594: {'lr': 3.9702290422369005e-06, 'samples': 27186048, 'steps': 141593, 'loss/train': 1.1449872255325317} 08/31/2021 14:56:17 - INFO - __main__ - Step 141595: {'lr': 3.96928710003644e-06, 'samples': 27186240, 'steps': 141594, 'loss/train': 0.8949043154716492} 08/31/2021 14:56:18 - INFO - __main__ - Step 141596: {'lr': 3.968345268693635e-06, 'samples': 27186432, 'steps': 141595, 'loss/train': 0.7319518327713013} 08/31/2021 14:56:19 - INFO - __main__ - Step 141597: {'lr': 3.967403548208903e-06, 'samples': 27186624, 'steps': 141596, 'loss/train': 0.9610642194747925} 08/31/2021 14:56:19 - INFO - __main__ - Step 141598: {'lr': 3.96646193858266e-06, 'samples': 27186816, 'steps': 141597, 'loss/train': 0.6438720226287842} 08/31/2021 14:56:19 - INFO - __main__ - Step 141599: {'lr': 3.965520439815323e-06, 'samples': 27187008, 'steps': 141598, 'loss/train': 0.6366215944290161} 08/31/2021 14:56:20 - INFO - __main__ - Step 141600: {'lr': 3.964579051907335e-06, 'samples': 27187200, 'steps': 141599, 'loss/train': 1.060752034187317} 08/31/2021 14:56:21 - INFO - __main__ - Step 141601: {'lr': 3.963637774859114e-06, 'samples': 27187392, 'steps': 141600, 'loss/train': 1.3698066473007202} 08/31/2021 14:56:22 - INFO - __main__ - Step 141602: {'lr': 3.9626966086710735e-06, 'samples': 27187584, 'steps': 141601, 'loss/train': 0.19853119552135468} 08/31/2021 14:56:22 - INFO - __main__ - Step 141603: {'lr': 3.96175555334366e-06, 'samples': 27187776, 'steps': 141602, 'loss/train': 0.9968665242195129} 08/31/2021 14:56:23 - INFO - __main__ - Step 141604: {'lr': 3.960814608877261e-06, 'samples': 27187968, 'steps': 141603, 'loss/train': 1.4495593309402466} 08/31/2021 14:56:23 - INFO - __main__ - Step 141605: {'lr': 3.959873775272349e-06, 'samples': 27188160, 'steps': 141604, 'loss/train': 0.9701135158538818} 08/31/2021 14:56:25 - INFO - __main__ - Step 141606: {'lr': 3.958933052529312e-06, 'samples': 27188352, 'steps': 141605, 'loss/train': 0.937767505645752} 08/31/2021 14:56:25 - INFO - __main__ - Step 141607: {'lr': 3.957992440648567e-06, 'samples': 27188544, 'steps': 141606, 'loss/train': 1.5865732431411743} 08/31/2021 14:56:25 - INFO - __main__ - Step 141608: {'lr': 3.957051939630557e-06, 'samples': 27188736, 'steps': 141607, 'loss/train': 0.10133387893438339} 08/31/2021 14:56:26 - INFO - __main__ - Step 141609: {'lr': 3.956111549475699e-06, 'samples': 27188928, 'steps': 141608, 'loss/train': 1.7028520107269287} 08/31/2021 14:56:26 - INFO - __main__ - Step 141610: {'lr': 3.955171270184438e-06, 'samples': 27189120, 'steps': 141609, 'loss/train': 0.11152588576078415} 08/31/2021 14:56:28 - INFO - __main__ - Step 141611: {'lr': 3.954231101757188e-06, 'samples': 27189312, 'steps': 141610, 'loss/train': 0.11935596168041229} 08/31/2021 14:56:29 - INFO - __main__ - Step 141612: {'lr': 3.953291044194341e-06, 'samples': 27189504, 'steps': 141611, 'loss/train': 1.1633005142211914} 08/31/2021 14:56:29 - INFO - __main__ - Step 141613: {'lr': 3.952351097496337e-06, 'samples': 27189696, 'steps': 141612, 'loss/train': 0.6269323229789734} 08/31/2021 14:56:29 - INFO - __main__ - Step 141614: {'lr': 3.951411261663623e-06, 'samples': 27189888, 'steps': 141613, 'loss/train': 0.7291042804718018} 08/31/2021 14:56:30 - INFO - __main__ - Step 141615: {'lr': 3.950471536696615e-06, 'samples': 27190080, 'steps': 141614, 'loss/train': 1.1781907081604004} 08/31/2021 14:56:32 - INFO - __main__ - Step 141616: {'lr': 3.9495319225957e-06, 'samples': 27190272, 'steps': 141615, 'loss/train': 0.579355776309967} 08/31/2021 14:56:32 - INFO - __main__ - Step 141617: {'lr': 3.948592419361352e-06, 'samples': 27190464, 'steps': 141616, 'loss/train': 1.2709388732910156} 08/31/2021 14:56:33 - INFO - __main__ - Step 141618: {'lr': 3.947653026993958e-06, 'samples': 27190656, 'steps': 141617, 'loss/train': 0.027081146836280823} 08/31/2021 14:56:33 - INFO - __main__ - Step 141619: {'lr': 3.9467137454939905e-06, 'samples': 27190848, 'steps': 141618, 'loss/train': 1.2004441022872925} 08/31/2021 14:56:33 - INFO - __main__ - Step 141620: {'lr': 3.94577457486181e-06, 'samples': 27191040, 'steps': 141619, 'loss/train': 1.2551229000091553} 08/31/2021 14:56:34 - INFO - __main__ - Step 141621: {'lr': 3.944835515097861e-06, 'samples': 27191232, 'steps': 141620, 'loss/train': 0.04122088477015495} 08/31/2021 14:56:35 - INFO - __main__ - Step 141622: {'lr': 3.9438965662025875e-06, 'samples': 27191424, 'steps': 141621, 'loss/train': 1.2901839017868042} 08/31/2021 14:56:36 - INFO - __main__ - Step 141623: {'lr': 3.942957728176377e-06, 'samples': 27191616, 'steps': 141622, 'loss/train': 0.30210375785827637} 08/31/2021 14:56:36 - INFO - __main__ - Step 141624: {'lr': 3.942019001019675e-06, 'samples': 27191808, 'steps': 141623, 'loss/train': 4.171998977661133} 08/31/2021 14:56:36 - INFO - __main__ - Step 141625: {'lr': 3.941080384732926e-06, 'samples': 27192000, 'steps': 141624, 'loss/train': 1.3898757696151733} 08/31/2021 14:56:37 - INFO - __main__ - Step 141626: {'lr': 3.9401418793165165e-06, 'samples': 27192192, 'steps': 141625, 'loss/train': 0.8716810941696167} 08/31/2021 14:56:38 - INFO - __main__ - Step 141627: {'lr': 3.939203484770865e-06, 'samples': 27192384, 'steps': 141626, 'loss/train': 1.2229524850845337} 08/31/2021 14:56:39 - INFO - __main__ - Step 141628: {'lr': 3.938265201096442e-06, 'samples': 27192576, 'steps': 141627, 'loss/train': 0.7603224515914917} 08/31/2021 14:56:39 - INFO - __main__ - Step 141629: {'lr': 3.937327028293608e-06, 'samples': 27192768, 'steps': 141628, 'loss/train': 0.3655274510383606} 08/31/2021 14:56:39 - INFO - __main__ - Step 141630: {'lr': 3.936388966362836e-06, 'samples': 27192960, 'steps': 141629, 'loss/train': 1.088605284690857} 08/31/2021 14:56:40 - INFO - __main__ - Step 141631: {'lr': 3.935451015304514e-06, 'samples': 27193152, 'steps': 141630, 'loss/train': 0.238754540681839} 08/31/2021 14:56:42 - INFO - __main__ - Step 141632: {'lr': 3.934513175119114e-06, 'samples': 27193344, 'steps': 141631, 'loss/train': 1.2243528366088867} 08/31/2021 14:56:42 - INFO - __main__ - Step 141633: {'lr': 3.933575445807025e-06, 'samples': 27193536, 'steps': 141632, 'loss/train': 0.6729673147201538} 08/31/2021 14:56:43 - INFO - __main__ - Step 141634: {'lr': 3.932637827368635e-06, 'samples': 27193728, 'steps': 141633, 'loss/train': 0.44035804271698} 08/31/2021 14:56:43 - INFO - __main__ - Step 141635: {'lr': 3.931700319804415e-06, 'samples': 27193920, 'steps': 141634, 'loss/train': 0.4290226101875305} 08/31/2021 14:56:43 - INFO - __main__ - Step 141636: {'lr': 3.930762923114783e-06, 'samples': 27194112, 'steps': 141635, 'loss/train': 0.5784733295440674} 08/31/2021 14:56:45 - INFO - __main__ - Step 141637: {'lr': 3.929825637300155e-06, 'samples': 27194304, 'steps': 141636, 'loss/train': 0.192193403840065} 08/31/2021 14:56:46 - INFO - __main__ - Step 141638: {'lr': 3.928888462360919e-06, 'samples': 27194496, 'steps': 141637, 'loss/train': 0.7964544296264648} 08/31/2021 14:56:46 - INFO - __main__ - Step 141639: {'lr': 3.927951398297547e-06, 'samples': 27194688, 'steps': 141638, 'loss/train': 1.5863838195800781} 08/31/2021 14:56:46 - INFO - __main__ - Step 141640: {'lr': 3.927014445110455e-06, 'samples': 27194880, 'steps': 141639, 'loss/train': 1.0840579271316528} 08/31/2021 14:56:47 - INFO - __main__ - Step 141641: {'lr': 3.926077602800032e-06, 'samples': 27195072, 'steps': 141640, 'loss/train': 1.0258921384811401} 08/31/2021 14:56:47 - INFO - __main__ - Step 141642: {'lr': 3.9251408713667505e-06, 'samples': 27195264, 'steps': 141641, 'loss/train': 0.04314885661005974} 08/31/2021 14:56:49 - INFO - __main__ - Step 141643: {'lr': 3.92420425081097e-06, 'samples': 27195456, 'steps': 141642, 'loss/train': 1.2306824922561646} 08/31/2021 14:56:49 - INFO - __main__ - Step 141644: {'lr': 3.923267741133163e-06, 'samples': 27195648, 'steps': 141643, 'loss/train': 0.8417636752128601} 08/31/2021 14:56:49 - INFO - __main__ - Step 141645: {'lr': 3.9223313423337455e-06, 'samples': 27195840, 'steps': 141644, 'loss/train': 1.1550134420394897} 08/31/2021 14:56:50 - INFO - __main__ - Step 141646: {'lr': 3.921395054413135e-06, 'samples': 27196032, 'steps': 141645, 'loss/train': 0.4495135247707367} 08/31/2021 14:56:50 - INFO - __main__ - Step 141647: {'lr': 3.9204588773717185e-06, 'samples': 27196224, 'steps': 141646, 'loss/train': 1.060025691986084} 08/31/2021 14:56:52 - INFO - __main__ - Step 141648: {'lr': 3.9195228112099415e-06, 'samples': 27196416, 'steps': 141647, 'loss/train': 0.8894687294960022} 08/31/2021 14:56:52 - INFO - __main__ - Step 141649: {'lr': 3.918586855928247e-06, 'samples': 27196608, 'steps': 141648, 'loss/train': 1.3397754430770874} 08/31/2021 14:56:52 - INFO - __main__ - Step 141650: {'lr': 3.917651011527051e-06, 'samples': 27196800, 'steps': 141649, 'loss/train': 1.13241708278656} 08/31/2021 14:56:53 - INFO - __main__ - Step 141651: {'lr': 3.916715278006744e-06, 'samples': 27196992, 'steps': 141650, 'loss/train': 1.4647791385650635} 08/31/2021 14:56:53 - INFO - __main__ - Step 141652: {'lr': 3.915779655367768e-06, 'samples': 27197184, 'steps': 141651, 'loss/train': 0.9909791946411133} 08/31/2021 14:56:55 - INFO - __main__ - Step 141653: {'lr': 3.914844143610541e-06, 'samples': 27197376, 'steps': 141652, 'loss/train': 5.387370586395264} 08/31/2021 14:56:55 - INFO - __main__ - Step 141654: {'lr': 3.9139087427355055e-06, 'samples': 27197568, 'steps': 141653, 'loss/train': 1.1151771545410156} 08/31/2021 14:56:55 - INFO - __main__ - Step 141655: {'lr': 3.9129734527430515e-06, 'samples': 27197760, 'steps': 141654, 'loss/train': 1.2453891038894653} 08/31/2021 14:56:56 - INFO - __main__ - Step 141656: {'lr': 3.912038273633622e-06, 'samples': 27197952, 'steps': 141655, 'loss/train': 0.6100502610206604} 08/31/2021 14:56:56 - INFO - __main__ - Step 141657: {'lr': 3.911103205407635e-06, 'samples': 27198144, 'steps': 141656, 'loss/train': 0.46999308466911316} 08/31/2021 14:56:56 - INFO - __main__ - Step 141658: {'lr': 3.910168248065504e-06, 'samples': 27198336, 'steps': 141657, 'loss/train': 1.3576183319091797} 08/31/2021 14:56:58 - INFO - __main__ - Step 141659: {'lr': 3.909233401607648e-06, 'samples': 27198528, 'steps': 141658, 'loss/train': 0.30483514070510864} 08/31/2021 14:56:58 - INFO - __main__ - Step 141660: {'lr': 3.90829866603451e-06, 'samples': 27198720, 'steps': 141659, 'loss/train': 0.7228787541389465} 08/31/2021 14:56:59 - INFO - __main__ - Step 141661: {'lr': 3.907364041346478e-06, 'samples': 27198912, 'steps': 141660, 'loss/train': 1.075919270515442} 08/31/2021 14:56:59 - INFO - __main__ - Step 141662: {'lr': 3.906429527543997e-06, 'samples': 27199104, 'steps': 141661, 'loss/train': 1.5044543743133545} 08/31/2021 14:56:59 - INFO - __main__ - Step 141663: {'lr': 3.9054951246274835e-06, 'samples': 27199296, 'steps': 141662, 'loss/train': 1.1950199604034424} 08/31/2021 14:57:01 - INFO - __main__ - Step 141664: {'lr': 3.904560832597354e-06, 'samples': 27199488, 'steps': 141663, 'loss/train': 0.7885874509811401} 08/31/2021 14:57:01 - INFO - __main__ - Step 141665: {'lr': 3.903626651454023e-06, 'samples': 27199680, 'steps': 141664, 'loss/train': 1.0352725982666016} 08/31/2021 14:57:02 - INFO - __main__ - Step 141666: {'lr': 3.902692581197936e-06, 'samples': 27199872, 'steps': 141665, 'loss/train': 1.2892264127731323} 08/31/2021 14:57:02 - INFO - __main__ - Step 141667: {'lr': 3.901758621829482e-06, 'samples': 27200064, 'steps': 141666, 'loss/train': 1.1580559015274048} 08/31/2021 14:57:02 - INFO - __main__ - Step 141668: {'lr': 3.900824773349105e-06, 'samples': 27200256, 'steps': 141667, 'loss/train': 1.5796489715576172} 08/31/2021 14:57:04 - INFO - __main__ - Step 141669: {'lr': 3.899891035757219e-06, 'samples': 27200448, 'steps': 141668, 'loss/train': 0.9567089676856995} 08/31/2021 14:57:05 - INFO - __main__ - Step 141670: {'lr': 3.898957409054243e-06, 'samples': 27200640, 'steps': 141669, 'loss/train': 5.676867485046387} 08/31/2021 14:57:05 - INFO - __main__ - Step 141671: {'lr': 3.898023893240593e-06, 'samples': 27200832, 'steps': 141670, 'loss/train': 0.5713093280792236} 08/31/2021 14:57:06 - INFO - __main__ - Step 141672: {'lr': 3.897090488316712e-06, 'samples': 27201024, 'steps': 141671, 'loss/train': 0.9165182113647461} 08/31/2021 14:57:06 - INFO - __main__ - Step 141673: {'lr': 3.896157194283018e-06, 'samples': 27201216, 'steps': 141672, 'loss/train': 0.6917372345924377} 08/31/2021 14:57:08 - INFO - __main__ - Step 141674: {'lr': 3.895224011139869e-06, 'samples': 27201408, 'steps': 141673, 'loss/train': 1.5206133127212524} 08/31/2021 14:57:08 - INFO - __main__ - Step 141675: {'lr': 3.894290938887768e-06, 'samples': 27201600, 'steps': 141674, 'loss/train': 0.7970404624938965} 08/31/2021 14:57:08 - INFO - __main__ - Step 141676: {'lr': 3.893357977527101e-06, 'samples': 27201792, 'steps': 141675, 'loss/train': 1.0263776779174805} 08/31/2021 14:57:09 - INFO - __main__ - Step 141677: {'lr': 3.892425127058286e-06, 'samples': 27201984, 'steps': 141676, 'loss/train': 0.6718407273292542} 08/31/2021 14:57:09 - INFO - __main__ - Step 141678: {'lr': 3.891492387481738e-06, 'samples': 27202176, 'steps': 141677, 'loss/train': 0.75889652967453} 08/31/2021 14:57:11 - INFO - __main__ - Step 141679: {'lr': 3.890559758797901e-06, 'samples': 27202368, 'steps': 141678, 'loss/train': 1.2171425819396973} 08/31/2021 14:57:11 - INFO - __main__ - Step 141680: {'lr': 3.889627241007165e-06, 'samples': 27202560, 'steps': 141679, 'loss/train': 1.4161427021026611} 08/31/2021 14:57:12 - INFO - __main__ - Step 141681: {'lr': 3.888694834109974e-06, 'samples': 27202752, 'steps': 141680, 'loss/train': 1.5087662935256958} 08/31/2021 14:57:12 - INFO - __main__ - Step 141682: {'lr': 3.887762538106715e-06, 'samples': 27202944, 'steps': 141681, 'loss/train': 1.0825450420379639} 08/31/2021 14:57:12 - INFO - __main__ - Step 141683: {'lr': 3.886830352997861e-06, 'samples': 27203136, 'steps': 141682, 'loss/train': 1.6280122995376587} 08/31/2021 14:57:13 - INFO - __main__ - Step 141684: {'lr': 3.8858982787838005e-06, 'samples': 27203328, 'steps': 141683, 'loss/train': 0.9567675590515137} 08/31/2021 14:57:14 - INFO - __main__ - Step 141685: {'lr': 3.88496631546495e-06, 'samples': 27203520, 'steps': 141684, 'loss/train': 1.5137146711349487} 08/31/2021 14:57:15 - INFO - __main__ - Step 141686: {'lr': 3.8840344630417526e-06, 'samples': 27203712, 'steps': 141685, 'loss/train': 0.7546533942222595} 08/31/2021 14:57:15 - INFO - __main__ - Step 141687: {'lr': 3.883102721514597e-06, 'samples': 27203904, 'steps': 141686, 'loss/train': 1.1336966753005981} 08/31/2021 14:57:15 - INFO - __main__ - Step 141688: {'lr': 3.8821710908839295e-06, 'samples': 27204096, 'steps': 141687, 'loss/train': 1.0896079540252686} 08/31/2021 14:57:16 - INFO - __main__ - Step 141689: {'lr': 3.881239571150136e-06, 'samples': 27204288, 'steps': 141688, 'loss/train': 0.590669572353363} 08/31/2021 14:57:18 - INFO - __main__ - Step 141690: {'lr': 3.880308162313662e-06, 'samples': 27204480, 'steps': 141689, 'loss/train': 1.127170443534851} 08/31/2021 14:57:18 - INFO - __main__ - Step 141691: {'lr': 3.879376864374923e-06, 'samples': 27204672, 'steps': 141690, 'loss/train': 0.845791757106781} 08/31/2021 14:57:18 - INFO - __main__ - Step 141692: {'lr': 3.878445677334363e-06, 'samples': 27204864, 'steps': 141691, 'loss/train': 1.0231105089187622} 08/31/2021 14:57:19 - INFO - __main__ - Step 141693: {'lr': 3.877514601192345e-06, 'samples': 27205056, 'steps': 141692, 'loss/train': 0.9956430792808533} 08/31/2021 14:57:19 - INFO - __main__ - Step 141694: {'lr': 3.876583635949338e-06, 'samples': 27205248, 'steps': 141693, 'loss/train': 0.8199685215950012} 08/31/2021 14:57:20 - INFO - __main__ - Step 141695: {'lr': 3.8756527816057596e-06, 'samples': 27205440, 'steps': 141694, 'loss/train': 1.5216774940490723} 08/31/2021 14:57:21 - INFO - __main__ - Step 141696: {'lr': 3.8747220381619705e-06, 'samples': 27205632, 'steps': 141695, 'loss/train': 1.7484619617462158} 08/31/2021 14:57:21 - INFO - __main__ - Step 141697: {'lr': 3.8737914056184706e-06, 'samples': 27205824, 'steps': 141696, 'loss/train': 1.0455174446105957} 08/31/2021 14:57:22 - INFO - __main__ - Step 141698: {'lr': 3.8728608839756205e-06, 'samples': 27206016, 'steps': 141697, 'loss/train': 0.8866690993309021} 08/31/2021 14:57:22 - INFO - __main__ - Step 141699: {'lr': 3.871930473233892e-06, 'samples': 27206208, 'steps': 141698, 'loss/train': 0.7189335823059082} 08/31/2021 14:57:22 - INFO - __main__ - Step 141700: {'lr': 3.871000173393674e-06, 'samples': 27206400, 'steps': 141699, 'loss/train': 1.0664339065551758} 08/31/2021 14:57:24 - INFO - __main__ - Step 141701: {'lr': 3.870069984455355e-06, 'samples': 27206592, 'steps': 141700, 'loss/train': 1.7592896223068237} 08/31/2021 14:57:24 - INFO - __main__ - Step 141702: {'lr': 3.8691399064194055e-06, 'samples': 27206784, 'steps': 141701, 'loss/train': 1.3102631568908691} 08/31/2021 14:57:25 - INFO - __main__ - Step 141703: {'lr': 3.868209939286216e-06, 'samples': 27206976, 'steps': 141702, 'loss/train': 1.7698278427124023} 08/31/2021 14:57:25 - INFO - __main__ - Step 141704: {'lr': 3.8672800830562016e-06, 'samples': 27207168, 'steps': 141703, 'loss/train': 0.31426703929901123} 08/31/2021 14:57:25 - INFO - __main__ - Step 141705: {'lr': 3.866350337729807e-06, 'samples': 27207360, 'steps': 141704, 'loss/train': 1.326433777809143} 08/31/2021 14:57:27 - INFO - __main__ - Step 141706: {'lr': 3.865420703307421e-06, 'samples': 27207552, 'steps': 141705, 'loss/train': 0.8934119939804077} 08/31/2021 14:57:27 - INFO - __main__ - Step 141707: {'lr': 3.864491179789487e-06, 'samples': 27207744, 'steps': 141706, 'loss/train': 0.6095495223999023} 08/31/2021 14:57:28 - INFO - __main__ - Step 141708: {'lr': 3.863561767176421e-06, 'samples': 27207936, 'steps': 141707, 'loss/train': 0.9005287289619446} 08/31/2021 14:57:28 - INFO - __main__ - Step 141709: {'lr': 3.862632465468613e-06, 'samples': 27208128, 'steps': 141708, 'loss/train': 0.5503246188163757} 08/31/2021 14:57:28 - INFO - __main__ - Step 141710: {'lr': 3.861703274666534e-06, 'samples': 27208320, 'steps': 141709, 'loss/train': 0.8287680745124817} 08/31/2021 14:57:30 - INFO - __main__ - Step 141711: {'lr': 3.860774194770572e-06, 'samples': 27208512, 'steps': 141710, 'loss/train': 0.700629711151123} 08/31/2021 14:57:31 - INFO - __main__ - Step 141712: {'lr': 3.859845225781117e-06, 'samples': 27208704, 'steps': 141711, 'loss/train': 0.9971359968185425} 08/31/2021 14:57:31 - INFO - __main__ - Step 141713: {'lr': 3.858916367698667e-06, 'samples': 27208896, 'steps': 141712, 'loss/train': 1.4369733333587646} 08/31/2021 14:57:31 - INFO - __main__ - Step 141714: {'lr': 3.857987620523557e-06, 'samples': 27209088, 'steps': 141713, 'loss/train': 0.7104864716529846} 08/31/2021 14:57:32 - INFO - __main__ - Step 141715: {'lr': 3.8570589842562564e-06, 'samples': 27209280, 'steps': 141714, 'loss/train': 0.22547248005867004} 08/31/2021 14:57:33 - INFO - __main__ - Step 141716: {'lr': 3.856130458897156e-06, 'samples': 27209472, 'steps': 141715, 'loss/train': 1.5270888805389404} 08/31/2021 14:57:34 - INFO - __main__ - Step 141717: {'lr': 3.85520204444667e-06, 'samples': 27209664, 'steps': 141716, 'loss/train': 1.556746006011963} 08/31/2021 14:57:34 - INFO - __main__ - Step 141718: {'lr': 3.854273740905245e-06, 'samples': 27209856, 'steps': 141717, 'loss/train': 3.254333019256592} 08/31/2021 14:57:34 - INFO - __main__ - Step 141719: {'lr': 3.853345548273296e-06, 'samples': 27210048, 'steps': 141718, 'loss/train': 1.4537147283554077} 08/31/2021 14:57:35 - INFO - __main__ - Step 141720: {'lr': 3.852417466551211e-06, 'samples': 27210240, 'steps': 141719, 'loss/train': 1.3663734197616577} 08/31/2021 14:57:35 - INFO - __main__ - Step 141721: {'lr': 3.851489495739435e-06, 'samples': 27210432, 'steps': 141720, 'loss/train': 1.6069707870483398} 08/31/2021 14:57:37 - INFO - __main__ - Step 141722: {'lr': 3.850561635838385e-06, 'samples': 27210624, 'steps': 141721, 'loss/train': 0.19551712274551392} 08/31/2021 14:57:37 - INFO - __main__ - Step 141723: {'lr': 3.8496338868484744e-06, 'samples': 27210816, 'steps': 141722, 'loss/train': 0.9851442575454712} 08/31/2021 14:57:38 - INFO - __main__ - Step 141724: {'lr': 3.848706248770123e-06, 'samples': 27211008, 'steps': 141723, 'loss/train': 0.516922116279602} 08/31/2021 14:57:38 - INFO - __main__ - Step 141725: {'lr': 3.847778721603745e-06, 'samples': 27211200, 'steps': 141724, 'loss/train': 0.9865259528160095} 08/31/2021 14:57:38 - INFO - __main__ - Step 141726: {'lr': 3.846851305349786e-06, 'samples': 27211392, 'steps': 141725, 'loss/train': 0.4302005171775818} 08/31/2021 14:57:40 - INFO - __main__ - Step 141727: {'lr': 3.845924000008605e-06, 'samples': 27211584, 'steps': 141726, 'loss/train': 0.7775846123695374} 08/31/2021 14:57:40 - INFO - __main__ - Step 141728: {'lr': 3.844996805580648e-06, 'samples': 27211776, 'steps': 141727, 'loss/train': 0.3427659273147583} 08/31/2021 14:57:41 - INFO - __main__ - Step 141729: {'lr': 3.844069722066329e-06, 'samples': 27211968, 'steps': 141728, 'loss/train': 1.322411060333252} 08/31/2021 14:57:41 - INFO - __main__ - Step 141730: {'lr': 3.843142749466094e-06, 'samples': 27212160, 'steps': 141729, 'loss/train': 0.564244270324707} 08/31/2021 14:57:41 - INFO - __main__ - Step 141731: {'lr': 3.842215887780332e-06, 'samples': 27212352, 'steps': 141730, 'loss/train': 1.160334587097168} 08/31/2021 14:57:43 - INFO - __main__ - Step 141732: {'lr': 3.841289137009485e-06, 'samples': 27212544, 'steps': 141731, 'loss/train': 0.9956570267677307} 08/31/2021 14:57:43 - INFO - __main__ - Step 141733: {'lr': 3.840362497153943e-06, 'samples': 27212736, 'steps': 141732, 'loss/train': 1.2325435876846313} 08/31/2021 14:57:44 - INFO - __main__ - Step 141734: {'lr': 3.839435968214122e-06, 'samples': 27212928, 'steps': 141733, 'loss/train': 1.1779221296310425} 08/31/2021 14:57:44 - INFO - __main__ - Step 141735: {'lr': 3.838509550190466e-06, 'samples': 27213120, 'steps': 141734, 'loss/train': 0.6418090462684631} 08/31/2021 14:57:44 - INFO - __main__ - Step 141736: {'lr': 3.837583243083393e-06, 'samples': 27213312, 'steps': 141735, 'loss/train': 0.9703522324562073} 08/31/2021 14:57:46 - INFO - __main__ - Step 141737: {'lr': 3.836657046893288e-06, 'samples': 27213504, 'steps': 141736, 'loss/train': 0.3730790913105011} 08/31/2021 14:57:46 - INFO - __main__ - Step 141738: {'lr': 3.835730961620571e-06, 'samples': 27213696, 'steps': 141737, 'loss/train': 0.80612713098526} 08/31/2021 14:57:47 - INFO - __main__ - Step 141739: {'lr': 3.8348049872657105e-06, 'samples': 27213888, 'steps': 141738, 'loss/train': 1.3257994651794434} 08/31/2021 14:57:47 - INFO - __main__ - Step 141740: {'lr': 3.83387912382907e-06, 'samples': 27214080, 'steps': 141739, 'loss/train': 1.7069950103759766} 08/31/2021 14:57:47 - INFO - __main__ - Step 141741: {'lr': 3.832953371311093e-06, 'samples': 27214272, 'steps': 141740, 'loss/train': 0.62673020362854} 08/31/2021 14:57:49 - INFO - __main__ - Step 141742: {'lr': 3.8320277297121955e-06, 'samples': 27214464, 'steps': 141741, 'loss/train': 0.5982646942138672} 08/31/2021 14:57:50 - INFO - __main__ - Step 141743: {'lr': 3.8311021990327654e-06, 'samples': 27214656, 'steps': 141742, 'loss/train': 1.0462112426757812} 08/31/2021 14:57:50 - INFO - __main__ - Step 141744: {'lr': 3.830176779273248e-06, 'samples': 27214848, 'steps': 141743, 'loss/train': 0.5744683146476746} 08/31/2021 14:57:51 - INFO - __main__ - Step 141745: {'lr': 3.829251470434059e-06, 'samples': 27215040, 'steps': 141744, 'loss/train': 1.225719690322876} 08/31/2021 14:57:51 - INFO - __main__ - Step 141746: {'lr': 3.828326272515614e-06, 'samples': 27215232, 'steps': 141745, 'loss/train': 1.3413830995559692} 08/31/2021 14:57:51 - INFO - __main__ - Step 141747: {'lr': 3.827401185518331e-06, 'samples': 27215424, 'steps': 141746, 'loss/train': 0.8831192255020142} 08/31/2021 14:57:53 - INFO - __main__ - Step 141748: {'lr': 3.826476209442598e-06, 'samples': 27215616, 'steps': 141747, 'loss/train': 0.45104292035102844} 08/31/2021 14:57:53 - INFO - __main__ - Step 141749: {'lr': 3.825551344288886e-06, 'samples': 27215808, 'steps': 141748, 'loss/train': 0.9558478593826294} 08/31/2021 14:57:54 - INFO - __main__ - Step 141750: {'lr': 3.824626590057556e-06, 'samples': 27216000, 'steps': 141749, 'loss/train': 0.08380917459726334} 08/31/2021 14:57:54 - INFO - __main__ - Step 141751: {'lr': 3.823701946749053e-06, 'samples': 27216192, 'steps': 141750, 'loss/train': 1.054816484451294} 08/31/2021 14:57:54 - INFO - __main__ - Step 141752: {'lr': 3.822777414363793e-06, 'samples': 27216384, 'steps': 141751, 'loss/train': 1.140375018119812} 08/31/2021 14:57:56 - INFO - __main__ - Step 141753: {'lr': 3.821852992902219e-06, 'samples': 27216576, 'steps': 141752, 'loss/train': 0.7811083793640137} 08/31/2021 14:57:57 - INFO - __main__ - Step 141754: {'lr': 3.820928682364722e-06, 'samples': 27216768, 'steps': 141753, 'loss/train': 1.5297192335128784} 08/31/2021 14:57:57 - INFO - __main__ - Step 141755: {'lr': 3.820004482751688e-06, 'samples': 27216960, 'steps': 141754, 'loss/train': 1.8231691122055054} 08/31/2021 14:57:57 - INFO - __main__ - Step 141756: {'lr': 3.8190803940635624e-06, 'samples': 27217152, 'steps': 141755, 'loss/train': 0.9929677844047546} 08/31/2021 14:57:58 - INFO - __main__ - Step 141757: {'lr': 3.818156416300761e-06, 'samples': 27217344, 'steps': 141756, 'loss/train': 1.1581839323043823} 08/31/2021 14:57:58 - INFO - __main__ - Step 141758: {'lr': 3.8172325494637004e-06, 'samples': 27217536, 'steps': 141757, 'loss/train': 0.925888180732727} 08/31/2021 14:58:00 - INFO - __main__ - Step 141759: {'lr': 3.816308793552798e-06, 'samples': 27217728, 'steps': 141758, 'loss/train': 0.13701795041561127} 08/31/2021 14:58:00 - INFO - __main__ - Step 141760: {'lr': 3.815385148568467e-06, 'samples': 27217920, 'steps': 141759, 'loss/train': 0.9789580702781677} 08/31/2021 14:58:01 - INFO - __main__ - Step 141761: {'lr': 3.8144616145111276e-06, 'samples': 27218112, 'steps': 141760, 'loss/train': 0.051966723054647446} 08/31/2021 14:58:01 - INFO - __main__ - Step 141762: {'lr': 3.8135381913811662e-06, 'samples': 27218304, 'steps': 141761, 'loss/train': 1.1647056341171265} 08/31/2021 14:58:01 - INFO - __main__ - Step 141763: {'lr': 3.8126148791790547e-06, 'samples': 27218496, 'steps': 141762, 'loss/train': 1.5655142068862915} 08/31/2021 14:58:03 - INFO - __main__ - Step 141764: {'lr': 3.8116916779051827e-06, 'samples': 27218688, 'steps': 141763, 'loss/train': 1.318764567375183} 08/31/2021 14:58:03 - INFO - __main__ - Step 141765: {'lr': 3.810768587559965e-06, 'samples': 27218880, 'steps': 141764, 'loss/train': 0.982479453086853} 08/31/2021 14:58:04 - INFO - __main__ - Step 141766: {'lr': 3.8098456081437917e-06, 'samples': 27219072, 'steps': 141765, 'loss/train': 0.6434670090675354} 08/31/2021 14:58:04 - INFO - __main__ - Step 141767: {'lr': 3.8089227396571337e-06, 'samples': 27219264, 'steps': 141766, 'loss/train': 0.7111935615539551} 08/31/2021 14:58:04 - INFO - __main__ - Step 141768: {'lr': 3.8079999821003797e-06, 'samples': 27219456, 'steps': 141767, 'loss/train': 1.4826538562774658} 08/31/2021 14:58:06 - INFO - __main__ - Step 141769: {'lr': 3.8070773354739187e-06, 'samples': 27219648, 'steps': 141768, 'loss/train': 1.1279927492141724} 08/31/2021 14:58:06 - INFO - __main__ - Step 141770: {'lr': 3.8061547997781943e-06, 'samples': 27219840, 'steps': 141769, 'loss/train': 1.1594696044921875} 08/31/2021 14:58:07 - INFO - __main__ - Step 141771: {'lr': 3.805232375013595e-06, 'samples': 27220032, 'steps': 141770, 'loss/train': 1.1818886995315552} 08/31/2021 14:58:07 - INFO - __main__ - Step 141772: {'lr': 3.8043100611805935e-06, 'samples': 27220224, 'steps': 141771, 'loss/train': 0.5654600858688354} 08/31/2021 14:58:07 - INFO - __main__ - Step 141773: {'lr': 3.80338785827955e-06, 'samples': 27220416, 'steps': 141772, 'loss/train': 0.36539873480796814} 08/31/2021 14:58:09 - INFO - __main__ - Step 141774: {'lr': 3.8024657663109087e-06, 'samples': 27220608, 'steps': 141773, 'loss/train': 1.528454303741455} 08/31/2021 14:58:10 - INFO - __main__ - Step 141775: {'lr': 3.8015437852750857e-06, 'samples': 27220800, 'steps': 141774, 'loss/train': 1.5148471593856812} 08/31/2021 14:58:10 - INFO - __main__ - Step 141776: {'lr': 3.8006219151724695e-06, 'samples': 27220992, 'steps': 141775, 'loss/train': 1.7550538778305054} 08/31/2021 14:58:11 - INFO - __main__ - Step 141777: {'lr': 3.799700156003505e-06, 'samples': 27221184, 'steps': 141776, 'loss/train': 1.1120673418045044} 08/31/2021 14:58:11 - INFO - __main__ - Step 141778: {'lr': 3.798778507768608e-06, 'samples': 27221376, 'steps': 141777, 'loss/train': 0.49329158663749695} 08/31/2021 14:58:11 - INFO - __main__ - Step 141779: {'lr': 3.7978569704681666e-06, 'samples': 27221568, 'steps': 141778, 'loss/train': 1.2582271099090576} 08/31/2021 14:58:13 - INFO - __main__ - Step 141780: {'lr': 3.7969355441026254e-06, 'samples': 27221760, 'steps': 141779, 'loss/train': 0.8663250803947449} 08/31/2021 14:58:13 - INFO - __main__ - Step 141781: {'lr': 3.796014228672373e-06, 'samples': 27221952, 'steps': 141780, 'loss/train': 0.3177328407764435} 08/31/2021 14:58:14 - INFO - __main__ - Step 141782: {'lr': 3.7950930241778536e-06, 'samples': 27222144, 'steps': 141781, 'loss/train': 1.4179962873458862} 08/31/2021 14:58:14 - INFO - __main__ - Step 141783: {'lr': 3.7941719306194556e-06, 'samples': 27222336, 'steps': 141782, 'loss/train': 1.4831321239471436} 08/31/2021 14:58:15 - INFO - __main__ - Step 141784: {'lr': 3.7932509479975954e-06, 'samples': 27222528, 'steps': 141783, 'loss/train': 0.8605830669403076} 08/31/2021 14:58:16 - INFO - __main__ - Step 141785: {'lr': 3.792330076312689e-06, 'samples': 27222720, 'steps': 141784, 'loss/train': 0.8747484087944031} 08/31/2021 14:58:17 - INFO - __main__ - Step 141786: {'lr': 3.791409315565181e-06, 'samples': 27222912, 'steps': 141785, 'loss/train': 1.4964507818222046} 08/31/2021 14:58:17 - INFO - __main__ - Step 141787: {'lr': 3.790488665755459e-06, 'samples': 27223104, 'steps': 141786, 'loss/train': 1.396935224533081} 08/31/2021 14:58:17 - INFO - __main__ - Step 141788: {'lr': 3.789568126883941e-06, 'samples': 27223296, 'steps': 141787, 'loss/train': 1.1271229982376099} 08/31/2021 14:58:18 - INFO - __main__ - Step 141789: {'lr': 3.7886476989510423e-06, 'samples': 27223488, 'steps': 141788, 'loss/train': 5.711116313934326} 08/31/2021 14:58:18 - INFO - __main__ - Step 141790: {'lr': 3.787727381957179e-06, 'samples': 27223680, 'steps': 141789, 'loss/train': 0.8184542059898376} 08/31/2021 14:58:19 - INFO - __main__ - Step 141791: {'lr': 3.786807175902768e-06, 'samples': 27223872, 'steps': 141790, 'loss/train': 1.0367145538330078} 08/31/2021 14:58:20 - INFO - __main__ - Step 141792: {'lr': 3.785887080788225e-06, 'samples': 27224064, 'steps': 141791, 'loss/train': 1.7357177734375} 08/31/2021 14:58:20 - INFO - __main__ - Step 141793: {'lr': 3.784967096613995e-06, 'samples': 27224256, 'steps': 141792, 'loss/train': 1.4296995401382446} 08/31/2021 14:58:21 - INFO - __main__ - Step 141794: {'lr': 3.78404722338041e-06, 'samples': 27224448, 'steps': 141793, 'loss/train': 0.71811842918396} 08/31/2021 14:58:21 - INFO - __main__ - Step 141795: {'lr': 3.7831274610879705e-06, 'samples': 27224640, 'steps': 141794, 'loss/train': 1.2171587944030762} 08/31/2021 14:58:22 - INFO - __main__ - Step 141796: {'lr': 3.7822078097370095e-06, 'samples': 27224832, 'steps': 141795, 'loss/train': 0.9809486865997314} 08/31/2021 14:58:23 - INFO - __main__ - Step 141797: {'lr': 3.781288269328026e-06, 'samples': 27225024, 'steps': 141796, 'loss/train': 1.482353925704956} 08/31/2021 14:58:23 - INFO - __main__ - Step 141798: {'lr': 3.7803688398613812e-06, 'samples': 27225216, 'steps': 141797, 'loss/train': 1.2971534729003906} 08/31/2021 14:58:24 - INFO - __main__ - Step 141799: {'lr': 3.779449521337491e-06, 'samples': 27225408, 'steps': 141798, 'loss/train': 0.9733189344406128} 08/31/2021 14:58:24 - INFO - __main__ - Step 141800: {'lr': 3.7785303137568007e-06, 'samples': 27225600, 'steps': 141799, 'loss/train': 0.5684516429901123} 08/31/2021 14:58:25 - INFO - __main__ - Step 141801: {'lr': 3.7776112171196976e-06, 'samples': 27225792, 'steps': 141800, 'loss/train': 1.3477654457092285} 08/31/2021 14:58:26 - INFO - __main__ - Step 141802: {'lr': 3.7766922314265985e-06, 'samples': 27225984, 'steps': 141801, 'loss/train': 1.33696448802948} 08/31/2021 14:58:26 - INFO - __main__ - Step 141803: {'lr': 3.7757733566779197e-06, 'samples': 27226176, 'steps': 141802, 'loss/train': 2.097899913787842} 08/31/2021 14:58:27 - INFO - __main__ - Step 141804: {'lr': 3.7748545928740775e-06, 'samples': 27226368, 'steps': 141803, 'loss/train': 1.4079184532165527} 08/31/2021 14:58:27 - INFO - __main__ - Step 141805: {'lr': 3.773935940015516e-06, 'samples': 27226560, 'steps': 141804, 'loss/train': 1.5892961025238037} 08/31/2021 14:58:28 - INFO - __main__ - Step 141806: {'lr': 3.773017398102596e-06, 'samples': 27226752, 'steps': 141805, 'loss/train': 0.8078332543373108} 08/31/2021 14:58:29 - INFO - __main__ - Step 141807: {'lr': 3.772098967135762e-06, 'samples': 27226944, 'steps': 141806, 'loss/train': 0.42444944381713867} 08/31/2021 14:58:29 - INFO - __main__ - Step 141808: {'lr': 3.771180647115402e-06, 'samples': 27227136, 'steps': 141807, 'loss/train': 1.0747941732406616} 08/31/2021 14:58:30 - INFO - __main__ - Step 141809: {'lr': 3.7702624380419604e-06, 'samples': 27227328, 'steps': 141808, 'loss/train': 1.0182228088378906} 08/31/2021 14:58:30 - INFO - __main__ - Step 141810: {'lr': 3.769344339915853e-06, 'samples': 27227520, 'steps': 141809, 'loss/train': 0.7574204802513123} 08/31/2021 14:58:31 - INFO - __main__ - Step 141811: {'lr': 3.7684263527374697e-06, 'samples': 27227712, 'steps': 141810, 'loss/train': 0.036828406155109406} 08/31/2021 14:58:32 - INFO - __main__ - Step 141812: {'lr': 3.7675084765072255e-06, 'samples': 27227904, 'steps': 141811, 'loss/train': 1.080641508102417} 08/31/2021 14:58:32 - INFO - __main__ - Step 141813: {'lr': 3.7665907112255373e-06, 'samples': 27228096, 'steps': 141812, 'loss/train': 0.8630663752555847} 08/31/2021 14:58:33 - INFO - __main__ - Step 141814: {'lr': 3.765673056892821e-06, 'samples': 27228288, 'steps': 141813, 'loss/train': 0.3979068100452423} 08/31/2021 14:58:33 - INFO - __main__ - Step 141815: {'lr': 3.7647555135095215e-06, 'samples': 27228480, 'steps': 141814, 'loss/train': 1.9918047189712524} 08/31/2021 14:58:35 - INFO - __main__ - Step 141816: {'lr': 3.7638380810760265e-06, 'samples': 27228672, 'steps': 141815, 'loss/train': 1.4532372951507568} 08/31/2021 14:58:35 - INFO - __main__ - Step 141817: {'lr': 3.762920759592725e-06, 'samples': 27228864, 'steps': 141816, 'loss/train': 1.4894351959228516} 08/31/2021 14:58:36 - INFO - __main__ - Step 141818: {'lr': 3.7620035490600337e-06, 'samples': 27229056, 'steps': 141817, 'loss/train': 1.9009640216827393} 08/31/2021 14:58:36 - INFO - __main__ - Step 141819: {'lr': 3.7610864494784234e-06, 'samples': 27229248, 'steps': 141818, 'loss/train': 0.0283599104732275} 08/31/2021 14:58:36 - INFO - __main__ - Step 141820: {'lr': 3.7601694608482283e-06, 'samples': 27229440, 'steps': 141819, 'loss/train': 0.015690643340349197} 08/31/2021 14:58:37 - INFO - __main__ - Step 141821: {'lr': 3.7592525831699197e-06, 'samples': 27229632, 'steps': 141820, 'loss/train': 1.0967292785644531} 08/31/2021 14:58:38 - INFO - __main__ - Step 141822: {'lr': 3.7583358164439143e-06, 'samples': 27229824, 'steps': 141821, 'loss/train': 0.5848379731178284} 08/31/2021 14:58:39 - INFO - __main__ - Step 141823: {'lr': 3.757419160670572e-06, 'samples': 27230016, 'steps': 141822, 'loss/train': 1.2378743886947632} 08/31/2021 14:58:39 - INFO - __main__ - Step 141824: {'lr': 3.756502615850338e-06, 'samples': 27230208, 'steps': 141823, 'loss/train': 1.3152953386306763} 08/31/2021 14:58:39 - INFO - __main__ - Step 141825: {'lr': 3.755586181983628e-06, 'samples': 27230400, 'steps': 141824, 'loss/train': 1.0820337533950806} 08/31/2021 14:58:40 - INFO - __main__ - Step 141826: {'lr': 3.754669859070886e-06, 'samples': 27230592, 'steps': 141825, 'loss/train': 0.8341705203056335} 08/31/2021 14:58:40 - INFO - __main__ - Step 141827: {'lr': 3.7537536471124733e-06, 'samples': 27230784, 'steps': 141826, 'loss/train': 1.3406269550323486} 08/31/2021 14:58:42 - INFO - __main__ - Step 141828: {'lr': 3.752837546108806e-06, 'samples': 27230976, 'steps': 141827, 'loss/train': 1.1886577606201172} 08/31/2021 14:58:43 - INFO - __main__ - Step 141829: {'lr': 3.7519215560603006e-06, 'samples': 27231168, 'steps': 141828, 'loss/train': 1.3095113039016724} 08/31/2021 14:58:43 - INFO - __main__ - Step 141830: {'lr': 3.7510056769673726e-06, 'samples': 27231360, 'steps': 141829, 'loss/train': 1.6590110063552856} 08/31/2021 14:58:43 - INFO - __main__ - Step 141831: {'lr': 3.7500899088304672e-06, 'samples': 27231552, 'steps': 141830, 'loss/train': 1.535127878189087} 08/31/2021 14:58:44 - INFO - __main__ - Step 141832: {'lr': 3.7491742516499728e-06, 'samples': 27231744, 'steps': 141831, 'loss/train': 0.9428468346595764} 08/31/2021 14:58:45 - INFO - __main__ - Step 141833: {'lr': 3.748258705426277e-06, 'samples': 27231936, 'steps': 141832, 'loss/train': 1.399284839630127} 08/31/2021 14:58:46 - INFO - __main__ - Step 141834: {'lr': 3.7473432701598255e-06, 'samples': 27232128, 'steps': 141833, 'loss/train': 0.9796013832092285} 08/31/2021 14:58:46 - INFO - __main__ - Step 141835: {'lr': 3.746427945851033e-06, 'samples': 27232320, 'steps': 141834, 'loss/train': 1.8319295644760132} 08/31/2021 14:58:46 - INFO - __main__ - Step 141836: {'lr': 3.745512732500289e-06, 'samples': 27232512, 'steps': 141835, 'loss/train': 1.242702841758728} 08/31/2021 14:58:47 - INFO - __main__ - Step 141837: {'lr': 3.7445976301080376e-06, 'samples': 27232704, 'steps': 141836, 'loss/train': 1.4086557626724243} 08/31/2021 14:58:48 - INFO - __main__ - Step 141838: {'lr': 3.743682638674667e-06, 'samples': 27232896, 'steps': 141837, 'loss/train': 0.8181802034378052} 08/31/2021 14:58:49 - INFO - __main__ - Step 141839: {'lr': 3.742767758200566e-06, 'samples': 27233088, 'steps': 141838, 'loss/train': 0.8985097408294678} 08/31/2021 14:58:49 - INFO - __main__ - Step 141840: {'lr': 3.7418529886861787e-06, 'samples': 27233280, 'steps': 141839, 'loss/train': 1.4773521423339844} 08/31/2021 14:58:49 - INFO - __main__ - Step 141841: {'lr': 3.740938330131921e-06, 'samples': 27233472, 'steps': 141840, 'loss/train': 1.4386372566223145} 08/31/2021 14:58:50 - INFO - __main__ - Step 141842: {'lr': 3.74002378253821e-06, 'samples': 27233664, 'steps': 141841, 'loss/train': 1.2111220359802246} 08/31/2021 14:58:51 - INFO - __main__ - Step 141843: {'lr': 3.7391093459054336e-06, 'samples': 27233856, 'steps': 141842, 'loss/train': 1.7853178977966309} 08/31/2021 14:58:52 - INFO - __main__ - Step 141844: {'lr': 3.7381950202340087e-06, 'samples': 27234048, 'steps': 141843, 'loss/train': 0.7573586106300354} 08/31/2021 14:58:52 - INFO - __main__ - Step 141845: {'lr': 3.7372808055243514e-06, 'samples': 27234240, 'steps': 141844, 'loss/train': 1.0112252235412598} 08/31/2021 14:58:52 - INFO - __main__ - Step 141846: {'lr': 3.7363667017768776e-06, 'samples': 27234432, 'steps': 141845, 'loss/train': 0.30571186542510986} 08/31/2021 14:58:53 - INFO - __main__ - Step 141847: {'lr': 3.7354527089920044e-06, 'samples': 27234624, 'steps': 141846, 'loss/train': 1.2527220249176025} 08/31/2021 14:58:54 - INFO - __main__ - Step 141848: {'lr': 3.7345388271701477e-06, 'samples': 27234816, 'steps': 141847, 'loss/train': 1.0971547365188599} 08/31/2021 14:58:55 - INFO - __main__ - Step 141849: {'lr': 3.733625056311696e-06, 'samples': 27235008, 'steps': 141848, 'loss/train': 1.0850094556808472} 08/31/2021 14:58:55 - INFO - __main__ - Step 141850: {'lr': 3.7327113964170656e-06, 'samples': 27235200, 'steps': 141849, 'loss/train': 0.8739469051361084} 08/31/2021 14:58:56 - INFO - __main__ - Step 141851: {'lr': 3.7317978474866733e-06, 'samples': 27235392, 'steps': 141850, 'loss/train': 0.050946835428476334} 08/31/2021 14:58:56 - INFO - __main__ - Step 141852: {'lr': 3.730884409520935e-06, 'samples': 27235584, 'steps': 141851, 'loss/train': 0.8428540229797363} 08/31/2021 14:58:57 - INFO - __main__ - Step 141853: {'lr': 3.729971082520267e-06, 'samples': 27235776, 'steps': 141852, 'loss/train': 1.0276347398757935} 08/31/2021 14:58:58 - INFO - __main__ - Step 141854: {'lr': 3.7290578664850583e-06, 'samples': 27235968, 'steps': 141853, 'loss/train': 1.6822048425674438} 08/31/2021 14:58:58 - INFO - __main__ - Step 141855: {'lr': 3.7281447614157526e-06, 'samples': 27236160, 'steps': 141854, 'loss/train': 1.4415451288223267} 08/31/2021 14:58:59 - INFO - __main__ - Step 141856: {'lr': 3.7272317673127388e-06, 'samples': 27236352, 'steps': 141855, 'loss/train': 1.5314371585845947} 08/31/2021 14:58:59 - INFO - __main__ - Step 141857: {'lr': 3.726318884176433e-06, 'samples': 27236544, 'steps': 141856, 'loss/train': 1.2908068895339966} 08/31/2021 14:58:59 - INFO - __main__ - Step 141858: {'lr': 3.725406112007251e-06, 'samples': 27236736, 'steps': 141857, 'loss/train': 1.5133105516433716} 08/31/2021 14:59:01 - INFO - __main__ - Step 141859: {'lr': 3.724493450805583e-06, 'samples': 27236928, 'steps': 141858, 'loss/train': 0.9490588307380676} 08/31/2021 14:59:01 - INFO - __main__ - Step 141860: {'lr': 3.7235809005718713e-06, 'samples': 27237120, 'steps': 141859, 'loss/train': 0.11955126374959946} 08/31/2021 14:59:02 - INFO - __main__ - Step 141861: {'lr': 3.722668461306533e-06, 'samples': 27237312, 'steps': 141860, 'loss/train': 1.1012529134750366} 08/31/2021 14:59:02 - INFO - __main__ - Step 141862: {'lr': 3.721756133009957e-06, 'samples': 27237504, 'steps': 141861, 'loss/train': 0.7208973169326782} 08/31/2021 14:59:02 - INFO - __main__ - Step 141863: {'lr': 3.7208439156825313e-06, 'samples': 27237696, 'steps': 141862, 'loss/train': 1.5199291706085205} 08/31/2021 14:59:04 - INFO - __main__ - Step 141864: {'lr': 3.7199318093247e-06, 'samples': 27237888, 'steps': 141863, 'loss/train': 0.34842240810394287} 08/31/2021 14:59:04 - INFO - __main__ - Step 141865: {'lr': 3.7190198139368803e-06, 'samples': 27238080, 'steps': 141864, 'loss/train': 0.5670157670974731} 08/31/2021 14:59:05 - INFO - __main__ - Step 141866: {'lr': 3.7181079295194598e-06, 'samples': 27238272, 'steps': 141865, 'loss/train': 0.34006479382514954} 08/31/2021 14:59:05 - INFO - __main__ - Step 141867: {'lr': 3.717196156072855e-06, 'samples': 27238464, 'steps': 141866, 'loss/train': 1.1972483396530151} 08/31/2021 14:59:05 - INFO - __main__ - Step 141868: {'lr': 3.7162844935974825e-06, 'samples': 27238656, 'steps': 141867, 'loss/train': 1.2002577781677246} 08/31/2021 14:59:07 - INFO - __main__ - Step 141869: {'lr': 3.715372942093759e-06, 'samples': 27238848, 'steps': 141868, 'loss/train': 1.4374418258666992} 08/31/2021 14:59:07 - INFO - __main__ - Step 141870: {'lr': 3.7144615015620997e-06, 'samples': 27239040, 'steps': 141869, 'loss/train': 1.1291364431381226} 08/31/2021 14:59:08 - INFO - __main__ - Step 141871: {'lr': 3.7135501720028943e-06, 'samples': 27239232, 'steps': 141870, 'loss/train': 1.3261938095092773} 08/31/2021 14:59:08 - INFO - __main__ - Step 141872: {'lr': 3.7126389534165306e-06, 'samples': 27239424, 'steps': 141871, 'loss/train': 0.9081524014472961} 08/31/2021 14:59:09 - INFO - __main__ - Step 141873: {'lr': 3.7117278458034807e-06, 'samples': 27239616, 'steps': 141872, 'loss/train': 0.723732590675354} 08/31/2021 14:59:10 - INFO - __main__ - Step 141874: {'lr': 3.7108168491641615e-06, 'samples': 27239808, 'steps': 141873, 'loss/train': 0.17616848647594452} 08/31/2021 14:59:11 - INFO - __main__ - Step 141875: {'lr': 3.7099059634989053e-06, 'samples': 27240000, 'steps': 141874, 'loss/train': 0.6374068260192871} 08/31/2021 14:59:11 - INFO - __main__ - Step 141876: {'lr': 3.708995188808156e-06, 'samples': 27240192, 'steps': 141875, 'loss/train': 1.4455444812774658} 08/31/2021 14:59:11 - INFO - __main__ - Step 141877: {'lr': 3.708084525092359e-06, 'samples': 27240384, 'steps': 141876, 'loss/train': 1.3287943601608276} 08/31/2021 14:59:12 - INFO - __main__ - Step 141878: {'lr': 3.707173972351874e-06, 'samples': 27240576, 'steps': 141877, 'loss/train': 1.3261942863464355} 08/31/2021 14:59:12 - INFO - __main__ - Step 141879: {'lr': 3.706263530587145e-06, 'samples': 27240768, 'steps': 141878, 'loss/train': 1.3485832214355469} 08/31/2021 14:59:13 - INFO - __main__ - Step 141880: {'lr': 3.705353199798589e-06, 'samples': 27240960, 'steps': 141879, 'loss/train': 1.4336293935775757} 08/31/2021 14:59:14 - INFO - __main__ - Step 141881: {'lr': 3.704442979986594e-06, 'samples': 27241152, 'steps': 141880, 'loss/train': 1.4437750577926636} 08/31/2021 14:59:14 - INFO - __main__ - Step 141882: {'lr': 3.703532871151549e-06, 'samples': 27241344, 'steps': 141881, 'loss/train': 1.4746475219726562} 08/31/2021 14:59:15 - INFO - __main__ - Step 141883: {'lr': 3.702622873293926e-06, 'samples': 27241536, 'steps': 141882, 'loss/train': 1.3116689920425415} 08/31/2021 14:59:15 - INFO - __main__ - Step 141884: {'lr': 3.701712986414085e-06, 'samples': 27241728, 'steps': 141883, 'loss/train': 0.5522528290748596} 08/31/2021 14:59:17 - INFO - __main__ - Step 141885: {'lr': 3.7008032105124433e-06, 'samples': 27241920, 'steps': 141884, 'loss/train': 0.7299410700798035} 08/31/2021 14:59:17 - INFO - __main__ - Step 141886: {'lr': 3.6998935455894444e-06, 'samples': 27242112, 'steps': 141885, 'loss/train': 1.4145259857177734} 08/31/2021 14:59:18 - INFO - __main__ - Step 141887: {'lr': 3.6989839916454494e-06, 'samples': 27242304, 'steps': 141886, 'loss/train': 0.6758699417114258} 08/31/2021 14:59:18 - INFO - __main__ - Step 141888: {'lr': 3.6980745486809296e-06, 'samples': 27242496, 'steps': 141887, 'loss/train': 1.0431329011917114} 08/31/2021 14:59:19 - INFO - __main__ - Step 141889: {'lr': 3.6971652166962187e-06, 'samples': 27242688, 'steps': 141888, 'loss/train': 1.3576364517211914} 08/31/2021 14:59:21 - INFO - __main__ - Step 141890: {'lr': 3.6962559956917606e-06, 'samples': 27242880, 'steps': 141889, 'loss/train': 0.9905571341514587} 08/31/2021 14:59:21 - INFO - __main__ - Step 141891: {'lr': 3.6953468856679996e-06, 'samples': 27243072, 'steps': 141890, 'loss/train': 1.7729488611221313} 08/31/2021 14:59:21 - INFO - __main__ - Step 141892: {'lr': 3.694437886625296e-06, 'samples': 27243264, 'steps': 141891, 'loss/train': 0.8210568428039551} 08/31/2021 14:59:22 - INFO - __main__ - Step 141893: {'lr': 3.693528998564066e-06, 'samples': 27243456, 'steps': 141892, 'loss/train': 0.32079604268074036} 08/31/2021 14:59:22 - INFO - __main__ - Step 141894: {'lr': 3.692620221484755e-06, 'samples': 27243648, 'steps': 141893, 'loss/train': 1.2629344463348389} 08/31/2021 14:59:22 - INFO - __main__ - Step 141895: {'lr': 3.6917115553877224e-06, 'samples': 27243840, 'steps': 141894, 'loss/train': 1.5152193307876587} 08/31/2021 14:59:24 - INFO - __main__ - Step 141896: {'lr': 3.6908030002734127e-06, 'samples': 27244032, 'steps': 141895, 'loss/train': 0.07712499797344208} 08/31/2021 14:59:24 - INFO - __main__ - Step 141897: {'lr': 3.6898945561422424e-06, 'samples': 27244224, 'steps': 141896, 'loss/train': 0.7763118743896484} 08/31/2021 14:59:25 - INFO - __main__ - Step 141898: {'lr': 3.6889862229946004e-06, 'samples': 27244416, 'steps': 141897, 'loss/train': 1.2925933599472046} 08/31/2021 14:59:25 - INFO - __main__ - Step 141899: {'lr': 3.6880780008308747e-06, 'samples': 27244608, 'steps': 141898, 'loss/train': 1.3636242151260376} 08/31/2021 14:59:25 - INFO - __main__ - Step 141900: {'lr': 3.6871698896515373e-06, 'samples': 27244800, 'steps': 141899, 'loss/train': 1.238092064857483} 08/31/2021 14:59:27 - INFO - __main__ - Step 141901: {'lr': 3.6862618894569488e-06, 'samples': 27244992, 'steps': 141900, 'loss/train': 0.6503772139549255} 08/31/2021 14:59:27 - INFO - __main__ - Step 141902: {'lr': 3.6853540002475262e-06, 'samples': 27245184, 'steps': 141901, 'loss/train': 0.9055055379867554} 08/31/2021 14:59:28 - INFO - __main__ - Step 141903: {'lr': 3.684446222023685e-06, 'samples': 27245376, 'steps': 141902, 'loss/train': 1.0059586763381958} 08/31/2021 14:59:28 - INFO - __main__ - Step 141904: {'lr': 3.6835385547858148e-06, 'samples': 27245568, 'steps': 141903, 'loss/train': 1.077229380607605} 08/31/2021 14:59:28 - INFO - __main__ - Step 141905: {'lr': 3.6826309985343585e-06, 'samples': 27245760, 'steps': 141904, 'loss/train': 0.8064035773277283} 08/31/2021 14:59:29 - INFO - __main__ - Step 141906: {'lr': 3.681723553269706e-06, 'samples': 27245952, 'steps': 141905, 'loss/train': 1.335695505142212} 08/31/2021 14:59:30 - INFO - __main__ - Step 141907: {'lr': 3.6808162189922446e-06, 'samples': 27246144, 'steps': 141906, 'loss/train': 0.8928954601287842} 08/31/2021 14:59:31 - INFO - __main__ - Step 141908: {'lr': 3.6799089957024468e-06, 'samples': 27246336, 'steps': 141907, 'loss/train': 1.0728371143341064} 08/31/2021 14:59:31 - INFO - __main__ - Step 141909: {'lr': 3.6790018834006457e-06, 'samples': 27246528, 'steps': 141908, 'loss/train': 1.0356582403182983} 08/31/2021 14:59:31 - INFO - __main__ - Step 141910: {'lr': 3.678094882087313e-06, 'samples': 27246720, 'steps': 141909, 'loss/train': 1.0119446516036987} 08/31/2021 14:59:33 - INFO - __main__ - Step 141911: {'lr': 3.6771879917628094e-06, 'samples': 27246912, 'steps': 141910, 'loss/train': 0.43349117040634155} 08/31/2021 14:59:33 - INFO - __main__ - Step 141912: {'lr': 3.676281212427579e-06, 'samples': 27247104, 'steps': 141911, 'loss/train': 0.9030687808990479} 08/31/2021 14:59:34 - INFO - __main__ - Step 141913: {'lr': 3.675374544081983e-06, 'samples': 27247296, 'steps': 141912, 'loss/train': 0.21432575583457947} 08/31/2021 14:59:34 - INFO - __main__ - Step 141914: {'lr': 3.6744679867265208e-06, 'samples': 27247488, 'steps': 141913, 'loss/train': 0.2248232215642929} 08/31/2021 14:59:34 - INFO - __main__ - Step 141915: {'lr': 3.6735615403614977e-06, 'samples': 27247680, 'steps': 141914, 'loss/train': 0.3377325236797333} 08/31/2021 14:59:35 - INFO - __main__ - Step 141916: {'lr': 3.672655204987385e-06, 'samples': 27247872, 'steps': 141915, 'loss/train': 0.7162972688674927} 08/31/2021 14:59:36 - INFO - __main__ - Step 141917: {'lr': 3.6717489806045725e-06, 'samples': 27248064, 'steps': 141916, 'loss/train': 0.8730019330978394} 08/31/2021 14:59:37 - INFO - __main__ - Step 141918: {'lr': 3.6708428672134475e-06, 'samples': 27248256, 'steps': 141917, 'loss/train': 0.9910103678703308} 08/31/2021 14:59:37 - INFO - __main__ - Step 141919: {'lr': 3.669936864814455e-06, 'samples': 27248448, 'steps': 141918, 'loss/train': 1.2464228868484497} 08/31/2021 14:59:37 - INFO - __main__ - Step 141920: {'lr': 3.669030973407983e-06, 'samples': 27248640, 'steps': 141919, 'loss/train': 1.4702471494674683} 08/31/2021 14:59:38 - INFO - __main__ - Step 141921: {'lr': 3.668125192994448e-06, 'samples': 27248832, 'steps': 141920, 'loss/train': 0.6803444027900696} 08/31/2021 14:59:39 - INFO - __main__ - Step 141922: {'lr': 3.6672195235742667e-06, 'samples': 27249024, 'steps': 141921, 'loss/train': 1.3808789253234863} 08/31/2021 14:59:40 - INFO - __main__ - Step 141923: {'lr': 3.6663139651477993e-06, 'samples': 27249216, 'steps': 141922, 'loss/train': 0.7443522810935974} 08/31/2021 14:59:40 - INFO - __main__ - Step 141924: {'lr': 3.6654085177155183e-06, 'samples': 27249408, 'steps': 141923, 'loss/train': 0.8777364492416382} 08/31/2021 14:59:40 - INFO - __main__ - Step 141925: {'lr': 3.664503181277812e-06, 'samples': 27249600, 'steps': 141924, 'loss/train': 0.0849505141377449} 08/31/2021 14:59:41 - INFO - __main__ - Step 141926: {'lr': 3.6635979558350685e-06, 'samples': 27249792, 'steps': 141925, 'loss/train': 0.6364791393280029} 08/31/2021 14:59:43 - INFO - __main__ - Step 141927: {'lr': 3.6626928413877046e-06, 'samples': 27249984, 'steps': 141926, 'loss/train': 0.7838609218597412} 08/31/2021 14:59:44 - INFO - __main__ - Step 141928: {'lr': 3.661787837936137e-06, 'samples': 27250176, 'steps': 141927, 'loss/train': 0.6536703109741211} 08/31/2021 14:59:44 - INFO - __main__ - Step 141929: {'lr': 3.6608829454807537e-06, 'samples': 27250368, 'steps': 141928, 'loss/train': 1.2223161458969116} 08/31/2021 14:59:44 - INFO - __main__ - Step 141930: {'lr': 3.659978164021971e-06, 'samples': 27250560, 'steps': 141929, 'loss/train': 1.1144682168960571} 08/31/2021 14:59:45 - INFO - __main__ - Step 141931: {'lr': 3.6590734935602053e-06, 'samples': 27250752, 'steps': 141930, 'loss/train': 1.7397139072418213} 08/31/2021 14:59:45 - INFO - __main__ - Step 141932: {'lr': 3.6581689340958733e-06, 'samples': 27250944, 'steps': 141931, 'loss/train': 1.737000823020935} 08/31/2021 14:59:45 - INFO - __main__ - Step 141933: {'lr': 3.6572644856293636e-06, 'samples': 27251136, 'steps': 141932, 'loss/train': 1.729636549949646} 08/31/2021 14:59:47 - INFO - __main__ - Step 141934: {'lr': 3.656360148161092e-06, 'samples': 27251328, 'steps': 141933, 'loss/train': 0.023505309596657753} 08/31/2021 14:59:47 - INFO - __main__ - Step 141935: {'lr': 3.6554559216914475e-06, 'samples': 27251520, 'steps': 141934, 'loss/train': 1.2377527952194214} 08/31/2021 14:59:48 - INFO - __main__ - Step 141936: {'lr': 3.6545518062208736e-06, 'samples': 27251712, 'steps': 141935, 'loss/train': 0.6002113223075867} 08/31/2021 14:59:48 - INFO - __main__ - Step 141937: {'lr': 3.6536478017497323e-06, 'samples': 27251904, 'steps': 141936, 'loss/train': 1.2318480014801025} 08/31/2021 14:59:48 - INFO - __main__ - Step 141938: {'lr': 3.6527439082784665e-06, 'samples': 27252096, 'steps': 141937, 'loss/train': 1.247273325920105} 08/31/2021 14:59:50 - INFO - __main__ - Step 141939: {'lr': 3.651840125807493e-06, 'samples': 27252288, 'steps': 141938, 'loss/train': 1.5877424478530884} 08/31/2021 14:59:51 - INFO - __main__ - Step 141940: {'lr': 3.6509364543371724e-06, 'samples': 27252480, 'steps': 141939, 'loss/train': 1.1756513118743896} 08/31/2021 14:59:51 - INFO - __main__ - Step 141941: {'lr': 3.650032893867977e-06, 'samples': 27252672, 'steps': 141940, 'loss/train': 1.7242640256881714} 08/31/2021 14:59:52 - INFO - __main__ - Step 141942: {'lr': 3.64912944440024e-06, 'samples': 27252864, 'steps': 141941, 'loss/train': 0.9172897338867188} 08/31/2021 14:59:52 - INFO - __main__ - Step 141943: {'lr': 3.6482261059344046e-06, 'samples': 27253056, 'steps': 141942, 'loss/train': 1.1062414646148682} 08/31/2021 14:59:53 - INFO - __main__ - Step 141944: {'lr': 3.647322878470888e-06, 'samples': 27253248, 'steps': 141943, 'loss/train': 1.037583827972412} 08/31/2021 14:59:54 - INFO - __main__ - Step 141945: {'lr': 3.6464197620100783e-06, 'samples': 27253440, 'steps': 141944, 'loss/train': 1.193118691444397} 08/31/2021 14:59:54 - INFO - __main__ - Step 141946: {'lr': 3.6455167565523916e-06, 'samples': 27253632, 'steps': 141945, 'loss/train': 1.603076696395874} 08/31/2021 14:59:55 - INFO - __main__ - Step 141947: {'lr': 3.644613862098245e-06, 'samples': 27253824, 'steps': 141946, 'loss/train': 1.0802713632583618} 08/31/2021 14:59:55 - INFO - __main__ - Step 141948: {'lr': 3.6437110786480265e-06, 'samples': 27254016, 'steps': 141947, 'loss/train': 1.3046003580093384} 08/31/2021 14:59:57 - INFO - __main__ - Step 141949: {'lr': 3.642808406202125e-06, 'samples': 27254208, 'steps': 141948, 'loss/train': 0.6674414277076721} 08/31/2021 14:59:57 - INFO - __main__ - Step 141950: {'lr': 3.641905844761012e-06, 'samples': 27254400, 'steps': 141949, 'loss/train': 1.1696099042892456} 08/31/2021 14:59:57 - INFO - __main__ - Step 141951: {'lr': 3.6410033943250207e-06, 'samples': 27254592, 'steps': 141950, 'loss/train': 0.9780378341674805} 08/31/2021 14:59:58 - INFO - __main__ - Step 141952: {'lr': 3.6401010548946234e-06, 'samples': 27254784, 'steps': 141951, 'loss/train': 1.1735467910766602} 08/31/2021 14:59:58 - INFO - __main__ - Step 141953: {'lr': 3.6391988264701804e-06, 'samples': 27254976, 'steps': 141952, 'loss/train': 0.6929429173469543} 08/31/2021 15:00:00 - INFO - __main__ - Step 141954: {'lr': 3.638296709052108e-06, 'samples': 27255168, 'steps': 141953, 'loss/train': 1.2420512437820435} 08/31/2021 15:00:00 - INFO - __main__ - Step 141955: {'lr': 3.6373947026408505e-06, 'samples': 27255360, 'steps': 141954, 'loss/train': 1.537024736404419} 08/31/2021 15:00:01 - INFO - __main__ - Step 141956: {'lr': 3.6364928072367407e-06, 'samples': 27255552, 'steps': 141955, 'loss/train': 1.2809308767318726} 08/31/2021 15:00:01 - INFO - __main__ - Step 141957: {'lr': 3.635591022840251e-06, 'samples': 27255744, 'steps': 141956, 'loss/train': 0.8876137733459473} 08/31/2021 15:00:01 - INFO - __main__ - Step 141958: {'lr': 3.634689349451742e-06, 'samples': 27255936, 'steps': 141957, 'loss/train': 1.491241693496704} 08/31/2021 15:00:02 - INFO - __main__ - Step 141959: {'lr': 3.6337877870716574e-06, 'samples': 27256128, 'steps': 141958, 'loss/train': 1.79803466796875} 08/31/2021 15:00:03 - INFO - __main__ - Step 141960: {'lr': 3.6328863357003582e-06, 'samples': 27256320, 'steps': 141959, 'loss/train': 0.7598419785499573} 08/31/2021 15:00:04 - INFO - __main__ - Step 141961: {'lr': 3.6319849953383164e-06, 'samples': 27256512, 'steps': 141960, 'loss/train': 0.5922835469245911} 08/31/2021 15:00:04 - INFO - __main__ - Step 141962: {'lr': 3.631083765985865e-06, 'samples': 27256704, 'steps': 141961, 'loss/train': 1.1181217432022095} 08/31/2021 15:00:04 - INFO - __main__ - Step 141963: {'lr': 3.6301826476434764e-06, 'samples': 27256896, 'steps': 141962, 'loss/train': 0.4881720244884491} 08/31/2021 15:00:05 - INFO - __main__ - Step 141964: {'lr': 3.6292816403115104e-06, 'samples': 27257088, 'steps': 141963, 'loss/train': 1.0763238668441772} 08/31/2021 15:00:06 - INFO - __main__ - Step 141965: {'lr': 3.628380743990384e-06, 'samples': 27257280, 'steps': 141964, 'loss/train': 1.4935837984085083} 08/31/2021 15:00:07 - INFO - __main__ - Step 141966: {'lr': 3.627479958680513e-06, 'samples': 27257472, 'steps': 141965, 'loss/train': 0.9513297080993652} 08/31/2021 15:00:07 - INFO - __main__ - Step 141967: {'lr': 3.6265792843822863e-06, 'samples': 27257664, 'steps': 141966, 'loss/train': 0.9431047439575195} 08/31/2021 15:00:08 - INFO - __main__ - Step 141968: {'lr': 3.6256787210961485e-06, 'samples': 27257856, 'steps': 141967, 'loss/train': 1.2321313619613647} 08/31/2021 15:00:08 - INFO - __main__ - Step 141969: {'lr': 3.6247782688224596e-06, 'samples': 27258048, 'steps': 141968, 'loss/train': 1.4622853994369507} 08/31/2021 15:00:09 - INFO - __main__ - Step 141970: {'lr': 3.623877927561664e-06, 'samples': 27258240, 'steps': 141969, 'loss/train': 1.2562947273254395} 08/31/2021 15:00:10 - INFO - __main__ - Step 141971: {'lr': 3.6229776973141228e-06, 'samples': 27258432, 'steps': 141970, 'loss/train': 0.10224083065986633} 08/31/2021 15:00:10 - INFO - __main__ - Step 141972: {'lr': 3.6220775780802794e-06, 'samples': 27258624, 'steps': 141971, 'loss/train': 0.9155038595199585} 08/31/2021 15:00:11 - INFO - __main__ - Step 141973: {'lr': 3.6211775698605232e-06, 'samples': 27258816, 'steps': 141972, 'loss/train': 1.3220969438552856} 08/31/2021 15:00:11 - INFO - __main__ - Step 141974: {'lr': 3.620277672655242e-06, 'samples': 27259008, 'steps': 141973, 'loss/train': 0.36688926815986633} 08/31/2021 15:00:12 - INFO - __main__ - Step 141975: {'lr': 3.6193778864648805e-06, 'samples': 27259200, 'steps': 141974, 'loss/train': 0.9009528160095215} 08/31/2021 15:00:13 - INFO - __main__ - Step 141976: {'lr': 3.618478211289827e-06, 'samples': 27259392, 'steps': 141975, 'loss/train': 0.8959639668464661} 08/31/2021 15:00:13 - INFO - __main__ - Step 141977: {'lr': 3.6175786471304706e-06, 'samples': 27259584, 'steps': 141976, 'loss/train': 1.166746735572815} 08/31/2021 15:00:13 - INFO - __main__ - Step 141978: {'lr': 3.6166791939872544e-06, 'samples': 27259776, 'steps': 141977, 'loss/train': 1.0865284204483032} 08/31/2021 15:00:14 - INFO - __main__ - Step 141979: {'lr': 3.61577985186054e-06, 'samples': 27259968, 'steps': 141978, 'loss/train': 0.164583221077919} 08/31/2021 15:00:14 - INFO - __main__ - Step 141980: {'lr': 3.6148806207507714e-06, 'samples': 27260160, 'steps': 141979, 'loss/train': 1.1734933853149414} 08/31/2021 15:00:16 - INFO - __main__ - Step 141981: {'lr': 3.6139815006583367e-06, 'samples': 27260352, 'steps': 141980, 'loss/train': 1.1971925497055054} 08/31/2021 15:00:16 - INFO - __main__ - Step 141982: {'lr': 3.6130824915836246e-06, 'samples': 27260544, 'steps': 141981, 'loss/train': 0.37045997381210327} 08/31/2021 15:00:17 - INFO - __main__ - Step 141983: {'lr': 3.61218359352708e-06, 'samples': 27260736, 'steps': 141982, 'loss/train': 3.6131720542907715} 08/31/2021 15:00:17 - INFO - __main__ - Step 141984: {'lr': 3.6112848064890626e-06, 'samples': 27260928, 'steps': 141983, 'loss/train': 1.3155453205108643} 08/31/2021 15:00:17 - INFO - __main__ - Step 141985: {'lr': 3.610386130469989e-06, 'samples': 27261120, 'steps': 141984, 'loss/train': 0.9675453901290894} 08/31/2021 15:00:19 - INFO - __main__ - Step 141986: {'lr': 3.6094875654702765e-06, 'samples': 27261312, 'steps': 141985, 'loss/train': 2.186328411102295} 08/31/2021 15:00:19 - INFO - __main__ - Step 141987: {'lr': 3.6085891114903402e-06, 'samples': 27261504, 'steps': 141986, 'loss/train': 0.2503807544708252} 08/31/2021 15:00:20 - INFO - __main__ - Step 141988: {'lr': 3.6076907685305693e-06, 'samples': 27261696, 'steps': 141987, 'loss/train': 1.506464958190918} 08/31/2021 15:00:20 - INFO - __main__ - Step 141989: {'lr': 3.60679253659138e-06, 'samples': 27261888, 'steps': 141988, 'loss/train': 1.2352112531661987} 08/31/2021 15:00:20 - INFO - __main__ - Step 141990: {'lr': 3.605894415673133e-06, 'samples': 27262080, 'steps': 141989, 'loss/train': 1.1629613637924194} 08/31/2021 15:00:22 - INFO - __main__ - Step 141991: {'lr': 3.604996405776301e-06, 'samples': 27262272, 'steps': 141990, 'loss/train': 1.127396583557129} 08/31/2021 15:00:22 - INFO - __main__ - Step 141992: {'lr': 3.6040985069012433e-06, 'samples': 27262464, 'steps': 141991, 'loss/train': 1.3568402528762817} 08/31/2021 15:00:23 - INFO - __main__ - Step 141993: {'lr': 3.6032007190483773e-06, 'samples': 27262656, 'steps': 141992, 'loss/train': 1.0188344717025757} 08/31/2021 15:00:23 - INFO - __main__ - Step 141994: {'lr': 3.602303042218119e-06, 'samples': 27262848, 'steps': 141993, 'loss/train': 1.7389720678329468} 08/31/2021 15:00:23 - INFO - __main__ - Step 141995: {'lr': 3.601405476410857e-06, 'samples': 27263040, 'steps': 141994, 'loss/train': 1.048274040222168} 08/31/2021 15:00:24 - INFO - __main__ - Step 141996: {'lr': 3.6005080216269804e-06, 'samples': 27263232, 'steps': 141995, 'loss/train': 1.0728790760040283} 08/31/2021 15:00:26 - INFO - __main__ - Step 141997: {'lr': 3.5996106778669326e-06, 'samples': 27263424, 'steps': 141996, 'loss/train': 0.611709475517273} 08/31/2021 15:00:26 - INFO - __main__ - Step 141998: {'lr': 3.598713445131102e-06, 'samples': 27263616, 'steps': 141997, 'loss/train': 0.6970728635787964} 08/31/2021 15:00:27 - INFO - __main__ - Step 141999: {'lr': 3.597816323419878e-06, 'samples': 27263808, 'steps': 141998, 'loss/train': 0.3445107042789459} 08/31/2021 15:00:27 - INFO - __main__ - Step 142000: {'lr': 3.5969193127336762e-06, 'samples': 27264000, 'steps': 141999, 'loss/train': 1.131650686264038} 08/31/2021 15:00:27 - INFO - __main__ - Step 142001: {'lr': 3.5960224130728858e-06, 'samples': 27264192, 'steps': 142000, 'loss/train': 0.40386196970939636} 08/31/2021 15:00:29 - INFO - __main__ - Step 142002: {'lr': 3.5951256244379506e-06, 'samples': 27264384, 'steps': 142001, 'loss/train': 0.8821851015090942} 08/31/2021 15:00:29 - INFO - __main__ - Step 142003: {'lr': 3.594228946829231e-06, 'samples': 27264576, 'steps': 142002, 'loss/train': 1.0946171283721924} 08/31/2021 15:00:30 - INFO - __main__ - Step 142004: {'lr': 3.593332380247144e-06, 'samples': 27264768, 'steps': 142003, 'loss/train': 1.72353196144104} 08/31/2021 15:00:30 - INFO - __main__ - Step 142005: {'lr': 3.5924359246921055e-06, 'samples': 27264960, 'steps': 142004, 'loss/train': 0.9341777563095093} 08/31/2021 15:00:30 - INFO - __main__ - Step 142006: {'lr': 3.591539580164532e-06, 'samples': 27265152, 'steps': 142005, 'loss/train': 1.1440342664718628} 08/31/2021 15:00:32 - INFO - __main__ - Step 142007: {'lr': 3.590643346664785e-06, 'samples': 27265344, 'steps': 142006, 'loss/train': 0.071035236120224} 08/31/2021 15:00:32 - INFO - __main__ - Step 142008: {'lr': 3.5897472241933072e-06, 'samples': 27265536, 'steps': 142007, 'loss/train': 0.8781927824020386} 08/31/2021 15:00:33 - INFO - __main__ - Step 142009: {'lr': 3.588851212750488e-06, 'samples': 27265728, 'steps': 142008, 'loss/train': 1.112837553024292} 08/31/2021 15:00:33 - INFO - __main__ - Step 142010: {'lr': 3.5879553123367438e-06, 'samples': 27265920, 'steps': 142009, 'loss/train': 0.8688191771507263} 08/31/2021 15:00:34 - INFO - __main__ - Step 142011: {'lr': 3.587059522952435e-06, 'samples': 27266112, 'steps': 142010, 'loss/train': 1.108267903327942} 08/31/2021 15:00:35 - INFO - __main__ - Step 142012: {'lr': 3.586163844598006e-06, 'samples': 27266304, 'steps': 142011, 'loss/train': 1.3440138101577759} 08/31/2021 15:00:35 - INFO - __main__ - Step 142013: {'lr': 3.5852682772738456e-06, 'samples': 27266496, 'steps': 142012, 'loss/train': 0.9723638296127319} 08/31/2021 15:00:36 - INFO - __main__ - Step 142014: {'lr': 3.5843728209803695e-06, 'samples': 27266688, 'steps': 142013, 'loss/train': 1.626837968826294} 08/31/2021 15:00:36 - INFO - __main__ - Step 142015: {'lr': 3.5834774757179665e-06, 'samples': 27266880, 'steps': 142014, 'loss/train': 1.1159015893936157} 08/31/2021 15:00:37 - INFO - __main__ - Step 142016: {'lr': 3.582582241487026e-06, 'samples': 27267072, 'steps': 142015, 'loss/train': 1.1995517015457153} 08/31/2021 15:00:37 - INFO - __main__ - Step 142017: {'lr': 3.581687118287991e-06, 'samples': 27267264, 'steps': 142016, 'loss/train': 1.0109928846359253} 08/31/2021 15:00:38 - INFO - __main__ - Step 142018: {'lr': 3.5807921061212503e-06, 'samples': 27267456, 'steps': 142017, 'loss/train': 1.0017821788787842} 08/31/2021 15:00:39 - INFO - __main__ - Step 142019: {'lr': 3.5798972049871926e-06, 'samples': 27267648, 'steps': 142018, 'loss/train': 1.1668578386306763} 08/31/2021 15:00:39 - INFO - __main__ - Step 142020: {'lr': 3.5790024148862345e-06, 'samples': 27267840, 'steps': 142019, 'loss/train': 1.494842290878296} 08/31/2021 15:00:40 - INFO - __main__ - Step 142021: {'lr': 3.578107735818792e-06, 'samples': 27268032, 'steps': 142020, 'loss/train': 0.5097752213478088} 08/31/2021 15:00:40 - INFO - __main__ - Step 142022: {'lr': 3.5772131677852536e-06, 'samples': 27268224, 'steps': 142021, 'loss/train': 0.9309543967247009} 08/31/2021 15:00:41 - INFO - __main__ - Step 142023: {'lr': 3.5763187107860083e-06, 'samples': 27268416, 'steps': 142022, 'loss/train': 1.4130810499191284} 08/31/2021 15:00:42 - INFO - __main__ - Step 142024: {'lr': 3.5754243648214445e-06, 'samples': 27268608, 'steps': 142023, 'loss/train': 0.8052539229393005} 08/31/2021 15:00:42 - INFO - __main__ - Step 142025: {'lr': 3.5745301298920343e-06, 'samples': 27268800, 'steps': 142024, 'loss/train': 0.9349585771560669} 08/31/2021 15:00:43 - INFO - __main__ - Step 142026: {'lr': 3.5736360059981098e-06, 'samples': 27268992, 'steps': 142025, 'loss/train': 1.1772040128707886} 08/31/2021 15:00:43 - INFO - __main__ - Step 142027: {'lr': 3.572741993140116e-06, 'samples': 27269184, 'steps': 142026, 'loss/train': 1.1604996919631958} 08/31/2021 15:00:44 - INFO - __main__ - Step 142028: {'lr': 3.5718480913184136e-06, 'samples': 27269376, 'steps': 142027, 'loss/train': 0.9499559998512268} 08/31/2021 15:00:45 - INFO - __main__ - Step 142029: {'lr': 3.5709543005334745e-06, 'samples': 27269568, 'steps': 142028, 'loss/train': 0.7278013229370117} 08/31/2021 15:00:45 - INFO - __main__ - Step 142030: {'lr': 3.5700606207856313e-06, 'samples': 27269760, 'steps': 142029, 'loss/train': 1.1551142930984497} 08/31/2021 15:00:46 - INFO - __main__ - Step 142031: {'lr': 3.5691670520753283e-06, 'samples': 27269952, 'steps': 142030, 'loss/train': 0.6043422818183899} 08/31/2021 15:00:46 - INFO - __main__ - Step 142032: {'lr': 3.5682735944029542e-06, 'samples': 27270144, 'steps': 142031, 'loss/train': 1.2483391761779785} 08/31/2021 15:00:47 - INFO - __main__ - Step 142033: {'lr': 3.5673802477689255e-06, 'samples': 27270336, 'steps': 142032, 'loss/train': 0.9010898470878601} 08/31/2021 15:00:48 - INFO - __main__ - Step 142034: {'lr': 3.5664870121736028e-06, 'samples': 27270528, 'steps': 142033, 'loss/train': 0.8488574624061584} 08/31/2021 15:00:48 - INFO - __main__ - Step 142035: {'lr': 3.5655938876174575e-06, 'samples': 27270720, 'steps': 142034, 'loss/train': 1.0672372579574585} 08/31/2021 15:00:48 - INFO - __main__ - Step 142036: {'lr': 3.5647008741008235e-06, 'samples': 27270912, 'steps': 142035, 'loss/train': 1.0362532138824463} 08/31/2021 15:00:49 - INFO - __main__ - Step 142037: {'lr': 3.5638079716241446e-06, 'samples': 27271104, 'steps': 142036, 'loss/train': 0.9511735439300537} 08/31/2021 15:00:50 - INFO - __main__ - Step 142038: {'lr': 3.562915180187809e-06, 'samples': 27271296, 'steps': 142037, 'loss/train': 1.1287891864776611} 08/31/2021 15:00:51 - INFO - __main__ - Step 142039: {'lr': 3.5620224997922337e-06, 'samples': 27271488, 'steps': 142038, 'loss/train': 0.9396621584892273} 08/31/2021 15:00:51 - INFO - __main__ - Step 142040: {'lr': 3.561129930437779e-06, 'samples': 27271680, 'steps': 142039, 'loss/train': 1.5468504428863525} 08/31/2021 15:00:51 - INFO - __main__ - Step 142041: {'lr': 3.560237472124889e-06, 'samples': 27271872, 'steps': 142040, 'loss/train': 1.2377241849899292} 08/31/2021 15:00:52 - INFO - __main__ - Step 142042: {'lr': 3.559345124853952e-06, 'samples': 27272064, 'steps': 142041, 'loss/train': 1.1659489870071411} 08/31/2021 15:00:53 - INFO - __main__ - Step 142043: {'lr': 3.5584528886253853e-06, 'samples': 27272256, 'steps': 142042, 'loss/train': 1.0974476337432861} 08/31/2021 15:00:54 - INFO - __main__ - Step 142044: {'lr': 3.5575607634395492e-06, 'samples': 27272448, 'steps': 142043, 'loss/train': 0.8690295815467834} 08/31/2021 15:00:54 - INFO - __main__ - Step 142045: {'lr': 3.5566687492969153e-06, 'samples': 27272640, 'steps': 142044, 'loss/train': 1.4208190441131592} 08/31/2021 15:00:54 - INFO - __main__ - Step 142046: {'lr': 3.555776846197817e-06, 'samples': 27272832, 'steps': 142045, 'loss/train': 1.1142359972000122} 08/31/2021 15:00:55 - INFO - __main__ - Step 142047: {'lr': 3.5548850541426702e-06, 'samples': 27273024, 'steps': 142046, 'loss/train': 1.0469920635223389} 08/31/2021 15:00:57 - INFO - __main__ - Step 142048: {'lr': 3.5539933731319196e-06, 'samples': 27273216, 'steps': 142047, 'loss/train': 0.13623178005218506} 08/31/2021 15:00:57 - INFO - __main__ - Step 142049: {'lr': 3.5531018031659255e-06, 'samples': 27273408, 'steps': 142048, 'loss/train': 1.6749597787857056} 08/31/2021 15:00:58 - INFO - __main__ - Step 142050: {'lr': 3.552210344245105e-06, 'samples': 27273600, 'steps': 142049, 'loss/train': 0.8649182915687561} 08/31/2021 15:00:58 - INFO - __main__ - Step 142051: {'lr': 3.5513189963698456e-06, 'samples': 27273792, 'steps': 142050, 'loss/train': 0.48098909854888916} 08/31/2021 15:00:59 - INFO - __main__ - Step 142052: {'lr': 3.5504277595405645e-06, 'samples': 27273984, 'steps': 142051, 'loss/train': 1.5840789079666138} 08/31/2021 15:00:59 - INFO - __main__ - Step 142053: {'lr': 3.5495366337576497e-06, 'samples': 27274176, 'steps': 142052, 'loss/train': 0.9739262461662292} 08/31/2021 15:01:01 - INFO - __main__ - Step 142054: {'lr': 3.548645619021518e-06, 'samples': 27274368, 'steps': 142053, 'loss/train': 1.0064852237701416} 08/31/2021 15:01:01 - INFO - __main__ - Step 142055: {'lr': 3.5477547153325573e-06, 'samples': 27274560, 'steps': 142054, 'loss/train': 0.3671053647994995} 08/31/2021 15:01:02 - INFO - __main__ - Step 142056: {'lr': 3.546863922691157e-06, 'samples': 27274752, 'steps': 142055, 'loss/train': 5.652730464935303} 08/31/2021 15:01:02 - INFO - __main__ - Step 142057: {'lr': 3.5459732410977606e-06, 'samples': 27274944, 'steps': 142056, 'loss/train': 5.71475887298584} 08/31/2021 15:01:02 - INFO - __main__ - Step 142058: {'lr': 3.5450826705527574e-06, 'samples': 27275136, 'steps': 142057, 'loss/train': 5.7562384605407715} 08/31/2021 15:01:03 - INFO - __main__ - Step 142059: {'lr': 3.5441922110565074e-06, 'samples': 27275328, 'steps': 142058, 'loss/train': 1.0010930299758911} 08/31/2021 15:01:04 - INFO - __main__ - Step 142060: {'lr': 3.543301862609455e-06, 'samples': 27275520, 'steps': 142059, 'loss/train': 0.8171534538269043} 08/31/2021 15:01:05 - INFO - __main__ - Step 142061: {'lr': 3.5424116252119885e-06, 'samples': 27275712, 'steps': 142060, 'loss/train': 0.8911505341529846} 08/31/2021 15:01:05 - INFO - __main__ - Step 142062: {'lr': 3.541521498864525e-06, 'samples': 27275904, 'steps': 142061, 'loss/train': 0.9177618622779846} 08/31/2021 15:01:05 - INFO - __main__ - Step 142063: {'lr': 3.5406314835674524e-06, 'samples': 27276096, 'steps': 142062, 'loss/train': 0.8128941059112549} 08/31/2021 15:01:06 - INFO - __main__ - Step 142064: {'lr': 3.5397415793211317e-06, 'samples': 27276288, 'steps': 142063, 'loss/train': 1.0630449056625366} 08/31/2021 15:01:08 - INFO - __main__ - Step 142065: {'lr': 3.538851786126035e-06, 'samples': 27276480, 'steps': 142064, 'loss/train': 1.2097448110580444} 08/31/2021 15:01:08 - INFO - __main__ - Step 142066: {'lr': 3.537962103982495e-06, 'samples': 27276672, 'steps': 142065, 'loss/train': 1.421787142753601} 08/31/2021 15:01:09 - INFO - __main__ - Step 142067: {'lr': 3.5370725328909557e-06, 'samples': 27276864, 'steps': 142066, 'loss/train': 0.23738424479961395} 08/31/2021 15:01:09 - INFO - __main__ - Step 142068: {'lr': 3.536183072851834e-06, 'samples': 27277056, 'steps': 142067, 'loss/train': 1.3508442640304565} 08/31/2021 15:01:09 - INFO - __main__ - Step 142069: {'lr': 3.5352937238654627e-06, 'samples': 27277248, 'steps': 142068, 'loss/train': 1.2034423351287842} 08/31/2021 15:01:10 - INFO - __main__ - Step 142070: {'lr': 3.534404485932313e-06, 'samples': 27277440, 'steps': 142069, 'loss/train': 1.110749363899231} 08/31/2021 15:01:11 - INFO - __main__ - Step 142071: {'lr': 3.533515359052747e-06, 'samples': 27277632, 'steps': 142070, 'loss/train': 0.5758362412452698} 08/31/2021 15:01:12 - INFO - __main__ - Step 142072: {'lr': 3.53262634322718e-06, 'samples': 27277824, 'steps': 142071, 'loss/train': 0.921920120716095} 08/31/2021 15:01:12 - INFO - __main__ - Step 142073: {'lr': 3.5317374384560286e-06, 'samples': 27278016, 'steps': 142072, 'loss/train': 1.0301129817962646} 08/31/2021 15:01:12 - INFO - __main__ - Step 142074: {'lr': 3.5308486447396537e-06, 'samples': 27278208, 'steps': 142073, 'loss/train': 1.553119421005249} 08/31/2021 15:01:13 - INFO - __main__ - Step 142075: {'lr': 3.5299599620784716e-06, 'samples': 27278400, 'steps': 142074, 'loss/train': 1.0414906740188599} 08/31/2021 15:01:14 - INFO - __main__ - Step 142076: {'lr': 3.529071390472899e-06, 'samples': 27278592, 'steps': 142075, 'loss/train': 1.0333402156829834} 08/31/2021 15:01:15 - INFO - __main__ - Step 142077: {'lr': 3.5281829299233237e-06, 'samples': 27278784, 'steps': 142076, 'loss/train': 1.2929644584655762} 08/31/2021 15:01:15 - INFO - __main__ - Step 142078: {'lr': 3.5272945804301347e-06, 'samples': 27278976, 'steps': 142077, 'loss/train': 1.1000362634658813} 08/31/2021 15:01:15 - INFO - __main__ - Step 142079: {'lr': 3.5264063419937486e-06, 'samples': 27279168, 'steps': 142078, 'loss/train': 1.4597071409225464} 08/31/2021 15:01:16 - INFO - __main__ - Step 142080: {'lr': 3.5255182146145535e-06, 'samples': 27279360, 'steps': 142079, 'loss/train': 0.7534598708152771} 08/31/2021 15:01:17 - INFO - __main__ - Step 142081: {'lr': 3.5246301982929385e-06, 'samples': 27279552, 'steps': 142080, 'loss/train': 0.766438901424408} 08/31/2021 15:01:18 - INFO - __main__ - Step 142082: {'lr': 3.5237422930293474e-06, 'samples': 27279744, 'steps': 142081, 'loss/train': 0.928270697593689} 08/31/2021 15:01:18 - INFO - __main__ - Step 142083: {'lr': 3.5228544988241682e-06, 'samples': 27279936, 'steps': 142082, 'loss/train': 0.7104824185371399} 08/31/2021 15:01:18 - INFO - __main__ - Step 142084: {'lr': 3.5219668156777906e-06, 'samples': 27280128, 'steps': 142083, 'loss/train': 0.3193926215171814} 08/31/2021 15:01:19 - INFO - __main__ - Step 142085: {'lr': 3.521079243590575e-06, 'samples': 27280320, 'steps': 142084, 'loss/train': 0.3711840510368347} 08/31/2021 15:01:20 - INFO - __main__ - Step 142086: {'lr': 3.5201917825629646e-06, 'samples': 27280512, 'steps': 142085, 'loss/train': 1.1710646152496338} 08/31/2021 15:01:21 - INFO - __main__ - Step 142087: {'lr': 3.5193044325953772e-06, 'samples': 27280704, 'steps': 142086, 'loss/train': 1.1892744302749634} 08/31/2021 15:01:21 - INFO - __main__ - Step 142088: {'lr': 3.5184171936881724e-06, 'samples': 27280896, 'steps': 142087, 'loss/train': 0.8214914202690125} 08/31/2021 15:01:22 - INFO - __main__ - Step 142089: {'lr': 3.5175300658417677e-06, 'samples': 27281088, 'steps': 142088, 'loss/train': 0.6542841792106628} 08/31/2021 15:01:22 - INFO - __main__ - Step 142090: {'lr': 3.5166430490565506e-06, 'samples': 27281280, 'steps': 142089, 'loss/train': 0.7765740752220154} 08/31/2021 15:01:22 - INFO - __main__ - Step 142091: {'lr': 3.515756143332938e-06, 'samples': 27281472, 'steps': 142090, 'loss/train': 1.4403666257858276} 08/31/2021 15:01:24 - INFO - __main__ - Step 142092: {'lr': 3.514869348671318e-06, 'samples': 27281664, 'steps': 142091, 'loss/train': 0.04043881967663765} 08/31/2021 15:01:24 - INFO - __main__ - Step 142093: {'lr': 3.5139826650721073e-06, 'samples': 27281856, 'steps': 142092, 'loss/train': 1.2335431575775146} 08/31/2021 15:01:25 - INFO - __main__ - Step 142094: {'lr': 3.513096092535667e-06, 'samples': 27282048, 'steps': 142093, 'loss/train': 1.1489739418029785} 08/31/2021 15:01:25 - INFO - __main__ - Step 142095: {'lr': 3.5122096310624686e-06, 'samples': 27282240, 'steps': 142094, 'loss/train': 1.2795746326446533} 08/31/2021 15:01:25 - INFO - __main__ - Step 142096: {'lr': 3.511323280652817e-06, 'samples': 27282432, 'steps': 142095, 'loss/train': 0.652859091758728} 08/31/2021 15:01:27 - INFO - __main__ - Step 142097: {'lr': 3.5104370413071853e-06, 'samples': 27282624, 'steps': 142096, 'loss/train': 1.1456959247589111} 08/31/2021 15:01:27 - INFO - __main__ - Step 142098: {'lr': 3.5095509130259327e-06, 'samples': 27282816, 'steps': 142097, 'loss/train': 0.6108925938606262} 08/31/2021 15:01:28 - INFO - __main__ - Step 142099: {'lr': 3.508664895809477e-06, 'samples': 27283008, 'steps': 142098, 'loss/train': 1.3384830951690674} 08/31/2021 15:01:28 - INFO - __main__ - Step 142100: {'lr': 3.5077789896582336e-06, 'samples': 27283200, 'steps': 142099, 'loss/train': 1.2308390140533447} 08/31/2021 15:01:28 - INFO - __main__ - Step 142101: {'lr': 3.5068931945725637e-06, 'samples': 27283392, 'steps': 142100, 'loss/train': 1.0495994091033936} 08/31/2021 15:01:30 - INFO - __main__ - Step 142102: {'lr': 3.5060075105528833e-06, 'samples': 27283584, 'steps': 142101, 'loss/train': 1.462727427482605} 08/31/2021 15:01:31 - INFO - __main__ - Step 142103: {'lr': 3.505121937599581e-06, 'samples': 27283776, 'steps': 142102, 'loss/train': 0.7561706304550171} 08/31/2021 15:01:31 - INFO - __main__ - Step 142104: {'lr': 3.504236475713074e-06, 'samples': 27283968, 'steps': 142103, 'loss/train': 1.0154718160629272} 08/31/2021 15:01:32 - INFO - __main__ - Step 142105: {'lr': 3.5033511248937777e-06, 'samples': 27284160, 'steps': 142104, 'loss/train': 1.075303554534912} 08/31/2021 15:01:32 - INFO - __main__ - Step 142106: {'lr': 3.502465885142053e-06, 'samples': 27284352, 'steps': 142105, 'loss/train': 1.6890389919281006} 08/31/2021 15:01:33 - INFO - __main__ - Step 142107: {'lr': 3.501580756458317e-06, 'samples': 27284544, 'steps': 142106, 'loss/train': 1.2791377305984497} 08/31/2021 15:01:34 - INFO - __main__ - Step 142108: {'lr': 3.5006957388429572e-06, 'samples': 27284736, 'steps': 142107, 'loss/train': 0.6852620840072632} 08/31/2021 15:01:34 - INFO - __main__ - Step 142109: {'lr': 3.4998108322963627e-06, 'samples': 27284928, 'steps': 142108, 'loss/train': 0.7136005163192749} 08/31/2021 15:01:35 - INFO - __main__ - Step 142110: {'lr': 3.498926036818978e-06, 'samples': 27285120, 'steps': 142109, 'loss/train': 0.7180091738700867} 08/31/2021 15:01:35 - INFO - __main__ - Step 142111: {'lr': 3.4980413524111632e-06, 'samples': 27285312, 'steps': 142110, 'loss/train': 0.540937066078186} 08/31/2021 15:01:36 - INFO - __main__ - Step 142112: {'lr': 3.497156779073335e-06, 'samples': 27285504, 'steps': 142111, 'loss/train': 1.2002290487289429} 08/31/2021 15:01:37 - INFO - __main__ - Step 142113: {'lr': 3.496272316805882e-06, 'samples': 27285696, 'steps': 142112, 'loss/train': 1.2071082592010498} 08/31/2021 15:01:37 - INFO - __main__ - Step 142114: {'lr': 3.4953879656091923e-06, 'samples': 27285888, 'steps': 142113, 'loss/train': 1.087273359298706} 08/31/2021 15:01:38 - INFO - __main__ - Step 142115: {'lr': 3.494503725483683e-06, 'samples': 27286080, 'steps': 142114, 'loss/train': 1.0484516620635986} 08/31/2021 15:01:38 - INFO - __main__ - Step 142116: {'lr': 3.4936195964297424e-06, 'samples': 27286272, 'steps': 142115, 'loss/train': 0.8096915483474731} 08/31/2021 15:01:39 - INFO - __main__ - Step 142117: {'lr': 3.4927355784477866e-06, 'samples': 27286464, 'steps': 142116, 'loss/train': 0.7675269842147827} 08/31/2021 15:01:40 - INFO - __main__ - Step 142118: {'lr': 3.4918516715382044e-06, 'samples': 27286656, 'steps': 142117, 'loss/train': 1.2888458967208862} 08/31/2021 15:01:40 - INFO - __main__ - Step 142119: {'lr': 3.490967875701384e-06, 'samples': 27286848, 'steps': 142118, 'loss/train': 0.915867805480957} 08/31/2021 15:01:41 - INFO - __main__ - Step 142120: {'lr': 3.4900841909377145e-06, 'samples': 27287040, 'steps': 142119, 'loss/train': 0.7701749205589294} 08/31/2021 15:01:41 - INFO - __main__ - Step 142121: {'lr': 3.489200617247612e-06, 'samples': 27287232, 'steps': 142120, 'loss/train': 1.563032627105713} 08/31/2021 15:01:43 - INFO - __main__ - Step 142122: {'lr': 3.488317154631493e-06, 'samples': 27287424, 'steps': 142121, 'loss/train': 0.7811850905418396} 08/31/2021 15:01:43 - INFO - __main__ - Step 142123: {'lr': 3.487433803089718e-06, 'samples': 27287616, 'steps': 142122, 'loss/train': 0.4397580027580261} 08/31/2021 15:01:43 - INFO - __main__ - Step 142124: {'lr': 3.4865505626227033e-06, 'samples': 27287808, 'steps': 142123, 'loss/train': 0.03492980822920799} 08/31/2021 15:01:44 - INFO - __main__ - Step 142125: {'lr': 3.485667433230838e-06, 'samples': 27288000, 'steps': 142124, 'loss/train': 1.5282458066940308} 08/31/2021 15:01:44 - INFO - __main__ - Step 142126: {'lr': 3.484784414914538e-06, 'samples': 27288192, 'steps': 142125, 'loss/train': 1.1389141082763672} 08/31/2021 15:01:44 - INFO - __main__ - Step 142127: {'lr': 3.4839015076741644e-06, 'samples': 27288384, 'steps': 142126, 'loss/train': 1.0662373304367065} 08/31/2021 15:01:46 - INFO - __main__ - Step 142128: {'lr': 3.483018711510161e-06, 'samples': 27288576, 'steps': 142127, 'loss/train': 0.8749184012413025} 08/31/2021 15:01:46 - INFO - __main__ - Step 142129: {'lr': 3.4821360264229165e-06, 'samples': 27288768, 'steps': 142128, 'loss/train': 0.5835163593292236} 08/31/2021 15:01:47 - INFO - __main__ - Step 142130: {'lr': 3.481253452412819e-06, 'samples': 27288960, 'steps': 142129, 'loss/train': 0.8474164009094238} 08/31/2021 15:01:47 - INFO - __main__ - Step 142131: {'lr': 3.4803709894802582e-06, 'samples': 27289152, 'steps': 142130, 'loss/train': 0.9479709267616272} 08/31/2021 15:01:47 - INFO - __main__ - Step 142132: {'lr': 3.479488637625622e-06, 'samples': 27289344, 'steps': 142131, 'loss/train': 0.8063335418701172} 08/31/2021 15:01:49 - INFO - __main__ - Step 142133: {'lr': 3.478606396849354e-06, 'samples': 27289536, 'steps': 142132, 'loss/train': 1.2488740682601929} 08/31/2021 15:01:49 - INFO - __main__ - Step 142134: {'lr': 3.4777242671517885e-06, 'samples': 27289728, 'steps': 142133, 'loss/train': 0.7784118056297302} 08/31/2021 15:01:50 - INFO - __main__ - Step 142135: {'lr': 3.4768422485333684e-06, 'samples': 27289920, 'steps': 142134, 'loss/train': 0.6174858808517456} 08/31/2021 15:01:50 - INFO - __main__ - Step 142136: {'lr': 3.4759603409944827e-06, 'samples': 27290112, 'steps': 142135, 'loss/train': 1.1602814197540283} 08/31/2021 15:01:50 - INFO - __main__ - Step 142137: {'lr': 3.4750785445355206e-06, 'samples': 27290304, 'steps': 142136, 'loss/train': 1.3942219018936157} 08/31/2021 15:01:52 - INFO - __main__ - Step 142138: {'lr': 3.4741968591568975e-06, 'samples': 27290496, 'steps': 142137, 'loss/train': 0.7496641278266907} 08/31/2021 15:01:53 - INFO - __main__ - Step 142139: {'lr': 3.4733152848589742e-06, 'samples': 27290688, 'steps': 142138, 'loss/train': 1.0478920936584473} 08/31/2021 15:01:53 - INFO - __main__ - Step 142140: {'lr': 3.472433821642196e-06, 'samples': 27290880, 'steps': 142139, 'loss/train': 1.3011080026626587} 08/31/2021 15:01:53 - INFO - __main__ - Step 142141: {'lr': 3.4715524695069223e-06, 'samples': 27291072, 'steps': 142140, 'loss/train': 1.7357327938079834} 08/31/2021 15:01:54 - INFO - __main__ - Step 142142: {'lr': 3.4706712284535424e-06, 'samples': 27291264, 'steps': 142141, 'loss/train': 1.710662841796875} 08/31/2021 15:01:56 - INFO - __main__ - Step 142143: {'lr': 3.469790098482528e-06, 'samples': 27291456, 'steps': 142142, 'loss/train': 0.02972984127700329} 08/31/2021 15:01:56 - INFO - __main__ - Step 142144: {'lr': 3.4689090795941847e-06, 'samples': 27291648, 'steps': 142143, 'loss/train': 0.9303612112998962} 08/31/2021 15:01:56 - INFO - __main__ - Step 142145: {'lr': 3.468028171788956e-06, 'samples': 27291840, 'steps': 142144, 'loss/train': 1.233770728111267} 08/31/2021 15:01:57 - INFO - __main__ - Step 142146: {'lr': 3.467147375067231e-06, 'samples': 27292032, 'steps': 142145, 'loss/train': 0.8999291658401489} 08/31/2021 15:01:57 - INFO - __main__ - Step 142147: {'lr': 3.466266689429398e-06, 'samples': 27292224, 'steps': 142146, 'loss/train': 0.7123954892158508} 08/31/2021 15:01:59 - INFO - __main__ - Step 142148: {'lr': 3.4653861148758457e-06, 'samples': 27292416, 'steps': 142147, 'loss/train': 0.4341326653957367} 08/31/2021 15:01:59 - INFO - __main__ - Step 142149: {'lr': 3.4645056514070183e-06, 'samples': 27292608, 'steps': 142148, 'loss/train': 0.15510131418704987} 08/31/2021 15:01:59 - INFO - __main__ - Step 142150: {'lr': 3.4636252990232487e-06, 'samples': 27292800, 'steps': 142149, 'loss/train': 1.0275100469589233} 08/31/2021 15:02:00 - INFO - __main__ - Step 142151: {'lr': 3.4627450577249808e-06, 'samples': 27292992, 'steps': 142150, 'loss/train': 1.2275424003601074} 08/31/2021 15:02:00 - INFO - __main__ - Step 142152: {'lr': 3.4618649275126034e-06, 'samples': 27293184, 'steps': 142151, 'loss/train': 1.6278213262557983} 08/31/2021 15:02:01 - INFO - __main__ - Step 142153: {'lr': 3.4609849083864777e-06, 'samples': 27293376, 'steps': 142152, 'loss/train': 0.8925881385803223} 08/31/2021 15:02:02 - INFO - __main__ - Step 142154: {'lr': 3.460105000347047e-06, 'samples': 27293568, 'steps': 142153, 'loss/train': 0.8473449945449829} 08/31/2021 15:02:02 - INFO - __main__ - Step 142155: {'lr': 3.4592252033947003e-06, 'samples': 27293760, 'steps': 142154, 'loss/train': 0.8217732310295105} 08/31/2021 15:02:03 - INFO - __main__ - Step 142156: {'lr': 3.458345517529826e-06, 'samples': 27293952, 'steps': 142155, 'loss/train': 0.7240082621574402} 08/31/2021 15:02:03 - INFO - __main__ - Step 142157: {'lr': 3.457465942752813e-06, 'samples': 27294144, 'steps': 142156, 'loss/train': 1.2743504047393799} 08/31/2021 15:02:05 - INFO - __main__ - Step 142158: {'lr': 3.45658647906405e-06, 'samples': 27294336, 'steps': 142157, 'loss/train': 0.9786372780799866} 08/31/2021 15:02:05 - INFO - __main__ - Step 142159: {'lr': 3.455707126463925e-06, 'samples': 27294528, 'steps': 142158, 'loss/train': 1.0452840328216553} 08/31/2021 15:02:06 - INFO - __main__ - Step 142160: {'lr': 3.4548278849528823e-06, 'samples': 27294720, 'steps': 142159, 'loss/train': 1.5411691665649414} 08/31/2021 15:02:06 - INFO - __main__ - Step 142161: {'lr': 3.453948754531283e-06, 'samples': 27294912, 'steps': 142160, 'loss/train': 0.8886067271232605} 08/31/2021 15:02:07 - INFO - __main__ - Step 142162: {'lr': 3.453069735199543e-06, 'samples': 27295104, 'steps': 142161, 'loss/train': 1.0802539587020874} 08/31/2021 15:02:08 - INFO - __main__ - Step 142163: {'lr': 3.4521908269580236e-06, 'samples': 27295296, 'steps': 142162, 'loss/train': 1.139526605606079} 08/31/2021 15:02:08 - INFO - __main__ - Step 142164: {'lr': 3.451312029807141e-06, 'samples': 27295488, 'steps': 142163, 'loss/train': 0.777332603931427} 08/31/2021 15:02:09 - INFO - __main__ - Step 142165: {'lr': 3.4504333437473113e-06, 'samples': 27295680, 'steps': 142164, 'loss/train': 0.11428218334913254} 08/31/2021 15:02:09 - INFO - __main__ - Step 142166: {'lr': 3.4495547687788953e-06, 'samples': 27295872, 'steps': 142165, 'loss/train': 1.5481735467910767} 08/31/2021 15:02:10 - INFO - __main__ - Step 142167: {'lr': 3.4486763049023096e-06, 'samples': 27296064, 'steps': 142166, 'loss/train': 0.8218513131141663} 08/31/2021 15:02:11 - INFO - __main__ - Step 142168: {'lr': 3.4477979521179426e-06, 'samples': 27296256, 'steps': 142167, 'loss/train': 1.3708256483078003} 08/31/2021 15:02:11 - INFO - __main__ - Step 142169: {'lr': 3.4469197104262106e-06, 'samples': 27296448, 'steps': 142168, 'loss/train': 1.0595570802688599} 08/31/2021 15:02:12 - INFO - __main__ - Step 142170: {'lr': 3.4460415798275023e-06, 'samples': 27296640, 'steps': 142169, 'loss/train': 0.7349686622619629} 08/31/2021 15:02:12 - INFO - __main__ - Step 142171: {'lr': 3.4451635603221787e-06, 'samples': 27296832, 'steps': 142170, 'loss/train': 0.6180616617202759} 08/31/2021 15:02:12 - INFO - __main__ - Step 142172: {'lr': 3.4442856519106556e-06, 'samples': 27297024, 'steps': 142171, 'loss/train': 2.8820137977600098} 08/31/2021 15:02:13 - INFO - __main__ - Step 142173: {'lr': 3.4434078545933502e-06, 'samples': 27297216, 'steps': 142172, 'loss/train': 0.5869908928871155} 08/31/2021 15:02:14 - INFO - __main__ - Step 142174: {'lr': 3.4425301683706225e-06, 'samples': 27297408, 'steps': 142173, 'loss/train': 0.6330884099006653} 08/31/2021 15:02:15 - INFO - __main__ - Step 142175: {'lr': 3.4416525932428887e-06, 'samples': 27297600, 'steps': 142174, 'loss/train': 1.1000882387161255} 08/31/2021 15:02:15 - INFO - __main__ - Step 142176: {'lr': 3.440775129210538e-06, 'samples': 27297792, 'steps': 142175, 'loss/train': 1.1587454080581665} 08/31/2021 15:02:15 - INFO - __main__ - Step 142177: {'lr': 3.439897776273987e-06, 'samples': 27297984, 'steps': 142176, 'loss/train': 0.7957360744476318} 08/31/2021 15:02:16 - INFO - __main__ - Step 142178: {'lr': 3.4390205344335955e-06, 'samples': 27298176, 'steps': 142177, 'loss/train': 0.522478461265564} 08/31/2021 15:02:17 - INFO - __main__ - Step 142179: {'lr': 3.4381434036897806e-06, 'samples': 27298368, 'steps': 142178, 'loss/train': 3.04154634475708} 08/31/2021 15:02:18 - INFO - __main__ - Step 142180: {'lr': 3.4372663840429587e-06, 'samples': 27298560, 'steps': 142179, 'loss/train': 0.6533383727073669} 08/31/2021 15:02:18 - INFO - __main__ - Step 142181: {'lr': 3.436389475493462e-06, 'samples': 27298752, 'steps': 142180, 'loss/train': 0.8212841153144836} 08/31/2021 15:02:19 - INFO - __main__ - Step 142182: {'lr': 3.4355126780417634e-06, 'samples': 27298944, 'steps': 142181, 'loss/train': 1.274457573890686} 08/31/2021 15:02:19 - INFO - __main__ - Step 142183: {'lr': 3.434635991688195e-06, 'samples': 27299136, 'steps': 142182, 'loss/train': 1.5631152391433716} 08/31/2021 15:02:20 - INFO - __main__ - Step 142184: {'lr': 3.433759416433174e-06, 'samples': 27299328, 'steps': 142183, 'loss/train': 1.2755497694015503} 08/31/2021 15:02:21 - INFO - __main__ - Step 142185: {'lr': 3.4328829522771168e-06, 'samples': 27299520, 'steps': 142184, 'loss/train': 0.14878134429454803} 08/31/2021 15:02:21 - INFO - __main__ - Step 142186: {'lr': 3.4320065992203554e-06, 'samples': 27299712, 'steps': 142185, 'loss/train': 1.5554029941558838} 08/31/2021 15:02:22 - INFO - __main__ - Step 142187: {'lr': 3.4311303572633624e-06, 'samples': 27299904, 'steps': 142186, 'loss/train': 0.9330010414123535} 08/31/2021 15:02:22 - INFO - __main__ - Step 142188: {'lr': 3.4302542264064985e-06, 'samples': 27300096, 'steps': 142187, 'loss/train': 0.8468676805496216} 08/31/2021 15:02:23 - INFO - __main__ - Step 142189: {'lr': 3.4293782066501245e-06, 'samples': 27300288, 'steps': 142188, 'loss/train': 1.3390249013900757} 08/31/2021 15:02:24 - INFO - __main__ - Step 142190: {'lr': 3.4285022979946844e-06, 'samples': 27300480, 'steps': 142189, 'loss/train': 0.9769401550292969} 08/31/2021 15:02:24 - INFO - __main__ - Step 142191: {'lr': 3.4276265004405673e-06, 'samples': 27300672, 'steps': 142190, 'loss/train': 1.0613071918487549} 08/31/2021 15:02:25 - INFO - __main__ - Step 142192: {'lr': 3.426750813988161e-06, 'samples': 27300864, 'steps': 142191, 'loss/train': 0.694545567035675} 08/31/2021 15:02:25 - INFO - __main__ - Step 142193: {'lr': 3.4258752386378267e-06, 'samples': 27301056, 'steps': 142192, 'loss/train': 0.6184166073799133} 08/31/2021 15:02:26 - INFO - __main__ - Step 142194: {'lr': 3.4249997743900083e-06, 'samples': 27301248, 'steps': 142193, 'loss/train': 1.007494330406189} 08/31/2021 15:02:27 - INFO - __main__ - Step 142195: {'lr': 3.424124421245095e-06, 'samples': 27301440, 'steps': 142194, 'loss/train': 1.4113086462020874} 08/31/2021 15:02:27 - INFO - __main__ - Step 142196: {'lr': 3.423249179203447e-06, 'samples': 27301632, 'steps': 142195, 'loss/train': 1.2771631479263306} 08/31/2021 15:02:28 - INFO - __main__ - Step 142197: {'lr': 3.422374048265481e-06, 'samples': 27301824, 'steps': 142196, 'loss/train': 1.089310646057129} 08/31/2021 15:02:28 - INFO - __main__ - Step 142198: {'lr': 3.421499028431585e-06, 'samples': 27302016, 'steps': 142197, 'loss/train': 0.9181151986122131} 08/31/2021 15:02:29 - INFO - __main__ - Step 142199: {'lr': 3.4206241197021758e-06, 'samples': 27302208, 'steps': 142198, 'loss/train': 0.626806378364563} 08/31/2021 15:02:30 - INFO - __main__ - Step 142200: {'lr': 3.4197493220775866e-06, 'samples': 27302400, 'steps': 142199, 'loss/train': 1.0159592628479004} 08/31/2021 15:02:30 - INFO - __main__ - Step 142201: {'lr': 3.4188746355582887e-06, 'samples': 27302592, 'steps': 142200, 'loss/train': 0.8952920436859131} 08/31/2021 15:02:31 - INFO - __main__ - Step 142202: {'lr': 3.4180000601446435e-06, 'samples': 27302784, 'steps': 142201, 'loss/train': 1.4020497798919678} 08/31/2021 15:02:31 - INFO - __main__ - Step 142203: {'lr': 3.4171255958370118e-06, 'samples': 27302976, 'steps': 142202, 'loss/train': 1.121180534362793} 08/31/2021 15:02:31 - INFO - __main__ - Step 142204: {'lr': 3.4162512426358373e-06, 'samples': 27303168, 'steps': 142203, 'loss/train': 0.5806765556335449} 08/31/2021 15:02:33 - INFO - __main__ - Step 142205: {'lr': 3.4153770005415085e-06, 'samples': 27303360, 'steps': 142204, 'loss/train': 0.992276132106781} 08/31/2021 15:02:34 - INFO - __main__ - Step 142206: {'lr': 3.4145028695543867e-06, 'samples': 27303552, 'steps': 142205, 'loss/train': 1.91611909866333} 08/31/2021 15:02:34 - INFO - __main__ - Step 142207: {'lr': 3.413628849674888e-06, 'samples': 27303744, 'steps': 142206, 'loss/train': 0.35328832268714905} 08/31/2021 15:02:34 - INFO - __main__ - Step 142208: {'lr': 3.412754940903401e-06, 'samples': 27303936, 'steps': 142207, 'loss/train': 1.0210442543029785} 08/31/2021 15:02:35 - INFO - __main__ - Step 142209: {'lr': 3.411881143240314e-06, 'samples': 27304128, 'steps': 142208, 'loss/train': 1.0425292253494263} 08/31/2021 15:02:35 - INFO - __main__ - Step 142210: {'lr': 3.4110074566860717e-06, 'samples': 27304320, 'steps': 142209, 'loss/train': 0.015892988070845604} 08/31/2021 15:02:37 - INFO - __main__ - Step 142211: {'lr': 3.410133881240979e-06, 'samples': 27304512, 'steps': 142210, 'loss/train': 1.3899505138397217} 08/31/2021 15:02:37 - INFO - __main__ - Step 142212: {'lr': 3.4092604169054796e-06, 'samples': 27304704, 'steps': 142211, 'loss/train': 1.2675014734268188} 08/31/2021 15:02:38 - INFO - __main__ - Step 142213: {'lr': 3.408387063679991e-06, 'samples': 27304896, 'steps': 142212, 'loss/train': 1.1265822649002075} 08/31/2021 15:02:38 - INFO - __main__ - Step 142214: {'lr': 3.407513821564845e-06, 'samples': 27305088, 'steps': 142213, 'loss/train': 0.626216471195221} 08/31/2021 15:02:39 - INFO - __main__ - Step 142215: {'lr': 3.4066406905604865e-06, 'samples': 27305280, 'steps': 142214, 'loss/train': 0.7674286365509033} 08/31/2021 15:02:40 - INFO - __main__ - Step 142216: {'lr': 3.405767670667276e-06, 'samples': 27305472, 'steps': 142215, 'loss/train': 0.9127048850059509} 08/31/2021 15:02:41 - INFO - __main__ - Step 142217: {'lr': 3.4048947618856294e-06, 'samples': 27305664, 'steps': 142216, 'loss/train': 1.0297882556915283} 08/31/2021 15:02:41 - INFO - __main__ - Step 142218: {'lr': 3.4040219642159366e-06, 'samples': 27305856, 'steps': 142217, 'loss/train': 1.3056046962738037} 08/31/2021 15:02:41 - INFO - __main__ - Step 142219: {'lr': 3.4031492776585846e-06, 'samples': 27306048, 'steps': 142218, 'loss/train': 0.8804499506950378} 08/31/2021 15:02:42 - INFO - __main__ - Step 142220: {'lr': 3.4022767022139635e-06, 'samples': 27306240, 'steps': 142219, 'loss/train': 0.7118746042251587} 08/31/2021 15:02:43 - INFO - __main__ - Step 142221: {'lr': 3.4014042378824607e-06, 'samples': 27306432, 'steps': 142220, 'loss/train': 1.396620750427246} 08/31/2021 15:02:44 - INFO - __main__ - Step 142222: {'lr': 3.4005318846644926e-06, 'samples': 27306624, 'steps': 142221, 'loss/train': 1.3101084232330322} 08/31/2021 15:02:44 - INFO - __main__ - Step 142223: {'lr': 3.399659642560449e-06, 'samples': 27306816, 'steps': 142222, 'loss/train': 1.414753794670105} 08/31/2021 15:02:45 - INFO - __main__ - Step 142224: {'lr': 3.398787511570717e-06, 'samples': 27307008, 'steps': 142223, 'loss/train': 1.1672834157943726} 08/31/2021 15:02:45 - INFO - __main__ - Step 142225: {'lr': 3.3979154916956856e-06, 'samples': 27307200, 'steps': 142224, 'loss/train': 0.21361477673053741} 08/31/2021 15:02:47 - INFO - __main__ - Step 142226: {'lr': 3.397043582935716e-06, 'samples': 27307392, 'steps': 142225, 'loss/train': 1.6219394207000732} 08/31/2021 15:02:47 - INFO - __main__ - Step 142227: {'lr': 3.396171785291252e-06, 'samples': 27307584, 'steps': 142226, 'loss/train': 1.164405345916748} 08/31/2021 15:02:47 - INFO - __main__ - Step 142228: {'lr': 3.3953000987626825e-06, 'samples': 27307776, 'steps': 142227, 'loss/train': 1.5311886072158813} 08/31/2021 15:02:48 - INFO - __main__ - Step 142229: {'lr': 3.394428523350368e-06, 'samples': 27307968, 'steps': 142228, 'loss/train': 0.38624441623687744} 08/31/2021 15:02:48 - INFO - __main__ - Step 142230: {'lr': 3.393557059054725e-06, 'samples': 27308160, 'steps': 142229, 'loss/train': 1.2204267978668213} 08/31/2021 15:02:50 - INFO - __main__ - Step 142231: {'lr': 3.392685705876142e-06, 'samples': 27308352, 'steps': 142230, 'loss/train': 1.304555892944336} 08/31/2021 15:02:50 - INFO - __main__ - Step 142232: {'lr': 3.3918144638150074e-06, 'samples': 27308544, 'steps': 142231, 'loss/train': 2.184022903442383} 08/31/2021 15:02:51 - INFO - __main__ - Step 142233: {'lr': 3.39094333287171e-06, 'samples': 27308736, 'steps': 142232, 'loss/train': 0.7016934752464294} 08/31/2021 15:02:51 - INFO - __main__ - Step 142234: {'lr': 3.3900723130466383e-06, 'samples': 27308928, 'steps': 142233, 'loss/train': 1.0295438766479492} 08/31/2021 15:02:51 - INFO - __main__ - Step 142235: {'lr': 3.3892014043402088e-06, 'samples': 27309120, 'steps': 142234, 'loss/train': 1.1673945188522339} 08/31/2021 15:02:52 - INFO - __main__ - Step 142236: {'lr': 3.3883306067528095e-06, 'samples': 27309312, 'steps': 142235, 'loss/train': 0.04172379523515701} 08/31/2021 15:02:53 - INFO - __main__ - Step 142237: {'lr': 3.38745992028483e-06, 'samples': 27309504, 'steps': 142236, 'loss/train': 1.1907354593276978} 08/31/2021 15:02:53 - INFO - __main__ - Step 142238: {'lr': 3.38658934493663e-06, 'samples': 27309696, 'steps': 142237, 'loss/train': 0.9402623176574707} 08/31/2021 15:02:54 - INFO - __main__ - Step 142239: {'lr': 3.385718880708627e-06, 'samples': 27309888, 'steps': 142238, 'loss/train': 1.1774775981903076} 08/31/2021 15:02:54 - INFO - __main__ - Step 142240: {'lr': 3.3848485276012364e-06, 'samples': 27310080, 'steps': 142239, 'loss/train': 0.5124437212944031} 08/31/2021 15:02:55 - INFO - __main__ - Step 142241: {'lr': 3.3839782856147918e-06, 'samples': 27310272, 'steps': 142240, 'loss/train': 1.031616449356079} 08/31/2021 15:02:56 - INFO - __main__ - Step 142242: {'lr': 3.383108154749737e-06, 'samples': 27310464, 'steps': 142241, 'loss/train': 1.0957591533660889} 08/31/2021 15:02:57 - INFO - __main__ - Step 142243: {'lr': 3.3822381350064603e-06, 'samples': 27310656, 'steps': 142242, 'loss/train': 1.313118815422058} 08/31/2021 15:02:57 - INFO - __main__ - Step 142244: {'lr': 3.3813682263853505e-06, 'samples': 27310848, 'steps': 142243, 'loss/train': 0.44730469584465027} 08/31/2021 15:02:57 - INFO - __main__ - Step 142245: {'lr': 3.3804984288867693e-06, 'samples': 27311040, 'steps': 142244, 'loss/train': 1.0828648805618286} 08/31/2021 15:02:58 - INFO - __main__ - Step 142246: {'lr': 3.3796287425111315e-06, 'samples': 27311232, 'steps': 142245, 'loss/train': 0.8417864441871643} 08/31/2021 15:02:59 - INFO - __main__ - Step 142247: {'lr': 3.378759167258827e-06, 'samples': 27311424, 'steps': 142246, 'loss/train': 0.7333716154098511} 08/31/2021 15:03:00 - INFO - __main__ - Step 142248: {'lr': 3.3778897031302435e-06, 'samples': 27311616, 'steps': 142247, 'loss/train': 1.3783800601959229} 08/31/2021 15:03:00 - INFO - __main__ - Step 142249: {'lr': 3.377020350125798e-06, 'samples': 27311808, 'steps': 142248, 'loss/train': 0.7352034449577332} 08/31/2021 15:03:01 - INFO - __main__ - Step 142250: {'lr': 3.3761511082458505e-06, 'samples': 27312000, 'steps': 142249, 'loss/train': 0.9417978525161743} 08/31/2021 15:03:01 - INFO - __main__ - Step 142251: {'lr': 3.375281977490818e-06, 'samples': 27312192, 'steps': 142250, 'loss/train': 1.7285382747650146} 08/31/2021 15:03:02 - INFO - __main__ - Step 142252: {'lr': 3.3744129578610616e-06, 'samples': 27312384, 'steps': 142251, 'loss/train': 1.2738893032073975} 08/31/2021 15:03:03 - INFO - __main__ - Step 142253: {'lr': 3.373544049356997e-06, 'samples': 27312576, 'steps': 142252, 'loss/train': 1.2565611600875854} 08/31/2021 15:03:03 - INFO - __main__ - Step 142254: {'lr': 3.372675251978985e-06, 'samples': 27312768, 'steps': 142253, 'loss/train': 2.911644220352173} 08/31/2021 15:03:04 - INFO - __main__ - Step 142255: {'lr': 3.37180656572747e-06, 'samples': 27312960, 'steps': 142254, 'loss/train': 0.44187018275260925} 08/31/2021 15:03:04 - INFO - __main__ - Step 142256: {'lr': 3.370937990602785e-06, 'samples': 27313152, 'steps': 142255, 'loss/train': 1.4081043004989624} 08/31/2021 15:03:06 - INFO - __main__ - Step 142257: {'lr': 3.370069526605374e-06, 'samples': 27313344, 'steps': 142256, 'loss/train': 1.4626058340072632} 08/31/2021 15:03:06 - INFO - __main__ - Step 142258: {'lr': 3.36920117373557e-06, 'samples': 27313536, 'steps': 142257, 'loss/train': 1.3445298671722412} 08/31/2021 15:03:07 - INFO - __main__ - Step 142259: {'lr': 3.368332931993845e-06, 'samples': 27313728, 'steps': 142258, 'loss/train': 1.0463701486587524} 08/31/2021 15:03:07 - INFO - __main__ - Step 142260: {'lr': 3.367464801380504e-06, 'samples': 27313920, 'steps': 142259, 'loss/train': 1.0286935567855835} 08/31/2021 15:03:07 - INFO - __main__ - Step 142261: {'lr': 3.366596781895992e-06, 'samples': 27314112, 'steps': 142260, 'loss/train': 0.0653514564037323} 08/31/2021 15:03:08 - INFO - __main__ - Step 142262: {'lr': 3.3657288735406965e-06, 'samples': 27314304, 'steps': 142261, 'loss/train': 1.3935343027114868} 08/31/2021 15:03:09 - INFO - __main__ - Step 142263: {'lr': 3.364861076314979e-06, 'samples': 27314496, 'steps': 142262, 'loss/train': 0.9913122653961182} 08/31/2021 15:03:10 - INFO - __main__ - Step 142264: {'lr': 3.363993390219283e-06, 'samples': 27314688, 'steps': 142263, 'loss/train': 0.675847589969635} 08/31/2021 15:03:10 - INFO - __main__ - Step 142265: {'lr': 3.3631258152539424e-06, 'samples': 27314880, 'steps': 142264, 'loss/train': 2.05964994430542} 08/31/2021 15:03:10 - INFO - __main__ - Step 142266: {'lr': 3.3622583514193726e-06, 'samples': 27315072, 'steps': 142265, 'loss/train': 1.2535609006881714} 08/31/2021 15:03:11 - INFO - __main__ - Step 142267: {'lr': 3.361390998715963e-06, 'samples': 27315264, 'steps': 142266, 'loss/train': 0.5570970177650452} 08/31/2021 15:03:13 - INFO - __main__ - Step 142268: {'lr': 3.360523757144102e-06, 'samples': 27315456, 'steps': 142267, 'loss/train': 1.1747404336929321} 08/31/2021 15:03:13 - INFO - __main__ - Step 142269: {'lr': 3.3596566267041772e-06, 'samples': 27315648, 'steps': 142268, 'loss/train': 0.6920332908630371} 08/31/2021 15:03:14 - INFO - __main__ - Step 142270: {'lr': 3.3587896073965783e-06, 'samples': 27315840, 'steps': 142269, 'loss/train': 0.12039225548505783} 08/31/2021 15:03:14 - INFO - __main__ - Step 142271: {'lr': 3.3579226992217214e-06, 'samples': 27316032, 'steps': 142270, 'loss/train': 0.6831345558166504} 08/31/2021 15:03:14 - INFO - __main__ - Step 142272: {'lr': 3.3570559021799673e-06, 'samples': 27316224, 'steps': 142271, 'loss/train': 1.2459533214569092} 08/31/2021 15:03:16 - INFO - __main__ - Step 142273: {'lr': 3.3561892162717324e-06, 'samples': 27316416, 'steps': 142272, 'loss/train': 0.9347904920578003} 08/31/2021 15:03:16 - INFO - __main__ - Step 142274: {'lr': 3.355322641497377e-06, 'samples': 27316608, 'steps': 142273, 'loss/train': 0.7760587930679321} 08/31/2021 15:03:17 - INFO - __main__ - Step 142275: {'lr': 3.354456177857318e-06, 'samples': 27316800, 'steps': 142274, 'loss/train': 0.8335232734680176} 08/31/2021 15:03:17 - INFO - __main__ - Step 142276: {'lr': 3.3535898253519437e-06, 'samples': 27316992, 'steps': 142275, 'loss/train': 0.8337229490280151} 08/31/2021 15:03:17 - INFO - __main__ - Step 142277: {'lr': 3.3527235839816428e-06, 'samples': 27317184, 'steps': 142276, 'loss/train': 1.2474135160446167} 08/31/2021 15:03:19 - INFO - __main__ - Step 142278: {'lr': 3.351857453746776e-06, 'samples': 27317376, 'steps': 142277, 'loss/train': 1.1838759183883667} 08/31/2021 15:03:19 - INFO - __main__ - Step 142279: {'lr': 3.35099143464776e-06, 'samples': 27317568, 'steps': 142278, 'loss/train': 0.15069027245044708} 08/31/2021 15:03:20 - INFO - __main__ - Step 142280: {'lr': 3.350125526684983e-06, 'samples': 27317760, 'steps': 142279, 'loss/train': 0.05803284794092178} 08/31/2021 15:03:20 - INFO - __main__ - Step 142281: {'lr': 3.3492597298588336e-06, 'samples': 27317952, 'steps': 142280, 'loss/train': 1.0135284662246704} 08/31/2021 15:03:20 - INFO - __main__ - Step 142282: {'lr': 3.3483940441697e-06, 'samples': 27318144, 'steps': 142281, 'loss/train': 0.14594799280166626} 08/31/2021 15:03:21 - INFO - __main__ - Step 142283: {'lr': 3.347528469617972e-06, 'samples': 27318336, 'steps': 142282, 'loss/train': 1.2109202146530151} 08/31/2021 15:03:22 - INFO - __main__ - Step 142284: {'lr': 3.346663006204037e-06, 'samples': 27318528, 'steps': 142283, 'loss/train': 0.49717918038368225} 08/31/2021 15:03:23 - INFO - __main__ - Step 142285: {'lr': 3.3457976539282842e-06, 'samples': 27318720, 'steps': 142284, 'loss/train': 0.8577773571014404} 08/31/2021 15:03:23 - INFO - __main__ - Step 142286: {'lr': 3.3449324127911294e-06, 'samples': 27318912, 'steps': 142285, 'loss/train': 1.4018174409866333} 08/31/2021 15:03:24 - INFO - __main__ - Step 142287: {'lr': 3.3440672827929342e-06, 'samples': 27319104, 'steps': 142286, 'loss/train': 0.8985536694526672} 08/31/2021 15:03:24 - INFO - __main__ - Step 142288: {'lr': 3.3432022639340866e-06, 'samples': 27319296, 'steps': 142287, 'loss/train': 0.9773856997489929} 08/31/2021 15:03:25 - INFO - __main__ - Step 142289: {'lr': 3.342337356215003e-06, 'samples': 27319488, 'steps': 142288, 'loss/train': 1.7765183448791504} 08/31/2021 15:03:26 - INFO - __main__ - Step 142290: {'lr': 3.341472559636044e-06, 'samples': 27319680, 'steps': 142289, 'loss/train': 0.9834728837013245} 08/31/2021 15:03:26 - INFO - __main__ - Step 142291: {'lr': 3.3406078741976266e-06, 'samples': 27319872, 'steps': 142290, 'loss/train': 0.4715215861797333} 08/31/2021 15:03:27 - INFO - __main__ - Step 142292: {'lr': 3.339743299900111e-06, 'samples': 27320064, 'steps': 142291, 'loss/train': 0.5703223347663879} 08/31/2021 15:03:27 - INFO - __main__ - Step 142293: {'lr': 3.3388788367439137e-06, 'samples': 27320256, 'steps': 142292, 'loss/train': 1.6765484809875488} 08/31/2021 15:03:29 - INFO - __main__ - Step 142294: {'lr': 3.338014484729396e-06, 'samples': 27320448, 'steps': 142293, 'loss/train': 1.0909825563430786} 08/31/2021 15:03:29 - INFO - __main__ - Step 142295: {'lr': 3.3371502438569733e-06, 'samples': 27320640, 'steps': 142294, 'loss/train': 0.7874840497970581} 08/31/2021 15:03:29 - INFO - __main__ - Step 142296: {'lr': 3.3362861141270075e-06, 'samples': 27320832, 'steps': 142295, 'loss/train': 0.11605468392372131} 08/31/2021 15:03:30 - INFO - __main__ - Step 142297: {'lr': 3.335422095539914e-06, 'samples': 27321024, 'steps': 142296, 'loss/train': 1.3462623357772827} 08/31/2021 15:03:30 - INFO - __main__ - Step 142298: {'lr': 3.3345581880960817e-06, 'samples': 27321216, 'steps': 142297, 'loss/train': 1.5649369955062866} 08/31/2021 15:03:32 - INFO - __main__ - Step 142299: {'lr': 3.3336943917958718e-06, 'samples': 27321408, 'steps': 142298, 'loss/train': 1.05557119846344} 08/31/2021 15:03:33 - INFO - __main__ - Step 142300: {'lr': 3.332830706639728e-06, 'samples': 27321600, 'steps': 142299, 'loss/train': 1.2415980100631714} 08/31/2021 15:03:33 - INFO - __main__ - Step 142301: {'lr': 3.3319671326279833e-06, 'samples': 27321792, 'steps': 142300, 'loss/train': 0.48147132992744446} 08/31/2021 15:03:33 - INFO - __main__ - Step 142302: {'lr': 3.3311036697610263e-06, 'samples': 27321984, 'steps': 142301, 'loss/train': 0.7325283288955688} 08/31/2021 15:03:34 - INFO - __main__ - Step 142303: {'lr': 3.3302403180393013e-06, 'samples': 27322176, 'steps': 142302, 'loss/train': 0.10554416477680206} 08/31/2021 15:03:35 - INFO - __main__ - Step 142304: {'lr': 3.3293770774631695e-06, 'samples': 27322368, 'steps': 142303, 'loss/train': 0.13232699036598206} 08/31/2021 15:03:36 - INFO - __main__ - Step 142305: {'lr': 3.328513948032991e-06, 'samples': 27322560, 'steps': 142304, 'loss/train': 1.2380778789520264} 08/31/2021 15:03:36 - INFO - __main__ - Step 142306: {'lr': 3.327650929749182e-06, 'samples': 27322752, 'steps': 142305, 'loss/train': 1.1650745868682861} 08/31/2021 15:03:36 - INFO - __main__ - Step 142307: {'lr': 3.3267880226121317e-06, 'samples': 27322944, 'steps': 142306, 'loss/train': 1.2628068923950195} 08/31/2021 15:03:37 - INFO - __main__ - Step 142308: {'lr': 3.3259252266222008e-06, 'samples': 27323136, 'steps': 142307, 'loss/train': 1.5649269819259644} 08/31/2021 15:03:38 - INFO - __main__ - Step 142309: {'lr': 3.325062541779833e-06, 'samples': 27323328, 'steps': 142308, 'loss/train': 1.336419939994812} 08/31/2021 15:03:39 - INFO - __main__ - Step 142310: {'lr': 3.324199968085362e-06, 'samples': 27323520, 'steps': 142309, 'loss/train': 1.2144020795822144} 08/31/2021 15:03:39 - INFO - __main__ - Step 142311: {'lr': 3.3233375055392313e-06, 'samples': 27323712, 'steps': 142310, 'loss/train': 1.4143425226211548} 08/31/2021 15:03:39 - INFO - __main__ - Step 142312: {'lr': 3.322475154141774e-06, 'samples': 27323904, 'steps': 142311, 'loss/train': 1.5767961740493774} 08/31/2021 15:03:40 - INFO - __main__ - Step 142313: {'lr': 3.321612913893407e-06, 'samples': 27324096, 'steps': 142312, 'loss/train': 1.415351390838623} 08/31/2021 15:03:40 - INFO - __main__ - Step 142314: {'lr': 3.3207507847945184e-06, 'samples': 27324288, 'steps': 142313, 'loss/train': 1.0489143133163452} 08/31/2021 15:03:42 - INFO - __main__ - Step 142315: {'lr': 3.319888766845469e-06, 'samples': 27324480, 'steps': 142314, 'loss/train': 1.196025013923645} 08/31/2021 15:03:42 - INFO - __main__ - Step 142316: {'lr': 3.319026860046703e-06, 'samples': 27324672, 'steps': 142315, 'loss/train': 0.8747081160545349} 08/31/2021 15:03:42 - INFO - __main__ - Step 142317: {'lr': 3.3181650643985537e-06, 'samples': 27324864, 'steps': 142316, 'loss/train': 0.9911971092224121} 08/31/2021 15:03:43 - INFO - __main__ - Step 142318: {'lr': 3.317303379901465e-06, 'samples': 27325056, 'steps': 142317, 'loss/train': 1.0691380500793457} 08/31/2021 15:03:43 - INFO - __main__ - Step 142319: {'lr': 3.31644180655577e-06, 'samples': 27325248, 'steps': 142318, 'loss/train': 0.7666994333267212} 08/31/2021 15:03:45 - INFO - __main__ - Step 142320: {'lr': 3.315580344361885e-06, 'samples': 27325440, 'steps': 142319, 'loss/train': 0.7932676076889038} 08/31/2021 15:03:45 - INFO - __main__ - Step 142321: {'lr': 3.3147189933201983e-06, 'samples': 27325632, 'steps': 142320, 'loss/train': 0.49238038063049316} 08/31/2021 15:03:46 - INFO - __main__ - Step 142322: {'lr': 3.313857753431071e-06, 'samples': 27325824, 'steps': 142321, 'loss/train': 0.8878105878829956} 08/31/2021 15:03:46 - INFO - __main__ - Step 142323: {'lr': 3.3129966246949193e-06, 'samples': 27326016, 'steps': 142322, 'loss/train': 1.3473916053771973} 08/31/2021 15:03:47 - INFO - __main__ - Step 142324: {'lr': 3.312135607112132e-06, 'samples': 27326208, 'steps': 142323, 'loss/train': 1.6006696224212646} 08/31/2021 15:03:48 - INFO - __main__ - Step 142325: {'lr': 3.311274700683098e-06, 'samples': 27326400, 'steps': 142324, 'loss/train': 0.9967631101608276} 08/31/2021 15:03:49 - INFO - __main__ - Step 142326: {'lr': 3.310413905408177e-06, 'samples': 27326592, 'steps': 142325, 'loss/train': 0.6987581253051758} 08/31/2021 15:03:49 - INFO - __main__ - Step 142327: {'lr': 3.3095532212877867e-06, 'samples': 27326784, 'steps': 142326, 'loss/train': 0.8589221239089966} 08/31/2021 15:03:49 - INFO - __main__ - Step 142328: {'lr': 3.3086926483223144e-06, 'samples': 27326976, 'steps': 142327, 'loss/train': 0.7886434197425842} 08/31/2021 15:03:50 - INFO - __main__ - Step 142329: {'lr': 3.307832186512122e-06, 'samples': 27327168, 'steps': 142328, 'loss/train': 1.1677005290985107} 08/31/2021 15:03:50 - INFO - __main__ - Step 142330: {'lr': 3.306971835857625e-06, 'samples': 27327360, 'steps': 142329, 'loss/train': 1.8663246631622314} 08/31/2021 15:03:52 - INFO - __main__ - Step 142331: {'lr': 3.3061115963592124e-06, 'samples': 27327552, 'steps': 142330, 'loss/train': 1.0522053241729736} 08/31/2021 15:03:53 - INFO - __main__ - Step 142332: {'lr': 3.3052514680172452e-06, 'samples': 27327744, 'steps': 142331, 'loss/train': 1.0955172777175903} 08/31/2021 15:03:53 - INFO - __main__ - Step 142333: {'lr': 3.3043914508321393e-06, 'samples': 27327936, 'steps': 142332, 'loss/train': 0.8391308188438416} 08/31/2021 15:03:53 - INFO - __main__ - Step 142334: {'lr': 3.303531544804256e-06, 'samples': 27328128, 'steps': 142333, 'loss/train': 1.112305998802185} 08/31/2021 15:03:54 - INFO - __main__ - Step 142335: {'lr': 3.302671749933983e-06, 'samples': 27328320, 'steps': 142334, 'loss/train': 1.040770411491394} 08/31/2021 15:03:54 - INFO - __main__ - Step 142336: {'lr': 3.301812066221738e-06, 'samples': 27328512, 'steps': 142335, 'loss/train': 0.7878981828689575} 08/31/2021 15:03:54 - INFO - __main__ - Step 142337: {'lr': 3.3009524936678526e-06, 'samples': 27328704, 'steps': 142336, 'loss/train': 0.01351124793291092} 08/31/2021 15:03:56 - INFO - __main__ - Step 142338: {'lr': 3.3000930322727998e-06, 'samples': 27328896, 'steps': 142337, 'loss/train': 0.1136450320482254} 08/31/2021 15:03:57 - INFO - __main__ - Step 142339: {'lr': 3.299233682036884e-06, 'samples': 27329088, 'steps': 142338, 'loss/train': 1.1581151485443115} 08/31/2021 15:03:57 - INFO - __main__ - Step 142340: {'lr': 3.29837444296055e-06, 'samples': 27329280, 'steps': 142339, 'loss/train': 1.49778151512146} 08/31/2021 15:03:57 - INFO - __main__ - Step 142341: {'lr': 3.297515315044131e-06, 'samples': 27329472, 'steps': 142340, 'loss/train': 0.08866672217845917} 08/31/2021 15:03:58 - INFO - __main__ - Step 142342: {'lr': 3.2966562982880977e-06, 'samples': 27329664, 'steps': 142341, 'loss/train': 0.7765032052993774} 08/31/2021 15:03:59 - INFO - __main__ - Step 142343: {'lr': 3.2957973926927287e-06, 'samples': 27329856, 'steps': 142342, 'loss/train': 1.5682700872421265} 08/31/2021 15:04:00 - INFO - __main__ - Step 142344: {'lr': 3.2949385982584954e-06, 'samples': 27330048, 'steps': 142343, 'loss/train': 1.0674721002578735} 08/31/2021 15:04:00 - INFO - __main__ - Step 142345: {'lr': 3.2940799149857593e-06, 'samples': 27330240, 'steps': 142344, 'loss/train': 0.783476710319519} 08/31/2021 15:04:00 - INFO - __main__ - Step 142346: {'lr': 3.29322134287488e-06, 'samples': 27330432, 'steps': 142345, 'loss/train': 1.2271778583526611} 08/31/2021 15:04:01 - INFO - __main__ - Step 142347: {'lr': 3.292362881926303e-06, 'samples': 27330624, 'steps': 142346, 'loss/train': 1.1711091995239258} 08/31/2021 15:04:02 - INFO - __main__ - Step 142348: {'lr': 3.2915045321403327e-06, 'samples': 27330816, 'steps': 142347, 'loss/train': 0.9248510599136353} 08/31/2021 15:04:03 - INFO - __main__ - Step 142349: {'lr': 3.290646293517441e-06, 'samples': 27331008, 'steps': 142348, 'loss/train': 0.605814516544342} 08/31/2021 15:04:03 - INFO - __main__ - Step 142350: {'lr': 3.289788166057961e-06, 'samples': 27331200, 'steps': 142349, 'loss/train': 1.188689947128296} 08/31/2021 15:04:03 - INFO - __main__ - Step 142351: {'lr': 3.2889301497623093e-06, 'samples': 27331392, 'steps': 142350, 'loss/train': 1.4569847583770752} 08/31/2021 15:04:04 - INFO - __main__ - Step 142352: {'lr': 3.2880722446308464e-06, 'samples': 27331584, 'steps': 142351, 'loss/train': 1.4958856105804443} 08/31/2021 15:04:05 - INFO - __main__ - Step 142353: {'lr': 3.287214450663989e-06, 'samples': 27331776, 'steps': 142352, 'loss/train': 1.2598451375961304} 08/31/2021 15:04:06 - INFO - __main__ - Step 142354: {'lr': 3.2863567678620974e-06, 'samples': 27331968, 'steps': 142353, 'loss/train': 2.099468469619751} 08/31/2021 15:04:06 - INFO - __main__ - Step 142355: {'lr': 3.285499196225561e-06, 'samples': 27332160, 'steps': 142354, 'loss/train': 1.4257961511611938} 08/31/2021 15:04:06 - INFO - __main__ - Step 142356: {'lr': 3.2846417357547675e-06, 'samples': 27332352, 'steps': 142355, 'loss/train': 0.5920061469078064} 08/31/2021 15:04:07 - INFO - __main__ - Step 142357: {'lr': 3.2837843864501062e-06, 'samples': 27332544, 'steps': 142356, 'loss/train': 1.3878984451293945} 08/31/2021 15:04:08 - INFO - __main__ - Step 142358: {'lr': 3.282927148311965e-06, 'samples': 27332736, 'steps': 142357, 'loss/train': 5.331491947174072} 08/31/2021 15:04:09 - INFO - __main__ - Step 142359: {'lr': 3.282070021340733e-06, 'samples': 27332928, 'steps': 142358, 'loss/train': 1.0575196743011475} 08/31/2021 15:04:09 - INFO - __main__ - Step 142360: {'lr': 3.2812130055367983e-06, 'samples': 27333120, 'steps': 142359, 'loss/train': 1.1091384887695312} 08/31/2021 15:04:09 - INFO - __main__ - Step 142361: {'lr': 3.28035610090055e-06, 'samples': 27333312, 'steps': 142360, 'loss/train': 0.46987244486808777} 08/31/2021 15:04:10 - INFO - __main__ - Step 142362: {'lr': 3.2794993074323487e-06, 'samples': 27333504, 'steps': 142361, 'loss/train': 2.013651132583618} 08/31/2021 15:04:10 - INFO - __main__ - Step 142363: {'lr': 3.278642625132583e-06, 'samples': 27333696, 'steps': 142362, 'loss/train': 0.7330825924873352} 08/31/2021 15:04:12 - INFO - __main__ - Step 142364: {'lr': 3.277786054001697e-06, 'samples': 27333888, 'steps': 142363, 'loss/train': 1.3322283029556274} 08/31/2021 15:04:12 - INFO - __main__ - Step 142365: {'lr': 3.2769295940400235e-06, 'samples': 27334080, 'steps': 142364, 'loss/train': 0.9658656716346741} 08/31/2021 15:04:13 - INFO - __main__ - Step 142366: {'lr': 3.2760732452479512e-06, 'samples': 27334272, 'steps': 142365, 'loss/train': 1.192859172821045} 08/31/2021 15:04:13 - INFO - __main__ - Step 142367: {'lr': 3.2752170076258413e-06, 'samples': 27334464, 'steps': 142366, 'loss/train': 0.463248074054718} 08/31/2021 15:04:13 - INFO - __main__ - Step 142368: {'lr': 3.2743608811741375e-06, 'samples': 27334656, 'steps': 142367, 'loss/train': 0.9947161674499512} 08/31/2021 15:04:15 - INFO - __main__ - Step 142369: {'lr': 3.273504865893201e-06, 'samples': 27334848, 'steps': 142368, 'loss/train': 1.501733422279358} 08/31/2021 15:04:15 - INFO - __main__ - Step 142370: {'lr': 3.2726489617834198e-06, 'samples': 27335040, 'steps': 142369, 'loss/train': 0.9951863288879395} 08/31/2021 15:04:16 - INFO - __main__ - Step 142371: {'lr': 3.271793168845183e-06, 'samples': 27335232, 'steps': 142370, 'loss/train': 1.2657307386398315} 08/31/2021 15:04:16 - INFO - __main__ - Step 142372: {'lr': 3.270937487078851e-06, 'samples': 27335424, 'steps': 142371, 'loss/train': 1.1585389375686646} 08/31/2021 15:04:16 - INFO - __main__ - Step 142373: {'lr': 3.2700819164848407e-06, 'samples': 27335616, 'steps': 142372, 'loss/train': 1.850806713104248} 08/31/2021 15:04:18 - INFO - __main__ - Step 142374: {'lr': 3.2692264570635123e-06, 'samples': 27335808, 'steps': 142373, 'loss/train': 1.500548243522644} 08/31/2021 15:04:19 - INFO - __main__ - Step 142375: {'lr': 3.2683711088152825e-06, 'samples': 27336000, 'steps': 142374, 'loss/train': 1.344795823097229} 08/31/2021 15:04:19 - INFO - __main__ - Step 142376: {'lr': 3.267515871740484e-06, 'samples': 27336192, 'steps': 142375, 'loss/train': 1.1154721975326538} 08/31/2021 15:04:19 - INFO - __main__ - Step 142377: {'lr': 3.2666607458395615e-06, 'samples': 27336384, 'steps': 142376, 'loss/train': 0.40989241003990173} 08/31/2021 15:04:20 - INFO - __main__ - Step 142378: {'lr': 3.2658057311128755e-06, 'samples': 27336576, 'steps': 142377, 'loss/train': 1.8959490060806274} 08/31/2021 15:04:20 - INFO - __main__ - Step 142379: {'lr': 3.2649508275607863e-06, 'samples': 27336768, 'steps': 142378, 'loss/train': 1.5476665496826172} 08/31/2021 15:04:22 - INFO - __main__ - Step 142380: {'lr': 3.264096035183711e-06, 'samples': 27336960, 'steps': 142379, 'loss/train': 1.0013724565505981} 08/31/2021 15:04:22 - INFO - __main__ - Step 142381: {'lr': 3.263241353982038e-06, 'samples': 27337152, 'steps': 142380, 'loss/train': 0.9874617457389832} 08/31/2021 15:04:23 - INFO - __main__ - Step 142382: {'lr': 3.262386783956128e-06, 'samples': 27337344, 'steps': 142381, 'loss/train': 0.885176420211792} 08/31/2021 15:04:23 - INFO - __main__ - Step 142383: {'lr': 3.261532325106398e-06, 'samples': 27337536, 'steps': 142382, 'loss/train': 0.4782138466835022} 08/31/2021 15:04:23 - INFO - __main__ - Step 142384: {'lr': 3.2606779774332074e-06, 'samples': 27337728, 'steps': 142383, 'loss/train': 1.5979653596878052} 08/31/2021 15:04:25 - INFO - __main__ - Step 142385: {'lr': 3.2598237409369458e-06, 'samples': 27337920, 'steps': 142384, 'loss/train': 0.6035732626914978} 08/31/2021 15:04:25 - INFO - __main__ - Step 142386: {'lr': 3.2589696156180016e-06, 'samples': 27338112, 'steps': 142385, 'loss/train': 1.1472924947738647} 08/31/2021 15:04:26 - INFO - __main__ - Step 142387: {'lr': 3.258115601476763e-06, 'samples': 27338304, 'steps': 142386, 'loss/train': 1.027910828590393} 08/31/2021 15:04:26 - INFO - __main__ - Step 142388: {'lr': 3.2572616985135915e-06, 'samples': 27338496, 'steps': 142387, 'loss/train': 0.7221935987472534} 08/31/2021 15:04:26 - INFO - __main__ - Step 142389: {'lr': 3.256407906728903e-06, 'samples': 27338688, 'steps': 142388, 'loss/train': 1.3147934675216675} 08/31/2021 15:04:28 - INFO - __main__ - Step 142390: {'lr': 3.2555542261230586e-06, 'samples': 27338880, 'steps': 142389, 'loss/train': 0.9969180822372437} 08/31/2021 15:04:28 - INFO - __main__ - Step 142391: {'lr': 3.2547006566964743e-06, 'samples': 27339072, 'steps': 142390, 'loss/train': 0.5674999356269836} 08/31/2021 15:04:29 - INFO - __main__ - Step 142392: {'lr': 3.253847198449511e-06, 'samples': 27339264, 'steps': 142391, 'loss/train': 4.1746320724487305} 08/31/2021 15:04:29 - INFO - __main__ - Step 142393: {'lr': 3.2529938513825297e-06, 'samples': 27339456, 'steps': 142392, 'loss/train': 0.9244550466537476} 08/31/2021 15:04:29 - INFO - __main__ - Step 142394: {'lr': 3.2521406154959744e-06, 'samples': 27339648, 'steps': 142393, 'loss/train': 0.5961514115333557} 08/31/2021 15:04:31 - INFO - __main__ - Step 142395: {'lr': 3.251287490790178e-06, 'samples': 27339840, 'steps': 142394, 'loss/train': 1.011344075202942} 08/31/2021 15:04:32 - INFO - __main__ - Step 142396: {'lr': 3.250434477265557e-06, 'samples': 27340032, 'steps': 142395, 'loss/train': 0.8842364549636841} 08/31/2021 15:04:32 - INFO - __main__ - Step 142397: {'lr': 3.2495815749224723e-06, 'samples': 27340224, 'steps': 142396, 'loss/train': 1.1796748638153076} 08/31/2021 15:04:32 - INFO - __main__ - Step 142398: {'lr': 3.24872878376134e-06, 'samples': 27340416, 'steps': 142397, 'loss/train': 1.1428112983703613} 08/31/2021 15:04:33 - INFO - __main__ - Step 142399: {'lr': 3.2478761037824934e-06, 'samples': 27340608, 'steps': 142398, 'loss/train': 0.07838449627161026} 08/31/2021 15:04:33 - INFO - __main__ - Step 142400: {'lr': 3.2470235349863487e-06, 'samples': 27340800, 'steps': 142399, 'loss/train': 1.2141727209091187} 08/31/2021 15:04:35 - INFO - __main__ - Step 142401: {'lr': 3.2461710773732946e-06, 'samples': 27340992, 'steps': 142400, 'loss/train': 1.5398715734481812} 08/31/2021 15:04:35 - INFO - __main__ - Step 142402: {'lr': 3.2453187309437193e-06, 'samples': 27341184, 'steps': 142401, 'loss/train': 1.3467730283737183} 08/31/2021 15:04:35 - INFO - __main__ - Step 142403: {'lr': 3.244466495697984e-06, 'samples': 27341376, 'steps': 142402, 'loss/train': 1.487655520439148} 08/31/2021 15:04:36 - INFO - __main__ - Step 142404: {'lr': 3.2436143716364774e-06, 'samples': 27341568, 'steps': 142403, 'loss/train': 0.673187255859375} 08/31/2021 15:04:36 - INFO - __main__ - Step 142405: {'lr': 3.2427623587596155e-06, 'samples': 27341760, 'steps': 142404, 'loss/train': 0.7265532612800598} 08/31/2021 15:04:38 - INFO - __main__ - Step 142406: {'lr': 3.2419104570677317e-06, 'samples': 27341952, 'steps': 142405, 'loss/train': 1.0159406661987305} 08/31/2021 15:04:38 - INFO - __main__ - Step 142407: {'lr': 3.241058666561242e-06, 'samples': 27342144, 'steps': 142406, 'loss/train': 0.7400513887405396} 08/31/2021 15:04:38 - INFO - __main__ - Step 142408: {'lr': 3.240206987240535e-06, 'samples': 27342336, 'steps': 142407, 'loss/train': 1.265699028968811} 08/31/2021 15:04:39 - INFO - __main__ - Step 142409: {'lr': 3.2393554191059715e-06, 'samples': 27342528, 'steps': 142408, 'loss/train': 0.7677097916603088} 08/31/2021 15:04:39 - INFO - __main__ - Step 142410: {'lr': 3.2385039621579405e-06, 'samples': 27342720, 'steps': 142409, 'loss/train': 0.9968071579933167} 08/31/2021 15:04:41 - INFO - __main__ - Step 142411: {'lr': 3.2376526163968303e-06, 'samples': 27342912, 'steps': 142410, 'loss/train': 0.4239655137062073} 08/31/2021 15:04:41 - INFO - __main__ - Step 142412: {'lr': 3.2368013818230567e-06, 'samples': 27343104, 'steps': 142411, 'loss/train': 0.4489210247993469} 08/31/2021 15:04:42 - INFO - __main__ - Step 142413: {'lr': 3.2359502584369536e-06, 'samples': 27343296, 'steps': 142412, 'loss/train': 0.5774958729743958} 08/31/2021 15:04:42 - INFO - __main__ - Step 142414: {'lr': 3.235099246238937e-06, 'samples': 27343488, 'steps': 142413, 'loss/train': 1.285080909729004} 08/31/2021 15:04:42 - INFO - __main__ - Step 142415: {'lr': 3.2342483452293403e-06, 'samples': 27343680, 'steps': 142414, 'loss/train': 1.80229651927948} 08/31/2021 15:04:44 - INFO - __main__ - Step 142416: {'lr': 3.233397555408607e-06, 'samples': 27343872, 'steps': 142415, 'loss/train': 0.9517128467559814} 08/31/2021 15:04:45 - INFO - __main__ - Step 142417: {'lr': 3.2325468767770983e-06, 'samples': 27344064, 'steps': 142416, 'loss/train': 0.8613637089729309} 08/31/2021 15:04:45 - INFO - __main__ - Step 142418: {'lr': 3.2316963093352027e-06, 'samples': 27344256, 'steps': 142417, 'loss/train': 0.056558508425951004} 08/31/2021 15:04:45 - INFO - __main__ - Step 142419: {'lr': 3.2308458530832805e-06, 'samples': 27344448, 'steps': 142418, 'loss/train': 0.13934822380542755} 08/31/2021 15:04:46 - INFO - __main__ - Step 142420: {'lr': 3.229995508021749e-06, 'samples': 27344640, 'steps': 142419, 'loss/train': 1.143898367881775} 08/31/2021 15:04:48 - INFO - __main__ - Step 142421: {'lr': 3.2291452741509407e-06, 'samples': 27344832, 'steps': 142420, 'loss/train': 0.8786838054656982} 08/31/2021 15:04:48 - INFO - __main__ - Step 142422: {'lr': 3.2282951514713e-06, 'samples': 27345024, 'steps': 142421, 'loss/train': 1.5038734674453735} 08/31/2021 15:04:48 - INFO - __main__ - Step 142423: {'lr': 3.2274451399831873e-06, 'samples': 27345216, 'steps': 142422, 'loss/train': 0.9259447455406189} 08/31/2021 15:04:49 - INFO - __main__ - Step 142424: {'lr': 3.2265952396869636e-06, 'samples': 27345408, 'steps': 142423, 'loss/train': 0.8418053984642029} 08/31/2021 15:04:49 - INFO - __main__ - Step 142425: {'lr': 3.225745450583045e-06, 'samples': 27345600, 'steps': 142424, 'loss/train': 0.9278397560119629} 08/31/2021 15:04:51 - INFO - __main__ - Step 142426: {'lr': 3.224895772671793e-06, 'samples': 27345792, 'steps': 142425, 'loss/train': 1.0871659517288208} 08/31/2021 15:04:52 - INFO - __main__ - Step 142427: {'lr': 3.224046205953568e-06, 'samples': 27345984, 'steps': 142426, 'loss/train': 1.1218669414520264} 08/31/2021 15:04:52 - INFO - __main__ - Step 142428: {'lr': 3.223196750428814e-06, 'samples': 27346176, 'steps': 142427, 'loss/train': 1.217394232749939} 08/31/2021 15:04:52 - INFO - __main__ - Step 142429: {'lr': 3.2223474060978643e-06, 'samples': 27346368, 'steps': 142428, 'loss/train': 0.8640347719192505} 08/31/2021 15:04:53 - INFO - __main__ - Step 142430: {'lr': 3.2214981729611072e-06, 'samples': 27346560, 'steps': 142429, 'loss/train': 0.037374142557382584} 08/31/2021 15:04:53 - INFO - __main__ - Step 142431: {'lr': 3.220649051018931e-06, 'samples': 27346752, 'steps': 142430, 'loss/train': 0.040632665157318115} 08/31/2021 15:04:55 - INFO - __main__ - Step 142432: {'lr': 3.219800040271753e-06, 'samples': 27346944, 'steps': 142431, 'loss/train': 1.3659095764160156} 08/31/2021 15:04:55 - INFO - __main__ - Step 142433: {'lr': 3.218951140719906e-06, 'samples': 27347136, 'steps': 142432, 'loss/train': 1.2928253412246704} 08/31/2021 15:04:56 - INFO - __main__ - Step 142434: {'lr': 3.2181023523637776e-06, 'samples': 27347328, 'steps': 142433, 'loss/train': 1.3934696912765503} 08/31/2021 15:04:56 - INFO - __main__ - Step 142435: {'lr': 3.217253675203785e-06, 'samples': 27347520, 'steps': 142434, 'loss/train': 3.980045795440674} 08/31/2021 15:04:56 - INFO - __main__ - Step 142436: {'lr': 3.216405109240289e-06, 'samples': 27347712, 'steps': 142435, 'loss/train': 4.041616916656494} 08/31/2021 15:04:57 - INFO - __main__ - Step 142437: {'lr': 3.215556654473678e-06, 'samples': 27347904, 'steps': 142436, 'loss/train': 0.3412696123123169} 08/31/2021 15:04:58 - INFO - __main__ - Step 142438: {'lr': 3.214708310904313e-06, 'samples': 27348096, 'steps': 142437, 'loss/train': 0.12488356977701187} 08/31/2021 15:04:59 - INFO - __main__ - Step 142439: {'lr': 3.21386007853261e-06, 'samples': 27348288, 'steps': 142438, 'loss/train': 1.0097543001174927} 08/31/2021 15:04:59 - INFO - __main__ - Step 142440: {'lr': 3.21301195735893e-06, 'samples': 27348480, 'steps': 142439, 'loss/train': 1.3161256313323975} 08/31/2021 15:04:59 - INFO - __main__ - Step 142441: {'lr': 3.212163947383634e-06, 'samples': 27348672, 'steps': 142440, 'loss/train': 0.3516896665096283} 08/31/2021 15:05:00 - INFO - __main__ - Step 142442: {'lr': 3.2113160486071658e-06, 'samples': 27348864, 'steps': 142441, 'loss/train': 0.6520240902900696} 08/31/2021 15:05:00 - INFO - __main__ - Step 142443: {'lr': 3.2104682610298308e-06, 'samples': 27349056, 'steps': 142442, 'loss/train': 0.4643857777118683} 08/31/2021 15:05:02 - INFO - __main__ - Step 142444: {'lr': 3.2096205846520734e-06, 'samples': 27349248, 'steps': 142443, 'loss/train': 0.957617998123169} 08/31/2021 15:05:02 - INFO - __main__ - Step 142445: {'lr': 3.208773019474254e-06, 'samples': 27349440, 'steps': 142444, 'loss/train': 1.0621458292007446} 08/31/2021 15:05:02 - INFO - __main__ - Step 142446: {'lr': 3.207925565496761e-06, 'samples': 27349632, 'steps': 142445, 'loss/train': 1.0766892433166504} 08/31/2021 15:05:03 - INFO - __main__ - Step 142447: {'lr': 3.2070782227199557e-06, 'samples': 27349824, 'steps': 142446, 'loss/train': 0.8458787202835083} 08/31/2021 15:05:03 - INFO - __main__ - Step 142448: {'lr': 3.2062309911442266e-06, 'samples': 27350016, 'steps': 142447, 'loss/train': 1.0666524171829224} 08/31/2021 15:05:05 - INFO - __main__ - Step 142449: {'lr': 3.2053838707699622e-06, 'samples': 27350208, 'steps': 142448, 'loss/train': 0.6998542547225952} 08/31/2021 15:05:05 - INFO - __main__ - Step 142450: {'lr': 3.204536861597551e-06, 'samples': 27350400, 'steps': 142449, 'loss/train': 1.5163013935089111} 08/31/2021 15:05:06 - INFO - __main__ - Step 142451: {'lr': 3.203689963627354e-06, 'samples': 27350592, 'steps': 142450, 'loss/train': 1.2573633193969727} 08/31/2021 15:05:06 - INFO - __main__ - Step 142452: {'lr': 3.2028431768598155e-06, 'samples': 27350784, 'steps': 142451, 'loss/train': 0.9069610238075256} 08/31/2021 15:05:06 - INFO - __main__ - Step 142453: {'lr': 3.2019965012952125e-06, 'samples': 27350976, 'steps': 142452, 'loss/train': 1.1230517625808716} 08/31/2021 15:05:08 - INFO - __main__ - Step 142454: {'lr': 3.201149936933989e-06, 'samples': 27351168, 'steps': 142453, 'loss/train': 0.7067015171051025} 08/31/2021 15:05:08 - INFO - __main__ - Step 142455: {'lr': 3.2003034837765345e-06, 'samples': 27351360, 'steps': 142454, 'loss/train': 0.658687174320221} 08/31/2021 15:05:09 - INFO - __main__ - Step 142456: {'lr': 3.1994571418232088e-06, 'samples': 27351552, 'steps': 142455, 'loss/train': 0.7769704461097717} 08/31/2021 15:05:09 - INFO - __main__ - Step 142457: {'lr': 3.198610911074401e-06, 'samples': 27351744, 'steps': 142456, 'loss/train': 0.7770208716392517} 08/31/2021 15:05:09 - INFO - __main__ - Step 142458: {'lr': 3.1977647915304997e-06, 'samples': 27351936, 'steps': 142457, 'loss/train': 1.3151772022247314} 08/31/2021 15:05:11 - INFO - __main__ - Step 142459: {'lr': 3.1969187831918656e-06, 'samples': 27352128, 'steps': 142458, 'loss/train': 0.6707305312156677} 08/31/2021 15:05:11 - INFO - __main__ - Step 142460: {'lr': 3.1960728860588873e-06, 'samples': 27352320, 'steps': 142459, 'loss/train': 1.1549067497253418} 08/31/2021 15:05:11 - INFO - __main__ - Step 142461: {'lr': 3.1952271001319533e-06, 'samples': 27352512, 'steps': 142460, 'loss/train': 1.1816277503967285} 08/31/2021 15:05:12 - INFO - __main__ - Step 142462: {'lr': 3.1943814254114523e-06, 'samples': 27352704, 'steps': 142461, 'loss/train': 1.1568710803985596} 08/31/2021 15:05:12 - INFO - __main__ - Step 142463: {'lr': 3.193535861897745e-06, 'samples': 27352896, 'steps': 142462, 'loss/train': 0.9673479795455933} 08/31/2021 15:05:14 - INFO - __main__ - Step 142464: {'lr': 3.1926904095912203e-06, 'samples': 27353088, 'steps': 142463, 'loss/train': 1.1967905759811401} 08/31/2021 15:05:14 - INFO - __main__ - Step 142465: {'lr': 3.191845068492266e-06, 'samples': 27353280, 'steps': 142464, 'loss/train': 1.8860721588134766} 08/31/2021 15:05:14 - INFO - __main__ - Step 142466: {'lr': 3.190999838601272e-06, 'samples': 27353472, 'steps': 142465, 'loss/train': 0.2632269561290741} 08/31/2021 15:05:15 - INFO - __main__ - Step 142467: {'lr': 3.1901547199185697e-06, 'samples': 27353664, 'steps': 142466, 'loss/train': 0.9472152590751648} 08/31/2021 15:05:15 - INFO - __main__ - Step 142468: {'lr': 3.189309712444605e-06, 'samples': 27353856, 'steps': 142467, 'loss/train': 1.3631377220153809} 08/31/2021 15:05:17 - INFO - __main__ - Step 142469: {'lr': 3.1884648161797094e-06, 'samples': 27354048, 'steps': 142468, 'loss/train': 1.318778157234192} 08/31/2021 15:05:17 - INFO - __main__ - Step 142470: {'lr': 3.1876200311242997e-06, 'samples': 27354240, 'steps': 142469, 'loss/train': 1.3739701509475708} 08/31/2021 15:05:18 - INFO - __main__ - Step 142471: {'lr': 3.1867753572787374e-06, 'samples': 27354432, 'steps': 142470, 'loss/train': 0.6899608373641968} 08/31/2021 15:05:18 - INFO - __main__ - Step 142472: {'lr': 3.1859307946433825e-06, 'samples': 27354624, 'steps': 142471, 'loss/train': 1.4393025636672974} 08/31/2021 15:05:18 - INFO - __main__ - Step 142473: {'lr': 3.1850863432186793e-06, 'samples': 27354816, 'steps': 142472, 'loss/train': 0.3044140636920929} 08/31/2021 15:05:19 - INFO - __main__ - Step 142474: {'lr': 3.1842420030049335e-06, 'samples': 27355008, 'steps': 142473, 'loss/train': 2.002443552017212} 08/31/2021 15:05:20 - INFO - __main__ - Step 142475: {'lr': 3.183397774002561e-06, 'samples': 27355200, 'steps': 142474, 'loss/train': 1.133888602256775} 08/31/2021 15:05:21 - INFO - __main__ - Step 142476: {'lr': 3.1825536562119508e-06, 'samples': 27355392, 'steps': 142475, 'loss/train': 1.5748523473739624} 08/31/2021 15:05:21 - INFO - __main__ - Step 142477: {'lr': 3.1817096496334906e-06, 'samples': 27355584, 'steps': 142476, 'loss/train': 0.901516318321228} 08/31/2021 15:05:21 - INFO - __main__ - Step 142478: {'lr': 3.1808657542675146e-06, 'samples': 27355776, 'steps': 142477, 'loss/train': 1.0114073753356934} 08/31/2021 15:05:22 - INFO - __main__ - Step 142479: {'lr': 3.1800219701144662e-06, 'samples': 27355968, 'steps': 142478, 'loss/train': 0.957028329372406} 08/31/2021 15:05:24 - INFO - __main__ - Step 142480: {'lr': 3.179178297174651e-06, 'samples': 27356160, 'steps': 142479, 'loss/train': 0.7748289704322815} 08/31/2021 15:05:24 - INFO - __main__ - Step 142481: {'lr': 3.1783347354485124e-06, 'samples': 27356352, 'steps': 142480, 'loss/train': 1.0709786415100098} 08/31/2021 15:05:25 - INFO - __main__ - Step 142482: {'lr': 3.1774912849364125e-06, 'samples': 27356544, 'steps': 142481, 'loss/train': 0.7644006609916687} 08/31/2021 15:05:25 - INFO - __main__ - Step 142483: {'lr': 3.176647945638711e-06, 'samples': 27356736, 'steps': 142482, 'loss/train': 0.9521414637565613} 08/31/2021 15:05:25 - INFO - __main__ - Step 142484: {'lr': 3.175804717555797e-06, 'samples': 27356928, 'steps': 142483, 'loss/train': 1.7109473943710327} 08/31/2021 15:05:27 - INFO - __main__ - Step 142485: {'lr': 3.174961600688059e-06, 'samples': 27357120, 'steps': 142484, 'loss/train': 0.9305998086929321} 08/31/2021 15:05:28 - INFO - __main__ - Step 142486: {'lr': 3.1741185950358854e-06, 'samples': 27357312, 'steps': 142485, 'loss/train': 1.4032907485961914} 08/31/2021 15:05:28 - INFO - __main__ - Step 142487: {'lr': 3.173275700599637e-06, 'samples': 27357504, 'steps': 142486, 'loss/train': 1.9423317909240723} 08/31/2021 15:05:28 - INFO - __main__ - Step 142488: {'lr': 3.1724329173797306e-06, 'samples': 27357696, 'steps': 142487, 'loss/train': 0.8927035927772522} 08/31/2021 15:05:29 - INFO - __main__ - Step 142489: {'lr': 3.171590245376471e-06, 'samples': 27357888, 'steps': 142488, 'loss/train': 0.023998629301786423} 08/31/2021 15:05:30 - INFO - __main__ - Step 142490: {'lr': 3.1707476845903025e-06, 'samples': 27358080, 'steps': 142489, 'loss/train': 1.1256370544433594} 08/31/2021 15:05:30 - INFO - __main__ - Step 142491: {'lr': 3.169905235021614e-06, 'samples': 27358272, 'steps': 142490, 'loss/train': 0.8612110018730164} 08/31/2021 15:05:31 - INFO - __main__ - Step 142492: {'lr': 3.1690628966707103e-06, 'samples': 27358464, 'steps': 142491, 'loss/train': 1.8395614624023438} 08/31/2021 15:05:31 - INFO - __main__ - Step 142493: {'lr': 3.168220669538063e-06, 'samples': 27358656, 'steps': 142492, 'loss/train': 0.8542649745941162} 08/31/2021 15:05:32 - INFO - __main__ - Step 142494: {'lr': 3.167378553624006e-06, 'samples': 27358848, 'steps': 142493, 'loss/train': 1.3657621145248413} 08/31/2021 15:05:32 - INFO - __main__ - Step 142495: {'lr': 3.166536548928872e-06, 'samples': 27359040, 'steps': 142494, 'loss/train': 1.0041935443878174} 08/31/2021 15:05:34 - INFO - __main__ - Step 142496: {'lr': 3.1656946554531328e-06, 'samples': 27359232, 'steps': 142495, 'loss/train': 0.5000417828559875} 08/31/2021 15:05:34 - INFO - __main__ - Step 142497: {'lr': 3.164852873197094e-06, 'samples': 27359424, 'steps': 142496, 'loss/train': 1.2874114513397217} 08/31/2021 15:05:34 - INFO - __main__ - Step 142498: {'lr': 3.164011202161171e-06, 'samples': 27359616, 'steps': 142497, 'loss/train': 0.502910315990448} 08/31/2021 15:05:35 - INFO - __main__ - Step 142499: {'lr': 3.1631696423457536e-06, 'samples': 27359808, 'steps': 142498, 'loss/train': 1.2879759073257446} 08/31/2021 15:05:35 - INFO - __main__ - Step 142500: {'lr': 3.1623281937511737e-06, 'samples': 27360000, 'steps': 142499, 'loss/train': 0.38636741042137146} 08/31/2021 15:05:37 - INFO - __main__ - Step 142501: {'lr': 3.1614868563778486e-06, 'samples': 27360192, 'steps': 142500, 'loss/train': 1.2293273210525513} 08/31/2021 15:05:37 - INFO - __main__ - Step 142502: {'lr': 3.1606456302261667e-06, 'samples': 27360384, 'steps': 142501, 'loss/train': 1.39033842086792} 08/31/2021 15:05:38 - INFO - __main__ - Step 142503: {'lr': 3.1598045152964605e-06, 'samples': 27360576, 'steps': 142502, 'loss/train': 1.4958585500717163} 08/31/2021 15:05:38 - INFO - __main__ - Step 142504: {'lr': 3.1589635115891746e-06, 'samples': 27360768, 'steps': 142503, 'loss/train': 1.1049339771270752} 08/31/2021 15:05:38 - INFO - __main__ - Step 142505: {'lr': 3.1581226191046144e-06, 'samples': 27360960, 'steps': 142504, 'loss/train': 1.1997853517532349} 08/31/2021 15:05:40 - INFO - __main__ - Step 142506: {'lr': 3.1572818378432233e-06, 'samples': 27361152, 'steps': 142505, 'loss/train': 1.4982513189315796} 08/31/2021 15:05:40 - INFO - __main__ - Step 142507: {'lr': 3.156441167805335e-06, 'samples': 27361344, 'steps': 142506, 'loss/train': 0.8624869585037231} 08/31/2021 15:05:40 - INFO - __main__ - Step 142508: {'lr': 3.1556006089913657e-06, 'samples': 27361536, 'steps': 142507, 'loss/train': 1.2077172994613647} 08/31/2021 15:05:41 - INFO - __main__ - Step 142509: {'lr': 3.1547601614016487e-06, 'samples': 27361728, 'steps': 142508, 'loss/train': 1.036497712135315} 08/31/2021 15:05:41 - INFO - __main__ - Step 142510: {'lr': 3.1539198250365997e-06, 'samples': 27361920, 'steps': 142509, 'loss/train': 0.8763101100921631} 08/31/2021 15:05:43 - INFO - __main__ - Step 142511: {'lr': 3.15307959989658e-06, 'samples': 27362112, 'steps': 142510, 'loss/train': 0.8251591920852661} 08/31/2021 15:05:43 - INFO - __main__ - Step 142512: {'lr': 3.152239485981978e-06, 'samples': 27362304, 'steps': 142511, 'loss/train': 1.5183132886886597} 08/31/2021 15:05:43 - INFO - __main__ - Step 142513: {'lr': 3.1513994832931547e-06, 'samples': 27362496, 'steps': 142512, 'loss/train': 1.4883854389190674} 08/31/2021 15:05:44 - INFO - __main__ - Step 142514: {'lr': 3.1505595918305264e-06, 'samples': 27362688, 'steps': 142513, 'loss/train': 1.0332651138305664} 08/31/2021 15:05:44 - INFO - __main__ - Step 142515: {'lr': 3.1497198115944258e-06, 'samples': 27362880, 'steps': 142514, 'loss/train': 1.2063448429107666} 08/31/2021 15:05:46 - INFO - __main__ - Step 142516: {'lr': 3.148880142585242e-06, 'samples': 27363072, 'steps': 142515, 'loss/train': 0.9634878635406494} 08/31/2021 15:05:46 - INFO - __main__ - Step 142517: {'lr': 3.148040584803391e-06, 'samples': 27363264, 'steps': 142516, 'loss/train': 0.8664341568946838} 08/31/2021 15:05:47 - INFO - __main__ - Step 142518: {'lr': 3.1472011382492062e-06, 'samples': 27363456, 'steps': 142517, 'loss/train': 1.531718373298645} 08/31/2021 15:05:47 - INFO - __main__ - Step 142519: {'lr': 3.1463618029231035e-06, 'samples': 27363648, 'steps': 142518, 'loss/train': 1.2958252429962158} 08/31/2021 15:05:47 - INFO - __main__ - Step 142520: {'lr': 3.145522578825444e-06, 'samples': 27363840, 'steps': 142519, 'loss/train': 1.6350170373916626} 08/31/2021 15:05:49 - INFO - __main__ - Step 142521: {'lr': 3.144683465956588e-06, 'samples': 27364032, 'steps': 142520, 'loss/train': 1.2897799015045166} 08/31/2021 15:05:49 - INFO - __main__ - Step 142522: {'lr': 3.1438444643169252e-06, 'samples': 27364224, 'steps': 142521, 'loss/train': 0.9901940226554871} 08/31/2021 15:05:50 - INFO - __main__ - Step 142523: {'lr': 3.1430055739068432e-06, 'samples': 27364416, 'steps': 142522, 'loss/train': 0.7397622466087341} 08/31/2021 15:05:50 - INFO - __main__ - Step 142524: {'lr': 3.142166794726703e-06, 'samples': 27364608, 'steps': 142523, 'loss/train': 1.1753796339035034} 08/31/2021 15:05:50 - INFO - __main__ - Step 142525: {'lr': 3.1413281267768936e-06, 'samples': 27364800, 'steps': 142524, 'loss/train': 0.8976891040802002} 08/31/2021 15:05:51 - INFO - __main__ - Step 142526: {'lr': 3.1404895700578027e-06, 'samples': 27364992, 'steps': 142525, 'loss/train': 0.22682121396064758} 08/31/2021 15:05:52 - INFO - __main__ - Step 142527: {'lr': 3.1396511245697922e-06, 'samples': 27365184, 'steps': 142526, 'loss/train': 1.855141043663025} 08/31/2021 15:05:53 - INFO - __main__ - Step 142528: {'lr': 3.13881279031325e-06, 'samples': 27365376, 'steps': 142527, 'loss/train': 1.6295431852340698} 08/31/2021 15:05:53 - INFO - __main__ - Step 142529: {'lr': 3.1379745672885376e-06, 'samples': 27365568, 'steps': 142528, 'loss/train': 1.3595173358917236} 08/31/2021 15:05:53 - INFO - __main__ - Step 142530: {'lr': 3.13713645549607e-06, 'samples': 27365760, 'steps': 142529, 'loss/train': 1.2207362651824951} 08/31/2021 15:05:54 - INFO - __main__ - Step 142531: {'lr': 3.1362984549361815e-06, 'samples': 27365952, 'steps': 142530, 'loss/train': 0.8559674620628357} 08/31/2021 15:05:56 - INFO - __main__ - Step 142532: {'lr': 3.1354605656092605e-06, 'samples': 27366144, 'steps': 142531, 'loss/train': 1.4196161031723022} 08/31/2021 15:05:57 - INFO - __main__ - Step 142533: {'lr': 3.134622787515723e-06, 'samples': 27366336, 'steps': 142532, 'loss/train': 0.015216417610645294} 08/31/2021 15:05:57 - INFO - __main__ - Step 142534: {'lr': 3.1337851206558743e-06, 'samples': 27366528, 'steps': 142533, 'loss/train': 0.01412285678088665} 08/31/2021 15:05:57 - INFO - __main__ - Step 142535: {'lr': 3.1329475650301588e-06, 'samples': 27366720, 'steps': 142534, 'loss/train': 1.2928396463394165} 08/31/2021 15:05:58 - INFO - __main__ - Step 142536: {'lr': 3.1321101206389092e-06, 'samples': 27366912, 'steps': 142535, 'loss/train': 0.9708343148231506} 08/31/2021 15:05:58 - INFO - __main__ - Step 142537: {'lr': 3.131272787482542e-06, 'samples': 27367104, 'steps': 142536, 'loss/train': 1.5130151510238647} 08/31/2021 15:06:00 - INFO - __main__ - Step 142538: {'lr': 3.1304355655613904e-06, 'samples': 27367296, 'steps': 142537, 'loss/train': 1.4704296588897705} 08/31/2021 15:06:00 - INFO - __main__ - Step 142539: {'lr': 3.1295984548758704e-06, 'samples': 27367488, 'steps': 142538, 'loss/train': 1.0014441013336182} 08/31/2021 15:06:01 - INFO - __main__ - Step 142540: {'lr': 3.128761455426343e-06, 'samples': 27367680, 'steps': 142539, 'loss/train': 0.8267748951911926} 08/31/2021 15:06:01 - INFO - __main__ - Step 142541: {'lr': 3.1279245672131974e-06, 'samples': 27367872, 'steps': 142540, 'loss/train': 1.1882213354110718} 08/31/2021 15:06:01 - INFO - __main__ - Step 142542: {'lr': 3.127087790236793e-06, 'samples': 27368064, 'steps': 142541, 'loss/train': 0.5185879468917847} 08/31/2021 15:06:03 - INFO - __main__ - Step 142543: {'lr': 3.1262511244974923e-06, 'samples': 27368256, 'steps': 142542, 'loss/train': 1.4344900846481323} 08/31/2021 15:06:03 - INFO - __main__ - Step 142544: {'lr': 3.1254145699957105e-06, 'samples': 27368448, 'steps': 142543, 'loss/train': 1.2038750648498535} 08/31/2021 15:06:04 - INFO - __main__ - Step 142545: {'lr': 3.1245781267318087e-06, 'samples': 27368640, 'steps': 142544, 'loss/train': 1.2036879062652588} 08/31/2021 15:06:04 - INFO - __main__ - Step 142546: {'lr': 3.1237417947061752e-06, 'samples': 27368832, 'steps': 142545, 'loss/train': 1.1410444974899292} 08/31/2021 15:06:04 - INFO - __main__ - Step 142547: {'lr': 3.122905573919144e-06, 'samples': 27369024, 'steps': 142546, 'loss/train': 0.705110490322113} 08/31/2021 15:06:06 - INFO - __main__ - Step 142548: {'lr': 3.122069464371158e-06, 'samples': 27369216, 'steps': 142547, 'loss/train': 0.8517383337020874} 08/31/2021 15:06:06 - INFO - __main__ - Step 142549: {'lr': 3.121233466062523e-06, 'samples': 27369408, 'steps': 142548, 'loss/train': 1.5420653820037842} 08/31/2021 15:06:07 - INFO - __main__ - Step 142550: {'lr': 3.1203975789936557e-06, 'samples': 27369600, 'steps': 142549, 'loss/train': 0.5383082628250122} 08/31/2021 15:06:07 - INFO - __main__ - Step 142551: {'lr': 3.119561803164944e-06, 'samples': 27369792, 'steps': 142550, 'loss/train': 1.4040937423706055} 08/31/2021 15:06:07 - INFO - __main__ - Step 142552: {'lr': 3.1187261385767494e-06, 'samples': 27369984, 'steps': 142551, 'loss/train': 0.2417614609003067} 08/31/2021 15:06:09 - INFO - __main__ - Step 142553: {'lr': 3.1178905852294327e-06, 'samples': 27370176, 'steps': 142552, 'loss/train': 1.7946170568466187} 08/31/2021 15:06:09 - INFO - __main__ - Step 142554: {'lr': 3.117055143123382e-06, 'samples': 27370368, 'steps': 142553, 'loss/train': 0.78835129737854} 08/31/2021 15:06:10 - INFO - __main__ - Step 142555: {'lr': 3.1162198122589856e-06, 'samples': 27370560, 'steps': 142554, 'loss/train': 1.2099344730377197} 08/31/2021 15:06:10 - INFO - __main__ - Step 142556: {'lr': 3.1153845926366053e-06, 'samples': 27370752, 'steps': 142555, 'loss/train': 1.4941867589950562} 08/31/2021 15:06:10 - INFO - __main__ - Step 142557: {'lr': 3.114549484256629e-06, 'samples': 27370944, 'steps': 142556, 'loss/train': 2.4686851501464844} 08/31/2021 15:06:12 - INFO - __main__ - Step 142558: {'lr': 3.1137144871194177e-06, 'samples': 27371136, 'steps': 142557, 'loss/train': 0.5290969014167786} 08/31/2021 15:06:12 - INFO - __main__ - Step 142559: {'lr': 3.1128796012253877e-06, 'samples': 27371328, 'steps': 142558, 'loss/train': 0.9941599369049072} 08/31/2021 15:06:13 - INFO - __main__ - Step 142560: {'lr': 3.1120448265748726e-06, 'samples': 27371520, 'steps': 142559, 'loss/train': 1.1743615865707397} 08/31/2021 15:06:13 - INFO - __main__ - Step 142561: {'lr': 3.1112101631682323e-06, 'samples': 27371712, 'steps': 142560, 'loss/train': 1.429196834564209} 08/31/2021 15:06:13 - INFO - __main__ - Step 142562: {'lr': 3.1103756110058835e-06, 'samples': 27371904, 'steps': 142561, 'loss/train': 1.3575876951217651} 08/31/2021 15:06:14 - INFO - __main__ - Step 142563: {'lr': 3.1095411700882148e-06, 'samples': 27372096, 'steps': 142562, 'loss/train': 1.2076703310012817} 08/31/2021 15:06:15 - INFO - __main__ - Step 142564: {'lr': 3.1087068404155593e-06, 'samples': 27372288, 'steps': 142563, 'loss/train': 0.2718793451786041} 08/31/2021 15:06:16 - INFO - __main__ - Step 142565: {'lr': 3.1078726219883058e-06, 'samples': 27372480, 'steps': 142564, 'loss/train': 0.09338629245758057} 08/31/2021 15:06:16 - INFO - __main__ - Step 142566: {'lr': 3.1070385148068148e-06, 'samples': 27372672, 'steps': 142565, 'loss/train': 0.9364549517631531} 08/31/2021 15:06:16 - INFO - __main__ - Step 142567: {'lr': 3.1062045188715305e-06, 'samples': 27372864, 'steps': 142566, 'loss/train': 0.10383664816617966} 08/31/2021 15:06:17 - INFO - __main__ - Step 142568: {'lr': 3.1053706341827304e-06, 'samples': 27373056, 'steps': 142567, 'loss/train': 1.696400761604309} 08/31/2021 15:06:18 - INFO - __main__ - Step 142569: {'lr': 3.1045368607408866e-06, 'samples': 27373248, 'steps': 142568, 'loss/train': 0.6209715604782104} 08/31/2021 15:06:19 - INFO - __main__ - Step 142570: {'lr': 3.1037031985463036e-06, 'samples': 27373440, 'steps': 142569, 'loss/train': 0.1100936233997345} 08/31/2021 15:06:19 - INFO - __main__ - Step 142571: {'lr': 3.102869647599371e-06, 'samples': 27373632, 'steps': 142570, 'loss/train': 0.26154622435569763} 08/31/2021 15:06:19 - INFO - __main__ - Step 142572: {'lr': 3.1020362079005047e-06, 'samples': 27373824, 'steps': 142571, 'loss/train': 0.14942628145217896} 08/31/2021 15:06:20 - INFO - __main__ - Step 142573: {'lr': 3.101202879450038e-06, 'samples': 27374016, 'steps': 142572, 'loss/train': 1.4628264904022217} 08/31/2021 15:06:21 - INFO - __main__ - Step 142574: {'lr': 3.1003696622483592e-06, 'samples': 27374208, 'steps': 142573, 'loss/train': 1.124691128730774} 08/31/2021 15:06:22 - INFO - __main__ - Step 142575: {'lr': 3.0995365562958565e-06, 'samples': 27374400, 'steps': 142574, 'loss/train': 1.162613034248352} 08/31/2021 15:06:22 - INFO - __main__ - Step 142576: {'lr': 3.098703561592864e-06, 'samples': 27374592, 'steps': 142575, 'loss/train': 0.022437214851379395} 08/31/2021 15:06:23 - INFO - __main__ - Step 142577: {'lr': 3.097870678139797e-06, 'samples': 27374784, 'steps': 142576, 'loss/train': 0.02426496520638466} 08/31/2021 15:06:23 - INFO - __main__ - Step 142578: {'lr': 3.097037905937017e-06, 'samples': 27374976, 'steps': 142577, 'loss/train': 0.565146803855896} 08/31/2021 15:06:25 - INFO - __main__ - Step 142579: {'lr': 3.096205244984912e-06, 'samples': 27375168, 'steps': 142578, 'loss/train': 1.3689261674880981} 08/31/2021 15:06:25 - INFO - __main__ - Step 142580: {'lr': 3.0953726952838435e-06, 'samples': 27375360, 'steps': 142579, 'loss/train': 1.6959078311920166} 08/31/2021 15:06:25 - INFO - __main__ - Step 142581: {'lr': 3.0945402568341997e-06, 'samples': 27375552, 'steps': 142580, 'loss/train': 1.1560245752334595} 08/31/2021 15:06:26 - INFO - __main__ - Step 142582: {'lr': 3.093707929636341e-06, 'samples': 27375744, 'steps': 142581, 'loss/train': 0.5342504978179932} 08/31/2021 15:06:26 - INFO - __main__ - Step 142583: {'lr': 3.0928757136906295e-06, 'samples': 27375936, 'steps': 142582, 'loss/train': 1.1139371395111084} 08/31/2021 15:06:28 - INFO - __main__ - Step 142584: {'lr': 3.09204360899748e-06, 'samples': 27376128, 'steps': 142583, 'loss/train': 1.0714514255523682} 08/31/2021 15:06:28 - INFO - __main__ - Step 142585: {'lr': 3.0912116155572266e-06, 'samples': 27376320, 'steps': 142584, 'loss/train': 1.118817925453186} 08/31/2021 15:06:29 - INFO - __main__ - Step 142586: {'lr': 3.0903797333702853e-06, 'samples': 27376512, 'steps': 142585, 'loss/train': 1.1936335563659668} 08/31/2021 15:06:29 - INFO - __main__ - Step 142587: {'lr': 3.0895479624370173e-06, 'samples': 27376704, 'steps': 142586, 'loss/train': 0.3432590961456299} 08/31/2021 15:06:29 - INFO - __main__ - Step 142588: {'lr': 3.0887163027577546e-06, 'samples': 27376896, 'steps': 142587, 'loss/train': 0.4523930549621582} 08/31/2021 15:06:31 - INFO - __main__ - Step 142589: {'lr': 3.0878847543329145e-06, 'samples': 27377088, 'steps': 142588, 'loss/train': 1.4963836669921875} 08/31/2021 15:06:32 - INFO - __main__ - Step 142590: {'lr': 3.0870533171628857e-06, 'samples': 27377280, 'steps': 142589, 'loss/train': 1.4530314207077026} 08/31/2021 15:06:32 - INFO - __main__ - Step 142591: {'lr': 3.0862219912480007e-06, 'samples': 27377472, 'steps': 142590, 'loss/train': 0.9478835463523865} 08/31/2021 15:06:33 - INFO - __main__ - Step 142592: {'lr': 3.085390776588648e-06, 'samples': 27377664, 'steps': 142591, 'loss/train': 1.1626797914505005} 08/31/2021 15:06:33 - INFO - __main__ - Step 142593: {'lr': 3.0845596731852167e-06, 'samples': 27377856, 'steps': 142592, 'loss/train': 0.1113412082195282} 08/31/2021 15:06:34 - INFO - __main__ - Step 142594: {'lr': 3.0837286810380673e-06, 'samples': 27378048, 'steps': 142593, 'loss/train': 1.0611417293548584} 08/31/2021 15:06:35 - INFO - __main__ - Step 142595: {'lr': 3.082897800147588e-06, 'samples': 27378240, 'steps': 142594, 'loss/train': 1.0922836065292358} 08/31/2021 15:06:35 - INFO - __main__ - Step 142596: {'lr': 3.0820670305141407e-06, 'samples': 27378432, 'steps': 142595, 'loss/train': 0.9472509622573853} 08/31/2021 15:06:36 - INFO - __main__ - Step 142597: {'lr': 3.081236372138113e-06, 'samples': 27378624, 'steps': 142596, 'loss/train': 1.2742135524749756} 08/31/2021 15:06:36 - INFO - __main__ - Step 142598: {'lr': 3.0804058250198663e-06, 'samples': 27378816, 'steps': 142597, 'loss/train': 0.9853524565696716} 08/31/2021 15:06:37 - INFO - __main__ - Step 142599: {'lr': 3.079575389159761e-06, 'samples': 27379008, 'steps': 142598, 'loss/train': 1.155458688735962} 08/31/2021 15:06:38 - INFO - __main__ - Step 142600: {'lr': 3.0787450645582136e-06, 'samples': 27379200, 'steps': 142599, 'loss/train': 1.4542428255081177} 08/31/2021 15:06:38 - INFO - __main__ - Step 142601: {'lr': 3.077914851215585e-06, 'samples': 27379392, 'steps': 142600, 'loss/train': 0.246517613530159} 08/31/2021 15:06:39 - INFO - __main__ - Step 142602: {'lr': 3.0770847491322085e-06, 'samples': 27379584, 'steps': 142601, 'loss/train': 1.1098605394363403} 08/31/2021 15:06:39 - INFO - __main__ - Step 142603: {'lr': 3.0762547583085e-06, 'samples': 27379776, 'steps': 142602, 'loss/train': 1.1278948783874512} 08/31/2021 15:06:39 - INFO - __main__ - Step 142604: {'lr': 3.0754248787447923e-06, 'samples': 27379968, 'steps': 142603, 'loss/train': 1.6025471687316895} 08/31/2021 15:06:41 - INFO - __main__ - Step 142605: {'lr': 3.0745951104415303e-06, 'samples': 27380160, 'steps': 142604, 'loss/train': 1.3865163326263428} 08/31/2021 15:06:41 - INFO - __main__ - Step 142606: {'lr': 3.073765453399019e-06, 'samples': 27380352, 'steps': 142605, 'loss/train': 0.029157215729355812} 08/31/2021 15:06:41 - INFO - __main__ - Step 142607: {'lr': 3.0729359076176464e-06, 'samples': 27380544, 'steps': 142606, 'loss/train': 1.0960482358932495} 08/31/2021 15:06:42 - INFO - __main__ - Step 142608: {'lr': 3.07210647309783e-06, 'samples': 27380736, 'steps': 142607, 'loss/train': 0.39745286107063293} 08/31/2021 15:06:42 - INFO - __main__ - Step 142609: {'lr': 3.0712771498399015e-06, 'samples': 27380928, 'steps': 142608, 'loss/train': 1.0246564149856567} 08/31/2021 15:06:44 - INFO - __main__ - Step 142610: {'lr': 3.070447937844251e-06, 'samples': 27381120, 'steps': 142609, 'loss/train': 0.10028982162475586} 08/31/2021 15:06:44 - INFO - __main__ - Step 142611: {'lr': 3.0696188371112377e-06, 'samples': 27381312, 'steps': 142610, 'loss/train': 1.0548219680786133} 08/31/2021 15:06:45 - INFO - __main__ - Step 142612: {'lr': 3.0687898476412512e-06, 'samples': 27381504, 'steps': 142611, 'loss/train': 1.1089246273040771} 08/31/2021 15:06:45 - INFO - __main__ - Step 142613: {'lr': 3.0679609694346523e-06, 'samples': 27381696, 'steps': 142612, 'loss/train': 1.2331268787384033} 08/31/2021 15:06:45 - INFO - __main__ - Step 142614: {'lr': 3.0671322024918292e-06, 'samples': 27381888, 'steps': 142613, 'loss/train': 0.6913325786590576} 08/31/2021 15:06:46 - INFO - __main__ - Step 142615: {'lr': 3.066303546813115e-06, 'samples': 27382080, 'steps': 142614, 'loss/train': 0.5790106058120728} 08/31/2021 15:06:47 - INFO - __main__ - Step 142616: {'lr': 3.065475002398954e-06, 'samples': 27382272, 'steps': 142615, 'loss/train': 1.4448654651641846} 08/31/2021 15:06:48 - INFO - __main__ - Step 142617: {'lr': 3.0646465692496516e-06, 'samples': 27382464, 'steps': 142616, 'loss/train': 0.8193567991256714} 08/31/2021 15:06:48 - INFO - __main__ - Step 142618: {'lr': 3.063818247365624e-06, 'samples': 27382656, 'steps': 142617, 'loss/train': 1.1696808338165283} 08/31/2021 15:06:48 - INFO - __main__ - Step 142619: {'lr': 3.062990036747204e-06, 'samples': 27382848, 'steps': 142618, 'loss/train': 0.6994596123695374} 08/31/2021 15:06:49 - INFO - __main__ - Step 142620: {'lr': 3.0621619373948084e-06, 'samples': 27383040, 'steps': 142619, 'loss/train': 0.03451652452349663} 08/31/2021 15:06:51 - INFO - __main__ - Step 142621: {'lr': 3.0613339493087978e-06, 'samples': 27383232, 'steps': 142620, 'loss/train': 0.5847698450088501} 08/31/2021 15:06:51 - INFO - __main__ - Step 142622: {'lr': 3.0605060724895607e-06, 'samples': 27383424, 'steps': 142621, 'loss/train': 1.107977032661438} 08/31/2021 15:06:51 - INFO - __main__ - Step 142623: {'lr': 3.0596783069374025e-06, 'samples': 27383616, 'steps': 142622, 'loss/train': 0.959342360496521} 08/31/2021 15:06:52 - INFO - __main__ - Step 142624: {'lr': 3.058850652652767e-06, 'samples': 27383808, 'steps': 142623, 'loss/train': 0.6585644483566284} 08/31/2021 15:06:52 - INFO - __main__ - Step 142625: {'lr': 3.0580231096360155e-06, 'samples': 27384000, 'steps': 142624, 'loss/train': 1.1188770532608032} 08/31/2021 15:06:53 - INFO - __main__ - Step 142626: {'lr': 3.057195677887481e-06, 'samples': 27384192, 'steps': 142625, 'loss/train': 1.206531047821045} 08/31/2021 15:06:54 - INFO - __main__ - Step 142627: {'lr': 3.0563683574075795e-06, 'samples': 27384384, 'steps': 142626, 'loss/train': 0.6723710894584656} 08/31/2021 15:06:54 - INFO - __main__ - Step 142628: {'lr': 3.0555411481966446e-06, 'samples': 27384576, 'steps': 142627, 'loss/train': 0.9088649153709412} 08/31/2021 15:06:55 - INFO - __main__ - Step 142629: {'lr': 3.0547140502550917e-06, 'samples': 27384768, 'steps': 142628, 'loss/train': 1.7959007024765015} 08/31/2021 15:06:55 - INFO - __main__ - Step 142630: {'lr': 3.053887063583283e-06, 'samples': 27384960, 'steps': 142629, 'loss/train': 0.7396068572998047} 08/31/2021 15:06:57 - INFO - __main__ - Step 142631: {'lr': 3.0530601881815776e-06, 'samples': 27385152, 'steps': 142630, 'loss/train': 0.17802272737026215} 08/31/2021 15:06:57 - INFO - __main__ - Step 142632: {'lr': 3.052233424050338e-06, 'samples': 27385344, 'steps': 142631, 'loss/train': 1.3002249002456665} 08/31/2021 15:06:57 - INFO - __main__ - Step 142633: {'lr': 3.0514067711899796e-06, 'samples': 27385536, 'steps': 142632, 'loss/train': 1.1943410634994507} 08/31/2021 15:06:58 - INFO - __main__ - Step 142634: {'lr': 3.0505802296008354e-06, 'samples': 27385728, 'steps': 142633, 'loss/train': 0.4483835995197296} 08/31/2021 15:06:58 - INFO - __main__ - Step 142635: {'lr': 3.049753799283267e-06, 'samples': 27385920, 'steps': 142634, 'loss/train': 0.6532551050186157} 08/31/2021 15:07:00 - INFO - __main__ - Step 142636: {'lr': 3.04892748023769e-06, 'samples': 27386112, 'steps': 142635, 'loss/train': 0.7484351396560669} 08/31/2021 15:07:01 - INFO - __main__ - Step 142637: {'lr': 3.0481012724644375e-06, 'samples': 27386304, 'steps': 142636, 'loss/train': 0.6415653228759766} 08/31/2021 15:07:01 - INFO - __main__ - Step 142638: {'lr': 3.0472751759639263e-06, 'samples': 27386496, 'steps': 142637, 'loss/train': 0.38593488931655884} 08/31/2021 15:07:01 - INFO - __main__ - Step 142639: {'lr': 3.046449190736461e-06, 'samples': 27386688, 'steps': 142638, 'loss/train': 1.0661813020706177} 08/31/2021 15:07:02 - INFO - __main__ - Step 142640: {'lr': 3.0456233167824865e-06, 'samples': 27386880, 'steps': 142639, 'loss/train': 0.17192023992538452} 08/31/2021 15:07:02 - INFO - __main__ - Step 142641: {'lr': 3.0447975541023354e-06, 'samples': 27387072, 'steps': 142640, 'loss/train': 1.578075885772705} 08/31/2021 15:07:04 - INFO - __main__ - Step 142642: {'lr': 3.0439719026963965e-06, 'samples': 27387264, 'steps': 142641, 'loss/train': 0.11951223760843277} 08/31/2021 15:07:05 - INFO - __main__ - Step 142643: {'lr': 3.0431463625650302e-06, 'samples': 27387456, 'steps': 142642, 'loss/train': 1.2484006881713867} 08/31/2021 15:07:05 - INFO - __main__ - Step 142644: {'lr': 3.0423209337086253e-06, 'samples': 27387648, 'steps': 142643, 'loss/train': 0.554592490196228} 08/31/2021 15:07:05 - INFO - __main__ - Step 142645: {'lr': 3.0414956161275155e-06, 'samples': 27387840, 'steps': 142644, 'loss/train': 0.7189651131629944} 08/31/2021 15:07:06 - INFO - __main__ - Step 142646: {'lr': 3.040670409822116e-06, 'samples': 27388032, 'steps': 142645, 'loss/train': 0.29134759306907654} 08/31/2021 15:07:07 - INFO - __main__ - Step 142647: {'lr': 3.0398453147927605e-06, 'samples': 27388224, 'steps': 142646, 'loss/train': 1.1516363620758057} 08/31/2021 15:07:08 - INFO - __main__ - Step 142648: {'lr': 3.039020331039838e-06, 'samples': 27388416, 'steps': 142647, 'loss/train': 1.118537187576294} 08/31/2021 15:07:08 - INFO - __main__ - Step 142649: {'lr': 3.0381954585637362e-06, 'samples': 27388608, 'steps': 142648, 'loss/train': 0.7558110952377319} 08/31/2021 15:07:08 - INFO - __main__ - Step 142650: {'lr': 3.0373706973647885e-06, 'samples': 27388800, 'steps': 142649, 'loss/train': 0.7964173555374146} 08/31/2021 15:07:09 - INFO - __main__ - Step 142651: {'lr': 3.0365460474434115e-06, 'samples': 27388992, 'steps': 142650, 'loss/train': 1.922858715057373} 08/31/2021 15:07:10 - INFO - __main__ - Step 142652: {'lr': 3.0357215087999655e-06, 'samples': 27389184, 'steps': 142651, 'loss/train': 0.9141982793807983} 08/31/2021 15:07:11 - INFO - __main__ - Step 142653: {'lr': 3.034897081434812e-06, 'samples': 27389376, 'steps': 142652, 'loss/train': 0.6732100248336792} 08/31/2021 15:07:11 - INFO - __main__ - Step 142654: {'lr': 3.0340727653483115e-06, 'samples': 27389568, 'steps': 142653, 'loss/train': 0.824532151222229} 08/31/2021 15:07:11 - INFO - __main__ - Step 142655: {'lr': 3.033248560540852e-06, 'samples': 27389760, 'steps': 142654, 'loss/train': 1.085857629776001} 08/31/2021 15:07:12 - INFO - __main__ - Step 142656: {'lr': 3.0324244670127956e-06, 'samples': 27389952, 'steps': 142655, 'loss/train': 1.3837528228759766} 08/31/2021 15:07:13 - INFO - __main__ - Step 142657: {'lr': 3.031600484764502e-06, 'samples': 27390144, 'steps': 142656, 'loss/train': 1.3438421487808228} 08/31/2021 15:07:14 - INFO - __main__ - Step 142658: {'lr': 3.0307766137963876e-06, 'samples': 27390336, 'steps': 142657, 'loss/train': 1.1891202926635742} 08/31/2021 15:07:14 - INFO - __main__ - Step 142659: {'lr': 3.0299528541087862e-06, 'samples': 27390528, 'steps': 142658, 'loss/train': 1.0635849237442017} 08/31/2021 15:07:14 - INFO - __main__ - Step 142660: {'lr': 3.029129205702058e-06, 'samples': 27390720, 'steps': 142659, 'loss/train': 0.21377626061439514} 08/31/2021 15:07:15 - INFO - __main__ - Step 142661: {'lr': 3.02830566857662e-06, 'samples': 27390912, 'steps': 142660, 'loss/train': 0.164967879652977} 08/31/2021 15:07:16 - INFO - __main__ - Step 142662: {'lr': 3.027482242732804e-06, 'samples': 27391104, 'steps': 142661, 'loss/train': 1.1929845809936523} 08/31/2021 15:07:17 - INFO - __main__ - Step 142663: {'lr': 3.026658928170972e-06, 'samples': 27391296, 'steps': 142662, 'loss/train': 0.9047489762306213} 08/31/2021 15:07:17 - INFO - __main__ - Step 142664: {'lr': 3.02583572489154e-06, 'samples': 27391488, 'steps': 142663, 'loss/train': 1.2317086458206177} 08/31/2021 15:07:17 - INFO - __main__ - Step 142665: {'lr': 3.025012632894841e-06, 'samples': 27391680, 'steps': 142664, 'loss/train': 0.11301615834236145} 08/31/2021 15:07:18 - INFO - __main__ - Step 142666: {'lr': 3.0241896521812917e-06, 'samples': 27391872, 'steps': 142665, 'loss/train': 0.5918393731117249} 08/31/2021 15:07:19 - INFO - __main__ - Step 142667: {'lr': 3.0233667827512248e-06, 'samples': 27392064, 'steps': 142666, 'loss/train': 1.7065173387527466} 08/31/2021 15:07:20 - INFO - __main__ - Step 142668: {'lr': 3.022544024605001e-06, 'samples': 27392256, 'steps': 142667, 'loss/train': 1.863252878189087} 08/31/2021 15:07:20 - INFO - __main__ - Step 142669: {'lr': 3.0217213777430086e-06, 'samples': 27392448, 'steps': 142668, 'loss/train': 0.662661075592041} 08/31/2021 15:07:20 - INFO - __main__ - Step 142670: {'lr': 3.0208988421656093e-06, 'samples': 27392640, 'steps': 142669, 'loss/train': 1.2466423511505127} 08/31/2021 15:07:21 - INFO - __main__ - Step 142671: {'lr': 3.020076417873191e-06, 'samples': 27392832, 'steps': 142670, 'loss/train': 1.0675321817398071} 08/31/2021 15:07:22 - INFO - __main__ - Step 142672: {'lr': 3.019254104866115e-06, 'samples': 27393024, 'steps': 142671, 'loss/train': 1.113044023513794} 08/31/2021 15:07:23 - INFO - __main__ - Step 142673: {'lr': 3.0184319031447693e-06, 'samples': 27393216, 'steps': 142672, 'loss/train': 0.9753028750419617} 08/31/2021 15:07:23 - INFO - __main__ - Step 142674: {'lr': 3.0176098127094876e-06, 'samples': 27393408, 'steps': 142673, 'loss/train': 1.1141260862350464} 08/31/2021 15:07:23 - INFO - __main__ - Step 142675: {'lr': 3.016787833560658e-06, 'samples': 27393600, 'steps': 142674, 'loss/train': 1.1063392162322998} 08/31/2021 15:07:24 - INFO - __main__ - Step 142676: {'lr': 3.0159659656986693e-06, 'samples': 27393792, 'steps': 142675, 'loss/train': 1.2702052593231201} 08/31/2021 15:07:24 - INFO - __main__ - Step 142677: {'lr': 3.0151442091238548e-06, 'samples': 27393984, 'steps': 142676, 'loss/train': 1.2195358276367188} 08/31/2021 15:07:26 - INFO - __main__ - Step 142678: {'lr': 3.0143225638366025e-06, 'samples': 27394176, 'steps': 142677, 'loss/train': 0.7189428210258484} 08/31/2021 15:07:26 - INFO - __main__ - Step 142679: {'lr': 3.0135010298373012e-06, 'samples': 27394368, 'steps': 142678, 'loss/train': 0.7161270380020142} 08/31/2021 15:07:27 - INFO - __main__ - Step 142680: {'lr': 3.012679607126312e-06, 'samples': 27394560, 'steps': 142679, 'loss/train': 1.0892221927642822} 08/31/2021 15:07:27 - INFO - __main__ - Step 142681: {'lr': 3.0118582957039953e-06, 'samples': 27394752, 'steps': 142680, 'loss/train': 0.44760534167289734} 08/31/2021 15:07:27 - INFO - __main__ - Step 142682: {'lr': 3.011037095570712e-06, 'samples': 27394944, 'steps': 142681, 'loss/train': 0.014423848129808903} 08/31/2021 15:07:28 - INFO - __main__ - Step 142683: {'lr': 3.0102160067268515e-06, 'samples': 27395136, 'steps': 142682, 'loss/train': 0.4822647273540497} 08/31/2021 15:07:29 - INFO - __main__ - Step 142684: {'lr': 3.0093950291727736e-06, 'samples': 27395328, 'steps': 142683, 'loss/train': 0.8869467973709106} 08/31/2021 15:07:30 - INFO - __main__ - Step 142685: {'lr': 3.008574162908839e-06, 'samples': 27395520, 'steps': 142684, 'loss/train': 0.508783221244812} 08/31/2021 15:07:30 - INFO - __main__ - Step 142686: {'lr': 3.0077534079354372e-06, 'samples': 27395712, 'steps': 142685, 'loss/train': 1.0348964929580688} 08/31/2021 15:07:31 - INFO - __main__ - Step 142687: {'lr': 3.006932764252929e-06, 'samples': 27395904, 'steps': 142686, 'loss/train': 1.033965826034546} 08/31/2021 15:07:31 - INFO - __main__ - Step 142688: {'lr': 3.0061122318617018e-06, 'samples': 27396096, 'steps': 142687, 'loss/train': 0.9648315906524658} 08/31/2021 15:07:32 - INFO - __main__ - Step 142689: {'lr': 3.0052918107620895e-06, 'samples': 27396288, 'steps': 142688, 'loss/train': 1.3340106010437012} 08/31/2021 15:07:33 - INFO - __main__ - Step 142690: {'lr': 3.004471500954481e-06, 'samples': 27396480, 'steps': 142689, 'loss/train': 0.6856335997581482} 08/31/2021 15:07:33 - INFO - __main__ - Step 142691: {'lr': 3.0036513024392644e-06, 'samples': 27396672, 'steps': 142690, 'loss/train': 1.7899388074874878} 08/31/2021 15:07:33 - INFO - __main__ - Step 142692: {'lr': 3.0028312152167724e-06, 'samples': 27396864, 'steps': 142691, 'loss/train': 0.5828734040260315} 08/31/2021 15:07:34 - INFO - __main__ - Step 142693: {'lr': 3.002011239287422e-06, 'samples': 27397056, 'steps': 142692, 'loss/train': 0.9058591723442078} 08/31/2021 15:07:36 - INFO - __main__ - Step 142694: {'lr': 3.0011913746515462e-06, 'samples': 27397248, 'steps': 142693, 'loss/train': 1.3630220890045166} 08/31/2021 15:07:37 - INFO - __main__ - Step 142695: {'lr': 3.0003716213095054e-06, 'samples': 27397440, 'steps': 142694, 'loss/train': 1.1115891933441162} 08/31/2021 15:07:37 - INFO - __main__ - Step 142696: {'lr': 2.9995519792616887e-06, 'samples': 27397632, 'steps': 142695, 'loss/train': 0.48193463683128357} 08/31/2021 15:07:38 - INFO - __main__ - Step 142697: {'lr': 2.9987324485084567e-06, 'samples': 27397824, 'steps': 142696, 'loss/train': 0.6354557871818542} 08/31/2021 15:07:38 - INFO - __main__ - Step 142698: {'lr': 2.9979130290501976e-06, 'samples': 27398016, 'steps': 142697, 'loss/train': 0.7321183085441589} 08/31/2021 15:07:38 - INFO - __main__ - Step 142699: {'lr': 2.9970937208872727e-06, 'samples': 27398208, 'steps': 142698, 'loss/train': 1.09126615524292} 08/31/2021 15:07:40 - INFO - __main__ - Step 142700: {'lr': 2.9962745240200153e-06, 'samples': 27398400, 'steps': 142699, 'loss/train': 0.9229062795639038} 08/31/2021 15:07:40 - INFO - __main__ - Step 142701: {'lr': 2.995455438448841e-06, 'samples': 27398592, 'steps': 142700, 'loss/train': 0.5901551246643066} 08/31/2021 15:07:41 - INFO - __main__ - Step 142702: {'lr': 2.994636464174111e-06, 'samples': 27398784, 'steps': 142701, 'loss/train': 0.7643672823905945} 08/31/2021 15:07:41 - INFO - __main__ - Step 142703: {'lr': 2.9938176011961858e-06, 'samples': 27398976, 'steps': 142702, 'loss/train': 0.0220881886780262} 08/31/2021 15:07:41 - INFO - __main__ - Step 142704: {'lr': 2.992998849515427e-06, 'samples': 27399168, 'steps': 142703, 'loss/train': 0.8949490785598755} 08/31/2021 15:07:43 - INFO - __main__ - Step 142705: {'lr': 2.9921802091322227e-06, 'samples': 27399360, 'steps': 142704, 'loss/train': 0.8625321388244629} 08/31/2021 15:07:43 - INFO - __main__ - Step 142706: {'lr': 2.9913616800469055e-06, 'samples': 27399552, 'steps': 142705, 'loss/train': 1.3557313680648804} 08/31/2021 15:07:44 - INFO - __main__ - Step 142707: {'lr': 2.9905432622598926e-06, 'samples': 27399744, 'steps': 142706, 'loss/train': 0.831397533416748} 08/31/2021 15:07:44 - INFO - __main__ - Step 142708: {'lr': 2.9897249557715445e-06, 'samples': 27399936, 'steps': 142707, 'loss/train': 1.205366611480713} 08/31/2021 15:07:44 - INFO - __main__ - Step 142709: {'lr': 2.988906760582194e-06, 'samples': 27400128, 'steps': 142708, 'loss/train': 1.1805399656295776} 08/31/2021 15:07:46 - INFO - __main__ - Step 142710: {'lr': 2.98808867669223e-06, 'samples': 27400320, 'steps': 142709, 'loss/train': 0.8384592533111572} 08/31/2021 15:07:46 - INFO - __main__ - Step 142711: {'lr': 2.987270704102013e-06, 'samples': 27400512, 'steps': 142710, 'loss/train': 0.5244017839431763} 08/31/2021 15:07:47 - INFO - __main__ - Step 142712: {'lr': 2.986452842811932e-06, 'samples': 27400704, 'steps': 142711, 'loss/train': 1.1082401275634766} 08/31/2021 15:07:47 - INFO - __main__ - Step 142713: {'lr': 2.9856350928223475e-06, 'samples': 27400896, 'steps': 142712, 'loss/train': 1.012021780014038} 08/31/2021 15:07:48 - INFO - __main__ - Step 142714: {'lr': 2.9848174541336205e-06, 'samples': 27401088, 'steps': 142713, 'loss/train': 1.1712619066238403} 08/31/2021 15:07:49 - INFO - __main__ - Step 142715: {'lr': 2.9839999267461116e-06, 'samples': 27401280, 'steps': 142714, 'loss/train': 1.0009750127792358} 08/31/2021 15:07:49 - INFO - __main__ - Step 142716: {'lr': 2.9831825106602096e-06, 'samples': 27401472, 'steps': 142715, 'loss/train': 0.6074602007865906} 08/31/2021 15:07:50 - INFO - __main__ - Step 142717: {'lr': 2.982365205876275e-06, 'samples': 27401664, 'steps': 142716, 'loss/train': 1.3716167211532593} 08/31/2021 15:07:50 - INFO - __main__ - Step 142718: {'lr': 2.9815480123946693e-06, 'samples': 27401856, 'steps': 142717, 'loss/train': 0.6470297574996948} 08/31/2021 15:07:51 - INFO - __main__ - Step 142719: {'lr': 2.9807309302157802e-06, 'samples': 27402048, 'steps': 142718, 'loss/train': 1.1738481521606445} 08/31/2021 15:07:51 - INFO - __main__ - Step 142720: {'lr': 2.9799139593399414e-06, 'samples': 27402240, 'steps': 142719, 'loss/train': 1.714851975440979} 08/31/2021 15:07:52 - INFO - __main__ - Step 142721: {'lr': 2.979097099767569e-06, 'samples': 27402432, 'steps': 142720, 'loss/train': 0.1513957530260086} 08/31/2021 15:07:53 - INFO - __main__ - Step 142722: {'lr': 2.978280351498969e-06, 'samples': 27402624, 'steps': 142721, 'loss/train': 1.0207873582839966} 08/31/2021 15:07:53 - INFO - __main__ - Step 142723: {'lr': 2.977463714534584e-06, 'samples': 27402816, 'steps': 142722, 'loss/train': 1.032150387763977} 08/31/2021 15:07:53 - INFO - __main__ - Step 142724: {'lr': 2.9766471888747204e-06, 'samples': 27403008, 'steps': 142723, 'loss/train': 0.3848349452018738} 08/31/2021 15:07:54 - INFO - __main__ - Step 142725: {'lr': 2.9758307745197665e-06, 'samples': 27403200, 'steps': 142724, 'loss/train': 0.778667688369751} 08/31/2021 15:07:55 - INFO - __main__ - Step 142726: {'lr': 2.9750144714700834e-06, 'samples': 27403392, 'steps': 142725, 'loss/train': 0.08058379590511322} 08/31/2021 15:07:56 - INFO - __main__ - Step 142727: {'lr': 2.9741982797260593e-06, 'samples': 27403584, 'steps': 142726, 'loss/train': 0.7012301683425903} 08/31/2021 15:07:56 - INFO - __main__ - Step 142728: {'lr': 2.9733821992880273e-06, 'samples': 27403776, 'steps': 142727, 'loss/train': 0.18567688763141632} 08/31/2021 15:07:57 - INFO - __main__ - Step 142729: {'lr': 2.9725662301564036e-06, 'samples': 27403968, 'steps': 142728, 'loss/train': 0.7733358144760132} 08/31/2021 15:07:57 - INFO - __main__ - Step 142730: {'lr': 2.971750372331522e-06, 'samples': 27404160, 'steps': 142729, 'loss/train': 1.0877225399017334} 08/31/2021 15:07:57 - INFO - __main__ - Step 142731: {'lr': 2.9709346258137703e-06, 'samples': 27404352, 'steps': 142730, 'loss/train': 0.7183570861816406} 08/31/2021 15:07:59 - INFO - __main__ - Step 142732: {'lr': 2.970118990603482e-06, 'samples': 27404544, 'steps': 142731, 'loss/train': 1.6146247386932373} 08/31/2021 15:07:59 - INFO - __main__ - Step 142733: {'lr': 2.9693034667010453e-06, 'samples': 27404736, 'steps': 142732, 'loss/train': 0.7060798406600952} 08/31/2021 15:08:00 - INFO - __main__ - Step 142734: {'lr': 2.9684880541068495e-06, 'samples': 27404928, 'steps': 142733, 'loss/train': 0.5292254090309143} 08/31/2021 15:08:00 - INFO - __main__ - Step 142735: {'lr': 2.967672752821254e-06, 'samples': 27405120, 'steps': 142734, 'loss/train': 1.0645806789398193} 08/31/2021 15:08:00 - INFO - __main__ - Step 142736: {'lr': 2.966857562844566e-06, 'samples': 27405312, 'steps': 142735, 'loss/train': 2.1124632358551025} 08/31/2021 15:08:02 - INFO - __main__ - Step 142737: {'lr': 2.966042484177228e-06, 'samples': 27405504, 'steps': 142736, 'loss/train': 1.2605164051055908} 08/31/2021 15:08:02 - INFO - __main__ - Step 142738: {'lr': 2.965227516819574e-06, 'samples': 27405696, 'steps': 142737, 'loss/train': 0.8451231718063354} 08/31/2021 15:08:03 - INFO - __main__ - Step 142739: {'lr': 2.9644126607719923e-06, 'samples': 27405888, 'steps': 142738, 'loss/train': 1.0852729082107544} 08/31/2021 15:08:03 - INFO - __main__ - Step 142740: {'lr': 2.963597916034816e-06, 'samples': 27406080, 'steps': 142739, 'loss/train': 0.3191607594490051} 08/31/2021 15:08:03 - INFO - __main__ - Step 142741: {'lr': 2.9627832826084335e-06, 'samples': 27406272, 'steps': 142740, 'loss/train': 1.0108749866485596} 08/31/2021 15:08:05 - INFO - __main__ - Step 142742: {'lr': 2.9619687604932056e-06, 'samples': 27406464, 'steps': 142741, 'loss/train': 1.381377100944519} 08/31/2021 15:08:06 - INFO - __main__ - Step 142743: {'lr': 2.9611543496894933e-06, 'samples': 27406656, 'steps': 142742, 'loss/train': 0.4053606688976288} 08/31/2021 15:08:06 - INFO - __main__ - Step 142744: {'lr': 2.9603400501976853e-06, 'samples': 27406848, 'steps': 142743, 'loss/train': 0.9705228805541992} 08/31/2021 15:08:06 - INFO - __main__ - Step 142745: {'lr': 2.959525862018142e-06, 'samples': 27407040, 'steps': 142744, 'loss/train': 0.01570429839193821} 08/31/2021 15:08:07 - INFO - __main__ - Step 142746: {'lr': 2.9587117851512246e-06, 'samples': 27407232, 'steps': 142745, 'loss/train': 1.3606616258621216} 08/31/2021 15:08:07 - INFO - __main__ - Step 142747: {'lr': 2.9578978195972937e-06, 'samples': 27407424, 'steps': 142746, 'loss/train': 1.6678141355514526} 08/31/2021 15:08:09 - INFO - __main__ - Step 142748: {'lr': 2.9570839653567383e-06, 'samples': 27407616, 'steps': 142747, 'loss/train': 0.11131734400987625} 08/31/2021 15:08:09 - INFO - __main__ - Step 142749: {'lr': 2.956270222429891e-06, 'samples': 27407808, 'steps': 142748, 'loss/train': 0.9471508860588074} 08/31/2021 15:08:10 - INFO - __main__ - Step 142750: {'lr': 2.9554565908171405e-06, 'samples': 27408000, 'steps': 142749, 'loss/train': 1.2752407789230347} 08/31/2021 15:08:10 - INFO - __main__ - Step 142751: {'lr': 2.9546430705188477e-06, 'samples': 27408192, 'steps': 142750, 'loss/train': 0.19878460466861725} 08/31/2021 15:08:10 - INFO - __main__ - Step 142752: {'lr': 2.9538296615353734e-06, 'samples': 27408384, 'steps': 142751, 'loss/train': 0.7844179272651672} 08/31/2021 15:08:11 - INFO - __main__ - Step 142753: {'lr': 2.953016363867078e-06, 'samples': 27408576, 'steps': 142752, 'loss/train': 1.741661548614502} 08/31/2021 15:08:13 - INFO - __main__ - Step 142754: {'lr': 2.952203177514379e-06, 'samples': 27408768, 'steps': 142753, 'loss/train': 0.6466696262359619} 08/31/2021 15:08:13 - INFO - __main__ - Step 142755: {'lr': 2.95139010247758e-06, 'samples': 27408960, 'steps': 142754, 'loss/train': 1.6465028524398804} 08/31/2021 15:08:13 - INFO - __main__ - Step 142756: {'lr': 2.9505771387570713e-06, 'samples': 27409152, 'steps': 142755, 'loss/train': 0.7374575734138489} 08/31/2021 15:08:14 - INFO - __main__ - Step 142757: {'lr': 2.9497642863532402e-06, 'samples': 27409344, 'steps': 142756, 'loss/train': 2.061509370803833} 08/31/2021 15:08:14 - INFO - __main__ - Step 142758: {'lr': 2.9489515452664206e-06, 'samples': 27409536, 'steps': 142757, 'loss/train': 1.1140024662017822} 08/31/2021 15:08:17 - INFO - __main__ - Step 142759: {'lr': 2.948138915496973e-06, 'samples': 27409728, 'steps': 142758, 'loss/train': 1.5693938732147217} 08/31/2021 15:08:17 - INFO - __main__ - Step 142760: {'lr': 2.9473263970453134e-06, 'samples': 27409920, 'steps': 142759, 'loss/train': 1.2573356628417969} 08/31/2021 15:08:18 - INFO - __main__ - Step 142761: {'lr': 2.9465139899117754e-06, 'samples': 27410112, 'steps': 142760, 'loss/train': 0.3328073024749756} 08/31/2021 15:08:18 - INFO - __main__ - Step 142762: {'lr': 2.9457016940967198e-06, 'samples': 27410304, 'steps': 142761, 'loss/train': 0.8442925214767456} 08/31/2021 15:08:18 - INFO - __main__ - Step 142763: {'lr': 2.944889509600507e-06, 'samples': 27410496, 'steps': 142762, 'loss/train': 1.089276671409607} 08/31/2021 15:08:19 - INFO - __main__ - Step 142764: {'lr': 2.9440774364235256e-06, 'samples': 27410688, 'steps': 142763, 'loss/train': 2.7426981925964355} 08/31/2021 15:08:19 - INFO - __main__ - Step 142765: {'lr': 2.943265474566109e-06, 'samples': 27410880, 'steps': 142764, 'loss/train': 2.6014533042907715} 08/31/2021 15:08:19 - INFO - __main__ - Step 142766: {'lr': 2.942453624028674e-06, 'samples': 27411072, 'steps': 142765, 'loss/train': 2.646996259689331} 08/31/2021 15:08:21 - INFO - __main__ - Step 142767: {'lr': 2.9416418848115243e-06, 'samples': 27411264, 'steps': 142766, 'loss/train': 2.724843978881836} 08/31/2021 15:08:22 - INFO - __main__ - Step 142768: {'lr': 2.940830256915078e-06, 'samples': 27411456, 'steps': 142767, 'loss/train': 1.1140477657318115} 08/31/2021 15:08:22 - INFO - __main__ - Step 142769: {'lr': 2.940018740339695e-06, 'samples': 27411648, 'steps': 142768, 'loss/train': 0.6814544200897217} 08/31/2021 15:08:22 - INFO - __main__ - Step 142770: {'lr': 2.9392073350857085e-06, 'samples': 27411840, 'steps': 142769, 'loss/train': 1.583571195602417} 08/31/2021 15:08:23 - INFO - __main__ - Step 142771: {'lr': 2.938396041153507e-06, 'samples': 27412032, 'steps': 142770, 'loss/train': 0.9604199528694153} 08/31/2021 15:08:25 - INFO - __main__ - Step 142772: {'lr': 2.9375848585434516e-06, 'samples': 27412224, 'steps': 142771, 'loss/train': 0.9511529207229614} 08/31/2021 15:08:25 - INFO - __main__ - Step 142773: {'lr': 2.936773787255903e-06, 'samples': 27412416, 'steps': 142772, 'loss/train': 1.0387063026428223} 08/31/2021 15:08:25 - INFO - __main__ - Step 142774: {'lr': 2.9359628272912496e-06, 'samples': 27412608, 'steps': 142773, 'loss/train': 0.9263020157814026} 08/31/2021 15:08:26 - INFO - __main__ - Step 142775: {'lr': 2.935151978649825e-06, 'samples': 27412800, 'steps': 142774, 'loss/train': 0.7748773694038391} 08/31/2021 15:08:26 - INFO - __main__ - Step 142776: {'lr': 2.934341241332017e-06, 'samples': 27412992, 'steps': 142775, 'loss/train': 1.1229121685028076} 08/31/2021 15:08:26 - INFO - __main__ - Step 142777: {'lr': 2.933530615338187e-06, 'samples': 27413184, 'steps': 142776, 'loss/train': 0.8225696086883545} 08/31/2021 15:08:28 - INFO - __main__ - Step 142778: {'lr': 2.9327201006686677e-06, 'samples': 27413376, 'steps': 142777, 'loss/train': 0.30707699060440063} 08/31/2021 15:08:28 - INFO - __main__ - Step 142779: {'lr': 2.9319096973238755e-06, 'samples': 27413568, 'steps': 142778, 'loss/train': 0.7086403965950012} 08/31/2021 15:08:29 - INFO - __main__ - Step 142780: {'lr': 2.931099405304144e-06, 'samples': 27413760, 'steps': 142779, 'loss/train': 0.6255918741226196} 08/31/2021 15:08:29 - INFO - __main__ - Step 142781: {'lr': 2.930289224609861e-06, 'samples': 27413952, 'steps': 142780, 'loss/train': 0.7962057590484619} 08/31/2021 15:08:29 - INFO - __main__ - Step 142782: {'lr': 2.9294791552413603e-06, 'samples': 27414144, 'steps': 142781, 'loss/train': 0.8575882911682129} 08/31/2021 15:08:31 - INFO - __main__ - Step 142783: {'lr': 2.92866919719903e-06, 'samples': 27414336, 'steps': 142782, 'loss/train': 0.32201534509658813} 08/31/2021 15:08:31 - INFO - __main__ - Step 142784: {'lr': 2.9278593504832307e-06, 'samples': 27414528, 'steps': 142783, 'loss/train': 1.0679240226745605} 08/31/2021 15:08:32 - INFO - __main__ - Step 142785: {'lr': 2.927049615094296e-06, 'samples': 27414720, 'steps': 142784, 'loss/train': 0.35089802742004395} 08/31/2021 15:08:32 - INFO - __main__ - Step 142786: {'lr': 2.92623999103267e-06, 'samples': 27414912, 'steps': 142785, 'loss/train': 1.080353021621704} 08/31/2021 15:08:32 - INFO - __main__ - Step 142787: {'lr': 2.9254304782986297e-06, 'samples': 27415104, 'steps': 142786, 'loss/train': 1.1022975444793701} 08/31/2021 15:08:34 - INFO - __main__ - Step 142788: {'lr': 2.9246210768926196e-06, 'samples': 27415296, 'steps': 142787, 'loss/train': 0.706607460975647} 08/31/2021 15:08:34 - INFO - __main__ - Step 142789: {'lr': 2.9238117868149173e-06, 'samples': 27415488, 'steps': 142788, 'loss/train': 1.093587040901184} 08/31/2021 15:08:35 - INFO - __main__ - Step 142790: {'lr': 2.9230026080659664e-06, 'samples': 27415680, 'steps': 142789, 'loss/train': 1.742302417755127} 08/31/2021 15:08:35 - INFO - __main__ - Step 142791: {'lr': 2.922193540646073e-06, 'samples': 27415872, 'steps': 142790, 'loss/train': 1.176785945892334} 08/31/2021 15:08:35 - INFO - __main__ - Step 142792: {'lr': 2.9213845845556253e-06, 'samples': 27416064, 'steps': 142791, 'loss/train': 1.1766932010650635} 08/31/2021 15:08:36 - INFO - __main__ - Step 142793: {'lr': 2.920575739795012e-06, 'samples': 27416256, 'steps': 142792, 'loss/train': 0.651750922203064} 08/31/2021 15:08:38 - INFO - __main__ - Step 142794: {'lr': 2.9197670063645655e-06, 'samples': 27416448, 'steps': 142793, 'loss/train': 0.919739305973053} 08/31/2021 15:08:39 - INFO - __main__ - Step 142795: {'lr': 2.918958384264647e-06, 'samples': 27416640, 'steps': 142794, 'loss/train': 1.064317226409912} 08/31/2021 15:08:39 - INFO - __main__ - Step 142796: {'lr': 2.9181498734956456e-06, 'samples': 27416832, 'steps': 142795, 'loss/train': 0.8655226826667786} 08/31/2021 15:08:39 - INFO - __main__ - Step 142797: {'lr': 2.917341474057894e-06, 'samples': 27417024, 'steps': 142796, 'loss/train': 0.8912912607192993} 08/31/2021 15:08:40 - INFO - __main__ - Step 142798: {'lr': 2.916533185951781e-06, 'samples': 27417216, 'steps': 142797, 'loss/train': 0.7575246691703796} 08/31/2021 15:08:40 - INFO - __main__ - Step 142799: {'lr': 2.9157250091776942e-06, 'samples': 27417408, 'steps': 142798, 'loss/train': 0.22145231068134308} 08/31/2021 15:08:40 - INFO - __main__ - Step 142800: {'lr': 2.9149169437359403e-06, 'samples': 27417600, 'steps': 142799, 'loss/train': 0.2235521674156189} 08/31/2021 15:08:42 - INFO - __main__ - Step 142801: {'lr': 2.9141089896269345e-06, 'samples': 27417792, 'steps': 142800, 'loss/train': 1.052187204360962} 08/31/2021 15:08:42 - INFO - __main__ - Step 142802: {'lr': 2.913301146851011e-06, 'samples': 27417984, 'steps': 142801, 'loss/train': 0.7498342990875244} 08/31/2021 15:08:43 - INFO - __main__ - Step 142803: {'lr': 2.912493415408529e-06, 'samples': 27418176, 'steps': 142802, 'loss/train': 1.4848315715789795} 08/31/2021 15:08:43 - INFO - __main__ - Step 142804: {'lr': 2.9116857952998787e-06, 'samples': 27418368, 'steps': 142803, 'loss/train': 0.8652680516242981} 08/31/2021 15:08:44 - INFO - __main__ - Step 142805: {'lr': 2.9108782865253923e-06, 'samples': 27418560, 'steps': 142804, 'loss/train': 1.3091998100280762} 08/31/2021 15:08:45 - INFO - __main__ - Step 142806: {'lr': 2.910070889085459e-06, 'samples': 27418752, 'steps': 142805, 'loss/train': 0.4284785985946655} 08/31/2021 15:08:45 - INFO - __main__ - Step 142807: {'lr': 2.9092636029804387e-06, 'samples': 27418944, 'steps': 142806, 'loss/train': 0.9791443943977356} 08/31/2021 15:08:46 - INFO - __main__ - Step 142808: {'lr': 2.9084564282106928e-06, 'samples': 27419136, 'steps': 142807, 'loss/train': 0.048730894923210144} 08/31/2021 15:08:46 - INFO - __main__ - Step 142809: {'lr': 2.907649364776582e-06, 'samples': 27419328, 'steps': 142808, 'loss/train': 1.486319899559021} 08/31/2021 15:08:46 - INFO - __main__ - Step 142810: {'lr': 2.9068424126784674e-06, 'samples': 27419520, 'steps': 142809, 'loss/train': 1.1633903980255127} 08/31/2021 15:08:49 - INFO - __main__ - Step 142811: {'lr': 2.9060355719167376e-06, 'samples': 27419712, 'steps': 142810, 'loss/train': 1.3849942684173584} 08/31/2021 15:08:49 - INFO - __main__ - Step 142812: {'lr': 2.905228842491697e-06, 'samples': 27419904, 'steps': 142811, 'loss/train': 1.016023874282837} 08/31/2021 15:08:49 - INFO - __main__ - Step 142813: {'lr': 2.904422224403763e-06, 'samples': 27420096, 'steps': 142812, 'loss/train': 1.1836366653442383} 08/31/2021 15:08:50 - INFO - __main__ - Step 142814: {'lr': 2.9036157176532964e-06, 'samples': 27420288, 'steps': 142813, 'loss/train': 0.5628450512886047} 08/31/2021 15:08:50 - INFO - __main__ - Step 142815: {'lr': 2.902809322240657e-06, 'samples': 27420480, 'steps': 142814, 'loss/train': 0.6434985399246216} 08/31/2021 15:08:51 - INFO - __main__ - Step 142816: {'lr': 2.9020030381661787e-06, 'samples': 27420672, 'steps': 142815, 'loss/train': 0.39605480432510376} 08/31/2021 15:08:52 - INFO - __main__ - Step 142817: {'lr': 2.90119686543025e-06, 'samples': 27420864, 'steps': 142816, 'loss/train': 1.2142091989517212} 08/31/2021 15:08:52 - INFO - __main__ - Step 142818: {'lr': 2.9003908040332315e-06, 'samples': 27421056, 'steps': 142817, 'loss/train': 0.95583176612854} 08/31/2021 15:08:53 - INFO - __main__ - Step 142819: {'lr': 2.8995848539754844e-06, 'samples': 27421248, 'steps': 142818, 'loss/train': 0.9329709410667419} 08/31/2021 15:08:53 - INFO - __main__ - Step 142820: {'lr': 2.898779015257341e-06, 'samples': 27421440, 'steps': 142819, 'loss/train': 0.9255535006523132} 08/31/2021 15:08:55 - INFO - __main__ - Step 142821: {'lr': 2.8979732878792463e-06, 'samples': 27421632, 'steps': 142820, 'loss/train': 2.2962732315063477} 08/31/2021 15:08:55 - INFO - __main__ - Step 142822: {'lr': 2.8971676718414774e-06, 'samples': 27421824, 'steps': 142821, 'loss/train': 0.8791472911834717} 08/31/2021 15:08:56 - INFO - __main__ - Step 142823: {'lr': 2.896362167144423e-06, 'samples': 27422016, 'steps': 142822, 'loss/train': 1.316982388496399} 08/31/2021 15:08:56 - INFO - __main__ - Step 142824: {'lr': 2.8955567737884713e-06, 'samples': 27422208, 'steps': 142823, 'loss/train': 0.9791011214256287} 08/31/2021 15:08:56 - INFO - __main__ - Step 142825: {'lr': 2.8947514917739837e-06, 'samples': 27422400, 'steps': 142824, 'loss/train': 0.8978142738342285} 08/31/2021 15:08:57 - INFO - __main__ - Step 142826: {'lr': 2.893946321101293e-06, 'samples': 27422592, 'steps': 142825, 'loss/train': 0.8913540840148926} 08/31/2021 15:08:59 - INFO - __main__ - Step 142827: {'lr': 2.8931412617707597e-06, 'samples': 27422784, 'steps': 142826, 'loss/train': 0.9529169797897339} 08/31/2021 15:08:59 - INFO - __main__ - Step 142828: {'lr': 2.892336313782801e-06, 'samples': 27422976, 'steps': 142827, 'loss/train': 1.2759997844696045} 08/31/2021 15:08:59 - INFO - __main__ - Step 142829: {'lr': 2.891531477137721e-06, 'samples': 27423168, 'steps': 142828, 'loss/train': 0.665288507938385} 08/31/2021 15:09:00 - INFO - __main__ - Step 142830: {'lr': 2.890726751835909e-06, 'samples': 27423360, 'steps': 142829, 'loss/train': 1.248808741569519} 08/31/2021 15:09:00 - INFO - __main__ - Step 142831: {'lr': 2.8899221378777262e-06, 'samples': 27423552, 'steps': 142830, 'loss/train': 1.1046351194381714} 08/31/2021 15:09:02 - INFO - __main__ - Step 142832: {'lr': 2.8891176352635053e-06, 'samples': 27423744, 'steps': 142831, 'loss/train': 1.349936604499817} 08/31/2021 15:09:02 - INFO - __main__ - Step 142833: {'lr': 2.888313243993662e-06, 'samples': 27423936, 'steps': 142832, 'loss/train': 1.1245529651641846} 08/31/2021 15:09:03 - INFO - __main__ - Step 142834: {'lr': 2.8875089640685303e-06, 'samples': 27424128, 'steps': 142833, 'loss/train': 1.140756607055664} 08/31/2021 15:09:03 - INFO - __main__ - Step 142835: {'lr': 2.8867047954884707e-06, 'samples': 27424320, 'steps': 142834, 'loss/train': 0.5437763333320618} 08/31/2021 15:09:03 - INFO - __main__ - Step 142836: {'lr': 2.8859007382538436e-06, 'samples': 27424512, 'steps': 142835, 'loss/train': 1.0402493476867676} 08/31/2021 15:09:05 - INFO - __main__ - Step 142837: {'lr': 2.8850967923650106e-06, 'samples': 27424704, 'steps': 142836, 'loss/train': 1.269801378250122} 08/31/2021 15:09:05 - INFO - __main__ - Step 142838: {'lr': 2.884292957822332e-06, 'samples': 27424896, 'steps': 142837, 'loss/train': 0.691527783870697} 08/31/2021 15:09:05 - INFO - __main__ - Step 142839: {'lr': 2.8834892346261963e-06, 'samples': 27425088, 'steps': 142838, 'loss/train': 2.025477409362793} 08/31/2021 15:09:06 - INFO - __main__ - Step 142840: {'lr': 2.8826856227769648e-06, 'samples': 27425280, 'steps': 142839, 'loss/train': 0.7807239294052124} 08/31/2021 15:09:06 - INFO - __main__ - Step 142841: {'lr': 2.8818821222749427e-06, 'samples': 27425472, 'steps': 142840, 'loss/train': 0.4594504237174988} 08/31/2021 15:09:08 - INFO - __main__ - Step 142842: {'lr': 2.8810787331205735e-06, 'samples': 27425664, 'steps': 142841, 'loss/train': 0.9817196726799011} 08/31/2021 15:09:08 - INFO - __main__ - Step 142843: {'lr': 2.880275455314135e-06, 'samples': 27425856, 'steps': 142842, 'loss/train': 1.716488003730774} 08/31/2021 15:09:09 - INFO - __main__ - Step 142844: {'lr': 2.879472288856072e-06, 'samples': 27426048, 'steps': 142843, 'loss/train': 0.3454185724258423} 08/31/2021 15:09:09 - INFO - __main__ - Step 142845: {'lr': 2.8786692337466614e-06, 'samples': 27426240, 'steps': 142844, 'loss/train': 1.8714889287948608} 08/31/2021 15:09:09 - INFO - __main__ - Step 142846: {'lr': 2.8778662899863474e-06, 'samples': 27426432, 'steps': 142845, 'loss/train': 0.7011143565177917} 08/31/2021 15:09:11 - INFO - __main__ - Step 142847: {'lr': 2.877063457575435e-06, 'samples': 27426624, 'steps': 142846, 'loss/train': 0.9778382778167725} 08/31/2021 15:09:11 - INFO - __main__ - Step 142848: {'lr': 2.8762607365142856e-06, 'samples': 27426816, 'steps': 142847, 'loss/train': 0.9171531200408936} 08/31/2021 15:09:12 - INFO - __main__ - Step 142849: {'lr': 2.8754581268033152e-06, 'samples': 27427008, 'steps': 142848, 'loss/train': 0.5177428126335144} 08/31/2021 15:09:12 - INFO - __main__ - Step 142850: {'lr': 2.8746556284428294e-06, 'samples': 27427200, 'steps': 142849, 'loss/train': 1.0442931652069092} 08/31/2021 15:09:12 - INFO - __main__ - Step 142851: {'lr': 2.8738532414332165e-06, 'samples': 27427392, 'steps': 142850, 'loss/train': 0.7301311492919922} 08/31/2021 15:09:14 - INFO - __main__ - Step 142852: {'lr': 2.8730509657748373e-06, 'samples': 27427584, 'steps': 142851, 'loss/train': 1.006319284439087} 08/31/2021 15:09:14 - INFO - __main__ - Step 142853: {'lr': 2.8722488014680248e-06, 'samples': 27427776, 'steps': 142852, 'loss/train': 0.8335249423980713} 08/31/2021 15:09:15 - INFO - __main__ - Step 142854: {'lr': 2.8714467485131956e-06, 'samples': 27427968, 'steps': 142853, 'loss/train': 1.2346218824386597} 08/31/2021 15:09:15 - INFO - __main__ - Step 142855: {'lr': 2.870644806910655e-06, 'samples': 27428160, 'steps': 142854, 'loss/train': 0.4958459138870239} 08/31/2021 15:09:15 - INFO - __main__ - Step 142856: {'lr': 2.869842976660819e-06, 'samples': 27428352, 'steps': 142855, 'loss/train': 1.5961833000183105} 08/31/2021 15:09:16 - INFO - __main__ - Step 142857: {'lr': 2.8690412577639937e-06, 'samples': 27428544, 'steps': 142856, 'loss/train': 0.6796299815177917} 08/31/2021 15:09:17 - INFO - __main__ - Step 142858: {'lr': 2.8682396502205665e-06, 'samples': 27428736, 'steps': 142857, 'loss/train': 0.7470130324363708} 08/31/2021 15:09:18 - INFO - __main__ - Step 142859: {'lr': 2.8674381540308993e-06, 'samples': 27428928, 'steps': 142858, 'loss/train': 0.6577277779579163} 08/31/2021 15:09:18 - INFO - __main__ - Step 142860: {'lr': 2.866636769195352e-06, 'samples': 27429120, 'steps': 142859, 'loss/train': 0.6270073056221008} 08/31/2021 15:09:18 - INFO - __main__ - Step 142861: {'lr': 2.8658354957142587e-06, 'samples': 27429312, 'steps': 142860, 'loss/train': 0.4276217818260193} 08/31/2021 15:09:19 - INFO - __main__ - Step 142862: {'lr': 2.865034333588035e-06, 'samples': 27429504, 'steps': 142861, 'loss/train': 2.1122636795043945} 08/31/2021 15:09:20 - INFO - __main__ - Step 142863: {'lr': 2.8642332828170135e-06, 'samples': 27429696, 'steps': 142862, 'loss/train': 0.9744994640350342} 08/31/2021 15:09:21 - INFO - __main__ - Step 142864: {'lr': 2.8634323434015564e-06, 'samples': 27429888, 'steps': 142863, 'loss/train': 1.0206615924835205} 08/31/2021 15:09:21 - INFO - __main__ - Step 142865: {'lr': 2.8626315153420234e-06, 'samples': 27430080, 'steps': 142864, 'loss/train': 0.9665061831474304} 08/31/2021 15:09:21 - INFO - __main__ - Step 142866: {'lr': 2.8618307986387484e-06, 'samples': 27430272, 'steps': 142865, 'loss/train': 1.2258294820785522} 08/31/2021 15:09:22 - INFO - __main__ - Step 142867: {'lr': 2.8610301932921467e-06, 'samples': 27430464, 'steps': 142866, 'loss/train': 0.9433009028434753} 08/31/2021 15:09:24 - INFO - __main__ - Step 142868: {'lr': 2.860229699302552e-06, 'samples': 27430656, 'steps': 142867, 'loss/train': 1.2268285751342773} 08/31/2021 15:09:24 - INFO - __main__ - Step 142869: {'lr': 2.8594293166703255e-06, 'samples': 27430848, 'steps': 142868, 'loss/train': 1.4887884855270386} 08/31/2021 15:09:25 - INFO - __main__ - Step 142870: {'lr': 2.8586290453957997e-06, 'samples': 27431040, 'steps': 142869, 'loss/train': 0.9833644032478333} 08/31/2021 15:09:25 - INFO - __main__ - Step 142871: {'lr': 2.857828885479391e-06, 'samples': 27431232, 'steps': 142870, 'loss/train': 0.9249805212020874} 08/31/2021 15:09:25 - INFO - __main__ - Step 142872: {'lr': 2.857028836921405e-06, 'samples': 27431424, 'steps': 142871, 'loss/train': 0.687981128692627} 08/31/2021 15:09:27 - INFO - __main__ - Step 142873: {'lr': 2.8562288997222576e-06, 'samples': 27431616, 'steps': 142872, 'loss/train': 0.9489179849624634} 08/31/2021 15:09:27 - INFO - __main__ - Step 142874: {'lr': 2.855429073882254e-06, 'samples': 27431808, 'steps': 142873, 'loss/train': 0.6500645279884338} 08/31/2021 15:09:28 - INFO - __main__ - Step 142875: {'lr': 2.8546293594017838e-06, 'samples': 27432000, 'steps': 142874, 'loss/train': 1.2246620655059814} 08/31/2021 15:09:28 - INFO - __main__ - Step 142876: {'lr': 2.8538297562812345e-06, 'samples': 27432192, 'steps': 142875, 'loss/train': 1.1356641054153442} 08/31/2021 15:09:28 - INFO - __main__ - Step 142877: {'lr': 2.853030264520912e-06, 'samples': 27432384, 'steps': 142876, 'loss/train': 1.047011375427246} 08/31/2021 15:09:30 - INFO - __main__ - Step 142878: {'lr': 2.8522308841211763e-06, 'samples': 27432576, 'steps': 142877, 'loss/train': 1.0477116107940674} 08/31/2021 15:09:30 - INFO - __main__ - Step 142879: {'lr': 2.851431615082445e-06, 'samples': 27432768, 'steps': 142878, 'loss/train': 0.9812164306640625} 08/31/2021 15:09:31 - INFO - __main__ - Step 142880: {'lr': 2.85063245740505e-06, 'samples': 27432960, 'steps': 142879, 'loss/train': 1.583359718322754} 08/31/2021 15:09:31 - INFO - __main__ - Step 142881: {'lr': 2.8498334110893255e-06, 'samples': 27433152, 'steps': 142880, 'loss/train': 0.7350178360939026} 08/31/2021 15:09:31 - INFO - __main__ - Step 142882: {'lr': 2.849034476135659e-06, 'samples': 27433344, 'steps': 142881, 'loss/train': 0.646099865436554} 08/31/2021 15:09:33 - INFO - __main__ - Step 142883: {'lr': 2.848235652544412e-06, 'samples': 27433536, 'steps': 142882, 'loss/train': 0.984942615032196} 08/31/2021 15:09:34 - INFO - __main__ - Step 142884: {'lr': 2.8474369403159172e-06, 'samples': 27433728, 'steps': 142883, 'loss/train': 0.4913431406021118} 08/31/2021 15:09:34 - INFO - __main__ - Step 142885: {'lr': 2.8466383394505633e-06, 'samples': 27433920, 'steps': 142884, 'loss/train': 1.1053640842437744} 08/31/2021 15:09:34 - INFO - __main__ - Step 142886: {'lr': 2.8458398499487116e-06, 'samples': 27434112, 'steps': 142885, 'loss/train': 1.614409327507019} 08/31/2021 15:09:35 - INFO - __main__ - Step 142887: {'lr': 2.8450414718106944e-06, 'samples': 27434304, 'steps': 142886, 'loss/train': 0.6954349875450134} 08/31/2021 15:09:35 - INFO - __main__ - Step 142888: {'lr': 2.8442432050369003e-06, 'samples': 27434496, 'steps': 142887, 'loss/train': 0.8754136562347412} 08/31/2021 15:09:37 - INFO - __main__ - Step 142889: {'lr': 2.8434450496276633e-06, 'samples': 27434688, 'steps': 142888, 'loss/train': 0.17151445150375366} 08/31/2021 15:09:37 - INFO - __main__ - Step 142890: {'lr': 2.842647005583371e-06, 'samples': 27434880, 'steps': 142889, 'loss/train': 0.8571166396141052} 08/31/2021 15:09:38 - INFO - __main__ - Step 142891: {'lr': 2.8418490729043565e-06, 'samples': 27435072, 'steps': 142890, 'loss/train': 1.4336788654327393} 08/31/2021 15:09:38 - INFO - __main__ - Step 142892: {'lr': 2.8410512515910093e-06, 'samples': 27435264, 'steps': 142891, 'loss/train': 0.7397403717041016} 08/31/2021 15:09:38 - INFO - __main__ - Step 142893: {'lr': 2.8402535416436613e-06, 'samples': 27435456, 'steps': 142892, 'loss/train': 0.6671050190925598} 08/31/2021 15:09:40 - INFO - __main__ - Step 142894: {'lr': 2.839455943062674e-06, 'samples': 27435648, 'steps': 142893, 'loss/train': 1.341416358947754} 08/31/2021 15:09:41 - INFO - __main__ - Step 142895: {'lr': 2.8386584558484087e-06, 'samples': 27435840, 'steps': 142894, 'loss/train': 1.1341825723648071} 08/31/2021 15:09:41 - INFO - __main__ - Step 142896: {'lr': 2.837861080001225e-06, 'samples': 27436032, 'steps': 142895, 'loss/train': 0.5684444308280945} 08/31/2021 15:09:41 - INFO - __main__ - Step 142897: {'lr': 2.8370638155215123e-06, 'samples': 27436224, 'steps': 142896, 'loss/train': 1.4941657781600952} 08/31/2021 15:09:42 - INFO - __main__ - Step 142898: {'lr': 2.836266662409576e-06, 'samples': 27436416, 'steps': 142897, 'loss/train': 0.7414981126785278} 08/31/2021 15:09:43 - INFO - __main__ - Step 142899: {'lr': 2.8354696206658315e-06, 'samples': 27436608, 'steps': 142898, 'loss/train': 0.9155738949775696} 08/31/2021 15:09:44 - INFO - __main__ - Step 142900: {'lr': 2.8346726902905852e-06, 'samples': 27436800, 'steps': 142899, 'loss/train': 0.9811596274375916} 08/31/2021 15:09:44 - INFO - __main__ - Step 142901: {'lr': 2.8338758712842527e-06, 'samples': 27436992, 'steps': 142900, 'loss/train': 0.8308423161506653} 08/31/2021 15:09:44 - INFO - __main__ - Step 142902: {'lr': 2.83307916364714e-06, 'samples': 27437184, 'steps': 142901, 'loss/train': 0.844718873500824} 08/31/2021 15:09:45 - INFO - __main__ - Step 142903: {'lr': 2.832282567379635e-06, 'samples': 27437376, 'steps': 142902, 'loss/train': 1.4544119834899902} 08/31/2021 15:09:45 - INFO - __main__ - Step 142904: {'lr': 2.831486082482071e-06, 'samples': 27437568, 'steps': 142903, 'loss/train': 1.0720479488372803} 08/31/2021 15:09:47 - INFO - __main__ - Step 142905: {'lr': 2.8306897089548367e-06, 'samples': 27437760, 'steps': 142904, 'loss/train': 1.701833724975586} 08/31/2021 15:09:47 - INFO - __main__ - Step 142906: {'lr': 2.829893446798293e-06, 'samples': 27437952, 'steps': 142905, 'loss/train': 0.7828990817070007} 08/31/2021 15:09:47 - INFO - __main__ - Step 142907: {'lr': 2.8290972960127725e-06, 'samples': 27438144, 'steps': 142906, 'loss/train': 0.6001361012458801} 08/31/2021 15:09:48 - INFO - __main__ - Step 142908: {'lr': 2.8283012565986367e-06, 'samples': 27438336, 'steps': 142907, 'loss/train': 0.9960376024246216} 08/31/2021 15:09:48 - INFO - __main__ - Step 142909: {'lr': 2.8275053285562735e-06, 'samples': 27438528, 'steps': 142908, 'loss/train': 1.3295732736587524} 08/31/2021 15:09:50 - INFO - __main__ - Step 142910: {'lr': 2.8267095118860166e-06, 'samples': 27438720, 'steps': 142909, 'loss/train': 0.7195670008659363} 08/31/2021 15:09:50 - INFO - __main__ - Step 142911: {'lr': 2.825913806588226e-06, 'samples': 27438912, 'steps': 142910, 'loss/train': 0.559389054775238} 08/31/2021 15:09:50 - INFO - __main__ - Step 142912: {'lr': 2.8251182126632914e-06, 'samples': 27439104, 'steps': 142911, 'loss/train': 1.016733169555664} 08/31/2021 15:09:51 - INFO - __main__ - Step 142913: {'lr': 2.8243227301115173e-06, 'samples': 27439296, 'steps': 142912, 'loss/train': 1.4761983156204224} 08/31/2021 15:09:51 - INFO - __main__ - Step 142914: {'lr': 2.8235273589332923e-06, 'samples': 27439488, 'steps': 142913, 'loss/train': 0.8819483518600464} 08/31/2021 15:09:53 - INFO - __main__ - Step 142915: {'lr': 2.8227320991289775e-06, 'samples': 27439680, 'steps': 142914, 'loss/train': 0.8922234773635864} 08/31/2021 15:09:53 - INFO - __main__ - Step 142916: {'lr': 2.8219369506989055e-06, 'samples': 27439872, 'steps': 142915, 'loss/train': 1.56525719165802} 08/31/2021 15:09:53 - INFO - __main__ - Step 142917: {'lr': 2.821141913643466e-06, 'samples': 27440064, 'steps': 142916, 'loss/train': 0.809757649898529} 08/31/2021 15:09:54 - INFO - __main__ - Step 142918: {'lr': 2.8203469879630182e-06, 'samples': 27440256, 'steps': 142917, 'loss/train': 1.3837980031967163} 08/31/2021 15:09:54 - INFO - __main__ - Step 142919: {'lr': 2.8195521736578965e-06, 'samples': 27440448, 'steps': 142918, 'loss/train': 1.0133837461471558} 08/31/2021 15:09:56 - INFO - __main__ - Step 142920: {'lr': 2.818757470728461e-06, 'samples': 27440640, 'steps': 142919, 'loss/train': 0.5002833008766174} 08/31/2021 15:09:57 - INFO - __main__ - Step 142921: {'lr': 2.8179628791751013e-06, 'samples': 27440832, 'steps': 142920, 'loss/train': 0.8954421877861023} 08/31/2021 15:09:57 - INFO - __main__ - Step 142922: {'lr': 2.817168398998121e-06, 'samples': 27441024, 'steps': 142921, 'loss/train': 0.2155185043811798} 08/31/2021 15:09:58 - INFO - __main__ - Step 142923: {'lr': 2.816374030197966e-06, 'samples': 27441216, 'steps': 142922, 'loss/train': 2.9138002395629883} 08/31/2021 15:09:58 - INFO - __main__ - Step 142924: {'lr': 2.8155797727748845e-06, 'samples': 27441408, 'steps': 142923, 'loss/train': 0.9219037890434265} 08/31/2021 15:09:58 - INFO - __main__ - Step 142925: {'lr': 2.8147856267293215e-06, 'samples': 27441600, 'steps': 142924, 'loss/train': 0.760391116142273} 08/31/2021 15:10:00 - INFO - __main__ - Step 142926: {'lr': 2.8139915920615823e-06, 'samples': 27441792, 'steps': 142925, 'loss/train': 0.02277304418385029} 08/31/2021 15:10:00 - INFO - __main__ - Step 142927: {'lr': 2.813197668772055e-06, 'samples': 27441984, 'steps': 142926, 'loss/train': 1.2463935613632202} 08/31/2021 15:10:01 - INFO - __main__ - Step 142928: {'lr': 2.8124038568610733e-06, 'samples': 27442176, 'steps': 142927, 'loss/train': 1.0020461082458496} 08/31/2021 15:10:01 - INFO - __main__ - Step 142929: {'lr': 2.811610156329025e-06, 'samples': 27442368, 'steps': 142928, 'loss/train': 1.17097806930542} 08/31/2021 15:10:01 - INFO - __main__ - Step 142930: {'lr': 2.810816567176244e-06, 'samples': 27442560, 'steps': 142929, 'loss/train': 0.09509013593196869} 08/31/2021 15:10:03 - INFO - __main__ - Step 142931: {'lr': 2.810023089403091e-06, 'samples': 27442752, 'steps': 142930, 'loss/train': 0.8444615006446838} 08/31/2021 15:10:03 - INFO - __main__ - Step 142932: {'lr': 2.809229723009926e-06, 'samples': 27442944, 'steps': 142931, 'loss/train': 1.2501614093780518} 08/31/2021 15:10:04 - INFO - __main__ - Step 142933: {'lr': 2.808436467997111e-06, 'samples': 27443136, 'steps': 142932, 'loss/train': 0.9698547124862671} 08/31/2021 15:10:04 - INFO - __main__ - Step 142934: {'lr': 2.8076433243650056e-06, 'samples': 27443328, 'steps': 142933, 'loss/train': 1.6763113737106323} 08/31/2021 15:10:04 - INFO - __main__ - Step 142935: {'lr': 2.806850292113944e-06, 'samples': 27443520, 'steps': 142934, 'loss/train': 1.3612309694290161} 08/31/2021 15:10:06 - INFO - __main__ - Step 142936: {'lr': 2.8060573712443416e-06, 'samples': 27443712, 'steps': 142935, 'loss/train': 0.0345979668200016} 08/31/2021 15:10:06 - INFO - __main__ - Step 142937: {'lr': 2.8052645617564764e-06, 'samples': 27443904, 'steps': 142936, 'loss/train': 0.9652528762817383} 08/31/2021 15:10:07 - INFO - __main__ - Step 142938: {'lr': 2.804471863650765e-06, 'samples': 27444096, 'steps': 142937, 'loss/train': 1.1601437330245972} 08/31/2021 15:10:07 - INFO - __main__ - Step 142939: {'lr': 2.8036792769275122e-06, 'samples': 27444288, 'steps': 142938, 'loss/train': 0.5986301302909851} 08/31/2021 15:10:07 - INFO - __main__ - Step 142940: {'lr': 2.8028868015871346e-06, 'samples': 27444480, 'steps': 142939, 'loss/train': 1.9423832893371582} 08/31/2021 15:10:09 - INFO - __main__ - Step 142941: {'lr': 2.802094437629965e-06, 'samples': 27444672, 'steps': 142940, 'loss/train': 0.9832858443260193} 08/31/2021 15:10:09 - INFO - __main__ - Step 142942: {'lr': 2.801302185056337e-06, 'samples': 27444864, 'steps': 142941, 'loss/train': 1.2428754568099976} 08/31/2021 15:10:10 - INFO - __main__ - Step 142943: {'lr': 2.8005100438666386e-06, 'samples': 27445056, 'steps': 142942, 'loss/train': 1.0643352270126343} 08/31/2021 15:10:10 - INFO - __main__ - Step 142944: {'lr': 2.799718014061231e-06, 'samples': 27445248, 'steps': 142943, 'loss/train': 0.957410454750061} 08/31/2021 15:10:10 - INFO - __main__ - Step 142945: {'lr': 2.7989260956404195e-06, 'samples': 27445440, 'steps': 142944, 'loss/train': 0.9029405117034912} 08/31/2021 15:10:11 - INFO - __main__ - Step 142946: {'lr': 2.79813428860462e-06, 'samples': 27445632, 'steps': 142945, 'loss/train': 1.0518975257873535} 08/31/2021 15:10:13 - INFO - __main__ - Step 142947: {'lr': 2.7973425929541663e-06, 'samples': 27445824, 'steps': 142946, 'loss/train': 1.0175178050994873} 08/31/2021 15:10:13 - INFO - __main__ - Step 142948: {'lr': 2.7965510086894185e-06, 'samples': 27446016, 'steps': 142947, 'loss/train': 0.03419780358672142} 08/31/2021 15:10:13 - INFO - __main__ - Step 142949: {'lr': 2.795759535810738e-06, 'samples': 27446208, 'steps': 142948, 'loss/train': 1.3808259963989258} 08/31/2021 15:10:14 - INFO - __main__ - Step 142950: {'lr': 2.7949681743184576e-06, 'samples': 27446400, 'steps': 142949, 'loss/train': 1.3605318069458008} 08/31/2021 15:10:14 - INFO - __main__ - Step 142951: {'lr': 2.7941769242129657e-06, 'samples': 27446592, 'steps': 142950, 'loss/train': 0.7967028021812439} 08/31/2021 15:10:16 - INFO - __main__ - Step 142952: {'lr': 2.7933857854945955e-06, 'samples': 27446784, 'steps': 142951, 'loss/train': 0.7317777276039124} 08/31/2021 15:10:17 - INFO - __main__ - Step 142953: {'lr': 2.7925947581637077e-06, 'samples': 27446976, 'steps': 142952, 'loss/train': 1.0788257122039795} 08/31/2021 15:10:17 - INFO - __main__ - Step 142954: {'lr': 2.791803842220664e-06, 'samples': 27447168, 'steps': 142953, 'loss/train': 1.4034987688064575} 08/31/2021 15:10:17 - INFO - __main__ - Step 142955: {'lr': 2.791013037665796e-06, 'samples': 27447360, 'steps': 142954, 'loss/train': 1.5424710512161255} 08/31/2021 15:10:18 - INFO - __main__ - Step 142956: {'lr': 2.7902223444995213e-06, 'samples': 27447552, 'steps': 142955, 'loss/train': 1.0468370914459229} 08/31/2021 15:10:20 - INFO - __main__ - Step 142957: {'lr': 2.7894317627221165e-06, 'samples': 27447744, 'steps': 142956, 'loss/train': 1.454128623008728} 08/31/2021 15:10:20 - INFO - __main__ - Step 142958: {'lr': 2.7886412923340263e-06, 'samples': 27447936, 'steps': 142957, 'loss/train': 0.8010607361793518} 08/31/2021 15:10:21 - INFO - __main__ - Step 142959: {'lr': 2.7878509333355286e-06, 'samples': 27448128, 'steps': 142958, 'loss/train': 0.0850190818309784} 08/31/2021 15:10:21 - INFO - __main__ - Step 142960: {'lr': 2.787060685727011e-06, 'samples': 27448320, 'steps': 142959, 'loss/train': 1.2043453454971313} 08/31/2021 15:10:21 - INFO - __main__ - Step 142961: {'lr': 2.786270549508835e-06, 'samples': 27448512, 'steps': 142960, 'loss/train': 0.7067431807518005} 08/31/2021 15:10:22 - INFO - __main__ - Step 142962: {'lr': 2.785480524681361e-06, 'samples': 27448704, 'steps': 142961, 'loss/train': 1.1851675510406494} 08/31/2021 15:10:23 - INFO - __main__ - Step 142963: {'lr': 2.7846906112449223e-06, 'samples': 27448896, 'steps': 142962, 'loss/train': 0.8074400424957275} 08/31/2021 15:10:24 - INFO - __main__ - Step 142964: {'lr': 2.7839008091999074e-06, 'samples': 27449088, 'steps': 142963, 'loss/train': 1.0098042488098145} 08/31/2021 15:10:24 - INFO - __main__ - Step 142965: {'lr': 2.7831111185466217e-06, 'samples': 27449280, 'steps': 142964, 'loss/train': 1.682671308517456} 08/31/2021 15:10:24 - INFO - __main__ - Step 142966: {'lr': 2.7823215392854818e-06, 'samples': 27449472, 'steps': 142965, 'loss/train': 0.25899630784988403} 08/31/2021 15:10:25 - INFO - __main__ - Step 142967: {'lr': 2.7815320714167922e-06, 'samples': 27449664, 'steps': 142966, 'loss/train': 1.0816850662231445} 08/31/2021 15:10:26 - INFO - __main__ - Step 142968: {'lr': 2.7807427149409147e-06, 'samples': 27449856, 'steps': 142967, 'loss/train': 1.3108183145523071} 08/31/2021 15:10:27 - INFO - __main__ - Step 142969: {'lr': 2.7799534698582372e-06, 'samples': 27450048, 'steps': 142968, 'loss/train': 1.0000691413879395} 08/31/2021 15:10:27 - INFO - __main__ - Step 142970: {'lr': 2.7791643361690934e-06, 'samples': 27450240, 'steps': 142969, 'loss/train': 1.122384786605835} 08/31/2021 15:10:27 - INFO - __main__ - Step 142971: {'lr': 2.778375313873871e-06, 'samples': 27450432, 'steps': 142970, 'loss/train': 1.0451024770736694} 08/31/2021 15:10:28 - INFO - __main__ - Step 142972: {'lr': 2.777586402972876e-06, 'samples': 27450624, 'steps': 142971, 'loss/train': 0.9063935279846191} 08/31/2021 15:10:30 - INFO - __main__ - Step 142973: {'lr': 2.776797603466469e-06, 'samples': 27450816, 'steps': 142972, 'loss/train': 1.095861554145813} 08/31/2021 15:10:30 - INFO - __main__ - Step 142974: {'lr': 2.776008915355038e-06, 'samples': 27451008, 'steps': 142973, 'loss/train': 1.3480099439620972} 08/31/2021 15:10:31 - INFO - __main__ - Step 142975: {'lr': 2.7752203386389174e-06, 'samples': 27451200, 'steps': 142974, 'loss/train': 1.0054904222488403} 08/31/2021 15:10:31 - INFO - __main__ - Step 142976: {'lr': 2.774431873318467e-06, 'samples': 27451392, 'steps': 142975, 'loss/train': 1.0582689046859741} 08/31/2021 15:10:31 - INFO - __main__ - Step 142977: {'lr': 2.7736435193940757e-06, 'samples': 27451584, 'steps': 142976, 'loss/train': 0.30054110288619995} 08/31/2021 15:10:33 - INFO - __main__ - Step 142978: {'lr': 2.7728552768660486e-06, 'samples': 27451776, 'steps': 142977, 'loss/train': 0.9570119976997375} 08/31/2021 15:10:33 - INFO - __main__ - Step 142979: {'lr': 2.7720671457347467e-06, 'samples': 27451968, 'steps': 142978, 'loss/train': 1.0077260732650757} 08/31/2021 15:10:34 - INFO - __main__ - Step 142980: {'lr': 2.771279126000531e-06, 'samples': 27452160, 'steps': 142979, 'loss/train': 0.24783660471439362} 08/31/2021 15:10:34 - INFO - __main__ - Step 142981: {'lr': 2.770491217663762e-06, 'samples': 27452352, 'steps': 142980, 'loss/train': 0.32335013151168823} 08/31/2021 15:10:34 - INFO - __main__ - Step 142982: {'lr': 2.7697034207248006e-06, 'samples': 27452544, 'steps': 142981, 'loss/train': 1.153263807296753} 08/31/2021 15:10:35 - INFO - __main__ - Step 142983: {'lr': 2.7689157351840076e-06, 'samples': 27452736, 'steps': 142982, 'loss/train': 0.656726062297821} 08/31/2021 15:10:36 - INFO - __main__ - Step 142984: {'lr': 2.7681281610417166e-06, 'samples': 27452928, 'steps': 142983, 'loss/train': 0.4741570055484772} 08/31/2021 15:10:37 - INFO - __main__ - Step 142985: {'lr': 2.7673406982982875e-06, 'samples': 27453120, 'steps': 142984, 'loss/train': 1.280829906463623} 08/31/2021 15:10:37 - INFO - __main__ - Step 142986: {'lr': 2.7665533469540817e-06, 'samples': 27453312, 'steps': 142985, 'loss/train': 0.8610295057296753} 08/31/2021 15:10:38 - INFO - __main__ - Step 142987: {'lr': 2.765766107009432e-06, 'samples': 27453504, 'steps': 142986, 'loss/train': 0.6748777031898499} 08/31/2021 15:10:38 - INFO - __main__ - Step 142988: {'lr': 2.764978978464755e-06, 'samples': 27453696, 'steps': 142987, 'loss/train': 0.7545771598815918} 08/31/2021 15:10:39 - INFO - __main__ - Step 142989: {'lr': 2.764191961320328e-06, 'samples': 27453888, 'steps': 142988, 'loss/train': 0.25118812918663025} 08/31/2021 15:10:40 - INFO - __main__ - Step 142990: {'lr': 2.7634050555765676e-06, 'samples': 27454080, 'steps': 142989, 'loss/train': 0.976530134677887} 08/31/2021 15:10:40 - INFO - __main__ - Step 142991: {'lr': 2.762618261233807e-06, 'samples': 27454272, 'steps': 142990, 'loss/train': 1.0033365488052368} 08/31/2021 15:10:40 - INFO - __main__ - Step 142992: {'lr': 2.761831578292379e-06, 'samples': 27454464, 'steps': 142991, 'loss/train': 0.34470102190971375} 08/31/2021 15:10:41 - INFO - __main__ - Step 142993: {'lr': 2.7610450067526437e-06, 'samples': 27454656, 'steps': 142992, 'loss/train': 0.7835801839828491} 08/31/2021 15:10:43 - INFO - __main__ - Step 142994: {'lr': 2.760258546614963e-06, 'samples': 27454848, 'steps': 142993, 'loss/train': 1.002428412437439} 08/31/2021 15:10:43 - INFO - __main__ - Step 142995: {'lr': 2.7594721978797253e-06, 'samples': 27455040, 'steps': 142994, 'loss/train': 0.505940318107605} 08/31/2021 15:10:43 - INFO - __main__ - Step 142996: {'lr': 2.758685960547236e-06, 'samples': 27455232, 'steps': 142995, 'loss/train': 1.3348286151885986} 08/31/2021 15:10:44 - INFO - __main__ - Step 142997: {'lr': 2.7578998346178554e-06, 'samples': 27455424, 'steps': 142996, 'loss/train': 0.41235315799713135} 08/31/2021 15:10:44 - INFO - __main__ - Step 142998: {'lr': 2.757113820091972e-06, 'samples': 27455616, 'steps': 142997, 'loss/train': 0.037851251661777496} 08/31/2021 15:10:46 - INFO - __main__ - Step 142999: {'lr': 2.756327916969892e-06, 'samples': 27455808, 'steps': 142998, 'loss/train': 0.435953289270401} 08/31/2021 15:10:47 - INFO - __main__ - Step 143000: {'lr': 2.7555421252520308e-06, 'samples': 27456000, 'steps': 142999, 'loss/train': 1.2351698875427246} 08/31/2021 15:10:47 - INFO - __main__ - Step 143001: {'lr': 2.7547564449386665e-06, 'samples': 27456192, 'steps': 143000, 'loss/train': 1.2085983753204346} 08/31/2021 15:10:47 - INFO - __main__ - Step 143002: {'lr': 2.753970876030215e-06, 'samples': 27456384, 'steps': 143001, 'loss/train': 5.706991672515869} 08/31/2021 15:10:48 - INFO - __main__ - Step 143003: {'lr': 2.753185418527038e-06, 'samples': 27456576, 'steps': 143002, 'loss/train': 5.7246012687683105} 08/31/2021 15:10:48 - INFO - __main__ - Step 143004: {'lr': 2.7524000724294397e-06, 'samples': 27456768, 'steps': 143003, 'loss/train': 0.843567967414856} 08/31/2021 15:10:50 - INFO - __main__ - Step 143005: {'lr': 2.7516148377377813e-06, 'samples': 27456960, 'steps': 143004, 'loss/train': 1.0614707469940186} 08/31/2021 15:10:50 - INFO - __main__ - Step 143006: {'lr': 2.750829714452424e-06, 'samples': 27457152, 'steps': 143005, 'loss/train': 1.1871330738067627} 08/31/2021 15:10:50 - INFO - __main__ - Step 143007: {'lr': 2.750044702573756e-06, 'samples': 27457344, 'steps': 143006, 'loss/train': 1.7155832052230835} 08/31/2021 15:10:51 - INFO - __main__ - Step 143008: {'lr': 2.7492598021020833e-06, 'samples': 27457536, 'steps': 143007, 'loss/train': 0.6108737587928772} 08/31/2021 15:10:51 - INFO - __main__ - Step 143009: {'lr': 2.7484750130377657e-06, 'samples': 27457728, 'steps': 143008, 'loss/train': 1.8419090509414673} 08/31/2021 15:10:51 - INFO - __main__ - Step 143010: {'lr': 2.747690335381192e-06, 'samples': 27457920, 'steps': 143009, 'loss/train': 1.1660419702529907} 08/31/2021 15:10:53 - INFO - __main__ - Step 143011: {'lr': 2.746905769132696e-06, 'samples': 27458112, 'steps': 143010, 'loss/train': 1.118274211883545} 08/31/2021 15:10:54 - INFO - __main__ - Step 143012: {'lr': 2.74612131429261e-06, 'samples': 27458304, 'steps': 143011, 'loss/train': 0.31823253631591797} 08/31/2021 15:10:54 - INFO - __main__ - Step 143013: {'lr': 2.745336970861323e-06, 'samples': 27458496, 'steps': 143012, 'loss/train': 1.3721463680267334} 08/31/2021 15:10:54 - INFO - __main__ - Step 143014: {'lr': 2.7445527388391676e-06, 'samples': 27458688, 'steps': 143013, 'loss/train': 0.014142820611596107} 08/31/2021 15:10:55 - INFO - __main__ - Step 143015: {'lr': 2.7437686182265053e-06, 'samples': 27458880, 'steps': 143014, 'loss/train': 0.892909049987793} 08/31/2021 15:10:55 - INFO - __main__ - Step 143016: {'lr': 2.742984609023669e-06, 'samples': 27459072, 'steps': 143015, 'loss/train': 0.8998364806175232} 08/31/2021 15:10:57 - INFO - __main__ - Step 143017: {'lr': 2.7422007112310464e-06, 'samples': 27459264, 'steps': 143016, 'loss/train': 1.5880770683288574} 08/31/2021 15:10:57 - INFO - __main__ - Step 143018: {'lr': 2.741416924848972e-06, 'samples': 27459456, 'steps': 143017, 'loss/train': 2.0262699127197266} 08/31/2021 15:10:58 - INFO - __main__ - Step 143019: {'lr': 2.7406332498777776e-06, 'samples': 27459648, 'steps': 143018, 'loss/train': 1.470426082611084} 08/31/2021 15:10:58 - INFO - __main__ - Step 143020: {'lr': 2.73984968631788e-06, 'samples': 27459840, 'steps': 143019, 'loss/train': 2.335425615310669} 08/31/2021 15:10:58 - INFO - __main__ - Step 143021: {'lr': 2.7390662341695572e-06, 'samples': 27460032, 'steps': 143020, 'loss/train': 2.3490092754364014} 08/31/2021 15:11:00 - INFO - __main__ - Step 143022: {'lr': 2.738282893433197e-06, 'samples': 27460224, 'steps': 143021, 'loss/train': 1.6502313613891602} 08/31/2021 15:11:01 - INFO - __main__ - Step 143023: {'lr': 2.737499664109161e-06, 'samples': 27460416, 'steps': 143022, 'loss/train': 0.8607718348503113} 08/31/2021 15:11:01 - INFO - __main__ - Step 143024: {'lr': 2.736716546197782e-06, 'samples': 27460608, 'steps': 143023, 'loss/train': 1.262585163116455} 08/31/2021 15:11:01 - INFO - __main__ - Step 143025: {'lr': 2.7359335396994202e-06, 'samples': 27460800, 'steps': 143024, 'loss/train': 3.2510762214660645} 08/31/2021 15:11:02 - INFO - __main__ - Step 143026: {'lr': 2.735150644614437e-06, 'samples': 27460992, 'steps': 143025, 'loss/train': 0.6885148286819458} 08/31/2021 15:11:02 - INFO - __main__ - Step 143027: {'lr': 2.734367860943193e-06, 'samples': 27461184, 'steps': 143026, 'loss/train': 1.1835191249847412} 08/31/2021 15:11:04 - INFO - __main__ - Step 143028: {'lr': 2.7335851886860217e-06, 'samples': 27461376, 'steps': 143027, 'loss/train': 1.3177813291549683} 08/31/2021 15:11:04 - INFO - __main__ - Step 143029: {'lr': 2.7328026278432563e-06, 'samples': 27461568, 'steps': 143028, 'loss/train': 0.015459326095879078} 08/31/2021 15:11:05 - INFO - __main__ - Step 143030: {'lr': 2.732020178415312e-06, 'samples': 27461760, 'steps': 143029, 'loss/train': 1.0479888916015625} 08/31/2021 15:11:05 - INFO - __main__ - Step 143031: {'lr': 2.731237840402495e-06, 'samples': 27461952, 'steps': 143030, 'loss/train': 1.014996886253357} 08/31/2021 15:11:05 - INFO - __main__ - Step 143032: {'lr': 2.730455613805166e-06, 'samples': 27462144, 'steps': 143031, 'loss/train': 0.8965495228767395} 08/31/2021 15:11:06 - INFO - __main__ - Step 143033: {'lr': 2.729673498623658e-06, 'samples': 27462336, 'steps': 143032, 'loss/train': 1.1659873723983765} 08/31/2021 15:11:08 - INFO - __main__ - Step 143034: {'lr': 2.72889149485836e-06, 'samples': 27462528, 'steps': 143033, 'loss/train': 1.211696982383728} 08/31/2021 15:11:08 - INFO - __main__ - Step 143035: {'lr': 2.7281096025096043e-06, 'samples': 27462720, 'steps': 143034, 'loss/train': 0.2985118329524994} 08/31/2021 15:11:09 - INFO - __main__ - Step 143036: {'lr': 2.727327821577752e-06, 'samples': 27462912, 'steps': 143035, 'loss/train': 1.2871185541152954} 08/31/2021 15:11:09 - INFO - __main__ - Step 143037: {'lr': 2.7265461520631363e-06, 'samples': 27463104, 'steps': 143036, 'loss/train': 1.7415536642074585} 08/31/2021 15:11:09 - INFO - __main__ - Step 143038: {'lr': 2.725764593966118e-06, 'samples': 27463296, 'steps': 143037, 'loss/train': 0.4395190179347992} 08/31/2021 15:11:11 - INFO - __main__ - Step 143039: {'lr': 2.7249831472870854e-06, 'samples': 27463488, 'steps': 143038, 'loss/train': 0.4040234088897705} 08/31/2021 15:11:12 - INFO - __main__ - Step 143040: {'lr': 2.7242018120263447e-06, 'samples': 27463680, 'steps': 143039, 'loss/train': 0.8014522790908813} 08/31/2021 15:11:12 - INFO - __main__ - Step 143041: {'lr': 2.7234205881842557e-06, 'samples': 27463872, 'steps': 143040, 'loss/train': 4.6871657371521} 08/31/2021 15:11:12 - INFO - __main__ - Step 143042: {'lr': 2.7226394757611795e-06, 'samples': 27464064, 'steps': 143041, 'loss/train': 0.6575129628181458} 08/31/2021 15:11:13 - INFO - __main__ - Step 143043: {'lr': 2.721858474757477e-06, 'samples': 27464256, 'steps': 143042, 'loss/train': 1.1481927633285522} 08/31/2021 15:11:14 - INFO - __main__ - Step 143044: {'lr': 2.7210775851734817e-06, 'samples': 27464448, 'steps': 143043, 'loss/train': 0.2528831958770752} 08/31/2021 15:11:15 - INFO - __main__ - Step 143045: {'lr': 2.7202968070095537e-06, 'samples': 27464640, 'steps': 143044, 'loss/train': 1.3004709482192993} 08/31/2021 15:11:15 - INFO - __main__ - Step 143046: {'lr': 2.719516140266054e-06, 'samples': 27464832, 'steps': 143045, 'loss/train': 0.944366991519928} 08/31/2021 15:11:15 - INFO - __main__ - Step 143047: {'lr': 2.718735584943316e-06, 'samples': 27465024, 'steps': 143046, 'loss/train': 1.6233917474746704} 08/31/2021 15:11:16 - INFO - __main__ - Step 143048: {'lr': 2.7179551410416726e-06, 'samples': 27465216, 'steps': 143047, 'loss/train': 1.0586435794830322} 08/31/2021 15:11:16 - INFO - __main__ - Step 143049: {'lr': 2.71717480856154e-06, 'samples': 27465408, 'steps': 143048, 'loss/train': 1.088592529296875} 08/31/2021 15:11:18 - INFO - __main__ - Step 143050: {'lr': 2.716394587503224e-06, 'samples': 27465600, 'steps': 143049, 'loss/train': 1.2185325622558594} 08/31/2021 15:11:18 - INFO - __main__ - Step 143051: {'lr': 2.7156144778670845e-06, 'samples': 27465792, 'steps': 143050, 'loss/train': 0.9954171180725098} 08/31/2021 15:11:18 - INFO - __main__ - Step 143052: {'lr': 2.714834479653455e-06, 'samples': 27465984, 'steps': 143051, 'loss/train': 0.8841710090637207} 08/31/2021 15:11:19 - INFO - __main__ - Step 143053: {'lr': 2.7140545928627247e-06, 'samples': 27466176, 'steps': 143052, 'loss/train': 0.07725343108177185} 08/31/2021 15:11:19 - INFO - __main__ - Step 143054: {'lr': 2.713274817495226e-06, 'samples': 27466368, 'steps': 143053, 'loss/train': 2.0922117233276367} 08/31/2021 15:11:21 - INFO - __main__ - Step 143055: {'lr': 2.712495153551292e-06, 'samples': 27466560, 'steps': 143054, 'loss/train': 0.1559174358844757} 08/31/2021 15:11:21 - INFO - __main__ - Step 143056: {'lr': 2.7117156010313114e-06, 'samples': 27466752, 'steps': 143055, 'loss/train': 1.359398365020752} 08/31/2021 15:11:21 - INFO - __main__ - Step 143057: {'lr': 2.7109361599356175e-06, 'samples': 27466944, 'steps': 143056, 'loss/train': 0.9766560792922974} 08/31/2021 15:11:22 - INFO - __main__ - Step 143058: {'lr': 2.7101568302645705e-06, 'samples': 27467136, 'steps': 143057, 'loss/train': 1.1135022640228271} 08/31/2021 15:11:22 - INFO - __main__ - Step 143059: {'lr': 2.7093776120184767e-06, 'samples': 27467328, 'steps': 143058, 'loss/train': 0.3391523063182831} 08/31/2021 15:11:24 - INFO - __main__ - Step 143060: {'lr': 2.7085985051977515e-06, 'samples': 27467520, 'steps': 143059, 'loss/train': 1.904396891593933} 08/31/2021 15:11:24 - INFO - __main__ - Step 143061: {'lr': 2.7078195098027e-06, 'samples': 27467712, 'steps': 143060, 'loss/train': 0.8245266675949097} 08/31/2021 15:11:25 - INFO - __main__ - Step 143062: {'lr': 2.7070406258336845e-06, 'samples': 27467904, 'steps': 143061, 'loss/train': 1.1807817220687866} 08/31/2021 15:11:25 - INFO - __main__ - Step 143063: {'lr': 2.7062618532910645e-06, 'samples': 27468096, 'steps': 143062, 'loss/train': 0.8729764223098755} 08/31/2021 15:11:25 - INFO - __main__ - Step 143064: {'lr': 2.7054831921751734e-06, 'samples': 27468288, 'steps': 143063, 'loss/train': 1.555196762084961} 08/31/2021 15:11:27 - INFO - __main__ - Step 143065: {'lr': 2.7047046424863996e-06, 'samples': 27468480, 'steps': 143064, 'loss/train': 1.5230581760406494} 08/31/2021 15:11:27 - INFO - __main__ - Step 143066: {'lr': 2.703926204225077e-06, 'samples': 27468672, 'steps': 143065, 'loss/train': 1.1827787160873413} 08/31/2021 15:11:27 - INFO - __main__ - Step 143067: {'lr': 2.7031478773915096e-06, 'samples': 27468864, 'steps': 143066, 'loss/train': 0.6550299525260925} 08/31/2021 15:11:28 - INFO - __main__ - Step 143068: {'lr': 2.702369661986115e-06, 'samples': 27469056, 'steps': 143067, 'loss/train': 1.5204393863677979} 08/31/2021 15:11:28 - INFO - __main__ - Step 143069: {'lr': 2.7015915580092252e-06, 'samples': 27469248, 'steps': 143068, 'loss/train': 2.8944616317749023} 08/31/2021 15:11:30 - INFO - __main__ - Step 143070: {'lr': 2.7008135654611743e-06, 'samples': 27469440, 'steps': 143069, 'loss/train': 1.6386524438858032} 08/31/2021 15:11:30 - INFO - __main__ - Step 143071: {'lr': 2.7000356843423223e-06, 'samples': 27469632, 'steps': 143070, 'loss/train': 0.9311707019805908} 08/31/2021 15:11:30 - INFO - __main__ - Step 143072: {'lr': 2.699257914653003e-06, 'samples': 27469824, 'steps': 143071, 'loss/train': 1.1852837800979614} 08/31/2021 15:11:31 - INFO - __main__ - Step 143073: {'lr': 2.698480256393604e-06, 'samples': 27470016, 'steps': 143072, 'loss/train': 0.5309869050979614} 08/31/2021 15:11:31 - INFO - __main__ - Step 143074: {'lr': 2.6977027095644314e-06, 'samples': 27470208, 'steps': 143073, 'loss/train': 0.987404465675354} 08/31/2021 15:11:32 - INFO - __main__ - Step 143075: {'lr': 2.6969252741658736e-06, 'samples': 27470400, 'steps': 143074, 'loss/train': 1.3202714920043945} 08/31/2021 15:11:33 - INFO - __main__ - Step 143076: {'lr': 2.6961479501982633e-06, 'samples': 27470592, 'steps': 143075, 'loss/train': 1.7425085306167603} 08/31/2021 15:11:34 - INFO - __main__ - Step 143077: {'lr': 2.695370737661934e-06, 'samples': 27470784, 'steps': 143076, 'loss/train': 0.7131166458129883} 08/31/2021 15:11:34 - INFO - __main__ - Step 143078: {'lr': 2.694593636557274e-06, 'samples': 27470976, 'steps': 143077, 'loss/train': 0.6086935997009277} 08/31/2021 15:11:34 - INFO - __main__ - Step 143079: {'lr': 2.693816646884617e-06, 'samples': 27471168, 'steps': 143078, 'loss/train': 0.0697324201464653} 08/31/2021 15:11:35 - INFO - __main__ - Step 143080: {'lr': 2.6930397686442953e-06, 'samples': 27471360, 'steps': 143079, 'loss/train': 0.8318976759910583} 08/31/2021 15:11:37 - INFO - __main__ - Step 143081: {'lr': 2.69226300183667e-06, 'samples': 27471552, 'steps': 143080, 'loss/train': 0.933901309967041} 08/31/2021 15:11:38 - INFO - __main__ - Step 143082: {'lr': 2.691486346462102e-06, 'samples': 27471744, 'steps': 143081, 'loss/train': 0.2513200640678406} 08/31/2021 15:11:38 - INFO - __main__ - Step 143083: {'lr': 2.690709802520952e-06, 'samples': 27471936, 'steps': 143082, 'loss/train': 0.22953201830387115} 08/31/2021 15:11:38 - INFO - __main__ - Step 143084: {'lr': 2.689933370013553e-06, 'samples': 27472128, 'steps': 143083, 'loss/train': 1.1664886474609375} 08/31/2021 15:11:39 - INFO - __main__ - Step 143085: {'lr': 2.6891570489402384e-06, 'samples': 27472320, 'steps': 143084, 'loss/train': 1.3291398286819458} 08/31/2021 15:11:39 - INFO - __main__ - Step 143086: {'lr': 2.688380839301369e-06, 'samples': 27472512, 'steps': 143085, 'loss/train': 1.3073126077651978} 08/31/2021 15:11:41 - INFO - __main__ - Step 143087: {'lr': 2.6876047410973047e-06, 'samples': 27472704, 'steps': 143086, 'loss/train': 1.0284230709075928} 08/31/2021 15:11:41 - INFO - __main__ - Step 143088: {'lr': 2.68682875432838e-06, 'samples': 27472896, 'steps': 143087, 'loss/train': 0.030718311667442322} 08/31/2021 15:11:42 - INFO - __main__ - Step 143089: {'lr': 2.6860528789949545e-06, 'samples': 27473088, 'steps': 143088, 'loss/train': 0.0966661348938942} 08/31/2021 15:11:42 - INFO - __main__ - Step 143090: {'lr': 2.6852771150973898e-06, 'samples': 27473280, 'steps': 143089, 'loss/train': 1.0382643938064575} 08/31/2021 15:11:42 - INFO - __main__ - Step 143091: {'lr': 2.6845014626360187e-06, 'samples': 27473472, 'steps': 143090, 'loss/train': 1.1473281383514404} 08/31/2021 15:11:44 - INFO - __main__ - Step 143092: {'lr': 2.683725921611202e-06, 'samples': 27473664, 'steps': 143091, 'loss/train': 1.3178136348724365} 08/31/2021 15:11:45 - INFO - __main__ - Step 143093: {'lr': 2.6829504920232726e-06, 'samples': 27473856, 'steps': 143092, 'loss/train': 1.4576135873794556} 08/31/2021 15:11:45 - INFO - __main__ - Step 143094: {'lr': 2.6821751738725917e-06, 'samples': 27474048, 'steps': 143093, 'loss/train': 1.8848236799240112} 08/31/2021 15:11:45 - INFO - __main__ - Step 143095: {'lr': 2.6813999671594923e-06, 'samples': 27474240, 'steps': 143094, 'loss/train': 0.9114314317703247} 08/31/2021 15:11:46 - INFO - __main__ - Step 143096: {'lr': 2.680624871884363e-06, 'samples': 27474432, 'steps': 143095, 'loss/train': 1.145810604095459} 08/31/2021 15:11:46 - INFO - __main__ - Step 143097: {'lr': 2.6798498880475087e-06, 'samples': 27474624, 'steps': 143096, 'loss/train': 0.7212299704551697} 08/31/2021 15:11:47 - INFO - __main__ - Step 143098: {'lr': 2.679075015649318e-06, 'samples': 27474816, 'steps': 143097, 'loss/train': 1.7923105955123901} 08/31/2021 15:11:48 - INFO - __main__ - Step 143099: {'lr': 2.678300254690097e-06, 'samples': 27475008, 'steps': 143098, 'loss/train': 0.9541445374488831} 08/31/2021 15:11:48 - INFO - __main__ - Step 143100: {'lr': 2.6775256051702335e-06, 'samples': 27475200, 'steps': 143099, 'loss/train': 1.4491689205169678} 08/31/2021 15:11:49 - INFO - __main__ - Step 143101: {'lr': 2.6767510670900608e-06, 'samples': 27475392, 'steps': 143100, 'loss/train': 1.4020888805389404} 08/31/2021 15:11:49 - INFO - __main__ - Step 143102: {'lr': 2.675976640449912e-06, 'samples': 27475584, 'steps': 143101, 'loss/train': 1.2951613664627075} 08/31/2021 15:11:50 - INFO - __main__ - Step 143103: {'lr': 2.675202325250148e-06, 'samples': 27475776, 'steps': 143102, 'loss/train': 1.1876901388168335} 08/31/2021 15:11:51 - INFO - __main__ - Step 143104: {'lr': 2.674428121491157e-06, 'samples': 27475968, 'steps': 143103, 'loss/train': 0.09147586673498154} 08/31/2021 15:11:51 - INFO - __main__ - Step 143105: {'lr': 2.673654029173217e-06, 'samples': 27476160, 'steps': 143104, 'loss/train': 1.138280987739563} 08/31/2021 15:11:52 - INFO - __main__ - Step 143106: {'lr': 2.6728800482967164e-06, 'samples': 27476352, 'steps': 143105, 'loss/train': 0.5823646783828735} 08/31/2021 15:11:52 - INFO - __main__ - Step 143107: {'lr': 2.672106178862016e-06, 'samples': 27476544, 'steps': 143106, 'loss/train': 1.1591800451278687} 08/31/2021 15:11:54 - INFO - __main__ - Step 143108: {'lr': 2.6713324208694213e-06, 'samples': 27476736, 'steps': 143107, 'loss/train': 1.2995293140411377} 08/31/2021 15:11:54 - INFO - __main__ - Step 143109: {'lr': 2.6705587743193484e-06, 'samples': 27476928, 'steps': 143108, 'loss/train': 1.1749768257141113} 08/31/2021 15:11:54 - INFO - __main__ - Step 143110: {'lr': 2.6697852392120748e-06, 'samples': 27477120, 'steps': 143109, 'loss/train': 1.328401803970337} 08/31/2021 15:11:55 - INFO - __main__ - Step 143111: {'lr': 2.669011815547989e-06, 'samples': 27477312, 'steps': 143110, 'loss/train': 1.264045000076294} 08/31/2021 15:11:55 - INFO - __main__ - Step 143112: {'lr': 2.668238503327425e-06, 'samples': 27477504, 'steps': 143111, 'loss/train': 0.9918808341026306} 08/31/2021 15:11:57 - INFO - __main__ - Step 143113: {'lr': 2.667465302550742e-06, 'samples': 27477696, 'steps': 143112, 'loss/train': 0.024416157975792885} 08/31/2021 15:11:57 - INFO - __main__ - Step 143114: {'lr': 2.6666922132182747e-06, 'samples': 27477888, 'steps': 143113, 'loss/train': 0.825905442237854} 08/31/2021 15:11:57 - INFO - __main__ - Step 143115: {'lr': 2.665919235330383e-06, 'samples': 27478080, 'steps': 143114, 'loss/train': 1.0079697370529175} 08/31/2021 15:11:58 - INFO - __main__ - Step 143116: {'lr': 2.6651463688874277e-06, 'samples': 27478272, 'steps': 143115, 'loss/train': 1.6739912033081055} 08/31/2021 15:11:58 - INFO - __main__ - Step 143117: {'lr': 2.6643736138897147e-06, 'samples': 27478464, 'steps': 143116, 'loss/train': 1.4389100074768066} 08/31/2021 15:12:00 - INFO - __main__ - Step 143118: {'lr': 2.6636009703376317e-06, 'samples': 27478656, 'steps': 143117, 'loss/train': 0.8987045288085938} 08/31/2021 15:12:00 - INFO - __main__ - Step 143119: {'lr': 2.6628284382315125e-06, 'samples': 27478848, 'steps': 143118, 'loss/train': 1.4701539278030396} 08/31/2021 15:12:00 - INFO - __main__ - Step 143120: {'lr': 2.662056017571718e-06, 'samples': 27479040, 'steps': 143119, 'loss/train': 0.6649399995803833} 08/31/2021 15:12:01 - INFO - __main__ - Step 143121: {'lr': 2.661283708358553e-06, 'samples': 27479232, 'steps': 143120, 'loss/train': 0.0293129812926054} 08/31/2021 15:12:01 - INFO - __main__ - Step 143122: {'lr': 2.6605115105924337e-06, 'samples': 27479424, 'steps': 143121, 'loss/train': 1.3838205337524414} 08/31/2021 15:12:02 - INFO - __main__ - Step 143123: {'lr': 2.6597394242736382e-06, 'samples': 27479616, 'steps': 143122, 'loss/train': 0.9201852679252625} 08/31/2021 15:12:03 - INFO - __main__ - Step 143124: {'lr': 2.6589674494025552e-06, 'samples': 27479808, 'steps': 143123, 'loss/train': 1.0414278507232666} 08/31/2021 15:12:03 - INFO - __main__ - Step 143125: {'lr': 2.6581955859795447e-06, 'samples': 27480000, 'steps': 143124, 'loss/train': 0.8317307233810425} 08/31/2021 15:12:04 - INFO - __main__ - Step 143126: {'lr': 2.6574238340049408e-06, 'samples': 27480192, 'steps': 143125, 'loss/train': 0.8639060258865356} 08/31/2021 15:12:04 - INFO - __main__ - Step 143127: {'lr': 2.6566521934790476e-06, 'samples': 27480384, 'steps': 143126, 'loss/train': 1.1977211236953735} 08/31/2021 15:12:04 - INFO - __main__ - Step 143128: {'lr': 2.6558806644022826e-06, 'samples': 27480576, 'steps': 143127, 'loss/train': 0.9047868251800537} 08/31/2021 15:12:06 - INFO - __main__ - Step 143129: {'lr': 2.6551092467749505e-06, 'samples': 27480768, 'steps': 143128, 'loss/train': 1.490915060043335} 08/31/2021 15:12:07 - INFO - __main__ - Step 143130: {'lr': 2.6543379405973845e-06, 'samples': 27480960, 'steps': 143129, 'loss/train': 1.1608989238739014} 08/31/2021 15:12:07 - INFO - __main__ - Step 143131: {'lr': 2.653566745869973e-06, 'samples': 27481152, 'steps': 143130, 'loss/train': 0.8161336183547974} 08/31/2021 15:12:07 - INFO - __main__ - Step 143132: {'lr': 2.652795662593077e-06, 'samples': 27481344, 'steps': 143131, 'loss/train': 0.1679767668247223} 08/31/2021 15:12:08 - INFO - __main__ - Step 143133: {'lr': 2.652024690766974e-06, 'samples': 27481536, 'steps': 143132, 'loss/train': 1.3706321716308594} 08/31/2021 15:12:09 - INFO - __main__ - Step 143134: {'lr': 2.651253830392081e-06, 'samples': 27481728, 'steps': 143133, 'loss/train': 1.106339931488037} 08/31/2021 15:12:10 - INFO - __main__ - Step 143135: {'lr': 2.650483081468702e-06, 'samples': 27481920, 'steps': 143134, 'loss/train': 1.1217617988586426} 08/31/2021 15:12:10 - INFO - __main__ - Step 143136: {'lr': 2.6497124439971985e-06, 'samples': 27482112, 'steps': 143135, 'loss/train': 0.03442186489701271} 08/31/2021 15:12:10 - INFO - __main__ - Step 143137: {'lr': 2.648941917977904e-06, 'samples': 27482304, 'steps': 143136, 'loss/train': 0.9215664267539978} 08/31/2021 15:12:11 - INFO - __main__ - Step 143138: {'lr': 2.6481715034112065e-06, 'samples': 27482496, 'steps': 143137, 'loss/train': 1.2173864841461182} 08/31/2021 15:12:12 - INFO - __main__ - Step 143139: {'lr': 2.6474012002974114e-06, 'samples': 27482688, 'steps': 143138, 'loss/train': 1.0065523386001587} 08/31/2021 15:12:12 - INFO - __main__ - Step 143140: {'lr': 2.6466310086368794e-06, 'samples': 27482880, 'steps': 143139, 'loss/train': 0.7867581844329834} 08/31/2021 15:12:13 - INFO - __main__ - Step 143141: {'lr': 2.645860928429972e-06, 'samples': 27483072, 'steps': 143140, 'loss/train': 0.85610032081604} 08/31/2021 15:12:13 - INFO - __main__ - Step 143142: {'lr': 2.6450909596770214e-06, 'samples': 27483264, 'steps': 143141, 'loss/train': 1.9117027521133423} 08/31/2021 15:12:14 - INFO - __main__ - Step 143143: {'lr': 2.644321102378361e-06, 'samples': 27483456, 'steps': 143142, 'loss/train': 1.3082292079925537} 08/31/2021 15:12:16 - INFO - __main__ - Step 143144: {'lr': 2.6435513565343517e-06, 'samples': 27483648, 'steps': 143143, 'loss/train': 0.9055667519569397} 08/31/2021 15:12:16 - INFO - __main__ - Step 143145: {'lr': 2.642781722145354e-06, 'samples': 27483840, 'steps': 143144, 'loss/train': 1.8737057447433472} 08/31/2021 15:12:16 - INFO - __main__ - Step 143146: {'lr': 2.642012199211702e-06, 'samples': 27484032, 'steps': 143145, 'loss/train': 1.470784068107605} 08/31/2021 15:12:17 - INFO - __main__ - Step 143147: {'lr': 2.6412427877337276e-06, 'samples': 27484224, 'steps': 143146, 'loss/train': 0.9471886157989502} 08/31/2021 15:12:17 - INFO - __main__ - Step 143148: {'lr': 2.64047348771182e-06, 'samples': 27484416, 'steps': 143147, 'loss/train': 0.9908277988433838} 08/31/2021 15:12:19 - INFO - __main__ - Step 143149: {'lr': 2.639704299146284e-06, 'samples': 27484608, 'steps': 143148, 'loss/train': 0.6643915772438049} 08/31/2021 15:12:19 - INFO - __main__ - Step 143150: {'lr': 2.6389352220374527e-06, 'samples': 27484800, 'steps': 143149, 'loss/train': 1.4826024770736694} 08/31/2021 15:12:19 - INFO - __main__ - Step 143151: {'lr': 2.6381662563857435e-06, 'samples': 27484992, 'steps': 143150, 'loss/train': 1.0602562427520752} 08/31/2021 15:12:20 - INFO - __main__ - Step 143152: {'lr': 2.6373974021914325e-06, 'samples': 27485184, 'steps': 143151, 'loss/train': 1.0778776407241821} 08/31/2021 15:12:20 - INFO - __main__ - Step 143153: {'lr': 2.6366286594549094e-06, 'samples': 27485376, 'steps': 143152, 'loss/train': 0.8600075840950012} 08/31/2021 15:12:20 - INFO - __main__ - Step 143154: {'lr': 2.6358600281764788e-06, 'samples': 27485568, 'steps': 143153, 'loss/train': 0.8404996395111084} 08/31/2021 15:12:22 - INFO - __main__ - Step 143155: {'lr': 2.63509150835653e-06, 'samples': 27485760, 'steps': 143154, 'loss/train': 1.2329238653182983} 08/31/2021 15:12:22 - INFO - __main__ - Step 143156: {'lr': 2.634323099995395e-06, 'samples': 27485952, 'steps': 143155, 'loss/train': 0.9827155470848083} 08/31/2021 15:12:23 - INFO - __main__ - Step 143157: {'lr': 2.6335548030934075e-06, 'samples': 27486144, 'steps': 143156, 'loss/train': 0.9997552037239075} 08/31/2021 15:12:23 - INFO - __main__ - Step 143158: {'lr': 2.6327866176509284e-06, 'samples': 27486336, 'steps': 143157, 'loss/train': 0.8984110355377197} 08/31/2021 15:12:23 - INFO - __main__ - Step 143159: {'lr': 2.6320185436683187e-06, 'samples': 27486528, 'steps': 143158, 'loss/train': 1.0496423244476318} 08/31/2021 15:12:25 - INFO - __main__ - Step 143160: {'lr': 2.631250581145883e-06, 'samples': 27486720, 'steps': 143159, 'loss/train': 1.2923386096954346} 08/31/2021 15:12:25 - INFO - __main__ - Step 143161: {'lr': 2.6304827300839828e-06, 'samples': 27486912, 'steps': 143160, 'loss/train': 1.0050246715545654} 08/31/2021 15:12:26 - INFO - __main__ - Step 143162: {'lr': 2.6297149904829786e-06, 'samples': 27487104, 'steps': 143161, 'loss/train': 0.714752733707428} 08/31/2021 15:12:26 - INFO - __main__ - Step 143163: {'lr': 2.6289473623432038e-06, 'samples': 27487296, 'steps': 143162, 'loss/train': 1.1214749813079834} 08/31/2021 15:12:26 - INFO - __main__ - Step 143164: {'lr': 2.6281798456650184e-06, 'samples': 27487488, 'steps': 143163, 'loss/train': 1.0777844190597534} 08/31/2021 15:12:28 - INFO - __main__ - Step 143165: {'lr': 2.6274124404487287e-06, 'samples': 27487680, 'steps': 143164, 'loss/train': 1.6878169775009155} 08/31/2021 15:12:28 - INFO - __main__ - Step 143166: {'lr': 2.6266451466947505e-06, 'samples': 27487872, 'steps': 143165, 'loss/train': 0.4393136203289032} 08/31/2021 15:12:29 - INFO - __main__ - Step 143167: {'lr': 2.6258779644033616e-06, 'samples': 27488064, 'steps': 143166, 'loss/train': 1.1667860746383667} 08/31/2021 15:12:29 - INFO - __main__ - Step 143168: {'lr': 2.6251108935749224e-06, 'samples': 27488256, 'steps': 143167, 'loss/train': 0.15871736407279968} 08/31/2021 15:12:29 - INFO - __main__ - Step 143169: {'lr': 2.624343934209822e-06, 'samples': 27488448, 'steps': 143168, 'loss/train': 1.2521713972091675} 08/31/2021 15:12:31 - INFO - __main__ - Step 143170: {'lr': 2.623577086308393e-06, 'samples': 27488640, 'steps': 143169, 'loss/train': 0.7645890116691589} 08/31/2021 15:12:31 - INFO - __main__ - Step 143171: {'lr': 2.622810349870913e-06, 'samples': 27488832, 'steps': 143170, 'loss/train': 0.5983580946922302} 08/31/2021 15:12:32 - INFO - __main__ - Step 143172: {'lr': 2.6220437248977993e-06, 'samples': 27489024, 'steps': 143171, 'loss/train': 1.2362720966339111} 08/31/2021 15:12:32 - INFO - __main__ - Step 143173: {'lr': 2.6212772113893834e-06, 'samples': 27489216, 'steps': 143172, 'loss/train': 1.9171500205993652} 08/31/2021 15:12:32 - INFO - __main__ - Step 143174: {'lr': 2.6205108093459997e-06, 'samples': 27489408, 'steps': 143173, 'loss/train': 0.6873588562011719} 08/31/2021 15:12:34 - INFO - __main__ - Step 143175: {'lr': 2.6197445187679802e-06, 'samples': 27489600, 'steps': 143174, 'loss/train': 1.0779935121536255} 08/31/2021 15:12:34 - INFO - __main__ - Step 143176: {'lr': 2.6189783396556866e-06, 'samples': 27489792, 'steps': 143175, 'loss/train': 1.1517267227172852} 08/31/2021 15:12:35 - INFO - __main__ - Step 143177: {'lr': 2.6182122720094794e-06, 'samples': 27489984, 'steps': 143176, 'loss/train': 0.8579787015914917} 08/31/2021 15:12:35 - INFO - __main__ - Step 143178: {'lr': 2.6174463158296913e-06, 'samples': 27490176, 'steps': 143177, 'loss/train': 1.0275249481201172} 08/31/2021 15:12:35 - INFO - __main__ - Step 143179: {'lr': 2.6166804711166558e-06, 'samples': 27490368, 'steps': 143178, 'loss/train': 1.2088993787765503} 08/31/2021 15:12:36 - INFO - __main__ - Step 143180: {'lr': 2.615914737870706e-06, 'samples': 27490560, 'steps': 143179, 'loss/train': 0.9689136147499084} 08/31/2021 15:12:37 - INFO - __main__ - Step 143181: {'lr': 2.615149116092258e-06, 'samples': 27490752, 'steps': 143180, 'loss/train': 1.5500656366348267} 08/31/2021 15:12:38 - INFO - __main__ - Step 143182: {'lr': 2.6143836057815616e-06, 'samples': 27490944, 'steps': 143181, 'loss/train': 0.9447497725486755} 08/31/2021 15:12:38 - INFO - __main__ - Step 143183: {'lr': 2.6136182069390335e-06, 'samples': 27491136, 'steps': 143182, 'loss/train': 1.1191771030426025} 08/31/2021 15:12:38 - INFO - __main__ - Step 143184: {'lr': 2.6128529195649786e-06, 'samples': 27491328, 'steps': 143183, 'loss/train': 1.187723159790039} 08/31/2021 15:12:39 - INFO - __main__ - Step 143185: {'lr': 2.612087743659758e-06, 'samples': 27491520, 'steps': 143184, 'loss/train': 1.0530869960784912} 08/31/2021 15:12:40 - INFO - __main__ - Step 143186: {'lr': 2.6113226792237045e-06, 'samples': 27491712, 'steps': 143185, 'loss/train': 0.9970622658729553} 08/31/2021 15:12:41 - INFO - __main__ - Step 143187: {'lr': 2.610557726257179e-06, 'samples': 27491904, 'steps': 143186, 'loss/train': 0.6855319142341614} 08/31/2021 15:12:41 - INFO - __main__ - Step 143188: {'lr': 2.6097928847605145e-06, 'samples': 27492096, 'steps': 143187, 'loss/train': 1.2570528984069824} 08/31/2021 15:12:41 - INFO - __main__ - Step 143189: {'lr': 2.609028154734072e-06, 'samples': 27492288, 'steps': 143188, 'loss/train': 1.3306597471237183} 08/31/2021 15:12:42 - INFO - __main__ - Step 143190: {'lr': 2.6082635361781848e-06, 'samples': 27492480, 'steps': 143189, 'loss/train': 1.187342882156372} 08/31/2021 15:12:43 - INFO - __main__ - Step 143191: {'lr': 2.6074990290931857e-06, 'samples': 27492672, 'steps': 143190, 'loss/train': 0.7471204996109009} 08/31/2021 15:12:44 - INFO - __main__ - Step 143192: {'lr': 2.606734633479435e-06, 'samples': 27492864, 'steps': 143191, 'loss/train': 0.8388348817825317} 08/31/2021 15:12:44 - INFO - __main__ - Step 143193: {'lr': 2.6059703493372665e-06, 'samples': 27493056, 'steps': 143192, 'loss/train': 1.0013691186904907} 08/31/2021 15:12:44 - INFO - __main__ - Step 143194: {'lr': 2.605206176667041e-06, 'samples': 27493248, 'steps': 143193, 'loss/train': 1.3768855333328247} 08/31/2021 15:12:45 - INFO - __main__ - Step 143195: {'lr': 2.604442115469091e-06, 'samples': 27493440, 'steps': 143194, 'loss/train': 0.9313799142837524} 08/31/2021 15:12:47 - INFO - __main__ - Step 143196: {'lr': 2.6036781657437505e-06, 'samples': 27493632, 'steps': 143195, 'loss/train': 0.5001715421676636} 08/31/2021 15:12:47 - INFO - __main__ - Step 143197: {'lr': 2.602914327491379e-06, 'samples': 27493824, 'steps': 143196, 'loss/train': 1.3985406160354614} 08/31/2021 15:12:48 - INFO - __main__ - Step 143198: {'lr': 2.602150600712311e-06, 'samples': 27494016, 'steps': 143197, 'loss/train': 0.7090978026390076} 08/31/2021 15:12:48 - INFO - __main__ - Step 143199: {'lr': 2.601386985406906e-06, 'samples': 27494208, 'steps': 143198, 'loss/train': 0.7578645348548889} 08/31/2021 15:12:48 - INFO - __main__ - Step 143200: {'lr': 2.600623481575498e-06, 'samples': 27494400, 'steps': 143199, 'loss/train': 1.323346734046936} 08/31/2021 15:12:50 - INFO - __main__ - Step 143201: {'lr': 2.59986008921842e-06, 'samples': 27494592, 'steps': 143200, 'loss/train': 1.4608334302902222} 08/31/2021 15:12:50 - INFO - __main__ - Step 143202: {'lr': 2.599096808336032e-06, 'samples': 27494784, 'steps': 143201, 'loss/train': 1.27286696434021} 08/31/2021 15:12:51 - INFO - __main__ - Step 143203: {'lr': 2.5983336389286683e-06, 'samples': 27494976, 'steps': 143202, 'loss/train': 0.3284604549407959} 08/31/2021 15:12:51 - INFO - __main__ - Step 143204: {'lr': 2.5975705809966888e-06, 'samples': 27495168, 'steps': 143203, 'loss/train': 1.0804495811462402} 08/31/2021 15:12:51 - INFO - __main__ - Step 143205: {'lr': 2.5968076345404547e-06, 'samples': 27495360, 'steps': 143204, 'loss/train': 1.3527146577835083} 08/31/2021 15:12:52 - INFO - __main__ - Step 143206: {'lr': 2.596044799560243e-06, 'samples': 27495552, 'steps': 143205, 'loss/train': 0.753271758556366} 08/31/2021 15:12:53 - INFO - __main__ - Step 143207: {'lr': 2.5952820760564435e-06, 'samples': 27495744, 'steps': 143206, 'loss/train': 0.8525903820991516} 08/31/2021 15:12:54 - INFO - __main__ - Step 143208: {'lr': 2.594519464029388e-06, 'samples': 27495936, 'steps': 143207, 'loss/train': 0.5211095213890076} 08/31/2021 15:12:54 - INFO - __main__ - Step 143209: {'lr': 2.593756963479438e-06, 'samples': 27496128, 'steps': 143208, 'loss/train': 0.4734984040260315} 08/31/2021 15:12:54 - INFO - __main__ - Step 143210: {'lr': 2.5929945744068985e-06, 'samples': 27496320, 'steps': 143209, 'loss/train': 0.48714765906333923} 08/31/2021 15:12:55 - INFO - __main__ - Step 143211: {'lr': 2.5922322968121583e-06, 'samples': 27496512, 'steps': 143210, 'loss/train': 1.0656582117080688} 08/31/2021 15:12:56 - INFO - __main__ - Step 143212: {'lr': 2.59147013069555e-06, 'samples': 27496704, 'steps': 143211, 'loss/train': 0.9136120080947876} 08/31/2021 15:12:57 - INFO - __main__ - Step 143213: {'lr': 2.59070807605738e-06, 'samples': 27496896, 'steps': 143212, 'loss/train': 1.1032530069351196} 08/31/2021 15:12:57 - INFO - __main__ - Step 143214: {'lr': 2.589946132898036e-06, 'samples': 27497088, 'steps': 143213, 'loss/train': 1.2973753213882446} 08/31/2021 15:12:57 - INFO - __main__ - Step 143215: {'lr': 2.589184301217823e-06, 'samples': 27497280, 'steps': 143214, 'loss/train': 1.5472314357757568} 08/31/2021 15:12:58 - INFO - __main__ - Step 143216: {'lr': 2.58842258101713e-06, 'samples': 27497472, 'steps': 143215, 'loss/train': 0.9968109130859375} 08/31/2021 15:12:59 - INFO - __main__ - Step 143217: {'lr': 2.587660972296263e-06, 'samples': 27497664, 'steps': 143216, 'loss/train': 1.6778812408447266} 08/31/2021 15:13:00 - INFO - __main__ - Step 143218: {'lr': 2.5868994750556095e-06, 'samples': 27497856, 'steps': 143217, 'loss/train': 1.2124654054641724} 08/31/2021 15:13:00 - INFO - __main__ - Step 143219: {'lr': 2.5861380892954477e-06, 'samples': 27498048, 'steps': 143218, 'loss/train': 1.5127513408660889} 08/31/2021 15:13:01 - INFO - __main__ - Step 143220: {'lr': 2.585376815016166e-06, 'samples': 27498240, 'steps': 143219, 'loss/train': 0.03828919678926468} 08/31/2021 15:13:01 - INFO - __main__ - Step 143221: {'lr': 2.5846156522180977e-06, 'samples': 27498432, 'steps': 143220, 'loss/train': 0.974264919757843} 08/31/2021 15:13:03 - INFO - __main__ - Step 143222: {'lr': 2.583854600901575e-06, 'samples': 27498624, 'steps': 143221, 'loss/train': 0.5561078786849976} 08/31/2021 15:13:03 - INFO - __main__ - Step 143223: {'lr': 2.5830936610669597e-06, 'samples': 27498816, 'steps': 143222, 'loss/train': 0.8251829743385315} 08/31/2021 15:13:04 - INFO - __main__ - Step 143224: {'lr': 2.5823328327145844e-06, 'samples': 27499008, 'steps': 143223, 'loss/train': 1.5264865159988403} 08/31/2021 15:13:04 - INFO - __main__ - Step 143225: {'lr': 2.5815721158447825e-06, 'samples': 27499200, 'steps': 143224, 'loss/train': 0.9581038951873779} 08/31/2021 15:13:05 - INFO - __main__ - Step 143226: {'lr': 2.5808115104579144e-06, 'samples': 27499392, 'steps': 143225, 'loss/train': 1.2407886981964111} 08/31/2021 15:13:05 - INFO - __main__ - Step 143227: {'lr': 2.5800510165542855e-06, 'samples': 27499584, 'steps': 143226, 'loss/train': 1.384851336479187} 08/31/2021 15:13:07 - INFO - __main__ - Step 143228: {'lr': 2.5792906341343125e-06, 'samples': 27499776, 'steps': 143227, 'loss/train': 1.4301562309265137} 08/31/2021 15:13:07 - INFO - __main__ - Step 143229: {'lr': 2.5785303631982727e-06, 'samples': 27499968, 'steps': 143228, 'loss/train': 1.2567507028579712} 08/31/2021 15:13:07 - INFO - __main__ - Step 143230: {'lr': 2.5777702037465267e-06, 'samples': 27500160, 'steps': 143229, 'loss/train': 1.291072130203247} 08/31/2021 15:13:08 - INFO - __main__ - Step 143231: {'lr': 2.5770101557794077e-06, 'samples': 27500352, 'steps': 143230, 'loss/train': 0.8807265758514404} 08/31/2021 15:13:08 - INFO - __main__ - Step 143232: {'lr': 2.576250219297305e-06, 'samples': 27500544, 'steps': 143231, 'loss/train': 0.7496110200881958} 08/31/2021 15:13:10 - INFO - __main__ - Step 143233: {'lr': 2.575490394300495e-06, 'samples': 27500736, 'steps': 143232, 'loss/train': 0.7684992551803589} 08/31/2021 15:13:10 - INFO - __main__ - Step 143234: {'lr': 2.5747306807893665e-06, 'samples': 27500928, 'steps': 143233, 'loss/train': 1.0824459791183472} 08/31/2021 15:13:10 - INFO - __main__ - Step 143235: {'lr': 2.5739710787642534e-06, 'samples': 27501120, 'steps': 143234, 'loss/train': 1.5213816165924072} 08/31/2021 15:13:11 - INFO - __main__ - Step 143236: {'lr': 2.57321158822546e-06, 'samples': 27501312, 'steps': 143235, 'loss/train': 1.4224649667739868} 08/31/2021 15:13:11 - INFO - __main__ - Step 143237: {'lr': 2.572452209173404e-06, 'samples': 27501504, 'steps': 143236, 'loss/train': 0.574258029460907} 08/31/2021 15:13:13 - INFO - __main__ - Step 143238: {'lr': 2.5716929416083336e-06, 'samples': 27501696, 'steps': 143237, 'loss/train': 0.977538526058197} 08/31/2021 15:13:13 - INFO - __main__ - Step 143239: {'lr': 2.570933785530666e-06, 'samples': 27501888, 'steps': 143238, 'loss/train': 0.3369928300380707} 08/31/2021 15:13:14 - INFO - __main__ - Step 143240: {'lr': 2.570174740940734e-06, 'samples': 27502080, 'steps': 143239, 'loss/train': 1.0512782335281372} 08/31/2021 15:13:14 - INFO - __main__ - Step 143241: {'lr': 2.569415807838843e-06, 'samples': 27502272, 'steps': 143240, 'loss/train': 1.3435204029083252} 08/31/2021 15:13:14 - INFO - __main__ - Step 143242: {'lr': 2.568656986225354e-06, 'samples': 27502464, 'steps': 143241, 'loss/train': 1.36237633228302} 08/31/2021 15:13:15 - INFO - __main__ - Step 143243: {'lr': 2.5678982761005997e-06, 'samples': 27502656, 'steps': 143242, 'loss/train': 1.2315436601638794} 08/31/2021 15:13:16 - INFO - __main__ - Step 143244: {'lr': 2.5671396774649412e-06, 'samples': 27502848, 'steps': 143243, 'loss/train': 0.622775137424469} 08/31/2021 15:13:17 - INFO - __main__ - Step 143245: {'lr': 2.5663811903187117e-06, 'samples': 27503040, 'steps': 143244, 'loss/train': 1.3325825929641724} 08/31/2021 15:13:17 - INFO - __main__ - Step 143246: {'lr': 2.5656228146622718e-06, 'samples': 27503232, 'steps': 143245, 'loss/train': 1.2007296085357666} 08/31/2021 15:13:17 - INFO - __main__ - Step 143247: {'lr': 2.5648645504959265e-06, 'samples': 27503424, 'steps': 143246, 'loss/train': 0.571899950504303} 08/31/2021 15:13:18 - INFO - __main__ - Step 143248: {'lr': 2.5641063978200375e-06, 'samples': 27503616, 'steps': 143247, 'loss/train': 0.4737403392791748} 08/31/2021 15:13:20 - INFO - __main__ - Step 143249: {'lr': 2.563348356634965e-06, 'samples': 27503808, 'steps': 143248, 'loss/train': 2.1186070442199707} 08/31/2021 15:13:21 - INFO - __main__ - Step 143250: {'lr': 2.5625904269409863e-06, 'samples': 27504000, 'steps': 143249, 'loss/train': 1.442833662033081} 08/31/2021 15:13:21 - INFO - __main__ - Step 143251: {'lr': 2.561832608738518e-06, 'samples': 27504192, 'steps': 143250, 'loss/train': 1.1061269044876099} 08/31/2021 15:13:21 - INFO - __main__ - Step 143252: {'lr': 2.561074902027866e-06, 'samples': 27504384, 'steps': 143251, 'loss/train': 1.6942709684371948} 08/31/2021 15:13:22 - INFO - __main__ - Step 143253: {'lr': 2.560317306809362e-06, 'samples': 27504576, 'steps': 143252, 'loss/train': 1.0802258253097534} 08/31/2021 15:13:23 - INFO - __main__ - Step 143254: {'lr': 2.5595598230833684e-06, 'samples': 27504768, 'steps': 143253, 'loss/train': 0.9916514158248901} 08/31/2021 15:13:24 - INFO - __main__ - Step 143255: {'lr': 2.558802450850217e-06, 'samples': 27504960, 'steps': 143254, 'loss/train': 0.7235024571418762} 08/31/2021 15:13:24 - INFO - __main__ - Step 143256: {'lr': 2.55804519011027e-06, 'samples': 27505152, 'steps': 143255, 'loss/train': 1.1670643091201782} 08/31/2021 15:13:24 - INFO - __main__ - Step 143257: {'lr': 2.557288040863831e-06, 'samples': 27505344, 'steps': 143256, 'loss/train': 1.3496123552322388} 08/31/2021 15:13:25 - INFO - __main__ - Step 143258: {'lr': 2.556531003111262e-06, 'samples': 27505536, 'steps': 143257, 'loss/train': 1.6814491748809814} 08/31/2021 15:13:25 - INFO - __main__ - Step 143259: {'lr': 2.555774076852896e-06, 'samples': 27505728, 'steps': 143258, 'loss/train': 1.5364198684692383} 08/31/2021 15:13:27 - INFO - __main__ - Step 143260: {'lr': 2.5550172620890933e-06, 'samples': 27505920, 'steps': 143259, 'loss/train': 0.8221363425254822} 08/31/2021 15:13:27 - INFO - __main__ - Step 143261: {'lr': 2.5542605588201597e-06, 'samples': 27506112, 'steps': 143260, 'loss/train': 1.3169469833374023} 08/31/2021 15:13:27 - INFO - __main__ - Step 143262: {'lr': 2.5535039670464833e-06, 'samples': 27506304, 'steps': 143261, 'loss/train': 0.08410733938217163} 08/31/2021 15:13:28 - INFO - __main__ - Step 143263: {'lr': 2.5527474867683697e-06, 'samples': 27506496, 'steps': 143262, 'loss/train': 0.8303729295730591} 08/31/2021 15:13:28 - INFO - __main__ - Step 143264: {'lr': 2.5519911179861523e-06, 'samples': 27506688, 'steps': 143263, 'loss/train': 0.5710972547531128} 08/31/2021 15:13:30 - INFO - __main__ - Step 143265: {'lr': 2.551234860700219e-06, 'samples': 27506880, 'steps': 143264, 'loss/train': 0.6383888125419617} 08/31/2021 15:13:30 - INFO - __main__ - Step 143266: {'lr': 2.5504787149108756e-06, 'samples': 27507072, 'steps': 143265, 'loss/train': 1.8431884050369263} 08/31/2021 15:13:30 - INFO - __main__ - Step 143267: {'lr': 2.5497226806184548e-06, 'samples': 27507264, 'steps': 143266, 'loss/train': 0.9293462038040161} 08/31/2021 15:13:31 - INFO - __main__ - Step 143268: {'lr': 2.548966757823318e-06, 'samples': 27507456, 'steps': 143267, 'loss/train': 0.08545824140310287} 08/31/2021 15:13:31 - INFO - __main__ - Step 143269: {'lr': 2.5482109465257975e-06, 'samples': 27507648, 'steps': 143268, 'loss/train': 0.9325500726699829} 08/31/2021 15:13:33 - INFO - __main__ - Step 143270: {'lr': 2.547455246726227e-06, 'samples': 27507840, 'steps': 143269, 'loss/train': 1.434705376625061} 08/31/2021 15:13:33 - INFO - __main__ - Step 143271: {'lr': 2.546699658424939e-06, 'samples': 27508032, 'steps': 143270, 'loss/train': 1.0881072282791138} 08/31/2021 15:13:34 - INFO - __main__ - Step 143272: {'lr': 2.5459441816223504e-06, 'samples': 27508224, 'steps': 143271, 'loss/train': 0.09017053246498108} 08/31/2021 15:13:34 - INFO - __main__ - Step 143273: {'lr': 2.5451888163186833e-06, 'samples': 27508416, 'steps': 143272, 'loss/train': 0.10387692600488663} 08/31/2021 15:13:34 - INFO - __main__ - Step 143274: {'lr': 2.5444335625143533e-06, 'samples': 27508608, 'steps': 143273, 'loss/train': 1.2643132209777832} 08/31/2021 15:13:36 - INFO - __main__ - Step 143275: {'lr': 2.543678420209694e-06, 'samples': 27508800, 'steps': 143274, 'loss/train': 1.024057388305664} 08/31/2021 15:13:37 - INFO - __main__ - Step 143276: {'lr': 2.5429233894050108e-06, 'samples': 27508992, 'steps': 143275, 'loss/train': 0.9877641201019287} 08/31/2021 15:13:37 - INFO - __main__ - Step 143277: {'lr': 2.542168470100692e-06, 'samples': 27509184, 'steps': 143276, 'loss/train': 1.0394834280014038} 08/31/2021 15:13:38 - INFO - __main__ - Step 143278: {'lr': 2.541413662297043e-06, 'samples': 27509376, 'steps': 143277, 'loss/train': 1.1051907539367676} 08/31/2021 15:13:38 - INFO - __main__ - Step 143279: {'lr': 2.5406589659944245e-06, 'samples': 27509568, 'steps': 143278, 'loss/train': 0.01412678137421608} 08/31/2021 15:13:38 - INFO - __main__ - Step 143280: {'lr': 2.5399043811931423e-06, 'samples': 27509760, 'steps': 143279, 'loss/train': 0.7974869012832642} 08/31/2021 15:13:40 - INFO - __main__ - Step 143281: {'lr': 2.5391499078935845e-06, 'samples': 27509952, 'steps': 143280, 'loss/train': 0.9956141114234924} 08/31/2021 15:13:40 - INFO - __main__ - Step 143282: {'lr': 2.5383955460960564e-06, 'samples': 27510144, 'steps': 143281, 'loss/train': 0.34692978858947754} 08/31/2021 15:13:41 - INFO - __main__ - Step 143283: {'lr': 2.537641295800891e-06, 'samples': 27510336, 'steps': 143282, 'loss/train': 0.8778181672096252} 08/31/2021 15:13:41 - INFO - __main__ - Step 143284: {'lr': 2.5368871570084772e-06, 'samples': 27510528, 'steps': 143283, 'loss/train': 0.03881600871682167} 08/31/2021 15:13:41 - INFO - __main__ - Step 143285: {'lr': 2.5361331297191203e-06, 'samples': 27510720, 'steps': 143284, 'loss/train': 0.667392909526825} 08/31/2021 15:13:42 - INFO - __main__ - Step 143286: {'lr': 2.535379213933153e-06, 'samples': 27510912, 'steps': 143285, 'loss/train': 0.9565322399139404} 08/31/2021 15:13:43 - INFO - __main__ - Step 143287: {'lr': 2.5346254096509368e-06, 'samples': 27511104, 'steps': 143286, 'loss/train': 0.8129144310951233} 08/31/2021 15:13:44 - INFO - __main__ - Step 143288: {'lr': 2.5338717168727767e-06, 'samples': 27511296, 'steps': 143287, 'loss/train': 1.5723618268966675} 08/31/2021 15:13:44 - INFO - __main__ - Step 143289: {'lr': 2.533118135599061e-06, 'samples': 27511488, 'steps': 143288, 'loss/train': 0.8392542600631714} 08/31/2021 15:13:44 - INFO - __main__ - Step 143290: {'lr': 2.5323646658300945e-06, 'samples': 27511680, 'steps': 143289, 'loss/train': 0.03193729743361473} 08/31/2021 15:13:45 - INFO - __main__ - Step 143291: {'lr': 2.5316113075662115e-06, 'samples': 27511872, 'steps': 143290, 'loss/train': 1.374711513519287} 08/31/2021 15:13:47 - INFO - __main__ - Step 143292: {'lr': 2.5308580608077726e-06, 'samples': 27512064, 'steps': 143291, 'loss/train': 1.28076171875} 08/31/2021 15:13:47 - INFO - __main__ - Step 143293: {'lr': 2.53010492555511e-06, 'samples': 27512256, 'steps': 143292, 'loss/train': 0.8221546411514282} 08/31/2021 15:13:48 - INFO - __main__ - Step 143294: {'lr': 2.5293519018085575e-06, 'samples': 27512448, 'steps': 143293, 'loss/train': 0.21619673073291779} 08/31/2021 15:13:48 - INFO - __main__ - Step 143295: {'lr': 2.528598989568476e-06, 'samples': 27512640, 'steps': 143294, 'loss/train': 0.17052461206912994} 08/31/2021 15:13:48 - INFO - __main__ - Step 143296: {'lr': 2.527846188835198e-06, 'samples': 27512832, 'steps': 143295, 'loss/train': 1.9371305704116821} 08/31/2021 15:13:50 - INFO - __main__ - Step 143297: {'lr': 2.5270934996090287e-06, 'samples': 27513024, 'steps': 143296, 'loss/train': 1.2293287515640259} 08/31/2021 15:13:51 - INFO - __main__ - Step 143298: {'lr': 2.52634092189033e-06, 'samples': 27513216, 'steps': 143297, 'loss/train': 1.512026309967041} 08/31/2021 15:13:51 - INFO - __main__ - Step 143299: {'lr': 2.5255884556794896e-06, 'samples': 27513408, 'steps': 143298, 'loss/train': 0.4751892685890198} 08/31/2021 15:13:51 - INFO - __main__ - Step 143300: {'lr': 2.5248361009767573e-06, 'samples': 27513600, 'steps': 143299, 'loss/train': 1.5627399682998657} 08/31/2021 15:13:52 - INFO - __main__ - Step 143301: {'lr': 2.524083857782522e-06, 'samples': 27513792, 'steps': 143300, 'loss/train': 1.25809645652771} 08/31/2021 15:13:52 - INFO - __main__ - Step 143302: {'lr': 2.5233317260971167e-06, 'samples': 27513984, 'steps': 143301, 'loss/train': 0.019668838009238243} 08/31/2021 15:13:54 - INFO - __main__ - Step 143303: {'lr': 2.5225797059208745e-06, 'samples': 27514176, 'steps': 143302, 'loss/train': 0.029083436354994774} 08/31/2021 15:13:54 - INFO - __main__ - Step 143304: {'lr': 2.5218277972541557e-06, 'samples': 27514368, 'steps': 143303, 'loss/train': 0.9477612972259521} 08/31/2021 15:13:55 - INFO - __main__ - Step 143305: {'lr': 2.5210760000972666e-06, 'samples': 27514560, 'steps': 143304, 'loss/train': 0.9919060468673706} 08/31/2021 15:13:55 - INFO - __main__ - Step 143306: {'lr': 2.520324314450567e-06, 'samples': 27514752, 'steps': 143305, 'loss/train': 1.2991658449172974} 08/31/2021 15:13:55 - INFO - __main__ - Step 143307: {'lr': 2.519572740314391e-06, 'samples': 27514944, 'steps': 143306, 'loss/train': 1.1184004545211792} 08/31/2021 15:13:57 - INFO - __main__ - Step 143308: {'lr': 2.5188212776890705e-06, 'samples': 27515136, 'steps': 143307, 'loss/train': 1.265514850616455} 08/31/2021 15:13:57 - INFO - __main__ - Step 143309: {'lr': 2.5180699265749673e-06, 'samples': 27515328, 'steps': 143308, 'loss/train': 1.3964670896530151} 08/31/2021 15:13:58 - INFO - __main__ - Step 143310: {'lr': 2.5173186869723865e-06, 'samples': 27515520, 'steps': 143309, 'loss/train': 1.2892379760742188} 08/31/2021 15:13:58 - INFO - __main__ - Step 143311: {'lr': 2.5165675588816885e-06, 'samples': 27515712, 'steps': 143310, 'loss/train': 0.5711280107498169} 08/31/2021 15:13:59 - INFO - __main__ - Step 143312: {'lr': 2.5158165423032067e-06, 'samples': 27515904, 'steps': 143311, 'loss/train': 0.994391679763794} 08/31/2021 15:14:00 - INFO - __main__ - Step 143313: {'lr': 2.5150656372373014e-06, 'samples': 27516096, 'steps': 143312, 'loss/train': 2.135586977005005} 08/31/2021 15:14:01 - INFO - __main__ - Step 143314: {'lr': 2.514314843684251e-06, 'samples': 27516288, 'steps': 143313, 'loss/train': 2.5875866413116455} 08/31/2021 15:14:01 - INFO - __main__ - Step 143315: {'lr': 2.5135641616444437e-06, 'samples': 27516480, 'steps': 143314, 'loss/train': 0.01567695662379265} 08/31/2021 15:14:02 - INFO - __main__ - Step 143316: {'lr': 2.5128135911182125e-06, 'samples': 27516672, 'steps': 143315, 'loss/train': 1.6057184934616089} 08/31/2021 15:14:02 - INFO - __main__ - Step 143317: {'lr': 2.5120631321058907e-06, 'samples': 27516864, 'steps': 143316, 'loss/train': 1.1991591453552246} 08/31/2021 15:14:02 - INFO - __main__ - Step 143318: {'lr': 2.511312784607811e-06, 'samples': 27517056, 'steps': 143317, 'loss/train': 0.38490620255470276} 08/31/2021 15:14:04 - INFO - __main__ - Step 143319: {'lr': 2.5105625486243067e-06, 'samples': 27517248, 'steps': 143318, 'loss/train': 0.8738009333610535} 08/31/2021 15:14:04 - INFO - __main__ - Step 143320: {'lr': 2.5098124241557387e-06, 'samples': 27517440, 'steps': 143319, 'loss/train': 1.1964019536972046} 08/31/2021 15:14:05 - INFO - __main__ - Step 143321: {'lr': 2.509062411202412e-06, 'samples': 27517632, 'steps': 143320, 'loss/train': 0.8211725950241089} 08/31/2021 15:14:05 - INFO - __main__ - Step 143322: {'lr': 2.5083125097646875e-06, 'samples': 27517824, 'steps': 143321, 'loss/train': 1.4714758396148682} 08/31/2021 15:14:05 - INFO - __main__ - Step 143323: {'lr': 2.5075627198428985e-06, 'samples': 27518016, 'steps': 143322, 'loss/train': 0.9911873936653137} 08/31/2021 15:14:07 - INFO - __main__ - Step 143324: {'lr': 2.506813041437378e-06, 'samples': 27518208, 'steps': 143323, 'loss/train': 1.2196186780929565} 08/31/2021 15:14:07 - INFO - __main__ - Step 143325: {'lr': 2.5060634745484867e-06, 'samples': 27518400, 'steps': 143324, 'loss/train': 1.2224534749984741} 08/31/2021 15:14:08 - INFO - __main__ - Step 143326: {'lr': 2.50531401917653e-06, 'samples': 27518592, 'steps': 143325, 'loss/train': 0.11692921072244644} 08/31/2021 15:14:08 - INFO - __main__ - Step 143327: {'lr': 2.5045646753218687e-06, 'samples': 27518784, 'steps': 143326, 'loss/train': 1.4015562534332275} 08/31/2021 15:14:09 - INFO - __main__ - Step 143328: {'lr': 2.503815442984836e-06, 'samples': 27518976, 'steps': 143327, 'loss/train': 1.5892250537872314} 08/31/2021 15:14:09 - INFO - __main__ - Step 143329: {'lr': 2.5030663221657646e-06, 'samples': 27519168, 'steps': 143328, 'loss/train': 1.2706971168518066} 08/31/2021 15:14:11 - INFO - __main__ - Step 143330: {'lr': 2.5023173128649603e-06, 'samples': 27519360, 'steps': 143329, 'loss/train': 0.7424982786178589} 08/31/2021 15:14:11 - INFO - __main__ - Step 143331: {'lr': 2.5015684150828112e-06, 'samples': 27519552, 'steps': 143330, 'loss/train': 0.774270236492157} 08/31/2021 15:14:12 - INFO - __main__ - Step 143332: {'lr': 2.5008196288196504e-06, 'samples': 27519744, 'steps': 143331, 'loss/train': 0.01521974429488182} 08/31/2021 15:14:12 - INFO - __main__ - Step 143333: {'lr': 2.500070954075784e-06, 'samples': 27519936, 'steps': 143332, 'loss/train': 0.9832783937454224} 08/31/2021 15:14:12 - INFO - __main__ - Step 143334: {'lr': 2.499322390851572e-06, 'samples': 27520128, 'steps': 143333, 'loss/train': 1.0237151384353638} 08/31/2021 15:14:13 - INFO - __main__ - Step 143335: {'lr': 2.498573939147347e-06, 'samples': 27520320, 'steps': 143334, 'loss/train': 1.097272276878357} 08/31/2021 15:14:14 - INFO - __main__ - Step 143336: {'lr': 2.4978255989634436e-06, 'samples': 27520512, 'steps': 143335, 'loss/train': 0.18986772000789642} 08/31/2021 15:14:15 - INFO - __main__ - Step 143337: {'lr': 2.4970773703002216e-06, 'samples': 27520704, 'steps': 143336, 'loss/train': 0.8053091168403625} 08/31/2021 15:14:15 - INFO - __main__ - Step 143338: {'lr': 2.4963292531579584e-06, 'samples': 27520896, 'steps': 143337, 'loss/train': 0.9392197132110596} 08/31/2021 15:14:15 - INFO - __main__ - Step 143339: {'lr': 2.495581247537071e-06, 'samples': 27521088, 'steps': 143338, 'loss/train': 0.4058968424797058} 08/31/2021 15:14:16 - INFO - __main__ - Step 143340: {'lr': 2.4948333534378364e-06, 'samples': 27521280, 'steps': 143339, 'loss/train': 1.4934369325637817} 08/31/2021 15:14:17 - INFO - __main__ - Step 143341: {'lr': 2.494085570860616e-06, 'samples': 27521472, 'steps': 143340, 'loss/train': 1.1340471506118774} 08/31/2021 15:14:18 - INFO - __main__ - Step 143342: {'lr': 2.493337899805742e-06, 'samples': 27521664, 'steps': 143341, 'loss/train': 0.7995451092720032} 08/31/2021 15:14:18 - INFO - __main__ - Step 143343: {'lr': 2.492590340273548e-06, 'samples': 27521856, 'steps': 143342, 'loss/train': 0.9948822855949402} 08/31/2021 15:14:18 - INFO - __main__ - Step 143344: {'lr': 2.4918428922643676e-06, 'samples': 27522048, 'steps': 143343, 'loss/train': 1.63295316696167} 08/31/2021 15:14:19 - INFO - __main__ - Step 143345: {'lr': 2.4910955557785332e-06, 'samples': 27522240, 'steps': 143344, 'loss/train': 1.4981685876846313} 08/31/2021 15:14:19 - INFO - __main__ - Step 143346: {'lr': 2.4903483308164054e-06, 'samples': 27522432, 'steps': 143345, 'loss/train': 1.102403163909912} 08/31/2021 15:14:21 - INFO - __main__ - Step 143347: {'lr': 2.48960121737829e-06, 'samples': 27522624, 'steps': 143346, 'loss/train': 0.29577431082725525} 08/31/2021 15:14:21 - INFO - __main__ - Step 143348: {'lr': 2.4888542154645756e-06, 'samples': 27522816, 'steps': 143347, 'loss/train': 1.2429999113082886} 08/31/2021 15:14:21 - INFO - __main__ - Step 143349: {'lr': 2.4881073250755394e-06, 'samples': 27523008, 'steps': 143348, 'loss/train': 0.7326904535293579} 08/31/2021 15:14:22 - INFO - __main__ - Step 143350: {'lr': 2.487360546211542e-06, 'samples': 27523200, 'steps': 143349, 'loss/train': 0.8229616284370422} 08/31/2021 15:14:22 - INFO - __main__ - Step 143351: {'lr': 2.4866138788729176e-06, 'samples': 27523392, 'steps': 143350, 'loss/train': 1.2251991033554077} 08/31/2021 15:14:24 - INFO - __main__ - Step 143352: {'lr': 2.4858673230600258e-06, 'samples': 27523584, 'steps': 143351, 'loss/train': 3.1428046226501465} 08/31/2021 15:14:24 - INFO - __main__ - Step 143353: {'lr': 2.4851208787732003e-06, 'samples': 27523776, 'steps': 143352, 'loss/train': 1.804120659828186} 08/31/2021 15:14:24 - INFO - __main__ - Step 143354: {'lr': 2.4843745460127187e-06, 'samples': 27523968, 'steps': 143353, 'loss/train': 1.2122284173965454} 08/31/2021 15:14:25 - INFO - __main__ - Step 143355: {'lr': 2.4836283247789693e-06, 'samples': 27524160, 'steps': 143354, 'loss/train': 0.795992374420166} 08/31/2021 15:14:25 - INFO - __main__ - Step 143356: {'lr': 2.4828822150722853e-06, 'samples': 27524352, 'steps': 143355, 'loss/train': 1.1901863813400269} 08/31/2021 15:14:27 - INFO - __main__ - Step 143357: {'lr': 2.4821362168929718e-06, 'samples': 27524544, 'steps': 143356, 'loss/train': 0.8781167268753052} 08/31/2021 15:14:27 - INFO - __main__ - Step 143358: {'lr': 2.4813903302414175e-06, 'samples': 27524736, 'steps': 143357, 'loss/train': 1.2381716966629028} 08/31/2021 15:14:28 - INFO - __main__ - Step 143359: {'lr': 2.480644555117928e-06, 'samples': 27524928, 'steps': 143358, 'loss/train': 1.1689579486846924} 08/31/2021 15:14:28 - INFO - __main__ - Step 143360: {'lr': 2.4798988915228083e-06, 'samples': 27525120, 'steps': 143359, 'loss/train': 0.7421437501907349} 08/31/2021 15:14:28 - INFO - __main__ - Step 143361: {'lr': 2.4791533394564467e-06, 'samples': 27525312, 'steps': 143360, 'loss/train': 1.0742138624191284} 08/31/2021 15:14:30 - INFO - __main__ - Step 143362: {'lr': 2.478407898919177e-06, 'samples': 27525504, 'steps': 143361, 'loss/train': 1.293953776359558} 08/31/2021 15:14:31 - INFO - __main__ - Step 143363: {'lr': 2.477662569911304e-06, 'samples': 27525696, 'steps': 143362, 'loss/train': 1.2809112071990967} 08/31/2021 15:14:31 - INFO - __main__ - Step 143364: {'lr': 2.476917352433161e-06, 'samples': 27525888, 'steps': 143363, 'loss/train': 0.9326861500740051} 08/31/2021 15:14:31 - INFO - __main__ - Step 143365: {'lr': 2.476172246485109e-06, 'samples': 27526080, 'steps': 143364, 'loss/train': 1.4176710844039917} 08/31/2021 15:14:32 - INFO - __main__ - Step 143366: {'lr': 2.4754272520674804e-06, 'samples': 27526272, 'steps': 143365, 'loss/train': 0.3104593753814697} 08/31/2021 15:14:34 - INFO - __main__ - Step 143367: {'lr': 2.4746823691806362e-06, 'samples': 27526464, 'steps': 143366, 'loss/train': 0.45589837431907654} 08/31/2021 15:14:34 - INFO - __main__ - Step 143368: {'lr': 2.4739375978248268e-06, 'samples': 27526656, 'steps': 143367, 'loss/train': 0.5707389116287231} 08/31/2021 15:14:34 - INFO - __main__ - Step 143369: {'lr': 2.473192938000468e-06, 'samples': 27526848, 'steps': 143368, 'loss/train': 0.9575861692428589} 08/31/2021 15:14:35 - INFO - __main__ - Step 143370: {'lr': 2.4724483897078653e-06, 'samples': 27527040, 'steps': 143369, 'loss/train': 0.2613208293914795} 08/31/2021 15:14:35 - INFO - __main__ - Step 143371: {'lr': 2.4717039529473516e-06, 'samples': 27527232, 'steps': 143370, 'loss/train': 1.4199614524841309} 08/31/2021 15:14:37 - INFO - __main__ - Step 143372: {'lr': 2.4709596277192605e-06, 'samples': 27527424, 'steps': 143371, 'loss/train': 0.8702427744865417} 08/31/2021 15:14:37 - INFO - __main__ - Step 143373: {'lr': 2.470215414023952e-06, 'samples': 27527616, 'steps': 143372, 'loss/train': 1.0461235046386719} 08/31/2021 15:14:38 - INFO - __main__ - Step 143374: {'lr': 2.469471311861732e-06, 'samples': 27527808, 'steps': 143373, 'loss/train': 1.336685061454773} 08/31/2021 15:14:38 - INFO - __main__ - Step 143375: {'lr': 2.468727321232961e-06, 'samples': 27528000, 'steps': 143374, 'loss/train': 0.5689308643341064} 08/31/2021 15:14:38 - INFO - __main__ - Step 143376: {'lr': 2.467983442137972e-06, 'samples': 27528192, 'steps': 143375, 'loss/train': 1.1463013887405396} 08/31/2021 15:14:40 - INFO - __main__ - Step 143377: {'lr': 2.467239674577071e-06, 'samples': 27528384, 'steps': 143376, 'loss/train': 0.2574884295463562} 08/31/2021 15:14:40 - INFO - __main__ - Step 143378: {'lr': 2.466496018550618e-06, 'samples': 27528576, 'steps': 143377, 'loss/train': 1.3209483623504639} 08/31/2021 15:14:41 - INFO - __main__ - Step 143379: {'lr': 2.4657524740589187e-06, 'samples': 27528768, 'steps': 143378, 'loss/train': 1.1171075105667114} 08/31/2021 15:14:41 - INFO - __main__ - Step 143380: {'lr': 2.4650090411023895e-06, 'samples': 27528960, 'steps': 143379, 'loss/train': 1.0606954097747803} 08/31/2021 15:14:41 - INFO - __main__ - Step 143381: {'lr': 2.464265719681252e-06, 'samples': 27529152, 'steps': 143380, 'loss/train': 1.3223999738693237} 08/31/2021 15:14:43 - INFO - __main__ - Step 143382: {'lr': 2.4635225097959234e-06, 'samples': 27529344, 'steps': 143381, 'loss/train': 1.217580795288086} 08/31/2021 15:14:43 - INFO - __main__ - Step 143383: {'lr': 2.4627794114467086e-06, 'samples': 27529536, 'steps': 143382, 'loss/train': 1.3056660890579224} 08/31/2021 15:14:43 - INFO - __main__ - Step 143384: {'lr': 2.46203642463394e-06, 'samples': 27529728, 'steps': 143383, 'loss/train': 1.0064759254455566} 08/31/2021 15:14:44 - INFO - __main__ - Step 143385: {'lr': 2.4612935493579513e-06, 'samples': 27529920, 'steps': 143384, 'loss/train': 1.2091691493988037} 08/31/2021 15:14:44 - INFO - __main__ - Step 143386: {'lr': 2.4605507856191035e-06, 'samples': 27530112, 'steps': 143385, 'loss/train': 1.1364928483963013} 08/31/2021 15:14:45 - INFO - __main__ - Step 143387: {'lr': 2.4598081334177015e-06, 'samples': 27530304, 'steps': 143386, 'loss/train': 1.1750187873840332} 08/31/2021 15:14:46 - INFO - __main__ - Step 143388: {'lr': 2.4590655927540783e-06, 'samples': 27530496, 'steps': 143387, 'loss/train': 0.885895311832428} 08/31/2021 15:14:47 - INFO - __main__ - Step 143389: {'lr': 2.458323163628595e-06, 'samples': 27530688, 'steps': 143388, 'loss/train': 0.3945847749710083} 08/31/2021 15:14:47 - INFO - __main__ - Step 143390: {'lr': 2.4575808460415573e-06, 'samples': 27530880, 'steps': 143389, 'loss/train': 0.6139914393424988} 08/31/2021 15:14:48 - INFO - __main__ - Step 143391: {'lr': 2.4568386399933253e-06, 'samples': 27531072, 'steps': 143390, 'loss/train': 1.1626217365264893} 08/31/2021 15:14:48 - INFO - __main__ - Step 143392: {'lr': 2.456096545484232e-06, 'samples': 27531264, 'steps': 143391, 'loss/train': 1.3969584703445435} 08/31/2021 15:14:49 - INFO - __main__ - Step 143393: {'lr': 2.4553545625145835e-06, 'samples': 27531456, 'steps': 143392, 'loss/train': 0.021220140159130096} 08/31/2021 15:14:50 - INFO - __main__ - Step 143394: {'lr': 2.45461269108474e-06, 'samples': 27531648, 'steps': 143393, 'loss/train': 1.3118488788604736} 08/31/2021 15:14:50 - INFO - __main__ - Step 143395: {'lr': 2.453870931195035e-06, 'samples': 27531840, 'steps': 143394, 'loss/train': 0.7277050614356995} 08/31/2021 15:14:51 - INFO - __main__ - Step 143396: {'lr': 2.453129282845801e-06, 'samples': 27532032, 'steps': 143395, 'loss/train': 1.4699995517730713} 08/31/2021 15:14:51 - INFO - __main__ - Step 143397: {'lr': 2.4523877460373434e-06, 'samples': 27532224, 'steps': 143396, 'loss/train': 0.5459203720092773} 08/31/2021 15:14:53 - INFO - __main__ - Step 143398: {'lr': 2.4516463207700235e-06, 'samples': 27532416, 'steps': 143397, 'loss/train': 1.734177589416504} 08/31/2021 15:14:53 - INFO - __main__ - Step 143399: {'lr': 2.4509050070442017e-06, 'samples': 27532608, 'steps': 143398, 'loss/train': 1.2756634950637817} 08/31/2021 15:14:53 - INFO - __main__ - Step 143400: {'lr': 2.450163804860156e-06, 'samples': 27532800, 'steps': 143399, 'loss/train': 1.0073307752609253} 08/31/2021 15:14:54 - INFO - __main__ - Step 143401: {'lr': 2.4494227142182467e-06, 'samples': 27532992, 'steps': 143400, 'loss/train': 1.0054301023483276} 08/31/2021 15:14:54 - INFO - __main__ - Step 143402: {'lr': 2.4486817351188073e-06, 'samples': 27533184, 'steps': 143401, 'loss/train': 0.41171011328697205} 08/31/2021 15:14:56 - INFO - __main__ - Step 143403: {'lr': 2.4479408675621707e-06, 'samples': 27533376, 'steps': 143402, 'loss/train': 0.668194591999054} 08/31/2021 15:14:56 - INFO - __main__ - Step 143404: {'lr': 2.4472001115486695e-06, 'samples': 27533568, 'steps': 143403, 'loss/train': 0.06821220368146896} 08/31/2021 15:14:56 - INFO - __main__ - Step 143405: {'lr': 2.4464594670786655e-06, 'samples': 27533760, 'steps': 143404, 'loss/train': 0.8517752289772034} 08/31/2021 15:14:57 - INFO - __main__ - Step 143406: {'lr': 2.4457189341524634e-06, 'samples': 27533952, 'steps': 143405, 'loss/train': 0.23626048862934113} 08/31/2021 15:14:57 - INFO - __main__ - Step 143407: {'lr': 2.4449785127703683e-06, 'samples': 27534144, 'steps': 143406, 'loss/train': 0.5921896696090698} 08/31/2021 15:14:59 - INFO - __main__ - Step 143408: {'lr': 2.4442382029327693e-06, 'samples': 27534336, 'steps': 143407, 'loss/train': 1.2404754161834717} 08/31/2021 15:14:59 - INFO - __main__ - Step 143409: {'lr': 2.4434980046399715e-06, 'samples': 27534528, 'steps': 143408, 'loss/train': 1.0730204582214355} 08/31/2021 15:14:59 - INFO - __main__ - Step 143410: {'lr': 2.4427579178923076e-06, 'samples': 27534720, 'steps': 143409, 'loss/train': 1.1097891330718994} 08/31/2021 15:15:00 - INFO - __main__ - Step 143411: {'lr': 2.442017942690139e-06, 'samples': 27534912, 'steps': 143410, 'loss/train': 1.1198396682739258} 08/31/2021 15:15:00 - INFO - __main__ - Step 143412: {'lr': 2.441278079033743e-06, 'samples': 27535104, 'steps': 143411, 'loss/train': 1.1079262495040894} 08/31/2021 15:15:00 - INFO - __main__ - Step 143413: {'lr': 2.4405383269235082e-06, 'samples': 27535296, 'steps': 143412, 'loss/train': 1.4072544574737549} 08/31/2021 15:15:02 - INFO - __main__ - Step 143414: {'lr': 2.43979868635974e-06, 'samples': 27535488, 'steps': 143413, 'loss/train': 0.961877703666687} 08/31/2021 15:15:03 - INFO - __main__ - Step 143415: {'lr': 2.439059157342799e-06, 'samples': 27535680, 'steps': 143414, 'loss/train': 1.5552120208740234} 08/31/2021 15:15:03 - INFO - __main__ - Step 143416: {'lr': 2.438319739872963e-06, 'samples': 27535872, 'steps': 143415, 'loss/train': 0.7701666355133057} 08/31/2021 15:15:04 - INFO - __main__ - Step 143417: {'lr': 2.437580433950648e-06, 'samples': 27536064, 'steps': 143416, 'loss/train': 1.1054502725601196} 08/31/2021 15:15:04 - INFO - __main__ - Step 143418: {'lr': 2.4368412395761043e-06, 'samples': 27536256, 'steps': 143417, 'loss/train': 1.5349575281143188} 08/31/2021 15:15:05 - INFO - __main__ - Step 143419: {'lr': 2.436102156749692e-06, 'samples': 27536448, 'steps': 143418, 'loss/train': 1.30332612991333} 08/31/2021 15:15:06 - INFO - __main__ - Step 143420: {'lr': 2.435363185471773e-06, 'samples': 27536640, 'steps': 143419, 'loss/train': 1.2291359901428223} 08/31/2021 15:15:06 - INFO - __main__ - Step 143421: {'lr': 2.4346243257426514e-06, 'samples': 27536832, 'steps': 143420, 'loss/train': 0.4516160190105438} 08/31/2021 15:15:07 - INFO - __main__ - Step 143422: {'lr': 2.4338855775626613e-06, 'samples': 27537024, 'steps': 143421, 'loss/train': 0.9543395638465881} 08/31/2021 15:15:07 - INFO - __main__ - Step 143423: {'lr': 2.433146940932135e-06, 'samples': 27537216, 'steps': 143422, 'loss/train': 1.159040093421936} 08/31/2021 15:15:08 - INFO - __main__ - Step 143424: {'lr': 2.4324084158514336e-06, 'samples': 27537408, 'steps': 143423, 'loss/train': 0.9389001727104187} 08/31/2021 15:15:09 - INFO - __main__ - Step 143425: {'lr': 2.4316700023208626e-06, 'samples': 27537600, 'steps': 143424, 'loss/train': 1.5926059484481812} 08/31/2021 15:15:09 - INFO - __main__ - Step 143426: {'lr': 2.430931700340755e-06, 'samples': 27537792, 'steps': 143425, 'loss/train': 0.7133533954620361} 08/31/2021 15:15:10 - INFO - __main__ - Step 143427: {'lr': 2.4301935099114436e-06, 'samples': 27537984, 'steps': 143426, 'loss/train': 0.7435351014137268} 08/31/2021 15:15:10 - INFO - __main__ - Step 143428: {'lr': 2.4294554310332897e-06, 'samples': 27538176, 'steps': 143427, 'loss/train': 1.0688424110412598} 08/31/2021 15:15:11 - INFO - __main__ - Step 143429: {'lr': 2.428717463706598e-06, 'samples': 27538368, 'steps': 143428, 'loss/train': 0.8700969219207764} 08/31/2021 15:15:12 - INFO - __main__ - Step 143430: {'lr': 2.4279796079317016e-06, 'samples': 27538560, 'steps': 143429, 'loss/train': 1.0472768545150757} 08/31/2021 15:15:12 - INFO - __main__ - Step 143431: {'lr': 2.4272418637089346e-06, 'samples': 27538752, 'steps': 143430, 'loss/train': 0.7799927592277527} 08/31/2021 15:15:13 - INFO - __main__ - Step 143432: {'lr': 2.4265042310386287e-06, 'samples': 27538944, 'steps': 143431, 'loss/train': 1.3923118114471436} 08/31/2021 15:15:13 - INFO - __main__ - Step 143433: {'lr': 2.425766709921118e-06, 'samples': 27539136, 'steps': 143432, 'loss/train': 1.0760583877563477} 08/31/2021 15:15:14 - INFO - __main__ - Step 143434: {'lr': 2.4250293003567348e-06, 'samples': 27539328, 'steps': 143433, 'loss/train': 1.1049461364746094} 08/31/2021 15:15:15 - INFO - __main__ - Step 143435: {'lr': 2.4242920023458124e-06, 'samples': 27539520, 'steps': 143434, 'loss/train': 1.217383623123169} 08/31/2021 15:15:15 - INFO - __main__ - Step 143436: {'lr': 2.4235548158886846e-06, 'samples': 27539712, 'steps': 143435, 'loss/train': 1.0484832525253296} 08/31/2021 15:15:15 - INFO - __main__ - Step 143437: {'lr': 2.4228177409856832e-06, 'samples': 27539904, 'steps': 143436, 'loss/train': 0.573225736618042} 08/31/2021 15:15:16 - INFO - __main__ - Step 143438: {'lr': 2.42208077763717e-06, 'samples': 27540096, 'steps': 143437, 'loss/train': 1.1125096082687378} 08/31/2021 15:15:17 - INFO - __main__ - Step 143439: {'lr': 2.421343925843422e-06, 'samples': 27540288, 'steps': 143438, 'loss/train': 0.8862504959106445} 08/31/2021 15:15:18 - INFO - __main__ - Step 143440: {'lr': 2.4206071856048005e-06, 'samples': 27540480, 'steps': 143439, 'loss/train': 1.2045533657073975} 08/31/2021 15:15:18 - INFO - __main__ - Step 143441: {'lr': 2.4198705569216106e-06, 'samples': 27540672, 'steps': 143440, 'loss/train': 1.172961950302124} 08/31/2021 15:15:18 - INFO - __main__ - Step 143442: {'lr': 2.4191340397942405e-06, 'samples': 27540864, 'steps': 143441, 'loss/train': 1.5642211437225342} 08/31/2021 15:15:19 - INFO - __main__ - Step 143443: {'lr': 2.4183976342229684e-06, 'samples': 27541056, 'steps': 143442, 'loss/train': 0.9391852617263794} 08/31/2021 15:15:21 - INFO - __main__ - Step 143444: {'lr': 2.417661340208155e-06, 'samples': 27541248, 'steps': 143443, 'loss/train': 0.921647310256958} 08/31/2021 15:15:21 - INFO - __main__ - Step 143445: {'lr': 2.416925157750105e-06, 'samples': 27541440, 'steps': 143444, 'loss/train': 0.9203700423240662} 08/31/2021 15:15:22 - INFO - __main__ - Step 143446: {'lr': 2.41618908684918e-06, 'samples': 27541632, 'steps': 143445, 'loss/train': 0.9815099239349365} 08/31/2021 15:15:22 - INFO - __main__ - Step 143447: {'lr': 2.4154531275056845e-06, 'samples': 27541824, 'steps': 143446, 'loss/train': 1.0797958374023438} 08/31/2021 15:15:22 - INFO - __main__ - Step 143448: {'lr': 2.41471727971998e-06, 'samples': 27542016, 'steps': 143447, 'loss/train': 0.05123309791088104} 08/31/2021 15:15:23 - INFO - __main__ - Step 143449: {'lr': 2.4139815434923995e-06, 'samples': 27542208, 'steps': 143448, 'loss/train': 2.809079885482788} 08/31/2021 15:15:24 - INFO - __main__ - Step 143450: {'lr': 2.413245918823248e-06, 'samples': 27542400, 'steps': 143449, 'loss/train': 3.7438771724700928} 08/31/2021 15:15:25 - INFO - __main__ - Step 143451: {'lr': 2.412510405712859e-06, 'samples': 27542592, 'steps': 143450, 'loss/train': 1.5084829330444336} 08/31/2021 15:15:25 - INFO - __main__ - Step 143452: {'lr': 2.4117750041615926e-06, 'samples': 27542784, 'steps': 143451, 'loss/train': 1.2629464864730835} 08/31/2021 15:15:26 - INFO - __main__ - Step 143453: {'lr': 2.411039714169727e-06, 'samples': 27542976, 'steps': 143452, 'loss/train': 0.6127275228500366} 08/31/2021 15:15:26 - INFO - __main__ - Step 143454: {'lr': 2.4103045357376506e-06, 'samples': 27543168, 'steps': 143453, 'loss/train': 1.2145122289657593} 08/31/2021 15:15:28 - INFO - __main__ - Step 143455: {'lr': 2.409569468865669e-06, 'samples': 27543360, 'steps': 143454, 'loss/train': 0.08151309937238693} 08/31/2021 15:15:28 - INFO - __main__ - Step 143456: {'lr': 2.408834513554087e-06, 'samples': 27543552, 'steps': 143455, 'loss/train': 1.4329237937927246} 08/31/2021 15:15:28 - INFO - __main__ - Step 143457: {'lr': 2.4080996698032933e-06, 'samples': 27543744, 'steps': 143456, 'loss/train': 0.9261218309402466} 08/31/2021 15:15:29 - INFO - __main__ - Step 143458: {'lr': 2.407364937613593e-06, 'samples': 27543936, 'steps': 143457, 'loss/train': 1.3240069150924683} 08/31/2021 15:15:29 - INFO - __main__ - Step 143459: {'lr': 2.4066303169852923e-06, 'samples': 27544128, 'steps': 143458, 'loss/train': 0.8681619167327881} 08/31/2021 15:15:29 - INFO - __main__ - Step 143460: {'lr': 2.405895807918751e-06, 'samples': 27544320, 'steps': 143459, 'loss/train': 0.8260547518730164} 08/31/2021 15:15:31 - INFO - __main__ - Step 143461: {'lr': 2.4051614104143027e-06, 'samples': 27544512, 'steps': 143460, 'loss/train': 0.025068283081054688} 08/31/2021 15:15:32 - INFO - __main__ - Step 143462: {'lr': 2.4044271244722526e-06, 'samples': 27544704, 'steps': 143461, 'loss/train': 1.0818465948104858} 08/31/2021 15:15:32 - INFO - __main__ - Step 143463: {'lr': 2.4036929500929614e-06, 'samples': 27544896, 'steps': 143462, 'loss/train': 1.3614407777786255} 08/31/2021 15:15:32 - INFO - __main__ - Step 143464: {'lr': 2.402958887276735e-06, 'samples': 27545088, 'steps': 143463, 'loss/train': 1.2283668518066406} 08/31/2021 15:15:33 - INFO - __main__ - Step 143465: {'lr': 2.4022249360239057e-06, 'samples': 27545280, 'steps': 143464, 'loss/train': 0.7580286264419556} 08/31/2021 15:15:34 - INFO - __main__ - Step 143466: {'lr': 2.4014910963348348e-06, 'samples': 27545472, 'steps': 143465, 'loss/train': 1.096245527267456} 08/31/2021 15:15:35 - INFO - __main__ - Step 143467: {'lr': 2.4007573682098273e-06, 'samples': 27545664, 'steps': 143466, 'loss/train': 0.5502706170082092} 08/31/2021 15:15:35 - INFO - __main__ - Step 143468: {'lr': 2.400023751649216e-06, 'samples': 27545856, 'steps': 143467, 'loss/train': 0.12631045281887054} 08/31/2021 15:15:36 - INFO - __main__ - Step 143469: {'lr': 2.3992902466533072e-06, 'samples': 27546048, 'steps': 143468, 'loss/train': 0.800758421421051} 08/31/2021 15:15:36 - INFO - __main__ - Step 143470: {'lr': 2.3985568532224887e-06, 'samples': 27546240, 'steps': 143469, 'loss/train': 2.162898302078247} 08/31/2021 15:15:36 - INFO - __main__ - Step 143471: {'lr': 2.3978235713570386e-06, 'samples': 27546432, 'steps': 143470, 'loss/train': 0.7489755749702454} 08/31/2021 15:15:39 - INFO - __main__ - Step 143472: {'lr': 2.3970904010573167e-06, 'samples': 27546624, 'steps': 143471, 'loss/train': 0.9541181325912476} 08/31/2021 15:15:39 - INFO - __main__ - Step 143473: {'lr': 2.3963573423236573e-06, 'samples': 27546816, 'steps': 143472, 'loss/train': 1.4391512870788574} 08/31/2021 15:15:39 - INFO - __main__ - Step 143474: {'lr': 2.395624395156393e-06, 'samples': 27547008, 'steps': 143473, 'loss/train': 1.1650989055633545} 08/31/2021 15:15:40 - INFO - __main__ - Step 143475: {'lr': 2.3948915595558007e-06, 'samples': 27547200, 'steps': 143474, 'loss/train': 1.303499698638916} 08/31/2021 15:15:40 - INFO - __main__ - Step 143476: {'lr': 2.3941588355222697e-06, 'samples': 27547392, 'steps': 143475, 'loss/train': 1.4095267057418823} 08/31/2021 15:15:42 - INFO - __main__ - Step 143477: {'lr': 2.3934262230561055e-06, 'samples': 27547584, 'steps': 143476, 'loss/train': 1.2947173118591309} 08/31/2021 15:15:42 - INFO - __main__ - Step 143478: {'lr': 2.3926937221576407e-06, 'samples': 27547776, 'steps': 143477, 'loss/train': 1.4103201627731323} 08/31/2021 15:15:42 - INFO - __main__ - Step 143479: {'lr': 2.391961332827208e-06, 'samples': 27547968, 'steps': 143478, 'loss/train': 0.5732392072677612} 08/31/2021 15:15:43 - INFO - __main__ - Step 143480: {'lr': 2.3912290550651416e-06, 'samples': 27548160, 'steps': 143479, 'loss/train': 0.511223316192627} 08/31/2021 15:15:43 - INFO - __main__ - Step 143481: {'lr': 2.390496888871774e-06, 'samples': 27548352, 'steps': 143480, 'loss/train': 1.1334794759750366} 08/31/2021 15:15:45 - INFO - __main__ - Step 143482: {'lr': 2.38976483424741e-06, 'samples': 27548544, 'steps': 143481, 'loss/train': 0.10868528485298157} 08/31/2021 15:15:45 - INFO - __main__ - Step 143483: {'lr': 2.389032891192411e-06, 'samples': 27548736, 'steps': 143482, 'loss/train': 0.5801663994789124} 08/31/2021 15:15:46 - INFO - __main__ - Step 143484: {'lr': 2.388301059707082e-06, 'samples': 27548928, 'steps': 143483, 'loss/train': 0.8779439330101013} 08/31/2021 15:15:46 - INFO - __main__ - Step 143485: {'lr': 2.3875693397917565e-06, 'samples': 27549120, 'steps': 143484, 'loss/train': 1.5819647312164307} 08/31/2021 15:15:46 - INFO - __main__ - Step 143486: {'lr': 2.386837731446767e-06, 'samples': 27549312, 'steps': 143485, 'loss/train': 0.4077157974243164} 08/31/2021 15:15:48 - INFO - __main__ - Step 143487: {'lr': 2.386106234672475e-06, 'samples': 27549504, 'steps': 143486, 'loss/train': 0.812175452709198} 08/31/2021 15:15:48 - INFO - __main__ - Step 143488: {'lr': 2.3853748494691853e-06, 'samples': 27549696, 'steps': 143487, 'loss/train': 1.096325159072876} 08/31/2021 15:15:49 - INFO - __main__ - Step 143489: {'lr': 2.3846435758372033e-06, 'samples': 27549888, 'steps': 143488, 'loss/train': 0.8932665586471558} 08/31/2021 15:15:49 - INFO - __main__ - Step 143490: {'lr': 2.38391241377689e-06, 'samples': 27550080, 'steps': 143489, 'loss/train': 0.8563395738601685} 08/31/2021 15:15:49 - INFO - __main__ - Step 143491: {'lr': 2.38318136328855e-06, 'samples': 27550272, 'steps': 143490, 'loss/train': 1.1043778657913208} 08/31/2021 15:15:51 - INFO - __main__ - Step 143492: {'lr': 2.3824504243725452e-06, 'samples': 27550464, 'steps': 143491, 'loss/train': 1.3359254598617554} 08/31/2021 15:15:51 - INFO - __main__ - Step 143493: {'lr': 2.3817195970291805e-06, 'samples': 27550656, 'steps': 143492, 'loss/train': 0.994772732257843} 08/31/2021 15:15:52 - INFO - __main__ - Step 143494: {'lr': 2.380988881258789e-06, 'samples': 27550848, 'steps': 143493, 'loss/train': 0.32811716198921204} 08/31/2021 15:15:52 - INFO - __main__ - Step 143495: {'lr': 2.380258277061703e-06, 'samples': 27551040, 'steps': 143494, 'loss/train': 0.6407697200775146} 08/31/2021 15:15:52 - INFO - __main__ - Step 143496: {'lr': 2.3795277844382568e-06, 'samples': 27551232, 'steps': 143495, 'loss/train': 1.0071147680282593} 08/31/2021 15:15:53 - INFO - __main__ - Step 143497: {'lr': 2.3787974033887826e-06, 'samples': 27551424, 'steps': 143496, 'loss/train': 0.661283552646637} 08/31/2021 15:15:54 - INFO - __main__ - Step 143498: {'lr': 2.3780671339135863e-06, 'samples': 27551616, 'steps': 143497, 'loss/train': 1.44553542137146} 08/31/2021 15:15:55 - INFO - __main__ - Step 143499: {'lr': 2.377336976013028e-06, 'samples': 27551808, 'steps': 143498, 'loss/train': 1.2078924179077148} 08/31/2021 15:15:55 - INFO - __main__ - Step 143500: {'lr': 2.376606929687386e-06, 'samples': 27552000, 'steps': 143499, 'loss/train': 1.251776099205017} 08/31/2021 15:15:55 - INFO - __main__ - Step 143501: {'lr': 2.375876994937076e-06, 'samples': 27552192, 'steps': 143500, 'loss/train': 1.0414987802505493} 08/31/2021 15:15:56 - INFO - __main__ - Step 143502: {'lr': 2.3751471717623483e-06, 'samples': 27552384, 'steps': 143501, 'loss/train': 1.3906193971633911} 08/31/2021 15:15:57 - INFO - __main__ - Step 143503: {'lr': 2.374417460163536e-06, 'samples': 27552576, 'steps': 143502, 'loss/train': 1.4407106637954712} 08/31/2021 15:15:58 - INFO - __main__ - Step 143504: {'lr': 2.3736878601410274e-06, 'samples': 27552768, 'steps': 143503, 'loss/train': 0.5242232084274292} 08/31/2021 15:15:58 - INFO - __main__ - Step 143505: {'lr': 2.3729583716950996e-06, 'samples': 27552960, 'steps': 143504, 'loss/train': 0.8353415727615356} 08/31/2021 15:15:58 - INFO - __main__ - Step 143506: {'lr': 2.3722289948260865e-06, 'samples': 27553152, 'steps': 143505, 'loss/train': 1.0121151208877563} 08/31/2021 15:15:59 - INFO - __main__ - Step 143507: {'lr': 2.371499729534321e-06, 'samples': 27553344, 'steps': 143506, 'loss/train': 0.4924750030040741} 08/31/2021 15:16:00 - INFO - __main__ - Step 143508: {'lr': 2.3707705758201357e-06, 'samples': 27553536, 'steps': 143507, 'loss/train': 2.3459231853485107} 08/31/2021 15:16:01 - INFO - __main__ - Step 143509: {'lr': 2.3700415336838922e-06, 'samples': 27553728, 'steps': 143508, 'loss/train': 1.661998987197876} 08/31/2021 15:16:01 - INFO - __main__ - Step 143510: {'lr': 2.369312603125867e-06, 'samples': 27553920, 'steps': 143509, 'loss/train': 0.5603904128074646} 08/31/2021 15:16:02 - INFO - __main__ - Step 143511: {'lr': 2.368583784146394e-06, 'samples': 27554112, 'steps': 143510, 'loss/train': 0.5920781493186951} 08/31/2021 15:16:02 - INFO - __main__ - Step 143512: {'lr': 2.367855076745834e-06, 'samples': 27554304, 'steps': 143511, 'loss/train': 0.9168946743011475} 08/31/2021 15:16:03 - INFO - __main__ - Step 143513: {'lr': 2.367126480924492e-06, 'samples': 27554496, 'steps': 143512, 'loss/train': 1.2418988943099976} 08/31/2021 15:16:04 - INFO - __main__ - Step 143514: {'lr': 2.3663979966827287e-06, 'samples': 27554688, 'steps': 143513, 'loss/train': 0.7096533179283142} 08/31/2021 15:16:04 - INFO - __main__ - Step 143515: {'lr': 2.3656696240207942e-06, 'samples': 27554880, 'steps': 143514, 'loss/train': 1.1764001846313477} 08/31/2021 15:16:04 - INFO - __main__ - Step 143516: {'lr': 2.364941362939105e-06, 'samples': 27555072, 'steps': 143515, 'loss/train': 1.0136696100234985} 08/31/2021 15:16:05 - INFO - __main__ - Step 143517: {'lr': 2.3642132134379378e-06, 'samples': 27555264, 'steps': 143516, 'loss/train': 0.9791883826255798} 08/31/2021 15:16:06 - INFO - __main__ - Step 143518: {'lr': 2.363485175517627e-06, 'samples': 27555456, 'steps': 143517, 'loss/train': 1.1429556608200073} 08/31/2021 15:16:07 - INFO - __main__ - Step 143519: {'lr': 2.362757249178532e-06, 'samples': 27555648, 'steps': 143518, 'loss/train': 1.1845051050186157} 08/31/2021 15:16:07 - INFO - __main__ - Step 143520: {'lr': 2.3620294344209316e-06, 'samples': 27555840, 'steps': 143519, 'loss/train': 0.8495195508003235} 08/31/2021 15:16:07 - INFO - __main__ - Step 143521: {'lr': 2.3613017312451857e-06, 'samples': 27556032, 'steps': 143520, 'loss/train': 0.7189962863922119} 08/31/2021 15:16:08 - INFO - __main__ - Step 143522: {'lr': 2.3605741396516277e-06, 'samples': 27556224, 'steps': 143521, 'loss/train': 0.904242217540741} 08/31/2021 15:16:10 - INFO - __main__ - Step 143523: {'lr': 2.3598466596405634e-06, 'samples': 27556416, 'steps': 143522, 'loss/train': 1.3482062816619873} 08/31/2021 15:16:11 - INFO - __main__ - Step 143524: {'lr': 2.3591192912123526e-06, 'samples': 27556608, 'steps': 143523, 'loss/train': 1.2044472694396973} 08/31/2021 15:16:11 - INFO - __main__ - Step 143525: {'lr': 2.3583920343672738e-06, 'samples': 27556800, 'steps': 143524, 'loss/train': 0.7602493762969971} 08/31/2021 15:16:11 - INFO - __main__ - Step 143526: {'lr': 2.357664889105687e-06, 'samples': 27556992, 'steps': 143525, 'loss/train': 0.014356591738760471} 08/31/2021 15:16:12 - INFO - __main__ - Step 143527: {'lr': 2.3569378554279266e-06, 'samples': 27557184, 'steps': 143526, 'loss/train': 0.043805915862321854} 08/31/2021 15:16:12 - INFO - __main__ - Step 143528: {'lr': 2.356210933334324e-06, 'samples': 27557376, 'steps': 143527, 'loss/train': 1.0981327295303345} 08/31/2021 15:16:13 - INFO - __main__ - Step 143529: {'lr': 2.355484122825158e-06, 'samples': 27557568, 'steps': 143528, 'loss/train': 1.8140177726745605} 08/31/2021 15:16:14 - INFO - __main__ - Step 143530: {'lr': 2.3547574239007883e-06, 'samples': 27557760, 'steps': 143529, 'loss/train': 0.6177501678466797} 08/31/2021 15:16:14 - INFO - __main__ - Step 143531: {'lr': 2.354030836561577e-06, 'samples': 27557952, 'steps': 143530, 'loss/train': 0.9150406718254089} 08/31/2021 15:16:15 - INFO - __main__ - Step 143532: {'lr': 2.353304360807773e-06, 'samples': 27558144, 'steps': 143531, 'loss/train': 0.6897610425949097} 08/31/2021 15:16:15 - INFO - __main__ - Step 143533: {'lr': 2.352577996639793e-06, 'samples': 27558336, 'steps': 143532, 'loss/train': 1.1969455480575562} 08/31/2021 15:16:17 - INFO - __main__ - Step 143534: {'lr': 2.351851744057887e-06, 'samples': 27558528, 'steps': 143533, 'loss/train': 1.913367509841919} 08/31/2021 15:16:17 - INFO - __main__ - Step 143535: {'lr': 2.351125603062443e-06, 'samples': 27558720, 'steps': 143534, 'loss/train': 0.9281495213508606} 08/31/2021 15:16:18 - INFO - __main__ - Step 143536: {'lr': 2.3503995736537388e-06, 'samples': 27558912, 'steps': 143535, 'loss/train': 0.7156895995140076} 08/31/2021 15:16:18 - INFO - __main__ - Step 143537: {'lr': 2.3496736558321353e-06, 'samples': 27559104, 'steps': 143536, 'loss/train': 1.0014111995697021} 08/31/2021 15:16:18 - INFO - __main__ - Step 143538: {'lr': 2.348947849597938e-06, 'samples': 27559296, 'steps': 143537, 'loss/train': 0.03019961155951023} 08/31/2021 15:16:20 - INFO - __main__ - Step 143539: {'lr': 2.3482221549514792e-06, 'samples': 27559488, 'steps': 143538, 'loss/train': 1.6772236824035645} 08/31/2021 15:16:20 - INFO - __main__ - Step 143540: {'lr': 2.347496571893093e-06, 'samples': 27559680, 'steps': 143539, 'loss/train': 0.9590771198272705} 08/31/2021 15:16:21 - INFO - __main__ - Step 143541: {'lr': 2.346771100423112e-06, 'samples': 27559872, 'steps': 143540, 'loss/train': 0.9250132441520691} 08/31/2021 15:16:21 - INFO - __main__ - Step 143542: {'lr': 2.346045740541869e-06, 'samples': 27560064, 'steps': 143541, 'loss/train': 1.4565718173980713} 08/31/2021 15:16:21 - INFO - __main__ - Step 143543: {'lr': 2.345320492249642e-06, 'samples': 27560256, 'steps': 143542, 'loss/train': 1.7963207960128784} 08/31/2021 15:16:22 - INFO - __main__ - Step 143544: {'lr': 2.3445953555468192e-06, 'samples': 27560448, 'steps': 143543, 'loss/train': 1.0260206460952759} 08/31/2021 15:16:23 - INFO - __main__ - Step 143545: {'lr': 2.343870330433678e-06, 'samples': 27560640, 'steps': 143544, 'loss/train': 0.7694265842437744} 08/31/2021 15:16:24 - INFO - __main__ - Step 143546: {'lr': 2.3431454169105804e-06, 'samples': 27560832, 'steps': 143545, 'loss/train': 1.3185739517211914} 08/31/2021 15:16:24 - INFO - __main__ - Step 143547: {'lr': 2.3424206149778303e-06, 'samples': 27561024, 'steps': 143546, 'loss/train': 1.312752604484558} 08/31/2021 15:16:24 - INFO - __main__ - Step 143548: {'lr': 2.3416959246357893e-06, 'samples': 27561216, 'steps': 143547, 'loss/train': 0.675357460975647} 08/31/2021 15:16:25 - INFO - __main__ - Step 143549: {'lr': 2.3409713458847346e-06, 'samples': 27561408, 'steps': 143548, 'loss/train': 0.8840988874435425} 08/31/2021 15:16:26 - INFO - __main__ - Step 143550: {'lr': 2.3402468787250277e-06, 'samples': 27561600, 'steps': 143549, 'loss/train': 1.0236221551895142} 08/31/2021 15:16:27 - INFO - __main__ - Step 143551: {'lr': 2.339522523156973e-06, 'samples': 27561792, 'steps': 143550, 'loss/train': 1.3324611186981201} 08/31/2021 15:16:27 - INFO - __main__ - Step 143552: {'lr': 2.3387982791809035e-06, 'samples': 27561984, 'steps': 143551, 'loss/train': 1.09151029586792} 08/31/2021 15:16:27 - INFO - __main__ - Step 143553: {'lr': 2.3380741467971534e-06, 'samples': 27562176, 'steps': 143552, 'loss/train': 1.2936372756958008} 08/31/2021 15:16:28 - INFO - __main__ - Step 143554: {'lr': 2.337350126006055e-06, 'samples': 27562368, 'steps': 143553, 'loss/train': 0.2174513339996338} 08/31/2021 15:16:29 - INFO - __main__ - Step 143555: {'lr': 2.336626216807941e-06, 'samples': 27562560, 'steps': 143554, 'loss/train': 0.9416534304618835} 08/31/2021 15:16:30 - INFO - __main__ - Step 143556: {'lr': 2.3359024192030896e-06, 'samples': 27562752, 'steps': 143555, 'loss/train': 1.3184618949890137} 08/31/2021 15:16:30 - INFO - __main__ - Step 143557: {'lr': 2.3351787331918893e-06, 'samples': 27562944, 'steps': 143556, 'loss/train': 0.2501108646392822} 08/31/2021 15:16:30 - INFO - __main__ - Step 143558: {'lr': 2.3344551587746176e-06, 'samples': 27563136, 'steps': 143557, 'loss/train': 0.9581024050712585} 08/31/2021 15:16:31 - INFO - __main__ - Step 143559: {'lr': 2.3337316959516073e-06, 'samples': 27563328, 'steps': 143558, 'loss/train': 0.8639790415763855} 08/31/2021 15:16:32 - INFO - __main__ - Step 143560: {'lr': 2.3330083447232197e-06, 'samples': 27563520, 'steps': 143559, 'loss/train': 0.7109990119934082} 08/31/2021 15:16:33 - INFO - __main__ - Step 143561: {'lr': 2.332285105089732e-06, 'samples': 27563712, 'steps': 143560, 'loss/train': 1.1441617012023926} 08/31/2021 15:16:33 - INFO - __main__ - Step 143562: {'lr': 2.331561977051505e-06, 'samples': 27563904, 'steps': 143561, 'loss/train': 0.5071547031402588} 08/31/2021 15:16:34 - INFO - __main__ - Step 143563: {'lr': 2.330838960608872e-06, 'samples': 27564096, 'steps': 143562, 'loss/train': 0.03394634649157524} 08/31/2021 15:16:34 - INFO - __main__ - Step 143564: {'lr': 2.3301160557621105e-06, 'samples': 27564288, 'steps': 143563, 'loss/train': 0.7587885856628418} 08/31/2021 15:16:35 - INFO - __main__ - Step 143565: {'lr': 2.3293932625116088e-06, 'samples': 27564480, 'steps': 143564, 'loss/train': 1.0766569375991821} 08/31/2021 15:16:36 - INFO - __main__ - Step 143566: {'lr': 2.328670580857645e-06, 'samples': 27564672, 'steps': 143565, 'loss/train': 1.1160061359405518} 08/31/2021 15:16:36 - INFO - __main__ - Step 143567: {'lr': 2.3279480108005512e-06, 'samples': 27564864, 'steps': 143566, 'loss/train': 1.62546706199646} 08/31/2021 15:16:37 - INFO - __main__ - Step 143568: {'lr': 2.3272255523406892e-06, 'samples': 27565056, 'steps': 143567, 'loss/train': 0.32068532705307007} 08/31/2021 15:16:37 - INFO - __main__ - Step 143569: {'lr': 2.326503205478336e-06, 'samples': 27565248, 'steps': 143568, 'loss/train': 1.0087463855743408} 08/31/2021 15:16:38 - INFO - __main__ - Step 143570: {'lr': 2.3257809702138255e-06, 'samples': 27565440, 'steps': 143569, 'loss/train': 1.0240931510925293} 08/31/2021 15:16:39 - INFO - __main__ - Step 143571: {'lr': 2.3250588465475174e-06, 'samples': 27565632, 'steps': 143570, 'loss/train': 1.1810740232467651} 08/31/2021 15:16:39 - INFO - __main__ - Step 143572: {'lr': 2.324336834479718e-06, 'samples': 27565824, 'steps': 143571, 'loss/train': 1.0663394927978516} 08/31/2021 15:16:40 - INFO - __main__ - Step 143573: {'lr': 2.3236149340107317e-06, 'samples': 27566016, 'steps': 143572, 'loss/train': 0.775335967540741} 08/31/2021 15:16:40 - INFO - __main__ - Step 143574: {'lr': 2.32289314514092e-06, 'samples': 27566208, 'steps': 143573, 'loss/train': 1.0782843828201294} 08/31/2021 15:16:40 - INFO - __main__ - Step 143575: {'lr': 2.3221714678705876e-06, 'samples': 27566400, 'steps': 143574, 'loss/train': 1.0468170642852783} 08/31/2021 15:16:42 - INFO - __main__ - Step 143576: {'lr': 2.321449902200068e-06, 'samples': 27566592, 'steps': 143575, 'loss/train': 0.531882643699646} 08/31/2021 15:16:43 - INFO - __main__ - Step 143577: {'lr': 2.3207284481296663e-06, 'samples': 27566784, 'steps': 143576, 'loss/train': 1.0663408041000366} 08/31/2021 15:16:43 - INFO - __main__ - Step 143578: {'lr': 2.320007105659716e-06, 'samples': 27566976, 'steps': 143577, 'loss/train': 0.3265872001647949} 08/31/2021 15:16:43 - INFO - __main__ - Step 143579: {'lr': 2.3192858747905775e-06, 'samples': 27567168, 'steps': 143578, 'loss/train': 0.02771076373755932} 08/31/2021 15:16:44 - INFO - __main__ - Step 143580: {'lr': 2.3185647555225286e-06, 'samples': 27567360, 'steps': 143579, 'loss/train': 1.343719482421875} 08/31/2021 15:16:46 - INFO - __main__ - Step 143581: {'lr': 2.3178437478559023e-06, 'samples': 27567552, 'steps': 143580, 'loss/train': 1.352526307106018} 08/31/2021 15:16:46 - INFO - __main__ - Step 143582: {'lr': 2.317122851791087e-06, 'samples': 27567744, 'steps': 143581, 'loss/train': 0.40601691603660583} 08/31/2021 15:16:47 - INFO - __main__ - Step 143583: {'lr': 2.316402067328305e-06, 'samples': 27567936, 'steps': 143582, 'loss/train': 1.2891037464141846} 08/31/2021 15:16:47 - INFO - __main__ - Step 143584: {'lr': 2.3156813944679444e-06, 'samples': 27568128, 'steps': 143583, 'loss/train': 1.93926203250885} 08/31/2021 15:16:47 - INFO - __main__ - Step 143585: {'lr': 2.314960833210311e-06, 'samples': 27568320, 'steps': 143584, 'loss/train': 0.969443142414093} 08/31/2021 15:16:49 - INFO - __main__ - Step 143586: {'lr': 2.3142403835557102e-06, 'samples': 27568512, 'steps': 143585, 'loss/train': 0.2808222472667694} 08/31/2021 15:16:49 - INFO - __main__ - Step 143587: {'lr': 2.3135200455045302e-06, 'samples': 27568704, 'steps': 143586, 'loss/train': 0.8100923299789429} 08/31/2021 15:16:50 - INFO - __main__ - Step 143588: {'lr': 2.312799819057049e-06, 'samples': 27568896, 'steps': 143587, 'loss/train': 0.5234938263893127} 08/31/2021 15:16:50 - INFO - __main__ - Step 143589: {'lr': 2.3120797042135712e-06, 'samples': 27569088, 'steps': 143588, 'loss/train': 1.075089454650879} 08/31/2021 15:16:51 - INFO - __main__ - Step 143590: {'lr': 2.311359700974458e-06, 'samples': 27569280, 'steps': 143589, 'loss/train': 0.021040968596935272} 08/31/2021 15:16:52 - INFO - __main__ - Step 143591: {'lr': 2.310639809340043e-06, 'samples': 27569472, 'steps': 143590, 'loss/train': 0.8186303377151489} 08/31/2021 15:16:52 - INFO - __main__ - Step 143592: {'lr': 2.3099200293106305e-06, 'samples': 27569664, 'steps': 143591, 'loss/train': 1.182483434677124} 08/31/2021 15:16:53 - INFO - __main__ - Step 143593: {'lr': 2.3092003608865266e-06, 'samples': 27569856, 'steps': 143592, 'loss/train': 0.615818202495575} 08/31/2021 15:16:53 - INFO - __main__ - Step 143594: {'lr': 2.3084808040680915e-06, 'samples': 27570048, 'steps': 143593, 'loss/train': 1.1118807792663574} 08/31/2021 15:16:53 - INFO - __main__ - Step 143595: {'lr': 2.307761358855631e-06, 'samples': 27570240, 'steps': 143594, 'loss/train': 0.8707167506217957} 08/31/2021 15:16:55 - INFO - __main__ - Step 143596: {'lr': 2.3070420252494783e-06, 'samples': 27570432, 'steps': 143595, 'loss/train': 0.5936322808265686} 08/31/2021 15:16:56 - INFO - __main__ - Step 143597: {'lr': 2.3063228032499383e-06, 'samples': 27570624, 'steps': 143596, 'loss/train': 0.3413509428501129} 08/31/2021 15:16:56 - INFO - __main__ - Step 143598: {'lr': 2.305603692857344e-06, 'samples': 27570816, 'steps': 143597, 'loss/train': 1.39442777633667} 08/31/2021 15:16:56 - INFO - __main__ - Step 143599: {'lr': 2.304884694072029e-06, 'samples': 27571008, 'steps': 143598, 'loss/train': 0.9136261940002441} 08/31/2021 15:16:57 - INFO - __main__ - Step 143600: {'lr': 2.3041658068942984e-06, 'samples': 27571200, 'steps': 143599, 'loss/train': 0.48162680864334106} 08/31/2021 15:16:57 - INFO - __main__ - Step 143601: {'lr': 2.303447031324485e-06, 'samples': 27571392, 'steps': 143600, 'loss/train': 0.21897536516189575} 08/31/2021 15:16:59 - INFO - __main__ - Step 143602: {'lr': 2.3027283673629495e-06, 'samples': 27571584, 'steps': 143601, 'loss/train': 1.0941412448883057} 08/31/2021 15:16:59 - INFO - __main__ - Step 143603: {'lr': 2.3020098150099423e-06, 'samples': 27571776, 'steps': 143602, 'loss/train': 1.7493163347244263} 08/31/2021 15:17:00 - INFO - __main__ - Step 143604: {'lr': 2.3012913742658516e-06, 'samples': 27571968, 'steps': 143603, 'loss/train': 1.6178174018859863} 08/31/2021 15:17:00 - INFO - __main__ - Step 143605: {'lr': 2.3005730451309826e-06, 'samples': 27572160, 'steps': 143604, 'loss/train': 1.4831972122192383} 08/31/2021 15:17:00 - INFO - __main__ - Step 143606: {'lr': 2.2998548276056408e-06, 'samples': 27572352, 'steps': 143605, 'loss/train': 1.293825626373291} 08/31/2021 15:17:01 - INFO - __main__ - Step 143607: {'lr': 2.2991367216901593e-06, 'samples': 27572544, 'steps': 143606, 'loss/train': 1.2539242506027222} 08/31/2021 15:17:02 - INFO - __main__ - Step 143608: {'lr': 2.298418727384871e-06, 'samples': 27572736, 'steps': 143607, 'loss/train': 0.8457096219062805} 08/31/2021 15:17:03 - INFO - __main__ - Step 143609: {'lr': 2.2977008446901092e-06, 'samples': 27572928, 'steps': 143608, 'loss/train': 0.023205948993563652} 08/31/2021 15:17:03 - INFO - __main__ - Step 143610: {'lr': 2.2969830736061513e-06, 'samples': 27573120, 'steps': 143609, 'loss/train': 1.0833343267440796} 08/31/2021 15:17:03 - INFO - __main__ - Step 143611: {'lr': 2.296265414133358e-06, 'samples': 27573312, 'steps': 143610, 'loss/train': 1.6711784601211548} 08/31/2021 15:17:04 - INFO - __main__ - Step 143612: {'lr': 2.295547866272063e-06, 'samples': 27573504, 'steps': 143611, 'loss/train': 0.30764931440353394} 08/31/2021 15:17:05 - INFO - __main__ - Step 143613: {'lr': 2.294830430022543e-06, 'samples': 27573696, 'steps': 143612, 'loss/train': 1.9350451231002808} 08/31/2021 15:17:06 - INFO - __main__ - Step 143614: {'lr': 2.294113105385159e-06, 'samples': 27573888, 'steps': 143613, 'loss/train': 0.8211105465888977} 08/31/2021 15:17:06 - INFO - __main__ - Step 143615: {'lr': 2.293395892360245e-06, 'samples': 27574080, 'steps': 143614, 'loss/train': 1.104291558265686} 08/31/2021 15:17:06 - INFO - __main__ - Step 143616: {'lr': 2.2926787909480772e-06, 'samples': 27574272, 'steps': 143615, 'loss/train': 1.279613733291626} 08/31/2021 15:17:07 - INFO - __main__ - Step 143617: {'lr': 2.2919618011490173e-06, 'samples': 27574464, 'steps': 143616, 'loss/train': 0.8128180503845215} 08/31/2021 15:17:08 - INFO - __main__ - Step 143618: {'lr': 2.291244922963398e-06, 'samples': 27574656, 'steps': 143617, 'loss/train': 1.1521209478378296} 08/31/2021 15:17:09 - INFO - __main__ - Step 143619: {'lr': 2.290528156391497e-06, 'samples': 27574848, 'steps': 143618, 'loss/train': 1.1515653133392334} 08/31/2021 15:17:09 - INFO - __main__ - Step 143620: {'lr': 2.289811501433675e-06, 'samples': 27575040, 'steps': 143619, 'loss/train': 0.929634690284729} 08/31/2021 15:17:09 - INFO - __main__ - Step 143621: {'lr': 2.28909495809021e-06, 'samples': 27575232, 'steps': 143620, 'loss/train': 1.0455703735351562} 08/31/2021 15:17:10 - INFO - __main__ - Step 143622: {'lr': 2.2883785263615177e-06, 'samples': 27575424, 'steps': 143621, 'loss/train': 1.3708916902542114} 08/31/2021 15:17:11 - INFO - __main__ - Step 143623: {'lr': 2.2876622062478203e-06, 'samples': 27575616, 'steps': 143622, 'loss/train': 0.583446741104126} 08/31/2021 15:17:12 - INFO - __main__ - Step 143624: {'lr': 2.286945997749479e-06, 'samples': 27575808, 'steps': 143623, 'loss/train': 0.8119807839393616} 08/31/2021 15:17:12 - INFO - __main__ - Step 143625: {'lr': 2.2862299008667987e-06, 'samples': 27576000, 'steps': 143624, 'loss/train': 1.217305064201355} 08/31/2021 15:17:12 - INFO - __main__ - Step 143626: {'lr': 2.285513915600168e-06, 'samples': 27576192, 'steps': 143625, 'loss/train': 1.4194306135177612} 08/31/2021 15:17:13 - INFO - __main__ - Step 143627: {'lr': 2.284798041949837e-06, 'samples': 27576384, 'steps': 143626, 'loss/train': 0.6777478456497192} 08/31/2021 15:17:14 - INFO - __main__ - Step 143628: {'lr': 2.2840822799161386e-06, 'samples': 27576576, 'steps': 143627, 'loss/train': 2.2459969520568848} 08/31/2021 15:17:15 - INFO - __main__ - Step 143629: {'lr': 2.283366629499434e-06, 'samples': 27576768, 'steps': 143628, 'loss/train': 1.1596039533615112} 08/31/2021 15:17:15 - INFO - __main__ - Step 143630: {'lr': 2.2826510907e-06, 'samples': 27576960, 'steps': 143629, 'loss/train': 0.7351474165916443} 08/31/2021 15:17:15 - INFO - __main__ - Step 143631: {'lr': 2.2819356635181974e-06, 'samples': 27577152, 'steps': 143630, 'loss/train': 0.8800925016403198} 08/31/2021 15:17:16 - INFO - __main__ - Step 143632: {'lr': 2.2812203479543326e-06, 'samples': 27577344, 'steps': 143631, 'loss/train': 1.2930138111114502} 08/31/2021 15:17:18 - INFO - __main__ - Step 143633: {'lr': 2.28050514400871e-06, 'samples': 27577536, 'steps': 143632, 'loss/train': 1.502396821975708} 08/31/2021 15:17:18 - INFO - __main__ - Step 143634: {'lr': 2.2797900516816906e-06, 'samples': 27577728, 'steps': 143633, 'loss/train': 0.03397426754236221} 08/31/2021 15:17:19 - INFO - __main__ - Step 143635: {'lr': 2.2790750709735796e-06, 'samples': 27577920, 'steps': 143634, 'loss/train': 1.771663784980774} 08/31/2021 15:17:19 - INFO - __main__ - Step 143636: {'lr': 2.2783602018846827e-06, 'samples': 27578112, 'steps': 143635, 'loss/train': 1.1435105800628662} 08/31/2021 15:17:19 - INFO - __main__ - Step 143637: {'lr': 2.2776454444153326e-06, 'samples': 27578304, 'steps': 143636, 'loss/train': 1.317874550819397} 08/31/2021 15:17:21 - INFO - __main__ - Step 143638: {'lr': 2.2769307985658628e-06, 'samples': 27578496, 'steps': 143637, 'loss/train': 1.453877568244934} 08/31/2021 15:17:22 - INFO - __main__ - Step 143639: {'lr': 2.2762162643365504e-06, 'samples': 27578688, 'steps': 143638, 'loss/train': 1.3924275636672974} 08/31/2021 15:17:22 - INFO - __main__ - Step 143640: {'lr': 2.275501841727784e-06, 'samples': 27578880, 'steps': 143639, 'loss/train': 0.5665423274040222} 08/31/2021 15:17:22 - INFO - __main__ - Step 143641: {'lr': 2.2747875307398414e-06, 'samples': 27579072, 'steps': 143640, 'loss/train': 0.16304951906204224} 08/31/2021 15:17:23 - INFO - __main__ - Step 143642: {'lr': 2.274073331373083e-06, 'samples': 27579264, 'steps': 143641, 'loss/train': 1.8738327026367188} 08/31/2021 15:17:23 - INFO - __main__ - Step 143643: {'lr': 2.273359243627787e-06, 'samples': 27579456, 'steps': 143642, 'loss/train': 0.051870912313461304} 08/31/2021 15:17:24 - INFO - __main__ - Step 143644: {'lr': 2.272645267504286e-06, 'samples': 27579648, 'steps': 143643, 'loss/train': 0.8987761735916138} 08/31/2021 15:17:25 - INFO - __main__ - Step 143645: {'lr': 2.2719314030029137e-06, 'samples': 27579840, 'steps': 143644, 'loss/train': 1.0525388717651367} 08/31/2021 15:17:25 - INFO - __main__ - Step 143646: {'lr': 2.2712176501239745e-06, 'samples': 27580032, 'steps': 143645, 'loss/train': 2.7368102073669434} 08/31/2021 15:17:26 - INFO - __main__ - Step 143647: {'lr': 2.2705040088678296e-06, 'samples': 27580224, 'steps': 143646, 'loss/train': 0.7874393463134766} 08/31/2021 15:17:26 - INFO - __main__ - Step 143648: {'lr': 2.2697904792347566e-06, 'samples': 27580416, 'steps': 143647, 'loss/train': 1.3166334629058838} 08/31/2021 15:17:27 - INFO - __main__ - Step 143649: {'lr': 2.269077061225089e-06, 'samples': 27580608, 'steps': 143648, 'loss/train': 0.9692957401275635} 08/31/2021 15:17:28 - INFO - __main__ - Step 143650: {'lr': 2.268363754839159e-06, 'samples': 27580800, 'steps': 143649, 'loss/train': 1.1675341129302979} 08/31/2021 15:17:28 - INFO - __main__ - Step 143651: {'lr': 2.2676505600772724e-06, 'samples': 27580992, 'steps': 143650, 'loss/train': 0.9752352833747864} 08/31/2021 15:17:29 - INFO - __main__ - Step 143652: {'lr': 2.26693747693979e-06, 'samples': 27581184, 'steps': 143651, 'loss/train': 0.10234837234020233} 08/31/2021 15:17:29 - INFO - __main__ - Step 143653: {'lr': 2.2662245054269616e-06, 'samples': 27581376, 'steps': 143652, 'loss/train': 0.9988114237785339} 08/31/2021 15:17:31 - INFO - __main__ - Step 143654: {'lr': 2.2655116455391754e-06, 'samples': 27581568, 'steps': 143653, 'loss/train': 1.0591344833374023} 08/31/2021 15:17:31 - INFO - __main__ - Step 143655: {'lr': 2.2647988972767096e-06, 'samples': 27581760, 'steps': 143654, 'loss/train': 1.2269166707992554} 08/31/2021 15:17:31 - INFO - __main__ - Step 143656: {'lr': 2.2640862606399247e-06, 'samples': 27581952, 'steps': 143655, 'loss/train': 1.6878188848495483} 08/31/2021 15:17:32 - INFO - __main__ - Step 143657: {'lr': 2.2633737356290985e-06, 'samples': 27582144, 'steps': 143656, 'loss/train': 0.815038800239563} 08/31/2021 15:17:32 - INFO - __main__ - Step 143658: {'lr': 2.2626613222445914e-06, 'samples': 27582336, 'steps': 143657, 'loss/train': 0.6657351851463318} 08/31/2021 15:17:34 - INFO - __main__ - Step 143659: {'lr': 2.2619490204866812e-06, 'samples': 27582528, 'steps': 143658, 'loss/train': 1.0408072471618652} 08/31/2021 15:17:34 - INFO - __main__ - Step 143660: {'lr': 2.2612368303557285e-06, 'samples': 27582720, 'steps': 143659, 'loss/train': 0.7738538384437561} 08/31/2021 15:17:34 - INFO - __main__ - Step 143661: {'lr': 2.260524751852039e-06, 'samples': 27582912, 'steps': 143660, 'loss/train': 1.2365074157714844} 08/31/2021 15:17:35 - INFO - __main__ - Step 143662: {'lr': 2.259812784975945e-06, 'samples': 27583104, 'steps': 143661, 'loss/train': 0.9979814887046814} 08/31/2021 15:17:35 - INFO - __main__ - Step 143663: {'lr': 2.2591009297277533e-06, 'samples': 27583296, 'steps': 143662, 'loss/train': 1.0756776332855225} 08/31/2021 15:17:35 - INFO - __main__ - Step 143664: {'lr': 2.2583891861077953e-06, 'samples': 27583488, 'steps': 143663, 'loss/train': 0.41814759373664856} 08/31/2021 15:17:37 - INFO - __main__ - Step 143665: {'lr': 2.25767755411635e-06, 'samples': 27583680, 'steps': 143664, 'loss/train': 1.2231577634811401} 08/31/2021 15:17:37 - INFO - __main__ - Step 143666: {'lr': 2.2569660337538043e-06, 'samples': 27583872, 'steps': 143665, 'loss/train': 0.8338783383369446} 08/31/2021 15:17:38 - INFO - __main__ - Step 143667: {'lr': 2.2562546250204376e-06, 'samples': 27584064, 'steps': 143666, 'loss/train': 1.0981489419937134} 08/31/2021 15:17:38 - INFO - __main__ - Step 143668: {'lr': 2.2555433279165815e-06, 'samples': 27584256, 'steps': 143667, 'loss/train': 1.479569673538208} 08/31/2021 15:17:38 - INFO - __main__ - Step 143669: {'lr': 2.254832142442542e-06, 'samples': 27584448, 'steps': 143668, 'loss/train': 1.2009186744689941} 08/31/2021 15:17:40 - INFO - __main__ - Step 143670: {'lr': 2.2541210685986523e-06, 'samples': 27584640, 'steps': 143669, 'loss/train': 1.0188144445419312} 08/31/2021 15:17:40 - INFO - __main__ - Step 143671: {'lr': 2.2534101063852453e-06, 'samples': 27584832, 'steps': 143670, 'loss/train': 1.103427529335022} 08/31/2021 15:17:41 - INFO - __main__ - Step 143672: {'lr': 2.252699255802626e-06, 'samples': 27585024, 'steps': 143671, 'loss/train': 1.4264073371887207} 08/31/2021 15:17:41 - INFO - __main__ - Step 143673: {'lr': 2.251988516851128e-06, 'samples': 27585216, 'steps': 143672, 'loss/train': 0.7417457699775696} 08/31/2021 15:17:41 - INFO - __main__ - Step 143674: {'lr': 2.251277889531056e-06, 'samples': 27585408, 'steps': 143673, 'loss/train': 1.2181131839752197} 08/31/2021 15:17:43 - INFO - __main__ - Step 143675: {'lr': 2.2505673738427434e-06, 'samples': 27585600, 'steps': 143674, 'loss/train': 1.014173150062561} 08/31/2021 15:17:44 - INFO - __main__ - Step 143676: {'lr': 2.249856969786468e-06, 'samples': 27585792, 'steps': 143675, 'loss/train': 1.1111080646514893} 08/31/2021 15:17:44 - INFO - __main__ - Step 143677: {'lr': 2.2491466773626178e-06, 'samples': 27585984, 'steps': 143676, 'loss/train': 0.7711336612701416} 08/31/2021 15:17:45 - INFO - __main__ - Step 143678: {'lr': 2.2484364965714433e-06, 'samples': 27586176, 'steps': 143677, 'loss/train': 0.9906386733055115} 08/31/2021 15:17:45 - INFO - __main__ - Step 143679: {'lr': 2.2477264274133325e-06, 'samples': 27586368, 'steps': 143678, 'loss/train': 0.6189970970153809} 08/31/2021 15:17:45 - INFO - __main__ - Step 143680: {'lr': 2.247016469888563e-06, 'samples': 27586560, 'steps': 143679, 'loss/train': 0.014745249412953854} 08/31/2021 15:17:47 - INFO - __main__ - Step 143681: {'lr': 2.2463066239974685e-06, 'samples': 27586752, 'steps': 143680, 'loss/train': 0.01514012087136507} 08/31/2021 15:17:47 - INFO - __main__ - Step 143682: {'lr': 2.2455968897403536e-06, 'samples': 27586944, 'steps': 143681, 'loss/train': 0.4314851462841034} 08/31/2021 15:17:47 - INFO - __main__ - Step 143683: {'lr': 2.244887267117551e-06, 'samples': 27587136, 'steps': 143682, 'loss/train': 1.4308151006698608} 08/31/2021 15:17:48 - INFO - __main__ - Step 143684: {'lr': 2.244177756129395e-06, 'samples': 27587328, 'steps': 143683, 'loss/train': 1.3598387241363525} 08/31/2021 15:17:48 - INFO - __main__ - Step 143685: {'lr': 2.2434683567761627e-06, 'samples': 27587520, 'steps': 143684, 'loss/train': 1.3641297817230225} 08/31/2021 15:17:50 - INFO - __main__ - Step 143686: {'lr': 2.2427590690582424e-06, 'samples': 27587712, 'steps': 143685, 'loss/train': 0.4036838710308075} 08/31/2021 15:17:51 - INFO - __main__ - Step 143687: {'lr': 2.2420498929758836e-06, 'samples': 27587904, 'steps': 143686, 'loss/train': 1.0340774059295654} 08/31/2021 15:17:51 - INFO - __main__ - Step 143688: {'lr': 2.241340828529448e-06, 'samples': 27588096, 'steps': 143687, 'loss/train': 1.0004924535751343} 08/31/2021 15:17:51 - INFO - __main__ - Step 143689: {'lr': 2.240631875719212e-06, 'samples': 27588288, 'steps': 143688, 'loss/train': 0.5323731899261475} 08/31/2021 15:17:52 - INFO - __main__ - Step 143690: {'lr': 2.2399230345455378e-06, 'samples': 27588480, 'steps': 143689, 'loss/train': 0.49624401330947876} 08/31/2021 15:17:53 - INFO - __main__ - Step 143691: {'lr': 2.2392143050087577e-06, 'samples': 27588672, 'steps': 143690, 'loss/train': 1.141209363937378} 08/31/2021 15:17:54 - INFO - __main__ - Step 143692: {'lr': 2.2385056871091214e-06, 'samples': 27588864, 'steps': 143691, 'loss/train': 1.2878202199935913} 08/31/2021 15:17:54 - INFO - __main__ - Step 143693: {'lr': 2.2377971808470176e-06, 'samples': 27589056, 'steps': 143692, 'loss/train': 0.8639808297157288} 08/31/2021 15:17:54 - INFO - __main__ - Step 143694: {'lr': 2.237088786222724e-06, 'samples': 27589248, 'steps': 143693, 'loss/train': 0.8620937466621399} 08/31/2021 15:17:55 - INFO - __main__ - Step 143695: {'lr': 2.2363805032366013e-06, 'samples': 27589440, 'steps': 143694, 'loss/train': 1.3415464162826538} 08/31/2021 15:17:57 - INFO - __main__ - Step 143696: {'lr': 2.2356723318889273e-06, 'samples': 27589632, 'steps': 143695, 'loss/train': 1.016257882118225} 08/31/2021 15:17:57 - INFO - __main__ - Step 143697: {'lr': 2.2349642721800345e-06, 'samples': 27589824, 'steps': 143696, 'loss/train': 0.6385107636451721} 08/31/2021 15:17:58 - INFO - __main__ - Step 143698: {'lr': 2.2342563241102565e-06, 'samples': 27590016, 'steps': 143697, 'loss/train': 1.2765456438064575} 08/31/2021 15:17:58 - INFO - __main__ - Step 143699: {'lr': 2.2335484876798707e-06, 'samples': 27590208, 'steps': 143698, 'loss/train': 0.9940120577812195} 08/31/2021 15:17:58 - INFO - __main__ - Step 143700: {'lr': 2.232840762889238e-06, 'samples': 27590400, 'steps': 143699, 'loss/train': 0.06941685825586319} 08/31/2021 15:18:00 - INFO - __main__ - Step 143701: {'lr': 2.232133149738663e-06, 'samples': 27590592, 'steps': 143700, 'loss/train': 0.9223728179931641} 08/31/2021 15:18:00 - INFO - __main__ - Step 143702: {'lr': 2.23142564822848e-06, 'samples': 27590784, 'steps': 143701, 'loss/train': 0.8628811240196228} 08/31/2021 15:18:01 - INFO - __main__ - Step 143703: {'lr': 2.2307182583589934e-06, 'samples': 27590976, 'steps': 143702, 'loss/train': 1.612202525138855} 08/31/2021 15:18:01 - INFO - __main__ - Step 143704: {'lr': 2.230010980130509e-06, 'samples': 27591168, 'steps': 143703, 'loss/train': 0.3405311405658722} 08/31/2021 15:18:01 - INFO - __main__ - Step 143705: {'lr': 2.2293038135433595e-06, 'samples': 27591360, 'steps': 143704, 'loss/train': 1.0156129598617554} 08/31/2021 15:18:03 - INFO - __main__ - Step 143706: {'lr': 2.2285967585978507e-06, 'samples': 27591552, 'steps': 143705, 'loss/train': 0.8246502876281738} 08/31/2021 15:18:03 - INFO - __main__ - Step 143707: {'lr': 2.227889815294315e-06, 'samples': 27591744, 'steps': 143706, 'loss/train': 0.7269721031188965} 08/31/2021 15:18:04 - INFO - __main__ - Step 143708: {'lr': 2.2271829836331138e-06, 'samples': 27591936, 'steps': 143707, 'loss/train': 0.9325409531593323} 08/31/2021 15:18:04 - INFO - __main__ - Step 143709: {'lr': 2.2264762636144688e-06, 'samples': 27592128, 'steps': 143708, 'loss/train': 0.5461329817771912} 08/31/2021 15:18:04 - INFO - __main__ - Step 143710: {'lr': 2.2257696552387685e-06, 'samples': 27592320, 'steps': 143709, 'loss/train': 0.09911348670721054} 08/31/2021 15:18:06 - INFO - __main__ - Step 143711: {'lr': 2.2250631585063187e-06, 'samples': 27592512, 'steps': 143710, 'loss/train': 1.408462643623352} 08/31/2021 15:18:07 - INFO - __main__ - Step 143712: {'lr': 2.2243567734174242e-06, 'samples': 27592704, 'steps': 143711, 'loss/train': 0.11925352364778519} 08/31/2021 15:18:07 - INFO - __main__ - Step 143713: {'lr': 2.2236504999723905e-06, 'samples': 27592896, 'steps': 143712, 'loss/train': 1.298850655555725} 08/31/2021 15:18:08 - INFO - __main__ - Step 143714: {'lr': 2.2229443381715784e-06, 'samples': 27593088, 'steps': 143713, 'loss/train': 0.7295475602149963} 08/31/2021 15:18:08 - INFO - __main__ - Step 143715: {'lr': 2.2222382880152937e-06, 'samples': 27593280, 'steps': 143714, 'loss/train': 1.4190034866333008} 08/31/2021 15:18:08 - INFO - __main__ - Step 143716: {'lr': 2.2215323495038408e-06, 'samples': 27593472, 'steps': 143715, 'loss/train': 0.8389607667922974} 08/31/2021 15:18:10 - INFO - __main__ - Step 143717: {'lr': 2.2208265226375255e-06, 'samples': 27593664, 'steps': 143716, 'loss/train': 0.36128199100494385} 08/31/2021 15:18:10 - INFO - __main__ - Step 143718: {'lr': 2.2201208074167088e-06, 'samples': 27593856, 'steps': 143717, 'loss/train': 0.9217654466629028} 08/31/2021 15:18:11 - INFO - __main__ - Step 143719: {'lr': 2.2194152038416683e-06, 'samples': 27594048, 'steps': 143718, 'loss/train': 1.071846604347229} 08/31/2021 15:18:11 - INFO - __main__ - Step 143720: {'lr': 2.2187097119127362e-06, 'samples': 27594240, 'steps': 143719, 'loss/train': 0.4298073947429657} 08/31/2021 15:18:11 - INFO - __main__ - Step 143721: {'lr': 2.218004331630219e-06, 'samples': 27594432, 'steps': 143720, 'loss/train': 0.7453994154930115} 08/31/2021 15:18:13 - INFO - __main__ - Step 143722: {'lr': 2.217299062994449e-06, 'samples': 27594624, 'steps': 143721, 'loss/train': 0.9763699769973755} 08/31/2021 15:18:14 - INFO - __main__ - Step 143723: {'lr': 2.216593906005759e-06, 'samples': 27594816, 'steps': 143722, 'loss/train': 3.1367013454437256} 08/31/2021 15:18:14 - INFO - __main__ - Step 143724: {'lr': 2.215888860664428e-06, 'samples': 27595008, 'steps': 143723, 'loss/train': 1.3151556253433228} 08/31/2021 15:18:14 - INFO - __main__ - Step 143725: {'lr': 2.2151839269707873e-06, 'samples': 27595200, 'steps': 143724, 'loss/train': 1.549383282661438} 08/31/2021 15:18:15 - INFO - __main__ - Step 143726: {'lr': 2.214479104925171e-06, 'samples': 27595392, 'steps': 143725, 'loss/train': 1.6353894472122192} 08/31/2021 15:18:16 - INFO - __main__ - Step 143727: {'lr': 2.213774394527912e-06, 'samples': 27595584, 'steps': 143726, 'loss/train': 0.5813952684402466} 08/31/2021 15:18:17 - INFO - __main__ - Step 143728: {'lr': 2.21306979577926e-06, 'samples': 27595776, 'steps': 143727, 'loss/train': 0.6633939743041992} 08/31/2021 15:18:17 - INFO - __main__ - Step 143729: {'lr': 2.2123653086796035e-06, 'samples': 27595968, 'steps': 143728, 'loss/train': 1.0605411529541016} 08/31/2021 15:18:17 - INFO - __main__ - Step 143730: {'lr': 2.211660933229248e-06, 'samples': 27596160, 'steps': 143729, 'loss/train': 1.0664585828781128} 08/31/2021 15:18:18 - INFO - __main__ - Step 143731: {'lr': 2.210956669428471e-06, 'samples': 27596352, 'steps': 143730, 'loss/train': 0.7739843130111694} 08/31/2021 15:18:19 - INFO - __main__ - Step 143732: {'lr': 2.2102525172776056e-06, 'samples': 27596544, 'steps': 143731, 'loss/train': 1.0621156692504883} 08/31/2021 15:18:20 - INFO - __main__ - Step 143733: {'lr': 2.209548476776985e-06, 'samples': 27596736, 'steps': 143732, 'loss/train': 1.2382820844650269} 08/31/2021 15:18:20 - INFO - __main__ - Step 143734: {'lr': 2.2088445479269135e-06, 'samples': 27596928, 'steps': 143733, 'loss/train': 0.6573618650436401} 08/31/2021 15:18:20 - INFO - __main__ - Step 143735: {'lr': 2.2081407307277256e-06, 'samples': 27597120, 'steps': 143734, 'loss/train': 0.3685634732246399} 08/31/2021 15:18:21 - INFO - __main__ - Step 143736: {'lr': 2.2074370251796982e-06, 'samples': 27597312, 'steps': 143735, 'loss/train': 1.0903568267822266} 08/31/2021 15:18:22 - INFO - __main__ - Step 143737: {'lr': 2.206733431283192e-06, 'samples': 27597504, 'steps': 143736, 'loss/train': 1.1333707571029663} 08/31/2021 15:18:23 - INFO - __main__ - Step 143738: {'lr': 2.2060299490385127e-06, 'samples': 27597696, 'steps': 143737, 'loss/train': 0.36321553587913513} 08/31/2021 15:18:23 - INFO - __main__ - Step 143739: {'lr': 2.205326578445993e-06, 'samples': 27597888, 'steps': 143738, 'loss/train': 0.4751085638999939} 08/31/2021 15:18:23 - INFO - __main__ - Step 143740: {'lr': 2.204623319505883e-06, 'samples': 27598080, 'steps': 143739, 'loss/train': 0.9480031132698059} 08/31/2021 15:18:24 - INFO - __main__ - Step 143741: {'lr': 2.203920172218571e-06, 'samples': 27598272, 'steps': 143740, 'loss/train': 0.1007072925567627} 08/31/2021 15:18:26 - INFO - __main__ - Step 143742: {'lr': 2.2032171365843624e-06, 'samples': 27598464, 'steps': 143741, 'loss/train': 0.5106711387634277} 08/31/2021 15:18:26 - INFO - __main__ - Step 143743: {'lr': 2.2025142126035626e-06, 'samples': 27598656, 'steps': 143742, 'loss/train': 1.6379450559616089} 08/31/2021 15:18:27 - INFO - __main__ - Step 143744: {'lr': 2.2018114002764488e-06, 'samples': 27598848, 'steps': 143743, 'loss/train': 0.7040703892707825} 08/31/2021 15:18:27 - INFO - __main__ - Step 143745: {'lr': 2.20110869960341e-06, 'samples': 27599040, 'steps': 143744, 'loss/train': 0.9851428866386414} 08/31/2021 15:18:27 - INFO - __main__ - Step 143746: {'lr': 2.200406110584724e-06, 'samples': 27599232, 'steps': 143745, 'loss/train': 0.7803480625152588} 08/31/2021 15:18:28 - INFO - __main__ - Step 143747: {'lr': 2.1997036332206955e-06, 'samples': 27599424, 'steps': 143746, 'loss/train': 1.4278638362884521} 08/31/2021 15:18:29 - INFO - __main__ - Step 143748: {'lr': 2.199001267511658e-06, 'samples': 27599616, 'steps': 143747, 'loss/train': 0.40841418504714966} 08/31/2021 15:18:30 - INFO - __main__ - Step 143749: {'lr': 2.198299013457916e-06, 'samples': 27599808, 'steps': 143748, 'loss/train': 1.4824042320251465} 08/31/2021 15:18:30 - INFO - __main__ - Step 143750: {'lr': 2.1975968710598316e-06, 'samples': 27600000, 'steps': 143749, 'loss/train': 0.7738492488861084} 08/31/2021 15:18:30 - INFO - __main__ - Step 143751: {'lr': 2.1968948403176535e-06, 'samples': 27600192, 'steps': 143750, 'loss/train': 0.7580345273017883} 08/31/2021 15:18:31 - INFO - __main__ - Step 143752: {'lr': 2.1961929212317434e-06, 'samples': 27600384, 'steps': 143751, 'loss/train': 0.5561173558235168} 08/31/2021 15:18:32 - INFO - __main__ - Step 143753: {'lr': 2.195491113802406e-06, 'samples': 27600576, 'steps': 143752, 'loss/train': 1.717355489730835} 08/31/2021 15:18:33 - INFO - __main__ - Step 143754: {'lr': 2.1947894180299465e-06, 'samples': 27600768, 'steps': 143753, 'loss/train': 0.8647581338882446} 08/31/2021 15:18:33 - INFO - __main__ - Step 143755: {'lr': 2.1940878339146987e-06, 'samples': 27600960, 'steps': 143754, 'loss/train': 1.5264984369277954} 08/31/2021 15:18:33 - INFO - __main__ - Step 143756: {'lr': 2.193386361456995e-06, 'samples': 27601152, 'steps': 143755, 'loss/train': 1.1761133670806885} 08/31/2021 15:18:34 - INFO - __main__ - Step 143757: {'lr': 2.192685000657113e-06, 'samples': 27601344, 'steps': 143756, 'loss/train': 0.7983999848365784} 08/31/2021 15:18:35 - INFO - __main__ - Step 143758: {'lr': 2.1919837515153585e-06, 'samples': 27601536, 'steps': 143757, 'loss/train': 1.3354531526565552} 08/31/2021 15:18:36 - INFO - __main__ - Step 143759: {'lr': 2.191282614032092e-06, 'samples': 27601728, 'steps': 143758, 'loss/train': 0.9816437363624573} 08/31/2021 15:18:36 - INFO - __main__ - Step 143760: {'lr': 2.1905815882076187e-06, 'samples': 27601920, 'steps': 143759, 'loss/train': 0.7292410731315613} 08/31/2021 15:18:37 - INFO - __main__ - Step 143761: {'lr': 2.189880674042216e-06, 'samples': 27602112, 'steps': 143760, 'loss/train': 0.7872557640075684} 08/31/2021 15:18:37 - INFO - __main__ - Step 143762: {'lr': 2.1891798715362456e-06, 'samples': 27602304, 'steps': 143761, 'loss/train': 1.3212755918502808} 08/31/2021 15:18:38 - INFO - __main__ - Step 143763: {'lr': 2.188479180690012e-06, 'samples': 27602496, 'steps': 143762, 'loss/train': 0.9573819637298584} 08/31/2021 15:18:39 - INFO - __main__ - Step 143764: {'lr': 2.1877786015038205e-06, 'samples': 27602688, 'steps': 143763, 'loss/train': 1.141626000404358} 08/31/2021 15:18:39 - INFO - __main__ - Step 143765: {'lr': 2.1870781339780045e-06, 'samples': 27602880, 'steps': 143764, 'loss/train': 1.3027126789093018} 08/31/2021 15:18:40 - INFO - __main__ - Step 143766: {'lr': 2.1863777781128413e-06, 'samples': 27603072, 'steps': 143765, 'loss/train': 1.3929871320724487} 08/31/2021 15:18:40 - INFO - __main__ - Step 143767: {'lr': 2.185677533908692e-06, 'samples': 27603264, 'steps': 143766, 'loss/train': 0.9777714014053345} 08/31/2021 15:18:41 - INFO - __main__ - Step 143768: {'lr': 2.1849774013658343e-06, 'samples': 27603456, 'steps': 143767, 'loss/train': 1.4222134351730347} 08/31/2021 15:18:42 - INFO - __main__ - Step 143769: {'lr': 2.1842773804846283e-06, 'samples': 27603648, 'steps': 143768, 'loss/train': 1.2438113689422607} 08/31/2021 15:18:42 - INFO - __main__ - Step 143770: {'lr': 2.1835774712653524e-06, 'samples': 27603840, 'steps': 143769, 'loss/train': 1.3883686065673828} 08/31/2021 15:18:43 - INFO - __main__ - Step 143771: {'lr': 2.182877673708339e-06, 'samples': 27604032, 'steps': 143770, 'loss/train': 1.144851565361023} 08/31/2021 15:18:43 - INFO - __main__ - Step 143772: {'lr': 2.1821779878138936e-06, 'samples': 27604224, 'steps': 143771, 'loss/train': 1.1347112655639648} 08/31/2021 15:18:44 - INFO - __main__ - Step 143773: {'lr': 2.1814784135823217e-06, 'samples': 27604416, 'steps': 143772, 'loss/train': 1.0158460140228271} 08/31/2021 15:18:45 - INFO - __main__ - Step 143774: {'lr': 2.1807789510139565e-06, 'samples': 27604608, 'steps': 143773, 'loss/train': 0.8564300537109375} 08/31/2021 15:18:45 - INFO - __main__ - Step 143775: {'lr': 2.1800796001091027e-06, 'samples': 27604800, 'steps': 143774, 'loss/train': 0.7578564882278442} 08/31/2021 15:18:46 - INFO - __main__ - Step 143776: {'lr': 2.179380360868094e-06, 'samples': 27604992, 'steps': 143775, 'loss/train': 0.20439745485782623} 08/31/2021 15:18:46 - INFO - __main__ - Step 143777: {'lr': 2.178681233291208e-06, 'samples': 27605184, 'steps': 143776, 'loss/train': 1.411144733428955} 08/31/2021 15:18:47 - INFO - __main__ - Step 143778: {'lr': 2.1779822173788045e-06, 'samples': 27605376, 'steps': 143777, 'loss/train': 0.9283158183097839} 08/31/2021 15:18:48 - INFO - __main__ - Step 143779: {'lr': 2.17728331313119e-06, 'samples': 27605568, 'steps': 143778, 'loss/train': 1.159566044807434} 08/31/2021 15:18:48 - INFO - __main__ - Step 143780: {'lr': 2.1765845205486412e-06, 'samples': 27605760, 'steps': 143779, 'loss/train': 1.0724674463272095} 08/31/2021 15:18:48 - INFO - __main__ - Step 143781: {'lr': 2.1758858396315196e-06, 'samples': 27605952, 'steps': 143780, 'loss/train': 0.6575489640235901} 08/31/2021 15:18:49 - INFO - __main__ - Step 143782: {'lr': 2.1751872703801024e-06, 'samples': 27606144, 'steps': 143781, 'loss/train': 1.5355652570724487} 08/31/2021 15:18:51 - INFO - __main__ - Step 143783: {'lr': 2.1744888127947504e-06, 'samples': 27606336, 'steps': 143782, 'loss/train': 1.482098937034607} 08/31/2021 15:18:52 - INFO - __main__ - Step 143784: {'lr': 2.1737904668757137e-06, 'samples': 27606528, 'steps': 143783, 'loss/train': 1.0246729850769043} 08/31/2021 15:18:52 - INFO - __main__ - Step 143785: {'lr': 2.1730922326233804e-06, 'samples': 27606720, 'steps': 143784, 'loss/train': 0.6391031742095947} 08/31/2021 15:18:52 - INFO - __main__ - Step 143786: {'lr': 2.1723941100380006e-06, 'samples': 27606912, 'steps': 143785, 'loss/train': 0.23570701479911804} 08/31/2021 15:18:53 - INFO - __main__ - Step 143787: {'lr': 2.1716960991199075e-06, 'samples': 27607104, 'steps': 143786, 'loss/train': 0.2230018824338913} 08/31/2021 15:18:53 - INFO - __main__ - Step 143788: {'lr': 2.170998199869434e-06, 'samples': 27607296, 'steps': 143787, 'loss/train': 0.23083265125751495} 08/31/2021 15:18:55 - INFO - __main__ - Step 143789: {'lr': 2.1703004122868854e-06, 'samples': 27607488, 'steps': 143788, 'loss/train': 0.8109488487243652} 08/31/2021 15:18:55 - INFO - __main__ - Step 143790: {'lr': 2.1696027363725947e-06, 'samples': 27607680, 'steps': 143789, 'loss/train': 1.1305915117263794} 08/31/2021 15:18:55 - INFO - __main__ - Step 143791: {'lr': 2.168905172126839e-06, 'samples': 27607872, 'steps': 143790, 'loss/train': 0.9264000654220581} 08/31/2021 15:18:56 - INFO - __main__ - Step 143792: {'lr': 2.1682077195499527e-06, 'samples': 27608064, 'steps': 143791, 'loss/train': 0.8523517847061157} 08/31/2021 15:18:56 - INFO - __main__ - Step 143793: {'lr': 2.16751037864224e-06, 'samples': 27608256, 'steps': 143792, 'loss/train': 1.3377573490142822} 08/31/2021 15:18:58 - INFO - __main__ - Step 143794: {'lr': 2.1668131494040346e-06, 'samples': 27608448, 'steps': 143793, 'loss/train': 0.9447681903839111} 08/31/2021 15:18:59 - INFO - __main__ - Step 143795: {'lr': 2.1661160318356134e-06, 'samples': 27608640, 'steps': 143794, 'loss/train': 1.0514155626296997} 08/31/2021 15:18:59 - INFO - __main__ - Step 143796: {'lr': 2.1654190259373376e-06, 'samples': 27608832, 'steps': 143795, 'loss/train': 1.1242194175720215} 08/31/2021 15:18:59 - INFO - __main__ - Step 143797: {'lr': 2.164722131709512e-06, 'samples': 27609024, 'steps': 143796, 'loss/train': 1.361048936843872} 08/31/2021 15:19:00 - INFO - __main__ - Step 143798: {'lr': 2.164025349152443e-06, 'samples': 27609216, 'steps': 143797, 'loss/train': 0.8998450636863708} 08/31/2021 15:19:00 - INFO - __main__ - Step 143799: {'lr': 2.1633286782664073e-06, 'samples': 27609408, 'steps': 143798, 'loss/train': 0.7507154941558838} 08/31/2021 15:19:02 - INFO - __main__ - Step 143800: {'lr': 2.162632119051766e-06, 'samples': 27609600, 'steps': 143799, 'loss/train': 0.9241922497749329} 08/31/2021 15:19:02 - INFO - __main__ - Step 143801: {'lr': 2.1619356715088245e-06, 'samples': 27609792, 'steps': 143800, 'loss/train': 1.167985200881958} 08/31/2021 15:19:03 - INFO - __main__ - Step 143802: {'lr': 2.161239335637888e-06, 'samples': 27609984, 'steps': 143801, 'loss/train': 0.0286500696092844} 08/31/2021 15:19:03 - INFO - __main__ - Step 143803: {'lr': 2.1605431114392617e-06, 'samples': 27610176, 'steps': 143802, 'loss/train': 0.9558659791946411} 08/31/2021 15:19:03 - INFO - __main__ - Step 143804: {'lr': 2.1598469989132786e-06, 'samples': 27610368, 'steps': 143803, 'loss/train': 1.0759687423706055} 08/31/2021 15:19:05 - INFO - __main__ - Step 143805: {'lr': 2.1591509980602443e-06, 'samples': 27610560, 'steps': 143804, 'loss/train': 1.5207841396331787} 08/31/2021 15:19:05 - INFO - __main__ - Step 143806: {'lr': 2.158455108880464e-06, 'samples': 27610752, 'steps': 143805, 'loss/train': 0.472636878490448} 08/31/2021 15:19:06 - INFO - __main__ - Step 143807: {'lr': 2.1577593313742707e-06, 'samples': 27610944, 'steps': 143806, 'loss/train': 1.2422807216644287} 08/31/2021 15:19:06 - INFO - __main__ - Step 143808: {'lr': 2.1570636655419417e-06, 'samples': 27611136, 'steps': 143807, 'loss/train': 1.076182246208191} 08/31/2021 15:19:06 - INFO - __main__ - Step 143809: {'lr': 2.1563681113838383e-06, 'samples': 27611328, 'steps': 143808, 'loss/train': 1.23992121219635} 08/31/2021 15:19:08 - INFO - __main__ - Step 143810: {'lr': 2.155672668900266e-06, 'samples': 27611520, 'steps': 143809, 'loss/train': 0.964398980140686} 08/31/2021 15:19:08 - INFO - __main__ - Step 143811: {'lr': 2.1549773380915014e-06, 'samples': 27611712, 'steps': 143810, 'loss/train': 0.988508939743042} 08/31/2021 15:19:09 - INFO - __main__ - Step 143812: {'lr': 2.1542821189578786e-06, 'samples': 27611904, 'steps': 143811, 'loss/train': 1.130693793296814} 08/31/2021 15:19:09 - INFO - __main__ - Step 143813: {'lr': 2.1535870114997304e-06, 'samples': 27612096, 'steps': 143812, 'loss/train': 1.4221007823944092} 08/31/2021 15:19:09 - INFO - __main__ - Step 143814: {'lr': 2.1528920157173337e-06, 'samples': 27612288, 'steps': 143813, 'loss/train': 0.8389054536819458} 08/31/2021 15:19:11 - INFO - __main__ - Step 143815: {'lr': 2.1521971316110222e-06, 'samples': 27612480, 'steps': 143814, 'loss/train': 1.332910180091858} 08/31/2021 15:19:11 - INFO - __main__ - Step 143816: {'lr': 2.151502359181101e-06, 'samples': 27612672, 'steps': 143815, 'loss/train': 0.802862286567688} 08/31/2021 15:19:12 - INFO - __main__ - Step 143817: {'lr': 2.1508076984279037e-06, 'samples': 27612864, 'steps': 143816, 'loss/train': 1.0162793397903442} 08/31/2021 15:19:12 - INFO - __main__ - Step 143818: {'lr': 2.150113149351707e-06, 'samples': 27613056, 'steps': 143817, 'loss/train': 0.7998854517936707} 08/31/2021 15:19:12 - INFO - __main__ - Step 143819: {'lr': 2.1494187119528442e-06, 'samples': 27613248, 'steps': 143818, 'loss/train': 1.1353225708007812} 08/31/2021 15:19:14 - INFO - __main__ - Step 143820: {'lr': 2.1487243862316487e-06, 'samples': 27613440, 'steps': 143819, 'loss/train': 0.9723400473594666} 08/31/2021 15:19:15 - INFO - __main__ - Step 143821: {'lr': 2.1480301721883977e-06, 'samples': 27613632, 'steps': 143820, 'loss/train': 0.265840619802475} 08/31/2021 15:19:15 - INFO - __main__ - Step 143822: {'lr': 2.1473360698234245e-06, 'samples': 27613824, 'steps': 143821, 'loss/train': 0.8936226963996887} 08/31/2021 15:19:15 - INFO - __main__ - Step 143823: {'lr': 2.1466420791370624e-06, 'samples': 27614016, 'steps': 143822, 'loss/train': 0.7411752343177795} 08/31/2021 15:19:16 - INFO - __main__ - Step 143824: {'lr': 2.1459482001295884e-06, 'samples': 27614208, 'steps': 143823, 'loss/train': 1.5206705331802368} 08/31/2021 15:19:16 - INFO - __main__ - Step 143825: {'lr': 2.145254432801308e-06, 'samples': 27614400, 'steps': 143824, 'loss/train': 0.9448789358139038} 08/31/2021 15:19:17 - INFO - __main__ - Step 143826: {'lr': 2.1445607771525545e-06, 'samples': 27614592, 'steps': 143825, 'loss/train': 0.3368890881538391} 08/31/2021 15:19:18 - INFO - __main__ - Step 143827: {'lr': 2.143867233183633e-06, 'samples': 27614784, 'steps': 143826, 'loss/train': 1.6371581554412842} 08/31/2021 15:19:18 - INFO - __main__ - Step 143828: {'lr': 2.1431738008948767e-06, 'samples': 27614976, 'steps': 143827, 'loss/train': 1.2708486318588257} 08/31/2021 15:19:19 - INFO - __main__ - Step 143829: {'lr': 2.142480480286563e-06, 'samples': 27615168, 'steps': 143828, 'loss/train': 3.196638822555542} 08/31/2021 15:19:19 - INFO - __main__ - Step 143830: {'lr': 2.1417872713590247e-06, 'samples': 27615360, 'steps': 143829, 'loss/train': 0.5192945599555969} 08/31/2021 15:19:21 - INFO - __main__ - Step 143831: {'lr': 2.1410941741125956e-06, 'samples': 27615552, 'steps': 143830, 'loss/train': 1.0082581043243408} 08/31/2021 15:19:21 - INFO - __main__ - Step 143832: {'lr': 2.140401188547525e-06, 'samples': 27615744, 'steps': 143831, 'loss/train': 0.854350745677948} 08/31/2021 15:19:21 - INFO - __main__ - Step 143833: {'lr': 2.1397083146642016e-06, 'samples': 27615936, 'steps': 143832, 'loss/train': 1.025167465209961} 08/31/2021 15:19:22 - INFO - __main__ - Step 143834: {'lr': 2.139015552462875e-06, 'samples': 27616128, 'steps': 143833, 'loss/train': 1.8212318420410156} 08/31/2021 15:19:22 - INFO - __main__ - Step 143835: {'lr': 2.1383229019439067e-06, 'samples': 27616320, 'steps': 143834, 'loss/train': 0.9733675718307495} 08/31/2021 15:19:24 - INFO - __main__ - Step 143836: {'lr': 2.1376303631075734e-06, 'samples': 27616512, 'steps': 143835, 'loss/train': 0.9179556369781494} 08/31/2021 15:19:24 - INFO - __main__ - Step 143837: {'lr': 2.1369379359542083e-06, 'samples': 27616704, 'steps': 143836, 'loss/train': 1.1448684930801392} 08/31/2021 15:19:24 - INFO - __main__ - Step 143838: {'lr': 2.1362456204841173e-06, 'samples': 27616896, 'steps': 143837, 'loss/train': 1.6889652013778687} 08/31/2021 15:19:25 - INFO - __main__ - Step 143839: {'lr': 2.1355534166976053e-06, 'samples': 27617088, 'steps': 143838, 'loss/train': 1.3052403926849365} 08/31/2021 15:19:25 - INFO - __main__ - Step 143840: {'lr': 2.1348613245949775e-06, 'samples': 27617280, 'steps': 143839, 'loss/train': 1.89983332157135} 08/31/2021 15:19:25 - INFO - __main__ - Step 143841: {'lr': 2.13416934417654e-06, 'samples': 27617472, 'steps': 143840, 'loss/train': 0.6841766834259033} 08/31/2021 15:19:27 - INFO - __main__ - Step 143842: {'lr': 2.1334774754426523e-06, 'samples': 27617664, 'steps': 143841, 'loss/train': 1.3580446243286133} 08/31/2021 15:19:27 - INFO - __main__ - Step 143843: {'lr': 2.1327857183935927e-06, 'samples': 27617856, 'steps': 143842, 'loss/train': 1.317654013633728} 08/31/2021 15:19:28 - INFO - __main__ - Step 143844: {'lr': 2.132094073029639e-06, 'samples': 27618048, 'steps': 143843, 'loss/train': 0.0311414897441864} 08/31/2021 15:19:28 - INFO - __main__ - Step 143845: {'lr': 2.1314025393511795e-06, 'samples': 27618240, 'steps': 143844, 'loss/train': 0.3934270143508911} 08/31/2021 15:19:28 - INFO - __main__ - Step 143846: {'lr': 2.1307111173584637e-06, 'samples': 27618432, 'steps': 143845, 'loss/train': 1.0594223737716675} 08/31/2021 15:19:30 - INFO - __main__ - Step 143847: {'lr': 2.130019807051825e-06, 'samples': 27618624, 'steps': 143846, 'loss/train': 1.7697006464004517} 08/31/2021 15:19:31 - INFO - __main__ - Step 143848: {'lr': 2.1293286084315964e-06, 'samples': 27618816, 'steps': 143847, 'loss/train': 0.029453497380018234} 08/31/2021 15:19:31 - INFO - __main__ - Step 143849: {'lr': 2.1286375214980557e-06, 'samples': 27619008, 'steps': 143848, 'loss/train': 1.3073784112930298} 08/31/2021 15:19:31 - INFO - __main__ - Step 143850: {'lr': 2.127946546251508e-06, 'samples': 27619200, 'steps': 143849, 'loss/train': 1.1448867321014404} 08/31/2021 15:19:32 - INFO - __main__ - Step 143851: {'lr': 2.127255682692314e-06, 'samples': 27619392, 'steps': 143850, 'loss/train': 0.7305027842521667} 08/31/2021 15:19:34 - INFO - __main__ - Step 143852: {'lr': 2.1265649308207514e-06, 'samples': 27619584, 'steps': 143851, 'loss/train': 0.09837547689676285} 08/31/2021 15:19:34 - INFO - __main__ - Step 143853: {'lr': 2.1258742906370975e-06, 'samples': 27619776, 'steps': 143852, 'loss/train': 1.4467403888702393} 08/31/2021 15:19:35 - INFO - __main__ - Step 143854: {'lr': 2.1251837621417414e-06, 'samples': 27619968, 'steps': 143853, 'loss/train': 0.9623659253120422} 08/31/2021 15:19:35 - INFO - __main__ - Step 143855: {'lr': 2.1244933453349325e-06, 'samples': 27620160, 'steps': 143854, 'loss/train': 0.050607770681381226} 08/31/2021 15:19:35 - INFO - __main__ - Step 143856: {'lr': 2.123803040217004e-06, 'samples': 27620352, 'steps': 143855, 'loss/train': 0.758804202079773} 08/31/2021 15:19:37 - INFO - __main__ - Step 143857: {'lr': 2.123112846788261e-06, 'samples': 27620544, 'steps': 143856, 'loss/train': 1.2116963863372803} 08/31/2021 15:19:38 - INFO - __main__ - Step 143858: {'lr': 2.122422765049009e-06, 'samples': 27620736, 'steps': 143857, 'loss/train': 0.8966442942619324} 08/31/2021 15:19:38 - INFO - __main__ - Step 143859: {'lr': 2.121732794999581e-06, 'samples': 27620928, 'steps': 143858, 'loss/train': 1.2250820398330688} 08/31/2021 15:19:38 - INFO - __main__ - Step 143860: {'lr': 2.121042936640283e-06, 'samples': 27621120, 'steps': 143859, 'loss/train': 0.8053778409957886} 08/31/2021 15:19:39 - INFO - __main__ - Step 143861: {'lr': 2.1203531899713913e-06, 'samples': 27621312, 'steps': 143860, 'loss/train': 0.853137731552124} 08/31/2021 15:19:39 - INFO - __main__ - Step 143862: {'lr': 2.1196635549932676e-06, 'samples': 27621504, 'steps': 143861, 'loss/train': 1.0714577436447144} 08/31/2021 15:19:41 - INFO - __main__ - Step 143863: {'lr': 2.118974031706189e-06, 'samples': 27621696, 'steps': 143862, 'loss/train': 0.682694137096405} 08/31/2021 15:19:41 - INFO - __main__ - Step 143864: {'lr': 2.118284620110489e-06, 'samples': 27621888, 'steps': 143863, 'loss/train': 0.7124814987182617} 08/31/2021 15:19:41 - INFO - __main__ - Step 143865: {'lr': 2.1175953202064726e-06, 'samples': 27622080, 'steps': 143864, 'loss/train': 0.9753155708312988} 08/31/2021 15:19:42 - INFO - __main__ - Step 143866: {'lr': 2.116906131994417e-06, 'samples': 27622272, 'steps': 143865, 'loss/train': 1.7484984397888184} 08/31/2021 15:19:42 - INFO - __main__ - Step 143867: {'lr': 2.1162170554746564e-06, 'samples': 27622464, 'steps': 143866, 'loss/train': 1.5789735317230225} 08/31/2021 15:19:44 - INFO - __main__ - Step 143868: {'lr': 2.1155280906475228e-06, 'samples': 27622656, 'steps': 143867, 'loss/train': 1.3971589803695679} 08/31/2021 15:19:44 - INFO - __main__ - Step 143869: {'lr': 2.114839237513294e-06, 'samples': 27622848, 'steps': 143868, 'loss/train': 0.758830726146698} 08/31/2021 15:19:45 - INFO - __main__ - Step 143870: {'lr': 2.1141504960723036e-06, 'samples': 27623040, 'steps': 143869, 'loss/train': 1.3879306316375732} 08/31/2021 15:19:45 - INFO - __main__ - Step 143871: {'lr': 2.1134618663248284e-06, 'samples': 27623232, 'steps': 143870, 'loss/train': 1.0383901596069336} 08/31/2021 15:19:45 - INFO - __main__ - Step 143872: {'lr': 2.1127733482712295e-06, 'samples': 27623424, 'steps': 143871, 'loss/train': 1.268279790878296} 08/31/2021 15:19:46 - INFO - __main__ - Step 143873: {'lr': 2.1120849419117848e-06, 'samples': 27623616, 'steps': 143872, 'loss/train': 0.04257679358124733} 08/31/2021 15:19:47 - INFO - __main__ - Step 143874: {'lr': 2.111396647246799e-06, 'samples': 27623808, 'steps': 143873, 'loss/train': 1.2572869062423706} 08/31/2021 15:19:48 - INFO - __main__ - Step 143875: {'lr': 2.110708464276606e-06, 'samples': 27624000, 'steps': 143874, 'loss/train': 1.019472599029541} 08/31/2021 15:19:48 - INFO - __main__ - Step 143876: {'lr': 2.1100203930014826e-06, 'samples': 27624192, 'steps': 143875, 'loss/train': 1.4467697143554688} 08/31/2021 15:19:48 - INFO - __main__ - Step 143877: {'lr': 2.10933243342179e-06, 'samples': 27624384, 'steps': 143876, 'loss/train': 1.0676078796386719} 08/31/2021 15:19:49 - INFO - __main__ - Step 143878: {'lr': 2.1086445855377777e-06, 'samples': 27624576, 'steps': 143877, 'loss/train': 0.9910643100738525} 08/31/2021 15:19:51 - INFO - __main__ - Step 143879: {'lr': 2.107956849349807e-06, 'samples': 27624768, 'steps': 143878, 'loss/train': 1.2515052556991577} 08/31/2021 15:19:51 - INFO - __main__ - Step 143880: {'lr': 2.107269224858155e-06, 'samples': 27624960, 'steps': 143879, 'loss/train': 0.10774104297161102} 08/31/2021 15:19:52 - INFO - __main__ - Step 143881: {'lr': 2.106581712063127e-06, 'samples': 27625152, 'steps': 143880, 'loss/train': 0.16554096341133118} 08/31/2021 15:19:52 - INFO - __main__ - Step 143882: {'lr': 2.1058943109650563e-06, 'samples': 27625344, 'steps': 143881, 'loss/train': 0.528609573841095} 08/31/2021 15:19:52 - INFO - __main__ - Step 143883: {'lr': 2.105207021564276e-06, 'samples': 27625536, 'steps': 143882, 'loss/train': 1.2011810541152954} 08/31/2021 15:19:54 - INFO - __main__ - Step 143884: {'lr': 2.1045198438610357e-06, 'samples': 27625728, 'steps': 143883, 'loss/train': 1.5086644887924194} 08/31/2021 15:19:55 - INFO - __main__ - Step 143885: {'lr': 2.1038327778556687e-06, 'samples': 27625920, 'steps': 143884, 'loss/train': 1.0853716135025024} 08/31/2021 15:19:55 - INFO - __main__ - Step 143886: {'lr': 2.1031458235484802e-06, 'samples': 27626112, 'steps': 143885, 'loss/train': 1.5072717666625977} 08/31/2021 15:19:55 - INFO - __main__ - Step 143887: {'lr': 2.102458980939831e-06, 'samples': 27626304, 'steps': 143886, 'loss/train': 1.1658002138137817} 08/31/2021 15:19:56 - INFO - __main__ - Step 143888: {'lr': 2.101772250029943e-06, 'samples': 27626496, 'steps': 143887, 'loss/train': 0.6772908568382263} 08/31/2021 15:19:57 - INFO - __main__ - Step 143889: {'lr': 2.101085630819205e-06, 'samples': 27626688, 'steps': 143888, 'loss/train': 0.40995168685913086} 08/31/2021 15:19:58 - INFO - __main__ - Step 143890: {'lr': 2.1003991233078665e-06, 'samples': 27626880, 'steps': 143889, 'loss/train': 0.97225022315979} 08/31/2021 15:19:58 - INFO - __main__ - Step 143891: {'lr': 2.099712727496289e-06, 'samples': 27627072, 'steps': 143890, 'loss/train': 1.0354923009872437} 08/31/2021 15:19:58 - INFO - __main__ - Step 143892: {'lr': 2.0990264433847495e-06, 'samples': 27627264, 'steps': 143891, 'loss/train': 1.159458875656128} 08/31/2021 15:19:59 - INFO - __main__ - Step 143893: {'lr': 2.0983402709735535e-06, 'samples': 27627456, 'steps': 143892, 'loss/train': 0.36150237917900085} 08/31/2021 15:20:00 - INFO - __main__ - Step 143894: {'lr': 2.097654210263006e-06, 'samples': 27627648, 'steps': 143893, 'loss/train': 1.8520070314407349} 08/31/2021 15:20:00 - INFO - __main__ - Step 143895: {'lr': 2.0969682612534678e-06, 'samples': 27627840, 'steps': 143894, 'loss/train': 1.2339119911193848} 08/31/2021 15:20:01 - INFO - __main__ - Step 143896: {'lr': 2.0962824239451893e-06, 'samples': 27628032, 'steps': 143895, 'loss/train': 1.0673576593399048} 08/31/2021 15:20:01 - INFO - __main__ - Step 143897: {'lr': 2.0955966983384756e-06, 'samples': 27628224, 'steps': 143896, 'loss/train': 1.0876258611679077} 08/31/2021 15:20:02 - INFO - __main__ - Step 143898: {'lr': 2.0949110844336872e-06, 'samples': 27628416, 'steps': 143897, 'loss/train': 0.9685614109039307} 08/31/2021 15:20:03 - INFO - __main__ - Step 143899: {'lr': 2.094225582231102e-06, 'samples': 27628608, 'steps': 143898, 'loss/train': 1.5155613422393799} 08/31/2021 15:20:04 - INFO - __main__ - Step 143900: {'lr': 2.0935401917310527e-06, 'samples': 27628800, 'steps': 143899, 'loss/train': 1.0507476329803467} 08/31/2021 15:20:04 - INFO - __main__ - Step 143901: {'lr': 2.0928549129338172e-06, 'samples': 27628992, 'steps': 143900, 'loss/train': 2.189176559448242} 08/31/2021 15:20:04 - INFO - __main__ - Step 143902: {'lr': 2.0921697458397005e-06, 'samples': 27629184, 'steps': 143901, 'loss/train': 1.0463868379592896} 08/31/2021 15:20:05 - INFO - __main__ - Step 143903: {'lr': 2.091484690449036e-06, 'samples': 27629376, 'steps': 143902, 'loss/train': 0.9574213624000549} 08/31/2021 15:20:05 - INFO - __main__ - Step 143904: {'lr': 2.0907997467621286e-06, 'samples': 27629568, 'steps': 143903, 'loss/train': 0.3709849715232849} 08/31/2021 15:20:06 - INFO - __main__ - Step 143905: {'lr': 2.090114914779284e-06, 'samples': 27629760, 'steps': 143904, 'loss/train': 1.1929289102554321} 08/31/2021 15:20:07 - INFO - __main__ - Step 143906: {'lr': 2.0894301945008077e-06, 'samples': 27629952, 'steps': 143905, 'loss/train': 1.250739336013794} 08/31/2021 15:20:07 - INFO - __main__ - Step 143907: {'lr': 2.0887455859269764e-06, 'samples': 27630144, 'steps': 143906, 'loss/train': 0.8187044858932495} 08/31/2021 15:20:08 - INFO - __main__ - Step 143908: {'lr': 2.08806108905818e-06, 'samples': 27630336, 'steps': 143907, 'loss/train': 0.4097112715244293} 08/31/2021 15:20:08 - INFO - __main__ - Step 143909: {'lr': 2.087376703894639e-06, 'samples': 27630528, 'steps': 143908, 'loss/train': 1.1036690473556519} 08/31/2021 15:20:09 - INFO - __main__ - Step 143910: {'lr': 2.086692430436715e-06, 'samples': 27630720, 'steps': 143909, 'loss/train': 0.19681958854198456} 08/31/2021 15:20:10 - INFO - __main__ - Step 143911: {'lr': 2.086008268684714e-06, 'samples': 27630912, 'steps': 143910, 'loss/train': 0.6929347515106201} 08/31/2021 15:20:10 - INFO - __main__ - Step 143912: {'lr': 2.085324218638912e-06, 'samples': 27631104, 'steps': 143911, 'loss/train': 1.217911958694458} 08/31/2021 15:20:11 - INFO - __main__ - Step 143913: {'lr': 2.0846402802996433e-06, 'samples': 27631296, 'steps': 143912, 'loss/train': 1.0458674430847168} 08/31/2021 15:20:11 - INFO - __main__ - Step 143914: {'lr': 2.0839564536672127e-06, 'samples': 27631488, 'steps': 143913, 'loss/train': 0.3644431233406067} 08/31/2021 15:20:13 - INFO - __main__ - Step 143915: {'lr': 2.083272738741926e-06, 'samples': 27631680, 'steps': 143914, 'loss/train': 1.4067462682724} 08/31/2021 15:20:13 - INFO - __main__ - Step 143916: {'lr': 2.082589135524088e-06, 'samples': 27631872, 'steps': 143915, 'loss/train': 1.1970267295837402} 08/31/2021 15:20:13 - INFO - __main__ - Step 143917: {'lr': 2.0819056440140036e-06, 'samples': 27632064, 'steps': 143916, 'loss/train': 0.6855764389038086} 08/31/2021 15:20:14 - INFO - __main__ - Step 143918: {'lr': 2.0812222642120072e-06, 'samples': 27632256, 'steps': 143917, 'loss/train': 1.1427626609802246} 08/31/2021 15:20:14 - INFO - __main__ - Step 143919: {'lr': 2.0805389961183752e-06, 'samples': 27632448, 'steps': 143918, 'loss/train': 0.7376202940940857} 08/31/2021 15:20:16 - INFO - __main__ - Step 143920: {'lr': 2.079855839733441e-06, 'samples': 27632640, 'steps': 143919, 'loss/train': 0.10778234153985977} 08/31/2021 15:20:16 - INFO - __main__ - Step 143921: {'lr': 2.0791727950574822e-06, 'samples': 27632832, 'steps': 143920, 'loss/train': 1.4335752725601196} 08/31/2021 15:20:16 - INFO - __main__ - Step 143922: {'lr': 2.0784898620908044e-06, 'samples': 27633024, 'steps': 143921, 'loss/train': 1.3259998559951782} 08/31/2021 15:20:17 - INFO - __main__ - Step 143923: {'lr': 2.077807040833768e-06, 'samples': 27633216, 'steps': 143922, 'loss/train': 0.6227726936340332} 08/31/2021 15:20:17 - INFO - __main__ - Step 143924: {'lr': 2.0771243312866227e-06, 'samples': 27633408, 'steps': 143923, 'loss/train': 1.2853060960769653} 08/31/2021 15:20:19 - INFO - __main__ - Step 143925: {'lr': 2.0764417334497023e-06, 'samples': 27633600, 'steps': 143924, 'loss/train': 0.7801457643508911} 08/31/2021 15:20:19 - INFO - __main__ - Step 143926: {'lr': 2.075759247323311e-06, 'samples': 27633792, 'steps': 143925, 'loss/train': 1.2607696056365967} 08/31/2021 15:20:20 - INFO - __main__ - Step 143927: {'lr': 2.075076872907783e-06, 'samples': 27633984, 'steps': 143926, 'loss/train': 0.0553792379796505} 08/31/2021 15:20:20 - INFO - __main__ - Step 143928: {'lr': 2.0743946102033672e-06, 'samples': 27634176, 'steps': 143927, 'loss/train': 0.9815394878387451} 08/31/2021 15:20:20 - INFO - __main__ - Step 143929: {'lr': 2.073712459210425e-06, 'samples': 27634368, 'steps': 143928, 'loss/train': 1.0567964315414429} 08/31/2021 15:20:21 - INFO - __main__ - Step 143930: {'lr': 2.073030419929234e-06, 'samples': 27634560, 'steps': 143929, 'loss/train': 0.8069639205932617} 08/31/2021 15:20:23 - INFO - __main__ - Step 143931: {'lr': 2.072348492360099e-06, 'samples': 27634752, 'steps': 143930, 'loss/train': 0.6973642706871033} 08/31/2021 15:20:23 - INFO - __main__ - Step 143932: {'lr': 2.071666676503353e-06, 'samples': 27634944, 'steps': 143931, 'loss/train': 1.1519875526428223} 08/31/2021 15:20:24 - INFO - __main__ - Step 143933: {'lr': 2.0709849723593023e-06, 'samples': 27635136, 'steps': 143932, 'loss/train': 1.2871274948120117} 08/31/2021 15:20:24 - INFO - __main__ - Step 143934: {'lr': 2.0703033799281956e-06, 'samples': 27635328, 'steps': 143933, 'loss/train': 1.3126027584075928} 08/31/2021 15:20:25 - INFO - __main__ - Step 143935: {'lr': 2.069621899210422e-06, 'samples': 27635520, 'steps': 143934, 'loss/train': 1.3856878280639648} 08/31/2021 15:20:26 - INFO - __main__ - Step 143936: {'lr': 2.0689405302062314e-06, 'samples': 27635712, 'steps': 143935, 'loss/train': 1.5154860019683838} 08/31/2021 15:20:27 - INFO - __main__ - Step 143937: {'lr': 2.0682592729159567e-06, 'samples': 27635904, 'steps': 143936, 'loss/train': 1.230654239654541} 08/31/2021 15:20:27 - INFO - __main__ - Step 143938: {'lr': 2.067578127339903e-06, 'samples': 27636096, 'steps': 143937, 'loss/train': 0.05575750395655632} 08/31/2021 15:20:28 - INFO - __main__ - Step 143939: {'lr': 2.066897093478376e-06, 'samples': 27636288, 'steps': 143938, 'loss/train': 0.5235079526901245} 08/31/2021 15:20:28 - INFO - __main__ - Step 143940: {'lr': 2.066216171331653e-06, 'samples': 27636480, 'steps': 143939, 'loss/train': 0.6791667342185974} 08/31/2021 15:20:30 - INFO - __main__ - Step 143941: {'lr': 2.065535360900095e-06, 'samples': 27636672, 'steps': 143940, 'loss/train': 0.9428713917732239} 08/31/2021 15:20:30 - INFO - __main__ - Step 143942: {'lr': 2.0648546621839794e-06, 'samples': 27636864, 'steps': 143941, 'loss/train': 1.0227842330932617} 08/31/2021 15:20:30 - INFO - __main__ - Step 143943: {'lr': 2.0641740751836115e-06, 'samples': 27637056, 'steps': 143942, 'loss/train': 0.9665018916130066} 08/31/2021 15:20:31 - INFO - __main__ - Step 143944: {'lr': 2.0634935998992966e-06, 'samples': 27637248, 'steps': 143943, 'loss/train': 0.380728155374527} 08/31/2021 15:20:31 - INFO - __main__ - Step 143945: {'lr': 2.06281323633134e-06, 'samples': 27637440, 'steps': 143944, 'loss/train': 0.41766977310180664} 08/31/2021 15:20:33 - INFO - __main__ - Step 143946: {'lr': 2.0621329844800753e-06, 'samples': 27637632, 'steps': 143945, 'loss/train': 1.2235276699066162} 08/31/2021 15:20:33 - INFO - __main__ - Step 143947: {'lr': 2.0614528443457514e-06, 'samples': 27637824, 'steps': 143946, 'loss/train': 0.12257984280586243} 08/31/2021 15:20:34 - INFO - __main__ - Step 143948: {'lr': 2.0607728159287297e-06, 'samples': 27638016, 'steps': 143947, 'loss/train': 1.2474279403686523} 08/31/2021 15:20:34 - INFO - __main__ - Step 143949: {'lr': 2.0600928992293157e-06, 'samples': 27638208, 'steps': 143948, 'loss/train': 0.29868754744529724} 08/31/2021 15:20:34 - INFO - __main__ - Step 143950: {'lr': 2.0594130942477863e-06, 'samples': 27638400, 'steps': 143949, 'loss/train': 0.5468236207962036} 08/31/2021 15:20:35 - INFO - __main__ - Step 143951: {'lr': 2.058733400984447e-06, 'samples': 27638592, 'steps': 143950, 'loss/train': 0.889805018901825} 08/31/2021 15:20:36 - INFO - __main__ - Step 143952: {'lr': 2.058053819439604e-06, 'samples': 27638784, 'steps': 143951, 'loss/train': 1.2103216648101807} 08/31/2021 15:20:37 - INFO - __main__ - Step 143953: {'lr': 2.0573743496136165e-06, 'samples': 27638976, 'steps': 143952, 'loss/train': 0.34587356448173523} 08/31/2021 15:20:37 - INFO - __main__ - Step 143954: {'lr': 2.056694991506708e-06, 'samples': 27639168, 'steps': 143953, 'loss/train': 1.1028553247451782} 08/31/2021 15:20:38 - INFO - __main__ - Step 143955: {'lr': 2.056015745119266e-06, 'samples': 27639360, 'steps': 143954, 'loss/train': 1.7179059982299805} 08/31/2021 15:20:38 - INFO - __main__ - Step 143956: {'lr': 2.0553366104515415e-06, 'samples': 27639552, 'steps': 143955, 'loss/train': 0.8682430386543274} 08/31/2021 15:20:39 - INFO - __main__ - Step 143957: {'lr': 2.0546575875038664e-06, 'samples': 27639744, 'steps': 143956, 'loss/train': 0.2554634213447571} 08/31/2021 15:20:40 - INFO - __main__ - Step 143958: {'lr': 2.053978676276519e-06, 'samples': 27639936, 'steps': 143957, 'loss/train': 0.8887671232223511} 08/31/2021 15:20:40 - INFO - __main__ - Step 143959: {'lr': 2.0532998767698317e-06, 'samples': 27640128, 'steps': 143958, 'loss/train': 1.276845097541809} 08/31/2021 15:20:41 - INFO - __main__ - Step 143960: {'lr': 2.0526211889840827e-06, 'samples': 27640320, 'steps': 143959, 'loss/train': 0.4801960587501526} 08/31/2021 15:20:41 - INFO - __main__ - Step 143961: {'lr': 2.0519426129196328e-06, 'samples': 27640512, 'steps': 143960, 'loss/train': 0.9559433460235596} 08/31/2021 15:20:42 - INFO - __main__ - Step 143962: {'lr': 2.0512641485767313e-06, 'samples': 27640704, 'steps': 143961, 'loss/train': 1.4200459718704224} 08/31/2021 15:20:43 - INFO - __main__ - Step 143963: {'lr': 2.050585795955684e-06, 'samples': 27640896, 'steps': 143962, 'loss/train': 1.104257345199585} 08/31/2021 15:20:43 - INFO - __main__ - Step 143964: {'lr': 2.049907555056851e-06, 'samples': 27641088, 'steps': 143963, 'loss/train': 1.4104771614074707} 08/31/2021 15:20:43 - INFO - __main__ - Step 143965: {'lr': 2.0492294258804833e-06, 'samples': 27641280, 'steps': 143964, 'loss/train': 1.5075304508209229} 08/31/2021 15:20:44 - INFO - __main__ - Step 143966: {'lr': 2.048551408426913e-06, 'samples': 27641472, 'steps': 143965, 'loss/train': 1.0558439493179321} 08/31/2021 15:20:45 - INFO - __main__ - Step 143967: {'lr': 2.047873502696446e-06, 'samples': 27641664, 'steps': 143966, 'loss/train': 1.1921216249465942} 08/31/2021 15:20:46 - INFO - __main__ - Step 143968: {'lr': 2.0471957086893867e-06, 'samples': 27641856, 'steps': 143967, 'loss/train': 1.5422768592834473} 08/31/2021 15:20:46 - INFO - __main__ - Step 143969: {'lr': 2.0465180264060136e-06, 'samples': 27642048, 'steps': 143968, 'loss/train': 1.0277962684631348} 08/31/2021 15:20:46 - INFO - __main__ - Step 143970: {'lr': 2.0458404558466593e-06, 'samples': 27642240, 'steps': 143969, 'loss/train': 1.2062901258468628} 08/31/2021 15:20:47 - INFO - __main__ - Step 143971: {'lr': 2.045162997011629e-06, 'samples': 27642432, 'steps': 143970, 'loss/train': 1.4665203094482422} 08/31/2021 15:20:48 - INFO - __main__ - Step 143972: {'lr': 2.044485649901201e-06, 'samples': 27642624, 'steps': 143971, 'loss/train': 1.5462236404418945} 08/31/2021 15:20:49 - INFO - __main__ - Step 143973: {'lr': 2.0438084145157355e-06, 'samples': 27642816, 'steps': 143972, 'loss/train': 0.8872866034507751} 08/31/2021 15:20:49 - INFO - __main__ - Step 143974: {'lr': 2.0431312908554823e-06, 'samples': 27643008, 'steps': 143973, 'loss/train': 0.7784655690193176} 08/31/2021 15:20:50 - INFO - __main__ - Step 143975: {'lr': 2.0424542789207747e-06, 'samples': 27643200, 'steps': 143974, 'loss/train': 1.4565521478652954} 08/31/2021 15:20:50 - INFO - __main__ - Step 143976: {'lr': 2.0417773787119176e-06, 'samples': 27643392, 'steps': 143975, 'loss/train': 0.9000375866889954} 08/31/2021 15:20:51 - INFO - __main__ - Step 143977: {'lr': 2.041100590229189e-06, 'samples': 27643584, 'steps': 143976, 'loss/train': 1.993208885192871} 08/31/2021 15:20:52 - INFO - __main__ - Step 143978: {'lr': 2.040423913472922e-06, 'samples': 27643776, 'steps': 143977, 'loss/train': 1.2703485488891602} 08/31/2021 15:20:52 - INFO - __main__ - Step 143979: {'lr': 2.0397473484434213e-06, 'samples': 27643968, 'steps': 143978, 'loss/train': 0.6174092292785645} 08/31/2021 15:20:53 - INFO - __main__ - Step 143980: {'lr': 2.039070895140993e-06, 'samples': 27644160, 'steps': 143979, 'loss/train': 1.3501092195510864} 08/31/2021 15:20:53 - INFO - __main__ - Step 143981: {'lr': 2.0383945535659144e-06, 'samples': 27644352, 'steps': 143980, 'loss/train': 0.9033617377281189} 08/31/2021 15:20:53 - INFO - __main__ - Step 143982: {'lr': 2.0377183237185182e-06, 'samples': 27644544, 'steps': 143981, 'loss/train': 0.9058188199996948} 08/31/2021 15:20:55 - INFO - __main__ - Step 143983: {'lr': 2.037042205599082e-06, 'samples': 27644736, 'steps': 143982, 'loss/train': 0.030984893441200256} 08/31/2021 15:20:56 - INFO - __main__ - Step 143984: {'lr': 2.03636619920794e-06, 'samples': 27644928, 'steps': 143983, 'loss/train': 1.6306419372558594} 08/31/2021 15:20:56 - INFO - __main__ - Step 143985: {'lr': 2.0356903045453954e-06, 'samples': 27645120, 'steps': 143984, 'loss/train': 0.548737108707428} 08/31/2021 15:20:56 - INFO - __main__ - Step 143986: {'lr': 2.0350145216117277e-06, 'samples': 27645312, 'steps': 143985, 'loss/train': 1.0871281623840332} 08/31/2021 15:20:57 - INFO - __main__ - Step 143987: {'lr': 2.034338850407297e-06, 'samples': 27645504, 'steps': 143986, 'loss/train': 1.024617075920105} 08/31/2021 15:20:58 - INFO - __main__ - Step 143988: {'lr': 2.033663290932325e-06, 'samples': 27645696, 'steps': 143987, 'loss/train': 0.8214725852012634} 08/31/2021 15:20:59 - INFO - __main__ - Step 143989: {'lr': 2.032987843187173e-06, 'samples': 27645888, 'steps': 143988, 'loss/train': 1.241387128829956} 08/31/2021 15:20:59 - INFO - __main__ - Step 143990: {'lr': 2.032312507172118e-06, 'samples': 27646080, 'steps': 143989, 'loss/train': 0.22616948187351227} 08/31/2021 15:21:00 - INFO - __main__ - Step 143991: {'lr': 2.031637282887494e-06, 'samples': 27646272, 'steps': 143990, 'loss/train': 0.5089411735534668} 08/31/2021 15:21:00 - INFO - __main__ - Step 143992: {'lr': 2.03096217033355e-06, 'samples': 27646464, 'steps': 143991, 'loss/train': 0.7341603636741638} 08/31/2021 15:21:02 - INFO - __main__ - Step 143993: {'lr': 2.030287169510675e-06, 'samples': 27646656, 'steps': 143992, 'loss/train': 0.08823966234922409} 08/31/2021 15:21:02 - INFO - __main__ - Step 143994: {'lr': 2.029612280419091e-06, 'samples': 27646848, 'steps': 143993, 'loss/train': 0.8221617937088013} 08/31/2021 15:21:02 - INFO - __main__ - Step 143995: {'lr': 2.0289375030591584e-06, 'samples': 27647040, 'steps': 143994, 'loss/train': 1.0727347135543823} 08/31/2021 15:21:03 - INFO - __main__ - Step 143996: {'lr': 2.0282628374311553e-06, 'samples': 27647232, 'steps': 143995, 'loss/train': 0.3853916525840759} 08/31/2021 15:21:03 - INFO - __main__ - Step 143997: {'lr': 2.0275882835353865e-06, 'samples': 27647424, 'steps': 143996, 'loss/train': 1.5374387502670288} 08/31/2021 15:21:04 - INFO - __main__ - Step 143998: {'lr': 2.0269138413721856e-06, 'samples': 27647616, 'steps': 143997, 'loss/train': 0.36941975355148315} 08/31/2021 15:21:05 - INFO - __main__ - Step 143999: {'lr': 2.026239510941802e-06, 'samples': 27647808, 'steps': 143998, 'loss/train': 0.847658097743988} 08/31/2021 15:21:06 - INFO - __main__ - Step 144000: {'lr': 2.025565292244569e-06, 'samples': 27648000, 'steps': 143999, 'loss/train': 0.9799543023109436} 08/31/2021 15:21:06 - INFO - __main__ - Step 144001: {'lr': 2.024891185280792e-06, 'samples': 27648192, 'steps': 144000, 'loss/train': 1.3840551376342773} 08/31/2021 15:21:06 - INFO - __main__ - Step 144002: {'lr': 2.0242171900507757e-06, 'samples': 27648384, 'steps': 144001, 'loss/train': 0.028578151017427444} 08/31/2021 15:21:07 - INFO - __main__ - Step 144003: {'lr': 2.023543306554826e-06, 'samples': 27648576, 'steps': 144002, 'loss/train': 0.6709480881690979} 08/31/2021 15:21:08 - INFO - __main__ - Step 144004: {'lr': 2.02286953479322e-06, 'samples': 27648768, 'steps': 144003, 'loss/train': 0.6050856113433838} 08/31/2021 15:21:09 - INFO - __main__ - Step 144005: {'lr': 2.0221958747662916e-06, 'samples': 27648960, 'steps': 144004, 'loss/train': 1.0393776893615723} 08/31/2021 15:21:09 - INFO - __main__ - Step 144006: {'lr': 2.0215223264743456e-06, 'samples': 27649152, 'steps': 144005, 'loss/train': 1.315118432044983} 08/31/2021 15:21:09 - INFO - __main__ - Step 144007: {'lr': 2.020848889917687e-06, 'samples': 27649344, 'steps': 144006, 'loss/train': 0.1516926884651184} 08/31/2021 15:21:10 - INFO - __main__ - Step 144008: {'lr': 2.0201755650965934e-06, 'samples': 27649536, 'steps': 144007, 'loss/train': 1.2407753467559814} 08/31/2021 15:21:11 - INFO - __main__ - Step 144009: {'lr': 2.019502352011371e-06, 'samples': 27649728, 'steps': 144008, 'loss/train': 1.2090336084365845} 08/31/2021 15:21:11 - INFO - __main__ - Step 144010: {'lr': 2.018829250662352e-06, 'samples': 27649920, 'steps': 144009, 'loss/train': 0.3059943914413452} 08/31/2021 15:21:12 - INFO - __main__ - Step 144011: {'lr': 2.018156261049814e-06, 'samples': 27650112, 'steps': 144010, 'loss/train': 1.2479220628738403} 08/31/2021 15:21:12 - INFO - __main__ - Step 144012: {'lr': 2.0174833831740624e-06, 'samples': 27650304, 'steps': 144011, 'loss/train': 1.9297548532485962} 08/31/2021 15:21:13 - INFO - __main__ - Step 144013: {'lr': 2.0168106170354028e-06, 'samples': 27650496, 'steps': 144012, 'loss/train': 1.1370904445648193} 08/31/2021 15:21:14 - INFO - __main__ - Step 144014: {'lr': 2.016137962634168e-06, 'samples': 27650688, 'steps': 144013, 'loss/train': 1.4156757593154907} 08/31/2021 15:21:15 - INFO - __main__ - Step 144015: {'lr': 2.015465419970608e-06, 'samples': 27650880, 'steps': 144014, 'loss/train': 0.02039291150867939} 08/31/2021 15:21:15 - INFO - __main__ - Step 144016: {'lr': 2.0147929890450554e-06, 'samples': 27651072, 'steps': 144015, 'loss/train': 1.0850573778152466} 08/31/2021 15:21:15 - INFO - __main__ - Step 144017: {'lr': 2.0141206698578163e-06, 'samples': 27651264, 'steps': 144016, 'loss/train': 1.1610652208328247} 08/31/2021 15:21:16 - INFO - __main__ - Step 144018: {'lr': 2.013448462409195e-06, 'samples': 27651456, 'steps': 144017, 'loss/train': 0.900877058506012} 08/31/2021 15:21:17 - INFO - __main__ - Step 144019: {'lr': 2.01277636669947e-06, 'samples': 27651648, 'steps': 144018, 'loss/train': 1.0761165618896484} 08/31/2021 15:21:18 - INFO - __main__ - Step 144020: {'lr': 2.012104382728974e-06, 'samples': 27651840, 'steps': 144019, 'loss/train': 1.2953931093215942} 08/31/2021 15:21:18 - INFO - __main__ - Step 144021: {'lr': 2.0114325104980125e-06, 'samples': 27652032, 'steps': 144020, 'loss/train': 0.4425607919692993} 08/31/2021 15:21:18 - INFO - __main__ - Step 144022: {'lr': 2.0107607500068347e-06, 'samples': 27652224, 'steps': 144021, 'loss/train': 1.1820980310440063} 08/31/2021 15:21:19 - INFO - __main__ - Step 144023: {'lr': 2.010089101255802e-06, 'samples': 27652416, 'steps': 144022, 'loss/train': 1.3750104904174805} 08/31/2021 15:21:20 - INFO - __main__ - Step 144024: {'lr': 2.009417564245192e-06, 'samples': 27652608, 'steps': 144023, 'loss/train': 1.0600236654281616} 08/31/2021 15:21:21 - INFO - __main__ - Step 144025: {'lr': 2.008746138975337e-06, 'samples': 27652800, 'steps': 144024, 'loss/train': 0.8920503258705139} 08/31/2021 15:21:21 - INFO - __main__ - Step 144026: {'lr': 2.0080748254464875e-06, 'samples': 27652992, 'steps': 144025, 'loss/train': 1.5362355709075928} 08/31/2021 15:21:22 - INFO - __main__ - Step 144027: {'lr': 2.0074036236589765e-06, 'samples': 27653184, 'steps': 144026, 'loss/train': 1.9454841613769531} 08/31/2021 15:21:22 - INFO - __main__ - Step 144028: {'lr': 2.006732533613109e-06, 'samples': 27653376, 'steps': 144027, 'loss/train': 0.925953209400177} 08/31/2021 15:21:22 - INFO - __main__ - Step 144029: {'lr': 2.006061555309191e-06, 'samples': 27653568, 'steps': 144028, 'loss/train': 2.9097864627838135} 08/31/2021 15:21:24 - INFO - __main__ - Step 144030: {'lr': 2.0053906887474994e-06, 'samples': 27653760, 'steps': 144029, 'loss/train': 2.9862091541290283} 08/31/2021 15:21:24 - INFO - __main__ - Step 144031: {'lr': 2.0047199339283395e-06, 'samples': 27653952, 'steps': 144030, 'loss/train': 0.4541974663734436} 08/31/2021 15:21:25 - INFO - __main__ - Step 144032: {'lr': 2.0040492908520445e-06, 'samples': 27654144, 'steps': 144031, 'loss/train': 0.5936429500579834} 08/31/2021 15:21:25 - INFO - __main__ - Step 144033: {'lr': 2.0033787595188923e-06, 'samples': 27654336, 'steps': 144032, 'loss/train': 1.0207359790802002} 08/31/2021 15:21:25 - INFO - __main__ - Step 144034: {'lr': 2.0027083399291877e-06, 'samples': 27654528, 'steps': 144033, 'loss/train': 1.6384247541427612} 08/31/2021 15:21:26 - INFO - __main__ - Step 144035: {'lr': 2.0020380320832366e-06, 'samples': 27654720, 'steps': 144034, 'loss/train': 0.9353376626968384} 08/31/2021 15:21:27 - INFO - __main__ - Step 144036: {'lr': 2.0013678359813435e-06, 'samples': 27654912, 'steps': 144035, 'loss/train': 1.4473265409469604} 08/31/2021 15:21:28 - INFO - __main__ - Step 144037: {'lr': 2.0006977516238145e-06, 'samples': 27655104, 'steps': 144036, 'loss/train': 1.1053650379180908} 08/31/2021 15:21:28 - INFO - __main__ - Step 144038: {'lr': 2.0000277790109267e-06, 'samples': 27655296, 'steps': 144037, 'loss/train': 1.6772416830062866} 08/31/2021 15:21:28 - INFO - __main__ - Step 144039: {'lr': 1.999357918143041e-06, 'samples': 27655488, 'steps': 144038, 'loss/train': 0.2989524304866791} 08/31/2021 15:21:29 - INFO - __main__ - Step 144040: {'lr': 1.9986881690203794e-06, 'samples': 27655680, 'steps': 144039, 'loss/train': 0.38046902418136597} 08/31/2021 15:21:31 - INFO - __main__ - Step 144041: {'lr': 1.998018531643275e-06, 'samples': 27655872, 'steps': 144040, 'loss/train': 0.6034666895866394} 08/31/2021 15:21:31 - INFO - __main__ - Step 144042: {'lr': 1.9973490060120613e-06, 'samples': 27656064, 'steps': 144041, 'loss/train': 1.5535142421722412} 08/31/2021 15:21:32 - INFO - __main__ - Step 144043: {'lr': 1.9966795921269876e-06, 'samples': 27656256, 'steps': 144042, 'loss/train': 0.953471839427948} 08/31/2021 15:21:32 - INFO - __main__ - Step 144044: {'lr': 1.9960102899884146e-06, 'samples': 27656448, 'steps': 144043, 'loss/train': 0.6365799307823181} 08/31/2021 15:21:32 - INFO - __main__ - Step 144045: {'lr': 1.9953410995965927e-06, 'samples': 27656640, 'steps': 144044, 'loss/train': 1.167367935180664} 08/31/2021 15:21:34 - INFO - __main__ - Step 144046: {'lr': 1.9946720209518544e-06, 'samples': 27656832, 'steps': 144045, 'loss/train': 1.4885752201080322} 08/31/2021 15:21:34 - INFO - __main__ - Step 144047: {'lr': 1.9940030540544775e-06, 'samples': 27657024, 'steps': 144046, 'loss/train': 1.070241928100586} 08/31/2021 15:21:35 - INFO - __main__ - Step 144048: {'lr': 1.993334198904795e-06, 'samples': 27657216, 'steps': 144047, 'loss/train': 0.6676796078681946} 08/31/2021 15:21:35 - INFO - __main__ - Step 144049: {'lr': 1.9926654555030564e-06, 'samples': 27657408, 'steps': 144048, 'loss/train': 0.8914034962654114} 08/31/2021 15:21:36 - INFO - __main__ - Step 144050: {'lr': 1.9919968238496233e-06, 'samples': 27657600, 'steps': 144049, 'loss/train': 1.6987099647521973} 08/31/2021 15:21:37 - INFO - __main__ - Step 144051: {'lr': 1.9913283039447727e-06, 'samples': 27657792, 'steps': 144050, 'loss/train': 0.9535067081451416} 08/31/2021 15:21:38 - INFO - __main__ - Step 144052: {'lr': 1.9906598957887822e-06, 'samples': 27657984, 'steps': 144051, 'loss/train': 1.18631911277771} 08/31/2021 15:21:38 - INFO - __main__ - Step 144053: {'lr': 1.989991599381985e-06, 'samples': 27658176, 'steps': 144052, 'loss/train': 1.6824707984924316} 08/31/2021 15:21:38 - INFO - __main__ - Step 144054: {'lr': 1.9893234147246864e-06, 'samples': 27658368, 'steps': 144053, 'loss/train': 1.0890405178070068} 08/31/2021 15:21:39 - INFO - __main__ - Step 144055: {'lr': 1.988655341817136e-06, 'samples': 27658560, 'steps': 144054, 'loss/train': 1.1335968971252441} 08/31/2021 15:21:40 - INFO - __main__ - Step 144056: {'lr': 1.987987380659695e-06, 'samples': 27658752, 'steps': 144055, 'loss/train': 1.2367843389511108} 08/31/2021 15:21:41 - INFO - __main__ - Step 144057: {'lr': 1.9873195312526405e-06, 'samples': 27658944, 'steps': 144056, 'loss/train': 1.3397899866104126} 08/31/2021 15:21:41 - INFO - __main__ - Step 144058: {'lr': 1.98665179359625e-06, 'samples': 27659136, 'steps': 144057, 'loss/train': 0.8665300011634827} 08/31/2021 15:21:41 - INFO - __main__ - Step 144059: {'lr': 1.9859841676908574e-06, 'samples': 27659328, 'steps': 144058, 'loss/train': 0.961898148059845} 08/31/2021 15:21:42 - INFO - __main__ - Step 144060: {'lr': 1.9853166535367673e-06, 'samples': 27659520, 'steps': 144059, 'loss/train': 0.028775624930858612} 08/31/2021 15:21:43 - INFO - __main__ - Step 144061: {'lr': 1.9846492511342573e-06, 'samples': 27659712, 'steps': 144060, 'loss/train': 1.7040514945983887} 08/31/2021 15:21:44 - INFO - __main__ - Step 144062: {'lr': 1.9839819604836327e-06, 'samples': 27659904, 'steps': 144061, 'loss/train': 1.191033959388733} 08/31/2021 15:21:44 - INFO - __main__ - Step 144063: {'lr': 1.9833147815851993e-06, 'samples': 27660096, 'steps': 144062, 'loss/train': 1.0841875076293945} 08/31/2021 15:21:45 - INFO - __main__ - Step 144064: {'lr': 1.982647714439262e-06, 'samples': 27660288, 'steps': 144063, 'loss/train': 1.4650732278823853} 08/31/2021 15:21:45 - INFO - __main__ - Step 144065: {'lr': 1.981980759046126e-06, 'samples': 27660480, 'steps': 144064, 'loss/train': 1.348002314567566} 08/31/2021 15:21:46 - INFO - __main__ - Step 144066: {'lr': 1.981313915406069e-06, 'samples': 27660672, 'steps': 144065, 'loss/train': 0.7706509232521057} 08/31/2021 15:21:47 - INFO - __main__ - Step 144067: {'lr': 1.9806471835194238e-06, 'samples': 27660864, 'steps': 144066, 'loss/train': 1.0662157535552979} 08/31/2021 15:21:47 - INFO - __main__ - Step 144068: {'lr': 1.979980563386441e-06, 'samples': 27661056, 'steps': 144067, 'loss/train': 0.9876429438591003} 08/31/2021 15:21:48 - INFO - __main__ - Step 144069: {'lr': 1.9793140550074807e-06, 'samples': 27661248, 'steps': 144068, 'loss/train': 0.9462432265281677} 08/31/2021 15:21:48 - INFO - __main__ - Step 144070: {'lr': 1.9786476583827927e-06, 'samples': 27661440, 'steps': 144069, 'loss/train': 0.8741456866264343} 08/31/2021 15:21:48 - INFO - __main__ - Step 144071: {'lr': 1.9779813735127108e-06, 'samples': 27661632, 'steps': 144070, 'loss/train': 0.8665781617164612} 08/31/2021 15:21:50 - INFO - __main__ - Step 144072: {'lr': 1.9773152003975115e-06, 'samples': 27661824, 'steps': 144071, 'loss/train': 0.20061983168125153} 08/31/2021 15:21:50 - INFO - __main__ - Step 144073: {'lr': 1.9766491390375285e-06, 'samples': 27662016, 'steps': 144072, 'loss/train': 1.3978019952774048} 08/31/2021 15:21:50 - INFO - __main__ - Step 144074: {'lr': 1.9759831894330114e-06, 'samples': 27662208, 'steps': 144073, 'loss/train': 1.0953240394592285} 08/31/2021 15:21:51 - INFO - __main__ - Step 144075: {'lr': 1.975317351584294e-06, 'samples': 27662400, 'steps': 144074, 'loss/train': 0.562920093536377} 08/31/2021 15:21:51 - INFO - __main__ - Step 144076: {'lr': 1.9746516254916803e-06, 'samples': 27662592, 'steps': 144075, 'loss/train': 1.7631932497024536} 08/31/2021 15:21:53 - INFO - __main__ - Step 144077: {'lr': 1.9739860111554765e-06, 'samples': 27662784, 'steps': 144076, 'loss/train': 1.2826443910598755} 08/31/2021 15:21:53 - INFO - __main__ - Step 144078: {'lr': 1.973320508575932e-06, 'samples': 27662976, 'steps': 144077, 'loss/train': 1.32064950466156} 08/31/2021 15:21:53 - INFO - __main__ - Step 144079: {'lr': 1.9726551177534357e-06, 'samples': 27663168, 'steps': 144078, 'loss/train': 1.345946192741394} 08/31/2021 15:21:54 - INFO - __main__ - Step 144080: {'lr': 1.9719898386881818e-06, 'samples': 27663360, 'steps': 144079, 'loss/train': 1.5386927127838135} 08/31/2021 15:21:54 - INFO - __main__ - Step 144081: {'lr': 1.9713246713805587e-06, 'samples': 27663552, 'steps': 144080, 'loss/train': 1.4540736675262451} 08/31/2021 15:21:56 - INFO - __main__ - Step 144082: {'lr': 1.9706596158308167e-06, 'samples': 27663744, 'steps': 144081, 'loss/train': 0.7770313024520874} 08/31/2021 15:21:57 - INFO - __main__ - Step 144083: {'lr': 1.9699946720392603e-06, 'samples': 27663936, 'steps': 144082, 'loss/train': 0.6151341199874878} 08/31/2021 15:21:57 - INFO - __main__ - Step 144084: {'lr': 1.9693298400061954e-06, 'samples': 27664128, 'steps': 144083, 'loss/train': 1.6681737899780273} 08/31/2021 15:21:57 - INFO - __main__ - Step 144085: {'lr': 1.968665119731927e-06, 'samples': 27664320, 'steps': 144084, 'loss/train': 0.6783236265182495} 08/31/2021 15:21:58 - INFO - __main__ - Step 144086: {'lr': 1.968000511216733e-06, 'samples': 27664512, 'steps': 144085, 'loss/train': 1.3445738554000854} 08/31/2021 15:21:58 - INFO - __main__ - Step 144087: {'lr': 1.9673360144609466e-06, 'samples': 27664704, 'steps': 144086, 'loss/train': 1.0452466011047363} 08/31/2021 15:21:59 - INFO - __main__ - Step 144088: {'lr': 1.9666716294648725e-06, 'samples': 27664896, 'steps': 144087, 'loss/train': 1.454525351524353} 08/31/2021 15:22:00 - INFO - __main__ - Step 144089: {'lr': 1.9660073562287606e-06, 'samples': 27665088, 'steps': 144088, 'loss/train': 1.2449578046798706} 08/31/2021 15:22:00 - INFO - __main__ - Step 144090: {'lr': 1.9653431947529444e-06, 'samples': 27665280, 'steps': 144089, 'loss/train': 1.2685306072235107} 08/31/2021 15:22:01 - INFO - __main__ - Step 144091: {'lr': 1.964679145037729e-06, 'samples': 27665472, 'steps': 144090, 'loss/train': 1.1016857624053955} 08/31/2021 15:22:01 - INFO - __main__ - Step 144092: {'lr': 1.9640152070833916e-06, 'samples': 27665664, 'steps': 144091, 'loss/train': 1.5742980241775513} 08/31/2021 15:22:03 - INFO - __main__ - Step 144093: {'lr': 1.963351380890238e-06, 'samples': 27665856, 'steps': 144092, 'loss/train': 1.6205973625183105} 08/31/2021 15:22:04 - INFO - __main__ - Step 144094: {'lr': 1.9626876664585737e-06, 'samples': 27666048, 'steps': 144093, 'loss/train': 0.7949786186218262} 08/31/2021 15:22:04 - INFO - __main__ - Step 144095: {'lr': 1.962024063788703e-06, 'samples': 27666240, 'steps': 144094, 'loss/train': 1.762734293937683} 08/31/2021 15:22:04 - INFO - __main__ - Step 144096: {'lr': 1.9613605728809046e-06, 'samples': 27666432, 'steps': 144095, 'loss/train': 0.9626136422157288} 08/31/2021 15:22:05 - INFO - __main__ - Step 144097: {'lr': 1.9606971937355113e-06, 'samples': 27666624, 'steps': 144096, 'loss/train': 0.2554587125778198} 08/31/2021 15:22:05 - INFO - __main__ - Step 144098: {'lr': 1.960033926352772e-06, 'samples': 27666816, 'steps': 144097, 'loss/train': 1.0521858930587769} 08/31/2021 15:22:07 - INFO - __main__ - Step 144099: {'lr': 1.959370770733021e-06, 'samples': 27667008, 'steps': 144098, 'loss/train': 2.7236316204071045} 08/31/2021 15:22:07 - INFO - __main__ - Step 144100: {'lr': 1.958707726876563e-06, 'samples': 27667200, 'steps': 144099, 'loss/train': 2.063138484954834} 08/31/2021 15:22:08 - INFO - __main__ - Step 144101: {'lr': 1.9580447947836755e-06, 'samples': 27667392, 'steps': 144100, 'loss/train': 0.9332437515258789} 08/31/2021 15:22:08 - INFO - __main__ - Step 144102: {'lr': 1.957381974454664e-06, 'samples': 27667584, 'steps': 144101, 'loss/train': 1.0813630819320679} 08/31/2021 15:22:10 - INFO - __main__ - Step 144103: {'lr': 1.9567192658898337e-06, 'samples': 27667776, 'steps': 144102, 'loss/train': 0.20929685235023499} 08/31/2021 15:22:10 - INFO - __main__ - Step 144104: {'lr': 1.956056669089462e-06, 'samples': 27667968, 'steps': 144103, 'loss/train': 1.7049769163131714} 08/31/2021 15:22:10 - INFO - __main__ - Step 144105: {'lr': 1.9553941840538823e-06, 'samples': 27668160, 'steps': 144104, 'loss/train': 0.668705940246582} 08/31/2021 15:22:11 - INFO - __main__ - Step 144106: {'lr': 1.9547318107834e-06, 'samples': 27668352, 'steps': 144105, 'loss/train': 1.8486299514770508} 08/31/2021 15:22:11 - INFO - __main__ - Step 144107: {'lr': 1.954069549278237e-06, 'samples': 27668544, 'steps': 144106, 'loss/train': 0.7009305953979492} 08/31/2021 15:22:12 - INFO - __main__ - Step 144108: {'lr': 1.953407399538781e-06, 'samples': 27668736, 'steps': 144107, 'loss/train': 0.355391263961792} 08/31/2021 15:22:13 - INFO - __main__ - Step 144109: {'lr': 1.9527453615652557e-06, 'samples': 27668928, 'steps': 144108, 'loss/train': 1.417988896369934} 08/31/2021 15:22:13 - INFO - __main__ - Step 144110: {'lr': 1.952083435358021e-06, 'samples': 27669120, 'steps': 144109, 'loss/train': 1.1320745944976807} 08/31/2021 15:22:14 - INFO - __main__ - Step 144111: {'lr': 1.951421620917354e-06, 'samples': 27669312, 'steps': 144110, 'loss/train': 1.6196309328079224} 08/31/2021 15:22:14 - INFO - __main__ - Step 144112: {'lr': 1.950759918243533e-06, 'samples': 27669504, 'steps': 144111, 'loss/train': 1.6537173986434937} 08/31/2021 15:22:15 - INFO - __main__ - Step 144113: {'lr': 1.9500983273368635e-06, 'samples': 27669696, 'steps': 144112, 'loss/train': 1.311592698097229} 08/31/2021 15:22:16 - INFO - __main__ - Step 144114: {'lr': 1.9494368481976778e-06, 'samples': 27669888, 'steps': 144113, 'loss/train': 0.840822696685791} 08/31/2021 15:22:16 - INFO - __main__ - Step 144115: {'lr': 1.948775480826226e-06, 'samples': 27670080, 'steps': 144114, 'loss/train': 0.7166501879692078} 08/31/2021 15:22:17 - INFO - __main__ - Step 144116: {'lr': 1.948114225222841e-06, 'samples': 27670272, 'steps': 144115, 'loss/train': 1.8186123371124268} 08/31/2021 15:22:17 - INFO - __main__ - Step 144117: {'lr': 1.9474530813878013e-06, 'samples': 27670464, 'steps': 144116, 'loss/train': 1.5418142080307007} 08/31/2021 15:22:17 - INFO - __main__ - Step 144118: {'lr': 1.946792049321411e-06, 'samples': 27670656, 'steps': 144117, 'loss/train': 0.5803681015968323} 08/31/2021 15:22:19 - INFO - __main__ - Step 144119: {'lr': 1.9461311290239757e-06, 'samples': 27670848, 'steps': 144118, 'loss/train': 0.9285066723823547} 08/31/2021 15:22:19 - INFO - __main__ - Step 144120: {'lr': 1.945470320495801e-06, 'samples': 27671040, 'steps': 144119, 'loss/train': 0.24915893375873566} 08/31/2021 15:22:20 - INFO - __main__ - Step 144121: {'lr': 1.944809623737137e-06, 'samples': 27671232, 'steps': 144120, 'loss/train': 1.0284827947616577} 08/31/2021 15:22:20 - INFO - __main__ - Step 144122: {'lr': 1.9441490387483442e-06, 'samples': 27671424, 'steps': 144121, 'loss/train': 0.751120924949646} 08/31/2021 15:22:20 - INFO - __main__ - Step 144123: {'lr': 1.9434885655296718e-06, 'samples': 27671616, 'steps': 144122, 'loss/train': 0.6512802839279175} 08/31/2021 15:22:21 - INFO - __main__ - Step 144124: {'lr': 1.9428282040814262e-06, 'samples': 27671808, 'steps': 144123, 'loss/train': 1.0616509914398193} 08/31/2021 15:22:22 - INFO - __main__ - Step 144125: {'lr': 1.9421679544039397e-06, 'samples': 27672000, 'steps': 144124, 'loss/train': 0.6698935627937317} 08/31/2021 15:22:23 - INFO - __main__ - Step 144126: {'lr': 1.941507816497462e-06, 'samples': 27672192, 'steps': 144125, 'loss/train': 1.045872688293457} 08/31/2021 15:22:23 - INFO - __main__ - Step 144127: {'lr': 1.940847790362327e-06, 'samples': 27672384, 'steps': 144126, 'loss/train': 1.1825506687164307} 08/31/2021 15:22:23 - INFO - __main__ - Step 144128: {'lr': 1.9401878759988113e-06, 'samples': 27672576, 'steps': 144127, 'loss/train': 0.4532921016216278} 08/31/2021 15:22:24 - INFO - __main__ - Step 144129: {'lr': 1.9395280734072207e-06, 'samples': 27672768, 'steps': 144128, 'loss/train': 1.1743439435958862} 08/31/2021 15:22:25 - INFO - __main__ - Step 144130: {'lr': 1.9388683825878604e-06, 'samples': 27672960, 'steps': 144129, 'loss/train': 1.3378769159317017} 08/31/2021 15:22:26 - INFO - __main__ - Step 144131: {'lr': 1.938208803541008e-06, 'samples': 27673152, 'steps': 144130, 'loss/train': 1.7330594062805176} 08/31/2021 15:22:26 - INFO - __main__ - Step 144132: {'lr': 1.9375493362669694e-06, 'samples': 27673344, 'steps': 144131, 'loss/train': 0.47968795895576477} 08/31/2021 15:22:26 - INFO - __main__ - Step 144133: {'lr': 1.936889980766049e-06, 'samples': 27673536, 'steps': 144132, 'loss/train': 1.1536366939544678} 08/31/2021 15:22:27 - INFO - __main__ - Step 144134: {'lr': 1.9362307370385525e-06, 'samples': 27673728, 'steps': 144133, 'loss/train': 1.412372350692749} 08/31/2021 15:22:28 - INFO - __main__ - Step 144135: {'lr': 1.9355716050847295e-06, 'samples': 27673920, 'steps': 144134, 'loss/train': 1.4482499361038208} 08/31/2021 15:22:29 - INFO - __main__ - Step 144136: {'lr': 1.934912584904941e-06, 'samples': 27674112, 'steps': 144135, 'loss/train': 0.8607556223869324} 08/31/2021 15:22:29 - INFO - __main__ - Step 144137: {'lr': 1.934253676499437e-06, 'samples': 27674304, 'steps': 144136, 'loss/train': 0.8535508513450623} 08/31/2021 15:22:29 - INFO - __main__ - Step 144138: {'lr': 1.933594879868522e-06, 'samples': 27674496, 'steps': 144137, 'loss/train': 0.4078623354434967} 08/31/2021 15:22:30 - INFO - __main__ - Step 144139: {'lr': 1.9329361950125025e-06, 'samples': 27674688, 'steps': 144138, 'loss/train': 0.8426548838615417} 08/31/2021 15:22:31 - INFO - __main__ - Step 144140: {'lr': 1.932277621931683e-06, 'samples': 27674880, 'steps': 144139, 'loss/train': 1.7055753469467163} 08/31/2021 15:22:32 - INFO - __main__ - Step 144141: {'lr': 1.931619160626341e-06, 'samples': 27675072, 'steps': 144140, 'loss/train': 1.2854870557785034} 08/31/2021 15:22:32 - INFO - __main__ - Step 144142: {'lr': 1.9309608110968104e-06, 'samples': 27675264, 'steps': 144141, 'loss/train': 1.3187817335128784} 08/31/2021 15:22:32 - INFO - __main__ - Step 144143: {'lr': 1.93030257334334e-06, 'samples': 27675456, 'steps': 144142, 'loss/train': 1.5011951923370361} 08/31/2021 15:22:33 - INFO - __main__ - Step 144144: {'lr': 1.9296444473662356e-06, 'samples': 27675648, 'steps': 144143, 'loss/train': 1.160898208618164} 08/31/2021 15:22:35 - INFO - __main__ - Step 144145: {'lr': 1.9289864331658303e-06, 'samples': 27675840, 'steps': 144144, 'loss/train': 1.4073017835617065} 08/31/2021 15:22:35 - INFO - __main__ - Step 144146: {'lr': 1.9283285307424013e-06, 'samples': 27676032, 'steps': 144145, 'loss/train': 1.320062279701233} 08/31/2021 15:22:36 - INFO - __main__ - Step 144147: {'lr': 1.9276707400962267e-06, 'samples': 27676224, 'steps': 144146, 'loss/train': 0.785269558429718} 08/31/2021 15:22:36 - INFO - __main__ - Step 144148: {'lr': 1.9270130612276115e-06, 'samples': 27676416, 'steps': 144147, 'loss/train': 0.5191885232925415} 08/31/2021 15:22:36 - INFO - __main__ - Step 144149: {'lr': 1.926355494136861e-06, 'samples': 27676608, 'steps': 144148, 'loss/train': 1.2720671892166138} 08/31/2021 15:22:37 - INFO - __main__ - Step 144150: {'lr': 1.9256980388242528e-06, 'samples': 27676800, 'steps': 144149, 'loss/train': 0.9370325803756714} 08/31/2021 15:22:38 - INFO - __main__ - Step 144151: {'lr': 1.92504069529012e-06, 'samples': 27676992, 'steps': 144150, 'loss/train': 1.527872085571289} 08/31/2021 15:22:39 - INFO - __main__ - Step 144152: {'lr': 1.9243834635347124e-06, 'samples': 27677184, 'steps': 144151, 'loss/train': 1.1838842630386353} 08/31/2021 15:22:39 - INFO - __main__ - Step 144153: {'lr': 1.923726343558363e-06, 'samples': 27677376, 'steps': 144152, 'loss/train': 0.895557701587677} 08/31/2021 15:22:39 - INFO - __main__ - Step 144154: {'lr': 1.9230693353613494e-06, 'samples': 27677568, 'steps': 144153, 'loss/train': 0.9510051608085632} 08/31/2021 15:22:40 - INFO - __main__ - Step 144155: {'lr': 1.9224124389439767e-06, 'samples': 27677760, 'steps': 144154, 'loss/train': 1.0696507692337036} 08/31/2021 15:22:41 - INFO - __main__ - Step 144156: {'lr': 1.9217556543065508e-06, 'samples': 27677952, 'steps': 144155, 'loss/train': 0.7852022051811218} 08/31/2021 15:22:42 - INFO - __main__ - Step 144157: {'lr': 1.9210989814493206e-06, 'samples': 27678144, 'steps': 144156, 'loss/train': 1.0818262100219727} 08/31/2021 15:22:42 - INFO - __main__ - Step 144158: {'lr': 1.920442420372648e-06, 'samples': 27678336, 'steps': 144157, 'loss/train': 0.9731062054634094} 08/31/2021 15:22:42 - INFO - __main__ - Step 144159: {'lr': 1.9197859710767817e-06, 'samples': 27678528, 'steps': 144158, 'loss/train': 0.27781376242637634} 08/31/2021 15:22:43 - INFO - __main__ - Step 144160: {'lr': 1.9191296335620277e-06, 'samples': 27678720, 'steps': 144159, 'loss/train': 0.1950768530368805} 08/31/2021 15:22:44 - INFO - __main__ - Step 144161: {'lr': 1.9184734078286914e-06, 'samples': 27678912, 'steps': 144160, 'loss/train': 1.2685298919677734} 08/31/2021 15:22:45 - INFO - __main__ - Step 144162: {'lr': 1.9178172938770777e-06, 'samples': 27679104, 'steps': 144161, 'loss/train': 0.20811395347118378} 08/31/2021 15:22:45 - INFO - __main__ - Step 144163: {'lr': 1.9171612917074368e-06, 'samples': 27679296, 'steps': 144162, 'loss/train': 0.7915980219841003} 08/31/2021 15:22:45 - INFO - __main__ - Step 144164: {'lr': 1.916505401320101e-06, 'samples': 27679488, 'steps': 144163, 'loss/train': 2.147878408432007} 08/31/2021 15:22:46 - INFO - __main__ - Step 144165: {'lr': 1.9158496227153767e-06, 'samples': 27679680, 'steps': 144164, 'loss/train': 0.6217755675315857} 08/31/2021 15:22:47 - INFO - __main__ - Step 144166: {'lr': 1.9151939558935407e-06, 'samples': 27679872, 'steps': 144165, 'loss/train': 0.9452087879180908} 08/31/2021 15:22:48 - INFO - __main__ - Step 144167: {'lr': 1.9145384008548706e-06, 'samples': 27680064, 'steps': 144166, 'loss/train': 0.8860426545143127} 08/31/2021 15:22:48 - INFO - __main__ - Step 144168: {'lr': 1.9138829575996997e-06, 'samples': 27680256, 'steps': 144167, 'loss/train': 1.1877789497375488} 08/31/2021 15:22:48 - INFO - __main__ - Step 144169: {'lr': 1.9132276261283054e-06, 'samples': 27680448, 'steps': 144168, 'loss/train': 0.9169272780418396} 08/31/2021 15:22:49 - INFO - __main__ - Step 144170: {'lr': 1.9125724064409655e-06, 'samples': 27680640, 'steps': 144169, 'loss/train': 0.7456784248352051} 08/31/2021 15:22:50 - INFO - __main__ - Step 144171: {'lr': 1.911917298538013e-06, 'samples': 27680832, 'steps': 144170, 'loss/train': 0.5785425901412964} 08/31/2021 15:22:51 - INFO - __main__ - Step 144172: {'lr': 1.9112623024196973e-06, 'samples': 27681024, 'steps': 144171, 'loss/train': 1.319954752922058} 08/31/2021 15:22:51 - INFO - __main__ - Step 144173: {'lr': 1.9106074180863796e-06, 'samples': 27681216, 'steps': 144172, 'loss/train': 0.7011103630065918} 08/31/2021 15:22:51 - INFO - __main__ - Step 144174: {'lr': 1.9099526455382822e-06, 'samples': 27681408, 'steps': 144173, 'loss/train': 1.3180948495864868} 08/31/2021 15:22:52 - INFO - __main__ - Step 144175: {'lr': 1.9092979847757373e-06, 'samples': 27681600, 'steps': 144174, 'loss/train': 0.492370069026947} 08/31/2021 15:22:53 - INFO - __main__ - Step 144176: {'lr': 1.9086434357990235e-06, 'samples': 27681792, 'steps': 144175, 'loss/train': 1.2037805318832397} 08/31/2021 15:22:54 - INFO - __main__ - Step 144177: {'lr': 1.9079889986084453e-06, 'samples': 27681984, 'steps': 144176, 'loss/train': 0.1483524739742279} 08/31/2021 15:22:54 - INFO - __main__ - Step 144178: {'lr': 1.9073346732043361e-06, 'samples': 27682176, 'steps': 144177, 'loss/train': 0.8147101402282715} 08/31/2021 15:22:55 - INFO - __main__ - Step 144179: {'lr': 1.906680459586918e-06, 'samples': 27682368, 'steps': 144178, 'loss/train': 0.5889177322387695} 08/31/2021 15:22:55 - INFO - __main__ - Step 144180: {'lr': 1.906026357756524e-06, 'samples': 27682560, 'steps': 144179, 'loss/train': 3.7289509773254395} 08/31/2021 15:22:57 - INFO - __main__ - Step 144181: {'lr': 1.9053723677134593e-06, 'samples': 27682752, 'steps': 144180, 'loss/train': 0.17589272558689117} 08/31/2021 15:22:57 - INFO - __main__ - Step 144182: {'lr': 1.9047184894580017e-06, 'samples': 27682944, 'steps': 144181, 'loss/train': 1.4511899948120117} 08/31/2021 15:22:58 - INFO - __main__ - Step 144183: {'lr': 1.9040647229904562e-06, 'samples': 27683136, 'steps': 144182, 'loss/train': 1.3111417293548584} 08/31/2021 15:22:58 - INFO - __main__ - Step 144184: {'lr': 1.9034110683111006e-06, 'samples': 27683328, 'steps': 144183, 'loss/train': 0.4104210436344147} 08/31/2021 15:22:58 - INFO - __main__ - Step 144185: {'lr': 1.9027575254202401e-06, 'samples': 27683520, 'steps': 144184, 'loss/train': 1.138095498085022} 08/31/2021 15:22:59 - INFO - __main__ - Step 144186: {'lr': 1.9021040943181521e-06, 'samples': 27683712, 'steps': 144185, 'loss/train': 1.9244279861450195} 08/31/2021 15:23:00 - INFO - __main__ - Step 144187: {'lr': 1.901450775005198e-06, 'samples': 27683904, 'steps': 144186, 'loss/train': 0.05161351338028908} 08/31/2021 15:23:01 - INFO - __main__ - Step 144188: {'lr': 1.9007975674815713e-06, 'samples': 27684096, 'steps': 144187, 'loss/train': 0.08652398735284805} 08/31/2021 15:23:01 - INFO - __main__ - Step 144189: {'lr': 1.9001444717476335e-06, 'samples': 27684288, 'steps': 144188, 'loss/train': 1.645440936088562} 08/31/2021 15:23:01 - INFO - __main__ - Step 144190: {'lr': 1.8994914878036618e-06, 'samples': 27684480, 'steps': 144189, 'loss/train': 1.0065990686416626} 08/31/2021 15:23:02 - INFO - __main__ - Step 144191: {'lr': 1.8988386156499616e-06, 'samples': 27684672, 'steps': 144190, 'loss/train': 1.9525610208511353} 08/31/2021 15:23:03 - INFO - __main__ - Step 144192: {'lr': 1.8981858552868104e-06, 'samples': 27684864, 'steps': 144191, 'loss/train': 0.8964541554450989} 08/31/2021 15:23:04 - INFO - __main__ - Step 144193: {'lr': 1.8975332067145134e-06, 'samples': 27685056, 'steps': 144192, 'loss/train': 1.536169409751892} 08/31/2021 15:23:04 - INFO - __main__ - Step 144194: {'lr': 1.8968806699333484e-06, 'samples': 27685248, 'steps': 144193, 'loss/train': 1.1478753089904785} 08/31/2021 15:23:04 - INFO - __main__ - Step 144195: {'lr': 1.8962282449436209e-06, 'samples': 27685440, 'steps': 144194, 'loss/train': 1.153307318687439} 08/31/2021 15:23:05 - INFO - __main__ - Step 144196: {'lr': 1.8955759317456079e-06, 'samples': 27685632, 'steps': 144195, 'loss/train': 1.0711851119995117} 08/31/2021 15:23:06 - INFO - __main__ - Step 144197: {'lr': 1.8949237303396428e-06, 'samples': 27685824, 'steps': 144196, 'loss/train': 1.1491199731826782} 08/31/2021 15:23:07 - INFO - __main__ - Step 144198: {'lr': 1.894271640726003e-06, 'samples': 27686016, 'steps': 144197, 'loss/train': 1.0555771589279175} 08/31/2021 15:23:07 - INFO - __main__ - Step 144199: {'lr': 1.8936196629049663e-06, 'samples': 27686208, 'steps': 144198, 'loss/train': 0.8439746499061584} 08/31/2021 15:23:07 - INFO - __main__ - Step 144200: {'lr': 1.8929677968768377e-06, 'samples': 27686400, 'steps': 144199, 'loss/train': 1.5108031034469604} 08/31/2021 15:23:08 - INFO - __main__ - Step 144201: {'lr': 1.892316042641923e-06, 'samples': 27686592, 'steps': 144200, 'loss/train': 0.3422452211380005} 08/31/2021 15:23:10 - INFO - __main__ - Step 144202: {'lr': 1.8916644002004712e-06, 'samples': 27686784, 'steps': 144201, 'loss/train': 1.313970923423767} 08/31/2021 15:23:10 - INFO - __main__ - Step 144203: {'lr': 1.8910128695528162e-06, 'samples': 27686976, 'steps': 144202, 'loss/train': 1.2908388376235962} 08/31/2021 15:23:11 - INFO - __main__ - Step 144204: {'lr': 1.8903614506992628e-06, 'samples': 27687168, 'steps': 144203, 'loss/train': 0.3342300355434418} 08/31/2021 15:23:11 - INFO - __main__ - Step 144205: {'lr': 1.889710143640061e-06, 'samples': 27687360, 'steps': 144204, 'loss/train': 0.8729282021522522} 08/31/2021 15:23:11 - INFO - __main__ - Step 144206: {'lr': 1.889058948375544e-06, 'samples': 27687552, 'steps': 144205, 'loss/train': 0.9382288455963135} 08/31/2021 15:23:12 - INFO - __main__ - Step 144207: {'lr': 1.888407864905961e-06, 'samples': 27687744, 'steps': 144206, 'loss/train': 1.3975884914398193} 08/31/2021 15:23:13 - INFO - __main__ - Step 144208: {'lr': 1.8877568932316736e-06, 'samples': 27687936, 'steps': 144207, 'loss/train': 0.8429046869277954} 08/31/2021 15:23:14 - INFO - __main__ - Step 144209: {'lr': 1.8871060333529032e-06, 'samples': 27688128, 'steps': 144208, 'loss/train': 1.4148287773132324} 08/31/2021 15:23:14 - INFO - __main__ - Step 144210: {'lr': 1.8864552852699835e-06, 'samples': 27688320, 'steps': 144209, 'loss/train': 1.5633097887039185} 08/31/2021 15:23:14 - INFO - __main__ - Step 144211: {'lr': 1.8858046489831915e-06, 'samples': 27688512, 'steps': 144210, 'loss/train': 0.8555722236633301} 08/31/2021 15:23:16 - INFO - __main__ - Step 144212: {'lr': 1.8851541244928328e-06, 'samples': 27688704, 'steps': 144211, 'loss/train': 1.4504716396331787} 08/31/2021 15:23:16 - INFO - __main__ - Step 144213: {'lr': 1.8845037117992126e-06, 'samples': 27688896, 'steps': 144212, 'loss/train': 1.227937936782837} 08/31/2021 15:23:17 - INFO - __main__ - Step 144214: {'lr': 1.8838534109025806e-06, 'samples': 27689088, 'steps': 144213, 'loss/train': 0.6646735668182373} 08/31/2021 15:23:17 - INFO - __main__ - Step 144215: {'lr': 1.88320322180327e-06, 'samples': 27689280, 'steps': 144214, 'loss/train': 1.0595462322235107} 08/31/2021 15:23:17 - INFO - __main__ - Step 144216: {'lr': 1.8825531445015588e-06, 'samples': 27689472, 'steps': 144215, 'loss/train': 5.60929536819458} 08/31/2021 15:23:18 - INFO - __main__ - Step 144217: {'lr': 1.8819031789977237e-06, 'samples': 27689664, 'steps': 144216, 'loss/train': 0.09554903209209442} 08/31/2021 15:23:19 - INFO - __main__ - Step 144218: {'lr': 1.8812533252920983e-06, 'samples': 27689856, 'steps': 144217, 'loss/train': 1.3885653018951416} 08/31/2021 15:23:20 - INFO - __main__ - Step 144219: {'lr': 1.8806035833849322e-06, 'samples': 27690048, 'steps': 144218, 'loss/train': 1.0013861656188965} 08/31/2021 15:23:20 - INFO - __main__ - Step 144220: {'lr': 1.8799539532765585e-06, 'samples': 27690240, 'steps': 144219, 'loss/train': 0.9262158274650574} 08/31/2021 15:23:20 - INFO - __main__ - Step 144221: {'lr': 1.8793044349672273e-06, 'samples': 27690432, 'steps': 144220, 'loss/train': 1.154605507850647} 08/31/2021 15:23:21 - INFO - __main__ - Step 144222: {'lr': 1.8786550284572712e-06, 'samples': 27690624, 'steps': 144221, 'loss/train': 1.8943272829055786} 08/31/2021 15:23:23 - INFO - __main__ - Step 144223: {'lr': 1.878005733746968e-06, 'samples': 27690816, 'steps': 144222, 'loss/train': 0.9722496867179871} 08/31/2021 15:23:23 - INFO - __main__ - Step 144224: {'lr': 1.8773565508365953e-06, 'samples': 27691008, 'steps': 144223, 'loss/train': 0.943861722946167} 08/31/2021 15:23:23 - INFO - __main__ - Step 144225: {'lr': 1.8767074797264306e-06, 'samples': 27691200, 'steps': 144224, 'loss/train': 0.18699300289154053} 08/31/2021 15:23:24 - INFO - __main__ - Step 144226: {'lr': 1.8760585204168345e-06, 'samples': 27691392, 'steps': 144225, 'loss/train': 0.4019748270511627} 08/31/2021 15:23:24 - INFO - __main__ - Step 144227: {'lr': 1.8754096729080295e-06, 'samples': 27691584, 'steps': 144226, 'loss/train': 0.34431254863739014} 08/31/2021 15:23:26 - INFO - __main__ - Step 144228: {'lr': 1.8747609372003482e-06, 'samples': 27691776, 'steps': 144227, 'loss/train': 0.5347645282745361} 08/31/2021 15:23:26 - INFO - __main__ - Step 144229: {'lr': 1.8741123132940685e-06, 'samples': 27691968, 'steps': 144228, 'loss/train': 1.193436861038208} 08/31/2021 15:23:26 - INFO - __main__ - Step 144230: {'lr': 1.8734638011894955e-06, 'samples': 27692160, 'steps': 144229, 'loss/train': 1.2939096689224243} 08/31/2021 15:23:27 - INFO - __main__ - Step 144231: {'lr': 1.8728154008868791e-06, 'samples': 27692352, 'steps': 144230, 'loss/train': 0.11459440737962723} 08/31/2021 15:23:27 - INFO - __main__ - Step 144232: {'lr': 1.8721671123865803e-06, 'samples': 27692544, 'steps': 144231, 'loss/train': 0.44391757249832153} 08/31/2021 15:23:28 - INFO - __main__ - Step 144233: {'lr': 1.8715189356888207e-06, 'samples': 27692736, 'steps': 144232, 'loss/train': 0.7088828086853027} 08/31/2021 15:23:29 - INFO - __main__ - Step 144234: {'lr': 1.8708708707939614e-06, 'samples': 27692928, 'steps': 144233, 'loss/train': 1.406536340713501} 08/31/2021 15:23:29 - INFO - __main__ - Step 144235: {'lr': 1.8702229177022523e-06, 'samples': 27693120, 'steps': 144234, 'loss/train': 1.2390817403793335} 08/31/2021 15:23:30 - INFO - __main__ - Step 144236: {'lr': 1.8695750764139707e-06, 'samples': 27693312, 'steps': 144235, 'loss/train': 0.813016414642334} 08/31/2021 15:23:30 - INFO - __main__ - Step 144237: {'lr': 1.8689273469294498e-06, 'samples': 27693504, 'steps': 144236, 'loss/train': 0.08709732443094254} 08/31/2021 15:23:30 - INFO - __main__ - Step 144238: {'lr': 1.8682797292489396e-06, 'samples': 27693696, 'steps': 144237, 'loss/train': 0.5225814580917358} 08/31/2021 15:23:32 - INFO - __main__ - Step 144239: {'lr': 1.8676322233727727e-06, 'samples': 27693888, 'steps': 144238, 'loss/train': 1.0916883945465088} 08/31/2021 15:23:32 - INFO - __main__ - Step 144240: {'lr': 1.8669848293011992e-06, 'samples': 27694080, 'steps': 144239, 'loss/train': 0.7991217374801636} 08/31/2021 15:23:33 - INFO - __main__ - Step 144241: {'lr': 1.8663375470345523e-06, 'samples': 27694272, 'steps': 144240, 'loss/train': 1.252778172492981} 08/31/2021 15:23:33 - INFO - __main__ - Step 144242: {'lr': 1.8656903765731093e-06, 'samples': 27694464, 'steps': 144241, 'loss/train': 1.109847903251648} 08/31/2021 15:23:33 - INFO - __main__ - Step 144243: {'lr': 1.8650433179171478e-06, 'samples': 27694656, 'steps': 144242, 'loss/train': 1.741288423538208} 08/31/2021 15:23:35 - INFO - __main__ - Step 144244: {'lr': 1.8643963710669732e-06, 'samples': 27694848, 'steps': 144243, 'loss/train': 1.576958179473877} 08/31/2021 15:23:36 - INFO - __main__ - Step 144245: {'lr': 1.8637495360228906e-06, 'samples': 27695040, 'steps': 144244, 'loss/train': 1.2814733982086182} 08/31/2021 15:23:36 - INFO - __main__ - Step 144246: {'lr': 1.8631028127851502e-06, 'samples': 27695232, 'steps': 144245, 'loss/train': 0.9123684167861938} 08/31/2021 15:23:36 - INFO - __main__ - Step 144247: {'lr': 1.8624562013540568e-06, 'samples': 27695424, 'steps': 144246, 'loss/train': 1.2174839973449707} 08/31/2021 15:23:37 - INFO - __main__ - Step 144248: {'lr': 1.8618097017299163e-06, 'samples': 27695616, 'steps': 144247, 'loss/train': 0.2594377398490906} 08/31/2021 15:23:38 - INFO - __main__ - Step 144249: {'lr': 1.8611633139130334e-06, 'samples': 27695808, 'steps': 144248, 'loss/train': 0.9471542835235596} 08/31/2021 15:23:39 - INFO - __main__ - Step 144250: {'lr': 1.8605170379036585e-06, 'samples': 27696000, 'steps': 144249, 'loss/train': 1.262650728225708} 08/31/2021 15:23:39 - INFO - __main__ - Step 144251: {'lr': 1.8598708737021241e-06, 'samples': 27696192, 'steps': 144250, 'loss/train': 0.2815028429031372} 08/31/2021 15:23:39 - INFO - __main__ - Step 144252: {'lr': 1.8592248213087082e-06, 'samples': 27696384, 'steps': 144251, 'loss/train': 1.641716718673706} 08/31/2021 15:23:40 - INFO - __main__ - Step 144253: {'lr': 1.8585788807236881e-06, 'samples': 27696576, 'steps': 144252, 'loss/train': 1.2452856302261353} 08/31/2021 15:23:40 - INFO - __main__ - Step 144254: {'lr': 1.8579330519473415e-06, 'samples': 27696768, 'steps': 144253, 'loss/train': 1.628233551979065} 08/31/2021 15:23:42 - INFO - __main__ - Step 144255: {'lr': 1.8572873349800012e-06, 'samples': 27696960, 'steps': 144254, 'loss/train': 0.9378513097763062} 08/31/2021 15:23:43 - INFO - __main__ - Step 144256: {'lr': 1.8566417298219451e-06, 'samples': 27697152, 'steps': 144255, 'loss/train': 1.597509503364563} 08/31/2021 15:23:43 - INFO - __main__ - Step 144257: {'lr': 1.8559962364734505e-06, 'samples': 27697344, 'steps': 144256, 'loss/train': 0.21938461065292358} 08/31/2021 15:23:43 - INFO - __main__ - Step 144258: {'lr': 1.8553508549348231e-06, 'samples': 27697536, 'steps': 144257, 'loss/train': 1.3942900896072388} 08/31/2021 15:23:44 - INFO - __main__ - Step 144259: {'lr': 1.85470558520634e-06, 'samples': 27697728, 'steps': 144258, 'loss/train': 0.667708694934845} 08/31/2021 15:23:45 - INFO - __main__ - Step 144260: {'lr': 1.8540604272882789e-06, 'samples': 27697920, 'steps': 144259, 'loss/train': 1.099261999130249} 08/31/2021 15:23:46 - INFO - __main__ - Step 144261: {'lr': 1.853415381180973e-06, 'samples': 27698112, 'steps': 144260, 'loss/train': 0.1870255172252655} 08/31/2021 15:23:46 - INFO - __main__ - Step 144262: {'lr': 1.8527704468846717e-06, 'samples': 27698304, 'steps': 144261, 'loss/train': 0.03478666767477989} 08/31/2021 15:23:47 - INFO - __main__ - Step 144263: {'lr': 1.852125624399681e-06, 'samples': 27698496, 'steps': 144262, 'loss/train': 0.5139164924621582} 08/31/2021 15:23:47 - INFO - __main__ - Step 144264: {'lr': 1.8514809137263056e-06, 'samples': 27698688, 'steps': 144263, 'loss/train': 0.9478005170822144} 08/31/2021 15:23:48 - INFO - __main__ - Step 144265: {'lr': 1.8508363148648233e-06, 'samples': 27698880, 'steps': 144264, 'loss/train': 1.2566370964050293} 08/31/2021 15:23:49 - INFO - __main__ - Step 144266: {'lr': 1.8501918278155394e-06, 'samples': 27699072, 'steps': 144265, 'loss/train': 0.8114171624183655} 08/31/2021 15:23:49 - INFO - __main__ - Step 144267: {'lr': 1.8495474525787037e-06, 'samples': 27699264, 'steps': 144266, 'loss/train': 0.9566011428833008} 08/31/2021 15:23:49 - INFO - __main__ - Step 144268: {'lr': 1.8489031891546492e-06, 'samples': 27699456, 'steps': 144267, 'loss/train': 0.7211319208145142} 08/31/2021 15:23:50 - INFO - __main__ - Step 144269: {'lr': 1.8482590375436536e-06, 'samples': 27699648, 'steps': 144268, 'loss/train': 0.9750387668609619} 08/31/2021 15:23:52 - INFO - __main__ - Step 144270: {'lr': 1.8476149977459944e-06, 'samples': 27699840, 'steps': 144269, 'loss/train': 1.1168431043624878} 08/31/2021 15:23:52 - INFO - __main__ - Step 144271: {'lr': 1.8469710697619492e-06, 'samples': 27700032, 'steps': 144270, 'loss/train': 0.8861424922943115} 08/31/2021 15:23:53 - INFO - __main__ - Step 144272: {'lr': 1.8463272535918508e-06, 'samples': 27700224, 'steps': 144271, 'loss/train': 0.0289422906935215} 08/31/2021 15:23:53 - INFO - __main__ - Step 144273: {'lr': 1.845683549235977e-06, 'samples': 27700416, 'steps': 144272, 'loss/train': 1.302763819694519} 08/31/2021 15:23:53 - INFO - __main__ - Step 144274: {'lr': 1.8450399566946051e-06, 'samples': 27700608, 'steps': 144273, 'loss/train': 1.352859377861023} 08/31/2021 15:23:55 - INFO - __main__ - Step 144275: {'lr': 1.8443964759680133e-06, 'samples': 27700800, 'steps': 144274, 'loss/train': 1.2754727602005005} 08/31/2021 15:23:55 - INFO - __main__ - Step 144276: {'lr': 1.843753107056506e-06, 'samples': 27700992, 'steps': 144275, 'loss/train': 1.766859769821167} 08/31/2021 15:23:56 - INFO - __main__ - Step 144277: {'lr': 1.8431098499603893e-06, 'samples': 27701184, 'steps': 144276, 'loss/train': 1.3976186513900757} 08/31/2021 15:23:56 - INFO - __main__ - Step 144278: {'lr': 1.8424667046799403e-06, 'samples': 27701376, 'steps': 144277, 'loss/train': 1.0998533964157104} 08/31/2021 15:23:56 - INFO - __main__ - Step 144279: {'lr': 1.8418236712154368e-06, 'samples': 27701568, 'steps': 144278, 'loss/train': 0.774133026599884} 08/31/2021 15:23:57 - INFO - __main__ - Step 144280: {'lr': 1.841180749567184e-06, 'samples': 27701760, 'steps': 144279, 'loss/train': 0.6601001024246216} 08/31/2021 15:23:58 - INFO - __main__ - Step 144281: {'lr': 1.8405379397354593e-06, 'samples': 27701952, 'steps': 144280, 'loss/train': 1.6664282083511353} 08/31/2021 15:23:59 - INFO - __main__ - Step 144282: {'lr': 1.8398952417205683e-06, 'samples': 27702144, 'steps': 144281, 'loss/train': 1.4565722942352295} 08/31/2021 15:23:59 - INFO - __main__ - Step 144283: {'lr': 1.8392526555227883e-06, 'samples': 27702336, 'steps': 144282, 'loss/train': 0.09138982743024826} 08/31/2021 15:23:59 - INFO - __main__ - Step 144284: {'lr': 1.8386101811423973e-06, 'samples': 27702528, 'steps': 144283, 'loss/train': 0.862453818321228} 08/31/2021 15:24:00 - INFO - __main__ - Step 144285: {'lr': 1.8379678185797277e-06, 'samples': 27702720, 'steps': 144284, 'loss/train': 1.4247534275054932} 08/31/2021 15:24:02 - INFO - __main__ - Step 144286: {'lr': 1.837325567835002e-06, 'samples': 27702912, 'steps': 144285, 'loss/train': 0.43095192313194275} 08/31/2021 15:24:02 - INFO - __main__ - Step 144287: {'lr': 1.836683428908581e-06, 'samples': 27703104, 'steps': 144286, 'loss/train': 0.7950143814086914} 08/31/2021 15:24:03 - INFO - __main__ - Step 144288: {'lr': 1.8360414018007142e-06, 'samples': 27703296, 'steps': 144287, 'loss/train': 1.35319185256958} 08/31/2021 15:24:03 - INFO - __main__ - Step 144289: {'lr': 1.8353994865116796e-06, 'samples': 27703488, 'steps': 144288, 'loss/train': 0.8310142159461975} 08/31/2021 15:24:03 - INFO - __main__ - Step 144290: {'lr': 1.83475768304181e-06, 'samples': 27703680, 'steps': 144289, 'loss/train': 1.3115756511688232} 08/31/2021 15:24:04 - INFO - __main__ - Step 144291: {'lr': 1.8341159913913553e-06, 'samples': 27703872, 'steps': 144290, 'loss/train': 1.5534523725509644} 08/31/2021 15:24:05 - INFO - __main__ - Step 144292: {'lr': 1.8334744115606205e-06, 'samples': 27704064, 'steps': 144291, 'loss/train': 0.795932948589325} 08/31/2021 15:24:06 - INFO - __main__ - Step 144293: {'lr': 1.8328329435498836e-06, 'samples': 27704256, 'steps': 144292, 'loss/train': 0.5799680352210999} 08/31/2021 15:24:06 - INFO - __main__ - Step 144294: {'lr': 1.8321915873594497e-06, 'samples': 27704448, 'steps': 144293, 'loss/train': 1.2266547679901123} 08/31/2021 15:24:06 - INFO - __main__ - Step 144295: {'lr': 1.831550342989624e-06, 'samples': 27704640, 'steps': 144294, 'loss/train': 1.002794623374939} 08/31/2021 15:24:07 - INFO - __main__ - Step 144296: {'lr': 1.830909210440629e-06, 'samples': 27704832, 'steps': 144295, 'loss/train': 0.9727395176887512} 08/31/2021 15:24:08 - INFO - __main__ - Step 144297: {'lr': 1.8302681897128248e-06, 'samples': 27705024, 'steps': 144296, 'loss/train': 1.5093077421188354} 08/31/2021 15:24:09 - INFO - __main__ - Step 144298: {'lr': 1.8296272808064619e-06, 'samples': 27705216, 'steps': 144297, 'loss/train': 0.6070737242698669} 08/31/2021 15:24:09 - INFO - __main__ - Step 144299: {'lr': 1.828986483721845e-06, 'samples': 27705408, 'steps': 144298, 'loss/train': 0.9692922830581665} 08/31/2021 15:24:09 - INFO - __main__ - Step 144300: {'lr': 1.8283457984592522e-06, 'samples': 27705600, 'steps': 144299, 'loss/train': 1.034731388092041} 08/31/2021 15:24:10 - INFO - __main__ - Step 144301: {'lr': 1.8277052250189885e-06, 'samples': 27705792, 'steps': 144300, 'loss/train': 0.29878559708595276} 08/31/2021 15:24:11 - INFO - __main__ - Step 144302: {'lr': 1.8270647634013316e-06, 'samples': 27705984, 'steps': 144301, 'loss/train': 1.0050324201583862} 08/31/2021 15:24:12 - INFO - __main__ - Step 144303: {'lr': 1.826424413606559e-06, 'samples': 27706176, 'steps': 144302, 'loss/train': 0.7178522944450378} 08/31/2021 15:24:12 - INFO - __main__ - Step 144304: {'lr': 1.8257841756349757e-06, 'samples': 27706368, 'steps': 144303, 'loss/train': 1.153124213218689} 08/31/2021 15:24:12 - INFO - __main__ - Step 144305: {'lr': 1.8251440494868598e-06, 'samples': 27706560, 'steps': 144304, 'loss/train': 1.1876866817474365} 08/31/2021 15:24:13 - INFO - __main__ - Step 144306: {'lr': 1.8245040351624886e-06, 'samples': 27706752, 'steps': 144305, 'loss/train': 0.8909226655960083} 08/31/2021 15:24:15 - INFO - __main__ - Step 144307: {'lr': 1.8238641326621953e-06, 'samples': 27706944, 'steps': 144306, 'loss/train': 0.8912987112998962} 08/31/2021 15:24:16 - INFO - __main__ - Step 144308: {'lr': 1.8232243419862293e-06, 'samples': 27707136, 'steps': 144307, 'loss/train': 0.8319383263587952} 08/31/2021 15:24:16 - INFO - __main__ - Step 144309: {'lr': 1.8225846631348964e-06, 'samples': 27707328, 'steps': 144308, 'loss/train': 0.027737682685256004} 08/31/2021 15:24:16 - INFO - __main__ - Step 144310: {'lr': 1.8219450961084738e-06, 'samples': 27707520, 'steps': 144309, 'loss/train': 1.2897709608078003} 08/31/2021 15:24:17 - INFO - __main__ - Step 144311: {'lr': 1.8213056409072394e-06, 'samples': 27707712, 'steps': 144310, 'loss/train': 0.4515572190284729} 08/31/2021 15:24:18 - INFO - __main__ - Step 144312: {'lr': 1.820666297531498e-06, 'samples': 27707904, 'steps': 144311, 'loss/train': 1.2833523750305176} 08/31/2021 15:24:18 - INFO - __main__ - Step 144313: {'lr': 1.8200270659815555e-06, 'samples': 27708096, 'steps': 144312, 'loss/train': 1.4026226997375488} 08/31/2021 15:24:19 - INFO - __main__ - Step 144314: {'lr': 1.8193879462576613e-06, 'samples': 27708288, 'steps': 144313, 'loss/train': 1.2720980644226074} 08/31/2021 15:24:19 - INFO - __main__ - Step 144315: {'lr': 1.8187489383601208e-06, 'samples': 27708480, 'steps': 144314, 'loss/train': 0.6023968458175659} 08/31/2021 15:24:20 - INFO - __main__ - Step 144316: {'lr': 1.8181100422892116e-06, 'samples': 27708672, 'steps': 144315, 'loss/train': 1.0128791332244873} 08/31/2021 15:24:22 - INFO - __main__ - Step 144317: {'lr': 1.817471258045239e-06, 'samples': 27708864, 'steps': 144316, 'loss/train': 0.872949481010437} 08/31/2021 15:24:22 - INFO - __main__ - Step 144318: {'lr': 1.8168325856285085e-06, 'samples': 27709056, 'steps': 144317, 'loss/train': 1.1605591773986816} 08/31/2021 15:24:23 - INFO - __main__ - Step 144319: {'lr': 1.8161940250392694e-06, 'samples': 27709248, 'steps': 144318, 'loss/train': 1.3095179796218872} 08/31/2021 15:24:23 - INFO - __main__ - Step 144320: {'lr': 1.8155555762777997e-06, 'samples': 27709440, 'steps': 144319, 'loss/train': 1.1822435855865479} 08/31/2021 15:24:23 - INFO - __main__ - Step 144321: {'lr': 1.81491723934446e-06, 'samples': 27709632, 'steps': 144320, 'loss/train': 1.303063154220581} 08/31/2021 15:24:24 - INFO - __main__ - Step 144322: {'lr': 1.814279014239445e-06, 'samples': 27709824, 'steps': 144321, 'loss/train': 1.2808618545532227} 08/31/2021 15:24:25 - INFO - __main__ - Step 144323: {'lr': 1.813640900963115e-06, 'samples': 27710016, 'steps': 144322, 'loss/train': 0.0987105518579483} 08/31/2021 15:24:26 - INFO - __main__ - Step 144324: {'lr': 1.81300289951572e-06, 'samples': 27710208, 'steps': 144323, 'loss/train': 0.7103400230407715} 08/31/2021 15:24:26 - INFO - __main__ - Step 144325: {'lr': 1.8123650098975375e-06, 'samples': 27710400, 'steps': 144324, 'loss/train': 1.2865101099014282} 08/31/2021 15:24:26 - INFO - __main__ - Step 144326: {'lr': 1.811727232108873e-06, 'samples': 27710592, 'steps': 144325, 'loss/train': 1.1878023147583008} 08/31/2021 15:24:27 - INFO - __main__ - Step 144327: {'lr': 1.8110895661500315e-06, 'samples': 27710784, 'steps': 144326, 'loss/train': 0.9886154532432556} 08/31/2021 15:24:28 - INFO - __main__ - Step 144328: {'lr': 1.8104520120212909e-06, 'samples': 27710976, 'steps': 144327, 'loss/train': 1.0164321660995483} 08/31/2021 15:24:29 - INFO - __main__ - Step 144329: {'lr': 1.8098145697229285e-06, 'samples': 27711168, 'steps': 144328, 'loss/train': 1.2903356552124023} 08/31/2021 15:24:29 - INFO - __main__ - Step 144330: {'lr': 1.809177239255222e-06, 'samples': 27711360, 'steps': 144329, 'loss/train': 1.251516580581665} 08/31/2021 15:24:29 - INFO - __main__ - Step 144331: {'lr': 1.8085400206184766e-06, 'samples': 27711552, 'steps': 144330, 'loss/train': 1.646662712097168} 08/31/2021 15:24:30 - INFO - __main__ - Step 144332: {'lr': 1.80790291381297e-06, 'samples': 27711744, 'steps': 144331, 'loss/train': 1.0735622644424438} 08/31/2021 15:24:31 - INFO - __main__ - Step 144333: {'lr': 1.8072659188389794e-06, 'samples': 27711936, 'steps': 144332, 'loss/train': 0.5697431564331055} 08/31/2021 15:24:32 - INFO - __main__ - Step 144334: {'lr': 1.8066290356968108e-06, 'samples': 27712128, 'steps': 144333, 'loss/train': 0.8992409706115723} 08/31/2021 15:24:32 - INFO - __main__ - Step 144335: {'lr': 1.8059922643867688e-06, 'samples': 27712320, 'steps': 144334, 'loss/train': 0.6689189076423645} 08/31/2021 15:24:32 - INFO - __main__ - Step 144336: {'lr': 1.8053556049091035e-06, 'samples': 27712512, 'steps': 144335, 'loss/train': 0.8955196142196655} 08/31/2021 15:24:33 - INFO - __main__ - Step 144337: {'lr': 1.8047190572641204e-06, 'samples': 27712704, 'steps': 144336, 'loss/train': 0.7593361139297485} 08/31/2021 15:24:34 - INFO - __main__ - Step 144338: {'lr': 1.8040826214520966e-06, 'samples': 27712896, 'steps': 144337, 'loss/train': 1.4068489074707031} 08/31/2021 15:24:35 - INFO - __main__ - Step 144339: {'lr': 1.80344629747331e-06, 'samples': 27713088, 'steps': 144338, 'loss/train': 0.9028355479240417} 08/31/2021 15:24:35 - INFO - __main__ - Step 144340: {'lr': 1.802810085328066e-06, 'samples': 27713280, 'steps': 144339, 'loss/train': 0.8134669661521912} 08/31/2021 15:24:35 - INFO - __main__ - Step 144341: {'lr': 1.8021739850166697e-06, 'samples': 27713472, 'steps': 144340, 'loss/train': 1.0764907598495483} 08/31/2021 15:24:36 - INFO - __main__ - Step 144342: {'lr': 1.801537996539343e-06, 'samples': 27713664, 'steps': 144341, 'loss/train': 1.245850682258606} 08/31/2021 15:24:38 - INFO - __main__ - Step 144343: {'lr': 1.800902119896447e-06, 'samples': 27713856, 'steps': 144342, 'loss/train': 1.0390251874923706} 08/31/2021 15:24:39 - INFO - __main__ - Step 144344: {'lr': 1.8002663550882036e-06, 'samples': 27714048, 'steps': 144343, 'loss/train': 1.2631686925888062} 08/31/2021 15:24:39 - INFO - __main__ - Step 144345: {'lr': 1.7996307021149738e-06, 'samples': 27714240, 'steps': 144344, 'loss/train': 1.2841533422470093} 08/31/2021 15:24:39 - INFO - __main__ - Step 144346: {'lr': 1.7989951609769518e-06, 'samples': 27714432, 'steps': 144345, 'loss/train': 1.246880054473877} 08/31/2021 15:24:40 - INFO - __main__ - Step 144347: {'lr': 1.7983597316744982e-06, 'samples': 27714624, 'steps': 144346, 'loss/train': 0.7927084565162659} 08/31/2021 15:24:40 - INFO - __main__ - Step 144348: {'lr': 1.7977244142078907e-06, 'samples': 27714816, 'steps': 144347, 'loss/train': 1.0204917192459106} 08/31/2021 15:24:40 - INFO - __main__ - Step 144349: {'lr': 1.7970892085773793e-06, 'samples': 27715008, 'steps': 144348, 'loss/train': 1.3192245960235596} 08/31/2021 15:24:42 - INFO - __main__ - Step 144350: {'lr': 1.7964541147832692e-06, 'samples': 27715200, 'steps': 144349, 'loss/train': 1.312880277633667} 08/31/2021 15:24:42 - INFO - __main__ - Step 144351: {'lr': 1.7958191328258656e-06, 'samples': 27715392, 'steps': 144350, 'loss/train': 0.9328517317771912} 08/31/2021 15:24:43 - INFO - __main__ - Step 144352: {'lr': 1.7951842627053905e-06, 'samples': 27715584, 'steps': 144351, 'loss/train': 1.4396276473999023} 08/31/2021 15:24:43 - INFO - __main__ - Step 144353: {'lr': 1.7945495044222048e-06, 'samples': 27715776, 'steps': 144352, 'loss/train': 0.9113434553146362} 08/31/2021 15:24:43 - INFO - __main__ - Step 144354: {'lr': 1.7939148579765863e-06, 'samples': 27715968, 'steps': 144353, 'loss/train': 1.1795954704284668} 08/31/2021 15:24:45 - INFO - __main__ - Step 144355: {'lr': 1.7932803233687568e-06, 'samples': 27716160, 'steps': 144354, 'loss/train': 1.0825129747390747} 08/31/2021 15:24:45 - INFO - __main__ - Step 144356: {'lr': 1.792645900599077e-06, 'samples': 27716352, 'steps': 144355, 'loss/train': 0.9776493906974792} 08/31/2021 15:24:46 - INFO - __main__ - Step 144357: {'lr': 1.792011589667797e-06, 'samples': 27716544, 'steps': 144356, 'loss/train': 1.0173155069351196} 08/31/2021 15:24:46 - INFO - __main__ - Step 144358: {'lr': 1.791377390575194e-06, 'samples': 27716736, 'steps': 144357, 'loss/train': 0.6597546935081482} 08/31/2021 15:24:46 - INFO - __main__ - Step 144359: {'lr': 1.7907433033215736e-06, 'samples': 27716928, 'steps': 144358, 'loss/train': 3.066621780395508} 08/31/2021 15:24:48 - INFO - __main__ - Step 144360: {'lr': 1.7901093279071857e-06, 'samples': 27717120, 'steps': 144359, 'loss/train': 1.1398382186889648} 08/31/2021 15:24:48 - INFO - __main__ - Step 144361: {'lr': 1.7894754643323907e-06, 'samples': 27717312, 'steps': 144360, 'loss/train': 0.8076197504997253} 08/31/2021 15:24:49 - INFO - __main__ - Step 144362: {'lr': 1.7888417125974111e-06, 'samples': 27717504, 'steps': 144361, 'loss/train': 0.8161877393722534} 08/31/2021 15:24:49 - INFO - __main__ - Step 144363: {'lr': 1.7882080727025517e-06, 'samples': 27717696, 'steps': 144362, 'loss/train': 0.6952217221260071} 08/31/2021 15:24:49 - INFO - __main__ - Step 144364: {'lr': 1.7875745446480906e-06, 'samples': 27717888, 'steps': 144363, 'loss/train': 1.1322073936462402} 08/31/2021 15:24:52 - INFO - __main__ - Step 144365: {'lr': 1.786941128434305e-06, 'samples': 27718080, 'steps': 144364, 'loss/train': 0.9246231317520142} 08/31/2021 15:24:52 - INFO - __main__ - Step 144366: {'lr': 1.7863078240615005e-06, 'samples': 27718272, 'steps': 144365, 'loss/train': 0.3872286379337311} 08/31/2021 15:24:53 - INFO - __main__ - Step 144367: {'lr': 1.7856746315299543e-06, 'samples': 27718464, 'steps': 144366, 'loss/train': 1.0703681707382202} 08/31/2021 15:24:53 - INFO - __main__ - Step 144368: {'lr': 1.785041550839972e-06, 'samples': 27718656, 'steps': 144367, 'loss/train': 0.718532919883728} 08/31/2021 15:24:53 - INFO - __main__ - Step 144369: {'lr': 1.7844085819918033e-06, 'samples': 27718848, 'steps': 144368, 'loss/train': 0.11052300035953522} 08/31/2021 15:24:55 - INFO - __main__ - Step 144370: {'lr': 1.7837757249857534e-06, 'samples': 27719040, 'steps': 144369, 'loss/train': 1.4333784580230713} 08/31/2021 15:24:56 - INFO - __main__ - Step 144371: {'lr': 1.7831429798221e-06, 'samples': 27719232, 'steps': 144370, 'loss/train': 1.0887223482131958} 08/31/2021 15:24:56 - INFO - __main__ - Step 144372: {'lr': 1.7825103465011482e-06, 'samples': 27719424, 'steps': 144371, 'loss/train': 1.4351096153259277} 08/31/2021 15:24:56 - INFO - __main__ - Step 144373: {'lr': 1.7818778250231483e-06, 'samples': 27719616, 'steps': 144372, 'loss/train': 0.7018144726753235} 08/31/2021 15:24:57 - INFO - __main__ - Step 144374: {'lr': 1.781245415388405e-06, 'samples': 27719808, 'steps': 144373, 'loss/train': 0.9627606272697449} 08/31/2021 15:24:57 - INFO - __main__ - Step 144375: {'lr': 1.780613117597224e-06, 'samples': 27720000, 'steps': 144374, 'loss/train': 1.0637545585632324} 08/31/2021 15:24:59 - INFO - __main__ - Step 144376: {'lr': 1.779980931649855e-06, 'samples': 27720192, 'steps': 144375, 'loss/train': 1.7076879739761353} 08/31/2021 15:24:59 - INFO - __main__ - Step 144377: {'lr': 1.7793488575466032e-06, 'samples': 27720384, 'steps': 144376, 'loss/train': 1.3311553001403809} 08/31/2021 15:25:00 - INFO - __main__ - Step 144378: {'lr': 1.7787168952877187e-06, 'samples': 27720576, 'steps': 144377, 'loss/train': 0.26233476400375366} 08/31/2021 15:25:00 - INFO - __main__ - Step 144379: {'lr': 1.7780850448735342e-06, 'samples': 27720768, 'steps': 144378, 'loss/train': 0.53152996301651} 08/31/2021 15:25:00 - INFO - __main__ - Step 144380: {'lr': 1.7774533063043274e-06, 'samples': 27720960, 'steps': 144379, 'loss/train': 0.8304467797279358} 08/31/2021 15:25:03 - INFO - __main__ - Step 144381: {'lr': 1.7768216795803483e-06, 'samples': 27721152, 'steps': 144380, 'loss/train': 1.3563750982284546} 08/31/2021 15:25:03 - INFO - __main__ - Step 144382: {'lr': 1.7761901647019018e-06, 'samples': 27721344, 'steps': 144381, 'loss/train': 0.9935734868049622} 08/31/2021 15:25:03 - INFO - __main__ - Step 144383: {'lr': 1.7755587616692937e-06, 'samples': 27721536, 'steps': 144382, 'loss/train': 1.1279747486114502} 08/31/2021 15:25:04 - INFO - __main__ - Step 144384: {'lr': 1.7749274704827733e-06, 'samples': 27721728, 'steps': 144383, 'loss/train': 1.739132285118103} 08/31/2021 15:25:04 - INFO - __main__ - Step 144385: {'lr': 1.7742962911426464e-06, 'samples': 27721920, 'steps': 144384, 'loss/train': 0.034201301634311676} 08/31/2021 15:25:05 - INFO - __main__ - Step 144386: {'lr': 1.7736652236491625e-06, 'samples': 27722112, 'steps': 144385, 'loss/train': 0.09436209499835968} 08/31/2021 15:25:06 - INFO - __main__ - Step 144387: {'lr': 1.7730342680026824e-06, 'samples': 27722304, 'steps': 144386, 'loss/train': 1.1847853660583496} 08/31/2021 15:25:06 - INFO - __main__ - Step 144388: {'lr': 1.7724034242034282e-06, 'samples': 27722496, 'steps': 144387, 'loss/train': 1.1426684856414795} 08/31/2021 15:25:07 - INFO - __main__ - Step 144389: {'lr': 1.7717726922516774e-06, 'samples': 27722688, 'steps': 144388, 'loss/train': 0.7977039217948914} 08/31/2021 15:25:07 - INFO - __main__ - Step 144390: {'lr': 1.7711420721477634e-06, 'samples': 27722880, 'steps': 144389, 'loss/train': 1.1699020862579346} 08/31/2021 15:25:08 - INFO - __main__ - Step 144391: {'lr': 1.7705115638919356e-06, 'samples': 27723072, 'steps': 144390, 'loss/train': 1.1084072589874268} 08/31/2021 15:25:09 - INFO - __main__ - Step 144392: {'lr': 1.7698811674844717e-06, 'samples': 27723264, 'steps': 144391, 'loss/train': 1.204643726348877} 08/31/2021 15:25:09 - INFO - __main__ - Step 144393: {'lr': 1.769250882925677e-06, 'samples': 27723456, 'steps': 144392, 'loss/train': 1.250011920928955} 08/31/2021 15:25:10 - INFO - __main__ - Step 144394: {'lr': 1.7686207102158014e-06, 'samples': 27723648, 'steps': 144393, 'loss/train': 0.9807118773460388} 08/31/2021 15:25:10 - INFO - __main__ - Step 144395: {'lr': 1.7679906493551778e-06, 'samples': 27723840, 'steps': 144394, 'loss/train': 1.7435799837112427} 08/31/2021 15:25:12 - INFO - __main__ - Step 144396: {'lr': 1.767360700344084e-06, 'samples': 27724032, 'steps': 144395, 'loss/train': 0.8853830695152283} 08/31/2021 15:25:12 - INFO - __main__ - Step 144397: {'lr': 1.7667308631827694e-06, 'samples': 27724224, 'steps': 144396, 'loss/train': 1.524159550666809} 08/31/2021 15:25:13 - INFO - __main__ - Step 144398: {'lr': 1.7661011378715396e-06, 'samples': 27724416, 'steps': 144397, 'loss/train': 1.0659751892089844} 08/31/2021 15:25:13 - INFO - __main__ - Step 144399: {'lr': 1.7654715244106722e-06, 'samples': 27724608, 'steps': 144398, 'loss/train': 1.2211778163909912} 08/31/2021 15:25:13 - INFO - __main__ - Step 144400: {'lr': 1.7648420228004446e-06, 'samples': 27724800, 'steps': 144399, 'loss/train': 0.7416049242019653} 08/31/2021 15:25:16 - INFO - __main__ - Step 144401: {'lr': 1.7642126330411624e-06, 'samples': 27724992, 'steps': 144400, 'loss/train': 1.5750651359558105} 08/31/2021 15:25:16 - INFO - __main__ - Step 144402: {'lr': 1.7635833551331026e-06, 'samples': 27725184, 'steps': 144401, 'loss/train': 1.6253243684768677} 08/31/2021 15:25:17 - INFO - __main__ - Step 144403: {'lr': 1.7629541890765155e-06, 'samples': 27725376, 'steps': 144402, 'loss/train': 0.6656354069709778} 08/31/2021 15:25:17 - INFO - __main__ - Step 144404: {'lr': 1.7623251348717339e-06, 'samples': 27725568, 'steps': 144403, 'loss/train': 0.9030802845954895} 08/31/2021 15:25:17 - INFO - __main__ - Step 144405: {'lr': 1.7616961925190077e-06, 'samples': 27725760, 'steps': 144404, 'loss/train': 0.5657002925872803} 08/31/2021 15:25:18 - INFO - __main__ - Step 144406: {'lr': 1.7610673620186145e-06, 'samples': 27725952, 'steps': 144405, 'loss/train': 1.0654345750808716} 08/31/2021 15:25:18 - INFO - __main__ - Step 144407: {'lr': 1.7604386433708874e-06, 'samples': 27726144, 'steps': 144406, 'loss/train': 0.8474590182304382} 08/31/2021 15:25:20 - INFO - __main__ - Step 144408: {'lr': 1.7598100365760483e-06, 'samples': 27726336, 'steps': 144407, 'loss/train': 0.7731505036354065} 08/31/2021 15:25:20 - INFO - __main__ - Step 144409: {'lr': 1.7591815416344303e-06, 'samples': 27726528, 'steps': 144408, 'loss/train': 0.890163779258728} 08/31/2021 15:25:21 - INFO - __main__ - Step 144410: {'lr': 1.7585531585462832e-06, 'samples': 27726720, 'steps': 144409, 'loss/train': 0.771264910697937} 08/31/2021 15:25:21 - INFO - __main__ - Step 144411: {'lr': 1.7579248873118846e-06, 'samples': 27726912, 'steps': 144410, 'loss/train': 0.014228827320039272} 08/31/2021 15:25:21 - INFO - __main__ - Step 144412: {'lr': 1.75729672793154e-06, 'samples': 27727104, 'steps': 144411, 'loss/train': 0.015041946433484554} 08/31/2021 15:25:22 - INFO - __main__ - Step 144413: {'lr': 1.7566686804055542e-06, 'samples': 27727296, 'steps': 144412, 'loss/train': 0.1979520320892334} 08/31/2021 15:25:22 - INFO - __main__ - Step 144414: {'lr': 1.7560407447341497e-06, 'samples': 27727488, 'steps': 144413, 'loss/train': 1.520841121673584} 08/31/2021 15:25:24 - INFO - __main__ - Step 144415: {'lr': 1.7554129209176872e-06, 'samples': 27727680, 'steps': 144414, 'loss/train': 1.4351779222488403} 08/31/2021 15:25:24 - INFO - __main__ - Step 144416: {'lr': 1.754785208956361e-06, 'samples': 27727872, 'steps': 144415, 'loss/train': 1.0812042951583862} 08/31/2021 15:25:25 - INFO - __main__ - Step 144417: {'lr': 1.7541576088505319e-06, 'samples': 27728064, 'steps': 144416, 'loss/train': 1.010996699333191} 08/31/2021 15:25:25 - INFO - __main__ - Step 144418: {'lr': 1.7535301206004217e-06, 'samples': 27728256, 'steps': 144417, 'loss/train': 0.03873651102185249} 08/31/2021 15:25:25 - INFO - __main__ - Step 144419: {'lr': 1.7529027442063361e-06, 'samples': 27728448, 'steps': 144418, 'loss/train': 1.8632913827896118} 08/31/2021 15:25:27 - INFO - __main__ - Step 144420: {'lr': 1.7522754796685803e-06, 'samples': 27728640, 'steps': 144419, 'loss/train': 1.1333142518997192} 08/31/2021 15:25:28 - INFO - __main__ - Step 144421: {'lr': 1.7516483269874317e-06, 'samples': 27728832, 'steps': 144420, 'loss/train': 1.5558048486709595} 08/31/2021 15:25:28 - INFO - __main__ - Step 144422: {'lr': 1.7510212861631402e-06, 'samples': 27729024, 'steps': 144421, 'loss/train': 0.8279542922973633} 08/31/2021 15:25:28 - INFO - __main__ - Step 144423: {'lr': 1.7503943571959835e-06, 'samples': 27729216, 'steps': 144422, 'loss/train': 0.06350473314523697} 08/31/2021 15:25:29 - INFO - __main__ - Step 144424: {'lr': 1.7497675400862944e-06, 'samples': 27729408, 'steps': 144423, 'loss/train': 2.475301742553711} 08/31/2021 15:25:31 - INFO - __main__ - Step 144425: {'lr': 1.7491408348343508e-06, 'samples': 27729600, 'steps': 144424, 'loss/train': 0.9608761668205261} 08/31/2021 15:25:31 - INFO - __main__ - Step 144426: {'lr': 1.7485142414403743e-06, 'samples': 27729792, 'steps': 144425, 'loss/train': 0.4358336627483368} 08/31/2021 15:25:32 - INFO - __main__ - Step 144427: {'lr': 1.7478877599046983e-06, 'samples': 27729984, 'steps': 144426, 'loss/train': 0.7931246161460876} 08/31/2021 15:25:32 - INFO - __main__ - Step 144428: {'lr': 1.7472613902276002e-06, 'samples': 27730176, 'steps': 144427, 'loss/train': 1.4021800756454468} 08/31/2021 15:25:32 - INFO - __main__ - Step 144429: {'lr': 1.7466351324093855e-06, 'samples': 27730368, 'steps': 144428, 'loss/train': 1.01335608959198} 08/31/2021 15:25:34 - INFO - __main__ - Step 144430: {'lr': 1.746008986450276e-06, 'samples': 27730560, 'steps': 144429, 'loss/train': 1.13120698928833} 08/31/2021 15:25:34 - INFO - __main__ - Step 144431: {'lr': 1.745382952350577e-06, 'samples': 27730752, 'steps': 144430, 'loss/train': 0.6770511269569397} 08/31/2021 15:25:35 - INFO - __main__ - Step 144432: {'lr': 1.7447570301105664e-06, 'samples': 27730944, 'steps': 144431, 'loss/train': 1.192978024482727} 08/31/2021 15:25:35 - INFO - __main__ - Step 144433: {'lr': 1.7441312197305492e-06, 'samples': 27731136, 'steps': 144432, 'loss/train': 0.6289136409759521} 08/31/2021 15:25:36 - INFO - __main__ - Step 144434: {'lr': 1.7435055212108031e-06, 'samples': 27731328, 'steps': 144433, 'loss/train': 0.7693009376525879} 08/31/2021 15:25:37 - INFO - __main__ - Step 144435: {'lr': 1.7428799345516056e-06, 'samples': 27731520, 'steps': 144434, 'loss/train': 0.7267928719520569} 08/31/2021 15:25:38 - INFO - __main__ - Step 144436: {'lr': 1.7422544597532341e-06, 'samples': 27731712, 'steps': 144435, 'loss/train': 1.2352429628372192} 08/31/2021 15:25:38 - INFO - __main__ - Step 144437: {'lr': 1.7416290968159664e-06, 'samples': 27731904, 'steps': 144436, 'loss/train': 0.08789899945259094} 08/31/2021 15:25:38 - INFO - __main__ - Step 144438: {'lr': 1.74100384574008e-06, 'samples': 27732096, 'steps': 144437, 'loss/train': 1.2884713411331177} 08/31/2021 15:25:39 - INFO - __main__ - Step 144439: {'lr': 1.7403787065258803e-06, 'samples': 27732288, 'steps': 144438, 'loss/train': 0.08832728117704391} 08/31/2021 15:25:39 - INFO - __main__ - Step 144440: {'lr': 1.7397536791736446e-06, 'samples': 27732480, 'steps': 144439, 'loss/train': 1.4725251197814941} 08/31/2021 15:25:40 - INFO - __main__ - Step 144441: {'lr': 1.7391287636836228e-06, 'samples': 27732672, 'steps': 144440, 'loss/train': 0.09649302065372467} 08/31/2021 15:25:41 - INFO - __main__ - Step 144442: {'lr': 1.738503960056148e-06, 'samples': 27732864, 'steps': 144441, 'loss/train': 1.5401021242141724} 08/31/2021 15:25:41 - INFO - __main__ - Step 144443: {'lr': 1.7378792682914423e-06, 'samples': 27733056, 'steps': 144442, 'loss/train': 0.9356503486633301} 08/31/2021 15:25:41 - INFO - __main__ - Step 144444: {'lr': 1.737254688389839e-06, 'samples': 27733248, 'steps': 144443, 'loss/train': 0.4010135531425476} 08/31/2021 15:25:42 - INFO - __main__ - Step 144445: {'lr': 1.736630220351587e-06, 'samples': 27733440, 'steps': 144444, 'loss/train': 1.7875128984451294} 08/31/2021 15:25:44 - INFO - __main__ - Step 144446: {'lr': 1.736005864176965e-06, 'samples': 27733632, 'steps': 144445, 'loss/train': 0.661197304725647} 08/31/2021 15:25:44 - INFO - __main__ - Step 144447: {'lr': 1.7353816198662776e-06, 'samples': 27733824, 'steps': 144446, 'loss/train': 1.6146498918533325} 08/31/2021 15:25:45 - INFO - __main__ - Step 144448: {'lr': 1.7347574874198024e-06, 'samples': 27734016, 'steps': 144447, 'loss/train': 0.02842995710670948} 08/31/2021 15:25:45 - INFO - __main__ - Step 144449: {'lr': 1.7341334668378173e-06, 'samples': 27734208, 'steps': 144448, 'loss/train': 0.059247974306344986} 08/31/2021 15:25:45 - INFO - __main__ - Step 144450: {'lr': 1.7335095581205994e-06, 'samples': 27734400, 'steps': 144449, 'loss/train': 0.46205928921699524} 08/31/2021 15:25:46 - INFO - __main__ - Step 144451: {'lr': 1.7328857612684267e-06, 'samples': 27734592, 'steps': 144450, 'loss/train': 0.866544246673584} 08/31/2021 15:25:47 - INFO - __main__ - Step 144452: {'lr': 1.7322620762815766e-06, 'samples': 27734784, 'steps': 144451, 'loss/train': 0.8587614893913269} 08/31/2021 15:25:48 - INFO - __main__ - Step 144453: {'lr': 1.7316385031603542e-06, 'samples': 27734976, 'steps': 144452, 'loss/train': 0.377729207277298} 08/31/2021 15:25:48 - INFO - __main__ - Step 144454: {'lr': 1.7310150419050097e-06, 'samples': 27735168, 'steps': 144453, 'loss/train': 0.8296071887016296} 08/31/2021 15:25:48 - INFO - __main__ - Step 144455: {'lr': 1.730391692515848e-06, 'samples': 27735360, 'steps': 144454, 'loss/train': 0.19971945881843567} 08/31/2021 15:25:49 - INFO - __main__ - Step 144456: {'lr': 1.729768454993147e-06, 'samples': 27735552, 'steps': 144455, 'loss/train': 1.801640272140503} 08/31/2021 15:25:50 - INFO - __main__ - Step 144457: {'lr': 1.729145329337184e-06, 'samples': 27735744, 'steps': 144456, 'loss/train': 1.094085693359375} 08/31/2021 15:25:51 - INFO - __main__ - Step 144458: {'lr': 1.7285223155482088e-06, 'samples': 27735936, 'steps': 144457, 'loss/train': 1.279839277267456} 08/31/2021 15:25:51 - INFO - __main__ - Step 144459: {'lr': 1.7278994136265546e-06, 'samples': 27736128, 'steps': 144458, 'loss/train': 0.9725357890129089} 08/31/2021 15:25:51 - INFO - __main__ - Step 144460: {'lr': 1.7272766235724712e-06, 'samples': 27736320, 'steps': 144459, 'loss/train': 1.3388333320617676} 08/31/2021 15:25:52 - INFO - __main__ - Step 144461: {'lr': 1.7266539453862363e-06, 'samples': 27736512, 'steps': 144460, 'loss/train': 1.2564771175384521} 08/31/2021 15:25:53 - INFO - __main__ - Step 144462: {'lr': 1.7260313790681547e-06, 'samples': 27736704, 'steps': 144461, 'loss/train': 1.0854511260986328} 08/31/2021 15:25:54 - INFO - __main__ - Step 144463: {'lr': 1.7254089246185045e-06, 'samples': 27736896, 'steps': 144462, 'loss/train': 0.5895073413848877} 08/31/2021 15:25:54 - INFO - __main__ - Step 144464: {'lr': 1.7247865820375352e-06, 'samples': 27737088, 'steps': 144463, 'loss/train': 1.3205466270446777} 08/31/2021 15:25:54 - INFO - __main__ - Step 144465: {'lr': 1.7241643513255246e-06, 'samples': 27737280, 'steps': 144464, 'loss/train': 1.1590291261672974} 08/31/2021 15:25:55 - INFO - __main__ - Step 144466: {'lr': 1.7235422324828054e-06, 'samples': 27737472, 'steps': 144465, 'loss/train': 1.2805062532424927} 08/31/2021 15:25:56 - INFO - __main__ - Step 144467: {'lr': 1.7229202255096276e-06, 'samples': 27737664, 'steps': 144466, 'loss/train': 0.8218740820884705} 08/31/2021 15:25:57 - INFO - __main__ - Step 144468: {'lr': 1.7222983304062411e-06, 'samples': 27737856, 'steps': 144467, 'loss/train': 1.688248872756958} 08/31/2021 15:25:57 - INFO - __main__ - Step 144469: {'lr': 1.7216765471730066e-06, 'samples': 27738048, 'steps': 144468, 'loss/train': 0.5404371619224548} 08/31/2021 15:25:57 - INFO - __main__ - Step 144470: {'lr': 1.7210548758101186e-06, 'samples': 27738240, 'steps': 144469, 'loss/train': 0.8177011609077454} 08/31/2021 15:25:58 - INFO - __main__ - Step 144471: {'lr': 1.720433316317882e-06, 'samples': 27738432, 'steps': 144470, 'loss/train': 1.4544811248779297} 08/31/2021 15:25:58 - INFO - __main__ - Step 144472: {'lr': 1.7198118686966025e-06, 'samples': 27738624, 'steps': 144471, 'loss/train': 1.3495556116104126} 08/31/2021 15:25:59 - INFO - __main__ - Step 144473: {'lr': 1.7191905329465574e-06, 'samples': 27738816, 'steps': 144472, 'loss/train': 1.3468830585479736} 08/31/2021 15:26:00 - INFO - __main__ - Step 144474: {'lr': 1.7185693090679965e-06, 'samples': 27739008, 'steps': 144473, 'loss/train': 0.8866291642189026} 08/31/2021 15:26:00 - INFO - __main__ - Step 144475: {'lr': 1.7179481970612254e-06, 'samples': 27739200, 'steps': 144474, 'loss/train': 1.1600477695465088} 08/31/2021 15:26:01 - INFO - __main__ - Step 144476: {'lr': 1.7173271969264936e-06, 'samples': 27739392, 'steps': 144475, 'loss/train': 0.3844433128833771} 08/31/2021 15:26:01 - INFO - __main__ - Step 144477: {'lr': 1.7167063086641344e-06, 'samples': 27739584, 'steps': 144476, 'loss/train': 1.5827112197875977} 08/31/2021 15:26:03 - INFO - __main__ - Step 144478: {'lr': 1.7160855322743696e-06, 'samples': 27739776, 'steps': 144477, 'loss/train': 0.9750518202781677} 08/31/2021 15:26:04 - INFO - __main__ - Step 144479: {'lr': 1.7154648677575323e-06, 'samples': 27739968, 'steps': 144478, 'loss/train': 0.7982320785522461} 08/31/2021 15:26:04 - INFO - __main__ - Step 144480: {'lr': 1.7148443151138448e-06, 'samples': 27740160, 'steps': 144479, 'loss/train': 1.3063068389892578} 08/31/2021 15:26:04 - INFO - __main__ - Step 144481: {'lr': 1.71422387434364e-06, 'samples': 27740352, 'steps': 144480, 'loss/train': 1.3107329607009888} 08/31/2021 15:26:05 - INFO - __main__ - Step 144482: {'lr': 1.7136035454471676e-06, 'samples': 27740544, 'steps': 144481, 'loss/train': 1.1436485052108765} 08/31/2021 15:26:06 - INFO - __main__ - Step 144483: {'lr': 1.712983328424733e-06, 'samples': 27740736, 'steps': 144482, 'loss/train': 1.2277835607528687} 08/31/2021 15:26:07 - INFO - __main__ - Step 144484: {'lr': 1.7123632232765584e-06, 'samples': 27740928, 'steps': 144483, 'loss/train': 0.84306800365448} 08/31/2021 15:26:07 - INFO - __main__ - Step 144485: {'lr': 1.7117432300030044e-06, 'samples': 27741120, 'steps': 144484, 'loss/train': 1.2266380786895752} 08/31/2021 15:26:07 - INFO - __main__ - Step 144486: {'lr': 1.7111233486042655e-06, 'samples': 27741312, 'steps': 144485, 'loss/train': 0.026591258123517036} 08/31/2021 15:26:08 - INFO - __main__ - Step 144487: {'lr': 1.7105035790807023e-06, 'samples': 27741504, 'steps': 144486, 'loss/train': 0.9301146864891052} 08/31/2021 15:26:10 - INFO - __main__ - Step 144488: {'lr': 1.709883921432509e-06, 'samples': 27741696, 'steps': 144487, 'loss/train': 1.561537742614746} 08/31/2021 15:26:10 - INFO - __main__ - Step 144489: {'lr': 1.7092643756600468e-06, 'samples': 27741888, 'steps': 144488, 'loss/train': 0.15788385272026062} 08/31/2021 15:26:11 - INFO - __main__ - Step 144490: {'lr': 1.7086449417635374e-06, 'samples': 27742080, 'steps': 144489, 'loss/train': 5.3201212882995605} 08/31/2021 15:26:11 - INFO - __main__ - Step 144491: {'lr': 1.7080256197433143e-06, 'samples': 27742272, 'steps': 144490, 'loss/train': 2.058365821838379} 08/31/2021 15:26:11 - INFO - __main__ - Step 144492: {'lr': 1.707406409599599e-06, 'samples': 27742464, 'steps': 144491, 'loss/train': 0.7696351408958435} 08/31/2021 15:26:12 - INFO - __main__ - Step 144493: {'lr': 1.7067873113326971e-06, 'samples': 27742656, 'steps': 144492, 'loss/train': 1.4327718019485474} 08/31/2021 15:26:13 - INFO - __main__ - Step 144494: {'lr': 1.706168324942886e-06, 'samples': 27742848, 'steps': 144493, 'loss/train': 1.4478343725204468} 08/31/2021 15:26:14 - INFO - __main__ - Step 144495: {'lr': 1.7055494504304435e-06, 'samples': 27743040, 'steps': 144494, 'loss/train': 1.2232284545898438} 08/31/2021 15:26:14 - INFO - __main__ - Step 144496: {'lr': 1.7049306877956473e-06, 'samples': 27743232, 'steps': 144495, 'loss/train': 0.8782786726951599} 08/31/2021 15:26:14 - INFO - __main__ - Step 144497: {'lr': 1.7043120370387743e-06, 'samples': 27743424, 'steps': 144496, 'loss/train': 0.9854140281677246} 08/31/2021 15:26:15 - INFO - __main__ - Step 144498: {'lr': 1.7036934981601303e-06, 'samples': 27743616, 'steps': 144497, 'loss/train': 1.2330752611160278} 08/31/2021 15:26:15 - INFO - __main__ - Step 144499: {'lr': 1.7030750711599373e-06, 'samples': 27743808, 'steps': 144498, 'loss/train': 1.4633969068527222} 08/31/2021 15:26:17 - INFO - __main__ - Step 144500: {'lr': 1.7024567560385284e-06, 'samples': 27744000, 'steps': 144499, 'loss/train': 0.7984563708305359} 08/31/2021 15:26:17 - INFO - __main__ - Step 144501: {'lr': 1.7018385527961532e-06, 'samples': 27744192, 'steps': 144500, 'loss/train': 0.6472494006156921} 08/31/2021 15:26:17 - INFO - __main__ - Step 144502: {'lr': 1.7012204614330895e-06, 'samples': 27744384, 'steps': 144501, 'loss/train': 1.5272748470306396} 08/31/2021 15:26:18 - INFO - __main__ - Step 144503: {'lr': 1.7006024819496701e-06, 'samples': 27744576, 'steps': 144502, 'loss/train': 0.6699045896530151} 08/31/2021 15:26:18 - INFO - __main__ - Step 144504: {'lr': 1.6999846143460895e-06, 'samples': 27744768, 'steps': 144503, 'loss/train': 1.0112032890319824} 08/31/2021 15:26:20 - INFO - __main__ - Step 144505: {'lr': 1.699366858622653e-06, 'samples': 27744960, 'steps': 144504, 'loss/train': 0.0985301062464714} 08/31/2021 15:26:20 - INFO - __main__ - Step 144506: {'lr': 1.6987492147796656e-06, 'samples': 27745152, 'steps': 144505, 'loss/train': 0.20228958129882812} 08/31/2021 15:26:21 - INFO - __main__ - Step 144507: {'lr': 1.6981316828173775e-06, 'samples': 27745344, 'steps': 144506, 'loss/train': 0.38038453459739685} 08/31/2021 15:26:21 - INFO - __main__ - Step 144508: {'lr': 1.697514262736094e-06, 'samples': 27745536, 'steps': 144507, 'loss/train': 1.1043888330459595} 08/31/2021 15:26:22 - INFO - __main__ - Step 144509: {'lr': 1.6968969545360924e-06, 'samples': 27745728, 'steps': 144508, 'loss/train': 0.5157090425491333} 08/31/2021 15:26:23 - INFO - __main__ - Step 144510: {'lr': 1.6962797582176227e-06, 'samples': 27745920, 'steps': 144509, 'loss/train': 1.4663537740707397} 08/31/2021 15:26:24 - INFO - __main__ - Step 144511: {'lr': 1.6956626737809622e-06, 'samples': 27746112, 'steps': 144510, 'loss/train': 1.2295793294906616} 08/31/2021 15:26:24 - INFO - __main__ - Step 144512: {'lr': 1.6950457012264165e-06, 'samples': 27746304, 'steps': 144511, 'loss/train': 1.2854232788085938} 08/31/2021 15:26:24 - INFO - __main__ - Step 144513: {'lr': 1.694428840554263e-06, 'samples': 27746496, 'steps': 144512, 'loss/train': 0.6631656289100647} 08/31/2021 15:26:25 - INFO - __main__ - Step 144514: {'lr': 1.6938120917647792e-06, 'samples': 27746688, 'steps': 144513, 'loss/train': 1.1751285791397095} 08/31/2021 15:26:26 - INFO - __main__ - Step 144515: {'lr': 1.6931954548582152e-06, 'samples': 27746880, 'steps': 144514, 'loss/train': 1.6398581266403198} 08/31/2021 15:26:27 - INFO - __main__ - Step 144516: {'lr': 1.6925789298348482e-06, 'samples': 27747072, 'steps': 144515, 'loss/train': 1.2912745475769043} 08/31/2021 15:26:27 - INFO - __main__ - Step 144517: {'lr': 1.6919625166949836e-06, 'samples': 27747264, 'steps': 144516, 'loss/train': 0.8279125094413757} 08/31/2021 15:26:27 - INFO - __main__ - Step 144518: {'lr': 1.6913462154388993e-06, 'samples': 27747456, 'steps': 144517, 'loss/train': 1.3122550249099731} 08/31/2021 15:26:28 - INFO - __main__ - Step 144519: {'lr': 1.6907300260668445e-06, 'samples': 27747648, 'steps': 144518, 'loss/train': 1.3140877485275269} 08/31/2021 15:26:29 - INFO - __main__ - Step 144520: {'lr': 1.690113948579125e-06, 'samples': 27747840, 'steps': 144519, 'loss/train': 0.5067278146743774} 08/31/2021 15:26:30 - INFO - __main__ - Step 144521: {'lr': 1.6894979829760182e-06, 'samples': 27748032, 'steps': 144520, 'loss/train': 1.0230720043182373} 08/31/2021 15:26:30 - INFO - __main__ - Step 144522: {'lr': 1.6888821292578016e-06, 'samples': 27748224, 'steps': 144521, 'loss/train': 1.474599838256836} 08/31/2021 15:26:31 - INFO - __main__ - Step 144523: {'lr': 1.6882663874247251e-06, 'samples': 27748416, 'steps': 144522, 'loss/train': 1.3557289838790894} 08/31/2021 15:26:31 - INFO - __main__ - Step 144524: {'lr': 1.687650757477066e-06, 'samples': 27748608, 'steps': 144523, 'loss/train': 1.4175878763198853} 08/31/2021 15:26:33 - INFO - __main__ - Step 144525: {'lr': 1.6870352394151579e-06, 'samples': 27748800, 'steps': 144524, 'loss/train': 0.09106522053480148} 08/31/2021 15:26:33 - INFO - __main__ - Step 144526: {'lr': 1.6864198332392221e-06, 'samples': 27748992, 'steps': 144525, 'loss/train': 0.45537084341049194} 08/31/2021 15:26:34 - INFO - __main__ - Step 144527: {'lr': 1.6858045389495646e-06, 'samples': 27749184, 'steps': 144526, 'loss/train': 0.8599051237106323} 08/31/2021 15:26:34 - INFO - __main__ - Step 144528: {'lr': 1.6851893565464348e-06, 'samples': 27749376, 'steps': 144527, 'loss/train': 1.1140289306640625} 08/31/2021 15:26:34 - INFO - __main__ - Step 144529: {'lr': 1.6845742860301383e-06, 'samples': 27749568, 'steps': 144528, 'loss/train': 0.7008621096611023} 08/31/2021 15:26:35 - INFO - __main__ - Step 144530: {'lr': 1.6839593274009247e-06, 'samples': 27749760, 'steps': 144529, 'loss/train': 0.35324689745903015} 08/31/2021 15:26:37 - INFO - __main__ - Step 144531: {'lr': 1.6833444806590992e-06, 'samples': 27749952, 'steps': 144530, 'loss/train': 0.013796929270029068} 08/31/2021 15:26:38 - INFO - __main__ - Step 144532: {'lr': 1.6827297458049117e-06, 'samples': 27750144, 'steps': 144531, 'loss/train': 0.8646529912948608} 08/31/2021 15:26:38 - INFO - __main__ - Step 144533: {'lr': 1.6821151228386678e-06, 'samples': 27750336, 'steps': 144532, 'loss/train': 1.0973453521728516} 08/31/2021 15:26:38 - INFO - __main__ - Step 144534: {'lr': 1.6815006117606446e-06, 'samples': 27750528, 'steps': 144533, 'loss/train': 0.9640709757804871} 08/31/2021 15:26:39 - INFO - __main__ - Step 144535: {'lr': 1.680886212571092e-06, 'samples': 27750720, 'steps': 144534, 'loss/train': 0.7391974329948425} 08/31/2021 15:26:39 - INFO - __main__ - Step 144536: {'lr': 1.6802719252703159e-06, 'samples': 27750912, 'steps': 144535, 'loss/train': 5.719367504119873} 08/31/2021 15:26:40 - INFO - __main__ - Step 144537: {'lr': 1.6796577498585375e-06, 'samples': 27751104, 'steps': 144536, 'loss/train': 0.4671221971511841} 08/31/2021 15:26:41 - INFO - __main__ - Step 144538: {'lr': 1.6790436863361181e-06, 'samples': 27751296, 'steps': 144537, 'loss/train': 0.05378734692931175} 08/31/2021 15:26:41 - INFO - __main__ - Step 144539: {'lr': 1.6784297347032518e-06, 'samples': 27751488, 'steps': 144538, 'loss/train': 0.9702728390693665} 08/31/2021 15:26:42 - INFO - __main__ - Step 144540: {'lr': 1.6778158949602718e-06, 'samples': 27751680, 'steps': 144539, 'loss/train': 1.1326720714569092} 08/31/2021 15:26:42 - INFO - __main__ - Step 144541: {'lr': 1.6772021671074556e-06, 'samples': 27751872, 'steps': 144540, 'loss/train': 1.193772554397583} 08/31/2021 15:26:43 - INFO - __main__ - Step 144542: {'lr': 1.6765885511450252e-06, 'samples': 27752064, 'steps': 144541, 'loss/train': 1.4088562726974487} 08/31/2021 15:26:44 - INFO - __main__ - Step 144543: {'lr': 1.6759750470733138e-06, 'samples': 27752256, 'steps': 144542, 'loss/train': 1.61353600025177} 08/31/2021 15:26:44 - INFO - __main__ - Step 144544: {'lr': 1.675361654892571e-06, 'samples': 27752448, 'steps': 144543, 'loss/train': 1.271638035774231} 08/31/2021 15:26:45 - INFO - __main__ - Step 144545: {'lr': 1.6747483746030745e-06, 'samples': 27752640, 'steps': 144544, 'loss/train': 0.8865293264389038} 08/31/2021 15:26:45 - INFO - __main__ - Step 144546: {'lr': 1.6741352062051018e-06, 'samples': 27752832, 'steps': 144545, 'loss/train': 1.5547196865081787} 08/31/2021 15:26:46 - INFO - __main__ - Step 144547: {'lr': 1.6735221496989306e-06, 'samples': 27753024, 'steps': 144546, 'loss/train': 0.8386971950531006} 08/31/2021 15:26:47 - INFO - __main__ - Step 144548: {'lr': 1.6729092050848383e-06, 'samples': 27753216, 'steps': 144547, 'loss/train': 0.8777576088905334} 08/31/2021 15:26:47 - INFO - __main__ - Step 144549: {'lr': 1.6722963723631023e-06, 'samples': 27753408, 'steps': 144548, 'loss/train': 0.7275466322898865} 08/31/2021 15:26:47 - INFO - __main__ - Step 144550: {'lr': 1.6716836515340283e-06, 'samples': 27753600, 'steps': 144549, 'loss/train': 0.9872475862503052} 08/31/2021 15:26:48 - INFO - __main__ - Step 144551: {'lr': 1.6710710425978381e-06, 'samples': 27753792, 'steps': 144550, 'loss/train': 1.1065219640731812} 08/31/2021 15:26:49 - INFO - __main__ - Step 144552: {'lr': 1.670458545554837e-06, 'samples': 27753984, 'steps': 144551, 'loss/train': 0.9095864295959473} 08/31/2021 15:26:50 - INFO - __main__ - Step 144553: {'lr': 1.669846160405275e-06, 'samples': 27754176, 'steps': 144552, 'loss/train': 1.1304125785827637} 08/31/2021 15:26:50 - INFO - __main__ - Step 144554: {'lr': 1.6692338871494573e-06, 'samples': 27754368, 'steps': 144553, 'loss/train': 1.6947275400161743} 08/31/2021 15:26:50 - INFO - __main__ - Step 144555: {'lr': 1.6686217257876612e-06, 'samples': 27754560, 'steps': 144554, 'loss/train': 1.0706545114517212} 08/31/2021 15:26:51 - INFO - __main__ - Step 144556: {'lr': 1.6680096763201369e-06, 'samples': 27754752, 'steps': 144555, 'loss/train': 1.3070290088653564} 08/31/2021 15:26:51 - INFO - __main__ - Step 144557: {'lr': 1.6673977387471895e-06, 'samples': 27754944, 'steps': 144556, 'loss/train': 1.087037205696106} 08/31/2021 15:26:53 - INFO - __main__ - Step 144558: {'lr': 1.6667859130690689e-06, 'samples': 27755136, 'steps': 144557, 'loss/train': 0.6483209133148193} 08/31/2021 15:26:53 - INFO - __main__ - Step 144559: {'lr': 1.6661741992860802e-06, 'samples': 27755328, 'steps': 144558, 'loss/train': 1.6373672485351562} 08/31/2021 15:26:54 - INFO - __main__ - Step 144560: {'lr': 1.6655625973984735e-06, 'samples': 27755520, 'steps': 144559, 'loss/train': 0.6164926290512085} 08/31/2021 15:26:54 - INFO - __main__ - Step 144561: {'lr': 1.664951107406526e-06, 'samples': 27755712, 'steps': 144560, 'loss/train': 0.40980759263038635} 08/31/2021 15:26:54 - INFO - __main__ - Step 144562: {'lr': 1.6643397293105156e-06, 'samples': 27755904, 'steps': 144561, 'loss/train': 1.6799862384796143} 08/31/2021 15:26:56 - INFO - __main__ - Step 144563: {'lr': 1.6637284631107475e-06, 'samples': 27756096, 'steps': 144562, 'loss/train': 1.2129409313201904} 08/31/2021 15:26:56 - INFO - __main__ - Step 144564: {'lr': 1.6631173088074436e-06, 'samples': 27756288, 'steps': 144563, 'loss/train': 0.8660604953765869} 08/31/2021 15:26:57 - INFO - __main__ - Step 144565: {'lr': 1.6625062664009094e-06, 'samples': 27756480, 'steps': 144564, 'loss/train': 0.9708388447761536} 08/31/2021 15:26:57 - INFO - __main__ - Step 144566: {'lr': 1.6618953358914224e-06, 'samples': 27756672, 'steps': 144565, 'loss/train': 1.4979559183120728} 08/31/2021 15:26:57 - INFO - __main__ - Step 144567: {'lr': 1.6612845172792601e-06, 'samples': 27756864, 'steps': 144566, 'loss/train': 1.1847199201583862} 08/31/2021 15:26:59 - INFO - __main__ - Step 144568: {'lr': 1.6606738105646723e-06, 'samples': 27757056, 'steps': 144567, 'loss/train': 1.243362307548523} 08/31/2021 15:26:59 - INFO - __main__ - Step 144569: {'lr': 1.6600632157479922e-06, 'samples': 27757248, 'steps': 144568, 'loss/train': 1.173525333404541} 08/31/2021 15:27:00 - INFO - __main__ - Step 144570: {'lr': 1.659452732829414e-06, 'samples': 27757440, 'steps': 144569, 'loss/train': 0.550159215927124} 08/31/2021 15:27:00 - INFO - __main__ - Step 144571: {'lr': 1.6588423618092707e-06, 'samples': 27757632, 'steps': 144570, 'loss/train': 0.766830563545227} 08/31/2021 15:27:00 - INFO - __main__ - Step 144572: {'lr': 1.6582321026878122e-06, 'samples': 27757824, 'steps': 144571, 'loss/train': 1.3572643995285034} 08/31/2021 15:27:02 - INFO - __main__ - Step 144573: {'lr': 1.6576219554653437e-06, 'samples': 27758016, 'steps': 144572, 'loss/train': 0.9103975296020508} 08/31/2021 15:27:02 - INFO - __main__ - Step 144574: {'lr': 1.6570119201420875e-06, 'samples': 27758208, 'steps': 144573, 'loss/train': 0.3275948464870453} 08/31/2021 15:27:03 - INFO - __main__ - Step 144575: {'lr': 1.6564019967183762e-06, 'samples': 27758400, 'steps': 144574, 'loss/train': 1.3013916015625} 08/31/2021 15:27:03 - INFO - __main__ - Step 144576: {'lr': 1.6557921851944601e-06, 'samples': 27758592, 'steps': 144575, 'loss/train': 1.1020410060882568} 08/31/2021 15:27:03 - INFO - __main__ - Step 144577: {'lr': 1.6551824855705889e-06, 'samples': 27758784, 'steps': 144576, 'loss/train': 1.2093714475631714} 08/31/2021 15:27:05 - INFO - __main__ - Step 144578: {'lr': 1.6545728978470953e-06, 'samples': 27758976, 'steps': 144577, 'loss/train': 1.921748161315918} 08/31/2021 15:27:05 - INFO - __main__ - Step 144579: {'lr': 1.653963422024174e-06, 'samples': 27759168, 'steps': 144578, 'loss/train': 0.9938532114028931} 08/31/2021 15:27:06 - INFO - __main__ - Step 144580: {'lr': 1.6533540581021855e-06, 'samples': 27759360, 'steps': 144579, 'loss/train': 0.8849532008171082} 08/31/2021 15:27:06 - INFO - __main__ - Step 144581: {'lr': 1.6527448060813245e-06, 'samples': 27759552, 'steps': 144580, 'loss/train': 1.0254261493682861} 08/31/2021 15:27:06 - INFO - __main__ - Step 144582: {'lr': 1.6521356659619236e-06, 'samples': 27759744, 'steps': 144581, 'loss/train': 1.225942611694336} 08/31/2021 15:27:09 - INFO - __main__ - Step 144583: {'lr': 1.6515266377442327e-06, 'samples': 27759936, 'steps': 144582, 'loss/train': 0.882499098777771} 08/31/2021 15:27:09 - INFO - __main__ - Step 144584: {'lr': 1.6509177214285575e-06, 'samples': 27760128, 'steps': 144583, 'loss/train': 0.8972037434577942} 08/31/2021 15:27:09 - INFO - __main__ - Step 144585: {'lr': 1.6503089170151197e-06, 'samples': 27760320, 'steps': 144584, 'loss/train': 0.9267489910125732} 08/31/2021 15:27:10 - INFO - __main__ - Step 144586: {'lr': 1.6497002245042248e-06, 'samples': 27760512, 'steps': 144585, 'loss/train': 1.2025892734527588} 08/31/2021 15:27:10 - INFO - __main__ - Step 144587: {'lr': 1.6490916438961501e-06, 'samples': 27760704, 'steps': 144586, 'loss/train': 1.1889337301254272} 08/31/2021 15:27:12 - INFO - __main__ - Step 144588: {'lr': 1.6484831751911455e-06, 'samples': 27760896, 'steps': 144587, 'loss/train': 1.4356708526611328} 08/31/2021 15:27:12 - INFO - __main__ - Step 144589: {'lr': 1.6478748183895164e-06, 'samples': 27761088, 'steps': 144588, 'loss/train': 1.6370253562927246} 08/31/2021 15:27:12 - INFO - __main__ - Step 144590: {'lr': 1.6472665734915405e-06, 'samples': 27761280, 'steps': 144589, 'loss/train': 0.6680771708488464} 08/31/2021 15:27:13 - INFO - __main__ - Step 144591: {'lr': 1.6466584404974394e-06, 'samples': 27761472, 'steps': 144590, 'loss/train': 0.4834795892238617} 08/31/2021 15:27:13 - INFO - __main__ - Step 144592: {'lr': 1.6460504194075466e-06, 'samples': 27761664, 'steps': 144591, 'loss/train': 0.9426723122596741} 08/31/2021 15:27:14 - INFO - __main__ - Step 144593: {'lr': 1.6454425102220838e-06, 'samples': 27761856, 'steps': 144592, 'loss/train': 1.2454185485839844} 08/31/2021 15:27:15 - INFO - __main__ - Step 144594: {'lr': 1.6448347129413844e-06, 'samples': 27762048, 'steps': 144593, 'loss/train': 0.5319004058837891} 08/31/2021 15:27:15 - INFO - __main__ - Step 144595: {'lr': 1.6442270275656702e-06, 'samples': 27762240, 'steps': 144594, 'loss/train': 1.147962212562561} 08/31/2021 15:27:16 - INFO - __main__ - Step 144596: {'lr': 1.6436194540952464e-06, 'samples': 27762432, 'steps': 144595, 'loss/train': 0.9314134120941162} 08/31/2021 15:27:16 - INFO - __main__ - Step 144597: {'lr': 1.6430119925303632e-06, 'samples': 27762624, 'steps': 144596, 'loss/train': 1.1945406198501587} 08/31/2021 15:27:17 - INFO - __main__ - Step 144598: {'lr': 1.642404642871298e-06, 'samples': 27762816, 'steps': 144597, 'loss/train': 0.9457131028175354} 08/31/2021 15:27:18 - INFO - __main__ - Step 144599: {'lr': 1.641797405118356e-06, 'samples': 27763008, 'steps': 144598, 'loss/train': 1.3158645629882812} 08/31/2021 15:27:19 - INFO - __main__ - Step 144600: {'lr': 1.641190279271787e-06, 'samples': 27763200, 'steps': 144599, 'loss/train': 1.3313393592834473} 08/31/2021 15:27:19 - INFO - __main__ - Step 144601: {'lr': 1.6405832653318408e-06, 'samples': 27763392, 'steps': 144600, 'loss/train': 1.4597532749176025} 08/31/2021 15:27:19 - INFO - __main__ - Step 144602: {'lr': 1.639976363298823e-06, 'samples': 27763584, 'steps': 144601, 'loss/train': 1.2708899974822998} 08/31/2021 15:27:20 - INFO - __main__ - Step 144603: {'lr': 1.6393695731730384e-06, 'samples': 27763776, 'steps': 144602, 'loss/train': 1.1517692804336548} 08/31/2021 15:27:21 - INFO - __main__ - Step 144604: {'lr': 1.6387628949546817e-06, 'samples': 27763968, 'steps': 144603, 'loss/train': 0.5087442994117737} 08/31/2021 15:27:22 - INFO - __main__ - Step 144605: {'lr': 1.638156328644086e-06, 'samples': 27764160, 'steps': 144604, 'loss/train': 0.8538126945495605} 08/31/2021 15:27:22 - INFO - __main__ - Step 144606: {'lr': 1.6375498742414729e-06, 'samples': 27764352, 'steps': 144605, 'loss/train': 1.107141375541687} 08/31/2021 15:27:23 - INFO - __main__ - Step 144607: {'lr': 1.636943531747176e-06, 'samples': 27764544, 'steps': 144606, 'loss/train': 1.2992631196975708} 08/31/2021 15:27:23 - INFO - __main__ - Step 144608: {'lr': 1.636337301161417e-06, 'samples': 27764736, 'steps': 144607, 'loss/train': 0.0330415740609169} 08/31/2021 15:27:25 - INFO - __main__ - Step 144609: {'lr': 1.635731182484529e-06, 'samples': 27764928, 'steps': 144608, 'loss/train': 1.1884245872497559} 08/31/2021 15:27:25 - INFO - __main__ - Step 144610: {'lr': 1.6351251757167063e-06, 'samples': 27765120, 'steps': 144609, 'loss/train': 1.228363275527954} 08/31/2021 15:27:26 - INFO - __main__ - Step 144611: {'lr': 1.634519280858282e-06, 'samples': 27765312, 'steps': 144610, 'loss/train': 1.56273353099823} 08/31/2021 15:27:26 - INFO - __main__ - Step 144612: {'lr': 1.6339134979095062e-06, 'samples': 27765504, 'steps': 144611, 'loss/train': 1.488146185874939} 08/31/2021 15:27:26 - INFO - __main__ - Step 144613: {'lr': 1.6333078268706835e-06, 'samples': 27765696, 'steps': 144612, 'loss/train': 0.9879398345947266} 08/31/2021 15:27:27 - INFO - __main__ - Step 144614: {'lr': 1.6327022677420368e-06, 'samples': 27765888, 'steps': 144613, 'loss/train': 1.8356660604476929} 08/31/2021 15:27:28 - INFO - __main__ - Step 144615: {'lr': 1.632096820523843e-06, 'samples': 27766080, 'steps': 144614, 'loss/train': 1.6305187940597534} 08/31/2021 15:27:29 - INFO - __main__ - Step 144616: {'lr': 1.6314914852164352e-06, 'samples': 27766272, 'steps': 144615, 'loss/train': 1.3013461828231812} 08/31/2021 15:27:29 - INFO - __main__ - Step 144617: {'lr': 1.630886261820036e-06, 'samples': 27766464, 'steps': 144616, 'loss/train': 1.4726226329803467} 08/31/2021 15:27:30 - INFO - __main__ - Step 144618: {'lr': 1.6302811503348947e-06, 'samples': 27766656, 'steps': 144617, 'loss/train': 0.4986772835254669} 08/31/2021 15:27:30 - INFO - __main__ - Step 144619: {'lr': 1.6296761507613445e-06, 'samples': 27766848, 'steps': 144618, 'loss/train': 0.844673752784729} 08/31/2021 15:27:32 - INFO - __main__ - Step 144620: {'lr': 1.6290712630996073e-06, 'samples': 27767040, 'steps': 144619, 'loss/train': 0.7413556575775146} 08/31/2021 15:27:32 - INFO - __main__ - Step 144621: {'lr': 1.6284664873500165e-06, 'samples': 27767232, 'steps': 144620, 'loss/train': 1.168747901916504} 08/31/2021 15:27:32 - INFO - __main__ - Step 144622: {'lr': 1.6278618235127662e-06, 'samples': 27767424, 'steps': 144621, 'loss/train': 1.1202799081802368} 08/31/2021 15:27:33 - INFO - __main__ - Step 144623: {'lr': 1.6272572715881894e-06, 'samples': 27767616, 'steps': 144622, 'loss/train': 1.1273202896118164} 08/31/2021 15:27:33 - INFO - __main__ - Step 144624: {'lr': 1.626652831576536e-06, 'samples': 27767808, 'steps': 144623, 'loss/train': 1.0437335968017578} 08/31/2021 15:27:34 - INFO - __main__ - Step 144625: {'lr': 1.626048503478056e-06, 'samples': 27768000, 'steps': 144624, 'loss/train': 0.3053008019924164} 08/31/2021 15:27:35 - INFO - __main__ - Step 144626: {'lr': 1.6254442872930818e-06, 'samples': 27768192, 'steps': 144625, 'loss/train': 1.2711721658706665} 08/31/2021 15:27:36 - INFO - __main__ - Step 144627: {'lr': 1.6248401830218362e-06, 'samples': 27768384, 'steps': 144626, 'loss/train': 0.029808497056365013} 08/31/2021 15:27:36 - INFO - __main__ - Step 144628: {'lr': 1.6242361906645963e-06, 'samples': 27768576, 'steps': 144627, 'loss/train': 1.6706526279449463} 08/31/2021 15:27:37 - INFO - __main__ - Step 144629: {'lr': 1.6236323102216398e-06, 'samples': 27768768, 'steps': 144628, 'loss/train': 1.0990822315216064} 08/31/2021 15:27:37 - INFO - __main__ - Step 144630: {'lr': 1.6230285416932722e-06, 'samples': 27768960, 'steps': 144629, 'loss/train': 0.8005375266075134} 08/31/2021 15:27:39 - INFO - __main__ - Step 144631: {'lr': 1.6224248850797152e-06, 'samples': 27769152, 'steps': 144630, 'loss/train': 1.3014332056045532} 08/31/2021 15:27:39 - INFO - __main__ - Step 144632: {'lr': 1.6218213403812466e-06, 'samples': 27769344, 'steps': 144631, 'loss/train': 0.06503663957118988} 08/31/2021 15:27:40 - INFO - __main__ - Step 144633: {'lr': 1.6212179075981714e-06, 'samples': 27769536, 'steps': 144632, 'loss/train': 1.5668509006500244} 08/31/2021 15:27:40 - INFO - __main__ - Step 144634: {'lr': 1.6206145867307397e-06, 'samples': 27769728, 'steps': 144633, 'loss/train': 1.0912076234817505} 08/31/2021 15:27:40 - INFO - __main__ - Step 144635: {'lr': 1.620011377779229e-06, 'samples': 27769920, 'steps': 144634, 'loss/train': 0.6029649972915649} 08/31/2021 15:27:41 - INFO - __main__ - Step 144636: {'lr': 1.619408280743917e-06, 'samples': 27770112, 'steps': 144635, 'loss/train': 0.7904089689254761} 08/31/2021 15:27:43 - INFO - __main__ - Step 144637: {'lr': 1.6188052956250533e-06, 'samples': 27770304, 'steps': 144636, 'loss/train': 0.7112222909927368} 08/31/2021 15:27:43 - INFO - __main__ - Step 144638: {'lr': 1.6182024224229152e-06, 'samples': 27770496, 'steps': 144637, 'loss/train': 0.8555136919021606} 08/31/2021 15:27:43 - INFO - __main__ - Step 144639: {'lr': 1.6175996611377808e-06, 'samples': 27770688, 'steps': 144638, 'loss/train': 0.6178436875343323} 08/31/2021 15:27:44 - INFO - __main__ - Step 144640: {'lr': 1.6169970117699273e-06, 'samples': 27770880, 'steps': 144639, 'loss/train': 0.7104742527008057} 08/31/2021 15:27:44 - INFO - __main__ - Step 144641: {'lr': 1.6163944743196323e-06, 'samples': 27771072, 'steps': 144640, 'loss/train': 0.9631250500679016} 08/31/2021 15:27:46 - INFO - __main__ - Step 144642: {'lr': 1.6157920487871458e-06, 'samples': 27771264, 'steps': 144641, 'loss/train': 0.986133873462677} 08/31/2021 15:27:46 - INFO - __main__ - Step 144643: {'lr': 1.6151897351727728e-06, 'samples': 27771456, 'steps': 144642, 'loss/train': 0.8497476577758789} 08/31/2021 15:27:47 - INFO - __main__ - Step 144644: {'lr': 1.6145875334767635e-06, 'samples': 27771648, 'steps': 144643, 'loss/train': 1.3606899976730347} 08/31/2021 15:27:47 - INFO - __main__ - Step 144645: {'lr': 1.6139854436993673e-06, 'samples': 27771840, 'steps': 144644, 'loss/train': 1.1482406854629517} 08/31/2021 15:27:47 - INFO - __main__ - Step 144646: {'lr': 1.6133834658408898e-06, 'samples': 27772032, 'steps': 144645, 'loss/train': 1.1947494745254517} 08/31/2021 15:27:49 - INFO - __main__ - Step 144647: {'lr': 1.6127815999015805e-06, 'samples': 27772224, 'steps': 144646, 'loss/train': 0.03600210323929787} 08/31/2021 15:27:49 - INFO - __main__ - Step 144648: {'lr': 1.612179845881717e-06, 'samples': 27772416, 'steps': 144647, 'loss/train': 1.0258221626281738} 08/31/2021 15:27:50 - INFO - __main__ - Step 144649: {'lr': 1.6115782037815497e-06, 'samples': 27772608, 'steps': 144648, 'loss/train': 1.3131978511810303} 08/31/2021 15:27:50 - INFO - __main__ - Step 144650: {'lr': 1.6109766736014109e-06, 'samples': 27772800, 'steps': 144649, 'loss/train': 0.9392852783203125} 08/31/2021 15:27:50 - INFO - __main__ - Step 144651: {'lr': 1.610375255341523e-06, 'samples': 27772992, 'steps': 144650, 'loss/train': 1.8287243843078613} 08/31/2021 15:27:52 - INFO - __main__ - Step 144652: {'lr': 1.6097739490021634e-06, 'samples': 27773184, 'steps': 144651, 'loss/train': 1.4323153495788574} 08/31/2021 15:27:52 - INFO - __main__ - Step 144653: {'lr': 1.60917275458361e-06, 'samples': 27773376, 'steps': 144652, 'loss/train': 1.070042610168457} 08/31/2021 15:27:53 - INFO - __main__ - Step 144654: {'lr': 1.608571672086112e-06, 'samples': 27773568, 'steps': 144653, 'loss/train': 2.0956897735595703} 08/31/2021 15:27:53 - INFO - __main__ - Step 144655: {'lr': 1.6079707015099755e-06, 'samples': 27773760, 'steps': 144654, 'loss/train': 0.4580603837966919} 08/31/2021 15:27:53 - INFO - __main__ - Step 144656: {'lr': 1.6073698428554494e-06, 'samples': 27773952, 'steps': 144655, 'loss/train': 0.8602921366691589} 08/31/2021 15:27:55 - INFO - __main__ - Step 144657: {'lr': 1.6067690961228398e-06, 'samples': 27774144, 'steps': 144656, 'loss/train': 2.8769843578338623} 08/31/2021 15:27:55 - INFO - __main__ - Step 144658: {'lr': 1.6061684613123407e-06, 'samples': 27774336, 'steps': 144657, 'loss/train': 1.0817890167236328} 08/31/2021 15:27:56 - INFO - __main__ - Step 144659: {'lr': 1.605567938424285e-06, 'samples': 27774528, 'steps': 144658, 'loss/train': 1.2329258918762207} 08/31/2021 15:27:56 - INFO - __main__ - Step 144660: {'lr': 1.6049675274589503e-06, 'samples': 27774720, 'steps': 144659, 'loss/train': 1.0506718158721924} 08/31/2021 15:27:56 - INFO - __main__ - Step 144661: {'lr': 1.604367228416559e-06, 'samples': 27774912, 'steps': 144660, 'loss/train': 1.0225646495819092} 08/31/2021 15:27:57 - INFO - __main__ - Step 144662: {'lr': 1.603767041297416e-06, 'samples': 27775104, 'steps': 144661, 'loss/train': 0.36540764570236206} 08/31/2021 15:27:58 - INFO - __main__ - Step 144663: {'lr': 1.6031669661017712e-06, 'samples': 27775296, 'steps': 144662, 'loss/train': 0.8478705883026123} 08/31/2021 15:27:59 - INFO - __main__ - Step 144664: {'lr': 1.60256700282993e-06, 'samples': 27775488, 'steps': 144663, 'loss/train': 1.564232349395752} 08/31/2021 15:27:59 - INFO - __main__ - Step 144665: {'lr': 1.6019671514821145e-06, 'samples': 27775680, 'steps': 144664, 'loss/train': 0.893753170967102} 08/31/2021 15:28:00 - INFO - __main__ - Step 144666: {'lr': 1.6013674120586297e-06, 'samples': 27775872, 'steps': 144665, 'loss/train': 0.07951977103948593} 08/31/2021 15:28:00 - INFO - __main__ - Step 144667: {'lr': 1.6007677845597257e-06, 'samples': 27776064, 'steps': 144666, 'loss/train': 0.8429645299911499} 08/31/2021 15:28:01 - INFO - __main__ - Step 144668: {'lr': 1.6001682689857077e-06, 'samples': 27776256, 'steps': 144667, 'loss/train': 1.2498817443847656} 08/31/2021 15:28:02 - INFO - __main__ - Step 144669: {'lr': 1.5995688653367978e-06, 'samples': 27776448, 'steps': 144668, 'loss/train': 0.8494486808776855} 08/31/2021 15:28:02 - INFO - __main__ - Step 144670: {'lr': 1.5989695736133013e-06, 'samples': 27776640, 'steps': 144669, 'loss/train': 0.734678328037262} 08/31/2021 15:28:03 - INFO - __main__ - Step 144671: {'lr': 1.5983703938154681e-06, 'samples': 27776832, 'steps': 144670, 'loss/train': 1.4967440366744995} 08/31/2021 15:28:03 - INFO - __main__ - Step 144672: {'lr': 1.5977713259435755e-06, 'samples': 27777024, 'steps': 144671, 'loss/train': 1.7290462255477905} 08/31/2021 15:28:05 - INFO - __main__ - Step 144673: {'lr': 1.5971723699979013e-06, 'samples': 27777216, 'steps': 144672, 'loss/train': 1.1501461267471313} 08/31/2021 15:28:05 - INFO - __main__ - Step 144674: {'lr': 1.596573525978695e-06, 'samples': 27777408, 'steps': 144673, 'loss/train': 0.3989434838294983} 08/31/2021 15:28:05 - INFO - __main__ - Step 144675: {'lr': 1.5959747938862624e-06, 'samples': 27777600, 'steps': 144674, 'loss/train': 1.388984203338623} 08/31/2021 15:28:06 - INFO - __main__ - Step 144676: {'lr': 1.595376173720825e-06, 'samples': 27777792, 'steps': 144675, 'loss/train': 0.9966038465499878} 08/31/2021 15:28:06 - INFO - __main__ - Step 144677: {'lr': 1.5947776654826884e-06, 'samples': 27777984, 'steps': 144676, 'loss/train': 1.0292363166809082} 08/31/2021 15:28:07 - INFO - __main__ - Step 144678: {'lr': 1.5941792691721302e-06, 'samples': 27778176, 'steps': 144677, 'loss/train': 0.6394853591918945} 08/31/2021 15:28:08 - INFO - __main__ - Step 144679: {'lr': 1.5935809847893724e-06, 'samples': 27778368, 'steps': 144678, 'loss/train': 1.2356071472167969} 08/31/2021 15:28:08 - INFO - __main__ - Step 144680: {'lr': 1.59298281233472e-06, 'samples': 27778560, 'steps': 144679, 'loss/train': 1.007953405380249} 08/31/2021 15:28:09 - INFO - __main__ - Step 144681: {'lr': 1.592384751808451e-06, 'samples': 27778752, 'steps': 144680, 'loss/train': 0.09521235525608063} 08/31/2021 15:28:09 - INFO - __main__ - Step 144682: {'lr': 1.591786803210815e-06, 'samples': 27778944, 'steps': 144681, 'loss/train': 1.4549998044967651} 08/31/2021 15:28:09 - INFO - __main__ - Step 144683: {'lr': 1.5911889665420898e-06, 'samples': 27779136, 'steps': 144682, 'loss/train': 1.1714928150177002} 08/31/2021 15:28:11 - INFO - __main__ - Step 144684: {'lr': 1.5905912418025524e-06, 'samples': 27779328, 'steps': 144683, 'loss/train': 1.1322423219680786} 08/31/2021 15:28:11 - INFO - __main__ - Step 144685: {'lr': 1.5899936289924255e-06, 'samples': 27779520, 'steps': 144684, 'loss/train': 1.4204334020614624} 08/31/2021 15:28:12 - INFO - __main__ - Step 144686: {'lr': 1.5893961281120416e-06, 'samples': 27779712, 'steps': 144685, 'loss/train': 0.8836378455162048} 08/31/2021 15:28:12 - INFO - __main__ - Step 144687: {'lr': 1.5887987391616231e-06, 'samples': 27779904, 'steps': 144686, 'loss/train': 1.2406585216522217} 08/31/2021 15:28:12 - INFO - __main__ - Step 144688: {'lr': 1.5882014621414754e-06, 'samples': 27780096, 'steps': 144687, 'loss/train': 0.7716458439826965} 08/31/2021 15:28:14 - INFO - __main__ - Step 144689: {'lr': 1.5876042970518478e-06, 'samples': 27780288, 'steps': 144688, 'loss/train': 0.028792552649974823} 08/31/2021 15:28:15 - INFO - __main__ - Step 144690: {'lr': 1.5870072438930183e-06, 'samples': 27780480, 'steps': 144689, 'loss/train': 1.0928030014038086} 08/31/2021 15:28:15 - INFO - __main__ - Step 144691: {'lr': 1.5864103026652367e-06, 'samples': 27780672, 'steps': 144690, 'loss/train': 1.2368965148925781} 08/31/2021 15:28:15 - INFO - __main__ - Step 144692: {'lr': 1.5858134733687801e-06, 'samples': 27780864, 'steps': 144691, 'loss/train': 1.6206316947937012} 08/31/2021 15:28:16 - INFO - __main__ - Step 144693: {'lr': 1.5852167560039265e-06, 'samples': 27781056, 'steps': 144692, 'loss/train': 0.08116088062524796} 08/31/2021 15:28:18 - INFO - __main__ - Step 144694: {'lr': 1.5846201505709534e-06, 'samples': 27781248, 'steps': 144693, 'loss/train': 1.1221317052841187} 08/31/2021 15:28:18 - INFO - __main__ - Step 144695: {'lr': 1.5840236570701106e-06, 'samples': 27781440, 'steps': 144694, 'loss/train': 0.6731188297271729} 08/31/2021 15:28:19 - INFO - __main__ - Step 144696: {'lr': 1.5834272755016755e-06, 'samples': 27781632, 'steps': 144695, 'loss/train': 0.9484378099441528} 08/31/2021 15:28:19 - INFO - __main__ - Step 144697: {'lr': 1.5828310058659256e-06, 'samples': 27781824, 'steps': 144696, 'loss/train': 0.8658807277679443} 08/31/2021 15:28:19 - INFO - __main__ - Step 144698: {'lr': 1.582234848163111e-06, 'samples': 27782016, 'steps': 144697, 'loss/train': 0.7725310325622559} 08/31/2021 15:28:20 - INFO - __main__ - Step 144699: {'lr': 1.581638802393509e-06, 'samples': 27782208, 'steps': 144698, 'loss/train': 1.0475223064422607} 08/31/2021 15:28:22 - INFO - __main__ - Step 144700: {'lr': 1.5810428685573698e-06, 'samples': 27782400, 'steps': 144699, 'loss/train': 1.2491587400436401} 08/31/2021 15:28:23 - INFO - __main__ - Step 144701: {'lr': 1.580447046654998e-06, 'samples': 27782592, 'steps': 144700, 'loss/train': 1.5679826736450195} 08/31/2021 15:28:23 - INFO - __main__ - Step 144702: {'lr': 1.579851336686644e-06, 'samples': 27782784, 'steps': 144701, 'loss/train': 1.4512195587158203} 08/31/2021 15:28:23 - INFO - __main__ - Step 144703: {'lr': 1.5792557386525574e-06, 'samples': 27782976, 'steps': 144702, 'loss/train': 1.187706708908081} 08/31/2021 15:28:24 - INFO - __main__ - Step 144704: {'lr': 1.5786602525530435e-06, 'samples': 27783168, 'steps': 144703, 'loss/train': 1.161070466041565} 08/31/2021 15:28:25 - INFO - __main__ - Step 144705: {'lr': 1.5780648783883522e-06, 'samples': 27783360, 'steps': 144704, 'loss/train': 0.039619285613298416} 08/31/2021 15:28:26 - INFO - __main__ - Step 144706: {'lr': 1.5774696161587332e-06, 'samples': 27783552, 'steps': 144705, 'loss/train': 1.0050208568572998} 08/31/2021 15:28:26 - INFO - __main__ - Step 144707: {'lr': 1.5768744658644919e-06, 'samples': 27783744, 'steps': 144706, 'loss/train': 1.3305050134658813} 08/31/2021 15:28:26 - INFO - __main__ - Step 144708: {'lr': 1.57627942750585e-06, 'samples': 27783936, 'steps': 144707, 'loss/train': 1.1957942247390747} 08/31/2021 15:28:27 - INFO - __main__ - Step 144709: {'lr': 1.5756845010831412e-06, 'samples': 27784128, 'steps': 144708, 'loss/train': 1.3909506797790527} 08/31/2021 15:28:28 - INFO - __main__ - Step 144710: {'lr': 1.5750896865965592e-06, 'samples': 27784320, 'steps': 144709, 'loss/train': 1.2449079751968384} 08/31/2021 15:28:29 - INFO - __main__ - Step 144711: {'lr': 1.5744949840464372e-06, 'samples': 27784512, 'steps': 144710, 'loss/train': 1.0306719541549683} 08/31/2021 15:28:29 - INFO - __main__ - Step 144712: {'lr': 1.5739003934329977e-06, 'samples': 27784704, 'steps': 144711, 'loss/train': 0.9626026749610901} 08/31/2021 15:28:29 - INFO - __main__ - Step 144713: {'lr': 1.5733059147565454e-06, 'samples': 27784896, 'steps': 144712, 'loss/train': 1.873079538345337} 08/31/2021 15:28:30 - INFO - __main__ - Step 144714: {'lr': 1.5727115480173027e-06, 'samples': 27785088, 'steps': 144713, 'loss/train': 1.535658359527588} 08/31/2021 15:28:31 - INFO - __main__ - Step 144715: {'lr': 1.5721172932155746e-06, 'samples': 27785280, 'steps': 144714, 'loss/train': 0.3704327940940857} 08/31/2021 15:28:32 - INFO - __main__ - Step 144716: {'lr': 1.5715231503516114e-06, 'samples': 27785472, 'steps': 144715, 'loss/train': 0.5059962272644043} 08/31/2021 15:28:32 - INFO - __main__ - Step 144717: {'lr': 1.5709291194256903e-06, 'samples': 27785664, 'steps': 144716, 'loss/train': 1.6573694944381714} 08/31/2021 15:28:32 - INFO - __main__ - Step 144718: {'lr': 1.5703352004380889e-06, 'samples': 27785856, 'steps': 144717, 'loss/train': 1.019164800643921} 08/31/2021 15:28:33 - INFO - __main__ - Step 144719: {'lr': 1.5697413933890292e-06, 'samples': 27786048, 'steps': 144718, 'loss/train': 1.175014853477478} 08/31/2021 15:28:34 - INFO - __main__ - Step 144720: {'lr': 1.5691476982788445e-06, 'samples': 27786240, 'steps': 144719, 'loss/train': 0.0203896202147007} 08/31/2021 15:28:35 - INFO - __main__ - Step 144721: {'lr': 1.5685541151077566e-06, 'samples': 27786432, 'steps': 144720, 'loss/train': 1.2886850833892822} 08/31/2021 15:28:35 - INFO - __main__ - Step 144722: {'lr': 1.5679606438760152e-06, 'samples': 27786624, 'steps': 144721, 'loss/train': 0.8663396239280701} 08/31/2021 15:28:35 - INFO - __main__ - Step 144723: {'lr': 1.5673672845839538e-06, 'samples': 27786816, 'steps': 144722, 'loss/train': 1.4279743432998657} 08/31/2021 15:28:36 - INFO - __main__ - Step 144724: {'lr': 1.566774037231794e-06, 'samples': 27787008, 'steps': 144723, 'loss/train': 1.1698583364486694} 08/31/2021 15:28:37 - INFO - __main__ - Step 144725: {'lr': 1.5661809018198138e-06, 'samples': 27787200, 'steps': 144724, 'loss/train': 2.2830123901367188} 08/31/2021 15:28:38 - INFO - __main__ - Step 144726: {'lr': 1.5655878783482902e-06, 'samples': 27787392, 'steps': 144725, 'loss/train': 0.9740299582481384} 08/31/2021 15:28:38 - INFO - __main__ - Step 144727: {'lr': 1.5649949668174457e-06, 'samples': 27787584, 'steps': 144726, 'loss/train': 0.8096803426742554} 08/31/2021 15:28:38 - INFO - __main__ - Step 144728: {'lr': 1.5644021672276131e-06, 'samples': 27787776, 'steps': 144727, 'loss/train': 1.4189634323120117} 08/31/2021 15:28:39 - INFO - __main__ - Step 144729: {'lr': 1.5638094795790147e-06, 'samples': 27787968, 'steps': 144728, 'loss/train': 1.3870625495910645} 08/31/2021 15:28:40 - INFO - __main__ - Step 144730: {'lr': 1.563216903871928e-06, 'samples': 27788160, 'steps': 144729, 'loss/train': 1.3948816061019897} 08/31/2021 15:28:41 - INFO - __main__ - Step 144731: {'lr': 1.5626244401066302e-06, 'samples': 27788352, 'steps': 144730, 'loss/train': 1.2296464443206787} 08/31/2021 15:28:41 - INFO - __main__ - Step 144732: {'lr': 1.5620320882833717e-06, 'samples': 27788544, 'steps': 144731, 'loss/train': 0.8537009954452515} 08/31/2021 15:28:41 - INFO - __main__ - Step 144733: {'lr': 1.5614398484024295e-06, 'samples': 27788736, 'steps': 144732, 'loss/train': 0.8711768984794617} 08/31/2021 15:28:42 - INFO - __main__ - Step 144734: {'lr': 1.5608477204640536e-06, 'samples': 27788928, 'steps': 144733, 'loss/train': 0.5074065327644348} 08/31/2021 15:28:44 - INFO - __main__ - Step 144735: {'lr': 1.5602557044685496e-06, 'samples': 27789120, 'steps': 144734, 'loss/train': 1.4186813831329346} 08/31/2021 15:28:44 - INFO - __main__ - Step 144736: {'lr': 1.559663800416139e-06, 'samples': 27789312, 'steps': 144735, 'loss/train': 0.886302649974823} 08/31/2021 15:28:45 - INFO - __main__ - Step 144737: {'lr': 1.5590720083071275e-06, 'samples': 27789504, 'steps': 144736, 'loss/train': 0.015701089054346085} 08/31/2021 15:28:45 - INFO - __main__ - Step 144738: {'lr': 1.5584803281417647e-06, 'samples': 27789696, 'steps': 144737, 'loss/train': 1.2794716358184814} 08/31/2021 15:28:45 - INFO - __main__ - Step 144739: {'lr': 1.5578887599203283e-06, 'samples': 27789888, 'steps': 144738, 'loss/train': 1.467657446861267} 08/31/2021 15:28:46 - INFO - __main__ - Step 144740: {'lr': 1.5572973036430405e-06, 'samples': 27790080, 'steps': 144739, 'loss/train': 1.0493236780166626} 08/31/2021 15:28:47 - INFO - __main__ - Step 144741: {'lr': 1.556705959310234e-06, 'samples': 27790272, 'steps': 144740, 'loss/train': 0.8618087768554688} 08/31/2021 15:28:48 - INFO - __main__ - Step 144742: {'lr': 1.556114726922131e-06, 'samples': 27790464, 'steps': 144741, 'loss/train': 1.6550565958023071} 08/31/2021 15:28:48 - INFO - __main__ - Step 144743: {'lr': 1.5555236064789813e-06, 'samples': 27790656, 'steps': 144742, 'loss/train': 0.9514336585998535} 08/31/2021 15:28:49 - INFO - __main__ - Step 144744: {'lr': 1.554932597981118e-06, 'samples': 27790848, 'steps': 144743, 'loss/train': 0.026554252952337265} 08/31/2021 15:28:49 - INFO - __main__ - Step 144745: {'lr': 1.5543417014287353e-06, 'samples': 27791040, 'steps': 144744, 'loss/train': 0.09850951284170151} 08/31/2021 15:28:49 - INFO - __main__ - Step 144746: {'lr': 1.5537509168221665e-06, 'samples': 27791232, 'steps': 144745, 'loss/train': 1.5339696407318115} 08/31/2021 15:28:51 - INFO - __main__ - Step 144747: {'lr': 1.5531602441616332e-06, 'samples': 27791424, 'steps': 144746, 'loss/train': 1.4387863874435425} 08/31/2021 15:28:51 - INFO - __main__ - Step 144748: {'lr': 1.5525696834473857e-06, 'samples': 27791616, 'steps': 144747, 'loss/train': 0.7530081868171692} 08/31/2021 15:28:52 - INFO - __main__ - Step 144749: {'lr': 1.5519792346797568e-06, 'samples': 27791808, 'steps': 144748, 'loss/train': 1.4343905448913574} 08/31/2021 15:28:52 - INFO - __main__ - Step 144750: {'lr': 1.5513888978589407e-06, 'samples': 27792000, 'steps': 144749, 'loss/train': 0.3955624997615814} 08/31/2021 15:28:52 - INFO - __main__ - Step 144751: {'lr': 1.550798672985243e-06, 'samples': 27792192, 'steps': 144750, 'loss/train': 1.435219407081604} 08/31/2021 15:28:54 - INFO - __main__ - Step 144752: {'lr': 1.5502085600589411e-06, 'samples': 27792384, 'steps': 144751, 'loss/train': 0.3315712809562683} 08/31/2021 15:28:55 - INFO - __main__ - Step 144753: {'lr': 1.549618559080257e-06, 'samples': 27792576, 'steps': 144752, 'loss/train': 1.190575122833252} 08/31/2021 15:28:55 - INFO - __main__ - Step 144754: {'lr': 1.549028670049496e-06, 'samples': 27792768, 'steps': 144753, 'loss/train': 0.37799763679504395} 08/31/2021 15:28:56 - INFO - __main__ - Step 144755: {'lr': 1.548438892966908e-06, 'samples': 27792960, 'steps': 144754, 'loss/train': 0.8677529692649841} 08/31/2021 15:28:56 - INFO - __main__ - Step 144756: {'lr': 1.5478492278327426e-06, 'samples': 27793152, 'steps': 144755, 'loss/train': 0.09543292224407196} 08/31/2021 15:28:58 - INFO - __main__ - Step 144757: {'lr': 1.5472596746473056e-06, 'samples': 27793344, 'steps': 144756, 'loss/train': 1.3294274806976318} 08/31/2021 15:28:58 - INFO - __main__ - Step 144758: {'lr': 1.5466702334108185e-06, 'samples': 27793536, 'steps': 144757, 'loss/train': 1.0107394456863403} 08/31/2021 15:28:59 - INFO - __main__ - Step 144759: {'lr': 1.5460809041235591e-06, 'samples': 27793728, 'steps': 144758, 'loss/train': 0.9864488244056702} 08/31/2021 15:28:59 - INFO - __main__ - Step 144760: {'lr': 1.5454916867858327e-06, 'samples': 27793920, 'steps': 144759, 'loss/train': 0.19800546765327454} 08/31/2021 15:28:59 - INFO - __main__ - Step 144761: {'lr': 1.5449025813978613e-06, 'samples': 27794112, 'steps': 144760, 'loss/train': 0.8435027003288269} 08/31/2021 15:29:00 - INFO - __main__ - Step 144762: {'lr': 1.5443135879599224e-06, 'samples': 27794304, 'steps': 144761, 'loss/train': 1.7421849966049194} 08/31/2021 15:29:01 - INFO - __main__ - Step 144763: {'lr': 1.5437247064722937e-06, 'samples': 27794496, 'steps': 144762, 'loss/train': 1.3809654712677002} 08/31/2021 15:29:02 - INFO - __main__ - Step 144764: {'lr': 1.543135936935225e-06, 'samples': 27794688, 'steps': 144763, 'loss/train': 0.9409404993057251} 08/31/2021 15:29:02 - INFO - __main__ - Step 144765: {'lr': 1.5425472793489659e-06, 'samples': 27794880, 'steps': 144764, 'loss/train': 0.7671105861663818} 08/31/2021 15:29:02 - INFO - __main__ - Step 144766: {'lr': 1.541958733713822e-06, 'samples': 27795072, 'steps': 144765, 'loss/train': 0.8871117234230042} 08/31/2021 15:29:03 - INFO - __main__ - Step 144767: {'lr': 1.541370300030015e-06, 'samples': 27795264, 'steps': 144766, 'loss/train': 1.3722468614578247} 08/31/2021 15:29:03 - INFO - __main__ - Step 144768: {'lr': 1.5407819782978504e-06, 'samples': 27795456, 'steps': 144767, 'loss/train': 1.2267967462539673} 08/31/2021 15:29:05 - INFO - __main__ - Step 144769: {'lr': 1.5401937685175781e-06, 'samples': 27795648, 'steps': 144768, 'loss/train': 0.48614078760147095} 08/31/2021 15:29:05 - INFO - __main__ - Step 144770: {'lr': 1.5396056706894478e-06, 'samples': 27795840, 'steps': 144769, 'loss/train': 1.113306999206543} 08/31/2021 15:29:05 - INFO - __main__ - Step 144771: {'lr': 1.5390176848137371e-06, 'samples': 27796032, 'steps': 144770, 'loss/train': 0.8095574975013733} 08/31/2021 15:29:06 - INFO - __main__ - Step 144772: {'lr': 1.5384298108907236e-06, 'samples': 27796224, 'steps': 144771, 'loss/train': 1.2423149347305298} 08/31/2021 15:29:06 - INFO - __main__ - Step 144773: {'lr': 1.5378420489206568e-06, 'samples': 27796416, 'steps': 144772, 'loss/train': 0.7086910605430603} 08/31/2021 15:29:08 - INFO - __main__ - Step 144774: {'lr': 1.5372543989037867e-06, 'samples': 27796608, 'steps': 144773, 'loss/train': 0.9128066897392273} 08/31/2021 15:29:08 - INFO - __main__ - Step 144775: {'lr': 1.5366668608404188e-06, 'samples': 27796800, 'steps': 144774, 'loss/train': 0.9450587630271912} 08/31/2021 15:29:08 - INFO - __main__ - Step 144776: {'lr': 1.5360794347307749e-06, 'samples': 27796992, 'steps': 144775, 'loss/train': 1.2528613805770874} 08/31/2021 15:29:09 - INFO - __main__ - Step 144777: {'lr': 1.5354921205751603e-06, 'samples': 27797184, 'steps': 144776, 'loss/train': 1.3382140398025513} 08/31/2021 15:29:09 - INFO - __main__ - Step 144778: {'lr': 1.5349049183737973e-06, 'samples': 27797376, 'steps': 144777, 'loss/train': 1.217680811882019} 08/31/2021 15:29:11 - INFO - __main__ - Step 144779: {'lr': 1.534317828126991e-06, 'samples': 27797568, 'steps': 144778, 'loss/train': 0.8034261465072632} 08/31/2021 15:29:11 - INFO - __main__ - Step 144780: {'lr': 1.5337308498349911e-06, 'samples': 27797760, 'steps': 144779, 'loss/train': 0.7401661276817322} 08/31/2021 15:29:11 - INFO - __main__ - Step 144781: {'lr': 1.5331439834980477e-06, 'samples': 27797952, 'steps': 144780, 'loss/train': 1.0720338821411133} 08/31/2021 15:29:12 - INFO - __main__ - Step 144782: {'lr': 1.5325572291164102e-06, 'samples': 27798144, 'steps': 144781, 'loss/train': 1.5913400650024414} 08/31/2021 15:29:12 - INFO - __main__ - Step 144783: {'lr': 1.531970586690412e-06, 'samples': 27798336, 'steps': 144782, 'loss/train': 1.381583333015442} 08/31/2021 15:29:14 - INFO - __main__ - Step 144784: {'lr': 1.5313840562202475e-06, 'samples': 27798528, 'steps': 144783, 'loss/train': 0.996282696723938} 08/31/2021 15:29:14 - INFO - __main__ - Step 144785: {'lr': 1.5307976377062216e-06, 'samples': 27798720, 'steps': 144784, 'loss/train': 0.4827715754508972} 08/31/2021 15:29:14 - INFO - __main__ - Step 144786: {'lr': 1.5302113311485843e-06, 'samples': 27798912, 'steps': 144785, 'loss/train': 1.201194405555725} 08/31/2021 15:29:15 - INFO - __main__ - Step 144787: {'lr': 1.5296251365475855e-06, 'samples': 27799104, 'steps': 144786, 'loss/train': 0.7239636778831482} 08/31/2021 15:29:15 - INFO - __main__ - Step 144788: {'lr': 1.5290390539035027e-06, 'samples': 27799296, 'steps': 144787, 'loss/train': 1.7537181377410889} 08/31/2021 15:29:17 - INFO - __main__ - Step 144789: {'lr': 1.5284530832166132e-06, 'samples': 27799488, 'steps': 144788, 'loss/train': 1.3899860382080078} 08/31/2021 15:29:17 - INFO - __main__ - Step 144790: {'lr': 1.5278672244871671e-06, 'samples': 27799680, 'steps': 144789, 'loss/train': 0.9918471574783325} 08/31/2021 15:29:17 - INFO - __main__ - Step 144791: {'lr': 1.5272814777154142e-06, 'samples': 27799872, 'steps': 144790, 'loss/train': 1.2795658111572266} 08/31/2021 15:29:18 - INFO - __main__ - Step 144792: {'lr': 1.5266958429016597e-06, 'samples': 27800064, 'steps': 144791, 'loss/train': 1.641595482826233} 08/31/2021 15:29:18 - INFO - __main__ - Step 144793: {'lr': 1.5261103200461257e-06, 'samples': 27800256, 'steps': 144792, 'loss/train': 1.354115605354309} 08/31/2021 15:29:20 - INFO - __main__ - Step 144794: {'lr': 1.5255249091490897e-06, 'samples': 27800448, 'steps': 144793, 'loss/train': 1.2768419981002808} 08/31/2021 15:29:21 - INFO - __main__ - Step 144795: {'lr': 1.5249396102108294e-06, 'samples': 27800640, 'steps': 144794, 'loss/train': 1.2696856260299683} 08/31/2021 15:29:21 - INFO - __main__ - Step 144796: {'lr': 1.5243544232315942e-06, 'samples': 27800832, 'steps': 144795, 'loss/train': 1.109387755393982} 08/31/2021 15:29:21 - INFO - __main__ - Step 144797: {'lr': 1.5237693482116345e-06, 'samples': 27801024, 'steps': 144796, 'loss/train': 0.8023906350135803} 08/31/2021 15:29:22 - INFO - __main__ - Step 144798: {'lr': 1.523184385151255e-06, 'samples': 27801216, 'steps': 144797, 'loss/train': 1.0448355674743652} 08/31/2021 15:29:22 - INFO - __main__ - Step 144799: {'lr': 1.5225995340506782e-06, 'samples': 27801408, 'steps': 144798, 'loss/train': 0.022185923531651497} 08/31/2021 15:29:22 - INFO - __main__ - Step 144800: {'lr': 1.5220147949101815e-06, 'samples': 27801600, 'steps': 144799, 'loss/train': 0.6963250041007996} 08/31/2021 15:29:24 - INFO - __main__ - Step 144801: {'lr': 1.5214301677300425e-06, 'samples': 27801792, 'steps': 144800, 'loss/train': 0.09108814597129822} 08/31/2021 15:29:24 - INFO - __main__ - Step 144802: {'lr': 1.5208456525105107e-06, 'samples': 27801984, 'steps': 144801, 'loss/train': 1.2502920627593994} 08/31/2021 15:29:25 - INFO - __main__ - Step 144803: {'lr': 1.5202612492518365e-06, 'samples': 27802176, 'steps': 144802, 'loss/train': 0.589115560054779} 08/31/2021 15:29:25 - INFO - __main__ - Step 144804: {'lr': 1.5196769579542967e-06, 'samples': 27802368, 'steps': 144803, 'loss/train': 0.9208965301513672} 08/31/2021 15:29:25 - INFO - __main__ - Step 144805: {'lr': 1.5190927786181973e-06, 'samples': 27802560, 'steps': 144804, 'loss/train': 1.1066049337387085} 08/31/2021 15:29:28 - INFO - __main__ - Step 144806: {'lr': 1.5185087112437323e-06, 'samples': 27802752, 'steps': 144805, 'loss/train': 1.0819281339645386} 08/31/2021 15:29:28 - INFO - __main__ - Step 144807: {'lr': 1.5179247558311793e-06, 'samples': 27802944, 'steps': 144806, 'loss/train': 1.6110482215881348} 08/31/2021 15:29:28 - INFO - __main__ - Step 144808: {'lr': 1.5173409123808434e-06, 'samples': 27803136, 'steps': 144807, 'loss/train': 0.6717273592948914} 08/31/2021 15:29:29 - INFO - __main__ - Step 144809: {'lr': 1.516757180892947e-06, 'samples': 27803328, 'steps': 144808, 'loss/train': 1.0303826332092285} 08/31/2021 15:29:29 - INFO - __main__ - Step 144810: {'lr': 1.5161735613677397e-06, 'samples': 27803520, 'steps': 144809, 'loss/train': 1.3143006563186646} 08/31/2021 15:29:31 - INFO - __main__ - Step 144811: {'lr': 1.5155900538055546e-06, 'samples': 27803712, 'steps': 144810, 'loss/train': 0.3276086747646332} 08/31/2021 15:29:31 - INFO - __main__ - Step 144812: {'lr': 1.5150066582065857e-06, 'samples': 27803904, 'steps': 144811, 'loss/train': 0.5858139395713806} 08/31/2021 15:29:31 - INFO - __main__ - Step 144813: {'lr': 1.514423374571111e-06, 'samples': 27804096, 'steps': 144812, 'loss/train': 0.7150455713272095} 08/31/2021 15:29:32 - INFO - __main__ - Step 144814: {'lr': 1.5138402028994081e-06, 'samples': 27804288, 'steps': 144813, 'loss/train': 1.3002393245697021} 08/31/2021 15:29:32 - INFO - __main__ - Step 144815: {'lr': 1.5132571431917541e-06, 'samples': 27804480, 'steps': 144814, 'loss/train': 1.4542574882507324} 08/31/2021 15:29:34 - INFO - __main__ - Step 144816: {'lr': 1.5126741954483714e-06, 'samples': 27804672, 'steps': 144815, 'loss/train': 1.1075891256332397} 08/31/2021 15:29:34 - INFO - __main__ - Step 144817: {'lr': 1.5120913596695651e-06, 'samples': 27804864, 'steps': 144816, 'loss/train': 1.6921292543411255} 08/31/2021 15:29:34 - INFO - __main__ - Step 144818: {'lr': 1.5115086358555574e-06, 'samples': 27805056, 'steps': 144817, 'loss/train': 0.9700313806533813} 08/31/2021 15:29:35 - INFO - __main__ - Step 144819: {'lr': 1.5109260240066536e-06, 'samples': 27805248, 'steps': 144818, 'loss/train': 1.0327171087265015} 08/31/2021 15:29:35 - INFO - __main__ - Step 144820: {'lr': 1.5103435241230757e-06, 'samples': 27805440, 'steps': 144819, 'loss/train': 1.4955836534500122} 08/31/2021 15:29:36 - INFO - __main__ - Step 144821: {'lr': 1.5097611362051012e-06, 'samples': 27805632, 'steps': 144820, 'loss/train': 0.93947434425354} 08/31/2021 15:29:37 - INFO - __main__ - Step 144822: {'lr': 1.50917886025298e-06, 'samples': 27805824, 'steps': 144821, 'loss/train': 1.1183600425720215} 08/31/2021 15:29:38 - INFO - __main__ - Step 144823: {'lr': 1.5085966962669896e-06, 'samples': 27806016, 'steps': 144822, 'loss/train': 1.545547604560852} 08/31/2021 15:29:38 - INFO - __main__ - Step 144824: {'lr': 1.5080146442474075e-06, 'samples': 27806208, 'steps': 144823, 'loss/train': 1.4168423414230347} 08/31/2021 15:29:38 - INFO - __main__ - Step 144825: {'lr': 1.5074327041944834e-06, 'samples': 27806400, 'steps': 144824, 'loss/train': 1.6176809072494507} 08/31/2021 15:29:39 - INFO - __main__ - Step 144826: {'lr': 1.5068508761084677e-06, 'samples': 27806592, 'steps': 144825, 'loss/train': 1.2818719148635864} 08/31/2021 15:29:40 - INFO - __main__ - Step 144827: {'lr': 1.5062691599896372e-06, 'samples': 27806784, 'steps': 144826, 'loss/train': 1.3357914686203003} 08/31/2021 15:29:41 - INFO - __main__ - Step 144828: {'lr': 1.5056875558382144e-06, 'samples': 27806976, 'steps': 144827, 'loss/train': 0.9111418128013611} 08/31/2021 15:29:41 - INFO - __main__ - Step 144829: {'lr': 1.505106063654532e-06, 'samples': 27807168, 'steps': 144828, 'loss/train': 1.0446875095367432} 08/31/2021 15:29:41 - INFO - __main__ - Step 144830: {'lr': 1.5045246834388126e-06, 'samples': 27807360, 'steps': 144829, 'loss/train': 1.2339931726455688} 08/31/2021 15:29:42 - INFO - __main__ - Step 144831: {'lr': 1.5039434151913055e-06, 'samples': 27807552, 'steps': 144830, 'loss/train': 0.3778100311756134} 08/31/2021 15:29:44 - INFO - __main__ - Step 144832: {'lr': 1.5033622589122885e-06, 'samples': 27807744, 'steps': 144831, 'loss/train': 0.3295924663543701} 08/31/2021 15:29:44 - INFO - __main__ - Step 144833: {'lr': 1.5027812146020391e-06, 'samples': 27807936, 'steps': 144832, 'loss/train': 1.7565102577209473} 08/31/2021 15:29:44 - INFO - __main__ - Step 144834: {'lr': 1.5022002822607794e-06, 'samples': 27808128, 'steps': 144833, 'loss/train': 0.8071702122688293} 08/31/2021 15:29:45 - INFO - __main__ - Step 144835: {'lr': 1.5016194618888147e-06, 'samples': 27808320, 'steps': 144834, 'loss/train': 0.9699976444244385} 08/31/2021 15:29:45 - INFO - __main__ - Step 144836: {'lr': 1.5010387534863667e-06, 'samples': 27808512, 'steps': 144835, 'loss/train': 1.048069715499878} 08/31/2021 15:29:45 - INFO - __main__ - Step 144837: {'lr': 1.5004581570537136e-06, 'samples': 27808704, 'steps': 144836, 'loss/train': 0.8994148373603821} 08/31/2021 15:29:47 - INFO - __main__ - Step 144838: {'lr': 1.4998776725911324e-06, 'samples': 27808896, 'steps': 144837, 'loss/train': 1.6325753927230835} 08/31/2021 15:29:47 - INFO - __main__ - Step 144839: {'lr': 1.499297300098873e-06, 'samples': 27809088, 'steps': 144838, 'loss/train': 0.8654227256774902} 08/31/2021 15:29:48 - INFO - __main__ - Step 144840: {'lr': 1.4987170395771854e-06, 'samples': 27809280, 'steps': 144839, 'loss/train': 0.7346940040588379} 08/31/2021 15:29:48 - INFO - __main__ - Step 144841: {'lr': 1.4981368910263472e-06, 'samples': 27809472, 'steps': 144840, 'loss/train': 1.0473805665969849} 08/31/2021 15:29:48 - INFO - __main__ - Step 144842: {'lr': 1.497556854446608e-06, 'samples': 27809664, 'steps': 144841, 'loss/train': 0.49377235770225525} 08/31/2021 15:29:50 - INFO - __main__ - Step 144843: {'lr': 1.4969769298382453e-06, 'samples': 27809856, 'steps': 144842, 'loss/train': 0.9974554181098938} 08/31/2021 15:29:50 - INFO - __main__ - Step 144844: {'lr': 1.4963971172014812e-06, 'samples': 27810048, 'steps': 144843, 'loss/train': 0.9338001608848572} 08/31/2021 15:29:51 - INFO - __main__ - Step 144845: {'lr': 1.495817416536649e-06, 'samples': 27810240, 'steps': 144844, 'loss/train': 1.465160846710205} 08/31/2021 15:29:51 - INFO - __main__ - Step 144846: {'lr': 1.4952378278439428e-06, 'samples': 27810432, 'steps': 144845, 'loss/train': 1.254398226737976} 08/31/2021 15:29:52 - INFO - __main__ - Step 144847: {'lr': 1.4946583511236677e-06, 'samples': 27810624, 'steps': 144846, 'loss/train': 0.9773467779159546} 08/31/2021 15:29:53 - INFO - __main__ - Step 144848: {'lr': 1.4940789863760462e-06, 'samples': 27810816, 'steps': 144847, 'loss/train': 0.10411940515041351} 08/31/2021 15:29:53 - INFO - __main__ - Step 144849: {'lr': 1.4934997336013557e-06, 'samples': 27811008, 'steps': 144848, 'loss/train': 1.1520894765853882} 08/31/2021 15:29:54 - INFO - __main__ - Step 144850: {'lr': 1.4929205927998457e-06, 'samples': 27811200, 'steps': 144849, 'loss/train': 1.1577926874160767} 08/31/2021 15:29:54 - INFO - __main__ - Step 144851: {'lr': 1.4923415639718219e-06, 'samples': 27811392, 'steps': 144850, 'loss/train': 1.5641404390335083} 08/31/2021 15:29:54 - INFO - __main__ - Step 144852: {'lr': 1.4917626471175061e-06, 'samples': 27811584, 'steps': 144851, 'loss/train': 0.9027588963508606} 08/31/2021 15:29:56 - INFO - __main__ - Step 144853: {'lr': 1.491183842237148e-06, 'samples': 27811776, 'steps': 144852, 'loss/train': 0.949227511882782} 08/31/2021 15:29:56 - INFO - __main__ - Step 144854: {'lr': 1.4906051493310534e-06, 'samples': 27811968, 'steps': 144853, 'loss/train': 0.8342257142066956} 08/31/2021 15:29:57 - INFO - __main__ - Step 144855: {'lr': 1.490026568399444e-06, 'samples': 27812160, 'steps': 144854, 'loss/train': 0.8517415523529053} 08/31/2021 15:29:57 - INFO - __main__ - Step 144856: {'lr': 1.4894480994425973e-06, 'samples': 27812352, 'steps': 144855, 'loss/train': 0.8627418875694275} 08/31/2021 15:29:57 - INFO - __main__ - Step 144857: {'lr': 1.4888697424607632e-06, 'samples': 27812544, 'steps': 144856, 'loss/train': 0.8653096556663513} 08/31/2021 15:29:59 - INFO - __main__ - Step 144858: {'lr': 1.4882914974542195e-06, 'samples': 27812736, 'steps': 144857, 'loss/train': 1.380764126777649} 08/31/2021 15:29:59 - INFO - __main__ - Step 144859: {'lr': 1.4877133644232433e-06, 'samples': 27812928, 'steps': 144858, 'loss/train': 0.4064285457134247} 08/31/2021 15:30:00 - INFO - __main__ - Step 144860: {'lr': 1.487135343368029e-06, 'samples': 27813120, 'steps': 144859, 'loss/train': 1.2373954057693481} 08/31/2021 15:30:00 - INFO - __main__ - Step 144861: {'lr': 1.4865574342888821e-06, 'samples': 27813312, 'steps': 144860, 'loss/train': 0.2210538387298584} 08/31/2021 15:30:00 - INFO - __main__ - Step 144862: {'lr': 1.4859796371860522e-06, 'samples': 27813504, 'steps': 144861, 'loss/train': 0.42294129729270935} 08/31/2021 15:30:01 - INFO - __main__ - Step 144863: {'lr': 1.4854019520598171e-06, 'samples': 27813696, 'steps': 144862, 'loss/train': 1.230223298072815} 08/31/2021 15:30:03 - INFO - __main__ - Step 144864: {'lr': 1.4848243789104265e-06, 'samples': 27813888, 'steps': 144863, 'loss/train': 1.5136277675628662} 08/31/2021 15:30:03 - INFO - __main__ - Step 144865: {'lr': 1.4842469177381578e-06, 'samples': 27814080, 'steps': 144864, 'loss/train': 0.9008239507675171} 08/31/2021 15:30:03 - INFO - __main__ - Step 144866: {'lr': 1.4836695685432056e-06, 'samples': 27814272, 'steps': 144865, 'loss/train': 1.2382892370224} 08/31/2021 15:30:04 - INFO - __main__ - Step 144867: {'lr': 1.4830923313259026e-06, 'samples': 27814464, 'steps': 144866, 'loss/train': 1.0274938344955444} 08/31/2021 15:30:04 - INFO - __main__ - Step 144868: {'lr': 1.4825152060864989e-06, 'samples': 27814656, 'steps': 144867, 'loss/train': 1.1041154861450195} 08/31/2021 15:30:06 - INFO - __main__ - Step 144869: {'lr': 1.4819381928252163e-06, 'samples': 27814848, 'steps': 144868, 'loss/train': 1.2789311408996582} 08/31/2021 15:30:06 - INFO - __main__ - Step 144870: {'lr': 1.4813612915423325e-06, 'samples': 27815040, 'steps': 144869, 'loss/train': 1.6931496858596802} 08/31/2021 15:30:07 - INFO - __main__ - Step 144871: {'lr': 1.480784502238125e-06, 'samples': 27815232, 'steps': 144870, 'loss/train': 1.454072117805481} 08/31/2021 15:30:07 - INFO - __main__ - Step 144872: {'lr': 1.4802078249128714e-06, 'samples': 27815424, 'steps': 144871, 'loss/train': 1.3261827230453491} 08/31/2021 15:30:07 - INFO - __main__ - Step 144873: {'lr': 1.479631259566766e-06, 'samples': 27815616, 'steps': 144872, 'loss/train': 1.0122870206832886} 08/31/2021 15:30:09 - INFO - __main__ - Step 144874: {'lr': 1.4790548062001142e-06, 'samples': 27815808, 'steps': 144873, 'loss/train': 1.1977711915969849} 08/31/2021 15:30:10 - INFO - __main__ - Step 144875: {'lr': 1.4784784648131378e-06, 'samples': 27816000, 'steps': 144874, 'loss/train': 1.220166563987732} 08/31/2021 15:30:10 - INFO - __main__ - Step 144876: {'lr': 1.47790223540617e-06, 'samples': 27816192, 'steps': 144875, 'loss/train': 1.369294285774231} 08/31/2021 15:30:10 - INFO - __main__ - Step 144877: {'lr': 1.4773261179793774e-06, 'samples': 27816384, 'steps': 144876, 'loss/train': 1.1601884365081787} 08/31/2021 15:30:11 - INFO - __main__ - Step 144878: {'lr': 1.476750112533093e-06, 'samples': 27816576, 'steps': 144877, 'loss/train': 1.4103103876113892} 08/31/2021 15:30:11 - INFO - __main__ - Step 144879: {'lr': 1.4761742190675665e-06, 'samples': 27816768, 'steps': 144878, 'loss/train': 1.1672430038452148} 08/31/2021 15:30:12 - INFO - __main__ - Step 144880: {'lr': 1.47559843758302e-06, 'samples': 27816960, 'steps': 144879, 'loss/train': 0.03976040706038475} 08/31/2021 15:30:13 - INFO - __main__ - Step 144881: {'lr': 1.4750227680797313e-06, 'samples': 27817152, 'steps': 144880, 'loss/train': 0.8345832228660583} 08/31/2021 15:30:13 - INFO - __main__ - Step 144882: {'lr': 1.4744472105579499e-06, 'samples': 27817344, 'steps': 144881, 'loss/train': 0.8614228963851929} 08/31/2021 15:30:14 - INFO - __main__ - Step 144883: {'lr': 1.4738717650179812e-06, 'samples': 27817536, 'steps': 144882, 'loss/train': 2.2149057388305664} 08/31/2021 15:30:14 - INFO - __main__ - Step 144884: {'lr': 1.4732964314600194e-06, 'samples': 27817728, 'steps': 144883, 'loss/train': 0.7643997073173523} 08/31/2021 15:30:15 - INFO - __main__ - Step 144885: {'lr': 1.47272120988437e-06, 'samples': 27817920, 'steps': 144884, 'loss/train': 1.0692753791809082} 08/31/2021 15:30:16 - INFO - __main__ - Step 144886: {'lr': 1.4721461002912828e-06, 'samples': 27818112, 'steps': 144885, 'loss/train': 1.1556766033172607} 08/31/2021 15:30:16 - INFO - __main__ - Step 144887: {'lr': 1.4715711026810075e-06, 'samples': 27818304, 'steps': 144886, 'loss/train': 1.3777029514312744} 08/31/2021 15:30:17 - INFO - __main__ - Step 144888: {'lr': 1.4709962170538217e-06, 'samples': 27818496, 'steps': 144887, 'loss/train': 1.1614060401916504} 08/31/2021 15:30:17 - INFO - __main__ - Step 144889: {'lr': 1.4704214434099471e-06, 'samples': 27818688, 'steps': 144888, 'loss/train': 0.8321806192398071} 08/31/2021 15:30:19 - INFO - __main__ - Step 144890: {'lr': 1.469846781749662e-06, 'samples': 27818880, 'steps': 144889, 'loss/train': 0.5837674140930176} 08/31/2021 15:30:19 - INFO - __main__ - Step 144891: {'lr': 1.4692722320732433e-06, 'samples': 27819072, 'steps': 144890, 'loss/train': 0.9307003617286682} 08/31/2021 15:30:19 - INFO - __main__ - Step 144892: {'lr': 1.468697794380941e-06, 'samples': 27819264, 'steps': 144891, 'loss/train': 1.6440316438674927} 08/31/2021 15:30:20 - INFO - __main__ - Step 144893: {'lr': 1.4681234686729772e-06, 'samples': 27819456, 'steps': 144892, 'loss/train': 0.9633156657218933} 08/31/2021 15:30:20 - INFO - __main__ - Step 144894: {'lr': 1.4675492549496572e-06, 'samples': 27819648, 'steps': 144893, 'loss/train': 1.0951639413833618} 08/31/2021 15:30:22 - INFO - __main__ - Step 144895: {'lr': 1.4669751532112308e-06, 'samples': 27819840, 'steps': 144894, 'loss/train': 1.2455668449401855} 08/31/2021 15:30:22 - INFO - __main__ - Step 144896: {'lr': 1.4664011634579477e-06, 'samples': 27820032, 'steps': 144895, 'loss/train': 0.40128517150878906} 08/31/2021 15:30:22 - INFO - __main__ - Step 144897: {'lr': 1.4658272856900856e-06, 'samples': 27820224, 'steps': 144896, 'loss/train': 1.0795074701309204} 08/31/2021 15:30:23 - INFO - __main__ - Step 144898: {'lr': 1.4652535199078665e-06, 'samples': 27820416, 'steps': 144897, 'loss/train': 1.1088529825210571} 08/31/2021 15:30:23 - INFO - __main__ - Step 144899: {'lr': 1.4646798661115957e-06, 'samples': 27820608, 'steps': 144898, 'loss/train': 2.0359833240509033} 08/31/2021 15:30:23 - INFO - __main__ - Step 144900: {'lr': 1.4641063243014674e-06, 'samples': 27820800, 'steps': 144899, 'loss/train': 1.0141938924789429} 08/31/2021 15:30:25 - INFO - __main__ - Step 144901: {'lr': 1.4635328944778148e-06, 'samples': 27820992, 'steps': 144900, 'loss/train': 0.9294154644012451} 08/31/2021 15:30:25 - INFO - __main__ - Step 144902: {'lr': 1.4629595766408322e-06, 'samples': 27821184, 'steps': 144901, 'loss/train': 1.1653757095336914} 08/31/2021 15:30:26 - INFO - __main__ - Step 144903: {'lr': 1.462386370790797e-06, 'samples': 27821376, 'steps': 144902, 'loss/train': 0.2895003855228424} 08/31/2021 15:30:26 - INFO - __main__ - Step 144904: {'lr': 1.4618132769279869e-06, 'samples': 27821568, 'steps': 144903, 'loss/train': 1.4312739372253418} 08/31/2021 15:30:27 - INFO - __main__ - Step 144905: {'lr': 1.4612402950526516e-06, 'samples': 27821760, 'steps': 144904, 'loss/train': 0.8223730325698853} 08/31/2021 15:30:28 - INFO - __main__ - Step 144906: {'lr': 1.4606674251650687e-06, 'samples': 27821952, 'steps': 144905, 'loss/train': 0.9698007106781006} 08/31/2021 15:30:28 - INFO - __main__ - Step 144907: {'lr': 1.4600946672654324e-06, 'samples': 27822144, 'steps': 144906, 'loss/train': 0.8083205819129944} 08/31/2021 15:30:29 - INFO - __main__ - Step 144908: {'lr': 1.459522021354076e-06, 'samples': 27822336, 'steps': 144907, 'loss/train': 0.7724575400352478} 08/31/2021 15:30:29 - INFO - __main__ - Step 144909: {'lr': 1.4589494874311937e-06, 'samples': 27822528, 'steps': 144908, 'loss/train': 0.6580686569213867} 08/31/2021 15:30:30 - INFO - __main__ - Step 144910: {'lr': 1.4583770654970906e-06, 'samples': 27822720, 'steps': 144909, 'loss/train': 1.2956013679504395} 08/31/2021 15:30:31 - INFO - __main__ - Step 144911: {'lr': 1.457804755552017e-06, 'samples': 27822912, 'steps': 144910, 'loss/train': 1.146933913230896} 08/31/2021 15:30:31 - INFO - __main__ - Step 144912: {'lr': 1.4572325575961941e-06, 'samples': 27823104, 'steps': 144911, 'loss/train': 0.7293142080307007} 08/31/2021 15:30:32 - INFO - __main__ - Step 144913: {'lr': 1.456660471629928e-06, 'samples': 27823296, 'steps': 144912, 'loss/train': 1.417371153831482} 08/31/2021 15:30:32 - INFO - __main__ - Step 144914: {'lr': 1.4560884976534684e-06, 'samples': 27823488, 'steps': 144913, 'loss/train': 0.8332089185714722} 08/31/2021 15:30:33 - INFO - __main__ - Step 144915: {'lr': 1.455516635667037e-06, 'samples': 27823680, 'steps': 144914, 'loss/train': 1.2411471605300903} 08/31/2021 15:30:35 - INFO - __main__ - Step 144916: {'lr': 1.4549448856709114e-06, 'samples': 27823872, 'steps': 144915, 'loss/train': 1.3083860874176025} 08/31/2021 15:30:35 - INFO - __main__ - Step 144917: {'lr': 1.4543732476653692e-06, 'samples': 27824064, 'steps': 144916, 'loss/train': 1.5397346019744873} 08/31/2021 15:30:36 - INFO - __main__ - Step 144918: {'lr': 1.4538017216506326e-06, 'samples': 27824256, 'steps': 144917, 'loss/train': 0.15883493423461914} 08/31/2021 15:30:36 - INFO - __main__ - Step 144919: {'lr': 1.4532303076269793e-06, 'samples': 27824448, 'steps': 144918, 'loss/train': 1.4392554759979248} 08/31/2021 15:30:36 - INFO - __main__ - Step 144920: {'lr': 1.4526590055946865e-06, 'samples': 27824640, 'steps': 144919, 'loss/train': 0.6283054351806641} 08/31/2021 15:30:37 - INFO - __main__ - Step 144921: {'lr': 1.4520878155539763e-06, 'samples': 27824832, 'steps': 144920, 'loss/train': 1.2652045488357544} 08/31/2021 15:30:38 - INFO - __main__ - Step 144922: {'lr': 1.4515167375051264e-06, 'samples': 27825024, 'steps': 144921, 'loss/train': 0.05703287944197655} 08/31/2021 15:30:39 - INFO - __main__ - Step 144923: {'lr': 1.4509457714483865e-06, 'samples': 27825216, 'steps': 144922, 'loss/train': 0.8725543022155762} 08/31/2021 15:30:39 - INFO - __main__ - Step 144924: {'lr': 1.4503749173840065e-06, 'samples': 27825408, 'steps': 144923, 'loss/train': 1.2017923593521118} 08/31/2021 15:30:39 - INFO - __main__ - Step 144925: {'lr': 1.449804175312236e-06, 'samples': 27825600, 'steps': 144924, 'loss/train': 1.1772561073303223} 08/31/2021 15:30:40 - INFO - __main__ - Step 144926: {'lr': 1.4492335452333805e-06, 'samples': 27825792, 'steps': 144925, 'loss/train': 1.199763536453247} 08/31/2021 15:30:41 - INFO - __main__ - Step 144927: {'lr': 1.448663027147662e-06, 'samples': 27825984, 'steps': 144926, 'loss/train': 1.325812816619873} 08/31/2021 15:30:42 - INFO - __main__ - Step 144928: {'lr': 1.4480926210553303e-06, 'samples': 27826176, 'steps': 144927, 'loss/train': 0.710207998752594} 08/31/2021 15:30:42 - INFO - __main__ - Step 144929: {'lr': 1.447522326956663e-06, 'samples': 27826368, 'steps': 144928, 'loss/train': 1.5074753761291504} 08/31/2021 15:30:42 - INFO - __main__ - Step 144930: {'lr': 1.446952144851882e-06, 'samples': 27826560, 'steps': 144929, 'loss/train': 1.378393292427063} 08/31/2021 15:30:43 - INFO - __main__ - Step 144931: {'lr': 1.4463820747412925e-06, 'samples': 27826752, 'steps': 144930, 'loss/train': 0.17131473124027252} 08/31/2021 15:30:44 - INFO - __main__ - Step 144932: {'lr': 1.445812116625117e-06, 'samples': 27826944, 'steps': 144931, 'loss/train': 1.7025710344314575} 08/31/2021 15:30:44 - INFO - __main__ - Step 144933: {'lr': 1.4452422705036328e-06, 'samples': 27827136, 'steps': 144932, 'loss/train': 0.8638817667961121} 08/31/2021 15:30:45 - INFO - __main__ - Step 144934: {'lr': 1.4446725363770618e-06, 'samples': 27827328, 'steps': 144933, 'loss/train': 0.6299419403076172} 08/31/2021 15:30:45 - INFO - __main__ - Step 144935: {'lr': 1.4441029142457097e-06, 'samples': 27827520, 'steps': 144934, 'loss/train': 0.9098430871963501} 08/31/2021 15:30:46 - INFO - __main__ - Step 144936: {'lr': 1.443533404109798e-06, 'samples': 27827712, 'steps': 144935, 'loss/train': 0.5852532982826233} 08/31/2021 15:30:47 - INFO - __main__ - Step 144937: {'lr': 1.4429640059696047e-06, 'samples': 27827904, 'steps': 144936, 'loss/train': 0.5663968920707703} 08/31/2021 15:30:48 - INFO - __main__ - Step 144938: {'lr': 1.4423947198253796e-06, 'samples': 27828096, 'steps': 144937, 'loss/train': 0.8630596995353699} 08/31/2021 15:30:48 - INFO - __main__ - Step 144939: {'lr': 1.4418255456773722e-06, 'samples': 27828288, 'steps': 144938, 'loss/train': 0.6895926594734192} 08/31/2021 15:30:48 - INFO - __main__ - Step 144940: {'lr': 1.4412564835258602e-06, 'samples': 27828480, 'steps': 144939, 'loss/train': 1.2204846143722534} 08/31/2021 15:30:49 - INFO - __main__ - Step 144941: {'lr': 1.440687533371038e-06, 'samples': 27828672, 'steps': 144940, 'loss/train': 0.7932266592979431} 08/31/2021 15:30:50 - INFO - __main__ - Step 144942: {'lr': 1.4401186952132384e-06, 'samples': 27828864, 'steps': 144941, 'loss/train': 1.498125672340393} 08/31/2021 15:30:51 - INFO - __main__ - Step 144943: {'lr': 1.4395499690526836e-06, 'samples': 27829056, 'steps': 144942, 'loss/train': 1.0894962549209595} 08/31/2021 15:30:51 - INFO - __main__ - Step 144944: {'lr': 1.4389813548896235e-06, 'samples': 27829248, 'steps': 144943, 'loss/train': 1.1276447772979736} 08/31/2021 15:30:51 - INFO - __main__ - Step 144945: {'lr': 1.4384128527243357e-06, 'samples': 27829440, 'steps': 144944, 'loss/train': 0.7035526037216187} 08/31/2021 15:30:52 - INFO - __main__ - Step 144946: {'lr': 1.4378444625570418e-06, 'samples': 27829632, 'steps': 144945, 'loss/train': 0.975106418132782} 08/31/2021 15:30:53 - INFO - __main__ - Step 144947: {'lr': 1.43727618438802e-06, 'samples': 27829824, 'steps': 144946, 'loss/train': 1.6187361478805542} 08/31/2021 15:30:54 - INFO - __main__ - Step 144948: {'lr': 1.4367080182175473e-06, 'samples': 27830016, 'steps': 144947, 'loss/train': 0.8977347612380981} 08/31/2021 15:30:54 - INFO - __main__ - Step 144949: {'lr': 1.436139964045846e-06, 'samples': 27830208, 'steps': 144948, 'loss/train': 1.185367465019226} 08/31/2021 15:30:54 - INFO - __main__ - Step 144950: {'lr': 1.4355720218731939e-06, 'samples': 27830400, 'steps': 144949, 'loss/train': 0.8358384370803833} 08/31/2021 15:30:55 - INFO - __main__ - Step 144951: {'lr': 1.4350041916998124e-06, 'samples': 27830592, 'steps': 144950, 'loss/train': 1.195806622505188} 08/31/2021 15:30:56 - INFO - __main__ - Step 144952: {'lr': 1.4344364735260073e-06, 'samples': 27830784, 'steps': 144951, 'loss/train': 0.9419152140617371} 08/31/2021 15:30:57 - INFO - __main__ - Step 144953: {'lr': 1.4338688673520284e-06, 'samples': 27830976, 'steps': 144952, 'loss/train': 1.1949721574783325} 08/31/2021 15:30:57 - INFO - __main__ - Step 144954: {'lr': 1.4333013731780697e-06, 'samples': 27831168, 'steps': 144953, 'loss/train': 0.4738578200340271} 08/31/2021 15:30:57 - INFO - __main__ - Step 144955: {'lr': 1.4327339910044368e-06, 'samples': 27831360, 'steps': 144954, 'loss/train': 1.1256433725357056} 08/31/2021 15:30:58 - INFO - __main__ - Step 144956: {'lr': 1.432166720831407e-06, 'samples': 27831552, 'steps': 144955, 'loss/train': 1.7977759838104248} 08/31/2021 15:30:59 - INFO - __main__ - Step 144957: {'lr': 1.4315995626591749e-06, 'samples': 27831744, 'steps': 144956, 'loss/train': 0.7680811285972595} 08/31/2021 15:31:00 - INFO - __main__ - Step 144958: {'lr': 1.4310325164880455e-06, 'samples': 27831936, 'steps': 144957, 'loss/train': 1.4001480340957642} 08/31/2021 15:31:00 - INFO - __main__ - Step 144959: {'lr': 1.4304655823182688e-06, 'samples': 27832128, 'steps': 144958, 'loss/train': 0.6449358463287354} 08/31/2021 15:31:00 - INFO - __main__ - Step 144960: {'lr': 1.4298987601500667e-06, 'samples': 27832320, 'steps': 144959, 'loss/train': 1.5061289072036743} 08/31/2021 15:31:01 - INFO - __main__ - Step 144961: {'lr': 1.429332049983717e-06, 'samples': 27832512, 'steps': 144960, 'loss/train': 0.5223925113677979} 08/31/2021 15:31:02 - INFO - __main__ - Step 144962: {'lr': 1.4287654518194693e-06, 'samples': 27832704, 'steps': 144961, 'loss/train': 1.2128567695617676} 08/31/2021 15:31:03 - INFO - __main__ - Step 144963: {'lr': 1.4281989656576011e-06, 'samples': 27832896, 'steps': 144962, 'loss/train': 1.141776204109192} 08/31/2021 15:31:03 - INFO - __main__ - Step 144964: {'lr': 1.4276325914983623e-06, 'samples': 27833088, 'steps': 144963, 'loss/train': 1.4226362705230713} 08/31/2021 15:31:03 - INFO - __main__ - Step 144965: {'lr': 1.427066329341975e-06, 'samples': 27833280, 'steps': 144964, 'loss/train': 1.099146842956543} 08/31/2021 15:31:04 - INFO - __main__ - Step 144966: {'lr': 1.4265001791887168e-06, 'samples': 27833472, 'steps': 144965, 'loss/train': 1.059755563735962} 08/31/2021 15:31:06 - INFO - __main__ - Step 144967: {'lr': 1.4259341410388649e-06, 'samples': 27833664, 'steps': 144966, 'loss/train': 1.0528197288513184} 08/31/2021 15:31:06 - INFO - __main__ - Step 144968: {'lr': 1.425368214892614e-06, 'samples': 27833856, 'steps': 144967, 'loss/train': 0.45867353677749634} 08/31/2021 15:31:07 - INFO - __main__ - Step 144969: {'lr': 1.424802400750269e-06, 'samples': 27834048, 'steps': 144968, 'loss/train': 1.059086799621582} 08/31/2021 15:31:07 - INFO - __main__ - Step 144970: {'lr': 1.4242366986120802e-06, 'samples': 27834240, 'steps': 144969, 'loss/train': 1.1316746473312378} 08/31/2021 15:31:07 - INFO - __main__ - Step 144971: {'lr': 1.423671108478297e-06, 'samples': 27834432, 'steps': 144970, 'loss/train': 0.9079710245132446} 08/31/2021 15:31:08 - INFO - __main__ - Step 144972: {'lr': 1.4231056303491697e-06, 'samples': 27834624, 'steps': 144971, 'loss/train': 1.502551555633545} 08/31/2021 15:31:09 - INFO - __main__ - Step 144973: {'lr': 1.4225402642249475e-06, 'samples': 27834816, 'steps': 144972, 'loss/train': 0.6637545824050903} 08/31/2021 15:31:10 - INFO - __main__ - Step 144974: {'lr': 1.4219750101059082e-06, 'samples': 27835008, 'steps': 144973, 'loss/train': 0.9381924867630005} 08/31/2021 15:31:10 - INFO - __main__ - Step 144975: {'lr': 1.4214098679922739e-06, 'samples': 27835200, 'steps': 144974, 'loss/train': 1.4616221189498901} 08/31/2021 15:31:10 - INFO - __main__ - Step 144976: {'lr': 1.420844837884322e-06, 'samples': 27835392, 'steps': 144975, 'loss/train': 1.281522512435913} 08/31/2021 15:31:11 - INFO - __main__ - Step 144977: {'lr': 1.4202799197823024e-06, 'samples': 27835584, 'steps': 144976, 'loss/train': 1.5628044605255127} 08/31/2021 15:31:12 - INFO - __main__ - Step 144978: {'lr': 1.419715113686465e-06, 'samples': 27835776, 'steps': 144977, 'loss/train': 1.5633667707443237} 08/31/2021 15:31:13 - INFO - __main__ - Step 144979: {'lr': 1.4191504195970872e-06, 'samples': 27835968, 'steps': 144978, 'loss/train': 1.708048701286316} 08/31/2021 15:31:13 - INFO - __main__ - Step 144980: {'lr': 1.4185858375143913e-06, 'samples': 27836160, 'steps': 144979, 'loss/train': 0.015263761393725872} 08/31/2021 15:31:14 - INFO - __main__ - Step 144981: {'lr': 1.4180213674386544e-06, 'samples': 27836352, 'steps': 144980, 'loss/train': 0.10068803280591965} 08/31/2021 15:31:14 - INFO - __main__ - Step 144982: {'lr': 1.417457009370099e-06, 'samples': 27836544, 'steps': 144981, 'loss/train': 0.3357735872268677} 08/31/2021 15:31:14 - INFO - __main__ - Step 144983: {'lr': 1.4168927633090023e-06, 'samples': 27836736, 'steps': 144982, 'loss/train': 1.0904067754745483} 08/31/2021 15:31:16 - INFO - __main__ - Step 144984: {'lr': 1.416328629255642e-06, 'samples': 27836928, 'steps': 144983, 'loss/train': 0.7663041353225708} 08/31/2021 15:31:17 - INFO - __main__ - Step 144985: {'lr': 1.4157646072102405e-06, 'samples': 27837120, 'steps': 144984, 'loss/train': 0.35057908296585083} 08/31/2021 15:31:17 - INFO - __main__ - Step 144986: {'lr': 1.4152006971730468e-06, 'samples': 27837312, 'steps': 144985, 'loss/train': 1.0625817775726318} 08/31/2021 15:31:17 - INFO - __main__ - Step 144987: {'lr': 1.4146368991443392e-06, 'samples': 27837504, 'steps': 144986, 'loss/train': 0.9238815307617188} 08/31/2021 15:31:18 - INFO - __main__ - Step 144988: {'lr': 1.4140732131243394e-06, 'samples': 27837696, 'steps': 144987, 'loss/train': 1.3119864463806152} 08/31/2021 15:31:19 - INFO - __main__ - Step 144989: {'lr': 1.413509639113353e-06, 'samples': 27837888, 'steps': 144988, 'loss/train': 0.47467803955078125} 08/31/2021 15:31:20 - INFO - __main__ - Step 144990: {'lr': 1.4129461771115737e-06, 'samples': 27838080, 'steps': 144989, 'loss/train': 1.152143120765686} 08/31/2021 15:31:20 - INFO - __main__ - Step 144991: {'lr': 1.4123828271193072e-06, 'samples': 27838272, 'steps': 144990, 'loss/train': 1.2915408611297607} 08/31/2021 15:31:20 - INFO - __main__ - Step 144992: {'lr': 1.4118195891367757e-06, 'samples': 27838464, 'steps': 144991, 'loss/train': 1.1164432764053345} 08/31/2021 15:31:21 - INFO - __main__ - Step 144993: {'lr': 1.4112564631642565e-06, 'samples': 27838656, 'steps': 144992, 'loss/train': 1.7403841018676758} 08/31/2021 15:31:21 - INFO - __main__ - Step 144994: {'lr': 1.4106934492019718e-06, 'samples': 27838848, 'steps': 144993, 'loss/train': 1.034409999847412} 08/31/2021 15:31:23 - INFO - __main__ - Step 144995: {'lr': 1.4101305472501991e-06, 'samples': 27839040, 'steps': 144994, 'loss/train': 0.035407617688179016} 08/31/2021 15:31:23 - INFO - __main__ - Step 144996: {'lr': 1.409567757309188e-06, 'samples': 27839232, 'steps': 144995, 'loss/train': 0.4572407007217407} 08/31/2021 15:31:24 - INFO - __main__ - Step 144997: {'lr': 1.4090050793791886e-06, 'samples': 27839424, 'steps': 144996, 'loss/train': 0.6845808029174805} 08/31/2021 15:31:24 - INFO - __main__ - Step 144998: {'lr': 1.4084425134604506e-06, 'samples': 27839616, 'steps': 144997, 'loss/train': 1.2327361106872559} 08/31/2021 15:31:24 - INFO - __main__ - Step 144999: {'lr': 1.4078800595532238e-06, 'samples': 27839808, 'steps': 144998, 'loss/train': 0.6176981925964355} 08/31/2021 15:31:26 - INFO - __main__ - Step 145000: {'lr': 1.4073177176577855e-06, 'samples': 27840000, 'steps': 144999, 'loss/train': 1.2570289373397827} 08/31/2021 15:31:27 - INFO - __main__ - Step 145001: {'lr': 1.406755487774386e-06, 'samples': 27840192, 'steps': 145000, 'loss/train': 1.246425747871399} 08/31/2021 15:31:27 - INFO - __main__ - Step 145002: {'lr': 1.4061933699032469e-06, 'samples': 27840384, 'steps': 145001, 'loss/train': 1.0527700185775757} 08/31/2021 15:31:27 - INFO - __main__ - Step 145003: {'lr': 1.405631364044646e-06, 'samples': 27840576, 'steps': 145002, 'loss/train': 1.722686767578125} 08/31/2021 15:31:28 - INFO - __main__ - Step 145004: {'lr': 1.405069470198833e-06, 'samples': 27840768, 'steps': 145003, 'loss/train': 1.195019245147705} 08/31/2021 15:31:29 - INFO - __main__ - Step 145005: {'lr': 1.404507688366058e-06, 'samples': 27840960, 'steps': 145004, 'loss/train': 0.8701494932174683} 08/31/2021 15:31:29 - INFO - __main__ - Step 145006: {'lr': 1.4039460185465703e-06, 'samples': 27841152, 'steps': 145005, 'loss/train': 0.9965485334396362} 08/31/2021 15:31:30 - INFO - __main__ - Step 145007: {'lr': 1.4033844607406477e-06, 'samples': 27841344, 'steps': 145006, 'loss/train': 1.3522335290908813} 08/31/2021 15:31:30 - INFO - __main__ - Step 145008: {'lr': 1.4028230149484844e-06, 'samples': 27841536, 'steps': 145007, 'loss/train': 1.054368019104004} 08/31/2021 15:31:30 - INFO - __main__ - Step 145009: {'lr': 1.4022616811704136e-06, 'samples': 27841728, 'steps': 145008, 'loss/train': 1.0914562940597534} 08/31/2021 15:31:32 - INFO - __main__ - Step 145010: {'lr': 1.4017004594066295e-06, 'samples': 27841920, 'steps': 145009, 'loss/train': 1.321310043334961} 08/31/2021 15:31:32 - INFO - __main__ - Step 145011: {'lr': 1.40113934965741e-06, 'samples': 27842112, 'steps': 145010, 'loss/train': 1.117152452468872} 08/31/2021 15:31:33 - INFO - __main__ - Step 145012: {'lr': 1.4005783519229763e-06, 'samples': 27842304, 'steps': 145011, 'loss/train': 1.323660135269165} 08/31/2021 15:31:33 - INFO - __main__ - Step 145013: {'lr': 1.4000174662036347e-06, 'samples': 27842496, 'steps': 145012, 'loss/train': 1.0109953880310059} 08/31/2021 15:31:33 - INFO - __main__ - Step 145014: {'lr': 1.3994566924996066e-06, 'samples': 27842688, 'steps': 145013, 'loss/train': 1.1468788385391235} 08/31/2021 15:31:35 - INFO - __main__ - Step 145015: {'lr': 1.3988960308111421e-06, 'samples': 27842880, 'steps': 145014, 'loss/train': 0.9237123727798462} 08/31/2021 15:31:35 - INFO - __main__ - Step 145016: {'lr': 1.3983354811384908e-06, 'samples': 27843072, 'steps': 145015, 'loss/train': 1.1820287704467773} 08/31/2021 15:31:36 - INFO - __main__ - Step 145017: {'lr': 1.3977750434819026e-06, 'samples': 27843264, 'steps': 145016, 'loss/train': 1.705682396888733} 08/31/2021 15:31:36 - INFO - __main__ - Step 145018: {'lr': 1.3972147178416827e-06, 'samples': 27843456, 'steps': 145017, 'loss/train': 1.2940064668655396} 08/31/2021 15:31:36 - INFO - __main__ - Step 145019: {'lr': 1.3966545042180257e-06, 'samples': 27843648, 'steps': 145018, 'loss/train': 0.7011511325836182} 08/31/2021 15:31:38 - INFO - __main__ - Step 145020: {'lr': 1.396094402611181e-06, 'samples': 27843840, 'steps': 145019, 'loss/train': 0.926256000995636} 08/31/2021 15:31:38 - INFO - __main__ - Step 145021: {'lr': 1.3955344130214266e-06, 'samples': 27844032, 'steps': 145020, 'loss/train': 0.8424403667449951} 08/31/2021 15:31:39 - INFO - __main__ - Step 145022: {'lr': 1.3949745354490118e-06, 'samples': 27844224, 'steps': 145021, 'loss/train': 1.543492317199707} 08/31/2021 15:31:39 - INFO - __main__ - Step 145023: {'lr': 1.3944147698941867e-06, 'samples': 27844416, 'steps': 145022, 'loss/train': 0.3359614312648773} 08/31/2021 15:31:39 - INFO - __main__ - Step 145024: {'lr': 1.3938551163572011e-06, 'samples': 27844608, 'steps': 145023, 'loss/train': 1.676973819732666} 08/31/2021 15:31:40 - INFO - __main__ - Step 145025: {'lr': 1.3932955748383048e-06, 'samples': 27844800, 'steps': 145024, 'loss/train': 0.7650589942932129} 08/31/2021 15:31:42 - INFO - __main__ - Step 145026: {'lr': 1.3927361453377474e-06, 'samples': 27844992, 'steps': 145025, 'loss/train': 1.1831504106521606} 08/31/2021 15:31:43 - INFO - __main__ - Step 145027: {'lr': 1.3921768278558066e-06, 'samples': 27845184, 'steps': 145026, 'loss/train': 1.3886992931365967} 08/31/2021 15:31:43 - INFO - __main__ - Step 145028: {'lr': 1.3916176223927047e-06, 'samples': 27845376, 'steps': 145027, 'loss/train': 1.006085991859436} 08/31/2021 15:31:43 - INFO - __main__ - Step 145029: {'lr': 1.391058528948691e-06, 'samples': 27845568, 'steps': 145028, 'loss/train': 1.3587217330932617} 08/31/2021 15:31:44 - INFO - __main__ - Step 145030: {'lr': 1.3904995475240712e-06, 'samples': 27845760, 'steps': 145029, 'loss/train': 1.2992289066314697} 08/31/2021 15:31:45 - INFO - __main__ - Step 145031: {'lr': 1.3899406781190115e-06, 'samples': 27845952, 'steps': 145030, 'loss/train': 1.119165301322937} 08/31/2021 15:31:46 - INFO - __main__ - Step 145032: {'lr': 1.3893819207338177e-06, 'samples': 27846144, 'steps': 145031, 'loss/train': 1.569446325302124} 08/31/2021 15:31:46 - INFO - __main__ - Step 145033: {'lr': 1.388823275368739e-06, 'samples': 27846336, 'steps': 145032, 'loss/train': 0.9604732394218445} 08/31/2021 15:31:46 - INFO - __main__ - Step 145034: {'lr': 1.3882647420240258e-06, 'samples': 27846528, 'steps': 145033, 'loss/train': 0.9489377737045288} 08/31/2021 15:31:47 - INFO - __main__ - Step 145035: {'lr': 1.3877063206999274e-06, 'samples': 27846720, 'steps': 145034, 'loss/train': 0.5191325545310974} 08/31/2021 15:31:48 - INFO - __main__ - Step 145036: {'lr': 1.3871480113966662e-06, 'samples': 27846912, 'steps': 145035, 'loss/train': 0.6738141179084778} 08/31/2021 15:31:49 - INFO - __main__ - Step 145037: {'lr': 1.3865898141145471e-06, 'samples': 27847104, 'steps': 145036, 'loss/train': 1.2080343961715698} 08/31/2021 15:31:49 - INFO - __main__ - Step 145038: {'lr': 1.3860317288537927e-06, 'samples': 27847296, 'steps': 145037, 'loss/train': 0.03148719668388367} 08/31/2021 15:31:50 - INFO - __main__ - Step 145039: {'lr': 1.3854737556146246e-06, 'samples': 27847488, 'steps': 145038, 'loss/train': 0.9986587762832642} 08/31/2021 15:31:50 - INFO - __main__ - Step 145040: {'lr': 1.3849158943973484e-06, 'samples': 27847680, 'steps': 145039, 'loss/train': 0.5418528914451599} 08/31/2021 15:31:50 - INFO - __main__ - Step 145041: {'lr': 1.3843581452022136e-06, 'samples': 27847872, 'steps': 145040, 'loss/train': 1.143209457397461} 08/31/2021 15:31:52 - INFO - __main__ - Step 145042: {'lr': 1.3838005080294146e-06, 'samples': 27848064, 'steps': 145041, 'loss/train': 1.0785378217697144} 08/31/2021 15:31:52 - INFO - __main__ - Step 145043: {'lr': 1.383242982879257e-06, 'samples': 27848256, 'steps': 145042, 'loss/train': 0.15565302968025208} 08/31/2021 15:31:53 - INFO - __main__ - Step 145044: {'lr': 1.3826855697519626e-06, 'samples': 27848448, 'steps': 145043, 'loss/train': 0.8254909515380859} 08/31/2021 15:31:53 - INFO - __main__ - Step 145045: {'lr': 1.3821282686478088e-06, 'samples': 27848640, 'steps': 145044, 'loss/train': 0.3830847144126892} 08/31/2021 15:31:53 - INFO - __main__ - Step 145046: {'lr': 1.3815710795670177e-06, 'samples': 27848832, 'steps': 145045, 'loss/train': 0.8979357481002808} 08/31/2021 15:31:55 - INFO - __main__ - Step 145047: {'lr': 1.3810140025098672e-06, 'samples': 27849024, 'steps': 145046, 'loss/train': 0.7718183398246765} 08/31/2021 15:31:55 - INFO - __main__ - Step 145048: {'lr': 1.3804570374765791e-06, 'samples': 27849216, 'steps': 145047, 'loss/train': 0.8186159133911133} 08/31/2021 15:31:56 - INFO - __main__ - Step 145049: {'lr': 1.3799001844674308e-06, 'samples': 27849408, 'steps': 145048, 'loss/train': 0.2698640823364258} 08/31/2021 15:31:56 - INFO - __main__ - Step 145050: {'lr': 1.3793434434826724e-06, 'samples': 27849600, 'steps': 145049, 'loss/train': 0.569001317024231} 08/31/2021 15:31:56 - INFO - __main__ - Step 145051: {'lr': 1.3787868145225535e-06, 'samples': 27849792, 'steps': 145050, 'loss/train': 0.6737318634986877} 08/31/2021 15:31:58 - INFO - __main__ - Step 145052: {'lr': 1.3782302975872963e-06, 'samples': 27849984, 'steps': 145051, 'loss/train': 0.32600119709968567} 08/31/2021 15:31:59 - INFO - __main__ - Step 145053: {'lr': 1.3776738926771782e-06, 'samples': 27850176, 'steps': 145052, 'loss/train': 1.4058020114898682} 08/31/2021 15:31:59 - INFO - __main__ - Step 145054: {'lr': 1.3771175997924213e-06, 'samples': 27850368, 'steps': 145053, 'loss/train': 0.03910285606980324} 08/31/2021 15:31:59 - INFO - __main__ - Step 145055: {'lr': 1.3765614189333309e-06, 'samples': 27850560, 'steps': 145054, 'loss/train': 0.5404941439628601} 08/31/2021 15:32:00 - INFO - __main__ - Step 145056: {'lr': 1.3760053501001013e-06, 'samples': 27850752, 'steps': 145055, 'loss/train': 0.9859158396720886} 08/31/2021 15:32:00 - INFO - __main__ - Step 145057: {'lr': 1.3754493932930102e-06, 'samples': 27850944, 'steps': 145056, 'loss/train': 0.5489372611045837} 08/31/2021 15:32:01 - INFO - __main__ - Step 145058: {'lr': 1.3748935485123072e-06, 'samples': 27851136, 'steps': 145057, 'loss/train': 1.1104367971420288} 08/31/2021 15:32:02 - INFO - __main__ - Step 145059: {'lr': 1.3743378157582698e-06, 'samples': 27851328, 'steps': 145058, 'loss/train': 1.348591923713684} 08/31/2021 15:32:02 - INFO - __main__ - Step 145060: {'lr': 1.3737821950310924e-06, 'samples': 27851520, 'steps': 145059, 'loss/train': 1.2638050317764282} 08/31/2021 15:32:03 - INFO - __main__ - Step 145061: {'lr': 1.3732266863310527e-06, 'samples': 27851712, 'steps': 145060, 'loss/train': 1.9138760566711426} 08/31/2021 15:32:03 - INFO - __main__ - Step 145062: {'lr': 1.3726712896584003e-06, 'samples': 27851904, 'steps': 145061, 'loss/train': 1.0429120063781738} 08/31/2021 15:32:04 - INFO - __main__ - Step 145063: {'lr': 1.3721160050133851e-06, 'samples': 27852096, 'steps': 145062, 'loss/train': 1.325175404548645} 08/31/2021 15:32:05 - INFO - __main__ - Step 145064: {'lr': 1.371560832396257e-06, 'samples': 27852288, 'steps': 145063, 'loss/train': 0.20678271353244781} 08/31/2021 15:32:05 - INFO - __main__ - Step 145065: {'lr': 1.3710057718072933e-06, 'samples': 27852480, 'steps': 145064, 'loss/train': 0.60531085729599} 08/31/2021 15:32:06 - INFO - __main__ - Step 145066: {'lr': 1.3704508232466882e-06, 'samples': 27852672, 'steps': 145065, 'loss/train': 1.031455159187317} 08/31/2021 15:32:06 - INFO - __main__ - Step 145067: {'lr': 1.3698959867147199e-06, 'samples': 27852864, 'steps': 145066, 'loss/train': 0.9744763374328613} 08/31/2021 15:32:07 - INFO - __main__ - Step 145068: {'lr': 1.3693412622116652e-06, 'samples': 27853056, 'steps': 145067, 'loss/train': 1.571357011795044} 08/31/2021 15:32:08 - INFO - __main__ - Step 145069: {'lr': 1.3687866497377188e-06, 'samples': 27853248, 'steps': 145068, 'loss/train': 0.9908581972122192} 08/31/2021 15:32:08 - INFO - __main__ - Step 145070: {'lr': 1.368232149293186e-06, 'samples': 27853440, 'steps': 145069, 'loss/train': 1.226055383682251} 08/31/2021 15:32:09 - INFO - __main__ - Step 145071: {'lr': 1.367677760878261e-06, 'samples': 27853632, 'steps': 145070, 'loss/train': 0.7578662037849426} 08/31/2021 15:32:09 - INFO - __main__ - Step 145072: {'lr': 1.367123484493249e-06, 'samples': 27853824, 'steps': 145071, 'loss/train': 1.1101419925689697} 08/31/2021 15:32:11 - INFO - __main__ - Step 145073: {'lr': 1.3665693201383722e-06, 'samples': 27854016, 'steps': 145072, 'loss/train': 1.4227874279022217} 08/31/2021 15:32:11 - INFO - __main__ - Step 145074: {'lr': 1.3660152678138804e-06, 'samples': 27854208, 'steps': 145073, 'loss/train': 1.4112282991409302} 08/31/2021 15:32:12 - INFO - __main__ - Step 145075: {'lr': 1.3654613275200235e-06, 'samples': 27854400, 'steps': 145074, 'loss/train': 1.4146177768707275} 08/31/2021 15:32:12 - INFO - __main__ - Step 145076: {'lr': 1.364907499257051e-06, 'samples': 27854592, 'steps': 145075, 'loss/train': 0.04614391550421715} 08/31/2021 15:32:12 - INFO - __main__ - Step 145077: {'lr': 1.3643537830252128e-06, 'samples': 27854784, 'steps': 145076, 'loss/train': 0.952210009098053} 08/31/2021 15:32:15 - INFO - __main__ - Step 145078: {'lr': 1.363800178824759e-06, 'samples': 27854976, 'steps': 145077, 'loss/train': 1.3245418071746826} 08/31/2021 15:32:15 - INFO - __main__ - Step 145079: {'lr': 1.363246686655939e-06, 'samples': 27855168, 'steps': 145078, 'loss/train': 0.4109124541282654} 08/31/2021 15:32:16 - INFO - __main__ - Step 145080: {'lr': 1.3626933065190306e-06, 'samples': 27855360, 'steps': 145079, 'loss/train': 1.5624514818191528} 08/31/2021 15:32:16 - INFO - __main__ - Step 145081: {'lr': 1.362140038414228e-06, 'samples': 27855552, 'steps': 145080, 'loss/train': 1.3285428285598755} 08/31/2021 15:32:16 - INFO - __main__ - Step 145082: {'lr': 1.3615868823418088e-06, 'samples': 27855744, 'steps': 145081, 'loss/train': 0.0861043706536293} 08/31/2021 15:32:18 - INFO - __main__ - Step 145083: {'lr': 1.3610338383020226e-06, 'samples': 27855936, 'steps': 145082, 'loss/train': 1.5767862796783447} 08/31/2021 15:32:18 - INFO - __main__ - Step 145084: {'lr': 1.3604809062951195e-06, 'samples': 27856128, 'steps': 145083, 'loss/train': 1.0891953706741333} 08/31/2021 15:32:19 - INFO - __main__ - Step 145085: {'lr': 1.3599280863213492e-06, 'samples': 27856320, 'steps': 145084, 'loss/train': 1.246302604675293} 08/31/2021 15:32:19 - INFO - __main__ - Step 145086: {'lr': 1.3593753783809614e-06, 'samples': 27856512, 'steps': 145085, 'loss/train': 0.5555835962295532} 08/31/2021 15:32:19 - INFO - __main__ - Step 145087: {'lr': 1.3588227824742062e-06, 'samples': 27856704, 'steps': 145086, 'loss/train': 0.5765762329101562} 08/31/2021 15:32:21 - INFO - __main__ - Step 145088: {'lr': 1.3582702986013329e-06, 'samples': 27856896, 'steps': 145087, 'loss/train': 2.3248729705810547} 08/31/2021 15:32:22 - INFO - __main__ - Step 145089: {'lr': 1.3577179267625638e-06, 'samples': 27857088, 'steps': 145088, 'loss/train': 1.3737181425094604} 08/31/2021 15:32:22 - INFO - __main__ - Step 145090: {'lr': 1.3571656669582044e-06, 'samples': 27857280, 'steps': 145089, 'loss/train': 1.0779601335525513} 08/31/2021 15:32:22 - INFO - __main__ - Step 145091: {'lr': 1.3566135191884488e-06, 'samples': 27857472, 'steps': 145090, 'loss/train': 0.7191308736801147} 08/31/2021 15:32:23 - INFO - __main__ - Step 145092: {'lr': 1.3560614834535467e-06, 'samples': 27857664, 'steps': 145091, 'loss/train': 0.7382230162620544} 08/31/2021 15:32:23 - INFO - __main__ - Step 145093: {'lr': 1.3555095597538037e-06, 'samples': 27857856, 'steps': 145092, 'loss/train': 0.03112521953880787} 08/31/2021 15:32:25 - INFO - __main__ - Step 145094: {'lr': 1.3549577480893859e-06, 'samples': 27858048, 'steps': 145093, 'loss/train': 0.8770160675048828} 08/31/2021 15:32:25 - INFO - __main__ - Step 145095: {'lr': 1.354406048460627e-06, 'samples': 27858240, 'steps': 145094, 'loss/train': 0.11822724342346191} 08/31/2021 15:32:25 - INFO - __main__ - Step 145096: {'lr': 1.3538544608677205e-06, 'samples': 27858432, 'steps': 145095, 'loss/train': 1.0681337118148804} 08/31/2021 15:32:26 - INFO - __main__ - Step 145097: {'lr': 1.3533029853109447e-06, 'samples': 27858624, 'steps': 145096, 'loss/train': 1.063847541809082} 08/31/2021 15:32:26 - INFO - __main__ - Step 145098: {'lr': 1.3527516217905212e-06, 'samples': 27858816, 'steps': 145097, 'loss/train': 0.6455039978027344} 08/31/2021 15:32:28 - INFO - __main__ - Step 145099: {'lr': 1.3522003703066998e-06, 'samples': 27859008, 'steps': 145098, 'loss/train': 1.7345752716064453} 08/31/2021 15:32:28 - INFO - __main__ - Step 145100: {'lr': 1.3516492308597583e-06, 'samples': 27859200, 'steps': 145099, 'loss/train': 1.3433752059936523} 08/31/2021 15:32:28 - INFO - __main__ - Step 145101: {'lr': 1.3510982034499187e-06, 'samples': 27859392, 'steps': 145100, 'loss/train': 0.704902172088623} 08/31/2021 15:32:29 - INFO - __main__ - Step 145102: {'lr': 1.3505472880774305e-06, 'samples': 27859584, 'steps': 145101, 'loss/train': 0.5566375851631165} 08/31/2021 15:32:29 - INFO - __main__ - Step 145103: {'lr': 1.3499964847425717e-06, 'samples': 27859776, 'steps': 145102, 'loss/train': 0.7702327966690063} 08/31/2021 15:32:31 - INFO - __main__ - Step 145104: {'lr': 1.349445793445564e-06, 'samples': 27859968, 'steps': 145103, 'loss/train': 1.3054141998291016} 08/31/2021 15:32:31 - INFO - __main__ - Step 145105: {'lr': 1.3488952141866294e-06, 'samples': 27860160, 'steps': 145104, 'loss/train': 1.0475459098815918} 08/31/2021 15:32:32 - INFO - __main__ - Step 145106: {'lr': 1.3483447469660737e-06, 'samples': 27860352, 'steps': 145105, 'loss/train': 1.1136144399642944} 08/31/2021 15:32:32 - INFO - __main__ - Step 145107: {'lr': 1.3477943917840907e-06, 'samples': 27860544, 'steps': 145106, 'loss/train': 0.3007815480232239} 08/31/2021 15:32:32 - INFO - __main__ - Step 145108: {'lr': 1.3472441486409859e-06, 'samples': 27860736, 'steps': 145107, 'loss/train': 0.667866051197052} 08/31/2021 15:32:33 - INFO - __main__ - Step 145109: {'lr': 1.3466940175369536e-06, 'samples': 27860928, 'steps': 145108, 'loss/train': 1.2664202451705933} 08/31/2021 15:32:34 - INFO - __main__ - Step 145110: {'lr': 1.3461439984722711e-06, 'samples': 27861120, 'steps': 145109, 'loss/train': 1.0805000066757202} 08/31/2021 15:32:35 - INFO - __main__ - Step 145111: {'lr': 1.3455940914471886e-06, 'samples': 27861312, 'steps': 145110, 'loss/train': 0.5691450834274292} 08/31/2021 15:32:35 - INFO - __main__ - Step 145112: {'lr': 1.3450442964619281e-06, 'samples': 27861504, 'steps': 145111, 'loss/train': 2.558608293533325} 08/31/2021 15:32:35 - INFO - __main__ - Step 145113: {'lr': 1.3444946135167668e-06, 'samples': 27861696, 'steps': 145112, 'loss/train': 1.5379528999328613} 08/31/2021 15:32:36 - INFO - __main__ - Step 145114: {'lr': 1.343945042611955e-06, 'samples': 27861888, 'steps': 145113, 'loss/train': 1.582442045211792} 08/31/2021 15:32:37 - INFO - __main__ - Step 145115: {'lr': 1.3433955837476862e-06, 'samples': 27862080, 'steps': 145114, 'loss/train': 1.5347199440002441} 08/31/2021 15:32:38 - INFO - __main__ - Step 145116: {'lr': 1.3428462369242666e-06, 'samples': 27862272, 'steps': 145115, 'loss/train': 0.783500075340271} 08/31/2021 15:32:38 - INFO - __main__ - Step 145117: {'lr': 1.3422970021419178e-06, 'samples': 27862464, 'steps': 145116, 'loss/train': 1.279647707939148} 08/31/2021 15:32:39 - INFO - __main__ - Step 145118: {'lr': 1.3417478794008896e-06, 'samples': 27862656, 'steps': 145117, 'loss/train': 0.2641325294971466} 08/31/2021 15:32:39 - INFO - __main__ - Step 145119: {'lr': 1.3411988687014598e-06, 'samples': 27862848, 'steps': 145118, 'loss/train': 0.3380524814128876} 08/31/2021 15:32:40 - INFO - __main__ - Step 145120: {'lr': 1.3406499700438224e-06, 'samples': 27863040, 'steps': 145119, 'loss/train': 0.18714839220046997} 08/31/2021 15:32:41 - INFO - __main__ - Step 145121: {'lr': 1.340101183428255e-06, 'samples': 27863232, 'steps': 145120, 'loss/train': 1.4222501516342163} 08/31/2021 15:32:41 - INFO - __main__ - Step 145122: {'lr': 1.3395525088550075e-06, 'samples': 27863424, 'steps': 145121, 'loss/train': 0.6800535917282104} 08/31/2021 15:32:41 - INFO - __main__ - Step 145123: {'lr': 1.339003946324302e-06, 'samples': 27863616, 'steps': 145122, 'loss/train': 0.6490256786346436} 08/31/2021 15:32:42 - INFO - __main__ - Step 145124: {'lr': 1.3384554958364158e-06, 'samples': 27863808, 'steps': 145123, 'loss/train': 0.9567385315895081} 08/31/2021 15:32:42 - INFO - __main__ - Step 145125: {'lr': 1.3379071573915992e-06, 'samples': 27864000, 'steps': 145124, 'loss/train': 1.261738896369934} 08/31/2021 15:32:44 - INFO - __main__ - Step 145126: {'lr': 1.3373589309900458e-06, 'samples': 27864192, 'steps': 145125, 'loss/train': 0.8467316627502441} 08/31/2021 15:32:44 - INFO - __main__ - Step 145127: {'lr': 1.3368108166320891e-06, 'samples': 27864384, 'steps': 145126, 'loss/train': 0.9213722944259644} 08/31/2021 15:32:44 - INFO - __main__ - Step 145128: {'lr': 1.3362628143178957e-06, 'samples': 27864576, 'steps': 145127, 'loss/train': 1.33773934841156} 08/31/2021 15:32:45 - INFO - __main__ - Step 145129: {'lr': 1.3357149240477707e-06, 'samples': 27864768, 'steps': 145128, 'loss/train': 1.0900652408599854} 08/31/2021 15:32:45 - INFO - __main__ - Step 145130: {'lr': 1.3351671458219083e-06, 'samples': 27864960, 'steps': 145129, 'loss/train': 0.9448072910308838} 08/31/2021 15:32:47 - INFO - __main__ - Step 145131: {'lr': 1.3346194796406141e-06, 'samples': 27865152, 'steps': 145130, 'loss/train': 0.9494211077690125} 08/31/2021 15:32:48 - INFO - __main__ - Step 145132: {'lr': 1.3340719255040822e-06, 'samples': 27865344, 'steps': 145131, 'loss/train': 1.5523897409439087} 08/31/2021 15:32:48 - INFO - __main__ - Step 145133: {'lr': 1.3335244834125626e-06, 'samples': 27865536, 'steps': 145132, 'loss/train': 1.022971272468567} 08/31/2021 15:32:49 - INFO - __main__ - Step 145134: {'lr': 1.3329771533663604e-06, 'samples': 27865728, 'steps': 145133, 'loss/train': 1.1242074966430664} 08/31/2021 15:32:49 - INFO - __main__ - Step 145135: {'lr': 1.332429935365642e-06, 'samples': 27865920, 'steps': 145134, 'loss/train': 1.4444568157196045} 08/31/2021 15:32:51 - INFO - __main__ - Step 145136: {'lr': 1.3318828294107133e-06, 'samples': 27866112, 'steps': 145135, 'loss/train': 0.3318002223968506} 08/31/2021 15:32:51 - INFO - __main__ - Step 145137: {'lr': 1.3313358355017958e-06, 'samples': 27866304, 'steps': 145136, 'loss/train': 1.1492398977279663} 08/31/2021 15:32:51 - INFO - __main__ - Step 145138: {'lr': 1.3307889536391394e-06, 'samples': 27866496, 'steps': 145137, 'loss/train': 1.3724920749664307} 08/31/2021 15:32:52 - INFO - __main__ - Step 145139: {'lr': 1.3302421838230217e-06, 'samples': 27866688, 'steps': 145138, 'loss/train': 0.09224426746368408} 08/31/2021 15:32:52 - INFO - __main__ - Step 145140: {'lr': 1.329695526053637e-06, 'samples': 27866880, 'steps': 145139, 'loss/train': 1.2205805778503418} 08/31/2021 15:32:54 - INFO - __main__ - Step 145141: {'lr': 1.3291489803312629e-06, 'samples': 27867072, 'steps': 145140, 'loss/train': 0.6376721262931824} 08/31/2021 15:32:54 - INFO - __main__ - Step 145142: {'lr': 1.3286025466561212e-06, 'samples': 27867264, 'steps': 145141, 'loss/train': 1.2710611820220947} 08/31/2021 15:32:55 - INFO - __main__ - Step 145143: {'lr': 1.3280562250284622e-06, 'samples': 27867456, 'steps': 145142, 'loss/train': 0.5678625106811523} 08/31/2021 15:32:55 - INFO - __main__ - Step 145144: {'lr': 1.327510015448563e-06, 'samples': 27867648, 'steps': 145143, 'loss/train': 1.454421877861023} 08/31/2021 15:32:55 - INFO - __main__ - Step 145145: {'lr': 1.326963917916646e-06, 'samples': 27867840, 'steps': 145144, 'loss/train': 4.91648006439209} 08/31/2021 15:32:56 - INFO - __main__ - Step 145146: {'lr': 1.3264179324329884e-06, 'samples': 27868032, 'steps': 145145, 'loss/train': 0.36510568857192993} 08/31/2021 15:32:58 - INFO - __main__ - Step 145147: {'lr': 1.3258720589977846e-06, 'samples': 27868224, 'steps': 145146, 'loss/train': 1.3895536661148071} 08/31/2021 15:32:58 - INFO - __main__ - Step 145148: {'lr': 1.3253262976112844e-06, 'samples': 27868416, 'steps': 145147, 'loss/train': 0.9536512494087219} 08/31/2021 15:32:58 - INFO - __main__ - Step 145149: {'lr': 1.3247806482737933e-06, 'samples': 27868608, 'steps': 145148, 'loss/train': 0.17482493817806244} 08/31/2021 15:32:59 - INFO - __main__ - Step 145150: {'lr': 1.3242351109855055e-06, 'samples': 27868800, 'steps': 145149, 'loss/train': 0.6958736777305603} 08/31/2021 15:32:59 - INFO - __main__ - Step 145151: {'lr': 1.3236896857466706e-06, 'samples': 27868992, 'steps': 145150, 'loss/train': 1.6315065622329712} 08/31/2021 15:33:01 - INFO - __main__ - Step 145152: {'lr': 1.3231443725575388e-06, 'samples': 27869184, 'steps': 145151, 'loss/train': 0.29531654715538025} 08/31/2021 15:33:01 - INFO - __main__ - Step 145153: {'lr': 1.3225991714183872e-06, 'samples': 27869376, 'steps': 145152, 'loss/train': 0.8877847790718079} 08/31/2021 15:33:02 - INFO - __main__ - Step 145154: {'lr': 1.3220540823294104e-06, 'samples': 27869568, 'steps': 145153, 'loss/train': 0.9156060814857483} 08/31/2021 15:33:02 - INFO - __main__ - Step 145155: {'lr': 1.3215091052909133e-06, 'samples': 27869760, 'steps': 145154, 'loss/train': 1.1686903238296509} 08/31/2021 15:33:02 - INFO - __main__ - Step 145156: {'lr': 1.3209642403030631e-06, 'samples': 27869952, 'steps': 145155, 'loss/train': 0.736021876335144} 08/31/2021 15:33:04 - INFO - __main__ - Step 145157: {'lr': 1.3204194873661924e-06, 'samples': 27870144, 'steps': 145156, 'loss/train': 1.3149062395095825} 08/31/2021 15:33:04 - INFO - __main__ - Step 145158: {'lr': 1.3198748464804677e-06, 'samples': 27870336, 'steps': 145157, 'loss/train': 0.9950311779975891} 08/31/2021 15:33:04 - INFO - __main__ - Step 145159: {'lr': 1.3193303176461946e-06, 'samples': 27870528, 'steps': 145158, 'loss/train': 0.8694955110549927} 08/31/2021 15:33:05 - INFO - __main__ - Step 145160: {'lr': 1.318785900863567e-06, 'samples': 27870720, 'steps': 145159, 'loss/train': 0.9273254871368408} 08/31/2021 15:33:05 - INFO - __main__ - Step 145161: {'lr': 1.318241596132863e-06, 'samples': 27870912, 'steps': 145160, 'loss/train': 1.077387809753418} 08/31/2021 15:33:06 - INFO - __main__ - Step 145162: {'lr': 1.317697403454332e-06, 'samples': 27871104, 'steps': 145161, 'loss/train': 0.726141095161438} 08/31/2021 15:33:07 - INFO - __main__ - Step 145163: {'lr': 1.3171533228282239e-06, 'samples': 27871296, 'steps': 145162, 'loss/train': 0.8813947439193726} 08/31/2021 15:33:07 - INFO - __main__ - Step 145164: {'lr': 1.316609354254733e-06, 'samples': 27871488, 'steps': 145163, 'loss/train': 0.4210819602012634} 08/31/2021 15:33:08 - INFO - __main__ - Step 145165: {'lr': 1.3160654977341646e-06, 'samples': 27871680, 'steps': 145164, 'loss/train': 1.2491650581359863} 08/31/2021 15:33:08 - INFO - __main__ - Step 145166: {'lr': 1.3155217532667408e-06, 'samples': 27871872, 'steps': 145165, 'loss/train': 1.1245795488357544} 08/31/2021 15:33:09 - INFO - __main__ - Step 145167: {'lr': 1.3149781208526834e-06, 'samples': 27872064, 'steps': 145166, 'loss/train': 1.062972068786621} 08/31/2021 15:33:10 - INFO - __main__ - Step 145168: {'lr': 1.314434600492298e-06, 'samples': 27872256, 'steps': 145167, 'loss/train': 1.1513967514038086} 08/31/2021 15:33:10 - INFO - __main__ - Step 145169: {'lr': 1.3138911921857787e-06, 'samples': 27872448, 'steps': 145168, 'loss/train': 1.462688684463501} 08/31/2021 15:33:11 - INFO - __main__ - Step 145170: {'lr': 1.3133478959333757e-06, 'samples': 27872640, 'steps': 145169, 'loss/train': 1.5766605138778687} 08/31/2021 15:33:11 - INFO - __main__ - Step 145171: {'lr': 1.3128047117353104e-06, 'samples': 27872832, 'steps': 145170, 'loss/train': 0.8847333192825317} 08/31/2021 15:33:12 - INFO - __main__ - Step 145172: {'lr': 1.3122616395918884e-06, 'samples': 27873024, 'steps': 145171, 'loss/train': 1.5353890657424927} 08/31/2021 15:33:13 - INFO - __main__ - Step 145173: {'lr': 1.311718679503332e-06, 'samples': 27873216, 'steps': 145172, 'loss/train': 0.9388139247894287} 08/31/2021 15:33:14 - INFO - __main__ - Step 145174: {'lr': 1.3111758314698629e-06, 'samples': 27873408, 'steps': 145173, 'loss/train': 1.4620356559753418} 08/31/2021 15:33:14 - INFO - __main__ - Step 145175: {'lr': 1.310633095491731e-06, 'samples': 27873600, 'steps': 145174, 'loss/train': 1.0922354459762573} 08/31/2021 15:33:15 - INFO - __main__ - Step 145176: {'lr': 1.3100904715692142e-06, 'samples': 27873792, 'steps': 145175, 'loss/train': 0.10509781539440155} 08/31/2021 15:33:15 - INFO - __main__ - Step 145177: {'lr': 1.309547959702534e-06, 'samples': 27873984, 'steps': 145176, 'loss/train': 0.11224306374788284} 08/31/2021 15:33:17 - INFO - __main__ - Step 145178: {'lr': 1.3090055598919126e-06, 'samples': 27874176, 'steps': 145177, 'loss/train': 0.43712905049324036} 08/31/2021 15:33:17 - INFO - __main__ - Step 145179: {'lr': 1.3084632721376276e-06, 'samples': 27874368, 'steps': 145178, 'loss/train': 0.9915969371795654} 08/31/2021 15:33:18 - INFO - __main__ - Step 145180: {'lr': 1.3079210964399014e-06, 'samples': 27874560, 'steps': 145179, 'loss/train': 1.2785664796829224} 08/31/2021 15:33:18 - INFO - __main__ - Step 145181: {'lr': 1.3073790327989832e-06, 'samples': 27874752, 'steps': 145180, 'loss/train': 0.8044809699058533} 08/31/2021 15:33:18 - INFO - __main__ - Step 145182: {'lr': 1.3068370812151509e-06, 'samples': 27874944, 'steps': 145181, 'loss/train': 1.2516502141952515} 08/31/2021 15:33:20 - INFO - __main__ - Step 145183: {'lr': 1.3062952416885987e-06, 'samples': 27875136, 'steps': 145182, 'loss/train': 2.0071210861206055} 08/31/2021 15:33:20 - INFO - __main__ - Step 145184: {'lr': 1.3057535142196043e-06, 'samples': 27875328, 'steps': 145183, 'loss/train': 1.5752546787261963} 08/31/2021 15:33:21 - INFO - __main__ - Step 145185: {'lr': 1.3052118988083894e-06, 'samples': 27875520, 'steps': 145184, 'loss/train': 0.8790700435638428} 08/31/2021 15:33:21 - INFO - __main__ - Step 145186: {'lr': 1.304670395455232e-06, 'samples': 27875712, 'steps': 145185, 'loss/train': 1.0771291255950928} 08/31/2021 15:33:21 - INFO - __main__ - Step 145187: {'lr': 1.304129004160326e-06, 'samples': 27875904, 'steps': 145186, 'loss/train': 1.7743204832077026} 08/31/2021 15:33:24 - INFO - __main__ - Step 145188: {'lr': 1.303587724923949e-06, 'samples': 27876096, 'steps': 145187, 'loss/train': 1.107465147972107} 08/31/2021 15:33:24 - INFO - __main__ - Step 145189: {'lr': 1.3030465577463236e-06, 'samples': 27876288, 'steps': 145188, 'loss/train': 0.490841269493103} 08/31/2021 15:33:25 - INFO - __main__ - Step 145190: {'lr': 1.3025055026277267e-06, 'samples': 27876480, 'steps': 145189, 'loss/train': 0.014808895997703075} 08/31/2021 15:33:25 - INFO - __main__ - Step 145191: {'lr': 1.3019645595683804e-06, 'samples': 27876672, 'steps': 145190, 'loss/train': 0.8652048707008362} 08/31/2021 15:33:25 - INFO - __main__ - Step 145192: {'lr': 1.301423728568535e-06, 'samples': 27876864, 'steps': 145191, 'loss/train': 1.2433053255081177} 08/31/2021 15:33:26 - INFO - __main__ - Step 145193: {'lr': 1.3008830096284118e-06, 'samples': 27877056, 'steps': 145192, 'loss/train': 1.1757538318634033} 08/31/2021 15:33:27 - INFO - __main__ - Step 145194: {'lr': 1.3003424027482892e-06, 'samples': 27877248, 'steps': 145193, 'loss/train': 1.13893723487854} 08/31/2021 15:33:28 - INFO - __main__ - Step 145195: {'lr': 1.2998019079284162e-06, 'samples': 27877440, 'steps': 145194, 'loss/train': 1.3230395317077637} 08/31/2021 15:33:28 - INFO - __main__ - Step 145196: {'lr': 1.2992615251689876e-06, 'samples': 27877632, 'steps': 145195, 'loss/train': 1.4263801574707031} 08/31/2021 15:33:29 - INFO - __main__ - Step 145197: {'lr': 1.298721254470281e-06, 'samples': 27877824, 'steps': 145196, 'loss/train': 0.3854316174983978} 08/31/2021 15:33:29 - INFO - __main__ - Step 145198: {'lr': 1.298181095832518e-06, 'samples': 27878016, 'steps': 145197, 'loss/train': 0.9711531400680542} 08/31/2021 15:33:29 - INFO - __main__ - Step 145199: {'lr': 1.2976410492559765e-06, 'samples': 27878208, 'steps': 145198, 'loss/train': 0.22018565237522125} 08/31/2021 15:33:31 - INFO - __main__ - Step 145200: {'lr': 1.2971011147408506e-06, 'samples': 27878400, 'steps': 145199, 'loss/train': 1.7412266731262207} 08/31/2021 15:33:31 - INFO - __main__ - Step 145201: {'lr': 1.296561292287446e-06, 'samples': 27878592, 'steps': 145200, 'loss/train': 1.613516092300415} 08/31/2021 15:33:32 - INFO - __main__ - Step 145202: {'lr': 1.2960215818959565e-06, 'samples': 27878784, 'steps': 145201, 'loss/train': 0.8280038237571716} 08/31/2021 15:33:32 - INFO - __main__ - Step 145203: {'lr': 1.2954819835666321e-06, 'samples': 27878976, 'steps': 145202, 'loss/train': 0.4651368260383606} 08/31/2021 15:33:32 - INFO - __main__ - Step 145204: {'lr': 1.2949424972997503e-06, 'samples': 27879168, 'steps': 145203, 'loss/train': 1.3041874170303345} 08/31/2021 15:33:34 - INFO - __main__ - Step 145205: {'lr': 1.2944031230955056e-06, 'samples': 27879360, 'steps': 145204, 'loss/train': 1.0453377962112427} 08/31/2021 15:33:34 - INFO - __main__ - Step 145206: {'lr': 1.2938638609542031e-06, 'samples': 27879552, 'steps': 145205, 'loss/train': 1.0499608516693115} 08/31/2021 15:33:35 - INFO - __main__ - Step 145207: {'lr': 1.2933247108760093e-06, 'samples': 27879744, 'steps': 145206, 'loss/train': 0.10046137124300003} 08/31/2021 15:33:35 - INFO - __main__ - Step 145208: {'lr': 1.2927856728612297e-06, 'samples': 27879936, 'steps': 145207, 'loss/train': 1.2755943536758423} 08/31/2021 15:33:36 - INFO - __main__ - Step 145209: {'lr': 1.2922467469100863e-06, 'samples': 27880128, 'steps': 145208, 'loss/train': 1.3234046697616577} 08/31/2021 15:33:37 - INFO - __main__ - Step 145210: {'lr': 1.291707933022801e-06, 'samples': 27880320, 'steps': 145209, 'loss/train': 0.8950221538543701} 08/31/2021 15:33:38 - INFO - __main__ - Step 145211: {'lr': 1.2911692311996238e-06, 'samples': 27880512, 'steps': 145210, 'loss/train': 1.514664649963379} 08/31/2021 15:33:38 - INFO - __main__ - Step 145212: {'lr': 1.290630641440832e-06, 'samples': 27880704, 'steps': 145211, 'loss/train': 1.1911797523498535} 08/31/2021 15:33:38 - INFO - __main__ - Step 145213: {'lr': 1.2900921637466201e-06, 'samples': 27880896, 'steps': 145212, 'loss/train': 0.913774311542511} 08/31/2021 15:33:39 - INFO - __main__ - Step 145214: {'lr': 1.2895537981172933e-06, 'samples': 27881088, 'steps': 145213, 'loss/train': 1.1243804693222046} 08/31/2021 15:33:39 - INFO - __main__ - Step 145215: {'lr': 1.2890155445530182e-06, 'samples': 27881280, 'steps': 145214, 'loss/train': 1.0346884727478027} 08/31/2021 15:33:40 - INFO - __main__ - Step 145216: {'lr': 1.2884774030541003e-06, 'samples': 27881472, 'steps': 145215, 'loss/train': 0.3161027729511261} 08/31/2021 15:33:41 - INFO - __main__ - Step 145217: {'lr': 1.2879393736207335e-06, 'samples': 27881664, 'steps': 145216, 'loss/train': 0.7887649536132812} 08/31/2021 15:33:41 - INFO - __main__ - Step 145218: {'lr': 1.2874014562531954e-06, 'samples': 27881856, 'steps': 145217, 'loss/train': 1.266473650932312} 08/31/2021 15:33:42 - INFO - __main__ - Step 145219: {'lr': 1.2868636509517084e-06, 'samples': 27882048, 'steps': 145218, 'loss/train': 0.9429899454116821} 08/31/2021 15:33:42 - INFO - __main__ - Step 145220: {'lr': 1.2863259577165497e-06, 'samples': 27882240, 'steps': 145219, 'loss/train': 0.32369834184646606} 08/31/2021 15:33:43 - INFO - __main__ - Step 145221: {'lr': 1.2857883765479139e-06, 'samples': 27882432, 'steps': 145220, 'loss/train': 1.1065940856933594} 08/31/2021 15:33:44 - INFO - __main__ - Step 145222: {'lr': 1.2852509074460784e-06, 'samples': 27882624, 'steps': 145221, 'loss/train': 1.0179346799850464} 08/31/2021 15:33:44 - INFO - __main__ - Step 145223: {'lr': 1.2847135504112372e-06, 'samples': 27882816, 'steps': 145222, 'loss/train': 0.9677623510360718} 08/31/2021 15:33:45 - INFO - __main__ - Step 145224: {'lr': 1.284176305443696e-06, 'samples': 27883008, 'steps': 145223, 'loss/train': 0.8760411739349365} 08/31/2021 15:33:45 - INFO - __main__ - Step 145225: {'lr': 1.2836391725436491e-06, 'samples': 27883200, 'steps': 145224, 'loss/train': 0.037374306470155716} 08/31/2021 15:33:46 - INFO - __main__ - Step 145226: {'lr': 1.283102151711374e-06, 'samples': 27883392, 'steps': 145225, 'loss/train': 1.1551706790924072} 08/31/2021 15:33:47 - INFO - __main__ - Step 145227: {'lr': 1.2825652429470924e-06, 'samples': 27883584, 'steps': 145226, 'loss/train': 1.3185850381851196} 08/31/2021 15:33:47 - INFO - __main__ - Step 145228: {'lr': 1.2820284462510267e-06, 'samples': 27883776, 'steps': 145227, 'loss/train': 1.1472444534301758} 08/31/2021 15:33:48 - INFO - __main__ - Step 145229: {'lr': 1.2814917616234546e-06, 'samples': 27883968, 'steps': 145228, 'loss/train': 1.32960045337677} 08/31/2021 15:33:48 - INFO - __main__ - Step 145230: {'lr': 1.2809551890646253e-06, 'samples': 27884160, 'steps': 145229, 'loss/train': 1.445002555847168} 08/31/2021 15:33:50 - INFO - __main__ - Step 145231: {'lr': 1.2804187285747337e-06, 'samples': 27884352, 'steps': 145230, 'loss/train': 0.6201932430267334} 08/31/2021 15:33:50 - INFO - __main__ - Step 145232: {'lr': 1.2798823801540571e-06, 'samples': 27884544, 'steps': 145231, 'loss/train': 2.374494791030884} 08/31/2021 15:33:50 - INFO - __main__ - Step 145233: {'lr': 1.2793461438028176e-06, 'samples': 27884736, 'steps': 145232, 'loss/train': 0.14810021221637726} 08/31/2021 15:33:51 - INFO - __main__ - Step 145234: {'lr': 1.2788100195212649e-06, 'samples': 27884928, 'steps': 145233, 'loss/train': 1.037188172340393} 08/31/2021 15:33:51 - INFO - __main__ - Step 145235: {'lr': 1.2782740073096767e-06, 'samples': 27885120, 'steps': 145234, 'loss/train': 1.0448578596115112} 08/31/2021 15:33:52 - INFO - __main__ - Step 145236: {'lr': 1.2777381071682192e-06, 'samples': 27885312, 'steps': 145235, 'loss/train': 1.0927209854125977} 08/31/2021 15:33:53 - INFO - __main__ - Step 145237: {'lr': 1.2772023190971982e-06, 'samples': 27885504, 'steps': 145236, 'loss/train': 1.1055529117584229} 08/31/2021 15:33:53 - INFO - __main__ - Step 145238: {'lr': 1.2766666430968354e-06, 'samples': 27885696, 'steps': 145237, 'loss/train': 1.2512911558151245} 08/31/2021 15:33:54 - INFO - __main__ - Step 145239: {'lr': 1.276131079167353e-06, 'samples': 27885888, 'steps': 145238, 'loss/train': 1.4835293292999268} 08/31/2021 15:33:54 - INFO - __main__ - Step 145240: {'lr': 1.2755956273090008e-06, 'samples': 27886080, 'steps': 145239, 'loss/train': 1.4460841417312622} 08/31/2021 15:33:54 - INFO - __main__ - Step 145241: {'lr': 1.2750602875220562e-06, 'samples': 27886272, 'steps': 145240, 'loss/train': 1.075988531112671} 08/31/2021 15:33:56 - INFO - __main__ - Step 145242: {'lr': 1.2745250598067137e-06, 'samples': 27886464, 'steps': 145241, 'loss/train': 1.0332450866699219} 08/31/2021 15:33:57 - INFO - __main__ - Step 145243: {'lr': 1.273989944163223e-06, 'samples': 27886656, 'steps': 145242, 'loss/train': 1.1006476879119873} 08/31/2021 15:33:57 - INFO - __main__ - Step 145244: {'lr': 1.2734549405918617e-06, 'samples': 27886848, 'steps': 145243, 'loss/train': 1.0123834609985352} 08/31/2021 15:33:58 - INFO - __main__ - Step 145245: {'lr': 1.272920049092824e-06, 'samples': 27887040, 'steps': 145244, 'loss/train': 0.9386531114578247} 08/31/2021 15:33:58 - INFO - __main__ - Step 145246: {'lr': 1.2723852696663597e-06, 'samples': 27887232, 'steps': 145245, 'loss/train': 1.5757683515548706} 08/31/2021 15:34:00 - INFO - __main__ - Step 145247: {'lr': 1.2718506023127464e-06, 'samples': 27887424, 'steps': 145246, 'loss/train': 0.6149266958236694} 08/31/2021 15:34:00 - INFO - __main__ - Step 145248: {'lr': 1.2713160470321782e-06, 'samples': 27887616, 'steps': 145247, 'loss/train': 1.1414154767990112} 08/31/2021 15:34:00 - INFO - __main__ - Step 145249: {'lr': 1.270781603824933e-06, 'samples': 27887808, 'steps': 145248, 'loss/train': 0.6882911324501038} 08/31/2021 15:34:01 - INFO - __main__ - Step 145250: {'lr': 1.2702472726912328e-06, 'samples': 27888000, 'steps': 145249, 'loss/train': 0.8584545850753784} 08/31/2021 15:34:01 - INFO - __main__ - Step 145251: {'lr': 1.2697130536312995e-06, 'samples': 27888192, 'steps': 145250, 'loss/train': 0.20862659811973572} 08/31/2021 15:34:03 - INFO - __main__ - Step 145252: {'lr': 1.2691789466454107e-06, 'samples': 27888384, 'steps': 145251, 'loss/train': 0.4939326047897339} 08/31/2021 15:34:03 - INFO - __main__ - Step 145253: {'lr': 1.2686449517337884e-06, 'samples': 27888576, 'steps': 145252, 'loss/train': 1.2076466083526611} 08/31/2021 15:34:03 - INFO - __main__ - Step 145254: {'lr': 1.2681110688966823e-06, 'samples': 27888768, 'steps': 145253, 'loss/train': 0.09242776036262512} 08/31/2021 15:34:04 - INFO - __main__ - Step 145255: {'lr': 1.2675772981343426e-06, 'samples': 27888960, 'steps': 145254, 'loss/train': 0.8096334934234619} 08/31/2021 15:34:04 - INFO - __main__ - Step 145256: {'lr': 1.267043639446963e-06, 'samples': 27889152, 'steps': 145255, 'loss/train': 1.3223663568496704} 08/31/2021 15:34:06 - INFO - __main__ - Step 145257: {'lr': 1.2665100928348217e-06, 'samples': 27889344, 'steps': 145256, 'loss/train': 1.3319638967514038} 08/31/2021 15:34:06 - INFO - __main__ - Step 145258: {'lr': 1.265976658298168e-06, 'samples': 27889536, 'steps': 145257, 'loss/train': 1.450392723083496} 08/31/2021 15:34:06 - INFO - __main__ - Step 145259: {'lr': 1.265443335837224e-06, 'samples': 27889728, 'steps': 145258, 'loss/train': 1.8324174880981445} 08/31/2021 15:34:07 - INFO - __main__ - Step 145260: {'lr': 1.26491012545224e-06, 'samples': 27889920, 'steps': 145259, 'loss/train': 0.8507016897201538} 08/31/2021 15:34:07 - INFO - __main__ - Step 145261: {'lr': 1.2643770271434373e-06, 'samples': 27890112, 'steps': 145260, 'loss/train': 1.6331748962402344} 08/31/2021 15:34:09 - INFO - __main__ - Step 145262: {'lr': 1.2638440409110663e-06, 'samples': 27890304, 'steps': 145261, 'loss/train': 2.1550590991973877} 08/31/2021 15:34:09 - INFO - __main__ - Step 145263: {'lr': 1.2633111667553765e-06, 'samples': 27890496, 'steps': 145262, 'loss/train': 1.0521700382232666} 08/31/2021 15:34:09 - INFO - __main__ - Step 145264: {'lr': 1.26277840467659e-06, 'samples': 27890688, 'steps': 145263, 'loss/train': 0.8037829995155334} 08/31/2021 15:34:10 - INFO - __main__ - Step 145265: {'lr': 1.2622457546749566e-06, 'samples': 27890880, 'steps': 145264, 'loss/train': 0.7728898525238037} 08/31/2021 15:34:10 - INFO - __main__ - Step 145266: {'lr': 1.2617132167507262e-06, 'samples': 27891072, 'steps': 145265, 'loss/train': 1.728892207145691} 08/31/2021 15:34:10 - INFO - __main__ - Step 145267: {'lr': 1.2611807909041207e-06, 'samples': 27891264, 'steps': 145266, 'loss/train': 1.0946458578109741} 08/31/2021 15:34:12 - INFO - __main__ - Step 145268: {'lr': 1.2606484771353898e-06, 'samples': 27891456, 'steps': 145267, 'loss/train': 1.2899502515792847} 08/31/2021 15:34:13 - INFO - __main__ - Step 145269: {'lr': 1.2601162754447836e-06, 'samples': 27891648, 'steps': 145268, 'loss/train': 0.9466043710708618} 08/31/2021 15:34:13 - INFO - __main__ - Step 145270: {'lr': 1.259584185832524e-06, 'samples': 27891840, 'steps': 145269, 'loss/train': 0.9048909544944763} 08/31/2021 15:34:13 - INFO - __main__ - Step 145271: {'lr': 1.259052208298861e-06, 'samples': 27892032, 'steps': 145270, 'loss/train': 0.737131655216217} 08/31/2021 15:34:14 - INFO - __main__ - Step 145272: {'lr': 1.2585203428440162e-06, 'samples': 27892224, 'steps': 145271, 'loss/train': 1.1887025833129883} 08/31/2021 15:34:15 - INFO - __main__ - Step 145273: {'lr': 1.2579885894682674e-06, 'samples': 27892416, 'steps': 145272, 'loss/train': 0.26810404658317566} 08/31/2021 15:34:16 - INFO - __main__ - Step 145274: {'lr': 1.257456948171809e-06, 'samples': 27892608, 'steps': 145273, 'loss/train': 2.2686893939971924} 08/31/2021 15:34:16 - INFO - __main__ - Step 145275: {'lr': 1.2569254189549183e-06, 'samples': 27892800, 'steps': 145274, 'loss/train': 0.7586264610290527} 08/31/2021 15:34:17 - INFO - __main__ - Step 145276: {'lr': 1.2563940018178176e-06, 'samples': 27892992, 'steps': 145275, 'loss/train': 1.5308107137680054} 08/31/2021 15:34:17 - INFO - __main__ - Step 145277: {'lr': 1.2558626967607566e-06, 'samples': 27893184, 'steps': 145276, 'loss/train': 1.9169375896453857} 08/31/2021 15:34:17 - INFO - __main__ - Step 145278: {'lr': 1.2553315037839297e-06, 'samples': 27893376, 'steps': 145277, 'loss/train': 0.6970431804656982} 08/31/2021 15:34:19 - INFO - __main__ - Step 145279: {'lr': 1.254800422887642e-06, 'samples': 27893568, 'steps': 145278, 'loss/train': 0.025452157482504845} 08/31/2021 15:34:19 - INFO - __main__ - Step 145280: {'lr': 1.2542694540720877e-06, 'samples': 27893760, 'steps': 145279, 'loss/train': 1.22373366355896} 08/31/2021 15:34:20 - INFO - __main__ - Step 145281: {'lr': 1.2537385973375448e-06, 'samples': 27893952, 'steps': 145280, 'loss/train': 0.6005436778068542} 08/31/2021 15:34:20 - INFO - __main__ - Step 145282: {'lr': 1.2532078526842072e-06, 'samples': 27894144, 'steps': 145281, 'loss/train': 1.0315064191818237} 08/31/2021 15:34:20 - INFO - __main__ - Step 145283: {'lr': 1.2526772201123249e-06, 'samples': 27894336, 'steps': 145282, 'loss/train': 1.079476237297058} 08/31/2021 15:34:22 - INFO - __main__ - Step 145284: {'lr': 1.2521466996221753e-06, 'samples': 27894528, 'steps': 145283, 'loss/train': 0.08776997774839401} 08/31/2021 15:34:23 - INFO - __main__ - Step 145285: {'lr': 1.2516162912139528e-06, 'samples': 27894720, 'steps': 145284, 'loss/train': 1.595673680305481} 08/31/2021 15:34:23 - INFO - __main__ - Step 145286: {'lr': 1.2510859948879071e-06, 'samples': 27894912, 'steps': 145285, 'loss/train': 1.5144237279891968} 08/31/2021 15:34:24 - INFO - __main__ - Step 145287: {'lr': 1.250555810644316e-06, 'samples': 27895104, 'steps': 145286, 'loss/train': 1.0423284769058228} 08/31/2021 15:34:24 - INFO - __main__ - Step 145288: {'lr': 1.2500257384833736e-06, 'samples': 27895296, 'steps': 145287, 'loss/train': 0.8894967436790466} 08/31/2021 15:34:25 - INFO - __main__ - Step 145289: {'lr': 1.2494957784053019e-06, 'samples': 27895488, 'steps': 145288, 'loss/train': 0.035532597452402115} 08/31/2021 15:34:26 - INFO - __main__ - Step 145290: {'lr': 1.2489659304104062e-06, 'samples': 27895680, 'steps': 145289, 'loss/train': 1.8099843263626099} 08/31/2021 15:34:26 - INFO - __main__ - Step 145291: {'lr': 1.248436194498853e-06, 'samples': 27895872, 'steps': 145290, 'loss/train': 0.8164318799972534} 08/31/2021 15:34:26 - INFO - __main__ - Step 145292: {'lr': 1.247906570670948e-06, 'samples': 27896064, 'steps': 145291, 'loss/train': 1.6372689008712769} 08/31/2021 15:34:27 - INFO - __main__ - Step 145293: {'lr': 1.2473770589268852e-06, 'samples': 27896256, 'steps': 145292, 'loss/train': 0.6029307246208191} 08/31/2021 15:34:29 - INFO - __main__ - Step 145294: {'lr': 1.2468476592669143e-06, 'samples': 27896448, 'steps': 145293, 'loss/train': 0.9634100198745728} 08/31/2021 15:34:30 - INFO - __main__ - Step 145295: {'lr': 1.246318371691285e-06, 'samples': 27896640, 'steps': 145294, 'loss/train': 1.0416842699050903} 08/31/2021 15:34:30 - INFO - __main__ - Step 145296: {'lr': 1.2457891962001922e-06, 'samples': 27896832, 'steps': 145295, 'loss/train': 5.722753524780273} 08/31/2021 15:34:30 - INFO - __main__ - Step 145297: {'lr': 1.2452601327939405e-06, 'samples': 27897024, 'steps': 145296, 'loss/train': 1.3966925144195557} 08/31/2021 15:34:31 - INFO - __main__ - Step 145298: {'lr': 1.2447311814727524e-06, 'samples': 27897216, 'steps': 145297, 'loss/train': 0.9163579344749451} 08/31/2021 15:34:31 - INFO - __main__ - Step 145299: {'lr': 1.244202342236822e-06, 'samples': 27897408, 'steps': 145298, 'loss/train': 1.0976208448410034} 08/31/2021 15:34:31 - INFO - __main__ - Step 145300: {'lr': 1.243673615086427e-06, 'samples': 27897600, 'steps': 145299, 'loss/train': 0.4171101748943329} 08/31/2021 15:34:33 - INFO - __main__ - Step 145301: {'lr': 1.2431450000217615e-06, 'samples': 27897792, 'steps': 145300, 'loss/train': 0.023702049627900124} 08/31/2021 15:34:33 - INFO - __main__ - Step 145302: {'lr': 1.242616497043131e-06, 'samples': 27897984, 'steps': 145301, 'loss/train': 1.0123471021652222} 08/31/2021 15:34:34 - INFO - __main__ - Step 145303: {'lr': 1.2420881061507295e-06, 'samples': 27898176, 'steps': 145302, 'loss/train': 1.0675960779190063} 08/31/2021 15:34:34 - INFO - __main__ - Step 145304: {'lr': 1.241559827344807e-06, 'samples': 27898368, 'steps': 145303, 'loss/train': 0.6774590611457825} 08/31/2021 15:34:34 - INFO - __main__ - Step 145305: {'lr': 1.2410316606255856e-06, 'samples': 27898560, 'steps': 145304, 'loss/train': 1.1425164937973022} 08/31/2021 15:34:36 - INFO - __main__ - Step 145306: {'lr': 1.2405036059933427e-06, 'samples': 27898752, 'steps': 145305, 'loss/train': 0.1338777095079422} 08/31/2021 15:34:36 - INFO - __main__ - Step 145307: {'lr': 1.2399756634482728e-06, 'samples': 27898944, 'steps': 145306, 'loss/train': 1.63996160030365} 08/31/2021 15:34:37 - INFO - __main__ - Step 145308: {'lr': 1.2394478329906256e-06, 'samples': 27899136, 'steps': 145307, 'loss/train': 1.0387083292007446} 08/31/2021 15:34:37 - INFO - __main__ - Step 145309: {'lr': 1.2389201146206784e-06, 'samples': 27899328, 'steps': 145308, 'loss/train': 1.3919333219528198} 08/31/2021 15:34:37 - INFO - __main__ - Step 145310: {'lr': 1.2383925083385982e-06, 'samples': 27899520, 'steps': 145309, 'loss/train': 1.506675362586975} 08/31/2021 15:34:39 - INFO - __main__ - Step 145311: {'lr': 1.2378650141446624e-06, 'samples': 27899712, 'steps': 145310, 'loss/train': 0.6441639065742493} 08/31/2021 15:34:39 - INFO - __main__ - Step 145312: {'lr': 1.2373376320391206e-06, 'samples': 27899904, 'steps': 145311, 'loss/train': 0.7241489887237549} 08/31/2021 15:34:40 - INFO - __main__ - Step 145313: {'lr': 1.2368103620221949e-06, 'samples': 27900096, 'steps': 145312, 'loss/train': 0.7311826944351196} 08/31/2021 15:34:40 - INFO - __main__ - Step 145314: {'lr': 1.2362832040941075e-06, 'samples': 27900288, 'steps': 145313, 'loss/train': 1.1112170219421387} 08/31/2021 15:34:40 - INFO - __main__ - Step 145315: {'lr': 1.2357561582551357e-06, 'samples': 27900480, 'steps': 145314, 'loss/train': 0.7351357340812683} 08/31/2021 15:34:42 - INFO - __main__ - Step 145316: {'lr': 1.235229224505474e-06, 'samples': 27900672, 'steps': 145315, 'loss/train': 1.5278067588806152} 08/31/2021 15:34:42 - INFO - __main__ - Step 145317: {'lr': 1.2347024028454001e-06, 'samples': 27900864, 'steps': 145316, 'loss/train': 1.1811035871505737} 08/31/2021 15:34:43 - INFO - __main__ - Step 145318: {'lr': 1.234175693275108e-06, 'samples': 27901056, 'steps': 145317, 'loss/train': 1.2071526050567627} 08/31/2021 15:34:43 - INFO - __main__ - Step 145319: {'lr': 1.2336490957948477e-06, 'samples': 27901248, 'steps': 145318, 'loss/train': 0.8303143382072449} 08/31/2021 15:34:43 - INFO - __main__ - Step 145320: {'lr': 1.2331226104048965e-06, 'samples': 27901440, 'steps': 145319, 'loss/train': 1.5708599090576172} 08/31/2021 15:34:45 - INFO - __main__ - Step 145321: {'lr': 1.2325962371054766e-06, 'samples': 27901632, 'steps': 145320, 'loss/train': 1.552138090133667} 08/31/2021 15:34:45 - INFO - __main__ - Step 145322: {'lr': 1.2320699758967824e-06, 'samples': 27901824, 'steps': 145321, 'loss/train': 0.9257957935333252} 08/31/2021 15:34:46 - INFO - __main__ - Step 145323: {'lr': 1.2315438267790636e-06, 'samples': 27902016, 'steps': 145322, 'loss/train': 0.3889770209789276} 08/31/2021 15:34:46 - INFO - __main__ - Step 145324: {'lr': 1.2310177897525977e-06, 'samples': 27902208, 'steps': 145323, 'loss/train': 1.5753626823425293} 08/31/2021 15:34:46 - INFO - __main__ - Step 145325: {'lr': 1.230491864817579e-06, 'samples': 27902400, 'steps': 145324, 'loss/train': 1.0254135131835938} 08/31/2021 15:34:48 - INFO - __main__ - Step 145326: {'lr': 1.229966051974285e-06, 'samples': 27902592, 'steps': 145325, 'loss/train': 3.073033332824707} 08/31/2021 15:34:49 - INFO - __main__ - Step 145327: {'lr': 1.2294403512229103e-06, 'samples': 27902784, 'steps': 145326, 'loss/train': 1.2597764730453491} 08/31/2021 15:34:49 - INFO - __main__ - Step 145328: {'lr': 1.2289147625637042e-06, 'samples': 27902976, 'steps': 145327, 'loss/train': 1.8241411447525024} 08/31/2021 15:34:49 - INFO - __main__ - Step 145329: {'lr': 1.228389285996917e-06, 'samples': 27903168, 'steps': 145328, 'loss/train': 0.7708770036697388} 08/31/2021 15:34:50 - INFO - __main__ - Step 145330: {'lr': 1.2278639215227983e-06, 'samples': 27903360, 'steps': 145329, 'loss/train': 5.636222839355469} 08/31/2021 15:34:50 - INFO - __main__ - Step 145331: {'lr': 1.22733866914157e-06, 'samples': 27903552, 'steps': 145330, 'loss/train': 5.706679821014404} 08/31/2021 15:34:50 - INFO - __main__ - Step 145332: {'lr': 1.2268135288534266e-06, 'samples': 27903744, 'steps': 145331, 'loss/train': 1.4552760124206543} 08/31/2021 15:34:52 - INFO - __main__ - Step 145333: {'lr': 1.2262885006586732e-06, 'samples': 27903936, 'steps': 145332, 'loss/train': 1.3799149990081787} 08/31/2021 15:34:53 - INFO - __main__ - Step 145334: {'lr': 1.2257635845575044e-06, 'samples': 27904128, 'steps': 145333, 'loss/train': 1.530313491821289} 08/31/2021 15:34:53 - INFO - __main__ - Step 145335: {'lr': 1.2252387805501697e-06, 'samples': 27904320, 'steps': 145334, 'loss/train': 0.8162120580673218} 08/31/2021 15:34:53 - INFO - __main__ - Step 145336: {'lr': 1.2247140886368912e-06, 'samples': 27904512, 'steps': 145335, 'loss/train': 1.394993782043457} 08/31/2021 15:34:54 - INFO - __main__ - Step 145337: {'lr': 1.2241895088179189e-06, 'samples': 27904704, 'steps': 145336, 'loss/train': 1.2094873189926147} 08/31/2021 15:34:55 - INFO - __main__ - Step 145338: {'lr': 1.2236650410935024e-06, 'samples': 27904896, 'steps': 145337, 'loss/train': 0.9190184473991394} 08/31/2021 15:34:56 - INFO - __main__ - Step 145339: {'lr': 1.223140685463864e-06, 'samples': 27905088, 'steps': 145338, 'loss/train': 1.255389928817749} 08/31/2021 15:34:56 - INFO - __main__ - Step 145340: {'lr': 1.2226164419292252e-06, 'samples': 27905280, 'steps': 145339, 'loss/train': 1.618626594543457} 08/31/2021 15:34:56 - INFO - __main__ - Step 145341: {'lr': 1.2220923104898364e-06, 'samples': 27905472, 'steps': 145340, 'loss/train': 0.33828204870224} 08/31/2021 15:34:57 - INFO - __main__ - Step 145342: {'lr': 1.2215682911459469e-06, 'samples': 27905664, 'steps': 145341, 'loss/train': 0.3279208242893219} 08/31/2021 15:34:58 - INFO - __main__ - Step 145343: {'lr': 1.2210443838977791e-06, 'samples': 27905856, 'steps': 145342, 'loss/train': 0.9122441411018372} 08/31/2021 15:34:59 - INFO - __main__ - Step 145344: {'lr': 1.220520588745555e-06, 'samples': 27906048, 'steps': 145343, 'loss/train': 0.7256739735603333} 08/31/2021 15:34:59 - INFO - __main__ - Step 145345: {'lr': 1.2199969056895522e-06, 'samples': 27906240, 'steps': 145344, 'loss/train': 0.5732923150062561} 08/31/2021 15:34:59 - INFO - __main__ - Step 145346: {'lr': 1.2194733347299647e-06, 'samples': 27906432, 'steps': 145345, 'loss/train': 0.9606587290763855} 08/31/2021 15:35:00 - INFO - __main__ - Step 145347: {'lr': 1.2189498758670425e-06, 'samples': 27906624, 'steps': 145346, 'loss/train': 1.0382393598556519} 08/31/2021 15:35:00 - INFO - __main__ - Step 145348: {'lr': 1.2184265291010077e-06, 'samples': 27906816, 'steps': 145347, 'loss/train': 0.9386528730392456} 08/31/2021 15:35:02 - INFO - __main__ - Step 145349: {'lr': 1.2179032944321377e-06, 'samples': 27907008, 'steps': 145348, 'loss/train': 0.3893321454524994} 08/31/2021 15:35:03 - INFO - __main__ - Step 145350: {'lr': 1.217380171860627e-06, 'samples': 27907200, 'steps': 145349, 'loss/train': 1.0164752006530762} 08/31/2021 15:35:03 - INFO - __main__ - Step 145351: {'lr': 1.2168571613867253e-06, 'samples': 27907392, 'steps': 145350, 'loss/train': 0.6031122803688049} 08/31/2021 15:35:03 - INFO - __main__ - Step 145352: {'lr': 1.2163342630106821e-06, 'samples': 27907584, 'steps': 145351, 'loss/train': 1.2582074403762817} 08/31/2021 15:35:04 - INFO - __main__ - Step 145353: {'lr': 1.2158114767326922e-06, 'samples': 27907776, 'steps': 145352, 'loss/train': 1.063843011856079} 08/31/2021 15:35:06 - INFO - __main__ - Step 145354: {'lr': 1.215288802553033e-06, 'samples': 27907968, 'steps': 145353, 'loss/train': 0.9785943031311035} 08/31/2021 15:35:06 - INFO - __main__ - Step 145355: {'lr': 1.2147662404719262e-06, 'samples': 27908160, 'steps': 145354, 'loss/train': 0.3398923873901367} 08/31/2021 15:35:07 - INFO - __main__ - Step 145356: {'lr': 1.2142437904896219e-06, 'samples': 27908352, 'steps': 145355, 'loss/train': 1.098716378211975} 08/31/2021 15:35:07 - INFO - __main__ - Step 145357: {'lr': 1.2137214526063422e-06, 'samples': 27908544, 'steps': 145356, 'loss/train': 0.45781129598617554} 08/31/2021 15:35:07 - INFO - __main__ - Step 145358: {'lr': 1.2131992268222814e-06, 'samples': 27908736, 'steps': 145357, 'loss/train': 0.6978310942649841} 08/31/2021 15:35:09 - INFO - __main__ - Step 145359: {'lr': 1.2126771131377444e-06, 'samples': 27908928, 'steps': 145358, 'loss/train': 1.204379916191101} 08/31/2021 15:35:09 - INFO - __main__ - Step 145360: {'lr': 1.212155111552926e-06, 'samples': 27909120, 'steps': 145359, 'loss/train': 0.3627912700176239} 08/31/2021 15:35:10 - INFO - __main__ - Step 145361: {'lr': 1.2116332220680758e-06, 'samples': 27909312, 'steps': 145360, 'loss/train': 0.9958862066268921} 08/31/2021 15:35:10 - INFO - __main__ - Step 145362: {'lr': 1.2111114446834437e-06, 'samples': 27909504, 'steps': 145361, 'loss/train': 1.2643401622772217} 08/31/2021 15:35:10 - INFO - __main__ - Step 145363: {'lr': 1.2105897793992238e-06, 'samples': 27909696, 'steps': 145362, 'loss/train': 1.0962904691696167} 08/31/2021 15:35:11 - INFO - __main__ - Step 145364: {'lr': 1.210068226215666e-06, 'samples': 27909888, 'steps': 145363, 'loss/train': 1.1145890951156616} 08/31/2021 15:35:13 - INFO - __main__ - Step 145365: {'lr': 1.20954678513302e-06, 'samples': 27910080, 'steps': 145364, 'loss/train': 1.340361475944519} 08/31/2021 15:35:13 - INFO - __main__ - Step 145366: {'lr': 1.209025456151508e-06, 'samples': 27910272, 'steps': 145365, 'loss/train': 0.7484146952629089} 08/31/2021 15:35:13 - INFO - __main__ - Step 145367: {'lr': 1.2085042392713796e-06, 'samples': 27910464, 'steps': 145366, 'loss/train': 0.6510564088821411} 08/31/2021 15:35:14 - INFO - __main__ - Step 145368: {'lr': 1.207983134492857e-06, 'samples': 27910656, 'steps': 145367, 'loss/train': 0.7142650485038757} 08/31/2021 15:35:14 - INFO - __main__ - Step 145369: {'lr': 1.2074621418161902e-06, 'samples': 27910848, 'steps': 145368, 'loss/train': 0.4813281297683716} 08/31/2021 15:35:16 - INFO - __main__ - Step 145370: {'lr': 1.2069412612416008e-06, 'samples': 27911040, 'steps': 145369, 'loss/train': 1.2420181035995483} 08/31/2021 15:35:16 - INFO - __main__ - Step 145371: {'lr': 1.2064204927693111e-06, 'samples': 27911232, 'steps': 145370, 'loss/train': 1.3662961721420288} 08/31/2021 15:35:16 - INFO - __main__ - Step 145372: {'lr': 1.205899836399571e-06, 'samples': 27911424, 'steps': 145371, 'loss/train': 0.9356164932250977} 08/31/2021 15:35:17 - INFO - __main__ - Step 145373: {'lr': 1.2053792921326024e-06, 'samples': 27911616, 'steps': 145372, 'loss/train': 0.7484167814254761} 08/31/2021 15:35:17 - INFO - __main__ - Step 145374: {'lr': 1.2048588599686828e-06, 'samples': 27911808, 'steps': 145373, 'loss/train': 1.383810043334961} 08/31/2021 15:35:19 - INFO - __main__ - Step 145375: {'lr': 1.2043385399079787e-06, 'samples': 27912000, 'steps': 145374, 'loss/train': 1.4603469371795654} 08/31/2021 15:35:19 - INFO - __main__ - Step 145376: {'lr': 1.2038183319507957e-06, 'samples': 27912192, 'steps': 145375, 'loss/train': 0.8339101672172546} 08/31/2021 15:35:20 - INFO - __main__ - Step 145377: {'lr': 1.2032982360972999e-06, 'samples': 27912384, 'steps': 145376, 'loss/train': 1.0361272096633911} 08/31/2021 15:35:20 - INFO - __main__ - Step 145378: {'lr': 1.2027782523477693e-06, 'samples': 27912576, 'steps': 145377, 'loss/train': 0.8391222357749939} 08/31/2021 15:35:20 - INFO - __main__ - Step 145379: {'lr': 1.2022583807024257e-06, 'samples': 27912768, 'steps': 145378, 'loss/train': 0.802770733833313} 08/31/2021 15:35:22 - INFO - __main__ - Step 145380: {'lr': 1.201738621161519e-06, 'samples': 27912960, 'steps': 145379, 'loss/train': 0.940288245677948} 08/31/2021 15:35:22 - INFO - __main__ - Step 145381: {'lr': 1.201218973725271e-06, 'samples': 27913152, 'steps': 145380, 'loss/train': 1.408375859260559} 08/31/2021 15:35:23 - INFO - __main__ - Step 145382: {'lr': 1.200699438393904e-06, 'samples': 27913344, 'steps': 145381, 'loss/train': 0.9823253750801086} 08/31/2021 15:35:23 - INFO - __main__ - Step 145383: {'lr': 1.2001800151676678e-06, 'samples': 27913536, 'steps': 145382, 'loss/train': 0.7674738168716431} 08/31/2021 15:35:23 - INFO - __main__ - Step 145384: {'lr': 1.1996607040467845e-06, 'samples': 27913728, 'steps': 145383, 'loss/train': 0.0365624874830246} 08/31/2021 15:35:24 - INFO - __main__ - Step 145385: {'lr': 1.1991415050315035e-06, 'samples': 27913920, 'steps': 145384, 'loss/train': 0.20291754603385925} 08/31/2021 15:35:25 - INFO - __main__ - Step 145386: {'lr': 1.1986224181220473e-06, 'samples': 27914112, 'steps': 145385, 'loss/train': 0.6258845329284668} 08/31/2021 15:35:26 - INFO - __main__ - Step 145387: {'lr': 1.1981034433186378e-06, 'samples': 27914304, 'steps': 145386, 'loss/train': 1.502203106880188} 08/31/2021 15:35:26 - INFO - __main__ - Step 145388: {'lr': 1.1975845806215246e-06, 'samples': 27914496, 'steps': 145387, 'loss/train': 1.1804193258285522} 08/31/2021 15:35:26 - INFO - __main__ - Step 145389: {'lr': 1.1970658300309579e-06, 'samples': 27914688, 'steps': 145388, 'loss/train': 0.8398965001106262} 08/31/2021 15:35:27 - INFO - __main__ - Step 145390: {'lr': 1.1965471915471592e-06, 'samples': 27914880, 'steps': 145389, 'loss/train': 1.1628848314285278} 08/31/2021 15:35:29 - INFO - __main__ - Step 145391: {'lr': 1.1960286651703512e-06, 'samples': 27915072, 'steps': 145390, 'loss/train': 1.6302145719528198} 08/31/2021 15:35:29 - INFO - __main__ - Step 145392: {'lr': 1.1955102509007553e-06, 'samples': 27915264, 'steps': 145391, 'loss/train': 0.7934972047805786} 08/31/2021 15:35:29 - INFO - __main__ - Step 145393: {'lr': 1.1949919487386218e-06, 'samples': 27915456, 'steps': 145392, 'loss/train': 1.097159504890442} 08/31/2021 15:35:30 - INFO - __main__ - Step 145394: {'lr': 1.1944737586842002e-06, 'samples': 27915648, 'steps': 145393, 'loss/train': 1.2102242708206177} 08/31/2021 15:35:30 - INFO - __main__ - Step 145395: {'lr': 1.1939556807377128e-06, 'samples': 27915840, 'steps': 145394, 'loss/train': 1.1906883716583252} 08/31/2021 15:35:31 - INFO - __main__ - Step 145396: {'lr': 1.1934377148993814e-06, 'samples': 27916032, 'steps': 145395, 'loss/train': 0.05699215456843376} 08/31/2021 15:35:32 - INFO - __main__ - Step 145397: {'lr': 1.1929198611694837e-06, 'samples': 27916224, 'steps': 145396, 'loss/train': 0.7145869731903076} 08/31/2021 15:35:32 - INFO - __main__ - Step 145398: {'lr': 1.1924021195481582e-06, 'samples': 27916416, 'steps': 145397, 'loss/train': 1.083951473236084} 08/31/2021 15:35:33 - INFO - __main__ - Step 145399: {'lr': 1.1918844900357385e-06, 'samples': 27916608, 'steps': 145398, 'loss/train': 1.3928300142288208} 08/31/2021 15:35:33 - INFO - __main__ - Step 145400: {'lr': 1.1913669726323905e-06, 'samples': 27916800, 'steps': 145399, 'loss/train': 1.5620545148849487} 08/31/2021 15:35:35 - INFO - __main__ - Step 145401: {'lr': 1.1908495673383924e-06, 'samples': 27916992, 'steps': 145400, 'loss/train': 1.138598084449768} 08/31/2021 15:35:35 - INFO - __main__ - Step 145402: {'lr': 1.190332274153938e-06, 'samples': 27917184, 'steps': 145401, 'loss/train': 1.4314560890197754} 08/31/2021 15:35:36 - INFO - __main__ - Step 145403: {'lr': 1.189815093079305e-06, 'samples': 27917376, 'steps': 145402, 'loss/train': 0.9837670922279358} 08/31/2021 15:35:36 - INFO - __main__ - Step 145404: {'lr': 1.1892980241146879e-06, 'samples': 27917568, 'steps': 145403, 'loss/train': 0.8386191725730896} 08/31/2021 15:35:36 - INFO - __main__ - Step 145405: {'lr': 1.188781067260336e-06, 'samples': 27917760, 'steps': 145404, 'loss/train': 1.0960367918014526} 08/31/2021 15:35:37 - INFO - __main__ - Step 145406: {'lr': 1.188264222516472e-06, 'samples': 27917952, 'steps': 145405, 'loss/train': 1.378166913986206} 08/31/2021 15:35:38 - INFO - __main__ - Step 145407: {'lr': 1.1877474898833451e-06, 'samples': 27918144, 'steps': 145406, 'loss/train': 1.02308988571167} 08/31/2021 15:35:39 - INFO - __main__ - Step 145408: {'lr': 1.1872308693611777e-06, 'samples': 27918336, 'steps': 145407, 'loss/train': 1.0973398685455322} 08/31/2021 15:35:39 - INFO - __main__ - Step 145409: {'lr': 1.1867143609502196e-06, 'samples': 27918528, 'steps': 145408, 'loss/train': 1.3313885927200317} 08/31/2021 15:35:39 - INFO - __main__ - Step 145410: {'lr': 1.1861979646506649e-06, 'samples': 27918720, 'steps': 145409, 'loss/train': 0.48031264543533325} 08/31/2021 15:35:40 - INFO - __main__ - Step 145411: {'lr': 1.1856816804627912e-06, 'samples': 27918912, 'steps': 145410, 'loss/train': 1.2530126571655273} 08/31/2021 15:35:41 - INFO - __main__ - Step 145412: {'lr': 1.1851655083867929e-06, 'samples': 27919104, 'steps': 145411, 'loss/train': 0.662722647190094} 08/31/2021 15:35:42 - INFO - __main__ - Step 145413: {'lr': 1.1846494484229198e-06, 'samples': 27919296, 'steps': 145412, 'loss/train': 1.31016206741333} 08/31/2021 15:35:42 - INFO - __main__ - Step 145414: {'lr': 1.1841335005714215e-06, 'samples': 27919488, 'steps': 145413, 'loss/train': 1.2707487344741821} 08/31/2021 15:35:43 - INFO - __main__ - Step 145415: {'lr': 1.1836176648324925e-06, 'samples': 27919680, 'steps': 145414, 'loss/train': 0.9564348459243774} 08/31/2021 15:35:43 - INFO - __main__ - Step 145416: {'lr': 1.1831019412063826e-06, 'samples': 27919872, 'steps': 145415, 'loss/train': 1.2758588790893555} 08/31/2021 15:35:44 - INFO - __main__ - Step 145417: {'lr': 1.1825863296933415e-06, 'samples': 27920064, 'steps': 145416, 'loss/train': 0.9566817283630371} 08/31/2021 15:35:45 - INFO - __main__ - Step 145418: {'lr': 1.1820708302935913e-06, 'samples': 27920256, 'steps': 145417, 'loss/train': 1.5895719528198242} 08/31/2021 15:35:45 - INFO - __main__ - Step 145419: {'lr': 1.1815554430073538e-06, 'samples': 27920448, 'steps': 145418, 'loss/train': 1.239463448524475} 08/31/2021 15:35:46 - INFO - __main__ - Step 145420: {'lr': 1.1810401678348792e-06, 'samples': 27920640, 'steps': 145419, 'loss/train': 0.9496492743492126} 08/31/2021 15:35:46 - INFO - __main__ - Step 145421: {'lr': 1.1805250047763616e-06, 'samples': 27920832, 'steps': 145420, 'loss/train': 0.6216456294059753} 08/31/2021 15:35:46 - INFO - __main__ - Step 145422: {'lr': 1.1800099538320785e-06, 'samples': 27921024, 'steps': 145421, 'loss/train': 1.1006447076797485} 08/31/2021 15:35:49 - INFO - __main__ - Step 145423: {'lr': 1.1794950150022522e-06, 'samples': 27921216, 'steps': 145422, 'loss/train': 1.2087290287017822} 08/31/2021 15:35:49 - INFO - __main__ - Step 145424: {'lr': 1.1789801882871043e-06, 'samples': 27921408, 'steps': 145423, 'loss/train': 1.2604955434799194} 08/31/2021 15:35:50 - INFO - __main__ - Step 145425: {'lr': 1.1784654736868571e-06, 'samples': 27921600, 'steps': 145424, 'loss/train': 1.4664686918258667} 08/31/2021 15:35:50 - INFO - __main__ - Step 145426: {'lr': 1.1779508712017607e-06, 'samples': 27921792, 'steps': 145425, 'loss/train': 0.2313372790813446} 08/31/2021 15:35:50 - INFO - __main__ - Step 145427: {'lr': 1.1774363808320087e-06, 'samples': 27921984, 'steps': 145426, 'loss/train': 0.23076952993869781} 08/31/2021 15:35:51 - INFO - __main__ - Step 145428: {'lr': 1.176922002577907e-06, 'samples': 27922176, 'steps': 145427, 'loss/train': 1.4654935598373413} 08/31/2021 15:35:52 - INFO - __main__ - Step 145429: {'lr': 1.176407736439622e-06, 'samples': 27922368, 'steps': 145428, 'loss/train': 0.6339372396469116} 08/31/2021 15:35:53 - INFO - __main__ - Step 145430: {'lr': 1.1758935824174033e-06, 'samples': 27922560, 'steps': 145429, 'loss/train': 0.7374603152275085} 08/31/2021 15:35:53 - INFO - __main__ - Step 145431: {'lr': 1.1753795405115009e-06, 'samples': 27922752, 'steps': 145430, 'loss/train': 0.08556349575519562} 08/31/2021 15:35:53 - INFO - __main__ - Step 145432: {'lr': 1.1748656107221366e-06, 'samples': 27922944, 'steps': 145431, 'loss/train': 1.1061991453170776} 08/31/2021 15:35:54 - INFO - __main__ - Step 145433: {'lr': 1.1743517930495329e-06, 'samples': 27923136, 'steps': 145432, 'loss/train': 1.3133279085159302} 08/31/2021 15:35:55 - INFO - __main__ - Step 145434: {'lr': 1.173838087493939e-06, 'samples': 27923328, 'steps': 145433, 'loss/train': 0.9833865165710449} 08/31/2021 15:35:56 - INFO - __main__ - Step 145435: {'lr': 1.1733244940555499e-06, 'samples': 27923520, 'steps': 145434, 'loss/train': 0.4948348104953766} 08/31/2021 15:35:56 - INFO - __main__ - Step 145436: {'lr': 1.1728110127346424e-06, 'samples': 27923712, 'steps': 145435, 'loss/train': 0.8602849841117859} 08/31/2021 15:35:56 - INFO - __main__ - Step 145437: {'lr': 1.1722976435314115e-06, 'samples': 27923904, 'steps': 145436, 'loss/train': 0.516488254070282} 08/31/2021 15:35:57 - INFO - __main__ - Step 145438: {'lr': 1.1717843864461065e-06, 'samples': 27924096, 'steps': 145437, 'loss/train': 1.4101721048355103} 08/31/2021 15:35:58 - INFO - __main__ - Step 145439: {'lr': 1.1712712414789496e-06, 'samples': 27924288, 'steps': 145438, 'loss/train': 1.260985016822815} 08/31/2021 15:35:59 - INFO - __main__ - Step 145440: {'lr': 1.1707582086301905e-06, 'samples': 27924480, 'steps': 145439, 'loss/train': 0.9145862460136414} 08/31/2021 15:35:59 - INFO - __main__ - Step 145441: {'lr': 1.1702452879000514e-06, 'samples': 27924672, 'steps': 145440, 'loss/train': 1.5495359897613525} 08/31/2021 15:35:59 - INFO - __main__ - Step 145442: {'lr': 1.1697324792887544e-06, 'samples': 27924864, 'steps': 145441, 'loss/train': 0.9494919776916504} 08/31/2021 15:36:00 - INFO - __main__ - Step 145443: {'lr': 1.1692197827965211e-06, 'samples': 27925056, 'steps': 145442, 'loss/train': 0.967411458492279} 08/31/2021 15:36:01 - INFO - __main__ - Step 145444: {'lr': 1.1687071984236298e-06, 'samples': 27925248, 'steps': 145443, 'loss/train': 0.5333949327468872} 08/31/2021 15:36:02 - INFO - __main__ - Step 145445: {'lr': 1.1681947261702464e-06, 'samples': 27925440, 'steps': 145444, 'loss/train': 1.2866742610931396} 08/31/2021 15:36:02 - INFO - __main__ - Step 145446: {'lr': 1.1676823660366486e-06, 'samples': 27925632, 'steps': 145445, 'loss/train': 0.9010270237922668} 08/31/2021 15:36:02 - INFO - __main__ - Step 145447: {'lr': 1.1671701180230588e-06, 'samples': 27925824, 'steps': 145446, 'loss/train': 0.9475289583206177} 08/31/2021 15:36:03 - INFO - __main__ - Step 145448: {'lr': 1.1666579821296986e-06, 'samples': 27926016, 'steps': 145447, 'loss/train': 0.871455729007721} 08/31/2021 15:36:03 - INFO - __main__ - Step 145449: {'lr': 1.1661459583567902e-06, 'samples': 27926208, 'steps': 145448, 'loss/train': 1.5687860250473022} 08/31/2021 15:36:05 - INFO - __main__ - Step 145450: {'lr': 1.165634046704611e-06, 'samples': 27926400, 'steps': 145449, 'loss/train': 1.2747623920440674} 08/31/2021 15:36:05 - INFO - __main__ - Step 145451: {'lr': 1.1651222471733281e-06, 'samples': 27926592, 'steps': 145450, 'loss/train': 1.2999979257583618} 08/31/2021 15:36:06 - INFO - __main__ - Step 145452: {'lr': 1.1646105597631906e-06, 'samples': 27926784, 'steps': 145451, 'loss/train': 1.4394744634628296} 08/31/2021 15:36:06 - INFO - __main__ - Step 145453: {'lr': 1.1640989844744764e-06, 'samples': 27926976, 'steps': 145452, 'loss/train': 1.2322587966918945} 08/31/2021 15:36:06 - INFO - __main__ - Step 145454: {'lr': 1.1635875213073522e-06, 'samples': 27927168, 'steps': 145453, 'loss/train': 0.016232315450906754} 08/31/2021 15:36:07 - INFO - __main__ - Step 145455: {'lr': 1.1630761702620952e-06, 'samples': 27927360, 'steps': 145454, 'loss/train': 0.03837273642420769} 08/31/2021 15:36:09 - INFO - __main__ - Step 145456: {'lr': 1.1625649313388998e-06, 'samples': 27927552, 'steps': 145455, 'loss/train': 0.817348837852478} 08/31/2021 15:36:09 - INFO - __main__ - Step 145457: {'lr': 1.1620538045380158e-06, 'samples': 27927744, 'steps': 145456, 'loss/train': 0.73881596326828} 08/31/2021 15:36:10 - INFO - __main__ - Step 145458: {'lr': 1.1615427898596653e-06, 'samples': 27927936, 'steps': 145457, 'loss/train': 1.055042028427124} 08/31/2021 15:36:10 - INFO - __main__ - Step 145459: {'lr': 1.161031887304098e-06, 'samples': 27928128, 'steps': 145458, 'loss/train': 0.016425084322690964} 08/31/2021 15:36:10 - INFO - __main__ - Step 145460: {'lr': 1.1605210968715086e-06, 'samples': 27928320, 'steps': 145459, 'loss/train': 1.1862753629684448} 08/31/2021 15:36:11 - INFO - __main__ - Step 145461: {'lr': 1.160010418562174e-06, 'samples': 27928512, 'steps': 145460, 'loss/train': 1.6047981977462769} 08/31/2021 15:36:13 - INFO - __main__ - Step 145462: {'lr': 1.159499852376289e-06, 'samples': 27928704, 'steps': 145461, 'loss/train': 1.1538041830062866} 08/31/2021 15:36:13 - INFO - __main__ - Step 145463: {'lr': 1.1589893983140753e-06, 'samples': 27928896, 'steps': 145462, 'loss/train': 1.0671170949935913} 08/31/2021 15:36:14 - INFO - __main__ - Step 145464: {'lr': 1.1584790563758108e-06, 'samples': 27929088, 'steps': 145463, 'loss/train': 1.7290135622024536} 08/31/2021 15:36:14 - INFO - __main__ - Step 145465: {'lr': 1.1579688265616895e-06, 'samples': 27929280, 'steps': 145464, 'loss/train': 0.7859745025634766} 08/31/2021 15:36:14 - INFO - __main__ - Step 145466: {'lr': 1.1574587088719335e-06, 'samples': 27929472, 'steps': 145465, 'loss/train': 1.1716272830963135} 08/31/2021 15:36:15 - INFO - __main__ - Step 145467: {'lr': 1.1569487033067926e-06, 'samples': 27929664, 'steps': 145466, 'loss/train': 1.0296367406845093} 08/31/2021 15:36:16 - INFO - __main__ - Step 145468: {'lr': 1.156438809866489e-06, 'samples': 27929856, 'steps': 145467, 'loss/train': 1.6376515626907349} 08/31/2021 15:36:17 - INFO - __main__ - Step 145469: {'lr': 1.1559290285512724e-06, 'samples': 27930048, 'steps': 145468, 'loss/train': 0.5981963872909546} 08/31/2021 15:36:17 - INFO - __main__ - Step 145470: {'lr': 1.155419359361337e-06, 'samples': 27930240, 'steps': 145469, 'loss/train': 0.6232224106788635} 08/31/2021 15:36:17 - INFO - __main__ - Step 145471: {'lr': 1.1549098022969328e-06, 'samples': 27930432, 'steps': 145470, 'loss/train': 1.0765185356140137} 08/31/2021 15:36:18 - INFO - __main__ - Step 145472: {'lr': 1.1544003573582818e-06, 'samples': 27930624, 'steps': 145471, 'loss/train': 1.0543180704116821} 08/31/2021 15:36:19 - INFO - __main__ - Step 145473: {'lr': 1.1538910245456058e-06, 'samples': 27930816, 'steps': 145472, 'loss/train': 0.9048942923545837} 08/31/2021 15:36:20 - INFO - __main__ - Step 145474: {'lr': 1.1533818038591826e-06, 'samples': 27931008, 'steps': 145473, 'loss/train': 1.5672000646591187} 08/31/2021 15:36:20 - INFO - __main__ - Step 145475: {'lr': 1.1528726952991786e-06, 'samples': 27931200, 'steps': 145474, 'loss/train': 1.1843675374984741} 08/31/2021 15:36:21 - INFO - __main__ - Step 145476: {'lr': 1.1523636988658436e-06, 'samples': 27931392, 'steps': 145475, 'loss/train': 0.9590216875076294} 08/31/2021 15:36:21 - INFO - __main__ - Step 145477: {'lr': 1.1518548145594554e-06, 'samples': 27931584, 'steps': 145476, 'loss/train': 0.0684104636311531} 08/31/2021 15:36:23 - INFO - __main__ - Step 145478: {'lr': 1.1513460423801524e-06, 'samples': 27931776, 'steps': 145477, 'loss/train': 1.0381771326065063} 08/31/2021 15:36:23 - INFO - __main__ - Step 145479: {'lr': 1.1508373823282402e-06, 'samples': 27931968, 'steps': 145478, 'loss/train': 0.7411602139472961} 08/31/2021 15:36:23 - INFO - __main__ - Step 145480: {'lr': 1.1503288344039132e-06, 'samples': 27932160, 'steps': 145479, 'loss/train': 0.44184184074401855} 08/31/2021 15:36:24 - INFO - __main__ - Step 145481: {'lr': 1.1498203986074207e-06, 'samples': 27932352, 'steps': 145480, 'loss/train': 1.5162640810012817} 08/31/2021 15:36:24 - INFO - __main__ - Step 145482: {'lr': 1.1493120749389573e-06, 'samples': 27932544, 'steps': 145481, 'loss/train': 1.0178366899490356} 08/31/2021 15:36:26 - INFO - __main__ - Step 145483: {'lr': 1.148803863398773e-06, 'samples': 27932736, 'steps': 145482, 'loss/train': 0.6397128701210022} 08/31/2021 15:36:26 - INFO - __main__ - Step 145484: {'lr': 1.1482957639871172e-06, 'samples': 27932928, 'steps': 145483, 'loss/train': 0.9552046656608582} 08/31/2021 15:36:26 - INFO - __main__ - Step 145485: {'lr': 1.1477877767041844e-06, 'samples': 27933120, 'steps': 145484, 'loss/train': 0.4917597472667694} 08/31/2021 15:36:27 - INFO - __main__ - Step 145486: {'lr': 1.1472799015502244e-06, 'samples': 27933312, 'steps': 145485, 'loss/train': 1.0618075132369995} 08/31/2021 15:36:27 - INFO - __main__ - Step 145487: {'lr': 1.1467721385254593e-06, 'samples': 27933504, 'steps': 145486, 'loss/train': 0.4433017075061798} 08/31/2021 15:36:29 - INFO - __main__ - Step 145488: {'lr': 1.1462644876301387e-06, 'samples': 27933696, 'steps': 145487, 'loss/train': 0.18083345890045166} 08/31/2021 15:36:29 - INFO - __main__ - Step 145489: {'lr': 1.1457569488644293e-06, 'samples': 27933888, 'steps': 145488, 'loss/train': 1.4753828048706055} 08/31/2021 15:36:29 - INFO - __main__ - Step 145490: {'lr': 1.1452495222286363e-06, 'samples': 27934080, 'steps': 145489, 'loss/train': 0.5678617358207703} 08/31/2021 15:36:30 - INFO - __main__ - Step 145491: {'lr': 1.1447422077229542e-06, 'samples': 27934272, 'steps': 145490, 'loss/train': 0.7987917065620422} 08/31/2021 15:36:30 - INFO - __main__ - Step 145492: {'lr': 1.1442350053476048e-06, 'samples': 27934464, 'steps': 145491, 'loss/train': 1.1993030309677124} 08/31/2021 15:36:32 - INFO - __main__ - Step 145493: {'lr': 1.1437279151028102e-06, 'samples': 27934656, 'steps': 145492, 'loss/train': 0.9293263554573059} 08/31/2021 15:36:32 - INFO - __main__ - Step 145494: {'lr': 1.1432209369888202e-06, 'samples': 27934848, 'steps': 145493, 'loss/train': 1.4518393278121948} 08/31/2021 15:36:32 - INFO - __main__ - Step 145495: {'lr': 1.142714071005857e-06, 'samples': 27935040, 'steps': 145494, 'loss/train': 0.5094594955444336} 08/31/2021 15:36:33 - INFO - __main__ - Step 145496: {'lr': 1.1422073171541424e-06, 'samples': 27935232, 'steps': 145495, 'loss/train': 1.3436212539672852} 08/31/2021 15:36:33 - INFO - __main__ - Step 145497: {'lr': 1.1417006754338988e-06, 'samples': 27935424, 'steps': 145496, 'loss/train': 1.404923439025879} 08/31/2021 15:36:35 - INFO - __main__ - Step 145498: {'lr': 1.1411941458453755e-06, 'samples': 27935616, 'steps': 145497, 'loss/train': 0.7918860912322998} 08/31/2021 15:36:35 - INFO - __main__ - Step 145499: {'lr': 1.140687728388795e-06, 'samples': 27935808, 'steps': 145498, 'loss/train': 1.205543875694275} 08/31/2021 15:36:35 - INFO - __main__ - Step 145500: {'lr': 1.1401814230643791e-06, 'samples': 27936000, 'steps': 145499, 'loss/train': 1.350069284439087} 08/31/2021 15:36:36 - INFO - __main__ - Step 145501: {'lr': 1.13967522987235e-06, 'samples': 27936192, 'steps': 145500, 'loss/train': 0.8481290936470032} 08/31/2021 15:36:36 - INFO - __main__ - Step 145502: {'lr': 1.1391691488129296e-06, 'samples': 27936384, 'steps': 145501, 'loss/train': 1.3726749420166016} 08/31/2021 15:36:36 - INFO - __main__ - Step 145503: {'lr': 1.1386631798863956e-06, 'samples': 27936576, 'steps': 145502, 'loss/train': 0.8900147676467896} 08/31/2021 15:36:38 - INFO - __main__ - Step 145504: {'lr': 1.1381573230929143e-06, 'samples': 27936768, 'steps': 145503, 'loss/train': 1.3385728597640991} 08/31/2021 15:36:38 - INFO - __main__ - Step 145505: {'lr': 1.1376515784327634e-06, 'samples': 27936960, 'steps': 145504, 'loss/train': 0.6924827098846436} 08/31/2021 15:36:39 - INFO - __main__ - Step 145506: {'lr': 1.1371459459061095e-06, 'samples': 27937152, 'steps': 145505, 'loss/train': 1.4088261127471924} 08/31/2021 15:36:39 - INFO - __main__ - Step 145507: {'lr': 1.1366404255132578e-06, 'samples': 27937344, 'steps': 145506, 'loss/train': 0.9314965605735779} 08/31/2021 15:36:39 - INFO - __main__ - Step 145508: {'lr': 1.1361350172543749e-06, 'samples': 27937536, 'steps': 145507, 'loss/train': 0.09685208648443222} 08/31/2021 15:36:41 - INFO - __main__ - Step 145509: {'lr': 1.1356297211297107e-06, 'samples': 27937728, 'steps': 145508, 'loss/train': 1.7781240940093994} 08/31/2021 15:36:41 - INFO - __main__ - Step 145510: {'lr': 1.135124537139487e-06, 'samples': 27937920, 'steps': 145509, 'loss/train': 0.9946441054344177} 08/31/2021 15:36:42 - INFO - __main__ - Step 145511: {'lr': 1.134619465283926e-06, 'samples': 27938112, 'steps': 145510, 'loss/train': 1.1525367498397827} 08/31/2021 15:36:42 - INFO - __main__ - Step 145512: {'lr': 1.1341145055632774e-06, 'samples': 27938304, 'steps': 145511, 'loss/train': 1.6711400747299194} 08/31/2021 15:36:42 - INFO - __main__ - Step 145513: {'lr': 1.1336096579777632e-06, 'samples': 27938496, 'steps': 145512, 'loss/train': 1.585500955581665} 08/31/2021 15:36:45 - INFO - __main__ - Step 145514: {'lr': 1.1331049225276059e-06, 'samples': 27938688, 'steps': 145513, 'loss/train': 0.8605786561965942} 08/31/2021 15:36:45 - INFO - __main__ - Step 145515: {'lr': 1.132600299213027e-06, 'samples': 27938880, 'steps': 145514, 'loss/train': 1.0154050588607788} 08/31/2021 15:36:45 - INFO - __main__ - Step 145516: {'lr': 1.1320957880342486e-06, 'samples': 27939072, 'steps': 145515, 'loss/train': 0.5332388281822205} 08/31/2021 15:36:46 - INFO - __main__ - Step 145517: {'lr': 1.1315913889915209e-06, 'samples': 27939264, 'steps': 145516, 'loss/train': 1.2441836595535278} 08/31/2021 15:36:46 - INFO - __main__ - Step 145518: {'lr': 1.1310871020850377e-06, 'samples': 27939456, 'steps': 145517, 'loss/train': 1.184056043624878} 08/31/2021 15:36:48 - INFO - __main__ - Step 145519: {'lr': 1.130582927315077e-06, 'samples': 27939648, 'steps': 145518, 'loss/train': 1.314980387687683} 08/31/2021 15:36:48 - INFO - __main__ - Step 145520: {'lr': 1.130078864681805e-06, 'samples': 27939840, 'steps': 145519, 'loss/train': 1.139156460762024} 08/31/2021 15:36:48 - INFO - __main__ - Step 145521: {'lr': 1.1295749141854994e-06, 'samples': 27940032, 'steps': 145520, 'loss/train': 0.6498112082481384} 08/31/2021 15:36:49 - INFO - __main__ - Step 145522: {'lr': 1.1290710758263545e-06, 'samples': 27940224, 'steps': 145521, 'loss/train': 0.6080315709114075} 08/31/2021 15:36:49 - INFO - __main__ - Step 145523: {'lr': 1.12856734960462e-06, 'samples': 27940416, 'steps': 145522, 'loss/train': 0.9715793132781982} 08/31/2021 15:36:51 - INFO - __main__ - Step 145524: {'lr': 1.1280637355205182e-06, 'samples': 27940608, 'steps': 145523, 'loss/train': 1.0848675966262817} 08/31/2021 15:36:51 - INFO - __main__ - Step 145525: {'lr': 1.1275602335742429e-06, 'samples': 27940800, 'steps': 145524, 'loss/train': 0.3818615674972534} 08/31/2021 15:36:51 - INFO - __main__ - Step 145526: {'lr': 1.1270568437660723e-06, 'samples': 27940992, 'steps': 145525, 'loss/train': 0.589363157749176} 08/31/2021 15:36:52 - INFO - __main__ - Step 145527: {'lr': 1.1265535660962001e-06, 'samples': 27941184, 'steps': 145526, 'loss/train': 1.3167248964309692} 08/31/2021 15:36:52 - INFO - __main__ - Step 145528: {'lr': 1.1260504005648765e-06, 'samples': 27941376, 'steps': 145527, 'loss/train': 1.1109728813171387} 08/31/2021 15:36:52 - INFO - __main__ - Step 145529: {'lr': 1.1255473471722954e-06, 'samples': 27941568, 'steps': 145528, 'loss/train': 0.9119405150413513} 08/31/2021 15:36:55 - INFO - __main__ - Step 145530: {'lr': 1.125044405918707e-06, 'samples': 27941760, 'steps': 145529, 'loss/train': 0.9231281876564026} 08/31/2021 15:36:55 - INFO - __main__ - Step 145531: {'lr': 1.124541576804361e-06, 'samples': 27941952, 'steps': 145530, 'loss/train': 1.2061384916305542} 08/31/2021 15:36:56 - INFO - __main__ - Step 145532: {'lr': 1.1240388598294238e-06, 'samples': 27942144, 'steps': 145531, 'loss/train': 0.9848916530609131} 08/31/2021 15:36:56 - INFO - __main__ - Step 145533: {'lr': 1.1235362549941453e-06, 'samples': 27942336, 'steps': 145532, 'loss/train': 0.25659477710723877} 08/31/2021 15:36:56 - INFO - __main__ - Step 145534: {'lr': 1.1230337622987752e-06, 'samples': 27942528, 'steps': 145533, 'loss/train': 0.23428624868392944} 08/31/2021 15:36:57 - INFO - __main__ - Step 145535: {'lr': 1.1225313817435355e-06, 'samples': 27942720, 'steps': 145534, 'loss/train': 0.9741677045822144} 08/31/2021 15:36:59 - INFO - __main__ - Step 145536: {'lr': 1.1220291133286486e-06, 'samples': 27942912, 'steps': 145535, 'loss/train': 0.9779700636863708} 08/31/2021 15:36:59 - INFO - __main__ - Step 145537: {'lr': 1.1215269570543086e-06, 'samples': 27943104, 'steps': 145536, 'loss/train': 1.9944820404052734} 08/31/2021 15:36:59 - INFO - __main__ - Step 145538: {'lr': 1.1210249129207929e-06, 'samples': 27943296, 'steps': 145537, 'loss/train': 0.4905310869216919} 08/31/2021 15:37:00 - INFO - __main__ - Step 145539: {'lr': 1.1205229809282958e-06, 'samples': 27943488, 'steps': 145538, 'loss/train': 0.7068735957145691} 08/31/2021 15:37:00 - INFO - __main__ - Step 145540: {'lr': 1.1200211610770394e-06, 'samples': 27943680, 'steps': 145539, 'loss/train': 1.0860896110534668} 08/31/2021 15:37:00 - INFO - __main__ - Step 145541: {'lr': 1.1195194533672737e-06, 'samples': 27943872, 'steps': 145540, 'loss/train': 0.4070773124694824} 08/31/2021 15:37:02 - INFO - __main__ - Step 145542: {'lr': 1.1190178577991928e-06, 'samples': 27944064, 'steps': 145541, 'loss/train': 1.2066375017166138} 08/31/2021 15:37:02 - INFO - __main__ - Step 145543: {'lr': 1.1185163743730465e-06, 'samples': 27944256, 'steps': 145542, 'loss/train': 1.476602554321289} 08/31/2021 15:37:03 - INFO - __main__ - Step 145544: {'lr': 1.1180150030890846e-06, 'samples': 27944448, 'steps': 145543, 'loss/train': 1.4627712965011597} 08/31/2021 15:37:03 - INFO - __main__ - Step 145545: {'lr': 1.1175137439475013e-06, 'samples': 27944640, 'steps': 145544, 'loss/train': 0.8238804340362549} 08/31/2021 15:37:03 - INFO - __main__ - Step 145546: {'lr': 1.1170125969484912e-06, 'samples': 27944832, 'steps': 145545, 'loss/train': 1.0197213888168335} 08/31/2021 15:37:05 - INFO - __main__ - Step 145547: {'lr': 1.1165115620923317e-06, 'samples': 27945024, 'steps': 145546, 'loss/train': 1.713483452796936} 08/31/2021 15:37:05 - INFO - __main__ - Step 145548: {'lr': 1.1160106393792445e-06, 'samples': 27945216, 'steps': 145547, 'loss/train': 1.114660382270813} 08/31/2021 15:37:06 - INFO - __main__ - Step 145549: {'lr': 1.1155098288094245e-06, 'samples': 27945408, 'steps': 145548, 'loss/train': 1.2676117420196533} 08/31/2021 15:37:06 - INFO - __main__ - Step 145550: {'lr': 1.115009130383121e-06, 'samples': 27945600, 'steps': 145549, 'loss/train': 1.2764854431152344} 08/31/2021 15:37:06 - INFO - __main__ - Step 145551: {'lr': 1.1145085441005565e-06, 'samples': 27945792, 'steps': 145550, 'loss/train': 0.37796321511268616} 08/31/2021 15:37:08 - INFO - __main__ - Step 145552: {'lr': 1.1140080699619527e-06, 'samples': 27945984, 'steps': 145551, 'loss/train': 0.868546724319458} 08/31/2021 15:37:08 - INFO - __main__ - Step 145553: {'lr': 1.1135077079675316e-06, 'samples': 27946176, 'steps': 145552, 'loss/train': 1.424458622932434} 08/31/2021 15:37:09 - INFO - __main__ - Step 145554: {'lr': 1.1130074581175431e-06, 'samples': 27946368, 'steps': 145553, 'loss/train': 0.7180452346801758} 08/31/2021 15:37:09 - INFO - __main__ - Step 145555: {'lr': 1.1125073204121538e-06, 'samples': 27946560, 'steps': 145554, 'loss/train': 0.9831549525260925} 08/31/2021 15:37:09 - INFO - __main__ - Step 145556: {'lr': 1.112007294851669e-06, 'samples': 27946752, 'steps': 145555, 'loss/train': 1.1245023012161255} 08/31/2021 15:37:11 - INFO - __main__ - Step 145557: {'lr': 1.1115073814362553e-06, 'samples': 27946944, 'steps': 145556, 'loss/train': 0.6824666857719421} 08/31/2021 15:37:12 - INFO - __main__ - Step 145558: {'lr': 1.1110075801661622e-06, 'samples': 27947136, 'steps': 145557, 'loss/train': 0.7132357954978943} 08/31/2021 15:37:12 - INFO - __main__ - Step 145559: {'lr': 1.1105078910416121e-06, 'samples': 27947328, 'steps': 145558, 'loss/train': 1.1975553035736084} 08/31/2021 15:37:12 - INFO - __main__ - Step 145560: {'lr': 1.1100083140627993e-06, 'samples': 27947520, 'steps': 145559, 'loss/train': 0.12382229417562485} 08/31/2021 15:37:13 - INFO - __main__ - Step 145561: {'lr': 1.109508849230001e-06, 'samples': 27947712, 'steps': 145560, 'loss/train': 1.05746328830719} 08/31/2021 15:37:14 - INFO - __main__ - Step 145562: {'lr': 1.1090094965434117e-06, 'samples': 27947904, 'steps': 145561, 'loss/train': 0.5053921937942505} 08/31/2021 15:37:15 - INFO - __main__ - Step 145563: {'lr': 1.1085102560032534e-06, 'samples': 27948096, 'steps': 145562, 'loss/train': 0.9703015685081482} 08/31/2021 15:37:15 - INFO - __main__ - Step 145564: {'lr': 1.1080111276097759e-06, 'samples': 27948288, 'steps': 145563, 'loss/train': 0.6654146909713745} 08/31/2021 15:37:15 - INFO - __main__ - Step 145565: {'lr': 1.1075121113631736e-06, 'samples': 27948480, 'steps': 145564, 'loss/train': 1.117435336112976} 08/31/2021 15:37:16 - INFO - __main__ - Step 145566: {'lr': 1.1070132072636963e-06, 'samples': 27948672, 'steps': 145565, 'loss/train': 0.7244942784309387} 08/31/2021 15:37:16 - INFO - __main__ - Step 145567: {'lr': 1.1065144153115658e-06, 'samples': 27948864, 'steps': 145566, 'loss/train': 1.0573151111602783} 08/31/2021 15:37:18 - INFO - __main__ - Step 145568: {'lr': 1.1060157355069766e-06, 'samples': 27949056, 'steps': 145567, 'loss/train': 0.942295491695404} 08/31/2021 15:37:18 - INFO - __main__ - Step 145569: {'lr': 1.1055171678501786e-06, 'samples': 27949248, 'steps': 145568, 'loss/train': 1.1520936489105225} 08/31/2021 15:37:18 - INFO - __main__ - Step 145570: {'lr': 1.1050187123413936e-06, 'samples': 27949440, 'steps': 145569, 'loss/train': 0.7393146753311157} 08/31/2021 15:37:19 - INFO - __main__ - Step 145571: {'lr': 1.1045203689808713e-06, 'samples': 27949632, 'steps': 145570, 'loss/train': 0.6159013509750366} 08/31/2021 15:37:19 - INFO - __main__ - Step 145572: {'lr': 1.1040221377687786e-06, 'samples': 27949824, 'steps': 145571, 'loss/train': 0.7198237180709839} 08/31/2021 15:37:22 - INFO - __main__ - Step 145573: {'lr': 1.103524018705393e-06, 'samples': 27950016, 'steps': 145572, 'loss/train': 1.451677918434143} 08/31/2021 15:37:22 - INFO - __main__ - Step 145574: {'lr': 1.1030260117909086e-06, 'samples': 27950208, 'steps': 145573, 'loss/train': 0.5889366865158081} 08/31/2021 15:37:22 - INFO - __main__ - Step 145575: {'lr': 1.1025281170255752e-06, 'samples': 27950400, 'steps': 145574, 'loss/train': 1.2035112380981445} 08/31/2021 15:37:23 - INFO - __main__ - Step 145576: {'lr': 1.1020303344095871e-06, 'samples': 27950592, 'steps': 145575, 'loss/train': 0.04730543866753578} 08/31/2021 15:37:23 - INFO - __main__ - Step 145577: {'lr': 1.1015326639431944e-06, 'samples': 27950784, 'steps': 145576, 'loss/train': 1.3274152278900146} 08/31/2021 15:37:24 - INFO - __main__ - Step 145578: {'lr': 1.1010351056266188e-06, 'samples': 27950976, 'steps': 145577, 'loss/train': 0.8697763681411743} 08/31/2021 15:37:25 - INFO - __main__ - Step 145579: {'lr': 1.1005376594600547e-06, 'samples': 27951168, 'steps': 145578, 'loss/train': 2.030884027481079} 08/31/2021 15:37:25 - INFO - __main__ - Step 145580: {'lr': 1.1000403254437518e-06, 'samples': 27951360, 'steps': 145579, 'loss/train': 1.088680386543274} 08/31/2021 15:37:26 - INFO - __main__ - Step 145581: {'lr': 1.0995431035779325e-06, 'samples': 27951552, 'steps': 145580, 'loss/train': 1.08927583694458} 08/31/2021 15:37:26 - INFO - __main__ - Step 145582: {'lr': 1.0990459938628183e-06, 'samples': 27951744, 'steps': 145581, 'loss/train': 1.2687139511108398} 08/31/2021 15:37:28 - INFO - __main__ - Step 145583: {'lr': 1.0985489962986316e-06, 'samples': 27951936, 'steps': 145582, 'loss/train': 1.317606806755066} 08/31/2021 15:37:28 - INFO - __main__ - Step 145584: {'lr': 1.0980521108855946e-06, 'samples': 27952128, 'steps': 145583, 'loss/train': 1.219222068786621} 08/31/2021 15:37:28 - INFO - __main__ - Step 145585: {'lr': 1.0975553376239566e-06, 'samples': 27952320, 'steps': 145584, 'loss/train': 1.702106237411499} 08/31/2021 15:37:29 - INFO - __main__ - Step 145586: {'lr': 1.0970586765138846e-06, 'samples': 27952512, 'steps': 145585, 'loss/train': 1.051770567893982} 08/31/2021 15:37:29 - INFO - __main__ - Step 145587: {'lr': 1.096562127555656e-06, 'samples': 27952704, 'steps': 145586, 'loss/train': 1.148178219795227} 08/31/2021 15:37:31 - INFO - __main__ - Step 145588: {'lr': 1.0960656907494927e-06, 'samples': 27952896, 'steps': 145587, 'loss/train': 1.4676212072372437} 08/31/2021 15:37:31 - INFO - __main__ - Step 145589: {'lr': 1.095569366095589e-06, 'samples': 27953088, 'steps': 145588, 'loss/train': 2.009814977645874} 08/31/2021 15:37:31 - INFO - __main__ - Step 145590: {'lr': 1.0950731535941672e-06, 'samples': 27953280, 'steps': 145589, 'loss/train': 0.03189246356487274} 08/31/2021 15:37:32 - INFO - __main__ - Step 145591: {'lr': 1.0945770532454769e-06, 'samples': 27953472, 'steps': 145590, 'loss/train': 0.6192760467529297} 08/31/2021 15:37:32 - INFO - __main__ - Step 145592: {'lr': 1.0940810650497402e-06, 'samples': 27953664, 'steps': 145591, 'loss/train': 1.4639099836349487} 08/31/2021 15:37:34 - INFO - __main__ - Step 145593: {'lr': 1.0935851890071512e-06, 'samples': 27953856, 'steps': 145592, 'loss/train': 1.001424789428711} 08/31/2021 15:37:34 - INFO - __main__ - Step 145594: {'lr': 1.0930894251179324e-06, 'samples': 27954048, 'steps': 145593, 'loss/train': 1.6915696859359741} 08/31/2021 15:37:35 - INFO - __main__ - Step 145595: {'lr': 1.092593773382361e-06, 'samples': 27954240, 'steps': 145594, 'loss/train': 0.9065850377082825} 08/31/2021 15:37:35 - INFO - __main__ - Step 145596: {'lr': 1.0920982338006036e-06, 'samples': 27954432, 'steps': 145595, 'loss/train': 1.138465404510498} 08/31/2021 15:37:35 - INFO - __main__ - Step 145597: {'lr': 1.0916028063729377e-06, 'samples': 27954624, 'steps': 145596, 'loss/train': 0.8749446272850037} 08/31/2021 15:37:37 - INFO - __main__ - Step 145598: {'lr': 1.09110749109953e-06, 'samples': 27954816, 'steps': 145597, 'loss/train': 1.0504250526428223} 08/31/2021 15:37:38 - INFO - __main__ - Step 145599: {'lr': 1.0906122879806301e-06, 'samples': 27955008, 'steps': 145598, 'loss/train': 0.013159595429897308} 08/31/2021 15:37:38 - INFO - __main__ - Step 145600: {'lr': 1.0901171970164604e-06, 'samples': 27955200, 'steps': 145599, 'loss/train': 0.015209573321044445} 08/31/2021 15:37:38 - INFO - __main__ - Step 145601: {'lr': 1.0896222182072423e-06, 'samples': 27955392, 'steps': 145600, 'loss/train': 0.778203547000885} 08/31/2021 15:37:39 - INFO - __main__ - Step 145602: {'lr': 1.0891273515531986e-06, 'samples': 27955584, 'steps': 145601, 'loss/train': 0.317481130361557} 08/31/2021 15:37:39 - INFO - __main__ - Step 145603: {'lr': 1.0886325970545786e-06, 'samples': 27955776, 'steps': 145602, 'loss/train': 1.1938624382019043} 08/31/2021 15:37:41 - INFO - __main__ - Step 145604: {'lr': 1.0881379547115488e-06, 'samples': 27955968, 'steps': 145603, 'loss/train': 0.5363753437995911} 08/31/2021 15:37:41 - INFO - __main__ - Step 145605: {'lr': 1.0876434245243593e-06, 'samples': 27956160, 'steps': 145604, 'loss/train': 1.0776435136795044} 08/31/2021 15:37:41 - INFO - __main__ - Step 145606: {'lr': 1.08714900649326e-06, 'samples': 27956352, 'steps': 145605, 'loss/train': 1.5691314935684204} 08/31/2021 15:37:42 - INFO - __main__ - Step 145607: {'lr': 1.0866547006184447e-06, 'samples': 27956544, 'steps': 145606, 'loss/train': 0.9260202050209045} 08/31/2021 15:37:42 - INFO - __main__ - Step 145608: {'lr': 1.0861605069001357e-06, 'samples': 27956736, 'steps': 145607, 'loss/train': 1.2422138452529907} 08/31/2021 15:37:42 - INFO - __main__ - Step 145609: {'lr': 1.0856664253385552e-06, 'samples': 27956928, 'steps': 145608, 'loss/train': 1.303816556930542} 08/31/2021 15:37:44 - INFO - __main__ - Step 145610: {'lr': 1.085172455933925e-06, 'samples': 27957120, 'steps': 145609, 'loss/train': 1.3495094776153564} 08/31/2021 15:37:45 - INFO - __main__ - Step 145611: {'lr': 1.0846785986864948e-06, 'samples': 27957312, 'steps': 145610, 'loss/train': 1.101851463317871} 08/31/2021 15:37:45 - INFO - __main__ - Step 145612: {'lr': 1.084184853596487e-06, 'samples': 27957504, 'steps': 145611, 'loss/train': 0.09469404816627502} 08/31/2021 15:37:45 - INFO - __main__ - Step 145613: {'lr': 1.0836912206640681e-06, 'samples': 27957696, 'steps': 145612, 'loss/train': 0.6952628493309021} 08/31/2021 15:37:46 - INFO - __main__ - Step 145614: {'lr': 1.0831976998895155e-06, 'samples': 27957888, 'steps': 145613, 'loss/train': 0.032267943024635315} 08/31/2021 15:37:47 - INFO - __main__ - Step 145615: {'lr': 1.0827042912730233e-06, 'samples': 27958080, 'steps': 145614, 'loss/train': 1.1175179481506348} 08/31/2021 15:37:48 - INFO - __main__ - Step 145616: {'lr': 1.082210994814814e-06, 'samples': 27958272, 'steps': 145615, 'loss/train': 0.10709288716316223} 08/31/2021 15:37:48 - INFO - __main__ - Step 145617: {'lr': 1.081717810515137e-06, 'samples': 27958464, 'steps': 145616, 'loss/train': 1.0308337211608887} 08/31/2021 15:37:48 - INFO - __main__ - Step 145618: {'lr': 1.0812247383741868e-06, 'samples': 27958656, 'steps': 145617, 'loss/train': 0.6074899435043335} 08/31/2021 15:37:49 - INFO - __main__ - Step 145619: {'lr': 1.0807317783922133e-06, 'samples': 27958848, 'steps': 145618, 'loss/train': 1.449289083480835} 08/31/2021 15:37:50 - INFO - __main__ - Step 145620: {'lr': 1.0802389305694105e-06, 'samples': 27959040, 'steps': 145619, 'loss/train': 1.4093906879425049} 08/31/2021 15:37:51 - INFO - __main__ - Step 145621: {'lr': 1.0797461949060005e-06, 'samples': 27959232, 'steps': 145620, 'loss/train': 1.000004529953003} 08/31/2021 15:37:51 - INFO - __main__ - Step 145622: {'lr': 1.0792535714022333e-06, 'samples': 27959424, 'steps': 145621, 'loss/train': 0.6911143660545349} 08/31/2021 15:37:51 - INFO - __main__ - Step 145623: {'lr': 1.0787610600583031e-06, 'samples': 27959616, 'steps': 145622, 'loss/train': 1.200852870941162} 08/31/2021 15:37:52 - INFO - __main__ - Step 145624: {'lr': 1.0782686608744319e-06, 'samples': 27959808, 'steps': 145623, 'loss/train': 0.3977526128292084} 08/31/2021 15:37:54 - INFO - __main__ - Step 145625: {'lr': 1.0777763738508694e-06, 'samples': 27960000, 'steps': 145624, 'loss/train': 0.8599663972854614} 08/31/2021 15:37:54 - INFO - __main__ - Step 145626: {'lr': 1.0772841989878101e-06, 'samples': 27960192, 'steps': 145625, 'loss/train': 0.7397372722625732} 08/31/2021 15:37:55 - INFO - __main__ - Step 145627: {'lr': 1.0767921362855037e-06, 'samples': 27960384, 'steps': 145626, 'loss/train': 1.1664880514144897} 08/31/2021 15:37:55 - INFO - __main__ - Step 145628: {'lr': 1.0763001857441446e-06, 'samples': 27960576, 'steps': 145627, 'loss/train': 1.024751901626587} 08/31/2021 15:37:56 - INFO - __main__ - Step 145629: {'lr': 1.0758083473639546e-06, 'samples': 27960768, 'steps': 145628, 'loss/train': 4.099145889282227} 08/31/2021 15:37:56 - INFO - __main__ - Step 145630: {'lr': 1.075316621145156e-06, 'samples': 27960960, 'steps': 145629, 'loss/train': 0.8436825275421143} 08/31/2021 15:37:57 - INFO - __main__ - Step 145631: {'lr': 1.0748250070879983e-06, 'samples': 27961152, 'steps': 145630, 'loss/train': 0.3822677433490753} 08/31/2021 15:37:58 - INFO - __main__ - Step 145632: {'lr': 1.0743335051926762e-06, 'samples': 27961344, 'steps': 145631, 'loss/train': 0.8703880310058594} 08/31/2021 15:37:58 - INFO - __main__ - Step 145633: {'lr': 1.0738421154594114e-06, 'samples': 27961536, 'steps': 145632, 'loss/train': 1.072175145149231} 08/31/2021 15:37:59 - INFO - __main__ - Step 145634: {'lr': 1.073350837888426e-06, 'samples': 27961728, 'steps': 145633, 'loss/train': 0.05618523806333542} 08/31/2021 15:37:59 - INFO - __main__ - Step 145635: {'lr': 1.07285967247997e-06, 'samples': 27961920, 'steps': 145634, 'loss/train': 1.3839123249053955} 08/31/2021 15:38:01 - INFO - __main__ - Step 145636: {'lr': 1.0723686192342375e-06, 'samples': 27962112, 'steps': 145635, 'loss/train': 1.4457091093063354} 08/31/2021 15:38:01 - INFO - __main__ - Step 145637: {'lr': 1.0718776781514505e-06, 'samples': 27962304, 'steps': 145636, 'loss/train': 0.03420514613389969} 08/31/2021 15:38:01 - INFO - __main__ - Step 145638: {'lr': 1.0713868492318313e-06, 'samples': 27962496, 'steps': 145637, 'loss/train': 1.3343114852905273} 08/31/2021 15:38:02 - INFO - __main__ - Step 145639: {'lr': 1.0708961324756017e-06, 'samples': 27962688, 'steps': 145638, 'loss/train': 1.1390994787216187} 08/31/2021 15:38:02 - INFO - __main__ - Step 145640: {'lr': 1.0704055278829838e-06, 'samples': 27962880, 'steps': 145639, 'loss/train': 1.1831107139587402} 08/31/2021 15:38:04 - INFO - __main__ - Step 145641: {'lr': 1.0699150354541997e-06, 'samples': 27963072, 'steps': 145640, 'loss/train': 1.0595712661743164} 08/31/2021 15:38:04 - INFO - __main__ - Step 145642: {'lr': 1.0694246551894993e-06, 'samples': 27963264, 'steps': 145641, 'loss/train': 0.48843371868133545} 08/31/2021 15:38:04 - INFO - __main__ - Step 145643: {'lr': 1.068934387089049e-06, 'samples': 27963456, 'steps': 145642, 'loss/train': 1.1977027654647827} 08/31/2021 15:38:05 - INFO - __main__ - Step 145644: {'lr': 1.0684442311530985e-06, 'samples': 27963648, 'steps': 145643, 'loss/train': 1.2628117799758911} 08/31/2021 15:38:05 - INFO - __main__ - Step 145645: {'lr': 1.0679541873818422e-06, 'samples': 27963840, 'steps': 145644, 'loss/train': 0.29221659898757935} 08/31/2021 15:38:07 - INFO - __main__ - Step 145646: {'lr': 1.0674642557755575e-06, 'samples': 27964032, 'steps': 145645, 'loss/train': 1.3858948945999146} 08/31/2021 15:38:07 - INFO - __main__ - Step 145647: {'lr': 1.0669744363344113e-06, 'samples': 27964224, 'steps': 145646, 'loss/train': 1.6279799938201904} 08/31/2021 15:38:08 - INFO - __main__ - Step 145648: {'lr': 1.0664847290586533e-06, 'samples': 27964416, 'steps': 145647, 'loss/train': 1.9065583944320679} 08/31/2021 15:38:08 - INFO - __main__ - Step 145649: {'lr': 1.0659951339485052e-06, 'samples': 27964608, 'steps': 145648, 'loss/train': 0.02716049551963806} 08/31/2021 15:38:08 - INFO - __main__ - Step 145650: {'lr': 1.0655056510041895e-06, 'samples': 27964800, 'steps': 145649, 'loss/train': 1.1836599111557007} 08/31/2021 15:38:10 - INFO - __main__ - Step 145651: {'lr': 1.0650162802258723e-06, 'samples': 27964992, 'steps': 145650, 'loss/train': 0.35329005122184753} 08/31/2021 15:38:10 - INFO - __main__ - Step 145652: {'lr': 1.0645270216138592e-06, 'samples': 27965184, 'steps': 145651, 'loss/train': 0.7300090193748474} 08/31/2021 15:38:11 - INFO - __main__ - Step 145653: {'lr': 1.0640378751683166e-06, 'samples': 27965376, 'steps': 145652, 'loss/train': 1.4385459423065186} 08/31/2021 15:38:11 - INFO - __main__ - Step 145654: {'lr': 1.0635488408894667e-06, 'samples': 27965568, 'steps': 145653, 'loss/train': 0.8454102873802185} 08/31/2021 15:38:11 - INFO - __main__ - Step 145655: {'lr': 1.0630599187775592e-06, 'samples': 27965760, 'steps': 145654, 'loss/train': 1.615218162536621} 08/31/2021 15:38:12 - INFO - __main__ - Step 145656: {'lr': 1.0625711088327882e-06, 'samples': 27965952, 'steps': 145655, 'loss/train': 1.0910714864730835} 08/31/2021 15:38:13 - INFO - __main__ - Step 145657: {'lr': 1.0620824110553763e-06, 'samples': 27966144, 'steps': 145656, 'loss/train': 0.7761285901069641} 08/31/2021 15:38:13 - INFO - __main__ - Step 145658: {'lr': 1.061593825445545e-06, 'samples': 27966336, 'steps': 145657, 'loss/train': 1.4011476039886475} 08/31/2021 15:38:14 - INFO - __main__ - Step 145659: {'lr': 1.0611053520035163e-06, 'samples': 27966528, 'steps': 145658, 'loss/train': 0.6596784591674805} 08/31/2021 15:38:14 - INFO - __main__ - Step 145660: {'lr': 1.0606169907295127e-06, 'samples': 27966720, 'steps': 145659, 'loss/train': 1.1438482999801636} 08/31/2021 15:38:14 - INFO - __main__ - Step 145661: {'lr': 1.060128741623756e-06, 'samples': 27966912, 'steps': 145660, 'loss/train': 1.0341626405715942} 08/31/2021 15:38:16 - INFO - __main__ - Step 145662: {'lr': 1.0596406046864682e-06, 'samples': 27967104, 'steps': 145661, 'loss/train': 1.3413408994674683} 08/31/2021 15:38:16 - INFO - __main__ - Step 145663: {'lr': 1.0591525799178714e-06, 'samples': 27967296, 'steps': 145662, 'loss/train': 0.6524856686592102} 08/31/2021 15:38:17 - INFO - __main__ - Step 145664: {'lr': 1.05866466731816e-06, 'samples': 27967488, 'steps': 145663, 'loss/train': 1.2549922466278076} 08/31/2021 15:38:17 - INFO - __main__ - Step 145665: {'lr': 1.0581768668875836e-06, 'samples': 27967680, 'steps': 145664, 'loss/train': 0.7436306476593018} 08/31/2021 15:38:17 - INFO - __main__ - Step 145666: {'lr': 1.0576891786263643e-06, 'samples': 27967872, 'steps': 145665, 'loss/train': 0.8170806169509888} 08/31/2021 15:38:19 - INFO - __main__ - Step 145667: {'lr': 1.0572016025346964e-06, 'samples': 27968064, 'steps': 145666, 'loss/train': 0.7027176022529602} 08/31/2021 15:38:19 - INFO - __main__ - Step 145668: {'lr': 1.0567141386128298e-06, 'samples': 27968256, 'steps': 145667, 'loss/train': 0.23064389824867249} 08/31/2021 15:38:20 - INFO - __main__ - Step 145669: {'lr': 1.056226786860931e-06, 'samples': 27968448, 'steps': 145668, 'loss/train': 1.0174235105514526} 08/31/2021 15:38:20 - INFO - __main__ - Step 145670: {'lr': 1.0557395472792775e-06, 'samples': 27968640, 'steps': 145669, 'loss/train': 4.795950889587402} 08/31/2021 15:38:20 - INFO - __main__ - Step 145671: {'lr': 1.0552524198680635e-06, 'samples': 27968832, 'steps': 145670, 'loss/train': 1.0477288961410522} 08/31/2021 15:38:22 - INFO - __main__ - Step 145672: {'lr': 1.0547654046275114e-06, 'samples': 27969024, 'steps': 145671, 'loss/train': 1.0246284008026123} 08/31/2021 15:38:22 - INFO - __main__ - Step 145673: {'lr': 1.0542785015578426e-06, 'samples': 27969216, 'steps': 145672, 'loss/train': 0.7801172137260437} 08/31/2021 15:38:23 - INFO - __main__ - Step 145674: {'lr': 1.053791710659252e-06, 'samples': 27969408, 'steps': 145673, 'loss/train': 1.076855182647705} 08/31/2021 15:38:23 - INFO - __main__ - Step 145675: {'lr': 1.053305031932017e-06, 'samples': 27969600, 'steps': 145674, 'loss/train': 0.7252219319343567} 08/31/2021 15:38:24 - INFO - __main__ - Step 145676: {'lr': 1.052818465376304e-06, 'samples': 27969792, 'steps': 145675, 'loss/train': 1.3079843521118164} 08/31/2021 15:38:25 - INFO - __main__ - Step 145677: {'lr': 1.052332010992335e-06, 'samples': 27969984, 'steps': 145676, 'loss/train': 1.1266597509384155} 08/31/2021 15:38:26 - INFO - __main__ - Step 145678: {'lr': 1.0518456687803601e-06, 'samples': 27970176, 'steps': 145677, 'loss/train': 1.6948398351669312} 08/31/2021 15:38:26 - INFO - __main__ - Step 145679: {'lr': 1.0513594387406012e-06, 'samples': 27970368, 'steps': 145678, 'loss/train': 0.670698344707489} 08/31/2021 15:38:26 - INFO - __main__ - Step 145680: {'lr': 1.0508733208732246e-06, 'samples': 27970560, 'steps': 145679, 'loss/train': 1.1523544788360596} 08/31/2021 15:38:27 - INFO - __main__ - Step 145681: {'lr': 1.0503873151785081e-06, 'samples': 27970752, 'steps': 145680, 'loss/train': 1.3303298950195312} 08/31/2021 15:38:29 - INFO - __main__ - Step 145682: {'lr': 1.0499014216566183e-06, 'samples': 27970944, 'steps': 145681, 'loss/train': 1.5124157667160034} 08/31/2021 15:38:29 - INFO - __main__ - Step 145683: {'lr': 1.0494156403078048e-06, 'samples': 27971136, 'steps': 145682, 'loss/train': 0.3591834306716919} 08/31/2021 15:38:30 - INFO - __main__ - Step 145684: {'lr': 1.0489299711323176e-06, 'samples': 27971328, 'steps': 145683, 'loss/train': 0.9088113903999329} 08/31/2021 15:38:30 - INFO - __main__ - Step 145685: {'lr': 1.0484444141302952e-06, 'samples': 27971520, 'steps': 145684, 'loss/train': 0.08897338807582855} 08/31/2021 15:38:30 - INFO - __main__ - Step 145686: {'lr': 1.047958969302043e-06, 'samples': 27971712, 'steps': 145685, 'loss/train': 1.091475486755371} 08/31/2021 15:38:32 - INFO - __main__ - Step 145687: {'lr': 1.0474736366477e-06, 'samples': 27971904, 'steps': 145686, 'loss/train': 0.6157782077789307} 08/31/2021 15:38:32 - INFO - __main__ - Step 145688: {'lr': 1.0469884161675435e-06, 'samples': 27972096, 'steps': 145687, 'loss/train': 0.02102532424032688} 08/31/2021 15:38:33 - INFO - __main__ - Step 145689: {'lr': 1.0465033078617958e-06, 'samples': 27972288, 'steps': 145688, 'loss/train': 0.41254937648773193} 08/31/2021 15:38:33 - INFO - __main__ - Step 145690: {'lr': 1.0460183117306232e-06, 'samples': 27972480, 'steps': 145689, 'loss/train': 1.2606924772262573} 08/31/2021 15:38:33 - INFO - __main__ - Step 145691: {'lr': 1.0455334277742756e-06, 'samples': 27972672, 'steps': 145690, 'loss/train': 1.454842448234558} 08/31/2021 15:38:35 - INFO - __main__ - Step 145692: {'lr': 1.045048655992975e-06, 'samples': 27972864, 'steps': 145691, 'loss/train': 0.8789738416671753} 08/31/2021 15:38:35 - INFO - __main__ - Step 145693: {'lr': 1.0445639963869435e-06, 'samples': 27973056, 'steps': 145692, 'loss/train': 0.9689561128616333} 08/31/2021 15:38:36 - INFO - __main__ - Step 145694: {'lr': 1.0440794489563754e-06, 'samples': 27973248, 'steps': 145693, 'loss/train': 1.4921932220458984} 08/31/2021 15:38:36 - INFO - __main__ - Step 145695: {'lr': 1.0435950137014926e-06, 'samples': 27973440, 'steps': 145694, 'loss/train': 0.5896124839782715} 08/31/2021 15:38:37 - INFO - __main__ - Step 145696: {'lr': 1.0431106906225451e-06, 'samples': 27973632, 'steps': 145695, 'loss/train': 1.1759158372879028} 08/31/2021 15:38:37 - INFO - __main__ - Step 145697: {'lr': 1.042626479719727e-06, 'samples': 27973824, 'steps': 145696, 'loss/train': 1.7395668029785156} 08/31/2021 15:38:38 - INFO - __main__ - Step 145698: {'lr': 1.0421423809932606e-06, 'samples': 27974016, 'steps': 145697, 'loss/train': 0.19969768822193146} 08/31/2021 15:38:39 - INFO - __main__ - Step 145699: {'lr': 1.04165839444334e-06, 'samples': 27974208, 'steps': 145698, 'loss/train': 0.9057420492172241} 08/31/2021 15:38:39 - INFO - __main__ - Step 145700: {'lr': 1.0411745200702427e-06, 'samples': 27974400, 'steps': 145699, 'loss/train': 0.3845801055431366} 08/31/2021 15:38:40 - INFO - __main__ - Step 145701: {'lr': 1.0406907578741353e-06, 'samples': 27974592, 'steps': 145700, 'loss/train': 1.225089192390442} 08/31/2021 15:38:40 - INFO - __main__ - Step 145702: {'lr': 1.04020710785524e-06, 'samples': 27974784, 'steps': 145701, 'loss/train': 1.3238790035247803} 08/31/2021 15:38:41 - INFO - __main__ - Step 145703: {'lr': 1.0397235700138063e-06, 'samples': 27974976, 'steps': 145702, 'loss/train': 1.2826173305511475} 08/31/2021 15:38:42 - INFO - __main__ - Step 145704: {'lr': 1.039240144350001e-06, 'samples': 27975168, 'steps': 145703, 'loss/train': 1.5687006711959839} 08/31/2021 15:38:42 - INFO - __main__ - Step 145705: {'lr': 1.0387568308641015e-06, 'samples': 27975360, 'steps': 145704, 'loss/train': 0.8749332427978516} 08/31/2021 15:38:42 - INFO - __main__ - Step 145706: {'lr': 1.0382736295563023e-06, 'samples': 27975552, 'steps': 145705, 'loss/train': 1.0429061651229858} 08/31/2021 15:38:43 - INFO - __main__ - Step 145707: {'lr': 1.0377905404267973e-06, 'samples': 27975744, 'steps': 145706, 'loss/train': 0.5644189119338989} 08/31/2021 15:38:45 - INFO - __main__ - Step 145708: {'lr': 1.037307563475809e-06, 'samples': 27975936, 'steps': 145707, 'loss/train': 1.226904034614563} 08/31/2021 15:38:45 - INFO - __main__ - Step 145709: {'lr': 1.0368246987035868e-06, 'samples': 27976128, 'steps': 145708, 'loss/train': 0.6723236441612244} 08/31/2021 15:38:46 - INFO - __main__ - Step 145710: {'lr': 1.0363419461103252e-06, 'samples': 27976320, 'steps': 145709, 'loss/train': 0.8188007473945618} 08/31/2021 15:38:46 - INFO - __main__ - Step 145711: {'lr': 1.0358593056962462e-06, 'samples': 27976512, 'steps': 145710, 'loss/train': 1.187186598777771} 08/31/2021 15:38:46 - INFO - __main__ - Step 145712: {'lr': 1.035376777461572e-06, 'samples': 27976704, 'steps': 145711, 'loss/train': 0.3544260859489441} 08/31/2021 15:38:47 - INFO - __main__ - Step 145713: {'lr': 1.0348943614064964e-06, 'samples': 27976896, 'steps': 145712, 'loss/train': 1.220163106918335} 08/31/2021 15:38:49 - INFO - __main__ - Step 145714: {'lr': 1.0344120575312699e-06, 'samples': 27977088, 'steps': 145713, 'loss/train': 0.014840825460851192} 08/31/2021 15:38:49 - INFO - __main__ - Step 145715: {'lr': 1.033929865836114e-06, 'samples': 27977280, 'steps': 145714, 'loss/train': 1.6608797311782837} 08/31/2021 15:38:49 - INFO - __main__ - Step 145716: {'lr': 1.0334477863211956e-06, 'samples': 27977472, 'steps': 145715, 'loss/train': 0.06995733827352524} 08/31/2021 15:38:50 - INFO - __main__ - Step 145717: {'lr': 1.0329658189867641e-06, 'samples': 27977664, 'steps': 145716, 'loss/train': 0.0224966648966074} 08/31/2021 15:38:50 - INFO - __main__ - Step 145718: {'lr': 1.0324839638330696e-06, 'samples': 27977856, 'steps': 145717, 'loss/train': 0.6813735961914062} 08/31/2021 15:38:52 - INFO - __main__ - Step 145719: {'lr': 1.0320022208602787e-06, 'samples': 27978048, 'steps': 145718, 'loss/train': 1.102996587753296} 08/31/2021 15:38:53 - INFO - __main__ - Step 145720: {'lr': 1.0315205900686132e-06, 'samples': 27978240, 'steps': 145719, 'loss/train': 0.9049062132835388} 08/31/2021 15:38:53 - INFO - __main__ - Step 145721: {'lr': 1.0310390714583229e-06, 'samples': 27978432, 'steps': 145720, 'loss/train': 1.098334789276123} 08/31/2021 15:38:53 - INFO - __main__ - Step 145722: {'lr': 1.0305576650296023e-06, 'samples': 27978624, 'steps': 145721, 'loss/train': 0.7988100051879883} 08/31/2021 15:38:54 - INFO - __main__ - Step 145723: {'lr': 1.0300763707826455e-06, 'samples': 27978816, 'steps': 145722, 'loss/train': 0.14947989583015442} 08/31/2021 15:38:54 - INFO - __main__ - Step 145724: {'lr': 1.0295951887177302e-06, 'samples': 27979008, 'steps': 145723, 'loss/train': 0.14696872234344482} 08/31/2021 15:38:54 - INFO - __main__ - Step 145725: {'lr': 1.0291141188349951e-06, 'samples': 27979200, 'steps': 145724, 'loss/train': 0.03449798747897148} 08/31/2021 15:38:56 - INFO - __main__ - Step 145726: {'lr': 1.0286331611347455e-06, 'samples': 27979392, 'steps': 145725, 'loss/train': 0.0672304779291153} 08/31/2021 15:38:56 - INFO - __main__ - Step 145727: {'lr': 1.0281523156171201e-06, 'samples': 27979584, 'steps': 145726, 'loss/train': 1.0929625034332275} 08/31/2021 15:38:57 - INFO - __main__ - Step 145728: {'lr': 1.027671582282369e-06, 'samples': 27979776, 'steps': 145727, 'loss/train': 1.4119117259979248} 08/31/2021 15:38:57 - INFO - __main__ - Step 145729: {'lr': 1.027190961130714e-06, 'samples': 27979968, 'steps': 145728, 'loss/train': 0.8320447206497192} 08/31/2021 15:38:57 - INFO - __main__ - Step 145730: {'lr': 1.0267104521623771e-06, 'samples': 27980160, 'steps': 145729, 'loss/train': 1.3774038553237915} 08/31/2021 15:38:59 - INFO - __main__ - Step 145731: {'lr': 1.0262300553775527e-06, 'samples': 27980352, 'steps': 145730, 'loss/train': 0.9930540323257446} 08/31/2021 15:39:00 - INFO - __main__ - Step 145732: {'lr': 1.025749770776463e-06, 'samples': 27980544, 'steps': 145731, 'loss/train': 1.1655874252319336} 08/31/2021 15:39:00 - INFO - __main__ - Step 145733: {'lr': 1.0252695983593296e-06, 'samples': 27980736, 'steps': 145732, 'loss/train': 1.3429756164550781} 08/31/2021 15:39:00 - INFO - __main__ - Step 145734: {'lr': 1.024789538126375e-06, 'samples': 27980928, 'steps': 145733, 'loss/train': 0.0314631462097168} 08/31/2021 15:39:01 - INFO - __main__ - Step 145735: {'lr': 1.0243095900777931e-06, 'samples': 27981120, 'steps': 145734, 'loss/train': 1.0257271528244019} 08/31/2021 15:39:03 - INFO - __main__ - Step 145736: {'lr': 1.023829754213834e-06, 'samples': 27981312, 'steps': 145735, 'loss/train': 1.7329823970794678} 08/31/2021 15:39:03 - INFO - __main__ - Step 145737: {'lr': 1.0233500305346921e-06, 'samples': 27981504, 'steps': 145736, 'loss/train': 1.2965794801712036} 08/31/2021 15:39:04 - INFO - __main__ - Step 145738: {'lr': 1.0228704190405891e-06, 'samples': 27981696, 'steps': 145737, 'loss/train': 1.3738479614257812} 08/31/2021 15:39:04 - INFO - __main__ - Step 145739: {'lr': 1.0223909197317193e-06, 'samples': 27981888, 'steps': 145738, 'loss/train': 1.3576533794403076} 08/31/2021 15:39:04 - INFO - __main__ - Step 145740: {'lr': 1.0219115326083327e-06, 'samples': 27982080, 'steps': 145739, 'loss/train': 1.3094042539596558} 08/31/2021 15:39:05 - INFO - __main__ - Step 145741: {'lr': 1.0214322576706236e-06, 'samples': 27982272, 'steps': 145740, 'loss/train': 1.1691988706588745} 08/31/2021 15:39:06 - INFO - __main__ - Step 145742: {'lr': 1.0209530949188138e-06, 'samples': 27982464, 'steps': 145741, 'loss/train': 1.0563733577728271} 08/31/2021 15:39:07 - INFO - __main__ - Step 145743: {'lr': 1.0204740443531258e-06, 'samples': 27982656, 'steps': 145742, 'loss/train': 0.17139676213264465} 08/31/2021 15:39:07 - INFO - __main__ - Step 145744: {'lr': 1.0199951059737812e-06, 'samples': 27982848, 'steps': 145743, 'loss/train': 1.26922607421875} 08/31/2021 15:39:07 - INFO - __main__ - Step 145745: {'lr': 1.0195162797809743e-06, 'samples': 27983040, 'steps': 145744, 'loss/train': 1.4529799222946167} 08/31/2021 15:39:08 - INFO - __main__ - Step 145746: {'lr': 1.0190375657749273e-06, 'samples': 27983232, 'steps': 145745, 'loss/train': 1.208059310913086} 08/31/2021 15:39:09 - INFO - __main__ - Step 145747: {'lr': 1.0185589639558623e-06, 'samples': 27983424, 'steps': 145746, 'loss/train': 1.1282528638839722} 08/31/2021 15:39:10 - INFO - __main__ - Step 145748: {'lr': 1.0180804743240013e-06, 'samples': 27983616, 'steps': 145747, 'loss/train': 0.8257214426994324} 08/31/2021 15:39:10 - INFO - __main__ - Step 145749: {'lr': 1.0176020968795385e-06, 'samples': 27983808, 'steps': 145748, 'loss/train': 1.740381121635437} 08/31/2021 15:39:11 - INFO - __main__ - Step 145750: {'lr': 1.0171238316227237e-06, 'samples': 27984000, 'steps': 145749, 'loss/train': 1.1244126558303833} 08/31/2021 15:39:11 - INFO - __main__ - Step 145751: {'lr': 1.0166456785537237e-06, 'samples': 27984192, 'steps': 145750, 'loss/train': 0.978011965751648} 08/31/2021 15:39:13 - INFO - __main__ - Step 145752: {'lr': 1.016167637672788e-06, 'samples': 27984384, 'steps': 145751, 'loss/train': 0.9130120873451233} 08/31/2021 15:39:13 - INFO - __main__ - Step 145753: {'lr': 1.0156897089801387e-06, 'samples': 27984576, 'steps': 145752, 'loss/train': 1.0885801315307617} 08/31/2021 15:39:14 - INFO - __main__ - Step 145754: {'lr': 1.01521189247597e-06, 'samples': 27984768, 'steps': 145753, 'loss/train': 0.9155888557434082} 08/31/2021 15:39:14 - INFO - __main__ - Step 145755: {'lr': 1.0147341881605044e-06, 'samples': 27984960, 'steps': 145754, 'loss/train': 1.9947453737258911} 08/31/2021 15:39:14 - INFO - __main__ - Step 145756: {'lr': 1.0142565960339356e-06, 'samples': 27985152, 'steps': 145755, 'loss/train': 1.3142801523208618} 08/31/2021 15:39:16 - INFO - __main__ - Step 145757: {'lr': 1.0137791160965414e-06, 'samples': 27985344, 'steps': 145756, 'loss/train': 0.83419269323349} 08/31/2021 15:39:16 - INFO - __main__ - Step 145758: {'lr': 1.0133017483484608e-06, 'samples': 27985536, 'steps': 145757, 'loss/train': 0.11063005775213242} 08/31/2021 15:39:17 - INFO - __main__ - Step 145759: {'lr': 1.012824492789971e-06, 'samples': 27985728, 'steps': 145758, 'loss/train': 1.0233314037322998} 08/31/2021 15:39:17 - INFO - __main__ - Step 145760: {'lr': 1.0123473494212388e-06, 'samples': 27985920, 'steps': 145759, 'loss/train': 1.313448190689087} 08/31/2021 15:39:17 - INFO - __main__ - Step 145761: {'lr': 1.0118703182425137e-06, 'samples': 27986112, 'steps': 145760, 'loss/train': 1.6770553588867188} 08/31/2021 15:39:18 - INFO - __main__ - Step 145762: {'lr': 1.0113933992539903e-06, 'samples': 27986304, 'steps': 145761, 'loss/train': 0.8077322840690613} 08/31/2021 15:39:19 - INFO - __main__ - Step 145763: {'lr': 1.0109165924559182e-06, 'samples': 27986496, 'steps': 145762, 'loss/train': 1.460976004600525} 08/31/2021 15:39:20 - INFO - __main__ - Step 145764: {'lr': 1.010439897848464e-06, 'samples': 27986688, 'steps': 145763, 'loss/train': 0.8470409512519836} 08/31/2021 15:39:20 - INFO - __main__ - Step 145765: {'lr': 1.0099633154318499e-06, 'samples': 27986880, 'steps': 145764, 'loss/train': 1.3188776969909668} 08/31/2021 15:39:20 - INFO - __main__ - Step 145766: {'lr': 1.0094868452063254e-06, 'samples': 27987072, 'steps': 145765, 'loss/train': 1.0815306901931763} 08/31/2021 15:39:21 - INFO - __main__ - Step 145767: {'lr': 1.0090104871720574e-06, 'samples': 27987264, 'steps': 145766, 'loss/train': 0.7753162980079651} 08/31/2021 15:39:23 - INFO - __main__ - Step 145768: {'lr': 1.008534241329323e-06, 'samples': 27987456, 'steps': 145767, 'loss/train': 1.3433283567428589} 08/31/2021 15:39:23 - INFO - __main__ - Step 145769: {'lr': 1.0080581076782613e-06, 'samples': 27987648, 'steps': 145768, 'loss/train': 0.7285488843917847} 08/31/2021 15:39:24 - INFO - __main__ - Step 145770: {'lr': 1.0075820862191498e-06, 'samples': 27987840, 'steps': 145769, 'loss/train': 1.5150450468063354} 08/31/2021 15:39:24 - INFO - __main__ - Step 145771: {'lr': 1.0071061769521828e-06, 'samples': 27988032, 'steps': 145770, 'loss/train': 0.324390709400177} 08/31/2021 15:39:24 - INFO - __main__ - Step 145772: {'lr': 1.0066303798775545e-06, 'samples': 27988224, 'steps': 145771, 'loss/train': 0.8835569620132446} 08/31/2021 15:39:25 - INFO - __main__ - Step 145773: {'lr': 1.0061546949955146e-06, 'samples': 27988416, 'steps': 145772, 'loss/train': 1.1701271533966064} 08/31/2021 15:39:26 - INFO - __main__ - Step 145774: {'lr': 1.0056791223062577e-06, 'samples': 27988608, 'steps': 145773, 'loss/train': 0.016341200098395348} 08/31/2021 15:39:27 - INFO - __main__ - Step 145775: {'lr': 1.0052036618100057e-06, 'samples': 27988800, 'steps': 145774, 'loss/train': 1.3779515027999878} 08/31/2021 15:39:27 - INFO - __main__ - Step 145776: {'lr': 1.004728313506953e-06, 'samples': 27988992, 'steps': 145775, 'loss/train': 1.1425634622573853} 08/31/2021 15:39:27 - INFO - __main__ - Step 145777: {'lr': 1.0042530773973213e-06, 'samples': 27989184, 'steps': 145776, 'loss/train': 0.8298846483230591} 08/31/2021 15:39:28 - INFO - __main__ - Step 145778: {'lr': 1.003777953481333e-06, 'samples': 27989376, 'steps': 145777, 'loss/train': 1.0090988874435425} 08/31/2021 15:39:29 - INFO - __main__ - Step 145779: {'lr': 1.0033029417592098e-06, 'samples': 27989568, 'steps': 145778, 'loss/train': 0.43855687975883484} 08/31/2021 15:39:30 - INFO - __main__ - Step 145780: {'lr': 1.0028280422311464e-06, 'samples': 27989760, 'steps': 145779, 'loss/train': 0.8206732869148254} 08/31/2021 15:39:30 - INFO - __main__ - Step 145781: {'lr': 1.0023532548973924e-06, 'samples': 27989952, 'steps': 145780, 'loss/train': 0.1005236804485321} 08/31/2021 15:39:30 - INFO - __main__ - Step 145782: {'lr': 1.0018785797581142e-06, 'samples': 27990144, 'steps': 145781, 'loss/train': 0.4285023510456085} 08/31/2021 15:39:31 - INFO - __main__ - Step 145783: {'lr': 1.001404016813534e-06, 'samples': 27990336, 'steps': 145782, 'loss/train': 1.233227014541626} 08/31/2021 15:39:32 - INFO - __main__ - Step 145784: {'lr': 1.0009295660639018e-06, 'samples': 27990528, 'steps': 145783, 'loss/train': 0.968188464641571} 08/31/2021 15:39:33 - INFO - __main__ - Step 145785: {'lr': 1.0004552275094114e-06, 'samples': 27990720, 'steps': 145784, 'loss/train': 1.0287606716156006} 08/31/2021 15:39:33 - INFO - __main__ - Step 145786: {'lr': 9.999810011502575e-07, 'samples': 27990912, 'steps': 145785, 'loss/train': 0.8563015460968018} 08/31/2021 15:39:34 - INFO - __main__ - Step 145787: {'lr': 9.995068869866897e-07, 'samples': 27991104, 'steps': 145786, 'loss/train': 0.8566734790802002} 08/31/2021 15:39:34 - INFO - __main__ - Step 145788: {'lr': 9.990328850188745e-07, 'samples': 27991296, 'steps': 145787, 'loss/train': 0.7011215090751648} 08/31/2021 15:39:34 - INFO - __main__ - Step 145789: {'lr': 9.98558995247062e-07, 'samples': 27991488, 'steps': 145788, 'loss/train': 0.06733179837465286} 08/31/2021 15:39:36 - INFO - __main__ - Step 145790: {'lr': 9.980852176714738e-07, 'samples': 27991680, 'steps': 145789, 'loss/train': 0.9649040699005127} 08/31/2021 15:39:36 - INFO - __main__ - Step 145791: {'lr': 9.97611552292277e-07, 'samples': 27991872, 'steps': 145790, 'loss/train': 1.2583764791488647} 08/31/2021 15:39:37 - INFO - __main__ - Step 145792: {'lr': 9.971379991097484e-07, 'samples': 27992064, 'steps': 145791, 'loss/train': 1.3265734910964966} 08/31/2021 15:39:37 - INFO - __main__ - Step 145793: {'lr': 9.966645581240275e-07, 'samples': 27992256, 'steps': 145792, 'loss/train': 1.0501376390457153} 08/31/2021 15:39:37 - INFO - __main__ - Step 145794: {'lr': 9.961912293353913e-07, 'samples': 27992448, 'steps': 145793, 'loss/train': 0.8190084099769592} 08/31/2021 15:39:40 - INFO - __main__ - Step 145795: {'lr': 9.957180127440345e-07, 'samples': 27992640, 'steps': 145794, 'loss/train': 1.377530813217163} 08/31/2021 15:39:40 - INFO - __main__ - Step 145796: {'lr': 9.952449083501514e-07, 'samples': 27992832, 'steps': 145795, 'loss/train': 1.1791880130767822} 08/31/2021 15:39:40 - INFO - __main__ - Step 145797: {'lr': 9.947719161539637e-07, 'samples': 27993024, 'steps': 145796, 'loss/train': 0.5505144596099854} 08/31/2021 15:39:41 - INFO - __main__ - Step 145798: {'lr': 9.942990361556936e-07, 'samples': 27993216, 'steps': 145797, 'loss/train': 0.6419426202774048} 08/31/2021 15:39:41 - INFO - __main__ - Step 145799: {'lr': 9.938262683555632e-07, 'samples': 27993408, 'steps': 145798, 'loss/train': 1.712838888168335} 08/31/2021 15:39:43 - INFO - __main__ - Step 145800: {'lr': 9.933536127537667e-07, 'samples': 27993600, 'steps': 145799, 'loss/train': 1.3396577835083008} 08/31/2021 15:39:43 - INFO - __main__ - Step 145801: {'lr': 9.928810693505263e-07, 'samples': 27993792, 'steps': 145800, 'loss/train': 1.2785429954528809} 08/31/2021 15:39:44 - INFO - __main__ - Step 145802: {'lr': 9.924086381460361e-07, 'samples': 27993984, 'steps': 145801, 'loss/train': 0.998432457447052} 08/31/2021 15:39:44 - INFO - __main__ - Step 145803: {'lr': 9.919363191405462e-07, 'samples': 27994176, 'steps': 145802, 'loss/train': 0.8196386098861694} 08/31/2021 15:39:44 - INFO - __main__ - Step 145804: {'lr': 9.914641123342227e-07, 'samples': 27994368, 'steps': 145803, 'loss/train': 0.6509098410606384} 08/31/2021 15:39:46 - INFO - __main__ - Step 145805: {'lr': 9.909920177273157e-07, 'samples': 27994560, 'steps': 145804, 'loss/train': 0.5771018862724304} 08/31/2021 15:39:46 - INFO - __main__ - Step 145806: {'lr': 9.905200353200194e-07, 'samples': 27994752, 'steps': 145805, 'loss/train': 0.9508628845214844} 08/31/2021 15:39:47 - INFO - __main__ - Step 145807: {'lr': 9.900481651125558e-07, 'samples': 27994944, 'steps': 145806, 'loss/train': 0.7302990555763245} 08/31/2021 15:39:47 - INFO - __main__ - Step 145808: {'lr': 9.895764071051472e-07, 'samples': 27995136, 'steps': 145807, 'loss/train': 1.4860237836837769} 08/31/2021 15:39:47 - INFO - __main__ - Step 145809: {'lr': 9.891047612979875e-07, 'samples': 27995328, 'steps': 145808, 'loss/train': 0.7629567384719849} 08/31/2021 15:39:49 - INFO - __main__ - Step 145810: {'lr': 9.886332276912713e-07, 'samples': 27995520, 'steps': 145809, 'loss/train': 1.5598526000976562} 08/31/2021 15:39:49 - INFO - __main__ - Step 145811: {'lr': 9.881618062852482e-07, 'samples': 27995712, 'steps': 145810, 'loss/train': 1.513700008392334} 08/31/2021 15:39:50 - INFO - __main__ - Step 145812: {'lr': 9.876904970801404e-07, 'samples': 27995904, 'steps': 145811, 'loss/train': 1.0645897388458252} 08/31/2021 15:39:50 - INFO - __main__ - Step 145813: {'lr': 9.872193000761144e-07, 'samples': 27996096, 'steps': 145812, 'loss/train': 0.6443301439285278} 08/31/2021 15:39:51 - INFO - __main__ - Step 145814: {'lr': 9.867482152734198e-07, 'samples': 27996288, 'steps': 145813, 'loss/train': 1.4520503282546997} 08/31/2021 15:39:51 - INFO - __main__ - Step 145815: {'lr': 9.862772426722234e-07, 'samples': 27996480, 'steps': 145814, 'loss/train': 1.132883071899414} 08/31/2021 15:39:53 - INFO - __main__ - Step 145816: {'lr': 9.858063822728024e-07, 'samples': 27996672, 'steps': 145815, 'loss/train': 1.1329960823059082} 08/31/2021 15:39:53 - INFO - __main__ - Step 145817: {'lr': 9.853356340752961e-07, 'samples': 27996864, 'steps': 145816, 'loss/train': 1.169083595275879} 08/31/2021 15:39:54 - INFO - __main__ - Step 145818: {'lr': 9.848649980799817e-07, 'samples': 27997056, 'steps': 145817, 'loss/train': 0.8951396346092224} 08/31/2021 15:39:54 - INFO - __main__ - Step 145819: {'lr': 9.843944742870537e-07, 'samples': 27997248, 'steps': 145818, 'loss/train': 0.022302739322185516} 08/31/2021 15:39:54 - INFO - __main__ - Step 145820: {'lr': 9.83924062696706e-07, 'samples': 27997440, 'steps': 145819, 'loss/train': 0.06821350008249283} 08/31/2021 15:39:55 - INFO - __main__ - Step 145821: {'lr': 9.834537633091334e-07, 'samples': 27997632, 'steps': 145820, 'loss/train': 1.3557333946228027} 08/31/2021 15:39:57 - INFO - __main__ - Step 145822: {'lr': 9.82983576124613e-07, 'samples': 27997824, 'steps': 145821, 'loss/train': 0.9178797602653503} 08/31/2021 15:39:57 - INFO - __main__ - Step 145823: {'lr': 9.82513501143284e-07, 'samples': 27998016, 'steps': 145822, 'loss/train': 1.8147460222244263} 08/31/2021 15:39:58 - INFO - __main__ - Step 145824: {'lr': 9.820435383654236e-07, 'samples': 27998208, 'steps': 145823, 'loss/train': 1.072903037071228} 08/31/2021 15:39:58 - INFO - __main__ - Step 145825: {'lr': 9.815736877911984e-07, 'samples': 27998400, 'steps': 145824, 'loss/train': 0.05255547910928726} 08/31/2021 15:39:58 - INFO - __main__ - Step 145826: {'lr': 9.811039494208308e-07, 'samples': 27998592, 'steps': 145825, 'loss/train': 0.584496259689331} 08/31/2021 15:40:00 - INFO - __main__ - Step 145827: {'lr': 9.806343232545424e-07, 'samples': 27998784, 'steps': 145826, 'loss/train': 1.340554118156433} 08/31/2021 15:40:00 - INFO - __main__ - Step 145828: {'lr': 9.801648092925276e-07, 'samples': 27998976, 'steps': 145827, 'loss/train': 0.8439211249351501} 08/31/2021 15:40:00 - INFO - __main__ - Step 145829: {'lr': 9.796954075350083e-07, 'samples': 27999168, 'steps': 145828, 'loss/train': 0.9866899847984314} 08/31/2021 15:40:01 - INFO - __main__ - Step 145830: {'lr': 9.792261179821792e-07, 'samples': 27999360, 'steps': 145829, 'loss/train': 1.3701163530349731} 08/31/2021 15:40:01 - INFO - __main__ - Step 145831: {'lr': 9.7875694063429e-07, 'samples': 27999552, 'steps': 145830, 'loss/train': 0.6991339325904846} 08/31/2021 15:40:03 - INFO - __main__ - Step 145832: {'lr': 9.782878754915347e-07, 'samples': 27999744, 'steps': 145831, 'loss/train': 1.1727842092514038} 08/31/2021 15:40:03 - INFO - __main__ - Step 145833: {'lr': 9.778189225541078e-07, 'samples': 27999936, 'steps': 145832, 'loss/train': 0.6880083084106445} 08/31/2021 15:40:03 - INFO - __main__ - Step 145834: {'lr': 9.773500818222314e-07, 'samples': 28000128, 'steps': 145833, 'loss/train': 0.9289262294769287} 08/31/2021 15:40:04 - INFO - __main__ - Step 145835: {'lr': 9.768813532961273e-07, 'samples': 28000320, 'steps': 145834, 'loss/train': 1.406042218208313} 08/31/2021 15:40:04 - INFO - __main__ - Step 145836: {'lr': 9.764127369760178e-07, 'samples': 28000512, 'steps': 145835, 'loss/train': 0.735226035118103} 08/31/2021 15:40:06 - INFO - __main__ - Step 145837: {'lr': 9.759442328620693e-07, 'samples': 28000704, 'steps': 145836, 'loss/train': 1.6001255512237549} 08/31/2021 15:40:06 - INFO - __main__ - Step 145838: {'lr': 9.75475840954504e-07, 'samples': 28000896, 'steps': 145837, 'loss/train': 0.06322430074214935} 08/31/2021 15:40:07 - INFO - __main__ - Step 145839: {'lr': 9.750075612535714e-07, 'samples': 28001088, 'steps': 145838, 'loss/train': 0.03162258118391037} 08/31/2021 15:40:07 - INFO - __main__ - Step 145840: {'lr': 9.74539393759466e-07, 'samples': 28001280, 'steps': 145839, 'loss/train': 0.9537074565887451} 08/31/2021 15:40:07 - INFO - __main__ - Step 145841: {'lr': 9.740713384723542e-07, 'samples': 28001472, 'steps': 145840, 'loss/train': 1.3454452753067017} 08/31/2021 15:40:09 - INFO - __main__ - Step 145842: {'lr': 9.736033953925138e-07, 'samples': 28001664, 'steps': 145841, 'loss/train': 1.3766282796859741} 08/31/2021 15:40:09 - INFO - __main__ - Step 145843: {'lr': 9.731355645201112e-07, 'samples': 28001856, 'steps': 145842, 'loss/train': 1.1825774908065796} 08/31/2021 15:40:10 - INFO - __main__ - Step 145844: {'lr': 9.726678458553683e-07, 'samples': 28002048, 'steps': 145843, 'loss/train': 1.9628254175186157} 08/31/2021 15:40:10 - INFO - __main__ - Step 145845: {'lr': 9.722002393985075e-07, 'samples': 28002240, 'steps': 145844, 'loss/train': 0.801016628742218} 08/31/2021 15:40:10 - INFO - __main__ - Step 145846: {'lr': 9.717327451497226e-07, 'samples': 28002432, 'steps': 145845, 'loss/train': 1.2537380456924438} 08/31/2021 15:40:11 - INFO - __main__ - Step 145847: {'lr': 9.71265363109236e-07, 'samples': 28002624, 'steps': 145846, 'loss/train': 0.6081877946853638} 08/31/2021 15:40:13 - INFO - __main__ - Step 145848: {'lr': 9.707980932772697e-07, 'samples': 28002816, 'steps': 145847, 'loss/train': 1.2964987754821777} 08/31/2021 15:40:13 - INFO - __main__ - Step 145849: {'lr': 9.703309356539903e-07, 'samples': 28003008, 'steps': 145848, 'loss/train': 1.3780180215835571} 08/31/2021 15:40:14 - INFO - __main__ - Step 145850: {'lr': 9.698638902396473e-07, 'samples': 28003200, 'steps': 145849, 'loss/train': 1.2573161125183105} 08/31/2021 15:40:14 - INFO - __main__ - Step 145851: {'lr': 9.693969570344629e-07, 'samples': 28003392, 'steps': 145850, 'loss/train': 0.620339572429657} 08/31/2021 15:40:14 - INFO - __main__ - Step 145852: {'lr': 9.689301360386037e-07, 'samples': 28003584, 'steps': 145851, 'loss/train': 1.0385491847991943} 08/31/2021 15:40:16 - INFO - __main__ - Step 145853: {'lr': 9.684634272522919e-07, 'samples': 28003776, 'steps': 145852, 'loss/train': 0.04274126887321472} 08/31/2021 15:40:16 - INFO - __main__ - Step 145854: {'lr': 9.679968306757769e-07, 'samples': 28003968, 'steps': 145853, 'loss/train': 1.2542132139205933} 08/31/2021 15:40:17 - INFO - __main__ - Step 145855: {'lr': 9.675303463092255e-07, 'samples': 28004160, 'steps': 145854, 'loss/train': 0.7460969090461731} 08/31/2021 15:40:17 - INFO - __main__ - Step 145856: {'lr': 9.670639741528598e-07, 'samples': 28004352, 'steps': 145855, 'loss/train': 1.0319918394088745} 08/31/2021 15:40:17 - INFO - __main__ - Step 145857: {'lr': 9.665977142068738e-07, 'samples': 28004544, 'steps': 145856, 'loss/train': 0.3437948226928711} 08/31/2021 15:40:19 - INFO - __main__ - Step 145858: {'lr': 9.661315664715453e-07, 'samples': 28004736, 'steps': 145857, 'loss/train': 1.153718113899231} 08/31/2021 15:40:19 - INFO - __main__ - Step 145859: {'lr': 9.656655309469852e-07, 'samples': 28004928, 'steps': 145858, 'loss/train': 1.0766102075576782} 08/31/2021 15:40:20 - INFO - __main__ - Step 145860: {'lr': 9.651996076334712e-07, 'samples': 28005120, 'steps': 145859, 'loss/train': 0.32668712735176086} 08/31/2021 15:40:20 - INFO - __main__ - Step 145861: {'lr': 9.647337965311975e-07, 'samples': 28005312, 'steps': 145860, 'loss/train': 1.0374857187271118} 08/31/2021 15:40:21 - INFO - __main__ - Step 145862: {'lr': 9.642680976403862e-07, 'samples': 28005504, 'steps': 145861, 'loss/train': 1.4203581809997559} 08/31/2021 15:40:22 - INFO - __main__ - Step 145863: {'lr': 9.638025109612037e-07, 'samples': 28005696, 'steps': 145862, 'loss/train': 0.966488242149353} 08/31/2021 15:40:22 - INFO - __main__ - Step 145864: {'lr': 9.633370364938999e-07, 'samples': 28005888, 'steps': 145863, 'loss/train': 0.7777501940727234} 08/31/2021 15:40:23 - INFO - __main__ - Step 145865: {'lr': 9.628716742386967e-07, 'samples': 28006080, 'steps': 145864, 'loss/train': 1.0930931568145752} 08/31/2021 15:40:23 - INFO - __main__ - Step 145866: {'lr': 9.624064241957609e-07, 'samples': 28006272, 'steps': 145865, 'loss/train': 1.0030665397644043} 08/31/2021 15:40:24 - INFO - __main__ - Step 145867: {'lr': 9.619412863653144e-07, 'samples': 28006464, 'steps': 145866, 'loss/train': 0.6383369565010071} 08/31/2021 15:40:24 - INFO - __main__ - Step 145868: {'lr': 9.61476260747579e-07, 'samples': 28006656, 'steps': 145867, 'loss/train': 0.6845178008079529} 08/31/2021 15:40:25 - INFO - __main__ - Step 145869: {'lr': 9.610113473427773e-07, 'samples': 28006848, 'steps': 145868, 'loss/train': 0.9423589706420898} 08/31/2021 15:40:26 - INFO - __main__ - Step 145870: {'lr': 9.605465461510753e-07, 'samples': 28007040, 'steps': 145869, 'loss/train': 1.017603874206543} 08/31/2021 15:40:26 - INFO - __main__ - Step 145871: {'lr': 9.600818571727232e-07, 'samples': 28007232, 'steps': 145870, 'loss/train': 1.902103066444397} 08/31/2021 15:40:26 - INFO - __main__ - Step 145872: {'lr': 9.59617280407915e-07, 'samples': 28007424, 'steps': 145871, 'loss/train': 1.0343713760375977} 08/31/2021 15:40:27 - INFO - __main__ - Step 145873: {'lr': 9.591528158568453e-07, 'samples': 28007616, 'steps': 145872, 'loss/train': 1.0574135780334473} 08/31/2021 15:40:28 - INFO - __main__ - Step 145874: {'lr': 9.586884635197636e-07, 'samples': 28007808, 'steps': 145873, 'loss/train': 1.1619598865509033} 08/31/2021 15:40:29 - INFO - __main__ - Step 145875: {'lr': 9.582242233968363e-07, 'samples': 28008000, 'steps': 145874, 'loss/train': 0.02270864136517048} 08/31/2021 15:40:29 - INFO - __main__ - Step 145876: {'lr': 9.577600954882858e-07, 'samples': 28008192, 'steps': 145875, 'loss/train': 0.8516996502876282} 08/31/2021 15:40:29 - INFO - __main__ - Step 145877: {'lr': 9.572960797943342e-07, 'samples': 28008384, 'steps': 145876, 'loss/train': 1.0014092922210693} 08/31/2021 15:40:30 - INFO - __main__ - Step 145878: {'lr': 9.568321763151756e-07, 'samples': 28008576, 'steps': 145877, 'loss/train': 1.3301293849945068} 08/31/2021 15:40:31 - INFO - __main__ - Step 145879: {'lr': 9.563683850510319e-07, 'samples': 28008768, 'steps': 145878, 'loss/train': 0.9875851273536682} 08/31/2021 15:40:32 - INFO - __main__ - Step 145880: {'lr': 9.559047060021254e-07, 'samples': 28008960, 'steps': 145879, 'loss/train': 1.3591629266738892} 08/31/2021 15:40:32 - INFO - __main__ - Step 145881: {'lr': 9.554411391686225e-07, 'samples': 28009152, 'steps': 145880, 'loss/train': 0.9386593103408813} 08/31/2021 15:40:33 - INFO - __main__ - Step 145882: {'lr': 9.549776845507452e-07, 'samples': 28009344, 'steps': 145881, 'loss/train': 1.2742247581481934} 08/31/2021 15:40:33 - INFO - __main__ - Step 145883: {'lr': 9.545143421487435e-07, 'samples': 28009536, 'steps': 145882, 'loss/train': 0.973842442035675} 08/31/2021 15:40:35 - INFO - __main__ - Step 145884: {'lr': 9.54051111962756e-07, 'samples': 28009728, 'steps': 145883, 'loss/train': 1.3740850687026978} 08/31/2021 15:40:35 - INFO - __main__ - Step 145885: {'lr': 9.535879939930603e-07, 'samples': 28009920, 'steps': 145884, 'loss/train': 1.2716609239578247} 08/31/2021 15:40:36 - INFO - __main__ - Step 145886: {'lr': 9.531249882398229e-07, 'samples': 28010112, 'steps': 145885, 'loss/train': 1.606218695640564} 08/31/2021 15:40:36 - INFO - __main__ - Step 145887: {'lr': 9.526620947032661e-07, 'samples': 28010304, 'steps': 145886, 'loss/train': 0.014341837726533413} 08/31/2021 15:40:37 - INFO - __main__ - Step 145888: {'lr': 9.521993133835838e-07, 'samples': 28010496, 'steps': 145887, 'loss/train': 1.449406385421753} 08/31/2021 15:40:37 - INFO - __main__ - Step 145889: {'lr': 9.51736644281026e-07, 'samples': 28010688, 'steps': 145888, 'loss/train': 0.6110820174217224} 08/31/2021 15:40:39 - INFO - __main__ - Step 145890: {'lr': 9.512740873957592e-07, 'samples': 28010880, 'steps': 145889, 'loss/train': 0.6937428116798401} 08/31/2021 15:40:39 - INFO - __main__ - Step 145891: {'lr': 9.508116427279779e-07, 'samples': 28011072, 'steps': 145890, 'loss/train': 0.2906927168369293} 08/31/2021 15:40:40 - INFO - __main__ - Step 145892: {'lr': 9.503493102779592e-07, 'samples': 28011264, 'steps': 145891, 'loss/train': 0.48993682861328125} 08/31/2021 15:40:40 - INFO - __main__ - Step 145893: {'lr': 9.498870900458422e-07, 'samples': 28011456, 'steps': 145892, 'loss/train': 1.0787255764007568} 08/31/2021 15:40:40 - INFO - __main__ - Step 145894: {'lr': 9.494249820318768e-07, 'samples': 28011648, 'steps': 145893, 'loss/train': 0.014635633677244186} 08/31/2021 15:40:41 - INFO - __main__ - Step 145895: {'lr': 9.48962986236257e-07, 'samples': 28011840, 'steps': 145894, 'loss/train': 1.4123879671096802} 08/31/2021 15:40:42 - INFO - __main__ - Step 145896: {'lr': 9.48501102659205e-07, 'samples': 28012032, 'steps': 145895, 'loss/train': 1.1866828203201294} 08/31/2021 15:40:42 - INFO - __main__ - Step 145897: {'lr': 9.480393313008873e-07, 'samples': 28012224, 'steps': 145896, 'loss/train': 0.8498523831367493} 08/31/2021 15:40:43 - INFO - __main__ - Step 145898: {'lr': 9.475776721615537e-07, 'samples': 28012416, 'steps': 145897, 'loss/train': 0.8738054633140564} 08/31/2021 15:40:43 - INFO - __main__ - Step 145899: {'lr': 9.471161252413984e-07, 'samples': 28012608, 'steps': 145898, 'loss/train': 1.208335041999817} 08/31/2021 15:40:44 - INFO - __main__ - Step 145900: {'lr': 9.46654690540616e-07, 'samples': 28012800, 'steps': 145899, 'loss/train': 1.4086207151412964} 08/31/2021 15:40:46 - INFO - __main__ - Step 145901: {'lr': 9.461933680594559e-07, 'samples': 28012992, 'steps': 145900, 'loss/train': 1.3755733966827393} 08/31/2021 15:40:46 - INFO - __main__ - Step 145902: {'lr': 9.457321577980849e-07, 'samples': 28013184, 'steps': 145901, 'loss/train': 0.38141828775405884} 08/31/2021 15:40:46 - INFO - __main__ - Step 145903: {'lr': 9.452710597566971e-07, 'samples': 28013376, 'steps': 145902, 'loss/train': 1.0907354354858398} 08/31/2021 15:40:47 - INFO - __main__ - Step 145904: {'lr': 9.448100739355703e-07, 'samples': 28013568, 'steps': 145903, 'loss/train': 1.4059090614318848} 08/31/2021 15:40:47 - INFO - __main__ - Step 145905: {'lr': 9.443492003348431e-07, 'samples': 28013760, 'steps': 145904, 'loss/train': 1.7544567584991455} 08/31/2021 15:40:49 - INFO - __main__ - Step 145906: {'lr': 9.438884389547375e-07, 'samples': 28013952, 'steps': 145905, 'loss/train': 1.3907438516616821} 08/31/2021 15:40:49 - INFO - __main__ - Step 145907: {'lr': 9.434277897955034e-07, 'samples': 28014144, 'steps': 145906, 'loss/train': 0.7761678099632263} 08/31/2021 15:40:50 - INFO - __main__ - Step 145908: {'lr': 9.429672528573075e-07, 'samples': 28014336, 'steps': 145907, 'loss/train': 1.1164437532424927} 08/31/2021 15:40:50 - INFO - __main__ - Step 145909: {'lr': 9.425068281403714e-07, 'samples': 28014528, 'steps': 145908, 'loss/train': 2.0386619567871094} 08/31/2021 15:40:50 - INFO - __main__ - Step 145910: {'lr': 9.420465156448898e-07, 'samples': 28014720, 'steps': 145909, 'loss/train': 0.037189334630966187} 08/31/2021 15:40:52 - INFO - __main__ - Step 145911: {'lr': 9.415863153710846e-07, 'samples': 28014912, 'steps': 145910, 'loss/train': 1.4021897315979004} 08/31/2021 15:40:53 - INFO - __main__ - Step 145912: {'lr': 9.411262273191501e-07, 'samples': 28015104, 'steps': 145911, 'loss/train': 0.9978731274604797} 08/31/2021 15:40:53 - INFO - __main__ - Step 145913: {'lr': 9.406662514893083e-07, 'samples': 28015296, 'steps': 145912, 'loss/train': 0.8542333841323853} 08/31/2021 15:40:53 - INFO - __main__ - Step 145914: {'lr': 9.402063878817535e-07, 'samples': 28015488, 'steps': 145913, 'loss/train': 0.9760128855705261} 08/31/2021 15:40:54 - INFO - __main__ - Step 145915: {'lr': 9.397466364966801e-07, 'samples': 28015680, 'steps': 145914, 'loss/train': 0.8982588052749634} 08/31/2021 15:40:55 - INFO - __main__ - Step 145916: {'lr': 9.392869973343377e-07, 'samples': 28015872, 'steps': 145915, 'loss/train': 1.3542968034744263} 08/31/2021 15:40:56 - INFO - __main__ - Step 145917: {'lr': 9.388274703949207e-07, 'samples': 28016064, 'steps': 145916, 'loss/train': 1.3344677686691284} 08/31/2021 15:40:56 - INFO - __main__ - Step 145918: {'lr': 9.383680556785956e-07, 'samples': 28016256, 'steps': 145917, 'loss/train': 0.11364889144897461} 08/31/2021 15:40:57 - INFO - __main__ - Step 145919: {'lr': 9.379087531856123e-07, 'samples': 28016448, 'steps': 145918, 'loss/train': 1.2231136560440063} 08/31/2021 15:40:57 - INFO - __main__ - Step 145920: {'lr': 9.37449562916165e-07, 'samples': 28016640, 'steps': 145919, 'loss/train': 1.269698977470398} 08/31/2021 15:40:57 - INFO - __main__ - Step 145921: {'lr': 9.369904848704757e-07, 'samples': 28016832, 'steps': 145920, 'loss/train': 0.8033469319343567} 08/31/2021 15:40:59 - INFO - __main__ - Step 145922: {'lr': 9.365315190487111e-07, 'samples': 28017024, 'steps': 145921, 'loss/train': 0.017245711758732796} 08/31/2021 15:41:00 - INFO - __main__ - Step 145923: {'lr': 9.360726654510932e-07, 'samples': 28017216, 'steps': 145922, 'loss/train': 0.9044644832611084} 08/31/2021 15:41:00 - INFO - __main__ - Step 145924: {'lr': 9.356139240778716e-07, 'samples': 28017408, 'steps': 145923, 'loss/train': 0.9546906352043152} 08/31/2021 15:41:01 - INFO - __main__ - Step 145925: {'lr': 9.351552949291853e-07, 'samples': 28017600, 'steps': 145924, 'loss/train': 2.1726346015930176} 08/31/2021 15:41:01 - INFO - __main__ - Step 145926: {'lr': 9.34696778005284e-07, 'samples': 28017792, 'steps': 145925, 'loss/train': 2.1446611881256104} 08/31/2021 15:41:01 - INFO - __main__ - Step 145927: {'lr': 9.342383733063898e-07, 'samples': 28017984, 'steps': 145926, 'loss/train': 1.7723714113235474} 08/31/2021 15:41:03 - INFO - __main__ - Step 145928: {'lr': 9.337800808326691e-07, 'samples': 28018176, 'steps': 145927, 'loss/train': 1.443975567817688} 08/31/2021 15:41:04 - INFO - __main__ - Step 145929: {'lr': 9.333219005843163e-07, 'samples': 28018368, 'steps': 145928, 'loss/train': 0.810783863067627} 08/31/2021 15:41:04 - INFO - __main__ - Step 145930: {'lr': 9.32863832561609e-07, 'samples': 28018560, 'steps': 145929, 'loss/train': 1.2999515533447266} 08/31/2021 15:41:04 - INFO - __main__ - Step 145931: {'lr': 9.324058767646859e-07, 'samples': 28018752, 'steps': 145930, 'loss/train': 0.1210528314113617} 08/31/2021 15:41:05 - INFO - __main__ - Step 145932: {'lr': 9.31948033193769e-07, 'samples': 28018944, 'steps': 145931, 'loss/train': 0.7069069147109985} 08/31/2021 15:41:06 - INFO - __main__ - Step 145933: {'lr': 9.314903018490806e-07, 'samples': 28019136, 'steps': 145932, 'loss/train': 1.1648061275482178} 08/31/2021 15:41:07 - INFO - __main__ - Step 145934: {'lr': 9.310326827308424e-07, 'samples': 28019328, 'steps': 145933, 'loss/train': 1.0262073278427124} 08/31/2021 15:41:07 - INFO - __main__ - Step 145935: {'lr': 9.305751758392212e-07, 'samples': 28019520, 'steps': 145934, 'loss/train': 1.0122023820877075} 08/31/2021 15:41:07 - INFO - __main__ - Step 145936: {'lr': 9.301177811744388e-07, 'samples': 28019712, 'steps': 145935, 'loss/train': 1.257809042930603} 08/31/2021 15:41:08 - INFO - __main__ - Step 145937: {'lr': 9.296604987366897e-07, 'samples': 28019904, 'steps': 145936, 'loss/train': 0.9510401487350464} 08/31/2021 15:41:09 - INFO - __main__ - Step 145938: {'lr': 9.292033285262236e-07, 'samples': 28020096, 'steps': 145937, 'loss/train': 1.3535829782485962} 08/31/2021 15:41:10 - INFO - __main__ - Step 145939: {'lr': 9.287462705431793e-07, 'samples': 28020288, 'steps': 145938, 'loss/train': 0.36559680104255676} 08/31/2021 15:41:10 - INFO - __main__ - Step 145940: {'lr': 9.282893247878066e-07, 'samples': 28020480, 'steps': 145939, 'loss/train': 1.5366480350494385} 08/31/2021 15:41:10 - INFO - __main__ - Step 145941: {'lr': 9.278324912603276e-07, 'samples': 28020672, 'steps': 145940, 'loss/train': 1.5493144989013672} 08/31/2021 15:41:11 - INFO - __main__ - Step 145942: {'lr': 9.273757699609087e-07, 'samples': 28020864, 'steps': 145941, 'loss/train': 1.2206048965454102} 08/31/2021 15:41:11 - INFO - __main__ - Step 145943: {'lr': 9.26919160889772e-07, 'samples': 28021056, 'steps': 145942, 'loss/train': 1.0848885774612427} 08/31/2021 15:41:13 - INFO - __main__ - Step 145944: {'lr': 9.264626640471119e-07, 'samples': 28021248, 'steps': 145943, 'loss/train': 1.0422216653823853} 08/31/2021 15:41:13 - INFO - __main__ - Step 145945: {'lr': 9.260062794331503e-07, 'samples': 28021440, 'steps': 145944, 'loss/train': 0.7916135191917419} 08/31/2021 15:41:13 - INFO - __main__ - Step 145946: {'lr': 9.255500070480816e-07, 'samples': 28021632, 'steps': 145945, 'loss/train': 1.422181248664856} 08/31/2021 15:41:14 - INFO - __main__ - Step 145947: {'lr': 9.250938468921278e-07, 'samples': 28021824, 'steps': 145946, 'loss/train': 1.9565402269363403} 08/31/2021 15:41:14 - INFO - __main__ - Step 145948: {'lr': 9.246377989654831e-07, 'samples': 28022016, 'steps': 145947, 'loss/train': 1.528106451034546} 08/31/2021 15:41:16 - INFO - __main__ - Step 145949: {'lr': 9.241818632683419e-07, 'samples': 28022208, 'steps': 145948, 'loss/train': 1.1467593908309937} 08/31/2021 15:41:16 - INFO - __main__ - Step 145950: {'lr': 9.237260398009261e-07, 'samples': 28022400, 'steps': 145949, 'loss/train': 0.6319223046302795} 08/31/2021 15:41:16 - INFO - __main__ - Step 145951: {'lr': 9.23270328563458e-07, 'samples': 28022592, 'steps': 145950, 'loss/train': 0.41254544258117676} 08/31/2021 15:41:17 - INFO - __main__ - Step 145952: {'lr': 9.228147295561041e-07, 'samples': 28022784, 'steps': 145951, 'loss/train': 1.2561191320419312} 08/31/2021 15:41:17 - INFO - __main__ - Step 145953: {'lr': 9.223592427790584e-07, 'samples': 28022976, 'steps': 145952, 'loss/train': 1.0549312829971313} 08/31/2021 15:41:19 - INFO - __main__ - Step 145954: {'lr': 9.219038682325986e-07, 'samples': 28023168, 'steps': 145953, 'loss/train': 1.0803110599517822} 08/31/2021 15:41:20 - INFO - __main__ - Step 145955: {'lr': 9.214486059168636e-07, 'samples': 28023360, 'steps': 145954, 'loss/train': 1.437951683998108} 08/31/2021 15:41:20 - INFO - __main__ - Step 145956: {'lr': 9.209934558320754e-07, 'samples': 28023552, 'steps': 145955, 'loss/train': 0.41326984763145447} 08/31/2021 15:41:20 - INFO - __main__ - Step 145957: {'lr': 9.20538417978456e-07, 'samples': 28023744, 'steps': 145956, 'loss/train': 0.46636319160461426} 08/31/2021 15:41:21 - INFO - __main__ - Step 145958: {'lr': 9.200834923561719e-07, 'samples': 28023936, 'steps': 145957, 'loss/train': 1.503411889076233} 08/31/2021 15:41:22 - INFO - __main__ - Step 145959: {'lr': 9.196286789655006e-07, 'samples': 28024128, 'steps': 145958, 'loss/train': 1.2374284267425537} 08/31/2021 15:41:23 - INFO - __main__ - Step 145960: {'lr': 9.191739778065533e-07, 'samples': 28024320, 'steps': 145959, 'loss/train': 0.9995163083076477} 08/31/2021 15:41:23 - INFO - __main__ - Step 145961: {'lr': 9.187193888796353e-07, 'samples': 28024512, 'steps': 145960, 'loss/train': 1.4219958782196045} 08/31/2021 15:41:23 - INFO - __main__ - Step 145962: {'lr': 9.182649121848574e-07, 'samples': 28024704, 'steps': 145961, 'loss/train': 1.4028735160827637} 08/31/2021 15:41:24 - INFO - __main__ - Step 145963: {'lr': 9.178105477224696e-07, 'samples': 28024896, 'steps': 145962, 'loss/train': 1.4420504570007324} 08/31/2021 15:41:25 - INFO - __main__ - Step 145964: {'lr': 9.173562954926939e-07, 'samples': 28025088, 'steps': 145963, 'loss/train': 1.1629257202148438} 08/31/2021 15:41:26 - INFO - __main__ - Step 145965: {'lr': 9.169021554956969e-07, 'samples': 28025280, 'steps': 145964, 'loss/train': 0.6959947347640991} 08/31/2021 15:41:26 - INFO - __main__ - Step 145966: {'lr': 9.164481277317005e-07, 'samples': 28025472, 'steps': 145965, 'loss/train': 1.5766534805297852} 08/31/2021 15:41:26 - INFO - __main__ - Step 145967: {'lr': 9.159942122009269e-07, 'samples': 28025664, 'steps': 145966, 'loss/train': 1.029273271560669} 08/31/2021 15:41:27 - INFO - __main__ - Step 145968: {'lr': 9.155404089035424e-07, 'samples': 28025856, 'steps': 145967, 'loss/train': 1.3435413837432861} 08/31/2021 15:41:27 - INFO - __main__ - Step 145969: {'lr': 9.150867178397692e-07, 'samples': 28026048, 'steps': 145968, 'loss/train': 0.5343133211135864} 08/31/2021 15:41:29 - INFO - __main__ - Step 145970: {'lr': 9.146331390098294e-07, 'samples': 28026240, 'steps': 145969, 'loss/train': 0.9556995630264282} 08/31/2021 15:41:29 - INFO - __main__ - Step 145971: {'lr': 9.141796724138895e-07, 'samples': 28026432, 'steps': 145970, 'loss/train': 1.8867002725601196} 08/31/2021 15:41:29 - INFO - __main__ - Step 145972: {'lr': 9.137263180521993e-07, 'samples': 28026624, 'steps': 145971, 'loss/train': 0.9256072044372559} 08/31/2021 15:41:30 - INFO - __main__ - Step 145973: {'lr': 9.132730759249252e-07, 'samples': 28026816, 'steps': 145972, 'loss/train': 0.28208962082862854} 08/31/2021 15:41:30 - INFO - __main__ - Step 145974: {'lr': 9.128199460323172e-07, 'samples': 28027008, 'steps': 145973, 'loss/train': 0.026304641738533974} 08/31/2021 15:41:32 - INFO - __main__ - Step 145975: {'lr': 9.12366928374514e-07, 'samples': 28027200, 'steps': 145974, 'loss/train': 0.7617393732070923} 08/31/2021 15:41:32 - INFO - __main__ - Step 145976: {'lr': 9.119140229517653e-07, 'samples': 28027392, 'steps': 145975, 'loss/train': 1.109067440032959} 08/31/2021 15:41:32 - INFO - __main__ - Step 145977: {'lr': 9.114612297642655e-07, 'samples': 28027584, 'steps': 145976, 'loss/train': 1.3541898727416992} 08/31/2021 15:41:33 - INFO - __main__ - Step 145978: {'lr': 9.110085488122367e-07, 'samples': 28027776, 'steps': 145977, 'loss/train': 0.9054210186004639} 08/31/2021 15:41:33 - INFO - __main__ - Step 145979: {'lr': 9.105559800958452e-07, 'samples': 28027968, 'steps': 145978, 'loss/train': 0.8206726312637329} 08/31/2021 15:41:33 - INFO - __main__ - Step 145980: {'lr': 9.101035236153133e-07, 'samples': 28028160, 'steps': 145979, 'loss/train': 0.6299381852149963} 08/31/2021 15:41:35 - INFO - __main__ - Step 145981: {'lr': 9.09651179370835e-07, 'samples': 28028352, 'steps': 145980, 'loss/train': 0.8441950082778931} 08/31/2021 15:41:36 - INFO - __main__ - Step 145982: {'lr': 9.091989473626327e-07, 'samples': 28028544, 'steps': 145981, 'loss/train': 1.0685386657714844} 08/31/2021 15:41:36 - INFO - __main__ - Step 145983: {'lr': 9.087468275909006e-07, 'samples': 28028736, 'steps': 145982, 'loss/train': 0.6513147950172424} 08/31/2021 15:41:36 - INFO - __main__ - Step 145984: {'lr': 9.082948200558606e-07, 'samples': 28028928, 'steps': 145983, 'loss/train': 1.1673731803894043} 08/31/2021 15:41:37 - INFO - __main__ - Step 145985: {'lr': 9.078429247576792e-07, 'samples': 28029120, 'steps': 145984, 'loss/train': 1.7252246141433716} 08/31/2021 15:41:37 - INFO - __main__ - Step 145986: {'lr': 9.073911416965785e-07, 'samples': 28029312, 'steps': 145985, 'loss/train': 0.6964435577392578} 08/31/2021 15:41:39 - INFO - __main__ - Step 145987: {'lr': 9.069394708727807e-07, 'samples': 28029504, 'steps': 145986, 'loss/train': 1.198531985282898} 08/31/2021 15:41:40 - INFO - __main__ - Step 145988: {'lr': 9.0648791228648e-07, 'samples': 28029696, 'steps': 145987, 'loss/train': 0.7306763529777527} 08/31/2021 15:41:40 - INFO - __main__ - Step 145989: {'lr': 9.060364659378428e-07, 'samples': 28029888, 'steps': 145988, 'loss/train': 0.03377271071076393} 08/31/2021 15:41:40 - INFO - __main__ - Step 145990: {'lr': 9.055851318271191e-07, 'samples': 28030080, 'steps': 145989, 'loss/train': 0.7941257357597351} 08/31/2021 15:41:41 - INFO - __main__ - Step 145991: {'lr': 9.051339099544753e-07, 'samples': 28030272, 'steps': 145990, 'loss/train': 0.04516663774847984} 08/31/2021 15:41:42 - INFO - __main__ - Step 145992: {'lr': 9.046828003201613e-07, 'samples': 28030464, 'steps': 145991, 'loss/train': 0.9719338417053223} 08/31/2021 15:41:43 - INFO - __main__ - Step 145993: {'lr': 9.042318029243435e-07, 'samples': 28030656, 'steps': 145992, 'loss/train': 1.1898164749145508} 08/31/2021 15:41:43 - INFO - __main__ - Step 145994: {'lr': 9.037809177672162e-07, 'samples': 28030848, 'steps': 145993, 'loss/train': 1.1050623655319214} 08/31/2021 15:41:43 - INFO - __main__ - Step 145995: {'lr': 9.033301448490294e-07, 'samples': 28031040, 'steps': 145994, 'loss/train': 1.005064606666565} 08/31/2021 15:41:44 - INFO - __main__ - Step 145996: {'lr': 9.028794841699495e-07, 'samples': 28031232, 'steps': 145995, 'loss/train': 1.1456981897354126} 08/31/2021 15:41:44 - INFO - __main__ - Step 145997: {'lr': 9.024289357301707e-07, 'samples': 28031424, 'steps': 145996, 'loss/train': 0.4648797810077667} 08/31/2021 15:41:46 - INFO - __main__ - Step 145998: {'lr': 9.019784995299429e-07, 'samples': 28031616, 'steps': 145997, 'loss/train': 0.02749633975327015} 08/31/2021 15:41:46 - INFO - __main__ - Step 145999: {'lr': 9.015281755694327e-07, 'samples': 28031808, 'steps': 145998, 'loss/train': 1.044128656387329} 08/31/2021 15:41:46 - INFO - __main__ - Step 146000: {'lr': 9.010779638488342e-07, 'samples': 28032000, 'steps': 145999, 'loss/train': 0.9037817120552063} 08/31/2021 15:41:47 - INFO - __main__ - Step 146001: {'lr': 9.006278643683696e-07, 'samples': 28032192, 'steps': 146000, 'loss/train': 1.0164406299591064} 08/31/2021 15:41:47 - INFO - __main__ - Step 146002: {'lr': 9.001778771282609e-07, 'samples': 28032384, 'steps': 146001, 'loss/train': 0.6247076392173767} 08/31/2021 15:41:49 - INFO - __main__ - Step 146003: {'lr': 8.997280021286747e-07, 'samples': 28032576, 'steps': 146002, 'loss/train': 1.311667561531067} 08/31/2021 15:41:49 - INFO - __main__ - Step 146004: {'lr': 8.992782393698051e-07, 'samples': 28032768, 'steps': 146003, 'loss/train': 1.2112668752670288} 08/31/2021 15:41:49 - INFO - __main__ - Step 146005: {'lr': 8.988285888519021e-07, 'samples': 28032960, 'steps': 146004, 'loss/train': 0.6422314643859863} 08/31/2021 15:41:50 - INFO - __main__ - Step 146006: {'lr': 8.983790505751322e-07, 'samples': 28033152, 'steps': 146005, 'loss/train': 0.963500440120697} 08/31/2021 15:41:50 - INFO - __main__ - Step 146007: {'lr': 8.979296245397172e-07, 'samples': 28033344, 'steps': 146006, 'loss/train': 0.5945030450820923} 08/31/2021 15:41:52 - INFO - __main__ - Step 146008: {'lr': 8.974803107458518e-07, 'samples': 28033536, 'steps': 146007, 'loss/train': 1.5592927932739258} 08/31/2021 15:41:52 - INFO - __main__ - Step 146009: {'lr': 8.9703110919373e-07, 'samples': 28033728, 'steps': 146008, 'loss/train': 1.380167007446289} 08/31/2021 15:41:52 - INFO - __main__ - Step 146010: {'lr': 8.965820198835461e-07, 'samples': 28033920, 'steps': 146009, 'loss/train': 1.562402606010437} 08/31/2021 15:41:53 - INFO - __main__ - Step 146011: {'lr': 8.961330428155501e-07, 'samples': 28034112, 'steps': 146010, 'loss/train': 1.1084940433502197} 08/31/2021 15:41:53 - INFO - __main__ - Step 146012: {'lr': 8.956841779899083e-07, 'samples': 28034304, 'steps': 146011, 'loss/train': 0.9568097591400146} 08/31/2021 15:41:55 - INFO - __main__ - Step 146013: {'lr': 8.952354254068151e-07, 'samples': 28034496, 'steps': 146012, 'loss/train': 0.046997930854558945} 08/31/2021 15:41:56 - INFO - __main__ - Step 146014: {'lr': 8.947867850664926e-07, 'samples': 28034688, 'steps': 146013, 'loss/train': 0.023152709007263184} 08/31/2021 15:41:56 - INFO - __main__ - Step 146015: {'lr': 8.94338256969135e-07, 'samples': 28034880, 'steps': 146014, 'loss/train': 0.9803063869476318} 08/31/2021 15:41:56 - INFO - __main__ - Step 146016: {'lr': 8.938898411149366e-07, 'samples': 28035072, 'steps': 146015, 'loss/train': 1.4148718118667603} 08/31/2021 15:41:57 - INFO - __main__ - Step 146017: {'lr': 8.934415375041194e-07, 'samples': 28035264, 'steps': 146016, 'loss/train': 0.7971121668815613} 08/31/2021 15:41:58 - INFO - __main__ - Step 146018: {'lr': 8.9299334613685e-07, 'samples': 28035456, 'steps': 146017, 'loss/train': 1.0000569820404053} 08/31/2021 15:41:59 - INFO - __main__ - Step 146019: {'lr': 8.925452670133783e-07, 'samples': 28035648, 'steps': 146018, 'loss/train': 0.5812630653381348} 08/31/2021 15:41:59 - INFO - __main__ - Step 146020: {'lr': 8.920973001338705e-07, 'samples': 28035840, 'steps': 146019, 'loss/train': 0.8105009198188782} 08/31/2021 15:42:00 - INFO - __main__ - Step 146021: {'lr': 8.916494454985491e-07, 'samples': 28036032, 'steps': 146020, 'loss/train': 0.8118460178375244} 08/31/2021 15:42:00 - INFO - __main__ - Step 146022: {'lr': 8.912017031075804e-07, 'samples': 28036224, 'steps': 146021, 'loss/train': 0.17990240454673767} 08/31/2021 15:42:01 - INFO - __main__ - Step 146023: {'lr': 8.90754072961214e-07, 'samples': 28036416, 'steps': 146022, 'loss/train': 1.3443301916122437} 08/31/2021 15:42:02 - INFO - __main__ - Step 146024: {'lr': 8.903065550596445e-07, 'samples': 28036608, 'steps': 146023, 'loss/train': 0.8486469984054565} 08/31/2021 15:42:02 - INFO - __main__ - Step 146025: {'lr': 8.898591494030384e-07, 'samples': 28036800, 'steps': 146024, 'loss/train': 0.8797221779823303} 08/31/2021 15:42:03 - INFO - __main__ - Step 146026: {'lr': 8.894118559916176e-07, 'samples': 28036992, 'steps': 146025, 'loss/train': 1.375723123550415} 08/31/2021 15:42:03 - INFO - __main__ - Step 146027: {'lr': 8.889646748255764e-07, 'samples': 28037184, 'steps': 146026, 'loss/train': 1.2266281843185425} 08/31/2021 15:42:04 - INFO - __main__ - Step 146028: {'lr': 8.885176059051369e-07, 'samples': 28037376, 'steps': 146027, 'loss/train': 0.6858140230178833} 08/31/2021 15:42:05 - INFO - __main__ - Step 146029: {'lr': 8.880706492304935e-07, 'samples': 28037568, 'steps': 146028, 'loss/train': 0.6172080636024475} 08/31/2021 15:42:05 - INFO - __main__ - Step 146030: {'lr': 8.876238048018404e-07, 'samples': 28037760, 'steps': 146029, 'loss/train': 0.5351584553718567} 08/31/2021 15:42:06 - INFO - __main__ - Step 146031: {'lr': 8.871770726193718e-07, 'samples': 28037952, 'steps': 146030, 'loss/train': 0.09182210266590118} 08/31/2021 15:42:06 - INFO - __main__ - Step 146032: {'lr': 8.86730452683282e-07, 'samples': 28038144, 'steps': 146031, 'loss/train': 0.18161483108997345} 08/31/2021 15:42:07 - INFO - __main__ - Step 146033: {'lr': 8.862839449938209e-07, 'samples': 28038336, 'steps': 146032, 'loss/train': 0.023276275023818016} 08/31/2021 15:42:08 - INFO - __main__ - Step 146034: {'lr': 8.858375495511273e-07, 'samples': 28038528, 'steps': 146033, 'loss/train': 0.6855226755142212} 08/31/2021 15:42:08 - INFO - __main__ - Step 146035: {'lr': 8.853912663554508e-07, 'samples': 28038720, 'steps': 146034, 'loss/train': 1.7071380615234375} 08/31/2021 15:42:09 - INFO - __main__ - Step 146036: {'lr': 8.849450954069582e-07, 'samples': 28038912, 'steps': 146035, 'loss/train': 1.1730639934539795} 08/31/2021 15:42:09 - INFO - __main__ - Step 146037: {'lr': 8.844990367058714e-07, 'samples': 28039104, 'steps': 146036, 'loss/train': 0.9242681860923767} 08/31/2021 15:42:09 - INFO - __main__ - Step 146038: {'lr': 8.840530902523847e-07, 'samples': 28039296, 'steps': 146037, 'loss/train': 1.1035507917404175} 08/31/2021 15:42:11 - INFO - __main__ - Step 146039: {'lr': 8.836072560466923e-07, 'samples': 28039488, 'steps': 146038, 'loss/train': 0.41958409547805786} 08/31/2021 15:42:11 - INFO - __main__ - Step 146040: {'lr': 8.831615340890165e-07, 'samples': 28039680, 'steps': 146039, 'loss/train': 1.3167296648025513} 08/31/2021 15:42:12 - INFO - __main__ - Step 146041: {'lr': 8.827159243795513e-07, 'samples': 28039872, 'steps': 146040, 'loss/train': 0.8714505434036255} 08/31/2021 15:42:12 - INFO - __main__ - Step 146042: {'lr': 8.822704269184633e-07, 'samples': 28040064, 'steps': 146041, 'loss/train': 0.2435053586959839} 08/31/2021 15:42:12 - INFO - __main__ - Step 146043: {'lr': 8.818250417060026e-07, 'samples': 28040256, 'steps': 146042, 'loss/train': 1.3697882890701294} 08/31/2021 15:42:14 - INFO - __main__ - Step 146044: {'lr': 8.813797687423353e-07, 'samples': 28040448, 'steps': 146043, 'loss/train': 1.3828635215759277} 08/31/2021 15:42:14 - INFO - __main__ - Step 146045: {'lr': 8.809346080276837e-07, 'samples': 28040640, 'steps': 146044, 'loss/train': 1.4458682537078857} 08/31/2021 15:42:15 - INFO - __main__ - Step 146046: {'lr': 8.80489559562242e-07, 'samples': 28040832, 'steps': 146045, 'loss/train': 1.4659144878387451} 08/31/2021 15:42:15 - INFO - __main__ - Step 146047: {'lr': 8.800446233461768e-07, 'samples': 28041024, 'steps': 146046, 'loss/train': 0.6634551286697388} 08/31/2021 15:42:15 - INFO - __main__ - Step 146048: {'lr': 8.795997993797378e-07, 'samples': 28041216, 'steps': 146047, 'loss/train': 1.2120563983917236} 08/31/2021 15:42:17 - INFO - __main__ - Step 146049: {'lr': 8.791550876631193e-07, 'samples': 28041408, 'steps': 146048, 'loss/train': 0.7316702008247375} 08/31/2021 15:42:18 - INFO - __main__ - Step 146050: {'lr': 8.78710488196488e-07, 'samples': 28041600, 'steps': 146049, 'loss/train': 1.4294883012771606} 08/31/2021 15:42:18 - INFO - __main__ - Step 146051: {'lr': 8.782660009800936e-07, 'samples': 28041792, 'steps': 146050, 'loss/train': 1.2077558040618896} 08/31/2021 15:42:18 - INFO - __main__ - Step 146052: {'lr': 8.778216260140748e-07, 'samples': 28041984, 'steps': 146051, 'loss/train': 0.9874078631401062} 08/31/2021 15:42:19 - INFO - __main__ - Step 146053: {'lr': 8.773773632987092e-07, 'samples': 28042176, 'steps': 146052, 'loss/train': 0.07403577119112015} 08/31/2021 15:42:20 - INFO - __main__ - Step 146054: {'lr': 8.769332128341079e-07, 'samples': 28042368, 'steps': 146053, 'loss/train': 1.4792729616165161} 08/31/2021 15:42:21 - INFO - __main__ - Step 146055: {'lr': 8.764891746205483e-07, 'samples': 28042560, 'steps': 146054, 'loss/train': 0.3490804135799408} 08/31/2021 15:42:21 - INFO - __main__ - Step 146056: {'lr': 8.760452486581971e-07, 'samples': 28042752, 'steps': 146055, 'loss/train': 1.5114567279815674} 08/31/2021 15:42:21 - INFO - __main__ - Step 146057: {'lr': 8.756014349472208e-07, 'samples': 28042944, 'steps': 146056, 'loss/train': 1.3769069910049438} 08/31/2021 15:42:22 - INFO - __main__ - Step 146058: {'lr': 8.751577334878969e-07, 'samples': 28043136, 'steps': 146057, 'loss/train': 1.005852222442627} 08/31/2021 15:42:23 - INFO - __main__ - Step 146059: {'lr': 8.747141442803641e-07, 'samples': 28043328, 'steps': 146058, 'loss/train': 0.9402498006820679} 08/31/2021 15:42:24 - INFO - __main__ - Step 146060: {'lr': 8.742706673248168e-07, 'samples': 28043520, 'steps': 146059, 'loss/train': 1.6852413415908813} 08/31/2021 15:42:24 - INFO - __main__ - Step 146061: {'lr': 8.738273026215049e-07, 'samples': 28043712, 'steps': 146060, 'loss/train': 1.2715779542922974} 08/31/2021 15:42:25 - INFO - __main__ - Step 146062: {'lr': 8.733840501705948e-07, 'samples': 28043904, 'steps': 146061, 'loss/train': 1.220359206199646} 08/31/2021 15:42:25 - INFO - __main__ - Step 146063: {'lr': 8.729409099723085e-07, 'samples': 28044096, 'steps': 146062, 'loss/train': 0.047081608325242996} 08/31/2021 15:42:27 - INFO - __main__ - Step 146064: {'lr': 8.724978820268126e-07, 'samples': 28044288, 'steps': 146063, 'loss/train': 1.2925788164138794} 08/31/2021 15:42:27 - INFO - __main__ - Step 146065: {'lr': 8.720549663343291e-07, 'samples': 28044480, 'steps': 146064, 'loss/train': 1.1410820484161377} 08/31/2021 15:42:28 - INFO - __main__ - Step 146066: {'lr': 8.716121628950802e-07, 'samples': 28044672, 'steps': 146065, 'loss/train': 1.0129390954971313} 08/31/2021 15:42:28 - INFO - __main__ - Step 146067: {'lr': 8.711694717092045e-07, 'samples': 28044864, 'steps': 146066, 'loss/train': 0.7975931763648987} 08/31/2021 15:42:28 - INFO - __main__ - Step 146068: {'lr': 8.707268927769518e-07, 'samples': 28045056, 'steps': 146067, 'loss/train': 0.36561599373817444} 08/31/2021 15:42:29 - INFO - __main__ - Step 146069: {'lr': 8.702844260984888e-07, 'samples': 28045248, 'steps': 146068, 'loss/train': 0.8323183655738831} 08/31/2021 15:42:30 - INFO - __main__ - Step 146070: {'lr': 8.698420716740652e-07, 'samples': 28045440, 'steps': 146069, 'loss/train': 0.6613779664039612} 08/31/2021 15:42:31 - INFO - __main__ - Step 146071: {'lr': 8.693998295038196e-07, 'samples': 28045632, 'steps': 146070, 'loss/train': 0.7853391170501709} 08/31/2021 15:42:31 - INFO - __main__ - Step 146072: {'lr': 8.689576995879744e-07, 'samples': 28045824, 'steps': 146071, 'loss/train': 0.706511378288269} 08/31/2021 15:42:31 - INFO - __main__ - Step 146073: {'lr': 8.685156819267515e-07, 'samples': 28046016, 'steps': 146072, 'loss/train': 0.3474108874797821} 08/31/2021 15:42:32 - INFO - __main__ - Step 146074: {'lr': 8.680737765203173e-07, 'samples': 28046208, 'steps': 146073, 'loss/train': 0.8922346830368042} 08/31/2021 15:42:33 - INFO - __main__ - Step 146075: {'lr': 8.676319833688662e-07, 'samples': 28046400, 'steps': 146074, 'loss/train': 1.4710966348648071} 08/31/2021 15:42:34 - INFO - __main__ - Step 146076: {'lr': 8.67190302472648e-07, 'samples': 28046592, 'steps': 146075, 'loss/train': 1.2481447458267212} 08/31/2021 15:42:34 - INFO - __main__ - Step 146077: {'lr': 8.667487338318292e-07, 'samples': 28046784, 'steps': 146076, 'loss/train': 1.0752851963043213} 08/31/2021 15:42:35 - INFO - __main__ - Step 146078: {'lr': 8.663072774465763e-07, 'samples': 28046976, 'steps': 146077, 'loss/train': 1.2081942558288574} 08/31/2021 15:42:35 - INFO - __main__ - Step 146079: {'lr': 8.658659333171392e-07, 'samples': 28047168, 'steps': 146078, 'loss/train': 0.3024600148200989} 08/31/2021 15:42:37 - INFO - __main__ - Step 146080: {'lr': 8.654247014437122e-07, 'samples': 28047360, 'steps': 146079, 'loss/train': 1.4166333675384521} 08/31/2021 15:42:37 - INFO - __main__ - Step 146081: {'lr': 8.649835818264617e-07, 'samples': 28047552, 'steps': 146080, 'loss/train': 0.6766840815544128} 08/31/2021 15:42:37 - INFO - __main__ - Step 146082: {'lr': 8.645425744656376e-07, 'samples': 28047744, 'steps': 146081, 'loss/train': 1.0065650939941406} 08/31/2021 15:42:38 - INFO - __main__ - Step 146083: {'lr': 8.641016793613787e-07, 'samples': 28047936, 'steps': 146082, 'loss/train': 0.5996636152267456} 08/31/2021 15:42:38 - INFO - __main__ - Step 146084: {'lr': 8.63660896513907e-07, 'samples': 28048128, 'steps': 146083, 'loss/train': 1.6891721487045288} 08/31/2021 15:42:40 - INFO - __main__ - Step 146085: {'lr': 8.632202259234445e-07, 'samples': 28048320, 'steps': 146084, 'loss/train': 1.6775857210159302} 08/31/2021 15:42:40 - INFO - __main__ - Step 146086: {'lr': 8.627796675901578e-07, 'samples': 28048512, 'steps': 146085, 'loss/train': 0.11666492372751236} 08/31/2021 15:42:40 - INFO - __main__ - Step 146087: {'lr': 8.623392215142689e-07, 'samples': 28048704, 'steps': 146086, 'loss/train': 0.708040177822113} 08/31/2021 15:42:41 - INFO - __main__ - Step 146088: {'lr': 8.618988876959443e-07, 'samples': 28048896, 'steps': 146087, 'loss/train': 1.3026052713394165} 08/31/2021 15:42:41 - INFO - __main__ - Step 146089: {'lr': 8.614586661354063e-07, 'samples': 28049088, 'steps': 146088, 'loss/train': 1.0242050886154175} 08/31/2021 15:42:42 - INFO - __main__ - Step 146090: {'lr': 8.610185568328766e-07, 'samples': 28049280, 'steps': 146089, 'loss/train': 0.10882702469825745} 08/31/2021 15:42:43 - INFO - __main__ - Step 146091: {'lr': 8.605785597884941e-07, 'samples': 28049472, 'steps': 146090, 'loss/train': 0.3634350597858429} 08/31/2021 15:42:43 - INFO - __main__ - Step 146092: {'lr': 8.601386750025086e-07, 'samples': 28049664, 'steps': 146091, 'loss/train': 1.3407995700836182} 08/31/2021 15:42:44 - INFO - __main__ - Step 146093: {'lr': 8.596989024751145e-07, 'samples': 28049856, 'steps': 146092, 'loss/train': 1.2412946224212646} 08/31/2021 15:42:44 - INFO - __main__ - Step 146094: {'lr': 8.592592422064782e-07, 'samples': 28050048, 'steps': 146093, 'loss/train': 0.03768062964081764} 08/31/2021 15:42:46 - INFO - __main__ - Step 146095: {'lr': 8.588196941968218e-07, 'samples': 28050240, 'steps': 146094, 'loss/train': 1.4386016130447388} 08/31/2021 15:42:46 - INFO - __main__ - Step 146096: {'lr': 8.583802584463118e-07, 'samples': 28050432, 'steps': 146095, 'loss/train': 1.124129056930542} 08/31/2021 15:42:47 - INFO - __main__ - Step 146097: {'lr': 8.579409349551981e-07, 'samples': 28050624, 'steps': 146096, 'loss/train': 1.2935945987701416} 08/31/2021 15:42:47 - INFO - __main__ - Step 146098: {'lr': 8.575017237236471e-07, 'samples': 28050816, 'steps': 146097, 'loss/train': 0.4901546239852905} 08/31/2021 15:42:47 - INFO - __main__ - Step 146099: {'lr': 8.570626247518532e-07, 'samples': 28051008, 'steps': 146098, 'loss/train': 1.4142206907272339} 08/31/2021 15:42:48 - INFO - __main__ - Step 146100: {'lr': 8.566236380400383e-07, 'samples': 28051200, 'steps': 146099, 'loss/train': 1.184327244758606} 08/31/2021 15:42:49 - INFO - __main__ - Step 146101: {'lr': 8.56184763588369e-07, 'samples': 28051392, 'steps': 146100, 'loss/train': 0.8240171670913696} 08/31/2021 15:42:50 - INFO - __main__ - Step 146102: {'lr': 8.557460013970675e-07, 'samples': 28051584, 'steps': 146101, 'loss/train': 1.3338292837142944} 08/31/2021 15:42:50 - INFO - __main__ - Step 146103: {'lr': 8.553073514663279e-07, 'samples': 28051776, 'steps': 146102, 'loss/train': 0.7114743590354919} 08/31/2021 15:42:50 - INFO - __main__ - Step 146104: {'lr': 8.548688137963168e-07, 'samples': 28051968, 'steps': 146103, 'loss/train': 0.3189873993396759} 08/31/2021 15:42:51 - INFO - __main__ - Step 146105: {'lr': 8.544303883872839e-07, 'samples': 28052160, 'steps': 146104, 'loss/train': 0.32242071628570557} 08/31/2021 15:42:52 - INFO - __main__ - Step 146106: {'lr': 8.539920752393959e-07, 'samples': 28052352, 'steps': 146105, 'loss/train': 1.584821105003357} 08/31/2021 15:42:53 - INFO - __main__ - Step 146107: {'lr': 8.535538743528471e-07, 'samples': 28052544, 'steps': 146106, 'loss/train': 0.8348439335823059} 08/31/2021 15:42:53 - INFO - __main__ - Step 146108: {'lr': 8.531157857278315e-07, 'samples': 28052736, 'steps': 146107, 'loss/train': 0.8858653903007507} 08/31/2021 15:42:53 - INFO - __main__ - Step 146109: {'lr': 8.526778093645715e-07, 'samples': 28052928, 'steps': 146108, 'loss/train': 1.4666250944137573} 08/31/2021 15:42:54 - INFO - __main__ - Step 146110: {'lr': 8.522399452632613e-07, 'samples': 28053120, 'steps': 146109, 'loss/train': 0.5119116306304932} 08/31/2021 15:42:55 - INFO - __main__ - Step 146111: {'lr': 8.518021934240672e-07, 'samples': 28053312, 'steps': 146110, 'loss/train': 0.9996175169944763} 08/31/2021 15:42:56 - INFO - __main__ - Step 146112: {'lr': 8.513645538472114e-07, 'samples': 28053504, 'steps': 146111, 'loss/train': 1.3898886442184448} 08/31/2021 15:42:56 - INFO - __main__ - Step 146113: {'lr': 8.509270265328883e-07, 'samples': 28053696, 'steps': 146112, 'loss/train': 1.4534543752670288} 08/31/2021 15:42:56 - INFO - __main__ - Step 146114: {'lr': 8.504896114812921e-07, 'samples': 28053888, 'steps': 146113, 'loss/train': 1.2475563287734985} 08/31/2021 15:42:57 - INFO - __main__ - Step 146115: {'lr': 8.500523086926171e-07, 'samples': 28054080, 'steps': 146114, 'loss/train': 0.7903081178665161} 08/31/2021 15:42:58 - INFO - __main__ - Step 146116: {'lr': 8.496151181670853e-07, 'samples': 28054272, 'steps': 146115, 'loss/train': 1.3924440145492554} 08/31/2021 15:42:59 - INFO - __main__ - Step 146117: {'lr': 8.491780399048354e-07, 'samples': 28054464, 'steps': 146116, 'loss/train': 1.5478239059448242} 08/31/2021 15:42:59 - INFO - __main__ - Step 146118: {'lr': 8.487410739061175e-07, 'samples': 28054656, 'steps': 146117, 'loss/train': 0.11042194813489914} 08/31/2021 15:42:59 - INFO - __main__ - Step 146119: {'lr': 8.483042201711255e-07, 'samples': 28054848, 'steps': 146118, 'loss/train': 1.5065069198608398} 08/31/2021 15:43:00 - INFO - __main__ - Step 146120: {'lr': 8.478674787000262e-07, 'samples': 28055040, 'steps': 146119, 'loss/train': 0.9966450333595276} 08/31/2021 15:43:02 - INFO - __main__ - Step 146121: {'lr': 8.474308494930416e-07, 'samples': 28055232, 'steps': 146120, 'loss/train': 0.04240383580327034} 08/31/2021 15:43:03 - INFO - __main__ - Step 146122: {'lr': 8.46994332550366e-07, 'samples': 28055424, 'steps': 146121, 'loss/train': 1.6142724752426147} 08/31/2021 15:43:03 - INFO - __main__ - Step 146123: {'lr': 8.465579278721658e-07, 'samples': 28055616, 'steps': 146122, 'loss/train': 0.11305395513772964} 08/31/2021 15:43:03 - INFO - __main__ - Step 146124: {'lr': 8.46121635458691e-07, 'samples': 28055808, 'steps': 146123, 'loss/train': 0.052099235355854034} 08/31/2021 15:43:04 - INFO - __main__ - Step 146125: {'lr': 8.456854553101078e-07, 'samples': 28056000, 'steps': 146124, 'loss/train': 1.941589593887329} 08/31/2021 15:43:05 - INFO - __main__ - Step 146126: {'lr': 8.45249387426611e-07, 'samples': 28056192, 'steps': 146125, 'loss/train': 0.7739947438240051} 08/31/2021 15:43:06 - INFO - __main__ - Step 146127: {'lr': 8.448134318083667e-07, 'samples': 28056384, 'steps': 146126, 'loss/train': 1.1218541860580444} 08/31/2021 15:43:06 - INFO - __main__ - Step 146128: {'lr': 8.443775884556526e-07, 'samples': 28056576, 'steps': 146127, 'loss/train': 0.5268375873565674} 08/31/2021 15:43:06 - INFO - __main__ - Step 146129: {'lr': 8.439418573685798e-07, 'samples': 28056768, 'steps': 146128, 'loss/train': 1.041263461112976} 08/31/2021 15:43:07 - INFO - __main__ - Step 146130: {'lr': 8.435062385473979e-07, 'samples': 28056960, 'steps': 146129, 'loss/train': 0.7829344272613525} 08/31/2021 15:43:08 - INFO - __main__ - Step 146131: {'lr': 8.430707319923015e-07, 'samples': 28057152, 'steps': 146130, 'loss/train': 1.594598650932312} 08/31/2021 15:43:09 - INFO - __main__ - Step 146132: {'lr': 8.426353377034568e-07, 'samples': 28057344, 'steps': 146131, 'loss/train': 0.9247457385063171} 08/31/2021 15:43:09 - INFO - __main__ - Step 146133: {'lr': 8.422000556810583e-07, 'samples': 28057536, 'steps': 146132, 'loss/train': 0.5704241991043091} 08/31/2021 15:43:09 - INFO - __main__ - Step 146134: {'lr': 8.417648859253557e-07, 'samples': 28057728, 'steps': 146133, 'loss/train': 1.4445825815200806} 08/31/2021 15:43:10 - INFO - __main__ - Step 146135: {'lr': 8.413298284364878e-07, 'samples': 28057920, 'steps': 146134, 'loss/train': 0.6750638484954834} 08/31/2021 15:43:12 - INFO - __main__ - Step 146136: {'lr': 8.408948832146767e-07, 'samples': 28058112, 'steps': 146135, 'loss/train': 0.4506920576095581} 08/31/2021 15:43:12 - INFO - __main__ - Step 146137: {'lr': 8.404600502601167e-07, 'samples': 28058304, 'steps': 146136, 'loss/train': 1.0581343173980713} 08/31/2021 15:43:13 - INFO - __main__ - Step 146138: {'lr': 8.40025329573002e-07, 'samples': 28058496, 'steps': 146137, 'loss/train': 1.415162205696106} 08/31/2021 15:43:13 - INFO - __main__ - Step 146139: {'lr': 8.395907211534992e-07, 'samples': 28058688, 'steps': 146138, 'loss/train': 0.014929905533790588} 08/31/2021 15:43:13 - INFO - __main__ - Step 146140: {'lr': 8.39156225001858e-07, 'samples': 28058880, 'steps': 146139, 'loss/train': 0.10884824395179749} 08/31/2021 15:43:14 - INFO - __main__ - Step 146141: {'lr': 8.387218411182451e-07, 'samples': 28059072, 'steps': 146140, 'loss/train': 0.061563640832901} 08/31/2021 15:43:15 - INFO - __main__ - Step 146142: {'lr': 8.382875695028547e-07, 'samples': 28059264, 'steps': 146141, 'loss/train': 0.7700304388999939} 08/31/2021 15:43:16 - INFO - __main__ - Step 146143: {'lr': 8.378534101559087e-07, 'samples': 28059456, 'steps': 146142, 'loss/train': 0.8966755867004395} 08/31/2021 15:43:16 - INFO - __main__ - Step 146144: {'lr': 8.374193630775461e-07, 'samples': 28059648, 'steps': 146143, 'loss/train': 1.7276393175125122} 08/31/2021 15:43:17 - INFO - __main__ - Step 146145: {'lr': 8.369854282680168e-07, 'samples': 28059840, 'steps': 146144, 'loss/train': 1.117967128753662} 08/31/2021 15:43:17 - INFO - __main__ - Step 146146: {'lr': 8.365516057274869e-07, 'samples': 28060032, 'steps': 146145, 'loss/train': 1.7143436670303345} 08/31/2021 15:43:17 - INFO - __main__ - Step 146147: {'lr': 8.361178954561787e-07, 'samples': 28060224, 'steps': 146146, 'loss/train': 1.1487674713134766} 08/31/2021 15:43:19 - INFO - __main__ - Step 146148: {'lr': 8.356842974542589e-07, 'samples': 28060416, 'steps': 146147, 'loss/train': 0.20913763344287872} 08/31/2021 15:43:19 - INFO - __main__ - Step 146149: {'lr': 8.352508117219493e-07, 'samples': 28060608, 'steps': 146148, 'loss/train': 1.2158186435699463} 08/31/2021 15:43:20 - INFO - __main__ - Step 146150: {'lr': 8.348174382594165e-07, 'samples': 28060800, 'steps': 146149, 'loss/train': 0.6283102631568909} 08/31/2021 15:43:20 - INFO - __main__ - Step 146151: {'lr': 8.343841770668826e-07, 'samples': 28060992, 'steps': 146150, 'loss/train': 1.0216141939163208} 08/31/2021 15:43:20 - INFO - __main__ - Step 146152: {'lr': 8.33951028144514e-07, 'samples': 28061184, 'steps': 146151, 'loss/train': 0.8363977670669556} 08/31/2021 15:43:22 - INFO - __main__ - Step 146153: {'lr': 8.335179914925328e-07, 'samples': 28061376, 'steps': 146152, 'loss/train': 1.126650333404541} 08/31/2021 15:43:22 - INFO - __main__ - Step 146154: {'lr': 8.330850671111334e-07, 'samples': 28061568, 'steps': 146153, 'loss/train': 1.3588906526565552} 08/31/2021 15:43:23 - INFO - __main__ - Step 146155: {'lr': 8.326522550004823e-07, 'samples': 28061760, 'steps': 146154, 'loss/train': 1.3130946159362793} 08/31/2021 15:43:23 - INFO - __main__ - Step 146156: {'lr': 8.322195551608014e-07, 'samples': 28061952, 'steps': 146155, 'loss/train': 0.42069554328918457} 08/31/2021 15:43:24 - INFO - __main__ - Step 146157: {'lr': 8.317869675922574e-07, 'samples': 28062144, 'steps': 146156, 'loss/train': 0.8598584532737732} 08/31/2021 15:43:25 - INFO - __main__ - Step 146158: {'lr': 8.313544922951e-07, 'samples': 28062336, 'steps': 146157, 'loss/train': 0.9622029662132263} 08/31/2021 15:43:26 - INFO - __main__ - Step 146159: {'lr': 8.309221292694679e-07, 'samples': 28062528, 'steps': 146158, 'loss/train': 0.38872772455215454} 08/31/2021 15:43:26 - INFO - __main__ - Step 146160: {'lr': 8.304898785155834e-07, 'samples': 28062720, 'steps': 146159, 'loss/train': 1.2871931791305542} 08/31/2021 15:43:26 - INFO - __main__ - Step 146161: {'lr': 8.300577400336407e-07, 'samples': 28062912, 'steps': 146160, 'loss/train': 1.1592057943344116} 08/31/2021 15:43:27 - INFO - __main__ - Step 146162: {'lr': 8.296257138238061e-07, 'samples': 28063104, 'steps': 146161, 'loss/train': 0.8937740921974182} 08/31/2021 15:43:28 - INFO - __main__ - Step 146163: {'lr': 8.291937998863297e-07, 'samples': 28063296, 'steps': 146162, 'loss/train': 0.7852945327758789} 08/31/2021 15:43:29 - INFO - __main__ - Step 146164: {'lr': 8.287619982213502e-07, 'samples': 28063488, 'steps': 146163, 'loss/train': 1.2492135763168335} 08/31/2021 15:43:29 - INFO - __main__ - Step 146165: {'lr': 8.283303088290894e-07, 'samples': 28063680, 'steps': 146164, 'loss/train': 0.020742928609251976} 08/31/2021 15:43:29 - INFO - __main__ - Step 146166: {'lr': 8.278987317097419e-07, 'samples': 28063872, 'steps': 146165, 'loss/train': 0.8295261859893799} 08/31/2021 15:43:30 - INFO - __main__ - Step 146167: {'lr': 8.274672668635019e-07, 'samples': 28064064, 'steps': 146166, 'loss/train': 1.2065012454986572} 08/31/2021 15:43:30 - INFO - __main__ - Step 146168: {'lr': 8.270359142905637e-07, 'samples': 28064256, 'steps': 146167, 'loss/train': 0.946008026599884} 08/31/2021 15:43:31 - INFO - __main__ - Step 146169: {'lr': 8.266046739910937e-07, 'samples': 28064448, 'steps': 146168, 'loss/train': 1.135968565940857} 08/31/2021 15:43:32 - INFO - __main__ - Step 146170: {'lr': 8.261735459653418e-07, 'samples': 28064640, 'steps': 146169, 'loss/train': 1.211598515510559} 08/31/2021 15:43:32 - INFO - __main__ - Step 146171: {'lr': 8.257425302134469e-07, 'samples': 28064832, 'steps': 146170, 'loss/train': 0.6686730980873108} 08/31/2021 15:43:33 - INFO - __main__ - Step 146172: {'lr': 8.253116267356308e-07, 'samples': 28065024, 'steps': 146171, 'loss/train': 1.3085037469863892} 08/31/2021 15:43:33 - INFO - __main__ - Step 146173: {'lr': 8.248808355320881e-07, 'samples': 28065216, 'steps': 146172, 'loss/train': 1.4419338703155518} 08/31/2021 15:43:35 - INFO - __main__ - Step 146174: {'lr': 8.244501566030127e-07, 'samples': 28065408, 'steps': 146173, 'loss/train': 1.1371363401412964} 08/31/2021 15:43:35 - INFO - __main__ - Step 146175: {'lr': 8.240195899485992e-07, 'samples': 28065600, 'steps': 146174, 'loss/train': 1.201791763305664} 08/31/2021 15:43:36 - INFO - __main__ - Step 146176: {'lr': 8.235891355690417e-07, 'samples': 28065792, 'steps': 146175, 'loss/train': 1.2109675407409668} 08/31/2021 15:43:36 - INFO - __main__ - Step 146177: {'lr': 8.231587934645069e-07, 'samples': 28065984, 'steps': 146176, 'loss/train': 1.2010010480880737} 08/31/2021 15:43:36 - INFO - __main__ - Step 146178: {'lr': 8.227285636352444e-07, 'samples': 28066176, 'steps': 146177, 'loss/train': 0.8127798438072205} 08/31/2021 15:43:38 - INFO - __main__ - Step 146179: {'lr': 8.222984460813931e-07, 'samples': 28066368, 'steps': 146178, 'loss/train': 1.5905488729476929} 08/31/2021 15:43:38 - INFO - __main__ - Step 146180: {'lr': 8.218684408031752e-07, 'samples': 28066560, 'steps': 146179, 'loss/train': 1.4292622804641724} 08/31/2021 15:43:39 - INFO - __main__ - Step 146181: {'lr': 8.214385478007568e-07, 'samples': 28066752, 'steps': 146180, 'loss/train': 3.571485757827759} 08/31/2021 15:43:39 - INFO - __main__ - Step 146182: {'lr': 8.210087670743882e-07, 'samples': 28066944, 'steps': 146181, 'loss/train': 1.8450127840042114} 08/31/2021 15:43:39 - INFO - __main__ - Step 146183: {'lr': 8.205790986242079e-07, 'samples': 28067136, 'steps': 146182, 'loss/train': 0.6292204856872559} 08/31/2021 15:43:41 - INFO - __main__ - Step 146184: {'lr': 8.20149542450438e-07, 'samples': 28067328, 'steps': 146183, 'loss/train': 0.9434575438499451} 08/31/2021 15:43:41 - INFO - __main__ - Step 146185: {'lr': 8.197200985532449e-07, 'samples': 28067520, 'steps': 146184, 'loss/train': 1.6338448524475098} 08/31/2021 15:43:42 - INFO - __main__ - Step 146186: {'lr': 8.192907669328508e-07, 'samples': 28067712, 'steps': 146185, 'loss/train': 1.10805344581604} 08/31/2021 15:43:42 - INFO - __main__ - Step 146187: {'lr': 8.188615475894501e-07, 'samples': 28067904, 'steps': 146186, 'loss/train': 1.3049898147583008} 08/31/2021 15:43:42 - INFO - __main__ - Step 146188: {'lr': 8.184324405232091e-07, 'samples': 28068096, 'steps': 146187, 'loss/train': 0.4034380614757538} 08/31/2021 15:43:44 - INFO - __main__ - Step 146189: {'lr': 8.1800344573435e-07, 'samples': 28068288, 'steps': 146188, 'loss/train': 1.4420133829116821} 08/31/2021 15:43:44 - INFO - __main__ - Step 146190: {'lr': 8.175745632230669e-07, 'samples': 28068480, 'steps': 146189, 'loss/train': 0.9851023554801941} 08/31/2021 15:43:45 - INFO - __main__ - Step 146191: {'lr': 8.171457929895265e-07, 'samples': 28068672, 'steps': 146190, 'loss/train': 0.5789003372192383} 08/31/2021 15:43:45 - INFO - __main__ - Step 146192: {'lr': 8.167171350339231e-07, 'samples': 28068864, 'steps': 146191, 'loss/train': 1.0269240140914917} 08/31/2021 15:43:45 - INFO - __main__ - Step 146193: {'lr': 8.162885893564786e-07, 'samples': 28069056, 'steps': 146192, 'loss/train': 0.9199618101119995} 08/31/2021 15:43:46 - INFO - __main__ - Step 146194: {'lr': 8.158601559573597e-07, 'samples': 28069248, 'steps': 146193, 'loss/train': 0.910475492477417} 08/31/2021 15:43:47 - INFO - __main__ - Step 146195: {'lr': 8.154318348367607e-07, 'samples': 28069440, 'steps': 146194, 'loss/train': 1.3893013000488281} 08/31/2021 15:43:48 - INFO - __main__ - Step 146196: {'lr': 8.150036259949035e-07, 'samples': 28069632, 'steps': 146195, 'loss/train': 1.0456326007843018} 08/31/2021 15:43:48 - INFO - __main__ - Step 146197: {'lr': 8.145755294319268e-07, 'samples': 28069824, 'steps': 146196, 'loss/train': 0.023774610832333565} 08/31/2021 15:43:48 - INFO - __main__ - Step 146198: {'lr': 8.141475451480807e-07, 'samples': 28070016, 'steps': 146197, 'loss/train': 1.0555264949798584} 08/31/2021 15:43:49 - INFO - __main__ - Step 146199: {'lr': 8.137196731435315e-07, 'samples': 28070208, 'steps': 146198, 'loss/train': 1.1378535032272339} 08/31/2021 15:43:50 - INFO - __main__ - Step 146200: {'lr': 8.132919134184736e-07, 'samples': 28070400, 'steps': 146199, 'loss/train': 1.1213730573654175} 08/31/2021 15:43:51 - INFO - __main__ - Step 146201: {'lr': 8.128642659731289e-07, 'samples': 28070592, 'steps': 146200, 'loss/train': 1.0297484397888184} 08/31/2021 15:43:51 - INFO - __main__ - Step 146202: {'lr': 8.124367308076364e-07, 'samples': 28070784, 'steps': 146201, 'loss/train': 1.1258360147476196} 08/31/2021 15:43:51 - INFO - __main__ - Step 146203: {'lr': 8.120093079222179e-07, 'samples': 28070976, 'steps': 146202, 'loss/train': 1.1647390127182007} 08/31/2021 15:43:52 - INFO - __main__ - Step 146204: {'lr': 8.11581997317068e-07, 'samples': 28071168, 'steps': 146203, 'loss/train': 0.5049115419387817} 08/31/2021 15:43:53 - INFO - __main__ - Step 146205: {'lr': 8.111547989923529e-07, 'samples': 28071360, 'steps': 146204, 'loss/train': 1.7043776512145996} 08/31/2021 15:43:54 - INFO - __main__ - Step 146206: {'lr': 8.107277129482949e-07, 'samples': 28071552, 'steps': 146205, 'loss/train': 0.9487787485122681} 08/31/2021 15:43:54 - INFO - __main__ - Step 146207: {'lr': 8.103007391850881e-07, 'samples': 28071744, 'steps': 146206, 'loss/train': 1.2094420194625854} 08/31/2021 15:43:55 - INFO - __main__ - Step 146208: {'lr': 8.098738777028991e-07, 'samples': 28071936, 'steps': 146207, 'loss/train': 1.1784098148345947} 08/31/2021 15:43:55 - INFO - __main__ - Step 146209: {'lr': 8.0944712850195e-07, 'samples': 28072128, 'steps': 146208, 'loss/train': 0.8992607593536377} 08/31/2021 15:43:57 - INFO - __main__ - Step 146210: {'lr': 8.090204915824351e-07, 'samples': 28072320, 'steps': 146209, 'loss/train': 1.3437039852142334} 08/31/2021 15:43:57 - INFO - __main__ - Step 146211: {'lr': 8.085939669444931e-07, 'samples': 28072512, 'steps': 146210, 'loss/train': 1.1817455291748047} 08/31/2021 15:43:57 - INFO - __main__ - Step 146212: {'lr': 8.081675545883737e-07, 'samples': 28072704, 'steps': 146211, 'loss/train': 1.3671557903289795} 08/31/2021 15:43:58 - INFO - __main__ - Step 146213: {'lr': 8.077412545142437e-07, 'samples': 28072896, 'steps': 146212, 'loss/train': 1.0467615127563477} 08/31/2021 15:43:58 - INFO - __main__ - Step 146214: {'lr': 8.073150667222973e-07, 'samples': 28073088, 'steps': 146213, 'loss/train': 0.41841545701026917} 08/31/2021 15:43:58 - INFO - __main__ - Step 146215: {'lr': 8.068889912127287e-07, 'samples': 28073280, 'steps': 146214, 'loss/train': 0.41710156202316284} 08/31/2021 15:44:00 - INFO - __main__ - Step 146216: {'lr': 8.064630279857598e-07, 'samples': 28073472, 'steps': 146215, 'loss/train': 1.0477179288864136} 08/31/2021 15:44:00 - INFO - __main__ - Step 146217: {'lr': 8.060371770415298e-07, 'samples': 28073664, 'steps': 146216, 'loss/train': 1.0109267234802246} 08/31/2021 15:44:01 - INFO - __main__ - Step 146218: {'lr': 8.056114383802605e-07, 'samples': 28073856, 'steps': 146217, 'loss/train': 0.7940033674240112} 08/31/2021 15:44:01 - INFO - __main__ - Step 146219: {'lr': 8.051858120021182e-07, 'samples': 28074048, 'steps': 146218, 'loss/train': 1.2815220355987549} 08/31/2021 15:44:01 - INFO - __main__ - Step 146220: {'lr': 8.047602979073254e-07, 'samples': 28074240, 'steps': 146219, 'loss/train': 0.8556249141693115} 08/31/2021 15:44:03 - INFO - __main__ - Step 146221: {'lr': 8.043348960960761e-07, 'samples': 28074432, 'steps': 146220, 'loss/train': 1.0306795835494995} 08/31/2021 15:44:03 - INFO - __main__ - Step 146222: {'lr': 8.039096065685369e-07, 'samples': 28074624, 'steps': 146221, 'loss/train': 0.975150465965271} 08/31/2021 15:44:04 - INFO - __main__ - Step 146223: {'lr': 8.034844293249022e-07, 'samples': 28074816, 'steps': 146222, 'loss/train': 1.3470432758331299} 08/31/2021 15:44:04 - INFO - __main__ - Step 146224: {'lr': 8.03059364365366e-07, 'samples': 28075008, 'steps': 146223, 'loss/train': 0.7520530223846436} 08/31/2021 15:44:04 - INFO - __main__ - Step 146225: {'lr': 8.026344116901507e-07, 'samples': 28075200, 'steps': 146224, 'loss/train': 0.9497421383857727} 08/31/2021 15:44:07 - INFO - __main__ - Step 146226: {'lr': 8.022095712994227e-07, 'samples': 28075392, 'steps': 146225, 'loss/train': 0.7838554978370667} 08/31/2021 15:44:07 - INFO - __main__ - Step 146227: {'lr': 8.017848431933484e-07, 'samples': 28075584, 'steps': 146226, 'loss/train': 1.349069356918335} 08/31/2021 15:44:08 - INFO - __main__ - Step 146228: {'lr': 8.013602273721499e-07, 'samples': 28075776, 'steps': 146227, 'loss/train': 1.3634662628173828} 08/31/2021 15:44:08 - INFO - __main__ - Step 146229: {'lr': 8.009357238360215e-07, 'samples': 28075968, 'steps': 146228, 'loss/train': 0.5465161204338074} 08/31/2021 15:44:08 - INFO - __main__ - Step 146230: {'lr': 8.005113325851576e-07, 'samples': 28076160, 'steps': 146229, 'loss/train': 0.8988214135169983} 08/31/2021 15:44:09 - INFO - __main__ - Step 146231: {'lr': 8.000870536197247e-07, 'samples': 28076352, 'steps': 146230, 'loss/train': 1.540000557899475} 08/31/2021 15:44:10 - INFO - __main__ - Step 146232: {'lr': 7.996628869399447e-07, 'samples': 28076544, 'steps': 146231, 'loss/train': 0.6639962196350098} 08/31/2021 15:44:11 - INFO - __main__ - Step 146233: {'lr': 7.992388325459565e-07, 'samples': 28076736, 'steps': 146232, 'loss/train': 0.8064926862716675} 08/31/2021 15:44:11 - INFO - __main__ - Step 146234: {'lr': 7.988148904380099e-07, 'samples': 28076928, 'steps': 146233, 'loss/train': 0.6987605094909668} 08/31/2021 15:44:12 - INFO - __main__ - Step 146235: {'lr': 7.983910606162714e-07, 'samples': 28077120, 'steps': 146234, 'loss/train': 1.3223079442977905} 08/31/2021 15:44:12 - INFO - __main__ - Step 146236: {'lr': 7.979673430809353e-07, 'samples': 28077312, 'steps': 146235, 'loss/train': 0.5568172931671143} 08/31/2021 15:44:12 - INFO - __main__ - Step 146237: {'lr': 7.975437378321682e-07, 'samples': 28077504, 'steps': 146236, 'loss/train': 1.132835030555725} 08/31/2021 15:44:14 - INFO - __main__ - Step 146238: {'lr': 7.971202448702198e-07, 'samples': 28077696, 'steps': 146237, 'loss/train': 0.8536075949668884} 08/31/2021 15:44:14 - INFO - __main__ - Step 146239: {'lr': 7.966968641952011e-07, 'samples': 28077888, 'steps': 146238, 'loss/train': 0.73796147108078} 08/31/2021 15:44:15 - INFO - __main__ - Step 146240: {'lr': 7.962735958073619e-07, 'samples': 28078080, 'steps': 146239, 'loss/train': 0.9743026494979858} 08/31/2021 15:44:15 - INFO - __main__ - Step 146241: {'lr': 7.958504397068966e-07, 'samples': 28078272, 'steps': 146240, 'loss/train': 1.1964526176452637} 08/31/2021 15:44:15 - INFO - __main__ - Step 146242: {'lr': 7.95427395893944e-07, 'samples': 28078464, 'steps': 146241, 'loss/train': 1.227726697921753} 08/31/2021 15:44:17 - INFO - __main__ - Step 146243: {'lr': 7.950044643687537e-07, 'samples': 28078656, 'steps': 146242, 'loss/train': 1.2017731666564941} 08/31/2021 15:44:17 - INFO - __main__ - Step 146244: {'lr': 7.945816451314647e-07, 'samples': 28078848, 'steps': 146243, 'loss/train': 1.2353684902191162} 08/31/2021 15:44:17 - INFO - __main__ - Step 146245: {'lr': 7.941589381823267e-07, 'samples': 28079040, 'steps': 146244, 'loss/train': 1.6112985610961914} 08/31/2021 15:44:18 - INFO - __main__ - Step 146246: {'lr': 7.937363435214507e-07, 'samples': 28079232, 'steps': 146245, 'loss/train': 0.6965735554695129} 08/31/2021 15:44:18 - INFO - __main__ - Step 146247: {'lr': 7.933138611491142e-07, 'samples': 28079424, 'steps': 146246, 'loss/train': 1.2720730304718018} 08/31/2021 15:44:20 - INFO - __main__ - Step 146248: {'lr': 7.928914910654283e-07, 'samples': 28079616, 'steps': 146247, 'loss/train': 0.9181706309318542} 08/31/2021 15:44:20 - INFO - __main__ - Step 146249: {'lr': 7.924692332706429e-07, 'samples': 28079808, 'steps': 146248, 'loss/train': 1.1369500160217285} 08/31/2021 15:44:20 - INFO - __main__ - Step 146250: {'lr': 7.920470877649243e-07, 'samples': 28080000, 'steps': 146249, 'loss/train': 0.9653664231300354} 08/31/2021 15:44:21 - INFO - __main__ - Step 146251: {'lr': 7.916250545484393e-07, 'samples': 28080192, 'steps': 146250, 'loss/train': 1.5476361513137817} 08/31/2021 15:44:21 - INFO - __main__ - Step 146252: {'lr': 7.912031336214376e-07, 'samples': 28080384, 'steps': 146251, 'loss/train': 1.2260541915893555} 08/31/2021 15:44:23 - INFO - __main__ - Step 146253: {'lr': 7.907813249840301e-07, 'samples': 28080576, 'steps': 146252, 'loss/train': 0.11424611508846283} 08/31/2021 15:44:23 - INFO - __main__ - Step 146254: {'lr': 7.903596286364945e-07, 'samples': 28080768, 'steps': 146253, 'loss/train': 0.8167659640312195} 08/31/2021 15:44:24 - INFO - __main__ - Step 146255: {'lr': 7.899380445789695e-07, 'samples': 28080960, 'steps': 146254, 'loss/train': 0.8596407175064087} 08/31/2021 15:44:24 - INFO - __main__ - Step 146256: {'lr': 7.895165728116216e-07, 'samples': 28081152, 'steps': 146255, 'loss/train': 0.9679020047187805} 08/31/2021 15:44:24 - INFO - __main__ - Step 146257: {'lr': 7.890952133347007e-07, 'samples': 28081344, 'steps': 146256, 'loss/train': 1.1221528053283691} 08/31/2021 15:44:26 - INFO - __main__ - Step 146258: {'lr': 7.886739661483732e-07, 'samples': 28081536, 'steps': 146257, 'loss/train': 0.7075342535972595} 08/31/2021 15:44:26 - INFO - __main__ - Step 146259: {'lr': 7.882528312528059e-07, 'samples': 28081728, 'steps': 146258, 'loss/train': 1.1915034055709839} 08/31/2021 15:44:27 - INFO - __main__ - Step 146260: {'lr': 7.878318086482205e-07, 'samples': 28081920, 'steps': 146259, 'loss/train': 1.8289247751235962} 08/31/2021 15:44:27 - INFO - __main__ - Step 146261: {'lr': 7.874108983347839e-07, 'samples': 28082112, 'steps': 146260, 'loss/train': 0.028403175994753838} 08/31/2021 15:44:27 - INFO - __main__ - Step 146262: {'lr': 7.869901003126901e-07, 'samples': 28082304, 'steps': 146261, 'loss/train': 1.3807194232940674} 08/31/2021 15:44:29 - INFO - __main__ - Step 146263: {'lr': 7.865694145821334e-07, 'samples': 28082496, 'steps': 146262, 'loss/train': 0.595659077167511} 08/31/2021 15:44:29 - INFO - __main__ - Step 146264: {'lr': 7.861488411433082e-07, 'samples': 28082688, 'steps': 146263, 'loss/train': 1.4800832271575928} 08/31/2021 15:44:30 - INFO - __main__ - Step 146265: {'lr': 7.857283799964088e-07, 'samples': 28082880, 'steps': 146264, 'loss/train': 1.2911345958709717} 08/31/2021 15:44:30 - INFO - __main__ - Step 146266: {'lr': 7.853080311416016e-07, 'samples': 28083072, 'steps': 146265, 'loss/train': 1.4266008138656616} 08/31/2021 15:44:30 - INFO - __main__ - Step 146267: {'lr': 7.848877945790811e-07, 'samples': 28083264, 'steps': 146266, 'loss/train': 0.4053651988506317} 08/31/2021 15:44:31 - INFO - __main__ - Step 146268: {'lr': 7.844676703090692e-07, 'samples': 28083456, 'steps': 146267, 'loss/train': 1.4483857154846191} 08/31/2021 15:44:32 - INFO - __main__ - Step 146269: {'lr': 7.840476583317047e-07, 'samples': 28083648, 'steps': 146268, 'loss/train': 1.5123450756072998} 08/31/2021 15:44:33 - INFO - __main__ - Step 146270: {'lr': 7.836277586472096e-07, 'samples': 28083840, 'steps': 146269, 'loss/train': 1.472276210784912} 08/31/2021 15:44:33 - INFO - __main__ - Step 146271: {'lr': 7.832079712557782e-07, 'samples': 28084032, 'steps': 146270, 'loss/train': 1.1244004964828491} 08/31/2021 15:44:34 - INFO - __main__ - Step 146272: {'lr': 7.827882961575772e-07, 'samples': 28084224, 'steps': 146271, 'loss/train': 0.8806130290031433} 08/31/2021 15:44:34 - INFO - __main__ - Step 146273: {'lr': 7.823687333528007e-07, 'samples': 28084416, 'steps': 146272, 'loss/train': 1.4358924627304077} 08/31/2021 15:44:35 - INFO - __main__ - Step 146274: {'lr': 7.819492828416707e-07, 'samples': 28084608, 'steps': 146273, 'loss/train': 0.8457197546958923} 08/31/2021 15:44:36 - INFO - __main__ - Step 146275: {'lr': 7.815299446243262e-07, 'samples': 28084800, 'steps': 146274, 'loss/train': 0.5789939761161804} 08/31/2021 15:44:36 - INFO - __main__ - Step 146276: {'lr': 7.811107187009892e-07, 'samples': 28084992, 'steps': 146275, 'loss/train': 0.9651727676391602} 08/31/2021 15:44:37 - INFO - __main__ - Step 146277: {'lr': 7.80691605071826e-07, 'samples': 28085184, 'steps': 146276, 'loss/train': 1.1674981117248535} 08/31/2021 15:44:37 - INFO - __main__ - Step 146278: {'lr': 7.802726037370311e-07, 'samples': 28085376, 'steps': 146277, 'loss/train': 1.2100366353988647} 08/31/2021 15:44:39 - INFO - __main__ - Step 146279: {'lr': 7.798537146967988e-07, 'samples': 28085568, 'steps': 146278, 'loss/train': 1.0825897455215454} 08/31/2021 15:44:39 - INFO - __main__ - Step 146280: {'lr': 7.79434937951351e-07, 'samples': 28085760, 'steps': 146279, 'loss/train': 1.261021614074707} 08/31/2021 15:44:40 - INFO - __main__ - Step 146281: {'lr': 7.790162735008266e-07, 'samples': 28085952, 'steps': 146280, 'loss/train': 1.0157456398010254} 08/31/2021 15:44:40 - INFO - __main__ - Step 146282: {'lr': 7.785977213454199e-07, 'samples': 28086144, 'steps': 146281, 'loss/train': 1.4863777160644531} 08/31/2021 15:44:40 - INFO - __main__ - Step 146283: {'lr': 7.78179281485325e-07, 'samples': 28086336, 'steps': 146282, 'loss/train': 1.2476369142532349} 08/31/2021 15:44:41 - INFO - __main__ - Step 146284: {'lr': 7.777609539207642e-07, 'samples': 28086528, 'steps': 146283, 'loss/train': 1.8375012874603271} 08/31/2021 15:44:43 - INFO - __main__ - Step 146285: {'lr': 7.773427386519039e-07, 'samples': 28086720, 'steps': 146284, 'loss/train': 1.5618793964385986} 08/31/2021 15:44:43 - INFO - __main__ - Step 146286: {'lr': 7.769246356789106e-07, 'samples': 28086912, 'steps': 146285, 'loss/train': 0.8521448373794556} 08/31/2021 15:44:43 - INFO - __main__ - Step 146287: {'lr': 7.765066450019786e-07, 'samples': 28087104, 'steps': 146286, 'loss/train': 1.4892311096191406} 08/31/2021 15:44:44 - INFO - __main__ - Step 146288: {'lr': 7.760887666213024e-07, 'samples': 28087296, 'steps': 146287, 'loss/train': 1.0992367267608643} 08/31/2021 15:44:44 - INFO - __main__ - Step 146289: {'lr': 7.756710005371037e-07, 'samples': 28087488, 'steps': 146288, 'loss/train': 1.3750238418579102} 08/31/2021 15:44:46 - INFO - __main__ - Step 146290: {'lr': 7.752533467495215e-07, 'samples': 28087680, 'steps': 146289, 'loss/train': 1.0776641368865967} 08/31/2021 15:44:46 - INFO - __main__ - Step 146291: {'lr': 7.748358052587778e-07, 'samples': 28087872, 'steps': 146290, 'loss/train': 0.9532565474510193} 08/31/2021 15:44:46 - INFO - __main__ - Step 146292: {'lr': 7.744183760650392e-07, 'samples': 28088064, 'steps': 146291, 'loss/train': 3.2793548107147217} 08/31/2021 15:44:47 - INFO - __main__ - Step 146293: {'lr': 7.740010591684998e-07, 'samples': 28088256, 'steps': 146292, 'loss/train': 1.431043028831482} 08/31/2021 15:44:47 - INFO - __main__ - Step 146294: {'lr': 7.735838545693541e-07, 'samples': 28088448, 'steps': 146293, 'loss/train': 1.1325230598449707} 08/31/2021 15:44:49 - INFO - __main__ - Step 146295: {'lr': 7.731667622677685e-07, 'samples': 28088640, 'steps': 146294, 'loss/train': 0.8988775610923767} 08/31/2021 15:44:49 - INFO - __main__ - Step 146296: {'lr': 7.727497822639651e-07, 'samples': 28088832, 'steps': 146295, 'loss/train': 0.5203791260719299} 08/31/2021 15:44:49 - INFO - __main__ - Step 146297: {'lr': 7.723329145581381e-07, 'samples': 28089024, 'steps': 146296, 'loss/train': 1.4136910438537598} 08/31/2021 15:44:50 - INFO - __main__ - Step 146298: {'lr': 7.719161591504264e-07, 'samples': 28089216, 'steps': 146297, 'loss/train': 1.0665264129638672} 08/31/2021 15:44:50 - INFO - __main__ - Step 146299: {'lr': 7.714995160410243e-07, 'samples': 28089408, 'steps': 146298, 'loss/train': 0.8690909147262573} 08/31/2021 15:44:50 - INFO - __main__ - Step 146300: {'lr': 7.710829852301815e-07, 'samples': 28089600, 'steps': 146299, 'loss/train': 0.6129075884819031} 08/31/2021 15:44:53 - INFO - __main__ - Step 146301: {'lr': 7.70666566718009e-07, 'samples': 28089792, 'steps': 146300, 'loss/train': 1.2133572101593018} 08/31/2021 15:44:53 - INFO - __main__ - Step 146302: {'lr': 7.70250260504729e-07, 'samples': 28089984, 'steps': 146301, 'loss/train': 1.904563069343567} 08/31/2021 15:44:53 - INFO - __main__ - Step 146303: {'lr': 7.698340665905356e-07, 'samples': 28090176, 'steps': 146302, 'loss/train': 1.2371246814727783} 08/31/2021 15:44:54 - INFO - __main__ - Step 146304: {'lr': 7.694179849756234e-07, 'samples': 28090368, 'steps': 146303, 'loss/train': 1.5520782470703125} 08/31/2021 15:44:54 - INFO - __main__ - Step 146305: {'lr': 7.690020156601585e-07, 'samples': 28090560, 'steps': 146304, 'loss/train': 1.4493314027786255} 08/31/2021 15:44:55 - INFO - __main__ - Step 146306: {'lr': 7.685861586443354e-07, 'samples': 28090752, 'steps': 146305, 'loss/train': 1.6038742065429688} 08/31/2021 15:44:56 - INFO - __main__ - Step 146307: {'lr': 7.681704139283207e-07, 'samples': 28090944, 'steps': 146306, 'loss/train': 0.4720715582370758} 08/31/2021 15:44:56 - INFO - __main__ - Step 146308: {'lr': 7.677547815123365e-07, 'samples': 28091136, 'steps': 146307, 'loss/train': 0.3563140630722046} 08/31/2021 15:44:57 - INFO - __main__ - Step 146309: {'lr': 7.673392613965769e-07, 'samples': 28091328, 'steps': 146308, 'loss/train': 0.7517101168632507} 08/31/2021 15:44:57 - INFO - __main__ - Step 146310: {'lr': 7.669238535811807e-07, 'samples': 28091520, 'steps': 146309, 'loss/train': 0.6790096759796143} 08/31/2021 15:44:59 - INFO - __main__ - Step 146311: {'lr': 7.6650855806637e-07, 'samples': 28091712, 'steps': 146310, 'loss/train': 1.0939804315567017} 08/31/2021 15:44:59 - INFO - __main__ - Step 146312: {'lr': 7.660933748523391e-07, 'samples': 28091904, 'steps': 146311, 'loss/train': 0.876081109046936} 08/31/2021 15:44:59 - INFO - __main__ - Step 146313: {'lr': 7.656783039392545e-07, 'samples': 28092096, 'steps': 146312, 'loss/train': 1.3336641788482666} 08/31/2021 15:45:00 - INFO - __main__ - Step 146314: {'lr': 7.652633453273106e-07, 'samples': 28092288, 'steps': 146313, 'loss/train': 0.9852471351623535} 08/31/2021 15:45:00 - INFO - __main__ - Step 146315: {'lr': 7.648484990166738e-07, 'samples': 28092480, 'steps': 146314, 'loss/train': 1.2288519144058228} 08/31/2021 15:45:01 - INFO - __main__ - Step 146316: {'lr': 7.644337650075661e-07, 'samples': 28092672, 'steps': 146315, 'loss/train': 1.1154375076293945} 08/31/2021 15:45:02 - INFO - __main__ - Step 146317: {'lr': 7.640191433001542e-07, 'samples': 28092864, 'steps': 146316, 'loss/train': 0.5179261565208435} 08/31/2021 15:45:02 - INFO - __main__ - Step 146318: {'lr': 7.636046338946323e-07, 'samples': 28093056, 'steps': 146317, 'loss/train': 1.1068198680877686} 08/31/2021 15:45:03 - INFO - __main__ - Step 146319: {'lr': 7.63190236791167e-07, 'samples': 28093248, 'steps': 146318, 'loss/train': 1.0555284023284912} 08/31/2021 15:45:03 - INFO - __main__ - Step 146320: {'lr': 7.627759519899802e-07, 'samples': 28093440, 'steps': 146319, 'loss/train': 0.907180905342102} 08/31/2021 15:45:03 - INFO - __main__ - Step 146321: {'lr': 7.623617794912385e-07, 'samples': 28093632, 'steps': 146320, 'loss/train': 0.14104902744293213} 08/31/2021 15:45:05 - INFO - __main__ - Step 146322: {'lr': 7.619477192951363e-07, 'samples': 28093824, 'steps': 146321, 'loss/train': 1.0831702947616577} 08/31/2021 15:45:05 - INFO - __main__ - Step 146323: {'lr': 7.6153377140184e-07, 'samples': 28094016, 'steps': 146322, 'loss/train': 1.4905714988708496} 08/31/2021 15:45:06 - INFO - __main__ - Step 146324: {'lr': 7.611199358115717e-07, 'samples': 28094208, 'steps': 146323, 'loss/train': 1.7438533306121826} 08/31/2021 15:45:06 - INFO - __main__ - Step 146325: {'lr': 7.607062125244702e-07, 'samples': 28094400, 'steps': 146324, 'loss/train': 0.9836022257804871} 08/31/2021 15:45:06 - INFO - __main__ - Step 146326: {'lr': 7.602926015407852e-07, 'samples': 28094592, 'steps': 146325, 'loss/train': 1.6869484186172485} 08/31/2021 15:45:08 - INFO - __main__ - Step 146327: {'lr': 7.598791028606277e-07, 'samples': 28094784, 'steps': 146326, 'loss/train': 0.7012932896614075} 08/31/2021 15:45:09 - INFO - __main__ - Step 146328: {'lr': 7.594657164842478e-07, 'samples': 28094976, 'steps': 146327, 'loss/train': 0.4349936842918396} 08/31/2021 15:45:09 - INFO - __main__ - Step 146329: {'lr': 7.590524424117839e-07, 'samples': 28095168, 'steps': 146328, 'loss/train': 1.7396280765533447} 08/31/2021 15:45:09 - INFO - __main__ - Step 146330: {'lr': 7.586392806434583e-07, 'samples': 28095360, 'steps': 146329, 'loss/train': 0.1434277892112732} 08/31/2021 15:45:10 - INFO - __main__ - Step 146331: {'lr': 7.582262311794374e-07, 'samples': 28095552, 'steps': 146330, 'loss/train': 0.10651928186416626} 08/31/2021 15:45:12 - INFO - __main__ - Step 146332: {'lr': 7.578132940199156e-07, 'samples': 28095744, 'steps': 146331, 'loss/train': 1.6836013793945312} 08/31/2021 15:45:12 - INFO - __main__ - Step 146333: {'lr': 7.574004691650871e-07, 'samples': 28095936, 'steps': 146332, 'loss/train': 0.928441047668457} 08/31/2021 15:45:12 - INFO - __main__ - Step 146334: {'lr': 7.569877566151185e-07, 'samples': 28096128, 'steps': 146333, 'loss/train': 1.5618654489517212} 08/31/2021 15:45:13 - INFO - __main__ - Step 146335: {'lr': 7.565751563702039e-07, 'samples': 28096320, 'steps': 146334, 'loss/train': 1.0174896717071533} 08/31/2021 15:45:13 - INFO - __main__ - Step 146336: {'lr': 7.561626684305378e-07, 'samples': 28096512, 'steps': 146335, 'loss/train': 1.511059284210205} 08/31/2021 15:45:15 - INFO - __main__ - Step 146337: {'lr': 7.557502927963144e-07, 'samples': 28096704, 'steps': 146336, 'loss/train': 0.12423857301473618} 08/31/2021 15:45:16 - INFO - __main__ - Step 146338: {'lr': 7.553380294676726e-07, 'samples': 28096896, 'steps': 146337, 'loss/train': 1.2312787771224976} 08/31/2021 15:45:16 - INFO - __main__ - Step 146339: {'lr': 7.54925878444862e-07, 'samples': 28097088, 'steps': 146338, 'loss/train': 0.9284732341766357} 08/31/2021 15:45:17 - INFO - __main__ - Step 146340: {'lr': 7.545138397280216e-07, 'samples': 28097280, 'steps': 146339, 'loss/train': 0.022267254069447517} 08/31/2021 15:45:17 - INFO - __main__ - Step 146341: {'lr': 7.541019133173454e-07, 'samples': 28097472, 'steps': 146340, 'loss/train': 0.2816447913646698} 08/31/2021 15:45:17 - INFO - __main__ - Step 146342: {'lr': 7.536900992130003e-07, 'samples': 28097664, 'steps': 146341, 'loss/train': 1.0666691064834595} 08/31/2021 15:45:19 - INFO - __main__ - Step 146343: {'lr': 7.532783974152357e-07, 'samples': 28097856, 'steps': 146342, 'loss/train': 0.15419451892375946} 08/31/2021 15:45:19 - INFO - __main__ - Step 146344: {'lr': 7.528668079241907e-07, 'samples': 28098048, 'steps': 146343, 'loss/train': 1.7505611181259155} 08/31/2021 15:45:20 - INFO - __main__ - Step 146345: {'lr': 7.524553307400317e-07, 'samples': 28098240, 'steps': 146344, 'loss/train': 0.7988718152046204} 08/31/2021 15:45:20 - INFO - __main__ - Step 146346: {'lr': 7.520439658630085e-07, 'samples': 28098432, 'steps': 146345, 'loss/train': 0.9217109084129333} 08/31/2021 15:45:21 - INFO - __main__ - Step 146347: {'lr': 7.516327132932321e-07, 'samples': 28098624, 'steps': 146346, 'loss/train': 0.09433729201555252} 08/31/2021 15:45:23 - INFO - __main__ - Step 146348: {'lr': 7.512215730309524e-07, 'samples': 28098816, 'steps': 146347, 'loss/train': 0.7027103900909424} 08/31/2021 15:45:23 - INFO - __main__ - Step 146349: {'lr': 7.50810545076308e-07, 'samples': 28099008, 'steps': 146348, 'loss/train': 1.1656125783920288} 08/31/2021 15:45:23 - INFO - __main__ - Step 146350: {'lr': 7.503996294294934e-07, 'samples': 28099200, 'steps': 146349, 'loss/train': 1.1189405918121338} 08/31/2021 15:45:24 - INFO - __main__ - Step 146351: {'lr': 7.499888260907306e-07, 'samples': 28099392, 'steps': 146350, 'loss/train': 1.0959763526916504} 08/31/2021 15:45:24 - INFO - __main__ - Step 146352: {'lr': 7.495781350601583e-07, 'samples': 28099584, 'steps': 146351, 'loss/train': 0.7821909785270691} 08/31/2021 15:45:24 - INFO - __main__ - Step 146353: {'lr': 7.491675563379984e-07, 'samples': 28099776, 'steps': 146352, 'loss/train': 1.1539801359176636} 08/31/2021 15:45:26 - INFO - __main__ - Step 146354: {'lr': 7.4875708992439e-07, 'samples': 28099968, 'steps': 146353, 'loss/train': 1.3629839420318604} 08/31/2021 15:45:27 - INFO - __main__ - Step 146355: {'lr': 7.48346735819555e-07, 'samples': 28100160, 'steps': 146354, 'loss/train': 0.7194393873214722} 08/31/2021 15:45:27 - INFO - __main__ - Step 146356: {'lr': 7.479364940236877e-07, 'samples': 28100352, 'steps': 146355, 'loss/train': 0.9299411773681641} 08/31/2021 15:45:27 - INFO - __main__ - Step 146357: {'lr': 7.475263645369268e-07, 'samples': 28100544, 'steps': 146356, 'loss/train': 1.26774263381958} 08/31/2021 15:45:28 - INFO - __main__ - Step 146358: {'lr': 7.471163473594945e-07, 'samples': 28100736, 'steps': 146357, 'loss/train': 1.131282091140747} 08/31/2021 15:45:29 - INFO - __main__ - Step 146359: {'lr': 7.467064424915848e-07, 'samples': 28100928, 'steps': 146358, 'loss/train': 0.02993808500468731} 08/31/2021 15:45:30 - INFO - __main__ - Step 146360: {'lr': 7.462966499333368e-07, 'samples': 28101120, 'steps': 146359, 'loss/train': 1.1971685886383057} 08/31/2021 15:45:30 - INFO - __main__ - Step 146361: {'lr': 7.458869696849723e-07, 'samples': 28101312, 'steps': 146360, 'loss/train': 1.3269699811935425} 08/31/2021 15:45:30 - INFO - __main__ - Step 146362: {'lr': 7.454774017466581e-07, 'samples': 28101504, 'steps': 146361, 'loss/train': 0.702416181564331} 08/31/2021 15:45:31 - INFO - __main__ - Step 146363: {'lr': 7.45067946118616e-07, 'samples': 28101696, 'steps': 146362, 'loss/train': 1.1263892650604248} 08/31/2021 15:45:32 - INFO - __main__ - Step 146364: {'lr': 7.446586028009572e-07, 'samples': 28101888, 'steps': 146363, 'loss/train': 1.4185996055603027} 08/31/2021 15:45:33 - INFO - __main__ - Step 146365: {'lr': 7.442493717939313e-07, 'samples': 28102080, 'steps': 146364, 'loss/train': 0.013307602144777775} 08/31/2021 15:45:33 - INFO - __main__ - Step 146366: {'lr': 7.438402530977051e-07, 'samples': 28102272, 'steps': 146365, 'loss/train': 0.014546306803822517} 08/31/2021 15:45:34 - INFO - __main__ - Step 146367: {'lr': 7.434312467124449e-07, 'samples': 28102464, 'steps': 146366, 'loss/train': 0.48180168867111206} 08/31/2021 15:45:34 - INFO - __main__ - Step 146368: {'lr': 7.430223526383451e-07, 'samples': 28102656, 'steps': 146367, 'loss/train': 0.8314539790153503} 08/31/2021 15:45:34 - INFO - __main__ - Step 146369: {'lr': 7.426135708755999e-07, 'samples': 28102848, 'steps': 146368, 'loss/train': 0.8412771821022034} 08/31/2021 15:45:36 - INFO - __main__ - Step 146370: {'lr': 7.42204901424376e-07, 'samples': 28103040, 'steps': 146369, 'loss/train': 0.7801233530044556} 08/31/2021 15:45:36 - INFO - __main__ - Step 146371: {'lr': 7.417963442848952e-07, 'samples': 28103232, 'steps': 146370, 'loss/train': 1.077889084815979} 08/31/2021 15:45:37 - INFO - __main__ - Step 146372: {'lr': 7.413878994572964e-07, 'samples': 28103424, 'steps': 146371, 'loss/train': 0.641349732875824} 08/31/2021 15:45:37 - INFO - __main__ - Step 146373: {'lr': 7.409795669418018e-07, 'samples': 28103616, 'steps': 146372, 'loss/train': 1.1695365905761719} 08/31/2021 15:45:37 - INFO - __main__ - Step 146374: {'lr': 7.4057134673855e-07, 'samples': 28103808, 'steps': 146373, 'loss/train': 0.6532749533653259} 08/31/2021 15:45:39 - INFO - __main__ - Step 146375: {'lr': 7.401632388477631e-07, 'samples': 28104000, 'steps': 146374, 'loss/train': 1.0097627639770508} 08/31/2021 15:45:40 - INFO - __main__ - Step 146376: {'lr': 7.397552432696076e-07, 'samples': 28104192, 'steps': 146375, 'loss/train': 0.31616613268852234} 08/31/2021 15:45:40 - INFO - __main__ - Step 146377: {'lr': 7.393473600042777e-07, 'samples': 28104384, 'steps': 146376, 'loss/train': 1.2610282897949219} 08/31/2021 15:45:40 - INFO - __main__ - Step 146378: {'lr': 7.389395890519401e-07, 'samples': 28104576, 'steps': 146377, 'loss/train': 1.1016238927841187} 08/31/2021 15:45:41 - INFO - __main__ - Step 146379: {'lr': 7.385319304127891e-07, 'samples': 28104768, 'steps': 146378, 'loss/train': 4.762984275817871} 08/31/2021 15:45:41 - INFO - __main__ - Step 146380: {'lr': 7.381243840870189e-07, 'samples': 28104960, 'steps': 146379, 'loss/train': 1.2647643089294434} 08/31/2021 15:45:41 - INFO - __main__ - Step 146381: {'lr': 7.37716950074796e-07, 'samples': 28105152, 'steps': 146380, 'loss/train': 0.1920507252216339} 08/31/2021 15:45:43 - INFO - __main__ - Step 146382: {'lr': 7.373096283763147e-07, 'samples': 28105344, 'steps': 146381, 'loss/train': 1.1984293460845947} 08/31/2021 15:45:43 - INFO - __main__ - Step 146383: {'lr': 7.369024189917695e-07, 'samples': 28105536, 'steps': 146382, 'loss/train': 0.029753487557172775} 08/31/2021 15:45:44 - INFO - __main__ - Step 146384: {'lr': 7.364953219213267e-07, 'samples': 28105728, 'steps': 146383, 'loss/train': 0.7185097336769104} 08/31/2021 15:45:44 - INFO - __main__ - Step 146385: {'lr': 7.360883371651528e-07, 'samples': 28105920, 'steps': 146384, 'loss/train': 1.0200610160827637} 08/31/2021 15:45:45 - INFO - __main__ - Step 146386: {'lr': 7.3568146472347e-07, 'samples': 28106112, 'steps': 146385, 'loss/train': 1.5246604681015015} 08/31/2021 15:45:47 - INFO - __main__ - Step 146387: {'lr': 7.35274704596417e-07, 'samples': 28106304, 'steps': 146386, 'loss/train': 0.2926810681819916} 08/31/2021 15:45:48 - INFO - __main__ - Step 146388: {'lr': 7.348680567842158e-07, 'samples': 28106496, 'steps': 146387, 'loss/train': 1.300031065940857} 08/31/2021 15:45:48 - INFO - __main__ - Step 146389: {'lr': 7.344615212870609e-07, 'samples': 28106688, 'steps': 146388, 'loss/train': 0.7522328495979309} 08/31/2021 15:45:48 - INFO - __main__ - Step 146390: {'lr': 7.340550981050909e-07, 'samples': 28106880, 'steps': 146389, 'loss/train': 0.36817774176597595} 08/31/2021 15:45:49 - INFO - __main__ - Step 146391: {'lr': 7.336487872385e-07, 'samples': 28107072, 'steps': 146390, 'loss/train': 1.3638581037521362} 08/31/2021 15:45:49 - INFO - __main__ - Step 146392: {'lr': 7.332425886874827e-07, 'samples': 28107264, 'steps': 146391, 'loss/train': 1.7381870746612549} 08/31/2021 15:45:49 - INFO - __main__ - Step 146393: {'lr': 7.328365024522332e-07, 'samples': 28107456, 'steps': 146392, 'loss/train': 1.7385010719299316} 08/31/2021 15:45:51 - INFO - __main__ - Step 146394: {'lr': 7.32430528532918e-07, 'samples': 28107648, 'steps': 146393, 'loss/train': 1.725993275642395} 08/31/2021 15:45:52 - INFO - __main__ - Step 146395: {'lr': 7.320246669297315e-07, 'samples': 28107840, 'steps': 146394, 'loss/train': 1.5982111692428589} 08/31/2021 15:45:52 - INFO - __main__ - Step 146396: {'lr': 7.3161891764284e-07, 'samples': 28108032, 'steps': 146395, 'loss/train': 1.5838078260421753} 08/31/2021 15:45:53 - INFO - __main__ - Step 146397: {'lr': 7.312132806724103e-07, 'samples': 28108224, 'steps': 146396, 'loss/train': 0.7576094269752502} 08/31/2021 15:45:53 - INFO - __main__ - Step 146398: {'lr': 7.308077560186921e-07, 'samples': 28108416, 'steps': 146397, 'loss/train': 0.2784371078014374} 08/31/2021 15:45:53 - INFO - __main__ - Step 146399: {'lr': 7.304023436817964e-07, 'samples': 28108608, 'steps': 146398, 'loss/train': 0.642554521560669} 08/31/2021 15:45:55 - INFO - __main__ - Step 146400: {'lr': 7.299970436619452e-07, 'samples': 28108800, 'steps': 146399, 'loss/train': 0.8758476376533508} 08/31/2021 15:45:56 - INFO - __main__ - Step 146401: {'lr': 7.295918559593051e-07, 'samples': 28108992, 'steps': 146400, 'loss/train': 1.2785496711730957} 08/31/2021 15:45:56 - INFO - __main__ - Step 146402: {'lr': 7.291867805740704e-07, 'samples': 28109184, 'steps': 146401, 'loss/train': 1.7935289144515991} 08/31/2021 15:45:56 - INFO - __main__ - Step 146403: {'lr': 7.287818175064076e-07, 'samples': 28109376, 'steps': 146402, 'loss/train': 0.711563229560852} 08/31/2021 15:45:57 - INFO - __main__ - Step 146404: {'lr': 7.28376966756511e-07, 'samples': 28109568, 'steps': 146403, 'loss/train': 0.042092010378837585} 08/31/2021 15:45:58 - INFO - __main__ - Step 146405: {'lr': 7.279722283245749e-07, 'samples': 28109760, 'steps': 146404, 'loss/train': 1.429260492324829} 08/31/2021 15:45:58 - INFO - __main__ - Step 146406: {'lr': 7.275676022107658e-07, 'samples': 28109952, 'steps': 146405, 'loss/train': 0.6991660594940186} 08/31/2021 15:45:59 - INFO - __main__ - Step 146407: {'lr': 7.271630884152502e-07, 'samples': 28110144, 'steps': 146406, 'loss/train': 0.9546354413032532} 08/31/2021 15:45:59 - INFO - __main__ - Step 146408: {'lr': 7.267586869382503e-07, 'samples': 28110336, 'steps': 146407, 'loss/train': 0.9494917392730713} 08/31/2021 15:46:00 - INFO - __main__ - Step 146409: {'lr': 7.263543977799047e-07, 'samples': 28110528, 'steps': 146408, 'loss/train': 1.0518769025802612} 08/31/2021 15:46:01 - INFO - __main__ - Step 146410: {'lr': 7.259502209404357e-07, 'samples': 28110720, 'steps': 146409, 'loss/train': 1.189315676689148} 08/31/2021 15:46:01 - INFO - __main__ - Step 146411: {'lr': 7.255461564200095e-07, 'samples': 28110912, 'steps': 146410, 'loss/train': 0.8487309217453003} 08/31/2021 15:46:02 - INFO - __main__ - Step 146412: {'lr': 7.251422042187927e-07, 'samples': 28111104, 'steps': 146411, 'loss/train': 0.8214071989059448} 08/31/2021 15:46:02 - INFO - __main__ - Step 146413: {'lr': 7.247383643369798e-07, 'samples': 28111296, 'steps': 146412, 'loss/train': 0.15903979539871216} 08/31/2021 15:46:02 - INFO - __main__ - Step 146414: {'lr': 7.24334636774765e-07, 'samples': 28111488, 'steps': 146413, 'loss/train': 0.5425670146942139} 08/31/2021 15:46:04 - INFO - __main__ - Step 146415: {'lr': 7.239310215323147e-07, 'samples': 28111680, 'steps': 146414, 'loss/train': 1.4799818992614746} 08/31/2021 15:46:04 - INFO - __main__ - Step 146416: {'lr': 7.235275186097956e-07, 'samples': 28111872, 'steps': 146415, 'loss/train': 1.0961161851882935} 08/31/2021 15:46:05 - INFO - __main__ - Step 146417: {'lr': 7.231241280074296e-07, 'samples': 28112064, 'steps': 146416, 'loss/train': 0.37094026803970337} 08/31/2021 15:46:05 - INFO - __main__ - Step 146418: {'lr': 7.227208497253835e-07, 'samples': 28112256, 'steps': 146417, 'loss/train': 1.5092581510543823} 08/31/2021 15:46:05 - INFO - __main__ - Step 146419: {'lr': 7.223176837638234e-07, 'samples': 28112448, 'steps': 146418, 'loss/train': 1.0585588216781616} 08/31/2021 15:46:07 - INFO - __main__ - Step 146420: {'lr': 7.21914630122944e-07, 'samples': 28112640, 'steps': 146419, 'loss/train': 0.5696896910667419} 08/31/2021 15:46:07 - INFO - __main__ - Step 146421: {'lr': 7.215116888029117e-07, 'samples': 28112832, 'steps': 146420, 'loss/train': 0.36043205857276917} 08/31/2021 15:46:08 - INFO - __main__ - Step 146422: {'lr': 7.211088598039206e-07, 'samples': 28113024, 'steps': 146421, 'loss/train': 0.9989597201347351} 08/31/2021 15:46:08 - INFO - __main__ - Step 146423: {'lr': 7.207061431261652e-07, 'samples': 28113216, 'steps': 146422, 'loss/train': 0.7075081467628479} 08/31/2021 15:46:08 - INFO - __main__ - Step 146424: {'lr': 7.203035387697843e-07, 'samples': 28113408, 'steps': 146423, 'loss/train': 1.0081225633621216} 08/31/2021 15:46:10 - INFO - __main__ - Step 146425: {'lr': 7.199010467349998e-07, 'samples': 28113600, 'steps': 146424, 'loss/train': 1.2975577116012573} 08/31/2021 15:46:10 - INFO - __main__ - Step 146426: {'lr': 7.19498667022006e-07, 'samples': 28113792, 'steps': 146425, 'loss/train': 0.8644345998764038} 08/31/2021 15:46:11 - INFO - __main__ - Step 146427: {'lr': 7.190963996309419e-07, 'samples': 28113984, 'steps': 146426, 'loss/train': 1.243687391281128} 08/31/2021 15:46:11 - INFO - __main__ - Step 146428: {'lr': 7.186942445620015e-07, 'samples': 28114176, 'steps': 146427, 'loss/train': 1.1149111986160278} 08/31/2021 15:46:11 - INFO - __main__ - Step 146429: {'lr': 7.182922018153793e-07, 'samples': 28114368, 'steps': 146428, 'loss/train': 1.350539207458496} 08/31/2021 15:46:13 - INFO - __main__ - Step 146430: {'lr': 7.178902713912417e-07, 'samples': 28114560, 'steps': 146429, 'loss/train': 0.30572521686553955} 08/31/2021 15:46:13 - INFO - __main__ - Step 146431: {'lr': 7.174884532897829e-07, 'samples': 28114752, 'steps': 146430, 'loss/train': 1.0393823385238647} 08/31/2021 15:46:14 - INFO - __main__ - Step 146432: {'lr': 7.170867475111697e-07, 'samples': 28114944, 'steps': 146431, 'loss/train': 0.642935037612915} 08/31/2021 15:46:14 - INFO - __main__ - Step 146433: {'lr': 7.166851540555963e-07, 'samples': 28115136, 'steps': 146432, 'loss/train': 1.9014742374420166} 08/31/2021 15:46:14 - INFO - __main__ - Step 146434: {'lr': 7.162836729232292e-07, 'samples': 28115328, 'steps': 146433, 'loss/train': 0.926256000995636} 08/31/2021 15:46:16 - INFO - __main__ - Step 146435: {'lr': 7.158823041142626e-07, 'samples': 28115520, 'steps': 146434, 'loss/train': 1.0171782970428467} 08/31/2021 15:46:16 - INFO - __main__ - Step 146436: {'lr': 7.154810476288909e-07, 'samples': 28115712, 'steps': 146435, 'loss/train': 1.1916768550872803} 08/31/2021 15:46:17 - INFO - __main__ - Step 146437: {'lr': 7.150799034672528e-07, 'samples': 28115904, 'steps': 146436, 'loss/train': 1.016087532043457} 08/31/2021 15:46:17 - INFO - __main__ - Step 146438: {'lr': 7.146788716295705e-07, 'samples': 28116096, 'steps': 146437, 'loss/train': 0.676456093788147} 08/31/2021 15:46:17 - INFO - __main__ - Step 146439: {'lr': 7.142779521159826e-07, 'samples': 28116288, 'steps': 146438, 'loss/train': 0.9796266555786133} 08/31/2021 15:46:19 - INFO - __main__ - Step 146440: {'lr': 7.138771449267112e-07, 'samples': 28116480, 'steps': 146439, 'loss/train': 1.4829972982406616} 08/31/2021 15:46:19 - INFO - __main__ - Step 146441: {'lr': 7.134764500619228e-07, 'samples': 28116672, 'steps': 146440, 'loss/train': 0.9472459554672241} 08/31/2021 15:46:20 - INFO - __main__ - Step 146442: {'lr': 7.130758675217841e-07, 'samples': 28116864, 'steps': 146441, 'loss/train': 0.6471658945083618} 08/31/2021 15:46:20 - INFO - __main__ - Step 146443: {'lr': 7.126753973064892e-07, 'samples': 28117056, 'steps': 146442, 'loss/train': 1.269720196723938} 08/31/2021 15:46:21 - INFO - __main__ - Step 146444: {'lr': 7.122750394162325e-07, 'samples': 28117248, 'steps': 146443, 'loss/train': 1.171790599822998} 08/31/2021 15:46:22 - INFO - __main__ - Step 146445: {'lr': 7.118747938511528e-07, 'samples': 28117440, 'steps': 146444, 'loss/train': 0.9079278111457825} 08/31/2021 15:46:22 - INFO - __main__ - Step 146446: {'lr': 7.114746606114719e-07, 'samples': 28117632, 'steps': 146445, 'loss/train': 0.25538405776023865} 08/31/2021 15:46:23 - INFO - __main__ - Step 146447: {'lr': 7.110746396973567e-07, 'samples': 28117824, 'steps': 146446, 'loss/train': 0.4779548645019531} 08/31/2021 15:46:23 - INFO - __main__ - Step 146448: {'lr': 7.106747311089734e-07, 'samples': 28118016, 'steps': 146447, 'loss/train': 1.4354814291000366} 08/31/2021 15:46:24 - INFO - __main__ - Step 146449: {'lr': 7.102749348465165e-07, 'samples': 28118208, 'steps': 146448, 'loss/train': 1.4079852104187012} 08/31/2021 15:46:24 - INFO - __main__ - Step 146450: {'lr': 7.098752509101803e-07, 'samples': 28118400, 'steps': 146449, 'loss/train': 0.8804789781570435} 08/31/2021 15:46:26 - INFO - __main__ - Step 146451: {'lr': 7.094756793001034e-07, 'samples': 28118592, 'steps': 146450, 'loss/train': 1.1990398168563843} 08/31/2021 15:46:27 - INFO - __main__ - Step 146452: {'lr': 7.09076220016508e-07, 'samples': 28118784, 'steps': 146451, 'loss/train': 1.2989962100982666} 08/31/2021 15:46:27 - INFO - __main__ - Step 146453: {'lr': 7.086768730595328e-07, 'samples': 28118976, 'steps': 146452, 'loss/train': 0.9952651262283325} 08/31/2021 15:46:27 - INFO - __main__ - Step 146454: {'lr': 7.082776384293998e-07, 'samples': 28119168, 'steps': 146453, 'loss/train': 1.5700606107711792} 08/31/2021 15:46:28 - INFO - __main__ - Step 146455: {'lr': 7.07878516126248e-07, 'samples': 28119360, 'steps': 146454, 'loss/train': 0.6922996640205383} 08/31/2021 15:46:29 - INFO - __main__ - Step 146456: {'lr': 7.074795061502992e-07, 'samples': 28119552, 'steps': 146455, 'loss/train': 5.393682956695557} 08/31/2021 15:46:30 - INFO - __main__ - Step 146457: {'lr': 7.070806085017201e-07, 'samples': 28119744, 'steps': 146456, 'loss/train': 0.9928367137908936} 08/31/2021 15:46:30 - INFO - __main__ - Step 146458: {'lr': 7.066818231806771e-07, 'samples': 28119936, 'steps': 146457, 'loss/train': 1.174907922744751} 08/31/2021 15:46:30 - INFO - __main__ - Step 146459: {'lr': 7.062831501873368e-07, 'samples': 28120128, 'steps': 146458, 'loss/train': 1.1696345806121826} 08/31/2021 15:46:31 - INFO - __main__ - Step 146460: {'lr': 7.058845895219213e-07, 'samples': 28120320, 'steps': 146459, 'loss/train': 0.7969629764556885} 08/31/2021 15:46:32 - INFO - __main__ - Step 146461: {'lr': 7.054861411845969e-07, 'samples': 28120512, 'steps': 146460, 'loss/train': 1.4575481414794922} 08/31/2021 15:46:33 - INFO - __main__ - Step 146462: {'lr': 7.050878051755027e-07, 'samples': 28120704, 'steps': 146461, 'loss/train': 1.2053302526474} 08/31/2021 15:46:33 - INFO - __main__ - Step 146463: {'lr': 7.046895814948606e-07, 'samples': 28120896, 'steps': 146462, 'loss/train': 0.9299903512001038} 08/31/2021 15:46:33 - INFO - __main__ - Step 146464: {'lr': 7.042914701428371e-07, 'samples': 28121088, 'steps': 146463, 'loss/train': 1.3753993511199951} 08/31/2021 15:46:34 - INFO - __main__ - Step 146465: {'lr': 7.038934711196265e-07, 'samples': 28121280, 'steps': 146464, 'loss/train': 1.4665710926055908} 08/31/2021 15:46:35 - INFO - __main__ - Step 146466: {'lr': 7.034955844253954e-07, 'samples': 28121472, 'steps': 146465, 'loss/train': 1.2312513589859009} 08/31/2021 15:46:36 - INFO - __main__ - Step 146467: {'lr': 7.030978100603102e-07, 'samples': 28121664, 'steps': 146466, 'loss/train': 1.360856056213379} 08/31/2021 15:46:36 - INFO - __main__ - Step 146468: {'lr': 7.027001480245654e-07, 'samples': 28121856, 'steps': 146467, 'loss/train': 1.4137216806411743} 08/31/2021 15:46:36 - INFO - __main__ - Step 146469: {'lr': 7.023025983183273e-07, 'samples': 28122048, 'steps': 146468, 'loss/train': 1.0831784009933472} 08/31/2021 15:46:37 - INFO - __main__ - Step 146470: {'lr': 7.019051609417904e-07, 'samples': 28122240, 'steps': 146469, 'loss/train': 0.8986758589744568} 08/31/2021 15:46:38 - INFO - __main__ - Step 146471: {'lr': 7.01507835895121e-07, 'samples': 28122432, 'steps': 146470, 'loss/train': 1.1250241994857788} 08/31/2021 15:46:39 - INFO - __main__ - Step 146472: {'lr': 7.011106231785414e-07, 'samples': 28122624, 'steps': 146471, 'loss/train': 1.4011516571044922} 08/31/2021 15:46:39 - INFO - __main__ - Step 146473: {'lr': 7.007135227921624e-07, 'samples': 28122816, 'steps': 146472, 'loss/train': 1.1032330989837646} 08/31/2021 15:46:39 - INFO - __main__ - Step 146474: {'lr': 7.003165347362061e-07, 'samples': 28123008, 'steps': 146473, 'loss/train': 0.668557345867157} 08/31/2021 15:46:40 - INFO - __main__ - Step 146475: {'lr': 6.999196590108392e-07, 'samples': 28123200, 'steps': 146474, 'loss/train': 0.6510877013206482} 08/31/2021 15:46:41 - INFO - __main__ - Step 146476: {'lr': 6.995228956162281e-07, 'samples': 28123392, 'steps': 146475, 'loss/train': 0.022890035063028336} 08/31/2021 15:46:42 - INFO - __main__ - Step 146477: {'lr': 6.99126244552567e-07, 'samples': 28123584, 'steps': 146476, 'loss/train': 0.3606428802013397} 08/31/2021 15:46:42 - INFO - __main__ - Step 146478: {'lr': 6.987297058200503e-07, 'samples': 28123776, 'steps': 146477, 'loss/train': 1.2672942876815796} 08/31/2021 15:46:42 - INFO - __main__ - Step 146479: {'lr': 6.983332794188169e-07, 'samples': 28123968, 'steps': 146478, 'loss/train': 1.5404032468795776} 08/31/2021 15:46:43 - INFO - __main__ - Step 146480: {'lr': 6.979369653490886e-07, 'samples': 28124160, 'steps': 146479, 'loss/train': 1.1581839323043823} 08/31/2021 15:46:44 - INFO - __main__ - Step 146481: {'lr': 6.975407636110043e-07, 'samples': 28124352, 'steps': 146480, 'loss/train': 1.4204397201538086} 08/31/2021 15:46:45 - INFO - __main__ - Step 146482: {'lr': 6.97144674204786e-07, 'samples': 28124544, 'steps': 146481, 'loss/train': 0.14535365998744965} 08/31/2021 15:46:45 - INFO - __main__ - Step 146483: {'lr': 6.967486971305725e-07, 'samples': 28124736, 'steps': 146482, 'loss/train': 0.8704214096069336} 08/31/2021 15:46:45 - INFO - __main__ - Step 146484: {'lr': 6.963528323885304e-07, 'samples': 28124928, 'steps': 146483, 'loss/train': 0.9135756492614746} 08/31/2021 15:46:46 - INFO - __main__ - Step 146485: {'lr': 6.959570799789095e-07, 'samples': 28125120, 'steps': 146484, 'loss/train': 1.478072166442871} 08/31/2021 15:46:47 - INFO - __main__ - Step 146486: {'lr': 6.955614399018207e-07, 'samples': 28125312, 'steps': 146485, 'loss/train': 0.5734322667121887} 08/31/2021 15:46:48 - INFO - __main__ - Step 146487: {'lr': 6.95165912157486e-07, 'samples': 28125504, 'steps': 146486, 'loss/train': 1.1254769563674927} 08/31/2021 15:46:48 - INFO - __main__ - Step 146488: {'lr': 6.947704967460444e-07, 'samples': 28125696, 'steps': 146487, 'loss/train': 1.068725824356079} 08/31/2021 15:46:48 - INFO - __main__ - Step 146489: {'lr': 6.943751936676901e-07, 'samples': 28125888, 'steps': 146488, 'loss/train': 1.1464543342590332} 08/31/2021 15:46:49 - INFO - __main__ - Step 146490: {'lr': 6.939800029225896e-07, 'samples': 28126080, 'steps': 146489, 'loss/train': 0.7499122023582458} 08/31/2021 15:46:49 - INFO - __main__ - Step 146491: {'lr': 6.935849245109649e-07, 'samples': 28126272, 'steps': 146490, 'loss/train': 1.1701523065567017} 08/31/2021 15:46:51 - INFO - __main__ - Step 146492: {'lr': 6.931899584329548e-07, 'samples': 28126464, 'steps': 146491, 'loss/train': 1.1465409994125366} 08/31/2021 15:46:51 - INFO - __main__ - Step 146493: {'lr': 6.92795104688726e-07, 'samples': 28126656, 'steps': 146492, 'loss/train': 0.9173479080200195} 08/31/2021 15:46:52 - INFO - __main__ - Step 146494: {'lr': 6.924003632785003e-07, 'samples': 28126848, 'steps': 146493, 'loss/train': 0.027239345014095306} 08/31/2021 15:46:52 - INFO - __main__ - Step 146495: {'lr': 6.920057342024167e-07, 'samples': 28127040, 'steps': 146494, 'loss/train': 1.2854944467544556} 08/31/2021 15:46:53 - INFO - __main__ - Step 146496: {'lr': 6.916112174606692e-07, 'samples': 28127232, 'steps': 146495, 'loss/train': 1.3319025039672852} 08/31/2021 15:46:53 - INFO - __main__ - Step 146497: {'lr': 6.912168130534524e-07, 'samples': 28127424, 'steps': 146496, 'loss/train': 0.8417389392852783} 08/31/2021 15:46:55 - INFO - __main__ - Step 146498: {'lr': 6.908225209809049e-07, 'samples': 28127616, 'steps': 146497, 'loss/train': 1.3601808547973633} 08/31/2021 15:46:55 - INFO - __main__ - Step 146499: {'lr': 6.904283412432488e-07, 'samples': 28127808, 'steps': 146498, 'loss/train': 1.422876238822937} 08/31/2021 15:46:55 - INFO - __main__ - Step 146500: {'lr': 6.900342738406229e-07, 'samples': 28128000, 'steps': 146499, 'loss/train': 0.4073752164840698} 08/31/2021 15:46:56 - INFO - __main__ - Step 146501: {'lr': 6.896403187732214e-07, 'samples': 28128192, 'steps': 146500, 'loss/train': 0.7277045845985413} 08/31/2021 15:46:56 - INFO - __main__ - Step 146502: {'lr': 6.892464760412387e-07, 'samples': 28128384, 'steps': 146501, 'loss/train': 1.6084511280059814} 08/31/2021 15:46:58 - INFO - __main__ - Step 146503: {'lr': 6.888527456448134e-07, 'samples': 28128576, 'steps': 146502, 'loss/train': 1.1804534196853638} 08/31/2021 15:46:59 - INFO - __main__ - Step 146504: {'lr': 6.884591275841401e-07, 'samples': 28128768, 'steps': 146503, 'loss/train': 1.0723553895950317} 08/31/2021 15:46:59 - INFO - __main__ - Step 146505: {'lr': 6.880656218594128e-07, 'samples': 28128960, 'steps': 146504, 'loss/train': 0.409322589635849} 08/31/2021 15:47:00 - INFO - __main__ - Step 146506: {'lr': 6.876722284707981e-07, 'samples': 28129152, 'steps': 146505, 'loss/train': 0.9404261708259583} 08/31/2021 15:47:00 - INFO - __main__ - Step 146507: {'lr': 6.872789474184627e-07, 'samples': 28129344, 'steps': 146506, 'loss/train': 0.761543333530426} 08/31/2021 15:47:01 - INFO - __main__ - Step 146508: {'lr': 6.868857787026006e-07, 'samples': 28129536, 'steps': 146507, 'loss/train': 1.287343144416809} 08/31/2021 15:47:02 - INFO - __main__ - Step 146509: {'lr': 6.864927223233785e-07, 'samples': 28129728, 'steps': 146508, 'loss/train': 1.3277552127838135} 08/31/2021 15:47:02 - INFO - __main__ - Step 146510: {'lr': 6.860997782809631e-07, 'samples': 28129920, 'steps': 146509, 'loss/train': 1.8286950588226318} 08/31/2021 15:47:03 - INFO - __main__ - Step 146511: {'lr': 6.857069465755484e-07, 'samples': 28130112, 'steps': 146510, 'loss/train': 0.45883262157440186} 08/31/2021 15:47:03 - INFO - __main__ - Step 146512: {'lr': 6.85314227207301e-07, 'samples': 28130304, 'steps': 146511, 'loss/train': 1.0813961029052734} 08/31/2021 15:47:05 - INFO - __main__ - Step 146513: {'lr': 6.84921620176443e-07, 'samples': 28130496, 'steps': 146512, 'loss/train': 0.2687155306339264} 08/31/2021 15:47:05 - INFO - __main__ - Step 146514: {'lr': 6.845291254830854e-07, 'samples': 28130688, 'steps': 146513, 'loss/train': 1.4391578435897827} 08/31/2021 15:47:06 - INFO - __main__ - Step 146515: {'lr': 6.841367431274226e-07, 'samples': 28130880, 'steps': 146514, 'loss/train': 1.2962007522583008} 08/31/2021 15:47:06 - INFO - __main__ - Step 146516: {'lr': 6.837444731096487e-07, 'samples': 28131072, 'steps': 146515, 'loss/train': 1.1170756816864014} 08/31/2021 15:47:06 - INFO - __main__ - Step 146517: {'lr': 6.833523154299303e-07, 'samples': 28131264, 'steps': 146516, 'loss/train': 1.6392086744308472} 08/31/2021 15:47:07 - INFO - __main__ - Step 146518: {'lr': 6.829602700884341e-07, 'samples': 28131456, 'steps': 146517, 'loss/train': 1.3129491806030273} 08/31/2021 15:47:08 - INFO - __main__ - Step 146519: {'lr': 6.825683370853819e-07, 'samples': 28131648, 'steps': 146518, 'loss/train': 1.3639734983444214} 08/31/2021 15:47:09 - INFO - __main__ - Step 146520: {'lr': 6.821765164208849e-07, 'samples': 28131840, 'steps': 146519, 'loss/train': 1.069796085357666} 08/31/2021 15:47:09 - INFO - __main__ - Step 146521: {'lr': 6.817848080951649e-07, 'samples': 28132032, 'steps': 146520, 'loss/train': 1.4670473337173462} 08/31/2021 15:47:09 - INFO - __main__ - Step 146522: {'lr': 6.813932121083888e-07, 'samples': 28132224, 'steps': 146521, 'loss/train': 1.029901385307312} 08/31/2021 15:47:10 - INFO - __main__ - Step 146523: {'lr': 6.810017284607229e-07, 'samples': 28132416, 'steps': 146522, 'loss/train': 1.1989312171936035} 08/31/2021 15:47:12 - INFO - __main__ - Step 146524: {'lr': 6.806103571523614e-07, 'samples': 28132608, 'steps': 146523, 'loss/train': 1.151542067527771} 08/31/2021 15:47:12 - INFO - __main__ - Step 146525: {'lr': 6.802190981834433e-07, 'samples': 28132800, 'steps': 146524, 'loss/train': 1.1654926538467407} 08/31/2021 15:47:12 - INFO - __main__ - Step 146526: {'lr': 6.798279515541906e-07, 'samples': 28132992, 'steps': 146525, 'loss/train': 0.02758375182747841} 08/31/2021 15:47:13 - INFO - __main__ - Step 146527: {'lr': 6.794369172647697e-07, 'samples': 28133184, 'steps': 146526, 'loss/train': 0.0697530061006546} 08/31/2021 15:47:13 - INFO - __main__ - Step 146528: {'lr': 6.790459953153471e-07, 'samples': 28133376, 'steps': 146527, 'loss/train': 1.5779364109039307} 08/31/2021 15:47:13 - INFO - __main__ - Step 146529: {'lr': 6.786551857060896e-07, 'samples': 28133568, 'steps': 146528, 'loss/train': 1.0852137804031372} 08/31/2021 15:47:15 - INFO - __main__ - Step 146530: {'lr': 6.782644884371636e-07, 'samples': 28133760, 'steps': 146529, 'loss/train': 0.10374508798122406} 08/31/2021 15:47:16 - INFO - __main__ - Step 146531: {'lr': 6.778739035087911e-07, 'samples': 28133952, 'steps': 146530, 'loss/train': 0.32010942697525024} 08/31/2021 15:47:16 - INFO - __main__ - Step 146532: {'lr': 6.774834309211109e-07, 'samples': 28134144, 'steps': 146531, 'loss/train': 0.2195625752210617} 08/31/2021 15:47:17 - INFO - __main__ - Step 146533: {'lr': 6.770930706743172e-07, 'samples': 28134336, 'steps': 146532, 'loss/train': 1.2944486141204834} 08/31/2021 15:47:17 - INFO - __main__ - Step 146534: {'lr': 6.767028227685767e-07, 'samples': 28134528, 'steps': 146533, 'loss/train': 0.11402763426303864} 08/31/2021 15:47:17 - INFO - __main__ - Step 146535: {'lr': 6.763126872040559e-07, 'samples': 28134720, 'steps': 146534, 'loss/train': 0.8196799755096436} 08/31/2021 15:47:19 - INFO - __main__ - Step 146536: {'lr': 6.759226639809491e-07, 'samples': 28134912, 'steps': 146535, 'loss/train': 0.6260151267051697} 08/31/2021 15:47:19 - INFO - __main__ - Step 146537: {'lr': 6.755327530994227e-07, 'samples': 28135104, 'steps': 146536, 'loss/train': 1.6057206392288208} 08/31/2021 15:47:20 - INFO - __main__ - Step 146538: {'lr': 6.751429545596432e-07, 'samples': 28135296, 'steps': 146537, 'loss/train': 1.4413923025131226} 08/31/2021 15:47:20 - INFO - __main__ - Step 146539: {'lr': 6.74753268361833e-07, 'samples': 28135488, 'steps': 146538, 'loss/train': 0.9805883765220642} 08/31/2021 15:47:20 - INFO - __main__ - Step 146540: {'lr': 6.743636945061027e-07, 'samples': 28135680, 'steps': 146539, 'loss/train': 2.523559331893921} 08/31/2021 15:47:22 - INFO - __main__ - Step 146541: {'lr': 6.739742329926468e-07, 'samples': 28135872, 'steps': 146540, 'loss/train': 1.0320324897766113} 08/31/2021 15:47:22 - INFO - __main__ - Step 146542: {'lr': 6.735848838216597e-07, 'samples': 28136064, 'steps': 146541, 'loss/train': 1.397234559059143} 08/31/2021 15:47:23 - INFO - __main__ - Step 146543: {'lr': 6.731956469933077e-07, 'samples': 28136256, 'steps': 146542, 'loss/train': 1.2516926527023315} 08/31/2021 15:47:23 - INFO - __main__ - Step 146544: {'lr': 6.728065225077851e-07, 'samples': 28136448, 'steps': 146543, 'loss/train': 0.5796407461166382} 08/31/2021 15:47:23 - INFO - __main__ - Step 146545: {'lr': 6.724175103652308e-07, 'samples': 28136640, 'steps': 146544, 'loss/train': 1.134217619895935} 08/31/2021 15:47:25 - INFO - __main__ - Step 146546: {'lr': 6.720286105658391e-07, 'samples': 28136832, 'steps': 146545, 'loss/train': 0.11156166344881058} 08/31/2021 15:47:26 - INFO - __main__ - Step 146547: {'lr': 6.716398231098042e-07, 'samples': 28137024, 'steps': 146546, 'loss/train': 0.641684353351593} 08/31/2021 15:47:26 - INFO - __main__ - Step 146548: {'lr': 6.712511479972372e-07, 'samples': 28137216, 'steps': 146547, 'loss/train': 0.04414059594273567} 08/31/2021 15:47:26 - INFO - __main__ - Step 146549: {'lr': 6.708625852283878e-07, 'samples': 28137408, 'steps': 146548, 'loss/train': 1.1119611263275146} 08/31/2021 15:47:27 - INFO - __main__ - Step 146550: {'lr': 6.704741348033949e-07, 'samples': 28137600, 'steps': 146549, 'loss/train': 0.781699001789093} 08/31/2021 15:47:29 - INFO - __main__ - Step 146551: {'lr': 6.700857967224527e-07, 'samples': 28137792, 'steps': 146550, 'loss/train': 0.7138271927833557} 08/31/2021 15:47:29 - INFO - __main__ - Step 146552: {'lr': 6.696975709857001e-07, 'samples': 28137984, 'steps': 146551, 'loss/train': 0.8807732462882996} 08/31/2021 15:47:29 - INFO - __main__ - Step 146553: {'lr': 6.69309457593359e-07, 'samples': 28138176, 'steps': 146552, 'loss/train': 0.8653419017791748} 08/31/2021 15:47:30 - INFO - __main__ - Step 146554: {'lr': 6.689214565455682e-07, 'samples': 28138368, 'steps': 146553, 'loss/train': 0.8510024547576904} 08/31/2021 15:47:30 - INFO - __main__ - Step 146555: {'lr': 6.685335678424942e-07, 'samples': 28138560, 'steps': 146554, 'loss/train': 0.8198210597038269} 08/31/2021 15:47:31 - INFO - __main__ - Step 146556: {'lr': 6.681457914843592e-07, 'samples': 28138752, 'steps': 146555, 'loss/train': 1.4194782972335815} 08/31/2021 15:47:33 - INFO - __main__ - Step 146557: {'lr': 6.677581274713019e-07, 'samples': 28138944, 'steps': 146556, 'loss/train': 2.150726556777954} 08/31/2021 15:47:33 - INFO - __main__ - Step 146558: {'lr': 6.673705758034887e-07, 'samples': 28139136, 'steps': 146557, 'loss/train': 0.3015074133872986} 08/31/2021 15:47:33 - INFO - __main__ - Step 146559: {'lr': 6.669831364811419e-07, 'samples': 28139328, 'steps': 146558, 'loss/train': 1.1143295764923096} 08/31/2021 15:47:34 - INFO - __main__ - Step 146560: {'lr': 6.665958095043723e-07, 'samples': 28139520, 'steps': 146559, 'loss/train': 1.1986340284347534} 08/31/2021 15:47:34 - INFO - __main__ - Step 146561: {'lr': 6.66208594873402e-07, 'samples': 28139712, 'steps': 146560, 'loss/train': 1.1907992362976074} 08/31/2021 15:47:36 - INFO - __main__ - Step 146562: {'lr': 6.658214925883977e-07, 'samples': 28139904, 'steps': 146561, 'loss/train': 1.2284804582595825} 08/31/2021 15:47:36 - INFO - __main__ - Step 146563: {'lr': 6.654345026495256e-07, 'samples': 28140096, 'steps': 146562, 'loss/train': 0.7441185116767883} 08/31/2021 15:47:37 - INFO - __main__ - Step 146564: {'lr': 6.650476250569526e-07, 'samples': 28140288, 'steps': 146563, 'loss/train': 0.06972922384738922} 08/31/2021 15:47:37 - INFO - __main__ - Step 146565: {'lr': 6.646608598108728e-07, 'samples': 28140480, 'steps': 146564, 'loss/train': 1.558050274848938} 08/31/2021 15:47:38 - INFO - __main__ - Step 146566: {'lr': 6.642742069114249e-07, 'samples': 28140672, 'steps': 146565, 'loss/train': 0.7133501768112183} 08/31/2021 15:47:39 - INFO - __main__ - Step 146567: {'lr': 6.638876663588312e-07, 'samples': 28140864, 'steps': 146566, 'loss/train': 0.8337854743003845} 08/31/2021 15:47:40 - INFO - __main__ - Step 146568: {'lr': 6.635012381532302e-07, 'samples': 28141056, 'steps': 146567, 'loss/train': 1.0853607654571533} 08/31/2021 15:47:40 - INFO - __main__ - Step 146569: {'lr': 6.631149222948163e-07, 'samples': 28141248, 'steps': 146568, 'loss/train': 0.894649863243103} 08/31/2021 15:47:40 - INFO - __main__ - Step 146570: {'lr': 6.627287187837561e-07, 'samples': 28141440, 'steps': 146569, 'loss/train': 0.4945046007633209} 08/31/2021 15:47:41 - INFO - __main__ - Step 146571: {'lr': 6.62342627620216e-07, 'samples': 28141632, 'steps': 146570, 'loss/train': 0.6739189028739929} 08/31/2021 15:47:42 - INFO - __main__ - Step 146572: {'lr': 6.619566488043904e-07, 'samples': 28141824, 'steps': 146571, 'loss/train': 1.0327553749084473} 08/31/2021 15:47:43 - INFO - __main__ - Step 146573: {'lr': 6.615707823364181e-07, 'samples': 28142016, 'steps': 146572, 'loss/train': 0.9765403270721436} 08/31/2021 15:47:43 - INFO - __main__ - Step 146574: {'lr': 6.61185028216521e-07, 'samples': 28142208, 'steps': 146573, 'loss/train': 0.7719163298606873} 08/31/2021 15:47:43 - INFO - __main__ - Step 146575: {'lr': 6.607993864448103e-07, 'samples': 28142400, 'steps': 146574, 'loss/train': 0.19227392971515656} 08/31/2021 15:47:44 - INFO - __main__ - Step 146576: {'lr': 6.604138570215356e-07, 'samples': 28142592, 'steps': 146575, 'loss/train': 1.387738585472107} 08/31/2021 15:47:45 - INFO - __main__ - Step 146577: {'lr': 6.600284399468082e-07, 'samples': 28142784, 'steps': 146576, 'loss/train': 1.5432425737380981} 08/31/2021 15:47:46 - INFO - __main__ - Step 146578: {'lr': 6.596431352208221e-07, 'samples': 28142976, 'steps': 146577, 'loss/train': 0.8932512998580933} 08/31/2021 15:47:46 - INFO - __main__ - Step 146579: {'lr': 6.59257942843744e-07, 'samples': 28143168, 'steps': 146578, 'loss/train': 1.119421362876892} 08/31/2021 15:47:47 - INFO - __main__ - Step 146580: {'lr': 6.588728628157958e-07, 'samples': 28143360, 'steps': 146579, 'loss/train': 0.6089969277381897} 08/31/2021 15:47:47 - INFO - __main__ - Step 146581: {'lr': 6.584878951370887e-07, 'samples': 28143552, 'steps': 146580, 'loss/train': 0.970358669757843} 08/31/2021 15:47:49 - INFO - __main__ - Step 146582: {'lr': 6.581030398078169e-07, 'samples': 28143744, 'steps': 146581, 'loss/train': 0.4504278004169464} 08/31/2021 15:47:49 - INFO - __main__ - Step 146583: {'lr': 6.57718296828147e-07, 'samples': 28143936, 'steps': 146582, 'loss/train': 0.1785103678703308} 08/31/2021 15:47:50 - INFO - __main__ - Step 146584: {'lr': 6.573336661982731e-07, 'samples': 28144128, 'steps': 146583, 'loss/train': 0.014989282004535198} 08/31/2021 15:47:50 - INFO - __main__ - Step 146585: {'lr': 6.56949147918362e-07, 'samples': 28144320, 'steps': 146584, 'loss/train': 0.8892912268638611} 08/31/2021 15:47:50 - INFO - __main__ - Step 146586: {'lr': 6.565647419885801e-07, 'samples': 28144512, 'steps': 146585, 'loss/train': 0.8499550819396973} 08/31/2021 15:47:51 - INFO - __main__ - Step 146587: {'lr': 6.561804484090938e-07, 'samples': 28144704, 'steps': 146586, 'loss/train': 0.969206690788269} 08/31/2021 15:47:51 - INFO - __main__ - Step 146588: {'lr': 6.557962671800977e-07, 'samples': 28144896, 'steps': 146587, 'loss/train': 1.1009893417358398} 08/31/2021 15:47:53 - INFO - __main__ - Step 146589: {'lr': 6.554121983017303e-07, 'samples': 28145088, 'steps': 146588, 'loss/train': 1.5824211835861206} 08/31/2021 15:47:53 - INFO - __main__ - Step 146590: {'lr': 6.550282417742137e-07, 'samples': 28145280, 'steps': 146589, 'loss/train': 0.8119791746139526} 08/31/2021 15:47:53 - INFO - __main__ - Step 146591: {'lr': 6.54644397597659e-07, 'samples': 28145472, 'steps': 146590, 'loss/train': 1.5288723707199097} 08/31/2021 15:47:54 - INFO - __main__ - Step 146592: {'lr': 6.54260665772316e-07, 'samples': 28145664, 'steps': 146591, 'loss/train': 0.9646052718162537} 08/31/2021 15:47:54 - INFO - __main__ - Step 146593: {'lr': 6.538770462982957e-07, 'samples': 28145856, 'steps': 146592, 'loss/train': 1.0151572227478027} 08/31/2021 15:47:56 - INFO - __main__ - Step 146594: {'lr': 6.534935391757923e-07, 'samples': 28146048, 'steps': 146593, 'loss/train': 1.5597766637802124} 08/31/2021 15:47:56 - INFO - __main__ - Step 146595: {'lr': 6.531101444049725e-07, 'samples': 28146240, 'steps': 146594, 'loss/train': 0.14976122975349426} 08/31/2021 15:47:57 - INFO - __main__ - Step 146596: {'lr': 6.527268619860027e-07, 'samples': 28146432, 'steps': 146595, 'loss/train': 0.3219236731529236} 08/31/2021 15:47:57 - INFO - __main__ - Step 146597: {'lr': 6.523436919190773e-07, 'samples': 28146624, 'steps': 146596, 'loss/train': 1.5327123403549194} 08/31/2021 15:47:57 - INFO - __main__ - Step 146598: {'lr': 6.519606342043627e-07, 'samples': 28146816, 'steps': 146597, 'loss/train': 0.5059858560562134} 08/31/2021 15:47:59 - INFO - __main__ - Step 146599: {'lr': 6.515776888420255e-07, 'samples': 28147008, 'steps': 146598, 'loss/train': 0.4784668982028961} 08/31/2021 15:47:59 - INFO - __main__ - Step 146600: {'lr': 6.5119485583226e-07, 'samples': 28147200, 'steps': 146599, 'loss/train': 1.1148748397827148} 08/31/2021 15:48:00 - INFO - __main__ - Step 146601: {'lr': 6.508121351751773e-07, 'samples': 28147392, 'steps': 146600, 'loss/train': 1.0953928232192993} 08/31/2021 15:48:00 - INFO - __main__ - Step 146602: {'lr': 6.50429526871027e-07, 'samples': 28147584, 'steps': 146601, 'loss/train': 0.8985076546669006} 08/31/2021 15:48:00 - INFO - __main__ - Step 146603: {'lr': 6.500470309199202e-07, 'samples': 28147776, 'steps': 146602, 'loss/train': 0.8040664196014404} 08/31/2021 15:48:02 - INFO - __main__ - Step 146604: {'lr': 6.496646473220513e-07, 'samples': 28147968, 'steps': 146603, 'loss/train': 0.3515785336494446} 08/31/2021 15:48:02 - INFO - __main__ - Step 146605: {'lr': 6.492823760776146e-07, 'samples': 28148160, 'steps': 146604, 'loss/train': 0.7057737708091736} 08/31/2021 15:48:03 - INFO - __main__ - Step 146606: {'lr': 6.489002171867764e-07, 'samples': 28148352, 'steps': 146605, 'loss/train': 0.20612336695194244} 08/31/2021 15:48:03 - INFO - __main__ - Step 146607: {'lr': 6.485181706496756e-07, 'samples': 28148544, 'steps': 146606, 'loss/train': 1.4270497560501099} 08/31/2021 15:48:03 - INFO - __main__ - Step 146608: {'lr': 6.481362364665066e-07, 'samples': 28148736, 'steps': 146607, 'loss/train': 0.8721032738685608} 08/31/2021 15:48:04 - INFO - __main__ - Step 146609: {'lr': 6.477544146374359e-07, 'samples': 28148928, 'steps': 146608, 'loss/train': 1.2362251281738281} 08/31/2021 15:48:05 - INFO - __main__ - Step 146610: {'lr': 6.473727051626299e-07, 'samples': 28149120, 'steps': 146609, 'loss/train': 1.5757378339767456} 08/31/2021 15:48:06 - INFO - __main__ - Step 146611: {'lr': 6.46991108042283e-07, 'samples': 28149312, 'steps': 146610, 'loss/train': 0.9283193945884705} 08/31/2021 15:48:06 - INFO - __main__ - Step 146612: {'lr': 6.466096232765617e-07, 'samples': 28149504, 'steps': 146611, 'loss/train': 0.9546610116958618} 08/31/2021 15:48:06 - INFO - __main__ - Step 146613: {'lr': 6.462282508656326e-07, 'samples': 28149696, 'steps': 146612, 'loss/train': 1.2714989185333252} 08/31/2021 15:48:07 - INFO - __main__ - Step 146614: {'lr': 6.458469908096342e-07, 'samples': 28149888, 'steps': 146613, 'loss/train': 0.6341965198516846} 08/31/2021 15:48:09 - INFO - __main__ - Step 146615: {'lr': 6.454658431088167e-07, 'samples': 28150080, 'steps': 146614, 'loss/train': 0.810292661190033} 08/31/2021 15:48:10 - INFO - __main__ - Step 146616: {'lr': 6.450848077632632e-07, 'samples': 28150272, 'steps': 146615, 'loss/train': 0.7028378248214722} 08/31/2021 15:48:10 - INFO - __main__ - Step 146617: {'lr': 6.447038847731957e-07, 'samples': 28150464, 'steps': 146616, 'loss/train': 1.0073614120483398} 08/31/2021 15:48:10 - INFO - __main__ - Step 146618: {'lr': 6.443230741387807e-07, 'samples': 28150656, 'steps': 146617, 'loss/train': 1.086380958557129} 08/31/2021 15:48:11 - INFO - __main__ - Step 146619: {'lr': 6.439423758601848e-07, 'samples': 28150848, 'steps': 146618, 'loss/train': 1.0203386545181274} 08/31/2021 15:48:12 - INFO - __main__ - Step 146620: {'lr': 6.435617899376023e-07, 'samples': 28151040, 'steps': 146619, 'loss/train': 1.1589913368225098} 08/31/2021 15:48:12 - INFO - __main__ - Step 146621: {'lr': 6.43181316371172e-07, 'samples': 28151232, 'steps': 146620, 'loss/train': 0.7114095687866211} 08/31/2021 15:48:13 - INFO - __main__ - Step 146622: {'lr': 6.428009551610603e-07, 'samples': 28151424, 'steps': 146621, 'loss/train': 1.332844614982605} 08/31/2021 15:48:13 - INFO - __main__ - Step 146623: {'lr': 6.424207063074617e-07, 'samples': 28151616, 'steps': 146622, 'loss/train': 0.21209610998630524} 08/31/2021 15:48:14 - INFO - __main__ - Step 146624: {'lr': 6.420405698105425e-07, 'samples': 28151808, 'steps': 146623, 'loss/train': 0.8086966872215271} 08/31/2021 15:48:15 - INFO - __main__ - Step 146625: {'lr': 6.416605456704694e-07, 'samples': 28152000, 'steps': 146624, 'loss/train': 1.3935494422912598} 08/31/2021 15:48:15 - INFO - __main__ - Step 146626: {'lr': 6.412806338874366e-07, 'samples': 28152192, 'steps': 146625, 'loss/train': 0.266196608543396} 08/31/2021 15:48:16 - INFO - __main__ - Step 146627: {'lr': 6.409008344615553e-07, 'samples': 28152384, 'steps': 146626, 'loss/train': 1.2210605144500732} 08/31/2021 15:48:16 - INFO - __main__ - Step 146628: {'lr': 6.40521147393075e-07, 'samples': 28152576, 'steps': 146627, 'loss/train': 0.41528621315956116} 08/31/2021 15:48:16 - INFO - __main__ - Step 146629: {'lr': 6.401415726821069e-07, 'samples': 28152768, 'steps': 146628, 'loss/train': 1.1234276294708252} 08/31/2021 15:48:18 - INFO - __main__ - Step 146630: {'lr': 6.397621103288454e-07, 'samples': 28152960, 'steps': 146629, 'loss/train': 1.3945444822311401} 08/31/2021 15:48:18 - INFO - __main__ - Step 146631: {'lr': 6.393827603334568e-07, 'samples': 28153152, 'steps': 146630, 'loss/train': 0.9539845585823059} 08/31/2021 15:48:19 - INFO - __main__ - Step 146632: {'lr': 6.390035226961355e-07, 'samples': 28153344, 'steps': 146631, 'loss/train': 1.3862332105636597} 08/31/2021 15:48:19 - INFO - __main__ - Step 146633: {'lr': 6.386243974170203e-07, 'samples': 28153536, 'steps': 146632, 'loss/train': 0.7565214037895203} 08/31/2021 15:48:20 - INFO - __main__ - Step 146634: {'lr': 6.382453844962776e-07, 'samples': 28153728, 'steps': 146633, 'loss/train': 1.6239088773727417} 08/31/2021 15:48:21 - INFO - __main__ - Step 146635: {'lr': 6.378664839341019e-07, 'samples': 28153920, 'steps': 146634, 'loss/train': 0.9288923144340515} 08/31/2021 15:48:22 - INFO - __main__ - Step 146636: {'lr': 6.374876957306597e-07, 'samples': 28154112, 'steps': 146635, 'loss/train': 1.1081491708755493} 08/31/2021 15:48:22 - INFO - __main__ - Step 146637: {'lr': 6.371090198861174e-07, 'samples': 28154304, 'steps': 146636, 'loss/train': 1.359301209449768} 08/31/2021 15:48:22 - INFO - __main__ - Step 146638: {'lr': 6.367304564006415e-07, 'samples': 28154496, 'steps': 146637, 'loss/train': 0.23754411935806274} 08/31/2021 15:48:23 - INFO - __main__ - Step 146639: {'lr': 6.363520052743988e-07, 'samples': 28154688, 'steps': 146638, 'loss/train': 0.03695805370807648} 08/31/2021 15:48:24 - INFO - __main__ - Step 146640: {'lr': 6.359736665075832e-07, 'samples': 28154880, 'steps': 146639, 'loss/train': 0.8529530167579651} 08/31/2021 15:48:25 - INFO - __main__ - Step 146641: {'lr': 6.355954401003339e-07, 'samples': 28155072, 'steps': 146640, 'loss/train': 0.6600702404975891} 08/31/2021 15:48:25 - INFO - __main__ - Step 146642: {'lr': 6.352173260528727e-07, 'samples': 28155264, 'steps': 146641, 'loss/train': 1.0505526065826416} 08/31/2021 15:48:25 - INFO - __main__ - Step 146643: {'lr': 6.348393243653106e-07, 'samples': 28155456, 'steps': 146642, 'loss/train': 0.7169730067253113} 08/31/2021 15:48:26 - INFO - __main__ - Step 146644: {'lr': 6.344614350378419e-07, 'samples': 28155648, 'steps': 146643, 'loss/train': 1.243630290031433} 08/31/2021 15:48:27 - INFO - __main__ - Step 146645: {'lr': 6.340836580706332e-07, 'samples': 28155840, 'steps': 146644, 'loss/train': 0.6686453223228455} 08/31/2021 15:48:28 - INFO - __main__ - Step 146646: {'lr': 6.337059934638511e-07, 'samples': 28156032, 'steps': 146645, 'loss/train': 0.7497760057449341} 08/31/2021 15:48:28 - INFO - __main__ - Step 146647: {'lr': 6.333284412176899e-07, 'samples': 28156224, 'steps': 146646, 'loss/train': 1.189753532409668} 08/31/2021 15:48:28 - INFO - __main__ - Step 146648: {'lr': 6.329510013322881e-07, 'samples': 28156416, 'steps': 146647, 'loss/train': 1.0204190015792847} 08/31/2021 15:48:29 - INFO - __main__ - Step 146649: {'lr': 6.325736738078403e-07, 'samples': 28156608, 'steps': 146648, 'loss/train': 0.6323971748352051} 08/31/2021 15:48:29 - INFO - __main__ - Step 146650: {'lr': 6.321964586445128e-07, 'samples': 28156800, 'steps': 146649, 'loss/train': 0.8778408169746399} 08/31/2021 15:48:31 - INFO - __main__ - Step 146651: {'lr': 6.318193558424722e-07, 'samples': 28156992, 'steps': 146650, 'loss/train': 1.354294776916504} 08/31/2021 15:48:31 - INFO - __main__ - Step 146652: {'lr': 6.314423654018575e-07, 'samples': 28157184, 'steps': 146651, 'loss/train': 0.9486708641052246} 08/31/2021 15:48:31 - INFO - __main__ - Step 146653: {'lr': 6.310654873228905e-07, 'samples': 28157376, 'steps': 146652, 'loss/train': 1.012181282043457} 08/31/2021 15:48:32 - INFO - __main__ - Step 146654: {'lr': 6.306887216057377e-07, 'samples': 28157568, 'steps': 146653, 'loss/train': 0.766834020614624} 08/31/2021 15:48:32 - INFO - __main__ - Step 146655: {'lr': 6.303120682505104e-07, 'samples': 28157760, 'steps': 146654, 'loss/train': 1.594043493270874} 08/31/2021 15:48:34 - INFO - __main__ - Step 146656: {'lr': 6.299355272574303e-07, 'samples': 28157952, 'steps': 146655, 'loss/train': 1.462342381477356} 08/31/2021 15:48:34 - INFO - __main__ - Step 146657: {'lr': 6.295590986266641e-07, 'samples': 28158144, 'steps': 146656, 'loss/train': 0.8087441921234131} 08/31/2021 15:48:35 - INFO - __main__ - Step 146658: {'lr': 6.291827823583507e-07, 'samples': 28158336, 'steps': 146657, 'loss/train': 1.5531423091888428} 08/31/2021 15:48:35 - INFO - __main__ - Step 146659: {'lr': 6.288065784526842e-07, 'samples': 28158528, 'steps': 146658, 'loss/train': 1.2204005718231201} 08/31/2021 15:48:35 - INFO - __main__ - Step 146660: {'lr': 6.284304869098312e-07, 'samples': 28158720, 'steps': 146659, 'loss/train': 0.19491688907146454} 08/31/2021 15:48:37 - INFO - __main__ - Step 146661: {'lr': 6.280545077299582e-07, 'samples': 28158912, 'steps': 146660, 'loss/train': 1.0564587116241455} 08/31/2021 15:48:37 - INFO - __main__ - Step 146662: {'lr': 6.276786409132318e-07, 'samples': 28159104, 'steps': 146661, 'loss/train': 0.9948574304580688} 08/31/2021 15:48:38 - INFO - __main__ - Step 146663: {'lr': 6.273028864598462e-07, 'samples': 28159296, 'steps': 146662, 'loss/train': 1.7555060386657715} 08/31/2021 15:48:38 - INFO - __main__ - Step 146664: {'lr': 6.269272443699403e-07, 'samples': 28159488, 'steps': 146663, 'loss/train': 0.7027807235717773} 08/31/2021 15:48:38 - INFO - __main__ - Step 146665: {'lr': 6.265517146436806e-07, 'samples': 28159680, 'steps': 146664, 'loss/train': 0.3768279254436493} 08/31/2021 15:48:40 - INFO - __main__ - Step 146666: {'lr': 6.261762972812612e-07, 'samples': 28159872, 'steps': 146665, 'loss/train': 0.905976414680481} 08/31/2021 15:48:40 - INFO - __main__ - Step 146667: {'lr': 6.25800992282849e-07, 'samples': 28160064, 'steps': 146666, 'loss/train': 0.48629438877105713} 08/31/2021 15:48:41 - INFO - __main__ - Step 146668: {'lr': 6.254257996485824e-07, 'samples': 28160256, 'steps': 146667, 'loss/train': 0.9253823161125183} 08/31/2021 15:48:41 - INFO - __main__ - Step 146669: {'lr': 6.250507193786558e-07, 'samples': 28160448, 'steps': 146668, 'loss/train': 2.330805778503418} 08/31/2021 15:48:41 - INFO - __main__ - Step 146670: {'lr': 6.24675751473236e-07, 'samples': 28160640, 'steps': 146669, 'loss/train': 1.0161014795303345} 08/31/2021 15:48:44 - INFO - __main__ - Step 146671: {'lr': 6.243008959324892e-07, 'samples': 28160832, 'steps': 146670, 'loss/train': 0.9709852933883667} 08/31/2021 15:48:45 - INFO - __main__ - Step 146672: {'lr': 6.239261527565821e-07, 'samples': 28161024, 'steps': 146671, 'loss/train': 0.9771214127540588} 08/31/2021 15:48:45 - INFO - __main__ - Step 146673: {'lr': 6.235515219456811e-07, 'samples': 28161216, 'steps': 146672, 'loss/train': 1.167862892150879} 08/31/2021 15:48:45 - INFO - __main__ - Step 146674: {'lr': 6.231770034999529e-07, 'samples': 28161408, 'steps': 146673, 'loss/train': 0.9887828826904297} 08/31/2021 15:48:46 - INFO - __main__ - Step 146675: {'lr': 6.228025974195916e-07, 'samples': 28161600, 'steps': 146674, 'loss/train': 0.14746995270252228} 08/31/2021 15:48:46 - INFO - __main__ - Step 146676: {'lr': 6.224283037047362e-07, 'samples': 28161792, 'steps': 146675, 'loss/train': 0.024238184094429016} 08/31/2021 15:48:46 - INFO - __main__ - Step 146677: {'lr': 6.220541223555809e-07, 'samples': 28161984, 'steps': 146676, 'loss/train': 0.04248055815696716} 08/31/2021 15:48:48 - INFO - __main__ - Step 146678: {'lr': 6.216800533722644e-07, 'samples': 28162176, 'steps': 146677, 'loss/train': 1.0868266820907593} 08/31/2021 15:48:48 - INFO - __main__ - Step 146679: {'lr': 6.213060967549811e-07, 'samples': 28162368, 'steps': 146678, 'loss/train': 1.0929538011550903} 08/31/2021 15:48:49 - INFO - __main__ - Step 146680: {'lr': 6.209322525038697e-07, 'samples': 28162560, 'steps': 146679, 'loss/train': 0.06736812740564346} 08/31/2021 15:48:49 - INFO - __main__ - Step 146681: {'lr': 6.205585206191522e-07, 'samples': 28162752, 'steps': 146680, 'loss/train': 0.27127954363822937} 08/31/2021 15:48:49 - INFO - __main__ - Step 146682: {'lr': 6.201849011009397e-07, 'samples': 28162944, 'steps': 146681, 'loss/train': 1.5929546356201172} 08/31/2021 15:48:51 - INFO - __main__ - Step 146683: {'lr': 6.198113939494265e-07, 'samples': 28163136, 'steps': 146682, 'loss/train': 0.7243564128875732} 08/31/2021 15:48:51 - INFO - __main__ - Step 146684: {'lr': 6.194379991647792e-07, 'samples': 28163328, 'steps': 146683, 'loss/train': 1.1270606517791748} 08/31/2021 15:48:52 - INFO - __main__ - Step 146685: {'lr': 6.190647167471641e-07, 'samples': 28163520, 'steps': 146684, 'loss/train': 0.25371649861335754} 08/31/2021 15:48:52 - INFO - __main__ - Step 146686: {'lr': 6.18691546696748e-07, 'samples': 28163712, 'steps': 146685, 'loss/train': 1.3719329833984375} 08/31/2021 15:48:52 - INFO - __main__ - Step 146687: {'lr': 6.183184890136973e-07, 'samples': 28163904, 'steps': 146686, 'loss/train': 1.3949404954910278} 08/31/2021 15:48:54 - INFO - __main__ - Step 146688: {'lr': 6.179455436982062e-07, 'samples': 28164096, 'steps': 146687, 'loss/train': 0.3292410969734192} 08/31/2021 15:48:54 - INFO - __main__ - Step 146689: {'lr': 6.175727107504136e-07, 'samples': 28164288, 'steps': 146688, 'loss/train': 1.3673429489135742} 08/31/2021 15:48:55 - INFO - __main__ - Step 146690: {'lr': 6.171999901704861e-07, 'samples': 28164480, 'steps': 146689, 'loss/train': 1.5586518049240112} 08/31/2021 15:48:55 - INFO - __main__ - Step 146691: {'lr': 6.168273819585901e-07, 'samples': 28164672, 'steps': 146690, 'loss/train': 1.023390293121338} 08/31/2021 15:48:56 - INFO - __main__ - Step 146692: {'lr': 6.164548861149199e-07, 'samples': 28164864, 'steps': 146691, 'loss/train': 1.5955244302749634} 08/31/2021 15:48:57 - INFO - __main__ - Step 146693: {'lr': 6.160825026396144e-07, 'samples': 28165056, 'steps': 146692, 'loss/train': 1.6389291286468506} 08/31/2021 15:48:57 - INFO - __main__ - Step 146694: {'lr': 6.157102315328677e-07, 'samples': 28165248, 'steps': 146693, 'loss/train': 0.2487802505493164} 08/31/2021 15:48:58 - INFO - __main__ - Step 146695: {'lr': 6.153380727948188e-07, 'samples': 28165440, 'steps': 146694, 'loss/train': 0.9060778617858887} 08/31/2021 15:48:58 - INFO - __main__ - Step 146696: {'lr': 6.149660264256618e-07, 'samples': 28165632, 'steps': 146695, 'loss/train': 1.0987907648086548} 08/31/2021 15:48:58 - INFO - __main__ - Step 146697: {'lr': 6.145940924255356e-07, 'samples': 28165824, 'steps': 146696, 'loss/train': 0.7840496301651001} 08/31/2021 15:49:00 - INFO - __main__ - Step 146698: {'lr': 6.142222707946343e-07, 'samples': 28166016, 'steps': 146697, 'loss/train': 0.754593551158905} 08/31/2021 15:49:00 - INFO - __main__ - Step 146699: {'lr': 6.138505615331246e-07, 'samples': 28166208, 'steps': 146698, 'loss/train': 1.4372146129608154} 08/31/2021 15:49:01 - INFO - __main__ - Step 146700: {'lr': 6.134789646411732e-07, 'samples': 28166400, 'steps': 146699, 'loss/train': 1.311166524887085} 08/31/2021 15:49:01 - INFO - __main__ - Step 146701: {'lr': 6.131074801189185e-07, 'samples': 28166592, 'steps': 146700, 'loss/train': 1.2332788705825806} 08/31/2021 15:49:01 - INFO - __main__ - Step 146702: {'lr': 6.12736107966555e-07, 'samples': 28166784, 'steps': 146701, 'loss/train': 0.9156632423400879} 08/31/2021 15:49:04 - INFO - __main__ - Step 146703: {'lr': 6.123648481842492e-07, 'samples': 28166976, 'steps': 146702, 'loss/train': 0.5665979385375977} 08/31/2021 15:49:04 - INFO - __main__ - Step 146704: {'lr': 6.119937007721677e-07, 'samples': 28167168, 'steps': 146703, 'loss/train': 1.1957623958587646} 08/31/2021 15:49:04 - INFO - __main__ - Step 146705: {'lr': 6.116226657304768e-07, 'samples': 28167360, 'steps': 146704, 'loss/train': 0.9607832431793213} 08/31/2021 15:49:05 - INFO - __main__ - Step 146706: {'lr': 6.112517430593156e-07, 'samples': 28167552, 'steps': 146705, 'loss/train': 0.4622051417827606} 08/31/2021 15:49:05 - INFO - __main__ - Step 146707: {'lr': 6.10880932758906e-07, 'samples': 28167744, 'steps': 146706, 'loss/train': 1.136648416519165} 08/31/2021 15:49:05 - INFO - __main__ - Step 146708: {'lr': 6.10510234829359e-07, 'samples': 28167936, 'steps': 146707, 'loss/train': 1.130346655845642} 08/31/2021 15:49:06 - INFO - __main__ - Step 146709: {'lr': 6.101396492708966e-07, 'samples': 28168128, 'steps': 146708, 'loss/train': 1.5629959106445312} 08/31/2021 15:49:07 - INFO - __main__ - Step 146710: {'lr': 6.0976917608363e-07, 'samples': 28168320, 'steps': 146709, 'loss/train': 0.8623641133308411} 08/31/2021 15:49:08 - INFO - __main__ - Step 146711: {'lr': 6.093988152677532e-07, 'samples': 28168512, 'steps': 146710, 'loss/train': 1.5580620765686035} 08/31/2021 15:49:08 - INFO - __main__ - Step 146712: {'lr': 6.090285668234607e-07, 'samples': 28168704, 'steps': 146711, 'loss/train': 0.978346586227417} 08/31/2021 15:49:08 - INFO - __main__ - Step 146713: {'lr': 6.086584307508635e-07, 'samples': 28168896, 'steps': 146712, 'loss/train': 1.3007909059524536} 08/31/2021 15:49:09 - INFO - __main__ - Step 146714: {'lr': 6.082884070501838e-07, 'samples': 28169088, 'steps': 146713, 'loss/train': 0.5707855224609375} 08/31/2021 15:49:10 - INFO - __main__ - Step 146715: {'lr': 6.079184957215322e-07, 'samples': 28169280, 'steps': 146714, 'loss/train': 0.12579938769340515} 08/31/2021 15:49:11 - INFO - __main__ - Step 146716: {'lr': 6.075486967651312e-07, 'samples': 28169472, 'steps': 146715, 'loss/train': 1.059232234954834} 08/31/2021 15:49:11 - INFO - __main__ - Step 146717: {'lr': 6.071790101810915e-07, 'samples': 28169664, 'steps': 146716, 'loss/train': 0.5786444544792175} 08/31/2021 15:49:11 - INFO - __main__ - Step 146718: {'lr': 6.068094359696352e-07, 'samples': 28169856, 'steps': 146717, 'loss/train': 1.2741503715515137} 08/31/2021 15:49:12 - INFO - __main__ - Step 146719: {'lr': 6.064399741308735e-07, 'samples': 28170048, 'steps': 146718, 'loss/train': 1.0939514636993408} 08/31/2021 15:49:13 - INFO - __main__ - Step 146720: {'lr': 6.060706246650283e-07, 'samples': 28170240, 'steps': 146719, 'loss/train': 1.0850815773010254} 08/31/2021 15:49:14 - INFO - __main__ - Step 146721: {'lr': 6.057013875722106e-07, 'samples': 28170432, 'steps': 146720, 'loss/train': 2.0102431774139404} 08/31/2021 15:49:14 - INFO - __main__ - Step 146722: {'lr': 6.053322628526425e-07, 'samples': 28170624, 'steps': 146721, 'loss/train': 0.900249183177948} 08/31/2021 15:49:14 - INFO - __main__ - Step 146723: {'lr': 6.049632505064628e-07, 'samples': 28170816, 'steps': 146722, 'loss/train': 1.3735042810440063} 08/31/2021 15:49:15 - INFO - __main__ - Step 146724: {'lr': 6.045943505338103e-07, 'samples': 28171008, 'steps': 146723, 'loss/train': 0.23059290647506714} 08/31/2021 15:49:18 - INFO - __main__ - Step 146725: {'lr': 6.04225562934907e-07, 'samples': 28171200, 'steps': 146724, 'loss/train': 0.7258821129798889} 08/31/2021 15:49:18 - INFO - __main__ - Step 146726: {'lr': 6.038568877098916e-07, 'samples': 28171392, 'steps': 146725, 'loss/train': 1.2232955694198608} 08/31/2021 15:49:18 - INFO - __main__ - Step 146727: {'lr': 6.03488324858903e-07, 'samples': 28171584, 'steps': 146726, 'loss/train': 0.264955997467041} 08/31/2021 15:49:19 - INFO - __main__ - Step 146728: {'lr': 6.031198743821631e-07, 'samples': 28171776, 'steps': 146727, 'loss/train': 2.0367441177368164} 08/31/2021 15:49:19 - INFO - __main__ - Step 146729: {'lr': 6.027515362798108e-07, 'samples': 28171968, 'steps': 146728, 'loss/train': 0.5401058793067932} 08/31/2021 15:49:19 - INFO - __main__ - Step 146730: {'lr': 6.02383310551985e-07, 'samples': 28172160, 'steps': 146729, 'loss/train': 0.5398393273353577} 08/31/2021 15:49:21 - INFO - __main__ - Step 146731: {'lr': 6.020151971989075e-07, 'samples': 28172352, 'steps': 146730, 'loss/train': 1.1947323083877563} 08/31/2021 15:49:21 - INFO - __main__ - Step 146732: {'lr': 6.016471962206893e-07, 'samples': 28172544, 'steps': 146731, 'loss/train': 1.3179583549499512} 08/31/2021 15:49:22 - INFO - __main__ - Step 146733: {'lr': 6.012793076175249e-07, 'samples': 28172736, 'steps': 146732, 'loss/train': 0.7638825178146362} 08/31/2021 15:49:22 - INFO - __main__ - Step 146734: {'lr': 6.009115313895808e-07, 'samples': 28172928, 'steps': 146733, 'loss/train': 1.742355465888977} 08/31/2021 15:49:23 - INFO - __main__ - Step 146735: {'lr': 6.005438675369956e-07, 'samples': 28173120, 'steps': 146734, 'loss/train': 1.598337173461914} 08/31/2021 15:49:23 - INFO - __main__ - Step 146736: {'lr': 6.001763160599916e-07, 'samples': 28173312, 'steps': 146735, 'loss/train': 1.3534595966339111} 08/31/2021 15:49:24 - INFO - __main__ - Step 146737: {'lr': 5.998088769586796e-07, 'samples': 28173504, 'steps': 146736, 'loss/train': 1.6624559164047241} 08/31/2021 15:49:25 - INFO - __main__ - Step 146738: {'lr': 5.99441550233254e-07, 'samples': 28173696, 'steps': 146737, 'loss/train': 1.0010831356048584} 08/31/2021 15:49:25 - INFO - __main__ - Step 146739: {'lr': 5.990743358838536e-07, 'samples': 28173888, 'steps': 146738, 'loss/train': 0.9211687445640564} 08/31/2021 15:49:26 - INFO - __main__ - Step 146740: {'lr': 5.987072339106725e-07, 'samples': 28174080, 'steps': 146739, 'loss/train': 0.28539684414863586} 08/31/2021 15:49:26 - INFO - __main__ - Step 146741: {'lr': 5.983402443138774e-07, 'samples': 28174272, 'steps': 146740, 'loss/train': 1.2739825248718262} 08/31/2021 15:49:27 - INFO - __main__ - Step 146742: {'lr': 5.979733670936072e-07, 'samples': 28174464, 'steps': 146741, 'loss/train': 0.18764401972293854} 08/31/2021 15:49:28 - INFO - __main__ - Step 146743: {'lr': 5.976066022500559e-07, 'samples': 28174656, 'steps': 146742, 'loss/train': 1.0238393545150757} 08/31/2021 15:49:28 - INFO - __main__ - Step 146744: {'lr': 5.972399497833625e-07, 'samples': 28174848, 'steps': 146743, 'loss/train': 1.2469218969345093} 08/31/2021 15:49:29 - INFO - __main__ - Step 146745: {'lr': 5.968734096936935e-07, 'samples': 28175040, 'steps': 146744, 'loss/train': 1.4550986289978027} 08/31/2021 15:49:29 - INFO - __main__ - Step 146746: {'lr': 5.965069819812429e-07, 'samples': 28175232, 'steps': 146745, 'loss/train': 1.308447241783142} 08/31/2021 15:49:31 - INFO - __main__ - Step 146747: {'lr': 5.9614066664615e-07, 'samples': 28175424, 'steps': 146746, 'loss/train': 1.2533093690872192} 08/31/2021 15:49:31 - INFO - __main__ - Step 146748: {'lr': 5.957744636886087e-07, 'samples': 28175616, 'steps': 146747, 'loss/train': 1.2908707857131958} 08/31/2021 15:49:31 - INFO - __main__ - Step 146749: {'lr': 5.954083731087301e-07, 'samples': 28175808, 'steps': 146748, 'loss/train': 0.28610488772392273} 08/31/2021 15:49:32 - INFO - __main__ - Step 146750: {'lr': 5.950423949067362e-07, 'samples': 28176000, 'steps': 146749, 'loss/train': 1.5111143589019775} 08/31/2021 15:49:32 - INFO - __main__ - Step 146751: {'lr': 5.946765290827383e-07, 'samples': 28176192, 'steps': 146750, 'loss/train': 1.888665795326233} 08/31/2021 15:49:34 - INFO - __main__ - Step 146752: {'lr': 5.943107756369582e-07, 'samples': 28176384, 'steps': 146751, 'loss/train': 0.778156042098999} 08/31/2021 15:49:34 - INFO - __main__ - Step 146753: {'lr': 5.939451345695345e-07, 'samples': 28176576, 'steps': 146752, 'loss/train': 1.767214059829712} 08/31/2021 15:49:34 - INFO - __main__ - Step 146754: {'lr': 5.935796058806064e-07, 'samples': 28176768, 'steps': 146753, 'loss/train': 0.805902898311615} 08/31/2021 15:49:35 - INFO - __main__ - Step 146755: {'lr': 5.932141895703957e-07, 'samples': 28176960, 'steps': 146754, 'loss/train': 1.1693451404571533} 08/31/2021 15:49:35 - INFO - __main__ - Step 146756: {'lr': 5.928488856390136e-07, 'samples': 28177152, 'steps': 146755, 'loss/train': 0.8725908994674683} 08/31/2021 15:49:37 - INFO - __main__ - Step 146757: {'lr': 5.92483694086654e-07, 'samples': 28177344, 'steps': 146756, 'loss/train': 1.4350957870483398} 08/31/2021 15:49:37 - INFO - __main__ - Step 146758: {'lr': 5.921186149134561e-07, 'samples': 28177536, 'steps': 146757, 'loss/train': 0.8159868717193604} 08/31/2021 15:49:38 - INFO - __main__ - Step 146759: {'lr': 5.91753648119614e-07, 'samples': 28177728, 'steps': 146758, 'loss/train': 0.7336620092391968} 08/31/2021 15:49:38 - INFO - __main__ - Step 146760: {'lr': 5.913887937052664e-07, 'samples': 28177920, 'steps': 146759, 'loss/train': 0.01421552337706089} 08/31/2021 15:49:39 - INFO - __main__ - Step 146761: {'lr': 5.910240516706078e-07, 'samples': 28178112, 'steps': 146760, 'loss/train': 1.0363171100616455} 08/31/2021 15:49:39 - INFO - __main__ - Step 146762: {'lr': 5.906594220157768e-07, 'samples': 28178304, 'steps': 146761, 'loss/train': 0.8448397517204285} 08/31/2021 15:49:40 - INFO - __main__ - Step 146763: {'lr': 5.902949047409401e-07, 'samples': 28178496, 'steps': 146762, 'loss/train': 1.2515887022018433} 08/31/2021 15:49:41 - INFO - __main__ - Step 146764: {'lr': 5.899304998462917e-07, 'samples': 28178688, 'steps': 146763, 'loss/train': 0.8201763033866882} 08/31/2021 15:49:41 - INFO - __main__ - Step 146765: {'lr': 5.89566207331943e-07, 'samples': 28178880, 'steps': 146764, 'loss/train': 0.03664536029100418} 08/31/2021 15:49:41 - INFO - __main__ - Step 146766: {'lr': 5.89202027198088e-07, 'samples': 28179072, 'steps': 146765, 'loss/train': 1.005171298980713} 08/31/2021 15:49:42 - INFO - __main__ - Step 146767: {'lr': 5.888379594449211e-07, 'samples': 28179264, 'steps': 146766, 'loss/train': 1.4636393785476685} 08/31/2021 15:49:42 - INFO - __main__ - Step 146768: {'lr': 5.884740040725533e-07, 'samples': 28179456, 'steps': 146767, 'loss/train': 1.3351672887802124} 08/31/2021 15:49:44 - INFO - __main__ - Step 146769: {'lr': 5.881101610811789e-07, 'samples': 28179648, 'steps': 146768, 'loss/train': 0.035197433084249496} 08/31/2021 15:49:44 - INFO - __main__ - Step 146770: {'lr': 5.877464304709367e-07, 'samples': 28179840, 'steps': 146769, 'loss/train': 1.2616126537322998} 08/31/2021 15:49:44 - INFO - __main__ - Step 146771: {'lr': 5.87382812242021e-07, 'samples': 28180032, 'steps': 146770, 'loss/train': 0.853895902633667} 08/31/2021 15:49:45 - INFO - __main__ - Step 146772: {'lr': 5.870193063945706e-07, 'samples': 28180224, 'steps': 146771, 'loss/train': 0.7462028861045837} 08/31/2021 15:49:45 - INFO - __main__ - Step 146773: {'lr': 5.866559129287797e-07, 'samples': 28180416, 'steps': 146772, 'loss/train': 0.9461861252784729} 08/31/2021 15:49:47 - INFO - __main__ - Step 146774: {'lr': 5.862926318447593e-07, 'samples': 28180608, 'steps': 146773, 'loss/train': 1.0010751485824585} 08/31/2021 15:49:47 - INFO - __main__ - Step 146775: {'lr': 5.859294631427314e-07, 'samples': 28180800, 'steps': 146774, 'loss/train': 0.4341460168361664} 08/31/2021 15:49:47 - INFO - __main__ - Step 146776: {'lr': 5.85566406822835e-07, 'samples': 28180992, 'steps': 146775, 'loss/train': 1.4378633499145508} 08/31/2021 15:49:48 - INFO - __main__ - Step 146777: {'lr': 5.852034628852366e-07, 'samples': 28181184, 'steps': 146776, 'loss/train': 1.398794174194336} 08/31/2021 15:49:48 - INFO - __main__ - Step 146778: {'lr': 5.848406313301025e-07, 'samples': 28181376, 'steps': 146777, 'loss/train': 0.9208905100822449} 08/31/2021 15:49:50 - INFO - __main__ - Step 146779: {'lr': 5.844779121575716e-07, 'samples': 28181568, 'steps': 146778, 'loss/train': 1.1077176332473755} 08/31/2021 15:49:50 - INFO - __main__ - Step 146780: {'lr': 5.841153053678383e-07, 'samples': 28181760, 'steps': 146779, 'loss/train': 1.0434094667434692} 08/31/2021 15:49:51 - INFO - __main__ - Step 146781: {'lr': 5.837528109610413e-07, 'samples': 28181952, 'steps': 146780, 'loss/train': 1.1566555500030518} 08/31/2021 15:49:51 - INFO - __main__ - Step 146782: {'lr': 5.833904289373748e-07, 'samples': 28182144, 'steps': 146781, 'loss/train': 1.267569899559021} 08/31/2021 15:49:51 - INFO - __main__ - Step 146783: {'lr': 5.830281592969777e-07, 'samples': 28182336, 'steps': 146782, 'loss/train': 1.2324105501174927} 08/31/2021 15:49:53 - INFO - __main__ - Step 146784: {'lr': 5.826660020400166e-07, 'samples': 28182528, 'steps': 146783, 'loss/train': 0.17552503943443298} 08/31/2021 15:49:53 - INFO - __main__ - Step 146785: {'lr': 5.823039571666577e-07, 'samples': 28182720, 'steps': 146784, 'loss/train': 0.9972260594367981} 08/31/2021 15:49:54 - INFO - __main__ - Step 146786: {'lr': 5.819420246770402e-07, 'samples': 28182912, 'steps': 146785, 'loss/train': 1.1706701517105103} 08/31/2021 15:49:54 - INFO - __main__ - Step 146787: {'lr': 5.815802045713858e-07, 'samples': 28183104, 'steps': 146786, 'loss/train': 1.1116549968719482} 08/31/2021 15:49:54 - INFO - __main__ - Step 146788: {'lr': 5.812184968498057e-07, 'samples': 28183296, 'steps': 146787, 'loss/train': 0.979037880897522} 08/31/2021 15:49:56 - INFO - __main__ - Step 146789: {'lr': 5.808569015124943e-07, 'samples': 28183488, 'steps': 146788, 'loss/train': 1.3123193979263306} 08/31/2021 15:49:57 - INFO - __main__ - Step 146790: {'lr': 5.804954185595901e-07, 'samples': 28183680, 'steps': 146789, 'loss/train': 1.0272040367126465} 08/31/2021 15:49:57 - INFO - __main__ - Step 146791: {'lr': 5.801340479912598e-07, 'samples': 28183872, 'steps': 146790, 'loss/train': 0.5824059844017029} 08/31/2021 15:49:57 - INFO - __main__ - Step 146792: {'lr': 5.797727898076699e-07, 'samples': 28184064, 'steps': 146791, 'loss/train': 1.189934253692627} 08/31/2021 15:49:58 - INFO - __main__ - Step 146793: {'lr': 5.794116440089869e-07, 'samples': 28184256, 'steps': 146792, 'loss/train': 1.016689419746399} 08/31/2021 15:49:59 - INFO - __main__ - Step 146794: {'lr': 5.790506105953774e-07, 'samples': 28184448, 'steps': 146793, 'loss/train': 0.9172078371047974} 08/31/2021 15:49:59 - INFO - __main__ - Step 146795: {'lr': 5.786896895670079e-07, 'samples': 28184640, 'steps': 146794, 'loss/train': 1.0039726495742798} 08/31/2021 15:50:00 - INFO - __main__ - Step 146796: {'lr': 5.783288809240451e-07, 'samples': 28184832, 'steps': 146795, 'loss/train': 1.13925302028656} 08/31/2021 15:50:00 - INFO - __main__ - Step 146797: {'lr': 5.779681846665996e-07, 'samples': 28185024, 'steps': 146796, 'loss/train': 0.9719833135604858} 08/31/2021 15:50:01 - INFO - __main__ - Step 146798: {'lr': 5.776076007948939e-07, 'samples': 28185216, 'steps': 146797, 'loss/train': 1.1715446710586548} 08/31/2021 15:50:02 - INFO - __main__ - Step 146799: {'lr': 5.772471293090665e-07, 'samples': 28185408, 'steps': 146798, 'loss/train': 1.1995681524276733} 08/31/2021 15:50:02 - INFO - __main__ - Step 146800: {'lr': 5.76886770209284e-07, 'samples': 28185600, 'steps': 146799, 'loss/train': 0.23314259946346283} 08/31/2021 15:50:03 - INFO - __main__ - Step 146801: {'lr': 5.765265234957129e-07, 'samples': 28185792, 'steps': 146800, 'loss/train': 1.115456461906433} 08/31/2021 15:50:03 - INFO - __main__ - Step 146802: {'lr': 5.76166389168492e-07, 'samples': 28185984, 'steps': 146801, 'loss/train': 0.9865559339523315} 08/31/2021 15:50:04 - INFO - __main__ - Step 146803: {'lr': 5.758063672278157e-07, 'samples': 28186176, 'steps': 146802, 'loss/train': 0.5519859194755554} 08/31/2021 15:50:05 - INFO - __main__ - Step 146804: {'lr': 5.754464576738505e-07, 'samples': 28186368, 'steps': 146803, 'loss/train': 1.5612568855285645} 08/31/2021 15:50:05 - INFO - __main__ - Step 146805: {'lr': 5.750866605067073e-07, 'samples': 28186560, 'steps': 146804, 'loss/train': 1.2749416828155518} 08/31/2021 15:50:06 - INFO - __main__ - Step 146806: {'lr': 5.747269757265805e-07, 'samples': 28186752, 'steps': 146805, 'loss/train': 1.1372674703598022} 08/31/2021 15:50:06 - INFO - __main__ - Step 146807: {'lr': 5.743674033336644e-07, 'samples': 28186944, 'steps': 146806, 'loss/train': 0.8045451045036316} 08/31/2021 15:50:07 - INFO - __main__ - Step 146808: {'lr': 5.740079433280698e-07, 'samples': 28187136, 'steps': 146807, 'loss/train': 1.7427937984466553} 08/31/2021 15:50:07 - INFO - __main__ - Step 146809: {'lr': 5.736485957099913e-07, 'samples': 28187328, 'steps': 146808, 'loss/train': 0.9685978889465332} 08/31/2021 15:50:09 - INFO - __main__ - Step 146810: {'lr': 5.732893604795675e-07, 'samples': 28187520, 'steps': 146809, 'loss/train': 0.2245347499847412} 08/31/2021 15:50:09 - INFO - __main__ - Step 146811: {'lr': 5.729302376369649e-07, 'samples': 28187712, 'steps': 146810, 'loss/train': 1.0839462280273438} 08/31/2021 15:50:10 - INFO - __main__ - Step 146812: {'lr': 5.725712271823503e-07, 'samples': 28187904, 'steps': 146811, 'loss/train': 1.0867500305175781} 08/31/2021 15:50:10 - INFO - __main__ - Step 146813: {'lr': 5.722123291158898e-07, 'samples': 28188096, 'steps': 146812, 'loss/train': 0.01568068191409111} 08/31/2021 15:50:10 - INFO - __main__ - Step 146814: {'lr': 5.718535434377503e-07, 'samples': 28188288, 'steps': 146813, 'loss/train': 1.5900354385375977} 08/31/2021 15:50:11 - INFO - __main__ - Step 146815: {'lr': 5.714948701480704e-07, 'samples': 28188480, 'steps': 146814, 'loss/train': 0.8157340288162231} 08/31/2021 15:50:12 - INFO - __main__ - Step 146816: {'lr': 5.711363092470167e-07, 'samples': 28188672, 'steps': 146815, 'loss/train': 0.7420286536216736} 08/31/2021 15:50:13 - INFO - __main__ - Step 146817: {'lr': 5.707778607347836e-07, 'samples': 28188864, 'steps': 146816, 'loss/train': 0.033035892993211746} 08/31/2021 15:50:13 - INFO - __main__ - Step 146818: {'lr': 5.704195246115096e-07, 'samples': 28189056, 'steps': 146817, 'loss/train': 1.427107810974121} 08/31/2021 15:50:14 - INFO - __main__ - Step 146819: {'lr': 5.700613008773336e-07, 'samples': 28189248, 'steps': 146818, 'loss/train': 0.8448241949081421} 08/31/2021 15:50:14 - INFO - __main__ - Step 146820: {'lr': 5.697031895324778e-07, 'samples': 28189440, 'steps': 146819, 'loss/train': 1.158225655555725} 08/31/2021 15:50:16 - INFO - __main__ - Step 146821: {'lr': 5.693451905770252e-07, 'samples': 28189632, 'steps': 146820, 'loss/train': 1.2883429527282715} 08/31/2021 15:50:17 - INFO - __main__ - Step 146822: {'lr': 5.689873040111982e-07, 'samples': 28189824, 'steps': 146821, 'loss/train': 0.7440025210380554} 08/31/2021 15:50:17 - INFO - __main__ - Step 146823: {'lr': 5.686295298351351e-07, 'samples': 28190016, 'steps': 146822, 'loss/train': 0.8171569108963013} 08/31/2021 15:50:17 - INFO - __main__ - Step 146824: {'lr': 5.682718680490029e-07, 'samples': 28190208, 'steps': 146823, 'loss/train': 1.0196181535720825} 08/31/2021 15:50:18 - INFO - __main__ - Step 146825: {'lr': 5.679143186529401e-07, 'samples': 28190400, 'steps': 146824, 'loss/train': 0.4885979890823364} 08/31/2021 15:50:19 - INFO - __main__ - Step 146826: {'lr': 5.675568816471411e-07, 'samples': 28190592, 'steps': 146825, 'loss/train': 0.6870715618133545} 08/31/2021 15:50:20 - INFO - __main__ - Step 146827: {'lr': 5.671995570317445e-07, 'samples': 28190784, 'steps': 146826, 'loss/train': 1.1648584604263306} 08/31/2021 15:50:20 - INFO - __main__ - Step 146828: {'lr': 5.668423448069171e-07, 'samples': 28190976, 'steps': 146827, 'loss/train': 1.2754418849945068} 08/31/2021 15:50:20 - INFO - __main__ - Step 146829: {'lr': 5.664852449728253e-07, 'samples': 28191168, 'steps': 146828, 'loss/train': 0.4451183080673218} 08/31/2021 15:50:21 - INFO - __main__ - Step 146830: {'lr': 5.661282575296079e-07, 'samples': 28191360, 'steps': 146829, 'loss/train': 0.3961230218410492} 08/31/2021 15:50:23 - INFO - __main__ - Step 146831: {'lr': 5.657713824774869e-07, 'samples': 28191552, 'steps': 146830, 'loss/train': 0.8728887438774109} 08/31/2021 15:50:23 - INFO - __main__ - Step 146832: {'lr': 5.654146198165455e-07, 'samples': 28191744, 'steps': 146831, 'loss/train': 1.2233456373214722} 08/31/2021 15:50:24 - INFO - __main__ - Step 146833: {'lr': 5.650579695469782e-07, 'samples': 28191936, 'steps': 146832, 'loss/train': 1.719183087348938} 08/31/2021 15:50:24 - INFO - __main__ - Step 146834: {'lr': 5.647014316689513e-07, 'samples': 28192128, 'steps': 146833, 'loss/train': 1.0768333673477173} 08/31/2021 15:50:24 - INFO - __main__ - Step 146835: {'lr': 5.643450061826594e-07, 'samples': 28192320, 'steps': 146834, 'loss/train': 0.0711013451218605} 08/31/2021 15:50:25 - INFO - __main__ - Step 146836: {'lr': 5.639886930881854e-07, 'samples': 28192512, 'steps': 146835, 'loss/train': 1.0718988180160522} 08/31/2021 15:50:26 - INFO - __main__ - Step 146837: {'lr': 5.636324923857239e-07, 'samples': 28192704, 'steps': 146836, 'loss/train': 0.856525719165802} 08/31/2021 15:50:27 - INFO - __main__ - Step 146838: {'lr': 5.63276404075469e-07, 'samples': 28192896, 'steps': 146837, 'loss/train': 0.7384393215179443} 08/31/2021 15:50:27 - INFO - __main__ - Step 146839: {'lr': 5.629204281575317e-07, 'samples': 28193088, 'steps': 146838, 'loss/train': 0.7607845067977905} 08/31/2021 15:50:27 - INFO - __main__ - Step 146840: {'lr': 5.625645646321065e-07, 'samples': 28193280, 'steps': 146839, 'loss/train': 1.48887300491333} 08/31/2021 15:50:28 - INFO - __main__ - Step 146841: {'lr': 5.622088134993319e-07, 'samples': 28193472, 'steps': 146840, 'loss/train': 0.21379932761192322} 08/31/2021 15:50:29 - INFO - __main__ - Step 146842: {'lr': 5.618531747593747e-07, 'samples': 28193664, 'steps': 146841, 'loss/train': 0.5890496969223022} 08/31/2021 15:50:30 - INFO - __main__ - Step 146843: {'lr': 5.614976484124013e-07, 'samples': 28193856, 'steps': 146842, 'loss/train': 1.4403945207595825} 08/31/2021 15:50:30 - INFO - __main__ - Step 146844: {'lr': 5.611422344585504e-07, 'samples': 28194048, 'steps': 146843, 'loss/train': 0.4848019778728485} 08/31/2021 15:50:30 - INFO - __main__ - Step 146845: {'lr': 5.607869328980164e-07, 'samples': 28194240, 'steps': 146844, 'loss/train': 0.2610398232936859} 08/31/2021 15:50:31 - INFO - __main__ - Step 146846: {'lr': 5.604317437309381e-07, 'samples': 28194432, 'steps': 146845, 'loss/train': 0.7160634994506836} 08/31/2021 15:50:31 - INFO - __main__ - Step 146847: {'lr': 5.600766669574819e-07, 'samples': 28194624, 'steps': 146846, 'loss/train': 1.2881371974945068} 08/31/2021 15:50:33 - INFO - __main__ - Step 146848: {'lr': 5.597217025778145e-07, 'samples': 28194816, 'steps': 146847, 'loss/train': 1.2274446487426758} 08/31/2021 15:50:33 - INFO - __main__ - Step 146849: {'lr': 5.593668505921023e-07, 'samples': 28195008, 'steps': 146848, 'loss/train': 0.9828163385391235} 08/31/2021 15:50:33 - INFO - __main__ - Step 146850: {'lr': 5.590121110004565e-07, 'samples': 28195200, 'steps': 146849, 'loss/train': 0.9350258111953735} 08/31/2021 15:50:34 - INFO - __main__ - Step 146851: {'lr': 5.586574838030989e-07, 'samples': 28195392, 'steps': 146850, 'loss/train': 0.0591951459646225} 08/31/2021 15:50:34 - INFO - __main__ - Step 146852: {'lr': 5.583029690001407e-07, 'samples': 28195584, 'steps': 146851, 'loss/train': 0.9925699234008789} 08/31/2021 15:50:36 - INFO - __main__ - Step 146853: {'lr': 5.579485665917483e-07, 'samples': 28195776, 'steps': 146852, 'loss/train': 0.8029897212982178} 08/31/2021 15:50:37 - INFO - __main__ - Step 146854: {'lr': 5.575942765781161e-07, 'samples': 28195968, 'steps': 146853, 'loss/train': 1.0665850639343262} 08/31/2021 15:50:37 - INFO - __main__ - Step 146855: {'lr': 5.572400989593829e-07, 'samples': 28196160, 'steps': 146854, 'loss/train': 1.300750494003296} 08/31/2021 15:50:37 - INFO - __main__ - Step 146856: {'lr': 5.568860337357151e-07, 'samples': 28196352, 'steps': 146855, 'loss/train': 1.6892445087432861} 08/31/2021 15:50:38 - INFO - __main__ - Step 146857: {'lr': 5.565320809072516e-07, 'samples': 28196544, 'steps': 146856, 'loss/train': 1.5795307159423828} 08/31/2021 15:50:38 - INFO - __main__ - Step 146858: {'lr': 5.561782404741866e-07, 'samples': 28196736, 'steps': 146857, 'loss/train': 5.9014201164245605} 08/31/2021 15:50:38 - INFO - __main__ - Step 146859: {'lr': 5.558245124366312e-07, 'samples': 28196928, 'steps': 146858, 'loss/train': 5.7978620529174805} 08/31/2021 15:50:40 - INFO - __main__ - Step 146860: {'lr': 5.554708967947797e-07, 'samples': 28197120, 'steps': 146859, 'loss/train': 0.6735730767250061} 08/31/2021 15:50:40 - INFO - __main__ - Step 146861: {'lr': 5.551173935487986e-07, 'samples': 28197312, 'steps': 146860, 'loss/train': 0.0912000834941864} 08/31/2021 15:50:41 - INFO - __main__ - Step 146862: {'lr': 5.547640026988266e-07, 'samples': 28197504, 'steps': 146861, 'loss/train': 0.6707943081855774} 08/31/2021 15:50:41 - INFO - __main__ - Step 146863: {'lr': 5.544107242450302e-07, 'samples': 28197696, 'steps': 146862, 'loss/train': 0.8184758424758911} 08/31/2021 15:50:42 - INFO - __main__ - Step 146864: {'lr': 5.540575581875485e-07, 'samples': 28197888, 'steps': 146863, 'loss/train': 0.5891421437263489} 08/31/2021 15:50:43 - INFO - __main__ - Step 146865: {'lr': 5.537045045265754e-07, 'samples': 28198080, 'steps': 146864, 'loss/train': 0.6844558119773865} 08/31/2021 15:50:43 - INFO - __main__ - Step 146866: {'lr': 5.533515632622499e-07, 'samples': 28198272, 'steps': 146865, 'loss/train': 1.472096562385559} 08/31/2021 15:50:44 - INFO - __main__ - Step 146867: {'lr': 5.529987343947384e-07, 'samples': 28198464, 'steps': 146866, 'loss/train': 1.0008413791656494} 08/31/2021 15:50:44 - INFO - __main__ - Step 146868: {'lr': 5.526460179241799e-07, 'samples': 28198656, 'steps': 146867, 'loss/train': 0.6256805658340454} 08/31/2021 15:50:44 - INFO - __main__ - Step 146869: {'lr': 5.522934138507685e-07, 'samples': 28198848, 'steps': 146868, 'loss/train': 1.0154218673706055} 08/31/2021 15:50:46 - INFO - __main__ - Step 146870: {'lr': 5.51940922174643e-07, 'samples': 28199040, 'steps': 146869, 'loss/train': 1.6091283559799194} 08/31/2021 15:50:47 - INFO - __main__ - Step 146871: {'lr': 5.515885428959422e-07, 'samples': 28199232, 'steps': 146870, 'loss/train': 1.4470316171646118} 08/31/2021 15:50:47 - INFO - __main__ - Step 146872: {'lr': 5.512362760148603e-07, 'samples': 28199424, 'steps': 146871, 'loss/train': 0.7748004198074341} 08/31/2021 15:50:47 - INFO - __main__ - Step 146873: {'lr': 5.508841215315641e-07, 'samples': 28199616, 'steps': 146872, 'loss/train': 0.5133620500564575} 08/31/2021 15:50:48 - INFO - __main__ - Step 146874: {'lr': 5.505320794461643e-07, 'samples': 28199808, 'steps': 146873, 'loss/train': 0.988269567489624} 08/31/2021 15:50:50 - INFO - __main__ - Step 146875: {'lr': 5.501801497588555e-07, 'samples': 28200000, 'steps': 146874, 'loss/train': 1.3301531076431274} 08/31/2021 15:50:50 - INFO - __main__ - Step 146876: {'lr': 5.498283324697761e-07, 'samples': 28200192, 'steps': 146875, 'loss/train': 1.1099737882614136} 08/31/2021 15:50:51 - INFO - __main__ - Step 146877: {'lr': 5.494766275791208e-07, 'samples': 28200384, 'steps': 146876, 'loss/train': 1.140790343284607} 08/31/2021 15:50:51 - INFO - __main__ - Step 146878: {'lr': 5.491250350870003e-07, 'samples': 28200576, 'steps': 146877, 'loss/train': 0.850001335144043} 08/31/2021 15:50:51 - INFO - __main__ - Step 146879: {'lr': 5.487735549935813e-07, 'samples': 28200768, 'steps': 146878, 'loss/train': 1.0455515384674072} 08/31/2021 15:50:53 - INFO - __main__ - Step 146880: {'lr': 5.48422187299058e-07, 'samples': 28200960, 'steps': 146879, 'loss/train': 0.0224075298756361} 08/31/2021 15:50:53 - INFO - __main__ - Step 146881: {'lr': 5.480709320035693e-07, 'samples': 28201152, 'steps': 146880, 'loss/train': 1.223699927330017} 08/31/2021 15:50:54 - INFO - __main__ - Step 146882: {'lr': 5.477197891072538e-07, 'samples': 28201344, 'steps': 146881, 'loss/train': 1.4957634210586548} 08/31/2021 15:50:54 - INFO - __main__ - Step 146883: {'lr': 5.47368758610306e-07, 'samples': 28201536, 'steps': 146882, 'loss/train': 0.023150648921728134} 08/31/2021 15:50:55 - INFO - __main__ - Step 146884: {'lr': 5.470178405128368e-07, 'samples': 28201728, 'steps': 146883, 'loss/train': 0.3204248249530792} 08/31/2021 15:50:56 - INFO - __main__ - Step 146885: {'lr': 5.466670348150682e-07, 'samples': 28201920, 'steps': 146884, 'loss/train': 0.974912703037262} 08/31/2021 15:50:56 - INFO - __main__ - Step 146886: {'lr': 5.463163415170835e-07, 'samples': 28202112, 'steps': 146885, 'loss/train': 0.23830385506153107} 08/31/2021 15:50:57 - INFO - __main__ - Step 146887: {'lr': 5.459657606191049e-07, 'samples': 28202304, 'steps': 146886, 'loss/train': 1.3295098543167114} 08/31/2021 15:50:57 - INFO - __main__ - Step 146888: {'lr': 5.456152921212709e-07, 'samples': 28202496, 'steps': 146887, 'loss/train': 1.0626769065856934} 08/31/2021 15:50:58 - INFO - __main__ - Step 146889: {'lr': 5.452649360237205e-07, 'samples': 28202688, 'steps': 146888, 'loss/train': 1.4295692443847656} 08/31/2021 15:50:59 - INFO - __main__ - Step 146890: {'lr': 5.449146923266201e-07, 'samples': 28202880, 'steps': 146889, 'loss/train': 0.786999523639679} 08/31/2021 15:51:00 - INFO - __main__ - Step 146891: {'lr': 5.445645610301364e-07, 'samples': 28203072, 'steps': 146890, 'loss/train': 0.9176076054573059} 08/31/2021 15:51:00 - INFO - __main__ - Step 146892: {'lr': 5.442145421344358e-07, 'samples': 28203264, 'steps': 146891, 'loss/train': 0.06752276420593262} 08/31/2021 15:51:00 - INFO - __main__ - Step 146893: {'lr': 5.438646356396293e-07, 'samples': 28203456, 'steps': 146892, 'loss/train': 1.155289888381958} 08/31/2021 15:51:01 - INFO - __main__ - Step 146894: {'lr': 5.43514841545939e-07, 'samples': 28203648, 'steps': 146893, 'loss/train': 0.34838375449180603} 08/31/2021 15:51:01 - INFO - __main__ - Step 146895: {'lr': 5.431651598534759e-07, 'samples': 28203840, 'steps': 146894, 'loss/train': 1.8967984914779663} 08/31/2021 15:51:03 - INFO - __main__ - Step 146896: {'lr': 5.428155905624344e-07, 'samples': 28204032, 'steps': 146895, 'loss/train': 1.1524827480316162} 08/31/2021 15:51:03 - INFO - __main__ - Step 146897: {'lr': 5.424661336729253e-07, 'samples': 28204224, 'steps': 146896, 'loss/train': 0.03125375881791115} 08/31/2021 15:51:04 - INFO - __main__ - Step 146898: {'lr': 5.421167891851431e-07, 'samples': 28204416, 'steps': 146897, 'loss/train': 0.11073922365903854} 08/31/2021 15:51:04 - INFO - __main__ - Step 146899: {'lr': 5.417675570992264e-07, 'samples': 28204608, 'steps': 146898, 'loss/train': 0.9501520991325378} 08/31/2021 15:51:04 - INFO - __main__ - Step 146900: {'lr': 5.41418437415342e-07, 'samples': 28204800, 'steps': 146899, 'loss/train': 1.2854323387145996} 08/31/2021 15:51:05 - INFO - __main__ - Step 146901: {'lr': 5.41069430133656e-07, 'samples': 28204992, 'steps': 146900, 'loss/train': 0.7212469577789307} 08/31/2021 15:51:07 - INFO - __main__ - Step 146902: {'lr': 5.407205352543077e-07, 'samples': 28205184, 'steps': 146901, 'loss/train': 0.8053471446037292} 08/31/2021 15:51:07 - INFO - __main__ - Step 146903: {'lr': 5.403717527774632e-07, 'samples': 28205376, 'steps': 146902, 'loss/train': 1.509297251701355} 08/31/2021 15:51:08 - INFO - __main__ - Step 146904: {'lr': 5.400230827032615e-07, 'samples': 28205568, 'steps': 146903, 'loss/train': 1.0938377380371094} 08/31/2021 15:51:08 - INFO - __main__ - Step 146905: {'lr': 5.396745250318968e-07, 'samples': 28205760, 'steps': 146904, 'loss/train': 1.6468154191970825} 08/31/2021 15:51:08 - INFO - __main__ - Step 146906: {'lr': 5.39326079763508e-07, 'samples': 28205952, 'steps': 146905, 'loss/train': 0.016891496255993843} 08/31/2021 15:51:09 - INFO - __main__ - Step 146907: {'lr': 5.389777468982338e-07, 'samples': 28206144, 'steps': 146906, 'loss/train': 0.016313139349222183} 08/31/2021 15:51:10 - INFO - __main__ - Step 146908: {'lr': 5.386295264362407e-07, 'samples': 28206336, 'steps': 146907, 'loss/train': 0.14506085216999054} 08/31/2021 15:51:11 - INFO - __main__ - Step 146909: {'lr': 5.382814183777229e-07, 'samples': 28206528, 'steps': 146908, 'loss/train': 1.5660336017608643} 08/31/2021 15:51:11 - INFO - __main__ - Step 146910: {'lr': 5.379334227227639e-07, 'samples': 28206720, 'steps': 146909, 'loss/train': 1.1038235425949097} 08/31/2021 15:51:11 - INFO - __main__ - Step 146911: {'lr': 5.375855394716133e-07, 'samples': 28206912, 'steps': 146910, 'loss/train': 0.17306897044181824} 08/31/2021 15:51:12 - INFO - __main__ - Step 146912: {'lr': 5.372377686243546e-07, 'samples': 28207104, 'steps': 146911, 'loss/train': 1.3858810663223267} 08/31/2021 15:51:13 - INFO - __main__ - Step 146913: {'lr': 5.368901101811541e-07, 'samples': 28207296, 'steps': 146912, 'loss/train': 0.4174579977989197} 08/31/2021 15:51:14 - INFO - __main__ - Step 146914: {'lr': 5.365425641421784e-07, 'samples': 28207488, 'steps': 146913, 'loss/train': 0.14775674045085907} 08/31/2021 15:51:14 - INFO - __main__ - Step 146915: {'lr': 5.361951305075941e-07, 'samples': 28207680, 'steps': 146914, 'loss/train': 0.22979289293289185} 08/31/2021 15:51:14 - INFO - __main__ - Step 146916: {'lr': 5.358478092775676e-07, 'samples': 28207872, 'steps': 146915, 'loss/train': 0.7481430768966675} 08/31/2021 15:51:15 - INFO - __main__ - Step 146917: {'lr': 5.355006004522101e-07, 'samples': 28208064, 'steps': 146916, 'loss/train': 0.08951902389526367} 08/31/2021 15:51:16 - INFO - __main__ - Step 146918: {'lr': 5.351535040317435e-07, 'samples': 28208256, 'steps': 146917, 'loss/train': 1.312803030014038} 08/31/2021 15:51:17 - INFO - __main__ - Step 146919: {'lr': 5.348065200162511e-07, 'samples': 28208448, 'steps': 146918, 'loss/train': 1.1609435081481934} 08/31/2021 15:51:17 - INFO - __main__ - Step 146920: {'lr': 5.344596484059549e-07, 'samples': 28208640, 'steps': 146919, 'loss/train': 0.5579763054847717} 08/31/2021 15:51:17 - INFO - __main__ - Step 146921: {'lr': 5.341128892009661e-07, 'samples': 28208832, 'steps': 146920, 'loss/train': 0.7855011224746704} 08/31/2021 15:51:18 - INFO - __main__ - Step 146922: {'lr': 5.337662424014511e-07, 'samples': 28209024, 'steps': 146921, 'loss/train': 3.340231418609619} 08/31/2021 15:51:19 - INFO - __main__ - Step 146923: {'lr': 5.334197080075765e-07, 'samples': 28209216, 'steps': 146922, 'loss/train': 1.321990966796875} 08/31/2021 15:51:20 - INFO - __main__ - Step 146924: {'lr': 5.330732860195087e-07, 'samples': 28209408, 'steps': 146923, 'loss/train': 1.1594831943511963} 08/31/2021 15:51:20 - INFO - __main__ - Step 146925: {'lr': 5.327269764373588e-07, 'samples': 28209600, 'steps': 146924, 'loss/train': 0.9465349316596985} 08/31/2021 15:51:20 - INFO - __main__ - Step 146926: {'lr': 5.323807792613211e-07, 'samples': 28209792, 'steps': 146925, 'loss/train': 1.4597355127334595} 08/31/2021 15:51:21 - INFO - __main__ - Step 146927: {'lr': 5.320346944915621e-07, 'samples': 28209984, 'steps': 146926, 'loss/train': 0.6436576843261719} 08/31/2021 15:51:21 - INFO - __main__ - Step 146928: {'lr': 5.316887221282208e-07, 'samples': 28210176, 'steps': 146927, 'loss/train': 0.7362472414970398} 08/31/2021 15:51:23 - INFO - __main__ - Step 146929: {'lr': 5.313428621714356e-07, 'samples': 28210368, 'steps': 146928, 'loss/train': 1.3351448774337769} 08/31/2021 15:51:23 - INFO - __main__ - Step 146930: {'lr': 5.309971146213732e-07, 'samples': 28210560, 'steps': 146929, 'loss/train': 1.509209394454956} 08/31/2021 15:51:23 - INFO - __main__ - Step 146931: {'lr': 5.306514794782002e-07, 'samples': 28210752, 'steps': 146930, 'loss/train': 1.3650197982788086} 08/31/2021 15:51:24 - INFO - __main__ - Step 146932: {'lr': 5.303059567420554e-07, 'samples': 28210944, 'steps': 146931, 'loss/train': 1.1553194522857666} 08/31/2021 15:51:24 - INFO - __main__ - Step 146933: {'lr': 5.299605464131329e-07, 'samples': 28211136, 'steps': 146932, 'loss/train': 1.0178312063217163} 08/31/2021 15:51:26 - INFO - __main__ - Step 146934: {'lr': 5.296152484915439e-07, 'samples': 28211328, 'steps': 146933, 'loss/train': 0.25391411781311035} 08/31/2021 15:51:27 - INFO - __main__ - Step 146935: {'lr': 5.292700629774549e-07, 'samples': 28211520, 'steps': 146934, 'loss/train': 1.314357876777649} 08/31/2021 15:51:27 - INFO - __main__ - Step 146936: {'lr': 5.289249898710324e-07, 'samples': 28211712, 'steps': 146935, 'loss/train': 0.6963292956352234} 08/31/2021 15:51:27 - INFO - __main__ - Step 146937: {'lr': 5.28580029172443e-07, 'samples': 28211904, 'steps': 146936, 'loss/train': 1.538106083869934} 08/31/2021 15:51:28 - INFO - __main__ - Step 146938: {'lr': 5.282351808817975e-07, 'samples': 28212096, 'steps': 146937, 'loss/train': 1.2618809938430786} 08/31/2021 15:51:29 - INFO - __main__ - Step 146939: {'lr': 5.278904449992905e-07, 'samples': 28212288, 'steps': 146938, 'loss/train': 0.7646858096122742} 08/31/2021 15:51:29 - INFO - __main__ - Step 146940: {'lr': 5.275458215250606e-07, 'samples': 28212480, 'steps': 146939, 'loss/train': 0.7964028120040894} 08/31/2021 15:51:30 - INFO - __main__ - Step 146941: {'lr': 5.272013104592743e-07, 'samples': 28212672, 'steps': 146940, 'loss/train': 1.2528703212738037} 08/31/2021 15:51:30 - INFO - __main__ - Step 146942: {'lr': 5.268569118020982e-07, 'samples': 28212864, 'steps': 146941, 'loss/train': 1.7198916673660278} 08/31/2021 15:51:31 - INFO - __main__ - Step 146943: {'lr': 5.265126255536434e-07, 'samples': 28213056, 'steps': 146942, 'loss/train': 0.9136188626289368} 08/31/2021 15:51:32 - INFO - __main__ - Step 146944: {'lr': 5.261684517141318e-07, 'samples': 28213248, 'steps': 146943, 'loss/train': 1.5629050731658936} 08/31/2021 15:51:33 - INFO - __main__ - Step 146945: {'lr': 5.258243902836468e-07, 'samples': 28213440, 'steps': 146944, 'loss/train': 1.1151036024093628} 08/31/2021 15:51:33 - INFO - __main__ - Step 146946: {'lr': 5.254804412623826e-07, 'samples': 28213632, 'steps': 146945, 'loss/train': 1.1728602647781372} 08/31/2021 15:51:33 - INFO - __main__ - Step 146947: {'lr': 5.25136604650478e-07, 'samples': 28213824, 'steps': 146946, 'loss/train': 0.9161044955253601} 08/31/2021 15:51:34 - INFO - __main__ - Step 146948: {'lr': 5.247928804480994e-07, 'samples': 28214016, 'steps': 146947, 'loss/train': 0.9909813404083252} 08/31/2021 15:51:35 - INFO - __main__ - Step 146949: {'lr': 5.244492686554137e-07, 'samples': 28214208, 'steps': 146948, 'loss/train': 1.0034981966018677} 08/31/2021 15:51:36 - INFO - __main__ - Step 146950: {'lr': 5.241057692725593e-07, 'samples': 28214400, 'steps': 146949, 'loss/train': 1.2790791988372803} 08/31/2021 15:51:36 - INFO - __main__ - Step 146951: {'lr': 5.237623822996751e-07, 'samples': 28214592, 'steps': 146950, 'loss/train': 1.549663782119751} 08/31/2021 15:51:36 - INFO - __main__ - Step 146952: {'lr': 5.234191077369554e-07, 'samples': 28214784, 'steps': 146951, 'loss/train': 1.51301109790802} 08/31/2021 15:51:37 - INFO - __main__ - Step 146953: {'lr': 5.230759455845113e-07, 'samples': 28214976, 'steps': 146952, 'loss/train': 1.1978697776794434} 08/31/2021 15:51:38 - INFO - __main__ - Step 146954: {'lr': 5.22732895842537e-07, 'samples': 28215168, 'steps': 146953, 'loss/train': 1.4531162977218628} 08/31/2021 15:51:39 - INFO - __main__ - Step 146955: {'lr': 5.223899585111713e-07, 'samples': 28215360, 'steps': 146954, 'loss/train': 1.0039551258087158} 08/31/2021 15:51:39 - INFO - __main__ - Step 146956: {'lr': 5.22047133590553e-07, 'samples': 28215552, 'steps': 146955, 'loss/train': 0.25275322794914246} 08/31/2021 15:51:39 - INFO - __main__ - Step 146957: {'lr': 5.217044210808764e-07, 'samples': 28215744, 'steps': 146956, 'loss/train': 1.2280843257904053} 08/31/2021 15:51:40 - INFO - __main__ - Step 146958: {'lr': 5.213618209822524e-07, 'samples': 28215936, 'steps': 146957, 'loss/train': 1.3066576719284058} 08/31/2021 15:51:41 - INFO - __main__ - Step 146959: {'lr': 5.210193332948476e-07, 'samples': 28216128, 'steps': 146958, 'loss/train': 1.2539703845977783} 08/31/2021 15:51:42 - INFO - __main__ - Step 146960: {'lr': 5.206769580188286e-07, 'samples': 28216320, 'steps': 146959, 'loss/train': 1.3082396984100342} 08/31/2021 15:51:42 - INFO - __main__ - Step 146961: {'lr': 5.203346951543342e-07, 'samples': 28216512, 'steps': 146960, 'loss/train': 1.0678561925888062} 08/31/2021 15:51:42 - INFO - __main__ - Step 146962: {'lr': 5.199925447015307e-07, 'samples': 28216704, 'steps': 146961, 'loss/train': 0.7791662812232971} 08/31/2021 15:51:43 - INFO - __main__ - Step 146963: {'lr': 5.19650506660585e-07, 'samples': 28216896, 'steps': 146962, 'loss/train': 1.5291001796722412} 08/31/2021 15:51:44 - INFO - __main__ - Step 146964: {'lr': 5.193085810316078e-07, 'samples': 28217088, 'steps': 146963, 'loss/train': 1.3921078443527222} 08/31/2021 15:51:45 - INFO - __main__ - Step 146965: {'lr': 5.189667678147936e-07, 'samples': 28217280, 'steps': 146964, 'loss/train': 0.4773086905479431} 08/31/2021 15:51:45 - INFO - __main__ - Step 146966: {'lr': 5.18625067010281e-07, 'samples': 28217472, 'steps': 146965, 'loss/train': 1.0489429235458374} 08/31/2021 15:51:45 - INFO - __main__ - Step 146967: {'lr': 5.182834786182366e-07, 'samples': 28217664, 'steps': 146966, 'loss/train': 1.2322767972946167} 08/31/2021 15:51:46 - INFO - __main__ - Step 146968: {'lr': 5.179420026387993e-07, 'samples': 28217856, 'steps': 146967, 'loss/train': 0.037932634353637695} 08/31/2021 15:51:47 - INFO - __main__ - Step 146969: {'lr': 5.176006390721355e-07, 'samples': 28218048, 'steps': 146968, 'loss/train': 0.7336204648017883} 08/31/2021 15:51:48 - INFO - __main__ - Step 146970: {'lr': 5.17259387918384e-07, 'samples': 28218240, 'steps': 146969, 'loss/train': 0.928589940071106} 08/31/2021 15:51:48 - INFO - __main__ - Step 146971: {'lr': 5.169182491777113e-07, 'samples': 28218432, 'steps': 146970, 'loss/train': 1.3113372325897217} 08/31/2021 15:51:49 - INFO - __main__ - Step 146972: {'lr': 5.165772228502563e-07, 'samples': 28218624, 'steps': 146971, 'loss/train': 1.175877332687378} 08/31/2021 15:51:49 - INFO - __main__ - Step 146973: {'lr': 5.162363089361577e-07, 'samples': 28218816, 'steps': 146972, 'loss/train': 1.1973813772201538} 08/31/2021 15:51:49 - INFO - __main__ - Step 146974: {'lr': 5.158955074356375e-07, 'samples': 28219008, 'steps': 146973, 'loss/train': 1.4153605699539185} 08/31/2021 15:51:51 - INFO - __main__ - Step 146975: {'lr': 5.15554818348779e-07, 'samples': 28219200, 'steps': 146974, 'loss/train': 1.1865495443344116} 08/31/2021 15:51:51 - INFO - __main__ - Step 146976: {'lr': 5.152142416757766e-07, 'samples': 28219392, 'steps': 146975, 'loss/train': 0.09789250791072845} 08/31/2021 15:51:52 - INFO - __main__ - Step 146977: {'lr': 5.148737774167412e-07, 'samples': 28219584, 'steps': 146976, 'loss/train': 1.8553169965744019} 08/31/2021 15:51:52 - INFO - __main__ - Step 146978: {'lr': 5.145334255718948e-07, 'samples': 28219776, 'steps': 146977, 'loss/train': 0.7228317260742188} 08/31/2021 15:51:52 - INFO - __main__ - Step 146979: {'lr': 5.141931861413207e-07, 'samples': 28219968, 'steps': 146978, 'loss/train': 0.5527129173278809} 08/31/2021 15:51:54 - INFO - __main__ - Step 146980: {'lr': 5.138530591252133e-07, 'samples': 28220160, 'steps': 146979, 'loss/train': 1.1019080877304077} 08/31/2021 15:51:54 - INFO - __main__ - Step 146981: {'lr': 5.135130445237113e-07, 'samples': 28220352, 'steps': 146980, 'loss/train': 0.2823260724544525} 08/31/2021 15:51:55 - INFO - __main__ - Step 146982: {'lr': 5.131731423369534e-07, 'samples': 28220544, 'steps': 146981, 'loss/train': 1.0944942235946655} 08/31/2021 15:51:55 - INFO - __main__ - Step 146983: {'lr': 5.128333525651341e-07, 'samples': 28220736, 'steps': 146982, 'loss/train': 1.1987605094909668} 08/31/2021 15:51:56 - INFO - __main__ - Step 146984: {'lr': 5.124936752083642e-07, 'samples': 28220928, 'steps': 146983, 'loss/train': 0.4991147518157959} 08/31/2021 15:51:57 - INFO - __main__ - Step 146985: {'lr': 5.121541102668382e-07, 'samples': 28221120, 'steps': 146984, 'loss/train': 1.097976565361023} 08/31/2021 15:51:58 - INFO - __main__ - Step 146986: {'lr': 5.118146577406668e-07, 'samples': 28221312, 'steps': 146985, 'loss/train': 1.2895022630691528} 08/31/2021 15:51:58 - INFO - __main__ - Step 146987: {'lr': 5.114753176300169e-07, 'samples': 28221504, 'steps': 146986, 'loss/train': 1.4765857458114624} 08/31/2021 15:51:59 - INFO - __main__ - Step 146988: {'lr': 5.111360899350548e-07, 'samples': 28221696, 'steps': 146987, 'loss/train': 1.4793636798858643} 08/31/2021 15:51:59 - INFO - __main__ - Step 146989: {'lr': 5.107969746559471e-07, 'samples': 28221888, 'steps': 146988, 'loss/train': 0.10566465556621552} 08/31/2021 15:52:01 - INFO - __main__ - Step 146990: {'lr': 5.104579717928049e-07, 'samples': 28222080, 'steps': 146989, 'loss/train': 0.7345075607299805} 08/31/2021 15:52:01 - INFO - __main__ - Step 146991: {'lr': 5.101190813457945e-07, 'samples': 28222272, 'steps': 146990, 'loss/train': 0.34491926431655884} 08/31/2021 15:52:02 - INFO - __main__ - Step 146992: {'lr': 5.097803033150827e-07, 'samples': 28222464, 'steps': 146991, 'loss/train': 0.4110243022441864} 08/31/2021 15:52:02 - INFO - __main__ - Step 146993: {'lr': 5.094416377008082e-07, 'samples': 28222656, 'steps': 146992, 'loss/train': 1.606636881828308} 08/31/2021 15:52:02 - INFO - __main__ - Step 146994: {'lr': 5.091030845031097e-07, 'samples': 28222848, 'steps': 146993, 'loss/train': 1.12929105758667} 08/31/2021 15:52:04 - INFO - __main__ - Step 146995: {'lr': 5.087646437221815e-07, 'samples': 28223040, 'steps': 146994, 'loss/train': 1.082132339477539} 08/31/2021 15:52:04 - INFO - __main__ - Step 146996: {'lr': 5.084263153581625e-07, 'samples': 28223232, 'steps': 146995, 'loss/train': 1.1946922540664673} 08/31/2021 15:52:05 - INFO - __main__ - Step 146997: {'lr': 5.080880994111914e-07, 'samples': 28223424, 'steps': 146996, 'loss/train': 1.1501927375793457} 08/31/2021 15:52:05 - INFO - __main__ - Step 146998: {'lr': 5.077499958814347e-07, 'samples': 28223616, 'steps': 146997, 'loss/train': 1.2727525234222412} 08/31/2021 15:52:05 - INFO - __main__ - Step 146999: {'lr': 5.074120047690312e-07, 'samples': 28223808, 'steps': 146998, 'loss/train': 0.7545972466468811} 08/31/2021 15:52:07 - INFO - __main__ - Step 147000: {'lr': 5.070741260741197e-07, 'samples': 28224000, 'steps': 146999, 'loss/train': 0.8264737725257874} 08/31/2021 15:52:07 - INFO - __main__ - Step 147001: {'lr': 5.067363597968666e-07, 'samples': 28224192, 'steps': 147000, 'loss/train': 0.5070923566818237} 08/31/2021 15:52:08 - INFO - __main__ - Step 147002: {'lr': 5.063987059374664e-07, 'samples': 28224384, 'steps': 147001, 'loss/train': 0.832883894443512} 08/31/2021 15:52:08 - INFO - __main__ - Step 147003: {'lr': 5.060611644960022e-07, 'samples': 28224576, 'steps': 147002, 'loss/train': 0.6425313353538513} 08/31/2021 15:52:08 - INFO - __main__ - Step 147004: {'lr': 5.057237354726685e-07, 'samples': 28224768, 'steps': 147003, 'loss/train': 0.8575574159622192} 08/31/2021 15:52:10 - INFO - __main__ - Step 147005: {'lr': 5.053864188676038e-07, 'samples': 28224960, 'steps': 147004, 'loss/train': 1.412123680114746} 08/31/2021 15:52:11 - INFO - __main__ - Step 147006: {'lr': 5.050492146809471e-07, 'samples': 28225152, 'steps': 147005, 'loss/train': 0.10700607299804688} 08/31/2021 15:52:11 - INFO - __main__ - Step 147007: {'lr': 5.047121229128926e-07, 'samples': 28225344, 'steps': 147006, 'loss/train': 0.9492806196212769} 08/31/2021 15:52:11 - INFO - __main__ - Step 147008: {'lr': 5.043751435635513e-07, 'samples': 28225536, 'steps': 147007, 'loss/train': 1.1114856004714966} 08/31/2021 15:52:12 - INFO - __main__ - Step 147009: {'lr': 5.040382766330898e-07, 'samples': 28225728, 'steps': 147008, 'loss/train': 0.9484851360321045} 08/31/2021 15:52:12 - INFO - __main__ - Step 147010: {'lr': 5.037015221216468e-07, 'samples': 28225920, 'steps': 147009, 'loss/train': 1.6276493072509766} 08/31/2021 15:52:14 - INFO - __main__ - Step 147011: {'lr': 5.033648800293889e-07, 'samples': 28226112, 'steps': 147010, 'loss/train': 0.9598732590675354} 08/31/2021 15:52:14 - INFO - __main__ - Step 147012: {'lr': 5.030283503564825e-07, 'samples': 28226304, 'steps': 147011, 'loss/train': 0.6023682355880737} 08/31/2021 15:52:14 - INFO - __main__ - Step 147013: {'lr': 5.026919331030388e-07, 'samples': 28226496, 'steps': 147012, 'loss/train': 1.0281496047973633} 08/31/2021 15:52:15 - INFO - __main__ - Step 147014: {'lr': 5.023556282692521e-07, 'samples': 28226688, 'steps': 147013, 'loss/train': 0.147750586271286} 08/31/2021 15:52:15 - INFO - __main__ - Step 147015: {'lr': 5.02019435855261e-07, 'samples': 28226880, 'steps': 147014, 'loss/train': 0.3773502707481384} 08/31/2021 15:52:17 - INFO - __main__ - Step 147016: {'lr': 5.016833558611767e-07, 'samples': 28227072, 'steps': 147015, 'loss/train': 0.2444060891866684} 08/31/2021 15:52:17 - INFO - __main__ - Step 147017: {'lr': 5.013473882872211e-07, 'samples': 28227264, 'steps': 147016, 'loss/train': 1.1827387809753418} 08/31/2021 15:52:17 - INFO - __main__ - Step 147018: {'lr': 5.010115331334774e-07, 'samples': 28227456, 'steps': 147017, 'loss/train': 0.569034218788147} 08/31/2021 15:52:18 - INFO - __main__ - Step 147019: {'lr': 5.006757904001403e-07, 'samples': 28227648, 'steps': 147018, 'loss/train': 2.165041208267212} 08/31/2021 15:52:18 - INFO - __main__ - Step 147020: {'lr': 5.00340160087348e-07, 'samples': 28227840, 'steps': 147019, 'loss/train': 0.6858634352684021} 08/31/2021 15:52:20 - INFO - __main__ - Step 147021: {'lr': 5.000046421952398e-07, 'samples': 28228032, 'steps': 147020, 'loss/train': 1.3816819190979004} 08/31/2021 15:52:20 - INFO - __main__ - Step 147022: {'lr': 4.996692367240096e-07, 'samples': 28228224, 'steps': 147021, 'loss/train': 1.3750274181365967} 08/31/2021 15:52:21 - INFO - __main__ - Step 147023: {'lr': 4.993339436737687e-07, 'samples': 28228416, 'steps': 147022, 'loss/train': 0.705682098865509} 08/31/2021 15:52:21 - INFO - __main__ - Step 147024: {'lr': 4.989987630446558e-07, 'samples': 28228608, 'steps': 147023, 'loss/train': 0.02735552191734314} 08/31/2021 15:52:21 - INFO - __main__ - Step 147025: {'lr': 4.986636948368651e-07, 'samples': 28228800, 'steps': 147024, 'loss/train': 1.7253670692443848} 08/31/2021 15:52:22 - INFO - __main__ - Step 147026: {'lr': 4.983287390505353e-07, 'samples': 28228992, 'steps': 147025, 'loss/train': 1.7449535131454468} 08/31/2021 15:52:23 - INFO - __main__ - Step 147027: {'lr': 4.979938956857777e-07, 'samples': 28229184, 'steps': 147026, 'loss/train': 0.0326501727104187} 08/31/2021 15:52:24 - INFO - __main__ - Step 147028: {'lr': 4.976591647427864e-07, 'samples': 28229376, 'steps': 147027, 'loss/train': 5.755026817321777} 08/31/2021 15:52:24 - INFO - __main__ - Step 147029: {'lr': 4.973245462217002e-07, 'samples': 28229568, 'steps': 147028, 'loss/train': 0.8817733526229858} 08/31/2021 15:52:25 - INFO - __main__ - Step 147030: {'lr': 4.969900401226857e-07, 'samples': 28229760, 'steps': 147029, 'loss/train': 1.3492084741592407} 08/31/2021 15:52:25 - INFO - __main__ - Step 147031: {'lr': 4.966556464458538e-07, 'samples': 28229952, 'steps': 147030, 'loss/train': 0.5885536670684814} 08/31/2021 15:52:25 - INFO - __main__ - Step 147032: {'lr': 4.96321365191399e-07, 'samples': 28230144, 'steps': 147031, 'loss/train': 1.4417551755905151} 08/31/2021 15:52:27 - INFO - __main__ - Step 147033: {'lr': 4.95987196359432e-07, 'samples': 28230336, 'steps': 147032, 'loss/train': 0.0356210432946682} 08/31/2021 15:52:27 - INFO - __main__ - Step 147034: {'lr': 4.956531399501474e-07, 'samples': 28230528, 'steps': 147033, 'loss/train': 1.1990498304367065} 08/31/2021 15:52:28 - INFO - __main__ - Step 147035: {'lr': 4.95319195963656e-07, 'samples': 28230720, 'steps': 147034, 'loss/train': 1.0942702293395996} 08/31/2021 15:52:28 - INFO - __main__ - Step 147036: {'lr': 4.949853644001246e-07, 'samples': 28230912, 'steps': 147035, 'loss/train': 0.9405747056007385} 08/31/2021 15:52:28 - INFO - __main__ - Step 147037: {'lr': 4.946516452596917e-07, 'samples': 28231104, 'steps': 147036, 'loss/train': 0.3695267140865326} 08/31/2021 15:52:31 - INFO - __main__ - Step 147038: {'lr': 4.943180385425238e-07, 'samples': 28231296, 'steps': 147037, 'loss/train': 0.23631839454174042} 08/31/2021 15:52:31 - INFO - __main__ - Step 147039: {'lr': 4.939845442487878e-07, 'samples': 28231488, 'steps': 147038, 'loss/train': 0.9563180804252625} 08/31/2021 15:52:32 - INFO - __main__ - Step 147040: {'lr': 4.936511623785944e-07, 'samples': 28231680, 'steps': 147039, 'loss/train': 1.5362534523010254} 08/31/2021 15:52:32 - INFO - __main__ - Step 147041: {'lr': 4.933178929321103e-07, 'samples': 28231872, 'steps': 147040, 'loss/train': 1.1074600219726562} 08/31/2021 15:52:32 - INFO - __main__ - Step 147042: {'lr': 4.929847359095019e-07, 'samples': 28232064, 'steps': 147041, 'loss/train': 0.6656386852264404} 08/31/2021 15:52:33 - INFO - __main__ - Step 147043: {'lr': 4.926516913108803e-07, 'samples': 28232256, 'steps': 147042, 'loss/train': 0.7144848108291626} 08/31/2021 15:52:35 - INFO - __main__ - Step 147044: {'lr': 4.923187591364398e-07, 'samples': 28232448, 'steps': 147043, 'loss/train': 1.8398408889770508} 08/31/2021 15:52:35 - INFO - __main__ - Step 147045: {'lr': 4.919859393862913e-07, 'samples': 28232640, 'steps': 147044, 'loss/train': 1.0893491506576538} 08/31/2021 15:52:35 - INFO - __main__ - Step 147046: {'lr': 4.916532320606293e-07, 'samples': 28232832, 'steps': 147045, 'loss/train': 0.9816439747810364} 08/31/2021 15:52:36 - INFO - __main__ - Step 147047: {'lr': 4.913206371595647e-07, 'samples': 28233024, 'steps': 147046, 'loss/train': 2.1187186241149902} 08/31/2021 15:52:36 - INFO - __main__ - Step 147048: {'lr': 4.90988154683264e-07, 'samples': 28233216, 'steps': 147047, 'loss/train': 1.325272798538208} 08/31/2021 15:52:37 - INFO - __main__ - Step 147049: {'lr': 4.90655784631866e-07, 'samples': 28233408, 'steps': 147048, 'loss/train': 1.279679536819458} 08/31/2021 15:52:38 - INFO - __main__ - Step 147050: {'lr': 4.903235270055373e-07, 'samples': 28233600, 'steps': 147049, 'loss/train': 1.5549578666687012} 08/31/2021 15:52:38 - INFO - __main__ - Step 147051: {'lr': 4.899913818044166e-07, 'samples': 28233792, 'steps': 147050, 'loss/train': 0.912274181842804} 08/31/2021 15:52:39 - INFO - __main__ - Step 147052: {'lr': 4.896593490286427e-07, 'samples': 28233984, 'steps': 147051, 'loss/train': 0.644075334072113} 08/31/2021 15:52:39 - INFO - __main__ - Step 147053: {'lr': 4.893274286783822e-07, 'samples': 28234176, 'steps': 147052, 'loss/train': 0.9945221543312073} 08/31/2021 15:52:39 - INFO - __main__ - Step 147054: {'lr': 4.889956207538015e-07, 'samples': 28234368, 'steps': 147053, 'loss/train': 1.1950769424438477} 08/31/2021 15:52:41 - INFO - __main__ - Step 147055: {'lr': 4.886639252550118e-07, 'samples': 28234560, 'steps': 147054, 'loss/train': 0.6939789652824402} 08/31/2021 15:52:41 - INFO - __main__ - Step 147056: {'lr': 4.883323421821795e-07, 'samples': 28234752, 'steps': 147055, 'loss/train': 1.379747748374939} 08/31/2021 15:52:42 - INFO - __main__ - Step 147057: {'lr': 4.880008715354434e-07, 'samples': 28234944, 'steps': 147056, 'loss/train': 1.0887641906738281} 08/31/2021 15:52:42 - INFO - __main__ - Step 147058: {'lr': 4.876695133149977e-07, 'samples': 28235136, 'steps': 147057, 'loss/train': 1.283742904663086} 08/31/2021 15:52:42 - INFO - __main__ - Step 147059: {'lr': 4.873382675209259e-07, 'samples': 28235328, 'steps': 147058, 'loss/train': 0.7811993360519409} 08/31/2021 15:52:44 - INFO - __main__ - Step 147060: {'lr': 4.870071341534221e-07, 'samples': 28235520, 'steps': 147059, 'loss/train': 1.8057725429534912} 08/31/2021 15:52:45 - INFO - __main__ - Step 147061: {'lr': 4.866761132126252e-07, 'samples': 28235712, 'steps': 147060, 'loss/train': 1.0147650241851807} 08/31/2021 15:52:45 - INFO - __main__ - Step 147062: {'lr': 4.863452046986738e-07, 'samples': 28235904, 'steps': 147061, 'loss/train': 0.7813786864280701} 08/31/2021 15:52:46 - INFO - __main__ - Step 147063: {'lr': 4.860144086117347e-07, 'samples': 28236096, 'steps': 147062, 'loss/train': 1.62091863155365} 08/31/2021 15:52:46 - INFO - __main__ - Step 147064: {'lr': 4.856837249519463e-07, 'samples': 28236288, 'steps': 147063, 'loss/train': 1.2114958763122559} 08/31/2021 15:52:46 - INFO - __main__ - Step 147065: {'lr': 4.853531537194478e-07, 'samples': 28236480, 'steps': 147064, 'loss/train': 0.014282448217272758} 08/31/2021 15:52:48 - INFO - __main__ - Step 147066: {'lr': 4.850226949144054e-07, 'samples': 28236672, 'steps': 147065, 'loss/train': 1.2424744367599487} 08/31/2021 15:52:49 - INFO - __main__ - Step 147067: {'lr': 4.846923485369858e-07, 'samples': 28236864, 'steps': 147066, 'loss/train': 1.3580400943756104} 08/31/2021 15:52:49 - INFO - __main__ - Step 147068: {'lr': 4.843621145872723e-07, 'samples': 28237056, 'steps': 147067, 'loss/train': 0.037361156195402145} 08/31/2021 15:52:49 - INFO - __main__ - Step 147069: {'lr': 4.840319930654868e-07, 'samples': 28237248, 'steps': 147068, 'loss/train': 0.27043992280960083} 08/31/2021 15:52:50 - INFO - __main__ - Step 147070: {'lr': 4.837019839717127e-07, 'samples': 28237440, 'steps': 147069, 'loss/train': 1.558773398399353} 08/31/2021 15:52:50 - INFO - __main__ - Step 147071: {'lr': 4.83372087306172e-07, 'samples': 28237632, 'steps': 147070, 'loss/train': 1.3931273221969604} 08/31/2021 15:52:51 - INFO - __main__ - Step 147072: {'lr': 4.83042303068948e-07, 'samples': 28237824, 'steps': 147071, 'loss/train': 0.6359560489654541} 08/31/2021 15:52:52 - INFO - __main__ - Step 147073: {'lr': 4.827126312602071e-07, 'samples': 28238016, 'steps': 147072, 'loss/train': 0.6472160220146179} 08/31/2021 15:52:52 - INFO - __main__ - Step 147074: {'lr': 4.823830718801159e-07, 'samples': 28238208, 'steps': 147073, 'loss/train': 1.2766447067260742} 08/31/2021 15:52:53 - INFO - __main__ - Step 147075: {'lr': 4.820536249288133e-07, 'samples': 28238400, 'steps': 147074, 'loss/train': 1.2428289651870728} 08/31/2021 15:52:53 - INFO - __main__ - Step 147076: {'lr': 4.817242904064656e-07, 'samples': 28238592, 'steps': 147075, 'loss/train': 1.2197142839431763} 08/31/2021 15:52:54 - INFO - __main__ - Step 147077: {'lr': 4.81395068313184e-07, 'samples': 28238784, 'steps': 147076, 'loss/train': 1.5534452199935913} 08/31/2021 15:52:55 - INFO - __main__ - Step 147078: {'lr': 4.81065958649135e-07, 'samples': 28238976, 'steps': 147077, 'loss/train': 0.3822717070579529} 08/31/2021 15:52:55 - INFO - __main__ - Step 147079: {'lr': 4.807369614144852e-07, 'samples': 28239168, 'steps': 147078, 'loss/train': 1.0830241441726685} 08/31/2021 15:52:56 - INFO - __main__ - Step 147080: {'lr': 4.804080766093455e-07, 'samples': 28239360, 'steps': 147079, 'loss/train': 1.4778051376342773} 08/31/2021 15:52:56 - INFO - __main__ - Step 147081: {'lr': 4.800793042338825e-07, 'samples': 28239552, 'steps': 147080, 'loss/train': 1.445578694343567} 08/31/2021 15:52:57 - INFO - __main__ - Step 147082: {'lr': 4.797506442882626e-07, 'samples': 28239744, 'steps': 147081, 'loss/train': 0.6424028277397156} 08/31/2021 15:52:58 - INFO - __main__ - Step 147083: {'lr': 4.794220967725971e-07, 'samples': 28239936, 'steps': 147082, 'loss/train': 0.9751031994819641} 08/31/2021 15:52:58 - INFO - __main__ - Step 147084: {'lr': 4.790936616870522e-07, 'samples': 28240128, 'steps': 147083, 'loss/train': 0.843888521194458} 08/31/2021 15:52:59 - INFO - __main__ - Step 147085: {'lr': 4.787653390317948e-07, 'samples': 28240320, 'steps': 147084, 'loss/train': 1.38473379611969} 08/31/2021 15:52:59 - INFO - __main__ - Step 147086: {'lr': 4.784371288069356e-07, 'samples': 28240512, 'steps': 147085, 'loss/train': 0.7808778882026672} 08/31/2021 15:53:01 - INFO - __main__ - Step 147087: {'lr': 4.78109031012669e-07, 'samples': 28240704, 'steps': 147086, 'loss/train': 0.4519263207912445} 08/31/2021 15:53:01 - INFO - __main__ - Step 147088: {'lr': 4.777810456491061e-07, 'samples': 28240896, 'steps': 147087, 'loss/train': 0.8237951993942261} 08/31/2021 15:53:02 - INFO - __main__ - Step 147089: {'lr': 4.774531727163856e-07, 'samples': 28241088, 'steps': 147088, 'loss/train': 0.8509864807128906} 08/31/2021 15:53:02 - INFO - __main__ - Step 147090: {'lr': 4.771254122147017e-07, 'samples': 28241280, 'steps': 147089, 'loss/train': 1.7054579257965088} 08/31/2021 15:53:02 - INFO - __main__ - Step 147091: {'lr': 4.7679776414416567e-07, 'samples': 28241472, 'steps': 147090, 'loss/train': 0.36423808336257935} 08/31/2021 15:53:03 - INFO - __main__ - Step 147092: {'lr': 4.7647022850491603e-07, 'samples': 28241664, 'steps': 147091, 'loss/train': 1.2095154523849487} 08/31/2021 15:53:05 - INFO - __main__ - Step 147093: {'lr': 4.7614280529714724e-07, 'samples': 28241856, 'steps': 147092, 'loss/train': 0.5499565005302429} 08/31/2021 15:53:05 - INFO - __main__ - Step 147094: {'lr': 4.758154945209425e-07, 'samples': 28242048, 'steps': 147093, 'loss/train': 1.129482388496399} 08/31/2021 15:53:06 - INFO - __main__ - Step 147095: {'lr': 4.754882961765239e-07, 'samples': 28242240, 'steps': 147094, 'loss/train': 0.34875085949897766} 08/31/2021 15:53:06 - INFO - __main__ - Step 147096: {'lr': 4.751612102639746e-07, 'samples': 28242432, 'steps': 147095, 'loss/train': 0.7941421866416931} 08/31/2021 15:53:06 - INFO - __main__ - Step 147097: {'lr': 4.7483423678346126e-07, 'samples': 28242624, 'steps': 147096, 'loss/train': 1.2420494556427002} 08/31/2021 15:53:08 - INFO - __main__ - Step 147098: {'lr': 4.7450737573515036e-07, 'samples': 28242816, 'steps': 147097, 'loss/train': 1.815424919128418} 08/31/2021 15:53:08 - INFO - __main__ - Step 147099: {'lr': 4.7418062711918063e-07, 'samples': 28243008, 'steps': 147098, 'loss/train': 1.1097279787063599} 08/31/2021 15:53:09 - INFO - __main__ - Step 147100: {'lr': 4.738539909356909e-07, 'samples': 28243200, 'steps': 147099, 'loss/train': 0.7221484184265137} 08/31/2021 15:53:09 - INFO - __main__ - Step 147101: {'lr': 4.7352746718482e-07, 'samples': 28243392, 'steps': 147100, 'loss/train': 1.11329185962677} 08/31/2021 15:53:09 - INFO - __main__ - Step 147102: {'lr': 4.732010558667621e-07, 'samples': 28243584, 'steps': 147101, 'loss/train': 1.6077302694320679} 08/31/2021 15:53:11 - INFO - __main__ - Step 147103: {'lr': 4.7287475698160056e-07, 'samples': 28243776, 'steps': 147102, 'loss/train': 1.238761305809021} 08/31/2021 15:53:12 - INFO - __main__ - Step 147104: {'lr': 4.725485705295296e-07, 'samples': 28243968, 'steps': 147103, 'loss/train': 0.5786981582641602} 08/31/2021 15:53:12 - INFO - __main__ - Step 147105: {'lr': 4.722224965106603e-07, 'samples': 28244160, 'steps': 147104, 'loss/train': 0.32512760162353516} 08/31/2021 15:53:12 - INFO - __main__ - Step 147106: {'lr': 4.7189653492515915e-07, 'samples': 28244352, 'steps': 147105, 'loss/train': 0.4055621922016144} 08/31/2021 15:53:13 - INFO - __main__ - Step 147107: {'lr': 4.71570685773165e-07, 'samples': 28244544, 'steps': 147106, 'loss/train': 0.18956787884235382} 08/31/2021 15:53:14 - INFO - __main__ - Step 147108: {'lr': 4.7124494905484425e-07, 'samples': 28244736, 'steps': 147107, 'loss/train': 0.8543037176132202} 08/31/2021 15:53:15 - INFO - __main__ - Step 147109: {'lr': 4.709193247703081e-07, 'samples': 28244928, 'steps': 147108, 'loss/train': 1.5080560445785522} 08/31/2021 15:53:15 - INFO - __main__ - Step 147110: {'lr': 4.7059381291975066e-07, 'samples': 28245120, 'steps': 147109, 'loss/train': 0.6019323468208313} 08/31/2021 15:53:15 - INFO - __main__ - Step 147111: {'lr': 4.702684135032831e-07, 'samples': 28245312, 'steps': 147110, 'loss/train': 0.4530501365661621} 08/31/2021 15:53:16 - INFO - __main__ - Step 147112: {'lr': 4.6994312652107185e-07, 'samples': 28245504, 'steps': 147111, 'loss/train': 0.9801326394081116} 08/31/2021 15:53:16 - INFO - __main__ - Step 147113: {'lr': 4.6961795197322796e-07, 'samples': 28245696, 'steps': 147112, 'loss/train': 0.0979621633887291} 08/31/2021 15:53:18 - INFO - __main__ - Step 147114: {'lr': 4.692928898599458e-07, 'samples': 28245888, 'steps': 147113, 'loss/train': 1.1387302875518799} 08/31/2021 15:53:18 - INFO - __main__ - Step 147115: {'lr': 4.6896794018136404e-07, 'samples': 28246080, 'steps': 147114, 'loss/train': 1.1567771434783936} 08/31/2021 15:53:18 - INFO - __main__ - Step 147116: {'lr': 4.686431029375937e-07, 'samples': 28246272, 'steps': 147115, 'loss/train': 1.0929795503616333} 08/31/2021 15:53:19 - INFO - __main__ - Step 147117: {'lr': 4.683183781288014e-07, 'samples': 28246464, 'steps': 147116, 'loss/train': 0.40420079231262207} 08/31/2021 15:53:19 - INFO - __main__ - Step 147118: {'lr': 4.6799376575512585e-07, 'samples': 28246656, 'steps': 147117, 'loss/train': 0.5265489816665649} 08/31/2021 15:53:21 - INFO - __main__ - Step 147119: {'lr': 4.676692658167336e-07, 'samples': 28246848, 'steps': 147118, 'loss/train': 0.7116460800170898} 08/31/2021 15:53:21 - INFO - __main__ - Step 147120: {'lr': 4.6734487831376346e-07, 'samples': 28247040, 'steps': 147119, 'loss/train': 2.179368495941162} 08/31/2021 15:53:22 - INFO - __main__ - Step 147121: {'lr': 4.670206032463542e-07, 'samples': 28247232, 'steps': 147120, 'loss/train': 1.1767096519470215} 08/31/2021 15:53:22 - INFO - __main__ - Step 147122: {'lr': 4.6669644061464455e-07, 'samples': 28247424, 'steps': 147121, 'loss/train': 0.022563066333532333} 08/31/2021 15:53:22 - INFO - __main__ - Step 147123: {'lr': 4.663723904188011e-07, 'samples': 28247616, 'steps': 147122, 'loss/train': 1.456320881843567} 08/31/2021 15:53:24 - INFO - __main__ - Step 147124: {'lr': 4.660484526589626e-07, 'samples': 28247808, 'steps': 147123, 'loss/train': 1.3670482635498047} 08/31/2021 15:53:24 - INFO - __main__ - Step 147125: {'lr': 4.657246273352678e-07, 'samples': 28248000, 'steps': 147124, 'loss/train': 1.0712794065475464} 08/31/2021 15:53:24 - INFO - __main__ - Step 147126: {'lr': 4.654009144478555e-07, 'samples': 28248192, 'steps': 147125, 'loss/train': 1.2797399759292603} 08/31/2021 15:53:25 - INFO - __main__ - Step 147127: {'lr': 4.6507731399692e-07, 'samples': 28248384, 'steps': 147126, 'loss/train': 1.508109211921692} 08/31/2021 15:53:25 - INFO - __main__ - Step 147128: {'lr': 4.647538259825168e-07, 'samples': 28248576, 'steps': 147127, 'loss/train': 1.4345309734344482} 08/31/2021 15:53:27 - INFO - __main__ - Step 147129: {'lr': 4.6443045040489575e-07, 'samples': 28248768, 'steps': 147128, 'loss/train': 0.27688705921173096} 08/31/2021 15:53:28 - INFO - __main__ - Step 147130: {'lr': 4.641071872641123e-07, 'samples': 28248960, 'steps': 147129, 'loss/train': 0.7175091505050659} 08/31/2021 15:53:28 - INFO - __main__ - Step 147131: {'lr': 4.637840365603885e-07, 'samples': 28249152, 'steps': 147130, 'loss/train': 1.2554699182510376} 08/31/2021 15:53:28 - INFO - __main__ - Step 147132: {'lr': 4.6346099829380763e-07, 'samples': 28249344, 'steps': 147131, 'loss/train': 0.5999917387962341} 08/31/2021 15:53:29 - INFO - __main__ - Step 147133: {'lr': 4.631380724645362e-07, 'samples': 28249536, 'steps': 147132, 'loss/train': 0.9424809217453003} 08/31/2021 15:53:30 - INFO - __main__ - Step 147134: {'lr': 4.628152590727408e-07, 'samples': 28249728, 'steps': 147133, 'loss/train': 0.09296514093875885} 08/31/2021 15:53:31 - INFO - __main__ - Step 147135: {'lr': 4.6249255811853244e-07, 'samples': 28249920, 'steps': 147134, 'loss/train': 2.3216359615325928} 08/31/2021 15:53:31 - INFO - __main__ - Step 147136: {'lr': 4.6216996960210533e-07, 'samples': 28250112, 'steps': 147135, 'loss/train': 1.281577706336975} 08/31/2021 15:53:31 - INFO - __main__ - Step 147137: {'lr': 4.6184749352354284e-07, 'samples': 28250304, 'steps': 147136, 'loss/train': 1.1395801305770874} 08/31/2021 15:53:32 - INFO - __main__ - Step 147138: {'lr': 4.615251298830392e-07, 'samples': 28250496, 'steps': 147137, 'loss/train': 1.540104627609253} 08/31/2021 15:53:32 - INFO - __main__ - Step 147139: {'lr': 4.612028786807054e-07, 'samples': 28250688, 'steps': 147138, 'loss/train': 1.5732241868972778} 08/31/2021 15:53:34 - INFO - __main__ - Step 147140: {'lr': 4.608807399167081e-07, 'samples': 28250880, 'steps': 147139, 'loss/train': 0.8529884219169617} 08/31/2021 15:53:34 - INFO - __main__ - Step 147141: {'lr': 4.6055871359118594e-07, 'samples': 28251072, 'steps': 147140, 'loss/train': 1.3389618396759033} 08/31/2021 15:53:35 - INFO - __main__ - Step 147142: {'lr': 4.6023679970430555e-07, 'samples': 28251264, 'steps': 147141, 'loss/train': 1.1365381479263306} 08/31/2021 15:53:35 - INFO - __main__ - Step 147143: {'lr': 4.599149982561779e-07, 'samples': 28251456, 'steps': 147142, 'loss/train': 0.025969842448830605} 08/31/2021 15:53:35 - INFO - __main__ - Step 147144: {'lr': 4.5959330924694175e-07, 'samples': 28251648, 'steps': 147143, 'loss/train': 1.596434235572815} 08/31/2021 15:53:37 - INFO - __main__ - Step 147145: {'lr': 4.5927173267679144e-07, 'samples': 28251840, 'steps': 147144, 'loss/train': 0.9692836999893188} 08/31/2021 15:53:38 - INFO - __main__ - Step 147146: {'lr': 4.5895026854583797e-07, 'samples': 28252032, 'steps': 147145, 'loss/train': 0.013932849280536175} 08/31/2021 15:53:38 - INFO - __main__ - Step 147147: {'lr': 4.5862891685422014e-07, 'samples': 28252224, 'steps': 147146, 'loss/train': 0.011933350935578346} 08/31/2021 15:53:38 - INFO - __main__ - Step 147148: {'lr': 4.5830767760210445e-07, 'samples': 28252416, 'steps': 147147, 'loss/train': 0.5336282253265381} 08/31/2021 15:53:39 - INFO - __main__ - Step 147149: {'lr': 4.5798655078960196e-07, 'samples': 28252608, 'steps': 147148, 'loss/train': 0.6732375621795654} 08/31/2021 15:53:39 - INFO - __main__ - Step 147150: {'lr': 4.5766553641690686e-07, 'samples': 28252800, 'steps': 147149, 'loss/train': 1.3462252616882324} 08/31/2021 15:53:42 - INFO - __main__ - Step 147151: {'lr': 4.5734463448413033e-07, 'samples': 28252992, 'steps': 147150, 'loss/train': 1.0681017637252808} 08/31/2021 15:53:42 - INFO - __main__ - Step 147152: {'lr': 4.5702384499141106e-07, 'samples': 28253184, 'steps': 147151, 'loss/train': 0.7846493721008301} 08/31/2021 15:53:43 - INFO - __main__ - Step 147153: {'lr': 4.5670316793891554e-07, 'samples': 28253376, 'steps': 147152, 'loss/train': 1.1694858074188232} 08/31/2021 15:53:43 - INFO - __main__ - Step 147154: {'lr': 4.563826033267826e-07, 'samples': 28253568, 'steps': 147153, 'loss/train': 1.2273238897323608} 08/31/2021 15:53:43 - INFO - __main__ - Step 147155: {'lr': 4.56062151155151e-07, 'samples': 28253760, 'steps': 147154, 'loss/train': 0.9833497405052185} 08/31/2021 15:53:44 - INFO - __main__ - Step 147156: {'lr': 4.557418114241596e-07, 'samples': 28253952, 'steps': 147155, 'loss/train': 0.09569301456212997} 08/31/2021 15:53:45 - INFO - __main__ - Step 147157: {'lr': 4.5542158413397484e-07, 'samples': 28254144, 'steps': 147156, 'loss/train': 1.7769030332565308} 08/31/2021 15:53:46 - INFO - __main__ - Step 147158: {'lr': 4.5510146928470776e-07, 'samples': 28254336, 'steps': 147157, 'loss/train': 1.7746245861053467} 08/31/2021 15:53:46 - INFO - __main__ - Step 147159: {'lr': 4.5478146687655265e-07, 'samples': 28254528, 'steps': 147158, 'loss/train': 0.03189682960510254} 08/31/2021 15:53:46 - INFO - __main__ - Step 147160: {'lr': 4.544615769095928e-07, 'samples': 28254720, 'steps': 147159, 'loss/train': 0.22156491875648499} 08/31/2021 15:53:47 - INFO - __main__ - Step 147161: {'lr': 4.541417993839947e-07, 'samples': 28254912, 'steps': 147160, 'loss/train': 0.9185526371002197} 08/31/2021 15:53:48 - INFO - __main__ - Step 147162: {'lr': 4.538221342999249e-07, 'samples': 28255104, 'steps': 147161, 'loss/train': 0.6825401782989502} 08/31/2021 15:53:49 - INFO - __main__ - Step 147163: {'lr': 4.535025816575222e-07, 'samples': 28255296, 'steps': 147162, 'loss/train': 0.6396992206573486} 08/31/2021 15:53:49 - INFO - __main__ - Step 147164: {'lr': 4.5318314145689767e-07, 'samples': 28255488, 'steps': 147163, 'loss/train': 0.9431667923927307} 08/31/2021 15:53:49 - INFO - __main__ - Step 147165: {'lr': 4.528638136982455e-07, 'samples': 28255680, 'steps': 147164, 'loss/train': 1.0790379047393799} 08/31/2021 15:53:50 - INFO - __main__ - Step 147166: {'lr': 4.525445983816767e-07, 'samples': 28255872, 'steps': 147165, 'loss/train': 1.3316748142242432} 08/31/2021 15:53:51 - INFO - __main__ - Step 147167: {'lr': 4.5222549550733016e-07, 'samples': 28256064, 'steps': 147166, 'loss/train': 0.9585397839546204} 08/31/2021 15:53:52 - INFO - __main__ - Step 147168: {'lr': 4.519065050753446e-07, 'samples': 28256256, 'steps': 147167, 'loss/train': 0.35061579942703247} 08/31/2021 15:53:52 - INFO - __main__ - Step 147169: {'lr': 4.515876270859143e-07, 'samples': 28256448, 'steps': 147168, 'loss/train': 1.2758965492248535} 08/31/2021 15:53:52 - INFO - __main__ - Step 147170: {'lr': 4.512688615391225e-07, 'samples': 28256640, 'steps': 147169, 'loss/train': 1.4135836362838745} 08/31/2021 15:53:53 - INFO - __main__ - Step 147171: {'lr': 4.5095020843513577e-07, 'samples': 28256832, 'steps': 147170, 'loss/train': 1.3016207218170166} 08/31/2021 15:53:54 - INFO - __main__ - Step 147172: {'lr': 4.506316677741207e-07, 'samples': 28257024, 'steps': 147171, 'loss/train': 1.8392657041549683} 08/31/2021 15:53:55 - INFO - __main__ - Step 147173: {'lr': 4.503132395561882e-07, 'samples': 28257216, 'steps': 147172, 'loss/train': 1.1916882991790771} 08/31/2021 15:53:55 - INFO - __main__ - Step 147174: {'lr': 4.499949237814771e-07, 'samples': 28257408, 'steps': 147173, 'loss/train': 0.8660587072372437} 08/31/2021 15:53:56 - INFO - __main__ - Step 147175: {'lr': 4.496767204501817e-07, 'samples': 28257600, 'steps': 147174, 'loss/train': 0.9316332340240479} 08/31/2021 15:53:56 - INFO - __main__ - Step 147176: {'lr': 4.4935862956238525e-07, 'samples': 28257792, 'steps': 147175, 'loss/train': 0.8557221293449402} 08/31/2021 15:53:57 - INFO - __main__ - Step 147177: {'lr': 4.490406511182543e-07, 'samples': 28257984, 'steps': 147176, 'loss/train': 0.7864919304847717} 08/31/2021 15:53:58 - INFO - __main__ - Step 147178: {'lr': 4.487227851179554e-07, 'samples': 28258176, 'steps': 147177, 'loss/train': 0.8333731889724731} 08/31/2021 15:53:58 - INFO - __main__ - Step 147179: {'lr': 4.484050315615995e-07, 'samples': 28258368, 'steps': 147178, 'loss/train': 1.0905925035476685} 08/31/2021 15:53:59 - INFO - __main__ - Step 147180: {'lr': 4.480873904493532e-07, 'samples': 28258560, 'steps': 147179, 'loss/train': 1.1075389385223389} 08/31/2021 15:53:59 - INFO - __main__ - Step 147181: {'lr': 4.477698617813275e-07, 'samples': 28258752, 'steps': 147180, 'loss/train': 1.1723709106445312} 08/31/2021 15:53:59 - INFO - __main__ - Step 147182: {'lr': 4.474524455577167e-07, 'samples': 28258944, 'steps': 147181, 'loss/train': 0.9788334965705872} 08/31/2021 15:54:01 - INFO - __main__ - Step 147183: {'lr': 4.4713514177860404e-07, 'samples': 28259136, 'steps': 147182, 'loss/train': 1.5205321311950684} 08/31/2021 15:54:02 - INFO - __main__ - Step 147184: {'lr': 4.468179504441838e-07, 'samples': 28259328, 'steps': 147183, 'loss/train': 1.3932275772094727} 08/31/2021 15:54:02 - INFO - __main__ - Step 147185: {'lr': 4.4650087155453936e-07, 'samples': 28259520, 'steps': 147184, 'loss/train': 1.7519378662109375} 08/31/2021 15:54:02 - INFO - __main__ - Step 147186: {'lr': 4.461839051098926e-07, 'samples': 28259712, 'steps': 147185, 'loss/train': 1.7263975143432617} 08/31/2021 15:54:03 - INFO - __main__ - Step 147187: {'lr': 4.458670511103269e-07, 'samples': 28259904, 'steps': 147186, 'loss/train': 0.45570194721221924} 08/31/2021 15:54:03 - INFO - __main__ - Step 147188: {'lr': 4.4555030955598096e-07, 'samples': 28260096, 'steps': 147187, 'loss/train': 0.9792290925979614} 08/31/2021 15:54:05 - INFO - __main__ - Step 147189: {'lr': 4.4523368044704915e-07, 'samples': 28260288, 'steps': 147188, 'loss/train': 0.9678718447685242} 08/31/2021 15:54:05 - INFO - __main__ - Step 147190: {'lr': 4.4491716378364245e-07, 'samples': 28260480, 'steps': 147189, 'loss/train': 1.392496943473816} 08/31/2021 15:54:05 - INFO - __main__ - Step 147191: {'lr': 4.4460075956589964e-07, 'samples': 28260672, 'steps': 147190, 'loss/train': 1.1204103231430054} 08/31/2021 15:54:06 - INFO - __main__ - Step 147192: {'lr': 4.4428446779395946e-07, 'samples': 28260864, 'steps': 147191, 'loss/train': 0.9301878213882446} 08/31/2021 15:54:06 - INFO - __main__ - Step 147193: {'lr': 4.439682884679885e-07, 'samples': 28261056, 'steps': 147192, 'loss/train': 0.9759882092475891} 08/31/2021 15:54:08 - INFO - __main__ - Step 147194: {'lr': 4.4365222158812556e-07, 'samples': 28261248, 'steps': 147193, 'loss/train': 1.735116720199585} 08/31/2021 15:54:08 - INFO - __main__ - Step 147195: {'lr': 4.433362671544816e-07, 'samples': 28261440, 'steps': 147194, 'loss/train': 0.023091735318303108} 08/31/2021 15:54:09 - INFO - __main__ - Step 147196: {'lr': 4.4302042516722316e-07, 'samples': 28261632, 'steps': 147195, 'loss/train': 1.1832489967346191} 08/31/2021 15:54:09 - INFO - __main__ - Step 147197: {'lr': 4.4270469562648907e-07, 'samples': 28261824, 'steps': 147196, 'loss/train': 0.6674504280090332} 08/31/2021 15:54:09 - INFO - __main__ - Step 147198: {'lr': 4.4238907853241804e-07, 'samples': 28262016, 'steps': 147197, 'loss/train': 0.08803916722536087} 08/31/2021 15:54:11 - INFO - __main__ - Step 147199: {'lr': 4.4207357388514893e-07, 'samples': 28262208, 'steps': 147198, 'loss/train': 0.5032187104225159} 08/31/2021 15:54:11 - INFO - __main__ - Step 147200: {'lr': 4.4175818168484813e-07, 'samples': 28262400, 'steps': 147199, 'loss/train': 1.4865878820419312} 08/31/2021 15:54:12 - INFO - __main__ - Step 147201: {'lr': 4.414429019316268e-07, 'samples': 28262592, 'steps': 147200, 'loss/train': 1.1748108863830566} 08/31/2021 15:54:12 - INFO - __main__ - Step 147202: {'lr': 4.411277346256515e-07, 'samples': 28262784, 'steps': 147201, 'loss/train': 1.422563910484314} 08/31/2021 15:54:12 - INFO - __main__ - Step 147203: {'lr': 4.408126797670331e-07, 'samples': 28262976, 'steps': 147202, 'loss/train': 0.03456562012434006} 08/31/2021 15:54:14 - INFO - __main__ - Step 147204: {'lr': 4.4049773735596597e-07, 'samples': 28263168, 'steps': 147203, 'loss/train': 2.5399770736694336} 08/31/2021 15:54:15 - INFO - __main__ - Step 147205: {'lr': 4.401829073925334e-07, 'samples': 28263360, 'steps': 147204, 'loss/train': 1.850309133529663} 08/31/2021 15:54:15 - INFO - __main__ - Step 147206: {'lr': 4.398681898769019e-07, 'samples': 28263552, 'steps': 147205, 'loss/train': 1.0163002014160156} 08/31/2021 15:54:16 - INFO - __main__ - Step 147207: {'lr': 4.3955358480923804e-07, 'samples': 28263744, 'steps': 147206, 'loss/train': 0.9878507852554321} 08/31/2021 15:54:16 - INFO - __main__ - Step 147208: {'lr': 4.39239092189625e-07, 'samples': 28263936, 'steps': 147207, 'loss/train': 1.0473037958145142} 08/31/2021 15:54:17 - INFO - __main__ - Step 147209: {'lr': 4.3892471201828486e-07, 'samples': 28264128, 'steps': 147208, 'loss/train': 0.9826277494430542} 08/31/2021 15:54:18 - INFO - __main__ - Step 147210: {'lr': 4.386104442952732e-07, 'samples': 28264320, 'steps': 147209, 'loss/train': 1.2504596710205078} 08/31/2021 15:54:18 - INFO - __main__ - Step 147211: {'lr': 4.382962890207842e-07, 'samples': 28264512, 'steps': 147210, 'loss/train': 1.2910964488983154} 08/31/2021 15:54:19 - INFO - __main__ - Step 147212: {'lr': 4.379822461949845e-07, 'samples': 28264704, 'steps': 147211, 'loss/train': 1.351523518562317} 08/31/2021 15:54:19 - INFO - __main__ - Step 147213: {'lr': 4.3766831581792953e-07, 'samples': 28264896, 'steps': 147212, 'loss/train': 1.2671781778335571} 08/31/2021 15:54:21 - INFO - __main__ - Step 147214: {'lr': 4.373544978898414e-07, 'samples': 28265088, 'steps': 147213, 'loss/train': 0.4033363163471222} 08/31/2021 15:54:21 - INFO - __main__ - Step 147215: {'lr': 4.370407924108033e-07, 'samples': 28265280, 'steps': 147214, 'loss/train': 0.8780819177627563} 08/31/2021 15:54:21 - INFO - __main__ - Step 147216: {'lr': 4.367271993810096e-07, 'samples': 28265472, 'steps': 147215, 'loss/train': 0.5804996490478516} 08/31/2021 15:54:22 - INFO - __main__ - Step 147217: {'lr': 4.3641371880057125e-07, 'samples': 28265664, 'steps': 147216, 'loss/train': 1.7874304056167603} 08/31/2021 15:54:22 - INFO - __main__ - Step 147218: {'lr': 4.361003506696271e-07, 'samples': 28265856, 'steps': 147217, 'loss/train': 1.5173956155776978} 08/31/2021 15:54:22 - INFO - __main__ - Step 147219: {'lr': 4.357870949883158e-07, 'samples': 28266048, 'steps': 147218, 'loss/train': 1.1718723773956299} 08/31/2021 15:54:24 - INFO - __main__ - Step 147220: {'lr': 4.3547395175680404e-07, 'samples': 28266240, 'steps': 147219, 'loss/train': 1.100797176361084} 08/31/2021 15:54:24 - INFO - __main__ - Step 147221: {'lr': 4.351609209752028e-07, 'samples': 28266432, 'steps': 147220, 'loss/train': 1.0779656171798706} 08/31/2021 15:54:25 - INFO - __main__ - Step 147222: {'lr': 4.348480026436785e-07, 'samples': 28266624, 'steps': 147221, 'loss/train': 1.3587472438812256} 08/31/2021 15:54:25 - INFO - __main__ - Step 147223: {'lr': 4.345351967623423e-07, 'samples': 28266816, 'steps': 147222, 'loss/train': 1.445407509803772} 08/31/2021 15:54:25 - INFO - __main__ - Step 147224: {'lr': 4.342225033313607e-07, 'samples': 28267008, 'steps': 147223, 'loss/train': 1.5239033699035645} 08/31/2021 15:54:27 - INFO - __main__ - Step 147225: {'lr': 4.339099223509002e-07, 'samples': 28267200, 'steps': 147224, 'loss/train': 0.8691520094871521} 08/31/2021 15:54:27 - INFO - __main__ - Step 147226: {'lr': 4.335974538210441e-07, 'samples': 28267392, 'steps': 147225, 'loss/train': 1.1448737382888794} 08/31/2021 15:54:28 - INFO - __main__ - Step 147227: {'lr': 4.332850977419589e-07, 'samples': 28267584, 'steps': 147226, 'loss/train': 1.1848822832107544} 08/31/2021 15:54:28 - INFO - __main__ - Step 147228: {'lr': 4.3297285411375565e-07, 'samples': 28267776, 'steps': 147227, 'loss/train': 1.0311418771743774} 08/31/2021 15:54:28 - INFO - __main__ - Step 147229: {'lr': 4.326607229366564e-07, 'samples': 28267968, 'steps': 147228, 'loss/train': 0.4455092251300812} 08/31/2021 15:54:30 - INFO - __main__ - Step 147230: {'lr': 4.323487042107166e-07, 'samples': 28268160, 'steps': 147229, 'loss/train': 0.4233490824699402} 08/31/2021 15:54:31 - INFO - __main__ - Step 147231: {'lr': 4.3203679793610283e-07, 'samples': 28268352, 'steps': 147230, 'loss/train': 0.9522606730461121} 08/31/2021 15:54:31 - INFO - __main__ - Step 147232: {'lr': 4.3172500411298165e-07, 'samples': 28268544, 'steps': 147231, 'loss/train': 0.3652348518371582} 08/31/2021 15:54:31 - INFO - __main__ - Step 147233: {'lr': 4.3141332274146406e-07, 'samples': 28268736, 'steps': 147232, 'loss/train': 0.9212103486061096} 08/31/2021 15:54:32 - INFO - __main__ - Step 147234: {'lr': 4.3110175382171656e-07, 'samples': 28268928, 'steps': 147233, 'loss/train': 0.5007919073104858} 08/31/2021 15:54:33 - INFO - __main__ - Step 147235: {'lr': 4.307902973538502e-07, 'samples': 28269120, 'steps': 147234, 'loss/train': 1.0611320734024048} 08/31/2021 15:54:34 - INFO - __main__ - Step 147236: {'lr': 4.304789533380038e-07, 'samples': 28269312, 'steps': 147235, 'loss/train': 0.8130945563316345} 08/31/2021 15:54:34 - INFO - __main__ - Step 147237: {'lr': 4.3016772177434385e-07, 'samples': 28269504, 'steps': 147236, 'loss/train': 1.4791135787963867} 08/31/2021 15:54:34 - INFO - __main__ - Step 147238: {'lr': 4.298566026630091e-07, 'samples': 28269696, 'steps': 147237, 'loss/train': 1.31113862991333} 08/31/2021 15:54:35 - INFO - __main__ - Step 147239: {'lr': 4.2954559600413833e-07, 'samples': 28269888, 'steps': 147238, 'loss/train': 1.8073375225067139} 08/31/2021 15:54:36 - INFO - __main__ - Step 147240: {'lr': 4.292347017978426e-07, 'samples': 28270080, 'steps': 147239, 'loss/train': 1.0631954669952393} 08/31/2021 15:54:37 - INFO - __main__ - Step 147241: {'lr': 4.289239200442885e-07, 'samples': 28270272, 'steps': 147240, 'loss/train': 1.412800669670105} 08/31/2021 15:54:37 - INFO - __main__ - Step 147242: {'lr': 4.286132507436147e-07, 'samples': 28270464, 'steps': 147241, 'loss/train': 0.9174952507019043} 08/31/2021 15:54:37 - INFO - __main__ - Step 147243: {'lr': 4.2830269389595997e-07, 'samples': 28270656, 'steps': 147242, 'loss/train': 1.087448000907898} 08/31/2021 15:54:38 - INFO - __main__ - Step 147244: {'lr': 4.2799224950143547e-07, 'samples': 28270848, 'steps': 147243, 'loss/train': 0.805695116519928} 08/31/2021 15:54:38 - INFO - __main__ - Step 147245: {'lr': 4.276819175602353e-07, 'samples': 28271040, 'steps': 147244, 'loss/train': 1.5024218559265137} 08/31/2021 15:54:40 - INFO - __main__ - Step 147246: {'lr': 4.2737169807244293e-07, 'samples': 28271232, 'steps': 147245, 'loss/train': 0.6479320526123047} 08/31/2021 15:54:40 - INFO - __main__ - Step 147247: {'lr': 4.270615910382525e-07, 'samples': 28271424, 'steps': 147246, 'loss/train': 0.06425925344228745} 08/31/2021 15:54:41 - INFO - __main__ - Step 147248: {'lr': 4.2675159645777504e-07, 'samples': 28271616, 'steps': 147247, 'loss/train': 2.3146750926971436} 08/31/2021 15:54:41 - INFO - __main__ - Step 147249: {'lr': 4.264417143311494e-07, 'samples': 28271808, 'steps': 147248, 'loss/train': 0.22900255024433136} 08/31/2021 15:54:41 - INFO - __main__ - Step 147250: {'lr': 4.2613194465851436e-07, 'samples': 28272000, 'steps': 147249, 'loss/train': 0.10054288804531097} 08/31/2021 15:54:43 - INFO - __main__ - Step 147251: {'lr': 4.258222874400086e-07, 'samples': 28272192, 'steps': 147250, 'loss/train': 1.444608449935913} 08/31/2021 15:54:43 - INFO - __main__ - Step 147252: {'lr': 4.25512742675771e-07, 'samples': 28272384, 'steps': 147251, 'loss/train': 0.7910815477371216} 08/31/2021 15:54:44 - INFO - __main__ - Step 147253: {'lr': 4.2520331036596806e-07, 'samples': 28272576, 'steps': 147252, 'loss/train': 0.6008670926094055} 08/31/2021 15:54:44 - INFO - __main__ - Step 147254: {'lr': 4.24893990510683e-07, 'samples': 28272768, 'steps': 147253, 'loss/train': 0.8993385434150696} 08/31/2021 15:54:44 - INFO - __main__ - Step 147255: {'lr': 4.2458478311011015e-07, 'samples': 28272960, 'steps': 147254, 'loss/train': 0.8180072903633118} 08/31/2021 15:54:46 - INFO - __main__ - Step 147256: {'lr': 4.242756881643883e-07, 'samples': 28273152, 'steps': 147255, 'loss/train': 1.3460543155670166} 08/31/2021 15:54:46 - INFO - __main__ - Step 147257: {'lr': 4.2396670567360074e-07, 'samples': 28273344, 'steps': 147256, 'loss/train': 0.1807108223438263} 08/31/2021 15:54:47 - INFO - __main__ - Step 147258: {'lr': 4.236578356379417e-07, 'samples': 28273536, 'steps': 147257, 'loss/train': 1.598986029624939} 08/31/2021 15:54:47 - INFO - __main__ - Step 147259: {'lr': 4.233490780575222e-07, 'samples': 28273728, 'steps': 147258, 'loss/train': 1.2238538265228271} 08/31/2021 15:54:47 - INFO - __main__ - Step 147260: {'lr': 4.2304043293250883e-07, 'samples': 28273920, 'steps': 147259, 'loss/train': 0.3338411748409271} 08/31/2021 15:54:49 - INFO - __main__ - Step 147261: {'lr': 4.2273190026301256e-07, 'samples': 28274112, 'steps': 147260, 'loss/train': 0.9526783227920532} 08/31/2021 15:54:50 - INFO - __main__ - Step 147262: {'lr': 4.224234800491722e-07, 'samples': 28274304, 'steps': 147261, 'loss/train': 1.3933559656143188} 08/31/2021 15:54:50 - INFO - __main__ - Step 147263: {'lr': 4.2211517229115427e-07, 'samples': 28274496, 'steps': 147262, 'loss/train': 1.3167047500610352} 08/31/2021 15:54:51 - INFO - __main__ - Step 147264: {'lr': 4.2180697698906976e-07, 'samples': 28274688, 'steps': 147263, 'loss/train': 0.3497186005115509} 08/31/2021 15:54:51 - INFO - __main__ - Step 147265: {'lr': 4.2149889414305753e-07, 'samples': 28274880, 'steps': 147264, 'loss/train': 1.3126821517944336} 08/31/2021 15:54:51 - INFO - __main__ - Step 147266: {'lr': 4.2119092375328407e-07, 'samples': 28275072, 'steps': 147265, 'loss/train': 1.0823549032211304} 08/31/2021 15:54:53 - INFO - __main__ - Step 147267: {'lr': 4.2088306581986034e-07, 'samples': 28275264, 'steps': 147266, 'loss/train': 1.3406739234924316} 08/31/2021 15:54:53 - INFO - __main__ - Step 147268: {'lr': 4.2057532034292525e-07, 'samples': 28275456, 'steps': 147267, 'loss/train': 1.3915584087371826} 08/31/2021 15:54:54 - INFO - __main__ - Step 147269: {'lr': 4.202676873226452e-07, 'samples': 28275648, 'steps': 147268, 'loss/train': 2.0047271251678467} 08/31/2021 15:54:54 - INFO - __main__ - Step 147270: {'lr': 4.199601667591313e-07, 'samples': 28275840, 'steps': 147269, 'loss/train': 0.02541772462427616} 08/31/2021 15:54:54 - INFO - __main__ - Step 147271: {'lr': 4.1965275865255003e-07, 'samples': 28276032, 'steps': 147270, 'loss/train': 0.1798616200685501} 08/31/2021 15:54:56 - INFO - __main__ - Step 147272: {'lr': 4.193454630030125e-07, 'samples': 28276224, 'steps': 147271, 'loss/train': 0.8511913418769836} 08/31/2021 15:54:56 - INFO - __main__ - Step 147273: {'lr': 4.1903827981065736e-07, 'samples': 28276416, 'steps': 147272, 'loss/train': 1.021592378616333} 08/31/2021 15:54:57 - INFO - __main__ - Step 147274: {'lr': 4.187312090756512e-07, 'samples': 28276608, 'steps': 147273, 'loss/train': 1.0033494234085083} 08/31/2021 15:54:57 - INFO - __main__ - Step 147275: {'lr': 4.1842425079810506e-07, 'samples': 28276800, 'steps': 147274, 'loss/train': 0.9738830924034119} 08/31/2021 15:54:57 - INFO - __main__ - Step 147276: {'lr': 4.1811740497815777e-07, 'samples': 28276992, 'steps': 147275, 'loss/train': 1.135419487953186} 08/31/2021 15:54:59 - INFO - __main__ - Step 147277: {'lr': 4.1781067161594797e-07, 'samples': 28277184, 'steps': 147276, 'loss/train': 1.6997392177581787} 08/31/2021 15:55:00 - INFO - __main__ - Step 147278: {'lr': 4.175040507116423e-07, 'samples': 28277376, 'steps': 147277, 'loss/train': 1.455091118812561} 08/31/2021 15:55:00 - INFO - __main__ - Step 147279: {'lr': 4.171975422653518e-07, 'samples': 28277568, 'steps': 147278, 'loss/train': 0.9918901920318604} 08/31/2021 15:55:00 - INFO - __main__ - Step 147280: {'lr': 4.1689114627721514e-07, 'samples': 28277760, 'steps': 147279, 'loss/train': 1.6277155876159668} 08/31/2021 15:55:01 - INFO - __main__ - Step 147281: {'lr': 4.1658486274737115e-07, 'samples': 28277952, 'steps': 147280, 'loss/train': 1.5332204103469849} 08/31/2021 15:55:01 - INFO - __main__ - Step 147282: {'lr': 4.162786916759587e-07, 'samples': 28278144, 'steps': 147281, 'loss/train': 0.7139888405799866} 08/31/2021 15:55:03 - INFO - __main__ - Step 147283: {'lr': 4.1597263306314414e-07, 'samples': 28278336, 'steps': 147282, 'loss/train': 0.015344596467912197} 08/31/2021 15:55:03 - INFO - __main__ - Step 147284: {'lr': 4.1566668690903863e-07, 'samples': 28278528, 'steps': 147283, 'loss/train': 1.1576811075210571} 08/31/2021 15:55:03 - INFO - __main__ - Step 147285: {'lr': 4.1536085321375316e-07, 'samples': 28278720, 'steps': 147284, 'loss/train': 0.8771780133247375} 08/31/2021 15:55:04 - INFO - __main__ - Step 147286: {'lr': 4.1505513197748204e-07, 'samples': 28278912, 'steps': 147285, 'loss/train': 1.6887997388839722} 08/31/2021 15:55:04 - INFO - __main__ - Step 147287: {'lr': 4.147495232003362e-07, 'samples': 28279104, 'steps': 147286, 'loss/train': 0.8314182162284851} 08/31/2021 15:55:06 - INFO - __main__ - Step 147288: {'lr': 4.144440268824268e-07, 'samples': 28279296, 'steps': 147287, 'loss/train': 0.406919926404953} 08/31/2021 15:55:07 - INFO - __main__ - Step 147289: {'lr': 4.14138643023948e-07, 'samples': 28279488, 'steps': 147288, 'loss/train': 0.7537136077880859} 08/31/2021 15:55:07 - INFO - __main__ - Step 147290: {'lr': 4.1383337162498315e-07, 'samples': 28279680, 'steps': 147289, 'loss/train': 1.6156013011932373} 08/31/2021 15:55:07 - INFO - __main__ - Step 147291: {'lr': 4.1352821268569874e-07, 'samples': 28279872, 'steps': 147290, 'loss/train': 1.0904067754745483} 08/31/2021 15:55:08 - INFO - __main__ - Step 147292: {'lr': 4.1322316620623356e-07, 'samples': 28280064, 'steps': 147291, 'loss/train': 1.1147089004516602} 08/31/2021 15:55:08 - INFO - __main__ - Step 147293: {'lr': 4.129182321867264e-07, 'samples': 28280256, 'steps': 147292, 'loss/train': 1.5802563428878784} 08/31/2021 15:55:10 - INFO - __main__ - Step 147294: {'lr': 4.126134106272883e-07, 'samples': 28280448, 'steps': 147293, 'loss/train': 0.768143892288208} 08/31/2021 15:55:10 - INFO - __main__ - Step 147295: {'lr': 4.123087015280857e-07, 'samples': 28280640, 'steps': 147294, 'loss/train': 1.4623080492019653} 08/31/2021 15:55:10 - INFO - __main__ - Step 147296: {'lr': 4.1200410488925753e-07, 'samples': 28280832, 'steps': 147295, 'loss/train': 1.7285637855529785} 08/31/2021 15:55:11 - INFO - __main__ - Step 147297: {'lr': 4.116996207109147e-07, 'samples': 28281024, 'steps': 147296, 'loss/train': 1.170865535736084} 08/31/2021 15:55:11 - INFO - __main__ - Step 147298: {'lr': 4.11395248993196e-07, 'samples': 28281216, 'steps': 147297, 'loss/train': 1.1271735429763794} 08/31/2021 15:55:13 - INFO - __main__ - Step 147299: {'lr': 4.1109098973626804e-07, 'samples': 28281408, 'steps': 147298, 'loss/train': 0.7477739453315735} 08/31/2021 15:55:13 - INFO - __main__ - Step 147300: {'lr': 4.107868429402417e-07, 'samples': 28281600, 'steps': 147299, 'loss/train': 1.372625470161438} 08/31/2021 15:55:14 - INFO - __main__ - Step 147301: {'lr': 4.1048280860528363e-07, 'samples': 28281792, 'steps': 147300, 'loss/train': 0.9642738699913025} 08/31/2021 15:55:14 - INFO - __main__ - Step 147302: {'lr': 4.101788867315048e-07, 'samples': 28281984, 'steps': 147301, 'loss/train': 0.03832903504371643} 08/31/2021 15:55:14 - INFO - __main__ - Step 147303: {'lr': 4.0987507731904406e-07, 'samples': 28282176, 'steps': 147302, 'loss/train': 0.503314733505249} 08/31/2021 15:55:16 - INFO - __main__ - Step 147304: {'lr': 4.095713803680123e-07, 'samples': 28282368, 'steps': 147303, 'loss/train': 1.369084119796753} 08/31/2021 15:55:16 - INFO - __main__ - Step 147305: {'lr': 4.09267795878604e-07, 'samples': 28282560, 'steps': 147304, 'loss/train': 0.47181349992752075} 08/31/2021 15:55:17 - INFO - __main__ - Step 147306: {'lr': 4.0896432385093e-07, 'samples': 28282752, 'steps': 147305, 'loss/train': 0.9647570252418518} 08/31/2021 15:55:17 - INFO - __main__ - Step 147307: {'lr': 4.086609642851291e-07, 'samples': 28282944, 'steps': 147306, 'loss/train': 2.0204918384552} 08/31/2021 15:55:17 - INFO - __main__ - Step 147308: {'lr': 4.083577171813402e-07, 'samples': 28283136, 'steps': 147307, 'loss/train': 1.0032576322555542} 08/31/2021 15:55:19 - INFO - __main__ - Step 147309: {'lr': 4.080545825396742e-07, 'samples': 28283328, 'steps': 147308, 'loss/train': 0.9109102487564087} 08/31/2021 15:55:19 - INFO - __main__ - Step 147310: {'lr': 4.077515603602977e-07, 'samples': 28283520, 'steps': 147309, 'loss/train': 1.441416621208191} 08/31/2021 15:55:20 - INFO - __main__ - Step 147311: {'lr': 4.074486506433217e-07, 'samples': 28283712, 'steps': 147310, 'loss/train': 1.4022390842437744} 08/31/2021 15:55:20 - INFO - __main__ - Step 147312: {'lr': 4.071458533889127e-07, 'samples': 28283904, 'steps': 147311, 'loss/train': 0.9954402446746826} 08/31/2021 15:55:20 - INFO - __main__ - Step 147313: {'lr': 4.0684316859718185e-07, 'samples': 28284096, 'steps': 147312, 'loss/train': 0.897429347038269} 08/31/2021 15:55:23 - INFO - __main__ - Step 147314: {'lr': 4.0654059626829555e-07, 'samples': 28284288, 'steps': 147313, 'loss/train': 0.8915488719940186} 08/31/2021 15:55:23 - INFO - __main__ - Step 147315: {'lr': 4.062381364023371e-07, 'samples': 28284480, 'steps': 147314, 'loss/train': 0.6701155304908752} 08/31/2021 15:55:23 - INFO - __main__ - Step 147316: {'lr': 4.059357889995008e-07, 'samples': 28284672, 'steps': 147315, 'loss/train': 0.73176509141922} 08/31/2021 15:55:24 - INFO - __main__ - Step 147317: {'lr': 4.0563355405989766e-07, 'samples': 28284864, 'steps': 147316, 'loss/train': 1.6074870824813843} 08/31/2021 15:55:24 - INFO - __main__ - Step 147318: {'lr': 4.0533143158366647e-07, 'samples': 28285056, 'steps': 147317, 'loss/train': 1.008262038230896} 08/31/2021 15:55:24 - INFO - __main__ - Step 147319: {'lr': 4.0502942157094604e-07, 'samples': 28285248, 'steps': 147318, 'loss/train': 1.4567004442214966} 08/31/2021 15:55:26 - INFO - __main__ - Step 147320: {'lr': 4.047275240218473e-07, 'samples': 28285440, 'steps': 147319, 'loss/train': 1.3057034015655518} 08/31/2021 15:55:26 - INFO - __main__ - Step 147321: {'lr': 4.044257389365369e-07, 'samples': 28285632, 'steps': 147320, 'loss/train': 1.1958494186401367} 08/31/2021 15:55:27 - INFO - __main__ - Step 147322: {'lr': 4.041240663151535e-07, 'samples': 28285824, 'steps': 147321, 'loss/train': 0.6702435612678528} 08/31/2021 15:55:27 - INFO - __main__ - Step 147323: {'lr': 4.0382250615780823e-07, 'samples': 28286016, 'steps': 147322, 'loss/train': 0.1902715265750885} 08/31/2021 15:55:28 - INFO - __main__ - Step 147324: {'lr': 4.0352105846463985e-07, 'samples': 28286208, 'steps': 147323, 'loss/train': 0.9666156768798828} 08/31/2021 15:55:29 - INFO - __main__ - Step 147325: {'lr': 4.032197232358148e-07, 'samples': 28286400, 'steps': 147324, 'loss/train': 0.08428726345300674} 08/31/2021 15:55:29 - INFO - __main__ - Step 147326: {'lr': 4.029185004714164e-07, 'samples': 28286592, 'steps': 147325, 'loss/train': 1.155978798866272} 08/31/2021 15:55:30 - INFO - __main__ - Step 147327: {'lr': 4.02617390171639e-07, 'samples': 28286784, 'steps': 147326, 'loss/train': 1.184566855430603} 08/31/2021 15:55:30 - INFO - __main__ - Step 147328: {'lr': 4.0231639233659354e-07, 'samples': 28286976, 'steps': 147327, 'loss/train': 0.744377851486206} 08/31/2021 15:55:31 - INFO - __main__ - Step 147329: {'lr': 4.020155069663911e-07, 'samples': 28287168, 'steps': 147328, 'loss/train': 0.9690354466438293} 08/31/2021 15:55:31 - INFO - __main__ - Step 147330: {'lr': 4.0171473406119817e-07, 'samples': 28287360, 'steps': 147329, 'loss/train': 1.50806725025177} 08/31/2021 15:55:33 - INFO - __main__ - Step 147331: {'lr': 4.014140736211258e-07, 'samples': 28287552, 'steps': 147330, 'loss/train': 0.8580057621002197} 08/31/2021 15:55:34 - INFO - __main__ - Step 147332: {'lr': 4.011135256463405e-07, 'samples': 28287744, 'steps': 147331, 'loss/train': 0.48629772663116455} 08/31/2021 15:55:34 - INFO - __main__ - Step 147333: {'lr': 4.008130901369811e-07, 'samples': 28287936, 'steps': 147332, 'loss/train': 1.2972230911254883} 08/31/2021 15:55:34 - INFO - __main__ - Step 147334: {'lr': 4.0051276709315855e-07, 'samples': 28288128, 'steps': 147333, 'loss/train': 1.1041468381881714} 08/31/2021 15:55:35 - INFO - __main__ - Step 147335: {'lr': 4.0021255651498387e-07, 'samples': 28288320, 'steps': 147334, 'loss/train': 1.482036828994751} 08/31/2021 15:55:35 - INFO - __main__ - Step 147336: {'lr': 3.9991245840265147e-07, 'samples': 28288512, 'steps': 147335, 'loss/train': 0.3081664741039276} 08/31/2021 15:55:36 - INFO - __main__ - Step 147337: {'lr': 3.9961247275624445e-07, 'samples': 28288704, 'steps': 147336, 'loss/train': 0.05573245510458946} 08/31/2021 15:55:37 - INFO - __main__ - Step 147338: {'lr': 3.9931259957592946e-07, 'samples': 28288896, 'steps': 147337, 'loss/train': 0.736642599105835} 08/31/2021 15:55:37 - INFO - __main__ - Step 147339: {'lr': 3.990128388618175e-07, 'samples': 28289088, 'steps': 147338, 'loss/train': 1.3546730279922485} 08/31/2021 15:55:38 - INFO - __main__ - Step 147340: {'lr': 3.987131906140751e-07, 'samples': 28289280, 'steps': 147339, 'loss/train': 1.1313984394073486} 08/31/2021 15:55:38 - INFO - __main__ - Step 147341: {'lr': 3.9841365483284096e-07, 'samples': 28289472, 'steps': 147340, 'loss/train': 1.1225132942199707} 08/31/2021 15:55:39 - INFO - __main__ - Step 147342: {'lr': 3.9811423151819846e-07, 'samples': 28289664, 'steps': 147341, 'loss/train': 0.6817715764045715} 08/31/2021 15:55:40 - INFO - __main__ - Step 147343: {'lr': 3.9781492067031413e-07, 'samples': 28289856, 'steps': 147342, 'loss/train': 0.3893951177597046} 08/31/2021 15:55:40 - INFO - __main__ - Step 147344: {'lr': 3.975157222893266e-07, 'samples': 28290048, 'steps': 147343, 'loss/train': 1.2747210264205933} 08/31/2021 15:55:41 - INFO - __main__ - Step 147345: {'lr': 3.9721663637537486e-07, 'samples': 28290240, 'steps': 147344, 'loss/train': 0.5243844985961914} 08/31/2021 15:55:41 - INFO - __main__ - Step 147346: {'lr': 3.9691766292859753e-07, 'samples': 28290432, 'steps': 147345, 'loss/train': 1.7203058004379272} 08/31/2021 15:55:42 - INFO - __main__ - Step 147347: {'lr': 3.966188019491057e-07, 'samples': 28290624, 'steps': 147346, 'loss/train': 0.827803909778595} 08/31/2021 15:55:43 - INFO - __main__ - Step 147348: {'lr': 3.9632005343703816e-07, 'samples': 28290816, 'steps': 147347, 'loss/train': 1.0249443054199219} 08/31/2021 15:55:43 - INFO - __main__ - Step 147349: {'lr': 3.9602141739256136e-07, 'samples': 28291008, 'steps': 147348, 'loss/train': 1.659959077835083} 08/31/2021 15:55:44 - INFO - __main__ - Step 147350: {'lr': 3.9572289381575865e-07, 'samples': 28291200, 'steps': 147349, 'loss/train': 0.8895673155784607} 08/31/2021 15:55:44 - INFO - __main__ - Step 147351: {'lr': 3.954244827067965e-07, 'samples': 28291392, 'steps': 147350, 'loss/train': 0.7732047438621521} 08/31/2021 15:55:45 - INFO - __main__ - Step 147352: {'lr': 3.951261840658138e-07, 'samples': 28291584, 'steps': 147351, 'loss/train': 1.120715618133545} 08/31/2021 15:55:46 - INFO - __main__ - Step 147353: {'lr': 3.9482799789292147e-07, 'samples': 28291776, 'steps': 147352, 'loss/train': 0.7325787544250488} 08/31/2021 15:55:46 - INFO - __main__ - Step 147354: {'lr': 3.94529924188286e-07, 'samples': 28291968, 'steps': 147353, 'loss/train': 1.1008273363113403} 08/31/2021 15:55:47 - INFO - __main__ - Step 147355: {'lr': 3.942319629520186e-07, 'samples': 28292160, 'steps': 147354, 'loss/train': 1.1090030670166016} 08/31/2021 15:55:47 - INFO - __main__ - Step 147356: {'lr': 3.9393411418425786e-07, 'samples': 28292352, 'steps': 147355, 'loss/train': 0.23212096095085144} 08/31/2021 15:55:48 - INFO - __main__ - Step 147357: {'lr': 3.9363637788511487e-07, 'samples': 28292544, 'steps': 147356, 'loss/train': 0.9893768429756165} 08/31/2021 15:55:49 - INFO - __main__ - Step 147358: {'lr': 3.933387540547839e-07, 'samples': 28292736, 'steps': 147357, 'loss/train': 1.3991031646728516} 08/31/2021 15:55:49 - INFO - __main__ - Step 147359: {'lr': 3.930412426933483e-07, 'samples': 28292928, 'steps': 147358, 'loss/train': 2.0079946517944336} 08/31/2021 15:55:50 - INFO - __main__ - Step 147360: {'lr': 3.9274384380094676e-07, 'samples': 28293120, 'steps': 147359, 'loss/train': 1.093079924583435} 08/31/2021 15:55:50 - INFO - __main__ - Step 147361: {'lr': 3.9244655737774583e-07, 'samples': 28293312, 'steps': 147360, 'loss/train': 0.24704213440418243} 08/31/2021 15:55:51 - INFO - __main__ - Step 147362: {'lr': 3.921493834238288e-07, 'samples': 28293504, 'steps': 147361, 'loss/train': 0.9407469630241394} 08/31/2021 15:55:52 - INFO - __main__ - Step 147363: {'lr': 3.9185232193936214e-07, 'samples': 28293696, 'steps': 147362, 'loss/train': 1.191559910774231} 08/31/2021 15:55:52 - INFO - __main__ - Step 147364: {'lr': 3.9155537292448473e-07, 'samples': 28293888, 'steps': 147363, 'loss/train': 1.0388803482055664} 08/31/2021 15:55:53 - INFO - __main__ - Step 147365: {'lr': 3.912585363793353e-07, 'samples': 28294080, 'steps': 147364, 'loss/train': 0.7059980630874634} 08/31/2021 15:55:53 - INFO - __main__ - Step 147366: {'lr': 3.9096181230402486e-07, 'samples': 28294272, 'steps': 147365, 'loss/train': 2.2871785163879395} 08/31/2021 15:55:53 - INFO - __main__ - Step 147367: {'lr': 3.9066520069869217e-07, 'samples': 28294464, 'steps': 147366, 'loss/train': 1.214566707611084} 08/31/2021 15:55:55 - INFO - __main__ - Step 147368: {'lr': 3.903687015634483e-07, 'samples': 28294656, 'steps': 147367, 'loss/train': 1.3417384624481201} 08/31/2021 15:55:56 - INFO - __main__ - Step 147369: {'lr': 3.900723148984875e-07, 'samples': 28294848, 'steps': 147368, 'loss/train': 1.2477426528930664} 08/31/2021 15:55:56 - INFO - __main__ - Step 147370: {'lr': 3.8977604070389303e-07, 'samples': 28295040, 'steps': 147369, 'loss/train': 1.3526028394699097} 08/31/2021 15:55:57 - INFO - __main__ - Step 147371: {'lr': 3.8947987897980377e-07, 'samples': 28295232, 'steps': 147370, 'loss/train': 0.3189275562763214} 08/31/2021 15:55:57 - INFO - __main__ - Step 147372: {'lr': 3.891838297263861e-07, 'samples': 28295424, 'steps': 147371, 'loss/train': 1.0038083791732788} 08/31/2021 15:55:58 - INFO - __main__ - Step 147373: {'lr': 3.8888789294375115e-07, 'samples': 28295616, 'steps': 147372, 'loss/train': 1.7406731843948364} 08/31/2021 15:55:59 - INFO - __main__ - Step 147374: {'lr': 3.885920686320099e-07, 'samples': 28295808, 'steps': 147373, 'loss/train': 0.20152901113033295} 08/31/2021 15:55:59 - INFO - __main__ - Step 147375: {'lr': 3.882963567913289e-07, 'samples': 28296000, 'steps': 147374, 'loss/train': 0.7372331619262695} 08/31/2021 15:56:00 - INFO - __main__ - Step 147376: {'lr': 3.8800075742184695e-07, 'samples': 28296192, 'steps': 147375, 'loss/train': 1.5518462657928467} 08/31/2021 15:56:00 - INFO - __main__ - Step 147377: {'lr': 3.877052705236472e-07, 'samples': 28296384, 'steps': 147376, 'loss/train': 1.0267350673675537} 08/31/2021 15:56:01 - INFO - __main__ - Step 147378: {'lr': 3.874098960969241e-07, 'samples': 28296576, 'steps': 147377, 'loss/train': 0.7823746204376221} 08/31/2021 15:56:02 - INFO - __main__ - Step 147379: {'lr': 3.8711463414176087e-07, 'samples': 28296768, 'steps': 147378, 'loss/train': 0.967339277267456} 08/31/2021 15:56:02 - INFO - __main__ - Step 147380: {'lr': 3.8681948465832396e-07, 'samples': 28296960, 'steps': 147379, 'loss/train': 1.3255127668380737} 08/31/2021 15:56:03 - INFO - __main__ - Step 147381: {'lr': 3.8652444764672446e-07, 'samples': 28297152, 'steps': 147380, 'loss/train': 1.1522886753082275} 08/31/2021 15:56:03 - INFO - __main__ - Step 147382: {'lr': 3.862295231071011e-07, 'samples': 28297344, 'steps': 147381, 'loss/train': 1.2668805122375488} 08/31/2021 15:56:05 - INFO - __main__ - Step 147383: {'lr': 3.859347110396205e-07, 'samples': 28297536, 'steps': 147382, 'loss/train': 1.3310195207595825} 08/31/2021 15:56:05 - INFO - __main__ - Step 147384: {'lr': 3.856400114443659e-07, 'samples': 28297728, 'steps': 147383, 'loss/train': 1.9488420486450195} 08/31/2021 15:56:06 - INFO - __main__ - Step 147385: {'lr': 3.85345424321476e-07, 'samples': 28297920, 'steps': 147384, 'loss/train': 0.4307812452316284} 08/31/2021 15:56:06 - INFO - __main__ - Step 147386: {'lr': 3.850509496711174e-07, 'samples': 28298112, 'steps': 147385, 'loss/train': 1.2014068365097046} 08/31/2021 15:56:06 - INFO - __main__ - Step 147387: {'lr': 3.8475658749340116e-07, 'samples': 28298304, 'steps': 147386, 'loss/train': 0.9425061345100403} 08/31/2021 15:56:07 - INFO - __main__ - Step 147388: {'lr': 3.8446233778846596e-07, 'samples': 28298496, 'steps': 147387, 'loss/train': 0.651945173740387} 08/31/2021 15:56:08 - INFO - __main__ - Step 147389: {'lr': 3.841682005564229e-07, 'samples': 28298688, 'steps': 147388, 'loss/train': 0.6974482536315918} 08/31/2021 15:56:09 - INFO - __main__ - Step 147390: {'lr': 3.8387417579743844e-07, 'samples': 28298880, 'steps': 147389, 'loss/train': 1.3583043813705444} 08/31/2021 15:56:09 - INFO - __main__ - Step 147391: {'lr': 3.835802635116237e-07, 'samples': 28299072, 'steps': 147390, 'loss/train': 0.8703045845031738} 08/31/2021 15:56:09 - INFO - __main__ - Step 147392: {'lr': 3.8328646369911735e-07, 'samples': 28299264, 'steps': 147391, 'loss/train': 0.8368236422538757} 08/31/2021 15:56:10 - INFO - __main__ - Step 147393: {'lr': 3.829927763600305e-07, 'samples': 28299456, 'steps': 147392, 'loss/train': 1.1837246417999268} 08/31/2021 15:56:11 - INFO - __main__ - Step 147394: {'lr': 3.826992014945296e-07, 'samples': 28299648, 'steps': 147393, 'loss/train': 1.0260517597198486} 08/31/2021 15:56:12 - INFO - __main__ - Step 147395: {'lr': 3.8240573910275356e-07, 'samples': 28299840, 'steps': 147394, 'loss/train': 0.8310099840164185} 08/31/2021 15:56:12 - INFO - __main__ - Step 147396: {'lr': 3.8211238918478554e-07, 'samples': 28300032, 'steps': 147395, 'loss/train': 1.1979073286056519} 08/31/2021 15:56:13 - INFO - __main__ - Step 147397: {'lr': 3.8181915174079204e-07, 'samples': 28300224, 'steps': 147396, 'loss/train': 0.8236948251724243} 08/31/2021 15:56:13 - INFO - __main__ - Step 147398: {'lr': 3.81526026770912e-07, 'samples': 28300416, 'steps': 147397, 'loss/train': 0.8274499177932739} 08/31/2021 15:56:14 - INFO - __main__ - Step 147399: {'lr': 3.8123301427525623e-07, 'samples': 28300608, 'steps': 147398, 'loss/train': 0.5071419477462769} 08/31/2021 15:56:15 - INFO - __main__ - Step 147400: {'lr': 3.809401142539637e-07, 'samples': 28300800, 'steps': 147399, 'loss/train': 1.3424913883209229} 08/31/2021 15:56:15 - INFO - __main__ - Step 147401: {'lr': 3.8064732670717304e-07, 'samples': 28300992, 'steps': 147400, 'loss/train': 0.9594595432281494} 08/31/2021 15:56:15 - INFO - __main__ - Step 147402: {'lr': 3.8035465163499537e-07, 'samples': 28301184, 'steps': 147401, 'loss/train': 1.1314607858657837} 08/31/2021 15:56:16 - INFO - __main__ - Step 147403: {'lr': 3.800620890375972e-07, 'samples': 28301376, 'steps': 147402, 'loss/train': 0.5823214054107666} 08/31/2021 15:56:17 - INFO - __main__ - Step 147404: {'lr': 3.7976963891508953e-07, 'samples': 28301568, 'steps': 147403, 'loss/train': 0.9891665577888489} 08/31/2021 15:56:18 - INFO - __main__ - Step 147405: {'lr': 3.794773012675834e-07, 'samples': 28301760, 'steps': 147404, 'loss/train': 0.9958030581474304} 08/31/2021 15:56:18 - INFO - __main__ - Step 147406: {'lr': 3.7918507609524534e-07, 'samples': 28301952, 'steps': 147405, 'loss/train': 1.4427183866500854} 08/31/2021 15:56:18 - INFO - __main__ - Step 147407: {'lr': 3.788929633982141e-07, 'samples': 28302144, 'steps': 147406, 'loss/train': 0.9803681373596191} 08/31/2021 15:56:19 - INFO - __main__ - Step 147408: {'lr': 3.78600963176573e-07, 'samples': 28302336, 'steps': 147407, 'loss/train': 1.001212239265442} 08/31/2021 15:56:20 - INFO - __main__ - Step 147409: {'lr': 3.7830907543048854e-07, 'samples': 28302528, 'steps': 147408, 'loss/train': 1.118463158607483} 08/31/2021 15:56:21 - INFO - __main__ - Step 147410: {'lr': 3.780173001600995e-07, 'samples': 28302720, 'steps': 147409, 'loss/train': 1.19722580909729} 08/31/2021 15:56:21 - INFO - __main__ - Step 147411: {'lr': 3.777256373655169e-07, 'samples': 28302912, 'steps': 147410, 'loss/train': 0.09684344381093979} 08/31/2021 15:56:22 - INFO - __main__ - Step 147412: {'lr': 3.7743408704687953e-07, 'samples': 28303104, 'steps': 147411, 'loss/train': 0.4643876850605011} 08/31/2021 15:56:22 - INFO - __main__ - Step 147413: {'lr': 3.771426492043262e-07, 'samples': 28303296, 'steps': 147412, 'loss/train': 0.28367170691490173} 08/31/2021 15:56:24 - INFO - __main__ - Step 147414: {'lr': 3.768513238379678e-07, 'samples': 28303488, 'steps': 147413, 'loss/train': 1.7393107414245605} 08/31/2021 15:56:24 - INFO - __main__ - Step 147415: {'lr': 3.7656011094794327e-07, 'samples': 28303680, 'steps': 147414, 'loss/train': 0.8280009627342224} 08/31/2021 15:56:24 - INFO - __main__ - Step 147416: {'lr': 3.762690105343913e-07, 'samples': 28303872, 'steps': 147415, 'loss/train': 1.670923113822937} 08/31/2021 15:56:25 - INFO - __main__ - Step 147417: {'lr': 3.7597802259745075e-07, 'samples': 28304064, 'steps': 147416, 'loss/train': 1.2275125980377197} 08/31/2021 15:56:25 - INFO - __main__ - Step 147418: {'lr': 3.756871471372325e-07, 'samples': 28304256, 'steps': 147417, 'loss/train': 1.0375508069992065} 08/31/2021 15:56:27 - INFO - __main__ - Step 147419: {'lr': 3.753963841539032e-07, 'samples': 28304448, 'steps': 147418, 'loss/train': 1.3311622142791748} 08/31/2021 15:56:28 - INFO - __main__ - Step 147420: {'lr': 3.7510573364754606e-07, 'samples': 28304640, 'steps': 147419, 'loss/train': 0.9358599185943604} 08/31/2021 15:56:28 - INFO - __main__ - Step 147421: {'lr': 3.7481519561832765e-07, 'samples': 28304832, 'steps': 147420, 'loss/train': 1.501084327697754} 08/31/2021 15:56:28 - INFO - __main__ - Step 147422: {'lr': 3.7452477006633124e-07, 'samples': 28305024, 'steps': 147421, 'loss/train': 0.4785389304161072} 08/31/2021 15:56:29 - INFO - __main__ - Step 147423: {'lr': 3.7423445699175107e-07, 'samples': 28305216, 'steps': 147422, 'loss/train': 1.278638243675232} 08/31/2021 15:56:29 - INFO - __main__ - Step 147424: {'lr': 3.739442563946982e-07, 'samples': 28305408, 'steps': 147423, 'loss/train': 1.5117121934890747} 08/31/2021 15:56:31 - INFO - __main__ - Step 147425: {'lr': 3.7365416827528364e-07, 'samples': 28305600, 'steps': 147424, 'loss/train': 0.7711173892021179} 08/31/2021 15:56:31 - INFO - __main__ - Step 147426: {'lr': 3.733641926336462e-07, 'samples': 28305792, 'steps': 147425, 'loss/train': 0.7485366463661194} 08/31/2021 15:56:32 - INFO - __main__ - Step 147427: {'lr': 3.7307432946989685e-07, 'samples': 28305984, 'steps': 147426, 'loss/train': 0.09576380252838135} 08/31/2021 15:56:32 - INFO - __main__ - Step 147428: {'lr': 3.7278457878422987e-07, 'samples': 28306176, 'steps': 147427, 'loss/train': 0.16767428815364838} 08/31/2021 15:56:33 - INFO - __main__ - Step 147429: {'lr': 3.7249494057670084e-07, 'samples': 28306368, 'steps': 147428, 'loss/train': 0.7692899107933044} 08/31/2021 15:56:34 - INFO - __main__ - Step 147430: {'lr': 3.7220541484747627e-07, 'samples': 28306560, 'steps': 147429, 'loss/train': 1.0917930603027344} 08/31/2021 15:56:35 - INFO - __main__ - Step 147431: {'lr': 3.719160015966949e-07, 'samples': 28306752, 'steps': 147430, 'loss/train': 1.1830408573150635} 08/31/2021 15:56:35 - INFO - __main__ - Step 147432: {'lr': 3.7162670082449556e-07, 'samples': 28306944, 'steps': 147431, 'loss/train': 3.6603143215179443} 08/31/2021 15:56:35 - INFO - __main__ - Step 147433: {'lr': 3.713375125309615e-07, 'samples': 28307136, 'steps': 147432, 'loss/train': 1.1640517711639404} 08/31/2021 15:56:36 - INFO - __main__ - Step 147434: {'lr': 3.710484367162592e-07, 'samples': 28307328, 'steps': 147433, 'loss/train': 1.092061996459961} 08/31/2021 15:56:36 - INFO - __main__ - Step 147435: {'lr': 3.7075947338049976e-07, 'samples': 28307520, 'steps': 147434, 'loss/train': 0.5488002300262451} 08/31/2021 15:56:38 - INFO - __main__ - Step 147436: {'lr': 3.704706225238497e-07, 'samples': 28307712, 'steps': 147435, 'loss/train': 0.6144431233406067} 08/31/2021 15:56:38 - INFO - __main__ - Step 147437: {'lr': 3.701818841463922e-07, 'samples': 28307904, 'steps': 147436, 'loss/train': 0.6825043559074402} 08/31/2021 15:56:39 - INFO - __main__ - Step 147438: {'lr': 3.698932582482939e-07, 'samples': 28308096, 'steps': 147437, 'loss/train': 1.1148574352264404} 08/31/2021 15:56:39 - INFO - __main__ - Step 147439: {'lr': 3.69604744829638e-07, 'samples': 28308288, 'steps': 147438, 'loss/train': 0.01402879599481821} 08/31/2021 15:56:39 - INFO - __main__ - Step 147440: {'lr': 3.693163438906189e-07, 'samples': 28308480, 'steps': 147439, 'loss/train': 1.0433382987976074} 08/31/2021 15:56:40 - INFO - __main__ - Step 147441: {'lr': 3.6902805543131966e-07, 'samples': 28308672, 'steps': 147440, 'loss/train': 0.30136528611183167} 08/31/2021 15:56:41 - INFO - __main__ - Step 147442: {'lr': 3.6873987945187926e-07, 'samples': 28308864, 'steps': 147441, 'loss/train': 1.1449257135391235} 08/31/2021 15:56:42 - INFO - __main__ - Step 147443: {'lr': 3.6845181595246416e-07, 'samples': 28309056, 'steps': 147442, 'loss/train': 1.0694187879562378} 08/31/2021 15:56:42 - INFO - __main__ - Step 147444: {'lr': 3.681638649331298e-07, 'samples': 28309248, 'steps': 147443, 'loss/train': 1.133899211883545} 08/31/2021 15:56:43 - INFO - __main__ - Step 147445: {'lr': 3.678760263940706e-07, 'samples': 28309440, 'steps': 147444, 'loss/train': 0.9610821008682251} 08/31/2021 15:56:43 - INFO - __main__ - Step 147446: {'lr': 3.6758830033539746e-07, 'samples': 28309632, 'steps': 147445, 'loss/train': 1.1576217412948608} 08/31/2021 15:56:43 - INFO - __main__ - Step 147447: {'lr': 3.6730068675722153e-07, 'samples': 28309824, 'steps': 147446, 'loss/train': 0.015162200666964054} 08/31/2021 15:56:45 - INFO - __main__ - Step 147448: {'lr': 3.670131856597092e-07, 'samples': 28310016, 'steps': 147447, 'loss/train': 1.4256157875061035} 08/31/2021 15:56:45 - INFO - __main__ - Step 147449: {'lr': 3.6672579704297157e-07, 'samples': 28310208, 'steps': 147448, 'loss/train': 0.9643590450286865} 08/31/2021 15:56:46 - INFO - __main__ - Step 147450: {'lr': 3.664385209071197e-07, 'samples': 28310400, 'steps': 147449, 'loss/train': 1.1766709089279175} 08/31/2021 15:56:46 - INFO - __main__ - Step 147451: {'lr': 3.6615135725229234e-07, 'samples': 28310592, 'steps': 147450, 'loss/train': 1.409184455871582} 08/31/2021 15:56:46 - INFO - __main__ - Step 147452: {'lr': 3.658643060786282e-07, 'samples': 28310784, 'steps': 147451, 'loss/train': 0.5905706882476807} 08/31/2021 15:56:48 - INFO - __main__ - Step 147453: {'lr': 3.6557736738626613e-07, 'samples': 28310976, 'steps': 147452, 'loss/train': 1.8052723407745361} 08/31/2021 15:56:48 - INFO - __main__ - Step 147454: {'lr': 3.6529054117531715e-07, 'samples': 28311168, 'steps': 147453, 'loss/train': 1.304727554321289} 08/31/2021 15:56:49 - INFO - __main__ - Step 147455: {'lr': 3.6500382744589224e-07, 'samples': 28311360, 'steps': 147454, 'loss/train': 1.163197636604309} 08/31/2021 15:56:49 - INFO - __main__ - Step 147456: {'lr': 3.647172261981857e-07, 'samples': 28311552, 'steps': 147455, 'loss/train': 0.21511125564575195} 08/31/2021 15:56:50 - INFO - __main__ - Step 147457: {'lr': 3.644307374322531e-07, 'samples': 28311744, 'steps': 147456, 'loss/train': 0.9302747249603271} 08/31/2021 15:56:51 - INFO - __main__ - Step 147458: {'lr': 3.641443611482609e-07, 'samples': 28311936, 'steps': 147457, 'loss/train': 1.5146961212158203} 08/31/2021 15:56:51 - INFO - __main__ - Step 147459: {'lr': 3.638580973463479e-07, 'samples': 28312128, 'steps': 147458, 'loss/train': 0.9625511169433594} 08/31/2021 15:56:52 - INFO - __main__ - Step 147460: {'lr': 3.6357194602662514e-07, 'samples': 28312320, 'steps': 147459, 'loss/train': 0.8755598664283752} 08/31/2021 15:56:52 - INFO - __main__ - Step 147461: {'lr': 3.632859071892314e-07, 'samples': 28312512, 'steps': 147460, 'loss/train': 0.9553008079528809} 08/31/2021 15:56:52 - INFO - __main__ - Step 147462: {'lr': 3.629999808342777e-07, 'samples': 28312704, 'steps': 147461, 'loss/train': 0.20765931904315948} 08/31/2021 15:56:53 - INFO - __main__ - Step 147463: {'lr': 3.6271416696190276e-07, 'samples': 28312896, 'steps': 147462, 'loss/train': 0.5781210660934448} 08/31/2021 15:56:55 - INFO - __main__ - Step 147464: {'lr': 3.6242846557221765e-07, 'samples': 28313088, 'steps': 147463, 'loss/train': 1.1222865581512451} 08/31/2021 15:56:55 - INFO - __main__ - Step 147465: {'lr': 3.621428766654167e-07, 'samples': 28313280, 'steps': 147464, 'loss/train': 0.03488325700163841} 08/31/2021 15:56:55 - INFO - __main__ - Step 147466: {'lr': 3.6185740024155535e-07, 'samples': 28313472, 'steps': 147465, 'loss/train': 0.745933473110199} 08/31/2021 15:56:56 - INFO - __main__ - Step 147467: {'lr': 3.615720363007724e-07, 'samples': 28313664, 'steps': 147466, 'loss/train': 0.3888287842273712} 08/31/2021 15:56:56 - INFO - __main__ - Step 147468: {'lr': 3.612867848432344e-07, 'samples': 28313856, 'steps': 147467, 'loss/train': 1.1935820579528809} 08/31/2021 15:56:58 - INFO - __main__ - Step 147469: {'lr': 3.6100164586905236e-07, 'samples': 28314048, 'steps': 147468, 'loss/train': 1.0636467933654785} 08/31/2021 15:56:58 - INFO - __main__ - Step 147470: {'lr': 3.607166193783373e-07, 'samples': 28314240, 'steps': 147469, 'loss/train': 1.0611642599105835} 08/31/2021 15:56:59 - INFO - __main__ - Step 147471: {'lr': 3.6043170537122807e-07, 'samples': 28314432, 'steps': 147470, 'loss/train': 0.6204034686088562} 08/31/2021 15:56:59 - INFO - __main__ - Step 147472: {'lr': 3.601469038478633e-07, 'samples': 28314624, 'steps': 147471, 'loss/train': 1.7654392719268799} 08/31/2021 15:56:59 - INFO - __main__ - Step 147473: {'lr': 3.5986221480838186e-07, 'samples': 28314816, 'steps': 147472, 'loss/train': 0.8155888915061951} 08/31/2021 15:57:01 - INFO - __main__ - Step 147474: {'lr': 3.59577638252867e-07, 'samples': 28315008, 'steps': 147473, 'loss/train': 1.7551472187042236} 08/31/2021 15:57:02 - INFO - __main__ - Step 147475: {'lr': 3.5929317418148534e-07, 'samples': 28315200, 'steps': 147474, 'loss/train': 0.1751527637243271} 08/31/2021 15:57:02 - INFO - __main__ - Step 147476: {'lr': 3.5900882259434777e-07, 'samples': 28315392, 'steps': 147475, 'loss/train': 1.4909934997558594} 08/31/2021 15:57:02 - INFO - __main__ - Step 147477: {'lr': 3.5872458349162086e-07, 'samples': 28315584, 'steps': 147476, 'loss/train': 1.2088825702667236} 08/31/2021 15:57:03 - INFO - __main__ - Step 147478: {'lr': 3.5844045687336015e-07, 'samples': 28315776, 'steps': 147477, 'loss/train': 1.2985807657241821} 08/31/2021 15:57:04 - INFO - __main__ - Step 147479: {'lr': 3.581564427397599e-07, 'samples': 28315968, 'steps': 147478, 'loss/train': 1.246227502822876} 08/31/2021 15:57:05 - INFO - __main__ - Step 147480: {'lr': 3.578725410909034e-07, 'samples': 28316160, 'steps': 147479, 'loss/train': 0.7806896567344666} 08/31/2021 15:57:05 - INFO - __main__ - Step 147481: {'lr': 3.5758875192695716e-07, 'samples': 28316352, 'steps': 147480, 'loss/train': 1.5237233638763428} 08/31/2021 15:57:05 - INFO - __main__ - Step 147482: {'lr': 3.5730507524800446e-07, 'samples': 28316544, 'steps': 147481, 'loss/train': 0.2588030993938446} 08/31/2021 15:57:06 - INFO - __main__ - Step 147483: {'lr': 3.570215110542119e-07, 'samples': 28316736, 'steps': 147482, 'loss/train': 0.6292246580123901} 08/31/2021 15:57:07 - INFO - __main__ - Step 147484: {'lr': 3.5673805934569035e-07, 'samples': 28316928, 'steps': 147483, 'loss/train': 1.0525680780410767} 08/31/2021 15:57:07 - INFO - __main__ - Step 147485: {'lr': 3.5645472012257876e-07, 'samples': 28317120, 'steps': 147484, 'loss/train': 1.2707810401916504} 08/31/2021 15:57:08 - INFO - __main__ - Step 147486: {'lr': 3.56171493384988e-07, 'samples': 28317312, 'steps': 147485, 'loss/train': 0.7032885551452637} 08/31/2021 15:57:08 - INFO - __main__ - Step 147487: {'lr': 3.5588837913305695e-07, 'samples': 28317504, 'steps': 147486, 'loss/train': 1.0819448232650757} 08/31/2021 15:57:08 - INFO - __main__ - Step 147488: {'lr': 3.5560537736689656e-07, 'samples': 28317696, 'steps': 147487, 'loss/train': 0.950527012348175} 08/31/2021 15:57:10 - INFO - __main__ - Step 147489: {'lr': 3.5532248808667345e-07, 'samples': 28317888, 'steps': 147488, 'loss/train': 0.7624148726463318} 08/31/2021 15:57:11 - INFO - __main__ - Step 147490: {'lr': 3.5503971129247083e-07, 'samples': 28318080, 'steps': 147489, 'loss/train': 0.7014734745025635} 08/31/2021 15:57:11 - INFO - __main__ - Step 147491: {'lr': 3.547570469844275e-07, 'samples': 28318272, 'steps': 147490, 'loss/train': 0.7633970975875854} 08/31/2021 15:57:11 - INFO - __main__ - Step 147492: {'lr': 3.544744951626822e-07, 'samples': 28318464, 'steps': 147491, 'loss/train': 0.12117817997932434} 08/31/2021 15:57:12 - INFO - __main__ - Step 147493: {'lr': 3.541920558273737e-07, 'samples': 28318656, 'steps': 147492, 'loss/train': 0.28154289722442627} 08/31/2021 15:57:13 - INFO - __main__ - Step 147494: {'lr': 3.5390972897861305e-07, 'samples': 28318848, 'steps': 147493, 'loss/train': 0.046531256288290024} 08/31/2021 15:57:14 - INFO - __main__ - Step 147495: {'lr': 3.536275146165391e-07, 'samples': 28319040, 'steps': 147494, 'loss/train': 0.6204138994216919} 08/31/2021 15:57:14 - INFO - __main__ - Step 147496: {'lr': 3.53345412741235e-07, 'samples': 28319232, 'steps': 147495, 'loss/train': 1.034210443496704} 08/31/2021 15:57:15 - INFO - __main__ - Step 147497: {'lr': 3.530634233528951e-07, 'samples': 28319424, 'steps': 147496, 'loss/train': 0.3541390895843506} 08/31/2021 15:57:15 - INFO - __main__ - Step 147498: {'lr': 3.5278154645157487e-07, 'samples': 28319616, 'steps': 147497, 'loss/train': 2.471832513809204} 08/31/2021 15:57:15 - INFO - __main__ - Step 147499: {'lr': 3.524997820374687e-07, 'samples': 28319808, 'steps': 147498, 'loss/train': 1.3627538681030273} 08/31/2021 15:57:17 - INFO - __main__ - Step 147500: {'lr': 3.522181301106597e-07, 'samples': 28320000, 'steps': 147499, 'loss/train': 2.210113286972046} 08/31/2021 15:57:18 - INFO - __main__ - Step 147501: {'lr': 3.5193659067131456e-07, 'samples': 28320192, 'steps': 147500, 'loss/train': 1.1302473545074463} 08/31/2021 15:57:18 - INFO - __main__ - Step 147502: {'lr': 3.5165516371951647e-07, 'samples': 28320384, 'steps': 147501, 'loss/train': 1.113875389099121} 08/31/2021 15:57:18 - INFO - __main__ - Step 147503: {'lr': 3.5137384925540414e-07, 'samples': 28320576, 'steps': 147502, 'loss/train': 0.5711328387260437} 08/31/2021 15:57:19 - INFO - __main__ - Step 147504: {'lr': 3.510926472791165e-07, 'samples': 28320768, 'steps': 147503, 'loss/train': 1.063319444656372} 08/31/2021 15:57:19 - INFO - __main__ - Step 147505: {'lr': 3.508115577907645e-07, 'samples': 28320960, 'steps': 147504, 'loss/train': 1.3534116744995117} 08/31/2021 15:57:20 - INFO - __main__ - Step 147506: {'lr': 3.505305807904868e-07, 'samples': 28321152, 'steps': 147505, 'loss/train': 0.38797906041145325} 08/31/2021 15:57:21 - INFO - __main__ - Step 147507: {'lr': 3.502497162784224e-07, 'samples': 28321344, 'steps': 147506, 'loss/train': 0.20358221232891083} 08/31/2021 15:57:21 - INFO - __main__ - Step 147508: {'lr': 3.4996896425468216e-07, 'samples': 28321536, 'steps': 147507, 'loss/train': 0.33763617277145386} 08/31/2021 15:57:22 - INFO - __main__ - Step 147509: {'lr': 3.4968832471937715e-07, 'samples': 28321728, 'steps': 147508, 'loss/train': 0.44716933369636536} 08/31/2021 15:57:22 - INFO - __main__ - Step 147510: {'lr': 3.494077976726462e-07, 'samples': 28321920, 'steps': 147509, 'loss/train': 1.3591421842575073} 08/31/2021 15:57:23 - INFO - __main__ - Step 147511: {'lr': 3.4912738311465574e-07, 'samples': 28322112, 'steps': 147510, 'loss/train': 1.538789987564087} 08/31/2021 15:57:24 - INFO - __main__ - Step 147512: {'lr': 3.4884708104546137e-07, 'samples': 28322304, 'steps': 147511, 'loss/train': 1.0178465843200684} 08/31/2021 15:57:24 - INFO - __main__ - Step 147513: {'lr': 3.4856689146522957e-07, 'samples': 28322496, 'steps': 147512, 'loss/train': 1.7877366542816162} 08/31/2021 15:57:25 - INFO - __main__ - Step 147514: {'lr': 3.4828681437409913e-07, 'samples': 28322688, 'steps': 147513, 'loss/train': 1.449894905090332} 08/31/2021 15:57:25 - INFO - __main__ - Step 147515: {'lr': 3.4800684977215334e-07, 'samples': 28322880, 'steps': 147514, 'loss/train': 1.704241394996643} 08/31/2021 15:57:25 - INFO - __main__ - Step 147516: {'lr': 3.4772699765955874e-07, 'samples': 28323072, 'steps': 147515, 'loss/train': 0.851742148399353} 08/31/2021 15:57:27 - INFO - __main__ - Step 147517: {'lr': 3.474472580364263e-07, 'samples': 28323264, 'steps': 147516, 'loss/train': 1.7957658767700195} 08/31/2021 15:57:27 - INFO - __main__ - Step 147518: {'lr': 3.4716763090286707e-07, 'samples': 28323456, 'steps': 147517, 'loss/train': 0.8952515125274658} 08/31/2021 15:57:28 - INFO - __main__ - Step 147519: {'lr': 3.468881162590476e-07, 'samples': 28323648, 'steps': 147518, 'loss/train': 0.6878057718276978} 08/31/2021 15:57:28 - INFO - __main__ - Step 147520: {'lr': 3.4660871410505114e-07, 'samples': 28323840, 'steps': 147519, 'loss/train': 0.952942967414856} 08/31/2021 15:57:28 - INFO - __main__ - Step 147521: {'lr': 3.4632942444101647e-07, 'samples': 28324032, 'steps': 147520, 'loss/train': 0.597516655921936} 08/31/2021 15:57:30 - INFO - __main__ - Step 147522: {'lr': 3.4605024726708235e-07, 'samples': 28324224, 'steps': 147521, 'loss/train': 1.1791515350341797} 08/31/2021 15:57:31 - INFO - __main__ - Step 147523: {'lr': 3.457711825833598e-07, 'samples': 28324416, 'steps': 147522, 'loss/train': 0.85402512550354} 08/31/2021 15:57:31 - INFO - __main__ - Step 147524: {'lr': 3.454922303899877e-07, 'samples': 28324608, 'steps': 147523, 'loss/train': 0.6574445962905884} 08/31/2021 15:57:32 - INFO - __main__ - Step 147525: {'lr': 3.4521339068707694e-07, 'samples': 28324800, 'steps': 147524, 'loss/train': 0.9787129759788513} 08/31/2021 15:57:32 - INFO - __main__ - Step 147526: {'lr': 3.4493466347476634e-07, 'samples': 28324992, 'steps': 147525, 'loss/train': 0.03148568421602249} 08/31/2021 15:57:33 - INFO - __main__ - Step 147527: {'lr': 3.446560487531669e-07, 'samples': 28325184, 'steps': 147526, 'loss/train': 0.6839362382888794} 08/31/2021 15:57:34 - INFO - __main__ - Step 147528: {'lr': 3.443775465224175e-07, 'samples': 28325376, 'steps': 147527, 'loss/train': 0.8180304169654846} 08/31/2021 15:57:34 - INFO - __main__ - Step 147529: {'lr': 3.440991567826568e-07, 'samples': 28325568, 'steps': 147528, 'loss/train': 1.0171328783035278} 08/31/2021 15:57:35 - INFO - __main__ - Step 147530: {'lr': 3.438208795339681e-07, 'samples': 28325760, 'steps': 147529, 'loss/train': 0.7406070828437805} 08/31/2021 15:57:35 - INFO - __main__ - Step 147531: {'lr': 3.43542714776518e-07, 'samples': 28325952, 'steps': 147530, 'loss/train': 1.0662275552749634} 08/31/2021 15:57:37 - INFO - __main__ - Step 147532: {'lr': 3.432646625103897e-07, 'samples': 28326144, 'steps': 147531, 'loss/train': 1.177799105644226} 08/31/2021 15:57:38 - INFO - __main__ - Step 147533: {'lr': 3.4298672273577744e-07, 'samples': 28326336, 'steps': 147532, 'loss/train': 1.2986429929733276} 08/31/2021 15:57:38 - INFO - __main__ - Step 147534: {'lr': 3.427088954527369e-07, 'samples': 28326528, 'steps': 147533, 'loss/train': 0.09255031496286392} 08/31/2021 15:57:38 - INFO - __main__ - Step 147535: {'lr': 3.4243118066140665e-07, 'samples': 28326720, 'steps': 147534, 'loss/train': 0.8697530627250671} 08/31/2021 15:57:39 - INFO - __main__ - Step 147536: {'lr': 3.4215357836195336e-07, 'samples': 28326912, 'steps': 147535, 'loss/train': 0.9993215799331665} 08/31/2021 15:57:39 - INFO - __main__ - Step 147537: {'lr': 3.4187608855443255e-07, 'samples': 28327104, 'steps': 147536, 'loss/train': 0.0270112045109272} 08/31/2021 15:57:41 - INFO - __main__ - Step 147538: {'lr': 3.415987112390384e-07, 'samples': 28327296, 'steps': 147537, 'loss/train': 1.2960405349731445} 08/31/2021 15:57:41 - INFO - __main__ - Step 147539: {'lr': 3.4132144641588205e-07, 'samples': 28327488, 'steps': 147538, 'loss/train': 0.8903948664665222} 08/31/2021 15:57:42 - INFO - __main__ - Step 147540: {'lr': 3.4104429408504666e-07, 'samples': 28327680, 'steps': 147539, 'loss/train': 0.27883997559547424} 08/31/2021 15:57:42 - INFO - __main__ - Step 147541: {'lr': 3.4076725424669887e-07, 'samples': 28327872, 'steps': 147540, 'loss/train': 0.2914653420448303} 08/31/2021 15:57:42 - INFO - __main__ - Step 147542: {'lr': 3.4049032690092184e-07, 'samples': 28328064, 'steps': 147541, 'loss/train': 1.3246150016784668} 08/31/2021 15:57:44 - INFO - __main__ - Step 147543: {'lr': 3.4021351204790997e-07, 'samples': 28328256, 'steps': 147542, 'loss/train': 0.9231360554695129} 08/31/2021 15:57:45 - INFO - __main__ - Step 147544: {'lr': 3.399368096877187e-07, 'samples': 28328448, 'steps': 147543, 'loss/train': 0.2875881791114807} 08/31/2021 15:57:45 - INFO - __main__ - Step 147545: {'lr': 3.396602198204868e-07, 'samples': 28328640, 'steps': 147544, 'loss/train': 1.343342900276184} 08/31/2021 15:57:45 - INFO - __main__ - Step 147546: {'lr': 3.3938374244638084e-07, 'samples': 28328832, 'steps': 147545, 'loss/train': 0.11714337766170502} 08/31/2021 15:57:46 - INFO - __main__ - Step 147547: {'lr': 3.3910737756548405e-07, 'samples': 28329024, 'steps': 147546, 'loss/train': 0.0729975551366806} 08/31/2021 15:57:47 - INFO - __main__ - Step 147548: {'lr': 3.3883112517793523e-07, 'samples': 28329216, 'steps': 147547, 'loss/train': 0.3494182825088501} 08/31/2021 15:57:48 - INFO - __main__ - Step 147549: {'lr': 3.3855498528384545e-07, 'samples': 28329408, 'steps': 147548, 'loss/train': 1.2418186664581299} 08/31/2021 15:57:48 - INFO - __main__ - Step 147550: {'lr': 3.3827895788338115e-07, 'samples': 28329600, 'steps': 147549, 'loss/train': 1.2078889608383179} 08/31/2021 15:57:49 - INFO - __main__ - Step 147551: {'lr': 3.380030429765979e-07, 'samples': 28329792, 'steps': 147550, 'loss/train': 0.28309518098831177} 08/31/2021 15:57:49 - INFO - __main__ - Step 147552: {'lr': 3.3772724056369e-07, 'samples': 28329984, 'steps': 147551, 'loss/train': 1.5333048105239868} 08/31/2021 15:57:51 - INFO - __main__ - Step 147553: {'lr': 3.374515506447129e-07, 'samples': 28330176, 'steps': 147552, 'loss/train': 1.3026258945465088} 08/31/2021 15:57:51 - INFO - __main__ - Step 147554: {'lr': 3.371759732198609e-07, 'samples': 28330368, 'steps': 147553, 'loss/train': 1.3102610111236572} 08/31/2021 15:57:51 - INFO - __main__ - Step 147555: {'lr': 3.369005082892174e-07, 'samples': 28330560, 'steps': 147554, 'loss/train': 1.6283066272735596} 08/31/2021 15:57:52 - INFO - __main__ - Step 147556: {'lr': 3.366251558528932e-07, 'samples': 28330752, 'steps': 147555, 'loss/train': 0.7774179577827454} 08/31/2021 15:57:52 - INFO - __main__ - Step 147557: {'lr': 3.36349915911055e-07, 'samples': 28330944, 'steps': 147556, 'loss/train': 1.1758651733398438} 08/31/2021 15:57:54 - INFO - __main__ - Step 147558: {'lr': 3.3607478846381377e-07, 'samples': 28331136, 'steps': 147557, 'loss/train': 0.12740832567214966} 08/31/2021 15:57:54 - INFO - __main__ - Step 147559: {'lr': 3.357997735112528e-07, 'samples': 28331328, 'steps': 147558, 'loss/train': 1.1443462371826172} 08/31/2021 15:57:55 - INFO - __main__ - Step 147560: {'lr': 3.355248710535386e-07, 'samples': 28331520, 'steps': 147559, 'loss/train': 0.6327671408653259} 08/31/2021 15:57:55 - INFO - __main__ - Step 147561: {'lr': 3.352500810908099e-07, 'samples': 28331712, 'steps': 147560, 'loss/train': 0.022936342284083366} 08/31/2021 15:57:55 - INFO - __main__ - Step 147562: {'lr': 3.3497540362315007e-07, 'samples': 28331904, 'steps': 147561, 'loss/train': 1.0859748125076294} 08/31/2021 15:57:56 - INFO - __main__ - Step 147563: {'lr': 3.3470083865069777e-07, 'samples': 28332096, 'steps': 147562, 'loss/train': 0.885016679763794} 08/31/2021 15:57:57 - INFO - __main__ - Step 147564: {'lr': 3.344263861735641e-07, 'samples': 28332288, 'steps': 147563, 'loss/train': 0.47159138321876526} 08/31/2021 15:57:57 - INFO - __main__ - Step 147565: {'lr': 3.3415204619188787e-07, 'samples': 28332480, 'steps': 147564, 'loss/train': 0.40129297971725464} 08/31/2021 15:57:58 - INFO - __main__ - Step 147566: {'lr': 3.338778187058078e-07, 'samples': 28332672, 'steps': 147565, 'loss/train': 1.0719118118286133} 08/31/2021 15:57:58 - INFO - __main__ - Step 147567: {'lr': 3.3360370371540716e-07, 'samples': 28332864, 'steps': 147566, 'loss/train': 1.4640135765075684} 08/31/2021 15:57:59 - INFO - __main__ - Step 147568: {'lr': 3.3332970122085247e-07, 'samples': 28333056, 'steps': 147567, 'loss/train': 0.7814323306083679} 08/31/2021 15:58:00 - INFO - __main__ - Step 147569: {'lr': 3.330558112222271e-07, 'samples': 28333248, 'steps': 147568, 'loss/train': 0.8040931820869446} 08/31/2021 15:58:00 - INFO - __main__ - Step 147570: {'lr': 3.327820337196974e-07, 'samples': 28333440, 'steps': 147569, 'loss/train': 1.0992586612701416} 08/31/2021 15:58:01 - INFO - __main__ - Step 147571: {'lr': 3.3250836871334676e-07, 'samples': 28333632, 'steps': 147570, 'loss/train': 0.7997640371322632} 08/31/2021 15:58:01 - INFO - __main__ - Step 147572: {'lr': 3.3223481620331396e-07, 'samples': 28333824, 'steps': 147571, 'loss/train': 1.0971516370773315} 08/31/2021 15:58:02 - INFO - __main__ - Step 147573: {'lr': 3.3196137618973774e-07, 'samples': 28334016, 'steps': 147572, 'loss/train': 0.9718379974365234} 08/31/2021 15:58:03 - INFO - __main__ - Step 147574: {'lr': 3.3168804867270143e-07, 'samples': 28334208, 'steps': 147573, 'loss/train': 1.2861616611480713} 08/31/2021 15:58:04 - INFO - __main__ - Step 147575: {'lr': 3.3141483365237147e-07, 'samples': 28334400, 'steps': 147574, 'loss/train': 1.1613216400146484} 08/31/2021 15:58:04 - INFO - __main__ - Step 147576: {'lr': 3.3114173112885893e-07, 'samples': 28334592, 'steps': 147575, 'loss/train': 1.155849814414978} 08/31/2021 15:58:04 - INFO - __main__ - Step 147577: {'lr': 3.308687411022748e-07, 'samples': 28334784, 'steps': 147576, 'loss/train': 1.370921015739441} 08/31/2021 15:58:05 - INFO - __main__ - Step 147578: {'lr': 3.3059586357275795e-07, 'samples': 28334976, 'steps': 147577, 'loss/train': 1.054181694984436} 08/31/2021 15:58:06 - INFO - __main__ - Step 147579: {'lr': 3.3032309854039153e-07, 'samples': 28335168, 'steps': 147578, 'loss/train': 0.027801619842648506} 08/31/2021 15:58:07 - INFO - __main__ - Step 147580: {'lr': 3.300504460053699e-07, 'samples': 28335360, 'steps': 147579, 'loss/train': 1.1202155351638794} 08/31/2021 15:58:07 - INFO - __main__ - Step 147581: {'lr': 3.297779059677486e-07, 'samples': 28335552, 'steps': 147580, 'loss/train': 1.273463249206543} 08/31/2021 15:58:07 - INFO - __main__ - Step 147582: {'lr': 3.295054784276941e-07, 'samples': 28335744, 'steps': 147581, 'loss/train': 1.4679230451583862} 08/31/2021 15:58:08 - INFO - __main__ - Step 147583: {'lr': 3.2923316338528964e-07, 'samples': 28335936, 'steps': 147582, 'loss/train': 1.0928641557693481} 08/31/2021 15:58:10 - INFO - __main__ - Step 147584: {'lr': 3.2896096084070184e-07, 'samples': 28336128, 'steps': 147583, 'loss/train': 0.661677896976471} 08/31/2021 15:58:10 - INFO - __main__ - Step 147585: {'lr': 3.2868887079401386e-07, 'samples': 28336320, 'steps': 147584, 'loss/train': 1.135359287261963} 08/31/2021 15:58:11 - INFO - __main__ - Step 147586: {'lr': 3.284168932453646e-07, 'samples': 28336512, 'steps': 147585, 'loss/train': 0.9665747880935669} 08/31/2021 15:58:11 - INFO - __main__ - Step 147587: {'lr': 3.281450281948928e-07, 'samples': 28336704, 'steps': 147586, 'loss/train': 1.0086703300476074} 08/31/2021 15:58:11 - INFO - __main__ - Step 147588: {'lr': 3.278732756427094e-07, 'samples': 28336896, 'steps': 147587, 'loss/train': 1.5025807619094849} 08/31/2021 15:58:13 - INFO - __main__ - Step 147589: {'lr': 3.2760163558892554e-07, 'samples': 28337088, 'steps': 147588, 'loss/train': 0.9044806361198425} 08/31/2021 15:58:13 - INFO - __main__ - Step 147590: {'lr': 3.2733010803365217e-07, 'samples': 28337280, 'steps': 147589, 'loss/train': 1.3422986268997192} 08/31/2021 15:58:14 - INFO - __main__ - Step 147591: {'lr': 3.270586929770558e-07, 'samples': 28337472, 'steps': 147590, 'loss/train': 1.6911367177963257} 08/31/2021 15:58:14 - INFO - __main__ - Step 147592: {'lr': 3.267873904192198e-07, 'samples': 28337664, 'steps': 147591, 'loss/train': 1.1869583129882812} 08/31/2021 15:58:15 - INFO - __main__ - Step 147593: {'lr': 3.2651620036028284e-07, 'samples': 28337856, 'steps': 147592, 'loss/train': 1.4306825399398804} 08/31/2021 15:58:15 - INFO - __main__ - Step 147594: {'lr': 3.2624512280038376e-07, 'samples': 28338048, 'steps': 147593, 'loss/train': 0.8460341095924377} 08/31/2021 15:58:16 - INFO - __main__ - Step 147595: {'lr': 3.259741577396058e-07, 'samples': 28338240, 'steps': 147594, 'loss/train': 0.7679896950721741} 08/31/2021 15:58:17 - INFO - __main__ - Step 147596: {'lr': 3.2570330517811555e-07, 'samples': 28338432, 'steps': 147595, 'loss/train': 1.0957096815109253} 08/31/2021 15:58:17 - INFO - __main__ - Step 147597: {'lr': 3.254325651159684e-07, 'samples': 28338624, 'steps': 147596, 'loss/train': 0.6862013339996338} 08/31/2021 15:58:18 - INFO - __main__ - Step 147598: {'lr': 3.2516193755335876e-07, 'samples': 28338816, 'steps': 147597, 'loss/train': 1.1314697265625} 08/31/2021 15:58:18 - INFO - __main__ - Step 147599: {'lr': 3.2489142249036984e-07, 'samples': 28339008, 'steps': 147598, 'loss/train': 1.1301848888397217} 08/31/2021 15:58:20 - INFO - __main__ - Step 147600: {'lr': 3.2462101992714045e-07, 'samples': 28339200, 'steps': 147599, 'loss/train': 0.5248224139213562} 08/31/2021 15:58:20 - INFO - __main__ - Step 147601: {'lr': 3.2435072986378155e-07, 'samples': 28339392, 'steps': 147600, 'loss/train': 0.6486372351646423} 08/31/2021 15:58:20 - INFO - __main__ - Step 147602: {'lr': 3.2408055230043196e-07, 'samples': 28339584, 'steps': 147601, 'loss/train': 0.46985146403312683} 08/31/2021 15:58:21 - INFO - __main__ - Step 147603: {'lr': 3.23810487237175e-07, 'samples': 28339776, 'steps': 147602, 'loss/train': 1.0998677015304565} 08/31/2021 15:58:21 - INFO - __main__ - Step 147604: {'lr': 3.2354053467414937e-07, 'samples': 28339968, 'steps': 147603, 'loss/train': 1.2193644046783447} 08/31/2021 15:58:23 - INFO - __main__ - Step 147605: {'lr': 3.2327069461152156e-07, 'samples': 28340160, 'steps': 147604, 'loss/train': 0.9156765937805176} 08/31/2021 15:58:23 - INFO - __main__ - Step 147606: {'lr': 3.230009670493472e-07, 'samples': 28340352, 'steps': 147605, 'loss/train': 1.5197850465774536} 08/31/2021 15:58:23 - INFO - __main__ - Step 147607: {'lr': 3.2273135198776505e-07, 'samples': 28340544, 'steps': 147606, 'loss/train': 0.8595351576805115} 08/31/2021 15:58:24 - INFO - __main__ - Step 147608: {'lr': 3.224618494269138e-07, 'samples': 28340736, 'steps': 147607, 'loss/train': 1.164820671081543} 08/31/2021 15:58:24 - INFO - __main__ - Step 147609: {'lr': 3.221924593669323e-07, 'samples': 28340928, 'steps': 147608, 'loss/train': 1.1062986850738525} 08/31/2021 15:58:25 - INFO - __main__ - Step 147610: {'lr': 3.219231818079038e-07, 'samples': 28341120, 'steps': 147609, 'loss/train': 0.6708847284317017} 08/31/2021 15:58:26 - INFO - __main__ - Step 147611: {'lr': 3.216540167499671e-07, 'samples': 28341312, 'steps': 147610, 'loss/train': 1.266509771347046} 08/31/2021 15:58:26 - INFO - __main__ - Step 147612: {'lr': 3.2138496419323314e-07, 'samples': 28341504, 'steps': 147611, 'loss/train': 1.0166478157043457} 08/31/2021 15:58:27 - INFO - __main__ - Step 147613: {'lr': 3.211160241378408e-07, 'samples': 28341696, 'steps': 147612, 'loss/train': 0.6662333607673645} 08/31/2021 15:58:27 - INFO - __main__ - Step 147614: {'lr': 3.2084719658387327e-07, 'samples': 28341888, 'steps': 147613, 'loss/train': 1.6482187509536743} 08/31/2021 15:58:27 - INFO - __main__ - Step 147615: {'lr': 3.205784815315249e-07, 'samples': 28342080, 'steps': 147614, 'loss/train': 1.0898535251617432} 08/31/2021 15:58:29 - INFO - __main__ - Step 147616: {'lr': 3.203098789808234e-07, 'samples': 28342272, 'steps': 147615, 'loss/train': 1.1190943717956543} 08/31/2021 15:58:29 - INFO - __main__ - Step 147617: {'lr': 3.200413889319631e-07, 'samples': 28342464, 'steps': 147616, 'loss/train': 0.7788679599761963} 08/31/2021 15:58:30 - INFO - __main__ - Step 147618: {'lr': 3.197730113850272e-07, 'samples': 28342656, 'steps': 147617, 'loss/train': 0.9931880235671997} 08/31/2021 15:58:30 - INFO - __main__ - Step 147619: {'lr': 3.1950474634018233e-07, 'samples': 28342848, 'steps': 147618, 'loss/train': 1.3706563711166382} 08/31/2021 15:58:30 - INFO - __main__ - Step 147620: {'lr': 3.192365937974839e-07, 'samples': 28343040, 'steps': 147619, 'loss/train': 1.2728842496871948} 08/31/2021 15:58:32 - INFO - __main__ - Step 147621: {'lr': 3.1896855375709853e-07, 'samples': 28343232, 'steps': 147620, 'loss/train': 1.1715102195739746} 08/31/2021 15:58:32 - INFO - __main__ - Step 147622: {'lr': 3.1870062621910943e-07, 'samples': 28343424, 'steps': 147621, 'loss/train': 1.7368602752685547} 08/31/2021 15:58:33 - INFO - __main__ - Step 147623: {'lr': 3.184328111836832e-07, 'samples': 28343616, 'steps': 147622, 'loss/train': 0.8601597547531128} 08/31/2021 15:58:33 - INFO - __main__ - Step 147624: {'lr': 3.18165108650903e-07, 'samples': 28343808, 'steps': 147623, 'loss/train': 1.0242618322372437} 08/31/2021 15:58:34 - INFO - __main__ - Step 147625: {'lr': 3.1789751862090766e-07, 'samples': 28344000, 'steps': 147624, 'loss/train': 0.760238766670227} 08/31/2021 15:58:35 - INFO - __main__ - Step 147626: {'lr': 3.1763004109383596e-07, 'samples': 28344192, 'steps': 147625, 'loss/train': 0.17648696899414062} 08/31/2021 15:58:36 - INFO - __main__ - Step 147627: {'lr': 3.173626760697712e-07, 'samples': 28344384, 'steps': 147626, 'loss/train': 1.2603439092636108} 08/31/2021 15:58:36 - INFO - __main__ - Step 147628: {'lr': 3.170954235488521e-07, 'samples': 28344576, 'steps': 147627, 'loss/train': 0.9538726210594177} 08/31/2021 15:58:36 - INFO - __main__ - Step 147629: {'lr': 3.1682828353118974e-07, 'samples': 28344768, 'steps': 147628, 'loss/train': 0.8373232483863831} 08/31/2021 15:58:37 - INFO - __main__ - Step 147630: {'lr': 3.165612560169229e-07, 'samples': 28344960, 'steps': 147629, 'loss/train': 0.9551297426223755} 08/31/2021 15:58:37 - INFO - __main__ - Step 147631: {'lr': 3.162943410061625e-07, 'samples': 28345152, 'steps': 147630, 'loss/train': 0.20619359612464905} 08/31/2021 15:58:38 - INFO - __main__ - Step 147632: {'lr': 3.160275384990197e-07, 'samples': 28345344, 'steps': 147631, 'loss/train': 1.4115283489227295} 08/31/2021 15:58:39 - INFO - __main__ - Step 147633: {'lr': 3.1576084849563315e-07, 'samples': 28345536, 'steps': 147632, 'loss/train': 1.1908196210861206} 08/31/2021 15:58:39 - INFO - __main__ - Step 147634: {'lr': 3.154942709960862e-07, 'samples': 28345728, 'steps': 147633, 'loss/train': 2.477109909057617} 08/31/2021 15:58:40 - INFO - __main__ - Step 147635: {'lr': 3.1522780600054536e-07, 'samples': 28345920, 'steps': 147634, 'loss/train': 0.8958113193511963} 08/31/2021 15:58:40 - INFO - __main__ - Step 147636: {'lr': 3.1496145350912163e-07, 'samples': 28346112, 'steps': 147635, 'loss/train': 0.13949643075466156} 08/31/2021 15:58:42 - INFO - __main__ - Step 147637: {'lr': 3.146952135218983e-07, 'samples': 28346304, 'steps': 147636, 'loss/train': 0.7301592230796814} 08/31/2021 15:58:42 - INFO - __main__ - Step 147638: {'lr': 3.144290860390142e-07, 'samples': 28346496, 'steps': 147637, 'loss/train': 0.0505792573094368} 08/31/2021 15:58:43 - INFO - __main__ - Step 147639: {'lr': 3.1416307106060804e-07, 'samples': 28346688, 'steps': 147638, 'loss/train': 1.0352216958999634} 08/31/2021 15:58:43 - INFO - __main__ - Step 147640: {'lr': 3.1389716858679083e-07, 'samples': 28346880, 'steps': 147639, 'loss/train': 1.4609359502792358} 08/31/2021 15:58:43 - INFO - __main__ - Step 147641: {'lr': 3.1363137861770143e-07, 'samples': 28347072, 'steps': 147640, 'loss/train': 0.8474434614181519} 08/31/2021 15:58:46 - INFO - __main__ - Step 147642: {'lr': 3.1336570115339526e-07, 'samples': 28347264, 'steps': 147641, 'loss/train': 1.7690062522888184} 08/31/2021 15:58:46 - INFO - __main__ - Step 147643: {'lr': 3.131001361940666e-07, 'samples': 28347456, 'steps': 147642, 'loss/train': 0.8190132975578308} 08/31/2021 15:58:46 - INFO - __main__ - Step 147644: {'lr': 3.1283468373977107e-07, 'samples': 28347648, 'steps': 147643, 'loss/train': 1.3024711608886719} 08/31/2021 15:58:47 - INFO - __main__ - Step 147645: {'lr': 3.1256934379067513e-07, 'samples': 28347840, 'steps': 147644, 'loss/train': 0.37497836351394653} 08/31/2021 15:58:47 - INFO - __main__ - Step 147646: {'lr': 3.123041163468898e-07, 'samples': 28348032, 'steps': 147645, 'loss/train': 0.9880477786064148} 08/31/2021 15:58:48 - INFO - __main__ - Step 147647: {'lr': 3.1203900140852617e-07, 'samples': 28348224, 'steps': 147646, 'loss/train': 1.0373029708862305} 08/31/2021 15:58:49 - INFO - __main__ - Step 147648: {'lr': 3.117739989756951e-07, 'samples': 28348416, 'steps': 147647, 'loss/train': 1.442335844039917} 08/31/2021 15:58:49 - INFO - __main__ - Step 147649: {'lr': 3.115091090485356e-07, 'samples': 28348608, 'steps': 147648, 'loss/train': 1.1026588678359985} 08/31/2021 15:58:50 - INFO - __main__ - Step 147650: {'lr': 3.112443316271307e-07, 'samples': 28348800, 'steps': 147649, 'loss/train': 1.5787931680679321} 08/31/2021 15:58:50 - INFO - __main__ - Step 147651: {'lr': 3.109796667116471e-07, 'samples': 28348992, 'steps': 147650, 'loss/train': 1.3654111623764038} 08/31/2021 15:58:52 - INFO - __main__ - Step 147652: {'lr': 3.107151143021958e-07, 'samples': 28349184, 'steps': 147651, 'loss/train': 1.1795070171356201} 08/31/2021 15:58:52 - INFO - __main__ - Step 147653: {'lr': 3.1045067439885997e-07, 'samples': 28349376, 'steps': 147652, 'loss/train': 1.271836519241333} 08/31/2021 15:58:52 - INFO - __main__ - Step 147654: {'lr': 3.101863470018063e-07, 'samples': 28349568, 'steps': 147653, 'loss/train': 1.1695988178253174} 08/31/2021 15:58:53 - INFO - __main__ - Step 147655: {'lr': 3.099221321111179e-07, 'samples': 28349760, 'steps': 147654, 'loss/train': 0.9858011603355408} 08/31/2021 15:58:53 - INFO - __main__ - Step 147656: {'lr': 3.096580297269058e-07, 'samples': 28349952, 'steps': 147655, 'loss/train': 1.5897406339645386} 08/31/2021 15:58:54 - INFO - __main__ - Step 147657: {'lr': 3.093940398493367e-07, 'samples': 28350144, 'steps': 147656, 'loss/train': 1.0874276161193848} 08/31/2021 15:58:55 - INFO - __main__ - Step 147658: {'lr': 3.091301624784937e-07, 'samples': 28350336, 'steps': 147657, 'loss/train': 1.2581199407577515} 08/31/2021 15:58:55 - INFO - __main__ - Step 147659: {'lr': 3.088663976144879e-07, 'samples': 28350528, 'steps': 147658, 'loss/train': 1.3921444416046143} 08/31/2021 15:58:56 - INFO - __main__ - Step 147660: {'lr': 3.086027452574858e-07, 'samples': 28350720, 'steps': 147659, 'loss/train': 1.3740147352218628} 08/31/2021 15:58:56 - INFO - __main__ - Step 147661: {'lr': 3.083392054075429e-07, 'samples': 28350912, 'steps': 147660, 'loss/train': 1.5815496444702148} 08/31/2021 15:58:58 - INFO - __main__ - Step 147662: {'lr': 3.080757780648258e-07, 'samples': 28351104, 'steps': 147661, 'loss/train': 0.6419132351875305} 08/31/2021 15:58:58 - INFO - __main__ - Step 147663: {'lr': 3.0781246322944544e-07, 'samples': 28351296, 'steps': 147662, 'loss/train': 1.3662688732147217} 08/31/2021 15:58:59 - INFO - __main__ - Step 147664: {'lr': 3.0754926090148514e-07, 'samples': 28351488, 'steps': 147663, 'loss/train': 0.8512250185012817} 08/31/2021 15:58:59 - INFO - __main__ - Step 147665: {'lr': 3.072861710811115e-07, 'samples': 28351680, 'steps': 147664, 'loss/train': 1.2489789724349976} 08/31/2021 15:58:59 - INFO - __main__ - Step 147666: {'lr': 3.070231937684076e-07, 'samples': 28351872, 'steps': 147665, 'loss/train': 1.112248182296753} 08/31/2021 15:59:00 - INFO - __main__ - Step 147667: {'lr': 3.0676032896351237e-07, 'samples': 28352064, 'steps': 147666, 'loss/train': 1.0676878690719604} 08/31/2021 15:59:01 - INFO - __main__ - Step 147668: {'lr': 3.064975766665368e-07, 'samples': 28352256, 'steps': 147667, 'loss/train': 1.6997171640396118} 08/31/2021 15:59:02 - INFO - __main__ - Step 147669: {'lr': 3.062349368776196e-07, 'samples': 28352448, 'steps': 147668, 'loss/train': 0.040552057325839996} 08/31/2021 15:59:02 - INFO - __main__ - Step 147670: {'lr': 3.059724095968441e-07, 'samples': 28352640, 'steps': 147669, 'loss/train': 1.0531927347183228} 08/31/2021 15:59:03 - INFO - __main__ - Step 147671: {'lr': 3.057099948243214e-07, 'samples': 28352832, 'steps': 147670, 'loss/train': 0.9329245686531067} 08/31/2021 15:59:03 - INFO - __main__ - Step 147672: {'lr': 3.0544769256021787e-07, 'samples': 28353024, 'steps': 147671, 'loss/train': 0.8571233749389648} 08/31/2021 15:59:04 - INFO - __main__ - Step 147673: {'lr': 3.0518550280461686e-07, 'samples': 28353216, 'steps': 147672, 'loss/train': 1.4899314641952515} 08/31/2021 15:59:05 - INFO - __main__ - Step 147674: {'lr': 3.0492342555765715e-07, 'samples': 28353408, 'steps': 147673, 'loss/train': 0.9229223728179932} 08/31/2021 15:59:05 - INFO - __main__ - Step 147675: {'lr': 3.046614608194498e-07, 'samples': 28353600, 'steps': 147674, 'loss/train': 0.38889414072036743} 08/31/2021 15:59:06 - INFO - __main__ - Step 147676: {'lr': 3.0439960859010573e-07, 'samples': 28353792, 'steps': 147675, 'loss/train': 1.2214539051055908} 08/31/2021 15:59:06 - INFO - __main__ - Step 147677: {'lr': 3.0413786886973604e-07, 'samples': 28353984, 'steps': 147676, 'loss/train': 0.952312171459198} 08/31/2021 15:59:07 - INFO - __main__ - Step 147678: {'lr': 3.038762416584795e-07, 'samples': 28354176, 'steps': 147677, 'loss/train': 0.9646860957145691} 08/31/2021 15:59:08 - INFO - __main__ - Step 147679: {'lr': 3.0361472695641936e-07, 'samples': 28354368, 'steps': 147678, 'loss/train': 0.022397737950086594} 08/31/2021 15:59:08 - INFO - __main__ - Step 147680: {'lr': 3.0335332476372214e-07, 'samples': 28354560, 'steps': 147679, 'loss/train': 0.027066318318247795} 08/31/2021 15:59:09 - INFO - __main__ - Step 147681: {'lr': 3.030920350804711e-07, 'samples': 28354752, 'steps': 147680, 'loss/train': 1.240892767906189} 08/31/2021 15:59:09 - INFO - __main__ - Step 147682: {'lr': 3.028308579068051e-07, 'samples': 28354944, 'steps': 147681, 'loss/train': 0.9594149589538574} 08/31/2021 15:59:11 - INFO - __main__ - Step 147683: {'lr': 3.0256979324283506e-07, 'samples': 28355136, 'steps': 147682, 'loss/train': 1.0468090772628784} 08/31/2021 15:59:11 - INFO - __main__ - Step 147684: {'lr': 3.023088410886443e-07, 'samples': 28355328, 'steps': 147683, 'loss/train': 1.080463171005249} 08/31/2021 15:59:11 - INFO - __main__ - Step 147685: {'lr': 3.0204800144439937e-07, 'samples': 28355520, 'steps': 147684, 'loss/train': 0.6789920926094055} 08/31/2021 15:59:12 - INFO - __main__ - Step 147686: {'lr': 3.017872743101835e-07, 'samples': 28355712, 'steps': 147685, 'loss/train': 0.6479930281639099} 08/31/2021 15:59:12 - INFO - __main__ - Step 147687: {'lr': 3.015266596861632e-07, 'samples': 28355904, 'steps': 147686, 'loss/train': 1.0153909921646118} 08/31/2021 15:59:12 - INFO - __main__ - Step 147688: {'lr': 3.012661575723941e-07, 'samples': 28356096, 'steps': 147687, 'loss/train': 0.30743399262428284} 08/31/2021 15:59:14 - INFO - __main__ - Step 147689: {'lr': 3.010057679690148e-07, 'samples': 28356288, 'steps': 147688, 'loss/train': 0.5765534043312073} 08/31/2021 15:59:14 - INFO - __main__ - Step 147690: {'lr': 3.007454908761642e-07, 'samples': 28356480, 'steps': 147689, 'loss/train': 0.7078583240509033} 08/31/2021 15:59:15 - INFO - __main__ - Step 147691: {'lr': 3.004853262939533e-07, 'samples': 28356672, 'steps': 147690, 'loss/train': 0.7224470376968384} 08/31/2021 15:59:15 - INFO - __main__ - Step 147692: {'lr': 3.0022527422246536e-07, 'samples': 28356864, 'steps': 147691, 'loss/train': 0.5156662464141846} 08/31/2021 15:59:15 - INFO - __main__ - Step 147693: {'lr': 2.999653346618669e-07, 'samples': 28357056, 'steps': 147692, 'loss/train': 1.1025887727737427} 08/31/2021 15:59:17 - INFO - __main__ - Step 147694: {'lr': 2.997055076122412e-07, 'samples': 28357248, 'steps': 147693, 'loss/train': 1.5764617919921875} 08/31/2021 15:59:18 - INFO - __main__ - Step 147695: {'lr': 2.994457930737271e-07, 'samples': 28357440, 'steps': 147694, 'loss/train': 1.0018415451049805} 08/31/2021 15:59:18 - INFO - __main__ - Step 147696: {'lr': 2.9918619104640774e-07, 'samples': 28357632, 'steps': 147695, 'loss/train': 1.505734920501709} 08/31/2021 15:59:19 - INFO - __main__ - Step 147697: {'lr': 2.98926701530422e-07, 'samples': 28357824, 'steps': 147696, 'loss/train': 1.053847074508667} 08/31/2021 15:59:19 - INFO - __main__ - Step 147698: {'lr': 2.986673245259086e-07, 'samples': 28358016, 'steps': 147697, 'loss/train': 1.8347060680389404} 08/31/2021 15:59:21 - INFO - __main__ - Step 147699: {'lr': 2.9840806003295084e-07, 'samples': 28358208, 'steps': 147698, 'loss/train': 0.72541743516922} 08/31/2021 15:59:21 - INFO - __main__ - Step 147700: {'lr': 2.981489080516875e-07, 'samples': 28358400, 'steps': 147699, 'loss/train': 1.2922440767288208} 08/31/2021 15:59:22 - INFO - __main__ - Step 147701: {'lr': 2.9788986858220177e-07, 'samples': 28358592, 'steps': 147700, 'loss/train': 0.5772914886474609} 08/31/2021 15:59:22 - INFO - __main__ - Step 147702: {'lr': 2.976309416246603e-07, 'samples': 28358784, 'steps': 147701, 'loss/train': 1.0074366331100464} 08/31/2021 15:59:23 - INFO - __main__ - Step 147703: {'lr': 2.9737212717911857e-07, 'samples': 28358976, 'steps': 147702, 'loss/train': 1.0944788455963135} 08/31/2021 15:59:24 - INFO - __main__ - Step 147704: {'lr': 2.9711342524577077e-07, 'samples': 28359168, 'steps': 147703, 'loss/train': 0.47787436842918396} 08/31/2021 15:59:24 - INFO - __main__ - Step 147705: {'lr': 2.968548358246448e-07, 'samples': 28359360, 'steps': 147704, 'loss/train': 0.9428713321685791} 08/31/2021 15:59:25 - INFO - __main__ - Step 147706: {'lr': 2.9659635891593486e-07, 'samples': 28359552, 'steps': 147705, 'loss/train': 0.3719748258590698} 08/31/2021 15:59:25 - INFO - __main__ - Step 147707: {'lr': 2.963379945197242e-07, 'samples': 28359744, 'steps': 147706, 'loss/train': 0.801762044429779} 08/31/2021 15:59:25 - INFO - __main__ - Step 147708: {'lr': 2.960797426361239e-07, 'samples': 28359936, 'steps': 147707, 'loss/train': 1.36540687084198} 08/31/2021 15:59:26 - INFO - __main__ - Step 147709: {'lr': 2.95821603265245e-07, 'samples': 28360128, 'steps': 147708, 'loss/train': 0.8172628283500671} 08/31/2021 15:59:28 - INFO - __main__ - Step 147710: {'lr': 2.955635764072262e-07, 'samples': 28360320, 'steps': 147709, 'loss/train': 0.7348772287368774} 08/31/2021 15:59:28 - INFO - __main__ - Step 147711: {'lr': 2.9530566206217857e-07, 'samples': 28360512, 'steps': 147710, 'loss/train': 1.2482144832611084} 08/31/2021 15:59:28 - INFO - __main__ - Step 147712: {'lr': 2.9504786023021313e-07, 'samples': 28360704, 'steps': 147711, 'loss/train': 0.3421035706996918} 08/31/2021 15:59:29 - INFO - __main__ - Step 147713: {'lr': 2.947901709114409e-07, 'samples': 28360896, 'steps': 147712, 'loss/train': 0.6074262857437134} 08/31/2021 15:59:29 - INFO - __main__ - Step 147714: {'lr': 2.945325941059729e-07, 'samples': 28361088, 'steps': 147713, 'loss/train': 1.6583919525146484} 08/31/2021 15:59:31 - INFO - __main__ - Step 147715: {'lr': 2.9427512981394786e-07, 'samples': 28361280, 'steps': 147714, 'loss/train': 1.2127485275268555} 08/31/2021 15:59:31 - INFO - __main__ - Step 147716: {'lr': 2.9401777803547694e-07, 'samples': 28361472, 'steps': 147715, 'loss/train': 0.775338351726532} 08/31/2021 15:59:32 - INFO - __main__ - Step 147717: {'lr': 2.93760538770671e-07, 'samples': 28361664, 'steps': 147716, 'loss/train': 0.3120342791080475} 08/31/2021 15:59:32 - INFO - __main__ - Step 147718: {'lr': 2.935034120196134e-07, 'samples': 28361856, 'steps': 147717, 'loss/train': 1.649688720703125} 08/31/2021 15:59:32 - INFO - __main__ - Step 147719: {'lr': 2.9324639778247063e-07, 'samples': 28362048, 'steps': 147718, 'loss/train': 1.2278155088424683} 08/31/2021 15:59:34 - INFO - __main__ - Step 147720: {'lr': 2.9298949605935377e-07, 'samples': 28362240, 'steps': 147719, 'loss/train': 0.7888110280036926} 08/31/2021 15:59:34 - INFO - __main__ - Step 147721: {'lr': 2.9273270685034603e-07, 'samples': 28362432, 'steps': 147720, 'loss/train': 0.3620877265930176} 08/31/2021 15:59:34 - INFO - __main__ - Step 147722: {'lr': 2.924760301555585e-07, 'samples': 28362624, 'steps': 147721, 'loss/train': 0.9189907312393188} 08/31/2021 15:59:35 - INFO - __main__ - Step 147723: {'lr': 2.922194659751576e-07, 'samples': 28362816, 'steps': 147722, 'loss/train': 0.8958037495613098} 08/31/2021 15:59:35 - INFO - __main__ - Step 147724: {'lr': 2.919630143092267e-07, 'samples': 28363008, 'steps': 147723, 'loss/train': 0.6216367483139038} 08/31/2021 15:59:37 - INFO - __main__ - Step 147725: {'lr': 2.91706675157849e-07, 'samples': 28363200, 'steps': 147724, 'loss/train': 0.9983185529708862} 08/31/2021 15:59:37 - INFO - __main__ - Step 147726: {'lr': 2.9145044852121883e-07, 'samples': 28363392, 'steps': 147725, 'loss/train': 1.295749545097351} 08/31/2021 15:59:38 - INFO - __main__ - Step 147727: {'lr': 2.911943343993917e-07, 'samples': 28363584, 'steps': 147726, 'loss/train': 1.8514773845672607} 08/31/2021 15:59:38 - INFO - __main__ - Step 147728: {'lr': 2.909383327925064e-07, 'samples': 28363776, 'steps': 147727, 'loss/train': 1.2648093700408936} 08/31/2021 15:59:38 - INFO - __main__ - Step 147729: {'lr': 2.906824437006461e-07, 'samples': 28363968, 'steps': 147728, 'loss/train': 1.4424660205841064} 08/31/2021 15:59:40 - INFO - __main__ - Step 147730: {'lr': 2.904266671239775e-07, 'samples': 28364160, 'steps': 147729, 'loss/train': 1.246594786643982} 08/31/2021 15:59:40 - INFO - __main__ - Step 147731: {'lr': 2.901710030625837e-07, 'samples': 28364352, 'steps': 147730, 'loss/train': 0.7208046317100525} 08/31/2021 15:59:41 - INFO - __main__ - Step 147732: {'lr': 2.899154515165758e-07, 'samples': 28364544, 'steps': 147731, 'loss/train': 3.4926698207855225} 08/31/2021 15:59:41 - INFO - __main__ - Step 147733: {'lr': 2.896600124860926e-07, 'samples': 28364736, 'steps': 147732, 'loss/train': 1.253448247909546} 08/31/2021 15:59:41 - INFO - __main__ - Step 147734: {'lr': 2.894046859712174e-07, 'samples': 28364928, 'steps': 147733, 'loss/train': 1.0607459545135498} 08/31/2021 15:59:43 - INFO - __main__ - Step 147735: {'lr': 2.8914947197208884e-07, 'samples': 28365120, 'steps': 147734, 'loss/train': 1.0961252450942993} 08/31/2021 15:59:43 - INFO - __main__ - Step 147736: {'lr': 2.8889437048881807e-07, 'samples': 28365312, 'steps': 147735, 'loss/train': 1.7863787412643433} 08/31/2021 15:59:44 - INFO - __main__ - Step 147737: {'lr': 2.886393815215438e-07, 'samples': 28365504, 'steps': 147736, 'loss/train': 1.2995431423187256} 08/31/2021 15:59:44 - INFO - __main__ - Step 147738: {'lr': 2.8838450507032155e-07, 'samples': 28365696, 'steps': 147737, 'loss/train': 0.7560634016990662} 08/31/2021 15:59:45 - INFO - __main__ - Step 147739: {'lr': 2.881297411353179e-07, 'samples': 28365888, 'steps': 147738, 'loss/train': 1.5014818906784058} 08/31/2021 15:59:45 - INFO - __main__ - Step 147740: {'lr': 2.87875089716616e-07, 'samples': 28366080, 'steps': 147739, 'loss/train': 0.6296936273574829} 08/31/2021 15:59:46 - INFO - __main__ - Step 147741: {'lr': 2.876205508143548e-07, 'samples': 28366272, 'steps': 147740, 'loss/train': 1.0068689584732056} 08/31/2021 15:59:47 - INFO - __main__ - Step 147742: {'lr': 2.873661244286452e-07, 'samples': 28366464, 'steps': 147741, 'loss/train': 1.2268773317337036} 08/31/2021 15:59:47 - INFO - __main__ - Step 147743: {'lr': 2.871118105595705e-07, 'samples': 28366656, 'steps': 147742, 'loss/train': 1.7268720865249634} 08/31/2021 15:59:48 - INFO - __main__ - Step 147744: {'lr': 2.868576092072972e-07, 'samples': 28366848, 'steps': 147743, 'loss/train': 1.0351589918136597} 08/31/2021 15:59:48 - INFO - __main__ - Step 147745: {'lr': 2.8660352037188086e-07, 'samples': 28367040, 'steps': 147744, 'loss/train': 1.411874532699585} 08/31/2021 15:59:49 - INFO - __main__ - Step 147746: {'lr': 2.86349544053488e-07, 'samples': 28367232, 'steps': 147745, 'loss/train': 1.128438949584961} 08/31/2021 15:59:50 - INFO - __main__ - Step 147747: {'lr': 2.8609568025222963e-07, 'samples': 28367424, 'steps': 147746, 'loss/train': 0.7588422894477844} 08/31/2021 15:59:50 - INFO - __main__ - Step 147748: {'lr': 2.858419289681613e-07, 'samples': 28367616, 'steps': 147747, 'loss/train': 1.3707727193832397} 08/31/2021 15:59:51 - INFO - __main__ - Step 147749: {'lr': 2.8558829020147726e-07, 'samples': 28367808, 'steps': 147748, 'loss/train': 1.374921202659607} 08/31/2021 15:59:51 - INFO - __main__ - Step 147750: {'lr': 2.85334763952233e-07, 'samples': 28368000, 'steps': 147749, 'loss/train': 1.1967612504959106} 08/31/2021 15:59:53 - INFO - __main__ - Step 147751: {'lr': 2.8508135022056736e-07, 'samples': 28368192, 'steps': 147750, 'loss/train': 0.9614617228507996} 08/31/2021 15:59:53 - INFO - __main__ - Step 147752: {'lr': 2.848280490066191e-07, 'samples': 28368384, 'steps': 147751, 'loss/train': 1.0333912372589111} 08/31/2021 15:59:54 - INFO - __main__ - Step 147753: {'lr': 2.845748603104437e-07, 'samples': 28368576, 'steps': 147752, 'loss/train': 0.9453550577163696} 08/31/2021 15:59:54 - INFO - __main__ - Step 147754: {'lr': 2.843217841321799e-07, 'samples': 28368768, 'steps': 147753, 'loss/train': 1.1907262802124023} 08/31/2021 15:59:54 - INFO - __main__ - Step 147755: {'lr': 2.840688204719666e-07, 'samples': 28368960, 'steps': 147754, 'loss/train': 1.146618127822876} 08/31/2021 15:59:56 - INFO - __main__ - Step 147756: {'lr': 2.8381596932988693e-07, 'samples': 28369152, 'steps': 147755, 'loss/train': 1.4754548072814941} 08/31/2021 15:59:56 - INFO - __main__ - Step 147757: {'lr': 2.8356323070605204e-07, 'samples': 28369344, 'steps': 147756, 'loss/train': 0.6797695755958557} 08/31/2021 15:59:57 - INFO - __main__ - Step 147758: {'lr': 2.833106046006284e-07, 'samples': 28369536, 'steps': 147757, 'loss/train': 0.7896609306335449} 08/31/2021 15:59:57 - INFO - __main__ - Step 147759: {'lr': 2.8305809101364375e-07, 'samples': 28369728, 'steps': 147758, 'loss/train': 0.15731647610664368} 08/31/2021 15:59:57 - INFO - __main__ - Step 147760: {'lr': 2.8280568994529243e-07, 'samples': 28369920, 'steps': 147759, 'loss/train': 0.9151694178581238} 08/31/2021 15:59:59 - INFO - __main__ - Step 147761: {'lr': 2.8255340139565767e-07, 'samples': 28370112, 'steps': 147760, 'loss/train': 1.1806005239486694} 08/31/2021 16:00:00 - INFO - __main__ - Step 147762: {'lr': 2.8230122536485047e-07, 'samples': 28370304, 'steps': 147761, 'loss/train': 1.013900637626648} 08/31/2021 16:00:00 - INFO - __main__ - Step 147763: {'lr': 2.820491618529819e-07, 'samples': 28370496, 'steps': 147762, 'loss/train': 0.7000892162322998} 08/31/2021 16:00:00 - INFO - __main__ - Step 147764: {'lr': 2.8179721086016295e-07, 'samples': 28370688, 'steps': 147763, 'loss/train': 0.2830890417098999} 08/31/2021 16:00:01 - INFO - __main__ - Step 147765: {'lr': 2.815453723865047e-07, 'samples': 28370880, 'steps': 147764, 'loss/train': 0.7306237816810608} 08/31/2021 16:00:01 - INFO - __main__ - Step 147766: {'lr': 2.812936464321458e-07, 'samples': 28371072, 'steps': 147765, 'loss/train': 0.048512596637010574} 08/31/2021 16:00:03 - INFO - __main__ - Step 147767: {'lr': 2.810420329971697e-07, 'samples': 28371264, 'steps': 147766, 'loss/train': 0.9421295523643494} 08/31/2021 16:00:03 - INFO - __main__ - Step 147768: {'lr': 2.80790532081715e-07, 'samples': 28371456, 'steps': 147767, 'loss/train': 1.3295831680297852} 08/31/2021 16:00:03 - INFO - __main__ - Step 147769: {'lr': 2.805391436858651e-07, 'samples': 28371648, 'steps': 147768, 'loss/train': 1.155962347984314} 08/31/2021 16:00:04 - INFO - __main__ - Step 147770: {'lr': 2.802878678097587e-07, 'samples': 28371840, 'steps': 147769, 'loss/train': 0.8566438555717468} 08/31/2021 16:00:04 - INFO - __main__ - Step 147771: {'lr': 2.800367044535068e-07, 'samples': 28372032, 'steps': 147770, 'loss/train': 0.8959218859672546} 08/31/2021 16:00:06 - INFO - __main__ - Step 147772: {'lr': 2.797856536172205e-07, 'samples': 28372224, 'steps': 147771, 'loss/train': 1.5439157485961914} 08/31/2021 16:00:06 - INFO - __main__ - Step 147773: {'lr': 2.7953471530098307e-07, 'samples': 28372416, 'steps': 147772, 'loss/train': 0.8911628127098083} 08/31/2021 16:00:06 - INFO - __main__ - Step 147774: {'lr': 2.79283889504961e-07, 'samples': 28372608, 'steps': 147773, 'loss/train': 1.075864315032959} 08/31/2021 16:00:07 - INFO - __main__ - Step 147775: {'lr': 2.790331762292375e-07, 'samples': 28372800, 'steps': 147774, 'loss/train': 1.3963897228240967} 08/31/2021 16:00:07 - INFO - __main__ - Step 147776: {'lr': 2.787825754739237e-07, 'samples': 28372992, 'steps': 147775, 'loss/train': 1.3471407890319824} 08/31/2021 16:00:09 - INFO - __main__ - Step 147777: {'lr': 2.785320872391306e-07, 'samples': 28373184, 'steps': 147776, 'loss/train': 0.04241807013750076} 08/31/2021 16:00:09 - INFO - __main__ - Step 147778: {'lr': 2.7828171152499694e-07, 'samples': 28373376, 'steps': 147777, 'loss/train': 1.007779836654663} 08/31/2021 16:00:09 - INFO - __main__ - Step 147779: {'lr': 2.780314483315782e-07, 'samples': 28373568, 'steps': 147778, 'loss/train': 1.162466049194336} 08/31/2021 16:00:10 - INFO - __main__ - Step 147780: {'lr': 2.777812976590688e-07, 'samples': 28373760, 'steps': 147779, 'loss/train': 1.4648666381835938} 08/31/2021 16:00:10 - INFO - __main__ - Step 147781: {'lr': 2.7753125950752413e-07, 'samples': 28373952, 'steps': 147780, 'loss/train': 0.9878923892974854} 08/31/2021 16:00:12 - INFO - __main__ - Step 147782: {'lr': 2.772813338770552e-07, 'samples': 28374144, 'steps': 147781, 'loss/train': 0.0928288921713829} 08/31/2021 16:00:12 - INFO - __main__ - Step 147783: {'lr': 2.770315207678009e-07, 'samples': 28374336, 'steps': 147782, 'loss/train': 1.4498090744018555} 08/31/2021 16:00:13 - INFO - __main__ - Step 147784: {'lr': 2.767818201798444e-07, 'samples': 28374528, 'steps': 147783, 'loss/train': 0.8932427763938904} 08/31/2021 16:00:13 - INFO - __main__ - Step 147785: {'lr': 2.7653223211335233e-07, 'samples': 28374720, 'steps': 147784, 'loss/train': 0.9845299124717712} 08/31/2021 16:00:13 - INFO - __main__ - Step 147786: {'lr': 2.762827565683801e-07, 'samples': 28374912, 'steps': 147785, 'loss/train': 0.8426356315612793} 08/31/2021 16:00:15 - INFO - __main__ - Step 147787: {'lr': 2.7603339354506654e-07, 'samples': 28375104, 'steps': 147786, 'loss/train': 1.142260193824768} 08/31/2021 16:00:15 - INFO - __main__ - Step 147788: {'lr': 2.7578414304349487e-07, 'samples': 28375296, 'steps': 147787, 'loss/train': 1.0940674543380737} 08/31/2021 16:00:16 - INFO - __main__ - Step 147789: {'lr': 2.755350050638317e-07, 'samples': 28375488, 'steps': 147788, 'loss/train': 0.6270378232002258} 08/31/2021 16:00:16 - INFO - __main__ - Step 147790: {'lr': 2.752859796061602e-07, 'samples': 28375680, 'steps': 147789, 'loss/train': 0.613976776599884} 08/31/2021 16:00:16 - INFO - __main__ - Step 147791: {'lr': 2.750370666705637e-07, 'samples': 28375872, 'steps': 147790, 'loss/train': 1.1465089321136475} 08/31/2021 16:00:18 - INFO - __main__ - Step 147792: {'lr': 2.7478826625720875e-07, 'samples': 28376064, 'steps': 147791, 'loss/train': 1.3020169734954834} 08/31/2021 16:00:18 - INFO - __main__ - Step 147793: {'lr': 2.745395783661786e-07, 'samples': 28376256, 'steps': 147792, 'loss/train': 1.271572232246399} 08/31/2021 16:00:19 - INFO - __main__ - Step 147794: {'lr': 2.7429100299758425e-07, 'samples': 28376448, 'steps': 147793, 'loss/train': 0.895578145980835} 08/31/2021 16:00:19 - INFO - __main__ - Step 147795: {'lr': 2.740425401515367e-07, 'samples': 28376640, 'steps': 147794, 'loss/train': 0.24372634291648865} 08/31/2021 16:00:19 - INFO - __main__ - Step 147796: {'lr': 2.737941898281471e-07, 'samples': 28376832, 'steps': 147795, 'loss/train': 1.75745689868927} 08/31/2021 16:00:21 - INFO - __main__ - Step 147797: {'lr': 2.735459520275263e-07, 'samples': 28377024, 'steps': 147796, 'loss/train': 1.1893638372421265} 08/31/2021 16:00:21 - INFO - __main__ - Step 147798: {'lr': 2.732978267498132e-07, 'samples': 28377216, 'steps': 147797, 'loss/train': 0.02437029406428337} 08/31/2021 16:00:22 - INFO - __main__ - Step 147799: {'lr': 2.73049813995091e-07, 'samples': 28377408, 'steps': 147798, 'loss/train': 1.2843953371047974} 08/31/2021 16:00:22 - INFO - __main__ - Step 147800: {'lr': 2.728019137634707e-07, 'samples': 28377600, 'steps': 147799, 'loss/train': 1.2419434785842896} 08/31/2021 16:00:22 - INFO - __main__ - Step 147801: {'lr': 2.7255412605506347e-07, 'samples': 28377792, 'steps': 147800, 'loss/train': 1.0109837055206299} 08/31/2021 16:00:24 - INFO - __main__ - Step 147802: {'lr': 2.7230645087000794e-07, 'samples': 28377984, 'steps': 147801, 'loss/train': 1.062117576599121} 08/31/2021 16:00:25 - INFO - __main__ - Step 147803: {'lr': 2.7205888820841516e-07, 'samples': 28378176, 'steps': 147802, 'loss/train': 1.2182782888412476} 08/31/2021 16:00:25 - INFO - __main__ - Step 147804: {'lr': 2.718114380703407e-07, 'samples': 28378368, 'steps': 147803, 'loss/train': 1.3378629684448242} 08/31/2021 16:00:26 - INFO - __main__ - Step 147805: {'lr': 2.7156410045595103e-07, 'samples': 28378560, 'steps': 147804, 'loss/train': 1.6036326885223389} 08/31/2021 16:00:26 - INFO - __main__ - Step 147806: {'lr': 2.713168753653572e-07, 'samples': 28378752, 'steps': 147805, 'loss/train': 1.0063841342926025} 08/31/2021 16:00:26 - INFO - __main__ - Step 147807: {'lr': 2.7106976279861473e-07, 'samples': 28378944, 'steps': 147806, 'loss/train': 0.548610508441925} 08/31/2021 16:00:28 - INFO - __main__ - Step 147808: {'lr': 2.708227627559179e-07, 'samples': 28379136, 'steps': 147807, 'loss/train': 1.5336333513259888} 08/31/2021 16:00:28 - INFO - __main__ - Step 147809: {'lr': 2.705758752372944e-07, 'samples': 28379328, 'steps': 147808, 'loss/train': 0.7800307273864746} 08/31/2021 16:00:29 - INFO - __main__ - Step 147810: {'lr': 2.7032910024293866e-07, 'samples': 28379520, 'steps': 147809, 'loss/train': 1.4200798273086548} 08/31/2021 16:00:29 - INFO - __main__ - Step 147811: {'lr': 2.7008243777287833e-07, 'samples': 28379712, 'steps': 147810, 'loss/train': 1.2696181535720825} 08/31/2021 16:00:29 - INFO - __main__ - Step 147812: {'lr': 2.698358878273077e-07, 'samples': 28379904, 'steps': 147811, 'loss/train': 1.4476269483566284} 08/31/2021 16:00:31 - INFO - __main__ - Step 147813: {'lr': 2.695894504062546e-07, 'samples': 28380096, 'steps': 147812, 'loss/train': 0.9310665130615234} 08/31/2021 16:00:32 - INFO - __main__ - Step 147814: {'lr': 2.6934312550988547e-07, 'samples': 28380288, 'steps': 147813, 'loss/train': 0.8819773197174072} 08/31/2021 16:00:32 - INFO - __main__ - Step 147815: {'lr': 2.690969131383114e-07, 'samples': 28380480, 'steps': 147814, 'loss/train': 2.1405444145202637} 08/31/2021 16:00:32 - INFO - __main__ - Step 147816: {'lr': 2.6885081329161567e-07, 'samples': 28380672, 'steps': 147815, 'loss/train': 0.8251587152481079} 08/31/2021 16:00:33 - INFO - __main__ - Step 147817: {'lr': 2.6860482596993694e-07, 'samples': 28380864, 'steps': 147816, 'loss/train': 1.0620149374008179} 08/31/2021 16:00:34 - INFO - __main__ - Step 147818: {'lr': 2.6835895117335864e-07, 'samples': 28381056, 'steps': 147817, 'loss/train': 1.5022882223129272} 08/31/2021 16:00:35 - INFO - __main__ - Step 147819: {'lr': 2.681131889019917e-07, 'samples': 28381248, 'steps': 147818, 'loss/train': 0.7192501425743103} 08/31/2021 16:00:35 - INFO - __main__ - Step 147820: {'lr': 2.678675391559748e-07, 'samples': 28381440, 'steps': 147819, 'loss/train': 1.3509865999221802} 08/31/2021 16:00:35 - INFO - __main__ - Step 147821: {'lr': 2.676220019353914e-07, 'samples': 28381632, 'steps': 147820, 'loss/train': 0.9450573921203613} 08/31/2021 16:00:36 - INFO - __main__ - Step 147822: {'lr': 2.6737657724038025e-07, 'samples': 28381824, 'steps': 147821, 'loss/train': 0.7859818339347839} 08/31/2021 16:00:37 - INFO - __main__ - Step 147823: {'lr': 2.671312650710245e-07, 'samples': 28382016, 'steps': 147822, 'loss/train': 1.4986331462860107} 08/31/2021 16:00:38 - INFO - __main__ - Step 147824: {'lr': 2.668860654274352e-07, 'samples': 28382208, 'steps': 147823, 'loss/train': 1.247742772102356} 08/31/2021 16:00:38 - INFO - __main__ - Step 147825: {'lr': 2.666409783097512e-07, 'samples': 28382400, 'steps': 147824, 'loss/train': 0.5907729268074036} 08/31/2021 16:00:38 - INFO - __main__ - Step 147826: {'lr': 2.663960037180557e-07, 'samples': 28382592, 'steps': 147825, 'loss/train': 1.0069471597671509} 08/31/2021 16:00:39 - INFO - __main__ - Step 147827: {'lr': 2.661511416524875e-07, 'samples': 28382784, 'steps': 147826, 'loss/train': 0.9340017437934875} 08/31/2021 16:00:40 - INFO - __main__ - Step 147828: {'lr': 2.6590639211312995e-07, 'samples': 28382976, 'steps': 147827, 'loss/train': 1.0319547653198242} 08/31/2021 16:00:41 - INFO - __main__ - Step 147829: {'lr': 2.6566175510009396e-07, 'samples': 28383168, 'steps': 147828, 'loss/train': 1.1007531881332397} 08/31/2021 16:00:41 - INFO - __main__ - Step 147830: {'lr': 2.654172306134905e-07, 'samples': 28383360, 'steps': 147829, 'loss/train': 0.5737046003341675} 08/31/2021 16:00:41 - INFO - __main__ - Step 147831: {'lr': 2.6517281865345854e-07, 'samples': 28383552, 'steps': 147830, 'loss/train': 1.0430622100830078} 08/31/2021 16:00:42 - INFO - __main__ - Step 147832: {'lr': 2.6492851922005345e-07, 'samples': 28383744, 'steps': 147831, 'loss/train': 0.9405934810638428} 08/31/2021 16:00:43 - INFO - __main__ - Step 147833: {'lr': 2.646843323134418e-07, 'samples': 28383936, 'steps': 147832, 'loss/train': 1.2847974300384521} 08/31/2021 16:00:44 - INFO - __main__ - Step 147834: {'lr': 2.6444025793370685e-07, 'samples': 28384128, 'steps': 147833, 'loss/train': 0.593311607837677} 08/31/2021 16:00:44 - INFO - __main__ - Step 147835: {'lr': 2.6419629608095963e-07, 'samples': 28384320, 'steps': 147834, 'loss/train': 1.2187516689300537} 08/31/2021 16:00:44 - INFO - __main__ - Step 147836: {'lr': 2.6395244675531115e-07, 'samples': 28384512, 'steps': 147835, 'loss/train': 1.3268214464187622} 08/31/2021 16:00:45 - INFO - __main__ - Step 147837: {'lr': 2.6370870995687247e-07, 'samples': 28384704, 'steps': 147836, 'loss/train': 1.2242158651351929} 08/31/2021 16:00:46 - INFO - __main__ - Step 147838: {'lr': 2.6346508568575457e-07, 'samples': 28384896, 'steps': 147837, 'loss/train': 1.031998634338379} 08/31/2021 16:00:47 - INFO - __main__ - Step 147839: {'lr': 2.632215739420685e-07, 'samples': 28385088, 'steps': 147838, 'loss/train': 0.10313428193330765} 08/31/2021 16:00:47 - INFO - __main__ - Step 147840: {'lr': 2.629781747258975e-07, 'samples': 28385280, 'steps': 147839, 'loss/train': 0.6074146032333374} 08/31/2021 16:00:47 - INFO - __main__ - Step 147841: {'lr': 2.6273488803740807e-07, 'samples': 28385472, 'steps': 147840, 'loss/train': 1.3705459833145142} 08/31/2021 16:00:48 - INFO - __main__ - Step 147842: {'lr': 2.6249171387665584e-07, 'samples': 28385664, 'steps': 147841, 'loss/train': 0.9447439312934875} 08/31/2021 16:00:48 - INFO - __main__ - Step 147843: {'lr': 2.6224865224377946e-07, 'samples': 28385856, 'steps': 147842, 'loss/train': 0.4058563709259033} 08/31/2021 16:00:50 - INFO - __main__ - Step 147844: {'lr': 2.6200570313889004e-07, 'samples': 28386048, 'steps': 147843, 'loss/train': 1.15054452419281} 08/31/2021 16:00:50 - INFO - __main__ - Step 147845: {'lr': 2.6176286656207084e-07, 'samples': 28386240, 'steps': 147844, 'loss/train': 0.7476235032081604} 08/31/2021 16:00:50 - INFO - __main__ - Step 147846: {'lr': 2.615201425134606e-07, 'samples': 28386432, 'steps': 147845, 'loss/train': 1.194932460784912} 08/31/2021 16:00:51 - INFO - __main__ - Step 147847: {'lr': 2.6127753099314254e-07, 'samples': 28386624, 'steps': 147846, 'loss/train': 1.2615854740142822} 08/31/2021 16:00:51 - INFO - __main__ - Step 147848: {'lr': 2.610350320012278e-07, 'samples': 28386816, 'steps': 147847, 'loss/train': 0.6256484389305115} 08/31/2021 16:00:53 - INFO - __main__ - Step 147849: {'lr': 2.607926455378551e-07, 'samples': 28387008, 'steps': 147848, 'loss/train': 1.5783761739730835} 08/31/2021 16:00:53 - INFO - __main__ - Step 147850: {'lr': 2.6055037160313543e-07, 'samples': 28387200, 'steps': 147849, 'loss/train': 1.103700876235962} 08/31/2021 16:00:53 - INFO - __main__ - Step 147851: {'lr': 2.6030821019712436e-07, 'samples': 28387392, 'steps': 147850, 'loss/train': 1.2329286336898804} 08/31/2021 16:00:54 - INFO - __main__ - Step 147852: {'lr': 2.6006616131998837e-07, 'samples': 28387584, 'steps': 147851, 'loss/train': 1.6475844383239746} 08/31/2021 16:00:54 - INFO - __main__ - Step 147853: {'lr': 2.5982422497178304e-07, 'samples': 28387776, 'steps': 147852, 'loss/train': 0.7581873536109924} 08/31/2021 16:00:56 - INFO - __main__ - Step 147854: {'lr': 2.5958240115267486e-07, 'samples': 28387968, 'steps': 147853, 'loss/train': 0.38765254616737366} 08/31/2021 16:00:57 - INFO - __main__ - Step 147855: {'lr': 2.593406898627193e-07, 'samples': 28388160, 'steps': 147854, 'loss/train': 1.1525425910949707} 08/31/2021 16:00:57 - INFO - __main__ - Step 147856: {'lr': 2.5909909110208295e-07, 'samples': 28388352, 'steps': 147855, 'loss/train': 0.7323870062828064} 08/31/2021 16:00:57 - INFO - __main__ - Step 147857: {'lr': 2.588576048708213e-07, 'samples': 28388544, 'steps': 147856, 'loss/train': 0.5747232437133789} 08/31/2021 16:00:58 - INFO - __main__ - Step 147858: {'lr': 2.586162311690732e-07, 'samples': 28388736, 'steps': 147857, 'loss/train': 1.045346975326538} 08/31/2021 16:00:59 - INFO - __main__ - Step 147859: {'lr': 2.5837496999694955e-07, 'samples': 28388928, 'steps': 147858, 'loss/train': 1.2789119482040405} 08/31/2021 16:01:00 - INFO - __main__ - Step 147860: {'lr': 2.5813382135453367e-07, 'samples': 28389120, 'steps': 147859, 'loss/train': 1.1224876642227173} 08/31/2021 16:01:00 - INFO - __main__ - Step 147861: {'lr': 2.578927852419366e-07, 'samples': 28389312, 'steps': 147860, 'loss/train': 0.1376175433397293} 08/31/2021 16:01:00 - INFO - __main__ - Step 147862: {'lr': 2.576518616592971e-07, 'samples': 28389504, 'steps': 147861, 'loss/train': 0.9093033671379089} 08/31/2021 16:01:01 - INFO - __main__ - Step 147863: {'lr': 2.5741105060669844e-07, 'samples': 28389696, 'steps': 147862, 'loss/train': 1.2016414403915405} 08/31/2021 16:01:01 - INFO - __main__ - Step 147864: {'lr': 2.5717035208425164e-07, 'samples': 28389888, 'steps': 147863, 'loss/train': 1.2970905303955078} 08/31/2021 16:01:03 - INFO - __main__ - Step 147865: {'lr': 2.569297660920955e-07, 'samples': 28390080, 'steps': 147864, 'loss/train': 0.22414657473564148} 08/31/2021 16:01:03 - INFO - __main__ - Step 147866: {'lr': 2.566892926302855e-07, 'samples': 28390272, 'steps': 147865, 'loss/train': 0.6413567066192627} 08/31/2021 16:01:03 - INFO - __main__ - Step 147867: {'lr': 2.5644893169896045e-07, 'samples': 28390464, 'steps': 147866, 'loss/train': 0.21255140006542206} 08/31/2021 16:01:04 - INFO - __main__ - Step 147868: {'lr': 2.5620868329823133e-07, 'samples': 28390656, 'steps': 147867, 'loss/train': 1.1185977458953857} 08/31/2021 16:01:04 - INFO - __main__ - Step 147869: {'lr': 2.559685474282092e-07, 'samples': 28390848, 'steps': 147868, 'loss/train': 1.488619327545166} 08/31/2021 16:01:06 - INFO - __main__ - Step 147870: {'lr': 2.55728524089005e-07, 'samples': 28391040, 'steps': 147869, 'loss/train': 1.1713787317276} 08/31/2021 16:01:06 - INFO - __main__ - Step 147871: {'lr': 2.554886132807022e-07, 'samples': 28391232, 'steps': 147870, 'loss/train': 1.4023312330245972} 08/31/2021 16:01:06 - INFO - __main__ - Step 147872: {'lr': 2.552488150034116e-07, 'samples': 28391424, 'steps': 147871, 'loss/train': 1.123577356338501} 08/31/2021 16:01:07 - INFO - __main__ - Step 147873: {'lr': 2.550091292572443e-07, 'samples': 28391616, 'steps': 147872, 'loss/train': 1.237303376197815} 08/31/2021 16:01:07 - INFO - __main__ - Step 147874: {'lr': 2.547695560423391e-07, 'samples': 28391808, 'steps': 147873, 'loss/train': 1.1955703496932983} 08/31/2021 16:01:09 - INFO - __main__ - Step 147875: {'lr': 2.5453009535877924e-07, 'samples': 28392000, 'steps': 147874, 'loss/train': 1.1385973691940308} 08/31/2021 16:01:09 - INFO - __main__ - Step 147876: {'lr': 2.5429074720664803e-07, 'samples': 28392192, 'steps': 147875, 'loss/train': 0.6438006162643433} 08/31/2021 16:01:09 - INFO - __main__ - Step 147877: {'lr': 2.5405151158611197e-07, 'samples': 28392384, 'steps': 147876, 'loss/train': 0.7605816721916199} 08/31/2021 16:01:10 - INFO - __main__ - Step 147878: {'lr': 2.5381238849722655e-07, 'samples': 28392576, 'steps': 147877, 'loss/train': 1.117685079574585} 08/31/2021 16:01:10 - INFO - __main__ - Step 147879: {'lr': 2.535733779401306e-07, 'samples': 28392768, 'steps': 147878, 'loss/train': 1.278891682624817} 08/31/2021 16:01:12 - INFO - __main__ - Step 147880: {'lr': 2.5333447991490734e-07, 'samples': 28392960, 'steps': 147879, 'loss/train': 1.0668669939041138} 08/31/2021 16:01:12 - INFO - __main__ - Step 147881: {'lr': 2.5309569442169557e-07, 'samples': 28393152, 'steps': 147880, 'loss/train': 1.1162794828414917} 08/31/2021 16:01:13 - INFO - __main__ - Step 147882: {'lr': 2.5285702146057855e-07, 'samples': 28393344, 'steps': 147881, 'loss/train': 1.3686120510101318} 08/31/2021 16:01:13 - INFO - __main__ - Step 147883: {'lr': 2.526184610316673e-07, 'samples': 28393536, 'steps': 147882, 'loss/train': 0.3876149356365204} 08/31/2021 16:01:13 - INFO - __main__ - Step 147884: {'lr': 2.523800131350729e-07, 'samples': 28393728, 'steps': 147883, 'loss/train': 1.2428897619247437} 08/31/2021 16:01:15 - INFO - __main__ - Step 147885: {'lr': 2.5214167777090626e-07, 'samples': 28393920, 'steps': 147884, 'loss/train': 1.2622368335723877} 08/31/2021 16:01:15 - INFO - __main__ - Step 147886: {'lr': 2.5190345493927844e-07, 'samples': 28394112, 'steps': 147885, 'loss/train': 1.1646215915679932} 08/31/2021 16:01:16 - INFO - __main__ - Step 147887: {'lr': 2.516653446402728e-07, 'samples': 28394304, 'steps': 147886, 'loss/train': 1.0312061309814453} 08/31/2021 16:01:16 - INFO - __main__ - Step 147888: {'lr': 2.514273468740003e-07, 'samples': 28394496, 'steps': 147887, 'loss/train': 1.5802671909332275} 08/31/2021 16:01:16 - INFO - __main__ - Step 147889: {'lr': 2.5118946164059965e-07, 'samples': 28394688, 'steps': 147888, 'loss/train': 0.7884431481361389} 08/31/2021 16:01:18 - INFO - __main__ - Step 147890: {'lr': 2.5095168894018194e-07, 'samples': 28394880, 'steps': 147889, 'loss/train': 0.9546454548835754} 08/31/2021 16:01:19 - INFO - __main__ - Step 147891: {'lr': 2.507140287728027e-07, 'samples': 28395072, 'steps': 147890, 'loss/train': 1.2998332977294922} 08/31/2021 16:01:19 - INFO - __main__ - Step 147892: {'lr': 2.504764811386007e-07, 'samples': 28395264, 'steps': 147891, 'loss/train': 0.885482907295227} 08/31/2021 16:01:19 - INFO - __main__ - Step 147893: {'lr': 2.5023904603768685e-07, 'samples': 28395456, 'steps': 147892, 'loss/train': 0.01513533666729927} 08/31/2021 16:01:20 - INFO - __main__ - Step 147894: {'lr': 2.500017234701446e-07, 'samples': 28395648, 'steps': 147893, 'loss/train': 1.0753766298294067} 08/31/2021 16:01:20 - INFO - __main__ - Step 147895: {'lr': 2.4976451343611264e-07, 'samples': 28395840, 'steps': 147894, 'loss/train': 1.07646644115448} 08/31/2021 16:01:22 - INFO - __main__ - Step 147896: {'lr': 2.495274159356742e-07, 'samples': 28396032, 'steps': 147895, 'loss/train': 0.8507775664329529} 08/31/2021 16:01:22 - INFO - __main__ - Step 147897: {'lr': 2.492904309689681e-07, 'samples': 28396224, 'steps': 147896, 'loss/train': 2.295067310333252} 08/31/2021 16:01:23 - INFO - __main__ - Step 147898: {'lr': 2.4905355853604984e-07, 'samples': 28396416, 'steps': 147897, 'loss/train': 2.1283867359161377} 08/31/2021 16:01:23 - INFO - __main__ - Step 147899: {'lr': 2.488167986370582e-07, 'samples': 28396608, 'steps': 147898, 'loss/train': 1.382175326347351} 08/31/2021 16:01:23 - INFO - __main__ - Step 147900: {'lr': 2.485801512721042e-07, 'samples': 28396800, 'steps': 147899, 'loss/train': 0.4652118980884552} 08/31/2021 16:01:25 - INFO - __main__ - Step 147901: {'lr': 2.4834361644129887e-07, 'samples': 28396992, 'steps': 147900, 'loss/train': 0.037652041763067245} 08/31/2021 16:01:26 - INFO - __main__ - Step 147902: {'lr': 2.4810719414469774e-07, 'samples': 28397184, 'steps': 147901, 'loss/train': 1.6636261940002441} 08/31/2021 16:01:26 - INFO - __main__ - Step 147903: {'lr': 2.478708843824673e-07, 'samples': 28397376, 'steps': 147902, 'loss/train': 0.01831940747797489} 08/31/2021 16:01:26 - INFO - __main__ - Step 147904: {'lr': 2.4763468715471857e-07, 'samples': 28397568, 'steps': 147903, 'loss/train': 0.015641000121831894} 08/31/2021 16:01:27 - INFO - __main__ - Step 147905: {'lr': 2.4739860246150713e-07, 'samples': 28397760, 'steps': 147904, 'loss/train': 1.4044363498687744} 08/31/2021 16:01:27 - INFO - __main__ - Step 147906: {'lr': 2.4716263030294394e-07, 'samples': 28397952, 'steps': 147905, 'loss/train': 1.1233198642730713} 08/31/2021 16:01:29 - INFO - __main__ - Step 147907: {'lr': 2.469267706791956e-07, 'samples': 28398144, 'steps': 147906, 'loss/train': 1.291788101196289} 08/31/2021 16:01:29 - INFO - __main__ - Step 147908: {'lr': 2.4669102359028974e-07, 'samples': 28398336, 'steps': 147907, 'loss/train': 0.8353097438812256} 08/31/2021 16:01:29 - INFO - __main__ - Step 147909: {'lr': 2.46455389036393e-07, 'samples': 28398528, 'steps': 147908, 'loss/train': 0.66846764087677} 08/31/2021 16:01:30 - INFO - __main__ - Step 147910: {'lr': 2.4621986701758857e-07, 'samples': 28398720, 'steps': 147909, 'loss/train': 0.9119292497634888} 08/31/2021 16:01:30 - INFO - __main__ - Step 147911: {'lr': 2.459844575339876e-07, 'samples': 28398912, 'steps': 147910, 'loss/train': 1.157853364944458} 08/31/2021 16:01:32 - INFO - __main__ - Step 147912: {'lr': 2.457491605856732e-07, 'samples': 28399104, 'steps': 147911, 'loss/train': 1.5499192476272583} 08/31/2021 16:01:33 - INFO - __main__ - Step 147913: {'lr': 2.4551397617278424e-07, 'samples': 28399296, 'steps': 147912, 'loss/train': 0.6509994864463806} 08/31/2021 16:01:33 - INFO - __main__ - Step 147914: {'lr': 2.45278904295404e-07, 'samples': 28399488, 'steps': 147913, 'loss/train': 1.226131558418274} 08/31/2021 16:01:33 - INFO - __main__ - Step 147915: {'lr': 2.450439449536712e-07, 'samples': 28399680, 'steps': 147914, 'loss/train': 1.3272151947021484} 08/31/2021 16:01:34 - INFO - __main__ - Step 147916: {'lr': 2.4480909814764143e-07, 'samples': 28399872, 'steps': 147915, 'loss/train': 0.7206997275352478} 08/31/2021 16:01:34 - INFO - __main__ - Step 147917: {'lr': 2.4457436387745336e-07, 'samples': 28400064, 'steps': 147916, 'loss/train': 0.5339415669441223} 08/31/2021 16:01:36 - INFO - __main__ - Step 147918: {'lr': 2.4433974214321807e-07, 'samples': 28400256, 'steps': 147917, 'loss/train': 0.3287435472011566} 08/31/2021 16:01:36 - INFO - __main__ - Step 147919: {'lr': 2.441052329450188e-07, 'samples': 28400448, 'steps': 147918, 'loss/train': 1.1785888671875} 08/31/2021 16:01:37 - INFO - __main__ - Step 147920: {'lr': 2.438708362829667e-07, 'samples': 28400640, 'steps': 147919, 'loss/train': 1.5241073369979858} 08/31/2021 16:01:37 - INFO - __main__ - Step 147921: {'lr': 2.4363655215717264e-07, 'samples': 28400832, 'steps': 147920, 'loss/train': 0.3193591237068176} 08/31/2021 16:01:37 - INFO - __main__ - Step 147922: {'lr': 2.434023805677477e-07, 'samples': 28401024, 'steps': 147921, 'loss/train': 0.35859739780426025} 08/31/2021 16:01:39 - INFO - __main__ - Step 147923: {'lr': 2.431683215148028e-07, 'samples': 28401216, 'steps': 147922, 'loss/train': 0.928735613822937} 08/31/2021 16:01:39 - INFO - __main__ - Step 147924: {'lr': 2.429343749984214e-07, 'samples': 28401408, 'steps': 147923, 'loss/train': 1.1632167100906372} 08/31/2021 16:01:40 - INFO - __main__ - Step 147925: {'lr': 2.427005410187144e-07, 'samples': 28401600, 'steps': 147924, 'loss/train': 1.4393293857574463} 08/31/2021 16:01:40 - INFO - __main__ - Step 147926: {'lr': 2.4246681957579286e-07, 'samples': 28401792, 'steps': 147925, 'loss/train': 1.0848180055618286} 08/31/2021 16:01:40 - INFO - __main__ - Step 147927: {'lr': 2.4223321066976776e-07, 'samples': 28401984, 'steps': 147926, 'loss/train': 1.341496229171753} 08/31/2021 16:01:42 - INFO - __main__ - Step 147928: {'lr': 2.419997143007502e-07, 'samples': 28402176, 'steps': 147927, 'loss/train': 0.5581887364387512} 08/31/2021 16:01:42 - INFO - __main__ - Step 147929: {'lr': 2.4176633046882337e-07, 'samples': 28402368, 'steps': 147928, 'loss/train': 0.7419480681419373} 08/31/2021 16:01:43 - INFO - __main__ - Step 147930: {'lr': 2.415330591740983e-07, 'samples': 28402560, 'steps': 147929, 'loss/train': 1.0949070453643799} 08/31/2021 16:01:43 - INFO - __main__ - Step 147931: {'lr': 2.4129990041668603e-07, 'samples': 28402752, 'steps': 147930, 'loss/train': 1.0584467649459839} 08/31/2021 16:01:43 - INFO - __main__ - Step 147932: {'lr': 2.410668541966976e-07, 'samples': 28402944, 'steps': 147931, 'loss/train': 1.0347150564193726} 08/31/2021 16:01:45 - INFO - __main__ - Step 147933: {'lr': 2.408339205142163e-07, 'samples': 28403136, 'steps': 147932, 'loss/train': 0.9646388292312622} 08/31/2021 16:01:45 - INFO - __main__ - Step 147934: {'lr': 2.4060109936935304e-07, 'samples': 28403328, 'steps': 147933, 'loss/train': 1.0819545984268188} 08/31/2021 16:01:46 - INFO - __main__ - Step 147935: {'lr': 2.403683907622467e-07, 'samples': 28403520, 'steps': 147934, 'loss/train': 1.5649011135101318} 08/31/2021 16:01:46 - INFO - __main__ - Step 147936: {'lr': 2.4013579469295275e-07, 'samples': 28403712, 'steps': 147935, 'loss/train': 1.1737300157546997} 08/31/2021 16:01:46 - INFO - __main__ - Step 147937: {'lr': 2.3990331116161004e-07, 'samples': 28403904, 'steps': 147936, 'loss/train': 0.9337190389633179} 08/31/2021 16:01:47 - INFO - __main__ - Step 147938: {'lr': 2.396709401683295e-07, 'samples': 28404096, 'steps': 147937, 'loss/train': 0.8519755005836487} 08/31/2021 16:01:48 - INFO - __main__ - Step 147939: {'lr': 2.394386817131944e-07, 'samples': 28404288, 'steps': 147938, 'loss/train': 1.3000438213348389} 08/31/2021 16:01:49 - INFO - __main__ - Step 147940: {'lr': 2.3920653579628806e-07, 'samples': 28404480, 'steps': 147939, 'loss/train': 1.5523934364318848} 08/31/2021 16:01:49 - INFO - __main__ - Step 147941: {'lr': 2.38974502417777e-07, 'samples': 28404672, 'steps': 147940, 'loss/train': 0.9674025177955627} 08/31/2021 16:01:49 - INFO - __main__ - Step 147942: {'lr': 2.3874258157768894e-07, 'samples': 28404864, 'steps': 147941, 'loss/train': 0.9519960284233093} 08/31/2021 16:01:50 - INFO - __main__ - Step 147943: {'lr': 2.385107732761904e-07, 'samples': 28405056, 'steps': 147942, 'loss/train': 1.2046772241592407} 08/31/2021 16:01:51 - INFO - __main__ - Step 147944: {'lr': 2.3827907751336475e-07, 'samples': 28405248, 'steps': 147943, 'loss/train': 0.8858973979949951} 08/31/2021 16:01:52 - INFO - __main__ - Step 147945: {'lr': 2.3804749428932293e-07, 'samples': 28405440, 'steps': 147944, 'loss/train': 0.9279797077178955} 08/31/2021 16:01:52 - INFO - __main__ - Step 147946: {'lr': 2.3781602360414823e-07, 'samples': 28405632, 'steps': 147945, 'loss/train': 1.1330301761627197} 08/31/2021 16:01:52 - INFO - __main__ - Step 147947: {'lr': 2.375846654579794e-07, 'samples': 28405824, 'steps': 147946, 'loss/train': 0.11849530786275864} 08/31/2021 16:01:53 - INFO - __main__ - Step 147948: {'lr': 2.3735341985089976e-07, 'samples': 28406016, 'steps': 147947, 'loss/train': 1.0833712816238403} 08/31/2021 16:01:54 - INFO - __main__ - Step 147949: {'lr': 2.3712228678299252e-07, 'samples': 28406208, 'steps': 147948, 'loss/train': 0.39039963483810425} 08/31/2021 16:01:55 - INFO - __main__ - Step 147950: {'lr': 2.368912662543965e-07, 'samples': 28406400, 'steps': 147949, 'loss/train': 1.2313666343688965} 08/31/2021 16:01:55 - INFO - __main__ - Step 147951: {'lr': 2.366603582652227e-07, 'samples': 28406592, 'steps': 147950, 'loss/train': 0.4962552785873413} 08/31/2021 16:01:55 - INFO - __main__ - Step 147952: {'lr': 2.3642956281552664e-07, 'samples': 28406784, 'steps': 147951, 'loss/train': 1.642956018447876} 08/31/2021 16:01:56 - INFO - __main__ - Step 147953: {'lr': 2.3619887990544709e-07, 'samples': 28406976, 'steps': 147952, 'loss/train': 1.7100244760513306} 08/31/2021 16:01:57 - INFO - __main__ - Step 147954: {'lr': 2.3596830953509506e-07, 'samples': 28407168, 'steps': 147953, 'loss/train': 0.5733720660209656} 08/31/2021 16:01:58 - INFO - __main__ - Step 147955: {'lr': 2.3573785170455386e-07, 'samples': 28407360, 'steps': 147954, 'loss/train': 0.8134728074073792} 08/31/2021 16:01:58 - INFO - __main__ - Step 147956: {'lr': 2.3550750641393447e-07, 'samples': 28407552, 'steps': 147955, 'loss/train': 1.8592787981033325} 08/31/2021 16:01:58 - INFO - __main__ - Step 147957: {'lr': 2.352772736633202e-07, 'samples': 28407744, 'steps': 147956, 'loss/train': 1.111592173576355} 08/31/2021 16:01:59 - INFO - __main__ - Step 147958: {'lr': 2.3504715345284978e-07, 'samples': 28407936, 'steps': 147957, 'loss/train': 0.08822968602180481} 08/31/2021 16:02:00 - INFO - __main__ - Step 147959: {'lr': 2.3481714578263425e-07, 'samples': 28408128, 'steps': 147958, 'loss/train': 1.7635852098464966} 08/31/2021 16:02:01 - INFO - __main__ - Step 147960: {'lr': 2.345872506527291e-07, 'samples': 28408320, 'steps': 147959, 'loss/train': 1.3316394090652466} 08/31/2021 16:02:01 - INFO - __main__ - Step 147961: {'lr': 2.343574680632732e-07, 'samples': 28408512, 'steps': 147960, 'loss/train': 0.9714809060096741} 08/31/2021 16:02:01 - INFO - __main__ - Step 147962: {'lr': 2.3412779801437746e-07, 'samples': 28408704, 'steps': 147961, 'loss/train': 1.0693931579589844} 08/31/2021 16:02:02 - INFO - __main__ - Step 147963: {'lr': 2.3389824050612518e-07, 'samples': 28408896, 'steps': 147962, 'loss/train': 1.1361091136932373} 08/31/2021 16:02:04 - INFO - __main__ - Step 147964: {'lr': 2.3366879553859966e-07, 'samples': 28409088, 'steps': 147963, 'loss/train': 1.0633598566055298} 08/31/2021 16:02:04 - INFO - __main__ - Step 147965: {'lr': 2.334394631119674e-07, 'samples': 28409280, 'steps': 147964, 'loss/train': 0.1922682225704193} 08/31/2021 16:02:05 - INFO - __main__ - Step 147966: {'lr': 2.3321024322625618e-07, 'samples': 28409472, 'steps': 147965, 'loss/train': 0.6858893632888794} 08/31/2021 16:02:05 - INFO - __main__ - Step 147967: {'lr': 2.329811358816325e-07, 'samples': 28409664, 'steps': 147966, 'loss/train': 1.498412013053894} 08/31/2021 16:02:05 - INFO - __main__ - Step 147968: {'lr': 2.327521410781519e-07, 'samples': 28409856, 'steps': 147967, 'loss/train': 0.7603107690811157} 08/31/2021 16:02:07 - INFO - __main__ - Step 147969: {'lr': 2.3252325881595314e-07, 'samples': 28410048, 'steps': 147968, 'loss/train': 1.4907807111740112} 08/31/2021 16:02:08 - INFO - __main__ - Step 147970: {'lr': 2.3229448909511953e-07, 'samples': 28410240, 'steps': 147969, 'loss/train': 1.4383875131607056} 08/31/2021 16:02:08 - INFO - __main__ - Step 147971: {'lr': 2.3206583191576203e-07, 'samples': 28410432, 'steps': 147970, 'loss/train': 1.9613029956817627} 08/31/2021 16:02:08 - INFO - __main__ - Step 147972: {'lr': 2.3183728727799168e-07, 'samples': 28410624, 'steps': 147971, 'loss/train': 0.5585277080535889} 08/31/2021 16:02:09 - INFO - __main__ - Step 147973: {'lr': 2.316088551818918e-07, 'samples': 28410816, 'steps': 147972, 'loss/train': 0.05166059732437134} 08/31/2021 16:02:09 - INFO - __main__ - Step 147974: {'lr': 2.3138053562757333e-07, 'samples': 28411008, 'steps': 147973, 'loss/train': 0.021439170464873314} 08/31/2021 16:02:11 - INFO - __main__ - Step 147975: {'lr': 2.3115232861514736e-07, 'samples': 28411200, 'steps': 147974, 'loss/train': 0.024057164788246155} 08/31/2021 16:02:11 - INFO - __main__ - Step 147976: {'lr': 2.309242341446971e-07, 'samples': 28411392, 'steps': 147975, 'loss/train': 0.6942888498306274} 08/31/2021 16:02:11 - INFO - __main__ - Step 147977: {'lr': 2.3069625221633362e-07, 'samples': 28411584, 'steps': 147976, 'loss/train': 1.1308575868606567} 08/31/2021 16:02:12 - INFO - __main__ - Step 147978: {'lr': 2.3046838283019566e-07, 'samples': 28411776, 'steps': 147977, 'loss/train': 0.9016162753105164} 08/31/2021 16:02:12 - INFO - __main__ - Step 147979: {'lr': 2.3024062598631102e-07, 'samples': 28411968, 'steps': 147978, 'loss/train': 1.2356865406036377} 08/31/2021 16:02:14 - INFO - __main__ - Step 147980: {'lr': 2.300129816848462e-07, 'samples': 28412160, 'steps': 147979, 'loss/train': 1.1817553043365479} 08/31/2021 16:02:14 - INFO - __main__ - Step 147981: {'lr': 2.297854499259122e-07, 'samples': 28412352, 'steps': 147980, 'loss/train': 1.3175863027572632} 08/31/2021 16:02:14 - INFO - __main__ - Step 147982: {'lr': 2.2955803070953684e-07, 'samples': 28412544, 'steps': 147981, 'loss/train': 0.9860726594924927} 08/31/2021 16:02:15 - INFO - __main__ - Step 147983: {'lr': 2.2933072403588662e-07, 'samples': 28412736, 'steps': 147982, 'loss/train': 1.32563316822052} 08/31/2021 16:02:15 - INFO - __main__ - Step 147984: {'lr': 2.291035299050448e-07, 'samples': 28412928, 'steps': 147983, 'loss/train': 0.8879629373550415} 08/31/2021 16:02:17 - INFO - __main__ - Step 147985: {'lr': 2.288764483171224e-07, 'samples': 28413120, 'steps': 147984, 'loss/train': 1.0314539670944214} 08/31/2021 16:02:17 - INFO - __main__ - Step 147986: {'lr': 2.2864947927223045e-07, 'samples': 28413312, 'steps': 147985, 'loss/train': 0.9064592719078064} 08/31/2021 16:02:18 - INFO - __main__ - Step 147987: {'lr': 2.2842262277042447e-07, 'samples': 28413504, 'steps': 147986, 'loss/train': 0.30607569217681885} 08/31/2021 16:02:18 - INFO - __main__ - Step 147988: {'lr': 2.2819587881184322e-07, 'samples': 28413696, 'steps': 147987, 'loss/train': 1.5059049129486084} 08/31/2021 16:02:18 - INFO - __main__ - Step 147989: {'lr': 2.2796924739659776e-07, 'samples': 28413888, 'steps': 147988, 'loss/train': 1.523025631904602} 08/31/2021 16:02:19 - INFO - __main__ - Step 147990: {'lr': 2.2774272852474352e-07, 'samples': 28414080, 'steps': 147989, 'loss/train': 0.8045012950897217} 08/31/2021 16:02:20 - INFO - __main__ - Step 147991: {'lr': 2.2751632219644712e-07, 'samples': 28414272, 'steps': 147990, 'loss/train': 5.708052158355713} 08/31/2021 16:02:21 - INFO - __main__ - Step 147992: {'lr': 2.2729002841176404e-07, 'samples': 28414464, 'steps': 147991, 'loss/train': 1.0294387340545654} 08/31/2021 16:02:21 - INFO - __main__ - Step 147993: {'lr': 2.270638471708053e-07, 'samples': 28414656, 'steps': 147992, 'loss/train': 1.119577407836914} 08/31/2021 16:02:21 - INFO - __main__ - Step 147994: {'lr': 2.2683777847368192e-07, 'samples': 28414848, 'steps': 147993, 'loss/train': 0.9485573768615723} 08/31/2021 16:02:22 - INFO - __main__ - Step 147995: {'lr': 2.2661182232047717e-07, 'samples': 28415040, 'steps': 147994, 'loss/train': 1.5225167274475098} 08/31/2021 16:02:23 - INFO - __main__ - Step 147996: {'lr': 2.2638597871132982e-07, 'samples': 28415232, 'steps': 147995, 'loss/train': 1.2722755670547485} 08/31/2021 16:02:24 - INFO - __main__ - Step 147997: {'lr': 2.2616024764632315e-07, 'samples': 28415424, 'steps': 147996, 'loss/train': 1.083930253982544} 08/31/2021 16:02:24 - INFO - __main__ - Step 147998: {'lr': 2.2593462912554042e-07, 'samples': 28415616, 'steps': 147997, 'loss/train': 0.943109929561615} 08/31/2021 16:02:24 - INFO - __main__ - Step 147999: {'lr': 2.2570912314909264e-07, 'samples': 28415808, 'steps': 147998, 'loss/train': 1.0948740243911743} 08/31/2021 16:02:25 - INFO - __main__ - Step 148000: {'lr': 2.2548372971709085e-07, 'samples': 28416000, 'steps': 147999, 'loss/train': 0.4908160865306854} 08/31/2021 16:02:25 - INFO - __main__ - Step 148001: {'lr': 2.252584488296461e-07, 'samples': 28416192, 'steps': 148000, 'loss/train': 1.0601675510406494} 08/31/2021 16:02:27 - INFO - __main__ - Step 148002: {'lr': 2.2503328048681383e-07, 'samples': 28416384, 'steps': 148001, 'loss/train': 0.5858936309814453} 08/31/2021 16:02:27 - INFO - __main__ - Step 148003: {'lr': 2.248082246887606e-07, 'samples': 28416576, 'steps': 148002, 'loss/train': 1.0757954120635986} 08/31/2021 16:02:27 - INFO - __main__ - Step 148004: {'lr': 2.2458328143554197e-07, 'samples': 28416768, 'steps': 148003, 'loss/train': 0.7843337059020996} 08/31/2021 16:02:28 - INFO - __main__ - Step 148005: {'lr': 2.2435845072726891e-07, 'samples': 28416960, 'steps': 148004, 'loss/train': 0.8671941161155701} 08/31/2021 16:02:28 - INFO - __main__ - Step 148006: {'lr': 2.241337325640247e-07, 'samples': 28417152, 'steps': 148005, 'loss/train': 1.1727254390716553} 08/31/2021 16:02:30 - INFO - __main__ - Step 148007: {'lr': 2.2390912694597588e-07, 'samples': 28417344, 'steps': 148006, 'loss/train': 1.3512682914733887} 08/31/2021 16:02:30 - INFO - __main__ - Step 148008: {'lr': 2.236846338731502e-07, 'samples': 28417536, 'steps': 148007, 'loss/train': 1.4845277070999146} 08/31/2021 16:02:30 - INFO - __main__ - Step 148009: {'lr': 2.2346025334568644e-07, 'samples': 28417728, 'steps': 148008, 'loss/train': 2.5333473682403564} 08/31/2021 16:02:31 - INFO - __main__ - Step 148010: {'lr': 2.2323598536366785e-07, 'samples': 28417920, 'steps': 148009, 'loss/train': 1.4187241792678833} 08/31/2021 16:02:31 - INFO - __main__ - Step 148011: {'lr': 2.230118299272055e-07, 'samples': 28418112, 'steps': 148010, 'loss/train': 1.9742690324783325} 08/31/2021 16:02:33 - INFO - __main__ - Step 148012: {'lr': 2.2278778703641034e-07, 'samples': 28418304, 'steps': 148011, 'loss/train': 0.8289358615875244} 08/31/2021 16:02:33 - INFO - __main__ - Step 148013: {'lr': 2.225638566913657e-07, 'samples': 28418496, 'steps': 148012, 'loss/train': 0.8737871646881104} 08/31/2021 16:02:33 - INFO - __main__ - Step 148014: {'lr': 2.2234003889218258e-07, 'samples': 28418688, 'steps': 148013, 'loss/train': 0.13519810140132904} 08/31/2021 16:02:34 - INFO - __main__ - Step 148015: {'lr': 2.22116333638972e-07, 'samples': 28418880, 'steps': 148014, 'loss/train': 1.032361626625061} 08/31/2021 16:02:34 - INFO - __main__ - Step 148016: {'lr': 2.2189274093178947e-07, 'samples': 28419072, 'steps': 148015, 'loss/train': 1.3716319799423218} 08/31/2021 16:02:35 - INFO - __main__ - Step 148017: {'lr': 2.216692607708015e-07, 'samples': 28419264, 'steps': 148016, 'loss/train': 1.1019867658615112} 08/31/2021 16:02:36 - INFO - __main__ - Step 148018: {'lr': 2.2144589315606367e-07, 'samples': 28419456, 'steps': 148017, 'loss/train': 1.1384471654891968} 08/31/2021 16:02:37 - INFO - __main__ - Step 148019: {'lr': 2.2122263808768695e-07, 'samples': 28419648, 'steps': 148018, 'loss/train': 0.023683706298470497} 08/31/2021 16:02:37 - INFO - __main__ - Step 148020: {'lr': 2.2099949556575462e-07, 'samples': 28419840, 'steps': 148019, 'loss/train': 0.5276066660881042} 08/31/2021 16:02:38 - INFO - __main__ - Step 148021: {'lr': 2.2077646559040543e-07, 'samples': 28420032, 'steps': 148020, 'loss/train': 1.0994194746017456} 08/31/2021 16:02:38 - INFO - __main__ - Step 148022: {'lr': 2.2055354816172268e-07, 'samples': 28420224, 'steps': 148021, 'loss/train': 1.0113258361816406} 08/31/2021 16:02:40 - INFO - __main__ - Step 148023: {'lr': 2.2033074327978963e-07, 'samples': 28420416, 'steps': 148022, 'loss/train': 0.2955532670021057} 08/31/2021 16:02:40 - INFO - __main__ - Step 148024: {'lr': 2.201080509447173e-07, 'samples': 28420608, 'steps': 148023, 'loss/train': 1.5379377603530884} 08/31/2021 16:02:41 - INFO - __main__ - Step 148025: {'lr': 2.1988547115664448e-07, 'samples': 28420800, 'steps': 148024, 'loss/train': 1.508727788925171} 08/31/2021 16:02:41 - INFO - __main__ - Step 148026: {'lr': 2.196630039155989e-07, 'samples': 28420992, 'steps': 148025, 'loss/train': 1.010501503944397} 08/31/2021 16:02:41 - INFO - __main__ - Step 148027: {'lr': 2.1944064922174712e-07, 'samples': 28421184, 'steps': 148026, 'loss/train': 0.019542232155799866} 08/31/2021 16:02:43 - INFO - __main__ - Step 148028: {'lr': 2.1921840707514463e-07, 'samples': 28421376, 'steps': 148027, 'loss/train': 1.0597903728485107} 08/31/2021 16:02:44 - INFO - __main__ - Step 148029: {'lr': 2.1899627747590245e-07, 'samples': 28421568, 'steps': 148028, 'loss/train': 1.7546875476837158} 08/31/2021 16:02:44 - INFO - __main__ - Step 148030: {'lr': 2.1877426042413162e-07, 'samples': 28421760, 'steps': 148029, 'loss/train': 1.083483099937439} 08/31/2021 16:02:44 - INFO - __main__ - Step 148031: {'lr': 2.1855235591994316e-07, 'samples': 28421952, 'steps': 148030, 'loss/train': 0.41919732093811035} 08/31/2021 16:02:45 - INFO - __main__ - Step 148032: {'lr': 2.1833056396339256e-07, 'samples': 28422144, 'steps': 148031, 'loss/train': 0.04864969477057457} 08/31/2021 16:02:47 - INFO - __main__ - Step 148033: {'lr': 2.181088845546464e-07, 'samples': 28422336, 'steps': 148032, 'loss/train': 0.9370874762535095} 08/31/2021 16:02:47 - INFO - __main__ - Step 148034: {'lr': 2.1788731769373238e-07, 'samples': 28422528, 'steps': 148033, 'loss/train': 0.23179791867733002} 08/31/2021 16:02:47 - INFO - __main__ - Step 148035: {'lr': 2.1766586338078932e-07, 'samples': 28422720, 'steps': 148034, 'loss/train': 0.6209652423858643} 08/31/2021 16:02:48 - INFO - __main__ - Step 148036: {'lr': 2.174445216159282e-07, 'samples': 28422912, 'steps': 148035, 'loss/train': 1.607115387916565} 08/31/2021 16:02:48 - INFO - __main__ - Step 148037: {'lr': 2.1722329239920458e-07, 'samples': 28423104, 'steps': 148036, 'loss/train': 0.7208557724952698} 08/31/2021 16:02:49 - INFO - __main__ - Step 148038: {'lr': 2.1700217573075721e-07, 'samples': 28423296, 'steps': 148037, 'loss/train': 1.5397694110870361} 08/31/2021 16:02:50 - INFO - __main__ - Step 148039: {'lr': 2.167811716106971e-07, 'samples': 28423488, 'steps': 148038, 'loss/train': 0.7682721018791199} 08/31/2021 16:02:50 - INFO - __main__ - Step 148040: {'lr': 2.1656028003907978e-07, 'samples': 28423680, 'steps': 148039, 'loss/train': 0.9691418409347534} 08/31/2021 16:02:51 - INFO - __main__ - Step 148041: {'lr': 2.163395010160163e-07, 'samples': 28423872, 'steps': 148040, 'loss/train': 1.2531836032867432} 08/31/2021 16:02:51 - INFO - __main__ - Step 148042: {'lr': 2.161188345416454e-07, 'samples': 28424064, 'steps': 148041, 'loss/train': 1.199931263923645} 08/31/2021 16:02:53 - INFO - __main__ - Step 148043: {'lr': 2.158982806159948e-07, 'samples': 28424256, 'steps': 148042, 'loss/train': 1.222517490386963} 08/31/2021 16:02:53 - INFO - __main__ - Step 148044: {'lr': 2.1567783923923112e-07, 'samples': 28424448, 'steps': 148043, 'loss/train': 1.1647816896438599} 08/31/2021 16:02:53 - INFO - __main__ - Step 148045: {'lr': 2.1545751041143756e-07, 'samples': 28424640, 'steps': 148044, 'loss/train': 1.3090647459030151} 08/31/2021 16:02:54 - INFO - __main__ - Step 148046: {'lr': 2.1523729413269744e-07, 'samples': 28424832, 'steps': 148045, 'loss/train': 0.9558101296424866} 08/31/2021 16:02:54 - INFO - __main__ - Step 148047: {'lr': 2.1501719040312172e-07, 'samples': 28425024, 'steps': 148046, 'loss/train': 1.6994906663894653} 08/31/2021 16:02:54 - INFO - __main__ - Step 148048: {'lr': 2.1479719922279372e-07, 'samples': 28425216, 'steps': 148047, 'loss/train': 1.079070806503296} 08/31/2021 16:02:56 - INFO - __main__ - Step 148049: {'lr': 2.1457732059182443e-07, 'samples': 28425408, 'steps': 148048, 'loss/train': 1.0049716234207153} 08/31/2021 16:02:57 - INFO - __main__ - Step 148050: {'lr': 2.143575545103249e-07, 'samples': 28425600, 'steps': 148049, 'loss/train': 0.13356350362300873} 08/31/2021 16:02:57 - INFO - __main__ - Step 148051: {'lr': 2.1413790097837837e-07, 'samples': 28425792, 'steps': 148050, 'loss/train': 0.9804195165634155} 08/31/2021 16:02:57 - INFO - __main__ - Step 148052: {'lr': 2.1391835999606813e-07, 'samples': 28425984, 'steps': 148051, 'loss/train': 0.9949619174003601} 08/31/2021 16:02:58 - INFO - __main__ - Step 148053: {'lr': 2.1369893156353293e-07, 'samples': 28426176, 'steps': 148052, 'loss/train': 1.4160797595977783} 08/31/2021 16:02:59 - INFO - __main__ - Step 148054: {'lr': 2.134796156808283e-07, 'samples': 28426368, 'steps': 148053, 'loss/train': 1.0298957824707031} 08/31/2021 16:02:59 - INFO - __main__ - Step 148055: {'lr': 2.13260412348093e-07, 'samples': 28426560, 'steps': 148054, 'loss/train': 0.7297840714454651} 08/31/2021 16:03:00 - INFO - __main__ - Step 148056: {'lr': 2.1304132156541033e-07, 'samples': 28426752, 'steps': 148055, 'loss/train': 1.0069934129714966} 08/31/2021 16:03:00 - INFO - __main__ - Step 148057: {'lr': 2.1282234333286354e-07, 'samples': 28426944, 'steps': 148056, 'loss/train': 1.2767716646194458} 08/31/2021 16:03:01 - INFO - __main__ - Step 148058: {'lr': 2.1260347765056365e-07, 'samples': 28427136, 'steps': 148057, 'loss/train': 0.5618412494659424} 08/31/2021 16:03:02 - INFO - __main__ - Step 148059: {'lr': 2.123847245186217e-07, 'samples': 28427328, 'steps': 148058, 'loss/train': 1.0143266916275024} 08/31/2021 16:03:02 - INFO - __main__ - Step 148060: {'lr': 2.121660839371209e-07, 'samples': 28427520, 'steps': 148059, 'loss/train': 0.100196972489357} 08/31/2021 16:03:03 - INFO - __main__ - Step 148061: {'lr': 2.1194755590617232e-07, 'samples': 28427712, 'steps': 148060, 'loss/train': 1.1062607765197754} 08/31/2021 16:03:03 - INFO - __main__ - Step 148062: {'lr': 2.1172914042585922e-07, 'samples': 28427904, 'steps': 148061, 'loss/train': 1.316848635673523} 08/31/2021 16:03:04 - INFO - __main__ - Step 148063: {'lr': 2.1151083749629263e-07, 'samples': 28428096, 'steps': 148062, 'loss/train': 1.0601141452789307} 08/31/2021 16:03:05 - INFO - __main__ - Step 148064: {'lr': 2.112926471175558e-07, 'samples': 28428288, 'steps': 148063, 'loss/train': 1.0878788232803345} 08/31/2021 16:03:05 - INFO - __main__ - Step 148065: {'lr': 2.1107456928975975e-07, 'samples': 28428480, 'steps': 148064, 'loss/train': 1.315969467163086} 08/31/2021 16:03:06 - INFO - __main__ - Step 148066: {'lr': 2.1085660401298778e-07, 'samples': 28428672, 'steps': 148065, 'loss/train': 0.8817318081855774} 08/31/2021 16:03:06 - INFO - __main__ - Step 148067: {'lr': 2.1063875128735088e-07, 'samples': 28428864, 'steps': 148066, 'loss/train': 0.4289497435092926} 08/31/2021 16:03:07 - INFO - __main__ - Step 148068: {'lr': 2.104210111129601e-07, 'samples': 28429056, 'steps': 148067, 'loss/train': 1.1825662851333618} 08/31/2021 16:03:08 - INFO - __main__ - Step 148069: {'lr': 2.1020338348989864e-07, 'samples': 28429248, 'steps': 148068, 'loss/train': 1.4747209548950195} 08/31/2021 16:03:08 - INFO - __main__ - Step 148070: {'lr': 2.0998586841824984e-07, 'samples': 28429440, 'steps': 148069, 'loss/train': 1.001777172088623} 08/31/2021 16:03:09 - INFO - __main__ - Step 148071: {'lr': 2.097684658981247e-07, 'samples': 28429632, 'steps': 148070, 'loss/train': 1.1351426839828491} 08/31/2021 16:03:09 - INFO - __main__ - Step 148072: {'lr': 2.0955117592963424e-07, 'samples': 28429824, 'steps': 148071, 'loss/train': 1.1937973499298096} 08/31/2021 16:03:10 - INFO - __main__ - Step 148073: {'lr': 2.0933399851286173e-07, 'samples': 28430016, 'steps': 148072, 'loss/train': 0.20167666673660278} 08/31/2021 16:03:12 - INFO - __main__ - Step 148074: {'lr': 2.0911693364791816e-07, 'samples': 28430208, 'steps': 148073, 'loss/train': 1.0671521425247192} 08/31/2021 16:03:12 - INFO - __main__ - Step 148075: {'lr': 2.0889998133488685e-07, 'samples': 28430400, 'steps': 148074, 'loss/train': 1.3793665170669556} 08/31/2021 16:03:13 - INFO - __main__ - Step 148076: {'lr': 2.086831415738788e-07, 'samples': 28430592, 'steps': 148075, 'loss/train': 1.0331840515136719} 08/31/2021 16:03:13 - INFO - __main__ - Step 148077: {'lr': 2.0846641436497726e-07, 'samples': 28430784, 'steps': 148076, 'loss/train': 0.9718009829521179} 08/31/2021 16:03:13 - INFO - __main__ - Step 148078: {'lr': 2.082497997082655e-07, 'samples': 28430976, 'steps': 148077, 'loss/train': 1.022688865661621} 08/31/2021 16:03:15 - INFO - __main__ - Step 148079: {'lr': 2.0803329760388233e-07, 'samples': 28431168, 'steps': 148078, 'loss/train': 0.6314277052879333} 08/31/2021 16:03:15 - INFO - __main__ - Step 148080: {'lr': 2.07816908051911e-07, 'samples': 28431360, 'steps': 148079, 'loss/train': 1.0726264715194702} 08/31/2021 16:03:16 - INFO - __main__ - Step 148081: {'lr': 2.0760063105243477e-07, 'samples': 28431552, 'steps': 148080, 'loss/train': 1.0658128261566162} 08/31/2021 16:03:16 - INFO - __main__ - Step 148082: {'lr': 2.0738446660556465e-07, 'samples': 28431744, 'steps': 148081, 'loss/train': 0.5670775771141052} 08/31/2021 16:03:16 - INFO - __main__ - Step 148083: {'lr': 2.0716841471138392e-07, 'samples': 28431936, 'steps': 148082, 'loss/train': 1.18900465965271} 08/31/2021 16:03:18 - INFO - __main__ - Step 148084: {'lr': 2.0695247537000362e-07, 'samples': 28432128, 'steps': 148083, 'loss/train': 1.0689799785614014} 08/31/2021 16:03:19 - INFO - __main__ - Step 148085: {'lr': 2.06736648581507e-07, 'samples': 28432320, 'steps': 148084, 'loss/train': 0.6419141888618469} 08/31/2021 16:03:19 - INFO - __main__ - Step 148086: {'lr': 2.0652093434600504e-07, 'samples': 28432512, 'steps': 148085, 'loss/train': 0.0932016372680664} 08/31/2021 16:03:19 - INFO - __main__ - Step 148087: {'lr': 2.0630533266360884e-07, 'samples': 28432704, 'steps': 148086, 'loss/train': 0.383104145526886} 08/31/2021 16:03:20 - INFO - __main__ - Step 148088: {'lr': 2.0608984353437387e-07, 'samples': 28432896, 'steps': 148087, 'loss/train': 1.33073091506958} 08/31/2021 16:03:20 - INFO - __main__ - Step 148089: {'lr': 2.0587446695841117e-07, 'samples': 28433088, 'steps': 148088, 'loss/train': 0.2892843186855316} 08/31/2021 16:03:21 - INFO - __main__ - Step 148090: {'lr': 2.0565920293585949e-07, 'samples': 28433280, 'steps': 148089, 'loss/train': 0.42294928431510925} 08/31/2021 16:03:22 - INFO - __main__ - Step 148091: {'lr': 2.054440514667466e-07, 'samples': 28433472, 'steps': 148090, 'loss/train': 0.14632321894168854} 08/31/2021 16:03:22 - INFO - __main__ - Step 148092: {'lr': 2.0522901255123904e-07, 'samples': 28433664, 'steps': 148091, 'loss/train': 0.9107417464256287} 08/31/2021 16:03:23 - INFO - __main__ - Step 148093: {'lr': 2.050140861893923e-07, 'samples': 28433856, 'steps': 148092, 'loss/train': 1.4748984575271606} 08/31/2021 16:03:23 - INFO - __main__ - Step 148094: {'lr': 2.047992723812897e-07, 'samples': 28434048, 'steps': 148093, 'loss/train': 1.792205810546875} 08/31/2021 16:03:24 - INFO - __main__ - Step 148095: {'lr': 2.0458457112706996e-07, 'samples': 28434240, 'steps': 148094, 'loss/train': 1.1177945137023926} 08/31/2021 16:03:25 - INFO - __main__ - Step 148096: {'lr': 2.0436998242681637e-07, 'samples': 28434432, 'steps': 148095, 'loss/train': 0.5109391212463379} 08/31/2021 16:03:25 - INFO - __main__ - Step 148097: {'lr': 2.041555062806122e-07, 'samples': 28434624, 'steps': 148096, 'loss/train': 0.7516671419143677} 08/31/2021 16:03:25 - INFO - __main__ - Step 148098: {'lr': 2.039411426885407e-07, 'samples': 28434816, 'steps': 148097, 'loss/train': 0.989525556564331} 08/31/2021 16:03:26 - INFO - __main__ - Step 148099: {'lr': 2.0372689165074064e-07, 'samples': 28435008, 'steps': 148098, 'loss/train': 1.2314691543579102} 08/31/2021 16:03:27 - INFO - __main__ - Step 148100: {'lr': 2.0351275316729534e-07, 'samples': 28435200, 'steps': 148099, 'loss/train': 0.3602571487426758} 08/31/2021 16:03:28 - INFO - __main__ - Step 148101: {'lr': 2.03298727238288e-07, 'samples': 28435392, 'steps': 148100, 'loss/train': 0.5727855563163757} 08/31/2021 16:03:28 - INFO - __main__ - Step 148102: {'lr': 2.0308481386380195e-07, 'samples': 28435584, 'steps': 148101, 'loss/train': 0.9563926458358765} 08/31/2021 16:03:28 - INFO - __main__ - Step 148103: {'lr': 2.0287101304394818e-07, 'samples': 28435776, 'steps': 148102, 'loss/train': 1.233651041984558} 08/31/2021 16:03:29 - INFO - __main__ - Step 148104: {'lr': 2.0265732477883769e-07, 'samples': 28435968, 'steps': 148103, 'loss/train': 0.039928752928972244} 08/31/2021 16:03:30 - INFO - __main__ - Step 148105: {'lr': 2.024437490685538e-07, 'samples': 28436160, 'steps': 148104, 'loss/train': 0.8311025500297546} 08/31/2021 16:03:31 - INFO - __main__ - Step 148106: {'lr': 2.0223028591320746e-07, 'samples': 28436352, 'steps': 148105, 'loss/train': 0.9702659249305725} 08/31/2021 16:03:31 - INFO - __main__ - Step 148107: {'lr': 2.02016935312882e-07, 'samples': 28436544, 'steps': 148106, 'loss/train': 1.3804463148117065} 08/31/2021 16:03:32 - INFO - __main__ - Step 148108: {'lr': 2.0180369726766068e-07, 'samples': 28436736, 'steps': 148107, 'loss/train': 0.9136902093887329} 08/31/2021 16:03:32 - INFO - __main__ - Step 148109: {'lr': 2.0159057177762675e-07, 'samples': 28436928, 'steps': 148108, 'loss/train': 0.882952094078064} 08/31/2021 16:03:33 - INFO - __main__ - Step 148110: {'lr': 2.0137755884294673e-07, 'samples': 28437120, 'steps': 148109, 'loss/train': 1.0186628103256226} 08/31/2021 16:03:34 - INFO - __main__ - Step 148111: {'lr': 2.011646584636484e-07, 'samples': 28437312, 'steps': 148110, 'loss/train': 1.3904383182525635} 08/31/2021 16:03:34 - INFO - __main__ - Step 148112: {'lr': 2.0095187063984278e-07, 'samples': 28437504, 'steps': 148111, 'loss/train': 1.0781809091567993} 08/31/2021 16:03:35 - INFO - __main__ - Step 148113: {'lr': 2.0073919537166864e-07, 'samples': 28437696, 'steps': 148112, 'loss/train': 1.1611003875732422} 08/31/2021 16:03:35 - INFO - __main__ - Step 148114: {'lr': 2.0052663265915373e-07, 'samples': 28437888, 'steps': 148113, 'loss/train': 1.085184097290039} 08/31/2021 16:03:36 - INFO - __main__ - Step 148115: {'lr': 2.0031418250243684e-07, 'samples': 28438080, 'steps': 148114, 'loss/train': 0.7168339490890503} 08/31/2021 16:03:37 - INFO - __main__ - Step 148116: {'lr': 2.001018449016012e-07, 'samples': 28438272, 'steps': 148115, 'loss/train': 0.24330028891563416} 08/31/2021 16:03:37 - INFO - __main__ - Step 148117: {'lr': 1.998896198567579e-07, 'samples': 28438464, 'steps': 148116, 'loss/train': 0.6641662120819092} 08/31/2021 16:03:38 - INFO - __main__ - Step 148118: {'lr': 1.9967750736796242e-07, 'samples': 28438656, 'steps': 148117, 'loss/train': 1.9393219947814941} 08/31/2021 16:03:38 - INFO - __main__ - Step 148119: {'lr': 1.9946550743535353e-07, 'samples': 28438848, 'steps': 148118, 'loss/train': 0.1301070600748062} 08/31/2021 16:03:40 - INFO - __main__ - Step 148120: {'lr': 1.992536200590145e-07, 'samples': 28439040, 'steps': 148119, 'loss/train': 0.8776979446411133} 08/31/2021 16:03:40 - INFO - __main__ - Step 148121: {'lr': 1.9904184523902858e-07, 'samples': 28439232, 'steps': 148120, 'loss/train': 1.1359951496124268} 08/31/2021 16:03:41 - INFO - __main__ - Step 148122: {'lr': 1.9883018297550681e-07, 'samples': 28439424, 'steps': 148121, 'loss/train': 1.6133760213851929} 08/31/2021 16:03:41 - INFO - __main__ - Step 148123: {'lr': 1.9861863326853248e-07, 'samples': 28439616, 'steps': 148122, 'loss/train': 0.923520028591156} 08/31/2021 16:03:41 - INFO - __main__ - Step 148124: {'lr': 1.9840719611821656e-07, 'samples': 28439808, 'steps': 148123, 'loss/train': 1.5590440034866333} 08/31/2021 16:03:42 - INFO - __main__ - Step 148125: {'lr': 1.9819587152464235e-07, 'samples': 28440000, 'steps': 148124, 'loss/train': 0.3270132541656494} 08/31/2021 16:03:43 - INFO - __main__ - Step 148126: {'lr': 1.9798465948789314e-07, 'samples': 28440192, 'steps': 148125, 'loss/train': 0.11296364665031433} 08/31/2021 16:03:44 - INFO - __main__ - Step 148127: {'lr': 1.977735600080799e-07, 'samples': 28440384, 'steps': 148126, 'loss/train': 2.1312050819396973} 08/31/2021 16:03:44 - INFO - __main__ - Step 148128: {'lr': 1.9756257308531368e-07, 'samples': 28440576, 'steps': 148127, 'loss/train': 0.9687930941581726} 08/31/2021 16:03:44 - INFO - __main__ - Step 148129: {'lr': 1.9735169871965e-07, 'samples': 28440768, 'steps': 148128, 'loss/train': 0.4439353942871094} 08/31/2021 16:03:45 - INFO - __main__ - Step 148130: {'lr': 1.9714093691122757e-07, 'samples': 28440960, 'steps': 148129, 'loss/train': 1.2589387893676758} 08/31/2021 16:03:47 - INFO - __main__ - Step 148131: {'lr': 1.9693028766010203e-07, 'samples': 28441152, 'steps': 148130, 'loss/train': 0.18341858685016632} 08/31/2021 16:03:47 - INFO - __main__ - Step 148132: {'lr': 1.9671975096638428e-07, 'samples': 28441344, 'steps': 148131, 'loss/train': 0.5662155151367188} 08/31/2021 16:03:47 - INFO - __main__ - Step 148133: {'lr': 1.9650932683015766e-07, 'samples': 28441536, 'steps': 148132, 'loss/train': 0.5240796208381653} 08/31/2021 16:03:48 - INFO - __main__ - Step 148134: {'lr': 1.962990152515609e-07, 'samples': 28441728, 'steps': 148133, 'loss/train': 0.9945071935653687} 08/31/2021 16:03:48 - INFO - __main__ - Step 148135: {'lr': 1.960888162306218e-07, 'samples': 28441920, 'steps': 148134, 'loss/train': 0.8677831888198853} 08/31/2021 16:03:50 - INFO - __main__ - Step 148136: {'lr': 1.9587872976750688e-07, 'samples': 28442112, 'steps': 148135, 'loss/train': 1.392162561416626} 08/31/2021 16:03:50 - INFO - __main__ - Step 148137: {'lr': 1.9566875586224387e-07, 'samples': 28442304, 'steps': 148136, 'loss/train': 0.5133410096168518} 08/31/2021 16:03:51 - INFO - __main__ - Step 148138: {'lr': 1.9545889451497156e-07, 'samples': 28442496, 'steps': 148137, 'loss/train': 1.153288722038269} 08/31/2021 16:03:51 - INFO - __main__ - Step 148139: {'lr': 1.9524914572577325e-07, 'samples': 28442688, 'steps': 148138, 'loss/train': 0.39866653084754944} 08/31/2021 16:03:51 - INFO - __main__ - Step 148140: {'lr': 1.9503950949473214e-07, 'samples': 28442880, 'steps': 148139, 'loss/train': 1.5546094179153442} 08/31/2021 16:03:53 - INFO - __main__ - Step 148141: {'lr': 1.9482998582195932e-07, 'samples': 28443072, 'steps': 148140, 'loss/train': 1.1580461263656616} 08/31/2021 16:03:53 - INFO - __main__ - Step 148142: {'lr': 1.9462057470753803e-07, 'samples': 28443264, 'steps': 148141, 'loss/train': 1.6717252731323242} 08/31/2021 16:03:54 - INFO - __main__ - Step 148143: {'lr': 1.944112761515515e-07, 'samples': 28443456, 'steps': 148142, 'loss/train': 1.4609911441802979} 08/31/2021 16:03:54 - INFO - __main__ - Step 148144: {'lr': 1.942020901541386e-07, 'samples': 28443648, 'steps': 148143, 'loss/train': 0.36098429560661316} 08/31/2021 16:03:54 - INFO - __main__ - Step 148145: {'lr': 1.9399301671535475e-07, 'samples': 28443840, 'steps': 148144, 'loss/train': 1.2021164894104004} 08/31/2021 16:03:56 - INFO - __main__ - Step 148146: {'lr': 1.9378405583528325e-07, 'samples': 28444032, 'steps': 148145, 'loss/train': 1.3977229595184326} 08/31/2021 16:03:57 - INFO - __main__ - Step 148147: {'lr': 1.935752075140629e-07, 'samples': 28444224, 'steps': 148146, 'loss/train': 0.8641881942749023} 08/31/2021 16:03:57 - INFO - __main__ - Step 148148: {'lr': 1.9336647175174915e-07, 'samples': 28444416, 'steps': 148147, 'loss/train': 1.4243932962417603} 08/31/2021 16:03:57 - INFO - __main__ - Step 148149: {'lr': 1.9315784854845308e-07, 'samples': 28444608, 'steps': 148148, 'loss/train': 1.218568205833435} 08/31/2021 16:03:58 - INFO - __main__ - Step 148150: {'lr': 1.9294933790425796e-07, 'samples': 28444800, 'steps': 148149, 'loss/train': 0.3552066683769226} 08/31/2021 16:03:58 - INFO - __main__ - Step 148151: {'lr': 1.9274093981927476e-07, 'samples': 28444992, 'steps': 148150, 'loss/train': 1.7472755908966064} 08/31/2021 16:04:00 - INFO - __main__ - Step 148152: {'lr': 1.925326542935868e-07, 'samples': 28445184, 'steps': 148151, 'loss/train': 0.7054399847984314} 08/31/2021 16:04:00 - INFO - __main__ - Step 148153: {'lr': 1.9232448132727732e-07, 'samples': 28445376, 'steps': 148152, 'loss/train': 1.0156073570251465} 08/31/2021 16:04:00 - INFO - __main__ - Step 148154: {'lr': 1.9211642092045732e-07, 'samples': 28445568, 'steps': 148153, 'loss/train': 2.0530619621276855} 08/31/2021 16:04:01 - INFO - __main__ - Step 148155: {'lr': 1.9190847307321014e-07, 'samples': 28445760, 'steps': 148154, 'loss/train': 1.108052372932434} 08/31/2021 16:04:01 - INFO - __main__ - Step 148156: {'lr': 1.9170063778564673e-07, 'samples': 28445952, 'steps': 148155, 'loss/train': 1.4381773471832275} 08/31/2021 16:04:03 - INFO - __main__ - Step 148157: {'lr': 1.9149291505785038e-07, 'samples': 28446144, 'steps': 148156, 'loss/train': 1.4866529703140259} 08/31/2021 16:04:03 - INFO - __main__ - Step 148158: {'lr': 1.9128530488990435e-07, 'samples': 28446336, 'steps': 148157, 'loss/train': 0.9214202761650085} 08/31/2021 16:04:03 - INFO - __main__ - Step 148159: {'lr': 1.910778072819197e-07, 'samples': 28446528, 'steps': 148158, 'loss/train': 1.4047572612762451} 08/31/2021 16:04:04 - INFO - __main__ - Step 148160: {'lr': 1.908704222339519e-07, 'samples': 28446720, 'steps': 148159, 'loss/train': 1.2856303453445435} 08/31/2021 16:04:04 - INFO - __main__ - Step 148161: {'lr': 1.9066314974613973e-07, 'samples': 28446912, 'steps': 148160, 'loss/train': 1.3590654134750366} 08/31/2021 16:04:05 - INFO - __main__ - Step 148162: {'lr': 1.9045598981856648e-07, 'samples': 28447104, 'steps': 148161, 'loss/train': 1.3809764385223389} 08/31/2021 16:04:06 - INFO - __main__ - Step 148163: {'lr': 1.902489424513154e-07, 'samples': 28447296, 'steps': 148162, 'loss/train': 1.0089937448501587} 08/31/2021 16:04:06 - INFO - __main__ - Step 148164: {'lr': 1.9004200764449752e-07, 'samples': 28447488, 'steps': 148163, 'loss/train': 1.1183568239212036} 08/31/2021 16:04:07 - INFO - __main__ - Step 148165: {'lr': 1.8983518539816837e-07, 'samples': 28447680, 'steps': 148164, 'loss/train': 1.4738510847091675} 08/31/2021 16:04:07 - INFO - __main__ - Step 148166: {'lr': 1.8962847571246666e-07, 'samples': 28447872, 'steps': 148165, 'loss/train': 0.7104083299636841} 08/31/2021 16:04:09 - INFO - __main__ - Step 148167: {'lr': 1.8942187858744797e-07, 'samples': 28448064, 'steps': 148166, 'loss/train': 1.5293467044830322} 08/31/2021 16:04:09 - INFO - __main__ - Step 148168: {'lr': 1.892153940232233e-07, 'samples': 28448256, 'steps': 148167, 'loss/train': 1.1328736543655396} 08/31/2021 16:04:09 - INFO - __main__ - Step 148169: {'lr': 1.8900902201987591e-07, 'samples': 28448448, 'steps': 148168, 'loss/train': 1.3687798976898193} 08/31/2021 16:04:10 - INFO - __main__ - Step 148170: {'lr': 1.8880276257751684e-07, 'samples': 28448640, 'steps': 148169, 'loss/train': 1.243061900138855} 08/31/2021 16:04:10 - INFO - __main__ - Step 148171: {'lr': 1.8859661569622933e-07, 'samples': 28448832, 'steps': 148170, 'loss/train': 0.8270714282989502} 08/31/2021 16:04:11 - INFO - __main__ - Step 148172: {'lr': 1.8839058137612442e-07, 'samples': 28449024, 'steps': 148171, 'loss/train': 1.0211973190307617} 08/31/2021 16:04:12 - INFO - __main__ - Step 148173: {'lr': 1.8818465961722986e-07, 'samples': 28449216, 'steps': 148172, 'loss/train': 0.45967400074005127} 08/31/2021 16:04:12 - INFO - __main__ - Step 148174: {'lr': 1.879788504197122e-07, 'samples': 28449408, 'steps': 148173, 'loss/train': 1.129148006439209} 08/31/2021 16:04:13 - INFO - __main__ - Step 148175: {'lr': 1.8777315378362692e-07, 'samples': 28449600, 'steps': 148174, 'loss/train': 0.9961041212081909} 08/31/2021 16:04:13 - INFO - __main__ - Step 148176: {'lr': 1.8756756970908506e-07, 'samples': 28449792, 'steps': 148175, 'loss/train': 0.3104016184806824} 08/31/2021 16:04:13 - INFO - __main__ - Step 148177: {'lr': 1.8736209819616988e-07, 'samples': 28449984, 'steps': 148176, 'loss/train': 0.7274346351623535} 08/31/2021 16:04:15 - INFO - __main__ - Step 148178: {'lr': 1.8715673924499244e-07, 'samples': 28450176, 'steps': 148177, 'loss/train': 0.3851378858089447} 08/31/2021 16:04:15 - INFO - __main__ - Step 148179: {'lr': 1.869514928556082e-07, 'samples': 28450368, 'steps': 148178, 'loss/train': 1.0330439805984497} 08/31/2021 16:04:16 - INFO - __main__ - Step 148180: {'lr': 1.867463590281282e-07, 'samples': 28450560, 'steps': 148179, 'loss/train': 1.1937328577041626} 08/31/2021 16:04:16 - INFO - __main__ - Step 148181: {'lr': 1.865413377626357e-07, 'samples': 28450752, 'steps': 148180, 'loss/train': 1.272676944732666} 08/31/2021 16:04:16 - INFO - __main__ - Step 148182: {'lr': 1.8633642905924175e-07, 'samples': 28450944, 'steps': 148181, 'loss/train': 1.0622740983963013} 08/31/2021 16:04:19 - INFO - __main__ - Step 148183: {'lr': 1.8613163291802959e-07, 'samples': 28451136, 'steps': 148182, 'loss/train': 0.910628616809845} 08/31/2021 16:04:19 - INFO - __main__ - Step 148184: {'lr': 1.859269493390825e-07, 'samples': 28451328, 'steps': 148183, 'loss/train': 0.8855237364768982} 08/31/2021 16:04:20 - INFO - __main__ - Step 148185: {'lr': 1.857223783225115e-07, 'samples': 28451520, 'steps': 148184, 'loss/train': 0.8628913164138794} 08/31/2021 16:04:20 - INFO - __main__ - Step 148186: {'lr': 1.8551791986839983e-07, 'samples': 28451712, 'steps': 148185, 'loss/train': 1.0226702690124512} 08/31/2021 16:04:20 - INFO - __main__ - Step 148187: {'lr': 1.8531357397685856e-07, 'samples': 28451904, 'steps': 148186, 'loss/train': 0.6446859240531921} 08/31/2021 16:04:22 - INFO - __main__ - Step 148188: {'lr': 1.8510934064791542e-07, 'samples': 28452096, 'steps': 148187, 'loss/train': 0.9732741117477417} 08/31/2021 16:04:22 - INFO - __main__ - Step 148189: {'lr': 1.8490521988173692e-07, 'samples': 28452288, 'steps': 148188, 'loss/train': 1.283025860786438} 08/31/2021 16:04:22 - INFO - __main__ - Step 148190: {'lr': 1.847012116783786e-07, 'samples': 28452480, 'steps': 148189, 'loss/train': 1.7684887647628784} 08/31/2021 16:04:23 - INFO - __main__ - Step 148191: {'lr': 1.844973160379515e-07, 'samples': 28452672, 'steps': 148190, 'loss/train': 0.81388258934021} 08/31/2021 16:04:23 - INFO - __main__ - Step 148192: {'lr': 1.842935329605111e-07, 'samples': 28452864, 'steps': 148191, 'loss/train': 1.2564609050750732} 08/31/2021 16:04:25 - INFO - __main__ - Step 148193: {'lr': 1.8408986244619618e-07, 'samples': 28453056, 'steps': 148192, 'loss/train': 1.6718378067016602} 08/31/2021 16:04:25 - INFO - __main__ - Step 148194: {'lr': 1.8388630449506228e-07, 'samples': 28453248, 'steps': 148193, 'loss/train': 1.4191017150878906} 08/31/2021 16:04:26 - INFO - __main__ - Step 148195: {'lr': 1.8368285910722038e-07, 'samples': 28453440, 'steps': 148194, 'loss/train': 1.228891134262085} 08/31/2021 16:04:26 - INFO - __main__ - Step 148196: {'lr': 1.8347952628275376e-07, 'samples': 28453632, 'steps': 148195, 'loss/train': 1.183909296989441} 08/31/2021 16:04:26 - INFO - __main__ - Step 148197: {'lr': 1.8327630602174572e-07, 'samples': 28453824, 'steps': 148196, 'loss/train': 1.072027325630188} 08/31/2021 16:04:28 - INFO - __main__ - Step 148198: {'lr': 1.8307319832430725e-07, 'samples': 28454016, 'steps': 148197, 'loss/train': 1.6203707456588745} 08/31/2021 16:04:29 - INFO - __main__ - Step 148199: {'lr': 1.828702031905216e-07, 'samples': 28454208, 'steps': 148198, 'loss/train': 0.0509457141160965} 08/31/2021 16:04:29 - INFO - __main__ - Step 148200: {'lr': 1.8266732062049984e-07, 'samples': 28454400, 'steps': 148199, 'loss/train': 1.1211116313934326} 08/31/2021 16:04:29 - INFO - __main__ - Step 148201: {'lr': 1.8246455061429746e-07, 'samples': 28454592, 'steps': 148200, 'loss/train': 0.4036766290664673} 08/31/2021 16:04:30 - INFO - __main__ - Step 148202: {'lr': 1.822618931719977e-07, 'samples': 28454784, 'steps': 148201, 'loss/train': 0.46587780117988586} 08/31/2021 16:04:31 - INFO - __main__ - Step 148203: {'lr': 1.8205934829373937e-07, 'samples': 28454976, 'steps': 148202, 'loss/train': 1.0197172164916992} 08/31/2021 16:04:32 - INFO - __main__ - Step 148204: {'lr': 1.8185691597957798e-07, 'samples': 28455168, 'steps': 148203, 'loss/train': 1.120230793952942} 08/31/2021 16:04:32 - INFO - __main__ - Step 148205: {'lr': 1.8165459622962456e-07, 'samples': 28455360, 'steps': 148204, 'loss/train': 1.1776180267333984} 08/31/2021 16:04:32 - INFO - __main__ - Step 148206: {'lr': 1.8145238904399008e-07, 'samples': 28455552, 'steps': 148205, 'loss/train': 1.7194559574127197} 08/31/2021 16:04:33 - INFO - __main__ - Step 148207: {'lr': 1.8125029442270236e-07, 'samples': 28455744, 'steps': 148206, 'loss/train': 1.0695780515670776} 08/31/2021 16:04:33 - INFO - __main__ - Step 148208: {'lr': 1.8104831236590014e-07, 'samples': 28455936, 'steps': 148207, 'loss/train': 1.1475502252578735} 08/31/2021 16:04:34 - INFO - __main__ - Step 148209: {'lr': 1.808464428736667e-07, 'samples': 28456128, 'steps': 148208, 'loss/train': 1.146376132965088} 08/31/2021 16:04:35 - INFO - __main__ - Step 148210: {'lr': 1.806446859460853e-07, 'samples': 28456320, 'steps': 148209, 'loss/train': 1.3493413925170898} 08/31/2021 16:04:35 - INFO - __main__ - Step 148211: {'lr': 1.804430415832392e-07, 'samples': 28456512, 'steps': 148210, 'loss/train': 0.4685182273387909} 08/31/2021 16:04:36 - INFO - __main__ - Step 148212: {'lr': 1.8024150978523946e-07, 'samples': 28456704, 'steps': 148211, 'loss/train': 0.8654905557632446} 08/31/2021 16:04:36 - INFO - __main__ - Step 148213: {'lr': 1.800400905521693e-07, 'samples': 28456896, 'steps': 148212, 'loss/train': 1.7409294843673706} 08/31/2021 16:04:37 - INFO - __main__ - Step 148214: {'lr': 1.79838783884112e-07, 'samples': 28457088, 'steps': 148213, 'loss/train': 1.2520320415496826} 08/31/2021 16:04:38 - INFO - __main__ - Step 148215: {'lr': 1.796375897811786e-07, 'samples': 28457280, 'steps': 148214, 'loss/train': 0.8942515254020691} 08/31/2021 16:04:38 - INFO - __main__ - Step 148216: {'lr': 1.794365082434246e-07, 'samples': 28457472, 'steps': 148215, 'loss/train': 0.7555229663848877} 08/31/2021 16:04:39 - INFO - __main__ - Step 148217: {'lr': 1.7923553927096102e-07, 'samples': 28457664, 'steps': 148216, 'loss/train': 1.087287425994873} 08/31/2021 16:04:39 - INFO - __main__ - Step 148218: {'lr': 1.790346828638989e-07, 'samples': 28457856, 'steps': 148217, 'loss/train': 0.45834600925445557} 08/31/2021 16:04:41 - INFO - __main__ - Step 148219: {'lr': 1.788339390222937e-07, 'samples': 28458048, 'steps': 148218, 'loss/train': 0.12562035024166107} 08/31/2021 16:04:41 - INFO - __main__ - Step 148220: {'lr': 1.7863330774625652e-07, 'samples': 28458240, 'steps': 148219, 'loss/train': 0.36588501930236816} 08/31/2021 16:04:42 - INFO - __main__ - Step 148221: {'lr': 1.784327890358983e-07, 'samples': 28458432, 'steps': 148220, 'loss/train': 1.2727206945419312} 08/31/2021 16:04:42 - INFO - __main__ - Step 148222: {'lr': 1.782323828912469e-07, 'samples': 28458624, 'steps': 148221, 'loss/train': 0.9037144184112549} 08/31/2021 16:04:42 - INFO - __main__ - Step 148223: {'lr': 1.7803208931244096e-07, 'samples': 28458816, 'steps': 148222, 'loss/train': 0.8953102231025696} 08/31/2021 16:04:43 - INFO - __main__ - Step 148224: {'lr': 1.7783190829956385e-07, 'samples': 28459008, 'steps': 148223, 'loss/train': 1.1359784603118896} 08/31/2021 16:04:44 - INFO - __main__ - Step 148225: {'lr': 1.7763183985269881e-07, 'samples': 28459200, 'steps': 148224, 'loss/train': 0.03250480443239212} 08/31/2021 16:04:45 - INFO - __main__ - Step 148226: {'lr': 1.7743188397192912e-07, 'samples': 28459392, 'steps': 148225, 'loss/train': 1.90567946434021} 08/31/2021 16:04:45 - INFO - __main__ - Step 148227: {'lr': 1.7723204065736575e-07, 'samples': 28459584, 'steps': 148226, 'loss/train': 1.2210843563079834} 08/31/2021 16:04:45 - INFO - __main__ - Step 148228: {'lr': 1.7703230990906427e-07, 'samples': 28459776, 'steps': 148227, 'loss/train': 1.1138825416564941} 08/31/2021 16:04:46 - INFO - __main__ - Step 148229: {'lr': 1.7683269172716344e-07, 'samples': 28459968, 'steps': 148228, 'loss/train': 1.0868051052093506} 08/31/2021 16:04:47 - INFO - __main__ - Step 148230: {'lr': 1.7663318611171875e-07, 'samples': 28460160, 'steps': 148229, 'loss/train': 1.2625304460525513} 08/31/2021 16:04:48 - INFO - __main__ - Step 148231: {'lr': 1.764337930628135e-07, 'samples': 28460352, 'steps': 148230, 'loss/train': 0.519744336605072} 08/31/2021 16:04:48 - INFO - __main__ - Step 148232: {'lr': 1.7623451258055868e-07, 'samples': 28460544, 'steps': 148231, 'loss/train': 1.3892629146575928} 08/31/2021 16:04:49 - INFO - __main__ - Step 148233: {'lr': 1.7603534466503757e-07, 'samples': 28460736, 'steps': 148232, 'loss/train': 0.4860117435455322} 08/31/2021 16:04:49 - INFO - __main__ - Step 148234: {'lr': 1.758362893163612e-07, 'samples': 28460928, 'steps': 148233, 'loss/train': 0.9012115597724915} 08/31/2021 16:04:51 - INFO - __main__ - Step 148235: {'lr': 1.7563734653458508e-07, 'samples': 28461120, 'steps': 148234, 'loss/train': 1.4298616647720337} 08/31/2021 16:04:51 - INFO - __main__ - Step 148236: {'lr': 1.7543851631979245e-07, 'samples': 28461312, 'steps': 148235, 'loss/train': 0.478594034910202} 08/31/2021 16:04:52 - INFO - __main__ - Step 148237: {'lr': 1.7523979867212213e-07, 'samples': 28461504, 'steps': 148236, 'loss/train': 2.1389236450195312} 08/31/2021 16:04:52 - INFO - __main__ - Step 148238: {'lr': 1.7504119359160187e-07, 'samples': 28461696, 'steps': 148237, 'loss/train': 1.0369975566864014} 08/31/2021 16:04:53 - INFO - __main__ - Step 148239: {'lr': 1.7484270107837043e-07, 'samples': 28461888, 'steps': 148238, 'loss/train': 0.10161923617124557} 08/31/2021 16:04:54 - INFO - __main__ - Step 148240: {'lr': 1.7464432113251106e-07, 'samples': 28462080, 'steps': 148239, 'loss/train': 0.36802202463150024} 08/31/2021 16:04:55 - INFO - __main__ - Step 148241: {'lr': 1.744460537540793e-07, 'samples': 28462272, 'steps': 148240, 'loss/train': 0.6194533109664917} 08/31/2021 16:04:55 - INFO - __main__ - Step 148242: {'lr': 1.7424789894321392e-07, 'samples': 28462464, 'steps': 148241, 'loss/train': 1.2766739130020142} 08/31/2021 16:04:55 - INFO - __main__ - Step 148243: {'lr': 1.7404985669997043e-07, 'samples': 28462656, 'steps': 148242, 'loss/train': 1.0981934070587158} 08/31/2021 16:04:56 - INFO - __main__ - Step 148244: {'lr': 1.738519270244321e-07, 'samples': 28462848, 'steps': 148243, 'loss/train': 0.4937255382537842} 08/31/2021 16:04:56 - INFO - __main__ - Step 148245: {'lr': 1.7365410991670993e-07, 'samples': 28463040, 'steps': 148244, 'loss/train': 0.9076526165008545} 08/31/2021 16:04:58 - INFO - __main__ - Step 148246: {'lr': 1.7345640537685947e-07, 'samples': 28463232, 'steps': 148245, 'loss/train': 1.309383749961853} 08/31/2021 16:04:58 - INFO - __main__ - Step 148247: {'lr': 1.7325881340501948e-07, 'samples': 28463424, 'steps': 148246, 'loss/train': 1.3649193048477173} 08/31/2021 16:04:58 - INFO - __main__ - Step 148248: {'lr': 1.7306133400124547e-07, 'samples': 28463616, 'steps': 148247, 'loss/train': 0.2863960862159729} 08/31/2021 16:04:59 - INFO - __main__ - Step 148249: {'lr': 1.7286396716564845e-07, 'samples': 28463808, 'steps': 148248, 'loss/train': 1.2623376846313477} 08/31/2021 16:04:59 - INFO - __main__ - Step 148250: {'lr': 1.726667128983117e-07, 'samples': 28464000, 'steps': 148249, 'loss/train': 0.749363362789154} 08/31/2021 16:05:01 - INFO - __main__ - Step 148251: {'lr': 1.7246957119929075e-07, 'samples': 28464192, 'steps': 148250, 'loss/train': 0.9104845523834229} 08/31/2021 16:05:01 - INFO - __main__ - Step 148252: {'lr': 1.7227254206869657e-07, 'samples': 28464384, 'steps': 148251, 'loss/train': 1.112990140914917} 08/31/2021 16:05:01 - INFO - __main__ - Step 148253: {'lr': 1.7207562550664024e-07, 'samples': 28464576, 'steps': 148252, 'loss/train': 1.239583134651184} 08/31/2021 16:05:02 - INFO - __main__ - Step 148254: {'lr': 1.7187882151317725e-07, 'samples': 28464768, 'steps': 148253, 'loss/train': 1.689947485923767} 08/31/2021 16:05:02 - INFO - __main__ - Step 148255: {'lr': 1.716821300884186e-07, 'samples': 28464960, 'steps': 148254, 'loss/train': 0.5506095290184021} 08/31/2021 16:05:04 - INFO - __main__ - Step 148256: {'lr': 1.714855512324476e-07, 'samples': 28465152, 'steps': 148255, 'loss/train': 0.8432743549346924} 08/31/2021 16:05:04 - INFO - __main__ - Step 148257: {'lr': 1.7128908494534746e-07, 'samples': 28465344, 'steps': 148256, 'loss/train': 0.6467599272727966} 08/31/2021 16:05:04 - INFO - __main__ - Step 148258: {'lr': 1.7109273122720149e-07, 'samples': 28465536, 'steps': 148257, 'loss/train': 1.455475926399231} 08/31/2021 16:05:05 - INFO - __main__ - Step 148259: {'lr': 1.7089649007812069e-07, 'samples': 28465728, 'steps': 148258, 'loss/train': 0.5341975092887878} 08/31/2021 16:05:05 - INFO - __main__ - Step 148260: {'lr': 1.707003614981606e-07, 'samples': 28465920, 'steps': 148259, 'loss/train': 1.0361288785934448} 08/31/2021 16:05:07 - INFO - __main__ - Step 148261: {'lr': 1.7050434548745995e-07, 'samples': 28466112, 'steps': 148260, 'loss/train': 0.9303403496742249} 08/31/2021 16:05:07 - INFO - __main__ - Step 148262: {'lr': 1.7030844204604657e-07, 'samples': 28466304, 'steps': 148261, 'loss/train': 1.2562514543533325} 08/31/2021 16:05:08 - INFO - __main__ - Step 148263: {'lr': 1.701126511740314e-07, 'samples': 28466496, 'steps': 148262, 'loss/train': 0.7595005035400391} 08/31/2021 16:05:08 - INFO - __main__ - Step 148264: {'lr': 1.6991697287152552e-07, 'samples': 28466688, 'steps': 148263, 'loss/train': 1.2298933267593384} 08/31/2021 16:05:08 - INFO - __main__ - Step 148265: {'lr': 1.6972140713861216e-07, 'samples': 28466880, 'steps': 148264, 'loss/train': 0.5388721227645874} 08/31/2021 16:05:10 - INFO - __main__ - Step 148266: {'lr': 1.6952595397534687e-07, 'samples': 28467072, 'steps': 148265, 'loss/train': 0.21429508924484253} 08/31/2021 16:05:10 - INFO - __main__ - Step 148267: {'lr': 1.6933061338184065e-07, 'samples': 28467264, 'steps': 148266, 'loss/train': 0.6917371153831482} 08/31/2021 16:05:11 - INFO - __main__ - Step 148268: {'lr': 1.6913538535817673e-07, 'samples': 28467456, 'steps': 148267, 'loss/train': 0.7991604208946228} 08/31/2021 16:05:11 - INFO - __main__ - Step 148269: {'lr': 1.6894026990443846e-07, 'samples': 28467648, 'steps': 148268, 'loss/train': 1.7218765020370483} 08/31/2021 16:05:11 - INFO - __main__ - Step 148270: {'lr': 1.6874526702073678e-07, 'samples': 28467840, 'steps': 148269, 'loss/train': 1.435892105102539} 08/31/2021 16:05:13 - INFO - __main__ - Step 148271: {'lr': 1.6855037670712724e-07, 'samples': 28468032, 'steps': 148270, 'loss/train': 0.8819074630737305} 08/31/2021 16:05:14 - INFO - __main__ - Step 148272: {'lr': 1.6835559896374863e-07, 'samples': 28468224, 'steps': 148271, 'loss/train': 1.4538249969482422} 08/31/2021 16:05:14 - INFO - __main__ - Step 148273: {'lr': 1.681609337906287e-07, 'samples': 28468416, 'steps': 148272, 'loss/train': 0.9482267498970032} 08/31/2021 16:05:15 - INFO - __main__ - Step 148274: {'lr': 1.6796638118787843e-07, 'samples': 28468608, 'steps': 148273, 'loss/train': 1.3640437126159668} 08/31/2021 16:05:15 - INFO - __main__ - Step 148275: {'lr': 1.6777194115558113e-07, 'samples': 28468800, 'steps': 148274, 'loss/train': 1.3771090507507324} 08/31/2021 16:05:17 - INFO - __main__ - Step 148276: {'lr': 1.6757761369384783e-07, 'samples': 28468992, 'steps': 148275, 'loss/train': 0.8545650839805603} 08/31/2021 16:05:17 - INFO - __main__ - Step 148277: {'lr': 1.6738339880273402e-07, 'samples': 28469184, 'steps': 148276, 'loss/train': 0.2888132929801941} 08/31/2021 16:05:18 - INFO - __main__ - Step 148278: {'lr': 1.671892964823507e-07, 'samples': 28469376, 'steps': 148277, 'loss/train': 0.8429020047187805} 08/31/2021 16:05:18 - INFO - __main__ - Step 148279: {'lr': 1.669953067327812e-07, 'samples': 28469568, 'steps': 148278, 'loss/train': 0.07153959572315216} 08/31/2021 16:05:18 - INFO - __main__ - Step 148280: {'lr': 1.6680142955408094e-07, 'samples': 28469760, 'steps': 148279, 'loss/train': 1.342544674873352} 08/31/2021 16:05:20 - INFO - __main__ - Step 148281: {'lr': 1.666076649463888e-07, 'samples': 28469952, 'steps': 148280, 'loss/train': 1.2774146795272827} 08/31/2021 16:05:20 - INFO - __main__ - Step 148282: {'lr': 1.6641401290976022e-07, 'samples': 28470144, 'steps': 148281, 'loss/train': 0.859345555305481} 08/31/2021 16:05:20 - INFO - __main__ - Step 148283: {'lr': 1.6622047344430625e-07, 'samples': 28470336, 'steps': 148282, 'loss/train': 1.0948007106781006} 08/31/2021 16:05:21 - INFO - __main__ - Step 148284: {'lr': 1.6602704655008238e-07, 'samples': 28470528, 'steps': 148283, 'loss/train': 1.2042118310928345} 08/31/2021 16:05:21 - INFO - __main__ - Step 148285: {'lr': 1.6583373222719966e-07, 'samples': 28470720, 'steps': 148284, 'loss/train': 0.8473923802375793} 08/31/2021 16:05:23 - INFO - __main__ - Step 148286: {'lr': 1.6564053047574136e-07, 'samples': 28470912, 'steps': 148285, 'loss/train': 1.0400669574737549} 08/31/2021 16:05:23 - INFO - __main__ - Step 148287: {'lr': 1.6544744129576294e-07, 'samples': 28471104, 'steps': 148286, 'loss/train': 0.7434558272361755} 08/31/2021 16:05:24 - INFO - __main__ - Step 148288: {'lr': 1.6525446468740323e-07, 'samples': 28471296, 'steps': 148287, 'loss/train': 1.1227405071258545} 08/31/2021 16:05:24 - INFO - __main__ - Step 148289: {'lr': 1.6506160065071774e-07, 'samples': 28471488, 'steps': 148288, 'loss/train': 0.8712392449378967} 08/31/2021 16:05:25 - INFO - __main__ - Step 148290: {'lr': 1.6486884918581746e-07, 'samples': 28471680, 'steps': 148289, 'loss/train': 0.7579991817474365} 08/31/2021 16:05:25 - INFO - __main__ - Step 148291: {'lr': 1.646762102927579e-07, 'samples': 28471872, 'steps': 148290, 'loss/train': 1.2482554912567139} 08/31/2021 16:05:26 - INFO - __main__ - Step 148292: {'lr': 1.6448368397162238e-07, 'samples': 28472064, 'steps': 148291, 'loss/train': 1.3104450702667236} 08/31/2021 16:05:27 - INFO - __main__ - Step 148293: {'lr': 1.6429127022252188e-07, 'samples': 28472256, 'steps': 148292, 'loss/train': 1.236656665802002} 08/31/2021 16:05:27 - INFO - __main__ - Step 148294: {'lr': 1.6409896904556742e-07, 'samples': 28472448, 'steps': 148293, 'loss/train': 0.8136301636695862} 08/31/2021 16:05:27 - INFO - __main__ - Step 148295: {'lr': 1.6390678044078677e-07, 'samples': 28472640, 'steps': 148294, 'loss/train': 0.8404358625411987} 08/31/2021 16:05:28 - INFO - __main__ - Step 148296: {'lr': 1.6371470440829094e-07, 'samples': 28472832, 'steps': 148295, 'loss/train': 1.281876564025879} 08/31/2021 16:05:29 - INFO - __main__ - Step 148297: {'lr': 1.6352274094819098e-07, 'samples': 28473024, 'steps': 148296, 'loss/train': 0.8090136051177979} 08/31/2021 16:05:30 - INFO - __main__ - Step 148298: {'lr': 1.6333089006054236e-07, 'samples': 28473216, 'steps': 148297, 'loss/train': 0.8899070024490356} 08/31/2021 16:05:30 - INFO - __main__ - Step 148299: {'lr': 1.6313915174542836e-07, 'samples': 28473408, 'steps': 148298, 'loss/train': 1.3006649017333984} 08/31/2021 16:05:31 - INFO - __main__ - Step 148300: {'lr': 1.6294752600296002e-07, 'samples': 28473600, 'steps': 148299, 'loss/train': 1.0176937580108643} 08/31/2021 16:05:31 - INFO - __main__ - Step 148301: {'lr': 1.6275601283322061e-07, 'samples': 28473792, 'steps': 148300, 'loss/train': 1.4011850357055664} 08/31/2021 16:05:33 - INFO - __main__ - Step 148302: {'lr': 1.6256461223629336e-07, 'samples': 28473984, 'steps': 148301, 'loss/train': 0.7537987232208252} 08/31/2021 16:05:34 - INFO - __main__ - Step 148303: {'lr': 1.6237332421223382e-07, 'samples': 28474176, 'steps': 148302, 'loss/train': 0.526400089263916} 08/31/2021 16:05:34 - INFO - __main__ - Step 148304: {'lr': 1.6218214876118076e-07, 'samples': 28474368, 'steps': 148303, 'loss/train': 1.1542946100234985} 08/31/2021 16:05:34 - INFO - __main__ - Step 148305: {'lr': 1.6199108588316192e-07, 'samples': 28474560, 'steps': 148304, 'loss/train': 0.35603147745132446} 08/31/2021 16:05:35 - INFO - __main__ - Step 148306: {'lr': 1.6180013557831608e-07, 'samples': 28474752, 'steps': 148305, 'loss/train': 1.2565970420837402} 08/31/2021 16:05:35 - INFO - __main__ - Step 148307: {'lr': 1.6160929784669876e-07, 'samples': 28474944, 'steps': 148306, 'loss/train': 1.4897456169128418} 08/31/2021 16:05:35 - INFO - __main__ - Step 148308: {'lr': 1.6141857268842098e-07, 'samples': 28475136, 'steps': 148307, 'loss/train': 0.6298836469650269} 08/31/2021 16:05:37 - INFO - __main__ - Step 148309: {'lr': 1.6122796010353824e-07, 'samples': 28475328, 'steps': 148308, 'loss/train': 0.015389214269816875} 08/31/2021 16:05:37 - INFO - __main__ - Step 148310: {'lr': 1.6103746009216157e-07, 'samples': 28475520, 'steps': 148309, 'loss/train': 1.2721771001815796} 08/31/2021 16:05:38 - INFO - __main__ - Step 148311: {'lr': 1.608470726543465e-07, 'samples': 28475712, 'steps': 148310, 'loss/train': 1.142017126083374} 08/31/2021 16:05:38 - INFO - __main__ - Step 148312: {'lr': 1.606567977902318e-07, 'samples': 28475904, 'steps': 148311, 'loss/train': 1.5588104724884033} 08/31/2021 16:05:38 - INFO - __main__ - Step 148313: {'lr': 1.6046663549984518e-07, 'samples': 28476096, 'steps': 148312, 'loss/train': 0.6581487655639648} 08/31/2021 16:05:40 - INFO - __main__ - Step 148314: {'lr': 1.6027658578329774e-07, 'samples': 28476288, 'steps': 148313, 'loss/train': 1.064094066619873} 08/31/2021 16:05:40 - INFO - __main__ - Step 148315: {'lr': 1.6008664864067268e-07, 'samples': 28476480, 'steps': 148314, 'loss/train': 1.1522940397262573} 08/31/2021 16:05:41 - INFO - __main__ - Step 148316: {'lr': 1.598968240720533e-07, 'samples': 28476672, 'steps': 148315, 'loss/train': 0.34716978669166565} 08/31/2021 16:05:41 - INFO - __main__ - Step 148317: {'lr': 1.5970711207755063e-07, 'samples': 28476864, 'steps': 148316, 'loss/train': 1.3450535535812378} 08/31/2021 16:05:41 - INFO - __main__ - Step 148318: {'lr': 1.5951751265722013e-07, 'samples': 28477056, 'steps': 148317, 'loss/train': 0.592596173286438} 08/31/2021 16:05:43 - INFO - __main__ - Step 148319: {'lr': 1.5932802581114513e-07, 'samples': 28477248, 'steps': 148318, 'loss/train': 1.138163447380066} 08/31/2021 16:05:44 - INFO - __main__ - Step 148320: {'lr': 1.5913865153943662e-07, 'samples': 28477440, 'steps': 148319, 'loss/train': 0.0830782875418663} 08/31/2021 16:05:44 - INFO - __main__ - Step 148321: {'lr': 1.5894938984215013e-07, 'samples': 28477632, 'steps': 148320, 'loss/train': 0.07202664762735367} 08/31/2021 16:05:44 - INFO - __main__ - Step 148322: {'lr': 1.5876024071939665e-07, 'samples': 28477824, 'steps': 148321, 'loss/train': 1.0985387563705444} 08/31/2021 16:05:45 - INFO - __main__ - Step 148323: {'lr': 1.5857120417123173e-07, 'samples': 28478016, 'steps': 148322, 'loss/train': 0.844100832939148} 08/31/2021 16:05:47 - INFO - __main__ - Step 148324: {'lr': 1.583822801977941e-07, 'samples': 28478208, 'steps': 148323, 'loss/train': 2.6446495056152344} 08/31/2021 16:05:48 - INFO - __main__ - Step 148325: {'lr': 1.5819346879911155e-07, 'samples': 28478400, 'steps': 148324, 'loss/train': 0.7108029723167419} 08/31/2021 16:05:48 - INFO - __main__ - Step 148326: {'lr': 1.5800476997529512e-07, 'samples': 28478592, 'steps': 148325, 'loss/train': 0.858670711517334} 08/31/2021 16:05:48 - INFO - __main__ - Step 148327: {'lr': 1.5781618372642802e-07, 'samples': 28478784, 'steps': 148326, 'loss/train': 1.0856943130493164} 08/31/2021 16:05:49 - INFO - __main__ - Step 148328: {'lr': 1.5762771005259357e-07, 'samples': 28478976, 'steps': 148327, 'loss/train': 0.3073780834674835} 08/31/2021 16:05:50 - INFO - __main__ - Step 148329: {'lr': 1.57439348953875e-07, 'samples': 28479168, 'steps': 148328, 'loss/train': 0.9405158162117004} 08/31/2021 16:05:51 - INFO - __main__ - Step 148330: {'lr': 1.5725110043035563e-07, 'samples': 28479360, 'steps': 148329, 'loss/train': 0.7387101054191589} 08/31/2021 16:05:51 - INFO - __main__ - Step 148331: {'lr': 1.5706296448211864e-07, 'samples': 28479552, 'steps': 148330, 'loss/train': 0.9807290434837341} 08/31/2021 16:05:51 - INFO - __main__ - Step 148332: {'lr': 1.5687494110924738e-07, 'samples': 28479744, 'steps': 148331, 'loss/train': 1.039868712425232} 08/31/2021 16:05:52 - INFO - __main__ - Step 148333: {'lr': 1.5668703031185282e-07, 'samples': 28479936, 'steps': 148332, 'loss/train': 1.4686535596847534} 08/31/2021 16:05:54 - INFO - __main__ - Step 148334: {'lr': 1.564992320899905e-07, 'samples': 28480128, 'steps': 148333, 'loss/train': 0.1055508479475975} 08/31/2021 16:05:54 - INFO - __main__ - Step 148335: {'lr': 1.5631154644377144e-07, 'samples': 28480320, 'steps': 148334, 'loss/train': 0.4432590901851654} 08/31/2021 16:05:54 - INFO - __main__ - Step 148336: {'lr': 1.5612397337325114e-07, 'samples': 28480512, 'steps': 148335, 'loss/train': 1.177581548690796} 08/31/2021 16:05:55 - INFO - __main__ - Step 148337: {'lr': 1.5593651287851285e-07, 'samples': 28480704, 'steps': 148336, 'loss/train': 0.4032740592956543} 08/31/2021 16:05:55 - INFO - __main__ - Step 148338: {'lr': 1.5574916495966762e-07, 'samples': 28480896, 'steps': 148337, 'loss/train': 1.3147945404052734} 08/31/2021 16:05:55 - INFO - __main__ - Step 148339: {'lr': 1.555619296167987e-07, 'samples': 28481088, 'steps': 148338, 'loss/train': 0.8930029273033142} 08/31/2021 16:05:57 - INFO - __main__ - Step 148340: {'lr': 1.5537480684996163e-07, 'samples': 28481280, 'steps': 148339, 'loss/train': 1.229488730430603} 08/31/2021 16:05:58 - INFO - __main__ - Step 148341: {'lr': 1.5518779665923966e-07, 'samples': 28481472, 'steps': 148340, 'loss/train': 2.013883352279663} 08/31/2021 16:05:58 - INFO - __main__ - Step 148342: {'lr': 1.5500089904477154e-07, 'samples': 28481664, 'steps': 148341, 'loss/train': 1.0533792972564697} 08/31/2021 16:05:58 - INFO - __main__ - Step 148343: {'lr': 1.5481411400658506e-07, 'samples': 28481856, 'steps': 148342, 'loss/train': 0.09366954118013382} 08/31/2021 16:05:59 - INFO - __main__ - Step 148344: {'lr': 1.5462744154479125e-07, 'samples': 28482048, 'steps': 148343, 'loss/train': 1.1188440322875977} 08/31/2021 16:06:00 - INFO - __main__ - Step 148345: {'lr': 1.5444088165944558e-07, 'samples': 28482240, 'steps': 148344, 'loss/train': 0.08650995790958405} 08/31/2021 16:06:01 - INFO - __main__ - Step 148346: {'lr': 1.5425443435068687e-07, 'samples': 28482432, 'steps': 148345, 'loss/train': 1.5504608154296875} 08/31/2021 16:06:01 - INFO - __main__ - Step 148347: {'lr': 1.5406809961854283e-07, 'samples': 28482624, 'steps': 148346, 'loss/train': 0.3543296754360199} 08/31/2021 16:06:01 - INFO - __main__ - Step 148348: {'lr': 1.5388187746312453e-07, 'samples': 28482816, 'steps': 148347, 'loss/train': 0.7976148128509521} 08/31/2021 16:06:02 - INFO - __main__ - Step 148349: {'lr': 1.5369576788451522e-07, 'samples': 28483008, 'steps': 148348, 'loss/train': 1.1672121286392212} 08/31/2021 16:06:03 - INFO - __main__ - Step 148350: {'lr': 1.5350977088279816e-07, 'samples': 28483200, 'steps': 148349, 'loss/train': 0.6040314435958862} 08/31/2021 16:06:03 - INFO - __main__ - Step 148351: {'lr': 1.533238864580566e-07, 'samples': 28483392, 'steps': 148350, 'loss/train': 0.8831782937049866} 08/31/2021 16:06:04 - INFO - __main__ - Step 148352: {'lr': 1.531381146103461e-07, 'samples': 28483584, 'steps': 148351, 'loss/train': 1.3853740692138672} 08/31/2021 16:06:04 - INFO - __main__ - Step 148353: {'lr': 1.529524553398054e-07, 'samples': 28483776, 'steps': 148352, 'loss/train': 0.3747800290584564} 08/31/2021 16:06:05 - INFO - __main__ - Step 148354: {'lr': 1.5276690864649e-07, 'samples': 28483968, 'steps': 148353, 'loss/train': 1.1407756805419922} 08/31/2021 16:06:06 - INFO - __main__ - Step 148355: {'lr': 1.5258147453045545e-07, 'samples': 28484160, 'steps': 148354, 'loss/train': 1.3156830072402954} 08/31/2021 16:06:07 - INFO - __main__ - Step 148356: {'lr': 1.5239615299184051e-07, 'samples': 28484352, 'steps': 148355, 'loss/train': 1.1086957454681396} 08/31/2021 16:06:07 - INFO - __main__ - Step 148357: {'lr': 1.5221094403067294e-07, 'samples': 28484544, 'steps': 148356, 'loss/train': 0.9562599062919617} 08/31/2021 16:06:07 - INFO - __main__ - Step 148358: {'lr': 1.520258476470915e-07, 'samples': 28484736, 'steps': 148357, 'loss/train': 1.281926155090332} 08/31/2021 16:06:08 - INFO - __main__ - Step 148359: {'lr': 1.5184086384112394e-07, 'samples': 28484928, 'steps': 148358, 'loss/train': 1.2929792404174805} 08/31/2021 16:06:09 - INFO - __main__ - Step 148360: {'lr': 1.5165599261290909e-07, 'samples': 28485120, 'steps': 148359, 'loss/train': 0.8597173094749451} 08/31/2021 16:06:10 - INFO - __main__ - Step 148361: {'lr': 1.514712339625024e-07, 'samples': 28485312, 'steps': 148360, 'loss/train': 0.46329519152641296} 08/31/2021 16:06:10 - INFO - __main__ - Step 148362: {'lr': 1.5128658788995942e-07, 'samples': 28485504, 'steps': 148361, 'loss/train': 1.45842444896698} 08/31/2021 16:06:10 - INFO - __main__ - Step 148363: {'lr': 1.5110205439541892e-07, 'samples': 28485696, 'steps': 148362, 'loss/train': 0.7619034647941589} 08/31/2021 16:06:11 - INFO - __main__ - Step 148364: {'lr': 1.5091763347890864e-07, 'samples': 28485888, 'steps': 148363, 'loss/train': 0.09561243653297424} 08/31/2021 16:06:11 - INFO - __main__ - Step 148365: {'lr': 1.5073332514056736e-07, 'samples': 28486080, 'steps': 148364, 'loss/train': 1.0003719329833984} 08/31/2021 16:06:13 - INFO - __main__ - Step 148366: {'lr': 1.5054912938042288e-07, 'samples': 28486272, 'steps': 148365, 'loss/train': 0.8201858401298523} 08/31/2021 16:06:13 - INFO - __main__ - Step 148367: {'lr': 1.5036504619861392e-07, 'samples': 28486464, 'steps': 148366, 'loss/train': 0.9824175238609314} 08/31/2021 16:06:14 - INFO - __main__ - Step 148368: {'lr': 1.5018107559519602e-07, 'samples': 28486656, 'steps': 148367, 'loss/train': 0.9368962049484253} 08/31/2021 16:06:14 - INFO - __main__ - Step 148369: {'lr': 1.4999721757022465e-07, 'samples': 28486848, 'steps': 148368, 'loss/train': 1.1066114902496338} 08/31/2021 16:06:14 - INFO - __main__ - Step 148370: {'lr': 1.4981347212383866e-07, 'samples': 28487040, 'steps': 148369, 'loss/train': 1.608988881111145} 08/31/2021 16:06:16 - INFO - __main__ - Step 148371: {'lr': 1.4962983925606576e-07, 'samples': 28487232, 'steps': 148370, 'loss/train': 0.9076668620109558} 08/31/2021 16:06:16 - INFO - __main__ - Step 148372: {'lr': 1.4944631896701698e-07, 'samples': 28487424, 'steps': 148371, 'loss/train': 0.027978206053376198} 08/31/2021 16:06:17 - INFO - __main__ - Step 148373: {'lr': 1.492629112567756e-07, 'samples': 28487616, 'steps': 148372, 'loss/train': 0.4222635328769684} 08/31/2021 16:06:17 - INFO - __main__ - Step 148374: {'lr': 1.4907961612542487e-07, 'samples': 28487808, 'steps': 148373, 'loss/train': 0.740625262260437} 08/31/2021 16:06:17 - INFO - __main__ - Step 148375: {'lr': 1.4889643357304804e-07, 'samples': 28488000, 'steps': 148374, 'loss/train': 0.9207873940467834} 08/31/2021 16:06:19 - INFO - __main__ - Step 148376: {'lr': 1.4871336359970066e-07, 'samples': 28488192, 'steps': 148375, 'loss/train': 1.2746514081954956} 08/31/2021 16:06:19 - INFO - __main__ - Step 148377: {'lr': 1.485304062055215e-07, 'samples': 28488384, 'steps': 148376, 'loss/train': 1.352339744567871} 08/31/2021 16:06:19 - INFO - __main__ - Step 148378: {'lr': 1.483475613905383e-07, 'samples': 28488576, 'steps': 148377, 'loss/train': 0.8195126056671143} 08/31/2021 16:06:20 - INFO - __main__ - Step 148379: {'lr': 1.4816482915486207e-07, 'samples': 28488768, 'steps': 148378, 'loss/train': 0.630466103553772} 08/31/2021 16:06:20 - INFO - __main__ - Step 148380: {'lr': 1.4798220949854834e-07, 'samples': 28488960, 'steps': 148379, 'loss/train': 0.6151229739189148} 08/31/2021 16:06:22 - INFO - __main__ - Step 148381: {'lr': 1.477997024217359e-07, 'samples': 28489152, 'steps': 148380, 'loss/train': 0.9718965291976929} 08/31/2021 16:06:23 - INFO - __main__ - Step 148382: {'lr': 1.4761730792442473e-07, 'samples': 28489344, 'steps': 148381, 'loss/train': 1.2240912914276123} 08/31/2021 16:06:23 - INFO - __main__ - Step 148383: {'lr': 1.4743502600678138e-07, 'samples': 28489536, 'steps': 148382, 'loss/train': 1.350069522857666} 08/31/2021 16:06:23 - INFO - __main__ - Step 148384: {'lr': 1.4725285666883358e-07, 'samples': 28489728, 'steps': 148383, 'loss/train': 1.6441370248794556} 08/31/2021 16:06:24 - INFO - __main__ - Step 148385: {'lr': 1.4707079991066462e-07, 'samples': 28489920, 'steps': 148384, 'loss/train': 0.9764074683189392} 08/31/2021 16:06:26 - INFO - __main__ - Step 148386: {'lr': 1.4688885573238552e-07, 'samples': 28490112, 'steps': 148385, 'loss/train': 0.8790075182914734} 08/31/2021 16:06:27 - INFO - __main__ - Step 148387: {'lr': 1.467070241340518e-07, 'samples': 28490304, 'steps': 148386, 'loss/train': 1.3651658296585083} 08/31/2021 16:06:27 - INFO - __main__ - Step 148388: {'lr': 1.4652530511577444e-07, 'samples': 28490496, 'steps': 148387, 'loss/train': 0.7864856719970703} 08/31/2021 16:06:27 - INFO - __main__ - Step 148389: {'lr': 1.4634369867760899e-07, 'samples': 28490688, 'steps': 148388, 'loss/train': 1.2189058065414429} 08/31/2021 16:06:28 - INFO - __main__ - Step 148390: {'lr': 1.4616220481963872e-07, 'samples': 28490880, 'steps': 148389, 'loss/train': 1.6148202419281006} 08/31/2021 16:06:28 - INFO - __main__ - Step 148391: {'lr': 1.4598082354194686e-07, 'samples': 28491072, 'steps': 148390, 'loss/train': 1.5881094932556152} 08/31/2021 16:06:29 - INFO - __main__ - Step 148392: {'lr': 1.457995548446167e-07, 'samples': 28491264, 'steps': 148391, 'loss/train': 1.7423914670944214} 08/31/2021 16:06:30 - INFO - __main__ - Step 148393: {'lr': 1.456183987277593e-07, 'samples': 28491456, 'steps': 148392, 'loss/train': 1.228468418121338} 08/31/2021 16:06:31 - INFO - __main__ - Step 148394: {'lr': 1.4543735519140234e-07, 'samples': 28491648, 'steps': 148393, 'loss/train': 1.3543648719787598} 08/31/2021 16:06:31 - INFO - __main__ - Step 148395: {'lr': 1.4525642423568463e-07, 'samples': 28491840, 'steps': 148394, 'loss/train': 1.1766091585159302} 08/31/2021 16:06:32 - INFO - __main__ - Step 148396: {'lr': 1.450756058606617e-07, 'samples': 28492032, 'steps': 148395, 'loss/train': 1.0299705266952515} 08/31/2021 16:06:32 - INFO - __main__ - Step 148397: {'lr': 1.4489490006638905e-07, 'samples': 28492224, 'steps': 148396, 'loss/train': 0.053977012634277344} 08/31/2021 16:06:32 - INFO - __main__ - Step 148398: {'lr': 1.447143068529777e-07, 'samples': 28492416, 'steps': 148397, 'loss/train': 0.6561489701271057} 08/31/2021 16:06:34 - INFO - __main__ - Step 148399: {'lr': 1.4453382622048317e-07, 'samples': 28492608, 'steps': 148398, 'loss/train': 0.19202865660190582} 08/31/2021 16:06:34 - INFO - __main__ - Step 148400: {'lr': 1.443534581690442e-07, 'samples': 28492800, 'steps': 148399, 'loss/train': 0.6984990835189819} 08/31/2021 16:06:35 - INFO - __main__ - Step 148401: {'lr': 1.4417320269868862e-07, 'samples': 28492992, 'steps': 148400, 'loss/train': 1.2765724658966064} 08/31/2021 16:06:35 - INFO - __main__ - Step 148402: {'lr': 1.439930598094996e-07, 'samples': 28493184, 'steps': 148401, 'loss/train': 1.3795980215072632} 08/31/2021 16:06:35 - INFO - __main__ - Step 148403: {'lr': 1.4381302950158826e-07, 'samples': 28493376, 'steps': 148402, 'loss/train': 0.8358112573623657} 08/31/2021 16:06:37 - INFO - __main__ - Step 148404: {'lr': 1.4363311177501003e-07, 'samples': 28493568, 'steps': 148403, 'loss/train': 0.7234143018722534} 08/31/2021 16:06:37 - INFO - __main__ - Step 148405: {'lr': 1.4345330662984823e-07, 'samples': 28493760, 'steps': 148404, 'loss/train': 0.7223897576332092} 08/31/2021 16:06:37 - INFO - __main__ - Step 148406: {'lr': 1.4327361406621385e-07, 'samples': 28493952, 'steps': 148405, 'loss/train': 1.2586524486541748} 08/31/2021 16:06:38 - INFO - __main__ - Step 148407: {'lr': 1.4309403408416243e-07, 'samples': 28494144, 'steps': 148406, 'loss/train': 1.4603601694107056} 08/31/2021 16:06:38 - INFO - __main__ - Step 148408: {'lr': 1.4291456668374947e-07, 'samples': 28494336, 'steps': 148407, 'loss/train': 1.4760408401489258} 08/31/2021 16:06:40 - INFO - __main__ - Step 148409: {'lr': 1.4273521186511372e-07, 'samples': 28494528, 'steps': 148408, 'loss/train': 1.5501362085342407} 08/31/2021 16:06:40 - INFO - __main__ - Step 148410: {'lr': 1.42555969628283e-07, 'samples': 28494720, 'steps': 148409, 'loss/train': 0.9654907584190369} 08/31/2021 16:06:41 - INFO - __main__ - Step 148411: {'lr': 1.4237683997336826e-07, 'samples': 28494912, 'steps': 148410, 'loss/train': 0.2751343250274658} 08/31/2021 16:06:41 - INFO - __main__ - Step 148412: {'lr': 1.421978229004528e-07, 'samples': 28495104, 'steps': 148411, 'loss/train': 1.8455406427383423} 08/31/2021 16:06:41 - INFO - __main__ - Step 148413: {'lr': 1.4201891840961988e-07, 'samples': 28495296, 'steps': 148412, 'loss/train': 1.333597183227539} 08/31/2021 16:06:43 - INFO - __main__ - Step 148414: {'lr': 1.4184012650089729e-07, 'samples': 28495488, 'steps': 148413, 'loss/train': 0.3186003863811493} 08/31/2021 16:06:44 - INFO - __main__ - Step 148415: {'lr': 1.4166144717442374e-07, 'samples': 28495680, 'steps': 148414, 'loss/train': 1.2776167392730713} 08/31/2021 16:06:44 - INFO - __main__ - Step 148416: {'lr': 1.4148288043028256e-07, 'samples': 28495872, 'steps': 148415, 'loss/train': 1.550869345664978} 08/31/2021 16:06:45 - INFO - __main__ - Step 148417: {'lr': 1.413044262685015e-07, 'samples': 28496064, 'steps': 148416, 'loss/train': 0.8865749835968018} 08/31/2021 16:06:45 - INFO - __main__ - Step 148418: {'lr': 1.4112608468921928e-07, 'samples': 28496256, 'steps': 148417, 'loss/train': 0.7034140229225159} 08/31/2021 16:06:45 - INFO - __main__ - Step 148419: {'lr': 1.4094785569249147e-07, 'samples': 28496448, 'steps': 148418, 'loss/train': 0.8627696633338928} 08/31/2021 16:06:46 - INFO - __main__ - Step 148420: {'lr': 1.4076973927837356e-07, 'samples': 28496640, 'steps': 148419, 'loss/train': 2.0883078575134277} 08/31/2021 16:06:47 - INFO - __main__ - Step 148421: {'lr': 1.4059173544697657e-07, 'samples': 28496832, 'steps': 148420, 'loss/train': 0.3654997944831848} 08/31/2021 16:06:48 - INFO - __main__ - Step 148422: {'lr': 1.4041384419838376e-07, 'samples': 28497024, 'steps': 148421, 'loss/train': 0.2297213077545166} 08/31/2021 16:06:48 - INFO - __main__ - Step 148423: {'lr': 1.4023606553265067e-07, 'samples': 28497216, 'steps': 148422, 'loss/train': 0.34098759293556213} 08/31/2021 16:06:48 - INFO - __main__ - Step 148424: {'lr': 1.400583994498883e-07, 'samples': 28497408, 'steps': 148423, 'loss/train': 1.2465871572494507} 08/31/2021 16:06:49 - INFO - __main__ - Step 148425: {'lr': 1.3988084595015217e-07, 'samples': 28497600, 'steps': 148424, 'loss/train': 1.5347070693969727} 08/31/2021 16:06:50 - INFO - __main__ - Step 148426: {'lr': 1.3970340503352551e-07, 'samples': 28497792, 'steps': 148425, 'loss/train': 0.6088573336601257} 08/31/2021 16:06:51 - INFO - __main__ - Step 148427: {'lr': 1.3952607670009164e-07, 'samples': 28497984, 'steps': 148426, 'loss/train': 0.7358932495117188} 08/31/2021 16:06:51 - INFO - __main__ - Step 148428: {'lr': 1.3934886094993383e-07, 'samples': 28498176, 'steps': 148427, 'loss/train': 1.2591495513916016} 08/31/2021 16:06:51 - INFO - __main__ - Step 148429: {'lr': 1.3917175778313529e-07, 'samples': 28498368, 'steps': 148428, 'loss/train': 1.5281291007995605} 08/31/2021 16:06:52 - INFO - __main__ - Step 148430: {'lr': 1.3899476719977932e-07, 'samples': 28498560, 'steps': 148429, 'loss/train': 1.3320624828338623} 08/31/2021 16:06:53 - INFO - __main__ - Step 148431: {'lr': 1.3881788919992144e-07, 'samples': 28498752, 'steps': 148430, 'loss/train': 0.8144866824150085} 08/31/2021 16:06:54 - INFO - __main__ - Step 148432: {'lr': 1.3864112378367266e-07, 'samples': 28498944, 'steps': 148431, 'loss/train': 1.1672141551971436} 08/31/2021 16:06:54 - INFO - __main__ - Step 148433: {'lr': 1.3846447095106074e-07, 'samples': 28499136, 'steps': 148432, 'loss/train': 1.213122010231018} 08/31/2021 16:06:55 - INFO - __main__ - Step 148434: {'lr': 1.3828793070222444e-07, 'samples': 28499328, 'steps': 148433, 'loss/train': 1.1400082111358643} 08/31/2021 16:06:55 - INFO - __main__ - Step 148435: {'lr': 1.3811150303724707e-07, 'samples': 28499520, 'steps': 148434, 'loss/train': 1.2353830337524414} 08/31/2021 16:06:57 - INFO - __main__ - Step 148436: {'lr': 1.3793518795615635e-07, 'samples': 28499712, 'steps': 148435, 'loss/train': 1.1857256889343262} 08/31/2021 16:06:58 - INFO - __main__ - Step 148437: {'lr': 1.3775898545903554e-07, 'samples': 28499904, 'steps': 148436, 'loss/train': 1.107393503189087} 08/31/2021 16:06:58 - INFO - __main__ - Step 148438: {'lr': 1.3758289554599568e-07, 'samples': 28500096, 'steps': 148437, 'loss/train': 0.6732808351516724} 08/31/2021 16:06:58 - INFO - __main__ - Step 148439: {'lr': 1.3740691821712004e-07, 'samples': 28500288, 'steps': 148438, 'loss/train': 0.07135757803916931} 08/31/2021 16:06:59 - INFO - __main__ - Step 148440: {'lr': 1.3723105347246413e-07, 'samples': 28500480, 'steps': 148439, 'loss/train': 1.1153806447982788} 08/31/2021 16:07:00 - INFO - __main__ - Step 148441: {'lr': 1.3705530131213896e-07, 'samples': 28500672, 'steps': 148440, 'loss/train': 1.1555763483047485} 08/31/2021 16:07:01 - INFO - __main__ - Step 148442: {'lr': 1.3687966173617228e-07, 'samples': 28500864, 'steps': 148441, 'loss/train': 1.3251562118530273} 08/31/2021 16:07:01 - INFO - __main__ - Step 148443: {'lr': 1.3670413474467514e-07, 'samples': 28501056, 'steps': 148442, 'loss/train': 0.8886355757713318} 08/31/2021 16:07:01 - INFO - __main__ - Step 148444: {'lr': 1.3652872033773078e-07, 'samples': 28501248, 'steps': 148443, 'loss/train': 0.6251753568649292} 08/31/2021 16:07:02 - INFO - __main__ - Step 148445: {'lr': 1.363534185154225e-07, 'samples': 28501440, 'steps': 148444, 'loss/train': 1.114443063735962} 08/31/2021 16:07:03 - INFO - __main__ - Step 148446: {'lr': 1.3617822927780576e-07, 'samples': 28501632, 'steps': 148445, 'loss/train': 0.981783390045166} 08/31/2021 16:07:03 - INFO - __main__ - Step 148447: {'lr': 1.3600315262496388e-07, 'samples': 28501824, 'steps': 148446, 'loss/train': 0.9653605222702026} 08/31/2021 16:07:04 - INFO - __main__ - Step 148448: {'lr': 1.358281885569801e-07, 'samples': 28502016, 'steps': 148447, 'loss/train': 1.183505654335022} 08/31/2021 16:07:04 - INFO - __main__ - Step 148449: {'lr': 1.3565333707393767e-07, 'samples': 28502208, 'steps': 148448, 'loss/train': 1.4533270597457886} 08/31/2021 16:07:05 - INFO - __main__ - Step 148450: {'lr': 1.3547859817594766e-07, 'samples': 28502400, 'steps': 148449, 'loss/train': 1.3205126523971558} 08/31/2021 16:07:06 - INFO - __main__ - Step 148451: {'lr': 1.3530397186301003e-07, 'samples': 28502592, 'steps': 148450, 'loss/train': 0.8552331924438477} 08/31/2021 16:07:07 - INFO - __main__ - Step 148452: {'lr': 1.3512945813526355e-07, 'samples': 28502784, 'steps': 148451, 'loss/train': 0.19019527733325958} 08/31/2021 16:07:07 - INFO - __main__ - Step 148453: {'lr': 1.3495505699279154e-07, 'samples': 28502976, 'steps': 148452, 'loss/train': 0.6328084468841553} 08/31/2021 16:07:07 - INFO - __main__ - Step 148454: {'lr': 1.3478076843564945e-07, 'samples': 28503168, 'steps': 148453, 'loss/train': 1.4421312808990479} 08/31/2021 16:07:08 - INFO - __main__ - Step 148455: {'lr': 1.3460659246389285e-07, 'samples': 28503360, 'steps': 148454, 'loss/train': 1.0945472717285156} 08/31/2021 16:07:08 - INFO - __main__ - Step 148456: {'lr': 1.3443252907766046e-07, 'samples': 28503552, 'steps': 148455, 'loss/train': 1.8273290395736694} 08/31/2021 16:07:09 - INFO - __main__ - Step 148457: {'lr': 1.3425857827698008e-07, 'samples': 28503744, 'steps': 148456, 'loss/train': 1.3988362550735474} 08/31/2021 16:07:10 - INFO - __main__ - Step 148458: {'lr': 1.3408474006193495e-07, 'samples': 28503936, 'steps': 148457, 'loss/train': 1.550403356552124} 08/31/2021 16:07:10 - INFO - __main__ - Step 148459: {'lr': 1.339110144326361e-07, 'samples': 28504128, 'steps': 148458, 'loss/train': 1.6774847507476807} 08/31/2021 16:07:11 - INFO - __main__ - Step 148460: {'lr': 1.3373740138911127e-07, 'samples': 28504320, 'steps': 148459, 'loss/train': 0.03374672308564186} 08/31/2021 16:07:11 - INFO - __main__ - Step 148461: {'lr': 1.3356390093149928e-07, 'samples': 28504512, 'steps': 148460, 'loss/train': 0.6193333864212036} 08/31/2021 16:07:12 - INFO - __main__ - Step 148462: {'lr': 1.3339051305985562e-07, 'samples': 28504704, 'steps': 148461, 'loss/train': 0.5705530047416687} 08/31/2021 16:07:13 - INFO - __main__ - Step 148463: {'lr': 1.3321723777423577e-07, 'samples': 28504896, 'steps': 148462, 'loss/train': 1.169908046722412} 08/31/2021 16:07:13 - INFO - __main__ - Step 148464: {'lr': 1.3304407507472304e-07, 'samples': 28505088, 'steps': 148463, 'loss/train': 0.9797093868255615} 08/31/2021 16:07:14 - INFO - __main__ - Step 148465: {'lr': 1.328710249614007e-07, 'samples': 28505280, 'steps': 148464, 'loss/train': 0.9354491829872131} 08/31/2021 16:07:14 - INFO - __main__ - Step 148466: {'lr': 1.326980874343797e-07, 'samples': 28505472, 'steps': 148465, 'loss/train': 1.0726028680801392} 08/31/2021 16:07:16 - INFO - __main__ - Step 148467: {'lr': 1.3252526249368791e-07, 'samples': 28505664, 'steps': 148466, 'loss/train': 1.7874184846878052} 08/31/2021 16:07:16 - INFO - __main__ - Step 148468: {'lr': 1.323525501394085e-07, 'samples': 28505856, 'steps': 148467, 'loss/train': 0.9632892608642578} 08/31/2021 16:07:16 - INFO - __main__ - Step 148469: {'lr': 1.321799503716803e-07, 'samples': 28506048, 'steps': 148468, 'loss/train': 1.16350257396698} 08/31/2021 16:07:17 - INFO - __main__ - Step 148470: {'lr': 1.3200746319050328e-07, 'samples': 28506240, 'steps': 148469, 'loss/train': 1.6299433708190918} 08/31/2021 16:07:17 - INFO - __main__ - Step 148471: {'lr': 1.3183508859598847e-07, 'samples': 28506432, 'steps': 148470, 'loss/train': 1.5612308979034424} 08/31/2021 16:07:17 - INFO - __main__ - Step 148472: {'lr': 1.3166282658821915e-07, 'samples': 28506624, 'steps': 148471, 'loss/train': 1.3639591932296753} 08/31/2021 16:07:19 - INFO - __main__ - Step 148473: {'lr': 1.314906771672786e-07, 'samples': 28506816, 'steps': 148472, 'loss/train': 0.9761145710945129} 08/31/2021 16:07:19 - INFO - __main__ - Step 148474: {'lr': 1.3131864033322226e-07, 'samples': 28507008, 'steps': 148473, 'loss/train': 1.3968628644943237} 08/31/2021 16:07:20 - INFO - __main__ - Step 148475: {'lr': 1.311467160861335e-07, 'samples': 28507200, 'steps': 148474, 'loss/train': 0.4440236985683441} 08/31/2021 16:07:20 - INFO - __main__ - Step 148476: {'lr': 1.309749044260955e-07, 'samples': 28507392, 'steps': 148475, 'loss/train': 0.5996906161308289} 08/31/2021 16:07:21 - INFO - __main__ - Step 148477: {'lr': 1.3080320535319158e-07, 'samples': 28507584, 'steps': 148476, 'loss/train': 0.8849189281463623} 08/31/2021 16:07:22 - INFO - __main__ - Step 148478: {'lr': 1.3063161886747722e-07, 'samples': 28507776, 'steps': 148477, 'loss/train': 1.0428659915924072} 08/31/2021 16:07:22 - INFO - __main__ - Step 148479: {'lr': 1.3046014496906343e-07, 'samples': 28507968, 'steps': 148478, 'loss/train': 1.089023232460022} 08/31/2021 16:07:23 - INFO - __main__ - Step 148480: {'lr': 1.3028878365800578e-07, 'samples': 28508160, 'steps': 148479, 'loss/train': 0.819692075252533} 08/31/2021 16:07:23 - INFO - __main__ - Step 148481: {'lr': 1.3011753493438749e-07, 'samples': 28508352, 'steps': 148480, 'loss/train': 0.9203423857688904} 08/31/2021 16:07:24 - INFO - __main__ - Step 148482: {'lr': 1.2994639879826408e-07, 'samples': 28508544, 'steps': 148481, 'loss/train': 1.3151259422302246} 08/31/2021 16:07:25 - INFO - __main__ - Step 148483: {'lr': 1.297753752497466e-07, 'samples': 28508736, 'steps': 148482, 'loss/train': 0.8801024556159973} 08/31/2021 16:07:26 - INFO - __main__ - Step 148484: {'lr': 1.296044642888905e-07, 'samples': 28508928, 'steps': 148483, 'loss/train': 0.7401963472366333} 08/31/2021 16:07:26 - INFO - __main__ - Step 148485: {'lr': 1.294336659157791e-07, 'samples': 28509120, 'steps': 148484, 'loss/train': 0.9475867748260498} 08/31/2021 16:07:26 - INFO - __main__ - Step 148486: {'lr': 1.2926298013049563e-07, 'samples': 28509312, 'steps': 148485, 'loss/train': 0.7296110391616821} 08/31/2021 16:07:27 - INFO - __main__ - Step 148487: {'lr': 1.2909240693309564e-07, 'samples': 28509504, 'steps': 148486, 'loss/train': 1.155499815940857} 08/31/2021 16:07:28 - INFO - __main__ - Step 148488: {'lr': 1.2892194632369013e-07, 'samples': 28509696, 'steps': 148487, 'loss/train': 1.2049686908721924} 08/31/2021 16:07:29 - INFO - __main__ - Step 148489: {'lr': 1.2875159830230686e-07, 'samples': 28509888, 'steps': 148488, 'loss/train': 1.6932605504989624} 08/31/2021 16:07:29 - INFO - __main__ - Step 148490: {'lr': 1.2858136286908462e-07, 'samples': 28510080, 'steps': 148489, 'loss/train': 1.226349115371704} 08/31/2021 16:07:29 - INFO - __main__ - Step 148491: {'lr': 1.2841124002405112e-07, 'samples': 28510272, 'steps': 148490, 'loss/train': 1.4659278392791748} 08/31/2021 16:07:30 - INFO - __main__ - Step 148492: {'lr': 1.2824122976731746e-07, 'samples': 28510464, 'steps': 148491, 'loss/train': 0.9193451404571533} 08/31/2021 16:07:30 - INFO - __main__ - Step 148493: {'lr': 1.2807133209891132e-07, 'samples': 28510656, 'steps': 148492, 'loss/train': 1.206355094909668} 08/31/2021 16:07:32 - INFO - __main__ - Step 148494: {'lr': 1.279015470189715e-07, 'samples': 28510848, 'steps': 148493, 'loss/train': 1.4903589487075806} 08/31/2021 16:07:33 - INFO - __main__ - Step 148495: {'lr': 1.2773187452752578e-07, 'samples': 28511040, 'steps': 148494, 'loss/train': 1.4697288274765015} 08/31/2021 16:07:33 - INFO - __main__ - Step 148496: {'lr': 1.275623146246574e-07, 'samples': 28511232, 'steps': 148495, 'loss/train': 0.7826098203659058} 08/31/2021 16:07:33 - INFO - __main__ - Step 148497: {'lr': 1.273928673104774e-07, 'samples': 28511424, 'steps': 148496, 'loss/train': 0.7937135100364685} 08/31/2021 16:07:34 - INFO - __main__ - Step 148498: {'lr': 1.2722353258504126e-07, 'samples': 28511616, 'steps': 148497, 'loss/train': 0.2559116780757904} 08/31/2021 16:07:35 - INFO - __main__ - Step 148499: {'lr': 1.2705431044840453e-07, 'samples': 28511808, 'steps': 148498, 'loss/train': 1.3263663053512573} 08/31/2021 16:07:36 - INFO - __main__ - Step 148500: {'lr': 1.2688520090067824e-07, 'samples': 28512000, 'steps': 148499, 'loss/train': 1.9856065511703491} 08/31/2021 16:07:36 - INFO - __main__ - Step 148501: {'lr': 1.267162039418901e-07, 'samples': 28512192, 'steps': 148500, 'loss/train': 0.9287197589874268} 08/31/2021 16:07:37 - INFO - __main__ - Step 148502: {'lr': 1.265473195721789e-07, 'samples': 28512384, 'steps': 148501, 'loss/train': 1.1624083518981934} 08/31/2021 16:07:37 - INFO - __main__ - Step 148503: {'lr': 1.2637854779157243e-07, 'samples': 28512576, 'steps': 148502, 'loss/train': 0.817787230014801} 08/31/2021 16:07:39 - INFO - __main__ - Step 148504: {'lr': 1.2620988860018167e-07, 'samples': 28512768, 'steps': 148503, 'loss/train': 1.0061386823654175} 08/31/2021 16:07:39 - INFO - __main__ - Step 148505: {'lr': 1.2604134199806215e-07, 'samples': 28512960, 'steps': 148504, 'loss/train': 1.0617263317108154} 08/31/2021 16:07:39 - INFO - __main__ - Step 148506: {'lr': 1.258729079852694e-07, 'samples': 28513152, 'steps': 148505, 'loss/train': 1.0676528215408325} 08/31/2021 16:07:40 - INFO - __main__ - Step 148507: {'lr': 1.257045865619144e-07, 'samples': 28513344, 'steps': 148506, 'loss/train': 0.08616986870765686} 08/31/2021 16:07:40 - INFO - __main__ - Step 148508: {'lr': 1.2553637772808047e-07, 'samples': 28513536, 'steps': 148507, 'loss/train': 0.8951088786125183} 08/31/2021 16:07:42 - INFO - __main__ - Step 148509: {'lr': 1.253682814837953e-07, 'samples': 28513728, 'steps': 148508, 'loss/train': 0.7941495776176453} 08/31/2021 16:07:42 - INFO - __main__ - Step 148510: {'lr': 1.2520029782919772e-07, 'samples': 28513920, 'steps': 148509, 'loss/train': 1.1159783601760864} 08/31/2021 16:07:43 - INFO - __main__ - Step 148511: {'lr': 1.2503242676428772e-07, 'samples': 28514112, 'steps': 148510, 'loss/train': 1.5678597688674927} 08/31/2021 16:07:43 - INFO - __main__ - Step 148512: {'lr': 1.2486466828920406e-07, 'samples': 28514304, 'steps': 148511, 'loss/train': 1.26902437210083} 08/31/2021 16:07:43 - INFO - __main__ - Step 148513: {'lr': 1.2469702240400226e-07, 'samples': 28514496, 'steps': 148512, 'loss/train': 0.29271847009658813} 08/31/2021 16:07:44 - INFO - __main__ - Step 148514: {'lr': 1.245294891087656e-07, 'samples': 28514688, 'steps': 148513, 'loss/train': 0.9018805027008057} 08/31/2021 16:07:45 - INFO - __main__ - Step 148515: {'lr': 1.2436206840354957e-07, 'samples': 28514880, 'steps': 148514, 'loss/train': 0.9503424763679504} 08/31/2021 16:07:46 - INFO - __main__ - Step 148516: {'lr': 1.2419476028843747e-07, 'samples': 28515072, 'steps': 148515, 'loss/train': 1.6425708532333374} 08/31/2021 16:07:46 - INFO - __main__ - Step 148517: {'lr': 1.2402756476351252e-07, 'samples': 28515264, 'steps': 148516, 'loss/train': 1.4866092205047607} 08/31/2021 16:07:46 - INFO - __main__ - Step 148518: {'lr': 1.2386048182883026e-07, 'samples': 28515456, 'steps': 148517, 'loss/train': 1.7950559854507446} 08/31/2021 16:07:47 - INFO - __main__ - Step 148519: {'lr': 1.236935114845017e-07, 'samples': 28515648, 'steps': 148518, 'loss/train': 1.25162935256958} 08/31/2021 16:07:48 - INFO - __main__ - Step 148520: {'lr': 1.2352665373055462e-07, 'samples': 28515840, 'steps': 148519, 'loss/train': 0.03498346731066704} 08/31/2021 16:07:49 - INFO - __main__ - Step 148521: {'lr': 1.233599085671e-07, 'samples': 28516032, 'steps': 148520, 'loss/train': 1.3512840270996094} 08/31/2021 16:07:49 - INFO - __main__ - Step 148522: {'lr': 1.2319327599422115e-07, 'samples': 28516224, 'steps': 148521, 'loss/train': 1.085820198059082} 08/31/2021 16:07:50 - INFO - __main__ - Step 148523: {'lr': 1.2302675601197355e-07, 'samples': 28516416, 'steps': 148522, 'loss/train': 0.47631946206092834} 08/31/2021 16:07:50 - INFO - __main__ - Step 148524: {'lr': 1.2286034862041274e-07, 'samples': 28516608, 'steps': 148523, 'loss/train': 1.071112036705017} 08/31/2021 16:07:51 - INFO - __main__ - Step 148525: {'lr': 1.226940538196497e-07, 'samples': 28516800, 'steps': 148524, 'loss/train': 1.0039618015289307} 08/31/2021 16:07:52 - INFO - __main__ - Step 148526: {'lr': 1.2252787160973998e-07, 'samples': 28516992, 'steps': 148525, 'loss/train': 1.2358183860778809} 08/31/2021 16:07:52 - INFO - __main__ - Step 148527: {'lr': 1.2236180199076686e-07, 'samples': 28517184, 'steps': 148526, 'loss/train': 1.3618521690368652} 08/31/2021 16:07:53 - INFO - __main__ - Step 148528: {'lr': 1.2219584496281354e-07, 'samples': 28517376, 'steps': 148527, 'loss/train': 1.521665096282959} 08/31/2021 16:07:53 - INFO - __main__ - Step 148529: {'lr': 1.2203000052590784e-07, 'samples': 28517568, 'steps': 148528, 'loss/train': 0.5229730010032654} 08/31/2021 16:07:55 - INFO - __main__ - Step 148530: {'lr': 1.218642686801885e-07, 'samples': 28517760, 'steps': 148529, 'loss/train': 1.1191151142120361} 08/31/2021 16:07:55 - INFO - __main__ - Step 148531: {'lr': 1.2169864942571106e-07, 'samples': 28517952, 'steps': 148530, 'loss/train': 0.49695202708244324} 08/31/2021 16:07:56 - INFO - __main__ - Step 148532: {'lr': 1.2153314276250326e-07, 'samples': 28518144, 'steps': 148531, 'loss/train': 1.7549958229064941} 08/31/2021 16:07:56 - INFO - __main__ - Step 148533: {'lr': 1.2136774869070388e-07, 'samples': 28518336, 'steps': 148532, 'loss/train': 0.5296268463134766} 08/31/2021 16:07:56 - INFO - __main__ - Step 148534: {'lr': 1.2120246721036842e-07, 'samples': 28518528, 'steps': 148533, 'loss/train': 0.23832613229751587} 08/31/2021 16:07:57 - INFO - __main__ - Step 148535: {'lr': 1.2103729832155242e-07, 'samples': 28518720, 'steps': 148534, 'loss/train': 0.8135930895805359} 08/31/2021 16:07:58 - INFO - __main__ - Step 148536: {'lr': 1.208722420243391e-07, 'samples': 28518912, 'steps': 148535, 'loss/train': 0.7974370121955872} 08/31/2021 16:07:59 - INFO - __main__ - Step 148537: {'lr': 1.2070729831878402e-07, 'samples': 28519104, 'steps': 148536, 'loss/train': 1.1975831985473633} 08/31/2021 16:07:59 - INFO - __main__ - Step 148538: {'lr': 1.2054246720499817e-07, 'samples': 28519296, 'steps': 148537, 'loss/train': 1.0995515584945679} 08/31/2021 16:08:00 - INFO - __main__ - Step 148539: {'lr': 1.2037774868306485e-07, 'samples': 28519488, 'steps': 148538, 'loss/train': 1.245234489440918} 08/31/2021 16:08:00 - INFO - __main__ - Step 148540: {'lr': 1.2021314275301177e-07, 'samples': 28519680, 'steps': 148539, 'loss/train': 1.2634613513946533} 08/31/2021 16:08:01 - INFO - __main__ - Step 148541: {'lr': 1.2004864941492223e-07, 'samples': 28519872, 'steps': 148540, 'loss/train': 1.4627506732940674} 08/31/2021 16:08:02 - INFO - __main__ - Step 148542: {'lr': 1.1988426866890722e-07, 'samples': 28520064, 'steps': 148541, 'loss/train': 0.9710461497306824} 08/31/2021 16:08:02 - INFO - __main__ - Step 148543: {'lr': 1.1972000051499454e-07, 'samples': 28520256, 'steps': 148542, 'loss/train': 1.577299952507019} 08/31/2021 16:08:03 - INFO - __main__ - Step 148544: {'lr': 1.195558449532952e-07, 'samples': 28520448, 'steps': 148543, 'loss/train': 0.9492113590240479} 08/31/2021 16:08:03 - INFO - __main__ - Step 148545: {'lr': 1.1939180198386467e-07, 'samples': 28520640, 'steps': 148544, 'loss/train': 1.6077865362167358} 08/31/2021 16:08:05 - INFO - __main__ - Step 148546: {'lr': 1.192278716067863e-07, 'samples': 28520832, 'steps': 148545, 'loss/train': 0.36452338099479675} 08/31/2021 16:08:05 - INFO - __main__ - Step 148547: {'lr': 1.190640538221155e-07, 'samples': 28521024, 'steps': 148546, 'loss/train': 1.1194804906845093} 08/31/2021 16:08:06 - INFO - __main__ - Step 148548: {'lr': 1.189003486299356e-07, 'samples': 28521216, 'steps': 148547, 'loss/train': 0.7678212523460388} 08/31/2021 16:08:06 - INFO - __main__ - Step 148549: {'lr': 1.1873675603032986e-07, 'samples': 28521408, 'steps': 148548, 'loss/train': 1.8854622840881348} 08/31/2021 16:08:06 - INFO - __main__ - Step 148550: {'lr': 1.1857327602338153e-07, 'samples': 28521600, 'steps': 148549, 'loss/train': 1.2554606199264526} 08/31/2021 16:08:08 - INFO - __main__ - Step 148551: {'lr': 1.1840990860911838e-07, 'samples': 28521792, 'steps': 148550, 'loss/train': 0.522063672542572} 08/31/2021 16:08:08 - INFO - __main__ - Step 148552: {'lr': 1.1824665378765142e-07, 'samples': 28521984, 'steps': 148551, 'loss/train': 1.1541777849197388} 08/31/2021 16:08:09 - INFO - __main__ - Step 148553: {'lr': 1.1808351155906394e-07, 'samples': 28522176, 'steps': 148552, 'loss/train': 1.076424479484558} 08/31/2021 16:08:09 - INFO - __main__ - Step 148554: {'lr': 1.1792048192341143e-07, 'samples': 28522368, 'steps': 148553, 'loss/train': 1.1117674112319946} 08/31/2021 16:08:09 - INFO - __main__ - Step 148555: {'lr': 1.177575648807494e-07, 'samples': 28522560, 'steps': 148554, 'loss/train': 0.9305501580238342} 08/31/2021 16:08:11 - INFO - __main__ - Step 148556: {'lr': 1.1759476043118889e-07, 'samples': 28522752, 'steps': 148555, 'loss/train': 1.0512990951538086} 08/31/2021 16:08:11 - INFO - __main__ - Step 148557: {'lr': 1.1743206857478539e-07, 'samples': 28522944, 'steps': 148556, 'loss/train': 1.3116722106933594} 08/31/2021 16:08:12 - INFO - __main__ - Step 148558: {'lr': 1.1726948931159443e-07, 'samples': 28523136, 'steps': 148557, 'loss/train': 2.561020851135254} 08/31/2021 16:08:12 - INFO - __main__ - Step 148559: {'lr': 1.1710702264169926e-07, 'samples': 28523328, 'steps': 148558, 'loss/train': 1.5677471160888672} 08/31/2021 16:08:12 - INFO - __main__ - Step 148560: {'lr': 1.169446685652109e-07, 'samples': 28523520, 'steps': 148559, 'loss/train': 1.3026854991912842} 08/31/2021 16:08:14 - INFO - __main__ - Step 148561: {'lr': 1.1678242708212938e-07, 'samples': 28523712, 'steps': 148560, 'loss/train': 1.1792069673538208} 08/31/2021 16:08:15 - INFO - __main__ - Step 148562: {'lr': 1.1662029819259346e-07, 'samples': 28523904, 'steps': 148561, 'loss/train': 0.6806005835533142} 08/31/2021 16:08:15 - INFO - __main__ - Step 148563: {'lr': 1.1645828189665863e-07, 'samples': 28524096, 'steps': 148562, 'loss/train': 1.3043391704559326} 08/31/2021 16:08:15 - INFO - __main__ - Step 148564: {'lr': 1.1629637819438044e-07, 'samples': 28524288, 'steps': 148563, 'loss/train': 1.2881052494049072} 08/31/2021 16:08:16 - INFO - __main__ - Step 148565: {'lr': 1.1613458708586988e-07, 'samples': 28524480, 'steps': 148564, 'loss/train': 0.3544599711894989} 08/31/2021 16:08:16 - INFO - __main__ - Step 148566: {'lr': 1.1597290857112697e-07, 'samples': 28524672, 'steps': 148565, 'loss/train': 5.434115409851074} 08/31/2021 16:08:18 - INFO - __main__ - Step 148567: {'lr': 1.1581134265031823e-07, 'samples': 28524864, 'steps': 148566, 'loss/train': 0.755474328994751} 08/31/2021 16:08:18 - INFO - __main__ - Step 148568: {'lr': 1.1564988932344367e-07, 'samples': 28525056, 'steps': 148567, 'loss/train': 0.8541800379753113} 08/31/2021 16:08:19 - INFO - __main__ - Step 148569: {'lr': 1.1548854859058655e-07, 'samples': 28525248, 'steps': 148568, 'loss/train': 1.5252902507781982} 08/31/2021 16:08:19 - INFO - __main__ - Step 148570: {'lr': 1.153273204518579e-07, 'samples': 28525440, 'steps': 148569, 'loss/train': 1.312425971031189} 08/31/2021 16:08:19 - INFO - __main__ - Step 148571: {'lr': 1.1516620490731322e-07, 'samples': 28525632, 'steps': 148570, 'loss/train': 0.01417052373290062} 08/31/2021 16:08:20 - INFO - __main__ - Step 148572: {'lr': 1.1500520195700803e-07, 'samples': 28525824, 'steps': 148571, 'loss/train': 1.0573564767837524} 08/31/2021 16:08:21 - INFO - __main__ - Step 148573: {'lr': 1.1484431160102559e-07, 'samples': 28526016, 'steps': 148572, 'loss/train': 1.270023226737976} 08/31/2021 16:08:21 - INFO - __main__ - Step 148574: {'lr': 1.1468353383942143e-07, 'samples': 28526208, 'steps': 148573, 'loss/train': 0.5861756205558777} 08/31/2021 16:08:22 - INFO - __main__ - Step 148575: {'lr': 1.1452286867230655e-07, 'samples': 28526400, 'steps': 148574, 'loss/train': 1.255474328994751} 08/31/2021 16:08:22 - INFO - __main__ - Step 148576: {'lr': 1.143623160997087e-07, 'samples': 28526592, 'steps': 148575, 'loss/train': 0.8262231349945068} 08/31/2021 16:08:23 - INFO - __main__ - Step 148577: {'lr': 1.1420187612173893e-07, 'samples': 28526784, 'steps': 148576, 'loss/train': 1.0345466136932373} 08/31/2021 16:08:24 - INFO - __main__ - Step 148578: {'lr': 1.140415487384805e-07, 'samples': 28526976, 'steps': 148577, 'loss/train': 1.1233025789260864} 08/31/2021 16:08:25 - INFO - __main__ - Step 148579: {'lr': 1.1388133394993338e-07, 'samples': 28527168, 'steps': 148578, 'loss/train': 0.5395885705947876} 08/31/2021 16:08:25 - INFO - __main__ - Step 148580: {'lr': 1.1372123175623638e-07, 'samples': 28527360, 'steps': 148579, 'loss/train': 0.9322468638420105} 08/31/2021 16:08:25 - INFO - __main__ - Step 148581: {'lr': 1.1356124215744501e-07, 'samples': 28527552, 'steps': 148580, 'loss/train': 1.062735676765442} 08/31/2021 16:08:26 - INFO - __main__ - Step 148582: {'lr': 1.1340136515361477e-07, 'samples': 28527744, 'steps': 148581, 'loss/train': 0.6816586852073669} 08/31/2021 16:08:28 - INFO - __main__ - Step 148583: {'lr': 1.1324160074482893e-07, 'samples': 28527936, 'steps': 148582, 'loss/train': 0.1087312251329422} 08/31/2021 16:08:28 - INFO - __main__ - Step 148584: {'lr': 1.1308194893117074e-07, 'samples': 28528128, 'steps': 148583, 'loss/train': 1.0111980438232422} 08/31/2021 16:08:28 - INFO - __main__ - Step 148585: {'lr': 1.1292240971269574e-07, 'samples': 28528320, 'steps': 148584, 'loss/train': 1.1447339057922363} 08/31/2021 16:08:29 - INFO - __main__ - Step 148586: {'lr': 1.1276298308948718e-07, 'samples': 28528512, 'steps': 148585, 'loss/train': 0.046156127005815506} 08/31/2021 16:08:29 - INFO - __main__ - Step 148587: {'lr': 1.1260366906162833e-07, 'samples': 28528704, 'steps': 148586, 'loss/train': 1.5974042415618896} 08/31/2021 16:08:31 - INFO - __main__ - Step 148588: {'lr': 1.1244446762914695e-07, 'samples': 28528896, 'steps': 148587, 'loss/train': 1.3808839321136475} 08/31/2021 16:08:31 - INFO - __main__ - Step 148589: {'lr': 1.1228537879215406e-07, 'samples': 28529088, 'steps': 148588, 'loss/train': 0.44393253326416016} 08/31/2021 16:08:32 - INFO - __main__ - Step 148590: {'lr': 1.1212640255070516e-07, 'samples': 28529280, 'steps': 148589, 'loss/train': 0.6804307699203491} 08/31/2021 16:08:32 - INFO - __main__ - Step 148591: {'lr': 1.1196753890488354e-07, 'samples': 28529472, 'steps': 148590, 'loss/train': 1.2044073343276978} 08/31/2021 16:08:32 - INFO - __main__ - Step 148592: {'lr': 1.1180878785474469e-07, 'samples': 28529664, 'steps': 148591, 'loss/train': 0.8193149566650391} 08/31/2021 16:08:34 - INFO - __main__ - Step 148593: {'lr': 1.1165014940037188e-07, 'samples': 28529856, 'steps': 148592, 'loss/train': 0.7712115049362183} 08/31/2021 16:08:34 - INFO - __main__ - Step 148594: {'lr': 1.1149162354182062e-07, 'samples': 28530048, 'steps': 148593, 'loss/train': 1.4295268058776855} 08/31/2021 16:08:35 - INFO - __main__ - Step 148595: {'lr': 1.113332102791742e-07, 'samples': 28530240, 'steps': 148594, 'loss/train': 1.1694427728652954} 08/31/2021 16:08:35 - INFO - __main__ - Step 148596: {'lr': 1.1117490961251586e-07, 'samples': 28530432, 'steps': 148595, 'loss/train': 1.5731403827667236} 08/31/2021 16:08:35 - INFO - __main__ - Step 148597: {'lr': 1.1101672154192888e-07, 'samples': 28530624, 'steps': 148596, 'loss/train': 0.9154926538467407} 08/31/2021 16:08:36 - INFO - __main__ - Step 148598: {'lr': 1.10858646067441e-07, 'samples': 28530816, 'steps': 148597, 'loss/train': 1.4437100887298584} 08/31/2021 16:08:38 - INFO - __main__ - Step 148599: {'lr': 1.107006831891355e-07, 'samples': 28531008, 'steps': 148598, 'loss/train': 1.0724778175354004} 08/31/2021 16:08:38 - INFO - __main__ - Step 148600: {'lr': 1.1054283290709566e-07, 'samples': 28531200, 'steps': 148599, 'loss/train': 1.2566450834274292} 08/31/2021 16:08:39 - INFO - __main__ - Step 148601: {'lr': 1.1038509522140472e-07, 'samples': 28531392, 'steps': 148600, 'loss/train': 0.030964162200689316} 08/31/2021 16:08:39 - INFO - __main__ - Step 148602: {'lr': 1.1022747013209044e-07, 'samples': 28531584, 'steps': 148601, 'loss/train': 0.5267086625099182} 08/31/2021 16:08:39 - INFO - __main__ - Step 148603: {'lr': 1.1006995763929161e-07, 'samples': 28531776, 'steps': 148602, 'loss/train': 1.309455156326294} 08/31/2021 16:08:41 - INFO - __main__ - Step 148604: {'lr': 1.0991255774300823e-07, 'samples': 28531968, 'steps': 148603, 'loss/train': 1.0618339776992798} 08/31/2021 16:08:41 - INFO - __main__ - Step 148605: {'lr': 1.0975527044335132e-07, 'samples': 28532160, 'steps': 148604, 'loss/train': 0.29831141233444214} 08/31/2021 16:08:42 - INFO - __main__ - Step 148606: {'lr': 1.0959809574037639e-07, 'samples': 28532352, 'steps': 148605, 'loss/train': 1.107783555984497} 08/31/2021 16:08:42 - INFO - __main__ - Step 148607: {'lr': 1.0944103363416669e-07, 'samples': 28532544, 'steps': 148606, 'loss/train': 0.2935454845428467} 08/31/2021 16:08:42 - INFO - __main__ - Step 148608: {'lr': 1.0928408412477775e-07, 'samples': 28532736, 'steps': 148607, 'loss/train': 0.409391850233078} 08/31/2021 16:08:44 - INFO - __main__ - Step 148609: {'lr': 1.0912724721232059e-07, 'samples': 28532928, 'steps': 148608, 'loss/train': 1.7429884672164917} 08/31/2021 16:08:44 - INFO - __main__ - Step 148610: {'lr': 1.0897052289679521e-07, 'samples': 28533120, 'steps': 148609, 'loss/train': 0.47991448640823364} 08/31/2021 16:08:45 - INFO - __main__ - Step 148611: {'lr': 1.0881391117834038e-07, 'samples': 28533312, 'steps': 148610, 'loss/train': 1.1343348026275635} 08/31/2021 16:08:45 - INFO - __main__ - Step 148612: {'lr': 1.0865741205698387e-07, 'samples': 28533504, 'steps': 148611, 'loss/train': 0.8467828631401062} 08/31/2021 16:08:45 - INFO - __main__ - Step 148613: {'lr': 1.0850102553280893e-07, 'samples': 28533696, 'steps': 148612, 'loss/train': 0.9335867762565613} 08/31/2021 16:08:47 - INFO - __main__ - Step 148614: {'lr': 1.0834475160589885e-07, 'samples': 28533888, 'steps': 148613, 'loss/train': 1.1811572313308716} 08/31/2021 16:08:47 - INFO - __main__ - Step 148615: {'lr': 1.0818859027628137e-07, 'samples': 28534080, 'steps': 148614, 'loss/train': 0.09515223652124405} 08/31/2021 16:08:47 - INFO - __main__ - Step 148616: {'lr': 1.0803254154409525e-07, 'samples': 28534272, 'steps': 148615, 'loss/train': 1.1695446968078613} 08/31/2021 16:08:48 - INFO - __main__ - Step 148617: {'lr': 1.0787660540936827e-07, 'samples': 28534464, 'steps': 148616, 'loss/train': 0.8783602714538574} 08/31/2021 16:08:48 - INFO - __main__ - Step 148618: {'lr': 1.0772078187215595e-07, 'samples': 28534656, 'steps': 148617, 'loss/train': 1.4027166366577148} 08/31/2021 16:08:50 - INFO - __main__ - Step 148619: {'lr': 1.0756507093256929e-07, 'samples': 28534848, 'steps': 148618, 'loss/train': 0.7297250032424927} 08/31/2021 16:08:51 - INFO - __main__ - Step 148620: {'lr': 1.0740947259063605e-07, 'samples': 28535040, 'steps': 148619, 'loss/train': 0.6567363142967224} 08/31/2021 16:08:51 - INFO - __main__ - Step 148621: {'lr': 1.0725398684646725e-07, 'samples': 28535232, 'steps': 148620, 'loss/train': 0.4371701776981354} 08/31/2021 16:08:51 - INFO - __main__ - Step 148622: {'lr': 1.0709861370009066e-07, 'samples': 28535424, 'steps': 148621, 'loss/train': 1.1465760469436646} 08/31/2021 16:08:52 - INFO - __main__ - Step 148623: {'lr': 1.069433531516173e-07, 'samples': 28535616, 'steps': 148622, 'loss/train': 0.01646181009709835} 08/31/2021 16:08:52 - INFO - __main__ - Step 148624: {'lr': 1.0678820520110266e-07, 'samples': 28535808, 'steps': 148623, 'loss/train': 1.2405521869659424} 08/31/2021 16:08:54 - INFO - __main__ - Step 148625: {'lr': 1.0663316984860228e-07, 'samples': 28536000, 'steps': 148624, 'loss/train': 0.27052900195121765} 08/31/2021 16:08:54 - INFO - __main__ - Step 148626: {'lr': 1.064782470941994e-07, 'samples': 28536192, 'steps': 148625, 'loss/train': 1.3163005113601685} 08/31/2021 16:08:55 - INFO - __main__ - Step 148627: {'lr': 1.063234369379773e-07, 'samples': 28536384, 'steps': 148626, 'loss/train': 0.07584913074970245} 08/31/2021 16:08:55 - INFO - __main__ - Step 148628: {'lr': 1.0616873937996374e-07, 'samples': 28536576, 'steps': 148627, 'loss/train': 0.1900615096092224} 08/31/2021 16:08:55 - INFO - __main__ - Step 148629: {'lr': 1.0601415442026973e-07, 'samples': 28536768, 'steps': 148628, 'loss/train': 0.518674910068512} 08/31/2021 16:08:57 - INFO - __main__ - Step 148630: {'lr': 1.058596820589508e-07, 'samples': 28536960, 'steps': 148629, 'loss/train': 0.8634145855903625} 08/31/2021 16:08:57 - INFO - __main__ - Step 148631: {'lr': 1.0570532229606244e-07, 'samples': 28537152, 'steps': 148630, 'loss/train': 0.7341110706329346} 08/31/2021 16:08:58 - INFO - __main__ - Step 148632: {'lr': 1.0555107513171569e-07, 'samples': 28537344, 'steps': 148631, 'loss/train': 0.8369633555412292} 08/31/2021 16:08:58 - INFO - __main__ - Step 148633: {'lr': 1.053969405659383e-07, 'samples': 28537536, 'steps': 148632, 'loss/train': 1.1641064882278442} 08/31/2021 16:08:58 - INFO - __main__ - Step 148634: {'lr': 1.0524291859878577e-07, 'samples': 28537728, 'steps': 148633, 'loss/train': 0.8679566979408264} 08/31/2021 16:09:00 - INFO - __main__ - Step 148635: {'lr': 1.0508900923039688e-07, 'samples': 28537920, 'steps': 148634, 'loss/train': 1.5807124376296997} 08/31/2021 16:09:00 - INFO - __main__ - Step 148636: {'lr': 1.0493521246077165e-07, 'samples': 28538112, 'steps': 148635, 'loss/train': 0.8070257306098938} 08/31/2021 16:09:01 - INFO - __main__ - Step 148637: {'lr': 1.0478152829002108e-07, 'samples': 28538304, 'steps': 148636, 'loss/train': 1.588667869567871} 08/31/2021 16:09:01 - INFO - __main__ - Step 148638: {'lr': 1.0462795671817294e-07, 'samples': 28538496, 'steps': 148637, 'loss/train': 1.3980133533477783} 08/31/2021 16:09:01 - INFO - __main__ - Step 148639: {'lr': 1.0447449774533824e-07, 'samples': 28538688, 'steps': 148638, 'loss/train': 0.7684397101402283} 08/31/2021 16:09:03 - INFO - __main__ - Step 148640: {'lr': 1.043211513715725e-07, 'samples': 28538880, 'steps': 148639, 'loss/train': 0.5339434742927551} 08/31/2021 16:09:03 - INFO - __main__ - Step 148641: {'lr': 1.0416791759695898e-07, 'samples': 28539072, 'steps': 148640, 'loss/train': 1.5056906938552856} 08/31/2021 16:09:04 - INFO - __main__ - Step 148642: {'lr': 1.0401479642152545e-07, 'samples': 28539264, 'steps': 148641, 'loss/train': 1.6261743307113647} 08/31/2021 16:09:04 - INFO - __main__ - Step 148643: {'lr': 1.0386178784538292e-07, 'samples': 28539456, 'steps': 148642, 'loss/train': 1.1283308267593384} 08/31/2021 16:09:04 - INFO - __main__ - Step 148644: {'lr': 1.037088918685869e-07, 'samples': 28539648, 'steps': 148643, 'loss/train': 1.026817798614502} 08/31/2021 16:09:06 - INFO - __main__ - Step 148645: {'lr': 1.035561084911929e-07, 'samples': 28539840, 'steps': 148644, 'loss/train': 0.9195079803466797} 08/31/2021 16:09:06 - INFO - __main__ - Step 148646: {'lr': 1.034034377132842e-07, 'samples': 28540032, 'steps': 148645, 'loss/train': 0.6310496926307678} 08/31/2021 16:09:07 - INFO - __main__ - Step 148647: {'lr': 1.0325087953494406e-07, 'samples': 28540224, 'steps': 148646, 'loss/train': 0.4882849156856537} 08/31/2021 16:09:07 - INFO - __main__ - Step 148648: {'lr': 1.0309843395620022e-07, 'samples': 28540416, 'steps': 148647, 'loss/train': 0.5995073914527893} 08/31/2021 16:09:08 - INFO - __main__ - Step 148649: {'lr': 1.0294610097713597e-07, 'samples': 28540608, 'steps': 148648, 'loss/train': 1.206630825996399} 08/31/2021 16:09:08 - INFO - __main__ - Step 148650: {'lr': 1.0279388059783457e-07, 'samples': 28540800, 'steps': 148649, 'loss/train': 1.2872731685638428} 08/31/2021 16:09:09 - INFO - __main__ - Step 148651: {'lr': 1.0264177281837927e-07, 'samples': 28540992, 'steps': 148650, 'loss/train': 1.3661695718765259} 08/31/2021 16:09:10 - INFO - __main__ - Step 148652: {'lr': 1.0248977763879785e-07, 'samples': 28541184, 'steps': 148651, 'loss/train': 1.139601469039917} 08/31/2021 16:09:10 - INFO - __main__ - Step 148653: {'lr': 1.0233789505917357e-07, 'samples': 28541376, 'steps': 148652, 'loss/train': 1.48666512966156} 08/31/2021 16:09:11 - INFO - __main__ - Step 148654: {'lr': 1.021861250795897e-07, 'samples': 28541568, 'steps': 148653, 'loss/train': 1.1145009994506836} 08/31/2021 16:09:11 - INFO - __main__ - Step 148655: {'lr': 1.0203446770012947e-07, 'samples': 28541760, 'steps': 148654, 'loss/train': 0.9557012319564819} 08/31/2021 16:09:13 - INFO - __main__ - Step 148656: {'lr': 1.0188292292079293e-07, 'samples': 28541952, 'steps': 148655, 'loss/train': 0.8749726414680481} 08/31/2021 16:09:14 - INFO - __main__ - Step 148657: {'lr': 1.0173149074171883e-07, 'samples': 28542144, 'steps': 148656, 'loss/train': 1.7015180587768555} 08/31/2021 16:09:14 - INFO - __main__ - Step 148658: {'lr': 1.0158017116293494e-07, 'samples': 28542336, 'steps': 148657, 'loss/train': 1.0280072689056396} 08/31/2021 16:09:14 - INFO - __main__ - Step 148659: {'lr': 1.0142896418452452e-07, 'samples': 28542528, 'steps': 148658, 'loss/train': 1.229664921760559} 08/31/2021 16:09:15 - INFO - __main__ - Step 148660: {'lr': 1.0127786980657084e-07, 'samples': 28542720, 'steps': 148659, 'loss/train': 0.028133386746048927} 08/31/2021 16:09:15 - INFO - __main__ - Step 148661: {'lr': 1.0112688802910164e-07, 'samples': 28542912, 'steps': 148660, 'loss/train': 0.6626754999160767} 08/31/2021 16:09:17 - INFO - __main__ - Step 148662: {'lr': 1.0097601885222796e-07, 'samples': 28543104, 'steps': 148661, 'loss/train': 1.5271258354187012} 08/31/2021 16:09:17 - INFO - __main__ - Step 148663: {'lr': 1.0082526227597755e-07, 'samples': 28543296, 'steps': 148662, 'loss/train': 1.2876193523406982} 08/31/2021 16:09:17 - INFO - __main__ - Step 148664: {'lr': 1.0067461830046143e-07, 'samples': 28543488, 'steps': 148663, 'loss/train': 0.14663858711719513} 08/31/2021 16:09:18 - INFO - __main__ - Step 148665: {'lr': 1.0052408692570735e-07, 'samples': 28543680, 'steps': 148664, 'loss/train': 0.10681642591953278} 08/31/2021 16:09:18 - INFO - __main__ - Step 148666: {'lr': 1.003736681517986e-07, 'samples': 28543872, 'steps': 148665, 'loss/train': 0.5811681151390076} 08/31/2021 16:09:20 - INFO - __main__ - Step 148667: {'lr': 1.0022336197881843e-07, 'samples': 28544064, 'steps': 148666, 'loss/train': 1.1313467025756836} 08/31/2021 16:09:20 - INFO - __main__ - Step 148668: {'lr': 1.0007316840682234e-07, 'samples': 28544256, 'steps': 148667, 'loss/train': 0.3995094299316406} 08/31/2021 16:09:21 - INFO - __main__ - Step 148669: {'lr': 9.992308743586587e-08, 'samples': 28544448, 'steps': 148668, 'loss/train': 1.1491332054138184} 08/31/2021 16:09:21 - INFO - __main__ - Step 148670: {'lr': 9.977311906603226e-08, 'samples': 28544640, 'steps': 148669, 'loss/train': 1.2417163848876953} 08/31/2021 16:09:21 - INFO - __main__ - Step 148671: {'lr': 9.962326329737703e-08, 'samples': 28544832, 'steps': 148670, 'loss/train': 0.46075254678726196} 08/31/2021 16:09:23 - INFO - __main__ - Step 148672: {'lr': 9.947352012998345e-08, 'samples': 28545024, 'steps': 148671, 'loss/train': 1.410030722618103} 08/31/2021 16:09:23 - INFO - __main__ - Step 148673: {'lr': 9.93238895639348e-08, 'samples': 28545216, 'steps': 148672, 'loss/train': 1.7697184085845947} 08/31/2021 16:09:24 - INFO - __main__ - Step 148674: {'lr': 9.917437159923104e-08, 'samples': 28545408, 'steps': 148673, 'loss/train': 1.538795828819275} 08/31/2021 16:09:24 - INFO - __main__ - Step 148675: {'lr': 9.902496623601098e-08, 'samples': 28545600, 'steps': 148674, 'loss/train': 0.6319777965545654} 08/31/2021 16:09:24 - INFO - __main__ - Step 148676: {'lr': 9.887567347430237e-08, 'samples': 28545792, 'steps': 148675, 'loss/train': 0.7139697074890137} 08/31/2021 16:09:26 - INFO - __main__ - Step 148677: {'lr': 9.872649331418848e-08, 'samples': 28545984, 'steps': 148676, 'loss/train': 1.2796326875686646} 08/31/2021 16:09:26 - INFO - __main__ - Step 148678: {'lr': 9.857742575575256e-08, 'samples': 28546176, 'steps': 148677, 'loss/train': 1.0044275522232056} 08/31/2021 16:09:27 - INFO - __main__ - Step 148679: {'lr': 9.84284707990224e-08, 'samples': 28546368, 'steps': 148678, 'loss/train': 0.6111811995506287} 08/31/2021 16:09:27 - INFO - __main__ - Step 148680: {'lr': 9.827962844408122e-08, 'samples': 28546560, 'steps': 148679, 'loss/train': 0.9850530624389648} 08/31/2021 16:09:27 - INFO - __main__ - Step 148681: {'lr': 9.813089869098458e-08, 'samples': 28546752, 'steps': 148680, 'loss/train': 1.127926230430603} 08/31/2021 16:09:28 - INFO - __main__ - Step 148682: {'lr': 9.798228153984345e-08, 'samples': 28546944, 'steps': 148681, 'loss/train': 1.0174415111541748} 08/31/2021 16:09:29 - INFO - __main__ - Step 148683: {'lr': 9.783377699068563e-08, 'samples': 28547136, 'steps': 148682, 'loss/train': 1.44315505027771} 08/31/2021 16:09:30 - INFO - __main__ - Step 148684: {'lr': 9.768538504356661e-08, 'samples': 28547328, 'steps': 148683, 'loss/train': 0.6365396976470947} 08/31/2021 16:09:30 - INFO - __main__ - Step 148685: {'lr': 9.753710569859742e-08, 'samples': 28547520, 'steps': 148684, 'loss/train': 0.5114226341247559} 08/31/2021 16:09:30 - INFO - __main__ - Step 148686: {'lr': 9.738893895580581e-08, 'samples': 28547712, 'steps': 148685, 'loss/train': 0.7425395846366882} 08/31/2021 16:09:31 - INFO - __main__ - Step 148687: {'lr': 9.72408848153028e-08, 'samples': 28547904, 'steps': 148686, 'loss/train': 0.9204146265983582} 08/31/2021 16:09:32 - INFO - __main__ - Step 148688: {'lr': 9.709294327708839e-08, 'samples': 28548096, 'steps': 148687, 'loss/train': 1.488405704498291} 08/31/2021 16:09:33 - INFO - __main__ - Step 148689: {'lr': 9.694511434130138e-08, 'samples': 28548288, 'steps': 148688, 'loss/train': 1.0529271364212036} 08/31/2021 16:09:33 - INFO - __main__ - Step 148690: {'lr': 9.67973980079695e-08, 'samples': 28548480, 'steps': 148689, 'loss/train': 0.31292104721069336} 08/31/2021 16:09:33 - INFO - __main__ - Step 148691: {'lr': 9.664979427714826e-08, 'samples': 28548672, 'steps': 148690, 'loss/train': 0.11194711923599243} 08/31/2021 16:09:34 - INFO - __main__ - Step 148692: {'lr': 9.650230314892094e-08, 'samples': 28548864, 'steps': 148691, 'loss/train': 2.101940631866455} 08/31/2021 16:09:35 - INFO - __main__ - Step 148693: {'lr': 9.635492462337081e-08, 'samples': 28549056, 'steps': 148692, 'loss/train': 1.5274202823638916} 08/31/2021 16:09:36 - INFO - __main__ - Step 148694: {'lr': 9.620765870052562e-08, 'samples': 28549248, 'steps': 148693, 'loss/train': 0.8868553638458252} 08/31/2021 16:09:36 - INFO - __main__ - Step 148695: {'lr': 9.606050538049638e-08, 'samples': 28549440, 'steps': 148694, 'loss/train': 0.7659629583358765} 08/31/2021 16:09:36 - INFO - __main__ - Step 148696: {'lr': 9.591346466331086e-08, 'samples': 28549632, 'steps': 148695, 'loss/train': 0.12854932248592377} 08/31/2021 16:09:37 - INFO - __main__ - Step 148697: {'lr': 9.576653654905231e-08, 'samples': 28549824, 'steps': 148696, 'loss/train': 0.7952501773834229} 08/31/2021 16:09:38 - INFO - __main__ - Step 148698: {'lr': 9.561972103777628e-08, 'samples': 28550016, 'steps': 148697, 'loss/train': 1.631312608718872} 08/31/2021 16:09:39 - INFO - __main__ - Step 148699: {'lr': 9.547301812959375e-08, 'samples': 28550208, 'steps': 148698, 'loss/train': 0.355977863073349} 08/31/2021 16:09:39 - INFO - __main__ - Step 148700: {'lr': 9.532642782450473e-08, 'samples': 28550400, 'steps': 148699, 'loss/train': 0.6905191540718079} 08/31/2021 16:09:40 - INFO - __main__ - Step 148701: {'lr': 9.517995012259251e-08, 'samples': 28550592, 'steps': 148700, 'loss/train': 0.6426051259040833} 08/31/2021 16:09:40 - INFO - __main__ - Step 148702: {'lr': 9.503358502396809e-08, 'samples': 28550784, 'steps': 148701, 'loss/train': 1.2297916412353516} 08/31/2021 16:09:40 - INFO - __main__ - Step 148703: {'lr': 9.488733252863147e-08, 'samples': 28550976, 'steps': 148702, 'loss/train': 0.713025689125061} 08/31/2021 16:09:42 - INFO - __main__ - Step 148704: {'lr': 9.474119263672143e-08, 'samples': 28551168, 'steps': 148703, 'loss/train': 0.9973406791687012} 08/31/2021 16:09:43 - INFO - __main__ - Step 148705: {'lr': 9.459516534823798e-08, 'samples': 28551360, 'steps': 148704, 'loss/train': 0.06313274055719376} 08/31/2021 16:09:43 - INFO - __main__ - Step 148706: {'lr': 9.444925066329213e-08, 'samples': 28551552, 'steps': 148705, 'loss/train': 0.7314407825469971} 08/31/2021 16:09:43 - INFO - __main__ - Step 148707: {'lr': 9.430344858191164e-08, 'samples': 28551744, 'steps': 148706, 'loss/train': 1.670466423034668} 08/31/2021 16:09:44 - INFO - __main__ - Step 148708: {'lr': 9.415775910417979e-08, 'samples': 28551936, 'steps': 148707, 'loss/train': 1.7899055480957031} 08/31/2021 16:09:44 - INFO - __main__ - Step 148709: {'lr': 9.401218223017982e-08, 'samples': 28552128, 'steps': 148708, 'loss/train': 1.065930962562561} 08/31/2021 16:09:46 - INFO - __main__ - Step 148710: {'lr': 9.386671795996726e-08, 'samples': 28552320, 'steps': 148709, 'loss/train': 1.4095920324325562} 08/31/2021 16:09:47 - INFO - __main__ - Step 148711: {'lr': 9.372136629356987e-08, 'samples': 28552512, 'steps': 148710, 'loss/train': 0.7523168921470642} 08/31/2021 16:09:47 - INFO - __main__ - Step 148712: {'lr': 9.35761272311264e-08, 'samples': 28552704, 'steps': 148711, 'loss/train': 0.6467604041099548} 08/31/2021 16:09:47 - INFO - __main__ - Step 148713: {'lr': 9.343100077263689e-08, 'samples': 28552896, 'steps': 148712, 'loss/train': 1.7486417293548584} 08/31/2021 16:09:48 - INFO - __main__ - Step 148714: {'lr': 9.328598691818457e-08, 'samples': 28553088, 'steps': 148713, 'loss/train': 0.7876190543174744} 08/31/2021 16:09:50 - INFO - __main__ - Step 148715: {'lr': 9.314108566785273e-08, 'samples': 28553280, 'steps': 148714, 'loss/train': 0.9549469351768494} 08/31/2021 16:09:50 - INFO - __main__ - Step 148716: {'lr': 9.299629702169687e-08, 'samples': 28553472, 'steps': 148715, 'loss/train': 1.1382832527160645} 08/31/2021 16:09:51 - INFO - __main__ - Step 148717: {'lr': 9.285162097977251e-08, 'samples': 28553664, 'steps': 148716, 'loss/train': 0.09225618094205856} 08/31/2021 16:09:51 - INFO - __main__ - Step 148718: {'lr': 9.270705754216291e-08, 'samples': 28553856, 'steps': 148717, 'loss/train': 1.4477505683898926} 08/31/2021 16:09:51 - INFO - __main__ - Step 148719: {'lr': 9.256260670892358e-08, 'samples': 28554048, 'steps': 148718, 'loss/train': 1.0637431144714355} 08/31/2021 16:09:52 - INFO - __main__ - Step 148720: {'lr': 9.241826848011003e-08, 'samples': 28554240, 'steps': 148719, 'loss/train': 1.1255961656570435} 08/31/2021 16:09:53 - INFO - __main__ - Step 148721: {'lr': 9.227404285580554e-08, 'samples': 28554432, 'steps': 148720, 'loss/train': 0.037899214774370193} 08/31/2021 16:09:54 - INFO - __main__ - Step 148722: {'lr': 9.21299298360656e-08, 'samples': 28554624, 'steps': 148721, 'loss/train': 1.4192049503326416} 08/31/2021 16:09:54 - INFO - __main__ - Step 148723: {'lr': 9.198592942094575e-08, 'samples': 28554816, 'steps': 148722, 'loss/train': 1.0122065544128418} 08/31/2021 16:09:54 - INFO - __main__ - Step 148724: {'lr': 9.184204161052922e-08, 'samples': 28555008, 'steps': 148723, 'loss/train': 1.0824995040893555} 08/31/2021 16:09:55 - INFO - __main__ - Step 148725: {'lr': 9.169826640487156e-08, 'samples': 28555200, 'steps': 148724, 'loss/train': 1.3124414682388306} 08/31/2021 16:09:57 - INFO - __main__ - Step 148726: {'lr': 9.155460380402824e-08, 'samples': 28555392, 'steps': 148725, 'loss/train': 1.1291593313217163} 08/31/2021 16:09:57 - INFO - __main__ - Step 148727: {'lr': 9.141105380808256e-08, 'samples': 28555584, 'steps': 148726, 'loss/train': 0.6818799376487732} 08/31/2021 16:09:58 - INFO - __main__ - Step 148728: {'lr': 9.126761641709003e-08, 'samples': 28555776, 'steps': 148727, 'loss/train': 0.743565559387207} 08/31/2021 16:09:58 - INFO - __main__ - Step 148729: {'lr': 9.112429163110614e-08, 'samples': 28555968, 'steps': 148728, 'loss/train': 0.04821817949414253} 08/31/2021 16:09:58 - INFO - __main__ - Step 148730: {'lr': 9.098107945021417e-08, 'samples': 28556160, 'steps': 148729, 'loss/train': 0.8409026265144348} 08/31/2021 16:10:00 - INFO - __main__ - Step 148731: {'lr': 9.083797987446963e-08, 'samples': 28556352, 'steps': 148730, 'loss/train': 1.370753288269043} 08/31/2021 16:10:00 - INFO - __main__ - Step 148732: {'lr': 9.069499290395577e-08, 'samples': 28556544, 'steps': 148731, 'loss/train': 1.0304603576660156} 08/31/2021 16:10:01 - INFO - __main__ - Step 148733: {'lr': 9.055211853870038e-08, 'samples': 28556736, 'steps': 148732, 'loss/train': 1.3308573961257935} 08/31/2021 16:10:01 - INFO - __main__ - Step 148734: {'lr': 9.04093567787867e-08, 'samples': 28556928, 'steps': 148733, 'loss/train': 0.9205229878425598} 08/31/2021 16:10:01 - INFO - __main__ - Step 148735: {'lr': 9.026670762427025e-08, 'samples': 28557120, 'steps': 148734, 'loss/train': 1.1764214038848877} 08/31/2021 16:10:03 - INFO - __main__ - Step 148736: {'lr': 9.012417107523429e-08, 'samples': 28557312, 'steps': 148735, 'loss/train': 1.2977851629257202} 08/31/2021 16:10:03 - INFO - __main__ - Step 148737: {'lr': 8.998174713173435e-08, 'samples': 28557504, 'steps': 148736, 'loss/train': 0.4113406240940094} 08/31/2021 16:10:03 - INFO - __main__ - Step 148738: {'lr': 8.983943579382592e-08, 'samples': 28557696, 'steps': 148737, 'loss/train': 1.1587620973587036} 08/31/2021 16:10:04 - INFO - __main__ - Step 148739: {'lr': 8.969723706156452e-08, 'samples': 28557888, 'steps': 148738, 'loss/train': 0.6041648983955383} 08/31/2021 16:10:04 - INFO - __main__ - Step 148740: {'lr': 8.955515093506118e-08, 'samples': 28558080, 'steps': 148739, 'loss/train': 0.8763749003410339} 08/31/2021 16:10:04 - INFO - __main__ - Step 148741: {'lr': 8.941317741431587e-08, 'samples': 28558272, 'steps': 148740, 'loss/train': 0.742816686630249} 08/31/2021 16:10:06 - INFO - __main__ - Step 148742: {'lr': 8.927131649943965e-08, 'samples': 28558464, 'steps': 148741, 'loss/train': 0.9111738801002502} 08/31/2021 16:10:06 - INFO - __main__ - Step 148743: {'lr': 8.912956819048801e-08, 'samples': 28558656, 'steps': 148742, 'loss/train': 1.212270736694336} 08/31/2021 16:10:07 - INFO - __main__ - Step 148744: {'lr': 8.898793248751646e-08, 'samples': 28558848, 'steps': 148743, 'loss/train': 1.3530817031860352} 08/31/2021 16:10:07 - INFO - __main__ - Step 148745: {'lr': 8.884640939058053e-08, 'samples': 28559040, 'steps': 148744, 'loss/train': 0.634462833404541} 08/31/2021 16:10:07 - INFO - __main__ - Step 148746: {'lr': 8.870499889976347e-08, 'samples': 28559232, 'steps': 148745, 'loss/train': 1.416198968887329} 08/31/2021 16:10:09 - INFO - __main__ - Step 148747: {'lr': 8.85637010151208e-08, 'samples': 28559424, 'steps': 148746, 'loss/train': 1.3953876495361328} 08/31/2021 16:10:09 - INFO - __main__ - Step 148748: {'lr': 8.842251573670802e-08, 'samples': 28559616, 'steps': 148747, 'loss/train': 1.3381487131118774} 08/31/2021 16:10:10 - INFO - __main__ - Step 148749: {'lr': 8.828144306460839e-08, 'samples': 28559808, 'steps': 148748, 'loss/train': 1.2736616134643555} 08/31/2021 16:10:10 - INFO - __main__ - Step 148750: {'lr': 8.814048299884969e-08, 'samples': 28560000, 'steps': 148749, 'loss/train': 1.22115159034729} 08/31/2021 16:10:10 - INFO - __main__ - Step 148751: {'lr': 8.799963553954293e-08, 'samples': 28560192, 'steps': 148750, 'loss/train': 0.7931817770004272} 08/31/2021 16:10:13 - INFO - __main__ - Step 148752: {'lr': 8.785890068671587e-08, 'samples': 28560384, 'steps': 148751, 'loss/train': 0.49032458662986755} 08/31/2021 16:10:13 - INFO - __main__ - Step 148753: {'lr': 8.771827844042401e-08, 'samples': 28560576, 'steps': 148752, 'loss/train': 1.7185413837432861} 08/31/2021 16:10:14 - INFO - __main__ - Step 148754: {'lr': 8.75777688007784e-08, 'samples': 28560768, 'steps': 148753, 'loss/train': 1.4287010431289673} 08/31/2021 16:10:14 - INFO - __main__ - Step 148755: {'lr': 8.743737176780675e-08, 'samples': 28560960, 'steps': 148754, 'loss/train': 1.3861801624298096} 08/31/2021 16:10:14 - INFO - __main__ - Step 148756: {'lr': 8.729708734156461e-08, 'samples': 28561152, 'steps': 148755, 'loss/train': 1.5057733058929443} 08/31/2021 16:10:15 - INFO - __main__ - Step 148757: {'lr': 8.715691552216298e-08, 'samples': 28561344, 'steps': 148756, 'loss/train': 0.8117222189903259} 08/31/2021 16:10:16 - INFO - __main__ - Step 148758: {'lr': 8.701685630960188e-08, 'samples': 28561536, 'steps': 148757, 'loss/train': 0.6449706554412842} 08/31/2021 16:10:17 - INFO - __main__ - Step 148759: {'lr': 8.687690970399231e-08, 'samples': 28561728, 'steps': 148758, 'loss/train': 0.03735357150435448} 08/31/2021 16:10:17 - INFO - __main__ - Step 148760: {'lr': 8.673707570536204e-08, 'samples': 28561920, 'steps': 148759, 'loss/train': 0.9283035397529602} 08/31/2021 16:10:17 - INFO - __main__ - Step 148761: {'lr': 8.659735431379435e-08, 'samples': 28562112, 'steps': 148760, 'loss/train': 0.8531557321548462} 08/31/2021 16:10:18 - INFO - __main__ - Step 148762: {'lr': 8.645774552937246e-08, 'samples': 28562304, 'steps': 148761, 'loss/train': 0.11019258201122284} 08/31/2021 16:10:19 - INFO - __main__ - Step 148763: {'lr': 8.631824935212418e-08, 'samples': 28562496, 'steps': 148762, 'loss/train': 1.0007874965667725} 08/31/2021 16:10:20 - INFO - __main__ - Step 148764: {'lr': 8.6178865782105e-08, 'samples': 28562688, 'steps': 148763, 'loss/train': 0.9125156402587891} 08/31/2021 16:10:20 - INFO - __main__ - Step 148765: {'lr': 8.603959481942591e-08, 'samples': 28562880, 'steps': 148764, 'loss/train': 1.1072123050689697} 08/31/2021 16:10:20 - INFO - __main__ - Step 148766: {'lr': 8.590043646408696e-08, 'samples': 28563072, 'steps': 148765, 'loss/train': 1.100662112236023} 08/31/2021 16:10:21 - INFO - __main__ - Step 148767: {'lr': 8.57613907162269e-08, 'samples': 28563264, 'steps': 148766, 'loss/train': 1.3964625597000122} 08/31/2021 16:10:21 - INFO - __main__ - Step 148768: {'lr': 8.562245757584574e-08, 'samples': 28563456, 'steps': 148767, 'loss/train': 0.6705144643783569} 08/31/2021 16:10:23 - INFO - __main__ - Step 148769: {'lr': 8.548363704302675e-08, 'samples': 28563648, 'steps': 148768, 'loss/train': 0.8545612096786499} 08/31/2021 16:10:23 - INFO - __main__ - Step 148770: {'lr': 8.534492911782543e-08, 'samples': 28563840, 'steps': 148769, 'loss/train': 0.6986938118934631} 08/31/2021 16:10:24 - INFO - __main__ - Step 148771: {'lr': 8.520633380032505e-08, 'samples': 28564032, 'steps': 148770, 'loss/train': 1.7524418830871582} 08/31/2021 16:10:24 - INFO - __main__ - Step 148772: {'lr': 8.506785109055337e-08, 'samples': 28564224, 'steps': 148771, 'loss/train': 0.7467144727706909} 08/31/2021 16:10:25 - INFO - __main__ - Step 148773: {'lr': 8.492948098859366e-08, 'samples': 28564416, 'steps': 148772, 'loss/train': 1.3358296155929565} 08/31/2021 16:10:26 - INFO - __main__ - Step 148774: {'lr': 8.479122349452917e-08, 'samples': 28564608, 'steps': 148773, 'loss/train': 1.0206750631332397} 08/31/2021 16:10:26 - INFO - __main__ - Step 148775: {'lr': 8.465307860838766e-08, 'samples': 28564800, 'steps': 148774, 'loss/train': 0.7709123492240906} 08/31/2021 16:10:27 - INFO - __main__ - Step 148776: {'lr': 8.451504633025242e-08, 'samples': 28564992, 'steps': 148775, 'loss/train': 1.780118465423584} 08/31/2021 16:10:27 - INFO - __main__ - Step 148777: {'lr': 8.437712666017894e-08, 'samples': 28565184, 'steps': 148776, 'loss/train': 1.5255208015441895} 08/31/2021 16:10:28 - INFO - __main__ - Step 148778: {'lr': 8.423931959822273e-08, 'samples': 28565376, 'steps': 148777, 'loss/train': 0.7376360297203064} 08/31/2021 16:10:29 - INFO - __main__ - Step 148779: {'lr': 8.410162514446706e-08, 'samples': 28565568, 'steps': 148778, 'loss/train': 1.1175774335861206} 08/31/2021 16:10:29 - INFO - __main__ - Step 148780: {'lr': 8.396404329893969e-08, 'samples': 28565760, 'steps': 148779, 'loss/train': 1.1229281425476074} 08/31/2021 16:10:30 - INFO - __main__ - Step 148781: {'lr': 8.382657406175164e-08, 'samples': 28565952, 'steps': 148780, 'loss/train': 0.054407890886068344} 08/31/2021 16:10:30 - INFO - __main__ - Step 148782: {'lr': 8.368921743290292e-08, 'samples': 28566144, 'steps': 148781, 'loss/train': 1.5206598043441772} 08/31/2021 16:10:31 - INFO - __main__ - Step 148783: {'lr': 8.355197341250453e-08, 'samples': 28566336, 'steps': 148782, 'loss/train': 0.943060576915741} 08/31/2021 16:10:31 - INFO - __main__ - Step 148784: {'lr': 8.341484200058425e-08, 'samples': 28566528, 'steps': 148783, 'loss/train': 0.7598454356193542} 08/31/2021 16:10:33 - INFO - __main__ - Step 148785: {'lr': 8.327782319722533e-08, 'samples': 28566720, 'steps': 148784, 'loss/train': 0.9846994280815125} 08/31/2021 16:10:33 - INFO - __main__ - Step 148786: {'lr': 8.314091700248327e-08, 'samples': 28566912, 'steps': 148785, 'loss/train': 0.8886184096336365} 08/31/2021 16:10:33 - INFO - __main__ - Step 148787: {'lr': 8.300412341644137e-08, 'samples': 28567104, 'steps': 148786, 'loss/train': 1.1274782419204712} 08/31/2021 16:10:34 - INFO - __main__ - Step 148788: {'lr': 8.286744243912736e-08, 'samples': 28567296, 'steps': 148787, 'loss/train': 1.1549444198608398} 08/31/2021 16:10:34 - INFO - __main__ - Step 148789: {'lr': 8.273087407062452e-08, 'samples': 28567488, 'steps': 148788, 'loss/train': 1.181632161140442} 08/31/2021 16:10:36 - INFO - __main__ - Step 148790: {'lr': 8.259441831096059e-08, 'samples': 28567680, 'steps': 148789, 'loss/train': 0.7149519324302673} 08/31/2021 16:10:36 - INFO - __main__ - Step 148791: {'lr': 8.245807516024662e-08, 'samples': 28567872, 'steps': 148790, 'loss/train': 0.7715359926223755} 08/31/2021 16:10:37 - INFO - __main__ - Step 148792: {'lr': 8.232184461853808e-08, 'samples': 28568064, 'steps': 148791, 'loss/train': 1.0959010124206543} 08/31/2021 16:10:37 - INFO - __main__ - Step 148793: {'lr': 8.218572668583501e-08, 'samples': 28568256, 'steps': 148792, 'loss/train': 1.2082608938217163} 08/31/2021 16:10:37 - INFO - __main__ - Step 148794: {'lr': 8.204972136227618e-08, 'samples': 28568448, 'steps': 148793, 'loss/train': 0.5260429978370667} 08/31/2021 16:10:39 - INFO - __main__ - Step 148795: {'lr': 8.191382864788932e-08, 'samples': 28568640, 'steps': 148794, 'loss/train': 0.31803619861602783} 08/31/2021 16:10:40 - INFO - __main__ - Step 148796: {'lr': 8.177804854270221e-08, 'samples': 28568832, 'steps': 148795, 'loss/train': 0.014254039153456688} 08/31/2021 16:10:40 - INFO - __main__ - Step 148797: {'lr': 8.164238104685362e-08, 'samples': 28569024, 'steps': 148796, 'loss/train': 0.014694967307150364} 08/31/2021 16:10:41 - INFO - __main__ - Step 148798: {'lr': 8.150682616031579e-08, 'samples': 28569216, 'steps': 148797, 'loss/train': 0.8596964478492737} 08/31/2021 16:10:41 - INFO - __main__ - Step 148799: {'lr': 8.13713838832275e-08, 'samples': 28569408, 'steps': 148798, 'loss/train': 1.3426579236984253} 08/31/2021 16:10:41 - INFO - __main__ - Step 148800: {'lr': 8.123605421561652e-08, 'samples': 28569600, 'steps': 148799, 'loss/train': 0.3733118176460266} 08/31/2021 16:10:42 - INFO - __main__ - Step 148801: {'lr': 8.11008371575106e-08, 'samples': 28569792, 'steps': 148800, 'loss/train': 0.6952461004257202} 08/31/2021 16:10:43 - INFO - __main__ - Step 148802: {'lr': 8.09657327090485e-08, 'samples': 28569984, 'steps': 148801, 'loss/train': 0.25805848836898804} 08/31/2021 16:10:44 - INFO - __main__ - Step 148803: {'lr': 8.083074087023023e-08, 'samples': 28570176, 'steps': 148802, 'loss/train': 1.0272189378738403} 08/31/2021 16:10:44 - INFO - __main__ - Step 148804: {'lr': 8.069586164111132e-08, 'samples': 28570368, 'steps': 148803, 'loss/train': 0.7200711965560913} 08/31/2021 16:10:44 - INFO - __main__ - Step 148805: {'lr': 8.056109502180275e-08, 'samples': 28570560, 'steps': 148804, 'loss/train': 1.0831093788146973} 08/31/2021 16:10:45 - INFO - __main__ - Step 148806: {'lr': 8.042644101233232e-08, 'samples': 28570752, 'steps': 148805, 'loss/train': 1.083182454109192} 08/31/2021 16:10:46 - INFO - __main__ - Step 148807: {'lr': 8.029189961275551e-08, 'samples': 28570944, 'steps': 148806, 'loss/train': 1.3993033170700073} 08/31/2021 16:10:47 - INFO - __main__ - Step 148808: {'lr': 8.015747082312786e-08, 'samples': 28571136, 'steps': 148807, 'loss/train': 1.0153541564941406} 08/31/2021 16:10:47 - INFO - __main__ - Step 148809: {'lr': 8.002315464356036e-08, 'samples': 28571328, 'steps': 148808, 'loss/train': 0.7451040744781494} 08/31/2021 16:10:47 - INFO - __main__ - Step 148810: {'lr': 7.988895107405302e-08, 'samples': 28571520, 'steps': 148809, 'loss/train': 1.0807209014892578} 08/31/2021 16:10:48 - INFO - __main__ - Step 148811: {'lr': 7.975486011468913e-08, 'samples': 28571712, 'steps': 148810, 'loss/train': 0.8658995628356934} 08/31/2021 16:10:49 - INFO - __main__ - Step 148812: {'lr': 7.962088176555194e-08, 'samples': 28571904, 'steps': 148811, 'loss/train': 0.8843149542808533} 08/31/2021 16:10:50 - INFO - __main__ - Step 148813: {'lr': 7.948701602666918e-08, 'samples': 28572096, 'steps': 148812, 'loss/train': 0.5610803365707397} 08/31/2021 16:10:50 - INFO - __main__ - Step 148814: {'lr': 7.935326289812417e-08, 'samples': 28572288, 'steps': 148813, 'loss/train': 0.027046412229537964} 08/31/2021 16:10:50 - INFO - __main__ - Step 148815: {'lr': 7.921962237994462e-08, 'samples': 28572480, 'steps': 148814, 'loss/train': 1.2306642532348633} 08/31/2021 16:10:51 - INFO - __main__ - Step 148816: {'lr': 7.908609447221382e-08, 'samples': 28572672, 'steps': 148815, 'loss/train': 1.6918413639068604} 08/31/2021 16:10:52 - INFO - __main__ - Step 148817: {'lr': 7.895267917501503e-08, 'samples': 28572864, 'steps': 148816, 'loss/train': 0.9461345076560974} 08/31/2021 16:10:53 - INFO - __main__ - Step 148818: {'lr': 7.881937648834824e-08, 'samples': 28573056, 'steps': 148817, 'loss/train': 1.1736217737197876} 08/31/2021 16:10:53 - INFO - __main__ - Step 148819: {'lr': 7.868618641235226e-08, 'samples': 28573248, 'steps': 148818, 'loss/train': 1.3855229616165161} 08/31/2021 16:10:54 - INFO - __main__ - Step 148820: {'lr': 7.85531089469993e-08, 'samples': 28573440, 'steps': 148819, 'loss/train': 1.2420761585235596} 08/31/2021 16:10:54 - INFO - __main__ - Step 148821: {'lr': 7.842014409242815e-08, 'samples': 28573632, 'steps': 148820, 'loss/train': 0.7708941698074341} 08/31/2021 16:10:54 - INFO - __main__ - Step 148822: {'lr': 7.82872918486388e-08, 'samples': 28573824, 'steps': 148821, 'loss/train': 1.581626296043396} 08/31/2021 16:10:56 - INFO - __main__ - Step 148823: {'lr': 7.81545522157423e-08, 'samples': 28574016, 'steps': 148822, 'loss/train': 1.8524121046066284} 08/31/2021 16:10:57 - INFO - __main__ - Step 148824: {'lr': 7.802192519376638e-08, 'samples': 28574208, 'steps': 148823, 'loss/train': 0.9164565205574036} 08/31/2021 16:10:57 - INFO - __main__ - Step 148825: {'lr': 7.788941078276657e-08, 'samples': 28574400, 'steps': 148824, 'loss/train': 1.9908671379089355} 08/31/2021 16:10:58 - INFO - __main__ - Step 148826: {'lr': 7.775700898279835e-08, 'samples': 28574592, 'steps': 148825, 'loss/train': 0.6584232449531555} 08/31/2021 16:10:58 - INFO - __main__ - Step 148827: {'lr': 7.762471979397279e-08, 'samples': 28574784, 'steps': 148826, 'loss/train': 1.4061843156814575} 08/31/2021 16:11:00 - INFO - __main__ - Step 148828: {'lr': 7.749254321628985e-08, 'samples': 28574976, 'steps': 148827, 'loss/train': 0.8447316288948059} 08/31/2021 16:11:00 - INFO - __main__ - Step 148829: {'lr': 7.736047924983281e-08, 'samples': 28575168, 'steps': 148828, 'loss/train': 0.2714291214942932} 08/31/2021 16:11:00 - INFO - __main__ - Step 148830: {'lr': 7.722852789465718e-08, 'samples': 28575360, 'steps': 148829, 'loss/train': 0.8908082842826843} 08/31/2021 16:11:01 - INFO - __main__ - Step 148831: {'lr': 7.709668915084622e-08, 'samples': 28575552, 'steps': 148830, 'loss/train': 1.165263056755066} 08/31/2021 16:11:01 - INFO - __main__ - Step 148832: {'lr': 7.69649630184277e-08, 'samples': 28575744, 'steps': 148831, 'loss/train': 0.9899460077285767} 08/31/2021 16:11:03 - INFO - __main__ - Step 148833: {'lr': 7.683334949745712e-08, 'samples': 28575936, 'steps': 148832, 'loss/train': 0.035794731229543686} 08/31/2021 16:11:03 - INFO - __main__ - Step 148834: {'lr': 7.670184858804552e-08, 'samples': 28576128, 'steps': 148833, 'loss/train': 0.5948514342308044} 08/31/2021 16:11:04 - INFO - __main__ - Step 148835: {'lr': 7.657046029019288e-08, 'samples': 28576320, 'steps': 148834, 'loss/train': 0.9358752369880676} 08/31/2021 16:11:04 - INFO - __main__ - Step 148836: {'lr': 7.643918460398247e-08, 'samples': 28576512, 'steps': 148835, 'loss/train': 0.8186376690864563} 08/31/2021 16:11:05 - INFO - __main__ - Step 148837: {'lr': 7.630802152946981e-08, 'samples': 28576704, 'steps': 148836, 'loss/train': 0.014674182049930096} 08/31/2021 16:11:05 - INFO - __main__ - Step 148838: {'lr': 7.61769710667104e-08, 'samples': 28576896, 'steps': 148837, 'loss/train': 0.9260375499725342} 08/31/2021 16:11:06 - INFO - __main__ - Step 148839: {'lr': 7.604603321575976e-08, 'samples': 28577088, 'steps': 148838, 'loss/train': 1.9124884605407715} 08/31/2021 16:11:07 - INFO - __main__ - Step 148840: {'lr': 7.591520797670116e-08, 'samples': 28577280, 'steps': 148839, 'loss/train': 1.1043570041656494} 08/31/2021 16:11:07 - INFO - __main__ - Step 148841: {'lr': 7.578449534959009e-08, 'samples': 28577472, 'steps': 148840, 'loss/train': 1.5014268159866333} 08/31/2021 16:11:08 - INFO - __main__ - Step 148842: {'lr': 7.565389533445432e-08, 'samples': 28577664, 'steps': 148841, 'loss/train': 0.5823063254356384} 08/31/2021 16:11:08 - INFO - __main__ - Step 148843: {'lr': 7.552340793140488e-08, 'samples': 28577856, 'steps': 148842, 'loss/train': 0.7840695381164551} 08/31/2021 16:11:08 - INFO - __main__ - Step 148844: {'lr': 7.539303314044177e-08, 'samples': 28578048, 'steps': 148843, 'loss/train': 0.8366817235946655} 08/31/2021 16:11:10 - INFO - __main__ - Step 148845: {'lr': 7.526277096164825e-08, 'samples': 28578240, 'steps': 148844, 'loss/train': 0.4550592303276062} 08/31/2021 16:11:10 - INFO - __main__ - Step 148846: {'lr': 7.513262139507982e-08, 'samples': 28578432, 'steps': 148845, 'loss/train': 1.4125144481658936} 08/31/2021 16:11:11 - INFO - __main__ - Step 148847: {'lr': 7.500258444081976e-08, 'samples': 28578624, 'steps': 148846, 'loss/train': 0.20144768059253693} 08/31/2021 16:11:11 - INFO - __main__ - Step 148848: {'lr': 7.487266009889582e-08, 'samples': 28578816, 'steps': 148847, 'loss/train': 0.07510524988174438} 08/31/2021 16:11:11 - INFO - __main__ - Step 148849: {'lr': 7.474284836936351e-08, 'samples': 28579008, 'steps': 148848, 'loss/train': 1.065017819404602} 08/31/2021 16:11:13 - INFO - __main__ - Step 148850: {'lr': 7.461314925233387e-08, 'samples': 28579200, 'steps': 148849, 'loss/train': 0.8623935580253601} 08/31/2021 16:11:13 - INFO - __main__ - Step 148851: {'lr': 7.448356274777912e-08, 'samples': 28579392, 'steps': 148850, 'loss/train': 1.2715212106704712} 08/31/2021 16:11:14 - INFO - __main__ - Step 148852: {'lr': 7.435408885583806e-08, 'samples': 28579584, 'steps': 148851, 'loss/train': 1.0201704502105713} 08/31/2021 16:11:14 - INFO - __main__ - Step 148853: {'lr': 7.422472757653842e-08, 'samples': 28579776, 'steps': 148852, 'loss/train': 0.5572994947433472} 08/31/2021 16:11:14 - INFO - __main__ - Step 148854: {'lr': 7.409547890993573e-08, 'samples': 28579968, 'steps': 148853, 'loss/train': 1.0539305210113525} 08/31/2021 16:11:16 - INFO - __main__ - Step 148855: {'lr': 7.396634285605775e-08, 'samples': 28580160, 'steps': 148854, 'loss/train': 1.1863157749176025} 08/31/2021 16:11:16 - INFO - __main__ - Step 148856: {'lr': 7.383731941501549e-08, 'samples': 28580352, 'steps': 148855, 'loss/train': 0.35170868039131165} 08/31/2021 16:11:17 - INFO - __main__ - Step 148857: {'lr': 7.370840858686445e-08, 'samples': 28580544, 'steps': 148856, 'loss/train': 0.4551965892314911} 08/31/2021 16:11:17 - INFO - __main__ - Step 148858: {'lr': 7.357961037160466e-08, 'samples': 28580736, 'steps': 148857, 'loss/train': 1.0503345727920532} 08/31/2021 16:11:18 - INFO - __main__ - Step 148859: {'lr': 7.345092476937488e-08, 'samples': 28580928, 'steps': 148858, 'loss/train': 1.6015050411224365} 08/31/2021 16:11:18 - INFO - __main__ - Step 148860: {'lr': 7.332235178014735e-08, 'samples': 28581120, 'steps': 148859, 'loss/train': 1.2033770084381104} 08/31/2021 16:11:19 - INFO - __main__ - Step 148861: {'lr': 7.319389140406086e-08, 'samples': 28581312, 'steps': 148860, 'loss/train': 0.6299179792404175} 08/31/2021 16:11:20 - INFO - __main__ - Step 148862: {'lr': 7.30655436411154e-08, 'samples': 28581504, 'steps': 148861, 'loss/train': 1.3552701473236084} 08/31/2021 16:11:20 - INFO - __main__ - Step 148863: {'lr': 7.293730849139425e-08, 'samples': 28581696, 'steps': 148862, 'loss/train': 1.043883204460144} 08/31/2021 16:11:20 - INFO - __main__ - Step 148864: {'lr': 7.28091859549529e-08, 'samples': 28581888, 'steps': 148863, 'loss/train': 0.8955850005149841} 08/31/2021 16:11:21 - INFO - __main__ - Step 148865: {'lr': 7.268117603187463e-08, 'samples': 28582080, 'steps': 148864, 'loss/train': 0.9161765575408936} 08/31/2021 16:11:22 - INFO - __main__ - Step 148866: {'lr': 7.255327872215945e-08, 'samples': 28582272, 'steps': 148865, 'loss/train': 1.017480731010437} 08/31/2021 16:11:23 - INFO - __main__ - Step 148867: {'lr': 7.24254940258906e-08, 'samples': 28582464, 'steps': 148866, 'loss/train': 0.05458807572722435} 08/31/2021 16:11:23 - INFO - __main__ - Step 148868: {'lr': 7.229782194315138e-08, 'samples': 28582656, 'steps': 148867, 'loss/train': 1.138069748878479} 08/31/2021 16:11:24 - INFO - __main__ - Step 148869: {'lr': 7.217026247396952e-08, 'samples': 28582848, 'steps': 148868, 'loss/train': 0.9204478859901428} 08/31/2021 16:11:24 - INFO - __main__ - Step 148870: {'lr': 7.204281561840054e-08, 'samples': 28583040, 'steps': 148869, 'loss/train': 1.6629323959350586} 08/31/2021 16:11:26 - INFO - __main__ - Step 148871: {'lr': 7.191548137649994e-08, 'samples': 28583232, 'steps': 148870, 'loss/train': 0.9410166144371033} 08/31/2021 16:11:26 - INFO - __main__ - Step 148872: {'lr': 7.178825974837878e-08, 'samples': 28583424, 'steps': 148871, 'loss/train': 0.6051149964332581} 08/31/2021 16:11:27 - INFO - __main__ - Step 148873: {'lr': 7.166115073400925e-08, 'samples': 28583616, 'steps': 148872, 'loss/train': 0.06258133053779602} 08/31/2021 16:11:27 - INFO - __main__ - Step 148874: {'lr': 7.153415433353017e-08, 'samples': 28583808, 'steps': 148873, 'loss/train': 1.1173274517059326} 08/31/2021 16:11:27 - INFO - __main__ - Step 148875: {'lr': 7.140727054694152e-08, 'samples': 28584000, 'steps': 148874, 'loss/train': 0.4689524173736572} 08/31/2021 16:11:28 - INFO - __main__ - Step 148876: {'lr': 7.128049937432657e-08, 'samples': 28584192, 'steps': 148875, 'loss/train': 0.015855595469474792} 08/31/2021 16:11:30 - INFO - __main__ - Step 148877: {'lr': 7.115384081574083e-08, 'samples': 28584384, 'steps': 148876, 'loss/train': 0.9232336282730103} 08/31/2021 16:11:31 - INFO - __main__ - Step 148878: {'lr': 7.102729487121207e-08, 'samples': 28584576, 'steps': 148877, 'loss/train': 1.2591540813446045} 08/31/2021 16:11:31 - INFO - __main__ - Step 148879: {'lr': 7.09008615408513e-08, 'samples': 28584768, 'steps': 148878, 'loss/train': 0.32485485076904297} 08/31/2021 16:11:31 - INFO - __main__ - Step 148880: {'lr': 7.077454082468627e-08, 'samples': 28584960, 'steps': 148879, 'loss/train': 0.7637354135513306} 08/31/2021 16:11:32 - INFO - __main__ - Step 148881: {'lr': 7.064833272274473e-08, 'samples': 28585152, 'steps': 148880, 'loss/train': 0.9899616837501526} 08/31/2021 16:11:33 - INFO - __main__ - Step 148882: {'lr': 7.052223723513774e-08, 'samples': 28585344, 'steps': 148881, 'loss/train': 1.3698537349700928} 08/31/2021 16:11:34 - INFO - __main__ - Step 148883: {'lr': 7.039625436189301e-08, 'samples': 28585536, 'steps': 148882, 'loss/train': 1.1450446844100952} 08/31/2021 16:11:34 - INFO - __main__ - Step 148884: {'lr': 7.027038410306608e-08, 'samples': 28585728, 'steps': 148883, 'loss/train': 0.2988094091415405} 08/31/2021 16:11:35 - INFO - __main__ - Step 148885: {'lr': 7.014462645871244e-08, 'samples': 28585920, 'steps': 148884, 'loss/train': 1.1787474155426025} 08/31/2021 16:11:35 - INFO - __main__ - Step 148886: {'lr': 7.001898142888763e-08, 'samples': 28586112, 'steps': 148885, 'loss/train': 1.1050095558166504} 08/31/2021 16:11:35 - INFO - __main__ - Step 148887: {'lr': 6.989344901367489e-08, 'samples': 28586304, 'steps': 148886, 'loss/train': 1.2138583660125732} 08/31/2021 16:11:37 - INFO - __main__ - Step 148888: {'lr': 6.9768029213102e-08, 'samples': 28586496, 'steps': 148887, 'loss/train': 0.01591910794377327} 08/31/2021 16:11:37 - INFO - __main__ - Step 148889: {'lr': 6.96427220272522e-08, 'samples': 28586688, 'steps': 148888, 'loss/train': 1.6645883321762085} 08/31/2021 16:11:38 - INFO - __main__ - Step 148890: {'lr': 6.951752745615325e-08, 'samples': 28586880, 'steps': 148889, 'loss/train': 2.575498104095459} 08/31/2021 16:11:38 - INFO - __main__ - Step 148891: {'lr': 6.939244549986068e-08, 'samples': 28587072, 'steps': 148890, 'loss/train': 1.095457673072815} 08/31/2021 16:11:38 - INFO - __main__ - Step 148892: {'lr': 6.926747615845775e-08, 'samples': 28587264, 'steps': 148891, 'loss/train': 1.2176085710525513} 08/31/2021 16:11:39 - INFO - __main__ - Step 148893: {'lr': 6.91426194319722e-08, 'samples': 28587456, 'steps': 148892, 'loss/train': 1.4351023435592651} 08/31/2021 16:11:40 - INFO - __main__ - Step 148894: {'lr': 6.901787532048732e-08, 'samples': 28587648, 'steps': 148893, 'loss/train': 1.0039584636688232} 08/31/2021 16:11:41 - INFO - __main__ - Step 148895: {'lr': 6.88932438240586e-08, 'samples': 28587840, 'steps': 148894, 'loss/train': 1.6821651458740234} 08/31/2021 16:11:41 - INFO - __main__ - Step 148896: {'lr': 6.87687249427138e-08, 'samples': 28588032, 'steps': 148895, 'loss/train': 1.36106276512146} 08/31/2021 16:11:41 - INFO - __main__ - Step 148897: {'lr': 6.864431867650844e-08, 'samples': 28588224, 'steps': 148896, 'loss/train': 0.6871134042739868} 08/31/2021 16:11:42 - INFO - __main__ - Step 148898: {'lr': 6.852002502555355e-08, 'samples': 28588416, 'steps': 148897, 'loss/train': 0.9375991225242615} 08/31/2021 16:11:43 - INFO - __main__ - Step 148899: {'lr': 6.839584398982135e-08, 'samples': 28588608, 'steps': 148898, 'loss/train': 1.3749157190322876} 08/31/2021 16:11:44 - INFO - __main__ - Step 148900: {'lr': 6.827177556945064e-08, 'samples': 28588800, 'steps': 148899, 'loss/train': 0.9262028932571411} 08/31/2021 16:11:44 - INFO - __main__ - Step 148901: {'lr': 6.81478197644414e-08, 'samples': 28588992, 'steps': 148900, 'loss/train': 1.4668911695480347} 08/31/2021 16:11:44 - INFO - __main__ - Step 148902: {'lr': 6.802397657487691e-08, 'samples': 28589184, 'steps': 148901, 'loss/train': 0.11681091040372849} 08/31/2021 16:11:45 - INFO - __main__ - Step 148903: {'lr': 6.790024600081269e-08, 'samples': 28589376, 'steps': 148902, 'loss/train': 1.0481302738189697} 08/31/2021 16:11:46 - INFO - __main__ - Step 148904: {'lr': 6.777662804227647e-08, 'samples': 28589568, 'steps': 148903, 'loss/train': 1.2971758842468262} 08/31/2021 16:11:47 - INFO - __main__ - Step 148905: {'lr': 6.765312269935153e-08, 'samples': 28589760, 'steps': 148904, 'loss/train': 0.9779314994812012} 08/31/2021 16:11:47 - INFO - __main__ - Step 148906: {'lr': 6.752972997209338e-08, 'samples': 28589952, 'steps': 148905, 'loss/train': 1.0903446674346924} 08/31/2021 16:11:48 - INFO - __main__ - Step 148907: {'lr': 6.74064498605298e-08, 'samples': 28590144, 'steps': 148906, 'loss/train': 0.969416618347168} 08/31/2021 16:11:48 - INFO - __main__ - Step 148908: {'lr': 6.728328236474402e-08, 'samples': 28590336, 'steps': 148907, 'loss/train': 1.5130422115325928} 08/31/2021 16:11:49 - INFO - __main__ - Step 148909: {'lr': 6.716022748479156e-08, 'samples': 28590528, 'steps': 148908, 'loss/train': 2.0398330688476562} 08/31/2021 16:11:50 - INFO - __main__ - Step 148910: {'lr': 6.703728522072794e-08, 'samples': 28590720, 'steps': 148909, 'loss/train': 0.8973042368888855} 08/31/2021 16:11:50 - INFO - __main__ - Step 148911: {'lr': 6.691445557258091e-08, 'samples': 28590912, 'steps': 148910, 'loss/train': 1.0469369888305664} 08/31/2021 16:11:51 - INFO - __main__ - Step 148912: {'lr': 6.679173854043374e-08, 'samples': 28591104, 'steps': 148911, 'loss/train': 1.2547812461853027} 08/31/2021 16:11:51 - INFO - __main__ - Step 148913: {'lr': 6.666913412434194e-08, 'samples': 28591296, 'steps': 148912, 'loss/train': 0.6492270827293396} 08/31/2021 16:11:51 - INFO - __main__ - Step 148914: {'lr': 6.654664232433328e-08, 'samples': 28591488, 'steps': 148913, 'loss/train': 0.36769285798072815} 08/31/2021 16:11:53 - INFO - __main__ - Step 148915: {'lr': 6.642426314049099e-08, 'samples': 28591680, 'steps': 148914, 'loss/train': 0.27537107467651367} 08/31/2021 16:11:53 - INFO - __main__ - Step 148916: {'lr': 6.630199657287061e-08, 'samples': 28591872, 'steps': 148915, 'loss/train': 1.117913842201233} 08/31/2021 16:11:54 - INFO - __main__ - Step 148917: {'lr': 6.61798426214999e-08, 'samples': 28592064, 'steps': 148916, 'loss/train': 0.6738137006759644} 08/31/2021 16:11:54 - INFO - __main__ - Step 148918: {'lr': 6.605780128646211e-08, 'samples': 28592256, 'steps': 148917, 'loss/train': 1.2751307487487793} 08/31/2021 16:11:54 - INFO - __main__ - Step 148919: {'lr': 6.593587256781275e-08, 'samples': 28592448, 'steps': 148918, 'loss/train': 1.2678331136703491} 08/31/2021 16:11:56 - INFO - __main__ - Step 148920: {'lr': 6.581405646557959e-08, 'samples': 28592640, 'steps': 148919, 'loss/train': 0.2806331217288971} 08/31/2021 16:11:56 - INFO - __main__ - Step 148921: {'lr': 6.569235297984588e-08, 'samples': 28592832, 'steps': 148920, 'loss/train': 1.3482595682144165} 08/31/2021 16:11:57 - INFO - __main__ - Step 148922: {'lr': 6.557076211063939e-08, 'samples': 28593024, 'steps': 148921, 'loss/train': 0.24379906058311462} 08/31/2021 16:11:57 - INFO - __main__ - Step 148923: {'lr': 6.544928385804338e-08, 'samples': 28593216, 'steps': 148922, 'loss/train': 1.2737540006637573} 08/31/2021 16:11:57 - INFO - __main__ - Step 148924: {'lr': 6.532791822208561e-08, 'samples': 28593408, 'steps': 148923, 'loss/train': 1.1780035495758057} 08/31/2021 16:11:59 - INFO - __main__ - Step 148925: {'lr': 6.520666520284934e-08, 'samples': 28593600, 'steps': 148924, 'loss/train': 0.2473890781402588} 08/31/2021 16:11:59 - INFO - __main__ - Step 148926: {'lr': 6.508552480036234e-08, 'samples': 28593792, 'steps': 148925, 'loss/train': 1.180213451385498} 08/31/2021 16:12:00 - INFO - __main__ - Step 148927: {'lr': 6.49644970146801e-08, 'samples': 28593984, 'steps': 148926, 'loss/train': 1.7331656217575073} 08/31/2021 16:12:00 - INFO - __main__ - Step 148928: {'lr': 6.48435818458859e-08, 'samples': 28594176, 'steps': 148927, 'loss/train': 0.8757672905921936} 08/31/2021 16:12:00 - INFO - __main__ - Step 148929: {'lr': 6.472277929403525e-08, 'samples': 28594368, 'steps': 148928, 'loss/train': 0.8225656151771545} 08/31/2021 16:12:02 - INFO - __main__ - Step 148930: {'lr': 6.460208935912814e-08, 'samples': 28594560, 'steps': 148929, 'loss/train': 1.1670756340026855} 08/31/2021 16:12:02 - INFO - __main__ - Step 148931: {'lr': 6.448151204127561e-08, 'samples': 28594752, 'steps': 148930, 'loss/train': 0.5073421597480774} 08/31/2021 16:12:03 - INFO - __main__ - Step 148932: {'lr': 6.436104734050541e-08, 'samples': 28594944, 'steps': 148931, 'loss/train': 1.5612590312957764} 08/31/2021 16:12:03 - INFO - __main__ - Step 148933: {'lr': 6.424069525687304e-08, 'samples': 28595136, 'steps': 148932, 'loss/train': 0.9503674507141113} 08/31/2021 16:12:03 - INFO - __main__ - Step 148934: {'lr': 6.412045579043402e-08, 'samples': 28595328, 'steps': 148933, 'loss/train': 0.8426272869110107} 08/31/2021 16:12:06 - INFO - __main__ - Step 148935: {'lr': 6.400032894127161e-08, 'samples': 28595520, 'steps': 148934, 'loss/train': 0.08953966945409775} 08/31/2021 16:12:06 - INFO - __main__ - Step 148936: {'lr': 6.388031470938582e-08, 'samples': 28595712, 'steps': 148935, 'loss/train': 0.8128765821456909} 08/31/2021 16:12:06 - INFO - __main__ - Step 148937: {'lr': 6.376041309485992e-08, 'samples': 28595904, 'steps': 148936, 'loss/train': 1.0492480993270874} 08/31/2021 16:12:07 - INFO - __main__ - Step 148938: {'lr': 6.364062409777716e-08, 'samples': 28596096, 'steps': 148937, 'loss/train': 5.682063102722168} 08/31/2021 16:12:07 - INFO - __main__ - Step 148939: {'lr': 6.352094771813754e-08, 'samples': 28596288, 'steps': 148938, 'loss/train': 1.5133556127548218} 08/31/2021 16:12:08 - INFO - __main__ - Step 148940: {'lr': 6.340138395599659e-08, 'samples': 28596480, 'steps': 148939, 'loss/train': 0.9885678887367249} 08/31/2021 16:12:09 - INFO - __main__ - Step 148941: {'lr': 6.328193281146532e-08, 'samples': 28596672, 'steps': 148940, 'loss/train': 1.431917428970337} 08/31/2021 16:12:10 - INFO - __main__ - Step 148942: {'lr': 6.316259428454374e-08, 'samples': 28596864, 'steps': 148941, 'loss/train': 0.461620569229126} 08/31/2021 16:12:10 - INFO - __main__ - Step 148943: {'lr': 6.30433683753151e-08, 'samples': 28597056, 'steps': 148942, 'loss/train': 0.959169328212738} 08/31/2021 16:12:10 - INFO - __main__ - Step 148944: {'lr': 6.292425508383493e-08, 'samples': 28597248, 'steps': 148943, 'loss/train': 0.769020140171051} 08/31/2021 16:12:11 - INFO - __main__ - Step 148945: {'lr': 6.280525441010321e-08, 'samples': 28597440, 'steps': 148944, 'loss/train': 1.060842514038086} 08/31/2021 16:12:12 - INFO - __main__ - Step 148946: {'lr': 6.268636635425873e-08, 'samples': 28597632, 'steps': 148945, 'loss/train': 1.1742039918899536} 08/31/2021 16:12:13 - INFO - __main__ - Step 148947: {'lr': 6.256759091627372e-08, 'samples': 28597824, 'steps': 148946, 'loss/train': 1.1067984104156494} 08/31/2021 16:12:13 - INFO - __main__ - Step 148948: {'lr': 6.244892809625924e-08, 'samples': 28598016, 'steps': 148947, 'loss/train': 1.6498879194259644} 08/31/2021 16:12:13 - INFO - __main__ - Step 148949: {'lr': 6.233037789424301e-08, 'samples': 28598208, 'steps': 148948, 'loss/train': 0.8631417751312256} 08/31/2021 16:12:14 - INFO - __main__ - Step 148950: {'lr': 6.22119403103083e-08, 'samples': 28598400, 'steps': 148949, 'loss/train': 1.3119945526123047} 08/31/2021 16:12:15 - INFO - __main__ - Step 148951: {'lr': 6.209361534445513e-08, 'samples': 28598592, 'steps': 148950, 'loss/train': 0.4121369421482086} 08/31/2021 16:12:16 - INFO - __main__ - Step 148952: {'lr': 6.197540299676673e-08, 'samples': 28598784, 'steps': 148951, 'loss/train': 1.3305761814117432} 08/31/2021 16:12:16 - INFO - __main__ - Step 148953: {'lr': 6.185730326729866e-08, 'samples': 28598976, 'steps': 148952, 'loss/train': 1.364486575126648} 08/31/2021 16:12:16 - INFO - __main__ - Step 148954: {'lr': 6.17393161561064e-08, 'samples': 28599168, 'steps': 148953, 'loss/train': 1.5307625532150269} 08/31/2021 16:12:17 - INFO - __main__ - Step 148955: {'lr': 6.162144166324546e-08, 'samples': 28599360, 'steps': 148954, 'loss/train': 1.0715879201889038} 08/31/2021 16:12:17 - INFO - __main__ - Step 148956: {'lr': 6.15036797887436e-08, 'samples': 28599552, 'steps': 148955, 'loss/train': 1.7934062480926514} 08/31/2021 16:12:19 - INFO - __main__ - Step 148957: {'lr': 6.13860305326841e-08, 'samples': 28599744, 'steps': 148956, 'loss/train': 0.7710332274436951} 08/31/2021 16:12:19 - INFO - __main__ - Step 148958: {'lr': 6.12684938950947e-08, 'samples': 28599936, 'steps': 148957, 'loss/train': 0.7585294842720032} 08/31/2021 16:12:19 - INFO - __main__ - Step 148959: {'lr': 6.115106987605868e-08, 'samples': 28600128, 'steps': 148958, 'loss/train': 0.3887646794319153} 08/31/2021 16:12:20 - INFO - __main__ - Step 148960: {'lr': 6.103375847560377e-08, 'samples': 28600320, 'steps': 148959, 'loss/train': 0.8809558749198914} 08/31/2021 16:12:20 - INFO - __main__ - Step 148961: {'lr': 6.091655969378551e-08, 'samples': 28600512, 'steps': 148960, 'loss/train': 1.1558072566986084} 08/31/2021 16:12:22 - INFO - __main__ - Step 148962: {'lr': 6.07994735306594e-08, 'samples': 28600704, 'steps': 148961, 'loss/train': 0.9881504774093628} 08/31/2021 16:12:22 - INFO - __main__ - Step 148963: {'lr': 6.068249998628095e-08, 'samples': 28600896, 'steps': 148962, 'loss/train': 1.1681016683578491} 08/31/2021 16:12:22 - INFO - __main__ - Step 148964: {'lr': 6.056563906070566e-08, 'samples': 28601088, 'steps': 148963, 'loss/train': 1.196584939956665} 08/31/2021 16:12:23 - INFO - __main__ - Step 148965: {'lr': 6.044889075398908e-08, 'samples': 28601280, 'steps': 148964, 'loss/train': 1.289954423904419} 08/31/2021 16:12:23 - INFO - __main__ - Step 148966: {'lr': 6.033225506618666e-08, 'samples': 28601472, 'steps': 148965, 'loss/train': 1.200754165649414} 08/31/2021 16:12:25 - INFO - __main__ - Step 148967: {'lr': 6.021573199732622e-08, 'samples': 28601664, 'steps': 148966, 'loss/train': 1.1781178712844849} 08/31/2021 16:12:25 - INFO - __main__ - Step 148968: {'lr': 6.009932154746323e-08, 'samples': 28601856, 'steps': 148967, 'loss/train': 0.43575963377952576} 08/31/2021 16:12:25 - INFO - __main__ - Step 148969: {'lr': 5.998302371668096e-08, 'samples': 28602048, 'steps': 148968, 'loss/train': 0.207422137260437} 08/31/2021 16:12:26 - INFO - __main__ - Step 148970: {'lr': 5.986683850500718e-08, 'samples': 28602240, 'steps': 148969, 'loss/train': 1.141274333000183} 08/31/2021 16:12:26 - INFO - __main__ - Step 148971: {'lr': 5.97507659124974e-08, 'samples': 28602432, 'steps': 148970, 'loss/train': 1.471240520477295} 08/31/2021 16:12:28 - INFO - __main__ - Step 148972: {'lr': 5.963480593920711e-08, 'samples': 28602624, 'steps': 148971, 'loss/train': 0.059284619987010956} 08/31/2021 16:12:28 - INFO - __main__ - Step 148973: {'lr': 5.9518958585191854e-08, 'samples': 28602816, 'steps': 148972, 'loss/train': 1.161665678024292} 08/31/2021 16:12:28 - INFO - __main__ - Step 148974: {'lr': 5.9403223850507113e-08, 'samples': 28603008, 'steps': 148973, 'loss/train': 0.629358172416687} 08/31/2021 16:12:29 - INFO - __main__ - Step 148975: {'lr': 5.928760173518066e-08, 'samples': 28603200, 'steps': 148974, 'loss/train': 1.2894984483718872} 08/31/2021 16:12:29 - INFO - __main__ - Step 148976: {'lr': 5.917209223929576e-08, 'samples': 28603392, 'steps': 148975, 'loss/train': 1.1515445709228516} 08/31/2021 16:12:31 - INFO - __main__ - Step 148977: {'lr': 5.905669536290792e-08, 'samples': 28603584, 'steps': 148976, 'loss/train': 1.0581742525100708} 08/31/2021 16:12:31 - INFO - __main__ - Step 148978: {'lr': 5.894141110601714e-08, 'samples': 28603776, 'steps': 148977, 'loss/train': 1.1651761531829834} 08/31/2021 16:12:32 - INFO - __main__ - Step 148979: {'lr': 5.882623946873444e-08, 'samples': 28603968, 'steps': 148978, 'loss/train': 0.9137735962867737} 08/31/2021 16:12:32 - INFO - __main__ - Step 148980: {'lr': 5.871118045108759e-08, 'samples': 28604160, 'steps': 148979, 'loss/train': 0.09451430290937424} 08/31/2021 16:12:32 - INFO - __main__ - Step 148981: {'lr': 5.8596234053104326e-08, 'samples': 28604352, 'steps': 148980, 'loss/train': 0.8967050313949585} 08/31/2021 16:12:34 - INFO - __main__ - Step 148982: {'lr': 5.848140027489568e-08, 'samples': 28604544, 'steps': 148981, 'loss/train': 1.3369040489196777} 08/31/2021 16:12:34 - INFO - __main__ - Step 148983: {'lr': 5.836667911646165e-08, 'samples': 28604736, 'steps': 148982, 'loss/train': 1.2316454648971558} 08/31/2021 16:12:35 - INFO - __main__ - Step 148984: {'lr': 5.8252070577857755e-08, 'samples': 28604928, 'steps': 148983, 'loss/train': 0.8726186752319336} 08/31/2021 16:12:35 - INFO - __main__ - Step 148985: {'lr': 5.8137574659167244e-08, 'samples': 28605120, 'steps': 148984, 'loss/train': 1.3371875286102295} 08/31/2021 16:12:35 - INFO - __main__ - Step 148986: {'lr': 5.802319136041789e-08, 'samples': 28605312, 'steps': 148985, 'loss/train': 1.2934997081756592} 08/31/2021 16:12:36 - INFO - __main__ - Step 148987: {'lr': 5.79089206816652e-08, 'samples': 28605504, 'steps': 148986, 'loss/train': 1.6763811111450195} 08/31/2021 16:12:38 - INFO - __main__ - Step 148988: {'lr': 5.779476262296468e-08, 'samples': 28605696, 'steps': 148987, 'loss/train': 1.2823383808135986} 08/31/2021 16:12:38 - INFO - __main__ - Step 148989: {'lr': 5.7680717184344086e-08, 'samples': 28605888, 'steps': 148988, 'loss/train': 1.0987645387649536} 08/31/2021 16:12:39 - INFO - __main__ - Step 148990: {'lr': 5.756678436591445e-08, 'samples': 28606080, 'steps': 148989, 'loss/train': 1.2975666522979736} 08/31/2021 16:12:39 - INFO - __main__ - Step 148991: {'lr': 5.7452964167648004e-08, 'samples': 28606272, 'steps': 148990, 'loss/train': 0.6125346422195435} 08/31/2021 16:12:39 - INFO - __main__ - Step 148992: {'lr': 5.7339256589655776e-08, 'samples': 28606464, 'steps': 148991, 'loss/train': 1.6909111738204956} 08/31/2021 16:12:41 - INFO - __main__ - Step 148993: {'lr': 5.722566163199328e-08, 'samples': 28606656, 'steps': 148992, 'loss/train': 1.0059928894042969} 08/31/2021 16:12:41 - INFO - __main__ - Step 148994: {'lr': 5.7112179294660504e-08, 'samples': 28606848, 'steps': 148993, 'loss/train': 0.7033826112747192} 08/31/2021 16:12:42 - INFO - __main__ - Step 148995: {'lr': 5.699880957774073e-08, 'samples': 28607040, 'steps': 148994, 'loss/train': 0.7689277529716492} 08/31/2021 16:12:42 - INFO - __main__ - Step 148996: {'lr': 5.688555248126171e-08, 'samples': 28607232, 'steps': 148995, 'loss/train': 0.9170951843261719} 08/31/2021 16:12:42 - INFO - __main__ - Step 148997: {'lr': 5.677240800533445e-08, 'samples': 28607424, 'steps': 148996, 'loss/train': 0.5512761473655701} 08/31/2021 16:12:44 - INFO - __main__ - Step 148998: {'lr': 5.6659376149931216e-08, 'samples': 28607616, 'steps': 148997, 'loss/train': 1.042256236076355} 08/31/2021 16:12:44 - INFO - __main__ - Step 148999: {'lr': 5.6546456915163025e-08, 'samples': 28607808, 'steps': 148998, 'loss/train': 1.4469388723373413} 08/31/2021 16:12:45 - INFO - __main__ - Step 149000: {'lr': 5.643365030105763e-08, 'samples': 28608000, 'steps': 148999, 'loss/train': 0.07295497506856918} 08/31/2021 16:12:45 - INFO - __main__ - Step 149001: {'lr': 5.632095630764278e-08, 'samples': 28608192, 'steps': 149000, 'loss/train': 0.6973511576652527} 08/31/2021 16:12:45 - INFO - __main__ - Step 149002: {'lr': 5.620837493500175e-08, 'samples': 28608384, 'steps': 149001, 'loss/train': 0.9345473051071167} 08/31/2021 16:12:47 - INFO - __main__ - Step 149003: {'lr': 5.609590618319005e-08, 'samples': 28608576, 'steps': 149002, 'loss/train': 1.7964483499526978} 08/31/2021 16:12:47 - INFO - __main__ - Step 149004: {'lr': 5.598355005223543e-08, 'samples': 28608768, 'steps': 149003, 'loss/train': 1.3819894790649414} 08/31/2021 16:12:48 - INFO - __main__ - Step 149005: {'lr': 5.587130654222117e-08, 'samples': 28608960, 'steps': 149004, 'loss/train': 1.1999731063842773} 08/31/2021 16:12:48 - INFO - __main__ - Step 149006: {'lr': 5.5759175653147254e-08, 'samples': 28609152, 'steps': 149005, 'loss/train': 1.6542184352874756} 08/31/2021 16:12:48 - INFO - __main__ - Step 149007: {'lr': 5.564715738509696e-08, 'samples': 28609344, 'steps': 149006, 'loss/train': 0.5082119107246399} 08/31/2021 16:12:49 - INFO - __main__ - Step 149008: {'lr': 5.5535251738098036e-08, 'samples': 28609536, 'steps': 149007, 'loss/train': 1.1903425455093384} 08/31/2021 16:12:51 - INFO - __main__ - Step 149009: {'lr': 5.542345871226151e-08, 'samples': 28609728, 'steps': 149008, 'loss/train': 1.2064822912216187} 08/31/2021 16:12:51 - INFO - __main__ - Step 149010: {'lr': 5.531177830755962e-08, 'samples': 28609920, 'steps': 149009, 'loss/train': 1.0312360525131226} 08/31/2021 16:12:51 - INFO - __main__ - Step 149011: {'lr': 5.520021052407564e-08, 'samples': 28610112, 'steps': 149010, 'loss/train': 0.6539860367774963} 08/31/2021 16:12:52 - INFO - __main__ - Step 149012: {'lr': 5.508875536189284e-08, 'samples': 28610304, 'steps': 149011, 'loss/train': 1.2513432502746582} 08/31/2021 16:12:52 - INFO - __main__ - Step 149013: {'lr': 5.497741282101121e-08, 'samples': 28610496, 'steps': 149012, 'loss/train': 0.5602816343307495} 08/31/2021 16:12:54 - INFO - __main__ - Step 149014: {'lr': 5.486618290148626e-08, 'samples': 28610688, 'steps': 149013, 'loss/train': 3.2893619537353516} 08/31/2021 16:12:54 - INFO - __main__ - Step 149015: {'lr': 5.4755065603401265e-08, 'samples': 28610880, 'steps': 149014, 'loss/train': 0.8700896501541138} 08/31/2021 16:12:55 - INFO - __main__ - Step 149016: {'lr': 5.464406092678398e-08, 'samples': 28611072, 'steps': 149015, 'loss/train': 0.43273165822029114} 08/31/2021 16:12:55 - INFO - __main__ - Step 149017: {'lr': 5.4533168871662154e-08, 'samples': 28611264, 'steps': 149016, 'loss/train': 0.5175905227661133} 08/31/2021 16:12:55 - INFO - __main__ - Step 149018: {'lr': 5.4422389438146815e-08, 'samples': 28611456, 'steps': 149017, 'loss/train': 0.7545192837715149} 08/31/2021 16:12:57 - INFO - __main__ - Step 149019: {'lr': 5.4311722626237955e-08, 'samples': 28611648, 'steps': 149018, 'loss/train': 1.0249285697937012} 08/31/2021 16:12:57 - INFO - __main__ - Step 149020: {'lr': 5.42011684359911e-08, 'samples': 28611840, 'steps': 149019, 'loss/train': 1.406106948852539} 08/31/2021 16:12:58 - INFO - __main__ - Step 149021: {'lr': 5.409072686746175e-08, 'samples': 28612032, 'steps': 149020, 'loss/train': 0.965008020401001} 08/31/2021 16:12:58 - INFO - __main__ - Step 149022: {'lr': 5.398039792073317e-08, 'samples': 28612224, 'steps': 149021, 'loss/train': 1.1716011762619019} 08/31/2021 16:12:58 - INFO - __main__ - Step 149023: {'lr': 5.387018159577761e-08, 'samples': 28612416, 'steps': 149022, 'loss/train': 1.0749653577804565} 08/31/2021 16:13:00 - INFO - __main__ - Step 149024: {'lr': 5.376007789273385e-08, 'samples': 28612608, 'steps': 149023, 'loss/train': 1.3020983934402466} 08/31/2021 16:13:00 - INFO - __main__ - Step 149025: {'lr': 5.365008681157413e-08, 'samples': 28612800, 'steps': 149024, 'loss/train': 0.8464159965515137} 08/31/2021 16:13:01 - INFO - __main__ - Step 149026: {'lr': 5.354020835240947e-08, 'samples': 28612992, 'steps': 149025, 'loss/train': 0.6756709218025208} 08/31/2021 16:13:01 - INFO - __main__ - Step 149027: {'lr': 5.343044251526763e-08, 'samples': 28613184, 'steps': 149026, 'loss/train': 0.48856785893440247} 08/31/2021 16:13:01 - INFO - __main__ - Step 149028: {'lr': 5.332078930017637e-08, 'samples': 28613376, 'steps': 149027, 'loss/train': 1.2534562349319458} 08/31/2021 16:13:03 - INFO - __main__ - Step 149029: {'lr': 5.321124870719118e-08, 'samples': 28613568, 'steps': 149028, 'loss/train': 1.0543289184570312} 08/31/2021 16:13:04 - INFO - __main__ - Step 149030: {'lr': 5.3101820736395353e-08, 'samples': 28613760, 'steps': 149029, 'loss/train': 1.104640007019043} 08/31/2021 16:13:04 - INFO - __main__ - Step 149031: {'lr': 5.299250538778888e-08, 'samples': 28613952, 'steps': 149030, 'loss/train': 0.7878629565238953} 08/31/2021 16:13:04 - INFO - __main__ - Step 149032: {'lr': 5.288330266148278e-08, 'samples': 28614144, 'steps': 149031, 'loss/train': 0.3992297947406769} 08/31/2021 16:13:05 - INFO - __main__ - Step 149033: {'lr': 5.27742125574493e-08, 'samples': 28614336, 'steps': 149032, 'loss/train': 1.2426621913909912} 08/31/2021 16:13:05 - INFO - __main__ - Step 149034: {'lr': 5.266523507579946e-08, 'samples': 28614528, 'steps': 149033, 'loss/train': 0.5998043417930603} 08/31/2021 16:13:07 - INFO - __main__ - Step 149035: {'lr': 5.255637021656101e-08, 'samples': 28614720, 'steps': 149034, 'loss/train': 0.4030483365058899} 08/31/2021 16:13:07 - INFO - __main__ - Step 149036: {'lr': 5.2447617979789474e-08, 'samples': 28614912, 'steps': 149035, 'loss/train': 0.7560120224952698} 08/31/2021 16:13:07 - INFO - __main__ - Step 149037: {'lr': 5.233897836554036e-08, 'samples': 28615104, 'steps': 149036, 'loss/train': 0.6998457908630371} 08/31/2021 16:13:08 - INFO - __main__ - Step 149038: {'lr': 5.223045137381366e-08, 'samples': 28615296, 'steps': 149037, 'loss/train': 1.2181710004806519} 08/31/2021 16:13:08 - INFO - __main__ - Step 149039: {'lr': 5.21220370047204e-08, 'samples': 28615488, 'steps': 149038, 'loss/train': 1.0916403532028198} 08/31/2021 16:13:10 - INFO - __main__ - Step 149040: {'lr': 5.201373525828834e-08, 'samples': 28615680, 'steps': 149039, 'loss/train': 0.8144742250442505} 08/31/2021 16:13:11 - INFO - __main__ - Step 149041: {'lr': 5.190554613454524e-08, 'samples': 28615872, 'steps': 149040, 'loss/train': 1.1720690727233887} 08/31/2021 16:13:11 - INFO - __main__ - Step 149042: {'lr': 5.179746963357434e-08, 'samples': 28616064, 'steps': 149041, 'loss/train': 1.1936101913452148} 08/31/2021 16:13:11 - INFO - __main__ - Step 149043: {'lr': 5.168950575537568e-08, 'samples': 28616256, 'steps': 149042, 'loss/train': 1.4336131811141968} 08/31/2021 16:13:12 - INFO - __main__ - Step 149044: {'lr': 5.158165450006025e-08, 'samples': 28616448, 'steps': 149043, 'loss/train': 1.7734096050262451} 08/31/2021 16:13:13 - INFO - __main__ - Step 149045: {'lr': 5.147391586762806e-08, 'samples': 28616640, 'steps': 149044, 'loss/train': 0.4511971175670624} 08/31/2021 16:13:14 - INFO - __main__ - Step 149046: {'lr': 5.1366289858162385e-08, 'samples': 28616832, 'steps': 149045, 'loss/train': 0.9245467782020569} 08/31/2021 16:13:14 - INFO - __main__ - Step 149047: {'lr': 5.1258776471663213e-08, 'samples': 28617024, 'steps': 149046, 'loss/train': 1.1798630952835083} 08/31/2021 16:13:14 - INFO - __main__ - Step 149048: {'lr': 5.115137570824158e-08, 'samples': 28617216, 'steps': 149047, 'loss/train': 1.0934295654296875} 08/31/2021 16:13:15 - INFO - __main__ - Step 149049: {'lr': 5.104408756789747e-08, 'samples': 28617408, 'steps': 149048, 'loss/train': 1.0606337785720825} 08/31/2021 16:13:15 - INFO - __main__ - Step 149050: {'lr': 5.093691205071416e-08, 'samples': 28617600, 'steps': 149049, 'loss/train': 0.12038019299507141} 08/31/2021 16:13:17 - INFO - __main__ - Step 149051: {'lr': 5.0829849156691646e-08, 'samples': 28617792, 'steps': 149050, 'loss/train': 1.4842486381530762} 08/31/2021 16:13:17 - INFO - __main__ - Step 149052: {'lr': 5.0722898885940947e-08, 'samples': 28617984, 'steps': 149051, 'loss/train': 0.6831360459327698} 08/31/2021 16:13:18 - INFO - __main__ - Step 149053: {'lr': 5.061606123846207e-08, 'samples': 28618176, 'steps': 149052, 'loss/train': 1.3892619609832764} 08/31/2021 16:13:18 - INFO - __main__ - Step 149054: {'lr': 5.050933621431053e-08, 'samples': 28618368, 'steps': 149053, 'loss/train': 0.6912097334861755} 08/31/2021 16:13:20 - INFO - __main__ - Step 149055: {'lr': 5.0402723813541826e-08, 'samples': 28618560, 'steps': 149054, 'loss/train': 2.087946891784668} 08/31/2021 16:13:20 - INFO - __main__ - Step 149056: {'lr': 5.029622403621148e-08, 'samples': 28618752, 'steps': 149055, 'loss/train': 1.3191782236099243} 08/31/2021 16:13:20 - INFO - __main__ - Step 149057: {'lr': 5.0189836882374995e-08, 'samples': 28618944, 'steps': 149056, 'loss/train': 0.999272346496582} 08/31/2021 16:13:21 - INFO - __main__ - Step 149058: {'lr': 5.008356235203237e-08, 'samples': 28619136, 'steps': 149057, 'loss/train': 1.5549776554107666} 08/31/2021 16:13:21 - INFO - __main__ - Step 149059: {'lr': 4.9977400445294644e-08, 'samples': 28619328, 'steps': 149058, 'loss/train': 1.2669340372085571} 08/31/2021 16:13:23 - INFO - __main__ - Step 149060: {'lr': 4.987135116216179e-08, 'samples': 28619520, 'steps': 149059, 'loss/train': 0.9401475787162781} 08/31/2021 16:13:23 - INFO - __main__ - Step 149061: {'lr': 4.97654145027171e-08, 'samples': 28619712, 'steps': 149060, 'loss/train': 0.23874369263648987} 08/31/2021 16:13:24 - INFO - __main__ - Step 149062: {'lr': 4.965959046698831e-08, 'samples': 28619904, 'steps': 149061, 'loss/train': 0.5285965800285339} 08/31/2021 16:13:24 - INFO - __main__ - Step 149063: {'lr': 4.955387905503095e-08, 'samples': 28620096, 'steps': 149062, 'loss/train': 0.6167030930519104} 08/31/2021 16:13:25 - INFO - __main__ - Step 149064: {'lr': 4.9448280266872755e-08, 'samples': 28620288, 'steps': 149063, 'loss/train': 1.0674152374267578} 08/31/2021 16:13:25 - INFO - __main__ - Step 149065: {'lr': 4.934279410256925e-08, 'samples': 28620480, 'steps': 149064, 'loss/train': 0.48255622386932373} 08/31/2021 16:13:26 - INFO - __main__ - Step 149066: {'lr': 4.923742056220371e-08, 'samples': 28620672, 'steps': 149065, 'loss/train': 1.726493239402771} 08/31/2021 16:13:27 - INFO - __main__ - Step 149067: {'lr': 4.9132159645776106e-08, 'samples': 28620864, 'steps': 149066, 'loss/train': 1.0518922805786133} 08/31/2021 16:13:27 - INFO - __main__ - Step 149068: {'lr': 4.902701135334198e-08, 'samples': 28621056, 'steps': 149067, 'loss/train': 1.3054845333099365} 08/31/2021 16:13:28 - INFO - __main__ - Step 149069: {'lr': 4.8921975684984574e-08, 'samples': 28621248, 'steps': 149068, 'loss/train': 0.48276931047439575} 08/31/2021 16:13:28 - INFO - __main__ - Step 149070: {'lr': 4.881705264070391e-08, 'samples': 28621440, 'steps': 149069, 'loss/train': 1.4335073232650757} 08/31/2021 16:13:29 - INFO - __main__ - Step 149071: {'lr': 4.871224222058324e-08, 'samples': 28621632, 'steps': 149070, 'loss/train': 0.8333470821380615} 08/31/2021 16:13:30 - INFO - __main__ - Step 149072: {'lr': 4.860754442465032e-08, 'samples': 28621824, 'steps': 149071, 'loss/train': 0.612718403339386} 08/31/2021 16:13:30 - INFO - __main__ - Step 149073: {'lr': 4.8502959252960663e-08, 'samples': 28622016, 'steps': 149072, 'loss/train': 2.1064321994781494} 08/31/2021 16:13:31 - INFO - __main__ - Step 149074: {'lr': 4.839848670554203e-08, 'samples': 28622208, 'steps': 149073, 'loss/train': 0.6084479689598083} 08/31/2021 16:13:31 - INFO - __main__ - Step 149075: {'lr': 4.829412678247769e-08, 'samples': 28622400, 'steps': 149074, 'loss/train': 1.0263540744781494} 08/31/2021 16:13:33 - INFO - __main__ - Step 149076: {'lr': 4.818987948379538e-08, 'samples': 28622592, 'steps': 149075, 'loss/train': 0.37458521127700806} 08/31/2021 16:13:33 - INFO - __main__ - Step 149077: {'lr': 4.808574480952288e-08, 'samples': 28622784, 'steps': 149076, 'loss/train': 1.2332894802093506} 08/31/2021 16:13:34 - INFO - __main__ - Step 149078: {'lr': 4.798172275974344e-08, 'samples': 28622976, 'steps': 149077, 'loss/train': 1.6767833232879639} 08/31/2021 16:13:34 - INFO - __main__ - Step 149079: {'lr': 4.7877813334484824e-08, 'samples': 28623168, 'steps': 149078, 'loss/train': 1.5181021690368652} 08/31/2021 16:13:34 - INFO - __main__ - Step 149080: {'lr': 4.777401653380253e-08, 'samples': 28623360, 'steps': 149079, 'loss/train': 1.0845354795455933} 08/31/2021 16:13:36 - INFO - __main__ - Step 149081: {'lr': 4.767033235772433e-08, 'samples': 28623552, 'steps': 149080, 'loss/train': 0.8823024034500122} 08/31/2021 16:13:37 - INFO - __main__ - Step 149082: {'lr': 4.756676080630573e-08, 'samples': 28623744, 'steps': 149081, 'loss/train': 0.650286853313446} 08/31/2021 16:13:37 - INFO - __main__ - Step 149083: {'lr': 4.746330187960224e-08, 'samples': 28623936, 'steps': 149082, 'loss/train': 0.5445764660835266} 08/31/2021 16:13:37 - INFO - __main__ - Step 149084: {'lr': 4.7359955577641613e-08, 'samples': 28624128, 'steps': 149083, 'loss/train': 0.04676630347967148} 08/31/2021 16:13:38 - INFO - __main__ - Step 149085: {'lr': 4.7256721900507115e-08, 'samples': 28624320, 'steps': 149084, 'loss/train': 0.7911615967750549} 08/31/2021 16:13:38 - INFO - __main__ - Step 149086: {'lr': 4.7153600848198754e-08, 'samples': 28624512, 'steps': 149085, 'loss/train': 0.056042250245809555} 08/31/2021 16:13:40 - INFO - __main__ - Step 149087: {'lr': 4.7050592420799785e-08, 'samples': 28624704, 'steps': 149086, 'loss/train': 0.05756938084959984} 08/31/2021 16:13:40 - INFO - __main__ - Step 149088: {'lr': 4.6947696618337976e-08, 'samples': 28624896, 'steps': 149087, 'loss/train': 0.4039030969142914} 08/31/2021 16:13:41 - INFO - __main__ - Step 149089: {'lr': 4.684491344086883e-08, 'samples': 28625088, 'steps': 149088, 'loss/train': 0.8146288394927979} 08/31/2021 16:13:41 - INFO - __main__ - Step 149090: {'lr': 4.674224288844786e-08, 'samples': 28625280, 'steps': 149089, 'loss/train': 0.45559290051460266} 08/31/2021 16:13:41 - INFO - __main__ - Step 149091: {'lr': 4.6639684961075066e-08, 'samples': 28625472, 'steps': 149090, 'loss/train': 1.6168376207351685} 08/31/2021 16:13:42 - INFO - __main__ - Step 149092: {'lr': 4.6537239658861476e-08, 'samples': 28625664, 'steps': 149091, 'loss/train': 0.168777197599411} 08/31/2021 16:13:45 - INFO - __main__ - Step 149093: {'lr': 4.643490698180708e-08, 'samples': 28625856, 'steps': 149092, 'loss/train': 1.2547953128814697} 08/31/2021 16:13:45 - INFO - __main__ - Step 149094: {'lr': 4.6332686929967394e-08, 'samples': 28626048, 'steps': 149093, 'loss/train': 0.9806454181671143} 08/31/2021 16:13:45 - INFO - __main__ - Step 149095: {'lr': 4.623057950339793e-08, 'samples': 28626240, 'steps': 149094, 'loss/train': 0.8813533186912537} 08/31/2021 16:13:46 - INFO - __main__ - Step 149096: {'lr': 4.61285847021542e-08, 'samples': 28626432, 'steps': 149095, 'loss/train': 1.1232813596725464} 08/31/2021 16:13:46 - INFO - __main__ - Step 149097: {'lr': 4.6026702526236196e-08, 'samples': 28626624, 'steps': 149096, 'loss/train': 1.3855496644973755} 08/31/2021 16:13:47 - INFO - __main__ - Step 149098: {'lr': 4.592493297575495e-08, 'samples': 28626816, 'steps': 149097, 'loss/train': 0.5170398354530334} 08/31/2021 16:13:48 - INFO - __main__ - Step 149099: {'lr': 4.582327605068271e-08, 'samples': 28627008, 'steps': 149098, 'loss/train': 0.5291706919670105} 08/31/2021 16:13:48 - INFO - __main__ - Step 149100: {'lr': 4.572173175113048e-08, 'samples': 28627200, 'steps': 149099, 'loss/train': 1.1705684661865234} 08/31/2021 16:13:49 - INFO - __main__ - Step 149101: {'lr': 4.562030007712603e-08, 'samples': 28627392, 'steps': 149100, 'loss/train': 1.7279236316680908} 08/31/2021 16:13:49 - INFO - __main__ - Step 149102: {'lr': 4.5518981028697115e-08, 'samples': 28627584, 'steps': 149101, 'loss/train': 0.3363440930843353} 08/31/2021 16:13:50 - INFO - __main__ - Step 149103: {'lr': 4.541777460589924e-08, 'samples': 28627776, 'steps': 149102, 'loss/train': 1.2665306329727173} 08/31/2021 16:13:51 - INFO - __main__ - Step 149104: {'lr': 4.5316680808787926e-08, 'samples': 28627968, 'steps': 149103, 'loss/train': 1.049274206161499} 08/31/2021 16:13:52 - INFO - __main__ - Step 149105: {'lr': 4.5215699637390916e-08, 'samples': 28628160, 'steps': 149104, 'loss/train': 0.9441894888877869} 08/31/2021 16:13:52 - INFO - __main__ - Step 149106: {'lr': 4.5114831091791485e-08, 'samples': 28628352, 'steps': 149105, 'loss/train': 0.044809166342020035} 08/31/2021 16:13:52 - INFO - __main__ - Step 149107: {'lr': 4.501407517196188e-08, 'samples': 28628544, 'steps': 149106, 'loss/train': 1.4994792938232422} 08/31/2021 16:13:53 - INFO - __main__ - Step 149108: {'lr': 4.491343187801311e-08, 'samples': 28628736, 'steps': 149107, 'loss/train': 0.6606241464614868} 08/31/2021 16:13:55 - INFO - __main__ - Step 149109: {'lr': 4.4812901209972947e-08, 'samples': 28628928, 'steps': 149108, 'loss/train': 1.3065303564071655} 08/31/2021 16:13:55 - INFO - __main__ - Step 149110: {'lr': 4.4712483167869134e-08, 'samples': 28629120, 'steps': 149109, 'loss/train': 1.0365424156188965} 08/31/2021 16:13:56 - INFO - __main__ - Step 149111: {'lr': 4.461217775178494e-08, 'samples': 28629312, 'steps': 149110, 'loss/train': 1.269822359085083} 08/31/2021 16:13:56 - INFO - __main__ - Step 149112: {'lr': 4.451198496172038e-08, 'samples': 28629504, 'steps': 149111, 'loss/train': 1.347514033317566} 08/31/2021 16:13:56 - INFO - __main__ - Step 149113: {'lr': 4.4411904797758695e-08, 'samples': 28629696, 'steps': 149112, 'loss/train': 1.3252369165420532} 08/31/2021 16:13:57 - INFO - __main__ - Step 149114: {'lr': 4.431193725989991e-08, 'samples': 28629888, 'steps': 149113, 'loss/train': 0.9914235472679138} 08/31/2021 16:13:58 - INFO - __main__ - Step 149115: {'lr': 4.421208234822727e-08, 'samples': 28630080, 'steps': 149114, 'loss/train': 0.3435496985912323} 08/31/2021 16:13:59 - INFO - __main__ - Step 149116: {'lr': 4.41123400627963e-08, 'samples': 28630272, 'steps': 149115, 'loss/train': 1.0373821258544922} 08/31/2021 16:13:59 - INFO - __main__ - Step 149117: {'lr': 4.401271040360699e-08, 'samples': 28630464, 'steps': 149116, 'loss/train': 1.232800006866455} 08/31/2021 16:14:00 - INFO - __main__ - Step 149118: {'lr': 4.391319337074262e-08, 'samples': 28630656, 'steps': 149117, 'loss/train': 0.9511265158653259} 08/31/2021 16:14:00 - INFO - __main__ - Step 149119: {'lr': 4.381378896423094e-08, 'samples': 28630848, 'steps': 149118, 'loss/train': 1.042004942893982} 08/31/2021 16:14:00 - INFO - __main__ - Step 149120: {'lr': 4.371449718412745e-08, 'samples': 28631040, 'steps': 149119, 'loss/train': 0.014994390308856964} 08/31/2021 16:14:02 - INFO - __main__ - Step 149121: {'lr': 4.3615318030459926e-08, 'samples': 28631232, 'steps': 149120, 'loss/train': 0.7555932998657227} 08/31/2021 16:14:03 - INFO - __main__ - Step 149122: {'lr': 4.3516251503283864e-08, 'samples': 28631424, 'steps': 149121, 'loss/train': 0.026403972879052162} 08/31/2021 16:14:03 - INFO - __main__ - Step 149123: {'lr': 4.3417297602627026e-08, 'samples': 28631616, 'steps': 149122, 'loss/train': 0.015080839395523071} 08/31/2021 16:14:03 - INFO - __main__ - Step 149124: {'lr': 4.3318456328572674e-08, 'samples': 28631808, 'steps': 149123, 'loss/train': 1.5144511461257935} 08/31/2021 16:14:04 - INFO - __main__ - Step 149125: {'lr': 4.321972768114857e-08, 'samples': 28632000, 'steps': 149124, 'loss/train': 1.3466229438781738} 08/31/2021 16:14:04 - INFO - __main__ - Step 149126: {'lr': 4.3121111660354706e-08, 'samples': 28632192, 'steps': 149125, 'loss/train': 0.280972421169281} 08/31/2021 16:14:06 - INFO - __main__ - Step 149127: {'lr': 4.302260826630211e-08, 'samples': 28632384, 'steps': 149126, 'loss/train': 1.4239965677261353} 08/31/2021 16:14:06 - INFO - __main__ - Step 149128: {'lr': 4.292421749899078e-08, 'samples': 28632576, 'steps': 149127, 'loss/train': 0.707011342048645} 08/31/2021 16:14:06 - INFO - __main__ - Step 149129: {'lr': 4.282593935850399e-08, 'samples': 28632768, 'steps': 149128, 'loss/train': 1.8051570653915405} 08/31/2021 16:14:07 - INFO - __main__ - Step 149130: {'lr': 4.272777384484172e-08, 'samples': 28632960, 'steps': 149129, 'loss/train': 1.2446798086166382} 08/31/2021 16:14:07 - INFO - __main__ - Step 149131: {'lr': 4.262972095808726e-08, 'samples': 28633152, 'steps': 149130, 'loss/train': 0.5244982838630676} 08/31/2021 16:14:09 - INFO - __main__ - Step 149132: {'lr': 4.2531780698240595e-08, 'samples': 28633344, 'steps': 149131, 'loss/train': 1.8438689708709717} 08/31/2021 16:14:09 - INFO - __main__ - Step 149133: {'lr': 4.2433953065385e-08, 'samples': 28633536, 'steps': 149132, 'loss/train': 0.1547233760356903} 08/31/2021 16:14:09 - INFO - __main__ - Step 149134: {'lr': 4.233623805957598e-08, 'samples': 28633728, 'steps': 149133, 'loss/train': 1.8694967031478882} 08/31/2021 16:14:10 - INFO - __main__ - Step 149135: {'lr': 4.223863568081354e-08, 'samples': 28633920, 'steps': 149134, 'loss/train': 0.4691288471221924} 08/31/2021 16:14:10 - INFO - __main__ - Step 149136: {'lr': 4.214114592915319e-08, 'samples': 28634112, 'steps': 149135, 'loss/train': 1.2343324422836304} 08/31/2021 16:14:12 - INFO - __main__ - Step 149137: {'lr': 4.204376880465044e-08, 'samples': 28634304, 'steps': 149136, 'loss/train': 1.5000628232955933} 08/31/2021 16:14:12 - INFO - __main__ - Step 149138: {'lr': 4.1946504307333046e-08, 'samples': 28634496, 'steps': 149137, 'loss/train': 0.7757945656776428} 08/31/2021 16:14:13 - INFO - __main__ - Step 149139: {'lr': 4.184935243728427e-08, 'samples': 28634688, 'steps': 149138, 'loss/train': 0.9599605202674866} 08/31/2021 16:14:13 - INFO - __main__ - Step 149140: {'lr': 4.175231319450412e-08, 'samples': 28634880, 'steps': 149139, 'loss/train': 1.0929362773895264} 08/31/2021 16:14:14 - INFO - __main__ - Step 149141: {'lr': 4.16553865790481e-08, 'samples': 28635072, 'steps': 149140, 'loss/train': 0.014078721404075623} 08/31/2021 16:14:14 - INFO - __main__ - Step 149142: {'lr': 4.155857259099949e-08, 'samples': 28635264, 'steps': 149141, 'loss/train': 1.4850547313690186} 08/31/2021 16:14:15 - INFO - __main__ - Step 149143: {'lr': 4.146187123033052e-08, 'samples': 28635456, 'steps': 149142, 'loss/train': 1.0000497102737427} 08/31/2021 16:14:16 - INFO - __main__ - Step 149144: {'lr': 4.1365282497124455e-08, 'samples': 28635648, 'steps': 149143, 'loss/train': 1.2374088764190674} 08/31/2021 16:14:16 - INFO - __main__ - Step 149145: {'lr': 4.1268806391436816e-08, 'samples': 28635840, 'steps': 149144, 'loss/train': 1.2621873617172241} 08/31/2021 16:14:16 - INFO - __main__ - Step 149146: {'lr': 4.1172442913295364e-08, 'samples': 28636032, 'steps': 149145, 'loss/train': 1.2566617727279663} 08/31/2021 16:14:17 - INFO - __main__ - Step 149147: {'lr': 4.107619206272784e-08, 'samples': 28636224, 'steps': 149146, 'loss/train': 1.6786882877349854} 08/31/2021 16:14:19 - INFO - __main__ - Step 149148: {'lr': 4.098005383981751e-08, 'samples': 28636416, 'steps': 149147, 'loss/train': 0.7359365224838257} 08/31/2021 16:14:19 - INFO - __main__ - Step 149149: {'lr': 4.088402824459214e-08, 'samples': 28636608, 'steps': 149148, 'loss/train': 1.2934441566467285} 08/31/2021 16:14:19 - INFO - __main__ - Step 149150: {'lr': 4.0788115277051727e-08, 'samples': 28636800, 'steps': 149149, 'loss/train': 0.2191050797700882} 08/31/2021 16:14:20 - INFO - __main__ - Step 149151: {'lr': 4.0692314937307296e-08, 'samples': 28636992, 'steps': 149150, 'loss/train': 0.1712128221988678} 08/31/2021 16:14:20 - INFO - __main__ - Step 149152: {'lr': 4.0596627225331086e-08, 'samples': 28637184, 'steps': 149151, 'loss/train': 1.1880191564559937} 08/31/2021 16:14:22 - INFO - __main__ - Step 149153: {'lr': 4.050105214123412e-08, 'samples': 28637376, 'steps': 149152, 'loss/train': 1.2764050960540771} 08/31/2021 16:14:23 - INFO - __main__ - Step 149154: {'lr': 4.040558968504415e-08, 'samples': 28637568, 'steps': 149153, 'loss/train': 1.0560407638549805} 08/31/2021 16:14:23 - INFO - __main__ - Step 149155: {'lr': 4.031023985676119e-08, 'samples': 28637760, 'steps': 149154, 'loss/train': 0.6340455412864685} 08/31/2021 16:14:23 - INFO - __main__ - Step 149156: {'lr': 4.0215002656468494e-08, 'samples': 28637952, 'steps': 149155, 'loss/train': 1.233981966972351} 08/31/2021 16:14:24 - INFO - __main__ - Step 149157: {'lr': 4.0119878084193816e-08, 'samples': 28638144, 'steps': 149156, 'loss/train': 0.24437852203845978} 08/31/2021 16:14:24 - INFO - __main__ - Step 149158: {'lr': 4.0024866139992675e-08, 'samples': 28638336, 'steps': 149157, 'loss/train': 0.5237464904785156} 08/31/2021 16:14:26 - INFO - __main__ - Step 149159: {'lr': 3.9929966823892824e-08, 'samples': 28638528, 'steps': 149158, 'loss/train': 1.5407100915908813} 08/31/2021 16:14:26 - INFO - __main__ - Step 149160: {'lr': 3.983518013594978e-08, 'samples': 28638720, 'steps': 149159, 'loss/train': 1.3000767230987549} 08/31/2021 16:14:26 - INFO - __main__ - Step 149161: {'lr': 3.974050607619129e-08, 'samples': 28638912, 'steps': 149160, 'loss/train': 0.17247962951660156} 08/31/2021 16:14:27 - INFO - __main__ - Step 149162: {'lr': 3.964594464467286e-08, 'samples': 28639104, 'steps': 149161, 'loss/train': 0.7411871552467346} 08/31/2021 16:14:27 - INFO - __main__ - Step 149163: {'lr': 3.955149584142226e-08, 'samples': 28639296, 'steps': 149162, 'loss/train': 0.9777536392211914} 08/31/2021 16:14:29 - INFO - __main__ - Step 149164: {'lr': 3.945715966649499e-08, 'samples': 28639488, 'steps': 149163, 'loss/train': 1.8597569465637207} 08/31/2021 16:14:29 - INFO - __main__ - Step 149165: {'lr': 3.936293611994657e-08, 'samples': 28639680, 'steps': 149164, 'loss/train': 1.1009773015975952} 08/31/2021 16:14:29 - INFO - __main__ - Step 149166: {'lr': 3.9268825201804746e-08, 'samples': 28639872, 'steps': 149165, 'loss/train': 0.2617269456386566} 08/31/2021 16:14:30 - INFO - __main__ - Step 149167: {'lr': 3.917482691209728e-08, 'samples': 28640064, 'steps': 149166, 'loss/train': 1.0464255809783936} 08/31/2021 16:14:30 - INFO - __main__ - Step 149168: {'lr': 3.9080941250879686e-08, 'samples': 28640256, 'steps': 149167, 'loss/train': 0.31911376118659973} 08/31/2021 16:14:32 - INFO - __main__ - Step 149169: {'lr': 3.898716821820747e-08, 'samples': 28640448, 'steps': 149168, 'loss/train': 0.9082722663879395} 08/31/2021 16:14:32 - INFO - __main__ - Step 149170: {'lr': 3.889350781410839e-08, 'samples': 28640640, 'steps': 149169, 'loss/train': 0.4721933901309967} 08/31/2021 16:14:32 - INFO - __main__ - Step 149171: {'lr': 3.8799960038610194e-08, 'samples': 28640832, 'steps': 149170, 'loss/train': 0.8924411535263062} 08/31/2021 16:14:33 - INFO - __main__ - Step 149172: {'lr': 3.8706524891796155e-08, 'samples': 28641024, 'steps': 149171, 'loss/train': 0.4882557988166809} 08/31/2021 16:14:33 - INFO - __main__ - Step 149173: {'lr': 3.8613202373666276e-08, 'samples': 28641216, 'steps': 149172, 'loss/train': 0.7474424242973328} 08/31/2021 16:14:35 - INFO - __main__ - Step 149174: {'lr': 3.851999248427607e-08, 'samples': 28641408, 'steps': 149173, 'loss/train': 1.270816445350647} 08/31/2021 16:14:35 - INFO - __main__ - Step 149175: {'lr': 3.842689522368103e-08, 'samples': 28641600, 'steps': 149174, 'loss/train': 1.1252343654632568} 08/31/2021 16:14:35 - INFO - __main__ - Step 149176: {'lr': 3.8333910591908935e-08, 'samples': 28641792, 'steps': 149175, 'loss/train': 1.5081020593643188} 08/31/2021 16:14:36 - INFO - __main__ - Step 149177: {'lr': 3.824103858901529e-08, 'samples': 28641984, 'steps': 149176, 'loss/train': 1.2946196794509888} 08/31/2021 16:14:36 - INFO - __main__ - Step 149178: {'lr': 3.8148279215027835e-08, 'samples': 28642176, 'steps': 149177, 'loss/train': 1.0713740587234497} 08/31/2021 16:14:38 - INFO - __main__ - Step 149179: {'lr': 3.80556324700021e-08, 'samples': 28642368, 'steps': 149178, 'loss/train': 1.3242602348327637} 08/31/2021 16:14:38 - INFO - __main__ - Step 149180: {'lr': 3.796309835396583e-08, 'samples': 28642560, 'steps': 149179, 'loss/train': 1.6705498695373535} 08/31/2021 16:14:38 - INFO - __main__ - Step 149181: {'lr': 3.787067686694678e-08, 'samples': 28642752, 'steps': 149180, 'loss/train': 1.2672209739685059} 08/31/2021 16:14:39 - INFO - __main__ - Step 149182: {'lr': 3.777836800902823e-08, 'samples': 28642944, 'steps': 149181, 'loss/train': 1.2271742820739746} 08/31/2021 16:14:39 - INFO - __main__ - Step 149183: {'lr': 3.768617178023792e-08, 'samples': 28643136, 'steps': 149182, 'loss/train': 1.6146290302276611} 08/31/2021 16:14:40 - INFO - __main__ - Step 149184: {'lr': 3.759408818057586e-08, 'samples': 28643328, 'steps': 149183, 'loss/train': 0.2183658331632614} 08/31/2021 16:14:41 - INFO - __main__ - Step 149185: {'lr': 3.7502117210153065e-08, 'samples': 28643520, 'steps': 149184, 'loss/train': 1.423378348350525} 08/31/2021 16:14:42 - INFO - __main__ - Step 149186: {'lr': 3.7410258868941784e-08, 'samples': 28643712, 'steps': 149185, 'loss/train': 1.139907956123352} 08/31/2021 16:14:42 - INFO - __main__ - Step 149187: {'lr': 3.7318513157053036e-08, 'samples': 28643904, 'steps': 149186, 'loss/train': 0.9044199585914612} 08/31/2021 16:14:42 - INFO - __main__ - Step 149188: {'lr': 3.722688007445907e-08, 'samples': 28644096, 'steps': 149187, 'loss/train': 3.5893359184265137} 08/31/2021 16:14:43 - INFO - __main__ - Step 149189: {'lr': 3.7135359621243146e-08, 'samples': 28644288, 'steps': 149188, 'loss/train': 1.4239760637283325} 08/31/2021 16:14:44 - INFO - __main__ - Step 149190: {'lr': 3.7043951797433026e-08, 'samples': 28644480, 'steps': 149189, 'loss/train': 0.2818940281867981} 08/31/2021 16:14:45 - INFO - __main__ - Step 149191: {'lr': 3.6952656603084225e-08, 'samples': 28644672, 'steps': 149190, 'loss/train': 1.0184797048568726} 08/31/2021 16:14:45 - INFO - __main__ - Step 149192: {'lr': 3.6861474038224486e-08, 'samples': 28644864, 'steps': 149191, 'loss/train': 0.8473560214042664} 08/31/2021 16:14:45 - INFO - __main__ - Step 149193: {'lr': 3.677040410290933e-08, 'samples': 28645056, 'steps': 149192, 'loss/train': 1.6005959510803223} 08/31/2021 16:14:46 - INFO - __main__ - Step 149194: {'lr': 3.6679446797138746e-08, 'samples': 28645248, 'steps': 149193, 'loss/train': 0.9848872423171997} 08/31/2021 16:14:47 - INFO - __main__ - Step 149195: {'lr': 3.658860212099602e-08, 'samples': 28645440, 'steps': 149194, 'loss/train': 1.278652310371399} 08/31/2021 16:14:48 - INFO - __main__ - Step 149196: {'lr': 3.649787007453664e-08, 'samples': 28645632, 'steps': 149195, 'loss/train': 1.558336615562439} 08/31/2021 16:14:48 - INFO - __main__ - Step 149197: {'lr': 3.640725065773287e-08, 'samples': 28645824, 'steps': 149196, 'loss/train': 1.2916983366012573} 08/31/2021 16:14:49 - INFO - __main__ - Step 149198: {'lr': 3.631674387069572e-08, 'samples': 28646016, 'steps': 149197, 'loss/train': 0.5083322525024414} 08/31/2021 16:14:49 - INFO - __main__ - Step 149199: {'lr': 3.62263497134252e-08, 'samples': 28646208, 'steps': 149198, 'loss/train': 0.7824655175209045} 08/31/2021 16:14:49 - INFO - __main__ - Step 149200: {'lr': 3.613606818597681e-08, 'samples': 28646400, 'steps': 149199, 'loss/train': 1.24640953540802} 08/31/2021 16:14:51 - INFO - __main__ - Step 149201: {'lr': 3.604589928837832e-08, 'samples': 28646592, 'steps': 149200, 'loss/train': 0.018059302121400833} 08/31/2021 16:14:51 - INFO - __main__ - Step 149202: {'lr': 3.595584302068522e-08, 'samples': 28646784, 'steps': 149201, 'loss/train': 0.7182340621948242} 08/31/2021 16:14:52 - INFO - __main__ - Step 149203: {'lr': 3.5865899382953034e-08, 'samples': 28646976, 'steps': 149202, 'loss/train': 0.6561489701271057} 08/31/2021 16:14:52 - INFO - __main__ - Step 149204: {'lr': 3.577606837518177e-08, 'samples': 28647168, 'steps': 149203, 'loss/train': 1.381796956062317} 08/31/2021 16:14:52 - INFO - __main__ - Step 149205: {'lr': 3.5686349997426924e-08, 'samples': 28647360, 'steps': 149204, 'loss/train': 1.4782575368881226} 08/31/2021 16:14:54 - INFO - __main__ - Step 149206: {'lr': 3.559674424974402e-08, 'samples': 28647552, 'steps': 149205, 'loss/train': 1.290522575378418} 08/31/2021 16:14:54 - INFO - __main__ - Step 149207: {'lr': 3.55072511321608e-08, 'samples': 28647744, 'steps': 149206, 'loss/train': 1.2097357511520386} 08/31/2021 16:14:55 - INFO - __main__ - Step 149208: {'lr': 3.5417870644732784e-08, 'samples': 28647936, 'steps': 149207, 'loss/train': 1.2471719980239868} 08/31/2021 16:14:55 - INFO - __main__ - Step 149209: {'lr': 3.5328602787487726e-08, 'samples': 28648128, 'steps': 149208, 'loss/train': 0.38602781295776367} 08/31/2021 16:14:55 - INFO - __main__ - Step 149210: {'lr': 3.523944756045339e-08, 'samples': 28648320, 'steps': 149209, 'loss/train': 0.02496308647096157} 08/31/2021 16:14:57 - INFO - __main__ - Step 149211: {'lr': 3.515040496368527e-08, 'samples': 28648512, 'steps': 149210, 'loss/train': 1.3847414255142212} 08/31/2021 16:14:58 - INFO - __main__ - Step 149212: {'lr': 3.506147499721113e-08, 'samples': 28648704, 'steps': 149211, 'loss/train': 1.4030808210372925} 08/31/2021 16:14:58 - INFO - __main__ - Step 149213: {'lr': 3.4972657661114236e-08, 'samples': 28648896, 'steps': 149212, 'loss/train': 0.6655166745185852} 08/31/2021 16:14:59 - INFO - __main__ - Step 149214: {'lr': 3.488395295536684e-08, 'samples': 28649088, 'steps': 149213, 'loss/train': 1.5621157884597778} 08/31/2021 16:14:59 - INFO - __main__ - Step 149215: {'lr': 3.4795360880052195e-08, 'samples': 28649280, 'steps': 149214, 'loss/train': 1.3525896072387695} 08/31/2021 16:15:00 - INFO - __main__ - Step 149216: {'lr': 3.4706881435225823e-08, 'samples': 28649472, 'steps': 149215, 'loss/train': 1.4357209205627441} 08/31/2021 16:15:01 - INFO - __main__ - Step 149217: {'lr': 3.461851462088772e-08, 'samples': 28649664, 'steps': 149216, 'loss/train': 1.1789746284484863} 08/31/2021 16:15:01 - INFO - __main__ - Step 149218: {'lr': 3.4530260437093395e-08, 'samples': 28649856, 'steps': 149217, 'loss/train': 1.6143277883529663} 08/31/2021 16:15:02 - INFO - __main__ - Step 149219: {'lr': 3.444211888387061e-08, 'samples': 28650048, 'steps': 149218, 'loss/train': 1.6205854415893555} 08/31/2021 16:15:02 - INFO - __main__ - Step 149220: {'lr': 3.435408996127487e-08, 'samples': 28650240, 'steps': 149219, 'loss/train': 1.6312341690063477} 08/31/2021 16:15:02 - INFO - __main__ - Step 149221: {'lr': 3.426617366936169e-08, 'samples': 28650432, 'steps': 149220, 'loss/train': 0.8144856691360474} 08/31/2021 16:15:04 - INFO - __main__ - Step 149222: {'lr': 3.417837000813107e-08, 'samples': 28650624, 'steps': 149221, 'loss/train': 0.9121050834655762} 08/31/2021 16:15:04 - INFO - __main__ - Step 149223: {'lr': 3.409067897763851e-08, 'samples': 28650816, 'steps': 149222, 'loss/train': 0.25693219900131226} 08/31/2021 16:15:05 - INFO - __main__ - Step 149224: {'lr': 3.4003100577939536e-08, 'samples': 28651008, 'steps': 149223, 'loss/train': 0.6075150966644287} 08/31/2021 16:15:05 - INFO - __main__ - Step 149225: {'lr': 3.39156348090619e-08, 'samples': 28651200, 'steps': 149224, 'loss/train': 1.3200867176055908} 08/31/2021 16:15:05 - INFO - __main__ - Step 149226: {'lr': 3.3828281671033355e-08, 'samples': 28651392, 'steps': 149225, 'loss/train': 1.0296716690063477} 08/31/2021 16:15:07 - INFO - __main__ - Step 149227: {'lr': 3.374104116390941e-08, 'samples': 28651584, 'steps': 149226, 'loss/train': 1.4845950603485107} 08/31/2021 16:15:08 - INFO - __main__ - Step 149228: {'lr': 3.365391328774558e-08, 'samples': 28651776, 'steps': 149227, 'loss/train': 1.6153875589370728} 08/31/2021 16:15:08 - INFO - __main__ - Step 149229: {'lr': 3.356689804254187e-08, 'samples': 28651968, 'steps': 149228, 'loss/train': 1.0327125787734985} 08/31/2021 16:15:08 - INFO - __main__ - Step 149230: {'lr': 3.347999542835378e-08, 'samples': 28652160, 'steps': 149229, 'loss/train': 1.2007520198822021} 08/31/2021 16:15:09 - INFO - __main__ - Step 149231: {'lr': 3.3393205445209076e-08, 'samples': 28652352, 'steps': 149230, 'loss/train': 0.23467697203159332} 08/31/2021 16:15:10 - INFO - __main__ - Step 149232: {'lr': 3.330652809319101e-08, 'samples': 28652544, 'steps': 149231, 'loss/train': 1.8032130002975464} 08/31/2021 16:15:11 - INFO - __main__ - Step 149233: {'lr': 3.321996337227184e-08, 'samples': 28652736, 'steps': 149232, 'loss/train': 0.5710925459861755} 08/31/2021 16:15:11 - INFO - __main__ - Step 149234: {'lr': 3.313351128256259e-08, 'samples': 28652928, 'steps': 149233, 'loss/train': 0.5926491022109985} 08/31/2021 16:15:11 - INFO - __main__ - Step 149235: {'lr': 3.3047171824035496e-08, 'samples': 28653120, 'steps': 149234, 'loss/train': 0.7311880588531494} 08/31/2021 16:15:12 - INFO - __main__ - Step 149236: {'lr': 3.2960944996801576e-08, 'samples': 28653312, 'steps': 149235, 'loss/train': 1.0336174964904785} 08/31/2021 16:15:13 - INFO - __main__ - Step 149237: {'lr': 3.287483080080533e-08, 'samples': 28653504, 'steps': 149236, 'loss/train': 0.3446546196937561} 08/31/2021 16:15:14 - INFO - __main__ - Step 149238: {'lr': 3.2788829236185534e-08, 'samples': 28653696, 'steps': 149237, 'loss/train': 0.5510618090629578} 08/31/2021 16:15:14 - INFO - __main__ - Step 149239: {'lr': 3.270294030291443e-08, 'samples': 28653888, 'steps': 149238, 'loss/train': 0.7140340805053711} 08/31/2021 16:15:14 - INFO - __main__ - Step 149240: {'lr': 3.261716400104753e-08, 'samples': 28654080, 'steps': 149239, 'loss/train': 0.6437235474586487} 08/31/2021 16:15:15 - INFO - __main__ - Step 149241: {'lr': 3.2531500330612586e-08, 'samples': 28654272, 'steps': 149240, 'loss/train': 1.0258136987686157} 08/31/2021 16:15:16 - INFO - __main__ - Step 149242: {'lr': 3.244594929169287e-08, 'samples': 28654464, 'steps': 149241, 'loss/train': 0.7178216576576233} 08/31/2021 16:15:17 - INFO - __main__ - Step 149243: {'lr': 3.236051088426062e-08, 'samples': 28654656, 'steps': 149242, 'loss/train': 0.7850468754768372} 08/31/2021 16:15:17 - INFO - __main__ - Step 149244: {'lr': 3.227518510842686e-08, 'samples': 28654848, 'steps': 149243, 'loss/train': 1.3192178010940552} 08/31/2021 16:15:17 - INFO - __main__ - Step 149245: {'lr': 3.2189971964163846e-08, 'samples': 28655040, 'steps': 149244, 'loss/train': 1.2970492839813232} 08/31/2021 16:15:18 - INFO - __main__ - Step 149246: {'lr': 3.210487145155483e-08, 'samples': 28655232, 'steps': 149245, 'loss/train': 0.5852011442184448} 08/31/2021 16:15:19 - INFO - __main__ - Step 149247: {'lr': 3.201988357062757e-08, 'samples': 28655424, 'steps': 149246, 'loss/train': 0.9866169691085815} 08/31/2021 16:15:20 - INFO - __main__ - Step 149248: {'lr': 3.193500832138208e-08, 'samples': 28655616, 'steps': 149247, 'loss/train': 0.8637675642967224} 08/31/2021 16:15:20 - INFO - __main__ - Step 149249: {'lr': 3.185024570392936e-08, 'samples': 28655808, 'steps': 149248, 'loss/train': 1.640078067779541} 08/31/2021 16:15:20 - INFO - __main__ - Step 149250: {'lr': 3.176559571824167e-08, 'samples': 28656000, 'steps': 149249, 'loss/train': 1.0528913736343384} 08/31/2021 16:15:21 - INFO - __main__ - Step 149251: {'lr': 3.168105836440227e-08, 'samples': 28656192, 'steps': 149250, 'loss/train': 0.6573484539985657} 08/31/2021 16:15:22 - INFO - __main__ - Step 149252: {'lr': 3.159663364241117e-08, 'samples': 28656384, 'steps': 149251, 'loss/train': 1.197896122932434} 08/31/2021 16:15:23 - INFO - __main__ - Step 149253: {'lr': 3.1512321552323865e-08, 'samples': 28656576, 'steps': 149252, 'loss/train': 0.9272928833961487} 08/31/2021 16:15:23 - INFO - __main__ - Step 149254: {'lr': 3.1428122094195875e-08, 'samples': 28656768, 'steps': 149253, 'loss/train': 1.192272424697876} 08/31/2021 16:15:23 - INFO - __main__ - Step 149255: {'lr': 3.134403526805496e-08, 'samples': 28656960, 'steps': 149254, 'loss/train': 1.4141645431518555} 08/31/2021 16:15:24 - INFO - __main__ - Step 149256: {'lr': 3.1260061073901116e-08, 'samples': 28657152, 'steps': 149255, 'loss/train': 1.0919337272644043} 08/31/2021 16:15:25 - INFO - __main__ - Step 149257: {'lr': 3.117619951184536e-08, 'samples': 28657344, 'steps': 149256, 'loss/train': 0.8965848684310913} 08/31/2021 16:15:25 - INFO - __main__ - Step 149258: {'lr': 3.109245058185994e-08, 'samples': 28657536, 'steps': 149257, 'loss/train': 1.62427818775177} 08/31/2021 16:15:26 - INFO - __main__ - Step 149259: {'lr': 3.100881428400038e-08, 'samples': 28657728, 'steps': 149258, 'loss/train': 0.6467474699020386} 08/31/2021 16:15:26 - INFO - __main__ - Step 149260: {'lr': 3.092529061832217e-08, 'samples': 28657920, 'steps': 149259, 'loss/train': 1.2022550106048584} 08/31/2021 16:15:26 - INFO - __main__ - Step 149261: {'lr': 3.084187958485307e-08, 'samples': 28658112, 'steps': 149260, 'loss/train': 1.382685661315918} 08/31/2021 16:15:27 - INFO - __main__ - Step 149262: {'lr': 3.075858118362085e-08, 'samples': 28658304, 'steps': 149261, 'loss/train': 0.5444708466529846} 08/31/2021 16:15:29 - INFO - __main__ - Step 149263: {'lr': 3.0675395414681005e-08, 'samples': 28658496, 'steps': 149262, 'loss/train': 1.1460955142974854} 08/31/2021 16:15:30 - INFO - __main__ - Step 149264: {'lr': 3.05923222780613e-08, 'samples': 28658688, 'steps': 149263, 'loss/train': 0.028004378080368042} 08/31/2021 16:15:30 - INFO - __main__ - Step 149265: {'lr': 3.050936177378949e-08, 'samples': 28658880, 'steps': 149264, 'loss/train': 1.1260097026824951} 08/31/2021 16:15:31 - INFO - __main__ - Step 149266: {'lr': 3.0426513901921085e-08, 'samples': 28659072, 'steps': 149265, 'loss/train': 2.3120994567871094} 08/31/2021 16:15:31 - INFO - __main__ - Step 149267: {'lr': 3.0343778662483836e-08, 'samples': 28659264, 'steps': 149266, 'loss/train': 0.3319372534751892} 08/31/2021 16:15:31 - INFO - __main__ - Step 149268: {'lr': 3.02611560555055e-08, 'samples': 28659456, 'steps': 149267, 'loss/train': 2.625725269317627} 08/31/2021 16:15:33 - INFO - __main__ - Step 149269: {'lr': 3.017864608106935e-08, 'samples': 28659648, 'steps': 149268, 'loss/train': 2.6051878929138184} 08/31/2021 16:15:33 - INFO - __main__ - Step 149270: {'lr': 3.0096248739147625e-08, 'samples': 28659840, 'steps': 149269, 'loss/train': 0.7985467314720154} 08/31/2021 16:15:34 - INFO - __main__ - Step 149271: {'lr': 3.0013964029795835e-08, 'samples': 28660032, 'steps': 149270, 'loss/train': 0.6174179315567017} 08/31/2021 16:15:34 - INFO - __main__ - Step 149272: {'lr': 2.993179195309725e-08, 'samples': 28660224, 'steps': 149271, 'loss/train': 0.989940345287323} 08/31/2021 16:15:35 - INFO - __main__ - Step 149273: {'lr': 2.984973250902412e-08, 'samples': 28660416, 'steps': 149272, 'loss/train': 0.813663899898529} 08/31/2021 16:15:36 - INFO - __main__ - Step 149274: {'lr': 2.97677856976597e-08, 'samples': 28660608, 'steps': 149273, 'loss/train': 1.1589235067367554} 08/31/2021 16:15:36 - INFO - __main__ - Step 149275: {'lr': 2.968595151903175e-08, 'samples': 28660800, 'steps': 149274, 'loss/train': 0.9459737539291382} 08/31/2021 16:15:37 - INFO - __main__ - Step 149276: {'lr': 2.9604229973140273e-08, 'samples': 28660992, 'steps': 149275, 'loss/train': 1.0169799327850342} 08/31/2021 16:15:37 - INFO - __main__ - Step 149277: {'lr': 2.9522621060068533e-08, 'samples': 28661184, 'steps': 149276, 'loss/train': 1.4493043422698975} 08/31/2021 16:15:37 - INFO - __main__ - Step 149278: {'lr': 2.9441124779844287e-08, 'samples': 28661376, 'steps': 149277, 'loss/train': 0.8455621600151062} 08/31/2021 16:15:39 - INFO - __main__ - Step 149279: {'lr': 2.935974113249529e-08, 'samples': 28661568, 'steps': 149278, 'loss/train': 0.9291152954101562} 08/31/2021 16:15:40 - INFO - __main__ - Step 149280: {'lr': 2.9278470118049295e-08, 'samples': 28661760, 'steps': 149279, 'loss/train': 0.8682988882064819} 08/31/2021 16:15:40 - INFO - __main__ - Step 149281: {'lr': 2.9197311736561815e-08, 'samples': 28661952, 'steps': 149280, 'loss/train': 0.04809541627764702} 08/31/2021 16:15:41 - INFO - __main__ - Step 149282: {'lr': 2.9116265988060607e-08, 'samples': 28662144, 'steps': 149281, 'loss/train': 0.8042909502983093} 08/31/2021 16:15:41 - INFO - __main__ - Step 149283: {'lr': 2.9035332872573427e-08, 'samples': 28662336, 'steps': 149282, 'loss/train': 1.0257933139801025} 08/31/2021 16:15:42 - INFO - __main__ - Step 149284: {'lr': 2.8954512390155783e-08, 'samples': 28662528, 'steps': 149283, 'loss/train': 0.7918680310249329} 08/31/2021 16:15:43 - INFO - __main__ - Step 149285: {'lr': 2.8873804540835435e-08, 'samples': 28662720, 'steps': 149284, 'loss/train': 1.101383090019226} 08/31/2021 16:15:43 - INFO - __main__ - Step 149286: {'lr': 2.8793209324640136e-08, 'samples': 28662912, 'steps': 149285, 'loss/train': 0.7565836310386658} 08/31/2021 16:15:43 - INFO - __main__ - Step 149287: {'lr': 2.871272674159764e-08, 'samples': 28663104, 'steps': 149286, 'loss/train': 1.6241397857666016} 08/31/2021 16:15:44 - INFO - __main__ - Step 149288: {'lr': 2.8632356791791214e-08, 'samples': 28663296, 'steps': 149287, 'loss/train': 0.9071905016899109} 08/31/2021 16:15:44 - INFO - __main__ - Step 149289: {'lr': 2.8552099475193105e-08, 'samples': 28663488, 'steps': 149288, 'loss/train': 1.4075791835784912} 08/31/2021 16:15:46 - INFO - __main__ - Step 149290: {'lr': 2.8471954791914333e-08, 'samples': 28663680, 'steps': 149289, 'loss/train': 1.2057690620422363} 08/31/2021 16:15:46 - INFO - __main__ - Step 149291: {'lr': 2.8391922741927145e-08, 'samples': 28663872, 'steps': 149290, 'loss/train': 0.9161514043807983} 08/31/2021 16:15:47 - INFO - __main__ - Step 149292: {'lr': 2.831200332528705e-08, 'samples': 28664064, 'steps': 149291, 'loss/train': 1.4407062530517578} 08/31/2021 16:15:47 - INFO - __main__ - Step 149293: {'lr': 2.8232196542021803e-08, 'samples': 28664256, 'steps': 149292, 'loss/train': 0.7128425240516663} 08/31/2021 16:15:47 - INFO - __main__ - Step 149294: {'lr': 2.815250239218692e-08, 'samples': 28664448, 'steps': 149293, 'loss/train': 1.4948731660842896} 08/31/2021 16:15:49 - INFO - __main__ - Step 149295: {'lr': 2.8072920875810147e-08, 'samples': 28664640, 'steps': 149294, 'loss/train': 0.6396161913871765} 08/31/2021 16:15:49 - INFO - __main__ - Step 149296: {'lr': 2.799345199291925e-08, 'samples': 28664832, 'steps': 149295, 'loss/train': 1.0255714654922485} 08/31/2021 16:15:50 - INFO - __main__ - Step 149297: {'lr': 2.7914095743569734e-08, 'samples': 28665024, 'steps': 149296, 'loss/train': 0.3974173069000244} 08/31/2021 16:15:50 - INFO - __main__ - Step 149298: {'lr': 2.7834852127789356e-08, 'samples': 28665216, 'steps': 149297, 'loss/train': 0.8097521066665649} 08/31/2021 16:15:50 - INFO - __main__ - Step 149299: {'lr': 2.775572114560587e-08, 'samples': 28665408, 'steps': 149298, 'loss/train': 1.248744249343872} 08/31/2021 16:15:52 - INFO - __main__ - Step 149300: {'lr': 2.7676702797047036e-08, 'samples': 28665600, 'steps': 149299, 'loss/train': 1.5713183879852295} 08/31/2021 16:15:52 - INFO - __main__ - Step 149301: {'lr': 2.7597797082168365e-08, 'samples': 28665792, 'steps': 149300, 'loss/train': 1.1051762104034424} 08/31/2021 16:15:53 - INFO - __main__ - Step 149302: {'lr': 2.751900400096985e-08, 'samples': 28665984, 'steps': 149301, 'loss/train': 1.4289155006408691} 08/31/2021 16:15:53 - INFO - __main__ - Step 149303: {'lr': 2.7440323553562517e-08, 'samples': 28666176, 'steps': 149302, 'loss/train': 1.396754503250122} 08/31/2021 16:15:53 - INFO - __main__ - Step 149304: {'lr': 2.7361755739890858e-08, 'samples': 28666368, 'steps': 149303, 'loss/train': 0.8669261932373047} 08/31/2021 16:15:55 - INFO - __main__ - Step 149305: {'lr': 2.7283300560065894e-08, 'samples': 28666560, 'steps': 149304, 'loss/train': 1.387641429901123} 08/31/2021 16:15:55 - INFO - __main__ - Step 149306: {'lr': 2.7204958014059868e-08, 'samples': 28666752, 'steps': 149305, 'loss/train': 0.9075127243995667} 08/31/2021 16:15:56 - INFO - __main__ - Step 149307: {'lr': 2.7126728101956044e-08, 'samples': 28666944, 'steps': 149306, 'loss/train': 1.3421738147735596} 08/31/2021 16:15:56 - INFO - __main__ - Step 149308: {'lr': 2.7048610823782182e-08, 'samples': 28667136, 'steps': 149307, 'loss/train': 0.10680864751338959} 08/31/2021 16:15:56 - INFO - __main__ - Step 149309: {'lr': 2.6970606179538282e-08, 'samples': 28667328, 'steps': 149308, 'loss/train': 1.0830109119415283} 08/31/2021 16:15:58 - INFO - __main__ - Step 149310: {'lr': 2.689271416927985e-08, 'samples': 28667520, 'steps': 149309, 'loss/train': 0.7904610633850098} 08/31/2021 16:15:58 - INFO - __main__ - Step 149311: {'lr': 2.6814934793062408e-08, 'samples': 28667712, 'steps': 149310, 'loss/train': 1.2582954168319702} 08/31/2021 16:15:59 - INFO - __main__ - Step 149312: {'lr': 2.67372680509137e-08, 'samples': 28667904, 'steps': 149311, 'loss/train': 0.037715889513492584} 08/31/2021 16:15:59 - INFO - __main__ - Step 149313: {'lr': 2.665971394283373e-08, 'samples': 28668096, 'steps': 149312, 'loss/train': 0.9356303215026855} 08/31/2021 16:15:59 - INFO - __main__ - Step 149314: {'lr': 2.6582272468905767e-08, 'samples': 28668288, 'steps': 149313, 'loss/train': 0.936743974685669} 08/31/2021 16:16:01 - INFO - __main__ - Step 149315: {'lr': 2.6504943629129807e-08, 'samples': 28668480, 'steps': 149314, 'loss/train': 1.0989986658096313} 08/31/2021 16:16:02 - INFO - __main__ - Step 149316: {'lr': 2.6427727423561366e-08, 'samples': 28668672, 'steps': 149315, 'loss/train': 1.5901126861572266} 08/31/2021 16:16:02 - INFO - __main__ - Step 149317: {'lr': 2.6350623852228195e-08, 'samples': 28668864, 'steps': 149316, 'loss/train': 0.6985155940055847} 08/31/2021 16:16:02 - INFO - __main__ - Step 149318: {'lr': 2.6273632915158053e-08, 'samples': 28669056, 'steps': 149317, 'loss/train': 1.1387311220169067} 08/31/2021 16:16:03 - INFO - __main__ - Step 149319: {'lr': 2.619675461240645e-08, 'samples': 28669248, 'steps': 149318, 'loss/train': 1.2639551162719727} 08/31/2021 16:16:04 - INFO - __main__ - Step 149320: {'lr': 2.6119988943973384e-08, 'samples': 28669440, 'steps': 149319, 'loss/train': 0.7374293208122253} 08/31/2021 16:16:05 - INFO - __main__ - Step 149321: {'lr': 2.6043335909942122e-08, 'samples': 28669632, 'steps': 149320, 'loss/train': 1.0223761796951294} 08/31/2021 16:16:05 - INFO - __main__ - Step 149322: {'lr': 2.5966795510284912e-08, 'samples': 28669824, 'steps': 149321, 'loss/train': 0.8755068182945251} 08/31/2021 16:16:05 - INFO - __main__ - Step 149323: {'lr': 2.5890367745085018e-08, 'samples': 28670016, 'steps': 149322, 'loss/train': 0.6485480070114136} 08/31/2021 16:16:06 - INFO - __main__ - Step 149324: {'lr': 2.5814052614370197e-08, 'samples': 28670208, 'steps': 149323, 'loss/train': 0.27174535393714905} 08/31/2021 16:16:07 - INFO - __main__ - Step 149325: {'lr': 2.573785011814045e-08, 'samples': 28670400, 'steps': 149324, 'loss/train': 0.5316686630249023} 08/31/2021 16:16:08 - INFO - __main__ - Step 149326: {'lr': 2.566176025647904e-08, 'samples': 28670592, 'steps': 149325, 'loss/train': 0.5504992604255676} 08/31/2021 16:16:08 - INFO - __main__ - Step 149327: {'lr': 2.5585783029385967e-08, 'samples': 28670784, 'steps': 149326, 'loss/train': 1.2671395540237427} 08/31/2021 16:16:08 - INFO - __main__ - Step 149328: {'lr': 2.5509918436916745e-08, 'samples': 28670976, 'steps': 149327, 'loss/train': 1.4875746965408325} 08/31/2021 16:16:09 - INFO - __main__ - Step 149329: {'lr': 2.5434166479071374e-08, 'samples': 28671168, 'steps': 149328, 'loss/train': 1.386942982673645} 08/31/2021 16:16:10 - INFO - __main__ - Step 149330: {'lr': 2.535852715593312e-08, 'samples': 28671360, 'steps': 149329, 'loss/train': 0.2801617980003357} 08/31/2021 16:16:11 - INFO - __main__ - Step 149331: {'lr': 2.5283000467501984e-08, 'samples': 28671552, 'steps': 149330, 'loss/train': 1.2187702655792236} 08/31/2021 16:16:11 - INFO - __main__ - Step 149332: {'lr': 2.520758641383347e-08, 'samples': 28671744, 'steps': 149331, 'loss/train': 1.089982509613037} 08/31/2021 16:16:11 - INFO - __main__ - Step 149333: {'lr': 2.513228499492759e-08, 'samples': 28671936, 'steps': 149332, 'loss/train': 1.550225853919983} 08/31/2021 16:16:12 - INFO - __main__ - Step 149334: {'lr': 2.5057096210839846e-08, 'samples': 28672128, 'steps': 149333, 'loss/train': 1.172680377960205} 08/31/2021 16:16:12 - INFO - __main__ - Step 149335: {'lr': 2.4982020061625754e-08, 'samples': 28672320, 'steps': 149334, 'loss/train': 1.702683925628662} 08/31/2021 16:16:14 - INFO - __main__ - Step 149336: {'lr': 2.4907056547285312e-08, 'samples': 28672512, 'steps': 149335, 'loss/train': 1.3098315000534058} 08/31/2021 16:16:14 - INFO - __main__ - Step 149337: {'lr': 2.4832205667846273e-08, 'samples': 28672704, 'steps': 149336, 'loss/train': 1.1946101188659668} 08/31/2021 16:16:14 - INFO - __main__ - Step 149338: {'lr': 2.475746742339191e-08, 'samples': 28672896, 'steps': 149337, 'loss/train': 1.1380512714385986} 08/31/2021 16:16:15 - INFO - __main__ - Step 149339: {'lr': 2.468284181392222e-08, 'samples': 28673088, 'steps': 149338, 'loss/train': 1.4029631614685059} 08/31/2021 16:16:15 - INFO - __main__ - Step 149340: {'lr': 2.46083288394372e-08, 'samples': 28673280, 'steps': 149339, 'loss/train': 1.17002534866333} 08/31/2021 16:16:16 - INFO - __main__ - Step 149341: {'lr': 2.4533928500047876e-08, 'samples': 28673472, 'steps': 149340, 'loss/train': 0.486788809299469} 08/31/2021 16:16:17 - INFO - __main__ - Step 149342: {'lr': 2.445964079572649e-08, 'samples': 28673664, 'steps': 149341, 'loss/train': 1.3562792539596558} 08/31/2021 16:16:17 - INFO - __main__ - Step 149343: {'lr': 2.4385465726528557e-08, 'samples': 28673856, 'steps': 149342, 'loss/train': 1.073072075843811} 08/31/2021 16:16:18 - INFO - __main__ - Step 149344: {'lr': 2.4311403292481828e-08, 'samples': 28674048, 'steps': 149343, 'loss/train': 0.8422789573669434} 08/31/2021 16:16:18 - INFO - __main__ - Step 149345: {'lr': 2.4237453493641815e-08, 'samples': 28674240, 'steps': 149344, 'loss/train': 1.1109871864318848} 08/31/2021 16:16:19 - INFO - __main__ - Step 149346: {'lr': 2.416361633000852e-08, 'samples': 28674432, 'steps': 149345, 'loss/train': 0.6603028774261475} 08/31/2021 16:16:20 - INFO - __main__ - Step 149347: {'lr': 2.4089891801609698e-08, 'samples': 28674624, 'steps': 149346, 'loss/train': 1.538143515586853} 08/31/2021 16:16:20 - INFO - __main__ - Step 149348: {'lr': 2.4016279908528616e-08, 'samples': 28674816, 'steps': 149347, 'loss/train': 0.60844486951828} 08/31/2021 16:16:21 - INFO - __main__ - Step 149349: {'lr': 2.3942780650765273e-08, 'samples': 28675008, 'steps': 149348, 'loss/train': 1.267686128616333} 08/31/2021 16:16:21 - INFO - __main__ - Step 149350: {'lr': 2.3869394028347423e-08, 'samples': 28675200, 'steps': 149349, 'loss/train': 0.7339107990264893} 08/31/2021 16:16:22 - INFO - __main__ - Step 149351: {'lr': 2.3796120041302827e-08, 'samples': 28675392, 'steps': 149350, 'loss/train': 1.3607956171035767} 08/31/2021 16:16:23 - INFO - __main__ - Step 149352: {'lr': 2.3722958689686992e-08, 'samples': 28675584, 'steps': 149351, 'loss/train': 1.4330112934112549} 08/31/2021 16:16:23 - INFO - __main__ - Step 149353: {'lr': 2.3649909973555427e-08, 'samples': 28675776, 'steps': 149352, 'loss/train': 1.1327910423278809} 08/31/2021 16:16:24 - INFO - __main__ - Step 149354: {'lr': 2.3576973892880384e-08, 'samples': 28675968, 'steps': 149353, 'loss/train': 1.6701164245605469} 08/31/2021 16:16:24 - INFO - __main__ - Step 149355: {'lr': 2.3504150447717364e-08, 'samples': 28676160, 'steps': 149354, 'loss/train': 0.6367502808570862} 08/31/2021 16:16:25 - INFO - __main__ - Step 149356: {'lr': 2.3431439638121887e-08, 'samples': 28676352, 'steps': 149355, 'loss/train': 1.6727242469787598} 08/31/2021 16:16:26 - INFO - __main__ - Step 149357: {'lr': 2.335884146409395e-08, 'samples': 28676544, 'steps': 149356, 'loss/train': 0.8560212254524231} 08/31/2021 16:16:26 - INFO - __main__ - Step 149358: {'lr': 2.3286355925716817e-08, 'samples': 28676736, 'steps': 149357, 'loss/train': 0.5386105179786682} 08/31/2021 16:16:26 - INFO - __main__ - Step 149359: {'lr': 2.3213983022962735e-08, 'samples': 28676928, 'steps': 149358, 'loss/train': 1.3037306070327759} 08/31/2021 16:16:27 - INFO - __main__ - Step 149360: {'lr': 2.3141722755887216e-08, 'samples': 28677120, 'steps': 149359, 'loss/train': 1.340198040008545} 08/31/2021 16:16:28 - INFO - __main__ - Step 149361: {'lr': 2.3069575124545773e-08, 'samples': 28677312, 'steps': 149360, 'loss/train': 0.5033765435218811} 08/31/2021 16:16:29 - INFO - __main__ - Step 149362: {'lr': 2.29975401289384e-08, 'samples': 28677504, 'steps': 149361, 'loss/train': 1.1101455688476562} 08/31/2021 16:16:29 - INFO - __main__ - Step 149363: {'lr': 2.292561776912061e-08, 'samples': 28677696, 'steps': 149362, 'loss/train': 0.888960063457489} 08/31/2021 16:16:29 - INFO - __main__ - Step 149364: {'lr': 2.2853808045092407e-08, 'samples': 28677888, 'steps': 149363, 'loss/train': 0.8785412907600403} 08/31/2021 16:16:30 - INFO - __main__ - Step 149365: {'lr': 2.278211095693705e-08, 'samples': 28678080, 'steps': 149364, 'loss/train': 1.0721994638442993} 08/31/2021 16:16:31 - INFO - __main__ - Step 149366: {'lr': 2.271052650465455e-08, 'samples': 28678272, 'steps': 149365, 'loss/train': 1.037221908569336} 08/31/2021 16:16:32 - INFO - __main__ - Step 149367: {'lr': 2.2639054688272654e-08, 'samples': 28678464, 'steps': 149366, 'loss/train': 1.459964632987976} 08/31/2021 16:16:32 - INFO - __main__ - Step 149368: {'lr': 2.2567695507819118e-08, 'samples': 28678656, 'steps': 149367, 'loss/train': 1.289318323135376} 08/31/2021 16:16:33 - INFO - __main__ - Step 149369: {'lr': 2.2496448963377213e-08, 'samples': 28678848, 'steps': 149368, 'loss/train': 1.0719523429870605} 08/31/2021 16:16:33 - INFO - __main__ - Step 149370: {'lr': 2.2425315054891426e-08, 'samples': 28679040, 'steps': 149369, 'loss/train': 0.7586663365364075} 08/31/2021 16:16:33 - INFO - __main__ - Step 149371: {'lr': 2.2354293782472778e-08, 'samples': 28679232, 'steps': 149370, 'loss/train': 0.9285395741462708} 08/31/2021 16:16:35 - INFO - __main__ - Step 149372: {'lr': 2.2283385146121272e-08, 'samples': 28679424, 'steps': 149371, 'loss/train': 1.0957003831863403} 08/31/2021 16:16:36 - INFO - __main__ - Step 149373: {'lr': 2.2212589145892415e-08, 'samples': 28679616, 'steps': 149372, 'loss/train': 0.4124198257923126} 08/31/2021 16:16:36 - INFO - __main__ - Step 149374: {'lr': 2.2141905781758454e-08, 'samples': 28679808, 'steps': 149373, 'loss/train': 1.3710929155349731} 08/31/2021 16:16:37 - INFO - __main__ - Step 149375: {'lr': 2.2071335053802653e-08, 'samples': 28680000, 'steps': 149374, 'loss/train': 1.4291260242462158} 08/31/2021 16:16:37 - INFO - __main__ - Step 149376: {'lr': 2.2000876962052775e-08, 'samples': 28680192, 'steps': 149375, 'loss/train': 0.694853663444519} 08/31/2021 16:16:39 - INFO - __main__ - Step 149377: {'lr': 2.1930531506536567e-08, 'samples': 28680384, 'steps': 149376, 'loss/train': 0.7464139461517334} 08/31/2021 16:16:40 - INFO - __main__ - Step 149378: {'lr': 2.1860298687281787e-08, 'samples': 28680576, 'steps': 149377, 'loss/train': 0.7235710024833679} 08/31/2021 16:16:40 - INFO - __main__ - Step 149379: {'lr': 2.179017850428844e-08, 'samples': 28680768, 'steps': 149378, 'loss/train': 0.8886459469795227} 08/31/2021 16:16:40 - INFO - __main__ - Step 149380: {'lr': 2.1720170957639783e-08, 'samples': 28680960, 'steps': 149379, 'loss/train': 0.9554017186164856} 08/31/2021 16:16:41 - INFO - __main__ - Step 149381: {'lr': 2.165027604736358e-08, 'samples': 28681152, 'steps': 149380, 'loss/train': 0.9885128140449524} 08/31/2021 16:16:41 - INFO - __main__ - Step 149382: {'lr': 2.158049377345983e-08, 'samples': 28681344, 'steps': 149381, 'loss/train': 0.5809337496757507} 08/31/2021 16:16:43 - INFO - __main__ - Step 149383: {'lr': 2.1510824135956286e-08, 'samples': 28681536, 'steps': 149382, 'loss/train': 0.9914427995681763} 08/31/2021 16:16:43 - INFO - __main__ - Step 149384: {'lr': 2.1441267134936215e-08, 'samples': 28681728, 'steps': 149383, 'loss/train': 1.134682059288025} 08/31/2021 16:16:43 - INFO - __main__ - Step 149385: {'lr': 2.1371822770371864e-08, 'samples': 28681920, 'steps': 149384, 'loss/train': 1.1895174980163574} 08/31/2021 16:16:44 - INFO - __main__ - Step 149386: {'lr': 2.1302491042318738e-08, 'samples': 28682112, 'steps': 149385, 'loss/train': 1.051695466041565} 08/31/2021 16:16:44 - INFO - __main__ - Step 149387: {'lr': 2.1233271950832354e-08, 'samples': 28682304, 'steps': 149386, 'loss/train': 0.8212248086929321} 08/31/2021 16:16:46 - INFO - __main__ - Step 149388: {'lr': 2.1164165495912714e-08, 'samples': 28682496, 'steps': 149387, 'loss/train': 0.9022325277328491} 08/31/2021 16:16:46 - INFO - __main__ - Step 149389: {'lr': 2.1095171677587566e-08, 'samples': 28682688, 'steps': 149388, 'loss/train': 1.032414197921753} 08/31/2021 16:16:46 - INFO - __main__ - Step 149390: {'lr': 2.1026290495912425e-08, 'samples': 28682880, 'steps': 149389, 'loss/train': 1.1213934421539307} 08/31/2021 16:16:47 - INFO - __main__ - Step 149391: {'lr': 2.0957521950887294e-08, 'samples': 28683072, 'steps': 149390, 'loss/train': 1.2905840873718262} 08/31/2021 16:16:47 - INFO - __main__ - Step 149392: {'lr': 2.0888866042567677e-08, 'samples': 28683264, 'steps': 149391, 'loss/train': 0.9686596393585205} 08/31/2021 16:16:49 - INFO - __main__ - Step 149393: {'lr': 2.0820322770981337e-08, 'samples': 28683456, 'steps': 149392, 'loss/train': 0.9687290191650391} 08/31/2021 16:16:49 - INFO - __main__ - Step 149394: {'lr': 2.0751892136156025e-08, 'samples': 28683648, 'steps': 149393, 'loss/train': 5.696658611297607} 08/31/2021 16:16:50 - INFO - __main__ - Step 149395: {'lr': 2.0683574138147254e-08, 'samples': 28683840, 'steps': 149394, 'loss/train': 0.928611159324646} 08/31/2021 16:16:50 - INFO - __main__ - Step 149396: {'lr': 2.0615368776927267e-08, 'samples': 28684032, 'steps': 149395, 'loss/train': 1.5328214168548584} 08/31/2021 16:16:50 - INFO - __main__ - Step 149397: {'lr': 2.0547276052579333e-08, 'samples': 28684224, 'steps': 149396, 'loss/train': 0.6079760193824768} 08/31/2021 16:16:51 - INFO - __main__ - Step 149398: {'lr': 2.047929596510345e-08, 'samples': 28684416, 'steps': 149397, 'loss/train': 1.354782223701477} 08/31/2021 16:16:52 - INFO - __main__ - Step 149399: {'lr': 2.0411428514527375e-08, 'samples': 28684608, 'steps': 149398, 'loss/train': 1.4226962327957153} 08/31/2021 16:16:53 - INFO - __main__ - Step 149400: {'lr': 2.0343673700934374e-08, 'samples': 28684800, 'steps': 149399, 'loss/train': 1.4229941368103027} 08/31/2021 16:16:53 - INFO - __main__ - Step 149401: {'lr': 2.027603152429669e-08, 'samples': 28684992, 'steps': 149400, 'loss/train': 0.6491358876228333} 08/31/2021 16:16:53 - INFO - __main__ - Step 149402: {'lr': 2.0208501984669834e-08, 'samples': 28685184, 'steps': 149401, 'loss/train': 1.1153968572616577} 08/31/2021 16:16:54 - INFO - __main__ - Step 149403: {'lr': 2.014108508205381e-08, 'samples': 28685376, 'steps': 149402, 'loss/train': 0.8361360430717468} 08/31/2021 16:16:55 - INFO - __main__ - Step 149404: {'lr': 2.0073780816531884e-08, 'samples': 28685568, 'steps': 149403, 'loss/train': 0.7650647163391113} 08/31/2021 16:16:56 - INFO - __main__ - Step 149405: {'lr': 2.000658918810405e-08, 'samples': 28685760, 'steps': 149404, 'loss/train': 0.8320692181587219} 08/31/2021 16:16:56 - INFO - __main__ - Step 149406: {'lr': 1.993951019679807e-08, 'samples': 28685952, 'steps': 149405, 'loss/train': 1.3613494634628296} 08/31/2021 16:16:56 - INFO - __main__ - Step 149407: {'lr': 1.9872543842669456e-08, 'samples': 28686144, 'steps': 149406, 'loss/train': 1.3041677474975586} 08/31/2021 16:16:57 - INFO - __main__ - Step 149408: {'lr': 1.98056901257182e-08, 'samples': 28686336, 'steps': 149407, 'loss/train': 0.8491310477256775} 08/31/2021 16:16:58 - INFO - __main__ - Step 149409: {'lr': 1.9738949045972064e-08, 'samples': 28686528, 'steps': 149408, 'loss/train': 1.057273030281067} 08/31/2021 16:16:59 - INFO - __main__ - Step 149410: {'lr': 1.967232060348656e-08, 'samples': 28686720, 'steps': 149409, 'loss/train': 1.419836401939392} 08/31/2021 16:16:59 - INFO - __main__ - Step 149411: {'lr': 1.9605804798261684e-08, 'samples': 28686912, 'steps': 149410, 'loss/train': 0.9846921563148499} 08/31/2021 16:17:00 - INFO - __main__ - Step 149412: {'lr': 1.953940163035295e-08, 'samples': 28687104, 'steps': 149411, 'loss/train': 0.7937405705451965} 08/31/2021 16:17:00 - INFO - __main__ - Step 149413: {'lr': 1.947311109978811e-08, 'samples': 28687296, 'steps': 149412, 'loss/train': 4.851861000061035} 08/31/2021 16:17:00 - INFO - __main__ - Step 149414: {'lr': 1.9406933206594924e-08, 'samples': 28687488, 'steps': 149413, 'loss/train': 0.9580556154251099} 08/31/2021 16:17:02 - INFO - __main__ - Step 149415: {'lr': 1.9340867950801145e-08, 'samples': 28687680, 'steps': 149414, 'loss/train': 0.8248059749603271} 08/31/2021 16:17:02 - INFO - __main__ - Step 149416: {'lr': 1.927491533243453e-08, 'samples': 28687872, 'steps': 149415, 'loss/train': 0.9484409689903259} 08/31/2021 16:17:03 - INFO - __main__ - Step 149417: {'lr': 1.920907535152283e-08, 'samples': 28688064, 'steps': 149416, 'loss/train': 0.8546991944313049} 08/31/2021 16:17:03 - INFO - __main__ - Step 149418: {'lr': 1.9143348008093807e-08, 'samples': 28688256, 'steps': 149417, 'loss/train': 0.9884309768676758} 08/31/2021 16:17:03 - INFO - __main__ - Step 149419: {'lr': 1.9077733302175217e-08, 'samples': 28688448, 'steps': 149418, 'loss/train': 1.7223397493362427} 08/31/2021 16:17:04 - INFO - __main__ - Step 149420: {'lr': 1.9012231233822564e-08, 'samples': 28688640, 'steps': 149419, 'loss/train': 1.2177537679672241} 08/31/2021 16:17:05 - INFO - __main__ - Step 149421: {'lr': 1.8946841803035852e-08, 'samples': 28688832, 'steps': 149420, 'loss/train': 1.1690056324005127} 08/31/2021 16:17:06 - INFO - __main__ - Step 149422: {'lr': 1.8881565009842837e-08, 'samples': 28689024, 'steps': 149421, 'loss/train': 1.2149111032485962} 08/31/2021 16:17:06 - INFO - __main__ - Step 149423: {'lr': 1.881640085429903e-08, 'samples': 28689216, 'steps': 149422, 'loss/train': 0.8469328880310059} 08/31/2021 16:17:06 - INFO - __main__ - Step 149424: {'lr': 1.8751349336404435e-08, 'samples': 28689408, 'steps': 149423, 'loss/train': 0.8199699521064758} 08/31/2021 16:17:07 - INFO - __main__ - Step 149425: {'lr': 1.8686410456214554e-08, 'samples': 28689600, 'steps': 149424, 'loss/train': 0.4130759835243225} 08/31/2021 16:17:09 - INFO - __main__ - Step 149426: {'lr': 1.8621584213757148e-08, 'samples': 28689792, 'steps': 149425, 'loss/train': 0.07688076049089432} 08/31/2021 16:17:09 - INFO - __main__ - Step 149427: {'lr': 1.8556870609032217e-08, 'samples': 28689984, 'steps': 149426, 'loss/train': 1.1309326887130737} 08/31/2021 16:17:10 - INFO - __main__ - Step 149428: {'lr': 1.8492269642095272e-08, 'samples': 28690176, 'steps': 149427, 'loss/train': 1.2384443283081055} 08/31/2021 16:17:10 - INFO - __main__ - Step 149429: {'lr': 1.842778131297407e-08, 'samples': 28690368, 'steps': 149428, 'loss/train': 1.450964093208313} 08/31/2021 16:17:10 - INFO - __main__ - Step 149430: {'lr': 1.8363405621668606e-08, 'samples': 28690560, 'steps': 149429, 'loss/train': 1.9713541269302368} 08/31/2021 16:17:12 - INFO - __main__ - Step 149431: {'lr': 1.8299142568262152e-08, 'samples': 28690752, 'steps': 149430, 'loss/train': 1.038103699684143} 08/31/2021 16:17:12 - INFO - __main__ - Step 149432: {'lr': 1.8234992152726947e-08, 'samples': 28690944, 'steps': 149431, 'loss/train': 0.9896854758262634} 08/31/2021 16:17:13 - INFO - __main__ - Step 149433: {'lr': 1.817095437511851e-08, 'samples': 28691136, 'steps': 149432, 'loss/train': 0.8354292511940002} 08/31/2021 16:17:13 - INFO - __main__ - Step 149434: {'lr': 1.8107029235492345e-08, 'samples': 28691328, 'steps': 149433, 'loss/train': 1.5631258487701416} 08/31/2021 16:17:13 - INFO - __main__ - Step 149435: {'lr': 1.8043216733820698e-08, 'samples': 28691520, 'steps': 149434, 'loss/train': 0.855924665927887} 08/31/2021 16:17:15 - INFO - __main__ - Step 149436: {'lr': 1.7979516870186842e-08, 'samples': 28691712, 'steps': 149435, 'loss/train': 1.0031671524047852} 08/31/2021 16:17:15 - INFO - __main__ - Step 149437: {'lr': 1.7915929644563013e-08, 'samples': 28691904, 'steps': 149436, 'loss/train': 0.9945286512374878} 08/31/2021 16:17:16 - INFO - __main__ - Step 149438: {'lr': 1.7852455057032478e-08, 'samples': 28692096, 'steps': 149437, 'loss/train': 0.794974148273468} 08/31/2021 16:17:16 - INFO - __main__ - Step 149439: {'lr': 1.7789093107595245e-08, 'samples': 28692288, 'steps': 149438, 'loss/train': 1.5058069229125977} 08/31/2021 16:17:16 - INFO - __main__ - Step 149440: {'lr': 1.7725843796279063e-08, 'samples': 28692480, 'steps': 149439, 'loss/train': 1.2644840478897095} 08/31/2021 16:17:18 - INFO - __main__ - Step 149441: {'lr': 1.7662707123139443e-08, 'samples': 28692672, 'steps': 149440, 'loss/train': 1.0098118782043457} 08/31/2021 16:17:18 - INFO - __main__ - Step 149442: {'lr': 1.759968308814863e-08, 'samples': 28692864, 'steps': 149441, 'loss/train': 0.49024200439453125} 08/31/2021 16:17:19 - INFO - __main__ - Step 149443: {'lr': 1.7536771691389895e-08, 'samples': 28693056, 'steps': 149442, 'loss/train': 1.1553887128829956} 08/31/2021 16:17:19 - INFO - __main__ - Step 149444: {'lr': 1.7473972932890992e-08, 'samples': 28693248, 'steps': 149443, 'loss/train': 0.14327619969844818} 08/31/2021 16:17:19 - INFO - __main__ - Step 149445: {'lr': 1.741128681262416e-08, 'samples': 28693440, 'steps': 149444, 'loss/train': 1.4027020931243896} 08/31/2021 16:17:21 - INFO - __main__ - Step 149446: {'lr': 1.7348713330672673e-08, 'samples': 28693632, 'steps': 149445, 'loss/train': 0.7180373668670654} 08/31/2021 16:17:21 - INFO - __main__ - Step 149447: {'lr': 1.7286252487036524e-08, 'samples': 28693824, 'steps': 149446, 'loss/train': 1.492883563041687} 08/31/2021 16:17:22 - INFO - __main__ - Step 149448: {'lr': 1.722390428177123e-08, 'samples': 28694016, 'steps': 149447, 'loss/train': 0.999122142791748} 08/31/2021 16:17:22 - INFO - __main__ - Step 149449: {'lr': 1.7161668714876787e-08, 'samples': 28694208, 'steps': 149448, 'loss/train': 0.4853144884109497} 08/31/2021 16:17:22 - INFO - __main__ - Step 149450: {'lr': 1.7099545786380956e-08, 'samples': 28694400, 'steps': 149449, 'loss/train': 0.11799097061157227} 08/31/2021 16:17:24 - INFO - __main__ - Step 149451: {'lr': 1.7037535496339242e-08, 'samples': 28694592, 'steps': 149450, 'loss/train': 1.5450439453125} 08/31/2021 16:17:25 - INFO - __main__ - Step 149452: {'lr': 1.6975637844751645e-08, 'samples': 28694784, 'steps': 149451, 'loss/train': 1.0171922445297241} 08/31/2021 16:17:25 - INFO - __main__ - Step 149453: {'lr': 1.6913852831673683e-08, 'samples': 28694976, 'steps': 149452, 'loss/train': 1.182690143585205} 08/31/2021 16:17:25 - INFO - __main__ - Step 149454: {'lr': 1.685218045710535e-08, 'samples': 28695168, 'steps': 149453, 'loss/train': 1.3663207292556763} 08/31/2021 16:17:26 - INFO - __main__ - Step 149455: {'lr': 1.6790620721074403e-08, 'samples': 28695360, 'steps': 149454, 'loss/train': 0.47929465770721436} 08/31/2021 16:17:26 - INFO - __main__ - Step 149456: {'lr': 1.672917362363635e-08, 'samples': 28695552, 'steps': 149455, 'loss/train': 1.2085223197937012} 08/31/2021 16:17:28 - INFO - __main__ - Step 149457: {'lr': 1.6667839164818956e-08, 'samples': 28695744, 'steps': 149456, 'loss/train': 0.8823762536048889} 08/31/2021 16:17:29 - INFO - __main__ - Step 149458: {'lr': 1.6606617344594455e-08, 'samples': 28695936, 'steps': 149457, 'loss/train': 0.713706910610199} 08/31/2021 16:17:29 - INFO - __main__ - Step 149459: {'lr': 1.654550816304612e-08, 'samples': 28696128, 'steps': 149458, 'loss/train': 0.8502429127693176} 08/31/2021 16:17:29 - INFO - __main__ - Step 149460: {'lr': 1.6484511620201704e-08, 'samples': 28696320, 'steps': 149459, 'loss/train': 0.08805025368928909} 08/31/2021 16:17:30 - INFO - __main__ - Step 149461: {'lr': 1.6423627716061208e-08, 'samples': 28696512, 'steps': 149460, 'loss/train': 1.558963656425476} 08/31/2021 16:17:31 - INFO - __main__ - Step 149462: {'lr': 1.6362856450652385e-08, 'samples': 28696704, 'steps': 149461, 'loss/train': 1.283721685409546} 08/31/2021 16:17:32 - INFO - __main__ - Step 149463: {'lr': 1.630219782403075e-08, 'samples': 28696896, 'steps': 149462, 'loss/train': 1.6394845247268677} 08/31/2021 16:17:32 - INFO - __main__ - Step 149464: {'lr': 1.6241651836168547e-08, 'samples': 28697088, 'steps': 149463, 'loss/train': 0.4682273268699646} 08/31/2021 16:17:32 - INFO - __main__ - Step 149465: {'lr': 1.6181218487176798e-08, 'samples': 28697280, 'steps': 149464, 'loss/train': 0.618412435054779} 08/31/2021 16:17:33 - INFO - __main__ - Step 149466: {'lr': 1.6120897776999988e-08, 'samples': 28697472, 'steps': 149465, 'loss/train': 0.03529710695147514} 08/31/2021 16:17:34 - INFO - __main__ - Step 149467: {'lr': 1.6060689705721386e-08, 'samples': 28697664, 'steps': 149466, 'loss/train': 0.8561792373657227} 08/31/2021 16:17:35 - INFO - __main__ - Step 149468: {'lr': 1.6000594273340995e-08, 'samples': 28697856, 'steps': 149467, 'loss/train': 1.11272394657135} 08/31/2021 16:17:35 - INFO - __main__ - Step 149469: {'lr': 1.5940611479914325e-08, 'samples': 28698048, 'steps': 149468, 'loss/train': 1.0987269878387451} 08/31/2021 16:17:35 - INFO - __main__ - Step 149470: {'lr': 1.5880741325413616e-08, 'samples': 28698240, 'steps': 149469, 'loss/train': 0.9710449576377869} 08/31/2021 16:17:36 - INFO - __main__ - Step 149471: {'lr': 1.5820983809922142e-08, 'samples': 28698432, 'steps': 149470, 'loss/train': 0.34495967626571655} 08/31/2021 16:17:37 - INFO - __main__ - Step 149472: {'lr': 1.5761338933439896e-08, 'samples': 28698624, 'steps': 149471, 'loss/train': 1.1561020612716675} 08/31/2021 16:17:38 - INFO - __main__ - Step 149473: {'lr': 1.5701806695994636e-08, 'samples': 28698816, 'steps': 149472, 'loss/train': 1.2226369380950928} 08/31/2021 16:17:38 - INFO - __main__ - Step 149474: {'lr': 1.5642387097614118e-08, 'samples': 28699008, 'steps': 149473, 'loss/train': 0.7697595357894897} 08/31/2021 16:17:38 - INFO - __main__ - Step 149475: {'lr': 1.55830801383261e-08, 'samples': 28699200, 'steps': 149474, 'loss/train': 1.2551002502441406} 08/31/2021 16:17:39 - INFO - __main__ - Step 149476: {'lr': 1.552388581818609e-08, 'samples': 28699392, 'steps': 149475, 'loss/train': 0.8608070611953735} 08/31/2021 16:17:39 - INFO - __main__ - Step 149477: {'lr': 1.5464804137166332e-08, 'samples': 28699584, 'steps': 149476, 'loss/train': 1.7664400339126587} 08/31/2021 16:17:40 - INFO - __main__ - Step 149478: {'lr': 1.540583509532234e-08, 'samples': 28699776, 'steps': 149477, 'loss/train': 1.0682145357131958} 08/31/2021 16:17:41 - INFO - __main__ - Step 149479: {'lr': 1.5346978692681867e-08, 'samples': 28699968, 'steps': 149478, 'loss/train': 1.2386579513549805} 08/31/2021 16:17:41 - INFO - __main__ - Step 149480: {'lr': 1.528823492927267e-08, 'samples': 28700160, 'steps': 149479, 'loss/train': 0.9890946745872498} 08/31/2021 16:17:42 - INFO - __main__ - Step 149481: {'lr': 1.5229603805122505e-08, 'samples': 28700352, 'steps': 149480, 'loss/train': 1.1810591220855713} 08/31/2021 16:17:42 - INFO - __main__ - Step 149482: {'lr': 1.5171085320231372e-08, 'samples': 28700544, 'steps': 149481, 'loss/train': 0.8969607949256897} 08/31/2021 16:17:44 - INFO - __main__ - Step 149483: {'lr': 1.511267947465478e-08, 'samples': 28700736, 'steps': 149482, 'loss/train': 1.1022127866744995} 08/31/2021 16:17:45 - INFO - __main__ - Step 149484: {'lr': 1.5054386268420484e-08, 'samples': 28700928, 'steps': 149483, 'loss/train': 1.2295061349868774} 08/31/2021 16:17:45 - INFO - __main__ - Step 149485: {'lr': 1.4996205701528486e-08, 'samples': 28701120, 'steps': 149484, 'loss/train': 0.9227685928344727} 08/31/2021 16:17:45 - INFO - __main__ - Step 149486: {'lr': 1.49381377740343e-08, 'samples': 28701312, 'steps': 149485, 'loss/train': 1.4156889915466309} 08/31/2021 16:17:46 - INFO - __main__ - Step 149487: {'lr': 1.4880182485965677e-08, 'samples': 28701504, 'steps': 149486, 'loss/train': 1.6056159734725952} 08/31/2021 16:17:47 - INFO - __main__ - Step 149488: {'lr': 1.4822339837322619e-08, 'samples': 28701696, 'steps': 149487, 'loss/train': 0.5971378087997437} 08/31/2021 16:17:48 - INFO - __main__ - Step 149489: {'lr': 1.476460982813288e-08, 'samples': 28701888, 'steps': 149488, 'loss/train': 0.6176903247833252} 08/31/2021 16:17:48 - INFO - __main__ - Step 149490: {'lr': 1.4706992458424218e-08, 'samples': 28702080, 'steps': 149489, 'loss/train': 0.9453899264335632} 08/31/2021 16:17:48 - INFO - __main__ - Step 149491: {'lr': 1.4649487728252141e-08, 'samples': 28702272, 'steps': 149490, 'loss/train': 1.1441307067871094} 08/31/2021 16:17:49 - INFO - __main__ - Step 149492: {'lr': 1.4592095637616654e-08, 'samples': 28702464, 'steps': 149491, 'loss/train': 1.45304274559021} 08/31/2021 16:17:51 - INFO - __main__ - Step 149493: {'lr': 1.4534816186545507e-08, 'samples': 28702656, 'steps': 149492, 'loss/train': 1.2551989555358887} 08/31/2021 16:17:51 - INFO - __main__ - Step 149494: {'lr': 1.447764937506646e-08, 'samples': 28702848, 'steps': 149493, 'loss/train': 1.218214988708496} 08/31/2021 16:17:52 - INFO - __main__ - Step 149495: {'lr': 1.4420595203207264e-08, 'samples': 28703040, 'steps': 149494, 'loss/train': 0.10483254492282867} 08/31/2021 16:17:52 - INFO - __main__ - Step 149496: {'lr': 1.436365367099568e-08, 'samples': 28703232, 'steps': 149495, 'loss/train': 0.2583048939704895} 08/31/2021 16:17:52 - INFO - __main__ - Step 149497: {'lr': 1.430682477845946e-08, 'samples': 28703424, 'steps': 149496, 'loss/train': 1.5258179903030396} 08/31/2021 16:17:53 - INFO - __main__ - Step 149498: {'lr': 1.425010852562636e-08, 'samples': 28703616, 'steps': 149497, 'loss/train': 0.20035502314567566} 08/31/2021 16:17:53 - INFO - __main__ - Step 149499: {'lr': 1.419350491249638e-08, 'samples': 28703808, 'steps': 149498, 'loss/train': 2.3689560890197754} 08/31/2021 16:17:55 - INFO - __main__ - Step 149500: {'lr': 1.4137013939125031e-08, 'samples': 28704000, 'steps': 149499, 'loss/train': 2.2993505001068115} 08/31/2021 16:17:55 - INFO - __main__ - Step 149501: {'lr': 1.4080635605512315e-08, 'samples': 28704192, 'steps': 149500, 'loss/train': 0.8845888376235962} 08/31/2021 16:17:56 - INFO - __main__ - Step 149502: {'lr': 1.4024369911713742e-08, 'samples': 28704384, 'steps': 149501, 'loss/train': 1.349462628364563} 08/31/2021 16:17:56 - INFO - __main__ - Step 149503: {'lr': 1.396821685772931e-08, 'samples': 28704576, 'steps': 149502, 'loss/train': 1.4796016216278076} 08/31/2021 16:17:56 - INFO - __main__ - Step 149504: {'lr': 1.3912176443586778e-08, 'samples': 28704768, 'steps': 149503, 'loss/train': 1.0935126543045044} 08/31/2021 16:17:58 - INFO - __main__ - Step 149505: {'lr': 1.3856248669313897e-08, 'samples': 28704960, 'steps': 149504, 'loss/train': 0.7969018220901489} 08/31/2021 16:17:58 - INFO - __main__ - Step 149506: {'lr': 1.3800433534966184e-08, 'samples': 28705152, 'steps': 149505, 'loss/train': 0.3863592743873596} 08/31/2021 16:17:59 - INFO - __main__ - Step 149507: {'lr': 1.3744731040515879e-08, 'samples': 28705344, 'steps': 149506, 'loss/train': 1.2683818340301514} 08/31/2021 16:17:59 - INFO - __main__ - Step 149508: {'lr': 1.3689141186018495e-08, 'samples': 28705536, 'steps': 149507, 'loss/train': 1.1671522855758667} 08/31/2021 16:17:59 - INFO - __main__ - Step 149509: {'lr': 1.3633663971501787e-08, 'samples': 28705728, 'steps': 149508, 'loss/train': 1.6497350931167603} 08/31/2021 16:18:01 - INFO - __main__ - Step 149510: {'lr': 1.357829939699351e-08, 'samples': 28705920, 'steps': 149509, 'loss/train': 0.9861106872558594} 08/31/2021 16:18:01 - INFO - __main__ - Step 149511: {'lr': 1.3523047462493666e-08, 'samples': 28706112, 'steps': 149510, 'loss/train': 1.036027431488037} 08/31/2021 16:18:02 - INFO - __main__ - Step 149512: {'lr': 1.3467908168057763e-08, 'samples': 28706304, 'steps': 149511, 'loss/train': 1.113120436668396} 08/31/2021 16:18:02 - INFO - __main__ - Step 149513: {'lr': 1.3412881513685803e-08, 'samples': 28706496, 'steps': 149512, 'loss/train': 0.02048400044441223} 08/31/2021 16:18:02 - INFO - __main__ - Step 149514: {'lr': 1.3357967499405544e-08, 'samples': 28706688, 'steps': 149513, 'loss/train': 1.0190931558609009} 08/31/2021 16:18:04 - INFO - __main__ - Step 149515: {'lr': 1.3303166125244737e-08, 'samples': 28706880, 'steps': 149514, 'loss/train': 0.0681178867816925} 08/31/2021 16:18:04 - INFO - __main__ - Step 149516: {'lr': 1.3248477391258895e-08, 'samples': 28707072, 'steps': 149515, 'loss/train': 1.290552020072937} 08/31/2021 16:18:05 - INFO - __main__ - Step 149517: {'lr': 1.3193901297420262e-08, 'samples': 28707264, 'steps': 149516, 'loss/train': 0.9790732860565186} 08/31/2021 16:18:05 - INFO - __main__ - Step 149518: {'lr': 1.3139437843784352e-08, 'samples': 28707456, 'steps': 149517, 'loss/train': 0.504824697971344} 08/31/2021 16:18:05 - INFO - __main__ - Step 149519: {'lr': 1.3085087030378917e-08, 'samples': 28707648, 'steps': 149518, 'loss/train': 0.34429359436035156} 08/31/2021 16:18:07 - INFO - __main__ - Step 149520: {'lr': 1.3030848857231714e-08, 'samples': 28707840, 'steps': 149519, 'loss/train': 0.6398456692695618} 08/31/2021 16:18:07 - INFO - __main__ - Step 149521: {'lr': 1.2976723324342743e-08, 'samples': 28708032, 'steps': 149520, 'loss/train': 1.0720289945602417} 08/31/2021 16:18:08 - INFO - __main__ - Step 149522: {'lr': 1.2922710431739759e-08, 'samples': 28708224, 'steps': 149521, 'loss/train': 1.0947211980819702} 08/31/2021 16:18:08 - INFO - __main__ - Step 149523: {'lr': 1.2868810179450519e-08, 'samples': 28708416, 'steps': 149522, 'loss/train': 1.5823525190353394} 08/31/2021 16:18:08 - INFO - __main__ - Step 149524: {'lr': 1.2815022567530532e-08, 'samples': 28708608, 'steps': 149523, 'loss/train': 1.028520107269287} 08/31/2021 16:18:09 - INFO - __main__ - Step 149525: {'lr': 1.2761347595952044e-08, 'samples': 28708800, 'steps': 149524, 'loss/train': 1.565508484840393} 08/31/2021 16:18:10 - INFO - __main__ - Step 149526: {'lr': 1.2707785264798321e-08, 'samples': 28708992, 'steps': 149525, 'loss/train': 1.1072828769683838} 08/31/2021 16:18:11 - INFO - __main__ - Step 149527: {'lr': 1.2654335574041608e-08, 'samples': 28709184, 'steps': 149526, 'loss/train': 0.7958312034606934} 08/31/2021 16:18:11 - INFO - __main__ - Step 149528: {'lr': 1.2600998523709661e-08, 'samples': 28709376, 'steps': 149527, 'loss/train': 1.7865126132965088} 08/31/2021 16:18:11 - INFO - __main__ - Step 149529: {'lr': 1.254777411385799e-08, 'samples': 28709568, 'steps': 149528, 'loss/train': 0.6199784874916077} 08/31/2021 16:18:12 - INFO - __main__ - Step 149530: {'lr': 1.2494662344486596e-08, 'samples': 28709760, 'steps': 149529, 'loss/train': 1.4018020629882812} 08/31/2021 16:18:13 - INFO - __main__ - Step 149531: {'lr': 1.2441663215650988e-08, 'samples': 28709952, 'steps': 149530, 'loss/train': 0.9312519431114197} 08/31/2021 16:18:14 - INFO - __main__ - Step 149532: {'lr': 1.2388776727323414e-08, 'samples': 28710144, 'steps': 149531, 'loss/train': 1.3579342365264893} 08/31/2021 16:18:14 - INFO - __main__ - Step 149533: {'lr': 1.2336002879587138e-08, 'samples': 28710336, 'steps': 149532, 'loss/train': 0.10562362521886826} 08/31/2021 16:18:14 - INFO - __main__ - Step 149534: {'lr': 1.2283341672414405e-08, 'samples': 28710528, 'steps': 149533, 'loss/train': 1.1490263938903809} 08/31/2021 16:18:15 - INFO - __main__ - Step 149535: {'lr': 1.223079310583297e-08, 'samples': 28710720, 'steps': 149534, 'loss/train': 1.1506720781326294} 08/31/2021 16:18:17 - INFO - __main__ - Step 149536: {'lr': 1.2178357179898348e-08, 'samples': 28710912, 'steps': 149535, 'loss/train': 0.9336963891983032} 08/31/2021 16:18:17 - INFO - __main__ - Step 149537: {'lr': 1.212603389463829e-08, 'samples': 28711104, 'steps': 149536, 'loss/train': 1.4316428899765015} 08/31/2021 16:18:18 - INFO - __main__ - Step 149538: {'lr': 1.207382325002504e-08, 'samples': 28711296, 'steps': 149537, 'loss/train': 0.7815948724746704} 08/31/2021 16:18:18 - INFO - __main__ - Step 149539: {'lr': 1.2021725246141868e-08, 'samples': 28711488, 'steps': 149538, 'loss/train': 0.8327425122261047} 08/31/2021 16:18:18 - INFO - __main__ - Step 149540: {'lr': 1.1969739882961018e-08, 'samples': 28711680, 'steps': 149539, 'loss/train': 2.6270854473114014} 08/31/2021 16:18:20 - INFO - __main__ - Step 149541: {'lr': 1.1917867160538e-08, 'samples': 28711872, 'steps': 149540, 'loss/train': 1.6287497282028198} 08/31/2021 16:18:21 - INFO - __main__ - Step 149542: {'lr': 1.1866107078900568e-08, 'samples': 28712064, 'steps': 149541, 'loss/train': 0.17074613273143768} 08/31/2021 16:18:21 - INFO - __main__ - Step 149543: {'lr': 1.1814459638048725e-08, 'samples': 28712256, 'steps': 149542, 'loss/train': 0.03531385585665703} 08/31/2021 16:18:21 - INFO - __main__ - Step 149544: {'lr': 1.1762924838010225e-08, 'samples': 28712448, 'steps': 149543, 'loss/train': 0.8831509947776794} 08/31/2021 16:18:22 - INFO - __main__ - Step 149545: {'lr': 1.1711502678812824e-08, 'samples': 28712640, 'steps': 149544, 'loss/train': 0.9301120638847351} 08/31/2021 16:18:23 - INFO - __main__ - Step 149546: {'lr': 1.1660193160484279e-08, 'samples': 28712832, 'steps': 149545, 'loss/train': 0.9511616826057434} 08/31/2021 16:18:24 - INFO - __main__ - Step 149547: {'lr': 1.1608996283052342e-08, 'samples': 28713024, 'steps': 149546, 'loss/train': 0.8543250560760498} 08/31/2021 16:18:24 - INFO - __main__ - Step 149548: {'lr': 1.1557912046517016e-08, 'samples': 28713216, 'steps': 149547, 'loss/train': 1.1595582962036133} 08/31/2021 16:18:24 - INFO - __main__ - Step 149549: {'lr': 1.1506940450906056e-08, 'samples': 28713408, 'steps': 149548, 'loss/train': 0.43889307975769043} 08/31/2021 16:18:25 - INFO - __main__ - Step 149550: {'lr': 1.1456081496274972e-08, 'samples': 28713600, 'steps': 149549, 'loss/train': 1.094563603401184} 08/31/2021 16:18:27 - INFO - __main__ - Step 149551: {'lr': 1.1405335182623765e-08, 'samples': 28713792, 'steps': 149550, 'loss/train': 0.9280420541763306} 08/31/2021 16:18:27 - INFO - __main__ - Step 149552: {'lr': 1.1354701509980193e-08, 'samples': 28713984, 'steps': 149551, 'loss/train': 1.0691170692443848} 08/31/2021 16:18:27 - INFO - __main__ - Step 149553: {'lr': 1.130418047834425e-08, 'samples': 28714176, 'steps': 149552, 'loss/train': 1.3340116739273071} 08/31/2021 16:18:28 - INFO - __main__ - Step 149554: {'lr': 1.1253772087771453e-08, 'samples': 28714368, 'steps': 149553, 'loss/train': 0.9480631351470947} 08/31/2021 16:18:28 - INFO - __main__ - Step 149555: {'lr': 1.1203476338261798e-08, 'samples': 28714560, 'steps': 149554, 'loss/train': 2.3394408226013184} 08/31/2021 16:18:29 - INFO - __main__ - Step 149556: {'lr': 1.1153293229843042e-08, 'samples': 28714752, 'steps': 149555, 'loss/train': 2.054429531097412} 08/31/2021 16:18:30 - INFO - __main__ - Step 149557: {'lr': 1.1103222762542941e-08, 'samples': 28714944, 'steps': 149556, 'loss/train': 1.427158236503601} 08/31/2021 16:18:31 - INFO - __main__ - Step 149558: {'lr': 1.1053264936389252e-08, 'samples': 28715136, 'steps': 149557, 'loss/train': 0.9610145092010498} 08/31/2021 16:18:31 - INFO - __main__ - Step 149559: {'lr': 1.1003419751409727e-08, 'samples': 28715328, 'steps': 149558, 'loss/train': 1.3604391813278198} 08/31/2021 16:18:31 - INFO - __main__ - Step 149560: {'lr': 1.0953687207576613e-08, 'samples': 28715520, 'steps': 149559, 'loss/train': 0.9935261011123657} 08/31/2021 16:18:32 - INFO - __main__ - Step 149561: {'lr': 1.0904067304973175e-08, 'samples': 28715712, 'steps': 149560, 'loss/train': 0.848982036113739} 08/31/2021 16:18:33 - INFO - __main__ - Step 149562: {'lr': 1.0854560043599415e-08, 'samples': 28715904, 'steps': 149561, 'loss/train': 0.847670316696167} 08/31/2021 16:18:34 - INFO - __main__ - Step 149563: {'lr': 1.0805165423483088e-08, 'samples': 28716096, 'steps': 149562, 'loss/train': 0.3948458731174469} 08/31/2021 16:18:34 - INFO - __main__ - Step 149564: {'lr': 1.0755883444624193e-08, 'samples': 28716288, 'steps': 149563, 'loss/train': 1.9819256067276} 08/31/2021 16:18:34 - INFO - __main__ - Step 149565: {'lr': 1.0706714107078242e-08, 'samples': 28716480, 'steps': 149564, 'loss/train': 0.676403820514679} 08/31/2021 16:18:35 - INFO - __main__ - Step 149566: {'lr': 1.0657657410845235e-08, 'samples': 28716672, 'steps': 149565, 'loss/train': 0.899863064289093} 08/31/2021 16:18:35 - INFO - __main__ - Step 149567: {'lr': 1.0608713355952926e-08, 'samples': 28716864, 'steps': 149566, 'loss/train': 1.1617445945739746} 08/31/2021 16:18:37 - INFO - __main__ - Step 149568: {'lr': 1.0559881942401317e-08, 'samples': 28717056, 'steps': 149567, 'loss/train': 1.457402229309082} 08/31/2021 16:18:37 - INFO - __main__ - Step 149569: {'lr': 1.0511163170273675e-08, 'samples': 28717248, 'steps': 149568, 'loss/train': 1.2561559677124023} 08/31/2021 16:18:38 - INFO - __main__ - Step 149570: {'lr': 1.0462557039514486e-08, 'samples': 28717440, 'steps': 149569, 'loss/train': 1.129371166229248} 08/31/2021 16:18:38 - INFO - __main__ - Step 149571: {'lr': 1.041406355020702e-08, 'samples': 28717632, 'steps': 149570, 'loss/train': 1.0924153327941895} 08/31/2021 16:18:38 - INFO - __main__ - Step 149572: {'lr': 1.0365682702351276e-08, 'samples': 28717824, 'steps': 149571, 'loss/train': 0.015279746614396572} 08/31/2021 16:18:39 - INFO - __main__ - Step 149573: {'lr': 1.0317414495947252e-08, 'samples': 28718016, 'steps': 149572, 'loss/train': 1.1129649877548218} 08/31/2021 16:18:40 - INFO - __main__ - Step 149574: {'lr': 1.0269258931050463e-08, 'samples': 28718208, 'steps': 149573, 'loss/train': 0.8184803128242493} 08/31/2021 16:18:41 - INFO - __main__ - Step 149575: {'lr': 1.0221216007660905e-08, 'samples': 28718400, 'steps': 149574, 'loss/train': 0.793613612651825} 08/31/2021 16:18:41 - INFO - __main__ - Step 149576: {'lr': 1.0173285725806336e-08, 'samples': 28718592, 'steps': 149575, 'loss/train': 1.2266960144042969} 08/31/2021 16:18:41 - INFO - __main__ - Step 149577: {'lr': 1.012546808551451e-08, 'samples': 28718784, 'steps': 149576, 'loss/train': 1.009416103363037} 08/31/2021 16:18:42 - INFO - __main__ - Step 149578: {'lr': 1.0077763086813186e-08, 'samples': 28718976, 'steps': 149577, 'loss/train': 1.5411839485168457} 08/31/2021 16:18:43 - INFO - __main__ - Step 149579: {'lr': 1.003017072970236e-08, 'samples': 28719168, 'steps': 149578, 'loss/train': 0.5797566771507263} 08/31/2021 16:18:44 - INFO - __main__ - Step 149580: {'lr': 9.982691014209788e-09, 'samples': 28719360, 'steps': 149579, 'loss/train': 1.104348063468933} 08/31/2021 16:18:44 - INFO - __main__ - Step 149581: {'lr': 9.935323940363228e-09, 'samples': 28719552, 'steps': 149580, 'loss/train': 0.6968694925308228} 08/31/2021 16:18:45 - INFO - __main__ - Step 149582: {'lr': 9.888069508190434e-09, 'samples': 28719744, 'steps': 149581, 'loss/train': 1.1701431274414062} 08/31/2021 16:18:45 - INFO - __main__ - Step 149583: {'lr': 9.840927717691405e-09, 'samples': 28719936, 'steps': 149582, 'loss/train': 0.7002521753311157} 08/31/2021 16:18:47 - INFO - __main__ - Step 149584: {'lr': 9.793898568921655e-09, 'samples': 28720128, 'steps': 149583, 'loss/train': 1.417336106300354} 08/31/2021 16:18:47 - INFO - __main__ - Step 149585: {'lr': 9.746982061881182e-09, 'samples': 28720320, 'steps': 149584, 'loss/train': 1.2047553062438965} 08/31/2021 16:18:47 - INFO - __main__ - Step 149586: {'lr': 9.700178196569986e-09, 'samples': 28720512, 'steps': 149585, 'loss/train': 1.2463570833206177} 08/31/2021 16:18:48 - INFO - __main__ - Step 149587: {'lr': 9.653486973043579e-09, 'samples': 28720704, 'steps': 149586, 'loss/train': 1.345223307609558} 08/31/2021 16:18:48 - INFO - __main__ - Step 149588: {'lr': 9.606908391301961e-09, 'samples': 28720896, 'steps': 149587, 'loss/train': 0.03225768730044365} 08/31/2021 16:18:50 - INFO - __main__ - Step 149589: {'lr': 9.560442451372885e-09, 'samples': 28721088, 'steps': 149588, 'loss/train': 0.7894368767738342} 08/31/2021 16:18:51 - INFO - __main__ - Step 149590: {'lr': 9.514089153284112e-09, 'samples': 28721280, 'steps': 149589, 'loss/train': 1.7340964078903198} 08/31/2021 16:18:51 - INFO - __main__ - Step 149591: {'lr': 9.467848497035637e-09, 'samples': 28721472, 'steps': 149590, 'loss/train': 0.41732317209243774} 08/31/2021 16:18:51 - INFO - __main__ - Step 149592: {'lr': 9.421720482682972e-09, 'samples': 28721664, 'steps': 149591, 'loss/train': 1.595255732536316} 08/31/2021 16:18:52 - INFO - __main__ - Step 149593: {'lr': 9.375705110226119e-09, 'samples': 28721856, 'steps': 149592, 'loss/train': 1.4447284936904907} 08/31/2021 16:18:53 - INFO - __main__ - Step 149594: {'lr': 9.329802379692831e-09, 'samples': 28722048, 'steps': 149593, 'loss/train': 1.6878060102462769} 08/31/2021 16:18:54 - INFO - __main__ - Step 149595: {'lr': 9.28401229108311e-09, 'samples': 28722240, 'steps': 149594, 'loss/train': 1.6991393566131592} 08/31/2021 16:18:54 - INFO - __main__ - Step 149596: {'lr': 9.238334844424711e-09, 'samples': 28722432, 'steps': 149595, 'loss/train': 1.3326128721237183} 08/31/2021 16:18:54 - INFO - __main__ - Step 149597: {'lr': 9.192770039773146e-09, 'samples': 28722624, 'steps': 149596, 'loss/train': 1.1484010219573975} 08/31/2021 16:18:55 - INFO - __main__ - Step 149598: {'lr': 9.147317877100659e-09, 'samples': 28722816, 'steps': 149597, 'loss/train': 0.9700238704681396} 08/31/2021 16:18:55 - INFO - __main__ - Step 149599: {'lr': 9.101978356462759e-09, 'samples': 28723008, 'steps': 149598, 'loss/train': 1.2562471628189087} 08/31/2021 16:18:57 - INFO - __main__ - Step 149600: {'lr': 9.056751477859449e-09, 'samples': 28723200, 'steps': 149599, 'loss/train': 0.6050613522529602} 08/31/2021 16:18:57 - INFO - __main__ - Step 149601: {'lr': 9.011637241318482e-09, 'samples': 28723392, 'steps': 149600, 'loss/train': 1.3067055940628052} 08/31/2021 16:18:57 - INFO - __main__ - Step 149602: {'lr': 8.96663564683986e-09, 'samples': 28723584, 'steps': 149601, 'loss/train': 1.1793806552886963} 08/31/2021 16:18:58 - INFO - __main__ - Step 149603: {'lr': 8.921746694479093e-09, 'samples': 28723776, 'steps': 149602, 'loss/train': 1.4074515104293823} 08/31/2021 16:18:58 - INFO - __main__ - Step 149604: {'lr': 8.876970384236182e-09, 'samples': 28723968, 'steps': 149603, 'loss/train': 1.8068684339523315} 08/31/2021 16:19:00 - INFO - __main__ - Step 149605: {'lr': 8.832306716166637e-09, 'samples': 28724160, 'steps': 149604, 'loss/train': 1.4306917190551758} 08/31/2021 16:19:00 - INFO - __main__ - Step 149606: {'lr': 8.787755690214949e-09, 'samples': 28724352, 'steps': 149605, 'loss/train': 0.8558408617973328} 08/31/2021 16:19:00 - INFO - __main__ - Step 149607: {'lr': 8.743317306464383e-09, 'samples': 28724544, 'steps': 149606, 'loss/train': 1.6886805295944214} 08/31/2021 16:19:01 - INFO - __main__ - Step 149608: {'lr': 8.698991564914937e-09, 'samples': 28724736, 'steps': 149607, 'loss/train': 0.32686230540275574} 08/31/2021 16:19:01 - INFO - __main__ - Step 149609: {'lr': 8.654778465594371e-09, 'samples': 28724928, 'steps': 149608, 'loss/train': 0.9508690237998962} 08/31/2021 16:19:02 - INFO - __main__ - Step 149610: {'lr': 8.610678008530437e-09, 'samples': 28725120, 'steps': 149609, 'loss/train': 1.2642942667007446} 08/31/2021 16:19:03 - INFO - __main__ - Step 149611: {'lr': 8.566690193695382e-09, 'samples': 28725312, 'steps': 149610, 'loss/train': 1.5137252807617188} 08/31/2021 16:19:03 - INFO - __main__ - Step 149612: {'lr': 8.52281502117247e-09, 'samples': 28725504, 'steps': 149611, 'loss/train': 3.8357863426208496} 08/31/2021 16:19:04 - INFO - __main__ - Step 149613: {'lr': 8.479052490933948e-09, 'samples': 28725696, 'steps': 149612, 'loss/train': 1.24485182762146} 08/31/2021 16:19:04 - INFO - __main__ - Step 149614: {'lr': 8.43540260300757e-09, 'samples': 28725888, 'steps': 149613, 'loss/train': 1.282297968864441} 08/31/2021 16:19:05 - INFO - __main__ - Step 149615: {'lr': 8.391865357448847e-09, 'samples': 28726080, 'steps': 149614, 'loss/train': 1.122900366783142} 08/31/2021 16:19:06 - INFO - __main__ - Step 149616: {'lr': 8.348440754230025e-09, 'samples': 28726272, 'steps': 149615, 'loss/train': 1.0933996438980103} 08/31/2021 16:19:06 - INFO - __main__ - Step 149617: {'lr': 8.305128793406613e-09, 'samples': 28726464, 'steps': 149616, 'loss/train': 0.6921817064285278} 08/31/2021 16:19:07 - INFO - __main__ - Step 149618: {'lr': 8.261929474978614e-09, 'samples': 28726656, 'steps': 149617, 'loss/train': 0.837044894695282} 08/31/2021 16:19:07 - INFO - __main__ - Step 149619: {'lr': 8.218842798946025e-09, 'samples': 28726848, 'steps': 149618, 'loss/train': 0.5549581050872803} 08/31/2021 16:19:08 - INFO - __main__ - Step 149620: {'lr': 8.175868765392114e-09, 'samples': 28727040, 'steps': 149619, 'loss/train': 1.0975797176361084} 08/31/2021 16:19:09 - INFO - __main__ - Step 149621: {'lr': 8.13300737426137e-09, 'samples': 28727232, 'steps': 149620, 'loss/train': 1.726001501083374} 08/31/2021 16:19:09 - INFO - __main__ - Step 149622: {'lr': 8.09025862563706e-09, 'samples': 28727424, 'steps': 149621, 'loss/train': 1.456810712814331} 08/31/2021 16:19:10 - INFO - __main__ - Step 149623: {'lr': 8.047622519491427e-09, 'samples': 28727616, 'steps': 149622, 'loss/train': 0.8784780502319336} 08/31/2021 16:19:10 - INFO - __main__ - Step 149624: {'lr': 8.005099055879982e-09, 'samples': 28727808, 'steps': 149623, 'loss/train': 0.6974514722824097} 08/31/2021 16:19:10 - INFO - __main__ - Step 149625: {'lr': 7.962688234802729e-09, 'samples': 28728000, 'steps': 149624, 'loss/train': 0.9289398193359375} 08/31/2021 16:19:12 - INFO - __main__ - Step 149626: {'lr': 7.920390056259663e-09, 'samples': 28728192, 'steps': 149625, 'loss/train': 1.5209821462631226} 08/31/2021 16:19:12 - INFO - __main__ - Step 149627: {'lr': 7.878204520306298e-09, 'samples': 28728384, 'steps': 149626, 'loss/train': 1.0039420127868652} 08/31/2021 16:19:13 - INFO - __main__ - Step 149628: {'lr': 7.836131626942633e-09, 'samples': 28728576, 'steps': 149627, 'loss/train': 0.5907129645347595} 08/31/2021 16:19:13 - INFO - __main__ - Step 149629: {'lr': 7.794171376168669e-09, 'samples': 28728768, 'steps': 149628, 'loss/train': 0.684615433216095} 08/31/2021 16:19:13 - INFO - __main__ - Step 149630: {'lr': 7.752323768039914e-09, 'samples': 28728960, 'steps': 149629, 'loss/train': 0.7910118699073792} 08/31/2021 16:19:15 - INFO - __main__ - Step 149631: {'lr': 7.710588802584129e-09, 'samples': 28729152, 'steps': 149630, 'loss/train': 0.4474219083786011} 08/31/2021 16:19:16 - INFO - __main__ - Step 149632: {'lr': 7.668966479773553e-09, 'samples': 28729344, 'steps': 149631, 'loss/train': 0.054167136549949646} 08/31/2021 16:19:16 - INFO - __main__ - Step 149633: {'lr': 7.627456799635946e-09, 'samples': 28729536, 'steps': 149632, 'loss/train': 0.3271443545818329} 08/31/2021 16:19:16 - INFO - __main__ - Step 149634: {'lr': 7.586059762226816e-09, 'samples': 28729728, 'steps': 149633, 'loss/train': 0.7712791562080383} 08/31/2021 16:19:17 - INFO - __main__ - Step 149635: {'lr': 7.544775367546165e-09, 'samples': 28729920, 'steps': 149634, 'loss/train': 1.312298059463501} 08/31/2021 16:19:19 - INFO - __main__ - Step 149636: {'lr': 7.50360361559399e-09, 'samples': 28730112, 'steps': 149635, 'loss/train': 1.2544372081756592} 08/31/2021 16:19:19 - INFO - __main__ - Step 149637: {'lr': 7.462544506398051e-09, 'samples': 28730304, 'steps': 149636, 'loss/train': 0.6677826642990112} 08/31/2021 16:19:19 - INFO - __main__ - Step 149638: {'lr': 7.4215980399861e-09, 'samples': 28730496, 'steps': 149637, 'loss/train': 1.1938635110855103} 08/31/2021 16:19:20 - INFO - __main__ - Step 149639: {'lr': 7.380764216385893e-09, 'samples': 28730688, 'steps': 149638, 'loss/train': 1.6067657470703125} 08/31/2021 16:19:20 - INFO - __main__ - Step 149640: {'lr': 7.340043035597433e-09, 'samples': 28730880, 'steps': 149639, 'loss/train': 0.7225563526153564} 08/31/2021 16:19:20 - INFO - __main__ - Step 149641: {'lr': 7.299434497620716e-09, 'samples': 28731072, 'steps': 149640, 'loss/train': 0.30781495571136475} 08/31/2021 16:19:23 - INFO - __main__ - Step 149642: {'lr': 7.258938602511256e-09, 'samples': 28731264, 'steps': 149641, 'loss/train': 0.9034044146537781} 08/31/2021 16:19:23 - INFO - __main__ - Step 149643: {'lr': 7.218555350296807e-09, 'samples': 28731456, 'steps': 149642, 'loss/train': 0.5199916362762451} 08/31/2021 16:19:23 - INFO - __main__ - Step 149644: {'lr': 7.178284740949615e-09, 'samples': 28731648, 'steps': 149643, 'loss/train': 3.6193602085113525} 08/31/2021 16:19:24 - INFO - __main__ - Step 149645: {'lr': 7.1381267744974334e-09, 'samples': 28731840, 'steps': 149644, 'loss/train': 1.143140196800232} 08/31/2021 16:19:24 - INFO - __main__ - Step 149646: {'lr': 7.0980814509957745e-09, 'samples': 28732032, 'steps': 149645, 'loss/train': 1.4179879426956177} 08/31/2021 16:19:26 - INFO - __main__ - Step 149647: {'lr': 7.058148770444639e-09, 'samples': 28732224, 'steps': 149646, 'loss/train': 0.6692655682563782} 08/31/2021 16:19:26 - INFO - __main__ - Step 149648: {'lr': 7.01832873281627e-09, 'samples': 28732416, 'steps': 149647, 'loss/train': 1.2535823583602905} 08/31/2021 16:19:26 - INFO - __main__ - Step 149649: {'lr': 6.978621338193936e-09, 'samples': 28732608, 'steps': 149648, 'loss/train': 1.3260279893875122} 08/31/2021 16:19:27 - INFO - __main__ - Step 149650: {'lr': 6.939026586577635e-09, 'samples': 28732800, 'steps': 149649, 'loss/train': 1.9724435806274414} 08/31/2021 16:19:27 - INFO - __main__ - Step 149651: {'lr': 6.899544477967368e-09, 'samples': 28732992, 'steps': 149650, 'loss/train': 0.538083016872406} 08/31/2021 16:19:29 - INFO - __main__ - Step 149652: {'lr': 6.86017501239089e-09, 'samples': 28733184, 'steps': 149651, 'loss/train': 0.9778397679328918} 08/31/2021 16:19:29 - INFO - __main__ - Step 149653: {'lr': 6.820918189875958e-09, 'samples': 28733376, 'steps': 149652, 'loss/train': 1.5263283252716064} 08/31/2021 16:19:30 - INFO - __main__ - Step 149654: {'lr': 6.781774010394815e-09, 'samples': 28733568, 'steps': 149653, 'loss/train': 1.2472211122512817} 08/31/2021 16:19:30 - INFO - __main__ - Step 149655: {'lr': 6.742742474030728e-09, 'samples': 28733760, 'steps': 149654, 'loss/train': 0.28480392694473267} 08/31/2021 16:19:30 - INFO - __main__ - Step 149656: {'lr': 6.703823580755941e-09, 'samples': 28733952, 'steps': 149655, 'loss/train': 0.9684897661209106} 08/31/2021 16:19:31 - INFO - __main__ - Step 149657: {'lr': 6.665017330625966e-09, 'samples': 28734144, 'steps': 149656, 'loss/train': 1.2901363372802734} 08/31/2021 16:19:32 - INFO - __main__ - Step 149658: {'lr': 6.626323723613048e-09, 'samples': 28734336, 'steps': 149657, 'loss/train': 1.4150580167770386} 08/31/2021 16:19:33 - INFO - __main__ - Step 149659: {'lr': 6.587742759772697e-09, 'samples': 28734528, 'steps': 149658, 'loss/train': 1.057350993156433} 08/31/2021 16:19:33 - INFO - __main__ - Step 149660: {'lr': 6.549274439104913e-09, 'samples': 28734720, 'steps': 149659, 'loss/train': 1.4447689056396484} 08/31/2021 16:19:33 - INFO - __main__ - Step 149661: {'lr': 6.510918761609697e-09, 'samples': 28734912, 'steps': 149660, 'loss/train': 1.2212307453155518} 08/31/2021 16:19:34 - INFO - __main__ - Step 149662: {'lr': 6.472675727342559e-09, 'samples': 28735104, 'steps': 149661, 'loss/train': 0.7938899397850037} 08/31/2021 16:19:36 - INFO - __main__ - Step 149663: {'lr': 6.4345453362757436e-09, 'samples': 28735296, 'steps': 149662, 'loss/train': 0.5966348648071289} 08/31/2021 16:19:37 - INFO - __main__ - Step 149664: {'lr': 6.396527588464762e-09, 'samples': 28735488, 'steps': 149663, 'loss/train': 0.4048273265361786} 08/31/2021 16:19:37 - INFO - __main__ - Step 149665: {'lr': 6.358622483937371e-09, 'samples': 28735680, 'steps': 149664, 'loss/train': 0.25713372230529785} 08/31/2021 16:19:37 - INFO - __main__ - Step 149666: {'lr': 6.320830022665813e-09, 'samples': 28735872, 'steps': 149665, 'loss/train': 0.23606911301612854} 08/31/2021 16:19:38 - INFO - __main__ - Step 149667: {'lr': 6.283150204677845e-09, 'samples': 28736064, 'steps': 149666, 'loss/train': 0.24483489990234375} 08/31/2021 16:19:38 - INFO - __main__ - Step 149668: {'lr': 6.2455830300289785e-09, 'samples': 28736256, 'steps': 149667, 'loss/train': 1.0055527687072754} 08/31/2021 16:19:39 - INFO - __main__ - Step 149669: {'lr': 6.208128498691456e-09, 'samples': 28736448, 'steps': 149668, 'loss/train': 1.2272639274597168} 08/31/2021 16:19:40 - INFO - __main__ - Step 149670: {'lr': 6.170786610693036e-09, 'samples': 28736640, 'steps': 149669, 'loss/train': 1.1809580326080322} 08/31/2021 16:19:40 - INFO - __main__ - Step 149671: {'lr': 6.133557366061471e-09, 'samples': 28736832, 'steps': 149670, 'loss/train': 0.7155932784080505} 08/31/2021 16:19:41 - INFO - __main__ - Step 149672: {'lr': 6.096440764824518e-09, 'samples': 28737024, 'steps': 149671, 'loss/train': 1.2092984914779663} 08/31/2021 16:19:41 - INFO - __main__ - Step 149673: {'lr': 6.059436806954421e-09, 'samples': 28737216, 'steps': 149672, 'loss/train': 1.2588212490081787} 08/31/2021 16:19:42 - INFO - __main__ - Step 149674: {'lr': 6.022545492506693e-09, 'samples': 28737408, 'steps': 149673, 'loss/train': 0.4802881181240082} 08/31/2021 16:19:43 - INFO - __main__ - Step 149675: {'lr': 5.985766821509086e-09, 'samples': 28737600, 'steps': 149674, 'loss/train': 0.9139792323112488} 08/31/2021 16:19:43 - INFO - __main__ - Step 149676: {'lr': 5.9491007939338485e-09, 'samples': 28737792, 'steps': 149675, 'loss/train': 1.3920483589172363} 08/31/2021 16:19:44 - INFO - __main__ - Step 149677: {'lr': 5.912547409808733e-09, 'samples': 28737984, 'steps': 149676, 'loss/train': 1.6374351978302002} 08/31/2021 16:19:44 - INFO - __main__ - Step 149678: {'lr': 5.876106669189252e-09, 'samples': 28738176, 'steps': 149677, 'loss/train': 0.7872591018676758} 08/31/2021 16:19:46 - INFO - __main__ - Step 149679: {'lr': 5.839778572047649e-09, 'samples': 28738368, 'steps': 149678, 'loss/train': 1.9139896631240845} 08/31/2021 16:19:46 - INFO - __main__ - Step 149680: {'lr': 5.8035631184394365e-09, 'samples': 28738560, 'steps': 149679, 'loss/train': 1.55225670337677} 08/31/2021 16:19:46 - INFO - __main__ - Step 149681: {'lr': 5.767460308336858e-09, 'samples': 28738752, 'steps': 149680, 'loss/train': 0.5406900644302368} 08/31/2021 16:19:47 - INFO - __main__ - Step 149682: {'lr': 5.73147014176767e-09, 'samples': 28738944, 'steps': 149681, 'loss/train': 1.153140902519226} 08/31/2021 16:19:47 - INFO - __main__ - Step 149683: {'lr': 5.695592618787382e-09, 'samples': 28739136, 'steps': 149682, 'loss/train': 0.5650316476821899} 08/31/2021 16:19:49 - INFO - __main__ - Step 149684: {'lr': 5.65982773936824e-09, 'samples': 28739328, 'steps': 149683, 'loss/train': 1.279720664024353} 08/31/2021 16:19:49 - INFO - __main__ - Step 149685: {'lr': 5.624175503537998e-09, 'samples': 28739520, 'steps': 149684, 'loss/train': 0.9159745573997498} 08/31/2021 16:19:49 - INFO - __main__ - Step 149686: {'lr': 5.588635911324414e-09, 'samples': 28739712, 'steps': 149685, 'loss/train': 1.0970429182052612} 08/31/2021 16:19:50 - INFO - __main__ - Step 149687: {'lr': 5.553208962727485e-09, 'samples': 28739904, 'steps': 149686, 'loss/train': 0.8594608306884766} 08/31/2021 16:19:50 - INFO - __main__ - Step 149688: {'lr': 5.517894657774969e-09, 'samples': 28740096, 'steps': 149687, 'loss/train': 0.8018540740013123} 08/31/2021 16:19:50 - INFO - __main__ - Step 149689: {'lr': 5.482692996466865e-09, 'samples': 28740288, 'steps': 149688, 'loss/train': 1.2862061262130737} 08/31/2021 16:19:52 - INFO - __main__ - Step 149690: {'lr': 5.447603978858684e-09, 'samples': 28740480, 'steps': 149689, 'loss/train': 0.9315690398216248} 08/31/2021 16:19:52 - INFO - __main__ - Step 149691: {'lr': 5.412627604922671e-09, 'samples': 28740672, 'steps': 149690, 'loss/train': 1.235754132270813} 08/31/2021 16:19:53 - INFO - __main__ - Step 149692: {'lr': 5.377763874686581e-09, 'samples': 28740864, 'steps': 149691, 'loss/train': 0.9280973076820374} 08/31/2021 16:19:53 - INFO - __main__ - Step 149693: {'lr': 5.343012788150415e-09, 'samples': 28741056, 'steps': 149692, 'loss/train': 0.9418443441390991} 08/31/2021 16:19:53 - INFO - __main__ - Step 149694: {'lr': 5.308374345369682e-09, 'samples': 28741248, 'steps': 149693, 'loss/train': 1.1308698654174805} 08/31/2021 16:19:55 - INFO - __main__ - Step 149695: {'lr': 5.273848546344384e-09, 'samples': 28741440, 'steps': 149694, 'loss/train': 1.3018442392349243} 08/31/2021 16:19:55 - INFO - __main__ - Step 149696: {'lr': 5.239435391074521e-09, 'samples': 28741632, 'steps': 149695, 'loss/train': 0.8554083108901978} 08/31/2021 16:19:56 - INFO - __main__ - Step 149697: {'lr': 5.205134879615603e-09, 'samples': 28741824, 'steps': 149696, 'loss/train': 1.5866968631744385} 08/31/2021 16:19:56 - INFO - __main__ - Step 149698: {'lr': 5.17094701191212e-09, 'samples': 28742016, 'steps': 149697, 'loss/train': 0.9383453726768494} 08/31/2021 16:19:56 - INFO - __main__ - Step 149699: {'lr': 5.136871788047337e-09, 'samples': 28742208, 'steps': 149698, 'loss/train': 1.3620964288711548} 08/31/2021 16:19:58 - INFO - __main__ - Step 149700: {'lr': 5.1029092079935e-09, 'samples': 28742400, 'steps': 149699, 'loss/train': 1.1833852529525757} 08/31/2021 16:19:59 - INFO - __main__ - Step 149701: {'lr': 5.06905927180612e-09, 'samples': 28742592, 'steps': 149700, 'loss/train': 2.270453929901123} 08/31/2021 16:19:59 - INFO - __main__ - Step 149702: {'lr': 5.035321979457441e-09, 'samples': 28742784, 'steps': 149701, 'loss/train': 1.4180736541748047} 08/31/2021 16:19:59 - INFO - __main__ - Step 149703: {'lr': 5.001697330975219e-09, 'samples': 28742976, 'steps': 149702, 'loss/train': 0.7334849834442139} 08/31/2021 16:20:00 - INFO - __main__ - Step 149704: {'lr': 4.968185326387209e-09, 'samples': 28743168, 'steps': 149703, 'loss/train': 0.9593561291694641} 08/31/2021 16:20:00 - INFO - __main__ - Step 149705: {'lr': 4.934785965721167e-09, 'samples': 28743360, 'steps': 149704, 'loss/train': 4.278266429901123} 08/31/2021 16:20:02 - INFO - __main__ - Step 149706: {'lr': 4.901499248949337e-09, 'samples': 28743552, 'steps': 149705, 'loss/train': 1.2198717594146729} 08/31/2021 16:20:02 - INFO - __main__ - Step 149707: {'lr': 4.8683251761272304e-09, 'samples': 28743744, 'steps': 149706, 'loss/train': 1.341181755065918} 08/31/2021 16:20:03 - INFO - __main__ - Step 149708: {'lr': 4.835263747254848e-09, 'samples': 28743936, 'steps': 149707, 'loss/train': 1.3495080471038818} 08/31/2021 16:20:03 - INFO - __main__ - Step 149709: {'lr': 4.8023149623321885e-09, 'samples': 28744128, 'steps': 149708, 'loss/train': 1.2188630104064941} 08/31/2021 16:20:03 - INFO - __main__ - Step 149710: {'lr': 4.769478821414763e-09, 'samples': 28744320, 'steps': 149709, 'loss/train': 1.2607415914535522} 08/31/2021 16:20:05 - INFO - __main__ - Step 149711: {'lr': 4.736755324447062e-09, 'samples': 28744512, 'steps': 149710, 'loss/train': 0.9287093281745911} 08/31/2021 16:20:05 - INFO - __main__ - Step 149712: {'lr': 4.7041444715123506e-09, 'samples': 28744704, 'steps': 149711, 'loss/train': 1.5437678098678589} 08/31/2021 16:20:06 - INFO - __main__ - Step 149713: {'lr': 4.671646262610629e-09, 'samples': 28744896, 'steps': 149712, 'loss/train': 1.2055389881134033} 08/31/2021 16:20:06 - INFO - __main__ - Step 149714: {'lr': 4.6392606977418984e-09, 'samples': 28745088, 'steps': 149713, 'loss/train': 1.0458009243011475} 08/31/2021 16:20:06 - INFO - __main__ - Step 149715: {'lr': 4.606987776906158e-09, 'samples': 28745280, 'steps': 149714, 'loss/train': 1.0003172159194946} 08/31/2021 16:20:07 - INFO - __main__ - Step 149716: {'lr': 4.574827500158918e-09, 'samples': 28745472, 'steps': 149715, 'loss/train': 0.5292586088180542} 08/31/2021 16:20:08 - INFO - __main__ - Step 149717: {'lr': 4.542779867472424e-09, 'samples': 28745664, 'steps': 149716, 'loss/train': 0.2605065703392029} 08/31/2021 16:20:09 - INFO - __main__ - Step 149718: {'lr': 4.510844878902187e-09, 'samples': 28745856, 'steps': 149717, 'loss/train': 1.643288016319275} 08/31/2021 16:20:09 - INFO - __main__ - Step 149719: {'lr': 4.4790225344204515e-09, 'samples': 28746048, 'steps': 149718, 'loss/train': 1.3135814666748047} 08/31/2021 16:20:09 - INFO - __main__ - Step 149720: {'lr': 4.447312834082729e-09, 'samples': 28746240, 'steps': 149719, 'loss/train': 1.4023562669754028} 08/31/2021 16:20:10 - INFO - __main__ - Step 149721: {'lr': 4.415715777861262e-09, 'samples': 28746432, 'steps': 149720, 'loss/train': 0.8981016278266907} 08/31/2021 16:20:11 - INFO - __main__ - Step 149722: {'lr': 4.384231365811564e-09, 'samples': 28746624, 'steps': 149721, 'loss/train': 1.0292798280715942} 08/31/2021 16:20:12 - INFO - __main__ - Step 149723: {'lr': 4.352859597933634e-09, 'samples': 28746816, 'steps': 149722, 'loss/train': 0.4627261161804199} 08/31/2021 16:20:12 - INFO - __main__ - Step 149724: {'lr': 4.321600474227471e-09, 'samples': 28747008, 'steps': 149723, 'loss/train': 0.8779894113540649} 08/31/2021 16:20:12 - INFO - __main__ - Step 149725: {'lr': 4.290453994720833e-09, 'samples': 28747200, 'steps': 149724, 'loss/train': 0.9773738980293274} 08/31/2021 16:20:13 - INFO - __main__ - Step 149726: {'lr': 4.2594201594137184e-09, 'samples': 28747392, 'steps': 149725, 'loss/train': 0.8413561582565308} 08/31/2021 16:20:15 - INFO - __main__ - Step 149727: {'lr': 4.228498968333883e-09, 'samples': 28747584, 'steps': 149726, 'loss/train': 0.7768234014511108} 08/31/2021 16:20:15 - INFO - __main__ - Step 149728: {'lr': 4.197690421481326e-09, 'samples': 28747776, 'steps': 149727, 'loss/train': 0.33248504996299744} 08/31/2021 16:20:16 - INFO - __main__ - Step 149729: {'lr': 4.166994518883805e-09, 'samples': 28747968, 'steps': 149728, 'loss/train': 1.0108329057693481} 08/31/2021 16:20:16 - INFO - __main__ - Step 149730: {'lr': 4.136411260569073e-09, 'samples': 28748160, 'steps': 149729, 'loss/train': 0.9273701310157776} 08/31/2021 16:20:16 - INFO - __main__ - Step 149731: {'lr': 4.105940646509376e-09, 'samples': 28748352, 'steps': 149730, 'loss/train': 1.4278079271316528} 08/31/2021 16:20:18 - INFO - __main__ - Step 149732: {'lr': 4.0755826767602256e-09, 'samples': 28748544, 'steps': 149731, 'loss/train': 1.121805191040039} 08/31/2021 16:20:19 - INFO - __main__ - Step 149733: {'lr': 4.045337351293865e-09, 'samples': 28748736, 'steps': 149732, 'loss/train': 1.4470969438552856} 08/31/2021 16:20:19 - INFO - __main__ - Step 149734: {'lr': 4.015204670165806e-09, 'samples': 28748928, 'steps': 149733, 'loss/train': 0.9373084306716919} 08/31/2021 16:20:19 - INFO - __main__ - Step 149735: {'lr': 3.9851846333760486e-09, 'samples': 28749120, 'steps': 149734, 'loss/train': 1.5948129892349243} 08/31/2021 16:20:20 - INFO - __main__ - Step 149736: {'lr': 3.955277240924593e-09, 'samples': 28749312, 'steps': 149735, 'loss/train': 2.804141044616699} 08/31/2021 16:20:20 - INFO - __main__ - Step 149737: {'lr': 3.9254824928114385e-09, 'samples': 28749504, 'steps': 149736, 'loss/train': 1.282109260559082} 08/31/2021 16:20:21 - INFO - __main__ - Step 149738: {'lr': 3.8958003890920965e-09, 'samples': 28749696, 'steps': 149737, 'loss/train': 0.9720550775527954} 08/31/2021 16:20:22 - INFO - __main__ - Step 149739: {'lr': 3.866230929766568e-09, 'samples': 28749888, 'steps': 149738, 'loss/train': 1.2350693941116333} 08/31/2021 16:20:22 - INFO - __main__ - Step 149740: {'lr': 3.836774114834851e-09, 'samples': 28750080, 'steps': 149739, 'loss/train': 0.9403981566429138} 08/31/2021 16:20:23 - INFO - __main__ - Step 149741: {'lr': 3.8074299443247026e-09, 'samples': 28750272, 'steps': 149740, 'loss/train': 0.8172727823257446} 08/31/2021 16:20:23 - INFO - __main__ - Step 149742: {'lr': 3.7781984182361226e-09, 'samples': 28750464, 'steps': 149741, 'loss/train': 1.0117672681808472} 08/31/2021 16:20:25 - INFO - __main__ - Step 149743: {'lr': 3.749079536569111e-09, 'samples': 28750656, 'steps': 149742, 'loss/train': 1.156912922859192} 08/31/2021 16:20:25 - INFO - __main__ - Step 149744: {'lr': 3.720073299379179e-09, 'samples': 28750848, 'steps': 149743, 'loss/train': 1.2618870735168457} 08/31/2021 16:20:25 - INFO - __main__ - Step 149745: {'lr': 3.69117970663857e-09, 'samples': 28751040, 'steps': 149744, 'loss/train': 1.4143896102905273} 08/31/2021 16:20:26 - INFO - __main__ - Step 149746: {'lr': 3.662398758402796e-09, 'samples': 28751232, 'steps': 149745, 'loss/train': 0.10113050788640976} 08/31/2021 16:20:26 - INFO - __main__ - Step 149747: {'lr': 3.633730454644102e-09, 'samples': 28751424, 'steps': 149746, 'loss/train': 0.0225458275526762} 08/31/2021 16:20:28 - INFO - __main__ - Step 149748: {'lr': 3.605174795362487e-09, 'samples': 28751616, 'steps': 149747, 'loss/train': 0.16232040524482727} 08/31/2021 16:20:28 - INFO - __main__ - Step 149749: {'lr': 3.576731780641218e-09, 'samples': 28751808, 'steps': 149748, 'loss/train': 0.2616506814956665} 08/31/2021 16:20:29 - INFO - __main__ - Step 149750: {'lr': 3.5484014104247843e-09, 'samples': 28752000, 'steps': 149749, 'loss/train': 1.1272075176239014} 08/31/2021 16:20:29 - INFO - __main__ - Step 149751: {'lr': 3.5201836847686962e-09, 'samples': 28752192, 'steps': 149750, 'loss/train': 0.07463231682777405} 08/31/2021 16:20:29 - INFO - __main__ - Step 149752: {'lr': 3.492078603645199e-09, 'samples': 28752384, 'steps': 149751, 'loss/train': 0.3334938883781433} 08/31/2021 16:20:30 - INFO - __main__ - Step 149753: {'lr': 3.4640861671098035e-09, 'samples': 28752576, 'steps': 149752, 'loss/train': 1.17731773853302} 08/31/2021 16:20:31 - INFO - __main__ - Step 149754: {'lr': 3.4362063751625093e-09, 'samples': 28752768, 'steps': 149753, 'loss/train': 1.1139655113220215} 08/31/2021 16:20:32 - INFO - __main__ - Step 149755: {'lr': 3.408439227803317e-09, 'samples': 28752960, 'steps': 149754, 'loss/train': 0.8318261504173279} 08/31/2021 16:20:32 - INFO - __main__ - Step 149756: {'lr': 3.3807847250322264e-09, 'samples': 28753152, 'steps': 149755, 'loss/train': 1.1402465105056763} 08/31/2021 16:20:32 - INFO - __main__ - Step 149757: {'lr': 3.353242866904749e-09, 'samples': 28753344, 'steps': 149756, 'loss/train': 1.1994504928588867} 08/31/2021 16:20:33 - INFO - __main__ - Step 149758: {'lr': 3.3258136533931284e-09, 'samples': 28753536, 'steps': 149757, 'loss/train': 0.25141608715057373} 08/31/2021 16:20:34 - INFO - __main__ - Step 149759: {'lr': 3.2984970845251204e-09, 'samples': 28753728, 'steps': 149758, 'loss/train': 1.3394352197647095} 08/31/2021 16:20:35 - INFO - __main__ - Step 149760: {'lr': 3.271293160328481e-09, 'samples': 28753920, 'steps': 149759, 'loss/train': 1.125916600227356} 08/31/2021 16:20:35 - INFO - __main__ - Step 149761: {'lr': 3.2442018807754547e-09, 'samples': 28754112, 'steps': 149760, 'loss/train': 1.4043842554092407} 08/31/2021 16:20:35 - INFO - __main__ - Step 149762: {'lr': 3.217223245921552e-09, 'samples': 28754304, 'steps': 149761, 'loss/train': 0.7303379774093628} 08/31/2021 16:20:36 - INFO - __main__ - Step 149763: {'lr': 3.190357255739018e-09, 'samples': 28754496, 'steps': 149762, 'loss/train': 1.560152292251587} 08/31/2021 16:20:37 - INFO - __main__ - Step 149764: {'lr': 3.1636039102833635e-09, 'samples': 28754688, 'steps': 149763, 'loss/train': 0.7785356044769287} 08/31/2021 16:20:38 - INFO - __main__ - Step 149765: {'lr': 3.1369632095545884e-09, 'samples': 28754880, 'steps': 149764, 'loss/train': 1.2715423107147217} 08/31/2021 16:20:38 - INFO - __main__ - Step 149766: {'lr': 3.1104351535249375e-09, 'samples': 28755072, 'steps': 149765, 'loss/train': 1.3544142246246338} 08/31/2021 16:20:38 - INFO - __main__ - Step 149767: {'lr': 3.0840197422499217e-09, 'samples': 28755264, 'steps': 149766, 'loss/train': 0.6667425632476807} 08/31/2021 16:20:39 - INFO - __main__ - Step 149768: {'lr': 3.057716975729541e-09, 'samples': 28755456, 'steps': 149767, 'loss/train': 0.9821776747703552} 08/31/2021 16:20:40 - INFO - __main__ - Step 149769: {'lr': 3.0315268539637953e-09, 'samples': 28755648, 'steps': 149768, 'loss/train': 1.4265943765640259} 08/31/2021 16:20:41 - INFO - __main__ - Step 149770: {'lr': 3.0054493769804404e-09, 'samples': 28755840, 'steps': 149769, 'loss/train': 1.299194097518921} 08/31/2021 16:20:41 - INFO - __main__ - Step 149771: {'lr': 2.979484544779476e-09, 'samples': 28756032, 'steps': 149770, 'loss/train': 1.4077314138412476} 08/31/2021 16:20:41 - INFO - __main__ - Step 149772: {'lr': 2.9536323573886583e-09, 'samples': 28756224, 'steps': 149771, 'loss/train': 0.7322020530700684} 08/31/2021 16:20:42 - INFO - __main__ - Step 149773: {'lr': 2.9278928148079863e-09, 'samples': 28756416, 'steps': 149772, 'loss/train': 0.9508155584335327} 08/31/2021 16:20:42 - INFO - __main__ - Step 149774: {'lr': 2.9022659170652167e-09, 'samples': 28756608, 'steps': 149773, 'loss/train': 1.4542654752731323} 08/31/2021 16:20:44 - INFO - __main__ - Step 149775: {'lr': 2.876751664132593e-09, 'samples': 28756800, 'steps': 149774, 'loss/train': 1.0776715278625488} 08/31/2021 16:20:44 - INFO - __main__ - Step 149776: {'lr': 2.8513500560378714e-09, 'samples': 28756992, 'steps': 149775, 'loss/train': 0.7287393808364868} 08/31/2021 16:20:45 - INFO - __main__ - Step 149777: {'lr': 2.8260610928365625e-09, 'samples': 28757184, 'steps': 149776, 'loss/train': 0.9024563431739807} 08/31/2021 16:20:45 - INFO - __main__ - Step 149778: {'lr': 2.8008847744731557e-09, 'samples': 28757376, 'steps': 149777, 'loss/train': 1.6275546550750732} 08/31/2021 16:20:45 - INFO - __main__ - Step 149779: {'lr': 2.775821101003162e-09, 'samples': 28757568, 'steps': 149778, 'loss/train': 0.6281793713569641} 08/31/2021 16:20:48 - INFO - __main__ - Step 149780: {'lr': 2.750870072426581e-09, 'samples': 28757760, 'steps': 149779, 'loss/train': 1.744401216506958} 08/31/2021 16:20:48 - INFO - __main__ - Step 149781: {'lr': 2.7260316887434132e-09, 'samples': 28757952, 'steps': 149780, 'loss/train': 0.7994290590286255} 08/31/2021 16:20:49 - INFO - __main__ - Step 149782: {'lr': 2.701305949981414e-09, 'samples': 28758144, 'steps': 149781, 'loss/train': 0.5773376822471619} 08/31/2021 16:20:49 - INFO - __main__ - Step 149783: {'lr': 2.6766928561405834e-09, 'samples': 28758336, 'steps': 149782, 'loss/train': 1.2082575559616089} 08/31/2021 16:20:49 - INFO - __main__ - Step 149784: {'lr': 2.652192407248677e-09, 'samples': 28758528, 'steps': 149783, 'loss/train': 0.47325432300567627} 08/31/2021 16:20:51 - INFO - __main__ - Step 149785: {'lr': 2.627804603277939e-09, 'samples': 28758720, 'steps': 149784, 'loss/train': 1.0575505495071411} 08/31/2021 16:20:51 - INFO - __main__ - Step 149786: {'lr': 2.6035294442838807e-09, 'samples': 28758912, 'steps': 149785, 'loss/train': 1.3533554077148438} 08/31/2021 16:20:52 - INFO - __main__ - Step 149787: {'lr': 2.5793669302665024e-09, 'samples': 28759104, 'steps': 149786, 'loss/train': 1.5234413146972656} 08/31/2021 16:20:52 - INFO - __main__ - Step 149788: {'lr': 2.5553170611980482e-09, 'samples': 28759296, 'steps': 149787, 'loss/train': 1.3996204137802124} 08/31/2021 16:20:52 - INFO - __main__ - Step 149789: {'lr': 2.531379837134029e-09, 'samples': 28759488, 'steps': 149788, 'loss/train': 1.4700005054473877} 08/31/2021 16:20:54 - INFO - __main__ - Step 149790: {'lr': 2.507555258102201e-09, 'samples': 28759680, 'steps': 149789, 'loss/train': 1.7025258541107178} 08/31/2021 16:20:55 - INFO - __main__ - Step 149791: {'lr': 2.4838433240470526e-09, 'samples': 28759872, 'steps': 149790, 'loss/train': 0.025458145886659622} 08/31/2021 16:20:55 - INFO - __main__ - Step 149792: {'lr': 2.460244035024095e-09, 'samples': 28760064, 'steps': 149791, 'loss/train': 0.6745039820671082} 08/31/2021 16:20:55 - INFO - __main__ - Step 149793: {'lr': 2.4367573910333284e-09, 'samples': 28760256, 'steps': 149792, 'loss/train': 0.3142545223236084} 08/31/2021 16:20:56 - INFO - __main__ - Step 149794: {'lr': 2.4133833921025084e-09, 'samples': 28760448, 'steps': 149793, 'loss/train': 1.1363720893859863} 08/31/2021 16:20:56 - INFO - __main__ - Step 149795: {'lr': 2.390122038203879e-09, 'samples': 28760640, 'steps': 149794, 'loss/train': 0.9550213813781738} 08/31/2021 16:20:57 - INFO - __main__ - Step 149796: {'lr': 2.366973329392952e-09, 'samples': 28760832, 'steps': 149795, 'loss/train': 1.772907018661499} 08/31/2021 16:20:58 - INFO - __main__ - Step 149797: {'lr': 2.343937265641971e-09, 'samples': 28761024, 'steps': 149796, 'loss/train': 1.185416579246521} 08/31/2021 16:20:58 - INFO - __main__ - Step 149798: {'lr': 2.3210138469786922e-09, 'samples': 28761216, 'steps': 149797, 'loss/train': 1.0580741167068481} 08/31/2021 16:20:59 - INFO - __main__ - Step 149799: {'lr': 2.2982030734031158e-09, 'samples': 28761408, 'steps': 149798, 'loss/train': 0.5517670512199402} 08/31/2021 16:20:59 - INFO - __main__ - Step 149800: {'lr': 2.275504944970752e-09, 'samples': 28761600, 'steps': 149799, 'loss/train': 0.8814387321472168} 08/31/2021 16:21:00 - INFO - __main__ - Step 149801: {'lr': 2.2529194616260905e-09, 'samples': 28761792, 'steps': 149800, 'loss/train': 1.3015508651733398} 08/31/2021 16:21:01 - INFO - __main__ - Step 149802: {'lr': 2.230446623396887e-09, 'samples': 28761984, 'steps': 149801, 'loss/train': 1.2359369993209839} 08/31/2021 16:21:01 - INFO - __main__ - Step 149803: {'lr': 2.2080864303386515e-09, 'samples': 28762176, 'steps': 149802, 'loss/train': 0.9412114024162292} 08/31/2021 16:21:02 - INFO - __main__ - Step 149804: {'lr': 2.185838882395874e-09, 'samples': 28762368, 'steps': 149803, 'loss/train': 0.2618465721607208} 08/31/2021 16:21:02 - INFO - __main__ - Step 149805: {'lr': 2.1637039796240653e-09, 'samples': 28762560, 'steps': 149804, 'loss/train': 0.15842469036579132} 08/31/2021 16:21:04 - INFO - __main__ - Step 149806: {'lr': 2.1416817220232253e-09, 'samples': 28762752, 'steps': 149805, 'loss/train': 1.1453732252120972} 08/31/2021 16:21:04 - INFO - __main__ - Step 149807: {'lr': 2.1197721095933544e-09, 'samples': 28762944, 'steps': 149806, 'loss/train': 0.431525319814682} 08/31/2021 16:21:05 - INFO - __main__ - Step 149808: {'lr': 2.0979751423622075e-09, 'samples': 28763136, 'steps': 149807, 'loss/train': 0.758161187171936} 08/31/2021 16:21:05 - INFO - __main__ - Step 149809: {'lr': 2.076290820329785e-09, 'samples': 28763328, 'steps': 149808, 'loss/train': 0.9439501762390137} 08/31/2021 16:21:05 - INFO - __main__ - Step 149810: {'lr': 2.054719143468331e-09, 'samples': 28763520, 'steps': 149809, 'loss/train': 1.540806770324707} 08/31/2021 16:21:06 - INFO - __main__ - Step 149811: {'lr': 2.033260111861113e-09, 'samples': 28763712, 'steps': 149810, 'loss/train': 0.5501918792724609} 08/31/2021 16:21:07 - INFO - __main__ - Step 149812: {'lr': 2.0119137254803743e-09, 'samples': 28763904, 'steps': 149811, 'loss/train': 0.015610579401254654} 08/31/2021 16:21:08 - INFO - __main__ - Step 149813: {'lr': 1.9906799842983604e-09, 'samples': 28764096, 'steps': 149812, 'loss/train': 1.3756722211837769} 08/31/2021 16:21:08 - INFO - __main__ - Step 149814: {'lr': 1.9695588883983374e-09, 'samples': 28764288, 'steps': 149813, 'loss/train': 1.1515229940414429} 08/31/2021 16:21:08 - INFO - __main__ - Step 149815: {'lr': 1.9485504377525496e-09, 'samples': 28764480, 'steps': 149814, 'loss/train': 1.2280255556106567} 08/31/2021 16:21:09 - INFO - __main__ - Step 149816: {'lr': 1.927654632360998e-09, 'samples': 28764672, 'steps': 149815, 'loss/train': 0.35630935430526733} 08/31/2021 16:21:09 - INFO - __main__ - Step 149817: {'lr': 1.9068714722236813e-09, 'samples': 28764864, 'steps': 149816, 'loss/train': 1.5962209701538086} 08/31/2021 16:21:10 - INFO - __main__ - Step 149818: {'lr': 1.8862009573961112e-09, 'samples': 28765056, 'steps': 149817, 'loss/train': 1.461860179901123} 08/31/2021 16:21:11 - INFO - __main__ - Step 149819: {'lr': 1.865643087850533e-09, 'samples': 28765248, 'steps': 149818, 'loss/train': 0.9473564624786377} 08/31/2021 16:21:11 - INFO - __main__ - Step 149820: {'lr': 1.8451978636147005e-09, 'samples': 28765440, 'steps': 149819, 'loss/train': 0.9953125715255737} 08/31/2021 16:21:12 - INFO - __main__ - Step 149821: {'lr': 1.8248652846608594e-09, 'samples': 28765632, 'steps': 149820, 'loss/train': 1.0734580755233765} 08/31/2021 16:21:12 - INFO - __main__ - Step 149822: {'lr': 1.804645351072276e-09, 'samples': 28765824, 'steps': 149821, 'loss/train': 1.5520387887954712} 08/31/2021 16:21:13 - INFO - __main__ - Step 149823: {'lr': 1.7845380627934393e-09, 'samples': 28766016, 'steps': 149822, 'loss/train': 0.81812584400177} 08/31/2021 16:21:14 - INFO - __main__ - Step 149824: {'lr': 1.7645434198243494e-09, 'samples': 28766208, 'steps': 149823, 'loss/train': 0.3860863745212555} 08/31/2021 16:21:14 - INFO - __main__ - Step 149825: {'lr': 1.7446614222482725e-09, 'samples': 28766400, 'steps': 149824, 'loss/train': 0.10940290242433548} 08/31/2021 16:21:15 - INFO - __main__ - Step 149826: {'lr': 1.7248920700096982e-09, 'samples': 28766592, 'steps': 149825, 'loss/train': 0.9781619310379028} 08/31/2021 16:21:15 - INFO - __main__ - Step 149827: {'lr': 1.705235363108626e-09, 'samples': 28766784, 'steps': 149826, 'loss/train': 2.0218610763549805} 08/31/2021 16:21:17 - INFO - __main__ - Step 149828: {'lr': 1.6856913016283226e-09, 'samples': 28766976, 'steps': 149827, 'loss/train': 1.8022007942199707} 08/31/2021 16:21:17 - INFO - __main__ - Step 149829: {'lr': 1.6662598855132771e-09, 'samples': 28767168, 'steps': 149828, 'loss/train': 1.807294487953186} 08/31/2021 16:21:17 - INFO - __main__ - Step 149830: {'lr': 1.6469411147634894e-09, 'samples': 28767360, 'steps': 149829, 'loss/train': 0.2620094120502472} 08/31/2021 16:21:18 - INFO - __main__ - Step 149831: {'lr': 1.6277349894344707e-09, 'samples': 28767552, 'steps': 149830, 'loss/train': 1.4769299030303955} 08/31/2021 16:21:18 - INFO - __main__ - Step 149832: {'lr': 1.6086415095262208e-09, 'samples': 28767744, 'steps': 149831, 'loss/train': 0.8819641470909119} 08/31/2021 16:21:19 - INFO - __main__ - Step 149833: {'lr': 1.5896606750109844e-09, 'samples': 28767936, 'steps': 149832, 'loss/train': 1.8201056718826294} 08/31/2021 16:21:20 - INFO - __main__ - Step 149834: {'lr': 1.5707924859442723e-09, 'samples': 28768128, 'steps': 149833, 'loss/train': 1.0516140460968018} 08/31/2021 16:21:20 - INFO - __main__ - Step 149835: {'lr': 1.5520369422983294e-09, 'samples': 28768320, 'steps': 149834, 'loss/train': 1.1711570024490356} 08/31/2021 16:21:21 - INFO - __main__ - Step 149836: {'lr': 1.5333940441009109e-09, 'samples': 28768512, 'steps': 149835, 'loss/train': 0.8303213119506836} 08/31/2021 16:21:21 - INFO - __main__ - Step 149837: {'lr': 1.514863791352017e-09, 'samples': 28768704, 'steps': 149836, 'loss/train': 2.0586135387420654} 08/31/2021 16:21:23 - INFO - __main__ - Step 149838: {'lr': 1.496446184079403e-09, 'samples': 28768896, 'steps': 149837, 'loss/train': 1.122949481010437} 08/31/2021 16:21:24 - INFO - __main__ - Step 149839: {'lr': 1.4781412222553136e-09, 'samples': 28769088, 'steps': 149838, 'loss/train': 0.42874208092689514} 08/31/2021 16:21:24 - INFO - __main__ - Step 149840: {'lr': 1.4599489059075045e-09, 'samples': 28769280, 'steps': 149839, 'loss/train': 1.0688585042953491} 08/31/2021 16:21:24 - INFO - __main__ - Step 149841: {'lr': 1.4418692350637309e-09, 'samples': 28769472, 'steps': 149840, 'loss/train': 0.48271679878234863} 08/31/2021 16:21:25 - INFO - __main__ - Step 149842: {'lr': 1.4239022096962373e-09, 'samples': 28769664, 'steps': 149841, 'loss/train': 1.3102914094924927} 08/31/2021 16:21:26 - INFO - __main__ - Step 149843: {'lr': 1.4060478298327794e-09, 'samples': 28769856, 'steps': 149842, 'loss/train': 0.384466290473938} 08/31/2021 16:21:27 - INFO - __main__ - Step 149844: {'lr': 1.3883060954733572e-09, 'samples': 28770048, 'steps': 149843, 'loss/train': 0.7883098125457764} 08/31/2021 16:21:27 - INFO - __main__ - Step 149845: {'lr': 1.3706770066179707e-09, 'samples': 28770240, 'steps': 149844, 'loss/train': 0.867048442363739} 08/31/2021 16:21:27 - INFO - __main__ - Step 149846: {'lr': 1.3531605633221312e-09, 'samples': 28770432, 'steps': 149845, 'loss/train': 1.2505583763122559} 08/31/2021 16:21:28 - INFO - __main__ - Step 149847: {'lr': 1.3357567655303271e-09, 'samples': 28770624, 'steps': 149846, 'loss/train': 1.1372343301773071} 08/31/2021 16:21:28 - INFO - __main__ - Step 149848: {'lr': 1.31846561329807e-09, 'samples': 28770816, 'steps': 149847, 'loss/train': 1.1278516054153442} 08/31/2021 16:21:29 - INFO - __main__ - Step 149849: {'lr': 1.301287106597604e-09, 'samples': 28771008, 'steps': 149848, 'loss/train': 1.0247411727905273} 08/31/2021 16:21:30 - INFO - __main__ - Step 149850: {'lr': 1.2842212454566848e-09, 'samples': 28771200, 'steps': 149849, 'loss/train': 0.24309511482715607} 08/31/2021 16:21:30 - INFO - __main__ - Step 149851: {'lr': 1.2672680298753125e-09, 'samples': 28771392, 'steps': 149850, 'loss/train': 1.2550854682922363} 08/31/2021 16:21:31 - INFO - __main__ - Step 149852: {'lr': 1.2504274598812426e-09, 'samples': 28771584, 'steps': 149851, 'loss/train': 1.4521085023880005} 08/31/2021 16:21:31 - INFO - __main__ - Step 149853: {'lr': 1.2336995354467196e-09, 'samples': 28771776, 'steps': 149852, 'loss/train': 1.128719449043274} 08/31/2021 16:21:32 - INFO - __main__ - Step 149854: {'lr': 1.2170842566272544e-09, 'samples': 28771968, 'steps': 149853, 'loss/train': 1.347937822341919} 08/31/2021 16:21:33 - INFO - __main__ - Step 149855: {'lr': 1.200581623367336e-09, 'samples': 28772160, 'steps': 149854, 'loss/train': 1.733876347541809} 08/31/2021 16:21:33 - INFO - __main__ - Step 149856: {'lr': 1.1841916357224758e-09, 'samples': 28772352, 'steps': 149855, 'loss/train': 1.0650843381881714} 08/31/2021 16:21:34 - INFO - __main__ - Step 149857: {'lr': 1.1679142936926735e-09, 'samples': 28772544, 'steps': 149856, 'loss/train': 0.9139866232872009} 08/31/2021 16:21:34 - INFO - __main__ - Step 149858: {'lr': 1.151749597277929e-09, 'samples': 28772736, 'steps': 149857, 'loss/train': 0.6873379349708557} 08/31/2021 16:21:36 - INFO - __main__ - Step 149859: {'lr': 1.1356975464782427e-09, 'samples': 28772928, 'steps': 149858, 'loss/train': 0.7122147679328918} 08/31/2021 16:21:36 - INFO - __main__ - Step 149860: {'lr': 1.1197581413213698e-09, 'samples': 28773120, 'steps': 149859, 'loss/train': 0.8845395445823669} 08/31/2021 16:21:37 - INFO - __main__ - Step 149861: {'lr': 1.1039313818073105e-09, 'samples': 28773312, 'steps': 149860, 'loss/train': 1.164440393447876} 08/31/2021 16:21:37 - INFO - __main__ - Step 149862: {'lr': 1.088217267908309e-09, 'samples': 28773504, 'steps': 149861, 'loss/train': 1.0321398973464966} 08/31/2021 16:21:37 - INFO - __main__ - Step 149863: {'lr': 1.0726157996798768e-09, 'samples': 28773696, 'steps': 149862, 'loss/train': 0.8942901492118835} 08/31/2021 16:21:39 - INFO - __main__ - Step 149864: {'lr': 1.0571269771220137e-09, 'samples': 28773888, 'steps': 149863, 'loss/train': 1.0217773914337158} 08/31/2021 16:21:39 - INFO - __main__ - Step 149865: {'lr': 1.0417508002069642e-09, 'samples': 28774080, 'steps': 149864, 'loss/train': 0.8517250418663025} 08/31/2021 16:21:39 - INFO - __main__ - Step 149866: {'lr': 1.0264872689902394e-09, 'samples': 28774272, 'steps': 149865, 'loss/train': 0.7631605863571167} 08/31/2021 16:21:40 - INFO - __main__ - Step 149867: {'lr': 1.011336383416328e-09, 'samples': 28774464, 'steps': 149866, 'loss/train': 1.4431220293045044} 08/31/2021 16:21:40 - INFO - __main__ - Step 149868: {'lr': 9.96298143568497e-10, 'samples': 28774656, 'steps': 149867, 'loss/train': 1.0675197839736938} 08/31/2021 16:21:42 - INFO - __main__ - Step 149869: {'lr': 9.81372549391235e-10, 'samples': 28774848, 'steps': 149868, 'loss/train': 0.8099356889724731} 08/31/2021 16:21:42 - INFO - __main__ - Step 149870: {'lr': 9.665596009122978e-10, 'samples': 28775040, 'steps': 149869, 'loss/train': 1.2514350414276123} 08/31/2021 16:21:43 - INFO - __main__ - Step 149871: {'lr': 9.518592981594409e-10, 'samples': 28775232, 'steps': 149870, 'loss/train': 1.9397114515304565} 08/31/2021 16:21:43 - INFO - __main__ - Step 149872: {'lr': 9.372716411049087e-10, 'samples': 28775424, 'steps': 149871, 'loss/train': 1.2611044645309448} 08/31/2021 16:21:43 - INFO - __main__ - Step 149873: {'lr': 9.227966297764568e-10, 'samples': 28775616, 'steps': 149872, 'loss/train': 1.5490719079971313} 08/31/2021 16:21:45 - INFO - __main__ - Step 149874: {'lr': 9.08434264174085e-10, 'samples': 28775808, 'steps': 149873, 'loss/train': 0.896199643611908} 08/31/2021 16:21:45 - INFO - __main__ - Step 149875: {'lr': 8.941845442977936e-10, 'samples': 28776000, 'steps': 149874, 'loss/train': 1.1063991785049438} 08/31/2021 16:21:46 - INFO - __main__ - Step 149876: {'lr': 8.800474701475824e-10, 'samples': 28776192, 'steps': 149875, 'loss/train': 0.026715504005551338} 08/31/2021 16:21:46 - INFO - __main__ - Step 149877: {'lr': 8.660230417789627e-10, 'samples': 28776384, 'steps': 149876, 'loss/train': 0.12326253950595856} 08/31/2021 16:21:46 - INFO - __main__ - Step 149878: {'lr': 8.521112591364233e-10, 'samples': 28776576, 'steps': 149877, 'loss/train': 1.236390233039856} 08/31/2021 16:21:48 - INFO - __main__ - Step 149879: {'lr': 8.383121222477197e-10, 'samples': 28776768, 'steps': 149878, 'loss/train': 1.1805920600891113} 08/31/2021 16:21:48 - INFO - __main__ - Step 149880: {'lr': 8.246256311406076e-10, 'samples': 28776960, 'steps': 149879, 'loss/train': 1.019073247909546} 08/31/2021 16:21:49 - INFO - __main__ - Step 149881: {'lr': 8.110517858150867e-10, 'samples': 28777152, 'steps': 149880, 'loss/train': 1.4593138694763184} 08/31/2021 16:21:49 - INFO - __main__ - Step 149882: {'lr': 7.975905862434018e-10, 'samples': 28777344, 'steps': 149881, 'loss/train': 0.9222007393836975} 08/31/2021 16:21:49 - INFO - __main__ - Step 149883: {'lr': 7.842420324533084e-10, 'samples': 28777536, 'steps': 149882, 'loss/train': 1.0352226495742798} 08/31/2021 16:21:50 - INFO - __main__ - Step 149884: {'lr': 7.710061244725619e-10, 'samples': 28777728, 'steps': 149883, 'loss/train': 1.121339201927185} 08/31/2021 16:21:51 - INFO - __main__ - Step 149885: {'lr': 7.578828622734069e-10, 'samples': 28777920, 'steps': 149884, 'loss/train': 0.840016782283783} 08/31/2021 16:21:52 - INFO - __main__ - Step 149886: {'lr': 7.448722458558433e-10, 'samples': 28778112, 'steps': 149885, 'loss/train': 0.7876421213150024} 08/31/2021 16:21:52 - INFO - __main__ - Step 149887: {'lr': 7.319742752753822e-10, 'samples': 28778304, 'steps': 149886, 'loss/train': 1.5795661211013794} 08/31/2021 16:21:53 - INFO - __main__ - Step 149888: {'lr': 7.191889505042682e-10, 'samples': 28778496, 'steps': 149887, 'loss/train': 1.2262250185012817} 08/31/2021 16:21:53 - INFO - __main__ - Step 149889: {'lr': 7.065162715425011e-10, 'samples': 28778688, 'steps': 149888, 'loss/train': 0.1652972251176834} 08/31/2021 16:21:55 - INFO - __main__ - Step 149890: {'lr': 6.939562383900811e-10, 'samples': 28778880, 'steps': 149889, 'loss/train': 0.7854714393615723} 08/31/2021 16:21:55 - INFO - __main__ - Step 149891: {'lr': 6.815088511025192e-10, 'samples': 28779072, 'steps': 149890, 'loss/train': 0.4162340760231018} 08/31/2021 16:21:56 - INFO - __main__ - Step 149892: {'lr': 6.691741096243043e-10, 'samples': 28779264, 'steps': 149891, 'loss/train': 1.3495584726333618} 08/31/2021 16:21:56 - INFO - __main__ - Step 149893: {'lr': 6.569520139831919e-10, 'samples': 28779456, 'steps': 149892, 'loss/train': 0.7445064187049866} 08/31/2021 16:21:56 - INFO - __main__ - Step 149894: {'lr': 6.448425642069378e-10, 'samples': 28779648, 'steps': 149893, 'loss/train': 1.0273659229278564} 08/31/2021 16:21:58 - INFO - __main__ - Step 149895: {'lr': 6.328457602677862e-10, 'samples': 28779840, 'steps': 149894, 'loss/train': 1.1624023914337158} 08/31/2021 16:21:58 - INFO - __main__ - Step 149896: {'lr': 6.209616021934927e-10, 'samples': 28780032, 'steps': 149895, 'loss/train': 1.3080378770828247} 08/31/2021 16:21:59 - INFO - __main__ - Step 149897: {'lr': 6.091900899840575e-10, 'samples': 28780224, 'steps': 149896, 'loss/train': 1.285388469696045} 08/31/2021 16:21:59 - INFO - __main__ - Step 149898: {'lr': 5.975312236394803e-10, 'samples': 28780416, 'steps': 149897, 'loss/train': 0.9395138025283813} 08/31/2021 16:21:59 - INFO - __main__ - Step 149899: {'lr': 5.859850031597613e-10, 'samples': 28780608, 'steps': 149898, 'loss/train': 1.481035828590393} 08/31/2021 16:22:00 - INFO - __main__ - Step 149900: {'lr': 5.745514285726561e-10, 'samples': 28780800, 'steps': 149899, 'loss/train': 0.7471625804901123} 08/31/2021 16:22:01 - INFO - __main__ - Step 149901: {'lr': 5.63230499850409e-10, 'samples': 28780992, 'steps': 149900, 'loss/train': 1.0438016653060913} 08/31/2021 16:22:02 - INFO - __main__ - Step 149902: {'lr': 5.520222170485312e-10, 'samples': 28781184, 'steps': 149901, 'loss/train': 0.6642974019050598} 08/31/2021 16:22:02 - INFO - __main__ - Step 149903: {'lr': 5.409265801115116e-10, 'samples': 28781376, 'steps': 149902, 'loss/train': 1.1354416608810425} 08/31/2021 16:22:03 - INFO - __main__ - Step 149904: {'lr': 5.299435890671056e-10, 'samples': 28781568, 'steps': 149903, 'loss/train': 1.174433708190918} 08/31/2021 16:22:03 - INFO - __main__ - Step 149905: {'lr': 5.19073243943069e-10, 'samples': 28781760, 'steps': 149904, 'loss/train': 1.4627645015716553} 08/31/2021 16:22:05 - INFO - __main__ - Step 149906: {'lr': 5.083155447394017e-10, 'samples': 28781952, 'steps': 149905, 'loss/train': 1.116202712059021} 08/31/2021 16:22:05 - INFO - __main__ - Step 149907: {'lr': 4.976704914283481e-10, 'samples': 28782144, 'steps': 149906, 'loss/train': 0.029251568019390106} 08/31/2021 16:22:06 - INFO - __main__ - Step 149908: {'lr': 4.871380840376637e-10, 'samples': 28782336, 'steps': 149907, 'loss/train': 0.05578245967626572} 08/31/2021 16:22:06 - INFO - __main__ - Step 149909: {'lr': 4.767183225673488e-10, 'samples': 28782528, 'steps': 149908, 'loss/train': 0.03207721933722496} 08/31/2021 16:22:06 - INFO - __main__ - Step 149910: {'lr': 4.664112070451587e-10, 'samples': 28782720, 'steps': 149909, 'loss/train': 0.03267301619052887} 08/31/2021 16:22:07 - INFO - __main__ - Step 149911: {'lr': 4.562167374433379e-10, 'samples': 28782912, 'steps': 149910, 'loss/train': 0.11605348438024521} 08/31/2021 16:22:08 - INFO - __main__ - Step 149912: {'lr': 4.461349137618864e-10, 'samples': 28783104, 'steps': 149911, 'loss/train': 1.1344445943832397} 08/31/2021 16:22:09 - INFO - __main__ - Step 149913: {'lr': 4.361657360285598e-10, 'samples': 28783296, 'steps': 149912, 'loss/train': 5.672525405883789} 08/31/2021 16:22:09 - INFO - __main__ - Step 149914: {'lr': 4.2630920427111365e-10, 'samples': 28783488, 'steps': 149913, 'loss/train': 1.501252293586731} 08/31/2021 16:22:09 - INFO - __main__ - Step 149915: {'lr': 4.165653184340368e-10, 'samples': 28783680, 'steps': 149914, 'loss/train': 0.8637490272521973} 08/31/2021 16:22:10 - INFO - __main__ - Step 149916: {'lr': 4.069340785450848e-10, 'samples': 28783872, 'steps': 149915, 'loss/train': 1.0484521389007568} 08/31/2021 16:22:10 - INFO - __main__ - Step 149917: {'lr': 3.9741548463201325e-10, 'samples': 28784064, 'steps': 149916, 'loss/train': 0.7789521217346191} 08/31/2021 16:22:12 - INFO - __main__ - Step 149918: {'lr': 3.880095366670666e-10, 'samples': 28784256, 'steps': 149917, 'loss/train': 1.6114364862442017} 08/31/2021 16:22:12 - INFO - __main__ - Step 149919: {'lr': 3.7871623470575603e-10, 'samples': 28784448, 'steps': 149918, 'loss/train': 0.6512871384620667} 08/31/2021 16:22:13 - INFO - __main__ - Step 149920: {'lr': 3.695355786648147e-10, 'samples': 28784640, 'steps': 149919, 'loss/train': 1.140464425086975} 08/31/2021 16:22:13 - INFO - __main__ - Step 149921: {'lr': 3.604675686275094e-10, 'samples': 28784832, 'steps': 149920, 'loss/train': 1.021491289138794} 08/31/2021 16:22:13 - INFO - __main__ - Step 149922: {'lr': 3.515122045660846e-10, 'samples': 28785024, 'steps': 149921, 'loss/train': 0.7450493574142456} 08/31/2021 16:22:15 - INFO - __main__ - Step 149923: {'lr': 3.4266948650829576e-10, 'samples': 28785216, 'steps': 149922, 'loss/train': 2.0029022693634033} 08/31/2021 16:22:15 - INFO - __main__ - Step 149924: {'lr': 3.3393941442638743e-10, 'samples': 28785408, 'steps': 149923, 'loss/train': 1.6153922080993652} 08/31/2021 16:22:15 - INFO - __main__ - Step 149925: {'lr': 3.253219883203595e-10, 'samples': 28785600, 'steps': 149924, 'loss/train': 0.6124691367149353} 08/31/2021 16:22:16 - INFO - __main__ - Step 149926: {'lr': 3.1681720821796766e-10, 'samples': 28785792, 'steps': 149925, 'loss/train': 0.8562684655189514} 08/31/2021 16:22:16 - INFO - __main__ - Step 149927: {'lr': 3.0842507411921185e-10, 'samples': 28785984, 'steps': 149926, 'loss/train': 0.938255250453949} 08/31/2021 16:22:18 - INFO - __main__ - Step 149928: {'lr': 3.00145586024092e-10, 'samples': 28786176, 'steps': 149927, 'loss/train': 1.1064256429672241} 08/31/2021 16:22:18 - INFO - __main__ - Step 149929: {'lr': 2.9197874393260826e-10, 'samples': 28786368, 'steps': 149928, 'loss/train': 1.7105653285980225} 08/31/2021 16:22:19 - INFO - __main__ - Step 149930: {'lr': 2.8392454784476053e-10, 'samples': 28786560, 'steps': 149929, 'loss/train': 0.11060620099306107} 08/31/2021 16:22:19 - INFO - __main__ - Step 149931: {'lr': 2.7598299778830437e-10, 'samples': 28786752, 'steps': 149930, 'loss/train': 1.1264764070510864} 08/31/2021 16:22:19 - INFO - __main__ - Step 149932: {'lr': 2.681540937354843e-10, 'samples': 28786944, 'steps': 149931, 'loss/train': 1.2427358627319336} 08/31/2021 16:22:21 - INFO - __main__ - Step 149933: {'lr': 2.6043783571405576e-10, 'samples': 28787136, 'steps': 149932, 'loss/train': 1.65632164478302} 08/31/2021 16:22:21 - INFO - __main__ - Step 149934: {'lr': 2.528342236962633e-10, 'samples': 28787328, 'steps': 149933, 'loss/train': 1.0621076822280884} 08/31/2021 16:22:22 - INFO - __main__ - Step 149935: {'lr': 2.45343257737618e-10, 'samples': 28787520, 'steps': 149934, 'loss/train': 1.5249167680740356} 08/31/2021 16:22:22 - INFO - __main__ - Step 149936: {'lr': 2.3796493778260873e-10, 'samples': 28787712, 'steps': 149935, 'loss/train': 1.5345592498779297} 08/31/2021 16:22:23 - INFO - __main__ - Step 149937: {'lr': 2.3069926388674667e-10, 'samples': 28787904, 'steps': 149936, 'loss/train': 1.5181492567062378} 08/31/2021 16:22:23 - INFO - __main__ - Step 149938: {'lr': 2.235462360222762e-10, 'samples': 28788096, 'steps': 149937, 'loss/train': 1.4385374784469604} 08/31/2021 16:22:24 - INFO - __main__ - Step 149939: {'lr': 2.1650585418919733e-10, 'samples': 28788288, 'steps': 149938, 'loss/train': 1.3464770317077637} 08/31/2021 16:22:25 - INFO - __main__ - Step 149940: {'lr': 2.0957811841526563e-10, 'samples': 28788480, 'steps': 149939, 'loss/train': 1.1407819986343384} 08/31/2021 16:22:25 - INFO - __main__ - Step 149941: {'lr': 2.0276302867272557e-10, 'samples': 28788672, 'steps': 149940, 'loss/train': 0.5248652100563049} 08/31/2021 16:22:25 - INFO - __main__ - Step 149942: {'lr': 1.9606058498933267e-10, 'samples': 28788864, 'steps': 149941, 'loss/train': 0.9386979341506958} 08/31/2021 16:22:26 - INFO - __main__ - Step 149943: {'lr': 1.8947078736508693e-10, 'samples': 28789056, 'steps': 149942, 'loss/train': 0.7320161461830139} 08/31/2021 16:22:28 - INFO - __main__ - Step 149944: {'lr': 1.829936357999884e-10, 'samples': 28789248, 'steps': 149943, 'loss/train': 1.326582670211792} 08/31/2021 16:22:28 - INFO - __main__ - Step 149945: {'lr': 1.7662913029403706e-10, 'samples': 28789440, 'steps': 149944, 'loss/train': 1.4991451501846313} 08/31/2021 16:22:29 - INFO - __main__ - Step 149946: {'lr': 1.7037727081947728e-10, 'samples': 28789632, 'steps': 149945, 'loss/train': 1.1650111675262451} 08/31/2021 16:22:29 - INFO - __main__ - Step 149947: {'lr': 1.6423805745957586e-10, 'samples': 28789824, 'steps': 149946, 'loss/train': 1.3694195747375488} 08/31/2021 16:22:29 - INFO - __main__ - Step 149948: {'lr': 1.5821149013106605e-10, 'samples': 28790016, 'steps': 149947, 'loss/train': 1.2365660667419434} 08/31/2021 16:22:31 - INFO - __main__ - Step 149949: {'lr': 1.5229756888945901e-10, 'samples': 28790208, 'steps': 149948, 'loss/train': 0.5275929570198059} 08/31/2021 16:22:31 - INFO - __main__ - Step 149950: {'lr': 1.4649629370699914e-10, 'samples': 28790400, 'steps': 149949, 'loss/train': 0.7484543919563293} 08/31/2021 16:22:32 - INFO - __main__ - Step 149951: {'lr': 1.40807664611442e-10, 'samples': 28790592, 'steps': 149950, 'loss/train': 0.3227772116661072} 08/31/2021 16:22:32 - INFO - __main__ - Step 149952: {'lr': 1.3523168160278765e-10, 'samples': 28790784, 'steps': 149951, 'loss/train': 1.664406418800354} 08/31/2021 16:22:32 - INFO - __main__ - Step 149953: {'lr': 1.2976834468103606e-10, 'samples': 28790976, 'steps': 149952, 'loss/train': 0.285401850938797} 08/31/2021 16:22:34 - INFO - __main__ - Step 149954: {'lr': 1.2441765381843163e-10, 'samples': 28791168, 'steps': 149953, 'loss/train': 1.3196310997009277} 08/31/2021 16:22:34 - INFO - __main__ - Step 149955: {'lr': 1.1917960904272995e-10, 'samples': 28791360, 'steps': 149954, 'loss/train': 0.9173851013183594} 08/31/2021 16:22:35 - INFO - __main__ - Step 149956: {'lr': 1.1405421038168662e-10, 'samples': 28791552, 'steps': 149955, 'loss/train': 1.1894503831863403} 08/31/2021 16:22:35 - INFO - __main__ - Step 149957: {'lr': 1.0904145777979047e-10, 'samples': 28791744, 'steps': 149956, 'loss/train': 1.2109333276748657} 08/31/2021 16:22:35 - INFO - __main__ - Step 149958: {'lr': 1.0414135129255265e-10, 'samples': 28791936, 'steps': 149957, 'loss/train': 1.465036392211914} 08/31/2021 16:22:37 - INFO - __main__ - Step 149959: {'lr': 9.935389089221758e-11, 'samples': 28792128, 'steps': 149958, 'loss/train': 0.8519787192344666} 08/31/2021 16:22:37 - INFO - __main__ - Step 149960: {'lr': 9.467907660654085e-11, 'samples': 28792320, 'steps': 149959, 'loss/train': 1.2642061710357666} 08/31/2021 16:22:38 - INFO - __main__ - Step 149961: {'lr': 9.011690840776687e-11, 'samples': 28792512, 'steps': 149960, 'loss/train': 1.17654550075531} 08/31/2021 16:22:38 - INFO - __main__ - Step 149962: {'lr': 8.566738629589565e-11, 'samples': 28792704, 'steps': 149961, 'loss/train': 1.5724478960037231} 08/31/2021 16:22:38 - INFO - __main__ - Step 149963: {'lr': 8.133051029868277e-11, 'samples': 28792896, 'steps': 149962, 'loss/train': 1.0613826513290405} 08/31/2021 16:22:40 - INFO - __main__ - Step 149964: {'lr': 7.710628041612822e-11, 'samples': 28793088, 'steps': 149963, 'loss/train': 0.706835150718689} 08/31/2021 16:22:40 - INFO - __main__ - Step 149965: {'lr': 7.2994696648232e-11, 'samples': 28793280, 'steps': 149964, 'loss/train': 1.2184820175170898} 08/31/2021 16:22:41 - INFO - __main__ - Step 149966: {'lr': 6.899575896723852e-11, 'samples': 28793472, 'steps': 149965, 'loss/train': 0.7050849795341492} 08/31/2021 16:22:41 - INFO - __main__ - Step 149967: {'lr': 6.51094674009034e-11, 'samples': 28793664, 'steps': 149966, 'loss/train': 1.380181908607483} 08/31/2021 16:22:41 - INFO - __main__ - Step 149968: {'lr': 6.13358219492266e-11, 'samples': 28793856, 'steps': 149967, 'loss/train': 1.1519826650619507} 08/31/2021 16:22:43 - INFO - __main__ - Step 149969: {'lr': 5.767482261220813e-11, 'samples': 28794048, 'steps': 149968, 'loss/train': 0.9800353050231934} 08/31/2021 16:22:43 - INFO - __main__ - Step 149970: {'lr': 5.4126469417603575e-11, 'samples': 28794240, 'steps': 149969, 'loss/train': 0.5347627997398376} 08/31/2021 16:22:44 - INFO - __main__ - Step 149971: {'lr': 5.069076230990177e-11, 'samples': 28794432, 'steps': 149970, 'loss/train': 1.3286854028701782} 08/31/2021 16:22:44 - INFO - __main__ - Step 149972: {'lr': 4.7367701316858304e-11, 'samples': 28794624, 'steps': 149971, 'loss/train': 0.9551845788955688} 08/31/2021 16:22:44 - INFO - __main__ - Step 149973: {'lr': 4.415728646622874e-11, 'samples': 28794816, 'steps': 149972, 'loss/train': 1.2559815645217896} 08/31/2021 16:22:45 - INFO - __main__ - Step 149974: {'lr': 4.105951773025751e-11, 'samples': 28795008, 'steps': 149973, 'loss/train': 1.0617676973342896} 08/31/2021 16:22:46 - INFO - __main__ - Step 149975: {'lr': 3.807439510894461e-11, 'samples': 28795200, 'steps': 149974, 'loss/train': 1.2813369035720825} 08/31/2021 16:22:47 - INFO - __main__ - Step 149976: {'lr': 3.5201918630045624e-11, 'samples': 28795392, 'steps': 149975, 'loss/train': 1.0777987241744995} 08/31/2021 16:22:47 - INFO - __main__ - Step 149977: {'lr': 3.244208826580497e-11, 'samples': 28795584, 'steps': 149976, 'loss/train': 1.23732328414917} 08/31/2021 16:22:47 - INFO - __main__ - Step 149978: {'lr': 2.979490404397822e-11, 'samples': 28795776, 'steps': 149977, 'loss/train': 1.1419930458068848} 08/31/2021 16:22:48 - INFO - __main__ - Step 149979: {'lr': 2.7260365936809805e-11, 'samples': 28795968, 'steps': 149978, 'loss/train': 0.46907761693000793} 08/31/2021 16:22:49 - INFO - __main__ - Step 149980: {'lr': 2.48384739720553e-11, 'samples': 28796160, 'steps': 149979, 'loss/train': 1.204314947128296} 08/31/2021 16:22:50 - INFO - __main__ - Step 149981: {'lr': 2.252922812195912e-11, 'samples': 28796352, 'steps': 149980, 'loss/train': 1.4262733459472656} 08/31/2021 16:22:50 - INFO - __main__ - Step 149982: {'lr': 2.0332628414276854e-11, 'samples': 28796544, 'steps': 149981, 'loss/train': 1.0337615013122559} 08/31/2021 16:22:50 - INFO - __main__ - Step 149983: {'lr': 1.824867482125292e-11, 'samples': 28796736, 'steps': 149982, 'loss/train': 1.0361618995666504} 08/31/2021 16:22:51 - INFO - __main__ - Step 149984: {'lr': 1.627736737064289e-11, 'samples': 28796928, 'steps': 149983, 'loss/train': 1.951728105545044} 08/31/2021 16:22:52 - INFO - __main__ - Step 149985: {'lr': 1.4418706062446774e-11, 'samples': 28797120, 'steps': 149984, 'loss/train': 0.7959681749343872} 08/31/2021 16:22:53 - INFO - __main__ - Step 149986: {'lr': 1.2672690896664563e-11, 'samples': 28797312, 'steps': 149985, 'loss/train': 0.8000803589820862} 08/31/2021 16:22:53 - INFO - __main__ - Step 149987: {'lr': 1.103932187329626e-11, 'samples': 28797504, 'steps': 149986, 'loss/train': 0.8754225969314575} 08/31/2021 16:22:53 - INFO - __main__ - Step 149988: {'lr': 9.518598964586289e-12, 'samples': 28797696, 'steps': 149987, 'loss/train': 0.5680332183837891} 08/31/2021 16:22:54 - INFO - __main__ - Step 149989: {'lr': 8.110522198290227e-12, 'samples': 28797888, 'steps': 149988, 'loss/train': 0.9977171421051025} 08/31/2021 16:22:55 - INFO - __main__ - Step 149990: {'lr': 6.815091574408072e-12, 'samples': 28798080, 'steps': 149989, 'loss/train': 1.020878553390503} 08/31/2021 16:22:56 - INFO - __main__ - Step 149991: {'lr': 5.632307092939826e-12, 'samples': 28798272, 'steps': 149990, 'loss/train': 1.133468508720398} 08/31/2021 16:22:56 - INFO - __main__ - Step 149992: {'lr': 4.562168753885487e-12, 'samples': 28798464, 'steps': 149991, 'loss/train': 1.1032930612564087} 08/31/2021 16:22:56 - INFO - __main__ - Step 149993: {'lr': 3.604676557245057e-12, 'samples': 28798656, 'steps': 149992, 'loss/train': 1.0751497745513916} 08/31/2021 16:22:57 - INFO - __main__ - Step 149994: {'lr': 2.759830475262959e-12, 'samples': 28798848, 'steps': 149993, 'loss/train': 1.144357681274414} 08/31/2021 16:22:58 - INFO - __main__ - Step 149995: {'lr': 2.0276305634503443e-12, 'samples': 28799040, 'steps': 149994, 'loss/train': 0.9176002740859985} 08/31/2021 16:22:59 - INFO - __main__ - Step 149996: {'lr': 1.4080767662960624e-12, 'samples': 28799232, 'steps': 149995, 'loss/train': 1.3836370706558228} 08/31/2021 16:22:59 - INFO - __main__ - Step 149997: {'lr': 9.011691393112642e-13, 'samples': 28799424, 'steps': 149996, 'loss/train': 1.2611217498779297} 08/31/2021 16:22:59 - INFO - __main__ - Step 149998: {'lr': 5.069076269847983e-13, 'samples': 28799616, 'steps': 149997, 'loss/train': 0.2949366867542267} 08/31/2021 16:23:00 - INFO - __main__ - Step 149999: {'lr': 2.2529228482781605e-13, 'samples': 28799808, 'steps': 149998, 'loss/train': 1.0830192565917969} 08/31/2021 16:23:02 - INFO - __main__ - Step 150000: {'lr': 5.63230573291662e-14, 'samples': 28800000, 'steps': 149999, 'loss/train': 0.5880433917045593} 08/31/2021 16:23:02 - INFO - __main__ - Evaluating model checkpoint 08/31/2021 16:31:47 - INFO - __main__ - Step 150000: {'loss/eval': 0.9517361521720886, 'perplexity': 2.590202808380127} 08/31/2021 16:31:47 - INFO - __main__ - Saving model checkpoint 08/31/2021 16:32:49 - INFO - __main__ - Evaluating and saving model after training 08/31/2021 16:41:31 - INFO - __main__ - Step 150000: {'loss/eval': 0.9517361521720886, 'perplexity': 2.590202808380127}